mach64: optimize wait_for_fifo

This is a simple optimization for fifo waiting that improves scrolling performance by 5%. If the queue has more free entries that what we consume, we can skip the costly register read next time. Signed-off-by: Mikulas Patocka <mpatocka@redhat.com> Reviewed-by: Ville Syrjälä <syrjala@sci.fi> Signed-off-by: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
author: Mikulas Patocka <mpatocka@redhat.com> 2018-10-08 12:57:35 +0200
committer: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com> 2018-10-08 12:57:35 +0200
commit: 01c40a17249727472da3f52e2f344cc2cc4138c4 (patch)
tree: 8ec4aa2139d8f3a2bda32432481f8fef0388da83 /tools/perf/scripts/python
parent: c09bcc91bb94ed91f1391bffcbe294963d605732 (diff)
0 files changed, 0 insertions, 0 deletions
diff --git a/CREDITS b/CREDITS
index 206d0fcf07a5..0640e1650483 100644
--- a/CREDITS
+++ b/CREDITS
@@ -637,14 +637,13 @@ S: 14509 NE 39th Street #1096
 S: Bellevue, Washington 98007
 S: USA
 
-N: Christopher L. Cheney
-E: ccheney@debian.org
-E: ccheney@cheney.cx
-W: http://www.cheney.cx
+N: Chris Cheney
+E: chris.cheney@gmail.com
+E: ccheney@redhat.com
 P: 1024D/8E384AF2 2D31 1927 87D7 1F24 9FF9  1BC5 D106 5AB3 8E38 4AF2
 D: Vista Imaging usb webcam driver
-S: 314 Prince of Wales
-S: Conroe, TX 77304
+S: 2308 Therrell Way
+S: McKinney, TX 75070
 S: USA
 
 N: Stuart Cheshire
@@ -1120,6 +1119,7 @@ D: author of userfs filesystem
 D: Improved mmap and munmap handling
 D: General mm minor tidyups
 D: autofs v4 maintainer
+D: Xen subsystem
 S: 987 Alabama St
 S: San Francisco
 S: CA, 94110
@@ -2808,8 +2808,7 @@ S: Ottawa, Ontario
 S: Canada K2P 0X8
 
 N: Mikael Pettersson
-E: mikpe@it.uu.se
-W: http://user.it.uu.se/~mikpe/linux/
+E: mikpelinux@gmail.com
 D: Miscellaneous fixes
 
 N: Reed H. Petty
diff --git a/Documentation/00-INDEX b/Documentation/00-INDEX
index 0c4cc688e89a..38f8444bdd0e 100644
--- a/Documentation/00-INDEX
+++ b/Documentation/00-INDEX
@@ -40,7 +40,7 @@ IPMI.txt
 IRQ-affinity.txt
 	- how to select which CPU(s) handle which interrupt events on SMP.
 IRQ-domain.txt
-	- info on inerrupt numbering and setting up IRQ domains.
+	- info on interrupt numbering and setting up IRQ domains.
 IRQ.txt
 	- description of what an IRQ is.
 Intel-IOMMU.txt
diff --git a/Documentation/ABI/stable/sysfs-bus-usb b/Documentation/ABI/stable/sysfs-bus-usb
new file mode 100644
index 000000000000..a6b685724740
--- /dev/null
+++ b/Documentation/ABI/stable/sysfs-bus-usb
@@ -0,0 +1,142 @@
+What:		/sys/bus/usb/devices/.../power/persist
+Date:		May 2007
+KernelVersion:	2.6.23
+Contact:	Alan Stern <stern@rowland.harvard.edu>
+Description:
+		If CONFIG_USB_PERSIST is set, then each USB device directory
+		will contain a file named power/persist.  The file holds a
+		boolean value (0 or 1) indicating whether or not the
+		"USB-Persist" facility is enabled for the device.  Since the
+		facility is inherently dangerous, it is disabled by default
+		for all devices except hubs.  For more information, see
+		Documentation/usb/persist.txt.
+
+What:		/sys/bus/usb/devices/.../power/autosuspend
+Date:		March 2007
+KernelVersion:	2.6.21
+Contact:	Alan Stern <stern@rowland.harvard.edu>
+Description:
+		Each USB device directory will contain a file named
+		power/autosuspend.  This file holds the time (in seconds)
+		the device must be idle before it will be autosuspended.
+		0 means the device will be autosuspended as soon as
+		possible.  Negative values will prevent the device from
+		being autosuspended at all, and writing a negative value
+		will resume the device if it is already suspended.
+
+		The autosuspend delay for newly-created devices is set to
+		the value of the usbcore.autosuspend module parameter.
+
+What:		/sys/bus/usb/device/.../power/connected_duration
+Date:		January 2008
+KernelVersion:	2.6.25
+Contact:	Sarah Sharp <sarah.a.sharp@intel.com>
+Description:
+		If CONFIG_PM_RUNTIME is enabled then this file
+		is present.  When read, it returns the total time (in msec)
+		that the USB device has been connected to the machine.  This
+		file is read-only.
+Users:
+		PowerTOP <powertop@lists.01.org>
+		https://01.org/powertop/
+
+What:		/sys/bus/usb/device/.../power/active_duration
+Date:		January 2008
+KernelVersion:	2.6.25
+Contact:	Sarah Sharp <sarah.a.sharp@intel.com>
+Description:
+		If CONFIG_PM_RUNTIME is enabled then this file
+		is present.  When read, it returns the total time (in msec)
+		that the USB device has been active, i.e. not in a suspended
+		state.  This file is read-only.
+
+		Tools can use this file and the connected_duration file to
+		compute the percentage of time that a device has been active.
+		For example,
+		echo $((100 * `cat active_duration` / `cat connected_duration`))
+		will give an integer percentage.  Note that this does not
+		account for counter wrap.
+Users:
+		PowerTOP <powertop@lists.01.org>
+		https://01.org/powertop/
+
+What:		/sys/bus/usb/devices/<busnum>-<port[.port]>...:<config num>-<interface num>/supports_autosuspend
+Date:		January 2008
+KernelVersion:	2.6.27
+Contact:	Sarah Sharp <sarah.a.sharp@intel.com>
+Description:
+		When read, this file returns 1 if the interface driver
+		for this interface supports autosuspend.  It also
+		returns 1 if no driver has claimed this interface, as an
+		unclaimed interface will not stop the device from being
+		autosuspended if all other interface drivers are idle.
+		The file returns 0 if autosuspend support has not been
+		added to the driver.
+Users:
+		USB PM tool
+		git://git.moblin.org/users/sarah/usb-pm-tool/
+
+What:		/sys/bus/usb/device/.../avoid_reset_quirk
+Date:		December 2009
+Contact:	Oliver Neukum <oliver@neukum.org>
+Description:
+		Writing 1 to this file tells the kernel that this
+		device will morph into another mode when it is reset.
+		Drivers will not use reset for error handling for
+		such devices.
+Users:
+		usb_modeswitch
+
+What:		/sys/bus/usb/devices/.../devnum
+KernelVersion:	since at least 2.6.18
+Description:
+		Device address on the USB bus.
+Users:
+		libusb
+
+What:		/sys/bus/usb/devices/.../bConfigurationValue
+KernelVersion:	since at least 2.6.18
+Description:
+		bConfigurationValue of the *active* configuration for the
+		device. Writing 0 or -1 to bConfigurationValue will reset the
+		active configuration (unconfigure the device). Writing
+		another value will change the active configuration.
+
+		Note that some devices, in violation of the USB spec, have a
+		configuration with a value equal to 0. Writing 0 to
+		bConfigurationValue for these devices will install that
+		configuration, rather then unconfigure the device.
+
+		Writing -1 will always unconfigure the device.
+Users:
+		libusb
+
+What:		/sys/bus/usb/devices/.../busnum
+KernelVersion:	2.6.22
+Description:
+		Bus-number of the USB-bus the device is connected to.
+Users:
+		libusb
+
+What:		/sys/bus/usb/devices/.../descriptors
+KernelVersion:	2.6.26
+Description:
+		Binary file containing cached descriptors of the device. The
+		binary data consists of the device descriptor followed by the
+		descriptors for each configuration of the device.
+		Note that the wTotalLength of the config descriptors can not
+		be trusted, as the device may have a smaller config descriptor
+		than it advertises. The bLength field of each (sub) descriptor
+		can be trusted, and can be used to seek forward one (sub)
+		descriptor at a time until the next config descriptor is found.
+		All descriptors read from this file are in bus-endian format
+Users:
+		libusb
+
+What:		/sys/bus/usb/devices/.../speed
+KernelVersion:	since at least 2.6.18
+Description:
+		Speed the device is connected with to the usb-host in
+		Mbit / second. IE one of 1.5 / 12 / 480 / 5000.
+Users:
+		libusb
diff --git a/Documentation/ABI/testing/sysfs-block-zram b/Documentation/ABI/testing/sysfs-block-zram
index ec93fe33baa6..3f0b9ae61d8c 100644
--- a/Documentation/ABI/testing/sysfs-block-zram
+++ b/Documentation/ABI/testing/sysfs-block-zram
@@ -5,20 +5,21 @@ Description:
 		The disksize file is read-write and specifies the disk size
 		which represents the limit on the *uncompressed* worth of data
 		that can be stored in this disk.
+		Unit: bytes
 
 What:		/sys/block/zram<id>/initstate
 Date:		August 2010
 Contact:	Nitin Gupta <ngupta@vflare.org>
 Description:
-		The disksize file is read-only and shows the initialization
+		The initstate file is read-only and shows the initialization
 		state of the device.
 
 What:		/sys/block/zram<id>/reset
 Date:		August 2010
 Contact:	Nitin Gupta <ngupta@vflare.org>
 Description:
-		The disksize file is write-only and allows resetting the
-		device. The reset operation frees all the memory assocaited
+		The reset file is write-only and allows resetting the
+		device. The reset operation frees all the memory associated
 		with this device.
 
 What:		/sys/block/zram<id>/num_reads
@@ -48,7 +49,7 @@ Contact:	Nitin Gupta <ngupta@vflare.org>
 Description:
 		The notify_free file is read-only and specifies the number of
 		swap slot free notifications received by this device. These
-		notifications are send to a swap block device when a swap slot
+		notifications are sent to a swap block device when a swap slot
 		is freed. This statistic is applicable only when this disk is
 		being used as a swap disk.
 
diff --git a/Documentation/ABI/testing/sysfs-bus-iio b/Documentation/ABI/testing/sysfs-bus-iio
index dda81ffae5cf..39c8de0e53d0 100644
--- a/Documentation/ABI/testing/sysfs-bus-iio
+++ b/Documentation/ABI/testing/sysfs-bus-iio
@@ -351,6 +351,7 @@ Description:
 		6kohm_to_gnd: connected to ground via a 6kOhm resistor,
 		20kohm_to_gnd: connected to ground via a 20kOhm resistor,
 		100kohm_to_gnd: connected to ground via an 100kOhm resistor,
+		500kohm_to_gnd: connected to ground via a 500kOhm resistor,
 		three_state: left floating.
 		For a list of available output power down options read
 		outX_powerdown_mode_available. If Y is not present the
@@ -792,3 +793,21 @@ Contact:	linux-iio@vger.kernel.org
 Description:
 		This attribute is used to read the amount of quadrature error
 		present in the device at a given time.
+
+What:		/sys/.../iio:deviceX/in_accelX_power_mode
+KernelVersion:	3.11
+Contact:	linux-iio@vger.kernel.org
+Description:
+		Specifies the chip power mode.
+		low_noise: reduce noise level from ADC,
+		low_power: enable low current consumption.
+		For a list of available output power modes read
+		in_accel_power_mode_available.
+
+What:		/sys/bus/iio/devices/iio:deviceX/store_eeprom
+KernelVersion:	3.4.0
+Contact:	linux-iio@vger.kernel.org
+Description:
+		Writing '1' stores the current device configuration into
+		on-chip EEPROM. After power-up or chip reset the device will
+		automatically load the saved configuration.
diff --git a/Documentation/ABI/testing/sysfs-bus-iio-frequency-ad9523 b/Documentation/ABI/testing/sysfs-bus-iio-frequency-ad9523
index 2ce9c3f68eee..a91aeabe7b24 100644
--- a/Documentation/ABI/testing/sysfs-bus-iio-frequency-ad9523
+++ b/Documentation/ABI/testing/sysfs-bus-iio-frequency-ad9523
@@ -18,14 +18,6 @@ Description:
 		Reading returns either '1' or '0'. '1' means that the
 		pllY is locked.
 
-What:		/sys/bus/iio/devices/iio:deviceX/store_eeprom
-KernelVersion:	3.4.0
-Contact:	linux-iio@vger.kernel.org
-Description:
-		Writing '1' stores the current device configuration into
-		on-chip EEPROM. After power-up or chip reset the device will
-		automatically load the saved configuration.
-
 What:		/sys/bus/iio/devices/iio:deviceX/sync_dividers
 KernelVersion:	3.4.0
 Contact:	linux-iio@vger.kernel.org
diff --git a/Documentation/ABI/testing/sysfs-bus-iio-frequency-adf4350 b/Documentation/ABI/testing/sysfs-bus-iio-frequency-adf4350
index d89aded01c5a..1254457a726e 100644
--- a/Documentation/ABI/testing/sysfs-bus-iio-frequency-adf4350
+++ b/Documentation/ABI/testing/sysfs-bus-iio-frequency-adf4350
@@ -18,4 +18,4 @@ Description:
 		adjust the reference frequency accordingly.
 		The value written has no effect until out_altvoltageY_frequency
 		is updated. Consider to use out_altvoltageY_powerdown to power
-		down the PLL and it's RFOut buffers during REFin changes.
+		down the PLL and its RFOut buffers during REFin changes.
diff --git a/Documentation/ABI/testing/sysfs-bus-usb b/Documentation/ABI/testing/sysfs-bus-usb
index 9759b8c91332..1430f584b266 100644
--- a/Documentation/ABI/testing/sysfs-bus-usb
+++ b/Documentation/ABI/testing/sysfs-bus-usb
@@ -1,81 +1,3 @@
-What:		/sys/bus/usb/devices/.../power/autosuspend
-Date:		March 2007
-KernelVersion:	2.6.21
-Contact:	Alan Stern <stern@rowland.harvard.edu>
-Description:
-		Each USB device directory will contain a file named
-		power/autosuspend.  This file holds the time (in seconds)
-		the device must be idle before it will be autosuspended.
-		0 means the device will be autosuspended as soon as
-		possible.  Negative values will prevent the device from
-		being autosuspended at all, and writing a negative value
-		will resume the device if it is already suspended.
-
-		The autosuspend delay for newly-created devices is set to
-		the value of the usbcore.autosuspend module parameter.
-
-What:		/sys/bus/usb/devices/.../power/persist
-Date:		May 2007
-KernelVersion:	2.6.23
-Contact:	Alan Stern <stern@rowland.harvard.edu>
-Description:
-		If CONFIG_USB_PERSIST is set, then each USB device directory
-		will contain a file named power/persist.  The file holds a
-		boolean value (0 or 1) indicating whether or not the
-		"USB-Persist" facility is enabled for the device.  Since the
-		facility is inherently dangerous, it is disabled by default
-		for all devices except hubs.  For more information, see
-		Documentation/usb/persist.txt.
-
-What:		/sys/bus/usb/device/.../power/connected_duration
-Date:		January 2008
-KernelVersion:	2.6.25
-Contact:	Sarah Sharp <sarah.a.sharp@intel.com>
-Description:
-		If CONFIG_PM_RUNTIME is enabled then this file
-		is present.  When read, it returns the total time (in msec)
-		that the USB device has been connected to the machine.  This
-		file is read-only.
-Users:
-		PowerTOP <power@bughost.org>
-		http://www.lesswatts.org/projects/powertop/
-
-What:		/sys/bus/usb/device/.../power/active_duration
-Date:		January 2008
-KernelVersion:	2.6.25
-Contact:	Sarah Sharp <sarah.a.sharp@intel.com>
-Description:
-		If CONFIG_PM_RUNTIME is enabled then this file
-		is present.  When read, it returns the total time (in msec)
-		that the USB device has been active, i.e. not in a suspended
-		state.  This file is read-only.
-
-		Tools can use this file and the connected_duration file to
-		compute the percentage of time that a device has been active.
-		For example,
-		echo $((100 * `cat active_duration` / `cat connected_duration`))
-		will give an integer percentage.  Note that this does not
-		account for counter wrap.
-Users:
-		PowerTOP <power@bughost.org>
-		http://www.lesswatts.org/projects/powertop/
-
-What:		/sys/bus/usb/device/<busnum>-<devnum>...:<config num>-<interface num>/supports_autosuspend
-Date:		January 2008
-KernelVersion:	2.6.27
-Contact:	Sarah Sharp <sarah.a.sharp@intel.com>
-Description:
-		When read, this file returns 1 if the interface driver
-		for this interface supports autosuspend.  It also
-		returns 1 if no driver has claimed this interface, as an
-		unclaimed interface will not stop the device from being
-		autosuspended if all other interface drivers are idle.
-		The file returns 0 if autosuspend support has not been
-		added to the driver.
-Users:
-		USB PM tool
-		git://git.moblin.org/users/sarah/usb-pm-tool/
-
 What:		/sys/bus/usb/device/.../authorized
 Date:		July 2008
 KernelVersion:	2.6.26
@@ -172,17 +94,6 @@ Description:
 		device IDs, exactly like reading from the entry
 		"/sys/bus/usb/drivers/.../new_id"
 
-What:		/sys/bus/usb/device/.../avoid_reset_quirk
-Date:		December 2009
-Contact:	Oliver Neukum <oliver@neukum.org>
-Description:
-		Writing 1 to this file tells the kernel that this
-		device will morph into another mode when it is reset.
-		Drivers will not use reset for error handling for
-		such devices.
-Users:
-		usb_modeswitch
-
 What:		/sys/bus/usb/devices/.../power/usb2_hardware_lpm
 Date:		September 2011
 Contact:	Andiry Xu <andiry.xu@amd.com>
diff --git a/Documentation/ABI/testing/sysfs-class-mtd b/Documentation/ABI/testing/sysfs-class-mtd
index 3105644b3bfc..bfd119ace6ad 100644
--- a/Documentation/ABI/testing/sysfs-class-mtd
+++ b/Documentation/ABI/testing/sysfs-class-mtd
@@ -128,9 +128,8 @@ KernelVersion:	3.4
 Contact:	linux-mtd@lists.infradead.org
 Description:
 		Maximum number of bit errors that the device is capable of
-		correcting within each region covering an ecc step.  This will
-		always be a non-negative integer.  Note that some devices will
-		have multiple ecc steps within each writesize region.
+		correcting within each region covering an ECC step (see
+		ecc_step_size).  This will always be a non-negative integer.
 
 		In the case of devices lacking any ECC capability, it is 0.
 
@@ -173,3 +172,15 @@ Description:
 		This is generally applicable only to NAND flash devices with ECC
 		capability.  It is ignored on devices lacking ECC capability;
 		i.e., devices for which ecc_strength is zero.
+
+What:		/sys/class/mtd/mtdX/ecc_step_size
+Date:		May 2013
+KernelVersion:	3.10
+Contact:	linux-mtd@lists.infradead.org
+Description:
+		The size of a single region covered by ECC, known as the ECC
+		step.  Devices may have several equally sized ECC steps within
+		each writesize region.
+
+		It will always be a non-negative integer.  In the case of
+		devices lacking any ECC capability, it is 0.
diff --git a/Documentation/ABI/testing/sysfs-devices-power b/Documentation/ABI/testing/sysfs-devices-power
index 9d43e7670841..efe449bdf811 100644
--- a/Documentation/ABI/testing/sysfs-devices-power
+++ b/Documentation/ABI/testing/sysfs-devices-power
@@ -1,6 +1,6 @@
 What:		/sys/devices/.../power/
 Date:		January 2009
-Contact:	Rafael J. Wysocki <rjw@sisk.pl>
+Contact:	Rafael J. Wysocki <rjw@rjwysocki.net>
 Description:
 		The /sys/devices/.../power directory contains attributes
 		allowing the user space to check and modify some power
@@ -8,7 +8,7 @@ Description:
 
 What:		/sys/devices/.../power/wakeup
 Date:		January 2009
-Contact:	Rafael J. Wysocki <rjw@sisk.pl>
+Contact:	Rafael J. Wysocki <rjw@rjwysocki.net>
 Description:
 		The /sys/devices/.../power/wakeup attribute allows the user
 		space to check if the device is enabled to wake up the system
@@ -34,7 +34,7 @@ Description:
 
 What:		/sys/devices/.../power/control
 Date:		January 2009
-Contact:	Rafael J. Wysocki <rjw@sisk.pl>
+Contact:	Rafael J. Wysocki <rjw@rjwysocki.net>
 Description:
 		The /sys/devices/.../power/control attribute allows the user
 		space to control the run-time power management of the device.
@@ -53,7 +53,7 @@ Description:
 
 What:		/sys/devices/.../power/async
 Date:		January 2009
-Contact:	Rafael J. Wysocki <rjw@sisk.pl>
+Contact:	Rafael J. Wysocki <rjw@rjwysocki.net>
 Description:
 		The /sys/devices/.../async attribute allows the user space to
 		enable or diasble the device's suspend and resume callbacks to
@@ -79,7 +79,7 @@ Description:
 
 What:		/sys/devices/.../power/wakeup_count
 Date:		September 2010
-Contact:	Rafael J. Wysocki <rjw@sisk.pl>
+Contact:	Rafael J. Wysocki <rjw@rjwysocki.net>
 Description:
 		The /sys/devices/.../wakeup_count attribute contains the number
 		of signaled wakeup events associated with the device.  This
@@ -88,7 +88,7 @@ Description:
 
 What:		/sys/devices/.../power/wakeup_active_count
 Date:		September 2010
-Contact:	Rafael J. Wysocki <rjw@sisk.pl>
+Contact:	Rafael J. Wysocki <rjw@rjwysocki.net>
 Description:
 		The /sys/devices/.../wakeup_active_count attribute contains the
 		number of times the processing of wakeup events associated with
@@ -98,7 +98,7 @@ Description:
 
 What:		/sys/devices/.../power/wakeup_abort_count
 Date:		February 2012
-Contact:	Rafael J. Wysocki <rjw@sisk.pl>
+Contact:	Rafael J. Wysocki <rjw@rjwysocki.net>
 Description:
 		The /sys/devices/.../wakeup_abort_count attribute contains the
 		number of times the processing of a wakeup event associated with
@@ -109,7 +109,7 @@ Description:
 
 What:		/sys/devices/.../power/wakeup_expire_count
 Date:		February 2012
-Contact:	Rafael J. Wysocki <rjw@sisk.pl>
+Contact:	Rafael J. Wysocki <rjw@rjwysocki.net>
 Description:
 		The /sys/devices/.../wakeup_expire_count attribute contains the
 		number of times a wakeup event associated with the device has
@@ -119,7 +119,7 @@ Description:
 
 What:		/sys/devices/.../power/wakeup_active
 Date:		September 2010
-Contact:	Rafael J. Wysocki <rjw@sisk.pl>
+Contact:	Rafael J. Wysocki <rjw@rjwysocki.net>
 Description:
 		The /sys/devices/.../wakeup_active attribute contains either 1,
 		or 0, depending on whether or not a wakeup event associated with
@@ -129,7 +129,7 @@ Description:
 
 What:		/sys/devices/.../power/wakeup_total_time_ms
 Date:		September 2010
-Contact:	Rafael J. Wysocki <rjw@sisk.pl>
+Contact:	Rafael J. Wysocki <rjw@rjwysocki.net>
 Description:
 		The /sys/devices/.../wakeup_total_time_ms attribute contains
 		the total time of processing wakeup events associated with the
@@ -139,7 +139,7 @@ Description:
 
 What:		/sys/devices/.../power/wakeup_max_time_ms
 Date:		September 2010
-Contact:	Rafael J. Wysocki <rjw@sisk.pl>
+Contact:	Rafael J. Wysocki <rjw@rjwysocki.net>
 Description:
 		The /sys/devices/.../wakeup_max_time_ms attribute contains
 		the maximum time of processing a single wakeup event associated
@@ -149,7 +149,7 @@ Description:
 
 What:		/sys/devices/.../power/wakeup_last_time_ms
 Date:		September 2010
-Contact:	Rafael J. Wysocki <rjw@sisk.pl>
+Contact:	Rafael J. Wysocki <rjw@rjwysocki.net>
 Description:
 		The /sys/devices/.../wakeup_last_time_ms attribute contains
 		the value of the monotonic clock corresponding to the time of
@@ -160,7 +160,7 @@ Description:
 
 What:		/sys/devices/.../power/wakeup_prevent_sleep_time_ms
 Date:		February 2012
-Contact:	Rafael J. Wysocki <rjw@sisk.pl>
+Contact:	Rafael J. Wysocki <rjw@rjwysocki.net>
 Description:
 		The /sys/devices/.../wakeup_prevent_sleep_time_ms attribute
 		contains the total time the device has been preventing
@@ -189,7 +189,7 @@ Description:
 
 What:		/sys/devices/.../power/pm_qos_latency_us
 Date:		March 2012
-Contact:	Rafael J. Wysocki <rjw@sisk.pl>
+Contact:	Rafael J. Wysocki <rjw@rjwysocki.net>
 Description:
 		The /sys/devices/.../power/pm_qos_resume_latency_us attribute
 		contains the PM QoS resume latency limit for the given device,
@@ -207,7 +207,7 @@ Description:
 
 What:		/sys/devices/.../power/pm_qos_no_power_off
 Date:		September 2012
-Contact:	Rafael J. Wysocki <rjw@sisk.pl>
+Contact:	Rafael J. Wysocki <rjw@rjwysocki.net>
 Description:
 		The /sys/devices/.../power/pm_qos_no_power_off attribute
 		is used for manipulating the PM QoS "no power off" flag.  If
@@ -222,7 +222,7 @@ Description:
 
 What:		/sys/devices/.../power/pm_qos_remote_wakeup
 Date:		September 2012
-Contact:	Rafael J. Wysocki <rjw@sisk.pl>
+Contact:	Rafael J. Wysocki <rjw@rjwysocki.net>
 Description:
 		The /sys/devices/.../power/pm_qos_remote_wakeup attribute
 		is used for manipulating the PM QoS "remote wakeup required"
diff --git a/Documentation/ABI/testing/sysfs-fs-f2fs b/Documentation/ABI/testing/sysfs-fs-f2fs
new file mode 100644
index 000000000000..31942efcaf0e
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-fs-f2fs
@@ -0,0 +1,26 @@
+What:		/sys/fs/f2fs/<disk>/gc_max_sleep_time
+Date:		July 2013
+Contact:	"Namjae Jeon" <namjae.jeon@samsung.com>
+Description:
+		 Controls the maximun sleep time for gc_thread. Time
+		 is in milliseconds.
+
+What:		/sys/fs/f2fs/<disk>/gc_min_sleep_time
+Date:		July 2013
+Contact:	"Namjae Jeon" <namjae.jeon@samsung.com>
+Description:
+		 Controls the minimum sleep time for gc_thread. Time
+		 is in milliseconds.
+
+What:		/sys/fs/f2fs/<disk>/gc_no_gc_sleep_time
+Date:		July 2013
+Contact:	"Namjae Jeon" <namjae.jeon@samsung.com>
+Description:
+		 Controls the default sleep time for gc_thread. Time
+		 is in milliseconds.
+
+What:		/sys/fs/f2fs/<disk>/gc_idle
+Date:		July 2013
+Contact:	"Namjae Jeon" <namjae.jeon@samsung.com>
+Description:
+		 Controls the victim selection policy for garbage collection.
diff --git a/Documentation/ABI/testing/sysfs-power b/Documentation/ABI/testing/sysfs-power
index 217772615d02..205a73878441 100644
--- a/Documentation/ABI/testing/sysfs-power
+++ b/Documentation/ABI/testing/sysfs-power
@@ -1,6 +1,6 @@
 What:		/sys/power/
 Date:		August 2006
-Contact:	Rafael J. Wysocki <rjw@sisk.pl>
+Contact:	Rafael J. Wysocki <rjw@rjwysocki.net>
 Description:
 		The /sys/power directory will contain files that will
 		provide a unified interface to the power management
@@ -8,7 +8,7 @@ Description:
 
 What:		/sys/power/state
 Date:		August 2006
-Contact:	Rafael J. Wysocki <rjw@sisk.pl>
+Contact:	Rafael J. Wysocki <rjw@rjwysocki.net>
 Description:
 		The /sys/power/state file controls the system power state.
 		Reading from this file returns what states are supported,
@@ -22,7 +22,7 @@ Description:
 
 What:		/sys/power/disk
 Date:		September 2006
-Contact:	Rafael J. Wysocki <rjw@sisk.pl>
+Contact:	Rafael J. Wysocki <rjw@rjwysocki.net>
 Description:
 		The /sys/power/disk file controls the operating mode of the
 		suspend-to-disk mechanism.  Reading from this file returns
@@ -67,7 +67,7 @@ Description:
 
 What:		/sys/power/image_size
 Date:		August 2006
-Contact:	Rafael J. Wysocki <rjw@sisk.pl>
+Contact:	Rafael J. Wysocki <rjw@rjwysocki.net>
 Description:
 		The /sys/power/image_size file controls the size of the image
 		created by the suspend-to-disk mechanism.  It can be written a
@@ -84,7 +84,7 @@ Description:
 
 What:		/sys/power/pm_trace
 Date:		August 2006
-Contact:	Rafael J. Wysocki <rjw@sisk.pl>
+Contact:	Rafael J. Wysocki <rjw@rjwysocki.net>
 Description:
 		The /sys/power/pm_trace file controls the code which saves the
 		last PM event point in the RTC across reboots, so that you can
@@ -133,7 +133,7 @@ Description:
 
 What:		/sys/power/pm_async
 Date:		January 2009
-Contact:	Rafael J. Wysocki <rjw@sisk.pl>
+Contact:	Rafael J. Wysocki <rjw@rjwysocki.net>
 Description:
 		The /sys/power/pm_async file controls the switch allowing the
 		user space to enable or disable asynchronous suspend and resume
@@ -146,7 +146,7 @@ Description:
 
 What:		/sys/power/wakeup_count
 Date:		July 2010
-Contact:	Rafael J. Wysocki <rjw@sisk.pl>
+Contact:	Rafael J. Wysocki <rjw@rjwysocki.net>
 Description:
 		The /sys/power/wakeup_count file allows user space to put the
 		system into a sleep state while taking into account the
@@ -161,7 +161,7 @@ Description:
 
 What:		/sys/power/reserved_size
 Date:		May 2011
-Contact:	Rafael J. Wysocki <rjw@sisk.pl>
+Contact:	Rafael J. Wysocki <rjw@rjwysocki.net>
 Description:
 		The /sys/power/reserved_size file allows user space to control
 		the amount of memory reserved for allocations made by device
@@ -175,7 +175,7 @@ Description:
 
 What:		/sys/power/autosleep
 Date:		April 2012
-Contact:	Rafael J. Wysocki <rjw@sisk.pl>
+Contact:	Rafael J. Wysocki <rjw@rjwysocki.net>
 Description:
 		The /sys/power/autosleep file can be written one of the strings
 		returned by reads from /sys/power/state.  If that happens, a
@@ -192,7 +192,7 @@ Description:
 
 What:		/sys/power/wake_lock
 Date:		February 2012
-Contact:	Rafael J. Wysocki <rjw@sisk.pl>
+Contact:	Rafael J. Wysocki <rjw@rjwysocki.net>
 Description:
 		The /sys/power/wake_lock file allows user space to create
 		wakeup source objects and activate them on demand (if one of
@@ -219,7 +219,7 @@ Description:
 
 What:		/sys/power/wake_unlock
 Date:		February 2012
-Contact:	Rafael J. Wysocki <rjw@sisk.pl>
+Contact:	Rafael J. Wysocki <rjw@rjwysocki.net>
 Description:
 		The /sys/power/wake_unlock file allows user space to deactivate
 		wakeup sources created with the help of /sys/power/wake_lock.
diff --git a/Documentation/DocBook/80211.tmpl b/Documentation/DocBook/80211.tmpl
index 49267ea97568..f403ec3c5c9a 100644
--- a/Documentation/DocBook/80211.tmpl
+++ b/Documentation/DocBook/80211.tmpl
@@ -325,6 +325,7 @@
           <title>functions/definitions</title>
 !Finclude/net/mac80211.h ieee80211_rx_status
 !Finclude/net/mac80211.h mac80211_rx_flags
+!Finclude/net/mac80211.h mac80211_tx_info_flags
 !Finclude/net/mac80211.h mac80211_tx_control_flags
 !Finclude/net/mac80211.h mac80211_rate_control_flags
 !Finclude/net/mac80211.h ieee80211_tx_rate
diff --git a/Documentation/DocBook/drm.tmpl b/Documentation/DocBook/drm.tmpl
index 7d1278e7a434..ed1d6d289022 100644
--- a/Documentation/DocBook/drm.tmpl
+++ b/Documentation/DocBook/drm.tmpl
@@ -156,13 +156,6 @@
             </para></listitem>
           </varlistentry>
           <varlistentry>
-            <term>DRIVER_USE_MTRR</term>
-            <listitem><para>
-              Driver uses MTRR interface for mapping memory, the DRM core will
-              manage MTRR resources. Deprecated.
-            </para></listitem>
-          </varlistentry>
-          <varlistentry>
             <term>DRIVER_PCI_DMA</term>
             <listitem><para>
               Driver is capable of PCI DMA, mapping of PCI DMA buffers to
@@ -195,28 +188,6 @@
             </para></listitem>
           </varlistentry>
           <varlistentry>
-            <term>DRIVER_IRQ_VBL</term>
-            <listitem><para>Unused. Deprecated.</para></listitem>
-          </varlistentry>
-          <varlistentry>
-            <term>DRIVER_DMA_QUEUE</term>
-            <listitem><para>
-              Should be set if the driver queues DMA requests and completes them
-              asynchronously.  Deprecated.
-            </para></listitem>
-          </varlistentry>
-          <varlistentry>
-            <term>DRIVER_FB_DMA</term>
-            <listitem><para>
-              Driver supports DMA to/from the framebuffer, mapping of frambuffer
-              DMA buffers to userspace will be supported. Deprecated.
-            </para></listitem>
-          </varlistentry>
-          <varlistentry>
-            <term>DRIVER_IRQ_VBL2</term>
-            <listitem><para>Unused. Deprecated.</para></listitem>
-          </varlistentry>
-          <varlistentry>
             <term>DRIVER_GEM</term>
             <listitem><para>
               Driver use the GEM memory manager.
@@ -234,6 +205,12 @@
               Driver implements DRM PRIME buffer sharing.
             </para></listitem>
           </varlistentry>
+          <varlistentry>
+            <term>DRIVER_RENDER</term>
+            <listitem><para>
+              Driver supports dedicated render nodes.
+            </para></listitem>
+          </varlistentry>
         </variablelist>
       </sect3>
       <sect3>
@@ -2212,6 +2189,18 @@ void intel_crt_init(struct drm_device *dev)
 !Iinclude/drm/drm_rect.h
 !Edrivers/gpu/drm/drm_rect.c
     </sect2>
+    <sect2>
+      <title>Flip-work Helper Reference</title>
+!Pinclude/drm/drm_flip_work.h flip utils
+!Iinclude/drm/drm_flip_work.h
+!Edrivers/gpu/drm/drm_flip_work.c
+    </sect2>
+    <sect2>
+      <title>VMA Offset Manager</title>
+!Pdrivers/gpu/drm/drm_vma_manager.c vma offset manager
+!Edrivers/gpu/drm/drm_vma_manager.c
+!Iinclude/drm/drm_vma_manager.h
+    </sect2>
   </sect1>
 
   <!-- Internals: kms properties -->
@@ -2422,18 +2411,18 @@ void (*postclose) (struct drm_device *, struct drm_file *);</synopsis>
       </abstract>
       <para>
         The <methodname>firstopen</methodname> method is called by the DRM core
-	when an application opens a device that has no other opened file handle.
-	Similarly the <methodname>lastclose</methodname> method is called when
-	the last application holding a file handle opened on the device closes
-	it. Both methods are mostly used for UMS (User Mode Setting) drivers to
-	acquire and release device resources which should be done in the
-	<methodname>load</methodname> and <methodname>unload</methodname>
-	methods for KMS drivers.
+	for legacy UMS (User Mode Setting) drivers only when an application
+	opens a device that has no other opened file handle. UMS drivers can
+	implement it to acquire device resources. KMS drivers can't use the
+	method and must acquire resources in the <methodname>load</methodname>
+	method instead.
       </para>
       <para>
-        Note that the <methodname>lastclose</methodname> method is also called
-	at module unload time or, for hot-pluggable devices, when the device is
-	unplugged. The <methodname>firstopen</methodname> and
+	Similarly the <methodname>lastclose</methodname> method is called when
+	the last application holding a file handle opened on the device closes
+	it, for both UMS and KMS drivers. Additionally, the method is also
+	called at module unload time or, for hot-pluggable devices, when the
+	device is unplugged. The <methodname>firstopen</methodname> and
 	<methodname>lastclose</methodname> calls can thus be unbalanced.
       </para>
       <para>
@@ -2462,7 +2451,12 @@ void (*postclose) (struct drm_device *, struct drm_file *);</synopsis>
       <para>
         The <methodname>lastclose</methodname> method should restore CRTC and
 	plane properties to default value, so that a subsequent open of the
-	device will not inherit state from the previous user.
+	device will not inherit state from the previous user. It can also be
+	used to execute delayed power switching state changes, e.g. in
+	conjunction with the vga-switcheroo infrastructure. Beyond that KMS
+	drivers should not do any further cleanup. Only legacy UMS drivers might
+	need to clean up device state so that the vga console or an independent
+	fbdev driver could take over.
       </para>
     </sect2>
     <sect2>
@@ -2498,7 +2492,6 @@ void (*postclose) (struct drm_device *, struct drm_file *);</synopsis>
 	<programlisting>
 	.poll = drm_poll,
 	.read = drm_read,
-	.fasync = drm_fasync,
 	.llseek = no_llseek,
 	</programlisting>
       </para>
@@ -2657,6 +2650,69 @@ int (*resume) (struct drm_device *);</synopsis>
       info, since man pages should cover the rest.
     </para>
 
+  <!-- External: render nodes -->
+
+    <sect1>
+      <title>Render nodes</title>
+      <para>
+        DRM core provides multiple character-devices for user-space to use.
+        Depending on which device is opened, user-space can perform a different
+        set of operations (mainly ioctls). The primary node is always created
+        and called <term>card&lt;num&gt;</term>. Additionally, a currently
+        unused control node, called <term>controlD&lt;num&gt;</term> is also
+        created. The primary node provides all legacy operations and
+        historically was the only interface used by userspace. With KMS, the
+        control node was introduced. However, the planned KMS control interface
+        has never been written and so the control node stays unused to date.
+      </para>
+      <para>
+        With the increased use of offscreen renderers and GPGPU applications,
+        clients no longer require running compositors or graphics servers to
+        make use of a GPU. But the DRM API required unprivileged clients to
+        authenticate to a DRM-Master prior to getting GPU access. To avoid this
+        step and to grant clients GPU access without authenticating, render
+        nodes were introduced. Render nodes solely serve render clients, that
+        is, no modesetting or privileged ioctls can be issued on render nodes.
+        Only non-global rendering commands are allowed. If a driver supports
+        render nodes, it must advertise it via the <term>DRIVER_RENDER</term>
+        DRM driver capability. If not supported, the primary node must be used
+        for render clients together with the legacy drmAuth authentication
+        procedure.
+      </para>
+      <para>
+        If a driver advertises render node support, DRM core will create a
+        separate render node called <term>renderD&lt;num&gt;</term>. There will
+        be one render node per device. No ioctls except  PRIME-related ioctls
+        will be allowed on this node. Especially <term>GEM_OPEN</term> will be
+        explicitly prohibited. Render nodes are designed to avoid the
+        buffer-leaks, which occur if clients guess the flink names or mmap
+        offsets on the legacy interface. Additionally to this basic interface,
+        drivers must mark their driver-dependent render-only ioctls as
+        <term>DRM_RENDER_ALLOW</term> so render clients can use them. Driver
+        authors must be careful not to allow any privileged ioctls on render
+        nodes.
+      </para>
+      <para>
+        With render nodes, user-space can now control access to the render node
+        via basic file-system access-modes. A running graphics server which
+        authenticates clients on the privileged primary/legacy node is no longer
+        required. Instead, a client can open the render node and is immediately
+        granted GPU access. Communication between clients (or servers) is done
+        via PRIME. FLINK from render node to legacy node is not supported. New
+        clients must not use the insecure FLINK interface.
+      </para>
+      <para>
+        Besides dropping all modeset/global ioctls, render nodes also drop the
+        DRM-Master concept. There is no reason to associate render clients with
+        a DRM-Master as they are independent of any graphics server. Besides,
+        they must work without any running master, anyway.
+        Drivers must be able to run without a master object if they support
+        render nodes. If, on the other hand, a driver requires shared state
+        between clients which is visible to user-space and accessible beyond
+        open-file boundaries, they cannot support render nodes.
+      </para>
+    </sect1>
+
   <!-- External: vblank handling -->
 
     <sect1>
diff --git a/Documentation/DocBook/media/v4l/controls.xml b/Documentation/DocBook/media/v4l/controls.xml
index c2fc9ec1417e..7a3b49b3cc3b 100644
--- a/Documentation/DocBook/media/v4l/controls.xml
+++ b/Documentation/DocBook/media/v4l/controls.xml
@@ -722,17 +722,22 @@ for more details.</para>
     </section>
 
     <section id="mpeg-controls">
-      <title>MPEG Control Reference</title>
+      <title>Codec Control Reference</title>
 
-      <para>Below all controls within the MPEG control class are
+      <para>Below all controls within the Codec control class are
 described. First the generic controls, then controls specific for
 certain hardware.</para>
 
+      <para>Note: These controls are applicable to all codecs and
+not just MPEG. The defines are prefixed with V4L2_CID_MPEG/V4L2_MPEG
+as the controls were originally made for MPEG codecs and later
+extended to cover all encoding formats.</para>
+
       <section>
-	<title>Generic MPEG Controls</title>
+	<title>Generic Codec Controls</title>
 
 	<table pgwide="1" frame="none" id="mpeg-control-id">
-	  <title>MPEG Control IDs</title>
+	  <title>Codec Control IDs</title>
 	  <tgroup cols="4">
 	    <colspec colname="c1" colwidth="1*" />
 	    <colspec colname="c2" colwidth="6*" />
@@ -752,7 +757,7 @@ certain hardware.</para>
 	      <row>
 		<entry spanname="id"><constant>V4L2_CID_MPEG_CLASS</constant>&nbsp;</entry>
 		<entry>class</entry>
-	      </row><row><entry spanname="descr">The MPEG class
+	      </row><row><entry spanname="descr">The Codec class
 descriptor. Calling &VIDIOC-QUERYCTRL; for this control will return a
 description of this control class. This description can be used as the
 caption of a Tab page in a GUI, for example.</entry>
@@ -3009,6 +3014,159 @@ in by the application. 0 = do not insert, 1 = insert packets.</entry>
 	  </tgroup>
 	</table>
       </section>
+
+    <section>
+      <title>VPX Control Reference</title>
+
+      <para>The VPX controls include controls for encoding parameters
+      of VPx video codec.</para>
+
+      <table pgwide="1" frame="none" id="vpx-control-id">
+      <title>VPX Control IDs</title>
+
+      <tgroup cols="4">
+        <colspec colname="c1" colwidth="1*" />
+        <colspec colname="c2" colwidth="6*" />
+        <colspec colname="c3" colwidth="2*" />
+        <colspec colname="c4" colwidth="6*" />
+        <spanspec namest="c1" nameend="c2" spanname="id" />
+        <spanspec namest="c2" nameend="c4" spanname="descr" />
+        <thead>
+          <row>
+            <entry spanname="id" align="left">ID</entry>
+            <entry align="left">Type</entry>
+          </row><row rowsep="1"><entry spanname="descr" align="left">Description</entry>
+          </row>
+        </thead>
+        <tbody valign="top">
+          <row><entry></entry></row>
+
+	      <row><entry></entry></row>
+	      <row id="v4l2-vpx-num-partitions">
+		<entry spanname="id"><constant>V4L2_CID_MPEG_VIDEO_VPX_NUM_PARTITIONS</constant></entry>
+		<entry>enum v4l2_vp8_num_partitions</entry>
+	      </row>
+	      <row><entry spanname="descr">The number of token partitions to use in VP8 encoder.
+Possible values are:</entry>
+	      </row>
+	      <row>
+		<entrytbl spanname="descr" cols="2">
+		  <tbody valign="top">
+		    <row>
+		      <entry><constant>V4L2_CID_MPEG_VIDEO_VPX_1_PARTITION</constant></entry>
+		      <entry>1 coefficient partition</entry>
+		    </row>
+		    <row>
+		      <entry><constant>V4L2_CID_MPEG_VIDEO_VPX_2_PARTITIONS</constant></entry>
+		      <entry>2 coefficient partitions</entry>
+		    </row>
+		    <row>
+		      <entry><constant>V4L2_CID_MPEG_VIDEO_VPX_4_PARTITIONS</constant></entry>
+		      <entry>4 coefficient partitions</entry>
+		    </row>
+		    <row>
+		      <entry><constant>V4L2_CID_MPEG_VIDEO_VPX_8_PARTITIONS</constant></entry>
+		      <entry>8 coefficient partitions</entry>
+	            </row>
+                  </tbody>
+		</entrytbl>
+	      </row>
+
+	      <row><entry></entry></row>
+	      <row>
+		<entry spanname="id"><constant>V4L2_CID_MPEG_VIDEO_VPX_IMD_DISABLE_4X4</constant></entry>
+		<entry>boolean</entry>
+	      </row>
+	      <row><entry spanname="descr">Setting this prevents intra 4x4 mode in the intra mode decision.</entry>
+	      </row>
+
+	      <row><entry></entry></row>
+	      <row id="v4l2-vpx-num-ref-frames">
+		<entry spanname="id"><constant>V4L2_CID_MPEG_VIDEO_VPX_NUM_REF_FRAMES</constant></entry>
+		<entry>enum v4l2_vp8_num_ref_frames</entry>
+	      </row>
+	      <row><entry spanname="descr">The number of reference pictures for encoding P frames.
+Possible values are:</entry>
+	      </row>
+	      <row>
+		<entrytbl spanname="descr" cols="2">
+		  <tbody valign="top">
+		    <row>
+		      <entry><constant>V4L2_CID_MPEG_VIDEO_VPX_1_REF_FRAME</constant></entry>
+		      <entry>Last encoded frame will be searched</entry>
+		    </row>
+		    <row>
+		      <entry><constant>V4L2_CID_MPEG_VIDEO_VPX_2_REF_FRAME</constant></entry>
+		      <entry>Two frames will be searched among the last encoded frame, the golden frame
+and the alternate reference (altref) frame. The encoder implementation will decide which two are chosen.</entry>
+		    </row>
+		    <row>
+		      <entry><constant>V4L2_CID_MPEG_VIDEO_VPX_3_REF_FRAME</constant></entry>
+		      <entry>The last encoded frame, the golden frame and the altref frame will be searched.</entry>
+		    </row>
+                  </tbody>
+		</entrytbl>
+	      </row>
+
+	      <row><entry></entry></row>
+	      <row>
+		<entry spanname="id"><constant>V4L2_CID_MPEG_VIDEO_VPX_FILTER_LEVEL</constant></entry>
+		<entry>integer</entry>
+	      </row>
+	      <row><entry spanname="descr">Indicates the loop filter level. The adjustment of the loop
+filter level is done via a delta value against a baseline loop filter value.</entry>
+	      </row>
+
+	      <row><entry></entry></row>
+	      <row>
+		<entry spanname="id"><constant>V4L2_CID_MPEG_VIDEO_VPX_FILTER_SHARPNESS</constant></entry>
+		<entry>integer</entry>
+	      </row>
+	      <row><entry spanname="descr">This parameter affects the loop filter. Anything above
+zero weakens the deblocking effect on the loop filter.</entry>
+	      </row>
+
+	      <row><entry></entry></row>
+	      <row>
+		<entry spanname="id"><constant>V4L2_CID_MPEG_VIDEO_VPX_GOLDEN_FRAME_REF_PERIOD</constant></entry>
+		<entry>integer</entry>
+	      </row>
+	      <row><entry spanname="descr">Sets the refresh period for the golden frame. The period is defined
+in number of frames. For a value of 'n', every nth frame starting from the first key frame will be taken as a golden frame.
+For eg. for encoding sequence of 0, 1, 2, 3, 4, 5, 6, 7 where the golden frame refresh period is set as 4, the frames
+0, 4, 8 etc will be taken as the golden frames as frame 0 is always a key frame.</entry>
+	      </row>
+
+	      <row><entry></entry></row>
+	      <row id="v4l2-vpx-golden-frame-sel">
+		<entry spanname="id"><constant>V4L2_CID_MPEG_VIDEO_VPX_GOLDEN_FRAME_SEL</constant></entry>
+		<entry>enum v4l2_vp8_golden_frame_sel</entry>
+	      </row>
+	      <row><entry spanname="descr">Selects the golden frame for encoding.
+Possible values are:</entry>
+	      </row>
+	      <row>
+		<entrytbl spanname="descr" cols="2">
+		  <tbody valign="top">
+		    <row>
+		      <entry><constant>V4L2_CID_MPEG_VIDEO_VPX_GOLDEN_FRAME_USE_PREV</constant></entry>
+		      <entry>Use the (n-2)th frame as a golden frame, current frame index being 'n'.</entry>
+		    </row>
+		    <row>
+		      <entry><constant>V4L2_CID_MPEG_VIDEO_VPX_GOLDEN_FRAME_USE_REF_PERIOD</constant></entry>
+		      <entry>Use the previous specific frame indicated by
+V4L2_CID_MPEG_VIDEO_VPX_GOLDEN_FRAME_REF_PERIOD as a golden frame.</entry>
+		    </row>
+                  </tbody>
+		</entrytbl>
+	      </row>
+
+          <row><entry></entry></row>
+        </tbody>
+      </tgroup>
+      </table>
+
+      </section>
     </section>
 
     <section id="camera-controls">
diff --git a/Documentation/DocBook/media/v4l/lirc_device_interface.xml b/Documentation/DocBook/media/v4l/lirc_device_interface.xml
index 8d7eb6bf6312..34cada2ca710 100644
--- a/Documentation/DocBook/media/v4l/lirc_device_interface.xml
+++ b/Documentation/DocBook/media/v4l/lirc_device_interface.xml
@@ -46,7 +46,9 @@ describing an IR signal are read from the chardev.</para>
 values. Pulses and spaces are only marked implicitly by their position. The
 data must start and end with a pulse, therefore, the data must always include
 an uneven number of samples. The write function must block until the data has
-been transmitted by the hardware.</para>
+been transmitted by the hardware. If more data is provided than the hardware
+can send, the driver returns EINVAL.</para>
+
 </section>
 
 <section id="lirc_ioctl">
diff --git a/Documentation/DocBook/media/v4l/pixfmt-nv16m.xml b/Documentation/DocBook/media/v4l/pixfmt-nv16m.xml
new file mode 100644
index 000000000000..c51d5a4cda09
--- /dev/null
+++ b/Documentation/DocBook/media/v4l/pixfmt-nv16m.xml
@@ -0,0 +1,171 @@
+    <refentry>
+      <refmeta>
+	<refentrytitle>V4L2_PIX_FMT_NV16M ('NM16'), V4L2_PIX_FMT_NV61M ('NM61')</refentrytitle>
+	&manvol;
+      </refmeta>
+      <refnamediv>
+	<refname id="V4L2-PIX-FMT-NV16M"><constant>V4L2_PIX_FMT_NV16M</constant></refname>
+	<refname id="V4L2-PIX-FMT-NV61M"><constant>V4L2_PIX_FMT_NV61M</constant></refname>
+	<refpurpose>Variation of <constant>V4L2_PIX_FMT_NV16</constant> and <constant>V4L2_PIX_FMT_NV61</constant> with planes
+	  non contiguous in memory. </refpurpose>
+      </refnamediv>
+      <refsect1>
+	<title>Description</title>
+
+	<para>This is a multi-planar, two-plane version of the YUV 4:2:0 format.
+The three components are separated into two sub-images or planes.
+<constant>V4L2_PIX_FMT_NV16M</constant> differs from <constant>V4L2_PIX_FMT_NV16
+</constant> in that the two planes are non-contiguous in memory, i.e. the chroma
+plane does not necessarily immediately follows the luma plane.
+The luminance data occupies the first plane. The Y plane has one byte per pixel.
+In the second plane there is chrominance data with alternating chroma samples.
+The CbCr plane is the same width and height, in bytes, as the Y plane.
+Each CbCr pair belongs to four pixels. For example,
+Cb<subscript>0</subscript>/Cr<subscript>0</subscript> belongs to
+Y'<subscript>00</subscript>, Y'<subscript>01</subscript>,
+Y'<subscript>10</subscript>, Y'<subscript>11</subscript>.
+<constant>V4L2_PIX_FMT_NV61M</constant> is the same as <constant>V4L2_PIX_FMT_NV16M</constant>
+except the Cb and Cr bytes are swapped, the CrCb plane starts with a Cr byte.</para>
+
+	<para><constant>V4L2_PIX_FMT_NV16M</constant> and
+<constant>V4L2_PIX_FMT_NV61M</constant> are intended to be used only in drivers
+and applications that support the multi-planar API, described in
+<xref linkend="planar-apis"/>. </para>
+
+	<example>
+	  <title><constant>V4L2_PIX_FMT_NV16M</constant> 4 &times; 4 pixel image</title>
+
+	  <formalpara>
+	    <title>Byte Order.</title>
+	    <para>Each cell is one byte.
+		<informaltable frame="none">
+		<tgroup cols="5" align="center">
+		  <colspec align="left" colwidth="2*" />
+		  <tbody valign="top">
+		    <row>
+		      <entry>start0&nbsp;+&nbsp;0:</entry>
+		      <entry>Y'<subscript>00</subscript></entry>
+		      <entry>Y'<subscript>01</subscript></entry>
+		      <entry>Y'<subscript>02</subscript></entry>
+		      <entry>Y'<subscript>03</subscript></entry>
+		    </row>
+		    <row>
+		      <entry>start0&nbsp;+&nbsp;4:</entry>
+		      <entry>Y'<subscript>10</subscript></entry>
+		      <entry>Y'<subscript>11</subscript></entry>
+		      <entry>Y'<subscript>12</subscript></entry>
+		      <entry>Y'<subscript>13</subscript></entry>
+		    </row>
+		    <row>
+		      <entry>start0&nbsp;+&nbsp;8:</entry>
+		      <entry>Y'<subscript>20</subscript></entry>
+		      <entry>Y'<subscript>21</subscript></entry>
+		      <entry>Y'<subscript>22</subscript></entry>
+		      <entry>Y'<subscript>23</subscript></entry>
+		    </row>
+		    <row>
+		      <entry>start0&nbsp;+&nbsp;12:</entry>
+		      <entry>Y'<subscript>30</subscript></entry>
+		      <entry>Y'<subscript>31</subscript></entry>
+		      <entry>Y'<subscript>32</subscript></entry>
+		      <entry>Y'<subscript>33</subscript></entry>
+		    </row>
+		    <row>
+		      <entry></entry>
+		    </row>
+		    <row>
+		      <entry>start1&nbsp;+&nbsp;0:</entry>
+		      <entry>Cb<subscript>00</subscript></entry>
+		      <entry>Cr<subscript>00</subscript></entry>
+		      <entry>Cb<subscript>02</subscript></entry>
+		      <entry>Cr<subscript>02</subscript></entry>
+		    </row>
+		    <row>
+		      <entry>start1&nbsp;+&nbsp;4:</entry>
+		      <entry>Cb<subscript>10</subscript></entry>
+		      <entry>Cr<subscript>10</subscript></entry>
+		      <entry>Cb<subscript>12</subscript></entry>
+		      <entry>Cr<subscript>12</subscript></entry>
+		    </row>
+		    <row>
+		      <entry>start1&nbsp;+&nbsp;8:</entry>
+		      <entry>Cb<subscript>20</subscript></entry>
+		      <entry>Cr<subscript>20</subscript></entry>
+		      <entry>Cb<subscript>22</subscript></entry>
+		      <entry>Cr<subscript>22</subscript></entry>
+		    </row>
+		    <row>
+		      <entry>start1&nbsp;+&nbsp;12:</entry>
+		      <entry>Cb<subscript>30</subscript></entry>
+		      <entry>Cr<subscript>30</subscript></entry>
+		      <entry>Cb<subscript>32</subscript></entry>
+		      <entry>Cr<subscript>32</subscript></entry>
+		    </row>
+		  </tbody>
+		</tgroup>
+		</informaltable>
+	      </para>
+	  </formalpara>
+
+	  <formalpara>
+	    <title>Color Sample Location.</title>
+	    <para>
+		<informaltable frame="none">
+		<tgroup cols="7" align="center">
+		  <tbody valign="top">
+		    <row>
+		      <entry></entry>
+		      <entry>0</entry><entry></entry><entry>1</entry><entry></entry>
+		      <entry>2</entry><entry></entry><entry>3</entry>
+		    </row>
+		    <row>
+		      <entry>0</entry>
+		      <entry>Y</entry><entry></entry><entry>Y</entry><entry></entry>
+		      <entry>Y</entry><entry></entry><entry>Y</entry>
+		    </row>
+		    <row>
+		      <entry></entry>
+		      <entry></entry><entry>C</entry><entry></entry><entry></entry>
+		      <entry></entry><entry>C</entry><entry></entry>
+		    </row>
+		    <row>
+		      <entry>1</entry>
+		      <entry>Y</entry><entry></entry><entry>Y</entry><entry></entry>
+		      <entry>Y</entry><entry></entry><entry>Y</entry>
+		    </row>
+		    <row>
+		      <entry></entry>
+		      <entry></entry><entry>C</entry><entry></entry><entry></entry>
+		      <entry></entry><entry>C</entry><entry></entry>
+		    </row>
+		    <row>
+		      <entry></entry>
+		    </row>
+		    <row>
+		      <entry>2</entry>
+		      <entry>Y</entry><entry></entry><entry>Y</entry><entry></entry>
+		      <entry>Y</entry><entry></entry><entry>Y</entry>
+		    </row>
+		    <row>
+		      <entry></entry>
+		      <entry></entry><entry>C</entry><entry></entry><entry></entry>
+		      <entry></entry><entry>C</entry><entry></entry>
+		    </row>
+		    <row>
+		      <entry>3</entry>
+		      <entry>Y</entry><entry></entry><entry>Y</entry><entry></entry>
+		      <entry>Y</entry><entry></entry><entry>Y</entry>
+		    </row>
+		    <row>
+		      <entry></entry>
+		      <entry></entry><entry>C</entry><entry></entry><entry></entry>
+		      <entry></entry><entry>C</entry><entry></entry>
+		    </row>
+		  </tbody>
+		</tgroup>
+		</informaltable>
+	      </para>
+	  </formalpara>
+	</example>
+      </refsect1>
+    </refentry>
diff --git a/Documentation/DocBook/media/v4l/pixfmt.xml b/Documentation/DocBook/media/v4l/pixfmt.xml
index 99b8d2ad6e4f..72d72bd67d0a 100644
--- a/Documentation/DocBook/media/v4l/pixfmt.xml
+++ b/Documentation/DocBook/media/v4l/pixfmt.xml
@@ -391,9 +391,9 @@ clamp (double x)
 	else               return r;
 }
 
-y1 = (255 / 219.0) * (Y1 - 16);
-pb = (255 / 224.0) * (Cb - 128);
-pr = (255 / 224.0) * (Cr - 128);
+y1 = (Y1 - 16) / 219.0;
+pb = (Cb - 128) / 224.0;
+pr = (Cr - 128) / 224.0;
 
 r = 1.0 * y1 + 0     * pb + 1.402 * pr;
 g = 1.0 * y1 - 0.344 * pb - 0.714 * pr;
@@ -718,6 +718,7 @@ information.</para>
     &sub-nv12m;
     &sub-nv12mt;
     &sub-nv16;
+    &sub-nv16m;
     &sub-nv24;
     &sub-m420;
   </section>
diff --git a/Documentation/DocBook/media/v4l/subdev-formats.xml b/Documentation/DocBook/media/v4l/subdev-formats.xml
index adc61982df7b..f72c1cc93a9b 100644
--- a/Documentation/DocBook/media/v4l/subdev-formats.xml
+++ b/Documentation/DocBook/media/v4l/subdev-formats.xml
@@ -97,31 +97,39 @@
 	  <colspec colname="id" align="left" />
 	  <colspec colname="code" align="center"/>
 	  <colspec colname="bit" />
-	  <colspec colnum="4" colname="b23" align="center" />
-	  <colspec colnum="5" colname="b22" align="center" />
-	  <colspec colnum="6" colname="b21" align="center" />
-	  <colspec colnum="7" colname="b20" align="center" />
-	  <colspec colnum="8" colname="b19" align="center" />
-	  <colspec colnum="9" colname="b18" align="center" />
-	  <colspec colnum="10" colname="b17" align="center" />
-	  <colspec colnum="11" colname="b16" align="center" />
-	  <colspec colnum="12" colname="b15" align="center" />
-	  <colspec colnum="13" colname="b14" align="center" />
-	  <colspec colnum="14" colname="b13" align="center" />
-	  <colspec colnum="15" colname="b12" align="center" />
-	  <colspec colnum="16" colname="b11" align="center" />
-	  <colspec colnum="17" colname="b10" align="center" />
-	  <colspec colnum="18" colname="b09" align="center" />
-	  <colspec colnum="19" colname="b08" align="center" />
-	  <colspec colnum="20" colname="b07" align="center" />
-	  <colspec colnum="21" colname="b06" align="center" />
-	  <colspec colnum="22" colname="b05" align="center" />
-	  <colspec colnum="23" colname="b04" align="center" />
-	  <colspec colnum="24" colname="b03" align="center" />
-	  <colspec colnum="25" colname="b02" align="center" />
-	  <colspec colnum="26" colname="b01" align="center" />
-	  <colspec colnum="27" colname="b00" align="center" />
-	  <spanspec namest="b23" nameend="b00" spanname="b0" />
+	  <colspec colnum="4" colname="b31" align="center" />
+	  <colspec colnum="5" colname="b20" align="center" />
+	  <colspec colnum="6" colname="b29" align="center" />
+	  <colspec colnum="7" colname="b28" align="center" />
+	  <colspec colnum="8" colname="b27" align="center" />
+	  <colspec colnum="9" colname="b26" align="center" />
+	  <colspec colnum="10" colname="b25" align="center" />
+	  <colspec colnum="11" colname="b24" align="center" />
+	  <colspec colnum="12" colname="b23" align="center" />
+	  <colspec colnum="13" colname="b22" align="center" />
+	  <colspec colnum="14" colname="b21" align="center" />
+	  <colspec colnum="15" colname="b20" align="center" />
+	  <colspec colnum="16" colname="b19" align="center" />
+	  <colspec colnum="17" colname="b18" align="center" />
+	  <colspec colnum="18" colname="b17" align="center" />
+	  <colspec colnum="19" colname="b16" align="center" />
+	  <colspec colnum="20" colname="b15" align="center" />
+	  <colspec colnum="21" colname="b14" align="center" />
+	  <colspec colnum="22" colname="b13" align="center" />
+	  <colspec colnum="23" colname="b12" align="center" />
+	  <colspec colnum="24" colname="b11" align="center" />
+	  <colspec colnum="25" colname="b10" align="center" />
+	  <colspec colnum="26" colname="b09" align="center" />
+	  <colspec colnum="27" colname="b08" align="center" />
+	  <colspec colnum="28" colname="b07" align="center" />
+	  <colspec colnum="29" colname="b06" align="center" />
+	  <colspec colnum="30" colname="b05" align="center" />
+	  <colspec colnum="31" colname="b04" align="center" />
+	  <colspec colnum="32" colname="b03" align="center" />
+	  <colspec colnum="33" colname="b02" align="center" />
+	  <colspec colnum="34" colname="b01" align="center" />
+	  <colspec colnum="35" colname="b00" align="center" />
+	  <spanspec namest="b31" nameend="b00" spanname="b0" />
 	  <thead>
 	    <row>
 	      <entry>Identifier</entry>
@@ -133,6 +141,14 @@
 	      <entry></entry>
 	      <entry></entry>
 	      <entry>Bit</entry>
+	      <entry>31</entry>
+	      <entry>30</entry>
+	      <entry>29</entry>
+	      <entry>28</entry>
+	      <entry>27</entry>
+	      <entry>26</entry>
+	      <entry>25</entry>
+	      <entry>24</entry>
 	      <entry>23</entry>
 	      <entry>22</entry>
 	      <entry>21</entry>
@@ -164,7 +180,7 @@
 	      <entry>V4L2_MBUS_FMT_RGB444_2X8_PADHI_BE</entry>
 	      <entry>0x1001</entry>
 	      <entry></entry>
-	      &dash-ent-16;
+	      &dash-ent-24;
 	      <entry>0</entry>
 	      <entry>0</entry>
 	      <entry>0</entry>
@@ -178,7 +194,7 @@
 	      <entry></entry>
 	      <entry></entry>
 	      <entry></entry>
-	      &dash-ent-16;
+	      &dash-ent-24;
 	      <entry>g<subscript>3</subscript></entry>
 	      <entry>g<subscript>2</subscript></entry>
 	      <entry>g<subscript>1</subscript></entry>
@@ -192,7 +208,7 @@
 	      <entry>V4L2_MBUS_FMT_RGB444_2X8_PADHI_LE</entry>
 	      <entry>0x1002</entry>
 	      <entry></entry>
-	      &dash-ent-16;
+	      &dash-ent-24;
 	      <entry>g<subscript>3</subscript></entry>
 	      <entry>g<subscript>2</subscript></entry>
 	      <entry>g<subscript>1</subscript></entry>
@@ -206,7 +222,7 @@
 	      <entry></entry>
 	      <entry></entry>
 	      <entry></entry>
-	      &dash-ent-16;
+	      &dash-ent-24;
 	      <entry>0</entry>
 	      <entry>0</entry>
 	      <entry>0</entry>
@@ -220,7 +236,7 @@
 	      <entry>V4L2_MBUS_FMT_RGB555_2X8_PADHI_BE</entry>
 	      <entry>0x1003</entry>
 	      <entry></entry>
-	      &dash-ent-16;
+	      &dash-ent-24;
 	      <entry>0</entry>
 	      <entry>r<subscript>4</subscript></entry>
 	      <entry>r<subscript>3</subscript></entry>
@@ -234,7 +250,7 @@
 	      <entry></entry>
 	      <entry></entry>
 	      <entry></entry>
-	      &dash-ent-16;
+	      &dash-ent-24;
 	      <entry>g<subscript>2</subscript></entry>
 	      <entry>g<subscript>1</subscript></entry>
 	      <entry>g<subscript>0</subscript></entry>
@@ -248,7 +264,7 @@
 	      <entry>V4L2_MBUS_FMT_RGB555_2X8_PADHI_LE</entry>
 	      <entry>0x1004</entry>
 	      <entry></entry>
-	      &dash-ent-16;
+	      &dash-ent-24;
 	      <entry>g<subscript>2</subscript></entry>
 	      <entry>g<subscript>1</subscript></entry>
 	      <entry>g<subscript>0</subscript></entry>
@@ -262,7 +278,7 @@
 	      <entry></entry>
 	      <entry></entry>
 	      <entry></entry>
-	      &dash-ent-16;
+	      &dash-ent-24;
 	      <entry>0</entry>
 	      <entry>r<subscript>4</subscript></entry>
 	      <entry>r<subscript>3</subscript></entry>
@@ -276,7 +292,7 @@
 	      <entry>V4L2_MBUS_FMT_BGR565_2X8_BE</entry>
 	      <entry>0x1005</entry>
 	      <entry></entry>
-	      &dash-ent-16;
+	      &dash-ent-24;
 	      <entry>b<subscript>4</subscript></entry>
 	      <entry>b<subscript>3</subscript></entry>
 	      <entry>b<subscript>2</subscript></entry>
@@ -290,7 +306,7 @@
 	      <entry></entry>
 	      <entry></entry>
 	      <entry></entry>
-	      &dash-ent-16;
+	      &dash-ent-24;
 	      <entry>g<subscript>2</subscript></entry>
 	      <entry>g<subscript>1</subscript></entry>
 	      <entry>g<subscript>0</subscript></entry>
@@ -304,7 +320,7 @@
 	      <entry>V4L2_MBUS_FMT_BGR565_2X8_LE</entry>
 	      <entry>0x1006</entry>
 	      <entry></entry>
-	      &dash-ent-16;
+	      &dash-ent-24;
 	      <entry>g<subscript>2</subscript></entry>
 	      <entry>g<subscript>1</subscript></entry>
 	      <entry>g<subscript>0</subscript></entry>
@@ -318,7 +334,7 @@
 	      <entry></entry>
 	      <entry></entry>
 	      <entry></entry>
-	      &dash-ent-16;
+	      &dash-ent-24;
 	      <entry>b<subscript>4</subscript></entry>
 	      <entry>b<subscript>3</subscript></entry>
 	      <entry>b<subscript>2</subscript></entry>
@@ -332,7 +348,7 @@
 	      <entry>V4L2_MBUS_FMT_RGB565_2X8_BE</entry>
 	      <entry>0x1007</entry>
 	      <entry></entry>
-	      &dash-ent-16;
+	      &dash-ent-24;
 	      <entry>r<subscript>4</subscript></entry>
 	      <entry>r<subscript>3</subscript></entry>
 	      <entry>r<subscript>2</subscript></entry>
@@ -346,7 +362,7 @@
 	      <entry></entry>
 	      <entry></entry>
 	      <entry></entry>
-	      &dash-ent-16;
+	      &dash-ent-24;
 	      <entry>g<subscript>2</subscript></entry>
 	      <entry>g<subscript>1</subscript></entry>
 	      <entry>g<subscript>0</subscript></entry>
@@ -360,7 +376,7 @@
 	      <entry>V4L2_MBUS_FMT_RGB565_2X8_LE</entry>
 	      <entry>0x1008</entry>
 	      <entry></entry>
-	      &dash-ent-16;
+	      &dash-ent-24;
 	      <entry>g<subscript>2</subscript></entry>
 	      <entry>g<subscript>1</subscript></entry>
 	      <entry>g<subscript>0</subscript></entry>
@@ -374,7 +390,7 @@
 	      <entry></entry>
 	      <entry></entry>
 	      <entry></entry>
-	      &dash-ent-16;
+	      &dash-ent-24;
 	      <entry>r<subscript>4</subscript></entry>
 	      <entry>r<subscript>3</subscript></entry>
 	      <entry>r<subscript>2</subscript></entry>
@@ -388,12 +404,7 @@
 	      <entry>V4L2_MBUS_FMT_RGB666_1X18</entry>
 	      <entry>0x1009</entry>
 	      <entry></entry>
-	      <entry>-</entry>
-	      <entry>-</entry>
-	      <entry>-</entry>
-	      <entry>-</entry>
-	      <entry>-</entry>
-	      <entry>-</entry>
+	      &dash-ent-14;
 	      <entry>r<subscript>5</subscript></entry>
 	      <entry>r<subscript>4</subscript></entry>
 	      <entry>r<subscript>3</subscript></entry>
@@ -417,6 +428,7 @@
 	      <entry>V4L2_MBUS_FMT_RGB888_1X24</entry>
 	      <entry>0x100a</entry>
 	      <entry></entry>
+	      &dash-ent-8;
 	      <entry>r<subscript>7</subscript></entry>
 	      <entry>r<subscript>6</subscript></entry>
 	      <entry>r<subscript>5</subscript></entry>
@@ -446,9 +458,7 @@
 	      <entry>V4L2_MBUS_FMT_RGB888_2X12_BE</entry>
 	      <entry>0x100b</entry>
 	      <entry></entry>
-	      &dash-ent-10;
-	      <entry>-</entry>
-	      <entry>-</entry>
+	      &dash-ent-20;
 	      <entry>r<subscript>7</subscript></entry>
 	      <entry>r<subscript>6</subscript></entry>
 	      <entry>r<subscript>5</subscript></entry>
@@ -466,9 +476,7 @@
 	      <entry></entry>
 	      <entry></entry>
 	      <entry></entry>
-	      &dash-ent-10;
-	      <entry>-</entry>
-	      <entry>-</entry>
+	      &dash-ent-20;
 	      <entry>g<subscript>3</subscript></entry>
 	      <entry>g<subscript>2</subscript></entry>
 	      <entry>g<subscript>1</subscript></entry>
@@ -486,9 +494,7 @@
 	      <entry>V4L2_MBUS_FMT_RGB888_2X12_LE</entry>
 	      <entry>0x100c</entry>
 	      <entry></entry>
-	      &dash-ent-10;
-	      <entry>-</entry>
-	      <entry>-</entry>
+	      &dash-ent-20;
 	      <entry>g<subscript>3</subscript></entry>
 	      <entry>g<subscript>2</subscript></entry>
 	      <entry>g<subscript>1</subscript></entry>
@@ -506,9 +512,7 @@
 	      <entry></entry>
 	      <entry></entry>
 	      <entry></entry>
-	      &dash-ent-10;
-	      <entry>-</entry>
-	      <entry>-</entry>
+	      &dash-ent-20;
 	      <entry>r<subscript>7</subscript></entry>
 	      <entry>r<subscript>6</subscript></entry>
 	      <entry>r<subscript>5</subscript></entry>
@@ -522,6 +526,43 @@
 	      <entry>g<subscript>5</subscript></entry>
 	      <entry>g<subscript>4</subscript></entry>
 	    </row>
+	    <row id="V4L2-MBUS-FMT-ARGB888-1X32">
+	      <entry>V4L2_MBUS_FMT_ARGB888_1X32</entry>
+	      <entry>0x100d</entry>
+	      <entry></entry>
+	      <entry>a<subscript>7</subscript></entry>
+	      <entry>a<subscript>6</subscript></entry>
+	      <entry>a<subscript>5</subscript></entry>
+	      <entry>a<subscript>4</subscript></entry>
+	      <entry>a<subscript>3</subscript></entry>
+	      <entry>a<subscript>2</subscript></entry>
+	      <entry>a<subscript>1</subscript></entry>
+	      <entry>a<subscript>0</subscript></entry>
+	      <entry>r<subscript>7</subscript></entry>
+	      <entry>r<subscript>6</subscript></entry>
+	      <entry>r<subscript>5</subscript></entry>
+	      <entry>r<subscript>4</subscript></entry>
+	      <entry>r<subscript>3</subscript></entry>
+	      <entry>r<subscript>2</subscript></entry>
+	      <entry>r<subscript>1</subscript></entry>
+	      <entry>r<subscript>0</subscript></entry>
+	      <entry>g<subscript>7</subscript></entry>
+	      <entry>g<subscript>6</subscript></entry>
+	      <entry>g<subscript>5</subscript></entry>
+	      <entry>g<subscript>4</subscript></entry>
+	      <entry>g<subscript>3</subscript></entry>
+	      <entry>g<subscript>2</subscript></entry>
+	      <entry>g<subscript>1</subscript></entry>
+	      <entry>g<subscript>0</subscript></entry>
+	      <entry>b<subscript>7</subscript></entry>
+	      <entry>b<subscript>6</subscript></entry>
+	      <entry>b<subscript>5</subscript></entry>
+	      <entry>b<subscript>4</subscript></entry>
+	      <entry>b<subscript>3</subscript></entry>
+	      <entry>b<subscript>2</subscript></entry>
+	      <entry>b<subscript>1</subscript></entry>
+	      <entry>b<subscript>0</subscript></entry>
+	    </row>
 	  </tbody>
 	</tgroup>
       </table>
@@ -1149,6 +1190,7 @@
 	   <listitem><para>y<subscript>x</subscript> for luma component bit number x</para></listitem>
 	   <listitem><para>u<subscript>x</subscript> for blue chroma component bit number x</para></listitem>
 	   <listitem><para>v<subscript>x</subscript> for red chroma component bit number x</para></listitem>
+	   <listitem><para>a<subscript>x</subscript> for alpha component bit number x</para></listitem>
 	   <listitem><para>- for non-available bits (for positions higher than the bus width)</para></listitem>
 	   <listitem><para>d for dummy bits</para></listitem>
 	</itemizedlist>
@@ -1159,37 +1201,39 @@
 	  <colspec colname="id" align="left" />
 	  <colspec colname="code" align="center"/>
 	  <colspec colname="bit" />
-	  <colspec colnum="4" colname="b29" align="center" />
-	  <colspec colnum="5" colname="b28" align="center" />
-	  <colspec colnum="6" colname="b27" align="center" />
-	  <colspec colnum="7" colname="b26" align="center" />
-	  <colspec colnum="8" colname="b25" align="center" />
-	  <colspec colnum="9" colname="b24" align="center" />
-	  <colspec colnum="10" colname="b23" align="center" />
-	  <colspec colnum="11" colname="b22" align="center" />
-	  <colspec colnum="12" colname="b21" align="center" />
-	  <colspec colnum="13" colname="b20" align="center" />
-	  <colspec colnum="14" colname="b19" align="center" />
-	  <colspec colnum="15" colname="b18" align="center" />
-	  <colspec colnum="16" colname="b17" align="center" />
-	  <colspec colnum="17" colname="b16" align="center" />
-	  <colspec colnum="18" colname="b15" align="center" />
-	  <colspec colnum="19" colname="b14" align="center" />
-	  <colspec colnum="20" colname="b13" align="center" />
-	  <colspec colnum="21" colname="b12" align="center" />
-	  <colspec colnum="22" colname="b11" align="center" />
-	  <colspec colnum="23" colname="b10" align="center" />
-	  <colspec colnum="24" colname="b09" align="center" />
-	  <colspec colnum="25" colname="b08" align="center" />
-	  <colspec colnum="26" colname="b07" align="center" />
-	  <colspec colnum="27" colname="b06" align="center" />
-	  <colspec colnum="28" colname="b05" align="center" />
-	  <colspec colnum="29" colname="b04" align="center" />
-	  <colspec colnum="30" colname="b03" align="center" />
-	  <colspec colnum="31" colname="b02" align="center" />
-	  <colspec colnum="32" colname="b01" align="center" />
-	  <colspec colnum="33" colname="b00" align="center" />
-	  <spanspec namest="b29" nameend="b00" spanname="b0" />
+	  <colspec colnum="4" colname="b31" align="center" />
+	  <colspec colnum="5" colname="b20" align="center" />
+	  <colspec colnum="6" colname="b29" align="center" />
+	  <colspec colnum="7" colname="b28" align="center" />
+	  <colspec colnum="8" colname="b27" align="center" />
+	  <colspec colnum="9" colname="b26" align="center" />
+	  <colspec colnum="10" colname="b25" align="center" />
+	  <colspec colnum="11" colname="b24" align="center" />
+	  <colspec colnum="12" colname="b23" align="center" />
+	  <colspec colnum="13" colname="b22" align="center" />
+	  <colspec colnum="14" colname="b21" align="center" />
+	  <colspec colnum="15" colname="b20" align="center" />
+	  <colspec colnum="16" colname="b19" align="center" />
+	  <colspec colnum="17" colname="b18" align="center" />
+	  <colspec colnum="18" colname="b17" align="center" />
+	  <colspec colnum="19" colname="b16" align="center" />
+	  <colspec colnum="20" colname="b15" align="center" />
+	  <colspec colnum="21" colname="b14" align="center" />
+	  <colspec colnum="22" colname="b13" align="center" />
+	  <colspec colnum="23" colname="b12" align="center" />
+	  <colspec colnum="24" colname="b11" align="center" />
+	  <colspec colnum="25" colname="b10" align="center" />
+	  <colspec colnum="26" colname="b09" align="center" />
+	  <colspec colnum="27" colname="b08" align="center" />
+	  <colspec colnum="28" colname="b07" align="center" />
+	  <colspec colnum="29" colname="b06" align="center" />
+	  <colspec colnum="30" colname="b05" align="center" />
+	  <colspec colnum="31" colname="b04" align="center" />
+	  <colspec colnum="32" colname="b03" align="center" />
+	  <colspec colnum="33" colname="b02" align="center" />
+	  <colspec colnum="34" colname="b01" align="center" />
+	  <colspec colnum="35" colname="b00" align="center" />
+	  <spanspec namest="b31" nameend="b00" spanname="b0" />
 	  <thead>
 	    <row>
 	      <entry>Identifier</entry>
@@ -1201,6 +1245,8 @@
 	      <entry></entry>
 	      <entry></entry>
 	      <entry>Bit</entry>
+	      <entry>31</entry>
+	      <entry>30</entry>
 	      <entry>29</entry>
 	      <entry>28</entry>
 	      <entry>27</entry>
@@ -1238,10 +1284,7 @@
 	      <entry>V4L2_MBUS_FMT_Y8_1X8</entry>
 	      <entry>0x2001</entry>
 	      <entry></entry>
-	      &dash-ent-10;
-	      &dash-ent-10;
-	      <entry>-</entry>
-	      <entry>-</entry>
+	      &dash-ent-24;
 	      <entry>y<subscript>7</subscript></entry>
 	      <entry>y<subscript>6</subscript></entry>
 	      <entry>y<subscript>5</subscript></entry>
@@ -1255,18 +1298,7 @@
 	      <entry>V4L2_MBUS_FMT_UV8_1X8</entry>
 	      <entry>0x2015</entry>
 	      <entry></entry>
-	      <entry>-</entry>
-	      <entry>-</entry>
-	      <entry>-</entry>
-	      <entry>-</entry>
-	      <entry>-</entry>
-	      <entry>-</entry>
-	      <entry>-</entry>
-	      <entry>-</entry>
-	      <entry>-</entry>
-	      <entry>-</entry>
-	      <entry>-</entry>
-	      <entry>-</entry>
+	      &dash-ent-24;
 	      <entry>u<subscript>7</subscript></entry>
 	      <entry>u<subscript>6</subscript></entry>
 	      <entry>u<subscript>5</subscript></entry>
@@ -1280,18 +1312,7 @@
 	      <entry></entry>
 	      <entry></entry>
 	      <entry></entry>
-	      <entry>-</entry>
-	      <entry>-</entry>
-	      <entry>-</entry>
-	      <entry>-</entry>
-	      <entry>-</entry>
-	      <entry>-</entry>
-	      <entry>-</entry>
-	      <entry>-</entry>
-	      <entry>-</entry>
-	      <entry>-</entry>
-	      <entry>-</entry>
-	      <entry>-</entry>
+	      &dash-ent-24;
 	      <entry>v<subscript>7</subscript></entry>
 	      <entry>v<subscript>6</subscript></entry>
 	      <entry>v<subscript>5</subscript></entry>
@@ -1305,10 +1326,7 @@
 	      <entry>V4L2_MBUS_FMT_UYVY8_1_5X8</entry>
 	      <entry>0x2002</entry>
 	      <entry></entry>
-	      &dash-ent-10;
-	      &dash-ent-10;
-	      <entry>-</entry>
-	      <entry>-</entry>
+	      &dash-ent-24;
 	      <entry>u<subscript>7</subscript></entry>
 	      <entry>u<subscript>6</subscript></entry>
 	      <entry>u<subscript>5</subscript></entry>
@@ -1322,10 +1340,7 @@
 	      <entry></entry>
 	      <entry></entry>
 	      <entry></entry>
-	      &dash-ent-10;
-	      &dash-ent-10;
-	      <entry>-</entry>
-	      <entry>-</entry>
+	      &dash-ent-24;
 	      <entry>y<subscript>7</subscript></entry>
 	      <entry>y<subscript>6</subscript></entry>
 	      <entry>y<subscript>5</subscript></entry>
@@ -1339,10 +1354,7 @@
 	      <entry></entry>
 	      <entry></entry>
 	      <entry></entry>
-	      &dash-ent-10;
-	      &dash-ent-10;
-	      <entry>-</entry>
-	      <entry>-</entry>
+	      &dash-ent-24;
 	      <entry>y<subscript>7</subscript></entry>
 	      <entry>y<subscript>6</subscript></entry>
 	      <entry>y<subscript>5</subscript></entry>
@@ -1356,10 +1368,7 @@
 	      <entry></entry>
 	      <entry></entry>
 	      <entry></entry>
-	      &dash-ent-10;
-	      &dash-ent-10;
-	      <entry>-</entry>
-	      <entry>-</entry>
+	      &dash-ent-24;
 	      <entry>v<subscript>7</subscript></entry>
 	      <entry>v<subscript>6</subscript></entry>
 	      <entry>v<subscript>5</subscript></entry>
@@ -1373,10 +1382,7 @@
 	      <entry></entry>
 	      <entry></entry>
 	      <entry></entry>
-	      &dash-ent-10;
-	      &dash-ent-10;
-	      <entry>-</entry>
-	      <entry>-</entry>
+	      &dash-ent-24;
 	      <entry>y<subscript>7</subscript></entry>
 	      <entry>y<subscript>6</subscript></entry>
 	      <entry>y<subscript>5</subscript></entry>
@@ -1390,10 +1396,7 @@
 	      <entry></entry>
 	      <entry></entry>
 	      <entry></entry>
-	      &dash-ent-10;
-	      &dash-ent-10;
-	      <entry>-</entry>
-	      <entry>-</entry>
+	      &dash-ent-24;
 	      <entry>y<subscript>7</subscript></entry>
 	      <entry>y<subscript>6</subscript></entry>
 	      <entry>y<subscript>5</subscript></entry>
@@ -1407,10 +1410,7 @@
 	      <entry>V4L2_MBUS_FMT_VYUY8_1_5X8</entry>
 	      <entry>0x2003</entry>
 	      <entry></entry>
-	      &dash-ent-10;
-	      &dash-ent-10;
-	      <entry>-</entry>
-	      <entry>-</entry>
+	      &dash-ent-24;
 	      <entry>v<subscript>7</subscript></entry>
 	      <entry>v<subscript>6</subscript></entry>
 	      <entry>v<subscript>5</subscript></entry>
@@ -1424,10 +1424,7 @@
 	      <entry></entry>
 	      <entry></entry>
 	      <entry></entry>
-	      &dash-ent-10;
-	      &dash-ent-10;
-	      <entry>-</entry>
-	      <entry>-</entry>
+	      &dash-ent-24;
 	      <entry>y<subscript>7</subscript></entry>
 	      <entry>y<subscript>6</subscript></entry>
 	      <entry>y<subscript>5</subscript></entry>
@@ -1441,10 +1438,7 @@
 	      <entry></entry>
 	      <entry></entry>
 	      <entry></entry>
-	      &dash-ent-10;
-	      &dash-ent-10;
-	      <entry>-</entry>
-	      <entry>-</entry>
+	      &dash-ent-24;
 	      <entry>y<subscript>7</subscript></entry>
 	      <entry>y<subscript>6</subscript></entry>
 	      <entry>y<subscript>5</subscript></entry>
@@ -1458,10 +1452,7 @@
 	      <entry></entry>
 	      <entry></entry>
 	      <entry></entry>
-	      &dash-ent-10;
-	      &dash-ent-10;
-	      <entry>-</entry>
-	      <entry>-</entry>
+	      &dash-ent-24;
 	      <entry>u<subscript>7</subscript></entry>
 	      <entry>u<subscript>6</subscript></entry>
 	      <entry>u<subscript>5</subscript></entry>
@@ -1475,10 +1466,7 @@
 	      <entry></entry>
 	      <entry></entry>
 	      <entry></entry>
-	      &dash-ent-10;
-	      &dash-ent-10;
-	      <entry>-</entry>
-	      <entry>-</entry>
+	      &dash-ent-24;
 	      <entry>y<subscript>7</subscript></entry>
 	      <entry>y<subscript>6</subscript></entry>
 	      <entry>y<subscript>5</subscript></entry>
@@ -1492,10 +1480,7 @@
 	      <entry></entry>
 	      <entry></entry>
 	      <entry></entry>
-	      &dash-ent-10;
-	      &dash-ent-10;
-	      <entry>-</entry>
-	      <entry>-</entry>
+	      &dash-ent-24;
 	      <entry>y<subscript>7</subscript></entry>
 	      <entry>y<subscript>6</subscript></entry>
 	      <entry>y<subscript>5</subscript></entry>
@@ -1509,10 +1494,7 @@
 	      <entry>V4L2_MBUS_FMT_YUYV8_1_5X8</entry>
 	      <entry>0x2004</entry>
 	      <entry></entry>
-	      &dash-ent-10;
-	      &dash-ent-10;
-	      <entry>-</entry>
-	      <entry>-</entry>
+	      &dash-ent-24;
 	      <entry>y<subscript>7</subscript></entry>
 	      <entry>y<subscript>6</subscript></entry>
 	      <entry>y<subscript>5</subscript></entry>
@@ -1526,10 +1508,7 @@
 	      <entry></entry>
 	      <entry></entry>
 	      <entry></entry>
-	      &dash-ent-10;
-	      &dash-ent-10;
-	      <entry>-</entry>
-	      <entry>-</entry>
+	      &dash-ent-24;
 	      <entry>y<subscript>7</subscript></entry>
 	      <entry>y<subscript>6</subscript></entry>
 	      <entry>y<subscript>5</subscript></entry>
@@ -1543,10 +1522,7 @@
 	      <entry></entry>
 	      <entry></entry>
 	      <entry></entry>
-	      &dash-ent-10;
-	      &dash-ent-10;
-	      <entry>-</entry>
-	      <entry>-</entry>
+	      &dash-ent-24;
 	      <entry>u<subscript>7</subscript></entry>
 	      <entry>u<subscript>6</subscript></entry>
 	      <entry>u<subscript>5</subscript></entry>
@@ -1560,10 +1536,7 @@
 	      <entry></entry>
 	      <entry></entry>
 	      <entry></entry>
-	      &dash-ent-10;
-	      &dash-ent-10;
-	      <entry>-</entry>
-	      <entry>-</entry>
+	      &dash-ent-24;
 	      <entry>y<subscript>7</subscript></entry>
 	      <entry>y<subscript>6</subscript></entry>
 	      <entry>y<subscript>5</subscript></entry>
@@ -1577,10 +1550,7 @@
 	      <entry></entry>
 	      <entry></entry>
 	      <entry></entry>
-	      &dash-ent-10;
-	      &dash-ent-10;
-	      <entry>-</entry>
-	      <entry>-</entry>
+	      &dash-ent-24;
 	      <entry>y<subscript>7</subscript></entry>
 	      <entry>y<subscript>6</subscript></entry>
 	      <entry>y<subscript>5</subscript></entry>
@@ -1594,10 +1564,7 @@
 	      <entry></entry>
 	      <entry></entry>
 	      <entry></entry>
-	      &dash-ent-10;
-	      &dash-ent-10;
-	      <entry>-</entry>
-	      <entry>-</entry>
+	      &dash-ent-24;
 	      <entry>v<subscript>7</subscript></entry>
 	      <entry>v<subscript>6</subscript></entry>
 	      <entry>v<subscript>5</subscript></entry>
@@ -1611,10 +1578,7 @@
 	      <entry>V4L2_MBUS_FMT_YVYU8_1_5X8</entry>
 	      <entry>0x2005</entry>
 	      <entry></entry>
-	      &dash-ent-10;
-	      &dash-ent-10;
-	      <entry>-</entry>
-	      <entry>-</entry>
+	      &dash-ent-24;
 	      <entry>y<subscript>7</subscript></entry>
 	      <entry>y<subscript>6</subscript></entry>
 	      <entry>y<subscript>5</subscript></entry>
@@ -1628,10 +1592,7 @@
 	      <entry></entry>
 	      <entry></entry>
 	      <entry></entry>
-	      &dash-ent-10;
-	      &dash-ent-10;
-	      <entry>-</entry>
-	      <entry>-</entry>
+	      &dash-ent-24;
 	      <entry>y<subscript>7</subscript></entry>
 	      <entry>y<subscript>6</subscript></entry>
 	      <entry>y<subscript>5</subscript></entry>
@@ -1645,10 +1606,7 @@
 	      <entry></entry>
 	      <entry></entry>
 	      <entry></entry>
-	      &dash-ent-10;
-	      &dash-ent-10;
-	      <entry>-</entry>
-	      <entry>-</entry>
+	      &dash-ent-24;
 	      <entry>v<subscript>7</subscript></entry>
 	      <entry>v<subscript>6</subscript></entry>
 	      <entry>v<subscript>5</subscript></entry>
@@ -1662,10 +1620,7 @@
 	      <entry></entry>
 	      <entry></entry>
 	      <entry></entry>
-	      &dash-ent-10;
-	      &dash-ent-10;
-	      <entry>-</entry>
-	      <entry>-</entry>
+	      &dash-ent-24;
 	      <entry>y<subscript>7</subscript></entry>
 	      <entry>y<subscript>6</subscript></entry>
 	      <entry>y<subscript>5</subscript></entry>
@@ -1679,10 +1634,7 @@
 	      <entry></entry>
 	      <entry></entry>
 	      <entry></entry>
-	      &dash-ent-10;
-	      &dash-ent-10;
-	      <entry>-</entry>
-	      <entry>-</entry>
+	      &dash-ent-24;
 	      <entry>y<subscript>7</subscript></entry>
 	      <entry>y<subscript>6</subscript></entry>
 	      <entry>y<subscript>5</subscript></entry>
@@ -1696,10 +1648,7 @@
 	      <entry></entry>
 	      <entry></entry>
 	      <entry></entry>
-	      &dash-ent-10;
-	      &dash-ent-10;
-	      <entry>-</entry>
-	      <entry>-</entry>
+	      &dash-ent-24;
 	      <entry>u<subscript>7</subscript></entry>
 	      <entry>u<subscript>6</subscript></entry>
 	      <entry>u<subscript>5</subscript></entry>
@@ -1713,10 +1662,7 @@
 	      <entry>V4L2_MBUS_FMT_UYVY8_2X8</entry>
 	      <entry>0x2006</entry>
 	      <entry></entry>
-	      &dash-ent-10;
-	      &dash-ent-10;
-	      <entry>-</entry>
-	      <entry>-</entry>
+	      &dash-ent-24;
 	      <entry>u<subscript>7</subscript></entry>
 	      <entry>u<subscript>6</subscript></entry>
 	      <entry>u<subscript>5</subscript></entry>
@@ -1730,10 +1676,7 @@
 	      <entry></entry>
 	      <entry></entry>
 	      <entry></entry>
-	      &dash-ent-10;
-	      &dash-ent-10;
-	      <entry>-</entry>
-	      <entry>-</entry>
+	      &dash-ent-24;
 	      <entry>y<subscript>7</subscript></entry>
 	      <entry>y<subscript>6</subscript></entry>
 	      <entry>y<subscript>5</subscript></entry>
@@ -1747,10 +1690,7 @@
 	      <entry></entry>
 	      <entry></entry>
 	      <entry></entry>
-	      &dash-ent-10;
-	      &dash-ent-10;
-	      <entry>-</entry>
-	      <entry>-</entry>
+	      &dash-ent-24;
 	      <entry>v<subscript>7</subscript></entry>
 	      <entry>v<subscript>6</subscript></entry>
 	      <entry>v<subscript>5</subscript></entry>
@@ -1764,10 +1704,7 @@
 	      <entry></entry>
 	      <entry></entry>
 	      <entry></entry>
-	      &dash-ent-10;
-	      &dash-ent-10;
-	      <entry>-</entry>
-	      <entry>-</entry>
+	      &dash-ent-24;
 	      <entry>y<subscript>7</subscript></entry>
 	      <entry>y<subscript>6</subscript></entry>
 	      <entry>y<subscript>5</subscript></entry>
@@ -1781,10 +1718,7 @@
 	      <entry>V4L2_MBUS_FMT_VYUY8_2X8</entry>
 	      <entry>0x2007</entry>
 	      <entry></entry>
-	      &dash-ent-10;
-	      &dash-ent-10;
-	      <entry>-</entry>
-	      <entry>-</entry>
+	      &dash-ent-24;
 	      <entry>v<subscript>7</subscript></entry>
 	      <entry>v<subscript>6</subscript></entry>
 	      <entry>v<subscript>5</subscript></entry>
@@ -1798,10 +1732,7 @@
 	      <entry></entry>
 	      <entry></entry>
 	      <entry></entry>
-	      &dash-ent-10;
-	      &dash-ent-10;
-	      <entry>-</entry>
-	      <entry>-</entry>
+	      &dash-ent-24;
 	      <entry>y<subscript>7</subscript></entry>
 	      <entry>y<subscript>6</subscript></entry>
 	      <entry>y<subscript>5</subscript></entry>
@@ -1815,10 +1746,7 @@
 	      <entry></entry>
 	      <entry></entry>
 	      <entry></entry>
-	      &dash-ent-10;
-	      &dash-ent-10;
-	      <entry>-</entry>
-	      <entry>-</entry>
+	      &dash-ent-24;
 	      <entry>u<subscript>7</subscript></entry>
 	      <entry>u<subscript>6</subscript></entry>
 	      <entry>u<subscript>5</subscript></entry>
@@ -1832,10 +1760,7 @@
 	      <entry></entry>
 	      <entry></entry>
 	      <entry></entry>
-	      &dash-ent-10;
-	      &dash-ent-10;
-	      <entry>-</entry>
-	      <entry>-</entry>
+	      &dash-ent-24;
 	      <entry>y<subscript>7</subscript></entry>
 	      <entry>y<subscript>6</subscript></entry>
 	      <entry>y<subscript>5</subscript></entry>
@@ -1849,10 +1774,7 @@
 	      <entry>V4L2_MBUS_FMT_YUYV8_2X8</entry>
 	      <entry>0x2008</entry>
 	      <entry></entry>
-	      &dash-ent-10;
-	      &dash-ent-10;
-	      <entry>-</entry>
-	      <entry>-</entry>
+	      &dash-ent-24;
 	      <entry>y<subscript>7</subscript></entry>
 	      <entry>y<subscript>6</subscript></entry>
 	      <entry>y<subscript>5</subscript></entry>
@@ -1866,10 +1788,7 @@
 	      <entry></entry>
 	      <entry></entry>
 	      <entry></entry>
-	      &dash-ent-10;
-	      &dash-ent-10;
-	      <entry>-</entry>
-	      <entry>-</entry>
+	      &dash-ent-24;
 	      <entry>u<subscript>7</subscript></entry>
 	      <entry>u<subscript>6</subscript></entry>
 	      <entry>u<subscript>5</subscript></entry>
@@ -1883,10 +1802,7 @@
 	      <entry></entry>
 	      <entry></entry>
 	      <entry></entry>
-	      &dash-ent-10;
-	      &dash-ent-10;
-	      <entry>-</entry>
-	      <entry>-</entry>
+	      &dash-ent-24;
 	      <entry>y<subscript>7</subscript></entry>
 	      <entry>y<subscript>6</subscript></entry>
 	      <entry>y<subscript>5</subscript></entry>
@@ -1900,10 +1816,7 @@
 	      <entry></entry>
 	      <entry></entry>
 	      <entry></entry>
-	      &dash-ent-10;
-	      &dash-ent-10;
-	      <entry>-</entry>
-	      <entry>-</entry>
+	      &dash-ent-24;
 	      <entry>v<subscript>7</subscript></entry>
 	      <entry>v<subscript>6</subscript></entry>
 	      <entry>v<subscript>5</subscript></entry>
@@ -1917,10 +1830,7 @@
 	      <entry>V4L2_MBUS_FMT_YVYU8_2X8</entry>
 	      <entry>0x2009</entry>
 	      <entry></entry>
-	      &dash-ent-10;
-	      &dash-ent-10;
-	      <entry>-</entry>
-	      <entry>-</entry>
+	      &dash-ent-24;
 	      <entry>y<subscript>7</subscript></entry>
 	      <entry>y<subscript>6</subscript></entry>
 	      <entry>y<subscript>5</subscript></entry>
@@ -1934,10 +1844,7 @@
 	      <entry></entry>
 	      <entry></entry>
 	      <entry></entry>
-	      &dash-ent-10;
-	      &dash-ent-10;
-	      <entry>-</entry>
-	      <entry>-</entry>
+	      &dash-ent-24;
 	      <entry>v<subscript>7</subscript></entry>
 	      <entry>v<subscript>6</subscript></entry>
 	      <entry>v<subscript>5</subscript></entry>
@@ -1951,10 +1858,7 @@
 	      <entry></entry>
 	      <entry></entry>
 	      <entry></entry>
-	      &dash-ent-10;
-	      &dash-ent-10;
-	      <entry>-</entry>
-	      <entry>-</entry>
+	      &dash-ent-24;
 	      <entry>y<subscript>7</subscript></entry>
 	      <entry>y<subscript>6</subscript></entry>
 	      <entry>y<subscript>5</subscript></entry>
@@ -1968,10 +1872,7 @@
 	      <entry></entry>
 	      <entry></entry>
 	      <entry></entry>
-	      &dash-ent-10;
-	      &dash-ent-10;
-	      <entry>-</entry>
-	      <entry>-</entry>
+	      &dash-ent-24;
 	      <entry>u<subscript>7</subscript></entry>
 	      <entry>u<subscript>6</subscript></entry>
 	      <entry>u<subscript>5</subscript></entry>
@@ -1985,8 +1886,7 @@
 	      <entry>V4L2_MBUS_FMT_Y10_1X10</entry>
 	      <entry>0x200a</entry>
 	      <entry></entry>
-	      &dash-ent-10;
-	      &dash-ent-10;
+	      &dash-ent-22;
 	      <entry>y<subscript>9</subscript></entry>
 	      <entry>y<subscript>8</subscript></entry>
 	      <entry>y<subscript>7</subscript></entry>
@@ -2002,8 +1902,7 @@
 	      <entry>V4L2_MBUS_FMT_YUYV10_2X10</entry>
 	      <entry>0x200b</entry>
 	      <entry></entry>
-	      &dash-ent-10;
-	      &dash-ent-10;
+	      &dash-ent-22;
 	      <entry>y<subscript>9</subscript></entry>
 	      <entry>y<subscript>8</subscript></entry>
 	      <entry>y<subscript>7</subscript></entry>
@@ -2019,8 +1918,7 @@
 	      <entry></entry>
 	      <entry></entry>
 	      <entry></entry>
-	      &dash-ent-10;
-	      &dash-ent-10;
+	      &dash-ent-22;
 	      <entry>u<subscript>9</subscript></entry>
 	      <entry>u<subscript>8</subscript></entry>
 	      <entry>u<subscript>7</subscript></entry>
@@ -2036,8 +1934,7 @@
 	      <entry></entry>
 	      <entry></entry>
 	      <entry></entry>
-	      &dash-ent-10;
-	      &dash-ent-10;
+	      &dash-ent-22;
 	      <entry>y<subscript>9</subscript></entry>
 	      <entry>y<subscript>8</subscript></entry>
 	      <entry>y<subscript>7</subscript></entry>
@@ -2053,8 +1950,7 @@
 	      <entry></entry>
 	      <entry></entry>
 	      <entry></entry>
-	      &dash-ent-10;
-	      &dash-ent-10;
+	      &dash-ent-22;
 	      <entry>v<subscript>9</subscript></entry>
 	      <entry>v<subscript>8</subscript></entry>
 	      <entry>v<subscript>7</subscript></entry>
@@ -2070,8 +1966,7 @@
 	      <entry>V4L2_MBUS_FMT_YVYU10_2X10</entry>
 	      <entry>0x200c</entry>
 	      <entry></entry>
-	      &dash-ent-10;
-	      &dash-ent-10;
+	      &dash-ent-22;
 	      <entry>y<subscript>9</subscript></entry>
 	      <entry>y<subscript>8</subscript></entry>
 	      <entry>y<subscript>7</subscript></entry>
@@ -2087,8 +1982,7 @@
 	      <entry></entry>
 	      <entry></entry>
 	      <entry></entry>
-	      &dash-ent-10;
-	      &dash-ent-10;
+	      &dash-ent-22;
 	      <entry>v<subscript>9</subscript></entry>
 	      <entry>v<subscript>8</subscript></entry>
 	      <entry>v<subscript>7</subscript></entry>
@@ -2104,8 +1998,7 @@
 	      <entry></entry>
 	      <entry></entry>
 	      <entry></entry>
-	      &dash-ent-10;
-	      &dash-ent-10;
+	      &dash-ent-22;
 	      <entry>y<subscript>9</subscript></entry>
 	      <entry>y<subscript>8</subscript></entry>
 	      <entry>y<subscript>7</subscript></entry>
@@ -2121,8 +2014,7 @@
 	      <entry></entry>
 	      <entry></entry>
 	      <entry></entry>
-	      &dash-ent-10;
-	      &dash-ent-10;
+	      &dash-ent-22;
 	      <entry>u<subscript>9</subscript></entry>
 	      <entry>u<subscript>8</subscript></entry>
 	      <entry>u<subscript>7</subscript></entry>
@@ -2138,15 +2030,7 @@
 	      <entry>V4L2_MBUS_FMT_Y12_1X12</entry>
 	      <entry>0x2013</entry>
 	      <entry></entry>
-	      &dash-ent-10;
-	      <entry>-</entry>
-	      <entry>-</entry>
-	      <entry>-</entry>
-	      <entry>-</entry>
-	      <entry>-</entry>
-	      <entry>-</entry>
-	      <entry>-</entry>
-	      <entry>-</entry>
+	      &dash-ent-20;
 	      <entry>y<subscript>11</subscript></entry>
 	      <entry>y<subscript>10</subscript></entry>
 	      <entry>y<subscript>9</subscript></entry>
@@ -2164,11 +2048,7 @@
 	      <entry>V4L2_MBUS_FMT_UYVY8_1X16</entry>
 	      <entry>0x200f</entry>
 	      <entry></entry>
-	      &dash-ent-10;
-	      <entry>-</entry>
-	      <entry>-</entry>
-	      <entry>-</entry>
-	      <entry>-</entry>
+	      &dash-ent-16;
 	      <entry>u<subscript>7</subscript></entry>
 	      <entry>u<subscript>6</subscript></entry>
 	      <entry>u<subscript>5</subscript></entry>
@@ -2190,11 +2070,7 @@
 	      <entry></entry>
 	      <entry></entry>
 	      <entry></entry>
-	      &dash-ent-10;
-	      <entry>-</entry>
-	      <entry>-</entry>
-	      <entry>-</entry>
-	      <entry>-</entry>
+	      &dash-ent-16;
 	      <entry>v<subscript>7</subscript></entry>
 	      <entry>v<subscript>6</subscript></entry>
 	      <entry>v<subscript>5</subscript></entry>
@@ -2216,11 +2092,7 @@
 	      <entry>V4L2_MBUS_FMT_VYUY8_1X16</entry>
 	      <entry>0x2010</entry>
 	      <entry></entry>
-	      &dash-ent-10;
-	      <entry>-</entry>
-	      <entry>-</entry>
-	      <entry>-</entry>
-	      <entry>-</entry>
+	      &dash-ent-16;
 	      <entry>v<subscript>7</subscript></entry>
 	      <entry>v<subscript>6</subscript></entry>
 	      <entry>v<subscript>5</subscript></entry>
@@ -2242,11 +2114,7 @@
 	      <entry></entry>
 	      <entry></entry>
 	      <entry></entry>
-	      &dash-ent-10;
-	      <entry>-</entry>
-	      <entry>-</entry>
-	      <entry>-</entry>
-	      <entry>-</entry>
+	      &dash-ent-16;
 	      <entry>u<subscript>7</subscript></entry>
 	      <entry>u<subscript>6</subscript></entry>
 	      <entry>u<subscript>5</subscript></entry>
@@ -2268,11 +2136,7 @@
 	      <entry>V4L2_MBUS_FMT_YUYV8_1X16</entry>
 	      <entry>0x2011</entry>
 	      <entry></entry>
-	      &dash-ent-10;
-	      <entry>-</entry>
-	      <entry>-</entry>
-	      <entry>-</entry>
-	      <entry>-</entry>
+	      &dash-ent-16;
 	      <entry>y<subscript>7</subscript></entry>
 	      <entry>y<subscript>6</subscript></entry>
 	      <entry>y<subscript>5</subscript></entry>
@@ -2294,11 +2158,7 @@
 	      <entry></entry>
 	      <entry></entry>
 	      <entry></entry>
-	      &dash-ent-10;
-	      <entry>-</entry>
-	      <entry>-</entry>
-	      <entry>-</entry>
-	      <entry>-</entry>
+	      &dash-ent-16;
 	      <entry>y<subscript>7</subscript></entry>
 	      <entry>y<subscript>6</subscript></entry>
 	      <entry>y<subscript>5</subscript></entry>
@@ -2320,11 +2180,7 @@
 	      <entry>V4L2_MBUS_FMT_YVYU8_1X16</entry>
 	      <entry>0x2012</entry>
 	      <entry></entry>
-	      &dash-ent-10;
-	      <entry>-</entry>
-	      <entry>-</entry>
-	      <entry>-</entry>
-	      <entry>-</entry>
+	      &dash-ent-16;
 	      <entry>y<subscript>7</subscript></entry>
 	      <entry>y<subscript>6</subscript></entry>
 	      <entry>y<subscript>5</subscript></entry>
@@ -2346,11 +2202,7 @@
 	      <entry></entry>
 	      <entry></entry>
 	      <entry></entry>
-	      &dash-ent-10;
-	      <entry>-</entry>
-	      <entry>-</entry>
-	      <entry>-</entry>
-	      <entry>-</entry>
+	      &dash-ent-16;
 	      <entry>y<subscript>7</subscript></entry>
 	      <entry>y<subscript>6</subscript></entry>
 	      <entry>y<subscript>5</subscript></entry>
@@ -2372,10 +2224,7 @@
 	      <entry>V4L2_MBUS_FMT_YDYUYDYV8_1X16</entry>
 	      <entry>0x2014</entry>
 	      <entry></entry>
-	      <entry>-</entry>
-	      <entry>-</entry>
-	      <entry>-</entry>
-	      <entry>-</entry>
+	      &dash-ent-16;
 	      <entry>y<subscript>7</subscript></entry>
 	      <entry>y<subscript>6</subscript></entry>
 	      <entry>y<subscript>5</subscript></entry>
@@ -2397,10 +2246,7 @@
 	      <entry></entry>
 	      <entry></entry>
 	      <entry></entry>
-	      <entry>-</entry>
-	      <entry>-</entry>
-	      <entry>-</entry>
-	      <entry>-</entry>
+	      &dash-ent-16;
 	      <entry>y<subscript>7</subscript></entry>
 	      <entry>y<subscript>6</subscript></entry>
 	      <entry>y<subscript>5</subscript></entry>
@@ -2422,10 +2268,7 @@
 	      <entry></entry>
 	      <entry></entry>
 	      <entry></entry>
-	      <entry>-</entry>
-	      <entry>-</entry>
-	      <entry>-</entry>
-	      <entry>-</entry>
+	      &dash-ent-16;
 	      <entry>y<subscript>7</subscript></entry>
 	      <entry>y<subscript>6</subscript></entry>
 	      <entry>y<subscript>5</subscript></entry>
@@ -2447,10 +2290,7 @@
 	      <entry></entry>
 	      <entry></entry>
 	      <entry></entry>
-	      <entry>-</entry>
-	      <entry>-</entry>
-	      <entry>-</entry>
-	      <entry>-</entry>
+	      &dash-ent-16;
 	      <entry>y<subscript>7</subscript></entry>
 	      <entry>y<subscript>6</subscript></entry>
 	      <entry>y<subscript>5</subscript></entry>
@@ -2472,7 +2312,7 @@
 	      <entry>V4L2_MBUS_FMT_YUYV10_1X20</entry>
 	      <entry>0x200d</entry>
 	      <entry></entry>
-	      &dash-ent-10;
+	      &dash-ent-12;
 	      <entry>y<subscript>9</subscript></entry>
 	      <entry>y<subscript>8</subscript></entry>
 	      <entry>y<subscript>7</subscript></entry>
@@ -2498,7 +2338,7 @@
 	      <entry></entry>
 	      <entry></entry>
 	      <entry></entry>
-	      &dash-ent-10;
+	      &dash-ent-12;
 	      <entry>y<subscript>9</subscript></entry>
 	      <entry>y<subscript>8</subscript></entry>
 	      <entry>y<subscript>7</subscript></entry>
@@ -2524,7 +2364,7 @@
 	      <entry>V4L2_MBUS_FMT_YVYU10_1X20</entry>
 	      <entry>0x200e</entry>
 	      <entry></entry>
-	      &dash-ent-10;
+	      &dash-ent-12;
 	      <entry>y<subscript>9</subscript></entry>
 	      <entry>y<subscript>8</subscript></entry>
 	      <entry>y<subscript>7</subscript></entry>
@@ -2550,7 +2390,7 @@
 	      <entry></entry>
 	      <entry></entry>
 	      <entry></entry>
-	      &dash-ent-10;
+	      &dash-ent-12;
 	      <entry>y<subscript>9</subscript></entry>
 	      <entry>y<subscript>8</subscript></entry>
 	      <entry>y<subscript>7</subscript></entry>
@@ -2574,8 +2414,10 @@
 	    </row>
 	    <row id="V4L2-MBUS-FMT-YUV10-1X30">
 	      <entry>V4L2_MBUS_FMT_YUV10_1X30</entry>
-	      <entry>0x2014</entry>
+	      <entry>0x2016</entry>
 	      <entry></entry>
+	      <entry>-</entry>
+	      <entry>-</entry>
 	      <entry>y<subscript>9</subscript></entry>
 	      <entry>y<subscript>8</subscript></entry>
 	      <entry>y<subscript>7</subscript></entry>
@@ -2607,6 +2449,43 @@
 	      <entry>v<subscript>1</subscript></entry>
 	      <entry>v<subscript>0</subscript></entry>
 	    </row>
+	    <row id="V4L2-MBUS-FMT-AYUV8-1X32">
+	      <entry>V4L2_MBUS_FMT_AYUV8_1X32</entry>
+	      <entry>0x2017</entry>
+	      <entry></entry>
+	      <entry>a<subscript>7</subscript></entry>
+	      <entry>a<subscript>6</subscript></entry>
+	      <entry>a<subscript>5</subscript></entry>
+	      <entry>a<subscript>4</subscript></entry>
+	      <entry>a<subscript>3</subscript></entry>
+	      <entry>a<subscript>2</subscript></entry>
+	      <entry>a<subscript>1</subscript></entry>
+	      <entry>a<subscript>0</subscript></entry>
+	      <entry>y<subscript>7</subscript></entry>
+	      <entry>y<subscript>6</subscript></entry>
+	      <entry>y<subscript>5</subscript></entry>
+	      <entry>y<subscript>4</subscript></entry>
+	      <entry>y<subscript>3</subscript></entry>
+	      <entry>y<subscript>2</subscript></entry>
+	      <entry>y<subscript>1</subscript></entry>
+	      <entry>y<subscript>0</subscript></entry>
+	      <entry>u<subscript>7</subscript></entry>
+	      <entry>u<subscript>6</subscript></entry>
+	      <entry>u<subscript>5</subscript></entry>
+	      <entry>u<subscript>4</subscript></entry>
+	      <entry>u<subscript>3</subscript></entry>
+	      <entry>u<subscript>2</subscript></entry>
+	      <entry>u<subscript>1</subscript></entry>
+	      <entry>u<subscript>0</subscript></entry>
+	      <entry>v<subscript>7</subscript></entry>
+	      <entry>v<subscript>6</subscript></entry>
+	      <entry>v<subscript>5</subscript></entry>
+	      <entry>v<subscript>4</subscript></entry>
+	      <entry>v<subscript>3</subscript></entry>
+	      <entry>v<subscript>2</subscript></entry>
+	      <entry>v<subscript>1</subscript></entry>
+	      <entry>v<subscript>0</subscript></entry>
+	    </row>
 	  </tbody>
 	</tgroup>
       </table>
diff --git a/Documentation/DocBook/media/v4l/vidioc-create-bufs.xml b/Documentation/DocBook/media/v4l/vidioc-create-bufs.xml
index cd9943672434..9b700a5f4df7 100644
--- a/Documentation/DocBook/media/v4l/vidioc-create-bufs.xml
+++ b/Documentation/DocBook/media/v4l/vidioc-create-bufs.xml
@@ -62,18 +62,29 @@ addition to the <constant>VIDIOC_REQBUFS</constant> ioctl, when a tighter
 control over buffers is required. This ioctl can be called multiple times to
 create buffers of different sizes.</para>
 
-    <para>To allocate device buffers applications initialize relevant fields of
-the <structname>v4l2_create_buffers</structname> structure. They set the
-<structfield>type</structfield> field in the
-&v4l2-format; structure, embedded in this
-structure, to the respective stream or buffer type.
-<structfield>count</structfield> must be set to the number of required buffers.
-<structfield>memory</structfield> specifies the required I/O method. The
-<structfield>format</structfield> field shall typically be filled in using
-either the <constant>VIDIOC_TRY_FMT</constant> or
-<constant>VIDIOC_G_FMT</constant> ioctl(). Additionally, applications can adjust
-<structfield>sizeimage</structfield> fields to fit their specific needs. The
-<structfield>reserved</structfield> array must be zeroed.</para>
+    <para>To allocate the device buffers applications must initialize the
+relevant fields of the <structname>v4l2_create_buffers</structname> structure.
+The <structfield>count</structfield> field must be set to the number of
+requested buffers, the <structfield>memory</structfield> field specifies the
+requested I/O method and the <structfield>reserved</structfield> array must be
+zeroed.</para>
+
+    <para>The <structfield>format</structfield> field specifies the image format
+that the buffers must be able to handle. The application has to fill in this
+&v4l2-format;. Usually this will be done using the
+<constant>VIDIOC_TRY_FMT</constant> or <constant>VIDIOC_G_FMT</constant> ioctl()
+to ensure that the requested format is supported by the driver. Unsupported
+formats will result in an error.</para>
+
+    <para>The buffers created by this ioctl will have as minimum size the size
+defined by the <structfield>format.pix.sizeimage</structfield> field. If the
+<structfield>format.pix.sizeimage</structfield> field is less than the minimum
+required for the given format, then <structfield>sizeimage</structfield> will be
+increased by the driver to that minimum to allocate the buffers. If it is
+larger, then the value will be used as-is. The same applies to the
+<structfield>sizeimage</structfield> field of the
+<structname>v4l2_plane_pix_format</structname> structure in the case of
+multiplanar formats.</para>
 
     <para>When the ioctl is called with a pointer to this structure the driver
 will attempt to allocate up to the requested number of buffers and store the
@@ -144,9 +155,9 @@ mapped</link> I/O.</para>
       <varlistentry>
 	<term><errorcode>EINVAL</errorcode></term>
 	<listitem>
-	  <para>The buffer type (<structfield>type</structfield> field) or the
-requested I/O method (<structfield>memory</structfield>) is not
-supported.</para>
+	  <para>The buffer type (<structfield>format.type</structfield> field),
+requested I/O method (<structfield>memory</structfield>) or format
+(<structfield>format</structfield> field) is not valid.</para>
 	</listitem>
       </varlistentry>
     </variablelist>
diff --git a/Documentation/DocBook/media/v4l/vidioc-g-dv-timings.xml b/Documentation/DocBook/media/v4l/vidioc-g-dv-timings.xml
index 72369707bd77..c4336577ff06 100644
--- a/Documentation/DocBook/media/v4l/vidioc-g-dv-timings.xml
+++ b/Documentation/DocBook/media/v4l/vidioc-g-dv-timings.xml
@@ -156,19 +156,19 @@ bit 0 (V4L2_DV_VSYNC_POS_POL) is for vertical sync polarity and bit 1 (V4L2_DV_H
 	    <entry>__u32</entry>
 	    <entry><structfield>il_vfrontporch</structfield></entry>
 	    <entry>Vertical front porch in lines for the even field (aka field 2) of
-	    interlaced field formats.</entry>
+	    interlaced field formats. Must be 0 for progressive formats.</entry>
 	  </row>
 	  <row>
 	    <entry>__u32</entry>
 	    <entry><structfield>il_vsync</structfield></entry>
 	    <entry>Vertical sync length in lines for the even field (aka field 2) of
-	    interlaced field formats.</entry>
+	    interlaced field formats. Must be 0 for progressive formats.</entry>
 	  </row>
 	  <row>
 	    <entry>__u32</entry>
 	    <entry><structfield>il_vbackporch</structfield></entry>
 	    <entry>Vertical back porch in lines for the even field (aka field 2) of
-	    interlaced field formats.</entry>
+	    interlaced field formats. Must be 0 for progressive formats.</entry>
 	  </row>
 	  <row>
 	    <entry>__u32</entry>
diff --git a/Documentation/DocBook/media/v4l/vidioc-g-jpegcomp.xml b/Documentation/DocBook/media/v4l/vidioc-g-jpegcomp.xml
index 48748499c097..098ff483802e 100644
--- a/Documentation/DocBook/media/v4l/vidioc-g-jpegcomp.xml
+++ b/Documentation/DocBook/media/v4l/vidioc-g-jpegcomp.xml
@@ -92,8 +92,8 @@ to add them.</para>
 	    <entry>int</entry>
 	    <entry><structfield>quality</structfield></entry>
 	    <entry>Deprecated. If <link linkend="jpeg-quality-control"><constant>
-	    V4L2_CID_JPEG_IMAGE_QUALITY</constant></link> control is exposed by
-	    a driver applications should use it instead and ignore this field.
+	    V4L2_CID_JPEG_COMPRESSION_QUALITY</constant></link> control is exposed
+	    by a driver applications should use it instead and ignore this field.
 	    </entry>
 	  </row>
 	  <row>
diff --git a/Documentation/DocBook/media/v4l/vidioc-g-parm.xml b/Documentation/DocBook/media/v4l/vidioc-g-parm.xml
index 9058224d1bbf..f4e28e7d4751 100644
--- a/Documentation/DocBook/media/v4l/vidioc-g-parm.xml
+++ b/Documentation/DocBook/media/v4l/vidioc-g-parm.xml
@@ -132,7 +132,7 @@ devices.</para>
 	  <row>
 	    <entry>&v4l2-fract;</entry>
 	    <entry><structfield>timeperframe</structfield></entry>
-	    <entry><para>This is is the desired period between
+	    <entry><para>This is the desired period between
 successive frames captured by the driver, in seconds. The
 field is intended to skip frames on the driver side, saving I/O
 bandwidth.</para><para>Applications store here the desired frame
@@ -193,7 +193,7 @@ applications must set the array to zero.</entry>
 	  <row>
 	    <entry>&v4l2-fract;</entry>
 	    <entry><structfield>timeperframe</structfield></entry>
-	    <entry>This is is the desired period between
+	    <entry>This is the desired period between
 successive frames output by the driver, in seconds.</entry>
 	  </row>
 	  <row>
diff --git a/Documentation/DocBook/media_api.tmpl b/Documentation/DocBook/media_api.tmpl
index 9c92bb879b6d..4c8d282545a2 100644
--- a/Documentation/DocBook/media_api.tmpl
+++ b/Documentation/DocBook/media_api.tmpl
@@ -22,8 +22,14 @@
 
 <!-- LinuxTV v4l-dvb repository. -->
 <!ENTITY v4l-dvb		"<ulink url='http://linuxtv.org/repo/'>http://linuxtv.org/repo/</ulink>">
+<!ENTITY dash-ent-8             "<entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry>">
 <!ENTITY dash-ent-10            "<entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry>">
+<!ENTITY dash-ent-12            "<entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry>">
+<!ENTITY dash-ent-14            "<entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry>">
 <!ENTITY dash-ent-16            "<entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry>">
+<!ENTITY dash-ent-20            "<entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry>">
+<!ENTITY dash-ent-22            "<entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry>">
+<!ENTITY dash-ent-24            "<entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry><entry>-</entry>">
 ]>
 
 <book id="media_api">
diff --git a/Documentation/DocBook/mtdnand.tmpl b/Documentation/DocBook/mtdnand.tmpl
index fe122d6e686f..a248f42a121e 100644
--- a/Documentation/DocBook/mtdnand.tmpl
+++ b/Documentation/DocBook/mtdnand.tmpl
@@ -1224,8 +1224,6 @@ in this page</entry>
 #define NAND_BBT_CREATE		0x00000200
 /* Search good / bad pattern through all pages of a block */
 #define NAND_BBT_SCANALLPAGES	0x00000400
-/* Scan block empty during good / bad block scan */
-#define NAND_BBT_SCANEMPTY	0x00000800
 /* Write bbt if neccecary */
 #define NAND_BBT_WRITE		0x00001000
 /* Read and write back block contents when writing bbt */
diff --git a/Documentation/IRQ-affinity.txt b/Documentation/IRQ-affinity.txt
index 7890fae18529..01a675175a36 100644
--- a/Documentation/IRQ-affinity.txt
+++ b/Documentation/IRQ-affinity.txt
@@ -57,8 +57,8 @@ i.e counters for the CPU0-3 did not change.
 
 Here is an example of limiting that same irq (44) to cpus 1024 to 1031:
 
-[root@moon 44]# echo 1024-1031 > smp_affinity
-[root@moon 44]# cat smp_affinity
+[root@moon 44]# echo 1024-1031 > smp_affinity_list
+[root@moon 44]# cat smp_affinity_list
 1024-1031
 
 Note that to do this with a bitmask would require 32 bitmasks of zero
diff --git a/Documentation/RCU/RTFP.txt b/Documentation/RCU/RTFP.txt
index 7f40c72a9c51..273e654d7d08 100644
--- a/Documentation/RCU/RTFP.txt
+++ b/Documentation/RCU/RTFP.txt
@@ -39,7 +39,7 @@ in read-mostly situations.  This algorithm does take pains to avoid
 write-side contention and parallelize the other write-side overheads by
 providing a fine-grained locking design, however, it would be interesting
 to see how much of the performance advantage reported in 1990 remains
-in 2004.
+today.
 
 At about this same time, Adams [Adams91] described ``chaotic relaxation'',
 where the normal barriers between successive iterations of convergent
@@ -86,9 +86,9 @@ DYNIX/ptx kernel.  The corresponding conference paper appeared in 1998
 [McKenney98].
 
 In 1999, the Tornado and K42 groups described their "generations"
-mechanism, which quite similar to RCU [Gamsa99].  These operating systems
-made pervasive use of RCU in place of "existence locks", which greatly
-simplifies locking hierarchies.
+mechanism, which is quite similar to RCU [Gamsa99].  These operating
+systems made pervasive use of RCU in place of "existence locks", which
+greatly simplifies locking hierarchies and helps avoid deadlocks.
 
 2001 saw the first RCU presentation involving Linux [McKenney01a]
 at OLS.  The resulting abundance of RCU patches was presented the
@@ -106,8 +106,11 @@ these techniques still impose significant read-side overhead in the
 form of memory barriers.  Researchers at Sun worked along similar lines
 in the same timeframe [HerlihyLM02].  These techniques can be thought
 of as inside-out reference counts, where the count is represented by the
-number of hazard pointers referencing a given data structure (rather than
-the more conventional counter field within the data structure itself).
+number of hazard pointers referencing a given data structure rather than
+the more conventional counter field within the data structure itself.
+The key advantage of inside-out reference counts is that they can be
+stored in immortal variables, thus allowing races between access and
+deletion to be avoided.
 
 By the same token, RCU can be thought of as a "bulk reference count",
 where some form of reference counter covers all reference by a given CPU
@@ -179,7 +182,25 @@ tree using software transactional memory to protect concurrent updates
 (strange, but true!) [PhilHoward2011RCUTMRBTree], yet another variant of
 RCU-protected resizeable hash tables [Triplett:2011:RPHash], the 3.0 RCU
 trainwreck [PaulEMcKenney2011RCU3.0trainwreck], and Neil Brown's "Meet the
-Lockers" LWN article [NeilBrown2011MeetTheLockers].
+Lockers" LWN article [NeilBrown2011MeetTheLockers].  Some academic
+work looked at debugging uses of RCU [Seyster:2011:RFA:2075416.2075425].
+
+In 2012, Josh Triplett received his Ph.D. with his dissertation
+covering RCU-protected resizable hash tables and the relationship
+between memory barriers and read-side traversal order:  If the updater
+is making changes in the opposite direction from the read-side traveral
+order, the updater need only execute a memory-barrier instruction,
+but if in the same direction, the updater needs to wait for a grace
+period between the individual updates [JoshTriplettPhD].  Also in 2012,
+after seventeen years of attempts, an RCU paper made it into a top-flight
+academic journal, IEEE Transactions on Parallel and Distributed Systems
+[MathieuDesnoyers2012URCU].  A group of researchers in Spain applied
+user-level RCU to crowd simulation [GuillermoVigueras2012RCUCrowd], and
+another group of researchers in Europe produced a formal description of
+RCU based on separation logic [AlexeyGotsman2012VerifyGraceExtended],
+which was published in the 2013 European Symposium on Programming
+[AlexeyGotsman2013ESOPRCU].
+
 
 
 Bibtex Entries
@@ -193,13 +214,12 @@ Bibtex Entries
 ,volume="5"
 ,number="3"
 ,pages="354-382"
-,note="Available:
-\url{http://portal.acm.org/citation.cfm?id=320619&dl=GUIDE,}
-[Viewed December 3, 2007]"
 ,annotation={
 	Use garbage collector to clean up data after everyone is done with it.
 	.
 	Oldest use of something vaguely resembling RCU that I have found.
+	http://portal.acm.org/citation.cfm?id=320619&dl=GUIDE,
+	[Viewed December 3, 2007]
 }
 }
 
@@ -309,7 +329,7 @@ for Programming Languages and Operating Systems}"
 ,doi = {http://doi.acm.org/10.1145/42392.42399}
 ,publisher = {ACM}
 ,address = {New York, NY, USA}
-,annotation= {
+,annotation={
 	At the top of page 307: "Conflicts with deposits and withdrawals
 	are necessary if the reported total is to be up to date.  They
 	could be avoided by having total return a sum that is slightly
@@ -346,8 +366,9 @@ for Programming Languages and Operating Systems}"
 }
 }
 
-@Book{Adams91
-,Author="Gregory R. Adams"
+# Was Adams91, see also syncrefs.bib.
+@Book{Andrews91textbook
+,Author="Gregory R. Andrews"
 ,title="Concurrent Programming, Principles, and Practices"
 ,Publisher="Benjamin Cummins"
 ,Year="1991"
@@ -398,39 +419,39 @@ for Programming Languages and Operating Systems}"
 }
 }
 
-@conference{Pu95a,
-Author = "Calton Pu and Tito Autrey and Andrew Black and Charles Consel and
+@conference{Pu95a
+,Author = "Calton Pu and Tito Autrey and Andrew Black and Charles Consel and
 Crispin Cowan and Jon Inouye and Lakshmi Kethana and Jonathan Walpole and
-Ke Zhang",
-Title = "Optimistic Incremental Specialization: Streamlining a Commercial
-Operating System",
-Booktitle = "15\textsuperscript{th} ACM Symposium on
-Operating Systems Principles (SOSP'95)",
-address = "Copper Mountain, CO",
-month="December",
-year="1995",
-pages="314-321",
-annotation="
+Ke Zhang"
+,Title = "Optimistic Incremental Specialization: Streamlining a Commercial
+,Operating System"
+,Booktitle = "15\textsuperscript{th} ACM Symposium on
+,Operating Systems Principles (SOSP'95)"
+,address = "Copper Mountain, CO"
+,month="December"
+,year="1995"
+,pages="314-321"
+,annotation={
 	Uses a replugger, but with a flag to signal when people are
 	using the resource at hand.  Only one reader at a time.
-"
-}
-
-@conference{Cowan96a,
-Author = "Crispin Cowan and Tito Autrey and Charles Krasic and
-Calton Pu and Jonathan Walpole",
-Title = "Fast Concurrent Dynamic Linking for an Adaptive Operating System",
-Booktitle = "International Conference on Configurable Distributed Systems
-(ICCDS'96)",
-address = "Annapolis, MD",
-month="May",
-year="1996",
-pages="108",
-isbn="0-8186-7395-8",
-annotation="
+}
+}
+
+@conference{Cowan96a
+,Author = "Crispin Cowan and Tito Autrey and Charles Krasic and
+,Calton Pu and Jonathan Walpole"
+,Title = "Fast Concurrent Dynamic Linking for an Adaptive Operating System"
+,Booktitle = "International Conference on Configurable Distributed Systems
+(ICCDS'96)"
+,address = "Annapolis, MD"
+,month="May"
+,year="1996"
+,pages="108"
+,isbn="0-8186-7395-8"
+,annotation={
 	Uses a replugger, but with a counter to signal when people are
 	using the resource at hand.  Allows multiple readers.
-"
+}
 }
 
 @techreport{Slingwine95
@@ -493,14 +514,13 @@ Problems"
 ,Year="1998"
 ,pages="509-518"
 ,Address="Las Vegas, NV"
-,note="Available:
-\url{http://www.rdrop.com/users/paulmck/RCU/rclockpdcsproof.pdf}
-[Viewed December 3, 2007]"
 ,annotation={
 	Describes and analyzes RCU mechanism in DYNIX/ptx.  Describes
 	application to linked list update and log-buffer flushing.
 	Defines 'quiescent state'.  Includes both measured and analytic
 	evaluation.
+	http://www.rdrop.com/users/paulmck/RCU/rclockpdcsproof.pdf
+	[Viewed December 3, 2007]
 }
 }
 
@@ -514,13 +534,12 @@ Operating System Design and Implementation}"
 ,Year="1999"
 ,pages="87-100"
 ,Address="New Orleans, LA"
-,note="Available:
-\url{http://www.usenix.org/events/osdi99/full_papers/gamsa/gamsa.pdf}
-[Viewed August 30, 2006]"
 ,annotation={
 	Use of RCU-like facility in K42/Tornado.  Another independent
 	invention of RCU.
 	See especially pages 7-9 (Section 5).
+	http://www.usenix.org/events/osdi99/full_papers/gamsa/gamsa.pdf
+	[Viewed August 30, 2006]
 }
 }
 
@@ -611,9 +630,9 @@ Orran Krieger and Rusty Russell and Dipankar Sarma and Maneesh Soni"
 ,note="Available:
 \url{http://marc.theaimsgroup.com/?l=linux-kernel&m=100259266316456&w=2}
 [Viewed June 23, 2004]"
-,annotation="
+,annotation={
 	Memory-barrier and Alpha thread.  100 messages, not too bad...
-"
+}
 }
 
 @unpublished{Spraul01
@@ -624,10 +643,10 @@ Orran Krieger and Rusty Russell and Dipankar Sarma and Maneesh Soni"
 ,note="Available:
 \url{http://marc.theaimsgroup.com/?l=linux-kernel&m=100264675012867&w=2}
 [Viewed June 23, 2004]"
-,annotation="
+,annotation={
 	Suggested burying memory barriers in Linux's list-manipulation
 	primitives.
-"
+}
 }
 
 @unpublished{LinusTorvalds2001a
@@ -638,6 +657,8 @@ Orran Krieger and Rusty Russell and Dipankar Sarma and Maneesh Soni"
 ,note="Available:
 \url{http://lkml.org/lkml/2001/10/13/105}
 [Viewed August 21, 2004]"
+,annotation={
+}
 }
 
 @unpublished{Blanchard02a
@@ -657,10 +678,10 @@ Orran Krieger and Rusty Russell and Dipankar Sarma and Maneesh Soni"
 ,Month="June"
 ,Year="2002"
 ,pages="289-300"
-,annotation="
+,annotation={
 	Measured scalability of Linux 2.4 kernel's directory-entry cache
 	(dcache), and measured some scalability enhancements.
-"
+}
 }
 
 @Conference{McKenney02a
@@ -674,10 +695,10 @@ Andrea Arcangeli and Andi Kleen and Orran Krieger and Rusty Russell"
 ,note="Available:
 \url{http://www.linux.org.uk/~ajh/ols2002_proceedings.pdf.gz}
 [Viewed June 23, 2004]"
-,annotation="
+,annotation={
 	Presented and compared a number of RCU implementations for the
 	Linux kernel.
-"
+}
 }
 
 @unpublished{Sarma02a
@@ -688,9 +709,9 @@ Andrea Arcangeli and Andi Kleen and Orran Krieger and Rusty Russell"
 ,note="Available:
 \url{http://marc.theaimsgroup.com/?l=linux-kernel&m=102645767914212&w=2}
 [Viewed June 23, 2004]"
-,annotation="
+,annotation={
 	Compare fastwalk and RCU for dcache.  RCU won.
-"
+}
 }
 
 @unpublished{Barbieri02
@@ -701,9 +722,9 @@ Andrea Arcangeli and Andi Kleen and Orran Krieger and Rusty Russell"
 ,note="Available:
 \url{http://marc.theaimsgroup.com/?l=linux-kernel&m=103082050621241&w=2}
 [Viewed: June 23, 2004]"
-,annotation="
+,annotation={
 	Suggested RCU for vfs\_shared\_cred.
-"
+}
 }
 
 @unpublished{Dickins02a
@@ -722,10 +743,10 @@ Andrea Arcangeli and Andi Kleen and Orran Krieger and Rusty Russell"
 ,note="Available:
 \url{http://marc.theaimsgroup.com/?l=linux-kernel&m=103462075416638&w=2}
 [Viewed June 23, 2004]"
-,annotation="
+,annotation={
 	Performance of dcache RCU on kernbench for 16x NUMA-Q and 1x,
 	2x, and 4x systems.  RCU does no harm, and helps on 16x.
-"
+}
 }
 
 @unpublished{LinusTorvalds2003a
@@ -736,14 +757,14 @@ Andrea Arcangeli and Andi Kleen and Orran Krieger and Rusty Russell"
 ,note="Available:
 \url{http://lkml.org/lkml/2003/3/9/205}
 [Viewed March 13, 2006]"
-,annotation="
+,annotation={
 	Linus suggests replacing brlock with RCU and/or seqlocks:
 	.
 	'It's entirely possible that the current user could be replaced
 	by RCU and/or seqlocks, and we could get rid of brlocks entirely.'
 	.
 	Steve Hemminger responds by replacing them with RCU.
-"
+}
 }
 
 @article{Appavoo03a
@@ -758,9 +779,9 @@ B. Rosenburg and M. Stumm and J. Xenidis"
 ,volume="42"
 ,number="1"
 ,pages="60-76"
-,annotation="
+,annotation={
 	Use of RCU to enable hot-swapping for autonomic behavior in K42.
-"
+}
 }
 
 @unpublished{Seigh03
@@ -769,9 +790,9 @@ B. Rosenburg and M. Stumm and J. Xenidis"
 ,Year="2003"
 ,Month="March"
 ,note="email correspondence"
-,annotation="
+,annotation={
 	Described the relationship of the VM/XA passive serialization to RCU.
-"
+}
 }
 
 @Conference{Arcangeli03
@@ -785,14 +806,12 @@ Dipankar Sarma"
 ,year="2003"
 ,month="June"
 ,pages="297-310"
-,note="Available:
-\url{http://www.rdrop.com/users/paulmck/RCU/rcu.FREENIX.2003.06.14.pdf}
-[Viewed November 21, 2007]"
-,annotation="
+,annotation={
 	Compared updated RCU implementations for the Linux kernel, and
 	described System V IPC use of RCU, including order-of-magnitude
 	performance improvements.
-"
+	http://www.rdrop.com/users/paulmck/RCU/rcu.FREENIX.2003.06.14.pdf
+}
 }
 
 @Conference{Soules03a
@@ -820,10 +839,10 @@ Michal Ostrowski and Bryan Rosenburg and Jimi Xenidis"
 ,note="Available:
 \url{http://www.linuxjournal.com/article/6993}
 [Viewed November 14, 2007]"
-,annotation="
+,annotation={
 	Reader-friendly intro to RCU, with the infamous old-man-and-brat
 	cartoon.
-"
+}
 }
 
 @unpublished{Sarma03a
@@ -832,7 +851,9 @@ Michal Ostrowski and Bryan Rosenburg and Jimi Xenidis"
 ,month="December"
 ,year="2003"
 ,note="Message ID: 20031222180114.GA2248@in.ibm.com"
-,annotation="dipankar/ct.2004.03.27/RCUll.2003.12.22.patch"
+,annotation={
+	dipankar/ct.2004.03.27/RCUll.2003.12.22.patch
+}
 }
 
 @techreport{Friedberg03a
@@ -844,11 +865,11 @@ Michal Ostrowski and Bryan Rosenburg and Jimi Xenidis"
 ,number="US Patent 6,662,184"
 ,month="December"
 ,pages="112"
-,annotation="
+,annotation={
 	Applies RCU to a wildcard-search Patricia tree in order to permit
 	synchronization-free lookup.  RCU is used to retain removed nodes
 	for a grace period before freeing them.
-"
+}
 }
 
 @article{McKenney04a
@@ -860,12 +881,11 @@ Michal Ostrowski and Bryan Rosenburg and Jimi Xenidis"
 ,volume="1"
 ,number="118"
 ,pages="38-46"
-,note="Available:
-\url{http://www.linuxjournal.com/node/7124}
-[Viewed December 26, 2010]"
-,annotation="
+,annotation={
 	Reader friendly intro to dcache and RCU.
-"
+	http://www.linuxjournal.com/node/7124
+	[Viewed December 26, 2010]
+}
 }
 
 @Conference{McKenney04b
@@ -879,10 +899,10 @@ Michal Ostrowski and Bryan Rosenburg and Jimi Xenidis"
 \url{http://www.linux.org.au/conf/2004/abstracts.html#90}
 \url{http://www.rdrop.com/users/paulmck/RCU/lockperf.2004.01.17a.pdf}
 [Viewed June 23, 2004]"
-,annotation="
+,annotation={
 	Compares performance of RCU to that of other locking primitives
 	over a number of CPUs (x86, Opteron, Itanium, and PPC).
-"
+}
 }
 
 @unpublished{Sarma04a
@@ -891,7 +911,9 @@ Michal Ostrowski and Bryan Rosenburg and Jimi Xenidis"
 ,month="March"
 ,year="2004"
 ,note="\url{http://marc.theaimsgroup.com/?l=linux-kernel&m=108003746402892&w=2}"
-,annotation="Head of thread: dipankar/2004.03.23/rcu-low-lat.1.patch"
+,annotation={
+	Head of thread: dipankar/2004.03.23/rcu-low-lat.1.patch
+}
 }
 
 @unpublished{Sarma04b
@@ -900,7 +922,9 @@ Michal Ostrowski and Bryan Rosenburg and Jimi Xenidis"
 ,month="March"
 ,year="2004"
 ,note="\url{http://marc.theaimsgroup.com/?l=linux-kernel&m=108016474829546&w=2}"
-,annotation="dipankar/rcuth.2004.03.24/rcu-throttle.patch"
+,annotation={
+	dipankar/rcuth.2004.03.24/rcu-throttle.patch
+}
 }
 
 @unpublished{Spraul04a
@@ -911,9 +935,9 @@ Michal Ostrowski and Bryan Rosenburg and Jimi Xenidis"
 ,note="Available:
 \url{http://marc.theaimsgroup.com/?l=linux-kernel&m=108546407726602&w=2}
 [Viewed June 23, 2004]"
-,annotation="
+,annotation={
 	Hierarchical-bitmap patch for RCU infrastructure.
-"
+}
 }
 
 @unpublished{Steiner04a
@@ -950,10 +974,12 @@ Realtime Applications"
 ,year="2004"
 ,month="June"
 ,pages="182-191"
-,annotation="
+,annotation={
 	Describes and compares a number of modifications to the Linux RCU
 	implementation that make it friendly to realtime applications.
-"
+	https://www.usenix.org/conference/2004-usenix-annual-technical-conference/making-rcu-safe-deep-sub-millisecond-response
+	[Viewed July 26, 2012]
+}
 }
 
 @phdthesis{PaulEdwardMcKenneyPhD
@@ -964,14 +990,13 @@ in Operating System Kernels"
 ,school="OGI School of Science and Engineering at
 Oregon Health and Sciences University"
 ,year="2004"
-,note="Available:
-\url{http://www.rdrop.com/users/paulmck/RCU/RCUdissertation.2004.07.14e1.pdf}
-[Viewed October 15, 2004]"
-,annotation="
+,annotation={
 	Describes RCU implementations and presents design patterns
 	corresponding to common uses of RCU in several operating-system
 	kernels.
-"
+	http://www.rdrop.com/users/paulmck/RCU/RCUdissertation.2004.07.14e1.pdf
+	[Viewed October 15, 2004]
+}
 }
 
 @unpublished{PaulEMcKenney2004rcu:dereference
@@ -982,9 +1007,9 @@ Oregon Health and Sciences University"
 ,note="Available:
 \url{http://lkml.org/lkml/2004/8/6/237}
 [Viewed June 8, 2010]"
-,annotation="
+,annotation={
 	Introduce rcu_dereference().
-"
+}
 }
 
 @unpublished{JimHouston04a
@@ -995,11 +1020,11 @@ Oregon Health and Sciences University"
 ,note="Available:
 \url{http://lkml.org/lkml/2004/8/30/87}
 [Viewed February 17, 2005]"
-,annotation="
+,annotation={
 	Uses active code in rcu_read_lock() and rcu_read_unlock() to
 	make RCU happen, allowing RCU to function on CPUs that do not
 	receive a scheduling-clock interrupt.
-"
+}
 }
 
 @unpublished{TomHart04a
@@ -1010,9 +1035,9 @@ Oregon Health and Sciences University"
 ,note="Available:
 \url{http://www.cs.toronto.edu/~tomhart/masters_thesis.html}
 [Viewed October 15, 2004]"
-,annotation="
+,annotation={
 	Proposes comparing RCU to lock-free methods for the Linux kernel.
-"
+}
 }
 
 @unpublished{Vaddagiri04a
@@ -1023,9 +1048,9 @@ Oregon Health and Sciences University"
 ,note="Available:
 \url{http://marc.theaimsgroup.com/?t=109395731700004&r=1&w=2}
 [Viewed October 18, 2004]"
-,annotation="
+,annotation={
 	Srivatsa's RCU patch for tcp_ehash lookup.
-"
+}
 }
 
 @unpublished{Thirumalai04a
@@ -1036,9 +1061,9 @@ Oregon Health and Sciences University"
 ,note="Available:
 \url{http://marc.theaimsgroup.com/?t=109144217400003&r=1&w=2}
 [Viewed October 18, 2004]"
-,annotation="
+,annotation={
 	Ravikiran's lockfree FD patch.
-"
+}
 }
 
 @unpublished{Thirumalai04b
@@ -1049,9 +1074,9 @@ Oregon Health and Sciences University"
 ,note="Available:
 \url{http://marc.theaimsgroup.com/?l=linux-kernel&m=109152521410459&w=2}
 [Viewed October 18, 2004]"
-,annotation="
+,annotation={
 	Ravikiran's lockfree FD patch.
-"
+}
 }
 
 @unpublished{PaulEMcKenney2004rcu:assign:pointer
@@ -1062,9 +1087,9 @@ Oregon Health and Sciences University"
 ,note="Available:
 \url{http://lkml.org/lkml/2004/10/23/241}
 [Viewed June 8, 2010]"
-,annotation="
+,annotation={
 	Introduce rcu_assign_pointer().
-"
+}
 }
 
 @unpublished{JamesMorris04a
@@ -1073,12 +1098,12 @@ Oregon Health and Sciences University"
 ,day="15"
 ,month="November"
 ,year="2004"
-,note="Available:
-\url{http://marc.theaimsgroup.com/?l=linux-kernel&m=110054979416004&w=2}
-[Viewed December 10, 2004]"
-,annotation="
+,note="\url{http://marc.theaimsgroup.com/?l=linux-kernel&m=110054979416004&w=2}"
+,annotation={
 	James Morris posts Kaigai Kohei's patch to LKML.
-"
+	[Viewed December 10, 2004]
+	Kaigai's patch is at https://lkml.org/lkml/2004/9/27/52
+}
 }
 
 @unpublished{JamesMorris04b
@@ -1089,9 +1114,9 @@ Oregon Health and Sciences University"
 ,note="Available:
 \url{http://www.livejournal.com/users/james_morris/2153.html}
 [Viewed December 10, 2004]"
-,annotation="
+,annotation={
 	RCU helps SELinux performance.  ;-)  Made LWN.
-"
+}
 }
 
 @unpublished{PaulMcKenney2005RCUSemantics
@@ -1103,9 +1128,9 @@ Oregon Health and Sciences University"
 ,note="Available:
 \url{http://www.rdrop.com/users/paulmck/RCU/rcu-semantics.2005.01.30a.pdf}
 [Viewed December 6, 2009]"
-,annotation="
+,annotation={
 	Early derivation of RCU semantics.
-"
+}
 }
 
 @unpublished{PaulMcKenney2005e
@@ -1117,10 +1142,10 @@ Oregon Health and Sciences University"
 ,note="Available:
 \url{http://lkml.org/lkml/2005/3/17/199}
 [Viewed September 5, 2005]"
-,annotation="
+,annotation={
 	First posting showing how RCU can be safely adapted for
 	preemptable RCU read side critical sections.
-"
+}
 }
 
 @unpublished{EsbenNeilsen2005a
@@ -1132,12 +1157,12 @@ Oregon Health and Sciences University"
 ,note="Available:
 \url{http://lkml.org/lkml/2005/3/18/122}
 [Viewed March 30, 2006]"
-,annotation="
+,annotation={
 	Esben Neilsen suggests read-side suppression of grace-period
 	processing for crude-but-workable realtime RCU.  The downside
-	is indefinite grace periods...But this is OK for experimentation
+	is indefinite grace periods...  But this is OK for experimentation
 	and testing.
-"
+}
 }
 
 @unpublished{TomHart05a
@@ -1149,10 +1174,10 @@ Data Structures"
 ,note="Available:
 \url{ftp://ftp.cs.toronto.edu/csrg-technical-reports/515/}
 [Viewed March 4, 2005]"
-,annotation="
+,annotation={
 	Comparison of RCU, QBSR, and EBSR.  RCU wins for read-mostly
 	workloads.  ;-)
-"
+}
 }
 
 @unpublished{JonCorbet2005DeprecateSyncKernel
@@ -1164,10 +1189,10 @@ Data Structures"
 ,note="Available:
 \url{http://lwn.net/Articles/134484/}
 [Viewed May 3, 2005]"
-,annotation="
+,annotation={
 	Jon Corbet describes deprecation of synchronize_kernel()
 	in favor of synchronize_rcu() and synchronize_sched().
-"
+}
 }
 
 @unpublished{PaulMcKenney05a
@@ -1178,10 +1203,10 @@ Data Structures"
 ,note="Available:
 \url{http://lkml.org/lkml/2005/5/9/185}
 [Viewed May 13, 2005]"
-,annotation="
+,annotation={
 	First publication of working lock-based deferred free patches
 	for the CONFIG_PREEMPT_RT environment.
-"
+}
 }
 
 @conference{PaulMcKenney05b
@@ -1194,10 +1219,10 @@ Data Structures"
 ,note="Available:
 \url{http://www.rdrop.com/users/paulmck/RCU/realtimeRCU.2005.04.23a.pdf}
 [Viewed May 13, 2005]"
-,annotation="
+,annotation={
 	Realtime turns into making RCU yet more realtime friendly.
 	http://lca2005.linux.org.au/Papers/Paul%20McKenney/Towards%20Hard%20Realtime%20Response%20from%20the%20Linux%20Kernel/LKS.2005.04.22a.pdf
-"
+}
 }
 
 @unpublished{PaulEMcKenneyHomePage
@@ -1208,9 +1233,9 @@ Data Structures"
 ,note="Available:
 \url{http://www.rdrop.com/users/paulmck/}
 [Viewed May 25, 2005]"
-,annotation="
+,annotation={
 	Paul McKenney's home page.
-"
+}
 }
 
 @unpublished{PaulEMcKenneyRCUPage
@@ -1221,9 +1246,9 @@ Data Structures"
 ,note="Available:
 \url{http://www.rdrop.com/users/paulmck/RCU}
 [Viewed May 25, 2005]"
-,annotation="
+,annotation={
 	Paul McKenney's RCU page.
-"
+}
 }
 
 @unpublished{JosephSeigh2005a
@@ -1232,10 +1257,10 @@ Data Structures"
 ,month="July"
 ,year="2005"
 ,note="Personal communication"
-,annotation="
+,annotation={
 	Joe Seigh announcing his atomic-ptr-plus project.
 	http://sourceforge.net/projects/atomic-ptr-plus/
-"
+}
 }
 
 @unpublished{JosephSeigh2005b
@@ -1247,9 +1272,9 @@ Data Structures"
 ,note="Available:
 \url{http://sourceforge.net/projects/atomic-ptr-plus/}
 [Viewed August 8, 2005]"
-,annotation="
+,annotation={
 	Joe Seigh's atomic-ptr-plus project.
-"
+}
 }
 
 @unpublished{PaulMcKenney2005c
@@ -1261,9 +1286,9 @@ Data Structures"
 ,note="Available:
 \url{http://lkml.org/lkml/2005/8/1/155}
 [Viewed March 14, 2006]"
-,annotation="
+,annotation={
 	First operating counter-based realtime RCU patch posted to LKML.
-"
+}
 }
 
 @unpublished{PaulMcKenney2005d
@@ -1275,11 +1300,11 @@ Data Structures"
 ,note="Available:
 \url{http://lkml.org/lkml/2005/8/8/108}
 [Viewed March 14, 2006]"
-,annotation="
+,annotation={
 	First operating counter-based realtime RCU patch posted to LKML,
 	but fixed so that various unusual combinations of configuration
 	parameters all function properly.
-"
+}
 }
 
 @unpublished{PaulMcKenney2005rcutorture
@@ -1291,9 +1316,25 @@ Data Structures"
 ,note="Available:
 \url{http://lkml.org/lkml/2005/10/1/70}
 [Viewed March 14, 2006]"
-,annotation="
+,annotation={
 	First rcutorture patch.
-"
+}
+}
+
+@unpublished{DavidSMiller2006HashedLocking
+,Author="David S. Miller"
+,Title="Re: [{PATCH}, {RFC}] {RCU} : {OOM} avoidance and lower latency"
+,month="January"
+,day="6"
+,year="2006"
+,note="Available:
+\url{https://lkml.org/lkml/2006/1/7/22}
+[Viewed February 29, 2012]"
+,annotation={
+	David Miller's view on hashed arrays of locks: used to really
+	like it, but time he saw an opportunity for this technique,
+	something else always proved superior.  Partitioning or RCU.  ;-)
+}
 }
 
 @conference{ThomasEHart2006a
@@ -1309,10 +1350,10 @@ Distributed Processing Symposium"
 ,note="Available:
 \url{http://www.rdrop.com/users/paulmck/RCU/hart_ipdps06.pdf}
 [Viewed April 28, 2008]"
-,annotation="
+,annotation={
 	Compares QSBR, HPBR, EBR, and lock-free reference counting.
 	http://www.cs.toronto.edu/~tomhart/perflab/ipdps06.tgz
-"
+}
 }
 
 @unpublished{NickPiggin2006radixtree
@@ -1324,9 +1365,9 @@ Distributed Processing Symposium"
 ,note="Available:
 \url{http://lkml.org/lkml/2006/6/20/238}
 [Viewed March 25, 2008]"
-,annotation="
+,annotation={
 	RCU-protected radix tree.
-"
+}
 }
 
 @Conference{PaulEMcKenney2006b
@@ -1341,9 +1382,9 @@ Suparna Bhattacharya"
 \url{http://www.linuxsymposium.org/2006/view_abstract.php?content_key=184}
 \url{http://www.rdrop.com/users/paulmck/RCU/OLSrtRCU.2006.08.11a.pdf}
 [Viewed January 1, 2007]"
-,annotation="
+,annotation={
 	Described how to improve the -rt implementation of realtime RCU.
-"
+}
 }
 
 @unpublished{WikipediaRCU
@@ -1354,12 +1395,11 @@ Canis Rufus and Zoicon5 and Anome and Hal Eisen"
 ,month="July"
 ,day="8"
 ,year="2006"
-,note="Available:
-\url{http://en.wikipedia.org/wiki/Read-copy-update}
-[Viewed August 21, 2006]"
-,annotation="
+,note="\url{http://en.wikipedia.org/wiki/Read-copy-update}"
+,annotation={
 	Wikipedia RCU page as of July 8 2006.
-"
+	[Viewed August 21, 2006]
+}
 }
 
 @Conference{NickPiggin2006LocklessPageCache
@@ -1372,9 +1412,9 @@ Canis Rufus and Zoicon5 and Anome and Hal Eisen"
 ,note="Available:
 \url{http://www.linuxsymposium.org/2006/view_abstract.php?content_key=184}
 [Viewed January 11, 2009]"
-,annotation="
+,annotation={
 	Uses RCU-protected radix tree for a lockless page cache.
-"
+}
 }
 
 @unpublished{PaulEMcKenney2006c
@@ -1388,9 +1428,9 @@ Canis Rufus and Zoicon5 and Anome and Hal Eisen"
 Revised:
 \url{http://www.rdrop.com/users/paulmck/RCU/srcu.2007.01.14a.pdf}
 [Viewed August 21, 2006]"
-,annotation="
+,annotation={
 	LWN article introducing SRCU.
-"
+}
 }
 
 @unpublished{RobertOlsson2006a
@@ -1399,12 +1439,11 @@ Revised:
 ,month="August"
 ,day="18"
 ,year="2006"
-,note="Available:
-\url{http://www.nada.kth.se/~snilsson/publications/TRASH/trash.pdf}
-[Viewed March 4, 2011]"
-,annotation="
+,note="\url{http://www.nada.kth.se/~snilsson/publications/TRASH/trash.pdf}"
+,annotation={
 	RCU-protected dynamic trie-hash combination.
-"
+	[Viewed March 4, 2011]
+}
 }
 
 @unpublished{ChristophHellwig2006RCU2SRCU
@@ -1426,10 +1465,10 @@ Revised:
 ,note="Available:
 \url{http://www.rdrop.com/users/paulmck/RCU/linuxusage.html}
 [Viewed January 14, 2007]"
-,annotation="
+,annotation={
 	Paul McKenney's RCU page showing graphs plotting Linux-kernel
 	usage of RCU.
-"
+}
 }
 
 @unpublished{PaulEMcKenneyRCUusageRawDataPage
@@ -1440,10 +1479,10 @@ Revised:
 ,note="Available:
 \url{http://www.rdrop.com/users/paulmck/RCU/linuxusage/rculocktab.html}
 [Viewed January 14, 2007]"
-,annotation="
+,annotation={
 	Paul McKenney's RCU page showing Linux usage of RCU in tabular
 	form, with links to corresponding cscope databases.
-"
+}
 }
 
 @unpublished{GauthamShenoy2006RCUrwlock
@@ -1455,13 +1494,13 @@ Revised:
 ,note="Available:
 \url{http://lkml.org/lkml/2006/10/26/73}
 [Viewed January 26, 2009]"
-,annotation="
+,annotation={
 	RCU-based reader-writer lock that allows readers to proceed with
 	no memory barriers or atomic instruction in absence of writers.
 	If writer do show up, readers must of course wait as required by
 	the semantics of reader-writer locking.  This is a recursive
 	lock.
-"
+}
 }
 
 @unpublished{JensAxboe2006SlowSRCU
@@ -1474,11 +1513,11 @@ Revised:
 ,note="Available:
 \url{http://lkml.org/lkml/2006/11/17/56}
 [Viewed May 28, 2007]"
-,annotation="
+,annotation={
 	SRCU's grace periods are too slow for Jens, even after a
 	factor-of-three speedup.
 	Sped-up version of SRCU at http://lkml.org/lkml/2006/11/17/359.
-"
+}
 }
 
 @unpublished{OlegNesterov2006QRCU
@@ -1491,10 +1530,10 @@ Revised:
 ,note="Available:
 \url{http://lkml.org/lkml/2006/11/19/69}
 [Viewed May 28, 2007]"
-,annotation="
+,annotation={
 	First cut of QRCU.  Expanded/corrected versions followed.
 	Used to be OlegNesterov2007QRCU, now time-corrected.
-"
+}
 }
 
 @unpublished{OlegNesterov2006aQRCU
@@ -1506,10 +1545,10 @@ Revised:
 ,note="Available:
 \url{http://lkml.org/lkml/2006/11/29/330}
 [Viewed November 26, 2008]"
-,annotation="
+,annotation={
 	Expanded/corrected version of QRCU.
 	Used to be OlegNesterov2007aQRCU, now time-corrected.
-"
+}
 }
 
 @unpublished{EvgeniyPolyakov2006RCUslowdown
@@ -1521,10 +1560,10 @@ Revised:
 ,note="Available:
 \url{http://www.ioremap.net/node/41}
 [Viewed October 28, 2008]"
-,annotation="
+,annotation={
 	Using RCU as a pure delay leads to a 2.5x slowdown in skbs in
 	the Linux kernel.
-"
+}
 }
 
 @inproceedings{ChrisMatthews2006ClusteredObjectsRCU
@@ -1541,7 +1580,8 @@ Revised:
 ,annotation={
 	Uses K42's RCU-like functionality to manage clustered-object
 	lifetimes.
-}}
+}
+}
 
 @article{DilmaDaSilva2006K42
 ,author = {Silva, Dilma Da and Krieger, Orran and Wisniewski, Robert W. and Waterland, Amos and Tam, David and Baumann, Andrew}
@@ -1557,7 +1597,8 @@ Revised:
 ,address = {New York, NY, USA}
 ,annotation={
 	Describes relationship of K42 generations to RCU.
-}}
+}
+}
 
 # CoreyMinyard2007list_splice_rcu
 @unpublished{CoreyMinyard2007list:splice:rcu
@@ -1569,9 +1610,9 @@ Revised:
 ,note="Available:
 \url{http://lkml.org/lkml/2007/1/3/112}
 [Viewed May 28, 2007]"
-,annotation="
+,annotation={
 	Patch for list_splice_rcu().
-"
+}
 }
 
 @unpublished{PaulEMcKenney2007rcubarrier
@@ -1583,9 +1624,9 @@ Revised:
 ,note="Available:
 \url{http://lwn.net/Articles/217484/}
 [Viewed November 22, 2007]"
-,annotation="
+,annotation={
 	LWN article introducing the rcu_barrier() primitive.
-"
+}
 }
 
 @unpublished{PeterZijlstra2007SyncBarrier
@@ -1597,10 +1638,10 @@ Revised:
 ,note="Available:
 \url{http://lkml.org/lkml/2007/1/28/34}
 [Viewed March 27, 2008]"
-,annotation="
+,annotation={
 	RCU-like implementation for frequent updaters and rare readers(!).
 	Subsumed into QRCU.  Maybe...
-"
+}
 }
 
 @unpublished{PaulEMcKenney2007BoostRCU
@@ -1609,14 +1650,13 @@ Revised:
 ,month="February"
 ,day="5"
 ,year="2007"
-,note="Available:
-\url{http://lwn.net/Articles/220677/}
-Revised:
-\url{http://www.rdrop.com/users/paulmck/RCU/RCUbooststate.2007.04.16a.pdf}
-[Viewed September 7, 2007]"
-,annotation="
+,note="\url{http://lwn.net/Articles/220677/}"
+,annotation={
 	LWN article introducing RCU priority boosting.
-"
+	Revised:
+	http://www.rdrop.com/users/paulmck/RCU/RCUbooststate.2007.04.16a.pdf
+	[Viewed September 7, 2007]
+}
 }
 
 @unpublished{PaulMcKenney2007QRCUpatch
@@ -1628,9 +1668,9 @@ Revised:
 ,note="Available:
 \url{http://lkml.org/lkml/2007/2/25/18}
 [Viewed March 27, 2008]"
-,annotation="
+,annotation={
 	Patch for QRCU supplying lock-free fast path.
-"
+}
 }
 
 @article{JonathanAppavoo2007K42RCU
@@ -1647,7 +1687,8 @@ Revised:
 ,address = {New York, NY, USA}
 ,annotation={
 	Role of RCU in K42.
-}}
+}
+}
 
 @conference{RobertOlsson2007Trash
 ,Author="Robert Olsson and Stefan Nilsson"
@@ -1658,9 +1699,9 @@ Revised:
 ,note="Available:
 \url{http://ieeexplore.ieee.org/xpl/freeabs_all.jsp?arnumber=4281239}
 [Viewed October 1, 2010]"
-,annotation="
+,annotation={
 	RCU-protected dynamic trie-hash combination.
-"
+}
 }
 
 @conference{PeterZijlstra2007ConcurrentPagecacheRCU
@@ -1673,10 +1714,10 @@ Revised:
 ,note="Available:
 \url{http://ols.108.redhat.com/2007/Reprints/zijlstra-Reprint.pdf}
 [Viewed April 14, 2008]"
-,annotation="
+,annotation={
 	Page-cache modifications permitting RCU readers and concurrent
 	updates.
-"
+}
 }
 
 @unpublished{PaulEMcKenney2007whatisRCU
@@ -1701,11 +1742,11 @@ Revised:
 ,note="Available:
 \url{http://lwn.net/Articles/243851/}
 [Viewed September 8, 2007]"
-,annotation="
+,annotation={
 	LWN article describing Promela and spin, and also using Oleg
 	Nesterov's QRCU as an example (with Paul McKenney's fastpath).
 	Merged patch at: http://lkml.org/lkml/2007/2/25/18
-"
+}
 }
 
 @unpublished{PaulEMcKenney2007WG21DDOatomics
@@ -1714,12 +1755,12 @@ Revised:
 ,month="August"
 ,day="3"
 ,year="2007"
-,note="Preprint:
+,note="Available:
 \url{http://open-std.org/jtc1/sc22/wg21/docs/papers/2008/n2664.htm}
 [Viewed December 7, 2009]"
-,annotation="
+,annotation={
 	RCU for C++, parts 1 and 2.
-"
+}
 }
 
 @unpublished{PaulEMcKenney2007WG21DDOannotation
@@ -1728,12 +1769,12 @@ Revised:
 ,month="September"
 ,day="18"
 ,year="2008"
-,note="Preprint:
+,note="Available:
 \url{http://open-std.org/jtc1/sc22/wg21/docs/papers/2008/n2782.htm}
 [Viewed December 7, 2009]"
-,annotation="
+,annotation={
 	RCU for C++, part 2, updated many times.
-"
+}
 }
 
 @unpublished{PaulEMcKenney2007PreemptibleRCUPatch
@@ -1745,10 +1786,10 @@ Revised:
 ,note="Available:
 \url{http://lkml.org/lkml/2007/9/10/213}
 [Viewed October 25, 2007]"
-,annotation="
+,annotation={
 	Final patch for preemptable RCU to -rt.  (Later patches were
 	to mainline, eventually incorporated.)
-"
+}
 }
 
 @unpublished{PaulEMcKenney2007PreemptibleRCU
@@ -1760,9 +1801,9 @@ Revised:
 ,note="Available:
 \url{http://lwn.net/Articles/253651/}
 [Viewed October 25, 2007]"
-,annotation="
+,annotation={
 	LWN article describing the design of preemptible RCU.
-"
+}
 }
 
 @article{ThomasEHart2007a
@@ -1783,6 +1824,7 @@ Revised:
 }
 }
 
+# MathieuDesnoyers2007call_rcu_schedNeeded
 @unpublished{MathieuDesnoyers2007call:rcu:schedNeeded
 ,Author="Mathieu Desnoyers"
 ,Title="Re: [patch 1/2] {Linux} Kernel Markers - Support Multiple Probes"
@@ -1792,9 +1834,9 @@ Revised:
 ,note="Available:
 \url{http://lkml.org/lkml/2007/12/20/244}
 [Viewed March 27, 2008]"
-,annotation="
+,annotation={
 	Request for call_rcu_sched() and rcu_barrier_sched().
-"
+}
 }
 
 
@@ -1815,11 +1857,11 @@ Revised:
 ,note="Available:
 \url{http://lwn.net/Articles/262464/}
 [Viewed December 27, 2007]"
-,annotation="
+,annotation={
 	Lays out the three basic components of RCU: (1) publish-subscribe,
 	(2) wait for pre-existing readers to complete, and (2) maintain
 	multiple versions.
-"
+}
 }
 
 @unpublished{PaulEMcKenney2008WhatIsRCUUsage
@@ -1831,7 +1873,7 @@ Revised:
 ,note="Available:
 \url{http://lwn.net/Articles/263130/}
 [Viewed January 4, 2008]"
-,annotation="
+,annotation={
 	Lays out six uses of RCU:
 	1. RCU is a Reader-Writer Lock Replacement
 	2. RCU is a Restricted Reference-Counting Mechanism
@@ -1839,7 +1881,7 @@ Revised:
 	4. RCU is a Poor Man's Garbage Collector
 	5. RCU is a Way of Providing Existence Guarantees
 	6. RCU is a Way of Waiting for Things to Finish
-"
+}
 }
 
 @unpublished{PaulEMcKenney2008WhatIsRCUAPI
@@ -1851,10 +1893,10 @@ Revised:
 ,note="Available:
 \url{http://lwn.net/Articles/264090/}
 [Viewed January 10, 2008]"
-,annotation="
+,annotation={
 	Gives an overview of the Linux-kernel RCU API and a brief annotated RCU
 	bibliography.
-"
+}
 }
 
 #
@@ -1872,10 +1914,10 @@ Revised:
 ,note="Available:
 \url{http://lkml.org/lkml/2008/1/29/208}
 [Viewed March 27, 2008]"
-,annotation="
+,annotation={
 	Patch that prevents preemptible RCU from unnecessarily waking
 	up dynticks-idle CPUs.
-"
+}
 }
 
 @unpublished{PaulEMcKenney2008LKMLDependencyOrdering
@@ -1887,9 +1929,9 @@ Revised:
 ,note="Available:
 \url{http://lkml.org/lkml/2008/2/2/255}
 [Viewed October 18, 2008]"
-,annotation="
+,annotation={
 	Explanation of compilers violating dependency ordering.
-"
+}
 }
 
 @Conference{PaulEMcKenney2008Beijing
@@ -1916,24 +1958,26 @@ lot of {Linux} into your technology!!!"
 ,note="Available:
 \url{http://lwn.net/Articles/279077/}
 [Viewed April 24, 2008]"
-,annotation="
+,annotation={
 	Describes use of Promela and Spin to validate (and fix!) the
 	dynticks/RCU interface.
-"
+}
 }
 
 @article{DinakarGuniguntala2008IBMSysJ
 ,author="D. Guniguntala and P. E. McKenney and J. Triplett and J. Walpole"
 ,title="The read-copy-update mechanism for supporting real-time applications on shared-memory multiprocessor systems with {Linux}"
 ,Year="2008"
-,Month="April-June"
+,Month="May"
 ,journal="IBM Systems Journal"
 ,volume="47"
 ,number="2"
 ,pages="221-236"
-,annotation="
+,annotation={
 	RCU, realtime RCU, sleepable RCU, performance.
-"
+	http://www.research.ibm.com/journal/sj/472/guniguntala.pdf
+	[Viewed April 24, 2008]
+}
 }
 
 @unpublished{LaiJiangshan2008NewClassicAlgorithm
@@ -1945,11 +1989,11 @@ lot of {Linux} into your technology!!!"
 ,note="Available:
 \url{http://lkml.org/lkml/2008/6/2/539}
 [Viewed December 10, 2008]"
-,annotation="
+,annotation={
 	Updated RCU classic algorithm.  Introduced multi-tailed list
 	for RCU callbacks and also pulling common code into
 	__call_rcu().
-"
+}
 }
 
 @article{PaulEMcKenney2008RCUOSR
@@ -1966,6 +2010,7 @@ lot of {Linux} into your technology!!!"
 ,address="New York, NY, USA"
 ,annotation={
 	Linux changed RCU to a far greater degree than RCU has changed Linux.
+	http://portal.acm.org/citation.cfm?doid=1400097.1400099
 }
 }
 
@@ -1978,10 +2023,10 @@ lot of {Linux} into your technology!!!"
 ,note="Available:
 \url{http://lkml.org/lkml/2008/8/21/336}
 [Viewed December 8, 2008]"
-,annotation="
+,annotation={
 	State-based RCU.  One key thing that this patch does is to
 	separate the dynticks handling of NMIs and IRQs.
-"
+}
 }
 
 @unpublished{ManfredSpraul2008dyntickIRQNMI
@@ -1993,12 +2038,13 @@ lot of {Linux} into your technology!!!"
 ,note="Available:
 \url{http://lkml.org/lkml/2008/9/6/86}
 [Viewed December 8, 2008]"
-,annotation="
+,annotation={
 	Manfred notes a fix required to my attempt to separate irq
 	and NMI processing for hierarchical RCU's dynticks interface.
-"
+}
 }
 
+# Was PaulEMcKenney2011cyclicRCU
 @techreport{PaulEMcKenney2008cyclicRCU
 ,author="Paul E. McKenney"
 ,title="Efficient Support of Consistent Cyclic Search With Read-Copy Update"
@@ -2008,11 +2054,11 @@ lot of {Linux} into your technology!!!"
 ,number="US Patent 7,426,511"
 ,month="September"
 ,pages="23"
-,annotation="
+,annotation={
 	Maintains an additional level of indirection to allow
 	readers to confine themselves to the desired snapshot of the
 	data structure.  Only permits one update at a time.
-"
+}
 }
 
 @unpublished{PaulEMcKenney2008HierarchicalRCU
@@ -2021,13 +2067,12 @@ lot of {Linux} into your technology!!!"
 ,month="November"
 ,day="3"
 ,year="2008"
-,note="Available:
-\url{http://lwn.net/Articles/305782/}
-[Viewed November 6, 2008]"
-,annotation="
+,note="\url{http://lwn.net/Articles/305782/}"
+,annotation={
 	RCU with combining-tree-based grace-period detection,
 	permitting it to handle thousands of CPUs.
-"
+	[Viewed November 6, 2008]
+}
 }
 
 @unpublished{PaulEMcKenney2009BloatwatchRCU
@@ -2039,10 +2084,10 @@ lot of {Linux} into your technology!!!"
 ,note="Available:
 \url{http://lkml.org/lkml/2009/1/14/449}
 [Viewed January 15, 2009]"
-,annotation="
+,annotation={
 	Small-footprint implementation of RCU for uniprocessor
 	embedded applications -- and also for exposition purposes.
-"
+}
 }
 
 @conference{PaulEMcKenney2009MaliciousURCU
@@ -2055,9 +2100,9 @@ lot of {Linux} into your technology!!!"
 ,note="Available:
 \url{http://www.rdrop.com/users/paulmck/RCU/urcutorture.2009.01.22a.pdf}
 [Viewed February 2, 2009]"
-,annotation="
+,annotation={
 	Realtime RCU and torture-testing RCU uses.
-"
+}
 }
 
 @unpublished{MathieuDesnoyers2009URCU
@@ -2066,16 +2111,14 @@ lot of {Linux} into your technology!!!"
 ,month="February"
 ,day="5"
 ,year="2009"
-,note="Available:
-\url{http://lkml.org/lkml/2009/2/5/572}
-\url{http://lttng.org/urcu}
-[Viewed February 20, 2009]"
-,annotation="
+,note="\url{http://lttng.org/urcu}"
+,annotation={
 	Mathieu Desnoyers's user-space RCU implementation.
 	git://lttng.org/userspace-rcu.git
 	http://lttng.org/cgi-bin/gitweb.cgi?p=userspace-rcu.git
 	http://lttng.org/urcu
-"
+	http://lkml.org/lkml/2009/2/5/572
+}
 }
 
 @unpublished{PaulEMcKenney2009LWNBloatWatchRCU
@@ -2087,9 +2130,24 @@ lot of {Linux} into your technology!!!"
 ,note="Available:
 \url{http://lwn.net/Articles/323929/}
 [Viewed March 20, 2009]"
-,annotation="
+,annotation={
 	Uniprocessor assumptions allow simplified RCU implementation.
-"
+}
+}
+
+@unpublished{EvgeniyPolyakov2009EllipticsNetwork
+,Author="Evgeniy Polyakov"
+,Title="The Elliptics Network"
+,month="April"
+,day="17"
+,year="2009"
+,note="Available:
+\url{http://www.ioremap.net/projects/elliptics}
+[Viewed April 30, 2009]"
+,annotation={
+	Distributed hash table with transactions, using elliptic
+	hash functions to distribute data.
+}
 }
 
 @unpublished{PaulEMcKenney2009expeditedRCU
@@ -2101,9 +2159,9 @@ lot of {Linux} into your technology!!!"
 ,note="Available:
 \url{http://lkml.org/lkml/2009/6/25/306}
 [Viewed August 16, 2009]"
-,annotation="
+,annotation={
 	First posting of expedited RCU to be accepted into -tip.
-"
+}
 }
 
 @unpublished{PaulEMcKenney2009fastRTRCU
@@ -2115,21 +2173,21 @@ lot of {Linux} into your technology!!!"
 ,note="Available:
 \url{http://lkml.org/lkml/2009/7/23/294}
 [Viewed August 15, 2009]"
-,annotation="
+,annotation={
 	First posting of simple and fast preemptable RCU.
-"
+}
 }
 
-@InProceedings{JoshTriplett2009RPHash
+@unpublished{JoshTriplett2009RPHash
 ,Author="Josh Triplett"
 ,Title="Scalable concurrent hash tables via relativistic programming"
 ,month="September"
 ,year="2009"
-,booktitle="Linux Plumbers Conference 2009"
-,annotation="
+,note="Linux Plumbers Conference presentation"
+,annotation={
 	RP fun with hash tables.
-	See also JoshTriplett2010RPHash
-"
+	Superseded by JoshTriplett2010RPHash
+}
 }
 
 @phdthesis{MathieuDesnoyersPhD
@@ -2154,9 +2212,9 @@ lot of {Linux} into your technology!!!"
 ,note="Available:
 \url{http://wiki.cs.pdx.edu/rp/}
 [Viewed December 9, 2009]"
-,annotation="
+,annotation={
 	Main Relativistic Programming Wiki.
-"
+}
 }
 
 @conference{PaulEMcKenney2009DeterministicRCU
@@ -2180,9 +2238,9 @@ lot of {Linux} into your technology!!!"
 ,note="Available:
 \url{http://paulmck.livejournal.com/14639.html}
 [Viewed June 4, 2010]"
-,annotation="
+,annotation={
 	Day-one bug in Tree RCU that took forever to track down.
-"
+}
 }
 
 @unpublished{MathieuDesnoyers2009defer:rcu
@@ -2193,10 +2251,10 @@ lot of {Linux} into your technology!!!"
 ,note="Available:
 \url{http://lkml.org/lkml/2009/10/18/129}
 [Viewed December 29, 2009]"
-,annotation="
+,annotation={
 	Mathieu proposed defer_rcu() with fixed-size per-thread pool
 	of RCU callbacks.
-"
+}
 }
 
 @unpublished{MathieuDesnoyers2009VerifPrePub
@@ -2205,10 +2263,10 @@ lot of {Linux} into your technology!!!"
 ,month="December"
 ,year="2009"
 ,note="Submitted to IEEE TPDS"
-,annotation="
+,annotation={
 	OOMem model for Mathieu's user-level RCU mechanical proof of
 	correctness.
-"
+}
 }
 
 @unpublished{MathieuDesnoyers2009URCUPrePub
@@ -2216,15 +2274,15 @@ lot of {Linux} into your technology!!!"
 ,Title="User-Level Implementations of Read-Copy Update"
 ,month="December"
 ,year="2010"
-,url=\url{http://www.computer.org/csdl/trans/td/2012/02/ttd2012020375-abs.html}
-,annotation="
+,url={\url{http://www.computer.org/csdl/trans/td/2012/02/ttd2012020375-abs.html}}
+,annotation={
 	RCU overview, desiderata, semi-formal semantics, user-level RCU
 	usage scenarios, three classes of RCU implementation, wait-free
 	RCU updates, RCU grace-period batching, update overhead,
 	http://www.rdrop.com/users/paulmck/RCU/urcu-main-accepted.2011.08.30a.pdf
 	http://www.rdrop.com/users/paulmck/RCU/urcu-supp-accepted.2011.08.30a.pdf
 	Superseded by MathieuDesnoyers2012URCU.
-"
+}
 }
 
 @inproceedings{HariKannan2009DynamicAnalysisRCU
@@ -2240,7 +2298,8 @@ lot of {Linux} into your technology!!!"
 ,address = {New York, NY, USA}
 ,annotation={
 	Uses RCU to protect metadata used in dynamic analysis.
-}}
+}
+}
 
 @conference{PaulEMcKenney2010SimpleOptRCU
 ,Author="Paul E. McKenney"
@@ -2252,10 +2311,10 @@ lot of {Linux} into your technology!!!"
 ,note="Available:
 \url{http://www.rdrop.com/users/paulmck/RCU/SimplicityThruOptimization.2010.01.21f.pdf}
 [Viewed October 10, 2010]"
-,annotation="
+,annotation={
 	TREE_PREEMPT_RCU optimizations greatly simplified the old
 	PREEMPT_RCU implementation.
-"
+}
 }
 
 @unpublished{PaulEMcKenney2010LockdepRCU
@@ -2264,12 +2323,11 @@ lot of {Linux} into your technology!!!"
 ,month="February"
 ,year="2010"
 ,day="1"
-,note="Available:
-\url{https://lwn.net/Articles/371986/}
-[Viewed June 4, 2010]"
-,annotation="
+,note="\url{https://lwn.net/Articles/371986/}"
+,annotation={
 	CONFIG_PROVE_RCU, or at least an early version.
-"
+	[Viewed June 4, 2010]
+}
 }
 
 @unpublished{AviKivity2010KVM2RCU
@@ -2280,10 +2338,10 @@ lot of {Linux} into your technology!!!"
 ,note="Available:
 \url{http://www.mail-archive.com/kvm@vger.kernel.org/msg28640.html}
 [Viewed March 20, 2010]"
-,annotation="
+,annotation={
 	Use of RCU permits KVM to increase the size of guest OSes from
 	16 CPUs to 64 CPUs.
-"
+}
 }
 
 @unpublished{HerbertXu2010RCUResizeHash
@@ -2297,7 +2355,19 @@ lot of {Linux} into your technology!!!"
 ,annotation={
 	Use a pair of list_head structures to support RCU-protected
 	resizable hash tables.
-}}
+}
+}
+
+@mastersthesis{AbhinavDuggal2010Masters
+,author="Abhinav Duggal"
+,title="Stopping Data Races Using Redflag"
+,school="Stony Brook University"
+,year="2010"
+,annotation={
+	Data-race detector incorporating RCU.
+	http://www.filesystems.org/docs/abhinav-thesis/abhinav_thesis.pdf
+}
+}
 
 @article{JoshTriplett2010RPHash
 ,author="Josh Triplett and Paul E. McKenney and Jonathan Walpole"
@@ -2310,7 +2380,8 @@ lot of {Linux} into your technology!!!"
 ,annotation={
 	RP fun with hash tables.
 	http://portal.acm.org/citation.cfm?id=1842733.1842750
-}}
+}
+}
 
 @unpublished{PaulEMcKenney2010RCUAPI
 ,Author="Paul E. McKenney"
@@ -2318,12 +2389,11 @@ lot of {Linux} into your technology!!!"
 ,month="December"
 ,day="8"
 ,year="2010"
-,note="Available:
-\url{http://lwn.net/Articles/418853/}
-[Viewed December 8, 2010]"
-,annotation="
+,note="\url{http://lwn.net/Articles/418853/}"
+,annotation={
 	Includes updated software-engineering features.
-"
+	[Viewed December 8, 2010]
+}
 }
 
 @mastersthesis{AndrejPodzimek2010masters
@@ -2338,7 +2408,8 @@ lot of {Linux} into your technology!!!"
 	Reviews RCU implementations and creates a few for OpenSolaris.
 	Drives quiescent-state detection from RCU read-side primitives,
 	in a manner roughly similar to that of Jim Houston.
-}}
+}
+}
 
 @unpublished{LinusTorvalds2011Linux2:6:38:rc1:NPigginVFS
 ,Author="Linus Torvalds"
@@ -2358,7 +2429,8 @@ lot of {Linux} into your technology!!!"
 	of the most expensive parts of path component lookup, which was the
 	d_lock on every component lookup. So I'm seeing improvements of 30-50%
 	on some seriously pathname-lookup intensive loads."
-}}
+}
+}
 
 @techreport{JoshTriplett2011RPScalableCorrectOrdering
 ,author = {Josh Triplett and Philip W. Howard and Paul E. McKenney and Jonathan Walpole}
@@ -2392,12 +2464,12 @@ lot of {Linux} into your technology!!!"
 ,number="US Patent 7,953,778"
 ,month="May"
 ,pages="34"
-,annotation="
+,annotation={
 	Maintains an array of generation numbers to track in-flight
 	updates and keeps an additional level of indirection to allow
 	readers to confine themselves to the desired snapshot of the
 	data structure.
-"
+}
 }
 
 @inproceedings{Triplett:2011:RPHash
@@ -2408,7 +2480,7 @@ lot of {Linux} into your technology!!!"
 ,year = {2011}
 ,pages = {145--158}
 ,numpages = {14}
-,url={http://www.usenix.org/event/atc11/tech/final_files/atc11_proceedings.pdf}
+,url={http://www.usenix.org/event/atc11/tech/final_files/Triplett.pdf}
 ,publisher = {The USENIX Association}
 ,address = {Portland, OR USA}
 }
@@ -2419,27 +2491,58 @@ lot of {Linux} into your technology!!!"
 ,month="July"
 ,day="27"
 ,year="2011"
-,note="Available:
-\url{http://lwn.net/Articles/453002/}
-[Viewed July 27, 2011]"
-,annotation="
+,note="\url{http://lwn.net/Articles/453002/}"
+,annotation={
 	Analysis of the RCU trainwreck in Linux kernel 3.0.
-"
+	[Viewed July 27, 2011]
+}
 }
 
 @unpublished{NeilBrown2011MeetTheLockers
 ,Author="Neil Brown"
-,Title="Meet the Lockers"
+,Title="Meet the {Lockers}"
 ,month="August"
 ,day="3"
 ,year="2011"
 ,note="Available:
 \url{http://lwn.net/Articles/453685/}
 [Viewed September 2, 2011]"
-,annotation="
+,annotation={
 	The Locker family as an analogy for locking, reference counting,
 	RCU, and seqlock.
-"
+}
+}
+
+@inproceedings{Seyster:2011:RFA:2075416.2075425
+,author = {Seyster, Justin and Radhakrishnan, Prabakar and Katoch, Samriti and Duggal, Abhinav and Stoller, Scott D. and Zadok, Erez}
+,title = {Redflag: a framework for analysis of Kernel-level concurrency}
+,booktitle = {Proceedings of the 11th international conference on Algorithms and architectures for parallel processing - Volume Part I}
+,series = {ICA3PP'11}
+,year = {2011}
+,isbn = {978-3-642-24649-4}
+,location = {Melbourne, Australia}
+,pages = {66--79}
+,numpages = {14}
+,url = {http://dl.acm.org/citation.cfm?id=2075416.2075425}
+,acmid = {2075425}
+,publisher = {Springer-Verlag}
+,address = {Berlin, Heidelberg}
+}
+
+@phdthesis{JoshTriplettPhD
+,author="Josh Triplett"
+,title="Relativistic Causal Ordering: A Memory Model for Scalable Concurrent Data Structures"
+,school="Portland State University"
+,year="2012"
+,annotation={
+	RCU-protected hash tables, barriers vs. read-side traversal order.
+	.
+	If the updater is making changes in the opposite direction from
+	the read-side traveral order, the updater need only execute a
+	memory-barrier instruction, but if in the same direction, the
+	updater needs to wait for a grace period between the individual
+	updates.
+}
 }
 
 @article{MathieuDesnoyers2012URCU
@@ -2459,5 +2562,150 @@ lot of {Linux} into your technology!!!"
 	RCU updates, RCU grace-period batching, update overhead,
 	http://www.rdrop.com/users/paulmck/RCU/urcu-main-accepted.2011.08.30a.pdf
 	http://www.rdrop.com/users/paulmck/RCU/urcu-supp-accepted.2011.08.30a.pdf
+	http://www.computer.org/cms/Computer.org/dl/trans/td/2012/02/extras/ttd2012020375s.pdf
+}
+}
+
+@inproceedings{AustinClements2012RCULinux:mmapsem
+,author = {Austin Clements and Frans Kaashoek and Nickolai Zeldovich}
+,title = {Scalable Address Spaces Using {RCU} Balanced Trees}
+,booktitle = {Architectural Support for Programming Languages and Operating Systems (ASPLOS 2012)}
+,month = {March}
+,year = {2012}
+,pages = {199--210}
+,numpages = {12}
+,publisher = {ACM}
+,address = {London, UK}
+,url="http://people.csail.mit.edu/nickolai/papers/clements-bonsai.pdf"
+}
+
+@unpublished{PaulEMcKenney2012ELCbattery
+,Author="Paul E. McKenney"
+,Title="Making {RCU} Safe For Battery-Powered Devices"
+,month="February"
+,day="15"
+,year="2012"
+,note="Available:
+\url{http://www.rdrop.com/users/paulmck/RCU/RCUdynticks.2012.02.15b.pdf}
+[Viewed March 1, 2012]"
+,annotation={
+	RCU_FAST_NO_HZ, round 2.
+}
+}
+
+@article{GuillermoVigueras2012RCUCrowd
+,author = {Vigueras, Guillermo and Ordu\~{n}a, Juan M. and Lozano, Miguel}
+,day = {25}
+,doi = {10.1007/s11227-012-0766-x}
+,issn = {0920-8542}
+,journal = {The Journal of Supercomputing}
+,keywords = {linux, simulation}
+,month = apr
+,posted-at = {2012-05-03 09:12:04}
+,priority = {2}
+,title = {{A Read-Copy Update based parallel server for distributed crowd simulations}}
+,url = {http://dx.doi.org/10.1007/s11227-012-0766-x}
+,year = {2012}
+}
+
+
+@unpublished{JonCorbet2012ACCESS:ONCE
+,Author="Jon Corbet"
+,Title="{ACCESS\_ONCE()}"
+,month="August"
+,day="1"
+,year="2012"
+,note="\url{http://lwn.net/Articles/508991/}"
+,annotation={
+	A couple of simple specific compiler optimizations that motivate
+	ACCESS_ONCE().
+}
+}
+
+@unpublished{AlexeyGotsman2012VerifyGraceExtended
+,Author="Alexey Gotsman and Noam Rinetzky and Hongseok Yang"
+,Title="Verifying Highly Concurrent Algorithms with Grace (extended version)"
+,month="July"
+,day="10"
+,year="2012"
+,note="\url{http://software.imdea.org/~gotsman/papers/recycling-esop13-ext.pdf}"
+,annotation={
+	Separation-logic formulation of RCU uses.
+}
+}
+
+@unpublished{PaulMcKenney2012RCUUsage
+,Author="Paul E. McKenney and Silas Boyd-Wickizer and Jonathan Walpole"
+,Title="{RCU} Usage In the Linux Kernel: One Decade Later"
+,month="September"
+,day="17"
+,year="2012"
+,url=http://rdrop.com/users/paulmck/techreports/survey.2012.09.17a.pdf
+,note="Technical report paulmck.2012.09.17"
+,annotation={
+	Overview of the first variant of no-CBs CPUs for RCU.
+}
+}
+
+@unpublished{JonCorbet2012NOCB
+,Author="Jon Corbet"
+,Title="Relocating RCU callbacks"
+,month="October"
+,day="31"
+,year="2012"
+,note="\url{http://lwn.net/Articles/522262/}"
+,annotation={
+	Overview of the first variant of no-CBs CPUs for RCU.
+}
+}
+
+@phdthesis{JustinSeyster2012PhD
+,author="Justin Seyster"
+,title="Runtime Verification of Kernel-Level Concurrency Using Compiler-Based Instrumentation"
+,school="Stony Brook University"
+,year="2012"
+,annotation={
+	Looking for data races, including those involving RCU.
+	Proposal:
+	http://www.fsl.cs.sunysb.edu/docs/jseyster-proposal/redflag.pdf
+	Dissertation:
+	http://www.fsl.cs.sunysb.edu/docs/jseyster-dissertation/redflag.pdf
+}
+}
+
+@unpublished{PaulEMcKenney2013RCUUsage
+,Author="Paul E. McKenney and Silas Boyd-Wickizer and Jonathan Walpole"
+,Title="{RCU} Usage in the {Linux} Kernel: One Decade Later"
+,month="February"
+,day="24"
+,year="2013"
+,note="\url{http://rdrop.com/users/paulmck/techreports/RCUUsage.2013.02.24a.pdf}"
+,annotation={
+	Usage of RCU within the Linux kernel.
+}
+}
+
+@inproceedings{AlexeyGotsman2013ESOPRCU
+,author = {Alexey Gotsman and Noam Rinetzky and Hongseok Yang}
+,title = {Verifying concurrent memory reclamation algorithms with grace}
+,booktitle = {ESOP'13: European Symposium on Programming}
+,year = {2013}
+,pages = {249--269}
+,publisher = {Springer}
+,address = {Rome, Italy}
+,annotation={
+	http://software.imdea.org/~gotsman/papers/recycling-esop13.pdf
+}
+}
+
+@unpublished{PaulEMcKenney2013NoTinyPreempt
+,Author="Paul E. McKenney"
+,Title="Simplifying RCU"
+,month="March"
+,day="6"
+,year="2013"
+,note="\url{http://lwn.net/Articles/541037/}"
+,annotation={
+	Getting rid of TINY_PREEMPT_RCU.
 }
 }
diff --git a/Documentation/RCU/rcubarrier.txt b/Documentation/RCU/rcubarrier.txt
index 2e319d1b9ef2..b10cfe711e68 100644
--- a/Documentation/RCU/rcubarrier.txt
+++ b/Documentation/RCU/rcubarrier.txt
@@ -70,10 +70,14 @@ in realtime kernels in order to avoid excessive scheduling latencies.
 
 rcu_barrier()
 
-We instead need the rcu_barrier() primitive. This primitive is similar
-to synchronize_rcu(), but instead of waiting solely for a grace
-period to elapse, it also waits for all outstanding RCU callbacks to
-complete. Pseudo-code using rcu_barrier() is as follows:
+We instead need the rcu_barrier() primitive.  Rather than waiting for
+a grace period to elapse, rcu_barrier() waits for all outstanding RCU
+callbacks to complete.  Please note that rcu_barrier() does -not- imply
+synchronize_rcu(), in particular, if there are no RCU callbacks queued
+anywhere, rcu_barrier() is within its rights to return immediately,
+without waiting for a grace period to elapse.
+
+Pseudo-code using rcu_barrier() is as follows:
 
    1. Prevent any new RCU callbacks from being posted.
    2. Execute rcu_barrier().
diff --git a/Documentation/RCU/torture.txt b/Documentation/RCU/torture.txt
index d8a502387397..dac02a6219b1 100644
--- a/Documentation/RCU/torture.txt
+++ b/Documentation/RCU/torture.txt
@@ -42,6 +42,16 @@ fqs_holdoff	Holdoff time (in microseconds) between consecutive calls
 fqs_stutter	Wait time (in seconds) between consecutive bursts
 		of calls to force_quiescent_state().
 
+gp_normal	Make the fake writers use normal synchronous grace-period
+		primitives.
+
+gp_exp		Make the fake writers use expedited synchronous grace-period
+		primitives.  If both gp_normal and gp_exp are set, or
+		if neither gp_normal nor gp_exp are set, then randomly
+		choose the primitive so that about 50% are normal and
+		50% expedited.  By default, neither are set, which
+		gives best overall test coverage.
+
 irqreader	Says to invoke RCU readers from irq level.  This is currently
 		done via timers.  Defaults to "1" for variants of RCU that
 		permit this.  (Or, more accurately, variants of RCU that do
diff --git a/Documentation/SubmittingPatches b/Documentation/SubmittingPatches
index 6e97e73d87b5..26b1e31d5a13 100644
--- a/Documentation/SubmittingPatches
+++ b/Documentation/SubmittingPatches
@@ -109,6 +109,16 @@ probably didn't even receive earlier versions of the patch.
 If the patch fixes a logged bug entry, refer to that bug entry by
 number and URL.
 
+If you want to refer to a specific commit, don't just refer to the
+SHA-1 ID of the commit. Please also include the oneline summary of
+the commit, to make it easier for reviewers to know what it is about.
+Example:
+
+	Commit e21d2170f36602ae2708 ("video: remove unnecessary
+	platform_set_drvdata()") removed the unnecessary
+	platform_set_drvdata(), but left the variable "dev" unused,
+	delete it.
+
 
 3) Separate your changes.
 
diff --git a/Documentation/acpi/dsdt-override.txt b/Documentation/acpi/dsdt-override.txt
index febbb1ba4d23..784841caa6e6 100644
--- a/Documentation/acpi/dsdt-override.txt
+++ b/Documentation/acpi/dsdt-override.txt
@@ -4,4 +4,4 @@ CONFIG_ACPI_CUSTOM_DSDT builds the image into the kernel.
 
 When to use this method is described in detail on the
 Linux/ACPI home page:
-http://www.lesswatts.org/projects/acpi/overridingDSDT.php
+https://01.org/linux-acpi/documentation/overriding-dsdt
diff --git a/Documentation/acpi/enumeration.txt b/Documentation/acpi/enumeration.txt
index d9be7a97dff3..aca4e69121b7 100644
--- a/Documentation/acpi/enumeration.txt
+++ b/Documentation/acpi/enumeration.txt
@@ -207,7 +207,7 @@ passing those. One idea is to return this in _DSM method like:
 			Return (Local0)
 		}
 
-Then the at25 SPI driver can get this configation by calling _DSM on its
+Then the at25 SPI driver can get this configuration by calling _DSM on its
 ACPI handle like:
 
 	struct acpi_buffer output = { ACPI_ALLOCATE_BUFFER, NULL };
@@ -228,19 +228,9 @@ ACPI handle like:
 I2C serial bus support
 ~~~~~~~~~~~~~~~~~~~~~~
 The slaves behind I2C bus controller only need to add the ACPI IDs like
-with the platform and SPI drivers. However the I2C bus controller driver
-needs to call acpi_i2c_register_devices() after it has added the adapter.
-
-An I2C bus (controller) driver does:
-
-	...
-	ret = i2c_add_numbered_adapter(adapter);
-	if (ret)
-		/* handle error */
-
-	of_i2c_register_devices(adapter);
-	/* Enumerate the slave devices behind this bus via ACPI */
-	acpi_i2c_register_devices(adapter);
+with the platform and SPI drivers. The I2C core automatically enumerates
+any slave devices behind the controller device once the adapter is
+registered.
 
 Below is an example of how to add ACPI support to the existing mpu3050
 input driver:
diff --git a/Documentation/aoe/udev.txt b/Documentation/aoe/udev.txt
index 8686e789542e..1f06daf03f5b 100644
--- a/Documentation/aoe/udev.txt
+++ b/Documentation/aoe/udev.txt
@@ -23,4 +23,4 @@ SUBSYSTEM=="aoe", KERNEL=="revalidate",	NAME="etherd/%k", GROUP="disk", MODE="02
 SUBSYSTEM=="aoe", KERNEL=="flush",	NAME="etherd/%k", GROUP="disk", MODE="0220"
 
 # aoe block devices     
-KERNEL=="etherd*",       NAME="%k", GROUP="disk"
+KERNEL=="etherd*",       GROUP="disk"
diff --git a/Documentation/arm/Booting b/Documentation/arm/Booting
index 0c1f475fdf36..371814a36719 100644
--- a/Documentation/arm/Booting
+++ b/Documentation/arm/Booting
@@ -18,7 +18,8 @@ following:
 2. Initialise one serial port.
 3. Detect the machine type.
 4. Setup the kernel tagged list.
-5. Call the kernel image.
+5. Load initramfs.
+6. Call the kernel image.
 
 
 1. Setup and initialise RAM
@@ -120,12 +121,27 @@ tagged list.
 The boot loader must pass at a minimum the size and location of the
 system memory, and the root filesystem location.  The dtb must be
 placed in a region of memory where the kernel decompressor will not
-overwrite it.  The recommended placement is in the first 16KiB of RAM
-with the caveat that it may not be located at physical address 0 since
-the kernel interprets a value of 0 in r2 to mean neither a tagged list
-nor a dtb were passed.
+overwrite it, whilst remaining within the region which will be covered
+by the kernel's low-memory mapping.
 
-5. Calling the kernel image
+A safe location is just above the 128MiB boundary from start of RAM.
+
+5. Load initramfs.
+------------------
+
+Existing boot loaders:		OPTIONAL
+New boot loaders:		OPTIONAL
+
+If an initramfs is in use then, as with the dtb, it must be placed in
+a region of memory where the kernel decompressor will not overwrite it
+while also with the region which will be covered by the kernel's
+low-memory mapping.
+
+A safe location is just above the device tree blob which itself will
+be loaded just above the 128MiB boundary from the start of RAM as
+recommended above.
+
+6. Calling the kernel image
 ---------------------------
 
 Existing boot loaders:		MANDATORY
@@ -136,11 +152,17 @@ is stored in flash, and is linked correctly to be run from flash,
 then it is legal for the boot loader to call the zImage in flash
 directly.
 
-The zImage may also be placed in system RAM (at any location) and
-called there.  Note that the kernel uses 16K of RAM below the image
-to store page tables.  The recommended placement is 32KiB into RAM.
+The zImage may also be placed in system RAM and called there.  The
+kernel should be placed in the first 128MiB of RAM.  It is recommended
+that it is loaded above 32MiB in order to avoid the need to relocate
+prior to decompression, which will make the boot process slightly
+faster.
+
+When booting a raw (non-zImage) kernel the constraints are tighter.
+In this case the kernel must be loaded at an offset into system equal
+to TEXT_OFFSET - PAGE_OFFSET.
 
-In either case, the following conditions must be met:
+In any case, the following conditions must be met:
 
 - Quiesce all DMA capable devices so that memory does not get
   corrupted by bogus network packets or disk data. This will save
diff --git a/Documentation/arm/OMAP/omap_pm b/Documentation/arm/OMAP/omap_pm
index 9012bb039094..4ae915a9f899 100644
--- a/Documentation/arm/OMAP/omap_pm
+++ b/Documentation/arm/OMAP/omap_pm
@@ -78,7 +78,7 @@ to NULL.  Drivers should use the following idiom:
 The most common usage of these functions will probably be to specify
 the maximum time from when an interrupt occurs, to when the device
 becomes accessible.  To accomplish this, driver writers should use the
-set_max_mpu_wakeup_lat() function to to constrain the MPU wakeup
+set_max_mpu_wakeup_lat() function to constrain the MPU wakeup
 latency, and the set_max_dev_wakeup_lat() function to constrain the
 device wakeup latency (from clk_enable() to accessibility).  For
 example,
diff --git a/Documentation/arm/kernel_mode_neon.txt b/Documentation/arm/kernel_mode_neon.txt
new file mode 100644
index 000000000000..525452726d31
--- /dev/null
+++ b/Documentation/arm/kernel_mode_neon.txt
@@ -0,0 +1,121 @@
+Kernel mode NEON
+================
+
+TL;DR summary
+-------------
+* Use only NEON instructions, or VFP instructions that don't rely on support
+  code
+* Isolate your NEON code in a separate compilation unit, and compile it with
+  '-mfpu=neon -mfloat-abi=softfp'
+* Put kernel_neon_begin() and kernel_neon_end() calls around the calls into your
+  NEON code
+* Don't sleep in your NEON code, and be aware that it will be executed with
+  preemption disabled
+
+
+Introduction
+------------
+It is possible to use NEON instructions (and in some cases, VFP instructions) in
+code that runs in kernel mode. However, for performance reasons, the NEON/VFP
+register file is not preserved and restored at every context switch or taken
+exception like the normal register file is, so some manual intervention is
+required. Furthermore, special care is required for code that may sleep [i.e.,
+may call schedule()], as NEON or VFP instructions will be executed in a
+non-preemptible section for reasons outlined below.
+
+
+Lazy preserve and restore
+-------------------------
+The NEON/VFP register file is managed using lazy preserve (on UP systems) and
+lazy restore (on both SMP and UP systems). This means that the register file is
+kept 'live', and is only preserved and restored when multiple tasks are
+contending for the NEON/VFP unit (or, in the SMP case, when a task migrates to
+another core). Lazy restore is implemented by disabling the NEON/VFP unit after
+every context switch, resulting in a trap when subsequently a NEON/VFP
+instruction is issued, allowing the kernel to step in and perform the restore if
+necessary.
+
+Any use of the NEON/VFP unit in kernel mode should not interfere with this, so
+it is required to do an 'eager' preserve of the NEON/VFP register file, and
+enable the NEON/VFP unit explicitly so no exceptions are generated on first
+subsequent use. This is handled by the function kernel_neon_begin(), which
+should be called before any kernel mode NEON or VFP instructions are issued.
+Likewise, the NEON/VFP unit should be disabled again after use to make sure user
+mode will hit the lazy restore trap upon next use. This is handled by the
+function kernel_neon_end().
+
+
+Interruptions in kernel mode
+----------------------------
+For reasons of performance and simplicity, it was decided that there shall be no
+preserve/restore mechanism for the kernel mode NEON/VFP register contents. This
+implies that interruptions of a kernel mode NEON section can only be allowed if
+they are guaranteed not to touch the NEON/VFP registers. For this reason, the
+following rules and restrictions apply in the kernel:
+* NEON/VFP code is not allowed in interrupt context;
+* NEON/VFP code is not allowed to sleep;
+* NEON/VFP code is executed with preemption disabled.
+
+If latency is a concern, it is possible to put back to back calls to
+kernel_neon_end() and kernel_neon_begin() in places in your code where none of
+the NEON registers are live. (Additional calls to kernel_neon_begin() should be
+reasonably cheap if no context switch occurred in the meantime)
+
+
+VFP and support code
+--------------------
+Earlier versions of VFP (prior to version 3) rely on software support for things
+like IEEE-754 compliant underflow handling etc. When the VFP unit needs such
+software assistance, it signals the kernel by raising an undefined instruction
+exception. The kernel responds by inspecting the VFP control registers and the
+current instruction and arguments, and emulates the instruction in software.
+
+Such software assistance is currently not implemented for VFP instructions
+executed in kernel mode. If such a condition is encountered, the kernel will
+fail and generate an OOPS.
+
+
+Separating NEON code from ordinary code
+---------------------------------------
+The compiler is not aware of the special significance of kernel_neon_begin() and
+kernel_neon_end(), i.e., that it is only allowed to issue NEON/VFP instructions
+between calls to these respective functions. Furthermore, GCC may generate NEON
+instructions of its own at -O3 level if -mfpu=neon is selected, and even if the
+kernel is currently compiled at -O2, future changes may result in NEON/VFP
+instructions appearing in unexpected places if no special care is taken.
+
+Therefore, the recommended and only supported way of using NEON/VFP in the
+kernel is by adhering to the following rules:
+* isolate the NEON code in a separate compilation unit and compile it with
+  '-mfpu=neon -mfloat-abi=softfp';
+* issue the calls to kernel_neon_begin(), kernel_neon_end() as well as the calls
+  into the unit containing the NEON code from a compilation unit which is *not*
+  built with the GCC flag '-mfpu=neon' set.
+
+As the kernel is compiled with '-msoft-float', the above will guarantee that
+both NEON and VFP instructions will only ever appear in designated compilation
+units at any optimization level.
+
+
+NEON assembler
+--------------
+NEON assembler is supported with no additional caveats as long as the rules
+above are followed.
+
+
+NEON code generated by GCC
+--------------------------
+The GCC option -ftree-vectorize (implied by -O3) tries to exploit implicit
+parallelism, and generates NEON code from ordinary C source code. This is fully
+supported as long as the rules above are followed.
+
+
+NEON intrinsics
+---------------
+NEON intrinsics are also supported. However, as code using NEON intrinsics
+relies on the GCC header <arm_neon.h>, (which #includes <stdint.h>), you should
+observe the following in addition to the rules above:
+* Compile the unit containing the NEON intrinsics with '-ffreestanding' so GCC
+  uses its builtin version of <stdint.h> (this is a C99 header which the kernel
+  does not supply);
+* Include <arm_neon.h> last, or at least after <linux/types.h>
diff --git a/Documentation/arm64/booting.txt b/Documentation/arm64/booting.txt
index 9c4d388daddc..98df4a03807e 100644
--- a/Documentation/arm64/booting.txt
+++ b/Documentation/arm64/booting.txt
@@ -45,9 +45,9 @@ sees fit.)
 
 Requirement: MANDATORY
 
-The device tree blob (dtb) must be no bigger than 2 megabytes in size
-and placed at a 2-megabyte boundary within the first 512 megabytes from
-the start of the kernel image. This is to allow the kernel to map the
+The device tree blob (dtb) must be placed on an 8-byte boundary within
+the first 512 megabytes from the start of the kernel image and must not
+cross a 2-megabyte boundary. This is to allow the kernel to map the
 blob using a single section mapping in the initial page tables.
 
 
@@ -68,13 +68,23 @@ Image target is available instead.
 
 Requirement: MANDATORY
 
-The decompressed kernel image contains a 32-byte header as follows:
+The decompressed kernel image contains a 64-byte header as follows:
 
-  u32 magic	= 0x14000008;	/* branch to stext, little-endian */
-  u32 res0	= 0;		/* reserved */
+  u32 code0;			/* Executable code */
+  u32 code1;			/* Executable code */
   u64 text_offset;		/* Image load offset */
+  u64 res0	= 0;		/* reserved */
   u64 res1	= 0;		/* reserved */
   u64 res2	= 0;		/* reserved */
+  u64 res3	= 0;		/* reserved */
+  u64 res4	= 0;		/* reserved */
+  u32 magic	= 0x644d5241;	/* Magic number, little endian, "ARM\x64" */
+  u32 res5 = 0;      		/* reserved */
+
+
+Header notes:
+
+- code0/code1 are responsible for branching to stext.
 
 The image must be placed at the specified offset (currently 0x80000)
 from the start of the system RAM and called there. The start of the
diff --git a/Documentation/arm64/tagged-pointers.txt b/Documentation/arm64/tagged-pointers.txt
new file mode 100644
index 000000000000..d9995f1f51b3
--- /dev/null
+++ b/Documentation/arm64/tagged-pointers.txt
@@ -0,0 +1,34 @@
+		Tagged virtual addresses in AArch64 Linux
+		=========================================
+
+Author: Will Deacon <will.deacon@arm.com>
+Date  : 12 June 2013
+
+This document briefly describes the provision of tagged virtual
+addresses in the AArch64 translation system and their potential uses
+in AArch64 Linux.
+
+The kernel configures the translation tables so that translations made
+via TTBR0 (i.e. userspace mappings) have the top byte (bits 63:56) of
+the virtual address ignored by the translation hardware. This frees up
+this byte for application use, with the following caveats:
+
+	(1) The kernel requires that all user addresses passed to EL1
+	    are tagged with tag 0x00. This means that any syscall
+	    parameters containing user virtual addresses *must* have
+	    their top byte cleared before trapping to the kernel.
+
+	(2) Non-zero tags are not preserved when delivering signals.
+	    This means that signal handlers in applications making use
+	    of tags cannot rely on the tag information for user virtual
+	    addresses being maintained for fields inside siginfo_t.
+	    One exception to this rule is for signals raised in response
+	    to watchpoint debug exceptions, where the tag information
+	    will be preserved.
+
+	(3) Special care should be taken when using tagged pointers,
+	    since it is likely that C compilers will not hazard two
+	    virtual addresses differing only in the upper byte.
+
+The architecture prevents the use of a tagged PC, so the upper byte will
+be set to a sign-extension of bit 55 on exception return.
diff --git a/Documentation/block/00-INDEX b/Documentation/block/00-INDEX
index d18ecd827c40..929d9904f74b 100644
--- a/Documentation/block/00-INDEX
+++ b/Documentation/block/00-INDEX
@@ -6,6 +6,8 @@ capability.txt
 	- Generic Block Device Capability (/sys/block/<device>/capability)
 cfq-iosched.txt
 	- CFQ IO scheduler tunables
+cmdline-partition.txt
+	- how to specify block device partitions on kernel command line
 data-integrity.txt
 	- Block data integrity
 deadline-iosched.txt
diff --git a/Documentation/block/cfq-iosched.txt b/Documentation/block/cfq-iosched.txt
index 9887f0414c16..f3bc72945cbd 100644
--- a/Documentation/block/cfq-iosched.txt
+++ b/Documentation/block/cfq-iosched.txt
@@ -69,7 +69,7 @@ one, this value should be decreased relative to fifo_expire_async.
 group_idle
 -----------
 This parameter forces idling at the CFQ group level instead of CFQ
-queue level. This was introduced after after a bottleneck was observed
+queue level. This was introduced after a bottleneck was observed
 in higher end storage due to idle on sequential queue and allow dispatch
 from a single queue. The idea with this parameter is that it can be run with
 slice_idle=0 and group_idle=8, so that idling does not happen on individual
diff --git a/Documentation/block/cmdline-partition.txt b/Documentation/block/cmdline-partition.txt
new file mode 100644
index 000000000000..525b9f6d7fb4
--- /dev/null
+++ b/Documentation/block/cmdline-partition.txt
@@ -0,0 +1,39 @@
+Embedded device command line partition parsing
+=====================================================================
+
+Support for reading the block device partition table from the command line.
+It is typically used for fixed block (eMMC) embedded devices.
+It has no MBR, so saves storage space. Bootloader can be easily accessed
+by absolute address of data on the block device.
+Users can easily change the partition.
+
+The format for the command line is just like mtdparts:
+
+blkdevparts=<blkdev-def>[;<blkdev-def>]
+  <blkdev-def> := <blkdev-id>:<partdef>[,<partdef>]
+    <partdef> := <size>[@<offset>](part-name)
+
+<blkdev-id>
+    block device disk name, embedded device used fixed block device,
+    it's disk name also fixed. such as: mmcblk0, mmcblk1, mmcblk0boot0.
+
+<size>
+    partition size, in bytes, such as: 512, 1m, 1G.
+
+<offset>
+    partition start address, in bytes.
+
+(part-name)
+    partition name, kernel send uevent with "PARTNAME". application can create
+    a link to block device partition with the name "PARTNAME".
+    user space application can access partition by partition name.
+
+Example:
+    eMMC disk name is "mmcblk0" and "mmcblk0boot0"
+
+  bootargs:
+    'blkdevparts=mmcblk0:1G(data0),1G(data1),-;mmcblk0boot0:1m(boot),-(kernel)'
+
+  dmesg:
+    mmcblk0: p1(data0) p2(data1) p3()
+    mmcblk0boot0: p1(boot) p2(kernel)
diff --git a/Documentation/cachetlb.txt b/Documentation/cachetlb.txt
index 9b728dc17535..d79b008e4a32 100644
--- a/Documentation/cachetlb.txt
+++ b/Documentation/cachetlb.txt
@@ -57,7 +57,7 @@ changes occur:
 	interface must make sure that any previous page table
 	modifications for the address space 'vma->vm_mm' in the range
 	'start' to 'end-1' will be visible to the cpu.  That is, after
-	running, here will be no entries in the TLB for 'mm' for
+	running, there will be no entries in the TLB for 'mm' for
 	virtual addresses in the range 'start' to 'end-1'.
 
 	The "vma" is the backing store being used for the region.
@@ -375,8 +375,8 @@ maps this page at its virtual address.
 
   void flush_icache_page(struct vm_area_struct *vma, struct page *page)
 	All the functionality of flush_icache_page can be implemented in
-	flush_dcache_page and update_mmu_cache. In 2.7 the hope is to
-	remove this interface completely.
+	flush_dcache_page and update_mmu_cache. In the future, the hope
+	is to remove this interface completely.
 
 The final category of APIs is for I/O to deliberately aliased address
 ranges inside the kernel.  Such aliases are set up by use of the
diff --git a/Documentation/cgroups/memory.txt b/Documentation/cgroups/memory.txt
index 2a3330696372..8af4ad121828 100644
--- a/Documentation/cgroups/memory.txt
+++ b/Documentation/cgroups/memory.txt
@@ -490,6 +490,8 @@ pgpgin		- # of charging events to the memory cgroup. The charging
 pgpgout		- # of uncharging events to the memory cgroup. The uncharging
 		event happens each time a page is unaccounted from the cgroup.
 swap		- # of bytes of swap usage
+writeback	- # of bytes of file/anon cache that are queued for syncing to
+		disk.
 inactive_anon	- # of bytes of anonymous and swap cache memory on inactive
 		LRU list.
 active_anon	- # of bytes of anonymous and swap cache memory on active
diff --git a/Documentation/clk.txt b/Documentation/clk.txt
index 6f68ba0d1e01..3aeb5c440442 100644
--- a/Documentation/clk.txt
+++ b/Documentation/clk.txt
@@ -70,6 +70,10 @@ the operations defined in clk.h:
 						unsigned long parent_rate);
 		long		(*round_rate)(struct clk_hw *hw, unsigned long,
 						unsigned long *);
+		long		(*determine_rate)(struct clk_hw *hw,
+						unsigned long rate,
+						unsigned long *best_parent_rate,
+						struct clk **best_parent_clk);
 		int		(*set_parent)(struct clk_hw *hw, u8 index);
 		u8		(*get_parent)(struct clk_hw *hw);
 		int		(*set_rate)(struct clk_hw *hw, unsigned long);
@@ -179,26 +183,28 @@ mandatory, a cell marked as "n" implies that either including that
 callback is invalid or otherwise unnecessary.  Empty cells are either
 optional or must be evaluated on a case-by-case basis.
 
-                           clock hardware characteristics
-	     -----------------------------------------------------------
-             | gate | change rate | single parent | multiplexer | root |
-             |------|-------------|---------------|-------------|------|
-.prepare     |      |             |               |             |      |
-.unprepare   |      |             |               |             |      |
-             |      |             |               |             |      |
-.enable      | y    |             |               |             |      |
-.disable     | y    |             |               |             |      |
-.is_enabled  | y    |             |               |             |      |
-             |      |             |               |             |      |
-.recalc_rate |      | y           |               |             |      |
-.round_rate  |      | y           |               |             |      |
-.set_rate    |      | y           |               |             |      |
-             |      |             |               |             |      |
-.set_parent  |      |             | n             | y           | n    |
-.get_parent  |      |             | n             | y           | n    |
-             |      |             |               |             |      |
-.init        |      |             |               |             |      |
-	     -----------------------------------------------------------
+                              clock hardware characteristics
+                -----------------------------------------------------------
+                | gate | change rate | single parent | multiplexer | root |
+                |------|-------------|---------------|-------------|------|
+.prepare        |      |             |               |             |      |
+.unprepare      |      |             |               |             |      |
+                |      |             |               |             |      |
+.enable         | y    |             |               |             |      |
+.disable        | y    |             |               |             |      |
+.is_enabled     | y    |             |               |             |      |
+                |      |             |               |             |      |
+.recalc_rate    |      | y           |               |             |      |
+.round_rate     |      | y [1]       |               |             |      |
+.determine_rate |      | y [1]       |               |             |      |
+.set_rate       |      | y           |               |             |      |
+                |      |             |               |             |      |
+.set_parent     |      |             | n             | y           | n    |
+.get_parent     |      |             | n             | y           | n    |
+                |      |             |               |             |      |
+.init           |      |             |               |             |      |
+                -----------------------------------------------------------
+[1] either one of round_rate or determine_rate is required.
 
 Finally, register your clock at run-time with a hardware-specific
 registration function.  This function simply populates struct clk_foo's
diff --git a/Documentation/cpu-freq/cpu-drivers.txt b/Documentation/cpu-freq/cpu-drivers.txt
index 19fa98e07bf7..40282e617913 100644
--- a/Documentation/cpu-freq/cpu-drivers.txt
+++ b/Documentation/cpu-freq/cpu-drivers.txt
@@ -50,8 +50,6 @@ What shall this struct cpufreq_driver contain?
 
 cpufreq_driver.name -		The name of this driver.
 
-cpufreq_driver.owner -		THIS_MODULE;
-
 cpufreq_driver.init -		A pointer to the per-CPU initialization 
 				function.
 
diff --git a/Documentation/cputopology.txt b/Documentation/cputopology.txt
index 902d3151f527..0aad6deb2d96 100644
--- a/Documentation/cputopology.txt
+++ b/Documentation/cputopology.txt
@@ -22,7 +22,7 @@ to /proc/cpuinfo.
 
 4) /sys/devices/system/cpu/cpuX/topology/thread_siblings:
 
-	internel kernel map of cpuX's hardware threads within the same
+	internal kernel map of cpuX's hardware threads within the same
 	core as cpuX
 
 5) /sys/devices/system/cpu/cpuX/topology/core_siblings:
diff --git a/Documentation/development-process/2.Process b/Documentation/development-process/2.Process
index 4823577c6509..2e0617936e8f 100644
--- a/Documentation/development-process/2.Process
+++ b/Documentation/development-process/2.Process
@@ -276,7 +276,7 @@ mainline get there via -mm.
 The current -mm patch is available in the "mmotm" (-mm of the moment)
 directory at:
 
-	http://userweb.kernel.org/~akpm/mmotm/
+	http://www.ozlabs.org/~akpm/mmotm/
 
 Use of the MMOTM tree is likely to be a frustrating experience, though;
 there is a definite chance that it will not even compile.
@@ -287,7 +287,7 @@ the mainline is expected to look like after the next merge window closes.
 Linux-next trees are announced on the linux-kernel and linux-next mailing
 lists when they are assembled; they can be downloaded from:
 
-	http://www.kernel.org/pub/linux/kernel/people/sfr/linux-next/
+	http://www.kernel.org/pub/linux/kernel/next/
 
 Some information about linux-next has been gathered at:
 
diff --git a/Documentation/device-mapper/cache.txt b/Documentation/device-mapper/cache.txt
index e8cdf7241b66..33d45ee0b737 100644
--- a/Documentation/device-mapper/cache.txt
+++ b/Documentation/device-mapper/cache.txt
@@ -50,14 +50,16 @@ other parameters detailed later):
    which are dirty, and extra hints for use by the policy object.
    This information could be put on the cache device, but having it
    separate allows the volume manager to configure it differently,
-   e.g. as a mirror for extra robustness.
+   e.g. as a mirror for extra robustness.  This metadata device may only
+   be used by a single cache device.
 
 Fixed block size
 ----------------
 
 The origin is divided up into blocks of a fixed size.  This block size
 is configurable when you first create the cache.  Typically we've been
-using block sizes of 256k - 1024k.
+using block sizes of 256KB - 1024KB.  The block size must be between 64
+(32KB) and 2097152 (1GB) and a multiple of 64 (32KB).
 
 Having a fixed block size simplifies the target a lot.  But it is
 something of a compromise.  For instance, a small part of a block may be
diff --git a/Documentation/device-mapper/statistics.txt b/Documentation/device-mapper/statistics.txt
new file mode 100644
index 000000000000..2a1673adc200
--- /dev/null
+++ b/Documentation/device-mapper/statistics.txt
@@ -0,0 +1,186 @@
+DM statistics
+=============
+
+Device Mapper supports the collection of I/O statistics on user-defined
+regions of a DM device.	 If no regions are defined no statistics are
+collected so there isn't any performance impact.  Only bio-based DM
+devices are currently supported.
+
+Each user-defined region specifies a starting sector, length and step.
+Individual statistics will be collected for each step-sized area within
+the range specified.
+
+The I/O statistics counters for each step-sized area of a region are
+in the same format as /sys/block/*/stat or /proc/diskstats (see:
+Documentation/iostats.txt).  But two extra counters (12 and 13) are
+provided: total time spent reading and writing in milliseconds.	 All
+these counters may be accessed by sending the @stats_print message to
+the appropriate DM device via dmsetup.
+
+Each region has a corresponding unique identifier, which we call a
+region_id, that is assigned when the region is created.	 The region_id
+must be supplied when querying statistics about the region, deleting the
+region, etc.  Unique region_ids enable multiple userspace programs to
+request and process statistics for the same DM device without stepping
+on each other's data.
+
+The creation of DM statistics will allocate memory via kmalloc or
+fallback to using vmalloc space.  At most, 1/4 of the overall system
+memory may be allocated by DM statistics.  The admin can see how much
+memory is used by reading
+/sys/module/dm_mod/parameters/stats_current_allocated_bytes
+
+Messages
+========
+
+    @stats_create <range> <step> [<program_id> [<aux_data>]]
+
+	Create a new region and return the region_id.
+
+	<range>
+	  "-" - whole device
+	  "<start_sector>+<length>" - a range of <length> 512-byte sectors
+				      starting with <start_sector>.
+
+	<step>
+	  "<area_size>" - the range is subdivided into areas each containing
+			  <area_size> sectors.
+	  "/<number_of_areas>" - the range is subdivided into the specified
+				 number of areas.
+
+	<program_id>
+	  An optional parameter.  A name that uniquely identifies
+	  the userspace owner of the range.  This groups ranges together
+	  so that userspace programs can identify the ranges they
+	  created and ignore those created by others.
+	  The kernel returns this string back in the output of
+	  @stats_list message, but it doesn't use it for anything else.
+
+	<aux_data>
+	  An optional parameter.  A word that provides auxiliary data
+	  that is useful to the client program that created the range.
+	  The kernel returns this string back in the output of
+	  @stats_list message, but it doesn't use this value for anything.
+
+    @stats_delete <region_id>
+
+	Delete the region with the specified id.
+
+	<region_id>
+	  region_id returned from @stats_create
+
+    @stats_clear <region_id>
+
+	Clear all the counters except the in-flight i/o counters.
+
+	<region_id>
+	  region_id returned from @stats_create
+
+    @stats_list [<program_id>]
+
+	List all regions registered with @stats_create.
+
+	<program_id>
+	  An optional parameter.
+	  If this parameter is specified, only matching regions
+	  are returned.
+	  If it is not specified, all regions are returned.
+
+	Output format:
+	  <region_id>: <start_sector>+<length> <step> <program_id> <aux_data>
+
+    @stats_print <region_id> [<starting_line> <number_of_lines>]
+
+	Print counters for each step-sized area of a region.
+
+	<region_id>
+	  region_id returned from @stats_create
+
+	<starting_line>
+	  The index of the starting line in the output.
+	  If omitted, all lines are returned.
+
+	<number_of_lines>
+	  The number of lines to include in the output.
+	  If omitted, all lines are returned.
+
+	Output format for each step-sized area of a region:
+
+	  <start_sector>+<length> counters
+
+	  The first 11 counters have the same meaning as
+	  /sys/block/*/stat or /proc/diskstats.
+
+	  Please refer to Documentation/iostats.txt for details.
+
+	  1. the number of reads completed
+	  2. the number of reads merged
+	  3. the number of sectors read
+	  4. the number of milliseconds spent reading
+	  5. the number of writes completed
+	  6. the number of writes merged
+	  7. the number of sectors written
+	  8. the number of milliseconds spent writing
+	  9. the number of I/Os currently in progress
+	  10. the number of milliseconds spent doing I/Os
+	  11. the weighted number of milliseconds spent doing I/Os
+
+	  Additional counters:
+	  12. the total time spent reading in milliseconds
+	  13. the total time spent writing in milliseconds
+
+    @stats_print_clear <region_id> [<starting_line> <number_of_lines>]
+
+	Atomically print and then clear all the counters except the
+	in-flight i/o counters.	 Useful when the client consuming the
+	statistics does not want to lose any statistics (those updated
+	between printing and clearing).
+
+	<region_id>
+	  region_id returned from @stats_create
+
+	<starting_line>
+	  The index of the starting line in the output.
+	  If omitted, all lines are printed and then cleared.
+
+	<number_of_lines>
+	  The number of lines to process.
+	  If omitted, all lines are printed and then cleared.
+
+    @stats_set_aux <region_id> <aux_data>
+
+	Store auxiliary data aux_data for the specified region.
+
+	<region_id>
+	  region_id returned from @stats_create
+
+	<aux_data>
+	  The string that identifies data which is useful to the client
+	  program that created the range.  The kernel returns this
+	  string back in the output of @stats_list message, but it
+	  doesn't use this value for anything.
+
+Examples
+========
+
+Subdivide the DM device 'vol' into 100 pieces and start collecting
+statistics on them:
+
+  dmsetup message vol 0 @stats_create - /100
+
+Set the auxillary data string to "foo bar baz" (the escape for each
+space must also be escaped, otherwise the shell will consume them):
+
+  dmsetup message vol 0 @stats_set_aux 0 foo\\ bar\\ baz
+
+List the statistics:
+
+  dmsetup message vol 0 @stats_list
+
+Print the statistics:
+
+  dmsetup message vol 0 @stats_print 0
+
+Delete the statistics:
+
+  dmsetup message vol 0 @stats_delete 0
diff --git a/Documentation/device-mapper/thin-provisioning.txt b/Documentation/device-mapper/thin-provisioning.txt
index 30b8b83bd333..50c44cf79b0e 100644
--- a/Documentation/device-mapper/thin-provisioning.txt
+++ b/Documentation/device-mapper/thin-provisioning.txt
@@ -99,13 +99,14 @@ Using an existing pool device
 		 $data_block_size $low_water_mark"
 
 $data_block_size gives the smallest unit of disk space that can be
-allocated at a time expressed in units of 512-byte sectors.  People
-primarily interested in thin provisioning may want to use a value such
-as 1024 (512KB).  People doing lots of snapshotting may want a smaller value
-such as 128 (64KB).  If you are not zeroing newly-allocated data,
-a larger $data_block_size in the region of 256000 (128MB) is suggested.
-$data_block_size must be the same for the lifetime of the
-metadata device.
+allocated at a time expressed in units of 512-byte sectors.
+$data_block_size must be between 128 (64KB) and 2097152 (1GB) and a
+multiple of 128 (64KB).  $data_block_size cannot be changed after the
+thin-pool is created.  People primarily interested in thin provisioning
+may want to use a value such as 1024 (512KB).  People doing lots of
+snapshotting may want a smaller value such as 128 (64KB).  If you are
+not zeroing newly-allocated data, a larger $data_block_size in the
+region of 256000 (128MB) is suggested.
 
 $low_water_mark is expressed in blocks of size $data_block_size.  If
 free space on the data device drops below this level then a dm event
diff --git a/Documentation/devicetree/bindings/arm/arch_timer.txt b/Documentation/devicetree/bindings/arm/arch_timer.txt
index 20746e5abe6f..06fc7602593a 100644
--- a/Documentation/devicetree/bindings/arm/arch_timer.txt
+++ b/Documentation/devicetree/bindings/arm/arch_timer.txt
@@ -1,10 +1,14 @@
 * ARM architected timer
 
-ARM cores may have a per-core architected timer, which provides per-cpu timers.
+ARM cores may have a per-core architected timer, which provides per-cpu timers,
+or a memory mapped architected timer, which provides up to 8 frames with a
+physical and optional virtual timer per frame.
 
-The timer is attached to a GIC to deliver its per-processor interrupts.
+The per-core architected timer is attached to a GIC to deliver its
+per-processor interrupts via PPIs. The memory mapped timer is attached to a GIC
+to deliver its interrupts via SPIs.
 
-** Timer node properties:
+** CP15 Timer node properties:
 
 - compatible : Should at least contain one of
 	"arm,armv7-timer"
@@ -26,3 +30,52 @@ Example:
 			     <1 10 0xf08>;
 		clock-frequency = <100000000>;
 	};
+
+** Memory mapped timer node properties:
+
+- compatible : Should at least contain "arm,armv7-timer-mem".
+
+- clock-frequency : The frequency of the main counter, in Hz. Optional.
+
+- reg : The control frame base address.
+
+Note that #address-cells, #size-cells, and ranges shall be present to ensure
+the CPU can address a frame's registers.
+
+A timer node has up to 8 frame sub-nodes, each with the following properties:
+
+- frame-number: 0 to 7.
+
+- interrupts : Interrupt list for physical and virtual timers in that order.
+  The virtual timer interrupt is optional.
+
+- reg : The first and second view base addresses in that order. The second view
+  base address is optional.
+
+- status : "disabled" indicates the frame is not available for use. Optional.
+
+Example:
+
+	timer@f0000000 {
+		compatible = "arm,armv7-timer-mem";
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges;
+		reg = <0xf0000000 0x1000>;
+		clock-frequency = <50000000>;
+
+		frame@f0001000 {
+			frame-number = <0>
+			interrupts = <0 13 0x8>,
+				     <0 14 0x8>;
+			reg = <0xf0001000 0x1000>,
+			      <0xf0002000 0x1000>;
+		};
+
+		frame@f0003000 {
+			frame-number = <1>
+			interrupts = <0 15 0x8>;
+			reg = <0xf0003000 0x1000>;
+			status = "disabled";
+		};
+	};
diff --git a/Documentation/devicetree/bindings/arm/atmel-adc.txt b/Documentation/devicetree/bindings/arm/atmel-adc.txt
index 16769d9cedd6..723c205cb10d 100644
--- a/Documentation/devicetree/bindings/arm/atmel-adc.txt
+++ b/Documentation/devicetree/bindings/arm/atmel-adc.txt
@@ -1,18 +1,15 @@
 * AT91's Analog to Digital Converter (ADC)
 
 Required properties:
-  - compatible: Should be "atmel,at91sam9260-adc"
+  - compatible: Should be "atmel,<chip>-adc"
+    <chip> can be "at91sam9260", "at91sam9g45" or "at91sam9x5"
   - reg: Should contain ADC registers location and length
   - interrupts: Should contain the IRQ line for the ADC
-  - atmel,adc-channel-base: Offset of the first channel data register
   - atmel,adc-channels-used: Bitmask of the channels muxed and enable for this
     device
-  - atmel,adc-drdy-mask: Mask of the DRDY interruption in the ADC
   - atmel,adc-num-channels: Number of channels available in the ADC
   - atmel,adc-startup-time: Startup Time of the ADC in microseconds as
     defined in the datasheet
-  - atmel,adc-status-register: Offset of the Interrupt Status Register
-  - atmel,adc-trigger-register: Offset of the Trigger Register
   - atmel,adc-vref: Reference voltage in millivolts for the conversions
   - atmel,adc-res: List of resolution in bits supported by the ADC. List size
 		   must be two at least.
diff --git a/Documentation/devicetree/bindings/arm/bcm/bcm11351.txt b/Documentation/devicetree/bindings/arm/bcm/bcm11351.txt
index fb7b5cd2652f..0ff6560e6094 100644
--- a/Documentation/devicetree/bindings/arm/bcm/bcm11351.txt
+++ b/Documentation/devicetree/bindings/arm/bcm/bcm11351.txt
@@ -6,4 +6,5 @@ bcm11351, bcm28145, bcm28155 SoCs) shall have the following properties:
 
 Required root node property:
 
-compatible = "bcm,bcm11351";
+compatible = "brcm,bcm11351";
+DEPRECATED: compatible = "bcm,bcm11351";
diff --git a/Documentation/devicetree/bindings/arm/bcm/bcm,kona-timer.txt b/Documentation/devicetree/bindings/arm/bcm/kona-timer.txt
index 59fa6e68d4f6..17d88b233d1b 100644
--- a/Documentation/devicetree/bindings/arm/bcm/bcm,kona-timer.txt
+++ b/Documentation/devicetree/bindings/arm/bcm/kona-timer.txt
@@ -4,14 +4,15 @@ This timer is used in the following Broadcom SoCs:
  BCM11130, BCM11140, BCM11351, BCM28145, BCM28155
 
 Required properties:
-- compatible : "bcm,kona-timer"
+- compatible : "brcm,kona-timer"
+- DEPRECATED: compatible : "bcm,kona-timer"
 - reg : Register range for the timer
 - interrupts : interrupt for the timer
 - clock-frequency: frequency that the clock operates
 
 Example:
 	timer@35006000 {
-		compatible = "bcm,kona-timer";
+		compatible = "brcm,kona-timer";
 		reg = <0x35006000 0x1000>;
 		interrupts = <0x0 7 0x4>;
 		clock-frequency = <32768>;
diff --git a/Documentation/devicetree/bindings/arm/bcm/kona-wdt.txt b/Documentation/devicetree/bindings/arm/bcm/kona-wdt.txt
new file mode 100644
index 000000000000..2b86a00e351d
--- /dev/null
+++ b/Documentation/devicetree/bindings/arm/bcm/kona-wdt.txt
@@ -0,0 +1,15 @@
+Broadcom Kona Family Watchdog Timer
+-----------------------------------
+
+This watchdog timer is used in the following Broadcom SoCs:
+  BCM11130, BCM11140, BCM11351, BCM28145, BCM28155
+
+Required properties:
+  - compatible = "brcm,bcm11351-wdt", "brcm,kona-wdt";
+  - reg: memory address & range
+
+Example:
+	watchdog@35002f40 {
+		compatible = "brcm,bcm11351-wdt", "brcm,kona-wdt";
+		reg = <0x35002f40 0x6c>;
+	};
diff --git a/Documentation/devicetree/bindings/arm/l2cc.txt b/Documentation/devicetree/bindings/arm/l2cc.txt
index 69ddf9fad2dc..c0c7626fd0ff 100644
--- a/Documentation/devicetree/bindings/arm/l2cc.txt
+++ b/Documentation/devicetree/bindings/arm/l2cc.txt
@@ -16,9 +16,11 @@ Required properties:
      performs the same operation).
 	"marvell,"aurora-outer-cache: Marvell Controller designed to be
 	 compatible with the ARM one with outer cache mode.
-	"bcm,bcm11351-a2-pl310-cache": For Broadcom bcm11351 chipset where an
+	"brcm,bcm11351-a2-pl310-cache": For Broadcom bcm11351 chipset where an
 	offset needs to be added to the address before passing down to the L2
 	cache controller
+	"bcm,bcm11351-a2-pl310-cache": DEPRECATED by
+	                               "brcm,bcm11351-a2-pl310-cache"
 - cache-unified : Specifies the cache is a unified cache.
 - cache-level : Should be set to 2 for a level 2 cache.
 - reg : Physical base address and size of cache controller's memory mapped
diff --git a/Documentation/devicetree/bindings/arm/omap/omap.txt b/Documentation/devicetree/bindings/arm/omap/omap.txt
index 6d498c758b45..91b7049affa1 100644
--- a/Documentation/devicetree/bindings/arm/omap/omap.txt
+++ b/Documentation/devicetree/bindings/arm/omap/omap.txt
@@ -59,3 +59,6 @@ Boards:
 
 - AM43x EPOS EVM
   compatible = "ti,am43x-epos-evm", "ti,am4372", "ti,am43"
+
+- DRA7 EVM:  Software Developement Board for DRA7XX
+  compatible = "ti,dra7-evm", "ti,dra7"
diff --git a/Documentation/devicetree/bindings/arm/ste-u300.txt b/Documentation/devicetree/bindings/arm/ste-u300.txt
index 69b5ab0b5f4b..d11d80006a19 100644
--- a/Documentation/devicetree/bindings/arm/ste-u300.txt
+++ b/Documentation/devicetree/bindings/arm/ste-u300.txt
@@ -22,7 +22,7 @@ This contains the board-specific information.
 - compatible: must be "stericsson,s365".
 - vana15-supply: the regulator supplying the 1.5V to drive the
   board.
-- syscon: a pointer to the syscon node so we can acccess the
+- syscon: a pointer to the syscon node so we can access the
   syscon registers to set the board as self-powered.
 
 Example:
diff --git a/Documentation/devicetree/bindings/arm/vexpress-scc.txt b/Documentation/devicetree/bindings/arm/vexpress-scc.txt
new file mode 100644
index 000000000000..ae5043e42e5d
--- /dev/null
+++ b/Documentation/devicetree/bindings/arm/vexpress-scc.txt
@@ -0,0 +1,33 @@
+ARM Versatile Express Serial Configuration Controller
+-----------------------------------------------------
+
+Test chips for ARM Versatile Express platform implement SCC (Serial
+Configuration Controller) interface, used to set initial conditions
+for the test chip.
+
+In some cases its registers are also mapped in normal address space
+and can be used to obtain runtime information about the chip internals
+(like silicon temperature sensors) and as interface to other subsystems
+like platform configuration control and power management.
+
+Required properties:
+
+- compatible value: "arm,vexpress-scc,<model>", "arm,vexpress-scc";
+		    where <model> is the full tile model name (as used
+		    in the tile's Technical Reference Manual),
+		    eg. for Coretile Express A15x2 A7x3 (V2P-CA15_A7):
+	compatible = "arm,vexpress-scc,v2p-ca15_a7", "arm,vexpress-scc";
+
+Optional properties:
+
+- reg: when the SCC is memory mapped, physical address and size of the
+       registers window
+- interrupts: when the SCC can generate a system-level interrupt
+
+Example:
+
+	scc@7fff0000 {
+		compatible = "arm,vexpress-scc,v2p-ca15_a7", "arm,vexpress-scc";
+		reg = <0 0x7fff0000 0 0x1000>;
+		interrupts = <0 95 4>;
+	};
diff --git a/Documentation/devicetree/bindings/arm/vexpress-sysreg.txt b/Documentation/devicetree/bindings/arm/vexpress-sysreg.txt
index 9cf3f25544c7..5580e9c4bd85 100644
--- a/Documentation/devicetree/bindings/arm/vexpress-sysreg.txt
+++ b/Documentation/devicetree/bindings/arm/vexpress-sysreg.txt
@@ -32,8 +32,8 @@ numbers - see motherboard's TRM for more details.
 The node describing a config device must refer to the sysreg node via
 "arm,vexpress,config-bridge" phandle (can be also defined in the node's
 parent) and relies on the board topology properties - see main vexpress
-node documentation for more details. It must must also define the
-following property:
+node documentation for more details. It must also define the following
+property:
 - arm,vexpress-sysreg,func : must contain two cells:
   - first cell defines function number (eg. 1 for clock generator,
     2 for voltage regulators etc.)
diff --git a/Documentation/devicetree/bindings/ata/ahci-platform.txt b/Documentation/devicetree/bindings/ata/ahci-platform.txt
index 3ec0c5c4f0e9..89de1564950c 100644
--- a/Documentation/devicetree/bindings/ata/ahci-platform.txt
+++ b/Documentation/devicetree/bindings/ata/ahci-platform.txt
@@ -4,27 +4,17 @@ SATA nodes are defined to describe on-chip Serial ATA controllers.
 Each SATA controller should have its own node.
 
 Required properties:
-- compatible        : compatible list, contains "calxeda,hb-ahci" or "snps,spear-ahci"
+- compatible        : compatible list, contains "snps,spear-ahci"
 - interrupts        : <interrupt mapping for SATA IRQ>
 - reg               : <registers mapping>
 
 Optional properties:
-- calxeda,port-phys: phandle-combophy and lane assignment, which maps each
-			SATA port to a combophy and a lane within that
-			combophy
-- calxeda,sgpio-gpio: phandle-gpio bank, bit offset, and default on or off,
-			which indicates that the driver supports SGPIO
-			indicator lights using the indicated GPIOs
-- calxeda,led-order : a u32 array that map port numbers to offsets within the
-			SGPIO bitstream.
 - dma-coherent      : Present if dma operations are coherent
 
 Example:
         sata@ffe08000 {
-		compatible = "calxeda,hb-ahci";
-                reg = <0xffe08000 0x1000>;
-                interrupts = <115>;
-		calxeda,port-phys = <&combophy5 0 &combophy0 0 &combophy0 1
-					&combophy0 2 &combophy0 3>;
+		compatible = "snps,spear-ahci";
+		reg = <0xffe08000 0x1000>;
+		interrupts = <115>;
 
         };
diff --git a/Documentation/devicetree/bindings/ata/sata_highbank.txt b/Documentation/devicetree/bindings/ata/sata_highbank.txt
new file mode 100644
index 000000000000..aa83407cb7a4
--- /dev/null
+++ b/Documentation/devicetree/bindings/ata/sata_highbank.txt
@@ -0,0 +1,44 @@
+* Calxeda AHCI SATA Controller
+
+SATA nodes are defined to describe on-chip Serial ATA controllers.
+The Calxeda SATA controller mostly conforms to the AHCI interface
+with some special extensions to add functionality.
+Each SATA controller should have its own node.
+
+Required properties:
+- compatible        : compatible list, contains "calxeda,hb-ahci"
+- interrupts        : <interrupt mapping for SATA IRQ>
+- reg               : <registers mapping>
+
+Optional properties:
+- dma-coherent      : Present if dma operations are coherent
+- calxeda,port-phys : phandle-combophy and lane assignment, which maps each
+			SATA port to a combophy and a lane within that
+			combophy
+- calxeda,sgpio-gpio: phandle-gpio bank, bit offset, and default on or off,
+			which indicates that the driver supports SGPIO
+			indicator lights using the indicated GPIOs
+- calxeda,led-order : a u32 array that map port numbers to offsets within the
+			SGPIO bitstream.
+- calxeda,tx-atten  : a u32 array that contains TX attenuation override
+			codes, one per port. The upper 3 bytes are always
+			0 and thus ignored.
+- calxeda,pre-clocks : a u32 that indicates the number of additional clock
+			cycles to transmit before sending an SGPIO pattern
+- calxeda,post-clocks: a u32 that indicates the number of additional clock
+			cycles to transmit after sending an SGPIO pattern
+
+Example:
+        sata@ffe08000 {
+		compatible = "calxeda,hb-ahci";
+		reg = <0xffe08000 0x1000>;
+		interrupts = <115>;
+		dma-coherent;
+		calxeda,port-phys = <&combophy5 0 &combophy0 0 &combophy0 1
+					&combophy0 2 &combophy0 3>;
+		calxeda,sgpio-gpio =<&gpioh 5 1 &gpioh 6 1 &gpioh 7 1>;
+		calxeda,led-order = <4 0 1 2 3>;
+		calxeda,tx-atten = <0xff 22 0xff 0xff 23>;
+		calxeda,pre-clocks = <10>;
+		calxeda,post-clocks = <0>;
+        };
diff --git a/Documentation/devicetree/bindings/bus/imx-weim.txt b/Documentation/devicetree/bindings/bus/imx-weim.txt
index cedc2a9c4785..0fd76c405208 100644
--- a/Documentation/devicetree/bindings/bus/imx-weim.txt
+++ b/Documentation/devicetree/bindings/bus/imx-weim.txt
@@ -8,7 +8,7 @@ The actual devices are instantiated from the child nodes of a WEIM node.
 
 Required properties:
 
- - compatible:		Should be set to "fsl,imx6q-weim"
+ - compatible:		Should be set to "fsl,<soc>-weim"
  - reg:			A resource specifier for the register space
 			(see the example below)
  - clocks:		the clock, see the example below.
@@ -21,11 +21,18 @@ Required properties:
 
 Timing property for child nodes. It is mandatory, not optional.
 
- - fsl,weim-cs-timing:	The timing array, contains 6 timing values for the
+ - fsl,weim-cs-timing:	The timing array, contains timing values for the
 			child node. We can get the CS index from the child
-			node's "reg" property. This property contains the values
-			for the registers EIM_CSnGCR1, EIM_CSnGCR2, EIM_CSnRCR1,
-			EIM_CSnRCR2, EIM_CSnWCR1, EIM_CSnWCR2 in this order.
+			node's "reg" property. The number of registers depends
+			on the selected chip.
+			For i.MX1, i.MX21 ("fsl,imx1-weim") there are two
+			registers: CSxU, CSxL.
+			For i.MX25, i.MX27, i.MX31 and i.MX35 ("fsl,imx27-weim")
+			there are three registers: CSCRxU, CSCRxL, CSCRxA.
+			For i.MX50, i.MX53 ("fsl,imx50-weim"),
+			i.MX51 ("fsl,imx51-weim") and i.MX6Q ("fsl,imx6q-weim")
+			there are six registers: CSxGCR1, CSxGCR2, CSxRCR1,
+			CSxRCR2, CSxWCR1, CSxWCR2.
 
 Example for an imx6q-sabreauto board, the NOR flash connected to the WEIM:
 
diff --git a/Documentation/devicetree/bindings/bus/mvebu-mbus.txt b/Documentation/devicetree/bindings/bus/mvebu-mbus.txt
new file mode 100644
index 000000000000..7586fb68c072
--- /dev/null
+++ b/Documentation/devicetree/bindings/bus/mvebu-mbus.txt
@@ -0,0 +1,276 @@
+
+* Marvell MBus
+
+Required properties:
+
+- compatible:	 Should be set to one of the following:
+		 marvell,armada370-mbus
+		 marvell,armadaxp-mbus
+		 marvell,armada370-mbus
+		 marvell,armadaxp-mbus
+		 marvell,kirkwood-mbus
+		 marvell,dove-mbus
+		 marvell,orion5x-88f5281-mbus
+		 marvell,orion5x-88f5182-mbus
+		 marvell,orion5x-88f5181-mbus
+		 marvell,orion5x-88f6183-mbus
+		 marvell,mv78xx0-mbus
+
+- address-cells: Must be '2'. The first cell for the MBus ID encoding,
+                 the second cell for the address offset within the window.
+
+- size-cells:    Must be '1'.
+
+- ranges:        Must be set up to provide a proper translation for each child.
+	         See the examples below.
+
+- controller:    Contains a single phandle referring to the MBus controller
+                 node. This allows to specify the node that contains the
+		 registers that control the MBus, which is typically contained
+		 within the internal register window (see below).
+
+Optional properties:
+
+- pcie-mem-aperture:	This optional property contains the aperture for
+			the memory region of the PCIe driver.
+			If it's defined, it must encode the base address and
+			size for the address decoding windows allocated for
+			the PCIe memory region.
+
+- pcie-io-aperture:	Just as explained for the above property, this
+			optional property contains the aperture for the
+			I/O region of the PCIe driver.
+
+* Marvell MBus controller
+
+Required properties:
+
+- compatible:	Should be set to "marvell,mbus-controller".
+
+- reg:          Device's register space.
+		Two entries are expected (see the examples below):
+		the first one controls the devices decoding window and
+		the second one controls the SDRAM decoding window.
+
+Example:
+
+	soc {
+		compatible = "marvell,armada370-mbus", "simple-bus";
+		#address-cells = <2>;
+		#size-cells = <1>;
+		controller = <&mbusc>;
+		pcie-mem-aperture = <0xe0000000 0x8000000>;
+		pcie-io-aperture  = <0xe8000000 0x100000>;
+
+		internal-regs {
+			compatible = "simple-bus";
+
+			mbusc: mbus-controller@20000 {
+				compatible = "marvell,mbus-controller";
+				reg = <0x20000 0x100>, <0x20180 0x20>;
+			};
+
+			/* more children ...*/
+		};
+	};
+
+** MBus address decoding window specification
+
+The MBus children address space is comprised of two cells: the first one for
+the window ID and the second one for the offset within the window.
+In order to allow to describe valid and non-valid window entries, the
+following encoding is used:
+
+  0xSIAA0000 0x00oooooo
+
+Where:
+
+  S = 0x0 for a MBus valid window
+  S = 0xf for a non-valid window (see below)
+
+If S = 0x0, then:
+
+   I = 4-bit window target ID
+  AA = windpw attribute
+
+If S = 0xf, then:
+
+   I = don't care
+   AA = 1 for internal register
+
+Following the above encoding, for each ranges entry for a MBus valid window
+(S = 0x0), an address decoding window is allocated. On the other side,
+entries for translation that do not correspond to valid windows (S = 0xf)
+are skipped.
+
+	soc {
+		compatible = "marvell,armada370-mbus", "simple-bus";
+		#address-cells = <2>;
+		#size-cells = <1>;
+		controller = <&mbusc>;
+
+		ranges = <0xf0010000 0 0 0xd0000000 0x100000
+			  0x01e00000 0 0 0xfff00000 0x100000>;
+
+		bootrom {
+			compatible = "marvell,bootrom";
+			reg = <0x01e00000 0 0x100000>;
+		};
+
+		/* other children */
+		...
+
+		internal-regs {
+			compatible = "simple-bus";
+			ranges = <0 0xf0010000 0 0x100000>;
+
+			mbusc: mbus-controller@20000 {
+				compatible = "marvell,mbus-controller";
+				reg = <0x20000 0x100>, <0x20180 0x20>;
+			};
+
+			/* more children ...*/
+		};
+	};
+
+In the shown example, the translation entry in the 'ranges' property is what
+makes the MBus driver create a static decoding window for the corresponding
+given child device. Note that the binding does not require child nodes to be
+present. Of course, child nodes are needed to probe the devices.
+
+Since each window is identified by its target ID and attribute ID there's
+a special macro that can be use to simplify the translation entries:
+
+#define MBUS_ID(target,attributes) (((target) << 24) | ((attributes) << 16))
+
+Using this macro, the above example would be:
+
+	soc {
+		compatible = "marvell,armada370-mbus", "simple-bus";
+		#address-cells = <2>;
+		#size-cells = <1>;
+		controller = <&mbusc>;
+
+		ranges = < MBUS_ID(0xf0, 0x01) 0 0 0xd0000000 0x100000
+			   MBUS_ID(0x01, 0xe0) 0 0 0xfff00000 0x100000>;
+
+		bootrom {
+			compatible = "marvell,bootrom";
+			reg = <MBUS_ID(0x01, 0xe0) 0 0x100000>;
+		};
+
+		/* other children */
+		...
+
+		internal-regs {
+			compatible = "simple-bus";
+			#address-cells = <1>;
+			#size-cells = <1>;
+			ranges = <0 MBUS_ID(0xf0, 0x01) 0 0x100000>;
+
+			mbusc: mbus-controller@20000 {
+				compatible = "marvell,mbus-controller";
+				reg = <0x20000 0x100>, <0x20180 0x20>;
+			};
+
+			/* other children */
+			...
+		};
+	};
+
+
+** About the window base address
+
+Remember the MBus controller allows a great deal of flexibility for choosing
+the decoding window base address. When planning the device tree layout it's
+possible to choose any address as the base address, provided of course there's
+a region large enough available, and with the required alignment.
+
+Yet in other words: there's nothing preventing us from setting a base address
+of 0xf0000000, or 0xd0000000 for the NOR device shown above, if such region is
+unused.
+
+** Window allocation policy
+
+The mbus-node ranges property defines a set of mbus windows that are expected
+to be set by the operating system and that are guaranteed to be free of overlaps
+with one another or with the system memory ranges.
+
+Each entry in the property refers to exactly one window. If the operating system
+choses to use a different set of mbus windows, it must ensure that any address
+translations performed from downstream devices are adapted accordingly.
+
+The operating system may insert additional mbus windows that do not conflict
+with the ones listed in the ranges, e.g. for mapping PCIe devices.
+As a special case, the internal register window must be set up by the boot
+loader at the address listed in the ranges property, since access to that region
+is needed to set up the other windows.
+
+** Example
+
+See the example below, where a more complete device tree is shown:
+
+	soc {
+		compatible = "marvell,armadaxp-mbus", "simple-bus";
+		controller = <&mbusc>;
+
+		ranges = <MBUS_ID(0xf0, 0x01) 0 0 0xd0000000 0x100000   /* internal-regs */
+			  MBUS_ID(0x01, 0x1d) 0 0 0xfff00000 0x100000
+			  MBUS_ID(0x01, 0x2f) 0 0 0xf0000000 0x8000000>;
+
+		bootrom {
+			compatible = "marvell,bootrom";
+			reg = <MBUS_ID(0x01, 0x1d) 0 0x100000>;
+		};
+
+		devbus-bootcs {
+			status = "okay";
+			ranges = <0 MBUS_ID(0x01, 0x2f) 0 0x8000000>;
+
+			/* NOR */
+			nor {
+				compatible = "cfi-flash";
+				reg = <0 0x8000000>;
+				bank-width = <2>;
+			};
+		};
+
+		pcie-controller {
+			compatible = "marvell,armada-xp-pcie";
+			status = "okay";
+			device_type = "pci";
+
+			#address-cells = <3>;
+			#size-cells = <2>;
+
+			ranges =
+			       <0x82000000 0 0x40000 MBUS_ID(0xf0, 0x01) 0x40000 0 0x00002000   /* Port 0.0 registers */
+				0x82000000 0 0x42000 MBUS_ID(0xf0, 0x01) 0x42000 0 0x00002000   /* Port 2.0 registers */
+				0x82000000 0 0x44000 MBUS_ID(0xf0, 0x01) 0x44000 0 0x00002000   /* Port 0.1 registers */
+				0x82000000 0 0x48000 MBUS_ID(0xf0, 0x01) 0x48000 0 0x00002000   /* Port 0.2 registers */
+				0x82000000 0 0x4c000 MBUS_ID(0xf0, 0x01) 0x4c000 0 0x00002000   /* Port 0.3 registers */
+				0x82000800 0 0xe0000000 MBUS_ID(0x04, 0xe8) 0xe0000000 0 0x08000000 /* Port 0.0 MEM */
+				0x81000800 0 0          MBUS_ID(0x04, 0xe0) 0xe8000000 0 0x00100000 /* Port 0.0 IO */>;
+
+
+			pcie@1,0 {
+				/* Port 0, Lane 0 */
+				status = "okay";
+			};
+		};
+
+		internal-regs {
+			compatible = "simple-bus";
+			#address-cells = <1>;
+			#size-cells = <1>;
+			ranges = <0 MBUS_ID(0xf0, 0x01) 0 0x100000>;
+
+			mbusc: mbus-controller@20000 {
+				reg = <0x20000 0x100>, <0x20180 0x20>;
+			};
+
+			interrupt-controller@20000 {
+			      reg = <0x20a00 0x2d0>, <0x21070 0x58>;
+			};
+		};
+	};
diff --git a/Documentation/devicetree/bindings/c6x/dscr.txt b/Documentation/devicetree/bindings/c6x/dscr.txt
index d847758f2b20..b0e97144cfb1 100644
--- a/Documentation/devicetree/bindings/c6x/dscr.txt
+++ b/Documentation/devicetree/bindings/c6x/dscr.txt
@@ -5,7 +5,7 @@ TI C6X SoCs contain a region of miscellaneous registers which provide various
 function for SoC control or status. Details vary considerably among from SoC
 to SoC with no two being alike.
 
-In general, the Device State Configuraion Registers (DSCR) will provide one or
+In general, the Device State Configuration Registers (DSCR) will provide one or
 more configuration registers often protected by a lock register where one or
 more key values must be written to a lock register in order to unlock the
 configuration register for writes. These configuration register may be used to
diff --git a/Documentation/devicetree/bindings/clock/clk-exynos-audss.txt b/Documentation/devicetree/bindings/clock/clk-exynos-audss.txt
index a1201802f90d..75e2e1999f87 100644
--- a/Documentation/devicetree/bindings/clock/clk-exynos-audss.txt
+++ b/Documentation/devicetree/bindings/clock/clk-exynos-audss.txt
@@ -2,7 +2,7 @@
 
 The Samsung Audio Subsystem clock controller generates and supplies clocks
 to Audio Subsystem block available in the S5PV210 and Exynos SoCs. The clock
-binding described here is applicable to all SoC's in Exynos family.
+binding described here is applicable to all SoCs in Exynos family.
 
 Required Properties:
 
diff --git a/Documentation/devicetree/bindings/clock/exynos4-clock.txt b/Documentation/devicetree/bindings/clock/exynos4-clock.txt
index 14d5c2af26f4..c6bf8a6c8f52 100644
--- a/Documentation/devicetree/bindings/clock/exynos4-clock.txt
+++ b/Documentation/devicetree/bindings/clock/exynos4-clock.txt
@@ -236,6 +236,7 @@ Exynos4 SoC and this is specified where applicable.
   spi0_isp_sclk       380     Exynos4x12
   spi1_isp_sclk       381     Exynos4x12
   uart_isp_sclk       382     Exynos4x12
+  tmu_apbif           383
 
 		[Mux Clocks]
 
diff --git a/Documentation/devicetree/bindings/clock/exynos5250-clock.txt b/Documentation/devicetree/bindings/clock/exynos5250-clock.txt
index 781a6276adf7..24765c146e31 100644
--- a/Documentation/devicetree/bindings/clock/exynos5250-clock.txt
+++ b/Documentation/devicetree/bindings/clock/exynos5250-clock.txt
@@ -59,6 +59,9 @@ clock which they consume.
   sclk_spi0		154
   sclk_spi1		155
   sclk_spi2		156
+  div_i2s1		157
+  div_i2s2		158
+  sclk_hdmiphy		159
 
 
    [Peripheral Clock Gates]
@@ -154,7 +157,16 @@ clock which they consume.
   dsim0			341
   dp			342
   mixer			343
-  hdmi			345
+  hdmi			344
+  g2d			345
+
+
+   [Clock Muxes]
+
+  Clock			ID
+  ----------------------------
+  mout_hdmi		1024
+
 
 Example 1: An example of a clock controller node is listed below.
 
diff --git a/Documentation/devicetree/bindings/clock/exynos5420-clock.txt b/Documentation/devicetree/bindings/clock/exynos5420-clock.txt
index 9bcc4b1bff51..32aa34ecad36 100644
--- a/Documentation/devicetree/bindings/clock/exynos5420-clock.txt
+++ b/Documentation/devicetree/bindings/clock/exynos5420-clock.txt
@@ -59,6 +59,7 @@ clock which they consume.
   sclk_pwm		155
   sclk_gscl_wa		156
   sclk_gscl_wb		157
+  sclk_hdmiphy		158
 
    [Peripheral Clock Gates]
 
@@ -179,6 +180,17 @@ clock which they consume.
   fimc_lite3		495
   aclk_g3d		500
   g3d			501
+  smmu_mixer		502
+
+  Mux			ID
+  ----------------------------
+
+  mout_hdmi		640
+
+  Divider		ID
+  ----------------------------
+
+  dout_pixel		768
 
 Example 1: An example of a clock controller node is listed below.
 
diff --git a/Documentation/devicetree/bindings/clock/imx5-clock.txt b/Documentation/devicetree/bindings/clock/imx5-clock.txt
index f46f5625d8ad..4c029a8739d3 100644
--- a/Documentation/devicetree/bindings/clock/imx5-clock.txt
+++ b/Documentation/devicetree/bindings/clock/imx5-clock.txt
@@ -197,6 +197,7 @@ clocks and IDs.
 	spdif0_gate		183
 	spdif1_gate		184
 	spdif_ipg_gate		185
+	ocram			186
 
 Examples (for mx53):
 
diff --git a/Documentation/devicetree/bindings/clock/imx6q-clock.txt b/Documentation/devicetree/bindings/clock/imx6q-clock.txt
index a0e104f0527e..5a90a724b520 100644
--- a/Documentation/devicetree/bindings/clock/imx6q-clock.txt
+++ b/Documentation/devicetree/bindings/clock/imx6q-clock.txt
@@ -209,6 +209,12 @@ clocks and IDs.
 	pll5_post_div		194
 	pll5_video_div		195
 	eim_slow      		196
+	spdif      		197
+	cko2_sel      		198
+	cko2_podf      		199
+	cko2      		200
+	cko      		201
+	vdoa      		202
 
 Examples:
 
diff --git a/Documentation/devicetree/bindings/clock/samsung,s3c64xx-clock.txt b/Documentation/devicetree/bindings/clock/samsung,s3c64xx-clock.txt
new file mode 100644
index 000000000000..fa171dc4bd3c
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/samsung,s3c64xx-clock.txt
@@ -0,0 +1,77 @@
+* Samsung S3C64xx Clock Controller
+
+The S3C64xx clock controller generates and supplies clock to various controllers
+within the SoC. The clock binding described here is applicable to all SoCs in
+the S3C64xx family.
+
+Required Properties:
+
+- compatible: should be one of the following.
+  - "samsung,s3c6400-clock" - controller compatible with S3C6400 SoC.
+  - "samsung,s3c6410-clock" - controller compatible with S3C6410 SoC.
+
+- reg: physical base address of the controller and length of memory mapped
+  region.
+
+- #clock-cells: should be 1.
+
+Each clock is assigned an identifier and client nodes can use this identifier
+to specify the clock which they consume. Some of the clocks are available only
+on a particular S3C64xx SoC and this is specified where applicable.
+
+All available clocks are defined as preprocessor macros in
+dt-bindings/clock/samsung,s3c64xx-clock.h header and can be used in device
+tree sources.
+
+External clocks:
+
+There are several clocks that are generated outside the SoC. It is expected
+that they are defined using standard clock bindings with following
+clock-output-names:
+ - "fin_pll" - PLL input clock (xtal/extclk) - required,
+ - "xusbxti" - USB xtal - required,
+ - "iiscdclk0" - I2S0 codec clock - optional,
+ - "iiscdclk1" - I2S1 codec clock - optional,
+ - "iiscdclk2" - I2S2 codec clock - optional,
+ - "pcmcdclk0" - PCM0 codec clock - optional,
+ - "pcmcdclk1" - PCM1 codec clock - optional, only S3C6410.
+
+Example: Clock controller node:
+
+	clock: clock-controller@7e00f000 {
+		compatible = "samsung,s3c6410-clock";
+		reg = <0x7e00f000 0x1000>;
+		#clock-cells = <1>;
+	};
+
+Example: Required external clocks:
+
+	fin_pll: clock-fin-pll {
+		compatible = "fixed-clock";
+		clock-output-names = "fin_pll";
+		clock-frequency = <12000000>;
+		#clock-cells = <0>;
+	};
+
+	xusbxti: clock-xusbxti {
+		compatible = "fixed-clock";
+		clock-output-names = "xusbxti";
+		clock-frequency = <48000000>;
+		#clock-cells = <0>;
+	};
+
+Example: UART controller node that consumes the clock generated by the clock
+  controller (refer to the standard clock bindings for information about
+  "clocks" and "clock-names" properties):
+
+		uart0: serial@7f005000 {
+			compatible = "samsung,s3c6400-uart";
+			reg = <0x7f005000 0x100>;
+			interrupt-parent = <&vic1>;
+			interrupts = <5>;
+			clock-names = "uart", "clk_uart_baud2",
+					"clk_uart_baud3";
+			clocks = <&clock PCLK_UART0>, <&clocks PCLK_UART0>,
+					<&clock SCLK_UART>;
+			status = "disabled";
+		};
diff --git a/Documentation/devicetree/bindings/clock/st,nomadik.txt b/Documentation/devicetree/bindings/clock/st,nomadik.txt
index 7fc09773de46..40e0cf1f7b99 100644
--- a/Documentation/devicetree/bindings/clock/st,nomadik.txt
+++ b/Documentation/devicetree/bindings/clock/st,nomadik.txt
@@ -17,7 +17,7 @@ Optional properties for the SRC node:
 - disable-mxtal: if present this will disable the MXTALO,
   i.e. the driver output for the main (~19.2 MHz) chrystal,
   if the board has its own circuitry for providing this
-  osciallator
+  oscillator
 
 
 PLL nodes: these nodes represent the two PLLs on the system,
diff --git a/Documentation/devicetree/bindings/clock/sunxi.txt b/Documentation/devicetree/bindings/clock/sunxi.txt
index d495521a79d2..00a5c26454eb 100644
--- a/Documentation/devicetree/bindings/clock/sunxi.txt
+++ b/Documentation/devicetree/bindings/clock/sunxi.txt
@@ -8,19 +8,31 @@ Required properties:
 - compatible : shall be one of the following:
 	"allwinner,sun4i-osc-clk" - for a gatable oscillator
 	"allwinner,sun4i-pll1-clk" - for the main PLL clock
+	"allwinner,sun6i-a31-pll1-clk" - for the main PLL clock on A31
 	"allwinner,sun4i-cpu-clk" - for the CPU multiplexer clock
 	"allwinner,sun4i-axi-clk" - for the AXI clock
 	"allwinner,sun4i-axi-gates-clk" - for the AXI gates
 	"allwinner,sun4i-ahb-clk" - for the AHB clock
 	"allwinner,sun4i-ahb-gates-clk" - for the AHB gates on A10
 	"allwinner,sun5i-a13-ahb-gates-clk" - for the AHB gates on A13
+	"allwinner,sun5i-a10s-ahb-gates-clk" - for the AHB gates on A10s
+	"allwinner,sun7i-a20-ahb-gates-clk" - for the AHB gates on A20
+	"allwinner,sun6i-a31-ahb1-mux-clk" - for the AHB1 multiplexer on A31
+	"allwinner,sun6i-a31-ahb1-gates-clk" - for the AHB1 gates on A31
 	"allwinner,sun4i-apb0-clk" - for the APB0 clock
 	"allwinner,sun4i-apb0-gates-clk" - for the APB0 gates on A10
 	"allwinner,sun5i-a13-apb0-gates-clk" - for the APB0 gates on A13
+	"allwinner,sun5i-a10s-apb0-gates-clk" - for the APB0 gates on A10s
+	"allwinner,sun7i-a20-apb0-gates-clk" - for the APB0 gates on A20
 	"allwinner,sun4i-apb1-clk" - for the APB1 clock
 	"allwinner,sun4i-apb1-mux-clk" - for the APB1 clock muxing
 	"allwinner,sun4i-apb1-gates-clk" - for the APB1 gates on A10
 	"allwinner,sun5i-a13-apb1-gates-clk" - for the APB1 gates on A13
+	"allwinner,sun5i-a10s-apb1-gates-clk" - for the APB1 gates on A10s
+	"allwinner,sun6i-a31-apb1-gates-clk" - for the APB1 gates on A31
+	"allwinner,sun7i-a20-apb1-gates-clk" - for the APB1 gates on A20
+	"allwinner,sun6i-a31-apb2-div-clk" - for the APB2 gates on A31
+	"allwinner,sun6i-a31-apb2-gates-clk" - for the APB2 gates on A31
 
 Required properties for all clocks:
 - reg : shall be the control register address for the clock.
diff --git a/Documentation/devicetree/bindings/clock/sunxi/sun5i-a10s-gates.txt b/Documentation/devicetree/bindings/clock/sunxi/sun5i-a10s-gates.txt
new file mode 100644
index 000000000000..d24279fe1429
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/sunxi/sun5i-a10s-gates.txt
@@ -0,0 +1,75 @@
+Gate clock outputs
+------------------
+
+  * AXI gates ("allwinner,sun4i-axi-gates-clk")
+
+    DRAM					0
+
+  * AHB gates ("allwinner,sun5i-a10s-ahb-gates-clk")
+
+    USB0					0
+    EHCI0					1
+    OHCI0					2
+
+    SS						5
+    DMA						6
+    BIST					7
+    MMC0					8
+    MMC1					9
+    MMC2					10
+
+    NAND					13
+    SDRAM					14
+
+    EMAC					17
+    TS						18
+
+    SPI0					20
+    SPI1					21
+    SPI2					22
+
+    GPS						26
+
+    HSTIMER					28
+
+    VE						32
+
+    TVE						34
+
+    LCD						36
+
+    CSI						40
+
+    HDMI					43
+    DE_BE					44
+
+    DE_FE					46
+
+    IEP						51
+    MALI400					52
+
+  * APB0 gates ("allwinner,sun5i-a10s-apb0-gates-clk")
+
+    CODEC					0
+
+    IIS						3
+
+    PIO						5
+    IR						6
+
+    KEYPAD					10
+
+  * APB1 gates ("allwinner,sun5i-a10s-apb1-gates-clk")
+
+    I2C0					0
+    I2C1					1
+    I2C2					2
+
+    UART0					16
+    UART1					17
+    UART2					18
+    UART3					19
+
+Notation:
+ [*]:  The datasheet didn't mention these, but they are present on AW code
+ [**]: The datasheet had this marked as "NC" but they are used on AW code
diff --git a/Documentation/devicetree/bindings/clock/sunxi/sun6i-a31-gates.txt b/Documentation/devicetree/bindings/clock/sunxi/sun6i-a31-gates.txt
new file mode 100644
index 000000000000..fe44932b5c6b
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/sunxi/sun6i-a31-gates.txt
@@ -0,0 +1,83 @@
+Gate clock outputs
+------------------
+
+  * AHB1 gates ("allwinner,sun6i-a31-ahb1-gates-clk")
+
+    MIPI DSI					1
+
+    SS						5
+    DMA						6
+
+    MMC0					8
+    MMC1					9
+    MMC2					10
+    MMC3					11
+
+    NAND1					12
+    NAND0					13
+    SDRAM					14
+
+    GMAC					17
+    TS						18
+    HSTIMER					19
+    SPI0					20
+    SPI1					21
+    SPI2					22
+    SPI3					23
+    USB_OTG					24
+
+    EHCI0					26
+    EHCI1					27
+
+    OHCI0					29
+    OHCI1					30
+    OHCI2					31
+    VE						32
+
+    LCD0					36
+    LCD1					37
+
+    CSI						40
+
+    HDMI					43
+    DE_BE0					44
+    DE_BE1					45
+    DE_FE1					46
+    DE_FE1					47
+
+    MP						50
+
+    GPU						52
+
+    DEU0					55
+    DEU1					56
+    DRC0					57
+    DRC1					58
+
+  * APB1 gates ("allwinner,sun6i-a31-apb1-gates-clk")
+
+    CODEC					0
+
+    DIGITAL MIC					4
+    PIO						5
+
+    DAUDIO0					12
+    DAUDIO1					13
+
+  * APB2 gates ("allwinner,sun6i-a31-apb2-gates-clk")
+
+    I2C0					0
+    I2C1					1
+    I2C2					2
+    I2C3					3
+
+    UART0					16
+    UART1					17
+    UART2					18
+    UART3					19
+    UART4					20
+    UART5					21
+
+Notation:
+ [*]:  The datasheet didn't mention these, but they are present on AW code
+ [**]: The datasheet had this marked as "NC" but they are used on AW code
diff --git a/Documentation/devicetree/bindings/clock/sunxi/sun7i-a20-gates.txt b/Documentation/devicetree/bindings/clock/sunxi/sun7i-a20-gates.txt
new file mode 100644
index 000000000000..357f4fdc02ef
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/sunxi/sun7i-a20-gates.txt
@@ -0,0 +1,98 @@
+Gate clock outputs
+------------------
+
+  * AXI gates ("allwinner,sun4i-axi-gates-clk")
+
+    DRAM					0
+
+  * AHB gates ("allwinner,sun7i-a20-ahb-gates-clk")
+
+    USB0					0
+    EHCI0					1
+    OHCI0					2
+    EHCI1					3
+    OHCI1					4
+    SS						5
+    DMA						6
+    BIST					7
+    MMC0					8
+    MMC1					9
+    MMC2					10
+    MMC3					11
+    MS						12
+    NAND					13
+    SDRAM					14
+
+    ACE						16
+    EMAC					17
+    TS						18
+
+    SPI0					20
+    SPI1					21
+    SPI2					22
+    SPI3					23
+
+    SATA					25
+
+    HSTIMER					28
+
+    VE						32
+    TVD						33
+    TVE0					34
+    TVE1					35
+    LCD0					36
+    LCD1					37
+
+    CSI0					40
+    CSI1					41
+
+    HDMI1					42
+    HDMI0					43
+    DE_BE0					44
+    DE_BE1					45
+    DE_FE1					46
+    DE_FE1					47
+
+    GMAC					49
+    MP						50
+
+    MALI400					52
+
+  * APB0 gates ("allwinner,sun7i-a20-apb0-gates-clk")
+
+    CODEC					0
+    SPDIF					1
+    AC97					2
+    IIS0					3
+    IIS1					4
+    PIO						5
+    IR0						6
+    IR1						7
+    IIS2					8
+
+    KEYPAD					10
+
+  * APB1 gates ("allwinner,sun7i-a20-apb1-gates-clk")
+
+    I2C0					0
+    I2C1					1
+    I2C2					2
+    I2C3					3
+    CAN						4
+    SCR						5
+    PS20					6
+    PS21					7
+
+    I2C4					15
+    UART0					16
+    UART1					17
+    UART2					18
+    UART3					19
+    UART4					20
+    UART5					21
+    UART6					22
+    UART7					23
+
+Notation:
+ [*]:  The datasheet didn't mention these, but they are present on AW code
+ [**]: The datasheet had this marked as "NC" but they are used on AW code
diff --git a/Documentation/devicetree/bindings/crypto/fsl-sec6.txt b/Documentation/devicetree/bindings/crypto/fsl-sec6.txt
new file mode 100644
index 000000000000..c0a20cd972e3
--- /dev/null
+++ b/Documentation/devicetree/bindings/crypto/fsl-sec6.txt
@@ -0,0 +1,157 @@
+SEC 6 is as Freescale's Cryptographic Accelerator and Assurance Module (CAAM).
+Currently Freescale powerpc chip C29X is embeded with SEC 6.
+SEC 6 device tree binding include:
+   -SEC 6 Node
+   -Job Ring Node
+   -Full Example
+
+=====================================================================
+SEC 6 Node
+
+Description
+
+    Node defines the base address of the SEC 6 block.
+    This block specifies the address range of all global
+    configuration registers for the SEC 6 block.
+    For example, In C293, we could see three SEC 6 node.
+
+PROPERTIES
+
+   - compatible
+      Usage: required
+      Value type: <string>
+      Definition: Must include "fsl,sec-v6.0".
+
+   - fsl,sec-era
+      Usage: optional
+      Value type: <u32>
+      Definition: A standard property. Define the 'ERA' of the SEC
+          device.
+
+   - #address-cells
+       Usage: required
+       Value type: <u32>
+       Definition: A standard property.  Defines the number of cells
+           for representing physical addresses in child nodes.
+
+   - #size-cells
+       Usage: required
+       Value type: <u32>
+       Definition: A standard property.  Defines the number of cells
+           for representing the size of physical addresses in
+           child nodes.
+
+   - reg
+      Usage: required
+      Value type: <prop-encoded-array>
+      Definition: A standard property.  Specifies the physical
+          address and length of the SEC 6 configuration registers.
+
+   - ranges
+       Usage: required
+       Value type: <prop-encoded-array>
+       Definition: A standard property.  Specifies the physical address
+           range of the SEC 6.0 register space (-SNVS not included).  A
+           triplet that includes the child address, parent address, &
+           length.
+
+   Note: All other standard properties (see the ePAPR) are allowed
+   but are optional.
+
+EXAMPLE
+	crypto@a0000 {
+		compatible = "fsl,sec-v6.0";
+		fsl,sec-era = <6>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		reg = <0xa0000 0x20000>;
+		ranges = <0 0xa0000 0x20000>;
+	};
+
+=====================================================================
+Job Ring (JR) Node
+
+    Child of the crypto node defines data processing interface to SEC 6
+    across the peripheral bus for purposes of processing
+    cryptographic descriptors. The specified address
+    range can be made visible to one (or more) cores.
+    The interrupt defined for this node is controlled within
+    the address range of this node.
+
+  - compatible
+      Usage: required
+      Value type: <string>
+      Definition: Must include "fsl,sec-v6.0-job-ring".
+
+  - reg
+      Usage: required
+      Value type: <prop-encoded-array>
+      Definition: Specifies a two JR parameters:  an offset from
+           the parent physical address and the length the JR registers.
+
+   - interrupts
+      Usage: required
+      Value type: <prop_encoded-array>
+      Definition:  Specifies the interrupts generated by this
+           device.  The value of the interrupts property
+           consists of one interrupt specifier. The format
+           of the specifier is defined by the binding document
+           describing the node's interrupt parent.
+
+EXAMPLE
+	jr@1000 {
+		compatible = "fsl,sec-v6.0-job-ring";
+		reg = <0x1000 0x1000>;
+		interrupts = <49 2 0 0>;
+	};
+
+===================================================================
+Full Example
+
+Since some chips may contain more than one SEC, the dtsi contains
+only the node contents, not the node itself.  A chip using the SEC
+should include the dtsi inside each SEC node.  Example:
+
+In qoriq-sec6.0.dtsi:
+
+	compatible = "fsl,sec-v6.0";
+	fsl,sec-era = <6>;
+	#address-cells = <1>;
+	#size-cells = <1>;
+
+	jr@1000 {
+		compatible = "fsl,sec-v6.0-job-ring",
+			     "fsl,sec-v5.2-job-ring",
+			     "fsl,sec-v5.0-job-ring",
+			     "fsl,sec-v4.4-job-ring",
+			     "fsl,sec-v4.0-job-ring";
+		reg	   = <0x1000 0x1000>;
+	};
+
+	jr@2000 {
+		compatible = "fsl,sec-v6.0-job-ring",
+			     "fsl,sec-v5.2-job-ring",
+			     "fsl,sec-v5.0-job-ring",
+			     "fsl,sec-v4.4-job-ring",
+			     "fsl,sec-v4.0-job-ring";
+		reg	   = <0x2000 0x1000>;
+	};
+
+In the C293 device tree, we add the include of public property:
+
+	crypto@a0000 {
+		/include/ "qoriq-sec6.0.dtsi"
+	}
+
+	crypto@a0000 {
+		reg = <0xa0000 0x20000>;
+		ranges = <0 0xa0000 0x20000>;
+
+		jr@1000 {
+			interrupts = <49 2 0 0>;
+		};
+
+		jr@2000 {
+			interrupts = <50 2 0 0>;
+		};
+	};
diff --git a/Documentation/devicetree/bindings/dma/atmel-dma.txt b/Documentation/devicetree/bindings/dma/atmel-dma.txt
index c280a0e6f42d..e1f343c7a34b 100644
--- a/Documentation/devicetree/bindings/dma/atmel-dma.txt
+++ b/Documentation/devicetree/bindings/dma/atmel-dma.txt
@@ -18,14 +18,14 @@ dma0: dma@ffffec00 {
 
 DMA clients connected to the Atmel DMA controller must use the format
 described in the dma.txt file, using a three-cell specifier for each channel:
-a phandle plus two interger cells.
+a phandle plus two integer cells.
 The three cells in order are:
 
 1. A phandle pointing to the DMA controller.
 2. The memory interface (16 most significant bits), the peripheral interface
 (16 less significant bits).
 3. Parameters for the at91 DMA configuration register which are device
-dependant:
+dependent:
   - bit 7-0: peripheral identifier for the hardware handshaking interface. The
   identifier can be different for tx and rx.
   - bit 11-8: FIFO configuration. 0 for half FIFO, 1 for ALAP, 1 for ASAP.
diff --git a/Documentation/devicetree/bindings/dma/fsl-imx-dma.txt b/Documentation/devicetree/bindings/dma/fsl-imx-dma.txt
index 2717ecb47db9..7bd8847d6394 100644
--- a/Documentation/devicetree/bindings/dma/fsl-imx-dma.txt
+++ b/Documentation/devicetree/bindings/dma/fsl-imx-dma.txt
@@ -34,7 +34,7 @@ Clients have to specify the DMA requests with phandles in a list.
 Required properties:
 - dmas: List of one or more DMA request specifiers. One DMA request specifier
     consists of a phandle to the DMA controller followed by the integer
-    specifiying the request line.
+    specifying the request line.
 - dma-names: List of string identifiers for the DMA requests. For the correct
     names, have a look at the specific client driver.
 
diff --git a/Documentation/devicetree/bindings/dma/fsl-imx-sdma.txt b/Documentation/devicetree/bindings/dma/fsl-imx-sdma.txt
index 68cee4f5539f..4fa814d38321 100644
--- a/Documentation/devicetree/bindings/dma/fsl-imx-sdma.txt
+++ b/Documentation/devicetree/bindings/dma/fsl-imx-sdma.txt
@@ -1,7 +1,12 @@
 * Freescale Smart Direct Memory Access (SDMA) Controller for i.MX
 
 Required properties:
-- compatible : Should be "fsl,<chip>-sdma"
+- compatible : Should be "fsl,imx31-sdma", "fsl,imx31-to1-sdma",
+  "fsl,imx31-to2-sdma", "fsl,imx35-sdma", "fsl,imx35-to1-sdma",
+  "fsl,imx35-to2-sdma", "fsl,imx51-sdma", "fsl,imx53-sdma" or
+  "fsl,imx6q-sdma". The -to variants should be preferred since they
+  allow to determnine the correct ROM script addresses needed for
+  the driver to work without additional firmware.
 - reg : Should contain SDMA registers location and length
 - interrupts : Should contain SDMA interrupt
 - #dma-cells : Must be <3>.
diff --git a/Documentation/devicetree/bindings/dma/k3dma.txt b/Documentation/devicetree/bindings/dma/k3dma.txt
new file mode 100644
index 000000000000..23f8d712c3ce
--- /dev/null
+++ b/Documentation/devicetree/bindings/dma/k3dma.txt
@@ -0,0 +1,46 @@
+* Hisilicon K3 DMA controller
+
+See dma.txt first
+
+Required properties:
+- compatible: Should be "hisilicon,k3-dma-1.0"
+- reg: Should contain DMA registers location and length.
+- interrupts: Should contain one interrupt shared by all channel
+- #dma-cells: see dma.txt, should be 1, para number
+- dma-channels: physical channels supported
+- dma-requests: virtual channels supported, each virtual channel
+		have specific request line
+- clocks: clock required
+
+Example:
+
+Controller:
+		dma0: dma@fcd02000 {
+			compatible = "hisilicon,k3-dma-1.0";
+			reg = <0xfcd02000 0x1000>;
+			#dma-cells = <1>;
+			dma-channels = <16>;
+			dma-requests = <27>;
+			interrupts = <0 12 4>;
+			clocks = <&pclk>;
+			status = "disable";
+		};
+
+Client:
+Use specific request line passing from dmax
+For example, i2c0 read channel request line is 18, while write channel use 19
+
+		i2c0: i2c@fcb08000 {
+			compatible = "snps,designware-i2c";
+			dmas =	<&dma0 18          /* read channel */
+				 &dma0 19>;        /* write channel */
+			dma-names = "rx", "tx";
+		};
+
+		i2c1: i2c@fcb09000 {
+			compatible = "snps,designware-i2c";
+			dmas =	<&dma0 20          /* read channel */
+				 &dma0 21>;        /* write channel */
+			dma-names = "rx", "tx";
+		};
+
diff --git a/Documentation/devicetree/bindings/dma/shdma.txt b/Documentation/devicetree/bindings/dma/shdma.txt
index c15994aa1939..2a3f3b8946b9 100644
--- a/Documentation/devicetree/bindings/dma/shdma.txt
+++ b/Documentation/devicetree/bindings/dma/shdma.txt
@@ -22,42 +22,51 @@ Optional properties (currently unused):
 * DMA controller
 
 Required properties:
-- compatible:	should be "renesas,shdma"
+- compatible:	should be of the form "renesas,shdma-<soc>", where <soc> should
+		be replaced with the desired SoC model, e.g.
+		"renesas,shdma-r8a73a4" for the system DMAC on r8a73a4 SoC
 
 Example:
-	dmac: dma-mux0 {
+	dmac: dma-multiplexer@0 {
 		compatible = "renesas,shdma-mux";
 		#dma-cells = <1>;
-		dma-channels = <6>;
+		dma-channels = <20>;
 		dma-requests = <256>;
-		reg = <0 0>;	/* Needed for AUXDATA */
-		#address-cells = <1>;
-		#size-cells = <1>;
+		#address-cells = <2>;
+		#size-cells = <2>;
 		ranges;
 
-		dma0: shdma@fe008020 {
-			compatible = "renesas,shdma";
-			reg = <0xfe008020 0x270>,
-				<0xfe009000 0xc>;
+		dma0: dma-controller@e6700020 {
+			compatible = "renesas,shdma-r8a73a4";
+			reg = <0 0xe6700020 0 0x89e0>;
 			interrupt-parent = <&gic>;
-			interrupts = <0 34 4
-					0 28 4
-					0 29 4
-					0 30 4
-					0 31 4
-					0 32 4
-					0 33 4>;
+			interrupts = <0 220 4
+					0 200 4
+					0 201 4
+					0 202 4
+					0 203 4
+					0 204 4
+					0 205 4
+					0 206 4
+					0 207 4
+					0 208 4
+					0 209 4
+					0 210 4
+					0 211 4
+					0 212 4
+					0 213 4
+					0 214 4
+					0 215 4
+					0 216 4
+					0 217 4
+					0 218 4
+					0 219 4>;
 			interrupt-names = "error",
 					"ch0", "ch1", "ch2", "ch3",
-					"ch4", "ch5";
-		};
-
-		dma1: shdma@fe018020 {
-			...
-		};
-
-		dma2: shdma@fe028020 {
-			...
+					"ch4", "ch5", "ch6", "ch7",
+					"ch8", "ch9", "ch10", "ch11",
+					"ch12", "ch13", "ch14", "ch15",
+					"ch16", "ch17", "ch18", "ch19";
 		};
 	};
 
diff --git a/Documentation/devicetree/bindings/dma/ste-dma40.txt b/Documentation/devicetree/bindings/dma/ste-dma40.txt
index bea5b73a7390..a8c21c256baa 100644
--- a/Documentation/devicetree/bindings/dma/ste-dma40.txt
+++ b/Documentation/devicetree/bindings/dma/ste-dma40.txt
@@ -37,14 +37,14 @@ Each dmas request consists of 4 cells:
   1. A phandle pointing to the DMA controller
   2. Device Type
   3. The DMA request line number (only when 'use fixed channel' is set)
-  4. A 32bit mask specifying; mode, direction and endianess [NB: This list will grow]
+  4. A 32bit mask specifying; mode, direction and endianness [NB: This list will grow]
         0x00000001: Mode:
                 Logical channel when unset
                 Physical channel when set
         0x00000002: Direction:
                 Memory to Device when unset
                 Device to Memory when set
-        0x00000004: Endianess:
+        0x00000004: Endianness:
                 Little endian when unset
                 Big endian when set
         0x00000008: Use fixed channel:
diff --git a/Documentation/devicetree/bindings/extcon/extcon-twl.txt b/Documentation/devicetree/bindings/extcon/extcon-palmas.txt
index 58f531ab4df3..7dab6a8f4a0e 100644
--- a/Documentation/devicetree/bindings/extcon/extcon-twl.txt
+++ b/Documentation/devicetree/bindings/extcon/extcon-palmas.txt
@@ -1,15 +1,15 @@
-EXTCON FOR TWL CHIPS
+EXTCON FOR PALMAS/TWL CHIPS
 
 PALMAS USB COMPARATOR
 Required Properties:
  - compatible : Should be "ti,palmas-usb" or "ti,twl6035-usb"
- - vbus-supply : phandle to the regulator device tree node.
 
 Optional Properties:
  - ti,wakeup : To enable the wakeup comparator in probe
+ - ti,enable-id-detection: Perform ID detection.
+ - ti,enable-vbus-detection: Perform VBUS detection.
 
 palmas-usb {
        compatible = "ti,twl6035-usb", "ti,palmas-usb";
-       vbus-supply = <&smps10_reg>;
        ti,wakeup;
 };
diff --git a/Documentation/devicetree/bindings/gpio/gpio-mcp23s08.txt b/Documentation/devicetree/bindings/gpio/gpio-mcp23s08.txt
index 629d0ef17308..daa30174bcc1 100644
--- a/Documentation/devicetree/bindings/gpio/gpio-mcp23s08.txt
+++ b/Documentation/devicetree/bindings/gpio/gpio-mcp23s08.txt
@@ -3,10 +3,17 @@ Microchip MCP2308/MCP23S08/MCP23017/MCP23S17 driver for
 
 Required properties:
 - compatible : Should be
-    - "mcp,mcp23s08" for  8 GPIO SPI version
-    - "mcp,mcp23s17" for 16 GPIO SPI version
-    - "mcp,mcp23008" for  8 GPIO I2C version or
-    - "mcp,mcp23017" for 16 GPIO I2C version of the chip
+    - "mcp,mcp23s08" (DEPRECATED) for  8 GPIO SPI version
+    - "mcp,mcp23s17" (DEPRECATED) for 16 GPIO SPI version
+    - "mcp,mcp23008" (DEPRECATED) for  8 GPIO I2C version or
+    - "mcp,mcp23017" (DEPRECATED) for 16 GPIO I2C version of the chip
+
+    - "microchip,mcp23s08" for  8 GPIO SPI version
+    - "microchip,mcp23s17" for 16 GPIO SPI version
+    - "microchip,mcp23008" for  8 GPIO I2C version or
+    - "microchip,mcp23017" for 16 GPIO I2C version of the chip
+    NOTE: Do not use the old mcp prefix any more. It is deprecated and will be
+    removed.
 - #gpio-cells : Should be two.
   - first cell is the pin number
   - second cell is used to specify flags. Flags are currently unused.
@@ -15,10 +22,11 @@ Required properties:
         SPI uses this to specify the chipselect line which the chip is
         connected to. The driver and the SPI variant of the chip support
         multiple chips on the same chipselect. Have a look at
-        mcp,spi-present-mask below.
+        microchip,spi-present-mask below.
 
 Required device specific properties (only for SPI chips):
-- mcp,spi-present-mask : This is a present flag, that makes only sense for SPI
+- mcp,spi-present-mask (DEPRECATED)
+- microchip,spi-present-mask : This is a present flag, that makes only sense for SPI
         chips - as the name suggests. Multiple SPI chips can share the same
         SPI chipselect. Set a bit in bit0-7 in this mask to 1 if there is a
         chip connected with the corresponding spi address set. For example if
@@ -26,11 +34,13 @@ Required device specific properties (only for SPI chips):
         which is 0x08. mcp23s08 chip variant only supports bits 0-3. It is not
         possible to mix mcp23s08 and mcp23s17 on the same chipselect. Set at
         least one bit to 1 for SPI chips.
+    NOTE: Do not use the old mcp prefix any more. It is deprecated and will be
+    removed.
 - spi-max-frequency = The maximum frequency this chip is able to handle
 
 Example I2C:
 gpiom1: gpio@20 {
-        compatible = "mcp,mcp23017";
+        compatible = "microchip,mcp23017";
         gpio-controller;
         #gpio-cells = <2>;
         reg = <0x20>;
@@ -38,7 +48,7 @@ gpiom1: gpio@20 {
 
 Example SPI:
 gpiom1: gpio@0 {
-        compatible = "mcp,mcp23s17";
+        compatible = "microchip,mcp23s17";
         gpio-controller;
         #gpio-cells = <2>;
         spi-present-mask = <0x01>;
diff --git a/Documentation/devicetree/bindings/gpio/gpio-palmas.txt b/Documentation/devicetree/bindings/gpio/gpio-palmas.txt
new file mode 100644
index 000000000000..08b5b52a3ae0
--- /dev/null
+++ b/Documentation/devicetree/bindings/gpio/gpio-palmas.txt
@@ -0,0 +1,27 @@
+Palmas GPIO controller bindings
+
+Required properties:
+- compatible:
+  - "ti,palams-gpio" for palma series of the GPIO controller
+  - "ti,tps80036-gpio" for Palma series device TPS80036.
+  - "ti,tps65913-gpio" for palma series device TPS65913.
+  - "ti,tps65914-gpio" for palma series device TPS65914.
+- #gpio-cells : Should be two.
+  - first cell is the gpio pin number
+  - second cell is used to specify the gpio polarity:
+      0 = active high
+      1 = active low
+- gpio-controller : Marks the device node as a GPIO controller.
+
+Note: This gpio node will be sub node of palmas node.
+
+Example:
+	palmas: tps65913@58 {
+		:::::::::::
+		palmas_gpio: palmas_gpio {
+			compatible = "ti,palmas-gpio";
+			gpio-controller;
+			#gpio-cells = <2>;
+		};
+		:::::::::::
+	};
diff --git a/Documentation/devicetree/bindings/gpio/gpio-tz1090-pdc.txt b/Documentation/devicetree/bindings/gpio/gpio-tz1090-pdc.txt
new file mode 100644
index 000000000000..1fd98ffa8cb7
--- /dev/null
+++ b/Documentation/devicetree/bindings/gpio/gpio-tz1090-pdc.txt
@@ -0,0 +1,45 @@
+ImgTec TZ1090 PDC GPIO Controller
+
+Required properties:
+- compatible: Compatible property value should be "img,tz1090-pdc-gpio".
+
+- reg: Physical base address of the controller and length of memory mapped
+  region. This starts at and cover the SOC_GPIO_CONTROL registers.
+
+- gpio-controller: Specifies that the node is a gpio controller.
+
+- #gpio-cells: Should be 2. The syntax of the gpio specifier used by client
+  nodes should have the following values.
+     <[phandle of the gpio controller node]
+      [PDC gpio number]
+      [gpio flags]>
+
+  Values for gpio specifier:
+  - GPIO number: a value in the range 0 to 6.
+  - GPIO flags: bit field of flags, as defined in <dt-bindings/gpio/gpio.h>.
+    Only the following flags are supported:
+      GPIO_ACTIVE_HIGH
+      GPIO_ACTIVE_LOW
+
+Optional properties:
+- gpio-ranges: Mapping to pin controller pins (as described in
+  Documentation/devicetree/bindings/gpio/gpio.txt)
+
+- interrupts: Individual syswake interrupts (other GPIOs cannot interrupt)
+
+
+Example:
+
+	pdc_gpios: gpio-controller@02006500 {
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		compatible = "img,tz1090-pdc-gpio";
+		reg = <0x02006500 0x100>;
+
+		interrupt-parent = <&pdc>;
+		interrupts =	<8  IRQ_TYPE_NONE>,	/* Syswake 0 */
+				<9  IRQ_TYPE_NONE>,	/* Syswake 1 */
+				<10 IRQ_TYPE_NONE>;	/* Syswake 2 */
+		gpio-ranges = <&pdc_pinctrl 0 0 7>;
+	};
diff --git a/Documentation/devicetree/bindings/gpio/gpio-tz1090.txt b/Documentation/devicetree/bindings/gpio/gpio-tz1090.txt
new file mode 100644
index 000000000000..174cdf309170
--- /dev/null
+++ b/Documentation/devicetree/bindings/gpio/gpio-tz1090.txt
@@ -0,0 +1,88 @@
+ImgTec TZ1090 GPIO Controller
+
+Required properties:
+- compatible: Compatible property value should be "img,tz1090-gpio".
+
+- reg: Physical base address of the controller and length of memory mapped
+  region.
+
+- #address-cells: Should be 1 (for bank subnodes)
+
+- #size-cells: Should be 0 (for bank subnodes)
+
+- Each bank of GPIOs should have a subnode to represent it.
+
+  Bank subnode required properties:
+  - reg: Index of bank in the range 0 to 2.
+
+  - gpio-controller: Specifies that the node is a gpio controller.
+
+  - #gpio-cells: Should be 2. The syntax of the gpio specifier used by client
+    nodes should have the following values.
+       <[phandle of the gpio controller node]
+        [gpio number within the gpio bank]
+        [gpio flags]>
+
+    Values for gpio specifier:
+    - GPIO number: a value in the range 0 to 29.
+    - GPIO flags: bit field of flags, as defined in <dt-bindings/gpio/gpio.h>.
+      Only the following flags are supported:
+        GPIO_ACTIVE_HIGH
+        GPIO_ACTIVE_LOW
+
+  Bank subnode optional properties:
+  - gpio-ranges: Mapping to pin controller pins (as described in
+    Documentation/devicetree/bindings/gpio/gpio.txt)
+
+  - interrupts: Interrupt for the entire bank
+
+  - interrupt-controller: Specifies that the node is an interrupt controller
+
+  - #interrupt-cells: Should be 2. The syntax of the interrupt specifier used by
+    client nodes should have the following values.
+       <[phandle of the interurupt controller]
+        [gpio number within the gpio bank]
+        [irq flags]>
+
+    Values for irq specifier:
+    - GPIO number: a value in the range 0 to 29
+    - IRQ flags: value to describe edge and level triggering, as defined in
+      <dt-bindings/interrupt-controller/irq.h>. Only the following flags are
+      supported:
+        IRQ_TYPE_EDGE_RISING
+        IRQ_TYPE_EDGE_FALLING
+        IRQ_TYPE_EDGE_BOTH
+        IRQ_TYPE_LEVEL_HIGH
+        IRQ_TYPE_LEVEL_LOW
+
+
+
+Example:
+
+	gpios: gpio-controller@02005800 {
+		#address-cells = <1>;
+		#size-cells = <0>;
+		compatible = "img,tz1090-gpio";
+		reg = <0x02005800 0x90>;
+
+		/* bank 0 with an interrupt */
+		gpios0: bank@0 {
+			#gpio-cells = <2>;
+			#interrupt-cells = <2>;
+			reg = <0>;
+			interrupts = <13 IRQ_TYPE_LEVEL_HIGH>;
+			gpio-controller;
+			gpio-ranges = <&pinctrl 0 0 30>;
+			interrupt-controller;
+		};
+
+		/* bank 2 without interrupt */
+		gpios2: bank@2 {
+			#gpio-cells = <2>;
+			reg = <2>;
+			gpio-controller;
+			gpio-ranges = <&pinctrl 0 60 30>;
+		};
+	};
+
+
diff --git a/Documentation/devicetree/bindings/gpio/gpio.txt b/Documentation/devicetree/bindings/gpio/gpio.txt
index d933af370697..6cec6ff20d2e 100644
--- a/Documentation/devicetree/bindings/gpio/gpio.txt
+++ b/Documentation/devicetree/bindings/gpio/gpio.txt
@@ -75,23 +75,36 @@ Example of two SOC GPIO banks defined as gpio-controller nodes:
 		gpio-controller;
 	};
 
-2.1) gpio-controller and pinctrl subsystem
-------------------------------------------
+2.1) gpio- and pin-controller interaction
+-----------------------------------------
 
-gpio-controller on a SOC might be tightly coupled with the pinctrl
-subsystem, in the sense that the pins can be used by other functions
-together with optional gpio feature.
+Some or all of the GPIOs provided by a GPIO controller may be routed to pins
+on the package via a pin controller. This allows muxing those pins between
+GPIO and other functions.
 
-While the pin allocation is totally managed by the pin ctrl subsystem,
-gpio (under gpiolib) is still maintained by gpio drivers. It may happen
-that different pin ranges in a SoC is managed by different gpio drivers.
+It is useful to represent which GPIOs correspond to which pins on which pin
+controllers. The gpio-ranges property described below represents this, and
+contains information structures as follows:
 
-This makes it logical to let gpio drivers announce their pin ranges to
-the pin ctrl subsystem and call 'pinctrl_request_gpio' in order to
-request the corresponding pin before any gpio usage.
+	gpio-range-list ::= <single-gpio-range> [gpio-range-list]
+	single-gpio-range ::=
+			<pinctrl-phandle> <gpio-base> <pinctrl-base> <count>
+	gpio-phandle : phandle to pin controller node.
+	gpio-base : Base GPIO ID in the GPIO controller
+	pinctrl-base : Base pinctrl pin ID in the pin controller
+	count : The number of GPIOs/pins in this range
 
-For this, the gpio controller can use a pinctrl phandle and pins to
-announce the pinrange to the pin ctrl subsystem. For example,
+The "pin controller node" mentioned above must conform to the bindings
+described in ../pinctrl/pinctrl-bindings.txt.
+
+Previous versions of this binding required all pin controller nodes that
+were referenced by any gpio-ranges property to contain a property named
+#gpio-range-cells with value <3>. This requirement is now deprecated.
+However, that property may still exist in older device trees for
+compatibility reasons, and would still be required even in new device
+trees that need to be compatible with older software.
+
+Example:
 
 	qe_pio_e: gpio-controller@1460 {
 		#gpio-cells = <2>;
@@ -99,16 +112,8 @@ announce the pinrange to the pin ctrl subsystem. For example,
 		reg = <0x1460 0x18>;
 		gpio-controller;
 		gpio-ranges = <&pinctrl1 0 20 10>, <&pinctrl2 10 50 20>;
+	};
 
-    }
-
-where,
-   &pinctrl1 and &pinctrl2 is the phandle to the pinctrl DT node.
-
-   Next values specify the base pin and number of pins for the range
-   handled by 'qe_pio_e' gpio. In the given example from base pin 20 to
-   pin 29 under pinctrl1 with gpio offset 0 and pin 50 to pin 69 under
-   pinctrl2 with gpio offset 10 is handled by this gpio controller.
-
-The pinctrl node must have "#gpio-range-cells" property to show number of
-arguments to pass with phandle from gpio controllers node.
+Here, a single GPIO controller has GPIOs 0..9 routed to pin controller
+pinctrl1's pins 20..29, and GPIOs 10..19 routed to pin controller pinctrl2's
+pins 50..59.
diff --git a/Documentation/devicetree/bindings/gpio/mrvl-gpio.txt b/Documentation/devicetree/bindings/gpio/mrvl-gpio.txt
index 9b3f1d4a88d6..66416261e14d 100644
--- a/Documentation/devicetree/bindings/gpio/mrvl-gpio.txt
+++ b/Documentation/devicetree/bindings/gpio/mrvl-gpio.txt
@@ -10,8 +10,9 @@ Required properties:
   There're three gpio interrupts in arch-pxa, and they're gpio0,
   gpio1 and gpio_mux. There're only one gpio interrupt in arch-mmp,
   gpio_mux.
-- interrupt-name : Should be the name of irq resource. Each interrupt
-  binds its interrupt-name.
+- interrupt-names : Should be the names of irq resources. Each interrupt
+  uses its own interrupt name, so there should be as many interrupt names
+  as referenced interrups.
 - interrupt-controller : Identifies the node as an interrupt controller.
 - #interrupt-cells: Specifies the number of cells needed to encode an
   interrupt source.
@@ -24,7 +25,7 @@ Example:
 		compatible = "marvell,mmp-gpio";
 		reg = <0xd4019000 0x1000>;
 		interrupts = <49>;
-		interrupt-name = "gpio_mux";
+		interrupt-names = "gpio_mux";
 		gpio-controller;
 		#gpio-cells = <1>;
 		interrupt-controller;
diff --git a/Documentation/devicetree/bindings/gpio/renesas,gpio-rcar.txt b/Documentation/devicetree/bindings/gpio/renesas,gpio-rcar.txt
index cb3dc7bcd8e6..8655df9440d5 100644
--- a/Documentation/devicetree/bindings/gpio/renesas,gpio-rcar.txt
+++ b/Documentation/devicetree/bindings/gpio/renesas,gpio-rcar.txt
@@ -23,6 +23,10 @@ Required Properties:
 Please refer to gpio.txt in this directory for details of gpio-ranges property
 and the common GPIO bindings used by client devices.
 
+The GPIO controller also acts as an interrupt controller. It uses the default
+two cells specifier as described in Documentation/devicetree/bindings/
+interrupt-controller/interrupts.txt.
+
 Example: R8A7779 (R-Car H1) GPIO controller nodes
 
 	gpio0: gpio@ffc40000 {
@@ -33,6 +37,8 @@ Example: R8A7779 (R-Car H1) GPIO controller nodes
 		#gpio-cells = <2>;
 		gpio-controller;
 		gpio-ranges = <&pfc 0 0 32>;
+		interrupt-controller;
+		#interrupt-cells = <2>;
 	};
 	...
 	gpio6: gpio@ffc46000 {
@@ -43,4 +49,6 @@ Example: R8A7779 (R-Car H1) GPIO controller nodes
 		#gpio-cells = <2>;
 		gpio-controller;
 		gpio-ranges = <&pfc 0 192 9>;
+		interrupt-controller;
+		#interrupt-cells = <2>;
 	};
diff --git a/Documentation/devicetree/bindings/gpu/samsung-g2d.txt b/Documentation/devicetree/bindings/gpu/samsung-g2d.txt
index 3f454ffc654a..c4f358dafdaa 100644
--- a/Documentation/devicetree/bindings/gpu/samsung-g2d.txt
+++ b/Documentation/devicetree/bindings/gpu/samsung-g2d.txt
@@ -11,8 +11,11 @@ Required properties:
 
   - interrupts : G2D interrupt number to the CPU.
   - clocks : from common clock binding: handle to G2D clocks.
-  - clock-names : from common clock binding: must contain "sclk_fimg2d" and
-		  "fimg2d", corresponding to entries in the clocks property.
+  - clock-names : names of clocks listed in clocks property, in the same
+		  order, depending on SoC type:
+		  - for S5PV210 and Exynos4 based SoCs: "fimg2d" and
+		    "sclk_fimg2d"
+		  - for Exynos5250 SoC: "fimg2d".
 
 Example:
 	g2d@12800000 {
diff --git a/Documentation/devicetree/bindings/gpu/samsung-rotator.txt b/Documentation/devicetree/bindings/gpu/samsung-rotator.txt
new file mode 100644
index 000000000000..82cd1ed0be93
--- /dev/null
+++ b/Documentation/devicetree/bindings/gpu/samsung-rotator.txt
@@ -0,0 +1,27 @@
+* Samsung Image Rotator
+
+Required properties:
+  - compatible : value should be one of the following:
+	(a) "samsung,exynos4210-rotator" for Rotator IP in Exynos4210
+	(b) "samsung,exynos4212-rotator" for Rotator IP in Exynos4212/4412
+	(c) "samsung,exynos5250-rotator" for Rotator IP in Exynos5250
+
+  - reg : Physical base address of the IP registers and length of memory
+	  mapped region.
+
+  - interrupts : Interrupt specifier for rotator interrupt, according to format
+		 specific to interrupt parent.
+
+  - clocks : Clock specifier for rotator clock, according to generic clock
+	     bindings. (See Documentation/devicetree/bindings/clock/exynos*.txt)
+
+  - clock-names : Names of clocks. For exynos rotator, it should be "rotator".
+
+Example:
+	rotator@12810000 {
+		compatible = "samsung,exynos4210-rotator";
+		reg = <0x12810000 0x1000>;
+		interrupts = <0 83 0>;
+		clocks = <&clock 278>;
+		clock-names = "rotator";
+	};
diff --git a/Documentation/devicetree/bindings/hid/hid-over-i2c.txt b/Documentation/devicetree/bindings/hid/hid-over-i2c.txt
new file mode 100644
index 000000000000..488edcb264c4
--- /dev/null
+++ b/Documentation/devicetree/bindings/hid/hid-over-i2c.txt
@@ -0,0 +1,28 @@
+* HID over I2C Device-Tree bindings
+
+HID over I2C provides support for various Human Interface Devices over the
+I2C bus. These devices can be for example touchpads, keyboards, touch screens
+or sensors.
+
+The specification has been written by Microsoft and is currently available here:
+http://msdn.microsoft.com/en-us/library/windows/hardware/hh852380.aspx
+
+If this binding is used, the kernel module i2c-hid will handle the communication
+with the device and the generic hid core layer will handle the protocol.
+
+Required properties:
+- compatible: must be "hid-over-i2c"
+- reg: i2c slave address
+- hid-descr-addr: HID descriptor address
+- interrupt-parent: the phandle for the interrupt controller
+- interrupts: interrupt line
+
+Example:
+
+	i2c-hid-dev@2c {
+		compatible = "hid-over-i2c";
+		reg = <0x2c>;
+		hid-descr-addr = <0x0020>;
+		interrupt-parent = <&gpx3>;
+		interrupts = <3 2>;
+	};
diff --git a/Documentation/devicetree/bindings/i2c/i2c-imx.txt b/Documentation/devicetree/bindings/i2c/i2c-imx.txt
index 3614242e7732..4a8513e44740 100644
--- a/Documentation/devicetree/bindings/i2c/i2c-imx.txt
+++ b/Documentation/devicetree/bindings/i2c/i2c-imx.txt
@@ -1,7 +1,10 @@
 * Freescale Inter IC (I2C) and High Speed Inter IC (HS-I2C) for i.MX
 
 Required properties:
-- compatible : Should be "fsl,<chip>-i2c"
+- compatible :
+  - "fsl,imx1-i2c" for I2C compatible with the one integrated on i.MX1 SoC
+  - "fsl,imx21-i2c" for I2C compatible with the one integrated on i.MX21 SoC
+  - "fsl,vf610-i2c" for I2C compatible with the one integrated on Vybrid vf610 SoC
 - reg : Should contain I2C/HS-I2C registers location and length
 - interrupts : Should contain I2C/HS-I2C interrupt
 
diff --git a/Documentation/devicetree/bindings/i2c/i2c-mv64xxx.txt b/Documentation/devicetree/bindings/i2c/i2c-mv64xxx.txt
index 6113f9275f42..82e8f6f17179 100644
--- a/Documentation/devicetree/bindings/i2c/i2c-mv64xxx.txt
+++ b/Documentation/devicetree/bindings/i2c/i2c-mv64xxx.txt
@@ -5,6 +5,7 @@ Required properties :
 
  - reg             : Offset and length of the register set for the device
  - compatible      : Should be "marvell,mv64xxx-i2c" or "allwinner,sun4i-i2c"
+                     or "marvell,mv78230-i2c"
  - interrupts      : The interrupt number
 
 Optional properties :
@@ -20,3 +21,12 @@ Examples:
 		interrupts = <29>;
 		clock-frequency = <100000>;
 	};
+
+For the Armada XP:
+
+	i2c@11000 {
+		compatible = "marvell,mv78230-i2c", "marvell,mv64xxx-i2c";
+		reg = <0x11000 0x100>;
+		interrupts = <29>;
+		clock-frequency = <100000>;
+	};
diff --git a/Documentation/devicetree/bindings/iio/accel/bma180.txt b/Documentation/devicetree/bindings/iio/accel/bma180.txt
new file mode 100644
index 000000000000..c5933573e0f6
--- /dev/null
+++ b/Documentation/devicetree/bindings/iio/accel/bma180.txt
@@ -0,0 +1,24 @@
+* Bosch BMA180 triaxial acceleration sensor
+
+http://omapworld.com/BMA180_111_1002839.pdf
+
+Required properties:
+
+  - compatible : should be "bosch,bma180"
+  - reg : the I2C address of the sensor
+
+Optional properties:
+
+  - interrupt-parent : should be the phandle for the interrupt controller
+
+  - interrupts : interrupt mapping for GPIO IRQ, it should by configured with
+		flags IRQ_TYPE_LEVEL_HIGH | IRQ_TYPE_EDGE_RISING
+
+Example:
+
+bma180@40 {
+	compatible = "bosch,bma180";
+	reg = <0x40>;
+	interrupt-parent = <&gpio6>;
+	interrupts = <18 (IRQ_TYPE_LEVEL_HIGH | IRQ_TYPE_EDGE_RISING)>;
+};
diff --git a/Documentation/devicetree/bindings/iio/adc/nuvoton-nau7802.txt b/Documentation/devicetree/bindings/iio/adc/nuvoton-nau7802.txt
new file mode 100644
index 000000000000..e9582e6fe350
--- /dev/null
+++ b/Documentation/devicetree/bindings/iio/adc/nuvoton-nau7802.txt
@@ -0,0 +1,18 @@
+* Nuvoton NAU7802 Analog to Digital Converter (ADC)
+
+Required properties:
+  - compatible: Should be "nuvoton,nau7802"
+  - reg: Should contain the ADC I2C address
+
+Optional properties:
+  - nuvoton,vldo: Internal reference voltage in millivolts to be
+    configured valid values are between 2400 mV and 4500 mV.
+  - interrupts: IRQ line for the ADC. If not used the driver will use
+    polling.
+
+Example:
+adc2: nau7802@2a {
+	compatible = "nuvoton,nau7802";
+	reg = <0x2a>;
+	nuvoton,vldo = <3000>;
+};
diff --git a/Documentation/devicetree/bindings/iio/light/apds9300.txt b/Documentation/devicetree/bindings/iio/light/apds9300.txt
new file mode 100644
index 000000000000..d6f66c73ddbf
--- /dev/null
+++ b/Documentation/devicetree/bindings/iio/light/apds9300.txt
@@ -0,0 +1,22 @@
+* Avago APDS9300 ambient light sensor
+
+http://www.avagotech.com/docs/AV02-1077EN
+
+Required properties:
+
+  - compatible : should be "avago,apds9300"
+  - reg : the I2C address of the sensor
+
+Optional properties:
+
+  - interrupt-parent : should be the phandle for the interrupt controller
+  - interrupts : interrupt mapping for GPIO IRQ
+
+Example:
+
+apds9300@39 {
+	compatible = "avago,apds9300";
+	reg = <0x39>;
+	interrupt-parent = <&gpio2>;
+	interrupts = <29 8>;
+};
diff --git a/Documentation/devicetree/bindings/input/input-reset.txt b/Documentation/devicetree/bindings/input/input-reset.txt
new file mode 100644
index 000000000000..2bb2626fdb78
--- /dev/null
+++ b/Documentation/devicetree/bindings/input/input-reset.txt
@@ -0,0 +1,33 @@
+Input: sysrq reset sequence
+
+A simple binding to represent a set of keys as described in
+include/uapi/linux/input.h. This is to communicate a sequence of keys to the
+sysrq driver. Upon holding the keys for a specified amount of time (if
+specified) the system is sync'ed and reset.
+
+Key sequences are global to the system but all the keys in a set must be coming
+from the same input device.
+
+The /chosen node should contain a 'linux,sysrq-reset-seq' child node to define
+a set of keys.
+
+Required property:
+sysrq-reset-seq: array of Linux keycodes, one keycode per cell.
+
+Optional property:
+timeout-ms: duration keys must be pressed together in milliseconds before
+generating a sysrq. If omitted the system is rebooted immediately when a valid
+sequence has been recognized.
+
+Example:
+
+ chosen {
+                linux,sysrq-reset-seq {
+                        keyset = <0x03
+                                  0x04
+                                  0x0a>;
+                        timeout-ms = <3000>;
+                };
+         };
+
+Would represent KEY_2, KEY_3 and KEY_9.
diff --git a/Documentation/devicetree/bindings/input/touchscreen/egalax-ts.txt b/Documentation/devicetree/bindings/input/touchscreen/egalax-ts.txt
index df70318a617f..49fa14ed155c 100644
--- a/Documentation/devicetree/bindings/input/touchscreen/egalax-ts.txt
+++ b/Documentation/devicetree/bindings/input/touchscreen/egalax-ts.txt
@@ -6,7 +6,7 @@ Required properties:
 - interrupt-parent: the phandle for the interrupt controller
 - interrupts: touch controller interrupt
 - wakeup-gpios: the gpio pin to be used for waking up the controller
-  as well as uased as irq pin
+  and also used as irq pin
 
 Example:
 
diff --git a/Documentation/devicetree/bindings/leds/leds-lp55xx.txt b/Documentation/devicetree/bindings/leds/leds-lp55xx.txt
index d5176882d8b9..a61727f9a6d1 100644
--- a/Documentation/devicetree/bindings/leds/leds-lp55xx.txt
+++ b/Documentation/devicetree/bindings/leds/leds-lp55xx.txt
@@ -1,7 +1,7 @@
 Binding for TI/National Semiconductor LP55xx Led Drivers
 
 Required properties:
-- compatible: "national,lp5521" or "national,lp5523" or "ti,lp5562"
+- compatible: "national,lp5521" or "national,lp5523" or "ti,lp5562" or "ti,lp8501"
 - reg: I2C slave address
 - clock-mode: Input clock mode, (0: automode, 1: internal, 2: external)
 
@@ -11,6 +11,11 @@ Each child has own specific current settings
 
 Optional properties:
 - label: Used for naming LEDs
+- pwr-sel: LP8501 specific property. Power selection for output channels.
+         0: D1~9 are connected to VDD
+         1: D1~6 with VDD, D7~9 with VOUT
+         2: D1~6 with VOUT, D7~9 with VDD
+         3: D1~9 are connected to VOUT
 
 Alternatively, each child can have specific channel name
 - chan-name: Name of each channel name
@@ -145,3 +150,68 @@ lp5562@30 {
 		max-cur = /bits/ 8 <0x60>;
 	};
 };
+
+example 4) LP8501
+9 channels are defined. The 'pwr-sel' is LP8501 specific property.
+Others are same as LP5523.
+
+lp8501@32 {
+	compatible = "ti,lp8501";
+	reg = <0x32>;
+	clock-mode = /bits/ 8 <2>;
+	pwr-sel = /bits/ 8 <3>;	/* D1~9 connected to VOUT */
+
+	chan0 {
+		chan-name = "d1";
+		led-cur = /bits/ 8 <0x14>;
+		max-cur = /bits/ 8 <0x20>;
+	};
+
+	chan1 {
+		chan-name = "d2";
+		led-cur = /bits/ 8 <0x14>;
+		max-cur = /bits/ 8 <0x20>;
+	};
+
+	chan2 {
+		chan-name = "d3";
+		led-cur = /bits/ 8 <0x14>;
+		max-cur = /bits/ 8 <0x20>;
+	};
+
+	chan3 {
+		chan-name = "d4";
+		led-cur = /bits/ 8 <0x14>;
+		max-cur = /bits/ 8 <0x20>;
+	};
+
+	chan4 {
+		chan-name = "d5";
+		led-cur = /bits/ 8 <0x14>;
+		max-cur = /bits/ 8 <0x20>;
+	};
+
+	chan5 {
+		chan-name = "d6";
+		led-cur = /bits/ 8 <0x14>;
+		max-cur = /bits/ 8 <0x20>;
+	};
+
+	chan6 {
+		chan-name = "d7";
+		led-cur = /bits/ 8 <0x14>;
+		max-cur = /bits/ 8 <0x20>;
+	};
+
+	chan7 {
+		chan-name = "d8";
+		led-cur = /bits/ 8 <0x14>;
+		max-cur = /bits/ 8 <0x20>;
+	};
+
+	chan8 {
+		chan-name = "d9";
+		led-cur = /bits/ 8 <0x14>;
+		max-cur = /bits/ 8 <0x20>;
+	};
+};
diff --git a/Documentation/devicetree/bindings/leds/pca963x.txt b/Documentation/devicetree/bindings/leds/pca963x.txt
new file mode 100644
index 000000000000..aece3eac1b63
--- /dev/null
+++ b/Documentation/devicetree/bindings/leds/pca963x.txt
@@ -0,0 +1,47 @@
+LEDs connected to pca9632, pca9633 or pca9634
+
+Required properties:
+- compatible : should be : "nxp,pca9632", "nxp,pca9633" or "nxp,pca9634"
+
+Optional properties:
+- nxp,totem-pole : use totem pole (push-pull) instead of default open-drain
+- nxp,hw-blink : use hardware blinking instead of software blinking
+
+Each led is represented as a sub-node of the nxp,pca963x device.
+
+LED sub-node properties:
+- label : (optional) see Documentation/devicetree/bindings/leds/common.txt
+- reg : number of LED line (could be from 0 to 3  in pca9632 or pca9633
+		or 0 to 7 in pca9634)
+- linux,default-trigger : (optional)
+   see Documentation/devicetree/bindings/leds/common.txt
+
+Examples:
+
+pca9632: pca9632 {
+	compatible = "nxp,pca9632";
+	#address-cells = <1>;
+	#size-cells = <0>;
+	reg = <0x62>;
+
+	red@0 {
+		label = "red";
+		reg = <0>;
+		linux,default-trigger = "none";
+	};
+	green@1 {
+		label = "green";
+		reg = <1>;
+		linux,default-trigger = "none";
+	};
+	blue@2 {
+		label = "blue";
+		reg = <2>;
+		linux,default-trigger = "none";
+	};
+	unused@3 {
+		label = "unused";
+		reg = <3>;
+		linux,default-trigger = "none";
+	};
+};
diff --git a/Documentation/devicetree/bindings/media/i2c/adv7343.txt b/Documentation/devicetree/bindings/media/i2c/adv7343.txt
new file mode 100644
index 000000000000..5653bc2428b8
--- /dev/null
+++ b/Documentation/devicetree/bindings/media/i2c/adv7343.txt
@@ -0,0 +1,48 @@
+* Analog Devices adv7343 video encoder
+
+The ADV7343 are high speed, digital-to-analog video encoders in a 64-lead LQFP
+package. Six high speed, 3.3 V, 11-bit video DACs provide support for composite
+(CVBS), S-Video (Y-C), and component (YPrPb/RGB) analog outputs in standard
+definition (SD), enhanced definition (ED), or high definition (HD) video
+formats.
+
+Required Properties :
+- compatible: Must be "adi,adv7343"
+
+Optional Properties :
+- adi,power-mode-sleep-mode: on enable the current consumption is reduced to
+			      micro ampere level. All DACs and the internal PLL
+			      circuit are disabled.
+- adi,power-mode-pll-ctrl: PLL and oversampling control. This control allows
+			   internal PLL 1 circuit to be powered down and the
+			   oversampling to be switched off.
+- ad,adv7343-power-mode-dac: array configuring the power on/off DAC's 1..6,
+			      0 = OFF and 1 = ON, Default value when this
+			      property is not specified is <0 0 0 0 0 0>.
+- ad,adv7343-sd-config-dac-out: array configure SD DAC Output's 1 and 2, 0 = OFF
+				 and 1 = ON, Default value when this property is
+				 not specified is <0 0>.
+
+Example:
+
+i2c0@1c22000 {
+	...
+	...
+
+	adv7343@2a {
+		compatible = "adi,adv7343";
+		reg = <0x2a>;
+
+		port {
+			adv7343_1: endpoint {
+					adi,power-mode-sleep-mode;
+					adi,power-mode-pll-ctrl;
+					/* Use DAC1..3, DAC6 */
+					adi,dac-enable = <1 1 1 0 0 1>;
+					/* Use SD DAC output 1 */
+					adi,sd-dac-enable = <1 0>;
+			};
+		};
+	};
+	...
+};
diff --git a/Documentation/devicetree/bindings/media/i2c/ths8200.txt b/Documentation/devicetree/bindings/media/i2c/ths8200.txt
new file mode 100644
index 000000000000..285f6ae7dfa9
--- /dev/null
+++ b/Documentation/devicetree/bindings/media/i2c/ths8200.txt
@@ -0,0 +1,19 @@
+* Texas Instruments THS8200 video encoder
+
+The ths8200 device is a digital to analog converter used in DVD players, video
+recorders, set-top boxes.
+
+Required Properties :
+- compatible : value must be "ti,ths8200"
+
+Example:
+
+	i2c0@1c22000 {
+		...
+		...
+		ths8200@5c {
+			compatible = "ti,ths8200";
+			reg = <0x5c>;
+		};
+		...
+	};
diff --git a/Documentation/devicetree/bindings/media/i2c/tvp7002.txt b/Documentation/devicetree/bindings/media/i2c/tvp7002.txt
new file mode 100644
index 000000000000..5f28b5d9abcc
--- /dev/null
+++ b/Documentation/devicetree/bindings/media/i2c/tvp7002.txt
@@ -0,0 +1,53 @@
+* Texas Instruments TV7002 video decoder
+
+The TVP7002 device supports digitizing of video and graphics signal in RGB and
+YPbPr color space.
+
+Required Properties :
+- compatible : Must be "ti,tvp7002"
+
+Optional Properties:
+- hsync-active: HSYNC Polarity configuration for the bus. Default value when
+  this property is not specified is <0>.
+
+- vsync-active: VSYNC Polarity configuration for the bus. Default value when
+  this property is not specified is <0>.
+
+- pclk-sample: Clock polarity of the bus. Default value when this property is
+  not specified is <0>.
+
+- sync-on-green-active: Active state of Sync-on-green signal property of the
+  endpoint.
+  0 = Normal Operation (Active Low, Default)
+  1 = Inverted operation
+
+- field-even-active: Active-high Field ID output polarity control of the bus.
+  Under normal operation, the field ID output is set to logic 1 for an odd field
+  (field 1) and set to logic 0 for an even field (field 0).
+  0 = Normal Operation (Active Low, Default)
+  1 = FID output polarity inverted
+
+For further reading of port node refer Documentation/devicetree/bindings/media/
+video-interfaces.txt.
+
+Example:
+
+	i2c0@1c22000 {
+		...
+		...
+		tvp7002@5c {
+			compatible = "ti,tvp7002";
+			reg = <0x5c>;
+
+			port {
+				tvp7002_1: endpoint {
+					hsync-active = <1>;
+					vsync-active = <1>;
+					pclk-sample = <0>;
+					sync-on-green-active = <1>;
+					field-even-active = <0>;
+				};
+			};
+		};
+		...
+	};
diff --git a/Documentation/devicetree/bindings/media/s5p-mfc.txt b/Documentation/devicetree/bindings/media/s5p-mfc.txt
index df37b0230c75..f4181680831b 100644
--- a/Documentation/devicetree/bindings/media/s5p-mfc.txt
+++ b/Documentation/devicetree/bindings/media/s5p-mfc.txt
@@ -10,14 +10,15 @@ Required properties:
   - compatible : value should be either one among the following
 	(a) "samsung,mfc-v5" for MFC v5 present in Exynos4 SoCs
 	(b) "samsung,mfc-v6" for MFC v6 present in Exynos5 SoCs
+	(b) "samsung,mfc-v7" for MFC v7 present in Exynos5420 SoC
 
   - reg : Physical base address of the IP registers and length of memory
 	  mapped region.
 
   - interrupts : MFC interrupt number to the CPU.
-  - clocks : from common clock binding: handle to mfc clocks.
-  - clock-names : from common clock binding: must contain "sclk_mfc" and "mfc",
-		  corresponding to entries in the clocks property.
+  - clocks : from common clock binding: handle to mfc clock.
+  - clock-names : from common clock binding: must contain "mfc",
+		  corresponding to entry in the clocks property.
 
   - samsung,mfc-r : Base address of the first memory bank used by MFC
 		    for DMA contiguous memory allocation and its size.
@@ -37,8 +38,8 @@ mfc: codec@13400000 {
 	reg = <0x13400000 0x10000>;
 	interrupts = <0 94 0>;
 	samsung,power-domain = <&pd_mfc>;
-	clocks = <&clock 170>, <&clock 273>;
-	clock-names = "sclk_mfc", "mfc";
+	clocks = <&clock 273>;
+	clock-names = "mfc";
 };
 
 Board specific DT entry:
diff --git a/Documentation/devicetree/bindings/media/video-interfaces.txt b/Documentation/devicetree/bindings/media/video-interfaces.txt
index e022d2dc4962..ce719f89dd1c 100644
--- a/Documentation/devicetree/bindings/media/video-interfaces.txt
+++ b/Documentation/devicetree/bindings/media/video-interfaces.txt
@@ -88,6 +88,8 @@ Optional endpoint properties
 - field-even-active: field signal level during the even field data transmission.
 - pclk-sample: sample data on rising (1) or falling (0) edge of the pixel clock
   signal.
+- sync-on-green-active: active state of Sync-on-green (SoG) signal, 0/1 for
+  LOW/HIGH respectively.
 - data-lanes: an array of physical data lane indexes. Position of an entry
   determines the logical lane number, while the value of an entry indicates
   physical lane, e.g. for 2-lane MIPI CSI-2 bus we could have
diff --git a/Documentation/devicetree/bindings/metag/pdc-intc.txt b/Documentation/devicetree/bindings/metag/pdc-intc.txt
new file mode 100644
index 000000000000..a69118550344
--- /dev/null
+++ b/Documentation/devicetree/bindings/metag/pdc-intc.txt
@@ -0,0 +1,105 @@
+* ImgTec Powerdown Controller (PDC) Interrupt Controller Binding
+
+This binding specifies what properties must be available in the device tree
+representation of a PDC IRQ controller. This has a number of input interrupt
+lines which can wake the system, and are passed on through output interrupt
+lines.
+
+Required properties:
+
+    - compatible: Specifies the compatibility list for the interrupt controller.
+      The type shall be <string> and the value shall include "img,pdc-intc".
+
+    - reg: Specifies the base PDC physical address(s) and size(s) of the
+      addressable register space. The type shall be <prop-encoded-array>.
+
+    - interrupt-controller: The presence of this property identifies the node
+      as an interrupt controller. No property value shall be defined.
+
+    - #interrupt-cells: Specifies the number of cells needed to encode an
+      interrupt source. The type shall be a <u32> and the value shall be 2.
+
+    - num-perips: Number of waking peripherals.
+
+    - num-syswakes: Number of SysWake inputs.
+
+    - interrupts: List of interrupt specifiers. The first specifier shall be the
+      shared SysWake interrupt, and remaining specifies shall be PDC peripheral
+      interrupts in order.
+
+* Interrupt Specifier Definition
+
+  Interrupt specifiers consists of 2 cells encoded as follows:
+
+    - <1st-cell>: The interrupt-number that identifies the interrupt source.
+                    0-7:  Peripheral interrupts
+                    8-15: SysWake interrupts
+
+    - <2nd-cell>: The level-sense information, encoded using the Linux interrupt
+                  flags as follows (only 4 valid for peripheral interrupts):
+                    0 = none (decided by software)
+                    1 = low-to-high edge triggered
+                    2 = high-to-low edge triggered
+                    3 = both edge triggered
+                    4 = active-high level-sensitive (required for perip irqs)
+                    8 = active-low level-sensitive
+
+* Examples
+
+Example 1:
+
+	/*
+	 * TZ1090 PDC block
+	 */
+	pdc: pdc@0x02006000 {
+		// This is an interrupt controller node.
+		interrupt-controller;
+
+		// Three cells to encode interrupt sources.
+		#interrupt-cells = <2>;
+
+		// Offset address of 0x02006000 and size of 0x1000.
+		reg = <0x02006000 0x1000>;
+
+		// Compatible with Meta hardware trigger block.
+		compatible = "img,pdc-intc";
+
+		// Three peripherals are connected.
+		num-perips = <3>;
+
+		// Four SysWakes are connected.
+		num-syswakes = <4>;
+
+		interrupts = <18 4 /* level */>, /* Syswakes */
+			     <30 4 /* level */>, /* Peripheral 0 (RTC) */
+			     <29 4 /* level */>, /* Peripheral 1 (IR) */
+			     <31 4 /* level */>; /* Peripheral 2 (WDT) */
+	};
+
+Example 2:
+
+	/*
+	 * An SoC peripheral that is wired through the PDC.
+	 */
+	rtc0 {
+		// The interrupt controller that this device is wired to.
+		interrupt-parent = <&pdc>;
+
+		// Interrupt source Peripheral 0
+		interrupts = <0   /* Peripheral 0 (RTC) */
+		              4>  /* IRQ_TYPE_LEVEL_HIGH */
+	};
+
+Example 3:
+
+	/*
+	 * An interrupt generating device that is wired to a SysWake pin.
+	 */
+	touchscreen0 {
+		// The interrupt controller that this device is wired to.
+		interrupt-parent = <&pdc>;
+
+		// Interrupt source SysWake 0 that is active-low level-sensitive
+		interrupts = <8 /* SysWake0 */
+			      8 /* IRQ_TYPE_LEVEL_LOW */>;
+	};
diff --git a/Documentation/devicetree/bindings/mfd/cros-ec.txt b/Documentation/devicetree/bindings/mfd/cros-ec.txt
index e0e59c58a1f9..5f229c5f6da9 100644
--- a/Documentation/devicetree/bindings/mfd/cros-ec.txt
+++ b/Documentation/devicetree/bindings/mfd/cros-ec.txt
@@ -4,7 +4,7 @@ Google's ChromeOS EC is a Cortex-M device which talks to the AP and
 implements various function such as keyboard and battery charging.
 
 The EC can be connect through various means (I2C, SPI, LPC) and the
-compatible string used depends on the inteface. Each connection method has
+compatible string used depends on the interface. Each connection method has
 its own driver which connects to the top level interface-agnostic EC driver.
 Other Linux driver (such as cros-ec-keyb for the matrix keyboard) connect to
 the top-level driver.
diff --git a/Documentation/devicetree/bindings/mfd/palmas.txt b/Documentation/devicetree/bindings/mfd/palmas.txt
index 892537d1a48f..e5f0f8303461 100644
--- a/Documentation/devicetree/bindings/mfd/palmas.txt
+++ b/Documentation/devicetree/bindings/mfd/palmas.txt
@@ -5,6 +5,7 @@ twl6035 (palmas)
 twl6037 (palmas)
 tps65913 (palmas)
 tps65914 (palmas)
+tps659038
 
 Required properties:
 - compatible : Should be from the list
@@ -14,6 +15,7 @@ Required properties:
   ti,tps65913
   ti,tps65914
   ti,tps80036
+  ti,tps659038
 and also the generic series names
   ti,palmas
 - interrupt-controller : palmas has its own internal IRQs
diff --git a/Documentation/devicetree/bindings/mfd/s2mps11.txt b/Documentation/devicetree/bindings/mfd/s2mps11.txt
new file mode 100644
index 000000000000..c9332c626021
--- /dev/null
+++ b/Documentation/devicetree/bindings/mfd/s2mps11.txt
@@ -0,0 +1,109 @@
+
+* Samsung S2MPS11 Voltage and Current Regulator
+
+The Samsung S2MP211 is a multi-function device which includes voltage and
+current regulators, RTC, charger controller and other sub-blocks. It is
+interfaced to the host controller using a I2C interface. Each sub-block is
+addressed by the host system using different I2C slave address.
+
+Required properties:
+- compatible: Should be "samsung,s2mps11-pmic".
+- reg: Specifies the I2C slave address of the pmic block. It should be 0x66.
+
+Optional properties:
+- interrupt-parent: Specifies the phandle of the interrupt controller to which
+  the interrupts from s2mps11 are delivered to.
+- interrupts: Interrupt specifiers for interrupt sources.
+
+Optional nodes:
+- clocks: s2mps11 provides three(AP/CP/BT) buffered 32.768 KHz outputs, so to
+  register these as clocks with common clock framework instantiate a sub-node
+  named "clocks". It uses the common clock binding documented in :
+  [Documentation/devicetree/bindings/clock/clock-bindings.txt]
+  - #clock-cells: should be 1.
+
+  - The following is the list of clocks generated by the controller. Each clock
+    is assigned an identifier and client nodes use this identifier to specify
+    the clock which they consume.
+    Clock               ID
+    ----------------------
+    32KhzAP		0
+    32KhzCP		1
+    32KhzBT		2
+
+- regulators: The regulators of s2mps11 that have to be instantiated should be
+included in a sub-node named 'regulators'. Regulator nodes included in this
+sub-node should be of the format as listed below.
+
+	regulator_name {
+		[standard regulator constraints....];
+	};
+
+ regulator-ramp-delay for BUCKs = [6250/12500/25000(default)/50000] uV/us
+
+ BUCK[2/3/4/6] supports disabling ramp delay on hardware, so explictly
+ regulator-ramp-delay = <0> can be used for them to disable ramp delay.
+ In absence of regulator-ramp-delay property, default ramp delay will be used.
+
+NOTE: Some BUCKs share the ramp rate setting i.e. same ramp value will be set
+for a particular group of BUCKs. So provide same regulator-ramp-delay<value>.
+Grouping of BUCKs sharing ramp rate setting is as follow : BUCK[1, 6],
+BUCK[3, 4], and BUCK[7, 8, 10]
+
+The regulator constraints inside the regulator nodes use the standard regulator
+bindings which are documented elsewhere.
+
+The following are the names of the regulators that the s2mps11 pmic block
+supports. Note: The 'n' in LDOn and BUCKn represents the LDO or BUCK number
+as per the datasheet of s2mps11.
+
+	- LDOn
+		  - valid values for n are 1 to 28
+		  - Example: LDO0, LD01, LDO28
+	- BUCKn
+		  - valid values for n are 1 to 9.
+		  - Example: BUCK1, BUCK2, BUCK9
+
+Example:
+
+	s2mps11_pmic@66 {
+		compatible = "samsung,s2mps11-pmic";
+		reg = <0x66>;
+
+		s2m_osc: clocks{
+			#clock-cells = 1;
+			clock-output-names = "xx", "yy", "zz";
+		};
+
+		regulators {
+			ldo1_reg: LDO1 {
+				regulator-name = "VDD_ABB_3.3V";
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+			};
+
+			ldo2_reg: LDO2 {
+				regulator-name = "VDD_ALIVE_1.1V";
+				regulator-min-microvolt = <1100000>;
+				regulator-max-microvolt = <1100000>;
+				regulator-always-on;
+			};
+
+			buck1_reg: BUCK1 {
+				regulator-name = "vdd_mif";
+				regulator-min-microvolt = <950000>;
+				regulator-max-microvolt = <1350000>;
+				regulator-always-on;
+				regulator-boot-on;
+			};
+
+			buck2_reg: BUCK2 {
+				regulator-name = "vdd_arm";
+				regulator-min-microvolt = <950000>;
+				regulator-max-microvolt = <1350000>;
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-ramp-delay = <50000>;
+			};
+		};
+	};
diff --git a/Documentation/devicetree/bindings/misc/atmel-ssc.txt b/Documentation/devicetree/bindings/misc/atmel-ssc.txt
index 38e51ad2e07e..a45ae08c8ed1 100644
--- a/Documentation/devicetree/bindings/misc/atmel-ssc.txt
+++ b/Documentation/devicetree/bindings/misc/atmel-ssc.txt
@@ -7,9 +7,30 @@ Required properties:
 - reg: Should contain SSC registers location and length
 - interrupts: Should contain SSC interrupt
 
-Example:
+
+Required properties for devices compatible with "atmel,at91sam9g45-ssc":
+- dmas: DMA specifier, consisting of a phandle to DMA controller node,
+  the memory interface and SSC DMA channel ID (for tx and rx).
+  See Documentation/devicetree/bindings/dma/atmel-dma.txt for details.
+- dma-names: Must be "tx", "rx".
+
+Examples:
+- PDC transfer:
 ssc0: ssc@fffbc000 {
 	compatible = "atmel,at91rm9200-ssc";
 	reg = <0xfffbc000 0x4000>;
 	interrupts = <14 4 5>;
 };
+
+- DMA transfer:
+ssc0: ssc@f0010000 {
+      compatible = "atmel,at91sam9g45-ssc";
+      reg = <0xf0010000 0x4000>;
+      interrupts = <28 4 5>;
+      dmas = <&dma0 1 13>,
+	     <&dma0 1 14>;
+      dma-names = "tx", "rx";
+      pinctrl-names = "default";
+      pinctrl-0 = <&pinctrl_ssc0_tx &pinctrl_ssc0_rx>;
+      status = "disabled";
+};
diff --git a/Documentation/devicetree/bindings/misc/smc.txt b/Documentation/devicetree/bindings/misc/smc.txt
index 02b428136177..6c9f176f3571 100644
--- a/Documentation/devicetree/bindings/misc/smc.txt
+++ b/Documentation/devicetree/bindings/misc/smc.txt
@@ -4,11 +4,12 @@ This binding defines the location of the bounce buffer
 used for non-secure to secure communications.
 
 Required properties:
-- compatible : "bcm,kona-smc"
+- compatible : "brcm,kona-smc"
+- DEPRECATED: compatible : "bcm,kona-smc"
 - reg : Location and size of bounce buffer
 
 Example:
 	smc@0x3404c000 {
-		compatible = "bcm,bcm11351-smc", "bcm,kona-smc";
+		compatible = "brcm,bcm11351-smc", "brcm,kona-smc";
 		reg = <0x3404c000 0x400>; //1 KiB in SRAM
 	};
diff --git a/Documentation/devicetree/bindings/mmc/exynos-dw-mshc.txt b/Documentation/devicetree/bindings/mmc/exynos-dw-mshc.txt
index 6d1c0988cfc7..c67b975c8906 100644
--- a/Documentation/devicetree/bindings/mmc/exynos-dw-mshc.txt
+++ b/Documentation/devicetree/bindings/mmc/exynos-dw-mshc.txt
@@ -1,11 +1,11 @@
-* Samsung Exynos specific extensions to the Synopsis Designware Mobile
+* Samsung Exynos specific extensions to the Synopsys Designware Mobile
   Storage Host Controller
 
-The Synopsis designware mobile storage host controller is used to interface
+The Synopsys designware mobile storage host controller is used to interface
 a SoC with storage medium such as eMMC or SD/MMC cards. This file documents
-differences between the core Synopsis dw mshc controller properties described
-by synopsis-dw-mshc.txt and the properties used by the Samsung Exynos specific
-extensions to the Synopsis Designware Mobile Storage Host Controller.
+differences between the core Synopsys dw mshc controller properties described
+by synopsys-dw-mshc.txt and the properties used by the Samsung Exynos specific
+extensions to the Synopsys Designware Mobile Storage Host Controller.
 
 Required Properties:
 
diff --git a/Documentation/devicetree/bindings/mmc/fsl-esdhc.txt b/Documentation/devicetree/bindings/mmc/fsl-esdhc.txt
index bd9be0b5bc20..b7943f3f9995 100644
--- a/Documentation/devicetree/bindings/mmc/fsl-esdhc.txt
+++ b/Documentation/devicetree/bindings/mmc/fsl-esdhc.txt
@@ -19,6 +19,9 @@ Optional properties:
     "bus-width = <1>" property.
   - sdhci,auto-cmd12: specifies that a controller can only handle auto
     CMD12.
+  - voltage-ranges : two cells are required, first cell specifies minimum
+    slot voltage (mV), second cell specifies maximum slot voltage (mV).
+    Several ranges could be specified.
 
 Example:
 
@@ -29,4 +32,5 @@ sdhci@2e000 {
 	interrupt-parent = <&ipic>;
 	/* Filled in by U-Boot */
 	clock-frequency = <0>;
+	voltage-ranges = <3300 3300>;
 };
diff --git a/Documentation/devicetree/bindings/mmc/bcm,kona-sdhci.txt b/Documentation/devicetree/bindings/mmc/kona-sdhci.txt
index 094ae010f2fb..789fb07a426d 100644
--- a/Documentation/devicetree/bindings/mmc/bcm,kona-sdhci.txt
+++ b/Documentation/devicetree/bindings/mmc/kona-sdhci.txt
@@ -4,12 +4,13 @@ This file documents differences between the core properties in mmc.txt
 and the properties present in the bcm281xx SDHCI
 
 Required properties:
-- compatible : Should be "bcm,kona-sdhci"
+- compatible : Should be "brcm,kona-sdhci"
+- DEPRECATED: compatible : Should be "bcm,kona-sdhci"
 
 Example:
 
 sdio2: sdio@0x3f1a0000 {
-	compatible = "bcm,kona-sdhci";
+	compatible = "brcm,kona-sdhci";
 	reg = <0x3f1a0000 0x10000>;
 	interrupts = <0x0 74 0x4>;
 };
diff --git a/Documentation/devicetree/bindings/mmc/rockchip-dw-mshc.txt b/Documentation/devicetree/bindings/mmc/rockchip-dw-mshc.txt
index 8a3d91d47b6a..c559f3f36309 100644
--- a/Documentation/devicetree/bindings/mmc/rockchip-dw-mshc.txt
+++ b/Documentation/devicetree/bindings/mmc/rockchip-dw-mshc.txt
@@ -1,11 +1,11 @@
-* Rockchip specific extensions to the Synopsis Designware Mobile
+* Rockchip specific extensions to the Synopsys Designware Mobile
   Storage Host Controller
 
-The Synopsis designware mobile storage host controller is used to interface
+The Synopsys designware mobile storage host controller is used to interface
 a SoC with storage medium such as eMMC or SD/MMC cards. This file documents
-differences between the core Synopsis dw mshc controller properties described
-by synopsis-dw-mshc.txt and the properties used by the Rockchip specific
-extensions to the Synopsis Designware Mobile Storage Host Controller.
+differences between the core Synopsys dw mshc controller properties described
+by synopsys-dw-mshc.txt and the properties used by the Rockchip specific
+extensions to the Synopsys Designware Mobile Storage Host Controller.
 
 Required Properties:
 
diff --git a/Documentation/devicetree/bindings/mmc/synopsis-dw-mshc.txt b/Documentation/devicetree/bindings/mmc/synopsys-dw-mshc.txt
index cdcebea9c6f5..066a78b034ca 100644
--- a/Documentation/devicetree/bindings/mmc/synopsis-dw-mshc.txt
+++ b/Documentation/devicetree/bindings/mmc/synopsys-dw-mshc.txt
@@ -1,14 +1,14 @@
-* Synopsis Designware Mobile Storage Host Controller
+* Synopsys Designware Mobile Storage Host Controller
 
-The Synopsis designware mobile storage host controller is used to interface
+The Synopsys designware mobile storage host controller is used to interface
 a SoC with storage medium such as eMMC or SD/MMC cards. This file documents
 differences between the core mmc properties described by mmc.txt and the
-properties used by the Synopsis Designware Mobile Storage Host Controller.
+properties used by the Synopsys Designware Mobile Storage Host Controller.
 
 Required Properties:
 
 * compatible: should be
-	- snps,dw-mshc: for controllers compliant with synopsis dw-mshc.
+	- snps,dw-mshc: for controllers compliant with synopsys dw-mshc.
 * #address-cells: should be 1.
 * #size-cells: should be 0.
 
diff --git a/Documentation/devicetree/bindings/mmc/tmio_mmc.txt b/Documentation/devicetree/bindings/mmc/tmio_mmc.txt
index df204e18e030..6a2a1160a70d 100644
--- a/Documentation/devicetree/bindings/mmc/tmio_mmc.txt
+++ b/Documentation/devicetree/bindings/mmc/tmio_mmc.txt
@@ -9,12 +9,15 @@ compulsory and any optional properties, common to all SD/MMC drivers, as
 described in mmc.txt, can be used. Additionally the following tmio_mmc-specific
 optional bindings can be used.
 
+Required properties:
+- compatible:	"renesas,sdhi-shmobile" - a generic sh-mobile SDHI unit
+		"renesas,sdhi-sh7372" - SDHI IP on SH7372 SoC
+		"renesas,sdhi-sh73a0" - SDHI IP on SH73A0 SoC
+		"renesas,sdhi-r8a73a4" - SDHI IP on R8A73A4 SoC
+		"renesas,sdhi-r8a7740" - SDHI IP on R8A7740 SoC
+		"renesas,sdhi-r8a7778" - SDHI IP on R8A7778 SoC
+		"renesas,sdhi-r8a7779" - SDHI IP on R8A7779 SoC
+		"renesas,sdhi-r8a7790" - SDHI IP on R8A7790 SoC
+
 Optional properties:
 - toshiba,mmc-wrprotect-disable: write-protect detection is unavailable
-
-When used with Renesas SDHI hardware, the following compatibility strings
-configure various model-specific properties:
-
-"renesas,sh7372-sdhi":	(default) compatible with SH7372
-"renesas,r8a7740-sdhi":	compatible with R8A7740: certain MMC/SD commands have to
-			wait for the interface to become idle.
diff --git a/Documentation/devicetree/bindings/mtd/atmel-nand.txt b/Documentation/devicetree/bindings/mtd/atmel-nand.txt
index d555421ea49f..c4728839d0c1 100644
--- a/Documentation/devicetree/bindings/mtd/atmel-nand.txt
+++ b/Documentation/devicetree/bindings/mtd/atmel-nand.txt
@@ -15,6 +15,7 @@ Required properties:
   optional gpio and may be set to 0 if not present.
 
 Optional properties:
+- atmel,nand-has-dma : boolean to support dma transfer for nand read/write.
 - nand-ecc-mode : String, operation mode of the NAND ecc mode, soft by default.
   Supported values are: "none", "soft", "hw", "hw_syndrome", "hw_oob_first",
   "soft_bch".
@@ -29,6 +30,14 @@ Optional properties:
   sector size 1024.
 - nand-bus-width : 8 or 16 bus width if not present 8
 - nand-on-flash-bbt: boolean to enable on flash bbt option if not present false
+- Nand Flash Controller(NFC) is a slave driver under Atmel nand flash
+  - Required properties:
+    - compatible : "atmel,sama5d3-nfc".
+    - reg : should specify the address and size used for NFC command registers,
+            NFC registers and NFC Sram. NFC Sram address and size can be absent
+            if don't want to use it.
+  - Optional properties:
+    - atmel,write-by-sram: boolean to enable NFC write by sram.
 
 Examples:
 nand0: nand@40000000,0 {
@@ -77,3 +86,22 @@ nand0: nand@40000000 {
 		...
 	};
 };
+
+/* for NFC supported chips */
+nand0: nand@40000000 {
+	compatible = "atmel,at91rm9200-nand";
+	#address-cells = <1>;
+	#size-cells = <1>;
+	ranges;
+        ...
+        nfc@70000000 {
+		compatible = "atmel,sama5d3-nfc";
+		#address-cells = <1>;
+		#size-cells = <1>;
+		reg = <
+			0x70000000 0x10000000	/* NFC Command Registers */
+			0xffffc000 0x00000070	/* NFC HSMC regs */
+			0x00200000 0x00100000	/* NFC SRAM banks */
+		>;
+	};
+};
diff --git a/Documentation/devicetree/bindings/mtd/fsmc-nand.txt b/Documentation/devicetree/bindings/mtd/fsmc-nand.txt
index 2240ac09f6ba..ec42935f3908 100644
--- a/Documentation/devicetree/bindings/mtd/fsmc-nand.txt
+++ b/Documentation/devicetree/bindings/mtd/fsmc-nand.txt
@@ -1,4 +1,5 @@
-* FSMC NAND
+ST Microelectronics Flexible Static Memory Controller (FSMC)
+NAND Interface
 
 Required properties:
 - compatible : "st,spear600-fsmc-nand", "stericsson,fsmc-nand"
@@ -9,6 +10,26 @@ Optional properties:
 - bank-width : Width (in bytes) of the device.  If not present, the width
   defaults to 1 byte
 - nand-skip-bbtscan: Indicates the the BBT scanning should be skipped
+- timings: array of 6 bytes for NAND timings. The meanings of these bytes
+  are:
+  byte 0 TCLR  : CLE to RE delay in number of AHB clock cycles, only 4 bits
+                 are valid. Zero means one clockcycle, 15 means 16 clock
+                 cycles.
+  byte 1 TAR   : ALE to RE delay, 4 bits are valid. Same format as TCLR.
+  byte 2 THIZ  : number of HCLK clock cycles during which the data bus is
+                 kept in Hi-Z (tristate) after the start of a write access.
+                 Only valid for write transactions. Zero means zero cycles,
+                 255 means 255 cycles.
+  byte 3 THOLD : number of HCLK clock cycles to hold the address (and data
+                 when writing) after the command deassertation. Zero means
+                 one cycle, 255 means 256 cycles.
+  byte 4 TWAIT : number of HCLK clock cycles to assert the command to the
+                 NAND flash in response to SMWAITn. Zero means 1 cycle,
+                 255 means 256 cycles.
+  byte 5 TSET  : number of HCLK clock cycles to assert the address before the
+                 command is asserted. Zero means one cycle, 255 means 256
+                 cycles.
+- bank: default NAND bank to use (0-3 are valid, 0 is the default).
 
 Example:
 
@@ -24,6 +45,8 @@ Example:
 
 		bank-width = <1>;
 		nand-skip-bbtscan;
+		timings = /bits/ 8 <0 0 0 2 3 0>;
+		bank = <1>;
 
 		partition@0 {
 			...
diff --git a/Documentation/devicetree/bindings/mtd/partition.txt b/Documentation/devicetree/bindings/mtd/partition.txt
index 9315ac96b49b..8e5557da1955 100644
--- a/Documentation/devicetree/bindings/mtd/partition.txt
+++ b/Documentation/devicetree/bindings/mtd/partition.txt
@@ -4,6 +4,7 @@ Partitions can be represented by sub-nodes of an mtd device. This can be used
 on platforms which have strong conventions about which portions of a flash are
 used for what purposes, but which don't use an on-flash partition table such
 as RedBoot.
+NOTE: if the sub-node has a compatible string, then it is not a partition.
 
 #address-cells & #size-cells must both be present in the mtd device. There are
 two valid values for both:
diff --git a/Documentation/devicetree/bindings/net/can/atmel-can.txt b/Documentation/devicetree/bindings/net/can/atmel-can.txt
index 72cf0c5daff4..14e52a0d86ec 100644
--- a/Documentation/devicetree/bindings/net/can/atmel-can.txt
+++ b/Documentation/devicetree/bindings/net/can/atmel-can.txt
@@ -8,7 +8,7 @@ Required properties:
 Example:
 
 	can0: can@f000c000 {
-		compatbile = "atmel,at91sam9x5-can";
+		compatible = "atmel,at91sam9x5-can";
 		reg = <0xf000c000 0x300>;
 		interrupts = <40 4 5>
 	};
diff --git a/Documentation/devicetree/bindings/net/can/sja1000.txt b/Documentation/devicetree/bindings/net/can/sja1000.txt
index c2dbcec0ee31..f2105a47ec87 100644
--- a/Documentation/devicetree/bindings/net/can/sja1000.txt
+++ b/Documentation/devicetree/bindings/net/can/sja1000.txt
@@ -37,7 +37,7 @@ Optional properties:
 	If not specified or if the specified value is 0, the CLKOUT pin
 	will be disabled.
 
-- nxp,no-comparator-bypass : Allows to disable the CAN input comperator.
+- nxp,no-comparator-bypass : Allows to disable the CAN input comparator.
 
 For further information, please have a look to the SJA1000 data sheet.
 
diff --git a/Documentation/devicetree/bindings/net/fsl-tsec-phy.txt b/Documentation/devicetree/bindings/net/fsl-tsec-phy.txt
index 2c6be0377f55..d2ea4605d078 100644
--- a/Documentation/devicetree/bindings/net/fsl-tsec-phy.txt
+++ b/Documentation/devicetree/bindings/net/fsl-tsec-phy.txt
@@ -86,6 +86,7 @@ General Properties:
 
 Clock Properties:
 
+  - fsl,cksel        Timer reference clock source.
   - fsl,tclk-period  Timer reference clock period in nanoseconds.
   - fsl,tmr-prsc     Prescaler, divides the output clock.
   - fsl,tmr-add      Frequency compensation value.
@@ -97,7 +98,7 @@ Clock Properties:
   clock. You must choose these carefully for the clock to work right.
   Here is how to figure good values:
 
-  TimerOsc     = system clock               MHz
+  TimerOsc     = selected reference clock   MHz
   tclk_period  = desired clock period       nanoseconds
   NominalFreq  = 1000 / tclk_period         MHz
   FreqDivRatio = TimerOsc / NominalFreq     (must be greater that 1.0)
@@ -114,6 +115,20 @@ Clock Properties:
   Pulse Per Second (PPS) signal, since this will be offered to the PPS
   subsystem to synchronize the Linux clock.
 
+  Reference clock source is determined by the value, which is holded
+  in CKSEL bits in TMR_CTRL register. "fsl,cksel" property keeps the
+  value, which will be directly written in those bits, that is why,
+  according to reference manual, the next clock sources can be used:
+
+  <0> - external high precision timer reference clock (TSEC_TMR_CLK
+        input is used for this purpose);
+  <1> - eTSEC system clock;
+  <2> - eTSEC1 transmit clock;
+  <3> - RTC clock input.
+
+  When this attribute is not used, eTSEC system clock will serve as
+  IEEE 1588 timer reference clock.
+
 Example:
 
 	ptp_clock@24E00 {
@@ -121,6 +136,7 @@ Example:
 		reg = <0x24E00 0xB0>;
 		interrupts = <12 0x8 13 0x8>;
 		interrupt-parent = < &ipic >;
+		fsl,cksel       = <1>;
 		fsl,tclk-period = <10>;
 		fsl,tmr-prsc    = <100>;
 		fsl,tmr-add     = <0x999999A4>;
diff --git a/Documentation/devicetree/bindings/net/micrel-ksz9021.txt b/Documentation/devicetree/bindings/net/micrel-ksz9021.txt
new file mode 100644
index 000000000000..997a63f1aea1
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/micrel-ksz9021.txt
@@ -0,0 +1,49 @@
+Micrel KSZ9021 Gigabit Ethernet PHY
+
+Some boards require special tuning values, particularly when it comes to
+clock delays.  You can specify clock delay values by adding
+micrel-specific properties to an Ethernet OF device node.
+
+All skew control options are specified in picoseconds.  The minimum
+value is 0, and the maximum value is 3000.
+
+Optional properties:
+ - rxc-skew-ps : Skew control of RXC pad
+ - rxdv-skew-ps : Skew control of RX CTL pad
+ - txc-skew-ps : Skew control of TXC pad
+ - txen-skew-ps : Skew control of TX_CTL pad
+ - rxd0-skew-ps : Skew control of RX data 0 pad
+ - rxd1-skew-ps : Skew control of RX data 1 pad
+ - rxd2-skew-ps : Skew control of RX data 2 pad
+ - rxd3-skew-ps : Skew control of RX data 3 pad
+ - txd0-skew-ps : Skew control of TX data 0 pad
+ - txd1-skew-ps : Skew control of TX data 1 pad
+ - txd2-skew-ps : Skew control of TX data 2 pad
+ - txd3-skew-ps : Skew control of TX data 3 pad
+
+Examples:
+
+	/* Attach to an Ethernet device with autodetected PHY */
+	&enet {
+		rxc-skew-ps = <3000>;
+		rxdv-skew-ps = <0>;
+		txc-skew-ps = <3000>;
+		txen-skew-ps = <0>;
+		status = "okay";
+	};
+
+	/* Attach to an explicitly-specified PHY */
+	mdio {
+		phy0: ethernet-phy@0 {
+			rxc-skew-ps = <3000>;
+			rxdv-skew-ps = <0>;
+			txc-skew-ps = <3000>;
+			txen-skew-ps = <0>;
+			reg = <0>;
+		};
+	};
+	ethernet@70000 {
+		status = "okay";
+		phy = <&phy0>;
+		phy-mode = "rgmii-id";
+	};
diff --git a/Documentation/devicetree/bindings/net/moxa,moxart-mac.txt b/Documentation/devicetree/bindings/net/moxa,moxart-mac.txt
new file mode 100644
index 000000000000..583418b2c127
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/moxa,moxart-mac.txt
@@ -0,0 +1,21 @@
+MOXA ART Ethernet Controller
+
+Required properties:
+
+- compatible : Must be "moxa,moxart-mac"
+- reg : Should contain register location and length
+- interrupts : Should contain the mac interrupt number
+
+Example:
+
+	mac0: mac@90900000 {
+		compatible = "moxa,moxart-mac";
+		reg =	<0x90900000 0x100>;
+		interrupts = <25 0>;
+	};
+
+	mac1: mac@92000000 {
+		compatible = "moxa,moxart-mac";
+		reg =	<0x92000000 0x100>;
+		interrupts = <27 0>;
+	};
diff --git a/Documentation/devicetree/bindings/net/stmmac.txt b/Documentation/devicetree/bindings/net/stmmac.txt
index 261c563b5f06..eba0e5e59ebe 100644
--- a/Documentation/devicetree/bindings/net/stmmac.txt
+++ b/Documentation/devicetree/bindings/net/stmmac.txt
@@ -22,6 +22,11 @@ Required properties:
 - snps,pbl		Programmable Burst Length
 - snps,fixed-burst	Program the DMA to use the fixed burst mode
 - snps,mixed-burst	Program the DMA to use the mixed burst mode
+- snps,force_thresh_dma_mode	Force DMA to use the threshold mode for
+				both tx and rx
+- snps,force_sf_dma_mode	Force DMA to use the Store and Forward
+				mode for both tx and rx. This flag is
+				ignored if force_thresh_dma_mode is set.
 
 Optional properties:
 - mac-address: 6 bytes, mac address
diff --git a/Documentation/devicetree/bindings/pci/designware-pcie.txt b/Documentation/devicetree/bindings/pci/designware-pcie.txt
index e2371f5cdebe..e216af356847 100644
--- a/Documentation/devicetree/bindings/pci/designware-pcie.txt
+++ b/Documentation/devicetree/bindings/pci/designware-pcie.txt
@@ -1,4 +1,4 @@
-* Synopsis Designware PCIe interface
+* Synopsys Designware PCIe interface
 
 Required properties:
 - compatible: should contain "snps,dw-pcie" to identify the
@@ -18,6 +18,7 @@ Required properties:
 - interrupt-map-mask and interrupt-map: standard PCI properties
 	to define the mapping of the PCIe interface to interrupt
 	numbers.
+- num-lanes: number of lanes to use
 - reset-gpio: gpio pin number of power good signal
 
 Example:
@@ -41,6 +42,7 @@ SoC specific DT Entry:
 		#interrupt-cells = <1>;
 		interrupt-map-mask = <0 0 0 0>;
 		interrupt-map = <0x0 0 &gic 53>;
+		num-lanes = <4>;
 	};
 
 	pcie@2a0000 {
@@ -60,6 +62,7 @@ SoC specific DT Entry:
 		#interrupt-cells = <1>;
 		interrupt-map-mask = <0 0 0 0>;
 		interrupt-map = <0x0 0 &gic 56>;
+		num-lanes = <4>;
 	};
 
 Board specific DT Entry:
diff --git a/Documentation/devicetree/bindings/pci/mvebu-pci.txt b/Documentation/devicetree/bindings/pci/mvebu-pci.txt
index f8d405897a94..9556e2fedf6d 100644
--- a/Documentation/devicetree/bindings/pci/mvebu-pci.txt
+++ b/Documentation/devicetree/bindings/pci/mvebu-pci.txt
@@ -1,6 +1,7 @@
 * Marvell EBU PCIe interfaces
 
 Mandatory properties:
+
 - compatible: one of the following values:
     marvell,armada-370-pcie
     marvell,armada-xp-pcie
@@ -10,11 +11,49 @@ Mandatory properties:
 - #interrupt-cells, set to <1>
 - bus-range: PCI bus numbers covered
 - device_type, set to "pci"
-- ranges: ranges for the PCI memory and I/O regions, as well as the
-  MMIO registers to control the PCIe interfaces.
+- ranges: ranges describing the MMIO registers to control the PCIe
+  interfaces, and ranges describing the MBus windows needed to access
+  the memory and I/O regions of each PCIe interface.
+
+The ranges describing the MMIO registers have the following layout:
+
+    0x82000000 0 r MBUS_ID(0xf0, 0x01) r 0 s
+
+where:
+
+  * r is a 32-bits value that gives the offset of the MMIO
+  registers of this PCIe interface, from the base of the internal
+  registers.
+
+  * s is a 32-bits value that give the size of this MMIO
+  registers area. This range entry translates the '0x82000000 0 r' PCI
+  address into the 'MBUS_ID(0xf0, 0x01) r' CPU address, which is part
+  of the internal register window (as identified by MBUS_ID(0xf0,
+  0x01)).
+
+The ranges describing the MBus windows have the following layout:
+
+    0x8t000000 s 0     MBUS_ID(w, a) 0 1 0
+
+where:
+
+   * t is the type of the MBus window (as defined by the standard PCI DT
+   bindings), 1 for I/O and 2 for memory.
 
-In addition, the Device Tree node must have sub-nodes describing each
+   * s is the PCI slot that corresponds to this PCIe interface
+
+   * w is the 'target ID' value for the MBus window
+
+   * a the 'attribute' value for the MBus window.
+
+Since the location and size of the different MBus windows is not fixed in
+hardware, and only determined in runtime, those ranges cover the full first
+4 GB of the physical address space, and do not translate into a valid CPU
+address.
+
+In addition, the device tree node must have sub-nodes describing each
 PCIe interface, having the following mandatory properties:
+
 - reg: used only for interrupt mapping, so only the first four bytes
   are used to refer to the correct bus number and device number.
 - assigned-addresses: reference to the MMIO registers used to control
@@ -26,7 +65,8 @@ PCIe interface, having the following mandatory properties:
 - #address-cells, set to <3>
 - #size-cells, set to <2>
 - #interrupt-cells, set to <1>
-- ranges, empty property.
+- ranges, translating the MBus windows ranges of the parent node into
+  standard PCI addresses.
 - interrupt-map-mask and interrupt-map, standard PCI properties to
   define the mapping of the PCIe interface to interrupt numbers.
 
@@ -47,27 +87,50 @@ pcie-controller {
 
 	bus-range = <0x00 0xff>;
 
-	ranges = <0x82000000 0 0xd0040000 0xd0040000 0 0x00002000   /* Port 0.0 registers */
-		  0x82000000 0 0xd0042000 0xd0042000 0 0x00002000   /* Port 2.0 registers */
-		  0x82000000 0 0xd0044000 0xd0044000 0 0x00002000   /* Port 0.1 registers */
-		  0x82000000 0 0xd0048000 0xd0048000 0 0x00002000   /* Port 0.2 registers */
-		  0x82000000 0 0xd004c000 0xd004c000 0 0x00002000   /* Port 0.3 registers */
-		  0x82000000 0 0xd0080000 0xd0080000 0 0x00002000   /* Port 1.0 registers */
-		  0x82000000 0 0xd0082000 0xd0082000 0 0x00002000   /* Port 3.0 registers */
-		  0x82000000 0 0xd0084000 0xd0084000 0 0x00002000   /* Port 1.1 registers */
-		  0x82000000 0 0xd0088000 0xd0088000 0 0x00002000   /* Port 1.2 registers */
-		  0x82000000 0 0xd008c000 0xd008c000 0 0x00002000   /* Port 1.3 registers */
-		  0x82000000 0 0xe0000000 0xe0000000 0 0x08000000   /* non-prefetchable memory */
-		  0x81000000 0 0	  0xe8000000 0 0x00100000>; /* downstream I/O */
+	ranges =
+	       <0x82000000 0 0x40000 MBUS_ID(0xf0, 0x01) 0x40000 0 0x00002000	/* Port 0.0 registers */
+		0x82000000 0 0x42000 MBUS_ID(0xf0, 0x01) 0x42000 0 0x00002000	/* Port 2.0 registers */
+		0x82000000 0 0x44000 MBUS_ID(0xf0, 0x01) 0x44000 0 0x00002000	/* Port 0.1 registers */
+		0x82000000 0 0x48000 MBUS_ID(0xf0, 0x01) 0x48000 0 0x00002000	/* Port 0.2 registers */
+		0x82000000 0 0x4c000 MBUS_ID(0xf0, 0x01) 0x4c000 0 0x00002000	/* Port 0.3 registers */
+		0x82000000 0 0x80000 MBUS_ID(0xf0, 0x01) 0x80000 0 0x00002000	/* Port 1.0 registers */
+		0x82000000 0 0x82000 MBUS_ID(0xf0, 0x01) 0x82000 0 0x00002000	/* Port 3.0 registers */
+		0x82000000 0 0x84000 MBUS_ID(0xf0, 0x01) 0x84000 0 0x00002000	/* Port 1.1 registers */
+		0x82000000 0 0x88000 MBUS_ID(0xf0, 0x01) 0x88000 0 0x00002000	/* Port 1.2 registers */
+		0x82000000 0 0x8c000 MBUS_ID(0xf0, 0x01) 0x8c000 0 0x00002000	/* Port 1.3 registers */
+		0x82000000 0x1 0     MBUS_ID(0x04, 0xe8) 0 1 0 /* Port 0.0 MEM */
+		0x81000000 0x1 0     MBUS_ID(0x04, 0xe0) 0 1 0 /* Port 0.0 IO  */
+		0x82000000 0x2 0     MBUS_ID(0x04, 0xd8) 0 1 0 /* Port 0.1 MEM */
+		0x81000000 0x2 0     MBUS_ID(0x04, 0xd0) 0 1 0 /* Port 0.1 IO  */
+		0x82000000 0x3 0     MBUS_ID(0x04, 0xb8) 0 1 0 /* Port 0.2 MEM */
+		0x81000000 0x3 0     MBUS_ID(0x04, 0xb0) 0 1 0 /* Port 0.2 IO  */
+		0x82000000 0x4 0     MBUS_ID(0x04, 0x78) 0 1 0 /* Port 0.3 MEM */
+		0x81000000 0x4 0     MBUS_ID(0x04, 0x70) 0 1 0 /* Port 0.3 IO  */
+
+		0x82000000 0x5 0     MBUS_ID(0x08, 0xe8) 0 1 0 /* Port 1.0 MEM */
+		0x81000000 0x5 0     MBUS_ID(0x08, 0xe0) 0 1 0 /* Port 1.0 IO  */
+		0x82000000 0x6 0     MBUS_ID(0x08, 0xd8) 0 1 0 /* Port 1.1 MEM */
+		0x81000000 0x6 0     MBUS_ID(0x08, 0xd0) 0 1 0 /* Port 1.1 IO  */
+		0x82000000 0x7 0     MBUS_ID(0x08, 0xb8) 0 1 0 /* Port 1.2 MEM */
+		0x81000000 0x7 0     MBUS_ID(0x08, 0xb0) 0 1 0 /* Port 1.2 IO  */
+		0x82000000 0x8 0     MBUS_ID(0x08, 0x78) 0 1 0 /* Port 1.3 MEM */
+		0x81000000 0x8 0     MBUS_ID(0x08, 0x70) 0 1 0 /* Port 1.3 IO  */
+
+		0x82000000 0x9 0     MBUS_ID(0x04, 0xf8) 0 1 0 /* Port 2.0 MEM */
+		0x81000000 0x9 0     MBUS_ID(0x04, 0xf0) 0 1 0 /* Port 2.0 IO  */
+
+		0x82000000 0xa 0     MBUS_ID(0x08, 0xf8) 0 1 0 /* Port 3.0 MEM */
+		0x81000000 0xa 0     MBUS_ID(0x08, 0xf0) 0 1 0 /* Port 3.0 IO  */>;
 
 	pcie@1,0 {
 		device_type = "pci";
-		assigned-addresses = <0x82000800 0 0xd0040000 0 0x2000>;
+		assigned-addresses = <0x82000800 0 0x40000 0 0x2000>;
 		reg = <0x0800 0 0 0 0>;
 		#address-cells = <3>;
 		#size-cells = <2>;
 		#interrupt-cells = <1>;
-		ranges;
+		ranges = <0x82000000 0 0 0x82000000 0x1 0 1 0
+			  0x81000000 0 0 0x81000000 0x1 0 1 0>;
 		interrupt-map-mask = <0 0 0 0>;
 		interrupt-map = <0 0 0 0 &mpic 58>;
 		marvell,pcie-port = <0>;
@@ -78,12 +141,13 @@ pcie-controller {
 
 	pcie@2,0 {
 		device_type = "pci";
-		assigned-addresses = <0x82001000 0 0xd0044000 0 0x2000>;
+		assigned-addresses = <0x82001000 0 0x44000 0 0x2000>;
 		reg = <0x1000 0 0 0 0>;
 		#address-cells = <3>;
 		#size-cells = <2>;
 		#interrupt-cells = <1>;
-		ranges;
+		ranges = <0x82000000 0 0 0x82000000 0x2 0 1 0
+			  0x81000000 0 0 0x81000000 0x2 0 1 0>;
 		interrupt-map-mask = <0 0 0 0>;
 		interrupt-map = <0 0 0 0 &mpic 59>;
 		marvell,pcie-port = <0>;
@@ -94,12 +158,13 @@ pcie-controller {
 
 	pcie@3,0 {
 		device_type = "pci";
-		assigned-addresses = <0x82001800 0 0xd0048000 0 0x2000>;
+		assigned-addresses = <0x82001800 0 0x48000 0 0x2000>;
 		reg = <0x1800 0 0 0 0>;
 		#address-cells = <3>;
 		#size-cells = <2>;
 		#interrupt-cells = <1>;
-		ranges;
+		ranges = <0x82000000 0 0 0x82000000 0x3 0 1 0
+			  0x81000000 0 0 0x81000000 0x3 0 1 0>;
 		interrupt-map-mask = <0 0 0 0>;
 		interrupt-map = <0 0 0 0 &mpic 60>;
 		marvell,pcie-port = <0>;
@@ -110,12 +175,13 @@ pcie-controller {
 
 	pcie@4,0 {
 		device_type = "pci";
-		assigned-addresses = <0x82002000 0 0xd004c000 0 0x2000>;
+		assigned-addresses = <0x82002000 0 0x4c000 0 0x2000>;
 		reg = <0x2000 0 0 0 0>;
 		#address-cells = <3>;
 		#size-cells = <2>;
 		#interrupt-cells = <1>;
-		ranges;
+		ranges = <0x82000000 0 0 0x82000000 0x4 0 1 0
+			  0x81000000 0 0 0x81000000 0x4 0 1 0>;
 		interrupt-map-mask = <0 0 0 0>;
 		interrupt-map = <0 0 0 0 &mpic 61>;
 		marvell,pcie-port = <0>;
@@ -126,12 +192,13 @@ pcie-controller {
 
 	pcie@5,0 {
 		device_type = "pci";
-		assigned-addresses = <0x82002800 0 0xd0080000 0 0x2000>;
+		assigned-addresses = <0x82002800 0 0x80000 0 0x2000>;
 		reg = <0x2800 0 0 0 0>;
 		#address-cells = <3>;
 		#size-cells = <2>;
 		#interrupt-cells = <1>;
-		ranges;
+		ranges = <0x82000000 0 0 0x82000000 0x5 0 1 0
+			  0x81000000 0 0 0x81000000 0x5 0 1 0>;
 		interrupt-map-mask = <0 0 0 0>;
 		interrupt-map = <0 0 0 0 &mpic 62>;
 		marvell,pcie-port = <1>;
@@ -142,12 +209,13 @@ pcie-controller {
 
 	pcie@6,0 {
 		device_type = "pci";
-		assigned-addresses = <0x82003000 0 0xd0084000 0 0x2000>;
+		assigned-addresses = <0x82003000 0 0x84000 0 0x2000>;
 		reg = <0x3000 0 0 0 0>;
 		#address-cells = <3>;
 		#size-cells = <2>;
 		#interrupt-cells = <1>;
-		ranges;
+		ranges = <0x82000000 0 0 0x82000000 0x6 0 1 0
+			  0x81000000 0 0 0x81000000 0x6 0 1 0>;
 		interrupt-map-mask = <0 0 0 0>;
 		interrupt-map = <0 0 0 0 &mpic 63>;
 		marvell,pcie-port = <1>;
@@ -158,12 +226,13 @@ pcie-controller {
 
 	pcie@7,0 {
 		device_type = "pci";
-		assigned-addresses = <0x82003800 0 0xd0088000 0 0x2000>;
+		assigned-addresses = <0x82003800 0 0x88000 0 0x2000>;
 		reg = <0x3800 0 0 0 0>;
 		#address-cells = <3>;
 		#size-cells = <2>;
 		#interrupt-cells = <1>;
-		ranges;
+		ranges = <0x82000000 0 0 0x82000000 0x7 0 1 0
+			  0x81000000 0 0 0x81000000 0x7 0 1 0>;
 		interrupt-map-mask = <0 0 0 0>;
 		interrupt-map = <0 0 0 0 &mpic 64>;
 		marvell,pcie-port = <1>;
@@ -174,12 +243,13 @@ pcie-controller {
 
 	pcie@8,0 {
 		device_type = "pci";
-		assigned-addresses = <0x82004000 0 0xd008c000 0 0x2000>;
+		assigned-addresses = <0x82004000 0 0x8c000 0 0x2000>;
 		reg = <0x4000 0 0 0 0>;
 		#address-cells = <3>;
 		#size-cells = <2>;
 		#interrupt-cells = <1>;
-		ranges;
+		ranges = <0x82000000 0 0 0x82000000 0x8 0 1 0
+			  0x81000000 0 0 0x81000000 0x8 0 1 0>;
 		interrupt-map-mask = <0 0 0 0>;
 		interrupt-map = <0 0 0 0 &mpic 65>;
 		marvell,pcie-port = <1>;
@@ -187,14 +257,16 @@ pcie-controller {
 		clocks = <&gateclk 12>;
 		status = "disabled";
 	};
+
 	pcie@9,0 {
 		device_type = "pci";
-		assigned-addresses = <0x82004800 0 0xd0042000 0 0x2000>;
+		assigned-addresses = <0x82004800 0 0x42000 0 0x2000>;
 		reg = <0x4800 0 0 0 0>;
 		#address-cells = <3>;
 		#size-cells = <2>;
 		#interrupt-cells = <1>;
-		ranges;
+		ranges = <0x82000000 0 0 0x82000000 0x9 0 1 0
+			  0x81000000 0 0 0x81000000 0x9 0 1 0>;
 		interrupt-map-mask = <0 0 0 0>;
 		interrupt-map = <0 0 0 0 &mpic 99>;
 		marvell,pcie-port = <2>;
@@ -205,12 +277,13 @@ pcie-controller {
 
 	pcie@10,0 {
 		device_type = "pci";
-		assigned-addresses = <0x82005000 0 0xd0082000 0 0x2000>;
+		assigned-addresses = <0x82005000 0 0x82000 0 0x2000>;
 		reg = <0x5000 0 0 0 0>;
 		#address-cells = <3>;
 		#size-cells = <2>;
 		#interrupt-cells = <1>;
-		ranges;
+		ranges = <0x82000000 0 0 0x82000000 0xa 0 1 0
+			  0x81000000 0 0 0x81000000 0xa 0 1 0>;
 		interrupt-map-mask = <0 0 0 0>;
 		interrupt-map = <0 0 0 0 &mpic 103>;
 		marvell,pcie-port = <3>;
diff --git a/Documentation/devicetree/bindings/pci/nvidia,tegra20-pcie.txt b/Documentation/devicetree/bindings/pci/nvidia,tegra20-pcie.txt
new file mode 100644
index 000000000000..6b7510775c50
--- /dev/null
+++ b/Documentation/devicetree/bindings/pci/nvidia,tegra20-pcie.txt
@@ -0,0 +1,163 @@
+NVIDIA Tegra PCIe controller
+
+Required properties:
+- compatible: "nvidia,tegra20-pcie" or "nvidia,tegra30-pcie"
+- device_type: Must be "pci"
+- reg: A list of physical base address and length for each set of controller
+  registers. Must contain an entry for each entry in the reg-names property.
+- reg-names: Must include the following entries:
+  "pads": PADS registers
+  "afi": AFI registers
+  "cs": configuration space region
+- interrupts: A list of interrupt outputs of the controller. Must contain an
+  entry for each entry in the interrupt-names property.
+- interrupt-names: Must include the following entries:
+  "intr": The Tegra interrupt that is asserted for controller interrupts
+  "msi": The Tegra interrupt that is asserted when an MSI is received
+- pex-clk-supply: Supply voltage for internal reference clock
+- vdd-supply: Power supply for controller (1.05V)
+- avdd-supply: Power supply for controller (1.05V) (not required for Tegra20)
+- bus-range: Range of bus numbers associated with this controller
+- #address-cells: Address representation for root ports (must be 3)
+  - cell 0 specifies the bus and device numbers of the root port:
+    [23:16]: bus number
+    [15:11]: device number
+  - cell 1 denotes the upper 32 address bits and should be 0
+  - cell 2 contains the lower 32 address bits and is used to translate to the
+    CPU address space
+- #size-cells: Size representation for root ports (must be 2)
+- ranges: Describes the translation of addresses for root ports and standard
+  PCI regions. The entries must be 6 cells each, where the first three cells
+  correspond to the address as described for the #address-cells property
+  above, the fourth cell is the physical CPU address to translate to and the
+  fifth and six cells are as described for the #size-cells property above.
+  - The first two entries are expected to translate the addresses for the root
+    port registers, which are referenced by the assigned-addresses property of
+    the root port nodes (see below).
+  - The remaining entries setup the mapping for the standard I/O, memory and
+    prefetchable PCI regions. The first cell determines the type of region
+    that is setup:
+    - 0x81000000: I/O memory region
+    - 0x82000000: non-prefetchable memory region
+    - 0xc2000000: prefetchable memory region
+  Please refer to the standard PCI bus binding document for a more detailed
+  explanation.
+- clocks: List of clock inputs of the controller. Must contain an entry for
+  each entry in the clock-names property.
+- clock-names: Must include the following entries:
+  "pex": The Tegra clock of that name
+  "afi": The Tegra clock of that name
+  "pcie_xclk": The Tegra clock of that name
+  "pll_e": The Tegra clock of that name
+  "cml": The Tegra clock of that name (not required for Tegra20)
+
+Root ports are defined as subnodes of the PCIe controller node.
+
+Required properties:
+- device_type: Must be "pci"
+- assigned-addresses: Address and size of the port configuration registers
+- reg: PCI bus address of the root port
+- #address-cells: Must be 3
+- #size-cells: Must be 2
+- ranges: Sub-ranges distributed from the PCIe controller node. An empty
+  property is sufficient.
+- nvidia,num-lanes: Number of lanes to use for this port. Valid combinations
+  are:
+  - Root port 0 uses 4 lanes, root port 1 is unused.
+  - Both root ports use 2 lanes.
+
+Example:
+
+SoC DTSI:
+
+	pcie-controller {
+		compatible = "nvidia,tegra20-pcie";
+		device_type = "pci";
+		reg = <0x80003000 0x00000800   /* PADS registers */
+		       0x80003800 0x00000200   /* AFI registers */
+		       0x90000000 0x10000000>; /* configuration space */
+		reg-names = "pads", "afi", "cs";
+		interrupts = <0 98 0x04   /* controller interrupt */
+		              0 99 0x04>; /* MSI interrupt */
+		interrupt-names = "intr", "msi";
+
+		bus-range = <0x00 0xff>;
+		#address-cells = <3>;
+		#size-cells = <2>;
+
+		ranges = <0x82000000 0 0x80000000 0x80000000 0 0x00001000   /* port 0 registers */
+			  0x82000000 0 0x80001000 0x80001000 0 0x00001000   /* port 1 registers */
+			  0x81000000 0 0          0x82000000 0 0x00010000   /* downstream I/O */
+			  0x82000000 0 0xa0000000 0xa0000000 0 0x10000000   /* non-prefetchable memory */
+			  0xc2000000 0 0xb0000000 0xb0000000 0 0x10000000>; /* prefetchable memory */
+
+		clocks = <&tegra_car 70>, <&tegra_car 72>, <&tegra_car 74>,
+			 <&tegra_car 118>;
+		clock-names = "pex", "afi", "pcie_xclk", "pll_e";
+		status = "disabled";
+
+		pci@1,0 {
+			device_type = "pci";
+			assigned-addresses = <0x82000800 0 0x80000000 0 0x1000>;
+			reg = <0x000800 0 0 0 0>;
+			status = "disabled";
+
+			#address-cells = <3>;
+			#size-cells = <2>;
+
+			ranges;
+
+			nvidia,num-lanes = <2>;
+		};
+
+		pci@2,0 {
+			device_type = "pci";
+			assigned-addresses = <0x82001000 0 0x80001000 0 0x1000>;
+			reg = <0x001000 0 0 0 0>;
+			status = "disabled";
+
+			#address-cells = <3>;
+			#size-cells = <2>;
+
+			ranges;
+
+			nvidia,num-lanes = <2>;
+		};
+	};
+
+
+Board DTS:
+
+	pcie-controller {
+		status = "okay";
+
+		vdd-supply = <&pci_vdd_reg>;
+		pex-clk-supply = <&pci_clk_reg>;
+
+		/* root port 00:01.0 */
+		pci@1,0 {
+			status = "okay";
+
+			/* bridge 01:00.0 (optional) */
+			pci@0,0 {
+				reg = <0x010000 0 0 0 0>;
+
+				#address-cells = <3>;
+				#size-cells = <2>;
+
+				device_type = "pci";
+
+				/* endpoint 02:00.0 */
+				pci@0,0 {
+					reg = <0x020000 0 0 0 0>;
+				};
+			};
+		};
+	};
+
+Note that devices on the PCI bus are dynamically discovered using PCI's bus
+enumeration and therefore don't need corresponding device nodes in DT. However
+if a device on the PCI bus provides a non-probeable bus such as I2C or SPI,
+device nodes need to be added in order to allow the bus' children to be
+instantiated at the proper location in the operating system's device tree (as
+illustrated by the optional nodes in the example above).
diff --git a/Documentation/devicetree/bindings/pci/ralink,rt3883-pci.txt b/Documentation/devicetree/bindings/pci/ralink,rt3883-pci.txt
new file mode 100644
index 000000000000..8e0a1eb0acbb
--- /dev/null
+++ b/Documentation/devicetree/bindings/pci/ralink,rt3883-pci.txt
@@ -0,0 +1,190 @@
+* Mediatek/Ralink RT3883 PCI controller
+
+1) Main node
+
+   Required properties:
+
+   - compatible: must be "ralink,rt3883-pci"
+
+   - reg: specifies the physical base address of the controller and
+     the length of the memory mapped region.
+
+   - #address-cells: specifies the number of cells needed to encode an
+     address. The value must be 1.
+
+   - #size-cells: specifies the number of cells used to represent the size
+     of an address. The value must be 1.
+
+   - ranges: specifies the translation between child address space and parent
+     address space
+
+  Optional properties:
+
+   - status: indicates the operational status of the device.
+     Value must be either "disabled" or "okay".
+
+2) Child nodes
+
+   The main node must have two child nodes which describes the built-in
+   interrupt controller and the PCI host bridge.
+
+   a) Interrupt controller:
+
+   Required properties:
+
+   - interrupt-controller: identifies the node as an interrupt controller
+
+   - #address-cells: specifies the number of cells needed to encode an
+     address. The value must be 0. As such, 'interrupt-map' nodes do not
+     have to specify a parent unit address.
+
+   - #interrupt-cells: specifies the number of cells needed to encode an
+     interrupt source. The value must be 1.
+
+   - interrupt-parent: the phandle for the interrupt controller that
+     services interrupts for this device.
+
+   - interrupts: specifies the interrupt source of the parent interrupt
+     controller. The format of the interrupt specifier depends on the
+     parent interrupt controller.
+
+   b) PCI host bridge:
+
+   Required properties:
+
+   - #address-cells: specifies the number of cells needed to encode an
+     address. The value must be 0.
+
+   - #size-cells: specifies the number of cells used to represent the size
+     of an address. The value must be 2.
+
+   - #interrupt-cells: specifies the number of cells needed to encode an
+     interrupt source. The value must be 1.
+
+   - device_type: must be "pci"
+
+   - bus-range: PCI bus numbers covered
+
+   - ranges: specifies the ranges for the PCI memory and I/O regions
+
+   - interrupt-map-mask,
+   - interrupt-map: standard PCI properties to define the mapping of the
+     PCI interface to interrupt numbers.
+
+   The PCI host bridge node migh have additional sub-nodes representing
+   the onboard PCI devices/PCI slots. Each such sub-node must have the
+   following mandatory properties:
+
+     - reg: used only for interrupt mapping, so only the first four bytes
+       are used to refer to the correct bus number and device number.
+
+     - device_type: must be "pci"
+
+   If a given sub-node represents a PCI bridge it must have following
+   mandatory properties as well:
+
+     - #address-cells: must be set to <3>
+
+     - #size-cells: must set to <2>
+
+     - #interrupt-cells: must be set to <1>
+
+     - interrupt-map-mask,
+     - interrupt-map: standard PCI properties to define the mapping of the
+       PCI interface to interrupt numbers.
+
+   Besides the required properties the sub-nodes may have these optional
+   properties:
+
+     - status: indicates the operational status of the sub-node.
+       Value must be either "disabled" or "okay".
+
+3) Example:
+
+   a) SoC specific dtsi file:
+
+	pci@10140000 {
+		compatible = "ralink,rt3883-pci";
+		reg = <0x10140000 0x20000>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges; /* direct mapping */
+
+		status = "disabled";
+
+		pciintc: interrupt-controller {
+			interrupt-controller;
+			#address-cells = <0>;
+			#interrupt-cells = <1>;
+
+			interrupt-parent = <&cpuintc>;
+			interrupts = <4>;
+		};
+
+		host-bridge {
+			#address-cells = <3>;
+			#size-cells = <2>;
+			#interrupt-cells = <1>;
+
+			device_type = "pci";
+
+			bus-range = <0 255>;
+			ranges = <
+				0x02000000 0 0x00000000 0x20000000 0 0x10000000 /* pci memory */
+				0x01000000 0 0x00000000 0x10160000 0 0x00010000 /* io space */
+			>;
+
+			interrupt-map-mask = <0xf800 0 0 7>;
+			interrupt-map = <
+				/* IDSEL 17 */
+				0x8800 0 0 1 &pciintc 18
+				0x8800 0 0 2 &pciintc 18
+				0x8800 0 0 3 &pciintc 18
+				0x8800 0 0 4 &pciintc 18
+				/* IDSEL 18 */
+				0x9000 0 0 1 &pciintc 19
+				0x9000 0 0 2 &pciintc 19
+				0x9000 0 0 3 &pciintc 19
+				0x9000 0 0 4 &pciintc 19
+			>;
+
+			pci-bridge@1 {
+				reg = <0x0800 0 0 0 0>;
+				device_type = "pci";
+				#interrupt-cells = <1>;
+				#address-cells = <3>;
+				#size-cells = <2>;
+
+				interrupt-map-mask = <0x0 0 0 0>;
+				interrupt-map = <0x0 0 0 0 &pciintc 20>;
+
+				status = "disabled";
+			};
+
+			pci-slot@17 {
+				reg = <0x8800 0 0 0 0>;
+				device_type = "pci";
+
+				status = "disabled";
+			};
+
+			pci-slot@18 {
+				reg = <0x9000 0 0 0 0>;
+				device_type = "pci";
+
+				status = "disabled";
+			};
+		};
+	};
+
+   b) Board specific dts file:
+
+	pci@10140000 {
+		status = "okay";
+
+		host-bridge {
+			pci-bridge@1 {
+				status = "okay";
+			};
+		};
+	};
diff --git a/Documentation/devicetree/bindings/pinctrl/atmel,at91-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/atmel,at91-pinctrl.txt
index 648d60eb9fd8..7ccae490ff6d 100644
--- a/Documentation/devicetree/bindings/pinctrl/atmel,at91-pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/atmel,at91-pinctrl.txt
@@ -37,7 +37,7 @@ Bank: 3 (A, B and C)
   0xffffffff 0x7fff3ccf  /* pioB */
   0xffffffff 0x007fffff  /* pioC */
 
-For each peripheral/bank we will descibe in a u32 if a pin can can be
+For each peripheral/bank we will descibe in a u32 if a pin can be
 configured in it by putting 1 to the pin bit (1 << pin)
 
 Let's take the pioA on peripheral B
diff --git a/Documentation/devicetree/bindings/pinctrl/nvidia,tegra114-pinmux.txt b/Documentation/devicetree/bindings/pinctrl/nvidia,tegra114-pinmux.txt
index e204d009f16c..fb70856c5b51 100644
--- a/Documentation/devicetree/bindings/pinctrl/nvidia,tegra114-pinmux.txt
+++ b/Documentation/devicetree/bindings/pinctrl/nvidia,tegra114-pinmux.txt
@@ -80,6 +80,17 @@ Valid values for pin and group names are:
     dbg, sdio3, spi, uaa, uab, uart2, uart3, sdio1, ddc, gma, gme, gmf, gmg,
     gmh, owr, uda.
 
+Valid values for nvidia,functions are:
+
+  blink, cec, cldvfs, clk12, cpu, dap, dap1, dap2, dev3, displaya,
+  displaya_alt, displayb, dtv, emc_dll, extperiph1, extperiph2,
+  extperiph3, gmi, gmi_alt, hda, hsi, i2c1, i2c2, i2c3, i2c4, i2cpwr,
+  i2s0, i2s1, i2s2, i2s3, i2s4, irda, kbc, nand, nand_alt, owr, pmi,
+  pwm0, pwm1, pwm2, pwm3, pwron, reset_out_n, rsvd1, rsvd2, rsvd3,
+  rsvd4, sdmmc1, sdmmc2, sdmmc3, sdmmc4, soc, spdif, spi1, spi2, spi3,
+  spi4, spi5, spi6, sysclk, trace, uarta, uartb, uartc, uartd, ulpi,
+  usb, vgp1, vgp2, vgp3, vgp4, vgp5, vgp6, vi, vi_alt1, vi_alt3
+
 Example:
 
 	pinmux: pinmux {
diff --git a/Documentation/devicetree/bindings/pinctrl/nvidia,tegra20-pinmux.txt b/Documentation/devicetree/bindings/pinctrl/nvidia,tegra20-pinmux.txt
index 683fde93c4fb..61e73cde9ae9 100644
--- a/Documentation/devicetree/bindings/pinctrl/nvidia,tegra20-pinmux.txt
+++ b/Documentation/devicetree/bindings/pinctrl/nvidia,tegra20-pinmux.txt
@@ -103,6 +103,17 @@ Valid values for pin and group names are:
     drive_gma, drive_gmb, drive_gmc, drive_gmd, drive_gme, drive_owr,
     drive_uda.
 
+Valid values for nvidia,functions are:
+
+  ahb_clk, apb_clk, audio_sync, crt, dap1, dap2, dap3, dap4, dap5,
+  displaya, displayb, emc_test0_dll, emc_test1_dll, gmi, gmi_int,
+  hdmi, i2cp, i2c1, i2c2, i2c3, ide, irda, kbc, mio, mipi_hs, nand,
+  osc, owr, pcie, plla_out, pllc_out1, pllm_out1, pllp_out2, pllp_out3,
+  pllp_out4, pwm, pwr_intr, pwr_on, rsvd1, rsvd2, rsvd3, rsvd4, rtck,
+  sdio1, sdio2, sdio3, sdio4, sflash, spdif, spi1, spi2, spi2_alt,
+  spi3, spi4, trace, twc, uarta, uartb, uartc, uartd, uarte, ulpi,
+  vi, vi_sensor_clk, xio
+
 Example:
 
 	pinctrl@70000000 {
diff --git a/Documentation/devicetree/bindings/pinctrl/nvidia,tegra30-pinmux.txt b/Documentation/devicetree/bindings/pinctrl/nvidia,tegra30-pinmux.txt
index 6f426ed7009e..0e6354c11e6d 100644
--- a/Documentation/devicetree/bindings/pinctrl/nvidia,tegra30-pinmux.txt
+++ b/Documentation/devicetree/bindings/pinctrl/nvidia,tegra30-pinmux.txt
@@ -91,6 +91,18 @@ Valid values for pin and group names are:
     gmh, gpv, lcd1, lcd2, owr, sdio1, sdio2, sdio3, spi, uaa, uab, uart2,
     uart3, uda, vi1.
 
+Valid values for nvidia,functions are:
+
+  blink, cec, clk_12m_out, clk_32k_in, core_pwr_req, cpu_pwr_req, crt,
+  dap, ddr, dev3, displaya, displayb, dtv, extperiph1, extperiph2,
+  extperiph3, gmi, gmi_alt, hda, hdcp, hdmi, hsi, i2c1, i2c2, i2c3,
+  i2c4, i2cpwr, i2s0, i2s1, i2s2, i2s3, i2s4, invalid, kbc, mio, nand,
+  nand_alt, owr, pcie, pwm0, pwm1, pwm2, pwm3, pwr_int_n, rsvd1, rsvd2,
+  rsvd3, rsvd4, rtck, sata, sdmmc1, sdmmc2, sdmmc3, sdmmc4, spdif, spi1,
+  spi2, spi2_alt, spi3, spi4, spi5, spi6, sysclk, test, trace, uarta,
+  uartb, uartc, uartd, uarte, ulpi, vgp1, vgp2, vgp3, vgp4, vgp5, vgp6,
+  vi, vi_alt1, vi_alt2, vi_alt3
+
 Example:
 
 	pinctrl@70000000 {
diff --git a/Documentation/devicetree/bindings/pinctrl/pinctrl-bindings.txt b/Documentation/devicetree/bindings/pinctrl/pinctrl-bindings.txt
index aeb3c995cc04..1958ca9f9e5c 100644
--- a/Documentation/devicetree/bindings/pinctrl/pinctrl-bindings.txt
+++ b/Documentation/devicetree/bindings/pinctrl/pinctrl-bindings.txt
@@ -127,21 +127,20 @@ whether there is any interaction between the child and intermediate parent
 nodes, is again defined entirely by the binding for the individual pin
 controller device.
 
-== Using generic pinconfig options ==
+== Generic pin configuration node content ==
 
-Generic pinconfig parameters can be used by defining a separate node containing
-the applicable parameters (and optional values), like:
+Many data items that are represented in a pin configuration node are common
+and generic. Pin control bindings should use the properties defined below
+where they are applicable; not all of these properties are relevant or useful
+for all hardware or binding structures. Each individual binding document
+should state which of these generic properties, if any, are used, and the
+structure of the DT nodes that contain these properties.
 
-pcfg_pull_up: pcfg_pull_up {
-	bias-pull-up;
-	drive-strength = <20>;
-};
-
-This node should then be referenced in the appropriate pinctrl node as a phandle
-and parsed in the driver using the pinconf_generic_parse_dt_config function.
-
-Supported configuration parameters are:
+Supported generic properties are:
 
+pins			- the list of pins that properties in the node
+			  apply to
+function		- the mux function to select
 bias-disable		- disable any pin bias
 bias-high-impedance	- high impedance mode ("third-state", "floating")
 bias-bus-hold		- latch weakly
@@ -160,7 +159,21 @@ low-power-disable	- disable low power mode
 output-low		- set the pin to output mode with low level
 output-high		- set the pin to output mode with high level
 
-Arguments for parameters:
+Some of the generic properties take arguments. For those that do, the
+arguments are described below.
+
+- pins takes a list of pin names or IDs as a required argument. The specific
+  binding for the hardware defines:
+  - Whether the entries are integers or strings, and their meaning.
+
+- function takes a list of function names/IDs as a required argument. The
+  specific binding for the hardware defines:
+  - Whether the entries are integers or strings, and their meaning.
+  - Whether only a single entry is allowed (which is applied to all entries
+    in the pins property), or whether there may alternatively be one entry per
+    entry in the pins property, in which case the list lengths must match, and
+    for each list index i, the function at list index i is applied to the pin
+    at list index i.
 
 - bias-pull-up, -down and -pin-default take as optional argument on hardware
   supporting it the pull strength in Ohm. bias-disable will disable the pull.
@@ -170,7 +183,5 @@ Arguments for parameters:
 - input-debounce takes the debounce time in usec as argument
   or 0 to disable debouncing
 
-All parameters not listed here, do not take an argument.
-
 More in-depth documentation on these parameters can be found in
 <include/linux/pinctrl/pinconfig-generic.h>
diff --git a/Documentation/devicetree/bindings/pinctrl/pinctrl-palmas.txt b/Documentation/devicetree/bindings/pinctrl/pinctrl-palmas.txt
new file mode 100644
index 000000000000..734d9b04d533
--- /dev/null
+++ b/Documentation/devicetree/bindings/pinctrl/pinctrl-palmas.txt
@@ -0,0 +1,96 @@
+Palmas Pincontrol bindings
+
+The pins of Palmas device can be set on different option and provides
+the configuration for Pull UP/DOWN, open drain etc.
+
+Required properties:
+- compatible: It must be one of following:
+  - "ti,palmas-pinctrl" for Palma series of the pincontrol.
+  - "ti,tps65913-pinctrl" for Palma series device TPS65913.
+  - "ti,tps80036-pinctrl" for Palma series device TPS80036.
+
+Please refer to pinctrl-bindings.txt in this directory for details of the
+common pinctrl bindings used by client devices, including the meaning of the
+phrase "pin configuration node".
+
+Palmas's pin configuration nodes act as a container for an arbitrary number of
+subnodes. Each of these subnodes represents some desired configuration for a
+list of pins. This configuration can include the mux function to select on
+those pin(s), and various pin configuration parameters, such as pull-up,
+open drain.
+
+The name of each subnode is not important; all subnodes should be enumerated
+and processed purely based on their content.
+
+Each subnode only affects those parameters that are explicitly listed. In
+other words, a subnode that lists a mux function but no pin configuration
+parameters implies no information about any pin configuration parameters.
+Similarly, a pin subnode that describes a pullup parameter implies no
+information about e.g. the mux function.
+
+Optional properties:
+- ti,palmas-enable-dvfs1: Enable DVFS1. Configure pins for DVFS1 mode.
+	Selection primary or secondary function associated to I2C2_SCL_SCE,
+	I2C2_SDA_SDO pin/pad for DVFS1 interface
+- ti,palmas-enable-dvfs2: Enable DVFS2. Configure pins for DVFS2 mode.
+	Selection primary or secondary function associated to GPADC_START
+	and SYSEN2 pin/pad for DVFS2 interface
+
+This binding uses the following generic properties as defined in
+pinctrl-bindings.txt:
+
+Required: pins
+Options: function, bias-disable, bias-pull-up, bias-pull-down,
+	 bias-pin-default, drive-open-drain.
+
+Note that many of these properties are only valid for certain specific pins.
+See the Palmas device datasheet for complete details regarding which pins
+support which functionality.
+
+Valid values for pin names are:
+	gpio0, gpio1, gpio2, gpio3, gpio4, gpio5, gpio6, gpio7, gpio8, gpio9,
+	gpio10, gpio11, gpio12, gpio13, gpio14, gpio15, vac, powergood,
+	nreswarm, pwrdown, gpadc_start, reset_in, nsleep, enable1, enable2,
+	int.
+
+Valid value of function names are:
+	gpio, led, pwm, regen, sysen, clk32kgaudio, id, vbus_det, chrg_det,
+	vac, vacok, powergood, usb_psel, msecure, pwrhold, int, nreswarm,
+	simrsto, simrsti, low_vbat, wireless_chrg1, rcm, pwrdown, gpadc_start,
+	reset_in, nsleep, enable.
+
+There are 4 special functions: opt0, opt1, opt2 and opt3. If any of these
+functions is selected then directly pins register will be written with 0, 1, 2
+or 3 respectively if it is valid for that pins or list of pins.
+
+Example:
+	palmas: tps65913 {
+		....
+		pinctrl {
+			compatible = "ti,tps65913-pinctrl";
+			ti,palmas-enable-dvfs1;
+			pinctrl-names = "default";
+			pinctrl-0 = <&palmas_pins_state>;
+
+			palmas_pins_state: pinmux {
+				gpio0 {
+					pins = "gpio0";
+					function = "id";
+					bias-pull-up;
+				};
+
+				vac {
+					pins = "vac";
+					function = "vacok";
+					bias-pull-down;
+				};
+
+				gpio5 {
+					pins = "gpio5";
+					function = "opt0";
+					drive-open-drain = <1>;
+				};
+			};
+		};
+		....
+	};
diff --git a/Documentation/devicetree/bindings/pinctrl/samsung-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/samsung-pinctrl.txt
index 36281e7a2a46..257677de3e6b 100644
--- a/Documentation/devicetree/bindings/pinctrl/samsung-pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/samsung-pinctrl.txt
@@ -12,6 +12,7 @@ Required Properties:
   - "samsung,s3c2440-pinctrl": for S3C2440-compatible pin-controller,
   - "samsung,s3c2450-pinctrl": for S3C2450-compatible pin-controller,
   - "samsung,s3c64xx-pinctrl": for S3C64xx-compatible pin-controller,
+  - "samsung,s5pv210-pinctrl": for S5PV210-compatible pin-controller,
   - "samsung,exynos4210-pinctrl": for Exynos4210 compatible pin-controller.
   - "samsung,exynos4x12-pinctrl": for Exynos4x12 compatible pin-controller.
   - "samsung,exynos5250-pinctrl": for Exynos5250 compatible pin-controller.
@@ -128,7 +129,7 @@ B. External Wakeup Interrupts: For supporting external wakeup interrupts, a
      - samsung,s3c64xx-wakeup-eint: represents wakeup interrupt controller
        found on Samsung S3C64xx SoCs,
      - samsung,exynos4210-wakeup-eint: represents wakeup interrupt controller
-       found on Samsung Exynos4210 SoC.
+       found on Samsung Exynos4210 and S5PC110/S5PV210 SoCs.
    - interrupt-parent: phandle of the interrupt parent to which the external
      wakeup interrupts are forwarded to.
    - interrupts: interrupt used by multiplexed wakeup interrupts.
diff --git a/Documentation/devicetree/bindings/pinctrl/ste,nomadik.txt b/Documentation/devicetree/bindings/pinctrl/ste,nomadik.txt
index 9a2f3f420526..6b33b9f18e88 100644
--- a/Documentation/devicetree/bindings/pinctrl/ste,nomadik.txt
+++ b/Documentation/devicetree/bindings/pinctrl/ste,nomadik.txt
@@ -1,8 +1,8 @@
 ST Ericsson Nomadik pinmux controller
 
 Required properties:
-- compatible: "stericsson,nmk-pinctrl", "stericsson,nmk-pinctrl-db8540",
-              "stericsson,nmk-pinctrl-stn8815"
+- compatible: "stericsson,db8500-pinctrl", "stericsson,db8540-pinctrl",
+              "stericsson,stn8815-pinctrl"
 - reg: Should contain the register physical address and length of the PRCMU.
 
 Please refer to pinctrl-bindings.txt in this directory for details of the
@@ -68,7 +68,7 @@ Optional subnode-properties:
 Example board file extract:
 
 	pinctrl@80157000 {
-		compatible = "stericsson,nmk-pinctrl";
+		compatible = "stericsson,db8500-pinctrl";
 		reg = <0x80157000 0x2000>;
 
 		pinctrl-names = "default";
diff --git a/Documentation/devicetree/bindings/power_supply/msm-poweroff.txt b/Documentation/devicetree/bindings/power_supply/msm-poweroff.txt
new file mode 100644
index 000000000000..ce44ad357565
--- /dev/null
+++ b/Documentation/devicetree/bindings/power_supply/msm-poweroff.txt
@@ -0,0 +1,17 @@
+MSM Restart Driver
+
+A power supply hold (ps-hold) bit is set to power the msm chipsets.
+Clearing that bit allows us to restart/poweroff. The difference
+between poweroff and restart is determined by unique power manager IC
+settings.
+
+Required Properties:
+-compatible: "qcom,pshold"
+-reg: Specifies the physical address of the ps-hold register
+
+Example:
+
+	restart@fc4ab000 {
+		compatible = "qcom,pshold";
+		reg = <0xfc4ab000 0x4>;
+	};
diff --git a/Documentation/devicetree/bindings/powerpc/fsl/msi-pic.txt b/Documentation/devicetree/bindings/powerpc/fsl/msi-pic.txt
index 5693877ab377..82dd5b65cf48 100644
--- a/Documentation/devicetree/bindings/powerpc/fsl/msi-pic.txt
+++ b/Documentation/devicetree/bindings/powerpc/fsl/msi-pic.txt
@@ -1,21 +1,20 @@
 * Freescale MSI interrupt controller
 
 Required properties:
-- compatible : compatible list, contains 2 entries,
-  first is "fsl,CHIP-msi", where CHIP is the processor(mpc8610, mpc8572,
-  etc.) and the second is "fsl,mpic-msi" or "fsl,ipic-msi" depending on
-  the parent type.
+- compatible : compatible list, may contain one or two entries
+  The first is "fsl,CHIP-msi", where CHIP is the processor(mpc8610, mpc8572,
+  etc.) and the second is "fsl,mpic-msi" or "fsl,ipic-msi" or
+  "fsl,mpic-msi-v4.3" depending on the parent type and version. If mpic
+  version is 4.3, the number of MSI registers is increased to 16, MSIIR1 is
+  provided to access these 16 registers, and compatible "fsl,mpic-msi-v4.3"
+  should be used. The first entry is optional; the second entry is
+  required.
 
 - reg : It may contain one or two regions. The first region should contain
   the address and the length of the shared message interrupt register set.
-  The second region should contain the address of aliased MSIIR register for
-  platforms that have such an alias.
-
-- msi-available-ranges: use <start count> style section to define which
-  msi interrupt can be used in the 256 msi interrupts. This property is
-  optional, without this, all the 256 MSI interrupts can be used.
-  Each available range must begin and end on a multiple of 32 (i.e.
-  no splitting an individual MSI register or the associated PIC interrupt).
+  The second region should contain the address of aliased MSIIR or MSIIR1
+  register for platforms that have such an alias, if using MSIIR1, the second
+  region must be added because different MSI group has different MSIIR1 offset.
 
 - interrupts : each one of the interrupts here is one entry per 32 MSIs,
   and routed to the host interrupt controller. the interrupts should
@@ -28,6 +27,14 @@ Required properties:
   to MPIC.
 
 Optional properties:
+- msi-available-ranges: use <start count> style section to define which
+  msi interrupt can be used in the 256 msi interrupts. This property is
+  optional, without this, all the MSI interrupts can be used.
+  Each available range must begin and end on a multiple of 32 (i.e.
+  no splitting an individual MSI register or the associated PIC interrupt).
+  MPIC v4.3 does not support this property because the 32 interrupts of an
+  individual register are not continuous when using MSIIR1.
+
 - msi-address-64: 64-bit PCI address of the MSIIR register. The MSIIR register
   is used for MSI messaging.  The address of MSIIR in PCI address space is
   the MSI message address.
@@ -54,6 +61,28 @@ Example:
 		interrupt-parent = <&mpic>;
 	};
 
+	msi@41600 {
+		compatible = "fsl,mpic-msi-v4.3";
+		reg = <0x41600 0x200 0x44148 4>;
+		interrupts = <
+			0xe0 0 0 0
+			0xe1 0 0 0
+			0xe2 0 0 0
+			0xe3 0 0 0
+			0xe4 0 0 0
+			0xe5 0 0 0
+			0xe6 0 0 0
+			0xe7 0 0 0
+			0x100 0 0 0
+			0x101 0 0 0
+			0x102 0 0 0
+			0x103 0 0 0
+			0x104 0 0 0
+			0x105 0 0 0
+			0x106 0 0 0
+			0x107 0 0 0>;
+	};
+
 The Freescale hypervisor and msi-address-64
 -------------------------------------------
 Normally, PCI devices have access to all of CCSR via an ATMU mapping.  The
diff --git a/Documentation/devicetree/bindings/pwm/atmel-tcb-pwm.txt b/Documentation/devicetree/bindings/pwm/atmel-tcb-pwm.txt
index de0eaed86651..8031148bcf85 100644
--- a/Documentation/devicetree/bindings/pwm/atmel-tcb-pwm.txt
+++ b/Documentation/devicetree/bindings/pwm/atmel-tcb-pwm.txt
@@ -2,11 +2,9 @@ Atmel TCB PWM controller
 
 Required properties:
 - compatible: should be "atmel,tcb-pwm"
-- #pwm-cells: Should be 3.  The first cell specifies the per-chip index
-  of the PWM to use, the second cell is the period in nanoseconds and
-  bit 0 in the third cell is used to encode the polarity of PWM output.
-  Set bit 0 of the third cell in PWM specifier to 1 for inverse polarity &
-  set to 0 for normal polarity.
+- #pwm-cells: should be 3. See pwm.txt in this directory for a description of
+  the cells format. The only third cell flag supported by this binding is
+  PWM_POLARITY_INVERTED.
 - tc-block: The Timer Counter block to use as a PWM chip.
 
 Example:
diff --git a/Documentation/devicetree/bindings/pwm/imx-pwm.txt b/Documentation/devicetree/bindings/pwm/imx-pwm.txt
index 8522bfbccfd7..b50d7a6d9d7f 100644
--- a/Documentation/devicetree/bindings/pwm/imx-pwm.txt
+++ b/Documentation/devicetree/bindings/pwm/imx-pwm.txt
@@ -3,8 +3,8 @@ Freescale i.MX PWM controller
 Required properties:
 - compatible: should be "fsl,<soc>-pwm"
 - reg: physical base address and length of the controller's registers
-- #pwm-cells: should be 2.  The first cell specifies the per-chip index
-  of the PWM to use and the second cell is the period in nanoseconds.
+- #pwm-cells: should be 2. See pwm.txt in this directory for a description of
+  the cells format.
 - interrupts: The interrupt for the pwm controller
 
 Example:
diff --git a/Documentation/devicetree/bindings/pwm/mxs-pwm.txt b/Documentation/devicetree/bindings/pwm/mxs-pwm.txt
index 9e3f8f1d46a2..96cdde5f6208 100644
--- a/Documentation/devicetree/bindings/pwm/mxs-pwm.txt
+++ b/Documentation/devicetree/bindings/pwm/mxs-pwm.txt
@@ -3,8 +3,8 @@ Freescale MXS PWM controller
 Required properties:
 - compatible: should be "fsl,imx23-pwm"
 - reg: physical base address and length of the controller's registers
-- #pwm-cells: should be 2.  The first cell specifies the per-chip index
-  of the PWM to use and the second cell is the period in nanoseconds.
+- #pwm-cells: should be 2. See pwm.txt in this directory for a description of
+  the cells format.
 - fsl,pwm-number: the number of PWM devices
 
 Example:
diff --git a/Documentation/devicetree/bindings/pwm/nvidia,tegra20-pwm.txt b/Documentation/devicetree/bindings/pwm/nvidia,tegra20-pwm.txt
index 01438ecd6628..c3fc57af8772 100644
--- a/Documentation/devicetree/bindings/pwm/nvidia,tegra20-pwm.txt
+++ b/Documentation/devicetree/bindings/pwm/nvidia,tegra20-pwm.txt
@@ -5,9 +5,8 @@ Required properties:
   - "nvidia,tegra20-pwm"
   - "nvidia,tegra30-pwm"
 - reg: physical base address and length of the controller's registers
-- #pwm-cells: On Tegra the number of cells used to specify a PWM is 2. The
-  first cell specifies the per-chip index of the PWM to use and the second
-  cell is the period in nanoseconds.
+- #pwm-cells: should be 2. See pwm.txt in this directory for a description of
+  the cells format.
 
 Example:
 
diff --git a/Documentation/devicetree/bindings/pwm/nxp,pca9685-pwm.txt b/Documentation/devicetree/bindings/pwm/nxp,pca9685-pwm.txt
index 1e3dfe7a4894..f84ec9d291ea 100644
--- a/Documentation/devicetree/bindings/pwm/nxp,pca9685-pwm.txt
+++ b/Documentation/devicetree/bindings/pwm/nxp,pca9685-pwm.txt
@@ -3,8 +3,8 @@ NXP PCA9685 16-channel 12-bit PWM LED controller
 
 Required properties:
   - compatible: "nxp,pca9685-pwm"
-  - #pwm-cells: should be 2. The first cell specifies the per-chip index
-    of the PWM to use and the second cell is the period in nanoseconds.
+  - #pwm-cells: Should be 2. See pwm.txt in this directory for a description of
+    the cells format.
     The index 16 is the ALLCALL channel, that sets all PWM channels at the same
     time.
 
diff --git a/Documentation/devicetree/bindings/pwm/pwm-samsung.txt b/Documentation/devicetree/bindings/pwm/pwm-samsung.txt
index ac67c687a327..d61fccd40bad 100644
--- a/Documentation/devicetree/bindings/pwm/pwm-samsung.txt
+++ b/Documentation/devicetree/bindings/pwm/pwm-samsung.txt
@@ -19,13 +19,19 @@ Required properties:
 - reg: base address and size of register area
 - interrupts: list of timer interrupts (one interrupt per timer, starting at
   timer 0)
-- #pwm-cells: number of cells used for PWM specifier - must be 3
-   the specifier format is as follows:
-     - phandle to PWM controller node
-     - index of PWM channel (from 0 to 4)
-     - PWM signal period in nanoseconds
-     - bitmask of optional PWM flags:
-        0x1 - invert PWM signal
+- clock-names: should contain all following required clock names:
+    - "timers" - PWM base clock used to generate PWM signals,
+  and any subset of following optional clock names:
+    - "pwm-tclk0" - first external PWM clock source,
+    - "pwm-tclk1" - second external PWM clock source.
+  Note that not all IP variants allow using all external clock sources.
+  Refer to SoC documentation to learn which clock source configurations
+  are available.
+- clocks: should contain clock specifiers of all clocks, which input names
+  have been specified in clock-names property, in same order.
+- #pwm-cells: should be 3. See pwm.txt in this directory for a description of
+  the cells format. The only third cell flag supported by this binding is
+  PWM_POLARITY_INVERTED.
 
 Optional properties:
 - samsung,pwm-outputs: list of PWM channels used as PWM outputs on particular
@@ -38,6 +44,8 @@ Example:
 		reg = <0x7f006000 0x1000>;
 		interrupt-parent = <&vic0>;
 		interrupts = <23>, <24>, <25>, <27>, <28>;
+		clocks = <&clock 67>;
+		clock-names = "timers";
 		samsung,pwm-outputs = <0>, <1>;
 		#pwm-cells = <3>;
 	}
diff --git a/Documentation/devicetree/bindings/pwm/pwm-tiecap.txt b/Documentation/devicetree/bindings/pwm/pwm-tiecap.txt
index 681afad73778..fb81179dce37 100644
--- a/Documentation/devicetree/bindings/pwm/pwm-tiecap.txt
+++ b/Documentation/devicetree/bindings/pwm/pwm-tiecap.txt
@@ -4,11 +4,9 @@ Required properties:
 - compatible: Must be "ti,<soc>-ecap".
   for am33xx - compatible = "ti,am33xx-ecap";
   for da850  - compatible = "ti,da850-ecap", "ti,am33xx-ecap";
-- #pwm-cells: Should be 3. Number of cells being used to specify PWM property.
-  First cell specifies the per-chip index of the PWM to use, the second
-  cell is the period in nanoseconds and bit 0 in the third cell is used to
-  encode the polarity of PWM output. Set bit 0 of the third in PWM specifier
-  to 1 for inverse polarity & set to 0 for normal polarity.
+- #pwm-cells: should be 3. See pwm.txt in this directory for a description of
+  the cells format. The PWM channel index ranges from 0 to 4. The only third
+  cell flag supported by this binding is PWM_POLARITY_INVERTED.
 - reg: physical base address and size of the registers map.
 
 Optional properties:
diff --git a/Documentation/devicetree/bindings/pwm/pwm-tiehrpwm.txt b/Documentation/devicetree/bindings/pwm/pwm-tiehrpwm.txt
index 337c6fc65d3f..9c100b2c5b23 100644
--- a/Documentation/devicetree/bindings/pwm/pwm-tiehrpwm.txt
+++ b/Documentation/devicetree/bindings/pwm/pwm-tiehrpwm.txt
@@ -4,11 +4,9 @@ Required properties:
 - compatible: Must be "ti,<soc>-ehrpwm".
   for am33xx - compatible = "ti,am33xx-ehrpwm";
   for da850  - compatible = "ti,da850-ehrpwm", "ti,am33xx-ehrpwm";
-- #pwm-cells: Should be 3. Number of cells being used to specify PWM property.
-  First cell specifies the per-chip index of the PWM to use, the second
-  cell is the period in nanoseconds and bit 0 in the third cell is used to
-  encode the polarity of PWM output. Set bit 0 of the third in PWM specifier
-  to 1 for inverse polarity & set to 0 for normal polarity.
+- #pwm-cells: should be 3. See pwm.txt in this directory for a description of
+  the cells format. The only third cell flag supported by this binding is
+  PWM_POLARITY_INVERTED.
 - reg: physical base address and size of the registers map.
 
 Optional properties:
diff --git a/Documentation/devicetree/bindings/pwm/pwm.txt b/Documentation/devicetree/bindings/pwm/pwm.txt
index 06e67247859a..8556263b8502 100644
--- a/Documentation/devicetree/bindings/pwm/pwm.txt
+++ b/Documentation/devicetree/bindings/pwm/pwm.txt
@@ -43,13 +43,14 @@ because the name "backlight" would be used as fallback anyway.
 pwm-specifier typically encodes the chip-relative PWM number and the PWM
 period in nanoseconds.
 
-Optionally, the pwm-specifier can encode a number of flags in a third cell:
-- bit 0: PWM signal polarity (0: normal polarity, 1: inverse polarity)
+Optionally, the pwm-specifier can encode a number of flags (defined in
+<dt-bindings/pwm/pwm.h>) in a third cell:
+- PWM_POLARITY_INVERTED: invert the PWM signal polarity
 
 Example with optional PWM specifier for inverse polarity
 
 	bl: backlight {
-		pwms = <&pwm 0 5000000 1>;
+		pwms = <&pwm 0 5000000 PWM_POLARITY_INVERTED>;
 		pwm-names = "backlight";
 	};
 
diff --git a/Documentation/devicetree/bindings/pwm/renesas,tpu-pwm.txt b/Documentation/devicetree/bindings/pwm/renesas,tpu-pwm.txt
new file mode 100644
index 000000000000..b067e84a94b5
--- /dev/null
+++ b/Documentation/devicetree/bindings/pwm/renesas,tpu-pwm.txt
@@ -0,0 +1,28 @@
+* Renesas R-Car Timer Pulse Unit PWM Controller
+
+Required Properties:
+
+  - compatible: should be one of the following.
+    - "renesas,tpu-r8a73a4": for R8A77A4 (R-Mobile APE6) compatible PWM controller.
+    - "renesas,tpu-r8a7740": for R8A7740 (R-Mobile A1) compatible PWM controller.
+    - "renesas,tpu-r8a7790": for R8A7790 (R-Car H2) compatible PWM controller.
+    - "renesas,tpu-sh7372": for SH7372 (SH-Mobile AP4) compatible PWM controller.
+    - "renesas,tpu": for generic R-Car TPU PWM controller.
+
+  - reg: Base address and length of each memory resource used by the PWM
+    controller hardware module.
+
+  - #pwm-cells: should be 3. See pwm.txt in this directory for a description of
+    the cells format. The only third cell flag supported by this binding is
+    PWM_POLARITY_INVERTED.
+
+Please refer to pwm.txt in this directory for details of the common PWM bindings
+used by client devices.
+
+Example: R8A7740 (R-Car A1) TPU controller node
+
+	tpu: pwm@e6600000 {
+		compatible = "renesas,tpu-r8a7740", "renesas,tpu";
+		reg = <0xe6600000 0x100>;
+		#pwm-cells = <3>;
+	};
diff --git a/Documentation/devicetree/bindings/pwm/spear-pwm.txt b/Documentation/devicetree/bindings/pwm/spear-pwm.txt
index 3ac779d83386..b486de2c3fe3 100644
--- a/Documentation/devicetree/bindings/pwm/spear-pwm.txt
+++ b/Documentation/devicetree/bindings/pwm/spear-pwm.txt
@@ -5,9 +5,8 @@ Required properties:
   - "st,spear320-pwm"
   - "st,spear1340-pwm"
 - reg: physical base address and length of the controller's registers
-- #pwm-cells: number of cells used to specify PWM which is fixed to 2 on
-  SPEAr. The first cell specifies the per-chip index of the PWM to use and
-  the second cell is the period in nanoseconds.
+- #pwm-cells: should be 2. See pwm.txt in this directory for a description of
+  the cells format.
 
 Example:
 
diff --git a/Documentation/devicetree/bindings/pwm/ti,twl-pwm.txt b/Documentation/devicetree/bindings/pwm/ti,twl-pwm.txt
index 2943ee5fce00..4e32bee11201 100644
--- a/Documentation/devicetree/bindings/pwm/ti,twl-pwm.txt
+++ b/Documentation/devicetree/bindings/pwm/ti,twl-pwm.txt
@@ -6,8 +6,8 @@ On TWL6030 series: PWM0 and PWM1
 
 Required properties:
 - compatible: "ti,twl4030-pwm" or "ti,twl6030-pwm"
-- #pwm-cells: should be 2.  The first cell specifies the per-chip index
-  of the PWM to use and the second cell is the period in nanoseconds.
+- #pwm-cells: should be 2. See pwm.txt in this directory for a description of
+  the cells format.
 
 Example:
 
diff --git a/Documentation/devicetree/bindings/pwm/ti,twl-pwmled.txt b/Documentation/devicetree/bindings/pwm/ti,twl-pwmled.txt
index cb64f3acc10f..9f4b46090782 100644
--- a/Documentation/devicetree/bindings/pwm/ti,twl-pwmled.txt
+++ b/Documentation/devicetree/bindings/pwm/ti,twl-pwmled.txt
@@ -6,8 +6,8 @@ On TWL6030 series: LED PWM (mainly used as charging indicator LED)
 
 Required properties:
 - compatible: "ti,twl4030-pwmled" or "ti,twl6030-pwmled"
-- #pwm-cells: should be 2.  The first cell specifies the per-chip index
-  of the PWM to use and the second cell is the period in nanoseconds.
+- #pwm-cells: should be 2. See pwm.txt in this directory for a description of
+  the cells format.
 
 Example:
 
diff --git a/Documentation/devicetree/bindings/pwm/vt8500-pwm.txt b/Documentation/devicetree/bindings/pwm/vt8500-pwm.txt
index d21d82d29855..a76390e6df2e 100644
--- a/Documentation/devicetree/bindings/pwm/vt8500-pwm.txt
+++ b/Documentation/devicetree/bindings/pwm/vt8500-pwm.txt
@@ -3,11 +3,9 @@ VIA/Wondermedia VT8500/WM8xxx series SoC PWM controller
 Required properties:
 - compatible: should be "via,vt8500-pwm"
 - reg: physical base address and length of the controller's registers
-- #pwm-cells: Should be 3. Number of cells being used to specify PWM property.
-  First cell specifies the per-chip index of the PWM to use, the second
-  cell is the period in nanoseconds and bit 0 in the third cell is used to
-  encode the polarity of PWM output. Set bit 0 of the third in PWM specifier
-  to 1 for inverse polarity & set to 0 for normal polarity.
+- #pwm-cells: should be 3. See pwm.txt in this directory for a description of
+  the cells format. The only third cell flag supported by this binding is
+  PWM_POLARITY_INVERTED.
 - clocks: phandle to the PWM source clock
 
 Example:
diff --git a/Documentation/devicetree/bindings/regulator/88pm800.txt b/Documentation/devicetree/bindings/regulator/88pm800.txt
new file mode 100644
index 000000000000..e8a54c2a5821
--- /dev/null
+++ b/Documentation/devicetree/bindings/regulator/88pm800.txt
@@ -0,0 +1,38 @@
+Marvell 88PM800 regulator
+
+Required properties:
+- compatible: "marvell,88pm800"
+- reg: I2C slave address
+- regulators: A node that houses a sub-node for each regulator within the
+  device. Each sub-node is identified using the node's name (or the deprecated
+  regulator-compatible property if present), with valid values listed below.
+  The content of each sub-node is defined by the standard binding for
+  regulators; see regulator.txt.
+
+The valid names for regulators are:
+
+  buck1, buck2, buck3, buck4, buck5, ldo1, ldo2, ldo3, ldo4, ldo5, ldo6, ldo7,
+  ldo8, ldo9, ldo10, ldo11, ldo12, ldo13, ldo14, ldo15, ldo16, ldo17, ldo18, ldo19
+
+Example:
+
+	pmic: 88pm800@31 {
+		compatible = "marvell,88pm800";
+		reg = <0x31>;
+
+		regulators {
+			buck1 {
+			        regulator-min-microvolt = <600000>;
+			        regulator-max-microvolt = <3950000>;
+			        regulator-boot-on;
+			        regulator-always-on;
+			};
+			ldo1 {
+			        regulator-min-microvolt = <600000>;
+			        regulator-max-microvolt = <15000000>;
+			        regulator-boot-on;
+			        regulator-always-on;
+			};
+...
+		};
+	};
diff --git a/Documentation/devicetree/bindings/regulator/max8660.txt b/Documentation/devicetree/bindings/regulator/max8660.txt
new file mode 100644
index 000000000000..8ba994d8a142
--- /dev/null
+++ b/Documentation/devicetree/bindings/regulator/max8660.txt
@@ -0,0 +1,47 @@
+Maxim MAX8660 voltage regulator
+
+Required properties:
+- compatible: must be one of "maxim,max8660", "maxim,max8661"
+- reg: I2C slave address, usually 0x34
+- any required generic properties defined in regulator.txt
+
+Example:
+
+	i2c_master {
+		max8660@34 {
+			compatible = "maxim,max8660";
+			reg = <0x34>;
+
+			regulators {
+				regulator@0 {
+					regulator-compatible= "V3(DCDC)";
+					regulator-min-microvolt = <725000>;
+					regulator-max-microvolt = <1800000>;
+				};
+
+				regulator@1 {
+					regulator-compatible= "V4(DCDC)";
+					regulator-min-microvolt = <725000>;
+					regulator-max-microvolt = <1800000>;
+				};
+
+				regulator@2 {
+					regulator-compatible= "V5(LDO)";
+					regulator-min-microvolt = <1700000>;
+					regulator-max-microvolt = <2000000>;
+				};
+
+				regulator@3 {
+					regulator-compatible= "V6(LDO)";
+					regulator-min-microvolt = <1800000>;
+					regulator-max-microvolt = <3300000>;
+				};
+
+				regulator@4 {
+					regulator-compatible= "V7(LDO)";
+					regulator-min-microvolt = <1800000>;
+					regulator-max-microvolt = <3300000>;
+				};
+			};
+		};
+	};
diff --git a/Documentation/devicetree/bindings/regulator/palmas-pmic.txt b/Documentation/devicetree/bindings/regulator/palmas-pmic.txt
index 30b0581bb1ce..875639ae0606 100644
--- a/Documentation/devicetree/bindings/regulator/palmas-pmic.txt
+++ b/Documentation/devicetree/bindings/regulator/palmas-pmic.txt
@@ -25,8 +25,8 @@ Optional nodes:
 	       Additional custom properties  are listed below.
 
 	       For ti,palmas-pmic - smps12, smps123, smps3 depending on OTP,
-	       smps45, smps457, smps7 depending on variant, smps6, smps[8-10],
-	       ldo[1-9], ldoln, ldousb.
+	       smps45, smps457, smps7 depending on variant, smps6, smps[8-9],
+	       smps10_out2, smps10_out1, do[1-9], ldoln, ldousb.
 
 	       Optional sub-node properties:
 	       ti,warm-reset - maintain voltage during warm reset(boolean)
@@ -36,6 +36,9 @@ Optional nodes:
 	       ti,smps-range - OTP has the wrong range set for the hardware so override
 	       0 - low range, 1 - high range.
 
+- ti,system-power-controller: Telling whether or not this pmic is controlling
+			      the system power.
+
 Example:
 
 #include <dt-bindings/interrupt-controller/irq.h>
@@ -48,6 +51,8 @@ pmic {
 
 	ti,ldo6-vibrator;
 
+	ti,system-power-controller;
+
 	regulators {
 		smps12_reg : smps12 {
 			regulator-name = "smps12";
diff --git a/Documentation/devicetree/bindings/regulator/pfuze100.txt b/Documentation/devicetree/bindings/regulator/pfuze100.txt
new file mode 100644
index 000000000000..fc989b2e8057
--- /dev/null
+++ b/Documentation/devicetree/bindings/regulator/pfuze100.txt
@@ -0,0 +1,115 @@
+PFUZE100 family of regulators
+
+Required properties:
+- compatible: "fsl,pfuze100"
+- reg: I2C slave address
+
+Required child node:
+- regulators: This is the list of child nodes that specify the regulator
+  initialization data for defined regulators. Please refer to below doc
+  Documentation/devicetree/bindings/regulator/regulator.txt.
+
+  The valid names for regulators are:
+  sw1ab,sw1c,sw2,sw3a,sw3b,sw4,swbst,vsnvs,vrefddr,vgen1~vgen6
+
+Each regulator is defined using the standard binding for regulators.
+
+Example:
+
+	pmic: pfuze100@08 {
+		compatible = "fsl,pfuze100";
+		reg = <0x08>;
+
+		regulators {
+			sw1a_reg: sw1ab {
+				regulator-min-microvolt = <300000>;
+				regulator-max-microvolt = <1875000>;
+				regulator-boot-on;
+				regulator-always-on;
+				regulator-ramp-delay = <6250>;
+			};
+
+			sw1c_reg: sw1c {
+				regulator-min-microvolt = <300000>;
+				regulator-max-microvolt = <1875000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			sw2_reg: sw2 {
+				regulator-min-microvolt = <800000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			sw3a_reg: sw3a {
+				regulator-min-microvolt = <400000>;
+				regulator-max-microvolt = <1975000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			sw3b_reg: sw3b {
+				regulator-min-microvolt = <400000>;
+				regulator-max-microvolt = <1975000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			sw4_reg: sw4 {
+				regulator-min-microvolt = <800000>;
+				regulator-max-microvolt = <3300000>;
+			};
+
+			swbst_reg: swbst {
+				regulator-min-microvolt = <5000000>;
+				regulator-max-microvolt = <5150000>;
+			};
+
+			snvs_reg: vsnvs {
+				regulator-min-microvolt = <1000000>;
+				regulator-max-microvolt = <3000000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			vref_reg: vrefddr {
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			vgen1_reg: vgen1 {
+				regulator-min-microvolt = <800000>;
+				regulator-max-microvolt = <1550000>;
+			};
+
+			vgen2_reg: vgen2 {
+				regulator-min-microvolt = <800000>;
+				regulator-max-microvolt = <1550000>;
+			};
+
+			vgen3_reg: vgen3 {
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <3300000>;
+			};
+
+			vgen4_reg: vgen4 {
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-always-on;
+			};
+
+			vgen5_reg: vgen5 {
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-always-on;
+			};
+
+			vgen6_reg: vgen6 {
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-always-on;
+			};
+		};
+	};
diff --git a/Documentation/devicetree/bindings/regulator/regulator.txt b/Documentation/devicetree/bindings/regulator/regulator.txt
index 48a3b8e5d6bd..2bd8f0978765 100644
--- a/Documentation/devicetree/bindings/regulator/regulator.txt
+++ b/Documentation/devicetree/bindings/regulator/regulator.txt
@@ -12,6 +12,8 @@ Optional properties:
 - regulator-allow-bypass: allow the regulator to go into bypass mode
 - <name>-supply: phandle to the parent supply/regulator node
 - regulator-ramp-delay: ramp delay for regulator(in uV/uS)
+  For hardwares which support disabling ramp rate, it should be explicitly
+  intialised to zero (regulator-ramp-delay = <0>) for disabling ramp delay.
 
 Deprecated properties:
 - regulator-compatible: If a regulator chip contains multiple
diff --git a/Documentation/devicetree/bindings/rtc/dw-apb.txt b/Documentation/devicetree/bindings/rtc/dw-apb.txt
index eb2327b2bdb3..c703d51abb6c 100644
--- a/Documentation/devicetree/bindings/rtc/dw-apb.txt
+++ b/Documentation/devicetree/bindings/rtc/dw-apb.txt
@@ -1,7 +1,10 @@
 * Designware APB timer
 
 Required properties:
-- compatible: "snps,dw-apb-timer-sp" or "snps,dw-apb-timer-osc"
+- compatible: One of:
+ 	"snps,dw-apb-timer"
+	"snps,dw-apb-timer-sp" <DEPRECATED>
+	"snps,dw-apb-timer-osc" <DEPRECATED>
 - reg: physical base address of the controller and length of memory mapped
   region.
 - interrupts: IRQ line for the timer.
@@ -20,25 +23,10 @@ systems may use one.
 
 
 Example:
-
-		timer1: timer@ffc09000 {
-				compatible = "snps,dw-apb-timer-sp";
-				interrupts = <0 168 4>;
-				clock-frequency = <200000000>;
-				reg = <0xffc09000 0x1000>;
-			};
-
-		timer2: timer@ffd00000 {
-				compatible = "snps,dw-apb-timer-osc";
-				interrupts = <0 169 4>;
-				clock-frequency = <200000000>;
-				reg = <0xffd00000 0x1000>;
-			};
-
-		timer3: timer@ffe00000 {
-				compatible = "snps,dw-apb-timer-osc";
-				interrupts = <0 170 4>;
-				reg = <0xffe00000 0x1000>;
-				clocks = <&timer_clk>, <&timer_pclk>;
-				clock-names = "timer", "pclk";
-			};
+	timer@ffe00000 {
+		compatible = "snps,dw-apb-timer";
+		interrupts = <0 170 4>;
+		reg = <0xffe00000 0x1000>;
+		clocks = <&timer_clk>, <&timer_pclk>;
+		clock-names = "timer", "pclk";
+	};
diff --git a/Documentation/devicetree/bindings/rtc/moxa,moxart-rtc.txt b/Documentation/devicetree/bindings/rtc/moxa,moxart-rtc.txt
new file mode 100644
index 000000000000..c9d3ac1477fe
--- /dev/null
+++ b/Documentation/devicetree/bindings/rtc/moxa,moxart-rtc.txt
@@ -0,0 +1,17 @@
+MOXA ART real-time clock
+
+Required properties:
+
+- compatible : Should be "moxa,moxart-rtc"
+- gpio-rtc-sclk : RTC sclk gpio, with zero flags
+- gpio-rtc-data : RTC data gpio, with zero flags
+- gpio-rtc-reset : RTC reset gpio, with zero flags
+
+Example:
+
+	rtc: rtc {
+		compatible = "moxa,moxart-rtc";
+		gpio-rtc-sclk = <&gpio 5 0>;
+		gpio-rtc-data = <&gpio 6 0>;
+		gpio-rtc-reset = <&gpio 7 0>;
+	};
diff --git a/Documentation/devicetree/bindings/rtc/rtc-omap.txt b/Documentation/devicetree/bindings/rtc/rtc-omap.txt
index b47aa415c820..5a0f02d34d95 100644
--- a/Documentation/devicetree/bindings/rtc/rtc-omap.txt
+++ b/Documentation/devicetree/bindings/rtc/rtc-omap.txt
@@ -1,7 +1,11 @@
 TI Real Time Clock
 
 Required properties:
-- compatible: "ti,da830-rtc"
+- compatible:
+	- "ti,da830-rtc"  - for RTC IP used similar to that on DA8xx SoC family.
+	- "ti,am3352-rtc" - for RTC IP used similar to that on AM335x SoC family.
+			    This RTC IP has special WAKE-EN Register to enable
+			    Wakeup generation for event Alarm.
 - reg: Address range of rtc register set
 - interrupts: rtc timer, alarm interrupts in order
 - interrupt-parent: phandle for the interrupt controller
diff --git a/Documentation/devicetree/bindings/rtc/rtc-palmas.txt b/Documentation/devicetree/bindings/rtc/rtc-palmas.txt
new file mode 100644
index 000000000000..adbccc0a51e1
--- /dev/null
+++ b/Documentation/devicetree/bindings/rtc/rtc-palmas.txt
@@ -0,0 +1,33 @@
+Palmas RTC controller bindings
+
+Required properties:
+- compatible:
+  - "ti,palmas-rtc" for palma series of the RTC controller
+- interrupt-parent: Parent interrupt device, must be handle of palmas node.
+- interrupts: Interrupt number of RTC submodule on device.
+
+Optional properties:
+
+- ti,backup-battery-chargeable: The Palmas series device like TPS65913 or
+	TPS80036 supports the backup battery for powering the RTC when main
+	battery is removed or in very low power state. The backup battery
+	can be chargeable or non-chargeable. This flag will tells whether
+	battery is chargeable or not. If charging battery then driver can
+	enable the charging.
+- ti,backup-battery-charge-high-current: Enable high current charging in
+	backup battery. Device supports the < 100mA and > 100mA charging.
+	The high current will be > 100mA. Absence of this property will
+	charge battery to lower current i.e. < 100mA.
+
+Example:
+	palmas: tps65913@58 {
+		...
+		palmas_rtc: rtc {
+			compatible = "ti,palmas-rtc";
+			interrupt-parent = <&palmas>;
+			interrupts = <8 0>;
+			ti,backup-battery-chargeable;
+			ti,backup-battery-charge-high-current;
+		};
+		...
+	};
diff --git a/Documentation/devicetree/bindings/serial/altera_jtaguart.txt b/Documentation/devicetree/bindings/serial/altera_jtaguart.txt
index c152f65f9a28..55a901051e8f 100644
--- a/Documentation/devicetree/bindings/serial/altera_jtaguart.txt
+++ b/Documentation/devicetree/bindings/serial/altera_jtaguart.txt
@@ -1,4 +1,5 @@
 Altera JTAG UART
 
 Required properties:
-- compatible : should be "ALTR,juart-1.0"
+- compatible : should be "ALTR,juart-1.0" <DEPRECATED>
+- compatible : should be "altr,juart-1.0"
diff --git a/Documentation/devicetree/bindings/serial/altera_uart.txt b/Documentation/devicetree/bindings/serial/altera_uart.txt
index 71cae3f70100..81bf7ffb1a81 100644
--- a/Documentation/devicetree/bindings/serial/altera_uart.txt
+++ b/Documentation/devicetree/bindings/serial/altera_uart.txt
@@ -1,7 +1,8 @@
 Altera UART
 
 Required properties:
-- compatible : should be "ALTR,uart-1.0"
+- compatible : should be "ALTR,uart-1.0" <DEPRECATED>
+- compatible : should be "altr,uart-1.0"
 
 Optional properties:
 - clock-frequency : frequency of the clock input to the UART
diff --git a/Documentation/devicetree/bindings/tty/serial/arc-uart.txt b/Documentation/devicetree/bindings/serial/arc-uart.txt
index 5cae2eb686f8..5cae2eb686f8 100644
--- a/Documentation/devicetree/bindings/tty/serial/arc-uart.txt
+++ b/Documentation/devicetree/bindings/serial/arc-uart.txt
diff --git a/Documentation/devicetree/bindings/tty/serial/atmel-usart.txt b/Documentation/devicetree/bindings/serial/atmel-usart.txt
index a49d9a1d4ccf..2191dcb9f1da 100644
--- a/Documentation/devicetree/bindings/tty/serial/atmel-usart.txt
+++ b/Documentation/devicetree/bindings/serial/atmel-usart.txt
@@ -10,13 +10,18 @@ Required properties:
 Optional properties:
 - atmel,use-dma-rx: use of PDC or DMA for receiving data
 - atmel,use-dma-tx: use of PDC or DMA for transmitting data
+- add dma bindings for dma transfer:
+	- dmas: DMA specifier, consisting of a phandle to DMA controller node,
+		memory peripheral interface and USART DMA channel ID, FIFO configuration.
+		Refer to dma.txt and atmel-dma.txt for details.
+	- dma-names: "rx" for RX channel, "tx" for TX channel.
 
 <chip> compatible description:
 - at91rm9200:  legacy USART support
 - at91sam9260: generic USART implementation for SAM9 SoCs
 
 Example:
-
+- use PDC:
 	usart0: serial@fff8c000 {
 		compatible = "atmel,at91sam9260-usart";
 		reg = <0xfff8c000 0x4000>;
@@ -25,3 +30,14 @@ Example:
 		atmel,use-dma-tx;
 	};
 
+- use DMA:
+	usart0: serial@f001c000 {
+		compatible = "atmel,at91sam9260-usart";
+		reg = <0xf001c000 0x100>;
+		interrupts = <12 4 5>;
+		atmel,use-dma-rx;
+		atmel,use-dma-tx;
+		dmas = <&dma0 2 0x3>,
+		       <&dma0 2 0x204>;
+		dma-names = "tx", "rx";
+	};
diff --git a/Documentation/devicetree/bindings/tty/serial/efm32-uart.txt b/Documentation/devicetree/bindings/serial/efm32-uart.txt
index 8e080b893b49..8e080b893b49 100644
--- a/Documentation/devicetree/bindings/tty/serial/efm32-uart.txt
+++ b/Documentation/devicetree/bindings/serial/efm32-uart.txt
diff --git a/Documentation/devicetree/bindings/serial/fsl-imx-uart.txt b/Documentation/devicetree/bindings/serial/fsl-imx-uart.txt
index c58573b5b1a4..35ae1fb3537f 100644
--- a/Documentation/devicetree/bindings/serial/fsl-imx-uart.txt
+++ b/Documentation/devicetree/bindings/serial/fsl-imx-uart.txt
@@ -1,35 +1,29 @@
-* Freescale i.MX UART controller
+* Freescale i.MX Universal Asynchronous Receiver/Transmitter (UART)
 
 Required properties:
-- compatible : should be "fsl,imx21-uart"
+- compatible : Should be "fsl,<soc>-uart"
 - reg : Address and length of the register set for the device
-- interrupts : Should contain UART interrupt number
+- interrupts : Should contain uart interrupt
 
 Optional properties:
-- fsl,uart-has-rtscts: indicate that RTS/CTS signals are used
+- fsl,uart-has-rtscts : Indicate the uart has rts and cts
+- fsl,irda-mode : Indicate the uart supports irda mode
+- fsl,dte-mode : Indicate the uart works in DTE mode. The uart works
+                  is DCE mode by default.
 
 Note: Each uart controller should have an alias correctly numbered
 in "aliases" node.
 
 Example:
 
-- From imx51.dtsi:
 aliases {
 	serial0 = &uart1;
-	serial1 = &uart2;
-	serial2 = &uart3;
 };
 
 uart1: serial@73fbc000 {
 	compatible = "fsl,imx51-uart", "fsl,imx21-uart";
 	reg = <0x73fbc000 0x4000>;
 	interrupts = <31>;
-	status = "disabled";
-}
-
-- From imx51-babbage.dts:
-uart1: serial@73fbc000 {
 	fsl,uart-has-rtscts;
-	status = "okay";
+	fsl,dte-mode;
 };
-
diff --git a/Documentation/devicetree/bindings/tty/serial/fsl-lpuart.txt b/Documentation/devicetree/bindings/serial/fsl-lpuart.txt
index 6fd1dd1638dd..6fd1dd1638dd 100644
--- a/Documentation/devicetree/bindings/tty/serial/fsl-lpuart.txt
+++ b/Documentation/devicetree/bindings/serial/fsl-lpuart.txt
diff --git a/Documentation/devicetree/bindings/tty/serial/fsl-mxs-auart.txt b/Documentation/devicetree/bindings/serial/fsl-mxs-auart.txt
index 2c00ec64628e..59a40f18d551 100644
--- a/Documentation/devicetree/bindings/tty/serial/fsl-mxs-auart.txt
+++ b/Documentation/devicetree/bindings/serial/fsl-mxs-auart.txt
@@ -10,6 +10,10 @@ Required properties:
   Refer to dma.txt and fsl-mxs-dma.txt for details.
 - dma-names: "rx" for RX channel, "tx" for TX channel.
 
+Optional properties:
+- fsl,uart-has-rtscts : Indicate the UART has RTS and CTS lines,
+	it also means you enable the DMA support for this UART.
+
 Example:
 auart0: serial@8006a000 {
 	compatible = "fsl,imx28-auart", "fsl,imx23-auart";
diff --git a/Documentation/devicetree/bindings/serial/mrvl,pxa-ssp.txt b/Documentation/devicetree/bindings/serial/mrvl,pxa-ssp.txt
new file mode 100644
index 000000000000..669b8140dd79
--- /dev/null
+++ b/Documentation/devicetree/bindings/serial/mrvl,pxa-ssp.txt
@@ -0,0 +1,65 @@
+Device tree bindings for Marvell PXA SSP ports
+
+Required properties:
+
+	- compatible:	Must be one of
+				mrvl,pxa25x-ssp
+				mvrl,pxa25x-nssp
+				mrvl,pxa27x-ssp
+				mrvl,pxa3xx-ssp
+				mvrl,pxa168-ssp
+				mrvl,pxa910-ssp
+				mrvl,ce4100-ssp
+				mrvl,lpss-ssp
+
+	- reg:		The memory base
+	- dmas:		Two dma phandles, one for rx, one for tx
+	- dma-names:	Must be "rx", "tx"
+
+
+Example for PXA3xx:
+
+	ssp0: ssp@41000000 {
+		compatible = "mrvl,pxa3xx-ssp";
+		reg = <0x41000000 0x40>;
+		ssp-id = <1>;
+		interrupts = <24>;
+		clock-names = "pxa27x-ssp.0";
+		dmas = <&dma 13
+			&dma 14>;
+		dma-names = "rx", "tx";
+	};
+
+	ssp1: ssp@41700000 {
+		compatible = "mrvl,pxa3xx-ssp";
+		reg = <0x41700000 0x40>;
+		ssp-id = <2>;
+		interrupts = <16>;
+		clock-names = "pxa27x-ssp.1";
+		dmas = <&dma 15
+			&dma 16>;
+		dma-names = "rx", "tx";
+	};
+
+	ssp2: ssp@41900000 {
+		compatibl3 = "mrvl,pxa3xx-ssp";
+		reg = <0x41900000 0x40>;
+		ssp-id = <3>;
+		interrupts = <0>;
+		clock-names = "pxa27x-ssp.2";
+		dmas = <&dma 66
+			&dma 67>;
+		dma-names = "rx", "tx";
+	};
+
+	ssp3: ssp@41a00000 {
+		compatible = "mrvl,pxa3xx-ssp";
+		reg = <0x41a00000 0x40>;
+		ssp-id = <4>;
+		interrupts = <13>;
+		clock-names = "pxa27x-ssp.3";
+		dmas = <&dma 2
+			&dma 3>;
+		dma-names = "rx", "tx";
+	};
+
diff --git a/Documentation/devicetree/bindings/tty/serial/nxp-lpc32xx-hsuart.txt b/Documentation/devicetree/bindings/serial/nxp-lpc32xx-hsuart.txt
index 0d439dfc1aa5..0d439dfc1aa5 100644
--- a/Documentation/devicetree/bindings/tty/serial/nxp-lpc32xx-hsuart.txt
+++ b/Documentation/devicetree/bindings/serial/nxp-lpc32xx-hsuart.txt
diff --git a/Documentation/devicetree/bindings/tty/serial/of-serial.txt b/Documentation/devicetree/bindings/serial/of-serial.txt
index 1928a3e83cd0..1928a3e83cd0 100644
--- a/Documentation/devicetree/bindings/tty/serial/of-serial.txt
+++ b/Documentation/devicetree/bindings/serial/of-serial.txt
diff --git a/Documentation/devicetree/bindings/serial/qca,ar9330-uart.txt b/Documentation/devicetree/bindings/serial/qca,ar9330-uart.txt
new file mode 100644
index 000000000000..c5e032c85bf9
--- /dev/null
+++ b/Documentation/devicetree/bindings/serial/qca,ar9330-uart.txt
@@ -0,0 +1,34 @@
+* Qualcomm Atheros AR9330 High-Speed UART
+
+Required properties:
+
+- compatible: Must be "qca,ar9330-uart"
+
+- reg: Specifies the physical base address of the controller and
+  the length of the memory mapped region.
+
+- interrupt-parent: The phandle for the interrupt controller that
+  services interrupts for this device.
+
+- interrupts: Specifies the interrupt source of the parent interrupt
+  controller. The format of the interrupt specifier depends on the
+  parent interrupt controller.
+
+Additional requirements:
+
+  Each UART port must have an alias correctly numbered in "aliases"
+  node.
+
+Example:
+
+	aliases {
+		serial0 = &uart0;
+	};
+
+	uart0: uart@18020000 {
+		compatible = "qca,ar9330-uart";
+		reg = <0x18020000 0x14>;
+
+		interrupt-parent = <&intc>;
+		interrupts = <3>;
+	};
diff --git a/Documentation/devicetree/bindings/serial/qcom,msm-uart.txt b/Documentation/devicetree/bindings/serial/qcom,msm-uart.txt
new file mode 100644
index 000000000000..ce8c90161959
--- /dev/null
+++ b/Documentation/devicetree/bindings/serial/qcom,msm-uart.txt
@@ -0,0 +1,25 @@
+* MSM Serial UART
+
+The MSM serial UART hardware is designed for low-speed use cases where a
+dma-engine isn't needed. From a software perspective it's mostly compatible
+with the MSM serial UARTDM except that it only supports reading and writing one
+character at a time.
+
+Required properties:
+- compatible: Should contain "qcom,msm-uart"
+- reg: Should contain UART register location and length.
+- interrupts: Should contain UART interrupt.
+- clocks: Should contain the core clock.
+- clock-names: Should be "core".
+
+Example:
+
+A uart device at 0xa9c00000 with interrupt 11.
+
+serial@a9c00000 {
+	compatible = "qcom,msm-uart";
+	reg = <0xa9c00000 0x1000>;
+	interrupts = <11>;
+	clocks = <&uart_cxc>;
+	clock-names = "core";
+};
diff --git a/Documentation/devicetree/bindings/serial/qcom,msm-uartdm.txt b/Documentation/devicetree/bindings/serial/qcom,msm-uartdm.txt
new file mode 100644
index 000000000000..ffa5b784c66e
--- /dev/null
+++ b/Documentation/devicetree/bindings/serial/qcom,msm-uartdm.txt
@@ -0,0 +1,53 @@
+* MSM Serial UARTDM
+
+The MSM serial UARTDM hardware is designed for high-speed use cases where the
+transmit and/or receive channels can be offloaded to a dma-engine. From a
+software perspective it's mostly compatible with the MSM serial UART except
+that it supports reading and writing multiple characters at a time.
+
+Required properties:
+- compatible: Should contain at least "qcom,msm-uartdm".
+              A more specific property should be specified as follows depending
+	      on the version:
+		"qcom,msm-uartdm-v1.1"
+		"qcom,msm-uartdm-v1.2"
+		"qcom,msm-uartdm-v1.3"
+		"qcom,msm-uartdm-v1.4"
+- reg: Should contain UART register locations and lengths. The first
+       register shall specify the main control registers. An optional second
+       register location shall specify the GSBI control region.
+       "qcom,msm-uartdm-v1.3" is the only compatible value that might
+       need the GSBI control region.
+- interrupts: Should contain UART interrupt.
+- clocks: Should contain the core clock and the AHB clock.
+- clock-names: Should be "core" for the core clock and "iface" for the
+	       AHB clock.
+
+Optional properties:
+- dmas: Should contain dma specifiers for transmit and receive channels
+- dma-names: Should contain "tx" for transmit and "rx" for receive channels
+
+Examples:
+
+A uartdm v1.4 device with dma capabilities.
+
+serial@f991e000 {
+	compatible = "qcom,msm-uartdm-v1.4", "qcom,msm-uartdm";
+	reg = <0xf991e000 0x1000>;
+	interrupts = <0 108 0x0>;
+	clocks = <&blsp1_uart2_apps_cxc>, <&blsp1_ahb_cxc>;
+	clock-names = "core", "iface";
+	dmas = <&dma0 0>, <&dma0 1>;
+	dma-names = "tx", "rx";
+};
+
+A uartdm v1.3 device without dma capabilities and part of a GSBI complex.
+
+serial@19c40000 {
+	compatible = "qcom,msm-uartdm-v1.3", "qcom,msm-uartdm";
+	reg = <0x19c40000 0x1000>,
+	      <0x19c00000 0x1000>;
+	interrupts = <0 195 0x0>;
+	clocks = <&gsbi5_uart_cxc>, <&gsbi5_ahb_cxc>;
+	clock-names = "core", "iface";
+};
diff --git a/Documentation/devicetree/bindings/serial/rs485.txt b/Documentation/devicetree/bindings/serial/rs485.txt
index 1e753c69fc83..32b1fa1f2a5b 100644
--- a/Documentation/devicetree/bindings/serial/rs485.txt
+++ b/Documentation/devicetree/bindings/serial/rs485.txt
@@ -7,7 +7,7 @@ UART node.
 
 Required properties:
 - rs485-rts-delay: prop-encoded-array <a b> where:
-  * a is the delay beteween rts signal and beginning of data sent in milliseconds.
+  * a is the delay between rts signal and beginning of data sent in milliseconds.
       it corresponds to the delay before sending data.
   * b is the delay between end of data sent and rts signal in milliseconds
       it corresponds to the delay after sending data and actual release of the line.
diff --git a/Documentation/devicetree/bindings/serial/sirf-uart.txt b/Documentation/devicetree/bindings/serial/sirf-uart.txt
new file mode 100644
index 000000000000..a2dfc6522a91
--- /dev/null
+++ b/Documentation/devicetree/bindings/serial/sirf-uart.txt
@@ -0,0 +1,33 @@
+* CSR SiRFprimaII/atlasVI Universal Synchronous Asynchronous Receiver/Transmitter *
+
+Required properties:
+- compatible : Should be "sirf,prima2-uart" or "sirf, prima2-usp-uart"
+- reg : Offset and length of the register set for the device
+- interrupts : Should contain uart interrupt
+- fifosize : Should define hardware rx/tx fifo size
+- clocks : Should contain uart clock number
+
+Optional properties:
+- sirf,uart-has-rtscts: we have hardware flow controller pins in hardware
+- rts-gpios: RTS pin for USP-based UART if sirf,uart-has-rtscts is true
+- cts-gpios: CTS pin for USP-based UART if sirf,uart-has-rtscts is true
+
+Example:
+
+uart0: uart@b0050000 {
+	cell-index = <0>;
+	compatible = "sirf,prima2-uart";
+	reg = <0xb0050000 0x1000>;
+	interrupts = <17>;
+	fifosize = <128>;
+	clocks = <&clks 13>;
+};
+
+On the board-specific dts, we can put rts-gpios and cts-gpios like
+
+usp@b0090000 {
+	compatible = "sirf,prima2-usp-uart";
+	sirf,uart-has-rtscts;
+	rts-gpios = <&gpio 15 0>;
+	cts-gpios = <&gpio 46 0>;
+};
diff --git a/Documentation/devicetree/bindings/tty/serial/snps-dw-apb-uart.txt b/Documentation/devicetree/bindings/serial/snps-dw-apb-uart.txt
index f13f1c5be91c..f13f1c5be91c 100644
--- a/Documentation/devicetree/bindings/tty/serial/snps-dw-apb-uart.txt
+++ b/Documentation/devicetree/bindings/serial/snps-dw-apb-uart.txt
diff --git a/Documentation/devicetree/bindings/serial/st-asc.txt b/Documentation/devicetree/bindings/serial/st-asc.txt
new file mode 100644
index 000000000000..75d877f5968f
--- /dev/null
+++ b/Documentation/devicetree/bindings/serial/st-asc.txt
@@ -0,0 +1,18 @@
+*st-asc(Serial Port)
+
+Required properties:
+- compatible : Should be "st,asc".
+- reg, reg-names, interrupts, interrupt-names	: Standard way to define device
+			resources with names. look in
+			Documentation/devicetree/bindings/resource-names.txt
+
+Optional properties:
+- st,hw-flow-ctrl	bool flag to enable hardware flow control.
+- st,force-m1		bool flat to force asc to be in Mode-1 recommeded
+			for high bit rates (above 19.2K)
+Example:
+serial@fe440000{
+    compatible    = "st,asc";
+    reg         = <0xfe440000 0x2c>;
+    interrupts     =  <0 209 0>;
+};
diff --git a/Documentation/devicetree/bindings/tty/serial/via,vt8500-uart.txt b/Documentation/devicetree/bindings/serial/via,vt8500-uart.txt
index 5feef1ef167d..5feef1ef167d 100644
--- a/Documentation/devicetree/bindings/tty/serial/via,vt8500-uart.txt
+++ b/Documentation/devicetree/bindings/serial/via,vt8500-uart.txt
diff --git a/Documentation/devicetree/bindings/serio/altera_ps2.txt b/Documentation/devicetree/bindings/serio/altera_ps2.txt
index 4d9eecc2ef7d..520199e2e347 100644
--- a/Documentation/devicetree/bindings/serio/altera_ps2.txt
+++ b/Documentation/devicetree/bindings/serio/altera_ps2.txt
@@ -1,4 +1,5 @@
 Altera UP PS/2 controller
 
 Required properties:
-- compatible : should be "ALTR,ps2-1.0".
+- compatible : should be "ALTR,ps2-1.0". <DEPRECATED>
+- compatible : should be "altr,ps2-1.0".
diff --git a/Documentation/devicetree/bindings/sound/ak4554.c b/Documentation/devicetree/bindings/sound/ak4554.c
new file mode 100644
index 000000000000..934fa02754b3
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/ak4554.c
@@ -0,0 +1,11 @@
+AK4554 ADC/DAC
+
+Required properties:
+
+  - compatible : "asahi-kasei,ak4554"
+
+Example:
+
+ak4554-adc-dac {
+	compatible = "asahi-kasei,ak4554";
+};
diff --git a/Documentation/devicetree/bindings/sound/alc5632.txt b/Documentation/devicetree/bindings/sound/alc5632.txt
index 8608f747dcfe..ffd886d110bd 100644
--- a/Documentation/devicetree/bindings/sound/alc5632.txt
+++ b/Documentation/devicetree/bindings/sound/alc5632.txt
@@ -13,6 +13,25 @@ Required properties:
   - #gpio-cells : Should be two. The first cell is the pin number and the
     second cell is used to specify optional parameters (currently unused).
 
+Pins on the device (for linking into audio routes):
+
+  * SPK_OUTP
+  * SPK_OUTN
+  * HP_OUT_L
+  * HP_OUT_R
+  * AUX_OUT_P
+  * AUX_OUT_N
+  * LINE_IN_L
+  * LINE_IN_R
+  * PHONE_P
+  * PHONE_N
+  * MIC1_P
+  * MIC1_N
+  * MIC2_P
+  * MIC2_N
+  * MICBIAS1
+  * DMICDAT
+
 Example:
 
 alc5632: alc5632@1e {
diff --git a/Documentation/devicetree/bindings/sound/atmel-sam9x5-wm8731-audio.txt b/Documentation/devicetree/bindings/sound/atmel-sam9x5-wm8731-audio.txt
new file mode 100644
index 000000000000..0720857089a7
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/atmel-sam9x5-wm8731-audio.txt
@@ -0,0 +1,35 @@
+* Atmel at91sam9x5ek wm8731 audio complex
+
+Required properties:
+  - compatible: "atmel,sam9x5-wm8731-audio"
+  - atmel,model: The user-visible name of this sound complex.
+  - atmel,ssc-controller: The phandle of the SSC controller
+  - atmel,audio-codec: The phandle of the WM8731 audio codec
+  - atmel,audio-routing: A list of the connections between audio components.
+    Each entry is a pair of strings, the first being the connection's sink,
+    the second being the connection's source.
+
+Available audio endpoints for the audio-routing table:
+
+Board connectors:
+ * Headphone Jack
+ * Line In Jack
+
+wm8731 pins:
+cf Documentation/devicetree/bindings/sound/wm8731.txt
+
+Example:
+sound {
+	compatible = "atmel,sam9x5-wm8731-audio";
+
+	atmel,model = "wm8731 @ AT91SAM9X5EK";
+
+	atmel,audio-routing =
+		"Headphone Jack", "RHPOUT",
+		"Headphone Jack", "LHPOUT",
+		"LLINEIN", "Line In Jack",
+		"RLINEIN", "Line In Jack";
+
+	atmel,ssc-controller = <&ssc0>;
+	atmel,audio-codec = <&wm8731>;
+};
diff --git a/Documentation/devicetree/bindings/sound/atmel-wm8904.txt b/Documentation/devicetree/bindings/sound/atmel-wm8904.txt
new file mode 100644
index 000000000000..8bbe50c884b6
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/atmel-wm8904.txt
@@ -0,0 +1,55 @@
+Atmel ASoC driver with wm8904 audio codec complex
+
+Required properties:
+  - compatible: "atmel,asoc-wm8904"
+  - atmel,model: The user-visible name of this sound complex.
+  - atmel,audio-routing: A list of the connections between audio components.
+    Each entry is a pair of strings, the first being the connection's sink,
+    the second being the connection's source. Valid names for sources and
+    sinks are the WM8904's pins, and the jacks on the board:
+
+    WM8904 pins:
+
+    * IN1L
+    * IN1R
+    * IN2L
+    * IN2R
+    * IN3L
+    * IN3R
+    * HPOUTL
+    * HPOUTR
+    * LINEOUTL
+    * LINEOUTR
+    * MICBIAS
+
+    Board connectors:
+
+    * Headphone Jack
+    * Line In Jack
+    * Mic
+
+  - atmel,ssc-controller: The phandle of the SSC controller
+  - atmel,audio-codec: The phandle of the WM8904 audio codec
+
+Optional properties:
+  - pinctrl-names, pinctrl-0: Please refer to pinctrl-bindings.txt
+
+Example:
+sound {
+	compatible = "atmel,asoc-wm8904";
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_pck0_as_mck>;
+
+	atmel,model = "wm8904 @ AT91SAM9N12EK";
+
+	atmel,audio-routing =
+		"Headphone Jack", "HPOUTL",
+		"Headphone Jack", "HPOUTR",
+		"IN2L", "Line In Jack",
+		"IN2R", "Line In Jack",
+		"Mic", "MICBIAS",
+		"IN1L", "Mic";
+
+	atmel,ssc-controller = <&ssc0>;
+	atmel,audio-codec = <&wm8904>;
+};
diff --git a/Documentation/devicetree/bindings/sound/fsl,spdif.txt b/Documentation/devicetree/bindings/sound/fsl,spdif.txt
new file mode 100644
index 000000000000..f2ae335670f5
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/fsl,spdif.txt
@@ -0,0 +1,54 @@
+Freescale Sony/Philips Digital Interface Format (S/PDIF) Controller
+
+The Freescale S/PDIF audio block is a stereo transceiver that allows the
+processor to receive and transmit digital audio via an coaxial cable or
+a fibre cable.
+
+Required properties:
+
+  - compatible : Compatible list, must contain "fsl,imx35-spdif".
+
+  - reg : Offset and length of the register set for the device.
+
+  - interrupts : Contains the spdif interrupt.
+
+  - dmas : Generic dma devicetree binding as described in
+  Documentation/devicetree/bindings/dma/dma.txt.
+
+  - dma-names : Two dmas have to be defined, "tx" and "rx".
+
+  - clocks : Contains an entry for each entry in clock-names.
+
+  - clock-names : Includes the following entries:
+	"core"		The core clock of spdif controller
+	"rxtx<0-7>"	Clock source list for tx and rx clock.
+			This clock list should be identical to
+			the source list connecting to the spdif
+			clock mux in "SPDIF Transceiver Clock
+			Diagram" of SoC reference manual. It
+			can also be referred to TxClk_Source
+			bit of register SPDIF_STC.
+
+Example:
+
+spdif: spdif@02004000 {
+	compatible = "fsl,imx35-spdif";
+	reg = <0x02004000 0x4000>;
+	interrupts = <0 52 0x04>;
+	dmas = <&sdma 14 18 0>,
+	       <&sdma 15 18 0>;
+	dma-names = "rx", "tx";
+
+	clocks = <&clks 197>, <&clks 3>,
+	       <&clks 197>, <&clks 107>,
+	       <&clks 0>, <&clks 118>,
+	       <&clks 62>, <&clks 139>,
+	       <&clks 0>;
+	clock-names = "core", "rxtx0",
+		"rxtx1", "rxtx2",
+		"rxtx3", "rxtx4",
+		"rxtx5", "rxtx6",
+		"rxtx7";
+
+	status = "okay";
+};
diff --git a/Documentation/devicetree/bindings/powerpc/fsl/ssi.txt b/Documentation/devicetree/bindings/sound/fsl,ssi.txt
index 5ff76c9c57d2..4303b6ab6208 100644
--- a/Documentation/devicetree/bindings/powerpc/fsl/ssi.txt
+++ b/Documentation/devicetree/bindings/sound/fsl,ssi.txt
@@ -43,10 +43,22 @@ Required properties:
                     together.  This would still allow different sample sizes,
                     but not different sample rates.
 
+Required are also ac97 link bindings if ac97 is used. See
+Documentation/devicetree/bindings/sound/soc-ac97link.txt for the necessary
+bindings.
+
 Optional properties:
 - codec-handle:     Phandle to a 'codec' node that defines an audio
                     codec connected to this SSI.  This node is typically
                     a child of an I2C or other control node.
+- fsl,fiq-stream-filter: Bool property. Disabled DMA and use FIQ instead to
+		    filter the codec stream. This is necessary for some boards
+		    where an incompatible codec is connected to this SSI, e.g.
+		    on pca100 and pcm043.
+- dmas:		    Generic dma devicetree binding as described in
+		    Documentation/devicetree/bindings/dma/dma.txt.
+- dma-names:	    Two dmas have to be defined, "tx" and "rx", if fsl,imx-fiq
+		    is not defined.
 
 Child 'codec' node required properties:
 - compatible:       Compatible list, contains the name of the codec
diff --git a/Documentation/devicetree/bindings/sound/imx-audio-spdif.txt b/Documentation/devicetree/bindings/sound/imx-audio-spdif.txt
new file mode 100644
index 000000000000..7d13479f9c3c
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/imx-audio-spdif.txt
@@ -0,0 +1,34 @@
+Freescale i.MX audio complex with S/PDIF transceiver
+
+Required properties:
+
+  - compatible : "fsl,imx-audio-spdif"
+
+  - model : The user-visible name of this sound complex
+
+  - spdif-controller : The phandle of the i.MX S/PDIF controller
+
+
+Optional properties:
+
+  - spdif-out : This is a boolean property. If present, the transmitting
+    function of S/PDIF will be enabled, indicating there's a physical
+    S/PDIF out connector/jack on the board or it's connecting to some
+    other IP block, such as an HDMI encoder/display-controller.
+
+  - spdif-in : This is a boolean property. If present, the receiving
+    function of S/PDIF will be enabled, indicating there's a physical
+    S/PDIF in connector/jack on the board.
+
+* Note: At least one of these two properties should be set in the DT binding.
+
+
+Example:
+
+sound-spdif {
+	compatible = "fsl,imx-audio-spdif";
+	model = "imx-spdif";
+	spdif-controller = <&spdif>;
+	spdif-out;
+	spdif-in;
+};
diff --git a/Documentation/devicetree/bindings/sound/imx-audmux.txt b/Documentation/devicetree/bindings/sound/imx-audmux.txt
index 215aa9817213..f88a00e54c63 100644
--- a/Documentation/devicetree/bindings/sound/imx-audmux.txt
+++ b/Documentation/devicetree/bindings/sound/imx-audmux.txt
@@ -5,6 +5,15 @@ Required properties:
   or "fsl,imx31-audmux" for the version firstly used on i.MX31.
 - reg : Should contain AUDMUX registers location and length
 
+An initial configuration can be setup using child nodes.
+
+Required properties of optional child nodes:
+- fsl,audmux-port : Integer of the audmux port that is configured by this
+  child node.
+- fsl,port-config : List of configuration options for the specific port. For
+  imx31-audmux and above, it is a list of tuples <ptcr pdcr>. For
+  imx21-audmux it is a list of pcr values.
+
 Example:
 
 audmux@021d8000 {
diff --git a/Documentation/devicetree/bindings/sound/mrvl,pxa-ssp.txt b/Documentation/devicetree/bindings/sound/mrvl,pxa-ssp.txt
new file mode 100644
index 000000000000..74c9ba6c2823
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/mrvl,pxa-ssp.txt
@@ -0,0 +1,28 @@
+Marvell PXA SSP CPU DAI bindings
+
+Required properties:
+
+	compatible	Must be "mrvl,pxa-ssp-dai"
+	port		A phandle reference to a PXA ssp upstream device
+
+Example:
+
+	/* upstream device */
+
+	ssp0: ssp@41000000 {
+		compatible = "mrvl,pxa3xx-ssp";
+		reg = <0x41000000 0x40>;
+		interrupts = <24>;
+		clock-names = "pxa27x-ssp.0";
+		dmas = <&dma 13
+			&dma 14>;
+		dma-names = "rx", "tx";
+	};
+
+	/* DAI as user */
+
+	ssp_dai0: ssp_dai@0 {
+		compatible = "mrvl,pxa-ssp-dai";
+		port = <&ssp0>;
+	};
+
diff --git a/Documentation/devicetree/bindings/sound/mrvl,pxa2xx-pcm.txt b/Documentation/devicetree/bindings/sound/mrvl,pxa2xx-pcm.txt
new file mode 100644
index 000000000000..551fbb8348c2
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/mrvl,pxa2xx-pcm.txt
@@ -0,0 +1,15 @@
+DT bindings for ARM PXA2xx PCM platform driver
+
+This is just a dummy driver that registers the PXA ASoC platform driver.
+It does not have any resources assigned.
+
+Required properties:
+
+	- compatible		'mrvl,pxa-pcm-audio'
+
+Example:
+
+	pxa_pcm_audio: snd_soc_pxa_audio {
+		compatible = "mrvl,pxa-pcm-audio";
+	};
+
diff --git a/Documentation/devicetree/bindings/sound/mvebu-audio.txt b/Documentation/devicetree/bindings/sound/mvebu-audio.txt
new file mode 100644
index 000000000000..f0062c5871b4
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/mvebu-audio.txt
@@ -0,0 +1,33 @@
+* mvebu (Kirkwood, Dove, Armada 370) audio controller
+
+Required properties:
+
+- compatible:
+  "marvell,kirkwood-audio" for Kirkwood platforms
+  "marvell,dove-audio" for Dove platforms
+
+- reg: physical base address of the controller and length of memory mapped
+  region.
+
+- interrupts:
+  with "marvell,kirkwood-audio", the audio interrupt
+  with "marvell,dove-audio", a list of two interrupts, the first for
+  the data flow, and the second for errors.
+
+- clocks: one or two phandles.
+  The first one is mandatory and defines the internal clock.
+  The second one is optional and defines an external clock.
+
+- clock-names: names associated to the clocks:
+	"internal" for the internal clock
+	"extclk" for the external clock
+
+Example:
+
+i2s1: audio-controller@b4000 {
+	compatible = "marvell,dove-audio";
+	reg = <0xb4000 0x2210>;
+	interrupts = <21>, <22>;
+	clocks = <&gate_clk 13>;
+	clock-names = "internal";
+};
diff --git a/Documentation/devicetree/bindings/sound/nvidia,tegra-audio-alc5632.txt b/Documentation/devicetree/bindings/sound/nvidia,tegra-audio-alc5632.txt
index 05ffecb57103..8b8903ef0800 100644
--- a/Documentation/devicetree/bindings/sound/nvidia,tegra-audio-alc5632.txt
+++ b/Documentation/devicetree/bindings/sound/nvidia,tegra-audio-alc5632.txt
@@ -11,28 +11,8 @@ Required properties:
 - nvidia,audio-routing : A list of the connections between audio components.
   Each entry is a pair of strings, the first being the connection's sink,
   the second being the connection's source. Valid names for sources and
-  sinks are the ALC5632's pins:
-
-  ALC5632 pins:
-
-  * SPK_OUTP
-  * SPK_OUTN
-  * HP_OUT_L
-  * HP_OUT_R
-  * AUX_OUT_P
-  * AUX_OUT_N
-  * LINE_IN_L
-  * LINE_IN_R
-  * PHONE_P
-  * PHONE_N
-  * MIC1_P
-  * MIC1_N
-  * MIC2_P
-  * MIC2_N
-  * MICBIAS1
-  * DMICDAT
-
-  Board connectors:
+  sinks are the ALC5632's pins as documented in the binding for the device
+  and:
 
   * Headset Stereophone
   * Int Spk
diff --git a/Documentation/devicetree/bindings/sound/nvidia,tegra-audio-rt5640.txt b/Documentation/devicetree/bindings/sound/nvidia,tegra-audio-rt5640.txt
index d130818700b2..dc6224994d69 100644
--- a/Documentation/devicetree/bindings/sound/nvidia,tegra-audio-rt5640.txt
+++ b/Documentation/devicetree/bindings/sound/nvidia,tegra-audio-rt5640.txt
@@ -11,32 +11,12 @@ Required properties:
 - nvidia,audio-routing : A list of the connections between audio components.
   Each entry is a pair of strings, the first being the connection's sink,
   the second being the connection's source. Valid names for sources and
-  sinks are the RT5640's pins, and the jacks on the board:
-
-  RT5640 pins:
-
-  * DMIC1
-  * DMIC2
-  * MICBIAS1
-  * IN1P
-  * IN1R
-  * IN2P
-  * IN2R
-  * HPOL
-  * HPOR
-  * LOUTL
-  * LOUTR
-  * MONOP
-  * MONON
-  * SPOLP
-  * SPOLN
-  * SPORP
-  * SPORN
-
-  Board connectors:
+  sinks are the RT5640's pins (as documented in its binding), and the jacks
+  on the board:
 
   * Headphones
   * Speakers
+  * Mic Jack
 
 - nvidia,i2s-controller : The phandle of the Tegra I2S controller that's
   connected to the CODEC.
diff --git a/Documentation/devicetree/bindings/sound/nvidia,tegra-audio-wm8753.txt b/Documentation/devicetree/bindings/sound/nvidia,tegra-audio-wm8753.txt
index d14510613a7f..aab6ce0ad2fc 100644
--- a/Documentation/devicetree/bindings/sound/nvidia,tegra-audio-wm8753.txt
+++ b/Documentation/devicetree/bindings/sound/nvidia,tegra-audio-wm8753.txt
@@ -11,31 +11,8 @@ Required properties:
 - nvidia,audio-routing : A list of the connections between audio components.
   Each entry is a pair of strings, the first being the connection's sink,
   the second being the connection's source. Valid names for sources and
-  sinks are the WM8753's pins, and the jacks on the board:
-
-  WM8753 pins:
-
-  * LOUT1
-  * LOUT2
-  * ROUT1
-  * ROUT2
-  * MONO1
-  * MONO2
-  * OUT3
-  * OUT4
-  * LINE1
-  * LINE2
-  * RXP
-  * RXN
-  * ACIN
-  * ACOP
-  * MIC1N
-  * MIC1
-  * MIC2N
-  * MIC2
-  * Mic Bias
-
-  Board connectors:
+  sinks are the WM8753's pins as documented in the binding for the WM8753,
+  and the jacks on the board:
 
   * Headphone Jack
   * Mic Jack
diff --git a/Documentation/devicetree/bindings/sound/nvidia,tegra-audio-wm8903.txt b/Documentation/devicetree/bindings/sound/nvidia,tegra-audio-wm8903.txt
index 3bf722deb722..4b44dfb6ca0d 100644
--- a/Documentation/devicetree/bindings/sound/nvidia,tegra-audio-wm8903.txt
+++ b/Documentation/devicetree/bindings/sound/nvidia,tegra-audio-wm8903.txt
@@ -11,28 +11,8 @@ Required properties:
 - nvidia,audio-routing : A list of the connections between audio components.
   Each entry is a pair of strings, the first being the connection's sink,
   the second being the connection's source. Valid names for sources and
-  sinks are the WM8903's pins, and the jacks on the board:
-
-  WM8903 pins:
-
-  * IN1L
-  * IN1R
-  * IN2L
-  * IN2R
-  * IN3L
-  * IN3R
-  * DMICDAT
-  * HPOUTL
-  * HPOUTR
-  * LINEOUTL
-  * LINEOUTR
-  * LOP
-  * LON
-  * ROP
-  * RON
-  * MICBIAS
-
-  Board connectors:
+  sinks are the WM8903's pins (documented in the WM8903 binding document),
+  and the jacks on the board:
 
   * Headphone Jack
   * Int Spk
diff --git a/Documentation/devicetree/bindings/sound/pcm1792a.txt b/Documentation/devicetree/bindings/sound/pcm1792a.txt
new file mode 100644
index 000000000000..970ba1ed576f
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/pcm1792a.txt
@@ -0,0 +1,18 @@
+Texas Instruments pcm1792a DT bindings
+
+This driver supports the SPI bus.
+
+Required properties:
+
+ - compatible: "ti,pcm1792a"
+
+For required properties on SPI, please consult
+Documentation/devicetree/bindings/spi/spi-bus.txt
+
+Examples:
+
+	codec_spi: 1792a@0 {
+		compatible = "ti,pcm1792a";
+		spi-max-frequency = <600000>;
+	};
+
diff --git a/Documentation/devicetree/bindings/sound/rt5640.txt b/Documentation/devicetree/bindings/sound/rt5640.txt
index 005bcb24d72d..068a1141b06f 100644
--- a/Documentation/devicetree/bindings/sound/rt5640.txt
+++ b/Documentation/devicetree/bindings/sound/rt5640.txt
@@ -18,6 +18,26 @@ Optional properties:
 
 - realtek,ldo1-en-gpios : The GPIO that controls the CODEC's LDO1_EN pin.
 
+Pins on the device (for linking into audio routes):
+
+  * DMIC1
+  * DMIC2
+  * MICBIAS1
+  * IN1P
+  * IN1R
+  * IN2P
+  * IN2R
+  * HPOL
+  * HPOR
+  * LOUTL
+  * LOUTR
+  * MONOP
+  * MONON
+  * SPOLP
+  * SPOLN
+  * SPORP
+  * SPORN
+
 Example:
 
 rt5640 {
diff --git a/Documentation/devicetree/bindings/sound/samsung-i2s.txt b/Documentation/devicetree/bindings/sound/samsung-i2s.txt
index 025e66b85a43..7386d444ada1 100644
--- a/Documentation/devicetree/bindings/sound/samsung-i2s.txt
+++ b/Documentation/devicetree/bindings/sound/samsung-i2s.txt
@@ -2,7 +2,15 @@
 
 Required SoC Specific Properties:
 
-- compatible : "samsung,i2s-v5"
+- compatible : should be one of the following.
+   - samsung,s3c6410-i2s: for 8/16/24bit stereo I2S.
+   - samsung,s5pv210-i2s: for 8/16/24bit multichannel(5.1) I2S with
+     secondary fifo, s/w reset control and internal mux for root clk src.
+   - samsung,exynos5420-i2s: for 8/16/24bit multichannel(7.1) I2S with
+     secondary fifo, s/w reset control, internal mux for root clk src and
+     TDM support. TDM (Time division multiplexing) is to allow transfer of
+     multiple channel audio data on single data line.
+
 - reg: physical base address of the controller and length of memory mapped
   region.
 - dmas: list of DMA controller phandle and DMA request line ordered pairs.
@@ -21,13 +29,6 @@ Required SoC Specific Properties:
 
 Optional SoC Specific Properties:
 
-- samsung,supports-6ch: If the I2S Primary sound source has 5.1 Channel
-  support, this flag is enabled.
-- samsung,supports-rstclr: This flag should be set if I2S software reset bit
-  control is required. When this flag is set I2S software reset bit will be
-  enabled or disabled based on need.
-- samsung,supports-secdai:If I2S block has a secondary FIFO and internal DMA,
-  then this flag is enabled.
 - samsung,idma-addr: Internal DMA register base address of the audio
   sub system(used in secondary sound source).
 - pinctrl-0: Should specify pin control groups used for this controller.
@@ -36,7 +37,7 @@ Optional SoC Specific Properties:
 Example:
 
 i2s0: i2s@03830000 {
-	compatible = "samsung,i2s-v5";
+	compatible = "samsung,s5pv210-i2s";
 	reg = <0x03830000 0x100>;
 	dmas = <&pdma0 10
 		&pdma0 9
@@ -46,9 +47,6 @@ i2s0: i2s@03830000 {
 		<&clock_audss EXYNOS_I2S_BUS>,
 		<&clock_audss EXYNOS_SCLK_I2S>;
 	clock-names = "iis", "i2s_opclk0", "i2s_opclk1";
-	samsung,supports-6ch;
-	samsung,supports-rstclr;
-	samsung,supports-secdai;
 	samsung,idma-addr = <0x03000000>;
 	pinctrl-names = "default";
 	pinctrl-0 = <&i2s0_bus>;
diff --git a/Documentation/devicetree/bindings/sound/soc-ac97link.txt b/Documentation/devicetree/bindings/sound/soc-ac97link.txt
new file mode 100644
index 000000000000..80152a87f239
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/soc-ac97link.txt
@@ -0,0 +1,28 @@
+AC97 link bindings
+
+These bindings can be included within any other device node.
+
+Required properties:
+ - pinctrl-names: Has to contain following states to setup the correct
+   pinmuxing for the used gpios:
+	"ac97-running": AC97-link is active
+	"ac97-reset": AC97-link reset state
+	"ac97-warm-reset": AC97-link warm reset state
+ - ac97-gpios: List of gpio phandles with args in the order ac97-sync,
+   ac97-sdata, ac97-reset
+
+
+Example:
+
+ssi {
+	...
+
+	pinctrl-names = "default", "ac97-running", "ac97-reset", "ac97-warm-reset";
+	pinctrl-0 = <&ac97link_running>;
+	pinctrl-1 = <&ac97link_running>;
+	pinctrl-2 = <&ac97link_reset>;
+	pinctrl-3 = <&ac97link_warm_reset>;
+	ac97-gpios = <&gpio3 20 0 &gpio3 22 0 &gpio3 28 0>;
+
+	...
+};
diff --git a/Documentation/devicetree/bindings/sound/ti,pcm1681.txt b/Documentation/devicetree/bindings/sound/ti,pcm1681.txt
new file mode 100644
index 000000000000..4df17185ab80
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/ti,pcm1681.txt
@@ -0,0 +1,15 @@
+Texas Instruments PCM1681 8-channel PWM Processor
+
+Required properties:
+
+ - compatible:		Should contain "ti,pcm1681".
+ - reg:			The i2c address. Should contain <0x4c>.
+
+Examples:
+
+	i2c_bus {
+		pcm1681@4c {
+			compatible = "ti,pcm1681";
+			reg = <0x4c>;
+		};
+	};
diff --git a/Documentation/devicetree/bindings/sound/tlv320aic3x.txt b/Documentation/devicetree/bindings/sound/tlv320aic3x.txt
index f47c3f589fd0..705a6b156c6c 100644
--- a/Documentation/devicetree/bindings/sound/tlv320aic3x.txt
+++ b/Documentation/devicetree/bindings/sound/tlv320aic3x.txt
@@ -3,7 +3,14 @@ Texas Instruments - tlv320aic3x Codec module
 The tlv320aic3x serial control bus communicates through I2C protocols
 
 Required properties:
-- compatible - "string" -  "ti,tlv320aic3x"
+
+- compatible - "string" - One of:
+    "ti,tlv320aic3x" - Generic TLV320AIC3x device
+    "ti,tlv320aic33" - TLV320AIC33
+    "ti,tlv320aic3007" - TLV320AIC3007
+    "ti,tlv320aic3106" - TLV320AIC3106
+
+
 - reg - <int> -  I2C slave address
 
 
diff --git a/Documentation/devicetree/bindings/sound/wm8731.txt b/Documentation/devicetree/bindings/sound/wm8731.txt
index 15f70048469b..236690e99b87 100644
--- a/Documentation/devicetree/bindings/sound/wm8731.txt
+++ b/Documentation/devicetree/bindings/sound/wm8731.txt
@@ -16,3 +16,12 @@ codec: wm8731@1a {
 	compatible = "wlf,wm8731";
 	reg = <0x1a>;
 };
+
+Available audio endpoints for an audio-routing table:
+ * LOUT: Left Channel Line Output
+ * ROUT: Right Channel Line Output
+ * LHPOUT: Left Channel Headphone Output
+ * RHPOUT: Right Channel Headphone Output
+ * LLINEIN: Left Channel Line Input
+ * RLINEIN: Right Channel Line Input
+ * MICIN: Microphone Input
diff --git a/Documentation/devicetree/bindings/sound/wm8753.txt b/Documentation/devicetree/bindings/sound/wm8753.txt
index e65277a0fb60..8eee61282105 100644
--- a/Documentation/devicetree/bindings/sound/wm8753.txt
+++ b/Documentation/devicetree/bindings/sound/wm8753.txt
@@ -10,9 +10,31 @@ Required properties:
   - reg : the I2C address of the device for I2C, the chip select
           number for SPI.
 
+Pins on the device (for linking into audio routes):
+
+  * LOUT1
+  * LOUT2
+  * ROUT1
+  * ROUT2
+  * MONO1
+  * MONO2
+  * OUT3
+  * OUT4
+  * LINE1
+  * LINE2
+  * RXP
+  * RXN
+  * ACIN
+  * ACOP
+  * MIC1N
+  * MIC1
+  * MIC2N
+  * MIC2
+  * Mic Bias
+
 Example:
 
-codec: wm8737@1a {
+codec: wm8753@1a {
 	compatible = "wlf,wm8753";
 	reg = <0x1a>;
 };
diff --git a/Documentation/devicetree/bindings/sound/wm8903.txt b/Documentation/devicetree/bindings/sound/wm8903.txt
index f102cbc42694..94ec32c194bb 100644
--- a/Documentation/devicetree/bindings/sound/wm8903.txt
+++ b/Documentation/devicetree/bindings/sound/wm8903.txt
@@ -28,6 +28,25 @@ Optional properties:
     performed. If any entry has the value 0xffffffff, that GPIO's
     configuration will not be modified.
 
+Pins on the device (for linking into audio routes):
+
+  * IN1L
+  * IN1R
+  * IN2L
+  * IN2R
+  * IN3L
+  * IN3R
+  * DMICDAT
+  * HPOUTL
+  * HPOUTR
+  * LINEOUTL
+  * LINEOUTR
+  * LOP
+  * LON
+  * ROP
+  * RON
+  * MICBIAS
+
 Example:
 
 codec: wm8903@1a {
diff --git a/Documentation/devicetree/bindings/sound/wm8994.txt b/Documentation/devicetree/bindings/sound/wm8994.txt
index f2f3e80934d2..e045e90a0924 100644
--- a/Documentation/devicetree/bindings/sound/wm8994.txt
+++ b/Documentation/devicetree/bindings/sound/wm8994.txt
@@ -32,6 +32,10 @@ Optional properties:
     The second cell is the flags, encoded as the trigger masks from
     Documentation/devicetree/bindings/interrupts.txt
 
+  - clocks : A list of up to two phandle and clock specifier pairs
+  - clock-names : A list of clock names sorted in the same order as clocks.
+                  Valid clock names are "MCLK1" and "MCLK2".
+
   - wlf,gpio-cfg : A list of GPIO configuration register values. If absent,
     no configuration of these registers is performed. If any value is
     over 0xffff then the register will be left as default. If present 11
diff --git a/Documentation/devicetree/bindings/spi/efm32-spi.txt b/Documentation/devicetree/bindings/spi/efm32-spi.txt
new file mode 100644
index 000000000000..a590ca51be75
--- /dev/null
+++ b/Documentation/devicetree/bindings/spi/efm32-spi.txt
@@ -0,0 +1,34 @@
+* Energy Micro EFM32 SPI
+
+Required properties:
+- #address-cells: see spi-bus.txt
+- #size-cells: see spi-bus.txt
+- compatible: should be "efm32,spi"
+- reg: Offset and length of the register set for the controller
+- interrupts: pair specifying rx and tx irq
+- clocks: phandle to the spi clock
+- cs-gpios: see spi-bus.txt
+- location: Value to write to the ROUTE register's LOCATION bitfield to configure the pinmux for the device, see datasheet for values.
+
+Example:
+
+spi1: spi@0x4000c400 { /* USART1 */
+	#address-cells = <1>;
+	#size-cells = <0>;
+	compatible = "efm32,spi";
+	reg = <0x4000c400 0x400>;
+	interrupts = <15 16>;
+	clocks = <&cmu 20>;
+	cs-gpios = <&gpio 51 1>; // D3
+	location = <1>;
+	status = "ok";
+
+	ks8851@0 {
+		compatible = "ks8851";
+		spi-max-frequency = <6000000>;
+		reg = <0>;
+		interrupt-parent = <&boardfpga>;
+		interrupts = <4>;
+		status = "ok";
+	};
+};
diff --git a/Documentation/devicetree/bindings/spi/spi-bus.txt b/Documentation/devicetree/bindings/spi/spi-bus.txt
index 296015e3c632..800dafe5b01b 100644
--- a/Documentation/devicetree/bindings/spi/spi-bus.txt
+++ b/Documentation/devicetree/bindings/spi/spi-bus.txt
@@ -55,6 +55,16 @@ contain the following properties.
     		chip select active high
 - spi-3wire       - (optional) Empty property indicating device requires
     		    3-wire mode.
+- spi-tx-bus-width - (optional) The bus width(number of data wires) that
+                      used for MOSI. Defaults to 1 if not present.
+- spi-rx-bus-width - (optional) The bus width(number of data wires) that
+                      used for MISO. Defaults to 1 if not present.
+
+Some SPI controllers and devices support Dual and Quad SPI transfer mode.
+It allows data in SPI system transfered in 2 wires(DUAL) or 4 wires(QUAD).
+Now the value that spi-tx-bus-width and spi-rx-bus-width can receive is
+only 1(SINGLE), 2(DUAL) and 4(QUAD).
+Dual/Quad mode is not allowed when 3-wire mode is used.
 
 If a gpio chipselect is used for the SPI slave the gpio number will be passed
 via the cs_gpio
diff --git a/Documentation/devicetree/bindings/spi/spi-fsl-dspi.txt b/Documentation/devicetree/bindings/spi/spi-fsl-dspi.txt
new file mode 100644
index 000000000000..a1fb3035a42b
--- /dev/null
+++ b/Documentation/devicetree/bindings/spi/spi-fsl-dspi.txt
@@ -0,0 +1,42 @@
+ARM Freescale DSPI controller
+
+Required properties:
+- compatible : "fsl,vf610-dspi"
+- reg : Offset and length of the register set for the device
+- interrupts : Should contain SPI controller interrupt
+- clocks: from common clock binding: handle to dspi clock.
+- clock-names: from common clock binding: Shall be "dspi".
+- pinctrl-0: pin control group to be used for this controller.
+- pinctrl-names: must contain a "default" entry.
+- spi-num-chipselects : the number of the chipselect signals.
+- bus-num : the slave chip chipselect signal number.
+Example:
+
+dspi0@4002c000 {
+	#address-cells = <1>;
+	#size-cells = <0>;
+	compatible = "fsl,vf610-dspi";
+	reg = <0x4002c000 0x1000>;
+	interrupts = <0 67 0x04>;
+	clocks = <&clks VF610_CLK_DSPI0>;
+	clock-names = "dspi";
+	spi-num-chipselects = <5>;
+	bus-num = <0>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_dspi0_1>;
+	status = "okay";
+
+	sflash: at26df081a@0 {
+		#address-cells = <1>;
+		#size-cells = <1>;
+		compatible = "atmel,at26df081a";
+		spi-max-frequency = <16000000>;
+		spi-cpol;
+		spi-cpha;
+		reg = <0>;
+		linux,modalias = "m25p80";
+		modal = "at26df081a";
+	};
+};
+
+
diff --git a/Documentation/devicetree/bindings/spi/spi_altera.txt b/Documentation/devicetree/bindings/spi/spi_altera.txt
index dda375943506..31319dcf30ab 100644
--- a/Documentation/devicetree/bindings/spi/spi_altera.txt
+++ b/Documentation/devicetree/bindings/spi/spi_altera.txt
@@ -1,4 +1,5 @@
 Altera SPI
 
 Required properties:
-- compatible : should be "ALTR,spi-1.0".
+- compatible : should be "ALTR,spi-1.0". <DEPRECATED>
+- compatible : should be "altr,spi-1.0".
diff --git a/Documentation/devicetree/bindings/spi/ti_qspi.txt b/Documentation/devicetree/bindings/spi/ti_qspi.txt
new file mode 100644
index 000000000000..1f9641ade0b5
--- /dev/null
+++ b/Documentation/devicetree/bindings/spi/ti_qspi.txt
@@ -0,0 +1,22 @@
+TI QSPI controller.
+
+Required properties:
+- compatible : should be "ti,dra7xxx-qspi" or "ti,am4372-qspi".
+- reg: Should contain QSPI registers location and length.
+- #address-cells, #size-cells : Must be present if the device has sub-nodes
+- ti,hwmods: Name of the hwmod associated to the QSPI
+
+Recommended properties:
+- spi-max-frequency: Definition as per
+                     Documentation/devicetree/bindings/spi/spi-bus.txt
+
+Example:
+
+qspi: qspi@4b300000 {
+	compatible = "ti,dra7xxx-qspi";
+	reg = <0x4b300000 0x100>;
+	#address-cells = <1>;
+	#size-cells = <0>;
+	spi-max-frequency = <25000000>;
+	ti,hwmods = "qspi";
+};
diff --git a/Documentation/devicetree/bindings/thermal/exynos-thermal.txt b/Documentation/devicetree/bindings/thermal/exynos-thermal.txt
new file mode 100644
index 000000000000..284f5300fd8b
--- /dev/null
+++ b/Documentation/devicetree/bindings/thermal/exynos-thermal.txt
@@ -0,0 +1,55 @@
+* Exynos Thermal Management Unit (TMU)
+
+** Required properties:
+
+- compatible : One of the following:
+	       "samsung,exynos4412-tmu"
+	       "samsung,exynos4210-tmu"
+	       "samsung,exynos5250-tmu"
+	       "samsung,exynos5440-tmu"
+- interrupt-parent : The phandle for the interrupt controller
+- reg : Address range of the thermal registers. For soc's which has multiple
+	instances of TMU and some registers are shared across all TMU's like
+	interrupt related then 2 set of register has to supplied. First set
+	belongs	to each instance of TMU and second set belongs to common TMU
+	registers.
+- interrupts : Should contain interrupt for thermal system
+- clocks : The main clock for TMU device
+- clock-names : Thermal system clock name
+- vtmu-supply: This entry is optional and provides the regulator node supplying
+		voltage to TMU. If needed this entry can be placed inside
+		board/platform specific dts file.
+
+Example 1):
+
+	tmu@100C0000 {
+		compatible = "samsung,exynos4412-tmu";
+		interrupt-parent = <&combiner>;
+		reg = <0x100C0000 0x100>;
+		interrupts = <2 4>;
+		clocks = <&clock 383>;
+		clock-names = "tmu_apbif";
+		status = "disabled";
+		vtmu-supply = <&tmu_regulator_node>;
+	};
+
+Example 2):
+
+	tmuctrl_0: tmuctrl@160118 {
+		compatible = "samsung,exynos5440-tmu";
+		reg = <0x160118 0x230>, <0x160368 0x10>;
+		interrupts = <0 58 0>;
+		clocks = <&clock 21>;
+		clock-names = "tmu_apbif";
+	};
+
+Note: For multi-instance tmu each instance should have an alias correctly
+numbered in "aliases" node.
+
+Example:
+
+aliases {
+	tmuctrl0 = &tmuctrl_0;
+	tmuctrl1 = &tmuctrl_1;
+	tmuctrl2 = &tmuctrl_2;
+};
diff --git a/Documentation/devicetree/bindings/thermal/imx-thermal.txt b/Documentation/devicetree/bindings/thermal/imx-thermal.txt
new file mode 100644
index 000000000000..541c25e49abf
--- /dev/null
+++ b/Documentation/devicetree/bindings/thermal/imx-thermal.txt
@@ -0,0 +1,17 @@
+* Temperature Monitor (TEMPMON) on Freescale i.MX SoCs
+
+Required properties:
+- compatible : "fsl,imx6q-thermal"
+- fsl,tempmon : phandle pointer to system controller that contains TEMPMON
+  control registers, e.g. ANATOP on imx6q.
+- fsl,tempmon-data : phandle pointer to fuse controller that contains TEMPMON
+  calibration data, e.g. OCOTP on imx6q.  The details about calibration data
+  can be found in SoC Reference Manual.
+
+Example:
+
+tempmon {
+	compatible = "fsl,imx6q-tempmon";
+	fsl,tempmon = <&anatop>;
+	fsl,tempmon-data = <&ocotp>;
+};
diff --git a/Documentation/devicetree/bindings/timer/marvell,armada-370-xp-timer.txt b/Documentation/devicetree/bindings/timer/marvell,armada-370-xp-timer.txt
index 36381129d141..f455182b1086 100644
--- a/Documentation/devicetree/bindings/timer/marvell,armada-370-xp-timer.txt
+++ b/Documentation/devicetree/bindings/timer/marvell,armada-370-xp-timer.txt
@@ -2,14 +2,40 @@ Marvell Armada 370 and Armada XP Timers
 ---------------------------------------
 
 Required properties:
-- compatible: Should be "marvell,armada-370-xp-timer"
+- compatible: Should be either "marvell,armada-370-timer" or
+  "marvell,armada-xp-timer" as appropriate.
 - interrupts: Should contain the list of Global Timer interrupts and
   then local timer interrupts
 - reg: Should contain location and length for timers register. First
   pair for the Global Timer registers, second pair for the
   local/private timers.
-- clocks: clock driving the timer hardware
 
-Optional properties:
-- marvell,timer-25Mhz: Tells whether the Global timer supports the 25
-  Mhz fixed mode (available on Armada XP and not on Armada 370)
+Clocks required for compatible = "marvell,armada-370-timer":
+- clocks : Must contain a single entry describing the clock input
+
+Clocks required for compatible = "marvell,armada-xp-timer":
+- clocks : Must contain an entry for each entry in clock-names.
+- clock-names : Must include the following entries:
+  "nbclk" (L2/coherency fabric clock),
+  "fixed" (Reference 25 MHz fixed-clock).
+
+Examples:
+
+- Armada 370:
+
+	timer {
+		compatible = "marvell,armada-370-timer";
+		reg = <0x20300 0x30>, <0x21040 0x30>;
+		interrupts = <37>, <38>, <39>, <40>, <5>, <6>;
+		clocks = <&coreclk 2>;
+	};
+
+- Armada XP:
+
+	timer {
+		compatible = "marvell,armada-xp-timer";
+		reg = <0x20300 0x30>, <0x21040 0x30>;
+		interrupts = <37>, <38>, <39>, <40>, <5>, <6>;
+		clocks = <&coreclk 2>, <&refclk>;
+		clock-names = "nbclk", "fixed";
+	};
diff --git a/Documentation/devicetree/bindings/timer/moxa,moxart-timer.txt b/Documentation/devicetree/bindings/timer/moxa,moxart-timer.txt
new file mode 100644
index 000000000000..da2d510cae47
--- /dev/null
+++ b/Documentation/devicetree/bindings/timer/moxa,moxart-timer.txt
@@ -0,0 +1,17 @@
+MOXA ART timer
+
+Required properties:
+
+- compatible : Must be "moxa,moxart-timer"
+- reg : Should contain registers location and length
+- interrupts : Should contain the timer interrupt number
+- clocks : Should contain phandle for the clock that drives the counter
+
+Example:
+
+	timer: timer@98400000 {
+		compatible = "moxa,moxart-timer";
+		reg = <0x98400000 0x42>;
+		interrupts = <19 1>;
+		clocks = <&coreclk>;
+	};
diff --git a/Documentation/devicetree/bindings/tty/serial/fsl-imx-uart.txt b/Documentation/devicetree/bindings/tty/serial/fsl-imx-uart.txt
deleted file mode 100644
index c662eb36be29..000000000000
--- a/Documentation/devicetree/bindings/tty/serial/fsl-imx-uart.txt
+++ /dev/null
@@ -1,22 +0,0 @@
-* Freescale i.MX Universal Asynchronous Receiver/Transmitter (UART)
-
-Required properties:
-- compatible : Should be "fsl,<soc>-uart"
-- reg : Address and length of the register set for the device
-- interrupts : Should contain uart interrupt
-
-Optional properties:
-- fsl,uart-has-rtscts : Indicate the uart has rts and cts
-- fsl,irda-mode : Indicate the uart supports irda mode
-- fsl,dte-mode : Indicate the uart works in DTE mode. The uart works
-                  is DCE mode by default.
-
-Example:
-
-serial@73fbc000 {
-	compatible = "fsl,imx51-uart", "fsl,imx21-uart";
-	reg = <0x73fbc000 0x4000>;
-	interrupts = <31>;
-	fsl,uart-has-rtscts;
-	fsl,dte-mode;
-};
diff --git a/Documentation/devicetree/bindings/tty/serial/msm_serial.txt b/Documentation/devicetree/bindings/tty/serial/msm_serial.txt
deleted file mode 100644
index aef383eb8876..000000000000
--- a/Documentation/devicetree/bindings/tty/serial/msm_serial.txt
+++ /dev/null
@@ -1,27 +0,0 @@
-* Qualcomm MSM UART
-
-Required properties:
-- compatible :
-	- "qcom,msm-uart", and one of "qcom,msm-hsuart" or
-	  "qcom,msm-lsuart".
-- reg : offset and length of the register set for the device
-	for the hsuart operating in compatible mode, there should be a
-	second pair describing the gsbi registers.
-- interrupts : should contain the uart interrupt.
-
-There are two different UART blocks used in MSM devices,
-"qcom,msm-hsuart" and "qcom,msm-lsuart".  The msm-serial driver is
-able to handle both of these, and matches against the "qcom,msm-uart"
-as the compatibility.
-
-The registers for the "qcom,msm-hsuart" device need to specify both
-register blocks, even for the common driver.
-
-Example:
-
-	uart@19c400000 {
-		compatible = "qcom,msm-hsuart", "qcom,msm-uart";
-		reg = <0x19c40000 0x1000>,
-		      <0x19c00000 0x1000>;
-		interrupts = <195>;
-	};
diff --git a/Documentation/devicetree/bindings/usb/am33xx-usb.txt b/Documentation/devicetree/bindings/usb/am33xx-usb.txt
index dc9dc8c87f15..20c2ff2ba07e 100644
--- a/Documentation/devicetree/bindings/usb/am33xx-usb.txt
+++ b/Documentation/devicetree/bindings/usb/am33xx-usb.txt
@@ -1,35 +1,197 @@
-AM33XX MUSB GLUE
- - compatible : Should be "ti,musb-am33xx"
- - reg : offset and length of register sets, first usbss, then for musb instances
- - interrupts : usbss, musb instance interrupts in order
- - ti,hwmods : must be "usb_otg_hs"
- - multipoint : Should be "1" indicating the musb controller supports
-   multipoint. This is a MUSB configuration-specific setting.
- - num-eps : Specifies the number of endpoints. This is also a
-   MUSB configuration-specific setting. Should be set to "16"
- - ram-bits : Specifies the ram address size. Should be set to "12"
- - port0-mode : Should be "3" to represent OTG. "1" signifies HOST and "2"
-   represents PERIPHERAL.
- - port1-mode : Should be "1" to represent HOST. "3" signifies OTG and "2"
-   represents PERIPHERAL.
- - power : Should be "250". This signifies the controller can supply up to
-   500mA when operating in host mode.
+  AM33xx MUSB
+~~~~~~~~~~~~~~~
+- compatible: ti,am33xx-usb
+- reg: offset and length of the usbss register sets
+- ti,hwmods : must be "usb_otg_hs"
+
+The glue layer contains multiple child nodes. It is required the have
+at least a control module node, USB node and a PHY node. The second USB
+node and its PHY node is optional. The DMA node is also optional.
+
+Reset module
+~~~~~~~~~~~~
+- compatible: ti,am335x-usb-ctrl-module
+- reg: offset and length of the "USB control registers" in the "Control
+  Module" block. A second offset and length for the USB wake up control
+  in the same memory block.
+- reg-names: "phy_ctrl" for the "USB control registers" and "wakeup" for
+  the USB wake up control register.
+
+USB PHY
+~~~~~~~
+compatible: ti,am335x-usb-phy
+reg: offset and length of the "USB PHY" register space
+ti,ctrl_mod: reference to the "reset module" node
+reg-names: phy
+The PHY should have a "phy" alias numbered properly in the alias
+node.
+
+USB
+~~~
+- compatible: ti,musb-am33xx
+- reg: offset and length of "USB Controller Registers", and offset and
+  length of "USB Core" register space.
+- reg-names: control for the ""USB Controller Registers" and "mc" for
+  "USB Core" register space
+- interrupts: USB interrupt number
+- interrupt-names: mc
+- dr_mode: Should be one of "host", "peripheral" or "otg".
+- mentor,multipoint: Should be "1" indicating the musb controller supports
+  multipoint. This is a MUSB configuration-specific setting.
+- mentor,num-eps: Specifies the number of endpoints. This is also a
+  MUSB configuration-specific setting. Should be set to "16"
+- mentor,ram-bits: Specifies the ram address size. Should be set to "12"
+- mentor,power: Should be "500". This signifies the controller can supply up to
+  500mA when operating in host mode.
+- phys: reference to the USB phy
+- dmas: specifies the dma channels
+- dma-names: specifies the names of the channels. Use "rxN" for receive
+  and "txN" for transmit endpoints. N specifies the endpoint number.
+
+The controller should have an "usb" alias numbered properly in the alias
+node.
+
+DMA
+~~~
+- compatible: ti,am3359-cppi41
+- reg: offset and length of the following register spaces: USBSS, USB
+  CPPI DMA Controller, USB CPPI DMA Scheduler, USB Queue Manager
+- reg-names: glue, controller, scheduler, queuemgr
+- #dma-cells: should be set to 2. The first number represents the
+  endpoint number (0 … 14 for endpoints 1 … 15 on instance 0 and 15 … 29
+  for endpoints 1 … 15 on instance 1). The second number is 0 for RX and
+  1 for TX transfers.
+- #dma-channels: should be set to 30 representing the 15 endpoints for
+  each USB instance.
 
 Example:
+~~~~~~~~
+The following example contains all the nodes as used on am335x-evm:
+
+aliases {
+	usb0 = &usb0;
+	usb1 = &usb1;
+	phy0 = &usb0_phy;
+	phy1 = &usb1_phy;
+};
 
-usb@47400000  {
-	compatible = "ti,musb-am33xx";
-	reg = <0x47400000 0x1000	/* usbss */
-	       0x47401000 0x800		/* musb instance 0 */
-	       0x47401800 0x800>;	/* musb instance 1 */
-	interrupts = <17		/* usbss */
-		      18		/* musb instance 0 */
-		      19>;		/* musb instance 1 */
-	multipoint = <1>;
-	num-eps = <16>;
-	ram-bits = <12>;
-	port0-mode = <3>;
-	port1-mode = <3>;
-	power = <250>;
+usb: usb@47400000 {
+	compatible = "ti,am33xx-usb";
+	reg = <0x47400000 0x1000>;
+	ranges;
+	#address-cells = <1>;
+	#size-cells = <1>;
 	ti,hwmods = "usb_otg_hs";
+
+	ctrl_mod: control@44e10000 {
+		compatible = "ti,am335x-usb-ctrl-module";
+		reg = <0x44e10620 0x10
+			0x44e10648 0x4>;
+		reg-names = "phy_ctrl", "wakeup";
+	};
+
+	usb0_phy: usb-phy@47401300 {
+		compatible = "ti,am335x-usb-phy";
+		reg = <0x47401300 0x100>;
+		reg-names = "phy";
+		ti,ctrl_mod = <&ctrl_mod>;
+	};
+
+	usb0: usb@47401000 {
+		compatible = "ti,musb-am33xx";
+		reg = <0x47401400 0x400
+			0x47401000 0x200>;
+		reg-names = "mc", "control";
+
+		interrupts = <18>;
+		interrupt-names = "mc";
+		dr_mode = "otg"
+		mentor,multipoint = <1>;
+		mentor,num-eps = <16>;
+		mentor,ram-bits = <12>;
+		mentor,power = <500>;
+		phys = <&usb0_phy>;
+
+		dmas = <&cppi41dma  0 0 &cppi41dma  1 0
+			&cppi41dma  2 0 &cppi41dma  3 0
+			&cppi41dma  4 0 &cppi41dma  5 0
+			&cppi41dma  6 0 &cppi41dma  7 0
+			&cppi41dma  8 0 &cppi41dma  9 0
+			&cppi41dma 10 0 &cppi41dma 11 0
+			&cppi41dma 12 0 &cppi41dma 13 0
+			&cppi41dma 14 0 &cppi41dma  0 1
+			&cppi41dma  1 1 &cppi41dma  2 1
+			&cppi41dma  3 1 &cppi41dma  4 1
+			&cppi41dma  5 1 &cppi41dma  6 1
+			&cppi41dma  7 1 &cppi41dma  8 1
+			&cppi41dma  9 1 &cppi41dma 10 1
+			&cppi41dma 11 1 &cppi41dma 12 1
+			&cppi41dma 13 1 &cppi41dma 14 1>;
+		dma-names =
+			"rx1", "rx2", "rx3", "rx4", "rx5", "rx6", "rx7",
+			"rx8", "rx9", "rx10", "rx11", "rx12", "rx13",
+			"rx14", "rx15",
+			"tx1", "tx2", "tx3", "tx4", "tx5", "tx6", "tx7",
+			"tx8", "tx9", "tx10", "tx11", "tx12", "tx13",
+			"tx14", "tx15";
+	};
+
+	usb1_phy: usb-phy@47401b00 {
+		compatible = "ti,am335x-usb-phy";
+		reg = <0x47401b00 0x100>;
+		reg-names = "phy";
+		ti,ctrl_mod = <&ctrl_mod>;
+	};
+
+	usb1: usb@47401800 {
+		compatible = "ti,musb-am33xx";
+		reg = <0x47401c00 0x400
+			0x47401800 0x200>;
+		reg-names = "mc", "control";
+		interrupts = <19>;
+		interrupt-names = "mc";
+		dr_mode = "host"
+		mentor,multipoint = <1>;
+		mentor,num-eps = <16>;
+		mentor,ram-bits = <12>;
+		mentor,power = <500>;
+		phys = <&usb1_phy>;
+
+		dmas = <&cppi41dma 15 0 &cppi41dma 16 0
+			&cppi41dma 17 0 &cppi41dma 18 0
+			&cppi41dma 19 0 &cppi41dma 20 0
+			&cppi41dma 21 0 &cppi41dma 22 0
+			&cppi41dma 23 0 &cppi41dma 24 0
+			&cppi41dma 25 0 &cppi41dma 26 0
+			&cppi41dma 27 0 &cppi41dma 28 0
+			&cppi41dma 29 0 &cppi41dma 15 1
+			&cppi41dma 16 1 &cppi41dma 17 1
+			&cppi41dma 18 1 &cppi41dma 19 1
+			&cppi41dma 20 1 &cppi41dma 21 1
+			&cppi41dma 22 1 &cppi41dma 23 1
+			&cppi41dma 24 1 &cppi41dma 25 1
+			&cppi41dma 26 1 &cppi41dma 27 1
+			&cppi41dma 28 1 &cppi41dma 29 1>;
+		dma-names =
+			"rx1", "rx2", "rx3", "rx4", "rx5", "rx6", "rx7",
+			"rx8", "rx9", "rx10", "rx11", "rx12", "rx13",
+			"rx14", "rx15",
+			"tx1", "tx2", "tx3", "tx4", "tx5", "tx6", "tx7",
+			"tx8", "tx9", "tx10", "tx11", "tx12", "tx13",
+			"tx14", "tx15";
+	};
+
+	cppi41dma: dma-controller@07402000 {
+		compatible = "ti,am3359-cppi41";
+		reg =  <0x47400000 0x1000
+			0x47402000 0x1000
+			0x47403000 0x1000
+			0x47404000 0x4000>;
+		reg-names = "glue", "controller", "scheduler", "queuemgr";
+		interrupts = <17>;
+		interrupt-names = "glue";
+		#dma-cells = <2>;
+		#dma-channels = <30>;
+		#dma-requests = <256>;
+	};
 };
diff --git a/Documentation/devicetree/bindings/usb/dwc3.txt b/Documentation/devicetree/bindings/usb/dwc3.txt
index 7a95c651ceb3..e807635f9e1c 100644
--- a/Documentation/devicetree/bindings/usb/dwc3.txt
+++ b/Documentation/devicetree/bindings/usb/dwc3.txt
@@ -3,10 +3,12 @@ synopsys DWC3 CORE
 DWC3- USB3 CONTROLLER
 
 Required properties:
- - compatible: must be "synopsys,dwc3"
+ - compatible: must be "snps,dwc3"
  - reg : Address and length of the register set for the device
  - interrupts: Interrupts used by the dwc3 controller.
- - usb-phy : array of phandle for the PHY device
+ - usb-phy : array of phandle for the PHY device.  The first element
+   in the array is expected to be a handle to the USB2/HS PHY and
+   the second element is expected to be a handle to the USB3/SS PHY
 
 Optional properties:
  - tx-fifo-resize: determines if the FIFO *has* to be reallocated.
@@ -14,7 +16,7 @@ Optional properties:
 This is usually a subnode to DWC3 glue to which it is connected.
 
 dwc3@4a030000 {
-	compatible = "synopsys,dwc3";
+	compatible = "snps,dwc3";
 	reg = <0x4a030000 0xcfff>;
 	interrupts = <0 92 4>
 	usb-phy = <&usb2_phy>, <&usb3,phy>;
diff --git a/Documentation/devicetree/bindings/usb/generic.txt b/Documentation/devicetree/bindings/usb/generic.txt
new file mode 100644
index 000000000000..477d5bb5e51c
--- /dev/null
+++ b/Documentation/devicetree/bindings/usb/generic.txt
@@ -0,0 +1,24 @@
+Generic USB Properties
+
+Optional properties:
+ - maximum-speed: tells USB controllers we want to work up to a certain
+			speed. Valid arguments are "super-speed", "high-speed",
+			"full-speed" and "low-speed". In case this isn't passed
+			via DT, USB controllers should default to their maximum
+			HW capability.
+ - dr_mode: tells Dual-Role USB controllers that we want to work on a
+			particular mode. Valid arguments are "host",
+			"peripheral" and "otg". In case this attribute isn't
+			passed via DT, USB DRD controllers should default to
+			OTG.
+
+This is an attribute to a USB controller such as:
+
+dwc3@4a030000 {
+	compatible = "synopsys,dwc3";
+	reg = <0x4a030000 0xcfff>;
+	interrupts = <0 92 4>
+	usb-phy = <&usb2_phy>, <&usb3,phy>;
+	maximum-speed = "super-speed";
+	dr_mode = "otg";
+};
diff --git a/Documentation/devicetree/bindings/usb/nvidia,tegra20-usb-phy.txt b/Documentation/devicetree/bindings/usb/nvidia,tegra20-usb-phy.txt
index c4c9e9e664aa..ba797d3e6326 100644
--- a/Documentation/devicetree/bindings/usb/nvidia,tegra20-usb-phy.txt
+++ b/Documentation/devicetree/bindings/usb/nvidia,tegra20-usb-phy.txt
@@ -3,7 +3,7 @@ Tegra SOC USB PHY
 The device node for Tegra SOC USB PHY:
 
 Required properties :
- - compatible : Should be "nvidia,tegra20-usb-phy".
+ - compatible : Should be "nvidia,tegra<chip>-usb-phy".
  - reg : Defines the following set of registers, in the order listed:
    - The PHY's own register set.
      Always present.
@@ -24,17 +24,26 @@ Required properties :
 Required properties for phy_type == ulpi:
   - nvidia,phy-reset-gpio : The GPIO used to reset the PHY.
 
-Required PHY timing params for utmi phy:
+Required PHY timing params for utmi phy, for all chips:
   - nvidia,hssync-start-delay : Number of 480 Mhz clock cycles to wait before
     start of sync launches RxActive
   - nvidia,elastic-limit : Variable FIFO Depth of elastic input store
   - nvidia,idle-wait-delay : Number of 480 Mhz clock cycles of idle to wait
     before declare IDLE.
   - nvidia,term-range-adj : Range adjusment on terminations
-  - nvidia,xcvr-setup : HS driver output control
+  - Either one of the following for HS driver output control:
+    - nvidia,xcvr-setup : integer, uses the provided value.
+    - nvidia,xcvr-setup-use-fuses : boolean, indicates that the value is read
+      from the on-chip fuses
+    If both are provided, nvidia,xcvr-setup-use-fuses takes precedence.
   - nvidia,xcvr-lsfslew : LS falling slew rate control.
   - nvidia,xcvr-lsrslew :  LS rising slew rate control.
 
+Required PHY timing params for utmi phy, only on Tegra30 and above:
+  - nvidia,xcvr-hsslew : HS slew rate control.
+  - nvidia,hssquelch-level : HS squelch detector level.
+  - nvidia,hsdiscon-level : HS disconnect detector level.
+
 Optional properties:
   - nvidia,has-legacy-mode : boolean indicates whether this controller can
     operate in legacy mode (as APX 2500 / 2600). In legacy mode some
@@ -48,5 +57,5 @@ Optional properties:
       peripheral means it is device controller
       otg means it can operate as either ("on the go")
 
-Required properties for dr_mode == otg:
+VBUS control (required for dr_mode == otg, optional for dr_mode == host):
   - vbus-supply: regulator for VBUS
diff --git a/Documentation/devicetree/bindings/usb/omap-usb.txt b/Documentation/devicetree/bindings/usb/omap-usb.txt
index 57e71f6817d0..9088ab09e200 100644
--- a/Documentation/devicetree/bindings/usb/omap-usb.txt
+++ b/Documentation/devicetree/bindings/usb/omap-usb.txt
@@ -53,6 +53,11 @@ OMAP DWC3 GLUE
    It should be set to "1" for HW mode and "2" for SW mode.
  - ranges: the child address space are mapped 1:1 onto the parent address space
 
+Optional Properties:
+ - extcon : phandle for the extcon device omap dwc3 uses to detect
+   connect/disconnect events.
+ - vbus-supply : phandle to the regulator device tree node if needed.
+
 Sub-nodes:
 The dwc3 core should be added as subnode to omap dwc3 glue.
 - dwc3 :
diff --git a/Documentation/devicetree/bindings/usb/samsung-hsotg.txt b/Documentation/devicetree/bindings/usb/samsung-hsotg.txt
new file mode 100644
index 000000000000..b83d428a265e
--- /dev/null
+++ b/Documentation/devicetree/bindings/usb/samsung-hsotg.txt
@@ -0,0 +1,40 @@
+Samsung High Speed USB OTG controller
+-----------------------------
+
+The Samsung HSOTG IP can be found on Samsung SoCs, from S3C6400 onwards.
+It gives functionality of OTG-compliant USB 2.0 host and device with
+support for USB 2.0 high-speed (480Mbps) and full-speed (12 Mbps)
+operation.
+
+Currently only device mode is supported.
+
+Binding details
+-----
+
+Required properties:
+- compatible: "samsung,s3c6400-hsotg" should be used for all currently
+    supported SoC,
+- interrupt-parent: phandle for the interrupt controller to which the
+    interrupt signal of the HSOTG block is routed,
+- interrupts: specifier of interrupt signal of interrupt controller,
+    according to bindings of interrupt controller,
+- clocks: contains an array of clock specifiers:
+    - first entry: OTG clock
+- clock-names: contains array of clock names:
+    - first entry: must be "otg"
+- vusb_d-supply: phandle to voltage regulator of digital section,
+- vusb_a-supply: phandle to voltage regulator of analog section.
+
+Example
+-----
+
+	hsotg@12480000 {
+		compatible = "samsung,s3c6400-hsotg";
+		reg = <0x12480000 0x20000>;
+		interrupts = <0 71 0>;
+		clocks = <&clock 305>;
+		clock-names = "otg";
+		vusb_d-supply = <&vusb_reg>;
+		vusb_a-supply = <&vusbdac_reg>;
+	};
+
diff --git a/Documentation/devicetree/bindings/usb/usb-xhci.txt b/Documentation/devicetree/bindings/usb/usb-xhci.txt
new file mode 100644
index 000000000000..5752df0e17a2
--- /dev/null
+++ b/Documentation/devicetree/bindings/usb/usb-xhci.txt
@@ -0,0 +1,14 @@
+USB xHCI controllers
+
+Required properties:
+  - compatible: should be "xhci-platform".
+  - reg: should contain address and length of the standard XHCI
+    register set for the device.
+  - interrupts: one XHCI interrupt should be described here.
+
+Example:
+	usb@f0931000 {
+		compatible = "xhci-platform";
+		reg = <0xf0931000 0x8c8>;
+		interrupts = <0x0 0x4e 0x0>;
+	};
diff --git a/Documentation/devicetree/bindings/usb/usb3503.txt b/Documentation/devicetree/bindings/usb/usb3503.txt
index 8c5be48b43c8..a018da4a7ad7 100644
--- a/Documentation/devicetree/bindings/usb/usb3503.txt
+++ b/Documentation/devicetree/bindings/usb/usb3503.txt
@@ -1,8 +1,11 @@
 SMSC USB3503 High-Speed Hub Controller
 
 Required properties:
-- compatible: Should be "smsc,usb3503".
-- reg: Specifies the i2c slave address, it should be 0x08.
+- compatible: Should be "smsc,usb3503" or "smsc,usb3503a".
+
+Optional properties:
+- reg: Specifies the i2c slave address, it is required and should be 0x08
+       if I2C is used.
 - connect-gpios: Should specify GPIO for connect.
 - disabled-ports: Should specify the ports unused.
 	'1' or '2' or '3' are availe for this property to describe the port
diff --git a/Documentation/devicetree/bindings/vendor-prefixes.txt b/Documentation/devicetree/bindings/vendor-prefixes.txt
index 366ce9b87240..2956800f0240 100644
--- a/Documentation/devicetree/bindings/vendor-prefixes.txt
+++ b/Documentation/devicetree/bindings/vendor-prefixes.txt
@@ -7,10 +7,12 @@ ad	Avionic Design GmbH
 adi	Analog Devices, Inc.
 aeroflexgaisler	Aeroflex Gaisler AB
 ak	Asahi Kasei Corp.
+altr	Altera Corp.
 amcc	Applied Micro Circuits Corporation (APM, formally AMCC)
 apm	Applied Micro Circuits Corporation (APM)
 arm	ARM Ltd.
 atmel	Atmel Corporation
+avago	Avago Technologies
 bosch	Bosch Sensortec GmbH
 brcm	Broadcom Corporation
 cavium	Cavium, Inc.
@@ -36,6 +38,7 @@ linux	Linux-specific binding
 lsi	LSI Corp. (LSI Logic)
 marvell	Marvell Technology Group Ltd.
 maxim	Maxim Integrated Products
+microchip	Microchip Technology Inc.
 mosaixtech	Mosaix Technologies, Inc.
 national	National Semiconductor
 nintendo	Nintendo
diff --git a/Documentation/devicetree/bindings/video/simple-framebuffer.txt b/Documentation/devicetree/bindings/video/simple-framebuffer.txt
index 3ea460583111..70c26f3a5b9a 100644
--- a/Documentation/devicetree/bindings/video/simple-framebuffer.txt
+++ b/Documentation/devicetree/bindings/video/simple-framebuffer.txt
@@ -12,6 +12,7 @@ Required properties:
 - stride: The number of bytes in each line of the framebuffer.
 - format: The format of the framebuffer surface. Valid values are:
   - r5g6b5 (16-bit pixels, d[15:11]=r, d[10:5]=g, d[4:0]=b).
+  - a8b8g8r8 (32-bit pixels, d[31:24]=a, d[23:16]=b, d[15:8]=g, d[7:0]=r).
 
 Example:
 
diff --git a/Documentation/devicetree/bindings/watchdog/sun4i-wdt.txt b/Documentation/devicetree/bindings/watchdog/sunxi-wdt.txt
index ecd650adff31..e39cb266c8f4 100644
--- a/Documentation/devicetree/bindings/watchdog/sun4i-wdt.txt
+++ b/Documentation/devicetree/bindings/watchdog/sunxi-wdt.txt
@@ -1,8 +1,9 @@
-Allwinner sun4i Watchdog timer
+Allwinner SoCs Watchdog timer
 
 Required properties:
 
-- compatible : should be "allwinner,sun4i-wdt"
+- compatible : should be "allwinner,<soc-family>-wdt", the currently supported
+  SoC families being sun4i and sun6i
 - reg : Specifies base physical address and size of the registers.
 
 Example:
diff --git a/Documentation/dma-buf-sharing.txt b/Documentation/dma-buf-sharing.txt
index 0b23261561d2..505e71172ae7 100644
--- a/Documentation/dma-buf-sharing.txt
+++ b/Documentation/dma-buf-sharing.txt
@@ -321,7 +321,7 @@ Access to a dma_buf from the kernel context involves three steps:
 
    When the importer is done accessing the range specified in begin_cpu_access,
    it needs to announce this to the exporter (to facilitate cache flushing and
-   unpinning of any pinned resources). The result of of any dma_buf kmap calls
+   unpinning of any pinned resources). The result of any dma_buf kmap calls
    after end_cpu_access is undefined.
 
    Interface:
@@ -407,6 +407,18 @@ Being able to mmap an export dma-buf buffer object has 2 main use-cases:
    interesting ways depending upong the exporter (if userspace starts depending
    upon this implicit synchronization).
 
+Other Interfaces Exposed to Userspace on the dma-buf FD
+------------------------------------------------------
+
+- Since kernel 3.12 the dma-buf FD supports the llseek system call, but only
+  with offset=0 and whence=SEEK_END|SEEK_SET. SEEK_SET is supported to allow
+  the usual size discover pattern size = SEEK_END(0); SEEK_SET(0). Every other
+  llseek operation will report -EINVAL.
+
+  If llseek on dma-buf FDs isn't support the kernel will report -ESPIPE for all
+  cases. Userspace can use this to detect support for discovering the dma-buf
+  size using llseek.
+
 Miscellaneous notes
 -------------------
 
diff --git a/Documentation/dmatest.txt b/Documentation/dmatest.txt
index 132a094c7bc3..a2b5663eae26 100644
--- a/Documentation/dmatest.txt
+++ b/Documentation/dmatest.txt
@@ -16,15 +16,16 @@ be built as module or inside kernel. Let's consider those cases.
 	Part 2 - When dmatest is built as a module...
 
 After mounting debugfs and loading the module, the /sys/kernel/debug/dmatest
-folder with nodes will be created. They are the same as module parameters with
-addition of the 'run' node that controls run and stop phases of the test.
+folder with nodes will be created. There are two important files located. First
+is the 'run' node that controls run and stop phases of the test, and the second
+one, 'results', is used to get the test case results.
 
 Note that in this case test will not run on load automatically.
 
 Example of usage:
-	% echo dma0chan0 > /sys/kernel/debug/dmatest/channel
-	% echo 2000 > /sys/kernel/debug/dmatest/timeout
-	% echo 1 > /sys/kernel/debug/dmatest/iterations
+	% echo dma0chan0 > /sys/module/dmatest/parameters/channel
+	% echo 2000 > /sys/module/dmatest/parameters/timeout
+	% echo 1 > /sys/module/dmatest/parameters/iterations
 	% echo 1 > /sys/kernel/debug/dmatest/run
 
 Hint: available channel list could be extracted by running the following
@@ -55,8 +56,8 @@ for the first performed test. After user gets a control, the test could be
 re-run with the same or different parameters. For the details see the above
 section "Part 2 - When dmatest is built as a module..."
 
-In both cases the module parameters are used as initial values for the test case.
-You always could check them at run-time by running
+In both cases the module parameters are used as the actual values for the test
+case. You always could check them at run-time by running
 	% grep -H . /sys/module/dmatest/parameters/*
 
 	Part 4 - Gathering the test results
diff --git a/Documentation/driver-model/devres.txt b/Documentation/driver-model/devres.txt
index b4671459857f..fcb34a5697ea 100644
--- a/Documentation/driver-model/devres.txt
+++ b/Documentation/driver-model/devres.txt
@@ -237,6 +237,12 @@ MEM
   devm_kzalloc()
   devm_kfree()
 
+IIO
+  devm_iio_device_alloc()
+  devm_iio_device_free()
+  devm_iio_trigger_alloc()
+  devm_iio_trigger_free()
+
 IO region
   devm_request_region()
   devm_request_mem_region()
@@ -293,3 +299,6 @@ PWM
 PHY
   devm_usb_get_phy()
   devm_usb_put_phy()
+
+SLAVE DMA ENGINE
+  devm_acpi_dma_controller_register()
diff --git a/Documentation/early-userspace/README b/Documentation/early-userspace/README
index 661a73fad399..93e63a9af30b 100644
--- a/Documentation/early-userspace/README
+++ b/Documentation/early-userspace/README
@@ -83,8 +83,7 @@ Where's this all leading?
 
 The klibc distribution contains some of the necessary software to make
 early userspace useful.  The klibc distribution is currently
-maintained separately from the kernel, but this may change early in
-the 2.7 era (it missed the boat for 2.5).
+maintained separately from the kernel.
 
 You can obtain somewhat infrequent snapshots of klibc from
 ftp://ftp.kernel.org/pub/linux/libs/klibc/
diff --git a/Documentation/fb/fbcon.txt b/Documentation/fb/fbcon.txt
index 99ea58e65eff..4a9739abc860 100644
--- a/Documentation/fb/fbcon.txt
+++ b/Documentation/fb/fbcon.txt
@@ -150,7 +150,7 @@ C. Boot options
 
 C. Attaching, Detaching and Unloading
 
-Before going on on how to attach, detach and unload the framebuffer console, an
+Before going on how to attach, detach and unload the framebuffer console, an
 illustration of the dependencies may help.
 
 The console layer, as with most subsystems, needs a driver that interfaces with
diff --git a/Documentation/fb/viafb.modes b/Documentation/fb/viafb.modes
index 02e5b487f00e..2a547da2e5cc 100644
--- a/Documentation/fb/viafb.modes
+++ b/Documentation/fb/viafb.modes
@@ -571,7 +571,7 @@ mode "640x480-60"
 #                   160 chars   800 lines
 #   Blank Time      4.798 us    0.564 ms
 #                   50 chars    28 lines
-#   Polarity        negtive    positive
+#   Polarity        negative    positive
 #
     mode "1280x800-60"
 # D: 83.500 MHz, H: 49.702 kHz, V: 60.00 Hz
diff --git a/Documentation/fb/viafb.txt b/Documentation/fb/viafb.txt
index 444e34b52ae1..1cb2462a71ce 100644
--- a/Documentation/fb/viafb.txt
+++ b/Documentation/fb/viafb.txt
@@ -32,7 +32,7 @@
     Start viafb with default settings:
         #modprobe viafb
 
-    Start viafb with with user options:
+    Start viafb with user options:
         #modprobe viafb viafb_mode=800x600 viafb_bpp=16 viafb_refresh=60
                   viafb_active_dev=CRT+DVI viafb_dvi_port=DVP1
                   viafb_mode1=1024x768 viafb_bpp=16 viafb_refresh1=60
diff --git a/Documentation/filesystems/btrfs.txt b/Documentation/filesystems/btrfs.txt
index b349d57b76ea..9dae59407437 100644
--- a/Documentation/filesystems/btrfs.txt
+++ b/Documentation/filesystems/btrfs.txt
@@ -87,7 +87,7 @@ Unless otherwise specified, all options default to off.
 
   device=<devicepath>
 	Specify a device during mount so that ioctls on the control device
-	can be avoided.  Especialy useful when trying to mount a multi-device
+	can be avoided.  Especially useful when trying to mount a multi-device
 	setup as root.  May be specified multiple times for multiple devices.
 
   discard
diff --git a/Documentation/filesystems/caching/backend-api.txt b/Documentation/filesystems/caching/backend-api.txt
index d78bab9622c6..277d1e810670 100644
--- a/Documentation/filesystems/caching/backend-api.txt
+++ b/Documentation/filesystems/caching/backend-api.txt
@@ -299,6 +299,15 @@ performed on the denizens of the cache.  These are held in a structure of type:
      enough space in the cache to permit this.
 
 
+ (*) Check coherency state of an object [mandatory]:
+
+	int (*check_consistency)(struct fscache_object *object)
+
+     This method is called to have the cache check the saved auxiliary data of
+     the object against the netfs's idea of the state.  0 should be returned
+     if they're consistent and -ESTALE otherwise.  -ENOMEM and -ERESTARTSYS
+     may also be returned.
+
  (*) Update object [mandatory]:
 
 	int (*update_object)(struct fscache_object *object)
diff --git a/Documentation/filesystems/caching/netfs-api.txt b/Documentation/filesystems/caching/netfs-api.txt
index 97e6c0ecc5ef..11a0a40ce445 100644
--- a/Documentation/filesystems/caching/netfs-api.txt
+++ b/Documentation/filesystems/caching/netfs-api.txt
@@ -32,7 +32,7 @@ This document contains the following sections:
 	 (9) Setting the data file size
 	(10) Page alloc/read/write
 	(11) Page uncaching
-	(12) Index and data file update
+	(12) Index and data file consistency
 	(13) Miscellaneous cookie operations
 	(14) Cookie unregistration
 	(15) Index invalidation
@@ -433,7 +433,7 @@ to the caller.  The attribute adjustment excludes read and write operations.
 
 
 =====================
-PAGE READ/ALLOC/WRITE
+PAGE ALLOC/READ/WRITE
 =====================
 
 And the sixth step is to store and retrieve pages in the cache.  There are
@@ -499,7 +499,7 @@ Else if there's a copy of the page resident in the cache:
      (*) An argument that's 0 on success or negative for an error code.
 
      If an error occurs, it should be assumed that the page contains no usable
-     data.
+     data.  fscache_readpages_cancel() may need to be called.
 
      end_io_func() will be called in process context if the read is results in
      an error, but it might be called in interrupt context if the read is
@@ -623,6 +623,22 @@ some of the pages being read and some being allocated.  Those pages will have
 been marked appropriately and will need uncaching.
 
 
+CANCELLATION OF UNREAD PAGES
+----------------------------
+
+If one or more pages are passed to fscache_read_or_alloc_pages() but not then
+read from the cache and also not read from the underlying filesystem then
+those pages will need to have any marks and reservations removed.  This can be
+done by calling:
+
+	void fscache_readpages_cancel(struct fscache_cookie *cookie,
+				      struct list_head *pages);
+
+prior to returning to the caller.  The cookie argument should be as passed to
+fscache_read_or_alloc_pages().  Every page in the pages list will be examined
+and any that have PG_fscache set will be uncached.
+
+
 ==============
 PAGE UNCACHING
 ==============
@@ -690,9 +706,18 @@ written to the cache and for the cache to finish with the page generally.  No
 error is returned.
 
 
-==========================
-INDEX AND DATA FILE UPDATE
-==========================
+===============================
+INDEX AND DATA FILE CONSISTENCY
+===============================
+
+To find out whether auxiliary data for an object is up to data within the
+cache, the following function can be called:
+
+	int fscache_check_consistency(struct fscache_cookie *cookie)
+
+This will call back to the netfs to check whether the auxiliary data associated
+with a cookie is correct.  It returns 0 if it is and -ESTALE if it isn't; it
+may also return -ENOMEM and -ERESTARTSYS.
 
 To request an update of the index data for an index or other object, the
 following function should be called:
diff --git a/Documentation/filesystems/cifs.txt b/Documentation/filesystems/cifs.txt
deleted file mode 100644
index 49cc923a93e3..000000000000
--- a/Documentation/filesystems/cifs.txt
+++ /dev/null
@@ -1,51 +0,0 @@
-  This is the client VFS module for the Common Internet File System
-  (CIFS) protocol which is the successor to the Server Message Block 
-  (SMB) protocol, the native file sharing mechanism for most early
-  PC operating systems.  CIFS is fully supported by current network
-  file servers such as Windows 2000, Windows 2003 (including  
-  Windows XP) as well by Samba (which provides excellent CIFS
-  server support for Linux and many other operating systems), so
-  this network filesystem client can mount to a wide variety of
-  servers.  The smbfs module should be used instead of this cifs module
-  for mounting to older SMB servers such as OS/2.  The smbfs and cifs
-  modules can coexist and do not conflict.  The CIFS VFS filesystem
-  module is designed to work well with servers that implement the
-  newer versions (dialects) of the SMB/CIFS protocol such as Samba, 
-  the program written by Andrew Tridgell that turns any Unix host 
-  into a SMB/CIFS file server.
-
-  The intent of this module is to provide the most advanced network
-  file system function for CIFS compliant servers, including better
-  POSIX compliance, secure per-user session establishment, high
-  performance safe distributed caching (oplock), optional packet
-  signing, large files, Unicode support and other internationalization
-  improvements. Since both Samba server and this filesystem client support
-  the CIFS Unix extensions, the combination can provide a reasonable 
-  alternative to NFSv4 for fileserving in some Linux to Linux environments,
-  not just in Linux to Windows environments.
-
-  This filesystem has an optional mount utility (mount.cifs) that can
-  be obtained from the project page and installed in the path in the same
-  directory with the other mount helpers (such as mount.smbfs). 
-  Mounting using the cifs filesystem without installing the mount helper
-  requires specifying the server's ip address.
-
-  For Linux 2.4:
-    mount //anything/here /mnt_target -o
-            user=username,pass=password,unc=//ip_address_of_server/sharename
-
-  For Linux 2.5: 
-    mount //ip_address_of_server/sharename /mnt_target -o user=username, pass=password
-
-
-  For more information on the module see the project page at
-
-      http://us1.samba.org/samba/Linux_CIFS_client.html 
-
-  For more information on CIFS see:
-
-      http://www.snia.org/tech_activities/CIFS
-
-  or the Samba site:
-     
-      http://www.samba.org
diff --git a/fs/cifs/AUTHORS b/Documentation/filesystems/cifs/AUTHORS
index ea940b1db77b..ca4a67a0bb1e 100644
--- a/fs/cifs/AUTHORS
+++ b/Documentation/filesystems/cifs/AUTHORS
@@ -39,6 +39,7 @@ Shaggy (Dave Kleikamp) for innumerable small fs suggestions and some good cleanu
 Gunter Kukkukk (testing and suggestions for support of old servers)
 Igor Mammedov (DFS support)
 Jeff Layton (many, many fixes, as well as great work on the cifs Kerberos code)
+Scott Lovenberg
 
 Test case and Bug Report contributors
 -------------------------------------
diff --git a/fs/cifs/CHANGES b/Documentation/filesystems/cifs/CHANGES
index bc0025cdd1c9..bc0025cdd1c9 100644
--- a/fs/cifs/CHANGES
+++ b/Documentation/filesystems/cifs/CHANGES
diff --git a/fs/cifs/README b/Documentation/filesystems/cifs/README
index 2d5622f60e11..2d5622f60e11 100644
--- a/fs/cifs/README
+++ b/Documentation/filesystems/cifs/README
diff --git a/fs/cifs/TODO b/Documentation/filesystems/cifs/TODO
index 355abcdcda98..355abcdcda98 100644
--- a/fs/cifs/TODO
+++ b/Documentation/filesystems/cifs/TODO
diff --git a/Documentation/filesystems/cifs/cifs.txt b/Documentation/filesystems/cifs/cifs.txt
new file mode 100644
index 000000000000..2fac91ac96cf
--- /dev/null
+++ b/Documentation/filesystems/cifs/cifs.txt
@@ -0,0 +1,31 @@
+  This is the client VFS module for the Common Internet File System
+  (CIFS) protocol which is the successor to the Server Message Block 
+  (SMB) protocol, the native file sharing mechanism for most early
+  PC operating systems. New and improved versions of CIFS are now
+  called SMB2 and SMB3. These dialects are also supported by the
+  CIFS VFS module. CIFS is fully supported by network
+  file servers such as Windows 2000, 2003, 2008 and 2012
+  as well by Samba (which provides excellent CIFS
+  server support for Linux and many other operating systems), so
+  this network filesystem client can mount to a wide variety of
+  servers.
+
+  The intent of this module is to provide the most advanced network
+  file system function for CIFS compliant servers, including better
+  POSIX compliance, secure per-user session establishment, high
+  performance safe distributed caching (oplock), optional packet
+  signing, large files, Unicode support and other internationalization
+  improvements. Since both Samba server and this filesystem client support
+  the CIFS Unix extensions, the combination can provide a reasonable 
+  alternative to NFSv4 for fileserving in some Linux to Linux environments,
+  not just in Linux to Windows environments.
+
+  This filesystem has an mount utility (mount.cifs) that can be obtained from
+
+      https://ftp.samba.org/pub/linux-cifs/cifs-utils/
+
+  It must be installed in the directory with the other mount helpers.
+
+  For more information on the module see the project wiki page at
+
+      https://wiki.samba.org/index.php/LinuxCIFS_utils
diff --git a/Documentation/filesystems/cifs/winucase_convert.pl b/Documentation/filesystems/cifs/winucase_convert.pl
new file mode 100755
index 000000000000..322a9c833f23
--- /dev/null
+++ b/Documentation/filesystems/cifs/winucase_convert.pl
@@ -0,0 +1,62 @@
+#!/usr/bin/perl -w
+#
+# winucase_convert.pl -- convert "Windows 8 Upper Case Mapping Table.txt" to
+#                        a two-level set of C arrays.
+#
+#   Copyright 2013: Jeff Layton <jlayton@redhat.com>
+#
+#   This program is free software: you can redistribute it and/or modify
+#   it under the terms of the GNU General Public License as published by
+#   the Free Software Foundation, either version 3 of the License, or
+#   (at your option) any later version.
+#
+#   This program is distributed in the hope that it will be useful,
+#   but WITHOUT ANY WARRANTY; without even the implied warranty of
+#   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+#   GNU General Public License for more details.
+#
+#   You should have received a copy of the GNU General Public License
+#   along with this program.  If not, see <http://www.gnu.org/licenses/>.
+#
+
+while(<>) {
+	next if (!/^0x(..)(..)\t0x(....)\t/);
+	$firstchar = hex($1);
+	$secondchar = hex($2);
+	$uppercase = hex($3);
+
+	$top[$firstchar][$secondchar] = $uppercase;
+}
+
+for ($i = 0; $i < 256; $i++) {
+	next if (!$top[$i]);
+
+	printf("static const wchar_t t2_%2.2x[256] = {", $i);
+	for ($j = 0; $j < 256; $j++) {
+		if (($j % 8) == 0) {
+			print "\n\t";
+		} else {
+			print " ";
+		}
+		printf("0x%4.4x,", $top[$i][$j] ? $top[$i][$j] : 0);
+	}
+	print "\n};\n\n";
+}
+
+printf("static const wchar_t *const toplevel[256] = {", $i);
+for ($i = 0; $i < 256; $i++) {
+	if (($i % 8) == 0) {
+		print "\n\t";
+	} elsif ($top[$i]) {
+		print " ";
+	} else {
+		print "  ";
+	}
+
+	if ($top[$i]) {
+		printf("t2_%2.2x,", $i);
+	} else {
+		print "NULL,";
+	}
+}
+print "\n};\n\n";
diff --git a/Documentation/filesystems/ext3.txt b/Documentation/filesystems/ext3.txt
index 293855e95000..7ed0d17d6721 100644
--- a/Documentation/filesystems/ext3.txt
+++ b/Documentation/filesystems/ext3.txt
@@ -26,11 +26,12 @@ journal=inum		When a journal already exists, this option is ignored.
 			Otherwise, it specifies the number of the inode which
 			will represent the ext3 file system's journal file.
 
+journal_path=path
 journal_dev=devnum	When the external journal device's major/minor numbers
-			have changed, this option allows the user to specify
+			have changed, these options allow the user to specify
 			the new journal location.  The journal device is
-			identified through its new major/minor numbers encoded
-			in devnum.
+			identified through either its new major/minor numbers
+			encoded in devnum, or via a path to the device.
 
 norecovery		Don't load the journal on mounting. Note that this forces
 noload			mount of inconsistent filesystem, which can lead to
diff --git a/Documentation/filesystems/ext4.txt b/Documentation/filesystems/ext4.txt
index f7cbf574a875..919a3293aaa4 100644
--- a/Documentation/filesystems/ext4.txt
+++ b/Documentation/filesystems/ext4.txt
@@ -2,7 +2,7 @@
 Ext4 Filesystem
 ===============
 
-Ext4 is an an advanced level of the ext3 filesystem which incorporates
+Ext4 is an advanced level of the ext3 filesystem which incorporates
 scalability and reliability enhancements for supporting large filesystems
 (64 bit) in keeping with increasing disk capacities and state-of-the-art
 feature requirements.
@@ -144,11 +144,12 @@ journal_async_commit	Commit block can be written to disk without waiting
 			mount the device. This will enable 'journal_checksum'
 			internally.
 
+journal_path=path
 journal_dev=devnum	When the external journal device's major/minor numbers
-			have changed, this option allows the user to specify
+			have changed, these options allow the user to specify
 			the new journal location.  The journal device is
-			identified through its new major/minor numbers encoded
-			in devnum.
+			identified through either its new major/minor numbers
+			encoded in devnum, or via a path to the device.
 
 norecovery		Don't load the journal on mounting.  Note that
 noload			if the filesystem was not unmounted cleanly,
diff --git a/Documentation/filesystems/f2fs.txt b/Documentation/filesystems/f2fs.txt
index b91e2f26b672..3cd27bed6349 100644
--- a/Documentation/filesystems/f2fs.txt
+++ b/Documentation/filesystems/f2fs.txt
@@ -18,8 +18,8 @@ according to its internal geometry or flash memory management scheme, namely FTL
 F2FS and its tools support various parameters not only for configuring on-disk
 layout, but also for selecting allocation and cleaning algorithms.
 
-The file system formatting tool, "mkfs.f2fs", is available from the following
-git tree:
+The following git tree provides the file system formatting tool (mkfs.f2fs),
+a consistency checking tool (fsck.f2fs), and a debugging tool (dump.f2fs).
 >> git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs-tools.git
 
 For reporting bugs and sending patches, please use the following mailing list:
@@ -133,6 +133,38 @@ f2fs. Each file shows the whole f2fs information.
  - current memory footprint consumed by f2fs.
 
 ================================================================================
+SYSFS ENTRIES
+================================================================================
+
+Information about mounted f2f2 file systems can be found in
+/sys/fs/f2fs.  Each mounted filesystem will have a directory in
+/sys/fs/f2fs based on its device name (i.e., /sys/fs/f2fs/sda).
+The files in each per-device directory are shown in table below.
+
+Files in /sys/fs/f2fs/<devname>
+(see also Documentation/ABI/testing/sysfs-fs-f2fs)
+..............................................................................
+ File                         Content
+
+ gc_max_sleep_time            This tuning parameter controls the maximum sleep
+                              time for the garbage collection thread. Time is
+                              in milliseconds.
+
+ gc_min_sleep_time            This tuning parameter controls the minimum sleep
+                              time for the garbage collection thread. Time is
+                              in milliseconds.
+
+ gc_no_gc_sleep_time          This tuning parameter controls the default sleep
+                              time for the garbage collection thread. Time is
+                              in milliseconds.
+
+ gc_idle                      This parameter controls the selection of victim
+                              policy for garbage collection. Setting gc_idle = 0
+                              (default) will disable this option. Setting
+                              gc_idle = 1 will select the Cost Benefit approach
+                              & setting gc_idle = 2 will select the greedy aproach.
+
+================================================================================
 USAGE
 ================================================================================
 
@@ -149,8 +181,12 @@ USAGE
  # mkfs.f2fs -l label /dev/block_device
  # mount -t f2fs /dev/block_device /mnt/f2fs
 
-Format options
---------------
+mkfs.f2fs
+---------
+The mkfs.f2fs is for the use of formatting a partition as the f2fs filesystem,
+which builds a basic on-disk layout.
+
+The options consist of:
 -l [label]   : Give a volume label, up to 512 unicode name.
 -a [0 or 1]  : Split start location of each area for heap-based allocation.
                1 is set by default, which performs this.
@@ -164,6 +200,37 @@ Format options
 -t [0 or 1]  : Disable discard command or not.
                1 is set by default, which conducts discard.
 
+fsck.f2fs
+---------
+The fsck.f2fs is a tool to check the consistency of an f2fs-formatted
+partition, which examines whether the filesystem metadata and user-made data
+are cross-referenced correctly or not.
+Note that, initial version of the tool does not fix any inconsistency.
+
+The options consist of:
+  -d debug level [default:0]
+
+dump.f2fs
+---------
+The dump.f2fs shows the information of specific inode and dumps SSA and SIT to
+file. Each file is dump_ssa and dump_sit.
+
+The dump.f2fs is used to debug on-disk data structures of the f2fs filesystem.
+It shows on-disk inode information reconized by a given inode number, and is
+able to dump all the SSA and SIT entries into predefined files, ./dump_ssa and
+./dump_sit respectively.
+
+The options consist of:
+  -d debug level [default:0]
+  -i inode no (hex)
+  -s [SIT dump segno from #1~#2 (decimal), for all 0~-1]
+  -a [SSA dump segno from #1~#2 (decimal), for all 0~-1]
+
+Examples:
+# dump.f2fs -i [ino] /dev/sdx
+# dump.f2fs -s 0~-1 /dev/sdx (SIT dump)
+# dump.f2fs -a 0~-1 /dev/sdx (SSA dump)
+
 ================================================================================
 DESIGN
 ================================================================================
diff --git a/Documentation/filesystems/nfs/Exporting b/Documentation/filesystems/nfs/Exporting
index 09994c247289..e543b1a619cc 100644
--- a/Documentation/filesystems/nfs/Exporting
+++ b/Documentation/filesystems/nfs/Exporting
@@ -93,7 +93,7 @@ For a filesystem to be exportable it must:
    2/ make sure that d_splice_alias is used rather than d_add
       when ->lookup finds an inode for a given parent and name.
 
-      If inode is NULL, d_splice_alias(inode, dentry) is eqivalent to
+      If inode is NULL, d_splice_alias(inode, dentry) is equivalent to
 
 		d_add(dentry, inode), NULL
 
diff --git a/Documentation/filesystems/nfs/pnfs.txt b/Documentation/filesystems/nfs/pnfs.txt
index 52ae07f5f578..adc81a35fe2d 100644
--- a/Documentation/filesystems/nfs/pnfs.txt
+++ b/Documentation/filesystems/nfs/pnfs.txt
@@ -12,7 +12,7 @@ struct pnfs_layout_hdr
 ----------------------
 The on-the-wire command LAYOUTGET corresponds to struct
 pnfs_layout_segment, usually referred to by the variable name lseg.
-Each nfs_inode may hold a pointer to a cache of of these layout
+Each nfs_inode may hold a pointer to a cache of these layout
 segments in nfsi->layout, of type struct pnfs_layout_hdr.
 
 We reference the header for the inode pointing to it, across each
diff --git a/Documentation/filesystems/porting b/Documentation/filesystems/porting
index 206a1bdc7321..f0890581f7f6 100644
--- a/Documentation/filesystems/porting
+++ b/Documentation/filesystems/porting
@@ -451,3 +451,7 @@ in your dentry operations instead.
 --
 [mandatory]
 	->readdir() is gone now; switch to ->iterate()
+[mandatory]
+	vfs_follow_link has been removed.  Filesystems must use nd_set_link
+	from ->follow_link for normal symlinks, or nd_jump_link for magic
+	/proc/<pid> style links.
diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index fcc22c982a25..823c95faebd2 100644
--- a/Documentation/filesystems/proc.txt
+++ b/Documentation/filesystems/proc.txt
@@ -854,16 +854,15 @@ Committed_AS: The amount of memory presently allocated on the system.
               The committed memory is a sum of all of the memory which
               has been allocated by processes, even if it has not been
               "used" by them as of yet. A process which malloc()'s 1G
-              of memory, but only touches 300M of it will only show up
-              as using 300M of memory even if it has the address space
-              allocated for the entire 1G. This 1G is memory which has
-              been "committed" to by the VM and can be used at any time
-              by the allocating application. With strict overcommit
-              enabled on the system (mode 2 in 'vm.overcommit_memory'),
-              allocations which would exceed the CommitLimit (detailed
-              above) will not be permitted. This is useful if one needs
-              to guarantee that processes will not fail due to lack of
-              memory once that memory has been successfully allocated.
+              of memory, but only touches 300M of it will show up as
+	      using 1G. This 1G is memory which has been "committed" to
+              by the VM and can be used at any time by the allocating
+              application. With strict overcommit enabled on the system
+              (mode 2 in 'vm.overcommit_memory'),allocations which would
+              exceed the CommitLimit (detailed above) will not be permitted.
+              This is useful if one needs to guarantee that processes will
+              not fail due to lack of memory once that memory has been
+              successfully allocated.
 VmallocTotal: total size of vmalloc memory area
  VmallocUsed: amount of vmalloc area which is used
 VmallocChunk: largest contiguous block of vmalloc area which is free
diff --git a/Documentation/filesystems/qnx6.txt b/Documentation/filesystems/qnx6.txt
index 99e90184a72f..408679789136 100644
--- a/Documentation/filesystems/qnx6.txt
+++ b/Documentation/filesystems/qnx6.txt
@@ -149,7 +149,7 @@ Bitmap system area
 ------------------
 
 The bitmap itself is divided into three parts.
-First the system area, that is split into two halfs.
+First the system area, that is split into two halves.
 Then userspace.
 
 The requirement for a static, fixed preallocated system area comes from how
diff --git a/Documentation/filesystems/ramfs-rootfs-initramfs.txt b/Documentation/filesystems/ramfs-rootfs-initramfs.txt
index 59b4a0962e0f..b176928e6963 100644
--- a/Documentation/filesystems/ramfs-rootfs-initramfs.txt
+++ b/Documentation/filesystems/ramfs-rootfs-initramfs.txt
@@ -79,6 +79,10 @@ to just make sure certain lists can't become empty.
 Most systems just mount another filesystem over rootfs and ignore it.  The
 amount of space an empty instance of ramfs takes up is tiny.
 
+If CONFIG_TMPFS is enabled, rootfs will use tmpfs instead of ramfs by
+default.  To force ramfs, add "rootfstype=ramfs" to the kernel command
+line.
+
 What is initramfs?
 ------------------
 
diff --git a/Documentation/filesystems/relay.txt b/Documentation/filesystems/relay.txt
index 510b722667ac..33e2f3694733 100644
--- a/Documentation/filesystems/relay.txt
+++ b/Documentation/filesystems/relay.txt
@@ -31,7 +31,7 @@ Semantics
 
 Each relay channel has one buffer per CPU, each buffer has one or more
 sub-buffers.  Messages are written to the first sub-buffer until it is
-too full to contain a new message, in which case it it is written to
+too full to contain a new message, in which case it is written to
 the next (if available).  Messages are never split across sub-buffers.
 At this point, userspace can be notified so it empties the first
 sub-buffer, while the kernel continues writing to the next.
diff --git a/Documentation/filesystems/sysfs-tagging.txt b/Documentation/filesystems/sysfs-tagging.txt
index caaaf1266d8f..eb843e49c5a3 100644
--- a/Documentation/filesystems/sysfs-tagging.txt
+++ b/Documentation/filesystems/sysfs-tagging.txt
@@ -24,7 +24,7 @@ flag between KOBJ_NS_TYPE_NONE and KOBJ_NS_TYPES, and s_ns will
 point to the namespace to which it belongs.
 
 Each sysfs superblock's sysfs_super_info contains an array void
-*ns[KOBJ_NS_TYPES].  When a a task in a tagging namespace
+*ns[KOBJ_NS_TYPES].  When a task in a tagging namespace
 kobj_nstype first mounts sysfs, a new superblock is created.  It
 will be differentiated from other sysfs mounts by having its
 s_fs_info->ns[kobj_nstype] set to the new namespace.  Note that
diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt
index f93a88250a44..deb48b5fd883 100644
--- a/Documentation/filesystems/vfs.txt
+++ b/Documentation/filesystems/vfs.txt
@@ -359,11 +359,9 @@ struct inode_operations {
 	ssize_t (*listxattr) (struct dentry *, char *, size_t);
 	int (*removexattr) (struct dentry *, const char *);
 	void (*update_time)(struct inode *, struct timespec *, int);
-	int (*atomic_open)(struct inode *, struct dentry *,
+	int (*atomic_open)(struct inode *, struct dentry *, struct file *,
+			unsigned open_flag, umode_t create_mode, int *opened);
 	int (*tmpfile) (struct inode *, struct dentry *, umode_t);
-} ____cacheline_aligned;
-				struct file *, unsigned open_flag,
-				umode_t create_mode, int *opened);
 };
 
 Again, all methods are called without any locks being held, unless
@@ -470,9 +468,11 @@ otherwise noted.
   	method the filesystem can look up, possibly create and open the file in
   	one atomic operation.  If it cannot perform this (e.g. the file type
   	turned out to be wrong) it may signal this by returning 1 instead of
-  	usual 0 or -ve .  This method is only called if the last
-  	component is negative or needs lookup.  Cached positive dentries are
-  	still handled by f_op->open().
+	usual 0 or -ve .  This method is only called if the last component is
+	negative or needs lookup.  Cached positive dentries are still handled by
+	f_op->open().  If the file was created, the FILE_CREATED flag should be
+	set in "opened".  In case of O_EXCL the method must only succeed if the
+	file didn't exist and hence FILE_CREATED shall always be set on success.
 
   tmpfile: called in the end of O_TMPFILE open().  Optional, equivalent to
 	atomically creating, opening and unlinking a file in given directory.
diff --git a/Documentation/filesystems/xfs.txt b/Documentation/filesystems/xfs.txt
index 12525b17d9ed..5be51fd888bd 100644
--- a/Documentation/filesystems/xfs.txt
+++ b/Documentation/filesystems/xfs.txt
@@ -135,7 +135,7 @@ default behaviour.
 	If the memory cost of 8 log buffers is too high on small
 	systems, then it may be reduced at some cost to performance
 	on metadata intensive workloads. The logbsize option below
-	controls the size of each buffer and so is also relevent to
+	controls the size of each buffer and so is also relevant to
 	this case.
 
   logbsize=value
diff --git a/Documentation/fmc/carrier.txt b/Documentation/fmc/carrier.txt
index 173f6d65c88d..5e4f1dd3e98b 100644
--- a/Documentation/fmc/carrier.txt
+++ b/Documentation/fmc/carrier.txt
@@ -213,7 +213,7 @@ The individual methods perform the following tasks:
      methods: for example the SPEC driver may define that its carrier
      I2C memory is seen at offset 1M and the internal SPI flash is seen
      at offset 16M.  This multiplexing of several flash memories in the
-     same address space is is carrier-specific and should only be used
+     same address space is carrier-specific and should only be used
      by a driver that has verified the `carrier_name' field.
 
 
diff --git a/Documentation/hid/uhid.txt b/Documentation/hid/uhid.txt
index 3c741214dfbb..dc35a2b75eee 100644
--- a/Documentation/hid/uhid.txt
+++ b/Documentation/hid/uhid.txt
@@ -149,11 +149,13 @@ needs. Only UHID_OUTPUT and UHID_OUTPUT_EV have payloads.
   is of type "struct uhid_data_req".
   This may be received even though you haven't received UHID_OPEN, yet.
 
-  UHID_OUTPUT_EV:
+  UHID_OUTPUT_EV (obsolete):
   Same as UHID_OUTPUT but this contains a "struct input_event" as payload. This
   is called for force-feedback, LED or similar events which are received through
   an input device by the HID subsystem. You should convert this into raw reports
   and send them to your device similar to events of type UHID_OUTPUT.
+  This is no longer sent by newer kernels. Instead, HID core converts it into a
+  raw output report and sends it via UHID_OUTPUT.
 
   UHID_FEATURE:
   This event is sent if the kernel driver wants to perform a feature request as
diff --git a/Documentation/hwmon/abituguru-datasheet b/Documentation/hwmon/abituguru-datasheet
index 8d2be8a0b1e3..86c0b1251c81 100644
--- a/Documentation/hwmon/abituguru-datasheet
+++ b/Documentation/hwmon/abituguru-datasheet
@@ -299,7 +299,7 @@ Byte 1:
 min threshold (scale as bank 0x26)
 
 
-Warning for the adventerous
+Warning for the adventurous
 ===========================
 
 A word of caution to those who want to experiment and see if they can figure
diff --git a/Documentation/hwmon/ads1015 b/Documentation/hwmon/ads1015
index f6fe9c203733..063b80d857b1 100644
--- a/Documentation/hwmon/ads1015
+++ b/Documentation/hwmon/ads1015
@@ -6,6 +6,10 @@ Supported chips:
     Prefix: 'ads1015'
     Datasheet: Publicly available at the Texas Instruments website :
                http://focus.ti.com/lit/ds/symlink/ads1015.pdf
+  * Texas Instruments ADS1115
+    Prefix: 'ads1115'
+    Datasheet: Publicly available at the Texas Instruments website :
+               http://focus.ti.com/lit/ds/symlink/ads1115.pdf
 
 Authors:
         Dirk Eibach, Guntermann & Drunck GmbH <eibach@gdsys.de>
@@ -13,9 +17,9 @@ Authors:
 Description
 -----------
 
-This driver implements support for the Texas Instruments ADS1015.
+This driver implements support for the Texas Instruments ADS1015/ADS1115.
 
-This device is a 12-bit A-D converter with 4 inputs.
+This device is a 12/16-bit A-D converter with 4 inputs.
 
 The inputs can be used single ended or in certain differential combinations.
 
diff --git a/Documentation/hwmon/htu21 b/Documentation/hwmon/htu21
new file mode 100644
index 000000000000..f39a215fb6ae
--- /dev/null
+++ b/Documentation/hwmon/htu21
@@ -0,0 +1,46 @@
+Kernel driver htu21
+===================
+
+Supported chips:
+  * Measurement Specialties HTU21D
+    Prefix: 'htu21'
+    Addresses scanned: none
+    Datasheet: Publicly available at the Measurement Specialties website
+    http://www.meas-spec.com/downloads/HTU21D.pdf
+
+
+Author:
+  William Markezana <william.markezana@meas-spec.com>
+
+Description
+-----------
+
+The HTU21D is a humidity and temperature sensor in a DFN package of
+only 3 x 3 mm footprint and 0.9 mm height.
+
+The devices communicate with the I2C protocol. All sensors are set to the
+same I2C address 0x40, so an entry with I2C_BOARD_INFO("htu21", 0x40) can
+be used in the board setup code.
+
+This driver does not auto-detect devices. You will have to instantiate the
+devices explicitly. Please see Documentation/i2c/instantiating-devices
+for details.
+
+sysfs-Interface
+---------------
+
+temp1_input - temperature input
+humidity1_input - humidity input
+
+Notes
+-----
+
+The driver uses the default resolution settings of 12 bit for humidity and 14
+bit for temperature, which results in typical measurement times of 11 ms for
+humidity and 44 ms for temperature. To keep self heating below 0.1 degree
+Celsius, the device should not be active for more than 10% of the time. For
+this reason, the driver performs no more than two measurements per second and
+reports cached information if polled more frequently.
+
+Different resolutions, the on-chip heater, using the CRC checksum and reading
+the serial number are not supported yet.
diff --git a/Documentation/hwmon/k10temp b/Documentation/hwmon/k10temp
index 90956b618025..4dfdc8f83633 100644
--- a/Documentation/hwmon/k10temp
+++ b/Documentation/hwmon/k10temp
@@ -12,6 +12,7 @@ Supported chips:
 * AMD Family 12h processors: "Llano" (E2/A4/A6/A8-Series)
 * AMD Family 14h processors: "Brazos" (C/E/G/Z-Series)
 * AMD Family 15h processors: "Bulldozer" (FX-Series), "Trinity"
+* AMD Family 16h processors: "Kabini"
 
   Prefix: 'k10temp'
   Addresses scanned: PCI space
diff --git a/Documentation/hwmon/submitting-patches b/Documentation/hwmon/submitting-patches
index 46286460462b..3d1bac399a22 100644
--- a/Documentation/hwmon/submitting-patches
+++ b/Documentation/hwmon/submitting-patches
@@ -1,7 +1,7 @@
 	How to Get Your Patch Accepted Into the Hwmon Subsystem
 	-------------------------------------------------------
 
-This text is is a collection of suggestions for people writing patches or
+This text is a collection of suggestions for people writing patches or
 drivers for the hwmon subsystem. Following these suggestions will greatly
 increase the chances of your change being accepted.
 
diff --git a/Documentation/hwmon/w83791d b/Documentation/hwmon/w83791d
index 90387c3540f7..f4021a285460 100644
--- a/Documentation/hwmon/w83791d
+++ b/Documentation/hwmon/w83791d
@@ -17,7 +17,7 @@ Credits:
     Philip Edelbrock <phil@netroedge.com>,
     and Mark Studebaker <mdsxyz123@yahoo.com>
   w83792d.c:
-    Chunhao Huang <DZShen@Winbond.com.tw>,
+    Shane Huang (Winbond),
     Rudolf Marek <r.marek@assembler.cz>
 
 Additional contributors:
diff --git a/Documentation/hwmon/w83792d b/Documentation/hwmon/w83792d
index 8a023ce0b72e..53f7b6866fec 100644
--- a/Documentation/hwmon/w83792d
+++ b/Documentation/hwmon/w83792d
@@ -7,8 +7,7 @@ Supported chips:
     Addresses scanned: I2C 0x2c - 0x2f
     Datasheet: http://www.winbond.com.tw
 
-Author: Chunhao Huang
-Contact: DZShen <DZShen@Winbond.com.tw>
+Author: Shane Huang (Winbond)
 
 
 Module Parameters
diff --git a/Documentation/hwspinlock.txt b/Documentation/hwspinlock.txt
index a903ee5e9776..62f7d4ea6e26 100644
--- a/Documentation/hwspinlock.txt
+++ b/Documentation/hwspinlock.txt
@@ -241,7 +241,7 @@ int hwspinlock_example2(void)
      locks).
      Should be called from a process context (this function might sleep).
      Returns the address of hwspinlock on success, or NULL on error (e.g.
-     if the hwspinlock is sill in use).
+     if the hwspinlock is still in use).
 
 5. Important structs
 
diff --git a/Documentation/i2c/busses/i2c-piix4 b/Documentation/i2c/busses/i2c-piix4
index a370b2047cf3..c097e0f020fe 100644
--- a/Documentation/i2c/busses/i2c-piix4
+++ b/Documentation/i2c/busses/i2c-piix4
@@ -73,9 +73,10 @@ this driver on those mainboards.
 The ServerWorks Southbridges, the Intel 440MX, and the Victory66 are
 identical to the PIIX4 in I2C/SMBus support.
 
-The AMD SB700 and SP5100 chipsets implement two PIIX4-compatible SMBus
-controllers. If your BIOS initializes the secondary controller, it will
-be detected by this driver as an "Auxiliary SMBus Host Controller".
+The AMD SB700, SB800, SP5100 and Hudson-2 chipsets implement two
+PIIX4-compatible SMBus controllers. If your BIOS initializes the
+secondary controller, it will be detected by this driver as
+an "Auxiliary SMBus Host Controller".
 
 If you own Force CPCI735 motherboard or other OSB4 based systems you may need
 to change the SMBus Interrupt Select register so the SMBus controller uses
diff --git a/Documentation/i2c/instantiating-devices b/Documentation/i2c/instantiating-devices
index 22182660dda7..c70e7a7638d1 100644
--- a/Documentation/i2c/instantiating-devices
+++ b/Documentation/i2c/instantiating-devices
@@ -19,7 +19,7 @@ i2c_board_info which is registered by calling i2c_register_board_info().
 
 Example (from omap2 h4):
 
-static struct i2c_board_info __initdata h4_i2c_board_info[] = {
+static struct i2c_board_info h4_i2c_board_info[] __initdata = {
 	{
 		I2C_BOARD_INFO("isp1301_omap", 0x2d),
 		.irq		= OMAP_GPIO_IRQ(125),
diff --git a/Documentation/i2c/upgrading-clients b/Documentation/i2c/upgrading-clients
index d6991625c407..8e5fbd88c7d1 100644
--- a/Documentation/i2c/upgrading-clients
+++ b/Documentation/i2c/upgrading-clients
@@ -196,8 +196,8 @@ static int example_probe(struct i2c_client *i2c_client,
 
 Update the detach method, by changing the name to _remove and
 to delete the i2c_detach_client call. It is possible that you
-can also remove the ret variable as it is not not needed for
-any of the core functions.
+can also remove the ret variable as it is not needed for any
+of the core functions.
 
 - static int example_detach(struct i2c_client *client)
 + static int example_remove(struct i2c_client *client)
diff --git a/Documentation/input/gamepad.txt b/Documentation/input/gamepad.txt
new file mode 100644
index 000000000000..8002c894c6b0
--- /dev/null
+++ b/Documentation/input/gamepad.txt
@@ -0,0 +1,156 @@
+                            Linux Gamepad API
+----------------------------------------------------------------------------
+
+1. Intro
+~~~~~~~~
+Linux provides many different input drivers for gamepad hardware. To avoid
+having user-space deal with different button-mappings for each gamepad, this
+document defines how gamepads are supposed to report their data.
+
+2. Geometry
+~~~~~~~~~~~
+As "gamepad" we define devices which roughly look like this:
+
+            ____________________________              __
+           / [__ZL__]          [__ZR__] \               |
+          / [__ TL __]        [__ TR __] \              | Front Triggers
+       __/________________________________\__         __|
+      /                                  _   \          |
+     /      /\           __             (N)   \         |
+    /       ||      __  |MO|  __     _       _ \        | Main Pad
+   |    <===DP===> |SE|      |ST|   (W) -|- (E) |       |
+    \       ||    ___          ___       _     /        |
+    /\      \/   /   \        /   \     (S)   /\      __|
+   /  \________ | LS  | ____ |  RS | ________/  \       |
+  |         /  \ \___/ /    \ \___/ /  \         |      | Control Sticks
+  |        /    \_____/      \_____/    \        |    __|
+  |       /                              \       |
+   \_____/                                \_____/
+
+       |________|______|    |______|___________|
+         D-Pad    Left       Right   Action Pad
+                 Stick       Stick
+
+                   |_____________|
+                      Menu Pad
+
+Most gamepads have the following features:
+  - Action-Pad
+    4 buttons in diamonds-shape (on the right side). The buttons are
+    differently labeled on most devices so we define them as NORTH,
+    SOUTH, WEST and EAST.
+  - D-Pad (Direction-pad)
+    4 buttons (on the left side) that point up, down, left and right.
+  - Menu-Pad
+    Different constellations, but most-times 2 buttons: SELECT - START
+    Furthermore, many gamepads have a fancy branded button that is used as
+    special system-button. It often looks different to the other buttons and
+    is used to pop up system-menus or system-settings.
+  - Analog-Sticks
+    Analog-sticks provide freely moveable sticks to control directions. Not
+    all devices have both or any, but they are present at most times.
+    Analog-sticks may also provide a digital button if you press them.
+  - Triggers
+    Triggers are located on the upper-side of the pad in vertical direction.
+    Not all devices provide them, but the upper buttons are normally named
+    Left- and Right-Triggers, the lower buttons Z-Left and Z-Right.
+  - Rumble
+    Many devices provide force-feedback features. But are mostly just
+    simple rumble motors.
+
+3. Detection
+~~~~~~~~~~~~
+All gamepads that follow the protocol described here map BTN_GAMEPAD. This is
+an alias for BTN_SOUTH/BTN_A. It can be used to identify a gamepad as such.
+However, not all gamepads provide all features, so you need to test for all
+features that you need, first. How each feature is mapped is described below.
+
+Legacy drivers often don't comply to these rules. As we cannot change them
+for backwards-compatibility reasons, you need to provide fixup mappings in
+user-space yourself. Some of them might also provide module-options that
+change the mappings so you can adivce users to set these.
+
+All new gamepads are supposed to comply with this mapping. Please report any
+bugs, if they don't.
+
+There are a lot of less-featured/less-powerful devices out there, which re-use
+the buttons from this protocol. However, they try to do this in a compatible
+fashion. For example, the "Nintendo Wii Nunchuk" provides two trigger buttons
+and one analog stick. It reports them as if it were a gamepad with only one
+analog stick and two trigger buttons on the right side.
+But that means, that if you only support "real" gamepads, you must test
+devices for _all_ reported events that you need. Otherwise, you will also get
+devices that report a small subset of the events.
+
+No other devices, that do not look/feel like a gamepad, shall report these
+events.
+
+4. Events
+~~~~~~~~~
+Gamepads report the following events:
+
+Action-Pad:
+  Every gamepad device has at least 2 action buttons. This means, that every
+  device reports BTN_SOUTH (which BTN_GAMEPAD is an alias for). Regardless
+  of the labels on the buttons, the codes are sent according to the
+  physical position of the buttons.
+  Please note that 2- and 3-button pads are fairly rare and old. You might
+  want to filter gamepads that do not report all four.
+    2-Button Pad:
+      If only 2 action-buttons are present, they are reported as BTN_SOUTH and
+      BTN_EAST. For vertical layouts, the upper button is BTN_EAST. For
+      horizontal layouts, the button more on the right is BTN_EAST.
+    3-Button Pad:
+      If only 3 action-buttons are present, they are reported as (from left
+      to right): BTN_WEST, BTN_SOUTH, BTN_EAST
+      If the buttons are aligned perfectly vertically, they are reported as
+      (from top down): BTN_WEST, BTN_SOUTH, BTN_EAST
+    4-Button Pad:
+      If all 4 action-buttons are present, they can be aligned in two
+      different formations. If diamond-shaped, they are reported as BTN_NORTH,
+      BTN_WEST, BTN_SOUTH, BTN_EAST according to their physical location.
+      If rectangular-shaped, the upper-left button is BTN_NORTH, lower-left
+      is BTN_WEST, lower-right is BTN_SOUTH and upper-right is BTN_EAST.
+
+D-Pad:
+  Every gamepad provides a D-Pad with four directions: Up, Down, Left, Right
+  Some of these are available as digital buttons, some as analog buttons. Some
+  may even report both. The kernel does not convert between these so
+  applications should support both and choose what is more appropriate if
+  both are reported.
+    Digital buttons are reported as:
+      BTN_DPAD_*
+    Analog buttons are reported as:
+      ABS_HAT0X and ABS_HAT0Y
+
+Analog-Sticks:
+  The left analog-stick is reported as ABS_X, ABS_Y. The right analog stick is
+  reported as ABS_RX, ABS_RY. Zero, one or two sticks may be present.
+  If analog-sticks provide digital buttons, they are mapped accordingly as
+  BTN_THUMBL (first/left) and BTN_THUMBR (second/right).
+
+Triggers:
+  Trigger buttons can be available as digital or analog buttons or both. User-
+  space must correctly deal with any situation and choose the most appropriate
+  mode.
+  Upper trigger buttons are reported as BTN_TR or ABS_HAT1X (right) and BTN_TL
+  or ABS_HAT1Y (left). Lower trigger buttons are reported as BTN_TR2 or
+  ABS_HAT2X (right/ZR) and BTN_TL2 or ABS_HAT2Y (left/ZL).
+  If only one trigger-button combination is present (upper+lower), they are
+  reported as "right" triggers (BTN_TR/ABS_HAT1X).
+
+Menu-Pad:
+  Menu buttons are always digital and are mapped according to their location
+  instead of their labels. That is:
+    1-button Pad: Mapped as BTN_START
+    2-button Pad: Left button mapped as BTN_SELECT, right button mapped as
+                  BTN_START
+  Many pads also have a third button which is branded or has a special symbol
+  and meaning. Such buttons are mapped as BTN_MODE. Examples are the Nintendo
+  "HOME" button, the XBox "X"-button or Sony "P" button.
+
+Rumble:
+  Rumble is adverticed as FF_RUMBLE.
+
+----------------------------------------------------------------------------
+  Written 2013 by David Herrmann <dh.herrmann@gmail.com>
diff --git a/Documentation/kbuild/kconfig-language.txt b/Documentation/kbuild/kconfig-language.txt
index c858f8419eba..c420676c6fe3 100644
--- a/Documentation/kbuild/kconfig-language.txt
+++ b/Documentation/kbuild/kconfig-language.txt
@@ -147,6 +147,7 @@ applicable everywhere (see syntax).
   - "modules"
     This declares the symbol to be used as the MODULES symbol, which
     enables the third modular state for all config symbols.
+    At most one symbol may have the "modules" option set.
 
   - "env"=<value>
     This imports the environment variable into Kconfig. It behaves like
diff --git a/Documentation/kbuild/kconfig.txt b/Documentation/kbuild/kconfig.txt
index e349f293cc98..8ef6dbb6a462 100644
--- a/Documentation/kbuild/kconfig.txt
+++ b/Documentation/kbuild/kconfig.txt
@@ -175,11 +175,9 @@ Searching in menuconfig:
 		/^hotplug
 
 	When searching, symbols are sorted thus:
-	  - exact match first: an exact match is when the search matches
-	    the complete symbol name;
-	  - alphabetical order: when two symbols do not match exactly,
-	    they are sorted in alphabetical order (in the user's current
-	    locale).
+	  - first, exact matches, sorted alphabetically (an exact match
+	    is when the search matches the complete symbol name);
+	  - then, other matches, sorted alphabetically.
 	For example: ^ATH.K matches:
 	    ATH5K ATH9K ATH5K_AHB ATH5K_DEBUG [...] ATH6KL ATH6KL_DEBUG
 	    [...] ATH9K_AHB ATH9K_BTCOEX_SUPPORT ATH9K_COMMON [...]
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 7f9d4f53882c..fcbb736d55fe 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -235,10 +235,61 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			Format: To spoof as Windows 98: ="Microsoft Windows"
 
 	acpi_osi=	[HW,ACPI] Modify list of supported OS interface strings
-			acpi_osi="string1"	# add string1 -- only one string
-			acpi_osi="!string2"	# remove built-in string2
+			acpi_osi="string1"	# add string1
+			acpi_osi="!string2"	# remove string2
+			acpi_osi=!*		# remove all strings
+			acpi_osi=!		# disable all built-in OS vendor
+						  strings
 			acpi_osi=		# disable all strings
 
+			'acpi_osi=!' can be used in combination with single or
+			multiple 'acpi_osi="string1"' to support specific OS
+			vendor string(s).  Note that such command can only
+			affect the default state of the OS vendor strings, thus
+			it cannot affect the default state of the feature group
+			strings and the current state of the OS vendor strings,
+			specifying it multiple times through kernel command line
+			is meaningless.  This command is useful when one do not
+			care about the state of the feature group strings which
+			should be controlled by the OSPM.
+			Examples:
+			  1. 'acpi_osi=! acpi_osi="Windows 2000"' is equivalent
+			     to 'acpi_osi="Windows 2000" acpi_osi=!', they all
+			     can make '_OSI("Windows 2000")' TRUE.
+
+			'acpi_osi=' cannot be used in combination with other
+			'acpi_osi=' command lines, the _OSI method will not
+			exist in the ACPI namespace.  NOTE that such command can
+			only affect the _OSI support state, thus specifying it
+			multiple times through kernel command line is also
+			meaningless.
+			Examples:
+			  1. 'acpi_osi=' can make 'CondRefOf(_OSI, Local1)'
+			     FALSE.
+
+			'acpi_osi=!*' can be used in combination with single or
+			multiple 'acpi_osi="string1"' to support specific
+			string(s).  Note that such command can affect the
+			current state of both the OS vendor strings and the
+			feature group strings, thus specifying it multiple times
+			through kernel command line is meaningful.  But it may
+			still not able to affect the final state of a string if
+			there are quirks related to this string.  This command
+			is useful when one want to control the state of the
+			feature group strings to debug BIOS issues related to
+			the OSPM features.
+			Examples:
+			  1. 'acpi_osi="Module Device" acpi_osi=!*' can make
+			     '_OSI("Module Device")' FALSE.
+			  2. 'acpi_osi=!* acpi_osi="Module Device"' can make
+			     '_OSI("Module Device")' TRUE.
+			  3. 'acpi_osi=! acpi_osi=!* acpi_osi="Windows 2000"' is
+			     equivalent to
+			     'acpi_osi=!* acpi_osi=! acpi_osi="Windows 2000"'
+			     and
+			     'acpi_osi=!* acpi_osi="Windows 2000" acpi_osi=!',
+			     they all will make '_OSI("Windows 2000")' TRUE.
+
 	acpi_pm_good	[X86]
 			Override the pmtimer bug detection: force the kernel
 			to assume that this machine's pmtimer latches its value
@@ -429,6 +480,10 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			Format: <io>,<irq>,<mode>
 			See header of drivers/net/hamradio/baycom_ser_hdx.c.
 
+	blkdevparts=	Manual partition parsing of block device(s) for
+			embedded devices based on command line input.
+			See Documentation/block/cmdline-partition.txt
+
 	boot_delay=	Milliseconds to delay each printk during boot.
 			Values larger than 10 seconds (10000) are changed to
 			no delay (0).
@@ -1306,7 +1361,7 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			pages. In the event, a node is too small to have both
 			kernelcore and Movable pages, kernelcore pages will
 			take priority and other nodes will have a larger number
-			of kernelcore pages.  The Movable zone is used for the
+			of Movable pages.  The Movable zone is used for the
 			allocation of pages that may be reclaimed or moved
 			by the page migration subsystem.  This means that
 			HugeTLB pages may not be allocated from this zone.
@@ -1847,6 +1902,18 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			will be sent.
 			The default is to send the implementation identification
 			information.
+	
+	nfs.recover_lost_locks =
+			[NFSv4] Attempt to recover locks that were lost due
+			to a lease timeout on the server. Please note that
+			doing this risks data corruption, since there are
+			no guarantees that the file will remain unchanged
+			after the locks are lost.
+			If you want to enable the kernel legacy behaviour of
+			attempting to recover these locks, then set this
+			parameter to '1'.
+			The default parameter value of '0' causes the kernel
+			not to attempt recovery of lost locks.
 
 	nfsd.nfs4_disable_idmapping=
 			[NFSv4] When set to the default of '1', the NFSv4
@@ -3322,6 +3389,10 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			            them quite hard to use for exploits but
 			            might break your system.
 
+	vt.color=	[VT] Default text color.
+			Format: 0xYX, X = foreground, Y = background.
+			Default: 0x07 = light gray on black.
+
 	vt.cur_default=	[VT] Default cursor shape.
 			Format: 0xCCBBAA, where AA, BB, and CC are the same as
 			the parameters of the <Esc>[?A;B;Cc escape sequence;
@@ -3361,6 +3432,12 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			overridden by individual drivers. 0 will hide
 			cursors, 1 will display them.
 
+	vt.italic=	[VT] Default color for italic text; 0-15.
+			Default: 2 = green.
+
+	vt.underline=	[VT] Default color for underlined text; 0-15.
+			Default: 3 = cyan.
+
 	watchdog timers	[HW,WDT] For information on watchdog timers,
 			see Documentation/watchdog/watchdog-parameters.txt
 			or other driver-specific files in the
@@ -3412,6 +3489,10 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 				the unplug protocol
 			never -- do not unplug even if version check succeeds
 
+	xen_nopvspin	[X86,XEN]
+			Disables the ticketlock slowpath using Xen PV
+			optimizations.
+
 	xirc2ps_cs=	[NET,PCMCIA]
 			Format:
 			<irq>,<irq_mask>,<io>,<full_duplex>,<do_sound>,<lockup_hack>[,<irq2>[,<irq3>[,<irq4>]]]
diff --git a/Documentation/kmemcheck.txt b/Documentation/kmemcheck.txt
index c28f82895d6b..9398a501fdb9 100644
--- a/Documentation/kmemcheck.txt
+++ b/Documentation/kmemcheck.txt
@@ -91,9 +91,9 @@ information from the kmemcheck warnings, which is extremely valuable in
 debugging a problem. This option is not mandatory, however, because it slows
 down the compilation process and produces a much bigger kernel image.
 
-Now the kmemcheck menu should be visible (under "Kernel hacking" / "kmemcheck:
-trap use of uninitialized memory"). Here follows a description of the
-kmemcheck configuration variables:
+Now the kmemcheck menu should be visible (under "Kernel hacking" / "Memory
+Debugging" / "kmemcheck: trap use of uninitialized memory"). Here follows
+a description of the kmemcheck configuration variables:
 
   o CONFIG_KMEMCHECK
 
diff --git a/Documentation/ko_KR/HOWTO b/Documentation/ko_KR/HOWTO
index 2f48f205fedc..680e64635958 100644
--- a/Documentation/ko_KR/HOWTO
+++ b/Documentation/ko_KR/HOWTO
@@ -182,8 +182,8 @@ Documentation/DocBook/ 디렉토리 내에서 만들어지며 PDF, Postscript, H
 프로젝트를 봐야 한다.
     http://kernelnewbies.org
 그곳은 거의 모든 종류의 기본적인 커널 개발 질문들(질문하기 전에 먼저
-아카이브를 찾아봐라. 과거에 이미 답변되었을 수도 있다)을 할수있는 도움이
-될만한 메일링 리스트가 있다. 또한 실시간으로 질문 할수 있는 IRC 채널도
+아카이브를 찾아봐라. 과거에 이미 답변되었을 수도 있다)을 할 수 있는 도움이
+될만한 메일링 리스트가 있다. 또한 실시간으로 질문 할 수 있는 IRC 채널도
 가지고 있으며 리눅스 커널 개발을 배우는 데 유용한 문서들을 보유하고 있다.
 
 웹사이트는 코드구성, 서브시스템들, 그리고 현재 프로젝트들
@@ -245,7 +245,7 @@ Documentation/DocBook/ 디렉토리 내에서 만들어지며 PDF, Postscript, H
     것을 기억해라. 왜냐하면 변경이 자체내에서만 발생하고 추가된 코드가
     드라이버 외부의 다른 부분에는 영향을 주지 않으므로 그런 변경은
     회귀(역자주: 이전에는 존재하지 않았지만 새로운 기능추가나 변경으로 인해
-		생겨난 버그)를 일으킬 만한 위험을 가지고 있지 않기 때문이다. -rc1이
+    생겨난 버그)를 일으킬 만한 위험을 가지고 있지 않기 때문이다. -rc1이
     배포된 이후에 git를 사용하여 패치들을 Linus에게 보낼수 있지만 패치들은
     공식적인 메일링 리스트로 보내서 검토를 받을 필요가 있다.
   - 새로운 -rc는 Linus가 현재 git tree가 테스트 하기에 충분히 안정된 상태에
@@ -455,7 +455,7 @@ bugme-janitor 메일링 리스트(bugzilla에 모든 변화들이 여기서 메�
  - 의견
  - 변경을 위한 요구
  - 당위성을 위한 요구
- - 고요
+ - 침묵
 
 기억하라. 이것들은 여러분의 패치가 커널로 들어가기 위한 과정이다. 여러분의
 패치들은 비판과 다른 의견을 받을 수 있고 그것들을 기술적인 레벨로 평가하고
@@ -472,7 +472,7 @@ bugme-janitor 메일링 리스트(bugzilla에 모든 변화들이 여기서 메�
 가능한한 가장 좋은 기술적인 해답을 찾고 있는 커뮤니티에서는 항상
 어떤 패치가 얼마나 좋은지에 관하여 다른 의견들이 있을 수 있다. 여러분은
 협조적이어야 하고 기꺼이 여러분의 생각을 커널 내에 맞추어야 한다. 아니면
-적어도 여러분의 것이 가치있다는 것을 중명하여야 한다. 잘못된 것도 여러분이
+적어도 여러분의 것이 가치있다는 것을 증명하여야 한다. 잘못된 것도 여러분이
 올바른 방향의 해결책으로 이끌어갈 의지가 있다면 받아들여질 것이라는 점을
 기억하라.
 
@@ -488,21 +488,21 @@ bugme-janitor 메일링 리스트(bugzilla에 모든 변화들이 여기서 메�
 커널 커뮤니티는 가장 전통적인 회사의 개발 환경과는 다르다. 여기에 여러분들의
 문제를 피하기 위한 목록이 있다.
   여러분들이 제안한 변경들에 관하여 말할 때 좋은 것들 :
-    - "이것은 여러 문제들을 해겹합니다."
-    - "이것은 2000 라인의 코드를 제거합니다."
+    - "이것은 여러 문제들을 해결합니다."
+    - "이것은 2000 라인의 코드를 줄입니다."
     - "이것은 내가 말하려는 것에 관해 설명하는 패치입니다."
-    - "나는 5개의 다른 아키텍쳐에서 그것을 테스트했슴으로..."
-    - "여기에 일련의 작은 패치들이 있슴음로..."
-    - "이것은 일반적인 머신에서 성능을 향상시킴으로..."
+    - "나는 5개의 다른 아키텍쳐에서 그것을 테스트 했으므로..."
+    - "여기에 일련의 작은 패치들이 있으므로..."
+    - "이것은 일반적인 머신에서 성능을 향상함으로..."
 
   여러분들이 말할 때 피해야 할 좋지 않은 것들 :
-    - "우리를 그것을 AIT/ptx/Solaris에서 이러한 방법으로 했다. 그러므로 그것은 좋은 것임에 틀립없다..."
+    - "우리는 그것을 AIX/ptx/Solaris에서 이러한 방법으로 했다. 그러므로 그것은 좋은 것임에 틀림없다..."
     - "나는 20년동안 이것을 해왔다. 그러므로..."
     - "이것은 돈을 벌기위해 나의 회사가 필요로 하는 것이다."
     - "이것은 우리의 엔터프라이즈 상품 라인을 위한 것이다."
     - "여기에 나의 생각을 말하고 있는 1000 페이지 설계 문서가 있다."
     - "나는 6달동안 이것을 했으니..."
-    - "여기에 5000라인 짜리 패치가 있으니..."
+    - "여기에 5000 라인 짜리 패치가 있으니..."
     - "나는 현재 뒤죽박죽인 것을 재작성했다. 그리고 여기에..."
     - "나는 마감시한을 가지고 있으므로 이 패치는 지금 적용될 필요가 있다."
 
@@ -574,6 +574,7 @@ Pat이라는 이름을 가진 여자가 있을 수도 있는 것이다. 리눅�
 또한 완성되지 않았고 "나중에 수정될 것이다." 와 같은 것들을 포함하는
 패치들은 받아들여지지 않을 것이라는 점을 유념하라.
 
+
 변경을 정당화해라
 -----------------
 
diff --git a/Documentation/ko_KR/stable_api_nonsense.txt b/Documentation/ko_KR/stable_api_nonsense.txt
index 8f2b0e1d98c4..51f85ade4190 100644
--- a/Documentation/ko_KR/stable_api_nonsense.txt
+++ b/Documentation/ko_KR/stable_api_nonsense.txt
@@ -106,12 +106,12 @@ Greg Kroah-Hartman <greg@kroah.com>
 ---------------------------------
 
 리눅스 커널 드라이버를 계속해서 메인 커널 트리에 반영하지 않고
-유지보수하려고 하는 사름들과 이 문제를 논의하게 되면 훨씬 더
+유지보수하려고 하는 사람들과 이 문제를 논의하게 되면 훨씬 더
 "논란의 여지가 많은" 주제가 될 것이다.
 
 리눅스 커널 개발은 끊임없이 빠른 속도로 이루어지고 있으며 결코
 느슨해진 적이 없다. 커널 개발자들이 현재 인터페이스들에서 버그를
-발견하거나 무엇인가 할수 있는 더 좋은 방법을 찾게 되었다고 하자.
+발견하거나 무엇인가 할 수 있는 더 좋은 방법을 찾게 되었다고 하자.
 그들이 발견한 것을 실행한다면 아마도 더 잘 동작하도록 현재 인터페이스들을
 수정하게 될 것이다. 그들이 그런 일을 하게되면 함수 이름들은 변하게 되고,
 구조체들은 늘어나거나 줄어들게 되고, 함수 파라미터들은 재작업될 것이다.
@@ -174,7 +174,7 @@ GPL을 따르는 배포 드라이버에 관해 얘기하고 있다는 것을 상
 동작하는 것을 보장한다.
 
 메인 커널 트리에 여러분의 드라이버를 반영하면 얻게 되는 장점들은 다음과 같다.
-   - 관리의 드는 비용(원래 개발자의)은 줄어줄면서 드라이버의 질은 향상될 것이다.
+   - 관리에 드는 비용(원래 개발자의)은 줄어줄면서 드라이버의 질은 향상될 것이다.
    - 다른 개발자들이 여러분의 드라이버에 기능들을 추가 할 것이다.
    - 다른 사람들은 여러분의 드라이버에 버그를 발견하고 수정할 것이다.
    - 다른 사람들은 여러분의 드라이버의 개선점을 찾을 줄 것이다.
diff --git a/Documentation/laptops/asus-laptop.txt b/Documentation/laptops/asus-laptop.txt
index 69f9fb3701e0..79a1bc675a8d 100644
--- a/Documentation/laptops/asus-laptop.txt
+++ b/Documentation/laptops/asus-laptop.txt
@@ -8,8 +8,8 @@ http://acpi4asus.sf.net/
 
  This driver provides support for extra features of ACPI-compatible ASUS laptops.
  It may also support some MEDION, JVC or VICTOR laptops (such as MEDION 9675 or
- VICTOR XP7210 for example). It makes all the extra buttons generate standard
- ACPI events that go through /proc/acpi/events and input events (like keyboards).
+ VICTOR XP7210 for example). It makes all the extra buttons generate input
+ events (like keyboards).
  On some models adds support for changing the display brightness and output,
  switching the LCD backlight on and off, and most importantly, allows you to
  blink those fancy LEDs intended for reporting mail and wireless status.
@@ -55,8 +55,8 @@ Usage
   DSDT) to me.
 
   That's all, now, all the events generated by the hotkeys of your laptop
-  should be reported in your /proc/acpi/event entry. You can check with
-  "acpi_listen".
+  should be reported via netlink events. You can check with
+  "acpi_genl monitor" (part of the acpica project).
 
   Hotkeys are also reported as input keys (like keyboards) you can check
   which key are supported using "xev" under X11.
diff --git a/Documentation/laptops/sony-laptop.txt b/Documentation/laptops/sony-laptop.txt
index 0d5ac7f5287e..978b1e615155 100644
--- a/Documentation/laptops/sony-laptop.txt
+++ b/Documentation/laptops/sony-laptop.txt
@@ -12,10 +12,10 @@ Fn keys (hotkeys):
 ------------------
 Some models report hotkeys through the SNC or SPIC devices, such events are
 reported both through the ACPI subsystem as acpi events and through the INPUT
-subsystem. See the logs of acpid or /proc/acpi/event and
-/proc/bus/input/devices to find out what those events are and which input
-devices are created by the driver. Additionally, loading the driver with the
-debug option will report all events in the kernel log.
+subsystem. See the logs of /proc/bus/input/devices to find out what those
+events are and which input devices are created by the driver.
+Additionally, loading the driver with the debug option will report all events
+in the kernel log.
 
 The "scancodes" passed to the input system (that can be remapped with udev)
 are indexes to the table "sony_laptop_input_keycode_map" in the sony-laptop.c
diff --git a/Documentation/laptops/thinkpad-acpi.txt b/Documentation/laptops/thinkpad-acpi.txt
index cf7bc6cb9719..86c52360ffe7 100644
--- a/Documentation/laptops/thinkpad-acpi.txt
+++ b/Documentation/laptops/thinkpad-acpi.txt
@@ -329,20 +329,6 @@ sysfs notes:
 
 		This attribute has poll()/select() support.
 
-	hotkey_report_mode:
-		Returns the state of the procfs ACPI event report mode
-		filter for hot keys.  If it is set to 1 (the default),
-		all hot key presses are reported both through the input
-		layer and also as ACPI events through procfs (but not
-		through netlink).  If it is set to 2, hot key presses
-		are reported only through the input layer.
-
-		This attribute is read-only in kernels 2.6.23 or later,
-		and read-write on earlier kernels.
-
-		May return -EPERM (write access locked out by module
-		parameter) or -EACCES (read-only).
-
 	wakeup_reason:
 		Set to 1 if the system is waking up because the user
 		requested a bay ejection.  Set to 2 if the system is
@@ -518,24 +504,21 @@ SW_TABLET_MODE	Tablet ThinkPads HKEY events 0x5009 and 0x500A
 Non hotkey ACPI HKEY event map:
 -------------------------------
 
-Events that are not propagated by the driver, except for legacy
-compatibility purposes when hotkey_report_mode is set to 1:
-
-0x5001		Lid closed
-0x5002		Lid opened
-0x5009		Tablet swivel: switched to tablet mode
-0x500A		Tablet swivel: switched to normal mode
-0x7000		Radio Switch may have changed state
-
 Events that are never propagated by the driver:
 
 0x2304		System is waking up from suspend to undock
 0x2305		System is waking up from suspend to eject bay
 0x2404		System is waking up from hibernation to undock
 0x2405		System is waking up from hibernation to eject bay
+0x5001		Lid closed
+0x5002		Lid opened
+0x5009		Tablet swivel: switched to tablet mode
+0x500A		Tablet swivel: switched to normal mode
 0x5010		Brightness level changed/control event
 0x6000		KEYBOARD: Numlock key pressed
 0x6005		KEYBOARD: Fn key pressed (TO BE VERIFIED)
+0x7000		Radio Switch may have changed state
+
 
 Events that are propagated by the driver to userspace:
 
@@ -574,50 +557,6 @@ operating system is to force either an immediate suspend or hibernate
 cycle, or a system shutdown.  Obviously, something is very wrong if this
 happens.
 
-Compatibility notes:
-
-ibm-acpi and thinkpad-acpi 0.15 (mainline kernels before 2.6.23) never
-supported the input layer, and sent events over the procfs ACPI event
-interface.
-
-To avoid sending duplicate events over the input layer and the ACPI
-event interface, thinkpad-acpi 0.16 implements a module parameter
-(hotkey_report_mode), and also a sysfs device attribute with the same
-name.
-
-Make no mistake here: userspace is expected to switch to using the input
-layer interface of thinkpad-acpi, together with the ACPI netlink event
-interface in kernels 2.6.23 and later, or with the ACPI procfs event
-interface in kernels 2.6.22 and earlier.
-
-If no hotkey_report_mode module parameter is specified (or it is set to
-zero), the driver defaults to mode 1 (see below), and on kernels 2.6.22
-and earlier, also allows one to change the hotkey_report_mode through
-sysfs.  In kernels 2.6.23 and later, where the netlink ACPI event
-interface is available, hotkey_report_mode cannot be changed through
-sysfs (it is read-only).
-
-If the hotkey_report_mode module parameter is set to 1 or 2, it cannot
-be changed later through sysfs (any writes will return -EPERM to signal
-that hotkey_report_mode was locked.  On 2.6.23 and later, where
-hotkey_report_mode cannot be changed at all, writes will return -EACCES).
-
-hotkey_report_mode set to 1 makes the driver export through the procfs
-ACPI event interface all hot key presses (which are *also* sent to the
-input layer).  This is a legacy compatibility behaviour, and it is also
-the default mode of operation for the driver.
-
-hotkey_report_mode set to 2 makes the driver filter out the hot key
-presses from the procfs ACPI event interface, so these events will only
-be sent through the input layer.  Userspace that has been updated to use
-the thinkpad-acpi input layer interface should set hotkey_report_mode to
-2.
-
-Hot key press events are never sent to the ACPI netlink event interface.
-Really up-to-date userspace under kernel 2.6.23 and later is to use the
-netlink interface and the input layer interface, and don't bother at all
-with hotkey_report_mode.
-
 
 Brightness hotkey notes:
 
diff --git a/Documentation/leds/leds-lm3556.txt b/Documentation/leds/leds-lm3556.txt
index d9eb91b51913..62278e871b50 100644
--- a/Documentation/leds/leds-lm3556.txt
+++ b/Documentation/leds/leds-lm3556.txt
@@ -71,7 +71,7 @@ To register the chip at address 0x63 on specific adapter, set the platform data
 according to include/linux/platform_data/leds-lm3556.h, set the i2c board info
 
 Example:
-	static struct i2c_board_info __initdata board_i2c_ch4[]	= {
+	static struct i2c_board_info board_i2c_ch4[] __initdata = {
 		{
 			 I2C_BOARD_INFO(LM3556_NAME, 0x63),
 			 .platform_data = &lm3556_pdata,
diff --git a/Documentation/leds/leds-lp3944.txt b/Documentation/leds/leds-lp3944.txt
index c6eda18b15ef..e88ac3b60c08 100644
--- a/Documentation/leds/leds-lp3944.txt
+++ b/Documentation/leds/leds-lp3944.txt
@@ -37,7 +37,7 @@ registered using the i2c_board_info mechanism.
 To register the chip at address 0x60 on adapter 0, set the platform data
 according to include/linux/leds-lp3944.h, set the i2c board info:
 
-	static struct i2c_board_info __initdata a910_i2c_board_info[] = {
+	static struct i2c_board_info a910_i2c_board_info[] __initdata = {
 		{
 			I2C_BOARD_INFO("lp3944", 0x60),
 			.platform_data = &a910_lp3944_leds,
diff --git a/Documentation/leds/leds-lp5521.txt b/Documentation/leds/leds-lp5521.txt
index 79e4c2e6e5e8..d08d8c179f85 100644
--- a/Documentation/leds/leds-lp5521.txt
+++ b/Documentation/leds/leds-lp5521.txt
@@ -18,7 +18,25 @@ All three channels can be also controlled using the engine micro programs.
 More details of the instructions can be found from the public data sheet.
 
 LP5521 has the internal program memory for running various LED patterns.
-For the details, please refer to 'firmware' section in leds-lp55xx.txt
+There are two ways to run LED patterns.
+
+1) Legacy interface - enginex_mode and enginex_load
+  Control interface for the engines:
+  x is 1 .. 3
+  enginex_mode : disabled, load, run
+  enginex_load : store program (visible only in engine load mode)
+
+  Example (start to blink the channel 2 led):
+  cd   /sys/class/leds/lp5521:channel2/device
+  echo "load" > engine3_mode
+  echo "037f4d0003ff6000" > engine3_load
+  echo "run" > engine3_mode
+
+  To stop the engine:
+  echo "disabled" > engine3_mode
+
+2) Firmware interface - LP55xx common interface
+  For the details, please refer to 'firmware' section in leds-lp55xx.txt
 
 sysfs contains a selftest entry.
 The test communicates with the chip and checks that
diff --git a/Documentation/leds/leds-lp5523.txt b/Documentation/leds/leds-lp5523.txt
index 899fdad509fe..5b3e91d4ac59 100644
--- a/Documentation/leds/leds-lp5523.txt
+++ b/Documentation/leds/leds-lp5523.txt
@@ -28,7 +28,26 @@ If both fields are NULL, 'lp5523' is used by default.
 /sys/class/leds/lp5523:channelN  (N: 0 ~ 8)
 
 LP5523 has the internal program memory for running various LED patterns.
-For the details, please refer to 'firmware' section in leds-lp55xx.txt
+There are two ways to run LED patterns.
+
+1) Legacy interface - enginex_mode, enginex_load and enginex_leds
+  Control interface for the engines:
+  x is 1 .. 3
+  enginex_mode : disabled, load, run
+  enginex_load : microcode load (visible only in load mode)
+  enginex_leds : led mux control (visible only in load mode)
+
+  cd /sys/class/leds/lp5523:channel2/device
+  echo "load" > engine3_mode
+  echo "9d80400004ff05ff437f0000" > engine3_load
+  echo "111111111" > engine3_leds
+  echo "run" > engine3_mode
+
+  To stop the engine:
+  echo "disabled" > engine3_mode
+
+2) Firmware interface - LP55xx common interface
+  For the details, please refer to 'firmware' section in leds-lp55xx.txt
 
 Selftest uses always the current from the platform data.
 
diff --git a/Documentation/leds/leds-lp55xx.txt b/Documentation/leds/leds-lp55xx.txt
index eec8fa2ffe4e..82713ff92eb3 100644
--- a/Documentation/leds/leds-lp55xx.txt
+++ b/Documentation/leds/leds-lp55xx.txt
@@ -1,11 +1,11 @@
-LP5521/LP5523/LP55231 Common Driver
-===================================
+LP5521/LP5523/LP55231/LP5562/LP8501 Common Driver
+=================================================
 
 Authors: Milo(Woogyom) Kim <milo.kim@ti.com>
 
 Description
 -----------
-LP5521, LP5523/55231 and LP5562 have common features as below.
+LP5521, LP5523/55231, LP5562 and LP8501 have common features as below.
 
   Register access via the I2C
   Device initialization/deinitialization
@@ -109,6 +109,30 @@ As soon as 'loading' is set to 0, registered callback is called.
 Inside the callback, the selected engine is loaded and memory is updated.
 To run programmed pattern, 'run_engine' attribute should be enabled.
 
+The pattern sqeuence of LP8501 is same as LP5523.
+However pattern data is specific.
+Ex 1) Engine 1 is used
+echo 1 > /sys/bus/i2c/devices/xxxx/select_engine
+echo 1 > /sys/class/firmware/lp8501/loading
+echo "9d0140ff7e0040007e00a001c000" > /sys/class/firmware/lp8501/data
+echo 0 > /sys/class/firmware/lp8501/loading
+echo 1 > /sys/bus/i2c/devices/xxxx/run_engine
+
+Ex 2) Engine 2 and 3 are used at the same time
+echo 2 > /sys/bus/i2c/devices/xxxx/select_engine
+sleep 1
+echo 1 > /sys/class/firmware/lp8501/loading
+echo "9d0140ff7e0040007e00a001c000" > /sys/class/firmware/lp8501/data
+echo 0 > /sys/class/firmware/lp8501/loading
+sleep 1
+echo 3 > /sys/bus/i2c/devices/xxxx/select_engine
+sleep 1
+echo 1 > /sys/class/firmware/lp8501/loading
+echo "9d0340ff7e0040007e00a001c000" > /sys/class/firmware/lp8501/data
+echo 0 > /sys/class/firmware/lp8501/loading
+sleep 1
+echo 1 > /sys/class/leds/d1/device/run_engine
+
 ( 'run_engine' and 'firmware_cb' )
 The sequence of running the program data is common.
 But each device has own specific register addresses for commands.
diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt
index fa5d8a9ae205..c8c42e64e953 100644
--- a/Documentation/memory-barriers.txt
+++ b/Documentation/memory-barriers.txt
@@ -531,9 +531,10 @@ dependency barrier to make it work correctly.  Consider the following bit of
 code:
 
 	q = &a;
-	if (p)
+	if (p) {
+		<data dependency barrier>
 		q = &b;
-	<data dependency barrier>
+	}
 	x = *q;
 
 This will not have the desired effect because there is no actual data
@@ -542,9 +543,10 @@ attempting to predict the outcome in advance.  In such a case what's actually
 required is:
 
 	q = &a;
-	if (p)
+	if (p) {
+		<read barrier>
 		q = &b;
-	<read barrier>
+	}
 	x = *q;
 
 
diff --git a/Documentation/memory-hotplug.txt b/Documentation/memory-hotplug.txt
index 8e5eacbdcfa3..58340d50f8a6 100644
--- a/Documentation/memory-hotplug.txt
+++ b/Documentation/memory-hotplug.txt
@@ -163,7 +163,7 @@ a recent addition and not present on older kernels.
                     at read:  contains online/offline state of memory.
                     at write: user can specify "online_kernel",
                     "online_movable", "online", "offline" command
-                    which will be performed on al sections in the block.
+                    which will be performed on all sections in the block.
 'phys_device'     : read-only: designed to show the name of physical memory
                     device.  This is not well implemented now.
 'removable'       : read-only: contains an integer value indicating
@@ -210,13 +210,15 @@ If memory device is found, memory hotplug code will be called.
 
 4.2 Notify memory hot-add event by hand
 ------------
-In some environments, especially virtualized environment, firmware will not
-notify memory hotplug event to the kernel. For such environment, "probe"
-interface is supported. This interface depends on CONFIG_ARCH_MEMORY_PROBE.
-
-Now, CONFIG_ARCH_MEMORY_PROBE is supported only by powerpc but it does not
-contain highly architecture codes. Please add config if you need "probe"
-interface.
+On powerpc, the firmware does not notify a memory hotplug event to the kernel.
+Therefore, "probe" interface is supported to notify the event to the kernel.
+This interface depends on CONFIG_ARCH_MEMORY_PROBE.
+
+CONFIG_ARCH_MEMORY_PROBE is supported on powerpc only. On x86, this config
+option is disabled by default since ACPI notifies a memory hotplug event to
+the kernel, which performs its hotplug operation as the result. Please
+enable this option if you need the "probe" interface for testing purposes
+on x86.
 
 Probe interface is located at
 /sys/devices/system/memory/probe
diff --git a/Documentation/mtd/nand_ecc.txt b/Documentation/mtd/nand_ecc.txt
index 990efd7a9818..e129b2479ea8 100644
--- a/Documentation/mtd/nand_ecc.txt
+++ b/Documentation/mtd/nand_ecc.txt
@@ -543,7 +543,7 @@ THe code within the for loop was changed to:
     }
 
 As you can see tmppar is used to accumulate the parity within a for
-iteration. In the last 3 statements is is added to par and, if needed,
+iteration. In the last 3 statements is added to par and, if needed,
 to rp12 and rp14.
 
 While making the changes I also found that I could exploit that tmppar
diff --git a/Documentation/networking/00-INDEX b/Documentation/networking/00-INDEX
index 32dfbd924121..f11580f8719a 100644
--- a/Documentation/networking/00-INDEX
+++ b/Documentation/networking/00-INDEX
@@ -86,6 +86,8 @@ generic_netlink.txt
 	- info on Generic Netlink
 gianfar.txt
 	- Gianfar Ethernet Driver.
+i40e.txt
+	- README for the Intel Ethernet Controller XL710 Driver (i40e).
 ieee802154.txt
 	- Linux IEEE 802.15.4 implementation, API and drivers
 igb.txt
@@ -124,6 +126,8 @@ multiqueue.txt
 	- HOWTO for multiqueue network device support.
 netconsole.txt
 	- The network console module netconsole.ko: configuration and notes.
+netdev-FAQ.txt
+	- FAQ describing how to submit net changes to netdev mailing list.
 netdev-features.txt
 	- Network interface features API description.
 netdevices.txt
diff --git a/Documentation/networking/bonding.txt b/Documentation/networking/bonding.txt
index 87bbcfee2e06..9b28e714831a 100644
--- a/Documentation/networking/bonding.txt
+++ b/Documentation/networking/bonding.txt
@@ -1362,6 +1362,12 @@ To add ARP targets:
 To remove an ARP target:
 # echo -192.168.0.100 > /sys/class/net/bond0/bonding/arp_ip_target
 
+To configure the interval between learning packet transmits:
+# echo 12 > /sys/class/net/bond0/bonding/lp_interval
+	NOTE: the lp_inteval is the number of seconds between instances where
+the bonding driver sends learning packets to each slaves peer switch.  The
+default interval is 1 second.
+
 Example Configuration
 ---------------------
 	We begin with the same example that is shown in section 3.3,
diff --git a/Documentation/networking/e100.txt b/Documentation/networking/e100.txt
index fcb6c71cdb69..13a32124bca0 100644
--- a/Documentation/networking/e100.txt
+++ b/Documentation/networking/e100.txt
@@ -1,7 +1,7 @@
 Linux* Base Driver for the Intel(R) PRO/100 Family of Adapters
 ==============================================================
 
-November 15, 2005
+March 15, 2011
 
 Contents
 ========
@@ -122,7 +122,7 @@ Additional Configurations
   NOTE: This setting is not saved across reboots.
 
 
-  Ethtool
+  ethtool
   -------
 
   The driver utilizes the ethtool interface for driver configuration and
diff --git a/Documentation/networking/e1000.txt b/Documentation/networking/e1000.txt
index 71ca95855671..437b2099cced 100644
--- a/Documentation/networking/e1000.txt
+++ b/Documentation/networking/e1000.txt
@@ -1,8 +1,8 @@
-Linux* Base Driver for the Intel(R) PRO/1000 Family of Adapters
-===============================================================
+Linux* Base Driver for Intel(R) Ethernet Network Connection
+===========================================================
 
 Intel Gigabit Linux driver.
-Copyright(c) 1999 - 2010 Intel Corporation.
+Copyright(c) 1999 - 2013 Intel Corporation.
 
 Contents
 ========
@@ -420,15 +420,15 @@ Additional Configurations
   - The maximum MTU setting for Jumbo Frames is 16110.  This value coincides
     with the maximum Jumbo Frames size of 16128.
 
-  - Using Jumbo Frames at 10 or 100 Mbps may result in poor performance or
-    loss of link.
+  - Using Jumbo frames at 10 or 100 Mbps is not supported and may result in
+    poor performance or loss of link.
 
   - Adapters based on the Intel(R) 82542 and 82573V/E controller do not
     support Jumbo Frames. These correspond to the following product names:
      Intel(R) PRO/1000 Gigabit Server Adapter
      Intel(R) PRO/1000 PM Network Connection
 
-  Ethtool
+  ethtool
   -------
   The driver utilizes the ethtool interface for driver configuration and
   diagnostics, as well as displaying statistical information.  The ethtool
diff --git a/Documentation/networking/e1000e.txt b/Documentation/networking/e1000e.txt
index 97b5ba942ebf..ad2d9f38ce14 100644
--- a/Documentation/networking/e1000e.txt
+++ b/Documentation/networking/e1000e.txt
@@ -1,8 +1,8 @@
-Linux* Driver for Intel(R) Network Connection
-=============================================
+Linux* Driver for Intel(R) Ethernet Network Connection
+======================================================
 
 Intel Gigabit Linux driver.
-Copyright(c) 1999 - 2010 Intel Corporation.
+Copyright(c) 1999 - 2013 Intel Corporation.
 
 Contents
 ========
@@ -259,13 +259,16 @@ Additional Configurations
   - The maximum MTU setting for Jumbo Frames is 9216.  This value coincides
     with the maximum Jumbo Frames size of 9234 bytes.
 
-  - Using Jumbo Frames at 10 or 100 Mbps is not supported and may result in
+  - Using Jumbo frames at 10 or 100 Mbps is not supported and may result in
     poor performance or loss of link.
 
   - Some adapters limit Jumbo Frames sized packets to a maximum of
     4096 bytes and some adapters do not support Jumbo Frames.
 
-  Ethtool
+  - Jumbo Frames cannot be configured on an 82579-based Network device, if
+    MACSec is enabled on the system.
+
+  ethtool
   -------
   The driver utilizes the ethtool interface for driver configuration and
   diagnostics, as well as displaying statistical information.  We
@@ -273,6 +276,9 @@ Additional Configurations
 
   http://ftp.kernel.org/pub/software/network/ethtool/
 
+  NOTE: When validating enable/disable tests on some parts (82578, for example)
+  you need to add a few seconds between tests when working with ethtool.
+
   Speed and Duplex
   ----------------
   Speed and Duplex are configured through the ethtool* utility. For
diff --git a/Documentation/networking/i40e.txt b/Documentation/networking/i40e.txt
new file mode 100644
index 000000000000..f737273c6dc1
--- /dev/null
+++ b/Documentation/networking/i40e.txt
@@ -0,0 +1,115 @@
+Linux Base Driver for the Intel(R) Ethernet Controller XL710 Family
+===================================================================
+
+Intel i40e Linux driver.
+Copyright(c) 2013 Intel Corporation.
+
+Contents
+========
+
+- Identifying Your Adapter
+- Additional Configurations
+- Performance Tuning
+- Known Issues
+- Support
+
+
+Identifying Your Adapter
+========================
+
+The driver in this release is compatible with the Intel Ethernet
+Controller XL710 Family.
+
+For more information on how to identify your adapter, go to the Adapter &
+Driver ID Guide at:
+
+    http://support.intel.com/support/network/sb/CS-012904.htm
+
+
+Enabling the driver
+===================
+
+The driver is enabled via the standard kernel configuration system,
+using the make command:
+
+     Make oldconfig/silentoldconfig/menuconfig/etc.
+
+The driver is located in the menu structure at:
+
+	-> Device Drivers
+	  -> Network device support (NETDEVICES [=y])
+	    -> Ethernet driver support
+	      -> Intel devices
+	        -> Intel(R) Ethernet Controller XL710 Family
+
+Additional Configurations
+=========================
+
+  Generic Receive Offload (GRO)
+  -----------------------------
+  The driver supports the in-kernel software implementation of GRO.  GRO has
+  shown that by coalescing Rx traffic into larger chunks of data, CPU
+  utilization can be significantly reduced when under large Rx load.  GRO is
+  an evolution of the previously-used LRO interface.  GRO is able to coalesce
+  other protocols besides TCP.  It's also safe to use with configurations that
+  are problematic for LRO, namely bridging and iSCSI.
+
+  Ethtool
+  -------
+  The driver utilizes the ethtool interface for driver configuration and
+  diagnostics, as well as displaying statistical information. The latest
+  ethtool version is required for this functionality.
+
+  The latest release of ethtool can be found from
+  https://www.kernel.org/pub/software/network/ethtool
+
+  Data Center Bridging (DCB)
+  --------------------------
+  DCB configuration is not currently supported.
+
+  FCoE
+  ----
+  Fiber Channel over Ethernet (FCoE) hardware offload is not currently
+  supported.
+
+  MAC and VLAN anti-spoofing feature
+  ----------------------------------
+  When a malicious driver attempts to send a spoofed packet, it is dropped by
+  the hardware and not transmitted.  An interrupt is sent to the PF driver
+  notifying it of the spoof attempt.
+
+  When a spoofed packet is detected the PF driver will send the following
+  message to the system log (displayed by  the "dmesg" command):
+
+  Spoof event(s) detected on VF (n)
+
+  Where n=the VF that attempted to do the spoofing.
+
+
+Performance Tuning
+==================
+
+An excellent article on performance tuning can be found at:
+
+http://www.redhat.com/promo/summit/2008/downloads/pdf/Thursday/Mark_Wagner.pdf
+
+
+Known Issues
+============
+
+
+Support
+=======
+
+For general information, go to the Intel support website at:
+
+    http://support.intel.com
+
+or the Intel Wired Networking project hosted by Sourceforge at:
+
+    http://e1000.sourceforge.net
+
+If an issue is identified with the released source code on the supported
+kernel with a supported adapter, email the specific information related
+to the issue to e1000-devel@lists.sourceforge.net and copy
+netdev@vger.kernel.org.
diff --git a/Documentation/networking/igb.txt b/Documentation/networking/igb.txt
index 9a2a037194a5..4ebbd659256f 100644
--- a/Documentation/networking/igb.txt
+++ b/Documentation/networking/igb.txt
@@ -1,8 +1,8 @@
-Linux* Base Driver for Intel(R) Network Connection
-==================================================
+Linux* Base Driver for Intel(R) Ethernet Network Connection
+===========================================================
 
 Intel Gigabit Linux driver.
-Copyright(c) 1999 - 2010 Intel Corporation.
+Copyright(c) 1999 - 2013 Intel Corporation.
 
 Contents
 ========
@@ -36,6 +36,53 @@ Default Value: 0
 This parameter adds support for SR-IOV.  It causes the driver to spawn up to
 max_vfs worth of virtual function.
 
+QueuePairs
+----------
+Valid Range:  0-1
+Default Value:  1 (TX and RX will be paired onto one interrupt vector)
+
+If set to 0, when MSI-X is enabled, the TX and RX will attempt to occupy
+separate vectors.
+
+This option can be overridden to 1 if there are not sufficient interrupts
+available.  This can occur if any combination of RSS, VMDQ, and max_vfs
+results in more than 4 queues being used.
+
+Node
+----
+Valid Range:   0-n
+Default Value: -1 (off)
+
+  0 - n: where n is the number of the NUMA node that should be used to
+         allocate memory for this adapter port.
+  -1: uses the driver default of allocating memory on whichever processor is
+      running insmod/modprobe.
+
+  The Node parameter will allow you to pick which NUMA node you want to have
+  the adapter allocate memory from.  All driver structures, in-memory queues,
+  and receive buffers will be allocated on the node specified.  This parameter
+  is only useful when interrupt affinity is specified, otherwise some portion
+  of the time the interrupt could run on a different core than the memory is
+  allocated on, causing slower memory access and impacting throughput, CPU, or
+  both.
+
+EEE
+---
+Valid Range:  0-1
+Default Value: 1 (enabled)
+
+  A link between two EEE-compliant devices will result in periodic bursts of
+  data followed by long periods where in the link is in an idle state. This Low
+  Power Idle (LPI) state is supported in both 1Gbps and 100Mbps link speeds.
+  NOTE: EEE support requires autonegotiation.
+
+DMAC
+----
+Valid Range: 0-1
+Default Value: 1 (enabled)
+  Enables or disables DMA Coalescing feature.
+
+
 
 Additional Configurations
 =========================
@@ -55,10 +102,10 @@ Additional Configurations
   - The maximum MTU setting for Jumbo Frames is 9216.  This value coincides
     with the maximum Jumbo Frames size of 9234 bytes.
 
-  - Using Jumbo Frames at 10 or 100 Mbps may result in poor performance or
-    loss of link.
+  - Using Jumbo frames at 10 or 100 Mbps is not supported and may result in
+    poor performance or loss of link.
 
-  Ethtool
+  ethtool
   -------
   The driver utilizes the ethtool interface for driver configuration and
   diagnostics, as well as displaying statistical information. The latest
@@ -106,6 +153,14 @@ Additional Configurations
 
   Where n=the VF that attempted to do the spoofing.
 
+  Setting MAC Address, VLAN and Rate Limit Using IProute2 Tool
+  ------------------------------------------------------------
+  You can set a MAC address of a Virtual Function (VF), a default VLAN and the
+  rate limit using the IProute2 tool. Download the latest version of the
+  iproute2 tool from Sourceforge if your version does not have all the
+  features you require.
+
+
 Support
 =======
 
diff --git a/Documentation/networking/igbvf.txt b/Documentation/networking/igbvf.txt
index cbfe4ee65533..40db17a6665b 100644
--- a/Documentation/networking/igbvf.txt
+++ b/Documentation/networking/igbvf.txt
@@ -1,8 +1,8 @@
-Linux* Base Driver for Intel(R) Network Connection
-==================================================
+Linux* Base Driver for Intel(R) Ethernet Network Connection
+===========================================================
 
 Intel Gigabit Linux driver.
-Copyright(c) 1999 - 2010 Intel Corporation.
+Copyright(c) 1999 - 2013 Intel Corporation.
 
 Contents
 ========
@@ -55,7 +55,7 @@ networking link on the left to search for your adapter:
 Additional Configurations
 =========================
 
-  Ethtool
+  ethtool
   -------
   The driver utilizes the ethtool interface for driver configuration and
   diagnostics, as well as displaying statistical information.  The ethtool
diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index 10742902146f..a46d78583ae1 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -440,6 +440,10 @@ tcp_syncookies - BOOLEAN
 	SYN flood warnings in logs not being really flooded, your server
 	is seriously misconfigured.
 
+	If you want to test which effects syncookies have to your
+	network connections you can set this knob to 2 to enable
+	unconditionally generation of syncookies.
+
 tcp_fastopen - INTEGER
 	Enable TCP Fast Open feature (draft-ietf-tcpm-fastopen) to send data
 	in the opening SYN packet. To use this feature, the client application
@@ -478,6 +482,15 @@ tcp_syn_retries - INTEGER
 tcp_timestamps - BOOLEAN
 	Enable timestamps as defined in RFC1323.
 
+tcp_min_tso_segs - INTEGER
+	Minimal number of segments per TSO frame.
+	Since linux-3.12, TCP does an automatic sizing of TSO frames,
+	depending on flow rate, instead of filling 64Kbytes packets.
+	For specific usages, it's possible to force TCP to build big
+	TSO frames. Note that TCP stack might split too big TSO packets
+	if available window is too small.
+	Default: 2
+
 tcp_tso_win_divisor - INTEGER
 	This allows control over what percentage of the congestion window
 	can be consumed by a single TSO frame.
@@ -516,6 +529,19 @@ tcp_wmem - vector of 3 INTEGERs: min, default, max
 	this value is ignored.
 	Default: between 64K and 4MB, depending on RAM size.
 
+tcp_notsent_lowat - UNSIGNED INTEGER
+	A TCP socket can control the amount of unsent bytes in its write queue,
+	thanks to TCP_NOTSENT_LOWAT socket option. poll()/select()/epoll()
+	reports POLLOUT events if the amount of unsent bytes is below a per
+	socket value, and if the write queue is not full. sendmsg() will
+	also not add new buffers if the limit is hit.
+
+	This global variable controls the amount of unsent data for
+	sockets not using TCP_NOTSENT_LOWAT. For these sockets, a change
+	to the global variable has immediate effect.
+
+	Default: UINT_MAX (0xFFFFFFFF)
+
 tcp_workaround_signed_windows - BOOLEAN
 	If set, assume no receipt of a window scaling option means the
 	remote TCP is broken and treats the window as a signed quantity.
@@ -1022,7 +1048,15 @@ disable_policy - BOOLEAN
 disable_xfrm - BOOLEAN
 	Disable IPSEC encryption on this interface, whatever the policy
 
+igmpv2_unsolicited_report_interval - INTEGER
+	The interval in milliseconds in which the next unsolicited
+	IGMPv1 or IGMPv2 report retransmit will take place.
+	Default: 10000 (10 seconds)
 
+igmpv3_unsolicited_report_interval - INTEGER
+	The interval in milliseconds in which the next unsolicited
+	IGMPv3 report retransmit will take place.
+	Default: 1000 (1 seconds)
 
 tag - INTEGER
 	Allows you to write a number, which can be used as required.
@@ -1314,6 +1348,27 @@ ndisc_notify - BOOLEAN
 	1 - Generate unsolicited neighbour advertisements when device is brought
 	    up or hardware address changes.
 
+mldv1_unsolicited_report_interval - INTEGER
+	The interval in milliseconds in which the next unsolicited
+	MLDv1 report retransmit will take place.
+	Default: 10000 (10 seconds)
+
+mldv2_unsolicited_report_interval - INTEGER
+	The interval in milliseconds in which the next unsolicited
+	MLDv2 report retransmit will take place.
+	Default: 1000 (1 second)
+
+force_mld_version - INTEGER
+	0 - (default) No enforcement of a MLD version, MLDv1 fallback allowed
+	1 - Enforce to use MLD version 1
+	2 - Enforce to use MLD version 2
+
+suppress_frag_ndisc - INTEGER
+	Control RFC 6980 (Security Implications of IPv6 Fragmentation
+	with IPv6 Neighbor Discovery) behavior:
+	1 - (default) discard fragmented neighbor discovery packets
+	0 - allow fragmented neighbor discovery packets
+
 icmp/*:
 ratelimit - INTEGER
 	Limit the maximal rates for sending ICMPv6 packets.
diff --git a/Documentation/networking/ixgb.txt b/Documentation/networking/ixgb.txt
index d75a1f9565bb..1e0c045e89f7 100644
--- a/Documentation/networking/ixgb.txt
+++ b/Documentation/networking/ixgb.txt
@@ -1,7 +1,7 @@
-Linux Base Driver for 10 Gigabit Intel(R) Network Connection
-=============================================================
+Linux Base Driver for 10 Gigabit Intel(R) Ethernet Network Connection
+=====================================================================
 
-October 9, 2007
+March 14, 2011
 
 
 Contents
@@ -274,9 +274,9 @@ Additional Configurations
   -------------------------------------------------
   Configuring a network driver to load properly when the system is started is
   distribution dependent. Typically, the configuration process involves adding
-  an alias line to files in /etc/modprobe.d/ as well as editing other system
-  startup scripts and/or configuration files.  Many popular Linux distributions
-  ship with tools to make these changes for you.  To learn the proper way to
+  an alias line to /etc/modprobe.conf as well as editing other system startup
+  scripts and/or configuration files.  Many popular Linux distributions ship
+  with tools to make these changes for you.  To learn the proper way to
   configure a network device for your system, refer to your distribution
   documentation.  If during this process you are asked for the driver or module
   name, the name for the Linux Base Driver for the Intel 10GbE Family of
@@ -306,7 +306,7 @@ Additional Configurations
   with the maximum Jumbo Frames size of 16128.
 
 
-  Ethtool
+  ethtool
   -------
   The driver utilizes the ethtool interface for driver configuration and
   diagnostics, as well as displaying statistical information.  The ethtool
diff --git a/Documentation/networking/ixgbe.txt b/Documentation/networking/ixgbe.txt
index af77ed3c4172..96cccebb839b 100644
--- a/Documentation/networking/ixgbe.txt
+++ b/Documentation/networking/ixgbe.txt
@@ -1,8 +1,9 @@
-Linux Base Driver for 10 Gigabit PCI Express Intel(R) Network Connection
-========================================================================
+Linux* Base Driver for the Intel(R) Ethernet 10 Gigabit PCI Express Family of
+Adapters
+=============================================================================
 
-Intel Gigabit Linux driver.
-Copyright(c) 1999 - 2010 Intel Corporation.
+Intel 10 Gigabit Linux driver.
+Copyright(c) 1999 - 2013 Intel Corporation.
 
 Contents
 ========
@@ -16,8 +17,8 @@ Contents
 Identifying Your Adapter
 ========================
 
-The driver in this release is compatible with 82598 and 82599-based Intel
-Network Connections.
+The driver in this release is compatible with 82598, 82599 and X540-based
+Intel Network Connections.
 
 For more information on how to identify your adapter, go to the Adapter &
 Driver ID Guide at:
@@ -72,7 +73,7 @@ cables that comply with SFF-8431 v4.1 and SFF-8472 v10.4 specifications.
 Laser turns off for SFP+ when ifconfig down
 -------------------------------------------
 "ifconfig down" turns off the laser for 82599-based SFP+ fiber adapters.
-"ifconfig up" turns on the later.
+"ifconfig up" turns on the laser.
 
 
 82598-BASED ADAPTERS
@@ -118,6 +119,93 @@ NOTE: For 82598 backplane cards entering 1 gig mode, flow control default
 behavior is changed to off.  Flow control in 1 gig mode on these devices can
 lead to Tx hangs.
 
+Intel(R) Ethernet Flow Director
+-------------------------------
+Supports advanced filters that direct receive packets by their flows to
+different queues. Enables tight control on routing a flow in the platform.
+Matches flows and CPU cores for flow affinity. Supports multiple parameters
+for flexible flow classification and load balancing.
+
+Flow director is enabled only if the kernel is multiple TX queue capable.
+
+An included script (set_irq_affinity.sh) automates setting the IRQ to CPU
+affinity.
+
+You can verify that the driver is using Flow Director by looking at the counter
+in ethtool: fdir_miss and fdir_match.
+
+Other ethtool Commands:
+To enable Flow Director
+	ethtool -K ethX ntuple on
+To add a filter
+	Use -U switch. e.g., ethtool -U ethX flow-type tcp4 src-ip 0x178000a
+        action 1
+To see the list of filters currently present:
+	ethtool -u ethX
+
+Perfect Filter: Perfect filter is an interface to load the filter table that
+funnels all flow into queue_0 unless an alternative queue is specified using
+"action". In that case, any flow that matches the filter criteria will be
+directed to the appropriate queue.
+
+If the queue is defined as -1, filter will drop matching packets.
+
+To account for filter matches and misses, there are two stats in ethtool:
+fdir_match and fdir_miss. In addition, rx_queue_N_packets shows the number of
+packets processed by the Nth queue.
+
+NOTE: Receive Packet Steering (RPS) and Receive Flow Steering (RFS) are not
+compatible with Flow Director. IF Flow Director is enabled, these will be
+disabled.
+
+The following three parameters impact Flow Director.
+
+FdirMode
+--------
+Valid Range: 0-2 (0=off, 1=ATR, 2=Perfect filter mode)
+Default Value: 1
+
+  Flow Director filtering modes.
+
+FdirPballoc
+-----------
+Valid Range: 0-2 (0=64k, 1=128k, 2=256k)
+Default Value: 0
+
+  Flow Director allocated packet buffer size.
+
+AtrSampleRate
+--------------
+Valid Range: 1-100
+Default Value: 20
+
+  Software ATR Tx packet sample rate. For example, when set to 20, every 20th
+  packet, looks to see if the packet will create a new flow.
+
+Node
+----
+Valid Range:   0-n
+Default Value: 1 (off)
+
+  0 - n: where n is the number of NUMA nodes (i.e. 0 - 3) currently online in
+  your system
+  1: turns this option off
+
+  The Node parameter will allow you to pick which NUMA node you want to have
+  the adapter allocate memory on.
+
+max_vfs
+-------
+Valid Range:   1-63
+Default Value: 0
+
+  If the value is greater than 0 it will also force the VMDq parameter to be 1
+  or more.
+
+  This parameter adds support for SR-IOV.  It causes the driver to spawn up to
+  max_vfs worth of virtual function.
+
+
 Additional Configurations
 =========================
 
@@ -221,9 +309,10 @@ http://www.redhat.com/promo/summit/2008/downloads/pdf/Thursday/Mark_Wagner.pdf
 Known Issues
 ============
 
-  Enabling SR-IOV in a 32-bit Microsoft* Windows* Server 2008 Guest OS using
-  Intel (R) 82576-based GbE or Intel (R) 82599-based 10GbE controller under KVM
-  -----------------------------------------------------------------------------
+  Enabling SR-IOV in a 32-bit or 64-bit Microsoft* Windows* Server 2008/R2
+  Guest OS using Intel (R) 82576-based GbE or Intel (R) 82599-based 10GbE
+  controller under KVM
+  ------------------------------------------------------------------------
   KVM Hypervisor/VMM supports direct assignment of a PCIe device to a VM.  This
   includes traditional PCIe devices, as well as SR-IOV-capable devices using
   Intel 82576-based and 82599-based controllers.
diff --git a/Documentation/networking/ixgbevf.txt b/Documentation/networking/ixgbevf.txt
index 5a91a41fa946..53d8d2a5a6a3 100644
--- a/Documentation/networking/ixgbevf.txt
+++ b/Documentation/networking/ixgbevf.txt
@@ -1,8 +1,8 @@
-Linux* Base Driver for Intel(R) Network Connection
-==================================================
+Linux* Base Driver for Intel(R) Ethernet Network Connection
+===========================================================
 
 Intel Gigabit Linux driver.
-Copyright(c) 1999 - 2010 Intel Corporation.
+Copyright(c) 1999 - 2013 Intel Corporation.
 
 Contents
 ========
diff --git a/Documentation/networking/netdev-FAQ.txt b/Documentation/networking/netdev-FAQ.txt
new file mode 100644
index 000000000000..d9112f01c44a
--- /dev/null
+++ b/Documentation/networking/netdev-FAQ.txt
@@ -0,0 +1,224 @@
+
+Information you need to know about netdev
+-----------------------------------------
+
+Q: What is netdev?
+
+A: It is a mailing list for all network related linux stuff.  This includes
+   anything found under net/  (i.e. core code like IPv6) and drivers/net
+   (i.e. hardware specific drivers) in the linux source tree.
+
+   Note that some subsystems (e.g. wireless drivers) which have a high volume
+   of traffic have their own specific mailing lists.
+
+   The netdev list is managed (like many other linux mailing lists) through
+   VGER ( http://vger.kernel.org/ ) and archives can be found below:
+
+	http://marc.info/?l=linux-netdev
+	http://www.spinics.net/lists/netdev/
+
+   Aside from subsystems like that mentioned above, all network related linux
+   development (i.e. RFC, review, comments, etc) takes place on netdev.
+
+Q: How do the changes posted to netdev make their way into linux?
+
+A: There are always two trees (git repositories) in play.  Both are driven
+   by David Miller, the main network maintainer.  There is the "net" tree,
+   and the "net-next" tree.  As you can probably guess from the names, the
+   net tree is for fixes to existing code already in the mainline tree from
+   Linus, and net-next is where the new code goes for the future release.
+   You can find the trees here:
+
+	http://git.kernel.org/?p=linux/kernel/git/davem/net.git
+	http://git.kernel.org/?p=linux/kernel/git/davem/net-next.git
+
+Q: How often do changes from these trees make it to the mainline Linus tree?
+
+A: To understand this, you need to know a bit of background information
+   on the cadence of linux development.  Each new release starts off with
+   a two week "merge window" where the main maintainers feed their new
+   stuff to Linus for merging into the mainline tree.  After the two weeks,
+   the merge window is closed, and it is called/tagged "-rc1".  No new
+   features get mainlined after this -- only fixes to the rc1 content
+   are expected.  After roughly a week of collecting fixes to the rc1
+   content, rc2 is released.  This repeats on a roughly weekly basis
+   until rc7 (typically; sometimes rc6 if things are quiet, or rc8 if
+   things are in a state of churn), and a week after the last vX.Y-rcN
+   was done, the official "vX.Y" is released.
+
+   Relating that to netdev:  At the beginning of the 2 week merge window,
+   the net-next tree will be closed - no new changes/features.  The
+   accumulated new content of the past ~10 weeks will be passed onto
+   mainline/Linus via a pull request for vX.Y -- at the same time,
+   the "net" tree will start accumulating fixes for this pulled content
+   relating to vX.Y
+
+   An announcement indicating when net-next has been closed is usually
+   sent to netdev, but knowing the above, you can predict that in advance.
+
+   IMPORTANT:  Do not send new net-next content to netdev during the
+   period during which net-next tree is closed.
+
+   Shortly after the two weeks have passed, (and vX.Y-rc1 is released) the
+   tree for net-next reopens to collect content for the next (vX.Y+1) release.
+
+   If you aren't subscribed to netdev and/or are simply unsure if net-next
+   has re-opened yet, simply check the net-next git repository link above for
+   any new networking related commits.
+
+   The "net" tree continues to collect fixes for the vX.Y content, and
+   is fed back to Linus at regular (~weekly) intervals.  Meaning that the
+   focus for "net" is on stablilization and bugfixes.
+
+   Finally, the vX.Y gets released, and the whole cycle starts over.
+
+Q: So where are we now in this cycle?
+
+A: Load the mainline (Linus) page here:
+
+	http://git.kernel.org/?p=linux/kernel/git/torvalds/linux.git
+
+   and note the top of the "tags" section.  If it is rc1, it is early
+   in the dev cycle.  If it was tagged rc7 a week ago, then a release
+   is probably imminent.
+
+Q: How do I indicate which tree (net vs. net-next) my patch should be in?
+
+A: Firstly, think whether you have a bug fix or new "next-like" content.
+   Then once decided, assuming that you use git, use the prefix flag, i.e.
+
+	git format-patch --subject-prefix='PATCH net-next' start..finish
+
+   Use "net" instead of "net-next" (always lower case) in the above for
+   bug-fix net content.  If you don't use git, then note the only magic in
+   the above is just the subject text of the outgoing e-mail, and you can
+   manually change it yourself with whatever MUA you are comfortable with.
+
+Q: I sent a patch and I'm wondering what happened to it.  How can I tell
+   whether it got merged?
+
+A: Start by looking at the main patchworks queue for netdev:
+
+	http://patchwork.ozlabs.org/project/netdev/list/
+
+   The "State" field will tell you exactly where things are at with
+   your patch.
+
+Q: The above only says "Under Review".  How can I find out more?
+
+A: Generally speaking, the patches get triaged quickly (in less than 48h).
+   So be patient.  Asking the maintainer for status updates on your
+   patch is a good way to ensure your patch is ignored or pushed to
+   the bottom of the priority list.
+
+Q: How can I tell what patches are queued up for backporting to the
+   various stable releases?
+
+A: Normally Greg Kroah-Hartman collects stable commits himself, but
+   for networking, Dave collects up patches he deems critical for the
+   networking subsystem, and then hands them off to Greg.
+
+   There is a patchworks queue that you can see here:
+	http://patchwork.ozlabs.org/bundle/davem/stable/?state=*
+
+   It contains the patches which Dave has selected, but not yet handed
+   off to Greg.  If Greg already has the patch, then it will be here:
+	http://git.kernel.org/cgit/linux/kernel/git/stable/stable-queue.git
+
+   A quick way to find whether the patch is in this stable-queue is
+   to simply clone the repo, and then git grep the mainline commit ID, e.g.
+
+	stable-queue$ git grep -l 284041ef21fdf2e
+	releases/3.0.84/ipv6-fix-possible-crashes-in-ip6_cork_release.patch
+	releases/3.4.51/ipv6-fix-possible-crashes-in-ip6_cork_release.patch
+	releases/3.9.8/ipv6-fix-possible-crashes-in-ip6_cork_release.patch
+	stable/stable-queue$
+
+Q: I see a network patch and I think it should be backported to stable.
+   Should I request it via "stable@vger.kernel.org" like the references in
+   the kernel's Documentation/stable_kernel_rules.txt file say?
+
+A: No, not for networking.  Check the stable queues as per above 1st to see
+   if it is already queued.  If not, then send a mail to netdev, listing
+   the upstream commit ID and why you think it should be a stable candidate.
+
+   Before you jump to go do the above, do note that the normal stable rules
+   in Documentation/stable_kernel_rules.txt still apply.  So you need to
+   explicitly indicate why it is a critical fix and exactly what users are
+   impacted.  In addition, you need to convince yourself that you _really_
+   think it has been overlooked, vs. having been considered and rejected.
+
+   Generally speaking, the longer it has had a chance to "soak" in mainline,
+   the better the odds that it is an OK candidate for stable.  So scrambling
+   to request a commit be added the day after it appears should be avoided.
+
+Q: I have created a network patch and I think it should be backported to
+   stable.  Should I add a "Cc: stable@vger.kernel.org" like the references
+   in the kernel's Documentation/ directory say?
+
+A: No.  See above answer.  In short, if you think it really belongs in
+   stable, then ensure you write a decent commit log that describes who
+   gets impacted by the bugfix and how it manifests itself, and when the
+   bug was introduced.  If you do that properly, then the commit will
+   get handled appropriately and most likely get put in the patchworks
+   stable queue if it really warrants it.
+
+   If you think there is some valid information relating to it being in
+   stable that does _not_ belong in the commit log, then use the three
+   dash marker line as described in Documentation/SubmittingPatches to
+   temporarily embed that information into the patch that you send.
+
+Q: Someone said that the comment style and coding convention is different
+   for the networking content.  Is this true?
+
+A: Yes, in a largely trivial way.  Instead of this:
+
+	/*
+	 * foobar blah blah blah
+	 * another line of text
+	 */
+
+   it is requested that you make it look like this:
+
+	/* foobar blah blah blah
+	 * another line of text
+	 */
+
+Q: I am working in existing code that has the former comment style and not the
+   latter.  Should I submit new code in the former style or the latter?
+
+A: Make it the latter style, so that eventually all code in the domain of
+   netdev is of this format.
+
+Q: I found a bug that might have possible security implications or similar.
+   Should I mail the main netdev maintainer off-list?
+
+A: No. The current netdev maintainer has consistently requested that people
+   use the mailing lists and not reach out directly.  If you aren't OK with
+   that, then perhaps consider mailing "security@kernel.org" or reading about
+   http://oss-security.openwall.org/wiki/mailing-lists/distros
+   as possible alternative mechanisms.
+
+Q: What level of testing is expected before I submit my change?
+
+A: If your changes are against net-next, the expectation is that you
+   have tested by layering your changes on top of net-next.  Ideally you
+   will have done run-time testing specific to your change, but at a
+   minimum, your changes should survive an "allyesconfig" and an
+   "allmodconfig" build without new warnings or failures.
+
+Q: Any other tips to help ensure my net/net-next patch gets OK'd?
+
+A: Attention to detail.  Re-read your own work as if you were the
+   reviewer.  You can start with using checkpatch.pl, perhaps even
+   with the "--strict" flag.  But do not be mindlessly robotic in
+   doing so.  If your change is a bug-fix, make sure your commit log
+   indicates the end-user visible symptom, the underlying reason as
+   to why it happens, and then if necessary, explain why the fix proposed
+   is the best way to get things done.   Don't mangle whitespace, and as
+   is common, don't mis-indent function arguments that span multiple lines.
+   If it is your 1st patch, mail it to yourself so you can test apply
+   it to an unpatched tree to confirm infrastructure didn't mangle it.
+
+   Finally, go back and read Documentation/SubmittingPatches to be
+   sure you are not repeating some common mistake documented there.
diff --git a/Documentation/networking/openvswitch.txt b/Documentation/networking/openvswitch.txt
index 8fa2dd1e792e..37c20ee2455e 100644
--- a/Documentation/networking/openvswitch.txt
+++ b/Documentation/networking/openvswitch.txt
@@ -91,6 +91,46 @@ Often we ellipsize arguments not important to the discussion, e.g.:
     in_port(1), eth(...), eth_type(0x0800), ipv4(...), tcp(...)
 
 
+Wildcarded flow key format
+--------------------------
+
+A wildcarded flow is described with two sequences of Netlink attributes
+passed over the Netlink socket. A flow key, exactly as described above, and an
+optional corresponding flow mask.
+
+A wildcarded flow can represent a group of exact match flows. Each '1' bit
+in the mask specifies a exact match with the corresponding bit in the flow key.
+A '0' bit specifies a don't care bit, which will match either a '1' or '0' bit
+of a incoming packet. Using wildcarded flow can improve the flow set up rate
+by reduce the number of new flows need to be processed by the user space program.
+
+Support for the mask Netlink attribute is optional for both the kernel and user
+space program. The kernel can ignore the mask attribute, installing an exact
+match flow, or reduce the number of don't care bits in the kernel to less than
+what was specified by the user space program. In this case, variations in bits
+that the kernel does not implement will simply result in additional flow setups.
+The kernel module will also work with user space programs that neither support
+nor supply flow mask attributes.
+
+Since the kernel may ignore or modify wildcard bits, it can be difficult for
+the userspace program to know exactly what matches are installed. There are
+two possible approaches: reactively install flows as they miss the kernel
+flow table (and therefore not attempt to determine wildcard changes at all)
+or use the kernel's response messages to determine the installed wildcards.
+
+When interacting with userspace, the kernel should maintain the match portion
+of the key exactly as originally installed. This will provides a handle to
+identify the flow for all future operations. However, when reporting the
+mask of an installed flow, the mask should include any restrictions imposed
+by the kernel.
+
+The behavior when using overlapping wildcarded flows is undefined. It is the
+responsibility of the user space program to ensure that any incoming packet
+can match at most one flow, wildcarded or not. The current implementation
+performs best-effort detection of overlapping wildcarded flows and may reject
+some but not all of them. However, this behavior may change in future versions.
+
+
 Basic rule for evolving flow keys
 ---------------------------------
 
diff --git a/Documentation/networking/packet_mmap.txt b/Documentation/networking/packet_mmap.txt
index 8572796b1eb6..c01223628a87 100644
--- a/Documentation/networking/packet_mmap.txt
+++ b/Documentation/networking/packet_mmap.txt
@@ -543,6 +543,14 @@ TPACKET_V2 --> TPACKET_V3:
 In the AF_PACKET fanout mode, packet reception can be load balanced among
 processes. This also works in combination with mmap(2) on packet sockets.
 
+Currently implemented fanout policies are:
+
+  - PACKET_FANOUT_HASH: schedule to socket by skb's rxhash
+  - PACKET_FANOUT_LB: schedule to socket by round-robin
+  - PACKET_FANOUT_CPU: schedule to socket by CPU packet arrives on
+  - PACKET_FANOUT_RND: schedule to socket by random selection
+  - PACKET_FANOUT_ROLLOVER: if one socket is full, rollover to another
+
 Minimal example code by David S. Miller (try things like "./test eth0 hash",
 "./test eth0 lb", etc.):
 
diff --git a/Documentation/networking/sctp.txt b/Documentation/networking/sctp.txt
index 0c790a76910e..97b810ca9082 100644
--- a/Documentation/networking/sctp.txt
+++ b/Documentation/networking/sctp.txt
@@ -19,7 +19,6 @@ of SCTP that is RFC 2960 compliant and provides an programming interface
 referred to as the  UDP-style API of the Sockets Extensions for SCTP, as 
 proposed in IETF Internet-Drafts.    
 
-
 Caveats:  
 
 -lksctp can be built as statically or as a module.  However, be aware that 
@@ -33,6 +32,4 @@ For more information, please visit the lksctp project website:
    http://www.sf.net/projects/lksctp
 
 Or contact the lksctp developers through the mailing list:
-   <lksctp-developers@lists.sourceforge.net> 
-
-
+   <linux-sctp@vger.kernel.org>
diff --git a/Documentation/networking/stmmac.txt b/Documentation/networking/stmmac.txt
index 654d2e55c8cb..457b8bbafb08 100644
--- a/Documentation/networking/stmmac.txt
+++ b/Documentation/networking/stmmac.txt
@@ -123,6 +123,7 @@ struct plat_stmmacenet_data {
 	int bugged_jumbo;
 	int pmt;
 	int force_sf_dma_mode;
+	int force_thresh_dma_mode;
 	int riwt_off;
 	void (*fix_mac_speed)(void *priv, unsigned int speed);
 	void (*bus_setup)(void __iomem *ioaddr);
@@ -159,6 +160,8 @@ Where:
  o pmt: core has the embedded power module (optional).
  o force_sf_dma_mode: force DMA to use the Store and Forward mode
 		     instead of the Threshold.
+ o force_thresh_dma_mode: force DMA to use the Shreshold mode other than
+		     the Store and Forward mode.
  o riwt_off: force to disable the RX watchdog feature and switch to NAPI mode.
  o fix_mac_speed: this callback is used for modifying some syscfg registers
 		 (on ST SoCs) according to the link speed negotiated by the
diff --git a/Documentation/networking/tproxy.txt b/Documentation/networking/tproxy.txt
index 7b5996d9357e..ec11429e1d42 100644
--- a/Documentation/networking/tproxy.txt
+++ b/Documentation/networking/tproxy.txt
@@ -2,9 +2,8 @@ Transparent proxy support
 =========================
 
 This feature adds Linux 2.2-like transparent proxy support to current kernels.
-To use it, enable NETFILTER_TPROXY, the socket match and the TPROXY target in
-your kernel config. You will need policy routing too, so be sure to enable that
-as well.
+To use it, enable the socket match and the TPROXY target in your kernel config.
+You will need policy routing too, so be sure to enable that as well.
 
 
 1. Making non-local sockets work
diff --git a/Documentation/pinctrl.txt b/Documentation/pinctrl.txt
index 052e13af2d38..c0ffd30eb55e 100644
--- a/Documentation/pinctrl.txt
+++ b/Documentation/pinctrl.txt
@@ -81,7 +81,7 @@ int __init foo_probe(void)
 	struct pinctrl_dev *pctl;
 
 	pctl = pinctrl_register(&foo_desc, <PARENT>, NULL);
-	if (IS_ERR(pctl))
+	if (!pctl)
 		pr_err("could not register foo pin driver\n");
 }
 
@@ -795,18 +795,97 @@ special GPIO-handler is registered.
 GPIO mode pitfalls
 ==================
 
-Sometime the developer may be confused by a datasheet talking about a pin
-being possible to set into "GPIO mode". It appears that what hardware
-engineers mean with "GPIO mode" is not necessarily the use case that is
-implied in the kernel interface <linux/gpio.h>: a pin that you grab from
-kernel code and then either listen for input or drive high/low to
-assert/deassert some external line.
+Due to the naming conventions used by hardware engineers, where "GPIO"
+is taken to mean different things than what the kernel does, the developer
+may be confused by a datasheet talking about a pin being possible to set
+into "GPIO mode". It appears that what hardware engineers mean with
+"GPIO mode" is not necessarily the use case that is implied in the kernel
+interface <linux/gpio.h>: a pin that you grab from kernel code and then
+either listen for input or drive high/low to assert/deassert some
+external line.
 
 Rather hardware engineers think that "GPIO mode" means that you can
 software-control a few electrical properties of the pin that you would
 not be able to control if the pin was in some other mode, such as muxed in
 for a device.
 
+The GPIO portions of a pin and its relation to a certain pin controller
+configuration and muxing logic can be constructed in several ways. Here
+are two examples:
+
+(A)
+                       pin config
+                       logic regs
+                       |               +- SPI
+     Physical pins --- pad --- pinmux -+- I2C
+                               |       +- mmc
+                               |       +- GPIO
+                               pin
+                               multiplex
+                               logic regs
+
+Here some electrical properties of the pin can be configured no matter
+whether the pin is used for GPIO or not. If you multiplex a GPIO onto a
+pin, you can also drive it high/low from "GPIO" registers.
+Alternatively, the pin can be controlled by a certain peripheral, while
+still applying desired pin config properties. GPIO functionality is thus
+orthogonal to any other device using the pin.
+
+In this arrangement the registers for the GPIO portions of the pin controller,
+or the registers for the GPIO hardware module are likely to reside in a
+separate memory range only intended for GPIO driving, and the register
+range dealing with pin config and pin multiplexing get placed into a
+different memory range and a separate section of the data sheet.
+
+(B)
+
+                       pin config
+                       logic regs
+                       |               +- SPI
+     Physical pins --- pad --- pinmux -+- I2C
+                       |       |       +- mmc
+                       |       |
+                       GPIO    pin
+                               multiplex
+                               logic regs
+
+In this arrangement, the GPIO functionality can always be enabled, such that
+e.g. a GPIO input can be used to "spy" on the SPI/I2C/MMC signal while it is
+pulsed out. It is likely possible to disrupt the traffic on the pin by doing
+wrong things on the GPIO block, as it is never really disconnected. It is
+possible that the GPIO, pin config and pin multiplex registers are placed into
+the same memory range and the same section of the data sheet, although that
+need not be the case.
+
+From a kernel point of view, however, these are different aspects of the
+hardware and shall be put into different subsystems:
+
+- Registers (or fields within registers) that control electrical
+  properties of the pin such as biasing and drive strength should be
+  exposed through the pinctrl subsystem, as "pin configuration" settings.
+
+- Registers (or fields within registers) that control muxing of signals
+  from various other HW blocks (e.g. I2C, MMC, or GPIO) onto pins should
+  be exposed through the pinctrl subssytem, as mux functions.
+
+- Registers (or fields within registers) that control GPIO functionality
+  such as setting a GPIO's output value, reading a GPIO's input value, or
+  setting GPIO pin direction should be exposed through the GPIO subsystem,
+  and if they also support interrupt capabilities, through the irqchip
+  abstraction.
+
+Depending on the exact HW register design, some functions exposed by the
+GPIO subsystem may call into the pinctrl subsystem in order to
+co-ordinate register settings across HW modules. In particular, this may
+be needed for HW with separate GPIO and pin controller HW modules, where
+e.g. GPIO direction is determined by a register in the pin controller HW
+module rather than the GPIO HW module.
+
+Electrical properties of the pin such as biasing and drive strength
+may be placed at some pin-specific register in all cases or as part
+of the GPIO register in case (B) especially. This doesn't mean that such
+properties necessarily pertain to what the Linux kernel calls "GPIO".
+
 Example: a pin is usually muxed in to be used as a UART TX line. But during
 system sleep, we need to put this pin into "GPIO mode" and ground it.
 
@@ -856,7 +935,7 @@ static unsigned long uart_sleep_mode[] = {
     PIN_CONF_PACKED(PIN_CONFIG_OUTPUT, 0),
 };
 
-static struct pinctrl_map __initdata pinmap[] = {
+static struct pinctrl_map pinmap[] __initdata = {
     PIN_MAP_MUX_GROUP("uart", PINCTRL_STATE_DEFAULT, "pinctrl-foo",
                       "u0_group", "u0"),
     PIN_MAP_CONFIGS_PIN("uart", PINCTRL_STATE_DEFAULT, "pinctrl-foo",
@@ -951,7 +1030,7 @@ Since the above construct is pretty common there is a helper macro to make
 it even more compact which assumes you want to use pinctrl-foo and position
 0 for mapping, for example:
 
-static struct pinctrl_map __initdata mapping[] = {
+static struct pinctrl_map mapping[] __initdata = {
 	PIN_MAP_MUX_GROUP("foo-i2c.o", PINCTRL_STATE_DEFAULT, "pinctrl-foo", NULL, "i2c0"),
 };
 
@@ -970,7 +1049,7 @@ static unsigned long i2c_pin_configs[] = {
 	FOO_SLEW_RATE_SLOW,
 };
 
-static struct pinctrl_map __initdata mapping[] = {
+static struct pinctrl_map mapping[] __initdata = {
 	PIN_MAP_MUX_GROUP("foo-i2c.0", PINCTRL_STATE_DEFAULT, "pinctrl-foo", "i2c0", "i2c0"),
 	PIN_MAP_CONFIGS_GROUP("foo-i2c.0", PINCTRL_STATE_DEFAULT, "pinctrl-foo", "i2c0", i2c_grp_configs),
 	PIN_MAP_CONFIGS_PIN("foo-i2c.0", PINCTRL_STATE_DEFAULT, "pinctrl-foo", "i2c0scl", i2c_pin_configs),
@@ -984,7 +1063,7 @@ order to explicitly indicate that the states were provided and intended to
 be empty. Table entry macro PIN_MAP_DUMMY_STATE serves the purpose of defining
 a named state without causing any pin controller to be programmed:
 
-static struct pinctrl_map __initdata mapping[] = {
+static struct pinctrl_map mapping[] __initdata = {
 	PIN_MAP_DUMMY_STATE("foo-i2c.0", PINCTRL_STATE_DEFAULT),
 };
 
diff --git a/Documentation/power/basic-pm-debugging.txt b/Documentation/power/basic-pm-debugging.txt
index 262acf56fa79..e9b54de8fdf7 100644
--- a/Documentation/power/basic-pm-debugging.txt
+++ b/Documentation/power/basic-pm-debugging.txt
@@ -179,7 +179,7 @@ use the PM_TRACE mechanism documented in Documentation/power/s2ram.txt .
 
 To verify that the STR works, it is generally more convenient to use the s2ram
 tool available from http://suspend.sf.net and documented at
-http://en.opensuse.org/SDB:Suspend_to_RAM.
+http://en.opensuse.org/SDB:Suspend_to_RAM (S2RAM_LINK).
 
 Namely, after writing "freezer", "devices", "platform", "processors", or "core"
 into /sys/power/pm_test (available if the kernel is compiled with
@@ -194,10 +194,10 @@ Among other things, the testing with the help of /sys/power/pm_test may allow
 you to identify drivers that fail to suspend or resume their devices.  They
 should be unloaded every time before an STR transition.
 
-Next, you can follow the instructions at http://en.opensuse.org/s2ram to test
-the system, but if it does not work "out of the box", you may need to boot it
-with "init=/bin/bash" and test s2ram in the minimal configuration.  In that
-case, you may be able to search for failing drivers by following the procedure
+Next, you can follow the instructions at S2RAM_LINK to test the system, but if
+it does not work "out of the box", you may need to boot it with
+"init=/bin/bash" and test s2ram in the minimal configuration.  In that case,
+you may be able to search for failing drivers by following the procedure
 analogous to the one described in section 1.  If you find some failing drivers,
 you will have to unload them every time before an STR transition (ie. before
 you run s2ram), and please report the problems with them.
diff --git a/Documentation/power/swsusp.txt b/Documentation/power/swsusp.txt
index 0b4b63e7e9b6..079160e22bcc 100644
--- a/Documentation/power/swsusp.txt
+++ b/Documentation/power/swsusp.txt
@@ -50,6 +50,19 @@ echo N > /sys/power/image_size
 
 before suspend (it is limited to 500 MB by default).
 
+. The resume process checks for the presence of the resume device,
+if found, it then checks the contents for the hibernation image signature.
+If both are found, it resumes the hibernation image.
+
+. The resume process may be triggered in two ways:
+  1) During lateinit:  If resume=/dev/your_swap_partition is specified on
+     the kernel command line, lateinit runs the resume process.  If the
+     resume device has not been probed yet, the resume process fails and
+     bootup continues.
+  2) Manually from an initrd or initramfs:  May be run from
+     the init script by using the /sys/power/resume file.  It is vital
+     that this be done prior to remounting any filesystems (even as
+     read-only) otherwise data may be corrupted.
 
 Article about goals and implementation of Software Suspend for Linux
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
@@ -326,7 +339,7 @@ Q: How can distributions ship a swsusp-supporting kernel with modular
 disk drivers (especially SATA)?
 
 A: Well, it can be done, load the drivers, then do echo into
-/sys/power/disk/resume file from initrd. Be sure not to mount
+/sys/power/resume file from initrd. Be sure not to mount
 anything, not even read-only mount, or you are going to lose your
 data.
 
diff --git a/Documentation/powerpc/00-INDEX b/Documentation/powerpc/00-INDEX
index 05026ce1875e..6db73df04278 100644
--- a/Documentation/powerpc/00-INDEX
+++ b/Documentation/powerpc/00-INDEX
@@ -5,13 +5,20 @@ please mail me.
 
 00-INDEX
 	- this file
+bootwrapper.txt
+	- Information on how the powerpc kernel is wrapped for boot on various
+	  different platforms.
 cpu_features.txt
 	- info on how we support a variety of CPUs with minimal compile-time
 	options.
 eeh-pci-error-recovery.txt
 	- info on PCI Bus EEH Error Recovery
+firmware-assisted-dump.txt
+	- Documentation on the firmware assisted dump mechanism "fadump".
 hvcs.txt
 	- IBM "Hypervisor Virtual Console Server" Installation Guide
+kvm_440.txt
+	- Various notes on the implementation of KVM for PowerPC 440.
 mpc52xx.txt
 	- Linux 2.6.x on MPC52xx family
 pmu-ebb.txt
@@ -19,3 +26,7 @@ pmu-ebb.txt
 qe_firmware.txt
 	- describes the layout of firmware binaries for the Freescale QUICC
 	  Engine and the code that parses and uploads the microcode therein.
+ptrace.txt
+	- Information on the ptrace interfaces for hardware debug registers.
+transactional_memory.txt
+	- Overview of the Power8 transactional memory support.
diff --git a/Documentation/printk-formats.txt b/Documentation/printk-formats.txt
index 3e8cb73ac43c..445ad743ec81 100644
--- a/Documentation/printk-formats.txt
+++ b/Documentation/printk-formats.txt
@@ -97,7 +97,7 @@ IPv4 addresses:
 
 	%pI4	1.2.3.4
 	%pi4	001.002.003.004
-	%p[Ii][hnbl]
+	%p[Ii]4[hnbl]
 
 	For printing IPv4 dot-separated decimal addresses. The 'I4' and 'i4'
 	specifiers result in a printed address with ('i4') or without ('I4')
@@ -168,6 +168,15 @@ UUID/GUID addresses:
 	Where no additional specifiers are used the default little endian
 	order with lower case hex characters will be printed.
 
+dentry names:
+	%pd{,2,3,4}
+	%pD{,2,3,4}
+
+	For printing dentry name; if we race with d_move(), the name might be
+	a mix of old and new ones, but it won't oops.  %pd dentry is a safer
+	equivalent of %s dentry->d_name.name we used to use, %pd<n> prints
+	n last components.  %pD does the same thing for struct file.
+
 struct va_format:
 
 	%pV
@@ -185,11 +194,11 @@ struct va_format:
 
 u64 SHOULD be printed with %llu/%llx, (unsigned long long):
 
-	printk("%llu", (unsigned long long)u64_var);
+	printk("%llu", u64_var);
 
 s64 SHOULD be printed with %lld/%llx, (long long):
 
-	printk("%lld", (long long)s64_var);
+	printk("%lld", s64_var);
 
 If <type> is dependent on a config option for its size (e.g., sector_t,
 blkcnt_t) or is architecture-dependent for its size (e.g., tcflag_t), use a
diff --git a/Documentation/rapidio/rapidio.txt b/Documentation/rapidio/rapidio.txt
index 717f5aa388b1..28fbd877f85a 100644
--- a/Documentation/rapidio/rapidio.txt
+++ b/Documentation/rapidio/rapidio.txt
@@ -300,7 +300,7 @@ initialization.
 -------------------------------------------
 
 RapidIO subsystem code organization allows addition of new enumeration/discovery
-methods as new configuration options without significant impact to to the core
+methods as new configuration options without significant impact to the core
 RapidIO code.
 
 A new enumeration/discovery method has to be attached to one or more mport
diff --git a/Documentation/scheduler/sched-design-CFS.txt b/Documentation/scheduler/sched-design-CFS.txt
index d529e02d928d..f14f49304222 100644
--- a/Documentation/scheduler/sched-design-CFS.txt
+++ b/Documentation/scheduler/sched-design-CFS.txt
@@ -66,9 +66,7 @@ rq->cfs.load value, which is the sum of the weights of the tasks queued on the
 runqueue.
 
 CFS maintains a time-ordered rbtree, where all runnable tasks are sorted by the
-p->se.vruntime key (there is a subtraction using rq->cfs.min_vruntime to
-account for possible wraparounds).  CFS picks the "leftmost" task from this
-tree and sticks to it.
+p->se.vruntime key. CFS picks the "leftmost" task from this tree and sticks to it.
 As the system progresses forwards, the executed tasks are put into the tree
 more and more to the right --- slowly but surely giving a chance for every task
 to become the "leftmost task" and thus get on the CPU within a deterministic
diff --git a/Documentation/scsi/ChangeLog.megaraid_sas b/Documentation/scsi/ChangeLog.megaraid_sas
index cc92ca8c8963..6edaa65b0818 100644
--- a/Documentation/scsi/ChangeLog.megaraid_sas
+++ b/Documentation/scsi/ChangeLog.megaraid_sas
@@ -1,3 +1,13 @@
+Release Date    : Sat. Aug 31, 2013 17:00:00 PST 2013 -
+			(emaild-id:megaraidlinux@lsi.com)
+			Adam Radford
+			Kashyap Desai
+			Sumit Saxena
+Current Version : 06.700.06.00-rc1
+Old Version     : 06.600.18.00-rc1
+    1. Add High Availability clustering support using shared Logical Disks.
+    2. Version and Changelog update.
+-------------------------------------------------------------------------------
 Release Date    : Wed. May 15, 2013 17:00:00 PST 2013 -
 			(emaild-id:megaraidlinux@lsi.com)
 			Adam Radford
diff --git a/Documentation/scsi/LICENSE.qla4xxx b/Documentation/scsi/LICENSE.qla4xxx
index 78c169f0d7c6..fcc27ad27d74 100644
--- a/Documentation/scsi/LICENSE.qla4xxx
+++ b/Documentation/scsi/LICENSE.qla4xxx
@@ -1,4 +1,4 @@
-Copyright (c) 2003-2012 QLogic Corporation
+Copyright (c) 2003-2013 QLogic Corporation
 QLogic Linux iSCSI Driver
 
 This program includes a device driver for Linux 3.x.
diff --git a/Documentation/scsi/hptiop.txt b/Documentation/scsi/hptiop.txt
index 4a4f47e759cd..12ecfd308e55 100644
--- a/Documentation/scsi/hptiop.txt
+++ b/Documentation/scsi/hptiop.txt
@@ -151,7 +151,7 @@ To send a request to the controller:
       generated.
 
     - The host read the outbound list copy pointer shadow register and compare
-      with previous saved read ponter N. If they are different, the host will
+      with previous saved read pointer N. If they are different, the host will
       read the (N+1)th outbound list unit.
 
       The host get the index of the request from the (N+1)th outbound list
diff --git a/Documentation/sound/alsa/HD-Audio-Models.txt b/Documentation/sound/alsa/HD-Audio-Models.txt
index 809d72b8eff1..85c362d8ea34 100644
--- a/Documentation/sound/alsa/HD-Audio-Models.txt
+++ b/Documentation/sound/alsa/HD-Audio-Models.txt
@@ -28,6 +28,7 @@ ALC269/270/275/276/28x/29x
   alc269-dmic		Enable ALC269(VA) digital mic workaround
   alc271-dmic		Enable ALC271X digital mic workaround
   inv-dmic		Inverted internal mic workaround
+  headset-mic		Indicates a combined headset (headphone+mic) jack
   lenovo-dock   	Enables docking station I/O for some Lenovos
   dell-headset-multi	Headset jack, which can also be used as mic-in
   dell-headset-dock	Headset jack (without mic-in), and also dock I/O
@@ -244,6 +245,7 @@ STAC9227/9228/9229/927x
   5stack-no-fp	D965 5stack without front panel
   dell-3stack	Dell Dimension E520
   dell-bios	Fixes with Dell BIOS setup
+  dell-bios-amic Fixes with Dell BIOS setup including analog mic
   volknob	Fixes with volume-knob widget 0x24
   auto		BIOS setup (default)
 
@@ -295,6 +297,12 @@ Cirrus Logic CS4206/4207
   imac27	IMac 27 Inch
   auto		BIOS setup (default)
 
+Cirrus Logic CS4208
+===================
+  mba6		MacBook Air 6,1 and 6,2
+  gpio0		Enable GPIO 0 amp
+  auto		BIOS setup (default)
+
 VIA VT17xx/VT18xx/VT20xx
 ========================
   auto		BIOS setup (default)
diff --git a/Documentation/sound/alsa/HD-Audio.txt b/Documentation/sound/alsa/HD-Audio.txt
index c3c912d023cc..42a0a39b77e6 100644
--- a/Documentation/sound/alsa/HD-Audio.txt
+++ b/Documentation/sound/alsa/HD-Audio.txt
@@ -454,6 +454,8 @@ The generic parser supports the following hints:
 - need_dac_fix (bool): limits the DACs depending on the channel count
 - primary_hp (bool): probe headphone jacks as the primary outputs;
   default true
+- multi_io (bool): try probing multi-I/O config (e.g. shared
+  line-in/surround, mic/clfe jacks)
 - multi_cap_vol (bool): provide multiple capture volumes
 - inv_dmic_split (bool): provide split internal mic volume/switch for
   phase-inverted digital mics
diff --git a/Documentation/sound/alsa/README.maya44 b/Documentation/sound/alsa/README.maya44
index 0e41576fa13e..67b2ea1cc31d 100644
--- a/Documentation/sound/alsa/README.maya44
+++ b/Documentation/sound/alsa/README.maya44
@@ -120,7 +120,7 @@ Mic Phantom+48V: switch for +48V phantom power for electrostatic microphones on
     Make sure this is not turned on while any other source is connected to input 1/2.
     It might damage the source and/or the maya44 card.
 
-Mic/Line input: if switch is is on, input jack 1/2 is microphone input (mono), otherwise line input (stereo).
+Mic/Line input: if switch is on, input jack 1/2 is microphone input (mono), otherwise line input (stereo).
 
 Bypass: analogue bypass from ADC input to output for channel 1+2. Same as "Monitor" in the windows driver.
 Bypass 1: same for channel 3+4.
diff --git a/Documentation/sound/alsa/compress_offload.txt b/Documentation/sound/alsa/compress_offload.txt
index 0bcc55155911..fd74ff26376e 100644
--- a/Documentation/sound/alsa/compress_offload.txt
+++ b/Documentation/sound/alsa/compress_offload.txt
@@ -73,7 +73,7 @@ The main requirements are:
 
 Design
 
-The new API shares a number of concepts with with the PCM API for flow
+The new API shares a number of concepts with the PCM API for flow
 control. Start, pause, resume, drain and stop commands have the same
 semantics no matter what the content is.
 
@@ -130,7 +130,7 @@ the settings should remain the exception.
 The timestamp becomes a multiple field structure. It lists the number
 of bytes transferred, the number of samples processed and the number
 of samples rendered/grabbed. All these values can be used to determine
-the avarage bitrate, figure out if the ring buffer needs to be
+the average bitrate, figure out if the ring buffer needs to be
 refilled or the delay due to decoding/encoding/io on the DSP.
 
 Note that the list of codecs/profiles/modes was derived from the
diff --git a/Documentation/spi/spi-summary b/Documentation/spi/spi-summary
index 2331eb214146..f21edb983413 100644
--- a/Documentation/spi/spi-summary
+++ b/Documentation/spi/spi-summary
@@ -215,7 +215,7 @@ So for example arch/.../mach-*/board-*.c files might have code like:
 	/* if your mach-* infrastructure doesn't support kernels that can
 	 * run on multiple boards, pdata wouldn't benefit from "__init".
 	 */
-	static struct mysoc_spi_data __initdata pdata = { ... };
+	static struct mysoc_spi_data pdata __initdata = { ... };
 
 	static __init board_init(void)
 	{
diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt
index ab7d16efa96b..9d4c1d18ad44 100644
--- a/Documentation/sysctl/kernel.txt
+++ b/Documentation/sysctl/kernel.txt
@@ -182,6 +182,7 @@ core_pattern is used to specify a core dumpfile pattern name.
 	%<NUL>	'%' is dropped
 	%%	output one '%'
 	%p	pid
+	%P	global pid (init PID namespace)
 	%u	uid
 	%g	gid
 	%d	dump mode, matches PR_SET_DUMPABLE and
diff --git a/Documentation/sysctl/net.txt b/Documentation/sysctl/net.txt
index d569f2a424d5..9a0319a82470 100644
--- a/Documentation/sysctl/net.txt
+++ b/Documentation/sysctl/net.txt
@@ -50,6 +50,19 @@ The maximum number of packets that kernel can handle on a NAPI interrupt,
 it's a Per-CPU variable.
 Default: 64
 
+default_qdisc
+--------------
+
+The default queuing discipline to use for network devices. This allows
+overriding the default queue discipline of pfifo_fast with an
+alternative. Since the default queuing discipline is created with the
+no additional parameters so is best suited to queuing disciplines that
+work well without configuration like stochastic fair queue (sfq),
+CoDel (codel) or fair queue CoDel (fq_codel). Don't use queuing disciplines
+like Hierarchical Token Bucket or Deficit Round Robin which require setting
+up classes and bandwidths.
+Default: pfifo_fast
+
 busy_read
 ----------------
 Low latency busy poll timeout for socket reads. (needs CONFIG_NET_RX_BUSY_POLL)
diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt
index 36ecc26c7433..79a797eb3e87 100644
--- a/Documentation/sysctl/vm.txt
+++ b/Documentation/sysctl/vm.txt
@@ -200,17 +200,25 @@ fragmentation index is <= extfrag_threshold. The default value is 500.
 
 hugepages_treat_as_movable
 
-This parameter is only useful when kernelcore= is specified at boot time to
-create ZONE_MOVABLE for pages that may be reclaimed or migrated. Huge pages
-are not movable so are not normally allocated from ZONE_MOVABLE. A non-zero
-value written to hugepages_treat_as_movable allows huge pages to be allocated
-from ZONE_MOVABLE.
-
-Once enabled, the ZONE_MOVABLE is treated as an area of memory the huge
-pages pool can easily grow or shrink within. Assuming that applications are
-not running that mlock() a lot of memory, it is likely the huge pages pool
-can grow to the size of ZONE_MOVABLE by repeatedly entering the desired value
-into nr_hugepages and triggering page reclaim.
+This parameter controls whether we can allocate hugepages from ZONE_MOVABLE
+or not. If set to non-zero, hugepages can be allocated from ZONE_MOVABLE.
+ZONE_MOVABLE is created when kernel boot parameter kernelcore= is specified,
+so this parameter has no effect if used without kernelcore=.
+
+Hugepage migration is now available in some situations which depend on the
+architecture and/or the hugepage size. If a hugepage supports migration,
+allocation from ZONE_MOVABLE is always enabled for the hugepage regardless
+of the value of this parameter.
+IOW, this parameter affects only non-migratable hugepages.
+
+Assuming that hugepages are not migratable in your system, one usecase of
+this parameter is that users can make hugepage pool more extensible by
+enabling the allocation from ZONE_MOVABLE. This is because on ZONE_MOVABLE
+page reclaim/migration/compaction work more and you can get contiguous
+memory more likely. Note that using ZONE_MOVABLE for non-migratable
+hugepages can do harm to other features like memory hotremove (because
+memory hotremove expects that memory blocks on ZONE_MOVABLE are always
+removable,) so it's a trade-off responsible for the users.
 
 ==============================================================
 
diff --git a/Documentation/sysfs-rules.txt b/Documentation/sysfs-rules.txt
index c1a1fd636bf9..a5f985ee1822 100644
--- a/Documentation/sysfs-rules.txt
+++ b/Documentation/sysfs-rules.txt
@@ -47,7 +47,7 @@ versions of the sysfs interface.
         at device creation and removal
       - the unique key to the device at that point in time
       - the kernel's path to the device directory without the leading
-        /sys, and always starting with with a slash
+        /sys, and always starting with a slash
       - all elements of a devpath must be real directories. Symlinks
         pointing to /sys/devices must always be resolved to their real
         target and the target path must be used to access the device.
diff --git a/Documentation/target/tcm_mod_builder.py b/Documentation/target/tcm_mod_builder.py
index 3fe0d812dcec..54d29c1320ed 100755
--- a/Documentation/target/tcm_mod_builder.py
+++ b/Documentation/target/tcm_mod_builder.py
@@ -300,7 +300,7 @@ def tcm_mod_build_configfs(proto_ident, fabric_mod_dir_var, fabric_mod_name):
 	buf += "	int ret;\n\n"
 	buf += "	if (strstr(name, \"tpgt_\") != name)\n"
 	buf += "		return ERR_PTR(-EINVAL);\n"
-	buf += "	if (strict_strtoul(name + 5, 10, &tpgt) || tpgt > UINT_MAX)\n"
+	buf += "	if (kstrtoul(name + 5, 10, &tpgt) || tpgt > UINT_MAX)\n"
 	buf += "		return ERR_PTR(-EINVAL);\n\n"
 	buf += "	tpg = kzalloc(sizeof(struct " + fabric_mod_name + "_tpg), GFP_KERNEL);\n"
 	buf += "	if (!tpg) {\n"
diff --git a/Documentation/thermal/exynos_thermal b/Documentation/thermal/exynos_thermal
index 2b46f67b1ccb..9010c4416967 100644
--- a/Documentation/thermal/exynos_thermal
+++ b/Documentation/thermal/exynos_thermal
@@ -1,17 +1,17 @@
-Kernel driver exynos4_tmu
+Kernel driver exynos_tmu
 =================
 
 Supported chips:
-* ARM SAMSUNG EXYNOS4 series of SoC
-  Prefix: 'exynos4-tmu'
+* ARM SAMSUNG EXYNOS4, EXYNOS5 series of SoC
   Datasheet: Not publicly available
 
 Authors: Donggeun Kim <dg77.kim@samsung.com>
+Authors: Amit Daniel <amit.daniel@samsung.com>
 
-Description
------------
+TMU controller Description:
+---------------------------
 
-This driver allows to read temperature inside SAMSUNG EXYNOS4 series of SoC.
+This driver allows to read temperature inside SAMSUNG EXYNOS4/5 series of SoC.
 
 The chip only exposes the measured 8-bit temperature code value
 through a register.
@@ -34,9 +34,9 @@ The three equations are:
   TI2: Trimming info for 85 degree Celsius (stored at TRIMINFO register)
        Temperature code measured at 85 degree Celsius which is unchanged
 
-TMU(Thermal Management Unit) in EXYNOS4 generates interrupt
+TMU(Thermal Management Unit) in EXYNOS4/5 generates interrupt
 when temperature exceeds pre-defined levels.
-The maximum number of configurable threshold is four.
+The maximum number of configurable threshold is five.
 The threshold levels are defined as follows:
   Level_0: current temperature > trigger_level_0 + threshold
   Level_1: current temperature > trigger_level_1 + threshold
@@ -47,6 +47,31 @@ The threshold levels are defined as follows:
   through the corresponding registers.
 
 When an interrupt occurs, this driver notify kernel thermal framework
-with the function exynos4_report_trigger.
+with the function exynos_report_trigger.
 Although an interrupt condition for level_0 can be set,
 it can be used to synchronize the cooling action.
+
+TMU driver description:
+-----------------------
+
+The exynos thermal driver is structured as,
+
+					Kernel Core thermal framework
+				(thermal_core.c, step_wise.c, cpu_cooling.c)
+								^
+								|
+								|
+TMU configuration data -------> TMU Driver  <------> Exynos Core thermal wrapper
+(exynos_tmu_data.c)	      (exynos_tmu.c)	   (exynos_thermal_common.c)
+(exynos_tmu_data.h)	      (exynos_tmu.h)	   (exynos_thermal_common.h)
+
+a) TMU configuration data: This consist of TMU register offsets/bitfields
+		described through structure exynos_tmu_registers. Also several
+		other platform data (struct exynos_tmu_platform_data) members
+		are used to configure the TMU.
+b) TMU driver: This component initialises the TMU controller and sets different
+		thresholds. It invokes core thermal implementation with the call
+		exynos_report_trigger.
+c) Exynos Core thermal wrapper: This provides 3 wrapper function to use the
+		Kernel core thermal framework. They are exynos_unregister_thermal,
+		exynos_register_thermal and exynos_report_trigger.
diff --git a/Documentation/thermal/sysfs-api.txt b/Documentation/thermal/sysfs-api.txt
index a71bd5b90fe8..87519cb379ee 100644
--- a/Documentation/thermal/sysfs-api.txt
+++ b/Documentation/thermal/sysfs-api.txt
@@ -134,6 +134,13 @@ temperature) and throttle appropriate devices.
                this thermal zone and cdev, for a particular trip point.
                If nth bit is set, then the cdev and thermal zone are bound
                for trip point n.
+    .limits: This is an array of cooling state limits. Must have exactly
+         2 * thermal_zone.number_of_trip_points. It is an array consisting
+         of tuples <lower-state upper-state> of state limits. Each trip
+         will be associated with one state limit tuple when binding.
+         A NULL pointer means <THERMAL_NO_LIMITS THERMAL_NO_LIMITS>
+         on all trips. These limits are used when binding a cdev to a
+         trip point.
     .match: This call back returns success(0) if the 'tz and cdev' need to
 	    be bound, as per platform data.
 1.4.2 struct thermal_zone_params
@@ -142,6 +149,11 @@ temperature) and throttle appropriate devices.
     This is an optional feature where some platforms can choose not to
     provide this data.
     .governor_name: Name of the thermal governor used for this zone
+    .no_hwmon: a boolean to indicate if the thermal to hwmon sysfs interface
+               is required. when no_hwmon == false, a hwmon sysfs interface
+               will be created. when no_hwmon == true, nothing will be done.
+               In case the thermal_zone_params is NULL, the hwmon interface
+               will be created (for backward compatibility).
     .num_tbps: Number of thermal_bind_params entries for this zone
     .tbp: thermal_bind_params entries
 
diff --git a/Documentation/timers/NO_HZ.txt b/Documentation/timers/NO_HZ.txt
index 88697584242b..cca122f25120 100644
--- a/Documentation/timers/NO_HZ.txt
+++ b/Documentation/timers/NO_HZ.txt
@@ -24,8 +24,8 @@ There are three main ways of managing scheduling-clock interrupts
 	workloads, you will normally -not- want this option.
 
 These three cases are described in the following three sections, followed
-by a third section on RCU-specific considerations and a fourth and final
-section listing known issues.
+by a third section on RCU-specific considerations, a fourth section
+discussing testing, and a fifth and final section listing known issues.
 
 
 NEVER OMIT SCHEDULING-CLOCK TICKS
@@ -121,14 +121,15 @@ boot parameter specifies the adaptive-ticks CPUs.  For example,
 "nohz_full=1,6-8" says that CPUs 1, 6, 7, and 8 are to be adaptive-ticks
 CPUs.  Note that you are prohibited from marking all of the CPUs as
 adaptive-tick CPUs:  At least one non-adaptive-tick CPU must remain
-online to handle timekeeping tasks in order to ensure that system calls
-like gettimeofday() returns accurate values on adaptive-tick CPUs.
-(This is not an issue for CONFIG_NO_HZ_IDLE=y because there are no
-running user processes to observe slight drifts in clock rate.)
-Therefore, the boot CPU is prohibited from entering adaptive-ticks
-mode.  Specifying a "nohz_full=" mask that includes the boot CPU will
-result in a boot-time error message, and the boot CPU will be removed
-from the mask.
+online to handle timekeeping tasks in order to ensure that system
+calls like gettimeofday() returns accurate values on adaptive-tick CPUs.
+(This is not an issue for CONFIG_NO_HZ_IDLE=y because there are no running
+user processes to observe slight drifts in clock rate.)  Therefore, the
+boot CPU is prohibited from entering adaptive-ticks mode.  Specifying a
+"nohz_full=" mask that includes the boot CPU will result in a boot-time
+error message, and the boot CPU will be removed from the mask.  Note that
+this means that your system must have at least two CPUs in order for
+CONFIG_NO_HZ_FULL=y to do anything for you.
 
 Alternatively, the CONFIG_NO_HZ_FULL_ALL=y Kconfig parameter specifies
 that all CPUs other than the boot CPU are adaptive-ticks CPUs.  This
@@ -232,6 +233,29 @@ scheduler will decide where to run them, which might or might not be
 where you want them to run.
 
 
+TESTING
+
+So you enable all the OS-jitter features described in this document,
+but do not see any change in your workload's behavior.  Is this because
+your workload isn't affected that much by OS jitter, or is it because
+something else is in the way?  This section helps answer this question
+by providing a simple OS-jitter test suite, which is available on branch
+master of the following git archive:
+
+git://git.kernel.org/pub/scm/linux/kernel/git/frederic/dynticks-testing.git
+
+Clone this archive and follow the instructions in the README file.
+This test procedure will produce a trace that will allow you to evaluate
+whether or not you have succeeded in removing OS jitter from your system.
+If this trace shows that you have removed OS jitter as much as is
+possible, then you can conclude that your workload is not all that
+sensitive to OS jitter.
+
+Note: this test requires that your system have at least two CPUs.
+We do not currently have a good way to remove OS jitter from single-CPU
+systems.
+
+
 KNOWN ISSUES
 
 o	Dyntick-idle slows transitions to and from idle slightly.
diff --git a/Documentation/tpm/xen-tpmfront.txt b/Documentation/tpm/xen-tpmfront.txt
new file mode 100644
index 000000000000..69346de87ff3
--- /dev/null
+++ b/Documentation/tpm/xen-tpmfront.txt
@@ -0,0 +1,113 @@
+Virtual TPM interface for Xen
+
+Authors: Matthew Fioravante (JHUAPL), Daniel De Graaf (NSA)
+
+This document describes the virtual Trusted Platform Module (vTPM) subsystem for
+Xen. The reader is assumed to have familiarity with building and installing Xen,
+Linux, and a basic understanding of the TPM and vTPM concepts.
+
+INTRODUCTION
+
+The goal of this work is to provide a TPM functionality to a virtual guest
+operating system (in Xen terms, a DomU).  This allows programs to interact with
+a TPM in a virtual system the same way they interact with a TPM on the physical
+system.  Each guest gets its own unique, emulated, software TPM.  However, each
+of the vTPM's secrets (Keys, NVRAM, etc) are managed by a vTPM Manager domain,
+which seals the secrets to the Physical TPM.  If the process of creating each of
+these domains (manager, vTPM, and guest) is trusted, the vTPM subsystem extends
+the chain of trust rooted in the hardware TPM to virtual machines in Xen. Each
+major component of vTPM is implemented as a separate domain, providing secure
+separation guaranteed by the hypervisor. The vTPM domains are implemented in
+mini-os to reduce memory and processor overhead.
+
+This mini-os vTPM subsystem was built on top of the previous vTPM work done by
+IBM and Intel corporation.
+
+
+DESIGN OVERVIEW
+---------------
+
+The architecture of vTPM is described below:
+
++------------------+
+|    Linux DomU    | ...
+|       |  ^       |
+|       v  |       |
+|   xen-tpmfront   |
++------------------+
+        |  ^
+        v  |
++------------------+
+| mini-os/tpmback  |
+|       |  ^       |
+|       v  |       |
+|  vtpm-stubdom    | ...
+|       |  ^       |
+|       v  |       |
+| mini-os/tpmfront |
++------------------+
+        |  ^
+        v  |
++------------------+
+| mini-os/tpmback  |
+|       |  ^       |
+|       v  |       |
+| vtpmmgr-stubdom  |
+|       |  ^       |
+|       v  |       |
+| mini-os/tpm_tis  |
++------------------+
+        |  ^
+        v  |
++------------------+
+|   Hardware TPM   |
++------------------+
+
+ * Linux DomU: The Linux based guest that wants to use a vTPM. There may be
+	       more than one of these.
+
+ * xen-tpmfront.ko: Linux kernel virtual TPM frontend driver. This driver
+                    provides vTPM access to a Linux-based DomU.
+
+ * mini-os/tpmback: Mini-os TPM backend driver. The Linux frontend driver
+		    connects to this backend driver to facilitate communications
+		    between the Linux DomU and its vTPM. This driver is also
+		    used by vtpmmgr-stubdom to communicate with vtpm-stubdom.
+
+ * vtpm-stubdom: A mini-os stub domain that implements a vTPM. There is a
+		 one to one mapping between running vtpm-stubdom instances and
+                 logical vtpms on the system. The vTPM Platform Configuration
+                 Registers (PCRs) are normally all initialized to zero.
+
+ * mini-os/tpmfront: Mini-os TPM frontend driver. The vTPM mini-os domain
+		     vtpm-stubdom uses this driver to communicate with
+		     vtpmmgr-stubdom. This driver is also used in mini-os
+		     domains such as pv-grub that talk to the vTPM domain.
+
+ * vtpmmgr-stubdom: A mini-os domain that implements the vTPM manager. There is
+		    only one vTPM manager and it should be running during the
+		    entire lifetime of the machine.  This domain regulates
+		    access to the physical TPM on the system and secures the
+		    persistent state of each vTPM.
+
+ * mini-os/tpm_tis: Mini-os TPM version 1.2 TPM Interface Specification (TIS)
+                    driver. This driver used by vtpmmgr-stubdom to talk directly to
+                    the hardware TPM. Communication is facilitated by mapping
+                    hardware memory pages into vtpmmgr-stubdom.
+
+ * Hardware TPM: The physical TPM that is soldered onto the motherboard.
+
+
+INTEGRATION WITH XEN
+--------------------
+
+Support for the vTPM driver was added in Xen using the libxl toolstack in Xen
+4.3.  See the Xen documentation (docs/misc/vtpm.txt) for details on setting up
+the vTPM and vTPM Manager stub domains.  Once the stub domains are running, a
+vTPM device is set up in the same manner as a disk or network device in the
+domain's configuration file.
+
+In order to use features such as IMA that require a TPM to be loaded prior to
+the initrd, the xen-tpmfront driver must be compiled in to the kernel.  If not
+using such features, the driver can be compiled as a module and will be loaded
+as usual.
diff --git a/Documentation/trace/ftrace.txt b/Documentation/trace/ftrace.txt
index b937c6e2163c..ea2d35d64d26 100644
--- a/Documentation/trace/ftrace.txt
+++ b/Documentation/trace/ftrace.txt
@@ -735,7 +735,7 @@ Here are the available options:
 		 function as well as the function being traced.
 
   print-parent:
-   bash-4000  [01]  1477.606694: simple_strtoul <-strict_strtoul
+   bash-4000  [01]  1477.606694: simple_strtoul <-kstrtoul
 
   noprint-parent:
    bash-4000  [01]  1477.606694: simple_strtoul
@@ -759,7 +759,7 @@ Here are the available options:
             latency-format option is enabled.
 
     bash  4000 1 0 00000000 00010a95 [58127d26] 1720.415ms \
-    (+0.000ms): simple_strtoul (strict_strtoul)
+    (+0.000ms): simple_strtoul (kstrtoul)
 
   raw - This will display raw numbers. This option is best for
 	use with user applications that can translate the raw
diff --git a/Documentation/trace/tracepoints.txt b/Documentation/trace/tracepoints.txt
index da49437d5aeb..ac4170dd0f24 100644
--- a/Documentation/trace/tracepoints.txt
+++ b/Documentation/trace/tracepoints.txt
@@ -40,7 +40,13 @@ Two elements are required for tracepoints :
 
 In order to use tracepoints, you should include linux/tracepoint.h.
 
-In include/trace/subsys.h :
+In include/trace/events/subsys.h :
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM subsys
+
+#if !defined(_TRACE_SUBSYS_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_SUBSYS_H
 
 #include <linux/tracepoint.h>
 
@@ -48,10 +54,16 @@ DECLARE_TRACE(subsys_eventname,
 	TP_PROTO(int firstarg, struct task_struct *p),
 	TP_ARGS(firstarg, p));
 
+#endif /* _TRACE_SUBSYS_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
+
 In subsys/file.c (where the tracing statement must be added) :
 
-#include <trace/subsys.h>
+#include <trace/events/subsys.h>
 
+#define CREATE_TRACE_POINTS
 DEFINE_TRACE(subsys_eventname);
 
 void somefct(void)
@@ -72,6 +84,9 @@ Where :
 - TP_ARGS(firstarg, p) are the parameters names, same as found in the
   prototype.
 
+- if you use the header in multiple source files, #define CREATE_TRACE_POINTS
+  should appear only in one source file.
+
 Connecting a function (probe) to a tracepoint is done by providing a
 probe (function to call) for the specific tracepoint through
 register_trace_subsys_eventname().  Removing a probe is done through
diff --git a/Documentation/usb/URB.txt b/Documentation/usb/URB.txt
index 00d2c644068e..50da0d455444 100644
--- a/Documentation/usb/URB.txt
+++ b/Documentation/usb/URB.txt
@@ -195,13 +195,12 @@ by the completion handler.
 
 The handler is of the following type:
 
-	typedef void (*usb_complete_t)(struct urb *, struct pt_regs *)
+	typedef void (*usb_complete_t)(struct urb *)
 
-I.e., it gets the URB that caused the completion call, plus the
-register values at the time of the corresponding interrupt (if any).
-In the completion handler, you should have a look at urb->status to
-detect any USB errors. Since the context parameter is included in the URB,
-you can pass information to the completion handler. 
+I.e., it gets the URB that caused the completion call. In the completion
+handler, you should have a look at urb->status to detect any USB errors.
+Since the context parameter is included in the URB, you can pass
+information to the completion handler.
 
 Note that even when an error (or unlink) is reported, data may have been
 transferred.  That's because USB transfers are packetized; it might take
@@ -210,12 +209,12 @@ have transferred successfully before the completion was called.
 
 
 NOTE:  ***** WARNING *****
-NEVER SLEEP IN A COMPLETION HANDLER.  These are normally called
-during hardware interrupt processing.  If you can, defer substantial
-work to a tasklet (bottom half) to keep system latencies low.  You'll
-probably need to use spinlocks to protect data structures you manipulate
-in completion handlers.
+NEVER SLEEP IN A COMPLETION HANDLER.  These are often called in atomic
+context.
 
+In the current kernel, completion handlers run with local interrupts
+disabled, but in the future this will be changed, so don't assume that
+local IRQs are always disabled inside completion handlers.
 
 1.8. How to do isochronous (ISO) transfers?
 
diff --git a/Documentation/usb/proc_usb_info.txt b/Documentation/usb/proc_usb_info.txt
index c9c3f0f5ad7b..98be91982677 100644
--- a/Documentation/usb/proc_usb_info.txt
+++ b/Documentation/usb/proc_usb_info.txt
@@ -54,9 +54,12 @@ it and 002/048 sometime later.
 
 These files can be read as binary data.  The binary data consists
 of first the device descriptor, then the descriptors for each
-configuration of the device.  Multi-byte fields in the device and
-configuration descriptors, but not other descriptors, are converted
-to host endianness by the kernel.  This information is also shown
+configuration of the device.  Multi-byte fields in the device descriptor
+are converted to host endianness by the kernel.  The configuration
+descriptors are in bus endian format! The configuration descriptor
+are wTotalLength bytes apart. If a device returns less configuration
+descriptor data than indicated by wTotalLength there will be a hole in
+the file for the missing bytes.  This information is also shown
 in text form by the /proc/bus/usb/devices file, described later.
 
 These files may also be used to write user-level drivers for the USB
diff --git a/Documentation/vfio.txt b/Documentation/vfio.txt
index d7993dcf8537..b9ca02370d46 100644
--- a/Documentation/vfio.txt
+++ b/Documentation/vfio.txt
@@ -167,8 +167,8 @@ group and can access them as follows:
 	int container, group, device, i;
 	struct vfio_group_status group_status =
 					{ .argsz = sizeof(group_status) };
-	struct vfio_iommu_x86_info iommu_info = { .argsz = sizeof(iommu_info) };
-	struct vfio_iommu_x86_dma_map dma_map = { .argsz = sizeof(dma_map) };
+	struct vfio_iommu_type1_info iommu_info = { .argsz = sizeof(iommu_info) };
+	struct vfio_iommu_type1_dma_map dma_map = { .argsz = sizeof(dma_map) };
 	struct vfio_device_info device_info = { .argsz = sizeof(device_info) };
 
 	/* Create a new container */
@@ -193,7 +193,7 @@ group and can access them as follows:
 	ioctl(group, VFIO_GROUP_SET_CONTAINER, &container);
 
 	/* Enable the IOMMU model we want */
-	ioctl(container, VFIO_SET_IOMMU, VFIO_TYPE1_IOMMU)
+	ioctl(container, VFIO_SET_IOMMU, VFIO_TYPE1_IOMMU);
 
 	/* Get addition IOMMU info */
 	ioctl(container, VFIO_IOMMU_GET_INFO, &iommu_info);
@@ -229,7 +229,7 @@ group and can access them as follows:
 
 		irq.index = i;
 
-		ioctl(device, VFIO_DEVICE_GET_IRQ_INFO, &reg);
+		ioctl(device, VFIO_DEVICE_GET_IRQ_INFO, &irq);
 
 		/* Setup IRQs... eventfds, VFIO_DEVICE_SET_IRQS */
 	}
diff --git a/Documentation/video4linux/v4l2-controls.txt b/Documentation/video4linux/v4l2-controls.txt
index 676f87366025..06cf3ac83631 100644
--- a/Documentation/video4linux/v4l2-controls.txt
+++ b/Documentation/video4linux/v4l2-controls.txt
@@ -124,26 +124,27 @@ You add non-menu controls by calling v4l2_ctrl_new_std:
 			const struct v4l2_ctrl_ops *ops,
 			u32 id, s32 min, s32 max, u32 step, s32 def);
 
-Menu controls are added by calling v4l2_ctrl_new_std_menu:
+Menu and integer menu controls are added by calling v4l2_ctrl_new_std_menu:
 
 	struct v4l2_ctrl *v4l2_ctrl_new_std_menu(struct v4l2_ctrl_handler *hdl,
 			const struct v4l2_ctrl_ops *ops,
 			u32 id, s32 max, s32 skip_mask, s32 def);
 
-Or alternatively for integer menu controls, by calling v4l2_ctrl_new_int_menu:
+Menu controls with a driver specific menu are added by calling
+v4l2_ctrl_new_std_menu_items:
+
+       struct v4l2_ctrl *v4l2_ctrl_new_std_menu_items(
+                       struct v4l2_ctrl_handler *hdl,
+                       const struct v4l2_ctrl_ops *ops, u32 id, s32 max,
+                       s32 skip_mask, s32 def, const char * const *qmenu);
+
+Integer menu controls with a driver specific menu can be added by calling
+v4l2_ctrl_new_int_menu:
 
 	struct v4l2_ctrl *v4l2_ctrl_new_int_menu(struct v4l2_ctrl_handler *hdl,
 			const struct v4l2_ctrl_ops *ops,
 			u32 id, s32 max, s32 def, const s64 *qmenu_int);
 
-Standard menu controls with a driver specific menu are added by calling
-v4l2_ctrl_new_std_menu_items:
-
-	struct v4l2_ctrl *v4l2_ctrl_new_std_menu_items(
-		struct v4l2_ctrl_handler *hdl,
-		const struct v4l2_ctrl_ops *ops, u32 id, s32 max,
-		s32 skip_mask, s32 def, const char * const *qmenu);
-
 These functions are typically called right after the v4l2_ctrl_handler_init:
 
 	static const s64 exp_bias_qmenu[] = {
diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index ef925eaa1460..858aecf21db2 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -53,7 +53,7 @@ incompatible change are allowed.  However, there is an extension
 facility that allows backward-compatible extensions to the API to be
 queried and used.
 
-The extension mechanism is not based on on the Linux version number.
+The extension mechanism is not based on the Linux version number.
 Instead, kvm defines extension identifiers and a facility to query
 whether a particular extension identifier is available.  If it is, a
 set of ioctls is available for application use.
diff --git a/Documentation/virtual/kvm/cpuid.txt b/Documentation/virtual/kvm/cpuid.txt
index 83afe65d4966..22ff659bc0fb 100644
--- a/Documentation/virtual/kvm/cpuid.txt
+++ b/Documentation/virtual/kvm/cpuid.txt
@@ -43,6 +43,10 @@ KVM_FEATURE_CLOCKSOURCE2           ||     3 || kvmclock available at msrs
 KVM_FEATURE_ASYNC_PF               ||     4 || async pf can be enabled by
                                    ||       || writing to msr 0x4b564d02
 ------------------------------------------------------------------------------
+KVM_FEATURE_PV_UNHALT              ||     7 || guest checks this feature bit
+                                   ||       || before enabling paravirtualized
+                                   ||       || spinlock support.
+------------------------------------------------------------------------------
 KVM_FEATURE_CLOCKSOURCE_STABLE_BIT ||    24 || host will warn if no guest-side
                                    ||       || per-cpu warps are expected in
                                    ||       || kvmclock.
diff --git a/Documentation/virtual/kvm/hypercalls.txt b/Documentation/virtual/kvm/hypercalls.txt
index ea113b5d87a4..022198e389d7 100644
--- a/Documentation/virtual/kvm/hypercalls.txt
+++ b/Documentation/virtual/kvm/hypercalls.txt
@@ -64,3 +64,17 @@ Purpose: To enable communication between the hypervisor and guest there is a
 shared page that contains parts of supervisor visible register state.
 The guest can map this shared page to access its supervisor register through
 memory using this hypercall.
+
+5. KVM_HC_KICK_CPU
+------------------------
+Architecture: x86
+Status: active
+Purpose: Hypercall used to wakeup a vcpu from HLT state
+Usage example : A vcpu of a paravirtualized guest that is busywaiting in guest
+kernel mode for an event to occur (ex: a spinlock to become available) can
+execute HLT instruction once it has busy-waited for more than a threshold
+time-interval. Execution of HLT instruction would cause the hypervisor to put
+the vcpu to sleep until occurence of an appropriate event. Another vcpu of the
+same guest can wakeup the sleeping vcpu by issuing KVM_HC_KICK_CPU hypercall,
+specifying APIC ID (a1) of the vcpu to be woken up. An additional argument (a0)
+is used in the hypercall for future use.
diff --git a/Documentation/vm/hugetlbpage.txt b/Documentation/vm/hugetlbpage.txt
index 4ac359b7aa17..bdd4bb97fff7 100644
--- a/Documentation/vm/hugetlbpage.txt
+++ b/Documentation/vm/hugetlbpage.txt
@@ -165,6 +165,7 @@ which function as described above for the default huge page-sized case.
 
 
 Interaction of Task Memory Policy with Huge Page Allocation/Freeing
+===================================================================
 
 Whether huge pages are allocated and freed via the /proc interface or
 the /sysfs interface using the nr_hugepages_mempolicy attribute, the NUMA
@@ -229,6 +230,7 @@ resulting effect on persistent huge page allocation is as follows:
    of huge pages over all on-lines nodes with memory.
 
 Per Node Hugepages Attributes
+=============================
 
 A subset of the contents of the root huge page control directory in sysfs,
 described above, will be replicated under each the system device of each
@@ -258,6 +260,7 @@ applied, from which node the huge page allocation will be attempted.
 
 
 Using Huge Pages
+================
 
 If the user applications are going to request huge pages using mmap system
 call, then it is required that system administrator mount a file system of
@@ -296,20 +299,16 @@ calls, though the mount of filesystem will be required for using mmap calls
 without MAP_HUGETLB.  For an example of how to use mmap with MAP_HUGETLB see
 map_hugetlb.c.
 
-*******************************************************************
+Examples
+========
 
-/*
- * map_hugetlb: see tools/testing/selftests/vm/map_hugetlb.c
- */
+1) map_hugetlb: see tools/testing/selftests/vm/map_hugetlb.c
 
-*******************************************************************
+2) hugepage-shm:  see tools/testing/selftests/vm/hugepage-shm.c
 
-/*
- * hugepage-shm:  see tools/testing/selftests/vm/hugepage-shm.c
- */
+3) hugepage-mmap:  see tools/testing/selftests/vm/hugepage-mmap.c
 
-*******************************************************************
-
-/*
- * hugepage-mmap:  see tools/testing/selftests/vm/hugepage-mmap.c
- */
+4) The libhugetlbfs (http://libhugetlbfs.sourceforge.net) library provides a
+   wide range of userspace tools to help with huge page usability, environment
+   setup, and control. Furthermore it provides useful test cases that should be
+   used when modifying code to ensure no regressions are introduced.
diff --git a/Documentation/vm/soft-dirty.txt b/Documentation/vm/soft-dirty.txt
index 9a12a5956bc0..55684d11a1e8 100644
--- a/Documentation/vm/soft-dirty.txt
+++ b/Documentation/vm/soft-dirty.txt
@@ -28,6 +28,13 @@ This is so, since the pages are still mapped to physical memory, and thus all
 the kernel does is finds this fact out and puts both writable and soft-dirty
 bits on the PTE.
 
+  While in most cases tracking memory changes by #PF-s is more than enough
+there is still a scenario when we can lose soft dirty bits -- a task
+unmaps a previously mapped memory region and then maps a new one at exactly
+the same place. When unmap is called, the kernel internally clears PTE values
+including soft dirty bits. To notify user space application about such
+memory region renewal the kernel always marks new memory regions (and
+expanded regions) as soft dirty.
 
   This feature is actively used by the checkpoint-restore project. You
 can find more details about it on http://criu.org
diff --git a/Documentation/workqueue.txt b/Documentation/workqueue.txt
index a6ab4b62d926..f81a65b54c29 100644
--- a/Documentation/workqueue.txt
+++ b/Documentation/workqueue.txt
@@ -85,32 +85,31 @@ workqueue.
 Special purpose threads, called worker threads, execute the functions
 off of the queue, one after the other.  If no work is queued, the
 worker threads become idle.  These worker threads are managed in so
-called thread-pools.
+called worker-pools.
 
 The cmwq design differentiates between the user-facing workqueues that
 subsystems and drivers queue work items on and the backend mechanism
-which manages thread-pools and processes the queued work items.
+which manages worker-pools and processes the queued work items.
 
-The backend is called gcwq.  There is one gcwq for each possible CPU
-and one gcwq to serve work items queued on unbound workqueues.  Each
-gcwq has two thread-pools - one for normal work items and the other
-for high priority ones.
+There are two worker-pools, one for normal work items and the other
+for high priority ones, for each possible CPU and some extra
+worker-pools to serve work items queued on unbound workqueues - the
+number of these backing pools is dynamic.
 
 Subsystems and drivers can create and queue work items through special
 workqueue API functions as they see fit. They can influence some
 aspects of the way the work items are executed by setting flags on the
 workqueue they are putting the work item on. These flags include
-things like CPU locality, reentrancy, concurrency limits, priority and
-more.  To get a detailed overview refer to the API description of
+things like CPU locality, concurrency limits, priority and more.  To
+get a detailed overview refer to the API description of
 alloc_workqueue() below.
 
-When a work item is queued to a workqueue, the target gcwq and
-thread-pool is determined according to the queue parameters and
-workqueue attributes and appended on the shared worklist of the
-thread-pool.  For example, unless specifically overridden, a work item
-of a bound workqueue will be queued on the worklist of either normal
-or highpri thread-pool of the gcwq that is associated to the CPU the
-issuer is running on.
+When a work item is queued to a workqueue, the target worker-pool is
+determined according to the queue parameters and workqueue attributes
+and appended on the shared worklist of the worker-pool.  For example,
+unless specifically overridden, a work item of a bound workqueue will
+be queued on the worklist of either normal or highpri worker-pool that
+is associated to the CPU the issuer is running on.
 
 For any worker pool implementation, managing the concurrency level
 (how many execution contexts are active) is an important issue.  cmwq
@@ -118,14 +117,14 @@ tries to keep the concurrency at a minimal but sufficient level.
 Minimal to save resources and sufficient in that the system is used at
 its full capacity.
 
-Each thread-pool bound to an actual CPU implements concurrency
-management by hooking into the scheduler.  The thread-pool is notified
+Each worker-pool bound to an actual CPU implements concurrency
+management by hooking into the scheduler.  The worker-pool is notified
 whenever an active worker wakes up or sleeps and keeps track of the
 number of the currently runnable workers.  Generally, work items are
 not expected to hog a CPU and consume many cycles.  That means
 maintaining just enough concurrency to prevent work processing from
 stalling should be optimal.  As long as there are one or more runnable
-workers on the CPU, the thread-pool doesn't start execution of a new
+workers on the CPU, the worker-pool doesn't start execution of a new
 work, but, when the last running worker goes to sleep, it immediately
 schedules a new worker so that the CPU doesn't sit idle while there
 are pending work items.  This allows using a minimal number of workers
@@ -135,19 +134,20 @@ Keeping idle workers around doesn't cost other than the memory space
 for kthreads, so cmwq holds onto idle ones for a while before killing
 them.
 
-For an unbound wq, the above concurrency management doesn't apply and
-the thread-pools for the pseudo unbound CPU try to start executing all
-work items as soon as possible.  The responsibility of regulating
-concurrency level is on the users.  There is also a flag to mark a
-bound wq to ignore the concurrency management.  Please refer to the
-API section for details.
+For unbound workqueues, the number of backing pools is dynamic.
+Unbound workqueue can be assigned custom attributes using
+apply_workqueue_attrs() and workqueue will automatically create
+backing worker pools matching the attributes.  The responsibility of
+regulating concurrency level is on the users.  There is also a flag to
+mark a bound wq to ignore the concurrency management.  Please refer to
+the API section for details.
 
 Forward progress guarantee relies on that workers can be created when
 more execution contexts are necessary, which in turn is guaranteed
 through the use of rescue workers.  All work items which might be used
 on code paths that handle memory reclaim are required to be queued on
 wq's that have a rescue-worker reserved for execution under memory
-pressure.  Else it is possible that the thread-pool deadlocks waiting
+pressure.  Else it is possible that the worker-pool deadlocks waiting
 for execution contexts to free up.
 
 
@@ -166,25 +166,15 @@ resources, scheduled and executed.
 
 @flags:
 
-  WQ_NON_REENTRANT
-
-	By default, a wq guarantees non-reentrance only on the same
-	CPU.  A work item may not be executed concurrently on the same
-	CPU by multiple workers but is allowed to be executed
-	concurrently on multiple CPUs.  This flag makes sure
-	non-reentrance is enforced across all CPUs.  Work items queued
-	to a non-reentrant wq are guaranteed to be executed by at most
-	one worker system-wide at any given time.
-
   WQ_UNBOUND
 
-	Work items queued to an unbound wq are served by a special
-	gcwq which hosts workers which are not bound to any specific
-	CPU.  This makes the wq behave as a simple execution context
-	provider without concurrency management.  The unbound gcwq
-	tries to start execution of work items as soon as possible.
-	Unbound wq sacrifices locality but is useful for the following
-	cases.
+	Work items queued to an unbound wq are served by the special
+	woker-pools which host workers which are not bound to any
+	specific CPU.  This makes the wq behave as a simple execution
+	context provider without concurrency management.  The unbound
+	worker-pools try to start execution of work items as soon as
+	possible.  Unbound wq sacrifices locality but is useful for
+	the following cases.
 
 	* Wide fluctuation in the concurrency level requirement is
 	  expected and using bound wq may end up creating large number
@@ -209,10 +199,10 @@ resources, scheduled and executed.
   WQ_HIGHPRI
 
 	Work items of a highpri wq are queued to the highpri
-	thread-pool of the target gcwq.  Highpri thread-pools are
+	worker-pool of the target cpu.  Highpri worker-pools are
 	served by worker threads with elevated nice level.
 
-	Note that normal and highpri thread-pools don't interact with
+	Note that normal and highpri worker-pools don't interact with
 	each other.  Each maintain its separate pool of workers and
 	implements concurrency management among its workers.
 
@@ -221,7 +211,7 @@ resources, scheduled and executed.
 	Work items of a CPU intensive wq do not contribute to the
 	concurrency level.  In other words, runnable CPU intensive
 	work items will not prevent other work items in the same
-	thread-pool from starting execution.  This is useful for bound
+	worker-pool from starting execution.  This is useful for bound
 	work items which are expected to hog CPU cycles so that their
 	execution is regulated by the system scheduler.
 
@@ -233,6 +223,10 @@ resources, scheduled and executed.
 
 	This flag is meaningless for unbound wq.
 
+Note that the flag WQ_NON_REENTRANT no longer exists as all workqueues
+are now non-reentrant - any work item is guaranteed to be executed by
+at most one worker system-wide at any given time.
+
 @max_active:
 
 @max_active determines the maximum number of execution contexts per
@@ -254,9 +248,9 @@ recommended.
 
 Some users depend on the strict execution ordering of ST wq.  The
 combination of @max_active of 1 and WQ_UNBOUND is used to achieve this
-behavior.  Work items on such wq are always queued to the unbound gcwq
-and only one work item can be active at any given time thus achieving
-the same ordering property as ST wq.
+behavior.  Work items on such wq are always queued to the unbound
+worker-pools and only one work item can be active at any given time thus
+achieving the same ordering property as ST wq.
 
 
 5. Example Execution Scenarios
diff --git a/Documentation/x86/boot.txt b/Documentation/x86/boot.txt
index fc66d42422ee..f4f268c2b826 100644
--- a/Documentation/x86/boot.txt
+++ b/Documentation/x86/boot.txt
@@ -58,7 +58,7 @@ Protocol 2.11:	(Kernel 3.6) Added a field for offset of EFI handover
 		protocol entry point.
 
 Protocol 2.12:	(Kernel 3.8) Added the xloadflags field and extension fields
-	 	to struct boot_params for for loading bzImage and ramdisk
+	 	to struct boot_params for loading bzImage and ramdisk
 		above 4G in 64bit.
 
 **** MEMORY LAYOUT
diff --git a/Documentation/x86/x86_64/boot-options.txt b/Documentation/x86/x86_64/boot-options.txt
index e9e8ddbbf376..1228b22e142b 100644
--- a/Documentation/x86/x86_64/boot-options.txt
+++ b/Documentation/x86/x86_64/boot-options.txt
@@ -176,6 +176,11 @@ ACPI
 
   acpi=noirq	Don't route interrupts
 
+  acpi=nocmcff	Disable firmware first mode for corrected errors. This
+		disables parsing the HEST CMC error source to check if
+		firmware has set the FF flag. This may result in
+		duplicate corrected error reports.
+
 PCI
 
   pci=off		Don't use PCI
diff --git a/Documentation/zh_CN/SubmittingPatches b/Documentation/zh_CN/SubmittingPatches
index 0f4385a62a49..be0bd4725062 100644
--- a/Documentation/zh_CN/SubmittingPatches
+++ b/Documentation/zh_CN/SubmittingPatches
@@ -146,7 +146,7 @@ Majordomo lists of VGER.KERNEL.ORG at:
         <http://vger.kernel.org/vger-lists.html>
 
 如果改动影响了用户空间和内核之间的接口，请给 MAN-PAGES 的维护者（列在
-MAITAINERS 文件里的）发送一个手册页（man-pages）补丁，或者至少通知一下改
+MAINTAINERS 文件里的）发送一个手册页（man-pages）补丁，或者至少通知一下改
 变，让一些信息有途径进入手册页。
 
 即使在第四步的时候，维护者没有作出回应，也要确认在修改他们的代码的时候
diff --git a/MAINTAINERS b/MAINTAINERS
index b140c8123098..a7c34ef3509d 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -237,11 +237,11 @@ F:	drivers/platform/x86/acer-wmi.c
 
 ACPI
 M:	Len Brown <lenb@kernel.org>
-M:	Rafael J. Wysocki <rjw@sisk.pl>
+M:	Rafael J. Wysocki <rjw@rjwysocki.net>
 L:	linux-acpi@vger.kernel.org
-W:	http://www.lesswatts.org/projects/acpi/
-Q:	http://patchwork.kernel.org/project/linux-acpi/list/
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/lenb/linux
+W:	https://01.org/linux-acpi
+Q:	https://patchwork.kernel.org/project/linux-acpi/list/
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm
 S:	Supported
 F:	drivers/acpi/
 F:	drivers/pnp/pnpacpi/
@@ -256,21 +256,21 @@ F:	drivers/pci/*/*/*acpi*
 ACPI FAN DRIVER
 M:	Zhang Rui <rui.zhang@intel.com>
 L:	linux-acpi@vger.kernel.org
-W:	http://www.lesswatts.org/projects/acpi/
+W:	https://01.org/linux-acpi
 S:	Supported
 F:	drivers/acpi/fan.c
 
 ACPI THERMAL DRIVER
 M:	Zhang Rui <rui.zhang@intel.com>
 L:	linux-acpi@vger.kernel.org
-W:	http://www.lesswatts.org/projects/acpi/
+W:	https://01.org/linux-acpi
 S:	Supported
 F:	drivers/acpi/*thermal*
 
 ACPI VIDEO DRIVER
 M:	Zhang Rui <rui.zhang@intel.com>
 L:	linux-acpi@vger.kernel.org
-W:	http://www.lesswatts.org/projects/acpi/
+W:	https://01.org/linux-acpi
 S:	Supported
 F:	drivers/acpi/video.c
 
@@ -580,12 +580,24 @@ L:	linux-media@vger.kernel.org
 S:	Maintained
 F:	drivers/media/i2c/ad9389b*
 
+ANALOG DEVICES INC ADV7511 DRIVER
+M:	Hans Verkuil <hans.verkuil@cisco.com>
+L:	linux-media@vger.kernel.org
+S:	Maintained
+F:	drivers/media/i2c/adv7511*
+
 ANALOG DEVICES INC ADV7604 DRIVER
 M:	Hans Verkuil <hans.verkuil@cisco.com>
 L:	linux-media@vger.kernel.org
 S:	Maintained
 F:	drivers/media/i2c/adv7604*
 
+ANALOG DEVICES INC ADV7842 DRIVER
+M:	Hans Verkuil <hans.verkuil@cisco.com>
+L:	linux-media@vger.kernel.org
+S:	Maintained
+F:	drivers/media/i2c/adv7842*
+
 ANALOG DEVICES INC ASOC CODEC DRIVERS
 M:	Lars-Peter Clausen <lars@metafoo.de>
 L:	device-drivers-devel@blackfin.uclinux.org
@@ -595,6 +607,7 @@ S:	Supported
 F:	sound/soc/codecs/adau*
 F:	sound/soc/codecs/adav*
 F:	sound/soc/codecs/ad1*
+F:	sound/soc/codecs/ad7*
 F:	sound/soc/codecs/ssm*
 F:	sound/soc/codecs/sigmadsp.*
 
@@ -638,6 +651,12 @@ S:	Maintained
 F:	drivers/net/appletalk/
 F:	net/appletalk/
 
+APTINA CAMERA SENSOR PLL
+M:	Laurent Pinchart <Laurent.pinchart@ideasonboard.com>
+L:	linux-media@vger.kernel.org
+S:	Maintained
+F:	drivers/media/i2c/aptina-pll.*
+
 ARASAN COMPACT FLASH PATA CONTROLLER
 M:	Viresh Kumar <viresh.linux@gmail.com>
 L:	linux-ide@vger.kernel.org
@@ -805,15 +824,21 @@ S:	Maintained
 F:	arch/arm/mach-gemini/
 
 ARM/CSR SIRFPRIMA2 MACHINE SUPPORT
-M:	Barry Song <baohua.song@csr.com>
+M:	Barry Song <baohua@kernel.org>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/baohua/linux.git
 S:	Maintained
 F:	arch/arm/mach-prima2/
+F:	drivers/clk/clk-prima2.c
+F:	drivers/clocksource/timer-prima2.c
+F:	drivers/clocksource/timer-marco.c
 F:	drivers/dma/sirf-dma.c
 F:	drivers/i2c/busses/i2c-sirf.c
+F:	drivers/input/misc/sirfsoc-onkey.c
+F:	drivers/irqchip/irq-sirfsoc.c
 F:	drivers/mmc/host/sdhci-sirf.c
-F:	drivers/pinctrl/pinctrl-sirf.c
+F:	drivers/pinctrl/sirf/
+F:	drivers/rtc/rtc-sirfsoc.c
 F:	drivers/spi/spi-sirf.c
 
 ARM/EBSA110 MACHINE SUPPORT
@@ -914,24 +939,24 @@ F:	arch/arm/mach-pxa/colibri-pxa270-income.c
 
 ARM/INTEL IOP32X ARM ARCHITECTURE
 M:	Lennert Buytenhek <kernel@wantstofly.org>
-M:	Dan Williams <djbw@fb.com>
+M:	Dan Williams <dan.j.williams@intel.com>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
 
 ARM/INTEL IOP33X ARM ARCHITECTURE
-M:	Dan Williams <djbw@fb.com>
+M:	Dan Williams <dan.j.williams@intel.com>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
 
 ARM/INTEL IOP13XX ARM ARCHITECTURE
 M:	Lennert Buytenhek <kernel@wantstofly.org>
-M:	Dan Williams <djbw@fb.com>
+M:	Dan Williams <dan.j.williams@intel.com>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
 
 ARM/INTEL IQ81342EX MACHINE SUPPORT
 M:	Lennert Buytenhek <kernel@wantstofly.org>
-M:	Dan Williams <djbw@fb.com>
+M:	Dan Williams <dan.j.williams@intel.com>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
 
@@ -956,7 +981,7 @@ F:	drivers/pcmcia/pxa2xx_stargate2.c
 
 ARM/INTEL XSC3 (MANZANO) ARM CORE
 M:	Lennert Buytenhek <kernel@wantstofly.org>
-M:	Dan Williams <djbw@fb.com>
+M:	Dan Williams <dan.j.williams@intel.com>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
 
@@ -1009,7 +1034,7 @@ F:	arch/arm/mach-orion5x/ts78xx-*
 ARM/MICREL KS8695 ARCHITECTURE
 M:	Greg Ungerer <gerg@uclinux.org>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
-F:	arch/arm/mach-ks8695
+F:	arch/arm/mach-ks8695/
 S:	Odd Fixes
 
 ARM/MIOA701 MACHINE SUPPORT
@@ -1029,7 +1054,6 @@ M:	STEricsson <STEricsson_nomadik_linux@list.st.com>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
 F:	arch/arm/mach-nomadik/
-F:	arch/arm/plat-nomadik/
 F:	drivers/i2c/busses/i2c-nomadik.c
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/linusw/linux-nomadik.git
 
@@ -1051,7 +1075,7 @@ F:	drivers/mmc/host/msm_sdcc.h
 F:	drivers/tty/serial/msm_serial.h
 F:	drivers/tty/serial/msm_serial.c
 F:	drivers/*/pm8???-*
-F:	drivers/ssbi/
+F:	drivers/mfd/ssbi/
 F:	include/linux/mfd/pm8xxx/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/davidb/linux-msm.git
 S:	Maintained
@@ -1137,7 +1161,6 @@ L:	linux-samsung-soc@vger.kernel.org (moderated for non-subscribers)
 W:	http://www.fluff.org/ben/linux/
 S:	Maintained
 F:	arch/arm/plat-samsung/
-F:	arch/arm/plat-s3c24xx/
 F:	arch/arm/mach-s3c24*/
 F:	arch/arm/mach-s3c64xx/
 F:	drivers/*/*s3c2410*
@@ -1160,8 +1183,6 @@ L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
 F:	arch/arm/mach-s5pv210/mach-aquila.c
 F:	arch/arm/mach-s5pv210/mach-goni.c
-F:	arch/arm/mach-exynos/mach-universal_c210.c
-F:	arch/arm/mach-exynos/mach-nuri.c
 
 ARM/SAMSUNG S5P SERIES 2D GRAPHICS ACCELERATION (G2D) SUPPORT
 M:	Kyungmin Park <kyungmin.park@samsung.com>
@@ -1301,13 +1322,12 @@ L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
 F:	arch/arm/mach-vt8500/
 F:	drivers/clocksource/vt8500_timer.c
-F:	drivers/gpio/gpio-vt8500.c
 F:	drivers/i2c/busses/i2c-wmt.c
 F:	drivers/mmc/host/wmt-sdmmc.c
 F:	drivers/pwm/pwm-vt8500.c
 F:	drivers/rtc/rtc-vt8500.c
 F:	drivers/tty/serial/vt8500_serial.c
-F:	drivers/usb/host/ehci-vt8500.c
+F:	drivers/usb/host/ehci-platform.c
 F:	drivers/usb/host/uhci-platform.c
 F:	drivers/video/vt8500lcdfb.*
 F:	drivers/video/wm8505fb*
@@ -1368,7 +1388,7 @@ F:	drivers/platform/x86/asus*.c
 F:	drivers/platform/x86/eeepc*.c
 
 ASYNCHRONOUS TRANSFERS/TRANSFORMS (IOAT) API
-M:	Dan Williams <djbw@fb.com>
+M:	Dan Williams <dan.j.williams@intel.com>
 W:	http://sourceforge.net/projects/xscaleiop
 S:	Maintained
 F:	Documentation/crypto/async-tx-api.txt
@@ -1547,6 +1567,13 @@ W:	http://atmelwlandriver.sourceforge.net/
 S:	Maintained
 F:	drivers/net/wireless/atmel*
 
+ATTO EXPRESSSAS SAS/SATA RAID SCSI DRIVER
+M:      Bradley Grove <linuxdrivers@attotech.com>
+L:      linux-scsi@vger.kernel.org
+W:      http://www.attotech.com
+S:      Supported
+F:      drivers/scsi/esas2r
+
 AUDIT SUBSYSTEM
 M:	Al Viro <viro@zeniv.linux.org.uk>
 M:	Eric Paris <eparis@redhat.com>
@@ -1790,6 +1817,18 @@ L:	netdev@vger.kernel.org
 S:	Supported
 F:	drivers/net/ethernet/broadcom/bnx2x/
 
+BROADCOM BCM281XX/BCM11XXX ARM ARCHITECTURE
+M:	Christian Daudt <bcm@fixthebug.org>
+L:	bcm-kernel-feedback-list@broadcom.com
+T:	git git://git.github.com/broadcom/bcm11351
+S:	Maintained
+F:	arch/arm/mach-bcm/
+F:	arch/arm/boot/dts/bcm113*
+F:	arch/arm/boot/dts/bcm281*
+F:	arch/arm/configs/bcm_defconfig
+F:	drivers/mmc/host/sdhci_bcm_kona.c
+F:	drivers/clocksource/bcm_kona_timer.c
+
 BROADCOM BCM2835 ARM ARCHICTURE
 M:	Stephen Warren <swarren@wwwdotorg.org>
 L:	linux-rpi-kernel@lists.infradead.org (moderated for non-subscribers)
@@ -1823,6 +1862,12 @@ L:	linux-scsi@vger.kernel.org
 S:	Supported
 F:	drivers/scsi/bnx2fc/
 
+BROADCOM BNX2I 1/10 GIGABIT iSCSI DRIVER
+M:	Eddie Wai <eddie.wai@broadcom.com>
+L:	linux-scsi@vger.kernel.org
+S:	Supported
+F:	drivers/scsi/bnx2i/
+
 BROADCOM SPECIFIC AMBA DRIVER (BCMA)
 M:	Rafał Miłecki <zajec5@gmail.com>
 L:	linux-wireless@vger.kernel.org
@@ -2004,10 +2049,10 @@ W:	http://ceph.com/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client.git
 S:	Supported
 F:	Documentation/filesystems/ceph.txt
-F:	fs/ceph
-F:	net/ceph
-F:	include/linux/ceph
-F:	include/linux/crush
+F:	fs/ceph/
+F:	net/ceph/
+F:	include/linux/ceph/
+F:	include/linux/crush/
 
 CERTIFIED WIRELESS USB (WUSB) SUBSYSTEM:
 L:	linux-usb@vger.kernel.org
@@ -2076,7 +2121,8 @@ F:	drivers/usb/chipidea/
 
 CISCO VIC ETHERNET NIC DRIVER
 M:	Christian Benvenuti <benve@cisco.com>
-M:	Roopa Prabhu <roprabhu@cisco.com>
+M:	Sujith Sankar <ssujith@cisco.com>
+M:	Govindarajulu Varadarajan <govindarajulu90@gmail.com>
 M:	Neel Patel <neepatel@cisco.com>
 M:	Nishank Trivedi <nistrive@cisco.com>
 S:	Supported
@@ -2112,6 +2158,13 @@ M:	Russell King <linux@arm.linux.org.uk>
 S:	Maintained
 F:	include/linux/clk.h
 
+CLOCKSOURCE, CLOCKEVENT DRIVERS
+M:	Daniel Lezcano <daniel.lezcano@linaro.org>
+M:	Thomas Gleixner <tglx@linutronix.de>
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git timers/core
+S:	Supported
+F:	drivers/clocksource
+
 CISCO FCOE HBA DRIVER
 M:	Hiral Patel <hiralpat@cisco.com>
 M:	Suma Ramars <sramars@cisco.com>
@@ -2247,7 +2300,7 @@ S:	Maintained
 F:	drivers/net/ethernet/ti/cpmac.c
 
 CPU FREQUENCY DRIVERS
-M:	Rafael J. Wysocki <rjw@sisk.pl>
+M:	Rafael J. Wysocki <rjw@rjwysocki.net>
 M:	Viresh Kumar <viresh.kumar@linaro.org>
 L:	cpufreq@vger.kernel.org
 L:	linux-pm@vger.kernel.org
@@ -2268,8 +2321,17 @@ F:	drivers/cpufreq/arm_big_little.h
 F:	drivers/cpufreq/arm_big_little.c
 F:	drivers/cpufreq/arm_big_little_dt.c
 
+CPUIDLE DRIVER - ARM BIG LITTLE
+M:      Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
+M:      Daniel Lezcano <daniel.lezcano@linaro.org>
+L:      linux-pm@vger.kernel.org
+L:      linux-arm-kernel@lists.infradead.org
+T:      git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm.git
+S:      Maintained
+F:      drivers/cpuidle/cpuidle-big_little.c
+
 CPUIDLE DRIVERS
-M:	Rafael J. Wysocki <rjw@sisk.pl>
+M:	Rafael J. Wysocki <rjw@rjwysocki.net>
 M:	Daniel Lezcano <daniel.lezcano@linaro.org>
 L:	linux-pm@vger.kernel.org
 S:	Maintained
@@ -2287,7 +2349,7 @@ CPU POWER MONITORING SUBSYSTEM
 M:	Dominik Brodowski <linux@dominikbrodowski.net>
 M:	Thomas Renninger <trenn@suse.de>
 S:	Maintained
-F:	tools/power/cpupower
+F:	tools/power/cpupower/
 
 CPUSETS
 M:	Li Zefan <lizefan@huawei.com>
@@ -2454,9 +2516,9 @@ S:	Maintained
 F:	drivers/media/common/cypress_firmware*
 
 CYTTSP TOUCHSCREEN DRIVER
-M:	Javier Martinez Canillas <javier@dowhile0.org>
+M:	Ferruh Yigit <fery@cypress.com>
 L:	linux-input@vger.kernel.org
-S:	Maintained
+S:	Supported
 F:	drivers/input/touchscreen/cyttsp*
 F:	include/linux/input/cyttsp.h
 
@@ -2584,6 +2646,18 @@ F:	include/linux/device-mapper.h
 F:	include/linux/dm-*.h
 F:	include/uapi/linux/dm-*.h
 
+DIGI NEO AND CLASSIC PCI PRODUCTS
+M:	Lidza Louina <lidza.louina@gmail.com>
+L:	driverdev-devel@linuxdriverproject.org
+S:	Maintained
+F:	drivers/staging/dgnc/
+
+DIGI EPCA PCI PRODUCTS
+M:	Lidza Louina <lidza.louina@gmail.com>
+L:	driverdev-devel@linuxdriverproject.org
+S:	Maintained
+F:	drivers/staging/dgap/
+
 DIOLAN U2C-12 I2C DRIVER
 M:	Guenter Roeck <linux@roeck-us.net>
 L:	linux-i2c@vger.kernel.org
@@ -2643,7 +2717,7 @@ T:	git git://git.linaro.org/people/sumitsemwal/linux-dma-buf.git
 
 DMA GENERIC OFFLOAD ENGINE SUBSYSTEM
 M:	Vinod Koul <vinod.koul@intel.com>
-M:	Dan Williams <djbw@fb.com>
+M:	Dan Williams <dan.j.williams@intel.com>
 S:	Supported
 F:	drivers/dma/
 F:	include/linux/dma*
@@ -2725,7 +2799,7 @@ L:	intel-gfx@lists.freedesktop.org
 L:	dri-devel@lists.freedesktop.org
 T:	git git://people.freedesktop.org/~danvet/drm-intel
 S:	Supported
-F:	drivers/gpu/drm/i915
+F:	drivers/gpu/drm/i915/
 F:	include/drm/i915*
 F:	include/uapi/drm/i915*
 
@@ -2737,7 +2811,7 @@ M:	Kyungmin Park <kyungmin.park@samsung.com>
 L:	dri-devel@lists.freedesktop.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/daeinki/drm-exynos.git
 S:	Supported
-F:	drivers/gpu/drm/exynos
+F:	drivers/gpu/drm/exynos/
 F:	include/drm/exynos*
 F:	include/uapi/drm/exynos*
 
@@ -2990,7 +3064,7 @@ M:	Mauro Carvalho Chehab <m.chehab@samsung.com>
 L:	linux-edac@vger.kernel.org
 W:	bluesmoke.sourceforge.net
 S:	Maintained
-F:	drivers/edac/ghes-edac.c
+F:	drivers/edac/ghes_edac.c
 
 EDAC-I82443BXGX
 M:	Tim Small <tim@buttersideup.com>
@@ -3479,7 +3553,7 @@ F:	fs/freevxfs/
 
 FREEZER
 M:	Pavel Machek <pavel@ucw.cz>
-M:	"Rafael J. Wysocki" <rjw@sisk.pl>
+M:	"Rafael J. Wysocki" <rjw@rjwysocki.net>
 L:	linux-pm@vger.kernel.org
 S:	Supported
 F:	Documentation/power/freezing-of-tasks.txt
@@ -3550,6 +3624,12 @@ L:	linux-scsi@vger.kernel.org
 S:	Odd Fixes (e.g., new signatures)
 F:	drivers/scsi/fdomain.*
 
+GCOV BASED KERNEL PROFILING
+M:	Peter Oberparleiter <oberpar@linux.vnet.ibm.com>
+S:	Maintained
+F:	kernel/gcov/
+F:	Documentation/gcov.txt
+
 GDT SCSI DISK ARRAY CONTROLLER DRIVER
 M:	Achim Leubner <achim_leubner@adaptec.com>
 L:	linux-scsi@vger.kernel.org
@@ -3596,8 +3676,8 @@ M:	Arnd Bergmann <arnd@arndb.de>
 L:	linux-arch@vger.kernel.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/arnd/asm-generic.git
 S:	Maintained
-F:	include/asm-generic
-F:	include/uapi/asm-generic
+F:	include/asm-generic/
+F:	include/uapi/asm-generic/
 
 GENERIC UIO DRIVER FOR PCI DEVICES
 M:	"Michael S. Tsirkin" <mst@redhat.com>
@@ -3639,7 +3719,8 @@ GRE DEMULTIPLEXER DRIVER
 M:	Dmitry Kozlov <xeb@mail.ru>
 L:	netdev@vger.kernel.org
 S:	Maintained
-F:	net/ipv4/gre.c
+F:	net/ipv4/gre_demux.c
+F:	net/ipv4/gre_offload.c
 F:	include/net/gre.h
 
 GRETH 10/100/1G Ethernet MAC device driver
@@ -3717,7 +3798,7 @@ L:	linux-media@vger.kernel.org
 T:	git git://linuxtv.org/media_tree.git
 W:	http://linuxtv.org
 S:	Odd Fixes
-F:	drivers/media/usb/hdpvr
+F:	drivers/media/usb/hdpvr/
 
 HWPOISON MEMORY FAILURE HANDLING
 M:	Andi Kleen <andi@firstfloor.org>
@@ -3814,7 +3895,7 @@ F:	drivers/video/hgafb.c
 
 HIBERNATION (aka Software Suspend, aka swsusp)
 M:	Pavel Machek <pavel@ucw.cz>
-M:	"Rafael J. Wysocki" <rjw@sisk.pl>
+M:	"Rafael J. Wysocki" <rjw@rjwysocki.net>
 L:	linux-pm@vger.kernel.org
 S:	Supported
 F:	arch/x86/power/
@@ -4101,6 +4182,13 @@ W:	http://launchpad.net/ideapad-laptop
 S:	Maintained
 F:	drivers/platform/x86/ideapad-laptop.c
 
+IDEAPAD LAPTOP SLIDEBAR DRIVER
+M:	Andrey Moiseev <o2g.org.ru@gmail.com>
+L:	linux-input@vger.kernel.org
+W:	https://github.com/o2genum/ideapad-slidebar
+S:	Maintained
+F:	drivers/input/misc/ideapad_slidebar.c
+
 IDE/ATAPI DRIVERS
 M:	Borislav Petkov <bp@alien8.de>
 L:	linux-ide@vger.kernel.org
@@ -4257,7 +4345,7 @@ F:	drivers/video/i810/
 INTEL MENLOW THERMAL DRIVER
 M:	Sujith Thomas <sujith.thomas@intel.com>
 L:	platform-driver-x86@vger.kernel.org
-W:	http://www.lesswatts.org/projects/acpi/
+W:	https://01.org/linux-acpi
 S:	Supported
 F:	drivers/platform/x86/intel_menlow.c
 
@@ -4268,7 +4356,7 @@ F:	arch/x86/kernel/microcode_core.c
 F:	arch/x86/kernel/microcode_intel.c
 
 INTEL I/OAT DMA DRIVER
-M:	Dan Williams <djbw@fb.com>
+M:	Dan Williams <dan.j.williams@intel.com>
 S:	Maintained
 F:	drivers/dma/ioat*
 
@@ -4281,7 +4369,7 @@ F:	drivers/iommu/intel-iommu.c
 F:	include/linux/intel-iommu.h
 
 INTEL IOP-ADMA DMA DRIVER
-M:	Dan Williams <djbw@fb.com>
+M:	Dan Williams <dan.j.williams@intel.com>
 S:	Odd fixes
 F:	drivers/dma/iop-adma.c
 
@@ -4300,7 +4388,7 @@ M:	Deepak Saxena <dsaxena@plexity.net>
 S:	Maintained
 F:	drivers/char/hw_random/ixp4xx-rng.c
 
-INTEL ETHERNET DRIVERS (e100/e1000/e1000e/igb/igbvf/ixgb/ixgbe/ixgbevf)
+INTEL ETHERNET DRIVERS (e100/e1000/e1000e/igb/igbvf/ixgb/ixgbe/ixgbevf/i40e)
 M:	Jeff Kirsher <jeffrey.t.kirsher@intel.com>
 M:	Jesse Brandeburg <jesse.brandeburg@intel.com>
 M:	Bruce Allan <bruce.w.allan@intel.com>
@@ -4325,6 +4413,7 @@ F:	Documentation/networking/igbvf.txt
 F:	Documentation/networking/ixgb.txt
 F:	Documentation/networking/ixgbe.txt
 F:	Documentation/networking/ixgbevf.txt
+F:	Documentation/networking/i40e.txt
 F:	drivers/net/ethernet/intel/
 
 INTEL PRO/WIRELESS 2100, 2200BG, 2915ABG NETWORK CONNECTION SUPPORT
@@ -4365,7 +4454,7 @@ F:	drivers/net/wireless/iwlegacy/
 
 INTEL WIRELESS WIFI LINK (iwlwifi)
 M:	Johannes Berg <johannes.berg@intel.com>
-M:	Wey-Yi Guy <wey-yi.w.guy@intel.com>
+M:	Emmanuel Grumbach <emmanuel.grumbach@intel.com>
 M:	Intel Linux Wireless <ilw@linux.intel.com>
 L:	linux-wireless@vger.kernel.org
 W:	http://intellinuxwireless.org
@@ -4393,6 +4482,13 @@ L:	linux-serial@vger.kernel.org
 S:	Maintained
 F:	drivers/tty/serial/ioc3_serial.c
 
+IOMMU DRIVERS
+M:	Joerg Roedel <joro@8bytes.org>
+L:	iommu@lists.linux-foundation.org
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu.git
+S:	Maintained
+F:	drivers/iommu/
+
 IP MASQUERADING
 M:	Juanjo Ciarlante <jjciarla@raiz.uncu.edu.ar>
 S:	Maintained
@@ -4518,7 +4614,7 @@ S:	Supported
 W:	http://www.openfabrics.org
 W:	www.open-iscsi.org
 Q:	http://patchwork.kernel.org/project/linux-rdma/list/
-F:	drivers/infiniband/ulp/iser
+F:	drivers/infiniband/ulp/iser/
 
 ISDN SUBSYSTEM
 M:	Karsten Keil <isdn@linux-pingi.de>
@@ -4572,7 +4668,7 @@ W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
 T:	git git://linuxtv.org/anttip/media_tree.git
 S:	Maintained
-F:	drivers/media/tuners/it913x*
+F:	drivers/media/tuners/tuner_it913x*
 
 IVTV VIDEO4LINUX DRIVER
 M:	Andy Walls <awalls@md.metrocast.net>
@@ -5396,6 +5492,7 @@ F:	drivers/watchdog/mena21_wdt.c
 
 METAG ARCHITECTURE
 M:	James Hogan <james.hogan@imgtec.com>
+L:	linux-metag@vger.kernel.org
 S:	Supported
 F:	arch/metag/
 F:	Documentation/metag/
@@ -5497,7 +5594,7 @@ L:	platform-driver-x86@vger.kernel.org
 S:	Supported
 F:	drivers/platform/x86/msi-wmi.c
 
-MT9M032 SENSOR DRIVER
+MT9M032 APTINA SENSOR DRIVER
 M:	Laurent Pinchart <laurent.pinchart@ideasonboard.com>
 L:	linux-media@vger.kernel.org
 T:	git git://linuxtv.org/media_tree.git
@@ -5505,7 +5602,7 @@ S:	Maintained
 F:	drivers/media/i2c/mt9m032.c
 F:	include/media/mt9m032.h
 
-MT9P031 SENSOR DRIVER
+MT9P031 APTINA CAMERA SENSOR
 M:	Laurent Pinchart <laurent.pinchart@ideasonboard.com>
 L:	linux-media@vger.kernel.org
 T:	git git://linuxtv.org/media_tree.git
@@ -5513,7 +5610,7 @@ S:	Maintained
 F:	drivers/media/i2c/mt9p031.c
 F:	include/media/mt9p031.h
 
-MT9T001 SENSOR DRIVER
+MT9T001 APTINA CAMERA SENSOR
 M:	Laurent Pinchart <laurent.pinchart@ideasonboard.com>
 L:	linux-media@vger.kernel.org
 T:	git git://linuxtv.org/media_tree.git
@@ -5521,7 +5618,7 @@ S:	Maintained
 F:	drivers/media/i2c/mt9t001.c
 F:	include/media/mt9t001.h
 
-MT9V032 SENSOR DRIVER
+MT9V032 APTINA CAMERA SENSOR
 M:	Laurent Pinchart <laurent.pinchart@ideasonboard.com>
 L:	linux-media@vger.kernel.org
 T:	git git://linuxtv.org/media_tree.git
@@ -5792,7 +5889,7 @@ M:	Aloisio Almeida Jr <aloisio.almeida@openbossa.org>
 M:	Samuel Ortiz <sameo@linux.intel.com>
 L:	linux-wireless@vger.kernel.org
 L:	linux-nfc@lists.01.org (moderated for non-subscribers)
-S:	Maintained
+S:	Supported
 F:	net/nfc/
 F:	include/net/nfc/
 F:	include/uapi/linux/nfc.h
@@ -5843,6 +5940,8 @@ F:	drivers/scsi/nsp32*
 NTB DRIVER
 M:	Jon Mason <jon.mason@intel.com>
 S:	Supported
+W:	https://github.com/jonmason/ntb/wiki
+T:	git git://github.com/jonmason/ntb.git
 F:	drivers/ntb/
 F:	drivers/net/ntb_netdev.c
 F:	include/linux/ntb.h
@@ -5905,15 +6004,12 @@ S:	Maintained
 F:	arch/arm/*omap*/*pm*
 F:	drivers/cpufreq/omap-cpufreq.c
 
-OMAP POWERDOMAIN/CLOCKDOMAIN SOC ADAPTATION LAYER SUPPORT
+OMAP POWERDOMAIN SOC ADAPTATION LAYER SUPPORT
 M:	Rajendra Nayak <rnayak@ti.com>
 M:	Paul Walmsley <paul@pwsan.com>
 L:	linux-omap@vger.kernel.org
 S:	Maintained
-F:	arch/arm/mach-omap2/powerdomain2xxx_3xxx.c
-F:	arch/arm/mach-omap2/powerdomain44xx.c
-F:	arch/arm/mach-omap2/clockdomain2xxx_3xxx.c
-F:	arch/arm/mach-omap2/clockdomain44xx.c
+F:	arch/arm/mach-omap2/prm*
 
 OMAP AUDIO SUPPORT
 M:	Peter Ujfalusi <peter.ujfalusi@ti.com>
@@ -6079,7 +6175,7 @@ W:	http://openrisc.net
 L:	linux@lists.openrisc.net (moderated for non-subscribers)
 S:	Maintained
 T:	git git://openrisc.net/~jonas/linux
-F:	arch/openrisc
+F:	arch/openrisc/
 
 OPENVSWITCH
 M:	Jesse Gross <jesse@nicira.com>
@@ -6275,6 +6371,13 @@ F:	Documentation/PCI/
 F:	drivers/pci/
 F:	include/linux/pci*
 
+PCI DRIVER FOR NVIDIA TEGRA
+M:	Thierry Reding <thierry.reding@gmail.com>
+L:	linux-tegra@vger.kernel.org
+S:	Supported
+F:	Documentation/devicetree/bindings/pci/nvidia,tegra20-pcie.txt
+F:	drivers/pci/host/pci-tegra.c
+
 PCMCIA SUBSYSTEM
 P:	Linux PCMCIA Team
 L:	linux-pcmcia@lists.infradead.org
@@ -6363,7 +6466,7 @@ M:	Jamie Iles <jamie@jamieiles.com>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 T:	git git://github.com/jamieiles/linux-2.6-ji.git
 S:	Supported
-F:	arch/arm/mach-picoxcell
+F:	arch/arm/mach-picoxcell/
 F:	drivers/*/picoxcell*
 F:	drivers/*/*/picoxcell*
 
@@ -6524,7 +6627,7 @@ S:	Obsolete
 F:	drivers/net/wireless/prism54/
 
 PROMISE SATA TX2/TX4 CONTROLLER LIBATA DRIVER
-M:	Mikael Pettersson <mikpe@it.uu.se>
+M:	Mikael Pettersson <mikpelinux@gmail.com>
 L:	linux-ide@vger.kernel.org
 S:	Maintained
 F:	drivers/ata/sata_promise.*
@@ -6636,7 +6739,7 @@ F:	drivers/spi/spi-pxa2xx*
 F:	drivers/usb/gadget/pxa2*
 F:	include/sound/pxa2xx-lib.h
 F:	sound/arm/pxa*
-F:	sound/soc/pxa
+F:	sound/soc/pxa/
 
 MMP SUPPORT
 M:	Eric Miao <eric.y.miao@gmail.com>
@@ -6676,11 +6779,11 @@ F:	Documentation/scsi/LICENSE.qla2xxx
 F:	drivers/scsi/qla2xxx/
 
 QLOGIC QLA4XXX iSCSI DRIVER
-M:	Ravi Anand <ravi.anand@qlogic.com>
 M:	Vikas Chaudhary <vikas.chaudhary@qlogic.com>
 M:	iscsi-driver@qlogic.com
 L:	linux-scsi@vger.kernel.org
 S:	Supported
+F:	Documentation/scsi/LICENSE.qla4xxx
 F:	drivers/scsi/qla4xxx/
 
 QLOGIC QLA3XXX NETWORK DRIVER
@@ -6921,6 +7024,14 @@ M:	Maxim Levitsky <maximlevitsky@gmail.com>
 S:	Maintained
 F:	drivers/memstick/host/r592.*
 
+ROCCAT DRIVERS
+M:	Stefan Achatz <erazor_de@users.sourceforge.net>
+W:	http://sourceforge.net/projects/roccat/
+S:	Maintained
+F:	drivers/hid/hid-roccat*
+F:	include/linux/hid-roccat*
+F:	Documentation/ABI/*/sysfs-driver-hid-roccat*
+
 ROCKETPORT DRIVER
 P:	Comtrol Corp.
 W:	http://www.comtrol.com
@@ -7081,7 +7192,7 @@ SAMSUNG AUDIO (ASoC) DRIVERS
 M:	Sangbeom Kim <sbkim73@samsung.com>
 L:	alsa-devel@alsa-project.org (moderated for non-subscribers)
 S:	Supported
-F:	sound/soc/samsung
+F:	sound/soc/samsung/
 
 SAMSUNG FRAMEBUFFER DRIVER
 M:	Jingoo Han <jg1.han@samsung.com>
@@ -7127,10 +7238,11 @@ SERIAL DRIVERS
 M:	Greg Kroah-Hartman <gregkh@linuxfoundation.org>
 L:	linux-serial@vger.kernel.org
 S:	Maintained
-F:	drivers/tty/serial
+F:	drivers/tty/serial/
 
 SYNOPSYS DESIGNWARE DMAC DRIVER
 M:	Viresh Kumar <viresh.linux@gmail.com>
+M:	Andy Shevchenko <andriy.shevchenko@linux.intel.com>
 S:	Maintained
 F:	include/linux/dw_dmac.h
 F:	drivers/dma/dw/
@@ -7143,7 +7255,7 @@ S:	Maintained
 F:	include/linux/mmc/dw_mmc.h
 F:	drivers/mmc/host/dw_mmc*
 
-TIMEKEEPING, NTP
+TIMEKEEPING, CLOCKSOURCE CORE, NTP
 M:	John Stultz <john.stultz@linaro.org>
 M:	Thomas Gleixner <tglx@linutronix.de>
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git timers/core
@@ -7156,13 +7268,12 @@ F:	include/uapi/linux/timex.h
 F:	kernel/time/clocksource.c
 F:	kernel/time/time*.c
 F:	kernel/time/ntp.c
-F:	drivers/clocksource
 
 TLG2300 VIDEO4LINUX-2 DRIVER
 M:	Huang Shijie <shijie8@gmail.com>
 M:	Hans Verkuil <hverkuil@xs4all.nl>
 S:	Odd Fixes
-F:	drivers/media/usb/tlg2300
+F:	drivers/media/usb/tlg2300/
 
 SC1200 WDT DRIVER
 M:	Zwane Mwaikambo <zwane@arm.linux.org.uk>
@@ -7179,9 +7290,9 @@ F:	include/linux/sched.h
 F:	include/uapi/linux/sched.h
 
 SCORE ARCHITECTURE
-M:	Chen Liqin <liqin.chen@sunplusct.com>
+M:	Chen Liqin <liqin.linux@gmail.com>
 M:	Lennox Wu <lennox.wu@gmail.com>
-W:	http://www.sunplusct.com
+W:	http://www.sunplus.com
 S:	Supported
 F:	arch/score/
 
@@ -7236,6 +7347,7 @@ W:	http://lksctp.sourceforge.net
 S:	Maintained
 F:	Documentation/networking/sctp.txt
 F:	include/linux/sctp.h
+F:	include/uapi/linux/sctp.h
 F:	include/net/sctp/
 F:	net/sctp/
 
@@ -7422,7 +7534,7 @@ L:	linux-media@vger.kernel.org
 T:	git git://linuxtv.org/media_tree.git
 W:	http://linuxtv.org
 S:	Odd Fixes
-F:	drivers/media/radio/radio-si4713.h
+F:	drivers/media/radio/radio-si4713.c
 
 SIANO DVB DRIVER
 M:	Mauro Carvalho Chehab <m.chehab@samsung.com>
@@ -7431,9 +7543,9 @@ W:	http://linuxtv.org
 T:	git git://linuxtv.org/media_tree.git
 S:	Odd fixes
 F:	drivers/media/common/siano/
-F:	drivers/media/dvb/siano/
 F:	drivers/media/usb/siano/
-F:	drivers/media/mmc/siano
+F:	drivers/media/usb/siano/
+F:	drivers/media/mmc/siano/
 
 SH_VEU V4L2 MEM2MEM DRIVER
 M:	Guennadi Liakhovetski <g.liakhovetski@gmx.de>
@@ -7471,9 +7583,9 @@ P:	Vincent Sanders <vince@simtec.co.uk>
 M:	Simtec Linux Team <linux@simtec.co.uk>
 W:	http://www.simtec.co.uk/products/EB2410ITX/
 S:	Supported
-F:	arch/arm/mach-s3c2410/mach-bast.c
-F:	arch/arm/mach-s3c2410/bast-ide.c
-F:	arch/arm/mach-s3c2410/bast-irq.c
+F:	arch/arm/mach-s3c24xx/mach-bast.c
+F:	arch/arm/mach-s3c24xx/bast-ide.c
+F:	arch/arm/mach-s3c24xx/bast-irq.c
 
 TI DAVINCI MACHINE SUPPORT
 M:	Sekhar Nori <nsekhar@ti.com>
@@ -7482,7 +7594,7 @@ L:	davinci-linux-open-source@linux.davincidsp.com (moderated for non-subscribers
 T:	git git://gitorious.org/linux-davinci/linux-davinci.git
 Q:	http://patchwork.kernel.org/project/linux-davinci/list/
 S:	Supported
-F:	arch/arm/mach-davinci
+F:	arch/arm/mach-davinci/
 F:	drivers/i2c/busses/i2c-davinci.c
 
 TI DAVINCI SERIES MEDIA DRIVER
@@ -7550,6 +7662,14 @@ S:	Maintained
 F:	Documentation/security/Smack.txt
 F:	security/smack/
 
+SMARTREFLEX DRIVERS FOR ADAPTIVE VOLTAGE SCALING (AVS)
+M:	Kevin Hilman <khilman@kernel.org>
+M:	Nishanth Menon <nm@ti.com>
+S:	Maintained
+F:	drivers/power/avs/smartreflex.c
+F:	include/linux/power/smartreflex.h
+L:	linux-pm@vger.kernel.org
+
 SMC91x ETHERNET DRIVER
 M:	Nicolas Pitre <nico@fluxnic.net>
 S:	Odd Fixes
@@ -7559,7 +7679,7 @@ SMIA AND SMIA++ IMAGE SENSOR DRIVER
 M:	Sakari Ailus <sakari.ailus@iki.fi>
 L:	linux-media@vger.kernel.org
 S:	Maintained
-F:	drivers/media/i2c/smiapp
+F:	drivers/media/i2c/smiapp/
 F:	include/media/smiapp.h
 F:	drivers/media/i2c/smiapp-pll.c
 F:	drivers/media/i2c/smiapp-pll.h
@@ -7662,6 +7782,11 @@ W:	http://tifmxx.berlios.de/
 S:	Maintained
 F:	drivers/memstick/host/tifm_ms.c
 
+SONY MEMORYSTICK STANDARD SUPPORT
+M:	Maxim Levitsky <maximlevitsky@gmail.com>
+S:	Maintained
+F:	drivers/memstick/core/ms_block.*
+
 SOUND
 M:	Jaroslav Kysela <perex@perex.cz>
 M:	Takashi Iwai <tiwai@suse.de>
@@ -7675,6 +7800,17 @@ F:	include/sound/
 F:	include/uapi/sound/
 F:	sound/
 
+SOUND - COMPRESSED AUDIO
+M:	Vinod Koul <vinod.koul@intel.com>
+L:	alsa-devel@alsa-project.org (moderated for non-subscribers)
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tiwai/sound.git
+S:	Supported
+F:	Documentation/sound/alsa/compress_offload.txt
+F:	include/sound/compress_driver.h
+F:	include/uapi/sound/compress_*
+F:	sound/core/compress_offload.c
+F:	sound/soc/soc-compress.c
+
 SOUND - SOC LAYER / DYNAMIC AUDIO POWER MANAGEMENT (ASoC)
 M:	Liam Girdwood <lgirdwood@gmail.com>
 M:	Mark Brown <broonie@kernel.org>
@@ -7682,6 +7818,7 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/broonie/sound.git
 L:	alsa-devel@alsa-project.org (moderated for non-subscribers)
 W:	http://alsa-project.org/main/index.php/ASoC
 S:	Supported
+F:	Documentation/sound/alsa/soc/
 F:	sound/soc/
 F:	include/sound/soc*
 
@@ -7726,35 +7863,7 @@ L:	spear-devel@list.st.com
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 W:	http://www.st.com/spear
 S:	Maintained
-F:	arch/arm/plat-spear/
-
-SPEAR13XX MACHINE SUPPORT
-M:	Viresh Kumar <viresh.linux@gmail.com>
-M:	Shiraz Hashim <shiraz.hashim@st.com>
-L:	spear-devel@list.st.com
-L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
-W:	http://www.st.com/spear
-S:	Maintained
-F:	arch/arm/mach-spear13xx/
-
-SPEAR3XX MACHINE SUPPORT
-M:	Viresh Kumar <viresh.linux@gmail.com>
-M:	Shiraz Hashim <shiraz.hashim@st.com>
-L:	spear-devel@list.st.com
-L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
-W:	http://www.st.com/spear
-S:	Maintained
-F:	arch/arm/mach-spear3xx/
-
-SPEAR6XX MACHINE SUPPORT
-M:	Rajeev Kumar <rajeev-dlh.kumar@st.com>
-M:	Shiraz Hashim <shiraz.hashim@st.com>
-M:	Viresh Kumar <viresh.linux@gmail.com>
-L:	spear-devel@list.st.com
-L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
-W:	http://www.st.com/spear
-S:	Maintained
-F:	arch/arm/mach-spear6xx/
+F:	arch/arm/mach-spear/
 
 SPEAR CLOCK FRAMEWORK SUPPORT
 M:	Viresh Kumar <viresh.linux@gmail.com>
@@ -7890,11 +7999,11 @@ S:	Maintained
 F:	drivers/staging/nvec/
 
 STAGING - OLPC SECONDARY DISPLAY CONTROLLER (DCON)
-M:	Andres Salomon <dilinger@queued.net>
-M:	Chris Ball <cjb@laptop.org>
+M:	Jens Frederich <jfrederich@gmail.com>
+M:	Daniel Drake <dsd@laptop.org>
 M:	Jon Nettleton <jon.nettleton@gmail.com>
 W:	http://wiki.laptop.org/go/DCON
-S:	Odd Fixes
+S:	Maintained
 F:	drivers/staging/olpc_dcon/
 
 STAGING - OZMO DEVICES USB OVER WIFI DRIVER
@@ -7972,6 +8081,12 @@ F:	arch/m68k/sun3*/
 F:	arch/m68k/include/asm/sun3*
 F:	drivers/net/ethernet/i825xx/sun3*
 
+SUNDANCE NETWORK DRIVER
+M:	Denis Kirjanov <kda@linux-powerpc.org>
+L:	netdev@vger.kernel.org
+S:	Maintained
+F:	drivers/net/ethernet/dlink/sundance.c
+
 SUPERH
 M:	Paul Mundt <lethal@linux-sh.org>
 L:	linux-sh@vger.kernel.org
@@ -7986,7 +8101,7 @@ F:	drivers/sh/
 SUSPEND TO RAM
 M:	Len Brown <len.brown@intel.com>
 M:	Pavel Machek <pavel@ucw.cz>
-M:	"Rafael J. Wysocki" <rjw@sisk.pl>
+M:	"Rafael J. Wysocki" <rjw@rjwysocki.net>
 L:	linux-pm@vger.kernel.org
 S:	Supported
 F:	Documentation/power/
@@ -8017,7 +8132,7 @@ M:	Vineet Gupta <vgupta@synopsys.com>
 S:	Supported
 F:	arch/arc/
 F:	Documentation/devicetree/bindings/arc/
-F:	drivers/tty/serial/arc-uart.c
+F:	drivers/tty/serial/arc_uart.c
 
 SYSV FILESYSTEM
 M:	Christoph Hellwig <hch@infradead.org>
@@ -8307,9 +8422,14 @@ M:	Chris Metcalf <cmetcalf@tilera.com>
 W:	http://www.tilera.com/scm/
 S:	Supported
 F:	arch/tile/
-F:	drivers/tty/hvc/hvc_tile.c
-F:	drivers/net/ethernet/tile/
+F:	drivers/char/tile-srom.c
 F:	drivers/edac/tile_edac.c
+F:	drivers/net/ethernet/tile/
+F:	drivers/rtc/rtc-tile.c
+F:	drivers/tty/hvc/hvc_tile.c
+F:	drivers/tty/serial/tilegx.c
+F:	drivers/usb/host/*-tilegx.c
+F:	include/linux/usb/tilegx.h
 
 TLAN NETWORK DRIVER
 M:	Samuel Chessman <chessman@tux.org>
@@ -8636,9 +8756,8 @@ F:	Documentation/hid/hiddev.txt
 F:	drivers/hid/usbhid/
 
 USB/IP DRIVERS
-M:	Matt Mooney <mfm@muteddisk.com>
 L:	linux-usb@vger.kernel.org
-S:	Maintained
+S:	Orphan
 F:	drivers/staging/usbip/
 
 USB ISP116X DRIVER
@@ -8702,7 +8821,6 @@ L:	linux-usb@vger.kernel.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/balbi/usb.git
 S:	Maintained
 F:	drivers/usb/phy/
-F:	drivers/usb/otg/
 
 USB PRINTER DRIVER (usblp)
 M:	Pete Zaitcev <zaitcev@redhat.com>
@@ -8803,7 +8921,6 @@ W:	http://www.linux-usb.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/usb.git
 S:	Supported
 F:	Documentation/usb/
-F:	drivers/net/usb/
 F:	drivers/usb/
 F:	include/linux/usb.h
 F:	include/linux/usb/
@@ -9026,6 +9143,12 @@ F:	drivers/staging/vme/
 F:	drivers/vme/
 F:	include/linux/vme*
 
+VMWARE HYPERVISOR INTERFACE
+M:	Alok Kataria <akataria@vmware.com>
+L:	virtualization@lists.linux-foundation.org
+S:	Supported
+F:	arch/x86/kernel/cpu/vmware.c
+
 VMWARE VMXNET3 ETHERNET DRIVER
 M:	Shreyas Bhatewara <sbhatewara@vmware.com>
 M:	"VMware, Inc." <pv-drivers@vmware.com>
@@ -9228,7 +9351,7 @@ M:	Matthew Garrett <matthew.garrett@nebula.com>
 L:	platform-driver-x86@vger.kernel.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/mjg59/platform-drivers-x86.git
 S:	Maintained
-F:	drivers/platform/x86
+F:	drivers/platform/x86/
 
 X86 MCE INFRASTRUCTURE
 M:	Tony Luck <tony.luck@intel.com>
@@ -9247,9 +9370,9 @@ F:	drivers/media/tuners/tuner-xc2028.*
 
 XEN HYPERVISOR INTERFACE
 M:	Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
-M:	Jeremy Fitzhardinge <jeremy@goop.org>
-L:	xen-devel@lists.xensource.com (moderated for non-subscribers)
-L:	virtualization@lists.linux-foundation.org
+M:	Boris Ostrovsky <boris.ostrovsky@oracle.com>
+M:	David Vrabel <david.vrabel@citrix.com>
+L:	xen-devel@lists.xenproject.org (moderated for non-subscribers)
 S:	Supported
 F:	arch/x86/xen/
 F:	drivers/*/xen-*front.c
@@ -9260,35 +9383,36 @@ F:	include/uapi/xen/
 
 XEN HYPERVISOR ARM
 M:	Stefano Stabellini <stefano.stabellini@eu.citrix.com>
-L:	xen-devel@lists.xensource.com (moderated for non-subscribers)
+L:	xen-devel@lists.xenproject.org (moderated for non-subscribers)
 S:	Supported
 F:	arch/arm/xen/
 F:	arch/arm/include/asm/xen/
 
 XEN HYPERVISOR ARM64
 M:	Stefano Stabellini <stefano.stabellini@eu.citrix.com>
-L:	xen-devel@lists.xensource.com (moderated for non-subscribers)
+L:	xen-devel@lists.xenproject.org (moderated for non-subscribers)
 S:	Supported
 F:	arch/arm64/xen/
 F:	arch/arm64/include/asm/xen/
 
 XEN NETWORK BACKEND DRIVER
 M:	Ian Campbell <ian.campbell@citrix.com>
-L:	xen-devel@lists.xensource.com (moderated for non-subscribers)
+M:	Wei Liu <wei.liu2@citrix.com>
+L:	xen-devel@lists.xenproject.org (moderated for non-subscribers)
 L:	netdev@vger.kernel.org
 S:	Supported
 F:	drivers/net/xen-netback/*
 
 XEN PCI SUBSYSTEM
 M:	Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
-L:	xen-devel@lists.xensource.com (moderated for non-subscribers)
+L:	xen-devel@lists.xenproject.org (moderated for non-subscribers)
 S:	Supported
 F:	arch/x86/pci/*xen*
 F:	drivers/pci/*xen*
 
 XEN SWIOTLB SUBSYSTEM
 M:	Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
-L:	xen-devel@lists.xensource.com (moderated for non-subscribers)
+L:	xen-devel@lists.xenproject.org (moderated for non-subscribers)
 S:	Supported
 F:	arch/x86/xen/*swiotlb*
 F:	drivers/xen/*swiotlb*
diff --git a/Makefile b/Makefile
index fe8204be566d..deec08b7612b 100644
--- a/Makefile
+++ b/Makefile
@@ -1,8 +1,8 @@
 VERSION = 3
-PATCHLEVEL = 11
+PATCHLEVEL = 12
 SUBLEVEL = 0
-EXTRAVERSION =
-NAME = Linux for Workgroups
+EXTRAVERSION = -rc5
+NAME = One Giant Leap for Frogkind
 
 # *DOCUMENTATION*
 # To see a list of typical targets execute "make help"
@@ -794,10 +794,13 @@ PHONY += $(vmlinux-dirs)
 $(vmlinux-dirs): prepare scripts
 	$(Q)$(MAKE) $(build)=$@
 
+define filechk_kernel.release
+	echo "$(KERNELVERSION)$$($(CONFIG_SHELL) $(srctree)/scripts/setlocalversion $(srctree))"
+endef
+
 # Store (new) KERNELRELEASE string in include/config/kernel.release
 include/config/kernel.release: include/config/auto.conf FORCE
-	$(Q)rm -f $@
-	$(Q)echo "$(KERNELVERSION)$$($(CONFIG_SHELL) $(srctree)/scripts/setlocalversion $(srctree))" > $@
+	$(call filechk,kernel.release)
 
 
 # Things we need to do before we recursively start building the kernel
diff --git a/arch/Kconfig b/arch/Kconfig
index 1feb169274fe..af2cc6eabcc7 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -286,9 +286,6 @@ config HAVE_PERF_USER_STACK_DUMP
 config HAVE_ARCH_JUMP_LABEL
 	bool
 
-config HAVE_ARCH_MUTEX_CPU_RELAX
-	bool
-
 config HAVE_RCU_TABLE_FREE
 	bool
 
diff --git a/arch/alpha/Kconfig b/arch/alpha/Kconfig
index 082d9b4b5472..35a300d4a9fb 100644
--- a/arch/alpha/Kconfig
+++ b/arch/alpha/Kconfig
@@ -7,7 +7,6 @@ config ALPHA
 	select HAVE_PCSPKR_PLATFORM
 	select HAVE_PERF_EVENTS
 	select HAVE_DMA_ATTRS
-	select HAVE_GENERIC_HARDIRQS
 	select VIRT_TO_BUS
 	select GENERIC_IRQ_PROBE
 	select AUTO_IRQ_AFFINITY if SMP
diff --git a/arch/alpha/lib/csum_partial_copy.c b/arch/alpha/lib/csum_partial_copy.c
index 40736da9bea8..ffb19b7da999 100644
--- a/arch/alpha/lib/csum_partial_copy.c
+++ b/arch/alpha/lib/csum_partial_copy.c
@@ -338,6 +338,11 @@ csum_partial_copy_from_user(const void __user *src, void *dst, int len,
 	unsigned long doff = 7 & (unsigned long) dst;
 
 	if (len) {
+		if (!access_ok(VERIFY_READ, src, len)) {
+			*errp = -EFAULT;
+			memset(dst, 0, len);
+			return sum;
+		}
 		if (!doff) {
 			if (!soff)
 				checksum = csum_partial_cfu_aligned(
diff --git a/arch/alpha/mm/fault.c b/arch/alpha/mm/fault.c
index 0c4132dd3507..98838a05ba6d 100644
--- a/arch/alpha/mm/fault.c
+++ b/arch/alpha/mm/fault.c
@@ -89,8 +89,7 @@ do_page_fault(unsigned long address, unsigned long mmcsr,
 	const struct exception_table_entry *fixup;
 	int fault, si_code = SEGV_MAPERR;
 	siginfo_t info;
-	unsigned int flags = (FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
-			      (cause > 0 ? FAULT_FLAG_WRITE : 0));
+	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
 
 	/* As of EV6, a load into $31/$f31 is a prefetch, and never faults
 	   (or is suppressed by the PALcode).  Support that for older CPUs
@@ -115,7 +114,8 @@ do_page_fault(unsigned long address, unsigned long mmcsr,
 	if (address >= TASK_SIZE)
 		goto vmalloc_fault;
 #endif
-
+	if (user_mode(regs))
+		flags |= FAULT_FLAG_USER;
 retry:
 	down_read(&mm->mmap_sem);
 	vma = find_vma(mm, address);
@@ -142,6 +142,7 @@ retry:
 	} else {
 		if (!(vma->vm_flags & VM_WRITE))
 			goto bad_area;
+		flags |= FAULT_FLAG_WRITE;
 	}
 
 	/* If for any reason at all we couldn't handle the fault,
diff --git a/arch/alpha/oprofile/common.c b/arch/alpha/oprofile/common.c
index b8ce18f485d3..310a4ce1dccc 100644
--- a/arch/alpha/oprofile/common.c
+++ b/arch/alpha/oprofile/common.c
@@ -106,7 +106,7 @@ op_axp_stop(void)
 }
 
 static int
-op_axp_create_files(struct super_block *sb, struct dentry *root)
+op_axp_create_files(struct dentry *root)
 {
 	int i;
 
@@ -115,23 +115,23 @@ op_axp_create_files(struct super_block *sb, struct dentry *root)
 		char buf[4];
 
 		snprintf(buf, sizeof buf, "%d", i);
-		dir = oprofilefs_mkdir(sb, root, buf);
+		dir = oprofilefs_mkdir(root, buf);
 
-		oprofilefs_create_ulong(sb, dir, "enabled", &ctr[i].enabled);
-                oprofilefs_create_ulong(sb, dir, "event", &ctr[i].event);
-		oprofilefs_create_ulong(sb, dir, "count", &ctr[i].count);
+		oprofilefs_create_ulong(dir, "enabled", &ctr[i].enabled);
+                oprofilefs_create_ulong(dir, "event", &ctr[i].event);
+		oprofilefs_create_ulong(dir, "count", &ctr[i].count);
 		/* Dummies.  */
-		oprofilefs_create_ulong(sb, dir, "kernel", &ctr[i].kernel);
-		oprofilefs_create_ulong(sb, dir, "user", &ctr[i].user);
-		oprofilefs_create_ulong(sb, dir, "unit_mask", &ctr[i].unit_mask);
+		oprofilefs_create_ulong(dir, "kernel", &ctr[i].kernel);
+		oprofilefs_create_ulong(dir, "user", &ctr[i].user);
+		oprofilefs_create_ulong(dir, "unit_mask", &ctr[i].unit_mask);
 	}
 
 	if (model->can_set_proc_mode) {
-		oprofilefs_create_ulong(sb, root, "enable_pal",
+		oprofilefs_create_ulong(root, "enable_pal",
 					&sys.enable_pal);
-		oprofilefs_create_ulong(sb, root, "enable_kernel",
+		oprofilefs_create_ulong(root, "enable_kernel",
 					&sys.enable_kernel);
-		oprofilefs_create_ulong(sb, root, "enable_user",
+		oprofilefs_create_ulong(root, "enable_user",
 					&sys.enable_user);
 	}
 
diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
index 68fcbb2d59e2..91dbb2757afd 100644
--- a/arch/arc/Kconfig
+++ b/arch/arc/Kconfig
@@ -20,7 +20,6 @@ config ARC
 	select GENERIC_SMP_IDLE_THREAD
 	select HAVE_ARCH_KGDB
 	select HAVE_ARCH_TRACEHOOK
-	select HAVE_GENERIC_HARDIRQS
 	select HAVE_IOREMAP_PROT
 	select HAVE_KPROBES
 	select HAVE_KRETPROBES
diff --git a/arch/arc/boot/.gitignore b/arch/arc/boot/.gitignore
new file mode 100644
index 000000000000..5d65b54bf17a
--- /dev/null
+++ b/arch/arc/boot/.gitignore
@@ -0,0 +1 @@
+*.dtb*
diff --git a/arch/arc/include/asm/cache.h b/arch/arc/include/asm/cache.h
index 5802849a6cae..e4abdaac6f9f 100644
--- a/arch/arc/include/asm/cache.h
+++ b/arch/arc/include/asm/cache.h
@@ -57,7 +57,7 @@
 
 extern void arc_cache_init(void);
 extern char *arc_cache_mumbojumbo(int cpu_id, char *buf, int len);
-extern void __init read_decode_cache_bcr(void);
+extern void read_decode_cache_bcr(void);
 
 #endif	/* !__ASSEMBLY__ */
 
diff --git a/arch/arc/include/asm/delay.h b/arch/arc/include/asm/delay.h
index 442ce5d0f709..43de30256981 100644
--- a/arch/arc/include/asm/delay.h
+++ b/arch/arc/include/asm/delay.h
@@ -53,11 +53,10 @@ static inline void __udelay(unsigned long usecs)
 {
 	unsigned long loops;
 
-	/* (long long) cast ensures 64 bit MPY - real or emulated
+	/* (u64) cast ensures 64 bit MPY - real or emulated
 	 * HZ * 4295 is pre-evaluated by gcc - hence only 2 mpy ops
 	 */
-	loops = ((long long)(usecs * 4295 * HZ) *
-		 (long long)(loops_per_jiffy)) >> 32;
+	loops = ((u64) usecs * 4295 * HZ * loops_per_jiffy) >> 32;
 
 	__delay(loops);
 }
diff --git a/arch/arc/include/asm/entry.h b/arch/arc/include/asm/entry.h
index df57611652e5..884081099f80 100644
--- a/arch/arc/include/asm/entry.h
+++ b/arch/arc/include/asm/entry.h
@@ -365,7 +365,7 @@
  * it to memory (non-SMP case) or SCRATCH0 Aux Reg (SMP).
  *
  * Before saving the full regfile - this reg is restored back, only
- * to be saved again on kernel mode stack, as part of ptregs.
+ * to be saved again on kernel mode stack, as part of pt_regs.
  *-------------------------------------------------------------*/
 .macro EXCPN_PROLOG_FREEUP_REG	reg
 #ifdef CONFIG_SMP
@@ -384,6 +384,28 @@
 .endm
 
 /*--------------------------------------------------------------
+ * Exception Entry prologue
+ * -Switches stack to K mode (if not already)
+ * -Saves the register file
+ *
+ * After this it is safe to call the "C" handlers
+ *-------------------------------------------------------------*/
+.macro EXCEPTION_PROLOGUE
+
+	/* Need at least 1 reg to code the early exception prologue */
+	EXCPN_PROLOG_FREEUP_REG r9
+
+	/* U/K mode at time of exception (stack not switched if already K) */
+	lr  r9, [erstatus]
+
+	/* ARC700 doesn't provide auto-stack switching */
+	SWITCH_TO_KERNEL_STK
+
+	/* save the regfile */
+	SAVE_ALL_SYS
+.endm
+
+/*--------------------------------------------------------------
  * Save all registers used by Exceptions (TLB Miss, Prot-V, Mem err etc)
  * Requires SP to be already switched to kernel mode Stack
  * sp points to the next free element on the stack at exit of this macro.
diff --git a/arch/arc/include/asm/io.h b/arch/arc/include/asm/io.h
index 473424d7528b..334ce7017a18 100644
--- a/arch/arc/include/asm/io.h
+++ b/arch/arc/include/asm/io.h
@@ -100,6 +100,10 @@ static inline void __raw_writel(u32 w, volatile void __iomem *addr)
 
 }
 
+#define readb_relaxed readb
+#define readw_relaxed readw
+#define readl_relaxed readl
+
 #include <asm-generic/io.h>
 
 #endif /* _ASM_ARC_IO_H */
diff --git a/arch/arc/include/asm/irqflags.h b/arch/arc/include/asm/irqflags.h
index d99f79bcf865..b68b53f458d1 100644
--- a/arch/arc/include/asm/irqflags.h
+++ b/arch/arc/include/asm/irqflags.h
@@ -157,13 +157,6 @@ static inline void arch_unmask_irq(unsigned int irq)
 	flag	\scratch
 .endm
 
-.macro IRQ_DISABLE_SAVE  scratch, save
-	lr	\scratch, [status32]
-	mov	\save, \scratch		/* Make a copy */
-	bic	\scratch, \scratch, (STATUS_E1_MASK | STATUS_E2_MASK)
-	flag	\scratch
-.endm
-
 .macro IRQ_ENABLE  scratch
 	lr	\scratch, [status32]
 	or	\scratch, \scratch, (STATUS_E1_MASK | STATUS_E2_MASK)
diff --git a/arch/arc/include/asm/mmu.h b/arch/arc/include/asm/mmu.h
index 7c03fe61759c..c2663b32866b 100644
--- a/arch/arc/include/asm/mmu.h
+++ b/arch/arc/include/asm/mmu.h
@@ -32,6 +32,8 @@
 /* Error code if probe fails */
 #define TLB_LKUP_ERR		0x80000000
 
+#define TLB_DUP_ERR	(TLB_LKUP_ERR | 0x00000001)
+
 /* TLB Commands */
 #define TLBWrite    0x1
 #define TLBRead     0x2
@@ -46,21 +48,18 @@
 #ifndef __ASSEMBLY__
 
 typedef struct {
-	unsigned long asid;	/* Pvt Addr-Space ID for mm */
-#ifdef CONFIG_ARC_TLB_DBG
-	struct task_struct *tsk;
-#endif
+	unsigned long asid;	/* 8 bit MMU PID + Generation cycle */
 } mm_context_t;
 
 #ifdef CONFIG_ARC_DBG_TLB_PARANOIA
-void tlb_paranoid_check(unsigned int pid_sw, unsigned long address);
+void tlb_paranoid_check(unsigned int mm_asid, unsigned long address);
 #else
 #define tlb_paranoid_check(a, b)
 #endif
 
 void arc_mmu_init(void);
 extern char *arc_mmu_mumbojumbo(int cpu_id, char *buf, int len);
-void __init read_decode_mmu_bcr(void);
+void read_decode_mmu_bcr(void);
 
 #endif	/* !__ASSEMBLY__ */
 
diff --git a/arch/arc/include/asm/mmu_context.h b/arch/arc/include/asm/mmu_context.h
index 0d71fb11b57c..43a1b51bb8cc 100644
--- a/arch/arc/include/asm/mmu_context.h
+++ b/arch/arc/include/asm/mmu_context.h
@@ -34,95 +34,65 @@
  * When it reaches max 255, the allocation cycle starts afresh by flushing
  * the entire TLB and wrapping ASID back to zero.
  *
- * For book-keeping, Linux uses a couple of data-structures:
- *  -mm_struct has an @asid field to keep a note of task's ASID (needed at the
- *   time of say switch_mm( )
- *  -An array of mm structs @asid_mm_map[] for asid->mm the reverse mapping,
- *  given an ASID, finding the mm struct associated.
- *
- * The round-robin allocation algorithm allows for ASID stealing.
- * If asid tracker is at "x-1", a new req will allocate "x", even if "x" was
- * already assigned to another (switched-out) task. Obviously the prev owner
- * is marked with an invalid ASID to make it request for a new ASID when it
- * gets scheduled next time. However its TLB entries (with ASID "x") could
- * exist, which must be cleared before the same ASID is used by the new owner.
- * Flushing them would be plausible but costly solution. Instead we force a
- * allocation policy quirk, which ensures that a stolen ASID won't have any
- * TLB entries associates, alleviating the need to flush.
- * The quirk essentially is not allowing ASID allocated in prev cycle
- * to be used past a roll-over in the next cycle.
- * When this happens (i.e. task ASID > asid tracker), task needs to refresh
- * its ASID, aligning it to current value of tracker. If the task doesn't get
- * scheduled past a roll-over, hence its ASID is not yet realigned with
- * tracker, such ASID is anyways safely reusable because it is
- * gauranteed that TLB entries with that ASID wont exist.
+ * A new allocation cycle, post rollover, could potentially reassign an ASID
+ * to a different task. Thus the rule is to refresh the ASID in a new cycle.
+ * The 32 bit @asid_cache (and mm->asid) have 8 bits MMU PID and rest 24 bits
+ * serve as cycle/generation indicator and natural 32 bit unsigned math
+ * automagically increments the generation when lower 8 bits rollover.
  */
 
-#define FIRST_ASID  0
-#define MAX_ASID    255			/* 8 bit PID field in PID Aux reg */
-#define NO_ASID     (MAX_ASID + 1)	/* ASID Not alloc to mmu ctxt */
-#define NUM_ASID    ((MAX_ASID - FIRST_ASID) + 1)
+#define MM_CTXT_ASID_MASK	0x000000ff /* MMU PID reg :8 bit PID */
+#define MM_CTXT_CYCLE_MASK	(~MM_CTXT_ASID_MASK)
+
+#define MM_CTXT_FIRST_CYCLE	(MM_CTXT_ASID_MASK + 1)
+#define MM_CTXT_NO_ASID		0UL
 
-/* ASID to mm struct mapping */
-extern struct mm_struct *asid_mm_map[NUM_ASID + 1];
+#define hw_pid(mm)		(mm->context.asid & MM_CTXT_ASID_MASK)
 
-extern int asid_cache;
+extern unsigned int asid_cache;
 
 /*
- * Assign a new ASID to task. If the task already has an ASID, it is
- * relinquished.
+ * Get a new ASID if task doesn't have a valid one (unalloc or from prev cycle)
+ * Also set the MMU PID register to existing/updated ASID
  */
 static inline void get_new_mmu_context(struct mm_struct *mm)
 {
-	struct mm_struct *prev_owner;
 	unsigned long flags;
 
 	local_irq_save(flags);
 
 	/*
-	 * Relinquish the currently owned ASID (if any).
-	 * Doing unconditionally saves a cmp-n-branch; for already unused
-	 * ASID slot, the value was/remains NULL
+	 * Move to new ASID if it was not from current alloc-cycle/generation.
+	 * This is done by ensuring that the generation bits in both mm->ASID
+	 * and cpu's ASID counter are exactly same.
+	 *
+	 * Note: Callers needing new ASID unconditionally, independent of
+	 * 	 generation, e.g. local_flush_tlb_mm() for forking  parent,
+	 * 	 first need to destroy the context, setting it to invalid
+	 * 	 value.
 	 */
-	asid_mm_map[mm->context.asid] = (struct mm_struct *)NULL;
+	if (!((mm->context.asid ^ asid_cache) & MM_CTXT_CYCLE_MASK))
+		goto set_hw;
+
+	/* move to new ASID and handle rollover */
+	if (unlikely(!(++asid_cache & MM_CTXT_ASID_MASK))) {
 
-	/* move to new ASID */
-	if (++asid_cache > MAX_ASID) {	/* ASID roll-over */
-		asid_cache = FIRST_ASID;
 		flush_tlb_all();
-	}
 
-	/*
-	 * Is next ASID already owned by some-one else (we are stealing it).
-	 * If so, let the orig owner be aware of this, so when it runs, it
-	 * asks for a brand new ASID. This would only happen for a long-lived
-	 * task with ASID from prev allocation cycle (before ASID roll-over).
-	 *
-	 * This might look wrong - if we are re-using some other task's ASID,
-	 * won't we use it's stale TLB entries too. Actually switch_mm( ) takes
-	 * care of such a case: it ensures that task with ASID from prev alloc
-	 * cycle, when scheduled will refresh it's ASID: see switch_mm( ) below
-	 * The stealing scenario described here will only happen if that task
-	 * didn't get a chance to refresh it's ASID - implying stale entries
-	 * won't exist.
-	 */
-	prev_owner = asid_mm_map[asid_cache];
-	if (prev_owner)
-		prev_owner->context.asid = NO_ASID;
+		/*
+		 * Above checke for rollover of 8 bit ASID in 32 bit container.
+		 * If the container itself wrapped around, set it to a non zero
+		 * "generation" to distinguish from no context
+		 */
+		if (!asid_cache)
+			asid_cache = MM_CTXT_FIRST_CYCLE;
+	}
 
 	/* Assign new ASID to tsk */
-	asid_mm_map[asid_cache] = mm;
 	mm->context.asid = asid_cache;
 
-#ifdef CONFIG_ARC_TLB_DBG
-	pr_info("ARC_TLB_DBG: NewMM=0x%x OldMM=0x%x task_struct=0x%x Task: %s,"
-	       " pid:%u, assigned asid:%lu\n",
-	       (unsigned int)mm, (unsigned int)prev_owner,
-	       (unsigned int)(mm->context.tsk), (mm->context.tsk)->comm,
-	       (mm->context.tsk)->pid, mm->context.asid);
-#endif
-
-	write_aux_reg(ARC_REG_PID, asid_cache | MMU_ENABLE);
+set_hw:
+	write_aux_reg(ARC_REG_PID, hw_pid(mm) | MMU_ENABLE);
 
 	local_irq_restore(flags);
 }
@@ -134,10 +104,7 @@ static inline void get_new_mmu_context(struct mm_struct *mm)
 static inline int
 init_new_context(struct task_struct *tsk, struct mm_struct *mm)
 {
-	mm->context.asid = NO_ASID;
-#ifdef CONFIG_ARC_TLB_DBG
-	mm->context.tsk = tsk;
-#endif
+	mm->context.asid = MM_CTXT_NO_ASID;
 	return 0;
 }
 
@@ -152,40 +119,21 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 	write_aux_reg(ARC_REG_SCRATCH_DATA0, next->pgd);
 #endif
 
-	/*
-	 * Get a new ASID if task doesn't have a valid one. Possible when
-	 *  -task never had an ASID (fresh after fork)
-	 *  -it's ASID was stolen - past an ASID roll-over.
-	 *  -There's a third obscure scenario (if this task is running for the
-	 *   first time afer an ASID rollover), where despite having a valid
-	 *   ASID, we force a get for new ASID - see comments at top.
-	 *
-	 * Both the non-alloc scenario and first-use-after-rollover can be
-	 * detected using the single condition below:  NO_ASID = 256
-	 * while asid_cache is always a valid ASID value (0-255).
-	 */
-	if (next->context.asid > asid_cache) {
-		get_new_mmu_context(next);
-	} else {
-		/*
-		 * XXX: This will never happen given the chks above
-		 * BUG_ON(next->context.asid > MAX_ASID);
-		 */
-		write_aux_reg(ARC_REG_PID, next->context.asid | MMU_ENABLE);
-	}
-
+	get_new_mmu_context(next);
 }
 
+/*
+ * Called at the time of execve() to get a new ASID
+ * Note the subtlety here: get_new_mmu_context() behaves differently here
+ * vs. in switch_mm(). Here it always returns a new ASID, because mm has
+ * an unallocated "initial" value, while in latter, it moves to a new ASID,
+ * only if it was unallocated
+ */
+#define activate_mm(prev, next)		switch_mm(prev, next, NULL)
+
 static inline void destroy_context(struct mm_struct *mm)
 {
-	unsigned long flags;
-
-	local_irq_save(flags);
-
-	asid_mm_map[mm->context.asid] = NULL;
-	mm->context.asid = NO_ASID;
-
-	local_irq_restore(flags);
+	mm->context.asid = MM_CTXT_NO_ASID;
 }
 
 /* it seemed that deactivate_mm( ) is a reasonable place to do book-keeping
@@ -197,17 +145,6 @@ static inline void destroy_context(struct mm_struct *mm)
  */
 #define deactivate_mm(tsk, mm)   do { } while (0)
 
-static inline void activate_mm(struct mm_struct *prev, struct mm_struct *next)
-{
-#ifndef CONFIG_SMP
-	write_aux_reg(ARC_REG_SCRATCH_DATA0, next->pgd);
-#endif
-
-	/* Unconditionally get a new ASID */
-	get_new_mmu_context(next);
-
-}
-
 #define enter_lazy_tlb(mm, tsk)
 
 #endif /* __ASM_ARC_MMU_CONTEXT_H */
diff --git a/arch/arc/include/asm/pgtable.h b/arch/arc/include/asm/pgtable.h
index 4749a0eee1cf..6b0b7f7ef783 100644
--- a/arch/arc/include/asm/pgtable.h
+++ b/arch/arc/include/asm/pgtable.h
@@ -57,43 +57,31 @@
 
 #define _PAGE_ACCESSED      (1<<1)	/* Page is accessed (S) */
 #define _PAGE_CACHEABLE     (1<<2)	/* Page is cached (H) */
-#define _PAGE_U_EXECUTE     (1<<3)	/* Page has user execute perm (H) */
-#define _PAGE_U_WRITE       (1<<4)	/* Page has user write perm (H) */
-#define _PAGE_U_READ        (1<<5)	/* Page has user read perm (H) */
-#define _PAGE_K_EXECUTE     (1<<6)	/* Page has kernel execute perm (H) */
-#define _PAGE_K_WRITE       (1<<7)	/* Page has kernel write perm (H) */
-#define _PAGE_K_READ        (1<<8)	/* Page has kernel perm (H) */
-#define _PAGE_GLOBAL        (1<<9)	/* Page is global (H) */
-#define _PAGE_MODIFIED      (1<<10)	/* Page modified (dirty) (S) */
-#define _PAGE_FILE          (1<<10)	/* page cache/ swap (S) */
-#define _PAGE_PRESENT       (1<<11)	/* TLB entry is valid (H) */
+#define _PAGE_EXECUTE       (1<<3)	/* Page has user execute perm (H) */
+#define _PAGE_WRITE         (1<<4)	/* Page has user write perm (H) */
+#define _PAGE_READ          (1<<5)	/* Page has user read perm (H) */
+#define _PAGE_MODIFIED      (1<<6)	/* Page modified (dirty) (S) */
+#define _PAGE_FILE          (1<<7)	/* page cache/ swap (S) */
+#define _PAGE_GLOBAL        (1<<8)	/* Page is global (H) */
+#define _PAGE_PRESENT       (1<<10)	/* TLB entry is valid (H) */
 
-#else
+#else	/* MMU v3 onwards */
 
-/* PD1 */
 #define _PAGE_CACHEABLE     (1<<0)	/* Page is cached (H) */
-#define _PAGE_U_EXECUTE     (1<<1)	/* Page has user execute perm (H) */
-#define _PAGE_U_WRITE       (1<<2)	/* Page has user write perm (H) */
-#define _PAGE_U_READ        (1<<3)	/* Page has user read perm (H) */
-#define _PAGE_K_EXECUTE     (1<<4)	/* Page has kernel execute perm (H) */
-#define _PAGE_K_WRITE       (1<<5)	/* Page has kernel write perm (H) */
-#define _PAGE_K_READ        (1<<6)	/* Page has kernel perm (H) */
-#define _PAGE_ACCESSED      (1<<7)	/* Page is accessed (S) */
-
-/* PD0 */
+#define _PAGE_EXECUTE       (1<<1)	/* Page has user execute perm (H) */
+#define _PAGE_WRITE         (1<<2)	/* Page has user write perm (H) */
+#define _PAGE_READ          (1<<3)	/* Page has user read perm (H) */
+#define _PAGE_ACCESSED      (1<<4)	/* Page is accessed (S) */
+#define _PAGE_MODIFIED      (1<<5)	/* Page modified (dirty) (S) */
+#define _PAGE_FILE          (1<<6)	/* page cache/ swap (S) */
 #define _PAGE_GLOBAL        (1<<8)	/* Page is global (H) */
 #define _PAGE_PRESENT       (1<<9)	/* TLB entry is valid (H) */
-#define _PAGE_SHARED_CODE   (1<<10)	/* Shared Code page with cmn vaddr
+#define _PAGE_SHARED_CODE   (1<<11)	/* Shared Code page with cmn vaddr
 					   usable for shared TLB entries (H) */
-
-#define _PAGE_MODIFIED      (1<<11)	/* Page modified (dirty) (S) */
-#define _PAGE_FILE          (1<<12)	/* page cache/ swap (S) */
-
-#define _PAGE_SHARED_CODE_H (1<<31)	/* Hardware counterpart of above */
 #endif
 
-/* Kernel allowed all permissions for all pages */
-#define _K_PAGE_PERMS  (_PAGE_K_EXECUTE | _PAGE_K_WRITE | _PAGE_K_READ | \
+/* vmalloc permissions */
+#define _K_PAGE_PERMS  (_PAGE_EXECUTE | _PAGE_WRITE | _PAGE_READ | \
 			_PAGE_GLOBAL | _PAGE_PRESENT)
 
 #ifdef CONFIG_ARC_CACHE_PAGES
@@ -109,10 +97,6 @@
  */
 #define ___DEF (_PAGE_PRESENT | _PAGE_DEF_CACHEABLE)
 
-#define _PAGE_READ	(_PAGE_U_READ    | _PAGE_K_READ)
-#define _PAGE_WRITE	(_PAGE_U_WRITE   | _PAGE_K_WRITE)
-#define _PAGE_EXECUTE	(_PAGE_U_EXECUTE | _PAGE_K_EXECUTE)
-
 /* Set of bits not changed in pte_modify */
 #define _PAGE_CHG_MASK	(PAGE_MASK | _PAGE_ACCESSED | _PAGE_MODIFIED)
 
@@ -126,8 +110,8 @@
 
 #define PAGE_SHARED	PAGE_U_W_R
 
-/* While kernel runs out of unstrslated space, vmalloc/modules use a chunk of
- * kernel vaddr space - visible in all addr spaces, but kernel mode only
+/* While kernel runs out of unstranslated space, vmalloc/modules use a chunk of
+ * user vaddr space - visible in all addr spaces, but kernel mode only
  * Thus Global, all-kernel-access, no-user-access, cached
  */
 #define PAGE_KERNEL          __pgprot(_K_PAGE_PERMS | _PAGE_DEF_CACHEABLE)
@@ -136,10 +120,9 @@
 #define PAGE_KERNEL_NO_CACHE __pgprot(_K_PAGE_PERMS)
 
 /* Masks for actual TLB "PD"s */
-#define PTE_BITS_IN_PD0	(_PAGE_GLOBAL | _PAGE_PRESENT)
-#define PTE_BITS_IN_PD1	(PAGE_MASK | _PAGE_CACHEABLE | \
-			 _PAGE_U_EXECUTE | _PAGE_U_WRITE | _PAGE_U_READ | \
-			 _PAGE_K_EXECUTE | _PAGE_K_WRITE | _PAGE_K_READ)
+#define PTE_BITS_IN_PD0		(_PAGE_GLOBAL | _PAGE_PRESENT)
+#define PTE_BITS_RWX		(_PAGE_EXECUTE | _PAGE_WRITE | _PAGE_READ)
+#define PTE_BITS_NON_RWX_IN_PD1	(PAGE_MASK | _PAGE_CACHEABLE)
 
 /**************************************************************************
  * Mapping of vm_flags (Generic VM) to PTE flags (arch specific)
diff --git a/arch/arc/include/asm/ptrace.h b/arch/arc/include/asm/ptrace.h
index c9938e7a7dbd..1bfeec2c0558 100644
--- a/arch/arc/include/asm/ptrace.h
+++ b/arch/arc/include/asm/ptrace.h
@@ -20,27 +20,17 @@ struct pt_regs {
 
 	/* Real registers */
 	long bta;	/* bta_l1, bta_l2, erbta */
-	long lp_start;
-	long lp_end;
-	long lp_count;
+
+	long lp_start, lp_end, lp_count;
+
 	long status32;	/* status32_l1, status32_l2, erstatus */
 	long ret;	/* ilink1, ilink2 or eret */
 	long blink;
 	long fp;
 	long r26;	/* gp */
-	long r12;
-	long r11;
-	long r10;
-	long r9;
-	long r8;
-	long r7;
-	long r6;
-	long r5;
-	long r4;
-	long r3;
-	long r2;
-	long r1;
-	long r0;
+
+	long r12, r11, r10, r9, r8, r7, r6, r5, r4, r3, r2, r1, r0;
+
 	long sp;	/* user/kernel sp depending on where we came from  */
 	long orig_r0;
 
@@ -70,19 +60,7 @@ struct pt_regs {
 /* Callee saved registers - need to be saved only when you are scheduled out */
 
 struct callee_regs {
-	long r25;
-	long r24;
-	long r23;
-	long r22;
-	long r21;
-	long r20;
-	long r19;
-	long r18;
-	long r17;
-	long r16;
-	long r15;
-	long r14;
-	long r13;
+	long r25, r24, r23, r22, r21, r20, r19, r18, r17, r16, r15, r14, r13;
 };
 
 #define instruction_pointer(regs)	((regs)->ret)
diff --git a/arch/arc/include/asm/sections.h b/arch/arc/include/asm/sections.h
index 6fc1159dfefe..764f1e3ba752 100644
--- a/arch/arc/include/asm/sections.h
+++ b/arch/arc/include/asm/sections.h
@@ -11,7 +11,6 @@
 
 #include <asm-generic/sections.h>
 
-extern char _int_vec_base_lds[];
 extern char __arc_dccm_base[];
 extern char __dtb_start[];
 
diff --git a/arch/arc/include/asm/spinlock.h b/arch/arc/include/asm/spinlock.h
index f158197ac5b0..b6a8c2dfbe6e 100644
--- a/arch/arc/include/asm/spinlock.h
+++ b/arch/arc/include/asm/spinlock.h
@@ -45,7 +45,14 @@ static inline int arch_spin_trylock(arch_spinlock_t *lock)
 
 static inline void arch_spin_unlock(arch_spinlock_t *lock)
 {
-	lock->slock = __ARCH_SPIN_LOCK_UNLOCKED__;
+	unsigned int tmp = __ARCH_SPIN_LOCK_UNLOCKED__;
+
+	__asm__ __volatile__(
+	"	ex  %0, [%1]		\n"
+	: "+r" (tmp)
+	: "r"(&(lock->slock))
+	: "memory");
+
 	smp_mb();
 }
 
diff --git a/arch/arc/include/asm/spinlock_types.h b/arch/arc/include/asm/spinlock_types.h
index 8276bfd61704..662627ced4f2 100644
--- a/arch/arc/include/asm/spinlock_types.h
+++ b/arch/arc/include/asm/spinlock_types.h
@@ -20,9 +20,9 @@ typedef struct {
 #define __ARCH_SPIN_LOCK_LOCKED		{ __ARCH_SPIN_LOCK_LOCKED__ }
 
 /*
- * Unlocked:     0x01_00_00_00
- * Read lock(s): 0x00_FF_00_00 to say 0x01
- * Write lock:   0x0, but only possible if prior value "unlocked" 0x0100_0000
+ * Unlocked     : 0x0100_0000
+ * Read lock(s) : 0x00FF_FFFF to 0x01  (Multiple Readers decrement it)
+ * Write lock   : 0x0, but only if prior value is "unlocked" 0x0100_0000
  */
 typedef struct {
 	volatile unsigned int	counter;
diff --git a/arch/arc/include/asm/uaccess.h b/arch/arc/include/asm/uaccess.h
index 32420824375b..30c9baffa96f 100644
--- a/arch/arc/include/asm/uaccess.h
+++ b/arch/arc/include/asm/uaccess.h
@@ -43,7 +43,7 @@
  * Because it essentially checks if buffer end is within limit and @len is
  * non-ngeative, which implies that buffer start will be within limit too.
  *
- * The reason for rewriting being, for majorit yof cases, @len is generally
+ * The reason for rewriting being, for majority of cases, @len is generally
  * compile time constant, causing first sub-expression to be compile time
  * subsumed.
  *
@@ -53,7 +53,7 @@
  *
  */
 #define __user_ok(addr, sz)	(((sz) <= TASK_SIZE) && \
-				 (((addr)+(sz)) <= get_fs()))
+				 ((addr) <= (get_fs() - (sz))))
 #define __access_ok(addr, sz)	(unlikely(__kernel_ok) || \
 				 likely(__user_ok((addr), (sz))))
 
diff --git a/arch/arc/kernel/.gitignore b/arch/arc/kernel/.gitignore
new file mode 100644
index 000000000000..c5f676c3c224
--- /dev/null
+++ b/arch/arc/kernel/.gitignore
@@ -0,0 +1 @@
+vmlinux.lds
diff --git a/arch/arc/kernel/devtree.c b/arch/arc/kernel/devtree.c
index bdee3a812052..2340af0e1d6f 100644
--- a/arch/arc/kernel/devtree.c
+++ b/arch/arc/kernel/devtree.c
@@ -18,12 +18,6 @@
 #include <asm/clk.h>
 #include <asm/mach_desc.h>
 
-/* called from unflatten_device_tree() to bootstrap devicetree itself */
-void * __init early_init_dt_alloc_memory_arch(u64 size, u64 align)
-{
-	return __va(memblock_alloc(size, align));
-}
-
 /**
  * setup_machine_fdt - Machine setup when an dtb was passed to the kernel
  * @dt:		virtual address pointer to dt blob
diff --git a/arch/arc/kernel/entry.S b/arch/arc/kernel/entry.S
index 1d7165156e17..b908dde8a331 100644
--- a/arch/arc/kernel/entry.S
+++ b/arch/arc/kernel/entry.S
@@ -267,12 +267,7 @@ ARC_EXIT handle_interrupt_level1
 
 ARC_ENTRY instr_service
 
-	EXCPN_PROLOG_FREEUP_REG r9
-
-	lr  r9, [erstatus]
-
-	SWITCH_TO_KERNEL_STK
-	SAVE_ALL_SYS
+	EXCEPTION_PROLOGUE
 
 	lr  r0, [efa]
 	mov r1, sp
@@ -289,15 +284,13 @@ ARC_EXIT instr_service
 
 ARC_ENTRY mem_service
 
-	EXCPN_PROLOG_FREEUP_REG r9
-
-	lr  r9, [erstatus]
-
-	SWITCH_TO_KERNEL_STK
-	SAVE_ALL_SYS
+	EXCEPTION_PROLOGUE
 
 	lr  r0, [efa]
 	mov r1, sp
+
+	FAKE_RET_FROM_EXCPN r9
+
 	bl  do_memory_error
 	b   ret_from_exception
 ARC_EXIT mem_service
@@ -308,11 +301,7 @@ ARC_EXIT mem_service
 
 ARC_ENTRY EV_MachineCheck
 
-	EXCPN_PROLOG_FREEUP_REG r9
-	lr  r9, [erstatus]
-
-	SWITCH_TO_KERNEL_STK
-	SAVE_ALL_SYS
+	EXCEPTION_PROLOGUE
 
 	lr  r2, [ecr]
 	lr  r0, [efa]
@@ -342,13 +331,7 @@ ARC_EXIT EV_MachineCheck
 
 ARC_ENTRY EV_TLBProtV
 
-	EXCPN_PROLOG_FREEUP_REG r9
-
-	;Which mode (user/kernel) was the system in when Exception occured
-	lr  r9, [erstatus]
-
-	SWITCH_TO_KERNEL_STK
-	SAVE_ALL_SYS
+	EXCEPTION_PROLOGUE
 
 	;---------(3) Save some more regs-----------------
 	;  vineetg: Mar 6th: Random Seg Fault issue #1
@@ -406,12 +389,7 @@ ARC_EXIT EV_TLBProtV
 ; ---------------------------------------------
 ARC_ENTRY EV_PrivilegeV
 
-	EXCPN_PROLOG_FREEUP_REG r9
-
-	lr  r9, [erstatus]
-
-	SWITCH_TO_KERNEL_STK
-	SAVE_ALL_SYS
+	EXCEPTION_PROLOGUE
 
 	lr  r0, [efa]
 	mov r1, sp
@@ -427,14 +405,13 @@ ARC_EXIT EV_PrivilegeV
 ; ---------------------------------------------
 ARC_ENTRY EV_Extension
 
-	EXCPN_PROLOG_FREEUP_REG r9
-	lr  r9, [erstatus]
-
-	SWITCH_TO_KERNEL_STK
-	SAVE_ALL_SYS
+	EXCEPTION_PROLOGUE
 
 	lr  r0, [efa]
 	mov r1, sp
+
+	FAKE_RET_FROM_EXCPN r9
+
 	bl  do_extension_fault
 	b   ret_from_exception
 ARC_EXIT EV_Extension
@@ -526,14 +503,7 @@ trap_with_param:
 
 ARC_ENTRY EV_Trap
 
-	; Need at least 1 reg to code the early exception prolog
-	EXCPN_PROLOG_FREEUP_REG r9
-
-	;Which mode (user/kernel) was the system in when intr occured
-	lr  r9, [erstatus]
-
-	SWITCH_TO_KERNEL_STK
-	SAVE_ALL_SYS
+	EXCEPTION_PROLOGUE
 
 	;------- (4) What caused the Trap --------------
 	lr     r12, [ecr]
@@ -642,6 +612,9 @@ resume_kernel_mode:
 
 #ifdef CONFIG_PREEMPT
 
+	; This is a must for preempt_schedule_irq()
+	IRQ_DISABLE	r9
+
 	; Can't preempt if preemption disabled
 	GET_CURR_THR_INFO_FROM_SP   r10
 	ld  r8, [r10, THREAD_INFO_PREEMPT_COUNT]
@@ -651,8 +624,6 @@ resume_kernel_mode:
 	ld  r9, [r10, THREAD_INFO_FLAGS]
 	bbit0  r9, TIF_NEED_RESCHED, restore_regs
 
-	IRQ_DISABLE	r9
-
 	; Invoke PREEMPTION
 	bl      preempt_schedule_irq
 
@@ -665,12 +636,11 @@ resume_kernel_mode:
 ;
 ; Restore the saved sys context (common exit-path for EXCPN/IRQ/Trap)
 ; IRQ shd definitely not happen between now and rtie
+; All 2 entry points to here already disable interrupts
 
 restore_regs :
 
-	; Disable Interrupts while restoring reg-file back
-	; XXX can this be optimised out
-	IRQ_DISABLE_SAVE    r9, r10	;@r10 has prisitine (pre-disable) copy
+	lr	r10, [status32]
 
 	; Restore REG File. In case multiple Events outstanding,
 	; use the same priorty as rtie: EXCPN, L2 IRQ, L1 IRQ, None
diff --git a/arch/arc/kernel/head.S b/arch/arc/kernel/head.S
index 2a913f85a747..0f944f024513 100644
--- a/arch/arc/kernel/head.S
+++ b/arch/arc/kernel/head.S
@@ -34,6 +34,9 @@ stext:
 	;	IDENTITY Reg [ 3  2  1  0 ]
 	;	(cpu-id)             ^^^	=> Zero for UP ARC700
 	;					=> #Core-ID if SMP (Master 0)
+	; Note that non-boot CPUs might not land here if halt-on-reset and
+	; instead breath life from @first_lines_of_secondary, but we still
+	; need to make sure only boot cpu takes this path.
 	GET_CPU_ID  r5
 	cmp	r5, 0
 	jnz	arc_platform_smp_wait_to_boot
@@ -98,6 +101,8 @@ stext:
 
 first_lines_of_secondary:
 
+	sr	@_int_vec_base_lds, [AUX_INTR_VEC_BASE]
+
 	; setup per-cpu idle task as "current" on this CPU
 	ld	r0, [@secondary_idle_tsk]
 	SET_CURR_TASK_ON_CPU  r0, r1
diff --git a/arch/arc/kernel/irq.c b/arch/arc/kernel/irq.c
index 305b3f866aa7..5fc92455da36 100644
--- a/arch/arc/kernel/irq.c
+++ b/arch/arc/kernel/irq.c
@@ -24,7 +24,6 @@
  * -Needed for each CPU (hence not foldable into init_IRQ)
  *
  * what it does ?
- * -setup Vector Table Base Reg - in case Linux not linked at 0x8000_0000
  * -Disable all IRQs (on CPU side)
  * -Optionally, setup the High priority Interrupts as Level 2 IRQs
  */
diff --git a/arch/arc/kernel/ptrace.c b/arch/arc/kernel/ptrace.c
index 333238564b67..5d76706139dd 100644
--- a/arch/arc/kernel/ptrace.c
+++ b/arch/arc/kernel/ptrace.c
@@ -102,7 +102,7 @@ static int genregs_set(struct task_struct *target,
 	REG_IGNORE_ONE(pad2);
 	REG_IN_CHUNK(callee, efa, cregs);	/* callee_regs[r25..r13] */
 	REG_IGNORE_ONE(efa);			/* efa update invalid */
-	REG_IN_ONE(stop_pc, &ptregs->ret);	/* stop_pc: PC update */
+	REG_IGNORE_ONE(stop_pc);			/* PC updated via @ret */
 
 	return ret;
 }
diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c
index 6b083454d039..2c68bc7e6a78 100644
--- a/arch/arc/kernel/setup.c
+++ b/arch/arc/kernel/setup.c
@@ -47,10 +47,7 @@ void read_arc_build_cfg_regs(void)
 	READ_BCR(AUX_IDENTITY, cpu->core);
 
 	cpu->timers = read_aux_reg(ARC_REG_TIMERS_BCR);
-
 	cpu->vec_base = read_aux_reg(AUX_INTR_VEC_BASE);
-	if (cpu->vec_base == 0)
-		cpu->vec_base = (unsigned int)_int_vec_base_lds;
 
 	READ_BCR(ARC_REG_D_UNCACH_BCR, uncached_space);
 	cpu->uncached_base = uncached_space.start << 24;
@@ -357,8 +354,6 @@ void __init setup_arch(char **cmdline_p)
 	 */
 	root_mountflags &= ~MS_RDONLY;
 
-	console_verbose();
-
 #if defined(CONFIG_VT) && defined(CONFIG_DUMMY_CONSOLE)
 	conswitchp = &dummy_con;
 #endif
diff --git a/arch/arc/kernel/signal.c b/arch/arc/kernel/signal.c
index ee6ef2f60a28..7e95e1a86510 100644
--- a/arch/arc/kernel/signal.c
+++ b/arch/arc/kernel/signal.c
@@ -101,7 +101,6 @@ SYSCALL_DEFINE0(rt_sigreturn)
 {
 	struct rt_sigframe __user *sf;
 	unsigned int magic;
-	int err;
 	struct pt_regs *regs = current_pt_regs();
 
 	/* Always make any pending restarted system calls return -EINTR */
@@ -119,15 +118,16 @@ SYSCALL_DEFINE0(rt_sigreturn)
 	if (!access_ok(VERIFY_READ, sf, sizeof(*sf)))
 		goto badframe;
 
-	err = restore_usr_regs(regs, sf);
-	err |= __get_user(magic, &sf->sigret_magic);
-	if (err)
+	if (__get_user(magic, &sf->sigret_magic))
 		goto badframe;
 
 	if (unlikely(is_do_ss_needed(magic)))
 		if (restore_altstack(&sf->uc.uc_stack))
 			goto badframe;
 
+	if (restore_usr_regs(regs, sf))
+		goto badframe;
+
 	/* Don't restart from sigreturn */
 	syscall_wont_restart(regs);
 
@@ -191,6 +191,15 @@ setup_rt_frame(int signo, struct k_sigaction *ka, siginfo_t *info,
 		return 1;
 
 	/*
+	 * w/o SA_SIGINFO, struct ucontext is partially populated (only
+	 * uc_mcontext/uc_sigmask) for kernel's normal user state preservation
+	 * during signal handler execution. This works for SA_SIGINFO as well
+	 * although the semantics are now overloaded (the same reg state can be
+	 * inspected by userland: but are they allowed to fiddle with it ?
+	 */
+	err |= stash_usr_regs(sf, regs, set);
+
+	/*
 	 * SA_SIGINFO requires 3 args to signal handler:
 	 *  #1: sig-no (common to any handler)
 	 *  #2: struct siginfo
@@ -213,14 +222,6 @@ setup_rt_frame(int signo, struct k_sigaction *ka, siginfo_t *info,
 		magic = MAGIC_SIGALTSTK;
 	}
 
-	/*
-	 * w/o SA_SIGINFO, struct ucontext is partially populated (only
-	 * uc_mcontext/uc_sigmask) for kernel's normal user state preservation
-	 * during signal handler execution. This works for SA_SIGINFO as well
-	 * although the semantics are now overloaded (the same reg state can be
-	 * inspected by userland: but are they allowed to fiddle with it ?
-	 */
-	err |= stash_usr_regs(sf, regs, set);
 	err |= __put_user(magic, &sf->sigret_magic);
 	if (err)
 		return err;
diff --git a/arch/arc/kernel/time.c b/arch/arc/kernel/time.c
index 0e51e69cf30d..3fde7de3ea67 100644
--- a/arch/arc/kernel/time.c
+++ b/arch/arc/kernel/time.c
@@ -227,12 +227,9 @@ void __attribute__((weak)) arc_local_timer_setup(unsigned int cpu)
 {
 	struct clock_event_device *clk = &per_cpu(arc_clockevent_device, cpu);
 
-	clockevents_calc_mult_shift(clk, arc_get_core_freq(), 5);
-
-	clk->max_delta_ns = clockevent_delta2ns(ARC_TIMER_MAX, clk);
 	clk->cpumask = cpumask_of(cpu);
-
-	clockevents_register_device(clk);
+	clockevents_config_and_register(clk, arc_get_core_freq(),
+					0, ARC_TIMER_MAX);
 
 	/*
 	 * setup the per-cpu timer IRQ handler - for all cpus
diff --git a/arch/arc/kernel/unaligned.c b/arch/arc/kernel/unaligned.c
index c0f832f595d3..7ff5b5c183bb 100644
--- a/arch/arc/kernel/unaligned.c
+++ b/arch/arc/kernel/unaligned.c
@@ -16,6 +16,16 @@
 #include <linux/uaccess.h>
 #include <asm/disasm.h>
 
+#ifdef CONFIG_CPU_BIG_ENDIAN
+#define BE		1
+#define FIRST_BYTE_16	"swap %1, %1\n swape %1, %1\n"
+#define FIRST_BYTE_32	"swape %1, %1\n"
+#else
+#define BE		0
+#define FIRST_BYTE_16
+#define FIRST_BYTE_32
+#endif
+
 #define __get8_unaligned_check(val, addr, err)		\
 	__asm__(					\
 	"1:	ldb.ab	%1, [%2, 1]\n"			\
@@ -36,9 +46,9 @@
 	do {						\
 		unsigned int err = 0, v, a = addr;	\
 		__get8_unaligned_check(v, a, err);	\
-		val =  v ;				\
+		val =  v << ((BE) ? 8 : 0);		\
 		__get8_unaligned_check(v, a, err);	\
-		val |= v << 8;				\
+		val |= v << ((BE) ? 0 : 8);		\
 		if (err)				\
 			goto fault;			\
 	} while (0)
@@ -47,13 +57,13 @@
 	do {						\
 		unsigned int err = 0, v, a = addr;	\
 		__get8_unaligned_check(v, a, err);	\
-		val =  v << 0;				\
+		val =  v << ((BE) ? 24 : 0);		\
 		__get8_unaligned_check(v, a, err);	\
-		val |= v << 8;				\
+		val |= v << ((BE) ? 16 : 8);		\
 		__get8_unaligned_check(v, a, err);	\
-		val |= v << 16;				\
+		val |= v << ((BE) ? 8 : 16);		\
 		__get8_unaligned_check(v, a, err);	\
-		val |= v << 24;				\
+		val |= v << ((BE) ? 0 : 24);		\
 		if (err)				\
 			goto fault;			\
 	} while (0)
@@ -63,6 +73,7 @@
 		unsigned int err = 0, v = val, a = addr;\
 							\
 		__asm__(				\
+		FIRST_BYTE_16				\
 		"1:	stb.ab	%1, [%2, 1]\n"		\
 		"	lsr %1, %1, 8\n"		\
 		"2:	stb	%1, [%2]\n"		\
@@ -87,8 +98,9 @@
 #define put32_unaligned_check(val, addr)		\
 	do {						\
 		unsigned int err = 0, v = val, a = addr;\
-		__asm__(				\
 							\
+		__asm__(				\
+		FIRST_BYTE_32				\
 		"1:	stb.ab	%1, [%2, 1]\n"		\
 		"	lsr %1, %1, 8\n"		\
 		"2:	stb.ab	%1, [%2, 1]\n"		\
@@ -233,6 +245,12 @@ int misaligned_fixup(unsigned long address, struct pt_regs *regs,
 		regs->status32 &= ~STATUS_DE_MASK;
 	} else {
 		regs->ret += state.instr_len;
+
+		/* handle zero-overhead-loop */
+		if ((regs->ret == regs->lp_end) && (regs->lp_count)) {
+			regs->ret = regs->lp_start;
+			regs->lp_count--;
+		}
 	}
 
 	return 0;
diff --git a/arch/arc/mm/cache_arc700.c b/arch/arc/mm/cache_arc700.c
index f415d851b765..5a1259cd948c 100644
--- a/arch/arc/mm/cache_arc700.c
+++ b/arch/arc/mm/cache_arc700.c
@@ -622,12 +622,12 @@ void flush_icache_range(unsigned long kstart, unsigned long kend)
 /*
  * General purpose helper to make I and D cache lines consistent.
  * @paddr is phy addr of region
- * @vaddr is typically user or kernel vaddr (vmalloc)
- *    Howver in one instance, flush_icache_range() by kprobe (for a breakpt in
+ * @vaddr is typically user vaddr (breakpoint) or kernel vaddr (vmalloc)
+ *    However in one instance, when called by kprobe (for a breakpt in
  *    builtin kernel code) @vaddr will be paddr only, meaning CDU operation will
  *    use a paddr to index the cache (despite VIPT). This is fine since since a
- *    built-in kernel page will not have any virtual mappings (not even kernel)
- *    kprobe on loadable module is different as it will have kvaddr.
+ *    builtin kernel page will not have any virtual mappings.
+ *    kprobe on loadable module will be kernel vaddr.
  */
 void __sync_icache_dcache(unsigned long paddr, unsigned long vaddr, int len)
 {
diff --git a/arch/arc/mm/fault.c b/arch/arc/mm/fault.c
index 0fd1f0d515ff..d63f3de0cd5b 100644
--- a/arch/arc/mm/fault.c
+++ b/arch/arc/mm/fault.c
@@ -60,8 +60,7 @@ void do_page_fault(struct pt_regs *regs, unsigned long address)
 	siginfo_t info;
 	int fault, ret;
 	int write = regs->ecr_cause & ECR_C_PROTV_STORE;  /* ST/EX */
-	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
-				(write ? FAULT_FLAG_WRITE : 0);
+	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
 
 	/*
 	 * We fault-in kernel-space virtual memory on-demand. The
@@ -89,6 +88,8 @@ void do_page_fault(struct pt_regs *regs, unsigned long address)
 	if (in_atomic() || !mm)
 		goto no_context;
 
+	if (user_mode(regs))
+		flags |= FAULT_FLAG_USER;
 retry:
 	down_read(&mm->mmap_sem);
 	vma = find_vma(mm, address);
@@ -117,12 +118,12 @@ good_area:
 	if (write) {
 		if (!(vma->vm_flags & VM_WRITE))
 			goto bad_area;
+		flags |= FAULT_FLAG_WRITE;
 	} else {
 		if (!(vma->vm_flags & (VM_READ | VM_EXEC)))
 			goto bad_area;
 	}
 
-survive:
 	/*
 	 * If for any reason at all we couldn't handle the fault,
 	 * make sure we exit gracefully rather than endlessly redo
@@ -201,10 +202,6 @@ no_context:
 	die("Oops", regs, address);
 
 out_of_memory:
-	if (is_global_init(tsk)) {
-		yield();
-		goto survive;
-	}
 	up_read(&mm->mmap_sem);
 
 	if (user_mode(regs)) {
diff --git a/arch/arc/mm/init.c b/arch/arc/mm/init.c
index a08ce7185423..81279ec73a6a 100644
--- a/arch/arc/mm/init.c
+++ b/arch/arc/mm/init.c
@@ -127,9 +127,8 @@ void __init free_initrd_mem(unsigned long start, unsigned long end)
 #endif
 
 #ifdef CONFIG_OF_FLATTREE
-void __init early_init_dt_setup_initrd_arch(unsigned long start,
-					    unsigned long end)
+void __init early_init_dt_setup_initrd_arch(u64 start, u64 end)
 {
-	pr_err("%s(%lx, %lx)\n", __func__, start, end);
+	pr_err("%s(%llx, %llx)\n", __func__, start, end);
 }
 #endif /* CONFIG_OF_FLATTREE */
diff --git a/arch/arc/mm/tlb.c b/arch/arc/mm/tlb.c
index 7957dc4e4d4a..71cb26df4255 100644
--- a/arch/arc/mm/tlb.c
+++ b/arch/arc/mm/tlb.c
@@ -52,6 +52,7 @@
  */
 
 #include <linux/module.h>
+#include <linux/bug.h>
 #include <asm/arcregs.h>
 #include <asm/setup.h>
 #include <asm/mmu_context.h>
@@ -99,48 +100,45 @@
 
 
 /* A copy of the ASID from the PID reg is kept in asid_cache */
-int asid_cache = FIRST_ASID;
-
-/* ASID to mm struct mapping. We have one extra entry corresponding to
- * NO_ASID to save us a compare when clearing the mm entry for old asid
- * see get_new_mmu_context (asm-arc/mmu_context.h)
- */
-struct mm_struct *asid_mm_map[NUM_ASID + 1];
+unsigned int asid_cache = MM_CTXT_FIRST_CYCLE;
 
 /*
  * Utility Routine to erase a J-TLB entry
- * The procedure is to look it up in the MMU. If found, ERASE it by
- *  issuing a TlbWrite CMD with PD0 = PD1 = 0
+ * Caller needs to setup Index Reg (manually or via getIndex)
  */
-
-static void __tlb_entry_erase(void)
+static inline void __tlb_entry_erase(void)
 {
 	write_aux_reg(ARC_REG_TLBPD1, 0);
 	write_aux_reg(ARC_REG_TLBPD0, 0);
 	write_aux_reg(ARC_REG_TLBCOMMAND, TLBWrite);
 }
 
-static void tlb_entry_erase(unsigned int vaddr_n_asid)
+static inline unsigned int tlb_entry_lkup(unsigned long vaddr_n_asid)
 {
 	unsigned int idx;
 
-	/* Locate the TLB entry for this vaddr + ASID */
 	write_aux_reg(ARC_REG_TLBPD0, vaddr_n_asid);
+
 	write_aux_reg(ARC_REG_TLBCOMMAND, TLBProbe);
 	idx = read_aux_reg(ARC_REG_TLBINDEX);
 
+	return idx;
+}
+
+static void tlb_entry_erase(unsigned int vaddr_n_asid)
+{
+	unsigned int idx;
+
+	/* Locate the TLB entry for this vaddr + ASID */
+	idx = tlb_entry_lkup(vaddr_n_asid);
+
 	/* No error means entry found, zero it out */
 	if (likely(!(idx & TLB_LKUP_ERR))) {
 		__tlb_entry_erase();
-	} else {		/* Some sort of Error */
-
+	} else {
 		/* Duplicate entry error */
-		if (idx & 0x1) {
-			/* TODO we need to handle this case too */
-			pr_emerg("unhandled Duplicate flush for %x\n",
-			       vaddr_n_asid);
-		}
-		/* else entry not found so nothing to do */
+		WARN(idx == TLB_DUP_ERR, "Probe returned Dup PD for %x\n",
+					   vaddr_n_asid);
 	}
 }
 
@@ -159,7 +157,7 @@ static void utlb_invalidate(void)
 {
 #if (CONFIG_ARC_MMU_VER >= 2)
 
-#if (CONFIG_ARC_MMU_VER < 3)
+#if (CONFIG_ARC_MMU_VER == 2)
 	/* MMU v2 introduced the uTLB Flush command.
 	 * There was however an obscure hardware bug, where uTLB flush would
 	 * fail when a prior probe for J-TLB (both totally unrelated) would
@@ -182,6 +180,36 @@ static void utlb_invalidate(void)
 
 }
 
+static void tlb_entry_insert(unsigned int pd0, unsigned int pd1)
+{
+	unsigned int idx;
+
+	/*
+	 * First verify if entry for this vaddr+ASID already exists
+	 * This also sets up PD0 (vaddr, ASID..) for final commit
+	 */
+	idx = tlb_entry_lkup(pd0);
+
+	/*
+	 * If Not already present get a free slot from MMU.
+	 * Otherwise, Probe would have located the entry and set INDEX Reg
+	 * with existing location. This will cause Write CMD to over-write
+	 * existing entry with new PD0 and PD1
+	 */
+	if (likely(idx & TLB_LKUP_ERR))
+		write_aux_reg(ARC_REG_TLBCOMMAND, TLBGetIndex);
+
+	/* setup the other half of TLB entry (pfn, rwx..) */
+	write_aux_reg(ARC_REG_TLBPD1, pd1);
+
+	/*
+	 * Commit the Entry to MMU
+	 * It doesnt sound safe to use the TLBWriteNI cmd here
+	 * which doesn't flush uTLBs. I'd rather be safe than sorry.
+	 */
+	write_aux_reg(ARC_REG_TLBCOMMAND, TLBWrite);
+}
+
 /*
  * Un-conditionally (without lookup) erase the entire MMU contents
  */
@@ -224,13 +252,14 @@ noinline void local_flush_tlb_mm(struct mm_struct *mm)
 		return;
 
 	/*
-	 * Workaround for Android weirdism:
-	 * A binder VMA could end up in a task such that vma->mm != tsk->mm
-	 * old code would cause h/w - s/w ASID to get out of sync
+	 * - Move to a new ASID, but only if the mm is still wired in
+	 *   (Android Binder ended up calling this for vma->mm != tsk->mm,
+	 *    causing h/w - s/w ASID to get out of sync)
+	 * - Also get_new_mmu_context() new implementation allocates a new
+	 *   ASID only if it is not allocated already - so unallocate first
 	 */
-	if (current->mm != mm)
-		destroy_context(mm);
-	else
+	destroy_context(mm);
+	if (current->mm == mm)
 		get_new_mmu_context(mm);
 }
 
@@ -246,7 +275,6 @@ void local_flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
 			   unsigned long end)
 {
 	unsigned long flags;
-	unsigned int asid;
 
 	/* If range @start to @end is more than 32 TLB entries deep,
 	 * its better to move to a new ASID rather than searching for
@@ -268,11 +296,10 @@ void local_flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
 	start &= PAGE_MASK;
 
 	local_irq_save(flags);
-	asid = vma->vm_mm->context.asid;
 
-	if (asid != NO_ASID) {
+	if (vma->vm_mm->context.asid != MM_CTXT_NO_ASID) {
 		while (start < end) {
-			tlb_entry_erase(start | (asid & 0xff));
+			tlb_entry_erase(start | hw_pid(vma->vm_mm));
 			start += PAGE_SIZE;
 		}
 	}
@@ -326,9 +353,8 @@ void local_flush_tlb_page(struct vm_area_struct *vma, unsigned long page)
 	 */
 	local_irq_save(flags);
 
-	if (vma->vm_mm->context.asid != NO_ASID) {
-		tlb_entry_erase((page & PAGE_MASK) |
-				(vma->vm_mm->context.asid & 0xff));
+	if (vma->vm_mm->context.asid != MM_CTXT_NO_ASID) {
+		tlb_entry_erase((page & PAGE_MASK) | hw_pid(vma->vm_mm));
 		utlb_invalidate();
 	}
 
@@ -341,8 +367,8 @@ void local_flush_tlb_page(struct vm_area_struct *vma, unsigned long page)
 void create_tlb(struct vm_area_struct *vma, unsigned long address, pte_t *ptep)
 {
 	unsigned long flags;
-	unsigned int idx, asid_or_sasid;
-	unsigned long pd0_flags;
+	unsigned int asid_or_sasid, rwx;
+	unsigned long pd0, pd1;
 
 	/*
 	 * create_tlb() assumes that current->mm == vma->mm, since
@@ -381,40 +407,30 @@ void create_tlb(struct vm_area_struct *vma, unsigned long address, pte_t *ptep)
 	/* update this PTE credentials */
 	pte_val(*ptep) |= (_PAGE_PRESENT | _PAGE_ACCESSED);
 
-	/* Create HW TLB entry Flags (in PD0) from PTE Flags */
-#if (CONFIG_ARC_MMU_VER <= 2)
-	pd0_flags = ((pte_val(*ptep) & PTE_BITS_IN_PD0) >> 1);
-#else
-	pd0_flags = ((pte_val(*ptep) & PTE_BITS_IN_PD0));
-#endif
+	/* Create HW TLB(PD0,PD1) from PTE  */
 
 	/* ASID for this task */
 	asid_or_sasid = read_aux_reg(ARC_REG_PID) & 0xff;
 
-	write_aux_reg(ARC_REG_TLBPD0, address | pd0_flags | asid_or_sasid);
-
-	/* Load remaining info in PD1 (Page Frame Addr and Kx/Kw/Kr Flags) */
-	write_aux_reg(ARC_REG_TLBPD1, (pte_val(*ptep) & PTE_BITS_IN_PD1));
-
-	/* First verify if entry for this vaddr+ASID already exists */
-	write_aux_reg(ARC_REG_TLBCOMMAND, TLBProbe);
-	idx = read_aux_reg(ARC_REG_TLBINDEX);
+	pd0 = address | asid_or_sasid | (pte_val(*ptep) & PTE_BITS_IN_PD0);
 
 	/*
-	 * If Not already present get a free slot from MMU.
-	 * Otherwise, Probe would have located the entry and set INDEX Reg
-	 * with existing location. This will cause Write CMD to over-write
-	 * existing entry with new PD0 and PD1
+	 * ARC MMU provides fully orthogonal access bits for K/U mode,
+	 * however Linux only saves 1 set to save PTE real-estate
+	 * Here we convert 3 PTE bits into 6 MMU bits:
+	 * -Kernel only entries have Kr Kw Kx 0 0 0
+	 * -User entries have mirrored K and U bits
 	 */
-	if (likely(idx & TLB_LKUP_ERR))
-		write_aux_reg(ARC_REG_TLBCOMMAND, TLBGetIndex);
+	rwx = pte_val(*ptep) & PTE_BITS_RWX;
 
-	/*
-	 * Commit the Entry to MMU
-	 * It doesnt sound safe to use the TLBWriteNI cmd here
-	 * which doesn't flush uTLBs. I'd rather be safe than sorry.
-	 */
-	write_aux_reg(ARC_REG_TLBCOMMAND, TLBWrite);
+	if (pte_val(*ptep) & _PAGE_GLOBAL)
+		rwx <<= 3;		/* r w x => Kr Kw Kx 0 0 0 */
+	else
+		rwx |= (rwx << 3);	/* r w x => Kr Kw Kx Ur Uw Ux */
+
+	pd1 = rwx | (pte_val(*ptep) & PTE_BITS_NON_RWX_IN_PD1);
+
+	tlb_entry_insert(pd0, pd1);
 
 	local_irq_restore(flags);
 }
@@ -553,13 +569,6 @@ void arc_mmu_init(void)
 	if (mmu->pg_sz != PAGE_SIZE)
 		panic("MMU pg size != PAGE_SIZE (%luk)\n", TO_KB(PAGE_SIZE));
 
-	/*
-	 * ASID mgmt data structures are compile time init
-	 *  asid_cache = FIRST_ASID and asid_mm_map[] all zeroes
-	 */
-
-	local_flush_tlb_all();
-
 	/* Enable the MMU */
 	write_aux_reg(ARC_REG_PID, MMU_ENABLE);
 
@@ -671,25 +680,28 @@ void do_tlb_overlap_fault(unsigned long cause, unsigned long address,
  * Low Level ASM TLB handler calls this if it finds that HW and SW ASIDS
  * don't match
  */
-void print_asid_mismatch(int is_fast_path)
+void print_asid_mismatch(int mm_asid, int mmu_asid, int is_fast_path)
 {
-	int pid_sw, pid_hw;
-	pid_sw = current->active_mm->context.asid;
-	pid_hw = read_aux_reg(ARC_REG_PID) & 0xff;
-
 	pr_emerg("ASID Mismatch in %s Path Handler: sw-pid=0x%x hw-pid=0x%x\n",
-	       is_fast_path ? "Fast" : "Slow", pid_sw, pid_hw);
+	       is_fast_path ? "Fast" : "Slow", mm_asid, mmu_asid);
 
 	__asm__ __volatile__("flag 1");
 }
 
-void tlb_paranoid_check(unsigned int pid_sw, unsigned long addr)
+void tlb_paranoid_check(unsigned int mm_asid, unsigned long addr)
 {
-	unsigned int pid_hw;
+	unsigned int mmu_asid;
 
-	pid_hw = read_aux_reg(ARC_REG_PID) & 0xff;
+	mmu_asid = read_aux_reg(ARC_REG_PID) & 0xff;
 
-	if (addr < 0x70000000 && ((pid_hw != pid_sw) || (pid_sw == NO_ASID)))
-		print_asid_mismatch(0);
+	/*
+	 * At the time of a TLB miss/installation
+	 *   - HW version needs to match SW version
+	 *   - SW needs to have a valid ASID
+	 */
+	if (addr < 0x70000000 &&
+	    ((mm_asid == MM_CTXT_NO_ASID) ||
+	      (mmu_asid != (mm_asid & MM_CTXT_ASID_MASK))))
+		print_asid_mismatch(mm_asid, mmu_asid, 0);
 }
 #endif
diff --git a/arch/arc/mm/tlbex.S b/arch/arc/mm/tlbex.S
index 5c5bb23001b0..cf7d7d9ad695 100644
--- a/arch/arc/mm/tlbex.S
+++ b/arch/arc/mm/tlbex.S
@@ -44,17 +44,36 @@
 #include <asm/arcregs.h>
 #include <asm/cache.h>
 #include <asm/processor.h>
-#if (CONFIG_ARC_MMU_VER == 1)
 #include <asm/tlb-mmu1.h>
-#endif
 
-;--------------------------------------------------------------------------
-; scratch memory to save the registers (r0-r3) used to code TLB refill Handler
-; For details refer to comments before TLBMISS_FREEUP_REGS below
+;-----------------------------------------------------------------
+; ARC700 Exception Handling doesn't auto-switch stack and it only provides
+; ONE scratch AUX reg "ARC_REG_SCRATCH_DATA0"
+;
+; For Non-SMP, the scratch AUX reg is repurposed to cache task PGD, so a
+; "global" is used to free-up FIRST core reg to be able to code the rest of
+; exception prologue (IRQ auto-disabled on Exceptions, so it's IRQ-safe).
+; Since the Fast Path TLB Miss handler is coded with 4 regs, the remaining 3
+; need to be saved as well by extending the "global" to be 4 words. Hence
+;	".size   ex_saved_reg1, 16"
+; [All of this dance is to avoid stack switching for each TLB Miss, since we
+; only need to save only a handful of regs, as opposed to complete reg file]
+;
+; For ARC700 SMP, the "global" obviously can't be used for free up the FIRST
+; core reg as it will not be SMP safe.
+; Thus scratch AUX reg is used (and no longer used to cache task PGD).
+; To save the rest of 3 regs - per cpu, the global is made "per-cpu".
+; Epilogue thus has to locate the "per-cpu" storage for regs.
+; To avoid cache line bouncing the per-cpu global is aligned/sized per
+; L1_CACHE_SHIFT, despite fundamentally needing to be 12 bytes only. Hence
+;	".size   ex_saved_reg1, (CONFIG_NR_CPUS << L1_CACHE_SHIFT)"
+
+; As simple as that....
 ;--------------------------------------------------------------------------
 
+; scratch memory to save [r0-r3] used to code TLB refill Handler
 ARCFP_DATA ex_saved_reg1
-	.align 1 << L1_CACHE_SHIFT	; IMP: Must be Cache Line aligned
+	.align 1 << L1_CACHE_SHIFT
 	.type   ex_saved_reg1, @object
 #ifdef CONFIG_SMP
 	.size   ex_saved_reg1, (CONFIG_NR_CPUS << L1_CACHE_SHIFT)
@@ -66,6 +85,44 @@ ex_saved_reg1:
 	.zero 16
 #endif
 
+.macro TLBMISS_FREEUP_REGS
+#ifdef CONFIG_SMP
+	sr  r0, [ARC_REG_SCRATCH_DATA0]	; freeup r0 to code with
+	GET_CPU_ID  r0			; get to per cpu scratch mem,
+	lsl r0, r0, L1_CACHE_SHIFT	; cache line wide per cpu
+	add r0, @ex_saved_reg1, r0
+#else
+	st    r0, [@ex_saved_reg1]
+	mov_s r0, @ex_saved_reg1
+#endif
+	st_s  r1, [r0, 4]
+	st_s  r2, [r0, 8]
+	st_s  r3, [r0, 12]
+
+	; VERIFY if the ASID in MMU-PID Reg is same as
+	; one in Linux data structures
+
+	tlb_paranoid_check_asm
+.endm
+
+.macro TLBMISS_RESTORE_REGS
+#ifdef CONFIG_SMP
+	GET_CPU_ID  r0			; get to per cpu scratch mem
+	lsl r0, r0, L1_CACHE_SHIFT	; each is cache line wide
+	add r0, @ex_saved_reg1, r0
+	ld_s  r3, [r0,12]
+	ld_s  r2, [r0, 8]
+	ld_s  r1, [r0, 4]
+	lr    r0, [ARC_REG_SCRATCH_DATA0]
+#else
+	mov_s r0, @ex_saved_reg1
+	ld_s  r3, [r0,12]
+	ld_s  r2, [r0, 8]
+	ld_s  r1, [r0, 4]
+	ld_s  r0, [r0]
+#endif
+.endm
+
 ;============================================================================
 ;  Troubleshooting Stuff
 ;============================================================================
@@ -76,34 +133,35 @@ ex_saved_reg1:
 ; In bizzare scenrios SW and HW ASID can get out-of-sync which is trouble.
 ; So we try to detect this in TLB Mis shandler
 
-
-.macro DBG_ASID_MISMATCH
+.macro tlb_paranoid_check_asm
 
 #ifdef CONFIG_ARC_DBG_TLB_PARANOIA
 
-	; make sure h/w ASID is same as s/w ASID
-
 	GET_CURR_TASK_ON_CPU  r3
 	ld r0, [r3, TASK_ACT_MM]
 	ld r0, [r0, MM_CTXT+MM_CTXT_ASID]
+	breq r0, 0, 55f	; Error if no ASID allocated
 
 	lr r1, [ARC_REG_PID]
 	and r1, r1, 0xFF
-	breq r1, r0, 5f
 
+	and r2, r0, 0xFF	; MMU PID bits only for comparison
+	breq r1, r2, 5f
+
+55:
 	; Error if H/w and S/w ASID don't match, but NOT if in kernel mode
-	lr  r0, [erstatus]
-	bbit0 r0, STATUS_U_BIT, 5f
+	lr  r2, [erstatus]
+	bbit0 r2, STATUS_U_BIT, 5f
 
 	; We sure are in troubled waters, Flag the error, but to do so
 	; need to switch to kernel mode stack to call error routine
 	GET_TSK_STACK_BASE   r3, sp
 
 	; Call printk to shoutout aloud
-	mov r0, 1
+	mov r2, 1
 	j print_asid_mismatch
 
-5:   ; ASIDs match so proceed normally
+5:	; ASIDs match so proceed normally
 	nop
 
 #endif
@@ -161,13 +219,17 @@ ex_saved_reg1:
 ; IN: r0 = PTE, r1 = ptr to PTE
 
 .macro CONV_PTE_TO_TLB
-	and r3, r0, PTE_BITS_IN_PD1 ; Extract permission flags+PFN from PTE
-	sr  r3, [ARC_REG_TLBPD1]    ; these go in PD1
+	and    r3, r0, PTE_BITS_RWX	;       r w x
+	lsl    r2, r3, 3		; r w x 0 0 0
+	and.f  0,  r0, _PAGE_GLOBAL
+	or.z   r2, r2, r3		; r w x r w x
+
+	and r3, r0, PTE_BITS_NON_RWX_IN_PD1 ; Extract PFN+cache bits from PTE
+	or  r3, r3, r2
+
+	sr  r3, [ARC_REG_TLBPD1]    	; these go in PD1
 
 	and r2, r0, PTE_BITS_IN_PD0 ; Extract other PTE flags: (V)alid, (G)lb
-#if (CONFIG_ARC_MMU_VER <= 2)   /* Neednot be done with v3 onwards */
-	lsr r2, r2                  ; shift PTE flags to match layout in PD0
-#endif
 
 	lr  r3,[ARC_REG_TLBPD0]     ; MMU prepares PD0 with vaddr and asid
 
@@ -191,68 +253,6 @@ ex_saved_reg1:
 #endif
 .endm
 
-;-----------------------------------------------------------------
-; ARC700 Exception Handling doesn't auto-switch stack and it only provides
-; ONE scratch AUX reg "ARC_REG_SCRATCH_DATA0"
-;
-; For Non-SMP, the scratch AUX reg is repurposed to cache task PGD, so a
-; "global" is used to free-up FIRST core reg to be able to code the rest of
-; exception prologue (IRQ auto-disabled on Exceptions, so it's IRQ-safe).
-; Since the Fast Path TLB Miss handler is coded with 4 regs, the remaining 3
-; need to be saved as well by extending the "global" to be 4 words. Hence
-;	".size   ex_saved_reg1, 16"
-; [All of this dance is to avoid stack switching for each TLB Miss, since we
-; only need to save only a handful of regs, as opposed to complete reg file]
-;
-; For ARC700 SMP, the "global" obviously can't be used for free up the FIRST
-; core reg as it will not be SMP safe.
-; Thus scratch AUX reg is used (and no longer used to cache task PGD).
-; To save the rest of 3 regs - per cpu, the global is made "per-cpu".
-; Epilogue thus has to locate the "per-cpu" storage for regs.
-; To avoid cache line bouncing the per-cpu global is aligned/sized per
-; L1_CACHE_SHIFT, despite fundamentally needing to be 12 bytes only. Hence
-;	".size   ex_saved_reg1, (CONFIG_NR_CPUS << L1_CACHE_SHIFT)"
-
-; As simple as that....
-
-.macro TLBMISS_FREEUP_REGS
-#ifdef CONFIG_SMP
-	sr  r0, [ARC_REG_SCRATCH_DATA0]	; freeup r0 to code with
-	GET_CPU_ID  r0			; get to per cpu scratch mem,
-	lsl r0, r0, L1_CACHE_SHIFT	; cache line wide per cpu
-	add r0, @ex_saved_reg1, r0
-#else
-	st    r0, [@ex_saved_reg1]
-	mov_s r0, @ex_saved_reg1
-#endif
-	st_s  r1, [r0, 4]
-	st_s  r2, [r0, 8]
-	st_s  r3, [r0, 12]
-
-	; VERIFY if the ASID in MMU-PID Reg is same as
-	; one in Linux data structures
-
-	DBG_ASID_MISMATCH
-.endm
-
-;-----------------------------------------------------------------
-.macro TLBMISS_RESTORE_REGS
-#ifdef CONFIG_SMP
-	GET_CPU_ID  r0			; get to per cpu scratch mem
-	lsl r0, r0, L1_CACHE_SHIFT	; each is cache line wide
-	add r0, @ex_saved_reg1, r0
-	ld_s  r3, [r0,12]
-	ld_s  r2, [r0, 8]
-	ld_s  r1, [r0, 4]
-	lr    r0, [ARC_REG_SCRATCH_DATA0]
-#else
-	mov_s r0, @ex_saved_reg1
-	ld_s  r3, [r0,12]
-	ld_s  r2, [r0, 8]
-	ld_s  r1, [r0, 4]
-	ld_s  r0, [r0]
-#endif
-.endm
 
 ARCFP_CODE	;Fast Path Code, candidate for ICCM
 
@@ -277,8 +277,8 @@ ARC_ENTRY EV_TLBMissI
 	;----------------------------------------------------------------
 	; VERIFY_PTE: Check if PTE permissions approp for executing code
 	cmp_s   r2, VMALLOC_START
-	mov.lo  r2, (_PAGE_PRESENT | _PAGE_U_EXECUTE)
-	mov.hs  r2, (_PAGE_PRESENT | _PAGE_K_EXECUTE)
+	mov_s   r2, (_PAGE_PRESENT | _PAGE_EXECUTE)
+	or.hs   r2, r2, _PAGE_GLOBAL
 
 	and     r3, r0, r2  ; Mask out NON Flag bits from PTE
 	xor.f   r3, r3, r2  ; check ( ( pte & flags_test ) == flags_test )
@@ -317,26 +317,21 @@ ARC_ENTRY EV_TLBMissD
 	;----------------------------------------------------------------
 	; VERIFY_PTE: Chk if PTE permissions approp for data access (R/W/R+W)
 
-	mov_s   r2, 0
+	cmp_s	r2, VMALLOC_START
+	mov_s   r2, _PAGE_PRESENT	; common bit for K/U PTE
+	or.hs	r2, r2, _PAGE_GLOBAL	; kernel PTE only
+
+	; Linux PTE [RWX] bits are semantically overloaded:
+	; -If PAGE_GLOBAL set, they refer to kernel-only flags (vmalloc)
+	; -Otherwise they are user-mode permissions, and those are exactly
+	;  same for kernel mode as well (e.g. copy_(to|from)_user)
+
 	lr      r3, [ecr]
 	btst_s  r3, ECR_C_BIT_DTLB_LD_MISS	; Read Access
-	or.nz   r2, r2, _PAGE_U_READ      	; chk for Read flag in PTE
+	or.nz   r2, r2, _PAGE_READ      	; chk for Read flag in PTE
 	btst_s  r3, ECR_C_BIT_DTLB_ST_MISS	; Write Access
-	or.nz   r2, r2, _PAGE_U_WRITE     	; chk for Write flag in PTE
-	; Above laddering takes care of XCHG access
-	;   which is both Read and Write
-
-	; If kernel mode access, ; make _PAGE_xx flags as _PAGE_K_xx
-	; For copy_(to|from)_user, despite exception taken in kernel mode,
-	; this code is not hit, because EFA would still be the user mode
-	; address (EFA < 0x6000_0000).
-	; This code is for legit kernel mode faults, vmalloc specifically
-	; (EFA: 0x7000_0000 to 0x7FFF_FFFF)
-
-	lr      r3, [efa]
-	cmp     r3, VMALLOC_START - 1   ; If kernel mode access
-	asl.hi  r2, r2, 3               ; make _PAGE_xx flags as _PAGE_K_xx
-	or      r2, r2, _PAGE_PRESENT   ; Common flag for K/U mode
+	or.nz   r2, r2, _PAGE_WRITE     	; chk for Write flag in PTE
+	; Above laddering takes care of XCHG access (both R and W)
 
 	; By now, r2 setup with all the Flags we need to check in PTE
 	and     r3, r0, r2              ; Mask out NON Flag bits from PTE
@@ -371,13 +366,7 @@ do_slow_path_pf:
 
 	; Slow path TLB Miss handled as a regular ARC Exception
 	; (stack switching / save the complete reg-file).
-	; That requires freeing up r9
-	EXCPN_PROLOG_FREEUP_REG r9
-
-	lr  r9, [erstatus]
-
-	SWITCH_TO_KERNEL_STK
-	SAVE_ALL_SYS
+	EXCEPTION_PROLOGUE
 
 	; ------- setup args for Linux Page fault Hanlder ---------
 	mov_s r0, sp
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 43594d5116ef..1ad6fb6c094d 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -3,20 +3,21 @@ config ARM
 	default y
 	select ARCH_BINFMT_ELF_RANDOMIZE_PIE
 	select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
-	select ARCH_HAVE_CUSTOM_GPIO_H
 	select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
+	select ARCH_HAVE_CUSTOM_GPIO_H
 	select ARCH_WANT_IPC_PARSE_VERSION
 	select BUILDTIME_EXTABLE_SORT if MMU
+	select CLONE_BACKWARDS
 	select CPU_PM if (SUSPEND || CPU_IDLE)
 	select DCACHE_WORD_ACCESS if (CPU_V6 || CPU_V6K || CPU_V7) && !CPU_BIG_ENDIAN && MMU
 	select GENERIC_ATOMIC64 if (CPU_V7M || CPU_V6 || !CPU_32v6K || !AEABI)
 	select GENERIC_CLOCKEVENTS_BROADCAST if SMP
+	select GENERIC_IDLE_POLL_SETUP
 	select GENERIC_IRQ_PROBE
 	select GENERIC_IRQ_SHOW
 	select GENERIC_PCI_IOMAP
 	select GENERIC_SCHED_CLOCK
 	select GENERIC_SMP_IDLE_THREAD
-	select GENERIC_IDLE_POLL_SETUP
 	select GENERIC_STRNCPY_FROM_USER
 	select GENERIC_STRNLEN_USER
 	select HARDIRQS_SW_RESEND
@@ -25,6 +26,7 @@ config ARM
 	select HAVE_ARCH_SECCOMP_FILTER
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_BPF_JIT
+	select HAVE_CONTEXT_TRACKING
 	select HAVE_C_RECORDMCOUNT
 	select HAVE_DEBUG_KMEMLEAK
 	select HAVE_DMA_API_DEBUG
@@ -35,7 +37,6 @@ config ARM
 	select HAVE_FUNCTION_GRAPH_TRACER if (!THUMB2_KERNEL)
 	select HAVE_FUNCTION_TRACER if (!XIP_KERNEL)
 	select HAVE_GENERIC_DMA_COHERENT
-	select HAVE_GENERIC_HARDIRQS
 	select HAVE_HW_BREAKPOINT if (PERF_EVENTS && (CPU_V6 || CPU_V6K || CPU_V7))
 	select HAVE_IDE if PCI || ISA || PCMCIA
 	select HAVE_IRQ_TIME_ACCOUNTING
@@ -47,21 +48,22 @@ config ARM
 	select HAVE_KPROBES if !XIP_KERNEL
 	select HAVE_KRETPROBES if (HAVE_KPROBES)
 	select HAVE_MEMBLOCK
+	select HAVE_MOD_ARCH_SPECIFIC if ARM_UNWIND
 	select HAVE_OPROFILE if (HAVE_PERF_EVENTS)
 	select HAVE_PERF_EVENTS
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_SYSCALL_TRACEPOINTS
 	select HAVE_UID16
+	select IRQ_FORCED_THREADING
 	select KTIME_SCALAR
+	select MODULES_USE_ELF_REL
+	select OLD_SIGACTION
+	select OLD_SIGSUSPEND3
 	select PERF_USE_VMALLOC
 	select RTC_LIB
 	select SYS_SUPPORTS_APM_EMULATION
-	select HAVE_MOD_ARCH_SPECIFIC if ARM_UNWIND
-	select MODULES_USE_ELF_REL
-	select CLONE_BACKWARDS
-	select OLD_SIGSUSPEND3
-	select OLD_SIGACTION
-	select HAVE_CONTEXT_TRACKING
+	# Above selects are sorted alphabetically; please add new ones
+	# according to that.  Thanks.
 	help
 	  The ARM series is a line of low-power-consumption RISC chip designs
 	  licensed by ARM Ltd and targeted at embedded applications and
@@ -385,8 +387,8 @@ config ARCH_GEMINI
 	bool "Cortina Systems Gemini"
 	select ARCH_REQUIRE_GPIOLIB
 	select ARCH_USES_GETTIMEOFFSET
-	select NEED_MACH_GPIO_H
 	select CPU_FA526
+	select NEED_MACH_GPIO_H
 	help
 	  Support for the Cortina Systems Gemini family SoCs
 
@@ -441,7 +443,6 @@ config ARCH_NETX
 config ARCH_IOP13XX
 	bool "IOP13xx-based"
 	depends on MMU
-	select ARCH_SUPPORTS_MSI
 	select CPU_XSC3
 	select NEED_MACH_MEMORY_H
 	select NEED_RET_TO_USER
@@ -487,8 +488,8 @@ config ARCH_IXP4XX
 	select GENERIC_CLOCKEVENTS
 	select MIGHT_HAVE_PCI
 	select NEED_MACH_IO_H
-	select USB_EHCI_BIG_ENDIAN_MMIO
 	select USB_EHCI_BIG_ENDIAN_DESC
+	select USB_EHCI_BIG_ENDIAN_MMIO
 	help
 	  Support for Intel's IXP4XX (XScale) family of processors.
 
@@ -498,11 +499,11 @@ config ARCH_DOVE
 	select CPU_PJ4
 	select GENERIC_CLOCKEVENTS
 	select MIGHT_HAVE_PCI
+	select MVEBU_MBUS
 	select PINCTRL
 	select PINCTRL_DOVE
 	select PLAT_ORION_LEGACY
 	select USB_ARCH_HAS_EHCI
-	select MVEBU_MBUS
 	help
 	  Support for the Marvell Dove SoC 88AP510
 
@@ -512,12 +513,12 @@ config ARCH_KIRKWOOD
 	select ARCH_REQUIRE_GPIOLIB
 	select CPU_FEROCEON
 	select GENERIC_CLOCKEVENTS
+	select MVEBU_MBUS
 	select PCI
 	select PCI_QUIRKS
 	select PINCTRL
 	select PINCTRL_KIRKWOOD
 	select PLAT_ORION_LEGACY
-	select MVEBU_MBUS
 	help
 	  Support for the following Marvell Kirkwood series SoCs:
 	  88F6180, 88F6192 and 88F6281.
@@ -527,9 +528,9 @@ config ARCH_MV78XX0
 	select ARCH_REQUIRE_GPIOLIB
 	select CPU_FEROCEON
 	select GENERIC_CLOCKEVENTS
+	select MVEBU_MBUS
 	select PCI
 	select PLAT_ORION_LEGACY
-	select MVEBU_MBUS
 	help
 	  Support for the following Marvell MV78xx0 series SoCs:
 	  MV781x0, MV782x0.
@@ -540,9 +541,9 @@ config ARCH_ORION5X
 	select ARCH_REQUIRE_GPIOLIB
 	select CPU_FEROCEON
 	select GENERIC_CLOCKEVENTS
+	select MVEBU_MBUS
 	select PCI
 	select PLAT_ORION_LEGACY
-	select MVEBU_MBUS
 	help
 	  Support for the following Marvell Orion 5x series SoCs:
 	  Orion-1 (5181), Orion-VoIP (5181L), Orion-NAS (5182),
@@ -557,6 +558,7 @@ config ARCH_MMP
 	select GENERIC_CLOCKEVENTS
 	select GPIO_PXA
 	select IRQ_DOMAIN
+	select MULTI_IRQ_HANDLER
 	select NEED_MACH_GPIO_H
 	select PINCTRL
 	select PLAT_PXA
@@ -630,6 +632,7 @@ config ARCH_MSM
 	bool "Qualcomm MSM"
 	select ARCH_REQUIRE_GPIOLIB
 	select CLKDEV_LOOKUP
+	select CLKSRC_OF if OF
 	select COMMON_CLK
 	select GENERIC_CLOCKEVENTS
 	help
@@ -645,7 +648,7 @@ config ARCH_SHMOBILE
 	select CLKDEV_LOOKUP
 	select GENERIC_CLOCKEVENTS
 	select HAVE_ARM_SCU if SMP
-	select HAVE_ARM_TWD if LOCAL_TIMERS
+	select HAVE_ARM_TWD if SMP
 	select HAVE_CLK
 	select HAVE_MACH_CLKDEV
 	select HAVE_SMP
@@ -700,7 +703,7 @@ config ARCH_S3C24XX
 	select ARCH_HAS_CPUFREQ
 	select ARCH_REQUIRE_GPIOLIB
 	select CLKDEV_LOOKUP
-	select CLKSRC_MMIO
+	select CLKSRC_SAMSUNG_PWM
 	select GENERIC_CLOCKEVENTS
 	select GPIO_SAMSUNG
 	select HAVE_CLK
@@ -723,7 +726,7 @@ config ARCH_S3C64XX
 	select ARCH_REQUIRE_GPIOLIB
 	select ARM_VIC
 	select CLKDEV_LOOKUP
-	select CLKSRC_MMIO
+	select CLKSRC_SAMSUNG_PWM
 	select CPU_V6
 	select GENERIC_CLOCKEVENTS
 	select GPIO_SAMSUNG
@@ -739,7 +742,6 @@ config ARCH_S3C64XX
 	select SAMSUNG_ATAGS
 	select SAMSUNG_CLKSRC
 	select SAMSUNG_GPIOLIB_4BIT
-	select SAMSUNG_IRQ_VIC_TIMER
 	select SAMSUNG_WDT_RESET
 	select USB_ARCH_HAS_OHCI
 	help
@@ -748,7 +750,7 @@ config ARCH_S3C64XX
 config ARCH_S5P64X0
 	bool "Samsung S5P6440 S5P6450"
 	select CLKDEV_LOOKUP
-	select CLKSRC_MMIO
+	select CLKSRC_SAMSUNG_PWM
 	select CPU_V6
 	select GENERIC_CLOCKEVENTS
 	select GPIO_SAMSUNG
@@ -757,8 +759,8 @@ config ARCH_S5P64X0
 	select HAVE_S3C2410_WATCHDOG if WATCHDOG
 	select HAVE_S3C_RTC if RTC_CLASS
 	select NEED_MACH_GPIO_H
-	select SAMSUNG_WDT_RESET
 	select SAMSUNG_ATAGS
+	select SAMSUNG_WDT_RESET
 	help
 	  Samsung S5P64X0 CPU based systems, such as the Samsung SMDK6440,
 	  SMDK6450.
@@ -767,7 +769,7 @@ config ARCH_S5PC100
 	bool "Samsung S5PC100"
 	select ARCH_REQUIRE_GPIOLIB
 	select CLKDEV_LOOKUP
-	select CLKSRC_MMIO
+	select CLKSRC_SAMSUNG_PWM
 	select CPU_V7
 	select GENERIC_CLOCKEVENTS
 	select GPIO_SAMSUNG
@@ -776,8 +778,8 @@ config ARCH_S5PC100
 	select HAVE_S3C2410_WATCHDOG if WATCHDOG
 	select HAVE_S3C_RTC if RTC_CLASS
 	select NEED_MACH_GPIO_H
-	select SAMSUNG_WDT_RESET
 	select SAMSUNG_ATAGS
+	select SAMSUNG_WDT_RESET
 	help
 	  Samsung S5PC100 series based systems
 
@@ -787,7 +789,7 @@ config ARCH_S5PV210
 	select ARCH_HAS_HOLES_MEMORYMODEL
 	select ARCH_SPARSEMEM_ENABLE
 	select CLKDEV_LOOKUP
-	select CLKSRC_MMIO
+	select CLKSRC_SAMSUNG_PWM
 	select CPU_V7
 	select GENERIC_CLOCKEVENTS
 	select GPIO_SAMSUNG
@@ -1372,6 +1374,15 @@ config ARM_ERRATA_798181
 	  which sends an IPI to the CPUs that are running the same ASID
 	  as the one being invalidated.
 
+config ARM_ERRATA_773022
+	bool "ARM errata: incorrect instructions may be executed from loop buffer"
+	depends on CPU_V7
+	help
+	  This option enables the workaround for the 773022 Cortex-A15
+	  (up to r0p4) erratum. In certain rare sequences of code, the
+	  loop buffer may deliver incorrect instructions. This
+	  workaround disables the loop buffer to avoid the erratum.
+
 endmenu
 
 source "arch/arm/common/Kconfig"
@@ -1584,23 +1595,13 @@ config ARM_PSCI
 	  0022A ("Power State Coordination Interface System Software on
 	  ARM processors").
 
-config LOCAL_TIMERS
-	bool "Use local timer interrupts"
-	depends on SMP
-	default y
-	help
-	  Enable support for local timers on SMP platforms, rather then the
-	  legacy IPI broadcast method.  Local timers allows the system
-	  accounting to be spread across the timer interval, preventing a
-	  "thundering herd" at every timer tick.
-
 # The GPIO number here must be sorted by descending number. In case of
 # a multiplatform kernel, we just want the highest value required by the
 # selected platforms.
 config ARCH_NR_GPIO
 	int
 	default 1024 if ARCH_SHMOBILE || ARCH_TEGRA
-	default 512 if ARCH_EXYNOS || ARCH_KEYSTONE || SOC_OMAP5
+	default 512 if ARCH_EXYNOS || ARCH_KEYSTONE || SOC_OMAP5 || SOC_DRA7XX
 	default 392 if ARCH_U8500
 	default 352 if ARCH_VT8500
 	default 288 if ARCH_SUNXI
@@ -1613,13 +1614,50 @@ config ARCH_NR_GPIO
 
 source kernel/Kconfig.preempt
 
-config HZ
+config HZ_FIXED
 	int
 	default 200 if ARCH_EBSA110 || ARCH_S3C24XX || ARCH_S5P64X0 || \
 		ARCH_S5PV210 || ARCH_EXYNOS4
 	default AT91_TIMER_HZ if ARCH_AT91
 	default SHMOBILE_TIMER_HZ if ARCH_SHMOBILE
-	default 100
+	default 0
+
+choice
+	depends on HZ_FIXED = 0
+	prompt "Timer frequency"
+
+config HZ_100
+	bool "100 Hz"
+
+config HZ_200
+	bool "200 Hz"
+
+config HZ_250
+	bool "250 Hz"
+
+config HZ_300
+	bool "300 Hz"
+
+config HZ_500
+	bool "500 Hz"
+
+config HZ_1000
+	bool "1000 Hz"
+
+endchoice
+
+config HZ
+	int
+	default HZ_FIXED if HZ_FIXED != 0
+	default 100 if HZ_100
+	default 200 if HZ_200
+	default 250 if HZ_250
+	default 300 if HZ_300
+	default 500 if HZ_500
+	default 1000
+
+config SCHED_HRTICK
+	def_bool HIGH_RES_TIMERS
 
 config SCHED_HRTICK
 	def_bool HIGH_RES_TIMERS
@@ -1756,6 +1794,9 @@ config HAVE_ARCH_TRANSPARENT_HUGEPAGE
        def_bool y
        depends on ARM_LPAE
 
+config ARCH_WANT_GENERAL_HUGETLB
+	def_bool y
+
 source "mm/Kconfig"
 
 config FORCE_MAX_ZONEORDER
@@ -2064,8 +2105,7 @@ config KEXEC
 
 	  It is an ongoing process to be certain the hardware in a machine
 	  is properly shutdown, so do not be surprised if this code does not
-	  initially work for you.  It may help to enable device hotplugging
-	  support.
+	  initially work for you.
 
 config ATAGS_PROC
 	bool "Export atags in procfs"
@@ -2175,6 +2215,12 @@ config NEON
 	  Say Y to include support code for NEON, the ARMv7 Advanced SIMD
 	  Extension.
 
+config KERNEL_MODE_NEON
+	bool "Support for NEON in kernel mode"
+	depends on NEON && AEABI
+	help
+	  Say Y to include support for NEON in kernel mode.
+
 endmenu
 
 menu "Userspace binary formats"
@@ -2199,7 +2245,7 @@ source "kernel/power/Kconfig"
 
 config ARCH_SUSPEND_POSSIBLE
 	depends on !ARCH_S5PC100
-	depends on CPU_ARM920T || CPU_ARM926T || CPU_SA1100 || \
+	depends on CPU_ARM920T || CPU_ARM926T || CPU_FEROCEON || CPU_SA1100 || \
 		CPU_V6 || CPU_V6K || CPU_V7 || CPU_XSC3 || CPU_XSCALE || CPU_MOHAWK
 	def_bool y
 
diff --git a/arch/arm/Kconfig.debug b/arch/arm/Kconfig.debug
index 583f4a00ec32..9762c84b4198 100644
--- a/arch/arm/Kconfig.debug
+++ b/arch/arm/Kconfig.debug
@@ -92,6 +92,7 @@ choice
 	config DEBUG_BCM2835
 		bool "Kernel low-level debugging on BCM2835 PL011 UART"
 		depends on ARCH_BCM2835
+		select DEBUG_UART_PL01X
 
 	config DEBUG_CLPS711X_UART1
 		bool "Kernel low-level debugging messages via UART1"
@@ -110,6 +111,7 @@ choice
 	config DEBUG_CNS3XXX
 		bool "Kernel Kernel low-level debugging on Cavium Networks CNS3xxx"
 		depends on ARCH_CNS3XXX
+		select DEBUG_UART_PL01X
 		help
 		  Say Y here if you want the debug print routines to direct
                   their output to the CNS3xxx UART0.
@@ -117,6 +119,7 @@ choice
 	config DEBUG_DAVINCI_DA8XX_UART1
 		bool "Kernel low-level debugging on DaVinci DA8XX using UART1"
 		depends on ARCH_DAVINCI_DA8XX
+		select DEBUG_UART_8250
 		help
 		  Say Y here if you want the debug print routines to direct
 		  their output to UART1 serial port on DaVinci DA8XX devices.
@@ -124,6 +127,7 @@ choice
 	config DEBUG_DAVINCI_DA8XX_UART2
 		bool "Kernel low-level debugging on DaVinci DA8XX using UART2"
 		depends on ARCH_DAVINCI_DA8XX
+		select DEBUG_UART_8250
 		help
 		  Say Y here if you want the debug print routines to direct
 		  their output to UART2 serial port on DaVinci DA8XX devices.
@@ -131,6 +135,7 @@ choice
 	config DEBUG_DAVINCI_DMx_UART0
 		bool "Kernel low-level debugging on DaVinci DMx using UART0"
 		depends on ARCH_DAVINCI_DMx
+		select DEBUG_UART_8250
 		help
 		  Say Y here if you want the debug print routines to direct
 		  their output to UART0 serial port on DaVinci DMx devices.
@@ -138,6 +143,7 @@ choice
 	config DEBUG_DAVINCI_TNETV107X_UART1
 		bool "Kernel low-level debugging on DaVinci TNETV107x using UART1"
 		depends on ARCH_DAVINCI_TNETV107X
+		select DEBUG_UART_8250
 		help
 		  Say Y here if you want the debug print routines to direct
 		  their output to UART1 serial port on DaVinci TNETV107X
@@ -174,9 +180,26 @@ choice
 		  Say Y here if you want the debug print routines to direct
 		  their output to the 8250 at PCI COM1.
 
+	config DEBUG_HI3620_UART
+		bool "Hisilicon HI3620 Debug UART"
+		depends on ARCH_HI3xxx
+		select DEBUG_UART_PL01X
+		help
+		  Say Y here if you want kernel low-level debugging support
+		  on HI3620 UART.
+
+	config DEBUG_HI3716_UART
+		bool "Hisilicon Hi3716 Debug UART"
+		depends on ARCH_HI3xxx
+		select DEBUG_UART_PL01X
+		help
+		  Say Y here if you want kernel low-level debugging support
+		  on HI3716 UART.
+
 	config DEBUG_HIGHBANK_UART
 		bool "Kernel low-level debugging messages via Highbank UART"
 		depends on ARCH_HIGHBANK
+		select DEBUG_UART_PL01X
 		help
 		  Say Y here if you want the debug print routines to direct
 		  their output to the UART on Highbank based devices.
@@ -191,6 +214,7 @@ choice
 	config DEBUG_IMX23_UART
 		bool "i.MX23 Debug UART"
 		depends on SOC_IMX23
+		select DEBUG_UART_PL01X
 		help
 		  Say Y here if you want kernel low-level debugging support
 		  on i.MX23.
@@ -212,6 +236,7 @@ choice
 	config DEBUG_IMX28_UART
 		bool "i.MX28 Debug UART"
 		depends on SOC_IMX28
+		select DEBUG_UART_PL01X
 		help
 		  Say Y here if you want kernel low-level debugging support
 		  on i.MX28.
@@ -261,6 +286,7 @@ choice
 	config DEBUG_KEYSTONE_UART0
 		bool "Kernel low-level debugging on KEYSTONE2 using UART0"
 		depends on ARCH_KEYSTONE
+		select DEBUG_UART_8250
 		help
 		  Say Y here if you want the debug print routines to direct
 		  their output to UART0 serial port on KEYSTONE2 devices.
@@ -268,6 +294,7 @@ choice
 	config DEBUG_KEYSTONE_UART1
 		bool "Kernel low-level debugging on KEYSTONE2 using UART1"
 		depends on ARCH_KEYSTONE
+		select DEBUG_UART_8250
 		help
 		  Say Y here if you want the debug print routines to direct
 		  their output to UART1 serial port on KEYSTONE2 devices.
@@ -275,6 +302,7 @@ choice
 	config DEBUG_MMP_UART2
 		bool "Kernel low-level debugging message via MMP UART2"
 		depends on ARCH_MMP
+		select DEBUG_UART_8250
 		help
 		  Say Y here if you want kernel low-level debugging support
 		  on MMP UART2.
@@ -282,6 +310,7 @@ choice
 	config DEBUG_MMP_UART3
 		bool "Kernel low-level debugging message via MMP UART3"
 		depends on ARCH_MMP
+		select DEBUG_UART_8250
 		help
 		  Say Y here if you want kernel low-level debugging support
 		  on MMP UART3.
@@ -326,6 +355,7 @@ choice
 	config DEBUG_MVEBU_UART
 		bool "Kernel low-level debugging messages via MVEBU UART (old bootloaders)"
 		depends on ARCH_MVEBU
+		select DEBUG_UART_8250
 		help
 		  Say Y here if you want kernel low-level debugging support
 		  on MVEBU based platforms.
@@ -344,6 +374,7 @@ choice
 	config DEBUG_MVEBU_UART_ALTERNATE
 		bool "Kernel low-level debugging messages via MVEBU UART (new bootloaders)"
 		depends on ARCH_MVEBU
+		select DEBUG_UART_8250
 		help
 		  Say Y here if you want kernel low-level debugging support
 		  on MVEBU based platforms.
@@ -358,6 +389,7 @@ choice
 	config DEBUG_NOMADIK_UART
 		bool "Kernel low-level debugging messages via NOMADIK UART"
 		depends on ARCH_NOMADIK
+		select DEBUG_UART_PL01X
 		help
 		  Say Y here if you want kernel low-level debugging support
 		  on NOMADIK based platforms.
@@ -365,6 +397,7 @@ choice
 	config DEBUG_NSPIRE_CLASSIC_UART
 		bool "Kernel low-level debugging via TI-NSPIRE 8250 UART"
 		depends on ARCH_NSPIRE
+		select DEBUG_UART_8250
 		help
 		  Say Y here if you want kernel low-level debugging support
 		  on TI-NSPIRE classic models.
@@ -372,20 +405,82 @@ choice
 	config DEBUG_NSPIRE_CX_UART
 		bool "Kernel low-level debugging via TI-NSPIRE PL011 UART"
 		depends on ARCH_NSPIRE
+		select DEBUG_UART_PL01X
 		help
 		  Say Y here if you want kernel low-level debugging support
 		  on TI-NSPIRE CX models.
 
-	config DEBUG_OMAP2PLUS_UART
-		bool "Kernel low-level debugging messages via OMAP2PLUS UART"
+	config DEBUG_OMAP2UART1
+		bool "OMAP2/3/4 UART1 (omap2/3 sdp boards and some omap3 boards)"
 		depends on ARCH_OMAP2PLUS
+		select DEBUG_OMAP2PLUS_UART
 		help
-		  Say Y here if you want kernel low-level debugging support
-		  on OMAP2PLUS based platforms.
+		  This covers at least h4, 2430sdp, 3430sdp, 3630sdp,
+		  omap3 torpedo and 3530 lv som.
+
+	config DEBUG_OMAP2UART2
+		bool "Kernel low-level debugging messages via OMAP2/3/4 UART2"
+		depends on ARCH_OMAP2PLUS
+		select DEBUG_OMAP2PLUS_UART
+
+	config DEBUG_OMAP2UART3
+		bool "Kernel low-level debugging messages via OMAP2 UART3 (n8x0)"
+		depends on ARCH_OMAP2PLUS
+		select DEBUG_OMAP2PLUS_UART
+
+	config DEBUG_OMAP3UART3
+		bool "Kernel low-level debugging messages via OMAP3 UART3 (most omap3 boards)"
+		depends on ARCH_OMAP2PLUS
+		select DEBUG_OMAP2PLUS_UART
+		help
+		  This covers at least cm_t3x, beagle, crane, devkit8000,
+		  igep00x0, ldp, n900, n9(50), pandora, overo, touchbook,
+		  and 3517evm.
+
+	config DEBUG_OMAP4UART3
+		bool "Kernel low-level debugging messages via OMAP4/5 UART3 (omap4 blaze, panda, omap5 sevm)"
+		depends on ARCH_OMAP2PLUS
+		select DEBUG_OMAP2PLUS_UART
+
+	config DEBUG_OMAP3UART4
+		bool "Kernel low-level debugging messages via OMAP36XX UART4"
+		depends on ARCH_OMAP2PLUS
+		select DEBUG_OMAP2PLUS_UART
+
+	config DEBUG_OMAP4UART4
+		bool "Kernel low-level debugging messages via OMAP4/5 UART4"
+		depends on ARCH_OMAP2PLUS
+		select DEBUG_OMAP2PLUS_UART
+
+	config DEBUG_TI81XXUART1
+		bool "Kernel low-level debugging messages via TI81XX UART1 (ti8148evm)"
+		depends on ARCH_OMAP2PLUS
+		select DEBUG_OMAP2PLUS_UART
+
+	config DEBUG_TI81XXUART2
+		bool "Kernel low-level debugging messages via TI81XX UART2"
+		depends on ARCH_OMAP2PLUS
+		select DEBUG_OMAP2PLUS_UART
+
+	config DEBUG_TI81XXUART3
+		bool "Kernel low-level debugging messages via TI81XX UART3 (ti8168evm)"
+		depends on ARCH_OMAP2PLUS
+		select DEBUG_OMAP2PLUS_UART
+
+	config DEBUG_AM33XXUART1
+		bool "Kernel low-level debugging messages via AM33XX UART1"
+		depends on ARCH_OMAP2PLUS
+		select DEBUG_OMAP2PLUS_UART
+
+	config DEBUG_ZOOM_UART
+		bool "Kernel low-level debugging messages via Zoom2/3 UART"
+		depends on ARCH_OMAP2PLUS
+		select DEBUG_OMAP2PLUS_UART
 
 	config DEBUG_PICOXCELL_UART
 		depends on ARCH_PICOXCELL
 		bool "Use PicoXcell UART for low-level debug"
+		select DEBUG_UART_8250
 		help
 		  Say Y here if you want kernel low-level debugging support
 		  on PicoXcell based platforms.
@@ -393,6 +488,7 @@ choice
 	config DEBUG_PXA_UART1
 		depends on ARCH_PXA
 		bool "Use PXA UART1 for low-level debug"
+		select DEBUG_UART_8250
 		help
 		  Say Y here if you want kernel low-level debugging support
 		  on PXA UART1.
@@ -400,6 +496,7 @@ choice
 	config DEBUG_REALVIEW_STD_PORT
 		bool "RealView Default UART"
 		depends on ARCH_REALVIEW
+		select DEBUG_UART_PL01X
 		help
 		  Say Y here if you want the debug print routines to direct
 		  their output to the serial port on RealView EB, PB11MP, PBA8
@@ -408,14 +505,64 @@ choice
 	config DEBUG_REALVIEW_PB1176_PORT
 		bool "RealView PB1176 UART"
 		depends on MACH_REALVIEW_PB1176
+		select DEBUG_UART_PL01X
 		help
 		  Say Y here if you want the debug print routines to direct
 		  their output to the standard serial port on the RealView
 		  PB1176 platform.
 
-	config DEBUG_ROCKCHIP_UART
-		bool "Kernel low-level debugging messages via Rockchip UART"
+	config DEBUG_RK29_UART0
+		bool "Kernel low-level debugging messages via Rockchip RK29 UART0"
+		depends on ARCH_ROCKCHIP
+		select DEBUG_UART_8250
+		help
+		  Say Y here if you want kernel low-level debugging support
+		  on Rockchip based platforms.
+
+	config DEBUG_RK29_UART1
+		bool "Kernel low-level debugging messages via Rockchip RK29 UART1"
+		depends on ARCH_ROCKCHIP
+		select DEBUG_UART_8250
+		help
+		  Say Y here if you want kernel low-level debugging support
+		  on Rockchip based platforms.
+
+	config DEBUG_RK29_UART2
+		bool "Kernel low-level debugging messages via Rockchip RK29 UART2"
+		depends on ARCH_ROCKCHIP
+		select DEBUG_UART_8250
+		help
+		  Say Y here if you want kernel low-level debugging support
+		  on Rockchip based platforms.
+
+	config DEBUG_RK3X_UART0
+		bool "Kernel low-level debugging messages via Rockchip RK3X UART0"
+		depends on ARCH_ROCKCHIP
+		select DEBUG_UART_8250
+		help
+		  Say Y here if you want kernel low-level debugging support
+		  on Rockchip based platforms.
+
+	config DEBUG_RK3X_UART1
+		bool "Kernel low-level debugging messages via Rockchip RK3X UART1"
+		depends on ARCH_ROCKCHIP
+		select DEBUG_UART_8250
+		help
+		  Say Y here if you want kernel low-level debugging support
+		  on Rockchip based platforms.
+
+	config DEBUG_RK3X_UART2
+		bool "Kernel low-level debugging messages via Rockchip RK3X UART2"
+		depends on ARCH_ROCKCHIP
+		select DEBUG_UART_8250
+		help
+		  Say Y here if you want kernel low-level debugging support
+		  on Rockchip based platforms.
+
+	config DEBUG_RK3X_UART3
+		bool "Kernel low-level debugging messages via Rockchip RK3X UART3"
 		depends on ARCH_ROCKCHIP
+		select DEBUG_UART_8250
 		help
 		  Say Y here if you want kernel low-level debugging support
 		  on Rockchip based platforms.
@@ -471,6 +618,7 @@ choice
 	config DEBUG_SOCFPGA_UART
 		depends on ARCH_SOCFPGA
 		bool "Use SOCFPGA UART for low-level debug"
+		select DEBUG_UART_8250
 		help
 		  Say Y here if you want kernel low-level debugging support
 		  on SOCFPGA based platforms.
@@ -478,6 +626,7 @@ choice
 	config DEBUG_SUNXI_UART0
 		bool "Kernel low-level debugging messages via sunXi UART0"
 		depends on ARCH_SUNXI
+		select DEBUG_UART_8250
 		help
 		  Say Y here if you want kernel low-level debugging support
 		  on Allwinner A1X based platforms on the UART0.
@@ -485,13 +634,59 @@ choice
 	config DEBUG_SUNXI_UART1
 		bool "Kernel low-level debugging messages via sunXi UART1"
 		depends on ARCH_SUNXI
+		select DEBUG_UART_8250
 		help
 		  Say Y here if you want kernel low-level debugging support
 		  on Allwinner A1X based platforms on the UART1.
 
-	config DEBUG_TEGRA_UART
+	config TEGRA_DEBUG_UART_AUTO_ODMDATA
+		bool "Kernel low-level debugging messages via Tegra UART via ODMDATA"
+		depends on ARCH_TEGRA
+		select DEBUG_TEGRA_UART
+		help
+		  Automatically determines which UART to use for low-level
+		  debug based on the ODMDATA value. This value is part of
+		  the BCT, and is written to the boot memory device using
+		  nvflash, or other flashing tool.  When bits 19:18 are 3,
+		  then bits 17:15 indicate which UART to use; 0/1/2/3/4
+		  are UART A/B/C/D/E.
+
+	config TEGRA_DEBUG_UARTA
+		bool "Kernel low-level debugging messages via Tegra UART A"
+		depends on ARCH_TEGRA
+		select DEBUG_TEGRA_UART
+		help
+		  Say Y here if you want kernel low-level debugging support
+		  on Tegra based platforms.
+
+	config TEGRA_DEBUG_UARTB
+		bool "Kernel low-level debugging messages via Tegra UART B"
+		depends on ARCH_TEGRA
+		select DEBUG_TEGRA_UART
+		help
+		  Say Y here if you want kernel low-level debugging support
+		  on Tegra based platforms.
+
+	config TEGRA_DEBUG_UARTC
+		bool "Kernel low-level debugging messages via Tegra UART C"
+		depends on ARCH_TEGRA
+		select DEBUG_TEGRA_UART
+		help
+		  Say Y here if you want kernel low-level debugging support
+		  on Tegra based platforms.
+
+	config TEGRA_DEBUG_UARTD
+		bool "Kernel low-level debugging messages via Tegra UART D"
+		depends on ARCH_TEGRA
+		select DEBUG_TEGRA_UART
+		help
+		  Say Y here if you want kernel low-level debugging support
+		  on Tegra based platforms.
+
+	config TEGRA_DEBUG_UARTE
+		bool "Kernel low-level debugging messages via Tegra UART E"
 		depends on ARCH_TEGRA
-		bool "Use Tegra UART for low-level debug"
+		select DEBUG_TEGRA_UART
 		help
 		  Say Y here if you want kernel low-level debugging support
 		  on Tegra based platforms.
@@ -510,19 +705,32 @@ choice
 		  Say Y here if you want the debug print routines to direct
 		  their output to the uart1 port on SiRFmarco devices.
 
-	config DEBUG_STI_UART
+	config STIH41X_DEBUG_ASC2
+		bool "Use StiH415/416 ASC2 UART for low-level debug"
+		depends on ARCH_STI
+		select DEBUG_STI_UART
+		help
+		  Say Y here if you want kernel low-level debugging support
+		  on STiH415/416 based platforms like b2000, which has
+		  default UART wired up to ASC2.
+
+		  If unsure, say N.
+
+	config STIH41X_DEBUG_SBC_ASC1
+		bool "Use StiH415/416 SBC ASC1 UART for low-level debug"
 		depends on ARCH_STI
-		bool "Use StiH415/416 ASC for low-level debug"
+		select DEBUG_STI_UART
 		help
 		  Say Y here if you want kernel low-level debugging support
-		  on StiH415/416 based platforms like B2000, B2020.
-		  It support UART2 and SBC_UART1.
+		  on STiH415/416 based platforms like b2020. which has
+		  default UART wired up to SBC ASC1.
 
 		  If unsure, say N.
 
 	config DEBUG_U300_UART
 		bool "Kernel low-level debugging messages via U300 UART0"
 		depends on ARCH_U300
+		select DEBUG_UART_PL01X
 		help
 		  Say Y here if you want the debug print routines to direct
 		  their output to the uart port on U300 devices.
@@ -548,6 +756,7 @@ choice
 	config DEBUG_VEXPRESS_UART0_CA9
 		bool "Use PL011 UART0 at 0x10009000 (V2P-CA9 core tile)"
 		depends on ARCH_VEXPRESS
+		select DEBUG_UART_PL01X
 		help
 		  This option selects UART0 at 0x10009000. Except for custom models,
 		  this applies only to the V2P-CA9 tile.
@@ -555,6 +764,7 @@ choice
 	config DEBUG_VEXPRESS_UART0_RS1
 		bool "Use PL011 UART0 at 0x1c090000 (RS1 complaint tiles)"
 		depends on ARCH_VEXPRESS
+		select DEBUG_UART_PL01X
 		help
 		  This option selects UART0 at 0x1c090000. This applies to most
 		  of the tiles using the RS1 memory map, including all new A-class
@@ -563,6 +773,7 @@ choice
 	config DEBUG_VEXPRESS_UART0_CRX
 		bool "Use PL011 UART0 at 0xb0090000 (Cortex-R compliant tiles)"
 		depends on ARCH_VEXPRESS && !MMU
+		select DEBUG_UART_PL01X
 		help
 		  This option selects UART0 at 0xb0090000. This is appropriate for
 		  Cortex-R series tiles and SMMs, such as Cortex-R5 and Cortex-R7
@@ -579,7 +790,7 @@ choice
 		depends on !ARCH_MULTIPLATFORM
 		help
 		  Say Y here if your platform doesn't provide a UART option
-		  below. This relies on your platform choosing the right UART
+		  above. This relies on your platform choosing the right UART
 		  definition internally in order for low-level debugging to
 		  work.
 
@@ -610,11 +821,41 @@ choice
 		  For more details about semihosting, please see
 		  chapter 8 of DUI0203I_rvct_developer_guide.pdf from ARM Ltd.
 
+	config DEBUG_LL_UART_8250
+		bool "Kernel low-level debugging via 8250 UART"
+		help
+		  Say Y here if you wish the debug print routes to direct
+		  their output to an 8250 UART.  You can use this option
+		  to provide the parameters for the 8250 UART rather than
+		  selecting one of the platform specific options above if
+		  you know the parameters for the port.
+
+		  This option is preferred over the platform specific
+		  options; the platform specific options are deprecated
+		  and will be soon removed.
+
+	config DEBUG_LL_UART_PL01X
+		bool "Kernel low-level debugging via ARM Ltd PL01x Primecell UART"
+		help
+		  Say Y here if you wish the debug print routes to direct
+		  their output to a PL01x Primecell UART.  You can use
+		  this option to provide the parameters for the UART
+		  rather than selecting one of the platform specific
+		  options above if you know the parameters for the port.
+
+		  This option is preferred over the platform specific
+		  options; the platform specific options are deprecated
+		  and will be soon removed.
+
 endchoice
 
 config DEBUG_EXYNOS_UART
 	bool
 
+config DEBUG_OMAP2PLUS_UART
+	bool
+	depends on ARCH_OMAP2PLUS
+
 config DEBUG_IMX_UART_PORT
 	int "i.MX Debug UART Port Selection" if DEBUG_IMX1_UART || \
 						DEBUG_IMX25_UART || \
@@ -631,140 +872,19 @@ config DEBUG_IMX_UART_PORT
 	  Choose UART port on which kernel low-level debug messages
 	  should be output.
 
-choice
-	prompt "Low-level debug console UART"
-	depends on DEBUG_OMAP2PLUS_UART
-
-	config DEBUG_OMAP2UART1
-		bool "OMAP2/3/4 UART1 (omap2/3 sdp boards and some omap3 boards)"
-		help
-		  This covers at least h4, 2430sdp, 3430sdp, 3630sdp,
-		  omap3 torpedo and 3530 lv som.
-
-	config DEBUG_OMAP2UART2
-		bool "OMAP2/3/4 UART2"
-
-	config DEBUG_OMAP2UART3
-		bool "OMAP2 UART3 (n8x0)"
-
-	config DEBUG_OMAP3UART3
-		bool "OMAP3 UART3 (most omap3 boards)"
-		help
-		  This covers at least cm_t3x, beagle, crane, devkit8000,
-		  igep00x0, ldp, n900, n9(50), pandora, overo, touchbook,
-		  and 3517evm.
-
-	config DEBUG_OMAP4UART3
-		bool "OMAP4/5 UART3 (omap4 blaze, panda, omap5 sevm)"
-
-	config DEBUG_OMAP3UART4
-		bool "OMAP36XX UART4"
-
-	config DEBUG_OMAP4UART4
-		bool "OMAP4/5 UART4"
-
-	config DEBUG_TI81XXUART1
-		bool "TI81XX UART1 (ti8148evm)"
-
-	config DEBUG_TI81XXUART2
-		bool "TI81XX UART2"
-
-	config DEBUG_TI81XXUART3
-		bool "TI81XX UART3 (ti8168evm)"
-
-	config DEBUG_AM33XXUART1
-		bool "AM33XX UART1"
-
-	config DEBUG_ZOOM_UART
-		bool "Zoom2/3 UART"
-endchoice
-
-choice
-	prompt "Low-level debug console UART"
-	depends on DEBUG_ROCKCHIP_UART
-
-	config DEBUG_RK29_UART0
-		bool "RK29 UART0"
-
-	config DEBUG_RK29_UART1
-		bool "RK29 UART1"
-
-	config DEBUG_RK29_UART2
-		bool "RK29 UART2"
-
-	config DEBUG_RK3X_UART0
-		bool "RK3X UART0"
-
-	config DEBUG_RK3X_UART1
-		bool "RK3X UART1"
-
-	config DEBUG_RK3X_UART2
-		bool "RK3X UART2"
-
-	config DEBUG_RK3X_UART3
-		bool "RK3X UART3"
-endchoice
-
-choice
-	prompt "Low-level debug console UART"
-	depends on DEBUG_LL && DEBUG_TEGRA_UART
-
-	config TEGRA_DEBUG_UART_AUTO_ODMDATA
-	bool "Via ODMDATA"
-	help
-	  Automatically determines which UART to use for low-level debug based
-	  on the ODMDATA value. This value is part of the BCT, and is written
-	  to the boot memory device using nvflash, or other flashing tool.
-	  When bits 19:18 are 3, then bits 17:15 indicate which UART to use;
-	  0/1/2/3/4 are UART A/B/C/D/E.
-
-	config TEGRA_DEBUG_UARTA
-		bool "UART A"
-
-	config TEGRA_DEBUG_UARTB
-		bool "UART B"
-
-	config TEGRA_DEBUG_UARTC
-		bool "UART C"
-
-	config TEGRA_DEBUG_UARTD
-		bool "UART D"
-
-	config TEGRA_DEBUG_UARTE
-		bool "UART E"
-
-endchoice
-
-choice
-	prompt "Low-level debug console UART"
-	depends on DEBUG_LL && DEBUG_STI_UART
-
-	config STIH41X_DEBUG_ASC2
-		bool "ASC2 UART"
-		help
-		  Say Y here if you want kernel low-level debugging support
-		  on STiH415/416 based platforms like b2000, which has
-		  default UART wired up to ASC2.
-
-		  If unsure, say N.
-
-	config STIH41X_DEBUG_SBC_ASC1
-		bool "SBC ASC1 UART"
-		help
-		  Say Y here if you want kernel low-level debugging support
-		  on STiH415/416 based platforms like b2020. which has
-		  default UART wired up to SBC ASC1.
-
-		  If unsure, say N.
+config DEBUG_TEGRA_UART
+	bool
+	depends on ARCH_TEGRA
 
-endchoice
+config DEBUG_STI_UART
+	bool
+	depends on ARCH_STI
 
 config DEBUG_LL_INCLUDE
 	string
-	default "debug/bcm2835.S" if DEBUG_BCM2835
-	default "debug/cns3xxx.S" if DEBUG_CNS3XXX
+	default "debug/8250.S" if DEBUG_LL_UART_8250 || DEBUG_UART_8250
+	default "debug/pl01x.S" if DEBUG_LL_UART_PL01X || DEBUG_UART_PL01X
 	default "debug/exynos.S" if DEBUG_EXYNOS_UART
-	default "debug/highbank.S" if DEBUG_HIGHBANK_UART
 	default "debug/icedcc.S" if DEBUG_ICEDCC
 	default "debug/imx.S" if DEBUG_IMX1_UART || \
 				 DEBUG_IMX25_UART || \
@@ -775,38 +895,175 @@ config DEBUG_LL_INCLUDE
 				 DEBUG_IMX53_UART ||\
 				 DEBUG_IMX6Q_UART || \
 				 DEBUG_IMX6SL_UART
-	default "debug/keystone.S" if DEBUG_KEYSTONE_UART0 || \
-				      DEBUG_KEYSTONE_UART1
-	default "debug/mvebu.S" if DEBUG_MVEBU_UART || \
-				   DEBUG_MVEBU_UART_ALTERNATE
-	default "debug/mxs.S" if DEBUG_IMX23_UART || DEBUG_IMX28_UART
-	default "debug/nomadik.S" if DEBUG_NOMADIK_UART
-	default "debug/nspire.S" if 	DEBUG_NSPIRE_CX_UART || \
-					DEBUG_NSPIRE_CLASSIC_UART
+	default "debug/msm.S" if DEBUG_MSM_UART1 || \
+				 DEBUG_MSM_UART2 || \
+				 DEBUG_MSM_UART3 || \
+				 DEBUG_MSM8660_UART || \
+				 DEBUG_MSM8960_UART
 	default "debug/omap2plus.S" if DEBUG_OMAP2PLUS_UART
-	default "debug/picoxcell.S" if DEBUG_PICOXCELL_UART
-	default "debug/pxa.S" if DEBUG_PXA_UART1 || DEBUG_MMP_UART2 || \
-				 DEBUG_MMP_UART3
-	default "debug/rockchip.S" if DEBUG_ROCKCHIP_UART
 	default "debug/sirf.S" if DEBUG_SIRFPRIMA2_UART1 || DEBUG_SIRFMARCO_UART1
-	default "debug/socfpga.S" if DEBUG_SOCFPGA_UART
 	default "debug/sti.S" if DEBUG_STI_UART
-	default "debug/sunxi.S" if DEBUG_SUNXI_UART0 || DEBUG_SUNXI_UART1
 	default "debug/tegra.S" if DEBUG_TEGRA_UART
-	default "debug/u300.S" if DEBUG_U300_UART
 	default "debug/ux500.S" if DEBUG_UX500_UART
-	default "debug/vexpress.S" if DEBUG_VEXPRESS_UART0_DETECT || \
-		DEBUG_VEXPRESS_UART0_CA9 || DEBUG_VEXPRESS_UART0_RS1 || \
-		DEBUG_VEXPRESS_UART0_CRX
+	default "debug/vexpress.S" if DEBUG_VEXPRESS_UART0_DETECT
 	default "debug/vt8500.S" if DEBUG_VT8500_UART0
 	default "debug/zynq.S" if DEBUG_ZYNQ_UART0 || DEBUG_ZYNQ_UART1
 	default "mach/debug-macro.S"
 
+# Compatibility options for PL01x
+config DEBUG_UART_PL01X
+	def_bool ARCH_EP93XX || \
+		ARCH_INTEGRATOR || \
+		ARCH_SPEAR3XX || \
+		ARCH_SPEAR6XX || \
+		ARCH_SPEAR13XX || \
+		ARCH_VERSATILE
+
+# Compatibility options for 8250
+config DEBUG_UART_8250
+	def_bool ARCH_DOVE || ARCH_EBSA110 || \
+		(FOOTBRIDGE && !DEBUG_DC21285_PORT) || \
+		ARCH_GEMINI || ARCH_IOP13XX || ARCH_IOP32X || \
+		ARCH_IOP33X || ARCH_IXP4XX || ARCH_KIRKWOOD || \
+		ARCH_LPC32XX || ARCH_MV78XX0 || ARCH_ORION5X || ARCH_RPC
+
+config DEBUG_UART_PHYS
+	hex "Physical base address of debug UART"
+	default 0x01c20000 if DEBUG_DAVINCI_DMx_UART0
+	default 0x01c28000 if DEBUG_SUNXI_UART0
+	default 0x01c28400 if DEBUG_SUNXI_UART1
+	default 0x01d0c000 if DEBUG_DAVINCI_DA8XX_UART1
+	default 0x01d0d000 if DEBUG_DAVINCI_DA8XX_UART2
+	default 0x02530c00 if DEBUG_KEYSTONE_UART0
+	default 0x02531000 if DEBUG_KEYSTONE_UART1
+	default 0x03010fe0 if ARCH_RPC
+	default 0x08108300 if DEBUG_DAVINCI_TNETV107X_UART1
+	default 0x10009000 if DEBUG_REALVIEW_STD_PORT || DEBUG_CNS3XXX || \
+				DEBUG_VEXPRESS_UART0_CA9
+	default 0x1010c000 if DEBUG_REALVIEW_PB1176_PORT
+	default 0x10124000 if DEBUG_RK3X_UART0
+	default 0x10126000 if DEBUG_RK3X_UART1
+	default 0x101f1000 if ARCH_VERSATILE
+	default 0x101fb000 if DEBUG_NOMADIK_UART
+	default 0x16000000 if ARCH_INTEGRATOR
+	default 0x1c090000 if DEBUG_VEXPRESS_UART0_RS1
+	default 0x20060000 if DEBUG_RK29_UART0
+	default 0x20064000 if DEBUG_RK29_UART1 || DEBUG_RK3X_UART2
+	default 0x20068000 if DEBUG_RK29_UART2 || DEBUG_RK3X_UART3
+	default 0x20201000 if DEBUG_BCM2835
+	default 0x40090000 if ARCH_LPC32XX
+	default 0x40100000 if DEBUG_PXA_UART1
+	default 0x42000000 if ARCH_GEMINI
+	default 0x7c0003f8 if FOOTBRIDGE
+	default 0x80230000 if DEBUG_PICOXCELL_UART
+	default 0x80070000 if DEBUG_IMX23_UART
+	default 0x80074000 if DEBUG_IMX28_UART
+	default 0x808c0000 if ARCH_EP93XX
+	default 0x90020000 if DEBUG_NSPIRE_CLASSIC_UART || DEBUG_NSPIRE_CX_UART
+	default 0xb0090000 if DEBUG_VEXPRESS_UART0_CRX
+	default 0xc0013000 if DEBUG_U300_UART
+	default 0xc8000000 if ARCH_IXP4XX && !CPU_BIG_ENDIAN
+	default 0xc8000003 if ARCH_IXP4XX && CPU_BIG_ENDIAN
+	default 0xd0000000 if ARCH_SPEAR3XX || ARCH_SPEAR6XX
+	default 0xd0012000 if DEBUG_MVEBU_UART
+	default 0xd4017000 if DEBUG_MMP_UART2
+	default 0xd4018000 if DEBUG_MMP_UART3
+	default 0xe0000000 if ARCH_SPEAR13XX
+	default 0xf0000be0 if ARCH_EBSA110
+	default 0xf1012000 if DEBUG_MVEBU_UART_ALTERNATE
+	default 0xf1012000 if ARCH_DOVE || ARCH_KIRKWOOD || ARCH_MV78XX0 || \
+				ARCH_ORION5X
+	default 0xf8b00000 if DEBUG_HI3716_UART
+	default 0xfcb00000 if DEBUG_HI3620_UART
+	default 0xfe800000 if ARCH_IOP32X
+	default 0xffc02000 if DEBUG_SOCFPGA_UART
+	default 0xffd82340 if ARCH_IOP13XX
+	default 0xfff36000 if DEBUG_HIGHBANK_UART
+	default 0xfffff700 if ARCH_IOP33X
+	depends on DEBUG_LL_UART_8250 || DEBUG_LL_UART_PL01X || \
+		DEBUG_UART_8250 || DEBUG_UART_PL01X
+
+config DEBUG_UART_VIRT
+	hex "Virtual base address of debug UART"
+	default 0xe0010fe0 if ARCH_RPC
+	default 0xf0000be0 if ARCH_EBSA110
+	default 0xf0009000 if DEBUG_CNS3XXX
+	default 0xf01fb000 if DEBUG_NOMADIK_UART
+	default 0xf0201000 if DEBUG_BCM2835
+	default 0xf11f1000 if ARCH_VERSATILE
+	default 0xf1600000 if ARCH_INTEGRATOR
+	default 0xf1c28000 if DEBUG_SUNXI_UART0
+	default 0xf1c28400 if DEBUG_SUNXI_UART1
+	default 0xf2100000 if DEBUG_PXA_UART1
+	default 0xf4090000 if ARCH_LPC32XX
+	default 0xf4200000 if ARCH_GEMINI
+	default 0xf8009000 if DEBUG_VEXPRESS_UART0_CA9
+	default 0xf8090000 if DEBUG_VEXPRESS_UART0_RS1
+	default 0xfb009000 if DEBUG_REALVIEW_STD_PORT
+	default 0xfb10c000 if DEBUG_REALVIEW_PB1176_PORT
+	default 0xfd000000 if ARCH_SPEAR3XX || ARCH_SPEAR6XX
+	default 0xfd000000 if ARCH_SPEAR13XX
+	default 0xfd012000 if ARCH_MV78XX0
+	default 0xfde12000 if ARCH_DOVE
+	default 0xfe012000 if ARCH_ORION5X
+	default 0xfe017000 if DEBUG_MMP_UART2
+	default 0xfe018000 if DEBUG_MMP_UART3
+	default 0xfe100000 if DEBUG_IMX23_UART || DEBUG_IMX28_UART
+	default 0xfe230000 if DEBUG_PICOXCELL_UART
+	default 0xfe800000 if ARCH_IOP32X
+	default 0xfeb00000 if DEBUG_HI3620_UART || DEBUG_HI3716_UART
+	default 0xfeb24000 if DEBUG_RK3X_UART0
+	default 0xfeb26000 if DEBUG_RK3X_UART1
+	default 0xfeb30c00 if DEBUG_KEYSTONE_UART0
+	default 0xfeb31000 if DEBUG_KEYSTONE_UART1
+	default 0xfec12000 if DEBUG_MVEBU_UART || DEBUG_MVEBU_UART_ALTERNATE
+	default 0xfed60000 if DEBUG_RK29_UART0
+	default 0xfed64000 if DEBUG_RK29_UART1 || DEBUG_RK3X_UART2
+	default 0xfed68000 if DEBUG_RK29_UART2 || DEBUG_RK3X_UART3
+	default 0xfec02000 if DEBUG_SOCFPGA_UART
+	default 0xfec20000 if DEBUG_DAVINCI_DMx_UART0
+	default 0xfed0c000 if DEBUG_DAVINCI_DA8XX_UART1
+	default 0xfed0d000 if DEBUG_DAVINCI_DA8XX_UART2
+	default 0xfed12000 if ARCH_KIRKWOOD
+	default 0xfedc0000 if ARCH_EP93XX
+	default 0xfee003f8 if FOOTBRIDGE
+	default 0xfee08300 if DEBUG_DAVINCI_TNETV107X_UART1
+	default 0xfee20000 if DEBUG_NSPIRE_CLASSIC_UART || DEBUG_NSPIRE_CX_UART
+	default 0xfef36000 if DEBUG_HIGHBANK_UART
+	default 0xfee82340 if ARCH_IOP13XX
+	default 0xfef00000 if ARCH_IXP4XX && !CPU_BIG_ENDIAN
+	default 0xfef00003 if ARCH_IXP4XX && CPU_BIG_ENDIAN
+	default 0xfefff700 if ARCH_IOP33X
+	default 0xff003000 if DEBUG_U300_UART
+	default DEBUG_UART_PHYS if !MMU
+	depends on DEBUG_LL_UART_8250 || DEBUG_LL_UART_PL01X || \
+		DEBUG_UART_8250 || DEBUG_UART_PL01X
+
+config DEBUG_UART_8250_SHIFT
+	int "Register offset shift for the 8250 debug UART"
+	depends on DEBUG_LL_UART_8250 || DEBUG_UART_8250
+	default 0 if FOOTBRIDGE || ARCH_IOP32X
+	default 2
+
+config DEBUG_UART_8250_WORD
+	bool "Use 32-bit accesses for 8250 UART"
+	depends on DEBUG_LL_UART_8250 || DEBUG_UART_8250
+	depends on DEBUG_UART_8250_SHIFT >= 2
+	default y if DEBUG_PICOXCELL_UART || DEBUG_SOCFPGA_UART || \
+		ARCH_KEYSTONE || \
+		DEBUG_DAVINCI_DMx_UART0 || DEBUG_DAVINCI_DA8XX_UART1 || \
+		DEBUG_DAVINCI_DA8XX_UART2 || DEBUG_DAVINCI_TNETV107X_UART1
+
+config DEBUG_UART_8250_FLOW_CONTROL
+	bool "Enable flow control for 8250 UART"
+	depends on DEBUG_LL_UART_8250 || DEBUG_UART_8250
+	default y if ARCH_EBSA110 || FOOTBRIDGE || ARCH_GEMINI || ARCH_RPC
+
 config DEBUG_UNCOMPRESS
 	bool
-	depends on ARCH_MULTIPLATFORM
+	depends on ARCH_MULTIPLATFORM || ARCH_MSM
 	default y if DEBUG_LL && !DEBUG_OMAP2PLUS_UART && \
-		     !DEBUG_TEGRA_UART
+		     (!DEBUG_TEGRA_UART || !ZBOOT_ROM)
 	help
 	  This option influences the normal decompressor output for
 	  multiplatform kernels.  Normally, multiplatform kernels disable
@@ -820,7 +1077,7 @@ config DEBUG_UNCOMPRESS
 
 config UNCOMPRESS_INCLUDE
 	string
-	default "debug/uncompress.h" if ARCH_MULTIPLATFORM
+	default "debug/uncompress.h" if ARCH_MULTIPLATFORM || ARCH_MSM
 	default "mach/uncompress.h"
 
 config EARLY_PRINTK
diff --git a/arch/arm/Makefile b/arch/arm/Makefile
index 6fd2ceae305a..db50b626be98 100644
--- a/arch/arm/Makefile
+++ b/arch/arm/Makefile
@@ -190,6 +190,7 @@ machine-$(CONFIG_ARCH_S5PV210)		+= s5pv210
 machine-$(CONFIG_ARCH_SA1100)		+= sa1100
 machine-$(CONFIG_ARCH_SHARK)		+= shark
 machine-$(CONFIG_ARCH_SHMOBILE) 	+= shmobile
+machine-$(CONFIG_ARCH_SHMOBILE_MULTI) 	+= shmobile
 machine-$(CONFIG_ARCH_SIRF)		+= prima2
 machine-$(CONFIG_ARCH_SOCFPGA)		+= socfpga
 machine-$(CONFIG_ARCH_STI)		+= sti
@@ -295,10 +296,15 @@ archprepare:
 # Convert bzImage to zImage
 bzImage: zImage
 
-zImage Image xipImage bootpImage uImage: vmlinux
+BOOT_TARGETS	= zImage Image xipImage bootpImage uImage
+INSTALL_TARGETS	= zinstall uinstall install
+
+PHONY += bzImage $(BOOT_TARGETS) $(INSTALL_TARGETS)
+
+$(BOOT_TARGETS): vmlinux
 	$(Q)$(MAKE) $(build)=$(boot) MACHINE=$(MACHINE) $(boot)/$@
 
-zinstall uinstall install: vmlinux
+$(INSTALL_TARGETS):
 	$(Q)$(MAKE) $(build)=$(boot) MACHINE=$(MACHINE) $@
 
 %.dtb: | scripts
diff --git a/arch/arm/boot/Makefile b/arch/arm/boot/Makefile
index 84aa2caf07ed..ec2f8065f955 100644
--- a/arch/arm/boot/Makefile
+++ b/arch/arm/boot/Makefile
@@ -95,24 +95,24 @@ initrd:
 	@test "$(INITRD)" != "" || \
 	(echo You must specify INITRD; exit -1)
 
-install: $(obj)/Image
-	$(CONFIG_SHELL) $(srctree)/$(src)/install.sh $(KERNELRELEASE) \
+install:
+	$(CONFIG_SHELL) $(srctree)/$(src)/install.sh "$(KERNELRELEASE)" \
 	$(obj)/Image System.map "$(INSTALL_PATH)"
 
-zinstall: $(obj)/zImage
-	$(CONFIG_SHELL) $(srctree)/$(src)/install.sh $(KERNELRELEASE) \
+zinstall:
+	$(CONFIG_SHELL) $(srctree)/$(src)/install.sh "$(KERNELRELEASE)" \
 	$(obj)/zImage System.map "$(INSTALL_PATH)"
 
-uinstall: $(obj)/uImage
-	$(CONFIG_SHELL) $(srctree)/$(src)/install.sh $(KERNELRELEASE) \
+uinstall:
+	$(CONFIG_SHELL) $(srctree)/$(src)/install.sh "$(KERNELRELEASE)" \
 	$(obj)/uImage System.map "$(INSTALL_PATH)"
 
 zi:
-	$(CONFIG_SHELL) $(srctree)/$(src)/install.sh $(KERNELRELEASE) \
+	$(CONFIG_SHELL) $(srctree)/$(src)/install.sh "$(KERNELRELEASE)" \
 	$(obj)/zImage System.map "$(INSTALL_PATH)"
 
 i:
-	$(CONFIG_SHELL) $(srctree)/$(src)/install.sh $(KERNELRELEASE) \
+	$(CONFIG_SHELL) $(srctree)/$(src)/install.sh "$(KERNELRELEASE)" \
 	$(obj)/Image System.map "$(INSTALL_PATH)"
 
 subdir-	    := bootp compressed dts
diff --git a/arch/arm/boot/compressed/head-shmobile.S b/arch/arm/boot/compressed/head-shmobile.S
index e2d636336b7c..e7f80928949c 100644
--- a/arch/arm/boot/compressed/head-shmobile.S
+++ b/arch/arm/boot/compressed/head-shmobile.S
@@ -55,12 +55,47 @@ __tmp_stack:
 __continue:
 #endif /* CONFIG_ZBOOT_ROM_MMC || CONFIG_ZBOOT_ROM_SH_MOBILE_SDHI */
 
-	/* Set board ID necessary for boot */
-	ldr	r7, 1f				@ Set machine type register
-	mov	r8, #0				@ pass null pointer as atag
+	adr	r0, dtb_info
+	ldmia	r0, {r1, r3, r4, r5, r7}
+
+	sub	r0, r0, r1		@ calculate the delta offset
+	add	r5, r5, r0		@ _edata
+
+	ldr	lr, [r5, #0]		@ check if valid DTB is present
+	cmp	lr, r3
+	bne	0f
+
+	add	r9, r7, #31		@ rounded up to a multiple
+	bic	r9, r9, #31		@ ... of 32 bytes
+
+	add	r6, r9, r5		@ copy from _edata
+	add	r9, r9, r4		@ to MEMORY_START
+
+1:	ldmdb	r6!, {r0 - r3, r10 - r12, lr}
+	cmp	r6, r5
+	stmdb	r9!, {r0 - r3, r10 - r12, lr}
+	bhi	1b
+
+	/* Success: Zero board ID, pointer to start of memory for atag/dtb */
+	mov	r7, #0
+	mov	r8, r4
 	b	2f
 
-1 :	.long MACH_TYPE
+	.align	2
+dtb_info:
+	.word	dtb_info
+#ifndef __ARMEB__
+	.word	0xedfe0dd0		@ sig is 0xd00dfeed big endian
+#else
+	.word	0xd00dfeed
+#endif
+	.word	MEMORY_START
+	.word	_edata
+	.word	0x4000			@ maximum DTB size
+0:
+	/* Failure: Zero board ID, NULL atag/dtb */
+	mov 	r7, #0
+	mov	r8, #0			@ pass null pointer as atag
 2 :
 
 #endif /* CONFIG_ZBOOT_ROM */
diff --git a/arch/arm/boot/dts/Makefile b/arch/arm/boot/dts/Makefile
index 641b3c9a7028..802720e3e8fd 100644
--- a/arch/arm/boot/dts/Makefile
+++ b/arch/arm/boot/dts/Makefile
@@ -41,25 +41,30 @@ dtb-$(CONFIG_ARCH_AT91)	+= sama5d33ek.dtb
 dtb-$(CONFIG_ARCH_AT91)	+= sama5d34ek.dtb
 dtb-$(CONFIG_ARCH_AT91)	+= sama5d35ek.dtb
 
+dtb-$(CONFIG_ARCH_ATLAS6) += atlas6-evb.dtb
+
 dtb-$(CONFIG_ARCH_BCM2835) += bcm2835-rpi-b.dtb
-dtb-$(CONFIG_ARCH_BCM) += bcm11351-brt.dtb
+dtb-$(CONFIG_ARCH_BCM) += bcm11351-brt.dtb \
+	bcm28155-ap.dtb
 dtb-$(CONFIG_ARCH_DAVINCI) += da850-enbw-cmc.dtb \
 	da850-evm.dtb
 dtb-$(CONFIG_ARCH_DOVE) += dove-cm-a510.dtb \
 	dove-cubox.dtb \
+	dove-d2plug.dtb \
 	dove-dove-db.dtb
 dtb-$(CONFIG_ARCH_EXYNOS) += exynos4210-origen.dtb \
 	exynos4210-smdkv310.dtb \
 	exynos4210-trats.dtb \
 	exynos4210-universal_c210.dtb \
 	exynos4412-odroidx.dtb \
-	exynos4412-smdk4412.dtb \
 	exynos4412-origen.dtb \
+	exynos4412-smdk4412.dtb \
+	exynos4412-trats2.dtb \
 	exynos5250-arndale.dtb \
-	exynos5440-sd5v1.dtb \
 	exynos5250-smdk5250.dtb \
 	exynos5250-snow.dtb \
 	exynos5420-smdk5420.dtb \
+	exynos5440-sd5v1.dtb \
 	exynos5440-ssdk5440.dtb
 dtb-$(CONFIG_ARCH_HIGHBANK) += highbank.dtb \
 	ecx-2000.dtb
@@ -83,12 +88,14 @@ dtb-$(CONFIG_ARCH_KIRKWOOD) += kirkwood-cloudbox.dtb \
 	kirkwood-lschlv2.dtb \
 	kirkwood-lsxhl.dtb \
 	kirkwood-mplcec4.dtb \
+	kirkwood-mv88f6281gtw-ge.dtb \
 	kirkwood-netgear_readynas_duo_v2.dtb \
 	kirkwood-ns2.dtb \
 	kirkwood-ns2lite.dtb \
 	kirkwood-ns2max.dtb \
 	kirkwood-ns2mini.dtb \
 	kirkwood-nsa310.dtb \
+	kirkwood-nsa310a.dtb \
 	kirkwood-sheevaplug.dtb \
 	kirkwood-sheevaplug-esata.dtb \
 	kirkwood-topkick.dtb \
@@ -100,7 +107,9 @@ dtb-$(CONFIG_ARCH_MSM) += msm8660-surf.dtb \
 	msm8960-cdp.dtb
 dtb-$(CONFIG_ARCH_MVEBU) += armada-370-db.dtb \
 	armada-370-mirabox.dtb \
+	armada-370-netgear-rn102.dtb \
 	armada-370-rd.dtb \
+	armada-xp-axpwifiap.dtb \
 	armada-xp-db.dtb \
 	armada-xp-gp.dtb \
 	armada-xp-openblocks-ax3-4.dtb
@@ -112,6 +121,8 @@ dtb-$(CONFIG_ARCH_MXC) += \
 	imx27-pdk.dtb \
 	imx27-phytec-phycore-som.dtb \
 	imx27-phytec-phycore-rdk.dtb \
+	imx27-phytec-phycard-s-som.dtb \
+	imx27-phytec-phycard-s-rdk.dtb \
 	imx31-bug.dtb \
 	imx51-apf51.dtb \
 	imx51-apf51dev.dtb \
@@ -131,6 +142,7 @@ dtb-$(CONFIG_ARCH_MXC) += \
 	imx6q-sabrelite.dtb \
 	imx6q-sabresd.dtb \
 	imx6q-sbc6x.dtb \
+	imx6q-wandboard.dtb \
 	imx6sl-evk.dtb \
 	vf610-twr.dtb
 dtb-$(CONFIG_ARCH_MXS) += imx23-evk.dtb \
@@ -143,7 +155,9 @@ dtb-$(CONFIG_ARCH_MXS) += imx23-evk.dtb \
 	imx28-cfa10037.dtb \
 	imx28-cfa10049.dtb \
 	imx28-cfa10055.dtb \
+	imx28-cfa10056.dtb \
 	imx28-cfa10057.dtb \
+	imx28-cfa10058.dtb \
 	imx28-evk.dtb \
 	imx28-m28evk.dtb \
 	imx28-sps1.dtb \
@@ -171,27 +185,34 @@ dtb-$(CONFIG_ARCH_OMAP2PLUS) += omap2420-h4.dtb \
 	am335x-evm.dtb \
 	am335x-evmsk.dtb \
 	am335x-bone.dtb \
+	am335x-boneblack.dtb \
 	am3517-evm.dtb \
 	am3517_mt_ventoux.dtb \
 	am43x-epos-evm.dtb
 dtb-$(CONFIG_ARCH_ORION5X) += orion5x-lacie-ethernet-disk-mini-v2.dtb
 dtb-$(CONFIG_ARCH_PRIMA2) += prima2-evb.dtb
-dtb-$(CONFIG_ARCH_U8500) += snowball.dtb \
-	hrefprev60.dtb \
-	hrefv60plus.dtb \
-	ccu8540.dtb \
-	ccu9540.dtb
+dtb-$(CONFIG_ARCH_U8500) += ste-snowball.dtb \
+	ste-hrefprev60.dtb \
+	ste-hrefv60plus.dtb \
+	ste-ccu8540.dtb \
+	ste-ccu9540.dtb
 dtb-$(CONFIG_ARCH_S3C24XX) += s3c2416-smdk2416.dtb
 dtb-$(CONFIG_ARCH_SHMOBILE) += emev2-kzm9d.dtb \
+	emev2-kzm9d-reference.dtb \
 	r8a7740-armadillo800eva.dtb \
 	r8a7778-bockw.dtb \
+	r8a7778-bockw-reference.dtb \
 	r8a7740-armadillo800eva-reference.dtb \
+	r8a7779-marzen.dtb \
 	r8a7779-marzen-reference.dtb \
 	r8a7790-lager.dtb \
+	r8a7790-lager-reference.dtb \
 	sh73a0-kzm9g.dtb \
 	sh73a0-kzm9g-reference.dtb \
 	r8a73a4-ape6evm.dtb \
+	r8a73a4-ape6evm-reference.dtb \
 	sh7372-mackerel.dtb
+dtb-$(CONFIG_ARCH_SHMOBILE_MULTI) += emev2-kzm9d-reference.dtb
 dtb-$(CONFIG_ARCH_SOCFPGA) += socfpga_cyclone5.dtb \
 	socfpga_vt.dtb
 dtb-$(CONFIG_ARCH_SPEAR13XX) += spear1310-evb.dtb \
@@ -206,11 +227,15 @@ dtb-$(CONFIG_ARCH_STI)+= stih415-b2000.dtb \
 	stih415-b2020.dtb \
 	stih416-b2020.dtb
 dtb-$(CONFIG_ARCH_SUNXI) += \
+	sun4i-a10-a1000.dtb \
 	sun4i-a10-cubieboard.dtb \
 	sun4i-a10-mini-xplus.dtb \
 	sun4i-a10-hackberry.dtb \
 	sun5i-a10s-olinuxino-micro.dtb \
-	sun5i-a13-olinuxino.dtb
+	sun5i-a13-olinuxino.dtb \
+	sun6i-a31-colombus.dtb \
+	sun7i-a20-cubieboard2.dtb \
+	sun7i-a20-olinuxino-micro.dtb
 dtb-$(CONFIG_ARCH_TEGRA) += tegra20-harmony.dtb \
 	tegra20-iris-512.dtb \
 	tegra20-medcom-wide.dtb \
@@ -224,8 +249,7 @@ dtb-$(CONFIG_ARCH_TEGRA) += tegra20-harmony.dtb \
 	tegra30-beaver.dtb \
 	tegra30-cardhu-a02.dtb \
 	tegra30-cardhu-a04.dtb \
-	tegra114-dalmore.dtb \
-	tegra114-pluto.dtb
+	tegra114-dalmore.dtb
 dtb-$(CONFIG_ARCH_VERSATILE) += versatile-ab.dtb \
 	versatile-pb.dtb
 dtb-$(CONFIG_ARCH_U300) += ste-u300.dtb
diff --git a/arch/arm/boot/dts/am335x-bone-common.dtsi b/arch/arm/boot/dts/am335x-bone-common.dtsi
new file mode 100644
index 000000000000..2f66deda9f5c
--- /dev/null
+++ b/arch/arm/boot/dts/am335x-bone-common.dtsi
@@ -0,0 +1,262 @@
+/*
+ * Copyright (C) 2012 Texas Instruments Incorporated - http://www.ti.com/
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/ {
+	model = "TI AM335x BeagleBone";
+	compatible = "ti,am335x-bone", "ti,am33xx";
+
+	cpus {
+		cpu@0 {
+			cpu0-supply = <&dcdc2_reg>;
+		};
+	};
+
+	memory {
+		device_type = "memory";
+		reg = <0x80000000 0x10000000>; /* 256 MB */
+	};
+
+	am33xx_pinmux: pinmux@44e10800 {
+		pinctrl-names = "default";
+		pinctrl-0 = <&clkout2_pin>;
+
+		user_leds_s0: user_leds_s0 {
+			pinctrl-single,pins = <
+				0x54 (PIN_OUTPUT_PULLDOWN | MUX_MODE7)	/* gpmc_a5.gpio1_21 */
+				0x58 (PIN_OUTPUT_PULLUP | MUX_MODE7)	/* gpmc_a6.gpio1_22 */
+				0x5c (PIN_OUTPUT_PULLDOWN | MUX_MODE7)	/* gpmc_a7.gpio1_23 */
+				0x60 (PIN_OUTPUT_PULLUP | MUX_MODE7)	/* gpmc_a8.gpio1_24 */
+			>;
+		};
+
+		i2c0_pins: pinmux_i2c0_pins {
+			pinctrl-single,pins = <
+				0x188 (PIN_INPUT_PULLUP | MUX_MODE0)	/* i2c0_sda.i2c0_sda */
+				0x18c (PIN_INPUT_PULLUP | MUX_MODE0)	/* i2c0_scl.i2c0_scl */
+			>;
+		};
+
+		uart0_pins: pinmux_uart0_pins {
+			pinctrl-single,pins = <
+				0x170 (PIN_INPUT_PULLUP | MUX_MODE0)	/* uart0_rxd.uart0_rxd */
+				0x174 (PIN_OUTPUT_PULLDOWN | MUX_MODE0)	/* uart0_txd.uart0_txd */
+			>;
+		};
+
+		clkout2_pin: pinmux_clkout2_pin {
+			pinctrl-single,pins = <
+				0x1b4 (PIN_OUTPUT_PULLDOWN | MUX_MODE3)	/* xdma_event_intr1.clkout2 */
+			>;
+		};
+
+		cpsw_default: cpsw_default {
+			pinctrl-single,pins = <
+				/* Slave 1 */
+				0x110 (PIN_INPUT_PULLUP | MUX_MODE0)	/* mii1_rxerr.mii1_rxerr */
+				0x114 (PIN_OUTPUT_PULLDOWN | MUX_MODE0)	/* mii1_txen.mii1_txen */
+				0x118 (PIN_INPUT_PULLUP | MUX_MODE0)	/* mii1_rxdv.mii1_rxdv */
+				0x11c (PIN_OUTPUT_PULLDOWN | MUX_MODE0)	/* mii1_txd3.mii1_txd3 */
+				0x120 (PIN_OUTPUT_PULLDOWN | MUX_MODE0)	/* mii1_txd2.mii1_txd2 */
+				0x124 (PIN_OUTPUT_PULLDOWN | MUX_MODE0)	/* mii1_txd1.mii1_txd1 */
+				0x128 (PIN_OUTPUT_PULLDOWN | MUX_MODE0)	/* mii1_txd0.mii1_txd0 */
+				0x12c (PIN_INPUT_PULLUP | MUX_MODE0)	/* mii1_txclk.mii1_txclk */
+				0x130 (PIN_INPUT_PULLUP | MUX_MODE0)	/* mii1_rxclk.mii1_rxclk */
+				0x134 (PIN_INPUT_PULLUP | MUX_MODE0)	/* mii1_rxd3.mii1_rxd3 */
+				0x138 (PIN_INPUT_PULLUP | MUX_MODE0)	/* mii1_rxd2.mii1_rxd2 */
+				0x13c (PIN_INPUT_PULLUP | MUX_MODE0)	/* mii1_rxd1.mii1_rxd1 */
+				0x140 (PIN_INPUT_PULLUP | MUX_MODE0)	/* mii1_rxd0.mii1_rxd0 */
+			>;
+		};
+
+		cpsw_sleep: cpsw_sleep {
+			pinctrl-single,pins = <
+				/* Slave 1 reset value */
+				0x110 (PIN_INPUT_PULLDOWN | MUX_MODE7)
+				0x114 (PIN_INPUT_PULLDOWN | MUX_MODE7)
+				0x118 (PIN_INPUT_PULLDOWN | MUX_MODE7)
+				0x11c (PIN_INPUT_PULLDOWN | MUX_MODE7)
+				0x120 (PIN_INPUT_PULLDOWN | MUX_MODE7)
+				0x124 (PIN_INPUT_PULLDOWN | MUX_MODE7)
+				0x128 (PIN_INPUT_PULLDOWN | MUX_MODE7)
+				0x12c (PIN_INPUT_PULLDOWN | MUX_MODE7)
+				0x130 (PIN_INPUT_PULLDOWN | MUX_MODE7)
+				0x134 (PIN_INPUT_PULLDOWN | MUX_MODE7)
+				0x138 (PIN_INPUT_PULLDOWN | MUX_MODE7)
+				0x13c (PIN_INPUT_PULLDOWN | MUX_MODE7)
+				0x140 (PIN_INPUT_PULLDOWN | MUX_MODE7)
+			>;
+		};
+
+		davinci_mdio_default: davinci_mdio_default {
+			pinctrl-single,pins = <
+				/* MDIO */
+				0x148 (PIN_INPUT_PULLUP | SLEWCTRL_FAST | MUX_MODE0)	/* mdio_data.mdio_data */
+				0x14c (PIN_OUTPUT_PULLUP | MUX_MODE0)			/* mdio_clk.mdio_clk */
+			>;
+		};
+
+		davinci_mdio_sleep: davinci_mdio_sleep {
+			pinctrl-single,pins = <
+				/* MDIO reset value */
+				0x148 (PIN_INPUT_PULLDOWN | MUX_MODE7)
+				0x14c (PIN_INPUT_PULLDOWN | MUX_MODE7)
+			>;
+		};
+	};
+
+	ocp {
+		uart0: serial@44e09000 {
+			pinctrl-names = "default";
+			pinctrl-0 = <&uart0_pins>;
+
+			status = "okay";
+		};
+
+		musb: usb@47400000 {
+			status = "okay";
+
+			control@44e10000 {
+				status = "okay";
+			};
+
+			usb-phy@47401300 {
+				status = "okay";
+			};
+
+			usb-phy@47401b00 {
+				status = "okay";
+			};
+
+			usb@47401000 {
+				status = "okay";
+			};
+
+			usb@47401800 {
+				status = "okay";
+				dr_mode = "host";
+			};
+
+			dma-controller@07402000  {
+				status = "okay";
+			};
+		};
+
+		i2c0: i2c@44e0b000 {
+			pinctrl-names = "default";
+			pinctrl-0 = <&i2c0_pins>;
+
+			status = "okay";
+			clock-frequency = <400000>;
+
+			tps: tps@24 {
+				reg = <0x24>;
+			};
+
+		};
+	};
+
+	leds {
+		pinctrl-names = "default";
+		pinctrl-0 = <&user_leds_s0>;
+
+		compatible = "gpio-leds";
+
+		led@2 {
+			label = "beaglebone:green:heartbeat";
+			gpios = <&gpio1 21 GPIO_ACTIVE_HIGH>;
+			linux,default-trigger = "heartbeat";
+			default-state = "off";
+		};
+
+		led@3 {
+			label = "beaglebone:green:mmc0";
+			gpios = <&gpio1 22 GPIO_ACTIVE_HIGH>;
+			linux,default-trigger = "mmc0";
+			default-state = "off";
+		};
+
+		led@4 {
+			label = "beaglebone:green:usr2";
+			gpios = <&gpio1 23 GPIO_ACTIVE_HIGH>;
+			default-state = "off";
+		};
+
+		led@5 {
+			label = "beaglebone:green:usr3";
+			gpios = <&gpio1 24 GPIO_ACTIVE_HIGH>;
+			default-state = "off";
+		};
+	};
+};
+
+/include/ "tps65217.dtsi"
+
+&tps {
+	regulators {
+		dcdc1_reg: regulator@0 {
+			regulator-always-on;
+		};
+
+		dcdc2_reg: regulator@1 {
+			/* VDD_MPU voltage limits 0.95V - 1.26V with +/-4% tolerance */
+			regulator-name = "vdd_mpu";
+			regulator-min-microvolt = <925000>;
+			regulator-max-microvolt = <1325000>;
+			regulator-boot-on;
+			regulator-always-on;
+		};
+
+		dcdc3_reg: regulator@2 {
+			/* VDD_CORE voltage limits 0.95V - 1.1V with +/-4% tolerance */
+			regulator-name = "vdd_core";
+			regulator-min-microvolt = <925000>;
+			regulator-max-microvolt = <1150000>;
+			regulator-boot-on;
+			regulator-always-on;
+		};
+
+		ldo1_reg: regulator@3 {
+			regulator-always-on;
+		};
+
+		ldo2_reg: regulator@4 {
+			regulator-always-on;
+		};
+
+		ldo3_reg: regulator@5 {
+			regulator-always-on;
+		};
+
+		ldo4_reg: regulator@6 {
+			regulator-always-on;
+		};
+	};
+};
+
+&cpsw_emac0 {
+	phy_id = <&davinci_mdio>, <0>;
+	phy-mode = "mii";
+};
+
+&cpsw_emac1 {
+	phy_id = <&davinci_mdio>, <1>;
+	phy-mode = "mii";
+};
+
+&mac {
+	pinctrl-names = "default", "sleep";
+	pinctrl-0 = <&cpsw_default>;
+	pinctrl-1 = <&cpsw_sleep>;
+
+};
+
+&davinci_mdio {
+	pinctrl-names = "default", "sleep";
+	pinctrl-0 = <&davinci_mdio_default>;
+	pinctrl-1 = <&davinci_mdio_sleep>;
+};
diff --git a/arch/arm/boot/dts/am335x-bone.dts b/arch/arm/boot/dts/am335x-bone.dts
index 444b4ede0d60..7993c489982c 100644
--- a/arch/arm/boot/dts/am335x-bone.dts
+++ b/arch/arm/boot/dts/am335x-bone.dts
@@ -8,229 +8,4 @@
 /dts-v1/;
 
 #include "am33xx.dtsi"
-
-/ {
-	model = "TI AM335x BeagleBone";
-	compatible = "ti,am335x-bone", "ti,am33xx";
-
-	cpus {
-		cpu@0 {
-			cpu0-supply = <&dcdc2_reg>;
-		};
-	};
-
-	memory {
-		device_type = "memory";
-		reg = <0x80000000 0x10000000>; /* 256 MB */
-	};
-
-	am33xx_pinmux: pinmux@44e10800 {
-		pinctrl-names = "default";
-		pinctrl-0 = <&clkout2_pin>;
-
-		user_leds_s0: user_leds_s0 {
-			pinctrl-single,pins = <
-				0x54 (PIN_OUTPUT_PULLDOWN | MUX_MODE7)	/* gpmc_a5.gpio1_21 */
-				0x58 (PIN_OUTPUT_PULLUP | MUX_MODE7)	/* gpmc_a6.gpio1_22 */
-				0x5c (PIN_OUTPUT_PULLDOWN | MUX_MODE7)	/* gpmc_a7.gpio1_23 */
-				0x60 (PIN_OUTPUT_PULLUP | MUX_MODE7)	/* gpmc_a8.gpio1_24 */
-			>;
-		};
-
-		i2c0_pins: pinmux_i2c0_pins {
-			pinctrl-single,pins = <
-				0x188 (PIN_INPUT_PULLUP | MUX_MODE0)	/* i2c0_sda.i2c0_sda */
-				0x18c (PIN_INPUT_PULLUP | MUX_MODE0)	/* i2c0_scl.i2c0_scl */
-			>;
-		};
-
-		uart0_pins: pinmux_uart0_pins {
-			pinctrl-single,pins = <
-				0x170 (PIN_INPUT_PULLUP | MUX_MODE0)	/* uart0_rxd.uart0_rxd */
-				0x174 (PIN_OUTPUT_PULLDOWN | MUX_MODE0)	/* uart0_txd.uart0_txd */
-			>;
-		};
-
-		clkout2_pin: pinmux_clkout2_pin {
-			pinctrl-single,pins = <
-				0x1b4 (PIN_OUTPUT_PULLDOWN | MUX_MODE3)	/* xdma_event_intr1.clkout2 */
-			>;
-		};
-
-		cpsw_default: cpsw_default {
-			pinctrl-single,pins = <
-				/* Slave 1 */
-				0x110 (PIN_INPUT_PULLUP | MUX_MODE0)	/* mii1_rxerr.mii1_rxerr */
-				0x114 (PIN_OUTPUT_PULLDOWN | MUX_MODE0)	/* mii1_txen.mii1_txen */
-				0x118 (PIN_INPUT_PULLUP | MUX_MODE0)	/* mii1_rxdv.mii1_rxdv */
-				0x11c (PIN_OUTPUT_PULLDOWN | MUX_MODE0)	/* mii1_txd3.mii1_txd3 */
-				0x120 (PIN_OUTPUT_PULLDOWN | MUX_MODE0)	/* mii1_txd2.mii1_txd2 */
-				0x124 (PIN_OUTPUT_PULLDOWN | MUX_MODE0)	/* mii1_txd1.mii1_txd1 */
-				0x128 (PIN_OUTPUT_PULLDOWN | MUX_MODE0)	/* mii1_txd0.mii1_txd0 */
-				0x12c (PIN_INPUT_PULLUP | MUX_MODE0)	/* mii1_txclk.mii1_txclk */
-				0x130 (PIN_INPUT_PULLUP | MUX_MODE0)	/* mii1_rxclk.mii1_rxclk */
-				0x134 (PIN_INPUT_PULLUP | MUX_MODE0)	/* mii1_rxd3.mii1_rxd3 */
-				0x138 (PIN_INPUT_PULLUP | MUX_MODE0)	/* mii1_rxd2.mii1_rxd2 */
-				0x13c (PIN_INPUT_PULLUP | MUX_MODE0)	/* mii1_rxd1.mii1_rxd1 */
-				0x140 (PIN_INPUT_PULLUP | MUX_MODE0)	/* mii1_rxd0.mii1_rxd0 */
-			>;
-		};
-
-		cpsw_sleep: cpsw_sleep {
-			pinctrl-single,pins = <
-				/* Slave 1 reset value */
-				0x110 (PIN_INPUT_PULLDOWN | MUX_MODE7)
-				0x114 (PIN_INPUT_PULLDOWN | MUX_MODE7)
-				0x118 (PIN_INPUT_PULLDOWN | MUX_MODE7)
-				0x11c (PIN_INPUT_PULLDOWN | MUX_MODE7)
-				0x120 (PIN_INPUT_PULLDOWN | MUX_MODE7)
-				0x124 (PIN_INPUT_PULLDOWN | MUX_MODE7)
-				0x128 (PIN_INPUT_PULLDOWN | MUX_MODE7)
-				0x12c (PIN_INPUT_PULLDOWN | MUX_MODE7)
-				0x130 (PIN_INPUT_PULLDOWN | MUX_MODE7)
-				0x134 (PIN_INPUT_PULLDOWN | MUX_MODE7)
-				0x138 (PIN_INPUT_PULLDOWN | MUX_MODE7)
-				0x13c (PIN_INPUT_PULLDOWN | MUX_MODE7)
-				0x140 (PIN_INPUT_PULLDOWN | MUX_MODE7)
-			>;
-		};
-
-		davinci_mdio_default: davinci_mdio_default {
-			pinctrl-single,pins = <
-				/* MDIO */
-				0x148 (PIN_INPUT_PULLUP | SLEWCTRL_FAST | MUX_MODE0)	/* mdio_data.mdio_data */
-				0x14c (PIN_OUTPUT_PULLUP | MUX_MODE0)			/* mdio_clk.mdio_clk */
-			>;
-		};
-
-		davinci_mdio_sleep: davinci_mdio_sleep {
-			pinctrl-single,pins = <
-				/* MDIO reset value */
-				0x148 (PIN_INPUT_PULLDOWN | MUX_MODE7)
-				0x14c (PIN_INPUT_PULLDOWN | MUX_MODE7)
-			>;
-		};
-	};
-
-	ocp {
-		uart0: serial@44e09000 {
-			pinctrl-names = "default";
-			pinctrl-0 = <&uart0_pins>;
-
-			status = "okay";
-		};
-
-		i2c0: i2c@44e0b000 {
-			pinctrl-names = "default";
-			pinctrl-0 = <&i2c0_pins>;
-
-			status = "okay";
-			clock-frequency = <400000>;
-
-			tps: tps@24 {
-				reg = <0x24>;
-			};
-
-		};
-	};
-
-	leds {
-		pinctrl-names = "default";
-		pinctrl-0 = <&user_leds_s0>;
-
-		compatible = "gpio-leds";
-
-		led@2 {
-			label = "beaglebone:green:heartbeat";
-			gpios = <&gpio1 21 GPIO_ACTIVE_HIGH>;
-			linux,default-trigger = "heartbeat";
-			default-state = "off";
-		};
-
-		led@3 {
-			label = "beaglebone:green:mmc0";
-			gpios = <&gpio1 22 GPIO_ACTIVE_HIGH>;
-			linux,default-trigger = "mmc0";
-			default-state = "off";
-		};
-
-		led@4 {
-			label = "beaglebone:green:usr2";
-			gpios = <&gpio1 23 GPIO_ACTIVE_HIGH>;
-			default-state = "off";
-		};
-
-		led@5 {
-			label = "beaglebone:green:usr3";
-			gpios = <&gpio1 24 GPIO_ACTIVE_HIGH>;
-			default-state = "off";
-		};
-	};
-};
-
-/include/ "tps65217.dtsi"
-
-&tps {
-	regulators {
-		dcdc1_reg: regulator@0 {
-			regulator-always-on;
-		};
-
-		dcdc2_reg: regulator@1 {
-			/* VDD_MPU voltage limits 0.95V - 1.26V with +/-4% tolerance */
-			regulator-name = "vdd_mpu";
-			regulator-min-microvolt = <925000>;
-			regulator-max-microvolt = <1325000>;
-			regulator-boot-on;
-			regulator-always-on;
-		};
-
-		dcdc3_reg: regulator@2 {
-			/* VDD_CORE voltage limits 0.95V - 1.1V with +/-4% tolerance */
-			regulator-name = "vdd_core";
-			regulator-min-microvolt = <925000>;
-			regulator-max-microvolt = <1150000>;
-			regulator-boot-on;
-			regulator-always-on;
-		};
-
-		ldo1_reg: regulator@3 {
-			regulator-always-on;
-		};
-
-		ldo2_reg: regulator@4 {
-			regulator-always-on;
-		};
-
-		ldo3_reg: regulator@5 {
-			regulator-always-on;
-		};
-
-		ldo4_reg: regulator@6 {
-			regulator-always-on;
-		};
-	};
-};
-
-&cpsw_emac0 {
-	phy_id = <&davinci_mdio>, <0>;
-	phy-mode = "mii";
-};
-
-&cpsw_emac1 {
-	phy_id = <&davinci_mdio>, <1>;
-	phy-mode = "mii";
-};
-
-&mac {
-	pinctrl-names = "default", "sleep";
-	pinctrl-0 = <&cpsw_default>;
-	pinctrl-1 = <&cpsw_sleep>;
-
-};
-
-&davinci_mdio {
-	pinctrl-names = "default", "sleep";
-	pinctrl-0 = <&davinci_mdio_default>;
-	pinctrl-1 = <&davinci_mdio_sleep>;
-};
+#include "am335x-bone-common.dtsi"
diff --git a/arch/arm/boot/dts/am335x-boneblack.dts b/arch/arm/boot/dts/am335x-boneblack.dts
new file mode 100644
index 000000000000..197cadf72d2c
--- /dev/null
+++ b/arch/arm/boot/dts/am335x-boneblack.dts
@@ -0,0 +1,17 @@
+/*
+ * Copyright (C) 2012 Texas Instruments Incorporated - http://www.ti.com/
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+/dts-v1/;
+
+#include "am33xx.dtsi"
+#include "am335x-bone-common.dtsi"
+
+&ldo3_reg {
+	regulator-min-microvolt = <1800000>;
+	regulator-max-microvolt = <1800000>;
+	regulator-always-on;
+};
diff --git a/arch/arm/boot/dts/am335x-evm.dts b/arch/arm/boot/dts/am335x-evm.dts
index 3aee1a43782d..e8ec8756e498 100644
--- a/arch/arm/boot/dts/am335x-evm.dts
+++ b/arch/arm/boot/dts/am335x-evm.dts
@@ -171,6 +171,35 @@
 			};
 		};
 
+		musb: usb@47400000 {
+			status = "okay";
+
+			control@44e10000 {
+				status = "okay";
+			};
+
+			usb-phy@47401300 {
+				status = "okay";
+			};
+
+			usb-phy@47401b00 {
+				status = "okay";
+			};
+
+			usb@47401000 {
+				status = "okay";
+			};
+
+			usb@47401800 {
+				status = "okay";
+				dr_mode = "host";
+			};
+
+			dma-controller@07402000  {
+				status = "okay";
+			};
+		};
+
 		i2c1: i2c@4802a000 {
 			pinctrl-names = "default";
 			pinctrl-0 = <&i2c1_pins>;
diff --git a/arch/arm/boot/dts/am335x-evmsk.dts b/arch/arm/boot/dts/am335x-evmsk.dts
index 0c8ad173d2b0..4f339fa91c57 100644
--- a/arch/arm/boot/dts/am335x-evmsk.dts
+++ b/arch/arm/boot/dts/am335x-evmsk.dts
@@ -14,6 +14,7 @@
 /dts-v1/;
 
 #include "am33xx.dtsi"
+#include <dt-bindings/pwm/pwm.h>
 
 / {
 	model = "TI AM335x EVM-SK";
@@ -207,6 +208,22 @@
 			};
 		};
 
+		musb: usb@47400000 {
+			status = "okay";
+
+			control@44e10000 {
+				status = "okay";
+			};
+
+			usb-phy@47401300 {
+				status = "okay";
+			};
+
+			usb@47401000 {
+				status = "okay";
+			};
+		};
+
 		epwmss2: epwmss@48304000 {
 			status = "okay";
 
@@ -298,7 +315,7 @@
 
 	backlight {
 		compatible = "pwm-backlight";
-		pwms = <&ecap2 0 50000 1>;
+		pwms = <&ecap2 0 50000 PWM_POLARITY_INVERTED>;
 		brightness-levels = <0 58 61 66 75 90 125 170 255>;
 		default-brightness-level = <8>;
 	};
diff --git a/arch/arm/boot/dts/am33xx.dtsi b/arch/arm/boot/dts/am33xx.dtsi
index 38b446ba1ce1..f9c5da9c7fe1 100644
--- a/arch/arm/boot/dts/am33xx.dtsi
+++ b/arch/arm/boot/dts/am33xx.dtsi
@@ -26,6 +26,10 @@
 		serial5 = &uart5;
 		d_can0 = &dcan0;
 		d_can1 = &dcan1;
+		usb0 = &usb0;
+		usb1 = &usb1;
+		phy0 = &usb0_phy;
+		phy1 = &usb1_phy;
 	};
 
 	cpus {
@@ -333,21 +337,132 @@
 			status = "disabled";
 		};
 
-		usb@47400000 {
-			compatible = "ti,musb-am33xx";
-			reg = <0x47400000 0x1000	/* usbss */
-			       0x47401000 0x800		/* musb instance 0 */
-			       0x47401800 0x800>;	/* musb instance 1 */
-			interrupts = <17		/* usbss */
-				      18		/* musb instance 0 */
-				      19>;		/* musb instance 1 */
-			multipoint = <1>;
-			num-eps = <16>;
-			ram-bits = <12>;
-			port0-mode = <3>;
-			port1-mode = <3>;
-			power = <250>;
+		usb: usb@47400000 {
+			compatible = "ti,am33xx-usb";
+			reg = <0x47400000 0x1000>;
+			ranges;
+			#address-cells = <1>;
+			#size-cells = <1>;
 			ti,hwmods = "usb_otg_hs";
+			status = "disabled";
+
+			ctrl_mod: control@44e10000 {
+				compatible = "ti,am335x-usb-ctrl-module";
+				reg = <0x44e10620 0x10
+					0x44e10648 0x4>;
+				reg-names = "phy_ctrl", "wakeup";
+				status = "disabled";
+			};
+
+			usb0_phy: usb-phy@47401300 {
+				compatible = "ti,am335x-usb-phy";
+				reg = <0x47401300 0x100>;
+				reg-names = "phy";
+				status = "disabled";
+				ti,ctrl_mod = <&ctrl_mod>;
+			};
+
+			usb0: usb@47401000 {
+				compatible = "ti,musb-am33xx";
+				status = "disabled";
+				reg = <0x47401400 0x400
+					0x47401000 0x200>;
+				reg-names = "mc", "control";
+
+				interrupts = <18>;
+				interrupt-names = "mc";
+				dr_mode = "otg";
+				mentor,multipoint = <1>;
+				mentor,num-eps = <16>;
+				mentor,ram-bits = <12>;
+				mentor,power = <500>;
+				phys = <&usb0_phy>;
+
+				dmas = <&cppi41dma  0 0 &cppi41dma  1 0
+					&cppi41dma  2 0 &cppi41dma  3 0
+					&cppi41dma  4 0 &cppi41dma  5 0
+					&cppi41dma  6 0 &cppi41dma  7 0
+					&cppi41dma  8 0 &cppi41dma  9 0
+					&cppi41dma 10 0 &cppi41dma 11 0
+					&cppi41dma 12 0 &cppi41dma 13 0
+					&cppi41dma 14 0 &cppi41dma  0 1
+					&cppi41dma  1 1 &cppi41dma  2 1
+					&cppi41dma  3 1 &cppi41dma  4 1
+					&cppi41dma  5 1 &cppi41dma  6 1
+					&cppi41dma  7 1 &cppi41dma  8 1
+					&cppi41dma  9 1 &cppi41dma 10 1
+					&cppi41dma 11 1 &cppi41dma 12 1
+					&cppi41dma 13 1 &cppi41dma 14 1>;
+				dma-names =
+					"rx1", "rx2", "rx3", "rx4", "rx5", "rx6", "rx7",
+					"rx8", "rx9", "rx10", "rx11", "rx12", "rx13",
+					"rx14", "rx15",
+					"tx1", "tx2", "tx3", "tx4", "tx5", "tx6", "tx7",
+					"tx8", "tx9", "tx10", "tx11", "tx12", "tx13",
+					"tx14", "tx15";
+			};
+
+			usb1_phy: usb-phy@47401b00 {
+				compatible = "ti,am335x-usb-phy";
+				reg = <0x47401b00 0x100>;
+				reg-names = "phy";
+				status = "disabled";
+				ti,ctrl_mod = <&ctrl_mod>;
+			};
+
+			usb1: usb@47401800 {
+				compatible = "ti,musb-am33xx";
+				status = "disabled";
+				reg = <0x47401c00 0x400
+					0x47401800 0x200>;
+				reg-names = "mc", "control";
+				interrupts = <19>;
+				interrupt-names = "mc";
+				dr_mode = "otg";
+				mentor,multipoint = <1>;
+				mentor,num-eps = <16>;
+				mentor,ram-bits = <12>;
+				mentor,power = <500>;
+				phys = <&usb1_phy>;
+
+				dmas = <&cppi41dma 15 0 &cppi41dma 16 0
+					&cppi41dma 17 0 &cppi41dma 18 0
+					&cppi41dma 19 0 &cppi41dma 20 0
+					&cppi41dma 21 0 &cppi41dma 22 0
+					&cppi41dma 23 0 &cppi41dma 24 0
+					&cppi41dma 25 0 &cppi41dma 26 0
+					&cppi41dma 27 0 &cppi41dma 28 0
+					&cppi41dma 29 0 &cppi41dma 15 1
+					&cppi41dma 16 1 &cppi41dma 17 1
+					&cppi41dma 18 1 &cppi41dma 19 1
+					&cppi41dma 20 1 &cppi41dma 21 1
+					&cppi41dma 22 1 &cppi41dma 23 1
+					&cppi41dma 24 1 &cppi41dma 25 1
+					&cppi41dma 26 1 &cppi41dma 27 1
+					&cppi41dma 28 1 &cppi41dma 29 1>;
+				dma-names =
+					"rx1", "rx2", "rx3", "rx4", "rx5", "rx6", "rx7",
+					"rx8", "rx9", "rx10", "rx11", "rx12", "rx13",
+					"rx14", "rx15",
+					"tx1", "tx2", "tx3", "tx4", "tx5", "tx6", "tx7",
+					"tx8", "tx9", "tx10", "tx11", "tx12", "tx13",
+					"tx14", "tx15";
+			};
+
+			cppi41dma: dma-controller@07402000 {
+				compatible = "ti,am3359-cppi41";
+				reg =  <0x47400000 0x1000
+					0x47402000 0x1000
+					0x47403000 0x1000
+					0x47404000 0x4000>;
+				reg-names = "glue", "controller", "scheduler", "queuemgr";
+				interrupts = <17>;
+				interrupt-names = "glue";
+				#dma-cells = <2>;
+				#dma-channels = <30>;
+				#dma-requests = <256>;
+				status = "disabled";
+			};
 		};
 
 		epwmss0: epwmss@48300000 {
diff --git a/arch/arm/boot/dts/armada-370-db.dts b/arch/arm/boot/dts/armada-370-db.dts
index beee1699d49e..90ce29dbe119 100644
--- a/arch/arm/boot/dts/armada-370-db.dts
+++ b/arch/arm/boot/dts/armada-370-db.dts
@@ -14,7 +14,7 @@
  */
 
 /dts-v1/;
-/include/ "armada-370.dtsi"
+#include "armada-370.dtsi"
 
 / {
 	model = "Marvell Armada 370 Evaluation Board";
@@ -30,6 +30,9 @@
 	};
 
 	soc {
+		ranges = <MBUS_ID(0xf0, 0x01) 0 0xd0000000 0x100000
+			  MBUS_ID(0x01, 0xe0) 0 0xfff00000 0x100000>;
+
 		internal-regs {
 			serial@12000 {
 				clock-frequency = <200000000>;
diff --git a/arch/arm/boot/dts/armada-370-mirabox.dts b/arch/arm/boot/dts/armada-370-mirabox.dts
index 45b107763e3b..2471d9da767b 100644
--- a/arch/arm/boot/dts/armada-370-mirabox.dts
+++ b/arch/arm/boot/dts/armada-370-mirabox.dts
@@ -9,7 +9,7 @@
  */
 
 /dts-v1/;
-/include/ "armada-370.dtsi"
+#include "armada-370.dtsi"
 
 / {
 	model = "Globalscale Mirabox";
@@ -25,6 +25,25 @@
 	};
 
 	soc {
+		ranges = <MBUS_ID(0xf0, 0x01) 0 0xd0000000 0x100000
+			  MBUS_ID(0x01, 0xe0) 0 0xfff00000 0x100000>;
+
+		pcie-controller {
+			status = "okay";
+
+			/* Internal mini-PCIe connector */
+			pcie@1,0 {
+				/* Port 0, Lane 0 */
+				status = "okay";
+			};
+
+			/* Connected on the PCB to a USB 3.0 XHCI controller */
+			pcie@2,0 {
+				/* Port 1, Lane 0 */
+				status = "okay";
+			};
+		};
+
 		internal-regs {
 			serial@12000 {
 				clock-frequency = <200000000>;
@@ -120,22 +139,6 @@
 					reg = <0x25>;
 				};
 			};
-
-			pcie-controller {
-				status = "okay";
-
-				/* Internal mini-PCIe connector */
-				pcie@1,0 {
-					/* Port 0, Lane 0 */
-					status = "okay";
-				};
-
-				/* Connected on the PCB to a USB 3.0 XHCI controller */
-				pcie@2,0 {
-					/* Port 1, Lane 0 */
-					status = "okay";
-				};
-			};
 		};
 	};
 };
diff --git a/arch/arm/boot/dts/armada-370-netgear-rn102.dts b/arch/arm/boot/dts/armada-370-netgear-rn102.dts
new file mode 100644
index 000000000000..8ac2ac1f69cc
--- /dev/null
+++ b/arch/arm/boot/dts/armada-370-netgear-rn102.dts
@@ -0,0 +1,194 @@
+/*
+ * Device Tree file for NETGEAR ReadyNAS 102
+ *
+ * Copyright (C) 2013, Arnaud EBALARD <arno@natisbad.org>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+/dts-v1/;
+
+#include "armada-370.dtsi"
+
+/ {
+	model = "NETGEAR ReadyNAS 102";
+	compatible = "netgear,readynas-102", "marvell,armada370", "marvell,armada-370-xp";
+
+	chosen {
+		bootargs = "console=ttyS0,115200 earlyprintk";
+	};
+
+	memory {
+		device_type = "memory";
+		reg = <0x00000000 0x20000000>; /* 512 MB */
+	};
+
+	soc {
+		ranges = <MBUS_ID(0xf0, 0x01) 0 0xd0000000 0x100000
+			  MBUS_ID(0x01, 0xe0) 0 0xfff00000 0x100000>;
+
+		pcie-controller {
+			status = "okay";
+
+			/* Connected to Marvell SATA controller */
+			pcie@1,0 {
+				/* Port 0, Lane 0 */
+				status = "okay";
+			};
+
+			/* Connected to FL1009 USB 3.0 controller */
+			pcie@2,0 {
+				/* Port 1, Lane 0 */
+				status = "okay";
+			};
+		};
+
+		internal-regs {
+			serial@12000 {
+				clock-frequency = <200000000>;
+				status = "okay";
+			};
+
+			sata@a0000 {
+				nr-ports = <2>;
+				status = "okay";
+			};
+
+			pinctrl {
+				power_led_pin: power-led-pin {
+					marvell,pins = "mpp57";
+					marvell,function = "gpio";
+				};
+				sata1_led_pin: sata1-led-pin {
+					marvell,pins = "mpp15";
+					marvell,function = "gpio";
+				};
+
+				sata2_led_pin: sata2-led-pin {
+					marvell,pins = "mpp14";
+					marvell,function = "gpio";
+				};
+
+				backup_led_pin: backup-led-pin {
+					marvell,pins = "mpp56";
+					marvell,function = "gpio";
+				};
+
+				poweroff: poweroff {
+					marvell,pins = "mpp8";
+					marvell,function = "gpio";
+				};
+			};
+
+			mdio {
+				phy0: ethernet-phy@0 {
+					reg = <0>;
+				};
+			};
+
+			ethernet@74000 {
+				status = "okay";
+				phy = <&phy0>;
+				phy-mode = "rgmii-id";
+			};
+
+			usb@50000 {
+				status = "okay";
+			};
+
+			i2c@11000 {
+				compatible = "marvell,mv64xxx-i2c";
+				clock-frequency = <100000>;
+				status = "okay";
+
+				g762: g762@3e {
+					compatible = "gmt,g762";
+					reg = <0x3e>;
+					clocks = <&g762_clk>; /* input clock */
+					fan_gear_mode = <0>;
+					fan_startv = <1>;
+					pwm_polarity = <0>;
+				};
+			};
+		};
+	};
+
+	clocks {
+	       #address-cells = <1>;
+	       #size-cells = <0>;
+
+	       g762_clk: fixedclk {
+			 compatible = "fixed-clock";
+			 #clock-cells = <0>;
+			 clock-frequency = <8192>;
+	       };
+	};
+
+	gpio_leds {
+		compatible = "gpio-leds";
+		pinctrl-0 = < &power_led_pin
+			      &sata1_led_pin
+			      &sata2_led_pin
+			      &backup_led_pin >;
+		pinctrl-names = "default";
+
+		blue_power_led {
+			label = "rn102:blue:pwr";
+			gpios = <&gpio1 25 1>;  /* GPIO 57 Active Low */
+			linux,default-trigger = "heartbeat";
+		};
+
+		green_sata1_led {
+			label = "rn102:green:sata1";
+			gpios = <&gpio0 15 1>;  /* GPIO 15 Active Low */
+			default-state = "on";
+		};
+
+		green_sata2_led {
+			label = "rn102:green:sata2";
+			gpios = <&gpio0 14 1>;   /* GPIO 14 Active Low */
+			default-state = "on";
+		};
+
+		green_backup_led {
+			label = "rn102:green:backup";
+			gpios = <&gpio1 24 1>;   /* GPIO 56 Active Low */
+			default-state = "on";
+		};
+	};
+
+	gpio_keys {
+		compatible = "gpio-keys";
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		button@1 {
+			label = "Power Button";
+			linux,code = <116>;     /* KEY_POWER */
+			gpios = <&gpio1 30 0>;
+		};
+
+		button@2 {
+			label = "Reset Button";
+			linux,code = <0x198>;   /* KEY_RESTART */
+			gpios = <&gpio0 6 1>;
+		};
+
+		button@3 {
+			label = "Backup Button";
+			linux,code = <133>;     /* KEY_COPY */
+			gpios = <&gpio1 26 1>;
+		};
+	};
+
+	gpio_poweroff {
+		compatible = "gpio-poweroff";
+		pinctrl-0 = <&poweroff>;
+		pinctrl-names = "default";
+		gpios = <&gpio0 8 1>;
+	};
+
+};
diff --git a/arch/arm/boot/dts/armada-370-rd.dts b/arch/arm/boot/dts/armada-370-rd.dts
index a3a2fedb8726..f81810a59629 100644
--- a/arch/arm/boot/dts/armada-370-rd.dts
+++ b/arch/arm/boot/dts/armada-370-rd.dts
@@ -12,7 +12,7 @@
  */
 
 /dts-v1/;
-/include/ "armada-370.dtsi"
+#include "armada-370.dtsi"
 
 / {
 	model = "Marvell Armada 370 Reference Design";
@@ -28,6 +28,25 @@
 	};
 
 	soc {
+		ranges = <MBUS_ID(0xf0, 0x01) 0 0xd0000000 0x100000
+			  MBUS_ID(0x01, 0xe0) 0 0xfff00000 0x100000>;
+
+		pcie-controller {
+			status = "okay";
+
+			/* Internal mini-PCIe connector */
+			pcie@1,0 {
+				/* Port 0, Lane 0 */
+				status = "okay";
+			};
+
+			/* Internal mini-PCIe connector */
+			pcie@2,0 {
+				/* Port 1, Lane 0 */
+				status = "okay";
+			};
+		};
+
 		internal-regs {
 			serial@12000 {
 				clock-frequency = <200000000>;
@@ -85,22 +104,6 @@
 					gpios = <&gpio0 6 1>;
 				};
 			};
-
-			pcie-controller {
-				status = "okay";
-
-				/* Internal mini-PCIe connector */
-				pcie@1,0 {
-					/* Port 0, Lane 0 */
-					status = "okay";
-				};
-
-				/* Internal mini-PCIe connector */
-				pcie@2,0 {
-					/* Port 1, Lane 0 */
-					status = "okay";
-				};
-			};
 		};
 	};
  };
diff --git a/arch/arm/boot/dts/armada-370-xp.dtsi b/arch/arm/boot/dts/armada-370-xp.dtsi
index 90b117624abb..1de2dae0fdae 100644
--- a/arch/arm/boot/dts/armada-370-xp.dtsi
+++ b/arch/arm/boot/dts/armada-370-xp.dtsi
@@ -18,6 +18,8 @@
 
 /include/ "skeleton64.dtsi"
 
+#define MBUS_ID(target,attributes) (((target) << 24) | ((attributes) << 16))
+
 / {
 	model = "Marvell Armada 370 and XP SoC";
 	compatible = "marvell,armada-370-xp";
@@ -38,18 +40,73 @@
 	};
 
 	soc {
-		#address-cells = <1>;
+		#address-cells = <2>;
 		#size-cells = <1>;
-		compatible = "simple-bus";
+		controller = <&mbusc>;
 		interrupt-parent = <&mpic>;
-		ranges = <0          0 0xd0000000 0x0100000 /* internal registers */
-			  0xe0000000 0 0xe0000000 0x8100000 /* PCIe */>;
+		pcie-mem-aperture = <0xe0000000 0x8000000>;
+		pcie-io-aperture  = <0xe8000000 0x100000>;
+
+		devbus-bootcs {
+			compatible = "marvell,mvebu-devbus";
+			reg = <MBUS_ID(0xf0, 0x01) 0x10400 0x8>;
+			ranges = <0 MBUS_ID(0x01, 0x2f) 0 0xffffffff>;
+			#address-cells = <1>;
+			#size-cells = <1>;
+			clocks = <&coreclk 0>;
+			status = "disabled";
+		};
+
+		devbus-cs0 {
+			compatible = "marvell,mvebu-devbus";
+			reg = <MBUS_ID(0xf0, 0x01) 0x10408 0x8>;
+			ranges = <0 MBUS_ID(0x01, 0x3e) 0 0xffffffff>;
+			#address-cells = <1>;
+			#size-cells = <1>;
+			clocks = <&coreclk 0>;
+			status = "disabled";
+		};
+
+		devbus-cs1 {
+			compatible = "marvell,mvebu-devbus";
+			reg = <MBUS_ID(0xf0, 0x01) 0x10410 0x8>;
+			ranges = <0 MBUS_ID(0x01, 0x3d) 0 0xffffffff>;
+			#address-cells = <1>;
+			#size-cells = <1>;
+			clocks = <&coreclk 0>;
+			status = "disabled";
+		};
+
+		devbus-cs2 {
+			compatible = "marvell,mvebu-devbus";
+			reg = <MBUS_ID(0xf0, 0x01) 0x10418 0x8>;
+			ranges = <0 MBUS_ID(0x01, 0x3b) 0 0xffffffff>;
+			#address-cells = <1>;
+			#size-cells = <1>;
+			clocks = <&coreclk 0>;
+			status = "disabled";
+		};
+
+		devbus-cs3 {
+			compatible = "marvell,mvebu-devbus";
+			reg = <MBUS_ID(0xf0, 0x01) 0x10420 0x8>;
+			ranges = <0 MBUS_ID(0x01, 0x37) 0 0xffffffff>;
+			#address-cells = <1>;
+			#size-cells = <1>;
+			clocks = <&coreclk 0>;
+			status = "disabled";
+		};
 
 		internal-regs {
 			compatible = "simple-bus";
 			#address-cells = <1>;
 			#size-cells = <1>;
-			ranges;
+			ranges = <0 MBUS_ID(0xf0, 0x01) 0 0x100000>;
+
+			mbusc: mbus-controller@20000 {
+				compatible = "marvell,mbus-controller";
+				reg = <0x20000 0x100>, <0x20180 0x20>;
+			};
 
 			mpic: interrupt-controller@20000 {
 				compatible = "marvell,mpic";
@@ -81,10 +138,8 @@
 			};
 
 			timer@20300 {
-				compatible = "marvell,armada-370-xp-timer";
 				reg = <0x20300 0x30>, <0x21040 0x30>;
 				interrupts = <37>, <38>, <39>, <40>, <5>, <6>;
-				clocks = <&coreclk 2>;
 			};
 
 			sata@a0000 {
@@ -195,50 +250,6 @@
 				status = "disabled";
 			};
 
-			devbus-bootcs@10400 {
-				compatible = "marvell,mvebu-devbus";
-				reg = <0x10400 0x8>;
-				#address-cells = <1>;
-				#size-cells = <1>;
-				clocks = <&coreclk 0>;
-				status = "disabled";
-			};
-
-			devbus-cs0@10408 {
-				compatible = "marvell,mvebu-devbus";
-				reg = <0x10408 0x8>;
-				#address-cells = <1>;
-				#size-cells = <1>;
-				clocks = <&coreclk 0>;
-				status = "disabled";
-			};
-
-			devbus-cs1@10410 {
-				compatible = "marvell,mvebu-devbus";
-				reg = <0x10410 0x8>;
-				#address-cells = <1>;
-				#size-cells = <1>;
-				clocks = <&coreclk 0>;
-				status = "disabled";
-			};
-
-			devbus-cs2@10418 {
-				compatible = "marvell,mvebu-devbus";
-				reg = <0x10418 0x8>;
-				#address-cells = <1>;
-				#size-cells = <1>;
-				clocks = <&coreclk 0>;
-				status = "disabled";
-			};
-
-			devbus-cs3@10420 {
-				compatible = "marvell,mvebu-devbus";
-				reg = <0x10420 0x8>;
-				#address-cells = <1>;
-				#size-cells = <1>;
-				clocks = <&coreclk 0>;
-				status = "disabled";
-			};
 		};
 	};
  };
diff --git a/arch/arm/boot/dts/armada-370.dtsi b/arch/arm/boot/dts/armada-370.dtsi
index fa3dfc6b4c6a..e134d7a90c9a 100644
--- a/arch/arm/boot/dts/armada-370.dtsi
+++ b/arch/arm/boot/dts/armada-370.dtsi
@@ -15,7 +15,7 @@
  * common to all Armada SoCs.
  */
 
-/include/ "armada-370-xp.dtsi"
+#include "armada-370-xp.dtsi"
 /include/ "skeleton.dtsi"
 
 / {
@@ -29,8 +29,66 @@
 	};
 
 	soc {
-		ranges = <0          0xd0000000 0x0100000 /* internal registers */
-			  0xe0000000 0xe0000000 0x8100000 /* PCIe */>;
+		compatible = "marvell,armada370-mbus", "simple-bus";
+
+		bootrom {
+			compatible = "marvell,bootrom";
+			reg = <MBUS_ID(0x01, 0xe0) 0 0x100000>;
+		};
+
+		pcie-controller {
+			compatible = "marvell,armada-370-pcie";
+			status = "disabled";
+			device_type = "pci";
+
+			#address-cells = <3>;
+			#size-cells = <2>;
+
+			bus-range = <0x00 0xff>;
+
+			ranges =
+			       <0x82000000 0 0x40000 MBUS_ID(0xf0, 0x01) 0x40000 0 0x00002000
+				0x82000000 0 0x80000 MBUS_ID(0xf0, 0x01) 0x80000 0 0x00002000
+				0x82000000 0x1 0     MBUS_ID(0x04, 0xe8) 0       1 0 /* Port 0.0 MEM */
+				0x81000000 0x1 0     MBUS_ID(0x04, 0xe0) 0       1 0 /* Port 0.0 IO  */
+				0x82000000 0x2 0     MBUS_ID(0x08, 0xe8) 0       1 0 /* Port 1.0 MEM */
+				0x81000000 0x2 0     MBUS_ID(0x08, 0xe0) 0       1 0 /* Port 1.0 IO  */>;
+
+			pcie@1,0 {
+				device_type = "pci";
+				assigned-addresses = <0x82000800 0 0x40000 0 0x2000>;
+				reg = <0x0800 0 0 0 0>;
+				#address-cells = <3>;
+				#size-cells = <2>;
+				#interrupt-cells = <1>;
+                                ranges = <0x82000000 0 0 0x82000000 0x1 0 1 0
+                                          0x81000000 0 0 0x81000000 0x1 0 1 0>;
+				interrupt-map-mask = <0 0 0 0>;
+				interrupt-map = <0 0 0 0 &mpic 58>;
+				marvell,pcie-port = <0>;
+				marvell,pcie-lane = <0>;
+				clocks = <&gateclk 5>;
+				status = "disabled";
+			};
+
+			pcie@2,0 {
+				device_type = "pci";
+				assigned-addresses = <0x82002800 0 0x80000 0 0x2000>;
+				reg = <0x1000 0 0 0 0>;
+				#address-cells = <3>;
+				#size-cells = <2>;
+				#interrupt-cells = <1>;
+                                ranges = <0x82000000 0 0 0x82000000 0x2 0 1 0
+                                          0x81000000 0 0 0x81000000 0x2 0 1 0>;
+				interrupt-map-mask = <0 0 0 0>;
+				interrupt-map = <0 0 0 0 &mpic 62>;
+				marvell,pcie-port = <1>;
+				marvell,pcie-lane = <0>;
+				clocks = <&gateclk 9>;
+				status = "disabled";
+			};
+		};
+
 		internal-regs {
 			system-controller@18200 {
 				compatible = "marvell,armada-370-xp-system-controller";
@@ -78,7 +136,7 @@
 				gpio-controller;
 				#gpio-cells = <2>;
 				interrupt-controller;
-				#interrupts-cells = <2>;
+				#interrupt-cells = <2>;
 				interrupts = <82>, <83>, <84>, <85>;
 			};
 
@@ -89,7 +147,7 @@
 				gpio-controller;
 				#gpio-cells = <2>;
 				interrupt-controller;
-				#interrupts-cells = <2>;
+				#interrupt-cells = <2>;
 				interrupts = <87>, <88>, <89>, <90>;
 			};
 
@@ -100,10 +158,15 @@
 				gpio-controller;
 				#gpio-cells = <2>;
 				interrupt-controller;
-				#interrupts-cells = <2>;
+				#interrupt-cells = <2>;
 				interrupts = <91>;
 			};
 
+			timer@20300 {
+				compatible = "marvell,armada-370-timer";
+				clocks = <&coreclk 2>;
+			};
+
 			coreclk: mvebu-sar@18230 {
 				compatible = "marvell,armada-370-core-clock";
 				reg = <0x18230 0x08>;
@@ -169,54 +232,6 @@
 					0x18304 0x4>;
 				status = "okay";
 			};
-
-			pcie-controller {
-				compatible = "marvell,armada-370-pcie";
-				status = "disabled";
-				device_type = "pci";
-
-				#address-cells = <3>;
-				#size-cells = <2>;
-
-				bus-range = <0x00 0xff>;
-
-				ranges = <0x82000000 0 0x40000 0x40000 0 0x00002000   /* Port 0.0 registers */
-					0x82000000 0 0x80000 0x80000 0 0x00002000   /* Port 1.0 registers */
-					0x82000000 0 0xe0000000 0xe0000000 0 0x08000000   /* non-prefetchable memory */
-					0x81000000 0 0          0xe8000000 0 0x00100000>; /* downstream I/O */
-
-				pcie@1,0 {
-					device_type = "pci";
-					assigned-addresses = <0x82000800 0 0x40000 0 0x2000>;
-					reg = <0x0800 0 0 0 0>;
-					#address-cells = <3>;
-					#size-cells = <2>;
-					#interrupt-cells = <1>;
-					ranges;
-					interrupt-map-mask = <0 0 0 0>;
-					interrupt-map = <0 0 0 0 &mpic 58>;
-					marvell,pcie-port = <0>;
-					marvell,pcie-lane = <0>;
-					clocks = <&gateclk 5>;
-					status = "disabled";
-				};
-
-				pcie@2,0 {
-					device_type = "pci";
-					assigned-addresses = <0x82002800 0 0x80000 0 0x2000>;
-					reg = <0x1000 0 0 0 0>;
-					#address-cells = <3>;
-					#size-cells = <2>;
-					#interrupt-cells = <1>;
-					ranges;
-					interrupt-map-mask = <0 0 0 0>;
-					interrupt-map = <0 0 0 0 &mpic 62>;
-					marvell,pcie-port = <1>;
-					marvell,pcie-lane = <0>;
-					clocks = <&gateclk 9>;
-					status = "disabled";
-				};
-			};
 		};
 	};
 };
diff --git a/arch/arm/boot/dts/armada-xp-axpwifiap.dts b/arch/arm/boot/dts/armada-xp-axpwifiap.dts
new file mode 100644
index 000000000000..c5fe57269f5a
--- /dev/null
+++ b/arch/arm/boot/dts/armada-xp-axpwifiap.dts
@@ -0,0 +1,164 @@
+/*
+ * Device Tree file for Marvell RD-AXPWiFiAP.
+ *
+ * Note: this board is shipped with a new generation boot loader that
+ * remaps internal registers at 0xf1000000. Therefore, if earlyprintk
+ * is used, the CONFIG_DEBUG_MVEBU_UART_ALTERNATE option should be
+ * used.
+ *
+ * Copyright (C) 2013 Marvell
+ *
+ * Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2.  This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+/dts-v1/;
+#include "armada-xp-mv78230.dtsi"
+
+/ {
+	model = "Marvell RD-AXPWiFiAP";
+	compatible = "marvell,rd-axpwifiap", "marvell,armadaxp-mv78230", "marvell,armadaxp", "marvell,armada-370-xp";
+
+	chosen {
+		bootargs = "console=ttyS0,115200 earlyprintk";
+	};
+
+	memory {
+		device_type = "memory";
+		reg = <0x00000000 0x00000000 0x00000000 0x40000000>; /* 1GB */
+	};
+
+	soc {
+		ranges = <MBUS_ID(0xf0, 0x01) 0 0 0xf1000000 0x100000
+			  MBUS_ID(0x01, 0x1d) 0 0 0xfff00000 0x100000>;
+
+		pcie-controller {
+			status = "okay";
+
+			/* First mini-PCIe port */
+			pcie@1,0 {
+				/* Port 0, Lane 0 */
+				status = "okay";
+			};
+
+			/* Second mini-PCIe port */
+			pcie@2,0 {
+				/* Port 0, Lane 1 */
+				status = "okay";
+			};
+
+			/* Renesas uPD720202 USB 3.0 controller */
+			pcie@3,0 {
+				/* Port 0, Lane 3 */
+				status = "okay";
+			};
+		};
+
+		internal-regs {
+			pinctrl {
+				pinctrl-0 = <&pmx_phy_int>;
+				pinctrl-names = "default";
+
+				pmx_ge0: pmx-ge0 {
+					marvell,pins = "mpp0", "mpp1", "mpp2", "mpp3",
+						       "mpp4", "mpp5", "mpp6", "mpp7",
+						       "mpp8", "mpp9", "mpp10", "mpp11";
+					marvell,function = "ge0";
+				};
+
+				pmx_ge1: pmx-ge1 {
+					marvell,pins = "mpp12", "mpp13", "mpp14", "mpp15",
+						       "mpp16", "mpp17", "mpp18", "mpp19",
+						       "mpp20", "mpp21", "mpp22", "mpp23";
+					marvell,function = "ge1";
+				};
+
+				pmx_keys: pmx-keys {
+					marvell,pins = "mpp33";
+					marvell,function = "gpio";
+				};
+
+				pmx_spi: pmx-spi {
+					marvell,pins = "mpp36", "mpp37", "mpp38", "mpp39";
+					marvell,function = "spi";
+				};
+
+				pmx_phy_int: pmx-phy-int {
+					marvell,pins = "mpp32";
+					marvell,function = "gpio";
+				};
+			};
+
+			serial@12000 {
+				clock-frequency = <250000000>;
+				status = "okay";
+			};
+
+			serial@12100 {
+				clock-frequency = <250000000>;
+				status = "okay";
+			};
+
+			sata@a0000 {
+				nr-ports = <1>;
+				status = "okay";
+			};
+
+			mdio {
+				phy0: ethernet-phy@0 {
+					reg = <0>;
+				};
+
+				phy1: ethernet-phy@1 {
+					reg = <1>;
+				};
+			};
+
+			ethernet@70000 {
+				pinctrl-0 = <&pmx_ge0>;
+				pinctrl-names = "default";
+				status = "okay";
+				phy = <&phy0>;
+				phy-mode = "rgmii-id";
+			};
+			ethernet@74000 {
+				pinctrl-0 = <&pmx_ge1>;
+				pinctrl-names = "default";
+				status = "okay";
+				phy = <&phy1>;
+				phy-mode = "rgmii-id";
+			};
+
+			spi0: spi@10600 {
+				status = "okay";
+				pinctrl-0 = <&pmx_spi>;
+				pinctrl-names = "default";
+
+				spi-flash@0 {
+					#address-cells = <1>;
+					#size-cells = <1>;
+					compatible = "n25q128a13";
+					reg = <0>; /* Chip select 0 */
+					spi-max-frequency = <108000000>;
+				};
+			};
+		};
+	};
+
+	gpio_keys {
+		compatible = "gpio-keys";
+		#address-cells = <1>;
+		#size-cells = <0>;
+		pinctrl-0 = <&pmx_keys>;
+		pinctrl-names = "default";
+
+		button@1 {
+			label = "Factory Reset Button";
+			linux,code = <141>; /* KEY_SETUP */
+			gpios = <&gpio1 1 1>;
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/armada-xp-db.dts b/arch/arm/boot/dts/armada-xp-db.dts
index e28e68ff864d..bcf6d79a57ec 100644
--- a/arch/arm/boot/dts/armada-xp-db.dts
+++ b/arch/arm/boot/dts/armada-xp-db.dts
@@ -14,7 +14,7 @@
  */
 
 /dts-v1/;
-/include/ "armada-xp-mv78460.dtsi"
+#include "armada-xp-mv78460.dtsi"
 
 / {
 	model = "Marvell Armada XP Evaluation Board";
@@ -30,9 +30,70 @@
 	};
 
 	soc {
-		ranges = <0          0 0xd0000000 0x100000	/* Internal registers 1MiB */
-			  0xe0000000 0 0xe0000000 0x8100000     /* PCIe */
-			  0xf0000000 0 0xf0000000 0x1000000>;	/* Device Bus, NOR 16MiB   */
+		ranges = <MBUS_ID(0xf0, 0x01) 0 0 0xd0000000 0x100000
+			  MBUS_ID(0x01, 0x1d) 0 0 0xfff00000 0x100000
+			  MBUS_ID(0x01, 0x2f) 0 0 0xf0000000 0x1000000>;
+
+		devbus-bootcs {
+			status = "okay";
+
+			/* Device Bus parameters are required */
+
+			/* Read parameters */
+			devbus,bus-width    = <8>;
+			devbus,turn-off-ps  = <60000>;
+			devbus,badr-skew-ps = <0>;
+			devbus,acc-first-ps = <124000>;
+			devbus,acc-next-ps  = <248000>;
+			devbus,rd-setup-ps  = <0>;
+			devbus,rd-hold-ps   = <0>;
+
+			/* Write parameters */
+			devbus,sync-enable = <0>;
+			devbus,wr-high-ps  = <60000>;
+			devbus,wr-low-ps   = <60000>;
+			devbus,ale-wr-ps   = <60000>;
+
+			/* NOR 16 MiB */
+			nor@0 {
+				compatible = "cfi-flash";
+				reg = <0 0x1000000>;
+				bank-width = <2>;
+			};
+		};
+
+		pcie-controller {
+			status = "okay";
+
+			/*
+			 * All 6 slots are physically present as
+			 * standard PCIe slots on the board.
+			 */
+			pcie@1,0 {
+				/* Port 0, Lane 0 */
+				status = "okay";
+			};
+			pcie@2,0 {
+				/* Port 0, Lane 1 */
+				status = "okay";
+			};
+			pcie@3,0 {
+				/* Port 0, Lane 2 */
+				status = "okay";
+			};
+			pcie@4,0 {
+				/* Port 0, Lane 3 */
+				status = "okay";
+			};
+			pcie@9,0 {
+				/* Port 2, Lane 0 */
+				status = "okay";
+			};
+			pcie@10,0 {
+				/* Port 3, Lane 0 */
+				status = "okay";
+			};
+		};
 
 		internal-regs {
 			serial@12000 {
@@ -127,68 +188,6 @@
 					spi-max-frequency = <20000000>;
 				};
 			};
-
-			pcie-controller {
-				status = "okay";
-
-				/*
-				 * All 6 slots are physically present as
-				 * standard PCIe slots on the board.
-				 */
-				pcie@1,0 {
-					/* Port 0, Lane 0 */
-					status = "okay";
-				};
-				pcie@2,0 {
-					/* Port 0, Lane 1 */
-					status = "okay";
-				};
-				pcie@3,0 {
-					/* Port 0, Lane 2 */
-					status = "okay";
-				};
-				pcie@4,0 {
-					/* Port 0, Lane 3 */
-					status = "okay";
-				};
-				pcie@9,0 {
-					/* Port 2, Lane 0 */
-					status = "okay";
-				};
-				pcie@10,0 {
-					/* Port 3, Lane 0 */
-					status = "okay";
-				};
-			};
-
-			devbus-bootcs@10400 {
-				status = "okay";
-				ranges = <0 0xf0000000 0x1000000>;
-
-				/* Device Bus parameters are required */
-
-				/* Read parameters */
-				devbus,bus-width    = <8>;
-				devbus,turn-off-ps  = <60000>;
-				devbus,badr-skew-ps = <0>;
-				devbus,acc-first-ps = <124000>;
-				devbus,acc-next-ps  = <248000>;
-				devbus,rd-setup-ps  = <0>;
-				devbus,rd-hold-ps   = <0>;
-
-				/* Write parameters */
-				devbus,sync-enable = <0>;
-				devbus,wr-high-ps  = <60000>;
-				devbus,wr-low-ps   = <60000>;
-				devbus,ale-wr-ps   = <60000>;
-
-				/* NOR 16 MiB */
-				nor@0 {
-					compatible = "cfi-flash";
-					reg = <0 0x1000000>;
-					bank-width = <2>;
-				};
-			};
 		};
 	};
 };
diff --git a/arch/arm/boot/dts/armada-xp-gp.dts b/arch/arm/boot/dts/armada-xp-gp.dts
index c87b2de29c30..2298e4a910e2 100644
--- a/arch/arm/boot/dts/armada-xp-gp.dts
+++ b/arch/arm/boot/dts/armada-xp-gp.dts
@@ -14,7 +14,7 @@
  */
 
 /dts-v1/;
-/include/ "armada-xp-mv78460.dtsi"
+#include "armada-xp-mv78460.dtsi"
 
 / {
 	model = "Marvell Armada XP Development Board DB-MV784MP-GP";
@@ -39,9 +39,58 @@
 	};
 
 	soc {
-		ranges = <0          0 0xd0000000 0x100000  /* Internal registers 1MiB */
-			  0xe0000000 0 0xe0000000 0x8100000 /* PCIe */
-			  0xf0000000 0 0xf0000000 0x1000000 /* Device Bus, NOR 16MiB  */>;
+		ranges = <MBUS_ID(0xf0, 0x01) 0 0 0xd0000000 0x100000
+			  MBUS_ID(0x01, 0x1d) 0 0 0xfff00000 0x100000
+			  MBUS_ID(0x01, 0x2f) 0 0 0xf0000000 0x1000000>;
+
+		devbus-bootcs {
+			status = "okay";
+
+			/* Device Bus parameters are required */
+
+			/* Read parameters */
+			devbus,bus-width    = <8>;
+			devbus,turn-off-ps  = <60000>;
+			devbus,badr-skew-ps = <0>;
+			devbus,acc-first-ps = <124000>;
+			devbus,acc-next-ps  = <248000>;
+			devbus,rd-setup-ps  = <0>;
+			devbus,rd-hold-ps   = <0>;
+
+			/* Write parameters */
+			devbus,sync-enable = <0>;
+			devbus,wr-high-ps  = <60000>;
+			devbus,wr-low-ps   = <60000>;
+			devbus,ale-wr-ps   = <60000>;
+
+			/* NOR 16 MiB */
+			nor@0 {
+				compatible = "cfi-flash";
+				reg = <0 0x1000000>;
+				bank-width = <2>;
+			};
+		};
+
+		pcie-controller {
+			status = "okay";
+
+			/*
+			 * The 3 slots are physically present as
+			 * standard PCIe slots on the board.
+			 */
+			pcie@1,0 {
+				/* Port 0, Lane 0 */
+				status = "okay";
+			};
+			pcie@9,0 {
+				/* Port 2, Lane 0 */
+				status = "okay";
+			};
+			pcie@10,0 {
+				/* Port 3, Lane 0 */
+				status = "okay";
+			};
+		};
 
 		internal-regs {
 			serial@12000 {
@@ -126,56 +175,6 @@
 					spi-max-frequency = <108000000>;
 				};
 			};
-
-			devbus-bootcs@10400 {
-				status = "okay";
-				ranges = <0 0xf0000000 0x1000000>; /* @addr 0xf000000, size 0x1000000 */
-
-				/* Device Bus parameters are required */
-
-				/* Read parameters */
-				devbus,bus-width    = <8>;
-				devbus,turn-off-ps  = <60000>;
-				devbus,badr-skew-ps = <0>;
-				devbus,acc-first-ps = <124000>;
-				devbus,acc-next-ps  = <248000>;
-				devbus,rd-setup-ps  = <0>;
-				devbus,rd-hold-ps   = <0>;
-
-				/* Write parameters */
-				devbus,sync-enable = <0>;
-				devbus,wr-high-ps  = <60000>;
-				devbus,wr-low-ps   = <60000>;
-				devbus,ale-wr-ps   = <60000>;
-
-				/* NOR 16 MiB */
-				nor@0 {
-					compatible = "cfi-flash";
-					reg = <0 0x1000000>;
-					bank-width = <2>;
-				};
-			};
-
-			pcie-controller {
-				status = "okay";
-
-				/*
-				 * The 3 slots are physically present as
-				 * standard PCIe slots on the board.
-				 */
-				pcie@1,0 {
-					/* Port 0, Lane 0 */
-					status = "okay";
-				};
-				pcie@9,0 {
-					/* Port 2, Lane 0 */
-					status = "okay";
-				};
-				pcie@10,0 {
-					/* Port 3, Lane 0 */
-					status = "okay";
-				};
-			};
 		};
 	};
 };
diff --git a/arch/arm/boot/dts/armada-xp-mv78230.dtsi b/arch/arm/boot/dts/armada-xp-mv78230.dtsi
index f8eaa383e07f..0358a33cba48 100644
--- a/arch/arm/boot/dts/armada-xp-mv78230.dtsi
+++ b/arch/arm/boot/dts/armada-xp-mv78230.dtsi
@@ -13,7 +13,7 @@
  * common to all Armada XP SoCs.
  */
 
-/include/ "armada-xp.dtsi"
+#include "armada-xp.dtsi"
 
 / {
 	model = "Marvell Armada XP MV78230 SoC";
@@ -44,6 +44,124 @@
 	};
 
 	soc {
+		/*
+		 * MV78230 has 2 PCIe units Gen2.0: One unit can be
+		 * configured as x4 or quad x1 lanes. One unit is
+		 * x4/x1.
+		 */
+		pcie-controller {
+			compatible = "marvell,armada-xp-pcie";
+			status = "disabled";
+			device_type = "pci";
+
+			#address-cells = <3>;
+			#size-cells = <2>;
+
+			bus-range = <0x00 0xff>;
+
+			ranges =
+			       <0x82000000 0 0x40000 MBUS_ID(0xf0, 0x01) 0x40000 0 0x00002000   /* Port 0.0 registers */
+				0x82000000 0 0x42000 MBUS_ID(0xf0, 0x01) 0x42000 0 0x00002000   /* Port 2.0 registers */
+				0x82000000 0 0x44000 MBUS_ID(0xf0, 0x01) 0x44000 0 0x00002000   /* Port 0.1 registers */
+				0x82000000 0 0x48000 MBUS_ID(0xf0, 0x01) 0x48000 0 0x00002000   /* Port 0.2 registers */
+				0x82000000 0 0x4c000 MBUS_ID(0xf0, 0x01) 0x4c000 0 0x00002000   /* Port 0.3 registers */
+				0x82000000 0x1 0       MBUS_ID(0x04, 0xe8) 0 1 0 /* Port 0.0 MEM */
+				0x81000000 0x1 0       MBUS_ID(0x04, 0xe0) 0 1 0 /* Port 0.0 IO  */
+				0x82000000 0x2 0       MBUS_ID(0x04, 0xd8) 0 1 0 /* Port 0.1 MEM */
+				0x81000000 0x2 0       MBUS_ID(0x04, 0xd0) 0 1 0 /* Port 0.1 IO  */
+				0x82000000 0x3 0       MBUS_ID(0x04, 0xb8) 0 1 0 /* Port 0.2 MEM */
+				0x81000000 0x3 0       MBUS_ID(0x04, 0xb0) 0 1 0 /* Port 0.2 IO  */
+				0x82000000 0x4 0       MBUS_ID(0x04, 0x78) 0 1 0 /* Port 0.3 MEM */
+				0x81000000 0x4 0       MBUS_ID(0x04, 0x70) 0 1 0 /* Port 0.3 IO  */
+				0x82000000 0x9 0       MBUS_ID(0x04, 0xf8) 0 1 0 /* Port 2.0 MEM */
+				0x81000000 0x9 0       MBUS_ID(0x04, 0xf0) 0 1 0 /* Port 2.0 IO  */>;
+
+			pcie@1,0 {
+				device_type = "pci";
+				assigned-addresses = <0x82000800 0 0x40000 0 0x2000>;
+				reg = <0x0800 0 0 0 0>;
+				#address-cells = <3>;
+				#size-cells = <2>;
+				#interrupt-cells = <1>;
+				ranges = <0x82000000 0 0 0x82000000 0x1 0 1 0
+					  0x81000000 0 0 0x81000000 0x1 0 1 0>;
+				interrupt-map-mask = <0 0 0 0>;
+				interrupt-map = <0 0 0 0 &mpic 58>;
+				marvell,pcie-port = <0>;
+				marvell,pcie-lane = <0>;
+				clocks = <&gateclk 5>;
+				status = "disabled";
+			};
+
+			pcie@2,0 {
+				device_type = "pci";
+				assigned-addresses = <0x82000800 0 0x44000 0 0x2000>;
+				reg = <0x1000 0 0 0 0>;
+				#address-cells = <3>;
+				#size-cells = <2>;
+				#interrupt-cells = <1>;
+				ranges = <0x82000000 0 0 0x82000000 0x2 0 1 0
+					  0x81000000 0 0 0x81000000 0x2 0 1 0>;
+				interrupt-map-mask = <0 0 0 0>;
+				interrupt-map = <0 0 0 0 &mpic 59>;
+				marvell,pcie-port = <0>;
+				marvell,pcie-lane = <1>;
+				clocks = <&gateclk 6>;
+				status = "disabled";
+			};
+
+			pcie@3,0 {
+				device_type = "pci";
+				assigned-addresses = <0x82000800 0 0x48000 0 0x2000>;
+				reg = <0x1800 0 0 0 0>;
+				#address-cells = <3>;
+				#size-cells = <2>;
+				#interrupt-cells = <1>;
+				ranges = <0x82000000 0 0 0x82000000 0x3 0 1 0
+					  0x81000000 0 0 0x81000000 0x3 0 1 0>;
+				interrupt-map-mask = <0 0 0 0>;
+				interrupt-map = <0 0 0 0 &mpic 60>;
+				marvell,pcie-port = <0>;
+				marvell,pcie-lane = <2>;
+				clocks = <&gateclk 7>;
+				status = "disabled";
+			};
+
+			pcie@4,0 {
+				device_type = "pci";
+				assigned-addresses = <0x82000800 0 0x4c000 0 0x2000>;
+				reg = <0x2000 0 0 0 0>;
+				#address-cells = <3>;
+				#size-cells = <2>;
+				#interrupt-cells = <1>;
+				ranges = <0x82000000 0 0 0x82000000 0x4 0 1 0
+					  0x81000000 0 0 0x81000000 0x4 0 1 0>;
+				interrupt-map-mask = <0 0 0 0>;
+				interrupt-map = <0 0 0 0 &mpic 61>;
+				marvell,pcie-port = <0>;
+				marvell,pcie-lane = <3>;
+				clocks = <&gateclk 8>;
+				status = "disabled";
+			};
+
+			pcie@9,0 {
+				device_type = "pci";
+				assigned-addresses = <0x82000800 0 0x42000 0 0x2000>;
+				reg = <0x4800 0 0 0 0>;
+				#address-cells = <3>;
+				#size-cells = <2>;
+				#interrupt-cells = <1>;
+				ranges = <0x82000000 0 0 0x82000000 0x9 0 1 0
+					  0x81000000 0 0 0x81000000 0x9 0 1 0>;
+				interrupt-map-mask = <0 0 0 0>;
+				interrupt-map = <0 0 0 0 &mpic 99>;
+				marvell,pcie-port = <2>;
+				marvell,pcie-lane = <0>;
+				clocks = <&gateclk 26>;
+				status = "disabled";
+			};
+		};
+
 		internal-regs {
 			pinctrl {
 				compatible = "marvell,mv78230-pinctrl";
@@ -63,7 +181,7 @@
 				gpio-controller;
 				#gpio-cells = <2>;
 				interrupt-controller;
-				#interrupts-cells = <2>;
+				#interrupt-cells = <2>;
 				interrupts = <82>, <83>, <84>, <85>;
 			};
 
@@ -74,113 +192,9 @@
 				gpio-controller;
 				#gpio-cells = <2>;
 				interrupt-controller;
-				#interrupts-cells = <2>;
+				#interrupt-cells = <2>;
 				interrupts = <87>, <88>, <89>;
 			};
-
-			/*
-			 * MV78230 has 2 PCIe units Gen2.0: One unit can be
-			 * configured as x4 or quad x1 lanes. One unit is
-			 * x4/x1.
-			 */
-			pcie-controller {
-				compatible = "marvell,armada-xp-pcie";
-				status = "disabled";
-				device_type = "pci";
-
-#address-cells = <3>;
-#size-cells = <2>;
-
-				bus-range = <0x00 0xff>;
-
-				ranges = <0x82000000 0 0x40000 0x40000 0 0x00002000   /* Port 0.0 registers */
-					0x82000000 0 0x42000 0x42000 0 0x00002000   /* Port 2.0 registers */
-					0x82000000 0 0x44000 0x44000 0 0x00002000   /* Port 0.1 registers */
-					0x82000000 0 0x48000 0x48000 0 0x00002000   /* Port 0.2 registers */
-					0x82000000 0 0x4c000 0x4c000 0 0x00002000   /* Port 0.3 registers */
-					0x82000000 0 0xe0000000 0xe0000000 0 0x08000000   /* non-prefetchable memory */
-					0x81000000 0 0	  0xe8000000 0 0x00100000>; /* downstream I/O */
-
-				pcie@1,0 {
-					device_type = "pci";
-					assigned-addresses = <0x82000800 0 0x40000 0 0x2000>;
-					reg = <0x0800 0 0 0 0>;
-					#address-cells = <3>;
-					#size-cells = <2>;
-					#interrupt-cells = <1>;
-					ranges;
-					interrupt-map-mask = <0 0 0 0>;
-					interrupt-map = <0 0 0 0 &mpic 58>;
-					marvell,pcie-port = <0>;
-					marvell,pcie-lane = <0>;
-					clocks = <&gateclk 5>;
-					status = "disabled";
-				};
-
-				pcie@2,0 {
-					device_type = "pci";
-					assigned-addresses = <0x82000800 0 0x44000 0 0x2000>;
-					reg = <0x1000 0 0 0 0>;
-					#address-cells = <3>;
-					#size-cells = <2>;
-					#interrupt-cells = <1>;
-					ranges;
-					interrupt-map-mask = <0 0 0 0>;
-					interrupt-map = <0 0 0 0 &mpic 59>;
-					marvell,pcie-port = <0>;
-					marvell,pcie-lane = <1>;
-					clocks = <&gateclk 6>;
-					status = "disabled";
-				};
-
-				pcie@3,0 {
-					device_type = "pci";
-					assigned-addresses = <0x82000800 0 0x48000 0 0x2000>;
-					reg = <0x1800 0 0 0 0>;
-					#address-cells = <3>;
-					#size-cells = <2>;
-					#interrupt-cells = <1>;
-					ranges;
-					interrupt-map-mask = <0 0 0 0>;
-					interrupt-map = <0 0 0 0 &mpic 60>;
-					marvell,pcie-port = <0>;
-					marvell,pcie-lane = <2>;
-					clocks = <&gateclk 7>;
-					status = "disabled";
-				};
-
-				pcie@4,0 {
-					device_type = "pci";
-					assigned-addresses = <0x82000800 0 0x4c000 0 0x2000>;
-					reg = <0x2000 0 0 0 0>;
-					#address-cells = <3>;
-					#size-cells = <2>;
-					#interrupt-cells = <1>;
-					ranges;
-					interrupt-map-mask = <0 0 0 0>;
-					interrupt-map = <0 0 0 0 &mpic 61>;
-					marvell,pcie-port = <0>;
-					marvell,pcie-lane = <3>;
-					clocks = <&gateclk 8>;
-					status = "disabled";
-				};
-
-				pcie@9,0 {
-					device_type = "pci";
-					assigned-addresses = <0x82000800 0 0x42000 0 0x2000>;
-					reg = <0x4800 0 0 0 0>;
-					#address-cells = <3>;
-					#size-cells = <2>;
-					#interrupt-cells = <1>;
-					ranges;
-					interrupt-map-mask = <0 0 0 0>;
-					interrupt-map = <0 0 0 0 &mpic 99>;
-					marvell,pcie-port = <2>;
-					marvell,pcie-lane = <0>;
-					clocks = <&gateclk 26>;
-					status = "disabled";
-				};
-			};
 		};
 	};
 };
diff --git a/arch/arm/boot/dts/armada-xp-mv78260.dtsi b/arch/arm/boot/dts/armada-xp-mv78260.dtsi
index 2d9335da210c..0e82c5062243 100644
--- a/arch/arm/boot/dts/armada-xp-mv78260.dtsi
+++ b/arch/arm/boot/dts/armada-xp-mv78260.dtsi
@@ -13,7 +13,7 @@
  * common to all Armada XP SoCs.
  */
 
-/include/ "armada-xp.dtsi"
+#include "armada-xp.dtsi"
 
 / {
 	model = "Marvell Armada XP MV78260 SoC";
@@ -45,6 +45,145 @@
 	};
 
 	soc {
+		/*
+		 * MV78260 has 3 PCIe units Gen2.0: Two units can be
+		 * configured as x4 or quad x1 lanes. One unit is
+		 * x4/x1.
+		 */
+		pcie-controller {
+			compatible = "marvell,armada-xp-pcie";
+			status = "disabled";
+			device_type = "pci";
+
+			#address-cells = <3>;
+			#size-cells = <2>;
+
+			bus-range = <0x00 0xff>;
+
+			ranges =
+			       <0x82000000 0 0x40000 MBUS_ID(0xf0, 0x01) 0x40000 0 0x00002000   /* Port 0.0 registers */
+				0x82000000 0 0x42000 MBUS_ID(0xf0, 0x01) 0x42000 0 0x00002000   /* Port 2.0 registers */
+				0x82000000 0 0x44000 MBUS_ID(0xf0, 0x01) 0x44000 0 0x00002000   /* Port 0.1 registers */
+				0x82000000 0 0x48000 MBUS_ID(0xf0, 0x01) 0x48000 0 0x00002000   /* Port 0.2 registers */
+				0x82000000 0 0x4c000 MBUS_ID(0xf0, 0x01) 0x4c000 0 0x00002000   /* Port 0.3 registers */
+				0x82000000 0 0x80000 MBUS_ID(0xf0, 0x01) 0x80000 0 0x00002000   /* Port 1.0 registers */
+				0x82000000 0 0x82000 MBUS_ID(0xf0, 0x01) 0x82000 0 0x00002000   /* Port 3.0 registers */
+				0x82000000 0x1 0     MBUS_ID(0x04, 0xe8) 0 1 0 /* Port 0.0 MEM */
+				0x81000000 0x1 0     MBUS_ID(0x04, 0xe0) 0 1 0 /* Port 0.0 IO  */
+				0x82000000 0x2 0     MBUS_ID(0x04, 0xd8) 0 1 0 /* Port 0.1 MEM */
+				0x81000000 0x2 0     MBUS_ID(0x04, 0xd0) 0 1 0 /* Port 0.1 IO  */
+				0x82000000 0x3 0     MBUS_ID(0x04, 0xb8) 0 1 0 /* Port 0.2 MEM */
+				0x81000000 0x3 0     MBUS_ID(0x04, 0xb0) 0 1 0 /* Port 0.2 IO  */
+				0x82000000 0x4 0     MBUS_ID(0x04, 0x78) 0 1 0 /* Port 0.3 MEM */
+				0x81000000 0x4 0     MBUS_ID(0x04, 0x70) 0 1 0 /* Port 0.3 IO  */
+				0x82000000 0x9 0     MBUS_ID(0x08, 0xe8) 0 1 0 /* Port 1.0 MEM */
+				0x81000000 0x9 0     MBUS_ID(0x08, 0xe0) 0 1 0 /* Port 1.0 IO  */
+				0x82000000 0xa 0     MBUS_ID(0x08, 0xf8) 0 1 0 /* Port 3.0 MEM */
+				0x81000000 0xa 0     MBUS_ID(0x08, 0xf0) 0 1 0 /* Port 3.0 IO  */>;
+
+			pcie@1,0 {
+				device_type = "pci";
+				assigned-addresses = <0x82000800 0 0x40000 0 0x2000>;
+				reg = <0x0800 0 0 0 0>;
+				#address-cells = <3>;
+				#size-cells = <2>;
+				#interrupt-cells = <1>;
+				ranges = <0x82000000 0 0 0x82000000 0x1 0 1 0
+					  0x81000000 0 0 0x81000000 0x1 0 1 0>;
+				interrupt-map-mask = <0 0 0 0>;
+				interrupt-map = <0 0 0 0 &mpic 58>;
+				marvell,pcie-port = <0>;
+				marvell,pcie-lane = <0>;
+				clocks = <&gateclk 5>;
+				status = "disabled";
+			};
+
+			pcie@2,0 {
+				device_type = "pci";
+				assigned-addresses = <0x82000800 0 0x44000 0 0x2000>;
+				reg = <0x1000 0 0 0 0>;
+				#address-cells = <3>;
+				#size-cells = <2>;
+				#interrupt-cells = <1>;
+                                ranges = <0x82000000 0 0 0x82000000 0x2 0 1 0
+                                          0x81000000 0 0 0x81000000 0x2 0 1 0>;
+				interrupt-map-mask = <0 0 0 0>;
+				interrupt-map = <0 0 0 0 &mpic 59>;
+				marvell,pcie-port = <0>;
+				marvell,pcie-lane = <1>;
+				clocks = <&gateclk 6>;
+				status = "disabled";
+			};
+
+			pcie@3,0 {
+				device_type = "pci";
+				assigned-addresses = <0x82000800 0 0x48000 0 0x2000>;
+				reg = <0x1800 0 0 0 0>;
+				#address-cells = <3>;
+				#size-cells = <2>;
+				#interrupt-cells = <1>;
+				ranges = <0x82000000 0 0 0x82000000 0x3 0 1 0
+					  0x81000000 0 0 0x81000000 0x3 0 1 0>;
+				interrupt-map-mask = <0 0 0 0>;
+				interrupt-map = <0 0 0 0 &mpic 60>;
+				marvell,pcie-port = <0>;
+				marvell,pcie-lane = <2>;
+				clocks = <&gateclk 7>;
+				status = "disabled";
+			};
+
+			pcie@4,0 {
+				device_type = "pci";
+				assigned-addresses = <0x82000800 0 0x4c000 0 0x2000>;
+				reg = <0x2000 0 0 0 0>;
+				#address-cells = <3>;
+				#size-cells = <2>;
+				#interrupt-cells = <1>;
+				ranges = <0x82000000 0 0 0x82000000 0x4 0 1 0
+					  0x81000000 0 0 0x81000000 0x4 0 1 0>;
+				interrupt-map-mask = <0 0 0 0>;
+				interrupt-map = <0 0 0 0 &mpic 61>;
+				marvell,pcie-port = <0>;
+				marvell,pcie-lane = <3>;
+				clocks = <&gateclk 8>;
+				status = "disabled";
+			};
+
+			pcie@9,0 {
+				device_type = "pci";
+				assigned-addresses = <0x82000800 0 0x42000 0 0x2000>;
+				reg = <0x4800 0 0 0 0>;
+				#address-cells = <3>;
+				#size-cells = <2>;
+				#interrupt-cells = <1>;
+				ranges = <0x82000000 0 0 0x82000000 0x9 0 1 0
+					  0x81000000 0 0 0x81000000 0x9 0 1 0>;
+				interrupt-map-mask = <0 0 0 0>;
+				interrupt-map = <0 0 0 0 &mpic 99>;
+				marvell,pcie-port = <2>;
+				marvell,pcie-lane = <0>;
+				clocks = <&gateclk 26>;
+				status = "disabled";
+			};
+
+			pcie@10,0 {
+				device_type = "pci";
+				assigned-addresses = <0x82000800 0 0x82000 0 0x2000>;
+				reg = <0x5000 0 0 0 0>;
+				#address-cells = <3>;
+				#size-cells = <2>;
+				#interrupt-cells = <1>;
+				ranges = <0x82000000 0 0 0x82000000 0xa 0 1 0
+					  0x81000000 0 0 0x81000000 0xa 0 1 0>;
+				interrupt-map-mask = <0 0 0 0>;
+				interrupt-map = <0 0 0 0 &mpic 103>;
+				marvell,pcie-port = <3>;
+				marvell,pcie-lane = <0>;
+				clocks = <&gateclk 27>;
+				status = "disabled";
+			};
+		};
+
 		internal-regs {
 			pinctrl {
 				compatible = "marvell,mv78260-pinctrl";
@@ -64,7 +203,7 @@
 				gpio-controller;
 				#gpio-cells = <2>;
 				interrupt-controller;
-				#interrupts-cells = <2>;
+				#interrupt-cells = <2>;
 				interrupts = <82>, <83>, <84>, <85>;
 			};
 
@@ -75,7 +214,7 @@
 				gpio-controller;
 				#gpio-cells = <2>;
 				interrupt-controller;
-				#interrupts-cells = <2>;
+				#interrupt-cells = <2>;
 				interrupts = <87>, <88>, <89>, <90>;
 			};
 
@@ -86,7 +225,7 @@
 				gpio-controller;
 				#gpio-cells = <2>;
 				interrupt-controller;
-				#interrupts-cells = <2>;
+				#interrupt-cells = <2>;
 				interrupts = <91>;
 			};
 
@@ -97,128 +236,6 @@
 				clocks = <&gateclk 1>;
 				status = "disabled";
 			};
-
-			/*
-			 * MV78260 has 3 PCIe units Gen2.0: Two units can be
-			 * configured as x4 or quad x1 lanes. One unit is
-			 * x4/x1.
-			 */
-			pcie-controller {
-				compatible = "marvell,armada-xp-pcie";
-				status = "disabled";
-				device_type = "pci";
-
-				#address-cells = <3>;
-				#size-cells = <2>;
-
-				bus-range = <0x00 0xff>;
-
-				ranges = <0x82000000 0 0x40000 0x40000 0 0x00002000   /* Port 0.0 registers */
-					0x82000000 0 0x42000 0x42000 0 0x00002000   /* Port 2.0 registers */
-					0x82000000 0 0x44000 0x44000 0 0x00002000   /* Port 0.1 registers */
-					0x82000000 0 0x48000 0x48000 0 0x00002000   /* Port 0.2 registers */
-					0x82000000 0 0x4c000 0x4c000 0 0x00002000   /* Port 0.3 registers */
-					0x82000000 0 0x80000 0x80000 0 0x00002000   /* Port 1.0 registers */
-					0x82000000 0 0x82000 0x82000 0 0x00002000   /* Port 3.0 registers */
-					0x82000000 0 0xe0000000 0xe0000000 0 0x08000000   /* non-prefetchable memory */
-					0x81000000 0 0	  0xe8000000 0 0x00100000>; /* downstream I/O */
-
-				pcie@1,0 {
-					device_type = "pci";
-					assigned-addresses = <0x82000800 0 0x40000 0 0x2000>;
-					reg = <0x0800 0 0 0 0>;
-					#address-cells = <3>;
-					#size-cells = <2>;
-					#interrupt-cells = <1>;
-					ranges;
-					interrupt-map-mask = <0 0 0 0>;
-					interrupt-map = <0 0 0 0 &mpic 58>;
-					marvell,pcie-port = <0>;
-					marvell,pcie-lane = <0>;
-					clocks = <&gateclk 5>;
-					status = "disabled";
-				};
-
-				pcie@2,0 {
-					device_type = "pci";
-					assigned-addresses = <0x82000800 0 0x44000 0 0x2000>;
-					reg = <0x1000 0 0 0 0>;
-					#address-cells = <3>;
-					#size-cells = <2>;
-					#interrupt-cells = <1>;
-					ranges;
-					interrupt-map-mask = <0 0 0 0>;
-					interrupt-map = <0 0 0 0 &mpic 59>;
-					marvell,pcie-port = <0>;
-					marvell,pcie-lane = <1>;
-					clocks = <&gateclk 6>;
-					status = "disabled";
-				};
-
-				pcie@3,0 {
-					device_type = "pci";
-					assigned-addresses = <0x82000800 0 0x48000 0 0x2000>;
-					reg = <0x1800 0 0 0 0>;
-					#address-cells = <3>;
-					#size-cells = <2>;
-					#interrupt-cells = <1>;
-					ranges;
-					interrupt-map-mask = <0 0 0 0>;
-					interrupt-map = <0 0 0 0 &mpic 60>;
-					marvell,pcie-port = <0>;
-					marvell,pcie-lane = <2>;
-					clocks = <&gateclk 7>;
-					status = "disabled";
-				};
-
-				pcie@4,0 {
-					device_type = "pci";
-					assigned-addresses = <0x82000800 0 0x4c000 0 0x2000>;
-					reg = <0x2000 0 0 0 0>;
-					#address-cells = <3>;
-					#size-cells = <2>;
-					#interrupt-cells = <1>;
-					ranges;
-					interrupt-map-mask = <0 0 0 0>;
-					interrupt-map = <0 0 0 0 &mpic 61>;
-					marvell,pcie-port = <0>;
-					marvell,pcie-lane = <3>;
-					clocks = <&gateclk 8>;
-					status = "disabled";
-				};
-
-				pcie@9,0 {
-					device_type = "pci";
-					assigned-addresses = <0x82000800 0 0x42000 0 0x2000>;
-					reg = <0x4800 0 0 0 0>;
-					#address-cells = <3>;
-					#size-cells = <2>;
-					#interrupt-cells = <1>;
-					ranges;
-					interrupt-map-mask = <0 0 0 0>;
-					interrupt-map = <0 0 0 0 &mpic 99>;
-					marvell,pcie-port = <2>;
-					marvell,pcie-lane = <0>;
-					clocks = <&gateclk 26>;
-					status = "disabled";
-				};
-
-				pcie@10,0 {
-					device_type = "pci";
-					assigned-addresses = <0x82000800 0 0x82000 0 0x2000>;
-					reg = <0x5000 0 0 0 0>;
-					#address-cells = <3>;
-					#size-cells = <2>;
-					#interrupt-cells = <1>;
-					ranges;
-					interrupt-map-mask = <0 0 0 0>;
-					interrupt-map = <0 0 0 0 &mpic 103>;
-					marvell,pcie-port = <3>;
-					marvell,pcie-lane = <0>;
-					clocks = <&gateclk 27>;
-					status = "disabled";
-				};
-			};
 		};
 	};
 };
diff --git a/arch/arm/boot/dts/armada-xp-mv78460.dtsi b/arch/arm/boot/dts/armada-xp-mv78460.dtsi
index c7b1f4d5c1c7..e82c1b80af17 100644
--- a/arch/arm/boot/dts/armada-xp-mv78460.dtsi
+++ b/arch/arm/boot/dts/armada-xp-mv78460.dtsi
@@ -13,7 +13,7 @@
  * common to all Armada XP SoCs.
  */
 
-/include/ "armada-xp.dtsi"
+#include "armada-xp.dtsi"
 
 / {
 	model = "Marvell Armada XP MV78460 SoC";
@@ -61,6 +61,227 @@
 	};
 
 	soc {
+		/*
+		 * MV78460 has 4 PCIe units Gen2.0: Two units can be
+		 * configured as x4 or quad x1 lanes. Two units are
+		 * x4/x1.
+		 */
+		pcie-controller {
+			compatible = "marvell,armada-xp-pcie";
+			status = "disabled";
+			device_type = "pci";
+
+			#address-cells = <3>;
+			#size-cells = <2>;
+
+			bus-range = <0x00 0xff>;
+
+			ranges =
+			       <0x82000000 0 0x40000 MBUS_ID(0xf0, 0x01) 0x40000 0 0x00002000   /* Port 0.0 registers */
+				0x82000000 0 0x42000 MBUS_ID(0xf0, 0x01) 0x42000 0 0x00002000   /* Port 2.0 registers */
+				0x82000000 0 0x44000 MBUS_ID(0xf0, 0x01) 0x44000 0 0x00002000   /* Port 0.1 registers */
+				0x82000000 0 0x48000 MBUS_ID(0xf0, 0x01) 0x48000 0 0x00002000   /* Port 0.2 registers */
+				0x82000000 0 0x4c000 MBUS_ID(0xf0, 0x01) 0x4c000 0 0x00002000   /* Port 0.3 registers */
+				0x82000000 0 0x80000 MBUS_ID(0xf0, 0x01) 0x80000 0 0x00002000   /* Port 1.0 registers */
+				0x82000000 0 0x82000 MBUS_ID(0xf0, 0x01) 0x82000 0 0x00002000   /* Port 3.0 registers */
+				0x82000000 0 0x84000 MBUS_ID(0xf0, 0x01) 0x84000 0 0x00002000   /* Port 1.1 registers */
+				0x82000000 0 0x88000 MBUS_ID(0xf0, 0x01) 0x88000 0 0x00002000   /* Port 1.2 registers */
+				0x82000000 0 0x8c000 MBUS_ID(0xf0, 0x01) 0x8c000 0 0x00002000   /* Port 1.3 registers */
+				0x82000000 0x1 0     MBUS_ID(0x04, 0xe8) 0 1 0 /* Port 0.0 MEM */
+				0x81000000 0x1 0     MBUS_ID(0x04, 0xe0) 0 1 0 /* Port 0.0 IO  */
+				0x82000000 0x2 0     MBUS_ID(0x04, 0xd8) 0 1 0 /* Port 0.1 MEM */
+				0x81000000 0x2 0     MBUS_ID(0x04, 0xd0) 0 1 0 /* Port 0.1 IO  */
+				0x82000000 0x3 0     MBUS_ID(0x04, 0xb8) 0 1 0 /* Port 0.2 MEM */
+				0x81000000 0x3 0     MBUS_ID(0x04, 0xb0) 0 1 0 /* Port 0.2 IO  */
+				0x82000000 0x4 0     MBUS_ID(0x04, 0x78) 0 1 0 /* Port 0.3 MEM */
+				0x81000000 0x4 0     MBUS_ID(0x04, 0x70) 0 1 0 /* Port 0.3 IO  */
+
+				0x82000000 0x5 0     MBUS_ID(0x08, 0xe8) 0 1 0 /* Port 1.0 MEM */
+				0x81000000 0x5 0     MBUS_ID(0x08, 0xe0) 0 1 0 /* Port 1.0 IO  */
+				0x82000000 0x6 0     MBUS_ID(0x08, 0xd8) 0 1 0 /* Port 1.1 MEM */
+				0x81000000 0x6 0     MBUS_ID(0x08, 0xd0) 0 1 0 /* Port 1.1 IO  */
+				0x82000000 0x7 0     MBUS_ID(0x08, 0xb8) 0 1 0 /* Port 1.2 MEM */
+				0x81000000 0x7 0     MBUS_ID(0x08, 0xb0) 0 1 0 /* Port 1.2 IO  */
+				0x82000000 0x8 0     MBUS_ID(0x08, 0x78) 0 1 0 /* Port 1.3 MEM */
+				0x81000000 0x8 0     MBUS_ID(0x08, 0x70) 0 1 0 /* Port 1.3 IO  */
+
+				0x82000000 0x9 0     MBUS_ID(0x04, 0xf8) 0 1 0 /* Port 2.0 MEM */
+				0x81000000 0x9 0     MBUS_ID(0x04, 0xf0) 0 1 0 /* Port 2.0 IO  */
+
+				0x82000000 0xa 0     MBUS_ID(0x08, 0xf8) 0 1 0 /* Port 3.0 MEM */
+				0x81000000 0xa 0     MBUS_ID(0x08, 0xf0) 0 1 0 /* Port 3.0 IO  */>;
+
+			pcie@1,0 {
+				device_type = "pci";
+				assigned-addresses = <0x82000800 0 0x40000 0 0x2000>;
+				reg = <0x0800 0 0 0 0>;
+				#address-cells = <3>;
+				#size-cells = <2>;
+				#interrupt-cells = <1>;
+				ranges = <0x82000000 0 0 0x82000000 0x1 0 1 0
+					  0x81000000 0 0 0x81000000 0x1 0 1 0>;
+				interrupt-map-mask = <0 0 0 0>;
+				interrupt-map = <0 0 0 0 &mpic 58>;
+				marvell,pcie-port = <0>;
+				marvell,pcie-lane = <0>;
+				clocks = <&gateclk 5>;
+				status = "disabled";
+			};
+
+			pcie@2,0 {
+				device_type = "pci";
+				assigned-addresses = <0x82001000 0 0x44000 0 0x2000>;
+				reg = <0x1000 0 0 0 0>;
+				#address-cells = <3>;
+				#size-cells = <2>;
+				#interrupt-cells = <1>;
+				ranges = <0x82000000 0 0 0x82000000 0x2 0 1 0
+					  0x81000000 0 0 0x81000000 0x2 0 1 0>;
+				interrupt-map-mask = <0 0 0 0>;
+				interrupt-map = <0 0 0 0 &mpic 59>;
+				marvell,pcie-port = <0>;
+				marvell,pcie-lane = <1>;
+				clocks = <&gateclk 6>;
+				status = "disabled";
+			};
+
+			pcie@3,0 {
+				device_type = "pci";
+				assigned-addresses = <0x82001800 0 0x48000 0 0x2000>;
+				reg = <0x1800 0 0 0 0>;
+				#address-cells = <3>;
+				#size-cells = <2>;
+				#interrupt-cells = <1>;
+				ranges = <0x82000000 0 0 0x82000000 0x3 0 1 0
+					  0x81000000 0 0 0x81000000 0x3 0 1 0>;
+				interrupt-map-mask = <0 0 0 0>;
+				interrupt-map = <0 0 0 0 &mpic 60>;
+				marvell,pcie-port = <0>;
+				marvell,pcie-lane = <2>;
+				clocks = <&gateclk 7>;
+				status = "disabled";
+			};
+
+			pcie@4,0 {
+				device_type = "pci";
+				assigned-addresses = <0x82002000 0 0x4c000 0 0x2000>;
+				reg = <0x2000 0 0 0 0>;
+				#address-cells = <3>;
+				#size-cells = <2>;
+				#interrupt-cells = <1>;
+				ranges = <0x82000000 0 0 0x82000000 0x4 0 1 0
+					  0x81000000 0 0 0x81000000 0x4 0 1 0>;
+				interrupt-map-mask = <0 0 0 0>;
+				interrupt-map = <0 0 0 0 &mpic 61>;
+				marvell,pcie-port = <0>;
+				marvell,pcie-lane = <3>;
+				clocks = <&gateclk 8>;
+				status = "disabled";
+			};
+
+			pcie@5,0 {
+				device_type = "pci";
+				assigned-addresses = <0x82002800 0 0x80000 0 0x2000>;
+				reg = <0x2800 0 0 0 0>;
+				#address-cells = <3>;
+				#size-cells = <2>;
+				#interrupt-cells = <1>;
+				ranges = <0x82000000 0 0 0x82000000 0x5 0 1 0
+					  0x81000000 0 0 0x81000000 0x5 0 1 0>;
+				interrupt-map-mask = <0 0 0 0>;
+				interrupt-map = <0 0 0 0 &mpic 62>;
+				marvell,pcie-port = <1>;
+				marvell,pcie-lane = <0>;
+				clocks = <&gateclk 9>;
+				status = "disabled";
+			};
+
+			pcie@6,0 {
+				device_type = "pci";
+				assigned-addresses = <0x82003000 0 0x84000 0 0x2000>;
+				reg = <0x3000 0 0 0 0>;
+				#address-cells = <3>;
+				#size-cells = <2>;
+				#interrupt-cells = <1>;
+				ranges = <0x82000000 0 0 0x82000000 0x6 0 1 0
+					  0x81000000 0 0 0x81000000 0x6 0 1 0>;
+				interrupt-map-mask = <0 0 0 0>;
+				interrupt-map = <0 0 0 0 &mpic 63>;
+				marvell,pcie-port = <1>;
+				marvell,pcie-lane = <1>;
+				clocks = <&gateclk 10>;
+				status = "disabled";
+			};
+
+			pcie@7,0 {
+				device_type = "pci";
+				assigned-addresses = <0x82003800 0 0x88000 0 0x2000>;
+				reg = <0x3800 0 0 0 0>;
+				#address-cells = <3>;
+				#size-cells = <2>;
+				#interrupt-cells = <1>;
+				ranges = <0x82000000 0 0 0x82000000 0x7 0 1 0
+					  0x81000000 0 0 0x81000000 0x7 0 1 0>;
+				interrupt-map-mask = <0 0 0 0>;
+				interrupt-map = <0 0 0 0 &mpic 64>;
+				marvell,pcie-port = <1>;
+				marvell,pcie-lane = <2>;
+				clocks = <&gateclk 11>;
+				status = "disabled";
+			};
+
+			pcie@8,0 {
+				device_type = "pci";
+				assigned-addresses = <0x82004000 0 0x8c000 0 0x2000>;
+				reg = <0x4000 0 0 0 0>;
+				#address-cells = <3>;
+				#size-cells = <2>;
+				#interrupt-cells = <1>;
+				ranges = <0x82000000 0 0 0x82000000 0x8 0 1 0
+					  0x81000000 0 0 0x81000000 0x8 0 1 0>;
+				interrupt-map-mask = <0 0 0 0>;
+				interrupt-map = <0 0 0 0 &mpic 65>;
+				marvell,pcie-port = <1>;
+				marvell,pcie-lane = <3>;
+				clocks = <&gateclk 12>;
+				status = "disabled";
+			};
+
+			pcie@9,0 {
+				device_type = "pci";
+				assigned-addresses = <0x82004800 0 0x42000 0 0x2000>;
+				reg = <0x4800 0 0 0 0>;
+				#address-cells = <3>;
+				#size-cells = <2>;
+				#interrupt-cells = <1>;
+				ranges = <0x82000000 0 0 0x82000000 0x9 0 1 0
+					  0x81000000 0 0 0x81000000 0x9 0 1 0>;
+				interrupt-map-mask = <0 0 0 0>;
+				interrupt-map = <0 0 0 0 &mpic 99>;
+				marvell,pcie-port = <2>;
+				marvell,pcie-lane = <0>;
+				clocks = <&gateclk 26>;
+				status = "disabled";
+			};
+
+			pcie@10,0 {
+				device_type = "pci";
+				assigned-addresses = <0x82005000 0 0x82000 0 0x2000>;
+				reg = <0x5000 0 0 0 0>;
+				#address-cells = <3>;
+				#size-cells = <2>;
+				#interrupt-cells = <1>;
+				ranges = <0x82000000 0 0 0x82000000 0xa 0 1 0
+					  0x81000000 0 0 0x81000000 0xa 0 1 0>;
+				interrupt-map-mask = <0 0 0 0>;
+				interrupt-map = <0 0 0 0 &mpic 103>;
+				marvell,pcie-port = <3>;
+				marvell,pcie-lane = <0>;
+				clocks = <&gateclk 27>;
+				status = "disabled";
+			};
+		};
+
 		internal-regs {
 			pinctrl {
 				compatible = "marvell,mv78460-pinctrl";
@@ -80,7 +301,7 @@
 				gpio-controller;
 				#gpio-cells = <2>;
 				interrupt-controller;
-				#interrupts-cells = <2>;
+				#interrupt-cells = <2>;
 				interrupts = <82>, <83>, <84>, <85>;
 			};
 
@@ -91,7 +312,7 @@
 				gpio-controller;
 				#gpio-cells = <2>;
 				interrupt-controller;
-				#interrupts-cells = <2>;
+				#interrupt-cells = <2>;
 				interrupts = <87>, <88>, <89>, <90>;
 			};
 
@@ -102,7 +323,7 @@
 				gpio-controller;
 				#gpio-cells = <2>;
 				interrupt-controller;
-				#interrupts-cells = <2>;
+				#interrupt-cells = <2>;
 				interrupts = <91>;
 			};
 
@@ -113,194 +334,6 @@
 				clocks = <&gateclk 1>;
 				status = "disabled";
 			};
-
-			/*
-			 * MV78460 has 4 PCIe units Gen2.0: Two units can be
-			 * configured as x4 or quad x1 lanes. Two units are
-			 * x4/x1.
-			 */
-			pcie-controller {
-				compatible = "marvell,armada-xp-pcie";
-				status = "disabled";
-				device_type = "pci";
-
-				#address-cells = <3>;
-				#size-cells = <2>;
-
-				bus-range = <0x00 0xff>;
-
-				ranges = <0x82000000 0 0x40000 0x40000 0 0x00002000   /* Port 0.0 registers */
-					0x82000000 0 0x42000 0x42000 0 0x00002000   /* Port 2.0 registers */
-					0x82000000 0 0x44000 0x44000 0 0x00002000   /* Port 0.1 registers */
-					0x82000000 0 0x48000 0x48000 0 0x00002000   /* Port 0.2 registers */
-					0x82000000 0 0x4c000 0x4c000 0 0x00002000   /* Port 0.3 registers */
-					0x82000000 0 0x80000 0x80000 0 0x00002000   /* Port 1.0 registers */
-					0x82000000 0 0x82000 0x82000 0 0x00002000   /* Port 3.0 registers */
-					0x82000000 0 0x84000 0x84000 0 0x00002000   /* Port 1.1 registers */
-					0x82000000 0 0x88000 0x88000 0 0x00002000   /* Port 1.2 registers */
-					0x82000000 0 0x8c000 0x8c000 0 0x00002000   /* Port 1.3 registers */
-					0x82000000 0 0xe0000000 0xe0000000 0 0x08000000   /* non-prefetchable memory */
-					0x81000000 0 0	  0xe8000000 0 0x00100000>; /* downstream I/O */
-
-				pcie@1,0 {
-					device_type = "pci";
-					assigned-addresses = <0x82000800 0 0x40000 0 0x2000>;
-					reg = <0x0800 0 0 0 0>;
-					#address-cells = <3>;
-					#size-cells = <2>;
-					#interrupt-cells = <1>;
-					ranges;
-					interrupt-map-mask = <0 0 0 0>;
-					interrupt-map = <0 0 0 0 &mpic 58>;
-					marvell,pcie-port = <0>;
-					marvell,pcie-lane = <0>;
-					clocks = <&gateclk 5>;
-					status = "disabled";
-				};
-
-				pcie@2,0 {
-					device_type = "pci";
-					assigned-addresses = <0x82001000 0 0x44000 0 0x2000>;
-					reg = <0x1000 0 0 0 0>;
-					#address-cells = <3>;
-					#size-cells = <2>;
-					#interrupt-cells = <1>;
-					ranges;
-					interrupt-map-mask = <0 0 0 0>;
-					interrupt-map = <0 0 0 0 &mpic 59>;
-					marvell,pcie-port = <0>;
-					marvell,pcie-lane = <1>;
-					clocks = <&gateclk 6>;
-					status = "disabled";
-				};
-
-				pcie@3,0 {
-					device_type = "pci";
-					assigned-addresses = <0x82001800 0 0x48000 0 0x2000>;
-					reg = <0x1800 0 0 0 0>;
-					#address-cells = <3>;
-					#size-cells = <2>;
-					#interrupt-cells = <1>;
-					ranges;
-					interrupt-map-mask = <0 0 0 0>;
-					interrupt-map = <0 0 0 0 &mpic 60>;
-					marvell,pcie-port = <0>;
-					marvell,pcie-lane = <2>;
-					clocks = <&gateclk 7>;
-					status = "disabled";
-				};
-
-				pcie@4,0 {
-					device_type = "pci";
-					assigned-addresses = <0x82002000 0 0x4c000 0 0x2000>;
-					reg = <0x2000 0 0 0 0>;
-					#address-cells = <3>;
-					#size-cells = <2>;
-					#interrupt-cells = <1>;
-					ranges;
-					interrupt-map-mask = <0 0 0 0>;
-					interrupt-map = <0 0 0 0 &mpic 61>;
-					marvell,pcie-port = <0>;
-					marvell,pcie-lane = <3>;
-					clocks = <&gateclk 8>;
-					status = "disabled";
-				};
-
-				pcie@5,0 {
-					device_type = "pci";
-					assigned-addresses = <0x82002800 0 0x80000 0 0x2000>;
-					reg = <0x2800 0 0 0 0>;
-					#address-cells = <3>;
-					#size-cells = <2>;
-					#interrupt-cells = <1>;
-					ranges;
-					interrupt-map-mask = <0 0 0 0>;
-					interrupt-map = <0 0 0 0 &mpic 62>;
-					marvell,pcie-port = <1>;
-					marvell,pcie-lane = <0>;
-					clocks = <&gateclk 9>;
-					status = "disabled";
-				};
-
-				pcie@6,0 {
-					device_type = "pci";
-					assigned-addresses = <0x82003000 0 0x84000 0 0x2000>;
-					reg = <0x3000 0 0 0 0>;
-					#address-cells = <3>;
-					#size-cells = <2>;
-					#interrupt-cells = <1>;
-					ranges;
-					interrupt-map-mask = <0 0 0 0>;
-					interrupt-map = <0 0 0 0 &mpic 63>;
-					marvell,pcie-port = <1>;
-					marvell,pcie-lane = <1>;
-					clocks = <&gateclk 10>;
-					status = "disabled";
-				};
-
-				pcie@7,0 {
-					device_type = "pci";
-					assigned-addresses = <0x82003800 0 0x88000 0 0x2000>;
-					reg = <0x3800 0 0 0 0>;
-					#address-cells = <3>;
-					#size-cells = <2>;
-					#interrupt-cells = <1>;
-					ranges;
-					interrupt-map-mask = <0 0 0 0>;
-					interrupt-map = <0 0 0 0 &mpic 64>;
-					marvell,pcie-port = <1>;
-					marvell,pcie-lane = <2>;
-					clocks = <&gateclk 11>;
-					status = "disabled";
-				};
-
-				pcie@8,0 {
-					device_type = "pci";
-					assigned-addresses = <0x82004000 0 0x8c000 0 0x2000>;
-					reg = <0x4000 0 0 0 0>;
-					#address-cells = <3>;
-					#size-cells = <2>;
-					#interrupt-cells = <1>;
-					ranges;
-					interrupt-map-mask = <0 0 0 0>;
-					interrupt-map = <0 0 0 0 &mpic 65>;
-					marvell,pcie-port = <1>;
-					marvell,pcie-lane = <3>;
-					clocks = <&gateclk 12>;
-					status = "disabled";
-				};
-				pcie@9,0 {
-					device_type = "pci";
-					assigned-addresses = <0x82004800 0 0x42000 0 0x2000>;
-					reg = <0x4800 0 0 0 0>;
-					#address-cells = <3>;
-					#size-cells = <2>;
-					#interrupt-cells = <1>;
-					ranges;
-					interrupt-map-mask = <0 0 0 0>;
-					interrupt-map = <0 0 0 0 &mpic 99>;
-					marvell,pcie-port = <2>;
-					marvell,pcie-lane = <0>;
-					clocks = <&gateclk 26>;
-					status = "disabled";
-				};
-
-				pcie@10,0 {
-					device_type = "pci";
-					assigned-addresses = <0x82005000 0 0x82000 0 0x2000>;
-					reg = <0x5000 0 0 0 0>;
-					#address-cells = <3>;
-					#size-cells = <2>;
-					#interrupt-cells = <1>;
-					ranges;
-					interrupt-map-mask = <0 0 0 0>;
-					interrupt-map = <0 0 0 0 &mpic 103>;
-					marvell,pcie-port = <3>;
-					marvell,pcie-lane = <0>;
-					clocks = <&gateclk 27>;
-					status = "disabled";
-				};
-			};
 		};
 	};
 };
diff --git a/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts b/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts
index 8f510458ea86..5695afcc04bf 100644
--- a/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts
+++ b/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts
@@ -11,7 +11,7 @@
  */
 
 /dts-v1/;
-/include/ "armada-xp-mv78260.dtsi"
+#include "armada-xp-mv78260.dtsi"
 
 / {
 	model = "PlatHome OpenBlocks AX3-4 board";
@@ -27,9 +27,46 @@
 	};
 
 	soc {
-		ranges = <0          0 0xd0000000 0x100000	/* Internal registers 1MiB */
-			  0xe0000000 0 0xe0000000 0x8100000     /* PCIe */
-			  0xf0000000 0 0xf0000000 0x8000000     /* Device Bus, NOR 128MiB   */>;
+		ranges = <MBUS_ID(0xf0, 0x01) 0 0 0xd0000000 0x100000
+			  MBUS_ID(0x01, 0x1d) 0 0 0xfff00000 0x100000
+			  MBUS_ID(0x01, 0x2f) 0 0 0xf0000000 0x8000000>;
+
+		devbus-bootcs {
+			status = "okay";
+
+			/* Device Bus parameters are required */
+
+			/* Read parameters */
+			devbus,bus-width    = <8>;
+			devbus,turn-off-ps  = <60000>;
+			devbus,badr-skew-ps = <0>;
+			devbus,acc-first-ps = <124000>;
+			devbus,acc-next-ps  = <248000>;
+			devbus,rd-setup-ps  = <0>;
+			devbus,rd-hold-ps   = <0>;
+
+			/* Write parameters */
+			devbus,sync-enable = <0>;
+			devbus,wr-high-ps  = <60000>;
+			devbus,wr-low-ps   = <60000>;
+			devbus,ale-wr-ps   = <60000>;
+
+			/* NOR 128 MiB */
+			nor@0 {
+				compatible = "cfi-flash";
+				reg = <0 0x8000000>;
+				bank-width = <2>;
+			};
+		};
+
+		pcie-controller {
+			status = "okay";
+			/* Internal mini-PCIe connector */
+			pcie@1,0 {
+				/* Port 0, Lane 0 */
+				status = "okay";
+			};
+		};
 
 		internal-regs {
 			serial@12000 {
@@ -148,49 +185,6 @@
 			usb@51000 {
 				status = "okay";
 			};
-
-			/* USB interface in the mini-PCIe connector */
-			usb@52000 {
-				status = "okay";
-			};
-
-			devbus-bootcs@10400 {
-				status = "okay";
-				ranges = <0 0xf0000000 0x8000000>; /* @addr 0xf000000, size 0x8000000 */
-
-				/* Device Bus parameters are required */
-
-				/* Read parameters */
-				devbus,bus-width    = <8>;
-				devbus,turn-off-ps  = <60000>;
-				devbus,badr-skew-ps = <0>;
-				devbus,acc-first-ps = <124000>;
-				devbus,acc-next-ps  = <248000>;
-				devbus,rd-setup-ps  = <0>;
-				devbus,rd-hold-ps   = <0>;
-
-				/* Write parameters */
-				devbus,sync-enable = <0>;
-				devbus,wr-high-ps  = <60000>;
-				devbus,wr-low-ps   = <60000>;
-				devbus,ale-wr-ps   = <60000>;
-
-				/* NOR 128 MiB */
-				nor@0 {
-					compatible = "cfi-flash";
-					reg = <0 0x8000000>;
-					bank-width = <2>;
-				};
-			};
-
-			pcie-controller {
-				status = "okay";
-				/* Internal mini-PCIe connector */
-				pcie@1,0 {
-					/* Port 0, Lane 0 */
-					status = "okay";
-				};
-			};
 		};
 	};
 };
diff --git a/arch/arm/boot/dts/armada-xp.dtsi b/arch/arm/boot/dts/armada-xp.dtsi
index 416eb9481844..3058522f5aad 100644
--- a/arch/arm/boot/dts/armada-xp.dtsi
+++ b/arch/arm/boot/dts/armada-xp.dtsi
@@ -16,7 +16,7 @@
  * common to all Armada SoCs.
  */
 
-/include/ "armada-370-xp.dtsi"
+#include "armada-370-xp.dtsi"
 
 / {
 	model = "Marvell Armada XP family SoC";
@@ -27,6 +27,13 @@
 	};
 
 	soc {
+		compatible = "marvell,armadaxp-mbus", "simple-bus";
+
+		bootrom {
+			compatible = "marvell,bootrom";
+			reg = <MBUS_ID(0x01, 0x1d) 0 0x100000>;
+		};
+
 		internal-regs {
 			L2: l2-cache {
 				compatible = "marvell,aurora-system-cache";
@@ -62,7 +69,9 @@
 			};
 
 			timer@20300 {
-				marvell,timer-25Mhz;
+				compatible = "marvell,armada-xp-timer";
+				clocks = <&coreclk 2>, <&refclk>;
+				clock-names = "nbclk", "fixed";
 			};
 
 			coreclk: mvebu-sar@18230 {
@@ -162,4 +171,13 @@
 			};
 		};
 	};
+
+	clocks {
+		/* 25 MHz reference crystal */
+		refclk: oscillator {
+			compatible = "fixed-clock";
+			#clock-cells = <0>;
+			clock-frequency = <25000000>;
+		};
+	};
 };
diff --git a/arch/arm/boot/dts/at91rm9200.dtsi b/arch/arm/boot/dts/at91rm9200.dtsi
index 92b9e21389db..f77065506f1e 100644
--- a/arch/arm/boot/dts/at91rm9200.dtsi
+++ b/arch/arm/boot/dts/at91rm9200.dtsi
@@ -120,6 +120,7 @@
 				interrupts = <10 IRQ_TYPE_LEVEL_HIGH 0>;
 				#address-cells = <1>;
 				#size-cells = <0>;
+				pinctrl-names = "default";
 				status = "disabled";
 			};
 
diff --git a/arch/arm/boot/dts/at91rm9200_pqfp.dtsi b/arch/arm/boot/dts/at91rm9200_pqfp.dtsi
new file mode 100644
index 000000000000..93ca66f80360
--- /dev/null
+++ b/arch/arm/boot/dts/at91rm9200_pqfp.dtsi
@@ -0,0 +1,17 @@
+/*
+ * at91rm9200_pqfp.dtsi - Device Tree Include file for AT91RM9200 PQFP family SoC
+ *
+ * Copyright (C) 2013 Jean-Christophe PLAGNIOL-VILLARD <plagnioj@jcrosoft.com>
+ *
+ * Licensed under GPLv2 or later.
+ */
+
+#include "at91rm9200.dtsi"
+
+/ {
+	compatible = "atmel,at91rm9200-pqfp", "atmel,at91rm9200";
+};
+
+&pioD {
+	status = "disabled";
+};
diff --git a/arch/arm/boot/dts/at91sam9260.dtsi b/arch/arm/boot/dts/at91sam9260.dtsi
index c7ccbcbffb3e..56ee8282a7a8 100644
--- a/arch/arm/boot/dts/at91sam9260.dtsi
+++ b/arch/arm/boot/dts/at91sam9260.dtsi
@@ -572,6 +572,7 @@
 				interrupts = <9 IRQ_TYPE_LEVEL_HIGH 0>;
 				#address-cells = <1>;
 				#size-cells = <0>;
+				pinctrl-names = "default";
 				status = "disabled";
 			};
 
diff --git a/arch/arm/boot/dts/at91sam9n12.dtsi b/arch/arm/boot/dts/at91sam9n12.dtsi
index bb7f564b3a55..9fb7ffd32af2 100644
--- a/arch/arm/boot/dts/at91sam9n12.dtsi
+++ b/arch/arm/boot/dts/at91sam9n12.dtsi
@@ -291,6 +291,22 @@
 					};
 				};
 
+				i2c0 {
+					pinctrl_i2c0: i2c0-0 {
+						atmel,pins =
+							<AT91_PIOA 30 AT91_PERIPH_A AT91_PINCTRL_NONE
+							 AT91_PIOA 31 AT91_PERIPH_A AT91_PINCTRL_NONE>;
+					};
+				};
+
+				i2c1 {
+					pinctrl_i2c1: i2c1-0 {
+						atmel,pins =
+							<AT91_PIOC 0 AT91_PERIPH_C AT91_PINCTRL_NONE
+							 AT91_PIOC 1 AT91_PERIPH_C AT91_PINCTRL_NONE>;
+					};
+				};
+
 				tcb0 {
 					pinctrl_tcb0_tclk0: tcb0_tclk0-0 {
 						atmel,pins = <AT91_PIOA 24 AT91_PERIPH_A AT91_PINCTRL_NONE>;
@@ -471,6 +487,8 @@
 				dma-names = "tx", "rx";
 				#address-cells = <1>;
 				#size-cells = <0>;
+				pinctrl-names = "default";
+				pinctrl-0 = <&pinctrl_i2c0>;
 				status = "disabled";
 			};
 
@@ -483,6 +501,8 @@
 				dma-names = "tx", "rx";
 				#address-cells = <1>;
 				#size-cells = <0>;
+				pinctrl-names = "default";
+				pinctrl-0 = <&pinctrl_i2c1>;
 				status = "disabled";
 			};
 
diff --git a/arch/arm/boot/dts/at91sam9n12ek.dts b/arch/arm/boot/dts/at91sam9n12ek.dts
index 3d77dbe406f4..27a9352b9d7a 100644
--- a/arch/arm/boot/dts/at91sam9n12ek.dts
+++ b/arch/arm/boot/dts/at91sam9n12ek.dts
@@ -40,6 +40,15 @@
 
 			i2c0: i2c@f8010000 {
 				status = "okay";
+
+				qt1070: keyboard@1b {
+					compatible = "qt1070";
+					reg = <0x1b>;
+					interrupt-parent = <&pioA>;
+					interrupts = <2 IRQ_TYPE_EDGE_FALLING>;
+					pinctrl-names = "default";
+					pinctrl-0 = <&pinctrl_qt1070_irq>;
+				};
 			};
 
 			i2c1: i2c@f8014000 {
@@ -66,6 +75,13 @@
 							<AT91_PIOA 7 AT91_PERIPH_GPIO AT91_PINCTRL_PULL_UP_DEGLITCH>;	/* PA7 gpio CD pin pull up and deglitch */
 					};
 				};
+
+				qt1070 {
+					pinctrl_qt1070_irq: qt1070_irq {
+						atmel,pins =
+							<AT91_PIOA 2 AT91_PERIPH_GPIO AT91_PINCTRL_PULL_UP_DEGLITCH>;
+					};
+				};
 			};
 
 			spi0: spi@f0000000 {
@@ -121,7 +137,7 @@
 
 		enter {
 			label = "Enter";
-			gpios = <&pioB 4 GPIO_ACTIVE_LOW>;
+			gpios = <&pioB 3 GPIO_ACTIVE_LOW>;
 			linux,code = <28>;
 			gpio-key,wakeup;
 		};
diff --git a/arch/arm/boot/dts/at91sam9x5.dtsi b/arch/arm/boot/dts/at91sam9x5.dtsi
index 57d45f5bea09..e74dc15efa9d 100644
--- a/arch/arm/boot/dts/at91sam9x5.dtsi
+++ b/arch/arm/boot/dts/at91sam9x5.dtsi
@@ -190,12 +190,12 @@
 							 AT91_PIOA 8 AT91_PERIPH_A AT91_PINCTRL_NONE>;	/* PA8 periph A */
 					};
 
-					pinctrl_uart2_rts: uart2_rts-0 {
+					pinctrl_usart2_rts: usart2_rts-0 {
 						atmel,pins =
 							<AT91_PIOB 0 AT91_PERIPH_B AT91_PINCTRL_NONE>;	/* PB0 periph B */
 					};
 
-					pinctrl_uart2_cts: uart2_cts-0 {
+					pinctrl_usart2_cts: usart2_cts-0 {
 						atmel,pins =
 							<AT91_PIOB 1 AT91_PERIPH_B AT91_PINCTRL_NONE>;	/* PB1 periph B */
 					};
@@ -542,6 +542,9 @@
 				compatible = "atmel,at91sam9g45-ssc";
 				reg = <0xf0010000 0x4000>;
 				interrupts = <28 IRQ_TYPE_LEVEL_HIGH 5>;
+				dmas = <&dma0 1 AT91_DMA_CFG_PER_ID(13)>,
+				       <&dma0 1 AT91_DMA_CFG_PER_ID(14)>;
+				dma-names = "tx", "rx";
 				pinctrl-names = "default";
 				pinctrl-0 = <&pinctrl_ssc0_tx &pinctrl_ssc0_rx>;
 				status = "disabled";
@@ -553,6 +556,7 @@
 				interrupts = <12 IRQ_TYPE_LEVEL_HIGH 0>;
 				dmas = <&dma0 1 AT91_DMA_CFG_PER_ID(0)>;
 				dma-names = "rxtx";
+				pinctrl-names = "default";
 				#address-cells = <1>;
 				#size-cells = <0>;
 				status = "disabled";
@@ -564,6 +568,7 @@
 				interrupts = <26 IRQ_TYPE_LEVEL_HIGH 0>;
 				dmas = <&dma1 1 AT91_DMA_CFG_PER_ID(0)>;
 				dma-names = "rxtx";
+				pinctrl-names = "default";
 				#address-cells = <1>;
 				#size-cells = <0>;
 				status = "disabled";
diff --git a/arch/arm/boot/dts/at91sam9x5ek.dtsi b/arch/arm/boot/dts/at91sam9x5ek.dtsi
index 49e3c45818c2..3a9f6fa4a36a 100644
--- a/arch/arm/boot/dts/at91sam9x5ek.dtsi
+++ b/arch/arm/boot/dts/at91sam9x5ek.dtsi
@@ -59,6 +59,11 @@
 
 			i2c0: i2c@f8010000 {
 				status = "okay";
+
+				wm8731: wm8731@1a {
+					compatible = "wm8731";
+					reg = <0x1a>;
+				};
 			};
 
 			pinctrl@fffff400 {
@@ -90,6 +95,10 @@
 			watchdog@fffffe40 {
 				status = "okay";
 			};
+
+			ssc0: ssc@f0010000 {
+				status = "okay";
+			};
 		};
 
 		usb0: ohci@00600000 {
@@ -105,4 +114,19 @@
 			status = "okay";
 		};
 	};
+
+	sound {
+		compatible = "atmel,sam9x5-wm8731-audio";
+
+		atmel,model = "wm8731 @ AT91SAM9X5EK";
+
+		atmel,audio-routing =
+			"Headphone Jack", "RHPOUT",
+			"Headphone Jack", "LHPOUT",
+			"LLINEIN", "Line In Jack",
+			"RLINEIN", "Line In Jack";
+
+		atmel,ssc-controller = <&ssc0>;
+		atmel,audio-codec = <&wm8731>;
+	};
 };
diff --git a/arch/arm/boot/dts/atlas6.dtsi b/arch/arm/boot/dts/atlas6.dtsi
index a0f2721ea583..6db4f81d4795 100644
--- a/arch/arm/boot/dts/atlas6.dtsi
+++ b/arch/arm/boot/dts/atlas6.dtsi
@@ -181,6 +181,8 @@
 				interrupts = <17>;
 				fifosize = <128>;
 				clocks = <&clks 13>;
+				sirf,uart-dma-rx-channel = <21>;
+				sirf,uart-dma-tx-channel = <2>;
 			};
 
 			uart1: uart@b0060000 {
@@ -199,6 +201,8 @@
 				interrupts = <19>;
 				fifosize = <128>;
 				clocks = <&clks 15>;
+				sirf,uart-dma-rx-channel = <6>;
+				sirf,uart-dma-tx-channel = <7>;
 			};
 
 			usp0: usp@b0080000 {
@@ -206,7 +210,10 @@
 				compatible = "sirf,prima2-usp";
 				reg = <0xb0080000 0x10000>;
 				interrupts = <20>;
+				fifosize = <128>;
 				clocks = <&clks 28>;
+				sirf,usp-dma-rx-channel = <17>;
+				sirf,usp-dma-tx-channel = <18>;
 			};
 
 			usp1: usp@b0090000 {
@@ -214,7 +221,10 @@
 				compatible = "sirf,prima2-usp";
 				reg = <0xb0090000 0x10000>;
 				interrupts = <21>;
+				fifosize = <128>;
 				clocks = <&clks 29>;
+				sirf,usp-dma-rx-channel = <14>;
+				sirf,usp-dma-tx-channel = <15>;
 			};
 
 			dmac0: dma-controller@b00b0000 {
@@ -237,6 +247,8 @@
 				compatible = "sirf,prima2-vip";
 				reg = <0xb00C0000 0x10000>;
 				clocks = <&clks 31>;
+				interrupts = <14>;
+				sirf,vip-dma-rx-channel = <16>;
 			};
 
 			spi0: spi@b00d0000 {
@@ -329,6 +341,12 @@
 						sirf,function = "uart0";
 					};
 				};
+				uart0_noflow_pins_a: uart0@1 {
+					uart {
+						sirf,pins = "uart0_nostreamctrlgrp";
+						sirf,function = "uart0_nostreamctrl";
+					};
+				};
 				uart1_pins_a: uart1@0 {
 					uart {
 						sirf,pins = "uart1grp";
diff --git a/arch/arm/boot/dts/bcm11351-brt.dts b/arch/arm/boot/dts/bcm11351-brt.dts
index 67ec524098b5..9d36eb4e3c41 100644
--- a/arch/arm/boot/dts/bcm11351-brt.dts
+++ b/arch/arm/boot/dts/bcm11351-brt.dts
@@ -17,7 +17,7 @@
 
 / {
 	model = "BCM11351 BRT board";
-	compatible = "bcm,bcm11351-brt", "bcm,bcm11351";
+	compatible = "brcm,bcm11351-brt", "brcm,bcm11351";
 
 	memory {
 		reg = <0x80000000 0x40000000>; /* 1 GB */
@@ -27,18 +27,18 @@
 		status = "okay";
 	};
 
-	sdio0: sdio@0x3f180000 {
+	sdio1: sdio@3f180000 {
 		max-frequency = <48000000>;
 		status = "okay";
 	};
 
-	sdio1: sdio@0x3f190000 {
+	sdio2: sdio@3f190000 {
 		non-removable;
 		max-frequency = <48000000>;
 		status = "okay";
 	};
 
-	sdio3: sdio@0x3f1b0000 {
+	sdio4: sdio@3f1b0000 {
 		max-frequency = <48000000>;
 		status = "okay";
 	};
diff --git a/arch/arm/boot/dts/bcm11351.dtsi b/arch/arm/boot/dts/bcm11351.dtsi
index c0cdf66f8964..05a5aabe3b2c 100644
--- a/arch/arm/boot/dts/bcm11351.dtsi
+++ b/arch/arm/boot/dts/bcm11351.dtsi
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2012 Broadcom Corporation
+ * Copyright (C) 2012-2013 Broadcom Corporation
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License as
@@ -18,7 +18,7 @@
 
 / {
 	model = "BCM11351 SoC";
-	compatible = "bcm,bcm11351";
+	compatible = "brcm,bcm11351";
 	interrupt-parent = <&gic>;
 
 	chosen {
@@ -35,12 +35,12 @@
 	};
 
 	smc@0x3404c000 {
-		compatible = "bcm,bcm11351-smc", "bcm,kona-smc";
+		compatible = "brcm,bcm11351-smc", "brcm,kona-smc";
 		reg = <0x3404c000 0x400>; /* 1 KiB in SRAM */
 	};
 
 	uart@3e000000 {
-		compatible = "bcm,bcm11351-dw-apb-uart", "snps,dw-apb-uart";
+		compatible = "brcm,bcm11351-dw-apb-uart", "snps,dw-apb-uart";
 		status = "disabled";
 		reg = <0x3e000000 0x1000>;
 		clock-frequency = <13000000>;
@@ -50,42 +50,47 @@
 	};
 
 	L2: l2-cache {
-		compatible = "bcm,bcm11351-a2-pl310-cache";
+		compatible = "brcm,bcm11351-a2-pl310-cache";
 		reg = <0x3ff20000 0x1000>;
 		cache-unified;
 		cache-level = <2>;
 	};
 
+	watchdog@35002f40 {
+		compatible = "brcm,bcm11351-wdt", "brcm,kona-wdt";
+		reg = <0x35002f40 0x6c>;
+	};
+
 	timer@35006000 {
-		compatible = "bcm,kona-timer";
+		compatible = "brcm,kona-timer";
 		reg = <0x35006000 0x1000>;
 		interrupts = <GIC_SPI 7 IRQ_TYPE_LEVEL_HIGH>;
 		clock-frequency = <32768>;
 	};
 
-	sdio0: sdio@0x3f180000 {
-		compatible = "bcm,kona-sdhci";
+	sdio1: sdio@3f180000 {
+		compatible = "brcm,kona-sdhci";
 		reg = <0x3f180000 0x10000>;
 		interrupts = <0x0 77 0x4>;
 		status = "disabled";
 	};
 
-	sdio1: sdio@0x3f190000 {
-		compatible = "bcm,kona-sdhci";
+	sdio2: sdio@3f190000 {
+		compatible = "brcm,kona-sdhci";
 		reg = <0x3f190000 0x10000>;
 		interrupts = <0x0 76 0x4>;
 		status = "disabled";
 	};
 
-	sdio2: sdio@0x3f1a0000 {
-		compatible = "bcm,kona-sdhci";
+	sdio3: sdio@3f1a0000 {
+		compatible = "brcm,kona-sdhci";
 		reg = <0x3f1a0000 0x10000>;
 		interrupts = <0x0 74 0x4>;
 		status = "disabled";
 	};
 
-	sdio3: sdio@0x3f1b0000 {
-		compatible = "bcm,kona-sdhci";
+	sdio4: sdio@3f1b0000 {
+		compatible = "brcm,kona-sdhci";
 		reg = <0x3f1b0000 0x10000>;
 		interrupts = <0x0 73 0x4>;
 		status = "disabled";
diff --git a/arch/arm/boot/dts/bcm28155-ap.dts b/arch/arm/boot/dts/bcm28155-ap.dts
new file mode 100644
index 000000000000..96ae67a2f0d3
--- /dev/null
+++ b/arch/arm/boot/dts/bcm28155-ap.dts
@@ -0,0 +1,45 @@
+/*
+ * Copyright (C) 2013 Broadcom Corporation
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation version 2.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any
+ * kind, whether express or implied; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+/dts-v1/;
+
+#include "bcm11351.dtsi"
+
+/ {
+	model = "BCM28155 AP board";
+	compatible = "brcm,bcm28155-ap", "brcm,bcm11351";
+
+	memory {
+		reg = <0x80000000 0x40000000>; /* 1 GB */
+	};
+
+	uart@3e000000 {
+		status = "okay";
+	};
+
+	sdio1: sdio@3f180000 {
+		max-frequency = <48000000>;
+		status = "okay";
+	};
+
+	sdio2: sdio@3f190000 {
+		non-removable;
+		max-frequency = <48000000>;
+		status = "okay";
+	};
+
+	sdio4: sdio@3f1b0000 {
+		max-frequency = <48000000>;
+		status = "okay";
+	};
+};
diff --git a/arch/arm/boot/dts/ccu8540.dts b/arch/arm/boot/dts/ccu8540.dts
deleted file mode 100644
index 48ff03441f5a..000000000000
--- a/arch/arm/boot/dts/ccu8540.dts
+++ /dev/null
@@ -1,41 +0,0 @@
-/*
- * Copyright 2013 ST-Ericsson AB
- *
- * The code contained herein is licensed under the GNU General Public
- * License. You may obtain a copy of the GNU General Public License
- * Version 2 or later at the following locations:
- *
- * http://www.opensource.org/licenses/gpl-license.html
- * http://www.gnu.org/copyleft/gpl.html
- */
-
-/dts-v1/;
-#include "dbx5x0.dtsi"
-
-/ {
-	model = "ST-Ericsson U8540 platform with Device Tree";
-	compatible = "st-ericsson,ccu8540", "st-ericsson,u8540";
-
-	memory@0 {
-		reg = <0x20000000 0x1f000000>, <0xc0000000 0x3f000000>;
-	};
-
-	soc {
-		prcmu@80157000 {
-			reg = <0x80157000 0x2000>, <0x801b0000 0x8000>, <0x801b8000 0x3000>;
-			reg-names = "prcmu", "prcmu-tcpm", "prcmu-tcdm";
-		};
-
-		uart@80120000 {
-			status = "okay";
-		};
-
-		uart@80121000 {
-			status = "okay";
-		};
-
-		uart@80007000 {
-			status = "okay";
-		};
-	};
-};
diff --git a/arch/arm/boot/dts/da850-evm.dts b/arch/arm/boot/dts/da850-evm.dts
index 5bce7cc55cf3..588ce58a2959 100644
--- a/arch/arm/boot/dts/da850-evm.dts
+++ b/arch/arm/boot/dts/da850-evm.dts
@@ -90,6 +90,17 @@
 				};
 			};
 		};
+		mdio: mdio@1e24000 {
+			status = "okay";
+			pinctrl-names = "default";
+			pinctrl-0 = <&mdio_pins>;
+			bus_freq = <2200000>;
+		};
+		eth0: ethernet@1e20000 {
+			status = "okay";
+			pinctrl-names = "default";
+			pinctrl-0 = <&mii_pins>;
+		};
 	};
 	nand_cs3@62000000 {
 		status = "okay";
diff --git a/arch/arm/boot/dts/da850.dtsi b/arch/arm/boot/dts/da850.dtsi
index d70ba5504481..8d17346f9702 100644
--- a/arch/arm/boot/dts/da850.dtsi
+++ b/arch/arm/boot/dts/da850.dtsi
@@ -125,11 +125,33 @@
 					0x14 0x00000010 0x000000f0
 				>;
 			};
+			mdio_pins: pinmux_mdio_pins {
+				pinctrl-single,bits = <
+					/* MDIO_CLK, MDIO_D */
+					0x10 0x00000088 0x000000ff
+				>;
+			};
+			mii_pins: pinmux_mii_pins {
+				pinctrl-single,bits = <
+					/*
+					 * MII_TXEN, MII_TXCLK, MII_COL
+					 * MII_TXD_3, MII_TXD_2, MII_TXD_1
+					 * MII_TXD_0
+					 */
+					0x8 0x88888880 0xfffffff0
+					/*
+					 * MII_RXER, MII_CRS, MII_RXCLK
+					 * MII_RXDV, MII_RXD_3, MII_RXD_2
+					 * MII_RXD_1, MII_RXD_0
+					 */
+					0xc 0x88888888 0xffffffff
+				>;
+			};
+
 		};
 		serial0: serial@1c42000 {
 			compatible = "ns16550a";
 			reg = <0x42000 0x100>;
-			clock-frequency = <150000000>;
 			reg-shift = <2>;
 			interrupts = <25>;
 			status = "disabled";
@@ -137,7 +159,6 @@
 		serial1: serial@1d0c000 {
 			compatible = "ns16550a";
 			reg = <0x10c000 0x100>;
-			clock-frequency = <150000000>;
 			reg-shift = <2>;
 			interrupts = <53>;
 			status = "disabled";
@@ -145,7 +166,6 @@
 		serial2: serial@1d0d000 {
 			compatible = "ns16550a";
 			reg = <0x10d000 0x100>;
-			clock-frequency = <150000000>;
 			reg-shift = <2>;
 			interrupts = <61>;
 			status = "disabled";
@@ -216,6 +236,26 @@
 			interrupts = <56>;
 			status = "disabled";
 		};
+		mdio: mdio@1e24000 {
+			compatible = "ti,davinci_mdio";
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0x224000 0x1000>;
+		};
+		eth0: ethernet@1e20000 {
+			compatible = "ti,davinci-dm6467-emac";
+			reg = <0x220000 0x4000>;
+			ti,davinci-ctrl-reg-offset = <0x3000>;
+			ti,davinci-ctrl-mod-reg-offset = <0x2000>;
+			ti,davinci-ctrl-ram-offset = <0>;
+			ti,davinci-ctrl-ram-size = <0x2000>;
+			local-mac-address = [ 00 00 00 00 00 00 ];
+			interrupts = <33
+					34
+					35
+					36
+					>;
+		};
 	};
 	nand_cs3@62000000 {
 		compatible = "ti,davinci-nand";
diff --git a/arch/arm/boot/dts/dove-cubox.dts b/arch/arm/boot/dts/dove-cubox.dts
index 5cae2ab69762..022646ef4b38 100644
--- a/arch/arm/boot/dts/dove-cubox.dts
+++ b/arch/arm/boot/dts/dove-cubox.dts
@@ -42,6 +42,8 @@
 			regulator-always-on;
 			regulator-boot-on;
 			gpio = <&gpio0 1 0>;
+			pinctrl-0 = <&pmx_gpio_1>;
+			pinctrl-names = "default";
 		};
 	};
 
@@ -53,10 +55,24 @@
 			clock-frequency = <25000000>;
 		};
 	};
+
+	ir_recv: ir-receiver {
+		compatible = "gpio-ir-receiver";
+		gpios = <&gpio0 19 1>;
+		pinctrl-0 = <&pmx_gpio_19>;
+		pinctrl-names = "default";
+	};
 };
 
 &uart0 { status = "okay"; };
 &sata0 { status = "okay"; };
+&mdio { status = "okay"; };
+&eth { status = "okay"; };
+
+&ethphy {
+	compatible = "marvell,88e1310";
+	reg = <1>;
+};
 
 &i2c0 {
 	status = "okay";
@@ -103,6 +119,7 @@
 	status = "okay";
 	/* sdio0 card detect is connected to wrong pin on CuBox */
 	cd-gpios = <&gpio0 12 1>;
+	pinctrl-0 = <&pmx_sdio0 &pmx_gpio_12>;
 };
 
 &spi0 {
@@ -115,23 +132,3 @@
 		reg = <0>;
 	};
 };
-
-&pinctrl {
-	pinctrl-0 = <&pmx_gpio_1 &pmx_gpio_12>;
-	pinctrl-names = "default";
-
-	pmx_gpio_1: pmx-gpio-1 {
-		marvell,pins = "mpp1";
-		marvell,function = "gpio";
-	};
-
-	pmx_gpio_12: pmx-gpio-12 {
-		marvell,pins = "mpp12";
-		marvell,function = "gpio";
-	};
-
-	pmx_gpio_18: pmx-gpio-18 {
-		marvell,pins = "mpp18";
-		marvell,function = "gpio";
-	};
-};
diff --git a/arch/arm/boot/dts/dove-d2plug.dts b/arch/arm/boot/dts/dove-d2plug.dts
new file mode 100644
index 000000000000..e2222ce94f2f
--- /dev/null
+++ b/arch/arm/boot/dts/dove-d2plug.dts
@@ -0,0 +1,69 @@
+/dts-v1/;
+
+/include/ "dove.dtsi"
+
+/ {
+	model = "Globalscale D2Plug";
+	compatible = "globalscale,d2plug", "marvell,dove";
+
+	memory {
+		device_type = "memory";
+		reg = <0x00000000 0x40000000>;
+	};
+
+	chosen {
+		bootargs = "console=ttyS0,115200n8 earlyprintk";
+	};
+
+	leds {
+		compatible = "gpio-leds";
+		pinctrl-0 = <&pmx_gpio_0 &pmx_gpio_1 &pmx_gpio_2>;
+		pinctrl-names = "default";
+
+		wlan-ap {
+			label = "wlan-ap";
+			gpios = <&gpio0 0 1>;
+		};
+
+		wlan-act {
+			label = "wlan-act";
+			gpios = <&gpio0 1 1>;
+		};
+
+		bluetooth-act {
+			label = "bt-act";
+			gpios = <&gpio0 2 1>;
+		};
+	};
+};
+
+&uart0 { status = "okay"; };
+&sata0 { status = "okay"; };
+&i2c0 { status = "okay"; };
+&mdio { status = "okay"; };
+&eth { status = "okay"; };
+
+/* Samsung M8G2F eMMC */
+&sdio0 {
+	status = "okay";
+	non-removable;
+	bus-width = <4>;
+};
+
+/* Marvell SD8787 WLAN/BT */
+&sdio1 {
+	status = "okay";
+	non-removable;
+	bus-width = <4>;
+};
+
+&spi0 {
+	status = "okay";
+
+	/* spi0.0: 4M Flash Macronix MX25L3205D */
+	spi-flash@0 {
+		compatible = "st,m25l3205d";
+		spi-max-frequency = <20000000>;
+		reg = <0>;
+	};
+};
diff --git a/arch/arm/boot/dts/dove.dtsi b/arch/arm/boot/dts/dove.dtsi
index 6cab46849cdb..cc279166646f 100644
--- a/arch/arm/boot/dts/dove.dtsi
+++ b/arch/arm/boot/dts/dove.dtsi
@@ -10,6 +10,23 @@
 		gpio2 = &gpio2;
 	};
 
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cpu0: cpu@0 {
+			compatible = "marvell,pj4a", "marvell,sheeva-v7";
+			device_type = "cpu";
+			next-level-cache = <&l2>;
+			reg = <0>;
+		};
+	};
+
+	l2: l2-cache {
+		compatible = "marvell,tauros2-cache";
+		marvell,tauros2-cache-features = <0>;
+	};
+
 	soc@f1000000 {
 		compatible = "simple-bus";
 		#address-cells = <1>;
@@ -25,16 +42,28 @@
 		          0xf2100000 0xf2100000 0x0100000   /* PCIe0 I/O   1M */
 		          0xf8000000 0xf8000000 0x8000000>; /* BootROM   128M */
 
-		l2: l2-cache {
-			compatible = "marvell,tauros2-cache";
-			marvell,tauros2-cache-features = <0>;
+		timer: timer@20300 {
+			compatible = "marvell,orion-timer";
+			reg = <0x20300 0x20>;
+			interrupt-parent = <&bridge_intc>;
+			interrupts = <1>, <2>;
+			clocks = <&core_clk 0>;
 		};
 
-		intc: interrupt-controller {
+		intc: main-interrupt-ctrl@20200 {
 			compatible = "marvell,orion-intc";
 			interrupt-controller;
 			#interrupt-cells = <1>;
-			reg = <0x20204 0x04>, <0x20214 0x04>;
+			reg = <0x20200 0x10>, <0x20210 0x10>;
+		};
+
+		bridge_intc: bridge-interrupt-ctrl@20110 {
+			compatible = "marvell,orion-bridge-intc";
+			interrupt-controller;
+			#interrupt-cells = <1>;
+			reg = <0x20110 0x8>;
+			interrupts = <0>;
+			marvell,#interrupts = <5>;
 		};
 
 		core_clk: core-clocks@d0214 {
@@ -43,14 +72,14 @@
 			#clock-cells = <1>;
 		};
 
-		gate_clk: clock-gating-control@d0038 {
+		gate_clk: clock-gating-ctrl@d0038 {
 			compatible = "marvell,dove-gating-clock";
 			reg = <0xd0038 0x4>;
 			clocks = <&core_clk 0>;
 			#clock-cells = <1>;
 		};
 
-		thermal: thermal@d001c {
+		thermal: thermal-diode@d001c {
 			compatible = "marvell,dove-thermal";
 			reg = <0xd001c 0x0c>, <0xd005c 0x08>;
 		};
@@ -70,6 +99,8 @@
 			reg-shift = <2>;
 			interrupts = <8>;
 			clocks = <&core_clk 0>;
+			pinctrl-0 = <&pmx_uart1>;
+			pinctrl-names = "default";
 			status = "disabled";
 		};
 
@@ -91,7 +122,7 @@
 			status = "disabled";
 		};
 
-		gpio0: gpio@d0400 {
+		gpio0: gpio-ctrl@d0400 {
 			compatible = "marvell,orion-gpio";
 			#gpio-cells = <2>;
 			gpio-controller;
@@ -102,7 +133,7 @@
 			interrupts = <12>, <13>, <14>, <60>;
 		};
 
-		gpio1: gpio@d0420 {
+		gpio1: gpio-ctrl@d0420 {
 			compatible = "marvell,orion-gpio";
 			#gpio-cells = <2>;
 			gpio-controller;
@@ -113,7 +144,7 @@
 			interrupts = <61>;
 		};
 
-		gpio2: gpio@e8400 {
+		gpio2: gpio-ctrl@e8400 {
 			compatible = "marvell,orion-gpio";
 			#gpio-cells = <2>;
 			gpio-controller;
@@ -121,13 +152,188 @@
 			ngpios = <8>;
 		};
 
-		pinctrl: pinctrl@d0200 {
+		pinctrl: pin-ctrl@d0200 {
 			compatible = "marvell,dove-pinctrl";
 			reg = <0xd0200 0x10>;
 			clocks = <&gate_clk 22>;
+
+			pmx_gpio_0: pmx-gpio-0 {
+				marvell,pins = "mpp0";
+				marvell,function = "gpio";
+			};
+
+			pmx_gpio_1: pmx-gpio-1 {
+				marvell,pins = "mpp1";
+				marvell,function = "gpio";
+			};
+
+			pmx_gpio_2: pmx-gpio-2 {
+				marvell,pins = "mpp2";
+				marvell,function = "gpio";
+			};
+
+			pmx_gpio_3: pmx-gpio-3 {
+				marvell,pins = "mpp3";
+				marvell,function = "gpio";
+			};
+
+			pmx_gpio_4: pmx-gpio-4 {
+				marvell,pins = "mpp4";
+				marvell,function = "gpio";
+			};
+
+			pmx_gpio_5: pmx-gpio-5 {
+				marvell,pins = "mpp5";
+				marvell,function = "gpio";
+			};
+
+			pmx_gpio_6: pmx-gpio-6 {
+				marvell,pins = "mpp6";
+				marvell,function = "gpio";
+			};
+
+			pmx_gpio_7: pmx-gpio-7 {
+				marvell,pins = "mpp7";
+				marvell,function = "gpio";
+			};
+
+			pmx_gpio_8: pmx-gpio-8 {
+				marvell,pins = "mpp8";
+				marvell,function = "gpio";
+			};
+
+			pmx_gpio_9: pmx-gpio-9 {
+				marvell,pins = "mpp9";
+				marvell,function = "gpio";
+			};
+
+			pmx_gpio_10: pmx-gpio-10 {
+				marvell,pins = "mpp10";
+				marvell,function = "gpio";
+			};
+
+			pmx_gpio_11: pmx-gpio-11 {
+				marvell,pins = "mpp11";
+				marvell,function = "gpio";
+			};
+
+			pmx_gpio_12: pmx-gpio-12 {
+				marvell,pins = "mpp12";
+				marvell,function = "gpio";
+			};
+
+			pmx_gpio_13: pmx-gpio-13 {
+				marvell,pins = "mpp13";
+				marvell,function = "gpio";
+			};
+
+			pmx_gpio_14: pmx-gpio-14 {
+				marvell,pins = "mpp14";
+				marvell,function = "gpio";
+			};
+
+			pmx_gpio_15: pmx-gpio-15 {
+				marvell,pins = "mpp15";
+				marvell,function = "gpio";
+			};
+
+			pmx_gpio_16: pmx-gpio-16 {
+				marvell,pins = "mpp16";
+				marvell,function = "gpio";
+			};
+
+			pmx_gpio_17: pmx-gpio-17 {
+				marvell,pins = "mpp17";
+				marvell,function = "gpio";
+			};
+
+			pmx_gpio_18: pmx-gpio-18 {
+				marvell,pins = "mpp18";
+				marvell,function = "gpio";
+			};
+
+			pmx_gpio_19: pmx-gpio-19 {
+				marvell,pins = "mpp19";
+				marvell,function = "gpio";
+			};
+
+			pmx_gpio_20: pmx-gpio-20 {
+				marvell,pins = "mpp20";
+				marvell,function = "gpio";
+			};
+
+			pmx_gpio_21: pmx-gpio-21 {
+				marvell,pins = "mpp21";
+				marvell,function = "gpio";
+			};
+
+			pmx_camera: pmx-camera {
+				marvell,pins = "mpp_camera";
+				marvell,function = "camera";
+			};
+
+			pmx_camera_gpio: pmx-camera-gpio {
+				marvell,pins = "mpp_camera";
+				marvell,function = "gpio";
+			};
+
+			pmx_sdio0: pmx-sdio0 {
+				marvell,pins = "mpp_sdio0";
+				marvell,function = "sdio0";
+			};
+
+			pmx_sdio0_gpio: pmx-sdio0-gpio {
+				marvell,pins = "mpp_sdio0";
+				marvell,function = "gpio";
+			};
+
+			pmx_sdio1: pmx-sdio1 {
+				marvell,pins = "mpp_sdio1";
+				marvell,function = "sdio1";
+			};
+
+			pmx_sdio1_gpio: pmx-sdio1-gpio {
+				marvell,pins = "mpp_sdio1";
+				marvell,function = "gpio";
+			};
+
+			pmx_audio1_gpio: pmx-audio1-gpio {
+				marvell,pins = "mpp_audio1";
+				marvell,function = "gpio";
+			};
+
+			pmx_spi0: pmx-spi0 {
+				marvell,pins = "mpp_spi0";
+				marvell,function = "spi0";
+			};
+
+			pmx_spi0_gpio: pmx-spi0-gpio {
+				marvell,pins = "mpp_spi0";
+				marvell,function = "gpio";
+			};
+
+			pmx_uart1: pmx-uart1 {
+				marvell,pins = "mpp_uart1";
+				marvell,function = "uart1";
+			};
+
+			pmx_uart1_gpio: pmx-uart1-gpio {
+				marvell,pins = "mpp_uart1";
+				marvell,function = "gpio";
+			};
+
+			pmx_nand: pmx-nand {
+				marvell,pins = "mpp_nand";
+				marvell,function = "nand";
+			};
+
+			pmx_nand_gpo: pmx-nand-gpo {
+				marvell,pins = "mpp_nand";
+				marvell,function = "gpo";
+			};
 		};
 
-		spi0: spi@10600 {
+		spi0: spi-ctrl@10600 {
 			compatible = "marvell,orion-spi";
 			#address-cells = <1>;
 			#size-cells = <0>;
@@ -135,10 +341,12 @@
 			interrupts = <6>;
 			reg = <0x10600 0x28>;
 			clocks = <&core_clk 0>;
+			pinctrl-0 = <&pmx_spi0>;
+			pinctrl-names = "default";
 			status = "disabled";
 		};
 
-		spi1: spi@14600 {
+		spi1: spi-ctrl@14600 {
 			compatible = "marvell,orion-spi";
 			#address-cells = <1>;
 			#size-cells = <0>;
@@ -149,7 +357,7 @@
 			status = "disabled";
 		};
 
-		i2c0: i2c@11000 {
+		i2c0: i2c-ctrl@11000 {
 			compatible = "marvell,mv64xxx-i2c";
 			reg = <0x11000 0x20>;
 			#address-cells = <1>;
@@ -177,23 +385,27 @@
 			status = "okay";
 		};
 
-		sdio0: sdio@92000 {
+		sdio0: sdio-host@92000 {
 			compatible = "marvell,dove-sdhci";
 			reg = <0x92000 0x100>;
 			interrupts = <35>, <37>;
 			clocks = <&gate_clk 8>;
+			pinctrl-0 = <&pmx_sdio0>;
+			pinctrl-names = "default";
 			status = "disabled";
 		};
 
-		sdio1: sdio@90000 {
+		sdio1: sdio-host@90000 {
 			compatible = "marvell,dove-sdhci";
 			reg = <0x90000 0x100>;
 			interrupts = <36>, <38>;
 			clocks = <&gate_clk 9>;
+			pinctrl-0 = <&pmx_sdio1>;
+			pinctrl-names = "default";
 			status = "disabled";
 		};
 
-		sata0: sata@a0000 {
+		sata0: sata-host@a0000 {
 			compatible = "marvell,orion-sata";
 			reg = <0xa0000 0x2400>;
 			interrupts = <62>;
@@ -202,12 +414,12 @@
 			status = "disabled";
 		};
 
-		rtc@d8500 {
+		rtc: real-time-clock@d8500 {
 			compatible = "marvell,orion-rtc";
 			reg = <0xd8500 0x20>;
 		};
 
-		crypto: crypto@30000 {
+		crypto: crypto-engine@30000 {
 			compatible = "marvell,orion-crypto";
 			reg = <0x30000 0x10000>,
 			      <0xc8000000 0x800>;
@@ -258,5 +470,40 @@
 				dmacap,xor;
 			};
 		};
+
+		mdio: mdio-bus@72004 {
+			compatible = "marvell,orion-mdio";
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0x72004 0x84>;
+			interrupts = <30>;
+			clocks = <&gate_clk 2>;
+			status = "disabled";
+
+			ethphy: ethernet-phy {
+				device-type = "ethernet-phy";
+				/* set phy address in board file */
+			};
+		};
+
+		eth: ethernet-controller@72000 {
+			compatible = "marvell,orion-eth";
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0x72000 0x4000>;
+			clocks = <&gate_clk 2>;
+			marvell,tx-checksum-limit = <1600>;
+			status = "disabled";
+
+			ethernet-port@0 {
+				device_type = "network";
+				compatible = "marvell,orion-eth-port";
+				reg = <0>;
+				interrupts = <29>;
+				/* overwrite MAC address in bootloader */
+				local-mac-address = [00 00 00 00 00 00];
+				phy-handle = <&ethphy>;
+			};
+		};
 	};
 };
diff --git a/arch/arm/boot/dts/emev2-kzm9d-reference.dts b/arch/arm/boot/dts/emev2-kzm9d-reference.dts
new file mode 100644
index 000000000000..cceefda268b6
--- /dev/null
+++ b/arch/arm/boot/dts/emev2-kzm9d-reference.dts
@@ -0,0 +1,57 @@
+/*
+ * Device Tree Source for the KZM9D board
+ *
+ * Copyright (C) 2013 Renesas Solutions Corp.
+ *
+ * This file is licensed under the terms of the GNU General Public License
+ * version 2.  This program is licensed "as is" without any warranty of any
+ * kind, whether express or implied.
+ */
+/dts-v1/;
+
+/include/ "emev2.dtsi"
+
+/ {
+	model = "EMEV2 KZM9D Board";
+	compatible = "renesas,kzm9d-reference", "renesas,emev2";
+
+	memory {
+		device_type = "memory";
+		reg = <0x40000000 0x8000000>;
+	};
+
+	chosen {
+		bootargs = "console=ttyS1,115200n81 ignore_loglevel root=/dev/nfs ip=dhcp";
+	};
+
+	reg_1p8v: regulator@0 {
+		compatible = "regulator-fixed";
+		regulator-name = "fixed-1.8V";
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <1800000>;
+		regulator-always-on;
+		regulator-boot-on;
+	};
+
+	reg_3p3v: regulator@1 {
+		compatible = "regulator-fixed";
+		regulator-name = "fixed-3.3V";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		regulator-always-on;
+		regulator-boot-on;
+	};
+
+	lan9220@20000000 {
+		compatible = "smsc,lan9220", "smsc,lan9115";
+		reg = <0x20000000 0x10000>;
+		phy-mode = "mii";
+		interrupt-parent = <&gpio0>;
+		interrupts = <1 1>;	/* active high */
+		reg-io-width = <4>;
+		smsc,irq-active-high;
+		smsc,irq-push-pull;
+		vddvario-supply = <&reg_1p8v>;
+		vdd33a-supply = <&reg_3p3v>;
+	};
+};
diff --git a/arch/arm/boot/dts/emev2-kzm9d.dts b/arch/arm/boot/dts/emev2-kzm9d.dts
index b9b3241f173b..f92e812fdd9f 100644
--- a/arch/arm/boot/dts/emev2-kzm9d.dts
+++ b/arch/arm/boot/dts/emev2-kzm9d.dts
@@ -21,6 +21,6 @@
 	};
 
 	chosen {
-		bootargs = "console=tty0 console=ttyS1,115200n81 earlyprintk=serial8250-em.1,115200n81 mem=128M@0x40000000 ignore_loglevel root=/dev/nfs ip=dhcp nfsroot=,rsize=4096,wsize=4096";
+		bootargs = "console=ttyS1,115200n81 ignore_loglevel root=/dev/nfs ip=dhcp";
 	};
 };
diff --git a/arch/arm/boot/dts/emev2.dtsi b/arch/arm/boot/dts/emev2.dtsi
index c8a8c08b48dd..9063a4434d6a 100644
--- a/arch/arm/boot/dts/emev2.dtsi
+++ b/arch/arm/boot/dts/emev2.dtsi
@@ -14,6 +14,14 @@
 	compatible = "renesas,emev2";
 	interrupt-parent = <&gic>;
 
+	aliases {
+		gpio0 = &gpio0;
+		gpio1 = &gpio1;
+		gpio2 = &gpio2;
+		gpio3 = &gpio3;
+		gpio4 = &gpio4;
+	};
+
 	cpus {
 		#address-cells = <1>;
 		#size-cells = <0>;
@@ -38,6 +46,12 @@
 		      <0xe0020000 0x0100>;
 	};
 
+	pmu {
+		compatible = "arm,cortex-a9-pmu";
+		interrupts = <0 120 4>,
+			     <0 121 4>;
+	};
+
 	sti@e0180000 {
 		compatible = "renesas,em-sti";
 		reg = <0xe0180000 0x54>;
@@ -67,4 +81,55 @@
 		reg = <0xe1050000 0x38>;
 		interrupts = <0 11 0>;
 	};
+
+	gpio0: gpio@e0050000 {
+		compatible = "renesas,em-gio";
+		reg = <0xe0050000 0x2c>, <0xe0050040 0x20>;
+		interrupts = <0 67 0>, <0 68 0>;
+		gpio-controller;
+		#gpio-cells = <2>;
+		ngpios = <32>;
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+	gpio1: gpio@e0050080 {
+		compatible = "renesas,em-gio";
+		reg = <0xe0050080 0x2c>, <0xe00500c0 0x20>;
+		interrupts = <0 69 0>, <0 70 0>;
+		gpio-controller;
+		#gpio-cells = <2>;
+		ngpios = <32>;
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+	gpio2: gpio@e0050100 {
+		compatible = "renesas,em-gio";
+		reg = <0xe0050100 0x2c>, <0xe0050140 0x20>;
+		interrupts = <0 71 0>, <0 72 0>;
+		gpio-controller;
+		#gpio-cells = <2>;
+		ngpios = <32>;
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+	gpio3: gpio@e0050180 {
+		compatible = "renesas,em-gio";
+		reg = <0xe0050180 0x2c>, <0xe00501c0 0x20>;
+		interrupts = <0 73 0>, <0 74 0>;
+		gpio-controller;
+		#gpio-cells = <2>;
+		ngpios = <32>;
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+	gpio4: gpio@e0050200 {
+		compatible = "renesas,em-gio";
+		reg = <0xe0050200 0x2c>, <0xe0050240 0x20>;
+		interrupts = <0 75 0>, <0 76 0>;
+		gpio-controller;
+		#gpio-cells = <2>;
+		ngpios = <31>;
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
 };
diff --git a/arch/arm/boot/dts/exynos4.dtsi b/arch/arm/boot/dts/exynos4.dtsi
index 3f94fe8e3706..caadc0257342 100644
--- a/arch/arm/boot/dts/exynos4.dtsi
+++ b/arch/arm/boot/dts/exynos4.dtsi
@@ -36,6 +36,12 @@
 		i2c5 = &i2c_5;
 		i2c6 = &i2c_6;
 		i2c7 = &i2c_7;
+		csis0 = &csis_0;
+		csis1 = &csis_1;
+		fimc0 = &fimc_0;
+		fimc1 = &fimc_1;
+		fimc2 = &fimc_2;
+		fimc3 = &fimc_3;
 	};
 
 	chipid@10000000 {
@@ -92,6 +98,88 @@
 		reg = <0x10010000 0x400>;
 	};
 
+	camera {
+		compatible = "samsung,fimc", "simple-bus";
+		status = "disabled";
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges;
+
+		clock_cam: clock-controller {
+			 #clock-cells = <1>;
+		};
+
+		fimc_0: fimc@11800000 {
+			compatible = "samsung,exynos4210-fimc";
+			reg = <0x11800000 0x1000>;
+			interrupts = <0 84 0>;
+			clocks = <&clock 256>, <&clock 128>;
+			clock-names = "fimc", "sclk_fimc";
+			samsung,power-domain = <&pd_cam>;
+			samsung,sysreg = <&sys_reg>;
+			status = "disabled";
+		};
+
+		fimc_1: fimc@11810000 {
+			compatible = "samsung,exynos4210-fimc";
+			reg = <0x11810000 0x1000>;
+			interrupts = <0 85 0>;
+			clocks = <&clock 257>, <&clock 129>;
+			clock-names = "fimc", "sclk_fimc";
+			samsung,power-domain = <&pd_cam>;
+			samsung,sysreg = <&sys_reg>;
+			status = "disabled";
+		};
+
+		fimc_2: fimc@11820000 {
+			compatible = "samsung,exynos4210-fimc";
+			reg = <0x11820000 0x1000>;
+			interrupts = <0 86 0>;
+			clocks = <&clock 258>, <&clock 130>;
+			clock-names = "fimc", "sclk_fimc";
+			samsung,power-domain = <&pd_cam>;
+			samsung,sysreg = <&sys_reg>;
+			status = "disabled";
+		};
+
+		fimc_3: fimc@11830000 {
+			compatible = "samsung,exynos4210-fimc";
+			reg = <0x11830000 0x1000>;
+			interrupts = <0 87 0>;
+			clocks = <&clock 259>, <&clock 131>;
+			clock-names = "fimc", "sclk_fimc";
+			samsung,power-domain = <&pd_cam>;
+			samsung,sysreg = <&sys_reg>;
+			status = "disabled";
+		};
+
+		csis_0: csis@11880000 {
+			compatible = "samsung,exynos4210-csis";
+			reg = <0x11880000 0x4000>;
+			interrupts = <0 78 0>;
+			clocks = <&clock 260>, <&clock 134>;
+			clock-names = "csis", "sclk_csis";
+			bus-width = <4>;
+			samsung,power-domain = <&pd_cam>;
+			status = "disabled";
+			#address-cells = <1>;
+			#size-cells = <0>;
+		};
+
+		csis_1: csis@11890000 {
+			compatible = "samsung,exynos4210-csis";
+			reg = <0x11890000 0x4000>;
+			interrupts = <0 80 0>;
+			clocks = <&clock 261>, <&clock 135>;
+			clock-names = "csis", "sclk_csis";
+			bus-width = <2>;
+			samsung,power-domain = <&pd_cam>;
+			status = "disabled";
+			#address-cells = <1>;
+			#size-cells = <0>;
+		};
+	};
+
 	watchdog@10060000 {
 		compatible = "samsung,s3c2410-wdt";
 		reg = <0x10060000 0x100>;
@@ -155,13 +243,31 @@
 		status = "disabled";
 	};
 
+	ehci@12580000 {
+		compatible = "samsung,exynos4210-ehci";
+		reg = <0x12580000 0x100>;
+		interrupts = <0 70 0>;
+		clocks = <&clock 304>;
+		clock-names = "usbhost";
+		status = "disabled";
+	};
+
+	ohci@12590000 {
+		compatible = "samsung,exynos4210-ohci";
+		reg = <0x12590000 0x100>;
+		interrupts = <0 70 0>;
+		clocks = <&clock 304>;
+		clock-names = "usbhost";
+		status = "disabled";
+	};
+
 	mfc: codec@13400000 {
 		compatible = "samsung,mfc-v5";
 		reg = <0x13400000 0x10000>;
 		interrupts = <0 94 0>;
 		samsung,power-domain = <&pd_mfc>;
-		clocks = <&clock 170>, <&clock 273>;
-		clock-names = "sclk_mfc", "mfc";
+		clocks = <&clock 273>;
+		clock-names = "mfc";
 		status = "disabled";
 	};
 
@@ -297,8 +403,8 @@
 		compatible = "samsung,exynos4210-spi";
 		reg = <0x13920000 0x100>;
 		interrupts = <0 66 0>;
-		tx-dma-channel = <&pdma0 7>; /* preliminary */
-		rx-dma-channel = <&pdma0 6>; /* preliminary */
+		dmas = <&pdma0 7>, <&pdma0 6>;
+		dma-names = "tx", "rx";
 		#address-cells = <1>;
 		#size-cells = <0>;
 		clocks = <&clock 327>, <&clock 159>;
@@ -312,8 +418,8 @@
 		compatible = "samsung,exynos4210-spi";
 		reg = <0x13930000 0x100>;
 		interrupts = <0 67 0>;
-		tx-dma-channel = <&pdma1 7>; /* preliminary */
-		rx-dma-channel = <&pdma1 6>; /* preliminary */
+		dmas = <&pdma1 7>, <&pdma1 6>;
+		dma-names = "tx", "rx";
 		#address-cells = <1>;
 		#size-cells = <0>;
 		clocks = <&clock 328>, <&clock 160>;
@@ -327,8 +433,8 @@
 		compatible = "samsung,exynos4210-spi";
 		reg = <0x13940000 0x100>;
 		interrupts = <0 68 0>;
-		tx-dma-channel = <&pdma0 9>; /* preliminary */
-		rx-dma-channel = <&pdma0 8>; /* preliminary */
+		dmas = <&pdma0 9>, <&pdma0 8>;
+		dma-names = "tx", "rx";
 		#address-cells = <1>;
 		#size-cells = <0>;
 		clocks = <&clock 329>, <&clock 161>;
@@ -342,6 +448,8 @@
 		compatible = "samsung,exynos4210-pwm";
 		reg = <0x139D0000 0x1000>;
 		interrupts = <0 37 0>, <0 38 0>, <0 39 0>, <0 40 0>, <0 41 0>;
+		clocks = <&clock 336>;
+		clock-names = "timers";
 		#pwm-cells = <2>;
 		status = "disabled";
 	};
diff --git a/arch/arm/boot/dts/exynos4210-pinctrl.dtsi b/arch/arm/boot/dts/exynos4210-pinctrl.dtsi
index 553bceae8967..a7c212891674 100644
--- a/arch/arm/boot/dts/exynos4210-pinctrl.dtsi
+++ b/arch/arm/boot/dts/exynos4210-pinctrl.dtsi
@@ -797,6 +797,29 @@
 			samsung,pin-pud = <0>;
 			samsung,pin-drv = <0>;
 		};
+
+		cam_port_a_io: cam-port-a-io {
+			samsung,pins = "gpj0-0", "gpj0-1", "gpj0-2", "gpj0-3",
+					"gpj0-4", "gpj0-5", "gpj0-6", "gpj0-7",
+					"gpj1-0", "gpj1-1", "gpj1-2", "gpj1-4";
+			samsung,pin-function = <2>;
+			samsung,pin-pud = <0>;
+			samsung,pin-drv = <0>;
+		};
+
+		cam_port_a_clk_active: cam-port-a-clk-active {
+			samsung,pins = "gpj1-3";
+			samsung,pin-function = <2>;
+			samsung,pin-pud = <0>;
+			samsung,pin-drv = <3>;
+		};
+
+		cam_port_a_clk_idle: cam-port-a-clk-idle {
+			samsung,pins = "gpj1-3";
+			samsung,pin-function = <0>;
+			samsung,pin-pud = <1>;
+			samsung,pin-drv = <0>;
+		};
 	};
 
 	pinctrl@03860000 {
diff --git a/arch/arm/boot/dts/exynos4210-trats.dts b/arch/arm/boot/dts/exynos4210-trats.dts
index 94eebffe3044..1c164f234bcc 100644
--- a/arch/arm/boot/dts/exynos4210-trats.dts
+++ b/arch/arm/boot/dts/exynos4210-trats.dts
@@ -30,13 +30,62 @@
 		bootargs = "console=ttySAC2,115200N8 root=/dev/mmcblk0p5 rootwait earlyprintk panic=5";
 	};
 
-	vemmc_reg: voltage-regulator@0 {
-	        compatible = "regulator-fixed";
-		regulator-name = "VMEM_VDD_2.8V";
-		regulator-min-microvolt = <2800000>;
-		regulator-max-microvolt = <2800000>;
-		gpio = <&gpk0 2 0>;
-		enable-active-high;
+	regulators {
+		compatible = "simple-bus";
+
+		vemmc_reg: regulator-0 {
+			compatible = "regulator-fixed";
+			regulator-name = "VMEM_VDD_2.8V";
+			regulator-min-microvolt = <2800000>;
+			regulator-max-microvolt = <2800000>;
+			gpio = <&gpk0 2 0>;
+			enable-active-high;
+		};
+
+		tsp_reg: regulator-1 {
+			compatible = "regulator-fixed";
+			regulator-name = "TSP_FIXED_VOLTAGES";
+			regulator-min-microvolt = <2800000>;
+			regulator-max-microvolt = <2800000>;
+			gpio = <&gpl0 3 0>;
+			enable-active-high;
+		};
+
+		cam_af_28v_reg: regulator-2 {
+			compatible = "regulator-fixed";
+			regulator-name = "8M_AF_2.8V_EN";
+			regulator-min-microvolt = <2800000>;
+			regulator-max-microvolt = <2800000>;
+			gpio = <&gpk1 1 0>;
+			enable-active-high;
+		};
+
+		cam_io_en_reg: regulator-3 {
+			compatible = "regulator-fixed";
+			regulator-name = "CAM_IO_EN";
+			regulator-min-microvolt = <2800000>;
+			regulator-max-microvolt = <2800000>;
+			gpio = <&gpe2 1 0>;
+			enable-active-high;
+		};
+
+		cam_io_12v_reg: regulator-4 {
+			compatible = "regulator-fixed";
+			regulator-name = "8M_1.2V_EN";
+			regulator-min-microvolt = <1200000>;
+			regulator-max-microvolt = <1200000>;
+			gpio = <&gpe2 5 0>;
+			enable-active-high;
+		};
+
+		vt_core_15v_reg: regulator-5 {
+			compatible = "regulator-fixed";
+			regulator-name = "VT_CORE_1.5V";
+			regulator-min-microvolt = <1500000>;
+			regulator-max-microvolt = <1500000>;
+			gpio = <&gpe2 2 0>;
+			enable-active-high;
+		};
 	};
 
 	sdhci_emmc: sdhci@12510000 {
@@ -97,15 +146,6 @@
 		};
 	};
 
-	tsp_reg: voltage-regulator {
-		compatible = "regulator-fixed";
-		regulator-name = "TSP_FIXED_VOLTAGES";
-		regulator-min-microvolt = <2800000>;
-		regulator-max-microvolt = <2800000>;
-		gpio = <&gpl0 3 0>;
-		enable-active-high;
-	};
-
 	i2c@13890000 {
 		samsung,i2c-sda-delay = <100>;
 		samsung,i2c-slave-addr = <0x10>;
@@ -218,6 +258,12 @@
 				     regulator-always-on;
 				};
 
+				vtcam_reg: LDO12 {
+				     regulator-name = "VT_CAM_1.8V";
+				     regulator-min-microvolt = <1800000>;
+				     regulator-max-microvolt = <1800000>;
+				};
+
 				vcclcd_reg: LDO13 {
 				     regulator-name = "VCC_3.3V_LCD";
 				     regulator-min-microvolt = <3300000>;
@@ -301,4 +347,26 @@
 			clock-frequency = <24000000>;
 		};
 	};
+
+	camera {
+		pinctrl-names = "default";
+		pinctrl-0 = <>;
+		status = "okay";
+
+		fimc_0: fimc@11800000 {
+			status = "okay";
+		};
+
+		fimc_1: fimc@11810000 {
+			status = "okay";
+		};
+
+		fimc_2: fimc@11820000 {
+			status = "okay";
+		};
+
+		fimc_3: fimc@11830000 {
+			status = "okay";
+		};
+	};
 };
diff --git a/arch/arm/boot/dts/exynos4210.dtsi b/arch/arm/boot/dts/exynos4210.dtsi
index b7f358a93bcb..057d6829d319 100644
--- a/arch/arm/boot/dts/exynos4210.dtsi
+++ b/arch/arm/boot/dts/exynos4210.dtsi
@@ -72,7 +72,7 @@
 		};
 	};
 
-	clock: clock-controller@0x10030000 {
+	clock: clock-controller@10030000 {
 		compatible = "samsung,exynos4210-clock";
 		reg = <0x10030000 0x20000>;
 		#clock-cells = <1>;
@@ -125,4 +125,34 @@
 		clock-names = "sclk_fimg2d", "fimg2d";
 		status = "disabled";
 	};
+
+	camera {
+		clocks = <&clock 132>, <&clock 133>, <&clock 351>, <&clock 352>;
+		clock-names = "sclk_cam0", "sclk_cam1", "pxl_async0", "pxl_async1";
+
+		fimc_0: fimc@11800000 {
+			samsung,pix-limits = <4224 8192 1920 4224>;
+			samsung,mainscaler-ext;
+			samsung,cam-if;
+		};
+
+		fimc_1: fimc@11810000 {
+			samsung,pix-limits = <4224 8192 1920 4224>;
+			samsung,mainscaler-ext;
+			samsung,cam-if;
+		};
+
+		fimc_2: fimc@11820000 {
+			samsung,pix-limits = <4224 8192 1920 4224>;
+			samsung,mainscaler-ext;
+			samsung,lcd-wb;
+		};
+
+		fimc_3: fimc@11830000 {
+			samsung,pix-limits = <1920 8192 1366 1920>;
+			samsung,rotators = <0>;
+			samsung,mainscaler-ext;
+			samsung,lcd-wb;
+		};
+	};
 };
diff --git a/arch/arm/boot/dts/exynos4412-origen.dts b/arch/arm/boot/dts/exynos4412-origen.dts
index 7993641cb32a..8768b03702e5 100644
--- a/arch/arm/boot/dts/exynos4412-origen.dts
+++ b/arch/arm/boot/dts/exynos4412-origen.dts
@@ -27,6 +27,11 @@
 		bootargs ="console=ttySAC2,115200";
 	};
 
+	firmware@0203F000 {
+		compatible = "samsung,secure-firmware";
+		reg = <0x0203F000 0x1000>;
+	};
+
 	mmc_reg: voltage-regulator {
 		compatible = "regulator-fixed";
 		regulator-name = "VMEM_VDD_2.8V";
diff --git a/arch/arm/boot/dts/exynos4412-trats2.dts b/arch/arm/boot/dts/exynos4412-trats2.dts
new file mode 100644
index 000000000000..fb7b9ae5f399
--- /dev/null
+++ b/arch/arm/boot/dts/exynos4412-trats2.dts
@@ -0,0 +1,579 @@
+/*
+ * Samsung's Exynos4412 based Trats 2 board device tree source
+ *
+ * Copyright (c) 2013 Samsung Electronics Co., Ltd.
+ *		http://www.samsung.com
+ *
+ * Device tree source file for Samsung's Trats 2 board which is based on
+ * Samsung's Exynos4412 SoC.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+*/
+
+/dts-v1/;
+#include "exynos4412.dtsi"
+
+/ {
+	model = "Samsung Trats 2 based on Exynos4412";
+	compatible = "samsung,trats2", "samsung,exynos4412";
+
+	aliases {
+		i2c8 = &i2c_ak8975;
+	};
+
+	memory {
+		reg =  <0x40000000 0x40000000>;
+	};
+
+	chosen {
+		bootargs = "console=ttySAC2,115200N8 root=/dev/mmcblk0p5 rootwait earlyprintk panic=5";
+	};
+
+	firmware@0204F000 {
+		compatible = "samsung,secure-firmware";
+		reg = <0x0204F000 0x1000>;
+	};
+
+	fixed-rate-clocks {
+		xxti {
+			compatible = "samsung,clock-xxti", "fixed-clock";
+			clock-frequency = <0>;
+		};
+
+		xusbxti {
+			compatible = "samsung,clock-xusbxti", "fixed-clock";
+			clock-frequency = <24000000>;
+		};
+	};
+
+	regulators {
+		compatible = "simple-bus";
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		vemmc_reg: regulator-0 {
+			compatible = "regulator-fixed";
+			regulator-name = "VMEM_VDD_2.8V";
+			regulator-min-microvolt = <2800000>;
+			regulator-max-microvolt = <2800000>;
+			gpio = <&gpk0 2 0>;
+			enable-active-high;
+		};
+
+		cam_io_reg: voltage-regulator-1 {
+			compatible = "regulator-fixed";
+			regulator-name = "CAM_SENSOR_A";
+			regulator-min-microvolt = <2800000>;
+			regulator-max-microvolt = <2800000>;
+			gpio = <&gpm0 2 0>;
+			enable-active-high;
+		};
+
+		/* More to come */
+	};
+
+	gpio-keys {
+		compatible = "gpio-keys";
+
+		key-down {
+			interrupt-parent = <&gpj1>;
+			interrupts = <2 0>;
+			gpios = <&gpj1 2 1>;
+			linux,code = <114>;
+			label = "volume down";
+			debounce-interval = <10>;
+		};
+
+		key-up {
+			interrupt-parent = <&gpj1>;
+			interrupts = <1 0>;
+			gpios = <&gpj1 1 1>;
+			linux,code = <115>;
+			label = "volume up";
+			debounce-interval = <10>;
+		};
+
+		key-power {
+			interrupt-parent = <&gpx2>;
+			interrupts = <7 0>;
+			gpios = <&gpx2 7 1>;
+			linux,code = <116>;
+			label = "power";
+			debounce-interval = <10>;
+			gpio-key,wakeup;
+		};
+	};
+
+	i2c@13890000 {
+		samsung,i2c-sda-delay = <100>;
+		samsung,i2c-slave-addr = <0x10>;
+		samsung,i2c-max-bus-freq = <400000>;
+		pinctrl-0 = <&i2c3_bus>;
+		pinctrl-names = "default";
+		status = "okay";
+
+		mms114-touchscreen@48 {
+			compatible = "melfas,mms114";
+			reg = <0x48>;
+			interrupt-parent = <&gpm2>;
+			interrupts = <3 2>;
+			x-size = <720>;
+			y-size = <1280>;
+			avdd-supply = <&ldo23_reg>;
+			vdd-supply = <&ldo24_reg>;
+		};
+	};
+
+	i2c@138D0000 {
+		samsung,i2c-sda-delay = <100>;
+		samsung,i2c-slave-addr = <0x10>;
+		samsung,i2c-max-bus-freq = <100000>;
+		pinctrl-0 = <&i2c7_bus>;
+		pinctrl-names = "default";
+		status = "okay";
+
+		max77686_pmic@09 {
+			compatible = "maxim,max77686";
+			interrupt-parent = <&gpx0>;
+			interrupts = <7 0>;
+			reg = <0x09>;
+
+			voltage-regulators {
+				ldo1_reg: ldo1 {
+					regulator-compatible = "LDO1";
+					regulator-name = "VALIVE_1.0V_AP";
+					regulator-min-microvolt = <1000000>;
+					regulator-max-microvolt = <1000000>;
+					regulator-always-on;
+					regulator-mem-on;
+				};
+
+				ldo2_reg: ldo2 {
+					regulator-compatible = "LDO2";
+					regulator-name = "VM1M2_1.2V_AP";
+					regulator-min-microvolt = <1200000>;
+					regulator-max-microvolt = <1200000>;
+					regulator-always-on;
+					regulator-mem-on;
+				};
+
+				ldo3_reg: ldo3 {
+					regulator-compatible = "LDO3";
+					regulator-name = "VCC_1.8V_AP";
+					regulator-min-microvolt = <1800000>;
+					regulator-max-microvolt = <1800000>;
+					regulator-always-on;
+					regulator-mem-on;
+				};
+
+				ldo4_reg: ldo4 {
+					regulator-compatible = "LDO4";
+					regulator-name = "VCC_2.8V_AP";
+					regulator-min-microvolt = <2800000>;
+					regulator-max-microvolt = <2800000>;
+					regulator-always-on;
+					regulator-mem-on;
+				};
+
+				ldo5_reg: ldo5 {
+					regulator-compatible = "LDO5";
+					regulator-name = "VCC_1.8V_IO";
+					regulator-min-microvolt = <1800000>;
+					regulator-max-microvolt = <1800000>;
+					regulator-always-on;
+					regulator-mem-on;
+				};
+
+				ldo6_reg: ldo6 {
+					regulator-compatible = "LDO6";
+					regulator-name = "VMPLL_1.0V_AP";
+					regulator-min-microvolt = <1000000>;
+					regulator-max-microvolt = <1000000>;
+					regulator-always-on;
+					regulator-mem-on;
+				};
+
+				ldo7_reg: ldo7 {
+					regulator-compatible = "LDO7";
+					regulator-name = "VPLL_1.0V_AP";
+					regulator-min-microvolt = <1000000>;
+					regulator-max-microvolt = <1000000>;
+					regulator-always-on;
+					regulator-mem-on;
+				};
+
+				ldo8_reg: ldo8 {
+					regulator-compatible = "LDO8";
+					regulator-name = "VMIPI_1.0V";
+					regulator-min-microvolt = <1000000>;
+					regulator-max-microvolt = <1000000>;
+					regulator-mem-off;
+				};
+
+				ldo9_reg: ldo9 {
+					regulator-compatible = "LDO9";
+					regulator-name = "CAM_ISP_MIPI_1.2V";
+					regulator-min-microvolt = <1200000>;
+					regulator-max-microvolt = <1200000>;
+					regulator-mem-idle;
+				};
+
+				ldo10_reg: ldo10 {
+					regulator-compatible = "LDO10";
+					regulator-name = "VMIPI_1.8V";
+					regulator-min-microvolt = <1800000>;
+					regulator-max-microvolt = <1800000>;
+					regulator-mem-off;
+				};
+
+				ldo11_reg: ldo11 {
+					regulator-compatible = "LDO11";
+					regulator-name = "VABB1_1.95V";
+					regulator-min-microvolt = <1950000>;
+					regulator-max-microvolt = <1950000>;
+					regulator-always-on;
+					regulator-mem-off;
+				};
+
+				ldo12_reg: ldo12 {
+					regulator-compatible = "LDO12";
+					regulator-name = "VUOTG_3.0V";
+					regulator-min-microvolt = <3000000>;
+					regulator-max-microvolt = <3000000>;
+					regulator-mem-off;
+				};
+
+				ldo13_reg: ldo13 {
+					regulator-compatible = "LDO13";
+					regulator-name = "NFC_AVDD_1.8V";
+					regulator-min-microvolt = <1800000>;
+					regulator-max-microvolt = <1800000>;
+					regulator-mem-idle;
+				};
+
+				ldo14_reg: ldo14 {
+					regulator-compatible = "LDO14";
+					regulator-name = "VABB2_1.95V";
+					regulator-min-microvolt = <1950000>;
+					regulator-max-microvolt = <1950000>;
+					regulator-always-on;
+					regulator-mem-off;
+				};
+
+				ldo15_reg: ldo15 {
+					regulator-compatible = "LDO15";
+					regulator-name = "VHSIC_1.0V";
+					regulator-min-microvolt = <1000000>;
+					regulator-max-microvolt = <1000000>;
+					regulator-mem-off;
+				};
+
+				ldo16_reg: ldo16 {
+					regulator-compatible = "LDO16";
+					regulator-name = "VHSIC_1.8V";
+					regulator-min-microvolt = <1800000>;
+					regulator-max-microvolt = <1800000>;
+					regulator-mem-off;
+				};
+
+				ldo17_reg: ldo17 {
+					regulator-compatible = "LDO17";
+					regulator-name = "CAM_SENSOR_CORE_1.2V";
+					regulator-min-microvolt = <1200000>;
+					regulator-max-microvolt = <1200000>;
+					regulator-mem-idle;
+				};
+
+				ldo18_reg: ldo18 {
+					regulator-compatible = "LDO18";
+					regulator-name = "CAM_ISP_SEN_IO_1.8V";
+					regulator-min-microvolt = <1800000>;
+					regulator-max-microvolt = <1800000>;
+					regulator-mem-idle;
+				};
+
+				ldo19_reg: ldo19 {
+					regulator-compatible = "LDO19";
+					regulator-name = "VT_CAM_1.8V";
+					regulator-min-microvolt = <1800000>;
+					regulator-max-microvolt = <1800000>;
+					regulator-mem-idle;
+				};
+
+				ldo20_reg: ldo20 {
+					regulator-compatible = "LDO20";
+					regulator-name = "VDDQ_PRE_1.8V";
+					regulator-min-microvolt = <1800000>;
+					regulator-max-microvolt = <1800000>;
+					regulator-mem-idle;
+				};
+
+				ldo21_reg: ldo21 {
+					regulator-compatible = "LDO21";
+					regulator-name = "VTF_2.8V";
+					regulator-min-microvolt = <2800000>;
+					regulator-max-microvolt = <2800000>;
+					regulator-mem-idle;
+				};
+
+				ldo22_reg: ldo22 {
+					regulator-compatible = "LDO22";
+					regulator-name = "VMEM_VDD_2.8V";
+					regulator-min-microvolt = <2800000>;
+					regulator-max-microvolt = <2800000>;
+					regulator-always-on;
+					regulator-mem-off;
+				};
+
+				ldo23_reg: ldo23 {
+					regulator-compatible = "LDO23";
+					regulator-name = "TSP_AVDD_3.3V";
+					regulator-min-microvolt = <3300000>;
+					regulator-max-microvolt = <3300000>;
+					regulator-mem-idle;
+				};
+
+				ldo24_reg: ldo24 {
+					regulator-compatible = "LDO24";
+					regulator-name = "TSP_VDD_1.8V";
+					regulator-min-microvolt = <1800000>;
+					regulator-max-microvolt = <1800000>;
+					regulator-mem-idle;
+				};
+
+				ldo25_reg: ldo25 {
+					regulator-compatible = "LDO25";
+					regulator-name = "LCD_VCC_3.3V";
+					regulator-min-microvolt = <2800000>;
+					regulator-max-microvolt = <2800000>;
+					regulator-mem-idle;
+				};
+
+				ldo26_reg: ldo26 {
+					regulator-compatible = "LDO26";
+					regulator-name = "MOTOR_VCC_3.0V";
+					regulator-min-microvolt = <3000000>;
+					regulator-max-microvolt = <3000000>;
+					regulator-mem-idle;
+				};
+
+				buck1_reg: buck1 {
+					regulator-compatible = "BUCK1";
+					regulator-name = "vdd_mif";
+					regulator-min-microvolt = <850000>;
+					regulator-max-microvolt = <1100000>;
+					regulator-always-on;
+					regulator-boot-on;
+					regulator-mem-off;
+				};
+
+				buck2_reg: buck2 {
+					regulator-compatible = "BUCK2";
+					regulator-name = "vdd_arm";
+					regulator-min-microvolt = <850000>;
+					regulator-max-microvolt = <1500000>;
+					regulator-always-on;
+					regulator-boot-on;
+					regulator-mem-off;
+				};
+
+				buck3_reg: buck3 {
+					regulator-compatible = "BUCK3";
+					regulator-name = "vdd_int";
+					regulator-min-microvolt = <850000>;
+					regulator-max-microvolt = <1150000>;
+					regulator-always-on;
+					regulator-boot-on;
+					regulator-mem-off;
+				};
+
+				buck4_reg: buck4 {
+					regulator-compatible = "BUCK4";
+					regulator-name = "vdd_g3d";
+					regulator-min-microvolt = <850000>;
+					regulator-max-microvolt = <1150000>;
+					regulator-boot-on;
+					regulator-mem-off;
+				};
+
+				buck5_reg: buck5 {
+					regulator-compatible = "BUCK5";
+					regulator-name = "VMEM_1.2V_AP";
+					regulator-min-microvolt = <1200000>;
+					regulator-max-microvolt = <1200000>;
+					regulator-always-on;
+				};
+
+				buck6_reg: buck6 {
+					regulator-compatible = "BUCK6";
+					regulator-name = "VCC_SUB_1.35V";
+					regulator-min-microvolt = <1350000>;
+					regulator-max-microvolt = <1350000>;
+					regulator-always-on;
+				};
+
+				buck7_reg: buck7 {
+					regulator-compatible = "BUCK7";
+					regulator-name = "VCC_SUB_2.0V";
+					regulator-min-microvolt = <2000000>;
+					regulator-max-microvolt = <2000000>;
+					regulator-always-on;
+				};
+
+				buck8_reg: buck8 {
+					regulator-compatible = "BUCK8";
+					regulator-name = "VMEM_VDDF_3.0V";
+					regulator-min-microvolt = <2850000>;
+					regulator-max-microvolt = <2850000>;
+					regulator-always-on;
+					regulator-mem-off;
+				};
+
+				buck9_reg: buck9 {
+					regulator-compatible = "BUCK9";
+					regulator-name = "CAM_ISP_CORE_1.2V";
+					regulator-min-microvolt = <1000000>;
+					regulator-max-microvolt = <1200000>;
+					regulator-mem-off;
+				};
+			};
+		};
+	};
+
+	sdhci@12510000 {
+		bus-width = <8>;
+		non-removable;
+		pinctrl-0 = <&sd0_clk &sd0_cmd &sd0_bus8>;
+		pinctrl-names = "default";
+		vmmc-supply = <&vemmc_reg>;
+		status = "okay";
+	};
+
+	serial@13800000 {
+		status = "okay";
+	};
+
+	serial@13810000 {
+		status = "okay";
+	};
+
+	serial@13820000 {
+		status = "okay";
+	};
+
+	serial@13830000 {
+		status = "okay";
+	};
+
+	i2c_ak8975: i2c-gpio-0 {
+		compatible = "i2c-gpio";
+		gpios = <&gpy2 4 0>, <&gpy2 5 0>;
+		i2c-gpio,delay-us = <2>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+		status = "okay";
+
+		ak8975@0c {
+			compatible = "ak,ak8975";
+			reg = <0x0c>;
+			gpios = <&gpj0 7 0>;
+		};
+	};
+
+	spi_1: spi@13930000 {
+		pinctrl-names = "default";
+		pinctrl-0 = <&spi1_bus>;
+		status = "okay";
+
+		s5c73m3_spi: s5c73m3 {
+			compatible = "samsung,s5c73m3";
+			spi-max-frequency = <50000000>;
+			reg = <0>;
+			controller-data {
+				cs-gpio = <&gpb 5 0>;
+				samsung,spi-feedback-delay = <2>;
+			};
+		};
+	};
+
+	camera {
+		pinctrl-0 = <&cam_port_b_clk_active>;
+		pinctrl-names = "default";
+		status = "okay";
+
+		fimc_0: fimc@11800000 {
+			status = "okay";
+		};
+
+		fimc_1: fimc@11810000 {
+			status = "okay";
+		};
+
+		fimc_2: fimc@11820000 {
+			status = "okay";
+		};
+
+		fimc_3: fimc@11830000 {
+			status = "okay";
+		};
+
+		csis_1: csis@11890000 {
+			vddcore-supply = <&ldo8_reg>;
+			vddio-supply = <&ldo10_reg>;
+			clock-frequency = <160000000>;
+			status = "okay";
+
+			/* Camera D (4) MIPI CSI-2 (CSIS1) */
+			port@4 {
+				reg = <4>;
+				csis1_ep: endpoint {
+					remote-endpoint = <&is_s5k6a3_ep>;
+					data-lanes = <1>;
+					samsung,csis-hs-settle = <18>;
+					samsung,csis-wclk;
+				};
+			};
+		};
+
+		fimc_lite_0: fimc-lite@12390000 {
+			status = "okay";
+		};
+
+		fimc_lite_1: fimc-lite@123A0000 {
+			status = "okay";
+		};
+
+		fimc-is@12000000 {
+			pinctrl-0 = <&fimc_is_uart>;
+			pinctrl-names = "default";
+			status = "okay";
+
+			i2c1_isp: i2c-isp@12140000 {
+				pinctrl-0 = <&fimc_is_i2c1>;
+				pinctrl-names = "default";
+
+				s5k6a3@10 {
+					compatible = "samsung,s5k6a3";
+					reg = <0x10>;
+					svdda-supply = <&cam_io_reg>;
+					svddio-supply = <&ldo19_reg>;
+					clock-frequency = <24000000>;
+					/* CAM_B_CLKOUT */
+					clocks = <&clock_cam 1>;
+					clock-names = "mclk";
+					samsung,camclk-out = <1>;
+					gpios = <&gpm1 6 0>;
+
+					port {
+						is_s5k6a3_ep: endpoint {
+							remote-endpoint = <&csis1_ep>;
+							data-lanes = <1>;
+						};
+					};
+				};
+			};
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/exynos4x12-pinctrl.dtsi b/arch/arm/boot/dts/exynos4x12-pinctrl.dtsi
index 704290f7c5c0..99b26df8dbc7 100644
--- a/arch/arm/boot/dts/exynos4x12-pinctrl.dtsi
+++ b/arch/arm/boot/dts/exynos4x12-pinctrl.dtsi
@@ -401,13 +401,26 @@
 			samsung,pin-drv = <0>;
 		};
 
-		cam_port_a: cam-port-a {
+		cam_port_a_io: cam-port-a-io {
 			samsung,pins = "gpj0-0", "gpj0-1", "gpj0-2", "gpj0-3",
 					"gpj0-4", "gpj0-5", "gpj0-6", "gpj0-7",
-					"gpj1-0", "gpj1-1", "gpj1-2", "gpj1-3",
-					"gpj1-4";
+					"gpj1-0", "gpj1-1", "gpj1-2", "gpj1-4";
 			samsung,pin-function = <2>;
-			samsung,pin-pud = <3>;
+			samsung,pin-pud = <0>;
+			samsung,pin-drv = <0>;
+		};
+
+		cam_port_a_clk_active: cam-port-a-clk-active {
+			samsung,pins = "gpj1-3";
+			samsung,pin-function = <2>;
+			samsung,pin-pud = <0>;
+			samsung,pin-drv = <3>;
+		};
+
+		cam_port_a_clk_idle: cam-port-a-clk-idle {
+			samsung,pins = "gpj1-3";
+			samsung,pin-function = <0>;
+			samsung,pin-pud = <1>;
 			samsung,pin-drv = <0>;
 		};
 	};
@@ -778,16 +791,29 @@
 			samsung,pin-drv = <3>;
 		};
 
-		cam_port_b: cam-port-b {
+		cam_port_b_io: cam-port-b-io {
 			samsung,pins = "gpm0-0", "gpm0-1", "gpm0-2", "gpm0-3",
 					"gpm0-4", "gpm0-5", "gpm0-6", "gpm0-7",
-					"gpm1-0", "gpm1-1", "gpm2-0", "gpm2-1",
-					"gpm2-2";
+					"gpm1-0", "gpm1-1", "gpm2-0", "gpm2-1";
 			samsung,pin-function = <3>;
 			samsung,pin-pud = <3>;
 			samsung,pin-drv = <0>;
 		};
 
+		cam_port_b_clk_active: cam-port-b-clk-active {
+			samsung,pins = "gpm2-2";
+			samsung,pin-function = <3>;
+			samsung,pin-pud = <0>;
+			samsung,pin-drv = <3>;
+		};
+
+		cam_port_b_clk_idle: cam-port-b-clk-idle {
+			samsung,pins = "gpm2-2";
+			samsung,pin-function = <0>;
+			samsung,pin-pud = <1>;
+			samsung,pin-drv = <0>;
+		};
+
 		eint0: ext-int0 {
 			samsung,pins = "gpx0-0";
 			samsung,pin-function = <0xf>;
@@ -822,6 +848,27 @@
 			samsung,pin-pud = <0>;
 			samsung,pin-drv = <0>;
 		};
+
+		fimc_is_i2c0: fimc-is-i2c0 {
+			samsung,pins = "gpm4-0", "gpm4-1";
+			samsung,pin-function = <2>;
+			samsung,pin-pud = <0>;
+			samsung,pin-drv = <0>;
+		};
+
+		fimc_is_i2c1: fimc-is-i2c1 {
+			samsung,pins = "gpm4-2", "gpm4-3";
+			samsung,pin-function = <2>;
+			samsung,pin-pud = <0>;
+			samsung,pin-drv = <0>;
+		};
+
+		fimc_is_uart: fimc-is-uart {
+			samsung,pins = "gpm3-5", "gpm3-7";
+			samsung,pin-function = <3>;
+			samsung,pin-pud = <0>;
+			samsung,pin-drv = <0>;
+		};
 	};
 
 	pinctrl@03860000 {
diff --git a/arch/arm/boot/dts/exynos4x12.dtsi b/arch/arm/boot/dts/exynos4x12.dtsi
index 01da194ba329..ad531fe6ab95 100644
--- a/arch/arm/boot/dts/exynos4x12.dtsi
+++ b/arch/arm/boot/dts/exynos4x12.dtsi
@@ -26,9 +26,16 @@
 		pinctrl1 = &pinctrl_1;
 		pinctrl2 = &pinctrl_2;
 		pinctrl3 = &pinctrl_3;
+		fimc-lite0 = &fimc_lite_0;
+		fimc-lite1 = &fimc_lite_1;
 	};
 
-	clock: clock-controller@0x10030000 {
+	pd_isp: isp-power-domain@10023CA0 {
+		compatible = "samsung,exynos4210-pd";
+		reg = <0x10023CA0 0x20>;
+	};
+
+	clock: clock-controller@10030000 {
 		compatible = "samsung,exynos4412-clock";
 		reg = <0x10030000 0x20000>;
 		#clock-cells = <1>;
@@ -73,4 +80,100 @@
 		clock-names = "sclk_fimg2d", "fimg2d";
 		status = "disabled";
 	};
+
+	camera {
+		clocks = <&clock 132>, <&clock 133>, <&clock 351>, <&clock 352>;
+		clock-names = "sclk_cam0", "sclk_cam1", "pxl_async0", "pxl_async1";
+
+		fimc_0: fimc@11800000 {
+			compatible = "samsung,exynos4212-fimc";
+			samsung,pix-limits = <4224 8192 1920 4224>;
+			samsung,mainscaler-ext;
+			samsung,isp-wb;
+			samsung,cam-if;
+		};
+
+		fimc_1: fimc@11810000 {
+			compatible = "samsung,exynos4212-fimc";
+			samsung,pix-limits = <4224 8192 1920 4224>;
+			samsung,mainscaler-ext;
+			samsung,isp-wb;
+			samsung,cam-if;
+		};
+
+		fimc_2: fimc@11820000 {
+			compatible = "samsung,exynos4212-fimc";
+			samsung,pix-limits = <4224 8192 1920 4224>;
+			samsung,mainscaler-ext;
+			samsung,isp-wb;
+			samsung,lcd-wb;
+			samsung,cam-if;
+		};
+
+		fimc_3: fimc@11830000 {
+			compatible = "samsung,exynos4212-fimc";
+			samsung,pix-limits = <1920 8192 1366 1920>;
+			samsung,rotators = <0>;
+			samsung,mainscaler-ext;
+			samsung,isp-wb;
+			samsung,lcd-wb;
+		};
+
+		fimc_lite_0: fimc-lite@12390000 {
+			compatible = "samsung,exynos4212-fimc-lite";
+			reg = <0x12390000 0x1000>;
+			interrupts = <0 105 0>;
+			samsung,power-domain = <&pd_isp>;
+			clocks = <&clock 353>;
+			clock-names = "flite";
+			status = "disabled";
+		};
+
+		fimc_lite_1: fimc-lite@123A0000 {
+			compatible = "samsung,exynos4212-fimc-lite";
+			reg = <0x123A0000 0x1000>;
+			interrupts = <0 106 0>;
+			samsung,power-domain = <&pd_isp>;
+			clocks = <&clock 354>;
+			clock-names = "flite";
+			status = "disabled";
+		};
+
+		fimc_is: fimc-is@12000000 {
+			compatible = "samsung,exynos4212-fimc-is", "simple-bus";
+			reg = <0x12000000 0x260000>;
+			interrupts = <0 90 0>, <0 95 0>;
+			samsung,power-domain = <&pd_isp>;
+			clocks = <&clock 353>, <&clock 354>, <&clock 355>,
+				<&clock 356>, <&clock 17>, <&clock 357>,
+				<&clock 358>, <&clock 359>, <&clock 360>,
+				<&clock 450>,<&clock 451>, <&clock 452>,
+				<&clock 453>, <&clock 176>, <&clock 13>,
+				<&clock 454>, <&clock 395>, <&clock 455>;
+			clock-names = "lite0", "lite1", "ppmuispx",
+				      "ppmuispmx", "mpll", "isp",
+				      "drc", "fd", "mcuisp",
+				      "ispdiv0", "ispdiv1", "mcuispdiv0",
+				      "mcuispdiv1", "uart", "aclk200",
+				      "div_aclk200", "aclk400mcuisp",
+				      "div_aclk400mcuisp";
+			#address-cells = <1>;
+			#size-cells = <1>;
+			ranges;
+			status = "disabled";
+
+			pmu {
+				reg = <0x10020000 0x3000>;
+			};
+
+			i2c1_isp: i2c-isp@12140000 {
+				compatible = "samsung,exynos4212-i2c-isp";
+				reg = <0x12140000 0x100>;
+				clocks = <&clock 370>;
+				clock-names = "i2c_isp";
+				#address-cells = <1>;
+				#size-cells = <0>;
+			};
+		};
+	};
 };
diff --git a/arch/arm/boot/dts/exynos5.dtsi b/arch/arm/boot/dts/exynos5.dtsi
index f65e124c04a6..074739d39e2d 100644
--- a/arch/arm/boot/dts/exynos5.dtsi
+++ b/arch/arm/boot/dts/exynos5.dtsi
@@ -95,7 +95,7 @@
 		interrupts = <0 54 0>;
 	};
 
-	rtc {
+	rtc@101E0000 {
 		compatible = "samsung,s3c6410-rtc";
 		reg = <0x101E0000 0x100>;
 		interrupts = <0 43 0>, <0 44 0>;
@@ -108,4 +108,23 @@
 		interrupts = <0 42 0>;
 		status = "disabled";
 	};
+
+	fimd@14400000 {
+		compatible = "samsung,exynos5250-fimd";
+		interrupt-parent = <&combiner>;
+		reg = <0x14400000 0x40000>;
+		interrupt-names = "fifo", "vsync", "lcd_sys";
+		interrupts = <18 4>, <18 5>, <18 6>;
+		status = "disabled";
+	};
+
+	dp-controller@145B0000 {
+		compatible = "samsung,exynos5-dp";
+		reg = <0x145B0000 0x1000>;
+		interrupts = <10 3>;
+		interrupt-parent = <&combiner>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+		status = "disabled";
+	};
 };
diff --git a/arch/arm/boot/dts/exynos5250-arndale.dts b/arch/arm/boot/dts/exynos5250-arndale.dts
index abc7272c7afd..cee55fa33731 100644
--- a/arch/arm/boot/dts/exynos5250-arndale.dts
+++ b/arch/arm/boot/dts/exynos5250-arndale.dts
@@ -11,6 +11,7 @@
 
 /dts-v1/;
 #include "exynos5250.dtsi"
+#include <dt-bindings/interrupt-controller/irq.h>
 
 / {
 	model = "Insignal Arndale evaluation board based on EXYNOS5250";
@@ -37,6 +38,28 @@
 		s5m8767_pmic@66 {
 			compatible = "samsung,s5m8767-pmic";
 			reg = <0x66>;
+			interrupt-parent = <&gpx3>;
+			interrupts = <2 IRQ_TYPE_LEVEL_LOW>;
+
+			vinb1-supply = <&main_dc_reg>;
+			vinb2-supply = <&main_dc_reg>;
+			vinb3-supply = <&main_dc_reg>;
+			vinb4-supply = <&main_dc_reg>;
+			vinb5-supply = <&main_dc_reg>;
+			vinb6-supply = <&main_dc_reg>;
+			vinb7-supply = <&main_dc_reg>;
+			vinb8-supply = <&main_dc_reg>;
+			vinb9-supply = <&main_dc_reg>;
+
+			vinl1-supply = <&buck7_reg>;
+			vinl2-supply = <&buck7_reg>;
+			vinl3-supply = <&buck7_reg>;
+			vinl4-supply = <&main_dc_reg>;
+			vinl5-supply = <&main_dc_reg>;
+			vinl6-supply = <&main_dc_reg>;
+			vinl7-supply = <&main_dc_reg>;
+			vinl8-supply = <&buck8_reg>;
+			vinl9-supply = <&buck8_reg>;
 
 			s5m8767,pmic-buck2-dvs-voltage = <1300000>;
 			s5m8767,pmic-buck3-dvs-voltage = <1100000>;
@@ -276,6 +299,16 @@
 					op_mode = <1>;
 				};
 
+				buck7_reg: BUCK7 {
+					regulator-name = "PVDD_BUCK7";
+					regulator-always-on;
+				};
+
+				buck8_reg: BUCK8 {
+					regulator-name = "PVDD_BUCK8";
+					regulator-always-on;
+				};
+
 				buck9_reg: BUCK9 {
 					regulator-name = "VDD_33_OFF_EXT1";
 					regulator-min-microvolt = <750000>;
@@ -295,7 +328,22 @@
 	};
 
 	i2c@12C90000 {
-		status = "disabled";
+		wm1811a@1a {
+			compatible = "wlf,wm1811";
+			reg = <0x1a>;
+
+			AVDD2-supply = <&main_dc_reg>;
+			CPVDD-supply = <&main_dc_reg>;
+			DBVDD1-supply = <&main_dc_reg>;
+			DBVDD2-supply = <&main_dc_reg>;
+			DBVDD3-supply = <&main_dc_reg>;
+			LDO1VDD-supply = <&main_dc_reg>;
+			SPKVDD1-supply = <&main_dc_reg>;
+			SPKVDD2-supply = <&main_dc_reg>;
+
+			wlf,ldo1ena = <&gpb0 0 0>;
+			wlf,ldo2ena = <&gpb0 1 0>;
+		};
 	};
 
 	i2c@12CA0000 {
@@ -429,18 +477,29 @@
 		vdd-supply = <&ldo8_reg>;
 	};
 
-	mmc_reg: voltage-regulator {
-		compatible = "regulator-fixed";
-		regulator-name = "VDD_33ON_2.8V";
-		regulator-min-microvolt = <2800000>;
-		regulator-max-microvolt = <2800000>;
-		gpio = <&gpx1 1 1>;
-		enable-active-high;
-	};
+	regulators {
+		compatible = "simple-bus";
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		main_dc_reg: fixedregulator@1 {
+			compatible = "regulator-fixed";
+			regulator-name = "MAIN_DC";
+		};
 
-	reg_hdmi_en: fixedregulator@0 {
-		compatible = "regulator-fixed";
-		regulator-name = "hdmi-en";
+		mmc_reg: voltage-regulator {
+			compatible = "regulator-fixed";
+			regulator-name = "VDD_33ON_2.8V";
+			regulator-min-microvolt = <2800000>;
+			regulator-max-microvolt = <2800000>;
+			gpio = <&gpx1 1 1>;
+			enable-active-high;
+		};
+
+		reg_hdmi_en: fixedregulator@0 {
+			compatible = "regulator-fixed";
+			regulator-name = "hdmi-en";
+		};
 	};
 
 	fixed-rate-clocks {
@@ -450,16 +509,18 @@
 		};
 	};
 
-	dp-controller {
+	dp-controller@145B0000 {
 		samsung,color-space = <0>;
 		samsung,dynamic-range = <0>;
 		samsung,ycbcr-coeff = <0>;
 		samsung,color-depth = <1>;
 		samsung,link-rate = <0x0a>;
 		samsung,lane-count = <4>;
+		status = "okay";
 	};
 
 	fimd: fimd@14400000 {
+		status = "okay";
 		display-timings {
 			native-mode = <&timing0>;
 			timing0: timing@0 {
@@ -477,7 +538,21 @@
 		};
 	};
 
-	rtc {
-		status = "okay";
+	usb_hub_bus {
+		compatible = "simple-bus";
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		// SMSC USB3503 connected in hardware only mode as a PHY
+		usb_hub: usb_hub {
+			compatible = "smsc,usb3503a";
+
+			reset-gpios = <&gpx3 5 1>;
+			connect-gpios = <&gpd1 7 1>;
+		};
+	};
+
+	usb@12110000 {
+		usb-phy = <&usb2_phy>;
 	};
 };
diff --git a/arch/arm/boot/dts/exynos5250-smdk5250.dts b/arch/arm/boot/dts/exynos5250-smdk5250.dts
index 49f18c24a576..2538b329f2ce 100644
--- a/arch/arm/boot/dts/exynos5250-smdk5250.dts
+++ b/arch/arm/boot/dts/exynos5250-smdk5250.dts
@@ -250,7 +250,7 @@
 		samsung,vbus-gpio = <&gpx2 6 0>;
 	};
 
-	dp-controller {
+	dp-controller@145B0000 {
 		samsung,color-space = <0>;
 		samsung,dynamic-range = <0>;
 		samsung,ycbcr-coeff = <0>;
@@ -260,21 +260,25 @@
 
 		pinctrl-names = "default";
 		pinctrl-0 = <&dp_hpd>;
+		status = "okay";
 	};
 
-	display-timings {
-		native-mode = <&timing0>;
-		timing0: timing@0 {
-			/* 1280x800 */
-			clock-frequency = <50000>;
-			hactive = <1280>;
-			vactive = <800>;
-			hfront-porch = <4>;
-			hback-porch = <4>;
-			hsync-len = <4>;
-			vback-porch = <4>;
-			vfront-porch = <4>;
-			vsync-len = <4>;
+	fimd@14400000 {
+		status = "okay";
+		display-timings {
+			native-mode = <&timing0>;
+			timing0: timing@0 {
+				/* 1280x800 */
+				clock-frequency = <50000>;
+				hactive = <1280>;
+				vactive = <800>;
+				hfront-porch = <4>;
+				hback-porch = <4>;
+				hsync-len = <4>;
+				vback-porch = <4>;
+				vfront-porch = <4>;
+				vsync-len = <4>;
+			};
 		};
 	};
 
diff --git a/arch/arm/boot/dts/exynos5250-snow.dts b/arch/arm/boot/dts/exynos5250-snow.dts
index e79331dba12d..fd711e245e8d 100644
--- a/arch/arm/boot/dts/exynos5250-snow.dts
+++ b/arch/arm/boot/dts/exynos5250-snow.dts
@@ -171,10 +171,6 @@
 		};
 	};
 
-	rtc {
-		status = "okay";
-	};
-
 	/*
 	 * On Snow we've got SIP WiFi and so can keep drive strengths low to
 	 * reduce EMI.
diff --git a/arch/arm/boot/dts/exynos5250.dtsi b/arch/arm/boot/dts/exynos5250.dtsi
index ef57277fc38f..bbac42a78ce5 100644
--- a/arch/arm/boot/dts/exynos5250.dtsi
+++ b/arch/arm/boot/dts/exynos5250.dtsi
@@ -68,17 +68,17 @@
 		};
 	};
 
-	pd_gsc: gsc-power-domain@0x10044000 {
+	pd_gsc: gsc-power-domain@10044000 {
 		compatible = "samsung,exynos4210-pd";
 		reg = <0x10044000 0x20>;
 	};
 
-	pd_mfc: mfc-power-domain@0x10044040 {
+	pd_mfc: mfc-power-domain@10044040 {
 		compatible = "samsung,exynos4210-pd";
 		reg = <0x10044040 0x20>;
 	};
 
-	clock: clock-controller@0x10010000 {
+	clock: clock-controller@10010000 {
 		compatible = "samsung,exynos5250-clock";
 		reg = <0x10010000 0x30000>;
 		#clock-cells = <1>;
@@ -96,6 +96,11 @@
 			     <1 14 0xf08>,
 			     <1 11 0xf08>,
 			     <1 10 0xf08>;
+		/* Unfortunately we need this since some versions of U-Boot
+		 * on Exynos don't set the CNTFRQ register, so we need the
+		 * value from DT.
+		 */
+		clock-frequency = <24000000>;
 	};
 
 	mct@101C0000 {
@@ -163,16 +168,27 @@
 		clock-names = "watchdog";
 	};
 
+	g2d@10850000 {
+		compatible = "samsung,exynos5250-g2d";
+		reg = <0x10850000 0x1000>;
+		interrupts = <0 91 0>;
+		clocks = <&clock 345>;
+		clock-names = "fimg2d";
+	};
+
 	codec@11000000 {
 		compatible = "samsung,mfc-v6";
 		reg = <0x11000000 0x10000>;
 		interrupts = <0 96 0>;
 		samsung,power-domain = <&pd_mfc>;
+		clocks = <&clock 266>;
+		clock-names = "mfc";
 	};
 
-	rtc {
+	rtc@101E0000 {
 		clocks = <&clock 337>;
 		clock-names = "rtc";
+		status = "okay";
 	};
 
 	tmu@10060000 {
@@ -405,7 +421,7 @@
 	};
 
 	i2s0: i2s@03830000 {
-		compatible = "samsung,i2s-v5";
+		compatible = "samsung,s5pv210-i2s";
 		reg = <0x03830000 0x100>;
 		dmas = <&pdma0 10
 			&pdma0 9
@@ -415,16 +431,13 @@
 			<&clock_audss EXYNOS_I2S_BUS>,
 			<&clock_audss EXYNOS_SCLK_I2S>;
 		clock-names = "iis", "i2s_opclk0", "i2s_opclk1";
-		samsung,supports-6ch;
-		samsung,supports-rstclr;
-		samsung,supports-secdai;
 		samsung,idma-addr = <0x03000000>;
 		pinctrl-names = "default";
 		pinctrl-0 = <&i2s0_bus>;
 	};
 
 	i2s1: i2s@12D60000 {
-		compatible = "samsung,i2s-v5";
+		compatible = "samsung,s3c6410-i2s";
 		reg = <0x12D60000 0x100>;
 		dmas = <&pdma1 12
 			&pdma1 11>;
@@ -436,7 +449,7 @@
 	};
 
 	i2s2: i2s@12D70000 {
-		compatible = "samsung,i2s-v5";
+		compatible = "samsung,s3c6410-i2s";
 		reg = <0x12D70000 0x100>;
 		dmas = <&pdma0 12
 			&pdma0 11>;
@@ -562,7 +575,7 @@
 		};
 	};
 
-	gsc_0:  gsc@0x13e00000 {
+	gsc_0:  gsc@13e00000 {
 		compatible = "samsung,exynos5-gsc";
 		reg = <0x13e00000 0x1000>;
 		interrupts = <0 85 0>;
@@ -571,7 +584,7 @@
 		clock-names = "gscl";
 	};
 
-	gsc_1:  gsc@0x13e10000 {
+	gsc_1:  gsc@13e10000 {
 		compatible = "samsung,exynos5-gsc";
 		reg = <0x13e10000 0x1000>;
 		interrupts = <0 86 0>;
@@ -580,7 +593,7 @@
 		clock-names = "gscl";
 	};
 
-	gsc_2:  gsc@0x13e20000 {
+	gsc_2:  gsc@13e20000 {
 		compatible = "samsung,exynos5-gsc";
 		reg = <0x13e20000 0x1000>;
 		interrupts = <0 87 0>;
@@ -589,7 +602,7 @@
 		clock-names = "gscl";
 	};
 
-	gsc_3:  gsc@0x13e30000 {
+	gsc_3:  gsc@13e30000 {
 		compatible = "samsung,exynos5-gsc";
 		reg = <0x13e30000 0x1000>;
 		interrupts = <0 88 0>;
@@ -614,29 +627,32 @@
 		interrupts = <0 94 0>;
 	};
 
-	dp-controller {
-		compatible = "samsung,exynos5-dp";
-		reg = <0x145b0000 0x1000>;
-		interrupts = <10 3>;
-		interrupt-parent = <&combiner>;
+	dp_phy: video-phy@10040720 {
+		compatible = "samsung,exynos5250-dp-video-phy";
+		reg = <0x10040720 4>;
+		#phy-cells = <0>;
+	};
+
+	dp-controller@145B0000 {
 		clocks = <&clock 342>;
 		clock-names = "dp";
-		#address-cells = <1>;
-		#size-cells = <0>;
-
-		dptx-phy {
-			reg = <0x10040720>;
-			samsung,enable-mask = <1>;
-		};
+		phys = <&dp_phy>;
+		phy-names = "dp";
 	};
 
-	fimd {
-		compatible = "samsung,exynos5250-fimd";
-		interrupt-parent = <&combiner>;
-		reg = <0x14400000 0x40000>;
-		interrupt-names = "fifo", "vsync", "lcd_sys";
-		interrupts = <18 4>, <18 5>, <18 6>;
+	fimd@14400000 {
 		clocks = <&clock 133>, <&clock 339>;
 		clock-names = "sclk_fimd", "fimd";
 	};
+
+	adc: adc@12D10000 {
+		compatible = "samsung,exynos-adc-v1";
+		reg = <0x12D10000 0x100>, <0x10040718 0x4>;
+		interrupts = <0 106 0>;
+		clocks = <&clock 303>;
+		clock-names = "adc";
+		#io-channel-cells = <1>;
+		io-channel-ranges;
+		status = "disabled";
+	};
 };
diff --git a/arch/arm/boot/dts/exynos5420-pinctrl.dtsi b/arch/arm/boot/dts/exynos5420-pinctrl.dtsi
index 5848c425ae4d..e695aba5f73c 100644
--- a/arch/arm/boot/dts/exynos5420-pinctrl.dtsi
+++ b/arch/arm/boot/dts/exynos5420-pinctrl.dtsi
@@ -59,6 +59,13 @@
 			interrupt-controller;
 			#interrupt-cells = <2>;
 		};
+
+		dp_hpd: dp_hpd {
+			samsung,pins = "gpx0-7";
+			samsung,pin-function = <3>;
+			samsung,pin-pud = <0>;
+			samaung,pin-drv = <0>;
+		};
 	};
 
 	pinctrl@13410000 {
diff --git a/arch/arm/boot/dts/exynos5420-smdk5420.dts b/arch/arm/boot/dts/exynos5420-smdk5420.dts
index 08607df6a180..bafba25ba7c2 100644
--- a/arch/arm/boot/dts/exynos5420-smdk5420.dts
+++ b/arch/arm/boot/dts/exynos5420-smdk5420.dts
@@ -30,4 +30,35 @@
 			clock-frequency = <24000000>;
 		};
 	};
+
+	dp-controller@145B0000 {
+		pinctrl-names = "default";
+		pinctrl-0 = <&dp_hpd>;
+		samsung,color-space = <0>;
+		samsung,dynamic-range = <0>;
+		samsung,ycbcr-coeff = <0>;
+		samsung,color-depth = <1>;
+		samsung,link-rate = <0x0a>;
+		samsung,lane-count = <4>;
+		status = "okay";
+	};
+
+	fimd@14400000 {
+		status = "okay";
+		display-timings {
+			native-mode = <&timing0>;
+			timing0: timing@0 {
+				clock-frequency = <50000>;
+				hactive = <2560>;
+				vactive = <1600>;
+				hfront-porch = <48>;
+				hback-porch = <80>;
+				hsync-len = <32>;
+				vback-porch = <16>;
+				vfront-porch = <8>;
+				vsync-len = <6>;
+			};
+		};
+	};
+
 };
diff --git a/arch/arm/boot/dts/exynos5420.dtsi b/arch/arm/boot/dts/exynos5420.dtsi
index 8c54c4b74f0e..d537cd704e19 100644
--- a/arch/arm/boot/dts/exynos5420.dtsi
+++ b/arch/arm/boot/dts/exynos5420.dtsi
@@ -14,7 +14,10 @@
  */
 
 #include "exynos5.dtsi"
-/include/ "exynos5420-pinctrl.dtsi"
+#include "exynos5420-pinctrl.dtsi"
+
+#include <dt-bindings/clk/exynos-audss-clk.h>
+
 / {
 	compatible = "samsung,exynos5420";
 
@@ -59,12 +62,28 @@
 		};
 	};
 
-	clock: clock-controller@0x10010000 {
+	clock: clock-controller@10010000 {
 		compatible = "samsung,exynos5420-clock";
 		reg = <0x10010000 0x30000>;
 		#clock-cells = <1>;
 	};
 
+	clock_audss: audss-clock-controller@3810000 {
+		compatible = "samsung,exynos5420-audss-clock";
+		reg = <0x03810000 0x0C>;
+		#clock-cells = <1>;
+		clocks = <&clock 148>;
+		clock-names = "sclk_audio";
+	};
+
+	codec@11000000 {
+		compatible = "samsung,mfc-v7";
+		reg = <0x11000000 0x10000>;
+		interrupts = <0 96 0>;
+		clocks = <&clock 401>;
+		clock-names = "mfc";
+	};
+
 	mct@101C0000 {
 		compatible = "samsung,exynos4210-mct";
 		reg = <0x101C0000 0x800>;
@@ -90,6 +109,41 @@
 		};
 	};
 
+	gsc_pd: power-domain@10044000 {
+		compatible = "samsung,exynos4210-pd";
+		reg = <0x10044000 0x20>;
+	};
+
+	isp_pd: power-domain@10044020 {
+		compatible = "samsung,exynos4210-pd";
+		reg = <0x10044020 0x20>;
+	};
+
+	mfc_pd: power-domain@10044060 {
+		compatible = "samsung,exynos4210-pd";
+		reg = <0x10044060 0x20>;
+	};
+
+	disp_pd: power-domain@100440C0 {
+		compatible = "samsung,exynos4210-pd";
+		reg = <0x100440C0 0x20>;
+	};
+
+	mau_pd: power-domain@100440E0 {
+		compatible = "samsung,exynos4210-pd";
+		reg = <0x100440E0 0x20>;
+	};
+
+	g2d_pd: power-domain@10044100 {
+		compatible = "samsung,exynos4210-pd";
+		reg = <0x10044100 0x20>;
+	};
+
+	msc_pd: power-domain@10044120 {
+		compatible = "samsung,exynos4210-pd";
+		reg = <0x10044120 0x20>;
+	};
+
 	pinctrl_0: pinctrl@13400000 {
 		compatible = "samsung,exynos5420-pinctrl";
 		reg = <0x13400000 0x1000>;
@@ -126,6 +180,12 @@
 		interrupts = <0 47 0>;
 	};
 
+	rtc@101E0000 {
+		clocks = <&clock 317>;
+		clock-names = "rtc";
+		status = "okay";
+	};
+
 	serial@12C00000 {
 		clocks = <&clock 257>, <&clock 128>;
 		clock-names = "uart", "clk_uart_baud0";
@@ -145,4 +205,34 @@
 		clocks = <&clock 260>, <&clock 131>;
 		clock-names = "uart", "clk_uart_baud0";
 	};
+
+	dp_phy: video-phy@10040728 {
+		compatible = "samsung,exynos5250-dp-video-phy";
+		reg = <0x10040728 4>;
+		#phy-cells = <0>;
+	};
+
+	dp-controller@145B0000 {
+		clocks = <&clock 412>;
+		clock-names = "dp";
+		phys = <&dp_phy>;
+		phy-names = "dp";
+	};
+
+	fimd@14400000 {
+		samsung,power-domain = <&disp_pd>;
+		clocks = <&clock 147>, <&clock 421>;
+		clock-names = "sclk_fimd", "fimd";
+	};
+
+	adc: adc@12D10000 {
+		compatible = "samsung,exynos-adc-v2";
+		reg = <0x12D10000 0x100>, <0x10040720 0x4>;
+		interrupts = <0 106 0>;
+		clocks = <&clock 270>;
+		clock-names = "adc";
+		#io-channel-cells = <1>;
+		io-channel-ranges;
+		status = "disabled";
+	};
 };
diff --git a/arch/arm/boot/dts/exynos5440.dtsi b/arch/arm/boot/dts/exynos5440.dtsi
index ff7f5d855845..5d6cf4965d6e 100644
--- a/arch/arm/boot/dts/exynos5440.dtsi
+++ b/arch/arm/boot/dts/exynos5440.dtsi
@@ -18,9 +18,12 @@
 
 	aliases {
 		spi0 = &spi_0;
+		tmuctrl0 = &tmuctrl_0;
+		tmuctrl1 = &tmuctrl_1;
+		tmuctrl2 = &tmuctrl_2;
 	};
 
-	clock: clock-controller@0x160000 {
+	clock: clock-controller@160000 {
 		compatible = "samsung,exynos5440-clock";
 		reg = <0x160000 0x1000>;
 		#clock-cells = <1>;
@@ -207,6 +210,30 @@
 		clock-names = "rtc";
 	};
 
+	tmuctrl_0: tmuctrl@160118 {
+		compatible = "samsung,exynos5440-tmu";
+		reg = <0x160118 0x230>, <0x160368 0x10>;
+		interrupts = <0 58 0>;
+		clocks = <&clock 21>;
+		clock-names = "tmu_apbif";
+	};
+
+	tmuctrl_1: tmuctrl@16011C {
+		compatible = "samsung,exynos5440-tmu";
+		reg = <0x16011C 0x230>, <0x160368 0x10>;
+		interrupts = <0 58 0>;
+		clocks = <&clock 21>;
+		clock-names = "tmu_apbif";
+	};
+
+	tmuctrl_2: tmuctrl@160120 {
+		compatible = "samsung,exynos5440-tmu";
+		reg = <0x160120 0x230>, <0x160368 0x10>;
+		interrupts = <0 58 0>;
+		clocks = <&clock 21>;
+		clock-names = "tmu_apbif";
+	};
+
 	sata@210000 {
 		compatible = "snps,exynos5440-ahci";
 		reg = <0x210000 0x10000>;
@@ -248,6 +275,7 @@
 		#interrupt-cells = <1>;
 		interrupt-map-mask = <0 0 0 0>;
 		interrupt-map = <0x0 0 &gic 53>;
+		num-lanes = <4>;
 	};
 
 	pcie@2a0000 {
@@ -267,5 +295,6 @@
 		#interrupt-cells = <1>;
 		interrupt-map-mask = <0 0 0 0>;
 		interrupt-map = <0x0 0 &gic 56>;
+		num-lanes = <4>;
 	};
 };
diff --git a/arch/arm/boot/dts/imx23-evk.dts b/arch/arm/boot/dts/imx23-evk.dts
index da0588a04131..185c7c01102a 100644
--- a/arch/arm/boot/dts/imx23-evk.dts
+++ b/arch/arm/boot/dts/imx23-evk.dts
@@ -90,6 +90,11 @@
 		};
 
 		apbx@80040000 {
+			lradc@80050000 {
+				status = "okay";
+				fsl,lradc-touchscreen-wires = <4>;
+			};
+
 			pwm: pwm@80064000 {
 				pinctrl-names = "default";
 				pinctrl-0 = <&pwm2_pins_a>;
@@ -107,6 +112,16 @@
 				pinctrl-0 = <&duart_pins_a>;
 				status = "okay";
 			};
+
+			usbphy0: usbphy@8007c000 {
+				status = "okay";
+			};
+		};
+	};
+
+	ahb@80080000 {
+		usb0: usb@80080000 {
+			status = "okay";
 		};
 	};
 
diff --git a/arch/arm/boot/dts/imx23-olinuxino.dts b/arch/arm/boot/dts/imx23-olinuxino.dts
index d107c4af321f..fc766ae12e24 100644
--- a/arch/arm/boot/dts/imx23-olinuxino.dts
+++ b/arch/arm/boot/dts/imx23-olinuxino.dts
@@ -69,6 +69,10 @@
 		};
 
 		apbx@80040000 {
+			lradc@80050000 {
+				status = "okay";
+			};
+
 			duart: serial@80070000 {
 				pinctrl-names = "default";
 				pinctrl-0 = <&duart_pins_a>;
diff --git a/arch/arm/boot/dts/imx23.dtsi b/arch/arm/boot/dts/imx23.dtsi
index 587ceef81e45..28b5ce289662 100644
--- a/arch/arm/boot/dts/imx23.dtsi
+++ b/arch/arm/boot/dts/imx23.dtsi
@@ -20,6 +20,8 @@
 		gpio2 = &gpio2;
 		serial0 = &auart0;
 		serial1 = &auart1;
+		spi0 = &ssp0;
+		spi1 = &ssp1;
 	};
 
 	cpus {
@@ -76,23 +78,21 @@
 				#size-cells = <1>;
 				reg = <0x8000c000 0x2000>, <0x8000a000 0x2000>;
 				reg-names = "gpmi-nand", "bch";
-				interrupts = <13>, <56>;
-				interrupt-names = "gpmi-dma", "bch";
+				interrupts = <56>;
+				interrupt-names = "bch";
 				clocks = <&clks 34>;
 				clock-names = "gpmi_io";
 				dmas = <&dma_apbh 4>;
 				dma-names = "rx-tx";
-				fsl,gpmi-dma-channel = <4>;
 				status = "disabled";
 			};
 
 			ssp0: ssp@80010000 {
 				reg = <0x80010000 0x2000>;
-				interrupts = <15 14>;
+				interrupts = <15>;
 				clocks = <&clks 33>;
 				dmas = <&dma_apbh 1>;
 				dma-names = "rx-tx";
-				fsl,ssp-dma-channel = <1>;
 				status = "disabled";
 			};
 
@@ -366,11 +366,10 @@
 
 			ssp1: ssp@80034000 {
 				reg = <0x80034000 0x2000>;
-				interrupts = <2 20>;
+				interrupts = <2>;
 				clocks = <&clks 33>;
 				dmas = <&dma_apbh 2>;
 				dma-names = "rx-tx";
-				fsl,ssp-dma-channel = <2>;
 				status = "disabled";
 			};
 
@@ -472,7 +471,7 @@
 			auart0: serial@8006c000 {
 				compatible = "fsl,imx23-auart";
 				reg = <0x8006c000 0x2000>;
-				interrupts = <24 25 23>;
+				interrupts = <24>;
 				clocks = <&clks 32>;
 				dmas = <&dma_apbx 6>, <&dma_apbx 7>;
 				dma-names = "rx", "tx";
@@ -482,7 +481,7 @@
 			auart1: serial@8006e000 {
 				compatible = "fsl,imx23-auart";
 				reg = <0x8006e000 0x2000>;
-				interrupts = <59 60 58>;
+				interrupts = <59>;
 				clocks = <&clks 32>;
 				dmas = <&dma_apbx 8>, <&dma_apbx 9>;
 				dma-names = "rx", "tx";
diff --git a/arch/arm/boot/dts/imx25.dtsi b/arch/arm/boot/dts/imx25.dtsi
index 701153992c69..737ed5da8f71 100644
--- a/arch/arm/boot/dts/imx25.dtsi
+++ b/arch/arm/boot/dts/imx25.dtsi
@@ -13,19 +13,35 @@
 
 / {
 	aliases {
+		gpio0 = &gpio1;
+		gpio1 = &gpio2;
+		gpio2 = &gpio3;
+		gpio3 = &gpio4;
+		i2c0 = &i2c1;
+		i2c1 = &i2c2;
+		i2c2 = &i2c3;
 		serial0 = &uart1;
 		serial1 = &uart2;
 		serial2 = &uart3;
 		serial3 = &uart4;
 		serial4 = &uart5;
-		gpio0 = &gpio1;
-		gpio1 = &gpio2;
-		gpio2 = &gpio3;
-		gpio3 = &gpio4;
+		spi0 = &spi1;
+		spi1 = &spi2;
+		spi2 = &spi3;
 		usb0 = &usbotg;
 		usb1 = &usbhost1;
 	};
 
+	cpus {
+		#address-cells = <0>;
+		#size-cells = <0>;
+
+		cpu {
+			compatible = "arm,arm926ej-s";
+			device_type = "cpu";
+		};
+	};
+
 	asic: asic-interrupt-controller@68000000 {
 		compatible = "fsl,imx25-asic", "fsl,avic";
 		interrupt-controller;
@@ -377,7 +393,8 @@
 				status = "disabled";
 			};
 
-			lcdc@53fbc000 {
+			lcdc: lcdc@53fbc000 {
+				compatible = "fsl,imx25-fb", "fsl,imx21-fb";
 				reg = <0x53fbc000 0x4000>;
 				interrupts = <39>;
 				clocks = <&clks 103>, <&clks 66>, <&clks 49>;
@@ -424,6 +441,7 @@
 				reg = <0x53fd4000 0x4000>;
 				clocks = <&clks 112>, <&clks 68>;
 				clock-names = "ipg", "ahb";
+				#dma-cells = <3>;
 				interrupts = <34>;
 			};
 
@@ -444,6 +462,13 @@
 				interrupts = <26>;
 			};
 
+			iim: iim@53ff0000 {
+				compatible = "fsl,imx25-iim", "fsl,imx27-iim";
+				reg = <0x53ff0000 0x4000>;
+				interrupts = <19>;
+				clocks = <&clks 99>;
+			};
+
 			usbphy1: usbphy@1 {
 				compatible = "nop-usbphy";
 				status = "disabled";
diff --git a/arch/arm/boot/dts/imx27-apf27dev.dts b/arch/arm/boot/dts/imx27-apf27dev.dts
index 66b8e1c1b0be..2a377ca1881a 100644
--- a/arch/arm/boot/dts/imx27-apf27dev.dts
+++ b/arch/arm/boot/dts/imx27-apf27dev.dts
@@ -53,6 +53,11 @@
 &i2c1 {
 	clock-frequency = <400000>;
 	status = "okay";
+
+	rtc@68 {
+		compatible = "dallas,ds1374";
+		reg = <0x68>;
+	};
 };
 
 &i2c2 {
diff --git a/arch/arm/boot/dts/imx27-phytec-phycard-s-rdk.dts b/arch/arm/boot/dts/imx27-phytec-phycard-s-rdk.dts
new file mode 100644
index 000000000000..5a31c776513f
--- /dev/null
+++ b/arch/arm/boot/dts/imx27-phytec-phycard-s-rdk.dts
@@ -0,0 +1,93 @@
+/*
+ * Copyright 2012 Markus Pargmann, Pengutronix
+ *
+ * The code contained herein is licensed under the GNU General Public
+ * License. You may obtain a copy of the GNU General Public License
+ * Version 2 or later at the following locations:
+ *
+ * http://www.opensource.org/licenses/gpl-license.html
+ * http://www.gnu.org/copyleft/gpl.html
+ */
+
+#include "imx27-phytec-phycard-s-som.dts"
+
+/ {
+	model = "Phytec pca100 rapid development kit";
+	compatible = "phytec,imx27-pca100-rdk", "phytec,imx27-pca100", "fsl,imx27";
+
+	display: display {
+		model = "Primeview-PD050VL1";
+		native-mode = <&timing0>;
+		bits-per-pixel = <16>;  /* non-standard but required */
+		fsl,pcr = <0xf0c88080>;	/* non-standard but required */
+		display-timings {
+			timing0: 640x480 {
+				hactive = <640>;
+				vactive = <480>;
+				hback-porch = <112>;
+				hfront-porch = <36>;
+				hsync-len = <32>;
+				vback-porch = <33>;
+				vfront-porch = <33>;
+				vsync-len = <2>;
+				clock-frequency = <25000000>;
+			};
+		};
+	};
+
+	regulators {
+		compatible = "simple-bus";
+
+		reg_3v3: 3v3 {
+			compatible = "regulator-fixed";
+			regulator-name = "3V3";
+			regulator-min-microvolt = <3300000>;
+			regulator-max-microvolt = <3300000>;
+			regulator-always-on;
+		};
+	};
+};
+
+&fb {
+	display = <&display>;
+	status = "okay";
+};
+
+&i2c1 {
+	status = "okay";
+
+	rtc@51 {
+		compatible = "nxp,pcf8563";
+		reg = <0x51>;
+	};
+
+	adc@64 {
+		compatible = "maxim,max1037";
+		vcc-supply = <&reg_3v3>;
+		reg = <0x64>;
+	};
+};
+
+&owire {
+	status = "okay";
+};
+
+&sdhci2 {
+	cd-gpios = <&gpio3 29 0>;
+	status = "okay";
+};
+
+&uart1 {
+	fsl,uart-has-rtscts;
+	status = "okay";
+};
+
+&uart2 {
+	fsl,uart-has-rtscts;
+	status = "okay";
+};
+
+&uart3 {
+	fsl,uart-has-rtscts;
+	status = "okay";
+};
diff --git a/arch/arm/boot/dts/imx27-phytec-phycard-s-som.dts b/arch/arm/boot/dts/imx27-phytec-phycard-s-som.dts
new file mode 100644
index 000000000000..c8d57d1d0743
--- /dev/null
+++ b/arch/arm/boot/dts/imx27-phytec-phycard-s-som.dts
@@ -0,0 +1,44 @@
+/*
+ * Copyright 2012 Sascha Hauer, Uwe Kleine-König, Steffen Trumtrar
+ * and Markus Pargmann, Pengutronix
+ *
+ * The code contained herein is licensed under the GNU General Public
+ * License. You may obtain a copy of the GNU General Public License
+ * Version 2 or later at the following locations:
+ *
+ * http://www.opensource.org/licenses/gpl-license.html
+ * http://www.gnu.org/copyleft/gpl.html
+ */
+
+/dts-v1/;
+#include "imx27.dtsi"
+
+/ {
+	model = "Phytec pca100";
+	compatible = "phytec,imx27-pca100", "fsl,imx27";
+
+	memory {
+		reg = <0xa0000000 0x08000000>; /* 128MB */
+	};
+};
+
+&cspi1 {
+	fsl,spi-num-chipselects = <2>;
+	cs-gpios = <&gpio4 28 0>,
+		<&gpio4 27 0>;
+	status = "okay";
+};
+
+&fec {
+	status = "okay";
+};
+
+&i2c2 {
+	status = "okay";
+
+	at24@52 {
+		compatible = "at,24c32";
+		pagesize = <32>;
+		reg = <0x52>;
+	};
+};
diff --git a/arch/arm/boot/dts/imx27-phytec-phycore-rdk.dts b/arch/arm/boot/dts/imx27-phytec-phycore-rdk.dts
index e7ed9786920a..0fc6551786c6 100644
--- a/arch/arm/boot/dts/imx27-phytec-phycore-rdk.dts
+++ b/arch/arm/boot/dts/imx27-phytec-phycore-rdk.dts
@@ -35,3 +35,16 @@
 	fsl,uart-has-rtscts;
 	status = "okay";
 };
+
+&weim {
+	can@d4000000 {
+		compatible = "nxp,sja1000";
+		reg = <4 0x00000000 0x00000100>;
+		interrupt-parent = <&gpio5>;
+		interrupts = <19 0x2>;
+		nxp,external-clock-frequency = <16000000>;
+		nxp,tx-output-config = <0x16>;
+		nxp,no-comparator-bypass;
+		fsl,weim-cs-timing = <0x0000dcf6 0x444a0301 0x44443302>;
+	};
+};
diff --git a/arch/arm/boot/dts/imx27-phytec-phycore-som.dts b/arch/arm/boot/dts/imx27-phytec-phycore-som.dts
index f0105651869d..4ec402c38945 100644
--- a/arch/arm/boot/dts/imx27-phytec-phycore-som.dts
+++ b/arch/arm/boot/dts/imx27-phytec-phycore-som.dts
@@ -17,49 +17,22 @@
 	compatible = "phytec,imx27-pcm038", "fsl,imx27";
 
 	memory {
-		reg = <0x0 0x0>;
+		reg = <0xa0000000 0x08000000>;
 	};
+};
 
-	soc {
-		aipi@10000000 { /* aipi1 */
-			serial@1000a000 {
-				status = "okay";
-			};
-
-			i2c@1001d000 {
-				clock-frequency = <400000>;
-				status = "okay";
-				at24@52 {
-					compatible = "at,24c32";
-					pagesize = <32>;
-					reg = <0x52>;
-				};
-				pcf8563@51 {
-					compatible = "nxp,pcf8563";
-					reg = <0x51>;
-				};
-				lm75@4a {
-					compatible = "national,lm75";
-					reg = <0x4a>;
-				};
-			};
-		};
+&audmux {
+	status = "okay";
 
-		aipi@10020000 { /* aipi2 */
-			ethernet@1002b000 {
-				phy-reset-gpios = <&gpio3 30 0>;
-				status = "okay";
-			};
-		};
+	/* SSI0 <=> PINS_4 (MC13783 Audio) */
+	ssi0 {
+		fsl,audmux-port = <0>;
+		fsl,port-config = <0xcb205000>;
 	};
 
-	nor_flash@c0000000 {
-		compatible = "cfi-flash";
-		bank-width = <2>;
-		reg = <0xc0000000 0x02000000>;
-		linux,mtd-name = "physmap-flash.0";
-		#address-cells = <1>;
-		#size-cells = <1>;
+	pins4 {
+		fsl,audmux-port = <2>;
+		fsl,port-config = <0x00001000>;
 	};
 };
 
@@ -80,28 +53,16 @@
 		fsl,mc13xxx-uses-rtc;
 
 		regulators {
-			sw1a_reg: sw1a {
+			/* SW1A and SW1B joined operation */
+			sw1_reg: sw1a {
 				regulator-min-microvolt = <1200000>;
-				regulator-max-microvolt = <1200000>;
+				regulator-max-microvolt = <1520000>;
 				regulator-always-on;
 				regulator-boot-on;
 			};
 
-			sw1b_reg: sw1b {
-				regulator-min-microvolt = <1200000>;
-				regulator-max-microvolt = <1200000>;
-				regulator-always-on;
-				regulator-boot-on;
-			};
-
-			sw2a_reg: sw2a {
-				regulator-min-microvolt = <1800000>;
-				regulator-max-microvolt = <1800000>;
-				regulator-always-on;
-				regulator-boot-on;
-			};
-
-			sw2b_reg: sw2b {
+			/* SW2A and SW2B joined operation */
+			sw2_reg: sw2a {
 				regulator-min-microvolt = <1800000>;
 				regulator-max-microvolt = <1800000>;
 				regulator-always-on;
@@ -172,8 +133,62 @@
 	};
 };
 
+&fec {
+	phy-reset-gpios = <&gpio3 30 0>;
+	status = "okay";
+};
+
+&i2c2 {
+	clock-frequency = <400000>;
+	status = "okay";
+
+	at24@52 {
+		compatible = "at,24c32";
+		pagesize = <32>;
+		reg = <0x52>;
+	};
+
+	pcf8563@51 {
+		compatible = "nxp,pcf8563";
+		reg = <0x51>;
+	};
+
+	lm75@4a {
+		compatible = "national,lm75";
+		reg = <0x4a>;
+	};
+};
+
 &nfc {
 	nand-bus-width = <8>;
 	nand-ecc-mode = "hw";
 	status = "okay";
 };
+
+&uart1 {
+	status = "okay";
+};
+
+&weim {
+	status = "okay";
+
+	nor: nor@c0000000 {
+		compatible = "cfi-flash";
+		reg = <0 0x00000000 0x02000000>;
+		bank-width = <2>;
+		linux,mtd-name = "physmap-flash.0";
+		fsl,weim-cs-timing = <0x22c2cf00 0x75000d01 0x00000900>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+	};
+
+	sram: sram@c8000000 {
+		compatible = "mtd-ram";
+		reg = <1 0x00000000 0x00800000>;
+		bank-width = <2>;
+		linux,mtd-name = "mtd-ram.0";
+		fsl,weim-cs-timing = <0x0000d843 0x22252521 0x22220a00>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+	};
+};
diff --git a/arch/arm/boot/dts/imx27.dtsi b/arch/arm/boot/dts/imx27.dtsi
index 0695264ddf1b..b7a1c6d950b9 100644
--- a/arch/arm/boot/dts/imx27.dtsi
+++ b/arch/arm/boot/dts/imx27.dtsi
@@ -13,25 +13,27 @@
 
 / {
 	aliases {
-		serial0 = &uart1;
-		serial1 = &uart2;
-		serial2 = &uart3;
-		serial3 = &uart4;
-		serial4 = &uart5;
-		serial5 = &uart6;
 		gpio0 = &gpio1;
 		gpio1 = &gpio2;
 		gpio2 = &gpio3;
 		gpio3 = &gpio4;
 		gpio4 = &gpio5;
 		gpio5 = &gpio6;
+		i2c0 = &i2c1;
+		i2c1 = &i2c2;
+		serial0 = &uart1;
+		serial1 = &uart2;
+		serial2 = &uart3;
+		serial3 = &uart4;
+		serial4 = &uart5;
+		serial5 = &uart6;
 		spi0 = &cspi1;
 		spi1 = &cspi2;
 		spi2 = &cspi3;
 	};
 
-	avic: avic-interrupt-controller@e0000000 {
-		compatible = "fsl,imx27-avic", "fsl,avic";
+	aitc: aitc-interrupt-controller@e0000000 {
+		compatible = "fsl,imx27-aitc", "fsl,avic";
 		interrupt-controller;
 		#interrupt-cells = <1>;
 		reg = <0x10040000 0x1000>;
@@ -47,11 +49,29 @@
 		};
 	};
 
+	cpus {
+		#size-cells = <0>;
+		#address-cells = <1>;
+
+		cpu: cpu@0 {
+			device_type = "cpu";
+			compatible = "arm,arm926ej-s";
+			operating-points = <
+				/* kHz uV */
+				266000 1300000
+				399000 1450000
+			>;
+			clock-latency = <62500>;
+			clocks = <&clks 18>;
+			voltage-tolerance = <5>;
+		};
+	};
+
 	soc {
 		#address-cells = <1>;
 		#size-cells = <1>;
 		compatible = "simple-bus";
-		interrupt-parent = <&avic>;
+		interrupt-parent = <&aitc>;
 		ranges;
 
 		aipi@10000000 { /* AIPI1 */
@@ -75,7 +95,7 @@
 				compatible = "fsl,imx27-wdt", "fsl,imx21-wdt";
 				reg = <0x10002000 0x1000>;
 				interrupts = <27>;
-				clocks = <&clks 0>;
+				clocks = <&clks 74>;
 			};
 
 			gpt1: timer@10003000 {
@@ -102,7 +122,7 @@
 				clock-names = "ipg", "per";
 			};
 
-			pwm0: pwm@10006000 {
+			pwm: pwm@10006000 {
 				compatible = "fsl,imx27-pwm";
 				reg = <0x10006000 0x1000>;
 				interrupts = <23>;
@@ -110,6 +130,21 @@
 				clock-names = "ipg", "per";
 			};
 
+			kpp: kpp@10008000 {
+				compatible = "fsl,imx27-kpp", "fsl,imx21-kpp";
+				reg = <0x10008000 0x1000>;
+				interrupts = <21>;
+				clocks = <&clks 37>;
+				status = "disabled";
+			};
+
+			owire: owire@10009000 {
+				compatible = "fsl,imx27-owire", "fsl,imx21-owire";
+				reg = <0x10009000 0x1000>;
+				clocks = <&clks 35>;
+				status = "disabled";
+			};
+
 			uart1: serial@1000a000 {
 				compatible = "fsl,imx27-uart", "fsl,imx21-uart";
 				reg = <0x1000a000 0x1000>;
@@ -152,7 +187,7 @@
 				compatible = "fsl,imx27-cspi";
 				reg = <0x1000e000 0x1000>;
 				interrupts = <16>;
-				clocks = <&clks 53>, <&clks 53>;
+				clocks = <&clks 53>, <&clks 60>;
 				clock-names = "ipg", "per";
 				status = "disabled";
 			};
@@ -163,7 +198,7 @@
 				compatible = "fsl,imx27-cspi";
 				reg = <0x1000f000 0x1000>;
 				interrupts = <15>;
-				clocks = <&clks 52>, <&clks 52>;
+				clocks = <&clks 52>, <&clks 60>;
 				clock-names = "ipg", "per";
 				status = "disabled";
 			};
@@ -260,13 +295,21 @@
 				#interrupt-cells = <2>;
 			};
 
+			audmux: audmux@10016000 {
+				compatible = "fsl,imx27-audmux", "fsl,imx21-audmux";
+				reg = <0x10016000 0x1000>;
+				clocks = <&clks 0>;
+				clock-names = "audmux";
+				status = "disabled";
+			};
+
 			cspi3: cspi@10017000 {
 				#address-cells = <1>;
 				#size-cells = <0>;
 				compatible = "fsl,imx27-cspi";
 				reg = <0x10017000 0x1000>;
 				interrupts = <6>;
-				clocks = <&clks 51>, <&clks 51>;
+				clocks = <&clks 51>, <&clks 60>;
 				clock-names = "ipg", "per";
 				status = "disabled";
 			};
@@ -342,6 +385,15 @@
 			reg = <0x10020000 0x20000>;
 			ranges;
 
+			fb: fb@10021000 {
+				compatible = "fsl,imx27-fb", "fsl,imx21-fb";
+				interrupts = <61>;
+				reg = <0x10021000 0x1000>;
+				clocks = <&clks 36>, <&clks 65>, <&clks 59>;
+				clock-names = "ipg", "ahb", "per";
+				status = "disabled";
+			};
+
 			coda: coda@10023000 {
 				compatible = "fsl,imx27-vpu";
 				reg = <0x10023000 0x0200>;
@@ -351,27 +403,37 @@
 				iram = <&iram>;
 			};
 
+			sahara2: sahara@10025000 {
+				compatible = "fsl,imx27-sahara";
+				reg = <0x10025000 0x1000>;
+				interrupts = <59>;
+				clocks = <&clks 32>, <&clks 64>;
+				clock-names = "ipg", "ahb";
+			};
+
 			clks: ccm@10027000{
 				compatible = "fsl,imx27-ccm";
 				reg = <0x10027000 0x1000>;
 				#clock-cells = <1>;
 			};
 
+			iim: iim@10028000 {
+				compatible = "fsl,imx27-iim";
+				reg = <0x10028000 0x1000>;
+				interrupts = <62>;
+				clocks = <&clks 38>;
+			};
+
 			fec: ethernet@1002b000 {
 				compatible = "fsl,imx27-fec";
 				reg = <0x1002b000 0x4000>;
 				interrupts = <50>;
-				clocks = <&clks 48>, <&clks 67>, <&clks 0>;
-				clock-names = "ipg", "ahb", "ptp";
+				clocks = <&clks 48>, <&clks 67>;
+				clock-names = "ipg", "ahb";
 				status = "disabled";
 			};
 		};
 
-		iram: iram@ffff4c00 {
-			compatible = "mmio-sram";
-			reg = <0xffff4c00 0xb400>;
-		};
-
 		nfc: nand@d8000000 {
 			#address-cells = <1>;
 			#size-cells = <1>;
@@ -381,5 +443,27 @@
 			clocks = <&clks 54>;
 			status = "disabled";
 		};
+
+		weim: weim@d8002000 {
+			#address-cells = <2>;
+			#size-cells = <1>;
+			compatible = "fsl,imx27-weim";
+			reg = <0xd8002000 0x1000>;
+			clocks = <&clks 0>;
+			ranges = <
+				0 0 0xc0000000 0x08000000
+				1 0 0xc8000000 0x08000000
+				2 0 0xd0000000 0x02000000
+				3 0 0xd2000000 0x02000000
+				4 0 0xd4000000 0x02000000
+				5 0 0xd6000000 0x02000000
+			>;
+			status = "disabled";
+		};
+
+		iram: iram@ffff4c00 {
+			compatible = "mmio-sram";
+			reg = <0xffff4c00 0xb400>;
+		};
 	};
 };
diff --git a/arch/arm/boot/dts/imx28-cfa10036.dts b/arch/arm/boot/dts/imx28-cfa10036.dts
index 94c4476972c3..1ec8c94bbac9 100644
--- a/arch/arm/boot/dts/imx28-cfa10036.dts
+++ b/arch/arm/boot/dts/imx28-cfa10036.dts
@@ -23,10 +23,7 @@
 	apb@80000000 {
 		apbh@80000000 {
 			pinctrl@80018000 {
-				pinctrl-names = "default";
-				pinctrl-0 = <&hog_pins_cfa10036>;
-
-				hog_pins_cfa10036: hog-10036@0 {
+				ssd1306_cfa10036: ssd1306-10036@0 {
 					reg = <0>;
 					fsl,pinmux-ids = <
 						0x2073 /* MX28_PAD_SSP0_D7__GPIO_2_7 */
@@ -83,6 +80,8 @@
 
 				ssd1306: oled@3c {
 					compatible = "solomon,ssd1306fb-i2c";
+					pinctrl-names = "default";
+					pinctrl-0 = <&ssd1306_cfa10036>;
 					reg = <0x3c>;
 					reset-gpios = <&gpio2 7 0>;
 					solomon,height = <32>;
diff --git a/arch/arm/boot/dts/imx28-cfa10037.dts b/arch/arm/boot/dts/imx28-cfa10037.dts
index c2ef3a3d655e..182b99fe35f3 100644
--- a/arch/arm/boot/dts/imx28-cfa10037.dts
+++ b/arch/arm/boot/dts/imx28-cfa10037.dts
@@ -22,13 +22,19 @@
 	apb@80000000 {
 		apbh@80000000 {
 			pinctrl@80018000 {
-				pinctrl-names = "default", "default";
-				pinctrl-1 = <&hog_pins_cfa10037>;
-
-				hog_pins_cfa10037: hog-10037@0 {
+				usb_pins_cfa10037: usb-10037@0 {
 					reg = <0>;
 					fsl,pinmux-ids = <
 						0x0073 /* MX28_PAD_GPMI_D7__GPIO_0_7 */
+					>;
+					fsl,drive-strength = <0>;
+					fsl,voltage = <1>;
+					fsl,pull-up = <0>;
+				};
+
+				mac0_pins_cfa10037: mac0-10037@0 {
+					reg = <0>;
+					fsl,pinmux-ids = <
 						0x2153 /* MX28_PAD_SSP2_D5__GPIO_2_21 */
 					>;
 					fsl,drive-strength = <0>;
@@ -56,7 +62,8 @@
 		mac0: ethernet@800f0000 {
 			phy-mode = "rmii";
 			pinctrl-names = "default";
-			pinctrl-0 = <&mac0_pins_a>;
+			pinctrl-0 = <&mac0_pins_a
+				&mac0_pins_cfa10037>;
 			phy-reset-gpios = <&gpio2 21 0>;
 			phy-reset-duration = <100>;
 			status = "okay";
@@ -68,6 +75,8 @@
 
 		reg_usb1_vbus: usb1_vbus {
 			compatible = "regulator-fixed";
+			pinctrl-names = "default";
+			pinctrl-0 = <&usb_pins_cfa10037>;
 			regulator-name = "usb1_vbus";
 			regulator-min-microvolt = <5000000>;
 			regulator-max-microvolt = <5000000>;
diff --git a/arch/arm/boot/dts/imx28-cfa10049.dts b/arch/arm/boot/dts/imx28-cfa10049.dts
index 04b2f769ffbd..06e4cfaf7dd2 100644
--- a/arch/arm/boot/dts/imx28-cfa10049.dts
+++ b/arch/arm/boot/dts/imx28-cfa10049.dts
@@ -22,32 +22,62 @@
 	apb@80000000 {
 		apbh@80000000 {
 			pinctrl@80018000 {
-				pinctrl-names = "default", "default";
-				pinctrl-1 = <&hog_pins_cfa10049
-					&hog_pins_cfa10049_pullup>;
-
-				hog_pins_cfa10049: hog-10049@0 {
+				usb_pins_cfa10049: usb-10049@0 {
 					reg = <0>;
 					fsl,pinmux-ids = <
 						0x0073 /* MX28_PAD_GPMI_D7__GPIO_0_7 */
+					>;
+					fsl,drive-strength = <0>;
+					fsl,voltage = <1>;
+					fsl,pull-up = <0>;
+				};
+
+				i2cmux_pins_cfa10049: i2cmux-10049@0 {
+					reg = <0>;
+					fsl,pinmux-ids = <
 						0x1163 /* MX28_PAD_LCD_D22__GPIO_1_22 */
 						0x1173 /* MX28_PAD_LCD_D22__GPIO_1_23 */
+					>;
+					fsl,drive-strength = <0>;
+					fsl,voltage = <1>;
+					fsl,pull-up = <0>;
+				};
+
+				mac0_pins_cfa10049: mac0-10049@0 {
+					reg = <0>;
+					fsl,pinmux-ids = <
 						0x2153 /* MX28_PAD_SSP2_D5__GPIO_2_21 */
-						0x3053 /* MX28_PAD_AUART1_TX__GPIO_3_5 */
 					>;
 					fsl,drive-strength = <0>;
 					fsl,voltage = <1>;
 					fsl,pull-up = <0>;
 				};
 
-				hog_pins_cfa10049_pullup: hog-10049-pullup@0 {
+				pca_pins_cfa10049: pca-10049@0 {
 					reg = <0>;
 					fsl,pinmux-ids = <
 						0x2133 /* MX28_PAD_SSP2_D3__GPIO_2_19 */
+					>;
+					fsl,drive-strength = <0>;
+					fsl,voltage = <1>;
+					fsl,pull-up = <1>;
+				};
+
+				rotary_pins_cfa10049: rotary-10049@0 {
+					reg = <0>;
+					fsl,pinmux-ids = <
 						0x3183 /* MX28_PAD_I2C0_SCL__GPIO_3_24 */
 						0x3193 /* MX28_PAD_I2C0_SDA__GPIO_3_25 */
+					>;
+					fsl,drive-strength = <0>;
+					fsl,voltage = <1>;
+					fsl,pull-up = <1>;
+				};
+
+				rotary_btn_pins_cfa10049: rotary-btn-10049@0 {
+					reg = <0>;
+					fsl,pinmux-ids = <
 						0x31a3 /* MX28_PAD_SAIF_SDATA0__GPIO_3_26 */
-						0x31e3 /* MX28_PAD_LCD_RESET__GPIO_3_30 */
 					>;
 					fsl,drive-strength = <0>;
 					fsl,voltage = <1>;
@@ -60,6 +90,7 @@
 						0x2103 /* MX28_PAD_SSP2_SCK__GPIO_2_16 */
 						0x2113 /* MX28_PAD_SSP2_CMD__GPIO_2_17 */
 						0x2123 /* MX28_PAD_SSP2_D0__GPIO_2_18 */
+						0x3053 /* MX28_PAD_AUART1_TX__GPIO_3_5 */
 					>;
 					fsl,drive-strength = <1>;
 					fsl,voltage = <1>;
@@ -120,6 +151,16 @@
 					fsl,pull-up = <0>;
 				};
 
+				lcdif_pins_cfa10049_pullup: lcdif-10049-pullup@0 {
+					reg = <0>;
+					fsl,pinmux-ids = <
+						0x31e3 /* MX28_PAD_LCD_RESET__GPIO_3_30 */
+					>;
+					fsl,drive-strength = <0>;
+					fsl,voltage = <1>;
+					fsl,pull-up = <1>;
+				};
+
 				w1_gpio_pins: w1-gpio@0 {
 					reg = <0>;
 					fsl,pinmux-ids = <
@@ -134,7 +175,8 @@
 			lcdif@80030000 {
 				pinctrl-names = "default";
 				pinctrl-0 = <&lcdif_18bit_pins_cfa10049
-					     &lcdif_pins_cfa10049>;
+					     &lcdif_pins_cfa10049
+					     &lcdif_pins_cfa10049_pullup>;
 				display = <&display>;
 				status = "okay";
 
@@ -181,6 +223,8 @@
 				compatible = "i2c-mux-gpio";
 				#address-cells = <1>;
 				#size-cells = <0>;
+				pinctrl-names = "default";
+				pinctrl-0 = <&i2cmux_pins_cfa10049>;
 				mux-gpios = <&gpio1 22 0 &gpio1 23 0>;
 				i2c-parent = <&i2c1>;
 
@@ -203,6 +247,8 @@
 
 					pca9555: pca9555@20 {
 						compatible = "nxp,pca9555";
+						pinctrl-names = "default";
+						pinctrl-0 = <&pca_pins_cfa10049>;
 						interrupt-parent = <&gpio2>;
 						interrupts = <19 0x2>;
 						gpio-controller;
@@ -239,6 +285,8 @@
 
 		reg_usb1_vbus: usb1_vbus {
 			compatible = "regulator-fixed";
+			pinctrl-names = "default";
+			pinctrl-0 = <&usb_pins_cfa10049>;
 			regulator-name = "usb1_vbus";
 			regulator-min-microvolt = <5000000>;
 			regulator-max-microvolt = <5000000>;
@@ -250,7 +298,8 @@
 		mac0: ethernet@800f0000 {
 			phy-mode = "rmii";
 			pinctrl-names = "default";
-			pinctrl-0 = <&mac0_pins_a>;
+			pinctrl-0 = <&mac0_pins_a
+				&mac0_pins_cfa10049>;
 			phy-reset-gpios = <&gpio2 21 0>;
 			phy-reset-duration = <100>;
 			status = "okay";
@@ -320,6 +369,8 @@
 
 	gpio_keys {
 		compatible = "gpio-keys";
+		pinctrl-names = "default";
+		pinctrl-0 = <&rotary_btn_pins_cfa10049>;
 		#address-cells = <1>;
 		#size-cells = <0>;
 
@@ -333,6 +384,8 @@
 
 	rotary {
 		compatible = "rotary-encoder";
+		pinctrl-names = "default";
+		pinctrl-0 = <&rotary_pins_cfa10049>;
 		gpios = <&gpio3 24 1>, <&gpio3 25 1>;
 		linux,axis = <1>; /* REL_Y */
 		rotary-encoder,relative-axis;
diff --git a/arch/arm/boot/dts/imx28-cfa10055.dts b/arch/arm/boot/dts/imx28-cfa10055.dts
index 158111244122..171bcbe1ec4b 100644
--- a/arch/arm/boot/dts/imx28-cfa10055.dts
+++ b/arch/arm/boot/dts/imx28-cfa10055.dts
@@ -23,36 +23,13 @@
 	apb@80000000 {
 		apbh@80000000 {
 			pinctrl@80018000 {
-				pinctrl-names = "default", "default";
-				pinctrl-1 = <&hog_pins_cfa10055
-					&hog_pins_cfa10055_pullup>;
-
-				hog_pins_cfa10055: hog-10055@0 {
-					reg = <0>;
-					fsl,pinmux-ids = <
-						0x3053 /* MX28_PAD_AUART1_TX__GPIO_3_5 */
-					>;
-					fsl,drive-strength = <0>;
-					fsl,voltage = <1>;
-					fsl,pull-up = <0>;
-				};
-
-				hog_pins_cfa10055_pullup: hog-10055-pullup@0 {
-					reg = <0>;
-					fsl,pinmux-ids = <
-						0x31e3 /* MX28_PAD_LCD_RESET__GPIO_3_30 */
-					>;
-					fsl,drive-strength = <0>;
-					fsl,voltage = <1>;
-					fsl,pull-up = <1>;
-				};
-
 				spi2_pins_cfa10055: spi2-cfa10055@0 {
 					reg = <0>;
 					fsl,pinmux-ids = <
 						0x2103 /* MX28_PAD_SSP2_SCK__GPIO_2_16 */
 						0x2113 /* MX28_PAD_SSP2_CMD__GPIO_2_17 */
 						0x2123 /* MX28_PAD_SSP2_D0__GPIO_2_18 */
+						0x3053 /* MX28_PAD_AUART1_TX__GPIO_3_5 */
 					>;
 					fsl,drive-strength = <1>;
 					fsl,voltage = <1>;
@@ -98,12 +75,23 @@
 					fsl,voltage = <1>;
 					fsl,pull-up = <0>;
 				};
+
+				lcdif_pins_cfa10055_pullup: lcdif-10055-pullup@0 {
+					reg = <0>;
+					fsl,pinmux-ids = <
+						0x31e3 /* MX28_PAD_LCD_RESET__GPIO_3_30 */
+					>;
+					fsl,drive-strength = <0>;
+					fsl,voltage = <1>;
+					fsl,pull-up = <1>;
+				};
 			};
 
 			lcdif@80030000 {
 				pinctrl-names = "default";
 				pinctrl-0 = <&lcdif_18bit_pins_cfa10055
-					     &lcdif_pins_cfa10055>;
+					     &lcdif_pins_cfa10055
+					     &lcdif_pins_cfa10055_pullup>;
 				display = <&display>;
 				status = "okay";
 
diff --git a/arch/arm/boot/dts/imx28-cfa10056.dts b/arch/arm/boot/dts/imx28-cfa10056.dts
new file mode 100644
index 000000000000..b45dd0e4ee57
--- /dev/null
+++ b/arch/arm/boot/dts/imx28-cfa10056.dts
@@ -0,0 +1,119 @@
+/*
+ * Copyright 2013 Free Electrons
+ *
+ * The code contained herein is licensed under the GNU General Public
+ * License. You may obtain a copy of the GNU General Public License
+ * Version 2 or later at the following locations:
+ *
+ * http://www.opensource.org/licenses/gpl-license.html
+ * http://www.gnu.org/copyleft/gpl.html
+ */
+
+/*
+ * The CFA-10055 is an expansion board for the CFA-10036 module and
+ * CFA-10037, thus we need to include the CFA-10037 DTS.
+ */
+/include/ "imx28-cfa10037.dts"
+
+/ {
+	model = "Crystalfontz CFA-10056 Board";
+	compatible = "crystalfontz,cfa10056", "crystalfontz,cfa10037", "crystalfontz,cfa10036", "fsl,imx28";
+
+	apb@80000000 {
+		apbh@80000000 {
+			pinctrl@80018000 {
+				spi2_pins_cfa10056: spi2-cfa10056@0 {
+					reg = <0>;
+					fsl,pinmux-ids = <
+						0x2103 /* MX28_PAD_SSP2_SCK__GPIO_2_16 */
+						0x2113 /* MX28_PAD_SSP2_CMD__GPIO_2_17 */
+						0x2123 /* MX28_PAD_SSP2_D0__GPIO_2_18 */
+						0x3053 /* MX28_PAD_AUART1_TX__GPIO_3_5 */
+					>;
+					fsl,drive-strength = <1>;
+					fsl,voltage = <1>;
+					fsl,pull-up = <1>;
+				};
+
+				lcdif_pins_cfa10056: lcdif-10056@0 {
+					reg = <0>;
+					fsl,pinmux-ids = <
+						0x1181 /* MX28_PAD_LCD_RD_E__LCD_VSYNC */
+						0x1191 /* MX28_PAD_LCD_WR_RWN__LCD_HSYNC */
+						0x11a1 /* MX28_PAD_LCD_RS__LCD_DOTCLK */
+						0x11b1 /* MX28_PAD_LCD_CS__LCD_ENABLE */
+					>;
+					fsl,drive-strength = <0>;
+					fsl,voltage = <1>;
+					fsl,pull-up = <0>;
+				};
+
+				lcdif_pins_cfa10056_pullup: lcdif-10056-pullup@0 {
+					reg = <0>;
+					fsl,pinmux-ids = <
+						0x31e3 /* MX28_PAD_LCD_RESET__GPIO_3_30 */
+					>;
+					fsl,drive-strength = <0>;
+					fsl,voltage = <1>;
+					fsl,pull-up = <1>;
+				};
+			};
+
+			lcdif@80030000 {
+				pinctrl-names = "default";
+				pinctrl-0 = <&lcdif_24bit_pins_a
+						&lcdif_pins_cfa10056
+						&lcdif_pins_cfa10056_pullup >;
+				display = <&display>;
+				status = "okay";
+
+				display: display {
+					bits-per-pixel = <32>;
+					bus-width = <24>;
+
+					display-timings {
+						native-mode = <&timing0>;
+						timing0: timing0 {
+							clock-frequency = <32000000>;
+							hactive = <480>;
+							vactive = <800>;
+							hback-porch = <2>;
+							hfront-porch = <2>;
+							vback-porch = <2>;
+							vfront-porch = <2>;
+							hsync-len = <5>;
+							vsync-len = <5>;
+							hsync-active = <0>;
+							vsync-active = <0>;
+							de-active = <1>;
+							pixelclk-active = <1>;
+						};
+					};
+				};
+			};
+		};
+	};
+
+	spi2 {
+		compatible = "spi-gpio";
+		pinctrl-names = "default";
+		pinctrl-0 = <&spi2_pins_cfa10056>;
+		status = "okay";
+		gpio-sck = <&gpio2 16 0>;
+		gpio-mosi = <&gpio2 17 0>;
+		gpio-miso = <&gpio2 18 0>;
+		cs-gpios = <&gpio3 5 0>;
+		num-chipselects = <1>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		hx8369: hx8369@0 {
+			compatible = "himax,hx8369a", "himax,hx8369";
+			reg = <0>;
+			spi-max-frequency = <100000>;
+			spi-cpol;
+			spi-cpha;
+			gpios-reset = <&gpio3 30 0>;
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/imx28-cfa10057.dts b/arch/arm/boot/dts/imx28-cfa10057.dts
index 2da713cdb42a..0333c0532f28 100644
--- a/arch/arm/boot/dts/imx28-cfa10057.dts
+++ b/arch/arm/boot/dts/imx28-cfa10057.dts
@@ -23,35 +23,16 @@
 	apb@80000000 {
 		apbh@80000000 {
 			pinctrl@80018000 {
-				pinctrl-names = "default", "default";
-				pinctrl-1 = <&hog_pins_cfa10057
-					&hog_pins_cfa10057_pullup>;
-
-				hog_pins_cfa10057: hog-10057@0 {
+				usb_pins_cfa10057: usb-10057@0 {
 					reg = <0>;
 					fsl,pinmux-ids = <
 						0x0073 /* MX28_PAD_GPMI_D7__GPIO_0_7 */
-						0x3053 /* MX28_PAD_AUART1_TX__GPIO_3_5 */
 					>;
 					fsl,drive-strength = <0>;
 					fsl,voltage = <1>;
 					fsl,pull-up = <0>;
 				};
 
-				hog_pins_cfa10057_pullup: hog-10057-pullup@0 {
-					reg = <0>;
-					fsl,pinmux-ids = <
-						0x2133 /* MX28_PAD_SSP2_D3__GPIO_2_19 */
-						0x3183 /* MX28_PAD_I2C0_SCL__GPIO_3_24 */
-						0x3193 /* MX28_PAD_I2C0_SDA__GPIO_3_25 */
-						0x31a3 /* MX28_PAD_SAIF_SDATA0__GPIO_3_26 */
-						0x31e3 /* MX28_PAD_LCD_RESET__GPIO_3_30 */
-					>;
-					fsl,drive-strength = <0>;
-					fsl,voltage = <1>;
-					fsl,pull-up = <1>;
-				};
-
 				lcdif_18bit_pins_cfa10057: lcdif-18bit@0 {
 					reg = <0>;
 					fsl,pinmux-ids = <
@@ -164,6 +145,8 @@
 
 		reg_usb1_vbus: usb1_vbus {
 			compatible = "regulator-fixed";
+			pinctrl-names = "default";
+			pinctrl-0 = <&usb_pins_cfa10057>;
 			regulator-name = "usb1_vbus";
 			regulator-min-microvolt = <5000000>;
 			regulator-max-microvolt = <5000000>;
diff --git a/arch/arm/boot/dts/imx28-cfa10058.dts b/arch/arm/boot/dts/imx28-cfa10058.dts
new file mode 100644
index 000000000000..64c64c55a82a
--- /dev/null
+++ b/arch/arm/boot/dts/imx28-cfa10058.dts
@@ -0,0 +1,141 @@
+/*
+ * Copyright 2013 Crystalfontz America, Inc.
+ * Copyright 2013 Free Electrons
+ *
+ * The code contained herein is licensed under the GNU General Public
+ * License. You may obtain a copy of the GNU General Public License
+ * Version 2 or later at the following locations:
+ *
+ * http://www.opensource.org/licenses/gpl-license.html
+ * http://www.gnu.org/copyleft/gpl.html
+ */
+
+/*
+ * The CFA-10058 is an expansion board for the CFA-10036 module, thus we
+ * need to include the CFA-10036 DTS.
+ */
+/include/ "imx28-cfa10036.dts"
+
+/ {
+	model = "Crystalfontz CFA-10058 Board";
+	compatible = "crystalfontz,cfa10058", "crystalfontz,cfa10036", "fsl,imx28";
+
+	apb@80000000 {
+		apbh@80000000 {
+			pinctrl@80018000 {
+				usb_pins_cfa10058: usb-10058@0 {
+					reg = <0>;
+					fsl,pinmux-ids = <
+						0x0073 /* MX28_PAD_GPMI_D7__GPIO_0_7 */
+					>;
+					fsl,drive-strength = <0>;
+					fsl,voltage = <1>;
+					fsl,pull-up = <0>;
+				};
+
+				lcdif_pins_cfa10058: lcdif-10058@0 {
+					reg = <0>;
+					fsl,pinmux-ids = <
+						0x1181 /* MX28_PAD_LCD_RD_E__LCD_VSYNC */
+						0x1191 /* MX28_PAD_LCD_WR_RWN__LCD_HSYNC */
+						0x11a1 /* MX28_PAD_LCD_RS__LCD_DOTCLK */
+						0x11b1 /* MX28_PAD_LCD_CS__LCD_ENABLE */
+					>;
+					fsl,drive-strength = <0>;
+					fsl,voltage = <1>;
+					fsl,pull-up = <0>;
+				};
+			};
+
+			lcdif@80030000 {
+				pinctrl-names = "default";
+				pinctrl-0 = <&lcdif_24bit_pins_a
+						 &lcdif_pins_cfa10058>;
+				display = <&display>;
+				status = "okay";
+
+				display: display {
+					bits-per-pixel = <32>;
+					bus-width = <24>;
+
+					display-timings {
+						native-mode = <&timing0>;
+						timing0: timing0 {
+							clock-frequency = <30000000>;
+							hactive = <800>;
+							vactive = <480>;
+							hback-porch = <40>;
+							hfront-porch = <40>;
+							vback-porch = <13>;
+							vfront-porch = <29>;
+							hsync-len = <8>;
+							vsync-len = <8>;
+							hsync-active = <0>;
+							vsync-active = <0>;
+							de-active = <1>;
+							pixelclk-active = <1>;
+						};
+					};
+				};
+			};
+		};
+
+		apbx@80040000 {
+			lradc@80050000 {
+				fsl,lradc-touchscreen-wires = <4>;
+				status = "okay";
+			};
+
+			pwm: pwm@80064000 {
+				pinctrl-names = "default";
+				pinctrl-0 = <&pwm3_pins_b>;
+				status = "okay";
+			};
+
+			usbphy1: usbphy@8007e000 {
+				status = "okay";
+			};
+		};
+	};
+
+	ahb@80080000 {
+		usb1: usb@80090000 {
+			vbus-supply = <&reg_usb1_vbus>;
+			pinctrl-0 = <&usbphy1_pins_a>;
+			pinctrl-names = "default";
+			status = "okay";
+		};
+	};
+
+	regulators {
+		compatible = "simple-bus";
+
+		reg_usb1_vbus: usb1_vbus {
+			pinctrl-names = "default";
+			pinctrl-0 = <&usb_pins_cfa10058>;
+			compatible = "regulator-fixed";
+			regulator-name = "usb1_vbus";
+			regulator-min-microvolt = <5000000>;
+			regulator-max-microvolt = <5000000>;
+			gpio = <&gpio0 7 1>;
+		};
+	};
+
+	ahb@80080000 {
+		mac0: ethernet@800f0000 {
+			phy-mode = "rmii";
+			pinctrl-names = "default";
+			pinctrl-0 = <&mac0_pins_a>;
+			phy-reset-gpios = <&gpio2 21 0>;
+			phy-reset-duration = <100>;
+			status = "okay";
+		};
+	};
+
+	backlight {
+		compatible = "pwm-backlight";
+		pwms = <&pwm 3 5000000>;
+		brightness-levels = <0 4 8 16 32 64 128 255>;
+		default-brightness-level = <6>;
+	};
+};
diff --git a/arch/arm/boot/dts/imx28-evk.dts b/arch/arm/boot/dts/imx28-evk.dts
index e035f4664b97..15715d921d14 100644
--- a/arch/arm/boot/dts/imx28-evk.dts
+++ b/arch/arm/boot/dts/imx28-evk.dts
@@ -220,6 +220,7 @@
 			auart0: serial@8006a000 {
 				pinctrl-names = "default";
 				pinctrl-0 = <&auart0_pins_a>;
+				fsl,uart-has-rtscts;
 				status = "okay";
 			};
 
diff --git a/arch/arm/boot/dts/imx28-m28evk.dts b/arch/arm/boot/dts/imx28-m28evk.dts
index 44d9da57736e..0d322a2bebaf 100644
--- a/arch/arm/boot/dts/imx28-m28evk.dts
+++ b/arch/arm/boot/dts/imx28-m28evk.dts
@@ -235,6 +235,12 @@
 				pinctrl-0 = <&auart2_2pins_b>;
 				status = "okay";
 			};
+
+			pwm: pwm@80064000 {
+				pinctrl-names = "default";
+				pinctrl-0 = <&pwm4_pins_a>;
+				status = "okay";
+			};
 		};
 	};
 
@@ -270,6 +276,13 @@
 		};
 	};
 
+	backlight {
+		compatible = "pwm-backlight";
+		pwms = <&pwm 4 5000000>;
+		brightness-levels = <0 4 8 16 32 64 128 255>;
+		default-brightness-level = <6>;
+	};
+
 	regulators {
 		compatible = "simple-bus";
 
diff --git a/arch/arm/boot/dts/imx28.dtsi b/arch/arm/boot/dts/imx28.dtsi
index 9524a0571281..7363fded95ee 100644
--- a/arch/arm/boot/dts/imx28.dtsi
+++ b/arch/arm/boot/dts/imx28.dtsi
@@ -15,6 +15,8 @@
 	interrupt-parent = <&icoll>;
 
 	aliases {
+		ethernet0 = &mac0;
+		ethernet1 = &mac1;
 		gpio0 = &gpio0;
 		gpio1 = &gpio1;
 		gpio2 = &gpio2;
@@ -27,8 +29,8 @@
 		serial2 = &auart2;
 		serial3 = &auart3;
 		serial4 = &auart4;
-		ethernet0 = &mac0;
-		ethernet1 = &mac1;
+		spi0 = &ssp1;
+		spi1 = &ssp2;
 	};
 
 	cpus {
@@ -62,9 +64,9 @@
 				reg = <0x80000000 0x2000>;
 			};
 
-			hsadc@80002000 {
+			hsadc: hsadc@80002000 {
 				reg = <0x80002000 0x2000>;
-				interrupts = <13 87>;
+				interrupts = <13>;
 				dmas = <&dma_apbh 12>;
 				dma-names = "rx";
 				status = "disabled";
@@ -86,25 +88,24 @@
 				clocks = <&clks 25>;
 			};
 
-			perfmon@80006000 {
+			perfmon: perfmon@80006000 {
 				reg = <0x80006000 0x800>;
 				interrupts = <27>;
 				status = "disabled";
 			};
 
-			gpmi-nand@8000c000 {
+			gpmi: gpmi-nand@8000c000 {
 				compatible = "fsl,imx28-gpmi-nand";
 				#address-cells = <1>;
 				#size-cells = <1>;
 				reg = <0x8000c000 0x2000>, <0x8000a000 0x2000>;
 				reg-names = "gpmi-nand", "bch";
-				interrupts = <88>, <41>;
-				interrupt-names = "gpmi-dma", "bch";
+				interrupts = <41>;
+				interrupt-names = "bch";
 				clocks = <&clks 50>;
 				clock-names = "gpmi_io";
 				dmas = <&dma_apbh 4>;
 				dma-names = "rx-tx";
-				fsl,gpmi-dma-channel = <4>;
 				status = "disabled";
 			};
 
@@ -112,11 +113,10 @@
 				#address-cells = <1>;
 				#size-cells = <0>;
 				reg = <0x80010000 0x2000>;
-				interrupts = <96 82>;
+				interrupts = <96>;
 				clocks = <&clks 46>;
 				dmas = <&dma_apbh 0>;
 				dma-names = "rx-tx";
-				fsl,ssp-dma-channel = <0>;
 				status = "disabled";
 			};
 
@@ -124,11 +124,10 @@
 				#address-cells = <1>;
 				#size-cells = <0>;
 				reg = <0x80012000 0x2000>;
-				interrupts = <97 83>;
+				interrupts = <97>;
 				clocks = <&clks 47>;
 				dmas = <&dma_apbh 1>;
 				dma-names = "rx-tx";
-				fsl,ssp-dma-channel = <1>;
 				status = "disabled";
 			};
 
@@ -136,11 +135,10 @@
 				#address-cells = <1>;
 				#size-cells = <0>;
 				reg = <0x80014000 0x2000>;
-				interrupts = <98 84>;
+				interrupts = <98>;
 				clocks = <&clks 48>;
 				dmas = <&dma_apbh 2>;
 				dma-names = "rx-tx";
-				fsl,ssp-dma-channel = <2>;
 				status = "disabled";
 			};
 
@@ -148,15 +146,14 @@
 				#address-cells = <1>;
 				#size-cells = <0>;
 				reg = <0x80016000 0x2000>;
-				interrupts = <99 85>;
+				interrupts = <99>;
 				clocks = <&clks 49>;
 				dmas = <&dma_apbh 3>;
 				dma-names = "rx-tx";
-				fsl,ssp-dma-channel = <3>;
 				status = "disabled";
 			};
 
-			pinctrl@80018000 {
+			pinctrl: pinctrl@80018000 {
 				#address-cells = <1>;
 				#size-cells = <0>;
 				compatible = "fsl,imx28-pinctrl", "simple-bus";
@@ -521,6 +518,18 @@
 					fsl,pull-up = <1>;
 				};
 
+				saif0_pins_b: saif0@1 {
+					reg = <1>;
+					fsl,pinmux-ids = <
+						0x3150 /* MX28_PAD_SAIF0_LRCLK__SAIF0_LRCLK */
+						0x3160 /* MX28_PAD_SAIF0_BITCLK__SAIF0_BITCLK */
+						0x3170 /* MX28_PAD_SAIF0_SDATA0__SAIF0_SDATA0 */
+					>;
+					fsl,drive-strength = <2>;
+					fsl,voltage = <1>;
+					fsl,pull-up = <1>;
+				};
+
 				saif1_pins_a: saif1@0 {
 					reg = <0>;
 					fsl,pinmux-ids = <
@@ -639,6 +648,19 @@
 					fsl,pull-up = <0>;
 				};
 
+				lcdif_sync_pins_a: lcdif-sync@0 {
+					reg = <0>;
+					fsl,pinmux-ids = <
+						0x11a1 /* MX28_PAD_LCD_RS__LCD_DOTCLK */
+						0x11b1 /* MX28_PAD_LCD_CS__LCD_ENABLE */
+						0x1181 /* MX28_PAD_LCD_RD_E__LCD_VSYNC */
+						0x1191 /* MX28_PAD_LCD_WR_RWN__LCD_HSYNC */
+					>;
+					fsl,drive-strength = <0>;
+					fsl,voltage = <1>;
+					fsl,pull-up = <0>;
+				};
+
 				can0_pins_a: can0@0 {
 					reg = <0>;
 					fsl,pinmux-ids = <
@@ -674,6 +696,21 @@
 					fsl,pull-up = <1>;
 				};
 
+				spi3_pins_a: spi3@0 {
+					reg = <0>;
+					fsl,pinmux-ids = <
+						0x3082 /* MX28_PAD_AUART2_RX__SSP3_D4 */
+						0x3092 /* MX28_PAD_AUART2_TX__SSP3_D5 */
+						0x2180 /* MX28_PAD_SSP3_SCK__SSP3_SCK */
+						0x2190 /* MX28_PAD_SSP3_MOSI__SSP3_CMD */
+						0x21A0 /* MX28_PAD_SSP3_MISO__SSP3_D0 */
+						0x21B0 /* MX28_PAD_SSP3_SS0__SSP3_D3 */
+					>;
+					fsl,drive-strength = <1>;
+					fsl,voltage = <1>;
+					fsl,pull-up = <0>;
+				};
+
 				usbphy0_pins_a: usbphy0@0 {
 					reg = <0>;
 					fsl,pinmux-ids = <
@@ -705,14 +742,14 @@
 				};
 			};
 
-			digctl@8001c000 {
+			digctl: digctl@8001c000 {
 				compatible = "fsl,imx28-digctl", "fsl,imx23-digctl";
 				reg = <0x8001c000 0x2000>;
 				interrupts = <89>;
 				status = "disabled";
 			};
 
-			etm@80022000 {
+			etm: etm@80022000 {
 				reg = <0x80022000 0x2000>;
 				status = "disabled";
 			};
@@ -733,19 +770,19 @@
 				clocks = <&clks 26>;
 			};
 
-			dcp@80028000 {
+			dcp: dcp@80028000 {
 				reg = <0x80028000 0x2000>;
 				interrupts = <52 53 54>;
 				compatible = "fsl-dcp";
 			};
 
-			pxp@8002a000 {
+			pxp: pxp@8002a000 {
 				reg = <0x8002a000 0x2000>;
 				interrupts = <39>;
 				status = "disabled";
 			};
 
-			ocotp@8002c000 {
+			ocotp: ocotp@8002c000 {
 				compatible = "fsl,ocotp";
 				reg = <0x8002c000 0x2000>;
 				status = "disabled";
@@ -756,10 +793,10 @@
 				status = "disabled";
 			};
 
-			lcdif@80030000 {
+			lcdif: lcdif@80030000 {
 				compatible = "fsl,imx28-lcdif";
 				reg = <0x80030000 0x2000>;
-				interrupts = <38 86>;
+				interrupts = <38>;
 				clocks = <&clks 55>;
 				dmas = <&dma_apbh 13>;
 				dma-names = "rx";
@@ -784,41 +821,41 @@
 				status = "disabled";
 			};
 
-			simdbg@8003c000 {
+			simdbg: simdbg@8003c000 {
 				reg = <0x8003c000 0x200>;
 				status = "disabled";
 			};
 
-			simgpmisel@8003c200 {
+			simgpmisel: simgpmisel@8003c200 {
 				reg = <0x8003c200 0x100>;
 				status = "disabled";
 			};
 
-			simsspsel@8003c300 {
+			simsspsel: simsspsel@8003c300 {
 				reg = <0x8003c300 0x100>;
 				status = "disabled";
 			};
 
-			simmemsel@8003c400 {
+			simmemsel: simmemsel@8003c400 {
 				reg = <0x8003c400 0x100>;
 				status = "disabled";
 			};
 
-			gpiomon@8003c500 {
+			gpiomon: gpiomon@8003c500 {
 				reg = <0x8003c500 0x100>;
 				status = "disabled";
 			};
 
-			simenet@8003c700 {
+			simenet: simenet@8003c700 {
 				reg = <0x8003c700 0x100>;
 				status = "disabled";
 			};
 
-			armjtag@8003c800 {
+			armjtag: armjtag@8003c800 {
 				reg = <0x8003c800 0x100>;
 				status = "disabled";
 			};
-                };
+		};
 
 		apbx@80040000 {
 			compatible = "simple-bus";
@@ -836,16 +873,15 @@
 			saif0: saif@80042000 {
 				compatible = "fsl,imx28-saif";
 				reg = <0x80042000 0x2000>;
-				interrupts = <59 80>;
+				interrupts = <59>;
 				#clock-cells = <0>;
 				clocks = <&clks 53>;
 				dmas = <&dma_apbx 4>;
 				dma-names = "rx-tx";
-				fsl,saif-dma-channel = <4>;
 				status = "disabled";
 			};
 
-			power@80044000 {
+			power: power@80044000 {
 				reg = <0x80044000 0x2000>;
 				status = "disabled";
 			};
@@ -853,15 +889,14 @@
 			saif1: saif@80046000 {
 				compatible = "fsl,imx28-saif";
 				reg = <0x80046000 0x2000>;
-				interrupts = <58 81>;
+				interrupts = <58>;
 				clocks = <&clks 54>;
 				dmas = <&dma_apbx 5>;
 				dma-names = "rx-tx";
-				fsl,saif-dma-channel = <5>;
 				status = "disabled";
 			};
 
-			lradc@80050000 {
+			lradc: lradc@80050000 {
 				compatible = "fsl,imx28-lradc";
 				reg = <0x80050000 0x2000>;
 				interrupts = <10 14 15 16 17 18 19
@@ -869,15 +904,15 @@
 				status = "disabled";
 			};
 
-			spdif@80054000 {
+			spdif: spdif@80054000 {
 				reg = <0x80054000 0x2000>;
-				interrupts = <45 66>;
+				interrupts = <45>;
 				dmas = <&dma_apbx 2>;
 				dma-names = "tx";
 				status = "disabled";
 			};
 
-			rtc@80056000 {
+			mxs_rtc: rtc@80056000 {
 				compatible = "fsl,imx28-rtc", "fsl,stmp3xxx-rtc";
 				reg = <0x80056000 0x2000>;
 				interrupts = <29>;
@@ -888,11 +923,10 @@
 				#size-cells = <0>;
 				compatible = "fsl,imx28-i2c";
 				reg = <0x80058000 0x2000>;
-				interrupts = <111 68>;
+				interrupts = <111>;
 				clock-frequency = <100000>;
 				dmas = <&dma_apbx 6>;
 				dma-names = "rx-tx";
-				fsl,i2c-dma-channel = <6>;
 				status = "disabled";
 			};
 
@@ -901,11 +935,10 @@
 				#size-cells = <0>;
 				compatible = "fsl,imx28-i2c";
 				reg = <0x8005a000 0x2000>;
-				interrupts = <110 69>;
+				interrupts = <110>;
 				clock-frequency = <100000>;
 				dmas = <&dma_apbx 7>;
 				dma-names = "rx-tx";
-				fsl,i2c-dma-channel = <7>;
 				status = "disabled";
 			};
 
@@ -918,7 +951,7 @@
 				status = "disabled";
 			};
 
-			timrot@80068000 {
+			timer: timrot@80068000 {
 				compatible = "fsl,imx28-timrot", "fsl,timrot";
 				reg = <0x80068000 0x2000>;
 				interrupts = <48 49 50 51>;
@@ -928,10 +961,9 @@
 			auart0: serial@8006a000 {
 				compatible = "fsl,imx28-auart", "fsl,imx23-auart";
 				reg = <0x8006a000 0x2000>;
-				interrupts = <112 70 71>;
+				interrupts = <112>;
 				dmas = <&dma_apbx 8>, <&dma_apbx 9>;
 				dma-names = "rx", "tx";
-				fsl,auart-dma-channel = <8 9>;
 				clocks = <&clks 45>;
 				status = "disabled";
 			};
@@ -939,7 +971,7 @@
 			auart1: serial@8006c000 {
 				compatible = "fsl,imx28-auart", "fsl,imx23-auart";
 				reg = <0x8006c000 0x2000>;
-				interrupts = <113 72 73>;
+				interrupts = <113>;
 				dmas = <&dma_apbx 10>, <&dma_apbx 11>;
 				dma-names = "rx", "tx";
 				clocks = <&clks 45>;
@@ -949,7 +981,7 @@
 			auart2: serial@8006e000 {
 				compatible = "fsl,imx28-auart", "fsl,imx23-auart";
 				reg = <0x8006e000 0x2000>;
-				interrupts = <114 74 75>;
+				interrupts = <114>;
 				dmas = <&dma_apbx 12>, <&dma_apbx 13>;
 				dma-names = "rx", "tx";
 				clocks = <&clks 45>;
@@ -959,7 +991,7 @@
 			auart3: serial@80070000 {
 				compatible = "fsl,imx28-auart", "fsl,imx23-auart";
 				reg = <0x80070000 0x2000>;
-				interrupts = <115 76 77>;
+				interrupts = <115>;
 				dmas = <&dma_apbx 14>, <&dma_apbx 15>;
 				dma-names = "rx", "tx";
 				clocks = <&clks 45>;
@@ -969,7 +1001,7 @@
 			auart4: serial@80072000 {
 				compatible = "fsl,imx28-auart", "fsl,imx23-auart";
 				reg = <0x80072000 0x2000>;
-				interrupts = <116 78 79>;
+				interrupts = <116>;
 				dmas = <&dma_apbx 0>, <&dma_apbx 1>;
 				dma-names = "rx", "tx";
 				clocks = <&clks 45>;
@@ -1026,7 +1058,7 @@
 			status = "disabled";
 		};
 
-		dflpt@800c0000 {
+		dflpt: dflpt@800c0000 {
 			reg = <0x800c0000 0x10000>;
 			status = "disabled";
 		};
@@ -1049,10 +1081,9 @@
 			status = "disabled";
 		};
 
-		switch@800f8000 {
+		etn_switch: switch@800f8000 {
 			reg = <0x800f8000 0x8000>;
 			status = "disabled";
 		};
-
 	};
 };
diff --git a/arch/arm/boot/dts/imx31.dtsi b/arch/arm/boot/dts/imx31.dtsi
index c5449257ad9a..c34f82581248 100644
--- a/arch/arm/boot/dts/imx31.dtsi
+++ b/arch/arm/boot/dts/imx31.dtsi
@@ -20,6 +20,16 @@
 		serial4 = &uart5;
 	};
 
+	cpus {
+		#address-cells = <0>;
+		#size-cells = <0>;
+
+		cpu {
+			compatible = "arm,arm1136";
+			device_type = "cpu";
+		};
+	};
+
 	avic: avic-interrupt-controller@60000000 {
 		compatible = "fsl,imx31-avic", "fsl,avic";
 		interrupt-controller;
@@ -94,6 +104,13 @@
 				status = "disabled";
 			};
 
+			iim: iim@5001c000 {
+				compatible = "fsl,imx31-iim", "fsl,imx27-iim";
+				reg = <0x5001c000 0x1000>;
+				interrupts = <19>;
+				clocks = <&clks 25>;
+			};
+
 			clks: ccm@53f80000{
 				compatible = "fsl,imx31-ccm";
 				reg = <0x53f80000 0x4000>;
diff --git a/arch/arm/boot/dts/imx51-apf51.dts b/arch/arm/boot/dts/imx51-apf51.dts
index 8f7f9ac0b989..b3606993f2e8 100644
--- a/arch/arm/boot/dts/imx51-apf51.dts
+++ b/arch/arm/boot/dts/imx51-apf51.dts
@@ -26,10 +26,6 @@
 	};
 
 	clocks {
-		ckih1 {
-			clock-frequency = <0>;
-		};
-
 		osc {
 			clock-frequency = <33554432>;
 		};
diff --git a/arch/arm/boot/dts/imx51-babbage.dts b/arch/arm/boot/dts/imx51-babbage.dts
index ad3471ca17c7..1d337d99ecd5 100644
--- a/arch/arm/boot/dts/imx51-babbage.dts
+++ b/arch/arm/boot/dts/imx51-babbage.dts
@@ -63,6 +63,10 @@
 	};
 
 	clocks {
+		ckih1 {
+			clock-frequency = <22579200>;
+		};
+
 		clk_26M: codec_clock {
 			compatible = "fixed-clock";
 			reg=<0>;
@@ -108,6 +112,7 @@
 		#size-cells = <0>;
 		compatible = "fsl,mc13892";
 		spi-max-frequency = <6000000>;
+		spi-cs-high;
 		reg = <0>;
 		interrupt-parent = <&gpio1>;
 		interrupts = <8 0x4>;
diff --git a/arch/arm/boot/dts/imx51.dtsi b/arch/arm/boot/dts/imx51.dtsi
index 25764b505a61..54cee6517902 100644
--- a/arch/arm/boot/dts/imx51.dtsi
+++ b/arch/arm/boot/dts/imx51.dtsi
@@ -15,13 +15,18 @@
 
 / {
 	aliases {
-		serial0 = &uart1;
-		serial1 = &uart2;
-		serial2 = &uart3;
 		gpio0 = &gpio1;
 		gpio1 = &gpio2;
 		gpio2 = &gpio3;
 		gpio3 = &gpio4;
+		i2c0 = &i2c1;
+		i2c1 = &i2c2;
+		serial0 = &uart1;
+		serial1 = &uart2;
+		serial2 = &uart3;
+		spi0 = &ecspi1;
+		spi1 = &ecspi2;
+		spi2 = &cspi;
 	};
 
 	tzic: tz-interrupt-controller@e0000000 {
@@ -42,7 +47,7 @@
 
 		ckih1 {
 			compatible = "fsl,imx-ckih1", "fixed-clock";
-			clock-frequency = <22579200>;
+			clock-frequency = <0>;
 		};
 
 		ckih2 {
@@ -149,6 +154,9 @@
 					reg = <0x70014000 0x4000>;
 					interrupts = <30>;
 					clocks = <&clks 49>;
+					dmas = <&sdma 24 1 0>,
+					       <&sdma 25 1 0>;
+					dma-names = "rx", "tx";
 					fsl,fifo-depth = <15>;
 					fsl,ssi-dma-events = <25 24 23 22>; /* TX0 RX0 TX1 RX1 */
 					status = "disabled";
@@ -300,275 +308,6 @@
 			iomuxc: iomuxc@73fa8000 {
 				compatible = "fsl,imx51-iomuxc";
 				reg = <0x73fa8000 0x4000>;
-
-				audmux {
-					pinctrl_audmux_1: audmuxgrp-1 {
-						fsl,pins = <
-							MX51_PAD_AUD3_BB_TXD__AUD3_TXD 0x80000000
-							MX51_PAD_AUD3_BB_RXD__AUD3_RXD 0x80000000
-							MX51_PAD_AUD3_BB_CK__AUD3_TXC  0x80000000
-							MX51_PAD_AUD3_BB_FS__AUD3_TXFS 0x80000000
-						>;
-					};
-				};
-
-				fec {
-					pinctrl_fec_1: fecgrp-1 {
-						fsl,pins = <
-							MX51_PAD_EIM_EB2__FEC_MDIO	   0x80000000
-							MX51_PAD_EIM_EB3__FEC_RDATA1	   0x80000000
-							MX51_PAD_EIM_CS2__FEC_RDATA2	   0x80000000
-							MX51_PAD_EIM_CS3__FEC_RDATA3	   0x80000000
-							MX51_PAD_EIM_CS4__FEC_RX_ER	   0x80000000
-							MX51_PAD_EIM_CS5__FEC_CRS	   0x80000000
-							MX51_PAD_NANDF_RB2__FEC_COL	   0x80000000
-							MX51_PAD_NANDF_RB3__FEC_RX_CLK	   0x80000000
-							MX51_PAD_NANDF_D9__FEC_RDATA0	   0x80000000
-							MX51_PAD_NANDF_D8__FEC_TDATA0	   0x80000000
-							MX51_PAD_NANDF_CS2__FEC_TX_ER	   0x80000000
-							MX51_PAD_NANDF_CS3__FEC_MDC	   0x80000000
-							MX51_PAD_NANDF_CS4__FEC_TDATA1	   0x80000000
-							MX51_PAD_NANDF_CS5__FEC_TDATA2	   0x80000000
-							MX51_PAD_NANDF_CS6__FEC_TDATA3	   0x80000000
-							MX51_PAD_NANDF_CS7__FEC_TX_EN	   0x80000000
-							MX51_PAD_NANDF_RDY_INT__FEC_TX_CLK 0x80000000
-						>;
-					};
-
-					pinctrl_fec_2: fecgrp-2 {
-						fsl,pins = <
-							MX51_PAD_DI_GP3__FEC_TX_ER	  0x80000000
-							MX51_PAD_DI2_PIN4__FEC_CRS	  0x80000000
-							MX51_PAD_DI2_PIN2__FEC_MDC	  0x80000000
-							MX51_PAD_DI2_PIN3__FEC_MDIO	  0x80000000
-							MX51_PAD_DI2_DISP_CLK__FEC_RDATA1 0x80000000
-							MX51_PAD_DI_GP4__FEC_RDATA2	  0x80000000
-							MX51_PAD_DISP2_DAT0__FEC_RDATA3   0x80000000
-							MX51_PAD_DISP2_DAT1__FEC_RX_ER	  0x80000000
-							MX51_PAD_DISP2_DAT6__FEC_TDATA1	  0x80000000
-							MX51_PAD_DISP2_DAT7__FEC_TDATA2	  0x80000000
-							MX51_PAD_DISP2_DAT8__FEC_TDATA3	  0x80000000
-							MX51_PAD_DISP2_DAT9__FEC_TX_EN	  0x80000000
-							MX51_PAD_DISP2_DAT10__FEC_COL	  0x80000000
-							MX51_PAD_DISP2_DAT11__FEC_RX_CLK  0x80000000
-							MX51_PAD_DISP2_DAT12__FEC_RX_DV	  0x80000000
-							MX51_PAD_DISP2_DAT13__FEC_TX_CLK  0x80000000
-							MX51_PAD_DISP2_DAT14__FEC_RDATA0  0x80000000
-							MX51_PAD_DISP2_DAT15__FEC_TDATA0  0x80000000
-						>;
-					};
-				};
-
-				ecspi1 {
-					pinctrl_ecspi1_1: ecspi1grp-1 {
-						fsl,pins = <
-							MX51_PAD_CSPI1_MISO__ECSPI1_MISO 0x185
-							MX51_PAD_CSPI1_MOSI__ECSPI1_MOSI 0x185
-							MX51_PAD_CSPI1_SCLK__ECSPI1_SCLK 0x185
-						>;
-					};
-				};
-
-				ecspi2 {
-					pinctrl_ecspi2_1: ecspi2grp-1 {
-						fsl,pins = <
-							MX51_PAD_NANDF_RB3__ECSPI2_MISO 0x185
-							MX51_PAD_NANDF_D15__ECSPI2_MOSI 0x185
-							MX51_PAD_NANDF_RB2__ECSPI2_SCLK 0x185
-						>;
-					};
-				};
-
-				esdhc1 {
-					pinctrl_esdhc1_1: esdhc1grp-1 {
-						fsl,pins = <
-							MX51_PAD_SD1_CMD__SD1_CMD     0x400020d5
-							MX51_PAD_SD1_CLK__SD1_CLK     0x20d5
-							MX51_PAD_SD1_DATA0__SD1_DATA0 0x20d5
-							MX51_PAD_SD1_DATA1__SD1_DATA1 0x20d5
-							MX51_PAD_SD1_DATA2__SD1_DATA2 0x20d5
-							MX51_PAD_SD1_DATA3__SD1_DATA3 0x20d5
-						>;
-					};
-				};
-
-				esdhc2 {
-					pinctrl_esdhc2_1: esdhc2grp-1 {
-						fsl,pins = <
-							MX51_PAD_SD2_CMD__SD2_CMD     0x400020d5
-							MX51_PAD_SD2_CLK__SD2_CLK     0x20d5
-							MX51_PAD_SD2_DATA0__SD2_DATA0 0x20d5
-							MX51_PAD_SD2_DATA1__SD2_DATA1 0x20d5
-							MX51_PAD_SD2_DATA2__SD2_DATA2 0x20d5
-							MX51_PAD_SD2_DATA3__SD2_DATA3 0x20d5
-						>;
-					};
-				};
-
-				i2c2 {
-					pinctrl_i2c2_1: i2c2grp-1 {
-						fsl,pins = <
-							MX51_PAD_KEY_COL4__I2C2_SCL 0x400001ed
-							MX51_PAD_KEY_COL5__I2C2_SDA 0x400001ed
-						>;
-					};
-
-					pinctrl_i2c2_2: i2c2grp-2 {
-						fsl,pins = <
-							MX51_PAD_EIM_D27__I2C2_SCL 0x400001ed
-							MX51_PAD_EIM_D24__I2C2_SDA 0x400001ed
-						>;
-					};
-				};
-
-				ipu_disp1 {
-					pinctrl_ipu_disp1_1: ipudisp1grp-1 {
-						fsl,pins = <
-							MX51_PAD_DISP1_DAT0__DISP1_DAT0	  0x5
-							MX51_PAD_DISP1_DAT1__DISP1_DAT1   0x5
-							MX51_PAD_DISP1_DAT2__DISP1_DAT2   0x5
-							MX51_PAD_DISP1_DAT3__DISP1_DAT3   0x5
-							MX51_PAD_DISP1_DAT4__DISP1_DAT4   0x5
-							MX51_PAD_DISP1_DAT5__DISP1_DAT5   0x5
-							MX51_PAD_DISP1_DAT6__DISP1_DAT6   0x5
-							MX51_PAD_DISP1_DAT7__DISP1_DAT7   0x5
-							MX51_PAD_DISP1_DAT8__DISP1_DAT8   0x5
-							MX51_PAD_DISP1_DAT9__DISP1_DAT9   0x5
-							MX51_PAD_DISP1_DAT10__DISP1_DAT10 0x5
-							MX51_PAD_DISP1_DAT11__DISP1_DAT11 0x5
-							MX51_PAD_DISP1_DAT12__DISP1_DAT12 0x5
-							MX51_PAD_DISP1_DAT13__DISP1_DAT13 0x5
-							MX51_PAD_DISP1_DAT14__DISP1_DAT14 0x5
-							MX51_PAD_DISP1_DAT15__DISP1_DAT15 0x5
-							MX51_PAD_DISP1_DAT16__DISP1_DAT16 0x5
-							MX51_PAD_DISP1_DAT17__DISP1_DAT17 0x5
-							MX51_PAD_DISP1_DAT18__DISP1_DAT18 0x5
-							MX51_PAD_DISP1_DAT19__DISP1_DAT19 0x5
-							MX51_PAD_DISP1_DAT20__DISP1_DAT20 0x5
-							MX51_PAD_DISP1_DAT21__DISP1_DAT21 0x5
-							MX51_PAD_DISP1_DAT22__DISP1_DAT22 0x5
-							MX51_PAD_DISP1_DAT23__DISP1_DAT23 0x5
-							MX51_PAD_DI1_PIN2__DI1_PIN2	  0x5 /* hsync */
-							MX51_PAD_DI1_PIN3__DI1_PIN3	  0x5 /* vsync */
-						>;
-					};
-				};
-
-				ipu_disp2 {
-					pinctrl_ipu_disp2_1: ipudisp2grp-1 {
-						fsl,pins = <
-							MX51_PAD_DISP2_DAT0__DISP2_DAT0     0x5
-							MX51_PAD_DISP2_DAT1__DISP2_DAT1     0x5
-							MX51_PAD_DISP2_DAT2__DISP2_DAT2     0x5
-							MX51_PAD_DISP2_DAT3__DISP2_DAT3     0x5
-							MX51_PAD_DISP2_DAT4__DISP2_DAT4     0x5
-							MX51_PAD_DISP2_DAT5__DISP2_DAT5     0x5
-							MX51_PAD_DISP2_DAT6__DISP2_DAT6     0x5
-							MX51_PAD_DISP2_DAT7__DISP2_DAT7     0x5
-							MX51_PAD_DISP2_DAT8__DISP2_DAT8     0x5
-							MX51_PAD_DISP2_DAT9__DISP2_DAT9     0x5
-							MX51_PAD_DISP2_DAT10__DISP2_DAT10   0x5
-							MX51_PAD_DISP2_DAT11__DISP2_DAT11   0x5
-							MX51_PAD_DISP2_DAT12__DISP2_DAT12   0x5
-							MX51_PAD_DISP2_DAT13__DISP2_DAT13   0x5
-							MX51_PAD_DISP2_DAT14__DISP2_DAT14   0x5
-							MX51_PAD_DISP2_DAT15__DISP2_DAT15   0x5
-							MX51_PAD_DI2_PIN2__DI2_PIN2	    0x5 /* hsync */
-							MX51_PAD_DI2_PIN3__DI2_PIN3	    0x5 /* vsync */
-							MX51_PAD_DI2_DISP_CLK__DI2_DISP_CLK 0x5
-							MX51_PAD_DI_GP4__DI2_PIN15	    0x5
-						>;
-					};
-				};
-
-				pata {
-					pinctrl_pata_1: patagrp-1 {
-						fsl,pins = <
-							MX51_PAD_NANDF_WE_B__PATA_DIOW		0x2004
-							MX51_PAD_NANDF_RE_B__PATA_DIOR		0x2004
-							MX51_PAD_NANDF_ALE__PATA_BUFFER_EN	0x2004
-							MX51_PAD_NANDF_CLE__PATA_RESET_B	0x2004
-							MX51_PAD_NANDF_WP_B__PATA_DMACK		0x2004
-							MX51_PAD_NANDF_RB0__PATA_DMARQ		0x2004
-							MX51_PAD_NANDF_RB1__PATA_IORDY		0x2004
-							MX51_PAD_GPIO_NAND__PATA_INTRQ		0x2004
-							MX51_PAD_NANDF_CS2__PATA_CS_0		0x2004
-							MX51_PAD_NANDF_CS3__PATA_CS_1		0x2004
-							MX51_PAD_NANDF_CS4__PATA_DA_0		0x2004
-							MX51_PAD_NANDF_CS5__PATA_DA_1		0x2004
-							MX51_PAD_NANDF_CS6__PATA_DA_2		0x2004
-							MX51_PAD_NANDF_D15__PATA_DATA15		0x2004
-							MX51_PAD_NANDF_D14__PATA_DATA14		0x2004
-							MX51_PAD_NANDF_D13__PATA_DATA13		0x2004
-							MX51_PAD_NANDF_D12__PATA_DATA12		0x2004
-							MX51_PAD_NANDF_D11__PATA_DATA11		0x2004
-							MX51_PAD_NANDF_D10__PATA_DATA10		0x2004
-							MX51_PAD_NANDF_D9__PATA_DATA9		0x2004
-							MX51_PAD_NANDF_D8__PATA_DATA8		0x2004
-							MX51_PAD_NANDF_D7__PATA_DATA7		0x2004
-							MX51_PAD_NANDF_D6__PATA_DATA6		0x2004
-							MX51_PAD_NANDF_D5__PATA_DATA5		0x2004
-							MX51_PAD_NANDF_D4__PATA_DATA4		0x2004
-							MX51_PAD_NANDF_D3__PATA_DATA3		0x2004
-							MX51_PAD_NANDF_D2__PATA_DATA2		0x2004
-							MX51_PAD_NANDF_D1__PATA_DATA1		0x2004
-							MX51_PAD_NANDF_D0__PATA_DATA0		0x2004
-						>;
-					};
-				};
-
-				uart1 {
-					pinctrl_uart1_1: uart1grp-1 {
-						fsl,pins = <
-							MX51_PAD_UART1_RXD__UART1_RXD 0x1c5
-							MX51_PAD_UART1_TXD__UART1_TXD 0x1c5
-							MX51_PAD_UART1_RTS__UART1_RTS 0x1c5
-							MX51_PAD_UART1_CTS__UART1_CTS 0x1c5
-						>;
-					};
-				};
-
-				uart2 {
-					pinctrl_uart2_1: uart2grp-1 {
-						fsl,pins = <
-							MX51_PAD_UART2_RXD__UART2_RXD 0x1c5
-							MX51_PAD_UART2_TXD__UART2_TXD 0x1c5
-						>;
-					};
-				};
-
-				uart3 {
-					pinctrl_uart3_1: uart3grp-1 {
-						fsl,pins = <
-							MX51_PAD_EIM_D25__UART3_RXD 0x1c5
-							MX51_PAD_EIM_D26__UART3_TXD 0x1c5
-							MX51_PAD_EIM_D27__UART3_RTS 0x1c5
-							MX51_PAD_EIM_D24__UART3_CTS 0x1c5
-						>;
-					};
-
-					pinctrl_uart3_2: uart3grp-2 {
-						fsl,pins = <
-							MX51_PAD_UART3_RXD__UART3_RXD 0x1c5
-							MX51_PAD_UART3_TXD__UART3_TXD 0x1c5
-						>;
-					};
-				};
-
-				kpp {
-					pinctrl_kpp_1: kppgrp-1 {
-						fsl,pins = <
-							MX51_PAD_KEY_ROW0__KEY_ROW0 0xe0
-							MX51_PAD_KEY_ROW1__KEY_ROW1 0xe0
-							MX51_PAD_KEY_ROW2__KEY_ROW2 0xe0
-							MX51_PAD_KEY_ROW3__KEY_ROW3 0xe0
-							MX51_PAD_KEY_COL0__KEY_COL0 0xe8
-							MX51_PAD_KEY_COL1__KEY_COL1 0xe8
-							MX51_PAD_KEY_COL2__KEY_COL2 0xe8
-							MX51_PAD_KEY_COL3__KEY_COL3 0xe8
-						>;
-					};
-				};
 			};
 
 			pwm1: pwm@73fb4000 {
@@ -628,6 +367,13 @@
 			reg = <0x80000000 0x10000000>;
 			ranges;
 
+			iim: iim@83f98000 {
+				compatible = "fsl,imx51-iim", "fsl,imx27-iim";
+				reg = <0x83f98000 0x4000>;
+				interrupts = <69>;
+				clocks = <&clks 107>;
+			};
+
 			ecspi2: ecspi@83fac000 {
 				#address-cells = <1>;
 				#size-cells = <0>;
@@ -645,6 +391,7 @@
 				interrupts = <6>;
 				clocks = <&clks 56>, <&clks 56>;
 				clock-names = "ipg", "ahb";
+				#dma-cells = <3>;
 				fsl,sdma-ram-script-name = "imx/sdma/sdma-imx51.bin";
 			};
 
@@ -684,6 +431,9 @@
 				reg = <0x83fcc000 0x4000>;
 				interrupts = <29>;
 				clocks = <&clks 48>;
+				dmas = <&sdma 28 0 0>,
+				       <&sdma 29 0 0>;
+				dma-names = "rx", "tx";
 				fsl,fifo-depth = <15>;
 				fsl,ssi-dma-events = <29 28 27 26>; /* TX0 RX0 TX1 RX1 */
 				status = "disabled";
@@ -695,6 +445,23 @@
 				status = "disabled";
 			};
 
+			weim: weim@83fda000 {
+				#address-cells = <2>;
+				#size-cells = <1>;
+				compatible = "fsl,imx51-weim";
+				reg = <0x83fda000 0x1000>;
+				clocks = <&clks 57>;
+				ranges = <
+					0 0 0xb0000000 0x08000000
+					1 0 0xb8000000 0x08000000
+					2 0 0xc0000000 0x08000000
+					3 0 0xc8000000 0x04000000
+					4 0 0xcc000000 0x02000000
+					5 0 0xce000000 0x02000000
+				>;
+				status = "disabled";
+			};
+
 			nfc: nand@83fdb000 {
 				compatible = "fsl,imx51-nand";
 				reg = <0x83fdb000 0x1000 0xcfff0000 0x10000>;
@@ -707,7 +474,7 @@
 				compatible = "fsl,imx51-pata", "fsl,imx27-pata";
 				reg = <0x83fe0000 0x4000>;
 				interrupts = <70>;
-				clocks = <&clks 161>;
+				clocks = <&clks 172>;
 				status = "disabled";
 			};
 
@@ -716,6 +483,9 @@
 				reg = <0x83fe8000 0x4000>;
 				interrupts = <96>;
 				clocks = <&clks 50>;
+				dmas = <&sdma 46 0 0>,
+				       <&sdma 47 0 0>;
+				dma-names = "rx", "tx";
 				fsl,fifo-depth = <15>;
 				fsl,ssi-dma-events = <47 46 37 35>; /* TX0 RX0 TX1 RX1 */
 				status = "disabled";
@@ -732,3 +502,319 @@
 		};
 	};
 };
+
+&iomuxc {
+	audmux {
+		pinctrl_audmux_1: audmuxgrp-1 {
+			fsl,pins = <
+				MX51_PAD_AUD3_BB_TXD__AUD3_TXD 0x80000000
+				MX51_PAD_AUD3_BB_RXD__AUD3_RXD 0x80000000
+				MX51_PAD_AUD3_BB_CK__AUD3_TXC  0x80000000
+				MX51_PAD_AUD3_BB_FS__AUD3_TXFS 0x80000000
+			>;
+		};
+	};
+
+	fec {
+		pinctrl_fec_1: fecgrp-1 {
+			fsl,pins = <
+				MX51_PAD_EIM_EB2__FEC_MDIO	   0x80000000
+				MX51_PAD_EIM_EB3__FEC_RDATA1	   0x80000000
+				MX51_PAD_EIM_CS2__FEC_RDATA2	   0x80000000
+				MX51_PAD_EIM_CS3__FEC_RDATA3	   0x80000000
+				MX51_PAD_EIM_CS4__FEC_RX_ER	   0x80000000
+				MX51_PAD_EIM_CS5__FEC_CRS	   0x80000000
+				MX51_PAD_NANDF_RB2__FEC_COL	   0x80000000
+				MX51_PAD_NANDF_RB3__FEC_RX_CLK	   0x80000000
+				MX51_PAD_NANDF_D9__FEC_RDATA0	   0x80000000
+				MX51_PAD_NANDF_D8__FEC_TDATA0	   0x80000000
+				MX51_PAD_NANDF_CS2__FEC_TX_ER	   0x80000000
+				MX51_PAD_NANDF_CS3__FEC_MDC	   0x80000000
+				MX51_PAD_NANDF_CS4__FEC_TDATA1	   0x80000000
+				MX51_PAD_NANDF_CS5__FEC_TDATA2	   0x80000000
+				MX51_PAD_NANDF_CS6__FEC_TDATA3	   0x80000000
+				MX51_PAD_NANDF_CS7__FEC_TX_EN	   0x80000000
+				MX51_PAD_NANDF_RDY_INT__FEC_TX_CLK 0x80000000
+			>;
+		};
+
+		pinctrl_fec_2: fecgrp-2 {
+			fsl,pins = <
+				MX51_PAD_DI_GP3__FEC_TX_ER	  0x80000000
+				MX51_PAD_DI2_PIN4__FEC_CRS	  0x80000000
+				MX51_PAD_DI2_PIN2__FEC_MDC	  0x80000000
+				MX51_PAD_DI2_PIN3__FEC_MDIO	  0x80000000
+				MX51_PAD_DI2_DISP_CLK__FEC_RDATA1 0x80000000
+				MX51_PAD_DI_GP4__FEC_RDATA2	  0x80000000
+				MX51_PAD_DISP2_DAT0__FEC_RDATA3   0x80000000
+				MX51_PAD_DISP2_DAT1__FEC_RX_ER	  0x80000000
+				MX51_PAD_DISP2_DAT6__FEC_TDATA1	  0x80000000
+				MX51_PAD_DISP2_DAT7__FEC_TDATA2	  0x80000000
+				MX51_PAD_DISP2_DAT8__FEC_TDATA3	  0x80000000
+				MX51_PAD_DISP2_DAT9__FEC_TX_EN	  0x80000000
+				MX51_PAD_DISP2_DAT10__FEC_COL	  0x80000000
+				MX51_PAD_DISP2_DAT11__FEC_RX_CLK  0x80000000
+				MX51_PAD_DISP2_DAT12__FEC_RX_DV	  0x80000000
+				MX51_PAD_DISP2_DAT13__FEC_TX_CLK  0x80000000
+				MX51_PAD_DISP2_DAT14__FEC_RDATA0  0x80000000
+				MX51_PAD_DISP2_DAT15__FEC_TDATA0  0x80000000
+			>;
+		};
+	};
+
+	ecspi1 {
+		pinctrl_ecspi1_1: ecspi1grp-1 {
+			fsl,pins = <
+				MX51_PAD_CSPI1_MISO__ECSPI1_MISO 0x185
+				MX51_PAD_CSPI1_MOSI__ECSPI1_MOSI 0x185
+				MX51_PAD_CSPI1_SCLK__ECSPI1_SCLK 0x185
+			>;
+		};
+	};
+
+	ecspi2 {
+		pinctrl_ecspi2_1: ecspi2grp-1 {
+			fsl,pins = <
+				MX51_PAD_NANDF_RB3__ECSPI2_MISO 0x185
+				MX51_PAD_NANDF_D15__ECSPI2_MOSI 0x185
+				MX51_PAD_NANDF_RB2__ECSPI2_SCLK 0x185
+			>;
+		};
+	};
+
+	esdhc1 {
+		pinctrl_esdhc1_1: esdhc1grp-1 {
+			fsl,pins = <
+				MX51_PAD_SD1_CMD__SD1_CMD     0x400020d5
+				MX51_PAD_SD1_CLK__SD1_CLK     0x20d5
+				MX51_PAD_SD1_DATA0__SD1_DATA0 0x20d5
+				MX51_PAD_SD1_DATA1__SD1_DATA1 0x20d5
+				MX51_PAD_SD1_DATA2__SD1_DATA2 0x20d5
+				MX51_PAD_SD1_DATA3__SD1_DATA3 0x20d5
+			>;
+		};
+	};
+
+	esdhc2 {
+		pinctrl_esdhc2_1: esdhc2grp-1 {
+			fsl,pins = <
+				MX51_PAD_SD2_CMD__SD2_CMD     0x400020d5
+				MX51_PAD_SD2_CLK__SD2_CLK     0x20d5
+				MX51_PAD_SD2_DATA0__SD2_DATA0 0x20d5
+				MX51_PAD_SD2_DATA1__SD2_DATA1 0x20d5
+				MX51_PAD_SD2_DATA2__SD2_DATA2 0x20d5
+				MX51_PAD_SD2_DATA3__SD2_DATA3 0x20d5
+			>;
+		};
+	};
+
+	i2c2 {
+		pinctrl_i2c2_1: i2c2grp-1 {
+			fsl,pins = <
+				MX51_PAD_KEY_COL4__I2C2_SCL 0x400001ed
+				MX51_PAD_KEY_COL5__I2C2_SDA 0x400001ed
+			>;
+		};
+
+		pinctrl_i2c2_2: i2c2grp-2 {
+			fsl,pins = <
+				MX51_PAD_EIM_D27__I2C2_SCL 0x400001ed
+				MX51_PAD_EIM_D24__I2C2_SDA 0x400001ed
+			>;
+		};
+
+		pinctrl_i2c2_3: i2c2grp-3 {
+			fsl,pins = <
+				MX51_PAD_GPIO1_2__I2C2_SCL 0x400001ed
+				MX51_PAD_GPIO1_3__I2C2_SDA 0x400001ed
+			>;
+		};
+	};
+
+	ipu_disp1 {
+		pinctrl_ipu_disp1_1: ipudisp1grp-1 {
+			fsl,pins = <
+				MX51_PAD_DISP1_DAT0__DISP1_DAT0	  0x5
+				MX51_PAD_DISP1_DAT1__DISP1_DAT1	  0x5
+				MX51_PAD_DISP1_DAT2__DISP1_DAT2	  0x5
+				MX51_PAD_DISP1_DAT3__DISP1_DAT3	  0x5
+				MX51_PAD_DISP1_DAT4__DISP1_DAT4	  0x5
+				MX51_PAD_DISP1_DAT5__DISP1_DAT5	  0x5
+				MX51_PAD_DISP1_DAT6__DISP1_DAT6	  0x5
+				MX51_PAD_DISP1_DAT7__DISP1_DAT7	  0x5
+				MX51_PAD_DISP1_DAT8__DISP1_DAT8	  0x5
+				MX51_PAD_DISP1_DAT9__DISP1_DAT9	  0x5
+				MX51_PAD_DISP1_DAT10__DISP1_DAT10 0x5
+				MX51_PAD_DISP1_DAT11__DISP1_DAT11 0x5
+				MX51_PAD_DISP1_DAT12__DISP1_DAT12 0x5
+				MX51_PAD_DISP1_DAT13__DISP1_DAT13 0x5
+				MX51_PAD_DISP1_DAT14__DISP1_DAT14 0x5
+				MX51_PAD_DISP1_DAT15__DISP1_DAT15 0x5
+				MX51_PAD_DISP1_DAT16__DISP1_DAT16 0x5
+				MX51_PAD_DISP1_DAT17__DISP1_DAT17 0x5
+				MX51_PAD_DISP1_DAT18__DISP1_DAT18 0x5
+				MX51_PAD_DISP1_DAT19__DISP1_DAT19 0x5
+				MX51_PAD_DISP1_DAT20__DISP1_DAT20 0x5
+				MX51_PAD_DISP1_DAT21__DISP1_DAT21 0x5
+				MX51_PAD_DISP1_DAT22__DISP1_DAT22 0x5
+				MX51_PAD_DISP1_DAT23__DISP1_DAT23 0x5
+				MX51_PAD_DI1_PIN2__DI1_PIN2	  0x5 /* hsync */
+				MX51_PAD_DI1_PIN3__DI1_PIN3	  0x5 /* vsync */
+			>;
+		};
+	};
+
+	ipu_disp2 {
+		pinctrl_ipu_disp2_1: ipudisp2grp-1 {
+			fsl,pins = <
+				MX51_PAD_DISP2_DAT0__DISP2_DAT0	    0x5
+				MX51_PAD_DISP2_DAT1__DISP2_DAT1	    0x5
+				MX51_PAD_DISP2_DAT2__DISP2_DAT2	    0x5
+				MX51_PAD_DISP2_DAT3__DISP2_DAT3	    0x5
+				MX51_PAD_DISP2_DAT4__DISP2_DAT4	    0x5
+				MX51_PAD_DISP2_DAT5__DISP2_DAT5	    0x5
+				MX51_PAD_DISP2_DAT6__DISP2_DAT6	    0x5
+				MX51_PAD_DISP2_DAT7__DISP2_DAT7	    0x5
+				MX51_PAD_DISP2_DAT8__DISP2_DAT8	    0x5
+				MX51_PAD_DISP2_DAT9__DISP2_DAT9	    0x5
+				MX51_PAD_DISP2_DAT10__DISP2_DAT10   0x5
+				MX51_PAD_DISP2_DAT11__DISP2_DAT11   0x5
+				MX51_PAD_DISP2_DAT12__DISP2_DAT12   0x5
+				MX51_PAD_DISP2_DAT13__DISP2_DAT13   0x5
+				MX51_PAD_DISP2_DAT14__DISP2_DAT14   0x5
+				MX51_PAD_DISP2_DAT15__DISP2_DAT15   0x5
+				MX51_PAD_DI2_PIN2__DI2_PIN2	    0x5 /* hsync */
+				MX51_PAD_DI2_PIN3__DI2_PIN3	    0x5 /* vsync */
+				MX51_PAD_DI2_DISP_CLK__DI2_DISP_CLK 0x5 /* CLK */
+				MX51_PAD_DI_GP4__DI2_PIN15	    0x5 /* DE */
+			>;
+		};
+	};
+
+	kpp {
+		pinctrl_kpp_1: kppgrp-1 {
+			fsl,pins = <
+				MX51_PAD_KEY_ROW0__KEY_ROW0 0xe0
+				MX51_PAD_KEY_ROW1__KEY_ROW1 0xe0
+				MX51_PAD_KEY_ROW2__KEY_ROW2 0xe0
+				MX51_PAD_KEY_ROW3__KEY_ROW3 0xe0
+				MX51_PAD_KEY_COL0__KEY_COL0 0xe8
+				MX51_PAD_KEY_COL1__KEY_COL1 0xe8
+				MX51_PAD_KEY_COL2__KEY_COL2 0xe8
+				MX51_PAD_KEY_COL3__KEY_COL3 0xe8
+			>;
+		};
+	};
+
+	pata {
+		pinctrl_pata_1: patagrp-1 {
+			fsl,pins = <
+				MX51_PAD_NANDF_WE_B__PATA_DIOW	   0x2004
+				MX51_PAD_NANDF_RE_B__PATA_DIOR	   0x2004
+				MX51_PAD_NANDF_ALE__PATA_BUFFER_EN 0x2004
+				MX51_PAD_NANDF_CLE__PATA_RESET_B   0x2004
+				MX51_PAD_NANDF_WP_B__PATA_DMACK	   0x2004
+				MX51_PAD_NANDF_RB0__PATA_DMARQ	   0x2004
+				MX51_PAD_NANDF_RB1__PATA_IORDY	   0x2004
+				MX51_PAD_GPIO_NAND__PATA_INTRQ	   0x2004
+				MX51_PAD_NANDF_CS2__PATA_CS_0	   0x2004
+				MX51_PAD_NANDF_CS3__PATA_CS_1	   0x2004
+				MX51_PAD_NANDF_CS4__PATA_DA_0	   0x2004
+				MX51_PAD_NANDF_CS5__PATA_DA_1	   0x2004
+				MX51_PAD_NANDF_CS6__PATA_DA_2	   0x2004
+				MX51_PAD_NANDF_D15__PATA_DATA15	   0x2004
+				MX51_PAD_NANDF_D14__PATA_DATA14	   0x2004
+				MX51_PAD_NANDF_D13__PATA_DATA13	   0x2004
+				MX51_PAD_NANDF_D12__PATA_DATA12	   0x2004
+				MX51_PAD_NANDF_D11__PATA_DATA11	   0x2004
+				MX51_PAD_NANDF_D10__PATA_DATA10	   0x2004
+				MX51_PAD_NANDF_D9__PATA_DATA9	   0x2004
+				MX51_PAD_NANDF_D8__PATA_DATA8	   0x2004
+				MX51_PAD_NANDF_D7__PATA_DATA7	   0x2004
+				MX51_PAD_NANDF_D6__PATA_DATA6	  0x2004
+				MX51_PAD_NANDF_D5__PATA_DATA5	  0x2004
+				MX51_PAD_NANDF_D4__PATA_DATA4	  0x2004
+				MX51_PAD_NANDF_D3__PATA_DATA3	  0x2004
+				MX51_PAD_NANDF_D2__PATA_DATA2	  0x2004
+				MX51_PAD_NANDF_D1__PATA_DATA1	  0x2004
+				MX51_PAD_NANDF_D0__PATA_DATA0	  0x2004
+			>;
+		};
+	};
+
+	uart1 {
+		pinctrl_uart1_1: uart1grp-1 {
+			fsl,pins = <
+				MX51_PAD_UART1_RXD__UART1_RXD 0x1c5
+				MX51_PAD_UART1_TXD__UART1_TXD 0x1c5
+				MX51_PAD_UART1_RTS__UART1_RTS 0x1c5
+				MX51_PAD_UART1_CTS__UART1_CTS 0x1c5
+			>;
+		};
+	};
+
+	uart2 {
+		pinctrl_uart2_1: uart2grp-1 {
+			fsl,pins = <
+				MX51_PAD_UART2_RXD__UART2_RXD 0x1c5
+				MX51_PAD_UART2_TXD__UART2_TXD 0x1c5
+			>;
+		};
+	};
+
+	uart3 {
+		pinctrl_uart3_1: uart3grp-1 {
+			fsl,pins = <
+				MX51_PAD_EIM_D25__UART3_RXD 0x1c5
+				MX51_PAD_EIM_D26__UART3_TXD 0x1c5
+				MX51_PAD_EIM_D27__UART3_RTS 0x1c5
+				MX51_PAD_EIM_D24__UART3_CTS 0x1c5
+			>;
+		};
+
+		pinctrl_uart3_2: uart3grp-2 {
+			fsl,pins = <
+				MX51_PAD_UART3_RXD__UART3_RXD 0x1c5
+				MX51_PAD_UART3_TXD__UART3_TXD 0x1c5
+			>;
+		};
+	};
+
+	usbh1 {
+		pinctrl_usbh1_1: usbh1grp-1 {
+			fsl,pins = <
+				MX51_PAD_USBH1_DATA0__USBH1_DATA0 0x1e5
+				MX51_PAD_USBH1_DATA1__USBH1_DATA1 0x1e5
+				MX51_PAD_USBH1_DATA2__USBH1_DATA2 0x1e5
+				MX51_PAD_USBH1_DATA3__USBH1_DATA3 0x1e5
+				MX51_PAD_USBH1_DATA4__USBH1_DATA4 0x1e5
+				MX51_PAD_USBH1_DATA5__USBH1_DATA5 0x1e5
+				MX51_PAD_USBH1_DATA6__USBH1_DATA6 0x1e5
+				MX51_PAD_USBH1_DATA7__USBH1_DATA7 0x1e5
+				MX51_PAD_USBH1_CLK__USBH1_CLK	  0x1e5
+				MX51_PAD_USBH1_DIR__USBH1_DIR	  0x1e5
+				MX51_PAD_USBH1_NXT__USBH1_NXT	  0x1e5
+				MX51_PAD_USBH1_STP__USBH1_STP	  0x1e5
+			>;
+		};
+	};
+
+	usbh2 {
+		pinctrl_usbh2_1: usbh2grp-1 {
+			fsl,pins = <
+				MX51_PAD_EIM_D16__USBH2_DATA0 0x1e5
+				MX51_PAD_EIM_D17__USBH2_DATA1 0x1e5
+				MX51_PAD_EIM_D18__USBH2_DATA2 0x1e5
+				MX51_PAD_EIM_D19__USBH2_DATA3 0x1e5
+				MX51_PAD_EIM_D20__USBH2_DATA4 0x1e5
+				MX51_PAD_EIM_D21__USBH2_DATA5 0x1e5
+				MX51_PAD_EIM_D22__USBH2_DATA6 0x1e5
+				MX51_PAD_EIM_D23__USBH2_DATA7 0x1e5
+				MX51_PAD_EIM_A24__USBH2_CLK   0x1e5
+				MX51_PAD_EIM_A25__USBH2_DIR   0x1e5
+				MX51_PAD_EIM_A27__USBH2_NXT   0x1e5
+				MX51_PAD_EIM_A26__USBH2_STP   0x1e5
+			>;
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/imx53-qsb.dts b/arch/arm/boot/dts/imx53-qsb.dts
index 512a1f608253..e97ddae09d74 100644
--- a/arch/arm/boot/dts/imx53-qsb.dts
+++ b/arch/arm/boot/dts/imx53-qsb.dts
@@ -93,6 +93,15 @@
 			regulator-max-microvolt = <3200000>;
 			regulator-always-on;
 		};
+
+		reg_usb_vbus: usb_vbus {
+			compatible = "regulator-fixed";
+			regulator-name = "usb_vbus";
+			regulator-min-microvolt = <5000000>;
+			regulator-max-microvolt = <5000000>;
+			gpio = <&gpio7 8 0>;
+			enable-active-high;
+		};
 	};
 
 	sound {
@@ -145,6 +154,7 @@
 				MX53_PAD_EIM_DA12__GPIO3_12       0x80000000
 				MX53_PAD_EIM_DA13__GPIO3_13       0x80000000
 				MX53_PAD_PATA_DA_0__GPIO7_6       0x80000000
+				MX53_PAD_PATA_DA_2__GPIO7_8	  0x80000000
 				MX53_PAD_GPIO_16__GPIO7_11        0x80000000
 			>;
 		};
@@ -297,8 +307,14 @@
 	status = "okay";
 };
 
+&vpu {
+	status = "okay";
+};
+
 &usbh1 {
-       status = "okay";
+	vbus-supply = <&reg_usb_vbus>;
+	phy_type = "utmi";
+	status = "okay";
 };
 
 &usbotg {
diff --git a/arch/arm/boot/dts/imx53.dtsi b/arch/arm/boot/dts/imx53.dtsi
index 569aa9f2c4ed..4307e80b2d2e 100644
--- a/arch/arm/boot/dts/imx53.dtsi
+++ b/arch/arm/boot/dts/imx53.dtsi
@@ -15,11 +15,6 @@
 
 / {
 	aliases {
-		serial0 = &uart1;
-		serial1 = &uart2;
-		serial2 = &uart3;
-		serial3 = &uart4;
-		serial4 = &uart5;
 		gpio0 = &gpio1;
 		gpio1 = &gpio2;
 		gpio2 = &gpio3;
@@ -30,6 +25,24 @@
 		i2c0 = &i2c1;
 		i2c1 = &i2c2;
 		i2c2 = &i2c3;
+		serial0 = &uart1;
+		serial1 = &uart2;
+		serial2 = &uart3;
+		serial3 = &uart4;
+		serial4 = &uart5;
+		spi0 = &ecspi1;
+		spi1 = &ecspi2;
+		spi2 = &cspi;
+	};
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+		cpu@0 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a8";
+			reg = <0x0>;
+		};
 	};
 
 	tzic: tz-interrupt-controller@0fffc000 {
@@ -140,6 +153,9 @@
 					reg = <0x50014000 0x4000>;
 					interrupts = <30>;
 					clocks = <&clks 49>;
+					dmas = <&sdma 24 1 0>,
+					       <&sdma 25 1 0>;
+					dma-names = "rx", "tx";
 					fsl,fifo-depth = <15>;
 					fsl,ssi-dma-events = <25 24 23 22>; /* TX0 RX0 TX1 RX1 */
 					status = "disabled";
@@ -957,6 +973,13 @@
 			reg = <0x60000000 0x10000000>;
 			ranges;
 
+			iim: iim@63f98000 {
+				compatible = "fsl,imx53-iim", "fsl,imx27-iim";
+				reg = <0x63f98000 0x4000>;
+				interrupts = <69>;
+				clocks = <&clks 107>;
+			};
+
 			uart5: serial@63f90000 {
 				compatible = "fsl,imx53-uart", "fsl,imx21-uart";
 				reg = <0x63f90000 0x4000>;
@@ -990,6 +1013,7 @@
 				interrupts = <6>;
 				clocks = <&clks 56>, <&clks 56>;
 				clock-names = "ipg", "ahb";
+				#dma-cells = <3>;
 				fsl,sdma-ram-script-name = "imx/sdma/sdma-imx53.bin";
 			};
 
@@ -1029,6 +1053,9 @@
 				reg = <0x63fcc000 0x4000>;
 				interrupts = <29>;
 				clocks = <&clks 48>;
+				dmas = <&sdma 28 0 0>,
+				       <&sdma 29 0 0>;
+				dma-names = "rx", "tx";
 				fsl,fifo-depth = <15>;
 				fsl,ssi-dma-events = <29 28 27 26>; /* TX0 RX0 TX1 RX1 */
 				status = "disabled";
@@ -1053,6 +1080,9 @@
 				reg = <0x63fe8000 0x4000>;
 				interrupts = <96>;
 				clocks = <&clks 50>;
+				dmas = <&sdma 46 0 0>,
+				       <&sdma 47 0 0>;
+				dma-names = "rx", "tx";
 				fsl,fifo-depth = <15>;
 				fsl,ssi-dma-events = <47 46 45 44>; /* TX0 RX0 TX1 RX1 */
 				status = "disabled";
@@ -1076,6 +1106,22 @@
 				crtcs = <&ipu 1>;
 				status = "disabled";
 			};
+
+			vpu: vpu@63ff4000 {
+				compatible = "fsl,imx53-vpu";
+				reg = <0x63ff4000 0x1000>;
+				interrupts = <9>;
+				clocks = <&clks 63>, <&clks 63>;
+				clock-names = "per", "ahb";
+				iram = <&ocram>;
+				status = "disabled";
+			};
+		};
+
+		ocram: sram@f8000000 {
+			compatible = "mmio-sram";
+			reg = <0xf8000000 0x20000>;
+			clocks = <&clks 186>;
 		};
 	};
 };
diff --git a/arch/arm/boot/dts/imx6dl-pinfunc.h b/arch/arm/boot/dts/imx6dl-pinfunc.h
index 9aab950ec269..b81a7a4ebab6 100644
--- a/arch/arm/boot/dts/imx6dl-pinfunc.h
+++ b/arch/arm/boot/dts/imx6dl-pinfunc.h
@@ -14,1072 +14,1076 @@
  * The pin function ID is a tuple of
  * <mux_reg conf_reg input_reg mux_mode input_val>
  */
-#define MX6DL_PAD_CSI0_DAT10__IPU1_CSI0_DATA10     0x04c 0x360 0x000 0x0 0x0
-#define MX6DL_PAD_CSI0_DAT10__AUD3_RXC             0x04c 0x360 0x000 0x1 0x0
-#define MX6DL_PAD_CSI0_DAT10__ECSPI2_MISO          0x04c 0x360 0x7f8 0x2 0x0
-#define MX6DL_PAD_CSI0_DAT10__UART1_TX_DATA        0x04c 0x360 0x000 0x3 0x0
-#define MX6DL_PAD_CSI0_DAT10__UART1_RX_DATA        0x04c 0x360 0x8fc 0x3 0x0
-#define MX6DL_PAD_CSI0_DAT10__GPIO5_IO28           0x04c 0x360 0x000 0x5 0x0
-#define MX6DL_PAD_CSI0_DAT10__ARM_TRACE07          0x04c 0x360 0x000 0x7 0x0
-#define MX6DL_PAD_CSI0_DAT11__IPU1_CSI0_DATA11     0x050 0x364 0x000 0x0 0x0
-#define MX6DL_PAD_CSI0_DAT11__AUD3_RXFS            0x050 0x364 0x000 0x1 0x0
-#define MX6DL_PAD_CSI0_DAT11__ECSPI2_SS0           0x050 0x364 0x800 0x2 0x0
-#define MX6DL_PAD_CSI0_DAT11__UART1_RX_DATA        0x050 0x364 0x8fc 0x3 0x1
-#define MX6DL_PAD_CSI0_DAT11__UART1_TX_DATA        0x050 0x364 0x000 0x3 0x0
-#define MX6DL_PAD_CSI0_DAT11__GPIO5_IO29           0x050 0x364 0x000 0x5 0x0
-#define MX6DL_PAD_CSI0_DAT11__ARM_TRACE08          0x050 0x364 0x000 0x7 0x0
-#define MX6DL_PAD_CSI0_DAT12__IPU1_CSI0_DATA12     0x054 0x368 0x000 0x0 0x0
-#define MX6DL_PAD_CSI0_DAT12__EIM_DATA08           0x054 0x368 0x000 0x1 0x0
-#define MX6DL_PAD_CSI0_DAT12__UART4_TX_DATA        0x054 0x368 0x000 0x3 0x0
-#define MX6DL_PAD_CSI0_DAT12__UART4_RX_DATA        0x054 0x368 0x914 0x3 0x0
-#define MX6DL_PAD_CSI0_DAT12__GPIO5_IO30           0x054 0x368 0x000 0x5 0x0
-#define MX6DL_PAD_CSI0_DAT12__ARM_TRACE09          0x054 0x368 0x000 0x7 0x0
-#define MX6DL_PAD_CSI0_DAT13__IPU1_CSI0_DATA13     0x058 0x36c 0x000 0x0 0x0
-#define MX6DL_PAD_CSI0_DAT13__EIM_DATA09           0x058 0x36c 0x000 0x1 0x0
-#define MX6DL_PAD_CSI0_DAT13__UART4_RX_DATA        0x058 0x36c 0x914 0x3 0x1
-#define MX6DL_PAD_CSI0_DAT13__UART4_TX_DATA        0x058 0x36c 0x000 0x3 0x0
-#define MX6DL_PAD_CSI0_DAT13__GPIO5_IO31           0x058 0x36c 0x000 0x5 0x0
-#define MX6DL_PAD_CSI0_DAT13__ARM_TRACE10          0x058 0x36c 0x000 0x7 0x0
-#define MX6DL_PAD_CSI0_DAT14__IPU1_CSI0_DATA14     0x05c 0x370 0x000 0x0 0x0
-#define MX6DL_PAD_CSI0_DAT14__EIM_DATA10           0x05c 0x370 0x000 0x1 0x0
-#define MX6DL_PAD_CSI0_DAT14__UART5_TX_DATA        0x05c 0x370 0x000 0x3 0x0
-#define MX6DL_PAD_CSI0_DAT14__UART5_RX_DATA        0x05c 0x370 0x91c 0x3 0x0
-#define MX6DL_PAD_CSI0_DAT14__GPIO6_IO00           0x05c 0x370 0x000 0x5 0x0
-#define MX6DL_PAD_CSI0_DAT14__ARM_TRACE11          0x05c 0x370 0x000 0x7 0x0
-#define MX6DL_PAD_CSI0_DAT15__IPU1_CSI0_DATA15     0x060 0x374 0x000 0x0 0x0
-#define MX6DL_PAD_CSI0_DAT15__EIM_DATA11           0x060 0x374 0x000 0x1 0x0
-#define MX6DL_PAD_CSI0_DAT15__UART5_RX_DATA        0x060 0x374 0x91c 0x3 0x1
-#define MX6DL_PAD_CSI0_DAT15__UART5_TX_DATA        0x060 0x374 0x000 0x3 0x0
-#define MX6DL_PAD_CSI0_DAT15__GPIO6_IO01           0x060 0x374 0x000 0x5 0x0
-#define MX6DL_PAD_CSI0_DAT15__ARM_TRACE12          0x060 0x374 0x000 0x7 0x0
-#define MX6DL_PAD_CSI0_DAT16__IPU1_CSI0_DATA16     0x064 0x378 0x000 0x0 0x0
-#define MX6DL_PAD_CSI0_DAT16__EIM_DATA12           0x064 0x378 0x000 0x1 0x0
-#define MX6DL_PAD_CSI0_DAT16__UART4_RTS_B          0x064 0x378 0x910 0x3 0x0
-#define MX6DL_PAD_CSI0_DAT16__UART4_CTS_B          0x064 0x378 0x000 0x3 0x0
-#define MX6DL_PAD_CSI0_DAT16__GPIO6_IO02           0x064 0x378 0x000 0x5 0x0
-#define MX6DL_PAD_CSI0_DAT16__ARM_TRACE13          0x064 0x378 0x000 0x7 0x0
-#define MX6DL_PAD_CSI0_DAT17__IPU1_CSI0_DATA17     0x068 0x37c 0x000 0x0 0x0
-#define MX6DL_PAD_CSI0_DAT17__EIM_DATA13           0x068 0x37c 0x000 0x1 0x0
-#define MX6DL_PAD_CSI0_DAT17__UART4_CTS_B          0x068 0x37c 0x000 0x3 0x0
-#define MX6DL_PAD_CSI0_DAT17__UART4_RTS_B          0x068 0x37c 0x910 0x3 0x1
-#define MX6DL_PAD_CSI0_DAT17__GPIO6_IO03           0x068 0x37c 0x000 0x5 0x0
-#define MX6DL_PAD_CSI0_DAT17__ARM_TRACE14          0x068 0x37c 0x000 0x7 0x0
-#define MX6DL_PAD_CSI0_DAT18__IPU1_CSI0_DATA18     0x06c 0x380 0x000 0x0 0x0
-#define MX6DL_PAD_CSI0_DAT18__EIM_DATA14           0x06c 0x380 0x000 0x1 0x0
-#define MX6DL_PAD_CSI0_DAT18__UART5_RTS_B          0x06c 0x380 0x918 0x3 0x0
-#define MX6DL_PAD_CSI0_DAT18__UART5_CTS_B          0x06c 0x380 0x000 0x3 0x0
-#define MX6DL_PAD_CSI0_DAT18__GPIO6_IO04           0x06c 0x380 0x000 0x5 0x0
-#define MX6DL_PAD_CSI0_DAT18__ARM_TRACE15          0x06c 0x380 0x000 0x7 0x0
-#define MX6DL_PAD_CSI0_DAT19__IPU1_CSI0_DATA19     0x070 0x384 0x000 0x0 0x0
-#define MX6DL_PAD_CSI0_DAT19__EIM_DATA15           0x070 0x384 0x000 0x1 0x0
-#define MX6DL_PAD_CSI0_DAT19__UART5_CTS_B          0x070 0x384 0x000 0x3 0x0
-#define MX6DL_PAD_CSI0_DAT19__UART5_RTS_B          0x070 0x384 0x918 0x3 0x1
-#define MX6DL_PAD_CSI0_DAT19__GPIO6_IO05           0x070 0x384 0x000 0x5 0x0
-#define MX6DL_PAD_CSI0_DAT4__IPU1_CSI0_DATA04      0x074 0x388 0x000 0x0 0x0
-#define MX6DL_PAD_CSI0_DAT4__EIM_DATA02            0x074 0x388 0x000 0x1 0x0
-#define MX6DL_PAD_CSI0_DAT4__ECSPI1_SCLK           0x074 0x388 0x7d8 0x2 0x0
-#define MX6DL_PAD_CSI0_DAT4__KEY_COL5              0x074 0x388 0x8c0 0x3 0x0
-#define MX6DL_PAD_CSI0_DAT4__AUD3_TXC              0x074 0x388 0x000 0x4 0x0
-#define MX6DL_PAD_CSI0_DAT4__GPIO5_IO22            0x074 0x388 0x000 0x5 0x0
-#define MX6DL_PAD_CSI0_DAT4__ARM_TRACE01           0x074 0x388 0x000 0x7 0x0
-#define MX6DL_PAD_CSI0_DAT5__IPU1_CSI0_DATA05      0x078 0x38c 0x000 0x0 0x0
-#define MX6DL_PAD_CSI0_DAT5__EIM_DATA03            0x078 0x38c 0x000 0x1 0x0
-#define MX6DL_PAD_CSI0_DAT5__ECSPI1_MOSI           0x078 0x38c 0x7e0 0x2 0x0
-#define MX6DL_PAD_CSI0_DAT5__KEY_ROW5              0x078 0x38c 0x8cc 0x3 0x0
-#define MX6DL_PAD_CSI0_DAT5__AUD3_TXD              0x078 0x38c 0x000 0x4 0x0
-#define MX6DL_PAD_CSI0_DAT5__GPIO5_IO23            0x078 0x38c 0x000 0x5 0x0
-#define MX6DL_PAD_CSI0_DAT5__ARM_TRACE02           0x078 0x38c 0x000 0x7 0x0
-#define MX6DL_PAD_CSI0_DAT6__IPU1_CSI0_DATA06      0x07c 0x390 0x000 0x0 0x0
-#define MX6DL_PAD_CSI0_DAT6__EIM_DATA04            0x07c 0x390 0x000 0x1 0x0
-#define MX6DL_PAD_CSI0_DAT6__ECSPI1_MISO           0x07c 0x390 0x7dc 0x2 0x0
-#define MX6DL_PAD_CSI0_DAT6__KEY_COL6              0x07c 0x390 0x8c4 0x3 0x0
-#define MX6DL_PAD_CSI0_DAT6__AUD3_TXFS             0x07c 0x390 0x000 0x4 0x0
-#define MX6DL_PAD_CSI0_DAT6__GPIO5_IO24            0x07c 0x390 0x000 0x5 0x0
-#define MX6DL_PAD_CSI0_DAT6__ARM_TRACE03           0x07c 0x390 0x000 0x7 0x0
-#define MX6DL_PAD_CSI0_DAT7__IPU1_CSI0_DATA07      0x080 0x394 0x000 0x0 0x0
-#define MX6DL_PAD_CSI0_DAT7__EIM_DATA05            0x080 0x394 0x000 0x1 0x0
-#define MX6DL_PAD_CSI0_DAT7__ECSPI1_SS0            0x080 0x394 0x7e4 0x2 0x0
-#define MX6DL_PAD_CSI0_DAT7__KEY_ROW6              0x080 0x394 0x8d0 0x3 0x0
-#define MX6DL_PAD_CSI0_DAT7__AUD3_RXD              0x080 0x394 0x000 0x4 0x0
-#define MX6DL_PAD_CSI0_DAT7__GPIO5_IO25            0x080 0x394 0x000 0x5 0x0
-#define MX6DL_PAD_CSI0_DAT7__ARM_TRACE04           0x080 0x394 0x000 0x7 0x0
-#define MX6DL_PAD_CSI0_DAT8__IPU1_CSI0_DATA08      0x084 0x398 0x000 0x0 0x0
-#define MX6DL_PAD_CSI0_DAT8__EIM_DATA06            0x084 0x398 0x000 0x1 0x0
-#define MX6DL_PAD_CSI0_DAT8__ECSPI2_SCLK           0x084 0x398 0x7f4 0x2 0x0
-#define MX6DL_PAD_CSI0_DAT8__KEY_COL7              0x084 0x398 0x8c8 0x3 0x0
-#define MX6DL_PAD_CSI0_DAT8__I2C1_SDA              0x084 0x398 0x86c 0x4 0x0
-#define MX6DL_PAD_CSI0_DAT8__GPIO5_IO26            0x084 0x398 0x000 0x5 0x0
-#define MX6DL_PAD_CSI0_DAT8__ARM_TRACE05           0x084 0x398 0x000 0x7 0x0
-#define MX6DL_PAD_CSI0_DAT9__IPU1_CSI0_DATA09      0x088 0x39c 0x000 0x0 0x0
-#define MX6DL_PAD_CSI0_DAT9__EIM_DATA07            0x088 0x39c 0x000 0x1 0x0
-#define MX6DL_PAD_CSI0_DAT9__ECSPI2_MOSI           0x088 0x39c 0x7fc 0x2 0x0
-#define MX6DL_PAD_CSI0_DAT9__KEY_ROW7              0x088 0x39c 0x8d4 0x3 0x0
-#define MX6DL_PAD_CSI0_DAT9__I2C1_SCL              0x088 0x39c 0x868 0x4 0x0
-#define MX6DL_PAD_CSI0_DAT9__GPIO5_IO27            0x088 0x39c 0x000 0x5 0x0
-#define MX6DL_PAD_CSI0_DAT9__ARM_TRACE06           0x088 0x39c 0x000 0x7 0x0
-#define MX6DL_PAD_CSI0_DATA_EN__IPU1_CSI0_DATA_EN  0x08c 0x3a0 0x000 0x0 0x0
-#define MX6DL_PAD_CSI0_DATA_EN__EIM_DATA00         0x08c 0x3a0 0x000 0x1 0x0
-#define MX6DL_PAD_CSI0_DATA_EN__GPIO5_IO20         0x08c 0x3a0 0x000 0x5 0x0
-#define MX6DL_PAD_CSI0_DATA_EN__ARM_TRACE_CLK      0x08c 0x3a0 0x000 0x7 0x0
-#define MX6DL_PAD_CSI0_MCLK__IPU1_CSI0_HSYNC       0x090 0x3a4 0x000 0x0 0x0
-#define MX6DL_PAD_CSI0_MCLK__CCM_CLKO1             0x090 0x3a4 0x000 0x3 0x0
-#define MX6DL_PAD_CSI0_MCLK__GPIO5_IO19            0x090 0x3a4 0x000 0x5 0x0
-#define MX6DL_PAD_CSI0_MCLK__ARM_TRACE_CTL         0x090 0x3a4 0x000 0x7 0x0
-#define MX6DL_PAD_CSI0_PIXCLK__IPU1_CSI0_PIXCLK    0x094 0x3a8 0x000 0x0 0x0
-#define MX6DL_PAD_CSI0_PIXCLK__GPIO5_IO18          0x094 0x3a8 0x000 0x5 0x0
-#define MX6DL_PAD_CSI0_PIXCLK__ARM_EVENTO          0x094 0x3a8 0x000 0x7 0x0
-#define MX6DL_PAD_CSI0_VSYNC__IPU1_CSI0_VSYNC      0x098 0x3ac 0x000 0x0 0x0
-#define MX6DL_PAD_CSI0_VSYNC__EIM_DATA01           0x098 0x3ac 0x000 0x1 0x0
-#define MX6DL_PAD_CSI0_VSYNC__GPIO5_IO21           0x098 0x3ac 0x000 0x5 0x0
-#define MX6DL_PAD_CSI0_VSYNC__ARM_TRACE00          0x098 0x3ac 0x000 0x7 0x0
-#define MX6DL_PAD_DI0_DISP_CLK__IPU1_DI0_DISP_CLK  0x09c 0x3b0 0x000 0x0 0x0
-#define MX6DL_PAD_DI0_DISP_CLK__LCD_CLK            0x09c 0x3b0 0x000 0x1 0x0
-#define MX6DL_PAD_DI0_DISP_CLK__GPIO4_IO16         0x09c 0x3b0 0x000 0x5 0x0
-#define MX6DL_PAD_DI0_DISP_CLK__LCD_WR_RWN         0x09c 0x3b0 0x000 0x8 0x0
-#define MX6DL_PAD_DI0_PIN15__IPU1_DI0_PIN15        0x0a0 0x3b4 0x000 0x0 0x0
-#define MX6DL_PAD_DI0_PIN15__LCD_ENABLE            0x0a0 0x3b4 0x000 0x1 0x0
-#define MX6DL_PAD_DI0_PIN15__AUD6_TXC              0x0a0 0x3b4 0x000 0x2 0x0
-#define MX6DL_PAD_DI0_PIN15__GPIO4_IO17            0x0a0 0x3b4 0x000 0x5 0x0
-#define MX6DL_PAD_DI0_PIN15__LCD_RD_E              0x0a0 0x3b4 0x000 0x8 0x0
-#define MX6DL_PAD_DI0_PIN2__IPU1_DI0_PIN02         0x0a4 0x3b8 0x000 0x0 0x0
-#define MX6DL_PAD_DI0_PIN2__LCD_HSYNC              0x0a4 0x3b8 0x8d8 0x1 0x0
-#define MX6DL_PAD_DI0_PIN2__AUD6_TXD               0x0a4 0x3b8 0x000 0x2 0x0
-#define MX6DL_PAD_DI0_PIN2__GPIO4_IO18             0x0a4 0x3b8 0x000 0x5 0x0
-#define MX6DL_PAD_DI0_PIN2__LCD_RS                 0x0a4 0x3b8 0x000 0x8 0x0
-#define MX6DL_PAD_DI0_PIN3__IPU1_DI0_PIN03         0x0a8 0x3bc 0x000 0x0 0x0
-#define MX6DL_PAD_DI0_PIN3__LCD_VSYNC              0x0a8 0x3bc 0x000 0x1 0x0
-#define MX6DL_PAD_DI0_PIN3__AUD6_TXFS              0x0a8 0x3bc 0x000 0x2 0x0
-#define MX6DL_PAD_DI0_PIN3__GPIO4_IO19             0x0a8 0x3bc 0x000 0x5 0x0
-#define MX6DL_PAD_DI0_PIN3__LCD_CS                 0x0a8 0x3bc 0x000 0x8 0x0
-#define MX6DL_PAD_DI0_PIN4__IPU1_DI0_PIN04         0x0ac 0x3c0 0x000 0x0 0x0
-#define MX6DL_PAD_DI0_PIN4__LCD_BUSY               0x0ac 0x3c0 0x8d8 0x1 0x1
-#define MX6DL_PAD_DI0_PIN4__AUD6_RXD               0x0ac 0x3c0 0x000 0x2 0x0
-#define MX6DL_PAD_DI0_PIN4__SD1_WP                 0x0ac 0x3c0 0x92c 0x3 0x0
-#define MX6DL_PAD_DI0_PIN4__GPIO4_IO20             0x0ac 0x3c0 0x000 0x5 0x0
-#define MX6DL_PAD_DI0_PIN4__LCD_RESET              0x0ac 0x3c0 0x000 0x8 0x0
-#define MX6DL_PAD_DISP0_DAT0__IPU1_DISP0_DATA00    0x0b0 0x3c4 0x000 0x0 0x0
-#define MX6DL_PAD_DISP0_DAT0__LCD_DATA00           0x0b0 0x3c4 0x000 0x1 0x0
-#define MX6DL_PAD_DISP0_DAT0__ECSPI3_SCLK          0x0b0 0x3c4 0x000 0x2 0x0
-#define MX6DL_PAD_DISP0_DAT0__GPIO4_IO21           0x0b0 0x3c4 0x000 0x5 0x0
-#define MX6DL_PAD_DISP0_DAT1__IPU1_DISP0_DATA01    0x0b4 0x3c8 0x000 0x0 0x0
-#define MX6DL_PAD_DISP0_DAT1__LCD_DATA01           0x0b4 0x3c8 0x000 0x1 0x0
-#define MX6DL_PAD_DISP0_DAT1__ECSPI3_MOSI          0x0b4 0x3c8 0x000 0x2 0x0
-#define MX6DL_PAD_DISP0_DAT1__GPIO4_IO22           0x0b4 0x3c8 0x000 0x5 0x0
-#define MX6DL_PAD_DISP0_DAT10__IPU1_DISP0_DATA10   0x0b8 0x3cc 0x000 0x0 0x0
-#define MX6DL_PAD_DISP0_DAT10__LCD_DATA10          0x0b8 0x3cc 0x000 0x1 0x0
-#define MX6DL_PAD_DISP0_DAT10__GPIO4_IO31          0x0b8 0x3cc 0x000 0x5 0x0
-#define MX6DL_PAD_DISP0_DAT11__IPU1_DISP0_DATA11   0x0bc 0x3d0 0x000 0x0 0x0
-#define MX6DL_PAD_DISP0_DAT11__LCD_DATA11          0x0bc 0x3d0 0x000 0x1 0x0
-#define MX6DL_PAD_DISP0_DAT11__GPIO5_IO05          0x0bc 0x3d0 0x000 0x5 0x0
-#define MX6DL_PAD_DISP0_DAT12__IPU1_DISP0_DATA12   0x0c0 0x3d4 0x000 0x0 0x0
-#define MX6DL_PAD_DISP0_DAT12__LCD_DATA12          0x0c0 0x3d4 0x000 0x1 0x0
-#define MX6DL_PAD_DISP0_DAT12__GPIO5_IO06          0x0c0 0x3d4 0x000 0x5 0x0
-#define MX6DL_PAD_DISP0_DAT13__IPU1_DISP0_DATA13   0x0c4 0x3d8 0x000 0x0 0x0
-#define MX6DL_PAD_DISP0_DAT13__LCD_DATA13          0x0c4 0x3d8 0x000 0x1 0x0
-#define MX6DL_PAD_DISP0_DAT13__AUD5_RXFS           0x0c4 0x3d8 0x7bc 0x3 0x0
-#define MX6DL_PAD_DISP0_DAT13__GPIO5_IO07          0x0c4 0x3d8 0x000 0x5 0x0
-#define MX6DL_PAD_DISP0_DAT14__IPU1_DISP0_DATA14   0x0c8 0x3dc 0x000 0x0 0x0
-#define MX6DL_PAD_DISP0_DAT14__LCD_DATA14          0x0c8 0x3dc 0x000 0x1 0x0
-#define MX6DL_PAD_DISP0_DAT14__AUD5_RXC            0x0c8 0x3dc 0x7b8 0x3 0x0
-#define MX6DL_PAD_DISP0_DAT14__GPIO5_IO08          0x0c8 0x3dc 0x000 0x5 0x0
-#define MX6DL_PAD_DISP0_DAT15__IPU1_DISP0_DATA15   0x0cc 0x3e0 0x000 0x0 0x0
-#define MX6DL_PAD_DISP0_DAT15__LCD_DATA15          0x0cc 0x3e0 0x000 0x1 0x0
-#define MX6DL_PAD_DISP0_DAT15__ECSPI1_SS1          0x0cc 0x3e0 0x7e8 0x2 0x0
-#define MX6DL_PAD_DISP0_DAT15__ECSPI2_SS1          0x0cc 0x3e0 0x804 0x3 0x0
-#define MX6DL_PAD_DISP0_DAT15__GPIO5_IO09          0x0cc 0x3e0 0x000 0x5 0x0
-#define MX6DL_PAD_DISP0_DAT16__IPU1_DISP0_DATA16   0x0d0 0x3e4 0x000 0x0 0x0
-#define MX6DL_PAD_DISP0_DAT16__LCD_DATA16          0x0d0 0x3e4 0x000 0x1 0x0
-#define MX6DL_PAD_DISP0_DAT16__ECSPI2_MOSI         0x0d0 0x3e4 0x7fc 0x2 0x1
-#define MX6DL_PAD_DISP0_DAT16__AUD5_TXC            0x0d0 0x3e4 0x7c0 0x3 0x0
-#define MX6DL_PAD_DISP0_DAT16__SDMA_EXT_EVENT0     0x0d0 0x3e4 0x8e8 0x4 0x0
-#define MX6DL_PAD_DISP0_DAT16__GPIO5_IO10          0x0d0 0x3e4 0x000 0x5 0x0
-#define MX6DL_PAD_DISP0_DAT17__IPU1_DISP0_DATA17   0x0d4 0x3e8 0x000 0x0 0x0
-#define MX6DL_PAD_DISP0_DAT17__LCD_DATA17          0x0d4 0x3e8 0x000 0x1 0x0
-#define MX6DL_PAD_DISP0_DAT17__ECSPI2_MISO         0x0d4 0x3e8 0x7f8 0x2 0x1
-#define MX6DL_PAD_DISP0_DAT17__AUD5_TXD            0x0d4 0x3e8 0x7b4 0x3 0x0
-#define MX6DL_PAD_DISP0_DAT17__SDMA_EXT_EVENT1     0x0d4 0x3e8 0x8ec 0x4 0x0
-#define MX6DL_PAD_DISP0_DAT17__GPIO5_IO11          0x0d4 0x3e8 0x000 0x5 0x0
-#define MX6DL_PAD_DISP0_DAT18__IPU1_DISP0_DATA18   0x0d8 0x3ec 0x000 0x0 0x0
-#define MX6DL_PAD_DISP0_DAT18__LCD_DATA18          0x0d8 0x3ec 0x000 0x1 0x0
-#define MX6DL_PAD_DISP0_DAT18__ECSPI2_SS0          0x0d8 0x3ec 0x800 0x2 0x1
-#define MX6DL_PAD_DISP0_DAT18__AUD5_TXFS           0x0d8 0x3ec 0x7c4 0x3 0x0
-#define MX6DL_PAD_DISP0_DAT18__AUD4_RXFS           0x0d8 0x3ec 0x7a4 0x4 0x0
-#define MX6DL_PAD_DISP0_DAT18__GPIO5_IO12          0x0d8 0x3ec 0x000 0x5 0x0
-#define MX6DL_PAD_DISP0_DAT18__EIM_CS2_B           0x0d8 0x3ec 0x000 0x7 0x0
-#define MX6DL_PAD_DISP0_DAT19__IPU1_DISP0_DATA19   0x0dc 0x3f0 0x000 0x0 0x0
-#define MX6DL_PAD_DISP0_DAT19__LCD_DATA19          0x0dc 0x3f0 0x000 0x1 0x0
-#define MX6DL_PAD_DISP0_DAT19__ECSPI2_SCLK         0x0dc 0x3f0 0x7f4 0x2 0x1
-#define MX6DL_PAD_DISP0_DAT19__AUD5_RXD            0x0dc 0x3f0 0x7b0 0x3 0x0
-#define MX6DL_PAD_DISP0_DAT19__AUD4_RXC            0x0dc 0x3f0 0x7a0 0x4 0x0
-#define MX6DL_PAD_DISP0_DAT19__GPIO5_IO13          0x0dc 0x3f0 0x000 0x5 0x0
-#define MX6DL_PAD_DISP0_DAT19__EIM_CS3_B           0x0dc 0x3f0 0x000 0x7 0x0
-#define MX6DL_PAD_DISP0_DAT2__IPU1_DISP0_DATA02    0x0e0 0x3f4 0x000 0x0 0x0
-#define MX6DL_PAD_DISP0_DAT2__LCD_DATA02           0x0e0 0x3f4 0x000 0x1 0x0
-#define MX6DL_PAD_DISP0_DAT2__ECSPI3_MISO          0x0e0 0x3f4 0x000 0x2 0x0
-#define MX6DL_PAD_DISP0_DAT2__GPIO4_IO23           0x0e0 0x3f4 0x000 0x5 0x0
-#define MX6DL_PAD_DISP0_DAT20__IPU1_DISP0_DATA20   0x0e4 0x3f8 0x000 0x0 0x0
-#define MX6DL_PAD_DISP0_DAT20__LCD_DATA20          0x0e4 0x3f8 0x000 0x1 0x0
-#define MX6DL_PAD_DISP0_DAT20__ECSPI1_SCLK         0x0e4 0x3f8 0x7d8 0x2 0x1
-#define MX6DL_PAD_DISP0_DAT20__AUD4_TXC            0x0e4 0x3f8 0x7a8 0x3 0x0
-#define MX6DL_PAD_DISP0_DAT20__GPIO5_IO14          0x0e4 0x3f8 0x000 0x5 0x0
-#define MX6DL_PAD_DISP0_DAT21__IPU1_DISP0_DATA21   0x0e8 0x3fc 0x000 0x0 0x0
-#define MX6DL_PAD_DISP0_DAT21__LCD_DATA21          0x0e8 0x3fc 0x000 0x1 0x0
-#define MX6DL_PAD_DISP0_DAT21__ECSPI1_MOSI         0x0e8 0x3fc 0x7e0 0x2 0x1
-#define MX6DL_PAD_DISP0_DAT21__AUD4_TXD            0x0e8 0x3fc 0x79c 0x3 0x0
-#define MX6DL_PAD_DISP0_DAT21__GPIO5_IO15          0x0e8 0x3fc 0x000 0x5 0x0
-#define MX6DL_PAD_DISP0_DAT22__IPU1_DISP0_DATA22   0x0ec 0x400 0x000 0x0 0x0
-#define MX6DL_PAD_DISP0_DAT22__LCD_DATA22          0x0ec 0x400 0x000 0x1 0x0
-#define MX6DL_PAD_DISP0_DAT22__ECSPI1_MISO         0x0ec 0x400 0x7dc 0x2 0x1
-#define MX6DL_PAD_DISP0_DAT22__AUD4_TXFS           0x0ec 0x400 0x7ac 0x3 0x0
-#define MX6DL_PAD_DISP0_DAT22__GPIO5_IO16          0x0ec 0x400 0x000 0x5 0x0
-#define MX6DL_PAD_DISP0_DAT23__IPU1_DISP0_DATA23   0x0f0 0x404 0x000 0x0 0x0
-#define MX6DL_PAD_DISP0_DAT23__LCD_DATA23          0x0f0 0x404 0x000 0x1 0x0
-#define MX6DL_PAD_DISP0_DAT23__ECSPI1_SS0          0x0f0 0x404 0x7e4 0x2 0x1
-#define MX6DL_PAD_DISP0_DAT23__AUD4_RXD            0x0f0 0x404 0x798 0x3 0x0
-#define MX6DL_PAD_DISP0_DAT23__GPIO5_IO17          0x0f0 0x404 0x000 0x5 0x0
-#define MX6DL_PAD_DISP0_DAT3__IPU1_DISP0_DATA03    0x0f4 0x408 0x000 0x0 0x0
-#define MX6DL_PAD_DISP0_DAT3__LCD_DATA03           0x0f4 0x408 0x000 0x1 0x0
-#define MX6DL_PAD_DISP0_DAT3__ECSPI3_SS0           0x0f4 0x408 0x000 0x2 0x0
-#define MX6DL_PAD_DISP0_DAT3__GPIO4_IO24           0x0f4 0x408 0x000 0x5 0x0
-#define MX6DL_PAD_DISP0_DAT4__IPU1_DISP0_DATA04    0x0f8 0x40c 0x000 0x0 0x0
-#define MX6DL_PAD_DISP0_DAT4__LCD_DATA04           0x0f8 0x40c 0x000 0x1 0x0
-#define MX6DL_PAD_DISP0_DAT4__ECSPI3_SS1           0x0f8 0x40c 0x000 0x2 0x0
-#define MX6DL_PAD_DISP0_DAT4__GPIO4_IO25           0x0f8 0x40c 0x000 0x5 0x0
-#define MX6DL_PAD_DISP0_DAT5__IPU1_DISP0_DATA05    0x0fc 0x410 0x000 0x0 0x0
-#define MX6DL_PAD_DISP0_DAT5__LCD_DATA05           0x0fc 0x410 0x000 0x1 0x0
-#define MX6DL_PAD_DISP0_DAT5__ECSPI3_SS2           0x0fc 0x410 0x000 0x2 0x0
-#define MX6DL_PAD_DISP0_DAT5__AUD6_RXFS            0x0fc 0x410 0x000 0x3 0x0
-#define MX6DL_PAD_DISP0_DAT5__GPIO4_IO26           0x0fc 0x410 0x000 0x5 0x0
-#define MX6DL_PAD_DISP0_DAT6__IPU1_DISP0_DATA06    0x100 0x414 0x000 0x0 0x0
-#define MX6DL_PAD_DISP0_DAT6__LCD_DATA06           0x100 0x414 0x000 0x1 0x0
-#define MX6DL_PAD_DISP0_DAT6__ECSPI3_SS3           0x100 0x414 0x000 0x2 0x0
-#define MX6DL_PAD_DISP0_DAT6__AUD6_RXC             0x100 0x414 0x000 0x3 0x0
-#define MX6DL_PAD_DISP0_DAT6__GPIO4_IO27           0x100 0x414 0x000 0x5 0x0
-#define MX6DL_PAD_DISP0_DAT7__IPU1_DISP0_DATA07    0x104 0x418 0x000 0x0 0x0
-#define MX6DL_PAD_DISP0_DAT7__LCD_DATA07           0x104 0x418 0x000 0x1 0x0
-#define MX6DL_PAD_DISP0_DAT7__ECSPI3_RDY           0x104 0x418 0x000 0x2 0x0
-#define MX6DL_PAD_DISP0_DAT7__GPIO4_IO28           0x104 0x418 0x000 0x5 0x0
-#define MX6DL_PAD_DISP0_DAT8__IPU1_DISP0_DATA08    0x108 0x41c 0x000 0x0 0x0
-#define MX6DL_PAD_DISP0_DAT8__LCD_DATA08           0x108 0x41c 0x000 0x1 0x0
-#define MX6DL_PAD_DISP0_DAT8__PWM1_OUT             0x108 0x41c 0x000 0x2 0x0
-#define MX6DL_PAD_DISP0_DAT8__WDOG1_B              0x108 0x41c 0x000 0x3 0x0
-#define MX6DL_PAD_DISP0_DAT8__GPIO4_IO29           0x108 0x41c 0x000 0x5 0x0
-#define MX6DL_PAD_DISP0_DAT9__IPU1_DISP0_DATA09    0x10c 0x420 0x000 0x0 0x0
-#define MX6DL_PAD_DISP0_DAT9__LCD_DATA09           0x10c 0x420 0x000 0x1 0x0
-#define MX6DL_PAD_DISP0_DAT9__PWM2_OUT             0x10c 0x420 0x000 0x2 0x0
-#define MX6DL_PAD_DISP0_DAT9__WDOG2_B              0x10c 0x420 0x000 0x3 0x0
-#define MX6DL_PAD_DISP0_DAT9__GPIO4_IO30           0x10c 0x420 0x000 0x5 0x0
-#define MX6DL_PAD_EIM_A16__EIM_ADDR16              0x110 0x4e0 0x000 0x0 0x0
-#define MX6DL_PAD_EIM_A16__IPU1_DI1_DISP_CLK       0x110 0x4e0 0x000 0x1 0x0
-#define MX6DL_PAD_EIM_A16__IPU1_CSI1_PIXCLK        0x110 0x4e0 0x8b8 0x2 0x0
-#define MX6DL_PAD_EIM_A16__GPIO2_IO22              0x110 0x4e0 0x000 0x5 0x0
-#define MX6DL_PAD_EIM_A16__SRC_BOOT_CFG16          0x110 0x4e0 0x000 0x7 0x0
-#define MX6DL_PAD_EIM_A16__EPDC_DATA00             0x110 0x4e0 0x000 0x8 0x0
-#define MX6DL_PAD_EIM_A17__EIM_ADDR17              0x114 0x4e4 0x000 0x0 0x0
-#define MX6DL_PAD_EIM_A17__IPU1_DISP1_DATA12       0x114 0x4e4 0x000 0x1 0x0
-#define MX6DL_PAD_EIM_A17__IPU1_CSI1_DATA12        0x114 0x4e4 0x890 0x2 0x0
-#define MX6DL_PAD_EIM_A17__GPIO2_IO21              0x114 0x4e4 0x000 0x5 0x0
-#define MX6DL_PAD_EIM_A17__SRC_BOOT_CFG17          0x114 0x4e4 0x000 0x7 0x0
-#define MX6DL_PAD_EIM_A17__EPDC_PWR_STAT           0x114 0x4e4 0x000 0x8 0x0
-#define MX6DL_PAD_EIM_A18__EIM_ADDR18              0x118 0x4e8 0x000 0x0 0x0
-#define MX6DL_PAD_EIM_A18__IPU1_DISP1_DATA13       0x118 0x4e8 0x000 0x1 0x0
-#define MX6DL_PAD_EIM_A18__IPU1_CSI1_DATA13        0x118 0x4e8 0x894 0x2 0x0
-#define MX6DL_PAD_EIM_A18__GPIO2_IO20              0x118 0x4e8 0x000 0x5 0x0
-#define MX6DL_PAD_EIM_A18__SRC_BOOT_CFG18          0x118 0x4e8 0x000 0x7 0x0
-#define MX6DL_PAD_EIM_A18__EPDC_PWR_CTRL0          0x118 0x4e8 0x000 0x8 0x0
-#define MX6DL_PAD_EIM_A19__EIM_ADDR19              0x11c 0x4ec 0x000 0x0 0x0
-#define MX6DL_PAD_EIM_A19__IPU1_DISP1_DATA14       0x11c 0x4ec 0x000 0x1 0x0
-#define MX6DL_PAD_EIM_A19__IPU1_CSI1_DATA14        0x11c 0x4ec 0x898 0x2 0x0
-#define MX6DL_PAD_EIM_A19__GPIO2_IO19              0x11c 0x4ec 0x000 0x5 0x0
-#define MX6DL_PAD_EIM_A19__SRC_BOOT_CFG19          0x11c 0x4ec 0x000 0x7 0x0
-#define MX6DL_PAD_EIM_A19__EPDC_PWR_CTRL1          0x11c 0x4ec 0x000 0x8 0x0
-#define MX6DL_PAD_EIM_A20__EIM_ADDR20              0x120 0x4f0 0x000 0x0 0x0
-#define MX6DL_PAD_EIM_A20__IPU1_DISP1_DATA15       0x120 0x4f0 0x000 0x1 0x0
-#define MX6DL_PAD_EIM_A20__IPU1_CSI1_DATA15        0x120 0x4f0 0x89c 0x2 0x0
-#define MX6DL_PAD_EIM_A20__GPIO2_IO18              0x120 0x4f0 0x000 0x5 0x0
-#define MX6DL_PAD_EIM_A20__SRC_BOOT_CFG20          0x120 0x4f0 0x000 0x7 0x0
-#define MX6DL_PAD_EIM_A20__EPDC_PWR_CTRL2          0x120 0x4f0 0x000 0x8 0x0
-#define MX6DL_PAD_EIM_A21__EIM_ADDR21              0x124 0x4f4 0x000 0x0 0x0
-#define MX6DL_PAD_EIM_A21__IPU1_DISP1_DATA16       0x124 0x4f4 0x000 0x1 0x0
-#define MX6DL_PAD_EIM_A21__IPU1_CSI1_DATA16        0x124 0x4f4 0x8a0 0x2 0x0
-#define MX6DL_PAD_EIM_A21__GPIO2_IO17              0x124 0x4f4 0x000 0x5 0x0
-#define MX6DL_PAD_EIM_A21__SRC_BOOT_CFG21          0x124 0x4f4 0x000 0x7 0x0
-#define MX6DL_PAD_EIM_A21__EPDC_GDCLK              0x124 0x4f4 0x000 0x8 0x0
-#define MX6DL_PAD_EIM_A22__EIM_ADDR22              0x128 0x4f8 0x000 0x0 0x0
-#define MX6DL_PAD_EIM_A22__IPU1_DISP1_DATA17       0x128 0x4f8 0x000 0x1 0x0
-#define MX6DL_PAD_EIM_A22__IPU1_CSI1_DATA17        0x128 0x4f8 0x8a4 0x2 0x0
-#define MX6DL_PAD_EIM_A22__GPIO2_IO16              0x128 0x4f8 0x000 0x5 0x0
-#define MX6DL_PAD_EIM_A22__SRC_BOOT_CFG22          0x128 0x4f8 0x000 0x7 0x0
-#define MX6DL_PAD_EIM_A22__EPDC_GDSP               0x128 0x4f8 0x000 0x8 0x0
-#define MX6DL_PAD_EIM_A23__EIM_ADDR23              0x12c 0x4fc 0x000 0x0 0x0
-#define MX6DL_PAD_EIM_A23__IPU1_DISP1_DATA18       0x12c 0x4fc 0x000 0x1 0x0
-#define MX6DL_PAD_EIM_A23__IPU1_CSI1_DATA18        0x12c 0x4fc 0x8a8 0x2 0x0
-#define MX6DL_PAD_EIM_A23__IPU1_SISG3              0x12c 0x4fc 0x000 0x4 0x0
-#define MX6DL_PAD_EIM_A23__GPIO6_IO06              0x12c 0x4fc 0x000 0x5 0x0
-#define MX6DL_PAD_EIM_A23__SRC_BOOT_CFG23          0x12c 0x4fc 0x000 0x7 0x0
-#define MX6DL_PAD_EIM_A23__EPDC_GDOE               0x12c 0x4fc 0x000 0x8 0x0
-#define MX6DL_PAD_EIM_A24__EIM_ADDR24              0x130 0x500 0x000 0x0 0x0
-#define MX6DL_PAD_EIM_A24__IPU1_DISP1_DATA19       0x130 0x500 0x000 0x1 0x0
-#define MX6DL_PAD_EIM_A24__IPU1_CSI1_DATA19        0x130 0x500 0x8ac 0x2 0x0
-#define MX6DL_PAD_EIM_A24__IPU1_SISG2              0x130 0x500 0x000 0x4 0x0
-#define MX6DL_PAD_EIM_A24__GPIO5_IO04              0x130 0x500 0x000 0x5 0x0
-#define MX6DL_PAD_EIM_A24__SRC_BOOT_CFG24          0x130 0x500 0x000 0x7 0x0
-#define MX6DL_PAD_EIM_A24__EPDC_GDRL               0x130 0x500 0x000 0x8 0x0
-#define MX6DL_PAD_EIM_A25__EIM_ADDR25              0x134 0x504 0x000 0x0 0x0
-#define MX6DL_PAD_EIM_A25__ECSPI4_SS1              0x134 0x504 0x000 0x1 0x0
-#define MX6DL_PAD_EIM_A25__ECSPI2_RDY              0x134 0x504 0x000 0x2 0x0
-#define MX6DL_PAD_EIM_A25__IPU1_DI1_PIN12          0x134 0x504 0x000 0x3 0x0
-#define MX6DL_PAD_EIM_A25__IPU1_DI0_D1_CS          0x134 0x504 0x000 0x4 0x0
-#define MX6DL_PAD_EIM_A25__GPIO5_IO02              0x134 0x504 0x000 0x5 0x0
-#define MX6DL_PAD_EIM_A25__HDMI_TX_CEC_LINE        0x134 0x504 0x85c 0x6 0x0
-#define MX6DL_PAD_EIM_A25__EPDC_DATA15             0x134 0x504 0x000 0x8 0x0
-#define MX6DL_PAD_EIM_A25__EIM_ACLK_FREERUN        0x134 0x504 0x000 0x9 0x0
-#define MX6DL_PAD_EIM_BCLK__EIM_BCLK               0x138 0x508 0x000 0x0 0x0
-#define MX6DL_PAD_EIM_BCLK__IPU1_DI1_PIN16         0x138 0x508 0x000 0x1 0x0
-#define MX6DL_PAD_EIM_BCLK__GPIO6_IO31             0x138 0x508 0x000 0x5 0x0
-#define MX6DL_PAD_EIM_BCLK__EPDC_SDCE9             0x138 0x508 0x000 0x8 0x0
-#define MX6DL_PAD_EIM_CS0__EIM_CS0_B               0x13c 0x50c 0x000 0x0 0x0
-#define MX6DL_PAD_EIM_CS0__IPU1_DI1_PIN05          0x13c 0x50c 0x000 0x1 0x0
-#define MX6DL_PAD_EIM_CS0__ECSPI2_SCLK             0x13c 0x50c 0x7f4 0x2 0x2
-#define MX6DL_PAD_EIM_CS0__GPIO2_IO23              0x13c 0x50c 0x000 0x5 0x0
-#define MX6DL_PAD_EIM_CS0__EPDC_DATA06             0x13c 0x50c 0x000 0x8 0x0
-#define MX6DL_PAD_EIM_CS1__EIM_CS1_B               0x140 0x510 0x000 0x0 0x0
-#define MX6DL_PAD_EIM_CS1__IPU1_DI1_PIN06          0x140 0x510 0x000 0x1 0x0
-#define MX6DL_PAD_EIM_CS1__ECSPI2_MOSI             0x140 0x510 0x7fc 0x2 0x2
-#define MX6DL_PAD_EIM_CS1__GPIO2_IO24              0x140 0x510 0x000 0x5 0x0
-#define MX6DL_PAD_EIM_CS1__EPDC_DATA08             0x140 0x510 0x000 0x8 0x0
-#define MX6DL_PAD_EIM_D16__EIM_DATA16              0x144 0x514 0x000 0x0 0x0
-#define MX6DL_PAD_EIM_D16__ECSPI1_SCLK             0x144 0x514 0x7d8 0x1 0x2
-#define MX6DL_PAD_EIM_D16__IPU1_DI0_PIN05          0x144 0x514 0x000 0x2 0x0
-#define MX6DL_PAD_EIM_D16__IPU1_CSI1_DATA18        0x144 0x514 0x8a8 0x3 0x1
-#define MX6DL_PAD_EIM_D16__HDMI_TX_DDC_SDA         0x144 0x514 0x864 0x4 0x0
-#define MX6DL_PAD_EIM_D16__GPIO3_IO16              0x144 0x514 0x000 0x5 0x0
-#define MX6DL_PAD_EIM_D16__I2C2_SDA                0x144 0x514 0x874 0x6 0x0
-#define MX6DL_PAD_EIM_D16__EPDC_DATA10             0x144 0x514 0x000 0x8 0x0
-#define MX6DL_PAD_EIM_D17__EIM_DATA17              0x148 0x518 0x000 0x0 0x0
-#define MX6DL_PAD_EIM_D17__ECSPI1_MISO             0x148 0x518 0x7dc 0x1 0x2
-#define MX6DL_PAD_EIM_D17__IPU1_DI0_PIN06          0x148 0x518 0x000 0x2 0x0
-#define MX6DL_PAD_EIM_D17__IPU1_CSI1_PIXCLK        0x148 0x518 0x8b8 0x3 0x1
-#define MX6DL_PAD_EIM_D17__DCIC1_OUT               0x148 0x518 0x000 0x4 0x0
-#define MX6DL_PAD_EIM_D17__GPIO3_IO17              0x148 0x518 0x000 0x5 0x0
-#define MX6DL_PAD_EIM_D17__I2C3_SCL                0x148 0x518 0x878 0x6 0x0
-#define MX6DL_PAD_EIM_D17__EPDC_VCOM0              0x148 0x518 0x000 0x8 0x0
-#define MX6DL_PAD_EIM_D18__EIM_DATA18              0x14c 0x51c 0x000 0x0 0x0
-#define MX6DL_PAD_EIM_D18__ECSPI1_MOSI             0x14c 0x51c 0x7e0 0x1 0x2
-#define MX6DL_PAD_EIM_D18__IPU1_DI0_PIN07          0x14c 0x51c 0x000 0x2 0x0
-#define MX6DL_PAD_EIM_D18__IPU1_CSI1_DATA17        0x14c 0x51c 0x8a4 0x3 0x1
-#define MX6DL_PAD_EIM_D18__IPU1_DI1_D0_CS          0x14c 0x51c 0x000 0x4 0x0
-#define MX6DL_PAD_EIM_D18__GPIO3_IO18              0x14c 0x51c 0x000 0x5 0x0
-#define MX6DL_PAD_EIM_D18__I2C3_SDA                0x14c 0x51c 0x87c 0x6 0x0
-#define MX6DL_PAD_EIM_D18__EPDC_VCOM1              0x14c 0x51c 0x000 0x8 0x0
-#define MX6DL_PAD_EIM_D19__EIM_DATA19              0x150 0x520 0x000 0x0 0x0
-#define MX6DL_PAD_EIM_D19__ECSPI1_SS1              0x150 0x520 0x7e8 0x1 0x1
-#define MX6DL_PAD_EIM_D19__IPU1_DI0_PIN08          0x150 0x520 0x000 0x2 0x0
-#define MX6DL_PAD_EIM_D19__IPU1_CSI1_DATA16        0x150 0x520 0x8a0 0x3 0x1
-#define MX6DL_PAD_EIM_D19__UART1_CTS_B             0x150 0x520 0x000 0x4 0x0
-#define MX6DL_PAD_EIM_D19__UART1_RTS_B             0x150 0x520 0x8f8 0x4 0x0
-#define MX6DL_PAD_EIM_D19__GPIO3_IO19              0x150 0x520 0x000 0x5 0x0
-#define MX6DL_PAD_EIM_D19__EPIT1_OUT               0x150 0x520 0x000 0x6 0x0
-#define MX6DL_PAD_EIM_D19__EPDC_DATA12             0x150 0x520 0x000 0x8 0x0
-#define MX6DL_PAD_EIM_D20__EIM_DATA20              0x154 0x524 0x000 0x0 0x0
-#define MX6DL_PAD_EIM_D20__ECSPI4_SS0              0x154 0x524 0x808 0x1 0x0
-#define MX6DL_PAD_EIM_D20__IPU1_DI0_PIN16          0x154 0x524 0x000 0x2 0x0
-#define MX6DL_PAD_EIM_D20__IPU1_CSI1_DATA15        0x154 0x524 0x89c 0x3 0x1
-#define MX6DL_PAD_EIM_D20__UART1_RTS_B             0x154 0x524 0x8f8 0x4 0x1
-#define MX6DL_PAD_EIM_D20__UART1_CTS_B             0x154 0x524 0x000 0x4 0x0
-#define MX6DL_PAD_EIM_D20__GPIO3_IO20              0x154 0x524 0x000 0x5 0x0
-#define MX6DL_PAD_EIM_D20__EPIT2_OUT               0x154 0x524 0x000 0x6 0x0
-#define MX6DL_PAD_EIM_D21__EIM_DATA21              0x158 0x528 0x000 0x0 0x0
-#define MX6DL_PAD_EIM_D21__ECSPI4_SCLK             0x158 0x528 0x000 0x1 0x0
-#define MX6DL_PAD_EIM_D21__IPU1_DI0_PIN17          0x158 0x528 0x000 0x2 0x0
-#define MX6DL_PAD_EIM_D21__IPU1_CSI1_DATA11        0x158 0x528 0x88c 0x3 0x0
-#define MX6DL_PAD_EIM_D21__USB_OTG_OC              0x158 0x528 0x920 0x4 0x0
-#define MX6DL_PAD_EIM_D21__GPIO3_IO21              0x158 0x528 0x000 0x5 0x0
-#define MX6DL_PAD_EIM_D21__I2C1_SCL                0x158 0x528 0x868 0x6 0x1
-#define MX6DL_PAD_EIM_D21__SPDIF_IN                0x158 0x528 0x8f0 0x7 0x0
-#define MX6DL_PAD_EIM_D22__EIM_DATA22              0x15c 0x52c 0x000 0x0 0x0
-#define MX6DL_PAD_EIM_D22__ECSPI4_MISO             0x15c 0x52c 0x000 0x1 0x0
-#define MX6DL_PAD_EIM_D22__IPU1_DI0_PIN01          0x15c 0x52c 0x000 0x2 0x0
-#define MX6DL_PAD_EIM_D22__IPU1_CSI1_DATA10        0x15c 0x52c 0x888 0x3 0x0
-#define MX6DL_PAD_EIM_D22__USB_OTG_PWR             0x15c 0x52c 0x000 0x4 0x0
-#define MX6DL_PAD_EIM_D22__GPIO3_IO22              0x15c 0x52c 0x000 0x5 0x0
-#define MX6DL_PAD_EIM_D22__SPDIF_OUT               0x15c 0x52c 0x000 0x6 0x0
-#define MX6DL_PAD_EIM_D22__EPDC_SDCE6              0x15c 0x52c 0x000 0x8 0x0
-#define MX6DL_PAD_EIM_D23__EIM_DATA23              0x160 0x530 0x000 0x0 0x0
-#define MX6DL_PAD_EIM_D23__IPU1_DI0_D0_CS          0x160 0x530 0x000 0x1 0x0
-#define MX6DL_PAD_EIM_D23__UART3_CTS_B             0x160 0x530 0x000 0x2 0x0
-#define MX6DL_PAD_EIM_D23__UART3_RTS_B             0x160 0x530 0x908 0x2 0x0
-#define MX6DL_PAD_EIM_D23__UART1_DCD_B             0x160 0x530 0x000 0x3 0x0
-#define MX6DL_PAD_EIM_D23__IPU1_CSI1_DATA_EN       0x160 0x530 0x8b0 0x4 0x0
-#define MX6DL_PAD_EIM_D23__GPIO3_IO23              0x160 0x530 0x000 0x5 0x0
-#define MX6DL_PAD_EIM_D23__IPU1_DI1_PIN02          0x160 0x530 0x000 0x6 0x0
-#define MX6DL_PAD_EIM_D23__IPU1_DI1_PIN14          0x160 0x530 0x000 0x7 0x0
-#define MX6DL_PAD_EIM_D23__EPDC_DATA11             0x160 0x530 0x000 0x8 0x0
-#define MX6DL_PAD_EIM_D24__EIM_DATA24              0x164 0x534 0x000 0x0 0x0
-#define MX6DL_PAD_EIM_D24__ECSPI4_SS2              0x164 0x534 0x000 0x1 0x0
-#define MX6DL_PAD_EIM_D24__UART3_TX_DATA           0x164 0x534 0x000 0x2 0x0
-#define MX6DL_PAD_EIM_D24__UART3_RX_DATA           0x164 0x534 0x90c 0x2 0x0
-#define MX6DL_PAD_EIM_D24__ECSPI1_SS2              0x164 0x534 0x7ec 0x3 0x0
-#define MX6DL_PAD_EIM_D24__ECSPI2_SS2              0x164 0x534 0x000 0x4 0x0
-#define MX6DL_PAD_EIM_D24__GPIO3_IO24              0x164 0x534 0x000 0x5 0x0
-#define MX6DL_PAD_EIM_D24__AUD5_RXFS               0x164 0x534 0x7bc 0x6 0x1
-#define MX6DL_PAD_EIM_D24__UART1_DTR_B             0x164 0x534 0x000 0x7 0x0
-#define MX6DL_PAD_EIM_D24__EPDC_SDCE7              0x164 0x534 0x000 0x8 0x0
-#define MX6DL_PAD_EIM_D25__EIM_DATA25              0x168 0x538 0x000 0x0 0x0
-#define MX6DL_PAD_EIM_D25__ECSPI4_SS3              0x168 0x538 0x000 0x1 0x0
-#define MX6DL_PAD_EIM_D25__UART3_RX_DATA           0x168 0x538 0x90c 0x2 0x1
-#define MX6DL_PAD_EIM_D25__UART3_TX_DATA           0x168 0x538 0x000 0x2 0x0
-#define MX6DL_PAD_EIM_D25__ECSPI1_SS3              0x168 0x538 0x7f0 0x3 0x0
-#define MX6DL_PAD_EIM_D25__ECSPI2_SS3              0x168 0x538 0x000 0x4 0x0
-#define MX6DL_PAD_EIM_D25__GPIO3_IO25              0x168 0x538 0x000 0x5 0x0
-#define MX6DL_PAD_EIM_D25__AUD5_RXC                0x168 0x538 0x7b8 0x6 0x1
-#define MX6DL_PAD_EIM_D25__UART1_DSR_B             0x168 0x538 0x000 0x7 0x0
-#define MX6DL_PAD_EIM_D25__EPDC_SDCE8              0x168 0x538 0x000 0x8 0x0
-#define MX6DL_PAD_EIM_D26__EIM_DATA26              0x16c 0x53c 0x000 0x0 0x0
-#define MX6DL_PAD_EIM_D26__IPU1_DI1_PIN11          0x16c 0x53c 0x000 0x1 0x0
-#define MX6DL_PAD_EIM_D26__IPU1_CSI0_DATA01        0x16c 0x53c 0x000 0x2 0x0
-#define MX6DL_PAD_EIM_D26__IPU1_CSI1_DATA14        0x16c 0x53c 0x898 0x3 0x1
-#define MX6DL_PAD_EIM_D26__UART2_TX_DATA           0x16c 0x53c 0x000 0x4 0x0
-#define MX6DL_PAD_EIM_D26__UART2_RX_DATA           0x16c 0x53c 0x904 0x4 0x0
-#define MX6DL_PAD_EIM_D26__GPIO3_IO26              0x16c 0x53c 0x000 0x5 0x0
-#define MX6DL_PAD_EIM_D26__IPU1_SISG2              0x16c 0x53c 0x000 0x6 0x0
-#define MX6DL_PAD_EIM_D26__IPU1_DISP1_DATA22       0x16c 0x53c 0x000 0x7 0x0
-#define MX6DL_PAD_EIM_D26__EPDC_SDOED              0x16c 0x53c 0x000 0x8 0x0
-#define MX6DL_PAD_EIM_D27__EIM_DATA27              0x170 0x540 0x000 0x0 0x0
-#define MX6DL_PAD_EIM_D27__IPU1_DI1_PIN13          0x170 0x540 0x000 0x1 0x0
-#define MX6DL_PAD_EIM_D27__IPU1_CSI0_DATA00        0x170 0x540 0x000 0x2 0x0
-#define MX6DL_PAD_EIM_D27__IPU1_CSI1_DATA13        0x170 0x540 0x894 0x3 0x1
-#define MX6DL_PAD_EIM_D27__UART2_RX_DATA           0x170 0x540 0x904 0x4 0x1
-#define MX6DL_PAD_EIM_D27__UART2_TX_DATA           0x170 0x540 0x000 0x4 0x0
-#define MX6DL_PAD_EIM_D27__GPIO3_IO27              0x170 0x540 0x000 0x5 0x0
-#define MX6DL_PAD_EIM_D27__IPU1_SISG3              0x170 0x540 0x000 0x6 0x0
-#define MX6DL_PAD_EIM_D27__IPU1_DISP1_DATA23       0x170 0x540 0x000 0x7 0x0
-#define MX6DL_PAD_EIM_D27__EPDC_SDOE               0x170 0x540 0x000 0x8 0x0
-#define MX6DL_PAD_EIM_D28__EIM_DATA28              0x174 0x544 0x000 0x0 0x0
-#define MX6DL_PAD_EIM_D28__I2C1_SDA                0x174 0x544 0x86c 0x1 0x1
-#define MX6DL_PAD_EIM_D28__ECSPI4_MOSI             0x174 0x544 0x000 0x2 0x0
-#define MX6DL_PAD_EIM_D28__IPU1_CSI1_DATA12        0x174 0x544 0x890 0x3 0x1
-#define MX6DL_PAD_EIM_D28__UART2_CTS_B             0x174 0x544 0x000 0x4 0x0
-#define MX6DL_PAD_EIM_D28__UART2_RTS_B             0x174 0x544 0x900 0x4 0x0
-#define MX6DL_PAD_EIM_D28__GPIO3_IO28              0x174 0x544 0x000 0x5 0x0
-#define MX6DL_PAD_EIM_D28__IPU1_EXT_TRIG           0x174 0x544 0x000 0x6 0x0
-#define MX6DL_PAD_EIM_D28__IPU1_DI0_PIN13          0x174 0x544 0x000 0x7 0x0
-#define MX6DL_PAD_EIM_D28__EPDC_PWR_CTRL3          0x174 0x544 0x000 0x8 0x0
-#define MX6DL_PAD_EIM_D29__EIM_DATA29              0x178 0x548 0x000 0x0 0x0
-#define MX6DL_PAD_EIM_D29__IPU1_DI1_PIN15          0x178 0x548 0x000 0x1 0x0
-#define MX6DL_PAD_EIM_D29__ECSPI4_SS0              0x178 0x548 0x808 0x2 0x1
-#define MX6DL_PAD_EIM_D29__UART2_RTS_B             0x178 0x548 0x900 0x4 0x1
-#define MX6DL_PAD_EIM_D29__UART2_CTS_B             0x178 0x548 0x000 0x4 0x0
-#define MX6DL_PAD_EIM_D29__GPIO3_IO29              0x178 0x548 0x000 0x5 0x0
-#define MX6DL_PAD_EIM_D29__IPU1_CSI1_VSYNC         0x178 0x548 0x8bc 0x6 0x0
-#define MX6DL_PAD_EIM_D29__IPU1_DI0_PIN14          0x178 0x548 0x000 0x7 0x0
-#define MX6DL_PAD_EIM_D29__EPDC_PWR_WAKE           0x178 0x548 0x000 0x8 0x0
-#define MX6DL_PAD_EIM_D30__EIM_DATA30              0x17c 0x54c 0x000 0x0 0x0
-#define MX6DL_PAD_EIM_D30__IPU1_DISP1_DATA21       0x17c 0x54c 0x000 0x1 0x0
-#define MX6DL_PAD_EIM_D30__IPU1_DI0_PIN11          0x17c 0x54c 0x000 0x2 0x0
-#define MX6DL_PAD_EIM_D30__IPU1_CSI0_DATA03        0x17c 0x54c 0x000 0x3 0x0
-#define MX6DL_PAD_EIM_D30__UART3_CTS_B             0x17c 0x54c 0x000 0x4 0x0
-#define MX6DL_PAD_EIM_D30__UART3_RTS_B             0x17c 0x54c 0x908 0x4 0x1
-#define MX6DL_PAD_EIM_D30__GPIO3_IO30              0x17c 0x54c 0x000 0x5 0x0
-#define MX6DL_PAD_EIM_D30__USB_H1_OC               0x17c 0x54c 0x924 0x6 0x0
-#define MX6DL_PAD_EIM_D30__EPDC_SDOEZ              0x17c 0x54c 0x000 0x8 0x0
-#define MX6DL_PAD_EIM_D31__EIM_DATA31              0x180 0x550 0x000 0x0 0x0
-#define MX6DL_PAD_EIM_D31__IPU1_DISP1_DATA20       0x180 0x550 0x000 0x1 0x0
-#define MX6DL_PAD_EIM_D31__IPU1_DI0_PIN12          0x180 0x550 0x000 0x2 0x0
-#define MX6DL_PAD_EIM_D31__IPU1_CSI0_DATA02        0x180 0x550 0x000 0x3 0x0
-#define MX6DL_PAD_EIM_D31__UART3_RTS_B             0x180 0x550 0x908 0x4 0x2
-#define MX6DL_PAD_EIM_D31__UART3_CTS_B             0x180 0x550 0x000 0x4 0x0
-#define MX6DL_PAD_EIM_D31__GPIO3_IO31              0x180 0x550 0x000 0x5 0x0
-#define MX6DL_PAD_EIM_D31__USB_H1_PWR              0x180 0x550 0x000 0x6 0x0
-#define MX6DL_PAD_EIM_D31__EPDC_SDCLK_P            0x180 0x550 0x000 0x8 0x0
-#define MX6DL_PAD_EIM_D31__EIM_ACLK_FREERUN        0x180 0x550 0x000 0x9 0x0
-#define MX6DL_PAD_EIM_DA0__EIM_AD00                0x184 0x554 0x000 0x0 0x0
-#define MX6DL_PAD_EIM_DA0__IPU1_DISP1_DATA09       0x184 0x554 0x000 0x1 0x0
-#define MX6DL_PAD_EIM_DA0__IPU1_CSI1_DATA09        0x184 0x554 0x000 0x2 0x0
-#define MX6DL_PAD_EIM_DA0__GPIO3_IO00              0x184 0x554 0x000 0x5 0x0
-#define MX6DL_PAD_EIM_DA0__SRC_BOOT_CFG00          0x184 0x554 0x000 0x7 0x0
-#define MX6DL_PAD_EIM_DA0__EPDC_SDCLK_N            0x184 0x554 0x000 0x8 0x0
-#define MX6DL_PAD_EIM_DA1__EIM_AD01                0x188 0x558 0x000 0x0 0x0
-#define MX6DL_PAD_EIM_DA1__IPU1_DISP1_DATA08       0x188 0x558 0x000 0x1 0x0
-#define MX6DL_PAD_EIM_DA1__IPU1_CSI1_DATA08        0x188 0x558 0x000 0x2 0x0
-#define MX6DL_PAD_EIM_DA1__GPIO3_IO01              0x188 0x558 0x000 0x5 0x0
-#define MX6DL_PAD_EIM_DA1__SRC_BOOT_CFG01          0x188 0x558 0x000 0x7 0x0
-#define MX6DL_PAD_EIM_DA1__EPDC_SDLE               0x188 0x558 0x000 0x8 0x0
-#define MX6DL_PAD_EIM_DA10__EIM_AD10               0x18c 0x55c 0x000 0x0 0x0
-#define MX6DL_PAD_EIM_DA10__IPU1_DI1_PIN15         0x18c 0x55c 0x000 0x1 0x0
-#define MX6DL_PAD_EIM_DA10__IPU1_CSI1_DATA_EN      0x18c 0x55c 0x8b0 0x2 0x1
-#define MX6DL_PAD_EIM_DA10__GPIO3_IO10             0x18c 0x55c 0x000 0x5 0x0
-#define MX6DL_PAD_EIM_DA10__SRC_BOOT_CFG10         0x18c 0x55c 0x000 0x7 0x0
-#define MX6DL_PAD_EIM_DA10__EPDC_DATA01            0x18c 0x55c 0x000 0x8 0x0
-#define MX6DL_PAD_EIM_DA11__EIM_AD11               0x190 0x560 0x000 0x0 0x0
-#define MX6DL_PAD_EIM_DA11__IPU1_DI1_PIN02         0x190 0x560 0x000 0x1 0x0
-#define MX6DL_PAD_EIM_DA11__IPU1_CSI1_HSYNC        0x190 0x560 0x8b4 0x2 0x0
-#define MX6DL_PAD_EIM_DA11__GPIO3_IO11             0x190 0x560 0x000 0x5 0x0
-#define MX6DL_PAD_EIM_DA11__SRC_BOOT_CFG11         0x190 0x560 0x000 0x7 0x0
-#define MX6DL_PAD_EIM_DA11__EPDC_DATA03            0x190 0x560 0x000 0x8 0x0
-#define MX6DL_PAD_EIM_DA12__EIM_AD12               0x194 0x564 0x000 0x0 0x0
-#define MX6DL_PAD_EIM_DA12__IPU1_DI1_PIN03         0x194 0x564 0x000 0x1 0x0
-#define MX6DL_PAD_EIM_DA12__IPU1_CSI1_VSYNC        0x194 0x564 0x8bc 0x2 0x1
-#define MX6DL_PAD_EIM_DA12__GPIO3_IO12             0x194 0x564 0x000 0x5 0x0
-#define MX6DL_PAD_EIM_DA12__SRC_BOOT_CFG12         0x194 0x564 0x000 0x7 0x0
-#define MX6DL_PAD_EIM_DA12__EPDC_DATA02            0x194 0x564 0x000 0x8 0x0
-#define MX6DL_PAD_EIM_DA13__EIM_AD13               0x198 0x568 0x000 0x0 0x0
-#define MX6DL_PAD_EIM_DA13__IPU1_DI1_D0_CS         0x198 0x568 0x000 0x1 0x0
-#define MX6DL_PAD_EIM_DA13__GPIO3_IO13             0x198 0x568 0x000 0x5 0x0
-#define MX6DL_PAD_EIM_DA13__SRC_BOOT_CFG13         0x198 0x568 0x000 0x7 0x0
-#define MX6DL_PAD_EIM_DA13__EPDC_DATA13            0x198 0x568 0x000 0x8 0x0
-#define MX6DL_PAD_EIM_DA14__EIM_AD14               0x19c 0x56c 0x000 0x0 0x0
-#define MX6DL_PAD_EIM_DA14__IPU1_DI1_D1_CS         0x19c 0x56c 0x000 0x1 0x0
-#define MX6DL_PAD_EIM_DA14__GPIO3_IO14             0x19c 0x56c 0x000 0x5 0x0
-#define MX6DL_PAD_EIM_DA14__SRC_BOOT_CFG14         0x19c 0x56c 0x000 0x7 0x0
-#define MX6DL_PAD_EIM_DA14__EPDC_DATA14            0x19c 0x56c 0x000 0x8 0x0
-#define MX6DL_PAD_EIM_DA15__EIM_AD15               0x1a0 0x570 0x000 0x0 0x0
-#define MX6DL_PAD_EIM_DA15__IPU1_DI1_PIN01         0x1a0 0x570 0x000 0x1 0x0
-#define MX6DL_PAD_EIM_DA15__IPU1_DI1_PIN04         0x1a0 0x570 0x000 0x2 0x0
-#define MX6DL_PAD_EIM_DA15__GPIO3_IO15             0x1a0 0x570 0x000 0x5 0x0
-#define MX6DL_PAD_EIM_DA15__SRC_BOOT_CFG15         0x1a0 0x570 0x000 0x7 0x0
-#define MX6DL_PAD_EIM_DA15__EPDC_DATA09            0x1a0 0x570 0x000 0x8 0x0
-#define MX6DL_PAD_EIM_DA2__EIM_AD02                0x1a4 0x574 0x000 0x0 0x0
-#define MX6DL_PAD_EIM_DA2__IPU1_DISP1_DATA07       0x1a4 0x574 0x000 0x1 0x0
-#define MX6DL_PAD_EIM_DA2__IPU1_CSI1_DATA07        0x1a4 0x574 0x000 0x2 0x0
-#define MX6DL_PAD_EIM_DA2__GPIO3_IO02              0x1a4 0x574 0x000 0x5 0x0
-#define MX6DL_PAD_EIM_DA2__SRC_BOOT_CFG02          0x1a4 0x574 0x000 0x7 0x0
-#define MX6DL_PAD_EIM_DA2__EPDC_BDR0               0x1a4 0x574 0x000 0x8 0x0
-#define MX6DL_PAD_EIM_DA3__EIM_AD03                0x1a8 0x578 0x000 0x0 0x0
-#define MX6DL_PAD_EIM_DA3__IPU1_DISP1_DATA06       0x1a8 0x578 0x000 0x1 0x0
-#define MX6DL_PAD_EIM_DA3__IPU1_CSI1_DATA06        0x1a8 0x578 0x000 0x2 0x0
-#define MX6DL_PAD_EIM_DA3__GPIO3_IO03              0x1a8 0x578 0x000 0x5 0x0
-#define MX6DL_PAD_EIM_DA3__SRC_BOOT_CFG03          0x1a8 0x578 0x000 0x7 0x0
-#define MX6DL_PAD_EIM_DA3__EPDC_BDR1               0x1a8 0x578 0x000 0x8 0x0
-#define MX6DL_PAD_EIM_DA4__EIM_AD04                0x1ac 0x57c 0x000 0x0 0x0
-#define MX6DL_PAD_EIM_DA4__IPU1_DISP1_DATA05       0x1ac 0x57c 0x000 0x1 0x0
-#define MX6DL_PAD_EIM_DA4__IPU1_CSI1_DATA05        0x1ac 0x57c 0x000 0x2 0x0
-#define MX6DL_PAD_EIM_DA4__GPIO3_IO04              0x1ac 0x57c 0x000 0x5 0x0
-#define MX6DL_PAD_EIM_DA4__SRC_BOOT_CFG04          0x1ac 0x57c 0x000 0x7 0x0
-#define MX6DL_PAD_EIM_DA4__EPDC_SDCE0              0x1ac 0x57c 0x000 0x8 0x0
-#define MX6DL_PAD_EIM_DA5__EIM_AD05                0x1b0 0x580 0x000 0x0 0x0
-#define MX6DL_PAD_EIM_DA5__IPU1_DISP1_DATA04       0x1b0 0x580 0x000 0x1 0x0
-#define MX6DL_PAD_EIM_DA5__IPU1_CSI1_DATA04        0x1b0 0x580 0x000 0x2 0x0
-#define MX6DL_PAD_EIM_DA5__GPIO3_IO05              0x1b0 0x580 0x000 0x5 0x0
-#define MX6DL_PAD_EIM_DA5__SRC_BOOT_CFG05          0x1b0 0x580 0x000 0x7 0x0
-#define MX6DL_PAD_EIM_DA5__EPDC_SDCE1              0x1b0 0x580 0x000 0x8 0x0
-#define MX6DL_PAD_EIM_DA6__EIM_AD06                0x1b4 0x584 0x000 0x0 0x0
-#define MX6DL_PAD_EIM_DA6__IPU1_DISP1_DATA03       0x1b4 0x584 0x000 0x1 0x0
-#define MX6DL_PAD_EIM_DA6__IPU1_CSI1_DATA03        0x1b4 0x584 0x000 0x2 0x0
-#define MX6DL_PAD_EIM_DA6__GPIO3_IO06              0x1b4 0x584 0x000 0x5 0x0
-#define MX6DL_PAD_EIM_DA6__SRC_BOOT_CFG06          0x1b4 0x584 0x000 0x7 0x0
-#define MX6DL_PAD_EIM_DA6__EPDC_SDCE2              0x1b4 0x584 0x000 0x8 0x0
-#define MX6DL_PAD_EIM_DA7__EIM_AD07                0x1b8 0x588 0x000 0x0 0x0
-#define MX6DL_PAD_EIM_DA7__IPU1_DISP1_DATA02       0x1b8 0x588 0x000 0x1 0x0
-#define MX6DL_PAD_EIM_DA7__IPU1_CSI1_DATA02        0x1b8 0x588 0x000 0x2 0x0
-#define MX6DL_PAD_EIM_DA7__GPIO3_IO07              0x1b8 0x588 0x000 0x5 0x0
-#define MX6DL_PAD_EIM_DA7__SRC_BOOT_CFG07          0x1b8 0x588 0x000 0x7 0x0
-#define MX6DL_PAD_EIM_DA7__EPDC_SDCE3              0x1b8 0x588 0x000 0x8 0x0
-#define MX6DL_PAD_EIM_DA8__EIM_AD08                0x1bc 0x58c 0x000 0x0 0x0
-#define MX6DL_PAD_EIM_DA8__IPU1_DISP1_DATA01       0x1bc 0x58c 0x000 0x1 0x0
-#define MX6DL_PAD_EIM_DA8__IPU1_CSI1_DATA01        0x1bc 0x58c 0x000 0x2 0x0
-#define MX6DL_PAD_EIM_DA8__GPIO3_IO08              0x1bc 0x58c 0x000 0x5 0x0
-#define MX6DL_PAD_EIM_DA8__SRC_BOOT_CFG08          0x1bc 0x58c 0x000 0x7 0x0
-#define MX6DL_PAD_EIM_DA8__EPDC_SDCE4              0x1bc 0x58c 0x000 0x8 0x0
-#define MX6DL_PAD_EIM_DA9__EIM_AD09                0x1c0 0x590 0x000 0x0 0x0
-#define MX6DL_PAD_EIM_DA9__IPU1_DISP1_DATA00       0x1c0 0x590 0x000 0x1 0x0
-#define MX6DL_PAD_EIM_DA9__IPU1_CSI1_DATA00        0x1c0 0x590 0x000 0x2 0x0
-#define MX6DL_PAD_EIM_DA9__GPIO3_IO09              0x1c0 0x590 0x000 0x5 0x0
-#define MX6DL_PAD_EIM_DA9__SRC_BOOT_CFG09          0x1c0 0x590 0x000 0x7 0x0
-#define MX6DL_PAD_EIM_DA9__EPDC_SDCE5              0x1c0 0x590 0x000 0x8 0x0
-#define MX6DL_PAD_EIM_EB0__EIM_EB0_B               0x1c4 0x594 0x000 0x0 0x0
-#define MX6DL_PAD_EIM_EB0__IPU1_DISP1_DATA11       0x1c4 0x594 0x000 0x1 0x0
-#define MX6DL_PAD_EIM_EB0__IPU1_CSI1_DATA11        0x1c4 0x594 0x88c 0x2 0x1
-#define MX6DL_PAD_EIM_EB0__CCM_PMIC_READY          0x1c4 0x594 0x7d4 0x4 0x0
-#define MX6DL_PAD_EIM_EB0__GPIO2_IO28              0x1c4 0x594 0x000 0x5 0x0
-#define MX6DL_PAD_EIM_EB0__SRC_BOOT_CFG27          0x1c4 0x594 0x000 0x7 0x0
-#define MX6DL_PAD_EIM_EB0__EPDC_PWR_COM            0x1c4 0x594 0x000 0x8 0x0
-#define MX6DL_PAD_EIM_EB1__EIM_EB1_B               0x1c8 0x598 0x000 0x0 0x0
-#define MX6DL_PAD_EIM_EB1__IPU1_DISP1_DATA10       0x1c8 0x598 0x000 0x1 0x0
-#define MX6DL_PAD_EIM_EB1__IPU1_CSI1_DATA10        0x1c8 0x598 0x888 0x2 0x1
-#define MX6DL_PAD_EIM_EB1__GPIO2_IO29              0x1c8 0x598 0x000 0x5 0x0
-#define MX6DL_PAD_EIM_EB1__SRC_BOOT_CFG28          0x1c8 0x598 0x000 0x7 0x0
-#define MX6DL_PAD_EIM_EB1__EPDC_SDSHR              0x1c8 0x598 0x000 0x8 0x0
-#define MX6DL_PAD_EIM_EB2__EIM_EB2_B               0x1cc 0x59c 0x000 0x0 0x0
-#define MX6DL_PAD_EIM_EB2__ECSPI1_SS0              0x1cc 0x59c 0x7e4 0x1 0x2
-#define MX6DL_PAD_EIM_EB2__IPU1_CSI1_DATA19        0x1cc 0x59c 0x8ac 0x3 0x1
-#define MX6DL_PAD_EIM_EB2__HDMI_TX_DDC_SCL         0x1cc 0x59c 0x860 0x4 0x0
-#define MX6DL_PAD_EIM_EB2__GPIO2_IO30              0x1cc 0x59c 0x000 0x5 0x0
-#define MX6DL_PAD_EIM_EB2__I2C2_SCL                0x1cc 0x59c 0x870 0x6 0x0
-#define MX6DL_PAD_EIM_EB2__SRC_BOOT_CFG30          0x1cc 0x59c 0x000 0x7 0x0
-#define MX6DL_PAD_EIM_EB2__EPDC_DATA05             0x1cc 0x59c 0x000 0x8 0x0
-#define MX6DL_PAD_EIM_EB3__EIM_EB3_B               0x1d0 0x5a0 0x000 0x0 0x0
-#define MX6DL_PAD_EIM_EB3__ECSPI4_RDY              0x1d0 0x5a0 0x000 0x1 0x0
-#define MX6DL_PAD_EIM_EB3__UART3_RTS_B             0x1d0 0x5a0 0x908 0x2 0x3
-#define MX6DL_PAD_EIM_EB3__UART3_CTS_B             0x1d0 0x5a0 0x000 0x2 0x0
-#define MX6DL_PAD_EIM_EB3__UART1_RI_B              0x1d0 0x5a0 0x000 0x3 0x0
-#define MX6DL_PAD_EIM_EB3__IPU1_CSI1_HSYNC         0x1d0 0x5a0 0x8b4 0x4 0x1
-#define MX6DL_PAD_EIM_EB3__GPIO2_IO31              0x1d0 0x5a0 0x000 0x5 0x0
-#define MX6DL_PAD_EIM_EB3__IPU1_DI1_PIN03          0x1d0 0x5a0 0x000 0x6 0x0
-#define MX6DL_PAD_EIM_EB3__SRC_BOOT_CFG31          0x1d0 0x5a0 0x000 0x7 0x0
-#define MX6DL_PAD_EIM_EB3__EPDC_SDCE0              0x1d0 0x5a0 0x000 0x8 0x0
-#define MX6DL_PAD_EIM_EB3__EIM_ACLK_FREERUN        0x1d0 0x5a0 0x000 0x9 0x0
-#define MX6DL_PAD_EIM_LBA__EIM_LBA_B               0x1d4 0x5a4 0x000 0x0 0x0
-#define MX6DL_PAD_EIM_LBA__IPU1_DI1_PIN17          0x1d4 0x5a4 0x000 0x1 0x0
-#define MX6DL_PAD_EIM_LBA__ECSPI2_SS1              0x1d4 0x5a4 0x804 0x2 0x1
-#define MX6DL_PAD_EIM_LBA__GPIO2_IO27              0x1d4 0x5a4 0x000 0x5 0x0
-#define MX6DL_PAD_EIM_LBA__SRC_BOOT_CFG26          0x1d4 0x5a4 0x000 0x7 0x0
-#define MX6DL_PAD_EIM_LBA__EPDC_DATA04             0x1d4 0x5a4 0x000 0x8 0x0
-#define MX6DL_PAD_EIM_OE__EIM_OE_B                 0x1d8 0x5a8 0x000 0x0 0x0
-#define MX6DL_PAD_EIM_OE__IPU1_DI1_PIN07           0x1d8 0x5a8 0x000 0x1 0x0
-#define MX6DL_PAD_EIM_OE__ECSPI2_MISO              0x1d8 0x5a8 0x7f8 0x2 0x2
-#define MX6DL_PAD_EIM_OE__GPIO2_IO25               0x1d8 0x5a8 0x000 0x5 0x0
-#define MX6DL_PAD_EIM_OE__EPDC_PWR_IRQ             0x1d8 0x5a8 0x000 0x8 0x0
-#define MX6DL_PAD_EIM_RW__EIM_RW                   0x1dc 0x5ac 0x000 0x0 0x0
-#define MX6DL_PAD_EIM_RW__IPU1_DI1_PIN08           0x1dc 0x5ac 0x000 0x1 0x0
-#define MX6DL_PAD_EIM_RW__ECSPI2_SS0               0x1dc 0x5ac 0x800 0x2 0x2
-#define MX6DL_PAD_EIM_RW__GPIO2_IO26               0x1dc 0x5ac 0x000 0x5 0x0
-#define MX6DL_PAD_EIM_RW__SRC_BOOT_CFG29           0x1dc 0x5ac 0x000 0x7 0x0
-#define MX6DL_PAD_EIM_RW__EPDC_DATA07              0x1dc 0x5ac 0x000 0x8 0x0
-#define MX6DL_PAD_EIM_WAIT__EIM_WAIT_B             0x1e0 0x5b0 0x000 0x0 0x0
-#define MX6DL_PAD_EIM_WAIT__EIM_DTACK_B            0x1e0 0x5b0 0x000 0x1 0x0
-#define MX6DL_PAD_EIM_WAIT__GPIO5_IO00             0x1e0 0x5b0 0x000 0x5 0x0
-#define MX6DL_PAD_EIM_WAIT__SRC_BOOT_CFG25         0x1e0 0x5b0 0x000 0x7 0x0
-#define MX6DL_PAD_ENET_CRS_DV__ENET_RX_EN          0x1e4 0x5b4 0x828 0x1 0x0
-#define MX6DL_PAD_ENET_CRS_DV__ESAI_TX_CLK         0x1e4 0x5b4 0x840 0x2 0x0
-#define MX6DL_PAD_ENET_CRS_DV__SPDIF_EXT_CLK       0x1e4 0x5b4 0x8f4 0x3 0x0
-#define MX6DL_PAD_ENET_CRS_DV__GPIO1_IO25          0x1e4 0x5b4 0x000 0x5 0x0
-#define MX6DL_PAD_ENET_MDC__MLB_DATA               0x1e8 0x5b8 0x8e0 0x0 0x0
-#define MX6DL_PAD_ENET_MDC__ENET_MDC               0x1e8 0x5b8 0x000 0x1 0x0
-#define MX6DL_PAD_ENET_MDC__ESAI_TX5_RX0           0x1e8 0x5b8 0x858 0x2 0x0
-#define MX6DL_PAD_ENET_MDC__ENET_1588_EVENT1_IN    0x1e8 0x5b8 0x000 0x4 0x0
-#define MX6DL_PAD_ENET_MDC__GPIO1_IO31             0x1e8 0x5b8 0x000 0x5 0x0
-#define MX6DL_PAD_ENET_MDIO__ENET_MDIO             0x1ec 0x5bc 0x810 0x1 0x0
-#define MX6DL_PAD_ENET_MDIO__ESAI_RX_CLK           0x1ec 0x5bc 0x83c 0x2 0x0
-#define MX6DL_PAD_ENET_MDIO__ENET_1588_EVENT1_OUT  0x1ec 0x5bc 0x000 0x4 0x0
-#define MX6DL_PAD_ENET_MDIO__GPIO1_IO22            0x1ec 0x5bc 0x000 0x5 0x0
-#define MX6DL_PAD_ENET_MDIO__SPDIF_LOCK            0x1ec 0x5bc 0x000 0x6 0x0
-#define MX6DL_PAD_ENET_REF_CLK__ENET_TX_CLK        0x1f0 0x5c0 0x000 0x1 0x0
-#define MX6DL_PAD_ENET_REF_CLK__ESAI_RX_FS         0x1f0 0x5c0 0x82c 0x2 0x0
-#define MX6DL_PAD_ENET_REF_CLK__GPIO1_IO23         0x1f0 0x5c0 0x000 0x5 0x0
-#define MX6DL_PAD_ENET_REF_CLK__SPDIF_SR_CLK       0x1f0 0x5c0 0x000 0x6 0x0
-#define MX6DL_PAD_ENET_RX_ER__USB_OTG_ID           0x1f4 0x5c4 0x790 0x0 0x0
-#define MX6DL_PAD_ENET_RX_ER__ENET_RX_ER           0x1f4 0x5c4 0x000 0x1 0x0
-#define MX6DL_PAD_ENET_RX_ER__ESAI_RX_HF_CLK       0x1f4 0x5c4 0x834 0x2 0x0
-#define MX6DL_PAD_ENET_RX_ER__SPDIF_IN             0x1f4 0x5c4 0x8f0 0x3 0x1
-#define MX6DL_PAD_ENET_RX_ER__ENET_1588_EVENT2_OUT 0x1f4 0x5c4 0x000 0x4 0x0
-#define MX6DL_PAD_ENET_RX_ER__GPIO1_IO24           0x1f4 0x5c4 0x000 0x5 0x0
-#define MX6DL_PAD_ENET_RXD0__ENET_RX_DATA0         0x1f8 0x5c8 0x818 0x1 0x0
-#define MX6DL_PAD_ENET_RXD0__ESAI_TX_HF_CLK        0x1f8 0x5c8 0x838 0x2 0x0
-#define MX6DL_PAD_ENET_RXD0__SPDIF_OUT             0x1f8 0x5c8 0x000 0x3 0x0
-#define MX6DL_PAD_ENET_RXD0__GPIO1_IO27            0x1f8 0x5c8 0x000 0x5 0x0
-#define MX6DL_PAD_ENET_RXD1__MLB_SIG               0x1fc 0x5cc 0x8e4 0x0 0x0
-#define MX6DL_PAD_ENET_RXD1__ENET_RX_DATA1         0x1fc 0x5cc 0x81c 0x1 0x0
-#define MX6DL_PAD_ENET_RXD1__ESAI_TX_FS            0x1fc 0x5cc 0x830 0x2 0x0
-#define MX6DL_PAD_ENET_RXD1__ENET_1588_EVENT3_OUT  0x1fc 0x5cc 0x000 0x4 0x0
-#define MX6DL_PAD_ENET_RXD1__GPIO1_IO26            0x1fc 0x5cc 0x000 0x5 0x0
-#define MX6DL_PAD_ENET_TX_EN__ENET_TX_EN           0x200 0x5d0 0x000 0x1 0x0
-#define MX6DL_PAD_ENET_TX_EN__ESAI_TX3_RX2         0x200 0x5d0 0x850 0x2 0x0
-#define MX6DL_PAD_ENET_TX_EN__GPIO1_IO28           0x200 0x5d0 0x000 0x5 0x0
-#define MX6DL_PAD_ENET_TX_EN__I2C4_SCL             0x200 0x5d0 0x880 0x9 0x0
-#define MX6DL_PAD_ENET_TXD0__ENET_TX_DATA0         0x204 0x5d4 0x000 0x1 0x0
-#define MX6DL_PAD_ENET_TXD0__ESAI_TX4_RX1          0x204 0x5d4 0x854 0x2 0x0
-#define MX6DL_PAD_ENET_TXD0__GPIO1_IO30            0x204 0x5d4 0x000 0x5 0x0
-#define MX6DL_PAD_ENET_TXD1__MLB_CLK               0x208 0x5d8 0x8dc 0x0 0x0
-#define MX6DL_PAD_ENET_TXD1__ENET_TX_DATA1         0x208 0x5d8 0x000 0x1 0x0
-#define MX6DL_PAD_ENET_TXD1__ESAI_TX2_RX3          0x208 0x5d8 0x84c 0x2 0x0
-#define MX6DL_PAD_ENET_TXD1__ENET_1588_EVENT0_IN   0x208 0x5d8 0x000 0x4 0x0
-#define MX6DL_PAD_ENET_TXD1__GPIO1_IO29            0x208 0x5d8 0x000 0x5 0x0
-#define MX6DL_PAD_ENET_TXD1__I2C4_SDA              0x208 0x5d8 0x884 0x9 0x0
-#define MX6DL_PAD_GPIO_0__CCM_CLKO1                0x20c 0x5dc 0x000 0x0 0x0
-#define MX6DL_PAD_GPIO_0__KEY_COL5                 0x20c 0x5dc 0x8c0 0x2 0x1
-#define MX6DL_PAD_GPIO_0__ASRC_EXT_CLK             0x20c 0x5dc 0x794 0x3 0x0
-#define MX6DL_PAD_GPIO_0__EPIT1_OUT                0x20c 0x5dc 0x000 0x4 0x0
-#define MX6DL_PAD_GPIO_0__GPIO1_IO00               0x20c 0x5dc 0x000 0x5 0x0
-#define MX6DL_PAD_GPIO_0__USB_H1_PWR               0x20c 0x5dc 0x000 0x6 0x0
-#define MX6DL_PAD_GPIO_0__SNVS_VIO_5               0x20c 0x5dc 0x000 0x7 0x0
-#define MX6DL_PAD_GPIO_1__ESAI_RX_CLK              0x210 0x5e0 0x83c 0x0 0x1
-#define MX6DL_PAD_GPIO_1__WDOG2_B                  0x210 0x5e0 0x000 0x1 0x0
-#define MX6DL_PAD_GPIO_1__KEY_ROW5                 0x210 0x5e0 0x8cc 0x2 0x1
-#define MX6DL_PAD_GPIO_1__USB_OTG_ID               0x210 0x5e0 0x790 0x3 0x1
-#define MX6DL_PAD_GPIO_1__PWM2_OUT                 0x210 0x5e0 0x000 0x4 0x0
-#define MX6DL_PAD_GPIO_1__GPIO1_IO01               0x210 0x5e0 0x000 0x5 0x0
-#define MX6DL_PAD_GPIO_1__SD1_CD_B                 0x210 0x5e0 0x000 0x6 0x0
-#define MX6DL_PAD_GPIO_16__ESAI_TX3_RX2            0x214 0x5e4 0x850 0x0 0x1
-#define MX6DL_PAD_GPIO_16__ENET_1588_EVENT2_IN     0x214 0x5e4 0x000 0x1 0x0
-#define MX6DL_PAD_GPIO_16__ENET_REF_CLK            0x214 0x5e4 0x80c 0x2 0x0
-#define MX6DL_PAD_GPIO_16__SD1_LCTL                0x214 0x5e4 0x000 0x3 0x0
-#define MX6DL_PAD_GPIO_16__SPDIF_IN                0x214 0x5e4 0x8f0 0x4 0x2
-#define MX6DL_PAD_GPIO_16__GPIO7_IO11              0x214 0x5e4 0x000 0x5 0x0
-#define MX6DL_PAD_GPIO_16__I2C3_SDA                0x214 0x5e4 0x87c 0x6 0x1
-#define MX6DL_PAD_GPIO_16__JTAG_DE_B               0x214 0x5e4 0x000 0x7 0x0
-#define MX6DL_PAD_GPIO_17__ESAI_TX0                0x218 0x5e8 0x844 0x0 0x0
-#define MX6DL_PAD_GPIO_17__ENET_1588_EVENT3_IN     0x218 0x5e8 0x000 0x1 0x0
-#define MX6DL_PAD_GPIO_17__CCM_PMIC_READY          0x218 0x5e8 0x7d4 0x2 0x1
-#define MX6DL_PAD_GPIO_17__SDMA_EXT_EVENT0         0x218 0x5e8 0x8e8 0x3 0x1
-#define MX6DL_PAD_GPIO_17__SPDIF_OUT               0x218 0x5e8 0x000 0x4 0x0
-#define MX6DL_PAD_GPIO_17__GPIO7_IO12              0x218 0x5e8 0x000 0x5 0x0
-#define MX6DL_PAD_GPIO_18__ESAI_TX1                0x21c 0x5ec 0x848 0x0 0x0
-#define MX6DL_PAD_GPIO_18__ENET_RX_CLK             0x21c 0x5ec 0x814 0x1 0x0
-#define MX6DL_PAD_GPIO_18__SD3_VSELECT             0x21c 0x5ec 0x000 0x2 0x0
-#define MX6DL_PAD_GPIO_18__SDMA_EXT_EVENT1         0x21c 0x5ec 0x8ec 0x3 0x1
-#define MX6DL_PAD_GPIO_18__ASRC_EXT_CLK            0x21c 0x5ec 0x794 0x4 0x1
-#define MX6DL_PAD_GPIO_18__GPIO7_IO13              0x21c 0x5ec 0x000 0x5 0x0
-#define MX6DL_PAD_GPIO_18__SNVS_VIO_5_CTL          0x21c 0x5ec 0x000 0x6 0x0
-#define MX6DL_PAD_GPIO_19__KEY_COL5                0x220 0x5f0 0x8c0 0x0 0x2
-#define MX6DL_PAD_GPIO_19__ENET_1588_EVENT0_OUT    0x220 0x5f0 0x000 0x1 0x0
-#define MX6DL_PAD_GPIO_19__SPDIF_OUT               0x220 0x5f0 0x000 0x2 0x0
-#define MX6DL_PAD_GPIO_19__CCM_CLKO1               0x220 0x5f0 0x000 0x3 0x0
-#define MX6DL_PAD_GPIO_19__ECSPI1_RDY              0x220 0x5f0 0x000 0x4 0x0
-#define MX6DL_PAD_GPIO_19__GPIO4_IO05              0x220 0x5f0 0x000 0x5 0x0
-#define MX6DL_PAD_GPIO_19__ENET_TX_ER              0x220 0x5f0 0x000 0x6 0x0
-#define MX6DL_PAD_GPIO_2__ESAI_TX_FS               0x224 0x5f4 0x830 0x0 0x1
-#define MX6DL_PAD_GPIO_2__KEY_ROW6                 0x224 0x5f4 0x8d0 0x2 0x1
-#define MX6DL_PAD_GPIO_2__GPIO1_IO02               0x224 0x5f4 0x000 0x5 0x0
-#define MX6DL_PAD_GPIO_2__SD2_WP                   0x224 0x5f4 0x000 0x6 0x0
-#define MX6DL_PAD_GPIO_2__MLB_DATA                 0x224 0x5f4 0x8e0 0x7 0x1
-#define MX6DL_PAD_GPIO_3__ESAI_RX_HF_CLK           0x228 0x5f8 0x834 0x0 0x1
-#define MX6DL_PAD_GPIO_3__I2C3_SCL                 0x228 0x5f8 0x878 0x2 0x1
-#define MX6DL_PAD_GPIO_3__XTALOSC_REF_CLK_24M      0x228 0x5f8 0x000 0x3 0x0
-#define MX6DL_PAD_GPIO_3__CCM_CLKO2                0x228 0x5f8 0x000 0x4 0x0
-#define MX6DL_PAD_GPIO_3__GPIO1_IO03               0x228 0x5f8 0x000 0x5 0x0
-#define MX6DL_PAD_GPIO_3__USB_H1_OC                0x228 0x5f8 0x924 0x6 0x1
-#define MX6DL_PAD_GPIO_3__MLB_CLK                  0x228 0x5f8 0x8dc 0x7 0x1
-#define MX6DL_PAD_GPIO_4__ESAI_TX_HF_CLK           0x22c 0x5fc 0x838 0x0 0x1
-#define MX6DL_PAD_GPIO_4__KEY_COL7                 0x22c 0x5fc 0x8c8 0x2 0x1
-#define MX6DL_PAD_GPIO_4__GPIO1_IO04               0x22c 0x5fc 0x000 0x5 0x0
-#define MX6DL_PAD_GPIO_4__SD2_CD_B                 0x22c 0x5fc 0x000 0x6 0x0
-#define MX6DL_PAD_GPIO_5__ESAI_TX2_RX3             0x230 0x600 0x84c 0x0 0x1
-#define MX6DL_PAD_GPIO_5__KEY_ROW7                 0x230 0x600 0x8d4 0x2 0x1
-#define MX6DL_PAD_GPIO_5__CCM_CLKO1                0x230 0x600 0x000 0x3 0x0
-#define MX6DL_PAD_GPIO_5__GPIO1_IO05               0x230 0x600 0x000 0x5 0x0
-#define MX6DL_PAD_GPIO_5__I2C3_SCL                 0x230 0x600 0x878 0x6 0x2
-#define MX6DL_PAD_GPIO_5__ARM_EVENTI               0x230 0x600 0x000 0x7 0x0
-#define MX6DL_PAD_GPIO_6__ESAI_TX_CLK              0x234 0x604 0x840 0x0 0x1
-#define MX6DL_PAD_GPIO_6__I2C3_SDA                 0x234 0x604 0x87c 0x2 0x2
-#define MX6DL_PAD_GPIO_6__GPIO1_IO06               0x234 0x604 0x000 0x5 0x0
-#define MX6DL_PAD_GPIO_6__SD2_LCTL                 0x234 0x604 0x000 0x6 0x0
-#define MX6DL_PAD_GPIO_6__MLB_SIG                  0x234 0x604 0x8e4 0x7 0x1
-#define MX6DL_PAD_GPIO_7__ESAI_TX4_RX1             0x238 0x608 0x854 0x0 0x1
-#define MX6DL_PAD_GPIO_7__EPIT1_OUT                0x238 0x608 0x000 0x2 0x0
-#define MX6DL_PAD_GPIO_7__FLEXCAN1_TX              0x238 0x608 0x000 0x3 0x0
-#define MX6DL_PAD_GPIO_7__UART2_TX_DATA            0x238 0x608 0x000 0x4 0x0
-#define MX6DL_PAD_GPIO_7__UART2_RX_DATA            0x238 0x608 0x904 0x4 0x2
-#define MX6DL_PAD_GPIO_7__GPIO1_IO07               0x238 0x608 0x000 0x5 0x0
-#define MX6DL_PAD_GPIO_7__SPDIF_LOCK               0x238 0x608 0x000 0x6 0x0
-#define MX6DL_PAD_GPIO_7__USB_OTG_HOST_MODE        0x238 0x608 0x000 0x7 0x0
-#define MX6DL_PAD_GPIO_7__I2C4_SCL                 0x238 0x608 0x880 0x8 0x1
-#define MX6DL_PAD_GPIO_8__ESAI_TX5_RX0             0x23c 0x60c 0x858 0x0 0x1
-#define MX6DL_PAD_GPIO_8__XTALOSC_REF_CLK_32K      0x23c 0x60c 0x000 0x1 0x0
-#define MX6DL_PAD_GPIO_8__EPIT2_OUT                0x23c 0x60c 0x000 0x2 0x0
-#define MX6DL_PAD_GPIO_8__FLEXCAN1_RX              0x23c 0x60c 0x7c8 0x3 0x0
-#define MX6DL_PAD_GPIO_8__UART2_RX_DATA            0x23c 0x60c 0x904 0x4 0x3
-#define MX6DL_PAD_GPIO_8__UART2_TX_DATA            0x23c 0x60c 0x000 0x4 0x0
-#define MX6DL_PAD_GPIO_8__GPIO1_IO08               0x23c 0x60c 0x000 0x5 0x0
-#define MX6DL_PAD_GPIO_8__SPDIF_SR_CLK             0x23c 0x60c 0x000 0x6 0x0
-#define MX6DL_PAD_GPIO_8__USB_OTG_PWR_CTL_WAKE     0x23c 0x60c 0x000 0x7 0x0
-#define MX6DL_PAD_GPIO_8__I2C4_SDA                 0x23c 0x60c 0x884 0x8 0x1
-#define MX6DL_PAD_GPIO_9__ESAI_RX_FS               0x240 0x610 0x82c 0x0 0x1
-#define MX6DL_PAD_GPIO_9__WDOG1_B                  0x240 0x610 0x000 0x1 0x0
-#define MX6DL_PAD_GPIO_9__KEY_COL6                 0x240 0x610 0x8c4 0x2 0x1
-#define MX6DL_PAD_GPIO_9__CCM_REF_EN_B             0x240 0x610 0x000 0x3 0x0
-#define MX6DL_PAD_GPIO_9__PWM1_OUT                 0x240 0x610 0x000 0x4 0x0
-#define MX6DL_PAD_GPIO_9__GPIO1_IO09               0x240 0x610 0x000 0x5 0x0
-#define MX6DL_PAD_GPIO_9__SD1_WP                   0x240 0x610 0x92c 0x6 0x1
-#define MX6DL_PAD_KEY_COL0__ECSPI1_SCLK            0x244 0x62c 0x7d8 0x0 0x3
-#define MX6DL_PAD_KEY_COL0__ENET_RX_DATA3          0x244 0x62c 0x824 0x1 0x0
-#define MX6DL_PAD_KEY_COL0__AUD5_TXC               0x244 0x62c 0x7c0 0x2 0x1
-#define MX6DL_PAD_KEY_COL0__KEY_COL0               0x244 0x62c 0x000 0x3 0x0
-#define MX6DL_PAD_KEY_COL0__UART4_TX_DATA          0x244 0x62c 0x000 0x4 0x0
-#define MX6DL_PAD_KEY_COL0__UART4_RX_DATA          0x244 0x62c 0x914 0x4 0x2
-#define MX6DL_PAD_KEY_COL0__GPIO4_IO06             0x244 0x62c 0x000 0x5 0x0
-#define MX6DL_PAD_KEY_COL0__DCIC1_OUT              0x244 0x62c 0x000 0x6 0x0
-#define MX6DL_PAD_KEY_COL1__ECSPI1_MISO            0x248 0x630 0x7dc 0x0 0x3
-#define MX6DL_PAD_KEY_COL1__ENET_MDIO              0x248 0x630 0x810 0x1 0x1
-#define MX6DL_PAD_KEY_COL1__AUD5_TXFS              0x248 0x630 0x7c4 0x2 0x1
-#define MX6DL_PAD_KEY_COL1__KEY_COL1               0x248 0x630 0x000 0x3 0x0
-#define MX6DL_PAD_KEY_COL1__UART5_TX_DATA          0x248 0x630 0x000 0x4 0x0
-#define MX6DL_PAD_KEY_COL1__UART5_RX_DATA          0x248 0x630 0x91c 0x4 0x2
-#define MX6DL_PAD_KEY_COL1__GPIO4_IO08             0x248 0x630 0x000 0x5 0x0
-#define MX6DL_PAD_KEY_COL1__SD1_VSELECT            0x248 0x630 0x000 0x6 0x0
-#define MX6DL_PAD_KEY_COL2__ECSPI1_SS1             0x24c 0x634 0x7e8 0x0 0x2
-#define MX6DL_PAD_KEY_COL2__ENET_RX_DATA2          0x24c 0x634 0x820 0x1 0x0
-#define MX6DL_PAD_KEY_COL2__FLEXCAN1_TX            0x24c 0x634 0x000 0x2 0x0
-#define MX6DL_PAD_KEY_COL2__KEY_COL2               0x24c 0x634 0x000 0x3 0x0
-#define MX6DL_PAD_KEY_COL2__ENET_MDC               0x24c 0x634 0x000 0x4 0x0
-#define MX6DL_PAD_KEY_COL2__GPIO4_IO10             0x24c 0x634 0x000 0x5 0x0
-#define MX6DL_PAD_KEY_COL2__USB_H1_PWR_CTL_WAKE    0x24c 0x634 0x000 0x6 0x0
-#define MX6DL_PAD_KEY_COL3__ECSPI1_SS3             0x250 0x638 0x7f0 0x0 0x1
-#define MX6DL_PAD_KEY_COL3__ENET_CRS               0x250 0x638 0x000 0x1 0x0
-#define MX6DL_PAD_KEY_COL3__HDMI_TX_DDC_SCL        0x250 0x638 0x860 0x2 0x1
-#define MX6DL_PAD_KEY_COL3__KEY_COL3               0x250 0x638 0x000 0x3 0x0
-#define MX6DL_PAD_KEY_COL3__I2C2_SCL               0x250 0x638 0x870 0x4 0x1
-#define MX6DL_PAD_KEY_COL3__GPIO4_IO12             0x250 0x638 0x000 0x5 0x0
-#define MX6DL_PAD_KEY_COL3__SPDIF_IN               0x250 0x638 0x8f0 0x6 0x3
-#define MX6DL_PAD_KEY_COL4__FLEXCAN2_TX            0x254 0x63c 0x000 0x0 0x0
-#define MX6DL_PAD_KEY_COL4__IPU1_SISG4             0x254 0x63c 0x000 0x1 0x0
-#define MX6DL_PAD_KEY_COL4__USB_OTG_OC             0x254 0x63c 0x920 0x2 0x1
-#define MX6DL_PAD_KEY_COL4__KEY_COL4               0x254 0x63c 0x000 0x3 0x0
-#define MX6DL_PAD_KEY_COL4__UART5_RTS_B            0x254 0x63c 0x918 0x4 0x2
-#define MX6DL_PAD_KEY_COL4__UART5_CTS_B            0x254 0x63c 0x000 0x4 0x0
-#define MX6DL_PAD_KEY_COL4__GPIO4_IO14             0x254 0x63c 0x000 0x5 0x0
-#define MX6DL_PAD_KEY_ROW0__ECSPI1_MOSI            0x258 0x640 0x7e0 0x0 0x3
-#define MX6DL_PAD_KEY_ROW0__ENET_TX_DATA3          0x258 0x640 0x000 0x1 0x0
-#define MX6DL_PAD_KEY_ROW0__AUD5_TXD               0x258 0x640 0x7b4 0x2 0x1
-#define MX6DL_PAD_KEY_ROW0__KEY_ROW0               0x258 0x640 0x000 0x3 0x0
-#define MX6DL_PAD_KEY_ROW0__UART4_RX_DATA          0x258 0x640 0x914 0x4 0x3
-#define MX6DL_PAD_KEY_ROW0__UART4_TX_DATA          0x258 0x640 0x000 0x4 0x0
-#define MX6DL_PAD_KEY_ROW0__GPIO4_IO07             0x258 0x640 0x000 0x5 0x0
-#define MX6DL_PAD_KEY_ROW0__DCIC2_OUT              0x258 0x640 0x000 0x6 0x0
-#define MX6DL_PAD_KEY_ROW1__ECSPI1_SS0             0x25c 0x644 0x7e4 0x0 0x3
-#define MX6DL_PAD_KEY_ROW1__ENET_COL               0x25c 0x644 0x000 0x1 0x0
-#define MX6DL_PAD_KEY_ROW1__AUD5_RXD               0x25c 0x644 0x7b0 0x2 0x1
-#define MX6DL_PAD_KEY_ROW1__KEY_ROW1               0x25c 0x644 0x000 0x3 0x0
-#define MX6DL_PAD_KEY_ROW1__UART5_RX_DATA          0x25c 0x644 0x91c 0x4 0x3
-#define MX6DL_PAD_KEY_ROW1__UART5_TX_DATA          0x25c 0x644 0x000 0x4 0x0
-#define MX6DL_PAD_KEY_ROW1__GPIO4_IO09             0x25c 0x644 0x000 0x5 0x0
-#define MX6DL_PAD_KEY_ROW1__SD2_VSELECT            0x25c 0x644 0x000 0x6 0x0
-#define MX6DL_PAD_KEY_ROW2__ECSPI1_SS2             0x260 0x648 0x7ec 0x0 0x1
-#define MX6DL_PAD_KEY_ROW2__ENET_TX_DATA2          0x260 0x648 0x000 0x1 0x0
-#define MX6DL_PAD_KEY_ROW2__FLEXCAN1_RX            0x260 0x648 0x7c8 0x2 0x1
-#define MX6DL_PAD_KEY_ROW2__KEY_ROW2               0x260 0x648 0x000 0x3 0x0
-#define MX6DL_PAD_KEY_ROW2__SD2_VSELECT            0x260 0x648 0x000 0x4 0x0
-#define MX6DL_PAD_KEY_ROW2__GPIO4_IO11             0x260 0x648 0x000 0x5 0x0
-#define MX6DL_PAD_KEY_ROW2__HDMI_TX_CEC_LINE       0x260 0x648 0x85c 0x6 0x1
-#define MX6DL_PAD_KEY_ROW3__ASRC_EXT_CLK           0x264 0x64c 0x794 0x1 0x2
-#define MX6DL_PAD_KEY_ROW3__HDMI_TX_DDC_SDA        0x264 0x64c 0x864 0x2 0x1
-#define MX6DL_PAD_KEY_ROW3__KEY_ROW3               0x264 0x64c 0x000 0x3 0x0
-#define MX6DL_PAD_KEY_ROW3__I2C2_SDA               0x264 0x64c 0x874 0x4 0x1
-#define MX6DL_PAD_KEY_ROW3__GPIO4_IO13             0x264 0x64c 0x000 0x5 0x0
-#define MX6DL_PAD_KEY_ROW3__SD1_VSELECT            0x264 0x64c 0x000 0x6 0x0
-#define MX6DL_PAD_KEY_ROW4__FLEXCAN2_RX            0x268 0x650 0x7cc 0x0 0x0
-#define MX6DL_PAD_KEY_ROW4__IPU1_SISG5             0x268 0x650 0x000 0x1 0x0
-#define MX6DL_PAD_KEY_ROW4__USB_OTG_PWR            0x268 0x650 0x000 0x2 0x0
-#define MX6DL_PAD_KEY_ROW4__KEY_ROW4               0x268 0x650 0x000 0x3 0x0
-#define MX6DL_PAD_KEY_ROW4__UART5_CTS_B            0x268 0x650 0x000 0x4 0x0
-#define MX6DL_PAD_KEY_ROW4__UART5_RTS_B            0x268 0x650 0x918 0x4 0x3
-#define MX6DL_PAD_KEY_ROW4__GPIO4_IO15             0x268 0x650 0x000 0x5 0x0
-#define MX6DL_PAD_NANDF_ALE__NAND_ALE              0x26c 0x654 0x000 0x0 0x0
-#define MX6DL_PAD_NANDF_ALE__SD4_RESET             0x26c 0x654 0x000 0x1 0x0
-#define MX6DL_PAD_NANDF_ALE__GPIO6_IO08            0x26c 0x654 0x000 0x5 0x0
-#define MX6DL_PAD_NANDF_CLE__NAND_CLE              0x270 0x658 0x000 0x0 0x0
-#define MX6DL_PAD_NANDF_CLE__GPIO6_IO07            0x270 0x658 0x000 0x5 0x0
-#define MX6DL_PAD_NANDF_CS0__NAND_CE0_B            0x274 0x65c 0x000 0x0 0x0
-#define MX6DL_PAD_NANDF_CS0__GPIO6_IO11            0x274 0x65c 0x000 0x5 0x0
-#define MX6DL_PAD_NANDF_CS1__NAND_CE1_B            0x278 0x660 0x000 0x0 0x0
-#define MX6DL_PAD_NANDF_CS1__SD4_VSELECT           0x278 0x660 0x000 0x1 0x0
-#define MX6DL_PAD_NANDF_CS1__SD3_VSELECT           0x278 0x660 0x000 0x2 0x0
-#define MX6DL_PAD_NANDF_CS1__GPIO6_IO14            0x278 0x660 0x000 0x5 0x0
-#define MX6DL_PAD_NANDF_CS2__NAND_CE2_B            0x27c 0x664 0x000 0x0 0x0
-#define MX6DL_PAD_NANDF_CS2__IPU1_SISG0            0x27c 0x664 0x000 0x1 0x0
-#define MX6DL_PAD_NANDF_CS2__ESAI_TX0              0x27c 0x664 0x844 0x2 0x1
-#define MX6DL_PAD_NANDF_CS2__EIM_CRE               0x27c 0x664 0x000 0x3 0x0
-#define MX6DL_PAD_NANDF_CS2__CCM_CLKO2             0x27c 0x664 0x000 0x4 0x0
-#define MX6DL_PAD_NANDF_CS2__GPIO6_IO15            0x27c 0x664 0x000 0x5 0x0
-#define MX6DL_PAD_NANDF_CS3__NAND_CE3_B            0x280 0x668 0x000 0x0 0x0
-#define MX6DL_PAD_NANDF_CS3__IPU1_SISG1            0x280 0x668 0x000 0x1 0x0
-#define MX6DL_PAD_NANDF_CS3__ESAI_TX1              0x280 0x668 0x848 0x2 0x1
-#define MX6DL_PAD_NANDF_CS3__EIM_ADDR26            0x280 0x668 0x000 0x3 0x0
-#define MX6DL_PAD_NANDF_CS3__GPIO6_IO16            0x280 0x668 0x000 0x5 0x0
-#define MX6DL_PAD_NANDF_CS3__I2C4_SDA              0x280 0x668 0x884 0x9 0x2
-#define MX6DL_PAD_NANDF_D0__NAND_DATA00            0x284 0x66c 0x000 0x0 0x0
-#define MX6DL_PAD_NANDF_D0__SD1_DATA4              0x284 0x66c 0x000 0x1 0x0
-#define MX6DL_PAD_NANDF_D0__GPIO2_IO00             0x284 0x66c 0x000 0x5 0x0
-#define MX6DL_PAD_NANDF_D1__NAND_DATA01            0x288 0x670 0x000 0x0 0x0
-#define MX6DL_PAD_NANDF_D1__SD1_DATA5              0x288 0x670 0x000 0x1 0x0
-#define MX6DL_PAD_NANDF_D1__GPIO2_IO01             0x288 0x670 0x000 0x5 0x0
-#define MX6DL_PAD_NANDF_D2__NAND_DATA02            0x28c 0x674 0x000 0x0 0x0
-#define MX6DL_PAD_NANDF_D2__SD1_DATA6              0x28c 0x674 0x000 0x1 0x0
-#define MX6DL_PAD_NANDF_D2__GPIO2_IO02             0x28c 0x674 0x000 0x5 0x0
-#define MX6DL_PAD_NANDF_D3__NAND_DATA03            0x290 0x678 0x000 0x0 0x0
-#define MX6DL_PAD_NANDF_D3__SD1_DATA7              0x290 0x678 0x000 0x1 0x0
-#define MX6DL_PAD_NANDF_D3__GPIO2_IO03             0x290 0x678 0x000 0x5 0x0
-#define MX6DL_PAD_NANDF_D4__NAND_DATA04            0x294 0x67c 0x000 0x0 0x0
-#define MX6DL_PAD_NANDF_D4__SD2_DATA4              0x294 0x67c 0x000 0x1 0x0
-#define MX6DL_PAD_NANDF_D4__GPIO2_IO04             0x294 0x67c 0x000 0x5 0x0
-#define MX6DL_PAD_NANDF_D5__NAND_DATA05            0x298 0x680 0x000 0x0 0x0
-#define MX6DL_PAD_NANDF_D5__SD2_DATA5              0x298 0x680 0x000 0x1 0x0
-#define MX6DL_PAD_NANDF_D5__GPIO2_IO05             0x298 0x680 0x000 0x5 0x0
-#define MX6DL_PAD_NANDF_D6__NAND_DATA06            0x29c 0x684 0x000 0x0 0x0
-#define MX6DL_PAD_NANDF_D6__SD2_DATA6              0x29c 0x684 0x000 0x1 0x0
-#define MX6DL_PAD_NANDF_D6__GPIO2_IO06             0x29c 0x684 0x000 0x5 0x0
-#define MX6DL_PAD_NANDF_D7__NAND_DATA07            0x2a0 0x688 0x000 0x0 0x0
-#define MX6DL_PAD_NANDF_D7__SD2_DATA7              0x2a0 0x688 0x000 0x1 0x0
-#define MX6DL_PAD_NANDF_D7__GPIO2_IO07             0x2a0 0x688 0x000 0x5 0x0
-#define MX6DL_PAD_NANDF_RB0__NAND_READY_B          0x2a4 0x68c 0x000 0x0 0x0
-#define MX6DL_PAD_NANDF_RB0__GPIO6_IO10            0x2a4 0x68c 0x000 0x5 0x0
-#define MX6DL_PAD_NANDF_WP_B__NAND_WP_B            0x2a8 0x690 0x000 0x0 0x0
-#define MX6DL_PAD_NANDF_WP_B__GPIO6_IO09           0x2a8 0x690 0x000 0x5 0x0
-#define MX6DL_PAD_NANDF_WP_B__I2C4_SCL             0x2a8 0x690 0x880 0x9 0x2
-#define MX6DL_PAD_RGMII_RD0__HSI_RX_READY          0x2ac 0x694 0x000 0x0 0x0
-#define MX6DL_PAD_RGMII_RD0__RGMII_RD0             0x2ac 0x694 0x818 0x1 0x1
-#define MX6DL_PAD_RGMII_RD0__GPIO6_IO25            0x2ac 0x694 0x000 0x5 0x0
-#define MX6DL_PAD_RGMII_RD1__HSI_TX_FLAG           0x2b0 0x698 0x000 0x0 0x0
-#define MX6DL_PAD_RGMII_RD1__RGMII_RD1             0x2b0 0x698 0x81c 0x1 0x1
-#define MX6DL_PAD_RGMII_RD1__GPIO6_IO27            0x2b0 0x698 0x000 0x5 0x0
-#define MX6DL_PAD_RGMII_RD2__HSI_TX_DATA           0x2b4 0x69c 0x000 0x0 0x0
-#define MX6DL_PAD_RGMII_RD2__RGMII_RD2             0x2b4 0x69c 0x820 0x1 0x1
-#define MX6DL_PAD_RGMII_RD2__GPIO6_IO28            0x2b4 0x69c 0x000 0x5 0x0
-#define MX6DL_PAD_RGMII_RD3__HSI_TX_WAKE           0x2b8 0x6a0 0x000 0x0 0x0
-#define MX6DL_PAD_RGMII_RD3__RGMII_RD3             0x2b8 0x6a0 0x824 0x1 0x1
-#define MX6DL_PAD_RGMII_RD3__GPIO6_IO29            0x2b8 0x6a0 0x000 0x5 0x0
-#define MX6DL_PAD_RGMII_RX_CTL__USB_H3_DATA        0x2bc 0x6a4 0x000 0x0 0x0
-#define MX6DL_PAD_RGMII_RX_CTL__RGMII_RX_CTL       0x2bc 0x6a4 0x828 0x1 0x1
-#define MX6DL_PAD_RGMII_RX_CTL__GPIO6_IO24         0x2bc 0x6a4 0x000 0x5 0x0
-#define MX6DL_PAD_RGMII_RXC__USB_H3_STROBE         0x2c0 0x6a8 0x000 0x0 0x0
-#define MX6DL_PAD_RGMII_RXC__RGMII_RXC             0x2c0 0x6a8 0x814 0x1 0x1
-#define MX6DL_PAD_RGMII_RXC__GPIO6_IO30            0x2c0 0x6a8 0x000 0x5 0x0
-#define MX6DL_PAD_RGMII_TD0__HSI_TX_READY          0x2c4 0x6ac 0x000 0x0 0x0
-#define MX6DL_PAD_RGMII_TD0__RGMII_TD0             0x2c4 0x6ac 0x000 0x1 0x0
-#define MX6DL_PAD_RGMII_TD0__GPIO6_IO20            0x2c4 0x6ac 0x000 0x5 0x0
-#define MX6DL_PAD_RGMII_TD1__HSI_RX_FLAG           0x2c8 0x6b0 0x000 0x0 0x0
-#define MX6DL_PAD_RGMII_TD1__RGMII_TD1             0x2c8 0x6b0 0x000 0x1 0x0
-#define MX6DL_PAD_RGMII_TD1__GPIO6_IO21            0x2c8 0x6b0 0x000 0x5 0x0
-#define MX6DL_PAD_RGMII_TD2__HSI_RX_DATA           0x2cc 0x6b4 0x000 0x0 0x0
-#define MX6DL_PAD_RGMII_TD2__RGMII_TD2             0x2cc 0x6b4 0x000 0x1 0x0
-#define MX6DL_PAD_RGMII_TD2__GPIO6_IO22            0x2cc 0x6b4 0x000 0x5 0x0
-#define MX6DL_PAD_RGMII_TD3__HSI_RX_WAKE           0x2d0 0x6b8 0x000 0x0 0x0
-#define MX6DL_PAD_RGMII_TD3__RGMII_TD3             0x2d0 0x6b8 0x000 0x1 0x0
-#define MX6DL_PAD_RGMII_TD3__GPIO6_IO23            0x2d0 0x6b8 0x000 0x5 0x0
-#define MX6DL_PAD_RGMII_TX_CTL__USB_H2_STROBE      0x2d4 0x6bc 0x000 0x0 0x0
-#define MX6DL_PAD_RGMII_TX_CTL__RGMII_TX_CTL       0x2d4 0x6bc 0x000 0x1 0x0
-#define MX6DL_PAD_RGMII_TX_CTL__GPIO6_IO26         0x2d4 0x6bc 0x000 0x5 0x0
-#define MX6DL_PAD_RGMII_TX_CTL__ENET_REF_CLK       0x2d4 0x6bc 0x80c 0x7 0x1
-#define MX6DL_PAD_RGMII_TXC__USB_H2_DATA           0x2d8 0x6c0 0x000 0x0 0x0
-#define MX6DL_PAD_RGMII_TXC__RGMII_TXC             0x2d8 0x6c0 0x000 0x1 0x0
-#define MX6DL_PAD_RGMII_TXC__SPDIF_EXT_CLK         0x2d8 0x6c0 0x8f4 0x2 0x1
-#define MX6DL_PAD_RGMII_TXC__GPIO6_IO19            0x2d8 0x6c0 0x000 0x5 0x0
-#define MX6DL_PAD_RGMII_TXC__XTALOSC_REF_CLK_24M   0x2d8 0x6c0 0x000 0x7 0x0
-#define MX6DL_PAD_SD1_CLK__SD1_CLK                 0x2dc 0x6c4 0x928 0x0 0x1
-#define MX6DL_PAD_SD1_CLK__GPT_CLKIN               0x2dc 0x6c4 0x000 0x3 0x0
-#define MX6DL_PAD_SD1_CLK__GPIO1_IO20              0x2dc 0x6c4 0x000 0x5 0x0
-#define MX6DL_PAD_SD1_CMD__SD1_CMD                 0x2e0 0x6c8 0x000 0x0 0x0
-#define MX6DL_PAD_SD1_CMD__PWM4_OUT                0x2e0 0x6c8 0x000 0x2 0x0
-#define MX6DL_PAD_SD1_CMD__GPT_COMPARE1            0x2e0 0x6c8 0x000 0x3 0x0
-#define MX6DL_PAD_SD1_CMD__GPIO1_IO18              0x2e0 0x6c8 0x000 0x5 0x0
-#define MX6DL_PAD_SD1_DAT0__SD1_DATA0              0x2e4 0x6cc 0x000 0x0 0x0
-#define MX6DL_PAD_SD1_DAT0__GPT_CAPTURE1           0x2e4 0x6cc 0x000 0x3 0x0
-#define MX6DL_PAD_SD1_DAT0__GPIO1_IO16             0x2e4 0x6cc 0x000 0x5 0x0
-#define MX6DL_PAD_SD1_DAT1__SD1_DATA1              0x2e8 0x6d0 0x000 0x0 0x0
-#define MX6DL_PAD_SD1_DAT1__PWM3_OUT               0x2e8 0x6d0 0x000 0x2 0x0
-#define MX6DL_PAD_SD1_DAT1__GPT_CAPTURE2           0x2e8 0x6d0 0x000 0x3 0x0
-#define MX6DL_PAD_SD1_DAT1__GPIO1_IO17             0x2e8 0x6d0 0x000 0x5 0x0
-#define MX6DL_PAD_SD1_DAT2__SD1_DATA2              0x2ec 0x6d4 0x000 0x0 0x0
-#define MX6DL_PAD_SD1_DAT2__GPT_COMPARE2           0x2ec 0x6d4 0x000 0x2 0x0
-#define MX6DL_PAD_SD1_DAT2__PWM2_OUT               0x2ec 0x6d4 0x000 0x3 0x0
-#define MX6DL_PAD_SD1_DAT2__WDOG1_B                0x2ec 0x6d4 0x000 0x4 0x0
-#define MX6DL_PAD_SD1_DAT2__GPIO1_IO19             0x2ec 0x6d4 0x000 0x5 0x0
-#define MX6DL_PAD_SD1_DAT2__WDOG1_RESET_B_DEB      0x2ec 0x6d4 0x000 0x6 0x0
-#define MX6DL_PAD_SD1_DAT3__SD1_DATA3              0x2f0 0x6d8 0x000 0x0 0x0
-#define MX6DL_PAD_SD1_DAT3__GPT_COMPARE3           0x2f0 0x6d8 0x000 0x2 0x0
-#define MX6DL_PAD_SD1_DAT3__PWM1_OUT               0x2f0 0x6d8 0x000 0x3 0x0
-#define MX6DL_PAD_SD1_DAT3__WDOG2_B                0x2f0 0x6d8 0x000 0x4 0x0
-#define MX6DL_PAD_SD1_DAT3__GPIO1_IO21             0x2f0 0x6d8 0x000 0x5 0x0
-#define MX6DL_PAD_SD1_DAT3__WDOG2_RESET_B_DEB      0x2f0 0x6d8 0x000 0x6 0x0
-#define MX6DL_PAD_SD2_CLK__SD2_CLK                 0x2f4 0x6dc 0x930 0x0 0x1
-#define MX6DL_PAD_SD2_CLK__KEY_COL5                0x2f4 0x6dc 0x8c0 0x2 0x3
-#define MX6DL_PAD_SD2_CLK__AUD4_RXFS               0x2f4 0x6dc 0x7a4 0x3 0x1
-#define MX6DL_PAD_SD2_CLK__GPIO1_IO10              0x2f4 0x6dc 0x000 0x5 0x0
-#define MX6DL_PAD_SD2_CMD__SD2_CMD                 0x2f8 0x6e0 0x000 0x0 0x0
-#define MX6DL_PAD_SD2_CMD__KEY_ROW5                0x2f8 0x6e0 0x8cc 0x2 0x2
-#define MX6DL_PAD_SD2_CMD__AUD4_RXC                0x2f8 0x6e0 0x7a0 0x3 0x1
-#define MX6DL_PAD_SD2_CMD__GPIO1_IO11              0x2f8 0x6e0 0x000 0x5 0x0
-#define MX6DL_PAD_SD2_DAT0__SD2_DATA0              0x2fc 0x6e4 0x000 0x0 0x0
-#define MX6DL_PAD_SD2_DAT0__AUD4_RXD               0x2fc 0x6e4 0x798 0x3 0x1
-#define MX6DL_PAD_SD2_DAT0__KEY_ROW7               0x2fc 0x6e4 0x8d4 0x4 0x2
-#define MX6DL_PAD_SD2_DAT0__GPIO1_IO15             0x2fc 0x6e4 0x000 0x5 0x0
-#define MX6DL_PAD_SD2_DAT0__DCIC2_OUT              0x2fc 0x6e4 0x000 0x6 0x0
-#define MX6DL_PAD_SD2_DAT1__SD2_DATA1              0x300 0x6e8 0x000 0x0 0x0
-#define MX6DL_PAD_SD2_DAT1__EIM_CS2_B              0x300 0x6e8 0x000 0x2 0x0
-#define MX6DL_PAD_SD2_DAT1__AUD4_TXFS              0x300 0x6e8 0x7ac 0x3 0x1
-#define MX6DL_PAD_SD2_DAT1__KEY_COL7               0x300 0x6e8 0x8c8 0x4 0x2
-#define MX6DL_PAD_SD2_DAT1__GPIO1_IO14             0x300 0x6e8 0x000 0x5 0x0
-#define MX6DL_PAD_SD2_DAT2__SD2_DATA2              0x304 0x6ec 0x000 0x0 0x0
-#define MX6DL_PAD_SD2_DAT2__EIM_CS3_B              0x304 0x6ec 0x000 0x2 0x0
-#define MX6DL_PAD_SD2_DAT2__AUD4_TXD               0x304 0x6ec 0x79c 0x3 0x1
-#define MX6DL_PAD_SD2_DAT2__KEY_ROW6               0x304 0x6ec 0x8d0 0x4 0x2
-#define MX6DL_PAD_SD2_DAT2__GPIO1_IO13             0x304 0x6ec 0x000 0x5 0x0
-#define MX6DL_PAD_SD2_DAT3__SD2_DATA3              0x308 0x6f0 0x000 0x0 0x0
-#define MX6DL_PAD_SD2_DAT3__KEY_COL6               0x308 0x6f0 0x8c4 0x2 0x2
-#define MX6DL_PAD_SD2_DAT3__AUD4_TXC               0x308 0x6f0 0x7a8 0x3 0x1
-#define MX6DL_PAD_SD2_DAT3__GPIO1_IO12             0x308 0x6f0 0x000 0x5 0x0
-#define MX6DL_PAD_SD3_CLK__SD3_CLK                 0x30c 0x6f4 0x934 0x0 0x1
-#define MX6DL_PAD_SD3_CLK__UART2_RTS_B             0x30c 0x6f4 0x900 0x1 0x2
-#define MX6DL_PAD_SD3_CLK__UART2_CTS_B             0x30c 0x6f4 0x000 0x1 0x0
-#define MX6DL_PAD_SD3_CLK__FLEXCAN1_RX             0x30c 0x6f4 0x7c8 0x2 0x2
-#define MX6DL_PAD_SD3_CLK__GPIO7_IO03              0x30c 0x6f4 0x000 0x5 0x0
-#define MX6DL_PAD_SD3_CMD__SD3_CMD                 0x310 0x6f8 0x000 0x0 0x0
-#define MX6DL_PAD_SD3_CMD__UART2_CTS_B             0x310 0x6f8 0x000 0x1 0x0
-#define MX6DL_PAD_SD3_CMD__UART2_RTS_B             0x310 0x6f8 0x900 0x1 0x3
-#define MX6DL_PAD_SD3_CMD__FLEXCAN1_TX             0x310 0x6f8 0x000 0x2 0x0
-#define MX6DL_PAD_SD3_CMD__GPIO7_IO02              0x310 0x6f8 0x000 0x5 0x0
-#define MX6DL_PAD_SD3_DAT0__SD3_DATA0              0x314 0x6fc 0x000 0x0 0x0
-#define MX6DL_PAD_SD3_DAT0__UART1_CTS_B            0x314 0x6fc 0x000 0x1 0x0
-#define MX6DL_PAD_SD3_DAT0__UART1_RTS_B            0x314 0x6fc 0x8f8 0x1 0x2
-#define MX6DL_PAD_SD3_DAT0__FLEXCAN2_TX            0x314 0x6fc 0x000 0x2 0x0
-#define MX6DL_PAD_SD3_DAT0__GPIO7_IO04             0x314 0x6fc 0x000 0x5 0x0
-#define MX6DL_PAD_SD3_DAT1__SD3_DATA1              0x318 0x700 0x000 0x0 0x0
-#define MX6DL_PAD_SD3_DAT1__UART1_RTS_B            0x318 0x700 0x8f8 0x1 0x3
-#define MX6DL_PAD_SD3_DAT1__UART1_CTS_B            0x318 0x700 0x000 0x1 0x0
-#define MX6DL_PAD_SD3_DAT1__FLEXCAN2_RX            0x318 0x700 0x7cc 0x2 0x1
-#define MX6DL_PAD_SD3_DAT1__GPIO7_IO05             0x318 0x700 0x000 0x5 0x0
-#define MX6DL_PAD_SD3_DAT2__SD3_DATA2              0x31c 0x704 0x000 0x0 0x0
-#define MX6DL_PAD_SD3_DAT2__GPIO7_IO06             0x31c 0x704 0x000 0x5 0x0
-#define MX6DL_PAD_SD3_DAT3__SD3_DATA3              0x320 0x708 0x000 0x0 0x0
-#define MX6DL_PAD_SD3_DAT3__UART3_CTS_B            0x320 0x708 0x000 0x1 0x0
-#define MX6DL_PAD_SD3_DAT3__UART3_RTS_B            0x320 0x708 0x908 0x1 0x4
-#define MX6DL_PAD_SD3_DAT3__GPIO7_IO07             0x320 0x708 0x000 0x5 0x0
-#define MX6DL_PAD_SD3_DAT4__SD3_DATA4              0x324 0x70c 0x000 0x0 0x0
-#define MX6DL_PAD_SD3_DAT4__UART2_RX_DATA          0x324 0x70c 0x904 0x1 0x4
-#define MX6DL_PAD_SD3_DAT4__UART2_TX_DATA          0x324 0x70c 0x000 0x1 0x0
-#define MX6DL_PAD_SD3_DAT4__GPIO7_IO01             0x324 0x70c 0x000 0x5 0x0
-#define MX6DL_PAD_SD3_DAT5__SD3_DATA5              0x328 0x710 0x000 0x0 0x0
-#define MX6DL_PAD_SD3_DAT5__UART2_TX_DATA          0x328 0x710 0x000 0x1 0x0
-#define MX6DL_PAD_SD3_DAT5__UART2_RX_DATA          0x328 0x710 0x904 0x1 0x5
-#define MX6DL_PAD_SD3_DAT5__GPIO7_IO00             0x328 0x710 0x000 0x5 0x0
-#define MX6DL_PAD_SD3_DAT6__SD3_DATA6              0x32c 0x714 0x000 0x0 0x0
-#define MX6DL_PAD_SD3_DAT6__UART1_RX_DATA          0x32c 0x714 0x8fc 0x1 0x2
-#define MX6DL_PAD_SD3_DAT6__UART1_TX_DATA          0x32c 0x714 0x000 0x1 0x0
-#define MX6DL_PAD_SD3_DAT6__GPIO6_IO18             0x32c 0x714 0x000 0x5 0x0
-#define MX6DL_PAD_SD3_DAT7__SD3_DATA7              0x330 0x718 0x000 0x0 0x0
-#define MX6DL_PAD_SD3_DAT7__UART1_TX_DATA          0x330 0x718 0x000 0x1 0x0
-#define MX6DL_PAD_SD3_DAT7__UART1_RX_DATA          0x330 0x718 0x8fc 0x1 0x3
-#define MX6DL_PAD_SD3_DAT7__GPIO6_IO17             0x330 0x718 0x000 0x5 0x0
-#define MX6DL_PAD_SD3_RST__SD3_RESET               0x334 0x71c 0x000 0x0 0x0
-#define MX6DL_PAD_SD3_RST__UART3_RTS_B             0x334 0x71c 0x908 0x1 0x5
-#define MX6DL_PAD_SD3_RST__UART3_CTS_B             0x334 0x71c 0x000 0x1 0x0
-#define MX6DL_PAD_SD3_RST__GPIO7_IO08              0x334 0x71c 0x000 0x5 0x0
-#define MX6DL_PAD_SD4_CLK__SD4_CLK                 0x338 0x720 0x938 0x0 0x1
-#define MX6DL_PAD_SD4_CLK__NAND_WE_B               0x338 0x720 0x000 0x1 0x0
-#define MX6DL_PAD_SD4_CLK__UART3_RX_DATA           0x338 0x720 0x90c 0x2 0x2
-#define MX6DL_PAD_SD4_CLK__UART3_TX_DATA           0x338 0x720 0x000 0x2 0x0
-#define MX6DL_PAD_SD4_CLK__GPIO7_IO10              0x338 0x720 0x000 0x5 0x0
-#define MX6DL_PAD_SD4_CMD__SD4_CMD                 0x33c 0x724 0x000 0x0 0x0
-#define MX6DL_PAD_SD4_CMD__NAND_RE_B               0x33c 0x724 0x000 0x1 0x0
-#define MX6DL_PAD_SD4_CMD__UART3_TX_DATA           0x33c 0x724 0x000 0x2 0x0
-#define MX6DL_PAD_SD4_CMD__UART3_RX_DATA           0x33c 0x724 0x90c 0x2 0x3
-#define MX6DL_PAD_SD4_CMD__GPIO7_IO09              0x33c 0x724 0x000 0x5 0x0
-#define MX6DL_PAD_SD4_DAT0__SD4_DATA0              0x340 0x728 0x000 0x1 0x0
-#define MX6DL_PAD_SD4_DAT0__NAND_DQS               0x340 0x728 0x000 0x2 0x0
-#define MX6DL_PAD_SD4_DAT0__GPIO2_IO08             0x340 0x728 0x000 0x5 0x0
-#define MX6DL_PAD_SD4_DAT1__SD4_DATA1              0x344 0x72c 0x000 0x1 0x0
-#define MX6DL_PAD_SD4_DAT1__PWM3_OUT               0x344 0x72c 0x000 0x2 0x0
-#define MX6DL_PAD_SD4_DAT1__GPIO2_IO09             0x344 0x72c 0x000 0x5 0x0
-#define MX6DL_PAD_SD4_DAT2__SD4_DATA2              0x348 0x730 0x000 0x1 0x0
-#define MX6DL_PAD_SD4_DAT2__PWM4_OUT               0x348 0x730 0x000 0x2 0x0
-#define MX6DL_PAD_SD4_DAT2__GPIO2_IO10             0x348 0x730 0x000 0x5 0x0
-#define MX6DL_PAD_SD4_DAT3__SD4_DATA3              0x34c 0x734 0x000 0x1 0x0
-#define MX6DL_PAD_SD4_DAT3__GPIO2_IO11             0x34c 0x734 0x000 0x5 0x0
-#define MX6DL_PAD_SD4_DAT4__SD4_DATA4              0x350 0x738 0x000 0x1 0x0
-#define MX6DL_PAD_SD4_DAT4__UART2_RX_DATA          0x350 0x738 0x904 0x2 0x6
-#define MX6DL_PAD_SD4_DAT4__UART2_TX_DATA          0x350 0x738 0x000 0x2 0x0
-#define MX6DL_PAD_SD4_DAT4__GPIO2_IO12             0x350 0x738 0x000 0x5 0x0
-#define MX6DL_PAD_SD4_DAT5__SD4_DATA5              0x354 0x73c 0x000 0x1 0x0
-#define MX6DL_PAD_SD4_DAT5__UART2_RTS_B            0x354 0x73c 0x900 0x2 0x4
-#define MX6DL_PAD_SD4_DAT5__UART2_CTS_B            0x354 0x73c 0x000 0x2 0x0
-#define MX6DL_PAD_SD4_DAT5__GPIO2_IO13             0x354 0x73c 0x000 0x5 0x0
-#define MX6DL_PAD_SD4_DAT6__SD4_DATA6              0x358 0x740 0x000 0x1 0x0
-#define MX6DL_PAD_SD4_DAT6__UART2_CTS_B            0x358 0x740 0x000 0x2 0x0
-#define MX6DL_PAD_SD4_DAT6__UART2_RTS_B            0x358 0x740 0x900 0x2 0x5
-#define MX6DL_PAD_SD4_DAT6__GPIO2_IO14             0x358 0x740 0x000 0x5 0x0
-#define MX6DL_PAD_SD4_DAT7__SD4_DATA7              0x35c 0x744 0x000 0x1 0x0
-#define MX6DL_PAD_SD4_DAT7__UART2_TX_DATA          0x35c 0x744 0x000 0x2 0x0
-#define MX6DL_PAD_SD4_DAT7__UART2_RX_DATA          0x35c 0x744 0x904 0x2 0x7
-#define MX6DL_PAD_SD4_DAT7__GPIO2_IO15             0x35c 0x744 0x000 0x5 0x0
+#define MX6QDL_PAD_CSI0_DAT10__IPU1_CSI0_DATA10     0x04c 0x360 0x000 0x0 0x0
+#define MX6QDL_PAD_CSI0_DAT10__AUD3_RXC             0x04c 0x360 0x000 0x1 0x0
+#define MX6QDL_PAD_CSI0_DAT10__ECSPI2_MISO          0x04c 0x360 0x7f8 0x2 0x0
+#define MX6QDL_PAD_CSI0_DAT10__UART1_TX_DATA        0x04c 0x360 0x000 0x3 0x0
+#define MX6QDL_PAD_CSI0_DAT10__UART1_RX_DATA        0x04c 0x360 0x8fc 0x3 0x0
+#define MX6QDL_PAD_CSI0_DAT10__GPIO5_IO28           0x04c 0x360 0x000 0x5 0x0
+#define MX6QDL_PAD_CSI0_DAT10__ARM_TRACE07          0x04c 0x360 0x000 0x7 0x0
+#define MX6QDL_PAD_CSI0_DAT11__IPU1_CSI0_DATA11     0x050 0x364 0x000 0x0 0x0
+#define MX6QDL_PAD_CSI0_DAT11__AUD3_RXFS            0x050 0x364 0x000 0x1 0x0
+#define MX6QDL_PAD_CSI0_DAT11__ECSPI2_SS0           0x050 0x364 0x800 0x2 0x0
+#define MX6QDL_PAD_CSI0_DAT11__UART1_RX_DATA        0x050 0x364 0x8fc 0x3 0x1
+#define MX6QDL_PAD_CSI0_DAT11__UART1_TX_DATA        0x050 0x364 0x000 0x3 0x0
+#define MX6QDL_PAD_CSI0_DAT11__GPIO5_IO29           0x050 0x364 0x000 0x5 0x0
+#define MX6QDL_PAD_CSI0_DAT11__ARM_TRACE08          0x050 0x364 0x000 0x7 0x0
+#define MX6QDL_PAD_CSI0_DAT12__IPU1_CSI0_DATA12     0x054 0x368 0x000 0x0 0x0
+#define MX6QDL_PAD_CSI0_DAT12__EIM_DATA08           0x054 0x368 0x000 0x1 0x0
+#define MX6QDL_PAD_CSI0_DAT12__UART4_TX_DATA        0x054 0x368 0x000 0x3 0x0
+#define MX6QDL_PAD_CSI0_DAT12__UART4_RX_DATA        0x054 0x368 0x914 0x3 0x0
+#define MX6QDL_PAD_CSI0_DAT12__GPIO5_IO30           0x054 0x368 0x000 0x5 0x0
+#define MX6QDL_PAD_CSI0_DAT12__ARM_TRACE09          0x054 0x368 0x000 0x7 0x0
+#define MX6QDL_PAD_CSI0_DAT13__IPU1_CSI0_DATA13     0x058 0x36c 0x000 0x0 0x0
+#define MX6QDL_PAD_CSI0_DAT13__EIM_DATA09           0x058 0x36c 0x000 0x1 0x0
+#define MX6QDL_PAD_CSI0_DAT13__UART4_RX_DATA        0x058 0x36c 0x914 0x3 0x1
+#define MX6QDL_PAD_CSI0_DAT13__UART4_TX_DATA        0x058 0x36c 0x000 0x3 0x0
+#define MX6QDL_PAD_CSI0_DAT13__GPIO5_IO31           0x058 0x36c 0x000 0x5 0x0
+#define MX6QDL_PAD_CSI0_DAT13__ARM_TRACE10          0x058 0x36c 0x000 0x7 0x0
+#define MX6QDL_PAD_CSI0_DAT14__IPU1_CSI0_DATA14     0x05c 0x370 0x000 0x0 0x0
+#define MX6QDL_PAD_CSI0_DAT14__EIM_DATA10           0x05c 0x370 0x000 0x1 0x0
+#define MX6QDL_PAD_CSI0_DAT14__UART5_TX_DATA        0x05c 0x370 0x000 0x3 0x0
+#define MX6QDL_PAD_CSI0_DAT14__UART5_RX_DATA        0x05c 0x370 0x91c 0x3 0x0
+#define MX6QDL_PAD_CSI0_DAT14__GPIO6_IO00           0x05c 0x370 0x000 0x5 0x0
+#define MX6QDL_PAD_CSI0_DAT14__ARM_TRACE11          0x05c 0x370 0x000 0x7 0x0
+#define MX6QDL_PAD_CSI0_DAT15__IPU1_CSI0_DATA15     0x060 0x374 0x000 0x0 0x0
+#define MX6QDL_PAD_CSI0_DAT15__EIM_DATA11           0x060 0x374 0x000 0x1 0x0
+#define MX6QDL_PAD_CSI0_DAT15__UART5_RX_DATA        0x060 0x374 0x91c 0x3 0x1
+#define MX6QDL_PAD_CSI0_DAT15__UART5_TX_DATA        0x060 0x374 0x000 0x3 0x0
+#define MX6QDL_PAD_CSI0_DAT15__GPIO6_IO01           0x060 0x374 0x000 0x5 0x0
+#define MX6QDL_PAD_CSI0_DAT15__ARM_TRACE12          0x060 0x374 0x000 0x7 0x0
+#define MX6QDL_PAD_CSI0_DAT16__IPU1_CSI0_DATA16     0x064 0x378 0x000 0x0 0x0
+#define MX6QDL_PAD_CSI0_DAT16__EIM_DATA12           0x064 0x378 0x000 0x1 0x0
+#define MX6QDL_PAD_CSI0_DAT16__UART4_RTS_B          0x064 0x378 0x910 0x3 0x0
+#define MX6QDL_PAD_CSI0_DAT16__UART4_CTS_B          0x064 0x378 0x000 0x3 0x0
+#define MX6QDL_PAD_CSI0_DAT16__GPIO6_IO02           0x064 0x378 0x000 0x5 0x0
+#define MX6QDL_PAD_CSI0_DAT16__ARM_TRACE13          0x064 0x378 0x000 0x7 0x0
+#define MX6QDL_PAD_CSI0_DAT17__IPU1_CSI0_DATA17     0x068 0x37c 0x000 0x0 0x0
+#define MX6QDL_PAD_CSI0_DAT17__EIM_DATA13           0x068 0x37c 0x000 0x1 0x0
+#define MX6QDL_PAD_CSI0_DAT17__UART4_CTS_B          0x068 0x37c 0x000 0x3 0x0
+#define MX6QDL_PAD_CSI0_DAT17__UART4_RTS_B          0x068 0x37c 0x910 0x3 0x1
+#define MX6QDL_PAD_CSI0_DAT17__GPIO6_IO03           0x068 0x37c 0x000 0x5 0x0
+#define MX6QDL_PAD_CSI0_DAT17__ARM_TRACE14          0x068 0x37c 0x000 0x7 0x0
+#define MX6QDL_PAD_CSI0_DAT18__IPU1_CSI0_DATA18     0x06c 0x380 0x000 0x0 0x0
+#define MX6QDL_PAD_CSI0_DAT18__EIM_DATA14           0x06c 0x380 0x000 0x1 0x0
+#define MX6QDL_PAD_CSI0_DAT18__UART5_RTS_B          0x06c 0x380 0x918 0x3 0x0
+#define MX6QDL_PAD_CSI0_DAT18__UART5_CTS_B          0x06c 0x380 0x000 0x3 0x0
+#define MX6QDL_PAD_CSI0_DAT18__GPIO6_IO04           0x06c 0x380 0x000 0x5 0x0
+#define MX6QDL_PAD_CSI0_DAT18__ARM_TRACE15          0x06c 0x380 0x000 0x7 0x0
+#define MX6QDL_PAD_CSI0_DAT19__IPU1_CSI0_DATA19     0x070 0x384 0x000 0x0 0x0
+#define MX6QDL_PAD_CSI0_DAT19__EIM_DATA15           0x070 0x384 0x000 0x1 0x0
+#define MX6QDL_PAD_CSI0_DAT19__UART5_CTS_B          0x070 0x384 0x000 0x3 0x0
+#define MX6QDL_PAD_CSI0_DAT19__UART5_RTS_B          0x070 0x384 0x918 0x3 0x1
+#define MX6QDL_PAD_CSI0_DAT19__GPIO6_IO05           0x070 0x384 0x000 0x5 0x0
+#define MX6QDL_PAD_CSI0_DAT4__IPU1_CSI0_DATA04      0x074 0x388 0x000 0x0 0x0
+#define MX6QDL_PAD_CSI0_DAT4__EIM_DATA02            0x074 0x388 0x000 0x1 0x0
+#define MX6QDL_PAD_CSI0_DAT4__ECSPI1_SCLK           0x074 0x388 0x7d8 0x2 0x0
+#define MX6QDL_PAD_CSI0_DAT4__KEY_COL5              0x074 0x388 0x8c0 0x3 0x0
+#define MX6QDL_PAD_CSI0_DAT4__AUD3_TXC              0x074 0x388 0x000 0x4 0x0
+#define MX6QDL_PAD_CSI0_DAT4__GPIO5_IO22            0x074 0x388 0x000 0x5 0x0
+#define MX6QDL_PAD_CSI0_DAT4__ARM_TRACE01           0x074 0x388 0x000 0x7 0x0
+#define MX6QDL_PAD_CSI0_DAT5__IPU1_CSI0_DATA05      0x078 0x38c 0x000 0x0 0x0
+#define MX6QDL_PAD_CSI0_DAT5__EIM_DATA03            0x078 0x38c 0x000 0x1 0x0
+#define MX6QDL_PAD_CSI0_DAT5__ECSPI1_MOSI           0x078 0x38c 0x7e0 0x2 0x0
+#define MX6QDL_PAD_CSI0_DAT5__KEY_ROW5              0x078 0x38c 0x8cc 0x3 0x0
+#define MX6QDL_PAD_CSI0_DAT5__AUD3_TXD              0x078 0x38c 0x000 0x4 0x0
+#define MX6QDL_PAD_CSI0_DAT5__GPIO5_IO23            0x078 0x38c 0x000 0x5 0x0
+#define MX6QDL_PAD_CSI0_DAT5__ARM_TRACE02           0x078 0x38c 0x000 0x7 0x0
+#define MX6QDL_PAD_CSI0_DAT6__IPU1_CSI0_DATA06      0x07c 0x390 0x000 0x0 0x0
+#define MX6QDL_PAD_CSI0_DAT6__EIM_DATA04            0x07c 0x390 0x000 0x1 0x0
+#define MX6QDL_PAD_CSI0_DAT6__ECSPI1_MISO           0x07c 0x390 0x7dc 0x2 0x0
+#define MX6QDL_PAD_CSI0_DAT6__KEY_COL6              0x07c 0x390 0x8c4 0x3 0x0
+#define MX6QDL_PAD_CSI0_DAT6__AUD3_TXFS             0x07c 0x390 0x000 0x4 0x0
+#define MX6QDL_PAD_CSI0_DAT6__GPIO5_IO24            0x07c 0x390 0x000 0x5 0x0
+#define MX6QDL_PAD_CSI0_DAT6__ARM_TRACE03           0x07c 0x390 0x000 0x7 0x0
+#define MX6QDL_PAD_CSI0_DAT7__IPU1_CSI0_DATA07      0x080 0x394 0x000 0x0 0x0
+#define MX6QDL_PAD_CSI0_DAT7__EIM_DATA05            0x080 0x394 0x000 0x1 0x0
+#define MX6QDL_PAD_CSI0_DAT7__ECSPI1_SS0            0x080 0x394 0x7e4 0x2 0x0
+#define MX6QDL_PAD_CSI0_DAT7__KEY_ROW6              0x080 0x394 0x8d0 0x3 0x0
+#define MX6QDL_PAD_CSI0_DAT7__AUD3_RXD              0x080 0x394 0x000 0x4 0x0
+#define MX6QDL_PAD_CSI0_DAT7__GPIO5_IO25            0x080 0x394 0x000 0x5 0x0
+#define MX6QDL_PAD_CSI0_DAT7__ARM_TRACE04           0x080 0x394 0x000 0x7 0x0
+#define MX6QDL_PAD_CSI0_DAT8__IPU1_CSI0_DATA08      0x084 0x398 0x000 0x0 0x0
+#define MX6QDL_PAD_CSI0_DAT8__EIM_DATA06            0x084 0x398 0x000 0x1 0x0
+#define MX6QDL_PAD_CSI0_DAT8__ECSPI2_SCLK           0x084 0x398 0x7f4 0x2 0x0
+#define MX6QDL_PAD_CSI0_DAT8__KEY_COL7              0x084 0x398 0x8c8 0x3 0x0
+#define MX6QDL_PAD_CSI0_DAT8__I2C1_SDA              0x084 0x398 0x86c 0x4 0x0
+#define MX6QDL_PAD_CSI0_DAT8__GPIO5_IO26            0x084 0x398 0x000 0x5 0x0
+#define MX6QDL_PAD_CSI0_DAT8__ARM_TRACE05           0x084 0x398 0x000 0x7 0x0
+#define MX6QDL_PAD_CSI0_DAT9__IPU1_CSI0_DATA09      0x088 0x39c 0x000 0x0 0x0
+#define MX6QDL_PAD_CSI0_DAT9__EIM_DATA07            0x088 0x39c 0x000 0x1 0x0
+#define MX6QDL_PAD_CSI0_DAT9__ECSPI2_MOSI           0x088 0x39c 0x7fc 0x2 0x0
+#define MX6QDL_PAD_CSI0_DAT9__KEY_ROW7              0x088 0x39c 0x8d4 0x3 0x0
+#define MX6QDL_PAD_CSI0_DAT9__I2C1_SCL              0x088 0x39c 0x868 0x4 0x0
+#define MX6QDL_PAD_CSI0_DAT9__GPIO5_IO27            0x088 0x39c 0x000 0x5 0x0
+#define MX6QDL_PAD_CSI0_DAT9__ARM_TRACE06           0x088 0x39c 0x000 0x7 0x0
+#define MX6QDL_PAD_CSI0_DATA_EN__IPU1_CSI0_DATA_EN  0x08c 0x3a0 0x000 0x0 0x0
+#define MX6QDL_PAD_CSI0_DATA_EN__EIM_DATA00         0x08c 0x3a0 0x000 0x1 0x0
+#define MX6QDL_PAD_CSI0_DATA_EN__GPIO5_IO20         0x08c 0x3a0 0x000 0x5 0x0
+#define MX6QDL_PAD_CSI0_DATA_EN__ARM_TRACE_CLK      0x08c 0x3a0 0x000 0x7 0x0
+#define MX6QDL_PAD_CSI0_MCLK__IPU1_CSI0_HSYNC       0x090 0x3a4 0x000 0x0 0x0
+#define MX6QDL_PAD_CSI0_MCLK__CCM_CLKO1             0x090 0x3a4 0x000 0x3 0x0
+#define MX6QDL_PAD_CSI0_MCLK__GPIO5_IO19            0x090 0x3a4 0x000 0x5 0x0
+#define MX6QDL_PAD_CSI0_MCLK__ARM_TRACE_CTL         0x090 0x3a4 0x000 0x7 0x0
+#define MX6QDL_PAD_CSI0_PIXCLK__IPU1_CSI0_PIXCLK    0x094 0x3a8 0x000 0x0 0x0
+#define MX6QDL_PAD_CSI0_PIXCLK__GPIO5_IO18          0x094 0x3a8 0x000 0x5 0x0
+#define MX6QDL_PAD_CSI0_PIXCLK__ARM_EVENTO          0x094 0x3a8 0x000 0x7 0x0
+#define MX6QDL_PAD_CSI0_VSYNC__IPU1_CSI0_VSYNC      0x098 0x3ac 0x000 0x0 0x0
+#define MX6QDL_PAD_CSI0_VSYNC__EIM_DATA01           0x098 0x3ac 0x000 0x1 0x0
+#define MX6QDL_PAD_CSI0_VSYNC__GPIO5_IO21           0x098 0x3ac 0x000 0x5 0x0
+#define MX6QDL_PAD_CSI0_VSYNC__ARM_TRACE00          0x098 0x3ac 0x000 0x7 0x0
+#define MX6QDL_PAD_DI0_DISP_CLK__IPU1_DI0_DISP_CLK  0x09c 0x3b0 0x000 0x0 0x0
+#define MX6QDL_PAD_DI0_DISP_CLK__LCD_CLK            0x09c 0x3b0 0x000 0x1 0x0
+#define MX6QDL_PAD_DI0_DISP_CLK__GPIO4_IO16         0x09c 0x3b0 0x000 0x5 0x0
+#define MX6QDL_PAD_DI0_DISP_CLK__LCD_WR_RWN         0x09c 0x3b0 0x000 0x8 0x0
+#define MX6QDL_PAD_DI0_PIN15__IPU1_DI0_PIN15        0x0a0 0x3b4 0x000 0x0 0x0
+#define MX6QDL_PAD_DI0_PIN15__LCD_ENABLE            0x0a0 0x3b4 0x000 0x1 0x0
+#define MX6QDL_PAD_DI0_PIN15__AUD6_TXC              0x0a0 0x3b4 0x000 0x2 0x0
+#define MX6QDL_PAD_DI0_PIN15__GPIO4_IO17            0x0a0 0x3b4 0x000 0x5 0x0
+#define MX6QDL_PAD_DI0_PIN15__LCD_RD_E              0x0a0 0x3b4 0x000 0x8 0x0
+#define MX6QDL_PAD_DI0_PIN2__IPU1_DI0_PIN02         0x0a4 0x3b8 0x000 0x0 0x0
+#define MX6QDL_PAD_DI0_PIN2__LCD_HSYNC              0x0a4 0x3b8 0x8d8 0x1 0x0
+#define MX6QDL_PAD_DI0_PIN2__AUD6_TXD               0x0a4 0x3b8 0x000 0x2 0x0
+#define MX6QDL_PAD_DI0_PIN2__GPIO4_IO18             0x0a4 0x3b8 0x000 0x5 0x0
+#define MX6QDL_PAD_DI0_PIN2__LCD_RS                 0x0a4 0x3b8 0x000 0x8 0x0
+#define MX6QDL_PAD_DI0_PIN3__IPU1_DI0_PIN03         0x0a8 0x3bc 0x000 0x0 0x0
+#define MX6QDL_PAD_DI0_PIN3__LCD_VSYNC              0x0a8 0x3bc 0x000 0x1 0x0
+#define MX6QDL_PAD_DI0_PIN3__AUD6_TXFS              0x0a8 0x3bc 0x000 0x2 0x0
+#define MX6QDL_PAD_DI0_PIN3__GPIO4_IO19             0x0a8 0x3bc 0x000 0x5 0x0
+#define MX6QDL_PAD_DI0_PIN3__LCD_CS                 0x0a8 0x3bc 0x000 0x8 0x0
+#define MX6QDL_PAD_DI0_PIN4__IPU1_DI0_PIN04         0x0ac 0x3c0 0x000 0x0 0x0
+#define MX6QDL_PAD_DI0_PIN4__LCD_BUSY               0x0ac 0x3c0 0x8d8 0x1 0x1
+#define MX6QDL_PAD_DI0_PIN4__AUD6_RXD               0x0ac 0x3c0 0x000 0x2 0x0
+#define MX6QDL_PAD_DI0_PIN4__SD1_WP                 0x0ac 0x3c0 0x92c 0x3 0x0
+#define MX6QDL_PAD_DI0_PIN4__GPIO4_IO20             0x0ac 0x3c0 0x000 0x5 0x0
+#define MX6QDL_PAD_DI0_PIN4__LCD_RESET              0x0ac 0x3c0 0x000 0x8 0x0
+#define MX6QDL_PAD_DISP0_DAT0__IPU1_DISP0_DATA00    0x0b0 0x3c4 0x000 0x0 0x0
+#define MX6QDL_PAD_DISP0_DAT0__LCD_DATA00           0x0b0 0x3c4 0x000 0x1 0x0
+#define MX6QDL_PAD_DISP0_DAT0__ECSPI3_SCLK          0x0b0 0x3c4 0x000 0x2 0x0
+#define MX6QDL_PAD_DISP0_DAT0__GPIO4_IO21           0x0b0 0x3c4 0x000 0x5 0x0
+#define MX6QDL_PAD_DISP0_DAT1__IPU1_DISP0_DATA01    0x0b4 0x3c8 0x000 0x0 0x0
+#define MX6QDL_PAD_DISP0_DAT1__LCD_DATA01           0x0b4 0x3c8 0x000 0x1 0x0
+#define MX6QDL_PAD_DISP0_DAT1__ECSPI3_MOSI          0x0b4 0x3c8 0x000 0x2 0x0
+#define MX6QDL_PAD_DISP0_DAT1__GPIO4_IO22           0x0b4 0x3c8 0x000 0x5 0x0
+#define MX6QDL_PAD_DISP0_DAT10__IPU1_DISP0_DATA10   0x0b8 0x3cc 0x000 0x0 0x0
+#define MX6QDL_PAD_DISP0_DAT10__LCD_DATA10          0x0b8 0x3cc 0x000 0x1 0x0
+#define MX6QDL_PAD_DISP0_DAT10__GPIO4_IO31          0x0b8 0x3cc 0x000 0x5 0x0
+#define MX6QDL_PAD_DISP0_DAT11__IPU1_DISP0_DATA11   0x0bc 0x3d0 0x000 0x0 0x0
+#define MX6QDL_PAD_DISP0_DAT11__LCD_DATA11          0x0bc 0x3d0 0x000 0x1 0x0
+#define MX6QDL_PAD_DISP0_DAT11__GPIO5_IO05          0x0bc 0x3d0 0x000 0x5 0x0
+#define MX6QDL_PAD_DISP0_DAT12__IPU1_DISP0_DATA12   0x0c0 0x3d4 0x000 0x0 0x0
+#define MX6QDL_PAD_DISP0_DAT12__LCD_DATA12          0x0c0 0x3d4 0x000 0x1 0x0
+#define MX6QDL_PAD_DISP0_DAT12__GPIO5_IO06          0x0c0 0x3d4 0x000 0x5 0x0
+#define MX6QDL_PAD_DISP0_DAT13__IPU1_DISP0_DATA13   0x0c4 0x3d8 0x000 0x0 0x0
+#define MX6QDL_PAD_DISP0_DAT13__LCD_DATA13          0x0c4 0x3d8 0x000 0x1 0x0
+#define MX6QDL_PAD_DISP0_DAT13__AUD5_RXFS           0x0c4 0x3d8 0x7bc 0x3 0x0
+#define MX6QDL_PAD_DISP0_DAT13__GPIO5_IO07          0x0c4 0x3d8 0x000 0x5 0x0
+#define MX6QDL_PAD_DISP0_DAT14__IPU1_DISP0_DATA14   0x0c8 0x3dc 0x000 0x0 0x0
+#define MX6QDL_PAD_DISP0_DAT14__LCD_DATA14          0x0c8 0x3dc 0x000 0x1 0x0
+#define MX6QDL_PAD_DISP0_DAT14__AUD5_RXC            0x0c8 0x3dc 0x7b8 0x3 0x0
+#define MX6QDL_PAD_DISP0_DAT14__GPIO5_IO08          0x0c8 0x3dc 0x000 0x5 0x0
+#define MX6QDL_PAD_DISP0_DAT15__IPU1_DISP0_DATA15   0x0cc 0x3e0 0x000 0x0 0x0
+#define MX6QDL_PAD_DISP0_DAT15__LCD_DATA15          0x0cc 0x3e0 0x000 0x1 0x0
+#define MX6QDL_PAD_DISP0_DAT15__ECSPI1_SS1          0x0cc 0x3e0 0x7e8 0x2 0x0
+#define MX6QDL_PAD_DISP0_DAT15__ECSPI2_SS1          0x0cc 0x3e0 0x804 0x3 0x0
+#define MX6QDL_PAD_DISP0_DAT15__GPIO5_IO09          0x0cc 0x3e0 0x000 0x5 0x0
+#define MX6QDL_PAD_DISP0_DAT16__IPU1_DISP0_DATA16   0x0d0 0x3e4 0x000 0x0 0x0
+#define MX6QDL_PAD_DISP0_DAT16__LCD_DATA16          0x0d0 0x3e4 0x000 0x1 0x0
+#define MX6QDL_PAD_DISP0_DAT16__ECSPI2_MOSI         0x0d0 0x3e4 0x7fc 0x2 0x1
+#define MX6QDL_PAD_DISP0_DAT16__AUD5_TXC            0x0d0 0x3e4 0x7c0 0x3 0x0
+#define MX6QDL_PAD_DISP0_DAT16__SDMA_EXT_EVENT0     0x0d0 0x3e4 0x8e8 0x4 0x0
+#define MX6QDL_PAD_DISP0_DAT16__GPIO5_IO10          0x0d0 0x3e4 0x000 0x5 0x0
+#define MX6QDL_PAD_DISP0_DAT17__IPU1_DISP0_DATA17   0x0d4 0x3e8 0x000 0x0 0x0
+#define MX6QDL_PAD_DISP0_DAT17__LCD_DATA17          0x0d4 0x3e8 0x000 0x1 0x0
+#define MX6QDL_PAD_DISP0_DAT17__ECSPI2_MISO         0x0d4 0x3e8 0x7f8 0x2 0x1
+#define MX6QDL_PAD_DISP0_DAT17__AUD5_TXD            0x0d4 0x3e8 0x7b4 0x3 0x0
+#define MX6QDL_PAD_DISP0_DAT17__SDMA_EXT_EVENT1     0x0d4 0x3e8 0x8ec 0x4 0x0
+#define MX6QDL_PAD_DISP0_DAT17__GPIO5_IO11          0x0d4 0x3e8 0x000 0x5 0x0
+#define MX6QDL_PAD_DISP0_DAT18__IPU1_DISP0_DATA18   0x0d8 0x3ec 0x000 0x0 0x0
+#define MX6QDL_PAD_DISP0_DAT18__LCD_DATA18          0x0d8 0x3ec 0x000 0x1 0x0
+#define MX6QDL_PAD_DISP0_DAT18__ECSPI2_SS0          0x0d8 0x3ec 0x800 0x2 0x1
+#define MX6QDL_PAD_DISP0_DAT18__AUD5_TXFS           0x0d8 0x3ec 0x7c4 0x3 0x0
+#define MX6QDL_PAD_DISP0_DAT18__AUD4_RXFS           0x0d8 0x3ec 0x7a4 0x4 0x0
+#define MX6QDL_PAD_DISP0_DAT18__GPIO5_IO12          0x0d8 0x3ec 0x000 0x5 0x0
+#define MX6QDL_PAD_DISP0_DAT18__EIM_CS2_B           0x0d8 0x3ec 0x000 0x7 0x0
+#define MX6QDL_PAD_DISP0_DAT19__IPU1_DISP0_DATA19   0x0dc 0x3f0 0x000 0x0 0x0
+#define MX6QDL_PAD_DISP0_DAT19__LCD_DATA19          0x0dc 0x3f0 0x000 0x1 0x0
+#define MX6QDL_PAD_DISP0_DAT19__ECSPI2_SCLK         0x0dc 0x3f0 0x7f4 0x2 0x1
+#define MX6QDL_PAD_DISP0_DAT19__AUD5_RXD            0x0dc 0x3f0 0x7b0 0x3 0x0
+#define MX6QDL_PAD_DISP0_DAT19__AUD4_RXC            0x0dc 0x3f0 0x7a0 0x4 0x0
+#define MX6QDL_PAD_DISP0_DAT19__GPIO5_IO13          0x0dc 0x3f0 0x000 0x5 0x0
+#define MX6QDL_PAD_DISP0_DAT19__EIM_CS3_B           0x0dc 0x3f0 0x000 0x7 0x0
+#define MX6QDL_PAD_DISP0_DAT2__IPU1_DISP0_DATA02    0x0e0 0x3f4 0x000 0x0 0x0
+#define MX6QDL_PAD_DISP0_DAT2__LCD_DATA02           0x0e0 0x3f4 0x000 0x1 0x0
+#define MX6QDL_PAD_DISP0_DAT2__ECSPI3_MISO          0x0e0 0x3f4 0x000 0x2 0x0
+#define MX6QDL_PAD_DISP0_DAT2__GPIO4_IO23           0x0e0 0x3f4 0x000 0x5 0x0
+#define MX6QDL_PAD_DISP0_DAT20__IPU1_DISP0_DATA20   0x0e4 0x3f8 0x000 0x0 0x0
+#define MX6QDL_PAD_DISP0_DAT20__LCD_DATA20          0x0e4 0x3f8 0x000 0x1 0x0
+#define MX6QDL_PAD_DISP0_DAT20__ECSPI1_SCLK         0x0e4 0x3f8 0x7d8 0x2 0x1
+#define MX6QDL_PAD_DISP0_DAT20__AUD4_TXC            0x0e4 0x3f8 0x7a8 0x3 0x0
+#define MX6QDL_PAD_DISP0_DAT20__GPIO5_IO14          0x0e4 0x3f8 0x000 0x5 0x0
+#define MX6QDL_PAD_DISP0_DAT21__IPU1_DISP0_DATA21   0x0e8 0x3fc 0x000 0x0 0x0
+#define MX6QDL_PAD_DISP0_DAT21__LCD_DATA21          0x0e8 0x3fc 0x000 0x1 0x0
+#define MX6QDL_PAD_DISP0_DAT21__ECSPI1_MOSI         0x0e8 0x3fc 0x7e0 0x2 0x1
+#define MX6QDL_PAD_DISP0_DAT21__AUD4_TXD            0x0e8 0x3fc 0x79c 0x3 0x0
+#define MX6QDL_PAD_DISP0_DAT21__GPIO5_IO15          0x0e8 0x3fc 0x000 0x5 0x0
+#define MX6QDL_PAD_DISP0_DAT22__IPU1_DISP0_DATA22   0x0ec 0x400 0x000 0x0 0x0
+#define MX6QDL_PAD_DISP0_DAT22__LCD_DATA22          0x0ec 0x400 0x000 0x1 0x0
+#define MX6QDL_PAD_DISP0_DAT22__ECSPI1_MISO         0x0ec 0x400 0x7dc 0x2 0x1
+#define MX6QDL_PAD_DISP0_DAT22__AUD4_TXFS           0x0ec 0x400 0x7ac 0x3 0x0
+#define MX6QDL_PAD_DISP0_DAT22__GPIO5_IO16          0x0ec 0x400 0x000 0x5 0x0
+#define MX6QDL_PAD_DISP0_DAT23__IPU1_DISP0_DATA23   0x0f0 0x404 0x000 0x0 0x0
+#define MX6QDL_PAD_DISP0_DAT23__LCD_DATA23          0x0f0 0x404 0x000 0x1 0x0
+#define MX6QDL_PAD_DISP0_DAT23__ECSPI1_SS0          0x0f0 0x404 0x7e4 0x2 0x1
+#define MX6QDL_PAD_DISP0_DAT23__AUD4_RXD            0x0f0 0x404 0x798 0x3 0x0
+#define MX6QDL_PAD_DISP0_DAT23__GPIO5_IO17          0x0f0 0x404 0x000 0x5 0x0
+#define MX6QDL_PAD_DISP0_DAT3__IPU1_DISP0_DATA03    0x0f4 0x408 0x000 0x0 0x0
+#define MX6QDL_PAD_DISP0_DAT3__LCD_DATA03           0x0f4 0x408 0x000 0x1 0x0
+#define MX6QDL_PAD_DISP0_DAT3__ECSPI3_SS0           0x0f4 0x408 0x000 0x2 0x0
+#define MX6QDL_PAD_DISP0_DAT3__GPIO4_IO24           0x0f4 0x408 0x000 0x5 0x0
+#define MX6QDL_PAD_DISP0_DAT4__IPU1_DISP0_DATA04    0x0f8 0x40c 0x000 0x0 0x0
+#define MX6QDL_PAD_DISP0_DAT4__LCD_DATA04           0x0f8 0x40c 0x000 0x1 0x0
+#define MX6QDL_PAD_DISP0_DAT4__ECSPI3_SS1           0x0f8 0x40c 0x000 0x2 0x0
+#define MX6QDL_PAD_DISP0_DAT4__GPIO4_IO25           0x0f8 0x40c 0x000 0x5 0x0
+#define MX6QDL_PAD_DISP0_DAT5__IPU1_DISP0_DATA05    0x0fc 0x410 0x000 0x0 0x0
+#define MX6QDL_PAD_DISP0_DAT5__LCD_DATA05           0x0fc 0x410 0x000 0x1 0x0
+#define MX6QDL_PAD_DISP0_DAT5__ECSPI3_SS2           0x0fc 0x410 0x000 0x2 0x0
+#define MX6QDL_PAD_DISP0_DAT5__AUD6_RXFS            0x0fc 0x410 0x000 0x3 0x0
+#define MX6QDL_PAD_DISP0_DAT5__GPIO4_IO26           0x0fc 0x410 0x000 0x5 0x0
+#define MX6QDL_PAD_DISP0_DAT6__IPU1_DISP0_DATA06    0x100 0x414 0x000 0x0 0x0
+#define MX6QDL_PAD_DISP0_DAT6__LCD_DATA06           0x100 0x414 0x000 0x1 0x0
+#define MX6QDL_PAD_DISP0_DAT6__ECSPI3_SS3           0x100 0x414 0x000 0x2 0x0
+#define MX6QDL_PAD_DISP0_DAT6__AUD6_RXC             0x100 0x414 0x000 0x3 0x0
+#define MX6QDL_PAD_DISP0_DAT6__GPIO4_IO27           0x100 0x414 0x000 0x5 0x0
+#define MX6QDL_PAD_DISP0_DAT7__IPU1_DISP0_DATA07    0x104 0x418 0x000 0x0 0x0
+#define MX6QDL_PAD_DISP0_DAT7__LCD_DATA07           0x104 0x418 0x000 0x1 0x0
+#define MX6QDL_PAD_DISP0_DAT7__ECSPI3_RDY           0x104 0x418 0x000 0x2 0x0
+#define MX6QDL_PAD_DISP0_DAT7__GPIO4_IO28           0x104 0x418 0x000 0x5 0x0
+#define MX6QDL_PAD_DISP0_DAT8__IPU1_DISP0_DATA08    0x108 0x41c 0x000 0x0 0x0
+#define MX6QDL_PAD_DISP0_DAT8__LCD_DATA08           0x108 0x41c 0x000 0x1 0x0
+#define MX6QDL_PAD_DISP0_DAT8__PWM1_OUT             0x108 0x41c 0x000 0x2 0x0
+#define MX6QDL_PAD_DISP0_DAT8__WDOG1_B              0x108 0x41c 0x000 0x3 0x0
+#define MX6QDL_PAD_DISP0_DAT8__GPIO4_IO29           0x108 0x41c 0x000 0x5 0x0
+#define MX6QDL_PAD_DISP0_DAT9__IPU1_DISP0_DATA09    0x10c 0x420 0x000 0x0 0x0
+#define MX6QDL_PAD_DISP0_DAT9__LCD_DATA09           0x10c 0x420 0x000 0x1 0x0
+#define MX6QDL_PAD_DISP0_DAT9__PWM2_OUT             0x10c 0x420 0x000 0x2 0x0
+#define MX6QDL_PAD_DISP0_DAT9__WDOG2_B              0x10c 0x420 0x000 0x3 0x0
+#define MX6QDL_PAD_DISP0_DAT9__GPIO4_IO30           0x10c 0x420 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_A16__EIM_ADDR16              0x110 0x4e0 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_A16__IPU1_DI1_DISP_CLK       0x110 0x4e0 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_A16__IPU1_CSI1_PIXCLK        0x110 0x4e0 0x8b8 0x2 0x0
+#define MX6QDL_PAD_EIM_A16__GPIO2_IO22              0x110 0x4e0 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_A16__SRC_BOOT_CFG16          0x110 0x4e0 0x000 0x7 0x0
+#define MX6QDL_PAD_EIM_A16__EPDC_DATA00             0x110 0x4e0 0x000 0x8 0x0
+#define MX6QDL_PAD_EIM_A17__EIM_ADDR17              0x114 0x4e4 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_A17__IPU1_DISP1_DATA12       0x114 0x4e4 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_A17__IPU1_CSI1_DATA12        0x114 0x4e4 0x890 0x2 0x0
+#define MX6QDL_PAD_EIM_A17__GPIO2_IO21              0x114 0x4e4 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_A17__SRC_BOOT_CFG17          0x114 0x4e4 0x000 0x7 0x0
+#define MX6QDL_PAD_EIM_A17__EPDC_PWR_STAT           0x114 0x4e4 0x000 0x8 0x0
+#define MX6QDL_PAD_EIM_A18__EIM_ADDR18              0x118 0x4e8 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_A18__IPU1_DISP1_DATA13       0x118 0x4e8 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_A18__IPU1_CSI1_DATA13        0x118 0x4e8 0x894 0x2 0x0
+#define MX6QDL_PAD_EIM_A18__GPIO2_IO20              0x118 0x4e8 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_A18__SRC_BOOT_CFG18          0x118 0x4e8 0x000 0x7 0x0
+#define MX6QDL_PAD_EIM_A18__EPDC_PWR_CTRL0          0x118 0x4e8 0x000 0x8 0x0
+#define MX6QDL_PAD_EIM_A19__EIM_ADDR19              0x11c 0x4ec 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_A19__IPU1_DISP1_DATA14       0x11c 0x4ec 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_A19__IPU1_CSI1_DATA14        0x11c 0x4ec 0x898 0x2 0x0
+#define MX6QDL_PAD_EIM_A19__GPIO2_IO19              0x11c 0x4ec 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_A19__SRC_BOOT_CFG19          0x11c 0x4ec 0x000 0x7 0x0
+#define MX6QDL_PAD_EIM_A19__EPDC_PWR_CTRL1          0x11c 0x4ec 0x000 0x8 0x0
+#define MX6QDL_PAD_EIM_A20__EIM_ADDR20              0x120 0x4f0 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_A20__IPU1_DISP1_DATA15       0x120 0x4f0 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_A20__IPU1_CSI1_DATA15        0x120 0x4f0 0x89c 0x2 0x0
+#define MX6QDL_PAD_EIM_A20__GPIO2_IO18              0x120 0x4f0 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_A20__SRC_BOOT_CFG20          0x120 0x4f0 0x000 0x7 0x0
+#define MX6QDL_PAD_EIM_A20__EPDC_PWR_CTRL2          0x120 0x4f0 0x000 0x8 0x0
+#define MX6QDL_PAD_EIM_A21__EIM_ADDR21              0x124 0x4f4 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_A21__IPU1_DISP1_DATA16       0x124 0x4f4 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_A21__IPU1_CSI1_DATA16        0x124 0x4f4 0x8a0 0x2 0x0
+#define MX6QDL_PAD_EIM_A21__GPIO2_IO17              0x124 0x4f4 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_A21__SRC_BOOT_CFG21          0x124 0x4f4 0x000 0x7 0x0
+#define MX6QDL_PAD_EIM_A21__EPDC_GDCLK              0x124 0x4f4 0x000 0x8 0x0
+#define MX6QDL_PAD_EIM_A22__EIM_ADDR22              0x128 0x4f8 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_A22__IPU1_DISP1_DATA17       0x128 0x4f8 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_A22__IPU1_CSI1_DATA17        0x128 0x4f8 0x8a4 0x2 0x0
+#define MX6QDL_PAD_EIM_A22__GPIO2_IO16              0x128 0x4f8 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_A22__SRC_BOOT_CFG22          0x128 0x4f8 0x000 0x7 0x0
+#define MX6QDL_PAD_EIM_A22__EPDC_GDSP               0x128 0x4f8 0x000 0x8 0x0
+#define MX6QDL_PAD_EIM_A23__EIM_ADDR23              0x12c 0x4fc 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_A23__IPU1_DISP1_DATA18       0x12c 0x4fc 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_A23__IPU1_CSI1_DATA18        0x12c 0x4fc 0x8a8 0x2 0x0
+#define MX6QDL_PAD_EIM_A23__IPU1_SISG3              0x12c 0x4fc 0x000 0x4 0x0
+#define MX6QDL_PAD_EIM_A23__GPIO6_IO06              0x12c 0x4fc 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_A23__SRC_BOOT_CFG23          0x12c 0x4fc 0x000 0x7 0x0
+#define MX6QDL_PAD_EIM_A23__EPDC_GDOE               0x12c 0x4fc 0x000 0x8 0x0
+#define MX6QDL_PAD_EIM_A24__EIM_ADDR24              0x130 0x500 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_A24__IPU1_DISP1_DATA19       0x130 0x500 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_A24__IPU1_CSI1_DATA19        0x130 0x500 0x8ac 0x2 0x0
+#define MX6QDL_PAD_EIM_A24__IPU1_SISG2              0x130 0x500 0x000 0x4 0x0
+#define MX6QDL_PAD_EIM_A24__GPIO5_IO04              0x130 0x500 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_A24__SRC_BOOT_CFG24          0x130 0x500 0x000 0x7 0x0
+#define MX6QDL_PAD_EIM_A24__EPDC_GDRL               0x130 0x500 0x000 0x8 0x0
+#define MX6QDL_PAD_EIM_A25__EIM_ADDR25              0x134 0x504 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_A25__ECSPI4_SS1              0x134 0x504 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_A25__ECSPI2_RDY              0x134 0x504 0x000 0x2 0x0
+#define MX6QDL_PAD_EIM_A25__IPU1_DI1_PIN12          0x134 0x504 0x000 0x3 0x0
+#define MX6QDL_PAD_EIM_A25__IPU1_DI0_D1_CS          0x134 0x504 0x000 0x4 0x0
+#define MX6QDL_PAD_EIM_A25__GPIO5_IO02              0x134 0x504 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_A25__HDMI_TX_CEC_LINE        0x134 0x504 0x85c 0x6 0x0
+#define MX6QDL_PAD_EIM_A25__EPDC_DATA15             0x134 0x504 0x000 0x8 0x0
+#define MX6QDL_PAD_EIM_A25__EIM_ACLK_FREERUN        0x134 0x504 0x000 0x9 0x0
+#define MX6QDL_PAD_EIM_BCLK__EIM_BCLK               0x138 0x508 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_BCLK__IPU1_DI1_PIN16         0x138 0x508 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_BCLK__GPIO6_IO31             0x138 0x508 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_BCLK__EPDC_SDCE9             0x138 0x508 0x000 0x8 0x0
+#define MX6QDL_PAD_EIM_CS0__EIM_CS0_B               0x13c 0x50c 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_CS0__IPU1_DI1_PIN05          0x13c 0x50c 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_CS0__ECSPI2_SCLK             0x13c 0x50c 0x7f4 0x2 0x2
+#define MX6QDL_PAD_EIM_CS0__GPIO2_IO23              0x13c 0x50c 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_CS0__EPDC_DATA06             0x13c 0x50c 0x000 0x8 0x0
+#define MX6QDL_PAD_EIM_CS1__EIM_CS1_B               0x140 0x510 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_CS1__IPU1_DI1_PIN06          0x140 0x510 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_CS1__ECSPI2_MOSI             0x140 0x510 0x7fc 0x2 0x2
+#define MX6QDL_PAD_EIM_CS1__GPIO2_IO24              0x140 0x510 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_CS1__EPDC_DATA08             0x140 0x510 0x000 0x8 0x0
+#define MX6QDL_PAD_EIM_D16__EIM_DATA16              0x144 0x514 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_D16__ECSPI1_SCLK             0x144 0x514 0x7d8 0x1 0x2
+#define MX6QDL_PAD_EIM_D16__IPU1_DI0_PIN05          0x144 0x514 0x000 0x2 0x0
+#define MX6QDL_PAD_EIM_D16__IPU1_CSI1_DATA18        0x144 0x514 0x8a8 0x3 0x1
+#define MX6QDL_PAD_EIM_D16__HDMI_TX_DDC_SDA         0x144 0x514 0x864 0x4 0x0
+#define MX6QDL_PAD_EIM_D16__GPIO3_IO16              0x144 0x514 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_D16__I2C2_SDA                0x144 0x514 0x874 0x6 0x0
+#define MX6QDL_PAD_EIM_D16__EPDC_DATA10             0x144 0x514 0x000 0x8 0x0
+#define MX6QDL_PAD_EIM_D17__EIM_DATA17              0x148 0x518 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_D17__ECSPI1_MISO             0x148 0x518 0x7dc 0x1 0x2
+#define MX6QDL_PAD_EIM_D17__IPU1_DI0_PIN06          0x148 0x518 0x000 0x2 0x0
+#define MX6QDL_PAD_EIM_D17__IPU1_CSI1_PIXCLK        0x148 0x518 0x8b8 0x3 0x1
+#define MX6QDL_PAD_EIM_D17__DCIC1_OUT               0x148 0x518 0x000 0x4 0x0
+#define MX6QDL_PAD_EIM_D17__GPIO3_IO17              0x148 0x518 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_D17__I2C3_SCL                0x148 0x518 0x878 0x6 0x0
+#define MX6QDL_PAD_EIM_D17__EPDC_VCOM0              0x148 0x518 0x000 0x8 0x0
+#define MX6QDL_PAD_EIM_D18__EIM_DATA18              0x14c 0x51c 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_D18__ECSPI1_MOSI             0x14c 0x51c 0x7e0 0x1 0x2
+#define MX6QDL_PAD_EIM_D18__IPU1_DI0_PIN07          0x14c 0x51c 0x000 0x2 0x0
+#define MX6QDL_PAD_EIM_D18__IPU1_CSI1_DATA17        0x14c 0x51c 0x8a4 0x3 0x1
+#define MX6QDL_PAD_EIM_D18__IPU1_DI1_D0_CS          0x14c 0x51c 0x000 0x4 0x0
+#define MX6QDL_PAD_EIM_D18__GPIO3_IO18              0x14c 0x51c 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_D18__I2C3_SDA                0x14c 0x51c 0x87c 0x6 0x0
+#define MX6QDL_PAD_EIM_D18__EPDC_VCOM1              0x14c 0x51c 0x000 0x8 0x0
+#define MX6QDL_PAD_EIM_D19__EIM_DATA19              0x150 0x520 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_D19__ECSPI1_SS1              0x150 0x520 0x7e8 0x1 0x1
+#define MX6QDL_PAD_EIM_D19__IPU1_DI0_PIN08          0x150 0x520 0x000 0x2 0x0
+#define MX6QDL_PAD_EIM_D19__IPU1_CSI1_DATA16        0x150 0x520 0x8a0 0x3 0x1
+#define MX6QDL_PAD_EIM_D19__UART1_CTS_B             0x150 0x520 0x000 0x4 0x0
+#define MX6QDL_PAD_EIM_D19__UART1_RTS_B             0x150 0x520 0x8f8 0x4 0x0
+#define MX6QDL_PAD_EIM_D19__GPIO3_IO19              0x150 0x520 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_D19__EPIT1_OUT               0x150 0x520 0x000 0x6 0x0
+#define MX6QDL_PAD_EIM_D19__EPDC_DATA12             0x150 0x520 0x000 0x8 0x0
+#define MX6QDL_PAD_EIM_D20__EIM_DATA20              0x154 0x524 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_D20__ECSPI4_SS0              0x154 0x524 0x808 0x1 0x0
+#define MX6QDL_PAD_EIM_D20__IPU1_DI0_PIN16          0x154 0x524 0x000 0x2 0x0
+#define MX6QDL_PAD_EIM_D20__IPU1_CSI1_DATA15        0x154 0x524 0x89c 0x3 0x1
+#define MX6QDL_PAD_EIM_D20__UART1_RTS_B             0x154 0x524 0x8f8 0x4 0x1
+#define MX6QDL_PAD_EIM_D20__UART1_CTS_B             0x154 0x524 0x000 0x4 0x0
+#define MX6QDL_PAD_EIM_D20__GPIO3_IO20              0x154 0x524 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_D20__EPIT2_OUT               0x154 0x524 0x000 0x6 0x0
+#define MX6QDL_PAD_EIM_D21__EIM_DATA21              0x158 0x528 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_D21__ECSPI4_SCLK             0x158 0x528 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_D21__IPU1_DI0_PIN17          0x158 0x528 0x000 0x2 0x0
+#define MX6QDL_PAD_EIM_D21__IPU1_CSI1_DATA11        0x158 0x528 0x88c 0x3 0x0
+#define MX6QDL_PAD_EIM_D21__USB_OTG_OC              0x158 0x528 0x920 0x4 0x0
+#define MX6QDL_PAD_EIM_D21__GPIO3_IO21              0x158 0x528 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_D21__I2C1_SCL                0x158 0x528 0x868 0x6 0x1
+#define MX6QDL_PAD_EIM_D21__SPDIF_IN                0x158 0x528 0x8f0 0x7 0x0
+#define MX6QDL_PAD_EIM_D22__EIM_DATA22              0x15c 0x52c 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_D22__ECSPI4_MISO             0x15c 0x52c 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_D22__IPU1_DI0_PIN01          0x15c 0x52c 0x000 0x2 0x0
+#define MX6QDL_PAD_EIM_D22__IPU1_CSI1_DATA10        0x15c 0x52c 0x888 0x3 0x0
+#define MX6QDL_PAD_EIM_D22__USB_OTG_PWR             0x15c 0x52c 0x000 0x4 0x0
+#define MX6QDL_PAD_EIM_D22__GPIO3_IO22              0x15c 0x52c 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_D22__SPDIF_OUT               0x15c 0x52c 0x000 0x6 0x0
+#define MX6QDL_PAD_EIM_D22__EPDC_SDCE6              0x15c 0x52c 0x000 0x8 0x0
+#define MX6QDL_PAD_EIM_D23__EIM_DATA23              0x160 0x530 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_D23__IPU1_DI0_D0_CS          0x160 0x530 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_D23__UART3_CTS_B             0x160 0x530 0x000 0x2 0x0
+#define MX6QDL_PAD_EIM_D23__UART3_RTS_B             0x160 0x530 0x908 0x2 0x0
+#define MX6QDL_PAD_EIM_D23__UART1_DCD_B             0x160 0x530 0x000 0x3 0x0
+#define MX6QDL_PAD_EIM_D23__IPU1_CSI1_DATA_EN       0x160 0x530 0x8b0 0x4 0x0
+#define MX6QDL_PAD_EIM_D23__GPIO3_IO23              0x160 0x530 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_D23__IPU1_DI1_PIN02          0x160 0x530 0x000 0x6 0x0
+#define MX6QDL_PAD_EIM_D23__IPU1_DI1_PIN14          0x160 0x530 0x000 0x7 0x0
+#define MX6QDL_PAD_EIM_D23__EPDC_DATA11             0x160 0x530 0x000 0x8 0x0
+#define MX6QDL_PAD_EIM_D24__EIM_DATA24              0x164 0x534 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_D24__ECSPI4_SS2              0x164 0x534 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_D24__UART3_TX_DATA           0x164 0x534 0x000 0x2 0x0
+#define MX6QDL_PAD_EIM_D24__UART3_RX_DATA           0x164 0x534 0x90c 0x2 0x0
+#define MX6QDL_PAD_EIM_D24__ECSPI1_SS2              0x164 0x534 0x7ec 0x3 0x0
+#define MX6QDL_PAD_EIM_D24__ECSPI2_SS2              0x164 0x534 0x000 0x4 0x0
+#define MX6QDL_PAD_EIM_D24__GPIO3_IO24              0x164 0x534 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_D24__AUD5_RXFS               0x164 0x534 0x7bc 0x6 0x1
+#define MX6QDL_PAD_EIM_D24__UART1_DTR_B             0x164 0x534 0x000 0x7 0x0
+#define MX6QDL_PAD_EIM_D24__EPDC_SDCE7              0x164 0x534 0x000 0x8 0x0
+#define MX6QDL_PAD_EIM_D25__EIM_DATA25              0x168 0x538 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_D25__ECSPI4_SS3              0x168 0x538 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_D25__UART3_RX_DATA           0x168 0x538 0x90c 0x2 0x1
+#define MX6QDL_PAD_EIM_D25__UART3_TX_DATA           0x168 0x538 0x000 0x2 0x0
+#define MX6QDL_PAD_EIM_D25__ECSPI1_SS3              0x168 0x538 0x7f0 0x3 0x0
+#define MX6QDL_PAD_EIM_D25__ECSPI2_SS3              0x168 0x538 0x000 0x4 0x0
+#define MX6QDL_PAD_EIM_D25__GPIO3_IO25              0x168 0x538 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_D25__AUD5_RXC                0x168 0x538 0x7b8 0x6 0x1
+#define MX6QDL_PAD_EIM_D25__UART1_DSR_B             0x168 0x538 0x000 0x7 0x0
+#define MX6QDL_PAD_EIM_D25__EPDC_SDCE8              0x168 0x538 0x000 0x8 0x0
+#define MX6QDL_PAD_EIM_D26__EIM_DATA26              0x16c 0x53c 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_D26__IPU1_DI1_PIN11          0x16c 0x53c 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_D26__IPU1_CSI0_DATA01        0x16c 0x53c 0x000 0x2 0x0
+#define MX6QDL_PAD_EIM_D26__IPU1_CSI1_DATA14        0x16c 0x53c 0x898 0x3 0x1
+#define MX6QDL_PAD_EIM_D26__UART2_TX_DATA           0x16c 0x53c 0x000 0x4 0x0
+#define MX6QDL_PAD_EIM_D26__UART2_RX_DATA           0x16c 0x53c 0x904 0x4 0x0
+#define MX6QDL_PAD_EIM_D26__GPIO3_IO26              0x16c 0x53c 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_D26__IPU1_SISG2              0x16c 0x53c 0x000 0x6 0x0
+#define MX6QDL_PAD_EIM_D26__IPU1_DISP1_DATA22       0x16c 0x53c 0x000 0x7 0x0
+#define MX6QDL_PAD_EIM_D26__EPDC_SDOED              0x16c 0x53c 0x000 0x8 0x0
+#define MX6QDL_PAD_EIM_D27__EIM_DATA27              0x170 0x540 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_D27__IPU1_DI1_PIN13          0x170 0x540 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_D27__IPU1_CSI0_DATA00        0x170 0x540 0x000 0x2 0x0
+#define MX6QDL_PAD_EIM_D27__IPU1_CSI1_DATA13        0x170 0x540 0x894 0x3 0x1
+#define MX6QDL_PAD_EIM_D27__UART2_RX_DATA           0x170 0x540 0x904 0x4 0x1
+#define MX6QDL_PAD_EIM_D27__UART2_TX_DATA           0x170 0x540 0x000 0x4 0x0
+#define MX6QDL_PAD_EIM_D27__GPIO3_IO27              0x170 0x540 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_D27__IPU1_SISG3              0x170 0x540 0x000 0x6 0x0
+#define MX6QDL_PAD_EIM_D27__IPU1_DISP1_DATA23       0x170 0x540 0x000 0x7 0x0
+#define MX6QDL_PAD_EIM_D27__EPDC_SDOE               0x170 0x540 0x000 0x8 0x0
+#define MX6QDL_PAD_EIM_D28__EIM_DATA28              0x174 0x544 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_D28__I2C1_SDA                0x174 0x544 0x86c 0x1 0x1
+#define MX6QDL_PAD_EIM_D28__ECSPI4_MOSI             0x174 0x544 0x000 0x2 0x0
+#define MX6QDL_PAD_EIM_D28__IPU1_CSI1_DATA12        0x174 0x544 0x890 0x3 0x1
+#define MX6QDL_PAD_EIM_D28__UART2_CTS_B             0x174 0x544 0x000 0x4 0x0
+#define MX6QDL_PAD_EIM_D28__UART2_RTS_B             0x174 0x544 0x900 0x4 0x0
+#define MX6QDL_PAD_EIM_D28__UART2_DTE_CTS_B         0x174 0x544 0x900 0x4 0x0
+#define MX6QDL_PAD_EIM_D28__UART2_DTE_RTS_B         0x174 0x544 0x000 0x4 0x0
+#define MX6QDL_PAD_EIM_D28__GPIO3_IO28              0x174 0x544 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_D28__IPU1_EXT_TRIG           0x174 0x544 0x000 0x6 0x0
+#define MX6QDL_PAD_EIM_D28__IPU1_DI0_PIN13          0x174 0x544 0x000 0x7 0x0
+#define MX6QDL_PAD_EIM_D28__EPDC_PWR_CTRL3          0x174 0x544 0x000 0x8 0x0
+#define MX6QDL_PAD_EIM_D29__EIM_DATA29              0x178 0x548 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_D29__IPU1_DI1_PIN15          0x178 0x548 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_D29__ECSPI4_SS0              0x178 0x548 0x808 0x2 0x1
+#define MX6QDL_PAD_EIM_D29__UART2_RTS_B             0x178 0x548 0x900 0x4 0x1
+#define MX6QDL_PAD_EIM_D29__UART2_CTS_B             0x178 0x548 0x000 0x4 0x0
+#define MX6QDL_PAD_EIM_D29__UART2_DTE_RTS_B         0x178 0x548 0x000 0x4 0x0
+#define MX6QDL_PAD_EIM_D29__UART2_DTE_CTS_B         0x178 0x548 0x900 0x4 0x1
+#define MX6QDL_PAD_EIM_D29__GPIO3_IO29              0x178 0x548 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_D29__IPU1_CSI1_VSYNC         0x178 0x548 0x8bc 0x6 0x0
+#define MX6QDL_PAD_EIM_D29__IPU1_DI0_PIN14          0x178 0x548 0x000 0x7 0x0
+#define MX6QDL_PAD_EIM_D29__EPDC_PWR_WAKE           0x178 0x548 0x000 0x8 0x0
+#define MX6QDL_PAD_EIM_D30__EIM_DATA30              0x17c 0x54c 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_D30__IPU1_DISP1_DATA21       0x17c 0x54c 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_D30__IPU1_DI0_PIN11          0x17c 0x54c 0x000 0x2 0x0
+#define MX6QDL_PAD_EIM_D30__IPU1_CSI0_DATA03        0x17c 0x54c 0x000 0x3 0x0
+#define MX6QDL_PAD_EIM_D30__UART3_CTS_B             0x17c 0x54c 0x000 0x4 0x0
+#define MX6QDL_PAD_EIM_D30__UART3_RTS_B             0x17c 0x54c 0x908 0x4 0x1
+#define MX6QDL_PAD_EIM_D30__GPIO3_IO30              0x17c 0x54c 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_D30__USB_H1_OC               0x17c 0x54c 0x924 0x6 0x0
+#define MX6QDL_PAD_EIM_D30__EPDC_SDOEZ              0x17c 0x54c 0x000 0x8 0x0
+#define MX6QDL_PAD_EIM_D31__EIM_DATA31              0x180 0x550 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_D31__IPU1_DISP1_DATA20       0x180 0x550 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_D31__IPU1_DI0_PIN12          0x180 0x550 0x000 0x2 0x0
+#define MX6QDL_PAD_EIM_D31__IPU1_CSI0_DATA02        0x180 0x550 0x000 0x3 0x0
+#define MX6QDL_PAD_EIM_D31__UART3_RTS_B             0x180 0x550 0x908 0x4 0x2
+#define MX6QDL_PAD_EIM_D31__UART3_CTS_B             0x180 0x550 0x000 0x4 0x0
+#define MX6QDL_PAD_EIM_D31__GPIO3_IO31              0x180 0x550 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_D31__USB_H1_PWR              0x180 0x550 0x000 0x6 0x0
+#define MX6QDL_PAD_EIM_D31__EPDC_SDCLK_P            0x180 0x550 0x000 0x8 0x0
+#define MX6QDL_PAD_EIM_D31__EIM_ACLK_FREERUN        0x180 0x550 0x000 0x9 0x0
+#define MX6QDL_PAD_EIM_DA0__EIM_AD00                0x184 0x554 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_DA0__IPU1_DISP1_DATA09       0x184 0x554 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_DA0__IPU1_CSI1_DATA09        0x184 0x554 0x000 0x2 0x0
+#define MX6QDL_PAD_EIM_DA0__GPIO3_IO00              0x184 0x554 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_DA0__SRC_BOOT_CFG00          0x184 0x554 0x000 0x7 0x0
+#define MX6QDL_PAD_EIM_DA0__EPDC_SDCLK_N            0x184 0x554 0x000 0x8 0x0
+#define MX6QDL_PAD_EIM_DA1__EIM_AD01                0x188 0x558 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_DA1__IPU1_DISP1_DATA08       0x188 0x558 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_DA1__IPU1_CSI1_DATA08        0x188 0x558 0x000 0x2 0x0
+#define MX6QDL_PAD_EIM_DA1__GPIO3_IO01              0x188 0x558 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_DA1__SRC_BOOT_CFG01          0x188 0x558 0x000 0x7 0x0
+#define MX6QDL_PAD_EIM_DA1__EPDC_SDLE               0x188 0x558 0x000 0x8 0x0
+#define MX6QDL_PAD_EIM_DA10__EIM_AD10               0x18c 0x55c 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_DA10__IPU1_DI1_PIN15         0x18c 0x55c 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_DA10__IPU1_CSI1_DATA_EN      0x18c 0x55c 0x8b0 0x2 0x1
+#define MX6QDL_PAD_EIM_DA10__GPIO3_IO10             0x18c 0x55c 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_DA10__SRC_BOOT_CFG10         0x18c 0x55c 0x000 0x7 0x0
+#define MX6QDL_PAD_EIM_DA10__EPDC_DATA01            0x18c 0x55c 0x000 0x8 0x0
+#define MX6QDL_PAD_EIM_DA11__EIM_AD11               0x190 0x560 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_DA11__IPU1_DI1_PIN02         0x190 0x560 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_DA11__IPU1_CSI1_HSYNC        0x190 0x560 0x8b4 0x2 0x0
+#define MX6QDL_PAD_EIM_DA11__GPIO3_IO11             0x190 0x560 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_DA11__SRC_BOOT_CFG11         0x190 0x560 0x000 0x7 0x0
+#define MX6QDL_PAD_EIM_DA11__EPDC_DATA03            0x190 0x560 0x000 0x8 0x0
+#define MX6QDL_PAD_EIM_DA12__EIM_AD12               0x194 0x564 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_DA12__IPU1_DI1_PIN03         0x194 0x564 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_DA12__IPU1_CSI1_VSYNC        0x194 0x564 0x8bc 0x2 0x1
+#define MX6QDL_PAD_EIM_DA12__GPIO3_IO12             0x194 0x564 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_DA12__SRC_BOOT_CFG12         0x194 0x564 0x000 0x7 0x0
+#define MX6QDL_PAD_EIM_DA12__EPDC_DATA02            0x194 0x564 0x000 0x8 0x0
+#define MX6QDL_PAD_EIM_DA13__EIM_AD13               0x198 0x568 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_DA13__IPU1_DI1_D0_CS         0x198 0x568 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_DA13__GPIO3_IO13             0x198 0x568 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_DA13__SRC_BOOT_CFG13         0x198 0x568 0x000 0x7 0x0
+#define MX6QDL_PAD_EIM_DA13__EPDC_DATA13            0x198 0x568 0x000 0x8 0x0
+#define MX6QDL_PAD_EIM_DA14__EIM_AD14               0x19c 0x56c 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_DA14__IPU1_DI1_D1_CS         0x19c 0x56c 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_DA14__GPIO3_IO14             0x19c 0x56c 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_DA14__SRC_BOOT_CFG14         0x19c 0x56c 0x000 0x7 0x0
+#define MX6QDL_PAD_EIM_DA14__EPDC_DATA14            0x19c 0x56c 0x000 0x8 0x0
+#define MX6QDL_PAD_EIM_DA15__EIM_AD15               0x1a0 0x570 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_DA15__IPU1_DI1_PIN01         0x1a0 0x570 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_DA15__IPU1_DI1_PIN04         0x1a0 0x570 0x000 0x2 0x0
+#define MX6QDL_PAD_EIM_DA15__GPIO3_IO15             0x1a0 0x570 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_DA15__SRC_BOOT_CFG15         0x1a0 0x570 0x000 0x7 0x0
+#define MX6QDL_PAD_EIM_DA15__EPDC_DATA09            0x1a0 0x570 0x000 0x8 0x0
+#define MX6QDL_PAD_EIM_DA2__EIM_AD02                0x1a4 0x574 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_DA2__IPU1_DISP1_DATA07       0x1a4 0x574 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_DA2__IPU1_CSI1_DATA07        0x1a4 0x574 0x000 0x2 0x0
+#define MX6QDL_PAD_EIM_DA2__GPIO3_IO02              0x1a4 0x574 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_DA2__SRC_BOOT_CFG02          0x1a4 0x574 0x000 0x7 0x0
+#define MX6QDL_PAD_EIM_DA2__EPDC_BDR0               0x1a4 0x574 0x000 0x8 0x0
+#define MX6QDL_PAD_EIM_DA3__EIM_AD03                0x1a8 0x578 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_DA3__IPU1_DISP1_DATA06       0x1a8 0x578 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_DA3__IPU1_CSI1_DATA06        0x1a8 0x578 0x000 0x2 0x0
+#define MX6QDL_PAD_EIM_DA3__GPIO3_IO03              0x1a8 0x578 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_DA3__SRC_BOOT_CFG03          0x1a8 0x578 0x000 0x7 0x0
+#define MX6QDL_PAD_EIM_DA3__EPDC_BDR1               0x1a8 0x578 0x000 0x8 0x0
+#define MX6QDL_PAD_EIM_DA4__EIM_AD04                0x1ac 0x57c 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_DA4__IPU1_DISP1_DATA05       0x1ac 0x57c 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_DA4__IPU1_CSI1_DATA05        0x1ac 0x57c 0x000 0x2 0x0
+#define MX6QDL_PAD_EIM_DA4__GPIO3_IO04              0x1ac 0x57c 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_DA4__SRC_BOOT_CFG04          0x1ac 0x57c 0x000 0x7 0x0
+#define MX6QDL_PAD_EIM_DA4__EPDC_SDCE0              0x1ac 0x57c 0x000 0x8 0x0
+#define MX6QDL_PAD_EIM_DA5__EIM_AD05                0x1b0 0x580 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_DA5__IPU1_DISP1_DATA04       0x1b0 0x580 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_DA5__IPU1_CSI1_DATA04        0x1b0 0x580 0x000 0x2 0x0
+#define MX6QDL_PAD_EIM_DA5__GPIO3_IO05              0x1b0 0x580 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_DA5__SRC_BOOT_CFG05          0x1b0 0x580 0x000 0x7 0x0
+#define MX6QDL_PAD_EIM_DA5__EPDC_SDCE1              0x1b0 0x580 0x000 0x8 0x0
+#define MX6QDL_PAD_EIM_DA6__EIM_AD06                0x1b4 0x584 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_DA6__IPU1_DISP1_DATA03       0x1b4 0x584 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_DA6__IPU1_CSI1_DATA03        0x1b4 0x584 0x000 0x2 0x0
+#define MX6QDL_PAD_EIM_DA6__GPIO3_IO06              0x1b4 0x584 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_DA6__SRC_BOOT_CFG06          0x1b4 0x584 0x000 0x7 0x0
+#define MX6QDL_PAD_EIM_DA6__EPDC_SDCE2              0x1b4 0x584 0x000 0x8 0x0
+#define MX6QDL_PAD_EIM_DA7__EIM_AD07                0x1b8 0x588 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_DA7__IPU1_DISP1_DATA02       0x1b8 0x588 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_DA7__IPU1_CSI1_DATA02        0x1b8 0x588 0x000 0x2 0x0
+#define MX6QDL_PAD_EIM_DA7__GPIO3_IO07              0x1b8 0x588 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_DA7__SRC_BOOT_CFG07          0x1b8 0x588 0x000 0x7 0x0
+#define MX6QDL_PAD_EIM_DA7__EPDC_SDCE3              0x1b8 0x588 0x000 0x8 0x0
+#define MX6QDL_PAD_EIM_DA8__EIM_AD08                0x1bc 0x58c 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_DA8__IPU1_DISP1_DATA01       0x1bc 0x58c 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_DA8__IPU1_CSI1_DATA01        0x1bc 0x58c 0x000 0x2 0x0
+#define MX6QDL_PAD_EIM_DA8__GPIO3_IO08              0x1bc 0x58c 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_DA8__SRC_BOOT_CFG08          0x1bc 0x58c 0x000 0x7 0x0
+#define MX6QDL_PAD_EIM_DA8__EPDC_SDCE4              0x1bc 0x58c 0x000 0x8 0x0
+#define MX6QDL_PAD_EIM_DA9__EIM_AD09                0x1c0 0x590 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_DA9__IPU1_DISP1_DATA00       0x1c0 0x590 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_DA9__IPU1_CSI1_DATA00        0x1c0 0x590 0x000 0x2 0x0
+#define MX6QDL_PAD_EIM_DA9__GPIO3_IO09              0x1c0 0x590 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_DA9__SRC_BOOT_CFG09          0x1c0 0x590 0x000 0x7 0x0
+#define MX6QDL_PAD_EIM_DA9__EPDC_SDCE5              0x1c0 0x590 0x000 0x8 0x0
+#define MX6QDL_PAD_EIM_EB0__EIM_EB0_B               0x1c4 0x594 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_EB0__IPU1_DISP1_DATA11       0x1c4 0x594 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_EB0__IPU1_CSI1_DATA11        0x1c4 0x594 0x88c 0x2 0x1
+#define MX6QDL_PAD_EIM_EB0__CCM_PMIC_READY          0x1c4 0x594 0x7d4 0x4 0x0
+#define MX6QDL_PAD_EIM_EB0__GPIO2_IO28              0x1c4 0x594 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_EB0__SRC_BOOT_CFG27          0x1c4 0x594 0x000 0x7 0x0
+#define MX6QDL_PAD_EIM_EB0__EPDC_PWR_COM            0x1c4 0x594 0x000 0x8 0x0
+#define MX6QDL_PAD_EIM_EB1__EIM_EB1_B               0x1c8 0x598 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_EB1__IPU1_DISP1_DATA10       0x1c8 0x598 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_EB1__IPU1_CSI1_DATA10        0x1c8 0x598 0x888 0x2 0x1
+#define MX6QDL_PAD_EIM_EB1__GPIO2_IO29              0x1c8 0x598 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_EB1__SRC_BOOT_CFG28          0x1c8 0x598 0x000 0x7 0x0
+#define MX6QDL_PAD_EIM_EB1__EPDC_SDSHR              0x1c8 0x598 0x000 0x8 0x0
+#define MX6QDL_PAD_EIM_EB2__EIM_EB2_B               0x1cc 0x59c 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_EB2__ECSPI1_SS0              0x1cc 0x59c 0x7e4 0x1 0x2
+#define MX6QDL_PAD_EIM_EB2__IPU1_CSI1_DATA19        0x1cc 0x59c 0x8ac 0x3 0x1
+#define MX6QDL_PAD_EIM_EB2__HDMI_TX_DDC_SCL         0x1cc 0x59c 0x860 0x4 0x0
+#define MX6QDL_PAD_EIM_EB2__GPIO2_IO30              0x1cc 0x59c 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_EB2__I2C2_SCL                0x1cc 0x59c 0x870 0x6 0x0
+#define MX6QDL_PAD_EIM_EB2__SRC_BOOT_CFG30          0x1cc 0x59c 0x000 0x7 0x0
+#define MX6QDL_PAD_EIM_EB2__EPDC_DATA05             0x1cc 0x59c 0x000 0x8 0x0
+#define MX6QDL_PAD_EIM_EB3__EIM_EB3_B               0x1d0 0x5a0 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_EB3__ECSPI4_RDY              0x1d0 0x5a0 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_EB3__UART3_RTS_B             0x1d0 0x5a0 0x908 0x2 0x3
+#define MX6QDL_PAD_EIM_EB3__UART3_CTS_B             0x1d0 0x5a0 0x000 0x2 0x0
+#define MX6QDL_PAD_EIM_EB3__UART1_RI_B              0x1d0 0x5a0 0x000 0x3 0x0
+#define MX6QDL_PAD_EIM_EB3__IPU1_CSI1_HSYNC         0x1d0 0x5a0 0x8b4 0x4 0x1
+#define MX6QDL_PAD_EIM_EB3__GPIO2_IO31              0x1d0 0x5a0 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_EB3__IPU1_DI1_PIN03          0x1d0 0x5a0 0x000 0x6 0x0
+#define MX6QDL_PAD_EIM_EB3__SRC_BOOT_CFG31          0x1d0 0x5a0 0x000 0x7 0x0
+#define MX6QDL_PAD_EIM_EB3__EPDC_SDCE0              0x1d0 0x5a0 0x000 0x8 0x0
+#define MX6QDL_PAD_EIM_EB3__EIM_ACLK_FREERUN        0x1d0 0x5a0 0x000 0x9 0x0
+#define MX6QDL_PAD_EIM_LBA__EIM_LBA_B               0x1d4 0x5a4 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_LBA__IPU1_DI1_PIN17          0x1d4 0x5a4 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_LBA__ECSPI2_SS1              0x1d4 0x5a4 0x804 0x2 0x1
+#define MX6QDL_PAD_EIM_LBA__GPIO2_IO27              0x1d4 0x5a4 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_LBA__SRC_BOOT_CFG26          0x1d4 0x5a4 0x000 0x7 0x0
+#define MX6QDL_PAD_EIM_LBA__EPDC_DATA04             0x1d4 0x5a4 0x000 0x8 0x0
+#define MX6QDL_PAD_EIM_OE__EIM_OE_B                 0x1d8 0x5a8 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_OE__IPU1_DI1_PIN07           0x1d8 0x5a8 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_OE__ECSPI2_MISO              0x1d8 0x5a8 0x7f8 0x2 0x2
+#define MX6QDL_PAD_EIM_OE__GPIO2_IO25               0x1d8 0x5a8 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_OE__EPDC_PWR_IRQ             0x1d8 0x5a8 0x000 0x8 0x0
+#define MX6QDL_PAD_EIM_RW__EIM_RW                   0x1dc 0x5ac 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_RW__IPU1_DI1_PIN08           0x1dc 0x5ac 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_RW__ECSPI2_SS0               0x1dc 0x5ac 0x800 0x2 0x2
+#define MX6QDL_PAD_EIM_RW__GPIO2_IO26               0x1dc 0x5ac 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_RW__SRC_BOOT_CFG29           0x1dc 0x5ac 0x000 0x7 0x0
+#define MX6QDL_PAD_EIM_RW__EPDC_DATA07              0x1dc 0x5ac 0x000 0x8 0x0
+#define MX6QDL_PAD_EIM_WAIT__EIM_WAIT_B             0x1e0 0x5b0 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_WAIT__EIM_DTACK_B            0x1e0 0x5b0 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_WAIT__GPIO5_IO00             0x1e0 0x5b0 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_WAIT__SRC_BOOT_CFG25         0x1e0 0x5b0 0x000 0x7 0x0
+#define MX6QDL_PAD_ENET_CRS_DV__ENET_RX_EN          0x1e4 0x5b4 0x828 0x1 0x0
+#define MX6QDL_PAD_ENET_CRS_DV__ESAI_TX_CLK         0x1e4 0x5b4 0x840 0x2 0x0
+#define MX6QDL_PAD_ENET_CRS_DV__SPDIF_EXT_CLK       0x1e4 0x5b4 0x8f4 0x3 0x0
+#define MX6QDL_PAD_ENET_CRS_DV__GPIO1_IO25          0x1e4 0x5b4 0x000 0x5 0x0
+#define MX6QDL_PAD_ENET_MDC__MLB_DATA               0x1e8 0x5b8 0x8e0 0x0 0x0
+#define MX6QDL_PAD_ENET_MDC__ENET_MDC               0x1e8 0x5b8 0x000 0x1 0x0
+#define MX6QDL_PAD_ENET_MDC__ESAI_TX5_RX0           0x1e8 0x5b8 0x858 0x2 0x0
+#define MX6QDL_PAD_ENET_MDC__ENET_1588_EVENT1_IN    0x1e8 0x5b8 0x000 0x4 0x0
+#define MX6QDL_PAD_ENET_MDC__GPIO1_IO31             0x1e8 0x5b8 0x000 0x5 0x0
+#define MX6QDL_PAD_ENET_MDIO__ENET_MDIO             0x1ec 0x5bc 0x810 0x1 0x0
+#define MX6QDL_PAD_ENET_MDIO__ESAI_RX_CLK           0x1ec 0x5bc 0x83c 0x2 0x0
+#define MX6QDL_PAD_ENET_MDIO__ENET_1588_EVENT1_OUT  0x1ec 0x5bc 0x000 0x4 0x0
+#define MX6QDL_PAD_ENET_MDIO__GPIO1_IO22            0x1ec 0x5bc 0x000 0x5 0x0
+#define MX6QDL_PAD_ENET_MDIO__SPDIF_LOCK            0x1ec 0x5bc 0x000 0x6 0x0
+#define MX6QDL_PAD_ENET_REF_CLK__ENET_TX_CLK        0x1f0 0x5c0 0x000 0x1 0x0
+#define MX6QDL_PAD_ENET_REF_CLK__ESAI_RX_FS         0x1f0 0x5c0 0x82c 0x2 0x0
+#define MX6QDL_PAD_ENET_REF_CLK__GPIO1_IO23         0x1f0 0x5c0 0x000 0x5 0x0
+#define MX6QDL_PAD_ENET_REF_CLK__SPDIF_SR_CLK       0x1f0 0x5c0 0x000 0x6 0x0
+#define MX6QDL_PAD_ENET_RX_ER__USB_OTG_ID           0x1f4 0x5c4 0x790 0x0 0x0
+#define MX6QDL_PAD_ENET_RX_ER__ENET_RX_ER           0x1f4 0x5c4 0x000 0x1 0x0
+#define MX6QDL_PAD_ENET_RX_ER__ESAI_RX_HF_CLK       0x1f4 0x5c4 0x834 0x2 0x0
+#define MX6QDL_PAD_ENET_RX_ER__SPDIF_IN             0x1f4 0x5c4 0x8f0 0x3 0x1
+#define MX6QDL_PAD_ENET_RX_ER__ENET_1588_EVENT2_OUT 0x1f4 0x5c4 0x000 0x4 0x0
+#define MX6QDL_PAD_ENET_RX_ER__GPIO1_IO24           0x1f4 0x5c4 0x000 0x5 0x0
+#define MX6QDL_PAD_ENET_RXD0__ENET_RX_DATA0         0x1f8 0x5c8 0x818 0x1 0x0
+#define MX6QDL_PAD_ENET_RXD0__ESAI_TX_HF_CLK        0x1f8 0x5c8 0x838 0x2 0x0
+#define MX6QDL_PAD_ENET_RXD0__SPDIF_OUT             0x1f8 0x5c8 0x000 0x3 0x0
+#define MX6QDL_PAD_ENET_RXD0__GPIO1_IO27            0x1f8 0x5c8 0x000 0x5 0x0
+#define MX6QDL_PAD_ENET_RXD1__MLB_SIG               0x1fc 0x5cc 0x8e4 0x0 0x0
+#define MX6QDL_PAD_ENET_RXD1__ENET_RX_DATA1         0x1fc 0x5cc 0x81c 0x1 0x0
+#define MX6QDL_PAD_ENET_RXD1__ESAI_TX_FS            0x1fc 0x5cc 0x830 0x2 0x0
+#define MX6QDL_PAD_ENET_RXD1__ENET_1588_EVENT3_OUT  0x1fc 0x5cc 0x000 0x4 0x0
+#define MX6QDL_PAD_ENET_RXD1__GPIO1_IO26            0x1fc 0x5cc 0x000 0x5 0x0
+#define MX6QDL_PAD_ENET_TX_EN__ENET_TX_EN           0x200 0x5d0 0x000 0x1 0x0
+#define MX6QDL_PAD_ENET_TX_EN__ESAI_TX3_RX2         0x200 0x5d0 0x850 0x2 0x0
+#define MX6QDL_PAD_ENET_TX_EN__GPIO1_IO28           0x200 0x5d0 0x000 0x5 0x0
+#define MX6QDL_PAD_ENET_TX_EN__I2C4_SCL             0x200 0x5d0 0x880 0x9 0x0
+#define MX6QDL_PAD_ENET_TXD0__ENET_TX_DATA0         0x204 0x5d4 0x000 0x1 0x0
+#define MX6QDL_PAD_ENET_TXD0__ESAI_TX4_RX1          0x204 0x5d4 0x854 0x2 0x0
+#define MX6QDL_PAD_ENET_TXD0__GPIO1_IO30            0x204 0x5d4 0x000 0x5 0x0
+#define MX6QDL_PAD_ENET_TXD1__MLB_CLK               0x208 0x5d8 0x8dc 0x0 0x0
+#define MX6QDL_PAD_ENET_TXD1__ENET_TX_DATA1         0x208 0x5d8 0x000 0x1 0x0
+#define MX6QDL_PAD_ENET_TXD1__ESAI_TX2_RX3          0x208 0x5d8 0x84c 0x2 0x0
+#define MX6QDL_PAD_ENET_TXD1__ENET_1588_EVENT0_IN   0x208 0x5d8 0x000 0x4 0x0
+#define MX6QDL_PAD_ENET_TXD1__GPIO1_IO29            0x208 0x5d8 0x000 0x5 0x0
+#define MX6QDL_PAD_ENET_TXD1__I2C4_SDA              0x208 0x5d8 0x884 0x9 0x0
+#define MX6QDL_PAD_GPIO_0__CCM_CLKO1                0x20c 0x5dc 0x000 0x0 0x0
+#define MX6QDL_PAD_GPIO_0__KEY_COL5                 0x20c 0x5dc 0x8c0 0x2 0x1
+#define MX6QDL_PAD_GPIO_0__ASRC_EXT_CLK             0x20c 0x5dc 0x794 0x3 0x0
+#define MX6QDL_PAD_GPIO_0__EPIT1_OUT                0x20c 0x5dc 0x000 0x4 0x0
+#define MX6QDL_PAD_GPIO_0__GPIO1_IO00               0x20c 0x5dc 0x000 0x5 0x0
+#define MX6QDL_PAD_GPIO_0__USB_H1_PWR               0x20c 0x5dc 0x000 0x6 0x0
+#define MX6QDL_PAD_GPIO_0__SNVS_VIO_5               0x20c 0x5dc 0x000 0x7 0x0
+#define MX6QDL_PAD_GPIO_1__ESAI_RX_CLK              0x210 0x5e0 0x83c 0x0 0x1
+#define MX6QDL_PAD_GPIO_1__WDOG2_B                  0x210 0x5e0 0x000 0x1 0x0
+#define MX6QDL_PAD_GPIO_1__KEY_ROW5                 0x210 0x5e0 0x8cc 0x2 0x1
+#define MX6QDL_PAD_GPIO_1__USB_OTG_ID               0x210 0x5e0 0x790 0x3 0x1
+#define MX6QDL_PAD_GPIO_1__PWM2_OUT                 0x210 0x5e0 0x000 0x4 0x0
+#define MX6QDL_PAD_GPIO_1__GPIO1_IO01               0x210 0x5e0 0x000 0x5 0x0
+#define MX6QDL_PAD_GPIO_1__SD1_CD_B                 0x210 0x5e0 0x000 0x6 0x0
+#define MX6QDL_PAD_GPIO_16__ESAI_TX3_RX2            0x214 0x5e4 0x850 0x0 0x1
+#define MX6QDL_PAD_GPIO_16__ENET_1588_EVENT2_IN     0x214 0x5e4 0x000 0x1 0x0
+#define MX6QDL_PAD_GPIO_16__ENET_REF_CLK            0x214 0x5e4 0x80c 0x2 0x0
+#define MX6QDL_PAD_GPIO_16__SD1_LCTL                0x214 0x5e4 0x000 0x3 0x0
+#define MX6QDL_PAD_GPIO_16__SPDIF_IN                0x214 0x5e4 0x8f0 0x4 0x2
+#define MX6QDL_PAD_GPIO_16__GPIO7_IO11              0x214 0x5e4 0x000 0x5 0x0
+#define MX6QDL_PAD_GPIO_16__I2C3_SDA                0x214 0x5e4 0x87c 0x6 0x1
+#define MX6QDL_PAD_GPIO_16__JTAG_DE_B               0x214 0x5e4 0x000 0x7 0x0
+#define MX6QDL_PAD_GPIO_17__ESAI_TX0                0x218 0x5e8 0x844 0x0 0x0
+#define MX6QDL_PAD_GPIO_17__ENET_1588_EVENT3_IN     0x218 0x5e8 0x000 0x1 0x0
+#define MX6QDL_PAD_GPIO_17__CCM_PMIC_READY          0x218 0x5e8 0x7d4 0x2 0x1
+#define MX6QDL_PAD_GPIO_17__SDMA_EXT_EVENT0         0x218 0x5e8 0x8e8 0x3 0x1
+#define MX6QDL_PAD_GPIO_17__SPDIF_OUT               0x218 0x5e8 0x000 0x4 0x0
+#define MX6QDL_PAD_GPIO_17__GPIO7_IO12              0x218 0x5e8 0x000 0x5 0x0
+#define MX6QDL_PAD_GPIO_18__ESAI_TX1                0x21c 0x5ec 0x848 0x0 0x0
+#define MX6QDL_PAD_GPIO_18__ENET_RX_CLK             0x21c 0x5ec 0x814 0x1 0x0
+#define MX6QDL_PAD_GPIO_18__SD3_VSELECT             0x21c 0x5ec 0x000 0x2 0x0
+#define MX6QDL_PAD_GPIO_18__SDMA_EXT_EVENT1         0x21c 0x5ec 0x8ec 0x3 0x1
+#define MX6QDL_PAD_GPIO_18__ASRC_EXT_CLK            0x21c 0x5ec 0x794 0x4 0x1
+#define MX6QDL_PAD_GPIO_18__GPIO7_IO13              0x21c 0x5ec 0x000 0x5 0x0
+#define MX6QDL_PAD_GPIO_18__SNVS_VIO_5_CTL          0x21c 0x5ec 0x000 0x6 0x0
+#define MX6QDL_PAD_GPIO_19__KEY_COL5                0x220 0x5f0 0x8c0 0x0 0x2
+#define MX6QDL_PAD_GPIO_19__ENET_1588_EVENT0_OUT    0x220 0x5f0 0x000 0x1 0x0
+#define MX6QDL_PAD_GPIO_19__SPDIF_OUT               0x220 0x5f0 0x000 0x2 0x0
+#define MX6QDL_PAD_GPIO_19__CCM_CLKO1               0x220 0x5f0 0x000 0x3 0x0
+#define MX6QDL_PAD_GPIO_19__ECSPI1_RDY              0x220 0x5f0 0x000 0x4 0x0
+#define MX6QDL_PAD_GPIO_19__GPIO4_IO05              0x220 0x5f0 0x000 0x5 0x0
+#define MX6QDL_PAD_GPIO_19__ENET_TX_ER              0x220 0x5f0 0x000 0x6 0x0
+#define MX6QDL_PAD_GPIO_2__ESAI_TX_FS               0x224 0x5f4 0x830 0x0 0x1
+#define MX6QDL_PAD_GPIO_2__KEY_ROW6                 0x224 0x5f4 0x8d0 0x2 0x1
+#define MX6QDL_PAD_GPIO_2__GPIO1_IO02               0x224 0x5f4 0x000 0x5 0x0
+#define MX6QDL_PAD_GPIO_2__SD2_WP                   0x224 0x5f4 0x000 0x6 0x0
+#define MX6QDL_PAD_GPIO_2__MLB_DATA                 0x224 0x5f4 0x8e0 0x7 0x1
+#define MX6QDL_PAD_GPIO_3__ESAI_RX_HF_CLK           0x228 0x5f8 0x834 0x0 0x1
+#define MX6QDL_PAD_GPIO_3__I2C3_SCL                 0x228 0x5f8 0x878 0x2 0x1
+#define MX6QDL_PAD_GPIO_3__XTALOSC_REF_CLK_24M      0x228 0x5f8 0x000 0x3 0x0
+#define MX6QDL_PAD_GPIO_3__CCM_CLKO2                0x228 0x5f8 0x000 0x4 0x0
+#define MX6QDL_PAD_GPIO_3__GPIO1_IO03               0x228 0x5f8 0x000 0x5 0x0
+#define MX6QDL_PAD_GPIO_3__USB_H1_OC                0x228 0x5f8 0x924 0x6 0x1
+#define MX6QDL_PAD_GPIO_3__MLB_CLK                  0x228 0x5f8 0x8dc 0x7 0x1
+#define MX6QDL_PAD_GPIO_4__ESAI_TX_HF_CLK           0x22c 0x5fc 0x838 0x0 0x1
+#define MX6QDL_PAD_GPIO_4__KEY_COL7                 0x22c 0x5fc 0x8c8 0x2 0x1
+#define MX6QDL_PAD_GPIO_4__GPIO1_IO04               0x22c 0x5fc 0x000 0x5 0x0
+#define MX6QDL_PAD_GPIO_4__SD2_CD_B                 0x22c 0x5fc 0x000 0x6 0x0
+#define MX6QDL_PAD_GPIO_5__ESAI_TX2_RX3             0x230 0x600 0x84c 0x0 0x1
+#define MX6QDL_PAD_GPIO_5__KEY_ROW7                 0x230 0x600 0x8d4 0x2 0x1
+#define MX6QDL_PAD_GPIO_5__CCM_CLKO1                0x230 0x600 0x000 0x3 0x0
+#define MX6QDL_PAD_GPIO_5__GPIO1_IO05               0x230 0x600 0x000 0x5 0x0
+#define MX6QDL_PAD_GPIO_5__I2C3_SCL                 0x230 0x600 0x878 0x6 0x2
+#define MX6QDL_PAD_GPIO_5__ARM_EVENTI               0x230 0x600 0x000 0x7 0x0
+#define MX6QDL_PAD_GPIO_6__ESAI_TX_CLK              0x234 0x604 0x840 0x0 0x1
+#define MX6QDL_PAD_GPIO_6__I2C3_SDA                 0x234 0x604 0x87c 0x2 0x2
+#define MX6QDL_PAD_GPIO_6__GPIO1_IO06               0x234 0x604 0x000 0x5 0x0
+#define MX6QDL_PAD_GPIO_6__SD2_LCTL                 0x234 0x604 0x000 0x6 0x0
+#define MX6QDL_PAD_GPIO_6__MLB_SIG                  0x234 0x604 0x8e4 0x7 0x1
+#define MX6QDL_PAD_GPIO_7__ESAI_TX4_RX1             0x238 0x608 0x854 0x0 0x1
+#define MX6QDL_PAD_GPIO_7__EPIT1_OUT                0x238 0x608 0x000 0x2 0x0
+#define MX6QDL_PAD_GPIO_7__FLEXCAN1_TX              0x238 0x608 0x000 0x3 0x0
+#define MX6QDL_PAD_GPIO_7__UART2_TX_DATA            0x238 0x608 0x000 0x4 0x0
+#define MX6QDL_PAD_GPIO_7__UART2_RX_DATA            0x238 0x608 0x904 0x4 0x2
+#define MX6QDL_PAD_GPIO_7__GPIO1_IO07               0x238 0x608 0x000 0x5 0x0
+#define MX6QDL_PAD_GPIO_7__SPDIF_LOCK               0x238 0x608 0x000 0x6 0x0
+#define MX6QDL_PAD_GPIO_7__USB_OTG_HOST_MODE        0x238 0x608 0x000 0x7 0x0
+#define MX6QDL_PAD_GPIO_7__I2C4_SCL                 0x238 0x608 0x880 0x8 0x1
+#define MX6QDL_PAD_GPIO_8__ESAI_TX5_RX0             0x23c 0x60c 0x858 0x0 0x1
+#define MX6QDL_PAD_GPIO_8__XTALOSC_REF_CLK_32K      0x23c 0x60c 0x000 0x1 0x0
+#define MX6QDL_PAD_GPIO_8__EPIT2_OUT                0x23c 0x60c 0x000 0x2 0x0
+#define MX6QDL_PAD_GPIO_8__FLEXCAN1_RX              0x23c 0x60c 0x7c8 0x3 0x0
+#define MX6QDL_PAD_GPIO_8__UART2_RX_DATA            0x23c 0x60c 0x904 0x4 0x3
+#define MX6QDL_PAD_GPIO_8__UART2_TX_DATA            0x23c 0x60c 0x000 0x4 0x0
+#define MX6QDL_PAD_GPIO_8__GPIO1_IO08               0x23c 0x60c 0x000 0x5 0x0
+#define MX6QDL_PAD_GPIO_8__SPDIF_SR_CLK             0x23c 0x60c 0x000 0x6 0x0
+#define MX6QDL_PAD_GPIO_8__USB_OTG_PWR_CTL_WAKE     0x23c 0x60c 0x000 0x7 0x0
+#define MX6QDL_PAD_GPIO_8__I2C4_SDA                 0x23c 0x60c 0x884 0x8 0x1
+#define MX6QDL_PAD_GPIO_9__ESAI_RX_FS               0x240 0x610 0x82c 0x0 0x1
+#define MX6QDL_PAD_GPIO_9__WDOG1_B                  0x240 0x610 0x000 0x1 0x0
+#define MX6QDL_PAD_GPIO_9__KEY_COL6                 0x240 0x610 0x8c4 0x2 0x1
+#define MX6QDL_PAD_GPIO_9__CCM_REF_EN_B             0x240 0x610 0x000 0x3 0x0
+#define MX6QDL_PAD_GPIO_9__PWM1_OUT                 0x240 0x610 0x000 0x4 0x0
+#define MX6QDL_PAD_GPIO_9__GPIO1_IO09               0x240 0x610 0x000 0x5 0x0
+#define MX6QDL_PAD_GPIO_9__SD1_WP                   0x240 0x610 0x92c 0x6 0x1
+#define MX6QDL_PAD_KEY_COL0__ECSPI1_SCLK            0x244 0x62c 0x7d8 0x0 0x3
+#define MX6QDL_PAD_KEY_COL0__ENET_RX_DATA3          0x244 0x62c 0x824 0x1 0x0
+#define MX6QDL_PAD_KEY_COL0__AUD5_TXC               0x244 0x62c 0x7c0 0x2 0x1
+#define MX6QDL_PAD_KEY_COL0__KEY_COL0               0x244 0x62c 0x000 0x3 0x0
+#define MX6QDL_PAD_KEY_COL0__UART4_TX_DATA          0x244 0x62c 0x000 0x4 0x0
+#define MX6QDL_PAD_KEY_COL0__UART4_RX_DATA          0x244 0x62c 0x914 0x4 0x2
+#define MX6QDL_PAD_KEY_COL0__GPIO4_IO06             0x244 0x62c 0x000 0x5 0x0
+#define MX6QDL_PAD_KEY_COL0__DCIC1_OUT              0x244 0x62c 0x000 0x6 0x0
+#define MX6QDL_PAD_KEY_COL1__ECSPI1_MISO            0x248 0x630 0x7dc 0x0 0x3
+#define MX6QDL_PAD_KEY_COL1__ENET_MDIO              0x248 0x630 0x810 0x1 0x1
+#define MX6QDL_PAD_KEY_COL1__AUD5_TXFS              0x248 0x630 0x7c4 0x2 0x1
+#define MX6QDL_PAD_KEY_COL1__KEY_COL1               0x248 0x630 0x000 0x3 0x0
+#define MX6QDL_PAD_KEY_COL1__UART5_TX_DATA          0x248 0x630 0x000 0x4 0x0
+#define MX6QDL_PAD_KEY_COL1__UART5_RX_DATA          0x248 0x630 0x91c 0x4 0x2
+#define MX6QDL_PAD_KEY_COL1__GPIO4_IO08             0x248 0x630 0x000 0x5 0x0
+#define MX6QDL_PAD_KEY_COL1__SD1_VSELECT            0x248 0x630 0x000 0x6 0x0
+#define MX6QDL_PAD_KEY_COL2__ECSPI1_SS1             0x24c 0x634 0x7e8 0x0 0x2
+#define MX6QDL_PAD_KEY_COL2__ENET_RX_DATA2          0x24c 0x634 0x820 0x1 0x0
+#define MX6QDL_PAD_KEY_COL2__FLEXCAN1_TX            0x24c 0x634 0x000 0x2 0x0
+#define MX6QDL_PAD_KEY_COL2__KEY_COL2               0x24c 0x634 0x000 0x3 0x0
+#define MX6QDL_PAD_KEY_COL2__ENET_MDC               0x24c 0x634 0x000 0x4 0x0
+#define MX6QDL_PAD_KEY_COL2__GPIO4_IO10             0x24c 0x634 0x000 0x5 0x0
+#define MX6QDL_PAD_KEY_COL2__USB_H1_PWR_CTL_WAKE    0x24c 0x634 0x000 0x6 0x0
+#define MX6QDL_PAD_KEY_COL3__ECSPI1_SS3             0x250 0x638 0x7f0 0x0 0x1
+#define MX6QDL_PAD_KEY_COL3__ENET_CRS               0x250 0x638 0x000 0x1 0x0
+#define MX6QDL_PAD_KEY_COL3__HDMI_TX_DDC_SCL        0x250 0x638 0x860 0x2 0x1
+#define MX6QDL_PAD_KEY_COL3__KEY_COL3               0x250 0x638 0x000 0x3 0x0
+#define MX6QDL_PAD_KEY_COL3__I2C2_SCL               0x250 0x638 0x870 0x4 0x1
+#define MX6QDL_PAD_KEY_COL3__GPIO4_IO12             0x250 0x638 0x000 0x5 0x0
+#define MX6QDL_PAD_KEY_COL3__SPDIF_IN               0x250 0x638 0x8f0 0x6 0x3
+#define MX6QDL_PAD_KEY_COL4__FLEXCAN2_TX            0x254 0x63c 0x000 0x0 0x0
+#define MX6QDL_PAD_KEY_COL4__IPU1_SISG4             0x254 0x63c 0x000 0x1 0x0
+#define MX6QDL_PAD_KEY_COL4__USB_OTG_OC             0x254 0x63c 0x920 0x2 0x1
+#define MX6QDL_PAD_KEY_COL4__KEY_COL4               0x254 0x63c 0x000 0x3 0x0
+#define MX6QDL_PAD_KEY_COL4__UART5_RTS_B            0x254 0x63c 0x918 0x4 0x2
+#define MX6QDL_PAD_KEY_COL4__UART5_CTS_B            0x254 0x63c 0x000 0x4 0x0
+#define MX6QDL_PAD_KEY_COL4__GPIO4_IO14             0x254 0x63c 0x000 0x5 0x0
+#define MX6QDL_PAD_KEY_ROW0__ECSPI1_MOSI            0x258 0x640 0x7e0 0x0 0x3
+#define MX6QDL_PAD_KEY_ROW0__ENET_TX_DATA3          0x258 0x640 0x000 0x1 0x0
+#define MX6QDL_PAD_KEY_ROW0__AUD5_TXD               0x258 0x640 0x7b4 0x2 0x1
+#define MX6QDL_PAD_KEY_ROW0__KEY_ROW0               0x258 0x640 0x000 0x3 0x0
+#define MX6QDL_PAD_KEY_ROW0__UART4_RX_DATA          0x258 0x640 0x914 0x4 0x3
+#define MX6QDL_PAD_KEY_ROW0__UART4_TX_DATA          0x258 0x640 0x000 0x4 0x0
+#define MX6QDL_PAD_KEY_ROW0__GPIO4_IO07             0x258 0x640 0x000 0x5 0x0
+#define MX6QDL_PAD_KEY_ROW0__DCIC2_OUT              0x258 0x640 0x000 0x6 0x0
+#define MX6QDL_PAD_KEY_ROW1__ECSPI1_SS0             0x25c 0x644 0x7e4 0x0 0x3
+#define MX6QDL_PAD_KEY_ROW1__ENET_COL               0x25c 0x644 0x000 0x1 0x0
+#define MX6QDL_PAD_KEY_ROW1__AUD5_RXD               0x25c 0x644 0x7b0 0x2 0x1
+#define MX6QDL_PAD_KEY_ROW1__KEY_ROW1               0x25c 0x644 0x000 0x3 0x0
+#define MX6QDL_PAD_KEY_ROW1__UART5_RX_DATA          0x25c 0x644 0x91c 0x4 0x3
+#define MX6QDL_PAD_KEY_ROW1__UART5_TX_DATA          0x25c 0x644 0x000 0x4 0x0
+#define MX6QDL_PAD_KEY_ROW1__GPIO4_IO09             0x25c 0x644 0x000 0x5 0x0
+#define MX6QDL_PAD_KEY_ROW1__SD2_VSELECT            0x25c 0x644 0x000 0x6 0x0
+#define MX6QDL_PAD_KEY_ROW2__ECSPI1_SS2             0x260 0x648 0x7ec 0x0 0x1
+#define MX6QDL_PAD_KEY_ROW2__ENET_TX_DATA2          0x260 0x648 0x000 0x1 0x0
+#define MX6QDL_PAD_KEY_ROW2__FLEXCAN1_RX            0x260 0x648 0x7c8 0x2 0x1
+#define MX6QDL_PAD_KEY_ROW2__KEY_ROW2               0x260 0x648 0x000 0x3 0x0
+#define MX6QDL_PAD_KEY_ROW2__SD2_VSELECT            0x260 0x648 0x000 0x4 0x0
+#define MX6QDL_PAD_KEY_ROW2__GPIO4_IO11             0x260 0x648 0x000 0x5 0x0
+#define MX6QDL_PAD_KEY_ROW2__HDMI_TX_CEC_LINE       0x260 0x648 0x85c 0x6 0x1
+#define MX6QDL_PAD_KEY_ROW3__ASRC_EXT_CLK           0x264 0x64c 0x794 0x1 0x2
+#define MX6QDL_PAD_KEY_ROW3__HDMI_TX_DDC_SDA        0x264 0x64c 0x864 0x2 0x1
+#define MX6QDL_PAD_KEY_ROW3__KEY_ROW3               0x264 0x64c 0x000 0x3 0x0
+#define MX6QDL_PAD_KEY_ROW3__I2C2_SDA               0x264 0x64c 0x874 0x4 0x1
+#define MX6QDL_PAD_KEY_ROW3__GPIO4_IO13             0x264 0x64c 0x000 0x5 0x0
+#define MX6QDL_PAD_KEY_ROW3__SD1_VSELECT            0x264 0x64c 0x000 0x6 0x0
+#define MX6QDL_PAD_KEY_ROW4__FLEXCAN2_RX            0x268 0x650 0x7cc 0x0 0x0
+#define MX6QDL_PAD_KEY_ROW4__IPU1_SISG5             0x268 0x650 0x000 0x1 0x0
+#define MX6QDL_PAD_KEY_ROW4__USB_OTG_PWR            0x268 0x650 0x000 0x2 0x0
+#define MX6QDL_PAD_KEY_ROW4__KEY_ROW4               0x268 0x650 0x000 0x3 0x0
+#define MX6QDL_PAD_KEY_ROW4__UART5_CTS_B            0x268 0x650 0x000 0x4 0x0
+#define MX6QDL_PAD_KEY_ROW4__UART5_RTS_B            0x268 0x650 0x918 0x4 0x3
+#define MX6QDL_PAD_KEY_ROW4__GPIO4_IO15             0x268 0x650 0x000 0x5 0x0
+#define MX6QDL_PAD_NANDF_ALE__NAND_ALE              0x26c 0x654 0x000 0x0 0x0
+#define MX6QDL_PAD_NANDF_ALE__SD4_RESET             0x26c 0x654 0x000 0x1 0x0
+#define MX6QDL_PAD_NANDF_ALE__GPIO6_IO08            0x26c 0x654 0x000 0x5 0x0
+#define MX6QDL_PAD_NANDF_CLE__NAND_CLE              0x270 0x658 0x000 0x0 0x0
+#define MX6QDL_PAD_NANDF_CLE__GPIO6_IO07            0x270 0x658 0x000 0x5 0x0
+#define MX6QDL_PAD_NANDF_CS0__NAND_CE0_B            0x274 0x65c 0x000 0x0 0x0
+#define MX6QDL_PAD_NANDF_CS0__GPIO6_IO11            0x274 0x65c 0x000 0x5 0x0
+#define MX6QDL_PAD_NANDF_CS1__NAND_CE1_B            0x278 0x660 0x000 0x0 0x0
+#define MX6QDL_PAD_NANDF_CS1__SD4_VSELECT           0x278 0x660 0x000 0x1 0x0
+#define MX6QDL_PAD_NANDF_CS1__SD3_VSELECT           0x278 0x660 0x000 0x2 0x0
+#define MX6QDL_PAD_NANDF_CS1__GPIO6_IO14            0x278 0x660 0x000 0x5 0x0
+#define MX6QDL_PAD_NANDF_CS2__NAND_CE2_B            0x27c 0x664 0x000 0x0 0x0
+#define MX6QDL_PAD_NANDF_CS2__IPU1_SISG0            0x27c 0x664 0x000 0x1 0x0
+#define MX6QDL_PAD_NANDF_CS2__ESAI_TX0              0x27c 0x664 0x844 0x2 0x1
+#define MX6QDL_PAD_NANDF_CS2__EIM_CRE               0x27c 0x664 0x000 0x3 0x0
+#define MX6QDL_PAD_NANDF_CS2__CCM_CLKO2             0x27c 0x664 0x000 0x4 0x0
+#define MX6QDL_PAD_NANDF_CS2__GPIO6_IO15            0x27c 0x664 0x000 0x5 0x0
+#define MX6QDL_PAD_NANDF_CS3__NAND_CE3_B            0x280 0x668 0x000 0x0 0x0
+#define MX6QDL_PAD_NANDF_CS3__IPU1_SISG1            0x280 0x668 0x000 0x1 0x0
+#define MX6QDL_PAD_NANDF_CS3__ESAI_TX1              0x280 0x668 0x848 0x2 0x1
+#define MX6QDL_PAD_NANDF_CS3__EIM_ADDR26            0x280 0x668 0x000 0x3 0x0
+#define MX6QDL_PAD_NANDF_CS3__GPIO6_IO16            0x280 0x668 0x000 0x5 0x0
+#define MX6QDL_PAD_NANDF_CS3__I2C4_SDA              0x280 0x668 0x884 0x9 0x2
+#define MX6QDL_PAD_NANDF_D0__NAND_DATA00            0x284 0x66c 0x000 0x0 0x0
+#define MX6QDL_PAD_NANDF_D0__SD1_DATA4              0x284 0x66c 0x000 0x1 0x0
+#define MX6QDL_PAD_NANDF_D0__GPIO2_IO00             0x284 0x66c 0x000 0x5 0x0
+#define MX6QDL_PAD_NANDF_D1__NAND_DATA01            0x288 0x670 0x000 0x0 0x0
+#define MX6QDL_PAD_NANDF_D1__SD1_DATA5              0x288 0x670 0x000 0x1 0x0
+#define MX6QDL_PAD_NANDF_D1__GPIO2_IO01             0x288 0x670 0x000 0x5 0x0
+#define MX6QDL_PAD_NANDF_D2__NAND_DATA02            0x28c 0x674 0x000 0x0 0x0
+#define MX6QDL_PAD_NANDF_D2__SD1_DATA6              0x28c 0x674 0x000 0x1 0x0
+#define MX6QDL_PAD_NANDF_D2__GPIO2_IO02             0x28c 0x674 0x000 0x5 0x0
+#define MX6QDL_PAD_NANDF_D3__NAND_DATA03            0x290 0x678 0x000 0x0 0x0
+#define MX6QDL_PAD_NANDF_D3__SD1_DATA7              0x290 0x678 0x000 0x1 0x0
+#define MX6QDL_PAD_NANDF_D3__GPIO2_IO03             0x290 0x678 0x000 0x5 0x0
+#define MX6QDL_PAD_NANDF_D4__NAND_DATA04            0x294 0x67c 0x000 0x0 0x0
+#define MX6QDL_PAD_NANDF_D4__SD2_DATA4              0x294 0x67c 0x000 0x1 0x0
+#define MX6QDL_PAD_NANDF_D4__GPIO2_IO04             0x294 0x67c 0x000 0x5 0x0
+#define MX6QDL_PAD_NANDF_D5__NAND_DATA05            0x298 0x680 0x000 0x0 0x0
+#define MX6QDL_PAD_NANDF_D5__SD2_DATA5              0x298 0x680 0x000 0x1 0x0
+#define MX6QDL_PAD_NANDF_D5__GPIO2_IO05             0x298 0x680 0x000 0x5 0x0
+#define MX6QDL_PAD_NANDF_D6__NAND_DATA06            0x29c 0x684 0x000 0x0 0x0
+#define MX6QDL_PAD_NANDF_D6__SD2_DATA6              0x29c 0x684 0x000 0x1 0x0
+#define MX6QDL_PAD_NANDF_D6__GPIO2_IO06             0x29c 0x684 0x000 0x5 0x0
+#define MX6QDL_PAD_NANDF_D7__NAND_DATA07            0x2a0 0x688 0x000 0x0 0x0
+#define MX6QDL_PAD_NANDF_D7__SD2_DATA7              0x2a0 0x688 0x000 0x1 0x0
+#define MX6QDL_PAD_NANDF_D7__GPIO2_IO07             0x2a0 0x688 0x000 0x5 0x0
+#define MX6QDL_PAD_NANDF_RB0__NAND_READY_B          0x2a4 0x68c 0x000 0x0 0x0
+#define MX6QDL_PAD_NANDF_RB0__GPIO6_IO10            0x2a4 0x68c 0x000 0x5 0x0
+#define MX6QDL_PAD_NANDF_WP_B__NAND_WP_B            0x2a8 0x690 0x000 0x0 0x0
+#define MX6QDL_PAD_NANDF_WP_B__GPIO6_IO09           0x2a8 0x690 0x000 0x5 0x0
+#define MX6QDL_PAD_NANDF_WP_B__I2C4_SCL             0x2a8 0x690 0x880 0x9 0x2
+#define MX6QDL_PAD_RGMII_RD0__HSI_RX_READY          0x2ac 0x694 0x000 0x0 0x0
+#define MX6QDL_PAD_RGMII_RD0__RGMII_RD0             0x2ac 0x694 0x818 0x1 0x1
+#define MX6QDL_PAD_RGMII_RD0__GPIO6_IO25            0x2ac 0x694 0x000 0x5 0x0
+#define MX6QDL_PAD_RGMII_RD1__HSI_TX_FLAG           0x2b0 0x698 0x000 0x0 0x0
+#define MX6QDL_PAD_RGMII_RD1__RGMII_RD1             0x2b0 0x698 0x81c 0x1 0x1
+#define MX6QDL_PAD_RGMII_RD1__GPIO6_IO27            0x2b0 0x698 0x000 0x5 0x0
+#define MX6QDL_PAD_RGMII_RD2__HSI_TX_DATA           0x2b4 0x69c 0x000 0x0 0x0
+#define MX6QDL_PAD_RGMII_RD2__RGMII_RD2             0x2b4 0x69c 0x820 0x1 0x1
+#define MX6QDL_PAD_RGMII_RD2__GPIO6_IO28            0x2b4 0x69c 0x000 0x5 0x0
+#define MX6QDL_PAD_RGMII_RD3__HSI_TX_WAKE           0x2b8 0x6a0 0x000 0x0 0x0
+#define MX6QDL_PAD_RGMII_RD3__RGMII_RD3             0x2b8 0x6a0 0x824 0x1 0x1
+#define MX6QDL_PAD_RGMII_RD3__GPIO6_IO29            0x2b8 0x6a0 0x000 0x5 0x0
+#define MX6QDL_PAD_RGMII_RX_CTL__USB_H3_DATA        0x2bc 0x6a4 0x000 0x0 0x0
+#define MX6QDL_PAD_RGMII_RX_CTL__RGMII_RX_CTL       0x2bc 0x6a4 0x828 0x1 0x1
+#define MX6QDL_PAD_RGMII_RX_CTL__GPIO6_IO24         0x2bc 0x6a4 0x000 0x5 0x0
+#define MX6QDL_PAD_RGMII_RXC__USB_H3_STROBE         0x2c0 0x6a8 0x000 0x0 0x0
+#define MX6QDL_PAD_RGMII_RXC__RGMII_RXC             0x2c0 0x6a8 0x814 0x1 0x1
+#define MX6QDL_PAD_RGMII_RXC__GPIO6_IO30            0x2c0 0x6a8 0x000 0x5 0x0
+#define MX6QDL_PAD_RGMII_TD0__HSI_TX_READY          0x2c4 0x6ac 0x000 0x0 0x0
+#define MX6QDL_PAD_RGMII_TD0__RGMII_TD0             0x2c4 0x6ac 0x000 0x1 0x0
+#define MX6QDL_PAD_RGMII_TD0__GPIO6_IO20            0x2c4 0x6ac 0x000 0x5 0x0
+#define MX6QDL_PAD_RGMII_TD1__HSI_RX_FLAG           0x2c8 0x6b0 0x000 0x0 0x0
+#define MX6QDL_PAD_RGMII_TD1__RGMII_TD1             0x2c8 0x6b0 0x000 0x1 0x0
+#define MX6QDL_PAD_RGMII_TD1__GPIO6_IO21            0x2c8 0x6b0 0x000 0x5 0x0
+#define MX6QDL_PAD_RGMII_TD2__HSI_RX_DATA           0x2cc 0x6b4 0x000 0x0 0x0
+#define MX6QDL_PAD_RGMII_TD2__RGMII_TD2             0x2cc 0x6b4 0x000 0x1 0x0
+#define MX6QDL_PAD_RGMII_TD2__GPIO6_IO22            0x2cc 0x6b4 0x000 0x5 0x0
+#define MX6QDL_PAD_RGMII_TD3__HSI_RX_WAKE           0x2d0 0x6b8 0x000 0x0 0x0
+#define MX6QDL_PAD_RGMII_TD3__RGMII_TD3             0x2d0 0x6b8 0x000 0x1 0x0
+#define MX6QDL_PAD_RGMII_TD3__GPIO6_IO23            0x2d0 0x6b8 0x000 0x5 0x0
+#define MX6QDL_PAD_RGMII_TX_CTL__USB_H2_STROBE      0x2d4 0x6bc 0x000 0x0 0x0
+#define MX6QDL_PAD_RGMII_TX_CTL__RGMII_TX_CTL       0x2d4 0x6bc 0x000 0x1 0x0
+#define MX6QDL_PAD_RGMII_TX_CTL__GPIO6_IO26         0x2d4 0x6bc 0x000 0x5 0x0
+#define MX6QDL_PAD_RGMII_TX_CTL__ENET_REF_CLK       0x2d4 0x6bc 0x80c 0x7 0x1
+#define MX6QDL_PAD_RGMII_TXC__USB_H2_DATA           0x2d8 0x6c0 0x000 0x0 0x0
+#define MX6QDL_PAD_RGMII_TXC__RGMII_TXC             0x2d8 0x6c0 0x000 0x1 0x0
+#define MX6QDL_PAD_RGMII_TXC__SPDIF_EXT_CLK         0x2d8 0x6c0 0x8f4 0x2 0x1
+#define MX6QDL_PAD_RGMII_TXC__GPIO6_IO19            0x2d8 0x6c0 0x000 0x5 0x0
+#define MX6QDL_PAD_RGMII_TXC__XTALOSC_REF_CLK_24M   0x2d8 0x6c0 0x000 0x7 0x0
+#define MX6QDL_PAD_SD1_CLK__SD1_CLK                 0x2dc 0x6c4 0x928 0x0 0x1
+#define MX6QDL_PAD_SD1_CLK__GPT_CLKIN               0x2dc 0x6c4 0x000 0x3 0x0
+#define MX6QDL_PAD_SD1_CLK__GPIO1_IO20              0x2dc 0x6c4 0x000 0x5 0x0
+#define MX6QDL_PAD_SD1_CMD__SD1_CMD                 0x2e0 0x6c8 0x000 0x0 0x0
+#define MX6QDL_PAD_SD1_CMD__PWM4_OUT                0x2e0 0x6c8 0x000 0x2 0x0
+#define MX6QDL_PAD_SD1_CMD__GPT_COMPARE1            0x2e0 0x6c8 0x000 0x3 0x0
+#define MX6QDL_PAD_SD1_CMD__GPIO1_IO18              0x2e0 0x6c8 0x000 0x5 0x0
+#define MX6QDL_PAD_SD1_DAT0__SD1_DATA0              0x2e4 0x6cc 0x000 0x0 0x0
+#define MX6QDL_PAD_SD1_DAT0__GPT_CAPTURE1           0x2e4 0x6cc 0x000 0x3 0x0
+#define MX6QDL_PAD_SD1_DAT0__GPIO1_IO16             0x2e4 0x6cc 0x000 0x5 0x0
+#define MX6QDL_PAD_SD1_DAT1__SD1_DATA1              0x2e8 0x6d0 0x000 0x0 0x0
+#define MX6QDL_PAD_SD1_DAT1__PWM3_OUT               0x2e8 0x6d0 0x000 0x2 0x0
+#define MX6QDL_PAD_SD1_DAT1__GPT_CAPTURE2           0x2e8 0x6d0 0x000 0x3 0x0
+#define MX6QDL_PAD_SD1_DAT1__GPIO1_IO17             0x2e8 0x6d0 0x000 0x5 0x0
+#define MX6QDL_PAD_SD1_DAT2__SD1_DATA2              0x2ec 0x6d4 0x000 0x0 0x0
+#define MX6QDL_PAD_SD1_DAT2__GPT_COMPARE2           0x2ec 0x6d4 0x000 0x2 0x0
+#define MX6QDL_PAD_SD1_DAT2__PWM2_OUT               0x2ec 0x6d4 0x000 0x3 0x0
+#define MX6QDL_PAD_SD1_DAT2__WDOG1_B                0x2ec 0x6d4 0x000 0x4 0x0
+#define MX6QDL_PAD_SD1_DAT2__GPIO1_IO19             0x2ec 0x6d4 0x000 0x5 0x0
+#define MX6QDL_PAD_SD1_DAT2__WDOG1_RESET_B_DEB      0x2ec 0x6d4 0x000 0x6 0x0
+#define MX6QDL_PAD_SD1_DAT3__SD1_DATA3              0x2f0 0x6d8 0x000 0x0 0x0
+#define MX6QDL_PAD_SD1_DAT3__GPT_COMPARE3           0x2f0 0x6d8 0x000 0x2 0x0
+#define MX6QDL_PAD_SD1_DAT3__PWM1_OUT               0x2f0 0x6d8 0x000 0x3 0x0
+#define MX6QDL_PAD_SD1_DAT3__WDOG2_B                0x2f0 0x6d8 0x000 0x4 0x0
+#define MX6QDL_PAD_SD1_DAT3__GPIO1_IO21             0x2f0 0x6d8 0x000 0x5 0x0
+#define MX6QDL_PAD_SD1_DAT3__WDOG2_RESET_B_DEB      0x2f0 0x6d8 0x000 0x6 0x0
+#define MX6QDL_PAD_SD2_CLK__SD2_CLK                 0x2f4 0x6dc 0x930 0x0 0x1
+#define MX6QDL_PAD_SD2_CLK__KEY_COL5                0x2f4 0x6dc 0x8c0 0x2 0x3
+#define MX6QDL_PAD_SD2_CLK__AUD4_RXFS               0x2f4 0x6dc 0x7a4 0x3 0x1
+#define MX6QDL_PAD_SD2_CLK__GPIO1_IO10              0x2f4 0x6dc 0x000 0x5 0x0
+#define MX6QDL_PAD_SD2_CMD__SD2_CMD                 0x2f8 0x6e0 0x000 0x0 0x0
+#define MX6QDL_PAD_SD2_CMD__KEY_ROW5                0x2f8 0x6e0 0x8cc 0x2 0x2
+#define MX6QDL_PAD_SD2_CMD__AUD4_RXC                0x2f8 0x6e0 0x7a0 0x3 0x1
+#define MX6QDL_PAD_SD2_CMD__GPIO1_IO11              0x2f8 0x6e0 0x000 0x5 0x0
+#define MX6QDL_PAD_SD2_DAT0__SD2_DATA0              0x2fc 0x6e4 0x000 0x0 0x0
+#define MX6QDL_PAD_SD2_DAT0__AUD4_RXD               0x2fc 0x6e4 0x798 0x3 0x1
+#define MX6QDL_PAD_SD2_DAT0__KEY_ROW7               0x2fc 0x6e4 0x8d4 0x4 0x2
+#define MX6QDL_PAD_SD2_DAT0__GPIO1_IO15             0x2fc 0x6e4 0x000 0x5 0x0
+#define MX6QDL_PAD_SD2_DAT0__DCIC2_OUT              0x2fc 0x6e4 0x000 0x6 0x0
+#define MX6QDL_PAD_SD2_DAT1__SD2_DATA1              0x300 0x6e8 0x000 0x0 0x0
+#define MX6QDL_PAD_SD2_DAT1__EIM_CS2_B              0x300 0x6e8 0x000 0x2 0x0
+#define MX6QDL_PAD_SD2_DAT1__AUD4_TXFS              0x300 0x6e8 0x7ac 0x3 0x1
+#define MX6QDL_PAD_SD2_DAT1__KEY_COL7               0x300 0x6e8 0x8c8 0x4 0x2
+#define MX6QDL_PAD_SD2_DAT1__GPIO1_IO14             0x300 0x6e8 0x000 0x5 0x0
+#define MX6QDL_PAD_SD2_DAT2__SD2_DATA2              0x304 0x6ec 0x000 0x0 0x0
+#define MX6QDL_PAD_SD2_DAT2__EIM_CS3_B              0x304 0x6ec 0x000 0x2 0x0
+#define MX6QDL_PAD_SD2_DAT2__AUD4_TXD               0x304 0x6ec 0x79c 0x3 0x1
+#define MX6QDL_PAD_SD2_DAT2__KEY_ROW6               0x304 0x6ec 0x8d0 0x4 0x2
+#define MX6QDL_PAD_SD2_DAT2__GPIO1_IO13             0x304 0x6ec 0x000 0x5 0x0
+#define MX6QDL_PAD_SD2_DAT3__SD2_DATA3              0x308 0x6f0 0x000 0x0 0x0
+#define MX6QDL_PAD_SD2_DAT3__KEY_COL6               0x308 0x6f0 0x8c4 0x2 0x2
+#define MX6QDL_PAD_SD2_DAT3__AUD4_TXC               0x308 0x6f0 0x7a8 0x3 0x1
+#define MX6QDL_PAD_SD2_DAT3__GPIO1_IO12             0x308 0x6f0 0x000 0x5 0x0
+#define MX6QDL_PAD_SD3_CLK__SD3_CLK                 0x30c 0x6f4 0x934 0x0 0x1
+#define MX6QDL_PAD_SD3_CLK__UART2_RTS_B             0x30c 0x6f4 0x900 0x1 0x2
+#define MX6QDL_PAD_SD3_CLK__UART2_CTS_B             0x30c 0x6f4 0x000 0x1 0x0
+#define MX6QDL_PAD_SD3_CLK__FLEXCAN1_RX             0x30c 0x6f4 0x7c8 0x2 0x2
+#define MX6QDL_PAD_SD3_CLK__GPIO7_IO03              0x30c 0x6f4 0x000 0x5 0x0
+#define MX6QDL_PAD_SD3_CMD__SD3_CMD                 0x310 0x6f8 0x000 0x0 0x0
+#define MX6QDL_PAD_SD3_CMD__UART2_CTS_B             0x310 0x6f8 0x000 0x1 0x0
+#define MX6QDL_PAD_SD3_CMD__UART2_RTS_B             0x310 0x6f8 0x900 0x1 0x3
+#define MX6QDL_PAD_SD3_CMD__FLEXCAN1_TX             0x310 0x6f8 0x000 0x2 0x0
+#define MX6QDL_PAD_SD3_CMD__GPIO7_IO02              0x310 0x6f8 0x000 0x5 0x0
+#define MX6QDL_PAD_SD3_DAT0__SD3_DATA0              0x314 0x6fc 0x000 0x0 0x0
+#define MX6QDL_PAD_SD3_DAT0__UART1_CTS_B            0x314 0x6fc 0x000 0x1 0x0
+#define MX6QDL_PAD_SD3_DAT0__UART1_RTS_B            0x314 0x6fc 0x8f8 0x1 0x2
+#define MX6QDL_PAD_SD3_DAT0__FLEXCAN2_TX            0x314 0x6fc 0x000 0x2 0x0
+#define MX6QDL_PAD_SD3_DAT0__GPIO7_IO04             0x314 0x6fc 0x000 0x5 0x0
+#define MX6QDL_PAD_SD3_DAT1__SD3_DATA1              0x318 0x700 0x000 0x0 0x0
+#define MX6QDL_PAD_SD3_DAT1__UART1_RTS_B            0x318 0x700 0x8f8 0x1 0x3
+#define MX6QDL_PAD_SD3_DAT1__UART1_CTS_B            0x318 0x700 0x000 0x1 0x0
+#define MX6QDL_PAD_SD3_DAT1__FLEXCAN2_RX            0x318 0x700 0x7cc 0x2 0x1
+#define MX6QDL_PAD_SD3_DAT1__GPIO7_IO05             0x318 0x700 0x000 0x5 0x0
+#define MX6QDL_PAD_SD3_DAT2__SD3_DATA2              0x31c 0x704 0x000 0x0 0x0
+#define MX6QDL_PAD_SD3_DAT2__GPIO7_IO06             0x31c 0x704 0x000 0x5 0x0
+#define MX6QDL_PAD_SD3_DAT3__SD3_DATA3              0x320 0x708 0x000 0x0 0x0
+#define MX6QDL_PAD_SD3_DAT3__UART3_CTS_B            0x320 0x708 0x000 0x1 0x0
+#define MX6QDL_PAD_SD3_DAT3__UART3_RTS_B            0x320 0x708 0x908 0x1 0x4
+#define MX6QDL_PAD_SD3_DAT3__GPIO7_IO07             0x320 0x708 0x000 0x5 0x0
+#define MX6QDL_PAD_SD3_DAT4__SD3_DATA4              0x324 0x70c 0x000 0x0 0x0
+#define MX6QDL_PAD_SD3_DAT4__UART2_RX_DATA          0x324 0x70c 0x904 0x1 0x4
+#define MX6QDL_PAD_SD3_DAT4__UART2_TX_DATA          0x324 0x70c 0x000 0x1 0x0
+#define MX6QDL_PAD_SD3_DAT4__GPIO7_IO01             0x324 0x70c 0x000 0x5 0x0
+#define MX6QDL_PAD_SD3_DAT5__SD3_DATA5              0x328 0x710 0x000 0x0 0x0
+#define MX6QDL_PAD_SD3_DAT5__UART2_TX_DATA          0x328 0x710 0x000 0x1 0x0
+#define MX6QDL_PAD_SD3_DAT5__UART2_RX_DATA          0x328 0x710 0x904 0x1 0x5
+#define MX6QDL_PAD_SD3_DAT5__GPIO7_IO00             0x328 0x710 0x000 0x5 0x0
+#define MX6QDL_PAD_SD3_DAT6__SD3_DATA6              0x32c 0x714 0x000 0x0 0x0
+#define MX6QDL_PAD_SD3_DAT6__UART1_RX_DATA          0x32c 0x714 0x8fc 0x1 0x2
+#define MX6QDL_PAD_SD3_DAT6__UART1_TX_DATA          0x32c 0x714 0x000 0x1 0x0
+#define MX6QDL_PAD_SD3_DAT6__GPIO6_IO18             0x32c 0x714 0x000 0x5 0x0
+#define MX6QDL_PAD_SD3_DAT7__SD3_DATA7              0x330 0x718 0x000 0x0 0x0
+#define MX6QDL_PAD_SD3_DAT7__UART1_TX_DATA          0x330 0x718 0x000 0x1 0x0
+#define MX6QDL_PAD_SD3_DAT7__UART1_RX_DATA          0x330 0x718 0x8fc 0x1 0x3
+#define MX6QDL_PAD_SD3_DAT7__GPIO6_IO17             0x330 0x718 0x000 0x5 0x0
+#define MX6QDL_PAD_SD3_RST__SD3_RESET               0x334 0x71c 0x000 0x0 0x0
+#define MX6QDL_PAD_SD3_RST__UART3_RTS_B             0x334 0x71c 0x908 0x1 0x5
+#define MX6QDL_PAD_SD3_RST__UART3_CTS_B             0x334 0x71c 0x000 0x1 0x0
+#define MX6QDL_PAD_SD3_RST__GPIO7_IO08              0x334 0x71c 0x000 0x5 0x0
+#define MX6QDL_PAD_SD4_CLK__SD4_CLK                 0x338 0x720 0x938 0x0 0x1
+#define MX6QDL_PAD_SD4_CLK__NAND_WE_B               0x338 0x720 0x000 0x1 0x0
+#define MX6QDL_PAD_SD4_CLK__UART3_RX_DATA           0x338 0x720 0x90c 0x2 0x2
+#define MX6QDL_PAD_SD4_CLK__UART3_TX_DATA           0x338 0x720 0x000 0x2 0x0
+#define MX6QDL_PAD_SD4_CLK__GPIO7_IO10              0x338 0x720 0x000 0x5 0x0
+#define MX6QDL_PAD_SD4_CMD__SD4_CMD                 0x33c 0x724 0x000 0x0 0x0
+#define MX6QDL_PAD_SD4_CMD__NAND_RE_B               0x33c 0x724 0x000 0x1 0x0
+#define MX6QDL_PAD_SD4_CMD__UART3_TX_DATA           0x33c 0x724 0x000 0x2 0x0
+#define MX6QDL_PAD_SD4_CMD__UART3_RX_DATA           0x33c 0x724 0x90c 0x2 0x3
+#define MX6QDL_PAD_SD4_CMD__GPIO7_IO09              0x33c 0x724 0x000 0x5 0x0
+#define MX6QDL_PAD_SD4_DAT0__SD4_DATA0              0x340 0x728 0x000 0x1 0x0
+#define MX6QDL_PAD_SD4_DAT0__NAND_DQS               0x340 0x728 0x000 0x2 0x0
+#define MX6QDL_PAD_SD4_DAT0__GPIO2_IO08             0x340 0x728 0x000 0x5 0x0
+#define MX6QDL_PAD_SD4_DAT1__SD4_DATA1              0x344 0x72c 0x000 0x1 0x0
+#define MX6QDL_PAD_SD4_DAT1__PWM3_OUT               0x344 0x72c 0x000 0x2 0x0
+#define MX6QDL_PAD_SD4_DAT1__GPIO2_IO09             0x344 0x72c 0x000 0x5 0x0
+#define MX6QDL_PAD_SD4_DAT2__SD4_DATA2              0x348 0x730 0x000 0x1 0x0
+#define MX6QDL_PAD_SD4_DAT2__PWM4_OUT               0x348 0x730 0x000 0x2 0x0
+#define MX6QDL_PAD_SD4_DAT2__GPIO2_IO10             0x348 0x730 0x000 0x5 0x0
+#define MX6QDL_PAD_SD4_DAT3__SD4_DATA3              0x34c 0x734 0x000 0x1 0x0
+#define MX6QDL_PAD_SD4_DAT3__GPIO2_IO11             0x34c 0x734 0x000 0x5 0x0
+#define MX6QDL_PAD_SD4_DAT4__SD4_DATA4              0x350 0x738 0x000 0x1 0x0
+#define MX6QDL_PAD_SD4_DAT4__UART2_RX_DATA          0x350 0x738 0x904 0x2 0x6
+#define MX6QDL_PAD_SD4_DAT4__UART2_TX_DATA          0x350 0x738 0x000 0x2 0x0
+#define MX6QDL_PAD_SD4_DAT4__GPIO2_IO12             0x350 0x738 0x000 0x5 0x0
+#define MX6QDL_PAD_SD4_DAT5__SD4_DATA5              0x354 0x73c 0x000 0x1 0x0
+#define MX6QDL_PAD_SD4_DAT5__UART2_RTS_B            0x354 0x73c 0x900 0x2 0x4
+#define MX6QDL_PAD_SD4_DAT5__UART2_CTS_B            0x354 0x73c 0x000 0x2 0x0
+#define MX6QDL_PAD_SD4_DAT5__GPIO2_IO13             0x354 0x73c 0x000 0x5 0x0
+#define MX6QDL_PAD_SD4_DAT6__SD4_DATA6              0x358 0x740 0x000 0x1 0x0
+#define MX6QDL_PAD_SD4_DAT6__UART2_CTS_B            0x358 0x740 0x000 0x2 0x0
+#define MX6QDL_PAD_SD4_DAT6__UART2_RTS_B            0x358 0x740 0x900 0x2 0x5
+#define MX6QDL_PAD_SD4_DAT6__GPIO2_IO14             0x358 0x740 0x000 0x5 0x0
+#define MX6QDL_PAD_SD4_DAT7__SD4_DATA7              0x35c 0x744 0x000 0x1 0x0
+#define MX6QDL_PAD_SD4_DAT7__UART2_TX_DATA          0x35c 0x744 0x000 0x2 0x0
+#define MX6QDL_PAD_SD4_DAT7__UART2_RX_DATA          0x35c 0x744 0x904 0x2 0x7
+#define MX6QDL_PAD_SD4_DAT7__GPIO2_IO15             0x35c 0x744 0x000 0x5 0x0
 
 #endif /* __DTS_IMX6DL_PINFUNC_H */
diff --git a/arch/arm/boot/dts/imx6dl-sabreauto.dts b/arch/arm/boot/dts/imx6dl-sabreauto.dts
index 95da71185a4a..a6ce7b487ad7 100644
--- a/arch/arm/boot/dts/imx6dl-sabreauto.dts
+++ b/arch/arm/boot/dts/imx6dl-sabreauto.dts
@@ -15,25 +15,3 @@
 	model = "Freescale i.MX6 DualLite/Solo SABRE Automotive Board";
 	compatible = "fsl,imx6dl-sabreauto", "fsl,imx6dl";
 };
-
-&iomuxc {
-	pinctrl-names = "default";
-	pinctrl-0 = <&pinctrl_hog>;
-
-	hog {
-		pinctrl_hog: hoggrp {
-			fsl,pins = <
-				MX6DL_PAD_NANDF_CS2__GPIO6_IO15 0x80000000
-				MX6DL_PAD_SD2_DAT2__GPIO1_IO13  0x80000000
-			>;
-		};
-	};
-
-	ecspi1 {
-		pinctrl_ecspi1_sabreauto: ecspi1-sabreauto {
-			fsl,pins = <
-				MX6DL_PAD_EIM_D19__GPIO3_IO19  0x80000000
-			>;
-		};
-	};
-};
diff --git a/arch/arm/boot/dts/imx6dl-sabresd.dts b/arch/arm/boot/dts/imx6dl-sabresd.dts
index 8989df2b89e5..1e45f2f9d0b6 100644
--- a/arch/arm/boot/dts/imx6dl-sabresd.dts
+++ b/arch/arm/boot/dts/imx6dl-sabresd.dts
@@ -15,22 +15,3 @@
 	model = "Freescale i.MX6 DualLite SABRE Smart Device Board";
 	compatible = "fsl,imx6dl-sabresd", "fsl,imx6dl";
 };
-
-&iomuxc {
-	pinctrl-names = "default";
-	pinctrl-0 = <&pinctrl_hog>;
-
-	hog {
-		pinctrl_hog: hoggrp {
-			fsl,pins = <
-				MX6DL_PAD_GPIO_4__GPIO1_IO04   0x80000000
-				MX6DL_PAD_GPIO_5__GPIO1_IO05   0x80000000
-				MX6DL_PAD_NANDF_D0__GPIO2_IO00 0x80000000
-				MX6DL_PAD_NANDF_D1__GPIO2_IO01 0x80000000
-				MX6DL_PAD_NANDF_D2__GPIO2_IO02 0x80000000
-				MX6DL_PAD_NANDF_D3__GPIO2_IO03 0x80000000
-				MX6DL_PAD_GPIO_0__CCM_CLKO1    0x130b0
-			>;
-		};
-	};
-};
diff --git a/arch/arm/boot/dts/imx6dl-wandboard.dts b/arch/arm/boot/dts/imx6dl-wandboard.dts
index bfc59c3566a4..e672891c1626 100644
--- a/arch/arm/boot/dts/imx6dl-wandboard.dts
+++ b/arch/arm/boot/dts/imx6dl-wandboard.dts
@@ -10,6 +10,7 @@
  */
 /dts-v1/;
 #include "imx6dl.dtsi"
+#include "imx6qdl-wandboard.dtsi"
 
 / {
 	model = "Wandboard i.MX6 Dual Lite Board";
@@ -19,26 +20,3 @@
 		reg = <0x10000000 0x40000000>;
 	};
 };
-
-&fec {
-	pinctrl-names = "default";
-	pinctrl-0 = <&pinctrl_enet_1>;
-	phy-mode = "rgmii";
-	status = "okay";
-};
-
-&uart1 {
-	pinctrl-names = "default";
-	pinctrl-0 = <&pinctrl_uart1_1>;
-	status = "okay";
-};
-
-&usbh1 {
-	status = "okay";
-};
-
-&usdhc3 {
-	pinctrl-names = "default";
-	pinctrl-0 = <&pinctrl_usdhc3_2>;
-	status = "okay";
-};
diff --git a/arch/arm/boot/dts/imx6dl.dtsi b/arch/arm/boot/dts/imx6dl.dtsi
index 2b3ecd679350..9e8ae118fdd4 100644
--- a/arch/arm/boot/dts/imx6dl.dtsi
+++ b/arch/arm/boot/dts/imx6dl.dtsi
@@ -8,8 +8,8 @@
  *
  */
 
-#include "imx6qdl.dtsi"
 #include "imx6dl-pinfunc.h"
+#include "imx6qdl.dtsi"
 
 / {
 	cpus {
@@ -32,238 +32,15 @@
 	};
 
 	soc {
+		ocram: sram@00900000 {
+			compatible = "mmio-sram";
+			reg = <0x00900000 0x20000>;
+			clocks = <&clks 142>;
+		};
+
 		aips1: aips-bus@02000000 {
 			iomuxc: iomuxc@020e0000 {
 				compatible = "fsl,imx6dl-iomuxc";
-				reg = <0x020e0000 0x4000>;
-
-				audmux {
-					pinctrl_audmux_2: audmux-2 {
-						fsl,pins = <
-							MX6DL_PAD_CSI0_DAT7__AUD3_RXD  0x80000000
-							MX6DL_PAD_CSI0_DAT4__AUD3_TXC  0x80000000
-							MX6DL_PAD_CSI0_DAT5__AUD3_TXD  0x80000000
-							MX6DL_PAD_CSI0_DAT6__AUD3_TXFS 0x80000000
-						>;
-					};
-				};
-
-				ecspi1 {
-					pinctrl_ecspi1_1: ecspi1grp-1 {
-						fsl,pins = <
-							MX6DL_PAD_EIM_D17__ECSPI1_MISO 0x100b1
-							MX6DL_PAD_EIM_D18__ECSPI1_MOSI 0x100b1
-							MX6DL_PAD_EIM_D16__ECSPI1_SCLK 0x100b1
-						>;
-					};
-				};
-
-				enet {
-					pinctrl_enet_1: enetgrp-1 {
-						fsl,pins = <
-							MX6DL_PAD_ENET_MDIO__ENET_MDIO       0x1b0b0
-							MX6DL_PAD_ENET_MDC__ENET_MDC         0x1b0b0
-							MX6DL_PAD_RGMII_TXC__RGMII_TXC       0x1b0b0
-							MX6DL_PAD_RGMII_TD0__RGMII_TD0       0x1b0b0
-							MX6DL_PAD_RGMII_TD1__RGMII_TD1       0x1b0b0
-							MX6DL_PAD_RGMII_TD2__RGMII_TD2       0x1b0b0
-							MX6DL_PAD_RGMII_TD3__RGMII_TD3       0x1b0b0
-							MX6DL_PAD_RGMII_TX_CTL__RGMII_TX_CTL 0x1b0b0
-							MX6DL_PAD_ENET_REF_CLK__ENET_TX_CLK  0x1b0b0
-							MX6DL_PAD_RGMII_RXC__RGMII_RXC       0x1b0b0
-							MX6DL_PAD_RGMII_RD0__RGMII_RD0       0x1b0b0
-							MX6DL_PAD_RGMII_RD1__RGMII_RD1       0x1b0b0
-							MX6DL_PAD_RGMII_RD2__RGMII_RD2       0x1b0b0
-							MX6DL_PAD_RGMII_RD3__RGMII_RD3       0x1b0b0
-							MX6DL_PAD_RGMII_RX_CTL__RGMII_RX_CTL 0x1b0b0
-							MX6DL_PAD_GPIO_16__ENET_REF_CLK      0x4001b0a8
-						>;
-					};
-
-					pinctrl_enet_2: enetgrp-2 {
-						fsl,pins = <
-							MX6DL_PAD_KEY_COL1__ENET_MDIO        0x1b0b0
-							MX6DL_PAD_KEY_COL2__ENET_MDC         0x1b0b0
-							MX6DL_PAD_RGMII_TXC__RGMII_TXC       0x1b0b0
-							MX6DL_PAD_RGMII_TD0__RGMII_TD0       0x1b0b0
-							MX6DL_PAD_RGMII_TD1__RGMII_TD1       0x1b0b0
-							MX6DL_PAD_RGMII_TD2__RGMII_TD2       0x1b0b0
-							MX6DL_PAD_RGMII_TD3__RGMII_TD3       0x1b0b0
-							MX6DL_PAD_RGMII_TX_CTL__RGMII_TX_CTL 0x1b0b0
-							MX6DL_PAD_ENET_REF_CLK__ENET_TX_CLK  0x1b0b0
-							MX6DL_PAD_RGMII_RXC__RGMII_RXC       0x1b0b0
-							MX6DL_PAD_RGMII_RD0__RGMII_RD0       0x1b0b0
-							MX6DL_PAD_RGMII_RD1__RGMII_RD1       0x1b0b0
-							MX6DL_PAD_RGMII_RD2__RGMII_RD2       0x1b0b0
-							MX6DL_PAD_RGMII_RD3__RGMII_RD3       0x1b0b0
-							MX6DL_PAD_RGMII_RX_CTL__RGMII_RX_CTL 0x1b0b0
-						>;
-					};
-				};
-
-				gpmi-nand {
-					pinctrl_gpmi_nand_1: gpmi-nand-1 {
-						fsl,pins = <
-							MX6DL_PAD_NANDF_CLE__NAND_CLE     0xb0b1
-							MX6DL_PAD_NANDF_ALE__NAND_ALE     0xb0b1
-							MX6DL_PAD_NANDF_WP_B__NAND_WP_B   0xb0b1
-							MX6DL_PAD_NANDF_RB0__NAND_READY_B 0xb000
-							MX6DL_PAD_NANDF_CS0__NAND_CE0_B   0xb0b1
-							MX6DL_PAD_NANDF_CS1__NAND_CE1_B   0xb0b1
-							MX6DL_PAD_SD4_CMD__NAND_RE_B      0xb0b1
-							MX6DL_PAD_SD4_CLK__NAND_WE_B      0xb0b1
-							MX6DL_PAD_NANDF_D0__NAND_DATA00   0xb0b1
-							MX6DL_PAD_NANDF_D1__NAND_DATA01   0xb0b1
-							MX6DL_PAD_NANDF_D2__NAND_DATA02   0xb0b1
-							MX6DL_PAD_NANDF_D3__NAND_DATA03   0xb0b1
-							MX6DL_PAD_NANDF_D4__NAND_DATA04   0xb0b1
-							MX6DL_PAD_NANDF_D5__NAND_DATA05   0xb0b1
-							MX6DL_PAD_NANDF_D6__NAND_DATA06   0xb0b1
-							MX6DL_PAD_NANDF_D7__NAND_DATA07   0xb0b1
-							MX6DL_PAD_SD4_DAT0__NAND_DQS      0x00b1
-						>;
-					};
-				};
-
-				i2c1 {
-					pinctrl_i2c1_2: i2c1grp-2 {
-						fsl,pins = <
-							MX6DL_PAD_CSI0_DAT8__I2C1_SDA 0x4001b8b1
-							MX6DL_PAD_CSI0_DAT9__I2C1_SCL 0x4001b8b1
-						>;
-					};
-				};
-
-				uart1 {
-					pinctrl_uart1_1: uart1grp-1 {
-						fsl,pins = <
-							MX6DL_PAD_CSI0_DAT10__UART1_TX_DATA 0x1b0b1
-							MX6DL_PAD_CSI0_DAT11__UART1_RX_DATA 0x1b0b1
-						>;
-					};
-				};
-
-				uart4 {
-					pinctrl_uart4_1: uart4grp-1 {
-						fsl,pins = <
-							MX6DL_PAD_KEY_COL0__UART4_TX_DATA 0x1b0b1
-							MX6DL_PAD_KEY_ROW0__UART4_RX_DATA 0x1b0b1
-						>;
-					};
-				};
-
-				usbotg {
-					pinctrl_usbotg_2: usbotggrp-2 {
-						fsl,pins = <
-							MX6DL_PAD_ENET_RX_ER__USB_OTG_ID 0x17059
-						>;
-					};
-				};
-
-				usdhc2 {
-					pinctrl_usdhc2_1: usdhc2grp-1 {
-						fsl,pins = <
-							MX6DL_PAD_SD2_CMD__SD2_CMD    0x17059
-							MX6DL_PAD_SD2_CLK__SD2_CLK    0x10059
-							MX6DL_PAD_SD2_DAT0__SD2_DATA0 0x17059
-							MX6DL_PAD_SD2_DAT1__SD2_DATA1 0x17059
-							MX6DL_PAD_SD2_DAT2__SD2_DATA2 0x17059
-							MX6DL_PAD_SD2_DAT3__SD2_DATA3 0x17059
-							MX6DL_PAD_NANDF_D4__SD2_DATA4 0x17059
-							MX6DL_PAD_NANDF_D5__SD2_DATA5 0x17059
-							MX6DL_PAD_NANDF_D6__SD2_DATA6 0x17059
-							MX6DL_PAD_NANDF_D7__SD2_DATA7 0x17059
-						>;
-					};
-				};
-
-				usdhc3 {
-					pinctrl_usdhc3_1: usdhc3grp-1 {
-						fsl,pins = <
-							MX6DL_PAD_SD3_CMD__SD3_CMD    0x17059
-							MX6DL_PAD_SD3_CLK__SD3_CLK    0x10059
-							MX6DL_PAD_SD3_DAT0__SD3_DATA0 0x17059
-							MX6DL_PAD_SD3_DAT1__SD3_DATA1 0x17059
-							MX6DL_PAD_SD3_DAT2__SD3_DATA2 0x17059
-							MX6DL_PAD_SD3_DAT3__SD3_DATA3 0x17059
-							MX6DL_PAD_SD3_DAT4__SD3_DATA4 0x17059
-							MX6DL_PAD_SD3_DAT5__SD3_DATA5 0x17059
-							MX6DL_PAD_SD3_DAT6__SD3_DATA6 0x17059
-							MX6DL_PAD_SD3_DAT7__SD3_DATA7 0x17059
-						>;
-					};
-
-					pinctrl_usdhc3_2: usdhc3grp_2 {
-						fsl,pins = <
-							MX6DL_PAD_SD3_CMD__SD3_CMD    0x17059
-							MX6DL_PAD_SD3_CLK__SD3_CLK    0x10059
-							MX6DL_PAD_SD3_DAT0__SD3_DATA0 0x17059
-							MX6DL_PAD_SD3_DAT1__SD3_DATA1 0x17059
-							MX6DL_PAD_SD3_DAT2__SD3_DATA2 0x17059
-							MX6DL_PAD_SD3_DAT3__SD3_DATA3 0x17059
-						>;
-					};
-				};
-
-				weim {
-					pinctrl_weim_cs0_1: weim_cs0grp-1 {
-						fsl,pins = <
-							MX6DL_PAD_EIM_CS0__EIM_CS0_B   0xb0b1
-						>;
-					};
-
-					pinctrl_weim_nor_1: weim_norgrp-1 {
-						fsl,pins = <
-							MX6DL_PAD_EIM_OE__EIM_OE_B     0xb0b1
-							MX6DL_PAD_EIM_RW__EIM_RW       0xb0b1
-							MX6DL_PAD_EIM_WAIT__EIM_WAIT_B 0xb060
-							/* data */
-							MX6DL_PAD_EIM_D16__EIM_DATA16 0x1b0b0
-							MX6DL_PAD_EIM_D17__EIM_DATA17 0x1b0b0
-							MX6DL_PAD_EIM_D18__EIM_DATA18 0x1b0b0
-							MX6DL_PAD_EIM_D19__EIM_DATA19 0x1b0b0
-							MX6DL_PAD_EIM_D20__EIM_DATA20 0x1b0b0
-							MX6DL_PAD_EIM_D21__EIM_DATA21 0x1b0b0
-							MX6DL_PAD_EIM_D22__EIM_DATA22 0x1b0b0
-							MX6DL_PAD_EIM_D23__EIM_DATA23 0x1b0b0
-							MX6DL_PAD_EIM_D24__EIM_DATA24 0x1b0b0
-							MX6DL_PAD_EIM_D25__EIM_DATA25 0x1b0b0
-							MX6DL_PAD_EIM_D26__EIM_DATA26 0x1b0b0
-							MX6DL_PAD_EIM_D27__EIM_DATA27 0x1b0b0
-							MX6DL_PAD_EIM_D28__EIM_DATA28 0x1b0b0
-							MX6DL_PAD_EIM_D29__EIM_DATA29 0x1b0b0
-							MX6DL_PAD_EIM_D30__EIM_DATA30 0x1b0b0
-							MX6DL_PAD_EIM_D31__EIM_DATA31 0x1b0b0
-							/* address */
-							MX6DL_PAD_EIM_A23__EIM_ADDR23 0xb0b1
-							MX6DL_PAD_EIM_A22__EIM_ADDR22 0xb0b1
-							MX6DL_PAD_EIM_A21__EIM_ADDR21 0xb0b1
-							MX6DL_PAD_EIM_A20__EIM_ADDR20 0xb0b1
-							MX6DL_PAD_EIM_A19__EIM_ADDR19 0xb0b1
-							MX6DL_PAD_EIM_A18__EIM_ADDR18 0xb0b1
-							MX6DL_PAD_EIM_A17__EIM_ADDR17 0xb0b1
-							MX6DL_PAD_EIM_A16__EIM_ADDR16 0xb0b1
-							MX6DL_PAD_EIM_DA15__EIM_AD15  0xb0b1
-							MX6DL_PAD_EIM_DA14__EIM_AD14  0xb0b1
-							MX6DL_PAD_EIM_DA13__EIM_AD13  0xb0b1
-							MX6DL_PAD_EIM_DA12__EIM_AD12  0xb0b1
-							MX6DL_PAD_EIM_DA11__EIM_AD11  0xb0b1
-							MX6DL_PAD_EIM_DA10__EIM_AD10  0xb0b1
-							MX6DL_PAD_EIM_DA9__EIM_AD09   0xb0b1
-							MX6DL_PAD_EIM_DA8__EIM_AD08   0xb0b1
-							MX6DL_PAD_EIM_DA7__EIM_AD07   0xb0b1
-							MX6DL_PAD_EIM_DA6__EIM_AD06   0xb0b1
-							MX6DL_PAD_EIM_DA5__EIM_AD05   0xb0b1
-							MX6DL_PAD_EIM_DA4__EIM_AD04   0xb0b1
-							MX6DL_PAD_EIM_DA3__EIM_AD03   0xb0b1
-							MX6DL_PAD_EIM_DA2__EIM_AD02   0xb0b1
-							MX6DL_PAD_EIM_DA1__EIM_AD01   0xb0b1
-							MX6DL_PAD_EIM_DA0__EIM_AD00   0xb0b1
-						>;
-					};
-
-				};
-
 			};
 
 			pxp: pxp@020f0000 {
@@ -294,3 +71,20 @@
 		};
 	};
 };
+
+&ldb {
+	clocks = <&clks 33>, <&clks 34>,
+		 <&clks 39>, <&clks 40>,
+		 <&clks 135>, <&clks 136>;
+	clock-names = "di0_pll", "di1_pll",
+		      "di0_sel", "di1_sel",
+		      "di0", "di1";
+
+	lvds-channel@0 {
+		crtcs = <&ipu1 0>, <&ipu1 1>;
+	};
+
+	lvds-channel@1 {
+		crtcs = <&ipu1 0>, <&ipu1 1>;
+	};
+};
diff --git a/arch/arm/boot/dts/imx6q-arm2.dts b/arch/arm/boot/dts/imx6q-arm2.dts
index 4e54fde591bd..edf1bd967164 100644
--- a/arch/arm/boot/dts/imx6q-arm2.dts
+++ b/arch/arm/boot/dts/imx6q-arm2.dts
@@ -57,7 +57,7 @@
 	hog {
 		pinctrl_hog: hoggrp {
 			fsl,pins = <
-				MX6Q_PAD_EIM_D25__GPIO3_IO25 0x80000000
+				MX6QDL_PAD_EIM_D25__GPIO3_IO25 0x80000000
 			>;
 		};
 	};
@@ -65,8 +65,8 @@
 	arm2 {
 		pinctrl_usdhc3_arm2: usdhc3grp-arm2 {
 			fsl,pins = <
-				MX6Q_PAD_NANDF_CS0__GPIO6_IO11 0x80000000
-				MX6Q_PAD_NANDF_CS1__GPIO6_IO14 0x80000000
+				MX6QDL_PAD_NANDF_CS0__GPIO6_IO11 0x80000000
+				MX6QDL_PAD_NANDF_CS1__GPIO6_IO14 0x80000000
 			>;
 		};
 	};
@@ -97,6 +97,14 @@
 	status = "okay";
 };
 
+&uart2 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_uart2_2>;
+	fsl,dte-mode;
+	fsl,uart-has-rtscts;
+	status = "okay";
+};
+
 &uart4 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_uart4_1>;
diff --git a/arch/arm/boot/dts/imx6q-phytec-pfla02.dtsi b/arch/arm/boot/dts/imx6q-phytec-pfla02.dtsi
index f5e1981025ed..1a3b50d4d8fa 100644
--- a/arch/arm/boot/dts/imx6q-phytec-pfla02.dtsi
+++ b/arch/arm/boot/dts/imx6q-phytec-pfla02.dtsi
@@ -20,6 +20,110 @@
 	};
 };
 
+&ecspi3 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_ecspi3_1>;
+	status = "okay";
+	fsl,spi-num-chipselects = <1>;
+	cs-gpios = <&gpio4 24 0>;
+
+	flash@0 {
+		compatible = "m25p80";
+		spi-max-frequency = <20000000>;
+		reg = <0>;
+	};
+};
+
+&i2c1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_i2c1_1>;
+	status = "okay";
+
+	eeprom@50 {
+		compatible = "atmel,24c32";
+		reg = <0x50>;
+	};
+
+	pmic@58 {
+		compatible = "dialog,da9063";
+		reg = <0x58>;
+		interrupt-parent = <&gpio4>;
+		interrupts = <17 0x8>; /* active-low GPIO4_17 */
+
+		regulators {
+			vddcore_reg: bcore1 {
+				regulator-min-microvolt = <730000>;
+				regulator-max-microvolt = <1380000>;
+				regulator-always-on;
+			};
+
+			vddsoc_reg: bcore2 {
+				regulator-min-microvolt = <730000>;
+				regulator-max-microvolt = <1380000>;
+				regulator-always-on;
+			};
+
+			vdd_ddr3_reg: bpro {
+				regulator-min-microvolt = <1500000>;
+				regulator-max-microvolt = <1500000>;
+				regulator-always-on;
+			};
+
+			vdd_3v3_reg: bperi {
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-always-on;
+			};
+
+			vdd_buckmem_reg: bmem {
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-always-on;
+			};
+
+			vdd_eth_reg: bio {
+				regulator-min-microvolt = <1200000>;
+				regulator-max-microvolt = <1200000>;
+				regulator-always-on;
+			};
+
+			vdd_eth_io_reg: ldo4 {
+				regulator-min-microvolt = <2500000>;
+				regulator-max-microvolt = <2500000>;
+				regulator-always-on;
+			};
+
+			vdd_mx6_snvs_reg: ldo5 {
+				regulator-min-microvolt = <3000000>;
+				regulator-max-microvolt = <3000000>;
+				regulator-always-on;
+			};
+
+			vdd_3v3_pmic_io_reg: ldo6 {
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-always-on;
+			};
+
+			vdd_sd0_reg: ldo9 {
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+			};
+
+			vdd_sd1_reg: ldo10 {
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+			};
+
+			vdd_mx6_high_reg: ldo11 {
+				regulator-min-microvolt = <3000000>;
+				regulator-max-microvolt = <3000000>;
+				regulator-always-on;
+			};
+		};
+	};
+};
+
 &iomuxc {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_hog>;
@@ -27,7 +131,9 @@
 	hog {
 		pinctrl_hog: hoggrp {
 			fsl,pins = <
-				MX6Q_PAD_EIM_D23__GPIO3_IO23    0x80000000
+				MX6QDL_PAD_EIM_D23__GPIO3_IO23 0x80000000
+				MX6QDL_PAD_DISP0_DAT3__GPIO4_IO24 0x80000000 /* SPI NOR chipselect */
+				MX6QDL_PAD_DI0_PIN15__GPIO4_IO17  0x80000000 /* PMIC interrupt */
 			>;
 		};
 	};
@@ -35,8 +141,8 @@
 	pfla02 {
 		pinctrl_usdhc3_pfla02: usdhc3grp-pfla02 {
 			fsl,pins = <
-				MX6Q_PAD_ENET_RXD0__GPIO1_IO27  0x80000000
-				MX6Q_PAD_ENET_TXD1__GPIO1_IO29  0x80000000
+				MX6QDL_PAD_ENET_RXD0__GPIO1_IO27 0x80000000
+				MX6QDL_PAD_ENET_TXD1__GPIO1_IO29 0x80000000
 			>;
 		};
 	};
diff --git a/arch/arm/boot/dts/imx6q-pinfunc.h b/arch/arm/boot/dts/imx6q-pinfunc.h
index faea6e1ada00..9bbe82bdee41 100644
--- a/arch/arm/boot/dts/imx6q-pinfunc.h
+++ b/arch/arm/boot/dts/imx6q-pinfunc.h
@@ -14,1028 +14,1032 @@
  * The pin function ID is a tuple of
  * <mux_reg conf_reg input_reg mux_mode input_val>
  */
-#define MX6Q_PAD_SD2_DAT1__SD2_DATA1              0x04c 0x360 0x000 0x0 0x0
-#define MX6Q_PAD_SD2_DAT1__ECSPI5_SS0             0x04c 0x360 0x834 0x1 0x0
-#define MX6Q_PAD_SD2_DAT1__EIM_CS2_B              0x04c 0x360 0x000 0x2 0x0
-#define MX6Q_PAD_SD2_DAT1__AUD4_TXFS              0x04c 0x360 0x7c8 0x3 0x0
-#define MX6Q_PAD_SD2_DAT1__KEY_COL7               0x04c 0x360 0x8f0 0x4 0x0
-#define MX6Q_PAD_SD2_DAT1__GPIO1_IO14             0x04c 0x360 0x000 0x5 0x0
-#define MX6Q_PAD_SD2_DAT2__SD2_DATA2              0x050 0x364 0x000 0x0 0x0
-#define MX6Q_PAD_SD2_DAT2__ECSPI5_SS1             0x050 0x364 0x838 0x1 0x0
-#define MX6Q_PAD_SD2_DAT2__EIM_CS3_B              0x050 0x364 0x000 0x2 0x0
-#define MX6Q_PAD_SD2_DAT2__AUD4_TXD               0x050 0x364 0x7b8 0x3 0x0
-#define MX6Q_PAD_SD2_DAT2__KEY_ROW6               0x050 0x364 0x8f8 0x4 0x0
-#define MX6Q_PAD_SD2_DAT2__GPIO1_IO13             0x050 0x364 0x000 0x5 0x0
-#define MX6Q_PAD_SD2_DAT0__SD2_DATA0              0x054 0x368 0x000 0x0 0x0
-#define MX6Q_PAD_SD2_DAT0__ECSPI5_MISO            0x054 0x368 0x82c 0x1 0x0
-#define MX6Q_PAD_SD2_DAT0__AUD4_RXD               0x054 0x368 0x7b4 0x3 0x0
-#define MX6Q_PAD_SD2_DAT0__KEY_ROW7               0x054 0x368 0x8fc 0x4 0x0
-#define MX6Q_PAD_SD2_DAT0__GPIO1_IO15             0x054 0x368 0x000 0x5 0x0
-#define MX6Q_PAD_SD2_DAT0__DCIC2_OUT              0x054 0x368 0x000 0x6 0x0
-#define MX6Q_PAD_RGMII_TXC__USB_H2_DATA           0x058 0x36c 0x000 0x0 0x0
-#define MX6Q_PAD_RGMII_TXC__RGMII_TXC             0x058 0x36c 0x000 0x1 0x0
-#define MX6Q_PAD_RGMII_TXC__SPDIF_EXT_CLK         0x058 0x36c 0x918 0x2 0x0
-#define MX6Q_PAD_RGMII_TXC__GPIO6_IO19            0x058 0x36c 0x000 0x5 0x0
-#define MX6Q_PAD_RGMII_TXC__XTALOSC_REF_CLK_24M   0x058 0x36c 0x000 0x7 0x0
-#define MX6Q_PAD_RGMII_TD0__HSI_TX_READY          0x05c 0x370 0x000 0x0 0x0
-#define MX6Q_PAD_RGMII_TD0__RGMII_TD0             0x05c 0x370 0x000 0x1 0x0
-#define MX6Q_PAD_RGMII_TD0__GPIO6_IO20            0x05c 0x370 0x000 0x5 0x0
-#define MX6Q_PAD_RGMII_TD1__HSI_RX_FLAG           0x060 0x374 0x000 0x0 0x0
-#define MX6Q_PAD_RGMII_TD1__RGMII_TD1             0x060 0x374 0x000 0x1 0x0
-#define MX6Q_PAD_RGMII_TD1__GPIO6_IO21            0x060 0x374 0x000 0x5 0x0
-#define MX6Q_PAD_RGMII_TD2__HSI_RX_DATA           0x064 0x378 0x000 0x0 0x0
-#define MX6Q_PAD_RGMII_TD2__RGMII_TD2             0x064 0x378 0x000 0x1 0x0
-#define MX6Q_PAD_RGMII_TD2__GPIO6_IO22            0x064 0x378 0x000 0x5 0x0
-#define MX6Q_PAD_RGMII_TD3__HSI_RX_WAKE           0x068 0x37c 0x000 0x0 0x0
-#define MX6Q_PAD_RGMII_TD3__RGMII_TD3             0x068 0x37c 0x000 0x1 0x0
-#define MX6Q_PAD_RGMII_TD3__GPIO6_IO23            0x068 0x37c 0x000 0x5 0x0
-#define MX6Q_PAD_RGMII_RX_CTL__USB_H3_DATA        0x06c 0x380 0x000 0x0 0x0
-#define MX6Q_PAD_RGMII_RX_CTL__RGMII_RX_CTL       0x06c 0x380 0x858 0x1 0x0
-#define MX6Q_PAD_RGMII_RX_CTL__GPIO6_IO24         0x06c 0x380 0x000 0x5 0x0
-#define MX6Q_PAD_RGMII_RD0__HSI_RX_READY          0x070 0x384 0x000 0x0 0x0
-#define MX6Q_PAD_RGMII_RD0__RGMII_RD0             0x070 0x384 0x848 0x1 0x0
-#define MX6Q_PAD_RGMII_RD0__GPIO6_IO25            0x070 0x384 0x000 0x5 0x0
-#define MX6Q_PAD_RGMII_TX_CTL__USB_H2_STROBE      0x074 0x388 0x000 0x0 0x0
-#define MX6Q_PAD_RGMII_TX_CTL__RGMII_TX_CTL       0x074 0x388 0x000 0x1 0x0
-#define MX6Q_PAD_RGMII_TX_CTL__GPIO6_IO26         0x074 0x388 0x000 0x5 0x0
-#define MX6Q_PAD_RGMII_TX_CTL__ENET_REF_CLK       0x074 0x388 0x83c 0x7 0x0
-#define MX6Q_PAD_RGMII_RD1__HSI_TX_FLAG           0x078 0x38c 0x000 0x0 0x0
-#define MX6Q_PAD_RGMII_RD1__RGMII_RD1             0x078 0x38c 0x84c 0x1 0x0
-#define MX6Q_PAD_RGMII_RD1__GPIO6_IO27            0x078 0x38c 0x000 0x5 0x0
-#define MX6Q_PAD_RGMII_RD2__HSI_TX_DATA           0x07c 0x390 0x000 0x0 0x0
-#define MX6Q_PAD_RGMII_RD2__RGMII_RD2             0x07c 0x390 0x850 0x1 0x0
-#define MX6Q_PAD_RGMII_RD2__GPIO6_IO28            0x07c 0x390 0x000 0x5 0x0
-#define MX6Q_PAD_RGMII_RD3__HSI_TX_WAKE           0x080 0x394 0x000 0x0 0x0
-#define MX6Q_PAD_RGMII_RD3__RGMII_RD3             0x080 0x394 0x854 0x1 0x0
-#define MX6Q_PAD_RGMII_RD3__GPIO6_IO29            0x080 0x394 0x000 0x5 0x0
-#define MX6Q_PAD_RGMII_RXC__USB_H3_STROBE         0x084 0x398 0x000 0x0 0x0
-#define MX6Q_PAD_RGMII_RXC__RGMII_RXC             0x084 0x398 0x844 0x1 0x0
-#define MX6Q_PAD_RGMII_RXC__GPIO6_IO30            0x084 0x398 0x000 0x5 0x0
-#define MX6Q_PAD_EIM_A25__EIM_ADDR25              0x088 0x39c 0x000 0x0 0x0
-#define MX6Q_PAD_EIM_A25__ECSPI4_SS1              0x088 0x39c 0x000 0x1 0x0
-#define MX6Q_PAD_EIM_A25__ECSPI2_RDY              0x088 0x39c 0x000 0x2 0x0
-#define MX6Q_PAD_EIM_A25__IPU1_DI1_PIN12          0x088 0x39c 0x000 0x3 0x0
-#define MX6Q_PAD_EIM_A25__IPU1_DI0_D1_CS          0x088 0x39c 0x000 0x4 0x0
-#define MX6Q_PAD_EIM_A25__GPIO5_IO02              0x088 0x39c 0x000 0x5 0x0
-#define MX6Q_PAD_EIM_A25__HDMI_TX_CEC_LINE        0x088 0x39c 0x88c 0x6 0x0
-#define MX6Q_PAD_EIM_EB2__EIM_EB2_B               0x08c 0x3a0 0x000 0x0 0x0
-#define MX6Q_PAD_EIM_EB2__ECSPI1_SS0              0x08c 0x3a0 0x800 0x1 0x0
-#define MX6Q_PAD_EIM_EB2__IPU2_CSI1_DATA19        0x08c 0x3a0 0x8d4 0x3 0x0
-#define MX6Q_PAD_EIM_EB2__HDMI_TX_DDC_SCL         0x08c 0x3a0 0x890 0x4 0x0
-#define MX6Q_PAD_EIM_EB2__GPIO2_IO30              0x08c 0x3a0 0x000 0x5 0x0
-#define MX6Q_PAD_EIM_EB2__I2C2_SCL                0x08c 0x3a0 0x8a0 0x6 0x0
-#define MX6Q_PAD_EIM_EB2__SRC_BOOT_CFG30          0x08c 0x3a0 0x000 0x7 0x0
-#define MX6Q_PAD_EIM_D16__EIM_DATA16              0x090 0x3a4 0x000 0x0 0x0
-#define MX6Q_PAD_EIM_D16__ECSPI1_SCLK             0x090 0x3a4 0x7f4 0x1 0x0
-#define MX6Q_PAD_EIM_D16__IPU1_DI0_PIN05          0x090 0x3a4 0x000 0x2 0x0
-#define MX6Q_PAD_EIM_D16__IPU2_CSI1_DATA18        0x090 0x3a4 0x8d0 0x3 0x0
-#define MX6Q_PAD_EIM_D16__HDMI_TX_DDC_SDA         0x090 0x3a4 0x894 0x4 0x0
-#define MX6Q_PAD_EIM_D16__GPIO3_IO16              0x090 0x3a4 0x000 0x5 0x0
-#define MX6Q_PAD_EIM_D16__I2C2_SDA                0x090 0x3a4 0x8a4 0x6 0x0
-#define MX6Q_PAD_EIM_D17__EIM_DATA17              0x094 0x3a8 0x000 0x0 0x0
-#define MX6Q_PAD_EIM_D17__ECSPI1_MISO             0x094 0x3a8 0x7f8 0x1 0x0
-#define MX6Q_PAD_EIM_D17__IPU1_DI0_PIN06          0x094 0x3a8 0x000 0x2 0x0
-#define MX6Q_PAD_EIM_D17__IPU2_CSI1_PIXCLK        0x094 0x3a8 0x8e0 0x3 0x0
-#define MX6Q_PAD_EIM_D17__DCIC1_OUT               0x094 0x3a8 0x000 0x4 0x0
-#define MX6Q_PAD_EIM_D17__GPIO3_IO17              0x094 0x3a8 0x000 0x5 0x0
-#define MX6Q_PAD_EIM_D17__I2C3_SCL                0x094 0x3a8 0x8a8 0x6 0x0
-#define MX6Q_PAD_EIM_D18__EIM_DATA18              0x098 0x3ac 0x000 0x0 0x0
-#define MX6Q_PAD_EIM_D18__ECSPI1_MOSI             0x098 0x3ac 0x7fc 0x1 0x0
-#define MX6Q_PAD_EIM_D18__IPU1_DI0_PIN07          0x098 0x3ac 0x000 0x2 0x0
-#define MX6Q_PAD_EIM_D18__IPU2_CSI1_DATA17        0x098 0x3ac 0x8cc 0x3 0x0
-#define MX6Q_PAD_EIM_D18__IPU1_DI1_D0_CS          0x098 0x3ac 0x000 0x4 0x0
-#define MX6Q_PAD_EIM_D18__GPIO3_IO18              0x098 0x3ac 0x000 0x5 0x0
-#define MX6Q_PAD_EIM_D18__I2C3_SDA                0x098 0x3ac 0x8ac 0x6 0x0
-#define MX6Q_PAD_EIM_D19__EIM_DATA19              0x09c 0x3b0 0x000 0x0 0x0
-#define MX6Q_PAD_EIM_D19__ECSPI1_SS1              0x09c 0x3b0 0x804 0x1 0x0
-#define MX6Q_PAD_EIM_D19__IPU1_DI0_PIN08          0x09c 0x3b0 0x000 0x2 0x0
-#define MX6Q_PAD_EIM_D19__IPU2_CSI1_DATA16        0x09c 0x3b0 0x8c8 0x3 0x0
-#define MX6Q_PAD_EIM_D19__UART1_CTS_B             0x09c 0x3b0 0x000 0x4 0x0
-#define MX6Q_PAD_EIM_D19__UART1_RTS_B             0x09c 0x3b0 0x91c 0x4 0x0
-#define MX6Q_PAD_EIM_D19__GPIO3_IO19              0x09c 0x3b0 0x000 0x5 0x0
-#define MX6Q_PAD_EIM_D19__EPIT1_OUT               0x09c 0x3b0 0x000 0x6 0x0
-#define MX6Q_PAD_EIM_D20__EIM_DATA20              0x0a0 0x3b4 0x000 0x0 0x0
-#define MX6Q_PAD_EIM_D20__ECSPI4_SS0              0x0a0 0x3b4 0x824 0x1 0x0
-#define MX6Q_PAD_EIM_D20__IPU1_DI0_PIN16          0x0a0 0x3b4 0x000 0x2 0x0
-#define MX6Q_PAD_EIM_D20__IPU2_CSI1_DATA15        0x0a0 0x3b4 0x8c4 0x3 0x0
-#define MX6Q_PAD_EIM_D20__UART1_RTS_B             0x0a0 0x3b4 0x91c 0x4 0x1
-#define MX6Q_PAD_EIM_D20__UART1_CTS_B             0x0a0 0x3b4 0x000 0x4 0x0
-#define MX6Q_PAD_EIM_D20__GPIO3_IO20              0x0a0 0x3b4 0x000 0x5 0x0
-#define MX6Q_PAD_EIM_D20__EPIT2_OUT               0x0a0 0x3b4 0x000 0x6 0x0
-#define MX6Q_PAD_EIM_D21__EIM_DATA21              0x0a4 0x3b8 0x000 0x0 0x0
-#define MX6Q_PAD_EIM_D21__ECSPI4_SCLK             0x0a4 0x3b8 0x000 0x1 0x0
-#define MX6Q_PAD_EIM_D21__IPU1_DI0_PIN17          0x0a4 0x3b8 0x000 0x2 0x0
-#define MX6Q_PAD_EIM_D21__IPU2_CSI1_DATA11        0x0a4 0x3b8 0x8b4 0x3 0x0
-#define MX6Q_PAD_EIM_D21__USB_OTG_OC              0x0a4 0x3b8 0x944 0x4 0x0
-#define MX6Q_PAD_EIM_D21__GPIO3_IO21              0x0a4 0x3b8 0x000 0x5 0x0
-#define MX6Q_PAD_EIM_D21__I2C1_SCL                0x0a4 0x3b8 0x898 0x6 0x0
-#define MX6Q_PAD_EIM_D21__SPDIF_IN                0x0a4 0x3b8 0x914 0x7 0x0
-#define MX6Q_PAD_EIM_D22__EIM_DATA22              0x0a8 0x3bc 0x000 0x0 0x0
-#define MX6Q_PAD_EIM_D22__ECSPI4_MISO             0x0a8 0x3bc 0x000 0x1 0x0
-#define MX6Q_PAD_EIM_D22__IPU1_DI0_PIN01          0x0a8 0x3bc 0x000 0x2 0x0
-#define MX6Q_PAD_EIM_D22__IPU2_CSI1_DATA10        0x0a8 0x3bc 0x8b0 0x3 0x0
-#define MX6Q_PAD_EIM_D22__USB_OTG_PWR             0x0a8 0x3bc 0x000 0x4 0x0
-#define MX6Q_PAD_EIM_D22__GPIO3_IO22              0x0a8 0x3bc 0x000 0x5 0x0
-#define MX6Q_PAD_EIM_D22__SPDIF_OUT               0x0a8 0x3bc 0x000 0x6 0x0
-#define MX6Q_PAD_EIM_D23__EIM_DATA23              0x0ac 0x3c0 0x000 0x0 0x0
-#define MX6Q_PAD_EIM_D23__IPU1_DI0_D0_CS          0x0ac 0x3c0 0x000 0x1 0x0
-#define MX6Q_PAD_EIM_D23__UART3_CTS_B             0x0ac 0x3c0 0x000 0x2 0x0
-#define MX6Q_PAD_EIM_D23__UART3_RTS_B             0x0ac 0x3c0 0x92c 0x2 0x0
-#define MX6Q_PAD_EIM_D23__UART1_DCD_B             0x0ac 0x3c0 0x000 0x3 0x0
-#define MX6Q_PAD_EIM_D23__IPU2_CSI1_DATA_EN       0x0ac 0x3c0 0x8d8 0x4 0x0
-#define MX6Q_PAD_EIM_D23__GPIO3_IO23              0x0ac 0x3c0 0x000 0x5 0x0
-#define MX6Q_PAD_EIM_D23__IPU1_DI1_PIN02          0x0ac 0x3c0 0x000 0x6 0x0
-#define MX6Q_PAD_EIM_D23__IPU1_DI1_PIN14          0x0ac 0x3c0 0x000 0x7 0x0
-#define MX6Q_PAD_EIM_EB3__EIM_EB3_B               0x0b0 0x3c4 0x000 0x0 0x0
-#define MX6Q_PAD_EIM_EB3__ECSPI4_RDY              0x0b0 0x3c4 0x000 0x1 0x0
-#define MX6Q_PAD_EIM_EB3__UART3_RTS_B             0x0b0 0x3c4 0x92c 0x2 0x1
-#define MX6Q_PAD_EIM_EB3__UART3_CTS_B             0x0b0 0x3c4 0x000 0x2 0x0
-#define MX6Q_PAD_EIM_EB3__UART1_RI_B              0x0b0 0x3c4 0x000 0x3 0x0
-#define MX6Q_PAD_EIM_EB3__IPU2_CSI1_HSYNC         0x0b0 0x3c4 0x8dc 0x4 0x0
-#define MX6Q_PAD_EIM_EB3__GPIO2_IO31              0x0b0 0x3c4 0x000 0x5 0x0
-#define MX6Q_PAD_EIM_EB3__IPU1_DI1_PIN03          0x0b0 0x3c4 0x000 0x6 0x0
-#define MX6Q_PAD_EIM_EB3__SRC_BOOT_CFG31          0x0b0 0x3c4 0x000 0x7 0x0
-#define MX6Q_PAD_EIM_D24__EIM_DATA24              0x0b4 0x3c8 0x000 0x0 0x0
-#define MX6Q_PAD_EIM_D24__ECSPI4_SS2              0x0b4 0x3c8 0x000 0x1 0x0
-#define MX6Q_PAD_EIM_D24__UART3_TX_DATA           0x0b4 0x3c8 0x000 0x2 0x0
-#define MX6Q_PAD_EIM_D24__UART3_RX_DATA           0x0b4 0x3c8 0x930 0x2 0x0
-#define MX6Q_PAD_EIM_D24__ECSPI1_SS2              0x0b4 0x3c8 0x808 0x3 0x0
-#define MX6Q_PAD_EIM_D24__ECSPI2_SS2              0x0b4 0x3c8 0x000 0x4 0x0
-#define MX6Q_PAD_EIM_D24__GPIO3_IO24              0x0b4 0x3c8 0x000 0x5 0x0
-#define MX6Q_PAD_EIM_D24__AUD5_RXFS               0x0b4 0x3c8 0x7d8 0x6 0x0
-#define MX6Q_PAD_EIM_D24__UART1_DTR_B             0x0b4 0x3c8 0x000 0x7 0x0
-#define MX6Q_PAD_EIM_D25__EIM_DATA25              0x0b8 0x3cc 0x000 0x0 0x0
-#define MX6Q_PAD_EIM_D25__ECSPI4_SS3              0x0b8 0x3cc 0x000 0x1 0x0
-#define MX6Q_PAD_EIM_D25__UART3_RX_DATA           0x0b8 0x3cc 0x930 0x2 0x1
-#define MX6Q_PAD_EIM_D25__UART3_TX_DATA           0x0b8 0x3cc 0x000 0x2 0x0
-#define MX6Q_PAD_EIM_D25__ECSPI1_SS3              0x0b8 0x3cc 0x80c 0x3 0x0
-#define MX6Q_PAD_EIM_D25__ECSPI2_SS3              0x0b8 0x3cc 0x000 0x4 0x0
-#define MX6Q_PAD_EIM_D25__GPIO3_IO25              0x0b8 0x3cc 0x000 0x5 0x0
-#define MX6Q_PAD_EIM_D25__AUD5_RXC                0x0b8 0x3cc 0x7d4 0x6 0x0
-#define MX6Q_PAD_EIM_D25__UART1_DSR_B             0x0b8 0x3cc 0x000 0x7 0x0
-#define MX6Q_PAD_EIM_D26__EIM_DATA26              0x0bc 0x3d0 0x000 0x0 0x0
-#define MX6Q_PAD_EIM_D26__IPU1_DI1_PIN11          0x0bc 0x3d0 0x000 0x1 0x0
-#define MX6Q_PAD_EIM_D26__IPU1_CSI0_DATA01        0x0bc 0x3d0 0x000 0x2 0x0
-#define MX6Q_PAD_EIM_D26__IPU2_CSI1_DATA14        0x0bc 0x3d0 0x8c0 0x3 0x0
-#define MX6Q_PAD_EIM_D26__UART2_TX_DATA           0x0bc 0x3d0 0x000 0x4 0x0
-#define MX6Q_PAD_EIM_D26__UART2_RX_DATA           0x0bc 0x3d0 0x928 0x4 0x0
-#define MX6Q_PAD_EIM_D26__GPIO3_IO26              0x0bc 0x3d0 0x000 0x5 0x0
-#define MX6Q_PAD_EIM_D26__IPU1_SISG2              0x0bc 0x3d0 0x000 0x6 0x0
-#define MX6Q_PAD_EIM_D26__IPU1_DISP1_DATA22       0x0bc 0x3d0 0x000 0x7 0x0
-#define MX6Q_PAD_EIM_D27__EIM_DATA27              0x0c0 0x3d4 0x000 0x0 0x0
-#define MX6Q_PAD_EIM_D27__IPU1_DI1_PIN13          0x0c0 0x3d4 0x000 0x1 0x0
-#define MX6Q_PAD_EIM_D27__IPU1_CSI0_DATA00        0x0c0 0x3d4 0x000 0x2 0x0
-#define MX6Q_PAD_EIM_D27__IPU2_CSI1_DATA13        0x0c0 0x3d4 0x8bc 0x3 0x0
-#define MX6Q_PAD_EIM_D27__UART2_RX_DATA           0x0c0 0x3d4 0x928 0x4 0x1
-#define MX6Q_PAD_EIM_D27__UART2_TX_DATA           0x0c0 0x3d4 0x000 0x4 0x0
-#define MX6Q_PAD_EIM_D27__GPIO3_IO27              0x0c0 0x3d4 0x000 0x5 0x0
-#define MX6Q_PAD_EIM_D27__IPU1_SISG3              0x0c0 0x3d4 0x000 0x6 0x0
-#define MX6Q_PAD_EIM_D27__IPU1_DISP1_DATA23       0x0c0 0x3d4 0x000 0x7 0x0
-#define MX6Q_PAD_EIM_D28__EIM_DATA28              0x0c4 0x3d8 0x000 0x0 0x0
-#define MX6Q_PAD_EIM_D28__I2C1_SDA                0x0c4 0x3d8 0x89c 0x1 0x0
-#define MX6Q_PAD_EIM_D28__ECSPI4_MOSI             0x0c4 0x3d8 0x000 0x2 0x0
-#define MX6Q_PAD_EIM_D28__IPU2_CSI1_DATA12        0x0c4 0x3d8 0x8b8 0x3 0x0
-#define MX6Q_PAD_EIM_D28__UART2_CTS_B             0x0c4 0x3d8 0x000 0x4 0x0
-#define MX6Q_PAD_EIM_D28__UART2_RTS_B             0x0c4 0x3d8 0x924 0x4 0x0
-#define MX6Q_PAD_EIM_D28__GPIO3_IO28              0x0c4 0x3d8 0x000 0x5 0x0
-#define MX6Q_PAD_EIM_D28__IPU1_EXT_TRIG           0x0c4 0x3d8 0x000 0x6 0x0
-#define MX6Q_PAD_EIM_D28__IPU1_DI0_PIN13          0x0c4 0x3d8 0x000 0x7 0x0
-#define MX6Q_PAD_EIM_D29__EIM_DATA29              0x0c8 0x3dc 0x000 0x0 0x0
-#define MX6Q_PAD_EIM_D29__IPU1_DI1_PIN15          0x0c8 0x3dc 0x000 0x1 0x0
-#define MX6Q_PAD_EIM_D29__ECSPI4_SS0              0x0c8 0x3dc 0x824 0x2 0x1
-#define MX6Q_PAD_EIM_D29__UART2_RTS_B             0x0c8 0x3dc 0x924 0x4 0x1
-#define MX6Q_PAD_EIM_D29__UART2_CTS_B             0x0c8 0x3dc 0x000 0x4 0x0
-#define MX6Q_PAD_EIM_D29__GPIO3_IO29              0x0c8 0x3dc 0x000 0x5 0x0
-#define MX6Q_PAD_EIM_D29__IPU2_CSI1_VSYNC         0x0c8 0x3dc 0x8e4 0x6 0x0
-#define MX6Q_PAD_EIM_D29__IPU1_DI0_PIN14          0x0c8 0x3dc 0x000 0x7 0x0
-#define MX6Q_PAD_EIM_D30__EIM_DATA30              0x0cc 0x3e0 0x000 0x0 0x0
-#define MX6Q_PAD_EIM_D30__IPU1_DISP1_DATA21       0x0cc 0x3e0 0x000 0x1 0x0
-#define MX6Q_PAD_EIM_D30__IPU1_DI0_PIN11          0x0cc 0x3e0 0x000 0x2 0x0
-#define MX6Q_PAD_EIM_D30__IPU1_CSI0_DATA03        0x0cc 0x3e0 0x000 0x3 0x0
-#define MX6Q_PAD_EIM_D30__UART3_CTS_B             0x0cc 0x3e0 0x000 0x4 0x0
-#define MX6Q_PAD_EIM_D30__UART3_RTS_B             0x0cc 0x3e0 0x92c 0x4 0x2
-#define MX6Q_PAD_EIM_D30__GPIO3_IO30              0x0cc 0x3e0 0x000 0x5 0x0
-#define MX6Q_PAD_EIM_D30__USB_H1_OC               0x0cc 0x3e0 0x948 0x6 0x0
-#define MX6Q_PAD_EIM_D31__EIM_DATA31              0x0d0 0x3e4 0x000 0x0 0x0
-#define MX6Q_PAD_EIM_D31__IPU1_DISP1_DATA20       0x0d0 0x3e4 0x000 0x1 0x0
-#define MX6Q_PAD_EIM_D31__IPU1_DI0_PIN12          0x0d0 0x3e4 0x000 0x2 0x0
-#define MX6Q_PAD_EIM_D31__IPU1_CSI0_DATA02        0x0d0 0x3e4 0x000 0x3 0x0
-#define MX6Q_PAD_EIM_D31__UART3_RTS_B             0x0d0 0x3e4 0x92c 0x4 0x3
-#define MX6Q_PAD_EIM_D31__UART3_CTS_B             0x0d0 0x3e4 0x000 0x4 0x0
-#define MX6Q_PAD_EIM_D31__GPIO3_IO31              0x0d0 0x3e4 0x000 0x5 0x0
-#define MX6Q_PAD_EIM_D31__USB_H1_PWR              0x0d0 0x3e4 0x000 0x6 0x0
-#define MX6Q_PAD_EIM_A24__EIM_ADDR24              0x0d4 0x3e8 0x000 0x0 0x0
-#define MX6Q_PAD_EIM_A24__IPU1_DISP1_DATA19       0x0d4 0x3e8 0x000 0x1 0x0
-#define MX6Q_PAD_EIM_A24__IPU2_CSI1_DATA19        0x0d4 0x3e8 0x8d4 0x2 0x1
-#define MX6Q_PAD_EIM_A24__IPU2_SISG2              0x0d4 0x3e8 0x000 0x3 0x0
-#define MX6Q_PAD_EIM_A24__IPU1_SISG2              0x0d4 0x3e8 0x000 0x4 0x0
-#define MX6Q_PAD_EIM_A24__GPIO5_IO04              0x0d4 0x3e8 0x000 0x5 0x0
-#define MX6Q_PAD_EIM_A24__SRC_BOOT_CFG24          0x0d4 0x3e8 0x000 0x7 0x0
-#define MX6Q_PAD_EIM_A23__EIM_ADDR23              0x0d8 0x3ec 0x000 0x0 0x0
-#define MX6Q_PAD_EIM_A23__IPU1_DISP1_DATA18       0x0d8 0x3ec 0x000 0x1 0x0
-#define MX6Q_PAD_EIM_A23__IPU2_CSI1_DATA18        0x0d8 0x3ec 0x8d0 0x2 0x1
-#define MX6Q_PAD_EIM_A23__IPU2_SISG3              0x0d8 0x3ec 0x000 0x3 0x0
-#define MX6Q_PAD_EIM_A23__IPU1_SISG3              0x0d8 0x3ec 0x000 0x4 0x0
-#define MX6Q_PAD_EIM_A23__GPIO6_IO06              0x0d8 0x3ec 0x000 0x5 0x0
-#define MX6Q_PAD_EIM_A23__SRC_BOOT_CFG23          0x0d8 0x3ec 0x000 0x7 0x0
-#define MX6Q_PAD_EIM_A22__EIM_ADDR22              0x0dc 0x3f0 0x000 0x0 0x0
-#define MX6Q_PAD_EIM_A22__IPU1_DISP1_DATA17       0x0dc 0x3f0 0x000 0x1 0x0
-#define MX6Q_PAD_EIM_A22__IPU2_CSI1_DATA17        0x0dc 0x3f0 0x8cc 0x2 0x1
-#define MX6Q_PAD_EIM_A22__GPIO2_IO16              0x0dc 0x3f0 0x000 0x5 0x0
-#define MX6Q_PAD_EIM_A22__SRC_BOOT_CFG22          0x0dc 0x3f0 0x000 0x7 0x0
-#define MX6Q_PAD_EIM_A21__EIM_ADDR21              0x0e0 0x3f4 0x000 0x0 0x0
-#define MX6Q_PAD_EIM_A21__IPU1_DISP1_DATA16       0x0e0 0x3f4 0x000 0x1 0x0
-#define MX6Q_PAD_EIM_A21__IPU2_CSI1_DATA16        0x0e0 0x3f4 0x8c8 0x2 0x1
-#define MX6Q_PAD_EIM_A21__GPIO2_IO17              0x0e0 0x3f4 0x000 0x5 0x0
-#define MX6Q_PAD_EIM_A21__SRC_BOOT_CFG21          0x0e0 0x3f4 0x000 0x7 0x0
-#define MX6Q_PAD_EIM_A20__EIM_ADDR20              0x0e4 0x3f8 0x000 0x0 0x0
-#define MX6Q_PAD_EIM_A20__IPU1_DISP1_DATA15       0x0e4 0x3f8 0x000 0x1 0x0
-#define MX6Q_PAD_EIM_A20__IPU2_CSI1_DATA15        0x0e4 0x3f8 0x8c4 0x2 0x1
-#define MX6Q_PAD_EIM_A20__GPIO2_IO18              0x0e4 0x3f8 0x000 0x5 0x0
-#define MX6Q_PAD_EIM_A20__SRC_BOOT_CFG20          0x0e4 0x3f8 0x000 0x7 0x0
-#define MX6Q_PAD_EIM_A19__EIM_ADDR19              0x0e8 0x3fc 0x000 0x0 0x0
-#define MX6Q_PAD_EIM_A19__IPU1_DISP1_DATA14       0x0e8 0x3fc 0x000 0x1 0x0
-#define MX6Q_PAD_EIM_A19__IPU2_CSI1_DATA14        0x0e8 0x3fc 0x8c0 0x2 0x1
-#define MX6Q_PAD_EIM_A19__GPIO2_IO19              0x0e8 0x3fc 0x000 0x5 0x0
-#define MX6Q_PAD_EIM_A19__SRC_BOOT_CFG19          0x0e8 0x3fc 0x000 0x7 0x0
-#define MX6Q_PAD_EIM_A18__EIM_ADDR18              0x0ec 0x400 0x000 0x0 0x0
-#define MX6Q_PAD_EIM_A18__IPU1_DISP1_DATA13       0x0ec 0x400 0x000 0x1 0x0
-#define MX6Q_PAD_EIM_A18__IPU2_CSI1_DATA13        0x0ec 0x400 0x8bc 0x2 0x1
-#define MX6Q_PAD_EIM_A18__GPIO2_IO20              0x0ec 0x400 0x000 0x5 0x0
-#define MX6Q_PAD_EIM_A18__SRC_BOOT_CFG18          0x0ec 0x400 0x000 0x7 0x0
-#define MX6Q_PAD_EIM_A17__EIM_ADDR17              0x0f0 0x404 0x000 0x0 0x0
-#define MX6Q_PAD_EIM_A17__IPU1_DISP1_DATA12       0x0f0 0x404 0x000 0x1 0x0
-#define MX6Q_PAD_EIM_A17__IPU2_CSI1_DATA12        0x0f0 0x404 0x8b8 0x2 0x1
-#define MX6Q_PAD_EIM_A17__GPIO2_IO21              0x0f0 0x404 0x000 0x5 0x0
-#define MX6Q_PAD_EIM_A17__SRC_BOOT_CFG17          0x0f0 0x404 0x000 0x7 0x0
-#define MX6Q_PAD_EIM_A16__EIM_ADDR16              0x0f4 0x408 0x000 0x0 0x0
-#define MX6Q_PAD_EIM_A16__IPU1_DI1_DISP_CLK       0x0f4 0x408 0x000 0x1 0x0
-#define MX6Q_PAD_EIM_A16__IPU2_CSI1_PIXCLK        0x0f4 0x408 0x8e0 0x2 0x1
-#define MX6Q_PAD_EIM_A16__GPIO2_IO22              0x0f4 0x408 0x000 0x5 0x0
-#define MX6Q_PAD_EIM_A16__SRC_BOOT_CFG16          0x0f4 0x408 0x000 0x7 0x0
-#define MX6Q_PAD_EIM_CS0__EIM_CS0_B               0x0f8 0x40c 0x000 0x0 0x0
-#define MX6Q_PAD_EIM_CS0__IPU1_DI1_PIN05          0x0f8 0x40c 0x000 0x1 0x0
-#define MX6Q_PAD_EIM_CS0__ECSPI2_SCLK             0x0f8 0x40c 0x810 0x2 0x0
-#define MX6Q_PAD_EIM_CS0__GPIO2_IO23              0x0f8 0x40c 0x000 0x5 0x0
-#define MX6Q_PAD_EIM_CS1__EIM_CS1_B               0x0fc 0x410 0x000 0x0 0x0
-#define MX6Q_PAD_EIM_CS1__IPU1_DI1_PIN06          0x0fc 0x410 0x000 0x1 0x0
-#define MX6Q_PAD_EIM_CS1__ECSPI2_MOSI             0x0fc 0x410 0x818 0x2 0x0
-#define MX6Q_PAD_EIM_CS1__GPIO2_IO24              0x0fc 0x410 0x000 0x5 0x0
-#define MX6Q_PAD_EIM_OE__EIM_OE_B                 0x100 0x414 0x000 0x0 0x0
-#define MX6Q_PAD_EIM_OE__IPU1_DI1_PIN07           0x100 0x414 0x000 0x1 0x0
-#define MX6Q_PAD_EIM_OE__ECSPI2_MISO              0x100 0x414 0x814 0x2 0x0
-#define MX6Q_PAD_EIM_OE__GPIO2_IO25               0x100 0x414 0x000 0x5 0x0
-#define MX6Q_PAD_EIM_RW__EIM_RW                   0x104 0x418 0x000 0x0 0x0
-#define MX6Q_PAD_EIM_RW__IPU1_DI1_PIN08           0x104 0x418 0x000 0x1 0x0
-#define MX6Q_PAD_EIM_RW__ECSPI2_SS0               0x104 0x418 0x81c 0x2 0x0
-#define MX6Q_PAD_EIM_RW__GPIO2_IO26               0x104 0x418 0x000 0x5 0x0
-#define MX6Q_PAD_EIM_RW__SRC_BOOT_CFG29           0x104 0x418 0x000 0x7 0x0
-#define MX6Q_PAD_EIM_LBA__EIM_LBA_B               0x108 0x41c 0x000 0x0 0x0
-#define MX6Q_PAD_EIM_LBA__IPU1_DI1_PIN17          0x108 0x41c 0x000 0x1 0x0
-#define MX6Q_PAD_EIM_LBA__ECSPI2_SS1              0x108 0x41c 0x820 0x2 0x0
-#define MX6Q_PAD_EIM_LBA__GPIO2_IO27              0x108 0x41c 0x000 0x5 0x0
-#define MX6Q_PAD_EIM_LBA__SRC_BOOT_CFG26          0x108 0x41c 0x000 0x7 0x0
-#define MX6Q_PAD_EIM_EB0__EIM_EB0_B               0x10c 0x420 0x000 0x0 0x0
-#define MX6Q_PAD_EIM_EB0__IPU1_DISP1_DATA11       0x10c 0x420 0x000 0x1 0x0
-#define MX6Q_PAD_EIM_EB0__IPU2_CSI1_DATA11        0x10c 0x420 0x8b4 0x2 0x1
-#define MX6Q_PAD_EIM_EB0__CCM_PMIC_READY          0x10c 0x420 0x7f0 0x4 0x0
-#define MX6Q_PAD_EIM_EB0__GPIO2_IO28              0x10c 0x420 0x000 0x5 0x0
-#define MX6Q_PAD_EIM_EB0__SRC_BOOT_CFG27          0x10c 0x420 0x000 0x7 0x0
-#define MX6Q_PAD_EIM_EB1__EIM_EB1_B               0x110 0x424 0x000 0x0 0x0
-#define MX6Q_PAD_EIM_EB1__IPU1_DISP1_DATA10       0x110 0x424 0x000 0x1 0x0
-#define MX6Q_PAD_EIM_EB1__IPU2_CSI1_DATA10        0x110 0x424 0x8b0 0x2 0x1
-#define MX6Q_PAD_EIM_EB1__GPIO2_IO29              0x110 0x424 0x000 0x5 0x0
-#define MX6Q_PAD_EIM_EB1__SRC_BOOT_CFG28          0x110 0x424 0x000 0x7 0x0
-#define MX6Q_PAD_EIM_DA0__EIM_AD00                0x114 0x428 0x000 0x0 0x0
-#define MX6Q_PAD_EIM_DA0__IPU1_DISP1_DATA09       0x114 0x428 0x000 0x1 0x0
-#define MX6Q_PAD_EIM_DA0__IPU2_CSI1_DATA09        0x114 0x428 0x000 0x2 0x0
-#define MX6Q_PAD_EIM_DA0__GPIO3_IO00              0x114 0x428 0x000 0x5 0x0
-#define MX6Q_PAD_EIM_DA0__SRC_BOOT_CFG00          0x114 0x428 0x000 0x7 0x0
-#define MX6Q_PAD_EIM_DA1__EIM_AD01                0x118 0x42c 0x000 0x0 0x0
-#define MX6Q_PAD_EIM_DA1__IPU1_DISP1_DATA08       0x118 0x42c 0x000 0x1 0x0
-#define MX6Q_PAD_EIM_DA1__IPU2_CSI1_DATA08        0x118 0x42c 0x000 0x2 0x0
-#define MX6Q_PAD_EIM_DA1__GPIO3_IO01              0x118 0x42c 0x000 0x5 0x0
-#define MX6Q_PAD_EIM_DA1__SRC_BOOT_CFG01          0x118 0x42c 0x000 0x7 0x0
-#define MX6Q_PAD_EIM_DA2__EIM_AD02                0x11c 0x430 0x000 0x0 0x0
-#define MX6Q_PAD_EIM_DA2__IPU1_DISP1_DATA07       0x11c 0x430 0x000 0x1 0x0
-#define MX6Q_PAD_EIM_DA2__IPU2_CSI1_DATA07        0x11c 0x430 0x000 0x2 0x0
-#define MX6Q_PAD_EIM_DA2__GPIO3_IO02              0x11c 0x430 0x000 0x5 0x0
-#define MX6Q_PAD_EIM_DA2__SRC_BOOT_CFG02          0x11c 0x430 0x000 0x7 0x0
-#define MX6Q_PAD_EIM_DA3__EIM_AD03                0x120 0x434 0x000 0x0 0x0
-#define MX6Q_PAD_EIM_DA3__IPU1_DISP1_DATA06       0x120 0x434 0x000 0x1 0x0
-#define MX6Q_PAD_EIM_DA3__IPU2_CSI1_DATA06        0x120 0x434 0x000 0x2 0x0
-#define MX6Q_PAD_EIM_DA3__GPIO3_IO03              0x120 0x434 0x000 0x5 0x0
-#define MX6Q_PAD_EIM_DA3__SRC_BOOT_CFG03          0x120 0x434 0x000 0x7 0x0
-#define MX6Q_PAD_EIM_DA4__EIM_AD04                0x124 0x438 0x000 0x0 0x0
-#define MX6Q_PAD_EIM_DA4__IPU1_DISP1_DATA05       0x124 0x438 0x000 0x1 0x0
-#define MX6Q_PAD_EIM_DA4__IPU2_CSI1_DATA05        0x124 0x438 0x000 0x2 0x0
-#define MX6Q_PAD_EIM_DA4__GPIO3_IO04              0x124 0x438 0x000 0x5 0x0
-#define MX6Q_PAD_EIM_DA4__SRC_BOOT_CFG04          0x124 0x438 0x000 0x7 0x0
-#define MX6Q_PAD_EIM_DA5__EIM_AD05                0x128 0x43c 0x000 0x0 0x0
-#define MX6Q_PAD_EIM_DA5__IPU1_DISP1_DATA04       0x128 0x43c 0x000 0x1 0x0
-#define MX6Q_PAD_EIM_DA5__IPU2_CSI1_DATA04        0x128 0x43c 0x000 0x2 0x0
-#define MX6Q_PAD_EIM_DA5__GPIO3_IO05              0x128 0x43c 0x000 0x5 0x0
-#define MX6Q_PAD_EIM_DA5__SRC_BOOT_CFG05          0x128 0x43c 0x000 0x7 0x0
-#define MX6Q_PAD_EIM_DA6__EIM_AD06                0x12c 0x440 0x000 0x0 0x0
-#define MX6Q_PAD_EIM_DA6__IPU1_DISP1_DATA03       0x12c 0x440 0x000 0x1 0x0
-#define MX6Q_PAD_EIM_DA6__IPU2_CSI1_DATA03        0x12c 0x440 0x000 0x2 0x0
-#define MX6Q_PAD_EIM_DA6__GPIO3_IO06              0x12c 0x440 0x000 0x5 0x0
-#define MX6Q_PAD_EIM_DA6__SRC_BOOT_CFG06          0x12c 0x440 0x000 0x7 0x0
-#define MX6Q_PAD_EIM_DA7__EIM_AD07                0x130 0x444 0x000 0x0 0x0
-#define MX6Q_PAD_EIM_DA7__IPU1_DISP1_DATA02       0x130 0x444 0x000 0x1 0x0
-#define MX6Q_PAD_EIM_DA7__IPU2_CSI1_DATA02        0x130 0x444 0x000 0x2 0x0
-#define MX6Q_PAD_EIM_DA7__GPIO3_IO07              0x130 0x444 0x000 0x5 0x0
-#define MX6Q_PAD_EIM_DA7__SRC_BOOT_CFG07          0x130 0x444 0x000 0x7 0x0
-#define MX6Q_PAD_EIM_DA8__EIM_AD08                0x134 0x448 0x000 0x0 0x0
-#define MX6Q_PAD_EIM_DA8__IPU1_DISP1_DATA01       0x134 0x448 0x000 0x1 0x0
-#define MX6Q_PAD_EIM_DA8__IPU2_CSI1_DATA01        0x134 0x448 0x000 0x2 0x0
-#define MX6Q_PAD_EIM_DA8__GPIO3_IO08              0x134 0x448 0x000 0x5 0x0
-#define MX6Q_PAD_EIM_DA8__SRC_BOOT_CFG08          0x134 0x448 0x000 0x7 0x0
-#define MX6Q_PAD_EIM_DA9__EIM_AD09                0x138 0x44c 0x000 0x0 0x0
-#define MX6Q_PAD_EIM_DA9__IPU1_DISP1_DATA00       0x138 0x44c 0x000 0x1 0x0
-#define MX6Q_PAD_EIM_DA9__IPU2_CSI1_DATA00        0x138 0x44c 0x000 0x2 0x0
-#define MX6Q_PAD_EIM_DA9__GPIO3_IO09              0x138 0x44c 0x000 0x5 0x0
-#define MX6Q_PAD_EIM_DA9__SRC_BOOT_CFG09          0x138 0x44c 0x000 0x7 0x0
-#define MX6Q_PAD_EIM_DA10__EIM_AD10               0x13c 0x450 0x000 0x0 0x0
-#define MX6Q_PAD_EIM_DA10__IPU1_DI1_PIN15         0x13c 0x450 0x000 0x1 0x0
-#define MX6Q_PAD_EIM_DA10__IPU2_CSI1_DATA_EN      0x13c 0x450 0x8d8 0x2 0x1
-#define MX6Q_PAD_EIM_DA10__GPIO3_IO10             0x13c 0x450 0x000 0x5 0x0
-#define MX6Q_PAD_EIM_DA10__SRC_BOOT_CFG10         0x13c 0x450 0x000 0x7 0x0
-#define MX6Q_PAD_EIM_DA11__EIM_AD11               0x140 0x454 0x000 0x0 0x0
-#define MX6Q_PAD_EIM_DA11__IPU1_DI1_PIN02         0x140 0x454 0x000 0x1 0x0
-#define MX6Q_PAD_EIM_DA11__IPU2_CSI1_HSYNC        0x140 0x454 0x8dc 0x2 0x1
-#define MX6Q_PAD_EIM_DA11__GPIO3_IO11             0x140 0x454 0x000 0x5 0x0
-#define MX6Q_PAD_EIM_DA11__SRC_BOOT_CFG11         0x140 0x454 0x000 0x7 0x0
-#define MX6Q_PAD_EIM_DA12__EIM_AD12               0x144 0x458 0x000 0x0 0x0
-#define MX6Q_PAD_EIM_DA12__IPU1_DI1_PIN03         0x144 0x458 0x000 0x1 0x0
-#define MX6Q_PAD_EIM_DA12__IPU2_CSI1_VSYNC        0x144 0x458 0x8e4 0x2 0x1
-#define MX6Q_PAD_EIM_DA12__GPIO3_IO12             0x144 0x458 0x000 0x5 0x0
-#define MX6Q_PAD_EIM_DA12__SRC_BOOT_CFG12         0x144 0x458 0x000 0x7 0x0
-#define MX6Q_PAD_EIM_DA13__EIM_AD13               0x148 0x45c 0x000 0x0 0x0
-#define MX6Q_PAD_EIM_DA13__IPU1_DI1_D0_CS         0x148 0x45c 0x000 0x1 0x0
-#define MX6Q_PAD_EIM_DA13__GPIO3_IO13             0x148 0x45c 0x000 0x5 0x0
-#define MX6Q_PAD_EIM_DA13__SRC_BOOT_CFG13         0x148 0x45c 0x000 0x7 0x0
-#define MX6Q_PAD_EIM_DA14__EIM_AD14               0x14c 0x460 0x000 0x0 0x0
-#define MX6Q_PAD_EIM_DA14__IPU1_DI1_D1_CS         0x14c 0x460 0x000 0x1 0x0
-#define MX6Q_PAD_EIM_DA14__GPIO3_IO14             0x14c 0x460 0x000 0x5 0x0
-#define MX6Q_PAD_EIM_DA14__SRC_BOOT_CFG14         0x14c 0x460 0x000 0x7 0x0
-#define MX6Q_PAD_EIM_DA15__EIM_AD15               0x150 0x464 0x000 0x0 0x0
-#define MX6Q_PAD_EIM_DA15__IPU1_DI1_PIN01         0x150 0x464 0x000 0x1 0x0
-#define MX6Q_PAD_EIM_DA15__IPU1_DI1_PIN04         0x150 0x464 0x000 0x2 0x0
-#define MX6Q_PAD_EIM_DA15__GPIO3_IO15             0x150 0x464 0x000 0x5 0x0
-#define MX6Q_PAD_EIM_DA15__SRC_BOOT_CFG15         0x150 0x464 0x000 0x7 0x0
-#define MX6Q_PAD_EIM_WAIT__EIM_WAIT_B             0x154 0x468 0x000 0x0 0x0
-#define MX6Q_PAD_EIM_WAIT__EIM_DTACK_B            0x154 0x468 0x000 0x1 0x0
-#define MX6Q_PAD_EIM_WAIT__GPIO5_IO00             0x154 0x468 0x000 0x5 0x0
-#define MX6Q_PAD_EIM_WAIT__SRC_BOOT_CFG25         0x154 0x468 0x000 0x7 0x0
-#define MX6Q_PAD_EIM_BCLK__EIM_BCLK               0x158 0x46c 0x000 0x0 0x0
-#define MX6Q_PAD_EIM_BCLK__IPU1_DI1_PIN16         0x158 0x46c 0x000 0x1 0x0
-#define MX6Q_PAD_EIM_BCLK__GPIO6_IO31             0x158 0x46c 0x000 0x5 0x0
-#define MX6Q_PAD_DI0_DISP_CLK__IPU1_DI0_DISP_CLK  0x15c 0x470 0x000 0x0 0x0
-#define MX6Q_PAD_DI0_DISP_CLK__IPU2_DI0_DISP_CLK  0x15c 0x470 0x000 0x1 0x0
-#define MX6Q_PAD_DI0_DISP_CLK__GPIO4_IO16         0x15c 0x470 0x000 0x5 0x0
-#define MX6Q_PAD_DI0_PIN15__IPU1_DI0_PIN15        0x160 0x474 0x000 0x0 0x0
-#define MX6Q_PAD_DI0_PIN15__IPU2_DI0_PIN15        0x160 0x474 0x000 0x1 0x0
-#define MX6Q_PAD_DI0_PIN15__AUD6_TXC              0x160 0x474 0x000 0x2 0x0
-#define MX6Q_PAD_DI0_PIN15__GPIO4_IO17            0x160 0x474 0x000 0x5 0x0
-#define MX6Q_PAD_DI0_PIN2__IPU1_DI0_PIN02         0x164 0x478 0x000 0x0 0x0
-#define MX6Q_PAD_DI0_PIN2__IPU2_DI0_PIN02         0x164 0x478 0x000 0x1 0x0
-#define MX6Q_PAD_DI0_PIN2__AUD6_TXD               0x164 0x478 0x000 0x2 0x0
-#define MX6Q_PAD_DI0_PIN2__GPIO4_IO18             0x164 0x478 0x000 0x5 0x0
-#define MX6Q_PAD_DI0_PIN3__IPU1_DI0_PIN03         0x168 0x47c 0x000 0x0 0x0
-#define MX6Q_PAD_DI0_PIN3__IPU2_DI0_PIN03         0x168 0x47c 0x000 0x1 0x0
-#define MX6Q_PAD_DI0_PIN3__AUD6_TXFS              0x168 0x47c 0x000 0x2 0x0
-#define MX6Q_PAD_DI0_PIN3__GPIO4_IO19             0x168 0x47c 0x000 0x5 0x0
-#define MX6Q_PAD_DI0_PIN4__IPU1_DI0_PIN04         0x16c 0x480 0x000 0x0 0x0
-#define MX6Q_PAD_DI0_PIN4__IPU2_DI0_PIN04         0x16c 0x480 0x000 0x1 0x0
-#define MX6Q_PAD_DI0_PIN4__AUD6_RXD               0x16c 0x480 0x000 0x2 0x0
-#define MX6Q_PAD_DI0_PIN4__SD1_WP                 0x16c 0x480 0x94c 0x3 0x0
-#define MX6Q_PAD_DI0_PIN4__GPIO4_IO20             0x16c 0x480 0x000 0x5 0x0
-#define MX6Q_PAD_DISP0_DAT0__IPU1_DISP0_DATA00    0x170 0x484 0x000 0x0 0x0
-#define MX6Q_PAD_DISP0_DAT0__IPU2_DISP0_DATA00    0x170 0x484 0x000 0x1 0x0
-#define MX6Q_PAD_DISP0_DAT0__ECSPI3_SCLK          0x170 0x484 0x000 0x2 0x0
-#define MX6Q_PAD_DISP0_DAT0__GPIO4_IO21           0x170 0x484 0x000 0x5 0x0
-#define MX6Q_PAD_DISP0_DAT1__IPU1_DISP0_DATA01    0x174 0x488 0x000 0x0 0x0
-#define MX6Q_PAD_DISP0_DAT1__IPU2_DISP0_DATA01    0x174 0x488 0x000 0x1 0x0
-#define MX6Q_PAD_DISP0_DAT1__ECSPI3_MOSI          0x174 0x488 0x000 0x2 0x0
-#define MX6Q_PAD_DISP0_DAT1__GPIO4_IO22           0x174 0x488 0x000 0x5 0x0
-#define MX6Q_PAD_DISP0_DAT2__IPU1_DISP0_DATA02    0x178 0x48c 0x000 0x0 0x0
-#define MX6Q_PAD_DISP0_DAT2__IPU2_DISP0_DATA02    0x178 0x48c 0x000 0x1 0x0
-#define MX6Q_PAD_DISP0_DAT2__ECSPI3_MISO          0x178 0x48c 0x000 0x2 0x0
-#define MX6Q_PAD_DISP0_DAT2__GPIO4_IO23           0x178 0x48c 0x000 0x5 0x0
-#define MX6Q_PAD_DISP0_DAT3__IPU1_DISP0_DATA03    0x17c 0x490 0x000 0x0 0x0
-#define MX6Q_PAD_DISP0_DAT3__IPU2_DISP0_DATA03    0x17c 0x490 0x000 0x1 0x0
-#define MX6Q_PAD_DISP0_DAT3__ECSPI3_SS0           0x17c 0x490 0x000 0x2 0x0
-#define MX6Q_PAD_DISP0_DAT3__GPIO4_IO24           0x17c 0x490 0x000 0x5 0x0
-#define MX6Q_PAD_DISP0_DAT4__IPU1_DISP0_DATA04    0x180 0x494 0x000 0x0 0x0
-#define MX6Q_PAD_DISP0_DAT4__IPU2_DISP0_DATA04    0x180 0x494 0x000 0x1 0x0
-#define MX6Q_PAD_DISP0_DAT4__ECSPI3_SS1           0x180 0x494 0x000 0x2 0x0
-#define MX6Q_PAD_DISP0_DAT4__GPIO4_IO25           0x180 0x494 0x000 0x5 0x0
-#define MX6Q_PAD_DISP0_DAT5__IPU1_DISP0_DATA05    0x184 0x498 0x000 0x0 0x0
-#define MX6Q_PAD_DISP0_DAT5__IPU2_DISP0_DATA05    0x184 0x498 0x000 0x1 0x0
-#define MX6Q_PAD_DISP0_DAT5__ECSPI3_SS2           0x184 0x498 0x000 0x2 0x0
-#define MX6Q_PAD_DISP0_DAT5__AUD6_RXFS            0x184 0x498 0x000 0x3 0x0
-#define MX6Q_PAD_DISP0_DAT5__GPIO4_IO26           0x184 0x498 0x000 0x5 0x0
-#define MX6Q_PAD_DISP0_DAT6__IPU1_DISP0_DATA06    0x188 0x49c 0x000 0x0 0x0
-#define MX6Q_PAD_DISP0_DAT6__IPU2_DISP0_DATA06    0x188 0x49c 0x000 0x1 0x0
-#define MX6Q_PAD_DISP0_DAT6__ECSPI3_SS3           0x188 0x49c 0x000 0x2 0x0
-#define MX6Q_PAD_DISP0_DAT6__AUD6_RXC             0x188 0x49c 0x000 0x3 0x0
-#define MX6Q_PAD_DISP0_DAT6__GPIO4_IO27           0x188 0x49c 0x000 0x5 0x0
-#define MX6Q_PAD_DISP0_DAT7__IPU1_DISP0_DATA07    0x18c 0x4a0 0x000 0x0 0x0
-#define MX6Q_PAD_DISP0_DAT7__IPU2_DISP0_DATA07    0x18c 0x4a0 0x000 0x1 0x0
-#define MX6Q_PAD_DISP0_DAT7__ECSPI3_RDY           0x18c 0x4a0 0x000 0x2 0x0
-#define MX6Q_PAD_DISP0_DAT7__GPIO4_IO28           0x18c 0x4a0 0x000 0x5 0x0
-#define MX6Q_PAD_DISP0_DAT8__IPU1_DISP0_DATA08    0x190 0x4a4 0x000 0x0 0x0
-#define MX6Q_PAD_DISP0_DAT8__IPU2_DISP0_DATA08    0x190 0x4a4 0x000 0x1 0x0
-#define MX6Q_PAD_DISP0_DAT8__PWM1_OUT             0x190 0x4a4 0x000 0x2 0x0
-#define MX6Q_PAD_DISP0_DAT8__WDOG1_B              0x190 0x4a4 0x000 0x3 0x0
-#define MX6Q_PAD_DISP0_DAT8__GPIO4_IO29           0x190 0x4a4 0x000 0x5 0x0
-#define MX6Q_PAD_DISP0_DAT9__IPU1_DISP0_DATA09    0x194 0x4a8 0x000 0x0 0x0
-#define MX6Q_PAD_DISP0_DAT9__IPU2_DISP0_DATA09    0x194 0x4a8 0x000 0x1 0x0
-#define MX6Q_PAD_DISP0_DAT9__PWM2_OUT             0x194 0x4a8 0x000 0x2 0x0
-#define MX6Q_PAD_DISP0_DAT9__WDOG2_B              0x194 0x4a8 0x000 0x3 0x0
-#define MX6Q_PAD_DISP0_DAT9__GPIO4_IO30           0x194 0x4a8 0x000 0x5 0x0
-#define MX6Q_PAD_DISP0_DAT10__IPU1_DISP0_DATA10   0x198 0x4ac 0x000 0x0 0x0
-#define MX6Q_PAD_DISP0_DAT10__IPU2_DISP0_DATA10   0x198 0x4ac 0x000 0x1 0x0
-#define MX6Q_PAD_DISP0_DAT10__GPIO4_IO31          0x198 0x4ac 0x000 0x5 0x0
-#define MX6Q_PAD_DISP0_DAT11__IPU1_DISP0_DATA11   0x19c 0x4b0 0x000 0x0 0x0
-#define MX6Q_PAD_DISP0_DAT11__IPU2_DISP0_DATA11   0x19c 0x4b0 0x000 0x1 0x0
-#define MX6Q_PAD_DISP0_DAT11__GPIO5_IO05          0x19c 0x4b0 0x000 0x5 0x0
-#define MX6Q_PAD_DISP0_DAT12__IPU1_DISP0_DATA12   0x1a0 0x4b4 0x000 0x0 0x0
-#define MX6Q_PAD_DISP0_DAT12__IPU2_DISP0_DATA12   0x1a0 0x4b4 0x000 0x1 0x0
-#define MX6Q_PAD_DISP0_DAT12__GPIO5_IO06          0x1a0 0x4b4 0x000 0x5 0x0
-#define MX6Q_PAD_DISP0_DAT13__IPU1_DISP0_DATA13   0x1a4 0x4b8 0x000 0x0 0x0
-#define MX6Q_PAD_DISP0_DAT13__IPU2_DISP0_DATA13   0x1a4 0x4b8 0x000 0x1 0x0
-#define MX6Q_PAD_DISP0_DAT13__AUD5_RXFS           0x1a4 0x4b8 0x7d8 0x3 0x1
-#define MX6Q_PAD_DISP0_DAT13__GPIO5_IO07          0x1a4 0x4b8 0x000 0x5 0x0
-#define MX6Q_PAD_DISP0_DAT14__IPU1_DISP0_DATA14   0x1a8 0x4bc 0x000 0x0 0x0
-#define MX6Q_PAD_DISP0_DAT14__IPU2_DISP0_DATA14   0x1a8 0x4bc 0x000 0x1 0x0
-#define MX6Q_PAD_DISP0_DAT14__AUD5_RXC            0x1a8 0x4bc 0x7d4 0x3 0x1
-#define MX6Q_PAD_DISP0_DAT14__GPIO5_IO08          0x1a8 0x4bc 0x000 0x5 0x0
-#define MX6Q_PAD_DISP0_DAT15__IPU1_DISP0_DATA15   0x1ac 0x4c0 0x000 0x0 0x0
-#define MX6Q_PAD_DISP0_DAT15__IPU2_DISP0_DATA15   0x1ac 0x4c0 0x000 0x1 0x0
-#define MX6Q_PAD_DISP0_DAT15__ECSPI1_SS1          0x1ac 0x4c0 0x804 0x2 0x1
-#define MX6Q_PAD_DISP0_DAT15__ECSPI2_SS1          0x1ac 0x4c0 0x820 0x3 0x1
-#define MX6Q_PAD_DISP0_DAT15__GPIO5_IO09          0x1ac 0x4c0 0x000 0x5 0x0
-#define MX6Q_PAD_DISP0_DAT16__IPU1_DISP0_DATA16   0x1b0 0x4c4 0x000 0x0 0x0
-#define MX6Q_PAD_DISP0_DAT16__IPU2_DISP0_DATA16   0x1b0 0x4c4 0x000 0x1 0x0
-#define MX6Q_PAD_DISP0_DAT16__ECSPI2_MOSI         0x1b0 0x4c4 0x818 0x2 0x1
-#define MX6Q_PAD_DISP0_DAT16__AUD5_TXC            0x1b0 0x4c4 0x7dc 0x3 0x0
-#define MX6Q_PAD_DISP0_DAT16__SDMA_EXT_EVENT0     0x1b0 0x4c4 0x90c 0x4 0x0
-#define MX6Q_PAD_DISP0_DAT16__GPIO5_IO10          0x1b0 0x4c4 0x000 0x5 0x0
-#define MX6Q_PAD_DISP0_DAT17__IPU1_DISP0_DATA17   0x1b4 0x4c8 0x000 0x0 0x0
-#define MX6Q_PAD_DISP0_DAT17__IPU2_DISP0_DATA17   0x1b4 0x4c8 0x000 0x1 0x0
-#define MX6Q_PAD_DISP0_DAT17__ECSPI2_MISO         0x1b4 0x4c8 0x814 0x2 0x1
-#define MX6Q_PAD_DISP0_DAT17__AUD5_TXD            0x1b4 0x4c8 0x7d0 0x3 0x0
-#define MX6Q_PAD_DISP0_DAT17__SDMA_EXT_EVENT1     0x1b4 0x4c8 0x910 0x4 0x0
-#define MX6Q_PAD_DISP0_DAT17__GPIO5_IO11          0x1b4 0x4c8 0x000 0x5 0x0
-#define MX6Q_PAD_DISP0_DAT18__IPU1_DISP0_DATA18   0x1b8 0x4cc 0x000 0x0 0x0
-#define MX6Q_PAD_DISP0_DAT18__IPU2_DISP0_DATA18   0x1b8 0x4cc 0x000 0x1 0x0
-#define MX6Q_PAD_DISP0_DAT18__ECSPI2_SS0          0x1b8 0x4cc 0x81c 0x2 0x1
-#define MX6Q_PAD_DISP0_DAT18__AUD5_TXFS           0x1b8 0x4cc 0x7e0 0x3 0x0
-#define MX6Q_PAD_DISP0_DAT18__AUD4_RXFS           0x1b8 0x4cc 0x7c0 0x4 0x0
-#define MX6Q_PAD_DISP0_DAT18__GPIO5_IO12          0x1b8 0x4cc 0x000 0x5 0x0
-#define MX6Q_PAD_DISP0_DAT18__EIM_CS2_B           0x1b8 0x4cc 0x000 0x7 0x0
-#define MX6Q_PAD_DISP0_DAT19__IPU1_DISP0_DATA19   0x1bc 0x4d0 0x000 0x0 0x0
-#define MX6Q_PAD_DISP0_DAT19__IPU2_DISP0_DATA19   0x1bc 0x4d0 0x000 0x1 0x0
-#define MX6Q_PAD_DISP0_DAT19__ECSPI2_SCLK         0x1bc 0x4d0 0x810 0x2 0x1
-#define MX6Q_PAD_DISP0_DAT19__AUD5_RXD            0x1bc 0x4d0 0x7cc 0x3 0x0
-#define MX6Q_PAD_DISP0_DAT19__AUD4_RXC            0x1bc 0x4d0 0x7bc 0x4 0x0
-#define MX6Q_PAD_DISP0_DAT19__GPIO5_IO13          0x1bc 0x4d0 0x000 0x5 0x0
-#define MX6Q_PAD_DISP0_DAT19__EIM_CS3_B           0x1bc 0x4d0 0x000 0x7 0x0
-#define MX6Q_PAD_DISP0_DAT20__IPU1_DISP0_DATA20   0x1c0 0x4d4 0x000 0x0 0x0
-#define MX6Q_PAD_DISP0_DAT20__IPU2_DISP0_DATA20   0x1c0 0x4d4 0x000 0x1 0x0
-#define MX6Q_PAD_DISP0_DAT20__ECSPI1_SCLK         0x1c0 0x4d4 0x7f4 0x2 0x1
-#define MX6Q_PAD_DISP0_DAT20__AUD4_TXC            0x1c0 0x4d4 0x7c4 0x3 0x0
-#define MX6Q_PAD_DISP0_DAT20__GPIO5_IO14          0x1c0 0x4d4 0x000 0x5 0x0
-#define MX6Q_PAD_DISP0_DAT21__IPU1_DISP0_DATA21   0x1c4 0x4d8 0x000 0x0 0x0
-#define MX6Q_PAD_DISP0_DAT21__IPU2_DISP0_DATA21   0x1c4 0x4d8 0x000 0x1 0x0
-#define MX6Q_PAD_DISP0_DAT21__ECSPI1_MOSI         0x1c4 0x4d8 0x7fc 0x2 0x1
-#define MX6Q_PAD_DISP0_DAT21__AUD4_TXD            0x1c4 0x4d8 0x7b8 0x3 0x1
-#define MX6Q_PAD_DISP0_DAT21__GPIO5_IO15          0x1c4 0x4d8 0x000 0x5 0x0
-#define MX6Q_PAD_DISP0_DAT22__IPU1_DISP0_DATA22   0x1c8 0x4dc 0x000 0x0 0x0
-#define MX6Q_PAD_DISP0_DAT22__IPU2_DISP0_DATA22   0x1c8 0x4dc 0x000 0x1 0x0
-#define MX6Q_PAD_DISP0_DAT22__ECSPI1_MISO         0x1c8 0x4dc 0x7f8 0x2 0x1
-#define MX6Q_PAD_DISP0_DAT22__AUD4_TXFS           0x1c8 0x4dc 0x7c8 0x3 0x1
-#define MX6Q_PAD_DISP0_DAT22__GPIO5_IO16          0x1c8 0x4dc 0x000 0x5 0x0
-#define MX6Q_PAD_DISP0_DAT23__IPU1_DISP0_DATA23   0x1cc 0x4e0 0x000 0x0 0x0
-#define MX6Q_PAD_DISP0_DAT23__IPU2_DISP0_DATA23   0x1cc 0x4e0 0x000 0x1 0x0
-#define MX6Q_PAD_DISP0_DAT23__ECSPI1_SS0          0x1cc 0x4e0 0x800 0x2 0x1
-#define MX6Q_PAD_DISP0_DAT23__AUD4_RXD            0x1cc 0x4e0 0x7b4 0x3 0x1
-#define MX6Q_PAD_DISP0_DAT23__GPIO5_IO17          0x1cc 0x4e0 0x000 0x5 0x0
-#define MX6Q_PAD_ENET_MDIO__ENET_MDIO             0x1d0 0x4e4 0x840 0x1 0x0
-#define MX6Q_PAD_ENET_MDIO__ESAI_RX_CLK           0x1d0 0x4e4 0x86c 0x2 0x0
-#define MX6Q_PAD_ENET_MDIO__ENET_1588_EVENT1_OUT  0x1d0 0x4e4 0x000 0x4 0x0
-#define MX6Q_PAD_ENET_MDIO__GPIO1_IO22            0x1d0 0x4e4 0x000 0x5 0x0
-#define MX6Q_PAD_ENET_MDIO__SPDIF_LOCK            0x1d0 0x4e4 0x000 0x6 0x0
-#define MX6Q_PAD_ENET_REF_CLK__ENET_TX_CLK        0x1d4 0x4e8 0x000 0x1 0x0
-#define MX6Q_PAD_ENET_REF_CLK__ESAI_RX_FS         0x1d4 0x4e8 0x85c 0x2 0x0
-#define MX6Q_PAD_ENET_REF_CLK__GPIO1_IO23         0x1d4 0x4e8 0x000 0x5 0x0
-#define MX6Q_PAD_ENET_REF_CLK__SPDIF_SR_CLK       0x1d4 0x4e8 0x000 0x6 0x0
-#define MX6Q_PAD_ENET_RX_ER__USB_OTG_ID           0x1d8 0x4ec 0x000 0x0 0x0
-#define MX6Q_PAD_ENET_RX_ER__ENET_RX_ER           0x1d8 0x4ec 0x000 0x1 0x0
-#define MX6Q_PAD_ENET_RX_ER__ESAI_RX_HF_CLK       0x1d8 0x4ec 0x864 0x2 0x0
-#define MX6Q_PAD_ENET_RX_ER__SPDIF_IN             0x1d8 0x4ec 0x914 0x3 0x1
-#define MX6Q_PAD_ENET_RX_ER__ENET_1588_EVENT2_OUT 0x1d8 0x4ec 0x000 0x4 0x0
-#define MX6Q_PAD_ENET_RX_ER__GPIO1_IO24           0x1d8 0x4ec 0x000 0x5 0x0
-#define MX6Q_PAD_ENET_CRS_DV__ENET_RX_EN          0x1dc 0x4f0 0x858 0x1 0x1
-#define MX6Q_PAD_ENET_CRS_DV__ESAI_TX_CLK         0x1dc 0x4f0 0x870 0x2 0x0
-#define MX6Q_PAD_ENET_CRS_DV__SPDIF_EXT_CLK       0x1dc 0x4f0 0x918 0x3 0x1
-#define MX6Q_PAD_ENET_CRS_DV__GPIO1_IO25          0x1dc 0x4f0 0x000 0x5 0x0
-#define MX6Q_PAD_ENET_RXD1__MLB_SIG               0x1e0 0x4f4 0x908 0x0 0x0
-#define MX6Q_PAD_ENET_RXD1__ENET_RX_DATA1         0x1e0 0x4f4 0x84c 0x1 0x1
-#define MX6Q_PAD_ENET_RXD1__ESAI_TX_FS            0x1e0 0x4f4 0x860 0x2 0x0
-#define MX6Q_PAD_ENET_RXD1__ENET_1588_EVENT3_OUT  0x1e0 0x4f4 0x000 0x4 0x0
-#define MX6Q_PAD_ENET_RXD1__GPIO1_IO26            0x1e0 0x4f4 0x000 0x5 0x0
-#define MX6Q_PAD_ENET_RXD0__ENET_RX_DATA0         0x1e4 0x4f8 0x848 0x1 0x1
-#define MX6Q_PAD_ENET_RXD0__ESAI_TX_HF_CLK        0x1e4 0x4f8 0x868 0x2 0x0
-#define MX6Q_PAD_ENET_RXD0__SPDIF_OUT             0x1e4 0x4f8 0x000 0x3 0x0
-#define MX6Q_PAD_ENET_RXD0__GPIO1_IO27            0x1e4 0x4f8 0x000 0x5 0x0
-#define MX6Q_PAD_ENET_TX_EN__ENET_TX_EN           0x1e8 0x4fc 0x000 0x1 0x0
-#define MX6Q_PAD_ENET_TX_EN__ESAI_TX3_RX2         0x1e8 0x4fc 0x880 0x2 0x0
-#define MX6Q_PAD_ENET_TX_EN__GPIO1_IO28           0x1e8 0x4fc 0x000 0x5 0x0
-#define MX6Q_PAD_ENET_TXD1__MLB_CLK               0x1ec 0x500 0x900 0x0 0x0
-#define MX6Q_PAD_ENET_TXD1__ENET_TX_DATA1         0x1ec 0x500 0x000 0x1 0x0
-#define MX6Q_PAD_ENET_TXD1__ESAI_TX2_RX3          0x1ec 0x500 0x87c 0x2 0x0
-#define MX6Q_PAD_ENET_TXD1__ENET_1588_EVENT0_IN   0x1ec 0x500 0x000 0x4 0x0
-#define MX6Q_PAD_ENET_TXD1__GPIO1_IO29            0x1ec 0x500 0x000 0x5 0x0
-#define MX6Q_PAD_ENET_TXD0__ENET_TX_DATA0         0x1f0 0x504 0x000 0x1 0x0
-#define MX6Q_PAD_ENET_TXD0__ESAI_TX4_RX1          0x1f0 0x504 0x884 0x2 0x0
-#define MX6Q_PAD_ENET_TXD0__GPIO1_IO30            0x1f0 0x504 0x000 0x5 0x0
-#define MX6Q_PAD_ENET_MDC__MLB_DATA               0x1f4 0x508 0x904 0x0 0x0
-#define MX6Q_PAD_ENET_MDC__ENET_MDC               0x1f4 0x508 0x000 0x1 0x0
-#define MX6Q_PAD_ENET_MDC__ESAI_TX5_RX0           0x1f4 0x508 0x888 0x2 0x0
-#define MX6Q_PAD_ENET_MDC__ENET_1588_EVENT1_IN    0x1f4 0x508 0x000 0x4 0x0
-#define MX6Q_PAD_ENET_MDC__GPIO1_IO31             0x1f4 0x508 0x000 0x5 0x0
-#define MX6Q_PAD_KEY_COL0__ECSPI1_SCLK            0x1f8 0x5c8 0x7f4 0x0 0x2
-#define MX6Q_PAD_KEY_COL0__ENET_RX_DATA3          0x1f8 0x5c8 0x854 0x1 0x1
-#define MX6Q_PAD_KEY_COL0__AUD5_TXC               0x1f8 0x5c8 0x7dc 0x2 0x1
-#define MX6Q_PAD_KEY_COL0__KEY_COL0               0x1f8 0x5c8 0x000 0x3 0x0
-#define MX6Q_PAD_KEY_COL0__UART4_TX_DATA          0x1f8 0x5c8 0x000 0x4 0x0
-#define MX6Q_PAD_KEY_COL0__UART4_RX_DATA          0x1f8 0x5c8 0x938 0x4 0x0
-#define MX6Q_PAD_KEY_COL0__GPIO4_IO06             0x1f8 0x5c8 0x000 0x5 0x0
-#define MX6Q_PAD_KEY_COL0__DCIC1_OUT              0x1f8 0x5c8 0x000 0x6 0x0
-#define MX6Q_PAD_KEY_ROW0__ECSPI1_MOSI            0x1fc 0x5cc 0x7fc 0x0 0x2
-#define MX6Q_PAD_KEY_ROW0__ENET_TX_DATA3          0x1fc 0x5cc 0x000 0x1 0x0
-#define MX6Q_PAD_KEY_ROW0__AUD5_TXD               0x1fc 0x5cc 0x7d0 0x2 0x1
-#define MX6Q_PAD_KEY_ROW0__KEY_ROW0               0x1fc 0x5cc 0x000 0x3 0x0
-#define MX6Q_PAD_KEY_ROW0__UART4_RX_DATA          0x1fc 0x5cc 0x938 0x4 0x1
-#define MX6Q_PAD_KEY_ROW0__UART4_TX_DATA          0x1fc 0x5cc 0x000 0x4 0x0
-#define MX6Q_PAD_KEY_ROW0__GPIO4_IO07             0x1fc 0x5cc 0x000 0x5 0x0
-#define MX6Q_PAD_KEY_ROW0__DCIC2_OUT              0x1fc 0x5cc 0x000 0x6 0x0
-#define MX6Q_PAD_KEY_COL1__ECSPI1_MISO            0x200 0x5d0 0x7f8 0x0 0x2
-#define MX6Q_PAD_KEY_COL1__ENET_MDIO              0x200 0x5d0 0x840 0x1 0x1
-#define MX6Q_PAD_KEY_COL1__AUD5_TXFS              0x200 0x5d0 0x7e0 0x2 0x1
-#define MX6Q_PAD_KEY_COL1__KEY_COL1               0x200 0x5d0 0x000 0x3 0x0
-#define MX6Q_PAD_KEY_COL1__UART5_TX_DATA          0x200 0x5d0 0x000 0x4 0x0
-#define MX6Q_PAD_KEY_COL1__UART5_RX_DATA          0x200 0x5d0 0x940 0x4 0x0
-#define MX6Q_PAD_KEY_COL1__GPIO4_IO08             0x200 0x5d0 0x000 0x5 0x0
-#define MX6Q_PAD_KEY_COL1__SD1_VSELECT            0x200 0x5d0 0x000 0x6 0x0
-#define MX6Q_PAD_KEY_ROW1__ECSPI1_SS0             0x204 0x5d4 0x800 0x0 0x2
-#define MX6Q_PAD_KEY_ROW1__ENET_COL               0x204 0x5d4 0x000 0x1 0x0
-#define MX6Q_PAD_KEY_ROW1__AUD5_RXD               0x204 0x5d4 0x7cc 0x2 0x1
-#define MX6Q_PAD_KEY_ROW1__KEY_ROW1               0x204 0x5d4 0x000 0x3 0x0
-#define MX6Q_PAD_KEY_ROW1__UART5_RX_DATA          0x204 0x5d4 0x940 0x4 0x1
-#define MX6Q_PAD_KEY_ROW1__UART5_TX_DATA          0x204 0x5d4 0x000 0x4 0x0
-#define MX6Q_PAD_KEY_ROW1__GPIO4_IO09             0x204 0x5d4 0x000 0x5 0x0
-#define MX6Q_PAD_KEY_ROW1__SD2_VSELECT            0x204 0x5d4 0x000 0x6 0x0
-#define MX6Q_PAD_KEY_COL2__ECSPI1_SS1             0x208 0x5d8 0x804 0x0 0x2
-#define MX6Q_PAD_KEY_COL2__ENET_RX_DATA2          0x208 0x5d8 0x850 0x1 0x1
-#define MX6Q_PAD_KEY_COL2__FLEXCAN1_TX            0x208 0x5d8 0x000 0x2 0x0
-#define MX6Q_PAD_KEY_COL2__KEY_COL2               0x208 0x5d8 0x000 0x3 0x0
-#define MX6Q_PAD_KEY_COL2__ENET_MDC               0x208 0x5d8 0x000 0x4 0x0
-#define MX6Q_PAD_KEY_COL2__GPIO4_IO10             0x208 0x5d8 0x000 0x5 0x0
-#define MX6Q_PAD_KEY_COL2__USB_H1_PWR_CTL_WAKE    0x208 0x5d8 0x000 0x6 0x0
-#define MX6Q_PAD_KEY_ROW2__ECSPI1_SS2             0x20c 0x5dc 0x808 0x0 0x1
-#define MX6Q_PAD_KEY_ROW2__ENET_TX_DATA2          0x20c 0x5dc 0x000 0x1 0x0
-#define MX6Q_PAD_KEY_ROW2__FLEXCAN1_RX            0x20c 0x5dc 0x7e4 0x2 0x0
-#define MX6Q_PAD_KEY_ROW2__KEY_ROW2               0x20c 0x5dc 0x000 0x3 0x0
-#define MX6Q_PAD_KEY_ROW2__SD2_VSELECT            0x20c 0x5dc 0x000 0x4 0x0
-#define MX6Q_PAD_KEY_ROW2__GPIO4_IO11             0x20c 0x5dc 0x000 0x5 0x0
-#define MX6Q_PAD_KEY_ROW2__HDMI_TX_CEC_LINE       0x20c 0x5dc 0x88c 0x6 0x1
-#define MX6Q_PAD_KEY_COL3__ECSPI1_SS3             0x210 0x5e0 0x80c 0x0 0x1
-#define MX6Q_PAD_KEY_COL3__ENET_CRS               0x210 0x5e0 0x000 0x1 0x0
-#define MX6Q_PAD_KEY_COL3__HDMI_TX_DDC_SCL        0x210 0x5e0 0x890 0x2 0x1
-#define MX6Q_PAD_KEY_COL3__KEY_COL3               0x210 0x5e0 0x000 0x3 0x0
-#define MX6Q_PAD_KEY_COL3__I2C2_SCL               0x210 0x5e0 0x8a0 0x4 0x1
-#define MX6Q_PAD_KEY_COL3__GPIO4_IO12             0x210 0x5e0 0x000 0x5 0x0
-#define MX6Q_PAD_KEY_COL3__SPDIF_IN               0x210 0x5e0 0x914 0x6 0x2
-#define MX6Q_PAD_KEY_ROW3__ASRC_EXT_CLK           0x214 0x5e4 0x7b0 0x1 0x0
-#define MX6Q_PAD_KEY_ROW3__HDMI_TX_DDC_SDA        0x214 0x5e4 0x894 0x2 0x1
-#define MX6Q_PAD_KEY_ROW3__KEY_ROW3               0x214 0x5e4 0x000 0x3 0x0
-#define MX6Q_PAD_KEY_ROW3__I2C2_SDA               0x214 0x5e4 0x8a4 0x4 0x1
-#define MX6Q_PAD_KEY_ROW3__GPIO4_IO13             0x214 0x5e4 0x000 0x5 0x0
-#define MX6Q_PAD_KEY_ROW3__SD1_VSELECT            0x214 0x5e4 0x000 0x6 0x0
-#define MX6Q_PAD_KEY_COL4__FLEXCAN2_TX            0x218 0x5e8 0x000 0x0 0x0
-#define MX6Q_PAD_KEY_COL4__IPU1_SISG4             0x218 0x5e8 0x000 0x1 0x0
-#define MX6Q_PAD_KEY_COL4__USB_OTG_OC             0x218 0x5e8 0x944 0x2 0x1
-#define MX6Q_PAD_KEY_COL4__KEY_COL4               0x218 0x5e8 0x000 0x3 0x0
-#define MX6Q_PAD_KEY_COL4__UART5_RTS_B            0x218 0x5e8 0x93c 0x4 0x0
-#define MX6Q_PAD_KEY_COL4__UART5_CTS_B            0x218 0x5e8 0x000 0x4 0x0
-#define MX6Q_PAD_KEY_COL4__GPIO4_IO14             0x218 0x5e8 0x000 0x5 0x0
-#define MX6Q_PAD_KEY_ROW4__FLEXCAN2_RX            0x21c 0x5ec 0x7e8 0x0 0x0
-#define MX6Q_PAD_KEY_ROW4__IPU1_SISG5             0x21c 0x5ec 0x000 0x1 0x0
-#define MX6Q_PAD_KEY_ROW4__USB_OTG_PWR            0x21c 0x5ec 0x000 0x2 0x0
-#define MX6Q_PAD_KEY_ROW4__KEY_ROW4               0x21c 0x5ec 0x000 0x3 0x0
-#define MX6Q_PAD_KEY_ROW4__UART5_CTS_B            0x21c 0x5ec 0x000 0x4 0x0
-#define MX6Q_PAD_KEY_ROW4__UART5_RTS_B            0x21c 0x5ec 0x93c 0x4 0x1
-#define MX6Q_PAD_KEY_ROW4__GPIO4_IO15             0x21c 0x5ec 0x000 0x5 0x0
-#define MX6Q_PAD_GPIO_0__CCM_CLKO1                0x220 0x5f0 0x000 0x0 0x0
-#define MX6Q_PAD_GPIO_0__KEY_COL5                 0x220 0x5f0 0x8e8 0x2 0x0
-#define MX6Q_PAD_GPIO_0__ASRC_EXT_CLK             0x220 0x5f0 0x7b0 0x3 0x1
-#define MX6Q_PAD_GPIO_0__EPIT1_OUT                0x220 0x5f0 0x000 0x4 0x0
-#define MX6Q_PAD_GPIO_0__GPIO1_IO00               0x220 0x5f0 0x000 0x5 0x0
-#define MX6Q_PAD_GPIO_0__USB_H1_PWR               0x220 0x5f0 0x000 0x6 0x0
-#define MX6Q_PAD_GPIO_0__SNVS_VIO_5               0x220 0x5f0 0x000 0x7 0x0
-#define MX6Q_PAD_GPIO_1__ESAI_RX_CLK              0x224 0x5f4 0x86c 0x0 0x1
-#define MX6Q_PAD_GPIO_1__WDOG2_B                  0x224 0x5f4 0x000 0x1 0x0
-#define MX6Q_PAD_GPIO_1__KEY_ROW5                 0x224 0x5f4 0x8f4 0x2 0x0
-#define MX6Q_PAD_GPIO_1__USB_OTG_ID               0x224 0x5f4 0x000 0x3 0x0
-#define MX6Q_PAD_GPIO_1__PWM2_OUT                 0x224 0x5f4 0x000 0x4 0x0
-#define MX6Q_PAD_GPIO_1__GPIO1_IO01               0x224 0x5f4 0x000 0x5 0x0
-#define MX6Q_PAD_GPIO_1__SD1_CD_B                 0x224 0x5f4 0x000 0x6 0x0
-#define MX6Q_PAD_GPIO_9__ESAI_RX_FS               0x228 0x5f8 0x85c 0x0 0x1
-#define MX6Q_PAD_GPIO_9__WDOG1_B                  0x228 0x5f8 0x000 0x1 0x0
-#define MX6Q_PAD_GPIO_9__KEY_COL6                 0x228 0x5f8 0x8ec 0x2 0x0
-#define MX6Q_PAD_GPIO_9__CCM_REF_EN_B             0x228 0x5f8 0x000 0x3 0x0
-#define MX6Q_PAD_GPIO_9__PWM1_OUT                 0x228 0x5f8 0x000 0x4 0x0
-#define MX6Q_PAD_GPIO_9__GPIO1_IO09               0x228 0x5f8 0x000 0x5 0x0
-#define MX6Q_PAD_GPIO_9__SD1_WP                   0x228 0x5f8 0x94c 0x6 0x1
-#define MX6Q_PAD_GPIO_3__ESAI_RX_HF_CLK           0x22c 0x5fc 0x864 0x0 0x1
-#define MX6Q_PAD_GPIO_3__I2C3_SCL                 0x22c 0x5fc 0x8a8 0x2 0x1
-#define MX6Q_PAD_GPIO_3__XTALOSC_REF_CLK_24M      0x22c 0x5fc 0x000 0x3 0x0
-#define MX6Q_PAD_GPIO_3__CCM_CLKO2                0x22c 0x5fc 0x000 0x4 0x0
-#define MX6Q_PAD_GPIO_3__GPIO1_IO03               0x22c 0x5fc 0x000 0x5 0x0
-#define MX6Q_PAD_GPIO_3__USB_H1_OC                0x22c 0x5fc 0x948 0x6 0x1
-#define MX6Q_PAD_GPIO_3__MLB_CLK                  0x22c 0x5fc 0x900 0x7 0x1
-#define MX6Q_PAD_GPIO_6__ESAI_TX_CLK              0x230 0x600 0x870 0x0 0x1
-#define MX6Q_PAD_GPIO_6__I2C3_SDA                 0x230 0x600 0x8ac 0x2 0x1
-#define MX6Q_PAD_GPIO_6__GPIO1_IO06               0x230 0x600 0x000 0x5 0x0
-#define MX6Q_PAD_GPIO_6__SD2_LCTL                 0x230 0x600 0x000 0x6 0x0
-#define MX6Q_PAD_GPIO_6__MLB_SIG                  0x230 0x600 0x908 0x7 0x1
-#define MX6Q_PAD_GPIO_2__ESAI_TX_FS               0x234 0x604 0x860 0x0 0x1
-#define MX6Q_PAD_GPIO_2__KEY_ROW6                 0x234 0x604 0x8f8 0x2 0x1
-#define MX6Q_PAD_GPIO_2__GPIO1_IO02               0x234 0x604 0x000 0x5 0x0
-#define MX6Q_PAD_GPIO_2__SD2_WP                   0x234 0x604 0x000 0x6 0x0
-#define MX6Q_PAD_GPIO_2__MLB_DATA                 0x234 0x604 0x904 0x7 0x1
-#define MX6Q_PAD_GPIO_4__ESAI_TX_HF_CLK           0x238 0x608 0x868 0x0 0x1
-#define MX6Q_PAD_GPIO_4__KEY_COL7                 0x238 0x608 0x8f0 0x2 0x1
-#define MX6Q_PAD_GPIO_4__GPIO1_IO04               0x238 0x608 0x000 0x5 0x0
-#define MX6Q_PAD_GPIO_4__SD2_CD_B                 0x238 0x608 0x000 0x6 0x0
-#define MX6Q_PAD_GPIO_5__ESAI_TX2_RX3             0x23c 0x60c 0x87c 0x0 0x1
-#define MX6Q_PAD_GPIO_5__KEY_ROW7                 0x23c 0x60c 0x8fc 0x2 0x1
-#define MX6Q_PAD_GPIO_5__CCM_CLKO1                0x23c 0x60c 0x000 0x3 0x0
-#define MX6Q_PAD_GPIO_5__GPIO1_IO05               0x23c 0x60c 0x000 0x5 0x0
-#define MX6Q_PAD_GPIO_5__I2C3_SCL                 0x23c 0x60c 0x8a8 0x6 0x2
-#define MX6Q_PAD_GPIO_5__ARM_EVENTI               0x23c 0x60c 0x000 0x7 0x0
-#define MX6Q_PAD_GPIO_7__ESAI_TX4_RX1             0x240 0x610 0x884 0x0 0x1
-#define MX6Q_PAD_GPIO_7__ECSPI5_RDY               0x240 0x610 0x000 0x1 0x0
-#define MX6Q_PAD_GPIO_7__EPIT1_OUT                0x240 0x610 0x000 0x2 0x0
-#define MX6Q_PAD_GPIO_7__FLEXCAN1_TX              0x240 0x610 0x000 0x3 0x0
-#define MX6Q_PAD_GPIO_7__UART2_TX_DATA            0x240 0x610 0x000 0x4 0x0
-#define MX6Q_PAD_GPIO_7__UART2_RX_DATA            0x240 0x610 0x928 0x4 0x2
-#define MX6Q_PAD_GPIO_7__GPIO1_IO07               0x240 0x610 0x000 0x5 0x0
-#define MX6Q_PAD_GPIO_7__SPDIF_LOCK               0x240 0x610 0x000 0x6 0x0
-#define MX6Q_PAD_GPIO_7__USB_OTG_HOST_MODE        0x240 0x610 0x000 0x7 0x0
-#define MX6Q_PAD_GPIO_8__ESAI_TX5_RX0             0x244 0x614 0x888 0x0 0x1
-#define MX6Q_PAD_GPIO_8__XTALOSC_REF_CLK_32K      0x244 0x614 0x000 0x1 0x0
-#define MX6Q_PAD_GPIO_8__EPIT2_OUT                0x244 0x614 0x000 0x2 0x0
-#define MX6Q_PAD_GPIO_8__FLEXCAN1_RX              0x244 0x614 0x7e4 0x3 0x1
-#define MX6Q_PAD_GPIO_8__UART2_RX_DATA            0x244 0x614 0x928 0x4 0x3
-#define MX6Q_PAD_GPIO_8__UART2_TX_DATA            0x244 0x614 0x000 0x4 0x0
-#define MX6Q_PAD_GPIO_8__GPIO1_IO08               0x244 0x614 0x000 0x5 0x0
-#define MX6Q_PAD_GPIO_8__SPDIF_SR_CLK             0x244 0x614 0x000 0x6 0x0
-#define MX6Q_PAD_GPIO_8__USB_OTG_PWR_CTL_WAKE     0x244 0x614 0x000 0x7 0x0
-#define MX6Q_PAD_GPIO_16__ESAI_TX3_RX2            0x248 0x618 0x880 0x0 0x1
-#define MX6Q_PAD_GPIO_16__ENET_1588_EVENT2_IN     0x248 0x618 0x000 0x1 0x0
-#define MX6Q_PAD_GPIO_16__ENET_REF_CLK            0x248 0x618 0x83c 0x2 0x1
-#define MX6Q_PAD_GPIO_16__SD1_LCTL                0x248 0x618 0x000 0x3 0x0
-#define MX6Q_PAD_GPIO_16__SPDIF_IN                0x248 0x618 0x914 0x4 0x3
-#define MX6Q_PAD_GPIO_16__GPIO7_IO11              0x248 0x618 0x000 0x5 0x0
-#define MX6Q_PAD_GPIO_16__I2C3_SDA                0x248 0x618 0x8ac 0x6 0x2
-#define MX6Q_PAD_GPIO_16__JTAG_DE_B               0x248 0x618 0x000 0x7 0x0
-#define MX6Q_PAD_GPIO_17__ESAI_TX0                0x24c 0x61c 0x874 0x0 0x0
-#define MX6Q_PAD_GPIO_17__ENET_1588_EVENT3_IN     0x24c 0x61c 0x000 0x1 0x0
-#define MX6Q_PAD_GPIO_17__CCM_PMIC_READY          0x24c 0x61c 0x7f0 0x2 0x1
-#define MX6Q_PAD_GPIO_17__SDMA_EXT_EVENT0         0x24c 0x61c 0x90c 0x3 0x1
-#define MX6Q_PAD_GPIO_17__SPDIF_OUT               0x24c 0x61c 0x000 0x4 0x0
-#define MX6Q_PAD_GPIO_17__GPIO7_IO12              0x24c 0x61c 0x000 0x5 0x0
-#define MX6Q_PAD_GPIO_18__ESAI_TX1                0x250 0x620 0x878 0x0 0x0
-#define MX6Q_PAD_GPIO_18__ENET_RX_CLK             0x250 0x620 0x844 0x1 0x1
-#define MX6Q_PAD_GPIO_18__SD3_VSELECT             0x250 0x620 0x000 0x2 0x0
-#define MX6Q_PAD_GPIO_18__SDMA_EXT_EVENT1         0x250 0x620 0x910 0x3 0x1
-#define MX6Q_PAD_GPIO_18__ASRC_EXT_CLK            0x250 0x620 0x7b0 0x4 0x2
-#define MX6Q_PAD_GPIO_18__GPIO7_IO13              0x250 0x620 0x000 0x5 0x0
-#define MX6Q_PAD_GPIO_18__SNVS_VIO_5_CTL          0x250 0x620 0x000 0x6 0x0
-#define MX6Q_PAD_GPIO_19__KEY_COL5                0x254 0x624 0x8e8 0x0 0x1
-#define MX6Q_PAD_GPIO_19__ENET_1588_EVENT0_OUT    0x254 0x624 0x000 0x1 0x0
-#define MX6Q_PAD_GPIO_19__SPDIF_OUT               0x254 0x624 0x000 0x2 0x0
-#define MX6Q_PAD_GPIO_19__CCM_CLKO1               0x254 0x624 0x000 0x3 0x0
-#define MX6Q_PAD_GPIO_19__ECSPI1_RDY              0x254 0x624 0x000 0x4 0x0
-#define MX6Q_PAD_GPIO_19__GPIO4_IO05              0x254 0x624 0x000 0x5 0x0
-#define MX6Q_PAD_GPIO_19__ENET_TX_ER              0x254 0x624 0x000 0x6 0x0
-#define MX6Q_PAD_CSI0_PIXCLK__IPU1_CSI0_PIXCLK    0x258 0x628 0x000 0x0 0x0
-#define MX6Q_PAD_CSI0_PIXCLK__GPIO5_IO18          0x258 0x628 0x000 0x5 0x0
-#define MX6Q_PAD_CSI0_PIXCLK__ARM_EVENTO          0x258 0x628 0x000 0x7 0x0
-#define MX6Q_PAD_CSI0_MCLK__IPU1_CSI0_HSYNC       0x25c 0x62c 0x000 0x0 0x0
-#define MX6Q_PAD_CSI0_MCLK__CCM_CLKO1             0x25c 0x62c 0x000 0x3 0x0
-#define MX6Q_PAD_CSI0_MCLK__GPIO5_IO19            0x25c 0x62c 0x000 0x5 0x0
-#define MX6Q_PAD_CSI0_MCLK__ARM_TRACE_CTL         0x25c 0x62c 0x000 0x7 0x0
-#define MX6Q_PAD_CSI0_DATA_EN__IPU1_CSI0_DATA_EN  0x260 0x630 0x000 0x0 0x0
-#define MX6Q_PAD_CSI0_DATA_EN__EIM_DATA00         0x260 0x630 0x000 0x1 0x0
-#define MX6Q_PAD_CSI0_DATA_EN__GPIO5_IO20         0x260 0x630 0x000 0x5 0x0
-#define MX6Q_PAD_CSI0_DATA_EN__ARM_TRACE_CLK      0x260 0x630 0x000 0x7 0x0
-#define MX6Q_PAD_CSI0_VSYNC__IPU1_CSI0_VSYNC      0x264 0x634 0x000 0x0 0x0
-#define MX6Q_PAD_CSI0_VSYNC__EIM_DATA01           0x264 0x634 0x000 0x1 0x0
-#define MX6Q_PAD_CSI0_VSYNC__GPIO5_IO21           0x264 0x634 0x000 0x5 0x0
-#define MX6Q_PAD_CSI0_VSYNC__ARM_TRACE00          0x264 0x634 0x000 0x7 0x0
-#define MX6Q_PAD_CSI0_DAT4__IPU1_CSI0_DATA04      0x268 0x638 0x000 0x0 0x0
-#define MX6Q_PAD_CSI0_DAT4__EIM_DATA02            0x268 0x638 0x000 0x1 0x0
-#define MX6Q_PAD_CSI0_DAT4__ECSPI1_SCLK           0x268 0x638 0x7f4 0x2 0x3
-#define MX6Q_PAD_CSI0_DAT4__KEY_COL5              0x268 0x638 0x8e8 0x3 0x2
-#define MX6Q_PAD_CSI0_DAT4__AUD3_TXC              0x268 0x638 0x000 0x4 0x0
-#define MX6Q_PAD_CSI0_DAT4__GPIO5_IO22            0x268 0x638 0x000 0x5 0x0
-#define MX6Q_PAD_CSI0_DAT4__ARM_TRACE01           0x268 0x638 0x000 0x7 0x0
-#define MX6Q_PAD_CSI0_DAT5__IPU1_CSI0_DATA05      0x26c 0x63c 0x000 0x0 0x0
-#define MX6Q_PAD_CSI0_DAT5__EIM_DATA03            0x26c 0x63c 0x000 0x1 0x0
-#define MX6Q_PAD_CSI0_DAT5__ECSPI1_MOSI           0x26c 0x63c 0x7fc 0x2 0x3
-#define MX6Q_PAD_CSI0_DAT5__KEY_ROW5              0x26c 0x63c 0x8f4 0x3 0x1
-#define MX6Q_PAD_CSI0_DAT5__AUD3_TXD              0x26c 0x63c 0x000 0x4 0x0
-#define MX6Q_PAD_CSI0_DAT5__GPIO5_IO23            0x26c 0x63c 0x000 0x5 0x0
-#define MX6Q_PAD_CSI0_DAT5__ARM_TRACE02           0x26c 0x63c 0x000 0x7 0x0
-#define MX6Q_PAD_CSI0_DAT6__IPU1_CSI0_DATA06      0x270 0x640 0x000 0x0 0x0
-#define MX6Q_PAD_CSI0_DAT6__EIM_DATA04            0x270 0x640 0x000 0x1 0x0
-#define MX6Q_PAD_CSI0_DAT6__ECSPI1_MISO           0x270 0x640 0x7f8 0x2 0x3
-#define MX6Q_PAD_CSI0_DAT6__KEY_COL6              0x270 0x640 0x8ec 0x3 0x1
-#define MX6Q_PAD_CSI0_DAT6__AUD3_TXFS             0x270 0x640 0x000 0x4 0x0
-#define MX6Q_PAD_CSI0_DAT6__GPIO5_IO24            0x270 0x640 0x000 0x5 0x0
-#define MX6Q_PAD_CSI0_DAT6__ARM_TRACE03           0x270 0x640 0x000 0x7 0x0
-#define MX6Q_PAD_CSI0_DAT7__IPU1_CSI0_DATA07      0x274 0x644 0x000 0x0 0x0
-#define MX6Q_PAD_CSI0_DAT7__EIM_DATA05            0x274 0x644 0x000 0x1 0x0
-#define MX6Q_PAD_CSI0_DAT7__ECSPI1_SS0            0x274 0x644 0x800 0x2 0x3
-#define MX6Q_PAD_CSI0_DAT7__KEY_ROW6              0x274 0x644 0x8f8 0x3 0x2
-#define MX6Q_PAD_CSI0_DAT7__AUD3_RXD              0x274 0x644 0x000 0x4 0x0
-#define MX6Q_PAD_CSI0_DAT7__GPIO5_IO25            0x274 0x644 0x000 0x5 0x0
-#define MX6Q_PAD_CSI0_DAT7__ARM_TRACE04           0x274 0x644 0x000 0x7 0x0
-#define MX6Q_PAD_CSI0_DAT8__IPU1_CSI0_DATA08      0x278 0x648 0x000 0x0 0x0
-#define MX6Q_PAD_CSI0_DAT8__EIM_DATA06            0x278 0x648 0x000 0x1 0x0
-#define MX6Q_PAD_CSI0_DAT8__ECSPI2_SCLK           0x278 0x648 0x810 0x2 0x2
-#define MX6Q_PAD_CSI0_DAT8__KEY_COL7              0x278 0x648 0x8f0 0x3 0x2
-#define MX6Q_PAD_CSI0_DAT8__I2C1_SDA              0x278 0x648 0x89c 0x4 0x1
-#define MX6Q_PAD_CSI0_DAT8__GPIO5_IO26            0x278 0x648 0x000 0x5 0x0
-#define MX6Q_PAD_CSI0_DAT8__ARM_TRACE05           0x278 0x648 0x000 0x7 0x0
-#define MX6Q_PAD_CSI0_DAT9__IPU1_CSI0_DATA09      0x27c 0x64c 0x000 0x0 0x0
-#define MX6Q_PAD_CSI0_DAT9__EIM_DATA07            0x27c 0x64c 0x000 0x1 0x0
-#define MX6Q_PAD_CSI0_DAT9__ECSPI2_MOSI           0x27c 0x64c 0x818 0x2 0x2
-#define MX6Q_PAD_CSI0_DAT9__KEY_ROW7              0x27c 0x64c 0x8fc 0x3 0x2
-#define MX6Q_PAD_CSI0_DAT9__I2C1_SCL              0x27c 0x64c 0x898 0x4 0x1
-#define MX6Q_PAD_CSI0_DAT9__GPIO5_IO27            0x27c 0x64c 0x000 0x5 0x0
-#define MX6Q_PAD_CSI0_DAT9__ARM_TRACE06           0x27c 0x64c 0x000 0x7 0x0
-#define MX6Q_PAD_CSI0_DAT10__IPU1_CSI0_DATA10     0x280 0x650 0x000 0x0 0x0
-#define MX6Q_PAD_CSI0_DAT10__AUD3_RXC             0x280 0x650 0x000 0x1 0x0
-#define MX6Q_PAD_CSI0_DAT10__ECSPI2_MISO          0x280 0x650 0x814 0x2 0x2
-#define MX6Q_PAD_CSI0_DAT10__UART1_TX_DATA        0x280 0x650 0x000 0x3 0x0
-#define MX6Q_PAD_CSI0_DAT10__UART1_RX_DATA        0x280 0x650 0x920 0x3 0x0
-#define MX6Q_PAD_CSI0_DAT10__GPIO5_IO28           0x280 0x650 0x000 0x5 0x0
-#define MX6Q_PAD_CSI0_DAT10__ARM_TRACE07          0x280 0x650 0x000 0x7 0x0
-#define MX6Q_PAD_CSI0_DAT11__IPU1_CSI0_DATA11     0x284 0x654 0x000 0x0 0x0
-#define MX6Q_PAD_CSI0_DAT11__AUD3_RXFS            0x284 0x654 0x000 0x1 0x0
-#define MX6Q_PAD_CSI0_DAT11__ECSPI2_SS0           0x284 0x654 0x81c 0x2 0x2
-#define MX6Q_PAD_CSI0_DAT11__UART1_RX_DATA        0x284 0x654 0x920 0x3 0x1
-#define MX6Q_PAD_CSI0_DAT11__UART1_TX_DATA        0x284 0x654 0x000 0x3 0x0
-#define MX6Q_PAD_CSI0_DAT11__GPIO5_IO29           0x284 0x654 0x000 0x5 0x0
-#define MX6Q_PAD_CSI0_DAT11__ARM_TRACE08          0x284 0x654 0x000 0x7 0x0
-#define MX6Q_PAD_CSI0_DAT12__IPU1_CSI0_DATA12     0x288 0x658 0x000 0x0 0x0
-#define MX6Q_PAD_CSI0_DAT12__EIM_DATA08           0x288 0x658 0x000 0x1 0x0
-#define MX6Q_PAD_CSI0_DAT12__UART4_TX_DATA        0x288 0x658 0x000 0x3 0x0
-#define MX6Q_PAD_CSI0_DAT12__UART4_RX_DATA        0x288 0x658 0x938 0x3 0x2
-#define MX6Q_PAD_CSI0_DAT12__GPIO5_IO30           0x288 0x658 0x000 0x5 0x0
-#define MX6Q_PAD_CSI0_DAT12__ARM_TRACE09          0x288 0x658 0x000 0x7 0x0
-#define MX6Q_PAD_CSI0_DAT13__IPU1_CSI0_DATA13     0x28c 0x65c 0x000 0x0 0x0
-#define MX6Q_PAD_CSI0_DAT13__EIM_DATA09           0x28c 0x65c 0x000 0x1 0x0
-#define MX6Q_PAD_CSI0_DAT13__UART4_RX_DATA        0x28c 0x65c 0x938 0x3 0x3
-#define MX6Q_PAD_CSI0_DAT13__UART4_TX_DATA        0x28c 0x65c 0x000 0x3 0x0
-#define MX6Q_PAD_CSI0_DAT13__GPIO5_IO31           0x28c 0x65c 0x000 0x5 0x0
-#define MX6Q_PAD_CSI0_DAT13__ARM_TRACE10          0x28c 0x65c 0x000 0x7 0x0
-#define MX6Q_PAD_CSI0_DAT14__IPU1_CSI0_DATA14     0x290 0x660 0x000 0x0 0x0
-#define MX6Q_PAD_CSI0_DAT14__EIM_DATA10           0x290 0x660 0x000 0x1 0x0
-#define MX6Q_PAD_CSI0_DAT14__UART5_TX_DATA        0x290 0x660 0x000 0x3 0x0
-#define MX6Q_PAD_CSI0_DAT14__UART5_RX_DATA        0x290 0x660 0x940 0x3 0x2
-#define MX6Q_PAD_CSI0_DAT14__GPIO6_IO00           0x290 0x660 0x000 0x5 0x0
-#define MX6Q_PAD_CSI0_DAT14__ARM_TRACE11          0x290 0x660 0x000 0x7 0x0
-#define MX6Q_PAD_CSI0_DAT15__IPU1_CSI0_DATA15     0x294 0x664 0x000 0x0 0x0
-#define MX6Q_PAD_CSI0_DAT15__EIM_DATA11           0x294 0x664 0x000 0x1 0x0
-#define MX6Q_PAD_CSI0_DAT15__UART5_RX_DATA        0x294 0x664 0x940 0x3 0x3
-#define MX6Q_PAD_CSI0_DAT15__UART5_TX_DATA        0x294 0x664 0x000 0x3 0x0
-#define MX6Q_PAD_CSI0_DAT15__GPIO6_IO01           0x294 0x664 0x000 0x5 0x0
-#define MX6Q_PAD_CSI0_DAT15__ARM_TRACE12          0x294 0x664 0x000 0x7 0x0
-#define MX6Q_PAD_CSI0_DAT16__IPU1_CSI0_DATA16     0x298 0x668 0x000 0x0 0x0
-#define MX6Q_PAD_CSI0_DAT16__EIM_DATA12           0x298 0x668 0x000 0x1 0x0
-#define MX6Q_PAD_CSI0_DAT16__UART4_RTS_B          0x298 0x668 0x934 0x3 0x0
-#define MX6Q_PAD_CSI0_DAT16__UART4_CTS_B          0x298 0x668 0x000 0x3 0x0
-#define MX6Q_PAD_CSI0_DAT16__GPIO6_IO02           0x298 0x668 0x000 0x5 0x0
-#define MX6Q_PAD_CSI0_DAT16__ARM_TRACE13          0x298 0x668 0x000 0x7 0x0
-#define MX6Q_PAD_CSI0_DAT17__IPU1_CSI0_DATA17     0x29c 0x66c 0x000 0x0 0x0
-#define MX6Q_PAD_CSI0_DAT17__EIM_DATA13           0x29c 0x66c 0x000 0x1 0x0
-#define MX6Q_PAD_CSI0_DAT17__UART4_CTS_B          0x29c 0x66c 0x000 0x3 0x0
-#define MX6Q_PAD_CSI0_DAT17__UART4_RTS_B          0x29c 0x66c 0x934 0x3 0x1
-#define MX6Q_PAD_CSI0_DAT17__GPIO6_IO03           0x29c 0x66c 0x000 0x5 0x0
-#define MX6Q_PAD_CSI0_DAT17__ARM_TRACE14          0x29c 0x66c 0x000 0x7 0x0
-#define MX6Q_PAD_CSI0_DAT18__IPU1_CSI0_DATA18     0x2a0 0x670 0x000 0x0 0x0
-#define MX6Q_PAD_CSI0_DAT18__EIM_DATA14           0x2a0 0x670 0x000 0x1 0x0
-#define MX6Q_PAD_CSI0_DAT18__UART5_RTS_B          0x2a0 0x670 0x93c 0x3 0x2
-#define MX6Q_PAD_CSI0_DAT18__UART5_CTS_B          0x2a0 0x670 0x000 0x3 0x0
-#define MX6Q_PAD_CSI0_DAT18__GPIO6_IO04           0x2a0 0x670 0x000 0x5 0x0
-#define MX6Q_PAD_CSI0_DAT18__ARM_TRACE15          0x2a0 0x670 0x000 0x7 0x0
-#define MX6Q_PAD_CSI0_DAT19__IPU1_CSI0_DATA19     0x2a4 0x674 0x000 0x0 0x0
-#define MX6Q_PAD_CSI0_DAT19__EIM_DATA15           0x2a4 0x674 0x000 0x1 0x0
-#define MX6Q_PAD_CSI0_DAT19__UART5_CTS_B          0x2a4 0x674 0x000 0x3 0x0
-#define MX6Q_PAD_CSI0_DAT19__UART5_RTS_B          0x2a4 0x674 0x93c 0x3 0x3
-#define MX6Q_PAD_CSI0_DAT19__GPIO6_IO05           0x2a4 0x674 0x000 0x5 0x0
-#define MX6Q_PAD_SD3_DAT7__SD3_DATA7              0x2a8 0x690 0x000 0x0 0x0
-#define MX6Q_PAD_SD3_DAT7__UART1_TX_DATA          0x2a8 0x690 0x000 0x1 0x0
-#define MX6Q_PAD_SD3_DAT7__UART1_RX_DATA          0x2a8 0x690 0x920 0x1 0x2
-#define MX6Q_PAD_SD3_DAT7__GPIO6_IO17             0x2a8 0x690 0x000 0x5 0x0
-#define MX6Q_PAD_SD3_DAT6__SD3_DATA6              0x2ac 0x694 0x000 0x0 0x0
-#define MX6Q_PAD_SD3_DAT6__UART1_RX_DATA          0x2ac 0x694 0x920 0x1 0x3
-#define MX6Q_PAD_SD3_DAT6__UART1_TX_DATA          0x2ac 0x694 0x000 0x1 0x0
-#define MX6Q_PAD_SD3_DAT6__GPIO6_IO18             0x2ac 0x694 0x000 0x5 0x0
-#define MX6Q_PAD_SD3_DAT5__SD3_DATA5              0x2b0 0x698 0x000 0x0 0x0
-#define MX6Q_PAD_SD3_DAT5__UART2_TX_DATA          0x2b0 0x698 0x000 0x1 0x0
-#define MX6Q_PAD_SD3_DAT5__UART2_RX_DATA          0x2b0 0x698 0x928 0x1 0x4
-#define MX6Q_PAD_SD3_DAT5__GPIO7_IO00             0x2b0 0x698 0x000 0x5 0x0
-#define MX6Q_PAD_SD3_DAT4__SD3_DATA4              0x2b4 0x69c 0x000 0x0 0x0
-#define MX6Q_PAD_SD3_DAT4__UART2_RX_DATA          0x2b4 0x69c 0x928 0x1 0x5
-#define MX6Q_PAD_SD3_DAT4__UART2_TX_DATA          0x2b4 0x69c 0x000 0x1 0x0
-#define MX6Q_PAD_SD3_DAT4__GPIO7_IO01             0x2b4 0x69c 0x000 0x5 0x0
-#define MX6Q_PAD_SD3_CMD__SD3_CMD                 0x2b8 0x6a0 0x000 0x0 0x0
-#define MX6Q_PAD_SD3_CMD__UART2_CTS_B             0x2b8 0x6a0 0x000 0x1 0x0
-#define MX6Q_PAD_SD3_CMD__UART2_RTS_B             0x2b8 0x6a0 0x924 0x1 0x2
-#define MX6Q_PAD_SD3_CMD__FLEXCAN1_TX             0x2b8 0x6a0 0x000 0x2 0x0
-#define MX6Q_PAD_SD3_CMD__GPIO7_IO02              0x2b8 0x6a0 0x000 0x5 0x0
-#define MX6Q_PAD_SD3_CLK__SD3_CLK                 0x2bc 0x6a4 0x000 0x0 0x0
-#define MX6Q_PAD_SD3_CLK__UART2_RTS_B             0x2bc 0x6a4 0x924 0x1 0x3
-#define MX6Q_PAD_SD3_CLK__UART2_CTS_B             0x2bc 0x6a4 0x000 0x1 0x0
-#define MX6Q_PAD_SD3_CLK__FLEXCAN1_RX             0x2bc 0x6a4 0x7e4 0x2 0x2
-#define MX6Q_PAD_SD3_CLK__GPIO7_IO03              0x2bc 0x6a4 0x000 0x5 0x0
-#define MX6Q_PAD_SD3_DAT0__SD3_DATA0              0x2c0 0x6a8 0x000 0x0 0x0
-#define MX6Q_PAD_SD3_DAT0__UART1_CTS_B            0x2c0 0x6a8 0x000 0x1 0x0
-#define MX6Q_PAD_SD3_DAT0__UART1_RTS_B            0x2c0 0x6a8 0x91c 0x1 0x2
-#define MX6Q_PAD_SD3_DAT0__FLEXCAN2_TX            0x2c0 0x6a8 0x000 0x2 0x0
-#define MX6Q_PAD_SD3_DAT0__GPIO7_IO04             0x2c0 0x6a8 0x000 0x5 0x0
-#define MX6Q_PAD_SD3_DAT1__SD3_DATA1              0x2c4 0x6ac 0x000 0x0 0x0
-#define MX6Q_PAD_SD3_DAT1__UART1_RTS_B            0x2c4 0x6ac 0x91c 0x1 0x3
-#define MX6Q_PAD_SD3_DAT1__UART1_CTS_B            0x2c4 0x6ac 0x000 0x1 0x0
-#define MX6Q_PAD_SD3_DAT1__FLEXCAN2_RX            0x2c4 0x6ac 0x7e8 0x2 0x1
-#define MX6Q_PAD_SD3_DAT1__GPIO7_IO05             0x2c4 0x6ac 0x000 0x5 0x0
-#define MX6Q_PAD_SD3_DAT2__SD3_DATA2              0x2c8 0x6b0 0x000 0x0 0x0
-#define MX6Q_PAD_SD3_DAT2__GPIO7_IO06             0x2c8 0x6b0 0x000 0x5 0x0
-#define MX6Q_PAD_SD3_DAT3__SD3_DATA3              0x2cc 0x6b4 0x000 0x0 0x0
-#define MX6Q_PAD_SD3_DAT3__UART3_CTS_B            0x2cc 0x6b4 0x000 0x1 0x0
-#define MX6Q_PAD_SD3_DAT3__UART3_RTS_B            0x2cc 0x6b4 0x92c 0x1 0x4
-#define MX6Q_PAD_SD3_DAT3__GPIO7_IO07             0x2cc 0x6b4 0x000 0x5 0x0
-#define MX6Q_PAD_SD3_RST__SD3_RESET               0x2d0 0x6b8 0x000 0x0 0x0
-#define MX6Q_PAD_SD3_RST__UART3_RTS_B             0x2d0 0x6b8 0x92c 0x1 0x5
-#define MX6Q_PAD_SD3_RST__UART3_CTS_B             0x2d0 0x6b8 0x000 0x1 0x0
-#define MX6Q_PAD_SD3_RST__GPIO7_IO08              0x2d0 0x6b8 0x000 0x5 0x0
-#define MX6Q_PAD_NANDF_CLE__NAND_CLE              0x2d4 0x6bc 0x000 0x0 0x0
-#define MX6Q_PAD_NANDF_CLE__IPU2_SISG4            0x2d4 0x6bc 0x000 0x1 0x0
-#define MX6Q_PAD_NANDF_CLE__GPIO6_IO07            0x2d4 0x6bc 0x000 0x5 0x0
-#define MX6Q_PAD_NANDF_ALE__NAND_ALE              0x2d8 0x6c0 0x000 0x0 0x0
-#define MX6Q_PAD_NANDF_ALE__SD4_RESET             0x2d8 0x6c0 0x000 0x1 0x0
-#define MX6Q_PAD_NANDF_ALE__GPIO6_IO08            0x2d8 0x6c0 0x000 0x5 0x0
-#define MX6Q_PAD_NANDF_WP_B__NAND_WP_B            0x2dc 0x6c4 0x000 0x0 0x0
-#define MX6Q_PAD_NANDF_WP_B__IPU2_SISG5           0x2dc 0x6c4 0x000 0x1 0x0
-#define MX6Q_PAD_NANDF_WP_B__GPIO6_IO09           0x2dc 0x6c4 0x000 0x5 0x0
-#define MX6Q_PAD_NANDF_RB0__NAND_READY_B          0x2e0 0x6c8 0x000 0x0 0x0
-#define MX6Q_PAD_NANDF_RB0__IPU2_DI0_PIN01        0x2e0 0x6c8 0x000 0x1 0x0
-#define MX6Q_PAD_NANDF_RB0__GPIO6_IO10            0x2e0 0x6c8 0x000 0x5 0x0
-#define MX6Q_PAD_NANDF_CS0__NAND_CE0_B            0x2e4 0x6cc 0x000 0x0 0x0
-#define MX6Q_PAD_NANDF_CS0__GPIO6_IO11            0x2e4 0x6cc 0x000 0x5 0x0
-#define MX6Q_PAD_NANDF_CS1__NAND_CE1_B            0x2e8 0x6d0 0x000 0x0 0x0
-#define MX6Q_PAD_NANDF_CS1__SD4_VSELECT           0x2e8 0x6d0 0x000 0x1 0x0
-#define MX6Q_PAD_NANDF_CS1__SD3_VSELECT           0x2e8 0x6d0 0x000 0x2 0x0
-#define MX6Q_PAD_NANDF_CS1__GPIO6_IO14            0x2e8 0x6d0 0x000 0x5 0x0
-#define MX6Q_PAD_NANDF_CS2__NAND_CE2_B            0x2ec 0x6d4 0x000 0x0 0x0
-#define MX6Q_PAD_NANDF_CS2__IPU1_SISG0            0x2ec 0x6d4 0x000 0x1 0x0
-#define MX6Q_PAD_NANDF_CS2__ESAI_TX0              0x2ec 0x6d4 0x874 0x2 0x1
-#define MX6Q_PAD_NANDF_CS2__EIM_CRE               0x2ec 0x6d4 0x000 0x3 0x0
-#define MX6Q_PAD_NANDF_CS2__CCM_CLKO2             0x2ec 0x6d4 0x000 0x4 0x0
-#define MX6Q_PAD_NANDF_CS2__GPIO6_IO15            0x2ec 0x6d4 0x000 0x5 0x0
-#define MX6Q_PAD_NANDF_CS2__IPU2_SISG0            0x2ec 0x6d4 0x000 0x6 0x0
-#define MX6Q_PAD_NANDF_CS3__NAND_CE3_B            0x2f0 0x6d8 0x000 0x0 0x0
-#define MX6Q_PAD_NANDF_CS3__IPU1_SISG1            0x2f0 0x6d8 0x000 0x1 0x0
-#define MX6Q_PAD_NANDF_CS3__ESAI_TX1              0x2f0 0x6d8 0x878 0x2 0x1
-#define MX6Q_PAD_NANDF_CS3__EIM_ADDR26            0x2f0 0x6d8 0x000 0x3 0x0
-#define MX6Q_PAD_NANDF_CS3__GPIO6_IO16            0x2f0 0x6d8 0x000 0x5 0x0
-#define MX6Q_PAD_NANDF_CS3__IPU2_SISG1            0x2f0 0x6d8 0x000 0x6 0x0
-#define MX6Q_PAD_SD4_CMD__SD4_CMD                 0x2f4 0x6dc 0x000 0x0 0x0
-#define MX6Q_PAD_SD4_CMD__NAND_RE_B               0x2f4 0x6dc 0x000 0x1 0x0
-#define MX6Q_PAD_SD4_CMD__UART3_TX_DATA           0x2f4 0x6dc 0x000 0x2 0x0
-#define MX6Q_PAD_SD4_CMD__UART3_RX_DATA           0x2f4 0x6dc 0x930 0x2 0x2
-#define MX6Q_PAD_SD4_CMD__GPIO7_IO09              0x2f4 0x6dc 0x000 0x5 0x0
-#define MX6Q_PAD_SD4_CLK__SD4_CLK                 0x2f8 0x6e0 0x000 0x0 0x0
-#define MX6Q_PAD_SD4_CLK__NAND_WE_B               0x2f8 0x6e0 0x000 0x1 0x0
-#define MX6Q_PAD_SD4_CLK__UART3_RX_DATA           0x2f8 0x6e0 0x930 0x2 0x3
-#define MX6Q_PAD_SD4_CLK__UART3_TX_DATA           0x2f8 0x6e0 0x000 0x2 0x0
-#define MX6Q_PAD_SD4_CLK__GPIO7_IO10              0x2f8 0x6e0 0x000 0x5 0x0
-#define MX6Q_PAD_NANDF_D0__NAND_DATA00            0x2fc 0x6e4 0x000 0x0 0x0
-#define MX6Q_PAD_NANDF_D0__SD1_DATA4              0x2fc 0x6e4 0x000 0x1 0x0
-#define MX6Q_PAD_NANDF_D0__GPIO2_IO00             0x2fc 0x6e4 0x000 0x5 0x0
-#define MX6Q_PAD_NANDF_D1__NAND_DATA01            0x300 0x6e8 0x000 0x0 0x0
-#define MX6Q_PAD_NANDF_D1__SD1_DATA5              0x300 0x6e8 0x000 0x1 0x0
-#define MX6Q_PAD_NANDF_D1__GPIO2_IO01             0x300 0x6e8 0x000 0x5 0x0
-#define MX6Q_PAD_NANDF_D2__NAND_DATA02            0x304 0x6ec 0x000 0x0 0x0
-#define MX6Q_PAD_NANDF_D2__SD1_DATA6              0x304 0x6ec 0x000 0x1 0x0
-#define MX6Q_PAD_NANDF_D2__GPIO2_IO02             0x304 0x6ec 0x000 0x5 0x0
-#define MX6Q_PAD_NANDF_D3__NAND_DATA03            0x308 0x6f0 0x000 0x0 0x0
-#define MX6Q_PAD_NANDF_D3__SD1_DATA7              0x308 0x6f0 0x000 0x1 0x0
-#define MX6Q_PAD_NANDF_D3__GPIO2_IO03             0x308 0x6f0 0x000 0x5 0x0
-#define MX6Q_PAD_NANDF_D4__NAND_DATA04            0x30c 0x6f4 0x000 0x0 0x0
-#define MX6Q_PAD_NANDF_D4__SD2_DATA4              0x30c 0x6f4 0x000 0x1 0x0
-#define MX6Q_PAD_NANDF_D4__GPIO2_IO04             0x30c 0x6f4 0x000 0x5 0x0
-#define MX6Q_PAD_NANDF_D5__NAND_DATA05            0x310 0x6f8 0x000 0x0 0x0
-#define MX6Q_PAD_NANDF_D5__SD2_DATA5              0x310 0x6f8 0x000 0x1 0x0
-#define MX6Q_PAD_NANDF_D5__GPIO2_IO05             0x310 0x6f8 0x000 0x5 0x0
-#define MX6Q_PAD_NANDF_D6__NAND_DATA06            0x314 0x6fc 0x000 0x0 0x0
-#define MX6Q_PAD_NANDF_D6__SD2_DATA6              0x314 0x6fc 0x000 0x1 0x0
-#define MX6Q_PAD_NANDF_D6__GPIO2_IO06             0x314 0x6fc 0x000 0x5 0x0
-#define MX6Q_PAD_NANDF_D7__NAND_DATA07            0x318 0x700 0x000 0x0 0x0
-#define MX6Q_PAD_NANDF_D7__SD2_DATA7              0x318 0x700 0x000 0x1 0x0
-#define MX6Q_PAD_NANDF_D7__GPIO2_IO07             0x318 0x700 0x000 0x5 0x0
-#define MX6Q_PAD_SD4_DAT0__SD4_DATA0              0x31c 0x704 0x000 0x1 0x0
-#define MX6Q_PAD_SD4_DAT0__NAND_DQS               0x31c 0x704 0x000 0x2 0x0
-#define MX6Q_PAD_SD4_DAT0__GPIO2_IO08             0x31c 0x704 0x000 0x5 0x0
-#define MX6Q_PAD_SD4_DAT1__SD4_DATA1              0x320 0x708 0x000 0x1 0x0
-#define MX6Q_PAD_SD4_DAT1__PWM3_OUT               0x320 0x708 0x000 0x2 0x0
-#define MX6Q_PAD_SD4_DAT1__GPIO2_IO09             0x320 0x708 0x000 0x5 0x0
-#define MX6Q_PAD_SD4_DAT2__SD4_DATA2              0x324 0x70c 0x000 0x1 0x0
-#define MX6Q_PAD_SD4_DAT2__PWM4_OUT               0x324 0x70c 0x000 0x2 0x0
-#define MX6Q_PAD_SD4_DAT2__GPIO2_IO10             0x324 0x70c 0x000 0x5 0x0
-#define MX6Q_PAD_SD4_DAT3__SD4_DATA3              0x328 0x710 0x000 0x1 0x0
-#define MX6Q_PAD_SD4_DAT3__GPIO2_IO11             0x328 0x710 0x000 0x5 0x0
-#define MX6Q_PAD_SD4_DAT4__SD4_DATA4              0x32c 0x714 0x000 0x1 0x0
-#define MX6Q_PAD_SD4_DAT4__UART2_RX_DATA          0x32c 0x714 0x928 0x2 0x6
-#define MX6Q_PAD_SD4_DAT4__UART2_TX_DATA          0x32c 0x714 0x000 0x2 0x0
-#define MX6Q_PAD_SD4_DAT4__GPIO2_IO12             0x32c 0x714 0x000 0x5 0x0
-#define MX6Q_PAD_SD4_DAT5__SD4_DATA5              0x330 0x718 0x000 0x1 0x0
-#define MX6Q_PAD_SD4_DAT5__UART2_RTS_B            0x330 0x718 0x924 0x2 0x4
-#define MX6Q_PAD_SD4_DAT5__UART2_CTS_B            0x330 0x718 0x000 0x2 0x0
-#define MX6Q_PAD_SD4_DAT5__GPIO2_IO13             0x330 0x718 0x000 0x5 0x0
-#define MX6Q_PAD_SD4_DAT6__SD4_DATA6              0x334 0x71c 0x000 0x1 0x0
-#define MX6Q_PAD_SD4_DAT6__UART2_CTS_B            0x334 0x71c 0x000 0x2 0x0
-#define MX6Q_PAD_SD4_DAT6__UART2_RTS_B            0x334 0x71c 0x924 0x2 0x5
-#define MX6Q_PAD_SD4_DAT6__GPIO2_IO14             0x334 0x71c 0x000 0x5 0x0
-#define MX6Q_PAD_SD4_DAT7__SD4_DATA7              0x338 0x720 0x000 0x1 0x0
-#define MX6Q_PAD_SD4_DAT7__UART2_TX_DATA          0x338 0x720 0x000 0x2 0x0
-#define MX6Q_PAD_SD4_DAT7__UART2_RX_DATA          0x338 0x720 0x928 0x2 0x7
-#define MX6Q_PAD_SD4_DAT7__GPIO2_IO15             0x338 0x720 0x000 0x5 0x0
-#define MX6Q_PAD_SD1_DAT1__SD1_DATA1              0x33c 0x724 0x000 0x0 0x0
-#define MX6Q_PAD_SD1_DAT1__ECSPI5_SS0             0x33c 0x724 0x834 0x1 0x1
-#define MX6Q_PAD_SD1_DAT1__PWM3_OUT               0x33c 0x724 0x000 0x2 0x0
-#define MX6Q_PAD_SD1_DAT1__GPT_CAPTURE2           0x33c 0x724 0x000 0x3 0x0
-#define MX6Q_PAD_SD1_DAT1__GPIO1_IO17             0x33c 0x724 0x000 0x5 0x0
-#define MX6Q_PAD_SD1_DAT0__SD1_DATA0              0x340 0x728 0x000 0x0 0x0
-#define MX6Q_PAD_SD1_DAT0__ECSPI5_MISO            0x340 0x728 0x82c 0x1 0x1
-#define MX6Q_PAD_SD1_DAT0__GPT_CAPTURE1           0x340 0x728 0x000 0x3 0x0
-#define MX6Q_PAD_SD1_DAT0__GPIO1_IO16             0x340 0x728 0x000 0x5 0x0
-#define MX6Q_PAD_SD1_DAT3__SD1_DATA3              0x344 0x72c 0x000 0x0 0x0
-#define MX6Q_PAD_SD1_DAT3__ECSPI5_SS2             0x344 0x72c 0x000 0x1 0x0
-#define MX6Q_PAD_SD1_DAT3__GPT_COMPARE3           0x344 0x72c 0x000 0x2 0x0
-#define MX6Q_PAD_SD1_DAT3__PWM1_OUT               0x344 0x72c 0x000 0x3 0x0
-#define MX6Q_PAD_SD1_DAT3__WDOG2_B                0x344 0x72c 0x000 0x4 0x0
-#define MX6Q_PAD_SD1_DAT3__GPIO1_IO21             0x344 0x72c 0x000 0x5 0x0
-#define MX6Q_PAD_SD1_DAT3__WDOG2_RESET_B_DEB      0x344 0x72c 0x000 0x6 0x0
-#define MX6Q_PAD_SD1_CMD__SD1_CMD                 0x348 0x730 0x000 0x0 0x0
-#define MX6Q_PAD_SD1_CMD__ECSPI5_MOSI             0x348 0x730 0x830 0x1 0x0
-#define MX6Q_PAD_SD1_CMD__PWM4_OUT                0x348 0x730 0x000 0x2 0x0
-#define MX6Q_PAD_SD1_CMD__GPT_COMPARE1            0x348 0x730 0x000 0x3 0x0
-#define MX6Q_PAD_SD1_CMD__GPIO1_IO18              0x348 0x730 0x000 0x5 0x0
-#define MX6Q_PAD_SD1_DAT2__SD1_DATA2              0x34c 0x734 0x000 0x0 0x0
-#define MX6Q_PAD_SD1_DAT2__ECSPI5_SS1             0x34c 0x734 0x838 0x1 0x1
-#define MX6Q_PAD_SD1_DAT2__GPT_COMPARE2           0x34c 0x734 0x000 0x2 0x0
-#define MX6Q_PAD_SD1_DAT2__PWM2_OUT               0x34c 0x734 0x000 0x3 0x0
-#define MX6Q_PAD_SD1_DAT2__WDOG1_B                0x34c 0x734 0x000 0x4 0x0
-#define MX6Q_PAD_SD1_DAT2__GPIO1_IO19             0x34c 0x734 0x000 0x5 0x0
-#define MX6Q_PAD_SD1_DAT2__WDOG1_RESET_B_DEB      0x34c 0x734 0x000 0x6 0x0
-#define MX6Q_PAD_SD1_CLK__SD1_CLK                 0x350 0x738 0x000 0x0 0x0
-#define MX6Q_PAD_SD1_CLK__ECSPI5_SCLK             0x350 0x738 0x828 0x1 0x0
-#define MX6Q_PAD_SD1_CLK__GPT_CLKIN               0x350 0x738 0x000 0x3 0x0
-#define MX6Q_PAD_SD1_CLK__GPIO1_IO20              0x350 0x738 0x000 0x5 0x0
-#define MX6Q_PAD_SD2_CLK__SD2_CLK                 0x354 0x73c 0x000 0x0 0x0
-#define MX6Q_PAD_SD2_CLK__ECSPI5_SCLK             0x354 0x73c 0x828 0x1 0x1
-#define MX6Q_PAD_SD2_CLK__KEY_COL5                0x354 0x73c 0x8e8 0x2 0x3
-#define MX6Q_PAD_SD2_CLK__AUD4_RXFS               0x354 0x73c 0x7c0 0x3 0x1
-#define MX6Q_PAD_SD2_CLK__GPIO1_IO10              0x354 0x73c 0x000 0x5 0x0
-#define MX6Q_PAD_SD2_CMD__SD2_CMD                 0x358 0x740 0x000 0x0 0x0
-#define MX6Q_PAD_SD2_CMD__ECSPI5_MOSI             0x358 0x740 0x830 0x1 0x1
-#define MX6Q_PAD_SD2_CMD__KEY_ROW5                0x358 0x740 0x8f4 0x2 0x2
-#define MX6Q_PAD_SD2_CMD__AUD4_RXC                0x358 0x740 0x7bc 0x3 0x1
-#define MX6Q_PAD_SD2_CMD__GPIO1_IO11              0x358 0x740 0x000 0x5 0x0
-#define MX6Q_PAD_SD2_DAT3__SD2_DATA3              0x35c 0x744 0x000 0x0 0x0
-#define MX6Q_PAD_SD2_DAT3__ECSPI5_SS3             0x35c 0x744 0x000 0x1 0x0
-#define MX6Q_PAD_SD2_DAT3__KEY_COL6               0x35c 0x744 0x8ec 0x2 0x2
-#define MX6Q_PAD_SD2_DAT3__AUD4_TXC               0x35c 0x744 0x7c4 0x3 0x1
-#define MX6Q_PAD_SD2_DAT3__GPIO1_IO12             0x35c 0x744 0x000 0x5 0x0
+#define MX6QDL_PAD_SD2_DAT1__SD2_DATA1              0x04c 0x360 0x000 0x0 0x0
+#define MX6QDL_PAD_SD2_DAT1__ECSPI5_SS0             0x04c 0x360 0x834 0x1 0x0
+#define MX6QDL_PAD_SD2_DAT1__EIM_CS2_B              0x04c 0x360 0x000 0x2 0x0
+#define MX6QDL_PAD_SD2_DAT1__AUD4_TXFS              0x04c 0x360 0x7c8 0x3 0x0
+#define MX6QDL_PAD_SD2_DAT1__KEY_COL7               0x04c 0x360 0x8f0 0x4 0x0
+#define MX6QDL_PAD_SD2_DAT1__GPIO1_IO14             0x04c 0x360 0x000 0x5 0x0
+#define MX6QDL_PAD_SD2_DAT2__SD2_DATA2              0x050 0x364 0x000 0x0 0x0
+#define MX6QDL_PAD_SD2_DAT2__ECSPI5_SS1             0x050 0x364 0x838 0x1 0x0
+#define MX6QDL_PAD_SD2_DAT2__EIM_CS3_B              0x050 0x364 0x000 0x2 0x0
+#define MX6QDL_PAD_SD2_DAT2__AUD4_TXD               0x050 0x364 0x7b8 0x3 0x0
+#define MX6QDL_PAD_SD2_DAT2__KEY_ROW6               0x050 0x364 0x8f8 0x4 0x0
+#define MX6QDL_PAD_SD2_DAT2__GPIO1_IO13             0x050 0x364 0x000 0x5 0x0
+#define MX6QDL_PAD_SD2_DAT0__SD2_DATA0              0x054 0x368 0x000 0x0 0x0
+#define MX6QDL_PAD_SD2_DAT0__ECSPI5_MISO            0x054 0x368 0x82c 0x1 0x0
+#define MX6QDL_PAD_SD2_DAT0__AUD4_RXD               0x054 0x368 0x7b4 0x3 0x0
+#define MX6QDL_PAD_SD2_DAT0__KEY_ROW7               0x054 0x368 0x8fc 0x4 0x0
+#define MX6QDL_PAD_SD2_DAT0__GPIO1_IO15             0x054 0x368 0x000 0x5 0x0
+#define MX6QDL_PAD_SD2_DAT0__DCIC2_OUT              0x054 0x368 0x000 0x6 0x0
+#define MX6QDL_PAD_RGMII_TXC__USB_H2_DATA           0x058 0x36c 0x000 0x0 0x0
+#define MX6QDL_PAD_RGMII_TXC__RGMII_TXC             0x058 0x36c 0x000 0x1 0x0
+#define MX6QDL_PAD_RGMII_TXC__SPDIF_EXT_CLK         0x058 0x36c 0x918 0x2 0x0
+#define MX6QDL_PAD_RGMII_TXC__GPIO6_IO19            0x058 0x36c 0x000 0x5 0x0
+#define MX6QDL_PAD_RGMII_TXC__XTALOSC_REF_CLK_24M   0x058 0x36c 0x000 0x7 0x0
+#define MX6QDL_PAD_RGMII_TD0__HSI_TX_READY          0x05c 0x370 0x000 0x0 0x0
+#define MX6QDL_PAD_RGMII_TD0__RGMII_TD0             0x05c 0x370 0x000 0x1 0x0
+#define MX6QDL_PAD_RGMII_TD0__GPIO6_IO20            0x05c 0x370 0x000 0x5 0x0
+#define MX6QDL_PAD_RGMII_TD1__HSI_RX_FLAG           0x060 0x374 0x000 0x0 0x0
+#define MX6QDL_PAD_RGMII_TD1__RGMII_TD1             0x060 0x374 0x000 0x1 0x0
+#define MX6QDL_PAD_RGMII_TD1__GPIO6_IO21            0x060 0x374 0x000 0x5 0x0
+#define MX6QDL_PAD_RGMII_TD2__HSI_RX_DATA           0x064 0x378 0x000 0x0 0x0
+#define MX6QDL_PAD_RGMII_TD2__RGMII_TD2             0x064 0x378 0x000 0x1 0x0
+#define MX6QDL_PAD_RGMII_TD2__GPIO6_IO22            0x064 0x378 0x000 0x5 0x0
+#define MX6QDL_PAD_RGMII_TD3__HSI_RX_WAKE           0x068 0x37c 0x000 0x0 0x0
+#define MX6QDL_PAD_RGMII_TD3__RGMII_TD3             0x068 0x37c 0x000 0x1 0x0
+#define MX6QDL_PAD_RGMII_TD3__GPIO6_IO23            0x068 0x37c 0x000 0x5 0x0
+#define MX6QDL_PAD_RGMII_RX_CTL__USB_H3_DATA        0x06c 0x380 0x000 0x0 0x0
+#define MX6QDL_PAD_RGMII_RX_CTL__RGMII_RX_CTL       0x06c 0x380 0x858 0x1 0x0
+#define MX6QDL_PAD_RGMII_RX_CTL__GPIO6_IO24         0x06c 0x380 0x000 0x5 0x0
+#define MX6QDL_PAD_RGMII_RD0__HSI_RX_READY          0x070 0x384 0x000 0x0 0x0
+#define MX6QDL_PAD_RGMII_RD0__RGMII_RD0             0x070 0x384 0x848 0x1 0x0
+#define MX6QDL_PAD_RGMII_RD0__GPIO6_IO25            0x070 0x384 0x000 0x5 0x0
+#define MX6QDL_PAD_RGMII_TX_CTL__USB_H2_STROBE      0x074 0x388 0x000 0x0 0x0
+#define MX6QDL_PAD_RGMII_TX_CTL__RGMII_TX_CTL       0x074 0x388 0x000 0x1 0x0
+#define MX6QDL_PAD_RGMII_TX_CTL__GPIO6_IO26         0x074 0x388 0x000 0x5 0x0
+#define MX6QDL_PAD_RGMII_TX_CTL__ENET_REF_CLK       0x074 0x388 0x83c 0x7 0x0
+#define MX6QDL_PAD_RGMII_RD1__HSI_TX_FLAG           0x078 0x38c 0x000 0x0 0x0
+#define MX6QDL_PAD_RGMII_RD1__RGMII_RD1             0x078 0x38c 0x84c 0x1 0x0
+#define MX6QDL_PAD_RGMII_RD1__GPIO6_IO27            0x078 0x38c 0x000 0x5 0x0
+#define MX6QDL_PAD_RGMII_RD2__HSI_TX_DATA           0x07c 0x390 0x000 0x0 0x0
+#define MX6QDL_PAD_RGMII_RD2__RGMII_RD2             0x07c 0x390 0x850 0x1 0x0
+#define MX6QDL_PAD_RGMII_RD2__GPIO6_IO28            0x07c 0x390 0x000 0x5 0x0
+#define MX6QDL_PAD_RGMII_RD3__HSI_TX_WAKE           0x080 0x394 0x000 0x0 0x0
+#define MX6QDL_PAD_RGMII_RD3__RGMII_RD3             0x080 0x394 0x854 0x1 0x0
+#define MX6QDL_PAD_RGMII_RD3__GPIO6_IO29            0x080 0x394 0x000 0x5 0x0
+#define MX6QDL_PAD_RGMII_RXC__USB_H3_STROBE         0x084 0x398 0x000 0x0 0x0
+#define MX6QDL_PAD_RGMII_RXC__RGMII_RXC             0x084 0x398 0x844 0x1 0x0
+#define MX6QDL_PAD_RGMII_RXC__GPIO6_IO30            0x084 0x398 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_A25__EIM_ADDR25              0x088 0x39c 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_A25__ECSPI4_SS1              0x088 0x39c 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_A25__ECSPI2_RDY              0x088 0x39c 0x000 0x2 0x0
+#define MX6QDL_PAD_EIM_A25__IPU1_DI1_PIN12          0x088 0x39c 0x000 0x3 0x0
+#define MX6QDL_PAD_EIM_A25__IPU1_DI0_D1_CS          0x088 0x39c 0x000 0x4 0x0
+#define MX6QDL_PAD_EIM_A25__GPIO5_IO02              0x088 0x39c 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_A25__HDMI_TX_CEC_LINE        0x088 0x39c 0x88c 0x6 0x0
+#define MX6QDL_PAD_EIM_EB2__EIM_EB2_B               0x08c 0x3a0 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_EB2__ECSPI1_SS0              0x08c 0x3a0 0x800 0x1 0x0
+#define MX6QDL_PAD_EIM_EB2__IPU2_CSI1_DATA19        0x08c 0x3a0 0x8d4 0x3 0x0
+#define MX6QDL_PAD_EIM_EB2__HDMI_TX_DDC_SCL         0x08c 0x3a0 0x890 0x4 0x0
+#define MX6QDL_PAD_EIM_EB2__GPIO2_IO30              0x08c 0x3a0 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_EB2__I2C2_SCL                0x08c 0x3a0 0x8a0 0x6 0x0
+#define MX6QDL_PAD_EIM_EB2__SRC_BOOT_CFG30          0x08c 0x3a0 0x000 0x7 0x0
+#define MX6QDL_PAD_EIM_D16__EIM_DATA16              0x090 0x3a4 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_D16__ECSPI1_SCLK             0x090 0x3a4 0x7f4 0x1 0x0
+#define MX6QDL_PAD_EIM_D16__IPU1_DI0_PIN05          0x090 0x3a4 0x000 0x2 0x0
+#define MX6QDL_PAD_EIM_D16__IPU2_CSI1_DATA18        0x090 0x3a4 0x8d0 0x3 0x0
+#define MX6QDL_PAD_EIM_D16__HDMI_TX_DDC_SDA         0x090 0x3a4 0x894 0x4 0x0
+#define MX6QDL_PAD_EIM_D16__GPIO3_IO16              0x090 0x3a4 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_D16__I2C2_SDA                0x090 0x3a4 0x8a4 0x6 0x0
+#define MX6QDL_PAD_EIM_D17__EIM_DATA17              0x094 0x3a8 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_D17__ECSPI1_MISO             0x094 0x3a8 0x7f8 0x1 0x0
+#define MX6QDL_PAD_EIM_D17__IPU1_DI0_PIN06          0x094 0x3a8 0x000 0x2 0x0
+#define MX6QDL_PAD_EIM_D17__IPU2_CSI1_PIXCLK        0x094 0x3a8 0x8e0 0x3 0x0
+#define MX6QDL_PAD_EIM_D17__DCIC1_OUT               0x094 0x3a8 0x000 0x4 0x0
+#define MX6QDL_PAD_EIM_D17__GPIO3_IO17              0x094 0x3a8 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_D17__I2C3_SCL                0x094 0x3a8 0x8a8 0x6 0x0
+#define MX6QDL_PAD_EIM_D18__EIM_DATA18              0x098 0x3ac 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_D18__ECSPI1_MOSI             0x098 0x3ac 0x7fc 0x1 0x0
+#define MX6QDL_PAD_EIM_D18__IPU1_DI0_PIN07          0x098 0x3ac 0x000 0x2 0x0
+#define MX6QDL_PAD_EIM_D18__IPU2_CSI1_DATA17        0x098 0x3ac 0x8cc 0x3 0x0
+#define MX6QDL_PAD_EIM_D18__IPU1_DI1_D0_CS          0x098 0x3ac 0x000 0x4 0x0
+#define MX6QDL_PAD_EIM_D18__GPIO3_IO18              0x098 0x3ac 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_D18__I2C3_SDA                0x098 0x3ac 0x8ac 0x6 0x0
+#define MX6QDL_PAD_EIM_D19__EIM_DATA19              0x09c 0x3b0 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_D19__ECSPI1_SS1              0x09c 0x3b0 0x804 0x1 0x0
+#define MX6QDL_PAD_EIM_D19__IPU1_DI0_PIN08          0x09c 0x3b0 0x000 0x2 0x0
+#define MX6QDL_PAD_EIM_D19__IPU2_CSI1_DATA16        0x09c 0x3b0 0x8c8 0x3 0x0
+#define MX6QDL_PAD_EIM_D19__UART1_CTS_B             0x09c 0x3b0 0x000 0x4 0x0
+#define MX6QDL_PAD_EIM_D19__UART1_RTS_B             0x09c 0x3b0 0x91c 0x4 0x0
+#define MX6QDL_PAD_EIM_D19__GPIO3_IO19              0x09c 0x3b0 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_D19__EPIT1_OUT               0x09c 0x3b0 0x000 0x6 0x0
+#define MX6QDL_PAD_EIM_D20__EIM_DATA20              0x0a0 0x3b4 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_D20__ECSPI4_SS0              0x0a0 0x3b4 0x824 0x1 0x0
+#define MX6QDL_PAD_EIM_D20__IPU1_DI0_PIN16          0x0a0 0x3b4 0x000 0x2 0x0
+#define MX6QDL_PAD_EIM_D20__IPU2_CSI1_DATA15        0x0a0 0x3b4 0x8c4 0x3 0x0
+#define MX6QDL_PAD_EIM_D20__UART1_RTS_B             0x0a0 0x3b4 0x91c 0x4 0x1
+#define MX6QDL_PAD_EIM_D20__UART1_CTS_B             0x0a0 0x3b4 0x000 0x4 0x0
+#define MX6QDL_PAD_EIM_D20__GPIO3_IO20              0x0a0 0x3b4 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_D20__EPIT2_OUT               0x0a0 0x3b4 0x000 0x6 0x0
+#define MX6QDL_PAD_EIM_D21__EIM_DATA21              0x0a4 0x3b8 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_D21__ECSPI4_SCLK             0x0a4 0x3b8 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_D21__IPU1_DI0_PIN17          0x0a4 0x3b8 0x000 0x2 0x0
+#define MX6QDL_PAD_EIM_D21__IPU2_CSI1_DATA11        0x0a4 0x3b8 0x8b4 0x3 0x0
+#define MX6QDL_PAD_EIM_D21__USB_OTG_OC              0x0a4 0x3b8 0x944 0x4 0x0
+#define MX6QDL_PAD_EIM_D21__GPIO3_IO21              0x0a4 0x3b8 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_D21__I2C1_SCL                0x0a4 0x3b8 0x898 0x6 0x0
+#define MX6QDL_PAD_EIM_D21__SPDIF_IN                0x0a4 0x3b8 0x914 0x7 0x0
+#define MX6QDL_PAD_EIM_D22__EIM_DATA22              0x0a8 0x3bc 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_D22__ECSPI4_MISO             0x0a8 0x3bc 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_D22__IPU1_DI0_PIN01          0x0a8 0x3bc 0x000 0x2 0x0
+#define MX6QDL_PAD_EIM_D22__IPU2_CSI1_DATA10        0x0a8 0x3bc 0x8b0 0x3 0x0
+#define MX6QDL_PAD_EIM_D22__USB_OTG_PWR             0x0a8 0x3bc 0x000 0x4 0x0
+#define MX6QDL_PAD_EIM_D22__GPIO3_IO22              0x0a8 0x3bc 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_D22__SPDIF_OUT               0x0a8 0x3bc 0x000 0x6 0x0
+#define MX6QDL_PAD_EIM_D23__EIM_DATA23              0x0ac 0x3c0 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_D23__IPU1_DI0_D0_CS          0x0ac 0x3c0 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_D23__UART3_CTS_B             0x0ac 0x3c0 0x000 0x2 0x0
+#define MX6QDL_PAD_EIM_D23__UART3_RTS_B             0x0ac 0x3c0 0x92c 0x2 0x0
+#define MX6QDL_PAD_EIM_D23__UART1_DCD_B             0x0ac 0x3c0 0x000 0x3 0x0
+#define MX6QDL_PAD_EIM_D23__IPU2_CSI1_DATA_EN       0x0ac 0x3c0 0x8d8 0x4 0x0
+#define MX6QDL_PAD_EIM_D23__GPIO3_IO23              0x0ac 0x3c0 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_D23__IPU1_DI1_PIN02          0x0ac 0x3c0 0x000 0x6 0x0
+#define MX6QDL_PAD_EIM_D23__IPU1_DI1_PIN14          0x0ac 0x3c0 0x000 0x7 0x0
+#define MX6QDL_PAD_EIM_EB3__EIM_EB3_B               0x0b0 0x3c4 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_EB3__ECSPI4_RDY              0x0b0 0x3c4 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_EB3__UART3_RTS_B             0x0b0 0x3c4 0x92c 0x2 0x1
+#define MX6QDL_PAD_EIM_EB3__UART3_CTS_B             0x0b0 0x3c4 0x000 0x2 0x0
+#define MX6QDL_PAD_EIM_EB3__UART1_RI_B              0x0b0 0x3c4 0x000 0x3 0x0
+#define MX6QDL_PAD_EIM_EB3__IPU2_CSI1_HSYNC         0x0b0 0x3c4 0x8dc 0x4 0x0
+#define MX6QDL_PAD_EIM_EB3__GPIO2_IO31              0x0b0 0x3c4 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_EB3__IPU1_DI1_PIN03          0x0b0 0x3c4 0x000 0x6 0x0
+#define MX6QDL_PAD_EIM_EB3__SRC_BOOT_CFG31          0x0b0 0x3c4 0x000 0x7 0x0
+#define MX6QDL_PAD_EIM_D24__EIM_DATA24              0x0b4 0x3c8 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_D24__ECSPI4_SS2              0x0b4 0x3c8 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_D24__UART3_TX_DATA           0x0b4 0x3c8 0x000 0x2 0x0
+#define MX6QDL_PAD_EIM_D24__UART3_RX_DATA           0x0b4 0x3c8 0x930 0x2 0x0
+#define MX6QDL_PAD_EIM_D24__ECSPI1_SS2              0x0b4 0x3c8 0x808 0x3 0x0
+#define MX6QDL_PAD_EIM_D24__ECSPI2_SS2              0x0b4 0x3c8 0x000 0x4 0x0
+#define MX6QDL_PAD_EIM_D24__GPIO3_IO24              0x0b4 0x3c8 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_D24__AUD5_RXFS               0x0b4 0x3c8 0x7d8 0x6 0x0
+#define MX6QDL_PAD_EIM_D24__UART1_DTR_B             0x0b4 0x3c8 0x000 0x7 0x0
+#define MX6QDL_PAD_EIM_D25__EIM_DATA25              0x0b8 0x3cc 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_D25__ECSPI4_SS3              0x0b8 0x3cc 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_D25__UART3_RX_DATA           0x0b8 0x3cc 0x930 0x2 0x1
+#define MX6QDL_PAD_EIM_D25__UART3_TX_DATA           0x0b8 0x3cc 0x000 0x2 0x0
+#define MX6QDL_PAD_EIM_D25__ECSPI1_SS3              0x0b8 0x3cc 0x80c 0x3 0x0
+#define MX6QDL_PAD_EIM_D25__ECSPI2_SS3              0x0b8 0x3cc 0x000 0x4 0x0
+#define MX6QDL_PAD_EIM_D25__GPIO3_IO25              0x0b8 0x3cc 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_D25__AUD5_RXC                0x0b8 0x3cc 0x7d4 0x6 0x0
+#define MX6QDL_PAD_EIM_D25__UART1_DSR_B             0x0b8 0x3cc 0x000 0x7 0x0
+#define MX6QDL_PAD_EIM_D26__EIM_DATA26              0x0bc 0x3d0 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_D26__IPU1_DI1_PIN11          0x0bc 0x3d0 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_D26__IPU1_CSI0_DATA01        0x0bc 0x3d0 0x000 0x2 0x0
+#define MX6QDL_PAD_EIM_D26__IPU2_CSI1_DATA14        0x0bc 0x3d0 0x8c0 0x3 0x0
+#define MX6QDL_PAD_EIM_D26__UART2_TX_DATA           0x0bc 0x3d0 0x000 0x4 0x0
+#define MX6QDL_PAD_EIM_D26__UART2_RX_DATA           0x0bc 0x3d0 0x928 0x4 0x0
+#define MX6QDL_PAD_EIM_D26__GPIO3_IO26              0x0bc 0x3d0 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_D26__IPU1_SISG2              0x0bc 0x3d0 0x000 0x6 0x0
+#define MX6QDL_PAD_EIM_D26__IPU1_DISP1_DATA22       0x0bc 0x3d0 0x000 0x7 0x0
+#define MX6QDL_PAD_EIM_D27__EIM_DATA27              0x0c0 0x3d4 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_D27__IPU1_DI1_PIN13          0x0c0 0x3d4 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_D27__IPU1_CSI0_DATA00        0x0c0 0x3d4 0x000 0x2 0x0
+#define MX6QDL_PAD_EIM_D27__IPU2_CSI1_DATA13        0x0c0 0x3d4 0x8bc 0x3 0x0
+#define MX6QDL_PAD_EIM_D27__UART2_RX_DATA           0x0c0 0x3d4 0x928 0x4 0x1
+#define MX6QDL_PAD_EIM_D27__UART2_TX_DATA           0x0c0 0x3d4 0x000 0x4 0x0
+#define MX6QDL_PAD_EIM_D27__GPIO3_IO27              0x0c0 0x3d4 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_D27__IPU1_SISG3              0x0c0 0x3d4 0x000 0x6 0x0
+#define MX6QDL_PAD_EIM_D27__IPU1_DISP1_DATA23       0x0c0 0x3d4 0x000 0x7 0x0
+#define MX6QDL_PAD_EIM_D28__EIM_DATA28              0x0c4 0x3d8 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_D28__I2C1_SDA                0x0c4 0x3d8 0x89c 0x1 0x0
+#define MX6QDL_PAD_EIM_D28__ECSPI4_MOSI             0x0c4 0x3d8 0x000 0x2 0x0
+#define MX6QDL_PAD_EIM_D28__IPU2_CSI1_DATA12        0x0c4 0x3d8 0x8b8 0x3 0x0
+#define MX6QDL_PAD_EIM_D28__UART2_CTS_B             0x0c4 0x3d8 0x000 0x4 0x0
+#define MX6QDL_PAD_EIM_D28__UART2_RTS_B             0x0c4 0x3d8 0x924 0x4 0x0
+#define MX6QDL_PAD_EIM_D28__UART2_DTE_CTS_B         0x0c4 0x3d8 0x924 0x4 0x0
+#define MX6QDL_PAD_EIM_D28__UART2_DTE_RTS_B         0x0c4 0x3d8 0x000 0x4 0x0
+#define MX6QDL_PAD_EIM_D28__GPIO3_IO28              0x0c4 0x3d8 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_D28__IPU1_EXT_TRIG           0x0c4 0x3d8 0x000 0x6 0x0
+#define MX6QDL_PAD_EIM_D28__IPU1_DI0_PIN13          0x0c4 0x3d8 0x000 0x7 0x0
+#define MX6QDL_PAD_EIM_D29__EIM_DATA29              0x0c8 0x3dc 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_D29__IPU1_DI1_PIN15          0x0c8 0x3dc 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_D29__ECSPI4_SS0              0x0c8 0x3dc 0x824 0x2 0x1
+#define MX6QDL_PAD_EIM_D29__UART2_RTS_B             0x0c8 0x3dc 0x924 0x4 0x1
+#define MX6QDL_PAD_EIM_D29__UART2_CTS_B             0x0c8 0x3dc 0x000 0x4 0x0
+#define MX6QDL_PAD_EIM_D29__UART2_DTE_RTS_B         0x0c8 0x3dc 0x000 0x4 0x0
+#define MX6QDL_PAD_EIM_D29__UART2_DTE_CTS_B         0x0c8 0x3dc 0x924 0x4 0x1
+#define MX6QDL_PAD_EIM_D29__GPIO3_IO29              0x0c8 0x3dc 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_D29__IPU2_CSI1_VSYNC         0x0c8 0x3dc 0x8e4 0x6 0x0
+#define MX6QDL_PAD_EIM_D29__IPU1_DI0_PIN14          0x0c8 0x3dc 0x000 0x7 0x0
+#define MX6QDL_PAD_EIM_D30__EIM_DATA30              0x0cc 0x3e0 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_D30__IPU1_DISP1_DATA21       0x0cc 0x3e0 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_D30__IPU1_DI0_PIN11          0x0cc 0x3e0 0x000 0x2 0x0
+#define MX6QDL_PAD_EIM_D30__IPU1_CSI0_DATA03        0x0cc 0x3e0 0x000 0x3 0x0
+#define MX6QDL_PAD_EIM_D30__UART3_CTS_B             0x0cc 0x3e0 0x000 0x4 0x0
+#define MX6QDL_PAD_EIM_D30__UART3_RTS_B             0x0cc 0x3e0 0x92c 0x4 0x2
+#define MX6QDL_PAD_EIM_D30__GPIO3_IO30              0x0cc 0x3e0 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_D30__USB_H1_OC               0x0cc 0x3e0 0x948 0x6 0x0
+#define MX6QDL_PAD_EIM_D31__EIM_DATA31              0x0d0 0x3e4 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_D31__IPU1_DISP1_DATA20       0x0d0 0x3e4 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_D31__IPU1_DI0_PIN12          0x0d0 0x3e4 0x000 0x2 0x0
+#define MX6QDL_PAD_EIM_D31__IPU1_CSI0_DATA02        0x0d0 0x3e4 0x000 0x3 0x0
+#define MX6QDL_PAD_EIM_D31__UART3_RTS_B             0x0d0 0x3e4 0x92c 0x4 0x3
+#define MX6QDL_PAD_EIM_D31__UART3_CTS_B             0x0d0 0x3e4 0x000 0x4 0x0
+#define MX6QDL_PAD_EIM_D31__GPIO3_IO31              0x0d0 0x3e4 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_D31__USB_H1_PWR              0x0d0 0x3e4 0x000 0x6 0x0
+#define MX6QDL_PAD_EIM_A24__EIM_ADDR24              0x0d4 0x3e8 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_A24__IPU1_DISP1_DATA19       0x0d4 0x3e8 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_A24__IPU2_CSI1_DATA19        0x0d4 0x3e8 0x8d4 0x2 0x1
+#define MX6QDL_PAD_EIM_A24__IPU2_SISG2              0x0d4 0x3e8 0x000 0x3 0x0
+#define MX6QDL_PAD_EIM_A24__IPU1_SISG2              0x0d4 0x3e8 0x000 0x4 0x0
+#define MX6QDL_PAD_EIM_A24__GPIO5_IO04              0x0d4 0x3e8 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_A24__SRC_BOOT_CFG24          0x0d4 0x3e8 0x000 0x7 0x0
+#define MX6QDL_PAD_EIM_A23__EIM_ADDR23              0x0d8 0x3ec 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_A23__IPU1_DISP1_DATA18       0x0d8 0x3ec 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_A23__IPU2_CSI1_DATA18        0x0d8 0x3ec 0x8d0 0x2 0x1
+#define MX6QDL_PAD_EIM_A23__IPU2_SISG3              0x0d8 0x3ec 0x000 0x3 0x0
+#define MX6QDL_PAD_EIM_A23__IPU1_SISG3              0x0d8 0x3ec 0x000 0x4 0x0
+#define MX6QDL_PAD_EIM_A23__GPIO6_IO06              0x0d8 0x3ec 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_A23__SRC_BOOT_CFG23          0x0d8 0x3ec 0x000 0x7 0x0
+#define MX6QDL_PAD_EIM_A22__EIM_ADDR22              0x0dc 0x3f0 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_A22__IPU1_DISP1_DATA17       0x0dc 0x3f0 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_A22__IPU2_CSI1_DATA17        0x0dc 0x3f0 0x8cc 0x2 0x1
+#define MX6QDL_PAD_EIM_A22__GPIO2_IO16              0x0dc 0x3f0 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_A22__SRC_BOOT_CFG22          0x0dc 0x3f0 0x000 0x7 0x0
+#define MX6QDL_PAD_EIM_A21__EIM_ADDR21              0x0e0 0x3f4 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_A21__IPU1_DISP1_DATA16       0x0e0 0x3f4 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_A21__IPU2_CSI1_DATA16        0x0e0 0x3f4 0x8c8 0x2 0x1
+#define MX6QDL_PAD_EIM_A21__GPIO2_IO17              0x0e0 0x3f4 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_A21__SRC_BOOT_CFG21          0x0e0 0x3f4 0x000 0x7 0x0
+#define MX6QDL_PAD_EIM_A20__EIM_ADDR20              0x0e4 0x3f8 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_A20__IPU1_DISP1_DATA15       0x0e4 0x3f8 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_A20__IPU2_CSI1_DATA15        0x0e4 0x3f8 0x8c4 0x2 0x1
+#define MX6QDL_PAD_EIM_A20__GPIO2_IO18              0x0e4 0x3f8 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_A20__SRC_BOOT_CFG20          0x0e4 0x3f8 0x000 0x7 0x0
+#define MX6QDL_PAD_EIM_A19__EIM_ADDR19              0x0e8 0x3fc 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_A19__IPU1_DISP1_DATA14       0x0e8 0x3fc 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_A19__IPU2_CSI1_DATA14        0x0e8 0x3fc 0x8c0 0x2 0x1
+#define MX6QDL_PAD_EIM_A19__GPIO2_IO19              0x0e8 0x3fc 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_A19__SRC_BOOT_CFG19          0x0e8 0x3fc 0x000 0x7 0x0
+#define MX6QDL_PAD_EIM_A18__EIM_ADDR18              0x0ec 0x400 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_A18__IPU1_DISP1_DATA13       0x0ec 0x400 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_A18__IPU2_CSI1_DATA13        0x0ec 0x400 0x8bc 0x2 0x1
+#define MX6QDL_PAD_EIM_A18__GPIO2_IO20              0x0ec 0x400 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_A18__SRC_BOOT_CFG18          0x0ec 0x400 0x000 0x7 0x0
+#define MX6QDL_PAD_EIM_A17__EIM_ADDR17              0x0f0 0x404 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_A17__IPU1_DISP1_DATA12       0x0f0 0x404 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_A17__IPU2_CSI1_DATA12        0x0f0 0x404 0x8b8 0x2 0x1
+#define MX6QDL_PAD_EIM_A17__GPIO2_IO21              0x0f0 0x404 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_A17__SRC_BOOT_CFG17          0x0f0 0x404 0x000 0x7 0x0
+#define MX6QDL_PAD_EIM_A16__EIM_ADDR16              0x0f4 0x408 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_A16__IPU1_DI1_DISP_CLK       0x0f4 0x408 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_A16__IPU2_CSI1_PIXCLK        0x0f4 0x408 0x8e0 0x2 0x1
+#define MX6QDL_PAD_EIM_A16__GPIO2_IO22              0x0f4 0x408 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_A16__SRC_BOOT_CFG16          0x0f4 0x408 0x000 0x7 0x0
+#define MX6QDL_PAD_EIM_CS0__EIM_CS0_B               0x0f8 0x40c 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_CS0__IPU1_DI1_PIN05          0x0f8 0x40c 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_CS0__ECSPI2_SCLK             0x0f8 0x40c 0x810 0x2 0x0
+#define MX6QDL_PAD_EIM_CS0__GPIO2_IO23              0x0f8 0x40c 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_CS1__EIM_CS1_B               0x0fc 0x410 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_CS1__IPU1_DI1_PIN06          0x0fc 0x410 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_CS1__ECSPI2_MOSI             0x0fc 0x410 0x818 0x2 0x0
+#define MX6QDL_PAD_EIM_CS1__GPIO2_IO24              0x0fc 0x410 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_OE__EIM_OE_B                 0x100 0x414 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_OE__IPU1_DI1_PIN07           0x100 0x414 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_OE__ECSPI2_MISO              0x100 0x414 0x814 0x2 0x0
+#define MX6QDL_PAD_EIM_OE__GPIO2_IO25               0x100 0x414 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_RW__EIM_RW                   0x104 0x418 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_RW__IPU1_DI1_PIN08           0x104 0x418 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_RW__ECSPI2_SS0               0x104 0x418 0x81c 0x2 0x0
+#define MX6QDL_PAD_EIM_RW__GPIO2_IO26               0x104 0x418 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_RW__SRC_BOOT_CFG29           0x104 0x418 0x000 0x7 0x0
+#define MX6QDL_PAD_EIM_LBA__EIM_LBA_B               0x108 0x41c 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_LBA__IPU1_DI1_PIN17          0x108 0x41c 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_LBA__ECSPI2_SS1              0x108 0x41c 0x820 0x2 0x0
+#define MX6QDL_PAD_EIM_LBA__GPIO2_IO27              0x108 0x41c 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_LBA__SRC_BOOT_CFG26          0x108 0x41c 0x000 0x7 0x0
+#define MX6QDL_PAD_EIM_EB0__EIM_EB0_B               0x10c 0x420 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_EB0__IPU1_DISP1_DATA11       0x10c 0x420 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_EB0__IPU2_CSI1_DATA11        0x10c 0x420 0x8b4 0x2 0x1
+#define MX6QDL_PAD_EIM_EB0__CCM_PMIC_READY          0x10c 0x420 0x7f0 0x4 0x0
+#define MX6QDL_PAD_EIM_EB0__GPIO2_IO28              0x10c 0x420 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_EB0__SRC_BOOT_CFG27          0x10c 0x420 0x000 0x7 0x0
+#define MX6QDL_PAD_EIM_EB1__EIM_EB1_B               0x110 0x424 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_EB1__IPU1_DISP1_DATA10       0x110 0x424 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_EB1__IPU2_CSI1_DATA10        0x110 0x424 0x8b0 0x2 0x1
+#define MX6QDL_PAD_EIM_EB1__GPIO2_IO29              0x110 0x424 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_EB1__SRC_BOOT_CFG28          0x110 0x424 0x000 0x7 0x0
+#define MX6QDL_PAD_EIM_DA0__EIM_AD00                0x114 0x428 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_DA0__IPU1_DISP1_DATA09       0x114 0x428 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_DA0__IPU2_CSI1_DATA09        0x114 0x428 0x000 0x2 0x0
+#define MX6QDL_PAD_EIM_DA0__GPIO3_IO00              0x114 0x428 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_DA0__SRC_BOOT_CFG00          0x114 0x428 0x000 0x7 0x0
+#define MX6QDL_PAD_EIM_DA1__EIM_AD01                0x118 0x42c 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_DA1__IPU1_DISP1_DATA08       0x118 0x42c 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_DA1__IPU2_CSI1_DATA08        0x118 0x42c 0x000 0x2 0x0
+#define MX6QDL_PAD_EIM_DA1__GPIO3_IO01              0x118 0x42c 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_DA1__SRC_BOOT_CFG01          0x118 0x42c 0x000 0x7 0x0
+#define MX6QDL_PAD_EIM_DA2__EIM_AD02                0x11c 0x430 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_DA2__IPU1_DISP1_DATA07       0x11c 0x430 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_DA2__IPU2_CSI1_DATA07        0x11c 0x430 0x000 0x2 0x0
+#define MX6QDL_PAD_EIM_DA2__GPIO3_IO02              0x11c 0x430 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_DA2__SRC_BOOT_CFG02          0x11c 0x430 0x000 0x7 0x0
+#define MX6QDL_PAD_EIM_DA3__EIM_AD03                0x120 0x434 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_DA3__IPU1_DISP1_DATA06       0x120 0x434 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_DA3__IPU2_CSI1_DATA06        0x120 0x434 0x000 0x2 0x0
+#define MX6QDL_PAD_EIM_DA3__GPIO3_IO03              0x120 0x434 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_DA3__SRC_BOOT_CFG03          0x120 0x434 0x000 0x7 0x0
+#define MX6QDL_PAD_EIM_DA4__EIM_AD04                0x124 0x438 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_DA4__IPU1_DISP1_DATA05       0x124 0x438 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_DA4__IPU2_CSI1_DATA05        0x124 0x438 0x000 0x2 0x0
+#define MX6QDL_PAD_EIM_DA4__GPIO3_IO04              0x124 0x438 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_DA4__SRC_BOOT_CFG04          0x124 0x438 0x000 0x7 0x0
+#define MX6QDL_PAD_EIM_DA5__EIM_AD05                0x128 0x43c 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_DA5__IPU1_DISP1_DATA04       0x128 0x43c 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_DA5__IPU2_CSI1_DATA04        0x128 0x43c 0x000 0x2 0x0
+#define MX6QDL_PAD_EIM_DA5__GPIO3_IO05              0x128 0x43c 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_DA5__SRC_BOOT_CFG05          0x128 0x43c 0x000 0x7 0x0
+#define MX6QDL_PAD_EIM_DA6__EIM_AD06                0x12c 0x440 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_DA6__IPU1_DISP1_DATA03       0x12c 0x440 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_DA6__IPU2_CSI1_DATA03        0x12c 0x440 0x000 0x2 0x0
+#define MX6QDL_PAD_EIM_DA6__GPIO3_IO06              0x12c 0x440 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_DA6__SRC_BOOT_CFG06          0x12c 0x440 0x000 0x7 0x0
+#define MX6QDL_PAD_EIM_DA7__EIM_AD07                0x130 0x444 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_DA7__IPU1_DISP1_DATA02       0x130 0x444 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_DA7__IPU2_CSI1_DATA02        0x130 0x444 0x000 0x2 0x0
+#define MX6QDL_PAD_EIM_DA7__GPIO3_IO07              0x130 0x444 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_DA7__SRC_BOOT_CFG07          0x130 0x444 0x000 0x7 0x0
+#define MX6QDL_PAD_EIM_DA8__EIM_AD08                0x134 0x448 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_DA8__IPU1_DISP1_DATA01       0x134 0x448 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_DA8__IPU2_CSI1_DATA01        0x134 0x448 0x000 0x2 0x0
+#define MX6QDL_PAD_EIM_DA8__GPIO3_IO08              0x134 0x448 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_DA8__SRC_BOOT_CFG08          0x134 0x448 0x000 0x7 0x0
+#define MX6QDL_PAD_EIM_DA9__EIM_AD09                0x138 0x44c 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_DA9__IPU1_DISP1_DATA00       0x138 0x44c 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_DA9__IPU2_CSI1_DATA00        0x138 0x44c 0x000 0x2 0x0
+#define MX6QDL_PAD_EIM_DA9__GPIO3_IO09              0x138 0x44c 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_DA9__SRC_BOOT_CFG09          0x138 0x44c 0x000 0x7 0x0
+#define MX6QDL_PAD_EIM_DA10__EIM_AD10               0x13c 0x450 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_DA10__IPU1_DI1_PIN15         0x13c 0x450 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_DA10__IPU2_CSI1_DATA_EN      0x13c 0x450 0x8d8 0x2 0x1
+#define MX6QDL_PAD_EIM_DA10__GPIO3_IO10             0x13c 0x450 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_DA10__SRC_BOOT_CFG10         0x13c 0x450 0x000 0x7 0x0
+#define MX6QDL_PAD_EIM_DA11__EIM_AD11               0x140 0x454 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_DA11__IPU1_DI1_PIN02         0x140 0x454 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_DA11__IPU2_CSI1_HSYNC        0x140 0x454 0x8dc 0x2 0x1
+#define MX6QDL_PAD_EIM_DA11__GPIO3_IO11             0x140 0x454 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_DA11__SRC_BOOT_CFG11         0x140 0x454 0x000 0x7 0x0
+#define MX6QDL_PAD_EIM_DA12__EIM_AD12               0x144 0x458 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_DA12__IPU1_DI1_PIN03         0x144 0x458 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_DA12__IPU2_CSI1_VSYNC        0x144 0x458 0x8e4 0x2 0x1
+#define MX6QDL_PAD_EIM_DA12__GPIO3_IO12             0x144 0x458 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_DA12__SRC_BOOT_CFG12         0x144 0x458 0x000 0x7 0x0
+#define MX6QDL_PAD_EIM_DA13__EIM_AD13               0x148 0x45c 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_DA13__IPU1_DI1_D0_CS         0x148 0x45c 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_DA13__GPIO3_IO13             0x148 0x45c 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_DA13__SRC_BOOT_CFG13         0x148 0x45c 0x000 0x7 0x0
+#define MX6QDL_PAD_EIM_DA14__EIM_AD14               0x14c 0x460 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_DA14__IPU1_DI1_D1_CS         0x14c 0x460 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_DA14__GPIO3_IO14             0x14c 0x460 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_DA14__SRC_BOOT_CFG14         0x14c 0x460 0x000 0x7 0x0
+#define MX6QDL_PAD_EIM_DA15__EIM_AD15               0x150 0x464 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_DA15__IPU1_DI1_PIN01         0x150 0x464 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_DA15__IPU1_DI1_PIN04         0x150 0x464 0x000 0x2 0x0
+#define MX6QDL_PAD_EIM_DA15__GPIO3_IO15             0x150 0x464 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_DA15__SRC_BOOT_CFG15         0x150 0x464 0x000 0x7 0x0
+#define MX6QDL_PAD_EIM_WAIT__EIM_WAIT_B             0x154 0x468 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_WAIT__EIM_DTACK_B            0x154 0x468 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_WAIT__GPIO5_IO00             0x154 0x468 0x000 0x5 0x0
+#define MX6QDL_PAD_EIM_WAIT__SRC_BOOT_CFG25         0x154 0x468 0x000 0x7 0x0
+#define MX6QDL_PAD_EIM_BCLK__EIM_BCLK               0x158 0x46c 0x000 0x0 0x0
+#define MX6QDL_PAD_EIM_BCLK__IPU1_DI1_PIN16         0x158 0x46c 0x000 0x1 0x0
+#define MX6QDL_PAD_EIM_BCLK__GPIO6_IO31             0x158 0x46c 0x000 0x5 0x0
+#define MX6QDL_PAD_DI0_DISP_CLK__IPU1_DI0_DISP_CLK  0x15c 0x470 0x000 0x0 0x0
+#define MX6QDL_PAD_DI0_DISP_CLK__IPU2_DI0_DISP_CLK  0x15c 0x470 0x000 0x1 0x0
+#define MX6QDL_PAD_DI0_DISP_CLK__GPIO4_IO16         0x15c 0x470 0x000 0x5 0x0
+#define MX6QDL_PAD_DI0_PIN15__IPU1_DI0_PIN15        0x160 0x474 0x000 0x0 0x0
+#define MX6QDL_PAD_DI0_PIN15__IPU2_DI0_PIN15        0x160 0x474 0x000 0x1 0x0
+#define MX6QDL_PAD_DI0_PIN15__AUD6_TXC              0x160 0x474 0x000 0x2 0x0
+#define MX6QDL_PAD_DI0_PIN15__GPIO4_IO17            0x160 0x474 0x000 0x5 0x0
+#define MX6QDL_PAD_DI0_PIN2__IPU1_DI0_PIN02         0x164 0x478 0x000 0x0 0x0
+#define MX6QDL_PAD_DI0_PIN2__IPU2_DI0_PIN02         0x164 0x478 0x000 0x1 0x0
+#define MX6QDL_PAD_DI0_PIN2__AUD6_TXD               0x164 0x478 0x000 0x2 0x0
+#define MX6QDL_PAD_DI0_PIN2__GPIO4_IO18             0x164 0x478 0x000 0x5 0x0
+#define MX6QDL_PAD_DI0_PIN3__IPU1_DI0_PIN03         0x168 0x47c 0x000 0x0 0x0
+#define MX6QDL_PAD_DI0_PIN3__IPU2_DI0_PIN03         0x168 0x47c 0x000 0x1 0x0
+#define MX6QDL_PAD_DI0_PIN3__AUD6_TXFS              0x168 0x47c 0x000 0x2 0x0
+#define MX6QDL_PAD_DI0_PIN3__GPIO4_IO19             0x168 0x47c 0x000 0x5 0x0
+#define MX6QDL_PAD_DI0_PIN4__IPU1_DI0_PIN04         0x16c 0x480 0x000 0x0 0x0
+#define MX6QDL_PAD_DI0_PIN4__IPU2_DI0_PIN04         0x16c 0x480 0x000 0x1 0x0
+#define MX6QDL_PAD_DI0_PIN4__AUD6_RXD               0x16c 0x480 0x000 0x2 0x0
+#define MX6QDL_PAD_DI0_PIN4__SD1_WP                 0x16c 0x480 0x94c 0x3 0x0
+#define MX6QDL_PAD_DI0_PIN4__GPIO4_IO20             0x16c 0x480 0x000 0x5 0x0
+#define MX6QDL_PAD_DISP0_DAT0__IPU1_DISP0_DATA00    0x170 0x484 0x000 0x0 0x0
+#define MX6QDL_PAD_DISP0_DAT0__IPU2_DISP0_DATA00    0x170 0x484 0x000 0x1 0x0
+#define MX6QDL_PAD_DISP0_DAT0__ECSPI3_SCLK          0x170 0x484 0x000 0x2 0x0
+#define MX6QDL_PAD_DISP0_DAT0__GPIO4_IO21           0x170 0x484 0x000 0x5 0x0
+#define MX6QDL_PAD_DISP0_DAT1__IPU1_DISP0_DATA01    0x174 0x488 0x000 0x0 0x0
+#define MX6QDL_PAD_DISP0_DAT1__IPU2_DISP0_DATA01    0x174 0x488 0x000 0x1 0x0
+#define MX6QDL_PAD_DISP0_DAT1__ECSPI3_MOSI          0x174 0x488 0x000 0x2 0x0
+#define MX6QDL_PAD_DISP0_DAT1__GPIO4_IO22           0x174 0x488 0x000 0x5 0x0
+#define MX6QDL_PAD_DISP0_DAT2__IPU1_DISP0_DATA02    0x178 0x48c 0x000 0x0 0x0
+#define MX6QDL_PAD_DISP0_DAT2__IPU2_DISP0_DATA02    0x178 0x48c 0x000 0x1 0x0
+#define MX6QDL_PAD_DISP0_DAT2__ECSPI3_MISO          0x178 0x48c 0x000 0x2 0x0
+#define MX6QDL_PAD_DISP0_DAT2__GPIO4_IO23           0x178 0x48c 0x000 0x5 0x0
+#define MX6QDL_PAD_DISP0_DAT3__IPU1_DISP0_DATA03    0x17c 0x490 0x000 0x0 0x0
+#define MX6QDL_PAD_DISP0_DAT3__IPU2_DISP0_DATA03    0x17c 0x490 0x000 0x1 0x0
+#define MX6QDL_PAD_DISP0_DAT3__ECSPI3_SS0           0x17c 0x490 0x000 0x2 0x0
+#define MX6QDL_PAD_DISP0_DAT3__GPIO4_IO24           0x17c 0x490 0x000 0x5 0x0
+#define MX6QDL_PAD_DISP0_DAT4__IPU1_DISP0_DATA04    0x180 0x494 0x000 0x0 0x0
+#define MX6QDL_PAD_DISP0_DAT4__IPU2_DISP0_DATA04    0x180 0x494 0x000 0x1 0x0
+#define MX6QDL_PAD_DISP0_DAT4__ECSPI3_SS1           0x180 0x494 0x000 0x2 0x0
+#define MX6QDL_PAD_DISP0_DAT4__GPIO4_IO25           0x180 0x494 0x000 0x5 0x0
+#define MX6QDL_PAD_DISP0_DAT5__IPU1_DISP0_DATA05    0x184 0x498 0x000 0x0 0x0
+#define MX6QDL_PAD_DISP0_DAT5__IPU2_DISP0_DATA05    0x184 0x498 0x000 0x1 0x0
+#define MX6QDL_PAD_DISP0_DAT5__ECSPI3_SS2           0x184 0x498 0x000 0x2 0x0
+#define MX6QDL_PAD_DISP0_DAT5__AUD6_RXFS            0x184 0x498 0x000 0x3 0x0
+#define MX6QDL_PAD_DISP0_DAT5__GPIO4_IO26           0x184 0x498 0x000 0x5 0x0
+#define MX6QDL_PAD_DISP0_DAT6__IPU1_DISP0_DATA06    0x188 0x49c 0x000 0x0 0x0
+#define MX6QDL_PAD_DISP0_DAT6__IPU2_DISP0_DATA06    0x188 0x49c 0x000 0x1 0x0
+#define MX6QDL_PAD_DISP0_DAT6__ECSPI3_SS3           0x188 0x49c 0x000 0x2 0x0
+#define MX6QDL_PAD_DISP0_DAT6__AUD6_RXC             0x188 0x49c 0x000 0x3 0x0
+#define MX6QDL_PAD_DISP0_DAT6__GPIO4_IO27           0x188 0x49c 0x000 0x5 0x0
+#define MX6QDL_PAD_DISP0_DAT7__IPU1_DISP0_DATA07    0x18c 0x4a0 0x000 0x0 0x0
+#define MX6QDL_PAD_DISP0_DAT7__IPU2_DISP0_DATA07    0x18c 0x4a0 0x000 0x1 0x0
+#define MX6QDL_PAD_DISP0_DAT7__ECSPI3_RDY           0x18c 0x4a0 0x000 0x2 0x0
+#define MX6QDL_PAD_DISP0_DAT7__GPIO4_IO28           0x18c 0x4a0 0x000 0x5 0x0
+#define MX6QDL_PAD_DISP0_DAT8__IPU1_DISP0_DATA08    0x190 0x4a4 0x000 0x0 0x0
+#define MX6QDL_PAD_DISP0_DAT8__IPU2_DISP0_DATA08    0x190 0x4a4 0x000 0x1 0x0
+#define MX6QDL_PAD_DISP0_DAT8__PWM1_OUT             0x190 0x4a4 0x000 0x2 0x0
+#define MX6QDL_PAD_DISP0_DAT8__WDOG1_B              0x190 0x4a4 0x000 0x3 0x0
+#define MX6QDL_PAD_DISP0_DAT8__GPIO4_IO29           0x190 0x4a4 0x000 0x5 0x0
+#define MX6QDL_PAD_DISP0_DAT9__IPU1_DISP0_DATA09    0x194 0x4a8 0x000 0x0 0x0
+#define MX6QDL_PAD_DISP0_DAT9__IPU2_DISP0_DATA09    0x194 0x4a8 0x000 0x1 0x0
+#define MX6QDL_PAD_DISP0_DAT9__PWM2_OUT             0x194 0x4a8 0x000 0x2 0x0
+#define MX6QDL_PAD_DISP0_DAT9__WDOG2_B              0x194 0x4a8 0x000 0x3 0x0
+#define MX6QDL_PAD_DISP0_DAT9__GPIO4_IO30           0x194 0x4a8 0x000 0x5 0x0
+#define MX6QDL_PAD_DISP0_DAT10__IPU1_DISP0_DATA10   0x198 0x4ac 0x000 0x0 0x0
+#define MX6QDL_PAD_DISP0_DAT10__IPU2_DISP0_DATA10   0x198 0x4ac 0x000 0x1 0x0
+#define MX6QDL_PAD_DISP0_DAT10__GPIO4_IO31          0x198 0x4ac 0x000 0x5 0x0
+#define MX6QDL_PAD_DISP0_DAT11__IPU1_DISP0_DATA11   0x19c 0x4b0 0x000 0x0 0x0
+#define MX6QDL_PAD_DISP0_DAT11__IPU2_DISP0_DATA11   0x19c 0x4b0 0x000 0x1 0x0
+#define MX6QDL_PAD_DISP0_DAT11__GPIO5_IO05          0x19c 0x4b0 0x000 0x5 0x0
+#define MX6QDL_PAD_DISP0_DAT12__IPU1_DISP0_DATA12   0x1a0 0x4b4 0x000 0x0 0x0
+#define MX6QDL_PAD_DISP0_DAT12__IPU2_DISP0_DATA12   0x1a0 0x4b4 0x000 0x1 0x0
+#define MX6QDL_PAD_DISP0_DAT12__GPIO5_IO06          0x1a0 0x4b4 0x000 0x5 0x0
+#define MX6QDL_PAD_DISP0_DAT13__IPU1_DISP0_DATA13   0x1a4 0x4b8 0x000 0x0 0x0
+#define MX6QDL_PAD_DISP0_DAT13__IPU2_DISP0_DATA13   0x1a4 0x4b8 0x000 0x1 0x0
+#define MX6QDL_PAD_DISP0_DAT13__AUD5_RXFS           0x1a4 0x4b8 0x7d8 0x3 0x1
+#define MX6QDL_PAD_DISP0_DAT13__GPIO5_IO07          0x1a4 0x4b8 0x000 0x5 0x0
+#define MX6QDL_PAD_DISP0_DAT14__IPU1_DISP0_DATA14   0x1a8 0x4bc 0x000 0x0 0x0
+#define MX6QDL_PAD_DISP0_DAT14__IPU2_DISP0_DATA14   0x1a8 0x4bc 0x000 0x1 0x0
+#define MX6QDL_PAD_DISP0_DAT14__AUD5_RXC            0x1a8 0x4bc 0x7d4 0x3 0x1
+#define MX6QDL_PAD_DISP0_DAT14__GPIO5_IO08          0x1a8 0x4bc 0x000 0x5 0x0
+#define MX6QDL_PAD_DISP0_DAT15__IPU1_DISP0_DATA15   0x1ac 0x4c0 0x000 0x0 0x0
+#define MX6QDL_PAD_DISP0_DAT15__IPU2_DISP0_DATA15   0x1ac 0x4c0 0x000 0x1 0x0
+#define MX6QDL_PAD_DISP0_DAT15__ECSPI1_SS1          0x1ac 0x4c0 0x804 0x2 0x1
+#define MX6QDL_PAD_DISP0_DAT15__ECSPI2_SS1          0x1ac 0x4c0 0x820 0x3 0x1
+#define MX6QDL_PAD_DISP0_DAT15__GPIO5_IO09          0x1ac 0x4c0 0x000 0x5 0x0
+#define MX6QDL_PAD_DISP0_DAT16__IPU1_DISP0_DATA16   0x1b0 0x4c4 0x000 0x0 0x0
+#define MX6QDL_PAD_DISP0_DAT16__IPU2_DISP0_DATA16   0x1b0 0x4c4 0x000 0x1 0x0
+#define MX6QDL_PAD_DISP0_DAT16__ECSPI2_MOSI         0x1b0 0x4c4 0x818 0x2 0x1
+#define MX6QDL_PAD_DISP0_DAT16__AUD5_TXC            0x1b0 0x4c4 0x7dc 0x3 0x0
+#define MX6QDL_PAD_DISP0_DAT16__SDMA_EXT_EVENT0     0x1b0 0x4c4 0x90c 0x4 0x0
+#define MX6QDL_PAD_DISP0_DAT16__GPIO5_IO10          0x1b0 0x4c4 0x000 0x5 0x0
+#define MX6QDL_PAD_DISP0_DAT17__IPU1_DISP0_DATA17   0x1b4 0x4c8 0x000 0x0 0x0
+#define MX6QDL_PAD_DISP0_DAT17__IPU2_DISP0_DATA17   0x1b4 0x4c8 0x000 0x1 0x0
+#define MX6QDL_PAD_DISP0_DAT17__ECSPI2_MISO         0x1b4 0x4c8 0x814 0x2 0x1
+#define MX6QDL_PAD_DISP0_DAT17__AUD5_TXD            0x1b4 0x4c8 0x7d0 0x3 0x0
+#define MX6QDL_PAD_DISP0_DAT17__SDMA_EXT_EVENT1     0x1b4 0x4c8 0x910 0x4 0x0
+#define MX6QDL_PAD_DISP0_DAT17__GPIO5_IO11          0x1b4 0x4c8 0x000 0x5 0x0
+#define MX6QDL_PAD_DISP0_DAT18__IPU1_DISP0_DATA18   0x1b8 0x4cc 0x000 0x0 0x0
+#define MX6QDL_PAD_DISP0_DAT18__IPU2_DISP0_DATA18   0x1b8 0x4cc 0x000 0x1 0x0
+#define MX6QDL_PAD_DISP0_DAT18__ECSPI2_SS0          0x1b8 0x4cc 0x81c 0x2 0x1
+#define MX6QDL_PAD_DISP0_DAT18__AUD5_TXFS           0x1b8 0x4cc 0x7e0 0x3 0x0
+#define MX6QDL_PAD_DISP0_DAT18__AUD4_RXFS           0x1b8 0x4cc 0x7c0 0x4 0x0
+#define MX6QDL_PAD_DISP0_DAT18__GPIO5_IO12          0x1b8 0x4cc 0x000 0x5 0x0
+#define MX6QDL_PAD_DISP0_DAT18__EIM_CS2_B           0x1b8 0x4cc 0x000 0x7 0x0
+#define MX6QDL_PAD_DISP0_DAT19__IPU1_DISP0_DATA19   0x1bc 0x4d0 0x000 0x0 0x0
+#define MX6QDL_PAD_DISP0_DAT19__IPU2_DISP0_DATA19   0x1bc 0x4d0 0x000 0x1 0x0
+#define MX6QDL_PAD_DISP0_DAT19__ECSPI2_SCLK         0x1bc 0x4d0 0x810 0x2 0x1
+#define MX6QDL_PAD_DISP0_DAT19__AUD5_RXD            0x1bc 0x4d0 0x7cc 0x3 0x0
+#define MX6QDL_PAD_DISP0_DAT19__AUD4_RXC            0x1bc 0x4d0 0x7bc 0x4 0x0
+#define MX6QDL_PAD_DISP0_DAT19__GPIO5_IO13          0x1bc 0x4d0 0x000 0x5 0x0
+#define MX6QDL_PAD_DISP0_DAT19__EIM_CS3_B           0x1bc 0x4d0 0x000 0x7 0x0
+#define MX6QDL_PAD_DISP0_DAT20__IPU1_DISP0_DATA20   0x1c0 0x4d4 0x000 0x0 0x0
+#define MX6QDL_PAD_DISP0_DAT20__IPU2_DISP0_DATA20   0x1c0 0x4d4 0x000 0x1 0x0
+#define MX6QDL_PAD_DISP0_DAT20__ECSPI1_SCLK         0x1c0 0x4d4 0x7f4 0x2 0x1
+#define MX6QDL_PAD_DISP0_DAT20__AUD4_TXC            0x1c0 0x4d4 0x7c4 0x3 0x0
+#define MX6QDL_PAD_DISP0_DAT20__GPIO5_IO14          0x1c0 0x4d4 0x000 0x5 0x0
+#define MX6QDL_PAD_DISP0_DAT21__IPU1_DISP0_DATA21   0x1c4 0x4d8 0x000 0x0 0x0
+#define MX6QDL_PAD_DISP0_DAT21__IPU2_DISP0_DATA21   0x1c4 0x4d8 0x000 0x1 0x0
+#define MX6QDL_PAD_DISP0_DAT21__ECSPI1_MOSI         0x1c4 0x4d8 0x7fc 0x2 0x1
+#define MX6QDL_PAD_DISP0_DAT21__AUD4_TXD            0x1c4 0x4d8 0x7b8 0x3 0x1
+#define MX6QDL_PAD_DISP0_DAT21__GPIO5_IO15          0x1c4 0x4d8 0x000 0x5 0x0
+#define MX6QDL_PAD_DISP0_DAT22__IPU1_DISP0_DATA22   0x1c8 0x4dc 0x000 0x0 0x0
+#define MX6QDL_PAD_DISP0_DAT22__IPU2_DISP0_DATA22   0x1c8 0x4dc 0x000 0x1 0x0
+#define MX6QDL_PAD_DISP0_DAT22__ECSPI1_MISO         0x1c8 0x4dc 0x7f8 0x2 0x1
+#define MX6QDL_PAD_DISP0_DAT22__AUD4_TXFS           0x1c8 0x4dc 0x7c8 0x3 0x1
+#define MX6QDL_PAD_DISP0_DAT22__GPIO5_IO16          0x1c8 0x4dc 0x000 0x5 0x0
+#define MX6QDL_PAD_DISP0_DAT23__IPU1_DISP0_DATA23   0x1cc 0x4e0 0x000 0x0 0x0
+#define MX6QDL_PAD_DISP0_DAT23__IPU2_DISP0_DATA23   0x1cc 0x4e0 0x000 0x1 0x0
+#define MX6QDL_PAD_DISP0_DAT23__ECSPI1_SS0          0x1cc 0x4e0 0x800 0x2 0x1
+#define MX6QDL_PAD_DISP0_DAT23__AUD4_RXD            0x1cc 0x4e0 0x7b4 0x3 0x1
+#define MX6QDL_PAD_DISP0_DAT23__GPIO5_IO17          0x1cc 0x4e0 0x000 0x5 0x0
+#define MX6QDL_PAD_ENET_MDIO__ENET_MDIO             0x1d0 0x4e4 0x840 0x1 0x0
+#define MX6QDL_PAD_ENET_MDIO__ESAI_RX_CLK           0x1d0 0x4e4 0x86c 0x2 0x0
+#define MX6QDL_PAD_ENET_MDIO__ENET_1588_EVENT1_OUT  0x1d0 0x4e4 0x000 0x4 0x0
+#define MX6QDL_PAD_ENET_MDIO__GPIO1_IO22            0x1d0 0x4e4 0x000 0x5 0x0
+#define MX6QDL_PAD_ENET_MDIO__SPDIF_LOCK            0x1d0 0x4e4 0x000 0x6 0x0
+#define MX6QDL_PAD_ENET_REF_CLK__ENET_TX_CLK        0x1d4 0x4e8 0x000 0x1 0x0
+#define MX6QDL_PAD_ENET_REF_CLK__ESAI_RX_FS         0x1d4 0x4e8 0x85c 0x2 0x0
+#define MX6QDL_PAD_ENET_REF_CLK__GPIO1_IO23         0x1d4 0x4e8 0x000 0x5 0x0
+#define MX6QDL_PAD_ENET_REF_CLK__SPDIF_SR_CLK       0x1d4 0x4e8 0x000 0x6 0x0
+#define MX6QDL_PAD_ENET_RX_ER__USB_OTG_ID           0x1d8 0x4ec 0x000 0x0 0x0
+#define MX6QDL_PAD_ENET_RX_ER__ENET_RX_ER           0x1d8 0x4ec 0x000 0x1 0x0
+#define MX6QDL_PAD_ENET_RX_ER__ESAI_RX_HF_CLK       0x1d8 0x4ec 0x864 0x2 0x0
+#define MX6QDL_PAD_ENET_RX_ER__SPDIF_IN             0x1d8 0x4ec 0x914 0x3 0x1
+#define MX6QDL_PAD_ENET_RX_ER__ENET_1588_EVENT2_OUT 0x1d8 0x4ec 0x000 0x4 0x0
+#define MX6QDL_PAD_ENET_RX_ER__GPIO1_IO24           0x1d8 0x4ec 0x000 0x5 0x0
+#define MX6QDL_PAD_ENET_CRS_DV__ENET_RX_EN          0x1dc 0x4f0 0x858 0x1 0x1
+#define MX6QDL_PAD_ENET_CRS_DV__ESAI_TX_CLK         0x1dc 0x4f0 0x870 0x2 0x0
+#define MX6QDL_PAD_ENET_CRS_DV__SPDIF_EXT_CLK       0x1dc 0x4f0 0x918 0x3 0x1
+#define MX6QDL_PAD_ENET_CRS_DV__GPIO1_IO25          0x1dc 0x4f0 0x000 0x5 0x0
+#define MX6QDL_PAD_ENET_RXD1__MLB_SIG               0x1e0 0x4f4 0x908 0x0 0x0
+#define MX6QDL_PAD_ENET_RXD1__ENET_RX_DATA1         0x1e0 0x4f4 0x84c 0x1 0x1
+#define MX6QDL_PAD_ENET_RXD1__ESAI_TX_FS            0x1e0 0x4f4 0x860 0x2 0x0
+#define MX6QDL_PAD_ENET_RXD1__ENET_1588_EVENT3_OUT  0x1e0 0x4f4 0x000 0x4 0x0
+#define MX6QDL_PAD_ENET_RXD1__GPIO1_IO26            0x1e0 0x4f4 0x000 0x5 0x0
+#define MX6QDL_PAD_ENET_RXD0__ENET_RX_DATA0         0x1e4 0x4f8 0x848 0x1 0x1
+#define MX6QDL_PAD_ENET_RXD0__ESAI_TX_HF_CLK        0x1e4 0x4f8 0x868 0x2 0x0
+#define MX6QDL_PAD_ENET_RXD0__SPDIF_OUT             0x1e4 0x4f8 0x000 0x3 0x0
+#define MX6QDL_PAD_ENET_RXD0__GPIO1_IO27            0x1e4 0x4f8 0x000 0x5 0x0
+#define MX6QDL_PAD_ENET_TX_EN__ENET_TX_EN           0x1e8 0x4fc 0x000 0x1 0x0
+#define MX6QDL_PAD_ENET_TX_EN__ESAI_TX3_RX2         0x1e8 0x4fc 0x880 0x2 0x0
+#define MX6QDL_PAD_ENET_TX_EN__GPIO1_IO28           0x1e8 0x4fc 0x000 0x5 0x0
+#define MX6QDL_PAD_ENET_TXD1__MLB_CLK               0x1ec 0x500 0x900 0x0 0x0
+#define MX6QDL_PAD_ENET_TXD1__ENET_TX_DATA1         0x1ec 0x500 0x000 0x1 0x0
+#define MX6QDL_PAD_ENET_TXD1__ESAI_TX2_RX3          0x1ec 0x500 0x87c 0x2 0x0
+#define MX6QDL_PAD_ENET_TXD1__ENET_1588_EVENT0_IN   0x1ec 0x500 0x000 0x4 0x0
+#define MX6QDL_PAD_ENET_TXD1__GPIO1_IO29            0x1ec 0x500 0x000 0x5 0x0
+#define MX6QDL_PAD_ENET_TXD0__ENET_TX_DATA0         0x1f0 0x504 0x000 0x1 0x0
+#define MX6QDL_PAD_ENET_TXD0__ESAI_TX4_RX1          0x1f0 0x504 0x884 0x2 0x0
+#define MX6QDL_PAD_ENET_TXD0__GPIO1_IO30            0x1f0 0x504 0x000 0x5 0x0
+#define MX6QDL_PAD_ENET_MDC__MLB_DATA               0x1f4 0x508 0x904 0x0 0x0
+#define MX6QDL_PAD_ENET_MDC__ENET_MDC               0x1f4 0x508 0x000 0x1 0x0
+#define MX6QDL_PAD_ENET_MDC__ESAI_TX5_RX0           0x1f4 0x508 0x888 0x2 0x0
+#define MX6QDL_PAD_ENET_MDC__ENET_1588_EVENT1_IN    0x1f4 0x508 0x000 0x4 0x0
+#define MX6QDL_PAD_ENET_MDC__GPIO1_IO31             0x1f4 0x508 0x000 0x5 0x0
+#define MX6QDL_PAD_KEY_COL0__ECSPI1_SCLK            0x1f8 0x5c8 0x7f4 0x0 0x2
+#define MX6QDL_PAD_KEY_COL0__ENET_RX_DATA3          0x1f8 0x5c8 0x854 0x1 0x1
+#define MX6QDL_PAD_KEY_COL0__AUD5_TXC               0x1f8 0x5c8 0x7dc 0x2 0x1
+#define MX6QDL_PAD_KEY_COL0__KEY_COL0               0x1f8 0x5c8 0x000 0x3 0x0
+#define MX6QDL_PAD_KEY_COL0__UART4_TX_DATA          0x1f8 0x5c8 0x000 0x4 0x0
+#define MX6QDL_PAD_KEY_COL0__UART4_RX_DATA          0x1f8 0x5c8 0x938 0x4 0x0
+#define MX6QDL_PAD_KEY_COL0__GPIO4_IO06             0x1f8 0x5c8 0x000 0x5 0x0
+#define MX6QDL_PAD_KEY_COL0__DCIC1_OUT              0x1f8 0x5c8 0x000 0x6 0x0
+#define MX6QDL_PAD_KEY_ROW0__ECSPI1_MOSI            0x1fc 0x5cc 0x7fc 0x0 0x2
+#define MX6QDL_PAD_KEY_ROW0__ENET_TX_DATA3          0x1fc 0x5cc 0x000 0x1 0x0
+#define MX6QDL_PAD_KEY_ROW0__AUD5_TXD               0x1fc 0x5cc 0x7d0 0x2 0x1
+#define MX6QDL_PAD_KEY_ROW0__KEY_ROW0               0x1fc 0x5cc 0x000 0x3 0x0
+#define MX6QDL_PAD_KEY_ROW0__UART4_RX_DATA          0x1fc 0x5cc 0x938 0x4 0x1
+#define MX6QDL_PAD_KEY_ROW0__UART4_TX_DATA          0x1fc 0x5cc 0x000 0x4 0x0
+#define MX6QDL_PAD_KEY_ROW0__GPIO4_IO07             0x1fc 0x5cc 0x000 0x5 0x0
+#define MX6QDL_PAD_KEY_ROW0__DCIC2_OUT              0x1fc 0x5cc 0x000 0x6 0x0
+#define MX6QDL_PAD_KEY_COL1__ECSPI1_MISO            0x200 0x5d0 0x7f8 0x0 0x2
+#define MX6QDL_PAD_KEY_COL1__ENET_MDIO              0x200 0x5d0 0x840 0x1 0x1
+#define MX6QDL_PAD_KEY_COL1__AUD5_TXFS              0x200 0x5d0 0x7e0 0x2 0x1
+#define MX6QDL_PAD_KEY_COL1__KEY_COL1               0x200 0x5d0 0x000 0x3 0x0
+#define MX6QDL_PAD_KEY_COL1__UART5_TX_DATA          0x200 0x5d0 0x000 0x4 0x0
+#define MX6QDL_PAD_KEY_COL1__UART5_RX_DATA          0x200 0x5d0 0x940 0x4 0x0
+#define MX6QDL_PAD_KEY_COL1__GPIO4_IO08             0x200 0x5d0 0x000 0x5 0x0
+#define MX6QDL_PAD_KEY_COL1__SD1_VSELECT            0x200 0x5d0 0x000 0x6 0x0
+#define MX6QDL_PAD_KEY_ROW1__ECSPI1_SS0             0x204 0x5d4 0x800 0x0 0x2
+#define MX6QDL_PAD_KEY_ROW1__ENET_COL               0x204 0x5d4 0x000 0x1 0x0
+#define MX6QDL_PAD_KEY_ROW1__AUD5_RXD               0x204 0x5d4 0x7cc 0x2 0x1
+#define MX6QDL_PAD_KEY_ROW1__KEY_ROW1               0x204 0x5d4 0x000 0x3 0x0
+#define MX6QDL_PAD_KEY_ROW1__UART5_RX_DATA          0x204 0x5d4 0x940 0x4 0x1
+#define MX6QDL_PAD_KEY_ROW1__UART5_TX_DATA          0x204 0x5d4 0x000 0x4 0x0
+#define MX6QDL_PAD_KEY_ROW1__GPIO4_IO09             0x204 0x5d4 0x000 0x5 0x0
+#define MX6QDL_PAD_KEY_ROW1__SD2_VSELECT            0x204 0x5d4 0x000 0x6 0x0
+#define MX6QDL_PAD_KEY_COL2__ECSPI1_SS1             0x208 0x5d8 0x804 0x0 0x2
+#define MX6QDL_PAD_KEY_COL2__ENET_RX_DATA2          0x208 0x5d8 0x850 0x1 0x1
+#define MX6QDL_PAD_KEY_COL2__FLEXCAN1_TX            0x208 0x5d8 0x000 0x2 0x0
+#define MX6QDL_PAD_KEY_COL2__KEY_COL2               0x208 0x5d8 0x000 0x3 0x0
+#define MX6QDL_PAD_KEY_COL2__ENET_MDC               0x208 0x5d8 0x000 0x4 0x0
+#define MX6QDL_PAD_KEY_COL2__GPIO4_IO10             0x208 0x5d8 0x000 0x5 0x0
+#define MX6QDL_PAD_KEY_COL2__USB_H1_PWR_CTL_WAKE    0x208 0x5d8 0x000 0x6 0x0
+#define MX6QDL_PAD_KEY_ROW2__ECSPI1_SS2             0x20c 0x5dc 0x808 0x0 0x1
+#define MX6QDL_PAD_KEY_ROW2__ENET_TX_DATA2          0x20c 0x5dc 0x000 0x1 0x0
+#define MX6QDL_PAD_KEY_ROW2__FLEXCAN1_RX            0x20c 0x5dc 0x7e4 0x2 0x0
+#define MX6QDL_PAD_KEY_ROW2__KEY_ROW2               0x20c 0x5dc 0x000 0x3 0x0
+#define MX6QDL_PAD_KEY_ROW2__SD2_VSELECT            0x20c 0x5dc 0x000 0x4 0x0
+#define MX6QDL_PAD_KEY_ROW2__GPIO4_IO11             0x20c 0x5dc 0x000 0x5 0x0
+#define MX6QDL_PAD_KEY_ROW2__HDMI_TX_CEC_LINE       0x20c 0x5dc 0x88c 0x6 0x1
+#define MX6QDL_PAD_KEY_COL3__ECSPI1_SS3             0x210 0x5e0 0x80c 0x0 0x1
+#define MX6QDL_PAD_KEY_COL3__ENET_CRS               0x210 0x5e0 0x000 0x1 0x0
+#define MX6QDL_PAD_KEY_COL3__HDMI_TX_DDC_SCL        0x210 0x5e0 0x890 0x2 0x1
+#define MX6QDL_PAD_KEY_COL3__KEY_COL3               0x210 0x5e0 0x000 0x3 0x0
+#define MX6QDL_PAD_KEY_COL3__I2C2_SCL               0x210 0x5e0 0x8a0 0x4 0x1
+#define MX6QDL_PAD_KEY_COL3__GPIO4_IO12             0x210 0x5e0 0x000 0x5 0x0
+#define MX6QDL_PAD_KEY_COL3__SPDIF_IN               0x210 0x5e0 0x914 0x6 0x2
+#define MX6QDL_PAD_KEY_ROW3__ASRC_EXT_CLK           0x214 0x5e4 0x7b0 0x1 0x0
+#define MX6QDL_PAD_KEY_ROW3__HDMI_TX_DDC_SDA        0x214 0x5e4 0x894 0x2 0x1
+#define MX6QDL_PAD_KEY_ROW3__KEY_ROW3               0x214 0x5e4 0x000 0x3 0x0
+#define MX6QDL_PAD_KEY_ROW3__I2C2_SDA               0x214 0x5e4 0x8a4 0x4 0x1
+#define MX6QDL_PAD_KEY_ROW3__GPIO4_IO13             0x214 0x5e4 0x000 0x5 0x0
+#define MX6QDL_PAD_KEY_ROW3__SD1_VSELECT            0x214 0x5e4 0x000 0x6 0x0
+#define MX6QDL_PAD_KEY_COL4__FLEXCAN2_TX            0x218 0x5e8 0x000 0x0 0x0
+#define MX6QDL_PAD_KEY_COL4__IPU1_SISG4             0x218 0x5e8 0x000 0x1 0x0
+#define MX6QDL_PAD_KEY_COL4__USB_OTG_OC             0x218 0x5e8 0x944 0x2 0x1
+#define MX6QDL_PAD_KEY_COL4__KEY_COL4               0x218 0x5e8 0x000 0x3 0x0
+#define MX6QDL_PAD_KEY_COL4__UART5_RTS_B            0x218 0x5e8 0x93c 0x4 0x0
+#define MX6QDL_PAD_KEY_COL4__UART5_CTS_B            0x218 0x5e8 0x000 0x4 0x0
+#define MX6QDL_PAD_KEY_COL4__GPIO4_IO14             0x218 0x5e8 0x000 0x5 0x0
+#define MX6QDL_PAD_KEY_ROW4__FLEXCAN2_RX            0x21c 0x5ec 0x7e8 0x0 0x0
+#define MX6QDL_PAD_KEY_ROW4__IPU1_SISG5             0x21c 0x5ec 0x000 0x1 0x0
+#define MX6QDL_PAD_KEY_ROW4__USB_OTG_PWR            0x21c 0x5ec 0x000 0x2 0x0
+#define MX6QDL_PAD_KEY_ROW4__KEY_ROW4               0x21c 0x5ec 0x000 0x3 0x0
+#define MX6QDL_PAD_KEY_ROW4__UART5_CTS_B            0x21c 0x5ec 0x000 0x4 0x0
+#define MX6QDL_PAD_KEY_ROW4__UART5_RTS_B            0x21c 0x5ec 0x93c 0x4 0x1
+#define MX6QDL_PAD_KEY_ROW4__GPIO4_IO15             0x21c 0x5ec 0x000 0x5 0x0
+#define MX6QDL_PAD_GPIO_0__CCM_CLKO1                0x220 0x5f0 0x000 0x0 0x0
+#define MX6QDL_PAD_GPIO_0__KEY_COL5                 0x220 0x5f0 0x8e8 0x2 0x0
+#define MX6QDL_PAD_GPIO_0__ASRC_EXT_CLK             0x220 0x5f0 0x7b0 0x3 0x1
+#define MX6QDL_PAD_GPIO_0__EPIT1_OUT                0x220 0x5f0 0x000 0x4 0x0
+#define MX6QDL_PAD_GPIO_0__GPIO1_IO00               0x220 0x5f0 0x000 0x5 0x0
+#define MX6QDL_PAD_GPIO_0__USB_H1_PWR               0x220 0x5f0 0x000 0x6 0x0
+#define MX6QDL_PAD_GPIO_0__SNVS_VIO_5               0x220 0x5f0 0x000 0x7 0x0
+#define MX6QDL_PAD_GPIO_1__ESAI_RX_CLK              0x224 0x5f4 0x86c 0x0 0x1
+#define MX6QDL_PAD_GPIO_1__WDOG2_B                  0x224 0x5f4 0x000 0x1 0x0
+#define MX6QDL_PAD_GPIO_1__KEY_ROW5                 0x224 0x5f4 0x8f4 0x2 0x0
+#define MX6QDL_PAD_GPIO_1__USB_OTG_ID               0x224 0x5f4 0x000 0x3 0x0
+#define MX6QDL_PAD_GPIO_1__PWM2_OUT                 0x224 0x5f4 0x000 0x4 0x0
+#define MX6QDL_PAD_GPIO_1__GPIO1_IO01               0x224 0x5f4 0x000 0x5 0x0
+#define MX6QDL_PAD_GPIO_1__SD1_CD_B                 0x224 0x5f4 0x000 0x6 0x0
+#define MX6QDL_PAD_GPIO_9__ESAI_RX_FS               0x228 0x5f8 0x85c 0x0 0x1
+#define MX6QDL_PAD_GPIO_9__WDOG1_B                  0x228 0x5f8 0x000 0x1 0x0
+#define MX6QDL_PAD_GPIO_9__KEY_COL6                 0x228 0x5f8 0x8ec 0x2 0x0
+#define MX6QDL_PAD_GPIO_9__CCM_REF_EN_B             0x228 0x5f8 0x000 0x3 0x0
+#define MX6QDL_PAD_GPIO_9__PWM1_OUT                 0x228 0x5f8 0x000 0x4 0x0
+#define MX6QDL_PAD_GPIO_9__GPIO1_IO09               0x228 0x5f8 0x000 0x5 0x0
+#define MX6QDL_PAD_GPIO_9__SD1_WP                   0x228 0x5f8 0x94c 0x6 0x1
+#define MX6QDL_PAD_GPIO_3__ESAI_RX_HF_CLK           0x22c 0x5fc 0x864 0x0 0x1
+#define MX6QDL_PAD_GPIO_3__I2C3_SCL                 0x22c 0x5fc 0x8a8 0x2 0x1
+#define MX6QDL_PAD_GPIO_3__XTALOSC_REF_CLK_24M      0x22c 0x5fc 0x000 0x3 0x0
+#define MX6QDL_PAD_GPIO_3__CCM_CLKO2                0x22c 0x5fc 0x000 0x4 0x0
+#define MX6QDL_PAD_GPIO_3__GPIO1_IO03               0x22c 0x5fc 0x000 0x5 0x0
+#define MX6QDL_PAD_GPIO_3__USB_H1_OC                0x22c 0x5fc 0x948 0x6 0x1
+#define MX6QDL_PAD_GPIO_3__MLB_CLK                  0x22c 0x5fc 0x900 0x7 0x1
+#define MX6QDL_PAD_GPIO_6__ESAI_TX_CLK              0x230 0x600 0x870 0x0 0x1
+#define MX6QDL_PAD_GPIO_6__I2C3_SDA                 0x230 0x600 0x8ac 0x2 0x1
+#define MX6QDL_PAD_GPIO_6__GPIO1_IO06               0x230 0x600 0x000 0x5 0x0
+#define MX6QDL_PAD_GPIO_6__SD2_LCTL                 0x230 0x600 0x000 0x6 0x0
+#define MX6QDL_PAD_GPIO_6__MLB_SIG                  0x230 0x600 0x908 0x7 0x1
+#define MX6QDL_PAD_GPIO_2__ESAI_TX_FS               0x234 0x604 0x860 0x0 0x1
+#define MX6QDL_PAD_GPIO_2__KEY_ROW6                 0x234 0x604 0x8f8 0x2 0x1
+#define MX6QDL_PAD_GPIO_2__GPIO1_IO02               0x234 0x604 0x000 0x5 0x0
+#define MX6QDL_PAD_GPIO_2__SD2_WP                   0x234 0x604 0x000 0x6 0x0
+#define MX6QDL_PAD_GPIO_2__MLB_DATA                 0x234 0x604 0x904 0x7 0x1
+#define MX6QDL_PAD_GPIO_4__ESAI_TX_HF_CLK           0x238 0x608 0x868 0x0 0x1
+#define MX6QDL_PAD_GPIO_4__KEY_COL7                 0x238 0x608 0x8f0 0x2 0x1
+#define MX6QDL_PAD_GPIO_4__GPIO1_IO04               0x238 0x608 0x000 0x5 0x0
+#define MX6QDL_PAD_GPIO_4__SD2_CD_B                 0x238 0x608 0x000 0x6 0x0
+#define MX6QDL_PAD_GPIO_5__ESAI_TX2_RX3             0x23c 0x60c 0x87c 0x0 0x1
+#define MX6QDL_PAD_GPIO_5__KEY_ROW7                 0x23c 0x60c 0x8fc 0x2 0x1
+#define MX6QDL_PAD_GPIO_5__CCM_CLKO1                0x23c 0x60c 0x000 0x3 0x0
+#define MX6QDL_PAD_GPIO_5__GPIO1_IO05               0x23c 0x60c 0x000 0x5 0x0
+#define MX6QDL_PAD_GPIO_5__I2C3_SCL                 0x23c 0x60c 0x8a8 0x6 0x2
+#define MX6QDL_PAD_GPIO_5__ARM_EVENTI               0x23c 0x60c 0x000 0x7 0x0
+#define MX6QDL_PAD_GPIO_7__ESAI_TX4_RX1             0x240 0x610 0x884 0x0 0x1
+#define MX6QDL_PAD_GPIO_7__ECSPI5_RDY               0x240 0x610 0x000 0x1 0x0
+#define MX6QDL_PAD_GPIO_7__EPIT1_OUT                0x240 0x610 0x000 0x2 0x0
+#define MX6QDL_PAD_GPIO_7__FLEXCAN1_TX              0x240 0x610 0x000 0x3 0x0
+#define MX6QDL_PAD_GPIO_7__UART2_TX_DATA            0x240 0x610 0x000 0x4 0x0
+#define MX6QDL_PAD_GPIO_7__UART2_RX_DATA            0x240 0x610 0x928 0x4 0x2
+#define MX6QDL_PAD_GPIO_7__GPIO1_IO07               0x240 0x610 0x000 0x5 0x0
+#define MX6QDL_PAD_GPIO_7__SPDIF_LOCK               0x240 0x610 0x000 0x6 0x0
+#define MX6QDL_PAD_GPIO_7__USB_OTG_HOST_MODE        0x240 0x610 0x000 0x7 0x0
+#define MX6QDL_PAD_GPIO_8__ESAI_TX5_RX0             0x244 0x614 0x888 0x0 0x1
+#define MX6QDL_PAD_GPIO_8__XTALOSC_REF_CLK_32K      0x244 0x614 0x000 0x1 0x0
+#define MX6QDL_PAD_GPIO_8__EPIT2_OUT                0x244 0x614 0x000 0x2 0x0
+#define MX6QDL_PAD_GPIO_8__FLEXCAN1_RX              0x244 0x614 0x7e4 0x3 0x1
+#define MX6QDL_PAD_GPIO_8__UART2_RX_DATA            0x244 0x614 0x928 0x4 0x3
+#define MX6QDL_PAD_GPIO_8__UART2_TX_DATA            0x244 0x614 0x000 0x4 0x0
+#define MX6QDL_PAD_GPIO_8__GPIO1_IO08               0x244 0x614 0x000 0x5 0x0
+#define MX6QDL_PAD_GPIO_8__SPDIF_SR_CLK             0x244 0x614 0x000 0x6 0x0
+#define MX6QDL_PAD_GPIO_8__USB_OTG_PWR_CTL_WAKE     0x244 0x614 0x000 0x7 0x0
+#define MX6QDL_PAD_GPIO_16__ESAI_TX3_RX2            0x248 0x618 0x880 0x0 0x1
+#define MX6QDL_PAD_GPIO_16__ENET_1588_EVENT2_IN     0x248 0x618 0x000 0x1 0x0
+#define MX6QDL_PAD_GPIO_16__ENET_REF_CLK            0x248 0x618 0x83c 0x2 0x1
+#define MX6QDL_PAD_GPIO_16__SD1_LCTL                0x248 0x618 0x000 0x3 0x0
+#define MX6QDL_PAD_GPIO_16__SPDIF_IN                0x248 0x618 0x914 0x4 0x3
+#define MX6QDL_PAD_GPIO_16__GPIO7_IO11              0x248 0x618 0x000 0x5 0x0
+#define MX6QDL_PAD_GPIO_16__I2C3_SDA                0x248 0x618 0x8ac 0x6 0x2
+#define MX6QDL_PAD_GPIO_16__JTAG_DE_B               0x248 0x618 0x000 0x7 0x0
+#define MX6QDL_PAD_GPIO_17__ESAI_TX0                0x24c 0x61c 0x874 0x0 0x0
+#define MX6QDL_PAD_GPIO_17__ENET_1588_EVENT3_IN     0x24c 0x61c 0x000 0x1 0x0
+#define MX6QDL_PAD_GPIO_17__CCM_PMIC_READY          0x24c 0x61c 0x7f0 0x2 0x1
+#define MX6QDL_PAD_GPIO_17__SDMA_EXT_EVENT0         0x24c 0x61c 0x90c 0x3 0x1
+#define MX6QDL_PAD_GPIO_17__SPDIF_OUT               0x24c 0x61c 0x000 0x4 0x0
+#define MX6QDL_PAD_GPIO_17__GPIO7_IO12              0x24c 0x61c 0x000 0x5 0x0
+#define MX6QDL_PAD_GPIO_18__ESAI_TX1                0x250 0x620 0x878 0x0 0x0
+#define MX6QDL_PAD_GPIO_18__ENET_RX_CLK             0x250 0x620 0x844 0x1 0x1
+#define MX6QDL_PAD_GPIO_18__SD3_VSELECT             0x250 0x620 0x000 0x2 0x0
+#define MX6QDL_PAD_GPIO_18__SDMA_EXT_EVENT1         0x250 0x620 0x910 0x3 0x1
+#define MX6QDL_PAD_GPIO_18__ASRC_EXT_CLK            0x250 0x620 0x7b0 0x4 0x2
+#define MX6QDL_PAD_GPIO_18__GPIO7_IO13              0x250 0x620 0x000 0x5 0x0
+#define MX6QDL_PAD_GPIO_18__SNVS_VIO_5_CTL          0x250 0x620 0x000 0x6 0x0
+#define MX6QDL_PAD_GPIO_19__KEY_COL5                0x254 0x624 0x8e8 0x0 0x1
+#define MX6QDL_PAD_GPIO_19__ENET_1588_EVENT0_OUT    0x254 0x624 0x000 0x1 0x0
+#define MX6QDL_PAD_GPIO_19__SPDIF_OUT               0x254 0x624 0x000 0x2 0x0
+#define MX6QDL_PAD_GPIO_19__CCM_CLKO1               0x254 0x624 0x000 0x3 0x0
+#define MX6QDL_PAD_GPIO_19__ECSPI1_RDY              0x254 0x624 0x000 0x4 0x0
+#define MX6QDL_PAD_GPIO_19__GPIO4_IO05              0x254 0x624 0x000 0x5 0x0
+#define MX6QDL_PAD_GPIO_19__ENET_TX_ER              0x254 0x624 0x000 0x6 0x0
+#define MX6QDL_PAD_CSI0_PIXCLK__IPU1_CSI0_PIXCLK    0x258 0x628 0x000 0x0 0x0
+#define MX6QDL_PAD_CSI0_PIXCLK__GPIO5_IO18          0x258 0x628 0x000 0x5 0x0
+#define MX6QDL_PAD_CSI0_PIXCLK__ARM_EVENTO          0x258 0x628 0x000 0x7 0x0
+#define MX6QDL_PAD_CSI0_MCLK__IPU1_CSI0_HSYNC       0x25c 0x62c 0x000 0x0 0x0
+#define MX6QDL_PAD_CSI0_MCLK__CCM_CLKO1             0x25c 0x62c 0x000 0x3 0x0
+#define MX6QDL_PAD_CSI0_MCLK__GPIO5_IO19            0x25c 0x62c 0x000 0x5 0x0
+#define MX6QDL_PAD_CSI0_MCLK__ARM_TRACE_CTL         0x25c 0x62c 0x000 0x7 0x0
+#define MX6QDL_PAD_CSI0_DATA_EN__IPU1_CSI0_DATA_EN  0x260 0x630 0x000 0x0 0x0
+#define MX6QDL_PAD_CSI0_DATA_EN__EIM_DATA00         0x260 0x630 0x000 0x1 0x0
+#define MX6QDL_PAD_CSI0_DATA_EN__GPIO5_IO20         0x260 0x630 0x000 0x5 0x0
+#define MX6QDL_PAD_CSI0_DATA_EN__ARM_TRACE_CLK      0x260 0x630 0x000 0x7 0x0
+#define MX6QDL_PAD_CSI0_VSYNC__IPU1_CSI0_VSYNC      0x264 0x634 0x000 0x0 0x0
+#define MX6QDL_PAD_CSI0_VSYNC__EIM_DATA01           0x264 0x634 0x000 0x1 0x0
+#define MX6QDL_PAD_CSI0_VSYNC__GPIO5_IO21           0x264 0x634 0x000 0x5 0x0
+#define MX6QDL_PAD_CSI0_VSYNC__ARM_TRACE00          0x264 0x634 0x000 0x7 0x0
+#define MX6QDL_PAD_CSI0_DAT4__IPU1_CSI0_DATA04      0x268 0x638 0x000 0x0 0x0
+#define MX6QDL_PAD_CSI0_DAT4__EIM_DATA02            0x268 0x638 0x000 0x1 0x0
+#define MX6QDL_PAD_CSI0_DAT4__ECSPI1_SCLK           0x268 0x638 0x7f4 0x2 0x3
+#define MX6QDL_PAD_CSI0_DAT4__KEY_COL5              0x268 0x638 0x8e8 0x3 0x2
+#define MX6QDL_PAD_CSI0_DAT4__AUD3_TXC              0x268 0x638 0x000 0x4 0x0
+#define MX6QDL_PAD_CSI0_DAT4__GPIO5_IO22            0x268 0x638 0x000 0x5 0x0
+#define MX6QDL_PAD_CSI0_DAT4__ARM_TRACE01           0x268 0x638 0x000 0x7 0x0
+#define MX6QDL_PAD_CSI0_DAT5__IPU1_CSI0_DATA05      0x26c 0x63c 0x000 0x0 0x0
+#define MX6QDL_PAD_CSI0_DAT5__EIM_DATA03            0x26c 0x63c 0x000 0x1 0x0
+#define MX6QDL_PAD_CSI0_DAT5__ECSPI1_MOSI           0x26c 0x63c 0x7fc 0x2 0x3
+#define MX6QDL_PAD_CSI0_DAT5__KEY_ROW5              0x26c 0x63c 0x8f4 0x3 0x1
+#define MX6QDL_PAD_CSI0_DAT5__AUD3_TXD              0x26c 0x63c 0x000 0x4 0x0
+#define MX6QDL_PAD_CSI0_DAT5__GPIO5_IO23            0x26c 0x63c 0x000 0x5 0x0
+#define MX6QDL_PAD_CSI0_DAT5__ARM_TRACE02           0x26c 0x63c 0x000 0x7 0x0
+#define MX6QDL_PAD_CSI0_DAT6__IPU1_CSI0_DATA06      0x270 0x640 0x000 0x0 0x0
+#define MX6QDL_PAD_CSI0_DAT6__EIM_DATA04            0x270 0x640 0x000 0x1 0x0
+#define MX6QDL_PAD_CSI0_DAT6__ECSPI1_MISO           0x270 0x640 0x7f8 0x2 0x3
+#define MX6QDL_PAD_CSI0_DAT6__KEY_COL6              0x270 0x640 0x8ec 0x3 0x1
+#define MX6QDL_PAD_CSI0_DAT6__AUD3_TXFS             0x270 0x640 0x000 0x4 0x0
+#define MX6QDL_PAD_CSI0_DAT6__GPIO5_IO24            0x270 0x640 0x000 0x5 0x0
+#define MX6QDL_PAD_CSI0_DAT6__ARM_TRACE03           0x270 0x640 0x000 0x7 0x0
+#define MX6QDL_PAD_CSI0_DAT7__IPU1_CSI0_DATA07      0x274 0x644 0x000 0x0 0x0
+#define MX6QDL_PAD_CSI0_DAT7__EIM_DATA05            0x274 0x644 0x000 0x1 0x0
+#define MX6QDL_PAD_CSI0_DAT7__ECSPI1_SS0            0x274 0x644 0x800 0x2 0x3
+#define MX6QDL_PAD_CSI0_DAT7__KEY_ROW6              0x274 0x644 0x8f8 0x3 0x2
+#define MX6QDL_PAD_CSI0_DAT7__AUD3_RXD              0x274 0x644 0x000 0x4 0x0
+#define MX6QDL_PAD_CSI0_DAT7__GPIO5_IO25            0x274 0x644 0x000 0x5 0x0
+#define MX6QDL_PAD_CSI0_DAT7__ARM_TRACE04           0x274 0x644 0x000 0x7 0x0
+#define MX6QDL_PAD_CSI0_DAT8__IPU1_CSI0_DATA08      0x278 0x648 0x000 0x0 0x0
+#define MX6QDL_PAD_CSI0_DAT8__EIM_DATA06            0x278 0x648 0x000 0x1 0x0
+#define MX6QDL_PAD_CSI0_DAT8__ECSPI2_SCLK           0x278 0x648 0x810 0x2 0x2
+#define MX6QDL_PAD_CSI0_DAT8__KEY_COL7              0x278 0x648 0x8f0 0x3 0x2
+#define MX6QDL_PAD_CSI0_DAT8__I2C1_SDA              0x278 0x648 0x89c 0x4 0x1
+#define MX6QDL_PAD_CSI0_DAT8__GPIO5_IO26            0x278 0x648 0x000 0x5 0x0
+#define MX6QDL_PAD_CSI0_DAT8__ARM_TRACE05           0x278 0x648 0x000 0x7 0x0
+#define MX6QDL_PAD_CSI0_DAT9__IPU1_CSI0_DATA09      0x27c 0x64c 0x000 0x0 0x0
+#define MX6QDL_PAD_CSI0_DAT9__EIM_DATA07            0x27c 0x64c 0x000 0x1 0x0
+#define MX6QDL_PAD_CSI0_DAT9__ECSPI2_MOSI           0x27c 0x64c 0x818 0x2 0x2
+#define MX6QDL_PAD_CSI0_DAT9__KEY_ROW7              0x27c 0x64c 0x8fc 0x3 0x2
+#define MX6QDL_PAD_CSI0_DAT9__I2C1_SCL              0x27c 0x64c 0x898 0x4 0x1
+#define MX6QDL_PAD_CSI0_DAT9__GPIO5_IO27            0x27c 0x64c 0x000 0x5 0x0
+#define MX6QDL_PAD_CSI0_DAT9__ARM_TRACE06           0x27c 0x64c 0x000 0x7 0x0
+#define MX6QDL_PAD_CSI0_DAT10__IPU1_CSI0_DATA10     0x280 0x650 0x000 0x0 0x0
+#define MX6QDL_PAD_CSI0_DAT10__AUD3_RXC             0x280 0x650 0x000 0x1 0x0
+#define MX6QDL_PAD_CSI0_DAT10__ECSPI2_MISO          0x280 0x650 0x814 0x2 0x2
+#define MX6QDL_PAD_CSI0_DAT10__UART1_TX_DATA        0x280 0x650 0x000 0x3 0x0
+#define MX6QDL_PAD_CSI0_DAT10__UART1_RX_DATA        0x280 0x650 0x920 0x3 0x0
+#define MX6QDL_PAD_CSI0_DAT10__GPIO5_IO28           0x280 0x650 0x000 0x5 0x0
+#define MX6QDL_PAD_CSI0_DAT10__ARM_TRACE07          0x280 0x650 0x000 0x7 0x0
+#define MX6QDL_PAD_CSI0_DAT11__IPU1_CSI0_DATA11     0x284 0x654 0x000 0x0 0x0
+#define MX6QDL_PAD_CSI0_DAT11__AUD3_RXFS            0x284 0x654 0x000 0x1 0x0
+#define MX6QDL_PAD_CSI0_DAT11__ECSPI2_SS0           0x284 0x654 0x81c 0x2 0x2
+#define MX6QDL_PAD_CSI0_DAT11__UART1_RX_DATA        0x284 0x654 0x920 0x3 0x1
+#define MX6QDL_PAD_CSI0_DAT11__UART1_TX_DATA        0x284 0x654 0x000 0x3 0x0
+#define MX6QDL_PAD_CSI0_DAT11__GPIO5_IO29           0x284 0x654 0x000 0x5 0x0
+#define MX6QDL_PAD_CSI0_DAT11__ARM_TRACE08          0x284 0x654 0x000 0x7 0x0
+#define MX6QDL_PAD_CSI0_DAT12__IPU1_CSI0_DATA12     0x288 0x658 0x000 0x0 0x0
+#define MX6QDL_PAD_CSI0_DAT12__EIM_DATA08           0x288 0x658 0x000 0x1 0x0
+#define MX6QDL_PAD_CSI0_DAT12__UART4_TX_DATA        0x288 0x658 0x000 0x3 0x0
+#define MX6QDL_PAD_CSI0_DAT12__UART4_RX_DATA        0x288 0x658 0x938 0x3 0x2
+#define MX6QDL_PAD_CSI0_DAT12__GPIO5_IO30           0x288 0x658 0x000 0x5 0x0
+#define MX6QDL_PAD_CSI0_DAT12__ARM_TRACE09          0x288 0x658 0x000 0x7 0x0
+#define MX6QDL_PAD_CSI0_DAT13__IPU1_CSI0_DATA13     0x28c 0x65c 0x000 0x0 0x0
+#define MX6QDL_PAD_CSI0_DAT13__EIM_DATA09           0x28c 0x65c 0x000 0x1 0x0
+#define MX6QDL_PAD_CSI0_DAT13__UART4_RX_DATA        0x28c 0x65c 0x938 0x3 0x3
+#define MX6QDL_PAD_CSI0_DAT13__UART4_TX_DATA        0x28c 0x65c 0x000 0x3 0x0
+#define MX6QDL_PAD_CSI0_DAT13__GPIO5_IO31           0x28c 0x65c 0x000 0x5 0x0
+#define MX6QDL_PAD_CSI0_DAT13__ARM_TRACE10          0x28c 0x65c 0x000 0x7 0x0
+#define MX6QDL_PAD_CSI0_DAT14__IPU1_CSI0_DATA14     0x290 0x660 0x000 0x0 0x0
+#define MX6QDL_PAD_CSI0_DAT14__EIM_DATA10           0x290 0x660 0x000 0x1 0x0
+#define MX6QDL_PAD_CSI0_DAT14__UART5_TX_DATA        0x290 0x660 0x000 0x3 0x0
+#define MX6QDL_PAD_CSI0_DAT14__UART5_RX_DATA        0x290 0x660 0x940 0x3 0x2
+#define MX6QDL_PAD_CSI0_DAT14__GPIO6_IO00           0x290 0x660 0x000 0x5 0x0
+#define MX6QDL_PAD_CSI0_DAT14__ARM_TRACE11          0x290 0x660 0x000 0x7 0x0
+#define MX6QDL_PAD_CSI0_DAT15__IPU1_CSI0_DATA15     0x294 0x664 0x000 0x0 0x0
+#define MX6QDL_PAD_CSI0_DAT15__EIM_DATA11           0x294 0x664 0x000 0x1 0x0
+#define MX6QDL_PAD_CSI0_DAT15__UART5_RX_DATA        0x294 0x664 0x940 0x3 0x3
+#define MX6QDL_PAD_CSI0_DAT15__UART5_TX_DATA        0x294 0x664 0x000 0x3 0x0
+#define MX6QDL_PAD_CSI0_DAT15__GPIO6_IO01           0x294 0x664 0x000 0x5 0x0
+#define MX6QDL_PAD_CSI0_DAT15__ARM_TRACE12          0x294 0x664 0x000 0x7 0x0
+#define MX6QDL_PAD_CSI0_DAT16__IPU1_CSI0_DATA16     0x298 0x668 0x000 0x0 0x0
+#define MX6QDL_PAD_CSI0_DAT16__EIM_DATA12           0x298 0x668 0x000 0x1 0x0
+#define MX6QDL_PAD_CSI0_DAT16__UART4_RTS_B          0x298 0x668 0x934 0x3 0x0
+#define MX6QDL_PAD_CSI0_DAT16__UART4_CTS_B          0x298 0x668 0x000 0x3 0x0
+#define MX6QDL_PAD_CSI0_DAT16__GPIO6_IO02           0x298 0x668 0x000 0x5 0x0
+#define MX6QDL_PAD_CSI0_DAT16__ARM_TRACE13          0x298 0x668 0x000 0x7 0x0
+#define MX6QDL_PAD_CSI0_DAT17__IPU1_CSI0_DATA17     0x29c 0x66c 0x000 0x0 0x0
+#define MX6QDL_PAD_CSI0_DAT17__EIM_DATA13           0x29c 0x66c 0x000 0x1 0x0
+#define MX6QDL_PAD_CSI0_DAT17__UART4_CTS_B          0x29c 0x66c 0x000 0x3 0x0
+#define MX6QDL_PAD_CSI0_DAT17__UART4_RTS_B          0x29c 0x66c 0x934 0x3 0x1
+#define MX6QDL_PAD_CSI0_DAT17__GPIO6_IO03           0x29c 0x66c 0x000 0x5 0x0
+#define MX6QDL_PAD_CSI0_DAT17__ARM_TRACE14          0x29c 0x66c 0x000 0x7 0x0
+#define MX6QDL_PAD_CSI0_DAT18__IPU1_CSI0_DATA18     0x2a0 0x670 0x000 0x0 0x0
+#define MX6QDL_PAD_CSI0_DAT18__EIM_DATA14           0x2a0 0x670 0x000 0x1 0x0
+#define MX6QDL_PAD_CSI0_DAT18__UART5_RTS_B          0x2a0 0x670 0x93c 0x3 0x2
+#define MX6QDL_PAD_CSI0_DAT18__UART5_CTS_B          0x2a0 0x670 0x000 0x3 0x0
+#define MX6QDL_PAD_CSI0_DAT18__GPIO6_IO04           0x2a0 0x670 0x000 0x5 0x0
+#define MX6QDL_PAD_CSI0_DAT18__ARM_TRACE15          0x2a0 0x670 0x000 0x7 0x0
+#define MX6QDL_PAD_CSI0_DAT19__IPU1_CSI0_DATA19     0x2a4 0x674 0x000 0x0 0x0
+#define MX6QDL_PAD_CSI0_DAT19__EIM_DATA15           0x2a4 0x674 0x000 0x1 0x0
+#define MX6QDL_PAD_CSI0_DAT19__UART5_CTS_B          0x2a4 0x674 0x000 0x3 0x0
+#define MX6QDL_PAD_CSI0_DAT19__UART5_RTS_B          0x2a4 0x674 0x93c 0x3 0x3
+#define MX6QDL_PAD_CSI0_DAT19__GPIO6_IO05           0x2a4 0x674 0x000 0x5 0x0
+#define MX6QDL_PAD_SD3_DAT7__SD3_DATA7              0x2a8 0x690 0x000 0x0 0x0
+#define MX6QDL_PAD_SD3_DAT7__UART1_TX_DATA          0x2a8 0x690 0x000 0x1 0x0
+#define MX6QDL_PAD_SD3_DAT7__UART1_RX_DATA          0x2a8 0x690 0x920 0x1 0x2
+#define MX6QDL_PAD_SD3_DAT7__GPIO6_IO17             0x2a8 0x690 0x000 0x5 0x0
+#define MX6QDL_PAD_SD3_DAT6__SD3_DATA6              0x2ac 0x694 0x000 0x0 0x0
+#define MX6QDL_PAD_SD3_DAT6__UART1_RX_DATA          0x2ac 0x694 0x920 0x1 0x3
+#define MX6QDL_PAD_SD3_DAT6__UART1_TX_DATA          0x2ac 0x694 0x000 0x1 0x0
+#define MX6QDL_PAD_SD3_DAT6__GPIO6_IO18             0x2ac 0x694 0x000 0x5 0x0
+#define MX6QDL_PAD_SD3_DAT5__SD3_DATA5              0x2b0 0x698 0x000 0x0 0x0
+#define MX6QDL_PAD_SD3_DAT5__UART2_TX_DATA          0x2b0 0x698 0x000 0x1 0x0
+#define MX6QDL_PAD_SD3_DAT5__UART2_RX_DATA          0x2b0 0x698 0x928 0x1 0x4
+#define MX6QDL_PAD_SD3_DAT5__GPIO7_IO00             0x2b0 0x698 0x000 0x5 0x0
+#define MX6QDL_PAD_SD3_DAT4__SD3_DATA4              0x2b4 0x69c 0x000 0x0 0x0
+#define MX6QDL_PAD_SD3_DAT4__UART2_RX_DATA          0x2b4 0x69c 0x928 0x1 0x5
+#define MX6QDL_PAD_SD3_DAT4__UART2_TX_DATA          0x2b4 0x69c 0x000 0x1 0x0
+#define MX6QDL_PAD_SD3_DAT4__GPIO7_IO01             0x2b4 0x69c 0x000 0x5 0x0
+#define MX6QDL_PAD_SD3_CMD__SD3_CMD                 0x2b8 0x6a0 0x000 0x0 0x0
+#define MX6QDL_PAD_SD3_CMD__UART2_CTS_B             0x2b8 0x6a0 0x000 0x1 0x0
+#define MX6QDL_PAD_SD3_CMD__UART2_RTS_B             0x2b8 0x6a0 0x924 0x1 0x2
+#define MX6QDL_PAD_SD3_CMD__FLEXCAN1_TX             0x2b8 0x6a0 0x000 0x2 0x0
+#define MX6QDL_PAD_SD3_CMD__GPIO7_IO02              0x2b8 0x6a0 0x000 0x5 0x0
+#define MX6QDL_PAD_SD3_CLK__SD3_CLK                 0x2bc 0x6a4 0x000 0x0 0x0
+#define MX6QDL_PAD_SD3_CLK__UART2_RTS_B             0x2bc 0x6a4 0x924 0x1 0x3
+#define MX6QDL_PAD_SD3_CLK__UART2_CTS_B             0x2bc 0x6a4 0x000 0x1 0x0
+#define MX6QDL_PAD_SD3_CLK__FLEXCAN1_RX             0x2bc 0x6a4 0x7e4 0x2 0x2
+#define MX6QDL_PAD_SD3_CLK__GPIO7_IO03              0x2bc 0x6a4 0x000 0x5 0x0
+#define MX6QDL_PAD_SD3_DAT0__SD3_DATA0              0x2c0 0x6a8 0x000 0x0 0x0
+#define MX6QDL_PAD_SD3_DAT0__UART1_CTS_B            0x2c0 0x6a8 0x000 0x1 0x0
+#define MX6QDL_PAD_SD3_DAT0__UART1_RTS_B            0x2c0 0x6a8 0x91c 0x1 0x2
+#define MX6QDL_PAD_SD3_DAT0__FLEXCAN2_TX            0x2c0 0x6a8 0x000 0x2 0x0
+#define MX6QDL_PAD_SD3_DAT0__GPIO7_IO04             0x2c0 0x6a8 0x000 0x5 0x0
+#define MX6QDL_PAD_SD3_DAT1__SD3_DATA1              0x2c4 0x6ac 0x000 0x0 0x0
+#define MX6QDL_PAD_SD3_DAT1__UART1_RTS_B            0x2c4 0x6ac 0x91c 0x1 0x3
+#define MX6QDL_PAD_SD3_DAT1__UART1_CTS_B            0x2c4 0x6ac 0x000 0x1 0x0
+#define MX6QDL_PAD_SD3_DAT1__FLEXCAN2_RX            0x2c4 0x6ac 0x7e8 0x2 0x1
+#define MX6QDL_PAD_SD3_DAT1__GPIO7_IO05             0x2c4 0x6ac 0x000 0x5 0x0
+#define MX6QDL_PAD_SD3_DAT2__SD3_DATA2              0x2c8 0x6b0 0x000 0x0 0x0
+#define MX6QDL_PAD_SD3_DAT2__GPIO7_IO06             0x2c8 0x6b0 0x000 0x5 0x0
+#define MX6QDL_PAD_SD3_DAT3__SD3_DATA3              0x2cc 0x6b4 0x000 0x0 0x0
+#define MX6QDL_PAD_SD3_DAT3__UART3_CTS_B            0x2cc 0x6b4 0x000 0x1 0x0
+#define MX6QDL_PAD_SD3_DAT3__UART3_RTS_B            0x2cc 0x6b4 0x92c 0x1 0x4
+#define MX6QDL_PAD_SD3_DAT3__GPIO7_IO07             0x2cc 0x6b4 0x000 0x5 0x0
+#define MX6QDL_PAD_SD3_RST__SD3_RESET               0x2d0 0x6b8 0x000 0x0 0x0
+#define MX6QDL_PAD_SD3_RST__UART3_RTS_B             0x2d0 0x6b8 0x92c 0x1 0x5
+#define MX6QDL_PAD_SD3_RST__UART3_CTS_B             0x2d0 0x6b8 0x000 0x1 0x0
+#define MX6QDL_PAD_SD3_RST__GPIO7_IO08              0x2d0 0x6b8 0x000 0x5 0x0
+#define MX6QDL_PAD_NANDF_CLE__NAND_CLE              0x2d4 0x6bc 0x000 0x0 0x0
+#define MX6QDL_PAD_NANDF_CLE__IPU2_SISG4            0x2d4 0x6bc 0x000 0x1 0x0
+#define MX6QDL_PAD_NANDF_CLE__GPIO6_IO07            0x2d4 0x6bc 0x000 0x5 0x0
+#define MX6QDL_PAD_NANDF_ALE__NAND_ALE              0x2d8 0x6c0 0x000 0x0 0x0
+#define MX6QDL_PAD_NANDF_ALE__SD4_RESET             0x2d8 0x6c0 0x000 0x1 0x0
+#define MX6QDL_PAD_NANDF_ALE__GPIO6_IO08            0x2d8 0x6c0 0x000 0x5 0x0
+#define MX6QDL_PAD_NANDF_WP_B__NAND_WP_B            0x2dc 0x6c4 0x000 0x0 0x0
+#define MX6QDL_PAD_NANDF_WP_B__IPU2_SISG5           0x2dc 0x6c4 0x000 0x1 0x0
+#define MX6QDL_PAD_NANDF_WP_B__GPIO6_IO09           0x2dc 0x6c4 0x000 0x5 0x0
+#define MX6QDL_PAD_NANDF_RB0__NAND_READY_B          0x2e0 0x6c8 0x000 0x0 0x0
+#define MX6QDL_PAD_NANDF_RB0__IPU2_DI0_PIN01        0x2e0 0x6c8 0x000 0x1 0x0
+#define MX6QDL_PAD_NANDF_RB0__GPIO6_IO10            0x2e0 0x6c8 0x000 0x5 0x0
+#define MX6QDL_PAD_NANDF_CS0__NAND_CE0_B            0x2e4 0x6cc 0x000 0x0 0x0
+#define MX6QDL_PAD_NANDF_CS0__GPIO6_IO11            0x2e4 0x6cc 0x000 0x5 0x0
+#define MX6QDL_PAD_NANDF_CS1__NAND_CE1_B            0x2e8 0x6d0 0x000 0x0 0x0
+#define MX6QDL_PAD_NANDF_CS1__SD4_VSELECT           0x2e8 0x6d0 0x000 0x1 0x0
+#define MX6QDL_PAD_NANDF_CS1__SD3_VSELECT           0x2e8 0x6d0 0x000 0x2 0x0
+#define MX6QDL_PAD_NANDF_CS1__GPIO6_IO14            0x2e8 0x6d0 0x000 0x5 0x0
+#define MX6QDL_PAD_NANDF_CS2__NAND_CE2_B            0x2ec 0x6d4 0x000 0x0 0x0
+#define MX6QDL_PAD_NANDF_CS2__IPU1_SISG0            0x2ec 0x6d4 0x000 0x1 0x0
+#define MX6QDL_PAD_NANDF_CS2__ESAI_TX0              0x2ec 0x6d4 0x874 0x2 0x1
+#define MX6QDL_PAD_NANDF_CS2__EIM_CRE               0x2ec 0x6d4 0x000 0x3 0x0
+#define MX6QDL_PAD_NANDF_CS2__CCM_CLKO2             0x2ec 0x6d4 0x000 0x4 0x0
+#define MX6QDL_PAD_NANDF_CS2__GPIO6_IO15            0x2ec 0x6d4 0x000 0x5 0x0
+#define MX6QDL_PAD_NANDF_CS2__IPU2_SISG0            0x2ec 0x6d4 0x000 0x6 0x0
+#define MX6QDL_PAD_NANDF_CS3__NAND_CE3_B            0x2f0 0x6d8 0x000 0x0 0x0
+#define MX6QDL_PAD_NANDF_CS3__IPU1_SISG1            0x2f0 0x6d8 0x000 0x1 0x0
+#define MX6QDL_PAD_NANDF_CS3__ESAI_TX1              0x2f0 0x6d8 0x878 0x2 0x1
+#define MX6QDL_PAD_NANDF_CS3__EIM_ADDR26            0x2f0 0x6d8 0x000 0x3 0x0
+#define MX6QDL_PAD_NANDF_CS3__GPIO6_IO16            0x2f0 0x6d8 0x000 0x5 0x0
+#define MX6QDL_PAD_NANDF_CS3__IPU2_SISG1            0x2f0 0x6d8 0x000 0x6 0x0
+#define MX6QDL_PAD_SD4_CMD__SD4_CMD                 0x2f4 0x6dc 0x000 0x0 0x0
+#define MX6QDL_PAD_SD4_CMD__NAND_RE_B               0x2f4 0x6dc 0x000 0x1 0x0
+#define MX6QDL_PAD_SD4_CMD__UART3_TX_DATA           0x2f4 0x6dc 0x000 0x2 0x0
+#define MX6QDL_PAD_SD4_CMD__UART3_RX_DATA           0x2f4 0x6dc 0x930 0x2 0x2
+#define MX6QDL_PAD_SD4_CMD__GPIO7_IO09              0x2f4 0x6dc 0x000 0x5 0x0
+#define MX6QDL_PAD_SD4_CLK__SD4_CLK                 0x2f8 0x6e0 0x000 0x0 0x0
+#define MX6QDL_PAD_SD4_CLK__NAND_WE_B               0x2f8 0x6e0 0x000 0x1 0x0
+#define MX6QDL_PAD_SD4_CLK__UART3_RX_DATA           0x2f8 0x6e0 0x930 0x2 0x3
+#define MX6QDL_PAD_SD4_CLK__UART3_TX_DATA           0x2f8 0x6e0 0x000 0x2 0x0
+#define MX6QDL_PAD_SD4_CLK__GPIO7_IO10              0x2f8 0x6e0 0x000 0x5 0x0
+#define MX6QDL_PAD_NANDF_D0__NAND_DATA00            0x2fc 0x6e4 0x000 0x0 0x0
+#define MX6QDL_PAD_NANDF_D0__SD1_DATA4              0x2fc 0x6e4 0x000 0x1 0x0
+#define MX6QDL_PAD_NANDF_D0__GPIO2_IO00             0x2fc 0x6e4 0x000 0x5 0x0
+#define MX6QDL_PAD_NANDF_D1__NAND_DATA01            0x300 0x6e8 0x000 0x0 0x0
+#define MX6QDL_PAD_NANDF_D1__SD1_DATA5              0x300 0x6e8 0x000 0x1 0x0
+#define MX6QDL_PAD_NANDF_D1__GPIO2_IO01             0x300 0x6e8 0x000 0x5 0x0
+#define MX6QDL_PAD_NANDF_D2__NAND_DATA02            0x304 0x6ec 0x000 0x0 0x0
+#define MX6QDL_PAD_NANDF_D2__SD1_DATA6              0x304 0x6ec 0x000 0x1 0x0
+#define MX6QDL_PAD_NANDF_D2__GPIO2_IO02             0x304 0x6ec 0x000 0x5 0x0
+#define MX6QDL_PAD_NANDF_D3__NAND_DATA03            0x308 0x6f0 0x000 0x0 0x0
+#define MX6QDL_PAD_NANDF_D3__SD1_DATA7              0x308 0x6f0 0x000 0x1 0x0
+#define MX6QDL_PAD_NANDF_D3__GPIO2_IO03             0x308 0x6f0 0x000 0x5 0x0
+#define MX6QDL_PAD_NANDF_D4__NAND_DATA04            0x30c 0x6f4 0x000 0x0 0x0
+#define MX6QDL_PAD_NANDF_D4__SD2_DATA4              0x30c 0x6f4 0x000 0x1 0x0
+#define MX6QDL_PAD_NANDF_D4__GPIO2_IO04             0x30c 0x6f4 0x000 0x5 0x0
+#define MX6QDL_PAD_NANDF_D5__NAND_DATA05            0x310 0x6f8 0x000 0x0 0x0
+#define MX6QDL_PAD_NANDF_D5__SD2_DATA5              0x310 0x6f8 0x000 0x1 0x0
+#define MX6QDL_PAD_NANDF_D5__GPIO2_IO05             0x310 0x6f8 0x000 0x5 0x0
+#define MX6QDL_PAD_NANDF_D6__NAND_DATA06            0x314 0x6fc 0x000 0x0 0x0
+#define MX6QDL_PAD_NANDF_D6__SD2_DATA6              0x314 0x6fc 0x000 0x1 0x0
+#define MX6QDL_PAD_NANDF_D6__GPIO2_IO06             0x314 0x6fc 0x000 0x5 0x0
+#define MX6QDL_PAD_NANDF_D7__NAND_DATA07            0x318 0x700 0x000 0x0 0x0
+#define MX6QDL_PAD_NANDF_D7__SD2_DATA7              0x318 0x700 0x000 0x1 0x0
+#define MX6QDL_PAD_NANDF_D7__GPIO2_IO07             0x318 0x700 0x000 0x5 0x0
+#define MX6QDL_PAD_SD4_DAT0__SD4_DATA0              0x31c 0x704 0x000 0x1 0x0
+#define MX6QDL_PAD_SD4_DAT0__NAND_DQS               0x31c 0x704 0x000 0x2 0x0
+#define MX6QDL_PAD_SD4_DAT0__GPIO2_IO08             0x31c 0x704 0x000 0x5 0x0
+#define MX6QDL_PAD_SD4_DAT1__SD4_DATA1              0x320 0x708 0x000 0x1 0x0
+#define MX6QDL_PAD_SD4_DAT1__PWM3_OUT               0x320 0x708 0x000 0x2 0x0
+#define MX6QDL_PAD_SD4_DAT1__GPIO2_IO09             0x320 0x708 0x000 0x5 0x0
+#define MX6QDL_PAD_SD4_DAT2__SD4_DATA2              0x324 0x70c 0x000 0x1 0x0
+#define MX6QDL_PAD_SD4_DAT2__PWM4_OUT               0x324 0x70c 0x000 0x2 0x0
+#define MX6QDL_PAD_SD4_DAT2__GPIO2_IO10             0x324 0x70c 0x000 0x5 0x0
+#define MX6QDL_PAD_SD4_DAT3__SD4_DATA3              0x328 0x710 0x000 0x1 0x0
+#define MX6QDL_PAD_SD4_DAT3__GPIO2_IO11             0x328 0x710 0x000 0x5 0x0
+#define MX6QDL_PAD_SD4_DAT4__SD4_DATA4              0x32c 0x714 0x000 0x1 0x0
+#define MX6QDL_PAD_SD4_DAT4__UART2_RX_DATA          0x32c 0x714 0x928 0x2 0x6
+#define MX6QDL_PAD_SD4_DAT4__UART2_TX_DATA          0x32c 0x714 0x000 0x2 0x0
+#define MX6QDL_PAD_SD4_DAT4__GPIO2_IO12             0x32c 0x714 0x000 0x5 0x0
+#define MX6QDL_PAD_SD4_DAT5__SD4_DATA5              0x330 0x718 0x000 0x1 0x0
+#define MX6QDL_PAD_SD4_DAT5__UART2_RTS_B            0x330 0x718 0x924 0x2 0x4
+#define MX6QDL_PAD_SD4_DAT5__UART2_CTS_B            0x330 0x718 0x000 0x2 0x0
+#define MX6QDL_PAD_SD4_DAT5__GPIO2_IO13             0x330 0x718 0x000 0x5 0x0
+#define MX6QDL_PAD_SD4_DAT6__SD4_DATA6              0x334 0x71c 0x000 0x1 0x0
+#define MX6QDL_PAD_SD4_DAT6__UART2_CTS_B            0x334 0x71c 0x000 0x2 0x0
+#define MX6QDL_PAD_SD4_DAT6__UART2_RTS_B            0x334 0x71c 0x924 0x2 0x5
+#define MX6QDL_PAD_SD4_DAT6__GPIO2_IO14             0x334 0x71c 0x000 0x5 0x0
+#define MX6QDL_PAD_SD4_DAT7__SD4_DATA7              0x338 0x720 0x000 0x1 0x0
+#define MX6QDL_PAD_SD4_DAT7__UART2_TX_DATA          0x338 0x720 0x000 0x2 0x0
+#define MX6QDL_PAD_SD4_DAT7__UART2_RX_DATA          0x338 0x720 0x928 0x2 0x7
+#define MX6QDL_PAD_SD4_DAT7__GPIO2_IO15             0x338 0x720 0x000 0x5 0x0
+#define MX6QDL_PAD_SD1_DAT1__SD1_DATA1              0x33c 0x724 0x000 0x0 0x0
+#define MX6QDL_PAD_SD1_DAT1__ECSPI5_SS0             0x33c 0x724 0x834 0x1 0x1
+#define MX6QDL_PAD_SD1_DAT1__PWM3_OUT               0x33c 0x724 0x000 0x2 0x0
+#define MX6QDL_PAD_SD1_DAT1__GPT_CAPTURE2           0x33c 0x724 0x000 0x3 0x0
+#define MX6QDL_PAD_SD1_DAT1__GPIO1_IO17             0x33c 0x724 0x000 0x5 0x0
+#define MX6QDL_PAD_SD1_DAT0__SD1_DATA0              0x340 0x728 0x000 0x0 0x0
+#define MX6QDL_PAD_SD1_DAT0__ECSPI5_MISO            0x340 0x728 0x82c 0x1 0x1
+#define MX6QDL_PAD_SD1_DAT0__GPT_CAPTURE1           0x340 0x728 0x000 0x3 0x0
+#define MX6QDL_PAD_SD1_DAT0__GPIO1_IO16             0x340 0x728 0x000 0x5 0x0
+#define MX6QDL_PAD_SD1_DAT3__SD1_DATA3              0x344 0x72c 0x000 0x0 0x0
+#define MX6QDL_PAD_SD1_DAT3__ECSPI5_SS2             0x344 0x72c 0x000 0x1 0x0
+#define MX6QDL_PAD_SD1_DAT3__GPT_COMPARE3           0x344 0x72c 0x000 0x2 0x0
+#define MX6QDL_PAD_SD1_DAT3__PWM1_OUT               0x344 0x72c 0x000 0x3 0x0
+#define MX6QDL_PAD_SD1_DAT3__WDOG2_B                0x344 0x72c 0x000 0x4 0x0
+#define MX6QDL_PAD_SD1_DAT3__GPIO1_IO21             0x344 0x72c 0x000 0x5 0x0
+#define MX6QDL_PAD_SD1_DAT3__WDOG2_RESET_B_DEB      0x344 0x72c 0x000 0x6 0x0
+#define MX6QDL_PAD_SD1_CMD__SD1_CMD                 0x348 0x730 0x000 0x0 0x0
+#define MX6QDL_PAD_SD1_CMD__ECSPI5_MOSI             0x348 0x730 0x830 0x1 0x0
+#define MX6QDL_PAD_SD1_CMD__PWM4_OUT                0x348 0x730 0x000 0x2 0x0
+#define MX6QDL_PAD_SD1_CMD__GPT_COMPARE1            0x348 0x730 0x000 0x3 0x0
+#define MX6QDL_PAD_SD1_CMD__GPIO1_IO18              0x348 0x730 0x000 0x5 0x0
+#define MX6QDL_PAD_SD1_DAT2__SD1_DATA2              0x34c 0x734 0x000 0x0 0x0
+#define MX6QDL_PAD_SD1_DAT2__ECSPI5_SS1             0x34c 0x734 0x838 0x1 0x1
+#define MX6QDL_PAD_SD1_DAT2__GPT_COMPARE2           0x34c 0x734 0x000 0x2 0x0
+#define MX6QDL_PAD_SD1_DAT2__PWM2_OUT               0x34c 0x734 0x000 0x3 0x0
+#define MX6QDL_PAD_SD1_DAT2__WDOG1_B                0x34c 0x734 0x000 0x4 0x0
+#define MX6QDL_PAD_SD1_DAT2__GPIO1_IO19             0x34c 0x734 0x000 0x5 0x0
+#define MX6QDL_PAD_SD1_DAT2__WDOG1_RESET_B_DEB      0x34c 0x734 0x000 0x6 0x0
+#define MX6QDL_PAD_SD1_CLK__SD1_CLK                 0x350 0x738 0x000 0x0 0x0
+#define MX6QDL_PAD_SD1_CLK__ECSPI5_SCLK             0x350 0x738 0x828 0x1 0x0
+#define MX6QDL_PAD_SD1_CLK__GPT_CLKIN               0x350 0x738 0x000 0x3 0x0
+#define MX6QDL_PAD_SD1_CLK__GPIO1_IO20              0x350 0x738 0x000 0x5 0x0
+#define MX6QDL_PAD_SD2_CLK__SD2_CLK                 0x354 0x73c 0x000 0x0 0x0
+#define MX6QDL_PAD_SD2_CLK__ECSPI5_SCLK             0x354 0x73c 0x828 0x1 0x1
+#define MX6QDL_PAD_SD2_CLK__KEY_COL5                0x354 0x73c 0x8e8 0x2 0x3
+#define MX6QDL_PAD_SD2_CLK__AUD4_RXFS               0x354 0x73c 0x7c0 0x3 0x1
+#define MX6QDL_PAD_SD2_CLK__GPIO1_IO10              0x354 0x73c 0x000 0x5 0x0
+#define MX6QDL_PAD_SD2_CMD__SD2_CMD                 0x358 0x740 0x000 0x0 0x0
+#define MX6QDL_PAD_SD2_CMD__ECSPI5_MOSI             0x358 0x740 0x830 0x1 0x1
+#define MX6QDL_PAD_SD2_CMD__KEY_ROW5                0x358 0x740 0x8f4 0x2 0x2
+#define MX6QDL_PAD_SD2_CMD__AUD4_RXC                0x358 0x740 0x7bc 0x3 0x1
+#define MX6QDL_PAD_SD2_CMD__GPIO1_IO11              0x358 0x740 0x000 0x5 0x0
+#define MX6QDL_PAD_SD2_DAT3__SD2_DATA3              0x35c 0x744 0x000 0x0 0x0
+#define MX6QDL_PAD_SD2_DAT3__ECSPI5_SS3             0x35c 0x744 0x000 0x1 0x0
+#define MX6QDL_PAD_SD2_DAT3__KEY_COL6               0x35c 0x744 0x8ec 0x2 0x2
+#define MX6QDL_PAD_SD2_DAT3__AUD4_TXC               0x35c 0x744 0x7c4 0x3 0x1
+#define MX6QDL_PAD_SD2_DAT3__GPIO1_IO12             0x35c 0x744 0x000 0x5 0x0
 
 #endif /* __DTS_IMX6Q_PINFUNC_H */
diff --git a/arch/arm/boot/dts/imx6q-sabreauto.dts b/arch/arm/boot/dts/imx6q-sabreauto.dts
index 09a75807bc6d..334b9247e78c 100644
--- a/arch/arm/boot/dts/imx6q-sabreauto.dts
+++ b/arch/arm/boot/dts/imx6q-sabreauto.dts
@@ -20,24 +20,6 @@
 	compatible = "fsl,imx6q-sabreauto", "fsl,imx6q";
 };
 
-&iomuxc {
-	pinctrl-names = "default";
-	pinctrl-0 = <&pinctrl_hog>;
-
-	hog {
-		pinctrl_hog: hoggrp {
-			fsl,pins = <
-				MX6Q_PAD_NANDF_CS2__GPIO6_IO15 0x80000000
-				MX6Q_PAD_SD2_DAT2__GPIO1_IO13  0x80000000
-			>;
-		};
-	};
-
-	ecspi1 {
-		pinctrl_ecspi1_sabreauto: ecspi1-sabreauto {
-			fsl,pins = <
-				MX6Q_PAD_EIM_D19__GPIO3_IO19  0x80000000
-			>;
-		};
-	};
+&sata {
+	status = "okay";
 };
diff --git a/arch/arm/boot/dts/imx6q-sabrelite.dts b/arch/arm/boot/dts/imx6q-sabrelite.dts
index 6a000666c147..3530280f5150 100644
--- a/arch/arm/boot/dts/imx6q-sabrelite.dts
+++ b/arch/arm/boot/dts/imx6q-sabrelite.dts
@@ -65,6 +65,10 @@
 	};
 };
 
+&sata {
+	status = "okay";
+};
+
 &ecspi1 {
 	fsl,spi-num-chipselects = <1>;
 	cs-gpios = <&gpio3 19 0>;
@@ -91,14 +95,14 @@
 	hog {
 		pinctrl_hog: hoggrp {
 			fsl,pins = <
-				MX6Q_PAD_NANDF_D6__GPIO2_IO06 0x80000000
-				MX6Q_PAD_NANDF_D7__GPIO2_IO07 0x80000000
-				MX6Q_PAD_EIM_D19__GPIO3_IO19  0x80000000
-				MX6Q_PAD_EIM_D22__GPIO3_IO22  0x80000000
-				MX6Q_PAD_EIM_D23__GPIO3_IO23  0x80000000
-				MX6Q_PAD_SD3_DAT5__GPIO7_IO00 0x80000000
-				MX6Q_PAD_SD3_DAT4__GPIO7_IO01 0x1f0b0
-				MX6Q_PAD_GPIO_0__CCM_CLKO1    0x80000000
+				MX6QDL_PAD_NANDF_D6__GPIO2_IO06 0x80000000
+				MX6QDL_PAD_NANDF_D7__GPIO2_IO07 0x80000000
+				MX6QDL_PAD_EIM_D19__GPIO3_IO19  0x80000000
+				MX6QDL_PAD_EIM_D22__GPIO3_IO22  0x80000000
+				MX6QDL_PAD_EIM_D23__GPIO3_IO23  0x80000000
+				MX6QDL_PAD_SD3_DAT5__GPIO7_IO00 0x80000000
+				MX6QDL_PAD_SD3_DAT4__GPIO7_IO01 0x1f0b0
+				MX6QDL_PAD_GPIO_0__CCM_CLKO1    0x80000000
 			>;
 		};
 	};
@@ -163,7 +167,7 @@
 	codec: sgtl5000@0a {
 		compatible = "fsl,sgtl5000";
 		reg = <0x0a>;
-		clocks = <&clks 169>;
+		clocks = <&clks 201>;
 		VDDA-supply = <&reg_2p5v>;
 		VDDIO-supply = <&reg_3p3v>;
 	};
diff --git a/arch/arm/boot/dts/imx6q-sabresd.dts b/arch/arm/boot/dts/imx6q-sabresd.dts
index 0038228c508c..9cbdfe7a0931 100644
--- a/arch/arm/boot/dts/imx6q-sabresd.dts
+++ b/arch/arm/boot/dts/imx6q-sabresd.dts
@@ -20,21 +20,6 @@
 	compatible = "fsl,imx6q-sabresd", "fsl,imx6q";
 };
 
-&iomuxc {
-	pinctrl-names = "default";
-	pinctrl-0 = <&pinctrl_hog>;
-
-	hog {
-		pinctrl_hog: hoggrp {
-			fsl,pins = <
-				MX6Q_PAD_GPIO_4__GPIO1_IO04   0x80000000
-				MX6Q_PAD_GPIO_5__GPIO1_IO05   0x80000000
-				MX6Q_PAD_NANDF_D0__GPIO2_IO00 0x80000000
-				MX6Q_PAD_NANDF_D1__GPIO2_IO01 0x80000000
-				MX6Q_PAD_NANDF_D2__GPIO2_IO02 0x80000000
-				MX6Q_PAD_NANDF_D3__GPIO2_IO03 0x80000000
-				MX6Q_PAD_GPIO_0__CCM_CLKO1    0x130b0
-			>;
-		};
-	};
+&sata {
+	status = "okay";
 };
diff --git a/arch/arm/boot/dts/imx6q-wandboard.dts b/arch/arm/boot/dts/imx6q-wandboard.dts
new file mode 100644
index 000000000000..36be17f207b1
--- /dev/null
+++ b/arch/arm/boot/dts/imx6q-wandboard.dts
@@ -0,0 +1,26 @@
+/*
+ * Copyright 2013 Freescale Semiconductor, Inc.
+ *
+ * Author: Fabio Estevam <fabio.estevam@freescale.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+/dts-v1/;
+#include "imx6q.dtsi"
+#include "imx6qdl-wandboard.dtsi"
+
+/ {
+	model = "Wandboard i.MX6 Quad Board";
+	compatible = "wand,imx6q-wandboard", "fsl,imx6q";
+
+	memory {
+		reg = <0x10000000 0x80000000>;
+	};
+};
+
+&sata {
+	status = "okay";
+};
diff --git a/arch/arm/boot/dts/imx6q.dtsi b/arch/arm/boot/dts/imx6q.dtsi
index ba09dc32324e..f024ef28b34b 100644
--- a/arch/arm/boot/dts/imx6q.dtsi
+++ b/arch/arm/boot/dts/imx6q.dtsi
@@ -8,8 +8,8 @@
  *
  */
 
-#include "imx6qdl.dtsi"
 #include "imx6q-pinfunc.h"
+#include "imx6qdl.dtsi"
 
 / {
 	cpus {
@@ -61,6 +61,12 @@
 	};
 
 	soc {
+		ocram: sram@00900000 {
+			compatible = "mmio-sram";
+			reg = <0x00900000 0x40000>;
+			clocks = <&clks 142>;
+		};
+
 		aips-bus@02000000 { /* AIPS1 */
 			spba-bus@02000000 {
 				ecspi5: ecspi@02018000 {
@@ -77,357 +83,54 @@
 
 			iomuxc: iomuxc@020e0000 {
 				compatible = "fsl,imx6q-iomuxc";
-				reg = <0x020e0000 0x4000>;
-
-				/* shared pinctrl settings */
-				audmux {
-					pinctrl_audmux_1: audmux-1 {
-						fsl,pins = <
-							MX6Q_PAD_SD2_DAT0__AUD4_RXD  0x80000000
-							MX6Q_PAD_SD2_DAT3__AUD4_TXC  0x80000000
-							MX6Q_PAD_SD2_DAT2__AUD4_TXD  0x80000000
-							MX6Q_PAD_SD2_DAT1__AUD4_TXFS 0x80000000
-						>;
-					};
-
-					pinctrl_audmux_2: audmux-2 {
-						fsl,pins = <
-							MX6Q_PAD_CSI0_DAT7__AUD3_RXD  0x80000000
-							MX6Q_PAD_CSI0_DAT4__AUD3_TXC  0x80000000
-							MX6Q_PAD_CSI0_DAT5__AUD3_TXD  0x80000000
-							MX6Q_PAD_CSI0_DAT6__AUD3_TXFS 0x80000000
-						>;
-					};
-				};
-
-				ecspi1 {
-					pinctrl_ecspi1_1: ecspi1grp-1 {
-						fsl,pins = <
-							MX6Q_PAD_EIM_D17__ECSPI1_MISO 0x100b1
-							MX6Q_PAD_EIM_D18__ECSPI1_MOSI 0x100b1
-							MX6Q_PAD_EIM_D16__ECSPI1_SCLK 0x100b1
-						>;
-					};
-				};
-
-				ecspi3 {
-					pinctrl_ecspi3_1: ecspi3grp-1 {
-						fsl,pins = <
-							MX6Q_PAD_DISP0_DAT2__ECSPI3_MISO 0x100b1
-							MX6Q_PAD_DISP0_DAT1__ECSPI3_MOSI 0x100b1
-							MX6Q_PAD_DISP0_DAT0__ECSPI3_SCLK 0x100b1
-						>;
-					};
-				};
-
-				enet {
-					pinctrl_enet_1: enetgrp-1 {
-						fsl,pins = <
-							MX6Q_PAD_ENET_MDIO__ENET_MDIO       0x1b0b0
-							MX6Q_PAD_ENET_MDC__ENET_MDC         0x1b0b0
-							MX6Q_PAD_RGMII_TXC__RGMII_TXC       0x1b0b0
-							MX6Q_PAD_RGMII_TD0__RGMII_TD0       0x1b0b0
-							MX6Q_PAD_RGMII_TD1__RGMII_TD1       0x1b0b0
-							MX6Q_PAD_RGMII_TD2__RGMII_TD2       0x1b0b0
-							MX6Q_PAD_RGMII_TD3__RGMII_TD3       0x1b0b0
-							MX6Q_PAD_RGMII_TX_CTL__RGMII_TX_CTL 0x1b0b0
-							MX6Q_PAD_ENET_REF_CLK__ENET_TX_CLK  0x1b0b0
-							MX6Q_PAD_RGMII_RXC__RGMII_RXC       0x1b0b0
-							MX6Q_PAD_RGMII_RD0__RGMII_RD0       0x1b0b0
-							MX6Q_PAD_RGMII_RD1__RGMII_RD1       0x1b0b0
-							MX6Q_PAD_RGMII_RD2__RGMII_RD2       0x1b0b0
-							MX6Q_PAD_RGMII_RD3__RGMII_RD3       0x1b0b0
-							MX6Q_PAD_RGMII_RX_CTL__RGMII_RX_CTL 0x1b0b0
-							MX6Q_PAD_GPIO_16__ENET_REF_CLK      0x4001b0a8
-						>;
-					};
-
-					pinctrl_enet_2: enetgrp-2 {
-						fsl,pins = <
-							MX6Q_PAD_KEY_COL1__ENET_MDIO        0x1b0b0
-							MX6Q_PAD_KEY_COL2__ENET_MDC         0x1b0b0
-							MX6Q_PAD_RGMII_TXC__RGMII_TXC       0x1b0b0
-							MX6Q_PAD_RGMII_TD0__RGMII_TD0       0x1b0b0
-							MX6Q_PAD_RGMII_TD1__RGMII_TD1       0x1b0b0
-							MX6Q_PAD_RGMII_TD2__RGMII_TD2       0x1b0b0
-							MX6Q_PAD_RGMII_TD3__RGMII_TD3       0x1b0b0
-							MX6Q_PAD_RGMII_TX_CTL__RGMII_TX_CTL 0x1b0b0
-							MX6Q_PAD_ENET_REF_CLK__ENET_TX_CLK  0x1b0b0
-							MX6Q_PAD_RGMII_RXC__RGMII_RXC       0x1b0b0
-							MX6Q_PAD_RGMII_RD0__RGMII_RD0       0x1b0b0
-							MX6Q_PAD_RGMII_RD1__RGMII_RD1       0x1b0b0
-							MX6Q_PAD_RGMII_RD2__RGMII_RD2       0x1b0b0
-							MX6Q_PAD_RGMII_RD3__RGMII_RD3       0x1b0b0
-							MX6Q_PAD_RGMII_RX_CTL__RGMII_RX_CTL 0x1b0b0
-						>;
-					};
-
-					pinctrl_enet_3: enetgrp-3 {
-						fsl,pins = <
-							MX6Q_PAD_ENET_MDIO__ENET_MDIO       0x1b0b0
-							MX6Q_PAD_ENET_MDC__ENET_MDC         0x1b0b0
-							MX6Q_PAD_RGMII_TXC__RGMII_TXC       0x1b0b0
-							MX6Q_PAD_RGMII_TD0__RGMII_TD0       0x1b0b0
-							MX6Q_PAD_RGMII_TD1__RGMII_TD1       0x1b0b0
-							MX6Q_PAD_RGMII_TD2__RGMII_TD2       0x1b0b0
-							MX6Q_PAD_RGMII_TD3__RGMII_TD3       0x1b0b0
-							MX6Q_PAD_RGMII_TX_CTL__RGMII_TX_CTL 0x1b0b0
-							MX6Q_PAD_ENET_REF_CLK__ENET_TX_CLK  0x1b0b0
-							MX6Q_PAD_RGMII_RXC__RGMII_RXC       0x1b0b0
-							MX6Q_PAD_RGMII_RD0__RGMII_RD0       0x1b0b0
-							MX6Q_PAD_RGMII_RD1__RGMII_RD1       0x1b0b0
-							MX6Q_PAD_RGMII_RD2__RGMII_RD2       0x1b0b0
-							MX6Q_PAD_RGMII_RD3__RGMII_RD3       0x1b0b0
-							MX6Q_PAD_RGMII_RX_CTL__RGMII_RX_CTL 0x1b0b0
-							MX6Q_PAD_ENET_TX_EN__ENET_TX_EN     0x1b0b0
-						>;
-					};
-				};
-
-				gpmi-nand {
-					pinctrl_gpmi_nand_1: gpmi-nand-1 {
-						fsl,pins = <
-							MX6Q_PAD_NANDF_CLE__NAND_CLE     0xb0b1
-							MX6Q_PAD_NANDF_ALE__NAND_ALE     0xb0b1
-							MX6Q_PAD_NANDF_WP_B__NAND_WP_B   0xb0b1
-							MX6Q_PAD_NANDF_RB0__NAND_READY_B 0xb000
-							MX6Q_PAD_NANDF_CS0__NAND_CE0_B   0xb0b1
-							MX6Q_PAD_NANDF_CS1__NAND_CE1_B   0xb0b1
-							MX6Q_PAD_SD4_CMD__NAND_RE_B      0xb0b1
-							MX6Q_PAD_SD4_CLK__NAND_WE_B      0xb0b1
-							MX6Q_PAD_NANDF_D0__NAND_DATA00   0xb0b1
-							MX6Q_PAD_NANDF_D1__NAND_DATA01   0xb0b1
-							MX6Q_PAD_NANDF_D2__NAND_DATA02   0xb0b1
-							MX6Q_PAD_NANDF_D3__NAND_DATA03   0xb0b1
-							MX6Q_PAD_NANDF_D4__NAND_DATA04   0xb0b1
-							MX6Q_PAD_NANDF_D5__NAND_DATA05   0xb0b1
-							MX6Q_PAD_NANDF_D6__NAND_DATA06   0xb0b1
-							MX6Q_PAD_NANDF_D7__NAND_DATA07   0xb0b1
-							MX6Q_PAD_SD4_DAT0__NAND_DQS      0x00b1
-						>;
-					};
-				};
-
-				i2c1 {
-					pinctrl_i2c1_1: i2c1grp-1 {
-						fsl,pins = <
-							MX6Q_PAD_EIM_D21__I2C1_SCL 0x4001b8b1
-							MX6Q_PAD_EIM_D28__I2C1_SDA 0x4001b8b1
-						>;
-					};
 
-					pinctrl_i2c1_2: i2c1grp-2 {
-						fsl,pins = <
-							MX6Q_PAD_CSI0_DAT8__I2C1_SDA 0x4001b8b1
-							MX6Q_PAD_CSI0_DAT9__I2C1_SCL 0x4001b8b1
-						>;
-					};
-				};
-
-				i2c2 {
-					pinctrl_i2c2_1: i2c2grp-1 {
-						fsl,pins = <
-							MX6Q_PAD_EIM_EB2__I2C2_SCL 0x4001b8b1
-							MX6Q_PAD_EIM_D16__I2C2_SDA 0x4001b8b1
+				ipu2 {
+					pinctrl_ipu2_1: ipu2grp-1 {
+						fsl,pins = <
+							MX6QDL_PAD_DI0_DISP_CLK__IPU2_DI0_DISP_CLK 0x10
+							MX6QDL_PAD_DI0_PIN15__IPU2_DI0_PIN15       0x10
+							MX6QDL_PAD_DI0_PIN2__IPU2_DI0_PIN02        0x10
+							MX6QDL_PAD_DI0_PIN3__IPU2_DI0_PIN03        0x10
+							MX6QDL_PAD_DI0_PIN4__IPU2_DI0_PIN04        0x80000000
+							MX6QDL_PAD_DISP0_DAT0__IPU2_DISP0_DATA00   0x10
+							MX6QDL_PAD_DISP0_DAT1__IPU2_DISP0_DATA01   0x10
+							MX6QDL_PAD_DISP0_DAT2__IPU2_DISP0_DATA02   0x10
+							MX6QDL_PAD_DISP0_DAT3__IPU2_DISP0_DATA03   0x10
+							MX6QDL_PAD_DISP0_DAT4__IPU2_DISP0_DATA04   0x10
+							MX6QDL_PAD_DISP0_DAT5__IPU2_DISP0_DATA05   0x10
+							MX6QDL_PAD_DISP0_DAT6__IPU2_DISP0_DATA06   0x10
+							MX6QDL_PAD_DISP0_DAT7__IPU2_DISP0_DATA07   0x10
+							MX6QDL_PAD_DISP0_DAT8__IPU2_DISP0_DATA08   0x10
+							MX6QDL_PAD_DISP0_DAT9__IPU2_DISP0_DATA09   0x10
+							MX6QDL_PAD_DISP0_DAT10__IPU2_DISP0_DATA10  0x10
+							MX6QDL_PAD_DISP0_DAT11__IPU2_DISP0_DATA11  0x10
+							MX6QDL_PAD_DISP0_DAT12__IPU2_DISP0_DATA12  0x10
+							MX6QDL_PAD_DISP0_DAT13__IPU2_DISP0_DATA13  0x10
+							MX6QDL_PAD_DISP0_DAT14__IPU2_DISP0_DATA14  0x10
+							MX6QDL_PAD_DISP0_DAT15__IPU2_DISP0_DATA15  0x10
+							MX6QDL_PAD_DISP0_DAT16__IPU2_DISP0_DATA16  0x10
+							MX6QDL_PAD_DISP0_DAT17__IPU2_DISP0_DATA17  0x10
+							MX6QDL_PAD_DISP0_DAT18__IPU2_DISP0_DATA18  0x10
+							MX6QDL_PAD_DISP0_DAT19__IPU2_DISP0_DATA19  0x10
+							MX6QDL_PAD_DISP0_DAT20__IPU2_DISP0_DATA20  0x10
+							MX6QDL_PAD_DISP0_DAT21__IPU2_DISP0_DATA21  0x10
+							MX6QDL_PAD_DISP0_DAT22__IPU2_DISP0_DATA22  0x10
+							MX6QDL_PAD_DISP0_DAT23__IPU2_DISP0_DATA23  0x10
 						>;
 					};
 				};
-
-				i2c3 {
-					pinctrl_i2c3_1: i2c3grp-1 {
-						fsl,pins = <
-							MX6Q_PAD_EIM_D17__I2C3_SCL 0x4001b8b1
-							MX6Q_PAD_EIM_D18__I2C3_SDA 0x4001b8b1
-						>;
-					};
-				};
-
-				uart1 {
-					pinctrl_uart1_1: uart1grp-1 {
-						fsl,pins = <
-							MX6Q_PAD_CSI0_DAT10__UART1_TX_DATA 0x1b0b1
-							MX6Q_PAD_CSI0_DAT11__UART1_RX_DATA 0x1b0b1
-						>;
-					};
-				};
-
-				uart2 {
-					pinctrl_uart2_1: uart2grp-1 {
-						fsl,pins = <
-							MX6Q_PAD_EIM_D26__UART2_TX_DATA 0x1b0b1
-							MX6Q_PAD_EIM_D27__UART2_RX_DATA 0x1b0b1
-						>;
-					};
-				};
-
-				uart4 {
-					pinctrl_uart4_1: uart4grp-1 {
-						fsl,pins = <
-							MX6Q_PAD_KEY_COL0__UART4_TX_DATA 0x1b0b1
-							MX6Q_PAD_KEY_ROW0__UART4_RX_DATA 0x1b0b1
-						>;
-					};
-				};
-
-				usbotg {
-					pinctrl_usbotg_1: usbotggrp-1 {
-						fsl,pins = <
-							MX6Q_PAD_GPIO_1__USB_OTG_ID 0x17059
-						>;
-					};
-
-					pinctrl_usbotg_2: usbotggrp-2 {
-						fsl,pins = <
-							MX6Q_PAD_ENET_RX_ER__USB_OTG_ID 0x17059
-						>;
-					};
-				};
-
-				usdhc2 {
-					pinctrl_usdhc2_1: usdhc2grp-1 {
-						fsl,pins = <
-							MX6Q_PAD_SD2_CMD__SD2_CMD    0x17059
-							MX6Q_PAD_SD2_CLK__SD2_CLK    0x10059
-							MX6Q_PAD_SD2_DAT0__SD2_DATA0 0x17059
-							MX6Q_PAD_SD2_DAT1__SD2_DATA1 0x17059
-							MX6Q_PAD_SD2_DAT2__SD2_DATA2 0x17059
-							MX6Q_PAD_SD2_DAT3__SD2_DATA3 0x17059
-							MX6Q_PAD_NANDF_D4__SD2_DATA4 0x17059
-							MX6Q_PAD_NANDF_D5__SD2_DATA5 0x17059
-							MX6Q_PAD_NANDF_D6__SD2_DATA6 0x17059
-							MX6Q_PAD_NANDF_D7__SD2_DATA7 0x17059
-						>;
-					};
-
-					pinctrl_usdhc2_2: usdhc2grp-2 {
-						fsl,pins = <
-							MX6Q_PAD_SD2_CMD__SD2_CMD    0x17059
-							MX6Q_PAD_SD2_CLK__SD2_CLK    0x10059
-							MX6Q_PAD_SD2_DAT0__SD2_DATA0 0x17059
-							MX6Q_PAD_SD2_DAT1__SD2_DATA1 0x17059
-							MX6Q_PAD_SD2_DAT2__SD2_DATA2 0x17059
-							MX6Q_PAD_SD2_DAT3__SD2_DATA3 0x17059
-						>;
-					};
-				};
-
-				usdhc3 {
-					pinctrl_usdhc3_1: usdhc3grp-1 {
-						fsl,pins = <
-							MX6Q_PAD_SD3_CMD__SD3_CMD    0x17059
-							MX6Q_PAD_SD3_CLK__SD3_CLK    0x10059
-							MX6Q_PAD_SD3_DAT0__SD3_DATA0 0x17059
-							MX6Q_PAD_SD3_DAT1__SD3_DATA1 0x17059
-							MX6Q_PAD_SD3_DAT2__SD3_DATA2 0x17059
-							MX6Q_PAD_SD3_DAT3__SD3_DATA3 0x17059
-							MX6Q_PAD_SD3_DAT4__SD3_DATA4 0x17059
-							MX6Q_PAD_SD3_DAT5__SD3_DATA5 0x17059
-							MX6Q_PAD_SD3_DAT6__SD3_DATA6 0x17059
-							MX6Q_PAD_SD3_DAT7__SD3_DATA7 0x17059
-						>;
-					};
-
-					pinctrl_usdhc3_2: usdhc3grp-2 {
-						fsl,pins = <
-							MX6Q_PAD_SD3_CMD__SD3_CMD    0x17059
-							MX6Q_PAD_SD3_CLK__SD3_CLK    0x10059
-							MX6Q_PAD_SD3_DAT0__SD3_DATA0 0x17059
-							MX6Q_PAD_SD3_DAT1__SD3_DATA1 0x17059
-							MX6Q_PAD_SD3_DAT2__SD3_DATA2 0x17059
-							MX6Q_PAD_SD3_DAT3__SD3_DATA3 0x17059
-						>;
-					};
-				};
-
-				usdhc4 {
-					pinctrl_usdhc4_1: usdhc4grp-1 {
-						fsl,pins = <
-							MX6Q_PAD_SD4_CMD__SD4_CMD    0x17059
-							MX6Q_PAD_SD4_CLK__SD4_CLK    0x10059
-							MX6Q_PAD_SD4_DAT0__SD4_DATA0 0x17059
-							MX6Q_PAD_SD4_DAT1__SD4_DATA1 0x17059
-							MX6Q_PAD_SD4_DAT2__SD4_DATA2 0x17059
-							MX6Q_PAD_SD4_DAT3__SD4_DATA3 0x17059
-							MX6Q_PAD_SD4_DAT4__SD4_DATA4 0x17059
-							MX6Q_PAD_SD4_DAT5__SD4_DATA5 0x17059
-							MX6Q_PAD_SD4_DAT6__SD4_DATA6 0x17059
-							MX6Q_PAD_SD4_DAT7__SD4_DATA7 0x17059
-						>;
-					};
-
-					pinctrl_usdhc4_2: usdhc4grp-2 {
-						fsl,pins = <
-							MX6Q_PAD_SD4_CMD__SD4_CMD    0x17059
-							MX6Q_PAD_SD4_CLK__SD4_CLK    0x10059
-							MX6Q_PAD_SD4_DAT0__SD4_DATA0 0x17059
-							MX6Q_PAD_SD4_DAT1__SD4_DATA1 0x17059
-							MX6Q_PAD_SD4_DAT2__SD4_DATA2 0x17059
-							MX6Q_PAD_SD4_DAT3__SD4_DATA3 0x17059
-						>;
-					};
-				};
-
-				weim {
-					pinctrl_weim_cs0_1: weim_cs0grp-1 {
-						fsl,pins = <
-							MX6Q_PAD_EIM_CS0__EIM_CS0_B   0xb0b1
-						>;
-					};
-
-					pinctrl_weim_nor_1: weimnorgrp-1 {
-						fsl,pins = <
-							MX6Q_PAD_EIM_OE__EIM_OE_B     0xb0b1
-							MX6Q_PAD_EIM_RW__EIM_RW       0xb0b1
-							MX6Q_PAD_EIM_WAIT__EIM_WAIT_B 0xb060
-							/* data */
-							MX6Q_PAD_EIM_D16__EIM_DATA16 0x1b0b0
-							MX6Q_PAD_EIM_D17__EIM_DATA17 0x1b0b0
-							MX6Q_PAD_EIM_D18__EIM_DATA18 0x1b0b0
-							MX6Q_PAD_EIM_D19__EIM_DATA19 0x1b0b0
-							MX6Q_PAD_EIM_D20__EIM_DATA20 0x1b0b0
-							MX6Q_PAD_EIM_D21__EIM_DATA21 0x1b0b0
-							MX6Q_PAD_EIM_D22__EIM_DATA22 0x1b0b0
-							MX6Q_PAD_EIM_D23__EIM_DATA23 0x1b0b0
-							MX6Q_PAD_EIM_D24__EIM_DATA24 0x1b0b0
-							MX6Q_PAD_EIM_D25__EIM_DATA25 0x1b0b0
-							MX6Q_PAD_EIM_D26__EIM_DATA26 0x1b0b0
-							MX6Q_PAD_EIM_D27__EIM_DATA27 0x1b0b0
-							MX6Q_PAD_EIM_D28__EIM_DATA28 0x1b0b0
-							MX6Q_PAD_EIM_D29__EIM_DATA29 0x1b0b0
-							MX6Q_PAD_EIM_D30__EIM_DATA30 0x1b0b0
-							MX6Q_PAD_EIM_D31__EIM_DATA31 0x1b0b0
-							/* address */
-							MX6Q_PAD_EIM_A23__EIM_ADDR23 0xb0b1
-							MX6Q_PAD_EIM_A22__EIM_ADDR22 0xb0b1
-							MX6Q_PAD_EIM_A21__EIM_ADDR21 0xb0b1
-							MX6Q_PAD_EIM_A20__EIM_ADDR20 0xb0b1
-							MX6Q_PAD_EIM_A19__EIM_ADDR19 0xb0b1
-							MX6Q_PAD_EIM_A18__EIM_ADDR18 0xb0b1
-							MX6Q_PAD_EIM_A17__EIM_ADDR17 0xb0b1
-							MX6Q_PAD_EIM_A16__EIM_ADDR16 0xb0b1
-							MX6Q_PAD_EIM_DA15__EIM_AD15  0xb0b1
-							MX6Q_PAD_EIM_DA14__EIM_AD14  0xb0b1
-							MX6Q_PAD_EIM_DA13__EIM_AD13  0xb0b1
-							MX6Q_PAD_EIM_DA12__EIM_AD12  0xb0b1
-							MX6Q_PAD_EIM_DA11__EIM_AD11  0xb0b1
-							MX6Q_PAD_EIM_DA10__EIM_AD10  0xb0b1
-							MX6Q_PAD_EIM_DA9__EIM_AD09   0xb0b1
-							MX6Q_PAD_EIM_DA8__EIM_AD08   0xb0b1
-							MX6Q_PAD_EIM_DA7__EIM_AD07   0xb0b1
-							MX6Q_PAD_EIM_DA6__EIM_AD06   0xb0b1
-							MX6Q_PAD_EIM_DA5__EIM_AD05   0xb0b1
-							MX6Q_PAD_EIM_DA4__EIM_AD04   0xb0b1
-							MX6Q_PAD_EIM_DA3__EIM_AD03   0xb0b1
-							MX6Q_PAD_EIM_DA2__EIM_AD02   0xb0b1
-							MX6Q_PAD_EIM_DA1__EIM_AD01   0xb0b1
-							MX6Q_PAD_EIM_DA0__EIM_AD00   0xb0b1
-						>;
-					};
-
-				};
 			};
 		};
 
+		sata: sata@02200000 {
+			compatible = "fsl,imx6q-ahci";
+			reg = <0x02200000 0x4000>;
+			interrupts = <0 39 0x04>;
+			clocks =  <&clks 154>, <&clks 187>, <&clks 105>;
+			clock-names = "sata", "sata_ref", "ahb";
+			status = "disabled";
+		};
+
 		ipu2: ipu@02800000 {
 			#crtc-cells = <1>;
 			compatible = "fsl,imx6q-ipu";
diff --git a/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi b/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi
index e994011220e7..1cbbc5160d27 100644
--- a/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi
@@ -45,6 +45,28 @@
 	status = "okay";
 };
 
+&iomuxc {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_hog>;
+
+	hog {
+		pinctrl_hog: hoggrp {
+			fsl,pins = <
+				MX6QDL_PAD_NANDF_CS2__GPIO6_IO15 0x80000000
+				MX6QDL_PAD_SD2_DAT2__GPIO1_IO13  0x80000000
+			>;
+		};
+	};
+
+	ecspi1 {
+		pinctrl_ecspi1_sabreauto: ecspi1-sabreauto {
+			fsl,pins = <
+				MX6QDL_PAD_EIM_D19__GPIO3_IO19 0x80000000
+			>;
+		};
+	};
+};
+
 &uart4 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_uart4_1>;
diff --git a/arch/arm/boot/dts/imx6qdl-sabresd.dtsi b/arch/arm/boot/dts/imx6qdl-sabresd.dtsi
index 6e5dfdb32416..39eafc222a2e 100644
--- a/arch/arm/boot/dts/imx6qdl-sabresd.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-sabresd.dtsi
@@ -27,6 +27,15 @@
 			enable-active-high;
 		};
 
+		reg_usb_h1_vbus: usb_h1_vbus {
+			compatible = "regulator-fixed";
+			regulator-name = "usb_h1_vbus";
+			regulator-min-microvolt = <5000000>;
+			regulator-max-microvolt = <5000000>;
+			gpio = <&gpio1 29 0>;
+			enable-active-high;
+		};
+
 		reg_audio: wm8962_supply {
 			compatible = "regulator-fixed";
 			regulator-name = "wm8962-supply";
@@ -41,12 +50,14 @@
 		volume-up {
 			label = "Volume Up";
 			gpios = <&gpio1 4 0>;
+			gpio-key,wakeup;
 			linux,code = <115>; /* KEY_VOLUMEUP */
 		};
 
 		volume-down {
 			label = "Volume Down";
 			gpios = <&gpio1 5 0>;
+			gpio-key,wakeup;
 			linux,code = <114>; /* KEY_VOLUMEDOWN */
 		};
 	};
@@ -77,6 +88,22 @@
 	status = "okay";
 };
 
+&ecspi1 {
+	fsl,spi-num-chipselects = <1>;
+	cs-gpios = <&gpio4 9 0>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_ecspi1_2>;
+	status = "okay";
+
+	flash: m25p80@0 {
+		#address-cells = <1>;
+		#size-cells = <1>;
+		compatible = "st,m25p32";
+		spi-max-frequency = <20000000>;
+		reg = <0>;
+	};
+};
+
 &fec {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_enet_1>;
@@ -93,7 +120,7 @@
 	codec: wm8962@1a {
 		compatible = "wlf,wm8962";
 		reg = <0x1a>;
-		clocks = <&clks 169>;
+		clocks = <&clks 201>;
 		DCVDD-supply = <&reg_audio>;
 		DBVDD-supply = <&reg_audio>;
 		AVDD-supply = <&reg_audio>;
@@ -113,6 +140,68 @@
        };
 };
 
+&i2c3 {
+	clock-frequency = <100000>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_i2c3_2>;
+	status = "okay";
+
+	egalax_ts@04 {
+		compatible = "eeti,egalax_ts";
+		reg = <0x04>;
+		interrupt-parent = <&gpio6>;
+		interrupts = <7 2>;
+		wakeup-gpios = <&gpio6 7 0>;
+	};
+};
+
+&iomuxc {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_hog>;
+
+	hog {
+		pinctrl_hog: hoggrp {
+			fsl,pins = <
+				MX6QDL_PAD_GPIO_4__GPIO1_IO04   0x80000000
+				MX6QDL_PAD_GPIO_5__GPIO1_IO05   0x80000000
+				MX6QDL_PAD_NANDF_D0__GPIO2_IO00 0x80000000
+				MX6QDL_PAD_NANDF_D1__GPIO2_IO01 0x80000000
+				MX6QDL_PAD_NANDF_D2__GPIO2_IO02 0x80000000
+				MX6QDL_PAD_NANDF_D3__GPIO2_IO03 0x80000000
+				MX6QDL_PAD_GPIO_0__CCM_CLKO1    0x130b0
+				MX6QDL_PAD_NANDF_CLE__GPIO6_IO07 0x80000000
+				MX6QDL_PAD_ENET_TXD1__GPIO1_IO29 0x80000000
+				MX6QDL_PAD_EIM_D22__GPIO3_IO22  0x80000000
+			>;
+		};
+	};
+};
+
+&ldb {
+	status = "okay";
+
+	lvds-channel@1 {
+		fsl,data-mapping = "spwg";
+		fsl,data-width = <18>;
+		status = "okay";
+
+		display-timings {
+			native-mode = <&timing0>;
+			timing0: hsd100pxn1 {
+				clock-frequency = <65000000>;
+				hactive = <1024>;
+				vactive = <768>;
+				hback-porch = <220>;
+				hfront-porch = <40>;
+				vback-porch = <21>;
+				vfront-porch = <7>;
+				hsync-len = <60>;
+				vsync-len = <10>;
+			};
+		};
+	};
+};
+
 &ssi2 {
 	fsl,mode = "i2s-slave";
 	status = "okay";
@@ -125,6 +214,7 @@
 };
 
 &usbh1 {
+	vbus-supply = <&reg_usb_h1_vbus>;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/imx6qdl-wandboard.dtsi b/arch/arm/boot/dts/imx6qdl-wandboard.dtsi
new file mode 100644
index 000000000000..a55113e65bcb
--- /dev/null
+++ b/arch/arm/boot/dts/imx6qdl-wandboard.dtsi
@@ -0,0 +1,137 @@
+/*
+ * Copyright 2013 Freescale Semiconductor, Inc.
+ *
+ * Author: Fabio Estevam <fabio.estevam@freescale.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+/ {
+	regulators {
+		compatible = "simple-bus";
+
+		reg_2p5v: 2p5v {
+			compatible = "regulator-fixed";
+			regulator-name = "2P5V";
+			regulator-min-microvolt = <2500000>;
+			regulator-max-microvolt = <2500000>;
+			regulator-always-on;
+		};
+
+		reg_3p3v: 3p3v {
+			compatible = "regulator-fixed";
+			regulator-name = "3P3V";
+			regulator-min-microvolt = <3300000>;
+			regulator-max-microvolt = <3300000>;
+			regulator-always-on;
+		};
+	};
+
+	sound {
+		compatible = "fsl,imx6-wandboard-sgtl5000",
+			     "fsl,imx-audio-sgtl5000";
+		model = "imx6-wandboard-sgtl5000";
+		ssi-controller = <&ssi1>;
+		audio-codec = <&codec>;
+		audio-routing =
+			"MIC_IN", "Mic Jack",
+			"Mic Jack", "Mic Bias",
+			"Headphone Jack", "HP_OUT";
+		mux-int-port = <1>;
+		mux-ext-port = <3>;
+	};
+};
+
+&audmux {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_audmux_2>;
+	status = "okay";
+};
+
+&i2c2 {
+	clock-frequency = <100000>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_i2c2_2>;
+	status = "okay";
+
+	codec: sgtl5000@0a {
+		compatible = "fsl,sgtl5000";
+		reg = <0x0a>;
+		clocks = <&clks 201>;
+		VDDA-supply = <&reg_2p5v>;
+		VDDIO-supply = <&reg_3p3v>;
+	};
+};
+
+&iomuxc {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_hog>;
+
+	hog {
+		pinctrl_hog: hoggrp {
+			fsl,pins = <
+				MX6QDL_PAD_GPIO_0__CCM_CLKO1 	 0x130b0
+				MX6QDL_PAD_GPIO_2__GPIO1_IO02	 0x80000000
+				MX6QDL_PAD_EIM_DA9__GPIO3_IO09	 0x80000000
+				MX6QDL_PAD_EIM_EB1__GPIO2_IO29   0x80000000 /* WL_REF_ON */
+				MX6QDL_PAD_EIM_A25__GPIO5_IO02   0x80000000 /* WL_RST_N */
+				MX6QDL_PAD_ENET_RXD1__GPIO1_IO26 0x80000000 /* WL_REG_ON */
+				MX6QDL_PAD_ENET_TXD1__GPIO1_IO29 0x80000000 /* WL_HOST_WAKE */
+				MX6QDL_PAD_ENET_TXD0__GPIO1_IO30 0x80000000 /* WL_WAKE */
+			>;
+		};
+	};
+};
+
+&fec {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_enet_1>;
+	phy-mode = "rgmii";
+	status = "okay";
+};
+
+&ssi1 {
+	fsl,mode = "i2s-slave";
+	status = "okay";
+};
+
+&uart1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_uart1_1>;
+	status = "okay";
+};
+
+&uart3 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_uart3_2>;
+	fsl,uart-has-rtscts;
+	status = "okay";
+};
+
+&usbh1 {
+	status = "okay";
+};
+
+&usdhc1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_usdhc1_2>;
+	cd-gpios = <&gpio1 2 0>;
+	status = "okay";
+};
+
+&usdhc2 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_usdhc2_2>;
+	non-removable;
+	status = "okay";
+};
+
+&usdhc3 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_usdhc3_2>;
+	cd-gpios = <&gpio3 9 0>;
+	status = "okay";
+};
diff --git a/arch/arm/boot/dts/imx6qdl.dtsi b/arch/arm/boot/dts/imx6qdl.dtsi
index f21d259080fd..ccd55c2fdb67 100644
--- a/arch/arm/boot/dts/imx6qdl.dtsi
+++ b/arch/arm/boot/dts/imx6qdl.dtsi
@@ -14,11 +14,6 @@
 
 / {
 	aliases {
-		serial0 = &uart1;
-		serial1 = &uart2;
-		serial2 = &uart3;
-		serial3 = &uart4;
-		serial4 = &uart5;
 		gpio0 = &gpio1;
 		gpio1 = &gpio2;
 		gpio2 = &gpio3;
@@ -26,6 +21,18 @@
 		gpio4 = &gpio5;
 		gpio5 = &gpio6;
 		gpio6 = &gpio7;
+		i2c0 = &i2c1;
+		i2c1 = &i2c2;
+		i2c2 = &i2c3;
+		serial0 = &uart1;
+		serial1 = &uart2;
+		serial2 = &uart3;
+		serial3 = &uart4;
+		serial4 = &uart5;
+		spi0 = &ecspi1;
+		spi1 = &ecspi2;
+		spi2 = &ecspi3;
+		spi3 = &ecspi4;
 	};
 
 	intc: interrupt-controller@00a01000 {
@@ -81,15 +88,14 @@
 			#size-cells = <1>;
 			reg = <0x00112000 0x2000>, <0x00114000 0x2000>;
 			reg-names = "gpmi-nand", "bch";
-			interrupts = <0 13 0x04>, <0 15 0x04>;
-			interrupt-names = "gpmi-dma", "bch";
+			interrupts = <0 15 0x04>;
+			interrupt-names = "bch";
 			clocks = <&clks 152>, <&clks 153>, <&clks 151>,
 				 <&clks 150>, <&clks 149>;
 			clock-names = "gpmi_io", "gpmi_apb", "gpmi_bch",
 				      "gpmi_bch_apb", "per1_bch";
 			dmas = <&dma_apbh 0>;
 			dma-names = "rx-tx";
-			fsl,gpmi-dma-channel = <0>;
 			status = "disabled";
 		};
 
@@ -184,6 +190,8 @@
 					interrupts = <0 26 0x04>;
 					clocks = <&clks 160>, <&clks 161>;
 					clock-names = "ipg", "per";
+					dmas = <&sdma 25 4 0>, <&sdma 26 4 0>;
+					dma-names = "rx", "tx";
 					status = "disabled";
 				};
 
@@ -197,6 +205,9 @@
 					reg = <0x02028000 0x4000>;
 					interrupts = <0 46 0x04>;
 					clocks = <&clks 178>;
+					dmas = <&sdma 37 1 0>,
+					       <&sdma 38 1 0>;
+					dma-names = "rx", "tx";
 					fsl,fifo-depth = <15>;
 					fsl,ssi-dma-events = <38 37>;
 					status = "disabled";
@@ -207,6 +218,9 @@
 					reg = <0x0202c000 0x4000>;
 					interrupts = <0 47 0x04>;
 					clocks = <&clks 179>;
+					dmas = <&sdma 41 1 0>,
+					       <&sdma 42 1 0>;
+					dma-names = "rx", "tx";
 					fsl,fifo-depth = <15>;
 					fsl,ssi-dma-events = <42 41>;
 					status = "disabled";
@@ -217,6 +231,9 @@
 					reg = <0x02030000 0x4000>;
 					interrupts = <0 48 0x04>;
 					clocks = <&clks 180>;
+					dmas = <&sdma 45 1 0>,
+					       <&sdma 46 1 0>;
+					dma-names = "rx", "tx";
 					fsl,fifo-depth = <15>;
 					fsl,ssi-dma-events = <46 45>;
 					status = "disabled";
@@ -278,17 +295,23 @@
 			};
 
 			can1: flexcan@02090000 {
+				compatible = "fsl,imx6q-flexcan";
 				reg = <0x02090000 0x4000>;
 				interrupts = <0 110 0x04>;
+				clocks = <&clks 108>, <&clks 109>;
+				clock-names = "ipg", "per";
 			};
 
 			can2: flexcan@02094000 {
+				compatible = "fsl,imx6q-flexcan";
 				reg = <0x02094000 0x4000>;
 				interrupts = <0 111 0x04>;
+				clocks = <&clks 110>, <&clks 111>;
+				clock-names = "ipg", "per";
 			};
 
 			gpt: gpt@02098000 {
-				compatible = "fsl,imx6q-gpt";
+				compatible = "fsl,imx6q-gpt", "fsl,imx31-gpt";
 				reg = <0x02098000 0x4000>;
 				interrupts = <0 55 0x04>;
 				clocks = <&clks 119>, <&clks 120>;
@@ -491,6 +514,13 @@
 				};
 			};
 
+			tempmon: tempmon {
+				compatible = "fsl,imx6q-tempmon";
+				interrupts = <0 49 0x04>;
+				fsl,tempmon = <&anatop>;
+				fsl,tempmon-data = <&ocotp>;
+			};
+
 			usbphy1: usbphy@020c9000 {
 				compatible = "fsl,imx6q-usbphy", "fsl,imx23-usbphy";
 				reg = <0x020c9000 0x1000>;
@@ -546,6 +576,713 @@
 				reg = <0x020e0000 0x38>;
 			};
 
+			iomuxc: iomuxc@020e0000 {
+				compatible = "fsl,imx6dl-iomuxc", "fsl,imx6q-iomuxc";
+				reg = <0x020e0000 0x4000>;
+
+				audmux {
+					pinctrl_audmux_1: audmux-1 {
+						fsl,pins = <
+							MX6QDL_PAD_SD2_DAT0__AUD4_RXD  0x80000000
+							MX6QDL_PAD_SD2_DAT3__AUD4_TXC  0x80000000
+							MX6QDL_PAD_SD2_DAT2__AUD4_TXD  0x80000000
+							MX6QDL_PAD_SD2_DAT1__AUD4_TXFS 0x80000000
+						>;
+					};
+
+					pinctrl_audmux_2: audmux-2 {
+						fsl,pins = <
+							MX6QDL_PAD_CSI0_DAT7__AUD3_RXD  0x80000000
+							MX6QDL_PAD_CSI0_DAT4__AUD3_TXC  0x80000000
+							MX6QDL_PAD_CSI0_DAT5__AUD3_TXD  0x80000000
+							MX6QDL_PAD_CSI0_DAT6__AUD3_TXFS 0x80000000
+						>;
+					};
+
+					pinctrl_audmux_3: audmux-3 {
+						fsl,pins = <
+							MX6QDL_PAD_DISP0_DAT16__AUD5_TXC  0x80000000
+							MX6QDL_PAD_DISP0_DAT18__AUD5_TXFS 0x80000000
+							MX6QDL_PAD_DISP0_DAT19__AUD5_RXD  0x80000000
+						>;
+					};
+				};
+
+				ecspi1 {
+					pinctrl_ecspi1_1: ecspi1grp-1 {
+						fsl,pins = <
+							MX6QDL_PAD_EIM_D17__ECSPI1_MISO 0x100b1
+							MX6QDL_PAD_EIM_D18__ECSPI1_MOSI 0x100b1
+							MX6QDL_PAD_EIM_D16__ECSPI1_SCLK 0x100b1
+						>;
+					};
+
+					pinctrl_ecspi1_2: ecspi1grp-2 {
+						fsl,pins = <
+							MX6QDL_PAD_KEY_COL1__ECSPI1_MISO 0x100b1
+							MX6QDL_PAD_KEY_ROW0__ECSPI1_MOSI 0x100b1
+							MX6QDL_PAD_KEY_COL0__ECSPI1_SCLK 0x100b1
+						>;
+					};
+				};
+
+				ecspi3 {
+					pinctrl_ecspi3_1: ecspi3grp-1 {
+						fsl,pins = <
+							MX6QDL_PAD_DISP0_DAT2__ECSPI3_MISO 0x100b1
+							MX6QDL_PAD_DISP0_DAT1__ECSPI3_MOSI 0x100b1
+							MX6QDL_PAD_DISP0_DAT0__ECSPI3_SCLK 0x100b1
+						>;
+					};
+				};
+
+				enet {
+					pinctrl_enet_1: enetgrp-1 {
+						fsl,pins = <
+							MX6QDL_PAD_ENET_MDIO__ENET_MDIO       0x1b0b0
+							MX6QDL_PAD_ENET_MDC__ENET_MDC         0x1b0b0
+							MX6QDL_PAD_RGMII_TXC__RGMII_TXC       0x1b0b0
+							MX6QDL_PAD_RGMII_TD0__RGMII_TD0       0x1b0b0
+							MX6QDL_PAD_RGMII_TD1__RGMII_TD1       0x1b0b0
+							MX6QDL_PAD_RGMII_TD2__RGMII_TD2       0x1b0b0
+							MX6QDL_PAD_RGMII_TD3__RGMII_TD3       0x1b0b0
+							MX6QDL_PAD_RGMII_TX_CTL__RGMII_TX_CTL 0x1b0b0
+							MX6QDL_PAD_ENET_REF_CLK__ENET_TX_CLK  0x1b0b0
+							MX6QDL_PAD_RGMII_RXC__RGMII_RXC       0x1b0b0
+							MX6QDL_PAD_RGMII_RD0__RGMII_RD0       0x1b0b0
+							MX6QDL_PAD_RGMII_RD1__RGMII_RD1       0x1b0b0
+							MX6QDL_PAD_RGMII_RD2__RGMII_RD2       0x1b0b0
+							MX6QDL_PAD_RGMII_RD3__RGMII_RD3       0x1b0b0
+							MX6QDL_PAD_RGMII_RX_CTL__RGMII_RX_CTL 0x1b0b0
+							MX6QDL_PAD_GPIO_16__ENET_REF_CLK      0x4001b0a8
+						>;
+					};
+
+					pinctrl_enet_2: enetgrp-2 {
+						fsl,pins = <
+							MX6QDL_PAD_KEY_COL1__ENET_MDIO        0x1b0b0
+							MX6QDL_PAD_KEY_COL2__ENET_MDC         0x1b0b0
+							MX6QDL_PAD_RGMII_TXC__RGMII_TXC       0x1b0b0
+							MX6QDL_PAD_RGMII_TD0__RGMII_TD0       0x1b0b0
+							MX6QDL_PAD_RGMII_TD1__RGMII_TD1       0x1b0b0
+							MX6QDL_PAD_RGMII_TD2__RGMII_TD2       0x1b0b0
+							MX6QDL_PAD_RGMII_TD3__RGMII_TD3       0x1b0b0
+							MX6QDL_PAD_RGMII_TX_CTL__RGMII_TX_CTL 0x1b0b0
+							MX6QDL_PAD_ENET_REF_CLK__ENET_TX_CLK  0x1b0b0
+							MX6QDL_PAD_RGMII_RXC__RGMII_RXC       0x1b0b0
+							MX6QDL_PAD_RGMII_RD0__RGMII_RD0       0x1b0b0
+							MX6QDL_PAD_RGMII_RD1__RGMII_RD1       0x1b0b0
+							MX6QDL_PAD_RGMII_RD2__RGMII_RD2       0x1b0b0
+							MX6QDL_PAD_RGMII_RD3__RGMII_RD3       0x1b0b0
+							MX6QDL_PAD_RGMII_RX_CTL__RGMII_RX_CTL 0x1b0b0
+						>;
+					};
+
+					pinctrl_enet_3: enetgrp-3 {
+						fsl,pins = <
+							MX6QDL_PAD_ENET_MDIO__ENET_MDIO       0x1b0b0
+							MX6QDL_PAD_ENET_MDC__ENET_MDC         0x1b0b0
+							MX6QDL_PAD_RGMII_TXC__RGMII_TXC       0x1b0b0
+							MX6QDL_PAD_RGMII_TD0__RGMII_TD0       0x1b0b0
+							MX6QDL_PAD_RGMII_TD1__RGMII_TD1       0x1b0b0
+							MX6QDL_PAD_RGMII_TD2__RGMII_TD2       0x1b0b0
+							MX6QDL_PAD_RGMII_TD3__RGMII_TD3       0x1b0b0
+							MX6QDL_PAD_RGMII_TX_CTL__RGMII_TX_CTL 0x1b0b0
+							MX6QDL_PAD_ENET_REF_CLK__ENET_TX_CLK  0x1b0b0
+							MX6QDL_PAD_RGMII_RXC__RGMII_RXC       0x1b0b0
+							MX6QDL_PAD_RGMII_RD0__RGMII_RD0       0x1b0b0
+							MX6QDL_PAD_RGMII_RD1__RGMII_RD1       0x1b0b0
+							MX6QDL_PAD_RGMII_RD2__RGMII_RD2       0x1b0b0
+							MX6QDL_PAD_RGMII_RD3__RGMII_RD3       0x1b0b0
+							MX6QDL_PAD_RGMII_RX_CTL__RGMII_RX_CTL 0x1b0b0
+							MX6QDL_PAD_ENET_TX_EN__ENET_TX_EN     0x1b0b0
+						>;
+					};
+				};
+
+				esai {
+					pinctrl_esai_1: esaigrp-1 {
+						fsl,pins = <
+							MX6QDL_PAD_ENET_RXD0__ESAI_TX_HF_CLK 0x1b030
+							MX6QDL_PAD_ENET_CRS_DV__ESAI_TX_CLK  0x1b030
+							MX6QDL_PAD_ENET_RXD1__ESAI_TX_FS     0x1b030
+							MX6QDL_PAD_ENET_TX_EN__ESAI_TX3_RX2  0x1b030
+							MX6QDL_PAD_ENET_TXD1__ESAI_TX2_RX3   0x1b030
+							MX6QDL_PAD_ENET_TXD0__ESAI_TX4_RX1   0x1b030
+							MX6QDL_PAD_ENET_MDC__ESAI_TX5_RX0    0x1b030
+							MX6QDL_PAD_NANDF_CS2__ESAI_TX0       0x1b030
+							MX6QDL_PAD_NANDF_CS3__ESAI_TX1       0x1b030
+						>;
+					};
+
+					pinctrl_esai_2: esaigrp-2 {
+						fsl,pins = <
+							MX6QDL_PAD_ENET_CRS_DV__ESAI_TX_CLK 0x1b030
+							MX6QDL_PAD_ENET_RXD1__ESAI_TX_FS    0x1b030
+							MX6QDL_PAD_ENET_TX_EN__ESAI_TX3_RX2 0x1b030
+							MX6QDL_PAD_GPIO_5__ESAI_TX2_RX3     0x1b030
+							MX6QDL_PAD_ENET_TXD0__ESAI_TX4_RX1  0x1b030
+							MX6QDL_PAD_ENET_MDC__ESAI_TX5_RX0   0x1b030
+							MX6QDL_PAD_GPIO_17__ESAI_TX0        0x1b030
+							MX6QDL_PAD_NANDF_CS3__ESAI_TX1      0x1b030
+							MX6QDL_PAD_ENET_MDIO__ESAI_RX_CLK   0x1b030
+							MX6QDL_PAD_GPIO_9__ESAI_RX_FS       0x1b030
+						>;
+					};
+				};
+
+				flexcan1 {
+					pinctrl_flexcan1_1: flexcan1grp-1 {
+						fsl,pins = <
+							MX6QDL_PAD_KEY_ROW2__FLEXCAN1_RX 0x80000000
+							MX6QDL_PAD_KEY_COL2__FLEXCAN1_TX 0x80000000
+						>;
+					};
+
+					pinctrl_flexcan1_2: flexcan1grp-2 {
+						fsl,pins = <
+							MX6QDL_PAD_GPIO_7__FLEXCAN1_TX   0x80000000
+							MX6QDL_PAD_KEY_ROW2__FLEXCAN1_RX 0x80000000
+						>;
+					};
+				};
+
+				flexcan2 {
+					pinctrl_flexcan2_1: flexcan2grp-1 {
+						fsl,pins = <
+							MX6QDL_PAD_KEY_COL4__FLEXCAN2_TX 0x80000000
+							MX6QDL_PAD_KEY_ROW4__FLEXCAN2_RX 0x80000000
+						>;
+					};
+				};
+
+				gpmi-nand {
+					pinctrl_gpmi_nand_1: gpmi-nand-1 {
+						fsl,pins = <
+							MX6QDL_PAD_NANDF_CLE__NAND_CLE     0xb0b1
+							MX6QDL_PAD_NANDF_ALE__NAND_ALE     0xb0b1
+							MX6QDL_PAD_NANDF_WP_B__NAND_WP_B   0xb0b1
+							MX6QDL_PAD_NANDF_RB0__NAND_READY_B 0xb000
+							MX6QDL_PAD_NANDF_CS0__NAND_CE0_B   0xb0b1
+							MX6QDL_PAD_NANDF_CS1__NAND_CE1_B   0xb0b1
+							MX6QDL_PAD_SD4_CMD__NAND_RE_B      0xb0b1
+							MX6QDL_PAD_SD4_CLK__NAND_WE_B      0xb0b1
+							MX6QDL_PAD_NANDF_D0__NAND_DATA00   0xb0b1
+							MX6QDL_PAD_NANDF_D1__NAND_DATA01   0xb0b1
+							MX6QDL_PAD_NANDF_D2__NAND_DATA02   0xb0b1
+							MX6QDL_PAD_NANDF_D3__NAND_DATA03   0xb0b1
+							MX6QDL_PAD_NANDF_D4__NAND_DATA04   0xb0b1
+							MX6QDL_PAD_NANDF_D5__NAND_DATA05   0xb0b1
+							MX6QDL_PAD_NANDF_D6__NAND_DATA06   0xb0b1
+							MX6QDL_PAD_NANDF_D7__NAND_DATA07   0xb0b1
+							MX6QDL_PAD_SD4_DAT0__NAND_DQS      0x00b1
+						>;
+					};
+				};
+
+				hdmi_hdcp {
+					pinctrl_hdmi_hdcp_1: hdmihdcpgrp-1 {
+						fsl,pins = <
+							MX6QDL_PAD_KEY_COL3__HDMI_TX_DDC_SCL 0x4001b8b1
+							MX6QDL_PAD_KEY_ROW3__HDMI_TX_DDC_SDA 0x4001b8b1
+						>;
+					};
+
+					pinctrl_hdmi_hdcp_2: hdmihdcpgrp-2 {
+						fsl,pins = <
+							MX6QDL_PAD_EIM_EB2__HDMI_TX_DDC_SCL 0x4001b8b1
+							MX6QDL_PAD_EIM_D16__HDMI_TX_DDC_SDA 0x4001b8b1
+						>;
+					};
+
+					pinctrl_hdmi_hdcp_3: hdmihdcpgrp-3 {
+						fsl,pins = <
+							MX6QDL_PAD_EIM_EB2__HDMI_TX_DDC_SCL  0x4001b8b1
+							MX6QDL_PAD_KEY_ROW3__HDMI_TX_DDC_SDA 0x4001b8b1
+						>;
+					};
+				};
+
+				hdmi_cec {
+					pinctrl_hdmi_cec_1: hdmicecgrp-1 {
+						fsl,pins = <
+							MX6QDL_PAD_EIM_A25__HDMI_TX_CEC_LINE 0x1f8b0
+						>;
+					};
+
+					pinctrl_hdmi_cec_2: hdmicecgrp-2 {
+						fsl,pins = <
+							MX6QDL_PAD_KEY_ROW2__HDMI_TX_CEC_LINE 0x1f8b0
+						>;
+					};
+				};
+
+				i2c1 {
+					pinctrl_i2c1_1: i2c1grp-1 {
+						fsl,pins = <
+							MX6QDL_PAD_EIM_D21__I2C1_SCL 0x4001b8b1
+							MX6QDL_PAD_EIM_D28__I2C1_SDA 0x4001b8b1
+						>;
+					};
+
+					pinctrl_i2c1_2: i2c1grp-2 {
+						fsl,pins = <
+							MX6QDL_PAD_CSI0_DAT8__I2C1_SDA 0x4001b8b1
+							MX6QDL_PAD_CSI0_DAT9__I2C1_SCL 0x4001b8b1
+						>;
+					};
+				};
+
+				i2c2 {
+					pinctrl_i2c2_1: i2c2grp-1 {
+						fsl,pins = <
+							MX6QDL_PAD_EIM_EB2__I2C2_SCL 0x4001b8b1
+							MX6QDL_PAD_EIM_D16__I2C2_SDA 0x4001b8b1
+						>;
+					};
+
+					pinctrl_i2c2_2: i2c2grp-2 {
+						fsl,pins = <
+							MX6QDL_PAD_KEY_COL3__I2C2_SCL 0x4001b8b1
+							MX6QDL_PAD_KEY_ROW3__I2C2_SDA 0x4001b8b1
+						>;
+					};
+
+					pinctrl_i2c2_3: i2c2grp-3 {
+						fsl,pins = <
+							MX6QDL_PAD_EIM_EB2__I2C2_SCL  0x4001b8b1
+							MX6QDL_PAD_KEY_ROW3__I2C2_SDA 0x4001b8b1
+						>;
+					};
+				};
+
+				i2c3 {
+					pinctrl_i2c3_1: i2c3grp-1 {
+						fsl,pins = <
+							MX6QDL_PAD_EIM_D17__I2C3_SCL 0x4001b8b1
+							MX6QDL_PAD_EIM_D18__I2C3_SDA 0x4001b8b1
+						>;
+					};
+
+					pinctrl_i2c3_2: i2c3grp-2 {
+						fsl,pins = <
+							MX6QDL_PAD_GPIO_3__I2C3_SCL 0x4001b8b1
+							MX6QDL_PAD_GPIO_6__I2C3_SDA 0x4001b8b1
+						>;
+					};
+
+					pinctrl_i2c3_3: i2c3grp-3 {
+						fsl,pins = <
+							MX6QDL_PAD_GPIO_5__I2C3_SCL  0x4001b8b1
+							MX6QDL_PAD_GPIO_16__I2C3_SDA 0x4001b8b1
+						>;
+					};
+
+					pinctrl_i2c3_4: i2c3grp-4 {
+						fsl,pins = <
+							MX6QDL_PAD_GPIO_3__I2C3_SCL  0x4001b8b1
+							MX6QDL_PAD_EIM_D18__I2C3_SDA 0x4001b8b1
+						>;
+					};
+				};
+
+				ipu1 {
+					pinctrl_ipu1_1: ipu1grp-1 {
+						fsl,pins = <
+							MX6QDL_PAD_DI0_DISP_CLK__IPU1_DI0_DISP_CLK 0x10
+							MX6QDL_PAD_DI0_PIN15__IPU1_DI0_PIN15       0x10
+							MX6QDL_PAD_DI0_PIN2__IPU1_DI0_PIN02        0x10
+							MX6QDL_PAD_DI0_PIN3__IPU1_DI0_PIN03        0x10
+							MX6QDL_PAD_DI0_PIN4__IPU1_DI0_PIN04        0x80000000
+							MX6QDL_PAD_DISP0_DAT0__IPU1_DISP0_DATA00   0x10
+							MX6QDL_PAD_DISP0_DAT1__IPU1_DISP0_DATA01   0x10
+							MX6QDL_PAD_DISP0_DAT2__IPU1_DISP0_DATA02   0x10
+							MX6QDL_PAD_DISP0_DAT3__IPU1_DISP0_DATA03   0x10
+							MX6QDL_PAD_DISP0_DAT4__IPU1_DISP0_DATA04   0x10
+							MX6QDL_PAD_DISP0_DAT5__IPU1_DISP0_DATA05   0x10
+							MX6QDL_PAD_DISP0_DAT6__IPU1_DISP0_DATA06   0x10
+							MX6QDL_PAD_DISP0_DAT7__IPU1_DISP0_DATA07   0x10
+							MX6QDL_PAD_DISP0_DAT8__IPU1_DISP0_DATA08   0x10
+							MX6QDL_PAD_DISP0_DAT9__IPU1_DISP0_DATA09   0x10
+							MX6QDL_PAD_DISP0_DAT10__IPU1_DISP0_DATA10  0x10
+							MX6QDL_PAD_DISP0_DAT11__IPU1_DISP0_DATA11  0x10
+							MX6QDL_PAD_DISP0_DAT12__IPU1_DISP0_DATA12  0x10
+							MX6QDL_PAD_DISP0_DAT13__IPU1_DISP0_DATA13  0x10
+							MX6QDL_PAD_DISP0_DAT14__IPU1_DISP0_DATA14  0x10
+							MX6QDL_PAD_DISP0_DAT15__IPU1_DISP0_DATA15  0x10
+							MX6QDL_PAD_DISP0_DAT16__IPU1_DISP0_DATA16  0x10
+							MX6QDL_PAD_DISP0_DAT17__IPU1_DISP0_DATA17  0x10
+							MX6QDL_PAD_DISP0_DAT18__IPU1_DISP0_DATA18  0x10
+							MX6QDL_PAD_DISP0_DAT19__IPU1_DISP0_DATA19  0x10
+							MX6QDL_PAD_DISP0_DAT20__IPU1_DISP0_DATA20  0x10
+							MX6QDL_PAD_DISP0_DAT21__IPU1_DISP0_DATA21  0x10
+							MX6QDL_PAD_DISP0_DAT22__IPU1_DISP0_DATA22  0x10
+							MX6QDL_PAD_DISP0_DAT23__IPU1_DISP0_DATA23  0x10
+						>;
+					};
+
+					pinctrl_ipu1_2: ipu1grp-2 { /* parallel camera */
+						fsl,pins = <
+							MX6QDL_PAD_CSI0_DAT12__IPU1_CSI0_DATA12    0x80000000
+							MX6QDL_PAD_CSI0_DAT13__IPU1_CSI0_DATA13    0x80000000
+							MX6QDL_PAD_CSI0_DAT14__IPU1_CSI0_DATA14    0x80000000
+							MX6QDL_PAD_CSI0_DAT15__IPU1_CSI0_DATA15    0x80000000
+							MX6QDL_PAD_CSI0_DAT16__IPU1_CSI0_DATA16    0x80000000
+							MX6QDL_PAD_CSI0_DAT17__IPU1_CSI0_DATA17    0x80000000
+							MX6QDL_PAD_CSI0_DAT18__IPU1_CSI0_DATA18    0x80000000
+							MX6QDL_PAD_CSI0_DAT19__IPU1_CSI0_DATA19    0x80000000
+							MX6QDL_PAD_CSI0_DATA_EN__IPU1_CSI0_DATA_EN 0x80000000
+							MX6QDL_PAD_CSI0_PIXCLK__IPU1_CSI0_PIXCLK   0x80000000
+							MX6QDL_PAD_CSI0_MCLK__IPU1_CSI0_HSYNC      0x80000000
+							MX6QDL_PAD_CSI0_VSYNC__IPU1_CSI0_VSYNC     0x80000000
+						>;
+					};
+
+					pinctrl_ipu1_3: ipu1grp-3 { /* parallel port 16-bit */
+						fsl,pins = <
+							MX6QDL_PAD_CSI0_DAT4__IPU1_CSI0_DATA04   0x80000000
+							MX6QDL_PAD_CSI0_DAT5__IPU1_CSI0_DATA05   0x80000000
+							MX6QDL_PAD_CSI0_DAT6__IPU1_CSI0_DATA06   0x80000000
+							MX6QDL_PAD_CSI0_DAT7__IPU1_CSI0_DATA07   0x80000000
+							MX6QDL_PAD_CSI0_DAT8__IPU1_CSI0_DATA08   0x80000000
+							MX6QDL_PAD_CSI0_DAT9__IPU1_CSI0_DATA09   0x80000000
+							MX6QDL_PAD_CSI0_DAT10__IPU1_CSI0_DATA10  0x80000000
+							MX6QDL_PAD_CSI0_DAT11__IPU1_CSI0_DATA11  0x80000000
+							MX6QDL_PAD_CSI0_DAT12__IPU1_CSI0_DATA12  0x80000000
+							MX6QDL_PAD_CSI0_DAT13__IPU1_CSI0_DATA13  0x80000000
+							MX6QDL_PAD_CSI0_DAT14__IPU1_CSI0_DATA14  0x80000000
+							MX6QDL_PAD_CSI0_DAT15__IPU1_CSI0_DATA15  0x80000000
+							MX6QDL_PAD_CSI0_DAT16__IPU1_CSI0_DATA16  0x80000000
+							MX6QDL_PAD_CSI0_DAT17__IPU1_CSI0_DATA17  0x80000000
+							MX6QDL_PAD_CSI0_DAT18__IPU1_CSI0_DATA18  0x80000000
+							MX6QDL_PAD_CSI0_DAT19__IPU1_CSI0_DATA19  0x80000000
+							MX6QDL_PAD_CSI0_PIXCLK__IPU1_CSI0_PIXCLK 0x80000000
+							MX6QDL_PAD_CSI0_MCLK__IPU1_CSI0_HSYNC    0x80000000
+							MX6QDL_PAD_CSI0_VSYNC__IPU1_CSI0_VSYNC   0x80000000
+						>;
+					};
+				};
+
+				mlb {
+					pinctrl_mlb_1: mlbgrp-1 {
+						fsl,pins = <
+							MX6QDL_PAD_GPIO_3__MLB_CLK  0x71
+							MX6QDL_PAD_GPIO_6__MLB_SIG  0x71
+							MX6QDL_PAD_GPIO_2__MLB_DATA 0x71
+						>;
+					};
+
+					pinctrl_mlb_2: mlbgrp-2 {
+						fsl,pins = <
+							MX6QDL_PAD_ENET_TXD1__MLB_CLK 0x71
+							MX6QDL_PAD_GPIO_6__MLB_SIG    0x71
+							MX6QDL_PAD_GPIO_2__MLB_DATA   0x71
+						>;
+					};
+				};
+
+				pwm0 {
+					pinctrl_pwm0_1: pwm0grp-1 {
+						fsl,pins = <
+							MX6QDL_PAD_SD1_DAT3__PWM1_OUT 0x1b0b1
+						>;
+					};
+				};
+
+				pwm3 {
+					pinctrl_pwm3_1: pwm3grp-1 {
+						fsl,pins = <
+							MX6QDL_PAD_SD4_DAT1__PWM3_OUT 0x1b0b1
+						>;
+					};
+				};
+
+				spdif {
+					pinctrl_spdif_1: spdifgrp-1 {
+						fsl,pins = <
+							MX6QDL_PAD_KEY_COL3__SPDIF_IN 0x1b0b0
+						>;
+					};
+
+					pinctrl_spdif_2: spdifgrp-2 {
+						fsl,pins = <
+							MX6QDL_PAD_GPIO_16__SPDIF_IN  0x1b0b0
+							MX6QDL_PAD_GPIO_17__SPDIF_OUT 0x1b0b0
+						>;
+					};
+				};
+
+				uart1 {
+					pinctrl_uart1_1: uart1grp-1 {
+						fsl,pins = <
+							MX6QDL_PAD_CSI0_DAT10__UART1_TX_DATA 0x1b0b1
+							MX6QDL_PAD_CSI0_DAT11__UART1_RX_DATA 0x1b0b1
+						>;
+					};
+				};
+
+				uart2 {
+					pinctrl_uart2_1: uart2grp-1 {
+						fsl,pins = <
+							MX6QDL_PAD_EIM_D26__UART2_TX_DATA 0x1b0b1
+							MX6QDL_PAD_EIM_D27__UART2_RX_DATA 0x1b0b1
+						>;
+					};
+
+					pinctrl_uart2_2: uart2grp-2 { /* DTE mode */
+						fsl,pins = <
+							MX6QDL_PAD_EIM_D26__UART2_RX_DATA   0x1b0b1
+							MX6QDL_PAD_EIM_D27__UART2_TX_DATA   0x1b0b1
+							MX6QDL_PAD_EIM_D28__UART2_DTE_CTS_B 0x1b0b1
+							MX6QDL_PAD_EIM_D29__UART2_DTE_RTS_B 0x1b0b1
+						>;
+					};
+				};
+
+				uart3 {
+					pinctrl_uart3_1: uart3grp-1 {
+						fsl,pins = <
+							MX6QDL_PAD_SD4_CLK__UART3_RX_DATA 0x1b0b1
+							MX6QDL_PAD_SD4_CMD__UART3_TX_DATA 0x1b0b1
+							MX6QDL_PAD_EIM_D30__UART3_CTS_B   0x1b0b1
+							MX6QDL_PAD_EIM_EB3__UART3_RTS_B   0x1b0b1
+						>;
+					};
+
+					pinctrl_uart3_2: uart3grp-2 {
+						fsl,pins = <
+							MX6QDL_PAD_EIM_D24__UART3_TX_DATA 0x1b0b1
+							MX6QDL_PAD_EIM_D25__UART3_RX_DATA 0x1b0b1
+							MX6QDL_PAD_EIM_D23__UART3_CTS_B	  0x1b0b1
+							MX6QDL_PAD_EIM_EB3__UART3_RTS_B	  0x1b0b1
+						>;
+					};
+				};
+
+				uart4 {
+					pinctrl_uart4_1: uart4grp-1 {
+						fsl,pins = <
+							MX6QDL_PAD_KEY_COL0__UART4_TX_DATA 0x1b0b1
+							MX6QDL_PAD_KEY_ROW0__UART4_RX_DATA 0x1b0b1
+						>;
+					};
+				};
+
+				usbotg {
+					pinctrl_usbotg_1: usbotggrp-1 {
+						fsl,pins = <
+							MX6QDL_PAD_GPIO_1__USB_OTG_ID 0x17059
+						>;
+					};
+
+					pinctrl_usbotg_2: usbotggrp-2 {
+						fsl,pins = <
+							MX6QDL_PAD_ENET_RX_ER__USB_OTG_ID 0x17059
+						>;
+					};
+				};
+
+				usbh2 {
+					pinctrl_usbh2_1: usbh2grp-1 {
+						fsl,pins = <
+							MX6QDL_PAD_RGMII_TXC__USB_H2_DATA      0x40013030
+							MX6QDL_PAD_RGMII_TX_CTL__USB_H2_STROBE 0x40013030
+						>;
+					};
+
+					pinctrl_usbh2_2: usbh2grp-2 {
+						fsl,pins = <
+							MX6QDL_PAD_RGMII_TX_CTL__USB_H2_STROBE 0x40017030
+						>;
+					};
+				};
+
+				usbh3 {
+					pinctrl_usbh3_1: usbh3grp-1 {
+						fsl,pins = <
+							MX6QDL_PAD_RGMII_RX_CTL__USB_H3_DATA 0x40013030
+							MX6QDL_PAD_RGMII_RXC__USB_H3_STROBE  0x40013030
+						>;
+					};
+
+					pinctrl_usbh3_2: usbh3grp-2 {
+						fsl,pins = <
+							MX6QDL_PAD_RGMII_RXC__USB_H3_STROBE 0x40017030
+						>;
+					};
+				};
+
+				usdhc1 {
+					pinctrl_usdhc1_1: usdhc1grp-1 {
+						fsl,pins = <
+							MX6QDL_PAD_SD1_CMD__SD1_CMD    0x17059
+							MX6QDL_PAD_SD1_CLK__SD1_CLK    0x10059
+							MX6QDL_PAD_SD1_DAT0__SD1_DATA0 0x17059
+							MX6QDL_PAD_SD1_DAT1__SD1_DATA1 0x17059
+							MX6QDL_PAD_SD1_DAT2__SD1_DATA2 0x17059
+							MX6QDL_PAD_SD1_DAT3__SD1_DATA3 0x17059
+							MX6QDL_PAD_NANDF_D0__SD1_DATA4 0x17059
+							MX6QDL_PAD_NANDF_D1__SD1_DATA5 0x17059
+							MX6QDL_PAD_NANDF_D2__SD1_DATA6 0x17059
+							MX6QDL_PAD_NANDF_D3__SD1_DATA7 0x17059
+						>;
+					};
+
+					pinctrl_usdhc1_2: usdhc1grp-2 {
+						fsl,pins = <
+							MX6QDL_PAD_SD1_CMD__SD1_CMD    0x17059
+							MX6QDL_PAD_SD1_CLK__SD1_CLK    0x10059
+							MX6QDL_PAD_SD1_DAT0__SD1_DATA0 0x17059
+							MX6QDL_PAD_SD1_DAT1__SD1_DATA1 0x17059
+							MX6QDL_PAD_SD1_DAT2__SD1_DATA2 0x17059
+							MX6QDL_PAD_SD1_DAT3__SD1_DATA3 0x17059
+						>;
+					};
+				};
+
+				usdhc2 {
+					pinctrl_usdhc2_1: usdhc2grp-1 {
+						fsl,pins = <
+							MX6QDL_PAD_SD2_CMD__SD2_CMD    0x17059
+							MX6QDL_PAD_SD2_CLK__SD2_CLK    0x10059
+							MX6QDL_PAD_SD2_DAT0__SD2_DATA0 0x17059
+							MX6QDL_PAD_SD2_DAT1__SD2_DATA1 0x17059
+							MX6QDL_PAD_SD2_DAT2__SD2_DATA2 0x17059
+							MX6QDL_PAD_SD2_DAT3__SD2_DATA3 0x17059
+							MX6QDL_PAD_NANDF_D4__SD2_DATA4 0x17059
+							MX6QDL_PAD_NANDF_D5__SD2_DATA5 0x17059
+							MX6QDL_PAD_NANDF_D6__SD2_DATA6 0x17059
+							MX6QDL_PAD_NANDF_D7__SD2_DATA7 0x17059
+						>;
+					};
+
+					pinctrl_usdhc2_2: usdhc2grp-2 {
+						fsl,pins = <
+							MX6QDL_PAD_SD2_CMD__SD2_CMD    0x17059
+							MX6QDL_PAD_SD2_CLK__SD2_CLK    0x10059
+							MX6QDL_PAD_SD2_DAT0__SD2_DATA0 0x17059
+							MX6QDL_PAD_SD2_DAT1__SD2_DATA1 0x17059
+							MX6QDL_PAD_SD2_DAT2__SD2_DATA2 0x17059
+							MX6QDL_PAD_SD2_DAT3__SD2_DATA3 0x17059
+						>;
+					};
+				};
+
+				usdhc3 {
+					pinctrl_usdhc3_1: usdhc3grp-1 {
+						fsl,pins = <
+							MX6QDL_PAD_SD3_CMD__SD3_CMD    0x17059
+							MX6QDL_PAD_SD3_CLK__SD3_CLK    0x10059
+							MX6QDL_PAD_SD3_DAT0__SD3_DATA0 0x17059
+							MX6QDL_PAD_SD3_DAT1__SD3_DATA1 0x17059
+							MX6QDL_PAD_SD3_DAT2__SD3_DATA2 0x17059
+							MX6QDL_PAD_SD3_DAT3__SD3_DATA3 0x17059
+							MX6QDL_PAD_SD3_DAT4__SD3_DATA4 0x17059
+							MX6QDL_PAD_SD3_DAT5__SD3_DATA5 0x17059
+							MX6QDL_PAD_SD3_DAT6__SD3_DATA6 0x17059
+							MX6QDL_PAD_SD3_DAT7__SD3_DATA7 0x17059
+						>;
+					};
+
+					pinctrl_usdhc3_2: usdhc3grp-2 {
+						fsl,pins = <
+							MX6QDL_PAD_SD3_CMD__SD3_CMD    0x17059
+							MX6QDL_PAD_SD3_CLK__SD3_CLK    0x10059
+							MX6QDL_PAD_SD3_DAT0__SD3_DATA0 0x17059
+							MX6QDL_PAD_SD3_DAT1__SD3_DATA1 0x17059
+							MX6QDL_PAD_SD3_DAT2__SD3_DATA2 0x17059
+							MX6QDL_PAD_SD3_DAT3__SD3_DATA3 0x17059
+						>;
+					};
+				};
+
+				usdhc4 {
+					pinctrl_usdhc4_1: usdhc4grp-1 {
+						fsl,pins = <
+							MX6QDL_PAD_SD4_CMD__SD4_CMD    0x17059
+							MX6QDL_PAD_SD4_CLK__SD4_CLK    0x10059
+							MX6QDL_PAD_SD4_DAT0__SD4_DATA0 0x17059
+							MX6QDL_PAD_SD4_DAT1__SD4_DATA1 0x17059
+							MX6QDL_PAD_SD4_DAT2__SD4_DATA2 0x17059
+							MX6QDL_PAD_SD4_DAT3__SD4_DATA3 0x17059
+							MX6QDL_PAD_SD4_DAT4__SD4_DATA4 0x17059
+							MX6QDL_PAD_SD4_DAT5__SD4_DATA5 0x17059
+							MX6QDL_PAD_SD4_DAT6__SD4_DATA6 0x17059
+							MX6QDL_PAD_SD4_DAT7__SD4_DATA7 0x17059
+						>;
+					};
+
+					pinctrl_usdhc4_2: usdhc4grp-2 {
+						fsl,pins = <
+							MX6QDL_PAD_SD4_CMD__SD4_CMD    0x17059
+							MX6QDL_PAD_SD4_CLK__SD4_CLK    0x10059
+							MX6QDL_PAD_SD4_DAT0__SD4_DATA0 0x17059
+							MX6QDL_PAD_SD4_DAT1__SD4_DATA1 0x17059
+							MX6QDL_PAD_SD4_DAT2__SD4_DATA2 0x17059
+							MX6QDL_PAD_SD4_DAT3__SD4_DATA3 0x17059
+						>;
+					};
+				};
+
+				weim {
+					pinctrl_weim_cs0_1: weim_cs0grp-1 {
+						fsl,pins = <
+							MX6QDL_PAD_EIM_CS0__EIM_CS0_B   0xb0b1
+						>;
+					};
+
+					pinctrl_weim_nor_1: weim_norgrp-1 {
+						fsl,pins = <
+							MX6QDL_PAD_EIM_OE__EIM_OE_B     0xb0b1
+							MX6QDL_PAD_EIM_RW__EIM_RW       0xb0b1
+							MX6QDL_PAD_EIM_WAIT__EIM_WAIT_B 0xb060
+							/* data */
+							MX6QDL_PAD_EIM_D16__EIM_DATA16 0x1b0b0
+							MX6QDL_PAD_EIM_D17__EIM_DATA17 0x1b0b0
+							MX6QDL_PAD_EIM_D18__EIM_DATA18 0x1b0b0
+							MX6QDL_PAD_EIM_D19__EIM_DATA19 0x1b0b0
+							MX6QDL_PAD_EIM_D20__EIM_DATA20 0x1b0b0
+							MX6QDL_PAD_EIM_D21__EIM_DATA21 0x1b0b0
+							MX6QDL_PAD_EIM_D22__EIM_DATA22 0x1b0b0
+							MX6QDL_PAD_EIM_D23__EIM_DATA23 0x1b0b0
+							MX6QDL_PAD_EIM_D24__EIM_DATA24 0x1b0b0
+							MX6QDL_PAD_EIM_D25__EIM_DATA25 0x1b0b0
+							MX6QDL_PAD_EIM_D26__EIM_DATA26 0x1b0b0
+							MX6QDL_PAD_EIM_D27__EIM_DATA27 0x1b0b0
+							MX6QDL_PAD_EIM_D28__EIM_DATA28 0x1b0b0
+							MX6QDL_PAD_EIM_D29__EIM_DATA29 0x1b0b0
+							MX6QDL_PAD_EIM_D30__EIM_DATA30 0x1b0b0
+							MX6QDL_PAD_EIM_D31__EIM_DATA31 0x1b0b0
+							/* address */
+							MX6QDL_PAD_EIM_A23__EIM_ADDR23 0xb0b1
+							MX6QDL_PAD_EIM_A22__EIM_ADDR22 0xb0b1
+							MX6QDL_PAD_EIM_A21__EIM_ADDR21 0xb0b1
+							MX6QDL_PAD_EIM_A20__EIM_ADDR20 0xb0b1
+							MX6QDL_PAD_EIM_A19__EIM_ADDR19 0xb0b1
+							MX6QDL_PAD_EIM_A18__EIM_ADDR18 0xb0b1
+							MX6QDL_PAD_EIM_A17__EIM_ADDR17 0xb0b1
+							MX6QDL_PAD_EIM_A16__EIM_ADDR16 0xb0b1
+							MX6QDL_PAD_EIM_DA15__EIM_AD15  0xb0b1
+							MX6QDL_PAD_EIM_DA14__EIM_AD14  0xb0b1
+							MX6QDL_PAD_EIM_DA13__EIM_AD13  0xb0b1
+							MX6QDL_PAD_EIM_DA12__EIM_AD12  0xb0b1
+							MX6QDL_PAD_EIM_DA11__EIM_AD11  0xb0b1
+							MX6QDL_PAD_EIM_DA10__EIM_AD10  0xb0b1
+							MX6QDL_PAD_EIM_DA9__EIM_AD09   0xb0b1
+							MX6QDL_PAD_EIM_DA8__EIM_AD08   0xb0b1
+							MX6QDL_PAD_EIM_DA7__EIM_AD07   0xb0b1
+							MX6QDL_PAD_EIM_DA6__EIM_AD06   0xb0b1
+							MX6QDL_PAD_EIM_DA5__EIM_AD05   0xb0b1
+							MX6QDL_PAD_EIM_DA4__EIM_AD04   0xb0b1
+							MX6QDL_PAD_EIM_DA3__EIM_AD03   0xb0b1
+							MX6QDL_PAD_EIM_DA2__EIM_AD02   0xb0b1
+							MX6QDL_PAD_EIM_DA1__EIM_AD01   0xb0b1
+							MX6QDL_PAD_EIM_DA0__EIM_AD00   0xb0b1
+						>;
+					};
+				};
+			};
+
 			ldb: ldb@020e0008 {
 				#address-cells = <1>;
 				#size-cells = <0>;
@@ -555,13 +1292,11 @@
 
 				lvds-channel@0 {
 					reg = <0>;
-					crtcs = <&ipu1 0>;
 					status = "disabled";
 				};
 
 				lvds-channel@1 {
 					reg = <1>;
-					crtcs = <&ipu1 1>;
 					status = "disabled";
 				};
 			};
@@ -582,6 +1317,7 @@
 				interrupts = <0 2 0x04>;
 				clocks = <&clks 155>, <&clks 155>;
 				clock-names = "ipg", "ahb";
+				#dma-cells = <3>;
 				fsl,sdma-ram-script-name = "imx/sdma/sdma-imx6q.bin";
 			};
 		};
@@ -751,8 +1487,8 @@
 				clocks = <&clks 196>;
 			};
 
-			ocotp@021bc000 {
-				compatible = "fsl,imx6q-ocotp";
+			ocotp: ocotp@021bc000 {
+				compatible = "fsl,imx6q-ocotp", "syscon";
 				reg = <0x021bc000 0x4000>;
 			};
 
@@ -791,6 +1527,8 @@
 				interrupts = <0 27 0x04>;
 				clocks = <&clks 160>, <&clks 161>;
 				clock-names = "ipg", "per";
+				dmas = <&sdma 27 4 0>, <&sdma 28 4 0>;
+				dma-names = "rx", "tx";
 				status = "disabled";
 			};
 
@@ -800,6 +1538,8 @@
 				interrupts = <0 28 0x04>;
 				clocks = <&clks 160>, <&clks 161>;
 				clock-names = "ipg", "per";
+				dmas = <&sdma 29 4 0>, <&sdma 30 4 0>;
+				dma-names = "rx", "tx";
 				status = "disabled";
 			};
 
@@ -809,6 +1549,8 @@
 				interrupts = <0 29 0x04>;
 				clocks = <&clks 160>, <&clks 161>;
 				clock-names = "ipg", "per";
+				dmas = <&sdma 31 4 0>, <&sdma 32 4 0>;
+				dma-names = "rx", "tx";
 				status = "disabled";
 			};
 
@@ -818,6 +1560,8 @@
 				interrupts = <0 30 0x04>;
 				clocks = <&clks 160>, <&clks 161>;
 				clock-names = "ipg", "per";
+				dmas = <&sdma 33 4 0>, <&sdma 34 4 0>;
+				dma-names = "rx", "tx";
 				status = "disabled";
 			};
 		};
diff --git a/arch/arm/boot/dts/imx6sl.dtsi b/arch/arm/boot/dts/imx6sl.dtsi
index c5e5da02d7e3..c46651e4d966 100644
--- a/arch/arm/boot/dts/imx6sl.dtsi
+++ b/arch/arm/boot/dts/imx6sl.dtsi
@@ -152,32 +152,41 @@
 				};
 
 				uart5: serial@02018000 {
-					compatible = "fsl,imx6sl-uart", "fsl,imx21-uart";
+					compatible = "fsl,imx6sl-uart",
+						   "fsl,imx6q-uart", "fsl,imx21-uart";
 					reg = <0x02018000 0x4000>;
 					interrupts = <0 30 0x04>;
 					clocks = <&clks IMX6SL_CLK_UART>,
 						 <&clks IMX6SL_CLK_UART_SERIAL>;
 					clock-names = "ipg", "per";
+					dmas = <&sdma 33 4 0>, <&sdma 34 4 0>;
+					dma-names = "rx", "tx";
 					status = "disabled";
 				};
 
 				uart1: serial@02020000 {
-					compatible = "fsl,imx6sl-uart", "fsl,imx21-uart";
+					compatible = "fsl,imx6sl-uart",
+						   "fsl,imx6q-uart", "fsl,imx21-uart";
 					reg = <0x02020000 0x4000>;
 					interrupts = <0 26 0x04>;
 					clocks = <&clks IMX6SL_CLK_UART>,
 						 <&clks IMX6SL_CLK_UART_SERIAL>;
 					clock-names = "ipg", "per";
+					dmas = <&sdma 25 4 0>, <&sdma 26 4 0>;
+					dma-names = "rx", "tx";
 					status = "disabled";
 				};
 
 				uart2: serial@02024000 {
-					compatible = "fsl,imx6sl-uart", "fsl,imx21-uart";
+					compatible = "fsl,imx6sl-uart",
+						   "fsl,imx6q-uart", "fsl,imx21-uart";
 					reg = <0x02024000 0x4000>;
 					interrupts = <0 27 0x04>;
 					clocks = <&clks IMX6SL_CLK_UART>,
 						 <&clks IMX6SL_CLK_UART_SERIAL>;
 					clock-names = "ipg", "per";
+					dmas = <&sdma 27 4 0>, <&sdma 28 4 0>;
+					dma-names = "rx", "tx";
 					status = "disabled";
 				};
 
@@ -186,6 +195,9 @@
 					reg = <0x02028000 0x4000>;
 					interrupts = <0 46 0x04>;
 					clocks = <&clks IMX6SL_CLK_SSI1>;
+					dmas = <&sdma 37 1 0>,
+					       <&sdma 38 1 0>;
+					dma-names = "rx", "tx";
 					fsl,fifo-depth = <15>;
 					status = "disabled";
 				};
@@ -195,6 +207,9 @@
 					reg = <0x0202c000 0x4000>;
 					interrupts = <0 47 0x04>;
 					clocks = <&clks IMX6SL_CLK_SSI2>;
+					dmas = <&sdma 41 1 0>,
+					       <&sdma 42 1 0>;
+					dma-names = "rx", "tx";
 					fsl,fifo-depth = <15>;
 					status = "disabled";
 				};
@@ -204,27 +219,36 @@
 					reg = <0x02030000 0x4000>;
 					interrupts = <0 48 0x04>;
 					clocks = <&clks IMX6SL_CLK_SSI3>;
+					dmas = <&sdma 45 1 0>,
+					       <&sdma 46 1 0>;
+					dma-names = "rx", "tx";
 					fsl,fifo-depth = <15>;
 					status = "disabled";
 				};
 
 				uart3: serial@02034000 {
-					compatible = "fsl,imx6sl-uart", "fsl,imx21-uart";
+					compatible = "fsl,imx6sl-uart",
+						   "fsl,imx6q-uart", "fsl,imx21-uart";
 					reg = <0x02034000 0x4000>;
 					interrupts = <0 28 0x04>;
 					clocks = <&clks IMX6SL_CLK_UART>,
 						 <&clks IMX6SL_CLK_UART_SERIAL>;
 					clock-names = "ipg", "per";
+					dmas = <&sdma 29 4 0>, <&sdma 30 4 0>;
+					dma-names = "rx", "tx";
 					status = "disabled";
 				};
 
 				uart4: serial@02038000 {
-					compatible = "fsl,imx6sl-uart", "fsl,imx21-uart";
+					compatible = "fsl,imx6sl-uart",
+						   "fsl,imx6q-uart", "fsl,imx21-uart";
 					reg = <0x02038000 0x4000>;
 					interrupts = <0 29 0x04>;
 					clocks = <&clks IMX6SL_CLK_UART>,
 						 <&clks IMX6SL_CLK_UART_SERIAL>;
 					clock-names = "ipg", "per";
+					dmas = <&sdma 31 4 0>, <&sdma 32 4 0>;
+					dma-names = "rx", "tx";
 					status = "disabled";
 				};
 			};
@@ -594,6 +618,7 @@
 				clocks = <&clks IMX6SL_CLK_SDMA>,
 					 <&clks IMX6SL_CLK_SDMA>;
 				clock-names = "ipg", "ahb";
+				#dma-cells = <3>;
 				fsl,sdma-ram-script-name = "imx/sdma/sdma-imx6sl.bin";
 			};
 
diff --git a/arch/arm/boot/dts/keystone.dts b/arch/arm/boot/dts/keystone.dts
index 1334b42c6b77..a68e34bbecb2 100644
--- a/arch/arm/boot/dts/keystone.dts
+++ b/arch/arm/boot/dts/keystone.dts
@@ -7,7 +7,9 @@
  */
 
 /dts-v1/;
-/include/ "skeleton.dtsi"
+#include <dt-bindings/interrupt-controller/arm-gic.h>
+
+#include "skeleton.dtsi"
 
 / {
 	model = "Texas Instruments Keystone 2 SoC";
@@ -67,18 +69,23 @@
 
 	timer {
 		compatible = "arm,armv7-timer";
-		interrupts = <1 13 0xf08>,
-			     <1 14 0xf08>,
-			     <1 11 0xf08>,
-			     <1 10 0x308>;
+		interrupts =
+			<GIC_PPI 13
+				(GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>,
+			<GIC_PPI 14
+				(GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>,
+			<GIC_PPI 11
+				(GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>,
+			<GIC_PPI 10
+				(GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>;
 	};
 
 	pmu {
 		compatible = "arm,cortex-a15-pmu";
-		interrupts = <0 20 0xf01>,
-			     <0 21 0xf01>,
-			     <0 22 0xf01>,
-			     <0 23 0xf01>;
+		interrupts = <GIC_SPI 20 IRQ_TYPE_EDGE_RISING>,
+			     <GIC_SPI 21 IRQ_TYPE_EDGE_RISING>,
+			     <GIC_SPI 22 IRQ_TYPE_EDGE_RISING>,
+			     <GIC_SPI 23 IRQ_TYPE_EDGE_RISING>;
 	};
 
 	soc {
@@ -100,7 +107,7 @@
 			reg-io-width = <4>;
 			reg = <0x02530c00 0x100>;
 			clock-frequency = <133120000>;
-			interrupts = <0 277 0xf01>;
+			interrupts = <GIC_SPI 277 IRQ_TYPE_EDGE_RISING>;
 		};
 
 		uart1:	serial@02531000 {
@@ -110,7 +117,7 @@
 			reg-io-width = <4>;
 			reg = <0x02531000 0x100>;
 			clock-frequency = <133120000>;
-			interrupts = <0 280 0xf01>;
+			interrupts = <GIC_SPI 280 IRQ_TYPE_EDGE_RISING>;
 		};
 
 	};
diff --git a/arch/arm/boot/dts/kirkwood-6281.dtsi b/arch/arm/boot/dts/kirkwood-6281.dtsi
index 1e5bef0bead7..650ef30e1856 100644
--- a/arch/arm/boot/dts/kirkwood-6281.dtsi
+++ b/arch/arm/boot/dts/kirkwood-6281.dtsi
@@ -1,4 +1,39 @@
 / {
+	mbus {
+		pcie-controller {
+			compatible = "marvell,kirkwood-pcie";
+			status = "disabled";
+			device_type = "pci";
+
+			#address-cells = <3>;
+			#size-cells = <2>;
+
+			bus-range = <0x00 0xff>;
+
+			ranges =
+			       <0x82000000 0 0x40000 MBUS_ID(0xf0, 0x01) 0x40000 0 0x00002000
+				0x82000000 0x1 0     MBUS_ID(0x04, 0xe8) 0       1 0 /* Port 0.0 MEM */
+				0x81000000 0x1 0     MBUS_ID(0x04, 0xe0) 0       1 0 /* Port 0.0 IO  */>;
+
+			pcie@1,0 {
+				device_type = "pci";
+				assigned-addresses = <0x82000800 0 0x00040000 0 0x2000>;
+				reg = <0x0800 0 0 0 0>;
+				#address-cells = <3>;
+				#size-cells = <2>;
+				#interrupt-cells = <1>;
+				ranges = <0x82000000 0 0 0x82000000 0x1 0 1 0
+					  0x81000000 0 0 0x81000000 0x1 0 1 0>;
+				interrupt-map-mask = <0 0 0 0>;
+				interrupt-map = <0 0 0 0 &intc 9>;
+				marvell,pcie-port = <0>;
+				marvell,pcie-lane = <0>;
+				clocks = <&gate_clk 2>;
+				status = "disabled";
+			};
+		};
+	};
+
 	ocp@f1000000 {
 		pinctrl: pinctrl@10000 {
 			compatible = "marvell,88f6281-pinctrl";
@@ -41,37 +76,6 @@
 			};
 		};
 
-		pcie-controller {
-			compatible = "marvell,kirkwood-pcie";
-			status = "disabled";
-			device_type = "pci";
-
-			#address-cells = <3>;
-			#size-cells = <2>;
-
-			bus-range = <0x00 0xff>;
-
-			ranges = <0x82000000 0 0x00040000 0x00040000 0 0x00002000   /* Port 0.0 registers */
-				  0x82000000 0 0xe0000000 0xe0000000 0 0x08000000   /* non-prefetchable memory */
-			          0x81000000 0 0          0xe8000000 0 0x00100000>; /* downstream I/O */
-
-			pcie@1,0 {
-				device_type = "pci";
-				assigned-addresses = <0x82000800 0 0x00040000 0 0x2000>;
-				reg = <0x0800 0 0 0 0>;
-				#address-cells = <3>;
-				#size-cells = <2>;
-				#interrupt-cells = <1>;
-				ranges;
-				interrupt-map-mask = <0 0 0 0>;
-				interrupt-map = <0 0 0 0 &intc 9>;
-				marvell,pcie-port = <0>;
-				marvell,pcie-lane = <0>;
-				clocks = <&gate_clk 2>;
-				status = "disabled";
-			};
-		};
-
 		rtc@10300 {
 			compatible = "marvell,kirkwood-rtc", "marvell,orion-rtc";
 			reg = <0x10300 0x20>;
diff --git a/arch/arm/boot/dts/kirkwood-6282.dtsi b/arch/arm/boot/dts/kirkwood-6282.dtsi
index a63a11137262..3933a331ddc2 100644
--- a/arch/arm/boot/dts/kirkwood-6282.dtsi
+++ b/arch/arm/boot/dts/kirkwood-6282.dtsi
@@ -1,4 +1,59 @@
 / {
+	mbus {
+		pcie-controller {
+			compatible = "marvell,kirkwood-pcie";
+			status = "disabled";
+			device_type = "pci";
+
+			#address-cells = <3>;
+			#size-cells = <2>;
+
+			bus-range = <0x00 0xff>;
+
+			ranges =
+			       <0x82000000 0 0x40000 MBUS_ID(0xf0, 0x01) 0x40000 0 0x00002000
+			        0x82000000 0 0x44000 MBUS_ID(0xf0, 0x01) 0x44000 0 0x00002000
+				0x82000000 0 0x80000 MBUS_ID(0xf0, 0x01) 0x80000 0 0x00002000
+				0x82000000 0x1 0     MBUS_ID(0x04, 0xe8) 0       1 0 /* Port 0.0 MEM */
+				0x81000000 0x1 0     MBUS_ID(0x04, 0xe0) 0       1 0 /* Port 0.0 IO  */
+				0x82000000 0x2 0     MBUS_ID(0x04, 0xd8) 0       1 0 /* Port 1.0 MEM */
+				0x81000000 0x2 0     MBUS_ID(0x04, 0xd0) 0       1 0 /* Port 1.0 IO  */>;
+
+			pcie@1,0 {
+				device_type = "pci";
+				assigned-addresses = <0x82000800 0 0x00040000 0 0x2000>;
+				reg = <0x0800 0 0 0 0>;
+				#address-cells = <3>;
+				#size-cells = <2>;
+				#interrupt-cells = <1>;
+				ranges = <0x82000000 0 0 0x82000000 0x1 0 1 0
+					  0x81000000 0 0 0x81000000 0x1 0 1 0>;
+				interrupt-map-mask = <0 0 0 0>;
+				interrupt-map = <0 0 0 0 &intc 9>;
+				marvell,pcie-port = <0>;
+				marvell,pcie-lane = <0>;
+				clocks = <&gate_clk 2>;
+				status = "disabled";
+			};
+
+			pcie@2,0 {
+				device_type = "pci";
+				assigned-addresses = <0x82001000 0 0x00044000 0 0x2000>;
+				reg = <0x1000 0 0 0 0>;
+				#address-cells = <3>;
+				#size-cells = <2>;
+				#interrupt-cells = <1>;
+				ranges = <0x82000000 0 0 0x82000000 0x2 0 1 0
+					  0x81000000 0 0 0x81000000 0x2 0 1 0>;
+				interrupt-map-mask = <0 0 0 0>;
+				interrupt-map = <0 0 0 0 &intc 10>;
+				marvell,pcie-port = <1>;
+				marvell,pcie-lane = <0>;
+				clocks = <&gate_clk 18>;
+				status = "disabled";
+			};
+		};
+	};
 	ocp@f1000000 {
 
 		pinctrl: pinctrl@10000 {
@@ -94,52 +149,5 @@
 			status = "disabled";
 		};
 
-		pcie-controller {
-			compatible = "marvell,kirkwood-pcie";
-			status = "disabled";
-			device_type = "pci";
-
-			#address-cells = <3>;
-			#size-cells = <2>;
-
-			bus-range = <0x00 0xff>;
-
-			ranges = <0x82000000 0 0x00040000 0x00040000 0 0x00002000   /* Port 0.0 registers */
-			          0x82000000 0 0x00044000 0x00044000 0 0x00002000   /* Port 1.0 registers */
-				  0x82000000 0 0xe0000000 0xe0000000 0 0x08000000   /* non-prefetchable memory */
-			          0x81000000 0 0          0xe8000000 0 0x00100000>; /* downstream I/O */
-
-			pcie@1,0 {
-				device_type = "pci";
-				assigned-addresses = <0x82000800 0 0x00040000 0 0x2000>;
-				reg = <0x0800 0 0 0 0>;
-				#address-cells = <3>;
-				#size-cells = <2>;
-				#interrupt-cells = <1>;
-				ranges;
-				interrupt-map-mask = <0 0 0 0>;
-				interrupt-map = <0 0 0 0 &intc 9>;
-				marvell,pcie-port = <0>;
-				marvell,pcie-lane = <0>;
-				clocks = <&gate_clk 2>;
-				status = "disabled";
-			};
-
-			pcie@2,0 {
-				device_type = "pci";
-				assigned-addresses = <0x82001000 0 0x00044000 0 0x2000>;
-				reg = <0x1000 0 0 0 0>;
-				#address-cells = <3>;
-				#size-cells = <2>;
-				#interrupt-cells = <1>;
-				ranges;
-				interrupt-map-mask = <0 0 0 0>;
-				interrupt-map = <0 0 0 0 &intc 10>;
-				marvell,pcie-port = <1>;
-				marvell,pcie-lane = <0>;
-				clocks = <&gate_clk 18>;
-				status = "disabled";
-			};
-		};
 	};
 };
diff --git a/arch/arm/boot/dts/kirkwood-cloudbox.dts b/arch/arm/boot/dts/kirkwood-cloudbox.dts
index 00c48d26de68..142b9cd3b454 100644
--- a/arch/arm/boot/dts/kirkwood-cloudbox.dts
+++ b/arch/arm/boot/dts/kirkwood-cloudbox.dts
@@ -1,7 +1,7 @@
 /dts-v1/;
 
-/include/ "kirkwood.dtsi"
-/include/ "kirkwood-6281.dtsi"
+#include "kirkwood.dtsi"
+#include "kirkwood-6281.dtsi"
 
 / {
 	model = "LaCie CloudBox";
@@ -89,3 +89,19 @@
 		gpios = <&gpio0 17 0>;
 	};
 };
+
+&mdio {
+	status = "okay";
+
+	ethphy0: ethernet-phy@0 {
+		device_type = "ethernet-phy";
+		reg = <0>;
+	};
+};
+
+&eth0 {
+	status = "okay";
+	ethernet0-port@0 {
+		phy-handle = <&ethphy0>;
+	};
+};
diff --git a/arch/arm/boot/dts/kirkwood-db-88f6281.dts b/arch/arm/boot/dts/kirkwood-db-88f6281.dts
index 9d777edd1f36..72c4b0a0366f 100644
--- a/arch/arm/boot/dts/kirkwood-db-88f6281.dts
+++ b/arch/arm/boot/dts/kirkwood-db-88f6281.dts
@@ -11,14 +11,15 @@
 
 /dts-v1/;
 
-/include/ "kirkwood-db.dtsi"
-/include/ "kirkwood-6281.dtsi"
+#include "kirkwood-db.dtsi"
+#include "kirkwood-6281.dtsi"
 
 / {
 	model = "Marvell DB-88F6281-BP Development Board";
 	compatible = "marvell,db-88f6281-bp", "marvell,kirkwood-88f6281", "marvell,kirkwood";
 
-	ocp@f1000000 {
+	mbus {
+		ranges = <MBUS_ID(0xf0, 0x01) 0 0xf1000000 0x100000>;
 		pcie-controller {
 			status = "okay";
 
diff --git a/arch/arm/boot/dts/kirkwood-db-88f6282.dts b/arch/arm/boot/dts/kirkwood-db-88f6282.dts
index f4c852886d23..36c411d34926 100644
--- a/arch/arm/boot/dts/kirkwood-db-88f6282.dts
+++ b/arch/arm/boot/dts/kirkwood-db-88f6282.dts
@@ -11,14 +11,15 @@
 
 /dts-v1/;
 
-/include/ "kirkwood-db.dtsi"
-/include/ "kirkwood-6282.dtsi"
+#include "kirkwood-db.dtsi"
+#include "kirkwood-6282.dtsi"
 
 / {
 	model = "Marvell DB-88F6282-BP Development Board";
 	compatible = "marvell,db-88f6282-bp", "marvell,kirkwood-88f6282", "marvell,kirkwood";
 
-	ocp@f1000000 {
+	mbus {
+		ranges = <MBUS_ID(0xf0, 0x01) 0 0xf1000000 0x100000>;
 		pcie-controller {
 			status = "okay";
 
diff --git a/arch/arm/boot/dts/kirkwood-db.dtsi b/arch/arm/boot/dts/kirkwood-db.dtsi
index c87cfb816120..c0e2a5879174 100644
--- a/arch/arm/boot/dts/kirkwood-db.dtsi
+++ b/arch/arm/boot/dts/kirkwood-db.dtsi
@@ -12,7 +12,7 @@
  * and 6282 variants of the Marvell Kirkwood Development Board.
  */
 
-/include/ "kirkwood.dtsi"
+#include "kirkwood.dtsi"
 
 / {
 	memory {
@@ -77,13 +77,21 @@
 			cd-gpios = <&gpio1 6 0>;
 			status = "okay";
 		};
+	};
+};
 
-		pcie-controller {
-			status = "okay";
+&mdio {
+	status = "okay";
 
-			pcie@1,0 {
-				status = "okay";
-			};
-		};
+	ethphy0: ethernet-phy@8 {
+		device_type = "ethernet-phy";
+		reg = <8>;
+	};
+};
+
+&eth0 {
+	status = "okay";
+	ethernet0-port@0 {
+		phy-handle = <&ethphy0>;
 	};
 };
diff --git a/arch/arm/boot/dts/kirkwood-dns320.dts b/arch/arm/boot/dts/kirkwood-dns320.dts
index 14d4ceea3057..e112ca62d978 100644
--- a/arch/arm/boot/dts/kirkwood-dns320.dts
+++ b/arch/arm/boot/dts/kirkwood-dns320.dts
@@ -1,6 +1,6 @@
 /dts-v1/;
 
-/include/ "kirkwood-dnskw.dtsi"
+#include "kirkwood-dnskw.dtsi"
 
 / {
 	model = "D-Link DNS-320 NAS (Rev A1)";
diff --git a/arch/arm/boot/dts/kirkwood-dns325.dts b/arch/arm/boot/dts/kirkwood-dns325.dts
index 63872570e6ce..5119fb8a8eb6 100644
--- a/arch/arm/boot/dts/kirkwood-dns325.dts
+++ b/arch/arm/boot/dts/kirkwood-dns325.dts
@@ -1,6 +1,6 @@
 /dts-v1/;
 
-/include/ "kirkwood-dnskw.dtsi"
+#include "kirkwood-dnskw.dtsi"
 
 / {
 	model = "D-Link DNS-325 NAS (Rev A1)";
diff --git a/arch/arm/boot/dts/kirkwood-dnskw.dtsi b/arch/arm/boot/dts/kirkwood-dnskw.dtsi
index 0afe1d07c803..d544f77a4ca4 100644
--- a/arch/arm/boot/dts/kirkwood-dnskw.dtsi
+++ b/arch/arm/boot/dts/kirkwood-dnskw.dtsi
@@ -1,5 +1,5 @@
-/include/ "kirkwood.dtsi"
-/include/ "kirkwood-6281.dtsi"
+#include "kirkwood.dtsi"
+#include "kirkwood-6281.dtsi"
 
 / {
 	model = "D-Link DNS NASes (kirkwood-based)";
@@ -219,3 +219,19 @@
 		};
 	};
 };
+
+&mdio {
+	status = "okay";
+
+	ethphy0: ethernet-phy@8 {
+		device_type = "ethernet-phy";
+		reg = <8>;
+	};
+};
+
+&eth0 {
+	status = "okay";
+	ethernet0-port@0 {
+		phy-handle = <&ethphy0>;
+	};
+};
diff --git a/arch/arm/boot/dts/kirkwood-dockstar.dts b/arch/arm/boot/dts/kirkwood-dockstar.dts
index 7714742bb8d8..59a2117c35a7 100644
--- a/arch/arm/boot/dts/kirkwood-dockstar.dts
+++ b/arch/arm/boot/dts/kirkwood-dockstar.dts
@@ -1,7 +1,7 @@
 /dts-v1/;
 
-/include/ "kirkwood.dtsi"
-/include/ "kirkwood-6281.dtsi"
+#include "kirkwood.dtsi"
+#include "kirkwood-6281.dtsi"
 
 / {
 	model = "Seagate FreeAgent Dockstar";
@@ -90,3 +90,20 @@
 		};
 	};
 };
+
+&mdio {
+	status = "okay";
+
+	ethphy0: ethernet-phy@0 {
+		device_type = "ethernet-phy";
+		compatible = "marvell,88e1116";
+		reg = <0>;
+	};
+};
+
+&eth0 {
+	status = "okay";
+	ethernet0-port@0 {
+		phy-handle = <&ethphy0>;
+	};
+};
diff --git a/arch/arm/boot/dts/kirkwood-dreamplug.dts b/arch/arm/boot/dts/kirkwood-dreamplug.dts
index 36c7ba38d500..6f62af99c9cb 100644
--- a/arch/arm/boot/dts/kirkwood-dreamplug.dts
+++ b/arch/arm/boot/dts/kirkwood-dreamplug.dts
@@ -1,7 +1,7 @@
 /dts-v1/;
 
-/include/ "kirkwood.dtsi"
-/include/ "kirkwood-6281.dtsi"
+#include "kirkwood.dtsi"
+#include "kirkwood-6281.dtsi"
 
 / {
 	model = "Globalscale Technologies Dreamplug";
@@ -99,3 +99,31 @@
 		};
 	};
 };
+
+&mdio {
+	status = "okay";
+
+	ethphy0: ethernet-phy@0 {
+		device_type = "ethernet-phy";
+		reg = <0>;
+	};
+
+	ethphy1: ethernet-phy@1 {
+		device_type = "ethernet-phy";
+		reg = <1>;
+	};
+};
+
+&eth0 {
+	status = "okay";
+	ethernet0-port@0 {
+		phy-handle = <&ethphy0>;
+	};
+};
+
+&eth1 {
+	status = "okay";
+	ethernet1-port@0 {
+		phy-handle = <&ethphy1>;
+	};
+};
diff --git a/arch/arm/boot/dts/kirkwood-goflexnet.dts b/arch/arm/boot/dts/kirkwood-goflexnet.dts
index 31caa6405065..6f7c7d7ecf2a 100644
--- a/arch/arm/boot/dts/kirkwood-goflexnet.dts
+++ b/arch/arm/boot/dts/kirkwood-goflexnet.dts
@@ -1,7 +1,7 @@
 /dts-v1/;
 
-/include/ "kirkwood.dtsi"
-/include/ "kirkwood-6281.dtsi"
+#include "kirkwood.dtsi"
+#include "kirkwood-6281.dtsi"
 
 / {
 	model = "Seagate GoFlex Net";
@@ -170,3 +170,19 @@
 		};
 	};
 };
+
+&mdio {
+	status = "okay";
+
+	ethphy0: ethernet-phy@0 {
+		device_type = "ethernet-phy";
+		reg = <0>;
+	};
+};
+
+&eth0 {
+	status = "okay";
+	ethernet0-port@0 {
+		phy-handle = <&ethphy0>;
+	};
+};
diff --git a/arch/arm/boot/dts/kirkwood-guruplug-server-plus.dts b/arch/arm/boot/dts/kirkwood-guruplug-server-plus.dts
index 1e642f39b154..6548b9dc6855 100644
--- a/arch/arm/boot/dts/kirkwood-guruplug-server-plus.dts
+++ b/arch/arm/boot/dts/kirkwood-guruplug-server-plus.dts
@@ -1,7 +1,7 @@
 /dts-v1/;
 
-/include/ "kirkwood.dtsi"
-/include/ "kirkwood-6281.dtsi"
+#include "kirkwood.dtsi"
+#include "kirkwood-6281.dtsi"
 
 / {
 	model = "Globalscale Technologies Guruplug Server Plus";
@@ -96,3 +96,33 @@
 		};
 	};
 };
+
+&mdio {
+	status = "okay";
+
+	ethphy0: ethernet-phy@0 {
+		device_type = "ethernet-phy";
+		compatible = "marvell,88e1121";
+		reg = <0>;
+	};
+
+	ethphy1: ethernet-phy@1 {
+		device_type = "ethernet-phy";
+		compatible = "marvell,88e1121";
+		reg = <1>;
+	};
+};
+
+&eth0 {
+	status = "okay";
+	ethernet0-port@0 {
+		phy-handle = <&ethphy0>;
+	};
+};
+
+&eth1 {
+	status = "okay";
+	ethernet1-port@0 {
+		phy-handle = <&ethphy1>;
+	};
+};
diff --git a/arch/arm/boot/dts/kirkwood-ib62x0.dts b/arch/arm/boot/dts/kirkwood-ib62x0.dts
index 20c4b081f420..cb711a3bd983 100644
--- a/arch/arm/boot/dts/kirkwood-ib62x0.dts
+++ b/arch/arm/boot/dts/kirkwood-ib62x0.dts
@@ -1,7 +1,7 @@
 /dts-v1/;
 
-/include/ "kirkwood.dtsi"
-/include/ "kirkwood-6281.dtsi"
+#include "kirkwood.dtsi"
+#include "kirkwood-6281.dtsi"
 
 / {
 	model = "RaidSonic ICY BOX IB-NAS62x0 (Rev B)";
@@ -122,3 +122,19 @@
 
 
 };
+
+&mdio {
+	status = "okay";
+
+	ethphy0: ethernet-phy@8 {
+		device_type = "ethernet-phy";
+		reg = <8>;
+	};
+};
+
+&eth0 {
+	status = "okay";
+	ethernet0-port@0 {
+		phy-handle = <&ethphy0>;
+	};
+};
diff --git a/arch/arm/boot/dts/kirkwood-iconnect.dts b/arch/arm/boot/dts/kirkwood-iconnect.dts
index 441204e8abc6..0323f017eeed 100644
--- a/arch/arm/boot/dts/kirkwood-iconnect.dts
+++ b/arch/arm/boot/dts/kirkwood-iconnect.dts
@@ -1,7 +1,7 @@
 /dts-v1/;
 
-/include/ "kirkwood.dtsi"
-/include/ "kirkwood-6281.dtsi"
+#include "kirkwood.dtsi"
+#include "kirkwood-6281.dtsi"
 
 / {
 	model = "Iomega Iconnect";
@@ -18,6 +18,17 @@
 		linux,initrd-end   = <0x4800000>;
 	};
 
+	mbus {
+		ranges = <MBUS_ID(0xf0, 0x01) 0 0xf1000000 0x100000>;
+		pcie-controller {
+			status = "okay";
+
+			pcie@1,0 {
+				status = "okay";
+			};
+		};
+	};
+
 	ocp@f1000000 {
 		pinctrl: pinctrl@10000 {
 			pmx_button_reset: pmx-button-reset {
@@ -101,14 +112,6 @@
 				reg = <0x980000 0x1f400000>;
 			};
 		};
-
-		pcie-controller {
-			status = "okay";
-
-			pcie@1,0 {
-				status = "okay";
-			};
-		};
 	};
 
 	gpio-leds {
@@ -176,3 +179,19 @@
 		};
 	};
 };
+
+&mdio {
+	status = "okay";
+
+	ethphy0: ethernet-phy@11 {
+		device_type = "ethernet-phy";
+		reg = <11>;
+	};
+};
+
+&eth0 {
+	status = "okay";
+	ethernet0-port@0 {
+		phy-handle = <&ethphy0>;
+	};
+};
diff --git a/arch/arm/boot/dts/kirkwood-iomega_ix2_200.dts b/arch/arm/boot/dts/kirkwood-iomega_ix2_200.dts
index 00a7bfe5e83b..df8447442b37 100644
--- a/arch/arm/boot/dts/kirkwood-iomega_ix2_200.dts
+++ b/arch/arm/boot/dts/kirkwood-iomega_ix2_200.dts
@@ -1,7 +1,7 @@
 /dts-v1/;
 
-/include/ "kirkwood.dtsi"
-/include/ "kirkwood-6281.dtsi"
+#include "kirkwood.dtsi"
+#include "kirkwood-6281.dtsi"
 
 / {
 	model = "Iomega StorCenter ix2-200";
@@ -194,3 +194,27 @@
 		};
 	};
 };
+
+&mdio {
+	status = "okay";
+
+	ethphy1: ethernet-phy@11 {
+		device_type = "ethernet-phy";
+		reg = <11>;
+	};
+};
+
+&eth0 {
+	status = "okay";
+	ethernet0-port@0 {
+		speed = <1000>;
+		duplex = <1>;
+	};
+};
+
+&eth1 {
+	status = "okay";
+	ethernet1-port@0 {
+		phy-handle = <&ethphy1>;
+	};
+};
diff --git a/arch/arm/boot/dts/kirkwood-is2.dts b/arch/arm/boot/dts/kirkwood-is2.dts
index c3f036b86cca..da674bbd49a8 100644
--- a/arch/arm/boot/dts/kirkwood-is2.dts
+++ b/arch/arm/boot/dts/kirkwood-is2.dts
@@ -1,6 +1,6 @@
 /dts-v1/;
 
-/include/ "kirkwood-ns2-common.dtsi"
+#include "kirkwood-ns2-common.dtsi"
 
 / {
 	model = "LaCie Internet Space v2";
@@ -30,3 +30,5 @@
 		};
 	};
 };
+
+&ethphy0 { reg = <8>; };
diff --git a/arch/arm/boot/dts/kirkwood-km_kirkwood.dts b/arch/arm/boot/dts/kirkwood-km_kirkwood.dts
index 5d9f5ea78700..6899408482d2 100644
--- a/arch/arm/boot/dts/kirkwood-km_kirkwood.dts
+++ b/arch/arm/boot/dts/kirkwood-km_kirkwood.dts
@@ -1,7 +1,7 @@
 /dts-v1/;
 
-/include/ "kirkwood.dtsi"
-/include/ "kirkwood-98dx4122.dtsi"
+#include "kirkwood.dtsi"
+#include "kirkwood-98dx4122.dtsi"
 
 / {
 	model = "Keymile Kirkwood Reference Design";
@@ -50,3 +50,19 @@
 		i2c-gpio,delay-us = <2>;	/* ~100 kHz */
 	};
 };
+
+&mdio {
+	status = "okay";
+
+	ethphy0: ethernet-phy@0 {
+		device_type = "ethernet-phy";
+		reg = <0>;
+	};
+};
+
+&eth0 {
+	status = "okay";
+	ethernet0-port@0 {
+		phy-handle = <&ethphy0>;
+	};
+};
diff --git a/arch/arm/boot/dts/kirkwood-lschlv2.dts b/arch/arm/boot/dts/kirkwood-lschlv2.dts
index 9f55d95f35f5..e2fa368aef25 100644
--- a/arch/arm/boot/dts/kirkwood-lschlv2.dts
+++ b/arch/arm/boot/dts/kirkwood-lschlv2.dts
@@ -1,6 +1,6 @@
 /dts-v1/;
 
-/include/ "kirkwood-lsxl.dtsi"
+#include "kirkwood-lsxl.dtsi"
 
 / {
 	model = "Buffalo Linkstation LS-CHLv2";
diff --git a/arch/arm/boot/dts/kirkwood-lsxhl.dts b/arch/arm/boot/dts/kirkwood-lsxhl.dts
index 5c84c118ed8d..8d89cdf8d6bf 100644
--- a/arch/arm/boot/dts/kirkwood-lsxhl.dts
+++ b/arch/arm/boot/dts/kirkwood-lsxhl.dts
@@ -1,6 +1,6 @@
 /dts-v1/;
 
-/include/ "kirkwood-lsxl.dtsi"
+#include "kirkwood-lsxl.dtsi"
 
 / {
 	model = "Buffalo Linkstation LS-XHL";
diff --git a/arch/arm/boot/dts/kirkwood-lsxl.dtsi b/arch/arm/boot/dts/kirkwood-lsxl.dtsi
index 31b17f5b9d28..4e8f9e42c592 100644
--- a/arch/arm/boot/dts/kirkwood-lsxl.dtsi
+++ b/arch/arm/boot/dts/kirkwood-lsxl.dtsi
@@ -1,5 +1,5 @@
-/include/ "kirkwood.dtsi"
-/include/ "kirkwood-6281.dtsi"
+#include "kirkwood.dtsi"
+#include "kirkwood-6281.dtsi"
 
 / {
 	chosen {
@@ -207,3 +207,31 @@
 		};
 	};
 };
+
+&mdio {
+	status = "okay";
+
+	ethphy0: ethernet-phy@0 {
+		device_type = "ethernet-phy";
+		reg = <0>;
+	};
+
+	ethphy1: ethernet-phy@8 {
+		device_type = "ethernet-phy";
+		reg = <8>;
+	};
+};
+
+&eth0 {
+	status = "okay";
+	ethernet0-port@0 {
+		phy-handle = <&ethphy0>;
+	};
+};
+
+&eth1 {
+	status = "okay";
+	ethernet1-port@0 {
+		phy-handle = <&ethphy1>;
+	};
+};
diff --git a/arch/arm/boot/dts/kirkwood-mplcec4.dts b/arch/arm/boot/dts/kirkwood-mplcec4.dts
index 6179333fd71f..ce2b94b513db 100644
--- a/arch/arm/boot/dts/kirkwood-mplcec4.dts
+++ b/arch/arm/boot/dts/kirkwood-mplcec4.dts
@@ -1,7 +1,7 @@
 /dts-v1/;
 
-/include/ "kirkwood.dtsi"
-/include/ "kirkwood-6281.dtsi"
+#include "kirkwood.dtsi"
+#include "kirkwood-6281.dtsi"
 
 / {
 	model = "MPL CEC4";
@@ -16,6 +16,17 @@
                 bootargs = "console=ttyS0,115200n8 earlyprintk";
         };
 
+	mbus {
+		ranges = <MBUS_ID(0xf0, 0x01) 0 0xf1000000 0x100000>;
+		pcie-controller {
+			status = "okay";
+
+			pcie@1,0 {
+				status = "okay";
+			};
+		};
+	};
+
 	ocp@f1000000 {
 		pinctrl: pinctrl@10000 {
 			pmx_led_health: pmx-led-health {
@@ -134,14 +145,6 @@
 			cd-gpios = <&gpio1 15 1>;
 			/* No WP GPIO */
 		};
-
-		pcie-controller {
-			status = "okay";
-
-			pcie@1,0 {
-				status = "okay";
-			};
-		};
 	};
 
 	gpio-leds {
@@ -191,3 +194,30 @@
 	};
 };
 
+&mdio {
+	status = "okay";
+
+	ethphy0: ethernet-phy@1 {
+		device_type = "ethernet-phy";
+		reg = <1>;
+	};
+
+	ethphy1: ethernet-phy@2 {
+		device_type = "ethernet-phy";
+		reg = <2>;
+	};
+};
+
+&eth0 {
+	status = "okay";
+	ethernet0-port@0 {
+		phy-handle = <&ethphy0>;
+	};
+};
+
+&eth1 {
+	status = "okay";
+	ethernet1-port@0 {
+		phy-handle = <&ethphy1>;
+	};
+};
diff --git a/arch/arm/boot/dts/kirkwood-mv88f6281gtw-ge.dts b/arch/arm/boot/dts/kirkwood-mv88f6281gtw-ge.dts
new file mode 100644
index 000000000000..6317e1d088b3
--- /dev/null
+++ b/arch/arm/boot/dts/kirkwood-mv88f6281gtw-ge.dts
@@ -0,0 +1,125 @@
+/*
+ * Marvell 88F6281 GTW GE Board
+ *
+ * Lennert Buytenhek <buytenh@marvell.com>
+ * Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2.  This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ *
+ * This file contains the definitions that are common between the 6281
+ * and 6282 variants of the Marvell Kirkwood Development Board.
+ */
+
+/dts-v1/;
+
+#include "kirkwood.dtsi"
+#include "kirkwood-6281.dtsi"
+
+/ {
+	model = "Marvell 88F6281 GTW GE Board";
+	compatible = "marvell,mv88f6281gtw-ge", "marvell,kirkwood-88f6281", "marvell,kirkwood";
+
+	memory {
+		device_type = "memory";
+		reg = <0x00000000 0x20000000>; /* 512 MB */
+	};
+
+	chosen {
+		bootargs = "console=ttyS0,115200n8 earlyprintk";
+	};
+
+	ocp@f1000000 {
+		pinctrl@10000 {
+			pmx_usb_led: pmx-usb-led {
+				marvell,pins = "mpp12";
+				marvell,function = "gpo";
+			};
+
+			pmx_leds: pmx-leds {
+				marvell,pins = "mpp20", "mpp21";
+				marvell,function = "gpio";
+			};
+
+			pmx_keys: pmx-keys {
+				marvell,pins = "mpp46", "mpp47";
+				marvell,function = "gpio";
+			};
+		};
+
+		spi@10600 {
+			pinctrl-0 = <&pmx_spi>;
+			pinctrl-names = "default";
+			status = "okay";
+
+			flash@0 {
+				#address-cells = <1>;
+				#size-cells = <1>;
+				compatible = "mx25l12805d";
+				reg = <0>;
+				spi-max-frequency = <50000000>;
+				mode = <0>;
+			};
+		};
+
+		serial@12000 {
+			pinctrl-0 = <&pmx_uart0>;
+			pinctrl-names = "default";
+			clock-frequency = <200000000>;
+			status = "ok";
+		};
+
+		ehci@50000 {
+			status = "okay";
+		};
+
+		pcie-controller {
+			status = "okay";
+
+			pcie@1,0 {
+				status = "okay";
+			};
+		};
+	};
+
+	gpio-leds {
+		compatible = "gpio-leds";
+		pinctrl-0 = <&pmx_leds &pmx_usb_led>;
+		pinctrl-names = "default";
+
+		green-status {
+			label = "gtw:green:Status";
+			gpios = <&gpio0 20 0>;
+		};
+
+		red-status {
+			label = "gtw:red:Status";
+			gpios = <&gpio0 21 0>;
+		};
+
+		green-usb {
+			label = "gtw:green:USB";
+			gpios = <&gpio0 12 0>;
+		};
+	};
+
+	gpio_keys {
+		compatible = "gpio-keys";
+		#address-cells = <1>;
+		#size-cells = <0>;
+		pinctrl-0 = <&pmx_keys>;
+		pinctrl-names = "default";
+
+		button@1 {
+			label = "SWR Button";
+			linux,code = <0x198>; /* KEY_RESTART */
+			gpios = <&gpio1 15 1>;
+		};
+		button@2 {
+			label = "WPS Button";
+			linux,code = <0x211>; /* KEY_WPS_BUTTON */
+			gpios = <&gpio1 14 1>;
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/kirkwood-netgear_readynas_duo_v2.dts b/arch/arm/boot/dts/kirkwood-netgear_readynas_duo_v2.dts
index ad6ade7d9191..874857ea9cb8 100644
--- a/arch/arm/boot/dts/kirkwood-netgear_readynas_duo_v2.dts
+++ b/arch/arm/boot/dts/kirkwood-netgear_readynas_duo_v2.dts
@@ -1,7 +1,7 @@
 /dts-v1/;
 
-/include/ "kirkwood.dtsi"
-/include/ "kirkwood-6282.dtsi"
+#include "kirkwood.dtsi"
+#include "kirkwood-6282.dtsi"
 
 / {
 	model = "NETGEAR ReadyNAS Duo v2";
@@ -16,6 +16,17 @@
 		bootargs = "console=ttyS0,115200n8 earlyprintk";
 	};
 
+	mbus {
+		ranges = <MBUS_ID(0xf0, 0x01) 0 0xf1000000 0x100000>;
+		pcie-controller {
+			status = "okay";
+
+			pcie@1,0 {
+				status = "okay";
+			};
+		};
+	};
+
 	ocp@f1000000 {
 		pinctrl: pinctrl@10000 {
 			pmx_button_power: pmx-button-power {
@@ -52,6 +63,17 @@
 			};
 		};
 
+		clocks {
+		       #address-cells = <1>;
+		       #size-cells = <0>;
+
+		       g762_clk: fixedclk {
+				 compatible = "fixed-clock";
+				 #clock-cells = <0>;
+				 clock-frequency = <8192>;
+		       };
+		};
+
 		i2c@11000 {
 			status = "okay";
 
@@ -59,6 +81,15 @@
 				compatible = "ricoh,rs5c372a";
 				reg = <0x32>;
 			};
+
+			g762: g762@3e {
+				compatible = "gmt,g762";
+				reg = <0x3e>;
+				clocks = <&g762_clk>; /* input clock */
+				fan_gear_mode = <0>;
+				fan_startv = <1>;
+				pwm_polarity = <0>;
+			};
 		};
 
 		serial@12000 {
@@ -101,14 +132,6 @@
 			status = "okay";
 			nr-ports = <2>;
 		};
-
-		pcie-controller {
-			status = "okay";
-
-			pcie@1,0 {
-				status = "okay";
-			};
-		};
 	};
 
 	gpio-leds {
@@ -184,3 +207,19 @@
                 };
         };
 };
+
+&mdio {
+	status = "okay";
+
+	ethphy0: ethernet-phy@0 {
+		device_type = "ethernet-phy";
+		reg = <0>;
+	};
+};
+
+&eth0 {
+	status = "okay";
+	ethernet0-port@0 {
+		phy-handle = <&ethphy0>;
+	};
+};
diff --git a/arch/arm/boot/dts/kirkwood-ns2-common.dtsi b/arch/arm/boot/dts/kirkwood-ns2-common.dtsi
index 2afac0405816..2fcb82e20828 100644
--- a/arch/arm/boot/dts/kirkwood-ns2-common.dtsi
+++ b/arch/arm/boot/dts/kirkwood-ns2-common.dtsi
@@ -1,5 +1,5 @@
-/include/ "kirkwood.dtsi"
-/include/ "kirkwood-6281.dtsi"
+#include "kirkwood.dtsi"
+#include "kirkwood-6281.dtsi"
 
 / {
 	chosen {
@@ -84,3 +84,19 @@
 	};
 
 };
+
+&mdio {
+	status = "okay";
+
+	ethphy0: ethernet-phy {
+		device_type = "ethernet-phy";
+                /* overwrite reg property in board file */
+	};
+};
+
+&eth0 {
+	status = "okay";
+	ethernet0-port@0 {
+		phy-handle = <&ethphy0>;
+	};
+};
diff --git a/arch/arm/boot/dts/kirkwood-ns2.dts b/arch/arm/boot/dts/kirkwood-ns2.dts
index b50e93d7796c..53368d1022cc 100644
--- a/arch/arm/boot/dts/kirkwood-ns2.dts
+++ b/arch/arm/boot/dts/kirkwood-ns2.dts
@@ -1,6 +1,6 @@
 /dts-v1/;
 
-/include/ "kirkwood-ns2-common.dtsi"
+#include "kirkwood-ns2-common.dtsi"
 
 / {
 	model = "LaCie Network Space v2";
@@ -30,3 +30,5 @@
 		};
 	};
 };
+
+&ethphy0 { reg = <8>; };
diff --git a/arch/arm/boot/dts/kirkwood-ns2lite.dts b/arch/arm/boot/dts/kirkwood-ns2lite.dts
index af8259fe8955..279607093cdb 100644
--- a/arch/arm/boot/dts/kirkwood-ns2lite.dts
+++ b/arch/arm/boot/dts/kirkwood-ns2lite.dts
@@ -1,6 +1,6 @@
 /dts-v1/;
 
-/include/ "kirkwood-ns2-common.dtsi"
+#include "kirkwood-ns2-common.dtsi"
 
 / {
 	model = "LaCie Network Space Lite v2";
@@ -30,3 +30,5 @@
 		};
 	};
 };
+
+&ethphy0 { reg = <0>; };
diff --git a/arch/arm/boot/dts/kirkwood-ns2max.dts b/arch/arm/boot/dts/kirkwood-ns2max.dts
index 85f24d227e17..defdc77fb550 100644
--- a/arch/arm/boot/dts/kirkwood-ns2max.dts
+++ b/arch/arm/boot/dts/kirkwood-ns2max.dts
@@ -1,6 +1,6 @@
 /dts-v1/;
 
-/include/ "kirkwood-ns2-common.dtsi"
+#include "kirkwood-ns2-common.dtsi"
 
 / {
 	model = "LaCie Network Space Max v2";
@@ -49,3 +49,5 @@
 		};
 	};
 };
+
+&ethphy0 { reg = <8>; };
diff --git a/arch/arm/boot/dts/kirkwood-ns2mini.dts b/arch/arm/boot/dts/kirkwood-ns2mini.dts
index 329e530bffe7..adbafdd90991 100644
--- a/arch/arm/boot/dts/kirkwood-ns2mini.dts
+++ b/arch/arm/boot/dts/kirkwood-ns2mini.dts
@@ -1,6 +1,6 @@
 /dts-v1/;
 
-/include/ "kirkwood-ns2-common.dtsi"
+#include "kirkwood-ns2-common.dtsi"
 
 / {
 	/* This machine is embedded in the first LaCie CloudBox product. */
@@ -50,3 +50,5 @@
 		};
 	};
 };
+
+&ethphy0 { reg = <0>; };
diff --git a/arch/arm/boot/dts/kirkwood-nsa310-common.dtsi b/arch/arm/boot/dts/kirkwood-nsa310-common.dtsi
new file mode 100644
index 000000000000..06267a91de38
--- /dev/null
+++ b/arch/arm/boot/dts/kirkwood-nsa310-common.dtsi
@@ -0,0 +1,107 @@
+#include "kirkwood.dtsi"
+#include "kirkwood-6281.dtsi"
+
+/ {
+	model = "ZyXEL NSA310";
+
+	ocp@f1000000 {
+		pinctrl: pinctrl@10000 {
+
+			pmx_usb_power_off: pmx-usb-power-off {
+				marvell,pins = "mpp21";
+				marvell,function = "gpio";
+			};
+			pmx_pwr_off: pmx-pwr-off {
+				marvell,pins = "mpp48";
+				marvell,function = "gpio";
+			};
+
+		};
+
+		serial@12000 {
+			status = "ok";
+		};
+
+		sata@80000 {
+			status = "okay";
+			nr-ports = <2>;
+		};
+
+		nand@3000000 {
+			status = "okay";
+			chip-delay = <35>;
+
+			partition@0 {
+				label = "uboot";
+				reg = <0x0000000 0x0100000>;
+				read-only;
+			};
+			partition@100000 {
+				label = "uboot_env";
+				reg = <0x0100000 0x0080000>;
+			};
+			partition@180000 {
+				label = "key_store";
+				reg = <0x0180000 0x0080000>;
+			};
+			partition@200000 {
+				label = "info";
+				reg = <0x0200000 0x0080000>;
+			};
+			partition@280000 {
+				label = "etc";
+				reg = <0x0280000 0x0a00000>;
+			};
+			partition@c80000 {
+				label = "kernel_1";
+				reg = <0x0c80000 0x0a00000>;
+			};
+			partition@1680000 {
+				label = "rootfs1";
+				reg = <0x1680000 0x2fc0000>;
+			};
+			partition@4640000 {
+				label = "kernel_2";
+				reg = <0x4640000 0x0a00000>;
+			};
+			partition@5040000 {
+				label = "rootfs2";
+				reg = <0x5040000 0x2fc0000>;
+			};
+		};
+
+		pcie-controller {
+			status = "okay";
+
+			pcie@1,0 {
+				status = "okay";
+			};
+		};
+	};
+
+	gpio_poweroff {
+		compatible = "gpio-poweroff";
+		pinctrl-0 = <&pmx_pwr_off>;
+		pinctrl-names = "default";
+		gpios = <&gpio1 16 0>;
+	};
+
+	regulators {
+		compatible = "simple-bus";
+		#address-cells = <1>;
+		#size-cells = <0>;
+		pinctrl-0 = <&pmx_usb_power_off>;
+		pinctrl-names = "default";
+
+		usb0_power_off: regulator@1 {
+			compatible = "regulator-fixed";
+			reg = <1>;
+			regulator-name = "USB Power Off";
+			regulator-min-microvolt = <5000000>;
+			regulator-max-microvolt = <5000000>;
+			regulator-always-on;
+			regulator-boot-on;
+			gpio = <&gpio0 21 0>;
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/kirkwood-nsa310.dts b/arch/arm/boot/dts/kirkwood-nsa310.dts
index 69003598f5fa..7aeae0c2c1f4 100644
--- a/arch/arm/boot/dts/kirkwood-nsa310.dts
+++ b/arch/arm/boot/dts/kirkwood-nsa310.dts
@@ -1,10 +1,8 @@
 /dts-v1/;
 
-/include/ "kirkwood.dtsi"
-/include/ "kirkwood-6281.dtsi"
+#include "kirkwood-nsa310-common.dtsi"
 
 / {
-	model = "ZyXEL NSA310";
 	compatible = "zyxel,nsa310", "marvell,kirkwood-88f6281", "marvell,kirkwood";
 
 	memory {
@@ -16,6 +14,17 @@
 		bootargs = "console=ttyS0,115200";
 	};
 
+	mbus {
+		ranges = <MBUS_ID(0xf0, 0x01) 0 0xf1000000 0x100000>;
+		pcie-controller {
+			status = "okay";
+
+			pcie@1,0 {
+				status = "okay";
+			};
+		};
+	};
+
 	ocp@f1000000 {
 		pinctrl: pinctrl@10000 {
 			pinctrl-0 = <&pmx_unknown>;
@@ -41,11 +50,6 @@
 				marvell,function = "gpio";
 			};
 
-			pmx_usb_power_off: pmx-usb-power-off {
-				marvell,pins = "mpp21";
-				marvell,function = "gpio";
-			};
-
 			pmx_led_sys_green: pmx-led-sys-green {
 				marvell,pins = "mpp28";
 				marvell,function = "gpio";
@@ -95,20 +99,6 @@
 				marvell,pins = "mpp46";
 				marvell,function = "gpio";
 			};
-
-			pmx_pwr_off: pmx-pwr-off {
-				marvell,pins = "mpp48";
-				marvell,function = "gpio";
-			};
-		};
-
-		serial@12000 {
-			status = "ok";
-		};
-
-		sata@80000 {
-			status = "okay";
-			nr-ports = <2>;
 		};
 
 		i2c@11000 {
@@ -119,57 +109,6 @@
 				reg = <0x2e>;
 			};
 		};
-
-		nand@3000000 {
-			status = "okay";
-			chip-delay = <35>;
-
-			partition@0 {
-				label = "uboot";
-				reg = <0x0000000 0x0100000>;
-				read-only;
-			};
-			partition@100000 {
-				label = "uboot_env";
-				reg = <0x0100000 0x0080000>;
-			};
-			partition@180000 {
-				label = "key_store";
-				reg = <0x0180000 0x0080000>;
-			};
-			partition@200000 {
-				label = "info";
-				reg = <0x0200000 0x0080000>;
-			};
-			partition@280000 {
-				label = "etc";
-				reg = <0x0280000 0x0a00000>;
-			};
-			partition@c80000 {
-				label = "kernel_1";
-				reg = <0x0c80000 0x0a00000>;
-			};
-			partition@1680000 {
-				label = "rootfs1";
-				reg = <0x1680000 0x2fc0000>;
-			};
-			partition@4640000 {
-				label = "kernel_2";
-				reg = <0x4640000 0x0a00000>;
-			};
-			partition@5040000 {
-				label = "rootfs2";
-				reg = <0x5040000 0x2fc0000>;
-			};
-		};
-
-		pcie-controller {
-			status = "okay";
-
-			pcie@1,0 {
-				status = "okay";
-			};
-		};
 	};
 
 	gpio_keys {
@@ -246,30 +185,4 @@
 			gpios = <&gpio1 8 0>;
 		};
 	};
-
-	gpio_poweroff {
-		compatible = "gpio-poweroff";
-		pinctrl-0 = <&pmx_pwr_off>;
-		pinctrl-names = "default";
-		gpios = <&gpio1 16 0>;
-	};
-
-	regulators {
-		compatible = "simple-bus";
-		#address-cells = <1>;
-		#size-cells = <0>;
-		pinctrl-0 = <&pmx_usb_power_off>;
-		pinctrl-names = "default";
-
-		usb0_power_off: regulator@1 {
-			compatible = "regulator-fixed";
-			reg = <1>;
-			regulator-name = "USB Power Off";
-			regulator-min-microvolt = <5000000>;
-			regulator-max-microvolt = <5000000>;
-			regulator-always-on;
-			regulator-boot-on;
-			gpio = <&gpio0 21 0>;
-		};
-	};
 };
diff --git a/arch/arm/boot/dts/kirkwood-nsa310a.dts b/arch/arm/boot/dts/kirkwood-nsa310a.dts
new file mode 100644
index 000000000000..ab0212b0e6f5
--- /dev/null
+++ b/arch/arm/boot/dts/kirkwood-nsa310a.dts
@@ -0,0 +1,165 @@
+/dts-v1/;
+
+#include "kirkwood-nsa310-common.dtsi"
+
+/*
+ * There are at least two different NSA310 designs. This variant does
+ * not have the red USB Led.
+ */
+
+/ {
+	compatible = "zyxel,nsa310a", "zyxel,nsa310", "marvell,kirkwood-88f6281", "marvell,kirkwood";
+
+	memory {
+		device_type = "memory";
+		reg = <0x00000000 0x10000000>;
+	};
+
+	chosen {
+		bootargs = "console=ttyS0,115200";
+	};
+
+	ocp@f1000000 {
+		pinctrl: pinctrl@10000 {
+			pinctrl-names = "default";
+
+			pmx_led_esata_green: pmx-led-esata-green {
+				marvell,pins = "mpp12";
+				marvell,function = "gpio";
+			};
+
+			pmx_led_esata_red: pmx-led-esata-red {
+				marvell,pins = "mpp13";
+				marvell,function = "gpio";
+			};
+
+			pmx_led_usb_green: pmx-led-usb-green {
+				marvell,pins = "mpp15";
+				marvell,function = "gpio";
+			};
+
+			pmx_usb_power_off: pmx-usb-power-off {
+				marvell,pins = "mpp21";
+				marvell,function = "gpio";
+			};
+
+			pmx_led_sys_green: pmx-led-sys-green {
+				marvell,pins = "mpp28";
+				marvell,function = "gpio";
+			};
+
+			pmx_led_sys_red: pmx-led-sys-red {
+				marvell,pins = "mpp29";
+				marvell,function = "gpio";
+			};
+
+			pmx_btn_reset: pmx-btn-reset {
+				marvell,pins = "mpp36";
+				marvell,function = "gpio";
+			};
+
+			pmx_btn_copy: pmx-btn-copy {
+				marvell,pins = "mpp37";
+				marvell,function = "gpio";
+			};
+
+			pmx_led_copy_green: pmx-led-copy-green {
+				marvell,pins = "mpp39";
+				marvell,function = "gpio";
+			};
+
+			pmx_led_copy_red: pmx-led-copy-red {
+				marvell,pins = "mpp40";
+				marvell,function = "gpio";
+			};
+
+			pmx_led_hdd_green: pmx-led-hdd-green {
+				marvell,pins = "mpp41";
+				marvell,function = "gpio";
+			};
+
+			pmx_led_hdd_red: pmx-led-hdd-red {
+				marvell,pins = "mpp42";
+				marvell,function = "gpio";
+			};
+
+			pmx_btn_power: pmx-btn-power {
+				marvell,pins = "mpp46";
+				marvell,function = "gpio";
+			};
+
+		};
+
+		i2c@11000 {
+			status = "okay";
+
+			lm85: lm85@2e {
+				compatible = "lm85";
+				reg = <0x2e>;
+			};
+		};
+	};
+
+	gpio_keys {
+		compatible = "gpio-keys";
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		button@1 {
+			label = "Power Button";
+			linux,code = <116>;
+			gpios = <&gpio1 14 0>;
+		};
+		button@2 {
+			label = "Copy Button";
+			linux,code = <133>;
+			gpios = <&gpio1 5 1>;
+		};
+		button@3 {
+			label = "Reset Button";
+			linux,code = <0x198>;
+			gpios = <&gpio1 4 1>;
+		};
+	};
+
+	gpio-leds {
+		compatible = "gpio-leds";
+
+		green-sys {
+			label = "nsa310:green:sys";
+			gpios = <&gpio0 28 0>;
+		};
+		red-sys {
+			label = "nsa310:red:sys";
+			gpios = <&gpio0 29 0>;
+		};
+		green-hdd {
+			label = "nsa310:green:hdd";
+			gpios = <&gpio1 9 0>;
+		};
+		red-hdd {
+			label = "nsa310:red:hdd";
+			gpios = <&gpio1 10 0>;
+		};
+		green-esata {
+			label = "nsa310:green:esata";
+			gpios = <&gpio0 12 0>;
+		};
+		red-esata {
+			label = "nsa310:red:esata";
+			gpios = <&gpio0 13 0>;
+		};
+		green-usb {
+			label = "nsa310:green:usb";
+			gpios = <&gpio0 15 0>;
+		};
+		green-copy {
+			label = "nsa310:green:copy";
+			gpios = <&gpio1 7 0>;
+		};
+		red-copy {
+			label = "nsa310:red:copy";
+			gpios = <&gpio1 8 0>;
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/kirkwood-openblocks_a6.dts b/arch/arm/boot/dts/kirkwood-openblocks_a6.dts
index 38dc8517d777..85ccf8d8abb1 100644
--- a/arch/arm/boot/dts/kirkwood-openblocks_a6.dts
+++ b/arch/arm/boot/dts/kirkwood-openblocks_a6.dts
@@ -1,7 +1,7 @@
 /dts-v1/;
 
-/include/ "kirkwood.dtsi"
-/include/ "kirkwood-6282.dtsi"
+#include "kirkwood.dtsi"
+#include "kirkwood-6282.dtsi"
 
 / {
 	model = "Plat'Home OpenBlocksA6";
@@ -166,3 +166,19 @@
 		};
 	};
 };
+
+&mdio {
+	status = "okay";
+
+	ethphy0: ethernet-phy@0 {
+		device_type = "ethernet-phy";
+		reg = <0>;
+	};
+};
+
+&eth0 {
+	status = "okay";
+	ethernet0-port@0 {
+		phy-handle = <&ethphy0>;
+	};
+};
diff --git a/arch/arm/boot/dts/kirkwood-sheevaplug-common.dtsi b/arch/arm/boot/dts/kirkwood-sheevaplug-common.dtsi
index f7143f128504..5696b630b70b 100644
--- a/arch/arm/boot/dts/kirkwood-sheevaplug-common.dtsi
+++ b/arch/arm/boot/dts/kirkwood-sheevaplug-common.dtsi
@@ -6,8 +6,8 @@
  * Licensed under GPLv2
  */
 
-/include/ "kirkwood.dtsi"
-/include/ "kirkwood-6281.dtsi"
+#include "kirkwood.dtsi"
+#include "kirkwood-6281.dtsi"
 
 / {
 	memory {
@@ -91,3 +91,19 @@
 		};
 	};
 };
+
+&mdio {
+	status = "okay";
+
+	ethphy0: ethernet-phy@0 {
+		device_type = "ethernet-phy";
+		reg = <0>;
+	};
+};
+
+&eth0 {
+	status = "okay";
+	ethernet0-port@0 {
+		phy-handle = <&ethphy0>;
+	};
+};
diff --git a/arch/arm/boot/dts/kirkwood-sheevaplug-esata.dts b/arch/arm/boot/dts/kirkwood-sheevaplug-esata.dts
index f620ce48de97..eac6a21f3b1f 100644
--- a/arch/arm/boot/dts/kirkwood-sheevaplug-esata.dts
+++ b/arch/arm/boot/dts/kirkwood-sheevaplug-esata.dts
@@ -8,7 +8,7 @@
 
 /dts-v1/;
 
-/include/ "kirkwood-sheevaplug-common.dtsi"
+#include "kirkwood-sheevaplug-common.dtsi"
 
 / {
 	model = "Globalscale Technologies eSATA SheevaPlug";
diff --git a/arch/arm/boot/dts/kirkwood-sheevaplug.dts b/arch/arm/boot/dts/kirkwood-sheevaplug.dts
index bf1dff251432..bb61918313db 100644
--- a/arch/arm/boot/dts/kirkwood-sheevaplug.dts
+++ b/arch/arm/boot/dts/kirkwood-sheevaplug.dts
@@ -8,7 +8,7 @@
 
 /dts-v1/;
 
-/include/ "kirkwood-sheevaplug-common.dtsi"
+#include "kirkwood-sheevaplug-common.dtsi"
 
 / {
 	model = "Globalscale Technologies SheevaPlug";
diff --git a/arch/arm/boot/dts/kirkwood-topkick.dts b/arch/arm/boot/dts/kirkwood-topkick.dts
index f2052d7bc10f..30842b4ff293 100644
--- a/arch/arm/boot/dts/kirkwood-topkick.dts
+++ b/arch/arm/boot/dts/kirkwood-topkick.dts
@@ -1,7 +1,7 @@
 /dts-v1/;
 
-/include/ "kirkwood.dtsi"
-/include/ "kirkwood-6282.dtsi"
+#include "kirkwood.dtsi"
+#include "kirkwood-6282.dtsi"
 
 / {
 	model = "Univeral Scientific Industrial Co. Topkick-1281P2";
@@ -203,3 +203,19 @@
 		};
 	};
 };
+
+&mdio {
+	status = "okay";
+
+	ethphy0: ethernet-phy@0 {
+		device_type = "ethernet-phy";
+		reg = <0>;
+	};
+};
+
+&eth0 {
+	status = "okay";
+	ethernet0-port@0 {
+		phy-handle = <&ethphy0>;
+	};
+};
diff --git a/arch/arm/boot/dts/kirkwood-ts219-6281.dts b/arch/arm/boot/dts/kirkwood-ts219-6281.dts
index 6dd1038e4de4..f755bc1dc604 100644
--- a/arch/arm/boot/dts/kirkwood-ts219-6281.dts
+++ b/arch/arm/boot/dts/kirkwood-ts219-6281.dts
@@ -1,8 +1,8 @@
 /dts-v1/;
 
-/include/ "kirkwood.dtsi"
-/include/ "kirkwood-6281.dtsi"
-/include/ "kirkwood-ts219.dtsi"
+#include "kirkwood.dtsi"
+#include "kirkwood-6281.dtsi"
+#include "kirkwood-ts219.dtsi"
 
 / {
 	ocp@f1000000 {
@@ -50,4 +50,6 @@
 			gpios = <&gpio0 16 1>;
 		};
 	};
-};
-\ No newline at end of file
+};
+
+&ethphy0 { reg = <8>; };
diff --git a/arch/arm/boot/dts/kirkwood-ts219-6282.dts b/arch/arm/boot/dts/kirkwood-ts219-6282.dts
index 6fdc5ffcaae5..9efcd2dc79d3 100644
--- a/arch/arm/boot/dts/kirkwood-ts219-6282.dts
+++ b/arch/arm/boot/dts/kirkwood-ts219-6282.dts
@@ -1,10 +1,21 @@
 /dts-v1/;
 
-/include/ "kirkwood.dtsi"
-/include/ "kirkwood-6282.dtsi"
-/include/ "kirkwood-ts219.dtsi"
+#include "kirkwood.dtsi"
+#include "kirkwood-6282.dtsi"
+#include "kirkwood-ts219.dtsi"
 
 / {
+	mbus {
+		ranges = <MBUS_ID(0xf0, 0x01) 0 0xf1000000 0x100000>;
+		pcie-controller {
+			status = "okay";
+
+			pcie@2,0 {
+				status = "okay";
+			};
+		};
+	};
+
 	ocp@f1000000 {
 		pinctrl: pinctrl@10000 {
 
@@ -30,14 +41,6 @@
 				marvell,function = "gpio";
 			};
 		};
-		pcie-controller {
-			status = "okay";
-
-			pcie@2,0 {
-				status = "okay";
-			};
-		};
-
 	};
 
 	gpio_keys {
@@ -58,4 +61,6 @@
 			gpios = <&gpio1 5 1>;
 		};
 	};
-};
-\ No newline at end of file
+};
+
+&ethphy0 { reg = <0>; };
diff --git a/arch/arm/boot/dts/kirkwood-ts219.dtsi b/arch/arm/boot/dts/kirkwood-ts219.dtsi
index 0c9a94cd666c..39158cf16258 100644
--- a/arch/arm/boot/dts/kirkwood-ts219.dtsi
+++ b/arch/arm/boot/dts/kirkwood-ts219.dtsi
@@ -11,6 +11,16 @@
 		bootargs = "console=ttyS0,115200n8";
 	};
 
+	mbus {
+		pcie-controller {
+			status = "okay";
+
+			pcie@1,0 {
+				status = "okay";
+			};
+		};
+	};
+
 	ocp@f1000000 {
 		i2c@11000 {
 			status = "okay";
@@ -87,12 +97,21 @@
 			status = "okay";
 			nr-ports = <2>;
 		};
-		pcie-controller {
-			status = "okay";
+	};
+};
 
-			pcie@1,0 {
-				status = "okay";
-			};
-		};
+&mdio {
+	status = "okay";
+
+	ethphy0: ethernet-phy {
+		device_type = "ethernet-phy";
+                /* overwrite reg property in board file */
+	};
+};
+
+&eth0 {
+	status = "okay";
+	ethernet0-port@0 {
+		phy-handle = <&ethphy0>;
 	};
 };
diff --git a/arch/arm/boot/dts/kirkwood.dtsi b/arch/arm/boot/dts/kirkwood.dtsi
index 9809fc1f105c..1335b2e1bed4 100644
--- a/arch/arm/boot/dts/kirkwood.dtsi
+++ b/arch/arm/boot/dts/kirkwood.dtsi
@@ -1,5 +1,7 @@
 /include/ "skeleton.dtsi"
 
+#define MBUS_ID(target,attributes) (((target) << 24) | ((attributes) << 16))
+
 / {
 	compatible = "marvell,kirkwood";
 	interrupt-parent = <&intc>;
@@ -11,6 +13,7 @@
 		cpu@0 {
 			device_type = "cpu";
 			compatible = "marvell,feroceon";
+			reg = <0>;
 			clocks = <&core_clk 1>, <&core_clk 3>, <&gate_clk 11>;
 			clock-names = "cpu_clk", "ddrclk", "powersave";
 		};
@@ -20,23 +23,53 @@
 	       gpio0 = &gpio0;
 	       gpio1 = &gpio1;
 	};
-	intc: interrupt-controller {
-		compatible = "marvell,orion-intc", "marvell,intc";
-		interrupt-controller;
-		#interrupt-cells = <1>;
-		reg = <0xf1020204 0x04>,
-		      <0xf1020214 0x04>;
+
+	mbus {
+		compatible = "marvell,kirkwood-mbus", "simple-bus";
+		#address-cells = <2>;
+		#size-cells = <1>;
+		controller = <&mbusc>;
+		pcie-mem-aperture = <0xe0000000 0x10000000>; /* 256 MiB memory space */
+		pcie-io-aperture  = <0xf2000000 0x100000>;   /*   1 MiB    I/O space */
 	};
 
 	ocp@f1000000 {
 		compatible = "simple-bus";
 		ranges = <0x00000000 0xf1000000 0x0100000
-		          0xe0000000 0xe0000000 0x8100000 /* PCIE */
 		          0xf4000000 0xf4000000 0x0000400
 		          0xf5000000 0xf5000000 0x0000400>;
 		#address-cells = <1>;
 		#size-cells = <1>;
 
+		mbusc: mbus-controller@20000 {
+			compatible = "marvell,mbus-controller";
+			reg = <0x20000 0x80>, <0x1500 0x20>;
+		};
+
+		timer: timer@20300 {
+			compatible = "marvell,orion-timer";
+			reg = <0x20300 0x20>;
+			interrupt-parent = <&bridge_intc>;
+			interrupts = <1>, <2>;
+			clocks = <&core_clk 0>;
+		};
+
+		intc: main-interrupt-ctrl@20200 {
+			compatible = "marvell,orion-intc";
+			interrupt-controller;
+			#interrupt-cells = <1>;
+			reg = <0x20200 0x10>, <0x20210 0x10>;
+		};
+
+		bridge_intc: bridge-interrupt-ctrl@20110 {
+			compatible = "marvell,orion-bridge-intc";
+			interrupt-controller;
+			#interrupt-cells = <1>;
+			reg = <0x20110 0x8>;
+			interrupts = <1>;
+			marvell,#interrupts = <6>;
+		};
+
 		core_clk: core-clocks@10030 {
 			compatible = "marvell,kirkwood-core-clock";
 			reg = <0x10030 0x4>;
@@ -103,9 +136,11 @@
 			#clock-cells = <1>;
 		};
 
-		wdt@20300 {
+		wdt: watchdog-timer@20300 {
 			compatible = "marvell,orion-wdt";
 			reg = <0x20300 0x28>;
+			interrupt-parent = <&bridge_intc>;
+			interrupts = <3>;
 			clocks = <&gate_clk 7>;
 			status = "okay";
 		};
@@ -133,7 +168,7 @@
 		xor@60900 {
 			compatible = "marvell,orion-xor";
 			reg = <0x60900 0x100
-			       0xd0B00 0x100>;
+			       0x60B00 0x100>;
 			status = "okay";
 			clocks = <&gate_clk 16>;
 
@@ -192,5 +227,57 @@
 			clocks = <&gate_clk 17>;
 			status = "okay";
 		};
+
+		mdio: mdio-bus@72004 {
+			compatible = "marvell,orion-mdio";
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0x72004 0x84>;
+			interrupts = <46>;
+			clocks = <&gate_clk 0>;
+			status = "disabled";
+
+			/* add phy nodes in board file */
+		};
+
+		eth0: ethernet-controller@72000 {
+			compatible = "marvell,kirkwood-eth";
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0x72000 0x4000>;
+			clocks = <&gate_clk 0>;
+			marvell,tx-checksum-limit = <1600>;
+			status = "disabled";
+
+			ethernet0-port@0 {
+				device_type = "network";
+				compatible = "marvell,kirkwood-eth-port";
+				reg = <0>;
+				interrupts = <11>;
+				/* overwrite MAC address in bootloader */
+				local-mac-address = [00 00 00 00 00 00];
+				/* set phy-handle property in board file */
+			};
+		};
+
+		eth1: ethernet-controller@76000 {
+			compatible = "marvell,kirkwood-eth";
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0x76000 0x4000>;
+			clocks = <&gate_clk 19>;
+			marvell,tx-checksum-limit = <1600>;
+			status = "disabled";
+
+			ethernet1-port@0 {
+				device_type = "network";
+				compatible = "marvell,kirkwood-eth-port";
+				reg = <0>;
+				interrupts = <15>;
+				/* overwrite MAC address in bootloader */
+				local-mac-address = [00 00 00 00 00 00];
+				/* set phy-handle property in board file */
+			};
+		};
 	};
 };
diff --git a/arch/arm/boot/dts/msm8660-surf.dts b/arch/arm/boot/dts/msm8660-surf.dts
index cdc010e0f93e..386d42870215 100644
--- a/arch/arm/boot/dts/msm8660-surf.dts
+++ b/arch/arm/boot/dts/msm8660-surf.dts
@@ -38,7 +38,7 @@
 	};
 
 	serial@19c40000 {
-		compatible = "qcom,msm-hsuart", "qcom,msm-uart";
+		compatible = "qcom,msm-uartdm-v1.3", "qcom,msm-uartdm";
 		reg = <0x19c40000 0x1000>,
 		      <0x19c00000 0x1000>;
 		interrupts = <0 195 0x0>;
diff --git a/arch/arm/boot/dts/msm8960-cdp.dts b/arch/arm/boot/dts/msm8960-cdp.dts
index 9c1167b0459b..93e9f7e0b7ad 100644
--- a/arch/arm/boot/dts/msm8960-cdp.dts
+++ b/arch/arm/boot/dts/msm8960-cdp.dts
@@ -38,7 +38,7 @@
 	};
 
 	serial@16440000 {
-		compatible = "qcom,msm-hsuart", "qcom,msm-uart";
+		compatible = "qcom,msm-uartdm-v1.3", "qcom,msm-uartdm";
 		reg = <0x16440000 0x1000>,
 		      <0x16400000 0x1000>;
 		interrupts = <0 154 0x0>;
diff --git a/arch/arm/boot/dts/omap3-beagle-xm.dts b/arch/arm/boot/dts/omap3-beagle-xm.dts
index afdb16417d4e..2816bf612672 100644
--- a/arch/arm/boot/dts/omap3-beagle-xm.dts
+++ b/arch/arm/boot/dts/omap3-beagle-xm.dts
@@ -11,7 +11,7 @@
 
 / {
 	model = "TI OMAP3 BeagleBoard xM";
-	compatible = "ti,omap3-beagle-xm, ti,omap3-beagle", "ti,omap3";
+	compatible = "ti,omap3-beagle-xm", "ti,omap36xx", "ti,omap3";
 
 	cpus {
 		cpu@0 {
diff --git a/arch/arm/boot/dts/omap3-igep.dtsi b/arch/arm/boot/dts/omap3-igep.dtsi
index bc48b114eae6..2326d11462a5 100644
--- a/arch/arm/boot/dts/omap3-igep.dtsi
+++ b/arch/arm/boot/dts/omap3-igep.dtsi
@@ -48,6 +48,15 @@
 		>;
 	};
 
+	mcbsp2_pins: pinmux_mcbsp2_pins {
+		pinctrl-single,pins = <
+			0x10c (PIN_INPUT | MUX_MODE0)		/* mcbsp2_fsx.mcbsp2_fsx */
+			0x10e (PIN_INPUT | MUX_MODE0)		/* mcbsp2_clkx.mcbsp2_clkx */
+			0x110 (PIN_INPUT | MUX_MODE0)		/* mcbsp2_dr.mcbsp2.dr */
+			0x112 (PIN_OUTPUT | MUX_MODE0)		/* mcbsp2_dx.mcbsp2_dx */
+		>;
+	};
+
 	mmc1_pins: pinmux_mmc1_pins {
 		pinctrl-single,pins = <
 			0x114 (PIN_INPUT_PULLUP | MUX_MODE0)	/* sdmmc1_clk.sdmmc1_clk */
@@ -93,6 +102,11 @@
 	clock-frequency = <400000>;
 };
 
+&mcbsp2 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&mcbsp2_pins>;
+};
+
 &mmc1 {
       pinctrl-names = "default";
       pinctrl-0 = <&mmc1_pins>;
diff --git a/arch/arm/boot/dts/omap3.dtsi b/arch/arm/boot/dts/omap3.dtsi
index 7d95cda1fae4..b41bd57f4328 100644
--- a/arch/arm/boot/dts/omap3.dtsi
+++ b/arch/arm/boot/dts/omap3.dtsi
@@ -108,7 +108,7 @@
 			#address-cells = <1>;
 			#size-cells = <0>;
 			pinctrl-single,register-width = <16>;
-			pinctrl-single,function-mask = <0x7f1f>;
+			pinctrl-single,function-mask = <0xff1f>;
 		};
 
 		omap3_pmx_wkup: pinmux@0x48002a00 {
@@ -117,7 +117,7 @@
 			#address-cells = <1>;
 			#size-cells = <0>;
 			pinctrl-single,register-width = <16>;
-			pinctrl-single,function-mask = <0x7f1f>;
+			pinctrl-single,function-mask = <0xff1f>;
 		};
 
 		gpio1: gpio@48310000 {
diff --git a/arch/arm/boot/dts/omap4-panda-common.dtsi b/arch/arm/boot/dts/omap4-panda-common.dtsi
index faa95b5b242e..814ab67c8c29 100644
--- a/arch/arm/boot/dts/omap4-panda-common.dtsi
+++ b/arch/arm/boot/dts/omap4-panda-common.dtsi
@@ -107,6 +107,19 @@
 	 */
 		clock-frequency = <19200000>;
 	};
+
+	/* regulator for wl12xx on sdio5 */
+	wl12xx_vmmc: wl12xx_vmmc {
+		pinctrl-names = "default";
+		pinctrl-0 = <&wl12xx_gpio>;
+		compatible = "regulator-fixed";
+		regulator-name = "vwl1271";
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <1800000>;
+		gpio = <&gpio2 11 0>;
+		startup-delay-us = <70000>;
+		enable-active-high;
+	};
 };
 
 &omap4_pmx_wkup {
@@ -235,6 +248,33 @@
 			0x1c (PIN_OUTPUT | MUX_MODE3)	/* gpio_wk8 */
 		>;
 	};
+
+	/*
+	 * wl12xx GPIO outputs for WLAN_EN, BT_EN, FM_EN, BT_WAKEUP
+	 * REVISIT: Are the pull-ups needed for GPIO 48 and 49?
+	 */
+	wl12xx_gpio: pinmux_wl12xx_gpio {
+		pinctrl-single,pins = <
+			0x26 (PIN_OUTPUT | MUX_MODE3)		/* gpmc_a19.gpio_43 */
+			0x2c (PIN_OUTPUT | MUX_MODE3)		/* gpmc_a22.gpio_46 */
+			0x30 (PIN_OUTPUT_PULLUP | MUX_MODE3)	/* gpmc_a24.gpio_48 */
+			0x32 (PIN_OUTPUT_PULLUP | MUX_MODE3)	/* gpmc_a25.gpio_49 */
+		>;
+	};
+
+	/* wl12xx GPIO inputs and SDIO pins */
+	wl12xx_pins: pinmux_wl12xx_pins {
+		pinctrl-single,pins = <
+			0x38 (PIN_INPUT | MUX_MODE3)		/* gpmc_ncs2.gpio_52 */
+			0x3a (PIN_INPUT | MUX_MODE3)		/* gpmc_ncs3.gpio_53 */
+			0x108 (PIN_OUTPUT | MUX_MODE0)		/* sdmmc5_clk.sdmmc5_clk */
+			0x10a (PIN_INPUT_PULLUP | MUX_MODE0)	/* sdmmc5_cmd.sdmmc5_cmd */
+			0x10c (PIN_INPUT_PULLUP | MUX_MODE0)	/* sdmmc5_dat0.sdmmc5_dat0 */
+			0x10e (PIN_INPUT_PULLUP | MUX_MODE0)	/* sdmmc5_dat1.sdmmc5_dat1 */
+			0x110 (PIN_INPUT_PULLUP | MUX_MODE0)	/* sdmmc5_dat2.sdmmc5_dat2 */
+			0x112 (PIN_INPUT_PULLUP | MUX_MODE0)	/* sdmmc5_dat3.sdmmc5_dat3 */
+		>;
+	};
 };
 
 &i2c1 {
@@ -314,8 +354,12 @@
 };
 
 &mmc5 {
-	ti,non-removable;
+	pinctrl-names = "default";
+	pinctrl-0 = <&wl12xx_pins>;
+	vmmc-supply = <&wl12xx_vmmc>;
+	non-removable;
 	bus-width = <4>;
+	cap-power-off-card;
 };
 
 &emif1 {
diff --git a/arch/arm/boot/dts/omap4-sdp.dts b/arch/arm/boot/dts/omap4-sdp.dts
index 7951b4ea500a..4f78380ecdb8 100644
--- a/arch/arm/boot/dts/omap4-sdp.dts
+++ b/arch/arm/boot/dts/omap4-sdp.dts
@@ -140,6 +140,19 @@
 			"DMic", "Digital Mic",
 			"Digital Mic", "Digital Mic1 Bias";
 	};
+
+	/* regulator for wl12xx on sdio5 */
+	wl12xx_vmmc: wl12xx_vmmc {
+		pinctrl-names = "default";
+		pinctrl-0 = <&wl12xx_gpio>;
+		compatible = "regulator-fixed";
+		regulator-name = "vwl1271";
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <1800000>;
+		gpio = <&gpio2 22 0>;
+		startup-delay-us = <70000>;
+		enable-active-high;
+	};
 };
 
 &omap4_pmx_wkup {
@@ -295,6 +308,26 @@
 			0xf0 (PIN_INPUT_PULLUP | MUX_MODE0)	/* i2c4_sda */
 		>;
 	};
+
+	/* wl12xx GPIO output for WLAN_EN */
+	wl12xx_gpio: pinmux_wl12xx_gpio {
+		pinctrl-single,pins = <
+			0x3c (PIN_OUTPUT | MUX_MODE3)		/* gpmc_nwp.gpio_54 */
+		>;
+	};
+
+	/* wl12xx GPIO inputs and SDIO pins */
+	wl12xx_pins: pinmux_wl12xx_pins {
+		pinctrl-single,pins = <
+			0x3a (PIN_INPUT | MUX_MODE3)		/* gpmc_ncs3.gpio_53 */
+			0x108 (PIN_OUTPUT | MUX_MODE3)		/* sdmmc5_clk.sdmmc5_clk */
+			0x10a (PIN_INPUT_PULLUP | MUX_MODE3)	/* sdmmc5_cmd.sdmmc5_cmd */
+			0x10c (PIN_INPUT_PULLUP | MUX_MODE3)	/* sdmmc5_dat0.sdmmc5_dat0 */
+			0x10e (PIN_INPUT_PULLUP | MUX_MODE3)	/* sdmmc5_dat1.sdmmc5_dat1 */
+			0x110 (PIN_INPUT_PULLUP | MUX_MODE3)	/* sdmmc5_dat2.sdmmc5_dat2 */
+			0x112 (PIN_INPUT_PULLUP | MUX_MODE3)	/* sdmmc5_dat3.sdmmc5_dat3 */
+		>;
+	};
 };
 
 &i2c1 {
@@ -420,8 +453,12 @@
 };
 
 &mmc5 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&wl12xx_pins>;
+	vmmc-supply = <&wl12xx_vmmc>;
+	non-removable;
 	bus-width = <4>;
-	ti,non-removable;
+	cap-power-off-card;
 };
 
 &emif1 {
diff --git a/arch/arm/boot/dts/omap5.dtsi b/arch/arm/boot/dts/omap5.dtsi
index e643620417a9..7cdea1bfea09 100644
--- a/arch/arm/boot/dts/omap5.dtsi
+++ b/arch/arm/boot/dts/omap5.dtsi
@@ -637,25 +637,26 @@
 		omap_dwc3@4a020000 {
 			compatible = "ti,dwc3";
 			ti,hwmods = "usb_otg_ss";
-			reg = <0x4a020000 0x1000>;
+			reg = <0x4a020000 0x10000>;
 			interrupts = <GIC_SPI 93 IRQ_TYPE_LEVEL_HIGH>;
 			#address-cells = <1>;
 			#size-cells = <1>;
 			utmi-mode = <2>;
 			ranges;
 			dwc3@4a030000 {
-				compatible = "synopsys,dwc3";
-				reg = <0x4a030000 0x1000>;
+				compatible = "snps,dwc3";
+				reg = <0x4a030000 0x10000>;
 				interrupts = <GIC_SPI 92 IRQ_TYPE_LEVEL_HIGH>;
 				usb-phy = <&usb2_phy>, <&usb3_phy>;
 				tx-fifo-resize;
 			};
 		};
 
-		ocp2scp {
+		ocp2scp@4a080000 {
 			compatible = "ti,omap-ocp2scp";
 			#address-cells = <1>;
 			#size-cells = <1>;
+			reg = <0x4a080000 0x20>;
 			ranges;
 			ti,hwmods = "ocp2scp1";
 			usb2_phy: usb2phy@4a084000 {
diff --git a/arch/arm/boot/dts/orion5x-lacie-ethernet-disk-mini-v2.dts b/arch/arm/boot/dts/orion5x-lacie-ethernet-disk-mini-v2.dts
index 0077fc8510b7..aed83deaa991 100644
--- a/arch/arm/boot/dts/orion5x-lacie-ethernet-disk-mini-v2.dts
+++ b/arch/arm/boot/dts/orion5x-lacie-ethernet-disk-mini-v2.dts
@@ -53,3 +53,20 @@
 		};
 	};
 };
+
+&mdio {
+	status = "okay";
+
+	ethphy: ethernet-phy {
+		device-type = "ethernet-phy";
+		reg = <8>;
+	};
+};
+
+&eth {
+	status = "okay";
+
+	ethernet-port@0 {
+		phy-handle = <&ethphy>;
+	};
+};
diff --git a/arch/arm/boot/dts/orion5x.dtsi b/arch/arm/boot/dts/orion5x.dtsi
index 892c64e3f1e1..e06c37e91ac6 100644
--- a/arch/arm/boot/dts/orion5x.dtsi
+++ b/arch/arm/boot/dts/orion5x.dtsi
@@ -16,11 +16,12 @@
 	aliases {
 		gpio0 = &gpio0;
 	};
+
 	intc: interrupt-controller {
-		compatible = "marvell,orion-intc", "marvell,intc";
+		compatible = "marvell,orion-intc";
 		interrupt-controller;
 		#interrupt-cells = <1>;
-		reg = <0xf1020204 0x04>;
+		reg = <0xf1020200 0x08>;
 	};
 
 	ocp@f1000000 {
@@ -132,5 +133,34 @@
 			interrupts = <28>;
 			status = "okay";
 		};
+
+		mdio: mdio-bus@72004 {
+			compatible = "marvell,orion-mdio";
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0x72004 0x84>;
+			interrupts = <22>;
+			status = "disabled";
+
+			/* add phy nodes in board file */
+		};
+
+		eth: ethernet-controller@72000 {
+			compatible = "marvell,orion-eth";
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0x72000 0x4000>;
+			marvell,tx-checksum-limit = <1600>;
+			status = "disabled";
+
+			ethernet-port@0 {
+				device_type = "network";
+				compatible = "marvell,orion-eth-port";
+				reg = <0>;
+				/* overwrite MAC address in bootloader */
+				local-mac-address = [00 00 00 00 00 00];
+				/* set phy-handle property in board file */
+			};
+		};
 	};
 };
diff --git a/arch/arm/boot/dts/prima2.dtsi b/arch/arm/boot/dts/prima2.dtsi
index bbeb623fc2c6..27ed9f5144bc 100644
--- a/arch/arm/boot/dts/prima2.dtsi
+++ b/arch/arm/boot/dts/prima2.dtsi
@@ -171,7 +171,8 @@
 			compatible = "simple-bus";
 			#address-cells = <1>;
 			#size-cells = <1>;
-			ranges = <0xb0000000 0xb0000000 0x180000>;
+			ranges = <0xb0000000 0xb0000000 0x180000>,
+			       <0x56000000 0x56000000 0x1b00000>;
 
 			timer@b0020000 {
 				compatible = "sirf,prima2-tick";
@@ -196,25 +197,32 @@
 			uart0: uart@b0050000 {
 				cell-index = <0>;
 				compatible = "sirf,prima2-uart";
-				reg = <0xb0050000 0x10000>;
+				reg = <0xb0050000 0x1000>;
 				interrupts = <17>;
+				fifosize = <128>;
 				clocks = <&clks 13>;
+				sirf,uart-dma-rx-channel = <21>;
+				sirf,uart-dma-tx-channel = <2>;
 			};
 
 			uart1: uart@b0060000 {
 				cell-index = <1>;
 				compatible = "sirf,prima2-uart";
-				reg = <0xb0060000 0x10000>;
+				reg = <0xb0060000 0x1000>;
 				interrupts = <18>;
+				fifosize = <32>;
 				clocks = <&clks 14>;
 			};
 
 			uart2: uart@b0070000 {
 				cell-index = <2>;
 				compatible = "sirf,prima2-uart";
-				reg = <0xb0070000 0x10000>;
+				reg = <0xb0070000 0x1000>;
 				interrupts = <19>;
+				fifosize = <128>;
 				clocks = <&clks 15>;
+				sirf,uart-dma-rx-channel = <6>;
+				sirf,uart-dma-tx-channel = <7>;
 			};
 
 			usp0: usp@b0080000 {
@@ -222,7 +230,10 @@
 				compatible = "sirf,prima2-usp";
 				reg = <0xb0080000 0x10000>;
 				interrupts = <20>;
+				fifosize = <128>;
 				clocks = <&clks 28>;
+				sirf,usp-dma-rx-channel = <17>;
+				sirf,usp-dma-tx-channel = <18>;
 			};
 
 			usp1: usp@b0090000 {
@@ -230,7 +241,10 @@
 				compatible = "sirf,prima2-usp";
 				reg = <0xb0090000 0x10000>;
 				interrupts = <21>;
+				fifosize = <128>;
 				clocks = <&clks 29>;
+				sirf,usp-dma-rx-channel = <14>;
+				sirf,usp-dma-tx-channel = <15>;
 			};
 
 			usp2: usp@b00a0000 {
@@ -238,7 +252,10 @@
 				compatible = "sirf,prima2-usp";
 				reg = <0xb00a0000 0x10000>;
 				interrupts = <22>;
+				fifosize = <128>;
 				clocks = <&clks 30>;
+				sirf,usp-dma-rx-channel = <10>;
+				sirf,usp-dma-tx-channel = <11>;
 			};
 
 			dmac0: dma-controller@b00b0000 {
@@ -261,6 +278,8 @@
 				compatible = "sirf,prima2-vip";
 				reg = <0xb00C0000 0x10000>;
 				clocks = <&clks 31>;
+				interrupts = <14>;
+				sirf,vip-dma-rx-channel = <16>;
 			};
 
 			spi0: spi@b00d0000 {
diff --git a/arch/arm/boot/dts/pxa3xx.dtsi b/arch/arm/boot/dts/pxa3xx.dtsi
index f9d92da86783..83bb0eff697b 100644
--- a/arch/arm/boot/dts/pxa3xx.dtsi
+++ b/arch/arm/boot/dts/pxa3xx.dtsi
@@ -28,5 +28,16 @@
 			marvell,intc-priority;
 			marvell,intc-nr-irqs = <56>;
 		};
+
+		gpio: gpio@40e00000 {
+			compatible = "intel,pxa3xx-gpio";
+			reg = <0x40e00000 0x10000>;
+			interrupt-names = "gpio0", "gpio1", "gpio_mux";
+			interrupts = <8 9 10>;
+			gpio-controller;
+			#gpio-cells = <0x2>;
+			interrupt-controller;
+			#interrupt-cells = <0x2>;
+		};
 	};
 };
diff --git a/arch/arm/boot/dts/r8a73a4-ape6evm-reference.dts b/arch/arm/boot/dts/r8a73a4-ape6evm-reference.dts
new file mode 100644
index 000000000000..f444624eb097
--- /dev/null
+++ b/arch/arm/boot/dts/r8a73a4-ape6evm-reference.dts
@@ -0,0 +1,65 @@
+/*
+ * Device Tree Source for the APE6EVM board
+ *
+ * Copyright (C) 2013 Renesas Solutions Corp.
+ *
+ * This file is licensed under the terms of the GNU General Public License
+ * version 2.  This program is licensed "as is" without any warranty of any
+ * kind, whether express or implied.
+ */
+
+/dts-v1/;
+/include/ "r8a73a4.dtsi"
+
+/ {
+	model = "APE6EVM";
+	compatible = "renesas,ape6evm-reference", "renesas,r8a73a4";
+
+	chosen {
+		bootargs = "console=ttySC0,115200 ignore_loglevel rw";
+	};
+
+	memory@40000000 {
+		device_type = "memory";
+		reg = <0 0x40000000 0 0x40000000>;
+	};
+
+	lbsc {
+		compatible = "simple-bus";
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0 0 0 0x80000000>;
+	};
+};
+
+&i2c5 {
+	vdd_dvfs: max8973@1b {
+		compatible = "maxim,max8973";
+		reg = <0x1b>;
+
+		regulator-min-microvolt = <935000>;
+		regulator-max-microvolt = <1200000>;
+		regulator-boot-on;
+		regulator-always-on;
+	};
+};
+
+&cpu0 {
+	cpu0-supply = <&vdd_dvfs>;
+	operating-points = <
+		/* kHz  uV */
+		1950000 1115000
+		1462500  995000
+	>;
+	voltage-tolerance = <1>; /* 1% */
+};
+
+&pfc {
+	pinctrl-0 = <&scifa0_pins>;
+	pinctrl-names = "default";
+
+	scifa0_pins: scifa0 {
+		renesas,groups = "scifa0_data";
+		renesas,function = "scifa0";
+	};
+};
diff --git a/arch/arm/boot/dts/r8a73a4-ape6evm.dts b/arch/arm/boot/dts/r8a73a4-ape6evm.dts
index f603c6946c29..72f867e65791 100644
--- a/arch/arm/boot/dts/r8a73a4-ape6evm.dts
+++ b/arch/arm/boot/dts/r8a73a4-ape6evm.dts
@@ -16,7 +16,7 @@
 	compatible = "renesas,ape6evm", "renesas,r8a73a4";
 
 	chosen {
-		bootargs = "console=ttySC0,115200 ignore_loglevel root=/dev/nfs ip=dhcp";
+		bootargs = "console=ttySC0,115200 ignore_loglevel root=/dev/nfs ip=dhcp rw";
 	};
 
 	memory@40000000 {
@@ -50,3 +50,25 @@
 		};
 	};
 };
+
+&i2c5 {
+	vdd_dvfs: max8973@1b {
+		compatible = "maxim,max8973";
+		reg = <0x1b>;
+
+		regulator-min-microvolt = <935000>;
+		regulator-max-microvolt = <1200000>;
+		regulator-boot-on;
+		regulator-always-on;
+	};
+};
+
+&cpu0 {
+	cpu0-supply = <&vdd_dvfs>;
+	operating-points = <
+		/* kHz  uV */
+		1950000 1115000
+		1462500  995000
+	>;
+	voltage-tolerance = <1>; /* 1% */
+};
diff --git a/arch/arm/boot/dts/r8a73a4.dtsi b/arch/arm/boot/dts/r8a73a4.dtsi
index 4ff2019c0e30..658fcc537576 100644
--- a/arch/arm/boot/dts/r8a73a4.dtsi
+++ b/arch/arm/boot/dts/r8a73a4.dtsi
@@ -85,4 +85,137 @@
 		interrupt-parent = <&gic>;
 		interrupts = <0 69 4>;
 	};
+
+	i2c0: i2c@e6500000 {
+		#address-cells = <1>;
+		#size-cells = <0>;
+		compatible = "renesas,rmobile-iic";
+		reg = <0 0xe6500000 0 0x428>;
+		interrupt-parent = <&gic>;
+		interrupts = <0 174 0x4>;
+	};
+
+	i2c1: i2c@e6510000 {
+		#address-cells = <1>;
+		#size-cells = <0>;
+		compatible = "renesas,rmobile-iic";
+		reg = <0 0xe6510000 0 0x428>;
+		interrupt-parent = <&gic>;
+		interrupts = <0 175 0x4>;
+	};
+
+	i2c2: i2c@e6520000 {
+		#address-cells = <1>;
+		#size-cells = <0>;
+		compatible = "renesas,rmobile-iic";
+		reg = <0 0xe6520000 0 0x428>;
+		interrupt-parent = <&gic>;
+		interrupts = <0 176 0x4>;
+	};
+
+	i2c3: i2c@e6530000 {
+		#address-cells = <1>;
+		#size-cells = <0>;
+		compatible = "renesas,rmobile-iic";
+		reg = <0 0xe6530000 0 0x428>;
+		interrupt-parent = <&gic>;
+		interrupts = <0 177 0x4>;
+	};
+
+	i2c4: i2c@e6540000 {
+		#address-cells = <1>;
+		#size-cells = <0>;
+		compatible = "renesas,rmobile-iic";
+		reg = <0 0xe6540000 0 0x428>;
+		interrupt-parent = <&gic>;
+		interrupts = <0 178 0x4>;
+	};
+
+	i2c5: i2c@e60b0000 {
+		#address-cells = <1>;
+		#size-cells = <0>;
+		compatible = "renesas,rmobile-iic";
+		reg = <0 0xe60b0000 0 0x428>;
+		interrupt-parent = <&gic>;
+		interrupts = <0 179 0x4>;
+	};
+
+	i2c6: i2c@e6550000 {
+		#address-cells = <1>;
+		#size-cells = <0>;
+		compatible = "renesas,rmobile-iic";
+		reg = <0 0xe6550000 0 0x428>;
+		interrupt-parent = <&gic>;
+		interrupts = <0 184 0x4>;
+	};
+
+	i2c7: i2c@e6560000 {
+		#address-cells = <1>;
+		#size-cells = <0>;
+		compatible = "renesas,rmobile-iic";
+		reg = <0 0xe6560000 0 0x428>;
+		interrupt-parent = <&gic>;
+		interrupts = <0 185 0x4>;
+	};
+
+	i2c8: i2c@e6570000 {
+		#address-cells = <1>;
+		#size-cells = <0>;
+		compatible = "renesas,rmobile-iic";
+		reg = <0 0xe6570000 0 0x428>;
+		interrupt-parent = <&gic>;
+		interrupts = <0 173 0x4>;
+	};
+
+	mmcif0: mmcif@ee200000 {
+		compatible = "renesas,sh-mmcif";
+		reg = <0 0xee200000 0 0x80>;
+		interrupt-parent = <&gic>;
+		interrupts = <0 169 0x4>;
+		reg-io-width = <4>;
+		status = "disabled";
+	};
+
+	mmcif1: mmcif@ee220000 {
+		compatible = "renesas,sh-mmcif";
+		reg = <0 0xee220000 0 0x80>;
+		interrupt-parent = <&gic>;
+		interrupts = <0 170 0x4>;
+		reg-io-width = <4>;
+		status = "disabled";
+	};
+
+	pfc: pfc@e6050000 {
+		compatible = "renesas,pfc-r8a73a4";
+		reg = <0 0xe6050000 0 0x9000>;
+		gpio-controller;
+		#gpio-cells = <2>;
+	};
+
+	sdhi0: sdhi@ee100000 {
+		compatible = "renesas,sdhi-r8a73a4";
+		reg = <0 0xee100000 0 0x100>;
+		interrupt-parent = <&gic>;
+		interrupts = <0 165 4>;
+		cap-sd-highspeed;
+		status = "disabled";
+	};
+
+	sdhi1: sdhi@ee120000 {
+		compatible = "renesas,sdhi-r8a73a4";
+		reg = <0 0xee120000 0 0x100>;
+		interrupt-parent = <&gic>;
+		interrupts = <0 166 4>;
+		cap-sd-highspeed;
+		status = "disabled";
+	};
+
+	sdhi2: sdhi@ee140000 {
+		compatible = "renesas,sdhi-r8a73a4";
+		reg = <0 0xee140000 0 0x100>;
+		interrupt-parent = <&gic>;
+		interrupts = <0 167 4>;
+		cap-sd-highspeed;
+		status = "disabled";
+	};
 };
diff --git a/arch/arm/boot/dts/r8a7740-armadillo800eva-reference.dts b/arch/arm/boot/dts/r8a7740-armadillo800eva-reference.dts
index 09ea22c26359..c638e4ab91b8 100644
--- a/arch/arm/boot/dts/r8a7740-armadillo800eva-reference.dts
+++ b/arch/arm/boot/dts/r8a7740-armadillo800eva-reference.dts
@@ -10,13 +10,14 @@
 
 /dts-v1/;
 /include/ "r8a7740.dtsi"
+#include <dt-bindings/gpio/gpio.h>
 
 / {
 	model = "armadillo 800 eva reference";
 	compatible = "renesas,armadillo800eva-reference", "renesas,r8a7740";
 
 	chosen {
-		bootargs = "console=tty0 console=ttySC1,115200 earlyprintk=sh-sci.1,115200 ignore_loglevel root=/dev/nfs ip=dhcp nfsroot=,rsize=4096,wsize=4096 rw";
+		bootargs = "console=tty0 console=ttySC1,115200 earlyprintk=sh-sci.1,115200 ignore_loglevel root=/dev/nfs ip=dhcp rw";
 	};
 
 	memory {
@@ -33,6 +34,21 @@
 		regulator-boot-on;
 	};
 
+	leds {
+		compatible = "gpio-leds";
+		led1 {
+			gpios = <&pfc 102 GPIO_ACTIVE_HIGH>;
+		};
+		led2 {
+			gpios = <&pfc 111 GPIO_ACTIVE_HIGH>;
+		};
+		led3 {
+			gpios = <&pfc 110 GPIO_ACTIVE_HIGH>;
+		};
+		led4 {
+			gpios = <&pfc 177 GPIO_ACTIVE_HIGH>;
+		};
+	};
 };
 
 &i2c0 {
@@ -41,5 +57,23 @@
 		reg = <0x55>;
 		interrupt-parent = <&irqpin1>;
 		interrupts = <2 0>; /* IRQ10: hwirq 2 on irqpin1 */
+		pinctrl-0 = <&st1232_pins>;
+		pinctrl-names = "default";
+		gpios = <&pfc 166 GPIO_ACTIVE_LOW>;
+	};
+};
+
+&pfc {
+	pinctrl-0 = <&scifa1_pins>;
+	pinctrl-names = "default";
+
+	scifa1_pins: scifa1 {
+		renesas,groups = "scifa1_data";
+		renesas,function = "scifa1";
+	};
+
+	st1232_pins: st1232 {
+		renesas,groups = "intc_irq10";
+		renesas,function = "intc";
 	};
 };
diff --git a/arch/arm/boot/dts/r8a7740-armadillo800eva.dts b/arch/arm/boot/dts/r8a7740-armadillo800eva.dts
index 93da655b2598..426cd9c3e1c4 100644
--- a/arch/arm/boot/dts/r8a7740-armadillo800eva.dts
+++ b/arch/arm/boot/dts/r8a7740-armadillo800eva.dts
@@ -16,7 +16,7 @@
 	compatible = "renesas,armadillo800eva";
 
 	chosen {
-		bootargs = "console=tty0 console=ttySC1,115200 earlyprintk=sh-sci.1,115200 ignore_loglevel root=/dev/nfs ip=dhcp nfsroot=,rsize=4096,wsize=4096 rw";
+		bootargs = "console=tty0 console=ttySC1,115200 earlyprintk=sh-sci.1,115200 ignore_loglevel root=/dev/nfs ip=dhcp rw";
 	};
 
 	memory {
diff --git a/arch/arm/boot/dts/r8a7740.dtsi b/arch/arm/boot/dts/r8a7740.dtsi
index 24e930643821..44d3d520e01f 100644
--- a/arch/arm/boot/dts/r8a7740.dtsi
+++ b/arch/arm/boot/dts/r8a7740.dtsi
@@ -32,6 +32,11 @@
 		      <0xc2000000 0x1000>;
 	};
 
+	pmu {
+		compatible = "arm,cortex-a9-pmu";
+		interrupts = <0 83 4>;
+	};
+
 	/* irqpin0: IRQ0 - IRQ7 */
 	irqpin0: irqpin@e6900000 {
 		compatible = "renesas,intc-irqpin";
@@ -139,4 +144,19 @@
 			      0 72 0x4
 			      0 73 0x4>;
 	};
+
+	pfc: pfc@e6050000 {
+		compatible = "renesas,pfc-r8a7740";
+		reg = <0xe6050000 0x8000>,
+		      <0xe605800c 0x20>;
+		gpio-controller;
+		#gpio-cells = <2>;
+	};
+
+	tpu: pwm@e6600000 {
+		compatible = "renesas,tpu-r8a7740", "renesas,tpu";
+		reg = <0xe6600000 0x100>;
+		status = "disabled";
+		#pwm-cells = <3>;
+	};
 };
diff --git a/arch/arm/boot/dts/r8a7778-bockw-reference.dts b/arch/arm/boot/dts/r8a7778-bockw-reference.dts
new file mode 100644
index 000000000000..9bb903a3230d
--- /dev/null
+++ b/arch/arm/boot/dts/r8a7778-bockw-reference.dts
@@ -0,0 +1,32 @@
+/*
+ * Reference Device Tree Source for the Bock-W board
+ *
+ * Copyright (C) 2013  Renesas Solutions Corp.
+ * Copyright (C) 2013  Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
+ *
+ * based on r8a7779
+ *
+ * Copyright (C) 2013 Renesas Solutions Corp.
+ * Copyright (C) 2013 Simon Horman
+ *
+ * This file is licensed under the terms of the GNU General Public License
+ * version 2.  This program is licensed "as is" without any warranty of any
+ * kind, whether express or implied.
+ */
+
+/dts-v1/;
+/include/ "r8a7778.dtsi"
+
+/ {
+	model = "bockw";
+	compatible = "renesas,bockw-reference", "renesas,r8a7778";
+
+	chosen {
+		bootargs = "console=ttySC0,115200 ignore_loglevel rw";
+	};
+
+	memory {
+		device_type = "memory";
+		reg = <0x60000000 0x10000000>;
+	};
+};
diff --git a/arch/arm/boot/dts/r8a7778-bockw.dts b/arch/arm/boot/dts/r8a7778-bockw.dts
index 0076b1e8a0fb..12bbebc9c955 100644
--- a/arch/arm/boot/dts/r8a7778-bockw.dts
+++ b/arch/arm/boot/dts/r8a7778-bockw.dts
@@ -22,7 +22,7 @@
 	compatible = "renesas,bockw", "renesas,r8a7778";
 
 	chosen {
-		bootargs = "console=ttySC0,115200 ignore_loglevel ip=dhcp root=/dev/nfs";
+		bootargs = "console=ttySC0,115200 ignore_loglevel ip=dhcp root=/dev/nfs rw";
 	};
 
 	memory {
diff --git a/arch/arm/boot/dts/r8a7778.dtsi b/arch/arm/boot/dts/r8a7778.dtsi
index 474373559bdc..3577aba82583 100644
--- a/arch/arm/boot/dts/r8a7778.dtsi
+++ b/arch/arm/boot/dts/r8a7778.dtsi
@@ -32,4 +32,69 @@
 		reg = <0xfe438000 0x1000>,
 		      <0xfe430000 0x100>;
 	};
+
+	gpio0: gpio@ffc40000 {
+		compatible = "renesas,gpio-r8a7778", "renesas,gpio-rcar";
+		reg = <0xffc40000 0x2c>;
+		interrupt-parent = <&gic>;
+		interrupts = <0 103 0x4>;
+		#gpio-cells = <2>;
+		gpio-controller;
+		gpio-ranges = <&pfc 0 0 32>;
+		#interrupt-cells = <2>;
+		interrupt-controller;
+	};
+
+	gpio1: gpio@ffc41000 {
+		compatible = "renesas,gpio-r8a7778", "renesas,gpio-rcar";
+		reg = <0xffc41000 0x2c>;
+		interrupt-parent = <&gic>;
+		interrupts = <0 103 0x4>;
+		#gpio-cells = <2>;
+		gpio-controller;
+		gpio-ranges = <&pfc 0 32 32>;
+		#interrupt-cells = <2>;
+		interrupt-controller;
+	};
+
+	gpio2: gpio@ffc42000 {
+		compatible = "renesas,gpio-r8a7778", "renesas,gpio-rcar";
+		reg = <0xffc42000 0x2c>;
+		interrupt-parent = <&gic>;
+		interrupts = <0 103 0x4>;
+		#gpio-cells = <2>;
+		gpio-controller;
+		gpio-ranges = <&pfc 0 64 32>;
+		#interrupt-cells = <2>;
+		interrupt-controller;
+	};
+
+	gpio3: gpio@ffc43000 {
+		compatible = "renesas,gpio-r8a7778", "renesas,gpio-rcar";
+		reg = <0xffc43000 0x2c>;
+		interrupt-parent = <&gic>;
+		interrupts = <0 103 0x4>;
+		#gpio-cells = <2>;
+		gpio-controller;
+		gpio-ranges = <&pfc 0 96 32>;
+		#interrupt-cells = <2>;
+		interrupt-controller;
+	};
+
+	gpio4: gpio@ffc44000 {
+		compatible = "renesas,gpio-r8a7778", "renesas,gpio-rcar";
+		reg = <0xffc44000 0x2c>;
+		interrupt-parent = <&gic>;
+		interrupts = <0 103 0x4>;
+		#gpio-cells = <2>;
+		gpio-controller;
+		gpio-ranges = <&pfc 0 128 27>;
+		#interrupt-cells = <2>;
+		interrupt-controller;
+	};
+
+	pfc: pfc@fffc0000 {
+		compatible = "renesas,pfc-r8a7778";
+		reg = <0xfffc000 0x118>;
+	};
 };
diff --git a/arch/arm/boot/dts/r8a7779-marzen-reference.dts b/arch/arm/boot/dts/r8a7779-marzen-reference.dts
index 72be4c87cfb5..6d5508392252 100644
--- a/arch/arm/boot/dts/r8a7779-marzen-reference.dts
+++ b/arch/arm/boot/dts/r8a7779-marzen-reference.dts
@@ -11,13 +11,14 @@
 
 /dts-v1/;
 /include/ "r8a7779.dtsi"
+#include <dt-bindings/gpio/gpio.h>
 
 / {
 	model = "marzen";
 	compatible = "renesas,marzen-reference", "renesas,r8a7779";
 
 	chosen {
-		bootargs = "console=ttySC2,115200 earlyprintk=sh-sci.2,115200 ignore_loglevel root=/dev/nfs ip=on";
+		bootargs = "console=ttySC2,115200 earlyprintk=sh-sci.2,115200 ignore_loglevel root=/dev/nfs ip=on rw";
 	};
 
 	memory {
@@ -37,6 +38,9 @@
 	lan0@18000000 {
 		compatible = "smsc,lan9220", "smsc,lan9115";
 		reg = <0x18000000 0x100>;
+		pinctrl-0 = <&lan0_pins>;
+		pinctrl-names = "default";
+
 		phy-mode = "mii";
 		interrupt-parent = <&gic>;
 		interrupts = <0 28 0x4>;
@@ -44,4 +48,49 @@
 		vddvario-supply = <&fixedregulator3v3>;
 		vdd33a-supply = <&fixedregulator3v3>;
 	};
+
+	leds {
+		compatible = "gpio-leds";
+		led2 {
+			gpios = <&gpio4 29 GPIO_ACTIVE_HIGH>;
+		};
+		led3 {
+			gpios = <&gpio4 30 GPIO_ACTIVE_HIGH>;
+		};
+		led4 {
+			gpios = <&gpio4 31 GPIO_ACTIVE_HIGH>;
+		};
+	};
+};
+
+&pfc {
+	pinctrl-0 = <&scif2_pins &scif4_pins &sdhi0_pins>;
+	pinctrl-names = "default";
+
+	lan0_pins: lan0 {
+		intc {
+			renesas,groups = "intc_irq1_b";
+			renesas,function = "intc";
+		};
+		lbsc {
+			renesas,groups = "lbsc_ex_cs0";
+			renesas,function = "lbsc";
+		};
+	};
+
+	scif2_pins: scif2 {
+		renesas,groups = "scif2_data_c";
+		renesas,function = "scif2";
+	};
+
+	scif4_pins: scif4 {
+		renesas,groups = "scif4_data";
+		renesas,function = "scif4";
+	};
+
+	sdhi0_pins: sdhi0 {
+		renesas,groups = "sdhi0_data4", "sdhi0_ctrl", "sdhi0_cd",
+				 "sdhi0_wp";
+		renesas,function = "sdhi0";
+	};
 };
diff --git a/arch/arm/boot/dts/r8a7779-marzen.dts b/arch/arm/boot/dts/r8a7779-marzen.dts
new file mode 100644
index 000000000000..f3f7f7999736
--- /dev/null
+++ b/arch/arm/boot/dts/r8a7779-marzen.dts
@@ -0,0 +1,27 @@
+/*
+ * Device Tree Source for the Marzen board
+ *
+ * Copyright (C) 2013 Renesas Solutions Corp.
+ * Copyright (C) 2013 Simon Horman
+ *
+ * This file is licensed under the terms of the GNU General Public License
+ * version 2.  This program is licensed "as is" without any warranty of any
+ * kind, whether express or implied.
+ */
+
+/dts-v1/;
+/include/ "r8a7779.dtsi"
+
+/ {
+	model = "marzen";
+	compatible = "renesas,marzen", "renesas,r8a7779";
+
+	chosen {
+		bootargs = "console=ttySC2,115200 earlyprintk=sh-sci.2,115200 ignore_loglevel root=/dev/nfs ip=on";
+	};
+
+	memory {
+		device_type = "memory";
+		reg = <0x60000000 0x40000000>;
+	};
+};
diff --git a/arch/arm/boot/dts/r8a7779.dtsi b/arch/arm/boot/dts/r8a7779.dtsi
index 7f146c6bf756..ebbe507fcbfa 100644
--- a/arch/arm/boot/dts/r8a7779.dtsi
+++ b/arch/arm/boot/dts/r8a7779.dtsi
@@ -48,6 +48,90 @@
                       <0xf0000100 0x100>;
         };
 
+	gpio0: gpio@ffc40000 {
+		compatible = "renesas,gpio-r8a7779", "renesas,gpio-rcar";
+		reg = <0xffc40000 0x2c>;
+		interrupt-parent = <&gic>;
+		interrupts = <0 141 0x4>;
+		#gpio-cells = <2>;
+		gpio-controller;
+		gpio-ranges = <&pfc 0 0 32>;
+		#interrupt-cells = <2>;
+		interrupt-controller;
+	};
+
+	gpio1: gpio@ffc41000 {
+		compatible = "renesas,gpio-r8a7779", "renesas,gpio-rcar";
+		reg = <0xffc41000 0x2c>;
+		interrupt-parent = <&gic>;
+		interrupts = <0 142 0x4>;
+		#gpio-cells = <2>;
+		gpio-controller;
+		gpio-ranges = <&pfc 0 32 32>;
+		#interrupt-cells = <2>;
+		interrupt-controller;
+	};
+
+	gpio2: gpio@ffc42000 {
+		compatible = "renesas,gpio-r8a7779", "renesas,gpio-rcar";
+		reg = <0xffc42000 0x2c>;
+		interrupt-parent = <&gic>;
+		interrupts = <0 143 0x4>;
+		#gpio-cells = <2>;
+		gpio-controller;
+		gpio-ranges = <&pfc 0 64 32>;
+		#interrupt-cells = <2>;
+		interrupt-controller;
+	};
+
+	gpio3: gpio@ffc43000 {
+		compatible = "renesas,gpio-r8a7779", "renesas,gpio-rcar";
+		reg = <0xffc43000 0x2c>;
+		interrupt-parent = <&gic>;
+		interrupts = <0 144 0x4>;
+		#gpio-cells = <2>;
+		gpio-controller;
+		gpio-ranges = <&pfc 0 96 32>;
+		#interrupt-cells = <2>;
+		interrupt-controller;
+	};
+
+	gpio4: gpio@ffc44000 {
+		compatible = "renesas,gpio-r8a7779", "renesas,gpio-rcar";
+		reg = <0xffc44000 0x2c>;
+		interrupt-parent = <&gic>;
+		interrupts = <0 145 0x4>;
+		#gpio-cells = <2>;
+		gpio-controller;
+		gpio-ranges = <&pfc 0 128 32>;
+		#interrupt-cells = <2>;
+		interrupt-controller;
+	};
+
+	gpio5: gpio@ffc45000 {
+		compatible = "renesas,gpio-r8a7779", "renesas,gpio-rcar";
+		reg = <0xffc45000 0x2c>;
+		interrupt-parent = <&gic>;
+		interrupts = <0 146 0x4>;
+		#gpio-cells = <2>;
+		gpio-controller;
+		gpio-ranges = <&pfc 0 160 32>;
+		#interrupt-cells = <2>;
+		interrupt-controller;
+	};
+
+	gpio6: gpio@ffc46000 {
+		compatible = "renesas,gpio-r8a7779", "renesas,gpio-rcar";
+		reg = <0xffc46000 0x2c>;
+		interrupt-parent = <&gic>;
+		interrupts = <0 147 0x4>;
+		#gpio-cells = <2>;
+		gpio-controller;
+		gpio-ranges = <&pfc 0 192 9>;
+		#interrupt-cells = <2>;
+		interrupt-controller;
+	};
+
 	irqpin0: irqpin@fe780010 {
 		compatible = "renesas,intc-irqpin";
 		#interrupt-cells = <2>;
@@ -65,7 +149,7 @@
 		sense-bitfield-width = <2>;
 	};
 
-	i2c0: i2c@0xffc70000 {
+	i2c0: i2c@ffc70000 {
 		#address-cells = <1>;
 		#size-cells = <0>;
 		compatible = "renesas,rmobile-iic";
@@ -74,7 +158,7 @@
 		interrupts = <0 79 0x4>;
 	};
 
-	i2c1: i2c@0xffc71000 {
+	i2c1: i2c@ffc71000 {
 		#address-cells = <1>;
 		#size-cells = <0>;
 		compatible = "renesas,rmobile-iic";
@@ -83,7 +167,7 @@
 		interrupts = <0 82 0x4>;
 	};
 
-	i2c2: i2c@0xffc72000 {
+	i2c2: i2c@ffc72000 {
 		#address-cells = <1>;
 		#size-cells = <0>;
 		compatible = "renesas,rmobile-iic";
@@ -92,7 +176,7 @@
 		interrupts = <0 80 0x4>;
 	};
 
-	i2c3: i2c@0xffc73000 {
+	i2c3: i2c@ffc73000 {
 		#address-cells = <1>;
 		#size-cells = <0>;
 		compatible = "renesas,rmobile-iic";
@@ -101,6 +185,11 @@
 		interrupts = <0 81 0x4>;
 	};
 
+	pfc: pfc@fffc0000 {
+		compatible = "renesas,pfc-r8a7779";
+		reg = <0xfffc0000 0x23c>;
+	};
+
 	thermal@ffc48000 {
 		compatible = "renesas,rcar-thermal";
 		reg = <0xffc48000 0x38>;
diff --git a/arch/arm/boot/dts/r8a7790-lager-reference.dts b/arch/arm/boot/dts/r8a7790-lager-reference.dts
new file mode 100644
index 000000000000..c462ef138922
--- /dev/null
+++ b/arch/arm/boot/dts/r8a7790-lager-reference.dts
@@ -0,0 +1,45 @@
+/*
+ * Device Tree Source for the Lager board
+ *
+ * Copyright (C) 2013 Renesas Solutions Corp.
+ *
+ * This file is licensed under the terms of the GNU General Public License
+ * version 2.  This program is licensed "as is" without any warranty of any
+ * kind, whether express or implied.
+ */
+
+/dts-v1/;
+/include/ "r8a7790.dtsi"
+#include <dt-bindings/gpio/gpio.h>
+
+/ {
+	model = "Lager";
+	compatible = "renesas,lager-reference", "renesas,r8a7790";
+
+	chosen {
+		bootargs = "console=ttySC6,115200 ignore_loglevel rw";
+	};
+
+	memory@40000000 {
+		device_type = "memory";
+		reg = <0 0x40000000 0 0x80000000>;
+	};
+
+	lbsc {
+		#address-cells = <1>;
+		#size-cells = <1>;
+	};
+
+	leds {
+		compatible = "gpio-leds";
+		led6 {
+			gpios = <&gpio4 22 GPIO_ACTIVE_HIGH>;
+		};
+		led7 {
+			gpios = <&gpio4 23 GPIO_ACTIVE_HIGH>;
+		};
+		led8 {
+			gpios = <&gpio5 17 GPIO_ACTIVE_HIGH>;
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/r8a7790-lager.dts b/arch/arm/boot/dts/r8a7790-lager.dts
index 09a84fce89d6..203bd089af29 100644
--- a/arch/arm/boot/dts/r8a7790-lager.dts
+++ b/arch/arm/boot/dts/r8a7790-lager.dts
@@ -16,7 +16,7 @@
 	compatible = "renesas,lager", "renesas,r8a7790";
 
 	chosen {
-		bootargs = "console=ttySC6,115200 ignore_loglevel";
+		bootargs = "console=ttySC6,115200 ignore_loglevel rw root=/dev/nfs ip=dhcp";
 	};
 
 	memory@40000000 {
diff --git a/arch/arm/boot/dts/r8a7790.dtsi b/arch/arm/boot/dts/r8a7790.dtsi
index 339d9b11721c..413b4c29e782 100644
--- a/arch/arm/boot/dts/r8a7790.dtsi
+++ b/arch/arm/boot/dts/r8a7790.dtsi
@@ -38,6 +38,78 @@
 		interrupts = <1 9 0xf04>;
 	};
 
+	gpio0: gpio@ffc40000 {
+		compatible = "renesas,gpio-r8a7790", "renesas,gpio-rcar";
+		reg = <0 0xffc40000 0 0x2c>;
+		interrupt-parent = <&gic>;
+		interrupts = <0 4 0x4>;
+		#gpio-cells = <2>;
+		gpio-controller;
+		gpio-ranges = <&pfc 0 0 32>;
+		#interrupt-cells = <2>;
+		interrupt-controller;
+	};
+
+	gpio1: gpio@ffc41000 {
+		compatible = "renesas,gpio-r8a7790", "renesas,gpio-rcar";
+		reg = <0 0xffc41000 0 0x2c>;
+		interrupt-parent = <&gic>;
+		interrupts = <0 5 0x4>;
+		#gpio-cells = <2>;
+		gpio-controller;
+		gpio-ranges = <&pfc 0 32 32>;
+		#interrupt-cells = <2>;
+		interrupt-controller;
+	};
+
+	gpio2: gpio@ffc42000 {
+		compatible = "renesas,gpio-r8a7790", "renesas,gpio-rcar";
+		reg = <0 0xffc42000 0 0x2c>;
+		interrupt-parent = <&gic>;
+		interrupts = <0 6 0x4>;
+		#gpio-cells = <2>;
+		gpio-controller;
+		gpio-ranges = <&pfc 0 64 32>;
+		#interrupt-cells = <2>;
+		interrupt-controller;
+	};
+
+	gpio3: gpio@ffc43000 {
+		compatible = "renesas,gpio-r8a7790", "renesas,gpio-rcar";
+		reg = <0 0xffc43000 0 0x2c>;
+		interrupt-parent = <&gic>;
+		interrupts = <0 7 0x4>;
+		#gpio-cells = <2>;
+		gpio-controller;
+		gpio-ranges = <&pfc 0 96 32>;
+		#interrupt-cells = <2>;
+		interrupt-controller;
+	};
+
+	gpio4: gpio@ffc44000 {
+		compatible = "renesas,gpio-r8a7790", "renesas,gpio-rcar";
+		reg = <0 0xffc44000 0 0x2c>;
+		interrupt-parent = <&gic>;
+		interrupts = <0 8 0x4>;
+		#gpio-cells = <2>;
+		gpio-controller;
+		gpio-ranges = <&pfc 0 128 32>;
+		#interrupt-cells = <2>;
+		interrupt-controller;
+	};
+
+	gpio5: gpio@ffc45000 {
+		compatible = "renesas,gpio-r8a7790", "renesas,gpio-rcar";
+		reg = <0 0xffc45000 0 0x2c>;
+		interrupt-parent = <&gic>;
+		interrupts = <0 9 0x4>;
+		#gpio-cells = <2>;
+		gpio-controller;
+		gpio-ranges = <&pfc 0 160 32>;
+		#interrupt-cells = <2>;
+		interrupt-controller;
+	};
+
 	timer {
 		compatible = "arm,armv7-timer";
 		interrupts = <1 13 0xf08>,
@@ -54,4 +126,63 @@
 		interrupt-parent = <&gic>;
 		interrupts = <0 0 4>, <0 1 4>, <0 2 4>,	<0 3 4>;
 	};
+
+	mmcif0: mmcif@ee200000 {
+		compatible = "renesas,sh-mmcif";
+		reg = <0 0xee200000 0 0x80>;
+		interrupt-parent = <&gic>;
+		interrupts = <0 169 0x4>;
+		reg-io-width = <4>;
+		status = "disabled";
+	};
+
+	mmcif1: mmcif@ee220000 {
+		compatible = "renesas,sh-mmcif";
+		reg = <0 0xee220000 0 0x80>;
+		interrupt-parent = <&gic>;
+		interrupts = <0 170 0x4>;
+		reg-io-width = <4>;
+		status = "disabled";
+	};
+
+	pfc: pfc@e6060000 {
+		compatible = "renesas,pfc-r8a7790";
+		reg = <0 0xe6060000 0 0x250>;
+	};
+
+	sdhi0: sdhi@ee100000 {
+		compatible = "renesas,sdhi-r8a7790";
+		reg = <0 0xee100000 0 0x100>;
+		interrupt-parent = <&gic>;
+		interrupts = <0 165 4>;
+		cap-sd-highspeed;
+		status = "disabled";
+	};
+
+	sdhi1: sdhi@ee120000 {
+		compatible = "renesas,sdhi-r8a7790";
+		reg = <0 0xee120000 0 0x100>;
+		interrupt-parent = <&gic>;
+		interrupts = <0 166 4>;
+		cap-sd-highspeed;
+		status = "disabled";
+	};
+
+	sdhi2: sdhi@ee140000 {
+		compatible = "renesas,sdhi-r8a7790";
+		reg = <0 0xee140000 0 0x100>;
+		interrupt-parent = <&gic>;
+		interrupts = <0 167 4>;
+		cap-sd-highspeed;
+		status = "disabled";
+	};
+
+	sdhi3: sdhi@ee160000 {
+		compatible = "renesas,sdhi-r8a7790";
+		reg = <0 0xee160000 0 0x100>;
+		interrupt-parent = <&gic>;
+		interrupts = <0 168 4>;
+		cap-sd-highspeed;
+		status = "disabled";
+	};
 };
diff --git a/arch/arm/boot/dts/sama5d3.dtsi b/arch/arm/boot/dts/sama5d3.dtsi
index a1d5e25a6698..b7f49615120d 100644
--- a/arch/arm/boot/dts/sama5d3.dtsi
+++ b/arch/arm/boot/dts/sama5d3.dtsi
@@ -48,6 +48,11 @@
 		};
 	};
 
+	pmu {
+		compatible = "arm,cortex-a5-pmu";
+		interrupts = <46 IRQ_TYPE_LEVEL_HIGH 0>;
+	};
+
 	memory {
 		reg = <0x20000000 0x8000000>;
 	};
@@ -1029,21 +1034,30 @@
 			compatible = "atmel,at91rm9200-nand";
 			#address-cells = <1>;
 			#size-cells = <1>;
+			ranges;
 			reg = <	0x60000000 0x01000000	/* EBI CS3 */
 				0xffffc070 0x00000490	/* SMC PMECC regs */
 				0xffffc500 0x00000100	/* SMC PMECC Error Location regs */
-				0x00100000 0x00100000	/* ROM code */
-				0x70000000 0x10000000	/* NFC Command Registers */
-				0xffffc000 0x00000070	/* NFC HSMC regs */
-				0x00200000 0x00100000	/* NFC SRAM banks */
+				0x00110000 0x00018000	/* ROM code */
 				>;
 			interrupts = <5 IRQ_TYPE_LEVEL_HIGH 6>;
 			atmel,nand-addr-offset = <21>;
 			atmel,nand-cmd-offset = <22>;
 			pinctrl-names = "default";
 			pinctrl-0 = <&pinctrl_nand0_ale_cle>;
-			atmel,pmecc-lookup-table-offset = <0x10000 0x18000>;
+			atmel,pmecc-lookup-table-offset = <0x0 0x8000>;
 			status = "disabled";
+
+			nfc@70000000 {
+				compatible = "atmel,sama5d3-nfc";
+				#address-cells = <1>;
+				#size-cells = <1>;
+				reg = <
+					0x70000000 0x10000000	/* NFC Command Registers */
+					0xffffc000 0x00000070	/* NFC HSMC regs */
+					0x00200000 0x00100000	/* NFC SRAM banks */
+					>;
+			};
 		};
 	};
 };
diff --git a/arch/arm/boot/dts/sama5d3xcm.dtsi b/arch/arm/boot/dts/sama5d3xcm.dtsi
index 1f8050813a54..31ed9e3bb649 100644
--- a/arch/arm/boot/dts/sama5d3xcm.dtsi
+++ b/arch/arm/boot/dts/sama5d3xcm.dtsi
@@ -47,8 +47,6 @@
 			atmel,has-pmecc;
 			atmel,pmecc-cap = <4>;
 			atmel,pmecc-sector-size = <512>;
-			atmel,has-nfc;
-			atmel,use-nfc-sram;
 			nand-on-flash-bbt;
 			status = "okay";
 
diff --git a/arch/arm/boot/dts/sama5d3xmb.dtsi b/arch/arm/boot/dts/sama5d3xmb.dtsi
index 8a9e05d8a4b8..dba739b6ef36 100644
--- a/arch/arm/boot/dts/sama5d3xmb.dtsi
+++ b/arch/arm/boot/dts/sama5d3xmb.dtsi
@@ -81,6 +81,14 @@
 
 			macb1: ethernet@f802c000 {
 				phy-mode = "rmii";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+				phy0: ethernet-phy@1 {
+					interrupt-parent = <&pioE>;
+					interrupts = <30 IRQ_TYPE_EDGE_FALLING>;
+					reg = <1>;
+				};
 			};
 
 			pinctrl@fffff200 {
diff --git a/arch/arm/boot/dts/sh7372.dtsi b/arch/arm/boot/dts/sh7372.dtsi
index 7bf020ecadf5..249f65be2a50 100644
--- a/arch/arm/boot/dts/sh7372.dtsi
+++ b/arch/arm/boot/dts/sh7372.dtsi
@@ -23,4 +23,12 @@
 			reg = <0x0>;
 		};
 	};
+
+	pfc: pfc@e6050000 {
+		compatible = "renesas,pfc-sh7372";
+		reg = <0xe6050000 0x8000>,
+		      <0xe605801c 0x1c>;
+		gpio-controller;
+		#gpio-cells = <2>;
+	};
 };
diff --git a/arch/arm/boot/dts/sh73a0-kzm9g-reference.dts b/arch/arm/boot/dts/sh73a0-kzm9g-reference.dts
index b6f759e830ed..212230629f27 100644
--- a/arch/arm/boot/dts/sh73a0-kzm9g-reference.dts
+++ b/arch/arm/boot/dts/sh73a0-kzm9g-reference.dts
@@ -13,6 +13,7 @@
 
 /dts-v1/;
 /include/ "sh73a0.dtsi"
+#include <dt-bindings/gpio/gpio.h>
 
 / {
 	model = "KZM-A9-GT";
@@ -32,7 +33,7 @@
 	};
 
 	chosen {
-		bootargs = "console=tty0 console=ttySC4,115200 root=/dev/nfs ip=dhcp ignore_loglevel earlyprintk=sh-sci.4,115200";
+		bootargs = "console=tty0 console=ttySC4,115200 root=/dev/nfs ip=dhcp ignore_loglevel earlyprintk=sh-sci.4,115200 rw";
 	};
 
 	memory {
@@ -58,6 +59,24 @@
 		regulator-boot-on;
 	};
 
+	vmmc_sdhi0: regulator@2 {
+	        compatible = "regulator-fixed";
+		regulator-name = "SDHI0 Vcc";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		gpio = <&pfc 15 GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+	};
+
+	vmmc_sdhi2: regulator@3 {
+	        compatible = "regulator-fixed";
+		regulator-name = "SDHI2 Vcc";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		gpio = <&pfc 14 GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+	};
+
 	lan9220@10000000 {
 		compatible = "smsc,lan9220", "smsc,lan9115";
 		reg = <0x10000000 0x100>;
@@ -70,6 +89,22 @@
 		vddvario-supply = <&reg_1p8v>;
 		vdd33a-supply = <&reg_3p3v>;
 	};
+
+	leds {
+		compatible = "gpio-leds";
+		led1 {
+			gpios = <&pfc 20 GPIO_ACTIVE_LOW>;
+		};
+		led2 {
+			gpios = <&pfc 21 GPIO_ACTIVE_LOW>;
+		};
+		led3 {
+			gpios = <&pfc 22 GPIO_ACTIVE_LOW>;
+		};
+		led4 {
+			gpios = <&pfc 23 GPIO_ACTIVE_LOW>;
+		};
+	};
 };
 
 &i2c0 {
@@ -145,20 +180,71 @@
 	};
 };
 
+&i2c3 {
+	pinctrl-0 = <&i2c3_pins>;
+	pinctrl-names = "default";
+};
+
 &mmcif {
+	pinctrl-0 = <&mmcif_pins>;
+	pinctrl-names = "default";
+
 	bus-width = <8>;
 	vmmc-supply = <&reg_1p8v>;
 	status = "okay";
 };
 
+&pfc {
+	pinctrl-0 = <&scifa4_pins>;
+	pinctrl-names = "default";
+
+	i2c3_pins: i2c3 {
+		renesas,groups = "i2c3_1";
+		renesas,function = "i2c3";
+	};
+
+	mmcif_pins: mmcif {
+		mux {
+			renesas,groups = "mmc0_data8_0", "mmc0_ctrl_0";
+			renesas,function = "mmc0";
+		};
+		cfg {
+			renesas,groups = "mmc0_data8_0";
+			renesas,pins = "PORT279";
+			bias-pull-up;
+		};
+	};
+
+	scifa4_pins: scifa4 {
+		renesas,groups = "scifa4_data", "scifa4_ctrl";
+		renesas,function = "scifa4";
+	};
+
+	sdhi0_pins: sdhi0 {
+		renesas,groups = "sdhi0_data4", "sdhi0_ctrl", "sdhi0_cd", "sdhi0_wp";
+		renesas,function = "sdhi0";
+	};
+
+	sdhi2_pins: sdhi2 {
+		renesas,groups = "sdhi2_data4", "sdhi2_ctrl";
+		renesas,function = "sdhi2";
+	};
+};
+
 &sdhi0 {
-	vmmc-supply = <&reg_3p3v>;
+	pinctrl-0 = <&sdhi0_pins>;
+	pinctrl-names = "default";
+
+	vmmc-supply = <&vmmc_sdhi0>;
 	bus-width = <4>;
 	status = "okay";
 };
 
 &sdhi2 {
-	vmmc-supply = <&reg_3p3v>;
+	pinctrl-0 = <&sdhi2_pins>;
+	pinctrl-names = "default";
+
+	vmmc-supply = <&vmmc_sdhi2>;
 	bus-width = <4>;
 	broken-cd;
 	status = "okay";
diff --git a/arch/arm/boot/dts/sh73a0-kzm9g.dts b/arch/arm/boot/dts/sh73a0-kzm9g.dts
index 7c4071e7790c..0f1ca7792c46 100644
--- a/arch/arm/boot/dts/sh73a0-kzm9g.dts
+++ b/arch/arm/boot/dts/sh73a0-kzm9g.dts
@@ -16,7 +16,7 @@
 	compatible = "renesas,kzm9g", "renesas,sh73a0";
 
 	chosen {
-		bootargs = "console=tty0 console=ttySC4,115200 root=/dev/nfs ip=dhcp ignore_loglevel earlyprintk=sh-sci.4,115200";
+		bootargs = "console=tty0 console=ttySC4,115200 root=/dev/nfs ip=dhcp ignore_loglevel earlyprintk=sh-sci.4,115200 rw";
 	};
 
 	memory {
diff --git a/arch/arm/boot/dts/sh73a0.dtsi b/arch/arm/boot/dts/sh73a0.dtsi
index b97750256003..3955c7606a6f 100644
--- a/arch/arm/boot/dts/sh73a0.dtsi
+++ b/arch/arm/boot/dts/sh73a0.dtsi
@@ -38,6 +38,12 @@
 		      <0xf0000100 0x100>;
 	};
 
+	pmu {
+		compatible = "arm,cortex-a9-pmu";
+		interrupts = <0 55 4>,
+			     <0 56 4>;
+	};
+
 	irqpin0: irqpin@e6900000 {
 		compatible = "renesas,intc-irqpin";
 		#interrupt-cells = <2>;
@@ -190,7 +196,7 @@
 	};
 
 	sdhi0: sdhi@ee100000 {
-		compatible = "renesas,r8a7740-sdhi";
+		compatible = "renesas,sdhi-r8a7740";
 		reg = <0xee100000 0x100>;
 		interrupt-parent = <&gic>;
 		interrupts = <0 83 4
@@ -202,7 +208,7 @@
 
 	/* SDHI1 and SDHI2 have no CD pins, no need for CD IRQ */
 	sdhi1: sdhi@ee120000 {
-		compatible = "renesas,r8a7740-sdhi";
+		compatible = "renesas,sdhi-r8a7740";
 		reg = <0xee120000 0x100>;
 		interrupt-parent = <&gic>;
 		interrupts = <0 88 4
@@ -213,7 +219,7 @@
 	};
 
 	sdhi2: sdhi@ee140000 {
-		compatible = "renesas,r8a7740-sdhi";
+		compatible = "renesas,sdhi-r8a7740";
 		reg = <0xee140000 0x100>;
 		interrupt-parent = <&gic>;
 		interrupts = <0 104 4
@@ -222,4 +228,12 @@
 		cap-sd-highspeed;
 		status = "disabled";
 	};
+
+	pfc: pfc@e6050000 {
+		compatible = "renesas,pfc-sh73a0";
+		reg = <0xe6050000 0x8000>,
+		      <0xe605801c 0x1c>;
+		gpio-controller;
+		#gpio-cells = <2>;
+	};
 };
diff --git a/arch/arm/boot/dts/skeleton64.dtsi b/arch/arm/boot/dts/skeleton64.dtsi
index 15994158a998..b5d7f36f33de 100644
--- a/arch/arm/boot/dts/skeleton64.dtsi
+++ b/arch/arm/boot/dts/skeleton64.dtsi
@@ -9,5 +9,5 @@
 	#size-cells = <2>;
 	chosen { };
 	aliases { };
-	memory { device_type = "memory"; reg = <0 0>; };
+	memory { device_type = "memory"; reg = <0 0 0 0>; };
 };
diff --git a/arch/arm/boot/dts/socfpga.dtsi b/arch/arm/boot/dts/socfpga.dtsi
index bee62a2cf6d6..e273fa993b8c 100644
--- a/arch/arm/boot/dts/socfpga.dtsi
+++ b/arch/arm/boot/dts/socfpga.dtsi
@@ -476,25 +476,25 @@
 		};
 
 		timer0: timer0@ffc08000 {
-			compatible = "snps,dw-apb-timer-sp";
+			compatible = "snps,dw-apb-timer";
 			interrupts = <0 167 4>;
 			reg = <0xffc08000 0x1000>;
 		};
 
 		timer1: timer1@ffc09000 {
-			compatible = "snps,dw-apb-timer-sp";
+			compatible = "snps,dw-apb-timer";
 			interrupts = <0 168 4>;
 			reg = <0xffc09000 0x1000>;
 		};
 
 		timer2: timer2@ffd00000 {
-			compatible = "snps,dw-apb-timer-osc";
+			compatible = "snps,dw-apb-timer";
 			interrupts = <0 169 4>;
 			reg = <0xffd00000 0x1000>;
 		};
 
 		timer3: timer3@ffd01000 {
-			compatible = "snps,dw-apb-timer-osc";
+			compatible = "snps,dw-apb-timer";
 			interrupts = <0 170 4>;
 			reg = <0xffd01000 0x1000>;
 		};
diff --git a/arch/arm/boot/dts/ste-ccu8540-pinctrl.dtsi b/arch/arm/boot/dts/ste-ccu8540-pinctrl.dtsi
new file mode 100644
index 000000000000..e0799966bc25
--- /dev/null
+++ b/arch/arm/boot/dts/ste-ccu8540-pinctrl.dtsi
@@ -0,0 +1,196 @@
+/*
+ * Copyright 2012 ST-Ericsson
+ *
+ * The code contained herein is licensed under the GNU General Public
+ * License. You may obtain a copy of the GNU General Public License
+ * Version 2 or later at the following locations:
+ *
+ * http://www.opensource.org/licenses/gpl-license.html
+ * http://www.gnu.org/copyleft/gpl.html
+ */
+#include "ste-nomadik-pinctrl.dtsi"
+
+/ {
+	soc {
+		pinctrl {
+			uart0 {
+				uart0_default_mux: uart0_mux {
+					default_mux {
+						ste,function = "u0";
+						ste,pins = "u0_a_1";
+					};
+				};
+
+				uart0_default_mode: uart0_default {
+					default_cfg1 {
+						ste,pins = "GPIO0", "GPIO2";
+						ste,config = <&in_pu>;
+					};
+
+					default_cfg2 {
+						ste,pins = "GPIO1", "GPIO3";
+						ste,config = <&out_hi>;
+					};
+				};
+
+				uart0_sleep_mode: uart0_sleep {
+					sleep_cfg1 {
+						ste,pins = "GPIO0", "GPIO2";
+						ste,config = <&slpm_in_pu>;
+					};
+
+					sleep_cfg2 {
+						ste,pins = "GPIO1", "GPIO3";
+						ste,config = <&slpm_out_hi>;
+					};
+				};
+			};
+
+			uart2 {
+				uart2_default_mode: uart2_default {
+					default_mux {
+						ste,function = "u2";
+						ste,pins = "u2txrx_a_1";
+					};
+
+					default_cfg1 {
+						ste,pins = "GPIO120";
+						ste,config = <&in_pu>;
+					};
+
+					default_cfg2 {
+						ste,pins = "GPIO121";
+						ste,config = <&out_hi>;
+					};
+				};
+
+				uart2_sleep_mode: uart2_sleep {
+					sleep_cfg1 {
+						ste,pins = "GPIO120";
+						ste,config = <&slpm_in_pu>;
+					};
+
+					sleep_cfg2 {
+						ste,pins = "GPIO121";
+						ste,config = <&slpm_out_hi>;
+					};
+				};
+			};
+
+			i2c0 {
+				i2c0_default_mux: i2c_mux {
+					default_mux {
+						ste,function = "i2c0";
+						ste,pins = "i2c0_a_1";
+					};
+				};
+
+				i2c0_default_mode: i2c_default {
+					default_cfg1 {
+						ste,pins = "GPIO147", "GPIO148";
+						ste,config = <&in_pu>;
+					};
+				};
+
+				i2c0_sleep_mode: i2c_sleep {
+					sleep_cfg1 {
+						ste,pins = "GPIO147", "GPIO148";
+						ste,config = <&slpm_in_pu>;
+					};
+				};
+			};
+
+			i2c1 {
+				i2c1_default_mux: i2c_mux {
+					default_mux {
+						ste,function = "i2c1";
+						ste,pins = "i2c1_b_2";
+					};
+				};
+
+				i2c1_default_mode: i2c_default {
+					default_cfg1 {
+						ste,pins = "GPIO16", "GPIO17";
+						ste,config = <&in_pu>;
+					};
+				};
+
+				i2c1_sleep_mode: i2c_sleep {
+					sleep_cfg1 {
+						ste,pins = "GPIO16", "GPIO17";
+						ste,config = <&slpm_in_pu>;
+					};
+				};
+			};
+
+			i2c2 {
+				i2c2_default_mux: i2c_mux {
+					default_mux {
+						ste,function = "i2c2";
+						ste,pins = "i2c2_b_2";
+					};
+				};
+
+				i2c2_default_mode: i2c_default {
+					default_cfg1 {
+						ste,pins = "GPIO10", "GPIO11";
+						ste,config = <&in_pu>;
+					};
+				};
+
+				i2c2_sleep_mode: i2c_sleep {
+					sleep_cfg1 {
+						ste,pins = "GPIO11", "GPIO11";
+						ste,config = <&slpm_in_pu>;
+					};
+				};
+			};
+
+			i2c4 {
+				i2c4_default_mux: i2c_mux {
+					default_mux {
+						ste,function = "i2c4";
+						ste,pins = "i2c4_b_2";
+					};
+				};
+
+				i2c4_default_mode: i2c_default {
+					default_cfg1 {
+						ste,pins = "GPIO122", "GPIO123";
+						ste,config = <&in_pu>;
+					};
+				};
+
+				i2c4_sleep_mode: i2c_sleep {
+					sleep_cfg1 {
+						ste,pins = "GPIO122", "GPIO123";
+						ste,config = <&slpm_in_pu>;
+					};
+				};
+			};
+
+			i2c5 {
+				i2c5_default_mux: i2c_mux {
+					default_mux {
+						ste,function = "i2c5";
+						ste,pins = "i2c5_c_2";
+					};
+				};
+
+				i2c5_default_mode: i2c_default {
+					default_cfg1 {
+						ste,pins = "GPIO118", "GPIO119";
+						ste,config = <&in_pu>;
+					};
+				};
+
+				i2c5_sleep_mode: i2c_sleep {
+					sleep_cfg1 {
+						ste,pins = "GPIO118", "GPIO119";
+						ste,config = <&slpm_in_pu>;
+					};
+				};
+			};
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/ste-ccu8540.dts b/arch/arm/boot/dts/ste-ccu8540.dts
new file mode 100644
index 000000000000..7f3baf51a3a9
--- /dev/null
+++ b/arch/arm/boot/dts/ste-ccu8540.dts
@@ -0,0 +1,86 @@
+/*
+ * Copyright 2013 ST-Ericsson AB
+ *
+ * The code contained herein is licensed under the GNU General Public
+ * License. You may obtain a copy of the GNU General Public License
+ * Version 2 or later at the following locations:
+ *
+ * http://www.opensource.org/licenses/gpl-license.html
+ * http://www.gnu.org/copyleft/gpl.html
+ */
+
+/dts-v1/;
+#include "ste-dbx5x0.dtsi"
+#include "ste-ccu8540-pinctrl.dtsi"
+
+/ {
+	model = "ST-Ericsson U8540 platform with Device Tree";
+	compatible = "st-ericsson,ccu8540", "st-ericsson,u8540";
+
+	memory@0 {
+		reg = <0x20000000 0x1f000000>, <0xc0000000 0x3f000000>;
+	};
+
+	soc {
+		pinctrl {
+			compatible = "stericsson,db8540-pinctrl";
+		};
+
+		prcmu@80157000 {
+			reg = <0x80157000 0x2000>, <0x801b0000 0x8000>, <0x801b8000 0x3000>;
+			reg-names = "prcmu", "prcmu-tcpm", "prcmu-tcdm";
+		};
+
+		uart@80120000 {
+			pinctrl-names = "default", "sleep";
+			pinctrl-0 = <&uart0_default_mux>, <&uart0_default_mode>;
+			pinctrl-1 = <&uart0_sleep_mode>;
+			status = "okay";
+		};
+
+		uart@80121000 {
+			status = "okay";
+		};
+
+		uart@80007000 {
+			pinctrl-names = "default", "sleep";
+			pinctrl-0 = <&uart2_default_mode>;
+			pinctrl-1 = <&uart2_sleep_mode>;
+			status = "okay";
+		};
+
+		i2c0: i2c@80004000 {
+			pinctrl-names = "default","sleep";
+			pinctrl-0 = <&i2c0_default_mux>, <&i2c0_default_mode>;
+			pinctrl-1 = <&i2c0_sleep_mode>;
+		};
+
+		i2c1: i2c@80122000 {
+			pinctrl-names = "default","sleep";
+			pinctrl-0 = <&i2c1_default_mux>, <&i2c1_default_mode>;
+			pinctrl-1 = <&i2c1_sleep_mode>;
+		};
+
+		i2c2: i2c@80128000 {
+			pinctrl-names = "default","sleep";
+			pinctrl-0 = <&i2c2_default_mux>, <&i2c2_default_mode>;
+			pinctrl-1 = <&i2c2_sleep_mode>;
+		};
+
+		i2c3: i2c@80110000 {
+			status = "disabled";
+		};
+
+		i2c4: i2c@8012a000 {
+			pinctrl-names = "default","sleep";
+			pinctrl-0 = <&i2c4_default_mux>, <&i2c4_default_mode>;
+			pinctrl-1 = <&i2c4_sleep_mode>;
+		};
+
+		i2c5: i2c@80001000 {
+			pinctrl-names = "default","sleep";
+			pinctrl-0 = <&i2c5_default_mux>, <&i2c5_default_mode>;
+			pinctrl-1 = <&i2c5_sleep_mode>;
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/ccu9540.dts b/arch/arm/boot/dts/ste-ccu9540.dts
index ed29ec7288e4..229508750890 100644
--- a/arch/arm/boot/dts/ccu9540.dts
+++ b/arch/arm/boot/dts/ste-ccu9540.dts
@@ -10,7 +10,7 @@
  */
 
 /dts-v1/;
-#include "dbx5x0.dtsi"
+#include "ste-dbx5x0.dtsi"
 
 / {
 	model = "ST-Ericsson CCU9540 platform with Device Tree";
diff --git a/arch/arm/boot/dts/dbx5x0.dtsi b/arch/arm/boot/dts/ste-dbx5x0.dtsi
index a1529455f081..1c1091eedade 100644
--- a/arch/arm/boot/dts/dbx5x0.dtsi
+++ b/arch/arm/boot/dts/ste-dbx5x0.dtsi
@@ -245,7 +245,7 @@
 					     <22 IRQ_TYPE_LEVEL_HIGH>;
 				interrupt-names = "IRQ_HOTMON_LOW", "IRQ_HOTMON_HIGH";
 				status = "disabled";
-			 };
+			};
 
 			db8500-prcmu-regulators {
 				compatible = "stericsson,db8500-prcmu-regulator";
@@ -457,8 +457,36 @@
 					stericsson,earpeice-cmv = <950>; /* Units in mV. */
 				};
 
+				ext_regulators: ab8500-ext-regulators {
+					compatible = "stericsson,ab8500-ext-regulator";
+
+					ab8500_ext1_reg: ab8500_ext1 {
+						regulator-compatible = "ab8500_ext1";
+						regulator-min-microvolt = <1800000>;
+						regulator-max-microvolt = <1800000>;
+						regulator-boot-on;
+						regulator-always-on;
+					};
+
+					ab8500_ext2_reg: ab8500_ext2 {
+						regulator-compatible = "ab8500_ext2";
+						regulator-min-microvolt = <1360000>;
+						regulator-max-microvolt = <1360000>;
+						regulator-boot-on;
+						regulator-always-on;
+					};
+
+					ab8500_ext3_reg: ab8500_ext3 {
+						regulator-compatible = "ab8500_ext3";
+						regulator-min-microvolt = <3400000>;
+						regulator-max-microvolt = <3400000>;
+						regulator-boot-on;
+					};
+				};
+
 				ab8500-regulators {
 					compatible = "stericsson,ab8500-regulator";
+					vin-supply = <&ab8500_ext3_reg>;
 
 					// supplies to the display/camera
 					ab8500_ldo_aux1_reg: ab8500_ldo_aux1 {
diff --git a/arch/arm/boot/dts/href.dtsi b/arch/arm/boot/dts/ste-href.dtsi
index 9db41b9d8358..370e03f5e7b2 100644
--- a/arch/arm/boot/dts/href.dtsi
+++ b/arch/arm/boot/dts/ste-href.dtsi
@@ -10,7 +10,7 @@
  */
 
 #include <dt-bindings/interrupt-controller/irq.h>
-#include "dbx5x0.dtsi"
+#include "ste-dbx5x0.dtsi"
 
 / {
 	memory {
diff --git a/arch/arm/boot/dts/hrefprev60.dts b/arch/arm/boot/dts/ste-hrefprev60.dts
index c6bb07df2d1d..d8d3b99ab007 100644
--- a/arch/arm/boot/dts/hrefprev60.dts
+++ b/arch/arm/boot/dts/ste-hrefprev60.dts
@@ -10,9 +10,9 @@
  */
 
 /dts-v1/;
-#include "dbx5x0.dtsi"
-#include "href.dtsi"
-#include "stuib.dtsi"
+#include "ste-dbx5x0.dtsi"
+#include "ste-href.dtsi"
+#include "ste-stuib.dtsi"
 
 / {
 	model = "ST-Ericsson HREF (pre-v60) platform with Device Tree";
diff --git a/arch/arm/boot/dts/hrefv60plus.dts b/arch/arm/boot/dts/ste-hrefv60plus.dts
index 3d580d6447f9..6e52ebbf113f 100644
--- a/arch/arm/boot/dts/hrefv60plus.dts
+++ b/arch/arm/boot/dts/ste-hrefv60plus.dts
@@ -10,9 +10,9 @@
  */
 
 /dts-v1/;
-#include "dbx5x0.dtsi"
-#include "href.dtsi"
-#include "stuib.dtsi"
+#include "ste-dbx5x0.dtsi"
+#include "ste-href.dtsi"
+#include "ste-stuib.dtsi"
 
 / {
 	model = "ST-Ericsson HREF (v60+) platform with Device Tree";
diff --git a/arch/arm/boot/dts/ste-nomadik-pinctrl.dtsi b/arch/arm/boot/dts/ste-nomadik-pinctrl.dtsi
new file mode 100644
index 000000000000..efddee9403c4
--- /dev/null
+++ b/arch/arm/boot/dts/ste-nomadik-pinctrl.dtsi
@@ -0,0 +1,95 @@
+/*
+ * Copyright 2012 ST-Ericsson
+ *
+ * The code contained herein is licensed under the GNU General Public
+ * License. You may obtain a copy of the GNU General Public License
+ * Version 2 or later at the following locations:
+ *
+ * http://www.opensource.org/licenses/gpl-license.html
+ * http://www.gnu.org/copyleft/gpl.html
+ */
+#include <dt-bindings/pinctrl/nomadik.h>
+
+/ {
+	in_nopull: in_nopull {
+		ste,input = <INPUT_NOPULL>;
+	};
+
+	in_pu: input_pull_up {
+		ste,input = <INPUT_PULLUP>;
+	};
+
+	in_pd: input_pull_down {
+		ste,input = <INPUT_PULLDOWN>;
+	};
+
+	out_hi: output_high {
+		ste,output = <OUTPUT_HIGH>;
+	};
+
+	out_lo: output_low {
+		ste,output = <OUTPUT_LOW>;
+	};
+
+	gpio_out_lo: gpio_output_low {
+		ste,gpio = <GPIOMODE_ENABLED>;
+		ste,output = <OUTPUT_LOW>;
+	};
+
+	slpm_in_pu: slpm_in_pu {
+		ste,sleep = <SLPM_ENABLED>;
+		ste,sleep-input = <SLPM_INPUT_PULLUP>;
+		ste,sleep-wakeup = <SLPM_WAKEUP_ENABLE>;
+	};
+
+	slpm_in_wkup_pdis: slpm_in_wkup_pdis {
+		ste,sleep = <SLPM_ENABLED>;
+		ste,sleep-input = <SLPM_DIR_INPUT>;
+		ste,sleep-wakeup = <SLPM_WAKEUP_ENABLE>;
+		ste,sleep-pull-disable = <SLPM_PDIS_DISABLED>;
+	};
+
+	slpm_out_lo: slpm_out_lo {
+		ste,sleep = <SLPM_ENABLED>;
+		ste,sleep-output = <SLPM_OUTPUT_LOW>;
+		ste,sleep-wakeup = <SLPM_WAKEUP_ENABLE>;
+	};
+
+	slpm_out_hi: slpm_out_hi {
+		ste,sleep = <SLPM_ENABLED>;
+		ste,sleep-output = <SLPM_OUTPUT_HIGH>;
+		ste,sleep-wakeup = <SLPM_WAKEUP_ENABLE>;
+	};
+
+	slpm_out_hi_wkup_pdis: slpm_out_hi_wkup_pdis {
+		ste,sleep = <SLPM_ENABLED>;
+		ste,sleep-output = <SLPM_OUTPUT_HIGH>;
+		ste,sleep-wakeup = <SLPM_WAKEUP_ENABLE>;
+		ste,sleep-pull-disable = <SLPM_PDIS_DISABLED>;
+	};
+
+	slpm_out_wkup_pdis: slpm_out_wkup_pdis {
+		ste,sleep = <SLPM_ENABLED>;
+		ste,sleep-output = <SLPM_DIR_OUTPUT>;
+		ste,sleep-wakeup = <SLPM_WAKEUP_ENABLE>;
+		ste,sleep-pull-disable = <SLPM_PDIS_DISABLED>;
+	};
+
+	in_wkup_pdis: in_wkup_pdis {
+		ste,sleep-input = <SLPM_DIR_INPUT>;
+		ste,sleep-wakeup = <SLPM_WAKEUP_ENABLE>;
+		ste,sleep-pull-disable = <SLPM_PDIS_DISABLED>;
+	};
+
+	out_hi_wkup_pdis: out_hi_wkup_pdis {
+		ste,sleep-output = <SLPM_OUTPUT_HIGH>;
+		ste,sleep-wakeup = <SLPM_WAKEUP_ENABLE>;
+		ste,sleep-pull-disable = <SLPM_PDIS_DISABLED>;
+	};
+
+	out_wkup_pdis: out_wkup_pdis {
+		ste,sleep-output = <SLPM_DIR_OUTPUT>;
+		ste,sleep-wakeup = <SLPM_WAKEUP_ENABLE>;
+		ste,sleep-pull-disable = <SLPM_PDIS_DISABLED>;
+	};
+};
diff --git a/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi b/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi
index a3acfa7b3dc9..9169d3025f39 100644
--- a/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi
+++ b/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi
@@ -140,18 +140,30 @@
 			};
 		};
 		i2c0 {
+			i2c0_default_mux: i2c0_mux {
+				i2c0_default_mux {
+					ste,function = "i2c0";
+					ste,pins = "i2c0_a_1";
+				};
+			};
 			i2c0_default_mode: i2c0_default {
 				i2c0_default_cfg {
 					ste,pins = "GPIO62_D3", "GPIO63_D2";
-					ste,input = <1>;
+					ste,input = <0>;
 				};
 			};
 		};
 		i2c1 {
+			i2c1_default_mux: i2c1_mux {
+				i2c1_default_mux {
+					ste,function = "i2c1";
+					ste,pins = "i2c1_a_1";
+				};
+			};
 			i2c1_default_mode: i2c1_default {
 				i2c1_default_cfg {
 					ste,pins = "GPIO53_L4", "GPIO54_L3";
-					ste,input = <1>;
+					ste,input = <0>;
 				};
 			};
 		};
@@ -159,7 +171,7 @@
 			i2c2_default_mode: i2c2_default {
 				i2c2_default_cfg {
 					ste,pins = "GPIO73_C21", "GPIO74_C20";
-					ste,input = <1>;
+					ste,input = <0>;
 				};
 			};
 		};
@@ -682,13 +694,17 @@
 
 	/* I2C0 connected to the STw4811 power management chip */
 	i2c0 {
-		compatible = "i2c-gpio";
-		gpios = <&gpio1 31 0>, /* sda */
-			<&gpio1 30 0>; /* scl */
+		compatible = "st,nomadik-i2c", "arm,primecell";
+		reg = <0x101f8000 0x1000>;
+		interrupt-parent = <&vica>;
+		interrupts = <20>;
+		clock-frequency = <100000>;
 		#address-cells = <1>;
 		#size-cells = <0>;
+		clocks = <&i2c0clk>, <&pclki2c0>;
+		clock-names = "mclk", "apb_pclk";
 		pinctrl-names = "default";
-		pinctrl-0 = <&i2c0_default_mode>;
+		pinctrl-0 = <&i2c0_default_mux>, <&i2c0_default_mode>;
 
 		stw4811@2d {
 			   compatible = "st,stw4811";
@@ -698,13 +714,17 @@
 
 	/* I2C1 connected to various sensors */
 	i2c1 {
-		compatible = "i2c-gpio";
-		gpios = <&gpio1 22 0>, /* sda */
-			<&gpio1 21 0>; /* scl */
+		compatible = "st,nomadik-i2c", "arm,primecell";
+		reg = <0x101f7000 0x1000>;
+		interrupt-parent = <&vica>;
+		interrupts = <21>;
+		clock-frequency = <100000>;
 		#address-cells = <1>;
 		#size-cells = <0>;
+		clocks = <&i2c1clk>, <&pclki2c1>;
+		clock-names = "mclk", "apb_pclk";
 		pinctrl-names = "default";
-		pinctrl-0 = <&i2c1_default_mode>;
+		pinctrl-0 = <&i2c1_default_mux>, <&i2c1_default_mode>;
 
 		camera@2d {
 			   compatible = "st,camera";
diff --git a/arch/arm/boot/dts/snowball.dts b/arch/arm/boot/dts/ste-snowball.dts
index 49824be66845..f1fc128e249d 100644
--- a/arch/arm/boot/dts/snowball.dts
+++ b/arch/arm/boot/dts/ste-snowball.dts
@@ -10,7 +10,7 @@
  */
 
 /dts-v1/;
-#include "dbx5x0.dtsi"
+#include "ste-dbx5x0.dtsi"
 
 / {
 	model = "Calao Systems Snowball platform with device tree";
@@ -165,34 +165,6 @@
 			status = "okay";
 		};
 
-		i2c@80004000 {
-			tc3589x@42 {
-				//compatible = "tc3589x";
-				reg = <0x42>;
-				gpios = <&gpio6 25 0x4>;
-				interrupt-parent = <&gpio6>;
-			};
-			tps61052@33 {
-				//compatible = "tps61052";
-				reg = <0x33>;
-			};
-		};
-
-		i2c@80128000 {
-			lp5521@33 {
-				// compatible = "lp5521";
-				reg = <0x33>;
-			};
-			lp5521@34 {
-				// compatible = "lp5521";
-				reg = <0x34>;
-			};
-			bh1780@29 {
-				// compatible = "rohm,bh1780gli";
-				reg = <0x33>;
-			};
-		};
-
 		cpufreq-cooling {
 			status = "okay";
 		};
@@ -310,6 +282,20 @@
 					compatible = "stericsson,ab8500-gpio";
 				};
 
+				ext_regulators: ab8500-ext-regulators {
+					ab8500_ext1_reg: ab8500_ext1 {
+						regulator-name = "ab8500-ext-supply1";
+					};
+
+					ab8500_ext2_reg_reg: ab8500_ext2 {
+						regulator-name = "ab8500-ext-supply2";
+					};
+
+					ab8500_ext3_reg_reg: ab8500_ext3 {
+						regulator-name = "ab8500-ext-supply3";
+					};
+				};
+
 				ab8500-regulators {
 					ab8500_ldo_aux1_reg: ab8500_ldo_aux1 {
 						regulator-name = "V-DISPLAY";
diff --git a/arch/arm/boot/dts/stuib.dtsi b/arch/arm/boot/dts/ste-stuib.dtsi
index 524e33240ad4..524e33240ad4 100644
--- a/arch/arm/boot/dts/stuib.dtsi
+++ b/arch/arm/boot/dts/ste-stuib.dtsi
diff --git a/arch/arm/boot/dts/sun4i-a10-a1000.dts b/arch/arm/boot/dts/sun4i-a10-a1000.dts
new file mode 100644
index 000000000000..eb4d73b6a090
--- /dev/null
+++ b/arch/arm/boot/dts/sun4i-a10-a1000.dts
@@ -0,0 +1,101 @@
+/*
+ * Copyright 2013 Emilio López
+ *
+ * Emilio López <emilio@elopez.com.ar>
+ *
+ * The code contained herein is licensed under the GNU General Public
+ * License. You may obtain a copy of the GNU General Public License
+ * Version 2 or later at the following locations:
+ *
+ * http://www.opensource.org/licenses/gpl-license.html
+ * http://www.gnu.org/copyleft/gpl.html
+ */
+
+/dts-v1/;
+/include/ "sun4i-a10.dtsi"
+
+/ {
+	model = "Mele A1000";
+	compatible = "mele,a1000", "allwinner,sun4i-a10";
+
+	aliases {
+		serial0 = &uart0;
+	};
+
+	soc@01c00000 {
+		emac: ethernet@01c0b000 {
+			pinctrl-names = "default";
+			pinctrl-0 = <&emac_pins_a>;
+			phy = <&phy1>;
+			status = "okay";
+		};
+
+		mdio@01c0b080 {
+			phy-supply = <&reg_emac_3v3>;
+			status = "okay";
+
+			phy1: ethernet-phy@1 {
+				reg = <1>;
+			};
+		};
+
+		pinctrl@01c20800 {
+			emac_power_pin_a1000: emac_power_pin@0 {
+				allwinner,pins = "PH15";
+				allwinner,function = "gpio_out";
+				allwinner,drive = <0>;
+				allwinner,pull = <0>;
+			};
+
+			led_pins_a1000: led_pins@0 {
+				allwinner,pins = "PH10", "PH20";
+				allwinner,function = "gpio_out";
+				allwinner,drive = <0>;
+				allwinner,pull = <0>;
+			};
+		};
+
+		uart0: serial@01c28000 {
+			pinctrl-names = "default";
+			pinctrl-0 = <&uart0_pins_a>;
+			status = "okay";
+		};
+
+		i2c0: i2c@01c2ac00 {
+			pinctrl-names = "default";
+			pinctrl-0 = <&i2c0_pins_a>;
+			status = "okay";
+		};
+	};
+
+	leds {
+		compatible = "gpio-leds";
+		pinctrl-names = "default";
+		pinctrl-0 = <&led_pins_a1000>;
+
+		red {
+			label = "a1000:red:usr";
+			gpios = <&pio 7 10 0>;
+		};
+
+		blue {
+			label = "a1000:blue:usr";
+			gpios = <&pio 7 20 0>;
+		};
+	};
+
+	regulators {
+		compatible = "simple-bus";
+
+		reg_emac_3v3: emac-3v3 {
+			compatible = "regulator-fixed";
+			pinctrl-names = "default";
+			pinctrl-0 = <&emac_power_pin_a1000>;
+			regulator-name = "emac-3v3";
+			regulator-min-microvolt = <3300000>;
+			regulator-max-microvolt = <3300000>;
+			enable-active-high;
+			gpio = <&pio 7 15 0>;
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/sun4i-a10-cubieboard.dts b/arch/arm/boot/dts/sun4i-a10-cubieboard.dts
index 757c4cd900ee..425a7db898c5 100644
--- a/arch/arm/boot/dts/sun4i-a10-cubieboard.dts
+++ b/arch/arm/boot/dts/sun4i-a10-cubieboard.dts
@@ -26,7 +26,7 @@
 		bootargs = "earlyprintk console=ttyS0,115200";
 	};
 
-	soc@01c20000 {
+	soc@01c00000 {
 		emac: ethernet@01c0b000 {
 			pinctrl-names = "default";
 			pinctrl-0 = <&emac_pins_a>;
@@ -76,12 +76,12 @@
 		pinctrl-0 = <&led_pins_cubieboard>;
 
 		blue {
-			label = "cubieboard::blue";
+			label = "cubieboard:blue:usr";
 			gpios = <&pio 7 21 0>; /* LED1 */
 		};
 
 		green {
-			label = "cubieboard::green";
+			label = "cubieboard:green:usr";
 			gpios = <&pio 7 20 0>; /* LED2 */
 			linux,default-trigger = "heartbeat";
 		};
diff --git a/arch/arm/boot/dts/sun4i-a10-hackberry.dts b/arch/arm/boot/dts/sun4i-a10-hackberry.dts
index 3514b37d66bc..b3ae51fa9372 100644
--- a/arch/arm/boot/dts/sun4i-a10-hackberry.dts
+++ b/arch/arm/boot/dts/sun4i-a10-hackberry.dts
@@ -22,7 +22,7 @@
 		bootargs = "earlyprintk console=ttyS0,115200";
 	};
 
-	soc@01c20000 {
+	soc@01c00000 {
 		emac: ethernet@01c0b000 {
 			pinctrl-names = "default";
 			pinctrl-0 = <&emac_pins_a>;
diff --git a/arch/arm/boot/dts/sun4i-a10-mini-xplus.dts b/arch/arm/boot/dts/sun4i-a10-mini-xplus.dts
index 078ed7f618d7..0c1447c68059 100644
--- a/arch/arm/boot/dts/sun4i-a10-mini-xplus.dts
+++ b/arch/arm/boot/dts/sun4i-a10-mini-xplus.dts
@@ -22,7 +22,7 @@
 		bootargs = "earlyprintk console=ttyS0,115200";
 	};
 
-	soc@01c20000 {
+	soc@01c00000 {
 		uart0: serial@01c28000 {
 			pinctrl-names = "default";
 			pinctrl-0 = <&uart0_pins_a>;
diff --git a/arch/arm/boot/dts/sun4i-a10.dtsi b/arch/arm/boot/dts/sun4i-a10.dtsi
index b2bd6e124250..c32770a28acf 100644
--- a/arch/arm/boot/dts/sun4i-a10.dtsi
+++ b/arch/arm/boot/dts/sun4i-a10.dtsi
@@ -160,11 +160,10 @@
 		};
 	};
 
-	soc@01c20000 {
+	soc@01c00000 {
 		compatible = "simple-bus";
 		#address-cells = <1>;
 		#size-cells = <1>;
-		reg = <0x01c20000 0x300000>;
 		ranges;
 
 		emac: ethernet@01c0b000 {
diff --git a/arch/arm/boot/dts/sun5i-a10s-olinuxino-micro.dts b/arch/arm/boot/dts/sun5i-a10s-olinuxino-micro.dts
index 64dc0c42c43a..3c9f8b3cd3e3 100644
--- a/arch/arm/boot/dts/sun5i-a10s-olinuxino-micro.dts
+++ b/arch/arm/boot/dts/sun5i-a10s-olinuxino-micro.dts
@@ -18,7 +18,7 @@
 	model = "Olimex A10s-Olinuxino Micro";
 	compatible = "olimex,a10s-olinuxino-micro", "allwinner,sun5i-a10s";
 
-	soc@01c20000 {
+	soc@01c00000 {
 		emac: ethernet@01c0b000 {
 			pinctrl-names = "default";
 			pinctrl-0 = <&emac_pins_a>;
@@ -60,6 +60,31 @@
 			pinctrl-0 = <&uart3_pins_a>;
 			status = "okay";
 		};
+
+		i2c0: i2c@01c2ac00 {
+			pinctrl-names = "default";
+			pinctrl-0 = <&i2c0_pins_a>;
+			status = "okay";
+		};
+
+		i2c1: i2c@01c2b000 {
+			pinctrl-names = "default";
+			pinctrl-0 = <&i2c1_pins_a>;
+			status = "okay";
+
+			at24@50 {
+				compatible = "at,24c16";
+				pagesize = <16>;
+				reg = <0x50>;
+				read-only;
+			};
+		};
+
+		i2c2: i2c@01c2b400 {
+			pinctrl-names = "default";
+			pinctrl-0 = <&i2c2_pins_a>;
+			status = "okay";
+		};
 	};
 
 	leds {
diff --git a/arch/arm/boot/dts/sun5i-a10s.dtsi b/arch/arm/boot/dts/sun5i-a10s.dtsi
index 2307ce827ae0..3b4a0574f068 100644
--- a/arch/arm/boot/dts/sun5i-a10s.dtsi
+++ b/arch/arm/boot/dts/sun5i-a10s.dtsi
@@ -95,20 +95,16 @@
 
 		ahb_gates: ahb_gates@01c20060 {
 			#clock-cells = <1>;
-			compatible = "allwinner,sun4i-ahb-gates-clk";
+			compatible = "allwinner,sun5i-a10s-ahb-gates-clk";
 			reg = <0x01c20060 0x8>;
 			clocks = <&ahb>;
-			clock-output-names = "ahb_usb0", "ahb_ehci0",
-				"ahb_ohci0", "ahb_ehci1", "ahb_ohci1", "ahb_ss",
-				"ahb_dma", "ahb_bist", "ahb_mmc0", "ahb_mmc1",
-				"ahb_mmc2", "ahb_mmc3", "ahb_ms", "ahb_nand",
-				"ahb_sdram", "ahb_ace",	"ahb_emac", "ahb_ts",
-				"ahb_spi0", "ahb_spi1", "ahb_spi2", "ahb_spi3",
-				"ahb_pata", "ahb_sata", "ahb_gps", "ahb_ve",
-				"ahb_tvd", "ahb_tve0", "ahb_tve1", "ahb_lcd0",
-				"ahb_lcd1", "ahb_csi0", "ahb_csi1", "ahb_hdmi",
-				"ahb_de_be0", "ahb_de_be1", "ahb_de_fe0",
-				"ahb_de_fe1", "ahb_mp", "ahb_mali400";
+			clock-output-names = "ahb_usbotg", "ahb_ehci", "ahb_ohci",
+				"ahb_ss", "ahb_dma", "ahb_bist", "ahb_mmc0",
+				"ahb_mmc1", "ahb_mmc2", "ahb_nand", "ahb_sdram",
+				"ahb_emac", "ahb_ts", "ahb_spi0", "ahb_spi1",
+				"ahb_spi2", "ahb_gps", "ahb_stimer", "ahb_ve",
+				"ahb_tve", "ahb_lcd", "ahb_csi", "ahb_hdmi",
+				"ahb_de_be", "ahb_de_fe", "ahb_iep", "ahb_mali400";
 		};
 
 		apb0: apb0@01c20054 {
@@ -120,12 +116,11 @@
 
 		apb0_gates: apb0_gates@01c20068 {
 			#clock-cells = <1>;
-			compatible = "allwinner,sun4i-apb0-gates-clk";
+			compatible = "allwinner,sun5i-a10s-apb0-gates-clk";
 			reg = <0x01c20068 0x4>;
 			clocks = <&apb0>;
-			clock-output-names = "apb0_codec", "apb0_spdif",
-				"apb0_ac97", "apb0_iis", "apb0_pio", "apb0_ir0",
-				"apb0_ir1", "apb0_keypad";
+			clock-output-names = "apb0_codec", "apb0_iis", "apb0_pio",
+				"apb0_ir", "apb0_keypad";
 		};
 
 		/* dummy is pll62 */
@@ -145,23 +140,19 @@
 
 		apb1_gates: apb1_gates@01c2006c {
 			#clock-cells = <1>;
-			compatible = "allwinner,sun4i-apb1-gates-clk";
+			compatible = "allwinner,sun5i-a10s-apb1-gates-clk";
 			reg = <0x01c2006c 0x4>;
 			clocks = <&apb1>;
 			clock-output-names = "apb1_i2c0", "apb1_i2c1",
-				"apb1_i2c2", "apb1_can", "apb1_scr",
-				"apb1_ps20", "apb1_ps21", "apb1_uart0",
-				"apb1_uart1", "apb1_uart2", "apb1_uart3",
-				"apb1_uart4", "apb1_uart5", "apb1_uart6",
-				"apb1_uart7";
+				"apb1_i2c2", "apb1_uart0", "apb1_uart1",
+				"apb1_uart2", "apb1_uart3";
 		};
 	};
 
-	soc@01c20000 {
+	soc@01c00000 {
 		compatible = "simple-bus";
 		#address-cells = <1>;
 		#size-cells = <1>;
-		reg = <0x01c20000 0x300000>;
 		ranges;
 
 		emac: ethernet@01c0b000 {
@@ -229,6 +220,27 @@
 				allwinner,drive = <0>;
 				allwinner,pull = <0>;
 			};
+
+			i2c0_pins_a: i2c0@0 {
+				allwinner,pins = "PB0", "PB1";
+				allwinner,function = "i2c0";
+				allwinner,drive = <0>;
+				allwinner,pull = <0>;
+			};
+
+			i2c1_pins_a: i2c1@0 {
+				allwinner,pins = "PB15", "PB16";
+				allwinner,function = "i2c1";
+				allwinner,drive = <0>;
+				allwinner,pull = <0>;
+			};
+
+			i2c2_pins_a: i2c2@0 {
+				allwinner,pins = "PB17", "PB18";
+				allwinner,function = "i2c2";
+				allwinner,drive = <0>;
+				allwinner,pull = <0>;
+			};
 		};
 
 		timer@01c20c00 {
@@ -282,5 +294,38 @@
 			clocks = <&apb1_gates 19>;
 			status = "disabled";
 		};
+
+		i2c0: i2c@01c2ac00 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			compatible = "allwinner,sun4i-i2c";
+			reg = <0x01c2ac00 0x400>;
+			interrupts = <7>;
+			clocks = <&apb1_gates 0>;
+			clock-frequency = <100000>;
+			status = "disabled";
+		};
+
+		i2c1: i2c@01c2b000 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			compatible = "allwinner,sun4i-i2c";
+			reg = <0x01c2b000 0x400>;
+			interrupts = <8>;
+			clocks = <&apb1_gates 1>;
+			clock-frequency = <100000>;
+			status = "disabled";
+		};
+
+		i2c2: i2c@01c2b400 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			compatible = "allwinner,sun4i-i2c";
+			reg = <0x01c2b400 0x400>;
+			interrupts = <9>;
+			clocks = <&apb1_gates 2>;
+			clock-frequency = <100000>;
+			status = "disabled";
+		};
 	};
 };
diff --git a/arch/arm/boot/dts/sun5i-a13-olinuxino.dts b/arch/arm/boot/dts/sun5i-a13-olinuxino.dts
index 80497e376706..9e508dcc4245 100644
--- a/arch/arm/boot/dts/sun5i-a13-olinuxino.dts
+++ b/arch/arm/boot/dts/sun5i-a13-olinuxino.dts
@@ -22,7 +22,7 @@
 		bootargs = "earlyprintk console=ttyS0,115200";
 	};
 
-	soc@01c20000 {
+	soc@01c00000 {
 		pinctrl@01c20800 {
 			led_pins_olinuxino: led_pins@0 {
 				allwinner,pins = "PG9";
diff --git a/arch/arm/boot/dts/sun5i-a13.dtsi b/arch/arm/boot/dts/sun5i-a13.dtsi
index 7363211daf84..f6091dc0936c 100644
--- a/arch/arm/boot/dts/sun5i-a13.dtsi
+++ b/arch/arm/boot/dts/sun5i-a13.dtsi
@@ -150,11 +150,10 @@
 		};
 	};
 
-	soc@01c20000 {
+	soc@01c00000 {
 		compatible = "simple-bus";
 		#address-cells = <1>;
 		#size-cells = <1>;
-		reg = <0x01c20000 0x300000>;
 		ranges;
 
 		intc: interrupt-controller@01c20400 {
diff --git a/arch/arm/boot/dts/sun6i-a31-colombus.dts b/arch/arm/boot/dts/sun6i-a31-colombus.dts
new file mode 100644
index 000000000000..e5adae30899b
--- /dev/null
+++ b/arch/arm/boot/dts/sun6i-a31-colombus.dts
@@ -0,0 +1,32 @@
+/*
+ * Copyright 2013 Maxime Ripard
+ *
+ * Maxime Ripard <maxime.ripard@free-electrons.com>
+ *
+ * The code contained herein is licensed under the GNU General Public
+ * License. You may obtain a copy of the GNU General Public License
+ * Version 2 or later at the following locations:
+ *
+ * http://www.opensource.org/licenses/gpl-license.html
+ * http://www.gnu.org/copyleft/gpl.html
+ */
+
+/dts-v1/;
+/include/ "sun6i-a31.dtsi"
+
+/ {
+	model = "WITS A31 Colombus Evaluation Board";
+	compatible = "wits,colombus", "allwinner,sun6i-a31";
+
+	chosen {
+		bootargs = "earlyprintk console=ttyS0,115200";
+	};
+
+	soc@01c00000 {
+		uart0: serial@01c28000 {
+			pinctrl-names = "default";
+			pinctrl-0 = <&uart0_pins_a>;
+			status = "okay";
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/sun6i-a31.dtsi b/arch/arm/boot/dts/sun6i-a31.dtsi
new file mode 100644
index 000000000000..f244f5f02365
--- /dev/null
+++ b/arch/arm/boot/dts/sun6i-a31.dtsi
@@ -0,0 +1,299 @@
+/*
+ * Copyright 2013 Maxime Ripard
+ *
+ * Maxime Ripard <maxime.ripard@free-electrons.com>
+ *
+ * The code contained herein is licensed under the GNU General Public
+ * License. You may obtain a copy of the GNU General Public License
+ * Version 2 or later at the following locations:
+ *
+ * http://www.opensource.org/licenses/gpl-license.html
+ * http://www.gnu.org/copyleft/gpl.html
+ */
+
+/include/ "skeleton.dtsi"
+
+/ {
+	interrupt-parent = <&gic>;
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cpu@0 {
+			compatible = "arm,cortex-a7";
+			device_type = "cpu";
+			reg = <0>;
+		};
+
+		cpu@1 {
+			compatible = "arm,cortex-a7";
+			device_type = "cpu";
+			reg = <1>;
+		};
+
+		cpu@2 {
+			compatible = "arm,cortex-a7";
+			device_type = "cpu";
+			reg = <2>;
+		};
+
+		cpu@3 {
+			compatible = "arm,cortex-a7";
+			device_type = "cpu";
+			reg = <3>;
+		};
+	};
+
+	memory {
+		reg = <0x40000000 0x80000000>;
+	};
+
+	clocks {
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges;
+
+		osc24M: osc24M {
+			#clock-cells = <0>;
+			compatible = "fixed-clock";
+			clock-frequency = <24000000>;
+		};
+
+		osc32k: osc32k {
+			#clock-cells = <0>;
+			compatible = "fixed-clock";
+			clock-frequency = <32768>;
+		};
+
+		pll1: pll1@01c20000 {
+			#clock-cells = <0>;
+			compatible = "allwinner,sun6i-a31-pll1-clk";
+			reg = <0x01c20000 0x4>;
+			clocks = <&osc24M>;
+		};
+
+		/*
+		 * This is a dummy clock, to be used as placeholder on
+		 * other mux clocks when a specific parent clock is not
+		 * yet implemented. It should be dropped when the driver
+		 * is complete.
+		 */
+		pll6: pll6 {
+			#clock-cells = <0>;
+			compatible = "fixed-clock";
+			clock-frequency = <0>;
+		};
+
+		cpu: cpu@01c20050 {
+			#clock-cells = <0>;
+			compatible = "allwinner,sun4i-cpu-clk";
+			reg = <0x01c20050 0x4>;
+
+			/*
+			 * PLL1 is listed twice here.
+			 * While it looks suspicious, it's actually documented
+			 * that way both in the datasheet and in the code from
+			 * Allwinner.
+			 */
+			clocks = <&osc32k>, <&osc24M>, <&pll1>, <&pll1>;
+		};
+
+		axi: axi@01c20050 {
+			#clock-cells = <0>;
+			compatible = "allwinner,sun4i-axi-clk";
+			reg = <0x01c20050 0x4>;
+			clocks = <&cpu>;
+		};
+
+		ahb1_mux: ahb1_mux@01c20054 {
+			#clock-cells = <0>;
+			compatible = "allwinner,sun6i-a31-ahb1-mux-clk";
+			reg = <0x01c20054 0x4>;
+			clocks = <&osc32k>, <&osc24M>, <&axi>, <&pll6>;
+		};
+
+		ahb1: ahb1@01c20054 {
+			#clock-cells = <0>;
+			compatible = "allwinner,sun4i-ahb-clk";
+			reg = <0x01c20054 0x4>;
+			clocks = <&ahb1_mux>;
+		};
+
+		ahb1_gates: ahb1_gates@01c20060 {
+			#clock-cells = <1>;
+			compatible = "allwinner,sun6i-a31-ahb1-gates-clk";
+			reg = <0x01c20060 0x8>;
+			clocks = <&ahb1>;
+			clock-output-names = "ahb1_mipidsi", "ahb1_ss",
+					"ahb1_dma", "ahb1_mmc0", "ahb1_mmc1",
+					"ahb1_mmc2", "ahb1_mmc3", "ahb1_nand1",
+					"ahb1_nand0", "ahb1_sdram",
+					"ahb1_gmac", "ahb1_ts", "ahb1_hstimer",
+					"ahb1_spi0", "ahb1_spi1", "ahb1_spi2",
+					"ahb1_spi3", "ahb1_otg", "ahb1_ehci0",
+					"ahb1_ehci1", "ahb1_ohci0",
+					"ahb1_ohci1", "ahb1_ohci2", "ahb1_ve",
+					"ahb1_lcd0", "ahb1_lcd1", "ahb1_csi",
+					"ahb1_hdmi", "ahb1_de0", "ahb1_de1",
+					"ahb1_fe0", "ahb1_fe1", "ahb1_mp",
+					"ahb1_gpu", "ahb1_deu0", "ahb1_deu1",
+					"ahb1_drc0", "ahb1_drc1";
+		};
+
+		apb1: apb1@01c20054 {
+			#clock-cells = <0>;
+			compatible = "allwinner,sun4i-apb0-clk";
+			reg = <0x01c20054 0x4>;
+			clocks = <&ahb1>;
+		};
+
+		apb1_gates: apb1_gates@01c20060 {
+			#clock-cells = <1>;
+			compatible = "allwinner,sun6i-a31-apb1-gates-clk";
+			reg = <0x01c20068 0x4>;
+			clocks = <&apb1>;
+			clock-output-names = "apb1_codec", "apb1_digital_mic",
+					"apb1_pio", "apb1_daudio0",
+					"apb1_daudio1";
+		};
+
+		apb2_mux: apb2_mux@01c20058 {
+			#clock-cells = <0>;
+			compatible = "allwinner,sun4i-apb1-mux-clk";
+			reg = <0x01c20058 0x4>;
+			clocks = <&osc32k>, <&osc24M>, <&pll6>, <&pll6>;
+		};
+
+		apb2: apb2@01c20058 {
+			#clock-cells = <0>;
+			compatible = "allwinner,sun6i-a31-apb2-div-clk";
+			reg = <0x01c20058 0x4>;
+			clocks = <&apb2_mux>;
+		};
+
+		apb2_gates: apb2_gates@01c2006c {
+			#clock-cells = <1>;
+			compatible = "allwinner,sun6i-a31-apb2-gates-clk";
+			reg = <0x01c2006c 0x8>;
+			clocks = <&apb2>;
+			clock-output-names = "apb2_i2c0", "apb2_i2c1",
+					"apb2_i2c2", "apb2_i2c3", "apb2_uart0",
+					"apb2_uart1", "apb2_uart2", "apb2_uart3",
+					"apb2_uart4", "apb2_uart5";
+		};
+	};
+
+	soc@01c00000 {
+		compatible = "simple-bus";
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges;
+
+		pio: pinctrl@01c20800 {
+			compatible = "allwinner,sun6i-a31-pinctrl";
+			reg = <0x01c20800 0x400>;
+			interrupts = <0 11 1>, <0 15 1>, <0 16 1>, <0 17 1>;
+			clocks = <&apb1_gates 5>;
+			gpio-controller;
+			interrupt-controller;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			#gpio-cells = <3>;
+
+			uart0_pins_a: uart0@0 {
+				allwinner,pins = "PH20", "PH21";
+				allwinner,function = "uart0";
+				allwinner,drive = <0>;
+				allwinner,pull = <0>;
+			};
+		};
+
+		timer@01c20c00 {
+			compatible = "allwinner,sun4i-timer";
+			reg = <0x01c20c00 0xa0>;
+			interrupts = <0 18 1>,
+				     <0 19 1>,
+				     <0 20 1>,
+				     <0 21 1>,
+				     <0 22 1>;
+			clocks = <&osc24M>;
+		};
+
+		wdt1: watchdog@01c20ca0 {
+			compatible = "allwinner,sun6i-wdt";
+			reg = <0x01c20ca0 0x20>;
+		};
+
+		uart0: serial@01c28000 {
+			compatible = "snps,dw-apb-uart";
+			reg = <0x01c28000 0x400>;
+			interrupts = <0 0 1>;
+			reg-shift = <2>;
+			reg-io-width = <4>;
+			clocks = <&apb2_gates 16>;
+			status = "disabled";
+		};
+
+		uart1: serial@01c28400 {
+			compatible = "snps,dw-apb-uart";
+			reg = <0x01c28400 0x400>;
+			interrupts = <0 1 1>;
+			reg-shift = <2>;
+			reg-io-width = <4>;
+			clocks = <&apb2_gates 17>;
+			status = "disabled";
+		};
+
+		uart2: serial@01c28800 {
+			compatible = "snps,dw-apb-uart";
+			reg = <0x01c28800 0x400>;
+			interrupts = <0 2 1>;
+			reg-shift = <2>;
+			reg-io-width = <4>;
+			clocks = <&apb2_gates 18>;
+			status = "disabled";
+		};
+
+		uart3: serial@01c28c00 {
+			compatible = "snps,dw-apb-uart";
+			reg = <0x01c28c00 0x400>;
+			interrupts = <0 3 1>;
+			reg-shift = <2>;
+			reg-io-width = <4>;
+			clocks = <&apb2_gates 19>;
+			status = "disabled";
+		};
+
+		uart4: serial@01c29000 {
+			compatible = "snps,dw-apb-uart";
+			reg = <0x01c29000 0x400>;
+			interrupts = <0 4 1>;
+			reg-shift = <2>;
+			reg-io-width = <4>;
+			clocks = <&apb2_gates 20>;
+			status = "disabled";
+		};
+
+		uart5: serial@01c29400 {
+			compatible = "snps,dw-apb-uart";
+			reg = <0x01c29400 0x400>;
+			interrupts = <0 5 1>;
+			reg-shift = <2>;
+			reg-io-width = <4>;
+			clocks = <&apb2_gates 21>;
+			status = "disabled";
+		};
+
+		gic: interrupt-controller@01c81000 {
+			compatible = "arm,cortex-a7-gic", "arm,cortex-a15-gic";
+			reg = <0x01c81000 0x1000>,
+			      <0x01c82000 0x1000>,
+			      <0x01c84000 0x2000>,
+			      <0x01c86000 0x2000>;
+			interrupt-controller;
+			#interrupt-cells = <3>;
+			interrupts = <1 9 0xf04>;
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/sun7i-a20-cubieboard2.dts b/arch/arm/boot/dts/sun7i-a20-cubieboard2.dts
new file mode 100644
index 000000000000..15e625eca312
--- /dev/null
+++ b/arch/arm/boot/dts/sun7i-a20-cubieboard2.dts
@@ -0,0 +1,68 @@
+/*
+ * Copyright 2013 Maxime Ripard
+ *
+ * Maxime Ripard <maxime.ripard@free-electrons.com>
+ *
+ * The code contained herein is licensed under the GNU General Public
+ * License. You may obtain a copy of the GNU General Public License
+ * Version 2 or later at the following locations:
+ *
+ * http://www.opensource.org/licenses/gpl-license.html
+ * http://www.gnu.org/copyleft/gpl.html
+ */
+
+/dts-v1/;
+/include/ "sun7i-a20.dtsi"
+
+/ {
+	model = "Cubietech Cubieboard2";
+	compatible = "cubietech,cubieboard2", "allwinner,sun7i-a20";
+
+	soc@01c00000 {
+		emac: ethernet@01c0b000 {
+			pinctrl-names = "default";
+			pinctrl-0 = <&emac_pins_a>;
+			phy = <&phy1>;
+			status = "okay";
+		};
+
+		mdio@01c0b080 {
+			status = "okay";
+
+			phy1: ethernet-phy@1 {
+				reg = <1>;
+			};
+		};
+
+		pinctrl@01c20800 {
+			led_pins_cubieboard2: led_pins@0 {
+				allwinner,pins = "PH20", "PH21";
+				allwinner,function = "gpio_out";
+				allwinner,drive = <0>;
+				allwinner,pull = <0>;
+			};
+		};
+
+		uart0: serial@01c28000 {
+			pinctrl-names = "default";
+			pinctrl-0 = <&uart0_pins_a>;
+			status = "okay";
+		};
+	};
+
+	leds {
+		compatible = "gpio-leds";
+		pinctrl-names = "default";
+		pinctrl-0 = <&led_pins_cubieboard2>;
+
+		blue {
+			label = "cubieboard2:blue:usr";
+			gpios = <&pio 7 21 0>;
+		};
+
+		green {
+			label = "cubieboard2:green:usr";
+			gpios = <&pio 7 20 0>;
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/sun7i-a20-olinuxino-micro.dts b/arch/arm/boot/dts/sun7i-a20-olinuxino-micro.dts
new file mode 100644
index 000000000000..9e778557fadb
--- /dev/null
+++ b/arch/arm/boot/dts/sun7i-a20-olinuxino-micro.dts
@@ -0,0 +1,76 @@
+/*
+ * Copyright 2013 Maxime Ripard
+ *
+ * Maxime Ripard <maxime.ripard@free-electrons.com>
+ *
+ * The code contained herein is licensed under the GNU General Public
+ * License. You may obtain a copy of the GNU General Public License
+ * Version 2 or later at the following locations:
+ *
+ * http://www.opensource.org/licenses/gpl-license.html
+ * http://www.gnu.org/copyleft/gpl.html
+ */
+
+/dts-v1/;
+/include/ "sun7i-a20.dtsi"
+
+/ {
+	model = "Olimex A20-Olinuxino Micro";
+	compatible = "olimex,a20-olinuxino-micro", "allwinner,sun7i-a20";
+
+	soc@01c00000 {
+		emac: ethernet@01c0b000 {
+			pinctrl-names = "default";
+			pinctrl-0 = <&emac_pins_a>;
+			phy = <&phy1>;
+			status = "okay";
+		};
+
+		mdio@01c0b080 {
+			status = "okay";
+
+			phy1: ethernet-phy@1 {
+				reg = <1>;
+			};
+		};
+
+		pinctrl@01c20800 {
+			led_pins_olinuxino: led_pins@0 {
+				allwinner,pins = "PH2";
+				allwinner,function = "gpio_out";
+				allwinner,drive = <1>;
+				allwinner,pull = <0>;
+			};
+		};
+
+		uart0: serial@01c28000 {
+			pinctrl-names = "default";
+			pinctrl-0 = <&uart0_pins_a>;
+			status = "okay";
+		};
+
+		uart6: serial@01c29800 {
+			pinctrl-names = "default";
+			pinctrl-0 = <&uart6_pins_a>;
+			status = "okay";
+		};
+
+		uart7: serial@01c29c00 {
+			pinctrl-names = "default";
+			pinctrl-0 = <&uart7_pins_a>;
+			status = "okay";
+		};
+	};
+
+	leds {
+		compatible = "gpio-leds";
+		pinctrl-names = "default";
+		pinctrl-0 = <&led_pins_olinuxino>;
+
+		green {
+			label = "a20-olinuxino-micro:green:usr";
+			gpios = <&pio 7 2 0>;
+			default-state = "on";
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/sun7i-a20.dtsi b/arch/arm/boot/dts/sun7i-a20.dtsi
new file mode 100644
index 000000000000..80559cbdbc87
--- /dev/null
+++ b/arch/arm/boot/dts/sun7i-a20.dtsi
@@ -0,0 +1,338 @@
+/*
+ * Copyright 2013 Maxime Ripard
+ *
+ * Maxime Ripard <maxime.ripard@free-electrons.com>
+ *
+ * The code contained herein is licensed under the GNU General Public
+ * License. You may obtain a copy of the GNU General Public License
+ * Version 2 or later at the following locations:
+ *
+ * http://www.opensource.org/licenses/gpl-license.html
+ * http://www.gnu.org/copyleft/gpl.html
+ */
+
+/include/ "skeleton.dtsi"
+
+/ {
+	interrupt-parent = <&gic>;
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cpu@0 {
+			compatible = "arm,cortex-a7";
+			device_type = "cpu";
+			reg = <0>;
+		};
+
+		cpu@1 {
+			compatible = "arm,cortex-a7";
+			device_type = "cpu";
+			reg = <1>;
+		};
+	};
+
+	memory {
+		reg = <0x40000000 0x80000000>;
+	};
+
+	clocks {
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges;
+
+		osc24M: osc24M@01c20050 {
+			#clock-cells = <0>;
+			compatible = "allwinner,sun4i-osc-clk";
+			reg = <0x01c20050 0x4>;
+			clock-frequency = <24000000>;
+		};
+
+		osc32k: osc32k {
+			#clock-cells = <0>;
+			compatible = "fixed-clock";
+			clock-frequency = <32768>;
+		};
+
+		pll1: pll1@01c20000 {
+			#clock-cells = <0>;
+			compatible = "allwinner,sun4i-pll1-clk";
+			reg = <0x01c20000 0x4>;
+			clocks = <&osc24M>;
+		};
+
+		/*
+		 * This is a dummy clock, to be used as placeholder on
+		 * other mux clocks when a specific parent clock is not
+		 * yet implemented. It should be dropped when the driver
+		 * is complete.
+		 */
+		pll6: pll6 {
+			#clock-cells = <0>;
+			compatible = "fixed-clock";
+			clock-frequency = <0>;
+		};
+
+		cpu: cpu@01c20054 {
+			#clock-cells = <0>;
+			compatible = "allwinner,sun4i-cpu-clk";
+			reg = <0x01c20054 0x4>;
+			clocks = <&osc32k>, <&osc24M>, <&pll1>, <&pll6>;
+		};
+
+		axi: axi@01c20054 {
+			#clock-cells = <0>;
+			compatible = "allwinner,sun4i-axi-clk";
+			reg = <0x01c20054 0x4>;
+			clocks = <&cpu>;
+		};
+
+		ahb: ahb@01c20054 {
+			#clock-cells = <0>;
+			compatible = "allwinner,sun4i-ahb-clk";
+			reg = <0x01c20054 0x4>;
+			clocks = <&axi>;
+		};
+
+		ahb_gates: ahb_gates@01c20060 {
+			#clock-cells = <1>;
+			compatible = "allwinner,sun7i-a20-ahb-gates-clk";
+			reg = <0x01c20060 0x8>;
+			clocks = <&ahb>;
+			clock-output-names = "ahb_usb0", "ahb_ehci0",
+				"ahb_ohci0", "ahb_ehci1", "ahb_ohci1",
+				"ahb_ss", "ahb_dma", "ahb_bist", "ahb_mmc0",
+				"ahb_mmc1", "ahb_mmc2", "ahb_mmc3", "ahb_ms",
+				"ahb_nand", "ahb_sdram", "ahb_ace",
+				"ahb_emac", "ahb_ts", "ahb_spi0", "ahb_spi1",
+				"ahb_spi2", "ahb_spi3", "ahb_sata",
+				"ahb_hstimer", "ahb_ve", "ahb_tvd", "ahb_tve0",
+				"ahb_tve1", "ahb_lcd0", "ahb_lcd1", "ahb_csi0",
+				"ahb_csi1", "ahb_hdmi1", "ahb_hdmi0",
+				"ahb_de_be0", "ahb_de_be1", "ahb_de_fe0",
+				"ahb_de_fe1", "ahb_gmac", "ahb_mp",
+				"ahb_mali";
+		};
+
+		apb0: apb0@01c20054 {
+			#clock-cells = <0>;
+			compatible = "allwinner,sun4i-apb0-clk";
+			reg = <0x01c20054 0x4>;
+			clocks = <&ahb>;
+		};
+
+		apb0_gates: apb0_gates@01c20068 {
+			#clock-cells = <1>;
+			compatible = "allwinner,sun7i-a20-apb0-gates-clk";
+			reg = <0x01c20068 0x4>;
+			clocks = <&apb0>;
+			clock-output-names = "apb0_codec", "apb0_spdif",
+				"apb0_ac97", "apb0_iis0", "apb0_iis1",
+				"apb0_pio", "apb0_ir0", "apb0_ir1",
+				"apb0_iis2", "apb0_keypad";
+		};
+
+		apb1_mux: apb1_mux@01c20058 {
+			#clock-cells = <0>;
+			compatible = "allwinner,sun4i-apb1-mux-clk";
+			reg = <0x01c20058 0x4>;
+			clocks = <&osc24M>, <&pll6>, <&osc32k>;
+		};
+
+		apb1: apb1@01c20058 {
+			#clock-cells = <0>;
+			compatible = "allwinner,sun4i-apb1-clk";
+			reg = <0x01c20058 0x4>;
+			clocks = <&apb1_mux>;
+		};
+
+		apb1_gates: apb1_gates@01c2006c {
+			#clock-cells = <1>;
+			compatible = "allwinner,sun7i-a20-apb1-gates-clk";
+			reg = <0x01c2006c 0x4>;
+			clocks = <&apb1>;
+			clock-output-names = "apb1_i2c0", "apb1_i2c1",
+				"apb1_i2c2", "apb1_i2c3", "apb1_can",
+				"apb1_scr", "apb1_ps20", "apb1_ps21",
+				"apb1_i2c4", "apb1_uart0", "apb1_uart1",
+				"apb1_uart2", "apb1_uart3", "apb1_uart4",
+				"apb1_uart5", "apb1_uart6", "apb1_uart7";
+		};
+	};
+
+	soc@01c00000 {
+		compatible = "simple-bus";
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges;
+
+		emac: ethernet@01c0b000 {
+			compatible = "allwinner,sun4i-emac";
+			reg = <0x01c0b000 0x1000>;
+			interrupts = <0 55 1>;
+			clocks = <&ahb_gates 17>;
+			status = "disabled";
+		};
+
+		mdio@01c0b080 {
+			compatible = "allwinner,sun4i-mdio";
+			reg = <0x01c0b080 0x14>;
+			status = "disabled";
+			#address-cells = <1>;
+			#size-cells = <0>;
+		};
+
+		pio: pinctrl@01c20800 {
+			compatible = "allwinner,sun7i-a20-pinctrl";
+			reg = <0x01c20800 0x400>;
+			interrupts = <0 28 1>;
+			clocks = <&apb0_gates 5>;
+			gpio-controller;
+			interrupt-controller;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			#gpio-cells = <3>;
+
+			uart0_pins_a: uart0@0 {
+				allwinner,pins = "PB22", "PB23";
+				allwinner,function = "uart0";
+				allwinner,drive = <0>;
+				allwinner,pull = <0>;
+			};
+
+			uart6_pins_a: uart6@0 {
+				allwinner,pins = "PI12", "PI13";
+				allwinner,function = "uart6";
+				allwinner,drive = <0>;
+				allwinner,pull = <0>;
+			};
+
+			uart7_pins_a: uart7@0 {
+				allwinner,pins = "PI20", "PI21";
+				allwinner,function = "uart7";
+				allwinner,drive = <0>;
+				allwinner,pull = <0>;
+			};
+
+			emac_pins_a: emac0@0 {
+				allwinner,pins = "PA0", "PA1", "PA2",
+						"PA3", "PA4", "PA5", "PA6",
+						"PA7", "PA8", "PA9", "PA10",
+						"PA11", "PA12", "PA13", "PA14",
+						"PA15", "PA16";
+				allwinner,function = "emac";
+				allwinner,drive = <0>;
+				allwinner,pull = <0>;
+			};
+		};
+
+		timer@01c20c00 {
+			compatible = "allwinner,sun4i-timer";
+			reg = <0x01c20c00 0x90>;
+			interrupts = <0 22 1>,
+				     <0 23 1>,
+				     <0 24 1>,
+				     <0 25 1>,
+				     <0 67 1>,
+				     <0 68 1>;
+			clocks = <&osc24M>;
+		};
+
+		wdt: watchdog@01c20c90 {
+			compatible = "allwinner,sun4i-wdt";
+			reg = <0x01c20c90 0x10>;
+		};
+
+		uart0: serial@01c28000 {
+			compatible = "snps,dw-apb-uart";
+			reg = <0x01c28000 0x400>;
+			interrupts = <0 1 1>;
+			reg-shift = <2>;
+			reg-io-width = <4>;
+			clocks = <&apb1_gates 16>;
+			status = "disabled";
+		};
+
+		uart1: serial@01c28400 {
+			compatible = "snps,dw-apb-uart";
+			reg = <0x01c28400 0x400>;
+			interrupts = <0 2 1>;
+			reg-shift = <2>;
+			reg-io-width = <4>;
+			clocks = <&apb1_gates 17>;
+			status = "disabled";
+		};
+
+		uart2: serial@01c28800 {
+			compatible = "snps,dw-apb-uart";
+			reg = <0x01c28800 0x400>;
+			interrupts = <0 3 1>;
+			reg-shift = <2>;
+			reg-io-width = <4>;
+			clocks = <&apb1_gates 18>;
+			status = "disabled";
+		};
+
+		uart3: serial@01c28c00 {
+			compatible = "snps,dw-apb-uart";
+			reg = <0x01c28c00 0x400>;
+			interrupts = <0 4 1>;
+			reg-shift = <2>;
+			reg-io-width = <4>;
+			clocks = <&apb1_gates 19>;
+			status = "disabled";
+		};
+
+		uart4: serial@01c29000 {
+			compatible = "snps,dw-apb-uart";
+			reg = <0x01c29000 0x400>;
+			interrupts = <0 17 1>;
+			reg-shift = <2>;
+			reg-io-width = <4>;
+			clocks = <&apb1_gates 20>;
+			status = "disabled";
+		};
+
+		uart5: serial@01c29400 {
+			compatible = "snps,dw-apb-uart";
+			reg = <0x01c29400 0x400>;
+			interrupts = <0 18 1>;
+			reg-shift = <2>;
+			reg-io-width = <4>;
+			clocks = <&apb1_gates 21>;
+			status = "disabled";
+		};
+
+		uart6: serial@01c29800 {
+			compatible = "snps,dw-apb-uart";
+			reg = <0x01c29800 0x400>;
+			interrupts = <0 19 1>;
+			reg-shift = <2>;
+			reg-io-width = <4>;
+			clocks = <&apb1_gates 22>;
+			status = "disabled";
+		};
+
+		uart7: serial@01c29c00 {
+			compatible = "snps,dw-apb-uart";
+			reg = <0x01c29c00 0x400>;
+			interrupts = <0 20 1>;
+			reg-shift = <2>;
+			reg-io-width = <4>;
+			clocks = <&apb1_gates 23>;
+			status = "disabled";
+		};
+
+		gic: interrupt-controller@01c81000 {
+			compatible = "arm,cortex-a7-gic", "arm,cortex-a15-gic";
+			reg = <0x01c81000 0x1000>,
+			      <0x01c82000 0x1000>,
+			      <0x01c84000 0x2000>,
+			      <0x01c86000 0x2000>;
+			interrupt-controller;
+			#interrupt-cells = <3>;
+			interrupts = <1 9 0xf04>;
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/tegra114-dalmore.dts b/arch/arm/boot/dts/tegra114-dalmore.dts
index cb640eb6c932..60230288884b 100644
--- a/arch/arm/boot/dts/tegra114-dalmore.dts
+++ b/arch/arm/boot/dts/tegra114-dalmore.dts
@@ -791,7 +791,7 @@
 					regulator-boot-on;
 				};
 
-				dcdc3 {
+				tps65090_dcdc3_reg: dcdc3 {
 					regulator-name = "vdd-ao";
 					regulator-always-on;
 					regulator-boot-on;
@@ -836,6 +836,182 @@
 				};
 			};
 		};
+
+		palmas: tps65913 {
+			compatible = "ti,palmas";
+			reg = <0x58>;
+			interrupts = <0 86 IRQ_TYPE_LEVEL_LOW>;
+
+			#interrupt-cells = <2>;
+			interrupt-controller;
+
+			ti,system-power-controller;
+
+			palmas_gpio: gpio {
+				compatible = "ti,palmas-gpio";
+				gpio-controller;
+				#gpio-cells = <2>;
+			};
+
+			pmic {
+				compatible = "ti,tps65913-pmic", "ti,palmas-pmic";
+				smps1-in-supply = <&tps65090_dcdc3_reg>;
+				smps3-in-supply = <&tps65090_dcdc3_reg>;
+				smps4-in-supply = <&tps65090_dcdc2_reg>;
+				smps7-in-supply = <&tps65090_dcdc2_reg>;
+				smps8-in-supply = <&tps65090_dcdc2_reg>;
+				smps9-in-supply = <&tps65090_dcdc2_reg>;
+				ldo1-in-supply = <&tps65090_dcdc2_reg>;
+				ldo2-in-supply = <&tps65090_dcdc2_reg>;
+				ldo3-in-supply = <&palmas_smps3_reg>;
+				ldo4-in-supply = <&tps65090_dcdc2_reg>;
+				ldo5-in-supply = <&vdd_ac_bat_reg>;
+				ldo6-in-supply = <&tps65090_dcdc2_reg>;
+				ldo7-in-supply = <&tps65090_dcdc2_reg>;
+				ldo8-in-supply = <&tps65090_dcdc3_reg>;
+				ldo9-in-supply = <&palmas_smps9_reg>;
+				ldoln-in-supply = <&tps65090_dcdc1_reg>;
+				ldousb-in-supply = <&tps65090_dcdc1_reg>;
+
+				regulators {
+					smps12 {
+						regulator-name = "vddio-ddr";
+						regulator-min-microvolt = <1350000>;
+						regulator-max-microvolt = <1350000>;
+						regulator-always-on;
+						regulator-boot-on;
+					};
+
+					palmas_smps3_reg: smps3 {
+						regulator-name = "vddio-1v8";
+						regulator-min-microvolt = <1800000>;
+						regulator-max-microvolt = <1800000>;
+						regulator-always-on;
+						regulator-boot-on;
+					};
+
+					smps45 {
+						regulator-name = "vdd-core";
+						regulator-min-microvolt = <900000>;
+						regulator-max-microvolt = <1400000>;
+						regulator-always-on;
+						regulator-boot-on;
+					};
+
+					smps457 {
+						regulator-name = "vdd-core";
+						regulator-min-microvolt = <900000>;
+						regulator-max-microvolt = <1400000>;
+						regulator-always-on;
+						regulator-boot-on;
+					};
+
+					smps8 {
+						regulator-name = "avdd-pll";
+						regulator-min-microvolt = <1050000>;
+						regulator-max-microvolt = <1050000>;
+						regulator-always-on;
+						regulator-boot-on;
+					};
+
+					palmas_smps9_reg: smps9 {
+						regulator-name = "sdhci-vdd-sd-slot";
+						regulator-min-microvolt = <2800000>;
+						regulator-max-microvolt = <2800000>;
+						regulator-always-on;
+					};
+
+					ldo1 {
+						regulator-name = "avdd-cam1";
+						regulator-min-microvolt = <2800000>;
+						regulator-max-microvolt = <2800000>;
+					};
+
+					ldo2 {
+						regulator-name = "avdd-cam2";
+						regulator-min-microvolt = <2800000>;
+						regulator-max-microvolt = <2800000>;
+					};
+
+					ldo3 {
+						regulator-name = "avdd-dsi-csi";
+						regulator-min-microvolt = <1200000>;
+						regulator-max-microvolt = <1200000>;
+						regulator-always-on;
+						regulator-boot-on;
+					};
+
+					ldo4 {
+						regulator-name = "vpp-fuse";
+						regulator-min-microvolt = <1800000>;
+						regulator-max-microvolt = <1800000>;
+					};
+
+					ldo6 {
+						regulator-name = "vdd-sensor-2v85";
+						regulator-min-microvolt = <2850000>;
+						regulator-max-microvolt = <2850000>;
+					};
+
+					ldo7 {
+						regulator-name = "vdd-af-cam1";
+						regulator-min-microvolt = <2800000>;
+						regulator-max-microvolt = <2800000>;
+					};
+
+					ldo8 {
+						regulator-name = "vdd-rtc";
+						regulator-min-microvolt = <900000>;
+						regulator-max-microvolt = <900000>;
+						regulator-always-on;
+						regulator-boot-on;
+						ti,enable-ldo8-tracking;
+					};
+
+					ldo9 {
+						regulator-name = "vddio-sdmmc-2";
+						regulator-min-microvolt = <1800000>;
+						regulator-max-microvolt = <3300000>;
+						regulator-always-on;
+						regulator-boot-on;
+					};
+
+					ldoln {
+						regulator-name = "hvdd-usb";
+						regulator-min-microvolt = <3300000>;
+						regulator-max-microvolt = <3300000>;
+					};
+
+					ldousb {
+						regulator-name = "avdd-usb";
+						regulator-min-microvolt = <3300000>;
+						regulator-max-microvolt = <3300000>;
+						regulator-always-on;
+						regulator-boot-on;
+					};
+
+					regen1 {
+						regulator-name = "rail-3v3";
+						regulator-max-microvolt = <3300000>;
+						regulator-always-on;
+						regulator-boot-on;
+					};
+
+					regen2 {
+						regulator-name = "rail-5v0";
+						regulator-max-microvolt = <5000000>;
+						regulator-always-on;
+						regulator-boot-on;
+					};
+				};
+			};
+
+			rtc {
+				compatible = "ti,palmas-rtc";
+				interrupt-parent = <&palmas>;
+				interrupts = <8 0>;
+			};
+		};
 	};
 
 	spi@7000da00 {
@@ -850,6 +1026,13 @@
 
 	pmc {
 		nvidia,invert-interrupt;
+		nvidia,suspend-mode = <1>;
+		nvidia,cpu-pwr-good-time = <500>;
+		nvidia,cpu-pwr-off-time = <300>;
+		nvidia,core-pwr-good-time = <641 3845>;
+		nvidia,core-pwr-off-time = <61036>;
+		nvidia,core-power-req-active-high;
+		nvidia,sys-clock-req-active-high;
 	};
 
 	ahub {
@@ -870,6 +1053,15 @@
 		non-removable;
 	};
 
+	usb@7d008000 {
+		status = "okay";
+	};
+
+	usb-phy@7d008000 {
+		status = "okay";
+		vbus-supply = <&usb3_vbus_reg>;
+	};
+
 	clocks {
 		compatible = "simple-bus";
 		#address-cells = <1>;
@@ -883,6 +1075,35 @@
 		};
 	};
 
+	gpio-keys {
+		compatible = "gpio-keys";
+
+		home {
+			label = "Home";
+			gpios = <&gpio TEGRA_GPIO(I, 5) GPIO_ACTIVE_LOW>;
+			linux,code = <102>; /* KEY_HOME */
+		};
+
+		power {
+			label = "Power";
+			gpios = <&gpio TEGRA_GPIO(Q, 0) GPIO_ACTIVE_LOW>;
+			linux,code = <116>; /* KEY_POWER */
+			gpio-key,wakeup;
+		};
+
+		volume_down {
+			label = "Volume Down";
+			gpios = <&gpio TEGRA_GPIO(R, 1) GPIO_ACTIVE_LOW>;
+			linux,code = <114>; /* KEY_VOLUMEDOWN */
+		};
+
+		volume_up {
+			label = "Volume Up";
+			gpios = <&gpio TEGRA_GPIO(R, 2) GPIO_ACTIVE_LOW>;
+			linux,code = <115>; /* KEY_VOLUMEUP */
+		};
+	};
+
 	regulators {
 		compatible = "simple-bus";
 		#address-cells = <1>;
@@ -951,6 +1172,16 @@
 			gpio = <&gpio TEGRA_GPIO(K, 1) GPIO_ACTIVE_HIGH>;
 			vin-supply = <&tps65090_dcdc1_reg>;
 		};
+
+		vdd_cam_1v8_reg: regulator@6 {
+			compatible = "regulator-fixed";
+			reg = <6>;
+			regulator-name = "vdd_cam_1v8_reg";
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <1800000>;
+			enable-active-high;
+			gpio = <&palmas_gpio 6 0>;
+		};
 	};
 
 	sound {
@@ -964,7 +1195,9 @@
 			"Speakers", "SPORP",
 			"Speakers", "SPORN",
 			"Speakers", "SPOLP",
-			"Speakers", "SPOLN";
+			"Speakers", "SPOLN",
+			"Mic Jack", "MICBIAS1",
+			"IN2P", "Mic Jack";
 
 		nvidia,i2s-controller = <&tegra_i2s1>;
 		nvidia,audio-codec = <&rt5640>;
diff --git a/arch/arm/boot/dts/tegra114-pluto.dts b/arch/arm/boot/dts/tegra114-pluto.dts
deleted file mode 100644
index d5f8d3e0bde2..000000000000
--- a/arch/arm/boot/dts/tegra114-pluto.dts
+++ /dev/null
@@ -1,33 +0,0 @@
-/dts-v1/;
-
-#include "tegra114.dtsi"
-
-/ {
-	model = "NVIDIA Tegra114 Pluto evaluation board";
-	compatible = "nvidia,pluto", "nvidia,tegra114";
-
-	memory {
-		reg = <0x80000000 0x40000000>;
-	};
-
-	serial@70006300 {
-		status = "okay";
-	};
-
-	pmc {
-		nvidia,invert-interrupt;
-	};
-
-	clocks {
-		compatible = "simple-bus";
-		#address-cells = <1>;
-		#size-cells = <0>;
-
-		clk32k_in: clock {
-			compatible = "fixed-clock";
-			reg=<0>;
-			#clock-cells = <0>;
-			clock-frequency = <32768>;
-		};
-	};
-};
diff --git a/arch/arm/boot/dts/tegra114.dtsi b/arch/arm/boot/dts/tegra114.dtsi
index abf6c40d28c6..2905145d8e59 100644
--- a/arch/arm/boot/dts/tegra114.dtsi
+++ b/arch/arm/boot/dts/tegra114.dtsi
@@ -430,6 +430,68 @@
 		status = "disable";
 	};
 
+	usb@7d000000 {
+		compatible = "nvidia,tegra30-ehci", "usb-ehci";
+		reg = <0x7d000000 0x4000>;
+		interrupts = <GIC_SPI 20 IRQ_TYPE_LEVEL_HIGH>;
+		phy_type = "utmi";
+		clocks = <&tegra_car TEGRA114_CLK_USBD>;
+		nvidia,phy = <&phy1>;
+		status = "disabled";
+	};
+
+	phy1: usb-phy@7d000000 {
+		compatible = "nvidia,tegra30-usb-phy";
+		reg = <0x7d000000 0x4000 0x7d000000 0x4000>;
+		phy_type = "utmi";
+		clocks = <&tegra_car TEGRA114_CLK_USBD>,
+			 <&tegra_car TEGRA114_CLK_PLL_U>,
+			 <&tegra_car TEGRA114_CLK_USBD>;
+		clock-names = "reg", "pll_u", "utmi-pads";
+		nvidia,hssync-start-delay = <0>;
+		nvidia,idle-wait-delay = <17>;
+		nvidia,elastic-limit = <16>;
+		nvidia,term-range-adj = <6>;
+		nvidia,xcvr-setup = <9>;
+		nvidia,xcvr-lsfslew = <0>;
+		nvidia,xcvr-lsrslew = <3>;
+		nvidia,hssquelch-level = <2>;
+		nvidia,hsdiscon-level = <5>;
+		nvidia,xcvr-hsslew = <12>;
+		status = "disabled";
+	};
+
+	usb@7d008000 {
+		compatible = "nvidia,tegra30-ehci", "usb-ehci";
+		reg = <0x7d008000 0x4000>;
+		interrupts = <GIC_SPI 97 IRQ_TYPE_LEVEL_HIGH>;
+		phy_type = "utmi";
+		clocks = <&tegra_car TEGRA114_CLK_USB3>;
+		nvidia,phy = <&phy3>;
+		status = "disabled";
+	};
+
+	phy3: usb-phy@7d008000 {
+		compatible = "nvidia,tegra30-usb-phy";
+		reg = <0x7d008000 0x4000 0x7d000000 0x4000>;
+		phy_type = "utmi";
+		clocks = <&tegra_car TEGRA114_CLK_USB3>,
+			 <&tegra_car TEGRA114_CLK_PLL_U>,
+			 <&tegra_car TEGRA114_CLK_USBD>;
+		clock-names = "reg", "pll_u", "utmi-pads";
+		nvidia,hssync-start-delay = <0>;
+		nvidia,idle-wait-delay = <17>;
+		nvidia,elastic-limit = <16>;
+		nvidia,term-range-adj = <6>;
+		nvidia,xcvr-setup = <9>;
+		nvidia,xcvr-lsfslew = <0>;
+		nvidia,xcvr-lsrslew = <3>;
+		nvidia,hssquelch-level = <2>;
+		nvidia,hsdiscon-level = <5>;
+		nvidia,xcvr-hsslew = <12>;
+		status = "disabled";
+	};
+
 	cpus {
 		#address-cells = <1>;
 		#size-cells = <0>;
diff --git a/arch/arm/boot/dts/tegra20-colibri-512.dtsi b/arch/arm/boot/dts/tegra20-colibri-512.dtsi
index 5592be6f2f7a..d5c9bca01232 100644
--- a/arch/arm/boot/dts/tegra20-colibri-512.dtsi
+++ b/arch/arm/boot/dts/tegra20-colibri-512.dtsi
@@ -363,7 +363,7 @@
 	};
 
 	pmc {
-		nvidia,suspend-mode = <2>;
+		nvidia,suspend-mode = <1>;
 		nvidia,cpu-pwr-good-time = <5000>;
 		nvidia,cpu-pwr-off-time = <5000>;
 		nvidia,core-pwr-good-time = <3845 3845>;
diff --git a/arch/arm/boot/dts/tegra20-harmony.dts b/arch/arm/boot/dts/tegra20-harmony.dts
index d9f89cd879a7..e156ab30e763 100644
--- a/arch/arm/boot/dts/tegra20-harmony.dts
+++ b/arch/arm/boot/dts/tegra20-harmony.dts
@@ -335,7 +335,7 @@
 					regulator-always-on;
 				};
 
-				ldo0 {
+				pci_clk_reg: ldo0 {
 					regulator-name = "vdd_ldo0,vddio_pex_clk";
 					regulator-min-microvolt = <3300000>;
 					regulator-max-microvolt = <3300000>;
@@ -417,7 +417,7 @@
 
 	pmc {
 		nvidia,invert-interrupt;
-		nvidia,suspend-mode = <2>;
+		nvidia,suspend-mode = <1>;
 		nvidia,cpu-pwr-good-time = <5000>;
 		nvidia,cpu-pwr-off-time = <5000>;
 		nvidia,core-pwr-good-time = <3845 3845>;
@@ -425,6 +425,20 @@
 		nvidia,sys-clock-req-active-high;
 	};
 
+	pcie-controller {
+		pex-clk-supply = <&pci_clk_reg>;
+		vdd-supply = <&pci_vdd_reg>;
+		status = "okay";
+
+		pci@1,0 {
+			status = "okay";
+		};
+
+		pci@2,0 {
+			status = "okay";
+		};
+	};
+
 	usb@c5000000 {
 		status = "okay";
 	};
@@ -643,7 +657,7 @@
 			enable-active-high;
 		};
 
-		regulator@3 {
+		pci_vdd_reg: regulator@3 {
 			compatible = "regulator-fixed";
 			reg = <3>;
 			regulator-name = "vdd_1v05";
@@ -651,8 +665,6 @@
 			regulator-max-microvolt = <1050000>;
 			gpio = <&pmic 2 GPIO_ACTIVE_HIGH>;
 			enable-active-high;
-			/* Hack until board-harmony-pcie.c is removed */
-			status = "disabled";
 		};
 
 		regulator@4 {
diff --git a/arch/arm/boot/dts/tegra20-paz00.dts b/arch/arm/boot/dts/tegra20-paz00.dts
index cfd12763b1b2..8d71fc9d8a2f 100644
--- a/arch/arm/boot/dts/tegra20-paz00.dts
+++ b/arch/arm/boot/dts/tegra20-paz00.dts
@@ -417,7 +417,7 @@
 
 	pmc {
 		nvidia,invert-interrupt;
-		nvidia,suspend-mode = <2>;
+		nvidia,suspend-mode = <1>;
 		nvidia,cpu-pwr-good-time = <2000>;
 		nvidia,cpu-pwr-off-time = <0>;
 		nvidia,core-pwr-good-time = <3845 3845>;
diff --git a/arch/arm/boot/dts/tegra20-seaboard.dts b/arch/arm/boot/dts/tegra20-seaboard.dts
index 40e6fb280333..315aae26c3cd 100644
--- a/arch/arm/boot/dts/tegra20-seaboard.dts
+++ b/arch/arm/boot/dts/tegra20-seaboard.dts
@@ -518,7 +518,7 @@
 
 	pmc {
 		nvidia,invert-interrupt;
-		nvidia,suspend-mode = <2>;
+		nvidia,suspend-mode = <1>;
 		nvidia,cpu-pwr-good-time = <5000>;
 		nvidia,cpu-pwr-off-time = <5000>;
 		nvidia,core-pwr-good-time = <3845 3845>;
@@ -566,7 +566,6 @@
 
 	usb@c5000000 {
 		status = "okay";
-		nvidia,vbus-gpio = <&gpio TEGRA_GPIO(D, 0) GPIO_ACTIVE_HIGH>;
 		dr_mode = "otg";
 	};
 
@@ -829,7 +828,7 @@
 			regulator-min-microvolt = <5000000>;
 			regulator-max-microvolt = <5000000>;
 			enable-active-high;
-			gpio = <&gpio 24 0>; /* PD0 */
+			gpio = <&gpio TEGRA_GPIO(D, 0) 0>;
 			regulator-always-on;
 			regulator-boot-on;
 		};
diff --git a/arch/arm/boot/dts/tegra20-tamonten.dtsi b/arch/arm/boot/dts/tegra20-tamonten.dtsi
index c54faae7cfb3..7726dab3d08d 100644
--- a/arch/arm/boot/dts/tegra20-tamonten.dtsi
+++ b/arch/arm/boot/dts/tegra20-tamonten.dtsi
@@ -366,7 +366,7 @@
 					regulator-always-on;
 				};
 
-				ldo0 {
+				pci_clk_reg: ldo0 {
 					regulator-name = "vdd_ldo0,vddio_pex_clk";
 					regulator-min-microvolt = <3300000>;
 					regulator-max-microvolt = <3300000>;
@@ -459,7 +459,7 @@
 
 	pmc {
 		nvidia,invert-interrupt;
-		nvidia,suspend-mode = <2>;
+		nvidia,suspend-mode = <1>;
 		nvidia,cpu-pwr-good-time = <5000>;
 		nvidia,cpu-pwr-off-time = <5000>;
 		nvidia,core-pwr-good-time = <3845 3845>;
@@ -467,6 +467,11 @@
 		nvidia,sys-clock-req-active-high;
 	};
 
+	pcie-controller {
+		pex-clk-supply = <&pci_clk_reg>;
+		vdd-supply = <&pci_vdd_reg>;
+	};
+
 	usb@c5008000 {
 		status = "okay";
 	};
@@ -509,5 +514,15 @@
 			regulator-max-microvolt = <5000000>;
 			regulator-always-on;
 		};
+
+		pci_vdd_reg: regulator@1 {
+			compatible = "regulator-fixed";
+			reg = <1>;
+			regulator-name = "vdd_1v05";
+			regulator-min-microvolt = <1050000>;
+			regulator-max-microvolt = <1050000>;
+			gpio = <&pmic 2 0>;
+			enable-active-high;
+		};
 	};
 };
diff --git a/arch/arm/boot/dts/tegra20-tec.dts b/arch/arm/boot/dts/tegra20-tec.dts
index c572c43751b1..3ada3cb67f07 100644
--- a/arch/arm/boot/dts/tegra20-tec.dts
+++ b/arch/arm/boot/dts/tegra20-tec.dts
@@ -32,6 +32,14 @@
 		};
 	};
 
+	pcie-controller {
+		status = "okay";
+
+		pci@1,0 {
+			status = "okay";
+		};
+	};
+
 	sound {
 		compatible = "ad,tegra-audio-wm8903-tec",
 			     "nvidia,tegra-audio-wm8903";
diff --git a/arch/arm/boot/dts/tegra20-trimslice.dts b/arch/arm/boot/dts/tegra20-trimslice.dts
index 37c93d3c4812..78deea5c0d21 100644
--- a/arch/arm/boot/dts/tegra20-trimslice.dts
+++ b/arch/arm/boot/dts/tegra20-trimslice.dts
@@ -302,7 +302,7 @@
 	};
 
 	pmc {
-		nvidia,suspend-mode = <2>;
+		nvidia,suspend-mode = <1>;
 		nvidia,cpu-pwr-good-time = <5000>;
 		nvidia,cpu-pwr-off-time = <5000>;
 		nvidia,core-pwr-good-time = <3845 3845>;
@@ -310,9 +310,18 @@
 		nvidia,sys-clock-req-active-high;
 	};
 
+	pcie-controller {
+		status = "okay";
+		pex-clk-supply = <&pci_clk_reg>;
+		vdd-supply = <&pci_vdd_reg>;
+
+		pci@1,0 {
+			status = "okay";
+		};
+	};
+
 	usb@c5000000 {
 		status = "okay";
-		nvidia,vbus-gpio = <&gpio TEGRA_GPIO(V, 2) GPIO_ACTIVE_HIGH>;
 	};
 
 	usb-phy@c5000000 {
@@ -411,10 +420,28 @@
 			regulator-min-microvolt = <5000000>;
 			regulator-max-microvolt = <5000000>;
 			enable-active-high;
-			gpio = <&gpio 170 0>; /* PV2 */
+			gpio = <&gpio TEGRA_GPIO(V, 2) 0>;
 			regulator-always-on;
 			regulator-boot-on;
 		};
+
+		pci_clk_reg: regulator@3 {
+			compatible = "regulator-fixed";
+			reg = <3>;
+			regulator-name = "pci_clk";
+			regulator-min-microvolt = <3300000>;
+			regulator-max-microvolt = <3300000>;
+			regulator-always-on;
+		};
+
+		pci_vdd_reg: regulator@4 {
+			compatible = "regulator-fixed";
+			reg = <4>;
+			regulator-name = "pci_vdd";
+			regulator-min-microvolt = <1050000>;
+			regulator-max-microvolt = <1050000>;
+			regulator-always-on;
+		};
 	};
 
 	sound {
diff --git a/arch/arm/boot/dts/tegra20-ventana.dts b/arch/arm/boot/dts/tegra20-ventana.dts
index 7f8c28d1121f..aab872cd0530 100644
--- a/arch/arm/boot/dts/tegra20-ventana.dts
+++ b/arch/arm/boot/dts/tegra20-ventana.dts
@@ -494,7 +494,7 @@
 
 	pmc {
 		nvidia,invert-interrupt;
-		nvidia,suspend-mode = <2>;
+		nvidia,suspend-mode = <1>;
 		nvidia,cpu-pwr-good-time = <2000>;
 		nvidia,cpu-pwr-off-time = <100>;
 		nvidia,core-pwr-good-time = <3845 3845>;
diff --git a/arch/arm/boot/dts/tegra20-whistler.dts b/arch/arm/boot/dts/tegra20-whistler.dts
index a3d0ebad78a1..d33a73cf167c 100644
--- a/arch/arm/boot/dts/tegra20-whistler.dts
+++ b/arch/arm/boot/dts/tegra20-whistler.dts
@@ -497,7 +497,7 @@
 
 	pmc {
 		nvidia,invert-interrupt;
-		nvidia,suspend-mode = <2>;
+		nvidia,suspend-mode = <1>;
 		nvidia,cpu-pwr-good-time = <2000>;
 		nvidia,cpu-pwr-off-time = <1000>;
 		nvidia,core-pwr-good-time = <0 3845>;
@@ -509,7 +509,6 @@
 
 	usb@c5000000 {
 		status = "okay";
-		nvidia,vbus-gpio = <&tca6416 0 GPIO_ACTIVE_HIGH>;
 	};
 
 	usb-phy@c5000000 {
@@ -519,7 +518,6 @@
 
 	usb@c5008000 {
 		status = "okay";
-		nvidia,vbus-gpio = <&tca6416 1 GPIO_ACTIVE_HIGH>;
 	};
 
 	usb-phy@c5008000 {
diff --git a/arch/arm/boot/dts/tegra20.dtsi b/arch/arm/boot/dts/tegra20.dtsi
index 9653fd8288d2..df40b54fd8bc 100644
--- a/arch/arm/boot/dts/tegra20.dtsi
+++ b/arch/arm/boot/dts/tegra20.dtsi
@@ -455,6 +455,61 @@
 		#size-cells = <0>;
 	};
 
+	pcie-controller {
+		compatible = "nvidia,tegra20-pcie";
+		device_type = "pci";
+		reg = <0x80003000 0x00000800   /* PADS registers */
+		       0x80003800 0x00000200   /* AFI registers */
+		       0x90000000 0x10000000>; /* configuration space */
+		reg-names = "pads", "afi", "cs";
+		interrupts = <GIC_SPI 98 IRQ_TYPE_LEVEL_HIGH   /* controller interrupt */
+			      GIC_SPI 99 IRQ_TYPE_LEVEL_HIGH>; /* MSI interrupt */
+		interrupt-names = "intr", "msi";
+
+		bus-range = <0x00 0xff>;
+		#address-cells = <3>;
+		#size-cells = <2>;
+
+		ranges = <0x82000000 0 0x80000000 0x80000000 0 0x00001000   /* port 0 registers */
+			  0x82000000 0 0x80001000 0x80001000 0 0x00001000   /* port 1 registers */
+			  0x81000000 0 0          0x82000000 0 0x00010000   /* downstream I/O */
+			  0x82000000 0 0xa0000000 0xa0000000 0 0x08000000   /* non-prefetchable memory */
+			  0xc2000000 0 0xa8000000 0xa8000000 0 0x18000000>; /* prefetchable memory */
+
+		clocks = <&tegra_car TEGRA20_CLK_PEX>,
+			 <&tegra_car TEGRA20_CLK_AFI>,
+			 <&tegra_car TEGRA20_CLK_PCIE_XCLK>,
+			 <&tegra_car TEGRA20_CLK_PLL_E>;
+		clock-names = "pex", "afi", "pcie_xclk", "pll_e";
+		status = "disabled";
+
+		pci@1,0 {
+			device_type = "pci";
+			assigned-addresses = <0x82000800 0 0x80000000 0 0x1000>;
+			reg = <0x000800 0 0 0 0>;
+			status = "disabled";
+
+			#address-cells = <3>;
+			#size-cells = <2>;
+			ranges;
+
+			nvidia,num-lanes = <2>;
+		};
+
+		pci@2,0 {
+			device_type = "pci";
+			assigned-addresses = <0x82001000 0 0x80001000 0 0x1000>;
+			reg = <0x001000 0 0 0 0>;
+			status = "disabled";
+
+			#address-cells = <3>;
+			#size-cells = <2>;
+			ranges;
+
+			nvidia,num-lanes = <2>;
+		};
+	};
+
 	usb@c5000000 {
 		compatible = "nvidia,tegra20-ehci", "usb-ehci";
 		reg = <0xc5000000 0x4000>;
@@ -477,13 +532,13 @@
 			 <&tegra_car TEGRA20_CLK_USBD>;
 		clock-names = "reg", "pll_u", "timer", "utmi-pads";
 		nvidia,has-legacy-mode;
-		hssync_start_delay = <9>;
-		idle_wait_delay = <17>;
-		elastic_limit = <16>;
-		term_range_adj = <6>;
-		xcvr_setup = <9>;
-		xcvr_lsfslew = <1>;
-		xcvr_lsrslew = <1>;
+		nvidia,hssync-start-delay = <9>;
+		nvidia,idle-wait-delay = <17>;
+		nvidia,elastic-limit = <16>;
+		nvidia,term-range-adj = <6>;
+		nvidia,xcvr-setup = <9>;
+		nvidia,xcvr-lsfslew = <1>;
+		nvidia,xcvr-lsrslew = <1>;
 		status = "disabled";
 	};
 
@@ -527,13 +582,13 @@
 			 <&tegra_car TEGRA20_CLK_CLK_M>,
 			 <&tegra_car TEGRA20_CLK_USBD>;
 		clock-names = "reg", "pll_u", "timer", "utmi-pads";
-		hssync_start_delay = <9>;
-		idle_wait_delay = <17>;
-		elastic_limit = <16>;
-		term_range_adj = <6>;
-		xcvr_setup = <9>;
-		xcvr_lsfslew = <2>;
-		xcvr_lsrslew = <2>;
+		nvidia,hssync-start-delay = <9>;
+		nvidia,idle-wait-delay = <17>;
+		nvidia,elastic-limit = <16>;
+		nvidia,term-range-adj = <6>;
+		nvidia,xcvr-setup = <9>;
+		nvidia,xcvr-lsfslew = <2>;
+		nvidia,xcvr-lsrslew = <2>;
 		status = "disabled";
 	};
 
diff --git a/arch/arm/boot/dts/tegra30-beaver.dts b/arch/arm/boot/dts/tegra30-beaver.dts
index 87c5f7b7c271..08cad696e89f 100644
--- a/arch/arm/boot/dts/tegra30-beaver.dts
+++ b/arch/arm/boot/dts/tegra30-beaver.dts
@@ -10,6 +10,40 @@
 		reg = <0x80000000 0x7ff00000>;
 	};
 
+	pcie-controller {
+		status = "okay";
+		pex-clk-supply = <&sys_3v3_pexs_reg>;
+		vdd-supply = <&ldo1_reg>;
+		avdd-supply = <&ldo2_reg>;
+
+		pci@1,0 {
+			status = "okay";
+			nvidia,num-lanes = <2>;
+		};
+
+		pci@2,0 {
+			nvidia,num-lanes = <2>;
+		};
+
+		pci@3,0 {
+			status = "okay";
+			nvidia,num-lanes = <2>;
+		};
+	};
+
+	host1x {
+		hdmi {
+			status = "okay";
+
+			vdd-supply = <&sys_3v3_reg>;
+			pll-supply = <&vio_reg>;
+
+			nvidia,hpd-gpio =
+				<&gpio TEGRA_GPIO(N, 7) GPIO_ACTIVE_HIGH>;
+			nvidia,ddc-i2c-bus = <&hdmiddc>;
+		};
+	};
+
 	pinmux {
 		pinctrl-names = "default";
 		pinctrl-0 = <&state_default>;
@@ -76,6 +110,11 @@
 				nvidia,pull = <0>;
 				nvidia,tristate = <0>;
 			};
+			pex_l1_prsnt_n_pdd4 {
+				nvidia,pins =	"pex_l1_prsnt_n_pdd4",
+						"pex_l1_clkreq_n_pdd6";
+				nvidia,pull = <2>;
+			};
 			sdio3 {
 				nvidia,pins = "drive_sdio3";
 				nvidia,high-speed-mode = <0>;
@@ -85,6 +124,10 @@
 				nvidia,slew-rate-rising = <1>;
 				nvidia,slew-rate-falling = <1>;
 			};
+			gpv {
+				nvidia,pins = "drive_gpv";
+				nvidia,pull-up-strength = <16>;
+			};
 		};
 	};
 
@@ -107,7 +150,7 @@
 		clock-frequency = <100000>;
 	};
 
-	i2c@7000c700 {
+	hdmiddc: i2c@7000c700 {
 		status = "okay";
 		clock-frequency = <100000>;
 	};
@@ -262,7 +305,7 @@
 	pmc {
 		status = "okay";
 		nvidia,invert-interrupt;
-		nvidia,suspend-mode = <2>;
+		nvidia,suspend-mode = <1>;
 		nvidia,cpu-pwr-good-time = <2000>;
 		nvidia,cpu-pwr-off-time = <200>;
 		nvidia,core-pwr-good-time = <3845 3845>;
@@ -285,6 +328,15 @@
 		non-removable;
 	};
 
+	usb@7d008000 {
+		status = "okay";
+	};
+
+	usb-phy@7d008000 {
+		vbus-supply = <&usb3_vbus_reg>;
+		status = "okay";
+	};
+
 	clocks {
 		compatible = "simple-bus";
 		#address-cells = <1>;
@@ -357,7 +409,7 @@
 			regulator-min-microvolt = <5000000>;
 			regulator-max-microvolt = <5000000>;
 			enable-active-high;
-			gpio = <&gpio TEGRA_GPIO(I, 4) GPIO_ACTIVE_HIGH>;
+			gpio = <&gpio TEGRA_GPIO(DD, 6) GPIO_ACTIVE_HIGH>;
 			gpio-open-drain;
 			vin-supply = <&vdd_5v_in_reg>;
 		};
@@ -369,7 +421,7 @@
 			regulator-min-microvolt = <5000000>;
 			regulator-max-microvolt = <5000000>;
 			enable-active-high;
-			gpio = <&gpio TEGRA_GPIO(H, 7) GPIO_ACTIVE_HIGH>;
+			gpio = <&gpio TEGRA_GPIO(DD, 4) GPIO_ACTIVE_HIGH>;
 			gpio-open-drain;
 			vin-supply = <&vdd_5v_in_reg>;
 		};
@@ -421,7 +473,9 @@
 
 		nvidia,audio-routing =
 			"Headphones", "HPOR",
-			"Headphones", "HPOL";
+			"Headphones", "HPOL",
+			"Mic Jack", "MICBIAS1",
+			"IN2P", "Mic Jack";
 
 		nvidia,i2s-controller = <&tegra_i2s1>;
 		nvidia,audio-codec = <&rt5640>;
diff --git a/arch/arm/boot/dts/tegra30-cardhu.dtsi b/arch/arm/boot/dts/tegra30-cardhu.dtsi
index f65b53d32416..e19dbf238e5c 100644
--- a/arch/arm/boot/dts/tegra30-cardhu.dtsi
+++ b/arch/arm/boot/dts/tegra30-cardhu.dtsi
@@ -31,6 +31,26 @@
 		reg = <0x80000000 0x40000000>;
 	};
 
+	pcie-controller {
+		status = "okay";
+		pex-clk-supply = <&pex_hvdd_3v3_reg>;
+		vdd-supply = <&ldo1_reg>;
+		avdd-supply = <&ldo2_reg>;
+
+		pci@1,0 {
+			nvidia,num-lanes = <4>;
+		};
+
+		pci@2,0 {
+			nvidia,num-lanes = <1>;
+		};
+
+		pci@3,0 {
+			status = "okay";
+			nvidia,num-lanes = <1>;
+		};
+	};
+
 	pinmux {
 		pinctrl-names = "default";
 		pinctrl-0 = <&state_default>;
@@ -173,19 +193,6 @@
 			gpio-cfg = <0xffffffff 0xffffffff 0 0xffffffff 0xffffffff>;
 		};
 
-		tps62361 {
-			compatible = "ti,tps62361";
-			reg = <0x60>;
-
-			regulator-name = "tps62361-vout";
-			regulator-min-microvolt = <500000>;
-			regulator-max-microvolt = <1500000>;
-			regulator-boot-on;
-			regulator-always-on;
-			ti,vsel0-state-high;
-			ti,vsel1-state-high;
-		};
-
 		pmic: tps65911@2d {
 			compatible = "ti,tps65911";
 			reg = <0x2d>;
@@ -286,6 +293,26 @@
 				};
 			};
 		};
+
+		nct1008 {
+			compatible = "onnn,nct1008";
+			reg = <0x4c>;
+			interrupt-parent = <&gpio>;
+			interrupts = <TEGRA_GPIO(CC, 2) IRQ_TYPE_LEVEL_LOW>;
+		};
+
+		tps62361 {
+			compatible = "ti,tps62361";
+			reg = <0x60>;
+
+			regulator-name = "tps62361-vout";
+			regulator-min-microvolt = <500000>;
+			regulator-max-microvolt = <1500000>;
+			regulator-boot-on;
+			regulator-always-on;
+			ti,vsel0-state-high;
+			ti,vsel1-state-high;
+		};
 	};
 
 	spi@7000da00 {
@@ -307,7 +334,7 @@
 	pmc {
 		status = "okay";
 		nvidia,invert-interrupt;
-		nvidia,suspend-mode = <2>;
+		nvidia,suspend-mode = <1>;
 		nvidia,cpu-pwr-good-time = <2000>;
 		nvidia,cpu-pwr-off-time = <200>;
 		nvidia,core-pwr-good-time = <3845 3845>;
@@ -330,6 +357,15 @@
 		non-removable;
 	};
 
+	usb@7d008000 {
+		status = "okay";
+	};
+
+	usb-phy@7d008000 {
+		vbus-supply = <&usb3_vbus_reg>;
+		status = "okay";
+	};
+
 	clocks {
 		compatible = "simple-bus";
 		#address-cells = <1>;
diff --git a/arch/arm/boot/dts/tegra30.dtsi b/arch/arm/boot/dts/tegra30.dtsi
index d8783f0fae63..0022c127e1d9 100644
--- a/arch/arm/boot/dts/tegra30.dtsi
+++ b/arch/arm/boot/dts/tegra30.dtsi
@@ -16,6 +16,76 @@
 		serial4 = &uarte;
 	};
 
+	pcie-controller {
+		compatible = "nvidia,tegra30-pcie";
+		device_type = "pci";
+		reg = <0x00003000 0x00000800   /* PADS registers */
+		       0x00003800 0x00000200   /* AFI registers */
+		       0x10000000 0x10000000>; /* configuration space */
+		reg-names = "pads", "afi", "cs";
+		interrupts = <GIC_SPI 98 IRQ_TYPE_LEVEL_HIGH   /* controller interrupt */
+			      GIC_SPI 99 IRQ_TYPE_LEVEL_HIGH>; /* MSI interrupt */
+		interrupt-names = "intr", "msi";
+
+		bus-range = <0x00 0xff>;
+		#address-cells = <3>;
+		#size-cells = <2>;
+
+		ranges = <0x82000000 0 0x00000000 0x00000000 0 0x00001000   /* port 0 configuration space */
+			  0x82000000 0 0x00001000 0x00001000 0 0x00001000   /* port 1 configuration space */
+			  0x82000000 0 0x00004000 0x00004000 0 0x00001000   /* port 2 configuration space */
+			  0x81000000 0 0          0x02000000 0 0x00010000   /* downstream I/O */
+			  0x82000000 0 0x20000000 0x20000000 0 0x08000000   /* non-prefetchable memory */
+			  0xc2000000 0 0x28000000 0x28000000 0 0x18000000>; /* prefetchable memory */
+
+		clocks = <&tegra_car TEGRA30_CLK_PCIE>,
+			 <&tegra_car TEGRA30_CLK_AFI>,
+			 <&tegra_car TEGRA30_CLK_PCIEX>,
+			 <&tegra_car TEGRA30_CLK_PLL_E>,
+			 <&tegra_car TEGRA30_CLK_CML0>;
+		clock-names = "pex", "afi", "pcie_xclk", "pll_e", "cml";
+		status = "disabled";
+
+		pci@1,0 {
+			device_type = "pci";
+			assigned-addresses = <0x82000800 0 0x00000000 0 0x1000>;
+			reg = <0x000800 0 0 0 0>;
+			status = "disabled";
+
+			#address-cells = <3>;
+			#size-cells = <2>;
+			ranges;
+
+			nvidia,num-lanes = <2>;
+		};
+
+		pci@2,0 {
+			device_type = "pci";
+			assigned-addresses = <0x82001000 0 0x00001000 0 0x1000>;
+			reg = <0x001000 0 0 0 0>;
+			status = "disabled";
+
+			#address-cells = <3>;
+			#size-cells = <2>;
+			ranges;
+
+			nvidia,num-lanes = <2>;
+		};
+
+		pci@3,0 {
+			device_type = "pci";
+			assigned-addresses = <0x82001800 0 0x00004000 0 0x1000>;
+			reg = <0x001800 0 0 0 0>;
+			status = "disabled";
+
+			#address-cells = <3>;
+			#size-cells = <2>;
+			ranges;
+
+			nvidia,num-lanes = <2>;
+		};
+	};
+
 	host1x {
 		compatible = "nvidia,tegra30-host1x", "simple-bus";
 		reg = <0x50000000 0x00024000>;
@@ -561,6 +631,92 @@
 		status = "disabled";
 	};
 
+	usb@7d000000 {
+		compatible = "nvidia,tegra30-ehci", "usb-ehci";
+		reg = <0x7d000000 0x4000>;
+		interrupts = <GIC_SPI 20 IRQ_TYPE_LEVEL_HIGH>;
+		phy_type = "utmi";
+		clocks = <&tegra_car TEGRA30_CLK_USBD>;
+		nvidia,needs-double-reset;
+		nvidia,phy = <&phy1>;
+		status = "disabled";
+	};
+
+	phy1: usb-phy@7d000000 {
+		compatible = "nvidia,tegra30-usb-phy";
+		reg = <0x7d000000 0x4000 0x7d000000 0x4000>;
+		phy_type = "utmi";
+		clocks = <&tegra_car TEGRA30_CLK_USBD>,
+			 <&tegra_car TEGRA30_CLK_PLL_U>,
+			 <&tegra_car TEGRA30_CLK_USBD>;
+		clock-names = "reg", "pll_u", "utmi-pads";
+		nvidia,hssync-start-delay = <9>;
+		nvidia,idle-wait-delay = <17>;
+		nvidia,elastic-limit = <16>;
+		nvidia,term-range-adj = <6>;
+		nvidia,xcvr-setup = <51>;
+		nvidia.xcvr-setup-use-fuses;
+		nvidia,xcvr-lsfslew = <1>;
+		nvidia,xcvr-lsrslew = <1>;
+		nvidia,xcvr-hsslew = <32>;
+		nvidia,hssquelch-level = <2>;
+		nvidia,hsdiscon-level = <5>;
+		status = "disabled";
+	};
+
+	usb@7d004000 {
+		compatible = "nvidia,tegra30-ehci", "usb-ehci";
+		reg = <0x7d004000 0x4000>;
+		interrupts = <GIC_SPI 21 IRQ_TYPE_LEVEL_HIGH>;
+		phy_type = "ulpi";
+		clocks = <&tegra_car TEGRA30_CLK_USB2>;
+		nvidia,phy = <&phy2>;
+		status = "disabled";
+	};
+
+	phy2: usb-phy@7d004000 {
+		compatible = "nvidia,tegra30-usb-phy";
+		reg = <0x7d004000 0x4000>;
+		phy_type = "ulpi";
+		clocks = <&tegra_car TEGRA30_CLK_USB2>,
+			 <&tegra_car TEGRA30_CLK_PLL_U>,
+			 <&tegra_car TEGRA30_CLK_CDEV2>;
+		clock-names = "reg", "pll_u", "ulpi-link";
+		status = "disabled";
+	};
+
+	usb@7d008000 {
+		compatible = "nvidia,tegra30-ehci", "usb-ehci";
+		reg = <0x7d008000 0x4000>;
+		interrupts = <GIC_SPI 97 IRQ_TYPE_LEVEL_HIGH>;
+		phy_type = "utmi";
+		clocks = <&tegra_car TEGRA30_CLK_USB3>;
+		nvidia,phy = <&phy3>;
+		status = "disabled";
+	};
+
+	phy3: usb-phy@7d008000 {
+		compatible = "nvidia,tegra30-usb-phy";
+		reg = <0x7d008000 0x4000 0x7d000000 0x4000>;
+		phy_type = "utmi";
+		clocks = <&tegra_car TEGRA30_CLK_USB3>,
+			 <&tegra_car TEGRA30_CLK_PLL_U>,
+			 <&tegra_car TEGRA30_CLK_USBD>;
+		clock-names = "reg", "pll_u", "utmi-pads";
+		nvidia,hssync-start-delay = <0>;
+		nvidia,idle-wait-delay = <17>;
+		nvidia,elastic-limit = <16>;
+		nvidia,term-range-adj = <6>;
+		nvidia,xcvr-setup = <51>;
+		nvidia.xcvr-setup-use-fuses;
+		nvidia,xcvr-lsfslew = <2>;
+		nvidia,xcvr-lsrslew = <2>;
+		nvidia,xcvr-hsslew = <32>;
+		nvidia,hssquelch-level = <2>;
+		nvidia,hsdiscon-level = <5>;
+		status = "disabled";
+	};
+
 	cpus {
 		#address-cells = <1>;
 		#size-cells = <0>;
diff --git a/arch/arm/boot/dts/u9540.dts b/arch/arm/boot/dts/u9540.dts
deleted file mode 100644
index 95892ec6c342..000000000000
--- a/arch/arm/boot/dts/u9540.dts
+++ /dev/null
@@ -1,72 +0,0 @@
-/*
- * Copyright 2012 ST-Ericsson AB
- *
- * The code contained herein is licensed under the GNU General Public
- * License. You may obtain a copy of the GNU General Public License
- * Version 2 or later at the following locations:
- *
- * http://www.opensource.org/licenses/gpl-license.html
- * http://www.gnu.org/copyleft/gpl.html
- */
-
-/dts-v1/;
-/include/ "dbx5x0.dtsi"
-
-/ {
-	model = "ST-Ericsson U9540 platform with Device Tree";
-	compatible = "st-ericsson,u9540";
-
-	memory {
-		reg = <0x00000000 0x20000000>;
-	};
-
-	soc-u9500 {
-		uart@80120000 {
-			status = "okay";
-		};
-
-		uart@80121000 {
-			status = "okay";
-		};
-
-		uart@80007000 {
-			status = "okay";
-		};
-
-		// External Micro SD slot
-		sdi0_per1@80126000 {
-			arm,primecell-periphid = <0x10480180>;
-			max-frequency = <100000000>;
-			bus-width = <4>;
-			mmc-cap-sd-highspeed;
-			mmc-cap-mmc-highspeed;
-			vmmc-supply = <&ab8500_ldo_aux3_reg>;
-
-			cd-gpios  = <&gpio7 6 0x4>; // 230
-			cd-inverted;
-
-			status = "okay";
-		};
-
-
-		// WLAN SDIO channel
-		sdi1_per2@80118000 {
-			arm,primecell-periphid = <0x10480180>;
-			max-frequency = <50000000>;
-			bus-width = <4>;
-
-			status = "okay";
-		};
-
-		// On-board eMMC
-		sdi4_per2@80114000 {
-			arm,primecell-periphid = <0x10480180>;
-		        max-frequency = <100000000>;
-			bus-width = <8>;
-			mmc-cap-mmc-highspeed;
-			vmmc-supply = <&ab8500_ldo_aux2_reg>;
-
-			status = "okay";
-		};
-	};
-};
diff --git a/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts b/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts
index d2803be4e1a8..15f98cbcb75a 100644
--- a/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts
+++ b/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts
@@ -37,30 +37,35 @@
 			device_type = "cpu";
 			compatible = "arm,cortex-a15";
 			reg = <0>;
+			cci-control-port = <&cci_control1>;
 		};
 
 		cpu1: cpu@1 {
 			device_type = "cpu";
 			compatible = "arm,cortex-a15";
 			reg = <1>;
+			cci-control-port = <&cci_control1>;
 		};
 
 		cpu2: cpu@2 {
 			device_type = "cpu";
 			compatible = "arm,cortex-a7";
 			reg = <0x100>;
+			cci-control-port = <&cci_control2>;
 		};
 
 		cpu3: cpu@3 {
 			device_type = "cpu";
 			compatible = "arm,cortex-a7";
 			reg = <0x101>;
+			cci-control-port = <&cci_control2>;
 		};
 
 		cpu4: cpu@4 {
 			device_type = "cpu";
 			compatible = "arm,cortex-a7";
 			reg = <0x102>;
+			cci-control-port = <&cci_control2>;
 		};
 	};
 
@@ -104,6 +109,26 @@
 		interrupts = <1 9 0xf04>;
 	};
 
+	cci@2c090000 {
+		compatible = "arm,cci-400";
+		#address-cells = <1>;
+		#size-cells = <1>;
+		reg = <0 0x2c090000 0 0x1000>;
+		ranges = <0x0 0x0 0x2c090000 0x10000>;
+
+		cci_control1: slave-if@4000 {
+			compatible = "arm,cci-400-ctrl-if";
+			interface-type = "ace";
+			reg = <0x4000 0x1000>;
+		};
+
+		cci_control2: slave-if@5000 {
+			compatible = "arm,cci-400-ctrl-if";
+			interface-type = "ace";
+			reg = <0x5000 0x1000>;
+		};
+	};
+
 	memory-controller@7ffd0000 {
 		compatible = "arm,pl354", "arm,primecell";
 		reg = <0 0x7ffd0000 0 0x1000>;
@@ -125,6 +150,12 @@
 		clock-names = "apb_pclk";
 	};
 
+        scc@7fff0000 {
+		compatible = "arm,vexpress-scc,v2p-ca15_a7", "arm,vexpress-scc";
+		reg = <0 0x7fff0000 0 0x1000>;
+		interrupts = <0 95 4>;
+        };
+
 	timer {
 		compatible = "arm,armv7-timer";
 		interrupts = <1 13 0xf08>,
diff --git a/arch/arm/boot/dts/vf610-twr.dts b/arch/arm/boot/dts/vf610-twr.dts
index b3905f5bcaf9..1a58678b93fa 100644
--- a/arch/arm/boot/dts/vf610-twr.dts
+++ b/arch/arm/boot/dts/vf610-twr.dts
@@ -50,6 +50,13 @@
 	status = "okay";
 };
 
+&i2c0 {
+	clock-frequency = <100000>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_i2c0_1>;
+	status = "okay";
+};
+
 &uart1 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_uart1_1>;
diff --git a/arch/arm/boot/dts/wm8850-w70v2.dts b/arch/arm/boot/dts/wm8850-w70v2.dts
index 90e913fb64be..7a563d2523b0 100644
--- a/arch/arm/boot/dts/wm8850-w70v2.dts
+++ b/arch/arm/boot/dts/wm8850-w70v2.dts
@@ -11,13 +11,14 @@
 
 /dts-v1/;
 /include/ "wm8850.dtsi"
+#include <dt-bindings/pwm/pwm.h>
 
 / {
 	model = "Wondermedia WM8850-W70v2 Tablet";
 
 	backlight {
 		compatible = "pwm-backlight";
-		pwms = <&pwm 0 50000 1>;	/* duty inverted */
+		pwms = <&pwm 0 50000 PWM_POLARITY_INVERTED>;
 
 		brightness-levels = <0 40 60 80 100 130 190 255>;
 		default-brightness-level = <5>;
diff --git a/arch/arm/boot/dts/zynq-7000.dtsi b/arch/arm/boot/dts/zynq-7000.dtsi
index 6f54a64850eb..e32b92b949d2 100644
--- a/arch/arm/boot/dts/zynq-7000.dtsi
+++ b/arch/arm/boot/dts/zynq-7000.dtsi
@@ -41,8 +41,8 @@
 		L2: cache-controller {
 			compatible = "arm,pl310-cache";
 			reg = <0xF8F02000 0x1000>;
-			arm,data-latency = <2 3 2>;
-			arm,tag-latency = <2 3 2>;
+			arm,data-latency = <3 2 2>;
+			arm,tag-latency = <2 2 2>;
 			cache-unified;
 			cache-level = <2>;
 		};
diff --git a/arch/arm/boot/install.sh b/arch/arm/boot/install.sh
index 06ea7d42ce8e..2a45092a40e3 100644
--- a/arch/arm/boot/install.sh
+++ b/arch/arm/boot/install.sh
@@ -20,6 +20,20 @@
 #   $4 - default install path (blank if root directory)
 #
 
+verify () {
+	if [ ! -f "$1" ]; then
+		echo ""                                                   1>&2
+		echo " *** Missing file: $1"                              1>&2
+		echo ' *** You need to run "make" before "make install".' 1>&2
+		echo ""                                                   1>&2
+		exit 1
+	fi
+}
+
+# Make sure the files actually exist
+verify "$2"
+verify "$3"
+
 # User may have a custom install script
 if [ -x ~/bin/${INSTALLKERNEL} ]; then exec ~/bin/${INSTALLKERNEL} "$@"; fi
 if [ -x /sbin/${INSTALLKERNEL} ]; then exec /sbin/${INSTALLKERNEL} "$@"; fi
diff --git a/arch/arm/common/edma.c b/arch/arm/common/edma.c
index 39ad030ac0c7..8e1a0245907f 100644
--- a/arch/arm/common/edma.c
+++ b/arch/arm/common/edma.c
@@ -269,6 +269,11 @@ static const struct edmacc_param dummy_paramset = {
 	.ccnt = 1,
 };
 
+static const struct of_device_id edma_of_ids[] = {
+	{ .compatible = "ti,edma3", },
+	{}
+};
+
 /*****************************************************************************/
 
 static void map_dmach_queue(unsigned ctlr, unsigned ch_no,
@@ -560,14 +565,38 @@ static int reserve_contiguous_slots(int ctlr, unsigned int id,
 static int prepare_unused_channel_list(struct device *dev, void *data)
 {
 	struct platform_device *pdev = to_platform_device(dev);
-	int i, ctlr;
+	int i, count, ctlr;
+	struct of_phandle_args  dma_spec;
+
+	if (dev->of_node) {
+		count = of_property_count_strings(dev->of_node, "dma-names");
+		if (count < 0)
+			return 0;
+		for (i = 0; i < count; i++) {
+			if (of_parse_phandle_with_args(dev->of_node, "dmas",
+						       "#dma-cells", i,
+						       &dma_spec))
+				continue;
+
+			if (!of_match_node(edma_of_ids, dma_spec.np)) {
+				of_node_put(dma_spec.np);
+				continue;
+			}
 
+			clear_bit(EDMA_CHAN_SLOT(dma_spec.args[0]),
+				  edma_cc[0]->edma_unused);
+			of_node_put(dma_spec.np);
+		}
+		return 0;
+	}
+
+	/* For non-OF case */
 	for (i = 0; i < pdev->num_resources; i++) {
 		if ((pdev->resource[i].flags & IORESOURCE_DMA) &&
 				(int)pdev->resource[i].start >= 0) {
 			ctlr = EDMA_CTLR(pdev->resource[i].start);
 			clear_bit(EDMA_CHAN_SLOT(pdev->resource[i].start),
-					edma_cc[ctlr]->edma_unused);
+				  edma_cc[ctlr]->edma_unused);
 		}
 	}
 
@@ -1235,6 +1264,23 @@ void edma_resume(unsigned channel)
 }
 EXPORT_SYMBOL(edma_resume);
 
+int edma_trigger_channel(unsigned channel)
+{
+	unsigned ctlr;
+	unsigned int mask;
+
+	ctlr = EDMA_CTLR(channel);
+	channel = EDMA_CHAN_SLOT(channel);
+	mask = BIT(channel & 0x1f);
+
+	edma_shadow0_write_array(ctlr, SH_ESR, (channel >> 5), mask);
+
+	pr_debug("EDMA: ESR%d %08x\n", (channel >> 5),
+		 edma_shadow0_read_array(ctlr, SH_ESR, (channel >> 5)));
+	return 0;
+}
+EXPORT_SYMBOL(edma_trigger_channel);
+
 /**
  * edma_start - start dma on a channel
  * @channel: channel being activated
@@ -1745,11 +1791,6 @@ static int edma_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static const struct of_device_id edma_of_ids[] = {
-	{ .compatible = "ti,edma3", },
-	{}
-};
-
 static struct platform_driver edma_driver = {
 	.driver = {
 		.name	= "edma",
diff --git a/arch/arm/common/mcpm_entry.c b/arch/arm/common/mcpm_entry.c
index 370236dd1a03..990250965f2c 100644
--- a/arch/arm/common/mcpm_entry.c
+++ b/arch/arm/common/mcpm_entry.c
@@ -51,7 +51,8 @@ void mcpm_cpu_power_down(void)
 {
 	phys_reset_t phys_reset;
 
-	BUG_ON(!platform_ops);
+	if (WARN_ON_ONCE(!platform_ops || !platform_ops->power_down))
+		return;
 	BUG_ON(!irqs_disabled());
 
 	/*
@@ -93,7 +94,8 @@ void mcpm_cpu_suspend(u64 expected_residency)
 {
 	phys_reset_t phys_reset;
 
-	BUG_ON(!platform_ops);
+	if (WARN_ON_ONCE(!platform_ops || !platform_ops->suspend))
+		return;
 	BUG_ON(!irqs_disabled());
 
 	/* Very similar to mcpm_cpu_power_down() */
diff --git a/arch/arm/common/mcpm_head.S b/arch/arm/common/mcpm_head.S
index 80f033614a1f..39c96df3477a 100644
--- a/arch/arm/common/mcpm_head.S
+++ b/arch/arm/common/mcpm_head.S
@@ -151,7 +151,7 @@ mcpm_setup_leave:
 
 	mov	r0, #INBOUND_NOT_COMING_UP
 	strb	r0, [r8, #MCPM_SYNC_CLUSTER_INBOUND]
-	dsb
+	dsb	st
 	sev
 
 	mov	r0, r11
diff --git a/arch/arm/common/sharpsl_param.c b/arch/arm/common/sharpsl_param.c
index d56c932580eb..025f6ce38596 100644
--- a/arch/arm/common/sharpsl_param.c
+++ b/arch/arm/common/sharpsl_param.c
@@ -15,6 +15,7 @@
 #include <linux/module.h>
 #include <linux/string.h>
 #include <asm/mach/sharpsl_param.h>
+#include <asm/memory.h>
 
 /*
  * Certain hardware parameters determined at the time of device manufacture,
@@ -25,8 +26,10 @@
  */
 #ifdef CONFIG_ARCH_SA1100
 #define PARAM_BASE	0xe8ffc000
+#define param_start(x)	(void *)(x)
 #else
 #define PARAM_BASE	0xa0000a00
+#define param_start(x)	__va(x)
 #endif
 #define MAGIC_CHG(a,b,c,d) ( ( d << 24 ) | ( c << 16 )  | ( b << 8 ) | a )
 
@@ -41,7 +44,7 @@ EXPORT_SYMBOL(sharpsl_param);
 
 void sharpsl_save_param(void)
 {
-	memcpy(&sharpsl_param, (void *)PARAM_BASE, sizeof(struct sharpsl_param_info));
+	memcpy(&sharpsl_param, param_start(PARAM_BASE), sizeof(struct sharpsl_param_info));
 
 	if (sharpsl_param.comadj_keyword != COMADJ_MAGIC)
 		sharpsl_param.comadj=-1;
diff --git a/arch/arm/common/timer-sp.c b/arch/arm/common/timer-sp.c
index 023ee63827a2..e901d0f3e0bb 100644
--- a/arch/arm/common/timer-sp.c
+++ b/arch/arm/common/timer-sp.c
@@ -166,7 +166,8 @@ static int sp804_set_next_event(unsigned long next,
 }
 
 static struct clock_event_device sp804_clockevent = {
-	.features       = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT,
+	.features       = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT |
+		CLOCK_EVT_FEAT_DYNIRQ,
 	.set_mode	= sp804_set_mode,
 	.set_next_event	= sp804_set_next_event,
 	.rating		= 300,
diff --git a/arch/arm/common/vlock.S b/arch/arm/common/vlock.S
index ff198583f683..8b7df283fedf 100644
--- a/arch/arm/common/vlock.S
+++ b/arch/arm/common/vlock.S
@@ -42,7 +42,7 @@
 	dmb
 	mov	\rscratch, #0
 	strb	\rscratch, [\rbase, \rcpu]
-	dsb
+	dsb	st
 	sev
 .endm
 
@@ -102,7 +102,7 @@ ENTRY(vlock_unlock)
 	dmb
 	mov	r1, #VLOCK_OWNER_NONE
 	strb	r1, [r0, #VLOCK_OWNER_OFFSET]
-	dsb
+	dsb	st
 	sev
 	bx	lr
 ENDPROC(vlock_unlock)
diff --git a/arch/arm/configs/ag5evm_defconfig b/arch/arm/configs/ag5evm_defconfig
deleted file mode 100644
index 212ead354a6b..000000000000
--- a/arch/arm/configs/ag5evm_defconfig
+++ /dev/null
@@ -1,83 +0,0 @@
-CONFIG_EXPERIMENTAL=y
-CONFIG_SYSVIPC=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_LOG_BUF_SHIFT=16
-CONFIG_NAMESPACES=y
-# CONFIG_UTS_NS is not set
-# CONFIG_IPC_NS is not set
-# CONFIG_USER_NS is not set
-# CONFIG_PID_NS is not set
-CONFIG_BLK_DEV_INITRD=y
-CONFIG_INITRAMFS_SOURCE=""
-CONFIG_EXPERT=y
-CONFIG_SLAB=y
-# CONFIG_BLK_DEV_BSG is not set
-# CONFIG_IOSCHED_DEADLINE is not set
-# CONFIG_IOSCHED_CFQ is not set
-CONFIG_ARCH_SHMOBILE=y
-CONFIG_ARCH_SH73A0=y
-CONFIG_MACH_AG5EVM=y
-CONFIG_MEMORY_SIZE=0x10000000
-CONFIG_CPU_BPREDICT_DISABLE=y
-CONFIG_ARM_ERRATA_430973=y
-CONFIG_ARM_ERRATA_458693=y
-CONFIG_NO_HZ=y
-CONFIG_AEABI=y
-# CONFIG_OABI_COMPAT is not set
-CONFIG_HIGHMEM=y
-CONFIG_ZBOOT_ROM_TEXT=0x0
-CONFIG_ZBOOT_ROM_BSS=0x0
-CONFIG_CMDLINE="console=tty0 console=ttySC2,115200 earlyprintk=sh-sci.2,115200 ignore_loglevel"
-CONFIG_CMDLINE_FORCE=y
-CONFIG_KEXEC=y
-# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
-CONFIG_PM=y
-# CONFIG_SUSPEND is not set
-CONFIG_PM_RUNTIME=y
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_INET=y
-# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
-# CONFIG_INET_XFRM_MODE_TUNNEL is not set
-# CONFIG_INET_XFRM_MODE_BEET is not set
-# CONFIG_INET_LRO is not set
-# CONFIG_INET_DIAG is not set
-# CONFIG_IPV6 is not set
-# CONFIG_WIRELESS is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
-# CONFIG_BLK_DEV is not set
-CONFIG_NETDEVICES=y
-CONFIG_NET_ETHERNET=y
-CONFIG_SMSC911X=y
-# CONFIG_NETDEV_1000 is not set
-# CONFIG_NETDEV_10000 is not set
-# CONFIG_WLAN is not set
-CONFIG_INPUT_SPARSEKMAP=y
-# CONFIG_INPUT_MOUSEDEV_PSAUX is not set
-CONFIG_INPUT_EVDEV=y
-# CONFIG_INPUT_KEYBOARD is not set
-# CONFIG_INPUT_MOUSE is not set
-CONFIG_SERIAL_SH_SCI=y
-CONFIG_SERIAL_SH_SCI_NR_UARTS=9
-CONFIG_SERIAL_SH_SCI_CONSOLE=y
-# CONFIG_LEGACY_PTYS is not set
-# CONFIG_HW_RANDOM is not set
-CONFIG_I2C=y
-CONFIG_I2C_SH_MOBILE=y
-# CONFIG_HWMON is not set
-# CONFIG_MFD_SUPPORT is not set
-CONFIG_FB=y
-CONFIG_FB_SH_MOBILE_LCDC=y
-CONFIG_FRAMEBUFFER_CONSOLE=y
-CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y
-# CONFIG_HID_SUPPORT is not set
-# CONFIG_USB_SUPPORT is not set
-# CONFIG_DNOTIFY is not set
-# CONFIG_INOTIFY_USER is not set
-CONFIG_TMPFS=y
-# CONFIG_MISC_FILESYSTEMS is not set
-CONFIG_MAGIC_SYSRQ=y
-CONFIG_DEBUG_KERNEL=y
-# CONFIG_FTRACE is not set
diff --git a/arch/arm/configs/ape6evm_defconfig b/arch/arm/configs/ape6evm_defconfig
index dab5a7dfadc6..1ce39940795d 100644
--- a/arch/arm/configs/ape6evm_defconfig
+++ b/arch/arm/configs/ape6evm_defconfig
@@ -54,7 +54,8 @@ CONFIG_NETDEVICES=y
 CONFIG_SMC91X=y
 CONFIG_SMSC911X=y
 # CONFIG_INPUT_MOUSEDEV is not set
-# CONFIG_INPUT_KEYBOARD is not set
+CONFIG_INPUT_EVDEV=y
+CONFIG_KEYBOARD_GPIO=y
 # CONFIG_INPUT_MOUSE is not set
 # CONFIG_SERIO is not set
 CONFIG_SERIAL_NONSTANDARD=y
@@ -71,6 +72,9 @@ CONFIG_REGULATOR_FIXED_VOLTAGE=y
 CONFIG_REGULATOR_GPIO=y
 # CONFIG_HID is not set
 # CONFIG_USB_SUPPORT is not set
+CONFIG_NEW_LEDS=y
+CONFIG_LEDS_CLASS=y
+CONFIG_LEDS_GPIO=y
 # CONFIG_IOMMU_SUPPORT is not set
 # CONFIG_DNOTIFY is not set
 CONFIG_TMPFS=y
diff --git a/arch/arm/configs/at91_dt_defconfig b/arch/arm/configs/at91_dt_defconfig
index 75fd842d4071..690e89273230 100644
--- a/arch/arm/configs/at91_dt_defconfig
+++ b/arch/arm/configs/at91_dt_defconfig
@@ -14,11 +14,13 @@ CONFIG_MODULE_UNLOAD=y
 # CONFIG_IOSCHED_DEADLINE is not set
 # CONFIG_IOSCHED_CFQ is not set
 CONFIG_ARCH_AT91=y
+CONFIG_SOC_AT91RM9200=y
 CONFIG_SOC_AT91SAM9260=y
 CONFIG_SOC_AT91SAM9263=y
 CONFIG_SOC_AT91SAM9G45=y
 CONFIG_SOC_AT91SAM9X5=y
 CONFIG_SOC_AT91SAM9N12=y
+CONFIG_MACH_AT91RM9200_DT=y
 CONFIG_MACH_AT91SAM9_DT=y
 CONFIG_AT91_PROGRAMMABLE_CLOCKS=y
 CONFIG_AT91_TIMER_HZ=128
@@ -62,6 +64,7 @@ CONFIG_MTD=y
 CONFIG_MTD_CMDLINE_PARTS=y
 CONFIG_MTD_CHAR=y
 CONFIG_MTD_BLOCK=y
+CONFIG_MTD_DATAFLASH=y
 CONFIG_MTD_NAND=y
 CONFIG_MTD_NAND_ATMEL=y
 CONFIG_MTD_UBI=y
@@ -78,7 +81,6 @@ CONFIG_BLK_DEV_SD=y
 CONFIG_SCSI_MULTI_LUN=y
 # CONFIG_SCSI_LOWLEVEL is not set
 CONFIG_NETDEVICES=y
-CONFIG_MII=y
 CONFIG_MACB=y
 # CONFIG_NET_VENDOR_BROADCOM is not set
 # CONFIG_NET_VENDOR_FARADAY is not set
diff --git a/arch/arm/configs/bcm_defconfig b/arch/arm/configs/bcm_defconfig
index 65edf6d47215..6e4931097dd4 100644
--- a/arch/arm/configs/bcm_defconfig
+++ b/arch/arm/configs/bcm_defconfig
@@ -42,6 +42,18 @@ CONFIG_VFP=y
 CONFIG_NEON=y
 # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
 CONFIG_PM_RUNTIME=y
+CONFIG_NET=y
+CONFIG_PACKET=y
+CONFIG_PACKET_DIAG=y
+CONFIG_UNIX=y
+CONFIG_UNIX_DIAG=y
+CONFIG_NET_KEY=y
+CONFIG_INET=y
+CONFIG_IP_MULTICAST=y
+CONFIG_ARPD=y
+CONFIG_SYN_COOKIES=y
+CONFIG_TCP_MD5SIG=y
+CONFIG_IPV6=y
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
 CONFIG_PROC_DEVICETREE=y
@@ -112,7 +124,6 @@ CONFIG_DEFAULT_HUNG_TASK_TIMEOUT=110
 CONFIG_BOOTPARAM_HUNG_TASK_PANIC=y
 CONFIG_DEBUG_INFO=y
 # CONFIG_FTRACE is not set
-CONFIG_DEBUG_LL=y
 CONFIG_CRC_CCITT=y
 CONFIG_CRC_T10DIF=y
 CONFIG_CRC_ITU_T=y
diff --git a/arch/arm/configs/bockw_defconfig b/arch/arm/configs/bockw_defconfig
index 845f5cdf62b5..e7e94948d194 100644
--- a/arch/arm/configs/bockw_defconfig
+++ b/arch/arm/configs/bockw_defconfig
@@ -82,6 +82,13 @@ CONFIG_SERIAL_SH_SCI_CONSOLE=y
 # CONFIG_HWMON is not set
 CONFIG_I2C=y
 CONFIG_I2C_RCAR=y
+CONFIG_MEDIA_SUPPORT=y
+CONFIG_MEDIA_CAMERA_SUPPORT=y
+CONFIG_V4L_PLATFORM_DRIVERS=y
+CONFIG_SOC_CAMERA=y
+CONFIG_VIDEO_RCAR_VIN=y
+# CONFIG_MEDIA_SUBDRV_AUTOSELECT is not set
+CONFIG_VIDEO_ML86V7667=y
 CONFIG_SPI=y
 CONFIG_SPI_SH_HSPI=y
 CONFIG_USB=y
diff --git a/arch/arm/configs/dove_defconfig b/arch/arm/configs/dove_defconfig
index 4364eff5b01e..110105476848 100644
--- a/arch/arm/configs/dove_defconfig
+++ b/arch/arm/configs/dove_defconfig
@@ -13,6 +13,9 @@ CONFIG_ARCH_DOVE=y
 CONFIG_MACH_DOVE_DB=y
 CONFIG_MACH_CM_A510=y
 CONFIG_MACH_DOVE_DT=y
+CONFIG_PCI=y
+CONFIG_PCI_MSI=y
+CONFIG_PCI_MVEBU=y
 CONFIG_AEABI=y
 CONFIG_HIGHMEM=y
 CONFIG_ZBOOT_ROM_TEXT=0x0
@@ -78,6 +81,7 @@ CONFIG_SPI_ORION=y
 CONFIG_THERMAL=y
 CONFIG_DOVE_THERMAL=y
 CONFIG_USB=y
+CONFIG_USB_XHCI_HCD=y
 CONFIG_USB_EHCI_HCD=y
 CONFIG_USB_EHCI_ROOT_HUB_TT=y
 CONFIG_USB_STORAGE=y
diff --git a/arch/arm/configs/exynos4_defconfig b/arch/arm/configs/exynos4_defconfig
deleted file mode 100644
index bffe68e190a3..000000000000
--- a/arch/arm/configs/exynos4_defconfig
+++ /dev/null
@@ -1,68 +0,0 @@
-CONFIG_EXPERIMENTAL=y
-CONFIG_BLK_DEV_INITRD=y
-CONFIG_KALLSYMS_ALL=y
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-# CONFIG_BLK_DEV_BSG is not set
-CONFIG_ARCH_EXYNOS=y
-CONFIG_S3C_LOWLEVEL_UART_PORT=1
-CONFIG_MACH_SMDKC210=y
-CONFIG_MACH_ARMLEX4210=y
-CONFIG_MACH_UNIVERSAL_C210=y
-CONFIG_MACH_NURI=y
-CONFIG_MACH_ORIGEN=y
-CONFIG_MACH_SMDK4412=y
-CONFIG_NO_HZ=y
-CONFIG_HIGH_RES_TIMERS=y
-CONFIG_SMP=y
-CONFIG_NR_CPUS=2
-CONFIG_PREEMPT=y
-CONFIG_AEABI=y
-CONFIG_CMDLINE="root=/dev/ram0 rw ramdisk=8192 initrd=0x41000000,8M console=ttySAC1,115200 init=/linuxrc mem=256M"
-CONFIG_VFP=y
-CONFIG_NEON=y
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
-CONFIG_BLK_DEV_LOOP=y
-CONFIG_BLK_DEV_RAM=y
-CONFIG_BLK_DEV_RAM_SIZE=8192
-CONFIG_SCSI=y
-CONFIG_BLK_DEV_SD=y
-CONFIG_CHR_DEV_SG=y
-CONFIG_INPUT_EVDEV=y
-# CONFIG_INPUT_KEYBOARD is not set
-# CONFIG_INPUT_MOUSE is not set
-CONFIG_INPUT_TOUCHSCREEN=y
-CONFIG_SERIAL_8250=y
-CONFIG_SERIAL_SAMSUNG=y
-CONFIG_SERIAL_SAMSUNG_CONSOLE=y
-CONFIG_HW_RANDOM=y
-CONFIG_I2C=y
-# CONFIG_HWMON is not set
-# CONFIG_MFD_SUPPORT is not set
-# CONFIG_HID_SUPPORT is not set
-# CONFIG_USB_SUPPORT is not set
-CONFIG_EXT2_FS=y
-CONFIG_MSDOS_FS=y
-CONFIG_VFAT_FS=y
-CONFIG_TMPFS=y
-CONFIG_TMPFS_POSIX_ACL=y
-CONFIG_CRAMFS=y
-CONFIG_ROMFS_FS=y
-CONFIG_PARTITION_ADVANCED=y
-CONFIG_BSD_DISKLABEL=y
-CONFIG_SOLARIS_X86_PARTITION=y
-CONFIG_NLS_CODEPAGE_437=y
-CONFIG_NLS_ASCII=y
-CONFIG_NLS_ISO8859_1=y
-CONFIG_MAGIC_SYSRQ=y
-CONFIG_DEBUG_KERNEL=y
-CONFIG_DETECT_HUNG_TASK=y
-CONFIG_DEBUG_RT_MUTEXES=y
-CONFIG_DEBUG_SPINLOCK=y
-CONFIG_DEBUG_MUTEXES=y
-CONFIG_DEBUG_INFO=y
-CONFIG_SYSCTL_SYSCALL_CHECK=y
-CONFIG_DEBUG_USER=y
-CONFIG_DEBUG_LL=y
-CONFIG_EARLY_PRINTK=y
-CONFIG_CRC_CCITT=y
diff --git a/arch/arm/configs/imx_v4_v5_defconfig b/arch/arm/configs/imx_v4_v5_defconfig
index f07a847b00c9..e958ebe79779 100644
--- a/arch/arm/configs/imx_v4_v5_defconfig
+++ b/arch/arm/configs/imx_v4_v5_defconfig
@@ -1,4 +1,3 @@
-CONFIG_EXPERIMENTAL=y
 # CONFIG_SWAP is not set
 CONFIG_SYSVIPC=y
 CONFIG_POSIX_MQUEUE=y
@@ -17,16 +16,18 @@ CONFIG_MODULE_UNLOAD=y
 # CONFIG_BLK_DEV_BSG is not set
 # CONFIG_IOSCHED_DEADLINE is not set
 # CONFIG_IOSCHED_CFQ is not set
-CONFIG_ARCH_MXC=y
 CONFIG_ARCH_MULTI_V4T=y
 CONFIG_ARCH_MULTI_V5=y
 # CONFIG_ARCH_MULTI_V7 is not set
+CONFIG_ARCH_MXC=y
+CONFIG_MXC_IRQ_PRIOR=y
 CONFIG_ARCH_MX1ADS=y
 CONFIG_MACH_SCB9328=y
 CONFIG_MACH_APF9328=y
 CONFIG_MACH_MX21ADS=y
 CONFIG_MACH_MX25_3DS=y
 CONFIG_MACH_EUKREA_CPUIMX25SD=y
+CONFIG_MACH_IMX25_DT=y
 CONFIG_MACH_MX27ADS=y
 CONFIG_MACH_PCM038=y
 CONFIG_MACH_CPUIMX27=y
@@ -39,8 +40,6 @@ CONFIG_MACH_PCA100=y
 CONFIG_MACH_MXT_TD60=y
 CONFIG_MACH_IMX27IPCAM=y
 CONFIG_MACH_IMX27_DT=y
-CONFIG_MXC_IRQ_PRIOR=y
-CONFIG_MXC_PWM=y
 CONFIG_PREEMPT=y
 CONFIG_AEABI=y
 CONFIG_ZBOOT_ROM_TEXT=0x0
@@ -67,7 +66,6 @@ CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
 CONFIG_MTD=y
 CONFIG_MTD_CMDLINE_PARTS=y
-CONFIG_MTD_CHAR=y
 CONFIG_MTD_BLOCK=y
 CONFIG_MTD_CFI=y
 CONFIG_MTD_CFI_ADV_OPTIONS=y
@@ -123,24 +121,20 @@ CONFIG_REGULATOR_FIXED_VOLTAGE=y
 CONFIG_REGULATOR_MC13783=y
 CONFIG_REGULATOR_MC13892=y
 CONFIG_MEDIA_SUPPORT=y
-CONFIG_VIDEO_DEV=y
-CONFIG_V4L_PLATFORM_DRIVERS=y
 CONFIG_MEDIA_CAMERA_SUPPORT=y
+CONFIG_V4L_PLATFORM_DRIVERS=y
 CONFIG_SOC_CAMERA=y
-CONFIG_SOC_CAMERA_OV2640=y
 CONFIG_VIDEO_MX2=y
 CONFIG_V4L_MEM2MEM_DRIVERS=y
 CONFIG_VIDEO_CODA=y
+CONFIG_SOC_CAMERA_OV2640=y
 CONFIG_FB=y
 CONFIG_FB_IMX=y
 CONFIG_BACKLIGHT_LCD_SUPPORT=y
 CONFIG_LCD_CLASS_DEVICE=y
 CONFIG_LCD_L4F00242T03=y
 CONFIG_BACKLIGHT_CLASS_DEVICE=y
-CONFIG_BACKLIGHT_PWM=y
 CONFIG_FRAMEBUFFER_CONSOLE=y
-CONFIG_FONTS=y
-CONFIG_FONT_8x8=y
 CONFIG_LOGO=y
 CONFIG_SOUND=y
 CONFIG_SND=y
@@ -157,7 +151,6 @@ CONFIG_USB_HID=m
 CONFIG_USB=y
 CONFIG_USB_EHCI_HCD=y
 CONFIG_USB_EHCI_MXC=y
-CONFIG_USB_ULPI=y
 CONFIG_MMC=y
 CONFIG_MMC_SDHCI=y
 CONFIG_MMC_SDHCI_PLTFM=y
@@ -198,3 +191,5 @@ CONFIG_NLS_CODEPAGE_850=m
 CONFIG_NLS_ISO8859_1=y
 CONFIG_NLS_ISO8859_15=m
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
+CONFIG_FONTS=y
+CONFIG_FONT_8x8=y
diff --git a/arch/arm/configs/imx_v6_v7_defconfig b/arch/arm/configs/imx_v6_v7_defconfig
index 06686e7303a9..5d488c24b132 100644
--- a/arch/arm/configs/imx_v6_v7_defconfig
+++ b/arch/arm/configs/imx_v6_v7_defconfig
@@ -1,4 +1,3 @@
-CONFIG_EXPERIMENTAL=y
 # CONFIG_LOCALVERSION_AUTO is not set
 CONFIG_KERNEL_LZO=y
 CONFIG_SYSVIPC=y
@@ -17,10 +16,8 @@ CONFIG_MODULE_UNLOAD=y
 CONFIG_MODVERSIONS=y
 CONFIG_MODULE_SRCVERSION_ALL=y
 # CONFIG_BLK_DEV_BSG is not set
-CONFIG_ARCH_MXC=y
 CONFIG_ARCH_MULTI_V6=y
-CONFIG_ARCH_MULTI_V7=y
-CONFIG_MACH_IMX31_DT=y
+CONFIG_ARCH_MXC=y
 CONFIG_MACH_MX31LILLY=y
 CONFIG_MACH_MX31LITE=y
 CONFIG_MACH_PCM037=y
@@ -30,6 +27,7 @@ CONFIG_MACH_MX31MOBOARD=y
 CONFIG_MACH_QONG=y
 CONFIG_MACH_ARMADILLO5X0=y
 CONFIG_MACH_KZM_ARM11_01=y
+CONFIG_MACH_IMX31_DT=y
 CONFIG_MACH_PCM043=y
 CONFIG_MACH_MX35_3DS=y
 CONFIG_MACH_VPR200=y
@@ -39,7 +37,6 @@ CONFIG_SOC_IMX53=y
 CONFIG_SOC_IMX6Q=y
 CONFIG_SOC_IMX6SL=y
 CONFIG_SOC_VF610=y
-CONFIG_MXC_PWM=y
 CONFIG_SMP=y
 CONFIG_VMSPLIT_2G=y
 CONFIG_PREEMPT_VOLUNTARY=y
@@ -64,20 +61,24 @@ CONFIG_IP_PNP_DHCP=y
 # CONFIG_INET_LRO is not set
 CONFIG_IPV6=y
 CONFIG_NETFILTER=y
-# CONFIG_WIRELESS is not set
+CONFIG_CFG80211=y
+CONFIG_MAC80211=y
+CONFIG_RFKILL=y
+CONFIG_RFKILL_INPUT=y
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
 # CONFIG_STANDALONE is not set
+CONFIG_IMX_WEIM=y
 CONFIG_CONNECTOR=y
 CONFIG_MTD=y
 CONFIG_MTD_CMDLINE_PARTS=y
-CONFIG_MTD_CHAR=y
 CONFIG_MTD_BLOCK=y
 CONFIG_MTD_CFI=y
 CONFIG_MTD_JEDECPROBE=y
 CONFIG_MTD_CFI_INTELEXT=y
 CONFIG_MTD_CFI_AMDSTD=y
 CONFIG_MTD_CFI_STAA=y
+CONFIG_MTD_PHYSMAP_OF=y
 CONFIG_MTD_DATAFLASH=y
 CONFIG_MTD_M25P80=y
 CONFIG_MTD_SST25L=y
@@ -88,6 +89,7 @@ CONFIG_MTD_UBI=y
 CONFIG_BLK_DEV_LOOP=y
 CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_RAM_SIZE=65536
+CONFIG_SRAM=y
 CONFIG_EEPROM_AT24=y
 CONFIG_EEPROM_AT25=y
 # CONFIG_SCSI_PROC_FS is not set
@@ -98,10 +100,11 @@ CONFIG_SCSI_LOGGING=y
 CONFIG_SCSI_SCAN_ASYNC=y
 # CONFIG_SCSI_LOWLEVEL is not set
 CONFIG_ATA=y
+CONFIG_SATA_AHCI_PLATFORM=y
+CONFIG_AHCI_IMX=y
 CONFIG_PATA_IMX=y
 CONFIG_NETDEVICES=y
 # CONFIG_NET_VENDOR_BROADCOM is not set
-# CONFIG_NET_VENDOR_CHELSIO is not set
 CONFIG_CS89x0=y
 CONFIG_CS89x0_PLATFORM=y
 # CONFIG_NET_VENDOR_FARADAY is not set
@@ -115,7 +118,7 @@ CONFIG_SMC91X=y
 CONFIG_SMC911X=y
 CONFIG_SMSC911X=y
 # CONFIG_NET_VENDOR_STMICRO is not set
-# CONFIG_WLAN is not set
+CONFIG_BRCMFMAC=m
 # CONFIG_INPUT_MOUSEDEV_PSAUX is not set
 CONFIG_INPUT_EVDEV=y
 CONFIG_INPUT_EVBUG=m
@@ -124,6 +127,7 @@ CONFIG_KEYBOARD_IMX=y
 CONFIG_MOUSE_PS2=m
 CONFIG_MOUSE_PS2_ELANTECH=y
 CONFIG_INPUT_TOUCHSCREEN=y
+CONFIG_TOUCHSCREEN_EGALAX=y
 CONFIG_TOUCHSCREEN_MC13783=y
 CONFIG_INPUT_MISC=y
 CONFIG_INPUT_MMA8450=y
@@ -133,13 +137,13 @@ CONFIG_VT_HW_CONSOLE_BINDING=y
 # CONFIG_DEVKMEM is not set
 CONFIG_SERIAL_IMX=y
 CONFIG_SERIAL_IMX_CONSOLE=y
+CONFIG_SERIAL_FSL_LPUART=y
+CONFIG_SERIAL_FSL_LPUART_CONSOLE=y
 CONFIG_HW_RANDOM=y
 CONFIG_HW_RANDOM_MXC_RNGA=y
-CONFIG_I2C=y
 # CONFIG_I2C_COMPAT is not set
 CONFIG_I2C_CHARDEV=y
 # CONFIG_I2C_HELPER_AUTO is not set
-CONFIG_I2C_ALGOBIT=m
 CONFIG_I2C_ALGOPCF=m
 CONFIG_I2C_ALGOPCA=m
 CONFIG_I2C_IMX=y
@@ -155,30 +159,26 @@ CONFIG_MFD_MC13XXX_SPI=y
 CONFIG_MFD_MC13XXX_I2C=y
 CONFIG_REGULATOR=y
 CONFIG_REGULATOR_FIXED_VOLTAGE=y
-CONFIG_REGULATOR_DA9052=y
 CONFIG_REGULATOR_ANATOP=y
+CONFIG_REGULATOR_DA9052=y
 CONFIG_REGULATOR_MC13783=y
 CONFIG_REGULATOR_MC13892=y
 CONFIG_MEDIA_SUPPORT=y
-CONFIG_VIDEO_DEV=y
-CONFIG_V4L_PLATFORM_DRIVERS=y
 CONFIG_MEDIA_CAMERA_SUPPORT=y
+CONFIG_V4L_PLATFORM_DRIVERS=y
 CONFIG_SOC_CAMERA=y
+CONFIG_VIDEO_MX3=y
+CONFIG_V4L_MEM2MEM_DRIVERS=y
+CONFIG_VIDEO_CODA=y
 CONFIG_SOC_CAMERA_OV2640=y
 CONFIG_DRM=y
-CONFIG_VIDEO_MX3=y
-CONFIG_FB=y
-CONFIG_LCD_PLATFORM=y
 CONFIG_BACKLIGHT_LCD_SUPPORT=y
 CONFIG_LCD_CLASS_DEVICE=y
 CONFIG_LCD_L4F00242T03=y
+CONFIG_LCD_PLATFORM=y
 CONFIG_BACKLIGHT_CLASS_DEVICE=y
 CONFIG_BACKLIGHT_PWM=y
 CONFIG_FRAMEBUFFER_CONSOLE=y
-CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y
-CONFIG_FONTS=y
-CONFIG_FONT_8x8=y
-CONFIG_FONT_8x16=y
 CONFIG_LOGO=y
 CONFIG_SOUND=y
 CONFIG_SND=y
@@ -192,11 +192,12 @@ CONFIG_SND_SOC_IMX_MC13783=y
 CONFIG_USB=y
 CONFIG_USB_EHCI_HCD=y
 CONFIG_USB_EHCI_MXC=y
+CONFIG_USB_STORAGE=y
 CONFIG_USB_CHIPIDEA=y
 CONFIG_USB_CHIPIDEA_HOST=y
 CONFIG_USB_PHY=y
+CONFIG_NOP_USB_XCEIV=y
 CONFIG_USB_MXS_PHY=y
-CONFIG_USB_STORAGE=y
 CONFIG_MMC=y
 CONFIG_MMC_SDHCI=y
 CONFIG_MMC_SDHCI_PLTFM=y
@@ -213,9 +214,10 @@ CONFIG_IMX_SDMA=y
 CONFIG_MXS_DMA=y
 CONFIG_STAGING=y
 CONFIG_DRM_IMX=y
-CONFIG_DRM_IMX_TVE=y
 CONFIG_DRM_IMX_FB_HELPER=y
 CONFIG_DRM_IMX_PARALLEL_DISPLAY=y
+CONFIG_DRM_IMX_TVE=y
+CONFIG_DRM_IMX_LDB=y
 CONFIG_DRM_IMX_IPUV3_CORE=y
 CONFIG_DRM_IMX_IPUV3=y
 CONFIG_COMMON_CLK_DEBUG=y
@@ -269,3 +271,6 @@ CONFIG_CRC_CCITT=m
 CONFIG_CRC_T10DIF=y
 CONFIG_CRC7=m
 CONFIG_LIBCRC32C=m
+CONFIG_FONTS=y
+CONFIG_FONT_8x8=y
+CONFIG_FONT_8x16=y
diff --git a/arch/arm/configs/keystone_defconfig b/arch/arm/configs/keystone_defconfig
index 62e968cac9dc..1f36b823905f 100644
--- a/arch/arm/configs/keystone_defconfig
+++ b/arch/arm/configs/keystone_defconfig
@@ -104,6 +104,7 @@ CONFIG_IP_SCTP=y
 CONFIG_VLAN_8021Q=y
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_CMA=y
+CONFIG_DMA_CMA=y
 CONFIG_MTD=y
 CONFIG_MTD_CMDLINE_PARTS=y
 CONFIG_MTD_BLOCK=y
diff --git a/arch/arm/configs/kirkwood_defconfig b/arch/arm/configs/kirkwood_defconfig
index 0f2aa61911a3..0ae0eaebf6b2 100644
--- a/arch/arm/configs/kirkwood_defconfig
+++ b/arch/arm/configs/kirkwood_defconfig
@@ -10,49 +10,18 @@ CONFIG_MODULE_UNLOAD=y
 # CONFIG_BLK_DEV_BSG is not set
 CONFIG_ARCH_KIRKWOOD=y
 CONFIG_MACH_D2NET_V2=y
-CONFIG_MACH_DB88F6281_BP=y
-CONFIG_MACH_DOCKSTAR=y
-CONFIG_MACH_ESATA_SHEEVAPLUG=y
-CONFIG_MACH_GURUPLUG=y
-CONFIG_MACH_INETSPACE_V2=y
-CONFIG_MACH_MV88F6281GTW_GE=y
 CONFIG_MACH_NET2BIG_V2=y
 CONFIG_MACH_NET5BIG_V2=y
-CONFIG_MACH_NETSPACE_MAX_V2=y
-CONFIG_MACH_NETSPACE_V2=y
 CONFIG_MACH_OPENRD_BASE=y
 CONFIG_MACH_OPENRD_CLIENT=y
 CONFIG_MACH_OPENRD_ULTIMATE=y
 CONFIG_MACH_RD88F6192_NAS=y
 CONFIG_MACH_RD88F6281=y
-CONFIG_MACH_SHEEVAPLUG=y
 CONFIG_MACH_T5325=y
 CONFIG_MACH_TS219=y
 CONFIG_MACH_TS41X=y
-CONFIG_MACH_CLOUDBOX_DT=y
-CONFIG_MACH_DB88F628X_BP_DT=y
-CONFIG_MACH_DLINK_KIRKWOOD_DT=y
-CONFIG_MACH_DOCKSTAR_DT=y
-CONFIG_MACH_DREAMPLUG_DT=y
-CONFIG_MACH_GOFLEXNET_DT=y
-CONFIG_MACH_GURUPLUG_DT=y
-CONFIG_MACH_IB62X0_DT=y
-CONFIG_MACH_ICONNECT_DT=y
-CONFIG_MACH_INETSPACE_V2_DT=y
-CONFIG_MACH_IOMEGA_IX2_200_DT=y
-CONFIG_MACH_KM_KIRKWOOD_DT=y
-CONFIG_MACH_LSXL_DT=y
-CONFIG_MACH_MPLCEC4_DT=y
-CONFIG_MACH_NETSPACE_LITE_V2_DT=y
-CONFIG_MACH_NETSPACE_MAX_V2_DT=y
-CONFIG_MACH_NETSPACE_MINI_V2_DT=y
-CONFIG_MACH_NETSPACE_V2_DT=y
-CONFIG_MACH_NSA310_DT=y
-CONFIG_MACH_OPENBLOCKS_A6_DT=y
-CONFIG_MACH_READYNAS_DT=y
-CONFIG_MACH_SHEEVAPLUG_DT=y
-CONFIG_MACH_TOPKICK_DT=y
-CONFIG_MACH_TS219_DT=y
+CONFIG_ARCH_KIRKWOOD_DT=y
+CONFIG_MACH_MV88F6281GTW_GE_DT=y
 # CONFIG_CPU_FEROCEON_OLD_ID is not set
 CONFIG_PCI_MVEBU=y
 CONFIG_PREEMPT=y
@@ -92,6 +61,7 @@ CONFIG_MTD_M25P80=y
 CONFIG_MTD_NAND=y
 CONFIG_MTD_NAND_ORION=y
 CONFIG_BLK_DEV_LOOP=y
+CONFIG_EEPROM_AT24=y
 # CONFIG_SCSI_PROC_FS is not set
 CONFIG_BLK_DEV_SD=y
 CONFIG_BLK_DEV_SR=m
@@ -100,9 +70,9 @@ CONFIG_ATA=y
 CONFIG_SATA_AHCI=y
 CONFIG_SATA_MV=y
 CONFIG_NETDEVICES=y
-CONFIG_MII=y
 CONFIG_NET_DSA_MV88E6123_61_65=y
 CONFIG_MV643XX_ETH=y
+CONFIG_R8169=y
 CONFIG_MARVELL_PHY=y
 CONFIG_LIBERTAS=y
 CONFIG_LIBERTAS_SDIO=y
@@ -123,9 +93,11 @@ CONFIG_I2C_MV64XXX=y
 CONFIG_SPI=y
 CONFIG_SPI_ORION=y
 CONFIG_GPIO_SYSFS=y
-# CONFIG_HWMON is not set
+CONFIG_SENSORS_ADT7475=y
+CONFIG_SENSORS_LM63=y
+CONFIG_SENSORS_LM75=y
+CONFIG_SENSORS_LM85=y
 CONFIG_THERMAL=y
-CONFIG_KIRKWOOD_THERMAL=y
 CONFIG_WATCHDOG=y
 CONFIG_ORION_WATCHDOG=y
 CONFIG_HID_DRAGONRISE=y
@@ -164,6 +136,8 @@ CONFIG_LEDS_TRIGGER_TIMER=y
 CONFIG_LEDS_TRIGGER_HEARTBEAT=y
 CONFIG_LEDS_TRIGGER_DEFAULT_ON=y
 CONFIG_RTC_CLASS=y
+CONFIG_RTC_DRV_RS5C372=y
+CONFIG_RTC_DRV_PCF8563=y
 CONFIG_RTC_DRV_S35390A=y
 CONFIG_RTC_DRV_MV=y
 CONFIG_DMADEVICES=y
@@ -171,6 +145,7 @@ CONFIG_MV_XOR=y
 CONFIG_EXT2_FS=y
 CONFIG_EXT3_FS=y
 # CONFIG_EXT3_FS_XATTR is not set
+CONFIG_EXT4_FS=y
 CONFIG_ISO9660_FS=m
 CONFIG_JOLIET=y
 CONFIG_UDF_FS=m
@@ -186,12 +161,12 @@ CONFIG_NLS_CODEPAGE_850=y
 CONFIG_NLS_ISO8859_1=y
 CONFIG_NLS_ISO8859_2=y
 CONFIG_NLS_UTF8=y
-CONFIG_MAGIC_SYSRQ=y
+CONFIG_DEBUG_INFO=y
 CONFIG_DEBUG_FS=y
+CONFIG_MAGIC_SYSRQ=y
 CONFIG_DEBUG_KERNEL=y
 # CONFIG_SCHED_DEBUG is not set
 # CONFIG_DEBUG_PREEMPT is not set
-CONFIG_DEBUG_INFO=y
 # CONFIG_FTRACE is not set
 CONFIG_DEBUG_USER=y
 CONFIG_DEBUG_LL=y
diff --git a/arch/arm/configs/kota2_defconfig b/arch/arm/configs/lager_defconfig
index 57ad3d47de70..e777ef22b801 100644
--- a/arch/arm/configs/kota2_defconfig
+++ b/arch/arm/configs/lager_defconfig
@@ -1,52 +1,38 @@
-# CONFIG_ARM_PATCH_PHYS_VIRT is not set
-CONFIG_EXPERIMENTAL=y
 CONFIG_SYSVIPC=y
+CONFIG_NO_HZ=y
 CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
 CONFIG_LOG_BUF_SHIFT=16
-CONFIG_CGROUPS=y
-CONFIG_CPUSETS=y
-CONFIG_NAMESPACES=y
-# CONFIG_UTS_NS is not set
-# CONFIG_IPC_NS is not set
-# CONFIG_USER_NS is not set
-# CONFIG_PID_NS is not set
+CONFIG_CC_OPTIMIZE_FOR_SIZE=y
 CONFIG_SYSCTL_SYSCALL=y
 CONFIG_EMBEDDED=y
+CONFIG_PERF_EVENTS=y
 CONFIG_SLAB=y
+# CONFIG_LBDAF is not set
 # CONFIG_BLK_DEV_BSG is not set
 # CONFIG_IOSCHED_DEADLINE is not set
 # CONFIG_IOSCHED_CFQ is not set
 CONFIG_ARCH_SHMOBILE=y
-CONFIG_KEYBOARD_GPIO_POLLED=y
-CONFIG_ARCH_SH73A0=y
-CONFIG_MACH_KOTA2=y
-CONFIG_MEMORY_SIZE=0x1e000000
+CONFIG_ARCH_R8A7790=y
+CONFIG_MACH_LAGER=y
 # CONFIG_SH_TIMER_TMU is not set
-# CONFIG_SWP_EMULATE is not set
-CONFIG_CPU_BPREDICT_DISABLE=y
+# CONFIG_EM_TIMER_STI is not set
+CONFIG_ARM_ERRATA_430973=y
+CONFIG_ARM_ERRATA_458693=y
 CONFIG_ARM_ERRATA_460075=y
-CONFIG_ARM_ERRATA_742230=y
-CONFIG_ARM_ERRATA_742231=y
-CONFIG_PL310_ERRATA_588369=y
-CONFIG_ARM_ERRATA_720789=y
-CONFIG_PL310_ERRATA_727915=y
 CONFIG_ARM_ERRATA_743622=y
-CONFIG_ARM_ERRATA_751472=y
-CONFIG_PL310_ERRATA_753970=y
 CONFIG_ARM_ERRATA_754322=y
-CONFIG_PL310_ERRATA_769419=y
-CONFIG_NO_HZ=y
-CONFIG_SMP=y
+CONFIG_HAVE_ARM_ARCH_TIMER=y
 CONFIG_AEABI=y
 # CONFIG_OABI_COMPAT is not set
-CONFIG_HIGHMEM=y
+CONFIG_FORCE_MAX_ZONEORDER=13
 CONFIG_ZBOOT_ROM_TEXT=0x0
 CONFIG_ZBOOT_ROM_BSS=0x0
-CONFIG_CMDLINE="console=ttySC2,115200 earlyprintk=sh-sci.2,115200 ignore_loglevel"
-CONFIG_CMDLINE_FORCE=y
+CONFIG_ARM_APPENDED_DTB=y
 CONFIG_KEXEC=y
-CONFIG_CPU_IDLE=y
+CONFIG_AUTO_ZRELADDR=y
+CONFIG_VFP=y
+CONFIG_NEON=y
 # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
 CONFIG_PM_RUNTIME=y
 CONFIG_NET=y
@@ -61,47 +47,48 @@ CONFIG_IP_PNP_DHCP=y
 # CONFIG_INET_LRO is not set
 # CONFIG_INET_DIAG is not set
 # CONFIG_IPV6 is not set
-CONFIG_CFG80211=y
-CONFIG_WIRELESS_EXT_SYSFS=y
-CONFIG_MAC80211=y
+# CONFIG_WIRELESS is not set
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
-# CONFIG_BLK_DEV is not set
 CONFIG_NETDEVICES=y
+# CONFIG_NET_CORE is not set
+# CONFIG_NET_VENDOR_ARC is not set
+# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
-# CONFIG_NET_VENDOR_CHELSIO is not set
+# CONFIG_NET_VENDOR_CIRRUS is not set
 # CONFIG_NET_VENDOR_FARADAY is not set
 # CONFIG_NET_VENDOR_INTEL is not set
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MICREL is not set
 # CONFIG_NET_VENDOR_NATSEMI is not set
+CONFIG_SH_ETH=y
 # CONFIG_NET_VENDOR_SEEQ is not set
-CONFIG_SMSC911X=y
+# CONFIG_NET_VENDOR_SMSC is not set
 # CONFIG_NET_VENDOR_STMICRO is not set
-CONFIG_B43=y
-CONFIG_B43_PHY_N=y
-CONFIG_B43_DEBUG=y
-CONFIG_INPUT_SPARSEKMAP=y
+# CONFIG_NET_VENDOR_VIA is not set
+# CONFIG_NET_VENDOR_WIZNET is not set
+# CONFIG_WLAN is not set
 # CONFIG_INPUT_MOUSEDEV_PSAUX is not set
 CONFIG_INPUT_EVDEV=y
 # CONFIG_KEYBOARD_ATKBD is not set
 CONFIG_KEYBOARD_GPIO=y
-CONFIG_KEYBOARD_SH_KEYSC=y
 # CONFIG_INPUT_MOUSE is not set
+# CONFIG_SERIO is not set
 # CONFIG_LEGACY_PTYS is not set
 CONFIG_SERIAL_SH_SCI=y
-CONFIG_SERIAL_SH_SCI_NR_UARTS=9
+CONFIG_SERIAL_SH_SCI_NR_UARTS=10
 CONFIG_SERIAL_SH_SCI_CONSOLE=y
 # CONFIG_HW_RANDOM is not set
+CONFIG_I2C=y
+CONFIG_I2C_GPIO=y
 CONFIG_I2C_SH_MOBILE=y
+CONFIG_GPIO_SH_PFC=y
+CONFIG_GPIOLIB=y
+CONFIG_GPIO_RCAR=y
 # CONFIG_HWMON is not set
-CONFIG_BCMA=y
-CONFIG_BCMA_DEBUG=y
-CONFIG_FB=y
-CONFIG_FB_SH_MOBILE_LCDC=y
-CONFIG_LCD_PLATFORM=y
-CONFIG_FRAMEBUFFER_CONSOLE=y
-CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y
-# CONFIG_HID_SUPPORT is not set
+CONFIG_THERMAL=y
+CONFIG_RCAR_THERMAL=y
+CONFIG_REGULATOR=y
+CONFIG_REGULATOR_FIXED_VOLTAGE=y
 # CONFIG_USB_SUPPORT is not set
 CONFIG_MMC=y
 CONFIG_MMC_SDHI=y
@@ -109,13 +96,25 @@ CONFIG_MMC_SH_MMCIF=y
 CONFIG_NEW_LEDS=y
 CONFIG_LEDS_CLASS=y
 CONFIG_LEDS_GPIO=y
-CONFIG_LEDS_RENESAS_TPU=y
-CONFIG_LEDS_TRIGGERS=y
+CONFIG_RTC_CLASS=y
+CONFIG_DMADEVICES=y
+CONFIG_SH_DMAE=y
+# CONFIG_IOMMU_SUPPORT is not set
 # CONFIG_DNOTIFY is not set
+CONFIG_MSDOS_FS=y
+CONFIG_VFAT_FS=y
 CONFIG_TMPFS=y
+CONFIG_CONFIGFS_FS=y
 # CONFIG_MISC_FILESYSTEMS is not set
-CONFIG_MAGIC_SYSRQ=y
-CONFIG_DEBUG_INFO=y
-CONFIG_DEBUG_INFO_REDUCED=y
-# CONFIG_FTRACE is not set
-CONFIG_DEBUG_USER=y
+CONFIG_NFS_FS=y
+CONFIG_NFS_V3_ACL=y
+CONFIG_NFS_V4=y
+CONFIG_NFS_V4_1=y
+CONFIG_ROOT_NFS=y
+CONFIG_NLS_CODEPAGE_437=y
+CONFIG_NLS_ISO8859_1=y
+# CONFIG_ENABLE_WARN_DEPRECATED is not set
+# CONFIG_ENABLE_MUST_CHECK is not set
+# CONFIG_ARM_UNWIND is not set
+# CONFIG_CRYPTO_ANSI_CPRNG is not set
+# CONFIG_CRYPTO_HW is not set
diff --git a/arch/arm/configs/marzen_defconfig b/arch/arm/configs/marzen_defconfig
index 494e70aeb9e1..000e9205b2b9 100644
--- a/arch/arm/configs/marzen_defconfig
+++ b/arch/arm/configs/marzen_defconfig
@@ -29,6 +29,7 @@ CONFIG_AEABI=y
 CONFIG_HIGHMEM=y
 CONFIG_ZBOOT_ROM_TEXT=0x0
 CONFIG_ZBOOT_ROM_BSS=0x0
+CONFIG_ARM_APPENDED_DTB=y
 CONFIG_CMDLINE="console=ttySC2,115200 earlyprintk=sh-sci.2,115200 ignore_loglevel root=/dev/nfs ip=on"
 CONFIG_CMDLINE_FORCE=y
 CONFIG_KEXEC=y
@@ -84,6 +85,13 @@ CONFIG_GPIO_RCAR=y
 CONFIG_THERMAL=y
 CONFIG_RCAR_THERMAL=y
 CONFIG_SSB=y
+CONFIG_MEDIA_SUPPORT=y
+CONFIG_MEDIA_CAMERA_SUPPORT=y
+CONFIG_V4L_PLATFORM_DRIVERS=y
+CONFIG_SOC_CAMERA=y
+CONFIG_VIDEO_RCAR_VIN=y
+# CONFIG_MEDIA_SUBDRV_AUTOSELECT is not set
+CONFIG_VIDEO_ADV7180=y
 CONFIG_USB=y
 CONFIG_USB_RCAR_PHY=y
 CONFIG_MMC=y
diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig
index 6e572c64cf5a..119fc378fc52 100644
--- a/arch/arm/configs/multi_v7_defconfig
+++ b/arch/arm/configs/multi_v7_defconfig
@@ -36,6 +36,7 @@ CONFIG_ARCH_TEGRA_114_SOC=y
 CONFIG_TEGRA_PCI=y
 CONFIG_TEGRA_EMC_SCALING_ENABLE=y
 CONFIG_ARCH_U8500=y
+CONFIG_MACH_HREFV60=y
 CONFIG_MACH_SNOWBALL=y
 CONFIG_MACH_UX500_DT=y
 CONFIG_ARCH_VEXPRESS=y
@@ -46,6 +47,7 @@ CONFIG_ARCH_ZYNQ=y
 CONFIG_SMP=y
 CONFIG_HIGHPTE=y
 CONFIG_ARM_APPENDED_DTB=y
+CONFIG_ARM_ATAG_DTB_COMPAT=y
 CONFIG_NET=y
 CONFIG_UNIX=y
 CONFIG_INET=y
@@ -133,6 +135,7 @@ CONFIG_MMC=y
 CONFIG_MMC_ARMMMCI=y
 CONFIG_MMC_SDHCI=y
 CONFIG_MMC_SDHCI_PLTFM=y
+CONFIG_MMC_SDHCI_ESDHC_IMX=y
 CONFIG_MMC_SDHCI_TEGRA=y
 CONFIG_MMC_SDHCI_SPEAR=y
 CONFIG_MMC_OMAP=y
diff --git a/arch/arm/configs/mvebu_defconfig b/arch/arm/configs/mvebu_defconfig
index 731814e2c189..594d706b641f 100644
--- a/arch/arm/configs/mvebu_defconfig
+++ b/arch/arm/configs/mvebu_defconfig
@@ -39,6 +39,8 @@ CONFIG_MVNETA=y
 CONFIG_MARVELL_PHY=y
 CONFIG_MWIFIEX=y
 CONFIG_MWIFIEX_SDIO=y
+CONFIG_INPUT_EVDEV=y
+CONFIG_KEYBOARD_GPIO=y
 CONFIG_SERIAL_8250=y
 CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_I2C=y
diff --git a/arch/arm/configs/mxs_defconfig b/arch/arm/configs/mxs_defconfig
index 1d6d8fb7f4a1..4555c025629a 100644
--- a/arch/arm/configs/mxs_defconfig
+++ b/arch/arm/configs/mxs_defconfig
@@ -1,4 +1,3 @@
-CONFIG_EXPERIMENTAL=y
 CONFIG_SYSVIPC=y
 CONFIG_NO_HZ=y
 CONFIG_HIGH_RES_TIMERS=y
@@ -27,7 +26,6 @@ CONFIG_ARCH_MXS=y
 # CONFIG_ARM_THUMB is not set
 CONFIG_PREEMPT_VOLUNTARY=y
 CONFIG_AEABI=y
-CONFIG_AUTO_ZRELADDR=y
 CONFIG_FPE_NWFPE=y
 CONFIG_NET=y
 CONFIG_PACKET=y
@@ -43,8 +41,6 @@ CONFIG_SYN_COOKIES=y
 # CONFIG_INET_DIAG is not set
 # CONFIG_IPV6 is not set
 CONFIG_CAN=m
-CONFIG_CAN_RAW=m
-CONFIG_CAN_BCM=m
 CONFIG_CAN_FLEXCAN=m
 # CONFIG_WIRELESS is not set
 CONFIG_DEVTMPFS=y
@@ -52,7 +48,6 @@ CONFIG_DEVTMPFS_MOUNT=y
 # CONFIG_FIRMWARE_IN_KERNEL is not set
 CONFIG_MTD=y
 CONFIG_MTD_CMDLINE_PARTS=y
-CONFIG_MTD_CHAR=y
 CONFIG_MTD_BLOCK=y
 CONFIG_MTD_DATAFLASH=y
 CONFIG_MTD_M25P80=y
@@ -67,12 +62,12 @@ CONFIG_SCSI=y
 CONFIG_BLK_DEV_SD=y
 CONFIG_NETDEVICES=y
 CONFIG_ENC28J60=y
-CONFIG_USB_USBNET=y
-CONFIG_USB_NET_SMSC95XX=y
 CONFIG_SMSC_PHY=y
 CONFIG_ICPLUS_PHY=y
 CONFIG_REALTEK_PHY=y
 CONFIG_MICREL_PHY=y
+CONFIG_USB_USBNET=y
+CONFIG_USB_NET_SMSC95XX=y
 # CONFIG_WLAN is not set
 # CONFIG_INPUT_MOUSEDEV_PSAUX is not set
 CONFIG_INPUT_EVDEV=y
@@ -110,7 +105,6 @@ CONFIG_LCD_CLASS_DEVICE=y
 CONFIG_BACKLIGHT_CLASS_DEVICE=y
 CONFIG_BACKLIGHT_PWM=y
 CONFIG_FRAMEBUFFER_CONSOLE=y
-CONFIG_FONTS=y
 CONFIG_LOGO=y
 CONFIG_SOUND=y
 CONFIG_SND=y
@@ -119,9 +113,9 @@ CONFIG_SND_MXS_SOC=y
 CONFIG_SND_SOC_MXS_SGTL5000=y
 CONFIG_USB=y
 CONFIG_USB_EHCI_HCD=y
+CONFIG_USB_STORAGE=y
 CONFIG_USB_CHIPIDEA=y
 CONFIG_USB_CHIPIDEA_HOST=y
-CONFIG_USB_STORAGE=y
 CONFIG_USB_PHY=y
 CONFIG_USB_MXS_PHY=y
 CONFIG_MMC=y
@@ -143,9 +137,9 @@ CONFIG_DMADEVICES=y
 CONFIG_MXS_DMA=y
 CONFIG_STAGING=y
 CONFIG_MXS_LRADC=y
-CONFIG_IIO_SYSFS_TRIGGER=y
 CONFIG_COMMON_CLK_DEBUG=y
 CONFIG_IIO=y
+CONFIG_IIO_SYSFS_TRIGGER=y
 CONFIG_PWM=y
 CONFIG_PWM_MXS=y
 CONFIG_EXT2_FS=y
@@ -173,14 +167,14 @@ CONFIG_NLS_CODEPAGE_850=y
 CONFIG_NLS_ISO8859_1=y
 CONFIG_NLS_ISO8859_15=y
 CONFIG_PRINTK_TIME=y
+CONFIG_DEBUG_INFO=y
 CONFIG_FRAME_WARN=2048
-CONFIG_MAGIC_SYSRQ=y
 CONFIG_UNUSED_SYMBOLS=y
+CONFIG_MAGIC_SYSRQ=y
 CONFIG_DEBUG_KERNEL=y
 CONFIG_LOCKUP_DETECTOR=y
 CONFIG_TIMER_STATS=y
 CONFIG_PROVE_LOCKING=y
-CONFIG_DEBUG_INFO=y
 CONFIG_BLK_DEV_IO_TRACE=y
 CONFIG_STRICT_DEVMEM=y
 CONFIG_DEBUG_USER=y
@@ -188,3 +182,4 @@ CONFIG_DEBUG_USER=y
 # CONFIG_CRYPTO_HW is not set
 CONFIG_CRC_ITU_T=m
 CONFIG_CRC7=m
+CONFIG_FONTS=y
diff --git a/arch/arm/configs/omap2plus_defconfig b/arch/arm/configs/omap2plus_defconfig
index 5339e6a4d639..254cf0539439 100644
--- a/arch/arm/configs/omap2plus_defconfig
+++ b/arch/arm/configs/omap2plus_defconfig
@@ -78,6 +78,7 @@ CONFIG_MAC80211_RC_PID=y
 CONFIG_MAC80211_RC_DEFAULT_PID=y
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_CMA=y
+CONFIG_DMA_CMA=y
 CONFIG_CONNECTOR=y
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
@@ -185,13 +186,11 @@ CONFIG_OMAP2_DSS_RFBI=y
 CONFIG_OMAP2_DSS_SDI=y
 CONFIG_OMAP2_DSS_DSI=y
 CONFIG_FB_OMAP2=m
-CONFIG_PANEL_GENERIC_DPI=m
-CONFIG_PANEL_TFP410=m
-CONFIG_PANEL_SHARP_LS037V7DW01=m
-CONFIG_PANEL_NEC_NL8048HL11_01B=m
-CONFIG_PANEL_TAAL=m
-CONFIG_PANEL_TPO_TD043MTEA1=m
-CONFIG_PANEL_ACX565AKM=m
+CONFIG_DISPLAY_ENCODER_TFP410=m
+CONFIG_DISPLAY_ENCODER_TPD12S015=m
+CONFIG_DISPLAY_CONNECTOR_DVI=m
+CONFIG_DISPLAY_CONNECTOR_HDMI=m
+CONFIG_DISPLAY_PANEL_DPI=m
 CONFIG_BACKLIGHT_LCD_SUPPORT=y
 CONFIG_LCD_CLASS_DEVICE=y
 CONFIG_LCD_PLATFORM=y
@@ -306,3 +305,4 @@ CONFIG_TI_DAVINCI_MDIO=y
 CONFIG_TI_DAVINCI_CPDMA=y
 CONFIG_TI_CPSW=y
 CONFIG_AT803X_PHY=y
+CONFIG_SOC_DRA7XX=y
diff --git a/arch/arm/configs/tegra_defconfig b/arch/arm/configs/tegra_defconfig
index 1effb43dab80..ea042e80e54d 100644
--- a/arch/arm/configs/tegra_defconfig
+++ b/arch/arm/configs/tegra_defconfig
@@ -1,3 +1,4 @@
+CONFIG_SYSVIPC=y
 CONFIG_NO_HZ=y
 CONFIG_HIGH_RES_TIMERS=y
 CONFIG_IKCONFIG=y
@@ -26,8 +27,11 @@ CONFIG_ARCH_TEGRA=y
 CONFIG_ARCH_TEGRA_2x_SOC=y
 CONFIG_ARCH_TEGRA_3x_SOC=y
 CONFIG_ARCH_TEGRA_114_SOC=y
-CONFIG_TEGRA_PCI=y
 CONFIG_TEGRA_EMC_SCALING_ENABLE=y
+CONFIG_PCI=y
+CONFIG_PCI_MSI=y
+CONFIG_PCI_TEGRA=y
+CONFIG_PCIEPORTBUS=y
 CONFIG_SMP=y
 CONFIG_PREEMPT=y
 CONFIG_AEABI=y
@@ -79,6 +83,7 @@ CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
 # CONFIG_FIRMWARE_IN_KERNEL is not set
 CONFIG_CMA=y
+CONFIG_DMA_CMA=y
 CONFIG_MTD=y
 CONFIG_MTD_M25P80=y
 CONFIG_PROC_DEVICETREE=y
@@ -91,6 +96,7 @@ CONFIG_ISL29003=y
 CONFIG_SCSI=y
 CONFIG_BLK_DEV_SD=y
 CONFIG_BLK_DEV_SR=y
+CONFIG_SCSI_MULTI_LUN=y
 # CONFIG_SCSI_LOWLEVEL is not set
 CONFIG_NETDEVICES=y
 CONFIG_DUMMY=y
@@ -105,6 +111,7 @@ CONFIG_RT2800USB=m
 CONFIG_INPUT_EVDEV=y
 CONFIG_KEYBOARD_GPIO=y
 CONFIG_KEYBOARD_TEGRA=y
+CONFIG_MOUSE_PS2_ELANTECH=y
 CONFIG_INPUT_MISC=y
 CONFIG_INPUT_MPU3050=y
 # CONFIG_LEGACY_PTYS is not set
@@ -177,6 +184,7 @@ CONFIG_SND_SOC_TEGRA_WM8903=y
 CONFIG_SND_SOC_TEGRA_TRIMSLICE=y
 CONFIG_SND_SOC_TEGRA_ALC5632=y
 CONFIG_USB=y
+CONFIG_USB_XHCI_HCD=y
 CONFIG_USB_EHCI_HCD=y
 CONFIG_USB_EHCI_TEGRA=y
 CONFIG_USB_ACM=y
diff --git a/arch/arm/crypto/aes-armv4.S b/arch/arm/crypto/aes-armv4.S
index 19d6cd6f29f9..3a14ea8fe97e 100644
--- a/arch/arm/crypto/aes-armv4.S
+++ b/arch/arm/crypto/aes-armv4.S
@@ -148,7 +148,7 @@ AES_Te:
 @ 		 const AES_KEY *key) {
 .align	5
 ENTRY(AES_encrypt)
-	sub	r3,pc,#8		@ AES_encrypt
+	adr	r3,AES_encrypt
 	stmdb   sp!,{r1,r4-r12,lr}
 	mov	r12,r0		@ inp
 	mov	r11,r2
@@ -381,7 +381,7 @@ _armv4_AES_encrypt:
 .align	5
 ENTRY(private_AES_set_encrypt_key)
 _armv4_AES_set_encrypt_key:
-	sub	r3,pc,#8		@ AES_set_encrypt_key
+	adr	r3,_armv4_AES_set_encrypt_key
 	teq	r0,#0
 	moveq	r0,#-1
 	beq	.Labrt
@@ -843,7 +843,7 @@ AES_Td:
 @ 		 const AES_KEY *key) {
 .align	5
 ENTRY(AES_decrypt)
-	sub	r3,pc,#8		@ AES_decrypt
+	adr	r3,AES_decrypt
 	stmdb   sp!,{r1,r4-r12,lr}
 	mov	r12,r0		@ inp
 	mov	r11,r2
diff --git a/arch/arm/include/asm/Kbuild b/arch/arm/include/asm/Kbuild
index d3db39860b9c..59ceae8f3c95 100644
--- a/arch/arm/include/asm/Kbuild
+++ b/arch/arm/include/asm/Kbuild
@@ -31,5 +31,4 @@ generic-y += termbits.h
 generic-y += termios.h
 generic-y += timex.h
 generic-y += trace_clock.h
-generic-y += types.h
 generic-y += unaligned.h
diff --git a/arch/arm/include/asm/arch_timer.h b/arch/arm/include/asm/arch_timer.h
index e406d575c94f..5665134bfa3e 100644
--- a/arch/arm/include/asm/arch_timer.h
+++ b/arch/arm/include/asm/arch_timer.h
@@ -17,7 +17,8 @@ int arch_timer_arch_init(void);
  * nicely work out which register we want, and chuck away the rest of
  * the code. At least it does so with a recent GCC (4.6.3).
  */
-static inline void arch_timer_reg_write(const int access, const int reg, u32 val)
+static __always_inline
+void arch_timer_reg_write_cp15(int access, enum arch_timer_reg reg, u32 val)
 {
 	if (access == ARCH_TIMER_PHYS_ACCESS) {
 		switch (reg) {
@@ -28,9 +29,7 @@ static inline void arch_timer_reg_write(const int access, const int reg, u32 val
 			asm volatile("mcr p15, 0, %0, c14, c2, 0" : : "r" (val));
 			break;
 		}
-	}
-
-	if (access == ARCH_TIMER_VIRT_ACCESS) {
+	} else if (access == ARCH_TIMER_VIRT_ACCESS) {
 		switch (reg) {
 		case ARCH_TIMER_REG_CTRL:
 			asm volatile("mcr p15, 0, %0, c14, c3, 1" : : "r" (val));
@@ -44,7 +43,8 @@ static inline void arch_timer_reg_write(const int access, const int reg, u32 val
 	isb();
 }
 
-static inline u32 arch_timer_reg_read(const int access, const int reg)
+static __always_inline
+u32 arch_timer_reg_read_cp15(int access, enum arch_timer_reg reg)
 {
 	u32 val = 0;
 
@@ -57,9 +57,7 @@ static inline u32 arch_timer_reg_read(const int access, const int reg)
 			asm volatile("mrc p15, 0, %0, c14, c2, 0" : "=r" (val));
 			break;
 		}
-	}
-
-	if (access == ARCH_TIMER_VIRT_ACCESS) {
+	} else if (access == ARCH_TIMER_VIRT_ACCESS) {
 		switch (reg) {
 		case ARCH_TIMER_REG_CTRL:
 			asm volatile("mrc p15, 0, %0, c14, c3, 1" : "=r" (val));
diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h
index a5fef710af32..fcc1b5bf6979 100644
--- a/arch/arm/include/asm/assembler.h
+++ b/arch/arm/include/asm/assembler.h
@@ -220,9 +220,9 @@
 #ifdef CONFIG_SMP
 #if __LINUX_ARM_ARCH__ >= 7
 	.ifeqs "\mode","arm"
-	ALT_SMP(dmb)
+	ALT_SMP(dmb	ish)
 	.else
-	ALT_SMP(W(dmb))
+	ALT_SMP(W(dmb)	ish)
 	.endif
 #elif __LINUX_ARM_ARCH__ == 6
 	ALT_SMP(mcr	p15, 0, r0, c7, c10, 5)	@ dmb
diff --git a/arch/arm/include/asm/barrier.h b/arch/arm/include/asm/barrier.h
index 8dcd9c702d90..60f15e274e6d 100644
--- a/arch/arm/include/asm/barrier.h
+++ b/arch/arm/include/asm/barrier.h
@@ -14,27 +14,27 @@
 #endif
 
 #if __LINUX_ARM_ARCH__ >= 7
-#define isb() __asm__ __volatile__ ("isb" : : : "memory")
-#define dsb() __asm__ __volatile__ ("dsb" : : : "memory")
-#define dmb() __asm__ __volatile__ ("dmb" : : : "memory")
+#define isb(option) __asm__ __volatile__ ("isb " #option : : : "memory")
+#define dsb(option) __asm__ __volatile__ ("dsb " #option : : : "memory")
+#define dmb(option) __asm__ __volatile__ ("dmb " #option : : : "memory")
 #elif defined(CONFIG_CPU_XSC3) || __LINUX_ARM_ARCH__ == 6
-#define isb() __asm__ __volatile__ ("mcr p15, 0, %0, c7, c5, 4" \
+#define isb(x) __asm__ __volatile__ ("mcr p15, 0, %0, c7, c5, 4" \
 				    : : "r" (0) : "memory")
-#define dsb() __asm__ __volatile__ ("mcr p15, 0, %0, c7, c10, 4" \
+#define dsb(x) __asm__ __volatile__ ("mcr p15, 0, %0, c7, c10, 4" \
 				    : : "r" (0) : "memory")
-#define dmb() __asm__ __volatile__ ("mcr p15, 0, %0, c7, c10, 5" \
+#define dmb(x) __asm__ __volatile__ ("mcr p15, 0, %0, c7, c10, 5" \
 				    : : "r" (0) : "memory")
 #elif defined(CONFIG_CPU_FA526)
-#define isb() __asm__ __volatile__ ("mcr p15, 0, %0, c7, c5, 4" \
+#define isb(x) __asm__ __volatile__ ("mcr p15, 0, %0, c7, c5, 4" \
 				    : : "r" (0) : "memory")
-#define dsb() __asm__ __volatile__ ("mcr p15, 0, %0, c7, c10, 4" \
+#define dsb(x) __asm__ __volatile__ ("mcr p15, 0, %0, c7, c10, 4" \
 				    : : "r" (0) : "memory")
-#define dmb() __asm__ __volatile__ ("" : : : "memory")
+#define dmb(x) __asm__ __volatile__ ("" : : : "memory")
 #else
-#define isb() __asm__ __volatile__ ("" : : : "memory")
-#define dsb() __asm__ __volatile__ ("mcr p15, 0, %0, c7, c10, 4" \
+#define isb(x) __asm__ __volatile__ ("" : : : "memory")
+#define dsb(x) __asm__ __volatile__ ("mcr p15, 0, %0, c7, c10, 4" \
 				    : : "r" (0) : "memory")
-#define dmb() __asm__ __volatile__ ("" : : : "memory")
+#define dmb(x) __asm__ __volatile__ ("" : : : "memory")
 #endif
 
 #ifdef CONFIG_ARCH_HAS_BARRIERS
@@ -42,7 +42,7 @@
 #elif defined(CONFIG_ARM_DMA_MEM_BUFFERABLE) || defined(CONFIG_SMP)
 #define mb()		do { dsb(); outer_sync(); } while (0)
 #define rmb()		dsb()
-#define wmb()		mb()
+#define wmb()		do { dsb(st); outer_sync(); } while (0)
 #else
 #define mb()		barrier()
 #define rmb()		barrier()
@@ -54,9 +54,9 @@
 #define smp_rmb()	barrier()
 #define smp_wmb()	barrier()
 #else
-#define smp_mb()	dmb()
-#define smp_rmb()	dmb()
-#define smp_wmb()	dmb()
+#define smp_mb()	dmb(ish)
+#define smp_rmb()	smp_mb()
+#define smp_wmb()	dmb(ishst)
 #endif
 
 #define read_barrier_depends()		do { } while(0)
diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h
index 17d0ae8672fa..15f2d5bf8875 100644
--- a/arch/arm/include/asm/cacheflush.h
+++ b/arch/arm/include/asm/cacheflush.h
@@ -268,8 +268,7 @@ extern void flush_cache_page(struct vm_area_struct *vma, unsigned long user_addr
  * Harvard caches are synchronised for the user space address range.
  * This is used for the ARM private sys_cacheflush system call.
  */
-#define flush_cache_user_range(start,end) \
-	__cpuc_coherent_user_range((start) & PAGE_MASK, PAGE_ALIGN(end))
+#define flush_cache_user_range(s,e)	__cpuc_coherent_user_range(s,e)
 
 /*
  * Perform necessary cache operations to ensure that data previously
@@ -352,7 +351,7 @@ static inline void flush_cache_vmap(unsigned long start, unsigned long end)
 		 * set_pte_at() called from vmap_pte_range() does not
 		 * have a DSB after cleaning the cache line.
 		 */
-		dsb();
+		dsb(ishst);
 }
 
 static inline void flush_cache_vunmap(unsigned long start, unsigned long end)
diff --git a/arch/arm/include/asm/dma-contiguous.h b/arch/arm/include/asm/dma-contiguous.h
index 3ed37b4d93da..4f8e9e5514b1 100644
--- a/arch/arm/include/asm/dma-contiguous.h
+++ b/arch/arm/include/asm/dma-contiguous.h
@@ -2,10 +2,9 @@
 #define ASMARM_DMA_CONTIGUOUS_H
 
 #ifdef __KERNEL__
-#ifdef CONFIG_CMA
+#ifdef CONFIG_DMA_CMA
 
 #include <linux/types.h>
-#include <asm-generic/dma-contiguous.h>
 
 void dma_contiguous_early_fixup(phys_addr_t base, unsigned long size);
 
diff --git a/arch/arm/include/asm/elf.h b/arch/arm/include/asm/elf.h
index 56211f2084ef..f4b46d39b9cf 100644
--- a/arch/arm/include/asm/elf.h
+++ b/arch/arm/include/asm/elf.h
@@ -19,8 +19,6 @@ typedef elf_greg_t elf_gregset_t[ELF_NGREG];
 
 typedef struct user_fp elf_fpregset_t;
 
-#define EM_ARM	40
-
 #define EF_ARM_EABI_MASK	0xff000000
 #define EF_ARM_EABI_UNKNOWN	0x00000000
 #define EF_ARM_EABI_VER1	0x01000000
diff --git a/arch/arm/include/asm/hardware/debug-8250.S b/arch/arm/include/asm/hardware/debug-8250.S
deleted file mode 100644
index 22c689255e6e..000000000000
--- a/arch/arm/include/asm/hardware/debug-8250.S
+++ /dev/null
@@ -1,29 +0,0 @@
-/*
- * arch/arm/include/asm/hardware/debug-8250.S
- *
- *  Copyright (C) 1994-1999 Russell King
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/serial_reg.h>
-
-		.macro	senduart,rd,rx
-		strb	\rd, [\rx, #UART_TX << UART_SHIFT]
-		.endm
-
-		.macro	busyuart,rd,rx
-1002:		ldrb	\rd, [\rx, #UART_LSR << UART_SHIFT]
-		and	\rd, \rd, #UART_LSR_TEMT | UART_LSR_THRE
-		teq	\rd, #UART_LSR_TEMT | UART_LSR_THRE
-		bne	1002b
-		.endm
-
-		.macro	waituart,rd,rx
-#ifdef FLOW_CONTROL
-1001:		ldrb	\rd, [\rx, #UART_MSR << UART_SHIFT]
-		tst	\rd, #UART_MSR_CTS
-		beq	1001b
-#endif
-		.endm
diff --git a/arch/arm/include/asm/jump_label.h b/arch/arm/include/asm/jump_label.h
index bfc198c75913..863c892b4aaa 100644
--- a/arch/arm/include/asm/jump_label.h
+++ b/arch/arm/include/asm/jump_label.h
@@ -16,7 +16,7 @@
 
 static __always_inline bool arch_static_branch(struct static_key *key)
 {
-	asm goto("1:\n\t"
+	asm_volatile_goto("1:\n\t"
 		 JUMP_LABEL_NOP "\n\t"
 		 ".pushsection __jump_table,  \"aw\"\n\t"
 		 ".word 1b, %l[l_yes], %c0\n\t"
diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h
index 472ac7091003..9b28c41f4ba9 100644
--- a/arch/arm/include/asm/kvm_mmu.h
+++ b/arch/arm/include/asm/kvm_mmu.h
@@ -64,7 +64,7 @@ void kvm_clear_hyp_idmap(void);
 
 static inline void kvm_set_pte(pte_t *pte, pte_t new_pte)
 {
-	pte_val(*pte) = new_pte;
+	*pte = new_pte;
 	/*
 	 * flush_pmd_entry just takes a void pointer and cleans the necessary
 	 * cache entries, so we can reuse the function for ptes.
diff --git a/arch/arm/include/asm/localtimer.h b/arch/arm/include/asm/localtimer.h
deleted file mode 100644
index f77ffc1eb0c2..000000000000
--- a/arch/arm/include/asm/localtimer.h
+++ /dev/null
@@ -1,34 +0,0 @@
-/*
- *  arch/arm/include/asm/localtimer.h
- *
- *  Copyright (C) 2004-2005 ARM Ltd.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_ARM_LOCALTIMER_H
-#define __ASM_ARM_LOCALTIMER_H
-
-#include <linux/errno.h>
-
-struct clock_event_device;
-
-struct local_timer_ops {
-	int  (*setup)(struct clock_event_device *);
-	void (*stop)(struct clock_event_device *);
-};
-
-#ifdef CONFIG_LOCAL_TIMERS
-/*
- * Register a local timer driver
- */
-int local_timer_register(struct local_timer_ops *);
-#else
-static inline int local_timer_register(struct local_timer_ops *ops)
-{
-	return -ENXIO;
-}
-#endif
-
-#endif
diff --git a/arch/arm/include/asm/mach/arch.h b/arch/arm/include/asm/mach/arch.h
index 441efc491b50..402a2bc6aa68 100644
--- a/arch/arm/include/asm/mach/arch.h
+++ b/arch/arm/include/asm/mach/arch.h
@@ -35,7 +35,7 @@ struct machine_desc {
 	unsigned int		nr_irqs;	/* number of IRQs */
 
 #ifdef CONFIG_ZONE_DMA
-	unsigned long		dma_zone_size;	/* size of DMA-able area */
+	phys_addr_t		dma_zone_size;	/* size of DMA-able area */
 #endif
 
 	unsigned int		video_start;	/* start of video RAM	*/
@@ -65,12 +65,12 @@ struct machine_desc {
 /*
  * Current machine - only accessible during boot.
  */
-extern struct machine_desc *machine_desc;
+extern const struct machine_desc *machine_desc;
 
 /*
  * Machine type table - also only accessible during boot
  */
-extern struct machine_desc __arch_info_begin[], __arch_info_end[];
+extern const struct machine_desc __arch_info_begin[], __arch_info_end[];
 #define for_each_machine_desc(p)			\
 	for (p = __arch_info_begin; p < __arch_info_end; p++)
 
diff --git a/arch/arm/include/asm/mach/pci.h b/arch/arm/include/asm/mach/pci.h
index a1c90d7feb0e..454d642a4070 100644
--- a/arch/arm/include/asm/mach/pci.h
+++ b/arch/arm/include/asm/mach/pci.h
@@ -36,6 +36,8 @@ struct hw_pci {
 					  resource_size_t start,
 					  resource_size_t size,
 					  resource_size_t align);
+	void		(*add_bus)(struct pci_bus *bus);
+	void		(*remove_bus)(struct pci_bus *bus);
 };
 
 /*
@@ -63,6 +65,8 @@ struct pci_sys_data {
 					  resource_size_t start,
 					  resource_size_t size,
 					  resource_size_t align);
+	void		(*add_bus)(struct pci_bus *bus);
+	void		(*remove_bus)(struct pci_bus *bus);
 	void		*private_data;	/* platform controller private data	*/
 };
 
diff --git a/arch/arm/include/asm/mcpm.h b/arch/arm/include/asm/mcpm.h
index 0f7b7620e9a5..fc82a88f5b69 100644
--- a/arch/arm/include/asm/mcpm.h
+++ b/arch/arm/include/asm/mcpm.h
@@ -76,8 +76,11 @@ int mcpm_cpu_power_up(unsigned int cpu, unsigned int cluster);
  *
  * This must be called with interrupts disabled.
  *
- * This does not return.  Re-entry in the kernel is expected via
- * mcpm_entry_point.
+ * On success this does not return.  Re-entry in the kernel is expected
+ * via mcpm_entry_point.
+ *
+ * This will return if mcpm_platform_register() has not been called
+ * previously in which case the caller should take appropriate action.
  */
 void mcpm_cpu_power_down(void);
 
@@ -98,8 +101,11 @@ void mcpm_cpu_power_down(void);
  *
  * This must be called with interrupts disabled.
  *
- * This does not return.  Re-entry in the kernel is expected via
- * mcpm_entry_point.
+ * On success this does not return.  Re-entry in the kernel is expected
+ * via mcpm_entry_point.
+ *
+ * This will return if mcpm_platform_register() has not been called
+ * previously in which case the caller should take appropriate action.
  */
 void mcpm_cpu_suspend(u64 expected_residency);
 
diff --git a/arch/arm/include/asm/memblock.h b/arch/arm/include/asm/memblock.h
index 00ca5f92648e..c2f5102ae659 100644
--- a/arch/arm/include/asm/memblock.h
+++ b/arch/arm/include/asm/memblock.h
@@ -4,8 +4,7 @@
 struct meminfo;
 struct machine_desc;
 
-extern void arm_memblock_init(struct meminfo *, struct machine_desc *);
-
+void arm_memblock_init(struct meminfo *, const struct machine_desc *);
 phys_addr_t arm_memblock_steal(phys_addr_t size, phys_addr_t align);
 
 #endif
diff --git a/arch/arm/include/asm/module.h b/arch/arm/include/asm/module.h
index 0d3a28dbc8e5..ed690c49ef93 100644
--- a/arch/arm/include/asm/module.h
+++ b/arch/arm/include/asm/module.h
@@ -12,6 +12,8 @@ enum {
 	ARM_SEC_CORE,
 	ARM_SEC_EXIT,
 	ARM_SEC_DEVEXIT,
+	ARM_SEC_HOT,
+	ARM_SEC_UNLIKELY,
 	ARM_SEC_MAX,
 };
 
diff --git a/arch/arm/include/asm/neon.h b/arch/arm/include/asm/neon.h
new file mode 100644
index 000000000000..8f730fe70093
--- /dev/null
+++ b/arch/arm/include/asm/neon.h
@@ -0,0 +1,36 @@
+/*
+ * linux/arch/arm/include/asm/neon.h
+ *
+ * Copyright (C) 2013 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <asm/hwcap.h>
+
+#define cpu_has_neon()		(!!(elf_hwcap & HWCAP_NEON))
+
+#ifdef __ARM_NEON__
+
+/*
+ * If you are affected by the BUILD_BUG below, it probably means that you are
+ * using NEON code /and/ calling the kernel_neon_begin() function from the same
+ * compilation unit. To prevent issues that may arise from GCC reordering or
+ * generating(1) NEON instructions outside of these begin/end functions, the
+ * only supported way of using NEON code in the kernel is by isolating it in a
+ * separate compilation unit, and calling it from another unit from inside a
+ * kernel_neon_begin/kernel_neon_end pair.
+ *
+ * (1) Current GCC (4.7) might generate NEON instructions at O3 level if
+ *     -mpfu=neon is set.
+ */
+
+#define kernel_neon_begin() \
+	BUILD_BUG_ON_MSG(1, "kernel_neon_begin() called from NEON code")
+
+#else
+void kernel_neon_begin(void);
+#endif
+void kernel_neon_end(void);
diff --git a/arch/arm/include/asm/outercache.h b/arch/arm/include/asm/outercache.h
index 12f71a190422..f94784f0e3a6 100644
--- a/arch/arm/include/asm/outercache.h
+++ b/arch/arm/include/asm/outercache.h
@@ -37,10 +37,10 @@ struct outer_cache_fns {
 	void (*resume)(void);
 };
 
-#ifdef CONFIG_OUTER_CACHE
-
 extern struct outer_cache_fns outer_cache;
 
+#ifdef CONFIG_OUTER_CACHE
+
 static inline void outer_inv_range(phys_addr_t start, phys_addr_t end)
 {
 	if (outer_cache.inv_range)
diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h
index 04aeb02d2e11..be956dbf6bae 100644
--- a/arch/arm/include/asm/pgtable.h
+++ b/arch/arm/include/asm/pgtable.h
@@ -100,7 +100,7 @@ extern pgprot_t		pgprot_s2_device;
 #define PAGE_HYP		_MOD_PROT(pgprot_kernel, L_PTE_HYP)
 #define PAGE_HYP_DEVICE		_MOD_PROT(pgprot_hyp_device, L_PTE_HYP)
 #define PAGE_S2			_MOD_PROT(pgprot_s2, L_PTE_S2_RDONLY)
-#define PAGE_S2_DEVICE		_MOD_PROT(pgprot_s2_device, L_PTE_USER | L_PTE_S2_RDONLY)
+#define PAGE_S2_DEVICE		_MOD_PROT(pgprot_s2_device, L_PTE_S2_RDWR)
 
 #define __PAGE_NONE		__pgprot(_L_PTE_DEFAULT | L_PTE_RDONLY | L_PTE_XN | L_PTE_NONE)
 #define __PAGE_SHARED		__pgprot(_L_PTE_DEFAULT | L_PTE_USER | L_PTE_XN)
diff --git a/arch/arm/include/asm/prom.h b/arch/arm/include/asm/prom.h
index a219227c3e43..4a2985e21969 100644
--- a/arch/arm/include/asm/prom.h
+++ b/arch/arm/include/asm/prom.h
@@ -15,13 +15,13 @@
 
 #ifdef CONFIG_OF
 
-extern struct machine_desc *setup_machine_fdt(unsigned int dt_phys);
+extern const struct machine_desc *setup_machine_fdt(unsigned int dt_phys);
 extern void arm_dt_memblock_reserve(void);
 extern void __init arm_dt_init_cpu_maps(void);
 
 #else /* CONFIG_OF */
 
-static inline struct machine_desc *setup_machine_fdt(unsigned int dt_phys)
+static inline const struct machine_desc *setup_machine_fdt(unsigned int dt_phys)
 {
 	return NULL;
 }
diff --git a/arch/arm/include/asm/spinlock.h b/arch/arm/include/asm/spinlock.h
index b07c09e5a0ac..4f2c28060c9a 100644
--- a/arch/arm/include/asm/spinlock.h
+++ b/arch/arm/include/asm/spinlock.h
@@ -46,7 +46,7 @@ static inline void dsb_sev(void)
 {
 #if __LINUX_ARM_ARCH__ >= 7
 	__asm__ __volatile__ (
-		"dsb\n"
+		"dsb ishst\n"
 		SEV
 	);
 #else
diff --git a/arch/arm/include/asm/switch_to.h b/arch/arm/include/asm/switch_to.h
index fa09e6b49bf1..c99e259469f7 100644
--- a/arch/arm/include/asm/switch_to.h
+++ b/arch/arm/include/asm/switch_to.h
@@ -4,6 +4,16 @@
 #include <linux/thread_info.h>
 
 /*
+ * For v7 SMP cores running a preemptible kernel we may be pre-empted
+ * during a TLB maintenance operation, so execute an inner-shareable dsb
+ * to ensure that the maintenance completes in case we migrate to another
+ * CPU.
+ */
+#if defined(CONFIG_PREEMPT) && defined(CONFIG_SMP) && defined(CONFIG_CPU_V7)
+#define finish_arch_switch(prev)	dsb(ish)
+#endif
+
+/*
  * switch_to(prev, next) should switch from task `prev' to `next'
  * `prev' will never be the same as `next'.  schedule() itself
  * contains the memory barrier to tell GCC not to cache `current'.
diff --git a/arch/arm/include/asm/syscall.h b/arch/arm/include/asm/syscall.h
index f1d96d4e8092..73ddd7239b33 100644
--- a/arch/arm/include/asm/syscall.h
+++ b/arch/arm/include/asm/syscall.h
@@ -57,6 +57,9 @@ static inline void syscall_get_arguments(struct task_struct *task,
 					 unsigned int i, unsigned int n,
 					 unsigned long *args)
 {
+	if (n == 0)
+		return;
+
 	if (i + n > SYSCALL_MAX_ARGS) {
 		unsigned long *args_bad = args + SYSCALL_MAX_ARGS - i;
 		unsigned int n_bad = n + i - SYSCALL_MAX_ARGS;
@@ -81,6 +84,9 @@ static inline void syscall_set_arguments(struct task_struct *task,
 					 unsigned int i, unsigned int n,
 					 const unsigned long *args)
 {
+	if (n == 0)
+		return;
+
 	if (i + n > SYSCALL_MAX_ARGS) {
 		pr_warning("%s called with max args %d, handling only %d\n",
 			   __func__, i + n, SYSCALL_MAX_ARGS);
diff --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h
index 2b8114fcba09..df5e13d64f2c 100644
--- a/arch/arm/include/asm/thread_info.h
+++ b/arch/arm/include/asm/thread_info.h
@@ -43,6 +43,16 @@ struct cpu_context_save {
 	__u32	extra[2];		/* Xscale 'acc' register, etc */
 };
 
+struct arm_restart_block {
+	union {
+		/* For user cache flushing */
+		struct {
+			unsigned long start;
+			unsigned long end;
+		} cache;
+	};
+};
+
 /*
  * low level task data that entry.S needs immediate access to.
  * __switch_to() assumes cpu_context follows immediately after cpu_domain.
@@ -68,6 +78,7 @@ struct thread_info {
 	unsigned long		thumbee_state;	/* ThumbEE Handler Base register */
 #endif
 	struct restart_block	restart_block;
+	struct arm_restart_block	arm_restart_block;
 };
 
 #define INIT_THREAD_INFO(tsk)						\
diff --git a/arch/arm/include/asm/tlbflush.h b/arch/arm/include/asm/tlbflush.h
index f467e9b3f8d5..38960264040c 100644
--- a/arch/arm/include/asm/tlbflush.h
+++ b/arch/arm/include/asm/tlbflush.h
@@ -319,67 +319,110 @@ extern struct cpu_tlb_fns cpu_tlb;
 #define tlb_op(f, regs, arg)	__tlb_op(f, "p15, 0, %0, " regs, arg)
 #define tlb_l2_op(f, regs, arg)	__tlb_op(f, "p15, 1, %0, " regs, arg)
 
-static inline void local_flush_tlb_all(void)
+static inline void __local_flush_tlb_all(void)
 {
 	const int zero = 0;
 	const unsigned int __tlb_flag = __cpu_tlb_flags;
 
-	if (tlb_flag(TLB_WB))
-		dsb();
-
 	tlb_op(TLB_V4_U_FULL | TLB_V6_U_FULL, "c8, c7, 0", zero);
 	tlb_op(TLB_V4_D_FULL | TLB_V6_D_FULL, "c8, c6, 0", zero);
 	tlb_op(TLB_V4_I_FULL | TLB_V6_I_FULL, "c8, c5, 0", zero);
-	tlb_op(TLB_V7_UIS_FULL, "c8, c3, 0", zero);
+}
+
+static inline void local_flush_tlb_all(void)
+{
+	const int zero = 0;
+	const unsigned int __tlb_flag = __cpu_tlb_flags;
+
+	if (tlb_flag(TLB_WB))
+		dsb(nshst);
+
+	__local_flush_tlb_all();
+	tlb_op(TLB_V7_UIS_FULL, "c8, c7, 0", zero);
 
 	if (tlb_flag(TLB_BARRIER)) {
-		dsb();
+		dsb(nsh);
 		isb();
 	}
 }
 
-static inline void local_flush_tlb_mm(struct mm_struct *mm)
+static inline void __flush_tlb_all(void)
 {
 	const int zero = 0;
-	const int asid = ASID(mm);
 	const unsigned int __tlb_flag = __cpu_tlb_flags;
 
 	if (tlb_flag(TLB_WB))
-		dsb();
+		dsb(ishst);
+
+	__local_flush_tlb_all();
+	tlb_op(TLB_V7_UIS_FULL, "c8, c3, 0", zero);
+
+	if (tlb_flag(TLB_BARRIER)) {
+		dsb(ish);
+		isb();
+	}
+}
+
+static inline void __local_flush_tlb_mm(struct mm_struct *mm)
+{
+	const int zero = 0;
+	const int asid = ASID(mm);
+	const unsigned int __tlb_flag = __cpu_tlb_flags;
 
 	if (possible_tlb_flags & (TLB_V4_U_FULL|TLB_V4_D_FULL|TLB_V4_I_FULL)) {
-		if (cpumask_test_cpu(get_cpu(), mm_cpumask(mm))) {
+		if (cpumask_test_cpu(smp_processor_id(), mm_cpumask(mm))) {
 			tlb_op(TLB_V4_U_FULL, "c8, c7, 0", zero);
 			tlb_op(TLB_V4_D_FULL, "c8, c6, 0", zero);
 			tlb_op(TLB_V4_I_FULL, "c8, c5, 0", zero);
 		}
-		put_cpu();
 	}
 
 	tlb_op(TLB_V6_U_ASID, "c8, c7, 2", asid);
 	tlb_op(TLB_V6_D_ASID, "c8, c6, 2", asid);
 	tlb_op(TLB_V6_I_ASID, "c8, c5, 2", asid);
+}
+
+static inline void local_flush_tlb_mm(struct mm_struct *mm)
+{
+	const int asid = ASID(mm);
+	const unsigned int __tlb_flag = __cpu_tlb_flags;
+
+	if (tlb_flag(TLB_WB))
+		dsb(nshst);
+
+	__local_flush_tlb_mm(mm);
+	tlb_op(TLB_V7_UIS_ASID, "c8, c7, 2", asid);
+
+	if (tlb_flag(TLB_BARRIER))
+		dsb(nsh);
+}
+
+static inline void __flush_tlb_mm(struct mm_struct *mm)
+{
+	const unsigned int __tlb_flag = __cpu_tlb_flags;
+
+	if (tlb_flag(TLB_WB))
+		dsb(ishst);
+
+	__local_flush_tlb_mm(mm);
 #ifdef CONFIG_ARM_ERRATA_720789
-	tlb_op(TLB_V7_UIS_ASID, "c8, c3, 0", zero);
+	tlb_op(TLB_V7_UIS_ASID, "c8, c3, 0", 0);
 #else
-	tlb_op(TLB_V7_UIS_ASID, "c8, c3, 2", asid);
+	tlb_op(TLB_V7_UIS_ASID, "c8, c3, 2", ASID(mm));
 #endif
 
 	if (tlb_flag(TLB_BARRIER))
-		dsb();
+		dsb(ish);
 }
 
 static inline void
-local_flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr)
+__local_flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr)
 {
 	const int zero = 0;
 	const unsigned int __tlb_flag = __cpu_tlb_flags;
 
 	uaddr = (uaddr & PAGE_MASK) | ASID(vma->vm_mm);
 
-	if (tlb_flag(TLB_WB))
-		dsb();
-
 	if (possible_tlb_flags & (TLB_V4_U_PAGE|TLB_V4_D_PAGE|TLB_V4_I_PAGE|TLB_V4_I_FULL) &&
 	    cpumask_test_cpu(smp_processor_id(), mm_cpumask(vma->vm_mm))) {
 		tlb_op(TLB_V4_U_PAGE, "c8, c7, 1", uaddr);
@@ -392,6 +435,36 @@ local_flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr)
 	tlb_op(TLB_V6_U_PAGE, "c8, c7, 1", uaddr);
 	tlb_op(TLB_V6_D_PAGE, "c8, c6, 1", uaddr);
 	tlb_op(TLB_V6_I_PAGE, "c8, c5, 1", uaddr);
+}
+
+static inline void
+local_flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr)
+{
+	const unsigned int __tlb_flag = __cpu_tlb_flags;
+
+	uaddr = (uaddr & PAGE_MASK) | ASID(vma->vm_mm);
+
+	if (tlb_flag(TLB_WB))
+		dsb(nshst);
+
+	__local_flush_tlb_page(vma, uaddr);
+	tlb_op(TLB_V7_UIS_PAGE, "c8, c7, 1", uaddr);
+
+	if (tlb_flag(TLB_BARRIER))
+		dsb(nsh);
+}
+
+static inline void
+__flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr)
+{
+	const unsigned int __tlb_flag = __cpu_tlb_flags;
+
+	uaddr = (uaddr & PAGE_MASK) | ASID(vma->vm_mm);
+
+	if (tlb_flag(TLB_WB))
+		dsb(ishst);
+
+	__local_flush_tlb_page(vma, uaddr);
 #ifdef CONFIG_ARM_ERRATA_720789
 	tlb_op(TLB_V7_UIS_PAGE, "c8, c3, 3", uaddr & PAGE_MASK);
 #else
@@ -399,19 +472,14 @@ local_flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr)
 #endif
 
 	if (tlb_flag(TLB_BARRIER))
-		dsb();
+		dsb(ish);
 }
 
-static inline void local_flush_tlb_kernel_page(unsigned long kaddr)
+static inline void __local_flush_tlb_kernel_page(unsigned long kaddr)
 {
 	const int zero = 0;
 	const unsigned int __tlb_flag = __cpu_tlb_flags;
 
-	kaddr &= PAGE_MASK;
-
-	if (tlb_flag(TLB_WB))
-		dsb();
-
 	tlb_op(TLB_V4_U_PAGE, "c8, c7, 1", kaddr);
 	tlb_op(TLB_V4_D_PAGE, "c8, c6, 1", kaddr);
 	tlb_op(TLB_V4_I_PAGE, "c8, c5, 1", kaddr);
@@ -421,26 +489,75 @@ static inline void local_flush_tlb_kernel_page(unsigned long kaddr)
 	tlb_op(TLB_V6_U_PAGE, "c8, c7, 1", kaddr);
 	tlb_op(TLB_V6_D_PAGE, "c8, c6, 1", kaddr);
 	tlb_op(TLB_V6_I_PAGE, "c8, c5, 1", kaddr);
+}
+
+static inline void local_flush_tlb_kernel_page(unsigned long kaddr)
+{
+	const unsigned int __tlb_flag = __cpu_tlb_flags;
+
+	kaddr &= PAGE_MASK;
+
+	if (tlb_flag(TLB_WB))
+		dsb(nshst);
+
+	__local_flush_tlb_kernel_page(kaddr);
+	tlb_op(TLB_V7_UIS_PAGE, "c8, c7, 1", kaddr);
+
+	if (tlb_flag(TLB_BARRIER)) {
+		dsb(nsh);
+		isb();
+	}
+}
+
+static inline void __flush_tlb_kernel_page(unsigned long kaddr)
+{
+	const unsigned int __tlb_flag = __cpu_tlb_flags;
+
+	kaddr &= PAGE_MASK;
+
+	if (tlb_flag(TLB_WB))
+		dsb(ishst);
+
+	__local_flush_tlb_kernel_page(kaddr);
 	tlb_op(TLB_V7_UIS_PAGE, "c8, c3, 1", kaddr);
 
 	if (tlb_flag(TLB_BARRIER)) {
-		dsb();
+		dsb(ish);
 		isb();
 	}
 }
 
+/*
+ * Branch predictor maintenance is paired with full TLB invalidation, so
+ * there is no need for any barriers here.
+ */
+static inline void __local_flush_bp_all(void)
+{
+	const int zero = 0;
+	const unsigned int __tlb_flag = __cpu_tlb_flags;
+
+	if (tlb_flag(TLB_V6_BP))
+		asm("mcr p15, 0, %0, c7, c5, 6" : : "r" (zero));
+}
+
 static inline void local_flush_bp_all(void)
 {
 	const int zero = 0;
 	const unsigned int __tlb_flag = __cpu_tlb_flags;
 
+	__local_flush_bp_all();
 	if (tlb_flag(TLB_V7_UIS_BP))
-		asm("mcr p15, 0, %0, c7, c1, 6" : : "r" (zero));
-	else if (tlb_flag(TLB_V6_BP))
 		asm("mcr p15, 0, %0, c7, c5, 6" : : "r" (zero));
+}
 
-	if (tlb_flag(TLB_BARRIER))
-		isb();
+static inline void __flush_bp_all(void)
+{
+	const int zero = 0;
+	const unsigned int __tlb_flag = __cpu_tlb_flags;
+
+	__local_flush_bp_all();
+	if (tlb_flag(TLB_V7_UIS_BP))
+		asm("mcr p15, 0, %0, c7, c1, 6" : : "r" (zero));
 }
 
 #include <asm/cputype.h>
@@ -461,7 +578,7 @@ static inline void dummy_flush_tlb_a15_erratum(void)
 	 * Dummy TLBIMVAIS. Using the unmapped address 0 and ASID 0.
 	 */
 	asm("mcr p15, 0, %0, c8, c3, 1" : : "r" (0));
-	dsb();
+	dsb(ish);
 }
 #else
 static inline int erratum_a15_798181(void)
@@ -495,7 +612,7 @@ static inline void flush_pmd_entry(void *pmd)
 	tlb_l2_op(TLB_L2CLEAN_FR, "c15, c9, 1  @ L2 flush_pmd", pmd);
 
 	if (tlb_flag(TLB_WB))
-		dsb();
+		dsb(ishst);
 }
 
 static inline void clean_pmd_entry(void *pmd)
diff --git a/arch/arm/include/asm/types.h b/arch/arm/include/asm/types.h
new file mode 100644
index 000000000000..a53cdb8f068c
--- /dev/null
+++ b/arch/arm/include/asm/types.h
@@ -0,0 +1,40 @@
+#ifndef _ASM_TYPES_H
+#define _ASM_TYPES_H
+
+#include <asm-generic/int-ll64.h>
+
+/*
+ * The C99 types uintXX_t that are usually defined in 'stdint.h' are not as
+ * unambiguous on ARM as you would expect. For the types below, there is a
+ * difference on ARM between GCC built for bare metal ARM, GCC built for glibc
+ * and the kernel itself, which results in build errors if you try to build with
+ * -ffreestanding and include 'stdint.h' (such as when you include 'arm_neon.h'
+ * in order to use NEON intrinsics)
+ *
+ * As the typedefs for these types in 'stdint.h' are based on builtin defines
+ * supplied by GCC, we can tweak these to align with the kernel's idea of those
+ * types, so 'linux/types.h' and 'stdint.h' can be safely included from the same
+ * source file (provided that -ffreestanding is used).
+ *
+ *                    int32_t         uint32_t               uintptr_t
+ * bare metal GCC     long            unsigned long          unsigned int
+ * glibc GCC          int             unsigned int           unsigned int
+ * kernel             int             unsigned int           unsigned long
+ */
+
+#ifdef __INT32_TYPE__
+#undef __INT32_TYPE__
+#define __INT32_TYPE__		int
+#endif
+
+#ifdef __UINT32_TYPE__
+#undef __UINT32_TYPE__
+#define __UINT32_TYPE__	unsigned int
+#endif
+
+#ifdef __UINTPTR_TYPE__
+#undef __UINTPTR_TYPE__
+#define __UINTPTR_TYPE__	unsigned long
+#endif
+
+#endif /* _ASM_TYPES_H */
diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h
index 7e1f76027f66..72abdc541f38 100644
--- a/arch/arm/include/asm/uaccess.h
+++ b/arch/arm/include/asm/uaccess.h
@@ -19,6 +19,13 @@
 #include <asm/unified.h>
 #include <asm/compiler.h>
 
+#if __LINUX_ARM_ARCH__ < 6
+#include <asm-generic/uaccess-unaligned.h>
+#else
+#define __get_user_unaligned __get_user
+#define __put_user_unaligned __put_user
+#endif
+
 #define VERIFY_READ 0
 #define VERIFY_WRITE 1
 
diff --git a/arch/arm/include/asm/v7m.h b/arch/arm/include/asm/v7m.h
index fa88d09fa3d9..615781c61627 100644
--- a/arch/arm/include/asm/v7m.h
+++ b/arch/arm/include/asm/v7m.h
@@ -15,6 +15,10 @@
 
 #define V7M_SCB_VTOR			0x08
 
+#define V7M_SCB_AIRCR			0x0c
+#define V7M_SCB_AIRCR_VECTKEY			(0x05fa << 16)
+#define V7M_SCB_AIRCR_SYSRESETREQ		(1 << 2)
+
 #define V7M_SCB_SCR			0x10
 #define V7M_SCB_SCR_SLEEPDEEP			(1 << 2)
 
@@ -42,3 +46,11 @@
  */
 #define EXC_RET_STACK_MASK			0x00000004
 #define EXC_RET_THREADMODE_PROCESSSTACK		0xfffffffd
+
+#ifndef __ASSEMBLY__
+
+enum reboot_mode;
+
+void armv7m_restart(enum reboot_mode mode, const char *cmd);
+
+#endif /* __ASSEMBLY__ */
diff --git a/arch/arm/include/asm/xor.h b/arch/arm/include/asm/xor.h
index 7604673dc427..4ffb26d4cad8 100644
--- a/arch/arm/include/asm/xor.h
+++ b/arch/arm/include/asm/xor.h
@@ -7,7 +7,10 @@
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
  */
+#include <linux/hardirq.h>
 #include <asm-generic/xor.h>
+#include <asm/hwcap.h>
+#include <asm/neon.h>
 
 #define __XOR(a1, a2) a1 ^= a2
 
@@ -138,4 +141,74 @@ static struct xor_block_template xor_block_arm4regs = {
 		xor_speed(&xor_block_arm4regs);	\
 		xor_speed(&xor_block_8regs);	\
 		xor_speed(&xor_block_32regs);	\
+		NEON_TEMPLATES;			\
 	} while (0)
+
+#ifdef CONFIG_KERNEL_MODE_NEON
+
+extern struct xor_block_template const xor_block_neon_inner;
+
+static void
+xor_neon_2(unsigned long bytes, unsigned long *p1, unsigned long *p2)
+{
+	if (in_interrupt()) {
+		xor_arm4regs_2(bytes, p1, p2);
+	} else {
+		kernel_neon_begin();
+		xor_block_neon_inner.do_2(bytes, p1, p2);
+		kernel_neon_end();
+	}
+}
+
+static void
+xor_neon_3(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+		unsigned long *p3)
+{
+	if (in_interrupt()) {
+		xor_arm4regs_3(bytes, p1, p2, p3);
+	} else {
+		kernel_neon_begin();
+		xor_block_neon_inner.do_3(bytes, p1, p2, p3);
+		kernel_neon_end();
+	}
+}
+
+static void
+xor_neon_4(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+		unsigned long *p3, unsigned long *p4)
+{
+	if (in_interrupt()) {
+		xor_arm4regs_4(bytes, p1, p2, p3, p4);
+	} else {
+		kernel_neon_begin();
+		xor_block_neon_inner.do_4(bytes, p1, p2, p3, p4);
+		kernel_neon_end();
+	}
+}
+
+static void
+xor_neon_5(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+		unsigned long *p3, unsigned long *p4, unsigned long *p5)
+{
+	if (in_interrupt()) {
+		xor_arm4regs_5(bytes, p1, p2, p3, p4, p5);
+	} else {
+		kernel_neon_begin();
+		xor_block_neon_inner.do_5(bytes, p1, p2, p3, p4, p5);
+		kernel_neon_end();
+	}
+}
+
+static struct xor_block_template xor_block_neon = {
+	.name	= "neon",
+	.do_2	= xor_neon_2,
+	.do_3	= xor_neon_3,
+	.do_4	= xor_neon_4,
+	.do_5	= xor_neon_5
+};
+
+#define NEON_TEMPLATES	\
+	do { if (cpu_has_neon()) xor_speed(&xor_block_neon); } while (0)
+#else
+#define NEON_TEMPLATES
+#endif
diff --git a/arch/arm/include/debug/8250.S b/arch/arm/include/debug/8250.S
new file mode 100644
index 000000000000..7a2baf913aa0
--- /dev/null
+++ b/arch/arm/include/debug/8250.S
@@ -0,0 +1,54 @@
+/*
+ * arch/arm/include/debug/8250.S
+ *
+ *  Copyright (C) 1994-2013 Russell King
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/serial_reg.h>
+
+		.macro	addruart, rp, rv, tmp
+		ldr	\rp, =CONFIG_DEBUG_UART_PHYS
+		ldr	\rv, =CONFIG_DEBUG_UART_VIRT
+		.endm
+
+#ifdef CONFIG_DEBUG_UART_8250_WORD
+		.macro	store, rd, rx:vararg
+		str	\rd, \rx
+		.endm
+
+		.macro	load, rd, rx:vararg
+		ldr	\rd, \rx
+		.endm
+#else
+		.macro	store, rd, rx:vararg
+		strb	\rd, \rx
+		.endm
+
+		.macro	load, rd, rx:vararg
+		ldrb	\rd, \rx
+		.endm
+#endif
+
+#define UART_SHIFT CONFIG_DEBUG_UART_8250_SHIFT
+
+		.macro	senduart,rd,rx
+		store	\rd, [\rx, #UART_TX << UART_SHIFT]
+		.endm
+
+		.macro	busyuart,rd,rx
+1002:		load	\rd, [\rx, #UART_LSR << UART_SHIFT]
+		and	\rd, \rd, #UART_LSR_TEMT | UART_LSR_THRE
+		teq	\rd, #UART_LSR_TEMT | UART_LSR_THRE
+		bne	1002b
+		.endm
+
+		.macro	waituart,rd,rx
+#ifdef CONFIG_DEBUG_UART_8250_FLOW_CONTROL
+1001:		load	\rd, [\rx, #UART_MSR << UART_SHIFT]
+		tst	\rd, #UART_MSR_CTS
+		beq	1001b
+#endif
+		.endm
diff --git a/arch/arm/include/debug/8250_32.S b/arch/arm/include/debug/8250_32.S
deleted file mode 100644
index 8db01eeabbb4..000000000000
--- a/arch/arm/include/debug/8250_32.S
+++ /dev/null
@@ -1,27 +0,0 @@
-/*
- * Copyright (c) 2011 Picochip Ltd., Jamie Iles
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * Derived from arch/arm/mach-davinci/include/mach/debug-macro.S to use 32-bit
- * accesses to the 8250.
- */
-
-#include <linux/serial_reg.h>
-
-		.macro	senduart,rd,rx
-		str	\rd, [\rx, #UART_TX << UART_SHIFT]
-		.endm
-
-		.macro	busyuart,rd,rx
-1002:		ldr	\rd, [\rx, #UART_LSR << UART_SHIFT]
-		and	\rd, \rd, #UART_LSR_TEMT | UART_LSR_THRE
-		teq	\rd, #UART_LSR_TEMT | UART_LSR_THRE
-		bne	1002b
-		.endm
-
-		/* The UART's don't have any flow control IO's wired up. */
-		.macro	waituart,rd,rx
-		.endm
diff --git a/arch/arm/include/debug/bcm2835.S b/arch/arm/include/debug/bcm2835.S
deleted file mode 100644
index aed9199bd847..000000000000
--- a/arch/arm/include/debug/bcm2835.S
+++ /dev/null
@@ -1,22 +0,0 @@
-/*
- * Debugging macro include header
- *
- * Copyright (C) 2010 Broadcom
- * Copyright (C) 1994-1999 Russell King
- * Moved from linux/arch/arm/kernel/debug.S by Ben Dooks
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- */
-
-#define BCM2835_DEBUG_PHYS 0x20201000
-#define BCM2835_DEBUG_VIRT 0xf0201000
-
-	.macro	addruart, rp, rv, tmp
-	ldr	\rp, =BCM2835_DEBUG_PHYS
-	ldr	\rv, =BCM2835_DEBUG_VIRT
-	.endm
-
-#include <asm/hardware/debug-pl01x.S>
diff --git a/arch/arm/include/debug/cns3xxx.S b/arch/arm/include/debug/cns3xxx.S
deleted file mode 100644
index d04c150baa1c..000000000000
--- a/arch/arm/include/debug/cns3xxx.S
+++ /dev/null
@@ -1,19 +0,0 @@
-/*
- * Debugging macro include header
- *
- * Copyright 1994-1999 Russell King
- * Copyright 2008 Cavium Networks
- * Moved from linux/arch/arm/kernel/debug.S by Ben Dooks
- *
- * This file is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License, Version 2, as
- * published by the Free Software Foundation.
- */
-
-		.macro	addruart,rp,rv,tmp
-		mov	\rp, #0x00009000
-		orr	\rv, \rp, #0xf0000000	@ virtual base
-		orr	\rp, \rp, #0x10000000
-		.endm
-
-#include <asm/hardware/debug-pl01x.S>
diff --git a/arch/arm/include/debug/highbank.S b/arch/arm/include/debug/highbank.S
deleted file mode 100644
index 8cad4322a5a2..000000000000
--- a/arch/arm/include/debug/highbank.S
+++ /dev/null
@@ -1,17 +0,0 @@
-/*
- * Debugging macro include header
- *
- *  Copyright (C) 1994-1999 Russell King
- *  Moved from linux/arch/arm/kernel/debug.S by Ben Dooks
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-		.macro	addruart,rp,rv,tmp
-		ldr	\rv, =0xfee36000
-		ldr	\rp, =0xfff36000
-		.endm
-
-#include <asm/hardware/debug-pl01x.S>
diff --git a/arch/arm/include/debug/keystone.S b/arch/arm/include/debug/keystone.S
deleted file mode 100644
index 9aef9ba3f4f0..000000000000
--- a/arch/arm/include/debug/keystone.S
+++ /dev/null
@@ -1,43 +0,0 @@
-/*
- * Early serial debug output macro for Keystone SOCs
- *
- * Copyright 2013 Texas Instruments, Inc.
- *	Santosh Shilimkar <santosh.shilimkar@ti.com>
- *
- * Based on RMKs low level debug code.
- *  Copyright (C) 1994-1999 Russell King
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/serial_reg.h>
-
-#define UART_SHIFT 2
-#if defined(CONFIG_DEBUG_KEYSTONE_UART0)
-#define UART_PHYS		0x02530c00
-#define UART_VIRT		0xfeb30c00
-#elif defined(CONFIG_DEBUG_KEYSTONE_UART1)
-#define UART_PHYS		0x02531000
-#define UART_VIRT		0xfeb31000
-#endif
-
-	.macro	addruart, rp, rv, tmp
-	ldr	\rv, =UART_VIRT			@ physical base address
-	ldr	\rp, =UART_PHYS			@ virtual base address
-	.endm
-
-	.macro	senduart,rd,rx
-	str	\rd, [\rx, #UART_TX << UART_SHIFT]
-	.endm
-
-	.macro	busyuart,rd,rx
-1002:	ldr	\rd, [\rx, #UART_LSR << UART_SHIFT]
-	and	\rd, \rd, #UART_LSR_TEMT | UART_LSR_THRE
-	teq	\rd, #UART_LSR_TEMT | UART_LSR_THRE
-	bne	1002b
-	.endm
-
-	.macro	waituart,rd,rx
-	.endm
diff --git a/arch/arm/mach-msm/include/mach/debug-macro.S b/arch/arm/include/debug/msm.S
index 0e05f88abcd5..9166e1bc470e 100644
--- a/arch/arm/mach-msm/include/mach/debug-macro.S
+++ b/arch/arm/include/debug/msm.S
@@ -15,8 +15,36 @@
  *
  */
 
-#include <mach/hardware.h>
-#include <mach/msm_iomap.h>
+#if defined(CONFIG_ARCH_MSM7X00A) || defined(CONFIG_ARCH_QSD8X50)
+#define MSM_UART1_PHYS        0xA9A00000
+#define MSM_UART2_PHYS        0xA9B00000
+#define MSM_UART3_PHYS        0xA9C00000
+#elif defined(CONFIG_ARCH_MSM7X30)
+#define MSM_UART1_PHYS        0xACA00000
+#define MSM_UART2_PHYS        0xACB00000
+#define MSM_UART3_PHYS        0xACC00000
+#endif
+
+#if defined(CONFIG_DEBUG_MSM_UART1)
+#define MSM_DEBUG_UART_BASE	0xE1000000
+#define MSM_DEBUG_UART_PHYS	MSM_UART1_PHYS
+#elif defined(CONFIG_DEBUG_MSM_UART2)
+#define MSM_DEBUG_UART_BASE	0xE1000000
+#define MSM_DEBUG_UART_PHYS	MSM_UART2_PHYS
+#elif defined(CONFIG_DEBUG_MSM_UART3)
+#define MSM_DEBUG_UART_BASE	0xE1000000
+#define MSM_DEBUG_UART_PHYS	MSM_UART3_PHYS
+#endif
+
+#ifdef CONFIG_DEBUG_MSM8660_UART
+#define MSM_DEBUG_UART_BASE	0xF0040000
+#define MSM_DEBUG_UART_PHYS	0x19C40000
+#endif
+
+#ifdef CONFIG_DEBUG_MSM8960_UART
+#define MSM_DEBUG_UART_BASE	0xF0040000
+#define MSM_DEBUG_UART_PHYS	0x16440000
+#endif
 
 	.macro	addruart, rp, rv, tmp
 #ifdef MSM_DEBUG_UART_PHYS
diff --git a/arch/arm/include/debug/mvebu.S b/arch/arm/include/debug/mvebu.S
deleted file mode 100644
index 6517311a1c91..000000000000
--- a/arch/arm/include/debug/mvebu.S
+++ /dev/null
@@ -1,30 +0,0 @@
-/*
- * Early serial output macro for Marvell  SoC
- *
- * Copyright (C) 2012 Marvell
- *
- * Lior Amsalem <alior@marvell.com>
- * Gregory Clement <gregory.clement@free-electrons.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
-
-#ifdef CONFIG_DEBUG_MVEBU_UART_ALTERNATE
-#define ARMADA_370_XP_REGS_PHYS_BASE	0xf1000000
-#else
-#define ARMADA_370_XP_REGS_PHYS_BASE	0xd0000000
-#endif
-
-#define ARMADA_370_XP_REGS_VIRT_BASE	0xfec00000
-
-	.macro	addruart, rp, rv, tmp
-	ldr	\rp, =ARMADA_370_XP_REGS_PHYS_BASE
-	ldr	\rv, =ARMADA_370_XP_REGS_VIRT_BASE
-	orr	\rp, \rp, #0x00012000
-	orr	\rv, \rv, #0x00012000
-	.endm
-
-#define UART_SHIFT	2
-#include <asm/hardware/debug-8250.S>
diff --git a/arch/arm/include/debug/mxs.S b/arch/arm/include/debug/mxs.S
deleted file mode 100644
index d86951551ca1..000000000000
--- a/arch/arm/include/debug/mxs.S
+++ /dev/null
@@ -1,27 +0,0 @@
-/* arch/arm/mach-mxs/include/mach/debug-macro.S
- *
- * Debugging macro include header
- *
- *  Copyright (C) 1994-1999 Russell King
- *  Moved from linux/arch/arm/kernel/debug.S by Ben Dooks
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- */
-
-#ifdef CONFIG_DEBUG_IMX23_UART
-#define UART_PADDR	0x80070000
-#elif defined (CONFIG_DEBUG_IMX28_UART)
-#define UART_PADDR	0x80074000
-#endif
-
-#define UART_VADDR	0xfe100000
-
-		.macro	addruart, rp, rv, tmp
-		ldr	\rp, =UART_PADDR	@ physical
-		ldr	\rv, =UART_VADDR	@ virtual
-		.endm
-
-#include <asm/hardware/debug-pl01x.S>
diff --git a/arch/arm/include/debug/nomadik.S b/arch/arm/include/debug/nomadik.S
deleted file mode 100644
index 735417922ce2..000000000000
--- a/arch/arm/include/debug/nomadik.S
+++ /dev/null
@@ -1,20 +0,0 @@
-/*
- * Debugging macro include header
- *
- *  Copyright (C) 1994-1999 Russell King
- *  Moved from linux/arch/arm/kernel/debug.S by Ben Dooks
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
-*/
-
-		.macro	addruart, rp, rv, tmp
-		mov	\rp, #0x00100000
-		add	\rp, \rp, #0x000fb000
-		add	\rv, \rp, #0xf0000000	@ virtual base
-		add	\rp, \rp, #0x10000000	@ physical base address
-		.endm
-
-#include <asm/hardware/debug-pl01x.S>
diff --git a/arch/arm/include/debug/nspire.S b/arch/arm/include/debug/nspire.S
deleted file mode 100644
index 886fd276fcbc..000000000000
--- a/arch/arm/include/debug/nspire.S
+++ /dev/null
@@ -1,28 +0,0 @@
-/*
- *	linux/arch/arm/include/debug/nspire.S
- *
- *	Copyright (C) 2013 Daniel Tang <tangrs@tangrs.id.au>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2, as
- * published by the Free Software Foundation.
- *
- */
-
-#define NSPIRE_EARLY_UART_PHYS_BASE	   0x90020000
-#define NSPIRE_EARLY_UART_VIRT_BASE	   0xfee20000
-
-.macro	addruart, rp, rv, tmp
-	ldr \rp, =(NSPIRE_EARLY_UART_PHYS_BASE)		@ physical base address
-	ldr \rv, =(NSPIRE_EARLY_UART_VIRT_BASE)		@ virtual base address
-.endm
-
-
-#ifdef CONFIG_DEBUG_NSPIRE_CX_UART
-#include <asm/hardware/debug-pl01x.S>
-#endif
-
-#ifdef CONFIG_DEBUG_NSPIRE_CLASSIC_UART
-#define UART_SHIFT 2
-#include <asm/hardware/debug-8250.S>
-#endif
diff --git a/arch/arm/include/debug/picoxcell.S b/arch/arm/include/debug/picoxcell.S
deleted file mode 100644
index bc1f07c49cd4..000000000000
--- a/arch/arm/include/debug/picoxcell.S
+++ /dev/null
@@ -1,19 +0,0 @@
-/*
- * Copyright (c) 2011 Picochip Ltd., Jamie Iles
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- */
-
-#define UART_SHIFT 2
-#define PICOXCELL_UART1_BASE		0x80230000
-#define PHYS_TO_IO(x)			(((x) & 0x00ffffff) | 0xfe000000)
-
-		.macro	addruart, rp, rv, tmp
-		ldr	\rv, =PHYS_TO_IO(PICOXCELL_UART1_BASE)
-		ldr	\rp, =PICOXCELL_UART1_BASE
-		.endm
-
-#include "8250_32.S"
diff --git a/arch/arm/include/asm/hardware/debug-pl01x.S b/arch/arm/include/debug/pl01x.S
index f9fd083eff63..37c6895b87e6 100644
--- a/arch/arm/include/asm/hardware/debug-pl01x.S
+++ b/arch/arm/include/debug/pl01x.S
@@ -1,4 +1,4 @@
-/* arch/arm/include/asm/hardware/debug-pl01x.S
+/* arch/arm/include/debug/pl01x.S
  *
  * Debugging macro include header
  *
@@ -12,6 +12,13 @@
 */
 #include <linux/amba/serial.h>
 
+#ifdef CONFIG_DEBUG_UART_PHYS
+		.macro	addruart, rp, rv, tmp
+		ldr	\rp, =CONFIG_DEBUG_UART_PHYS
+		ldr	\rv, =CONFIG_DEBUG_UART_VIRT
+		.endm
+#endif
+
 		.macro	senduart,rd,rx
 		strb	\rd, [\rx, #UART01x_DR]
 		.endm
diff --git a/arch/arm/include/debug/pxa.S b/arch/arm/include/debug/pxa.S
deleted file mode 100644
index e1e795aa3d7f..000000000000
--- a/arch/arm/include/debug/pxa.S
+++ /dev/null
@@ -1,33 +0,0 @@
-/*
- * Early serial output macro for Marvell PXA/MMP SoC
- *
- * Copyright (C) 1994-1999 Russell King
- * Moved from linux/arch/arm/kernel/debug.S by Ben Dooks
- *
- * Copyright (C) 2013 Haojian Zhuang
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
-
-#if defined(CONFIG_DEBUG_PXA_UART1)
-#define PXA_UART_REG_PHYS_BASE	0x40100000
-#define PXA_UART_REG_VIRT_BASE	0xf2100000
-#elif defined(CONFIG_DEBUG_MMP_UART2)
-#define PXA_UART_REG_PHYS_BASE	0xd4017000
-#define PXA_UART_REG_VIRT_BASE	0xfe017000
-#elif defined(CONFIG_DEBUG_MMP_UART3)
-#define PXA_UART_REG_PHYS_BASE	0xd4018000
-#define PXA_UART_REG_VIRT_BASE	0xfe018000
-#else
-#error "Select uart for DEBUG_LL"
-#endif
-
-	.macro	addruart, rp, rv, tmp
-	ldr	\rp, =PXA_UART_REG_PHYS_BASE
-	ldr	\rv, =PXA_UART_REG_VIRT_BASE
-	.endm
-
-#define UART_SHIFT	2
-#include <asm/hardware/debug-8250.S>
diff --git a/arch/arm/include/debug/rockchip.S b/arch/arm/include/debug/rockchip.S
deleted file mode 100644
index cfd883e69588..000000000000
--- a/arch/arm/include/debug/rockchip.S
+++ /dev/null
@@ -1,42 +0,0 @@
-/*
- * Early serial output macro for Rockchip SoCs
- *
- * Copyright (C) 2012 Maxime Ripard
- *
- * Maxime Ripard <maxime.ripard@free-electrons.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
-
-#if defined(CONFIG_DEBUG_RK29_UART0)
-#define ROCKCHIP_UART_DEBUG_PHYS_BASE 0x20060000
-#define ROCKCHIP_UART_DEBUG_VIRT_BASE 0xfed60000
-#elif defined(CONFIG_DEBUG_RK29_UART1)
-#define ROCKCHIP_UART_DEBUG_PHYS_BASE 0x20064000
-#define ROCKCHIP_UART_DEBUG_VIRT_BASE 0xfed64000
-#elif defined(CONFIG_DEBUG_RK29_UART2)
-#define ROCKCHIP_UART_DEBUG_PHYS_BASE 0x20068000
-#define ROCKCHIP_UART_DEBUG_VIRT_BASE 0xfed68000
-#elif defined(CONFIG_DEBUG_RK3X_UART0)
-#define ROCKCHIP_UART_DEBUG_PHYS_BASE 0x10124000
-#define ROCKCHIP_UART_DEBUG_VIRT_BASE 0xfeb24000
-#elif defined(CONFIG_DEBUG_RK3X_UART1)
-#define ROCKCHIP_UART_DEBUG_PHYS_BASE 0x10126000
-#define ROCKCHIP_UART_DEBUG_VIRT_BASE 0xfeb26000
-#elif defined(CONFIG_DEBUG_RK3X_UART2)
-#define ROCKCHIP_UART_DEBUG_PHYS_BASE 0x20064000
-#define ROCKCHIP_UART_DEBUG_VIRT_BASE 0xfed64000
-#elif defined(CONFIG_DEBUG_RK3X_UART3)
-#define ROCKCHIP_UART_DEBUG_PHYS_BASE 0x20068000
-#define ROCKCHIP_UART_DEBUG_VIRT_BASE 0xfed68000
-#endif
-
-	.macro	addruart, rp, rv, tmp
-	ldr	\rp, =ROCKCHIP_UART_DEBUG_PHYS_BASE
-	ldr	\rv, =ROCKCHIP_UART_DEBUG_VIRT_BASE
-	.endm
-
-#define UART_SHIFT	2
-#include <asm/hardware/debug-8250.S>
diff --git a/arch/arm/include/debug/socfpga.S b/arch/arm/include/debug/socfpga.S
deleted file mode 100644
index 966b2f994946..000000000000
--- a/arch/arm/include/debug/socfpga.S
+++ /dev/null
@@ -1,21 +0,0 @@
-/*
- *  Copyright (C) 1994-1999 Russell King
- *  Moved from linux/arch/arm/kernel/debug.S by Ben Dooks
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#define UART_SHIFT 2
-#define DEBUG_LL_UART_OFFSET	0x00002000
-
-		.macro	addruart, rp, rv, tmp
-		mov	\rp, #DEBUG_LL_UART_OFFSET
-		orr	\rp, \rp, #0x00c00000
-		orr	\rv, \rp, #0xfe000000	@ virtual base
-		orr	\rp, \rp, #0xff000000	@ physical base
-		.endm
-
-#include "8250_32.S"
-
diff --git a/arch/arm/include/debug/sunxi.S b/arch/arm/include/debug/sunxi.S
deleted file mode 100644
index 04eb56d5db2c..000000000000
--- a/arch/arm/include/debug/sunxi.S
+++ /dev/null
@@ -1,27 +0,0 @@
-/*
- * Early serial output macro for Allwinner A1X SoCs
- *
- * Copyright (C) 2012 Maxime Ripard
- *
- * Maxime Ripard <maxime.ripard@free-electrons.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
-
-#if defined(CONFIG_DEBUG_SUNXI_UART0)
-#define SUNXI_UART_DEBUG_PHYS_BASE 0x01c28000
-#define SUNXI_UART_DEBUG_VIRT_BASE 0xf1c28000
-#elif defined(CONFIG_DEBUG_SUNXI_UART1)
-#define SUNXI_UART_DEBUG_PHYS_BASE 0x01c28400
-#define SUNXI_UART_DEBUG_VIRT_BASE 0xf1c28400
-#endif
-
-	.macro	addruart, rp, rv, tmp
-	ldr	\rp, =SUNXI_UART_DEBUG_PHYS_BASE
-	ldr	\rv, =SUNXI_UART_DEBUG_VIRT_BASE
-	.endm
-
-#define UART_SHIFT	2
-#include <asm/hardware/debug-8250.S>
diff --git a/arch/arm/include/debug/tegra.S b/arch/arm/include/debug/tegra.S
index 883d7c22fd9d..be6a720dd183 100644
--- a/arch/arm/include/debug/tegra.S
+++ b/arch/arm/include/debug/tegra.S
@@ -221,3 +221,32 @@
 1002:
 #endif
 		.endm
+
+/*
+ * Storage for the state maintained by the macros above.
+ *
+ * In the kernel proper, this data is located in arch/arm/mach-tegra/common.c.
+ * That's because this header is included from multiple files, and we only
+ * want a single copy of the data. In particular, the UART probing code above
+ * assumes it's running using physical addresses. This is true when this file
+ * is included from head.o, but not when included from debug.o. So we need
+ * to share the probe results between the two copies, rather than having
+ * to re-run the probing again later.
+ *
+ * In the decompressor, we put the symbol/storage right here, since common.c
+ * isn't included in the decompressor build. This symbol gets put in .text
+ * even though it's really data, since .data is discarded from the
+ * decompressor. Luckily, .text is writeable in the decompressor, unless
+ * CONFIG_ZBOOT_ROM. That dependency is handled in arch/arm/Kconfig.debug.
+ */
+#if defined(ZIMAGE)
+tegra_uart_config:
+	/* Debug UART initialization required */
+	.word 1
+	/* Debug UART physical address */
+	.word 0
+	/* Debug UART virtual address */
+	.word 0
+	/* Scratch space for debug macro */
+	.word 0
+#endif
diff --git a/arch/arm/include/debug/u300.S b/arch/arm/include/debug/u300.S
deleted file mode 100644
index 6f04f08a203c..000000000000
--- a/arch/arm/include/debug/u300.S
+++ /dev/null
@@ -1,18 +0,0 @@
-/*
- * Copyright (C) 2006-2013 ST-Ericsson AB
- * License terms: GNU General Public License (GPL) version 2
- * Debugging macro include header.
- * Author: Linus Walleij <linus.walleij@stericsson.com>
- */
-#define U300_SLOW_PER_PHYS_BASE		0xc0010000
-#define U300_SLOW_PER_VIRT_BASE		0xff000000
-
-	.macro	addruart, rp, rv, tmp
-	/* If we move the address using MMU, use this. */
-	ldr	\rp,	  = U300_SLOW_PER_PHYS_BASE @ MMU off, physical address
-	ldr	\rv,	  = U300_SLOW_PER_VIRT_BASE @ MMU on, virtual address
-	orr	\rp, \rp, #0x00003000
-	orr	\rv, \rv, #0x00003000
-	.endm
-
-#include <asm/hardware/debug-pl01x.S>
diff --git a/arch/arm/include/debug/ux500.S b/arch/arm/include/debug/ux500.S
index fbd24beeb1fa..aa7f63a8b5e0 100644
--- a/arch/arm/include/debug/ux500.S
+++ b/arch/arm/include/debug/ux500.S
@@ -45,4 +45,4 @@
 	ldr	\rv, =UART_VIRT_BASE		@ yes, virtual address
 	.endm
 
-#include <asm/hardware/debug-pl01x.S>
+#include <debug/pl01x.S>
diff --git a/arch/arm/include/debug/vexpress.S b/arch/arm/include/debug/vexpress.S
index acafb229e2b6..524acd5a223e 100644
--- a/arch/arm/include/debug/vexpress.S
+++ b/arch/arm/include/debug/vexpress.S
@@ -47,51 +47,5 @@
 
 		.endm
 
-#include <asm/hardware/debug-pl01x.S>
-
-#elif defined(CONFIG_DEBUG_VEXPRESS_UART0_CA9)
-
-		.macro	addruart,rp,rv,tmp
-		mov	\rp, #DEBUG_LL_UART_OFFSET
-		orr	\rv, \rp, #DEBUG_LL_VIRT_BASE
-		orr	\rp, \rp, #DEBUG_LL_PHYS_BASE
-		.endm
-
-#include <asm/hardware/debug-pl01x.S>
-
-#elif defined(CONFIG_DEBUG_VEXPRESS_UART0_RS1)
-
-		.macro	addruart,rp,rv,tmp
-		mov	\rp, #DEBUG_LL_UART_OFFSET_RS1
-		orr	\rv, \rp, #DEBUG_LL_VIRT_BASE
-		orr	\rp, \rp, #DEBUG_LL_PHYS_BASE_RS1
-		.endm
-
-#include <asm/hardware/debug-pl01x.S>
-
-#elif defined(CONFIG_DEBUG_VEXPRESS_UART0_CRX)
-
-		.macro	addruart,rp,tmp,tmp2
-		ldr	\rp, =DEBUG_LL_UART_PHYS_CRX
-		.endm
-
-#include <asm/hardware/debug-pl01x.S>
-
-#else /* CONFIG_DEBUG_LL_UART_NONE */
-
-		.macro	addruart, rp, rv, tmp
-		/* Safe dummy values */
-		mov	\rp, #0
-		mov	\rv, #DEBUG_LL_VIRT_BASE
-		.endm
-
-		.macro	senduart,rd,rx
-		.endm
-
-		.macro	waituart,rd,rx
-		.endm
-
-		.macro	busyuart,rd,rx
-		.endm
-
+#include <debug/pl01x.S>
 #endif
diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile
index 86d10dd47dc4..5140df5f23aa 100644
--- a/arch/arm/kernel/Makefile
+++ b/arch/arm/kernel/Makefile
@@ -24,7 +24,7 @@ obj-$(CONFIG_ATAGS_PROC)	+= atags_proc.o
 obj-$(CONFIG_DEPRECATED_PARAM_STRUCT) += atags_compat.o
 
 ifeq ($(CONFIG_CPU_V7M),y)
-obj-y		+= entry-v7m.o
+obj-y		+= entry-v7m.o v7m.o
 else
 obj-y		+= entry-armv.o
 endif
diff --git a/arch/arm/kernel/atags.h b/arch/arm/kernel/atags.h
index 9edc9692332d..ec4164da6e30 100644
--- a/arch/arm/kernel/atags.h
+++ b/arch/arm/kernel/atags.h
@@ -7,9 +7,10 @@ static inline void save_atags(struct tag *tags) { }
 void convert_to_tag_list(struct tag *tags);
 
 #ifdef CONFIG_ATAGS
-struct machine_desc *setup_machine_tags(phys_addr_t __atags_pointer, unsigned int machine_nr);
+const struct machine_desc *setup_machine_tags(phys_addr_t __atags_pointer,
+	unsigned int machine_nr);
 #else
-static inline struct machine_desc *
+static inline const struct machine_desc *
 setup_machine_tags(phys_addr_t __atags_pointer, unsigned int machine_nr)
 {
 	early_print("no ATAGS support: can't continue\n");
diff --git a/arch/arm/kernel/atags_parse.c b/arch/arm/kernel/atags_parse.c
index 14512e6931d8..8c14de8180c0 100644
--- a/arch/arm/kernel/atags_parse.c
+++ b/arch/arm/kernel/atags_parse.c
@@ -178,11 +178,11 @@ static void __init squash_mem_tags(struct tag *tag)
 			tag->hdr.tag = ATAG_NONE;
 }
 
-struct machine_desc * __init setup_machine_tags(phys_addr_t __atags_pointer,
-						unsigned int machine_nr)
+const struct machine_desc * __init
+setup_machine_tags(phys_addr_t __atags_pointer, unsigned int machine_nr)
 {
 	struct tag *tags = (struct tag *)&default_tags;
-	struct machine_desc *mdesc = NULL, *p;
+	const struct machine_desc *mdesc = NULL, *p;
 	char *from = default_command_line;
 
 	default_tags.mem.start = PHYS_OFFSET;
diff --git a/arch/arm/kernel/bios32.c b/arch/arm/kernel/bios32.c
index 261fcc826169..317da88ae65b 100644
--- a/arch/arm/kernel/bios32.c
+++ b/arch/arm/kernel/bios32.c
@@ -363,6 +363,20 @@ void pcibios_fixup_bus(struct pci_bus *bus)
 }
 EXPORT_SYMBOL(pcibios_fixup_bus);
 
+void pcibios_add_bus(struct pci_bus *bus)
+{
+	struct pci_sys_data *sys = bus->sysdata;
+	if (sys->add_bus)
+		sys->add_bus(bus);
+}
+
+void pcibios_remove_bus(struct pci_bus *bus)
+{
+	struct pci_sys_data *sys = bus->sysdata;
+	if (sys->remove_bus)
+		sys->remove_bus(bus);
+}
+
 /*
  * Swizzle the device pin each time we cross a bridge.  If a platform does
  * not provide a swizzle function, we perform the standard PCI swizzling.
@@ -464,6 +478,8 @@ static void pcibios_init_hw(struct device *parent, struct hw_pci *hw,
 		sys->swizzle = hw->swizzle;
 		sys->map_irq = hw->map_irq;
 		sys->align_resource = hw->align_resource;
+		sys->add_bus = hw->add_bus;
+		sys->remove_bus = hw->remove_bus;
 		INIT_LIST_HEAD(&sys->resources);
 
 		if (hw->private_data)
@@ -525,11 +541,6 @@ void pci_common_init_dev(struct device *parent, struct hw_pci *hw)
 			 * Assign resources.
 			 */
 			pci_bus_assign_resources(bus);
-
-			/*
-			 * Enable bridges
-			 */
-			pci_enable_bridges(bus);
 		}
 
 		/*
diff --git a/arch/arm/kernel/devtree.c b/arch/arm/kernel/devtree.c
index 5859c8bc727c..f35906b3d8c9 100644
--- a/arch/arm/kernel/devtree.c
+++ b/arch/arm/kernel/devtree.c
@@ -169,6 +169,11 @@ void __init arm_dt_init_cpu_maps(void)
 	}
 }
 
+bool arch_match_cpu_phys_id(int cpu, u64 phys_id)
+{
+	return (phys_id & MPIDR_HWID_BITMASK) == cpu_logical_map(cpu);
+}
+
 /**
  * setup_machine_fdt - Machine setup when an dtb was passed to the kernel
  * @dt_phys: physical address of dt blob
@@ -176,10 +181,10 @@ void __init arm_dt_init_cpu_maps(void)
  * If a dtb was passed to the kernel in r2, then use it to choose the
  * correct machine_desc and to setup the system.
  */
-struct machine_desc * __init setup_machine_fdt(unsigned int dt_phys)
+const struct machine_desc * __init setup_machine_fdt(unsigned int dt_phys)
 {
 	struct boot_param_header *devtree;
-	struct machine_desc *mdesc, *mdesc_best = NULL;
+	const struct machine_desc *mdesc, *mdesc_best = NULL;
 	unsigned int score, mdesc_score = ~1;
 	unsigned long dt_root;
 	const char *model;
@@ -188,7 +193,7 @@ struct machine_desc * __init setup_machine_fdt(unsigned int dt_phys)
 	DT_MACHINE_START(GENERIC_DT, "Generic DT based system")
 	MACHINE_END
 
-	mdesc_best = (struct machine_desc *)&__mach_desc_GENERIC_DT;
+	mdesc_best = &__mach_desc_GENERIC_DT;
 #endif
 
 	if (!dt_phys)
diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index 94104bf69719..bc6bd9683ba4 100644
--- a/arch/arm/kernel/entry-common.S
+++ b/arch/arm/kernel/entry-common.S
@@ -442,10 +442,10 @@ local_restart:
 	ldrcc	pc, [tbl, scno, lsl #2]		@ call sys_* routine
 
 	add	r1, sp, #S_OFF
-2:	mov	why, #0				@ no longer a real syscall
-	cmp	scno, #(__ARM_NR_BASE - __NR_SYSCALL_BASE)
+2:	cmp	scno, #(__ARM_NR_BASE - __NR_SYSCALL_BASE)
 	eor	r0, scno, #__NR_SYSCALL_BASE	@ put OS number back
-	bcs	arm_syscall	
+	bcs	arm_syscall
+	mov	why, #0				@ no longer a real syscall
 	b	sys_ni_syscall			@ not private func
 
 #if defined(CONFIG_OABI_COMPAT) || !defined(CONFIG_AEABI)
diff --git a/arch/arm/kernel/entry-header.S b/arch/arm/kernel/entry-header.S
index de23a9beed13..39f89fbd5111 100644
--- a/arch/arm/kernel/entry-header.S
+++ b/arch/arm/kernel/entry-header.S
@@ -329,10 +329,10 @@
 #ifdef CONFIG_CONTEXT_TRACKING
 	.if	\save
 	stmdb   sp!, {r0-r3, ip, lr}
-	bl	user_exit
+	bl	context_tracking_user_exit
 	ldmia	sp!, {r0-r3, ip, lr}
 	.else
-	bl	user_exit
+	bl	context_tracking_user_exit
 	.endif
 #endif
 	.endm
@@ -341,10 +341,10 @@
 #ifdef CONFIG_CONTEXT_TRACKING
 	.if	\save
 	stmdb   sp!, {r0-r3, ip, lr}
-	bl	user_enter
+	bl	context_tracking_user_enter
 	ldmia	sp!, {r0-r3, ip, lr}
 	.else
-	bl	user_enter
+	bl	context_tracking_user_enter
 	.endif
 #endif
 	.endm
diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S
index 2c7cc1e03473..476de57dcef2 100644
--- a/arch/arm/kernel/head.S
+++ b/arch/arm/kernel/head.S
@@ -487,7 +487,26 @@ __fixup_smp:
 	mrc	p15, 0, r0, c0, c0, 5	@ read MPIDR
 	and	r0, r0, #0xc0000000	@ multiprocessing extensions and
 	teq	r0, #0x80000000		@ not part of a uniprocessor system?
-	moveq	pc, lr			@ yes, assume SMP
+	bne    __fixup_smp_on_up	@ no, assume UP
+
+	@ Core indicates it is SMP. Check for Aegis SOC where a single
+	@ Cortex-A9 CPU is present but SMP operations fault.
+	mov	r4, #0x41000000
+	orr	r4, r4, #0x0000c000
+	orr	r4, r4, #0x00000090
+	teq	r3, r4			@ Check for ARM Cortex-A9
+	movne	pc, lr			@ Not ARM Cortex-A9,
+
+	@ If a future SoC *does* use 0x0 as the PERIPH_BASE, then the
+	@ below address check will need to be #ifdef'd or equivalent
+	@ for the Aegis platform.
+	mrc	p15, 4, r0, c15, c0	@ get SCU base address
+	teq	r0, #0x0		@ '0' on actual UP A9 hardware
+	beq	__fixup_smp_on_up	@ So its an A9 UP
+	ldr	r0, [r0, #4]		@ read SCU Config
+	and	r0, r0, #0x3		@ number of CPUs
+	teq	r0, #0x0		@ is 1?
+	movne	pc, lr
 
 __fixup_smp_on_up:
 	adr	r0, 1f
diff --git a/arch/arm/kernel/module.c b/arch/arm/kernel/module.c
index 85c3fb6c93c2..084dc8896986 100644
--- a/arch/arm/kernel/module.c
+++ b/arch/arm/kernel/module.c
@@ -292,12 +292,20 @@ int module_finalize(const Elf32_Ehdr *hdr, const Elf_Shdr *sechdrs,
 			maps[ARM_SEC_CORE].unw_sec = s;
 		else if (strcmp(".ARM.exidx.exit.text", secname) == 0)
 			maps[ARM_SEC_EXIT].unw_sec = s;
+		else if (strcmp(".ARM.exidx.text.unlikely", secname) == 0)
+			maps[ARM_SEC_UNLIKELY].unw_sec = s;
+		else if (strcmp(".ARM.exidx.text.hot", secname) == 0)
+			maps[ARM_SEC_HOT].unw_sec = s;
 		else if (strcmp(".init.text", secname) == 0)
 			maps[ARM_SEC_INIT].txt_sec = s;
 		else if (strcmp(".text", secname) == 0)
 			maps[ARM_SEC_CORE].txt_sec = s;
 		else if (strcmp(".exit.text", secname) == 0)
 			maps[ARM_SEC_EXIT].txt_sec = s;
+		else if (strcmp(".text.unlikely", secname) == 0)
+			maps[ARM_SEC_UNLIKELY].txt_sec = s;
+		else if (strcmp(".text.hot", secname) == 0)
+			maps[ARM_SEC_HOT].txt_sec = s;
 	}
 
 	for (i = 0; i < ARM_SEC_MAX; i++)
diff --git a/arch/arm/kernel/perf_event_cpu.c b/arch/arm/kernel/perf_event_cpu.c
index aebe0e99c153..8d6147b2001f 100644
--- a/arch/arm/kernel/perf_event_cpu.c
+++ b/arch/arm/kernel/perf_event_cpu.c
@@ -118,7 +118,8 @@ static int cpu_pmu_request_irq(struct arm_pmu *cpu_pmu, irq_handler_t handler)
 			continue;
 		}
 
-		err = request_irq(irq, handler, IRQF_NOBALANCING, "arm-pmu",
+		err = request_irq(irq, handler,
+				  IRQF_NOBALANCING | IRQF_NO_THREAD, "arm-pmu",
 				  cpu_pmu);
 		if (err) {
 			pr_err("unable to request IRQ%d for ARM PMU counters\n",
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index afc2489ee13b..0e1e2b3afa45 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -72,10 +72,10 @@ static int __init fpe_setup(char *line)
 __setup("fpe=", fpe_setup);
 #endif
 
-extern void paging_init(struct machine_desc *desc);
+extern void paging_init(const struct machine_desc *desc);
 extern void sanity_check_meminfo(void);
 extern enum reboot_mode reboot_mode;
-extern void setup_dma_zone(struct machine_desc *desc);
+extern void setup_dma_zone(const struct machine_desc *desc);
 
 unsigned int processor_id;
 EXPORT_SYMBOL(processor_id);
@@ -139,7 +139,7 @@ EXPORT_SYMBOL(elf_platform);
 static const char *cpu_name;
 static const char *machine_name;
 static char __initdata cmd_line[COMMAND_LINE_SIZE];
-struct machine_desc *machine_desc __initdata;
+const struct machine_desc *machine_desc __initdata;
 
 static union { char c[4]; unsigned long l; } endian_test __initdata = { { 'l', '?', '?', 'b' } };
 #define ENDIANNESS ((char)endian_test.l)
@@ -607,7 +607,7 @@ static void __init setup_processor(void)
 
 void __init dump_machine_table(void)
 {
-	struct machine_desc *p;
+	const struct machine_desc *p;
 
 	early_print("Available machine support:\n\nID (hex)\tNAME\n");
 	for_each_machine_desc(p)
@@ -694,7 +694,7 @@ static int __init early_mem(char *p)
 }
 early_param("mem", early_mem);
 
-static void __init request_standard_resources(struct machine_desc *mdesc)
+static void __init request_standard_resources(const struct machine_desc *mdesc)
 {
 	struct memblock_region *region;
 	struct resource *res;
@@ -852,7 +852,7 @@ void __init hyp_mode_check(void)
 
 void __init setup_arch(char **cmdline_p)
 {
-	struct machine_desc *mdesc;
+	const struct machine_desc *mdesc;
 
 	setup_processor();
 	mdesc = setup_machine_fdt(__atags_pointer);
@@ -994,15 +994,6 @@ static int c_show(struct seq_file *m, void *v)
 		seq_printf(m, "model name\t: %s rev %d (%s)\n",
 			   cpu_name, cpuid & 15, elf_platform);
 
-#if defined(CONFIG_SMP)
-		seq_printf(m, "BogoMIPS\t: %lu.%02lu\n",
-			   per_cpu(cpu_data, i).loops_per_jiffy / (500000UL/HZ),
-			   (per_cpu(cpu_data, i).loops_per_jiffy / (5000UL/HZ)) % 100);
-#else
-		seq_printf(m, "BogoMIPS\t: %lu.%02lu\n",
-			   loops_per_jiffy / (500000/HZ),
-			   (loops_per_jiffy / (5000/HZ)) % 100);
-#endif
 		/* dump out the processor features */
 		seq_puts(m, "Features\t: ");
 
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index 2dc19349eb19..72024ea8a3a6 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -41,7 +41,6 @@
 #include <asm/sections.h>
 #include <asm/tlbflush.h>
 #include <asm/ptrace.h>
-#include <asm/localtimer.h>
 #include <asm/smp_plat.h>
 #include <asm/virt.h>
 #include <asm/mach/arch.h>
@@ -156,8 +155,6 @@ int platform_can_cpu_hotplug(void)
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
-static void percpu_timer_stop(void);
-
 static int platform_cpu_kill(unsigned int cpu)
 {
 	if (smp_ops.cpu_kill)
@@ -201,11 +198,6 @@ int __cpu_disable(void)
 	migrate_irqs();
 
 	/*
-	 * Stop the local timer for this CPU.
-	 */
-	percpu_timer_stop();
-
-	/*
 	 * Flush user cache and TLB mappings, and then remove this CPU
 	 * from the vm mask set of all processes.
 	 *
@@ -326,8 +318,6 @@ static void smp_store_cpu_info(unsigned int cpuid)
 	store_cpu_topology(cpuid);
 }
 
-static void percpu_timer_setup(void);
-
 /*
  * This is the secondary CPU boot entry.  We're using this CPUs
  * idle thread stack, but a set of temporary page tables.
@@ -382,11 +372,6 @@ asmlinkage void secondary_start_kernel(void)
 	set_cpu_online(cpu, true);
 	complete(&cpu_running);
 
-	/*
-	 * Setup the percpu timer for this CPU.
-	 */
-	percpu_timer_setup();
-
 	local_irq_enable();
 	local_fiq_enable();
 
@@ -398,17 +383,8 @@ asmlinkage void secondary_start_kernel(void)
 
 void __init smp_cpus_done(unsigned int max_cpus)
 {
-	int cpu;
-	unsigned long bogosum = 0;
-
-	for_each_online_cpu(cpu)
-		bogosum += per_cpu(cpu_data, cpu).loops_per_jiffy;
-
-	printk(KERN_INFO "SMP: Total of %d processors activated "
-	       "(%lu.%02lu BogoMIPS).\n",
-	       num_online_cpus(),
-	       bogosum / (500000/HZ),
-	       (bogosum / (5000/HZ)) % 100);
+	printk(KERN_INFO "SMP: Total of %d processors activated.\n",
+	       num_online_cpus());
 
 	hyp_mode_check();
 }
@@ -433,12 +409,6 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 		max_cpus = ncores;
 	if (ncores > 1 && max_cpus) {
 		/*
-		 * Enable the local timer or broadcast device for the
-		 * boot CPU, but only if we have more than one CPU.
-		 */
-		percpu_timer_setup();
-
-		/*
 		 * Initialise the present map, which describes the set of CPUs
 		 * actually populated at the present time. A platform should
 		 * re-initialize the map in the platforms smp_prepare_cpus()
@@ -514,11 +484,6 @@ u64 smp_irq_stat_cpu(unsigned int cpu)
 	return sum;
 }
 
-/*
- * Timer (local or broadcast) support
- */
-static DEFINE_PER_CPU(struct clock_event_device, percpu_clockevent);
-
 #ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
 void tick_broadcast(const struct cpumask *mask)
 {
@@ -526,67 +491,6 @@ void tick_broadcast(const struct cpumask *mask)
 }
 #endif
 
-static void broadcast_timer_set_mode(enum clock_event_mode mode,
-	struct clock_event_device *evt)
-{
-}
-
-static void broadcast_timer_setup(struct clock_event_device *evt)
-{
-	evt->name	= "dummy_timer";
-	evt->features	= CLOCK_EVT_FEAT_ONESHOT |
-			  CLOCK_EVT_FEAT_PERIODIC |
-			  CLOCK_EVT_FEAT_DUMMY;
-	evt->rating	= 100;
-	evt->mult	= 1;
-	evt->set_mode	= broadcast_timer_set_mode;
-
-	clockevents_register_device(evt);
-}
-
-static struct local_timer_ops *lt_ops;
-
-#ifdef CONFIG_LOCAL_TIMERS
-int local_timer_register(struct local_timer_ops *ops)
-{
-	if (!is_smp() || !setup_max_cpus)
-		return -ENXIO;
-
-	if (lt_ops)
-		return -EBUSY;
-
-	lt_ops = ops;
-	return 0;
-}
-#endif
-
-static void percpu_timer_setup(void)
-{
-	unsigned int cpu = smp_processor_id();
-	struct clock_event_device *evt = &per_cpu(percpu_clockevent, cpu);
-
-	evt->cpumask = cpumask_of(cpu);
-
-	if (!lt_ops || lt_ops->setup(evt))
-		broadcast_timer_setup(evt);
-}
-
-#ifdef CONFIG_HOTPLUG_CPU
-/*
- * The generic clock events code purposely does not stop the local timer
- * on CPU_DEAD/CPU_DEAD_FROZEN hotplug events, so we have to do it
- * manually here.
- */
-static void percpu_timer_stop(void)
-{
-	unsigned int cpu = smp_processor_id();
-	struct clock_event_device *evt = &per_cpu(percpu_clockevent, cpu);
-
-	if (lt_ops)
-		lt_ops->stop(evt);
-}
-#endif
-
 static DEFINE_RAW_SPINLOCK(stop_lock);
 
 /*
diff --git a/arch/arm/kernel/smp_tlb.c b/arch/arm/kernel/smp_tlb.c
index c2edfff573c2..83ccca303df8 100644
--- a/arch/arm/kernel/smp_tlb.c
+++ b/arch/arm/kernel/smp_tlb.c
@@ -104,7 +104,7 @@ void flush_tlb_all(void)
 	if (tlb_ops_need_broadcast())
 		on_each_cpu(ipi_flush_tlb_all, NULL, 1);
 	else
-		local_flush_tlb_all();
+		__flush_tlb_all();
 	broadcast_tlb_a15_erratum();
 }
 
@@ -113,7 +113,7 @@ void flush_tlb_mm(struct mm_struct *mm)
 	if (tlb_ops_need_broadcast())
 		on_each_cpu_mask(mm_cpumask(mm), ipi_flush_tlb_mm, mm, 1);
 	else
-		local_flush_tlb_mm(mm);
+		__flush_tlb_mm(mm);
 	broadcast_tlb_mm_a15_erratum(mm);
 }
 
@@ -126,7 +126,7 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr)
 		on_each_cpu_mask(mm_cpumask(vma->vm_mm), ipi_flush_tlb_page,
 					&ta, 1);
 	} else
-		local_flush_tlb_page(vma, uaddr);
+		__flush_tlb_page(vma, uaddr);
 	broadcast_tlb_mm_a15_erratum(vma->vm_mm);
 }
 
@@ -137,7 +137,7 @@ void flush_tlb_kernel_page(unsigned long kaddr)
 		ta.ta_start = kaddr;
 		on_each_cpu(ipi_flush_tlb_kernel_page, &ta, 1);
 	} else
-		local_flush_tlb_kernel_page(kaddr);
+		__flush_tlb_kernel_page(kaddr);
 	broadcast_tlb_a15_erratum();
 }
 
@@ -173,5 +173,5 @@ void flush_bp_all(void)
 	if (tlb_ops_need_broadcast())
 		on_each_cpu(ipi_flush_bp_all, NULL, 1);
 	else
-		local_flush_bp_all();
+		__flush_bp_all();
 }
diff --git a/arch/arm/kernel/smp_twd.c b/arch/arm/kernel/smp_twd.c
index 25956204ef23..2985c9f0905d 100644
--- a/arch/arm/kernel/smp_twd.c
+++ b/arch/arm/kernel/smp_twd.c
@@ -11,6 +11,7 @@
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/clk.h>
+#include <linux/cpu.h>
 #include <linux/delay.h>
 #include <linux/device.h>
 #include <linux/err.h>
@@ -24,7 +25,6 @@
 
 #include <asm/smp_plat.h>
 #include <asm/smp_twd.h>
-#include <asm/localtimer.h>
 
 /* set up by the platform code */
 static void __iomem *twd_base;
@@ -33,7 +33,7 @@ static struct clk *twd_clk;
 static unsigned long twd_timer_rate;
 static DEFINE_PER_CPU(bool, percpu_setup_called);
 
-static struct clock_event_device __percpu **twd_evt;
+static struct clock_event_device __percpu *twd_evt;
 static int twd_ppi;
 
 static void twd_set_mode(enum clock_event_mode mode,
@@ -90,8 +90,10 @@ static int twd_timer_ack(void)
 	return 0;
 }
 
-static void twd_timer_stop(struct clock_event_device *clk)
+static void twd_timer_stop(void)
 {
+	struct clock_event_device *clk = __this_cpu_ptr(twd_evt);
+
 	twd_set_mode(CLOCK_EVT_MODE_UNUSED, clk);
 	disable_percpu_irq(clk->irq);
 }
@@ -106,7 +108,7 @@ static void twd_update_frequency(void *new_rate)
 {
 	twd_timer_rate = *((unsigned long *) new_rate);
 
-	clockevents_update_freq(*__this_cpu_ptr(twd_evt), twd_timer_rate);
+	clockevents_update_freq(__this_cpu_ptr(twd_evt), twd_timer_rate);
 }
 
 static int twd_rate_change(struct notifier_block *nb,
@@ -132,7 +134,7 @@ static struct notifier_block twd_clk_nb = {
 
 static int twd_clk_init(void)
 {
-	if (twd_evt && *__this_cpu_ptr(twd_evt) && !IS_ERR(twd_clk))
+	if (twd_evt && __this_cpu_ptr(twd_evt) && !IS_ERR(twd_clk))
 		return clk_notifier_register(twd_clk, &twd_clk_nb);
 
 	return 0;
@@ -151,7 +153,7 @@ static void twd_update_frequency(void *data)
 {
 	twd_timer_rate = clk_get_rate(twd_clk);
 
-	clockevents_update_freq(*__this_cpu_ptr(twd_evt), twd_timer_rate);
+	clockevents_update_freq(__this_cpu_ptr(twd_evt), twd_timer_rate);
 }
 
 static int twd_cpufreq_transition(struct notifier_block *nb,
@@ -177,7 +179,7 @@ static struct notifier_block twd_cpufreq_nb = {
 
 static int twd_cpufreq_init(void)
 {
-	if (twd_evt && *__this_cpu_ptr(twd_evt) && !IS_ERR(twd_clk))
+	if (twd_evt && __this_cpu_ptr(twd_evt) && !IS_ERR(twd_clk))
 		return cpufreq_register_notifier(&twd_cpufreq_nb,
 			CPUFREQ_TRANSITION_NOTIFIER);
 
@@ -228,7 +230,7 @@ static void twd_calibrate_rate(void)
 
 static irqreturn_t twd_handler(int irq, void *dev_id)
 {
-	struct clock_event_device *evt = *(struct clock_event_device **)dev_id;
+	struct clock_event_device *evt = dev_id;
 
 	if (twd_timer_ack()) {
 		evt->event_handler(evt);
@@ -265,9 +267,9 @@ static void twd_get_clock(struct device_node *np)
 /*
  * Setup the local clock events for a CPU.
  */
-static int twd_timer_setup(struct clock_event_device *clk)
+static void twd_timer_setup(void)
 {
-	struct clock_event_device **this_cpu_clk;
+	struct clock_event_device *clk = __this_cpu_ptr(twd_evt);
 	int cpu = smp_processor_id();
 
 	/*
@@ -276,9 +278,9 @@ static int twd_timer_setup(struct clock_event_device *clk)
 	 */
 	if (per_cpu(percpu_setup_called, cpu)) {
 		__raw_writel(0, twd_base + TWD_TIMER_CONTROL);
-		clockevents_register_device(*__this_cpu_ptr(twd_evt));
+		clockevents_register_device(clk);
 		enable_percpu_irq(clk->irq, 0);
-		return 0;
+		return;
 	}
 	per_cpu(percpu_setup_called, cpu) = true;
 
@@ -297,27 +299,37 @@ static int twd_timer_setup(struct clock_event_device *clk)
 	clk->set_mode = twd_set_mode;
 	clk->set_next_event = twd_set_next_event;
 	clk->irq = twd_ppi;
-
-	this_cpu_clk = __this_cpu_ptr(twd_evt);
-	*this_cpu_clk = clk;
+	clk->cpumask = cpumask_of(cpu);
 
 	clockevents_config_and_register(clk, twd_timer_rate,
 					0xf, 0xffffffff);
 	enable_percpu_irq(clk->irq, 0);
+}
 
-	return 0;
+static int twd_timer_cpu_notify(struct notifier_block *self,
+				unsigned long action, void *hcpu)
+{
+	switch (action & ~CPU_TASKS_FROZEN) {
+	case CPU_STARTING:
+		twd_timer_setup();
+		break;
+	case CPU_DYING:
+		twd_timer_stop();
+		break;
+	}
+
+	return NOTIFY_OK;
 }
 
-static struct local_timer_ops twd_lt_ops = {
-	.setup	= twd_timer_setup,
-	.stop	= twd_timer_stop,
+static struct notifier_block twd_timer_cpu_nb = {
+	.notifier_call = twd_timer_cpu_notify,
 };
 
 static int __init twd_local_timer_common_register(struct device_node *np)
 {
 	int err;
 
-	twd_evt = alloc_percpu(struct clock_event_device *);
+	twd_evt = alloc_percpu(struct clock_event_device);
 	if (!twd_evt) {
 		err = -ENOMEM;
 		goto out_free;
@@ -329,12 +341,22 @@ static int __init twd_local_timer_common_register(struct device_node *np)
 		goto out_free;
 	}
 
-	err = local_timer_register(&twd_lt_ops);
+	err = register_cpu_notifier(&twd_timer_cpu_nb);
 	if (err)
 		goto out_irq;
 
 	twd_get_clock(np);
 
+	/*
+	 * Immediately configure the timer on the boot CPU, unless we need
+	 * jiffies to be incrementing to calibrate the rate in which case
+	 * setup the timer in late_time_init.
+	 */
+	if (twd_timer_rate)
+		twd_timer_setup();
+	else
+		late_time_init = twd_timer_setup;
+
 	return 0;
 
 out_irq:
diff --git a/arch/arm/kernel/topology.c b/arch/arm/kernel/topology.c
index c5a59546a256..85a87370f144 100644
--- a/arch/arm/kernel/topology.c
+++ b/arch/arm/kernel/topology.c
@@ -74,12 +74,8 @@ struct cpu_efficiency table_efficiency[] = {
 	{NULL, },
 };
 
-struct cpu_capacity {
-	unsigned long hwid;
-	unsigned long capacity;
-};
-
-struct cpu_capacity *cpu_capacity;
+unsigned long *__cpu_capacity;
+#define cpu_capacity(cpu)	__cpu_capacity[cpu]
 
 unsigned long middle_capacity = 1;
 
@@ -100,15 +96,19 @@ static void __init parse_dt_topology(void)
 	unsigned long capacity = 0;
 	int alloc_size, cpu = 0;
 
-	alloc_size = nr_cpu_ids * sizeof(struct cpu_capacity);
-	cpu_capacity = kzalloc(alloc_size, GFP_NOWAIT);
+	alloc_size = nr_cpu_ids * sizeof(*__cpu_capacity);
+	__cpu_capacity = kzalloc(alloc_size, GFP_NOWAIT);
 
-	while ((cn = of_find_node_by_type(cn, "cpu"))) {
-		const u32 *rate, *reg;
+	for_each_possible_cpu(cpu) {
+		const u32 *rate;
 		int len;
 
-		if (cpu >= num_possible_cpus())
-			break;
+		/* too early to use cpu->of_node */
+		cn = of_get_cpu_node(cpu, NULL);
+		if (!cn) {
+			pr_err("missing device node for CPU %d\n", cpu);
+			continue;
+		}
 
 		for (cpu_eff = table_efficiency; cpu_eff->compatible; cpu_eff++)
 			if (of_device_is_compatible(cn, cpu_eff->compatible))
@@ -124,12 +124,6 @@ static void __init parse_dt_topology(void)
 			continue;
 		}
 
-		reg = of_get_property(cn, "reg", &len);
-		if (!reg || len != 4) {
-			pr_err("%s missing reg property\n", cn->full_name);
-			continue;
-		}
-
 		capacity = ((be32_to_cpup(rate)) >> 20) * cpu_eff->efficiency;
 
 		/* Save min capacity of the system */
@@ -140,13 +134,9 @@ static void __init parse_dt_topology(void)
 		if (capacity > max_capacity)
 			max_capacity = capacity;
 
-		cpu_capacity[cpu].capacity = capacity;
-		cpu_capacity[cpu++].hwid = be32_to_cpup(reg);
+		cpu_capacity(cpu) = capacity;
 	}
 
-	if (cpu < num_possible_cpus())
-		cpu_capacity[cpu].hwid = (unsigned long)(-1);
-
 	/* If min and max capacities are equals, we bypass the update of the
 	 * cpu_scale because all CPUs have the same capacity. Otherwise, we
 	 * compute a middle_capacity factor that will ensure that the capacity
@@ -154,9 +144,7 @@ static void __init parse_dt_topology(void)
 	 * SCHED_POWER_SCALE, which is the default value, but with the
 	 * constraint explained near table_efficiency[].
 	 */
-	if (min_capacity == max_capacity)
-		cpu_capacity[0].hwid = (unsigned long)(-1);
-	else if (4*max_capacity < (3*(max_capacity + min_capacity)))
+	if (4*max_capacity < (3*(max_capacity + min_capacity)))
 		middle_capacity = (min_capacity + max_capacity)
 				>> (SCHED_POWER_SHIFT+1);
 	else
@@ -170,23 +158,12 @@ static void __init parse_dt_topology(void)
  * boot. The update of all CPUs is in O(n^2) for heteregeneous system but the
  * function returns directly for SMP system.
  */
-void update_cpu_power(unsigned int cpu, unsigned long hwid)
+void update_cpu_power(unsigned int cpu)
 {
-	unsigned int idx = 0;
-
-	/* look for the cpu's hwid in the cpu capacity table */
-	for (idx = 0; idx < num_possible_cpus(); idx++) {
-		if (cpu_capacity[idx].hwid == hwid)
-			break;
-
-		if (cpu_capacity[idx].hwid == -1)
-			return;
-	}
-
-	if (idx == num_possible_cpus())
+	if (!cpu_capacity(cpu))
 		return;
 
-	set_power_scale(cpu, cpu_capacity[idx].capacity / middle_capacity);
+	set_power_scale(cpu, cpu_capacity(cpu) / middle_capacity);
 
 	printk(KERN_INFO "CPU%u: update cpu_power %lu\n",
 		cpu, arch_scale_freq_power(NULL, cpu));
@@ -194,7 +171,7 @@ void update_cpu_power(unsigned int cpu, unsigned long hwid)
 
 #else
 static inline void parse_dt_topology(void) {}
-static inline void update_cpu_power(unsigned int cpuid, unsigned int mpidr) {}
+static inline void update_cpu_power(unsigned int cpuid) {}
 #endif
 
  /*
@@ -281,7 +258,7 @@ void store_cpu_topology(unsigned int cpuid)
 
 	update_siblings_masks(cpuid);
 
-	update_cpu_power(cpuid, mpidr & MPIDR_HWID_BITMASK);
+	update_cpu_power(cpuid);
 
 	printk(KERN_INFO "CPU%u: thread %d, cpu %d, socket %d, mpidr %x\n",
 		cpuid, cpu_topology[cpuid].thread_id,
diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c
index ab517fcce21b..8fcda140358d 100644
--- a/arch/arm/kernel/traps.c
+++ b/arch/arm/kernel/traps.c
@@ -497,28 +497,64 @@ static int bad_syscall(int n, struct pt_regs *regs)
 	return regs->ARM_r0;
 }
 
+static long do_cache_op_restart(struct restart_block *);
+
 static inline int
-do_cache_op(unsigned long start, unsigned long end, int flags)
+__do_cache_op(unsigned long start, unsigned long end)
 {
-	struct mm_struct *mm = current->active_mm;
-	struct vm_area_struct *vma;
+	int ret;
+	unsigned long chunk = PAGE_SIZE;
+
+	do {
+		if (signal_pending(current)) {
+			struct thread_info *ti = current_thread_info();
+
+			ti->restart_block = (struct restart_block) {
+				.fn	= do_cache_op_restart,
+			};
+
+			ti->arm_restart_block = (struct arm_restart_block) {
+				{
+					.cache = {
+						.start	= start,
+						.end	= end,
+					},
+				},
+			};
+
+			return -ERESTART_RESTARTBLOCK;
+		}
+
+		ret = flush_cache_user_range(start, start + chunk);
+		if (ret)
+			return ret;
 
+		cond_resched();
+		start += chunk;
+	} while (start < end);
+
+	return 0;
+}
+
+static long do_cache_op_restart(struct restart_block *unused)
+{
+	struct arm_restart_block *restart_block;
+
+	restart_block = &current_thread_info()->arm_restart_block;
+	return __do_cache_op(restart_block->cache.start,
+			     restart_block->cache.end);
+}
+
+static inline int
+do_cache_op(unsigned long start, unsigned long end, int flags)
+{
 	if (end < start || flags)
 		return -EINVAL;
 
-	down_read(&mm->mmap_sem);
-	vma = find_vma(mm, start);
-	if (vma && vma->vm_start < end) {
-		if (start < vma->vm_start)
-			start = vma->vm_start;
-		if (end > vma->vm_end)
-			end = vma->vm_end;
+	if (!access_ok(VERIFY_READ, start, end - start))
+		return -EFAULT;
 
-		up_read(&mm->mmap_sem);
-		return flush_cache_user_range(start, end);
-	}
-	up_read(&mm->mmap_sem);
-	return -EINVAL;
+	return __do_cache_op(start, end);
 }
 
 /*
diff --git a/arch/arm/kernel/v7m.c b/arch/arm/kernel/v7m.c
new file mode 100644
index 000000000000..4d2cba94f5cc
--- /dev/null
+++ b/arch/arm/kernel/v7m.c
@@ -0,0 +1,19 @@
+/*
+ * Copyright (C) 2013 Uwe Kleine-Koenig for Pengutronix
+ *
+ * This program is free software; you can redistribute it and/or modify it under
+ * the terms of the GNU General Public License version 2 as published by the
+ * Free Software Foundation.
+ */
+#include <linux/io.h>
+#include <linux/reboot.h>
+#include <asm/barrier.h>
+#include <asm/v7m.h>
+
+void armv7m_restart(enum reboot_mode mode, const char *cmd)
+{
+	dsb();
+	__raw_writel(V7M_SCB_AIRCR_VECTKEY | V7M_SCB_AIRCR_SYSRESETREQ,
+			BASEADDR_V7M_SCB + V7M_SCB_AIRCR);
+	dsb();
+}
diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index 741f66a2edbd..9c697db2787e 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -219,6 +219,10 @@ long kvm_arch_dev_ioctl(struct file *filp,
 	return -EINVAL;
 }
 
+void kvm_arch_memslots_updated(struct kvm *kvm)
+{
+}
+
 int kvm_arch_prepare_memory_region(struct kvm *kvm,
 				   struct kvm_memory_slot *memslot,
 				   struct kvm_userspace_memory_region *mem,
diff --git a/arch/arm/kvm/init.S b/arch/arm/kvm/init.S
index f048338135f7..1b9844d369cc 100644
--- a/arch/arm/kvm/init.S
+++ b/arch/arm/kvm/init.S
@@ -142,7 +142,7 @@ target:	@ We're now in the trampoline code, switch page tables
 
 	@ Invalidate the old TLBs
 	mcr	p15, 4, r0, c8, c7, 0	@ TLBIALLH
-	dsb
+	dsb	ish
 
 	eret
 
diff --git a/arch/arm/kvm/interrupts.S b/arch/arm/kvm/interrupts.S
index 16cd4ba5d7fd..ddc15539bad2 100644
--- a/arch/arm/kvm/interrupts.S
+++ b/arch/arm/kvm/interrupts.S
@@ -55,7 +55,7 @@ ENTRY(__kvm_tlb_flush_vmid_ipa)
 	mcrr	p15, 6, r2, r3, c2	@ Write VTTBR
 	isb
 	mcr     p15, 0, r0, c8, c3, 0	@ TLBIALLIS (rt ignored)
-	dsb
+	dsb	ish
 	isb
 	mov	r2, #0
 	mov	r3, #0
@@ -79,7 +79,7 @@ ENTRY(__kvm_flush_vm_context)
 	mcr     p15, 4, r0, c8, c3, 4
 	/* Invalidate instruction caches Inner Shareable (ICIALLUIS) */
 	mcr     p15, 0, r0, c7, c1, 0
-	dsb
+	dsb	ish
 	isb				@ Not necessary if followed by eret
 
 	bx	lr
@@ -492,10 +492,10 @@ __kvm_hyp_code_end:
 	.section ".rodata"
 
 und_die_str:
-	.ascii	"unexpected undefined exception in Hyp mode at: %#08x"
+	.ascii	"unexpected undefined exception in Hyp mode at: %#08x\n"
 pabt_die_str:
-	.ascii	"unexpected prefetch abort in Hyp mode at: %#08x"
+	.ascii	"unexpected prefetch abort in Hyp mode at: %#08x\n"
 dabt_die_str:
-	.ascii	"unexpected data abort in Hyp mode at: %#08x"
+	.ascii	"unexpected data abort in Hyp mode at: %#08x\n"
 svc_die_str:
-	.ascii	"unexpected HVC/SVC trap in Hyp mode at: %#08x"
+	.ascii	"unexpected HVC/SVC trap in Hyp mode at: %#08x\n"
diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c
index 0988d9e04dd4..b0de86b56c13 100644
--- a/arch/arm/kvm/mmu.c
+++ b/arch/arm/kvm/mmu.c
@@ -489,7 +489,6 @@ int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa,
 
 	for (addr = guest_ipa; addr < end; addr += PAGE_SIZE) {
 		pte_t pte = pfn_pte(pfn, PAGE_S2_DEVICE);
-		kvm_set_s2pte_writable(&pte);
 
 		ret = mmu_topup_memory_cache(&cache, 2, 2);
 		if (ret)
diff --git a/arch/arm/kvm/reset.c b/arch/arm/kvm/reset.c
index b7840e7aa452..c02ba4af599f 100644
--- a/arch/arm/kvm/reset.c
+++ b/arch/arm/kvm/reset.c
@@ -40,7 +40,7 @@ static struct kvm_regs a15_regs_reset = {
 };
 
 static const struct kvm_irq_level a15_vtimer_irq = {
-	.irq = 27,
+	{ .irq = 27 },
 	.level = 1,
 };
 
@@ -58,14 +58,14 @@ static const struct kvm_irq_level a15_vtimer_irq = {
  */
 int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
 {
-	struct kvm_regs *cpu_reset;
+	struct kvm_regs *reset_regs;
 	const struct kvm_irq_level *cpu_vtimer_irq;
 
 	switch (vcpu->arch.target) {
 	case KVM_ARM_TARGET_CORTEX_A15:
 		if (vcpu->vcpu_id > a15_max_cpu_idx)
 			return -EINVAL;
-		cpu_reset = &a15_regs_reset;
+		reset_regs = &a15_regs_reset;
 		vcpu->arch.midr = read_cpuid_id();
 		cpu_vtimer_irq = &a15_vtimer_irq;
 		break;
@@ -74,7 +74,7 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
 	}
 
 	/* Reset core registers */
-	memcpy(&vcpu->arch.regs, cpu_reset, sizeof(vcpu->arch.regs));
+	memcpy(&vcpu->arch.regs, reset_regs, sizeof(vcpu->arch.regs));
 
 	/* Reset CP15 registers */
 	kvm_reset_coprocs(vcpu);
diff --git a/arch/arm/kvm/trace.h b/arch/arm/kvm/trace.h
index a8e73ed5ad5b..b1d640f78623 100644
--- a/arch/arm/kvm/trace.h
+++ b/arch/arm/kvm/trace.h
@@ -59,10 +59,9 @@ TRACE_EVENT(kvm_guest_fault,
 		__entry->ipa			= ipa;
 	),
 
-	TP_printk("guest fault at PC %#08lx (hxfar %#08lx, "
-		  "ipa %#16llx, hsr %#08lx",
-		  __entry->vcpu_pc, __entry->hxfar,
-		  __entry->ipa, __entry->hsr)
+	TP_printk("ipa %#llx, hsr %#08lx, hxfar %#08lx, pc %#08lx",
+		  __entry->ipa, __entry->hsr,
+		  __entry->hxfar, __entry->vcpu_pc)
 );
 
 TRACE_EVENT(kvm_irq_line,
diff --git a/arch/arm/lib/Makefile b/arch/arm/lib/Makefile
index af72969820b4..bd454b09133e 100644
--- a/arch/arm/lib/Makefile
+++ b/arch/arm/lib/Makefile
@@ -45,3 +45,9 @@ lib-$(CONFIG_ARCH_SHARK)	+= io-shark.o
 
 $(obj)/csumpartialcopy.o:	$(obj)/csumpartialcopygeneric.S
 $(obj)/csumpartialcopyuser.o:	$(obj)/csumpartialcopygeneric.S
+
+ifeq ($(CONFIG_KERNEL_MODE_NEON),y)
+  NEON_FLAGS			:= -mfloat-abi=softfp -mfpu=neon
+  CFLAGS_xor-neon.o		+= $(NEON_FLAGS)
+  obj-$(CONFIG_XOR_BLOCKS)	+= xor-neon.o
+endif
diff --git a/arch/arm/lib/xor-neon.c b/arch/arm/lib/xor-neon.c
new file mode 100644
index 000000000000..2c40aeab3eaa
--- /dev/null
+++ b/arch/arm/lib/xor-neon.c
@@ -0,0 +1,46 @@
+/*
+ * linux/arch/arm/lib/xor-neon.c
+ *
+ * Copyright (C) 2013 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/raid/xor.h>
+#include <linux/module.h>
+
+MODULE_LICENSE("GPL");
+
+#ifndef __ARM_NEON__
+#error You should compile this file with '-mfloat-abi=softfp -mfpu=neon'
+#endif
+
+/*
+ * Pull in the reference implementations while instructing GCC (through
+ * -ftree-vectorize) to attempt to exploit implicit parallelism and emit
+ * NEON instructions.
+ */
+#if __GNUC__ > 4 || (__GNUC__ == 4 && __GNUC_MINOR__ >= 6)
+#pragma GCC optimize "tree-vectorize"
+#else
+/*
+ * While older versions of GCC do not generate incorrect code, they fail to
+ * recognize the parallel nature of these functions, and emit plain ARM code,
+ * which is known to be slower than the optimized ARM code in asm-arm/xor.h.
+ */
+#warning This code requires at least version 4.6 of GCC
+#endif
+
+#pragma GCC diagnostic ignored "-Wunused-variable"
+#include <asm-generic/xor.h>
+
+struct xor_block_template const xor_block_neon_inner = {
+	.name	= "__inner_neon__",
+	.do_2	= xor_8regs_2,
+	.do_3	= xor_8regs_3,
+	.do_4	= xor_8regs_4,
+	.do_5	= xor_8regs_5,
+};
+EXPORT_SYMBOL(xor_block_neon_inner);
diff --git a/arch/arm/mach-at91/at91rm9200_time.c b/arch/arm/mach-at91/at91rm9200_time.c
index 180b3024bec3..f607deb40f4d 100644
--- a/arch/arm/mach-at91/at91rm9200_time.c
+++ b/arch/arm/mach-at91/at91rm9200_time.c
@@ -93,7 +93,7 @@ static irqreturn_t at91rm9200_timer_interrupt(int irq, void *dev_id)
 
 static struct irqaction at91rm9200_timer_irq = {
 	.name		= "at91_tick",
-	.flags		= IRQF_SHARED | IRQF_DISABLED | IRQF_TIMER | IRQF_IRQPOLL,
+	.flags		= IRQF_SHARED | IRQF_TIMER | IRQF_IRQPOLL,
 	.handler	= at91rm9200_timer_interrupt,
 	.irq		= NR_IRQS_LEGACY + AT91_ID_SYS,
 };
diff --git a/arch/arm/mach-at91/at91sam926x_time.c b/arch/arm/mach-at91/at91sam926x_time.c
index 3a4bc2e1a65e..bb392320a0dd 100644
--- a/arch/arm/mach-at91/at91sam926x_time.c
+++ b/arch/arm/mach-at91/at91sam926x_time.c
@@ -171,7 +171,7 @@ static irqreturn_t at91sam926x_pit_interrupt(int irq, void *dev_id)
 
 static struct irqaction at91sam926x_pit_irq = {
 	.name		= "at91_tick",
-	.flags		= IRQF_SHARED | IRQF_DISABLED | IRQF_TIMER | IRQF_IRQPOLL,
+	.flags		= IRQF_SHARED | IRQF_TIMER | IRQF_IRQPOLL,
 	.handler	= at91sam926x_pit_interrupt,
 	.irq		= NR_IRQS_LEGACY + AT91_ID_SYS,
 };
diff --git a/arch/arm/mach-at91/at91sam9g45_reset.S b/arch/arm/mach-at91/at91sam9g45_reset.S
index 721a1a34dd1d..c40c1e2ef80f 100644
--- a/arch/arm/mach-at91/at91sam9g45_reset.S
+++ b/arch/arm/mach-at91/at91sam9g45_reset.S
@@ -16,11 +16,17 @@
 #include "at91_rstc.h"
 			.arm
 
+/*
+ * at91_ramc_base is an array void*
+ * init at NULL if only one DDR controler is present in or DT
+ */
 			.globl	at91sam9g45_restart
 
 at91sam9g45_restart:
 			ldr	r5, =at91_ramc_base		@ preload constants
 			ldr	r0, [r5]
+			ldr	r5, [r5, #4]			@ ddr1
+			cmp	r5, #0
 			ldr	r4, =at91_rstc_base
 			ldr	r1, [r4]
 
@@ -30,6 +36,8 @@ at91sam9g45_restart:
 
 			.balign	32				@ align to cache line
 
+			strne	r2, [r5, #AT91_DDRSDRC_RTR]	@ disable DDR1 access
+			strne	r3, [r5, #AT91_DDRSDRC_LPR]	@ power down DDR1
 			str	r2, [r0, #AT91_DDRSDRC_RTR]	@ disable DDR0 access
 			str	r3, [r0, #AT91_DDRSDRC_LPR]	@ power down DDR0
 			str	r4, [r1, #AT91_RSTC_CR]		@ reset processor
diff --git a/arch/arm/mach-at91/at91x40_time.c b/arch/arm/mach-at91/at91x40_time.c
index 2919eba41ff4..c0e637adf65d 100644
--- a/arch/arm/mach-at91/at91x40_time.c
+++ b/arch/arm/mach-at91/at91x40_time.c
@@ -57,7 +57,7 @@ static irqreturn_t at91x40_timer_interrupt(int irq, void *dev_id)
 
 static struct irqaction at91x40_timer_irq = {
 	.name		= "at91_tick",
-	.flags		= IRQF_DISABLED | IRQF_TIMER,
+	.flags		= IRQF_TIMER,
 	.handler	= at91x40_timer_interrupt
 };
 
diff --git a/arch/arm/mach-at91/board-dt-sama5.c b/arch/arm/mach-at91/board-dt-sama5.c
index ad95f6a23a28..bf00d15d954d 100644
--- a/arch/arm/mach-at91/board-dt-sama5.c
+++ b/arch/arm/mach-at91/board-dt-sama5.c
@@ -42,20 +42,15 @@ static int ksz9021rn_phy_fixup(struct phy_device *phy)
 {
 	int value;
 
-#define GMII_RCCPSR	260
-#define GMII_RRDPSR	261
-#define GMII_ERCR	11
-#define GMII_ERDWR	12
-
 	/* Set delay values */
-	value = GMII_RCCPSR | 0x8000;
-	phy_write(phy, GMII_ERCR, value);
+	value = MICREL_KSZ9021_RGMII_CLK_CTRL_PAD_SCEW | 0x8000;
+	phy_write(phy, MICREL_KSZ9021_EXTREG_CTRL, value);
 	value = 0xF2F4;
-	phy_write(phy, GMII_ERDWR, value);
-	value = GMII_RRDPSR | 0x8000;
-	phy_write(phy, GMII_ERCR, value);
+	phy_write(phy, MICREL_KSZ9021_EXTREG_DATA_WRITE, value);
+	value = MICREL_KSZ9021_RGMII_RX_DATA_PAD_SCEW | 0x8000;
+	phy_write(phy, MICREL_KSZ9021_EXTREG_CTRL, value);
 	value = 0x2222;
-	phy_write(phy, GMII_ERDWR, value);
+	phy_write(phy, MICREL_KSZ9021_EXTREG_DATA_WRITE, value);
 
 	return 0;
 }
diff --git a/arch/arm/mach-at91/board-snapper9260.c b/arch/arm/mach-at91/board-snapper9260.c
index 3aaa9784cf0e..f1d49e929ccb 100644
--- a/arch/arm/mach-at91/board-snapper9260.c
+++ b/arch/arm/mach-at91/board-snapper9260.c
@@ -26,7 +26,7 @@
 #include <linux/gpio.h>
 #include <linux/platform_device.h>
 #include <linux/spi/spi.h>
-#include <linux/i2c/pca953x.h>
+#include <linux/platform_data/pca953x.h>
 
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
diff --git a/arch/arm/mach-at91/include/mach/at91_adc.h b/arch/arm/mach-at91/include/mach/at91_adc.h
index 8e7ed5c90817..048a57f76bd3 100644
--- a/arch/arm/mach-at91/include/mach/at91_adc.h
+++ b/arch/arm/mach-at91/include/mach/at91_adc.h
@@ -28,9 +28,12 @@
 #define			AT91_ADC_TRGSEL_EXTERNAL	(6 << 1)
 #define		AT91_ADC_LOWRES		(1 << 4)	/* Low Resolution */
 #define		AT91_ADC_SLEEP		(1 << 5)	/* Sleep Mode */
-#define		AT91_ADC_PRESCAL	(0x3f << 8)	/* Prescalar Rate Selection */
+#define		AT91_ADC_PRESCAL_9260	(0x3f << 8)	/* Prescalar Rate Selection */
+#define		AT91_ADC_PRESCAL_9G45	(0xff << 8)
 #define			AT91_ADC_PRESCAL_(x)	((x) << 8)
-#define		AT91_ADC_STARTUP	(0x1f << 16)	/* Startup Up Time */
+#define		AT91_ADC_STARTUP_9260	(0x1f << 16)	/* Startup Up Time */
+#define		AT91_ADC_STARTUP_9G45	(0x7f << 16)
+#define		AT91_ADC_STARTUP_9X5	(0xf << 16)
 #define			AT91_ADC_STARTUP_(x)	((x) << 16)
 #define		AT91_ADC_SHTIM		(0xf  << 24)	/* Sample & Hold Time */
 #define			AT91_ADC_SHTIM_(x)	((x) << 24)
@@ -48,6 +51,9 @@
 #define		AT91_ADC_ENDRX		(1 << 18)	/* End of RX Buffer */
 #define		AT91_ADC_RXFUFF		(1 << 19)	/* RX Buffer Full */
 
+#define AT91_ADC_SR_9X5		0x30		/* Status Register for 9x5 */
+#define		AT91_ADC_SR_DRDY_9X5	(1 << 24)	/* Data Ready */
+
 #define AT91_ADC_LCDR		0x20		/* Last Converted Data Register */
 #define		AT91_ADC_LDATA		(0x3ff)
 
@@ -58,4 +64,10 @@
 #define AT91_ADC_CHR(n)		(0x30 + ((n) * 4))	/* Channel Data Register N */
 #define		AT91_ADC_DATA		(0x3ff)
 
+#define AT91_ADC_CDR0_9X5	(0x50)			/* Channel Data Register 0 for 9X5 */
+
+#define AT91_ADC_TRGR_9260	AT91_ADC_MR
+#define AT91_ADC_TRGR_9G45	0x08
+#define AT91_ADC_TRGR_9X5	0xC0
+
 #endif
diff --git a/arch/arm/mach-at91/include/mach/hardware.h b/arch/arm/mach-at91/include/mach/hardware.h
index a832e0707611..f17aa3150019 100644
--- a/arch/arm/mach-at91/include/mach/hardware.h
+++ b/arch/arm/mach-at91/include/mach/hardware.h
@@ -33,6 +33,7 @@
 #include <mach/at91sam9g45.h>
 #include <mach/at91sam9x5.h>
 #include <mach/at91sam9n12.h>
+#include <mach/sama5d3.h>
 
 /*
  * On all at91 except rm9200 and x40 have the System Controller starts
diff --git a/arch/arm/mach-at91/include/mach/sama5d3.h b/arch/arm/mach-at91/include/mach/sama5d3.h
index 6dc81ee38048..31096a8aaf1d 100644
--- a/arch/arm/mach-at91/include/mach/sama5d3.h
+++ b/arch/arm/mach-at91/include/mach/sama5d3.h
@@ -65,6 +65,14 @@
 #define SAMA5D3_ID_IRQ0		47	/* Advanced Interrupt Controller (IRQ0) */
 
 /*
+ * User Peripheral physical base addresses.
+ */
+#define SAMA5D3_BASE_USART0	0xf001c000
+#define SAMA5D3_BASE_USART1	0xf0020000
+#define SAMA5D3_BASE_USART2	0xf8020000
+#define SAMA5D3_BASE_USART3	0xf8024000
+
+/*
  * Internal Memory
  */
 #define SAMA5D3_SRAM_BASE	0x00300000	/* Internal SRAM base address */
diff --git a/arch/arm/mach-at91/include/mach/uncompress.h b/arch/arm/mach-at91/include/mach/uncompress.h
index 5659f7c72120..4bb644f8e87c 100644
--- a/arch/arm/mach-at91/include/mach/uncompress.h
+++ b/arch/arm/mach-at91/include/mach/uncompress.h
@@ -94,6 +94,15 @@ static const u32 uarts_sam9x5[] = {
 	0,
 };
 
+static const u32 uarts_sama5[] = {
+	AT91_BASE_DBGU1,
+	SAMA5D3_BASE_USART0,
+	SAMA5D3_BASE_USART1,
+	SAMA5D3_BASE_USART2,
+	SAMA5D3_BASE_USART3,
+	0,
+};
+
 static inline const u32* decomp_soc_detect(void __iomem *dbgu_base)
 {
 	u32 cidr, socid;
@@ -121,8 +130,12 @@ static inline const u32* decomp_soc_detect(void __iomem *dbgu_base)
 	case ARCH_ID_AT91SAM9RL64:
 		return uarts_sam9rl;
 
+	case ARCH_ID_AT91SAM9N12:
 	case ARCH_ID_AT91SAM9X5:
 		return uarts_sam9x5;
+
+	case ARCH_ID_SAMA5D3:
+		return uarts_sama5;
 	}
 
 	/* at91sam9g10 */
diff --git a/arch/arm/mach-bcm/Kconfig b/arch/arm/mach-bcm/Kconfig
index f11289519c39..69d67f714a2f 100644
--- a/arch/arm/mach-bcm/Kconfig
+++ b/arch/arm/mach-bcm/Kconfig
@@ -12,6 +12,7 @@ config ARCH_BCM
 	select GPIO_BCM
 	select SPARSE_IRQ
 	select TICK_ONESHOT
+	select CACHE_L2X0
 	help
 	  This enables support for system based on Broadcom SoCs.
 	  It currently supports the 'BCM281XX' family, which includes
diff --git a/arch/arm/mach-bcm/Makefile b/arch/arm/mach-bcm/Makefile
index 6adb6aecf48f..e3d03033a7e2 100644
--- a/arch/arm/mach-bcm/Makefile
+++ b/arch/arm/mach-bcm/Makefile
@@ -1,5 +1,5 @@
 #
-# Copyright (C) 2012 Broadcom Corporation
+# Copyright (C) 2012-2013 Broadcom Corporation
 #
 # This program is free software; you can redistribute it and/or
 # modify it under the terms of the GNU General Public License as
@@ -10,6 +10,6 @@
 # of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 # GNU General Public License for more details.
 
-obj-$(CONFIG_ARCH_BCM)		:= board_bcm.o bcm_kona_smc.o bcm_kona_smc_asm.o
+obj-$(CONFIG_ARCH_BCM)		:= board_bcm281xx.o bcm_kona_smc.o bcm_kona_smc_asm.o kona.o
 plus_sec := $(call as-instr,.arch_extension sec,+sec)
 AFLAGS_bcm_kona_smc_asm.o	:=-Wa,-march=armv7-a$(plus_sec)
diff --git a/arch/arm/mach-bcm/bcm_kona_smc.c b/arch/arm/mach-bcm/bcm_kona_smc.c
index 56d9d19b2470..5e31e918f325 100644
--- a/arch/arm/mach-bcm/bcm_kona_smc.c
+++ b/arch/arm/mach-bcm/bcm_kona_smc.c
@@ -36,18 +36,20 @@ struct bcm_kona_smc_data {
 };
 
 static const struct of_device_id bcm_kona_smc_ids[] __initconst = {
-	{.compatible = "bcm,kona-smc"},
+	{.compatible = "brcm,kona-smc"},
+	{.compatible = "bcm,kona-smc"}, /* deprecated name */
 	{},
 };
 
 /* Map in the bounce area */
-void __init bcm_kona_smc_init(void)
+int __init bcm_kona_smc_init(void)
 {
 	struct device_node *node;
 
 	/* Read buffer addr and size from the device tree node */
 	node = of_find_matching_node(NULL, bcm_kona_smc_ids);
-	BUG_ON(!node);
+	if (!node)
+		return -ENODEV;
 
 	/* Don't care about size or flags of the DT node */
 	bridge_data.buffer_addr =
@@ -59,7 +61,9 @@ void __init bcm_kona_smc_init(void)
 
 	bridge_data.initialized = 1;
 
-	pr_info("Secure API initialized!\n");
+	pr_info("Kona Secure API initialized\n");
+
+	return 0;
 }
 
 /* __bcm_kona_smc() should only run on CPU 0, with pre-emption disabled */
diff --git a/arch/arm/mach-bcm/bcm_kona_smc.h b/arch/arm/mach-bcm/bcm_kona_smc.h
index 3bedbed1c21b..d098a7e76744 100644
--- a/arch/arm/mach-bcm/bcm_kona_smc.h
+++ b/arch/arm/mach-bcm/bcm_kona_smc.h
@@ -64,7 +64,7 @@
 #define SSAPI_BRCM_START_VC_CORE	0x0E000008
 
 #ifndef	__ASSEMBLY__
-extern void bcm_kona_smc_init(void);
+extern int __init bcm_kona_smc_init(void);
 
 extern unsigned bcm_kona_smc(unsigned service_id,
 			     unsigned arg0,
diff --git a/arch/arm/mach-bcm/board_bcm.c b/arch/arm/mach-bcm/board_bcm281xx.c
index 28599326d4ad..8d9f931164bb 100644
--- a/arch/arm/mach-bcm/board_bcm.c
+++ b/arch/arm/mach-bcm/board_bcm281xx.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2012 Broadcom Corporation
+ * Copyright (C) 2012-2013 Broadcom Corporation
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License as
@@ -21,23 +21,39 @@
 #include <asm/mach/time.h>
 #include <asm/hardware/cache-l2x0.h>
 
-
 #include "bcm_kona_smc.h"
+#include "kona.h"
 
 static int __init kona_l2_cache_init(void)
 {
 	if (!IS_ENABLED(CONFIG_CACHE_L2X0))
 		return 0;
 
+	if (bcm_kona_smc_init() < 0) {
+		pr_info("Kona secure API not available. Skipping L2 init\n");
+		return 0;
+	}
+
 	bcm_kona_smc(SSAPI_ENABLE_L2_CACHE, 0, 0, 0, 0);
 
 	/*
 	 * The aux_val and aux_mask have no effect since L2 cache is already
 	 * enabled.  Pass 0s for aux_val and 1s for aux_mask for default value.
 	 */
-	l2x0_of_init(0, ~0);
+	return l2x0_of_init(0, ~0);
+}
 
-	return 0;
+static void bcm_board_setup_restart(void)
+{
+	struct device_node *np;
+
+	np = of_find_compatible_node(NULL, NULL, "brcm,bcm11351");
+	if (np) {
+		if (of_device_is_available(np))
+			bcm_kona_setup_restart();
+		of_node_put(np);
+	}
+	/* Restart setup for other boards goes here */
 }
 
 static void __init board_init(void)
@@ -45,15 +61,15 @@ static void __init board_init(void)
 	of_platform_populate(NULL, of_default_bus_match_table, NULL,
 		&platform_bus);
 
-	bcm_kona_smc_init();
-
+	bcm_board_setup_restart();
 	kona_l2_cache_init();
 }
 
-static const char * const bcm11351_dt_compat[] = { "bcm,bcm11351", NULL, };
+static const char * const bcm11351_dt_compat[] = { "brcm,bcm11351", NULL, };
 
 DT_MACHINE_START(BCM11351_DT, "Broadcom Application Processor")
 	.init_time = clocksource_of_init,
 	.init_machine = board_init,
+	.restart = bcm_kona_restart,
 	.dt_compat = bcm11351_dt_compat,
 MACHINE_END
diff --git a/arch/arm/mach-bcm/kona.c b/arch/arm/mach-bcm/kona.c
new file mode 100644
index 000000000000..6939d9017f63
--- /dev/null
+++ b/arch/arm/mach-bcm/kona.c
@@ -0,0 +1,65 @@
+/*
+ * Copyright (C) 2013 Broadcom Corporation
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation version 2.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any
+ * kind, whether express or implied; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/of_address.h>
+#include <asm/io.h>
+
+#include "kona.h"
+
+static void __iomem *watchdog_base;
+
+void bcm_kona_setup_restart(void)
+{
+	struct device_node *np_wdog;
+
+	/*
+	 * The assumption is that whoever calls bcm_kona_setup_restart()
+	 * also needs a Kona Watchdog Timer entry in Device Tree, i.e. we
+	 * report an error if the DT entry is missing.
+	 */
+	np_wdog = of_find_compatible_node(NULL, NULL, "brcm,kona-wdt");
+	if (!np_wdog) {
+		pr_err("brcm,kona-wdt not found in DT, reboot disabled\n");
+		return;
+	}
+	watchdog_base = of_iomap(np_wdog, 0);
+	WARN(!watchdog_base, "failed to map watchdog base");
+	of_node_put(np_wdog);
+}
+
+#define SECWDOG_OFFSET			0x00000000
+#define SECWDOG_RESERVED_MASK		0xE2000000
+#define SECWDOG_WD_LOAD_FLAG_MASK	0x10000000
+#define SECWDOG_EN_MASK			0x08000000
+#define SECWDOG_SRSTEN_MASK		0x04000000
+#define SECWDOG_CLKS_SHIFT		20
+#define SECWDOG_LOCK_SHIFT		0
+
+void bcm_kona_restart(enum reboot_mode mode, const char *cmd)
+{
+	uint32_t val;
+
+	if (!watchdog_base)
+		panic("Watchdog not mapped. Reboot failed.\n");
+
+	/* Enable watchdog2 with very short timeout. */
+	val = readl(watchdog_base + SECWDOG_OFFSET);
+	val &= SECWDOG_RESERVED_MASK | SECWDOG_WD_LOAD_FLAG_MASK;
+	val |= SECWDOG_EN_MASK | SECWDOG_SRSTEN_MASK |
+		(0x8 << SECWDOG_CLKS_SHIFT) |
+		(0x8 << SECWDOG_LOCK_SHIFT);
+	writel(val, watchdog_base + SECWDOG_OFFSET);
+
+	while (1)
+		;
+}
diff --git a/arch/arm/mach-bcm/kona.h b/arch/arm/mach-bcm/kona.h
new file mode 100644
index 000000000000..291eca3e06ff
--- /dev/null
+++ b/arch/arm/mach-bcm/kona.h
@@ -0,0 +1,17 @@
+/*
+ * Copyright (C) 2013 Broadcom Corporation
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation version 2.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any
+ * kind, whether express or implied; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/reboot.h>
+
+void bcm_kona_setup_restart(void);
+void bcm_kona_restart(enum reboot_mode mode, const char *cmd);
diff --git a/arch/arm/mach-clps711x/Kconfig b/arch/arm/mach-clps711x/Kconfig
index 01ad4d41e728..bea6295c8c59 100644
--- a/arch/arm/mach-clps711x/Kconfig
+++ b/arch/arm/mach-clps711x/Kconfig
@@ -33,9 +33,6 @@ config ARCH_P720T
 	  Say Y here if you intend to run this kernel on the ARM Prospector
 	  720T.
 
-config ARCH_FORTUNET
-	bool "FORTUNET"
-
 config EP72XX_ROM_BOOT
 	bool "EP721x/EP731x ROM boot"
 	help
diff --git a/arch/arm/mach-clps711x/Makefile b/arch/arm/mach-clps711x/Makefile
index f30ed2b496fb..f04151efd96a 100644
--- a/arch/arm/mach-clps711x/Makefile
+++ b/arch/arm/mach-clps711x/Makefile
@@ -10,5 +10,4 @@ obj-$(CONFIG_ARCH_AUTCPU12)	+= board-autcpu12.o
 obj-$(CONFIG_ARCH_CDB89712)	+= board-cdb89712.o
 obj-$(CONFIG_ARCH_CLEP7312)	+= board-clep7312.o
 obj-$(CONFIG_ARCH_EDB7211)	+= board-edb7211.o
-obj-$(CONFIG_ARCH_FORTUNET)	+= board-fortunet.o
 obj-$(CONFIG_ARCH_P720T)	+= board-p720t.o
diff --git a/arch/arm/mach-clps711x/board-autcpu12.c b/arch/arm/mach-clps711x/board-autcpu12.c
index 5867aebd8d0c..f8d71a89644a 100644
--- a/arch/arm/mach-clps711x/board-autcpu12.c
+++ b/arch/arm/mach-clps711x/board-autcpu12.c
@@ -259,11 +259,7 @@ static void __init autcpu12_init(void)
 static void __init autcpu12_init_late(void)
 {
 	gpio_request_array(autcpu12_gpios, ARRAY_SIZE(autcpu12_gpios));
-
-	if (IS_ENABLED(MTD_NAND_GPIO) && IS_ENABLED(GPIO_GENERIC_PLATFORM)) {
-		/* We are need both drivers to handle NAND */
-		platform_device_register(&autcpu12_nand_pdev);
-	}
+	platform_device_register(&autcpu12_nand_pdev);
 }
 
 MACHINE_START(AUTCPU12, "autronix autcpu12")
diff --git a/arch/arm/mach-clps711x/board-edb7211.c b/arch/arm/mach-clps711x/board-edb7211.c
index 9dfb990f0801..fe6184ead896 100644
--- a/arch/arm/mach-clps711x/board-edb7211.c
+++ b/arch/arm/mach-clps711x/board-edb7211.c
@@ -126,21 +126,6 @@ static struct gpio edb7211_gpios[] __initconst = {
 	{ EDB7211_LCDBL,	GPIOF_OUT_INIT_LOW,	"LCD BACKLIGHT" },
 };
 
-static struct map_desc edb7211_io_desc[] __initdata = {
-	{	/* Memory-mapped extra keyboard row */
-		.virtual	= IO_ADDRESS(EDB7211_EXTKBD_BASE),
-		.pfn		= __phys_to_pfn(EDB7211_EXTKBD_BASE),
-		.length		= SZ_1M,
-		.type		= MT_DEVICE,
-	},
-};
-
-void __init edb7211_map_io(void)
-{
-	clps711x_map_io();
-	iotable_init(edb7211_io_desc, ARRAY_SIZE(edb7211_io_desc));
-}
-
 /* Reserve screen memory region at the start of main system memory. */
 static void __init edb7211_reserve(void)
 {
@@ -195,7 +180,7 @@ MACHINE_START(EDB7211, "CL-EDB7211 (EP7211 eval board)")
 	.nr_irqs	= CLPS711X_NR_IRQS,
 	.fixup		= fixup_edb7211,
 	.reserve	= edb7211_reserve,
-	.map_io		= edb7211_map_io,
+	.map_io		= clps711x_map_io,
 	.init_early	= clps711x_init_early,
 	.init_irq	= clps711x_init_irq,
 	.init_time	= clps711x_timer_init,
diff --git a/arch/arm/mach-clps711x/board-fortunet.c b/arch/arm/mach-clps711x/board-fortunet.c
deleted file mode 100644
index b1561e3d7c5c..000000000000
--- a/arch/arm/mach-clps711x/board-fortunet.c
+++ /dev/null
@@ -1,85 +0,0 @@
-/*
- *  linux/arch/arm/mach-clps711x/fortunet.c
- *
- *  Derived from linux/arch/arm/mach-integrator/arch.c
- *
- *  Copyright (C) 2000 Deep Blue Solutions Ltd
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- */
-#include <linux/types.h>
-#include <linux/init.h>
-#include <linux/initrd.h>
-
-#include <mach/hardware.h>
-#include <asm/setup.h>
-#include <asm/mach-types.h>
-
-#include <asm/mach/arch.h>
-
-#include <asm/memory.h>
-
-#include "common.h"
-
-struct meminfo memmap = {
-	.nr_banks	= 1,
-	.bank		= {
-		{
-			.start	= 0xC0000000,
-			.size	= 0x01000000,
-		},
-	},
-};
-
-typedef struct tag_IMAGE_PARAMS
-{
-	int	ramdisk_ok;
-	int	ramdisk_address;
-	int	ramdisk_size;
-	int	ram_size;
-	int	extra_param_type;
-	int	extra_param_ptr;
-	int	command_line;
-} IMAGE_PARAMS;
-
-#define IMAGE_PARAMS_PHYS	0xC01F0000
-
-static void __init
-fortunet_fixup(struct tag *tags, char **cmdline, struct meminfo *mi)
-{
-	IMAGE_PARAMS *ip = phys_to_virt(IMAGE_PARAMS_PHYS);
-	*cmdline = phys_to_virt(ip->command_line);
-#ifdef CONFIG_BLK_DEV_INITRD
-	if(ip->ramdisk_ok)
-	{
-		initrd_start = __phys_to_virt(ip->ramdisk_address);
-		initrd_end = initrd_start + ip->ramdisk_size;
-	}
-#endif
-	memmap.bank[0].size = ip->ram_size;
-	*mi = memmap;
-}
-
-MACHINE_START(FORTUNET, "ARM-FortuNet")
-	/* Maintainer: FortuNet Inc. */
-	.nr_irqs	= CLPS711X_NR_IRQS,
-	.fixup		= fortunet_fixup,
-	.map_io		= clps711x_map_io,
-	.init_early	= clps711x_init_early,
-	.init_irq	= clps711x_init_irq,
-	.init_time	= clps711x_timer_init,
-	.handle_irq	= clps711x_handle_irq,
-	.restart	= clps711x_restart,
-MACHINE_END
diff --git a/arch/arm/mach-clps711x/devices.c b/arch/arm/mach-clps711x/devices.c
index 856b81cf2f8a..fb77d1448fec 100644
--- a/arch/arm/mach-clps711x/devices.c
+++ b/arch/arm/mach-clps711x/devices.c
@@ -57,7 +57,7 @@ static void __init clps711x_add_syscon(void)
 	unsigned i;
 
 	for (i = 0; i < ARRAY_SIZE(clps711x_syscon_res); i++)
-		platform_device_register_simple("clps711x-syscon", i + 1,
+		platform_device_register_simple("syscon", i + 1,
 						&clps711x_syscon_res[i], 1);
 }
 
diff --git a/arch/arm/mach-davinci/board-da830-evm.c b/arch/arm/mach-davinci/board-da830-evm.c
index 1332de8c52c9..c4bdc0a1c36e 100644
--- a/arch/arm/mach-davinci/board-da830-evm.c
+++ b/arch/arm/mach-davinci/board-da830-evm.c
@@ -185,10 +185,6 @@ static __init void da830_evm_usb_init(void)
 			   __func__, ret);
 }
 
-static struct davinci_uart_config da830_evm_uart_config __initdata = {
-	.enabled_uarts = 0x7,
-};
-
 static const short da830_evm_mcasp1_pins[] = {
 	DA830_AHCLKX1, DA830_ACLKX1, DA830_AFSX1, DA830_AHCLKR1, DA830_AFSR1,
 	DA830_AMUTE1, DA830_AXR1_0, DA830_AXR1_1, DA830_AXR1_2, DA830_AXR1_5,
@@ -630,7 +626,7 @@ static __init void da830_evm_init(void)
 		pr_warning("da830_evm_init: watchdog registration failed: %d\n",
 				ret);
 
-	davinci_serial_init(&da830_evm_uart_config);
+	davinci_serial_init(da8xx_serial_device);
 	i2c_register_board_info(1, da830_evm_i2c_devices,
 			ARRAY_SIZE(da830_evm_i2c_devices));
 
diff --git a/arch/arm/mach-davinci/board-da850-evm.c b/arch/arm/mach-davinci/board-da850-evm.c
index bea6793a7ede..dd1fb24521aa 100644
--- a/arch/arm/mach-davinci/board-da850-evm.c
+++ b/arch/arm/mach-davinci/board-da850-evm.c
@@ -19,7 +19,7 @@
 #include <linux/kernel.h>
 #include <linux/i2c.h>
 #include <linux/i2c/at24.h>
-#include <linux/i2c/pca953x.h>
+#include <linux/platform_data/pca953x.h>
 #include <linux/input.h>
 #include <linux/input/tps6507x-ts.h>
 #include <linux/mfd/tps6507x.h>
@@ -746,10 +746,6 @@ static struct davinci_i2c_platform_data da850_evm_i2c_0_pdata = {
 	.bus_delay	= 0,	/* usec */
 };
 
-static struct davinci_uart_config da850_evm_uart_config __initdata = {
-	.enabled_uarts = 0x7,
-};
-
 /* davinci da850 evm audio machine driver */
 static u8 da850_iis_serializer_direction[] = {
 	INACTIVE_MODE,	INACTIVE_MODE,	INACTIVE_MODE,	INACTIVE_MODE,
@@ -1249,12 +1245,10 @@ static struct vpif_capture_config da850_vpif_capture_config = {
 
 static struct adv7343_platform_data adv7343_pdata = {
 	.mode_config = {
-		.dac_3 = 1,
-		.dac_2 = 1,
-		.dac_1 = 1,
+		.dac = { 1, 1, 1 },
 	},
 	.sd_config = {
-		.sd_dac_out1 = 1,
+		.sd_dac_out = { 1 },
 	},
 };
 
@@ -1494,7 +1488,7 @@ static __init void da850_evm_init(void)
 				__func__, ret);
 	}
 
-	davinci_serial_init(&da850_evm_uart_config);
+	davinci_serial_init(da8xx_serial_device);
 
 	i2c_register_board_info(1, da850_evm_i2c_devices,
 			ARRAY_SIZE(da850_evm_i2c_devices));
diff --git a/arch/arm/mach-davinci/board-dm355-evm.c b/arch/arm/mach-davinci/board-dm355-evm.c
index c2a0a67d09e0..42b23a3194a0 100644
--- a/arch/arm/mach-davinci/board-dm355-evm.c
+++ b/arch/arm/mach-davinci/board-dm355-evm.c
@@ -314,10 +314,6 @@ static struct platform_device *davinci_evm_devices[] __initdata = {
 	&davinci_nand_device,
 };
 
-static struct davinci_uart_config uart_config __initdata = {
-	.enabled_uarts = (1 << 0),
-};
-
 static void __init dm355_evm_map_io(void)
 {
 	dm355_init();
@@ -393,7 +389,7 @@ static __init void dm355_evm_init(void)
 	platform_add_devices(davinci_evm_devices,
 			     ARRAY_SIZE(davinci_evm_devices));
 	evm_init_i2c();
-	davinci_serial_init(&uart_config);
+	davinci_serial_init(dm355_serial_device);
 
 	/* NOTE:  NAND flash timings set by the UBL are slower than
 	 * needed by MT29F16G08FAA chips ... EMIF.A1CR is 0x40400204
diff --git a/arch/arm/mach-davinci/board-dm355-leopard.c b/arch/arm/mach-davinci/board-dm355-leopard.c
index 139e42da25f0..65a984c52df6 100644
--- a/arch/arm/mach-davinci/board-dm355-leopard.c
+++ b/arch/arm/mach-davinci/board-dm355-leopard.c
@@ -173,10 +173,6 @@ static struct platform_device *davinci_leopard_devices[] __initdata = {
 	&davinci_nand_device,
 };
 
-static struct davinci_uart_config uart_config __initdata = {
-	.enabled_uarts = (1 << 0),
-};
-
 static void __init dm355_leopard_map_io(void)
 {
 	dm355_init();
@@ -252,7 +248,7 @@ static __init void dm355_leopard_init(void)
 	platform_add_devices(davinci_leopard_devices,
 			     ARRAY_SIZE(davinci_leopard_devices));
 	leopard_init_i2c();
-	davinci_serial_init(&uart_config);
+	davinci_serial_init(dm355_serial_device);
 
 	/* NOTE:  NAND flash timings set by the UBL are slower than
 	 * needed by MT29F16G08FAA chips ... EMIF.A1CR is 0x40400204
diff --git a/arch/arm/mach-davinci/board-dm365-evm.c b/arch/arm/mach-davinci/board-dm365-evm.c
index 4cdb61c54459..4078ba93776b 100644
--- a/arch/arm/mach-davinci/board-dm365-evm.c
+++ b/arch/arm/mach-davinci/board-dm365-evm.c
@@ -176,7 +176,7 @@ static struct at24_platform_data eeprom_info = {
 	.context	= (void *)0x7f00,
 };
 
-static struct snd_platform_data dm365_evm_snd_data = {
+static struct snd_platform_data dm365_evm_snd_data __maybe_unused = {
 	.asp_chan_q = EVENTQ_3,
 };
 
@@ -718,10 +718,6 @@ fail:
 	/* REVISIT export switches: NTSC/PAL (SW5.6), EXTRA1 (SW5.2), etc */
 }
 
-static struct davinci_uart_config uart_config __initdata = {
-	.enabled_uarts = (1 << 0),
-};
-
 static void __init dm365_evm_map_io(void)
 {
 	dm365_init();
@@ -748,7 +744,7 @@ static struct spi_board_info dm365_evm_spi_info[] __initconst = {
 static __init void dm365_evm_init(void)
 {
 	evm_init_i2c();
-	davinci_serial_init(&uart_config);
+	davinci_serial_init(dm365_serial_device);
 
 	dm365evm_emac_configure();
 	dm365evm_mmc_configure();
diff --git a/arch/arm/mach-davinci/board-dm644x-evm.c b/arch/arm/mach-davinci/board-dm644x-evm.c
index fa4bfaf952d8..40bb9b5b87e8 100644
--- a/arch/arm/mach-davinci/board-dm644x-evm.c
+++ b/arch/arm/mach-davinci/board-dm644x-evm.c
@@ -727,10 +727,6 @@ static struct platform_device *davinci_evm_devices[] __initdata = {
 	&rtc_dev,
 };
 
-static struct davinci_uart_config uart_config __initdata = {
-	.enabled_uarts = (1 << 0),
-};
-
 static void __init
 davinci_evm_map_io(void)
 {
@@ -792,7 +788,7 @@ static __init void davinci_evm_init(void)
 	davinci_setup_mmc(0, &dm6446evm_mmc_config);
 	dm644x_init_video(&dm644xevm_capture_cfg, &dm644xevm_display_cfg);
 
-	davinci_serial_init(&uart_config);
+	davinci_serial_init(dm644x_serial_device);
 	dm644x_init_asp(&dm644x_evm_snd_data);
 
 	/* irlml6401 switches over 1A, in under 8 msec */
diff --git a/arch/arm/mach-davinci/board-dm646x-evm.c b/arch/arm/mach-davinci/board-dm646x-evm.c
index 0c005e876cac..2bc3651d56cc 100644
--- a/arch/arm/mach-davinci/board-dm646x-evm.c
+++ b/arch/arm/mach-davinci/board-dm646x-evm.c
@@ -750,10 +750,6 @@ static void __init davinci_map_io(void)
 	cdce_clk_init();
 }
 
-static struct davinci_uart_config uart_config __initdata = {
-	.enabled_uarts = (1 << 0),
-};
-
 #define DM646X_EVM_PHY_ID		"davinci_mdio-0:01"
 /*
  * The following EDMA channels/slots are not being used by drivers (for
@@ -793,7 +789,7 @@ static __init void evm_init(void)
 	struct davinci_soc_info *soc_info = &davinci_soc_info;
 
 	evm_init_i2c();
-	davinci_serial_init(&uart_config);
+	davinci_serial_init(dm646x_serial_device);
 	dm646x_init_mcasp0(&dm646x_evm_snd_data[0]);
 	dm646x_init_mcasp1(&dm646x_evm_snd_data[1]);
 
diff --git a/arch/arm/mach-davinci/board-mityomapl138.c b/arch/arm/mach-davinci/board-mityomapl138.c
index 9549d53aa63f..cd0f58730c2b 100644
--- a/arch/arm/mach-davinci/board-mityomapl138.c
+++ b/arch/arm/mach-davinci/board-mityomapl138.c
@@ -434,10 +434,6 @@ static void __init mityomapl138_setup_nand(void)
 				 ARRAY_SIZE(mityomapl138_devices));
 }
 
-static struct davinci_uart_config mityomapl138_uart_config __initdata = {
-	.enabled_uarts = 0x7,
-};
-
 static const short mityomap_mii_pins[] = {
 	DA850_MII_TXEN, DA850_MII_TXCLK, DA850_MII_COL, DA850_MII_TXD_3,
 	DA850_MII_TXD_2, DA850_MII_TXD_1, DA850_MII_TXD_0, DA850_MII_RXER,
@@ -517,7 +513,7 @@ static void __init mityomapl138_init(void)
 	if (ret)
 		pr_warning("watchdog registration failed: %d\n", ret);
 
-	davinci_serial_init(&mityomapl138_uart_config);
+	davinci_serial_init(da8xx_serial_device);
 
 	ret = da8xx_register_i2c(0, &mityomap_i2c_0_pdata);
 	if (ret)
diff --git a/arch/arm/mach-davinci/board-neuros-osd2.c b/arch/arm/mach-davinci/board-neuros-osd2.c
index 808233b60e3d..46f336fca803 100644
--- a/arch/arm/mach-davinci/board-neuros-osd2.c
+++ b/arch/arm/mach-davinci/board-neuros-osd2.c
@@ -154,10 +154,6 @@ static struct platform_device *davinci_ntosd2_devices[] __initdata = {
 	&ntosd2_leds_dev,
 };
 
-static struct davinci_uart_config uart_config __initdata = {
-	.enabled_uarts = (1 << 0),
-};
-
 static void __init davinci_ntosd2_map_io(void)
 {
 	dm644x_init();
@@ -198,7 +194,7 @@ static __init void davinci_ntosd2_init(void)
 	platform_add_devices(davinci_ntosd2_devices,
 				ARRAY_SIZE(davinci_ntosd2_devices));
 
-	davinci_serial_init(&uart_config);
+	davinci_serial_init(dm644x_serial_device);
 	dm644x_init_asp(&dm644x_ntosd2_snd_data);
 
 	soc_info->emac_pdata->phy_id = NEUROS_OSD2_PHY_ID;
diff --git a/arch/arm/mach-davinci/board-omapl138-hawk.c b/arch/arm/mach-davinci/board-omapl138-hawk.c
index b8c20de10ca2..ab98c75cabb4 100644
--- a/arch/arm/mach-davinci/board-omapl138-hawk.c
+++ b/arch/arm/mach-davinci/board-omapl138-hawk.c
@@ -286,15 +286,11 @@ usb11_setup_oc_fail:
 	gpio_free(DA850_USB1_VBUS_PIN);
 }
 
-static struct davinci_uart_config omapl138_hawk_uart_config __initdata = {
-	.enabled_uarts = 0x7,
-};
-
 static __init void omapl138_hawk_init(void)
 {
 	int ret;
 
-	davinci_serial_init(&omapl138_hawk_uart_config);
+	davinci_serial_init(da8xx_serial_device);
 
 	omapl138_hawk_config_emac();
 
diff --git a/arch/arm/mach-davinci/board-sffsdr.c b/arch/arm/mach-davinci/board-sffsdr.c
index 513eee14f77d..d84360148100 100644
--- a/arch/arm/mach-davinci/board-sffsdr.c
+++ b/arch/arm/mach-davinci/board-sffsdr.c
@@ -125,10 +125,6 @@ static struct platform_device *davinci_sffsdr_devices[] __initdata = {
 	&davinci_sffsdr_nandflash_device,
 };
 
-static struct davinci_uart_config uart_config __initdata = {
-	.enabled_uarts = (1 << 0),
-};
-
 static void __init davinci_sffsdr_map_io(void)
 {
 	dm644x_init();
@@ -141,7 +137,7 @@ static __init void davinci_sffsdr_init(void)
 	platform_add_devices(davinci_sffsdr_devices,
 			     ARRAY_SIZE(davinci_sffsdr_devices));
 	sffsdr_init_i2c();
-	davinci_serial_init(&uart_config);
+	davinci_serial_init(dm644x_serial_device);
 	soc_info->emac_pdata->phy_id = SFFSDR_PHY_ID;
 	davinci_setup_usb(0, 0); /* We support only peripheral mode. */
 
diff --git a/arch/arm/mach-davinci/cpuidle.c b/arch/arm/mach-davinci/cpuidle.c
index 36aef3a7dedb..f1ac1c94ac0f 100644
--- a/arch/arm/mach-davinci/cpuidle.c
+++ b/arch/arm/mach-davinci/cpuidle.c
@@ -65,7 +65,7 @@ static struct cpuidle_driver davinci_idle_driver = {
 	.states[1]		= {
 		.enter			= davinci_enter_idle,
 		.exit_latency		= 10,
-		.target_residency	= 100000,
+		.target_residency	= 10000,
 		.flags			= CPUIDLE_FLAG_TIME_VALID,
 		.name			= "DDR SR",
 		.desc			= "WFI and DDR Self Refresh",
diff --git a/arch/arm/mach-davinci/da830.c b/arch/arm/mach-davinci/da830.c
index abbaf0270be6..d6c746e35ad9 100644
--- a/arch/arm/mach-davinci/da830.c
+++ b/arch/arm/mach-davinci/da830.c
@@ -395,9 +395,9 @@ static struct clk_lookup da830_clks[] = {
 	CLK(NULL,		"tptc0",	&tptc0_clk),
 	CLK(NULL,		"tptc1",	&tptc1_clk),
 	CLK("da830-mmc.0",	NULL,		&mmcsd_clk),
-	CLK(NULL,		"uart0",	&uart0_clk),
-	CLK(NULL,		"uart1",	&uart1_clk),
-	CLK(NULL,		"uart2",	&uart2_clk),
+	CLK("serial8250.0",	NULL,		&uart0_clk),
+	CLK("serial8250.1",	NULL,		&uart1_clk),
+	CLK("serial8250.2",	NULL,		&uart2_clk),
 	CLK("spi_davinci.0",	NULL,		&spi0_clk),
 	CLK("spi_davinci.1",	NULL,		&spi1_clk),
 	CLK(NULL,		"ecap0",	&ecap0_clk),
@@ -417,6 +417,7 @@ static struct clk_lookup da830_clks[] = {
 	CLK(NULL,		"aintc",	&aintc_clk),
 	CLK(NULL,		"secu_mgr",	&secu_mgr_clk),
 	CLK("davinci_emac.1",	NULL,		&emac_clk),
+	CLK("davinci_mdio.0",   "fck",          &emac_clk),
 	CLK(NULL,		"gpio",		&gpio_clk),
 	CLK("i2c_davinci.2",	NULL,		&i2c1_clk),
 	CLK(NULL,		"usb11",	&usb11_clk),
@@ -1199,7 +1200,6 @@ static struct davinci_soc_info davinci_soc_info_da830 = {
 	.gpio_base		= DA8XX_GPIO_BASE,
 	.gpio_num		= 128,
 	.gpio_irq		= IRQ_DA8XX_GPIO0,
-	.serial_dev		= &da8xx_serial_device,
 	.emac_pdata		= &da8xx_emac_pdata,
 };
 
diff --git a/arch/arm/mach-davinci/da850.c b/arch/arm/mach-davinci/da850.c
index a0d4f6038b60..f56e5fbfa2fd 100644
--- a/arch/arm/mach-davinci/da850.c
+++ b/arch/arm/mach-davinci/da850.c
@@ -451,9 +451,9 @@ static struct clk_lookup da850_clks[] = {
 	CLK(NULL,		"tpcc1",	&tpcc1_clk),
 	CLK(NULL,		"tptc2",	&tptc2_clk),
 	CLK("pruss_uio",	"pruss",	&pruss_clk),
-	CLK(NULL,		"uart0",	&uart0_clk),
-	CLK(NULL,		"uart1",	&uart1_clk),
-	CLK(NULL,		"uart2",	&uart2_clk),
+	CLK("serial8250.0",	NULL,		&uart0_clk),
+	CLK("serial8250.1",	NULL,		&uart1_clk),
+	CLK("serial8250.2",	NULL,		&uart2_clk),
 	CLK(NULL,		"aintc",	&aintc_clk),
 	CLK(NULL,		"gpio",		&gpio_clk),
 	CLK("i2c_davinci.2",	NULL,		&i2c1_clk),
@@ -461,6 +461,7 @@ static struct clk_lookup da850_clks[] = {
 	CLK(NULL,		"arm",		&arm_clk),
 	CLK(NULL,		"rmii",		&rmii_clk),
 	CLK("davinci_emac.1",	NULL,		&emac_clk),
+	CLK("davinci_mdio.0",	"fck",		&emac_clk),
 	CLK("davinci-mcasp.0",	NULL,		&mcasp_clk),
 	CLK("da8xx_lcdc.0",	"fck",		&lcdc_clk),
 	CLK("da830-mmc.0",	NULL,		&mmcsd0_clk),
@@ -1301,7 +1302,6 @@ static struct davinci_soc_info davinci_soc_info_da850 = {
 	.gpio_base		= DA8XX_GPIO_BASE,
 	.gpio_num		= 144,
 	.gpio_irq		= IRQ_DA8XX_GPIO0,
-	.serial_dev		= &da8xx_serial_device,
 	.emac_pdata		= &da8xx_emac_pdata,
 	.sram_dma		= DA8XX_SHARED_RAM_BASE,
 	.sram_len		= SZ_128K,
diff --git a/arch/arm/mach-davinci/da8xx-dt.c b/arch/arm/mach-davinci/da8xx-dt.c
index 961aea8bbad5..d2bc574ae172 100644
--- a/arch/arm/mach-davinci/da8xx-dt.c
+++ b/arch/arm/mach-davinci/da8xx-dt.c
@@ -20,13 +20,6 @@
 
 #define DA8XX_NUM_UARTS	3
 
-static void __init da8xx_uart_clk_enable(void)
-{
-	int i;
-	for (i = 0; i < DA8XX_NUM_UARTS; i++)
-		davinci_serial_setup_clk(i, NULL);
-}
-
 static struct of_device_id da8xx_irq_match[] __initdata = {
 	{ .compatible = "ti,cp-intc", .data = cp_intc_of_init, },
 	{ }
@@ -47,6 +40,12 @@ static struct of_dev_auxdata da850_auxdata_lookup[] __initdata = {
 	OF_DEV_AUXDATA("ti,da850-ecap", 0x01f07000, "ecap", NULL),
 	OF_DEV_AUXDATA("ti,da850-ecap", 0x01f08000, "ecap", NULL),
 	OF_DEV_AUXDATA("ti,da830-spi", 0x01f0e000, "spi_davinci.1", NULL),
+	OF_DEV_AUXDATA("ns16550a", 0x01c42000, "serial8250.0", NULL),
+	OF_DEV_AUXDATA("ns16550a", 0x01d0c000, "serial8250.1", NULL),
+	OF_DEV_AUXDATA("ns16550a", 0x01d0d000, "serial8250.2", NULL),
+	OF_DEV_AUXDATA("ti,davinci_mdio", 0x01e24000, "davinci_mdio.0", NULL),
+	OF_DEV_AUXDATA("ti,davinci-dm6467-emac", 0x01e20000, "davinci_emac.1",
+		       NULL),
 	{}
 };
 
@@ -57,7 +56,6 @@ static void __init da850_init_machine(void)
 	of_platform_populate(NULL, of_default_bus_match_table,
 			     da850_auxdata_lookup, NULL);
 
-	da8xx_uart_clk_enable();
 }
 
 static const char *da850_boards_compat[] __initdata = {
diff --git a/arch/arm/mach-davinci/davinci.h b/arch/arm/mach-davinci/davinci.h
index a883043d0820..2ab5d577186f 100644
--- a/arch/arm/mach-davinci/davinci.h
+++ b/arch/arm/mach-davinci/davinci.h
@@ -106,4 +106,9 @@ int dm646x_init_edma(struct edma_rsv_info *rsv);
 void dm646x_video_init(void);
 void dm646x_setup_vpif(struct vpif_display_config *,
 		       struct vpif_capture_config *);
+
+extern struct platform_device dm365_serial_device[];
+extern struct platform_device dm355_serial_device[];
+extern struct platform_device dm644x_serial_device[];
+extern struct platform_device dm646x_serial_device[];
 #endif /*__DAVINCI_H */
diff --git a/arch/arm/mach-davinci/devices-da8xx.c b/arch/arm/mach-davinci/devices-da8xx.c
index 71a46a348761..2e473fefd71e 100644
--- a/arch/arm/mach-davinci/devices-da8xx.c
+++ b/arch/arm/mach-davinci/devices-da8xx.c
@@ -68,7 +68,7 @@
 void __iomem *da8xx_syscfg0_base;
 void __iomem *da8xx_syscfg1_base;
 
-static struct plat_serial8250_port da8xx_serial_pdata[] = {
+static struct plat_serial8250_port da8xx_serial0_pdata[] = {
 	{
 		.mapbase	= DA8XX_UART0_BASE,
 		.irq		= IRQ_DA8XX_UARTINT0,
@@ -78,6 +78,11 @@ static struct plat_serial8250_port da8xx_serial_pdata[] = {
 		.regshift	= 2,
 	},
 	{
+		.flags	= 0,
+	}
+};
+static struct plat_serial8250_port da8xx_serial1_pdata[] = {
+	{
 		.mapbase	= DA8XX_UART1_BASE,
 		.irq		= IRQ_DA8XX_UARTINT1,
 		.flags		= UPF_BOOT_AUTOCONF | UPF_SKIP_TEST |
@@ -86,6 +91,11 @@ static struct plat_serial8250_port da8xx_serial_pdata[] = {
 		.regshift	= 2,
 	},
 	{
+		.flags	= 0,
+	}
+};
+static struct plat_serial8250_port da8xx_serial2_pdata[] = {
+	{
 		.mapbase	= DA8XX_UART2_BASE,
 		.irq		= IRQ_DA8XX_UARTINT2,
 		.flags		= UPF_BOOT_AUTOCONF | UPF_SKIP_TEST |
@@ -95,15 +105,33 @@ static struct plat_serial8250_port da8xx_serial_pdata[] = {
 	},
 	{
 		.flags	= 0,
-	},
+	}
 };
 
-struct platform_device da8xx_serial_device = {
-	.name	= "serial8250",
-	.id	= PLAT8250_DEV_PLATFORM,
-	.dev	= {
-		.platform_data	= da8xx_serial_pdata,
+struct platform_device da8xx_serial_device[] = {
+	{
+		.name	= "serial8250",
+		.id	= PLAT8250_DEV_PLATFORM,
+		.dev	= {
+			.platform_data	= da8xx_serial0_pdata,
+		}
+	},
+	{
+		.name	= "serial8250",
+		.id	= PLAT8250_DEV_PLATFORM1,
+		.dev	= {
+			.platform_data	= da8xx_serial1_pdata,
+		}
+	},
+	{
+		.name	= "serial8250",
+		.id	= PLAT8250_DEV_PLATFORM2,
+		.dev	= {
+			.platform_data	= da8xx_serial2_pdata,
+		}
 	},
+	{
+	}
 };
 
 static s8 da8xx_queue_tc_mapping[][2] = {
@@ -453,12 +481,8 @@ int __init da8xx_register_emac(void)
 	ret = platform_device_register(&da8xx_mdio_device);
 	if (ret < 0)
 		return ret;
-	ret = platform_device_register(&da8xx_emac_device);
-	if (ret < 0)
-		return ret;
-	ret = clk_add_alias(NULL, dev_name(&da8xx_mdio_device.dev),
-			    NULL, &da8xx_emac_device.dev);
-	return ret;
+
+	return platform_device_register(&da8xx_emac_device);
 }
 
 static struct resource da830_mcasp1_resources[] = {
@@ -828,14 +852,7 @@ static struct platform_device da8xx_rtc_device = {
 
 int da8xx_register_rtc(void)
 {
-	int ret;
-
-	ret = platform_device_register(&da8xx_rtc_device);
-	if (!ret)
-		/* Atleast on DA850, RTC is a wakeup source */
-		device_init_wakeup(&da8xx_rtc_device.dev, true);
-
-	return ret;
+	return platform_device_register(&da8xx_rtc_device);
 }
 
 static void __iomem *da8xx_ddr2_ctlr_base;
diff --git a/arch/arm/mach-davinci/devices-tnetv107x.c b/arch/arm/mach-davinci/devices-tnetv107x.c
index 128cb9ae80f4..01d8686e553c 100644
--- a/arch/arm/mach-davinci/devices-tnetv107x.c
+++ b/arch/arm/mach-davinci/devices-tnetv107x.c
@@ -126,7 +126,7 @@ static struct platform_device edma_device = {
 	.dev.platform_data = tnetv107x_edma_info,
 };
 
-static struct plat_serial8250_port serial_data[] = {
+static struct plat_serial8250_port serial0_platform_data[] = {
 	{
 		.mapbase	= TNETV107X_UART0_BASE,
 		.irq		= IRQ_TNETV107X_UART0,
@@ -137,6 +137,11 @@ static struct plat_serial8250_port serial_data[] = {
 		.regshift	= 2,
 	},
 	{
+		.flags	= 0,
+	}
+};
+static struct plat_serial8250_port serial1_platform_data[] = {
+	{
 		.mapbase	= TNETV107X_UART1_BASE,
 		.irq		= IRQ_TNETV107X_UART1,
 		.flags		= UPF_BOOT_AUTOCONF | UPF_SKIP_TEST |
@@ -146,6 +151,11 @@ static struct plat_serial8250_port serial_data[] = {
 		.regshift	= 2,
 	},
 	{
+		.flags	= 0,
+	}
+};
+static struct plat_serial8250_port serial2_platform_data[] = {
+	{
 		.mapbase	= TNETV107X_UART2_BASE,
 		.irq		= IRQ_TNETV107X_UART2,
 		.flags		= UPF_BOOT_AUTOCONF | UPF_SKIP_TEST |
@@ -156,13 +166,28 @@ static struct plat_serial8250_port serial_data[] = {
 	},
 	{
 		.flags	= 0,
-	},
+	}
 };
 
-struct platform_device tnetv107x_serial_device = {
-	.name			= "serial8250",
-	.id			= PLAT8250_DEV_PLATFORM,
-	.dev.platform_data	= serial_data,
+
+struct platform_device tnetv107x_serial_device[] = {
+	{
+		.name			= "serial8250",
+		.id			= PLAT8250_DEV_PLATFORM,
+		.dev.platform_data	= serial0_platform_data,
+	},
+	{
+		.name			= "serial8250",
+		.id			= PLAT8250_DEV_PLATFORM1,
+		.dev.platform_data	= serial1_platform_data,
+	},
+	{
+		.name			= "serial8250",
+		.id			= PLAT8250_DEV_PLATFORM2,
+		.dev.platform_data	= serial2_platform_data,
+	},
+	{
+	}
 };
 
 static struct resource mmc0_resources[] = {
@@ -385,7 +410,7 @@ void __init tnetv107x_devices_init(struct tnetv107x_device_info *info)
 	platform_device_register(&tsc_device);
 
 	if (info->serial_config)
-		davinci_serial_init(info->serial_config);
+		davinci_serial_init(tnetv107x_serial_device);
 
 	for (i = 0; i < 2; i++)
 		if (info->mmc_config[i]) {
diff --git a/arch/arm/mach-davinci/dm355.c b/arch/arm/mach-davinci/dm355.c
index 86100d179694..3eaa5f6b2160 100644
--- a/arch/arm/mach-davinci/dm355.c
+++ b/arch/arm/mach-davinci/dm355.c
@@ -357,9 +357,9 @@ static struct clk_lookup dm355_clks[] = {
 	CLK(NULL, "clkout3", &clkout3_clk),
 	CLK(NULL, "arm", &arm_clk),
 	CLK(NULL, "mjcp", &mjcp_clk),
-	CLK(NULL, "uart0", &uart0_clk),
-	CLK(NULL, "uart1", &uart1_clk),
-	CLK(NULL, "uart2", &uart2_clk),
+	CLK("serial8250.0", NULL, &uart0_clk),
+	CLK("serial8250.1", NULL, &uart1_clk),
+	CLK("serial8250.2", NULL, &uart2_clk),
 	CLK("i2c_davinci.1", NULL, &i2c_clk),
 	CLK("davinci-mcbsp.0", NULL, &asp0_clk),
 	CLK("davinci-mcbsp.1", NULL, &asp1_clk),
@@ -922,7 +922,7 @@ static struct davinci_timer_info dm355_timer_info = {
 	.clocksource_id	= T0_TOP,
 };
 
-static struct plat_serial8250_port dm355_serial_platform_data[] = {
+static struct plat_serial8250_port dm355_serial0_platform_data[] = {
 	{
 		.mapbase	= DAVINCI_UART0_BASE,
 		.irq		= IRQ_UARTINT0,
@@ -932,6 +932,11 @@ static struct plat_serial8250_port dm355_serial_platform_data[] = {
 		.regshift	= 2,
 	},
 	{
+		.flags	= 0,
+	}
+};
+static struct plat_serial8250_port dm355_serial1_platform_data[] = {
+	{
 		.mapbase	= DAVINCI_UART1_BASE,
 		.irq		= IRQ_UARTINT1,
 		.flags		= UPF_BOOT_AUTOCONF | UPF_SKIP_TEST |
@@ -940,6 +945,11 @@ static struct plat_serial8250_port dm355_serial_platform_data[] = {
 		.regshift	= 2,
 	},
 	{
+		.flags	= 0,
+	}
+};
+static struct plat_serial8250_port dm355_serial2_platform_data[] = {
+	{
 		.mapbase	= DM355_UART2_BASE,
 		.irq		= IRQ_DM355_UARTINT2,
 		.flags		= UPF_BOOT_AUTOCONF | UPF_SKIP_TEST |
@@ -948,16 +958,34 @@ static struct plat_serial8250_port dm355_serial_platform_data[] = {
 		.regshift	= 2,
 	},
 	{
-		.flags		= 0
-	},
+		.flags	= 0,
+	}
 };
 
-static struct platform_device dm355_serial_device = {
-	.name			= "serial8250",
-	.id			= PLAT8250_DEV_PLATFORM,
-	.dev			= {
-		.platform_data	= dm355_serial_platform_data,
+struct platform_device dm355_serial_device[] = {
+	{
+		.name			= "serial8250",
+		.id			= PLAT8250_DEV_PLATFORM,
+		.dev			= {
+			.platform_data	= dm355_serial0_platform_data,
+		}
+	},
+	{
+		.name			= "serial8250",
+		.id			= PLAT8250_DEV_PLATFORM1,
+		.dev			= {
+			.platform_data	= dm355_serial1_platform_data,
+		}
 	},
+	{
+		.name			= "serial8250",
+		.id			= PLAT8250_DEV_PLATFORM2,
+		.dev			= {
+			.platform_data	= dm355_serial2_platform_data,
+		}
+	},
+	{
+	}
 };
 
 static struct davinci_soc_info davinci_soc_info_dm355 = {
@@ -981,7 +1009,6 @@ static struct davinci_soc_info davinci_soc_info_dm355 = {
 	.gpio_base		= DAVINCI_GPIO_BASE,
 	.gpio_num		= 104,
 	.gpio_irq		= IRQ_DM355_GPIOBNK0,
-	.serial_dev		= &dm355_serial_device,
 	.sram_dma		= 0x00010000,
 	.sram_len		= SZ_32K,
 };
diff --git a/arch/arm/mach-davinci/dm365.c b/arch/arm/mach-davinci/dm365.c
index dad28029ba9b..c29e324eb0bb 100644
--- a/arch/arm/mach-davinci/dm365.c
+++ b/arch/arm/mach-davinci/dm365.c
@@ -455,8 +455,8 @@ static struct clk_lookup dm365_clks[] = {
 	CLK("vpss", "master", &vpss_master_clk),
 	CLK("vpss", "slave", &vpss_slave_clk),
 	CLK(NULL, "arm", &arm_clk),
-	CLK(NULL, "uart0", &uart0_clk),
-	CLK(NULL, "uart1", &uart1_clk),
+	CLK("serial8250.0", NULL, &uart0_clk),
+	CLK("serial8250.1", NULL, &uart1_clk),
 	CLK("i2c_davinci.1", NULL, &i2c_clk),
 	CLK("da830-mmc.0", NULL, &mmcsd0_clk),
 	CLK("da830-mmc.1", NULL, &mmcsd1_clk),
@@ -477,6 +477,7 @@ static struct clk_lookup dm365_clks[] = {
 	CLK(NULL, "timer3", &timer3_clk),
 	CLK(NULL, "usb", &usb_clk),
 	CLK("davinci_emac.1", NULL, &emac_clk),
+	CLK("davinci_mdio.0", "fck", &emac_clk),
 	CLK("davinci_voicecodec", NULL, &voicecodec_clk),
 	CLK("davinci-mcbsp", NULL, &asp0_clk),
 	CLK(NULL, "rto", &rto_clk),
@@ -1041,7 +1042,7 @@ static struct davinci_timer_info dm365_timer_info = {
 
 #define DM365_UART1_BASE	(IO_PHYS + 0x106000)
 
-static struct plat_serial8250_port dm365_serial_platform_data[] = {
+static struct plat_serial8250_port dm365_serial0_platform_data[] = {
 	{
 		.mapbase	= DAVINCI_UART0_BASE,
 		.irq		= IRQ_UARTINT0,
@@ -1051,6 +1052,11 @@ static struct plat_serial8250_port dm365_serial_platform_data[] = {
 		.regshift	= 2,
 	},
 	{
+		.flags	= 0,
+	}
+};
+static struct plat_serial8250_port dm365_serial1_platform_data[] = {
+	{
 		.mapbase	= DM365_UART1_BASE,
 		.irq		= IRQ_UARTINT1,
 		.flags		= UPF_BOOT_AUTOCONF | UPF_SKIP_TEST |
@@ -1059,16 +1065,27 @@ static struct plat_serial8250_port dm365_serial_platform_data[] = {
 		.regshift	= 2,
 	},
 	{
-		.flags		= 0
-	},
+		.flags	= 0,
+	}
 };
 
-static struct platform_device dm365_serial_device = {
-	.name			= "serial8250",
-	.id			= PLAT8250_DEV_PLATFORM,
-	.dev			= {
-		.platform_data	= dm365_serial_platform_data,
+struct platform_device dm365_serial_device[] = {
+	{
+		.name			= "serial8250",
+		.id			= PLAT8250_DEV_PLATFORM,
+		.dev			= {
+			.platform_data	= dm365_serial0_platform_data,
+		}
+	},
+	{
+		.name			= "serial8250",
+		.id			= PLAT8250_DEV_PLATFORM1,
+		.dev			= {
+			.platform_data	= dm365_serial1_platform_data,
+		}
 	},
+	{
+	}
 };
 
 static struct davinci_soc_info davinci_soc_info_dm365 = {
@@ -1093,7 +1110,6 @@ static struct davinci_soc_info davinci_soc_info_dm365 = {
 	.gpio_num		= 104,
 	.gpio_irq		= IRQ_DM365_GPIO0,
 	.gpio_unbanked		= 8,	/* really 16 ... skip muxed GPIOs */
-	.serial_dev		= &dm365_serial_device,
 	.emac_pdata		= &dm365_emac_pdata,
 	.sram_dma		= 0x00010000,
 	.sram_len		= SZ_32K,
@@ -1407,8 +1423,6 @@ static int __init dm365_init_devices(void)
 
 	platform_device_register(&dm365_mdio_device);
 	platform_device_register(&dm365_emac_device);
-	clk_add_alias(NULL, dev_name(&dm365_mdio_device.dev),
-		      NULL, &dm365_emac_device.dev);
 
 	return 0;
 }
diff --git a/arch/arm/mach-davinci/dm644x.c b/arch/arm/mach-davinci/dm644x.c
index a49d18246fe9..4f74682293d6 100644
--- a/arch/arm/mach-davinci/dm644x.c
+++ b/arch/arm/mach-davinci/dm644x.c
@@ -303,10 +303,11 @@ static struct clk_lookup dm644x_clks[] = {
 	CLK("vpss", "master", &vpss_master_clk),
 	CLK("vpss", "slave", &vpss_slave_clk),
 	CLK(NULL, "arm", &arm_clk),
-	CLK(NULL, "uart0", &uart0_clk),
-	CLK(NULL, "uart1", &uart1_clk),
-	CLK(NULL, "uart2", &uart2_clk),
+	CLK("serial8250.0", NULL, &uart0_clk),
+	CLK("serial8250.1", NULL, &uart1_clk),
+	CLK("serial8250.2", NULL, &uart2_clk),
 	CLK("davinci_emac.1", NULL, &emac_clk),
+	CLK("davinci_mdio.0", "fck", &emac_clk),
 	CLK("i2c_davinci.1", NULL, &i2c_clk),
 	CLK("palm_bk3710", NULL, &ide_clk),
 	CLK("davinci-mcbsp", NULL, &asp_clk),
@@ -813,7 +814,7 @@ static struct davinci_timer_info dm644x_timer_info = {
 	.clocksource_id	= T0_TOP,
 };
 
-static struct plat_serial8250_port dm644x_serial_platform_data[] = {
+static struct plat_serial8250_port dm644x_serial0_platform_data[] = {
 	{
 		.mapbase	= DAVINCI_UART0_BASE,
 		.irq		= IRQ_UARTINT0,
@@ -823,6 +824,11 @@ static struct plat_serial8250_port dm644x_serial_platform_data[] = {
 		.regshift	= 2,
 	},
 	{
+		.flags	= 0,
+	}
+};
+static struct plat_serial8250_port dm644x_serial1_platform_data[] = {
+	{
 		.mapbase	= DAVINCI_UART1_BASE,
 		.irq		= IRQ_UARTINT1,
 		.flags		= UPF_BOOT_AUTOCONF | UPF_SKIP_TEST |
@@ -831,6 +837,11 @@ static struct plat_serial8250_port dm644x_serial_platform_data[] = {
 		.regshift	= 2,
 	},
 	{
+		.flags	= 0,
+	}
+};
+static struct plat_serial8250_port dm644x_serial2_platform_data[] = {
+	{
 		.mapbase	= DAVINCI_UART2_BASE,
 		.irq		= IRQ_UARTINT2,
 		.flags		= UPF_BOOT_AUTOCONF | UPF_SKIP_TEST |
@@ -839,16 +850,34 @@ static struct plat_serial8250_port dm644x_serial_platform_data[] = {
 		.regshift	= 2,
 	},
 	{
-		.flags		= 0
-	},
+		.flags	= 0,
+	}
 };
 
-static struct platform_device dm644x_serial_device = {
-	.name			= "serial8250",
-	.id			= PLAT8250_DEV_PLATFORM,
-	.dev			= {
-		.platform_data	= dm644x_serial_platform_data,
+struct platform_device dm644x_serial_device[] = {
+	{
+		.name			= "serial8250",
+		.id			= PLAT8250_DEV_PLATFORM,
+		.dev			= {
+			.platform_data	= dm644x_serial0_platform_data,
+		}
 	},
+	{
+		.name			= "serial8250",
+		.id			= PLAT8250_DEV_PLATFORM1,
+		.dev			= {
+			.platform_data	= dm644x_serial1_platform_data,
+		}
+	},
+	{
+		.name			= "serial8250",
+		.id			= PLAT8250_DEV_PLATFORM2,
+		.dev			= {
+			.platform_data	= dm644x_serial2_platform_data,
+		}
+	},
+	{
+	}
 };
 
 static struct davinci_soc_info davinci_soc_info_dm644x = {
@@ -872,7 +901,6 @@ static struct davinci_soc_info davinci_soc_info_dm644x = {
 	.gpio_base		= DAVINCI_GPIO_BASE,
 	.gpio_num		= 71,
 	.gpio_irq		= IRQ_GPIOBNK0,
-	.serial_dev		= &dm644x_serial_device,
 	.emac_pdata		= &dm644x_emac_pdata,
 	.sram_dma		= 0x00008000,
 	.sram_len		= SZ_16K,
@@ -923,8 +951,6 @@ static int __init dm644x_init_devices(void)
 
 	platform_device_register(&dm644x_mdio_device);
 	platform_device_register(&dm644x_emac_device);
-	clk_add_alias(NULL, dev_name(&dm644x_mdio_device.dev),
-		      NULL, &dm644x_emac_device.dev);
 
 	return 0;
 }
diff --git a/arch/arm/mach-davinci/dm646x.c b/arch/arm/mach-davinci/dm646x.c
index d1259e80141b..68f8d1f1aca1 100644
--- a/arch/arm/mach-davinci/dm646x.c
+++ b/arch/arm/mach-davinci/dm646x.c
@@ -342,15 +342,16 @@ static struct clk_lookup dm646x_clks[] = {
 	CLK(NULL, "edma_tc1", &edma_tc1_clk),
 	CLK(NULL, "edma_tc2", &edma_tc2_clk),
 	CLK(NULL, "edma_tc3", &edma_tc3_clk),
-	CLK(NULL, "uart0", &uart0_clk),
-	CLK(NULL, "uart1", &uart1_clk),
-	CLK(NULL, "uart2", &uart2_clk),
+	CLK("serial8250.0", NULL, &uart0_clk),
+	CLK("serial8250.1", NULL, &uart1_clk),
+	CLK("serial8250.2", NULL, &uart2_clk),
 	CLK("i2c_davinci.1", NULL, &i2c_clk),
 	CLK(NULL, "gpio", &gpio_clk),
 	CLK("davinci-mcasp.0", NULL, &mcasp0_clk),
 	CLK("davinci-mcasp.1", NULL, &mcasp1_clk),
 	CLK(NULL, "aemif", &aemif_clk),
 	CLK("davinci_emac.1", NULL, &emac_clk),
+	CLK("davinci_mdio.0", "fck", &emac_clk),
 	CLK(NULL, "pwm0", &pwm0_clk),
 	CLK(NULL, "pwm1", &pwm1_clk),
 	CLK(NULL, "timer0", &timer0_clk),
@@ -790,7 +791,7 @@ static struct davinci_timer_info dm646x_timer_info = {
 	.clocksource_id	= T0_TOP,
 };
 
-static struct plat_serial8250_port dm646x_serial_platform_data[] = {
+static struct plat_serial8250_port dm646x_serial0_platform_data[] = {
 	{
 		.mapbase	= DAVINCI_UART0_BASE,
 		.irq		= IRQ_UARTINT0,
@@ -800,6 +801,11 @@ static struct plat_serial8250_port dm646x_serial_platform_data[] = {
 		.regshift	= 2,
 	},
 	{
+		.flags	= 0,
+	}
+};
+static struct plat_serial8250_port dm646x_serial1_platform_data[] = {
+	{
 		.mapbase	= DAVINCI_UART1_BASE,
 		.irq		= IRQ_UARTINT1,
 		.flags		= UPF_BOOT_AUTOCONF | UPF_SKIP_TEST |
@@ -808,6 +814,11 @@ static struct plat_serial8250_port dm646x_serial_platform_data[] = {
 		.regshift	= 2,
 	},
 	{
+		.flags	= 0,
+	}
+};
+static struct plat_serial8250_port dm646x_serial2_platform_data[] = {
+	{
 		.mapbase	= DAVINCI_UART2_BASE,
 		.irq		= IRQ_DM646X_UARTINT2,
 		.flags		= UPF_BOOT_AUTOCONF | UPF_SKIP_TEST |
@@ -816,16 +827,34 @@ static struct plat_serial8250_port dm646x_serial_platform_data[] = {
 		.regshift	= 2,
 	},
 	{
-		.flags		= 0
-	},
+		.flags	= 0,
+	}
 };
 
-static struct platform_device dm646x_serial_device = {
-	.name			= "serial8250",
-	.id			= PLAT8250_DEV_PLATFORM,
-	.dev			= {
-		.platform_data	= dm646x_serial_platform_data,
+struct platform_device dm646x_serial_device[] = {
+	{
+		.name			= "serial8250",
+		.id			= PLAT8250_DEV_PLATFORM,
+		.dev			= {
+			.platform_data	= dm646x_serial0_platform_data,
+		}
+	},
+	{
+		.name			= "serial8250",
+		.id			= PLAT8250_DEV_PLATFORM1,
+		.dev			= {
+			.platform_data	= dm646x_serial1_platform_data,
+		}
 	},
+	{
+		.name			= "serial8250",
+		.id			= PLAT8250_DEV_PLATFORM2,
+		.dev			= {
+			.platform_data	= dm646x_serial2_platform_data,
+		}
+	},
+	{
+	}
 };
 
 static struct davinci_soc_info davinci_soc_info_dm646x = {
@@ -849,7 +878,6 @@ static struct davinci_soc_info davinci_soc_info_dm646x = {
 	.gpio_base		= DAVINCI_GPIO_BASE,
 	.gpio_num		= 43, /* Only 33 usable */
 	.gpio_irq		= IRQ_DM646X_GPIOBNK0,
-	.serial_dev		= &dm646x_serial_device,
 	.emac_pdata		= &dm646x_emac_pdata,
 	.sram_dma		= 0x10010000,
 	.sram_len		= SZ_32K,
@@ -913,8 +941,6 @@ static int __init dm646x_init_devices(void)
 
 	platform_device_register(&dm646x_mdio_device);
 	platform_device_register(&dm646x_emac_device);
-	clk_add_alias(NULL, dev_name(&dm646x_mdio_device.dev),
-		      NULL, &dm646x_emac_device.dev);
 
 	return 0;
 }
diff --git a/arch/arm/mach-davinci/include/mach/common.h b/arch/arm/mach-davinci/include/mach/common.h
index cce316b92c06..0b3c169758ed 100644
--- a/arch/arm/mach-davinci/include/mach/common.h
+++ b/arch/arm/mach-davinci/include/mach/common.h
@@ -72,7 +72,6 @@ struct davinci_soc_info {
 	unsigned			gpio_unbanked;
 	struct davinci_gpio_controller	*gpio_ctlrs;
 	int				gpio_ctlrs_num;
-	struct platform_device		*serial_dev;
 	struct emac_platform_data	*emac_pdata;
 	dma_addr_t			sram_dma;
 	unsigned			sram_len;
diff --git a/arch/arm/mach-davinci/include/mach/da8xx.h b/arch/arm/mach-davinci/include/mach/da8xx.h
index 7b41a5e9bc31..aae53072c0eb 100644
--- a/arch/arm/mach-davinci/include/mach/da8xx.h
+++ b/arch/arm/mach-davinci/include/mach/da8xx.h
@@ -111,7 +111,7 @@ void da8xx_restart(enum reboot_mode mode, const char *cmd);
 void da8xx_rproc_reserve_cma(void);
 int da8xx_register_rproc(void);
 
-extern struct platform_device da8xx_serial_device;
+extern struct platform_device da8xx_serial_device[];
 extern struct emac_platform_data da8xx_emac_pdata;
 extern struct da8xx_lcdc_platform_data sharp_lcd035q3dg01_pdata;
 extern struct da8xx_lcdc_platform_data sharp_lk043t1dg01_pdata;
diff --git a/arch/arm/mach-davinci/include/mach/debug-macro.S b/arch/arm/mach-davinci/include/mach/debug-macro.S
deleted file mode 100644
index b18b8ebc6508..000000000000
--- a/arch/arm/mach-davinci/include/mach/debug-macro.S
+++ /dev/null
@@ -1,65 +0,0 @@
-/*
- * Debugging macro for DaVinci
- *
- * Author: Kevin Hilman, MontaVista Software, Inc. <source@mvista.com>
- *
- * 2007 (c) MontaVista Software, Inc. This file is licensed under
- * the terms of the GNU General Public License version 2. This program
- * is licensed "as is" without any warranty of any kind, whether express
- * or implied.
- */
-
-/* Modifications
- * Jan 2009	Chaithrika U S	Added senduart, busyuart, waituart
- *				macros, based on debug-8250.S file
- *				but using 32-bit accesses required for
- *                              some davinci devices.
- */
-
-#include <linux/serial_reg.h>
-
-#include <mach/serial.h>
-
-#define UART_SHIFT	2
-
-#if defined(CONFIG_DEBUG_DAVINCI_DMx_UART0)
-#define UART_BASE	DAVINCI_UART0_BASE
-#elif defined(CONFIG_DEBUG_DAVINCI_DA8XX_UART1)
-#define UART_BASE	DA8XX_UART1_BASE
-#elif defined(CONFIG_DEBUG_DAVINCI_DA8XX_UART2)
-#define UART_BASE	DA8XX_UART2_BASE
-#elif defined(CONFIG_DEBUG_DAVINCI_TNETV107X_UART1)
-#define UART_BASE	TNETV107X_UART2_BASE
-#define UART_VIRTBASE	TNETV107X_UART2_VIRT
-#else
-#error "Select a specifc port for DEBUG_LL"
-#endif
-
-#ifndef UART_VIRTBASE
-#define UART_VIRTBASE	IO_ADDRESS(UART_BASE)
-#endif
-
-		.macro addruart, rp, rv, tmp
-		ldr	\rp, =UART_BASE
-		ldr	\rv, =UART_VIRTBASE
-		.endm
-
-		.macro	senduart,rd,rx
-		str	\rd, [\rx, #UART_TX << UART_SHIFT]
-		.endm
-
-		.macro	busyuart,rd,rx
-1002:		ldr	\rd, [\rx, #UART_LSR << UART_SHIFT]
-		and	\rd, \rd, #UART_LSR_TEMT | UART_LSR_THRE
-		teq	\rd, #UART_LSR_TEMT | UART_LSR_THRE
-		bne	1002b
-		.endm
-
-		.macro	waituart,rd,rx
-#ifdef FLOW_CONTROL
-1001:		ldr	\rd, [\rx, #UART_MSR << UART_SHIFT]
-		tst	\rd, #UART_MSR_CTS
-		beq	1001b
-#endif
-		.endm
-
diff --git a/arch/arm/mach-davinci/include/mach/serial.h b/arch/arm/mach-davinci/include/mach/serial.h
index 62ad300440f5..ce402cd21fa0 100644
--- a/arch/arm/mach-davinci/include/mach/serial.h
+++ b/arch/arm/mach-davinci/include/mach/serial.h
@@ -37,13 +37,9 @@
 #define UART_DM646X_SCR_TX_WATERMARK	0x08
 
 #ifndef __ASSEMBLY__
-struct davinci_uart_config {
-	/* Bit field of UARTs present; bit 0 --> UART0 */
-	unsigned int enabled_uarts;
-};
+#include <linux/platform_device.h>
 
-extern int davinci_serial_init(struct davinci_uart_config *);
-extern int davinci_serial_setup_clk(unsigned instance, unsigned int *rate);
+extern int davinci_serial_init(struct platform_device *);
 #endif
 
 #endif /* __ASM_ARCH_SERIAL_H */
diff --git a/arch/arm/mach-davinci/include/mach/tnetv107x.h b/arch/arm/mach-davinci/include/mach/tnetv107x.h
index 16314c64f755..494fcf5ccfe1 100644
--- a/arch/arm/mach-davinci/include/mach/tnetv107x.h
+++ b/arch/arm/mach-davinci/include/mach/tnetv107x.h
@@ -42,7 +42,6 @@
 #include <mach/serial.h>
 
 struct tnetv107x_device_info {
-	struct davinci_uart_config	*serial_config;
 	struct davinci_mmc_config	*mmc_config[2];  /* 2 controllers */
 	struct davinci_nand_pdata	*nand_config[4]; /* 4 chipsels */
 	struct matrix_keypad_platform_data *keypad_config;
@@ -50,7 +49,7 @@ struct tnetv107x_device_info {
 };
 
 extern struct platform_device tnetv107x_wdt_device;
-extern struct platform_device tnetv107x_serial_device;
+extern struct platform_device tnetv107x_serial_device[];
 
 extern void tnetv107x_init(void);
 extern void tnetv107x_devices_init(struct tnetv107x_device_info *);
diff --git a/arch/arm/mach-davinci/serial.c b/arch/arm/mach-davinci/serial.c
index f2625814c3c9..5e93a734c858 100644
--- a/arch/arm/mach-davinci/serial.c
+++ b/arch/arm/mach-davinci/serial.c
@@ -70,49 +70,36 @@ static void __init davinci_serial_reset(struct plat_serial8250_port *p)
 				 UART_DM646X_SCR_TX_WATERMARK);
 }
 
-/* Enable UART clock and obtain its rate */
-int __init davinci_serial_setup_clk(unsigned instance, unsigned int *rate)
+int __init davinci_serial_init(struct platform_device *serial_dev)
 {
-	char name[16];
+	int i, ret = 0;
+	struct device *dev;
+	struct plat_serial8250_port *p;
 	struct clk *clk;
-	struct davinci_soc_info *soc_info = &davinci_soc_info;
-	struct device *dev = &soc_info->serial_dev->dev;
-
-	sprintf(name, "uart%d", instance);
-	clk = clk_get(dev, name);
-	if (IS_ERR(clk)) {
-		pr_err("%s:%d: failed to get UART%d clock\n",
-					__func__, __LINE__, instance);
-		return PTR_ERR(clk);
-	}
-
-	clk_prepare_enable(clk);
-
-	if (rate)
-		*rate = clk_get_rate(clk);
-
-	return 0;
-}
-
-int __init davinci_serial_init(struct davinci_uart_config *info)
-{
-	int i, ret;
-	struct davinci_soc_info *soc_info = &davinci_soc_info;
-	struct device *dev = &soc_info->serial_dev->dev;
-	struct plat_serial8250_port *p = dev->platform_data;
 
 	/*
 	 * Make sure the serial ports are muxed on at this point.
 	 * You have to mux them off in device drivers later on if not needed.
 	 */
-	for (i = 0; p->flags; i++, p++) {
-		if (!(info->enabled_uarts & (1 << i)))
-			continue;
+	for (i = 0; serial_dev[i].dev.platform_data != NULL; i++) {
+		dev = &serial_dev[i].dev;
+		p = dev->platform_data;
 
-		ret = davinci_serial_setup_clk(i, &p->uartclk);
+		ret = platform_device_register(&serial_dev[i]);
 		if (ret)
 			continue;
 
+		clk = clk_get(dev, NULL);
+		if (IS_ERR(clk)) {
+			pr_err("%s:%d: failed to get UART%d clock\n",
+			       __func__, __LINE__, i);
+			continue;
+		}
+
+		clk_prepare_enable(clk);
+
+		p->uartclk = clk_get_rate(clk);
+
 		if (!p->membase && p->mapbase) {
 			p->membase = ioremap(p->mapbase, SZ_4K);
 
@@ -125,6 +112,5 @@ int __init davinci_serial_init(struct davinci_uart_config *info)
 		if (p->membase && p->type != PORT_AR7)
 			davinci_serial_reset(p);
 	}
-
-	return platform_device_register(soc_info->serial_dev);
+	return ret;
 }
diff --git a/arch/arm/mach-davinci/tnetv107x.c b/arch/arm/mach-davinci/tnetv107x.c
index 4545667ecd3c..f4d7fbb24b3b 100644
--- a/arch/arm/mach-davinci/tnetv107x.c
+++ b/arch/arm/mach-davinci/tnetv107x.c
@@ -264,7 +264,7 @@ static struct clk_lookup clks[] = {
 	CLK(NULL,		"clk_chipcfg",		&clk_chipcfg),
 	CLK("tnetv107x-ts.0",	NULL,			&clk_tsc),
 	CLK(NULL,		"clk_rom",		&clk_rom),
-	CLK(NULL,		"uart2",		&clk_uart2),
+	CLK("serial8250.2",     NULL,			&clk_uart2),
 	CLK(NULL,		"clk_pktsec",		&clk_pktsec),
 	CLK("tnetv107x-rng.0",	NULL,			&clk_rng),
 	CLK("tnetv107x-pka.0",	NULL,			&clk_pka),
@@ -274,8 +274,8 @@ static struct clk_lookup clks[] = {
 	CLK(NULL,		"clk_gpio",		&clk_gpio),
 	CLK(NULL,		"clk_mdio",		&clk_mdio),
 	CLK("dm6441-mmc.0",	NULL,			&clk_sdio0),
-	CLK(NULL,		"uart0",		&clk_uart0),
-	CLK(NULL,		"uart1",		&clk_uart1),
+	CLK("serial8250.0",	NULL,			&clk_uart0),
+	CLK("serial8250.1",	NULL,			&clk_uart1),
 	CLK(NULL,		"timer0",		&clk_timer0),
 	CLK(NULL,		"timer1",		&clk_timer1),
 	CLK("tnetv107x_wdt.0",	NULL,			&clk_wdt_arm),
@@ -757,7 +757,7 @@ static struct davinci_soc_info tnetv107x_soc_info = {
 	.gpio_type		= GPIO_TYPE_TNETV107X,
 	.gpio_num		= TNETV107X_N_GPIO,
 	.timer_info		= &timer_info,
-	.serial_dev		= &tnetv107x_serial_device,
+	.serial_dev		= tnetv107x_serial_device,
 };
 
 void __init tnetv107x_init(void)
diff --git a/arch/arm/mach-dove/Kconfig b/arch/arm/mach-dove/Kconfig
index dff7b2fd4e20..0bc7cdf8cf46 100644
--- a/arch/arm/mach-dove/Kconfig
+++ b/arch/arm/mach-dove/Kconfig
@@ -23,6 +23,8 @@ config MACH_CM_A510
 config MACH_DOVE_DT
 	bool "Marvell Dove Flattened Device Tree"
 	select DOVE_CLK
+	select ORION_IRQCHIP
+	select ORION_TIMER
 	select REGULATOR
 	select REGULATOR_FIXED_VOLTAGE
 	select USE_OF
diff --git a/arch/arm/mach-dove/Makefile b/arch/arm/mach-dove/Makefile
index 4d9d2ffc4535..cbc5c0618788 100644
--- a/arch/arm/mach-dove/Makefile
+++ b/arch/arm/mach-dove/Makefile
@@ -1,5 +1,5 @@
-obj-y				+= common.o irq.o
-obj-$(CONFIG_DOVE_LEGACY)	+= mpp.o
+obj-y				+= common.o
+obj-$(CONFIG_DOVE_LEGACY)	+= irq.o mpp.o
 obj-$(CONFIG_PCI)		+= pcie.o
 obj-$(CONFIG_MACH_DOVE_DB)	+= dove-db-setup.o
 obj-$(CONFIG_MACH_DOVE_DT)	+= board-dt.o
diff --git a/arch/arm/mach-dove/board-dt.c b/arch/arm/mach-dove/board-dt.c
index f3755ac81148..49f72a848423 100644
--- a/arch/arm/mach-dove/board-dt.c
+++ b/arch/arm/mach-dove/board-dt.c
@@ -10,11 +10,14 @@
 
 #include <linux/init.h>
 #include <linux/clk-provider.h>
+#include <linux/clocksource.h>
+#include <linux/irqchip.h>
 #include <linux/of.h>
 #include <linux/of_platform.h>
 #include <linux/platform_data/usb-ehci-orion.h>
 #include <asm/hardware/cache-tauros2.h>
 #include <asm/mach/arch.h>
+#include <mach/dove.h>
 #include <mach/pm.h>
 #include <plat/common.h>
 #include <plat/irq.h>
@@ -33,10 +36,6 @@ static void __init dove_legacy_clk_init(void)
 	clkspec.np = np;
 	clkspec.args_count = 1;
 
-	clkspec.args[0] = CLOCK_GATING_BIT_GBE;
-	orion_clkdev_add(NULL, "mv643xx_eth_port.0",
-			 of_clk_get_from_provider(&clkspec));
-
 	clkspec.args[0] = CLOCK_GATING_BIT_PCIE0;
 	orion_clkdev_add("0", "pcie",
 			 of_clk_get_from_provider(&clkspec));
@@ -46,15 +45,18 @@ static void __init dove_legacy_clk_init(void)
 			 of_clk_get_from_provider(&clkspec));
 }
 
-static void __init dove_of_clk_init(void)
+static void __init dove_dt_time_init(void)
 {
 	of_clk_init(NULL);
-	dove_legacy_clk_init();
+	clocksource_of_init();
 }
 
-static struct mv643xx_eth_platform_data dove_dt_ge00_data = {
-	.phy_addr = MV643XX_ETH_PHY_ADDR_DEFAULT,
-};
+static void __init dove_dt_init_early(void)
+{
+	mvebu_mbus_init("marvell,dove-mbus",
+			BRIDGE_WINS_BASE, BRIDGE_WINS_SZ,
+			DOVE_MC_WINS_BASE, DOVE_MC_WINS_SZ);
+}
 
 static void __init dove_dt_init(void)
 {
@@ -65,11 +67,10 @@ static void __init dove_dt_init(void)
 #endif
 	dove_setup_cpu_wins();
 
-	/* Setup root of clk tree */
-	dove_of_clk_init();
+	/* Setup clocks for legacy devices */
+	dove_legacy_clk_init();
 
 	/* Internal devices not ported to DT yet */
-	dove_ge00_init(&dove_dt_ge00_data);
 	dove_pcie_init(1, 1);
 
 	of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
@@ -82,9 +83,8 @@ static const char * const dove_dt_board_compat[] = {
 
 DT_MACHINE_START(DOVE_DT, "Marvell Dove (Flattened Device Tree)")
 	.map_io		= dove_map_io,
-	.init_early	= dove_init_early,
-	.init_irq	= orion_dt_init_irq,
-	.init_time	= dove_timer_init,
+	.init_early	= dove_dt_init_early,
+	.init_time	= dove_dt_time_init,
 	.init_machine	= dove_dt_init,
 	.restart	= dove_restart,
 	.dt_compat	= dove_dt_board_compat,
diff --git a/arch/arm/mach-dove/common.c b/arch/arm/mach-dove/common.c
index 00247c771313..c122bcff9f7c 100644
--- a/arch/arm/mach-dove/common.c
+++ b/arch/arm/mach-dove/common.c
@@ -27,6 +27,22 @@
 #include <plat/time.h>
 #include "common.h"
 
+/* These can go away once Dove uses the mvebu-mbus DT binding */
+#define DOVE_MBUS_PCIE0_MEM_TARGET    0x4
+#define DOVE_MBUS_PCIE0_MEM_ATTR      0xe8
+#define DOVE_MBUS_PCIE0_IO_TARGET     0x4
+#define DOVE_MBUS_PCIE0_IO_ATTR       0xe0
+#define DOVE_MBUS_PCIE1_MEM_TARGET    0x8
+#define DOVE_MBUS_PCIE1_MEM_ATTR      0xe8
+#define DOVE_MBUS_PCIE1_IO_TARGET     0x8
+#define DOVE_MBUS_PCIE1_IO_ATTR       0xe0
+#define DOVE_MBUS_CESA_TARGET         0x3
+#define DOVE_MBUS_CESA_ATTR           0x1
+#define DOVE_MBUS_BOOTROM_TARGET      0x1
+#define DOVE_MBUS_BOOTROM_ATTR        0xfd
+#define DOVE_MBUS_SCRATCHPAD_TARGET   0xd
+#define DOVE_MBUS_SCRATCHPAD_ATTR     0x0
+
 /*****************************************************************************
  * I/O Address Mapping
  ****************************************************************************/
@@ -108,8 +124,8 @@ static void __init dove_clk_init(void)
 	orion_clkdev_add(NULL, "sdhci-dove.1", sdio1);
 	orion_clkdev_add(NULL, "orion_nand", nand);
 	orion_clkdev_add(NULL, "cafe1000-ccic.0", camera);
-	orion_clkdev_add(NULL, "kirkwood-i2s.0", i2s0);
-	orion_clkdev_add(NULL, "kirkwood-i2s.1", i2s1);
+	orion_clkdev_add(NULL, "mvebu-audio.0", i2s0);
+	orion_clkdev_add(NULL, "mvebu-audio.1", i2s1);
 	orion_clkdev_add(NULL, "mv_crypto", crypto);
 	orion_clkdev_add(NULL, "dove-ac97", ac97);
 	orion_clkdev_add(NULL, "dove-pdma", pdma);
@@ -332,34 +348,40 @@ void __init dove_setup_cpu_wins(void)
 {
 	/*
 	 * The PCIe windows will no longer be statically allocated
-	 * here once Dove is migrated to the pci-mvebu driver.
+	 * here once Dove is migrated to the pci-mvebu driver. The
+	 * non-PCIe windows will no longer be created here once Dove
+	 * fully moves to DT.
 	 */
-	mvebu_mbus_add_window_remap_flags("pcie0.0",
+	mvebu_mbus_add_window_remap_by_id(DOVE_MBUS_PCIE0_IO_TARGET,
+					  DOVE_MBUS_PCIE0_IO_ATTR,
 					  DOVE_PCIE0_IO_PHYS_BASE,
 					  DOVE_PCIE0_IO_SIZE,
-					  DOVE_PCIE0_IO_BUS_BASE,
-					  MVEBU_MBUS_PCI_IO);
-	mvebu_mbus_add_window_remap_flags("pcie1.0",
+					  DOVE_PCIE0_IO_BUS_BASE);
+	mvebu_mbus_add_window_remap_by_id(DOVE_MBUS_PCIE1_IO_TARGET,
+					  DOVE_MBUS_PCIE1_IO_ATTR,
 					  DOVE_PCIE1_IO_PHYS_BASE,
 					  DOVE_PCIE1_IO_SIZE,
-					  DOVE_PCIE1_IO_BUS_BASE,
-					  MVEBU_MBUS_PCI_IO);
-	mvebu_mbus_add_window_remap_flags("pcie0.0",
-					  DOVE_PCIE0_MEM_PHYS_BASE,
-					  DOVE_PCIE0_MEM_SIZE,
-					  MVEBU_MBUS_NO_REMAP,
-					  MVEBU_MBUS_PCI_MEM);
-	mvebu_mbus_add_window_remap_flags("pcie1.0",
-					  DOVE_PCIE1_MEM_PHYS_BASE,
-					  DOVE_PCIE1_MEM_SIZE,
-					  MVEBU_MBUS_NO_REMAP,
-					  MVEBU_MBUS_PCI_MEM);
-	mvebu_mbus_add_window("cesa", DOVE_CESA_PHYS_BASE,
-			      DOVE_CESA_SIZE);
-	mvebu_mbus_add_window("bootrom", DOVE_BOOTROM_PHYS_BASE,
-			      DOVE_BOOTROM_SIZE);
-	mvebu_mbus_add_window("scratchpad", DOVE_SCRATCHPAD_PHYS_BASE,
-			      DOVE_SCRATCHPAD_SIZE);
+					  DOVE_PCIE1_IO_BUS_BASE);
+	mvebu_mbus_add_window_by_id(DOVE_MBUS_PCIE0_MEM_TARGET,
+				    DOVE_MBUS_PCIE0_MEM_ATTR,
+				    DOVE_PCIE0_MEM_PHYS_BASE,
+				    DOVE_PCIE0_MEM_SIZE);
+	mvebu_mbus_add_window_by_id(DOVE_MBUS_PCIE1_MEM_TARGET,
+				    DOVE_MBUS_PCIE1_MEM_ATTR,
+				    DOVE_PCIE1_MEM_PHYS_BASE,
+				    DOVE_PCIE1_MEM_SIZE);
+	mvebu_mbus_add_window_by_id(DOVE_MBUS_CESA_TARGET,
+				    DOVE_MBUS_CESA_ATTR,
+				    DOVE_CESA_PHYS_BASE,
+				    DOVE_CESA_SIZE);
+	mvebu_mbus_add_window_by_id(DOVE_MBUS_BOOTROM_TARGET,
+				    DOVE_MBUS_BOOTROM_ATTR,
+				    DOVE_BOOTROM_PHYS_BASE,
+				    DOVE_BOOTROM_SIZE);
+	mvebu_mbus_add_window_by_id(DOVE_MBUS_SCRATCHPAD_TARGET,
+				    DOVE_MBUS_SCRATCHPAD_ATTR,
+				    DOVE_SCRATCHPAD_PHYS_BASE,
+				    DOVE_SCRATCHPAD_SIZE);
 }
 
 void __init dove_init(void)
diff --git a/arch/arm/mach-dove/include/mach/debug-macro.S b/arch/arm/mach-dove/include/mach/debug-macro.S
deleted file mode 100644
index 5929cbc59161..000000000000
--- a/arch/arm/mach-dove/include/mach/debug-macro.S
+++ /dev/null
@@ -1,19 +0,0 @@
-/*
- * arch/arm/mach-dove/include/mach/debug-macro.S
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
-
-#include <mach/bridge-regs.h>
-
-	.macro	addruart, rp, rv, tmp
-	ldr	\rp, =DOVE_SB_REGS_PHYS_BASE
-	ldr	\rv, =DOVE_SB_REGS_VIRT_BASE
-	orr	\rp, \rp, #0x00012000
-	orr	\rv, \rv, #0x00012000
-	.endm
-
-#define UART_SHIFT	2
-#include <asm/hardware/debug-8250.S>
diff --git a/arch/arm/mach-dove/mpp.c b/arch/arm/mach-dove/mpp.c
index 60bd729a1ba5..8a433a51289c 100644
--- a/arch/arm/mach-dove/mpp.c
+++ b/arch/arm/mach-dove/mpp.c
@@ -47,7 +47,7 @@ static const struct dove_mpp_grp dove_mpp_grp[] = {
 
 /* Enable gpio for a range of pins. mode should be a combination of
    GPIO_OUTPUT_OK | GPIO_INPUT_OK */
-static void dove_mpp_gpio_mode(int start, int end, int gpio_mode)
+static void __init dove_mpp_gpio_mode(int start, int end, int gpio_mode)
 {
 	int i;
 
diff --git a/arch/arm/mach-ebsa110/include/mach/debug-macro.S b/arch/arm/mach-ebsa110/include/mach/debug-macro.S
deleted file mode 100644
index bb02c05e6812..000000000000
--- a/arch/arm/mach-ebsa110/include/mach/debug-macro.S
+++ /dev/null
@@ -1,22 +0,0 @@
-/* arch/arm/mach-ebsa110/include/mach/debug-macro.S
- *
- * Debugging macro include header
- *
- *  Copyright (C) 1994-1999 Russell King
- *  Moved from linux/arch/arm/kernel/debug.S by Ben Dooks
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
-**/
-
-		.macro	addruart, rp, rv, tmp
-		mov	\rp, #0xf0000000
-		orr	\rp, \rp, #0x00000be0
-		mov	\rp, \rv
-		.endm
-
-#define UART_SHIFT	2
-#define FLOW_CONTROL
-#include <asm/hardware/debug-8250.S>
diff --git a/arch/arm/mach-ep93xx/Kconfig b/arch/arm/mach-ep93xx/Kconfig
index fe3c1fa5462b..93e54fd4e3d5 100644
--- a/arch/arm/mach-ep93xx/Kconfig
+++ b/arch/arm/mach-ep93xx/Kconfig
@@ -194,20 +194,6 @@ config MACH_VISION_EP9307
 	  Say 'Y' here if you want your kernel to support the
 	  Vision Engraving Systems EP9307 SoM.
 
-choice
-	prompt "Select a UART for early kernel messages"
-
-config EP93XX_EARLY_UART1
-	bool "UART1"
-
-config EP93XX_EARLY_UART2
-	bool "UART2"
-
-config EP93XX_EARLY_UART3
-	bool "UART3"
-
-endchoice
-
 endmenu
 
 endif
diff --git a/arch/arm/mach-ep93xx/core.c b/arch/arm/mach-ep93xx/core.c
index df8612fbbc9c..3f12b885c083 100644
--- a/arch/arm/mach-ep93xx/core.c
+++ b/arch/arm/mach-ep93xx/core.c
@@ -281,7 +281,7 @@ static AMBA_APB_DEVICE(uart1, "apb:uart1", 0x00041010, EP93XX_UART1_PHYS_BASE,
 	{ IRQ_EP93XX_UART1 }, &ep93xx_uart_data);
 
 static AMBA_APB_DEVICE(uart2, "apb:uart2", 0x00041010, EP93XX_UART2_PHYS_BASE,
-	{ IRQ_EP93XX_UART2 }, &ep93xx_uart_data);
+	{ IRQ_EP93XX_UART2 }, NULL);
 
 static AMBA_APB_DEVICE(uart3, "apb:uart3", 0x00041010, EP93XX_UART3_PHYS_BASE,
 	{ IRQ_EP93XX_UART3 }, &ep93xx_uart_data);
diff --git a/arch/arm/mach-ep93xx/include/mach/debug-macro.S b/arch/arm/mach-ep93xx/include/mach/debug-macro.S
deleted file mode 100644
index af54e43132cf..000000000000
--- a/arch/arm/mach-ep93xx/include/mach/debug-macro.S
+++ /dev/null
@@ -1,21 +0,0 @@
-/*
- * arch/arm/mach-ep93xx/include/mach/debug-macro.S
- * Debugging macro include header
- *
- * Copyright (C) 2006 Lennert Buytenhek <buytenh@wantstofly.org>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or (at
- * your option) any later version.
- */
-#include <mach/ep93xx-regs.h>
-
-		.macro	addruart, rp, rv, tmp
-		ldr	\rp, =EP93XX_APB_PHYS_BASE	@ Physical base
-		ldr	\rv, =EP93XX_APB_VIRT_BASE	@ virtual base
-		orr	\rp, \rp, #0x000c0000
-		orr	\rv, \rv, #0x000c0000
-		.endm
-
-#include <asm/hardware/debug-pl01x.S>
diff --git a/arch/arm/mach-ep93xx/include/mach/uncompress.h b/arch/arm/mach-ep93xx/include/mach/uncompress.h
index b5cc77d2380b..03c42e5400d2 100644
--- a/arch/arm/mach-ep93xx/include/mach/uncompress.h
+++ b/arch/arm/mach-ep93xx/include/mach/uncompress.h
@@ -31,18 +31,8 @@ static void __raw_writel(unsigned int value, unsigned int ptr)
 	*((volatile unsigned int *)ptr) = value;
 }
 
-#if defined(CONFIG_EP93XX_EARLY_UART1)
-#define UART_BASE		EP93XX_UART1_PHYS_BASE
-#elif defined(CONFIG_EP93XX_EARLY_UART2)
-#define UART_BASE		EP93XX_UART2_PHYS_BASE
-#elif defined(CONFIG_EP93XX_EARLY_UART3)
-#define UART_BASE		EP93XX_UART3_PHYS_BASE
-#else
-#define UART_BASE		EP93XX_UART1_PHYS_BASE
-#endif
-
-#define PHYS_UART_DATA		(UART_BASE + 0x00)
-#define PHYS_UART_FLAG		(UART_BASE + 0x18)
+#define PHYS_UART_DATA		(CONFIG_DEBUG_UART_PHYS + 0x00)
+#define PHYS_UART_FLAG		(CONFIG_DEBUG_UART_PHYS + 0x18)
 #define UART_FLAG_TXFF		0x20
 
 static inline void putc(int c)
diff --git a/arch/arm/mach-ep93xx/vision_ep9307.c b/arch/arm/mach-ep93xx/vision_ep9307.c
index 605956fd07a2..6bc1c181581d 100644
--- a/arch/arm/mach-ep93xx/vision_ep9307.c
+++ b/arch/arm/mach-ep93xx/vision_ep9307.c
@@ -23,7 +23,7 @@
 #include <linux/mtd/partitions.h>
 #include <linux/i2c.h>
 #include <linux/i2c-gpio.h>
-#include <linux/i2c/pca953x.h>
+#include <linux/platform_data/pca953x.h>
 #include <linux/spi/spi.h>
 #include <linux/spi/flash.h>
 #include <linux/spi/mmc_spi.h>
@@ -224,62 +224,15 @@ static struct ep93xx_spi_chip_ops vision_spi_flash_hw = {
 #define VISION_SPI_MMC_WP	EP93XX_GPIO_LINE_F(0)
 #define VISION_SPI_MMC_CD	EP93XX_GPIO_LINE_EGPIO15
 
-static struct gpio vision_spi_mmc_gpios[] = {
-	{ VISION_SPI_MMC_WP, GPIOF_DIR_IN, "mmc_spi:wp" },
-	{ VISION_SPI_MMC_CD, GPIOF_DIR_IN, "mmc_spi:cd" },
-};
-
-static int vision_spi_mmc_init(struct device *pdev,
-			irqreturn_t (*func)(int, void *), void *pdata)
-{
-	int err;
-
-	err = gpio_request_array(vision_spi_mmc_gpios,
-				 ARRAY_SIZE(vision_spi_mmc_gpios));
-	if (err)
-		return err;
-
-	err = gpio_set_debounce(VISION_SPI_MMC_CD, 1);
-	if (err)
-		goto exit_err;
-
-	err = request_irq(gpio_to_irq(VISION_SPI_MMC_CD), func,
-			IRQ_TYPE_EDGE_BOTH, "mmc_spi:cd", pdata);
-	if (err)
-		goto exit_err;
-
-	return 0;
-
-exit_err:
-	gpio_free_array(vision_spi_mmc_gpios, ARRAY_SIZE(vision_spi_mmc_gpios));
-	return err;
-
-}
-
-static void vision_spi_mmc_exit(struct device *pdev, void *pdata)
-{
-	free_irq(gpio_to_irq(VISION_SPI_MMC_CD), pdata);
-	gpio_free_array(vision_spi_mmc_gpios, ARRAY_SIZE(vision_spi_mmc_gpios));
-}
-
-static int vision_spi_mmc_get_ro(struct device *pdev)
-{
-	return !!gpio_get_value(VISION_SPI_MMC_WP);
-}
-
-static int vision_spi_mmc_get_cd(struct device *pdev)
-{
-	return !gpio_get_value(VISION_SPI_MMC_CD);
-}
-
 static struct mmc_spi_platform_data vision_spi_mmc_data = {
-	.init		= vision_spi_mmc_init,
-	.exit		= vision_spi_mmc_exit,
-	.get_ro		= vision_spi_mmc_get_ro,
-	.get_cd		= vision_spi_mmc_get_cd,
 	.detect_delay	= 100,
 	.powerup_msecs	= 100,
 	.ocr_mask	= MMC_VDD_32_33 | MMC_VDD_33_34,
+	.flags		= MMC_SPI_USE_CD_GPIO | MMC_SPI_USE_RO_GPIO,
+	.cd_gpio	= VISION_SPI_MMC_CD,
+	.cd_debounce	= 1,
+	.ro_gpio	= VISION_SPI_MMC_WP,
+	.caps2		= MMC_CAP2_RO_ACTIVE_HIGH,
 };
 
 static int vision_spi_mmc_hw_setup(struct spi_device *spi)
diff --git a/arch/arm/mach-exynos/Kconfig b/arch/arm/mach-exynos/Kconfig
index 5952e68c76c4..56fe819ee10b 100644
--- a/arch/arm/mach-exynos/Kconfig
+++ b/arch/arm/mach-exynos/Kconfig
@@ -36,6 +36,7 @@ config CPU_EXYNOS4210
 	bool "SAMSUNG EXYNOS4210"
 	default y
 	depends on ARCH_EXYNOS4
+	select ARCH_HAS_BANDGAP
 	select ARM_CPU_SUSPEND if PM
 	select PINCTRL_EXYNOS
 	select PM_GENERIC_DOMAINS if PM
@@ -49,7 +50,9 @@ config SOC_EXYNOS4212
 	bool "SAMSUNG EXYNOS4212"
 	default y
 	depends on ARCH_EXYNOS4
+	select ARCH_HAS_BANDGAP
 	select PINCTRL_EXYNOS
+	select PM_GENERIC_DOMAINS if PM
 	select S5P_PM if PM
 	select S5P_SLEEP if PM
 	select SAMSUNG_DMADEV
@@ -60,7 +63,9 @@ config SOC_EXYNOS4412
 	bool "SAMSUNG EXYNOS4412"
 	default y
 	depends on ARCH_EXYNOS4
+	select ARCH_HAS_BANDGAP
 	select PINCTRL_EXYNOS
+	select PM_GENERIC_DOMAINS if PM
 	select SAMSUNG_DMADEV
 	help
 	  Enable EXYNOS4412 SoC support
@@ -69,6 +74,7 @@ config SOC_EXYNOS5250
 	bool "SAMSUNG EXYNOS5250"
 	default y
 	depends on ARCH_EXYNOS5
+	select ARCH_HAS_BANDGAP
 	select PINCTRL_EXYNOS
 	select PM_GENERIC_DOMAINS if PM
 	select S5P_PM if PM
@@ -93,6 +99,7 @@ config SOC_EXYNOS5440
 	default y
 	depends on ARCH_EXYNOS5
 	select ARCH_DMA_ADDR_T_64BIT if ARM_LPAE
+	select ARCH_HAS_BANDGAP
 	select ARCH_HAS_OPP
 	select HAVE_ARM_ARCH_TIMER
 	select AUTO_ZRELADDR
diff --git a/arch/arm/mach-exynos/common.h b/arch/arm/mach-exynos/common.h
index 972490fc09d6..8646a141ae46 100644
--- a/arch/arm/mach-exynos/common.h
+++ b/arch/arm/mach-exynos/common.h
@@ -17,7 +17,6 @@
 
 void mct_init(void __iomem *base, int irq_g0, int irq_l0, int irq_l1);
 void exynos_init_time(void);
-extern unsigned long xxti_f, xusbxti_f;
 
 struct map_desc;
 void exynos_init_io(void);
@@ -25,56 +24,14 @@ void exynos4_restart(enum reboot_mode mode, const char *cmd);
 void exynos5_restart(enum reboot_mode mode, const char *cmd);
 void exynos_init_late(void);
 
-/* ToDo: remove these after migrating legacy exynos4 platforms to dt */
-void exynos4_clk_init(struct device_node *np, int is_exynos4210, void __iomem *reg_base, unsigned long xom);
-void exynos4_clk_register_fixed_ext(unsigned long, unsigned long);
-
 void exynos_firmware_init(void);
 
-void exynos_set_timer_source(u8 channels);
-
 #ifdef CONFIG_PM_GENERIC_DOMAINS
 int exynos_pm_late_initcall(void);
 #else
 static inline int exynos_pm_late_initcall(void) { return 0; }
 #endif
 
-#ifdef CONFIG_ARCH_EXYNOS4
-void exynos4_register_clocks(void);
-void exynos4_setup_clocks(void);
-
-#else
-#define exynos4_register_clocks()
-#define exynos4_setup_clocks()
-#endif
-
-#ifdef CONFIG_ARCH_EXYNOS5
-void exynos5_register_clocks(void);
-void exynos5_setup_clocks(void);
-
-#else
-#define exynos5_register_clocks()
-#define exynos5_setup_clocks()
-#endif
-
-#ifdef CONFIG_CPU_EXYNOS4210
-void exynos4210_register_clocks(void);
-
-#else
-#define exynos4210_register_clocks()
-#endif
-
-#ifdef CONFIG_SOC_EXYNOS4212
-void exynos4212_register_clocks(void);
-
-#else
-#define exynos4212_register_clocks()
-#endif
-
-struct device_node;
-void combiner_init(void __iomem *combiner_base, struct device_node *np,
-			unsigned int max_nr, int irq_base);
-
 extern struct smp_operations exynos_smp_ops;
 
 extern void exynos_cpu_die(unsigned int cpu);
diff --git a/arch/arm/mach-exynos/cpuidle.c b/arch/arm/mach-exynos/cpuidle.c
index 225ee8431c72..ac139226d63c 100644
--- a/arch/arm/mach-exynos/cpuidle.c
+++ b/arch/arm/mach-exynos/cpuidle.c
@@ -200,6 +200,9 @@ static int __init exynos4_init_cpuidle(void)
 	if (soc_is_exynos5250())
 		exynos5_core_down_clk();
 
+	if (soc_is_exynos5440())
+		exynos4_idle_driver.state_count = 1;
+
 	ret = cpuidle_register_driver(&exynos4_idle_driver);
 	if (ret) {
 		printk(KERN_ERR "CPUidle failed to register driver\n");
diff --git a/arch/arm/mach-footbridge/include/mach/debug-macro.S b/arch/arm/mach-footbridge/include/mach/debug-macro.S
index c169f0c99b2a..02247f313e94 100644
--- a/arch/arm/mach-footbridge/include/mach/debug-macro.S
+++ b/arch/arm/mach-footbridge/include/mach/debug-macro.S
@@ -13,20 +13,6 @@
 
 #include <asm/hardware/dec21285.h>
 
-#ifndef CONFIG_DEBUG_DC21285_PORT
-	/* For NetWinder debugging */
-		.macro	addruart, rp, rv, tmp
-		mov	\rp, #0x000003f8
-		orr	\rv, \rp, #0xfe000000	@ virtual
-		orr	\rv, \rv, #0x00e00000	@ virtual
-		orr	\rp, \rp, #0x7c000000	@ physical
-		.endm
-
-#define UART_SHIFT	0
-#define FLOW_CONTROL
-#include <asm/hardware/debug-8250.S>
-
-#else
 #include <mach/hardware.h>
 	/* For EBSA285 debugging */
 		.equ	dc21285_high, ARMCSR_BASE & 0xff000000
@@ -54,4 +40,3 @@
 
 		.macro	waituart,rd,rx
 		.endm
-#endif
diff --git a/arch/arm/mach-gemini/include/mach/debug-macro.S b/arch/arm/mach-gemini/include/mach/debug-macro.S
deleted file mode 100644
index 837670763b85..000000000000
--- a/arch/arm/mach-gemini/include/mach/debug-macro.S
+++ /dev/null
@@ -1,21 +0,0 @@
-/*
- * Debugging macro include header
- *
- *  Copyright (C) 1994-1999 Russell King
- *  Copyright (C) 2001-2006 Storlink, Corp.
- *  Copyright (C) 2008-2009 Paulius Zaleckas <paulius.zaleckas@teltonika.lt>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <mach/hardware.h>
-
-	.macro	addruart, rp, rv, tmp
-	ldr	\rp, =GEMINI_UART_BASE			@ physical
-	ldr	\rv, =IO_ADDRESS(GEMINI_UART_BASE)	@ virtual
-	.endm
-
-#define UART_SHIFT	2
-#define FLOW_CONTROL
-#include <asm/hardware/debug-8250.S>
diff --git a/arch/arm/mach-highbank/Kconfig b/arch/arm/mach-highbank/Kconfig
index cd9fcb1cd7ab..8e8437dea3ce 100644
--- a/arch/arm/mach-highbank/Kconfig
+++ b/arch/arm/mach-highbank/Kconfig
@@ -1,9 +1,14 @@
 config ARCH_HIGHBANK
 	bool "Calxeda ECX-1000/2000 (Highbank/Midway)" if ARCH_MULTI_V7
+	select ARCH_DMA_ADDR_T_64BIT if ARM_LPAE
 	select ARCH_HAS_CPUFREQ
+	select ARCH_HAS_HOLES_MEMORYMODEL
 	select ARCH_HAS_OPP
 	select ARCH_WANT_OPTIONAL_GPIOLIB
 	select ARM_AMBA
+	select ARM_ERRATA_764369
+	select ARM_ERRATA_775420
+	select ARM_ERRATA_798181
 	select ARM_GIC
 	select ARM_TIMER_SP804
 	select CACHE_L2X0
@@ -12,9 +17,10 @@ config ARCH_HIGHBANK
 	select CPU_V7
 	select GENERIC_CLOCKEVENTS
 	select HAVE_ARM_SCU
-	select HAVE_ARM_TWD if LOCAL_TIMERS
+	select HAVE_ARM_TWD if SMP
 	select HAVE_SMP
 	select MAILBOX
 	select PL320_MBOX
 	select SPARSE_IRQ
 	select USE_OF
+	select ZONE_DMA if ARM_LPAE
diff --git a/arch/arm/mach-highbank/highbank.c b/arch/arm/mach-highbank/highbank.c
index 88815795fe26..8e63ccdb0de3 100644
--- a/arch/arm/mach-highbank/highbank.c
+++ b/arch/arm/mach-highbank/highbank.c
@@ -18,14 +18,11 @@
 #include <linux/clocksource.h>
 #include <linux/dma-mapping.h>
 #include <linux/io.h>
-#include <linux/irq.h>
 #include <linux/irqchip.h>
-#include <linux/irqdomain.h>
 #include <linux/of.h>
 #include <linux/of_irq.h>
 #include <linux/of_platform.h>
 #include <linux/of_address.h>
-#include <linux/smp.h>
 #include <linux/amba/bus.h>
 #include <linux/clk-provider.h>
 
@@ -35,7 +32,6 @@
 #include <asm/hardware/cache-l2x0.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
-#include <asm/mach/time.h>
 
 #include "core.h"
 #include "sysregs.h"
@@ -65,13 +61,11 @@ void highbank_set_cpu_jump(int cpu, void *jump_addr)
 			  HB_JUMP_TABLE_PHYS(cpu) + 15);
 }
 
-#ifdef CONFIG_CACHE_L2X0
 static void highbank_l2x0_disable(void)
 {
 	/* Disable PL310 L2 Cache controller */
 	highbank_smc1(0x102, 0x0);
 }
-#endif
 
 static void __init highbank_init_irq(void)
 {
@@ -80,12 +74,13 @@ static void __init highbank_init_irq(void)
 	if (of_find_compatible_node(NULL, NULL, "arm,cortex-a9"))
 		highbank_scu_map_io();
 
-#ifdef CONFIG_CACHE_L2X0
 	/* Enable PL310 L2 Cache controller */
-	highbank_smc1(0x102, 0x1);
-	l2x0_of_init(0, ~0UL);
-	outer_cache.disable = highbank_l2x0_disable;
-#endif
+	if (IS_ENABLED(CONFIG_CACHE_L2X0) &&
+	    of_find_compatible_node(NULL, NULL, "arm,pl310-cache")) {
+		highbank_smc1(0x102, 0x1);
+		l2x0_of_init(0, ~0UL);
+		outer_cache.disable = highbank_l2x0_disable;
+	}
 }
 
 static void __init highbank_timer_init(void)
@@ -176,6 +171,9 @@ static const char *highbank_match[] __initconst = {
 };
 
 DT_MACHINE_START(HIGHBANK, "Highbank")
+#if defined(CONFIG_ZONE_DMA) && defined(CONFIG_ARM_LPAE)
+	.dma_zone_size	= (4ULL * SZ_1G),
+#endif
 	.smp		= smp_ops(highbank_smp_ops),
 	.init_irq	= highbank_init_irq,
 	.init_time	= highbank_timer_init,
diff --git a/arch/arm/mach-imx/Kconfig b/arch/arm/mach-imx/Kconfig
index f54656091a9d..29a8af6922a8 100644
--- a/arch/arm/mach-imx/Kconfig
+++ b/arch/arm/mach-imx/Kconfig
@@ -1,6 +1,7 @@
 config ARCH_MXC
 	bool "Freescale i.MX family" if ARCH_MULTI_V4_V5 || ARCH_MULTI_V6_V7
 	select ARCH_REQUIRE_GPIOLIB
+	select ARM_CPU_SUSPEND if PM
 	select ARM_PATCH_PHYS_VIRT
 	select AUTO_ZRELADDR if !ZBOOT_ROM
 	select CLKDEV_LOOKUP
@@ -8,6 +9,7 @@ config ARCH_MXC
 	select GENERIC_ALLOCATOR
 	select GENERIC_CLOCKEVENTS
 	select GENERIC_IRQ_CHIP
+	select MIGHT_HAVE_CACHE_L2X0 if ARCH_MULTI_V6_V7
 	select MULTI_IRQ_HANDLER
 	select SPARSE_IRQ
 	select USE_OF
@@ -785,7 +787,6 @@ config SOC_IMX6Q
 	bool "i.MX6 Quad/DualLite support"
 	select ARCH_HAS_CPUFREQ
 	select ARCH_HAS_OPP
-	select ARM_CPU_SUSPEND if PM
 	select ARM_ERRATA_754322
 	select ARM_ERRATA_764369 if SMP
 	select ARM_ERRATA_775420
@@ -793,7 +794,7 @@ config SOC_IMX6Q
 	select COMMON_CLK
 	select CPU_V7
 	select HAVE_ARM_SCU if SMP
-	select HAVE_ARM_TWD if LOCAL_TIMERS
+	select HAVE_ARM_TWD if SMP
 	select HAVE_IMX_ANATOP
 	select HAVE_IMX_GPC
 	select HAVE_IMX_MMDC
diff --git a/arch/arm/mach-imx/Makefile b/arch/arm/mach-imx/Makefile
index e20f22d58fd8..5383c589ad71 100644
--- a/arch/arm/mach-imx/Makefile
+++ b/arch/arm/mach-imx/Makefile
@@ -15,7 +15,8 @@ imx5-pm-$(CONFIG_PM) += pm-imx5.o
 obj-$(CONFIG_SOC_IMX5) += cpu-imx5.o mm-imx5.o clk-imx51-imx53.o ehci-imx5.o $(imx5-pm-y)
 
 obj-$(CONFIG_COMMON_CLK) += clk-pllv1.o clk-pllv2.o clk-pllv3.o clk-gate2.o \
-			    clk-pfd.o clk-busy.o clk.o
+			    clk-pfd.o clk-busy.o clk.o \
+			    clk-fixup-div.o clk-fixup-mux.o
 
 obj-$(CONFIG_IMX_HAVE_IOMUX_V1) += iomux-v1.o
 obj-$(CONFIG_ARCH_MXC_IOMUX_V3) += iomux-v3.o
diff --git a/arch/arm/mach-imx/anatop.c b/arch/arm/mach-imx/anatop.c
index 0cfa07dd9aa4..ad3b755abb78 100644
--- a/arch/arm/mach-imx/anatop.c
+++ b/arch/arm/mach-imx/anatop.c
@@ -66,7 +66,7 @@ void imx_anatop_post_resume(void)
 	imx_anatop_enable_weak2p5(false);
 }
 
-void imx_anatop_usb_chrg_detect_disable(void)
+static void imx_anatop_usb_chrg_detect_disable(void)
 {
 	regmap_write(anatop, ANADIG_USB1_CHRG_DETECT,
 		BM_ANADIG_USB_CHRG_DETECT_EN_B
@@ -100,4 +100,6 @@ void __init imx_anatop_init(void)
 		pr_err("%s: failed to find imx6q-anatop regmap!\n", __func__);
 		return;
 	}
+
+	imx_anatop_usb_chrg_detect_disable();
 }
diff --git a/arch/arm/mach-imx/clk-fixup-div.c b/arch/arm/mach-imx/clk-fixup-div.c
new file mode 100644
index 000000000000..21db020b1f2d
--- /dev/null
+++ b/arch/arm/mach-imx/clk-fixup-div.c
@@ -0,0 +1,129 @@
+/*
+ * Copyright (C) 2013 Freescale Semiconductor, Inc.
+ *
+ * The code contained herein is licensed under the GNU General Public
+ * License. You may obtain a copy of the GNU General Public License
+ * Version 2 or later at the following locations:
+ *
+ * http://www.opensource.org/licenses/gpl-license.html
+ * http://www.gnu.org/copyleft/gpl.html
+ */
+
+#include <linux/clk-provider.h>
+#include <linux/err.h>
+#include <linux/io.h>
+#include <linux/slab.h>
+#include "clk.h"
+
+#define to_clk_div(_hw) container_of(_hw, struct clk_divider, hw)
+#define div_mask(d)	((1 << (d->width)) - 1)
+
+/**
+ * struct clk_fixup_div - imx integer fixup divider clock
+ * @divider: the parent class
+ * @ops: pointer to clk_ops of parent class
+ * @fixup: a hook to fixup the write value
+ *
+ * The imx fixup divider clock is a subclass of basic clk_divider
+ * with an addtional fixup hook.
+ */
+struct clk_fixup_div {
+	struct clk_divider divider;
+	const struct clk_ops *ops;
+	void (*fixup)(u32 *val);
+};
+
+static inline struct clk_fixup_div *to_clk_fixup_div(struct clk_hw *hw)
+{
+	struct clk_divider *divider = to_clk_div(hw);
+
+	return container_of(divider, struct clk_fixup_div, divider);
+}
+
+static unsigned long clk_fixup_div_recalc_rate(struct clk_hw *hw,
+					 unsigned long parent_rate)
+{
+	struct clk_fixup_div *fixup_div = to_clk_fixup_div(hw);
+
+	return fixup_div->ops->recalc_rate(&fixup_div->divider.hw, parent_rate);
+}
+
+static long clk_fixup_div_round_rate(struct clk_hw *hw, unsigned long rate,
+			       unsigned long *prate)
+{
+	struct clk_fixup_div *fixup_div = to_clk_fixup_div(hw);
+
+	return fixup_div->ops->round_rate(&fixup_div->divider.hw, rate, prate);
+}
+
+static int clk_fixup_div_set_rate(struct clk_hw *hw, unsigned long rate,
+			    unsigned long parent_rate)
+{
+	struct clk_fixup_div *fixup_div = to_clk_fixup_div(hw);
+	struct clk_divider *div = to_clk_div(hw);
+	unsigned int divider, value;
+	unsigned long flags = 0;
+	u32 val;
+
+	divider = parent_rate / rate;
+
+	/* Zero based divider */
+	value = divider - 1;
+
+	if (value > div_mask(div))
+		value = div_mask(div);
+
+	spin_lock_irqsave(div->lock, flags);
+
+	val = readl(div->reg);
+	val &= ~(div_mask(div) << div->shift);
+	val |= value << div->shift;
+	fixup_div->fixup(&val);
+	writel(val, div->reg);
+
+	spin_unlock_irqrestore(div->lock, flags);
+
+	return 0;
+}
+
+static const struct clk_ops clk_fixup_div_ops = {
+	.recalc_rate = clk_fixup_div_recalc_rate,
+	.round_rate = clk_fixup_div_round_rate,
+	.set_rate = clk_fixup_div_set_rate,
+};
+
+struct clk *imx_clk_fixup_divider(const char *name, const char *parent,
+				  void __iomem *reg, u8 shift, u8 width,
+				  void (*fixup)(u32 *val))
+{
+	struct clk_fixup_div *fixup_div;
+	struct clk *clk;
+	struct clk_init_data init;
+
+	if (!fixup)
+		return ERR_PTR(-EINVAL);
+
+	fixup_div = kzalloc(sizeof(*fixup_div), GFP_KERNEL);
+	if (!fixup_div)
+		return ERR_PTR(-ENOMEM);
+
+	init.name = name;
+	init.ops = &clk_fixup_div_ops;
+	init.flags = CLK_SET_RATE_PARENT;
+	init.parent_names = parent ? &parent : NULL;
+	init.num_parents = parent ? 1 : 0;
+
+	fixup_div->divider.reg = reg;
+	fixup_div->divider.shift = shift;
+	fixup_div->divider.width = width;
+	fixup_div->divider.lock = &imx_ccm_lock;
+	fixup_div->divider.hw.init = &init;
+	fixup_div->ops = &clk_divider_ops;
+	fixup_div->fixup = fixup;
+
+	clk = clk_register(NULL, &fixup_div->divider.hw);
+	if (IS_ERR(clk))
+		kfree(fixup_div);
+
+	return clk;
+}
diff --git a/arch/arm/mach-imx/clk-fixup-mux.c b/arch/arm/mach-imx/clk-fixup-mux.c
new file mode 100644
index 000000000000..0d40b35c557c
--- /dev/null
+++ b/arch/arm/mach-imx/clk-fixup-mux.c
@@ -0,0 +1,108 @@
+/*
+ * Copyright (C) 2013 Freescale Semiconductor, Inc.
+ *
+ * The code contained herein is licensed under the GNU General Public
+ * License. You may obtain a copy of the GNU General Public License
+ * Version 2 or later at the following locations:
+ *
+ * http://www.opensource.org/licenses/gpl-license.html
+ * http://www.gnu.org/copyleft/gpl.html
+ */
+
+#include <linux/clk-provider.h>
+#include <linux/err.h>
+#include <linux/io.h>
+#include <linux/slab.h>
+#include "clk.h"
+
+#define to_clk_mux(_hw) container_of(_hw, struct clk_mux, hw)
+
+/**
+ * struct clk_fixup_mux - imx integer fixup multiplexer clock
+ * @mux: the parent class
+ * @ops: pointer to clk_ops of parent class
+ * @fixup: a hook to fixup the write value
+ *
+ * The imx fixup multiplexer clock is a subclass of basic clk_mux
+ * with an addtional fixup hook.
+ */
+struct clk_fixup_mux {
+	struct clk_mux mux;
+	const struct clk_ops *ops;
+	void (*fixup)(u32 *val);
+};
+
+static inline struct clk_fixup_mux *to_clk_fixup_mux(struct clk_hw *hw)
+{
+	struct clk_mux *mux = to_clk_mux(hw);
+
+	return container_of(mux, struct clk_fixup_mux, mux);
+}
+
+static u8 clk_fixup_mux_get_parent(struct clk_hw *hw)
+{
+	struct clk_fixup_mux *fixup_mux = to_clk_fixup_mux(hw);
+
+	return fixup_mux->ops->get_parent(&fixup_mux->mux.hw);
+}
+
+static int clk_fixup_mux_set_parent(struct clk_hw *hw, u8 index)
+{
+	struct clk_fixup_mux *fixup_mux = to_clk_fixup_mux(hw);
+	struct clk_mux *mux = to_clk_mux(hw);
+	unsigned long flags = 0;
+	u32 val;
+
+	spin_lock_irqsave(mux->lock, flags);
+
+	val = readl(mux->reg);
+	val &= ~(mux->mask << mux->shift);
+	val |= index << mux->shift;
+	fixup_mux->fixup(&val);
+	writel(val, mux->reg);
+
+	spin_unlock_irqrestore(mux->lock, flags);
+
+	return 0;
+}
+
+static const struct clk_ops clk_fixup_mux_ops = {
+	.get_parent = clk_fixup_mux_get_parent,
+	.set_parent = clk_fixup_mux_set_parent,
+};
+
+struct clk *imx_clk_fixup_mux(const char *name, void __iomem *reg,
+			      u8 shift, u8 width, const char **parents,
+			      int num_parents, void (*fixup)(u32 *val))
+{
+	struct clk_fixup_mux *fixup_mux;
+	struct clk *clk;
+	struct clk_init_data init;
+
+	if (!fixup)
+		return ERR_PTR(-EINVAL);
+
+	fixup_mux = kzalloc(sizeof(*fixup_mux), GFP_KERNEL);
+	if (!fixup_mux)
+		return ERR_PTR(-ENOMEM);
+
+	init.name = name;
+	init.ops = &clk_fixup_mux_ops;
+	init.parent_names = parents;
+	init.num_parents = num_parents;
+	init.flags = 0;
+
+	fixup_mux->mux.reg = reg;
+	fixup_mux->mux.shift = shift;
+	fixup_mux->mux.mask = BIT(width) - 1;
+	fixup_mux->mux.lock = &imx_ccm_lock;
+	fixup_mux->mux.hw.init = &init;
+	fixup_mux->ops = &clk_mux_ops;
+	fixup_mux->fixup = fixup;
+
+	clk = clk_register(NULL, &fixup_mux->mux.hw);
+	if (IS_ERR(clk))
+		kfree(fixup_mux);
+
+	return clk;
+}
diff --git a/arch/arm/mach-imx/clk-imx27.c b/arch/arm/mach-imx/clk-imx27.c
index c3cfa4116dc0..c6b40f386786 100644
--- a/arch/arm/mach-imx/clk-imx27.c
+++ b/arch/arm/mach-imx/clk-imx27.c
@@ -285,7 +285,7 @@ int __init mx27_clocks_init(unsigned long fref)
 	clk_register_clkdev(clk[ata_ahb_gate], "ata", NULL);
 	clk_register_clkdev(clk[rtc_ipg_gate], NULL, "imx21-rtc");
 	clk_register_clkdev(clk[scc_ipg_gate], "scc", NULL);
-	clk_register_clkdev(clk[cpu_div], NULL, "cpufreq-cpu0.0");
+	clk_register_clkdev(clk[cpu_div], NULL, "cpu0");
 	clk_register_clkdev(clk[emi_ahb_gate], "emi_ahb" , NULL);
 
 	mxc_timer_init(MX27_IO_ADDRESS(MX27_GPT1_BASE_ADDR), MX27_INT_GPT1);
diff --git a/arch/arm/mach-imx/clk-imx51-imx53.c b/arch/arm/mach-imx/clk-imx51-imx53.c
index 9afac26fa1cc..7c0dc4540aa4 100644
--- a/arch/arm/mach-imx/clk-imx51-imx53.c
+++ b/arch/arm/mach-imx/clk-imx51-imx53.c
@@ -119,7 +119,7 @@ enum imx5_clks {
 	srtc_gate, pata_gate, sata_gate, spdif_xtal_sel, spdif0_sel,
 	spdif1_sel, spdif0_pred, spdif0_podf, spdif1_pred, spdif1_podf,
 	spdif0_com_s, spdif1_com_sel, spdif0_gate, spdif1_gate, spdif_ipg_gate,
-	clk_max
+	ocram, clk_max
 };
 
 static struct clk *clk[clk_max];
@@ -328,7 +328,7 @@ static void __init mx5_clocks_common_init(unsigned long rate_ckil,
 	clk_register_clkdev(clk[ssi2_ipg_gate], NULL, "imx-ssi.1");
 	clk_register_clkdev(clk[ssi3_ipg_gate], NULL, "imx-ssi.2");
 	clk_register_clkdev(clk[sdma_gate], NULL, "imx35-sdma");
-	clk_register_clkdev(clk[cpu_podf], NULL, "cpufreq-cpu0.0");
+	clk_register_clkdev(clk[cpu_podf], NULL, "cpu0");
 	clk_register_clkdev(clk[iim_gate], "iim", NULL);
 	clk_register_clkdev(clk[dummy], NULL, "imx2-wdt.0");
 	clk_register_clkdev(clk[dummy], NULL, "imx2-wdt.1");
@@ -397,7 +397,7 @@ int __init mx51_clocks_init(unsigned long rate_ckil, unsigned long rate_osc,
 				mx51_spdif_xtal_sel, ARRAY_SIZE(mx51_spdif_xtal_sel));
 	clk[spdif1_sel] = imx_clk_mux("spdif1_sel", MXC_CCM_CSCMR2, 2, 2,
 				spdif_sel, ARRAY_SIZE(spdif_sel));
-	clk[spdif1_pred] = imx_clk_divider("spdif1_podf", "spdif1_sel", MXC_CCM_CDCDR, 16, 3);
+	clk[spdif1_pred] = imx_clk_divider("spdif1_pred", "spdif1_sel", MXC_CCM_CDCDR, 16, 3);
 	clk[spdif1_podf] = imx_clk_divider("spdif1_podf", "spdif1_pred", MXC_CCM_CDCDR, 9, 6);
 	clk[spdif1_com_sel] = imx_clk_mux("spdif1_com_sel", MXC_CCM_CSCMR2, 5, 1,
 				mx51_spdif1_com_sel, ARRAY_SIZE(mx51_spdif1_com_sel));
@@ -506,6 +506,7 @@ int __init mx53_clocks_init(unsigned long rate_ckil, unsigned long rate_osc,
 				mx53_can_sel, ARRAY_SIZE(mx53_can_sel));
 	clk[can1_serial_gate] = imx_clk_gate2("can1_serial_gate", "can_sel", MXC_CCM_CCGR6, 22);
 	clk[can1_ipg_gate] = imx_clk_gate2("can1_ipg_gate", "ipg", MXC_CCM_CCGR6, 20);
+	clk[ocram] = imx_clk_gate2("ocram", "ahb", MXC_CCM_CCGR6, 2);
 	clk[can2_serial_gate] = imx_clk_gate2("can2_serial_gate", "can_sel", MXC_CCM_CCGR4, 8);
 	clk[can2_ipg_gate] = imx_clk_gate2("can2_ipg_gate", "ipg", MXC_CCM_CCGR4, 6);
 	clk[i2c3_gate] = imx_clk_gate2("i2c3_gate", "per_root", MXC_CCM_CCGR1, 22);
diff --git a/arch/arm/mach-imx/clk-imx6q.c b/arch/arm/mach-imx/clk-imx6q.c
index 86567d980b07..9181a241d3a8 100644
--- a/arch/arm/mach-imx/clk-imx6q.c
+++ b/arch/arm/mach-imx/clk-imx6q.c
@@ -206,6 +206,17 @@ static const char *vpu_axi_sels[]	= { "axi", "pll2_pfd2_396m", "pll2_pfd0_352m",
 static const char *cko1_sels[]	= { "pll3_usb_otg", "pll2_bus", "pll1_sys", "pll5_video_div",
 				    "dummy", "axi", "enfc", "ipu1_di0", "ipu1_di1", "ipu2_di0",
 				    "ipu2_di1", "ahb", "ipg", "ipg_per", "ckil", "pll4_post_div", };
+static const char *cko2_sels[] = {
+	"mmdc_ch0_axi", "mmdc_ch1_axi", "usdhc4", "usdhc1",
+	"gpu2d_axi", "dummy", "ecspi_root", "gpu3d_axi",
+	"usdhc3", "dummy", "arm", "ipu1",
+	"ipu2", "vdo_axi", "osc", "gpu2d_core",
+	"gpu3d_core", "usdhc2", "ssi1", "ssi2",
+	"ssi3", "gpu3d_shader", "vpu_axi", "can_root",
+	"ldb_di0", "ldb_di1", "esai", "eim_slow",
+	"uart_serial", "spdif", "asrc", "hsi_tx",
+};
+static const char *cko_sels[] = { "cko1", "cko2", };
 
 enum mx6q_clks {
 	dummy, ckil, ckih, osc, pll2_pfd0_352m, pll2_pfd1_594m, pll2_pfd2_396m,
@@ -239,7 +250,8 @@ enum mx6q_clks {
 	pll4_audio, pll5_video, pll8_mlb, pll7_usb_host, pll6_enet, ssi1_ipg,
 	ssi2_ipg, ssi3_ipg, rom, usbphy1, usbphy2, ldb_di0_div_3_5, ldb_di1_div_3_5,
 	sata_ref, sata_ref_100m, pcie_ref, pcie_ref_125m, enet_ref, usbphy1_gate,
-	usbphy2_gate, pll4_post_div, pll5_post_div, pll5_video_div, eim_slow, clk_max
+	usbphy2_gate, pll4_post_div, pll5_post_div, pll5_video_div, eim_slow,
+	spdif, cko2_sel, cko2_podf, cko2, cko, vdoa, clk_max
 };
 
 static struct clk *clk[clk_max];
@@ -276,6 +288,7 @@ static void __init imx6q_clocks_init(struct device_node *ccm_node)
 	struct device_node *np;
 	void __iomem *base;
 	int i, irq;
+	int ret;
 
 	clk[dummy] = imx_clk_fixed("dummy", 0);
 	clk[ckil] = imx_obtain_fixed_clock("ckil", 0);
@@ -384,19 +397,21 @@ static void __init imx6q_clocks_init(struct device_node *ccm_node)
 	clk[ipu2_di1_sel]     = imx_clk_mux("ipu2_di1_sel",     base + 0x38, 9,  3, ipu2_di1_sels,     ARRAY_SIZE(ipu2_di1_sels));
 	clk[hsi_tx_sel]       = imx_clk_mux("hsi_tx_sel",       base + 0x30, 28, 1, hsi_tx_sels,       ARRAY_SIZE(hsi_tx_sels));
 	clk[pcie_axi_sel]     = imx_clk_mux("pcie_axi_sel",     base + 0x18, 10, 1, pcie_axi_sels,     ARRAY_SIZE(pcie_axi_sels));
-	clk[ssi1_sel]         = imx_clk_mux("ssi1_sel",         base + 0x1c, 10, 2, ssi_sels,          ARRAY_SIZE(ssi_sels));
-	clk[ssi2_sel]         = imx_clk_mux("ssi2_sel",         base + 0x1c, 12, 2, ssi_sels,          ARRAY_SIZE(ssi_sels));
-	clk[ssi3_sel]         = imx_clk_mux("ssi3_sel",         base + 0x1c, 14, 2, ssi_sels,          ARRAY_SIZE(ssi_sels));
-	clk[usdhc1_sel]       = imx_clk_mux("usdhc1_sel",       base + 0x1c, 16, 1, usdhc_sels,        ARRAY_SIZE(usdhc_sels));
-	clk[usdhc2_sel]       = imx_clk_mux("usdhc2_sel",       base + 0x1c, 17, 1, usdhc_sels,        ARRAY_SIZE(usdhc_sels));
-	clk[usdhc3_sel]       = imx_clk_mux("usdhc3_sel",       base + 0x1c, 18, 1, usdhc_sels,        ARRAY_SIZE(usdhc_sels));
-	clk[usdhc4_sel]       = imx_clk_mux("usdhc4_sel",       base + 0x1c, 19, 1, usdhc_sels,        ARRAY_SIZE(usdhc_sels));
+	clk[ssi1_sel]         = imx_clk_fixup_mux("ssi1_sel",   base + 0x1c, 10, 2, ssi_sels,          ARRAY_SIZE(ssi_sels),          imx_cscmr1_fixup);
+	clk[ssi2_sel]         = imx_clk_fixup_mux("ssi2_sel",   base + 0x1c, 12, 2, ssi_sels,          ARRAY_SIZE(ssi_sels),          imx_cscmr1_fixup);
+	clk[ssi3_sel]         = imx_clk_fixup_mux("ssi3_sel",   base + 0x1c, 14, 2, ssi_sels,          ARRAY_SIZE(ssi_sels),          imx_cscmr1_fixup);
+	clk[usdhc1_sel]       = imx_clk_fixup_mux("usdhc1_sel", base + 0x1c, 16, 1, usdhc_sels,        ARRAY_SIZE(usdhc_sels),        imx_cscmr1_fixup);
+	clk[usdhc2_sel]       = imx_clk_fixup_mux("usdhc2_sel", base + 0x1c, 17, 1, usdhc_sels,        ARRAY_SIZE(usdhc_sels),        imx_cscmr1_fixup);
+	clk[usdhc3_sel]       = imx_clk_fixup_mux("usdhc3_sel", base + 0x1c, 18, 1, usdhc_sels,        ARRAY_SIZE(usdhc_sels),        imx_cscmr1_fixup);
+	clk[usdhc4_sel]       = imx_clk_fixup_mux("usdhc4_sel", base + 0x1c, 19, 1, usdhc_sels,        ARRAY_SIZE(usdhc_sels),        imx_cscmr1_fixup);
 	clk[enfc_sel]         = imx_clk_mux("enfc_sel",         base + 0x2c, 16, 2, enfc_sels,         ARRAY_SIZE(enfc_sels));
-	clk[emi_sel]          = imx_clk_mux("emi_sel",          base + 0x1c, 27, 2, emi_sels,          ARRAY_SIZE(emi_sels));
-	clk[emi_slow_sel]     = imx_clk_mux("emi_slow_sel",     base + 0x1c, 29, 2, emi_slow_sels,     ARRAY_SIZE(emi_slow_sels));
+	clk[emi_sel]          = imx_clk_fixup_mux("emi_sel",      base + 0x1c, 27, 2, emi_sels,        ARRAY_SIZE(emi_sels),          imx_cscmr1_fixup);
+	clk[emi_slow_sel]     = imx_clk_fixup_mux("emi_slow_sel", base + 0x1c, 29, 2, emi_slow_sels,   ARRAY_SIZE(emi_slow_sels),     imx_cscmr1_fixup);
 	clk[vdo_axi_sel]      = imx_clk_mux("vdo_axi_sel",      base + 0x18, 11, 1, vdo_axi_sels,      ARRAY_SIZE(vdo_axi_sels));
 	clk[vpu_axi_sel]      = imx_clk_mux("vpu_axi_sel",      base + 0x18, 14, 2, vpu_axi_sels,      ARRAY_SIZE(vpu_axi_sels));
 	clk[cko1_sel]         = imx_clk_mux("cko1_sel",         base + 0x60, 0,  4, cko1_sels,         ARRAY_SIZE(cko1_sels));
+	clk[cko2_sel]         = imx_clk_mux("cko2_sel",         base + 0x60, 16, 5, cko2_sels,         ARRAY_SIZE(cko2_sels));
+	clk[cko]              = imx_clk_mux("cko",              base + 0x60, 8, 1,  cko_sels,          ARRAY_SIZE(cko_sels));
 
 	/*                              name         reg      shift width busy: reg, shift parent_names  num_parents */
 	clk[periph]  = imx_clk_busy_mux("periph",  base + 0x14, 25,  1,   base + 0x48, 5,  periph_sels,  ARRAY_SIZE(periph_sels));
@@ -406,7 +421,7 @@ static void __init imx6q_clocks_init(struct device_node *ccm_node)
 	clk[periph_clk2]      = imx_clk_divider("periph_clk2",      "periph_clk2_sel",   base + 0x14, 27, 3);
 	clk[periph2_clk2]     = imx_clk_divider("periph2_clk2",     "periph2_clk2_sel",  base + 0x14, 0,  3);
 	clk[ipg]              = imx_clk_divider("ipg",              "ahb",               base + 0x14, 8,  2);
-	clk[ipg_per]          = imx_clk_divider("ipg_per",          "ipg",               base + 0x1c, 0,  6);
+	clk[ipg_per]          = imx_clk_fixup_divider("ipg_per",    "ipg",               base + 0x1c, 0,  6, imx_cscmr1_fixup);
 	clk[esai_pred]        = imx_clk_divider("esai_pred",        "esai_sel",          base + 0x28, 9,  3);
 	clk[esai_podf]        = imx_clk_divider("esai_podf",        "esai_pred",         base + 0x28, 25, 3);
 	clk[asrc_pred]        = imx_clk_divider("asrc_pred",        "asrc_sel",          base + 0x30, 12, 3);
@@ -442,10 +457,11 @@ static void __init imx6q_clocks_init(struct device_node *ccm_node)
 	clk[usdhc4_podf]      = imx_clk_divider("usdhc4_podf",      "usdhc4_sel",        base + 0x24, 22, 3);
 	clk[enfc_pred]        = imx_clk_divider("enfc_pred",        "enfc_sel",          base + 0x2c, 18, 3);
 	clk[enfc_podf]        = imx_clk_divider("enfc_podf",        "enfc_pred",         base + 0x2c, 21, 6);
-	clk[emi_podf]         = imx_clk_divider("emi_podf",         "emi_sel",           base + 0x1c, 20, 3);
-	clk[emi_slow_podf]    = imx_clk_divider("emi_slow_podf",    "emi_slow_sel",      base + 0x1c, 23, 3);
+	clk[emi_podf]         = imx_clk_fixup_divider("emi_podf",   "emi_sel",           base + 0x1c, 20, 3, imx_cscmr1_fixup);
+	clk[emi_slow_podf]    = imx_clk_fixup_divider("emi_slow_podf", "emi_slow_sel",   base + 0x1c, 23, 3, imx_cscmr1_fixup);
 	clk[vpu_axi_podf]     = imx_clk_divider("vpu_axi_podf",     "vpu_axi_sel",       base + 0x24, 25, 3);
 	clk[cko1_podf]        = imx_clk_divider("cko1_podf",        "cko1_sel",          base + 0x60, 4,  3);
+	clk[cko2_podf]        = imx_clk_divider("cko2_podf",        "cko2_sel",          base + 0x60, 21, 3);
 
 	/*                                            name                 parent_name    reg        shift width busy: reg, shift */
 	clk[axi]               = imx_clk_busy_divider("axi",               "axi_sel",     base + 0x14, 16,  3,   base + 0x48, 0);
@@ -486,6 +502,7 @@ static void __init imx6q_clocks_init(struct device_node *ccm_node)
 	clk[i2c3]         = imx_clk_gate2("i2c3",          "ipg_per",           base + 0x70, 10);
 	clk[iim]          = imx_clk_gate2("iim",           "ipg",               base + 0x70, 12);
 	clk[enfc]         = imx_clk_gate2("enfc",          "enfc_podf",         base + 0x70, 14);
+	clk[vdoa]         = imx_clk_gate2("vdoa",          "vdo_axi",           base + 0x70, 26);
 	clk[ipu1]         = imx_clk_gate2("ipu1",          "ipu1_podf",         base + 0x74, 0);
 	clk[ipu1_di0]     = imx_clk_gate2("ipu1_di0",      "ipu1_di0_sel",      base + 0x74, 2);
 	clk[ipu1_di1]     = imx_clk_gate2("ipu1_di1",      "ipu1_di1_sel",      base + 0x74, 4);
@@ -521,6 +538,7 @@ static void __init imx6q_clocks_init(struct device_node *ccm_node)
 	clk[sata]         = imx_clk_gate2("sata",          "ipg",               base + 0x7c, 4);
 	clk[sdma]         = imx_clk_gate2("sdma",          "ahb",               base + 0x7c, 6);
 	clk[spba]         = imx_clk_gate2("spba",          "ipg",               base + 0x7c, 12);
+	clk[spdif]        = imx_clk_gate2("spdif",         "spdif_podf",    	base + 0x7c, 14);
 	clk[ssi1_ipg]     = imx_clk_gate2("ssi1_ipg",      "ipg",               base + 0x7c, 18);
 	clk[ssi2_ipg]     = imx_clk_gate2("ssi2_ipg",      "ipg",               base + 0x7c, 20);
 	clk[ssi3_ipg]     = imx_clk_gate2("ssi3_ipg",      "ipg",               base + 0x7c, 22);
@@ -535,6 +553,7 @@ static void __init imx6q_clocks_init(struct device_node *ccm_node)
 	clk[vdo_axi]      = imx_clk_gate2("vdo_axi",       "vdo_axi_sel",       base + 0x80, 12);
 	clk[vpu_axi]      = imx_clk_gate2("vpu_axi",       "vpu_axi_podf",      base + 0x80, 14);
 	clk[cko1]         = imx_clk_gate("cko1",           "cko1_podf",         base + 0x60, 7);
+	clk[cko2]         = imx_clk_gate("cko2",           "cko2_podf",         base + 0x60, 24);
 
 	for (i = 0; i < ARRAY_SIZE(clk); i++)
 		if (IS_ERR(clk[i]))
@@ -554,7 +573,7 @@ static void __init imx6q_clocks_init(struct device_node *ccm_node)
 	clk_register_clkdev(clk[pll4_post_div], "pll4_post_div", NULL);
 	clk_register_clkdev(clk[pll4_audio], "pll4_audio", NULL);
 
-	if (imx6q_revision() != IMX_CHIP_REVISION_1_0) {
+	if ((imx6q_revision() != IMX_CHIP_REVISION_1_0) || cpu_is_imx6dl()) {
 		clk_set_parent(clk[ldb_di0_sel], clk[pll5_video_div]);
 		clk_set_parent(clk[ldb_di1_sel], clk[pll5_video_div]);
 	}
@@ -574,6 +593,16 @@ static void __init imx6q_clocks_init(struct device_node *ccm_node)
 		clk_prepare_enable(clk[usbphy2_gate]);
 	}
 
+	/*
+	 * Let's initially set up CLKO with OSC24M, since this configuration
+	 * is widely used by imx6q board designs to clock audio codec.
+	 */
+	ret = clk_set_parent(clk[cko2_sel], clk[osc]);
+	if (!ret)
+		ret = clk_set_parent(clk[cko], clk[cko2]);
+	if (ret)
+		pr_warn("failed to set up CLKO: %d\n", ret);
+
 	/* Set initial power mode */
 	imx6q_set_lpm(WAIT_CLOCKED);
 
diff --git a/arch/arm/mach-imx/clk-imx6sl.c b/arch/arm/mach-imx/clk-imx6sl.c
index a307ac22dffe..a5c3c5d21aee 100644
--- a/arch/arm/mach-imx/clk-imx6sl.c
+++ b/arch/arm/mach-imx/clk-imx6sl.c
@@ -138,14 +138,14 @@ static void __init imx6sl_clocks_init(struct device_node *ccm_node)
 	clks[IMX6SL_CLK_PERIPH_CLK2_SEL]  = imx_clk_mux("periph_clk2_sel",  base + 0x18, 12, 2, periph_clk2_sels,  ARRAY_SIZE(periph_clk2_sels));
 	clks[IMX6SL_CLK_CSI_SEL]          = imx_clk_mux("csi_sel",          base + 0x3c, 9,  2, csi_lcdif_sels,    ARRAY_SIZE(csi_lcdif_sels));
 	clks[IMX6SL_CLK_LCDIF_AXI_SEL]    = imx_clk_mux("lcdif_axi_sel",    base + 0x3c, 14, 2, csi_lcdif_sels,    ARRAY_SIZE(csi_lcdif_sels));
-	clks[IMX6SL_CLK_USDHC1_SEL]       = imx_clk_mux("usdhc1_sel",       base + 0x1c, 16, 1, usdhc_sels,        ARRAY_SIZE(usdhc_sels));
-	clks[IMX6SL_CLK_USDHC2_SEL]       = imx_clk_mux("usdhc2_sel",       base + 0x1c, 17, 1, usdhc_sels,        ARRAY_SIZE(usdhc_sels));
-	clks[IMX6SL_CLK_USDHC3_SEL]       = imx_clk_mux("usdhc3_sel",       base + 0x1c, 18, 1, usdhc_sels,        ARRAY_SIZE(usdhc_sels));
-	clks[IMX6SL_CLK_USDHC4_SEL]       = imx_clk_mux("usdhc4_sel",       base + 0x1c, 19, 1, usdhc_sels,        ARRAY_SIZE(usdhc_sels));
-	clks[IMX6SL_CLK_SSI1_SEL]         = imx_clk_mux("ssi1_sel",         base + 0x1c, 10, 2, ssi_sels,          ARRAY_SIZE(ssi_sels));
-	clks[IMX6SL_CLK_SSI2_SEL]         = imx_clk_mux("ssi2_sel",         base + 0x1c, 12, 2, ssi_sels,          ARRAY_SIZE(ssi_sels));
-	clks[IMX6SL_CLK_SSI3_SEL]         = imx_clk_mux("ssi3_sel",         base + 0x1c, 14, 2, ssi_sels,          ARRAY_SIZE(ssi_sels));
-	clks[IMX6SL_CLK_PERCLK_SEL]       = imx_clk_mux("perclk_sel",       base + 0x1c, 6,  1, perclk_sels,       ARRAY_SIZE(perclk_sels));
+	clks[IMX6SL_CLK_USDHC1_SEL]       = imx_clk_fixup_mux("usdhc1_sel", base + 0x1c, 16, 1, usdhc_sels,        ARRAY_SIZE(usdhc_sels),  imx_cscmr1_fixup);
+	clks[IMX6SL_CLK_USDHC2_SEL]       = imx_clk_fixup_mux("usdhc2_sel", base + 0x1c, 17, 1, usdhc_sels,        ARRAY_SIZE(usdhc_sels),  imx_cscmr1_fixup);
+	clks[IMX6SL_CLK_USDHC3_SEL]       = imx_clk_fixup_mux("usdhc3_sel", base + 0x1c, 18, 1, usdhc_sels,        ARRAY_SIZE(usdhc_sels),  imx_cscmr1_fixup);
+	clks[IMX6SL_CLK_USDHC4_SEL]       = imx_clk_fixup_mux("usdhc4_sel", base + 0x1c, 19, 1, usdhc_sels,        ARRAY_SIZE(usdhc_sels),  imx_cscmr1_fixup);
+	clks[IMX6SL_CLK_SSI1_SEL]         = imx_clk_fixup_mux("ssi1_sel",   base + 0x1c, 10, 2, ssi_sels,          ARRAY_SIZE(ssi_sels),    imx_cscmr1_fixup);
+	clks[IMX6SL_CLK_SSI2_SEL]         = imx_clk_fixup_mux("ssi2_sel",   base + 0x1c, 12, 2, ssi_sels,          ARRAY_SIZE(ssi_sels),    imx_cscmr1_fixup);
+	clks[IMX6SL_CLK_SSI3_SEL]         = imx_clk_fixup_mux("ssi3_sel",   base + 0x1c, 14, 2, ssi_sels,          ARRAY_SIZE(ssi_sels),    imx_cscmr1_fixup);
+	clks[IMX6SL_CLK_PERCLK_SEL]       = imx_clk_fixup_mux("perclk_sel", base + 0x1c, 6,  1, perclk_sels,       ARRAY_SIZE(perclk_sels), imx_cscmr1_fixup);
 	clks[IMX6SL_CLK_PXP_AXI_SEL]      = imx_clk_mux("pxp_axi_sel",      base + 0x34, 6,  3, epdc_pxp_sels,     ARRAY_SIZE(epdc_pxp_sels));
 	clks[IMX6SL_CLK_EPDC_AXI_SEL]     = imx_clk_mux("epdc_axi_sel",     base + 0x34, 15, 3, epdc_pxp_sels,     ARRAY_SIZE(epdc_pxp_sels));
 	clks[IMX6SL_CLK_GPU2D_OVG_SEL]    = imx_clk_mux("gpu2d_ovg_sel",    base + 0x18, 4,  2, gpu2d_ovg_sels,    ARRAY_SIZE(gpu2d_ovg_sels));
@@ -179,14 +179,14 @@ static void __init imx6sl_clocks_init(struct device_node *ccm_node)
 	clks[IMX6SL_CLK_SSI2_PODF]         = imx_clk_divider("ssi2_podf",         "ssi2_pred",         base + 0x2c, 0,  6);
 	clks[IMX6SL_CLK_SSI3_PRED]         = imx_clk_divider("ssi3_pred",         "ssi3_sel",          base + 0x28, 22, 3);
 	clks[IMX6SL_CLK_SSI3_PODF]         = imx_clk_divider("ssi3_podf",         "ssi3_pred",         base + 0x28, 16, 6);
-	clks[IMX6SL_CLK_PERCLK]            = imx_clk_divider("perclk",            "perclk_sel",        base + 0x1c, 0,  6);
+	clks[IMX6SL_CLK_PERCLK]            = imx_clk_fixup_divider("perclk",      "perclk_sel",        base + 0x1c, 0,  6, imx_cscmr1_fixup);
 	clks[IMX6SL_CLK_PXP_AXI_PODF]      = imx_clk_divider("pxp_axi_podf",      "pxp_axi_sel",       base + 0x34, 3,  3);
 	clks[IMX6SL_CLK_EPDC_AXI_PODF]     = imx_clk_divider("epdc_axi_podf",     "epdc_axi_sel",      base + 0x34, 12, 3);
 	clks[IMX6SL_CLK_GPU2D_OVG_PODF]    = imx_clk_divider("gpu2d_ovg_podf",    "gpu2d_ovg_sel",     base + 0x18, 26, 3);
 	clks[IMX6SL_CLK_GPU2D_PODF]        = imx_clk_divider("gpu2d_podf",        "gpu2d_sel",         base + 0x18, 29, 3);
 	clks[IMX6SL_CLK_LCDIF_PIX_PRED]    = imx_clk_divider("lcdif_pix_pred",    "lcdif_pix_sel",     base + 0x38, 3,  3);
 	clks[IMX6SL_CLK_EPDC_PIX_PRED]     = imx_clk_divider("epdc_pix_pred",     "epdc_pix_sel",      base + 0x38, 12, 3);
-	clks[IMX6SL_CLK_LCDIF_PIX_PODF]    = imx_clk_divider("lcdif_pix_podf",    "lcdif_pix_pred",    base + 0x1c, 20, 3);
+	clks[IMX6SL_CLK_LCDIF_PIX_PODF]    = imx_clk_fixup_divider("lcdif_pix_podf", "lcdif_pix_pred", base + 0x1c, 20, 3, imx_cscmr1_fixup);
 	clks[IMX6SL_CLK_EPDC_PIX_PODF]     = imx_clk_divider("epdc_pix_podf",     "epdc_pix_pred",     base + 0x18, 23, 3);
 	clks[IMX6SL_CLK_SPDIF0_PRED]       = imx_clk_divider("spdif0_pred",       "spdif0_sel",        base + 0x30, 25, 3);
 	clks[IMX6SL_CLK_SPDIF0_PODF]       = imx_clk_divider("spdif0_podf",       "spdif0_pred",       base + 0x30, 22, 3);
diff --git a/arch/arm/mach-imx/clk-pllv3.c b/arch/arm/mach-imx/clk-pllv3.c
index a9fad5f8d340..f6640b6a7b31 100644
--- a/arch/arm/mach-imx/clk-pllv3.c
+++ b/arch/arm/mach-imx/clk-pllv3.c
@@ -48,7 +48,7 @@ struct clk_pllv3 {
 static int clk_pllv3_prepare(struct clk_hw *hw)
 {
 	struct clk_pllv3 *pll = to_clk_pllv3(hw);
-	unsigned long timeout = jiffies + msecs_to_jiffies(10);
+	unsigned long timeout;
 	u32 val;
 
 	val = readl_relaxed(pll->base);
@@ -59,12 +59,19 @@ static int clk_pllv3_prepare(struct clk_hw *hw)
 		val &= ~BM_PLL_POWER;
 	writel_relaxed(val, pll->base);
 
+	timeout = jiffies + msecs_to_jiffies(10);
 	/* Wait for PLL to lock */
-	while (!(readl_relaxed(pll->base) & BM_PLL_LOCK))
+	do {
+		if (readl_relaxed(pll->base) & BM_PLL_LOCK)
+			break;
 		if (time_after(jiffies, timeout))
-			return -ETIMEDOUT;
+			break;
+	} while (1);
 
-	return 0;
+	if (readl_relaxed(pll->base) & BM_PLL_LOCK)
+		return 0;
+	else
+		return -ETIMEDOUT;
 }
 
 static void clk_pllv3_unprepare(struct clk_hw *hw)
diff --git a/arch/arm/mach-imx/clk.c b/arch/arm/mach-imx/clk.c
index 55bc80a00666..edc35df7bed4 100644
--- a/arch/arm/mach-imx/clk.c
+++ b/arch/arm/mach-imx/clk.c
@@ -37,3 +37,29 @@ struct clk * __init imx_obtain_fixed_clock(
 		clk = imx_clk_fixed(name, rate);
 	return clk;
 }
+
+/*
+ * This fixups the register CCM_CSCMR1 write value.
+ * The write/read/divider values of the aclk_podf field
+ * of that register have the relationship described by
+ * the following table:
+ *
+ * write value       read value        divider
+ * 3b'000            3b'110            7
+ * 3b'001            3b'111            8
+ * 3b'010            3b'100            5
+ * 3b'011            3b'101            6
+ * 3b'100            3b'010            3
+ * 3b'101            3b'011            4
+ * 3b'110            3b'000            1
+ * 3b'111            3b'001            2(default)
+ *
+ * That's why we do the xor operation below.
+ */
+#define CSCMR1_FIXUP	0x00600000
+
+void imx_cscmr1_fixup(u32 *val)
+{
+	*val ^= CSCMR1_FIXUP;
+	return;
+}
diff --git a/arch/arm/mach-imx/clk.h b/arch/arm/mach-imx/clk.h
index 0e4e8bb261b9..048c5ad8a80b 100644
--- a/arch/arm/mach-imx/clk.h
+++ b/arch/arm/mach-imx/clk.h
@@ -6,6 +6,8 @@
 
 extern spinlock_t imx_ccm_lock;
 
+extern void imx_cscmr1_fixup(u32 *val);
+
 struct clk *imx_clk_pllv1(const char *name, const char *parent,
 		void __iomem *base);
 
@@ -49,6 +51,14 @@ struct clk *imx_clk_busy_mux(const char *name, void __iomem *reg, u8 shift,
 			     u8 width, void __iomem *busy_reg, u8 busy_shift,
 			     const char **parent_names, int num_parents);
 
+struct clk *imx_clk_fixup_divider(const char *name, const char *parent,
+				  void __iomem *reg, u8 shift, u8 width,
+				  void (*fixup)(u32 *val));
+
+struct clk *imx_clk_fixup_mux(const char *name, void __iomem *reg,
+			      u8 shift, u8 width, const char **parents,
+			      int num_parents, void (*fixup)(u32 *val));
+
 static inline struct clk *imx_clk_fixed(const char *name, int rate)
 {
 	return clk_register_fixed_rate(NULL, name, NULL, CLK_IS_ROOT, rate);
@@ -79,7 +89,8 @@ static inline struct clk *imx_clk_gate(const char *name, const char *parent,
 static inline struct clk *imx_clk_mux(const char *name, void __iomem *reg,
 		u8 shift, u8 width, const char **parents, int num_parents)
 {
-	return clk_register_mux(NULL, name, parents, num_parents, 0, reg, shift,
+	return clk_register_mux(NULL, name, parents, num_parents,
+			CLK_SET_RATE_NO_REPARENT, reg, shift,
 			width, 0, &imx_ccm_lock);
 }
 
@@ -88,7 +99,7 @@ static inline struct clk *imx_clk_mux_flags(const char *name,
 		int num_parents, unsigned long flags)
 {
 	return clk_register_mux(NULL, name, parents, num_parents,
-			flags, reg, shift, width, 0,
+			flags | CLK_SET_RATE_NO_REPARENT, reg, shift, width, 0,
 			&imx_ccm_lock);
 }
 
diff --git a/arch/arm/mach-imx/common.h b/arch/arm/mach-imx/common.h
index cb6c838b63ed..4517fd760bfc 100644
--- a/arch/arm/mach-imx/common.h
+++ b/arch/arm/mach-imx/common.h
@@ -137,7 +137,6 @@ extern void imx_gpc_restore_all(void);
 extern void imx_anatop_init(void);
 extern void imx_anatop_pre_suspend(void);
 extern void imx_anatop_post_resume(void);
-extern void imx_anatop_usb_chrg_detect_disable(void);
 extern u32 imx_anatop_get_digprog(void);
 extern int imx6q_set_lpm(enum mxc_cpu_pwr_mode mode);
 extern void imx6q_set_chicken_bit(void);
@@ -147,12 +146,10 @@ extern int imx_cpu_kill(unsigned int cpu);
 
 #ifdef CONFIG_PM
 extern void imx6q_pm_init(void);
-extern void imx51_pm_init(void);
-extern void imx53_pm_init(void);
+extern void imx5_pm_init(void);
 #else
 static inline void imx6q_pm_init(void) {}
-static inline void imx51_pm_init(void) {}
-static inline void imx53_pm_init(void) {}
+static inline void imx5_pm_init(void) {}
 #endif
 
 #ifdef CONFIG_NEON
@@ -161,6 +158,12 @@ extern int mx51_neon_fixup(void);
 static inline int mx51_neon_fixup(void) { return 0; }
 #endif
 
+#ifdef CONFIG_CACHE_L2X0
+extern void imx_init_l2cache(void);
+#else
+static inline void imx_init_l2cache(void) {}
+#endif
+
 extern struct smp_operations imx_smp_ops;
 
 #endif
diff --git a/arch/arm/mach-imx/mach-imx27_visstrim_m10.c b/arch/arm/mach-imx/mach-imx27_visstrim_m10.c
index 29ac8ee651d2..97f9c6297fcf 100644
--- a/arch/arm/mach-imx/mach-imx27_visstrim_m10.c
+++ b/arch/arm/mach-imx/mach-imx27_visstrim_m10.c
@@ -26,7 +26,7 @@
 #include <linux/platform_device.h>
 #include <linux/mtd/physmap.h>
 #include <linux/i2c.h>
-#include <linux/i2c/pca953x.h>
+#include <linux/platform_data/pca953x.h>
 #include <linux/input.h>
 #include <linux/gpio.h>
 #include <linux/delay.h>
diff --git a/arch/arm/mach-imx/mach-imx6q.c b/arch/arm/mach-imx/mach-imx6q.c
index 7be13f8e69a0..90372a21087f 100644
--- a/arch/arm/mach-imx/mach-imx6q.c
+++ b/arch/arm/mach-imx/mach-imx6q.c
@@ -31,7 +31,7 @@
 #include <linux/regmap.h>
 #include <linux/micrel_phy.h>
 #include <linux/mfd/syscon.h>
-#include <asm/hardware/cache-l2x0.h>
+#include <linux/mfd/syscon/imx6q-iomuxc-gpr.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
 #include <asm/system_misc.h>
@@ -103,87 +103,77 @@ static int ksz9021rn_phy_fixup(struct phy_device *phydev)
 {
 	if (IS_BUILTIN(CONFIG_PHYLIB)) {
 		/* min rx data delay */
-		phy_write(phydev, 0x0b, 0x8105);
-		phy_write(phydev, 0x0c, 0x0000);
+		phy_write(phydev, MICREL_KSZ9021_EXTREG_CTRL,
+			0x8000 | MICREL_KSZ9021_RGMII_RX_DATA_PAD_SCEW);
+		phy_write(phydev, MICREL_KSZ9021_EXTREG_DATA_WRITE, 0x0000);
 
 		/* max rx/tx clock delay, min rx/tx control delay */
-		phy_write(phydev, 0x0b, 0x8104);
-		phy_write(phydev, 0x0c, 0xf0f0);
-		phy_write(phydev, 0x0b, 0x104);
+		phy_write(phydev, MICREL_KSZ9021_EXTREG_CTRL,
+			0x8000 | MICREL_KSZ9021_RGMII_CLK_CTRL_PAD_SCEW);
+		phy_write(phydev, MICREL_KSZ9021_EXTREG_DATA_WRITE, 0xf0f0);
+		phy_write(phydev, MICREL_KSZ9021_EXTREG_CTRL,
+			MICREL_KSZ9021_RGMII_CLK_CTRL_PAD_SCEW);
 	}
 
 	return 0;
 }
 
-static void __init imx6q_sabrelite_cko1_setup(void)
+static void mmd_write_reg(struct phy_device *dev, int device, int reg, int val)
 {
-	struct clk *cko1_sel, *ahb, *cko1;
-	unsigned long rate;
-
-	cko1_sel = clk_get_sys(NULL, "cko1_sel");
-	ahb = clk_get_sys(NULL, "ahb");
-	cko1 = clk_get_sys(NULL, "cko1");
-	if (IS_ERR(cko1_sel) || IS_ERR(ahb) || IS_ERR(cko1)) {
-		pr_err("cko1 setup failed!\n");
-		goto put_clk;
-	}
-	clk_set_parent(cko1_sel, ahb);
-	rate = clk_round_rate(cko1, 16000000);
-	clk_set_rate(cko1, rate);
-put_clk:
-	if (!IS_ERR(cko1_sel))
-		clk_put(cko1_sel);
-	if (!IS_ERR(ahb))
-		clk_put(ahb);
-	if (!IS_ERR(cko1))
-		clk_put(cko1);
+	phy_write(dev, 0x0d, device);
+	phy_write(dev, 0x0e, reg);
+	phy_write(dev, 0x0d, (1 << 14) | device);
+	phy_write(dev, 0x0e, val);
 }
 
-static void __init imx6q_sabrelite_init(void)
+static int ksz9031rn_phy_fixup(struct phy_device *dev)
 {
-	if (IS_BUILTIN(CONFIG_PHYLIB))
-		phy_register_fixup_for_uid(PHY_ID_KSZ9021, MICREL_PHY_ID_MASK,
-				ksz9021rn_phy_fixup);
-	imx6q_sabrelite_cko1_setup();
+	/*
+	 * min rx data delay, max rx/tx clock delay,
+	 * min rx/tx control delay
+	 */
+	mmd_write_reg(dev, 2, 4, 0);
+	mmd_write_reg(dev, 2, 5, 0);
+	mmd_write_reg(dev, 2, 8, 0x003ff);
+
+	return 0;
 }
 
-static void __init imx6q_sabresd_cko1_setup(void)
+static int ar8031_phy_fixup(struct phy_device *dev)
 {
-	struct clk *cko1_sel, *pll4, *pll4_post, *cko1;
-	unsigned long rate;
-
-	cko1_sel = clk_get_sys(NULL, "cko1_sel");
-	pll4 = clk_get_sys(NULL, "pll4_audio");
-	pll4_post = clk_get_sys(NULL, "pll4_post_div");
-	cko1 = clk_get_sys(NULL, "cko1");
-	if (IS_ERR(cko1_sel) || IS_ERR(pll4)
-			|| IS_ERR(pll4_post) || IS_ERR(cko1)) {
-		pr_err("cko1 setup failed!\n");
-		goto put_clk;
-	}
-	/*
-	 * Setting pll4 at 768MHz (24MHz * 32)
-	 * So its child clock can get 24MHz easily
-	 */
-	clk_set_rate(pll4, 768000000);
-
-	clk_set_parent(cko1_sel, pll4_post);
-	rate = clk_round_rate(cko1, 24000000);
-	clk_set_rate(cko1, rate);
-put_clk:
-	if (!IS_ERR(cko1_sel))
-		clk_put(cko1_sel);
-	if (!IS_ERR(pll4_post))
-		clk_put(pll4_post);
-	if (!IS_ERR(pll4))
-		clk_put(pll4);
-	if (!IS_ERR(cko1))
-		clk_put(cko1);
+	u16 val;
+
+	/* To enable AR8031 output a 125MHz clk from CLK_25M */
+	phy_write(dev, 0xd, 0x7);
+	phy_write(dev, 0xe, 0x8016);
+	phy_write(dev, 0xd, 0x4007);
+
+	val = phy_read(dev, 0xe);
+	val &= 0xffe3;
+	val |= 0x18;
+	phy_write(dev, 0xe, val);
+
+	/* introduce tx clock delay */
+	phy_write(dev, 0x1d, 0x5);
+	val = phy_read(dev, 0x1e);
+	val |= 0x0100;
+	phy_write(dev, 0x1e, val);
+
+	return 0;
 }
 
-static void __init imx6q_sabresd_init(void)
+#define PHY_ID_AR8031	0x004dd074
+
+static void __init imx6q_enet_phy_init(void)
 {
-	imx6q_sabresd_cko1_setup();
+	if (IS_BUILTIN(CONFIG_PHYLIB)) {
+		phy_register_fixup_for_uid(PHY_ID_KSZ9021, MICREL_PHY_ID_MASK,
+				ksz9021rn_phy_fixup);
+		phy_register_fixup_for_uid(PHY_ID_KSZ9031, MICREL_PHY_ID_MASK,
+				ksz9031rn_phy_fixup);
+		phy_register_fixup_for_uid(PHY_ID_AR8031, 0xffffffff,
+				ar8031_phy_fixup);
+	}
 }
 
 static void __init imx6q_1588_init(void)
@@ -192,29 +182,22 @@ static void __init imx6q_1588_init(void)
 
 	gpr = syscon_regmap_lookup_by_compatible("fsl,imx6q-iomuxc-gpr");
 	if (!IS_ERR(gpr))
-		regmap_update_bits(gpr, 0x4, 1 << 21, 1 << 21);
+		regmap_update_bits(gpr, IOMUXC_GPR1,
+				IMX6Q_GPR1_ENET_CLK_SEL_MASK,
+				IMX6Q_GPR1_ENET_CLK_SEL_ANATOP);
 	else
 		pr_err("failed to find fsl,imx6q-iomux-gpr regmap\n");
 
 }
-static void __init imx6q_usb_init(void)
-{
-	imx_anatop_usb_chrg_detect_disable();
-}
 
 static void __init imx6q_init_machine(void)
 {
-	if (of_machine_is_compatible("fsl,imx6q-sabrelite"))
-		imx6q_sabrelite_init();
-	else if (of_machine_is_compatible("fsl,imx6q-sabresd") ||
-			of_machine_is_compatible("fsl,imx6dl-sabresd"))
-		imx6q_sabresd_init();
+	imx6q_enet_phy_init();
 
 	of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
 
 	imx_anatop_init();
 	imx6q_pm_init();
-	imx6q_usb_init();
 	imx6q_1588_init();
 }
 
@@ -250,17 +233,21 @@ put_node:
 	of_node_put(np);
 }
 
-static void __init imx6q_opp_init(struct device *cpu_dev)
+static void __init imx6q_opp_init(void)
 {
 	struct device_node *np;
+	struct device *cpu_dev = get_cpu_device(0);
 
-	np = of_find_node_by_path("/cpus/cpu@0");
+	if (!cpu_dev) {
+		pr_warn("failed to get cpu0 device\n");
+		return;
+	}
+	np = of_node_get(cpu_dev->of_node);
 	if (!np) {
 		pr_warn("failed to find cpu0 node\n");
 		return;
 	}
 
-	cpu_dev->of_node = np;
 	if (of_init_opp_table(cpu_dev)) {
 		pr_warn("failed to init OPP table\n");
 		goto put_node;
@@ -286,7 +273,7 @@ static void __init imx6q_init_late(void)
 		imx6q_cpuidle_init();
 
 	if (IS_ENABLED(CONFIG_ARM_IMX6Q_CPUFREQ)) {
-		imx6q_opp_init(&imx6q_cpufreq_pdev.dev);
+		imx6q_opp_init();
 		platform_device_register(&imx6q_cpufreq_pdev);
 	}
 }
@@ -297,44 +284,10 @@ static void __init imx6q_map_io(void)
 	imx_scu_map_io();
 }
 
-#ifdef CONFIG_CACHE_L2X0
-static void __init imx6q_init_l2cache(void)
-{
-	void __iomem *l2x0_base;
-	struct device_node *np;
-	unsigned int val;
-
-	np = of_find_compatible_node(NULL, NULL, "arm,pl310-cache");
-	if (!np)
-		goto out;
-
-	l2x0_base = of_iomap(np, 0);
-	if (!l2x0_base) {
-		of_node_put(np);
-		goto out;
-	}
-
-	/* Configure the L2 PREFETCH and POWER registers */
-	val = readl_relaxed(l2x0_base + L2X0_PREFETCH_CTRL);
-	val |= 0x70800000;
-	writel_relaxed(val, l2x0_base + L2X0_PREFETCH_CTRL);
-	val = L2X0_DYNAMIC_CLK_GATING_EN | L2X0_STNDBY_MODE_EN;
-	writel_relaxed(val, l2x0_base + L2X0_POWER_CTRL);
-
-	iounmap(l2x0_base);
-	of_node_put(np);
-
-out:
-	l2x0_of_init(0, ~0UL);
-}
-#else
-static inline void imx6q_init_l2cache(void) {}
-#endif
-
 static void __init imx6q_init_irq(void)
 {
 	imx6q_init_revision();
-	imx6q_init_l2cache();
+	imx_init_l2cache();
 	imx_src_init();
 	imx_gpc_init();
 	irqchip_init();
diff --git a/arch/arm/mach-imx/mach-imx6sl.c b/arch/arm/mach-imx/mach-imx6sl.c
index 132db2609507..0d75dc54f715 100644
--- a/arch/arm/mach-imx/mach-imx6sl.c
+++ b/arch/arm/mach-imx/mach-imx6sl.c
@@ -11,7 +11,6 @@
 #include <linux/irqchip.h>
 #include <linux/of.h>
 #include <linux/of_platform.h>
-#include <asm/hardware/cache-l2x0.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
 
@@ -26,7 +25,7 @@ static void __init imx6sl_init_machine(void)
 
 static void __init imx6sl_init_irq(void)
 {
-	l2x0_of_init(0, ~0UL);
+	imx_init_l2cache();
 	imx_src_init();
 	imx_gpc_init();
 	irqchip_init();
diff --git a/arch/arm/mach-imx/mach-mxt_td60.c b/arch/arm/mach-imx/mach-mxt_td60.c
index a27faaba98ec..c91894003da9 100644
--- a/arch/arm/mach-imx/mach-mxt_td60.c
+++ b/arch/arm/mach-imx/mach-mxt_td60.c
@@ -26,7 +26,7 @@
 #include <asm/mach/time.h>
 #include <asm/mach/map.h>
 #include <linux/gpio.h>
-#include <linux/i2c/pca953x.h>
+#include <linux/platform_data/pca953x.h>
 
 #include "common.h"
 #include "devices-imx27.h"
diff --git a/arch/arm/mach-imx/mm-imx25.c b/arch/arm/mach-imx/mm-imx25.c
index e065c117f5a6..5211f62c624e 100644
--- a/arch/arm/mach-imx/mm-imx25.c
+++ b/arch/arm/mach-imx/mm-imx25.c
@@ -61,25 +61,8 @@ void __init mx25_init_irq(void)
 	mxc_init_irq(MX25_IO_ADDRESS(MX25_AVIC_BASE_ADDR));
 }
 
-static struct sdma_script_start_addrs imx25_sdma_script __initdata = {
-	.ap_2_ap_addr = 729,
-	.uart_2_mcu_addr = 904,
-	.per_2_app_addr = 1255,
-	.mcu_2_app_addr = 834,
-	.uartsh_2_mcu_addr = 1120,
-	.per_2_shp_addr = 1329,
-	.mcu_2_shp_addr = 1048,
-	.ata_2_mcu_addr = 1560,
-	.mcu_2_ata_addr = 1479,
-	.app_2_per_addr = 1189,
-	.app_2_mcu_addr = 770,
-	.shp_2_per_addr = 1407,
-	.shp_2_mcu_addr = 979,
-};
-
 static struct sdma_platform_data imx25_sdma_pdata __initdata = {
 	.fw_name = "sdma-imx25.bin",
-	.script_addrs = &imx25_sdma_script,
 };
 
 static const struct resource imx25_audmux_res[] __initconst = {
diff --git a/arch/arm/mach-imx/mm-imx5.c b/arch/arm/mach-imx/mm-imx5.c
index cf193d87274a..eb3cce38c70d 100644
--- a/arch/arm/mach-imx/mm-imx5.c
+++ b/arch/arm/mach-imx/mm-imx5.c
@@ -103,22 +103,8 @@ void __init mx53_init_irq(void)
 	tzic_init_irq(MX53_IO_ADDRESS(MX53_TZIC_BASE_ADDR));
 }
 
-static struct sdma_script_start_addrs imx51_sdma_script __initdata = {
-	.ap_2_ap_addr = 642,
-	.uart_2_mcu_addr = 817,
-	.mcu_2_app_addr = 747,
-	.mcu_2_shp_addr = 961,
-	.ata_2_mcu_addr = 1473,
-	.mcu_2_ata_addr = 1392,
-	.app_2_per_addr = 1033,
-	.app_2_mcu_addr = 683,
-	.shp_2_per_addr = 1251,
-	.shp_2_mcu_addr = 892,
-};
-
 static struct sdma_platform_data imx51_sdma_pdata __initdata = {
 	.fw_name = "sdma-imx51.bin",
-	.script_addrs = &imx51_sdma_script,
 };
 
 static const struct resource imx51_audmux_res[] __initconst = {
@@ -153,10 +139,10 @@ void __init imx51_soc_init(void)
 void __init imx51_init_late(void)
 {
 	mx51_neon_fixup();
-	imx51_pm_init();
+	imx5_pm_init();
 }
 
 void __init imx53_init_late(void)
 {
-	imx53_pm_init();
+	imx5_pm_init();
 }
diff --git a/arch/arm/mach-imx/pm-imx5.c b/arch/arm/mach-imx/pm-imx5.c
index 82e79c658eb2..58aeaf5baaf6 100644
--- a/arch/arm/mach-imx/pm-imx5.c
+++ b/arch/arm/mach-imx/pm-imx5.c
@@ -169,14 +169,9 @@ static int __init imx5_pm_common_init(void)
 	return imx5_cpuidle_init();
 }
 
-void __init imx51_pm_init(void)
+void __init imx5_pm_init(void)
 {
 	int ret = imx5_pm_common_init();
 	if (!ret)
 		suspend_set_ops(&mx5_suspend_ops);
 }
-
-void __init imx53_pm_init(void)
-{
-	imx5_pm_common_init();
-}
diff --git a/arch/arm/mach-imx/system.c b/arch/arm/mach-imx/system.c
index 6fe81bb4d3c9..80c177c36c5f 100644
--- a/arch/arm/mach-imx/system.c
+++ b/arch/arm/mach-imx/system.c
@@ -27,6 +27,7 @@
 #include <asm/system_misc.h>
 #include <asm/proc-fns.h>
 #include <asm/mach-types.h>
+#include <asm/hardware/cache-l2x0.h>
 
 #include "common.h"
 #include "hardware.h"
@@ -95,3 +96,46 @@ void __init mxc_arch_reset_init_dt(void)
 
 	clk_prepare(wdog_clk);
 }
+
+#ifdef CONFIG_CACHE_L2X0
+void __init imx_init_l2cache(void)
+{
+	void __iomem *l2x0_base;
+	struct device_node *np;
+	unsigned int val;
+
+	np = of_find_compatible_node(NULL, NULL, "arm,pl310-cache");
+	if (!np)
+		goto out;
+
+	l2x0_base = of_iomap(np, 0);
+	if (!l2x0_base) {
+		of_node_put(np);
+		goto out;
+	}
+
+	/* Configure the L2 PREFETCH and POWER registers */
+	val = readl_relaxed(l2x0_base + L2X0_PREFETCH_CTRL);
+	val |= 0x70800000;
+	/*
+	 * The L2 cache controller(PL310) version on the i.MX6D/Q is r3p1-50rel0
+	 * The L2 cache controller(PL310) version on the i.MX6DL/SOLO/SL is r3p2
+	 * But according to ARM PL310 errata: 752271
+	 * ID: 752271: Double linefill feature can cause data corruption
+	 * Fault Status: Present in: r3p0, r3p1, r3p1-50rel0. Fixed in r3p2
+	 * Workaround: The only workaround to this erratum is to disable the
+	 * double linefill feature. This is the default behavior.
+	 */
+	if (cpu_is_imx6q())
+		val &= ~(1 << 30 | 1 << 23);
+	writel_relaxed(val, l2x0_base + L2X0_PREFETCH_CTRL);
+	val = L2X0_DYNAMIC_CLK_GATING_EN | L2X0_STNDBY_MODE_EN;
+	writel_relaxed(val, l2x0_base + L2X0_POWER_CTRL);
+
+	iounmap(l2x0_base);
+	of_node_put(np);
+
+out:
+	l2x0_of_init(0, ~0UL);
+}
+#endif
diff --git a/arch/arm/mach-integrator/include/mach/debug-macro.S b/arch/arm/mach-integrator/include/mach/debug-macro.S
deleted file mode 100644
index 411b116077e4..000000000000
--- a/arch/arm/mach-integrator/include/mach/debug-macro.S
+++ /dev/null
@@ -1,20 +0,0 @@
-/* arch/arm/mach-integrator/include/mach/debug-macro.S
- *
- * Debugging macro include header
- *
- *  Copyright (C) 1994-1999 Russell King
- *  Moved from linux/arch/arm/kernel/debug.S by Ben Dooks
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
-*/
-
-		.macro	addruart, rp, rv, tmp
-		mov	\rp, #0x16000000	@ physical base address
-		mov	\rv, #0xf0000000	@ virtual base
-		add	\rv, \rv, #0x16000000 >> 4
-		.endm
-
-#include <asm/hardware/debug-pl01x.S>
diff --git a/arch/arm/mach-integrator/pci_v3.h b/arch/arm/mach-integrator/pci_v3.h
index 755fd29fed4a..06a9e2e7d007 100644
--- a/arch/arm/mach-integrator/pci_v3.h
+++ b/arch/arm/mach-integrator/pci_v3.h
@@ -1,2 +1,9 @@
 /* Simple oneliner include to the PCIv3 early init */
+#ifdef CONFIG_PCI
 extern int pci_v3_early_init(void);
+#else
+static inline int pci_v3_early_init(void)
+{
+	return 0;
+}
+#endif
diff --git a/arch/arm/mach-iop13xx/include/mach/debug-macro.S b/arch/arm/mach-iop13xx/include/mach/debug-macro.S
deleted file mode 100644
index d869a6f67e5c..000000000000
--- a/arch/arm/mach-iop13xx/include/mach/debug-macro.S
+++ /dev/null
@@ -1,24 +0,0 @@
-/*
- * arch/arm/mach-iop13xx/include/mach/debug-macro.S
- *
- * Debugging macro include header
- *
- * Copyright (C) 1994-1999 Russell King
- * Moved from linux/arch/arm/kernel/debug.S by Ben Dooks
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-	.macro	addruart, rp, rv, tmp
-	mov	\rp, #0x00002300
-	orr	\rp, \rp, #0x00000040
-	orr	\rv, \rp, #0xfe000000	@ virtual
-	orr	\rv, \rv, #0x00e80000
-	orr	\rp, \rp, #0xff000000	@ physical
-	orr	\rp, \rp, #0x00d80000
-	.endm
-
-#define UART_SHIFT	2
-#include <asm/hardware/debug-8250.S>
diff --git a/arch/arm/mach-iop32x/include/mach/debug-macro.S b/arch/arm/mach-iop32x/include/mach/debug-macro.S
deleted file mode 100644
index 363bdf90b34d..000000000000
--- a/arch/arm/mach-iop32x/include/mach/debug-macro.S
+++ /dev/null
@@ -1,21 +0,0 @@
-/*
- * arch/arm/mach-iop32x/include/mach/debug-macro.S
- *
- * Debugging macro include header
- *
- * Copyright (C) 1994-1999 Russell King
- * Moved from linux/arch/arm/kernel/debug.S by Ben Dooks
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-		.macro	addruart, rp, rv, tmp
-		mov	\rp, #0xfe000000	@ physical as well as virtual
-		orr	\rp, \rp, #0x00800000	@ location of the UART
-		mov	\rv, \rp
-		.endm
-
-#define UART_SHIFT	0
-#include <asm/hardware/debug-8250.S>
diff --git a/arch/arm/mach-iop33x/include/mach/debug-macro.S b/arch/arm/mach-iop33x/include/mach/debug-macro.S
deleted file mode 100644
index 361be1f6026e..000000000000
--- a/arch/arm/mach-iop33x/include/mach/debug-macro.S
+++ /dev/null
@@ -1,22 +0,0 @@
-/*
- * arch/arm/mach-iop33x/include/mach/debug-macro.S
- *
- * Debugging macro include header
- *
- * Copyright (C) 1994-1999 Russell King
- * Moved from linux/arch/arm/kernel/debug.S by Ben Dooks
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-		.macro	addruart, rp, rv, tmp
-		mov	\rp, #0x00ff0000
-		orr	\rp, \rp, #0x0000f700
-		orr	\rv, #0xfe000000	@ virtual
-		orr	\rp, #0xff000000	@ physical
-		.endm
-
-#define UART_SHIFT	2
-#include <asm/hardware/debug-8250.S>
diff --git a/arch/arm/mach-ixp4xx/include/mach/debug-macro.S b/arch/arm/mach-ixp4xx/include/mach/debug-macro.S
deleted file mode 100644
index ff686cbc5df4..000000000000
--- a/arch/arm/mach-ixp4xx/include/mach/debug-macro.S
+++ /dev/null
@@ -1,26 +0,0 @@
-/* arch/arm/mach-ixp4xx/include/mach/debug-macro.S
- *
- * Debugging macro include header
- *
- *  Copyright (C) 1994-1999 Russell King
- *  Moved from linux/arch/arm/kernel/debug.S by Ben Dooks
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
-
-                .macro  addruart, rp, rv, tmp
-#ifdef __ARMEB__
-                mov     \rp, #3         @ Uart regs are at off set of 3 if
-					@ byte writes used - Big Endian.
-#else
-		mov	\rp, #0
-#endif
-		orr	\rv, \rp, #0xfe000000	@ virtual
-		orr	\rv, \rv, #0x00f00000
-                orr     \rp, \rp, #0xc8000000	@ physical
-                .endm
-
-#define UART_SHIFT	2
-#include <asm/hardware/debug-8250.S>
diff --git a/arch/arm/mach-keystone/Kconfig b/arch/arm/mach-keystone/Kconfig
index 51a50e996840..366d1a3b418d 100644
--- a/arch/arm/mach-keystone/Kconfig
+++ b/arch/arm/mach-keystone/Kconfig
@@ -7,7 +7,6 @@ config ARCH_KEYSTONE
 	select HAVE_SMP
 	select CLKSRC_MMIO
 	select GENERIC_CLOCKEVENTS
-	select HAVE_SCHED_CLOCK
 	select ARCH_WANT_OPTIONAL_GPIOLIB
 	select ARM_ERRATA_798181 if SMP
 	help
diff --git a/arch/arm/mach-keystone/platsmp.c b/arch/arm/mach-keystone/platsmp.c
index 14378e3fef16..c12296157d4a 100644
--- a/arch/arm/mach-keystone/platsmp.c
+++ b/arch/arm/mach-keystone/platsmp.c
@@ -38,6 +38,5 @@ static int keystone_smp_boot_secondary(unsigned int cpu,
 }
 
 struct smp_operations keystone_smp_ops __initdata = {
-	.smp_init_cpus		= arm_dt_init_cpu_maps,
 	.smp_boot_secondary	= keystone_smp_boot_secondary,
 };
diff --git a/arch/arm/mach-keystone/smc.S b/arch/arm/mach-keystone/smc.S
index 9b9e4f7b241e..d15de8179fab 100644
--- a/arch/arm/mach-keystone/smc.S
+++ b/arch/arm/mach-keystone/smc.S
@@ -22,8 +22,7 @@
  * Return: Non zero value on failure
  */
 ENTRY(keystone_cpu_smc)
-	stmfd   sp!, {r4-r12, lr}
+	stmfd   sp!, {r4-r11, lr}
 	smc	#0
-	dsb
-	ldmfd   sp!, {r4-r12, pc}
+	ldmfd   sp!, {r4-r11, pc}
 ENDPROC(keystone_cpu_smc)
diff --git a/arch/arm/mach-kirkwood/Kconfig b/arch/arm/mach-kirkwood/Kconfig
index b634f9650a7b..fe8319ad3158 100644
--- a/arch/arm/mach-kirkwood/Kconfig
+++ b/arch/arm/mach-kirkwood/Kconfig
@@ -2,67 +2,32 @@ if ARCH_KIRKWOOD
 
 menu "Marvell Kirkwood Implementations"
 
+config KIRKWOOD_LEGACY
+	bool
+
 config MACH_D2NET_V2
 	bool "LaCie d2 Network v2 NAS Board"
+	select KIRKWOOD_LEGACY
 	help
 	  Say 'Y' here if you want your kernel to support the
 	  LaCie d2 Network v2 NAS.
 
-config MACH_DOCKSTAR
-	bool "Seagate FreeAgent DockStar"
-	help
-	  Say 'Y' here if you want your kernel to support the
-	  Seagate FreeAgent DockStar.
-
-config MACH_ESATA_SHEEVAPLUG
-	bool "Marvell eSATA SheevaPlug Reference Board"
-	help
-	  Say 'Y' here if you want your kernel to support the
-	  Marvell eSATA SheevaPlug Reference Board.
-
-config MACH_GURUPLUG
-	bool "Marvell GuruPlug Reference Board"
-	help
-	  Say 'Y' here if you want your kernel to support the
-	  Marvell GuruPlug Reference Board.
-
-config MACH_INETSPACE_V2
-	bool "LaCie Internet Space v2 NAS Board"
-	help
-	  Say 'Y' here if you want your kernel to support the
-	  LaCie Internet Space v2 NAS.
-
-config MACH_MV88F6281GTW_GE
-	bool "Marvell 88F6281 GTW GE Board"
-	help
-	  Say 'Y' here if you want your kernel to support the
-	  Marvell 88F6281 GTW GE Board.
-
 config MACH_NET2BIG_V2
 	bool "LaCie 2Big Network v2 NAS Board"
+	select KIRKWOOD_LEGACY
 	help
 	  Say 'Y' here if you want your kernel to support the
 	  LaCie 2Big Network v2 NAS.
 
 config MACH_NET5BIG_V2
 	bool "LaCie 5Big Network v2 NAS Board"
+	select KIRKWOOD_LEGACY
 	help
 	  Say 'Y' here if you want your kernel to support the
 	  LaCie 5Big Network v2 NAS.
 
-config MACH_NETSPACE_MAX_V2
-	bool "LaCie Network Space Max v2 NAS Board"
-	help
-	  Say 'Y' here if you want your kernel to support the
-	  LaCie Network Space Max v2 NAS.
-
-config MACH_NETSPACE_V2
-	bool "LaCie Network Space v2 NAS Board"
-	help
-	  Say 'Y' here if you want your kernel to support the
-	  LaCie Network Space v2 NAS.
-
 config MACH_OPENRD
+	select KIRKWOOD_LEGACY
         bool
 
 config MACH_OPENRD_BASE
@@ -88,30 +53,28 @@ config MACH_OPENRD_ULTIMATE
 
 config MACH_RD88F6192_NAS
 	bool "Marvell RD-88F6192-NAS Reference Board"
+	select KIRKWOOD_LEGACY
 	help
 	  Say 'Y' here if you want your kernel to support the
 	  Marvell RD-88F6192-NAS Reference Board.
 
 config MACH_RD88F6281
 	bool "Marvell RD-88F6281 Reference Board"
+	select KIRKWOOD_LEGACY
 	help
 	  Say 'Y' here if you want your kernel to support the
 	  Marvell RD-88F6281 Reference Board.
 
-config MACH_SHEEVAPLUG
-	bool "Marvell SheevaPlug Reference Board"
-	help
-	  Say 'Y' here if you want your kernel to support the
-	  Marvell SheevaPlug Reference Board.
-
 config MACH_T5325
 	bool "HP t5325 Thin Client"
+	select KIRKWOOD_LEGACY
 	help
 	  Say 'Y' here if you want your kernel to support the
 	  HP t5325 Thin Client.
 
 config MACH_TS219
 	bool "QNAP TS-110, TS-119, TS-119P+, TS-210, TS-219, TS-219P and TS-219P+ Turbo NAS"
+	select KIRKWOOD_LEGACY
 	help
 	  Say 'Y' here if you want your kernel to support the
 	  QNAP TS-110, TS-119, TS-119P+, TS-210, TS-219, TS-219P and
@@ -119,6 +82,7 @@ config MACH_TS219
 
 config MACH_TS41X
 	bool "QNAP TS-410, TS-410U, TS-419P, TS-419P+ and TS-419U Turbo NAS"
+	select KIRKWOOD_LEGACY
 	help
 	  Say 'Y' here if you want your kernel to support the
 	  QNAP TS-410, TS-410U, TS-419P, TS-419P+ and TS-419U Turbo
@@ -129,6 +93,9 @@ comment "Device tree entries"
 config ARCH_KIRKWOOD_DT
 	bool "Marvell Kirkwood Flattened Device Tree"
 	select KIRKWOOD_CLK
+	select OF_IRQ
+	select ORION_IRQCHIP
+	select ORION_TIMER
 	select POWER_SUPPLY
 	select POWER_RESET
 	select POWER_RESET_GPIO
@@ -139,184 +106,12 @@ config ARCH_KIRKWOOD_DT
 	  Say 'Y' here if you want your kernel to support the
 	  Marvell Kirkwood using flattened device tree.
 
-config MACH_CLOUDBOX_DT
-	bool "LaCie CloudBox NAS (Flattened Device Tree)"
-	select ARCH_KIRKWOOD_DT
-	help
-	  Say 'Y' here if you want your kernel to support the LaCie
-	  CloudBox NAS, using Flattened Device Tree.
-
-config MACH_DB88F628X_BP_DT
-	bool "Marvell DB-88F628x-BP Development Board (Flattened Device Tree)"
-	help
-	  Say 'Y' here if you want your kernel to support the Marvell
-	  DB-88F6281-BP and DB-88F6282-BP Development Board (Flattened
-	  Device Tree).
-
-config MACH_DLINK_KIRKWOOD_DT
-	bool "D-Link Kirkwood-based NAS (Flattened Device Tree)"
-	select ARCH_KIRKWOOD_DT
-	help
-	  Say 'Y' here if you want your kernel to support the
-	  Kirkwood-based D-Link NASes such as DNS-320 & DNS-325,
-	  using Flattened Device Tree.
-
-config MACH_DOCKSTAR_DT
-	bool "Seagate FreeAgent Dockstar (Flattened Device Tree)"
-	select ARCH_KIRKWOOD_DT
+config MACH_MV88F6281GTW_GE_DT
+	bool "Marvell 88F6281 GTW GE Board (Flattened Device Tree)"
+	depends on ARCH_KIRKWOOD_DT
 	help
 	  Say 'Y' here if you want your kernel to support the
-	  Seagate FreeAgent Dockstar (Flattened Device Tree).
-
-config MACH_DREAMPLUG_DT
-	bool "Marvell DreamPlug (Flattened Device Tree)"
-	select ARCH_KIRKWOOD_DT
-	help
-	  Say 'Y' here if you want your kernel to support the
-	  Marvell DreamPlug (Flattened Device Tree).
-
-config MACH_GOFLEXNET_DT
-	bool "Seagate GoFlex Net (Flattened Device Tree)"
-	select ARCH_KIRKWOOD_DT
-	help
-	  Say 'Y' here if you want your kernel to support the
-	  Seagate GoFlex Net (Flattened Device Tree).
-
-config MACH_GURUPLUG_DT
-	bool "Marvell GuruPlug Reference Board (Flattened Device Tree)"
-	select ARCH_KIRKWOOD_DT
-	help
-	  Say 'Y' here if you want your kernel to support the
-	  Marvell GuruPlug Reference Board (Flattened Device Tree).
-
-config MACH_IB62X0_DT
-	bool "RaidSonic IB-NAS6210, IB-NAS6220 (Flattened Device Tree)"
-	select ARCH_KIRKWOOD_DT
-	help
-	  Say 'Y' here if you want your kernel to support the
-	  RaidSonic IB-NAS6210 & IB-NAS6220 devices, using
-	  Flattened Device Tree.
-
-config MACH_ICONNECT_DT
-	bool "Iomega Iconnect (Flattened Device Tree)"
-	select ARCH_KIRKWOOD_DT
-	help
-	  Say 'Y' here to enable Iomega Iconnect support.
-
-config MACH_INETSPACE_V2_DT
-	bool "LaCie Internet Space v2 NAS (Flattened Device Tree)"
-	select ARCH_KIRKWOOD_DT
-	help
-	  Say 'Y' here if you want your kernel to support the LaCie
-	  Internet Space v2 NAS, using Flattened Device Tree.
-
-config MACH_IOMEGA_IX2_200_DT
-	bool "Iomega StorCenter ix2-200 (Flattened Device Tree)"
-	select ARCH_KIRKWOOD_DT
-	help
-	  Say 'Y' here if you want your kernel to support the
-	  Iomega StorCenter ix2-200 (Flattened Device Tree).
-
-config MACH_KM_KIRKWOOD_DT
-	bool "Keymile Kirkwood Reference Design (Flattened Device Tree)"
-	select ARCH_KIRKWOOD_DT
-	help
-	  Say 'Y' here if you want your kernel to support the
-	  Keymile Kirkwood Reference Desgin, using Flattened Device Tree.
-
-config MACH_LSXL_DT
-	bool "Buffalo Linkstation LS-XHL, LS-CHLv2 (Flattened Device Tree)"
-	select ARCH_KIRKWOOD_DT
-	select POWER_RESET_RESTART
-	help
-	  Say 'Y' here if you want your kernel to support the
-	  Buffalo Linkstation LS-XHL & LS-CHLv2 devices, using
-	  Flattened Device Tree.
-
-config MACH_MPLCEC4_DT
-	bool "MPL CEC4 (Flattened Device Tree)"
-	select ARCH_KIRKWOOD_DT
-	help
-	  Say 'Y' here if you want your kernel to support the
-	  MPL CEC4 (Flattened Device Tree).
-
-config MACH_NETSPACE_LITE_V2_DT
-	bool "LaCie Network Space Lite v2 NAS (Flattened Device Tree)"
-	select ARCH_KIRKWOOD_DT
-	help
-	  Say 'Y' here if you want your kernel to support the LaCie
-	  Network Space Lite v2 NAS, using Flattened Device Tree.
-
-config MACH_NETSPACE_MAX_V2_DT
-	bool "LaCie Network Space Max v2 NAS (Flattened Device Tree)"
-	select ARCH_KIRKWOOD_DT
-	help
-	  Say 'Y' here if you want your kernel to support the LaCie
-	  Network Space Max v2 NAS, using Flattened Device Tree.
-
-config MACH_NETSPACE_MINI_V2_DT
-	bool "LaCie Network Space Mini v2 NAS (Flattened Device Tree)"
-	select ARCH_KIRKWOOD_DT
-	help
-	  Say 'Y' here if you want your kernel to support the LaCie
-	  Network Space Mini v2 NAS using Flattened Device Tree.
-
-	  This board is embedded in a product named CloudBox, which
-	  provides automatic backup on a 100GB cloud storage. This
-	  should not confused with a more recent LaCie NAS also named
-	  CloudBox. For this last, the disk capacity is 1TB or above.
-
-config MACH_NETSPACE_V2_DT
-	bool "LaCie Network Space v2 NAS (Flattened Device Tree)"
-	select ARCH_KIRKWOOD_DT
-	help
-	  Say 'Y' here if you want your kernel to support the LaCie
-	  Network Space v2 NAS, using Flattened Device Tree.
-
-config MACH_OPENBLOCKS_A6_DT
-	bool "Plat'Home OpenBlocks A6 (Flattened Device Tree)"
-	select ARCH_KIRKWOOD_DT
-	help
-	  Say 'Y' here if you want your kernel to support the
-	  Plat'Home OpenBlocks A6 (Flattened Device Tree).
-
-config MACH_READYNAS_DT
-	bool "NETGEAR ReadyNAS Duo v2 (Flattened Device Tree)"
-	select ARCH_KIRKWOOD_DT
-	select ARM_APPENDED_DTB
-	select ARM_ATAG_DTB_COMPAT
-	help
-	  Say 'Y' here if you want your kernel to support the
-	  NETGEAR ReadyNAS Duo v2 using Fattened Device Tree.
-
-config MACH_SHEEVAPLUG_DT
-	bool "Marvell (eSATA) SheevaPlug (Flattened Device Tree)"
-	select ARCH_KIRKWOOD_DT
-	help
-	  Say 'Y' here if you want your kernel to support the
-	  Marvell (eSATA) SheevaPlug (Flattened Device Tree).
-
-config MACH_TOPKICK_DT
-	bool "USI Topkick (Flattened Device Tree)"
-	select ARCH_KIRKWOOD_DT
-	help
-	  Say 'Y' here if you want your kernel to support the
-	  USI Topkick, using Flattened Device Tree
-
-config MACH_TS219_DT
-	bool "Device Tree for QNAP TS-11X, TS-21X NAS"
-	select ARCH_KIRKWOOD_DT
-	select ARM_APPENDED_DTB
-	select ARM_ATAG_DTB_COMPAT
-	select POWER_RESET_QNAP
-	help
-	  Say 'Y' here if you want your kernel to support the QNAP
-	  TS-110, TS-119, TS-119P+, TS-210, TS-219, TS-219P and
-	  TS-219P+ Turbo NAS devices using Fattened Device Tree.
-	  There are two different Device Tree descriptions, depending
-	  on if the device is based on an if the board uses the MV6281
-	  or MV6282. If you have the wrong one, the buttons will not
-	  work.
+	  Marvell 88F6281 GTW GE Board (Flattened Device Tree).
 
 endmenu
 
diff --git a/arch/arm/mach-kirkwood/Makefile b/arch/arm/mach-kirkwood/Makefile
index ac4cd75dd499..d1f8e3d0793b 100644
--- a/arch/arm/mach-kirkwood/Makefile
+++ b/arch/arm/mach-kirkwood/Makefile
@@ -1,44 +1,14 @@
-obj-y				+= common.o irq.o pcie.o mpp.o
-
+obj-y				+= common.o pcie.o
+obj-$(CONFIG_KIRKWOOD_LEGACY)	+= irq.o mpp.o
 obj-$(CONFIG_MACH_D2NET_V2)		+= d2net_v2-setup.o lacie_v2-common.o
-obj-$(CONFIG_MACH_DOCKSTAR)		+= dockstar-setup.o
-obj-$(CONFIG_MACH_ESATA_SHEEVAPLUG)	+= sheevaplug-setup.o
-obj-$(CONFIG_MACH_GURUPLUG)		+= guruplug-setup.o
-obj-$(CONFIG_MACH_INETSPACE_V2)		+= netspace_v2-setup.o lacie_v2-common.o
-obj-$(CONFIG_MACH_MV88F6281GTW_GE)	+= mv88f6281gtw_ge-setup.o
 obj-$(CONFIG_MACH_NET2BIG_V2)		+= netxbig_v2-setup.o lacie_v2-common.o
 obj-$(CONFIG_MACH_NET5BIG_V2)		+= netxbig_v2-setup.o lacie_v2-common.o
-obj-$(CONFIG_MACH_NETSPACE_MAX_V2)	+= netspace_v2-setup.o lacie_v2-common.o
-obj-$(CONFIG_MACH_NETSPACE_V2)		+= netspace_v2-setup.o lacie_v2-common.o
 obj-$(CONFIG_MACH_OPENRD)		+= openrd-setup.o
 obj-$(CONFIG_MACH_RD88F6192_NAS)	+= rd88f6192-nas-setup.o
 obj-$(CONFIG_MACH_RD88F6281)		+= rd88f6281-setup.o
-obj-$(CONFIG_MACH_SHEEVAPLUG)		+= sheevaplug-setup.o
 obj-$(CONFIG_MACH_T5325)		+= t5325-setup.o
 obj-$(CONFIG_MACH_TS219)		+= ts219-setup.o tsx1x-common.o
 obj-$(CONFIG_MACH_TS41X)		+= ts41x-setup.o tsx1x-common.o
 
 obj-$(CONFIG_ARCH_KIRKWOOD_DT)		+= board-dt.o
-obj-$(CONFIG_MACH_CLOUDBOX_DT)		+= board-ns2.o
-obj-$(CONFIG_MACH_DB88F628X_BP_DT)	+= board-db88f628x-bp.o
-obj-$(CONFIG_MACH_DLINK_KIRKWOOD_DT)	+= board-dnskw.o
-obj-$(CONFIG_MACH_DOCKSTAR_DT)		+= board-dockstar.o
-obj-$(CONFIG_MACH_DREAMPLUG_DT)		+= board-dreamplug.o
-obj-$(CONFIG_MACH_GOFLEXNET_DT)		+= board-goflexnet.o
-obj-$(CONFIG_MACH_GURUPLUG_DT)		+= board-guruplug.o
-obj-$(CONFIG_MACH_IB62X0_DT)		+= board-ib62x0.o
-obj-$(CONFIG_MACH_ICONNECT_DT)		+= board-iconnect.o
-obj-$(CONFIG_MACH_INETSPACE_V2_DT)	+= board-ns2.o
-obj-$(CONFIG_MACH_IOMEGA_IX2_200_DT)	+= board-iomega_ix2_200.o
-obj-$(CONFIG_MACH_KM_KIRKWOOD_DT)	+= board-km_kirkwood.o
-obj-$(CONFIG_MACH_LSXL_DT)		+= board-lsxl.o
-obj-$(CONFIG_MACH_MPLCEC4_DT)		+= board-mplcec4.o
-obj-$(CONFIG_MACH_NETSPACE_LITE_V2_DT)	+= board-ns2.o
-obj-$(CONFIG_MACH_NETSPACE_MAX_V2_DT)	+= board-ns2.o
-obj-$(CONFIG_MACH_NETSPACE_MINI_V2_DT)	+= board-ns2.o
-obj-$(CONFIG_MACH_NETSPACE_V2_DT)	+= board-ns2.o
-obj-$(CONFIG_MACH_OPENBLOCKS_A6_DT)	+= board-openblocks_a6.o
-obj-$(CONFIG_MACH_READYNAS_DT)		+= board-readynas.o
-obj-$(CONFIG_MACH_SHEEVAPLUG_DT)	+= board-sheevaplug.o
-obj-$(CONFIG_MACH_TOPKICK_DT)		+= board-usi_topkick.o
-obj-$(CONFIG_MACH_TS219_DT)		+= board-ts219.o tsx1x-common.o
+obj-$(CONFIG_MACH_MV88F6281GTW_GE_DT)	+= board-mv88f6281gtw_ge.o
diff --git a/arch/arm/mach-kirkwood/board-db88f628x-bp.c b/arch/arm/mach-kirkwood/board-db88f628x-bp.c
deleted file mode 100644
index 2f574bc8ed40..000000000000
--- a/arch/arm/mach-kirkwood/board-db88f628x-bp.c
+++ /dev/null
@@ -1,24 +0,0 @@
-/*
- * Saeed Bishara <saeed@marvell.com>
- *
- * Marvell DB-88F628{1,2}-BP Development Board Setup
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2.  This program is licensed "as is" without any
- * warranty of any kind, whether express or implied.
- */
-
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/of.h>
-#include <linux/mv643xx_eth.h>
-#include "common.h"
-
-static struct mv643xx_eth_platform_data db88f628x_ge00_data = {
-	.phy_addr	= MV643XX_ETH_PHY_ADDR(8),
-};
-
-void __init db88f628x_init(void)
-{
-	kirkwood_ge00_init(&db88f628x_ge00_data);
-}
diff --git a/arch/arm/mach-kirkwood/board-dnskw.c b/arch/arm/mach-kirkwood/board-dnskw.c
deleted file mode 100644
index a1aa87f09180..000000000000
--- a/arch/arm/mach-kirkwood/board-dnskw.c
+++ /dev/null
@@ -1,43 +0,0 @@
-/*
- * Copyright 2012 (C), Jamie Lentin <jm@lentin.co.uk>
- *
- * arch/arm/mach-kirkwood/board-dnskw.c
- *
- * D-link DNS-320 & DNS-325 NAS Init for drivers not converted to
- * flattened device tree yet.
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2.  This program is licensed "as is" without any
- * warranty of any kind, whether express or implied.
- */
-
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/platform_device.h>
-#include <linux/mv643xx_eth.h>
-#include <linux/gpio.h>
-#include "common.h"
-
-static struct mv643xx_eth_platform_data dnskw_ge00_data = {
-	.phy_addr	= MV643XX_ETH_PHY_ADDR(8),
-};
-
-/* Register any GPIO for output and set the value */
-static void __init dnskw_gpio_register(unsigned gpio, char *name, int def)
-{
-	if (gpio_request(gpio, name) == 0 &&
-	    gpio_direction_output(gpio, 0) == 0) {
-		gpio_set_value(gpio, def);
-		if (gpio_export(gpio, 0) != 0)
-			pr_err("dnskw: Failed to export GPIO %s\n", name);
-	} else
-		pr_err("dnskw: Failed to register %s\n", name);
-}
-
-void __init dnskw_init(void)
-{
-	kirkwood_ge00_init(&dnskw_ge00_data);
-
-	/* Set NAS to turn back on after a power failure */
-	dnskw_gpio_register(37, "dnskw:power:recover", 1);
-}
diff --git a/arch/arm/mach-kirkwood/board-dockstar.c b/arch/arm/mach-kirkwood/board-dockstar.c
deleted file mode 100644
index d7196db33984..000000000000
--- a/arch/arm/mach-kirkwood/board-dockstar.c
+++ /dev/null
@@ -1,32 +0,0 @@
-/*
- * arch/arm/mach-kirkwood/board-dockstar.c
- *
- * Seagate FreeAgent Dockstar Board Init for drivers not converted to
- * flattened device tree yet.
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2.  This program is licensed "as is" without any
- * warranty of any kind, whether express or implied.
- *
- * Copied and modified for Seagate GoFlex Net support by
- * Joshua Coombs <josh.coombs@gmail.com> based on ArchLinux ARM's
- * GoFlex kernel patches.
- *
- */
-
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/mv643xx_eth.h>
-#include "common.h"
-
-static struct mv643xx_eth_platform_data dockstar_ge00_data = {
-	.phy_addr	= MV643XX_ETH_PHY_ADDR(0),
-};
-
-void __init dockstar_dt_init(void)
-{
-	/*
-	 * Basic setup. Needs to be called early.
-	 */
-	kirkwood_ge00_init(&dockstar_ge00_data);
-}
diff --git a/arch/arm/mach-kirkwood/board-dreamplug.c b/arch/arm/mach-kirkwood/board-dreamplug.c
deleted file mode 100644
index 0903242c00dc..000000000000
--- a/arch/arm/mach-kirkwood/board-dreamplug.c
+++ /dev/null
@@ -1,35 +0,0 @@
-/*
- * Copyright 2012 (C), Jason Cooper <jason@lakedaemon.net>
- *
- * arch/arm/mach-kirkwood/board-dreamplug.c
- *
- * Marvell DreamPlug Reference Board Init for drivers not converted to
- * flattened device tree yet.
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2.  This program is licensed "as is" without any
- * warranty of any kind, whether express or implied.
- */
-
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/mv643xx_eth.h>
-#include <linux/gpio.h>
-#include "common.h"
-
-static struct mv643xx_eth_platform_data dreamplug_ge00_data = {
-	.phy_addr	= MV643XX_ETH_PHY_ADDR(0),
-};
-
-static struct mv643xx_eth_platform_data dreamplug_ge01_data = {
-	.phy_addr	= MV643XX_ETH_PHY_ADDR(1),
-};
-
-void __init dreamplug_init(void)
-{
-	/*
-	 * Basic setup. Needs to be called early.
-	 */
-	kirkwood_ge00_init(&dreamplug_ge00_data);
-	kirkwood_ge01_init(&dreamplug_ge01_data);
-}
diff --git a/arch/arm/mach-kirkwood/board-dt.c b/arch/arm/mach-kirkwood/board-dt.c
index 6e122ed3282f..82d3ad8e87cf 100644
--- a/arch/arm/mach-kirkwood/board-dt.c
+++ b/arch/arm/mach-kirkwood/board-dt.c
@@ -15,6 +15,9 @@
 #include <linux/of.h>
 #include <linux/of_platform.h>
 #include <linux/clk-provider.h>
+#include <linux/clocksource.h>
+#include <linux/dma-mapping.h>
+#include <linux/irqchip.h>
 #include <linux/kexec.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
@@ -49,10 +52,6 @@ static void __init kirkwood_legacy_clk_init(void)
 	orion_clkdev_add("1", "pcie",
 			 of_clk_get_from_provider(&clkspec));
 
-	clkspec.args[0] = CGC_BIT_SDIO;
-	orion_clkdev_add(NULL, "mvsdio",
-			 of_clk_get_from_provider(&clkspec));
-
 	/*
 	 * The ethernet interfaces forget the MAC address assigned by
 	 * u-boot if the clocks are turned off. Until proper DT support
@@ -60,19 +59,24 @@ static void __init kirkwood_legacy_clk_init(void)
 	 */
 	clkspec.args[0] = CGC_BIT_GE0;
 	clk = of_clk_get_from_provider(&clkspec);
-	orion_clkdev_add(NULL, "mv643xx_eth_port.0", clk);
 	clk_prepare_enable(clk);
 
 	clkspec.args[0] = CGC_BIT_GE1;
 	clk = of_clk_get_from_provider(&clkspec);
-	orion_clkdev_add(NULL, "mv643xx_eth_port.1", clk);
 	clk_prepare_enable(clk);
 }
 
-static void __init kirkwood_of_clk_init(void)
+static void __init kirkwood_dt_time_init(void)
 {
 	of_clk_init(NULL);
-	kirkwood_legacy_clk_init();
+	clocksource_of_init();
+}
+
+static void __init kirkwood_dt_init_early(void)
+{
+	mvebu_mbus_init("marvell,kirkwood-mbus",
+			BRIDGE_WINS_BASE, BRIDGE_WINS_SZ,
+			DDR_WINDOW_CPU_BASE, DDR_WINDOW_CPU_SZ);
 }
 
 static void __init kirkwood_dt_init(void)
@@ -87,14 +91,15 @@ static void __init kirkwood_dt_init(void)
 	 */
 	writel(readl(CPU_CONFIG) & ~CPU_CONFIG_ERROR_PROP, CPU_CONFIG);
 
+	BUG_ON(mvebu_mbus_dt_init());
 	kirkwood_setup_wins();
 
 	kirkwood_l2_init();
 
 	kirkwood_cpufreq_init();
 
-	/* Setup root of clk tree */
-	kirkwood_of_clk_init();
+	/* Setup clocks for legacy devices */
+	kirkwood_legacy_clk_init();
 
 	kirkwood_cpuidle_init();
 
@@ -102,105 +107,22 @@ static void __init kirkwood_dt_init(void)
 	kexec_reinit = kirkwood_enable_pcie;
 #endif
 
-	if (of_machine_is_compatible("globalscale,dreamplug"))
-		dreamplug_init();
-
-	if (of_machine_is_compatible("globalscale,guruplug"))
-		guruplug_dt_init();
-
-	if (of_machine_is_compatible("globalscale,sheevaplug"))
-		sheevaplug_dt_init();
-
-	if (of_machine_is_compatible("dlink,dns-kirkwood"))
-		dnskw_init();
-
-	if (of_machine_is_compatible("iom,iconnect"))
-		iconnect_init();
-
-	if (of_machine_is_compatible("raidsonic,ib-nas62x0"))
-		ib62x0_init();
-
-	if (of_machine_is_compatible("qnap,ts219"))
-		qnap_dt_ts219_init();
-
-	if (of_machine_is_compatible("seagate,dockstar"))
-		dockstar_dt_init();
-
-	if (of_machine_is_compatible("seagate,goflexnet"))
-		goflexnet_init();
-
-	if (of_machine_is_compatible("buffalo,lsxl"))
-		lsxl_init();
-
-	if (of_machine_is_compatible("iom,ix2-200"))
-		iomega_ix2_200_init();
-
-	if (of_machine_is_compatible("keymile,km_kirkwood"))
-		km_kirkwood_init();
-
-	if (of_machine_is_compatible("lacie,cloudbox") ||
-	    of_machine_is_compatible("lacie,inetspace_v2") ||
-	    of_machine_is_compatible("lacie,netspace_lite_v2") ||
-	    of_machine_is_compatible("lacie,netspace_max_v2") ||
-	    of_machine_is_compatible("lacie,netspace_mini_v2") ||
-	    of_machine_is_compatible("lacie,netspace_v2"))
-		ns2_init();
-
-	if (of_machine_is_compatible("marvell,db-88f6281-bp") ||
-	    of_machine_is_compatible("marvell,db-88f6282-bp"))
-		db88f628x_init();
-
-	if (of_machine_is_compatible("mpl,cec4"))
-		mplcec4_init();
-
-	if (of_machine_is_compatible("netgear,readynas-duo-v2"))
-		netgear_readynas_init();
-
-	if (of_machine_is_compatible("plathome,openblocks-a6"))
-		openblocks_a6_init();
-
-	if (of_machine_is_compatible("usi,topkick"))
-		usi_topkick_init();
+	if (of_machine_is_compatible("marvell,mv88f6281gtw-ge"))
+		mv88f6281gtw_ge_init();
 
 	of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
 }
 
 static const char * const kirkwood_dt_board_compat[] = {
-	"globalscale,dreamplug",
-	"globalscale,guruplug",
-	"globalscale,sheevaplug",
-	"dlink,dns-320",
-	"dlink,dns-325",
-	"iom,iconnect",
-	"raidsonic,ib-nas62x0",
-	"qnap,ts219",
-	"seagate,dockstar",
-	"seagate,goflexnet",
-	"buffalo,lsxl",
-	"iom,ix2-200",
-	"keymile,km_kirkwood",
-	"lacie,cloudbox",
-	"lacie,inetspace_v2",
-	"lacie,netspace_lite_v2",
-	"lacie,netspace_max_v2",
-	"lacie,netspace_mini_v2",
-	"lacie,netspace_v2",
-	"marvell,db-88f6281-bp",
-	"marvell,db-88f6282-bp",
-	"mpl,cec4",
-	"netgear,readynas-duo-v2",
-	"plathome,openblocks-a6",
-	"usi,topkick",
-	"zyxel,nsa310",
+	"marvell,kirkwood",
 	NULL
 };
 
 DT_MACHINE_START(KIRKWOOD_DT, "Marvell Kirkwood (Flattened Device Tree)")
 	/* Maintainer: Jason Cooper <jason@lakedaemon.net> */
 	.map_io		= kirkwood_map_io,
-	.init_early	= kirkwood_init_early,
-	.init_irq	= orion_dt_init_irq,
-	.init_time	= kirkwood_timer_init,
+	.init_early	= kirkwood_dt_init_early,
+	.init_time	= kirkwood_dt_time_init,
 	.init_machine	= kirkwood_dt_init,
 	.restart	= kirkwood_restart,
 	.dt_compat	= kirkwood_dt_board_compat,
diff --git a/arch/arm/mach-kirkwood/board-goflexnet.c b/arch/arm/mach-kirkwood/board-goflexnet.c
deleted file mode 100644
index 9db979aec82e..000000000000
--- a/arch/arm/mach-kirkwood/board-goflexnet.c
+++ /dev/null
@@ -1,34 +0,0 @@
-/*
- * Copyright 2012 (C), Jason Cooper <jason@lakedaemon.net>
- *
- * arch/arm/mach-kirkwood/board-goflexnet.c
- *
- * Seagate GoFlext Net Board Init for drivers not converted to
- * flattened device tree yet.
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2.  This program is licensed "as is" without any
- * warranty of any kind, whether express or implied.
- *
- * Copied and modified for Seagate GoFlex Net support by
- * Joshua Coombs <josh.coombs@gmail.com> based on ArchLinux ARM's
- * GoFlex kernel patches.
- *
- */
-
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/mv643xx_eth.h>
-#include "common.h"
-
-static struct mv643xx_eth_platform_data goflexnet_ge00_data = {
-	.phy_addr	= MV643XX_ETH_PHY_ADDR(0),
-};
-
-void __init goflexnet_init(void)
-{
-	/*
-	 * Basic setup. Needs to be called early.
-	 */
-	kirkwood_ge00_init(&goflexnet_ge00_data);
-}
diff --git a/arch/arm/mach-kirkwood/board-guruplug.c b/arch/arm/mach-kirkwood/board-guruplug.c
deleted file mode 100644
index a857163954a5..000000000000
--- a/arch/arm/mach-kirkwood/board-guruplug.c
+++ /dev/null
@@ -1,33 +0,0 @@
-/*
- * arch/arm/mach-kirkwood/board-guruplug.c
- *
- * Marvell Guruplug Reference Board Init for drivers not converted to
- * flattened device tree yet.
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2.  This program is licensed "as is" without any
- * warranty of any kind, whether express or implied.
- */
-
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/mv643xx_eth.h>
-#include <linux/gpio.h>
-#include "common.h"
-
-static struct mv643xx_eth_platform_data guruplug_ge00_data = {
-	.phy_addr	= MV643XX_ETH_PHY_ADDR(0),
-};
-
-static struct mv643xx_eth_platform_data guruplug_ge01_data = {
-	.phy_addr	= MV643XX_ETH_PHY_ADDR(1),
-};
-
-void __init guruplug_dt_init(void)
-{
-	/*
-	 * Basic setup. Needs to be called early.
-	 */
-	kirkwood_ge00_init(&guruplug_ge00_data);
-	kirkwood_ge01_init(&guruplug_ge01_data);
-}
diff --git a/arch/arm/mach-kirkwood/board-ib62x0.c b/arch/arm/mach-kirkwood/board-ib62x0.c
deleted file mode 100644
index 9a857ae83984..000000000000
--- a/arch/arm/mach-kirkwood/board-ib62x0.c
+++ /dev/null
@@ -1,29 +0,0 @@
-/*
- * Copyright 2012 (C), Simon Baatz <gmbnomis@gmail.com>
- *
- * arch/arm/mach-kirkwood/board-ib62x0.c
- *
- * RaidSonic ICY BOX IB-NAS6210 & IB-NAS6220 init for drivers not
- * converted to flattened device tree yet.
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2.  This program is licensed "as is" without any
- * warranty of any kind, whether express or implied.
- */
-
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/mv643xx_eth.h>
-#include "common.h"
-
-static struct mv643xx_eth_platform_data ib62x0_ge00_data = {
-	.phy_addr	= MV643XX_ETH_PHY_ADDR(8),
-};
-
-void __init ib62x0_init(void)
-{
-	/*
-	 * Basic setup. Needs to be called early.
-	 */
-	kirkwood_ge00_init(&ib62x0_ge00_data);
-}
diff --git a/arch/arm/mach-kirkwood/board-iconnect.c b/arch/arm/mach-kirkwood/board-iconnect.c
deleted file mode 100644
index 98b5ad1bba90..000000000000
--- a/arch/arm/mach-kirkwood/board-iconnect.c
+++ /dev/null
@@ -1,24 +0,0 @@
-/*
- * arch/arm/mach-kirkwood/board-iconnect.c
- *
- * Iomega i-connect Board Setup
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2.  This program is licensed "as is" without any
- * warranty of any kind, whether express or implied.
- */
-
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/of.h>
-#include <linux/mv643xx_eth.h>
-#include "common.h"
-
-static struct mv643xx_eth_platform_data iconnect_ge00_data = {
-	.phy_addr	= MV643XX_ETH_PHY_ADDR(11),
-};
-
-void __init iconnect_init(void)
-{
-	kirkwood_ge00_init(&iconnect_ge00_data);
-}
diff --git a/arch/arm/mach-kirkwood/board-iomega_ix2_200.c b/arch/arm/mach-kirkwood/board-iomega_ix2_200.c
deleted file mode 100644
index e5f70415905a..000000000000
--- a/arch/arm/mach-kirkwood/board-iomega_ix2_200.c
+++ /dev/null
@@ -1,34 +0,0 @@
-/*
- * arch/arm/mach-kirkwood/board-iomega_ix2_200.c
- *
- * Iomega StorCenter ix2-200
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2.  This program is licensed "as is" without any
- * warranty of any kind, whether express or implied.
- */
-
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/mv643xx_eth.h>
-#include <linux/ethtool.h>
-#include "common.h"
-
-static struct mv643xx_eth_platform_data iomega_ix2_200_ge00_data = {
-	.phy_addr       = MV643XX_ETH_PHY_NONE,
-	.speed          = SPEED_1000,
-	.duplex         = DUPLEX_FULL,
-};
-
-static struct mv643xx_eth_platform_data iomega_ix2_200_ge01_data = {
-        .phy_addr       = MV643XX_ETH_PHY_ADDR(11),
-};
-
-void __init iomega_ix2_200_init(void)
-{
-	/*
-	 * Basic setup. Needs to be called early.
-	 */
-	kirkwood_ge00_init(&iomega_ix2_200_ge00_data);
-	kirkwood_ge01_init(&iomega_ix2_200_ge01_data);
-}
diff --git a/arch/arm/mach-kirkwood/board-km_kirkwood.c b/arch/arm/mach-kirkwood/board-km_kirkwood.c
deleted file mode 100644
index 44e4605ba0bf..000000000000
--- a/arch/arm/mach-kirkwood/board-km_kirkwood.c
+++ /dev/null
@@ -1,44 +0,0 @@
-/*
- * Copyright 2012 2012 KEYMILE AG, CH-3097 Bern
- * Valentin Longchamp <valentin.longchamp@keymile.com>
- *
- * arch/arm/mach-kirkwood/board-km_kirkwood.c
- *
- * Keymile km_kirkwood Reference Desing Init for drivers not converted to
- * flattened device tree yet.
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2.  This program is licensed "as is" without any
- * warranty of any kind, whether express or implied.
- */
-
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/mv643xx_eth.h>
-#include <linux/clk.h>
-#include <linux/clk-private.h>
-#include "common.h"
-
-static struct mv643xx_eth_platform_data km_kirkwood_ge00_data = {
-	.phy_addr	= MV643XX_ETH_PHY_ADDR(0),
-};
-
-void __init km_kirkwood_init(void)
-{
-	struct clk *sata_clk;
-	/*
-	 * Our variant of kirkwood (integrated in the Bobcat) hangs on accessing
-	 * SATA bits (14-15) of the Clock Gating Control Register. Since these
-	 * devices are also not present in this variant, their clocks get
-	 * disabled because unused when clk_disable_unused() gets called.
-	 * That's why we change the flags to these clocks to CLK_IGNORE_UNUSED
-	 */
-	sata_clk = clk_get_sys("sata_mv.0", "0");
-	if (!IS_ERR(sata_clk))
-		sata_clk->flags |= CLK_IGNORE_UNUSED;
-	sata_clk = clk_get_sys("sata_mv.0", "1");
-	if (!IS_ERR(sata_clk))
-		sata_clk->flags |= CLK_IGNORE_UNUSED;
-
-	kirkwood_ge00_init(&km_kirkwood_ge00_data);
-}
diff --git a/arch/arm/mach-kirkwood/board-lsxl.c b/arch/arm/mach-kirkwood/board-lsxl.c
deleted file mode 100644
index 348395238df6..000000000000
--- a/arch/arm/mach-kirkwood/board-lsxl.c
+++ /dev/null
@@ -1,36 +0,0 @@
-/*
- * Copyright 2012 (C), Michael Walle <michael@walle.cc>
- *
- * arch/arm/mach-kirkwood/board-lsxl.c
- *
- * Buffalo Linkstation LS-XHL and LS-CHLv2 init for drivers not
- * converted to flattened device tree yet.
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2.  This program is licensed "as is" without any
- * warranty of any kind, whether express or implied.
- */
-
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/platform_device.h>
-#include <linux/mv643xx_eth.h>
-#include "common.h"
-
-static struct mv643xx_eth_platform_data lsxl_ge00_data = {
-	.phy_addr	= MV643XX_ETH_PHY_ADDR(0),
-};
-
-static struct mv643xx_eth_platform_data lsxl_ge01_data = {
-	.phy_addr	= MV643XX_ETH_PHY_ADDR(8),
-};
-
-void __init lsxl_init(void)
-{
-	/*
-	 * Basic setup. Needs to be called early.
-	 */
-
-	kirkwood_ge00_init(&lsxl_ge00_data);
-	kirkwood_ge01_init(&lsxl_ge01_data);
-}
diff --git a/arch/arm/mach-kirkwood/board-mplcec4.c b/arch/arm/mach-kirkwood/board-mplcec4.c
deleted file mode 100644
index 938712e248f1..000000000000
--- a/arch/arm/mach-kirkwood/board-mplcec4.c
+++ /dev/null
@@ -1,35 +0,0 @@
-/*
- * Copyright (C) 2012 MPL AG, Switzerland
- * Stefan Peter <s.peter@mpl.ch>
- *
- * arch/arm/mach-kirkwood/board-mplcec4.c
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2.  This program is licensed "as is" without any
- * warranty of any kind, whether express or implied.
- */
-
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/mv643xx_eth.h>
-#include "common.h"
-
-static struct mv643xx_eth_platform_data mplcec4_ge00_data = {
-	.phy_addr	= MV643XX_ETH_PHY_ADDR(1),
-};
-
-static struct mv643xx_eth_platform_data mplcec4_ge01_data = {
-	.phy_addr	= MV643XX_ETH_PHY_ADDR(2),
-};
-
-void __init mplcec4_init(void)
-{
-	/*
-	 * Basic setup. Needs to be called early.
-	 */
-	kirkwood_ge00_init(&mplcec4_ge00_data);
-	kirkwood_ge01_init(&mplcec4_ge01_data);
-}
-
-
-
diff --git a/arch/arm/mach-kirkwood/board-mv88f6281gtw_ge.c b/arch/arm/mach-kirkwood/board-mv88f6281gtw_ge.c
new file mode 100644
index 000000000000..ee5eea678c11
--- /dev/null
+++ b/arch/arm/mach-kirkwood/board-mv88f6281gtw_ge.c
@@ -0,0 +1,50 @@
+/*
+ * arch/arm/mach-kirkwood/board-mv88f6281gtw_ge.c
+ *
+ * Marvell 88F6281 GTW GE Board Setup
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2.  This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/platform_device.h>
+#include <linux/irq.h>
+#include <linux/timer.h>
+#include <linux/mv643xx_eth.h>
+#include <linux/ethtool.h>
+#include <linux/gpio.h>
+#include <net/dsa.h>
+#include <asm/mach-types.h>
+#include <asm/mach/arch.h>
+#include <asm/mach/pci.h>
+#include <mach/kirkwood.h>
+#include "common.h"
+
+static struct mv643xx_eth_platform_data mv88f6281gtw_ge_ge00_data = {
+	.phy_addr	= MV643XX_ETH_PHY_NONE,
+	.speed		= SPEED_1000,
+	.duplex		= DUPLEX_FULL,
+};
+
+static struct dsa_chip_data mv88f6281gtw_ge_switch_chip_data = {
+	.port_names[0]	= "lan1",
+	.port_names[1]	= "lan2",
+	.port_names[2]	= "lan3",
+	.port_names[3]	= "lan4",
+	.port_names[4]	= "wan",
+	.port_names[5]	= "cpu",
+};
+
+static struct dsa_platform_data mv88f6281gtw_ge_switch_plat_data = {
+	.nr_chips	= 1,
+	.chip		= &mv88f6281gtw_ge_switch_chip_data,
+};
+
+void __init mv88f6281gtw_ge_init(void)
+{
+	kirkwood_ge00_init(&mv88f6281gtw_ge_ge00_data);
+	kirkwood_ge00_switch_init(&mv88f6281gtw_ge_switch_plat_data, NO_IRQ);
+}
diff --git a/arch/arm/mach-kirkwood/board-ns2.c b/arch/arm/mach-kirkwood/board-ns2.c
deleted file mode 100644
index f8f660525ace..000000000000
--- a/arch/arm/mach-kirkwood/board-ns2.c
+++ /dev/null
@@ -1,35 +0,0 @@
-/*
- * Copyright 2012 (C), Simon Guinot <simon.guinot@sequanux.org>
- *
- * arch/arm/mach-kirkwood/board-ns2.c
- *
- * LaCie Network Space v2 board (and parents) initialization for drivers
- * not converted to flattened device tree yet.
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2.  This program is licensed "as is" without any
- * warranty of any kind, whether express or implied.
- */
-
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/platform_device.h>
-#include <linux/mv643xx_eth.h>
-#include <linux/of.h>
-#include "common.h"
-
-static struct mv643xx_eth_platform_data ns2_ge00_data = {
-	.phy_addr	= MV643XX_ETH_PHY_ADDR(8),
-};
-
-void __init ns2_init(void)
-{
-	/*
-	 * Basic setup. Needs to be called early.
-	 */
-	if (of_machine_is_compatible("lacie,cloudbox") ||
-	    of_machine_is_compatible("lacie,netspace_lite_v2") ||
-	    of_machine_is_compatible("lacie,netspace_mini_v2"))
-		ns2_ge00_data.phy_addr = MV643XX_ETH_PHY_ADDR(0);
-	kirkwood_ge00_init(&ns2_ge00_data);
-}
diff --git a/arch/arm/mach-kirkwood/board-openblocks_a6.c b/arch/arm/mach-kirkwood/board-openblocks_a6.c
deleted file mode 100644
index b11d8fdeca93..000000000000
--- a/arch/arm/mach-kirkwood/board-openblocks_a6.c
+++ /dev/null
@@ -1,26 +0,0 @@
-/*
- * Copyright 2012 Nobuhiro Iwamatsu <iwamatsu@nigauri.org>
- *
- * arch/arm/mach-kirkwood/board-openblocks_a6.c
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2.  This program is licensed "as is" without any
- * warranty of any kind, whether express or implied.
- */
-
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/mv643xx_eth.h>
-#include "common.h"
-
-static struct mv643xx_eth_platform_data openblocks_ge00_data = {
-	.phy_addr	= MV643XX_ETH_PHY_ADDR(0),
-};
-
-void __init openblocks_a6_init(void)
-{
-	/*
-	 * Basic setup. Needs to be called early.
-	 */
-	kirkwood_ge00_init(&openblocks_ge00_data);
-}
diff --git a/arch/arm/mach-kirkwood/board-readynas.c b/arch/arm/mach-kirkwood/board-readynas.c
deleted file mode 100644
index 341b82d9cadb..000000000000
--- a/arch/arm/mach-kirkwood/board-readynas.c
+++ /dev/null
@@ -1,27 +0,0 @@
-/*
- * NETGEAR ReadyNAS Duo v2 Board setup for drivers not already
- * converted to DT.
- *
- * Copyright (C) 2013, Arnaud EBALARD <arno@natisbad.org>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- */
-
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/platform_device.h>
-#include <linux/mv643xx_eth.h>
-#include <mach/kirkwood.h>
-#include "common.h"
-
-static struct mv643xx_eth_platform_data netgear_readynas_ge00_data = {
-	.phy_addr	= MV643XX_ETH_PHY_ADDR(0),
-};
-
-void __init netgear_readynas_init(void)
-{
-	kirkwood_ge00_init(&netgear_readynas_ge00_data);
-}
diff --git a/arch/arm/mach-kirkwood/board-sheevaplug.c b/arch/arm/mach-kirkwood/board-sheevaplug.c
deleted file mode 100644
index fa389373ca74..000000000000
--- a/arch/arm/mach-kirkwood/board-sheevaplug.c
+++ /dev/null
@@ -1,27 +0,0 @@
-/*
- * arch/arm/mach-kirkwood/board-sheevaplug.c
- *
- * Marvell Sheevaplug Reference Board Init for drivers not converted to
- * flattened device tree yet.
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2.  This program is licensed "as is" without any
- * warranty of any kind, whether express or implied.
- */
-
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/mv643xx_eth.h>
-#include "common.h"
-
-static struct mv643xx_eth_platform_data sheevaplug_ge00_data = {
-	.phy_addr	= MV643XX_ETH_PHY_ADDR(0),
-};
-
-void __init sheevaplug_dt_init(void)
-{
-	/*
-	 * Basic setup. Needs to be called early.
-	 */
-	kirkwood_ge00_init(&sheevaplug_ge00_data);
-}
diff --git a/arch/arm/mach-kirkwood/board-ts219.c b/arch/arm/mach-kirkwood/board-ts219.c
deleted file mode 100644
index 860f44ab457d..000000000000
--- a/arch/arm/mach-kirkwood/board-ts219.c
+++ /dev/null
@@ -1,40 +0,0 @@
-/*
- *
- * QNAP TS-11x/TS-21x Turbo NAS Board Setup via DT
- *
- * Copyright (C) 2012 Andrew Lunn <andrew@lunn.ch>
- *
- * Based on the board file ts219-setup.c:
- *
- * Copyright (C) 2009  Martin Michlmayr <tbm@cyrius.com>
- * Copyright (C) 2008  Byron Bradley <byron.bbradley@gmail.com>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- */
-
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/platform_device.h>
-#include <linux/mv643xx_eth.h>
-#include <asm/mach-types.h>
-#include <asm/mach/arch.h>
-#include <mach/kirkwood.h>
-#include "common.h"
-
-static struct mv643xx_eth_platform_data qnap_ts219_ge00_data = {
-	.phy_addr	= MV643XX_ETH_PHY_ADDR(8),
-};
-
-void __init qnap_dt_ts219_init(void)
-{
-	u32 dev, rev;
-
-	kirkwood_pcie_id(&dev, &rev);
-	if (dev == MV88F6282_DEV_ID)
-		qnap_ts219_ge00_data.phy_addr = MV643XX_ETH_PHY_ADDR(0);
-
-	kirkwood_ge00_init(&qnap_ts219_ge00_data);
-}
diff --git a/arch/arm/mach-kirkwood/board-usi_topkick.c b/arch/arm/mach-kirkwood/board-usi_topkick.c
deleted file mode 100644
index 1cc04ec33f0b..000000000000
--- a/arch/arm/mach-kirkwood/board-usi_topkick.c
+++ /dev/null
@@ -1,29 +0,0 @@
-/*
- * Copyright 2012 (C), Jason Cooper <jason@lakedaemon.net>
- *
- * arch/arm/mach-kirkwood/board-usi_topkick.c
- *
- * USI Topkick Init for drivers not converted to flattened device tree yet.
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2.  This program is licensed "as is" without any
- * warranty of any kind, whether express or implied.
- */
-
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/mv643xx_eth.h>
-#include <linux/gpio.h>
-#include "common.h"
-
-static struct mv643xx_eth_platform_data topkick_ge00_data = {
-	.phy_addr	= MV643XX_ETH_PHY_ADDR(0),
-};
-
-void __init usi_topkick_init(void)
-{
-	/*
-	 * Basic setup. Needs to be called early.
-	 */
-	kirkwood_ge00_init(&topkick_ge00_data);
-}
diff --git a/arch/arm/mach-kirkwood/common.c b/arch/arm/mach-kirkwood/common.c
index e9238b5567ee..176761134a66 100644
--- a/arch/arm/mach-kirkwood/common.c
+++ b/arch/arm/mach-kirkwood/common.c
@@ -37,6 +37,12 @@
 #include <linux/platform_data/dma-mv_xor.h>
 #include "common.h"
 
+/* These can go away once Kirkwood uses the mvebu-mbus DT binding */
+#define KIRKWOOD_MBUS_NAND_TARGET 0x01
+#define KIRKWOOD_MBUS_NAND_ATTR   0x2f
+#define KIRKWOOD_MBUS_SRAM_TARGET 0x03
+#define KIRKWOOD_MBUS_SRAM_ATTR   0x01
+
 /*****************************************************************************
  * I/O Address Mapping
  ****************************************************************************/
@@ -264,7 +270,7 @@ void __init kirkwood_clk_init(void)
 	orion_clkdev_add(NULL, MV_XOR_NAME ".1", xor1);
 	orion_clkdev_add("0", "pcie", pex0);
 	orion_clkdev_add("1", "pcie", pex1);
-	orion_clkdev_add(NULL, "kirkwood-i2s", audio);
+	orion_clkdev_add(NULL, "mvebu-audio", audio);
 	orion_clkdev_add(NULL, MV64XXX_I2C_CTLR_NAME ".0", runit);
 	orion_clkdev_add(NULL, MV64XXX_I2C_CTLR_NAME ".1", runit);
 
@@ -528,10 +534,6 @@ void __init kirkwood_cpuidle_init(void)
 void __init kirkwood_init_early(void)
 {
 	orion_time_set_base(TIMER_VIRT_BASE);
-
-	mvebu_mbus_init("marvell,kirkwood-mbus",
-			BRIDGE_WINS_BASE, BRIDGE_WINS_SZ,
-			DDR_WINDOW_CPU_BASE, DDR_WINDOW_CPU_SZ);
 }
 
 int kirkwood_tclk;
@@ -560,7 +562,7 @@ void __init kirkwood_timer_init(void)
 /*****************************************************************************
  * Audio
  ****************************************************************************/
-static struct resource kirkwood_i2s_resources[] = {
+static struct resource kirkwood_audio_resources[] = {
 	[0] = {
 		.start  = AUDIO_PHYS_BASE,
 		.end    = AUDIO_PHYS_BASE + SZ_16K - 1,
@@ -573,29 +575,23 @@ static struct resource kirkwood_i2s_resources[] = {
 	},
 };
 
-static struct kirkwood_asoc_platform_data kirkwood_i2s_data = {
+static struct kirkwood_asoc_platform_data kirkwood_audio_data = {
 	.burst       = 128,
 };
 
-static struct platform_device kirkwood_i2s_device = {
-	.name		= "kirkwood-i2s",
+static struct platform_device kirkwood_audio_device = {
+	.name		= "mvebu-audio",
 	.id		= -1,
-	.num_resources	= ARRAY_SIZE(kirkwood_i2s_resources),
-	.resource	= kirkwood_i2s_resources,
+	.num_resources	= ARRAY_SIZE(kirkwood_audio_resources),
+	.resource	= kirkwood_audio_resources,
 	.dev		= {
-		.platform_data	= &kirkwood_i2s_data,
+		.platform_data	= &kirkwood_audio_data,
 	},
 };
 
-static struct platform_device kirkwood_pcm_device = {
-	.name		= "kirkwood-pcm-audio",
-	.id		= -1,
-};
-
 void __init kirkwood_audio_init(void)
 {
-	platform_device_register(&kirkwood_i2s_device);
-	platform_device_register(&kirkwood_pcm_device);
+	platform_device_register(&kirkwood_audio_device);
 }
 
 /*****************************************************************************
@@ -672,10 +668,14 @@ char * __init kirkwood_id(void)
 
 void __init kirkwood_setup_wins(void)
 {
-	mvebu_mbus_add_window("nand", KIRKWOOD_NAND_MEM_PHYS_BASE,
-			      KIRKWOOD_NAND_MEM_SIZE);
-	mvebu_mbus_add_window("sram", KIRKWOOD_SRAM_PHYS_BASE,
-			      KIRKWOOD_SRAM_SIZE);
+	mvebu_mbus_add_window_by_id(KIRKWOOD_MBUS_NAND_TARGET,
+				    KIRKWOOD_MBUS_NAND_ATTR,
+				    KIRKWOOD_NAND_MEM_PHYS_BASE,
+				    KIRKWOOD_NAND_MEM_SIZE);
+	mvebu_mbus_add_window_by_id(KIRKWOOD_MBUS_SRAM_TARGET,
+				    KIRKWOOD_MBUS_SRAM_ATTR,
+				    KIRKWOOD_SRAM_PHYS_BASE,
+				    KIRKWOOD_SRAM_SIZE);
 }
 
 void __init kirkwood_l2_init(void)
@@ -703,6 +703,10 @@ void __init kirkwood_init(void)
 	 */
 	writel(readl(CPU_CONFIG) & ~CPU_CONFIG_ERROR_PROP, CPU_CONFIG);
 
+	BUG_ON(mvebu_mbus_init("marvell,kirkwood-mbus",
+			BRIDGE_WINS_BASE, BRIDGE_WINS_SZ,
+			DDR_WINDOW_CPU_BASE, DDR_WINDOW_CPU_SZ));
+
 	kirkwood_setup_wins();
 
 	kirkwood_l2_init();
diff --git a/arch/arm/mach-kirkwood/common.h b/arch/arm/mach-kirkwood/common.h
index fcf3ba682e24..1296de94febf 100644
--- a/arch/arm/mach-kirkwood/common.h
+++ b/arch/arm/mach-kirkwood/common.h
@@ -59,119 +59,10 @@ void kirkwood_restart(enum reboot_mode, const char *);
 void kirkwood_clk_init(void);
 
 /* board init functions for boards not fully converted to fdt */
-#ifdef CONFIG_MACH_DREAMPLUG_DT
-void dreamplug_init(void);
+#ifdef CONFIG_MACH_MV88F6281GTW_GE_DT
+void mv88f6281gtw_ge_init(void);
 #else
-static inline void dreamplug_init(void) {};
-#endif
-#ifdef CONFIG_MACH_GURUPLUG_DT
-void guruplug_dt_init(void);
-#else
-static inline void guruplug_dt_init(void) {};
-#endif
-#ifdef CONFIG_MACH_SHEEVAPLUG_DT
-void sheevaplug_dt_init(void);
-#else
-static inline void sheevaplug_dt_init(void) {};
-#endif
-#ifdef CONFIG_MACH_TS219_DT
-void qnap_dt_ts219_init(void);
-#else
-static inline void qnap_dt_ts219_init(void) {};
-#endif
-
-#ifdef CONFIG_MACH_DLINK_KIRKWOOD_DT
-void dnskw_init(void);
-#else
-static inline void dnskw_init(void) {};
-#endif
-
-#ifdef CONFIG_MACH_ICONNECT_DT
-void iconnect_init(void);
-#else
-static inline void iconnect_init(void) {};
-#endif
-
-#ifdef CONFIG_MACH_IB62X0_DT
-void ib62x0_init(void);
-#else
-static inline void ib62x0_init(void) {};
-#endif
-
-#ifdef CONFIG_MACH_DOCKSTAR_DT
-void dockstar_dt_init(void);
-#else
-static inline void dockstar_dt_init(void) {};
-#endif
-
-#ifdef CONFIG_MACH_GOFLEXNET_DT
-void goflexnet_init(void);
-#else
-static inline void goflexnet_init(void) {};
-#endif
-
-#ifdef CONFIG_MACH_LSXL_DT
-void lsxl_init(void);
-#else
-static inline void lsxl_init(void) {};
-#endif
-
-#ifdef CONFIG_MACH_IOMEGA_IX2_200_DT
-void iomega_ix2_200_init(void);
-#else
-static inline void iomega_ix2_200_init(void) {};
-#endif
-
-#ifdef CONFIG_MACH_KM_KIRKWOOD_DT
-void km_kirkwood_init(void);
-#else
-static inline void km_kirkwood_init(void) {};
-#endif
-
-#ifdef CONFIG_MACH_DB88F628X_BP_DT
-void db88f628x_init(void);
-#else
-static inline void db88f628x_init(void) {};
-#endif
-
-#ifdef CONFIG_MACH_MPLCEC4_DT
-void mplcec4_init(void);
-#else
-static inline void mplcec4_init(void) {};
-#endif
-
-#if defined(CONFIG_MACH_INETSPACE_V2_DT) || \
-	defined(CONFIG_MACH_NETSPACE_V2_DT) || \
-	defined(CONFIG_MACH_NETSPACE_MAX_V2_DT) || \
-	defined(CONFIG_MACH_NETSPACE_LITE_V2_DT) || \
-	defined(CONFIG_MACH_NETSPACE_MINI_V2_DT)
-void ns2_init(void);
-#else
-static inline void ns2_init(void) {};
-#endif
-
-#ifdef CONFIG_MACH_OPENBLOCKS_A6_DT
-void openblocks_a6_init(void);
-#else
-static inline void openblocks_a6_init(void) {};
-#endif
-
-#ifdef CONFIG_MACH_READYNAS_DT
-void netgear_readynas_init(void);
-#else
-static inline void netgear_readynas_init(void) {};
-#endif
-
-#ifdef CONFIG_MACH_TOPKICK_DT
-void usi_topkick_init(void);
-#else
-static inline void usi_topkick_init(void) {};
-#endif
-
-#ifdef CONFIG_MACH_CLOUDBOX_DT
-void cloudbox_init(void);
-#else
-static inline void cloudbox_init(void) {};
+static inline void mv88f6281gtw_ge_init(void) {};
 #endif
 
 /* early init functions not converted to fdt yet */
diff --git a/arch/arm/mach-kirkwood/dockstar-setup.c b/arch/arm/mach-kirkwood/dockstar-setup.c
deleted file mode 100644
index 060ccf9cb63f..000000000000
--- a/arch/arm/mach-kirkwood/dockstar-setup.c
+++ /dev/null
@@ -1,111 +0,0 @@
-/*
- * arch/arm/mach-kirkwood/dockstar-setup.c
- *
- * Seagate FreeAgent DockStar Setup
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2.  This program is licensed "as is" without any
- * warranty of any kind, whether express or implied.
- */
-
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/platform_device.h>
-#include <linux/ata_platform.h>
-#include <linux/mtd/partitions.h>
-#include <linux/mv643xx_eth.h>
-#include <linux/gpio.h>
-#include <linux/leds.h>
-#include <asm/mach-types.h>
-#include <asm/mach/arch.h>
-#include <mach/kirkwood.h>
-#include "common.h"
-#include "mpp.h"
-
-static struct mtd_partition dockstar_nand_parts[] = {
-	{
-		.name = "u-boot",
-		.offset = 0,
-		.size = SZ_1M
-	}, {
-		.name = "uImage",
-		.offset = MTDPART_OFS_NXTBLK,
-		.size = SZ_4M
-	}, {
-		.name = "root",
-		.offset = MTDPART_OFS_NXTBLK,
-		.size = MTDPART_SIZ_FULL
-	},
-};
-
-static struct mv643xx_eth_platform_data dockstar_ge00_data = {
-	.phy_addr	= MV643XX_ETH_PHY_ADDR(0),
-};
-
-static struct gpio_led dockstar_led_pins[] = {
-	{
-		.name			= "dockstar:green:health",
-		.default_trigger	= "default-on",
-		.gpio			= 46,
-		.active_low		= 1,
-	},
-	{
-		.name			= "dockstar:orange:misc",
-		.default_trigger	= "none",
-		.gpio			= 47,
-		.active_low		= 1,
-	},
-};
-
-static struct gpio_led_platform_data dockstar_led_data = {
-	.leds		= dockstar_led_pins,
-	.num_leds	= ARRAY_SIZE(dockstar_led_pins),
-};
-
-static struct platform_device dockstar_leds = {
-	.name	= "leds-gpio",
-	.id	= -1,
-	.dev	= {
-		.platform_data	= &dockstar_led_data,
-	}
-};
-
-static unsigned int dockstar_mpp_config[] __initdata = {
-	MPP29_GPIO,	/* USB Power Enable */
-	MPP46_GPIO,	/* LED green */
-	MPP47_GPIO,	/* LED orange */
-	0
-};
-
-static void __init dockstar_init(void)
-{
-	/*
-	 * Basic setup. Needs to be called early.
-	 */
-	kirkwood_init();
-
-	/* setup gpio pin select */
-	kirkwood_mpp_conf(dockstar_mpp_config);
-
-	kirkwood_uart0_init();
-	kirkwood_nand_init(ARRAY_AND_SIZE(dockstar_nand_parts), 25);
-
-	if (gpio_request(29, "USB Power Enable") != 0 ||
-	    gpio_direction_output(29, 1) != 0)
-		pr_err("can't set up GPIO 29 (USB Power Enable)\n");
-	kirkwood_ehci_init();
-
-	kirkwood_ge00_init(&dockstar_ge00_data);
-
-	platform_device_register(&dockstar_leds);
-}
-
-MACHINE_START(DOCKSTAR, "Seagate FreeAgent DockStar")
-	.atag_offset	= 0x100,
-	.init_machine	= dockstar_init,
-	.map_io		= kirkwood_map_io,
-	.init_early	= kirkwood_init_early,
-	.init_irq	= kirkwood_init_irq,
-	.init_time	= kirkwood_timer_init,
-	.restart	= kirkwood_restart,
-MACHINE_END
diff --git a/arch/arm/mach-kirkwood/guruplug-setup.c b/arch/arm/mach-kirkwood/guruplug-setup.c
deleted file mode 100644
index 08dd739aa709..000000000000
--- a/arch/arm/mach-kirkwood/guruplug-setup.c
+++ /dev/null
@@ -1,133 +0,0 @@
-/*
- * arch/arm/mach-kirkwood/guruplug-setup.c
- *
- * Marvell GuruPlug Reference Board Setup
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2.  This program is licensed "as is" without any
- * warranty of any kind, whether express or implied.
- */
-
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/platform_device.h>
-#include <linux/mtd/partitions.h>
-#include <linux/ata_platform.h>
-#include <linux/mv643xx_eth.h>
-#include <linux/gpio.h>
-#include <linux/leds.h>
-#include <asm/mach-types.h>
-#include <asm/mach/arch.h>
-#include <mach/kirkwood.h>
-#include <linux/platform_data/mmc-mvsdio.h>
-#include "common.h"
-#include "mpp.h"
-
-static struct mtd_partition guruplug_nand_parts[] = {
-	{
-		.name = "u-boot",
-		.offset = 0,
-		.size = SZ_1M
-	}, {
-		.name = "uImage",
-		.offset = MTDPART_OFS_NXTBLK,
-		.size = SZ_4M
-	}, {
-		.name = "root",
-		.offset = MTDPART_OFS_NXTBLK,
-		.size = MTDPART_SIZ_FULL
-	},
-};
-
-static struct mv643xx_eth_platform_data guruplug_ge00_data = {
-	.phy_addr	= MV643XX_ETH_PHY_ADDR(0),
-};
-
-static struct mv643xx_eth_platform_data guruplug_ge01_data = {
-	.phy_addr	= MV643XX_ETH_PHY_ADDR(1),
-};
-
-static struct mv_sata_platform_data guruplug_sata_data = {
-	.n_ports	= 1,
-};
-
-static struct mvsdio_platform_data guruplug_mvsdio_data = {
-	/* unfortunately the CD signal has not been connected */
-	.gpio_card_detect = -1,
-	.gpio_write_protect = -1,
-};
-
-static struct gpio_led guruplug_led_pins[] = {
-	{
-		.name			= "guruplug:red:health",
-		.gpio			= 46,
-		.active_low		= 1,
-	},
-	{
-		.name			= "guruplug:green:health",
-		.gpio			= 47,
-		.active_low		= 1,
-	},
-	{
-		.name			= "guruplug:red:wmode",
-		.gpio			= 48,
-		.active_low		= 1,
-	},
-	{
-		.name			= "guruplug:green:wmode",
-		.gpio			= 49,
-		.active_low		= 1,
-	},
-};
-
-static struct gpio_led_platform_data guruplug_led_data = {
-	.leds		= guruplug_led_pins,
-	.num_leds	= ARRAY_SIZE(guruplug_led_pins),
-};
-
-static struct platform_device guruplug_leds = {
-	.name	= "leds-gpio",
-	.id	= -1,
-	.dev	= {
-		.platform_data	= &guruplug_led_data,
-	}
-};
-
-static unsigned int guruplug_mpp_config[] __initdata = {
-	MPP46_GPIO,	/* M_RLED */
-	MPP47_GPIO,	/* M_GLED */
-	MPP48_GPIO,	/* B_RLED */
-	MPP49_GPIO,	/* B_GLED */
-	0
-};
-
-static void __init guruplug_init(void)
-{
-	/*
-	 * Basic setup. Needs to be called early.
-	 */
-	kirkwood_init();
-	kirkwood_mpp_conf(guruplug_mpp_config);
-
-	kirkwood_uart0_init();
-	kirkwood_nand_init(ARRAY_AND_SIZE(guruplug_nand_parts), 25);
-
-	kirkwood_ehci_init();
-	kirkwood_ge00_init(&guruplug_ge00_data);
-	kirkwood_ge01_init(&guruplug_ge01_data);
-	kirkwood_sata_init(&guruplug_sata_data);
-	kirkwood_sdio_init(&guruplug_mvsdio_data);
-
-	platform_device_register(&guruplug_leds);
-}
-
-MACHINE_START(GURUPLUG, "Marvell GuruPlug Reference Board")
-	/* Maintainer: Siddarth Gore <gores@marvell.com> */
-	.atag_offset	= 0x100,
-	.init_machine	= guruplug_init,
-	.map_io		= kirkwood_map_io,
-	.init_early	= kirkwood_init_early,
-	.init_irq	= kirkwood_init_irq,
-	.init_time	= kirkwood_timer_init,
-	.restart	= kirkwood_restart,
-MACHINE_END
diff --git a/arch/arm/mach-kirkwood/include/mach/debug-macro.S b/arch/arm/mach-kirkwood/include/mach/debug-macro.S
deleted file mode 100644
index f785d401a607..000000000000
--- a/arch/arm/mach-kirkwood/include/mach/debug-macro.S
+++ /dev/null
@@ -1,19 +0,0 @@
-/*
- * arch/arm/mach-kirkwood/include/mach/debug-macro.S
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
-
-#include <mach/bridge-regs.h>
-
-	.macro	addruart, rp, rv, tmp
-	ldr	\rp, =KIRKWOOD_REGS_PHYS_BASE
-	ldr	\rv, =KIRKWOOD_REGS_VIRT_BASE
-	orr	\rp, \rp, #0x00012000
-	orr	\rv, \rv, #0x00012000
-	.endm
-
-#define UART_SHIFT	2
-#include <asm/hardware/debug-8250.S>
diff --git a/arch/arm/mach-kirkwood/mv88f6281gtw_ge-setup.c b/arch/arm/mach-kirkwood/mv88f6281gtw_ge-setup.c
deleted file mode 100644
index ba384b992bef..000000000000
--- a/arch/arm/mach-kirkwood/mv88f6281gtw_ge-setup.c
+++ /dev/null
@@ -1,172 +0,0 @@
-/*
- * arch/arm/mach-kirkwood/mv88f6281gtw_ge-setup.c
- *
- * Marvell 88F6281 GTW GE Board Setup
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2.  This program is licensed "as is" without any
- * warranty of any kind, whether express or implied.
- */
-
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/platform_device.h>
-#include <linux/pci.h>
-#include <linux/irq.h>
-#include <linux/mtd/physmap.h>
-#include <linux/timer.h>
-#include <linux/mv643xx_eth.h>
-#include <linux/ethtool.h>
-#include <linux/gpio.h>
-#include <linux/leds.h>
-#include <linux/input.h>
-#include <linux/gpio_keys.h>
-#include <linux/spi/flash.h>
-#include <linux/spi/spi.h>
-#include <net/dsa.h>
-#include <asm/mach-types.h>
-#include <asm/mach/arch.h>
-#include <asm/mach/pci.h>
-#include <mach/kirkwood.h>
-#include "common.h"
-#include "mpp.h"
-
-static struct mv643xx_eth_platform_data mv88f6281gtw_ge_ge00_data = {
-	.phy_addr	= MV643XX_ETH_PHY_NONE,
-	.speed		= SPEED_1000,
-	.duplex		= DUPLEX_FULL,
-};
-
-static struct dsa_chip_data mv88f6281gtw_ge_switch_chip_data = {
-	.port_names[0]	= "lan1",
-	.port_names[1]	= "lan2",
-	.port_names[2]	= "lan3",
-	.port_names[3]	= "lan4",
-	.port_names[4]	= "wan",
-	.port_names[5]	= "cpu",
-};
-
-static struct dsa_platform_data mv88f6281gtw_ge_switch_plat_data = {
-	.nr_chips	= 1,
-	.chip		= &mv88f6281gtw_ge_switch_chip_data,
-};
-
-static const struct flash_platform_data mv88f6281gtw_ge_spi_slave_data = {
-	.type		= "mx25l12805d",
-};
-
-static struct spi_board_info __initdata mv88f6281gtw_ge_spi_slave_info[] = {
-	{
-		.modalias	= "m25p80",
-		.platform_data	= &mv88f6281gtw_ge_spi_slave_data,
-		.irq		= -1,
-		.max_speed_hz	= 50000000,
-		.bus_num	= 0,
-		.chip_select	= 0,
-	},
-};
-
-static struct gpio_keys_button mv88f6281gtw_ge_button_pins[] = {
-	{
-		.code		= KEY_RESTART,
-		.gpio		= 47,
-		.desc		= "SWR Button",
-		.active_low	= 1,
-	}, {
-		.code		= KEY_WPS_BUTTON,
-		.gpio		= 46,
-		.desc		= "WPS Button",
-		.active_low	= 1,
-	},
-};
-
-static struct gpio_keys_platform_data mv88f6281gtw_ge_button_data = {
-	.buttons	= mv88f6281gtw_ge_button_pins,
-	.nbuttons	= ARRAY_SIZE(mv88f6281gtw_ge_button_pins),
-};
-
-static struct platform_device mv88f6281gtw_ge_buttons = {
-	.name		= "gpio-keys",
-	.id		= -1,
-	.num_resources	= 0,
-	.dev		= {
-		.platform_data	= &mv88f6281gtw_ge_button_data,
-	},
-};
-
-static struct gpio_led mv88f6281gtw_ge_led_pins[] = {
-	{
-		.name		= "gtw:green:Status",
-		.gpio		= 20,
-		.active_low	= 0,
-	}, {
-		.name		= "gtw:red:Status",
-		.gpio		= 21,
-		.active_low	= 0,
-	}, {
-		.name		= "gtw:green:USB",
-		.gpio		= 12,
-		.active_low	= 0,
-	},
-};
-
-static struct gpio_led_platform_data mv88f6281gtw_ge_led_data = {
-	.leds		= mv88f6281gtw_ge_led_pins,
-	.num_leds	= ARRAY_SIZE(mv88f6281gtw_ge_led_pins),
-};
-
-static struct platform_device mv88f6281gtw_ge_leds = {
-	.name	= "leds-gpio",
-	.id	= -1,
-	.dev	= {
-		.platform_data	= &mv88f6281gtw_ge_led_data,
-	},
-};
-
-static unsigned int mv88f6281gtw_ge_mpp_config[] __initdata = {
-	MPP12_GPO,	/* Status#_USB pin  */
-	MPP20_GPIO,	/* Status#_GLED pin */
-	MPP21_GPIO,	/* Status#_RLED pin */
-	MPP46_GPIO,	/* WPS_Switch pin   */
-	MPP47_GPIO,	/* SW_Init pin      */
-	0
-};
-
-static void __init mv88f6281gtw_ge_init(void)
-{
-	/*
-	 * Basic setup. Needs to be called early.
-	 */
-	kirkwood_init();
-	kirkwood_mpp_conf(mv88f6281gtw_ge_mpp_config);
-
-	kirkwood_ehci_init();
-	kirkwood_ge00_init(&mv88f6281gtw_ge_ge00_data);
-	kirkwood_ge00_switch_init(&mv88f6281gtw_ge_switch_plat_data, NO_IRQ);
-	spi_register_board_info(mv88f6281gtw_ge_spi_slave_info,
-				ARRAY_SIZE(mv88f6281gtw_ge_spi_slave_info));
-	kirkwood_spi_init();
-	kirkwood_uart0_init();
-	platform_device_register(&mv88f6281gtw_ge_leds);
-	platform_device_register(&mv88f6281gtw_ge_buttons);
-}
-
-static int __init mv88f6281gtw_ge_pci_init(void)
-{
-	if (machine_is_mv88f6281gtw_ge())
-		kirkwood_pcie_init(KW_PCIE0);
-
-	return 0;
-}
-subsys_initcall(mv88f6281gtw_ge_pci_init);
-
-MACHINE_START(MV88F6281GTW_GE, "Marvell 88F6281 GTW GE Board")
-	/* Maintainer: Lennert Buytenhek <buytenh@marvell.com> */
-	.atag_offset	= 0x100,
-	.init_machine	= mv88f6281gtw_ge_init,
-	.map_io		= kirkwood_map_io,
-	.init_early	= kirkwood_init_early,
-	.init_irq	= kirkwood_init_irq,
-	.init_time	= kirkwood_timer_init,
-	.restart	= kirkwood_restart,
-MACHINE_END
diff --git a/arch/arm/mach-kirkwood/netspace_v2-setup.c b/arch/arm/mach-kirkwood/netspace_v2-setup.c
deleted file mode 100644
index 3b706611da8e..000000000000
--- a/arch/arm/mach-kirkwood/netspace_v2-setup.c
+++ /dev/null
@@ -1,293 +0,0 @@
-/*
- * arch/arm/mach-kirkwood/netspace_v2-setup.c
- *
- * LaCie Network Space v2 board setup
- *
- * Copyright (C) 2009 Simon Guinot <sguinot@lacie.com>
- * Copyright (C) 2009 BenoÃ®t Canet <benoit.canet@gmail.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- */
-
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/platform_device.h>
-#include <linux/ata_platform.h>
-#include <linux/mv643xx_eth.h>
-#include <linux/input.h>
-#include <linux/gpio.h>
-#include <linux/gpio_keys.h>
-#include <linux/leds.h>
-#include <linux/gpio-fan.h>
-#include <asm/mach-types.h>
-#include <asm/mach/arch.h>
-#include <mach/kirkwood.h>
-#include <linux/platform_data/leds-kirkwood-ns2.h>
-#include "common.h"
-#include "mpp.h"
-#include "lacie_v2-common.h"
-
-/*****************************************************************************
- * Ethernet
- ****************************************************************************/
-
-static struct mv643xx_eth_platform_data netspace_v2_ge00_data = {
-	.phy_addr	= MV643XX_ETH_PHY_ADDR(8),
-};
-
-/*****************************************************************************
- * SATA
- ****************************************************************************/
-
-static struct mv_sata_platform_data netspace_v2_sata_data = {
-	.n_ports	= 2,
-};
-
-/*****************************************************************************
- * GPIO keys
- ****************************************************************************/
-
-#define NETSPACE_V2_PUSH_BUTTON		32
-
-static struct gpio_keys_button netspace_v2_buttons[] = {
-	[0] = {
-		.code		= KEY_POWER,
-		.gpio		= NETSPACE_V2_PUSH_BUTTON,
-		.desc		= "Power push button",
-		.active_low	= 0,
-	},
-};
-
-static struct gpio_keys_platform_data netspace_v2_button_data = {
-	.buttons	= netspace_v2_buttons,
-	.nbuttons	= ARRAY_SIZE(netspace_v2_buttons),
-};
-
-static struct platform_device netspace_v2_gpio_buttons = {
-	.name		= "gpio-keys",
-	.id		= -1,
-	.dev		= {
-		.platform_data	= &netspace_v2_button_data,
-	},
-};
-
-/*****************************************************************************
- * GPIO LEDs
- ****************************************************************************/
-
-#define NETSPACE_V2_GPIO_RED_LED	12
-
-static struct gpio_led netspace_v2_gpio_led_pins[] = {
-	{
-		.name	= "ns_v2:red:fail",
-		.gpio	= NETSPACE_V2_GPIO_RED_LED,
-	},
-};
-
-static struct gpio_led_platform_data netspace_v2_gpio_leds_data = {
-	.num_leds	= ARRAY_SIZE(netspace_v2_gpio_led_pins),
-	.leds		= netspace_v2_gpio_led_pins,
-};
-
-static struct platform_device netspace_v2_gpio_leds = {
-	.name		= "leds-gpio",
-	.id		= -1,
-	.dev		= {
-		.platform_data	= &netspace_v2_gpio_leds_data,
-	},
-};
-
-/*****************************************************************************
- * Dual-GPIO CPLD LEDs
- ****************************************************************************/
-
-#define NETSPACE_V2_GPIO_BLUE_LED_SLOW	29
-#define NETSPACE_V2_GPIO_BLUE_LED_CMD	30
-
-static struct ns2_led netspace_v2_led_pins[] = {
-	{
-		.name	= "ns_v2:blue:sata",
-		.cmd	= NETSPACE_V2_GPIO_BLUE_LED_CMD,
-		.slow	= NETSPACE_V2_GPIO_BLUE_LED_SLOW,
-	},
-};
-
-static struct ns2_led_platform_data netspace_v2_leds_data = {
-	.num_leds	= ARRAY_SIZE(netspace_v2_led_pins),
-	.leds		= netspace_v2_led_pins,
-};
-
-static struct platform_device netspace_v2_leds = {
-	.name		= "leds-ns2",
-	.id		= -1,
-	.dev		= {
-		.platform_data	= &netspace_v2_leds_data,
-	},
-};
-
-/*****************************************************************************
- * GPIO fan
- ****************************************************************************/
-
-/* Designed for fan 40x40x16: ADDA AD0412LB-D50 6000rpm@12v */
-static struct gpio_fan_speed netspace_max_v2_fan_speed[] = {
-	{    0,  0 },
-	{ 1500,	15 },
-	{ 1700,	14 },
-	{ 1800,	13 },
-	{ 2100,	12 },
-	{ 3100,	11 },
-	{ 3300,	10 },
-	{ 4300,	 9 },
-	{ 5500,	 8 },
-};
-
-static unsigned netspace_max_v2_fan_ctrl[] = { 22, 7, 33, 23 };
-
-static struct gpio_fan_alarm netspace_max_v2_fan_alarm = {
-	.gpio		= 25,
-	.active_low	= 1,
-};
-
-static struct gpio_fan_platform_data netspace_max_v2_fan_data = {
-	.num_ctrl	= ARRAY_SIZE(netspace_max_v2_fan_ctrl),
-	.ctrl		= netspace_max_v2_fan_ctrl,
-	.alarm		= &netspace_max_v2_fan_alarm,
-	.num_speed	= ARRAY_SIZE(netspace_max_v2_fan_speed),
-	.speed		= netspace_max_v2_fan_speed,
-};
-
-static struct platform_device netspace_max_v2_gpio_fan = {
-	.name	= "gpio-fan",
-	.id	= -1,
-	.dev	= {
-		.platform_data	= &netspace_max_v2_fan_data,
-	},
-};
-
-/*****************************************************************************
- * General Setup
- ****************************************************************************/
-
-static unsigned int netspace_v2_mpp_config[] __initdata = {
-	MPP0_SPI_SCn,
-	MPP1_SPI_MOSI,
-	MPP2_SPI_SCK,
-	MPP3_SPI_MISO,
-	MPP4_NF_IO6,
-	MPP5_NF_IO7,
-	MPP6_SYSRST_OUTn,
-	MPP7_GPO,		/* Fan speed (bit 1) */
-	MPP8_TW0_SDA,
-	MPP9_TW0_SCK,
-	MPP10_UART0_TXD,
-	MPP11_UART0_RXD,
-	MPP12_GPO,		/* Red led */
-	MPP14_GPIO,		/* USB fuse */
-	MPP16_GPIO,		/* SATA 0 power */
-	MPP17_GPIO,		/* SATA 1 power */
-	MPP18_NF_IO0,
-	MPP19_NF_IO1,
-	MPP20_SATA1_ACTn,
-	MPP21_SATA0_ACTn,
-	MPP22_GPIO,		/* Fan speed (bit 0) */
-	MPP23_GPIO,		/* Fan power */
-	MPP24_GPIO,		/* USB mode select */
-	MPP25_GPIO,		/* Fan rotation fail */
-	MPP26_GPIO,		/* USB device vbus */
-	MPP28_GPIO,		/* USB enable host vbus */
-	MPP29_GPIO,		/* Blue led (slow register) */
-	MPP30_GPIO,		/* Blue led (command register) */
-	MPP31_GPIO,		/* Board power off */
-	MPP32_GPIO,		/* Power button (0 = Released, 1 = Pushed) */
-	MPP33_GPO,		/* Fan speed (bit 2) */
-	0
-};
-
-#define NETSPACE_V2_GPIO_POWER_OFF	31
-
-static void netspace_v2_power_off(void)
-{
-	gpio_set_value(NETSPACE_V2_GPIO_POWER_OFF, 1);
-}
-
-static void __init netspace_v2_init(void)
-{
-	/*
-	 * Basic setup. Needs to be called early.
-	 */
-	kirkwood_init();
-	kirkwood_mpp_conf(netspace_v2_mpp_config);
-
-	if (machine_is_netspace_max_v2())
-		lacie_v2_hdd_power_init(2);
-	else
-		lacie_v2_hdd_power_init(1);
-
-	kirkwood_ehci_init();
-	kirkwood_ge00_init(&netspace_v2_ge00_data);
-	kirkwood_sata_init(&netspace_v2_sata_data);
-	kirkwood_uart0_init();
-	lacie_v2_register_flash();
-	lacie_v2_register_i2c_devices();
-
-	platform_device_register(&netspace_v2_leds);
-	platform_device_register(&netspace_v2_gpio_leds);
-	platform_device_register(&netspace_v2_gpio_buttons);
-	if (machine_is_netspace_max_v2())
-		platform_device_register(&netspace_max_v2_gpio_fan);
-
-	if (gpio_request(NETSPACE_V2_GPIO_POWER_OFF, "power-off") == 0 &&
-	    gpio_direction_output(NETSPACE_V2_GPIO_POWER_OFF, 0) == 0)
-		pm_power_off = netspace_v2_power_off;
-	else
-		pr_err("netspace_v2: failed to configure power-off GPIO\n");
-}
-
-#ifdef CONFIG_MACH_NETSPACE_V2
-MACHINE_START(NETSPACE_V2, "LaCie Network Space v2")
-	.atag_offset	= 0x100,
-	.init_machine	= netspace_v2_init,
-	.map_io		= kirkwood_map_io,
-	.init_early	= kirkwood_init_early,
-	.init_irq	= kirkwood_init_irq,
-	.init_time	= kirkwood_timer_init,
-	.restart	= kirkwood_restart,
-MACHINE_END
-#endif
-
-#ifdef CONFIG_MACH_INETSPACE_V2
-MACHINE_START(INETSPACE_V2, "LaCie Internet Space v2")
-	.atag_offset	= 0x100,
-	.init_machine	= netspace_v2_init,
-	.map_io		= kirkwood_map_io,
-	.init_early	= kirkwood_init_early,
-	.init_irq	= kirkwood_init_irq,
-	.init_time	= kirkwood_timer_init,
-	.restart	= kirkwood_restart,
-MACHINE_END
-#endif
-
-#ifdef CONFIG_MACH_NETSPACE_MAX_V2
-MACHINE_START(NETSPACE_MAX_V2, "LaCie Network Space Max v2")
-	.atag_offset	= 0x100,
-	.init_machine	= netspace_v2_init,
-	.map_io		= kirkwood_map_io,
-	.init_early	= kirkwood_init_early,
-	.init_irq	= kirkwood_init_irq,
-	.init_time	= kirkwood_timer_init,
-	.restart	= kirkwood_restart,
-MACHINE_END
-#endif
diff --git a/arch/arm/mach-kirkwood/openrd-setup.c b/arch/arm/mach-kirkwood/openrd-setup.c
index 6a6eb548307d..e5cf84103583 100644
--- a/arch/arm/mach-kirkwood/openrd-setup.c
+++ b/arch/arm/mach-kirkwood/openrd-setup.c
@@ -158,7 +158,8 @@ static void __init openrd_init(void)
 	kirkwood_mpp_conf(openrd_mpp_config);
 
 	kirkwood_uart0_init();
-	kirkwood_nand_init(ARRAY_AND_SIZE(openrd_nand_parts), 25);
+	kirkwood_nand_init(openrd_nand_parts, ARRAY_SIZE(openrd_nand_parts),
+			   25);
 
 	kirkwood_ehci_init();
 
diff --git a/arch/arm/mach-kirkwood/pcie.c b/arch/arm/mach-kirkwood/pcie.c
index ddcb09f5bdd3..12d86f39f380 100644
--- a/arch/arm/mach-kirkwood/pcie.c
+++ b/arch/arm/mach-kirkwood/pcie.c
@@ -20,6 +20,16 @@
 #include <mach/bridge-regs.h>
 #include "common.h"
 
+/* These can go away once Kirkwood uses the mvebu-mbus DT binding */
+#define KIRKWOOD_MBUS_PCIE0_MEM_TARGET    0x4
+#define KIRKWOOD_MBUS_PCIE0_MEM_ATTR      0xe8
+#define KIRKWOOD_MBUS_PCIE0_IO_TARGET     0x4
+#define KIRKWOOD_MBUS_PCIE0_IO_ATTR       0xe0
+#define KIRKWOOD_MBUS_PCIE1_MEM_TARGET    0x4
+#define KIRKWOOD_MBUS_PCIE1_MEM_ATTR      0xd8
+#define KIRKWOOD_MBUS_PCIE1_IO_TARGET     0x4
+#define KIRKWOOD_MBUS_PCIE1_IO_ATTR       0xd0
+
 static void kirkwood_enable_pcie_clk(const char *port)
 {
 	struct clk *clk;
@@ -254,26 +264,24 @@ static void __init add_pcie_port(int index, void __iomem *base)
 
 void __init kirkwood_pcie_init(unsigned int portmask)
 {
-	mvebu_mbus_add_window_remap_flags("pcie0.0",
+	mvebu_mbus_add_window_remap_by_id(KIRKWOOD_MBUS_PCIE0_IO_TARGET,
+					  KIRKWOOD_MBUS_PCIE0_IO_ATTR,
 					  KIRKWOOD_PCIE_IO_PHYS_BASE,
 					  KIRKWOOD_PCIE_IO_SIZE,
-					  KIRKWOOD_PCIE_IO_BUS_BASE,
-					  MVEBU_MBUS_PCI_IO);
-	mvebu_mbus_add_window_remap_flags("pcie0.0",
-					  KIRKWOOD_PCIE_MEM_PHYS_BASE,
-					  KIRKWOOD_PCIE_MEM_SIZE,
-					  MVEBU_MBUS_NO_REMAP,
-					  MVEBU_MBUS_PCI_MEM);
-	mvebu_mbus_add_window_remap_flags("pcie1.0",
+					  KIRKWOOD_PCIE_IO_BUS_BASE);
+	mvebu_mbus_add_window_by_id(KIRKWOOD_MBUS_PCIE0_MEM_TARGET,
+				    KIRKWOOD_MBUS_PCIE0_MEM_ATTR,
+				    KIRKWOOD_PCIE_MEM_PHYS_BASE,
+				    KIRKWOOD_PCIE_MEM_SIZE);
+	mvebu_mbus_add_window_remap_by_id(KIRKWOOD_MBUS_PCIE1_IO_TARGET,
+					  KIRKWOOD_MBUS_PCIE1_IO_ATTR,
 					  KIRKWOOD_PCIE1_IO_PHYS_BASE,
 					  KIRKWOOD_PCIE1_IO_SIZE,
-					  KIRKWOOD_PCIE1_IO_BUS_BASE,
-					  MVEBU_MBUS_PCI_IO);
-	mvebu_mbus_add_window_remap_flags("pcie1.0",
-					  KIRKWOOD_PCIE1_MEM_PHYS_BASE,
-					  KIRKWOOD_PCIE1_MEM_SIZE,
-					  MVEBU_MBUS_NO_REMAP,
-					  MVEBU_MBUS_PCI_MEM);
+					  KIRKWOOD_PCIE1_IO_BUS_BASE);
+	mvebu_mbus_add_window_by_id(KIRKWOOD_MBUS_PCIE1_MEM_TARGET,
+				    KIRKWOOD_MBUS_PCIE1_MEM_ATTR,
+				    KIRKWOOD_PCIE1_MEM_PHYS_BASE,
+				    KIRKWOOD_PCIE1_MEM_SIZE);
 
 	vga_base = KIRKWOOD_PCIE_MEM_PHYS_BASE;
 
diff --git a/arch/arm/mach-kirkwood/rd88f6281-setup.c b/arch/arm/mach-kirkwood/rd88f6281-setup.c
index d24223166e06..5154bd2a3ad3 100644
--- a/arch/arm/mach-kirkwood/rd88f6281-setup.c
+++ b/arch/arm/mach-kirkwood/rd88f6281-setup.c
@@ -87,7 +87,9 @@ static void __init rd88f6281_init(void)
 	kirkwood_init();
 	kirkwood_mpp_conf(rd88f6281_mpp_config);
 
-	kirkwood_nand_init(ARRAY_AND_SIZE(rd88f6281_nand_parts), 25);
+	kirkwood_nand_init(rd88f6281_nand_parts,
+			   ARRAY_SIZE(rd88f6281_nand_parts),
+			   25);
 	kirkwood_ehci_init();
 
 	kirkwood_ge00_init(&rd88f6281_ge00_data);
diff --git a/arch/arm/mach-kirkwood/sheevaplug-setup.c b/arch/arm/mach-kirkwood/sheevaplug-setup.c
deleted file mode 100644
index 55b68fa39f45..000000000000
--- a/arch/arm/mach-kirkwood/sheevaplug-setup.c
+++ /dev/null
@@ -1,161 +0,0 @@
-/*
- * arch/arm/mach-kirkwood/sheevaplug-setup.c
- *
- * Marvell SheevaPlug Reference Board Setup
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2.  This program is licensed "as is" without any
- * warranty of any kind, whether express or implied.
- */
-
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/platform_device.h>
-#include <linux/ata_platform.h>
-#include <linux/mtd/partitions.h>
-#include <linux/mv643xx_eth.h>
-#include <linux/gpio.h>
-#include <linux/leds.h>
-#include <asm/mach-types.h>
-#include <asm/mach/arch.h>
-#include <mach/kirkwood.h>
-#include <linux/platform_data/mmc-mvsdio.h>
-#include "common.h"
-#include "mpp.h"
-
-static struct mtd_partition sheevaplug_nand_parts[] = {
-	{
-		.name = "u-boot",
-		.offset = 0,
-		.size = SZ_1M
-	}, {
-		.name = "uImage",
-		.offset = MTDPART_OFS_NXTBLK,
-		.size = SZ_4M
-	}, {
-		.name = "root",
-		.offset = MTDPART_OFS_NXTBLK,
-		.size = MTDPART_SIZ_FULL
-	},
-};
-
-static struct mv643xx_eth_platform_data sheevaplug_ge00_data = {
-	.phy_addr	= MV643XX_ETH_PHY_ADDR(0),
-};
-
-static struct mv_sata_platform_data sheeva_esata_sata_data = {
-	.n_ports	= 2,
-};
-
-static struct mvsdio_platform_data sheevaplug_mvsdio_data = {
-	/* unfortunately the CD signal has not been connected */
-};
-
-static struct mvsdio_platform_data sheeva_esata_mvsdio_data = {
-	.gpio_write_protect = 44, /* MPP44 used as SD write protect */
-	.gpio_card_detect = 47,	  /* MPP47 used as SD card detect */
-};
-
-static struct gpio_led sheevaplug_led_pins[] = {
-	{
-		.name			= "plug:red:misc",
-		.default_trigger	= "none",
-		.gpio			= 46,
-		.active_low		= 1,
-	},
-	{
-		.name			= "plug:green:health",
-		.default_trigger	= "default-on",
-		.gpio			= 49,
-		.active_low		= 1,
-	},
-};
-
-static struct gpio_led_platform_data sheevaplug_led_data = {
-	.leds		= sheevaplug_led_pins,
-	.num_leds	= ARRAY_SIZE(sheevaplug_led_pins),
-};
-
-static struct platform_device sheevaplug_leds = {
-	.name	= "leds-gpio",
-	.id	= -1,
-	.dev	= {
-		.platform_data	= &sheevaplug_led_data,
-	}
-};
-
-static unsigned int sheevaplug_mpp_config[] __initdata = {
-	MPP29_GPIO,	/* USB Power Enable */
-	MPP46_GPIO,	/* LED Red */
-	MPP49_GPIO,	/* LED */
-	0
-};
-
-static unsigned int sheeva_esata_mpp_config[] __initdata = {
-	MPP29_GPIO,	/* USB Power Enable */
-	MPP44_GPIO,	/* SD Write Protect */
-	MPP47_GPIO,	/* SD Card Detect */
-	MPP49_GPIO,	/* LED Green */
-	0
-};
-
-static void __init sheevaplug_init(void)
-{
-	/*
-	 * Basic setup. Needs to be called early.
-	 */
-	kirkwood_init();
-
-	/* setup gpio pin select */
-	if (machine_is_esata_sheevaplug())
-		kirkwood_mpp_conf(sheeva_esata_mpp_config);
-	else
-		kirkwood_mpp_conf(sheevaplug_mpp_config);
-
-	kirkwood_uart0_init();
-	kirkwood_nand_init(ARRAY_AND_SIZE(sheevaplug_nand_parts), 25);
-
-	if (gpio_request(29, "USB Power Enable") != 0 ||
-	    gpio_direction_output(29, 1) != 0)
-		pr_err("can't set up GPIO 29 (USB Power Enable)\n");
-	kirkwood_ehci_init();
-
-	kirkwood_ge00_init(&sheevaplug_ge00_data);
-
-	/* honor lower power consumption for plugs with out eSATA */
-	if (machine_is_esata_sheevaplug())
-		kirkwood_sata_init(&sheeva_esata_sata_data);
-
-	/* enable sd wp and sd cd on plugs with esata */
-	if (machine_is_esata_sheevaplug())
-		kirkwood_sdio_init(&sheeva_esata_mvsdio_data);
-	else
-		kirkwood_sdio_init(&sheevaplug_mvsdio_data);
-
-	platform_device_register(&sheevaplug_leds);
-}
-
-#ifdef CONFIG_MACH_SHEEVAPLUG
-MACHINE_START(SHEEVAPLUG, "Marvell SheevaPlug Reference Board")
-	/* Maintainer: shadi Ammouri <shadi@marvell.com> */
-	.atag_offset	= 0x100,
-	.init_machine	= sheevaplug_init,
-	.map_io		= kirkwood_map_io,
-	.init_early	= kirkwood_init_early,
-	.init_irq	= kirkwood_init_irq,
-	.init_time	= kirkwood_timer_init,
-	.restart	= kirkwood_restart,
-MACHINE_END
-#endif
-
-#ifdef CONFIG_MACH_ESATA_SHEEVAPLUG
-MACHINE_START(ESATA_SHEEVAPLUG, "Marvell eSATA SheevaPlug Reference Board")
-	.atag_offset	= 0x100,
-	.init_machine	= sheevaplug_init,
-	.map_io		= kirkwood_map_io,
-	.init_early	= kirkwood_init_early,
-	.init_irq	= kirkwood_init_irq,
-	.init_time	= kirkwood_timer_init,
-	.restart	= kirkwood_restart,
-MACHINE_END
-#endif
diff --git a/arch/arm/mach-ks8695/board-acs5k.c b/arch/arm/mach-ks8695/board-acs5k.c
index 456d6386edf8..9f9c0441a917 100644
--- a/arch/arm/mach-ks8695/board-acs5k.c
+++ b/arch/arm/mach-ks8695/board-acs5k.c
@@ -20,7 +20,7 @@
 #include <linux/i2c.h>
 #include <linux/i2c-algo-bit.h>
 #include <linux/i2c-gpio.h>
-#include <linux/i2c/pca953x.h>
+#include <linux/platform_data/pca953x.h>
 
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/map.h>
diff --git a/arch/arm/mach-lpc32xx/include/mach/debug-macro.S b/arch/arm/mach-lpc32xx/include/mach/debug-macro.S
deleted file mode 100644
index 351bd6c84909..000000000000
--- a/arch/arm/mach-lpc32xx/include/mach/debug-macro.S
+++ /dev/null
@@ -1,29 +0,0 @@
-/*
- * arch/arm/mach-lpc32xx/include/mach/debug-macro.S
- *
- * Author: Kevin Wells <kevin.wells@nxp.com>
- *
- * Copyright (C) 2010 NXP Semiconductors
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
-
-/*
- * Debug output is hardcoded to standard UART 5
-*/
-
-	.macro	addruart, rp, rv, tmp
-	ldreq	\rp, =0x40090000
-	ldrne	\rv, =0xF4090000
-	.endm
-
-#define UART_SHIFT	2
-#include <asm/hardware/debug-8250.S>
diff --git a/arch/arm/mach-mmp/Makefile b/arch/arm/mach-mmp/Makefile
index 095c155d6fb8..9b702a1dc7b0 100644
--- a/arch/arm/mach-mmp/Makefile
+++ b/arch/arm/mach-mmp/Makefile
@@ -2,7 +2,7 @@
 # Makefile for Marvell's PXA168 processors line
 #
 
-obj-y				+= common.o devices.o time.o irq.o
+obj-y				+= common.o devices.o time.o
 
 # SoC support
 obj-$(CONFIG_CPU_PXA168)	+= pxa168.o
diff --git a/arch/arm/mach-mmp/common.h b/arch/arm/mach-mmp/common.h
index 991d7e9877de..cf445bae6d77 100644
--- a/arch/arm/mach-mmp/common.h
+++ b/arch/arm/mach-mmp/common.h
@@ -3,7 +3,6 @@
 
 extern void timer_init(int irq);
 
-extern void __init icu_init_irq(void);
 extern void __init mmp_map_io(void);
 extern void mmp_restart(enum reboot_mode, const char *);
 extern void __init pxa168_clk_init(void);
diff --git a/arch/arm/mach-mmp/include/mach/entry-macro.S b/arch/arm/mach-mmp/include/mach/entry-macro.S
deleted file mode 100644
index bd152e24e6d7..000000000000
--- a/arch/arm/mach-mmp/include/mach/entry-macro.S
+++ /dev/null
@@ -1,26 +0,0 @@
-/*
- * linux/arch/arm/mach-mmp/include/mach/entry-macro.S
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <asm/irq.h>
-#include <mach/regs-icu.h>
-
-	.macro	get_irqnr_preamble, base, tmp
-	mrc	p15, 0, \tmp, c0, c0, 0		@ CPUID
-	and	\tmp, \tmp, #0xff00
-	cmp	\tmp, #0x5800
-	ldr	\base, =mmp_icu_base
-	ldr	\base, [\base, #0]
-	addne	\base, \base, #0x10c		@ PJ1 AP INT SEL register
-	addeq	\base, \base, #0x104		@ PJ4 IRQ SEL register
-	.endm
-
-	.macro	get_irqnr_and_base, irqnr, irqstat, base, tmp
-	ldr	\tmp, [\base, #0]
-	and	\irqnr, \tmp, #0x3f
-	tst	\tmp, #(1 << 6)
-	.endm
diff --git a/arch/arm/mach-mmp/include/mach/pxa168.h b/arch/arm/mach-mmp/include/mach/pxa168.h
index 459c2d03eb5c..a83ba7cb525d 100644
--- a/arch/arm/mach-mmp/include/mach/pxa168.h
+++ b/arch/arm/mach-mmp/include/mach/pxa168.h
@@ -4,6 +4,7 @@
 #include <linux/reboot.h>
 
 extern void pxa168_timer_init(void);
+extern void __init icu_init_irq(void);
 extern void __init pxa168_init_irq(void);
 extern void pxa168_restart(enum reboot_mode, const char *);
 extern void pxa168_clear_keypad_wakeup(void);
diff --git a/arch/arm/mach-mmp/include/mach/pxa910.h b/arch/arm/mach-mmp/include/mach/pxa910.h
index b914afa1fcdc..92253203f5b4 100644
--- a/arch/arm/mach-mmp/include/mach/pxa910.h
+++ b/arch/arm/mach-mmp/include/mach/pxa910.h
@@ -2,6 +2,7 @@
 #define __ASM_MACH_PXA910_H
 
 extern void pxa910_timer_init(void);
+extern void __init icu_init_irq(void);
 extern void __init pxa910_init_irq(void);
 
 #include <linux/i2c.h>
diff --git a/arch/arm/mach-mmp/mmp-dt.c b/arch/arm/mach-mmp/mmp-dt.c
index b37915dc4470..cca529ceecb7 100644
--- a/arch/arm/mach-mmp/mmp-dt.c
+++ b/arch/arm/mach-mmp/mmp-dt.c
@@ -9,17 +9,13 @@
  *  publishhed by the Free Software Foundation.
  */
 
-#include <linux/irq.h>
-#include <linux/irqdomain.h>
-#include <linux/of_irq.h>
+#include <linux/irqchip.h>
 #include <linux/of_platform.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/time.h>
-#include <mach/irqs.h>
 
 #include "common.h"
 
-extern void __init mmp_dt_irq_init(void);
 extern void __init mmp_dt_init_timer(void);
 
 static const struct of_dev_auxdata pxa168_auxdata_lookup[] __initconst = {
@@ -64,7 +60,6 @@ static const char *mmp_dt_board_compat[] __initdata = {
 
 DT_MACHINE_START(PXA168_DT, "Marvell PXA168 (Device Tree Support)")
 	.map_io		= mmp_map_io,
-	.init_irq	= mmp_dt_irq_init,
 	.init_time	= mmp_dt_init_timer,
 	.init_machine	= pxa168_dt_init,
 	.dt_compat	= mmp_dt_board_compat,
@@ -72,7 +67,6 @@ MACHINE_END
 
 DT_MACHINE_START(PXA910_DT, "Marvell PXA910 (Device Tree Support)")
 	.map_io		= mmp_map_io,
-	.init_irq	= mmp_dt_irq_init,
 	.init_time	= mmp_dt_init_timer,
 	.init_machine	= pxa910_dt_init,
 	.dt_compat	= mmp_dt_board_compat,
diff --git a/arch/arm/mach-mmp/mmp2-dt.c b/arch/arm/mach-mmp/mmp2-dt.c
index 4ac256720f7d..023cb453f157 100644
--- a/arch/arm/mach-mmp/mmp2-dt.c
+++ b/arch/arm/mach-mmp/mmp2-dt.c
@@ -10,18 +10,13 @@
  */
 
 #include <linux/io.h>
-#include <linux/irq.h>
-#include <linux/irqdomain.h>
-#include <linux/of_irq.h>
+#include <linux/irqchip.h>
 #include <linux/of_platform.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/time.h>
-#include <mach/irqs.h>
-#include <mach/regs-apbc.h>
 
 #include "common.h"
 
-extern void __init mmp_dt_irq_init(void);
 extern void __init mmp_dt_init_timer(void);
 
 static const struct of_dev_auxdata mmp2_auxdata_lookup[] __initconst = {
@@ -49,7 +44,6 @@ static const char *mmp2_dt_board_compat[] __initdata = {
 
 DT_MACHINE_START(MMP2_DT, "Marvell MMP2 (Device Tree Support)")
 	.map_io		= mmp_map_io,
-	.init_irq	= mmp_dt_irq_init,
 	.init_time	= mmp_dt_init_timer,
 	.init_machine	= mmp2_dt_init,
 	.dt_compat	= mmp2_dt_board_compat,
diff --git a/arch/arm/mach-mmp/mmp2.c b/arch/arm/mach-mmp/mmp2.c
index c7592f168bbd..a70b5530bd42 100644
--- a/arch/arm/mach-mmp/mmp2.c
+++ b/arch/arm/mach-mmp/mmp2.c
@@ -13,6 +13,8 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/io.h>
+#include <linux/irq.h>
+#include <linux/irqchip/mmp.h>
 #include <linux/platform_device.h>
 
 #include <asm/hardware/cache-tauros2.h>
@@ -26,6 +28,7 @@
 #include <mach/mfp.h>
 #include <mach/devices.h>
 #include <mach/mmp2.h>
+#include <mach/pm-mmp2.h>
 
 #include "common.h"
 
@@ -94,6 +97,9 @@ void mmp2_clear_pmic_int(void)
 void __init mmp2_init_irq(void)
 {
 	mmp2_init_icu();
+#ifdef CONFIG_PM
+	icu_irq_chip.irq_set_wake = mmp2_set_wake;
+#endif
 }
 
 static int __init mmp2_init(void)
diff --git a/arch/arm/mach-mmp/pxa910.c b/arch/arm/mach-mmp/pxa910.c
index ce6393acad86..eb57ee196842 100644
--- a/arch/arm/mach-mmp/pxa910.c
+++ b/arch/arm/mach-mmp/pxa910.c
@@ -12,6 +12,8 @@
 #include <linux/init.h>
 #include <linux/list.h>
 #include <linux/io.h>
+#include <linux/irq.h>
+#include <linux/irqchip/mmp.h>
 #include <linux/platform_device.h>
 
 #include <asm/hardware/cache-tauros2.h>
@@ -23,6 +25,8 @@
 #include <mach/dma.h>
 #include <mach/mfp.h>
 #include <mach/devices.h>
+#include <mach/pm-pxa910.h>
+#include <mach/pxa910.h>
 
 #include "common.h"
 
@@ -79,6 +83,9 @@ static struct mfp_addr_map pxa910_mfp_addr_map[] __initdata =
 void __init pxa910_init_irq(void)
 {
 	icu_init_irq();
+#ifdef CONFIG_PM
+	icu_irq_chip.irq_set_wake = pxa910_set_wake;
+#endif
 }
 
 static int __init pxa910_init(void)
diff --git a/arch/arm/mach-mmp/ttc_dkb.c b/arch/arm/mach-mmp/ttc_dkb.c
index 8483906d4308..702232996c8c 100644
--- a/arch/arm/mach-mmp/ttc_dkb.c
+++ b/arch/arm/mach-mmp/ttc_dkb.c
@@ -15,7 +15,7 @@
 #include <linux/mtd/partitions.h>
 #include <linux/mtd/onenand.h>
 #include <linux/interrupt.h>
-#include <linux/i2c/pca953x.h>
+#include <linux/platform_data/pca953x.h>
 #include <linux/gpio.h>
 #include <linux/gpio-pxa.h>
 #include <linux/mfd/88pm860x.h>
diff --git a/arch/arm/mach-msm/Makefile b/arch/arm/mach-msm/Makefile
index d257ff40e16b..d872634c2f85 100644
--- a/arch/arm/mach-msm/Makefile
+++ b/arch/arm/mach-msm/Makefile
@@ -1,17 +1,16 @@
-obj-y += io.o timer.o
+obj-y += timer.o
 obj-y += clock.o
 
 obj-$(CONFIG_MSM_VIC) += irq-vic.o
-obj-$(CONFIG_MSM_IOMMU) += devices-iommu.o
 
 obj-$(CONFIG_ARCH_MSM7X00A) += irq.o
 obj-$(CONFIG_ARCH_QSD8X50) += sirc.o
 
 obj-$(CONFIG_MSM_PROC_COMM) += proc_comm.o clock-pcom.o vreg.o
 
-obj-$(CONFIG_ARCH_MSM7X00A) += dma.o
-obj-$(CONFIG_ARCH_MSM7X30) += dma.o
-obj-$(CONFIG_ARCH_QSD8X50) += dma.o
+obj-$(CONFIG_ARCH_MSM7X00A) += dma.o io.o
+obj-$(CONFIG_ARCH_MSM7X30) += dma.o io.o
+obj-$(CONFIG_ARCH_QSD8X50) += dma.o io.o
 
 obj-$(CONFIG_MSM_SMD) += smd.o smd_debug.o
 obj-$(CONFIG_MSM_SMD) += last_radio_log.o
diff --git a/arch/arm/mach-msm/board-dt-8660.c b/arch/arm/mach-msm/board-dt-8660.c
index 492f5cd87b0a..c2946892f5e3 100644
--- a/arch/arm/mach-msm/board-dt-8660.c
+++ b/arch/arm/mach-msm/board-dt-8660.c
@@ -15,8 +15,8 @@
 #include <linux/of_platform.h>
 
 #include <asm/mach/arch.h>
+#include <asm/mach/map.h>
 
-#include <mach/board.h>
 #include "common.h"
 
 static void __init msm8x60_init_late(void)
@@ -42,9 +42,7 @@ static const char *msm8x60_fluid_match[] __initdata = {
 
 DT_MACHINE_START(MSM_DT, "Qualcomm MSM (Flattened Device Tree)")
 	.smp = smp_ops(msm_smp_ops),
-	.map_io = msm_map_msm8x60_io,
 	.init_machine = msm8x60_dt_init,
 	.init_late = msm8x60_init_late,
-	.init_time	= msm_dt_timer_init,
 	.dt_compat = msm8x60_fluid_match,
 MACHINE_END
diff --git a/arch/arm/mach-msm/board-dt-8960.c b/arch/arm/mach-msm/board-dt-8960.c
index bb5530957c4f..d4ca52c45111 100644
--- a/arch/arm/mach-msm/board-dt-8960.c
+++ b/arch/arm/mach-msm/board-dt-8960.c
@@ -14,6 +14,7 @@
 #include <linux/of_platform.h>
 
 #include <asm/mach/arch.h>
+#include <asm/mach/map.h>
 
 #include "common.h"
 
@@ -29,8 +30,6 @@ static const char * const msm8960_dt_match[] __initconst = {
 
 DT_MACHINE_START(MSM8960_DT, "Qualcomm MSM (Flattened Device Tree)")
 	.smp = smp_ops(msm_smp_ops),
-	.map_io = msm_map_msm8960_io,
-	.init_time	= msm_dt_timer_init,
 	.init_machine = msm_dt_init,
 	.dt_compat = msm8960_dt_match,
 MACHINE_END
diff --git a/arch/arm/mach-msm/board-halibut.c b/arch/arm/mach-msm/board-halibut.c
index 803651ad4f62..a77529887cbc 100644
--- a/arch/arm/mach-msm/board-halibut.c
+++ b/arch/arm/mach-msm/board-halibut.c
@@ -29,7 +29,6 @@
 #include <asm/setup.h>
 
 #include <mach/irqs.h>
-#include <mach/board.h>
 #include <mach/msm_iomap.h>
 
 #include <linux/mtd/nand.h>
diff --git a/arch/arm/mach-msm/board-mahimahi.c b/arch/arm/mach-msm/board-mahimahi.c
index 30c3496db593..7d9981cb400e 100644
--- a/arch/arm/mach-msm/board-mahimahi.c
+++ b/arch/arm/mach-msm/board-mahimahi.c
@@ -28,12 +28,12 @@
 #include <asm/mach/map.h>
 #include <asm/setup.h>
 
-#include <mach/board.h>
 #include <mach/hardware.h>
 
 #include "board-mahimahi.h"
 #include "devices.h"
 #include "proc_comm.h"
+#include "common.h"
 
 static uint debug_uart;
 
diff --git a/arch/arm/mach-msm/board-msm7x30.c b/arch/arm/mach-msm/board-msm7x30.c
index db3d8c0bc8a4..f9af5a46e8b6 100644
--- a/arch/arm/mach-msm/board-msm7x30.c
+++ b/arch/arm/mach-msm/board-msm7x30.c
@@ -30,7 +30,6 @@
 #include <asm/memory.h>
 #include <asm/setup.h>
 
-#include <mach/board.h>
 #include <mach/msm_iomap.h>
 #include <mach/dma.h>
 
diff --git a/arch/arm/mach-msm/board-qsd8x50.c b/arch/arm/mach-msm/board-qsd8x50.c
index f14a73d86bc0..5f933bc50783 100644
--- a/arch/arm/mach-msm/board-qsd8x50.c
+++ b/arch/arm/mach-msm/board-qsd8x50.c
@@ -28,7 +28,6 @@
 #include <asm/io.h>
 #include <asm/setup.h>
 
-#include <mach/board.h>
 #include <mach/irqs.h>
 #include <mach/sirc.h>
 #include <mach/vreg.h>
diff --git a/arch/arm/mach-msm/board-sapphire.c b/arch/arm/mach-msm/board-sapphire.c
index 70730111b37c..327605174d63 100644
--- a/arch/arm/mach-msm/board-sapphire.c
+++ b/arch/arm/mach-msm/board-sapphire.c
@@ -28,7 +28,6 @@
 #include <asm/mach/map.h>
 #include <asm/mach/flash.h>
 #include <mach/vreg.h>
-#include <mach/board.h>
 
 #include <asm/io.h>
 #include <asm/delay.h>
@@ -41,6 +40,7 @@
 #include "board-sapphire.h"
 #include "proc_comm.h"
 #include "devices.h"
+#include "common.h"
 
 void msm_init_irq(void);
 void msm_init_gpio(void);
diff --git a/arch/arm/mach-msm/board-trout.c b/arch/arm/mach-msm/board-trout.c
index 64a46eb4fc49..ccf6621bc664 100644
--- a/arch/arm/mach-msm/board-trout.c
+++ b/arch/arm/mach-msm/board-trout.c
@@ -25,7 +25,6 @@
 #include <asm/mach/map.h>
 #include <asm/setup.h>
 
-#include <mach/board.h>
 #include <mach/hardware.h>
 #include <mach/msm_iomap.h>
 
diff --git a/arch/arm/mach-msm/board-trout.h b/arch/arm/mach-msm/board-trout.h
index 651851c3e1dd..b2379ede43bc 100644
--- a/arch/arm/mach-msm/board-trout.h
+++ b/arch/arm/mach-msm/board-trout.h
@@ -4,7 +4,7 @@
 #ifndef __ARCH_ARM_MACH_MSM_BOARD_TROUT_H
 #define __ARCH_ARM_MACH_MSM_BOARD_TROUT_H
 
-#include <mach/board.h>
+#include "common.h"
 
 #define MSM_SMI_BASE		0x00000000
 #define MSM_SMI_SIZE		0x00800000
diff --git a/arch/arm/mach-msm/common.h b/arch/arm/mach-msm/common.h
index 421cf7751a80..33c7725adae2 100644
--- a/arch/arm/mach-msm/common.h
+++ b/arch/arm/mach-msm/common.h
@@ -14,13 +14,10 @@
 
 extern void msm7x01_timer_init(void);
 extern void msm7x30_timer_init(void);
-extern void msm_dt_timer_init(void);
 extern void qsd8x50_timer_init(void);
 
 extern void msm_map_common_io(void);
 extern void msm_map_msm7x30_io(void);
-extern void msm_map_msm8x60_io(void);
-extern void msm_map_msm8960_io(void);
 extern void msm_map_qsd8x50_io(void);
 
 extern void __iomem *__msm_ioremap_caller(phys_addr_t phys_addr, size_t size,
@@ -29,4 +26,19 @@ extern void __iomem *__msm_ioremap_caller(phys_addr_t phys_addr, size_t size,
 extern struct smp_operations msm_smp_ops;
 extern void msm_cpu_die(unsigned int cpu);
 
+struct msm_mmc_platform_data;
+
+extern void msm_add_devices(void);
+extern void msm_init_irq(void);
+extern void msm_init_gpio(void);
+extern int msm_add_sdcc(unsigned int controller,
+			struct msm_mmc_platform_data *plat,
+			unsigned int stat_irq, unsigned long stat_irq_flags);
+
+#if defined(CONFIG_MSM_SMD) && defined(CONFIG_DEBUG_FS)
+extern int smd_debugfs_init(void);
+#else
+static inline int smd_debugfs_init(void) { return 0; }
+#endif
+
 #endif
diff --git a/arch/arm/mach-msm/devices-iommu.c b/arch/arm/mach-msm/devices-iommu.c
deleted file mode 100644
index 0fb7a17df398..000000000000
--- a/arch/arm/mach-msm/devices-iommu.c
+++ /dev/null
@@ -1,912 +0,0 @@
-/* Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
- * 02110-1301, USA.
- */
-
-#include <linux/kernel.h>
-#include <linux/platform_device.h>
-#include <linux/bootmem.h>
-#include <linux/module.h>
-#include <mach/irqs.h>
-#include <mach/iommu.h>
-
-static struct resource msm_iommu_jpegd_resources[] = {
-	{
-		.start = 0x07300000,
-		.end   = 0x07300000 + SZ_1M - 1,
-		.name  = "physbase",
-		.flags = IORESOURCE_MEM,
-	},
-	{
-		.name = "nonsecure_irq",
-		.start = SMMU_JPEGD_CB_SC_NON_SECURE_IRQ,
-		.end   = SMMU_JPEGD_CB_SC_NON_SECURE_IRQ,
-		.flags = IORESOURCE_IRQ,
-	},
-	{
-		.name = "secure_irq",
-		.start = SMMU_JPEGD_CB_SC_SECURE_IRQ,
-		.end   = SMMU_JPEGD_CB_SC_SECURE_IRQ,
-		.flags = IORESOURCE_IRQ,
-	},
-};
-
-static struct resource msm_iommu_vpe_resources[] = {
-	{
-		.start = 0x07400000,
-		.end   = 0x07400000 + SZ_1M - 1,
-		.name  = "physbase",
-		.flags = IORESOURCE_MEM,
-	},
-	{
-		.name = "nonsecure_irq",
-		.start = SMMU_VPE_CB_SC_NON_SECURE_IRQ,
-		.end   = SMMU_VPE_CB_SC_NON_SECURE_IRQ,
-		.flags = IORESOURCE_IRQ,
-	},
-	{
-		.name = "secure_irq",
-		.start = SMMU_VPE_CB_SC_SECURE_IRQ,
-		.end   = SMMU_VPE_CB_SC_SECURE_IRQ,
-		.flags = IORESOURCE_IRQ,
-	},
-};
-
-static struct resource msm_iommu_mdp0_resources[] = {
-	{
-		.start = 0x07500000,
-		.end   = 0x07500000 + SZ_1M - 1,
-		.name  = "physbase",
-		.flags = IORESOURCE_MEM,
-	},
-	{
-		.name = "nonsecure_irq",
-		.start = SMMU_MDP0_CB_SC_NON_SECURE_IRQ,
-		.end   = SMMU_MDP0_CB_SC_NON_SECURE_IRQ,
-		.flags = IORESOURCE_IRQ,
-	},
-	{
-		.name = "secure_irq",
-		.start = SMMU_MDP0_CB_SC_SECURE_IRQ,
-		.end   = SMMU_MDP0_CB_SC_SECURE_IRQ,
-		.flags = IORESOURCE_IRQ,
-	},
-};
-
-static struct resource msm_iommu_mdp1_resources[] = {
-	{
-		.start = 0x07600000,
-		.end   = 0x07600000 + SZ_1M - 1,
-		.name  = "physbase",
-		.flags = IORESOURCE_MEM,
-	},
-	{
-		.name = "nonsecure_irq",
-		.start = SMMU_MDP1_CB_SC_NON_SECURE_IRQ,
-		.end   = SMMU_MDP1_CB_SC_NON_SECURE_IRQ,
-		.flags = IORESOURCE_IRQ,
-	},
-	{
-		.name = "secure_irq",
-		.start = SMMU_MDP1_CB_SC_SECURE_IRQ,
-		.end   = SMMU_MDP1_CB_SC_SECURE_IRQ,
-		.flags = IORESOURCE_IRQ,
-	},
-};
-
-static struct resource msm_iommu_rot_resources[] = {
-	{
-		.start = 0x07700000,
-		.end   = 0x07700000 + SZ_1M - 1,
-		.name  = "physbase",
-		.flags = IORESOURCE_MEM,
-	},
-	{
-		.name = "nonsecure_irq",
-		.start = SMMU_ROT_CB_SC_NON_SECURE_IRQ,
-		.end   = SMMU_ROT_CB_SC_NON_SECURE_IRQ,
-		.flags = IORESOURCE_IRQ,
-	},
-	{
-		.name = "secure_irq",
-		.start = SMMU_ROT_CB_SC_SECURE_IRQ,
-		.end   = SMMU_ROT_CB_SC_SECURE_IRQ,
-		.flags = IORESOURCE_IRQ,
-	},
-};
-
-static struct resource msm_iommu_ijpeg_resources[] = {
-	{
-		.start = 0x07800000,
-		.end   = 0x07800000 + SZ_1M - 1,
-		.name  = "physbase",
-		.flags = IORESOURCE_MEM,
-	},
-	{
-		.name = "nonsecure_irq",
-		.start = SMMU_IJPEG_CB_SC_NON_SECURE_IRQ,
-		.end   = SMMU_IJPEG_CB_SC_NON_SECURE_IRQ,
-		.flags = IORESOURCE_IRQ,
-	},
-	{
-		.name = "secure_irq",
-		.start = SMMU_IJPEG_CB_SC_SECURE_IRQ,
-		.end   = SMMU_IJPEG_CB_SC_SECURE_IRQ,
-		.flags = IORESOURCE_IRQ,
-	},
-};
-
-static struct resource msm_iommu_vfe_resources[] = {
-	{
-		.start = 0x07900000,
-		.end   = 0x07900000 + SZ_1M - 1,
-		.name  = "physbase",
-		.flags = IORESOURCE_MEM,
-	},
-	{
-		.name = "nonsecure_irq",
-		.start = SMMU_VFE_CB_SC_NON_SECURE_IRQ,
-		.end   = SMMU_VFE_CB_SC_NON_SECURE_IRQ,
-		.flags = IORESOURCE_IRQ,
-	},
-	{
-		.name = "secure_irq",
-		.start = SMMU_VFE_CB_SC_SECURE_IRQ,
-		.end   = SMMU_VFE_CB_SC_SECURE_IRQ,
-		.flags = IORESOURCE_IRQ,
-	},
-};
-
-static struct resource msm_iommu_vcodec_a_resources[] = {
-	{
-		.start = 0x07A00000,
-		.end   = 0x07A00000 + SZ_1M - 1,
-		.name  = "physbase",
-		.flags = IORESOURCE_MEM,
-	},
-	{
-		.name = "nonsecure_irq",
-		.start = SMMU_VCODEC_A_CB_SC_NON_SECURE_IRQ,
-		.end   = SMMU_VCODEC_A_CB_SC_NON_SECURE_IRQ,
-		.flags = IORESOURCE_IRQ,
-	},
-	{
-		.name = "secure_irq",
-		.start = SMMU_VCODEC_A_CB_SC_SECURE_IRQ,
-		.end   = SMMU_VCODEC_A_CB_SC_SECURE_IRQ,
-		.flags = IORESOURCE_IRQ,
-	},
-};
-
-static struct resource msm_iommu_vcodec_b_resources[] = {
-	{
-		.start = 0x07B00000,
-		.end   = 0x07B00000 + SZ_1M - 1,
-		.name  = "physbase",
-		.flags = IORESOURCE_MEM,
-	},
-	{
-		.name = "nonsecure_irq",
-		.start = SMMU_VCODEC_B_CB_SC_NON_SECURE_IRQ,
-		.end   = SMMU_VCODEC_B_CB_SC_NON_SECURE_IRQ,
-		.flags = IORESOURCE_IRQ,
-	},
-	{
-		.name = "secure_irq",
-		.start = SMMU_VCODEC_B_CB_SC_SECURE_IRQ,
-		.end   = SMMU_VCODEC_B_CB_SC_SECURE_IRQ,
-		.flags = IORESOURCE_IRQ,
-	},
-};
-
-static struct resource msm_iommu_gfx3d_resources[] = {
-	{
-		.start = 0x07C00000,
-		.end   = 0x07C00000 + SZ_1M - 1,
-		.name  = "physbase",
-		.flags = IORESOURCE_MEM,
-	},
-	{
-		.name = "nonsecure_irq",
-		.start = SMMU_GFX3D_CB_SC_NON_SECURE_IRQ,
-		.end   = SMMU_GFX3D_CB_SC_NON_SECURE_IRQ,
-		.flags = IORESOURCE_IRQ,
-	},
-	{
-		.name = "secure_irq",
-		.start = SMMU_GFX3D_CB_SC_SECURE_IRQ,
-		.end   = SMMU_GFX3D_CB_SC_SECURE_IRQ,
-		.flags = IORESOURCE_IRQ,
-	},
-};
-
-static struct resource msm_iommu_gfx2d0_resources[] = {
-	{
-		.start = 0x07D00000,
-		.end   = 0x07D00000 + SZ_1M - 1,
-		.name  = "physbase",
-		.flags = IORESOURCE_MEM,
-	},
-	{
-		.name = "nonsecure_irq",
-		.start = SMMU_GFX2D0_CB_SC_NON_SECURE_IRQ,
-		.end   = SMMU_GFX2D0_CB_SC_NON_SECURE_IRQ,
-		.flags = IORESOURCE_IRQ,
-	},
-	{
-		.name = "secure_irq",
-		.start = SMMU_GFX2D0_CB_SC_SECURE_IRQ,
-		.end   = SMMU_GFX2D0_CB_SC_SECURE_IRQ,
-		.flags = IORESOURCE_IRQ,
-	},
-};
-
-static struct resource msm_iommu_gfx2d1_resources[] = {
-	{
-		.start = 0x07E00000,
-		.end   = 0x07E00000 + SZ_1M - 1,
-		.name  = "physbase",
-		.flags = IORESOURCE_MEM,
-	},
-	{
-		.name = "nonsecure_irq",
-		.start = SMMU_GFX2D1_CB_SC_NON_SECURE_IRQ,
-		.end   = SMMU_GFX2D1_CB_SC_NON_SECURE_IRQ,
-		.flags = IORESOURCE_IRQ,
-	},
-	{
-		.name = "secure_irq",
-		.start = SMMU_GFX2D1_CB_SC_SECURE_IRQ,
-		.end   = SMMU_GFX2D1_CB_SC_SECURE_IRQ,
-		.flags = IORESOURCE_IRQ,
-	},
-};
-
-static struct platform_device msm_root_iommu_dev = {
-	.name = "msm_iommu",
-	.id = -1,
-};
-
-static struct msm_iommu_dev jpegd_iommu = {
-	.name = "jpegd",
-	.ncb = 2,
-};
-
-static struct msm_iommu_dev vpe_iommu = {
-	.name = "vpe",
-	.ncb = 2,
-};
-
-static struct msm_iommu_dev mdp0_iommu = {
-	.name = "mdp0",
-	.ncb = 2,
-};
-
-static struct msm_iommu_dev mdp1_iommu = {
-	.name = "mdp1",
-	.ncb = 2,
-};
-
-static struct msm_iommu_dev rot_iommu = {
-	.name = "rot",
-	.ncb = 2,
-};
-
-static struct msm_iommu_dev ijpeg_iommu = {
-	.name = "ijpeg",
-	.ncb = 2,
-};
-
-static struct msm_iommu_dev vfe_iommu = {
-	.name = "vfe",
-	.ncb = 2,
-};
-
-static struct msm_iommu_dev vcodec_a_iommu = {
-	.name = "vcodec_a",
-	.ncb = 2,
-};
-
-static struct msm_iommu_dev vcodec_b_iommu = {
-	.name = "vcodec_b",
-	.ncb = 2,
-};
-
-static struct msm_iommu_dev gfx3d_iommu = {
-	.name = "gfx3d",
-	.ncb = 3,
-};
-
-static struct msm_iommu_dev gfx2d0_iommu = {
-	.name = "gfx2d0",
-	.ncb = 2,
-};
-
-static struct msm_iommu_dev gfx2d1_iommu = {
-	.name = "gfx2d1",
-	.ncb = 2,
-};
-
-static struct platform_device msm_device_iommu_jpegd = {
-	.name = "msm_iommu",
-	.id = 0,
-	.dev = {
-		.parent = &msm_root_iommu_dev.dev,
-	},
-	.num_resources = ARRAY_SIZE(msm_iommu_jpegd_resources),
-	.resource = msm_iommu_jpegd_resources,
-};
-
-static struct platform_device msm_device_iommu_vpe = {
-	.name = "msm_iommu",
-	.id = 1,
-	.dev = {
-		.parent = &msm_root_iommu_dev.dev,
-	},
-	.num_resources = ARRAY_SIZE(msm_iommu_vpe_resources),
-	.resource = msm_iommu_vpe_resources,
-};
-
-static struct platform_device msm_device_iommu_mdp0 = {
-	.name = "msm_iommu",
-	.id = 2,
-	.dev = {
-		.parent = &msm_root_iommu_dev.dev,
-	},
-	.num_resources = ARRAY_SIZE(msm_iommu_mdp0_resources),
-	.resource = msm_iommu_mdp0_resources,
-};
-
-static struct platform_device msm_device_iommu_mdp1 = {
-	.name = "msm_iommu",
-	.id = 3,
-	.dev = {
-		.parent = &msm_root_iommu_dev.dev,
-	},
-	.num_resources = ARRAY_SIZE(msm_iommu_mdp1_resources),
-	.resource = msm_iommu_mdp1_resources,
-};
-
-static struct platform_device msm_device_iommu_rot = {
-	.name = "msm_iommu",
-	.id = 4,
-	.dev = {
-		.parent = &msm_root_iommu_dev.dev,
-	},
-	.num_resources = ARRAY_SIZE(msm_iommu_rot_resources),
-	.resource = msm_iommu_rot_resources,
-};
-
-static struct platform_device msm_device_iommu_ijpeg = {
-	.name = "msm_iommu",
-	.id = 5,
-	.dev = {
-		.parent = &msm_root_iommu_dev.dev,
-	},
-	.num_resources = ARRAY_SIZE(msm_iommu_ijpeg_resources),
-	.resource = msm_iommu_ijpeg_resources,
-};
-
-static struct platform_device msm_device_iommu_vfe = {
-	.name = "msm_iommu",
-	.id = 6,
-	.dev = {
-		.parent = &msm_root_iommu_dev.dev,
-	},
-	.num_resources = ARRAY_SIZE(msm_iommu_vfe_resources),
-	.resource = msm_iommu_vfe_resources,
-};
-
-static struct platform_device msm_device_iommu_vcodec_a = {
-	.name = "msm_iommu",
-	.id = 7,
-	.dev = {
-		.parent = &msm_root_iommu_dev.dev,
-	},
-	.num_resources = ARRAY_SIZE(msm_iommu_vcodec_a_resources),
-	.resource = msm_iommu_vcodec_a_resources,
-};
-
-static struct platform_device msm_device_iommu_vcodec_b = {
-	.name = "msm_iommu",
-	.id = 8,
-	.dev = {
-		.parent = &msm_root_iommu_dev.dev,
-	},
-	.num_resources = ARRAY_SIZE(msm_iommu_vcodec_b_resources),
-	.resource = msm_iommu_vcodec_b_resources,
-};
-
-static struct platform_device msm_device_iommu_gfx3d = {
-	.name = "msm_iommu",
-	.id = 9,
-	.dev = {
-		.parent = &msm_root_iommu_dev.dev,
-	},
-	.num_resources = ARRAY_SIZE(msm_iommu_gfx3d_resources),
-	.resource = msm_iommu_gfx3d_resources,
-};
-
-static struct platform_device msm_device_iommu_gfx2d0 = {
-	.name = "msm_iommu",
-	.id = 10,
-	.dev = {
-		.parent = &msm_root_iommu_dev.dev,
-	},
-	.num_resources = ARRAY_SIZE(msm_iommu_gfx2d0_resources),
-	.resource = msm_iommu_gfx2d0_resources,
-};
-
-struct platform_device msm_device_iommu_gfx2d1 = {
-	.name = "msm_iommu",
-	.id = 11,
-	.dev = {
-		.parent = &msm_root_iommu_dev.dev,
-	},
-	.num_resources = ARRAY_SIZE(msm_iommu_gfx2d1_resources),
-	.resource = msm_iommu_gfx2d1_resources,
-};
-
-static struct msm_iommu_ctx_dev jpegd_src_ctx = {
-	.name = "jpegd_src",
-	.num = 0,
-	.mids = {0, -1}
-};
-
-static struct msm_iommu_ctx_dev jpegd_dst_ctx = {
-	.name = "jpegd_dst",
-	.num = 1,
-	.mids = {1, -1}
-};
-
-static struct msm_iommu_ctx_dev vpe_src_ctx = {
-	.name = "vpe_src",
-	.num = 0,
-	.mids = {0, -1}
-};
-
-static struct msm_iommu_ctx_dev vpe_dst_ctx = {
-	.name = "vpe_dst",
-	.num = 1,
-	.mids = {1, -1}
-};
-
-static struct msm_iommu_ctx_dev mdp_vg1_ctx = {
-	.name = "mdp_vg1",
-	.num = 0,
-	.mids = {0, 2, -1}
-};
-
-static struct msm_iommu_ctx_dev mdp_rgb1_ctx = {
-	.name = "mdp_rgb1",
-	.num = 1,
-	.mids = {1, 3, 4, 5, 6, 7, 8, 9, 10, -1}
-};
-
-static struct msm_iommu_ctx_dev mdp_vg2_ctx = {
-	.name = "mdp_vg2",
-	.num = 0,
-	.mids = {0, 2, -1}
-};
-
-static struct msm_iommu_ctx_dev mdp_rgb2_ctx = {
-	.name = "mdp_rgb2",
-	.num = 1,
-	.mids = {1, 3, 4, 5, 6, 7, 8, 9, 10, -1}
-};
-
-static struct msm_iommu_ctx_dev rot_src_ctx = {
-	.name = "rot_src",
-	.num = 0,
-	.mids = {0, -1}
-};
-
-static struct msm_iommu_ctx_dev rot_dst_ctx = {
-	.name = "rot_dst",
-	.num = 1,
-	.mids = {1, -1}
-};
-
-static struct msm_iommu_ctx_dev ijpeg_src_ctx = {
-	.name = "ijpeg_src",
-	.num = 0,
-	.mids = {0, -1}
-};
-
-static struct msm_iommu_ctx_dev ijpeg_dst_ctx = {
-	.name = "ijpeg_dst",
-	.num = 1,
-	.mids = {1, -1}
-};
-
-static struct msm_iommu_ctx_dev vfe_imgwr_ctx = {
-	.name = "vfe_imgwr",
-	.num = 0,
-	.mids = {2, 3, 4, 5, 6, 7, 8, -1}
-};
-
-static struct msm_iommu_ctx_dev vfe_misc_ctx = {
-	.name = "vfe_misc",
-	.num = 1,
-	.mids = {0, 1, 9, -1}
-};
-
-static struct msm_iommu_ctx_dev vcodec_a_stream_ctx = {
-	.name = "vcodec_a_stream",
-	.num = 0,
-	.mids = {2, 5, -1}
-};
-
-static struct msm_iommu_ctx_dev vcodec_a_mm1_ctx = {
-	.name = "vcodec_a_mm1",
-	.num = 1,
-	.mids = {0, 1, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, -1}
-};
-
-static struct msm_iommu_ctx_dev vcodec_b_mm2_ctx = {
-	.name = "vcodec_b_mm2",
-	.num = 0,
-	.mids = {0, 1, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, -1}
-};
-
-static struct msm_iommu_ctx_dev gfx3d_user_ctx = {
-	.name = "gfx3d_user",
-	.num = 0,
-	.mids = {0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, -1}
-};
-
-static struct msm_iommu_ctx_dev gfx3d_priv_ctx = {
-	.name = "gfx3d_priv",
-	.num = 1,
-	.mids = {16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30,
-		 31, -1}
-};
-
-static struct msm_iommu_ctx_dev gfx2d0_2d0_ctx = {
-	.name = "gfx2d0_2d0",
-	.num = 0,
-	.mids = {0, 1, 2, 3, 4, 5, 6, 7, -1}
-};
-
-static struct msm_iommu_ctx_dev gfx2d1_2d1_ctx = {
-	.name = "gfx2d1_2d1",
-	.num = 0,
-	.mids = {0, 1, 2, 3, 4, 5, 6, 7, -1}
-};
-
-static struct platform_device msm_device_jpegd_src_ctx = {
-	.name = "msm_iommu_ctx",
-	.id = 0,
-	.dev = {
-		.parent = &msm_device_iommu_jpegd.dev,
-	},
-};
-
-static struct platform_device msm_device_jpegd_dst_ctx = {
-	.name = "msm_iommu_ctx",
-	.id = 1,
-	.dev = {
-		.parent = &msm_device_iommu_jpegd.dev,
-	},
-};
-
-static struct platform_device msm_device_vpe_src_ctx = {
-	.name = "msm_iommu_ctx",
-	.id = 2,
-	.dev = {
-		.parent = &msm_device_iommu_vpe.dev,
-	},
-};
-
-static struct platform_device msm_device_vpe_dst_ctx = {
-	.name = "msm_iommu_ctx",
-	.id = 3,
-	.dev = {
-		.parent = &msm_device_iommu_vpe.dev,
-	},
-};
-
-static struct platform_device msm_device_mdp_vg1_ctx = {
-	.name = "msm_iommu_ctx",
-	.id = 4,
-	.dev = {
-		.parent = &msm_device_iommu_mdp0.dev,
-	},
-};
-
-static struct platform_device msm_device_mdp_rgb1_ctx = {
-	.name = "msm_iommu_ctx",
-	.id = 5,
-	.dev = {
-		.parent = &msm_device_iommu_mdp0.dev,
-	},
-};
-
-static struct platform_device msm_device_mdp_vg2_ctx = {
-	.name = "msm_iommu_ctx",
-	.id = 6,
-	.dev = {
-		.parent = &msm_device_iommu_mdp1.dev,
-	},
-};
-
-static struct platform_device msm_device_mdp_rgb2_ctx = {
-	.name = "msm_iommu_ctx",
-	.id = 7,
-	.dev = {
-		.parent = &msm_device_iommu_mdp1.dev,
-	},
-};
-
-static struct platform_device msm_device_rot_src_ctx = {
-	.name = "msm_iommu_ctx",
-	.id = 8,
-	.dev = {
-		.parent = &msm_device_iommu_rot.dev,
-	},
-};
-
-static struct platform_device msm_device_rot_dst_ctx = {
-	.name = "msm_iommu_ctx",
-	.id = 9,
-	.dev = {
-		.parent = &msm_device_iommu_rot.dev,
-	},
-};
-
-static struct platform_device msm_device_ijpeg_src_ctx = {
-	.name = "msm_iommu_ctx",
-	.id = 10,
-	.dev = {
-		.parent = &msm_device_iommu_ijpeg.dev,
-	},
-};
-
-static struct platform_device msm_device_ijpeg_dst_ctx = {
-	.name = "msm_iommu_ctx",
-	.id = 11,
-	.dev = {
-		.parent = &msm_device_iommu_ijpeg.dev,
-	},
-};
-
-static struct platform_device msm_device_vfe_imgwr_ctx = {
-	.name = "msm_iommu_ctx",
-	.id = 12,
-	.dev = {
-		.parent = &msm_device_iommu_vfe.dev,
-	},
-};
-
-static struct platform_device msm_device_vfe_misc_ctx = {
-	.name = "msm_iommu_ctx",
-	.id = 13,
-	.dev = {
-		.parent = &msm_device_iommu_vfe.dev,
-	},
-};
-
-static struct platform_device msm_device_vcodec_a_stream_ctx = {
-	.name = "msm_iommu_ctx",
-	.id = 14,
-	.dev = {
-		.parent = &msm_device_iommu_vcodec_a.dev,
-	},
-};
-
-static struct platform_device msm_device_vcodec_a_mm1_ctx = {
-	.name = "msm_iommu_ctx",
-	.id = 15,
-	.dev = {
-		.parent = &msm_device_iommu_vcodec_a.dev,
-	},
-};
-
-static struct platform_device msm_device_vcodec_b_mm2_ctx = {
-	.name = "msm_iommu_ctx",
-	.id = 16,
-	.dev = {
-		.parent = &msm_device_iommu_vcodec_b.dev,
-	},
-};
-
-static struct platform_device msm_device_gfx3d_user_ctx = {
-	.name = "msm_iommu_ctx",
-	.id = 17,
-	.dev = {
-		.parent = &msm_device_iommu_gfx3d.dev,
-	},
-};
-
-static struct platform_device msm_device_gfx3d_priv_ctx = {
-	.name = "msm_iommu_ctx",
-	.id = 18,
-	.dev = {
-		.parent = &msm_device_iommu_gfx3d.dev,
-	},
-};
-
-static struct platform_device msm_device_gfx2d0_2d0_ctx = {
-	.name = "msm_iommu_ctx",
-	.id = 19,
-	.dev = {
-		.parent = &msm_device_iommu_gfx2d0.dev,
-	},
-};
-
-static struct platform_device msm_device_gfx2d1_2d1_ctx = {
-	.name = "msm_iommu_ctx",
-	.id = 20,
-	.dev = {
-		.parent = &msm_device_iommu_gfx2d1.dev,
-	},
-};
-
-static struct platform_device *msm_iommu_devs[] = {
-	&msm_device_iommu_jpegd,
-	&msm_device_iommu_vpe,
-	&msm_device_iommu_mdp0,
-	&msm_device_iommu_mdp1,
-	&msm_device_iommu_rot,
-	&msm_device_iommu_ijpeg,
-	&msm_device_iommu_vfe,
-	&msm_device_iommu_vcodec_a,
-	&msm_device_iommu_vcodec_b,
-	&msm_device_iommu_gfx3d,
-	&msm_device_iommu_gfx2d0,
-	&msm_device_iommu_gfx2d1,
-};
-
-static struct msm_iommu_dev *msm_iommu_data[] = {
-	&jpegd_iommu,
-	&vpe_iommu,
-	&mdp0_iommu,
-	&mdp1_iommu,
-	&rot_iommu,
-	&ijpeg_iommu,
-	&vfe_iommu,
-	&vcodec_a_iommu,
-	&vcodec_b_iommu,
-	&gfx3d_iommu,
-	&gfx2d0_iommu,
-	&gfx2d1_iommu,
-};
-
-static struct platform_device *msm_iommu_ctx_devs[] = {
-	&msm_device_jpegd_src_ctx,
-	&msm_device_jpegd_dst_ctx,
-	&msm_device_vpe_src_ctx,
-	&msm_device_vpe_dst_ctx,
-	&msm_device_mdp_vg1_ctx,
-	&msm_device_mdp_rgb1_ctx,
-	&msm_device_mdp_vg2_ctx,
-	&msm_device_mdp_rgb2_ctx,
-	&msm_device_rot_src_ctx,
-	&msm_device_rot_dst_ctx,
-	&msm_device_ijpeg_src_ctx,
-	&msm_device_ijpeg_dst_ctx,
-	&msm_device_vfe_imgwr_ctx,
-	&msm_device_vfe_misc_ctx,
-	&msm_device_vcodec_a_stream_ctx,
-	&msm_device_vcodec_a_mm1_ctx,
-	&msm_device_vcodec_b_mm2_ctx,
-	&msm_device_gfx3d_user_ctx,
-	&msm_device_gfx3d_priv_ctx,
-	&msm_device_gfx2d0_2d0_ctx,
-	&msm_device_gfx2d1_2d1_ctx,
-};
-
-static struct msm_iommu_ctx_dev *msm_iommu_ctx_data[] = {
-	&jpegd_src_ctx,
-	&jpegd_dst_ctx,
-	&vpe_src_ctx,
-	&vpe_dst_ctx,
-	&mdp_vg1_ctx,
-	&mdp_rgb1_ctx,
-	&mdp_vg2_ctx,
-	&mdp_rgb2_ctx,
-	&rot_src_ctx,
-	&rot_dst_ctx,
-	&ijpeg_src_ctx,
-	&ijpeg_dst_ctx,
-	&vfe_imgwr_ctx,
-	&vfe_misc_ctx,
-	&vcodec_a_stream_ctx,
-	&vcodec_a_mm1_ctx,
-	&vcodec_b_mm2_ctx,
-	&gfx3d_user_ctx,
-	&gfx3d_priv_ctx,
-	&gfx2d0_2d0_ctx,
-	&gfx2d1_2d1_ctx,
-};
-
-static int __init msm8x60_iommu_init(void)
-{
-	int ret, i;
-
-	ret = platform_device_register(&msm_root_iommu_dev);
-	if (ret != 0) {
-		pr_err("Failed to register root IOMMU device!\n");
-		goto failure;
-	}
-
-	for (i = 0; i < ARRAY_SIZE(msm_iommu_devs); i++) {
-		ret = platform_device_add_data(msm_iommu_devs[i],
-					       msm_iommu_data[i],
-					       sizeof(struct msm_iommu_dev));
-		if (ret != 0) {
-			pr_err("platform_device_add_data failed, "
-			       "i = %d\n", i);
-			goto failure_unwind;
-		}
-
-		ret = platform_device_register(msm_iommu_devs[i]);
-
-		if (ret != 0) {
-			pr_err("platform_device_register iommu failed, "
-			       "i = %d\n", i);
-			goto failure_unwind;
-		}
-	}
-
-	for (i = 0; i < ARRAY_SIZE(msm_iommu_ctx_devs); i++) {
-		ret = platform_device_add_data(msm_iommu_ctx_devs[i],
-					       msm_iommu_ctx_data[i],
-					       sizeof(*msm_iommu_ctx_devs[i]));
-		if (ret != 0) {
-			pr_err("platform_device_add_data iommu failed, "
-			       "i = %d\n", i);
-			goto failure_unwind2;
-		}
-
-		ret = platform_device_register(msm_iommu_ctx_devs[i]);
-		if (ret != 0) {
-			pr_err("platform_device_register ctx failed, "
-			       "i = %d\n", i);
-			goto failure_unwind2;
-		}
-	}
-	return 0;
-
-failure_unwind2:
-	while (--i >= 0)
-		platform_device_unregister(msm_iommu_ctx_devs[i]);
-failure_unwind:
-	while (--i >= 0)
-		platform_device_unregister(msm_iommu_devs[i]);
-
-	platform_device_unregister(&msm_root_iommu_dev);
-failure:
-	return ret;
-}
-
-static void __exit msm8x60_iommu_exit(void)
-{
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(msm_iommu_ctx_devs); i++)
-		platform_device_unregister(msm_iommu_ctx_devs[i]);
-
-	for (i = 0; i < ARRAY_SIZE(msm_iommu_devs); ++i)
-		platform_device_unregister(msm_iommu_devs[i]);
-
-	platform_device_unregister(&msm_root_iommu_dev);
-}
-
-subsys_initcall(msm8x60_iommu_init);
-module_exit(msm8x60_iommu_exit);
-
-MODULE_LICENSE("GPL v2");
-MODULE_AUTHOR("Stepan Moskovchenko <stepanm@codeaurora.org>");
diff --git a/arch/arm/mach-msm/devices-msm7x00.c b/arch/arm/mach-msm/devices-msm7x00.c
index 6d50fb964863..d83404d4b328 100644
--- a/arch/arm/mach-msm/devices-msm7x00.c
+++ b/arch/arm/mach-msm/devices-msm7x00.c
@@ -456,9 +456,9 @@ static struct clk_pcom_desc msm_clocks_7x01a[] = {
 	CLK_PCOM("tsif_ref_clk",	TSIF_REF_CLK,	NULL, 0),
 	CLK_PCOM("tv_dac_clk",	TV_DAC_CLK,	NULL, 0),
 	CLK_PCOM("tv_enc_clk",	TV_ENC_CLK,	NULL, 0),
-	CLK_PCOM("uart_clk",	UART1_CLK,	"msm_serial.0", OFF),
-	CLK_PCOM("uart_clk",	UART2_CLK,	"msm_serial.1", 0),
-	CLK_PCOM("uart_clk",	UART3_CLK,	"msm_serial.2", OFF),
+	CLK_PCOM("core",	UART1_CLK,	"msm_serial.0", OFF),
+	CLK_PCOM("core",	UART2_CLK,	"msm_serial.1", 0),
+	CLK_PCOM("core",	UART3_CLK,	"msm_serial.2", OFF),
 	CLK_PCOM("uart1dm_clk",	UART1DM_CLK,	NULL, OFF),
 	CLK_PCOM("uart2dm_clk",	UART2DM_CLK,	NULL, 0),
 	CLK_PCOM("usb_hs_clk",	USB_HS_CLK,	"msm_hsusb", OFF),
diff --git a/arch/arm/mach-msm/devices-msm7x30.c b/arch/arm/mach-msm/devices-msm7x30.c
index d4db75acff56..c15ea8ab20a7 100644
--- a/arch/arm/mach-msm/devices-msm7x30.c
+++ b/arch/arm/mach-msm/devices-msm7x30.c
@@ -21,10 +21,10 @@
 #include <mach/irqs.h>
 #include <mach/msm_iomap.h>
 #include <mach/dma.h>
-#include <mach/board.h>
 
 #include "devices.h"
 #include "smd_private.h"
+#include "common.h"
 
 #include <asm/mach/flash.h>
 
@@ -211,7 +211,7 @@ static struct clk_pcom_desc msm_clocks_7x30[] = {
 	CLK_PCOM("spi_pclk",	SPI_P_CLK,	NULL, 0),
 	CLK_PCOM("tv_dac_clk",	TV_DAC_CLK,	NULL, 0),
 	CLK_PCOM("tv_enc_clk",	TV_ENC_CLK,	NULL, 0),
-	CLK_PCOM("uart_clk",	UART2_CLK,	"msm_serial.1", 0),
+	CLK_PCOM("core",	UART2_CLK,	"msm_serial.1", 0),
 	CLK_PCOM("usb_phy_clk",	USB_PHY_CLK,	NULL, 0),
 	CLK_PCOM("usb_hs_clk",		USB_HS_CLK,		NULL, OFF),
 	CLK_PCOM("usb_hs_pclk",		USB_HS_P_CLK,		NULL, OFF),
diff --git a/arch/arm/mach-msm/devices-qsd8x50.c b/arch/arm/mach-msm/devices-qsd8x50.c
index f5518112284b..9e1e9ce07b1a 100644
--- a/arch/arm/mach-msm/devices-qsd8x50.c
+++ b/arch/arm/mach-msm/devices-qsd8x50.c
@@ -21,9 +21,9 @@
 #include <mach/irqs.h>
 #include <mach/msm_iomap.h>
 #include <mach/dma.h>
-#include <mach/board.h>
 
 #include "devices.h"
+#include "common.h"
 
 #include <asm/mach/flash.h>
 
@@ -358,9 +358,9 @@ static struct clk_pcom_desc msm_clocks_8x50[] = {
 	CLK_PCOM("tsif_ref_clk",	TSIF_REF_CLK,	NULL, 0),
 	CLK_PCOM("tv_dac_clk",	TV_DAC_CLK,	NULL, 0),
 	CLK_PCOM("tv_enc_clk",	TV_ENC_CLK,	NULL, 0),
-	CLK_PCOM("uart_clk",	UART1_CLK,	NULL, OFF),
-	CLK_PCOM("uart_clk",	UART2_CLK,	NULL, 0),
-	CLK_PCOM("uart_clk",	UART3_CLK,	"msm_serial.2", OFF),
+	CLK_PCOM("core",	UART1_CLK,	NULL, OFF),
+	CLK_PCOM("core",	UART2_CLK,	NULL, 0),
+	CLK_PCOM("core",	UART3_CLK,	"msm_serial.2", OFF),
 	CLK_PCOM("uartdm_clk",	UART1DM_CLK,	NULL, OFF),
 	CLK_PCOM("uartdm_clk",	UART2DM_CLK,	NULL, 0),
 	CLK_PCOM("usb_hs_clk",	USB_HS_CLK,	NULL, OFF),
diff --git a/arch/arm/mach-msm/include/mach/board.h b/arch/arm/mach-msm/include/mach/board.h
deleted file mode 100644
index c34e246a3e07..000000000000
--- a/arch/arm/mach-msm/include/mach/board.h
+++ /dev/null
@@ -1,38 +0,0 @@
-/* arch/arm/mach-msm/include/mach/board.h
- *
- * Copyright (C) 2007 Google, Inc.
- * Author: Brian Swetland <swetland@google.com>
- *
- * This software is licensed under the terms of the GNU General Public
- * License version 2, as published by the Free Software Foundation, and
- * may be copied, distributed, and modified under those terms.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- */
-
-#ifndef __ASM_ARCH_MSM_BOARD_H
-#define __ASM_ARCH_MSM_BOARD_H
-
-#include <linux/types.h>
-#include <linux/platform_data/mmc-msm_sdcc.h>
-
-/* common init routines for use by arch/arm/mach-msm/board-*.c */
-
-void __init msm_add_devices(void);
-void __init msm_init_irq(void);
-void __init msm_init_gpio(void);
-int __init msm_add_sdcc(unsigned int controller,
-			struct msm_mmc_platform_data *plat,
-			unsigned int stat_irq, unsigned long stat_irq_flags);
-
-#if defined(CONFIG_MSM_SMD) && defined(CONFIG_DEBUG_FS)
-int smd_debugfs_init(void);
-#else
-static inline int smd_debugfs_init(void) { return 0; }
-#endif
-
-#endif
diff --git a/arch/arm/mach-msm/include/mach/msm_iomap-8960.h b/arch/arm/mach-msm/include/mach/msm_iomap-8960.h
deleted file mode 100644
index 7bca8d7108d6..000000000000
--- a/arch/arm/mach-msm/include/mach/msm_iomap-8960.h
+++ /dev/null
@@ -1,46 +0,0 @@
-/*
- * Copyright (C) 2007 Google, Inc.
- * Copyright (c) 2008-2011, Code Aurora Forum. All rights reserved.
- * Author: Brian Swetland <swetland@google.com>
- *
- * This software is licensed under the terms of the GNU General Public
- * License version 2, as published by the Free Software Foundation, and
- * may be copied, distributed, and modified under those terms.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- *
- * The MSM peripherals are spread all over across 768MB of physical
- * space, which makes just having a simple IO_ADDRESS macro to slide
- * them into the right virtual location rough.  Instead, we will
- * provide a master phys->virt mapping for peripherals here.
- *
- */
-
-#ifndef __ASM_ARCH_MSM_IOMAP_8960_H
-#define __ASM_ARCH_MSM_IOMAP_8960_H
-
-/* Physical base address and size of peripherals.
- * Ordered by the virtual base addresses they will be mapped at.
- *
- * If you add or remove entries here, you'll want to edit the
- * msm_io_desc array in arch/arm/mach-msm/io.c to reflect your
- * changes.
- *
- */
-
-#define MSM8960_TMR_PHYS	0x0200A000
-#define MSM8960_TMR_SIZE	SZ_4K
-
-#define MSM8960_TMR0_PHYS	0x0208A000
-#define MSM8960_TMR0_SIZE	SZ_4K
-
-#ifdef CONFIG_DEBUG_MSM8960_UART
-#define MSM_DEBUG_UART_BASE	0xF0040000
-#define MSM_DEBUG_UART_PHYS	0x16440000
-#endif
-
-#endif
diff --git a/arch/arm/mach-msm/include/mach/msm_iomap-8x60.h b/arch/arm/mach-msm/include/mach/msm_iomap-8x60.h
deleted file mode 100644
index 75a7b62c1c74..000000000000
--- a/arch/arm/mach-msm/include/mach/msm_iomap-8x60.h
+++ /dev/null
@@ -1,53 +0,0 @@
-/*
- * Copyright (C) 2007 Google, Inc.
- * Copyright (c) 2008-2011, Code Aurora Forum. All rights reserved.
- * Author: Brian Swetland <swetland@google.com>
- *
- * This software is licensed under the terms of the GNU General Public
- * License version 2, as published by the Free Software Foundation, and
- * may be copied, distributed, and modified under those terms.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- *
- * The MSM peripherals are spread all over across 768MB of physical
- * space, which makes just having a simple IO_ADDRESS macro to slide
- * them into the right virtual location rough.  Instead, we will
- * provide a master phys->virt mapping for peripherals here.
- *
- */
-
-#ifndef __ASM_ARCH_MSM_IOMAP_8X60_H
-#define __ASM_ARCH_MSM_IOMAP_8X60_H
-
-/* Physical base address and size of peripherals.
- * Ordered by the virtual base addresses they will be mapped at.
- *
- * MSM_VIC_BASE must be an value that can be loaded via a "mov"
- * instruction, otherwise entry-macro.S will not compile.
- *
- * If you add or remove entries here, you'll want to edit the
- * msm_io_desc array in arch/arm/mach-msm/io.c to reflect your
- * changes.
- *
- */
-
-#define MSM_TLMM_BASE		IOMEM(0xF0004000)
-#define MSM_TLMM_PHYS		0x00800000
-#define MSM_TLMM_SIZE		SZ_16K
-
-#define MSM8X60_TMR_PHYS	0x02000000
-#define MSM8X60_TMR_SIZE	SZ_4K
-
-#define MSM8X60_TMR0_PHYS	0x02040000
-#define MSM8X60_TMR0_SIZE	SZ_4K
-
-#ifdef CONFIG_DEBUG_MSM8660_UART
-#define MSM_DEBUG_UART_BASE	0xF0040000
-#define MSM_DEBUG_UART_PHYS	0x19C40000
-#endif
-
-#endif
diff --git a/arch/arm/mach-msm/include/mach/msm_iomap.h b/arch/arm/mach-msm/include/mach/msm_iomap.h
index c56e81ffdcde..0e4f49157684 100644
--- a/arch/arm/mach-msm/include/mach/msm_iomap.h
+++ b/arch/arm/mach-msm/include/mach/msm_iomap.h
@@ -45,25 +45,8 @@
 #include "msm_iomap-7x00.h"
 #endif
 
-#include "msm_iomap-8x60.h"
-#include "msm_iomap-8960.h"
-
-#define MSM_DEBUG_UART_SIZE	SZ_4K
-#if defined(CONFIG_DEBUG_MSM_UART1)
-#define MSM_DEBUG_UART_BASE	0xE1000000
-#define MSM_DEBUG_UART_PHYS	MSM_UART1_PHYS
-#elif defined(CONFIG_DEBUG_MSM_UART2)
-#define MSM_DEBUG_UART_BASE	0xE1000000
-#define MSM_DEBUG_UART_PHYS	MSM_UART2_PHYS
-#elif defined(CONFIG_DEBUG_MSM_UART3)
-#define MSM_DEBUG_UART_BASE	0xE1000000
-#define MSM_DEBUG_UART_PHYS	MSM_UART3_PHYS
-#endif
-
 /* Virtual addresses shared across all MSM targets. */
 #define MSM_CSR_BASE		IOMEM(0xE0001000)
-#define MSM_TMR_BASE		IOMEM(0xF0200000)
-#define MSM_TMR0_BASE		IOMEM(0xF0201000)
 #define MSM_GPIO1_BASE		IOMEM(0xE0003000)
 #define MSM_GPIO2_BASE		IOMEM(0xE0004000)
 
diff --git a/arch/arm/mach-msm/include/mach/uncompress.h b/arch/arm/mach-msm/include/mach/uncompress.h
deleted file mode 100644
index 94324870fb04..000000000000
--- a/arch/arm/mach-msm/include/mach/uncompress.h
+++ /dev/null
@@ -1,63 +0,0 @@
-/*
- * Copyright (C) 2007 Google, Inc.
- * Copyright (c) 2011, Code Aurora Forum. All rights reserved.
- *
- * This software is licensed under the terms of the GNU General Public
- * License version 2, as published by the Free Software Foundation, and
- * may be copied, distributed, and modified under those terms.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- */
-
-#ifndef __ASM_ARCH_MSM_UNCOMPRESS_H
-#define __ASM_ARCH_MSM_UNCOMPRESS_H
-
-#include <asm/barrier.h>
-#include <asm/processor.h>
-#include <mach/msm_iomap.h>
-
-#define UART_CSR      (*(volatile uint32_t *)(MSM_DEBUG_UART_PHYS + 0x08))
-#define UART_TF       (*(volatile uint32_t *)(MSM_DEBUG_UART_PHYS + 0x0c))
-
-#define UART_DM_SR    (*((volatile uint32_t *)(MSM_DEBUG_UART_PHYS + 0x08)))
-#define UART_DM_CR    (*((volatile uint32_t *)(MSM_DEBUG_UART_PHYS + 0x10)))
-#define UART_DM_ISR   (*((volatile uint32_t *)(MSM_DEBUG_UART_PHYS + 0x14)))
-#define UART_DM_NCHAR (*((volatile uint32_t *)(MSM_DEBUG_UART_PHYS + 0x40)))
-#define UART_DM_TF    (*((volatile uint32_t *)(MSM_DEBUG_UART_PHYS + 0x70)))
-
-static void putc(int c)
-{
-#if defined(MSM_DEBUG_UART_PHYS)
-#ifdef CONFIG_MSM_HAS_DEBUG_UART_HS
-	/*
-	 * Wait for TX_READY to be set; but skip it if we have a
-	 * TX underrun.
-	 */
-	if (!(UART_DM_SR & 0x08))
-		while (!(UART_DM_ISR & 0x80))
-			cpu_relax();
-
-	UART_DM_CR = 0x300;
-	UART_DM_NCHAR = 0x1;
-	UART_DM_TF = c;
-#else
-	while (!(UART_CSR & 0x04))
-		cpu_relax();
-	UART_TF = c;
-#endif
-#endif
-}
-
-static inline void flush(void)
-{
-}
-
-static inline void arch_decomp_setup(void)
-{
-}
-
-#endif
diff --git a/arch/arm/mach-msm/io.c b/arch/arm/mach-msm/io.c
index 3dc04ccaf59f..adc8971c7266 100644
--- a/arch/arm/mach-msm/io.c
+++ b/arch/arm/mach-msm/io.c
@@ -18,6 +18,7 @@
  */
 
 #include <linux/kernel.h>
+#include <linux/bug.h>
 #include <linux/init.h>
 #include <linux/io.h>
 #include <linux/export.h>
@@ -27,8 +28,6 @@
 #include <mach/msm_iomap.h>
 #include <asm/mach/map.h>
 
-#include <mach/board.h>
-
 #include "common.h"
 
 #define MSM_CHIP_DEVICE_TYPE(name, chip, mem_type) {			      \
@@ -52,26 +51,38 @@ static struct map_desc msm_io_desc[] __initdata = {
 	MSM_CHIP_DEVICE_TYPE(GPIO1, MSM7X00, MT_DEVICE_NONSHARED),
 	MSM_CHIP_DEVICE_TYPE(GPIO2, MSM7X00, MT_DEVICE_NONSHARED),
 	MSM_DEVICE_TYPE(CLK_CTL, MT_DEVICE_NONSHARED),
-#if defined(CONFIG_DEBUG_MSM_UART1) || defined(CONFIG_DEBUG_MSM_UART2) || \
-	defined(CONFIG_DEBUG_MSM_UART3)
-	MSM_DEVICE_TYPE(DEBUG_UART, MT_DEVICE_NONSHARED),
-#endif
 	{
 		.virtual =  (unsigned long) MSM_SHARED_RAM_BASE,
 		.pfn = __phys_to_pfn(MSM_SHARED_RAM_PHYS),
 		.length =   MSM_SHARED_RAM_SIZE,
 		.type =     MT_DEVICE,
 	},
+#if defined(CONFIG_DEBUG_MSM_UART1) || defined(CONFIG_DEBUG_MSM_UART2) || \
+		defined(CONFIG_DEBUG_MSM_UART3)
+	{
+		/* Must be last: virtual and pfn filled in by debug_ll_addr() */
+		.length = SZ_4K,
+		.type = MT_DEVICE_NONSHARED,
+	}
+#endif
 };
 
 void __init msm_map_common_io(void)
 {
+	size_t size = ARRAY_SIZE(msm_io_desc);
+
 	/* Make sure the peripheral register window is closed, since
 	 * we will use PTE flags (TEX[1]=1,B=0,C=1) to determine which
 	 * pages are peripheral interface or not.
 	 */
 	asm("mcr p15, 0, %0, c15, c2, 4" : : "r" (0));
-	iotable_init(msm_io_desc, ARRAY_SIZE(msm_io_desc));
+#if defined(CONFIG_DEBUG_MSM_UART1) || defined(CONFIG_DEBUG_MSM_UART2) || \
+		defined(CONFIG_DEBUG_MSM_UART3)
+	debug_ll_addr(&msm_io_desc[size - 1].pfn,
+		      &msm_io_desc[size - 1].virtual);
+	msm_io_desc[size - 1].pfn = __phys_to_pfn(msm_io_desc[size - 1].pfn);
+#endif
+	iotable_init(msm_io_desc, size);
 }
 #endif
 
@@ -87,10 +98,6 @@ static struct map_desc qsd8x50_io_desc[] __initdata = {
 	MSM_DEVICE(SCPLL),
 	MSM_DEVICE(AD5),
 	MSM_DEVICE(MDC),
-#if defined(CONFIG_DEBUG_MSM_UART1) || defined(CONFIG_DEBUG_MSM_UART2) || \
-	defined(CONFIG_DEBUG_MSM_UART3)
-	MSM_DEVICE(DEBUG_UART),
-#endif
 	{
 		.virtual =  (unsigned long) MSM_SHARED_RAM_BASE,
 		.pfn = __phys_to_pfn(MSM_SHARED_RAM_PHYS),
@@ -101,40 +108,11 @@ static struct map_desc qsd8x50_io_desc[] __initdata = {
 
 void __init msm_map_qsd8x50_io(void)
 {
+	debug_ll_io_init();
 	iotable_init(qsd8x50_io_desc, ARRAY_SIZE(qsd8x50_io_desc));
 }
 #endif /* CONFIG_ARCH_QSD8X50 */
 
-#ifdef CONFIG_ARCH_MSM8X60
-static struct map_desc msm8x60_io_desc[] __initdata = {
-	MSM_CHIP_DEVICE(TMR, MSM8X60),
-	MSM_CHIP_DEVICE(TMR0, MSM8X60),
-#ifdef CONFIG_DEBUG_MSM8660_UART
-	MSM_DEVICE(DEBUG_UART),
-#endif
-};
-
-void __init msm_map_msm8x60_io(void)
-{
-	iotable_init(msm8x60_io_desc, ARRAY_SIZE(msm8x60_io_desc));
-}
-#endif /* CONFIG_ARCH_MSM8X60 */
-
-#ifdef CONFIG_ARCH_MSM8960
-static struct map_desc msm8960_io_desc[] __initdata = {
-	MSM_CHIP_DEVICE(TMR, MSM8960),
-	MSM_CHIP_DEVICE(TMR0, MSM8960),
-#ifdef CONFIG_DEBUG_MSM8960_UART
-	MSM_DEVICE(DEBUG_UART),
-#endif
-};
-
-void __init msm_map_msm8960_io(void)
-{
-	iotable_init(msm8960_io_desc, ARRAY_SIZE(msm8960_io_desc));
-}
-#endif /* CONFIG_ARCH_MSM8960 */
-
 #ifdef CONFIG_ARCH_MSM7X30
 static struct map_desc msm7x30_io_desc[] __initdata = {
 	MSM_DEVICE(VIC),
@@ -150,10 +128,6 @@ static struct map_desc msm7x30_io_desc[] __initdata = {
 	MSM_DEVICE(SAW),
 	MSM_DEVICE(GCC),
 	MSM_DEVICE(TCSR),
-#if defined(CONFIG_DEBUG_MSM_UART1) || defined(CONFIG_DEBUG_MSM_UART2) || \
-	defined(CONFIG_DEBUG_MSM_UART3)
-	MSM_DEVICE(DEBUG_UART),
-#endif
 	{
 		.virtual =  (unsigned long) MSM_SHARED_RAM_BASE,
 		.pfn = __phys_to_pfn(MSM_SHARED_RAM_PHYS),
@@ -164,10 +138,12 @@ static struct map_desc msm7x30_io_desc[] __initdata = {
 
 void __init msm_map_msm7x30_io(void)
 {
+	debug_ll_io_init();
 	iotable_init(msm7x30_io_desc, ARRAY_SIZE(msm7x30_io_desc));
 }
 #endif /* CONFIG_ARCH_MSM7X30 */
 
+#ifdef CONFIG_ARCH_MSM7X00A
 void __iomem *__msm_ioremap_caller(phys_addr_t phys_addr, size_t size,
 				   unsigned int mtype, void *caller)
 {
@@ -182,3 +158,4 @@ void __iomem *__msm_ioremap_caller(phys_addr_t phys_addr, size_t size,
 
 	return __arm_ioremap_caller(phys_addr, size, mtype, caller);
 }
+#endif
diff --git a/arch/arm/mach-msm/timer.c b/arch/arm/mach-msm/timer.c
index 8697cfc0d0b6..696fb73296d0 100644
--- a/arch/arm/mach-msm/timer.c
+++ b/arch/arm/mach-msm/timer.c
@@ -16,6 +16,7 @@
 
 #include <linux/clocksource.h>
 #include <linux/clockchips.h>
+#include <linux/cpu.h>
 #include <linux/init.h>
 #include <linux/interrupt.h>
 #include <linux/irq.h>
@@ -26,7 +27,6 @@
 #include <linux/sched_clock.h>
 
 #include <asm/mach/time.h>
-#include <asm/localtimer.h>
 
 #include "common.h"
 
@@ -49,7 +49,7 @@ static void __iomem *sts_base;
 
 static irqreturn_t msm_timer_interrupt(int irq, void *dev_id)
 {
-	struct clock_event_device *evt = *(struct clock_event_device **)dev_id;
+	struct clock_event_device *evt = dev_id;
 	/* Stop the timer tick */
 	if (evt->mode == CLOCK_EVT_MODE_ONESHOT) {
 		u32 ctrl = readl_relaxed(event_base + TIMER_ENABLE);
@@ -101,18 +101,7 @@ static void msm_timer_set_mode(enum clock_event_mode mode,
 	writel_relaxed(ctrl, event_base + TIMER_ENABLE);
 }
 
-static struct clock_event_device msm_clockevent = {
-	.name		= "gp_timer",
-	.features	= CLOCK_EVT_FEAT_ONESHOT,
-	.rating		= 200,
-	.set_next_event	= msm_timer_set_next_event,
-	.set_mode	= msm_timer_set_mode,
-};
-
-static union {
-	struct clock_event_device *evt;
-	struct clock_event_device * __percpu *percpu_evt;
-} msm_evt;
+static struct clock_event_device __percpu *msm_evt;
 
 static void __iomem *source_base;
 
@@ -138,23 +127,34 @@ static struct clocksource msm_clocksource = {
 	.flags	= CLOCK_SOURCE_IS_CONTINUOUS,
 };
 
-#ifdef CONFIG_LOCAL_TIMERS
+static int msm_timer_irq;
+static int msm_timer_has_ppi;
+
 static int msm_local_timer_setup(struct clock_event_device *evt)
 {
-	/* Use existing clock_event for cpu 0 */
-	if (!smp_processor_id())
-		return 0;
-
-	evt->irq = msm_clockevent.irq;
-	evt->name = "local_timer";
-	evt->features = msm_clockevent.features;
-	evt->rating = msm_clockevent.rating;
+	int cpu = smp_processor_id();
+	int err;
+
+	evt->irq = msm_timer_irq;
+	evt->name = "msm_timer";
+	evt->features = CLOCK_EVT_FEAT_ONESHOT;
+	evt->rating = 200;
 	evt->set_mode = msm_timer_set_mode;
 	evt->set_next_event = msm_timer_set_next_event;
+	evt->cpumask = cpumask_of(cpu);
+
+	clockevents_config_and_register(evt, GPT_HZ, 4, 0xffffffff);
+
+	if (msm_timer_has_ppi) {
+		enable_percpu_irq(evt->irq, IRQ_TYPE_EDGE_RISING);
+	} else {
+		err = request_irq(evt->irq, msm_timer_interrupt,
+				IRQF_TIMER | IRQF_NOBALANCING |
+				IRQF_TRIGGER_RISING, "gp_timer", evt);
+		if (err)
+			pr_err("request_irq failed\n");
+	}
 
-	*__this_cpu_ptr(msm_evt.percpu_evt) = evt;
-	clockevents_config_and_register(evt, GPT_HZ, 4, 0xf0000000);
-	enable_percpu_irq(evt->irq, IRQ_TYPE_EDGE_RISING);
 	return 0;
 }
 
@@ -164,11 +164,28 @@ static void msm_local_timer_stop(struct clock_event_device *evt)
 	disable_percpu_irq(evt->irq);
 }
 
-static struct local_timer_ops msm_local_timer_ops = {
-	.setup	= msm_local_timer_setup,
-	.stop	= msm_local_timer_stop,
+static int msm_timer_cpu_notify(struct notifier_block *self,
+					   unsigned long action, void *hcpu)
+{
+	/*
+	 * Grab cpu pointer in each case to avoid spurious
+	 * preemptible warnings
+	 */
+	switch (action & ~CPU_TASKS_FROZEN) {
+	case CPU_STARTING:
+		msm_local_timer_setup(this_cpu_ptr(msm_evt));
+		break;
+	case CPU_DYING:
+		msm_local_timer_stop(this_cpu_ptr(msm_evt));
+		break;
+	}
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block msm_timer_cpu_nb = {
+	.notifier_call = msm_timer_cpu_notify,
 };
-#endif /* CONFIG_LOCAL_TIMERS */
 
 static notrace u32 msm_sched_clock_read(void)
 {
@@ -178,38 +195,35 @@ static notrace u32 msm_sched_clock_read(void)
 static void __init msm_timer_init(u32 dgt_hz, int sched_bits, int irq,
 				  bool percpu)
 {
-	struct clock_event_device *ce = &msm_clockevent;
 	struct clocksource *cs = &msm_clocksource;
-	int res;
+	int res = 0;
+
+	msm_timer_irq = irq;
+	msm_timer_has_ppi = percpu;
+
+	msm_evt = alloc_percpu(struct clock_event_device);
+	if (!msm_evt) {
+		pr_err("memory allocation failed for clockevents\n");
+		goto err;
+	}
 
-	ce->cpumask = cpumask_of(0);
-	ce->irq = irq;
+	if (percpu)
+		res = request_percpu_irq(irq, msm_timer_interrupt,
+					 "gp_timer", msm_evt);
 
-	clockevents_config_and_register(ce, GPT_HZ, 4, 0xffffffff);
-	if (percpu) {
-		msm_evt.percpu_evt = alloc_percpu(struct clock_event_device *);
-		if (!msm_evt.percpu_evt) {
-			pr_err("memory allocation failed for %s\n", ce->name);
+	if (res) {
+		pr_err("request_percpu_irq failed\n");
+	} else {
+		res = register_cpu_notifier(&msm_timer_cpu_nb);
+		if (res) {
+			free_percpu_irq(irq, msm_evt);
 			goto err;
 		}
-		*__this_cpu_ptr(msm_evt.percpu_evt) = ce;
-		res = request_percpu_irq(ce->irq, msm_timer_interrupt,
-					 ce->name, msm_evt.percpu_evt);
-		if (!res) {
-			enable_percpu_irq(ce->irq, IRQ_TYPE_EDGE_RISING);
-#ifdef CONFIG_LOCAL_TIMERS
-			local_timer_register(&msm_local_timer_ops);
-#endif
-		}
-	} else {
-		msm_evt.evt = ce;
-		res = request_irq(ce->irq, msm_timer_interrupt,
-				  IRQF_TIMER | IRQF_NOBALANCING |
-				  IRQF_TRIGGER_RISING, ce->name, &msm_evt.evt);
+
+		/* Immediately configure the timer on the boot CPU */
+		msm_local_timer_setup(__this_cpu_ptr(msm_evt));
 	}
 
-	if (res)
-		pr_err("request_irq failed for %s\n", ce->name);
 err:
 	writel_relaxed(TIMER_ENABLE_EN, source_base + TIMER_ENABLE);
 	res = clocksource_register_hz(cs, dgt_hz);
@@ -219,15 +233,8 @@ err:
 }
 
 #ifdef CONFIG_OF
-static const struct of_device_id msm_timer_match[] __initconst = {
-	{ .compatible = "qcom,kpss-timer" },
-	{ .compatible = "qcom,scss-timer" },
-	{ },
-};
-
-void __init msm_dt_timer_init(void)
+static void __init msm_dt_timer_init(struct device_node *np)
 {
-	struct device_node *np;
 	u32 freq;
 	int irq;
 	struct resource res;
@@ -235,12 +242,6 @@ void __init msm_dt_timer_init(void)
 	void __iomem *base;
 	void __iomem *cpu0_base;
 
-	np = of_find_matching_node(NULL, msm_timer_match);
-	if (!np) {
-		pr_err("Can't find msm timer DT node\n");
-		return;
-	}
-
 	base = of_iomap(np, 0);
 	if (!base) {
 		pr_err("Failed to map event base\n");
@@ -283,6 +284,8 @@ void __init msm_dt_timer_init(void)
 
 	msm_timer_init(freq, 32, irq, !!percpu_offset);
 }
+CLOCKSOURCE_OF_DECLARE(kpss_timer, "qcom,kpss-timer", msm_dt_timer_init);
+CLOCKSOURCE_OF_DECLARE(scss_timer, "qcom,scss-timer", msm_dt_timer_init);
 #endif
 
 static int __init msm_timer_map(phys_addr_t addr, u32 event, u32 source,
diff --git a/arch/arm/mach-mv78xx0/include/mach/debug-macro.S b/arch/arm/mach-mv78xx0/include/mach/debug-macro.S
deleted file mode 100644
index a7df02b049b7..000000000000
--- a/arch/arm/mach-mv78xx0/include/mach/debug-macro.S
+++ /dev/null
@@ -1,19 +0,0 @@
-/*
- * arch/arm/mach-mv78xx0/include/mach/debug-macro.S
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
-
-#include <mach/mv78xx0.h>
-
-	.macro	addruart, rp, rv, tmp
-	ldr	\rp, =MV78XX0_REGS_PHYS_BASE
-	ldr	\rv, =MV78XX0_REGS_VIRT_BASE
-	orr	\rp, \rp, #0x00012000
-	orr	\rv, \rv, #0x00012000
-	.endm
-
-#define UART_SHIFT	2
-#include <asm/hardware/debug-8250.S>
diff --git a/arch/arm/mach-mv78xx0/pcie.c b/arch/arm/mach-mv78xx0/pcie.c
index dc26a654c496..445e553f4a28 100644
--- a/arch/arm/mach-mv78xx0/pcie.c
+++ b/arch/arm/mach-mv78xx0/pcie.c
@@ -18,6 +18,11 @@
 #include <mach/mv78xx0.h>
 #include "common.h"
 
+#define MV78XX0_MBUS_PCIE_MEM_TARGET(port, lane) ((port) ? 8 : 4)
+#define MV78XX0_MBUS_PCIE_MEM_ATTR(port, lane)   (0xf8 & ~(0x10 << (lane)))
+#define MV78XX0_MBUS_PCIE_IO_TARGET(port, lane)  ((port) ? 8 : 4)
+#define MV78XX0_MBUS_PCIE_IO_ATTR(port, lane)    (0xf0 & ~(0x10 << (lane)))
+
 struct pcie_port {
 	u8			maj;
 	u8			min;
@@ -71,7 +76,6 @@ static void __init mv78xx0_pcie_preinit(void)
 	start = MV78XX0_PCIE_MEM_PHYS_BASE;
 	for (i = 0; i < num_pcie_ports; i++) {
 		struct pcie_port *pp = pcie_port + i;
-		char winname[MVEBU_MBUS_MAX_WINNAME_SZ];
 
 		snprintf(pp->mem_space_name, sizeof(pp->mem_space_name),
 			"PCIe %d.%d MEM", pp->maj, pp->min);
@@ -85,17 +89,12 @@ static void __init mv78xx0_pcie_preinit(void)
 		if (request_resource(&iomem_resource, &pp->res))
 			panic("can't allocate PCIe MEM sub-space");
 
-		snprintf(winname, sizeof(winname), "pcie%d.%d",
-			 pp->maj, pp->min);
-
-		mvebu_mbus_add_window_remap_flags(winname,
-						  pp->res.start,
-						  resource_size(&pp->res),
-						  MVEBU_MBUS_NO_REMAP,
-						  MVEBU_MBUS_PCI_MEM);
-		mvebu_mbus_add_window_remap_flags(winname,
-						  i * SZ_64K, SZ_64K,
-						  0, MVEBU_MBUS_PCI_IO);
+		mvebu_mbus_add_window_by_id(MV78XX0_MBUS_PCIE_MEM_TARGET(pp->maj, pp->min),
+					    MV78XX0_MBUS_PCIE_MEM_ATTR(pp->maj, pp->min),
+					    pp->res.start, resource_size(&pp->res));
+		mvebu_mbus_add_window_remap_by_id(MV78XX0_MBUS_PCIE_IO_TARGET(pp->maj, pp->min),
+						  MV78XX0_MBUS_PCIE_IO_ATTR(pp->maj, pp->min),
+						  i * SZ_64K, SZ_64K, 0);
 	}
 }
 
diff --git a/arch/arm/mach-mvebu/armada-370-xp.c b/arch/arm/mach-mvebu/armada-370-xp.c
index 97cbb8021919..e2acff98e750 100644
--- a/arch/arm/mach-mvebu/armada-370-xp.c
+++ b/arch/arm/mach-mvebu/armada-370-xp.c
@@ -18,7 +18,7 @@
 #include <linux/of_address.h>
 #include <linux/of_platform.h>
 #include <linux/io.h>
-#include <linux/time-armada-370-xp.h>
+#include <linux/clocksource.h>
 #include <linux/dma-mapping.h>
 #include <linux/mbus.h>
 #include <asm/hardware/cache-l2x0.h>
@@ -34,44 +34,12 @@ static void __init armada_370_xp_map_io(void)
 	debug_ll_io_init();
 }
 
-/*
- * This initialization will be replaced by a DT-based
- * initialization once the mvebu-mbus driver gains DT support.
- */
-
-#define ARMADA_370_XP_MBUS_WINS_OFFS   0x20000
-#define ARMADA_370_XP_MBUS_WINS_SIZE   0x100
-#define ARMADA_370_XP_SDRAM_WINS_OFFS  0x20180
-#define ARMADA_370_XP_SDRAM_WINS_SIZE  0x20
-
-static void __init armada_370_xp_mbus_init(void)
-{
-	char *mbus_soc_name;
-	struct device_node *dn;
-	const __be32 mbus_wins_offs = cpu_to_be32(ARMADA_370_XP_MBUS_WINS_OFFS);
-	const __be32 sdram_wins_offs = cpu_to_be32(ARMADA_370_XP_SDRAM_WINS_OFFS);
-
-	if (of_machine_is_compatible("marvell,armada370"))
-		mbus_soc_name = "marvell,armada370-mbus";
-	else
-		mbus_soc_name = "marvell,armadaxp-mbus";
-
-	dn = of_find_node_by_name(NULL, "internal-regs");
-	BUG_ON(!dn);
-
-	mvebu_mbus_init(mbus_soc_name,
-			of_translate_address(dn, &mbus_wins_offs),
-			ARMADA_370_XP_MBUS_WINS_SIZE,
-			of_translate_address(dn, &sdram_wins_offs),
-			ARMADA_370_XP_SDRAM_WINS_SIZE);
-}
-
 static void __init armada_370_xp_timer_and_clk_init(void)
 {
 	of_clk_init(NULL);
-	armada_370_xp_timer_init();
+	clocksource_of_init();
 	coherency_init();
-	armada_370_xp_mbus_init();
+	BUG_ON(mvebu_mbus_dt_init());
 #ifdef CONFIG_CACHE_L2X0
 	l2x0_of_init(0, ~0UL);
 #endif
diff --git a/arch/arm/mach-mvebu/coherency.c b/arch/arm/mach-mvebu/coherency.c
index 4c24303ec481..58adf2fd9cfc 100644
--- a/arch/arm/mach-mvebu/coherency.c
+++ b/arch/arm/mach-mvebu/coherency.c
@@ -140,6 +140,7 @@ int __init coherency_init(void)
 		coherency_base = of_iomap(np, 0);
 		coherency_cpu_base = of_iomap(np, 1);
 		set_cpu_coherent(cpu_logical_map(smp_processor_id()), 0);
+		of_node_put(np);
 	}
 
 	return 0;
@@ -147,9 +148,14 @@ int __init coherency_init(void)
 
 static int __init coherency_late_init(void)
 {
-	if (of_find_matching_node(NULL, of_coherency_table))
+	struct device_node *np;
+
+	np = of_find_matching_node(NULL, of_coherency_table);
+	if (np) {
 		bus_register_notifier(&platform_bus_type,
 				      &mvebu_hwcc_platform_nb);
+		of_node_put(np);
+	}
 	return 0;
 }
 
diff --git a/arch/arm/mach-mvebu/platsmp.c b/arch/arm/mach-mvebu/platsmp.c
index ce81d3031405..ff69c2df298b 100644
--- a/arch/arm/mach-mvebu/platsmp.c
+++ b/arch/arm/mach-mvebu/platsmp.c
@@ -21,6 +21,7 @@
 #include <linux/smp.h>
 #include <linux/clk.h>
 #include <linux/of.h>
+#include <linux/of_address.h>
 #include <linux/mbus.h>
 #include <asm/cacheflush.h>
 #include <asm/smp_plat.h>
@@ -29,45 +30,43 @@
 #include "pmsu.h"
 #include "coherency.h"
 
+#define AXP_BOOTROM_BASE 0xfff00000
+#define AXP_BOOTROM_SIZE 0x100000
+
+static struct clk *__init get_cpu_clk(int cpu)
+{
+	struct clk *cpu_clk;
+	struct device_node *np = of_get_cpu_node(cpu, NULL);
+
+	if (WARN(!np, "missing cpu node\n"))
+		return NULL;
+	cpu_clk = of_clk_get(np, 0);
+	if (WARN_ON(IS_ERR(cpu_clk)))
+		return NULL;
+	return cpu_clk;
+}
+
 void __init set_secondary_cpus_clock(void)
 {
-	int thiscpu;
+	int thiscpu, cpu;
 	unsigned long rate;
-	struct clk *cpu_clk = NULL;
-	struct device_node *np = NULL;
+	struct clk *cpu_clk;
 
 	thiscpu = smp_processor_id();
-	for_each_node_by_type(np, "cpu") {
-		int err;
-		int cpu;
-
-		err = of_property_read_u32(np, "reg", &cpu);
-		if (WARN_ON(err))
-			return;
-
-		if (cpu == thiscpu) {
-			cpu_clk = of_clk_get(np, 0);
-			break;
-		}
-	}
-	if (WARN_ON(IS_ERR(cpu_clk)))
+	cpu_clk = get_cpu_clk(thiscpu);
+	if (!cpu_clk)
 		return;
 	clk_prepare_enable(cpu_clk);
 	rate = clk_get_rate(cpu_clk);
 
 	/* set all the other CPU clk to the same rate than the boot CPU */
-	for_each_node_by_type(np, "cpu") {
-		int err;
-		int cpu;
-
-		err = of_property_read_u32(np, "reg", &cpu);
-		if (WARN_ON(err))
+	for_each_possible_cpu(cpu) {
+		if (cpu == thiscpu)
+			continue;
+		cpu_clk = get_cpu_clk(cpu);
+		if (!cpu_clk)
 			return;
-
-		if (cpu != thiscpu) {
-			cpu_clk = of_clk_get(np, 0);
-			clk_set_rate(cpu_clk, rate);
-		}
+		clk_set_rate(cpu_clk, rate);
 	}
 }
 
@@ -87,37 +86,39 @@ static int armada_xp_boot_secondary(unsigned int cpu, struct task_struct *idle)
 
 static void __init armada_xp_smp_init_cpus(void)
 {
-	struct device_node *np;
-	unsigned int i, ncores;
+	unsigned int ncores = num_possible_cpus();
 
-	np = of_find_node_by_name(NULL, "cpus");
-	if (!np)
-		panic("No 'cpus' node found\n");
-
-	ncores = of_get_child_count(np);
 	if (ncores == 0 || ncores > ARMADA_XP_MAX_CPUS)
 		panic("Invalid number of CPUs in DT\n");
 
-	/* Limit possible CPUs to defconfig */
-	if (ncores > nr_cpu_ids) {
-		pr_warn("SMP: %d CPUs physically present. Only %d configured.",
-			ncores, nr_cpu_ids);
-		pr_warn("Clipping CPU count to %d\n", nr_cpu_ids);
-		ncores = nr_cpu_ids;
-	}
-
-	for (i = 0; i < ncores; i++)
-		set_cpu_possible(i, true);
-
 	set_smp_cross_call(armada_mpic_send_doorbell);
 }
 
 void __init armada_xp_smp_prepare_cpus(unsigned int max_cpus)
 {
+	struct device_node *node;
+	struct resource res;
+	int err;
+
 	set_secondary_cpus_clock();
 	flush_cache_all();
 	set_cpu_coherent(cpu_logical_map(smp_processor_id()), 0);
-	mvebu_mbus_add_window("bootrom", 0xfff00000, SZ_1M);
+
+	/*
+	 * In order to boot the secondary CPUs we need to ensure
+	 * the bootROM is mapped at the correct address.
+	 */
+	node = of_find_compatible_node(NULL, NULL, "marvell,bootrom");
+	if (!node)
+		panic("Cannot find 'marvell,bootrom' compatible node");
+
+	err = of_address_to_resource(node, 0, &res);
+	if (err < 0)
+		panic("Cannot get 'bootrom' node address");
+
+	if (res.start != AXP_BOOTROM_BASE ||
+	    resource_size(&res) != AXP_BOOTROM_SIZE)
+		panic("The address for the BootROM is incorrect");
 }
 
 struct smp_operations armada_xp_smp_ops __initdata = {
diff --git a/arch/arm/mach-mvebu/pmsu.c b/arch/arm/mach-mvebu/pmsu.c
index 3cc4bef6401c..27fc4f049474 100644
--- a/arch/arm/mach-mvebu/pmsu.c
+++ b/arch/arm/mach-mvebu/pmsu.c
@@ -67,6 +67,7 @@ int __init armada_370_xp_pmsu_init(void)
 		pr_info("Initializing Power Management Service Unit\n");
 		pmsu_mp_base = of_iomap(np, 0);
 		pmsu_reset_base = of_iomap(np, 1);
+		of_node_put(np);
 	}
 
 	return 0;
diff --git a/arch/arm/mach-mvebu/system-controller.c b/arch/arm/mach-mvebu/system-controller.c
index f875124ff4f9..5175083cdb34 100644
--- a/arch/arm/mach-mvebu/system-controller.c
+++ b/arch/arm/mach-mvebu/system-controller.c
@@ -98,6 +98,7 @@ static int __init mvebu_system_controller_init(void)
 		BUG_ON(!match);
 		system_controller_base = of_iomap(np, 0);
 		mvebu_sc = (struct mvebu_system_controller *)match->data;
+		of_node_put(np);
 	}
 
 	return 0;
diff --git a/arch/arm/mach-mxs/mach-mxs.c b/arch/arm/mach-mxs/mach-mxs.c
index 4ce27b536dc9..98f6e2adb53e 100644
--- a/arch/arm/mach-mxs/mach-mxs.c
+++ b/arch/arm/mach-mxs/mach-mxs.c
@@ -14,6 +14,7 @@
 #include <linux/clk/mxs.h>
 #include <linux/clkdev.h>
 #include <linux/clocksource.h>
+#include <linux/clk-provider.h>
 #include <linux/delay.h>
 #include <linux/err.h>
 #include <linux/gpio.h>
@@ -61,6 +62,8 @@
 static u32 chipid;
 static u32 socid;
 
+static void __iomem *reset_addr;
+
 static inline void __mxs_setl(u32 mask, void __iomem *reg)
 {
 	__raw_writel(mask, reg + MXS_SET_ADDR);
@@ -393,12 +396,33 @@ static const char __init *mxs_get_revision(void)
 	u32 rev = mxs_get_cpu_rev();
 
 	if (rev != MXS_CHIP_REV_UNKNOWN)
-		return kasprintf(GFP_KERNEL, "TO%d.%d", (rev >> 4) & 0xf,
+		return kasprintf(GFP_KERNEL, "%d.%d", (rev >> 4) & 0xf,
 				rev & 0xf);
 	else
 		return kasprintf(GFP_KERNEL, "%s", "Unknown");
 }
 
+#define MX23_CLKCTRL_RESET_OFFSET	0x120
+#define MX28_CLKCTRL_RESET_OFFSET	0x1e0
+
+static int __init mxs_restart_init(void)
+{
+	struct device_node *np;
+
+	np = of_find_compatible_node(NULL, NULL, "fsl,clkctrl");
+	reset_addr = of_iomap(np, 0);
+	if (!reset_addr)
+		return -ENODEV;
+
+	if (of_device_is_compatible(np, "fsl,imx23-clkctrl"))
+		reset_addr += MX23_CLKCTRL_RESET_OFFSET;
+	else
+		reset_addr += MX28_CLKCTRL_RESET_OFFSET;
+	of_node_put(np);
+
+	return 0;
+}
+
 static void __init mxs_machine_init(void)
 {
 	struct device_node *root;
@@ -433,21 +457,18 @@ static void __init mxs_machine_init(void)
 		imx28_evk_init();
 	else if (of_machine_is_compatible("bluegiga,apx4devkit"))
 		apx4devkit_init();
-	else if (of_machine_is_compatible("crystalfontz,cfa10037") ||
-		 of_machine_is_compatible("crystalfontz,cfa10049") ||
-		 of_machine_is_compatible("crystalfontz,cfa10055") ||
-		 of_machine_is_compatible("crystalfontz,cfa10057"))
+	else if (of_machine_is_compatible("crystalfontz,cfa10036"))
 		crystalfontz_init();
 
 	of_platform_populate(NULL, of_default_bus_match_table,
 			     NULL, parent);
 
+	mxs_restart_init();
+
 	if (of_machine_is_compatible("karo,tx28"))
 		tx28_post_init();
 }
 
-#define MX23_CLKCTRL_RESET_OFFSET	0x120
-#define MX28_CLKCTRL_RESET_OFFSET	0x1e0
 #define MXS_CLKCTRL_RESET_CHIP		(1 << 1)
 
 /*
@@ -455,28 +476,16 @@ static void __init mxs_machine_init(void)
  */
 static void mxs_restart(enum reboot_mode mode, const char *cmd)
 {
-	struct device_node *np;
-	void __iomem *reset_addr;
+	if (reset_addr) {
+		/* reset the chip */
+		__mxs_setl(MXS_CLKCTRL_RESET_CHIP, reset_addr);
 
-	np = of_find_compatible_node(NULL, NULL, "fsl,clkctrl");
-	reset_addr = of_iomap(np, 0);
-	if (!reset_addr)
-		goto soft;
+		pr_err("Failed to assert the chip reset\n");
 
-	if (of_device_is_compatible(np, "fsl,imx23-clkctrl"))
-		reset_addr += MX23_CLKCTRL_RESET_OFFSET;
-	else
-		reset_addr += MX28_CLKCTRL_RESET_OFFSET;
-
-	/* reset the chip */
-	__mxs_setl(MXS_CLKCTRL_RESET_CHIP, reset_addr);
-
-	pr_err("Failed to assert the chip reset\n");
-
-	/* Delay to allow the serial port to show the message */
-	mdelay(50);
+		/* Delay to allow the serial port to show the message */
+		mdelay(50);
+	}
 
-soft:
 	/* We'll take a jump through zero as a poor second */
 	soft_restart(0);
 }
@@ -487,6 +496,7 @@ static void __init mxs_timer_init(void)
 		mx23_clocks_init();
 	else
 		mx28_clocks_init();
+	of_clk_init(NULL);
 	clocksource_of_init();
 }
 
diff --git a/arch/arm/mach-mxs/pm.c b/arch/arm/mach-mxs/pm.c
index b2494d2db2c4..0170e99fd70f 100644
--- a/arch/arm/mach-mxs/pm.c
+++ b/arch/arm/mach-mxs/pm.c
@@ -15,6 +15,7 @@
 #include <linux/kernel.h>
 #include <linux/suspend.h>
 #include <linux/io.h>
+#include "pm.h"
 
 static int mxs_suspend_enter(suspend_state_t state)
 {
diff --git a/arch/arm/mach-nomadik/Kconfig b/arch/arm/mach-nomadik/Kconfig
index 5981c3db9b41..4d42da49753c 100644
--- a/arch/arm/mach-nomadik/Kconfig
+++ b/arch/arm/mach-nomadik/Kconfig
@@ -27,6 +27,7 @@ config MACH_NOMADIK_8815NHK
 	select NOMADIK_8815
 	select I2C
 	select I2C_ALGOBIT
+	select I2C_NOMADIK
 
 endmenu
 endif
diff --git a/arch/arm/mach-omap1/include/mach/soc.h b/arch/arm/mach-omap1/include/mach/soc.h
index 6cf9c1cc2bef..612bd1cc257c 100644
--- a/arch/arm/mach-omap1/include/mach/soc.h
+++ b/arch/arm/mach-omap1/include/mach/soc.h
@@ -195,6 +195,7 @@ IS_OMAP_TYPE(1710, 0x1710)
 #define cpu_is_omap34xx()		0
 #define cpu_is_omap44xx()		0
 #define soc_is_omap54xx()		0
+#define soc_is_dra7xx()			0
 #define soc_is_am33xx()			0
 #define cpu_class_is_omap1()		1
 #define cpu_class_is_omap2()		0
diff --git a/arch/arm/mach-omap2/Kconfig b/arch/arm/mach-omap2/Kconfig
index 3eed0006d189..b5fb5f7992df 100644
--- a/arch/arm/mach-omap2/Kconfig
+++ b/arch/arm/mach-omap2/Kconfig
@@ -37,9 +37,8 @@ config ARCH_OMAP4
 	select CACHE_L2X0
 	select CPU_V7
 	select HAVE_ARM_SCU if SMP
-	select HAVE_ARM_TWD if LOCAL_TIMERS
+	select HAVE_ARM_TWD if SMP
 	select HAVE_SMP
-	select LOCAL_TIMERS if SMP
 	select OMAP_INTERCONNECT
 	select PL310_ERRATA_588369
 	select PL310_ERRATA_727915
@@ -65,7 +64,7 @@ config SOC_OMAP5
 	select ARM_ERRATA_798181 if SMP
 
 config SOC_AM33XX
-	bool "AM33XX support"
+	bool "TI AM33XX"
 	depends on ARCH_MULTI_V7
 	select ARCH_OMAP2PLUS
 	select ARM_CPU_SUSPEND if PM
@@ -118,7 +117,7 @@ config ARCH_OMAP2PLUS_TYPICAL
 	select I2C
 	select I2C_OMAP
 	select MENELAUS if ARCH_OMAP2
-	select NEON if ARCH_OMAP3 || ARCH_OMAP4 || SOC_OMAP5
+	select NEON if CPU_V7
 	select PM_RUNTIME
 	select REGULATOR
 	select TWL4030_CORE if ARCH_OMAP3 || ARCH_OMAP4
@@ -132,9 +131,17 @@ config SOC_HAS_OMAP2_SDRC
 
 config SOC_HAS_REALTIME_COUNTER
 	bool "Real time free running counter"
-	depends on SOC_OMAP5
+	depends on SOC_OMAP5 || SOC_DRA7XX
 	default y
 
+config SOC_DRA7XX
+	bool "TI DRA7XX"
+	select ARM_ARCH_TIMER
+	select CPU_V7
+	select ARM_GIC
+	select HAVE_SMP
+	select COMMON_CLK
+
 comment "OMAP Core Type"
 	depends on ARCH_OMAP2
 
diff --git a/arch/arm/mach-omap2/Makefile b/arch/arm/mach-omap2/Makefile
index d4f671547c37..afb457c3135b 100644
--- a/arch/arm/mach-omap2/Makefile
+++ b/arch/arm/mach-omap2/Makefile
@@ -23,6 +23,7 @@ obj-$(CONFIG_ARCH_OMAP4) += prm44xx.o $(hwmod-common) $(secure-common)
 obj-$(CONFIG_SOC_AM33XX) += irq.o $(hwmod-common)
 obj-$(CONFIG_SOC_OMAP5)	 += prm44xx.o $(hwmod-common) $(secure-common)
 obj-$(CONFIG_SOC_AM43XX) += $(hwmod-common) $(secure-common)
+obj-$(CONFIG_SOC_DRA7XX) += prm44xx.o $(hwmod-common) $(secure-common)
 
 ifneq ($(CONFIG_SND_OMAP_SOC_MCBSP),)
 obj-y += mcbsp.o
@@ -39,6 +40,7 @@ omap-4-5-common				=  omap4-common.o omap-wakeupgen.o
 obj-$(CONFIG_ARCH_OMAP4)		+= $(omap-4-5-common) $(smp-y) sleep44xx.o
 obj-$(CONFIG_SOC_OMAP5)			+= $(omap-4-5-common) $(smp-y) sleep44xx.o
 obj-$(CONFIG_SOC_AM43XX)		+= $(omap-4-5-common)
+obj-$(CONFIG_SOC_DRA7XX)		+= $(omap-4-5-common) $(smp-y)
 
 plus_sec := $(call as-instr,.arch_extension sec,+sec)
 AFLAGS_omap-headsmp.o			:=-Wa,-march=armv7-a$(plus_sec)
@@ -61,6 +63,7 @@ obj-$(CONFIG_SOC_AM33XX)		+= am33xx-restart.o
 obj-$(CONFIG_ARCH_OMAP3)		+= omap3-restart.o
 obj-$(CONFIG_ARCH_OMAP4)		+= omap4-restart.o
 obj-$(CONFIG_SOC_OMAP5)			+= omap4-restart.o
+obj-$(CONFIG_SOC_DRA7XX)		+= omap4-restart.o
 
 # Pin multiplexing
 obj-$(CONFIG_SOC_OMAP2420)		+= mux2420.o
@@ -87,6 +90,7 @@ obj-$(CONFIG_ARCH_OMAP2)		+= sleep24xx.o
 obj-$(CONFIG_ARCH_OMAP3)		+= pm34xx.o sleep34xx.o
 obj-$(CONFIG_ARCH_OMAP4)		+= pm44xx.o omap-mpuss-lowpower.o
 obj-$(CONFIG_SOC_OMAP5)			+= omap-mpuss-lowpower.o
+obj-$(CONFIG_SOC_DRA7XX)		+= omap-mpuss-lowpower.o
 obj-$(CONFIG_PM_DEBUG)			+= pm-debug.o
 
 obj-$(CONFIG_POWER_AVS_OMAP)		+= sr_device.o
@@ -114,6 +118,7 @@ omap-prcm-4-5-common			=  cminst44xx.o cm44xx.o prm44xx.o \
 					   vc44xx_data.o vp44xx_data.o
 obj-$(CONFIG_ARCH_OMAP4)		+= $(omap-prcm-4-5-common)
 obj-$(CONFIG_SOC_OMAP5)			+= $(omap-prcm-4-5-common)
+obj-$(CONFIG_SOC_DRA7XX)		+= $(omap-prcm-4-5-common)
 
 # OMAP voltage domains
 voltagedomain-common			:= voltage.o vc.o vp.o
@@ -143,6 +148,8 @@ obj-$(CONFIG_SOC_AM33XX)		+= powerdomains33xx_data.o
 obj-$(CONFIG_SOC_AM43XX)		+= $(powerdomain-common)
 obj-$(CONFIG_SOC_OMAP5)			+= $(powerdomain-common)
 obj-$(CONFIG_SOC_OMAP5)			+= powerdomains54xx_data.o
+obj-$(CONFIG_SOC_DRA7XX)		+= $(powerdomain-common)
+obj-$(CONFIG_SOC_DRA7XX)		+= powerdomains7xx_data.o
 
 # PRCM clockdomain control
 clockdomain-common			+= clockdomain.o
@@ -160,6 +167,8 @@ obj-$(CONFIG_SOC_AM33XX)		+= clockdomains33xx_data.o
 obj-$(CONFIG_SOC_AM43XX)		+= $(clockdomain-common)
 obj-$(CONFIG_SOC_OMAP5)			+= $(clockdomain-common)
 obj-$(CONFIG_SOC_OMAP5)			+= clockdomains54xx_data.o
+obj-$(CONFIG_SOC_DRA7XX)		+= $(clockdomain-common)
+obj-$(CONFIG_SOC_DRA7XX)		+= clockdomains7xx_data.o
 
 # Clock framework
 obj-$(CONFIG_ARCH_OMAP2)		+= $(clock-common) clock2xxx.o
@@ -203,6 +212,7 @@ obj-$(CONFIG_ARCH_OMAP3)		+= omap_hwmod_3xxx_data.o
 obj-$(CONFIG_SOC_AM33XX)		+= omap_hwmod_33xx_data.o
 obj-$(CONFIG_ARCH_OMAP4)		+= omap_hwmod_44xx_data.o
 obj-$(CONFIG_SOC_OMAP5)			+= omap_hwmod_54xx_data.o
+obj-$(CONFIG_SOC_DRA7XX)		+= omap_hwmod_7xx_data.o
 
 # EMU peripherals
 obj-$(CONFIG_OMAP3_EMU)			+= emu.o
diff --git a/arch/arm/mach-omap2/am33xx-restart.c b/arch/arm/mach-omap2/am33xx-restart.c
index 1eae96212315..c88d8df753c2 100644
--- a/arch/arm/mach-omap2/am33xx-restart.c
+++ b/arch/arm/mach-omap2/am33xx-restart.c
@@ -24,8 +24,8 @@ void am33xx_restart(enum reboot_mode mode, const char *cmd)
 {
 	/* TODO: Handle mode and cmd if necessary */
 
-	am33xx_prm_rmw_reg_bits(AM33XX_GLOBAL_WARM_SW_RST_MASK,
-				AM33XX_GLOBAL_WARM_SW_RST_MASK,
+	am33xx_prm_rmw_reg_bits(AM33XX_RST_GLOBAL_WARM_SW_MASK,
+				AM33XX_RST_GLOBAL_WARM_SW_MASK,
 				AM33XX_PRM_DEVICE_MOD,
 				AM33XX_PRM_RSTCTRL_OFFSET);
 
diff --git a/arch/arm/mach-omap2/board-2430sdp.c b/arch/arm/mach-omap2/board-2430sdp.c
index 244d8a5aa54b..c711ad6ac067 100644
--- a/arch/arm/mach-omap2/board-2430sdp.c
+++ b/arch/arm/mach-omap2/board-2430sdp.c
@@ -100,39 +100,52 @@ static struct platform_device sdp2430_flash_device = {
 	.resource	= &sdp2430_flash_resource,
 };
 
-static struct platform_device *sdp2430_devices[] __initdata = {
-	&sdp2430_flash_device,
-};
-
 /* LCD */
 #define SDP2430_LCD_PANEL_BACKLIGHT_GPIO	91
 #define SDP2430_LCD_PANEL_ENABLE_GPIO		154
 
-static struct panel_generic_dpi_data sdp2430_panel_data = {
-	.name			= "nec_nl2432dr22-11b",
-	.num_gpios		= 2,
-	.gpios			= {
-		SDP2430_LCD_PANEL_ENABLE_GPIO,
-		SDP2430_LCD_PANEL_BACKLIGHT_GPIO,
-	},
+static const struct display_timing sdp2430_lcd_videomode = {
+	.pixelclock	= { 0, 5400000, 0 },
+
+	.hactive = { 0, 240, 0 },
+	.hfront_porch = { 0, 3, 0 },
+	.hback_porch = { 0, 39, 0 },
+	.hsync_len = { 0, 3, 0 },
+
+	.vactive = { 0, 320, 0 },
+	.vfront_porch = { 0, 2, 0 },
+	.vback_porch = { 0, 7, 0 },
+	.vsync_len = { 0, 1, 0 },
+
+	.flags = DISPLAY_FLAGS_HSYNC_LOW | DISPLAY_FLAGS_VSYNC_LOW |
+		DISPLAY_FLAGS_DE_HIGH | DISPLAY_FLAGS_PIXDATA_POSEDGE,
 };
 
-static struct omap_dss_device sdp2430_lcd_device = {
-	.name			= "lcd",
-	.driver_name		= "generic_dpi_panel",
-	.type			= OMAP_DISPLAY_TYPE_DPI,
-	.phy.dpi.data_lines	= 16,
-	.data			= &sdp2430_panel_data,
+static struct panel_dpi_platform_data sdp2430_lcd_pdata = {
+	.name                   = "lcd",
+	.source                 = "dpi.0",
+
+	.data_lines		= 16,
+
+	.display_timing		= &sdp2430_lcd_videomode,
+
+	.enable_gpio		= SDP2430_LCD_PANEL_ENABLE_GPIO,
+	.backlight_gpio		= SDP2430_LCD_PANEL_BACKLIGHT_GPIO,
 };
 
-static struct omap_dss_device *sdp2430_dss_devices[] = {
-	&sdp2430_lcd_device,
+static struct platform_device sdp2430_lcd_device = {
+	.name                   = "panel-dpi",
+	.id                     = 0,
+	.dev.platform_data      = &sdp2430_lcd_pdata,
 };
 
 static struct omap_dss_board_info sdp2430_dss_data = {
-	.num_devices	= ARRAY_SIZE(sdp2430_dss_devices),
-	.devices	= sdp2430_dss_devices,
-	.default_device	= &sdp2430_lcd_device,
+	.default_display_name = "lcd",
+};
+
+static struct platform_device *sdp2430_devices[] __initdata = {
+	&sdp2430_flash_device,
+	&sdp2430_lcd_device,
 };
 
 #if IS_ENABLED(CONFIG_SMC91X)
diff --git a/arch/arm/mach-omap2/board-3430sdp.c b/arch/arm/mach-omap2/board-3430sdp.c
index 23b004afa3f8..d95d0ef1354a 100644
--- a/arch/arm/mach-omap2/board-3430sdp.c
+++ b/arch/arm/mach-omap2/board-3430sdp.c
@@ -126,53 +126,65 @@ static void __init sdp3430_display_init(void)
 
 }
 
-static struct panel_sharp_ls037v7dw01_data sdp3430_lcd_data = {
-	.resb_gpio = SDP3430_LCD_PANEL_ENABLE_GPIO,
-	.ini_gpio = -1,
-	.mo_gpio = -1,
-	.lr_gpio = -1,
-	.ud_gpio = -1,
+static struct panel_sharp_ls037v7dw01_platform_data sdp3430_lcd_pdata = {
+	.name                   = "lcd",
+	.source                 = "dpi.0",
+
+	.data_lines		= 16,
+
+	.resb_gpio		= SDP3430_LCD_PANEL_ENABLE_GPIO,
+	.ini_gpio		= -1,
+	.mo_gpio		= -1,
+	.lr_gpio		= -1,
+	.ud_gpio		= -1,
+};
+
+static struct platform_device sdp3430_lcd_device = {
+	.name                   = "panel-sharp-ls037v7dw01",
+	.id                     = 0,
+	.dev.platform_data      = &sdp3430_lcd_pdata,
 };
 
-static struct omap_dss_device sdp3430_lcd_device = {
-	.name			= "lcd",
-	.driver_name		= "sharp_ls_panel",
-	.type			= OMAP_DISPLAY_TYPE_DPI,
-	.phy.dpi.data_lines	= 16,
-	.data			= &sdp3430_lcd_data,
+static struct connector_dvi_platform_data sdp3430_dvi_connector_pdata = {
+	.name                   = "dvi",
+	.source                 = "tfp410.0",
+	.i2c_bus_num            = -1,
 };
 
-static struct tfp410_platform_data dvi_panel = {
-	.power_down_gpio	= -1,
-	.i2c_bus_num		= -1,
+static struct platform_device sdp3430_dvi_connector_device = {
+	.name                   = "connector-dvi",
+	.id                     = 0,
+	.dev.platform_data      = &sdp3430_dvi_connector_pdata,
 };
 
-static struct omap_dss_device sdp3430_dvi_device = {
-	.name			= "dvi",
-	.type			= OMAP_DISPLAY_TYPE_DPI,
-	.driver_name		= "tfp410",
-	.data			= &dvi_panel,
-	.phy.dpi.data_lines	= 24,
+static struct encoder_tfp410_platform_data sdp3430_tfp410_pdata = {
+	.name                   = "tfp410.0",
+	.source                 = "dpi.0",
+	.data_lines             = 24,
+	.power_down_gpio        = -1,
 };
 
-static struct omap_dss_device sdp3430_tv_device = {
-	.name			= "tv",
-	.driver_name		= "venc",
-	.type			= OMAP_DISPLAY_TYPE_VENC,
-	.phy.venc.type		= OMAP_DSS_VENC_TYPE_SVIDEO,
+static struct platform_device sdp3430_tfp410_device = {
+	.name                   = "tfp410",
+	.id                     = 0,
+	.dev.platform_data      = &sdp3430_tfp410_pdata,
 };
 
+static struct connector_atv_platform_data sdp3430_tv_pdata = {
+	.name = "tv",
+	.source = "venc.0",
+	.connector_type = OMAP_DSS_VENC_TYPE_SVIDEO,
+	.invert_polarity = false,
+};
 
-static struct omap_dss_device *sdp3430_dss_devices[] = {
-	&sdp3430_lcd_device,
-	&sdp3430_dvi_device,
-	&sdp3430_tv_device,
+static struct platform_device sdp3430_tv_connector_device = {
+	.name                   = "connector-analog-tv",
+	.id                     = 0,
+	.dev.platform_data      = &sdp3430_tv_pdata,
 };
 
 static struct omap_dss_board_info sdp3430_dss_data = {
-	.num_devices	= ARRAY_SIZE(sdp3430_dss_devices),
-	.devices	= sdp3430_dss_devices,
-	.default_device	= &sdp3430_lcd_device,
+	.default_display_name = "lcd",
 };
 
 static struct omap2_hsmmc_info mmc[] = {
@@ -583,6 +595,11 @@ static void __init omap_3430sdp_init(void)
 	omap_hsmmc_init(mmc);
 	omap3430_i2c_init();
 	omap_display_init(&sdp3430_dss_data);
+	platform_device_register(&sdp3430_lcd_device);
+	platform_device_register(&sdp3430_tfp410_device);
+	platform_device_register(&sdp3430_dvi_connector_device);
+	platform_device_register(&sdp3430_tv_connector_device);
+
 	if (omap_rev() > OMAP3430_REV_ES1_0)
 		gpio_pendown = SDP3430_TS_GPIO_IRQ_SDPV2;
 	else
diff --git a/arch/arm/mach-omap2/board-am3517crane.c b/arch/arm/mach-omap2/board-am3517crane.c
index fc53911d0d13..0d499a1878f6 100644
--- a/arch/arm/mach-omap2/board-am3517crane.c
+++ b/arch/arm/mach-omap2/board-am3517crane.c
@@ -110,8 +110,6 @@ static void __init am3517_crane_i2c_init(void)
 
 static void __init am3517_crane_init(void)
 {
-	int ret;
-
 	omap3_mux_init(board_mux, OMAP_PACKAGE_CBB);
 	omap_serial_init();
 	omap_sdrc_init(NULL, NULL);
diff --git a/arch/arm/mach-omap2/board-am3517evm.c b/arch/arm/mach-omap2/board-am3517evm.c
index d63f14b534b5..543d9a882de3 100644
--- a/arch/arm/mach-omap2/board-am3517evm.c
+++ b/arch/arm/mach-omap2/board-am3517evm.c
@@ -21,7 +21,7 @@
 #include <linux/clk.h>
 #include <linux/platform_device.h>
 #include <linux/gpio.h>
-#include <linux/i2c/pca953x.h>
+#include <linux/platform_data/pca953x.h>
 #include <linux/can/platform/ti_hecc.h>
 #include <linux/davinci_emac.h>
 #include <linux/mmc/host.h>
@@ -120,56 +120,95 @@ static int __init am3517_evm_i2c_init(void)
 	return 0;
 }
 
-static struct panel_generic_dpi_data lcd_panel = {
-	.name			= "sharp_lq",
-	.num_gpios		= 3,
-	.gpios			= {
-		LCD_PANEL_PWR,
-		LCD_PANEL_BKLIGHT_PWR,
-		LCD_PANEL_PWM,
-	},
+static const struct display_timing am3517_evm_lcd_videomode = {
+	.pixelclock	= { 0, 9000000, 0 },
+
+	.hactive = { 0, 480, 0 },
+	.hfront_porch = { 0, 3, 0 },
+	.hback_porch = { 0, 2, 0 },
+	.hsync_len = { 0, 42, 0 },
+
+	.vactive = { 0, 272, 0 },
+	.vfront_porch = { 0, 3, 0 },
+	.vback_porch = { 0, 2, 0 },
+	.vsync_len = { 0, 11, 0 },
+
+	.flags = DISPLAY_FLAGS_HSYNC_LOW | DISPLAY_FLAGS_VSYNC_LOW |
+		DISPLAY_FLAGS_DE_LOW | DISPLAY_FLAGS_PIXDATA_POSEDGE,
+};
+
+static struct panel_dpi_platform_data am3517_evm_lcd_pdata = {
+	.name                   = "lcd",
+	.source                 = "dpi.0",
+
+	.data_lines		= 16,
+
+	.display_timing		= &am3517_evm_lcd_videomode,
+
+	.enable_gpio		= LCD_PANEL_PWR,
+	.backlight_gpio		= LCD_PANEL_BKLIGHT_PWR,
+};
+
+static struct platform_device am3517_evm_lcd_device = {
+	.name                   = "panel-dpi",
+	.id                     = 0,
+	.dev.platform_data      = &am3517_evm_lcd_pdata,
 };
 
-static struct omap_dss_device am3517_evm_lcd_device = {
-	.type			= OMAP_DISPLAY_TYPE_DPI,
-	.name			= "lcd",
-	.driver_name		= "generic_dpi_panel",
-	.data			= &lcd_panel,
-	.phy.dpi.data_lines 	= 16,
+static struct connector_dvi_platform_data am3517_evm_dvi_connector_pdata = {
+	.name                   = "dvi",
+	.source                 = "tfp410.0",
+	.i2c_bus_num            = -1,
 };
 
-static struct omap_dss_device am3517_evm_tv_device = {
-	.type 			= OMAP_DISPLAY_TYPE_VENC,
-	.name 			= "tv",
-	.driver_name		= "venc",
-	.phy.venc.type		= OMAP_DSS_VENC_TYPE_SVIDEO,
+static struct platform_device am3517_evm_dvi_connector_device = {
+	.name                   = "connector-dvi",
+	.id                     = 0,
+	.dev.platform_data      = &am3517_evm_dvi_connector_pdata,
 };
 
-static struct tfp410_platform_data dvi_panel = {
-	.power_down_gpio	= -1,
-	.i2c_bus_num		= -1,
+static struct encoder_tfp410_platform_data am3517_evm_tfp410_pdata = {
+	.name                   = "tfp410.0",
+	.source                 = "dpi.0",
+	.data_lines             = 24,
+	.power_down_gpio        = -1,
 };
 
-static struct omap_dss_device am3517_evm_dvi_device = {
-	.type			= OMAP_DISPLAY_TYPE_DPI,
-	.name			= "dvi",
-	.driver_name		= "tfp410",
-	.data			= &dvi_panel,
-	.phy.dpi.data_lines	= 24,
+static struct platform_device am3517_evm_tfp410_device = {
+	.name                   = "tfp410",
+	.id                     = 0,
+	.dev.platform_data      = &am3517_evm_tfp410_pdata,
 };
 
-static struct omap_dss_device *am3517_evm_dss_devices[] = {
-	&am3517_evm_lcd_device,
-	&am3517_evm_tv_device,
-	&am3517_evm_dvi_device,
+static struct connector_atv_platform_data am3517_evm_tv_pdata = {
+	.name = "tv",
+	.source = "venc.0",
+	.connector_type = OMAP_DSS_VENC_TYPE_SVIDEO,
+	.invert_polarity = false,
+};
+
+static struct platform_device am3517_evm_tv_connector_device = {
+	.name                   = "connector-analog-tv",
+	.id                     = 0,
+	.dev.platform_data      = &am3517_evm_tv_pdata,
 };
 
 static struct omap_dss_board_info am3517_evm_dss_data = {
-	.num_devices	= ARRAY_SIZE(am3517_evm_dss_devices),
-	.devices	= am3517_evm_dss_devices,
-	.default_device	= &am3517_evm_lcd_device,
+	.default_display_name = "lcd",
 };
 
+static void __init am3517_evm_display_init(void)
+{
+	gpio_request_one(LCD_PANEL_PWM, GPIOF_OUT_INIT_HIGH, "lcd panel pwm");
+
+	omap_display_init(&am3517_evm_dss_data);
+
+	platform_device_register(&am3517_evm_tfp410_device);
+	platform_device_register(&am3517_evm_dvi_connector_device);
+	platform_device_register(&am3517_evm_lcd_device);
+	platform_device_register(&am3517_evm_tv_connector_device);
+}
+
 /*
  * Board initialization
  */
@@ -295,7 +334,9 @@ static void __init am3517_evm_init(void)
 	omap3_mux_init(board_mux, OMAP_PACKAGE_CBB);
 
 	am3517_evm_i2c_init();
-	omap_display_init(&am3517_evm_dss_data);
+
+	am3517_evm_display_init();
+
 	omap_serial_init();
 	omap_sdrc_init(NULL, NULL);
 
diff --git a/arch/arm/mach-omap2/board-cm-t35.c b/arch/arm/mach-omap2/board-cm-t35.c
index d4622ed26252..33d159e2386e 100644
--- a/arch/arm/mach-omap2/board-cm-t35.c
+++ b/arch/arm/mach-omap2/board-cm-t35.c
@@ -190,52 +190,81 @@ static inline void cm_t35_init_nand(void) {}
 #define CM_T35_LCD_BL_GPIO 58
 #define CM_T35_DVI_EN_GPIO 54
 
-static struct panel_generic_dpi_data lcd_panel = {
-	.name			= "toppoly_tdo35s",
-	.num_gpios		= 1,
-	.gpios			= {
-		CM_T35_LCD_BL_GPIO,
-	},
+static const struct display_timing cm_t35_lcd_videomode = {
+	.pixelclock	= { 0, 26000000, 0 },
+
+	.hactive = { 0, 480, 0 },
+	.hfront_porch = { 0, 104, 0 },
+	.hback_porch = { 0, 8, 0 },
+	.hsync_len = { 0, 8, 0 },
+
+	.vactive = { 0, 640, 0 },
+	.vfront_porch = { 0, 4, 0 },
+	.vback_porch = { 0, 2, 0 },
+	.vsync_len = { 0, 2, 0 },
+
+	.flags = DISPLAY_FLAGS_HSYNC_LOW | DISPLAY_FLAGS_VSYNC_LOW |
+		DISPLAY_FLAGS_DE_HIGH | DISPLAY_FLAGS_PIXDATA_NEGEDGE,
+};
+
+static struct panel_dpi_platform_data cm_t35_lcd_pdata = {
+	.name                   = "lcd",
+	.source                 = "dpi.0",
+
+	.data_lines		= 18,
+
+	.display_timing		= &cm_t35_lcd_videomode,
+
+	.enable_gpio		= -1,
+	.backlight_gpio		= CM_T35_LCD_BL_GPIO,
+};
+
+static struct platform_device cm_t35_lcd_device = {
+	.name                   = "panel-dpi",
+	.id                     = 0,
+	.dev.platform_data      = &cm_t35_lcd_pdata,
 };
 
-static struct omap_dss_device cm_t35_lcd_device = {
-	.name			= "lcd",
-	.type			= OMAP_DISPLAY_TYPE_DPI,
-	.driver_name		= "generic_dpi_panel",
-	.data			= &lcd_panel,
-	.phy.dpi.data_lines	= 18,
+static struct connector_dvi_platform_data cm_t35_dvi_connector_pdata = {
+	.name                   = "dvi",
+	.source                 = "tfp410.0",
+	.i2c_bus_num            = -1,
 };
 
-static struct tfp410_platform_data dvi_panel = {
-	.power_down_gpio	= CM_T35_DVI_EN_GPIO,
-	.i2c_bus_num		= -1,
+static struct platform_device cm_t35_dvi_connector_device = {
+	.name                   = "connector-dvi",
+	.id                     = 0,
+	.dev.platform_data      = &cm_t35_dvi_connector_pdata,
 };
 
-static struct omap_dss_device cm_t35_dvi_device = {
-	.name			= "dvi",
-	.type			= OMAP_DISPLAY_TYPE_DPI,
-	.driver_name		= "tfp410",
-	.data			= &dvi_panel,
-	.phy.dpi.data_lines	= 24,
+static struct encoder_tfp410_platform_data cm_t35_tfp410_pdata = {
+	.name                   = "tfp410.0",
+	.source                 = "dpi.0",
+	.data_lines             = 24,
+	.power_down_gpio        = CM_T35_DVI_EN_GPIO,
 };
 
-static struct omap_dss_device cm_t35_tv_device = {
-	.name			= "tv",
-	.driver_name		= "venc",
-	.type			= OMAP_DISPLAY_TYPE_VENC,
-	.phy.venc.type		= OMAP_DSS_VENC_TYPE_SVIDEO,
+static struct platform_device cm_t35_tfp410_device = {
+	.name                   = "tfp410",
+	.id                     = 0,
+	.dev.platform_data      = &cm_t35_tfp410_pdata,
 };
 
-static struct omap_dss_device *cm_t35_dss_devices[] = {
-	&cm_t35_lcd_device,
-	&cm_t35_dvi_device,
-	&cm_t35_tv_device,
+static struct connector_atv_platform_data cm_t35_tv_pdata = {
+	.name = "tv",
+	.source = "venc.0",
+	.connector_type = OMAP_DSS_VENC_TYPE_SVIDEO,
+	.invert_polarity = false,
+};
+
+static struct platform_device cm_t35_tv_connector_device = {
+	.name                   = "connector-analog-tv",
+	.id                     = 0,
+	.dev.platform_data      = &cm_t35_tv_pdata,
 };
 
 static struct omap_dss_board_info cm_t35_dss_data = {
-	.num_devices	= ARRAY_SIZE(cm_t35_dss_devices),
-	.devices	= cm_t35_dss_devices,
-	.default_device	= &cm_t35_dvi_device,
+	.default_display_name = "dvi",
 };
 
 static struct omap2_mcspi_device_config tdo24m_mcspi_config = {
@@ -280,6 +309,11 @@ static void __init cm_t35_init_display(void)
 		pr_err("CM-T35: failed to register DSS device\n");
 		gpio_free(CM_T35_LCD_EN_GPIO);
 	}
+
+	platform_device_register(&cm_t35_tfp410_device);
+	platform_device_register(&cm_t35_dvi_connector_device);
+	platform_device_register(&cm_t35_lcd_device);
+	platform_device_register(&cm_t35_tv_connector_device);
 }
 
 static struct regulator_consumer_supply cm_t35_vmmc1_supply[] = {
diff --git a/arch/arm/mach-omap2/board-devkit8000.c b/arch/arm/mach-omap2/board-devkit8000.c
index f1d91ba5d1ac..cdc4fb9960a9 100644
--- a/arch/arm/mach-omap2/board-devkit8000.c
+++ b/arch/arm/mach-omap2/board-devkit8000.c
@@ -112,50 +112,81 @@ static struct regulator_consumer_supply devkit8000_vio_supply[] = {
 	REGULATOR_SUPPLY("vcc", "spi2.0"),
 };
 
-static struct panel_generic_dpi_data lcd_panel = {
-	.name			= "innolux_at070tn83",
-	/* gpios filled in code */
+static const struct display_timing devkit8000_lcd_videomode = {
+	.pixelclock	= { 0, 40000000, 0 },
+
+	.hactive = { 0, 800, 0 },
+	.hfront_porch = { 0, 1, 0 },
+	.hback_porch = { 0, 1, 0 },
+	.hsync_len = { 0, 48, 0 },
+
+	.vactive = { 0, 480, 0 },
+	.vfront_porch = { 0, 12, 0 },
+	.vback_porch = { 0, 25, 0 },
+	.vsync_len = { 0, 3, 0 },
+
+	.flags = DISPLAY_FLAGS_HSYNC_LOW | DISPLAY_FLAGS_VSYNC_LOW |
+		DISPLAY_FLAGS_DE_HIGH | DISPLAY_FLAGS_PIXDATA_POSEDGE,
 };
 
-static struct omap_dss_device devkit8000_lcd_device = {
+static struct panel_dpi_platform_data devkit8000_lcd_pdata = {
 	.name                   = "lcd",
-	.type                   = OMAP_DISPLAY_TYPE_DPI,
-	.driver_name            = "generic_dpi_panel",
-	.data			= &lcd_panel,
-	.phy.dpi.data_lines     = 24,
+	.source                 = "dpi.0",
+
+	.data_lines		= 24,
+
+	.display_timing		= &devkit8000_lcd_videomode,
+
+	.enable_gpio		= -1,	/* filled in code */
+	.backlight_gpio		= -1,
 };
 
-static struct tfp410_platform_data dvi_panel = {
-	.power_down_gpio	= -1,
-	.i2c_bus_num		= 1,
+static struct platform_device devkit8000_lcd_device = {
+	.name                   = "panel-dpi",
+	.id                     = 0,
+	.dev.platform_data      = &devkit8000_lcd_pdata,
 };
 
-static struct omap_dss_device devkit8000_dvi_device = {
+static struct connector_dvi_platform_data devkit8000_dvi_connector_pdata = {
 	.name                   = "dvi",
-	.type                   = OMAP_DISPLAY_TYPE_DPI,
-	.driver_name            = "tfp410",
-	.data			= &dvi_panel,
-	.phy.dpi.data_lines     = 24,
+	.source                 = "tfp410.0",
+	.i2c_bus_num            = 1,
 };
 
-static struct omap_dss_device devkit8000_tv_device = {
-	.name                   = "tv",
-	.driver_name            = "venc",
-	.type                   = OMAP_DISPLAY_TYPE_VENC,
-	.phy.venc.type          = OMAP_DSS_VENC_TYPE_SVIDEO,
+static struct platform_device devkit8000_dvi_connector_device = {
+	.name                   = "connector-dvi",
+	.id                     = 0,
+	.dev.platform_data      = &devkit8000_dvi_connector_pdata,
 };
 
+static struct encoder_tfp410_platform_data devkit8000_tfp410_pdata = {
+	.name                   = "tfp410.0",
+	.source                 = "dpi.0",
+	.data_lines             = 24,
+	.power_down_gpio        = -1,	/* filled in code */
+};
 
-static struct omap_dss_device *devkit8000_dss_devices[] = {
-	&devkit8000_lcd_device,
-	&devkit8000_dvi_device,
-	&devkit8000_tv_device,
+static struct platform_device devkit8000_tfp410_device = {
+	.name                   = "tfp410",
+	.id                     = 0,
+	.dev.platform_data      = &devkit8000_tfp410_pdata,
+};
+
+static struct connector_atv_platform_data devkit8000_tv_pdata = {
+	.name = "tv",
+	.source = "venc.0",
+	.connector_type = OMAP_DSS_VENC_TYPE_SVIDEO,
+	.invert_polarity = false,
+};
+
+static struct platform_device devkit8000_tv_connector_device = {
+	.name                   = "connector-analog-tv",
+	.id                     = 0,
+	.dev.platform_data      = &devkit8000_tv_pdata,
 };
 
 static struct omap_dss_board_info devkit8000_dss_data = {
-	.num_devices = ARRAY_SIZE(devkit8000_dss_devices),
-	.devices = devkit8000_dss_devices,
-	.default_device = &devkit8000_lcd_device,
+	.default_display_name = "lcd",
 };
 
 static uint32_t board_keymap[] = {
@@ -204,11 +235,10 @@ static int devkit8000_twl_gpio_setup(struct device *dev,
 	gpio_leds[2].gpio = gpio + TWL4030_GPIO_MAX + 1;
 
 	/* TWL4030_GPIO_MAX + 0 is "LCD_PWREN" (out, active high) */
-	lcd_panel.num_gpios = 1;
-	lcd_panel.gpios[0] = gpio + TWL4030_GPIO_MAX + 0;
+	devkit8000_lcd_pdata.enable_gpio = gpio + TWL4030_GPIO_MAX + 0;
 
 	/* gpio + 7 is "DVI_PD" (out, active low) */
-	dvi_panel.power_down_gpio = gpio + 7;
+	devkit8000_tfp410_pdata.power_down_gpio = gpio + 7;
 
 	return 0;
 }
@@ -413,6 +443,10 @@ static struct platform_device *devkit8000_devices[] __initdata = {
 	&leds_gpio,
 	&keys_gpio,
 	&omap_dm9000_dev,
+	&devkit8000_lcd_device,
+	&devkit8000_tfp410_device,
+	&devkit8000_dvi_connector_device,
+	&devkit8000_tv_connector_device,
 };
 
 static struct usbhs_omap_platform_data usbhs_bdata __initdata = {
diff --git a/arch/arm/mach-omap2/board-generic.c b/arch/arm/mach-omap2/board-generic.c
index be5d005ebad2..87162e1b94a5 100644
--- a/arch/arm/mach-omap2/board-generic.c
+++ b/arch/arm/mach-omap2/board-generic.c
@@ -129,6 +129,24 @@ DT_MACHINE_START(OMAP3_DT, "Generic OMAP3 (Flattened Device Tree)")
 	.restart	= omap3xxx_restart,
 MACHINE_END
 
+static const char *omap36xx_boards_compat[] __initdata = {
+	"ti,omap36xx",
+	NULL,
+};
+
+DT_MACHINE_START(OMAP36XX_DT, "Generic OMAP36xx (Flattened Device Tree)")
+	.reserve	= omap_reserve,
+	.map_io		= omap3_map_io,
+	.init_early	= omap3630_init_early,
+	.init_irq	= omap_intc_of_init,
+	.handle_irq	= omap3_intc_handle_irq,
+	.init_machine	= omap_generic_init,
+	.init_late	= omap3_init_late,
+	.init_time	= omap3_sync32k_timer_init,
+	.dt_compat	= omap36xx_boards_compat,
+	.restart	= omap3xxx_restart,
+MACHINE_END
+
 static const char *omap3_gp_boards_compat[] __initdata = {
 	"ti,omap3-beagle",
 	"timll,omap3-devkit8000",
@@ -222,3 +240,22 @@ DT_MACHINE_START(AM43_DT, "Generic AM43 (Flattened Device Tree)")
 	.dt_compat	= am43_boards_compat,
 MACHINE_END
 #endif
+
+#ifdef CONFIG_SOC_DRA7XX
+static const char *dra7xx_boards_compat[] __initdata = {
+	"ti,dra7",
+	NULL,
+};
+
+DT_MACHINE_START(DRA7XX_DT, "Generic DRA7XX (Flattened Device Tree)")
+	.reserve	= omap_reserve,
+	.smp		= smp_ops(omap4_smp_ops),
+	.map_io		= omap5_map_io,
+	.init_early	= dra7xx_init_early,
+	.init_irq	= omap_gic_of_init,
+	.init_machine	= omap_generic_init,
+	.init_time	= omap5_realtime_timer_init,
+	.dt_compat	= dra7xx_boards_compat,
+	.restart	= omap44xx_restart,
+MACHINE_END
+#endif
diff --git a/arch/arm/mach-omap2/board-h4.c b/arch/arm/mach-omap2/board-h4.c
index 69c0acf5aa63..87e41a8b8d46 100644
--- a/arch/arm/mach-omap2/board-h4.c
+++ b/arch/arm/mach-omap2/board-h4.c
@@ -194,30 +194,48 @@ static struct platform_device h4_flash_device = {
 	.resource	= &h4_flash_resource,
 };
 
-static struct platform_device *h4_devices[] __initdata = {
-	&h4_flash_device,
+static const struct display_timing cm_t35_lcd_videomode = {
+	.pixelclock	= { 0, 6250000, 0 },
+
+	.hactive = { 0, 240, 0 },
+	.hfront_porch = { 0, 15, 0 },
+	.hback_porch = { 0, 60, 0 },
+	.hsync_len = { 0, 15, 0 },
+
+	.vactive = { 0, 320, 0 },
+	.vfront_porch = { 0, 1, 0 },
+	.vback_porch = { 0, 1, 0 },
+	.vsync_len = { 0, 1, 0 },
+
+	.flags = DISPLAY_FLAGS_HSYNC_HIGH | DISPLAY_FLAGS_VSYNC_HIGH |
+		DISPLAY_FLAGS_DE_HIGH | DISPLAY_FLAGS_PIXDATA_POSEDGE,
 };
 
-static struct panel_generic_dpi_data h4_panel_data = {
-	.name			= "h4",
+static struct panel_dpi_platform_data cm_t35_lcd_pdata = {
+	.name                   = "lcd",
+	.source                 = "dpi.0",
+
+	.data_lines		= 16,
+
+	.display_timing		= &cm_t35_lcd_videomode,
+
+	.enable_gpio		= -1,
+	.backlight_gpio		= -1,
 };
 
-static struct omap_dss_device h4_lcd_device = {
-	.name			= "lcd",
-	.driver_name		= "generic_dpi_panel",
-	.type			= OMAP_DISPLAY_TYPE_DPI,
-	.phy.dpi.data_lines	= 16,
-	.data			= &h4_panel_data,
+static struct platform_device cm_t35_lcd_device = {
+	.name                   = "panel-dpi",
+	.id                     = 0,
+	.dev.platform_data      = &cm_t35_lcd_pdata,
 };
 
-static struct omap_dss_device *h4_dss_devices[] = {
-	&h4_lcd_device,
+static struct platform_device *h4_devices[] __initdata = {
+	&h4_flash_device,
+	&cm_t35_lcd_device,
 };
 
 static struct omap_dss_board_info h4_dss_data = {
-	.num_devices	= ARRAY_SIZE(h4_dss_devices),
-	.devices	= h4_dss_devices,
-	.default_device	= &h4_lcd_device,
+	.default_display_name = "lcd",
 };
 
 /* 2420 Sysboot setup (2430 is different) */
diff --git a/arch/arm/mach-omap2/board-igep0020.c b/arch/arm/mach-omap2/board-igep0020.c
index 87e65dde8e13..06dbb2d3d38b 100644
--- a/arch/arm/mach-omap2/board-igep0020.c
+++ b/arch/arm/mach-omap2/board-igep0020.c
@@ -429,31 +429,39 @@ static struct twl4030_gpio_platform_data igep_twl4030_gpio_pdata = {
 	.setup		= igep_twl_gpio_setup,
 };
 
-static struct tfp410_platform_data dvi_panel = {
-	.i2c_bus_num		= 3,
-	.power_down_gpio	= IGEP2_GPIO_DVI_PUP,
+static struct connector_dvi_platform_data omap3stalker_dvi_connector_pdata = {
+	.name                   = "dvi",
+	.source                 = "tfp410.0",
+	.i2c_bus_num            = 3,
 };
 
-static struct omap_dss_device igep2_dvi_device = {
-	.type			= OMAP_DISPLAY_TYPE_DPI,
-	.name			= "dvi",
-	.driver_name		= "tfp410",
-	.data			= &dvi_panel,
-	.phy.dpi.data_lines	= 24,
+static struct platform_device omap3stalker_dvi_connector_device = {
+	.name                   = "connector-dvi",
+	.id                     = 0,
+	.dev.platform_data      = &omap3stalker_dvi_connector_pdata,
 };
 
-static struct omap_dss_device *igep2_dss_devices[] = {
-	&igep2_dvi_device
+static struct encoder_tfp410_platform_data omap3stalker_tfp410_pdata = {
+	.name                   = "tfp410.0",
+	.source                 = "dpi.0",
+	.data_lines             = 24,
+	.power_down_gpio        = IGEP2_GPIO_DVI_PUP,
+};
+
+static struct platform_device omap3stalker_tfp410_device = {
+	.name                   = "tfp410",
+	.id                     = 0,
+	.dev.platform_data      = &omap3stalker_tfp410_pdata,
 };
 
 static struct omap_dss_board_info igep2_dss_data = {
-	.num_devices	= ARRAY_SIZE(igep2_dss_devices),
-	.devices	= igep2_dss_devices,
-	.default_device	= &igep2_dvi_device,
+	.default_display_name = "dvi",
 };
 
 static struct platform_device *igep_devices[] __initdata = {
 	&igep_vwlan_device,
+	&omap3stalker_tfp410_device,
+	&omap3stalker_dvi_connector_device,
 };
 
 static int igep2_keymap[] = {
diff --git a/arch/arm/mach-omap2/board-ldp.c b/arch/arm/mach-omap2/board-ldp.c
index 62e4f701b63b..dd8da2c5399f 100644
--- a/arch/arm/mach-omap2/board-ldp.c
+++ b/arch/arm/mach-omap2/board-ldp.c
@@ -184,45 +184,70 @@ static inline void __init ldp_init_smsc911x(void)
 #define LCD_PANEL_RESET_GPIO		55
 #define LCD_PANEL_QVGA_GPIO		56
 
-static struct panel_generic_dpi_data ldp_panel_data = {
-	.name			= "nec_nl2432dr22-11b",
-	.num_gpios		= 4,
-	/* gpios filled in code */
+static const struct display_timing ldp_lcd_videomode = {
+	.pixelclock	= { 0, 5400000, 0 },
+
+	.hactive = { 0, 240, 0 },
+	.hfront_porch = { 0, 3, 0 },
+	.hback_porch = { 0, 39, 0 },
+	.hsync_len = { 0, 3, 0 },
+
+	.vactive = { 0, 320, 0 },
+	.vfront_porch = { 0, 2, 0 },
+	.vback_porch = { 0, 7, 0 },
+	.vsync_len = { 0, 1, 0 },
+
+	.flags = DISPLAY_FLAGS_HSYNC_LOW | DISPLAY_FLAGS_VSYNC_LOW |
+		DISPLAY_FLAGS_DE_HIGH | DISPLAY_FLAGS_PIXDATA_POSEDGE,
 };
 
-static struct omap_dss_device ldp_lcd_device = {
-	.name			= "lcd",
-	.driver_name		= "generic_dpi_panel",
-	.type			= OMAP_DISPLAY_TYPE_DPI,
-	.phy.dpi.data_lines	= 18,
-	.data			= &ldp_panel_data,
+static struct panel_dpi_platform_data ldp_lcd_pdata = {
+	.name                   = "lcd",
+	.source                 = "dpi.0",
+
+	.data_lines		= 18,
+
+	.display_timing		= &ldp_lcd_videomode,
+
+	.enable_gpio		= -1,	/* filled in code */
+	.backlight_gpio		= -1,	/* filled in code */
 };
 
-static struct omap_dss_device *ldp_dss_devices[] = {
-	&ldp_lcd_device,
+static struct platform_device ldp_lcd_device = {
+	.name                   = "panel-dpi",
+	.id                     = 0,
+	.dev.platform_data      = &ldp_lcd_pdata,
 };
 
 static struct omap_dss_board_info ldp_dss_data = {
-	.num_devices	= ARRAY_SIZE(ldp_dss_devices),
-	.devices	= ldp_dss_devices,
-	.default_device	= &ldp_lcd_device,
+	.default_display_name = "lcd",
 };
 
 static void __init ldp_display_init(void)
 {
-	ldp_panel_data.gpios[2] = LCD_PANEL_RESET_GPIO;
-	ldp_panel_data.gpios[3] = LCD_PANEL_QVGA_GPIO;
+	int r;
+
+	static struct gpio gpios[] __initdata = {
+		{LCD_PANEL_RESET_GPIO, GPIOF_OUT_INIT_HIGH, "LCD RESET"},
+		{LCD_PANEL_QVGA_GPIO, GPIOF_OUT_INIT_HIGH, "LCD QVGA"},
+	};
+
+	r = gpio_request_array(gpios, ARRAY_SIZE(gpios));
+	if (r) {
+		pr_err("Cannot request LCD GPIOs, error %d\n", r);
+		return;
+	}
 
 	omap_display_init(&ldp_dss_data);
 }
 
 static int ldp_twl_gpio_setup(struct device *dev, unsigned gpio, unsigned ngpio)
 {
-	ldp_panel_data.gpios[0] = gpio + 7;
-	ldp_panel_data.gpio_invert[0] = true;
+	/* LCD enable GPIO */
+	ldp_lcd_pdata.enable_gpio = gpio + 7;
 
-	ldp_panel_data.gpios[1] = gpio + 15;
-	ldp_panel_data.gpio_invert[1] = true;
+	/* Backlight enable GPIO */
+	ldp_lcd_pdata.backlight_gpio = gpio + 15;
 
 	return 0;
 }
@@ -322,6 +347,7 @@ static struct omap2_hsmmc_info mmc[] __initdata = {
 
 static struct platform_device *ldp_devices[] __initdata = {
 	&ldp_gpio_keys_device,
+	&ldp_lcd_device,
 };
 
 #ifdef CONFIG_OMAP_MUX
diff --git a/arch/arm/mach-omap2/board-omap3beagle.c b/arch/arm/mach-omap2/board-omap3beagle.c
index 04c116555412..f26918467efc 100644
--- a/arch/arm/mach-omap2/board-omap3beagle.c
+++ b/arch/arm/mach-omap2/board-omap3beagle.c
@@ -33,7 +33,7 @@
 #include <linux/mtd/nand.h>
 #include <linux/mmc/host.h>
 #include <linux/usb/phy.h>
-#include <linux/usb/nop-usb-xceiv.h>
+#include <linux/usb/usb_phy_gen_xceiv.h>
 
 #include <linux/regulator/machine.h>
 #include <linux/i2c/twl.h>
@@ -225,35 +225,46 @@ static struct mtd_partition omap3beagle_nand_partitions[] = {
 
 /* DSS */
 
-static struct tfp410_platform_data dvi_panel = {
-	.i2c_bus_num = 3,
-	.power_down_gpio = -1,
+static struct connector_dvi_platform_data beagle_dvi_connector_pdata = {
+	.name                   = "dvi",
+	.source                 = "tfp410.0",
+	.i2c_bus_num            = 3,
 };
 
-static struct omap_dss_device beagle_dvi_device = {
-	.type = OMAP_DISPLAY_TYPE_DPI,
-	.name = "dvi",
-	.driver_name = "tfp410",
-	.data = &dvi_panel,
-	.phy.dpi.data_lines = 24,
+static struct platform_device beagle_dvi_connector_device = {
+	.name                   = "connector-dvi",
+	.id                     = 0,
+	.dev.platform_data      = &beagle_dvi_connector_pdata,
 };
 
-static struct omap_dss_device beagle_tv_device = {
+static struct encoder_tfp410_platform_data beagle_tfp410_pdata = {
+	.name                   = "tfp410.0",
+	.source                 = "dpi.0",
+	.data_lines             = 24,
+	.power_down_gpio        = -1,
+};
+
+static struct platform_device beagle_tfp410_device = {
+	.name                   = "tfp410",
+	.id                     = 0,
+	.dev.platform_data      = &beagle_tfp410_pdata,
+};
+
+static struct connector_atv_platform_data beagle_tv_pdata = {
 	.name = "tv",
-	.driver_name = "venc",
-	.type = OMAP_DISPLAY_TYPE_VENC,
-	.phy.venc.type = OMAP_DSS_VENC_TYPE_SVIDEO,
+	.source = "venc.0",
+	.connector_type = OMAP_DSS_VENC_TYPE_SVIDEO,
+	.invert_polarity = false,
 };
 
-static struct omap_dss_device *beagle_dss_devices[] = {
-	&beagle_dvi_device,
-	&beagle_tv_device,
+static struct platform_device beagle_tv_connector_device = {
+	.name                   = "connector-analog-tv",
+	.id                     = 0,
+	.dev.platform_data      = &beagle_tv_pdata,
 };
 
 static struct omap_dss_board_info beagle_dss_data = {
-	.num_devices = ARRAY_SIZE(beagle_dss_devices),
-	.devices = beagle_dss_devices,
-	.default_device = &beagle_dvi_device,
+	.default_display_name = "dvi",
 };
 
 #include "sdram-micron-mt46h32m32lf-6.h"
@@ -279,7 +290,7 @@ static struct regulator_consumer_supply beagle_vsim_supply[] = {
 static struct gpio_led gpio_leds[];
 
 /* PHY's VCC regulator might be added later, so flag that we need it */
-static struct nop_usb_xceiv_platform_data hsusb2_phy_data = {
+static struct usb_phy_gen_xceiv_platform_data hsusb2_phy_data = {
 	.needs_vcc = true,
 };
 
@@ -332,7 +343,11 @@ static int beagle_twl_gpio_setup(struct device *dev,
 		if (gpio_request_one(gpio + 1, GPIOF_IN, "EHCI_nOC"))
 			pr_err("%s: unable to configure EHCI_nOC\n", __func__);
 	}
-	dvi_panel.power_down_gpio = beagle_config.dvi_pd_gpio;
+	beagle_tfp410_pdata.power_down_gpio = beagle_config.dvi_pd_gpio;
+
+	platform_device_register(&beagle_tfp410_device);
+	platform_device_register(&beagle_dvi_connector_device);
+	platform_device_register(&beagle_tv_connector_device);
 
 	/* TWL4030_GPIO_MAX i.e. LED_GPO controls HS USB Port 2 power */
 	phy_data[0].vcc_gpio = gpio + TWL4030_GPIO_MAX;
@@ -547,6 +562,7 @@ static void __init omap3_beagle_init(void)
 	if (gpio_is_valid(beagle_config.dvi_pd_gpio))
 		omap_mux_init_gpio(beagle_config.dvi_pd_gpio, OMAP_PIN_OUTPUT);
 	omap_display_init(&beagle_dss_data);
+
 	omap_serial_init();
 	omap_sdrc_init(mt46h32m32lf6_sdrc_params,
 				  mt46h32m32lf6_sdrc_params);
diff --git a/arch/arm/mach-omap2/board-omap3evm.c b/arch/arm/mach-omap2/board-omap3evm.c
index 8c026269baca..18143873346c 100644
--- a/arch/arm/mach-omap2/board-omap3evm.c
+++ b/arch/arm/mach-omap2/board-omap3evm.c
@@ -33,7 +33,7 @@
 #include <linux/i2c/twl.h>
 #include <linux/usb/otg.h>
 #include <linux/usb/musb.h>
-#include <linux/usb/nop-usb-xceiv.h>
+#include <linux/usb/usb_phy_gen_xceiv.h>
 #include <linux/smsc911x.h>
 
 #include <linux/wl12xx.h>
@@ -166,14 +166,6 @@ static inline void __init omap3evm_init_smsc911x(void) { return; }
  */
 #define OMAP3EVM_DVI_PANEL_EN_GPIO	199
 
-static struct panel_sharp_ls037v7dw01_data omap3_evm_lcd_data = {
-	.resb_gpio = OMAP3EVM_LCD_PANEL_RESB,
-	.ini_gpio = OMAP3EVM_LCD_PANEL_INI,
-	.mo_gpio = OMAP3EVM_LCD_PANEL_QVGA,
-	.lr_gpio = OMAP3EVM_LCD_PANEL_LR,
-	.ud_gpio = OMAP3EVM_LCD_PANEL_UD,
-};
-
 #ifdef CONFIG_BROKEN
 static void __init omap3_evm_display_init(void)
 {
@@ -196,44 +188,65 @@ static void __init omap3_evm_display_init(void)
 }
 #endif
 
-static struct omap_dss_device omap3_evm_lcd_device = {
-	.name			= "lcd",
-	.driver_name		= "sharp_ls_panel",
-	.type			= OMAP_DISPLAY_TYPE_DPI,
-	.phy.dpi.data_lines	= 18,
-	.data			= &omap3_evm_lcd_data,
+static struct panel_sharp_ls037v7dw01_platform_data omap3_evm_lcd_pdata = {
+	.name                   = "lcd",
+	.source                 = "dpi.0",
+
+	.data_lines		= 18,
+
+	.resb_gpio		= OMAP3EVM_LCD_PANEL_RESB,
+	.ini_gpio		= OMAP3EVM_LCD_PANEL_INI,
+	.mo_gpio		= OMAP3EVM_LCD_PANEL_QVGA,
+	.lr_gpio		= OMAP3EVM_LCD_PANEL_LR,
+	.ud_gpio		= OMAP3EVM_LCD_PANEL_UD,
+};
+
+static struct platform_device omap3_evm_lcd_device = {
+	.name                   = "panel-sharp-ls037v7dw01",
+	.id                     = 0,
+	.dev.platform_data      = &omap3_evm_lcd_pdata,
+};
+
+static struct connector_dvi_platform_data omap3_evm_dvi_connector_pdata = {
+	.name                   = "dvi",
+	.source                 = "tfp410.0",
+	.i2c_bus_num            = -1,
+};
+
+static struct platform_device omap3_evm_dvi_connector_device = {
+	.name                   = "connector-dvi",
+	.id                     = 0,
+	.dev.platform_data      = &omap3_evm_dvi_connector_pdata,
 };
 
-static struct omap_dss_device omap3_evm_tv_device = {
-	.name			= "tv",
-	.driver_name		= "venc",
-	.type			= OMAP_DISPLAY_TYPE_VENC,
-	.phy.venc.type		= OMAP_DSS_VENC_TYPE_SVIDEO,
+static struct encoder_tfp410_platform_data omap3_evm_tfp410_pdata = {
+	.name                   = "tfp410.0",
+	.source                 = "dpi.0",
+	.data_lines             = 24,
+	.power_down_gpio        = OMAP3EVM_DVI_PANEL_EN_GPIO,
 };
 
-static struct tfp410_platform_data dvi_panel = {
-	.power_down_gpio	= OMAP3EVM_DVI_PANEL_EN_GPIO,
-	.i2c_bus_num		= -1,
+static struct platform_device omap3_evm_tfp410_device = {
+	.name                   = "tfp410",
+	.id                     = 0,
+	.dev.platform_data      = &omap3_evm_tfp410_pdata,
 };
 
-static struct omap_dss_device omap3_evm_dvi_device = {
-	.name			= "dvi",
-	.type			= OMAP_DISPLAY_TYPE_DPI,
-	.driver_name		= "tfp410",
-	.data			= &dvi_panel,
-	.phy.dpi.data_lines	= 24,
+static struct connector_atv_platform_data omap3_evm_tv_pdata = {
+	.name = "tv",
+	.source = "venc.0",
+	.connector_type = OMAP_DSS_VENC_TYPE_SVIDEO,
+	.invert_polarity = false,
 };
 
-static struct omap_dss_device *omap3_evm_dss_devices[] = {
-	&omap3_evm_lcd_device,
-	&omap3_evm_tv_device,
-	&omap3_evm_dvi_device,
+static struct platform_device omap3_evm_tv_connector_device = {
+	.name                   = "connector-analog-tv",
+	.id                     = 0,
+	.dev.platform_data      = &omap3_evm_tv_pdata,
 };
 
 static struct omap_dss_board_info omap3_evm_dss_data = {
-	.num_devices	= ARRAY_SIZE(omap3_evm_dss_devices),
-	.devices	= omap3_evm_dss_devices,
-	.default_device	= &omap3_evm_lcd_device,
+	.default_display_name = "lcd",
 };
 
 static struct regulator_consumer_supply omap3evm_vmmc1_supply[] = {
@@ -468,7 +481,7 @@ struct wl12xx_platform_data omap3evm_wlan_data __initdata = {
 static struct regulator_consumer_supply omap3evm_vaux2_supplies[] = {
 	REGULATOR_SUPPLY("VDD_CSIPHY1", "omap3isp"),	/* OMAP ISP */
 	REGULATOR_SUPPLY("VDD_CSIPHY2", "omap3isp"),	/* OMAP ISP */
-	REGULATOR_SUPPLY("vcc", "nop_usb_xceiv.2"),	/* hsusb port 2 */
+	REGULATOR_SUPPLY("vcc", "usb_phy_gen_xceiv.2"),	/* hsusb port 2 */
 	REGULATOR_SUPPLY("vaux2", NULL),
 };
 
@@ -678,6 +691,10 @@ static void __init omap3_evm_init(void)
 	omap3_evm_i2c_init();
 
 	omap_display_init(&omap3_evm_dss_data);
+	platform_device_register(&omap3_evm_lcd_device);
+	platform_device_register(&omap3_evm_tfp410_device);
+	platform_device_register(&omap3_evm_dvi_connector_device);
+	platform_device_register(&omap3_evm_tv_connector_device);
 
 	omap_serial_init();
 	omap_sdrc_init(mt46h32m32lf6_sdrc_params, NULL);
diff --git a/arch/arm/mach-omap2/board-omap3pandora.c b/arch/arm/mach-omap2/board-omap3pandora.c
index b1547a0edfcd..de1bc6bbe585 100644
--- a/arch/arm/mach-omap2/board-omap3pandora.c
+++ b/arch/arm/mach-omap2/board-omap3pandora.c
@@ -231,34 +231,21 @@ static struct twl4030_keypad_data pandora_kp_data = {
 	.rep		= 1,
 };
 
-static struct panel_tpo_td043_data lcd_data = {
-	.nreset_gpio		= 157,
-};
-
-static struct omap_dss_device pandora_lcd_device = {
-	.name			= "lcd",
-	.driver_name		= "tpo_td043mtea1_panel",
-	.type			= OMAP_DISPLAY_TYPE_DPI,
-	.phy.dpi.data_lines	= 24,
-	.data			= &lcd_data,
-};
-
-static struct omap_dss_device pandora_tv_device = {
-	.name			= "tv",
-	.driver_name		= "venc",
-	.type			= OMAP_DISPLAY_TYPE_VENC,
-	.phy.venc.type		= OMAP_DSS_VENC_TYPE_SVIDEO,
+static struct connector_atv_platform_data pandora_tv_pdata = {
+	.name = "tv",
+	.source = "venc.0",
+	.connector_type = OMAP_DSS_VENC_TYPE_SVIDEO,
+	.invert_polarity = false,
 };
 
-static struct omap_dss_device *pandora_dss_devices[] = {
-	&pandora_lcd_device,
-	&pandora_tv_device,
+static struct platform_device pandora_tv_connector_device = {
+	.name                   = "connector-analog-tv",
+	.id                     = 0,
+	.dev.platform_data      = &pandora_tv_pdata,
 };
 
 static struct omap_dss_board_info pandora_dss_data = {
-	.num_devices	= ARRAY_SIZE(pandora_dss_devices),
-	.devices	= pandora_dss_devices,
-	.default_device	= &pandora_lcd_device,
+	.default_display_name = "lcd",
 };
 
 static void pandora_wl1251_init_card(struct mmc_card *card)
@@ -348,11 +335,11 @@ static struct regulator_consumer_supply pandora_vdds_supplies[] = {
 };
 
 static struct regulator_consumer_supply pandora_vcc_lcd_supply[] = {
-	REGULATOR_SUPPLY("vcc", "display0"),
+	REGULATOR_SUPPLY("vcc", "spi1.1"),
 };
 
 static struct regulator_consumer_supply pandora_usb_phy_supply[] = {
-	REGULATOR_SUPPLY("vcc", "nop_usb_xceiv.2"),	/* hsusb port 2 */
+	REGULATOR_SUPPLY("vcc", "usb_phy_gen_xceiv.2"),	/* hsusb port 2 */
 };
 
 /* ads7846 on SPI and 2 nub controllers on I2C */
@@ -529,13 +516,21 @@ static int __init omap3pandora_i2c_init(void)
 	return 0;
 }
 
+static struct panel_tpo_td043mtea1_platform_data pandora_lcd_pdata = {
+	.name                   = "lcd",
+	.source                 = "dpi.0",
+
+	.data_lines		= 24,
+	.nreset_gpio		= 157,
+};
+
 static struct spi_board_info omap3pandora_spi_board_info[] __initdata = {
 	{
-		.modalias		= "tpo_td043mtea1_panel_spi",
+		.modalias		= "panel-tpo-td043mtea1",
 		.bus_num		= 1,
 		.chip_select		= 1,
 		.max_speed_hz		= 375000,
-		.platform_data		= &pandora_lcd_device,
+		.platform_data		= &pandora_lcd_pdata,
 	}
 };
 
@@ -580,6 +575,7 @@ static struct platform_device *omap3pandora_devices[] __initdata = {
 	&pandora_keys_gpio,
 	&pandora_vwlan_device,
 	&pandora_backlight,
+	&pandora_tv_connector_device,
 };
 
 static struct usbhs_omap_platform_data usbhs_bdata __initdata = {
diff --git a/arch/arm/mach-omap2/board-omap3stalker.c b/arch/arm/mach-omap2/board-omap3stalker.c
index d37e6b187ae4..ba8342fef799 100644
--- a/arch/arm/mach-omap2/board-omap3stalker.c
+++ b/arch/arm/mach-omap2/board-omap3stalker.c
@@ -93,40 +93,50 @@ static void __init omap3_stalker_display_init(void)
 {
 	return;
 }
+static struct connector_dvi_platform_data omap3stalker_dvi_connector_pdata = {
+	.name                   = "dvi",
+	.source                 = "tfp410.0",
+	.i2c_bus_num            = -1,
+};
 
-static struct omap_dss_device omap3_stalker_tv_device = {
-	.name			= "tv",
-	.driver_name		= "venc",
-	.type			= OMAP_DISPLAY_TYPE_VENC,
-#if defined(CONFIG_OMAP2_VENC_OUT_TYPE_SVIDEO)
-	.phy.venc.type		= OMAP_DSS_VENC_TYPE_SVIDEO,
-#elif defined(CONFIG_OMAP2_VENC_OUT_TYPE_COMPOSITE)
-	.u.venc.type		= OMAP_DSS_VENC_TYPE_COMPOSITE,
-#endif
+static struct platform_device omap3stalker_dvi_connector_device = {
+	.name                   = "connector-dvi",
+	.id                     = 0,
+	.dev.platform_data      = &omap3stalker_dvi_connector_pdata,
 };
 
-static struct tfp410_platform_data dvi_panel = {
-	.power_down_gpio	= DSS_ENABLE_GPIO,
-	.i2c_bus_num		= -1,
+static struct encoder_tfp410_platform_data omap3stalker_tfp410_pdata = {
+	.name                   = "tfp410.0",
+	.source                 = "dpi.0",
+	.data_lines             = 24,
+	.power_down_gpio        = DSS_ENABLE_GPIO,
 };
 
-static struct omap_dss_device omap3_stalker_dvi_device = {
-	.name			= "dvi",
-	.type			= OMAP_DISPLAY_TYPE_DPI,
-	.driver_name		= "tfp410",
-	.data			= &dvi_panel,
-	.phy.dpi.data_lines	= 24,
+static struct platform_device omap3stalker_tfp410_device = {
+	.name                   = "tfp410",
+	.id                     = 0,
+	.dev.platform_data      = &omap3stalker_tfp410_pdata,
+};
+
+static struct connector_atv_platform_data omap3stalker_tv_pdata = {
+	.name = "tv",
+	.source = "venc.0",
+#if defined(CONFIG_OMAP2_VENC_OUT_TYPE_SVIDEO)
+	.connector_type = OMAP_DSS_VENC_TYPE_SVIDEO,
+#elif defined(CONFIG_OMAP2_VENC_OUT_TYPE_COMPOSITE)
+	.connector_type = OMAP_DSS_VENC_TYPE_COMPOSITE,
+#endif
+	.invert_polarity = false,
 };
 
-static struct omap_dss_device *omap3_stalker_dss_devices[] = {
-	&omap3_stalker_tv_device,
-	&omap3_stalker_dvi_device,
+static struct platform_device omap3stalker_tv_connector_device = {
+	.name                   = "connector-analog-tv",
+	.id                     = 0,
+	.dev.platform_data      = &omap3stalker_tv_pdata,
 };
 
 static struct omap_dss_board_info omap3_stalker_dss_data = {
-	.num_devices	= ARRAY_SIZE(omap3_stalker_dss_devices),
-	.devices	= omap3_stalker_dss_devices,
-	.default_device	= &omap3_stalker_dvi_device,
+	.default_display_name = "dvi",
 };
 
 static struct regulator_consumer_supply omap3stalker_vmmc1_supply[] = {
@@ -356,6 +366,9 @@ static struct usbhs_phy_data phy_data[] __initdata = {
 
 static struct platform_device *omap3_stalker_devices[] __initdata = {
 	&keys_gpio,
+	&omap3stalker_tfp410_device,
+	&omap3stalker_dvi_connector_device,
+	&omap3stalker_tv_connector_device,
 };
 
 static struct usbhs_omap_platform_data usbhs_bdata __initdata = {
diff --git a/arch/arm/mach-omap2/board-overo.c b/arch/arm/mach-omap2/board-overo.c
index 5748b5d06c23..f6d384111911 100644
--- a/arch/arm/mach-omap2/board-overo.c
+++ b/arch/arm/mach-omap2/board-overo.c
@@ -72,6 +72,9 @@
 #define OVERO_SMSC911X2_CS     4
 #define OVERO_SMSC911X2_GPIO   65
 
+/* whether to register LCD35 instead of LCD43 */
+static bool overo_use_lcd35;
+
 #if defined(CONFIG_TOUCHSCREEN_ADS7846) || \
 	defined(CONFIG_TOUCHSCREEN_ADS7846_MODULE)
 
@@ -149,78 +152,94 @@ static inline void __init overo_init_smsc911x(void) { return; }
 #define OVERO_GPIO_LCD_EN 144
 #define OVERO_GPIO_LCD_BL 145
 
-static struct tfp410_platform_data dvi_panel = {
-	.i2c_bus_num		= 3,
-	.power_down_gpio	= -1,
+static struct connector_atv_platform_data overo_tv_pdata = {
+	.name = "tv",
+	.source = "venc.0",
+	.connector_type = OMAP_DSS_VENC_TYPE_SVIDEO,
+	.invert_polarity = false,
 };
 
-static struct omap_dss_device overo_dvi_device = {
-	.name			= "dvi",
-	.type			= OMAP_DISPLAY_TYPE_DPI,
-	.driver_name		= "tfp410",
-	.data			= &dvi_panel,
-	.phy.dpi.data_lines	= 24,
+static struct platform_device overo_tv_connector_device = {
+	.name                   = "connector-analog-tv",
+	.id                     = 0,
+	.dev.platform_data      = &overo_tv_pdata,
 };
 
-static struct omap_dss_device overo_tv_device = {
-	.name = "tv",
-	.driver_name = "venc",
-	.type = OMAP_DISPLAY_TYPE_VENC,
-	.phy.venc.type = OMAP_DSS_VENC_TYPE_SVIDEO,
+static const struct display_timing overo_lcd43_videomode = {
+	.pixelclock	= { 0, 9200000, 0 },
+
+	.hactive = { 0, 480, 0 },
+	.hfront_porch = { 0, 8, 0 },
+	.hback_porch = { 0, 4, 0 },
+	.hsync_len = { 0, 41, 0 },
+
+	.vactive = { 0, 272, 0 },
+	.vfront_porch = { 0, 4, 0 },
+	.vback_porch = { 0, 2, 0 },
+	.vsync_len = { 0, 10, 0 },
+
+	.flags = DISPLAY_FLAGS_HSYNC_LOW | DISPLAY_FLAGS_VSYNC_LOW |
+		DISPLAY_FLAGS_DE_HIGH | DISPLAY_FLAGS_PIXDATA_POSEDGE,
 };
 
-static struct panel_generic_dpi_data lcd43_panel = {
-	.name			= "samsung_lte430wq_f0c",
-	.num_gpios		= 2,
-	.gpios			= {
-		OVERO_GPIO_LCD_EN,
-		OVERO_GPIO_LCD_BL
-	},
+static struct panel_dpi_platform_data overo_lcd43_pdata = {
+	.name                   = "lcd43",
+	.source                 = "dpi.0",
+
+	.data_lines		= 24,
+
+	.display_timing		= &overo_lcd43_videomode,
+
+	.enable_gpio		= OVERO_GPIO_LCD_EN,
+	.backlight_gpio		= OVERO_GPIO_LCD_BL,
 };
 
-static struct omap_dss_device overo_lcd43_device = {
-	.name			= "lcd43",
-	.type			= OMAP_DISPLAY_TYPE_DPI,
-	.driver_name		= "generic_dpi_panel",
-	.data			= &lcd43_panel,
-	.phy.dpi.data_lines	= 24,
+static struct platform_device overo_lcd43_device = {
+	.name                   = "panel-dpi",
+	.id                     = 0,
+	.dev.platform_data      = &overo_lcd43_pdata,
 };
 
-#if defined(CONFIG_PANEL_LGPHILIPS_LB035Q02) || \
-	defined(CONFIG_PANEL_LGPHILIPS_LB035Q02_MODULE)
-static struct panel_generic_dpi_data lcd35_panel = {
-	.num_gpios		= 2,
-	.gpios			= {
-		OVERO_GPIO_LCD_EN,
-		OVERO_GPIO_LCD_BL
-	},
+static struct connector_dvi_platform_data overo_dvi_connector_pdata = {
+	.name                   = "dvi",
+	.source                 = "tfp410.0",
+	.i2c_bus_num            = 3,
 };
 
-static struct omap_dss_device overo_lcd35_device = {
-	.type			= OMAP_DISPLAY_TYPE_DPI,
-	.name			= "lcd35",
-	.driver_name		= "lgphilips_lb035q02_panel",
-	.phy.dpi.data_lines	= 24,
-	.data			= &lcd35_panel,
+static struct platform_device overo_dvi_connector_device = {
+	.name                   = "connector-dvi",
+	.id                     = 0,
+	.dev.platform_data      = &overo_dvi_connector_pdata,
 };
-#endif
 
-static struct omap_dss_device *overo_dss_devices[] = {
-	&overo_dvi_device,
-	&overo_tv_device,
-#if defined(CONFIG_PANEL_LGPHILIPS_LB035Q02) || \
-	defined(CONFIG_PANEL_LGPHILIPS_LB035Q02_MODULE)
-	&overo_lcd35_device,
-#endif
-	&overo_lcd43_device,
+static struct encoder_tfp410_platform_data overo_tfp410_pdata = {
+	.name                   = "tfp410.0",
+	.source                 = "dpi.0",
+	.data_lines             = 24,
+	.power_down_gpio        = -1,
+};
+
+static struct platform_device overo_tfp410_device = {
+	.name                   = "tfp410",
+	.id                     = 0,
+	.dev.platform_data      = &overo_tfp410_pdata,
 };
 
 static struct omap_dss_board_info overo_dss_data = {
-	.num_devices	= ARRAY_SIZE(overo_dss_devices),
-	.devices	= overo_dss_devices,
-	.default_device	= &overo_dvi_device,
+	.default_display_name = "lcd43",
 };
 
+static void __init overo_display_init(void)
+{
+	omap_display_init(&overo_dss_data);
+
+	if (!overo_use_lcd35)
+		platform_device_register(&overo_lcd43_device);
+	platform_device_register(&overo_tfp410_device);
+	platform_device_register(&overo_dvi_connector_device);
+	platform_device_register(&overo_tv_connector_device);
+}
+
 static struct mtd_partition overo_nand_partitions[] = {
 	{
 		.name           = "xloader",
@@ -408,24 +427,41 @@ static int __init overo_i2c_init(void)
 	return 0;
 }
 
+static struct panel_lb035q02_platform_data overo_lcd35_pdata = {
+	.name                   = "lcd35",
+	.source                 = "dpi.0",
+
+	.data_lines		= 24,
+
+	.enable_gpio		= OVERO_GPIO_LCD_EN,
+	.backlight_gpio		= OVERO_GPIO_LCD_BL,
+};
+
+/*
+ * NOTE: We need to add either the lgphilips panel, or the lcd43 panel. The
+ * selection is done based on the overo_use_lcd35 field. If new SPI
+ * devices are added here, extra work is needed to make only the lgphilips panel
+ * affected by the overo_use_lcd35 field.
+ */
 static struct spi_board_info overo_spi_board_info[] __initdata = {
-#if defined(CONFIG_PANEL_LGPHILIPS_LB035Q02) || \
-	defined(CONFIG_PANEL_LGPHILIPS_LB035Q02_MODULE)
 	{
-		.modalias		= "lgphilips_lb035q02_panel-spi",
+		.modalias		= "panel_lgphilips_lb035q02",
 		.bus_num		= 1,
 		.chip_select		= 1,
 		.max_speed_hz		= 500000,
 		.mode			= SPI_MODE_3,
+		.platform_data		= &overo_lcd35_pdata,
 	},
-#endif
 };
 
 static int __init overo_spi_init(void)
 {
 	overo_ads7846_init();
-	spi_register_board_info(overo_spi_board_info,
-			ARRAY_SIZE(overo_spi_board_info));
+
+	if (overo_use_lcd35) {
+		spi_register_board_info(overo_spi_board_info,
+				ARRAY_SIZE(overo_spi_board_info));
+	}
 	return 0;
 }
 
@@ -463,11 +499,13 @@ static void __init overo_init(void)
 {
 	int ret;
 
+	if (strstr(boot_command_line, "omapdss.def_disp=lcd35"))
+		overo_use_lcd35 = true;
+
 	regulator_register_fixed(0, dummy_supplies, ARRAY_SIZE(dummy_supplies));
 	omap3_mux_init(board_mux, OMAP_PACKAGE_CBB);
 	overo_i2c_init();
 	omap_hsmmc_init(mmc);
-	omap_display_init(&overo_dss_data);
 	omap_serial_init();
 	omap_sdrc_init(mt46h32m32lf6_sdrc_params,
 				  mt46h32m32lf6_sdrc_params);
@@ -484,6 +522,8 @@ static void __init overo_init(void)
 	overo_init_keys();
 	omap_twl4030_audio_init("overo", NULL);
 
+	overo_display_init();
+
 	/* Ensure SDRC pins are mux'd for self-refresh */
 	omap_mux_init_signal("sdrc_cke0", OMAP_PIN_OUTPUT);
 	omap_mux_init_signal("sdrc_cke1", OMAP_PIN_OUTPUT);
diff --git a/arch/arm/mach-omap2/board-rx51-peripherals.c b/arch/arm/mach-omap2/board-rx51-peripherals.c
index 9c2dd102fbbb..f6fe388af989 100644
--- a/arch/arm/mach-omap2/board-rx51-peripherals.c
+++ b/arch/arm/mach-omap2/board-rx51-peripherals.c
@@ -45,6 +45,8 @@
 #include <linux/platform_data/tsl2563.h>
 #include <linux/lis3lv02d.h>
 
+#include <video/omap-panel-data.h>
+
 #if defined(CONFIG_IR_RX51) || defined(CONFIG_IR_RX51_MODULE)
 #include <media/ir-rx51.h>
 #endif
@@ -165,38 +167,47 @@ static struct lp55xx_led_config rx51_lp5523_led_config[] = {
 		.name		= "lp5523:kb1",
 		.chan_nr	= 0,
 		.led_current	= 50,
+		.max_current	= 100,
 	}, {
 		.name		= "lp5523:kb2",
 		.chan_nr	= 1,
 		.led_current	= 50,
+		.max_current	= 100,
 	}, {
 		.name		= "lp5523:kb3",
 		.chan_nr	= 2,
 		.led_current	= 50,
+		.max_current	= 100,
 	}, {
 		.name		= "lp5523:kb4",
 		.chan_nr	= 3,
 		.led_current	= 50,
+		.max_current	= 100,
 	}, {
 		.name		= "lp5523:b",
 		.chan_nr	= 4,
 		.led_current	= 50,
+		.max_current	= 100,
 	}, {
 		.name		= "lp5523:g",
 		.chan_nr	= 5,
 		.led_current	= 50,
+		.max_current	= 100,
 	}, {
 		.name		= "lp5523:r",
 		.chan_nr	= 6,
 		.led_current	= 50,
+		.max_current	= 100,
 	}, {
 		.name		= "lp5523:kb5",
 		.chan_nr	= 7,
 		.led_current	= 50,
+		.max_current	= 100,
 	}, {
 		.name		= "lp5523:kb6",
 		.chan_nr	= 8,
 		.led_current	= 50,
+		.max_current	= 100,
 	}
 };
 
@@ -226,6 +237,15 @@ static struct lp55xx_platform_data rx51_lp5523_platform_data = {
 };
 #endif
 
+#define RX51_LCD_RESET_GPIO	90
+
+static struct panel_acx565akm_platform_data acx_pdata = {
+	.name		= "lcd",
+	.source		= "sdi.0",
+	.reset_gpio	= RX51_LCD_RESET_GPIO,
+	.datapairs	= 2,
+};
+
 static struct omap2_mcspi_device_config wl1251_mcspi_config = {
 	.turbo_mode	= 0,
 };
@@ -254,6 +274,7 @@ static struct spi_board_info rx51_peripherals_spi_board_info[] __initdata = {
 		.chip_select		= 2,
 		.max_speed_hz		= 6000000,
 		.controller_data	= &mipid_mcspi_config,
+		.platform_data		= &acx_pdata,
 	},
 	[RX51_SPI_TSC2005] = {
 		.modalias		= "tsc2005",
diff --git a/arch/arm/mach-omap2/board-rx51-video.c b/arch/arm/mach-omap2/board-rx51-video.c
index bdd1e3a179e1..43a90c8d6837 100644
--- a/arch/arm/mach-omap2/board-rx51-video.c
+++ b/arch/arm/mach-omap2/board-rx51-video.c
@@ -29,34 +29,21 @@
 
 #if defined(CONFIG_FB_OMAP2) || defined(CONFIG_FB_OMAP2_MODULE)
 
-static struct panel_acx565akm_data lcd_data = {
-	.reset_gpio	= RX51_LCD_RESET_GPIO,
+static struct connector_atv_platform_data rx51_tv_pdata = {
+	.name = "tv",
+	.source = "venc.0",
+	.connector_type = OMAP_DSS_VENC_TYPE_COMPOSITE,
+	.invert_polarity = false,
 };
 
-static struct omap_dss_device rx51_lcd_device = {
-	.name			= "lcd",
-	.driver_name		= "panel-acx565akm",
-	.type			= OMAP_DISPLAY_TYPE_SDI,
-	.phy.sdi.datapairs	= 2,
-	.data			= &lcd_data,
-};
-
-static struct omap_dss_device  rx51_tv_device = {
-	.name			= "tv",
-	.type			= OMAP_DISPLAY_TYPE_VENC,
-	.driver_name		= "venc",
-	.phy.venc.type	        = OMAP_DSS_VENC_TYPE_COMPOSITE,
-};
-
-static struct omap_dss_device *rx51_dss_devices[] = {
-	&rx51_lcd_device,
-	&rx51_tv_device,
+static struct platform_device rx51_tv_connector_device = {
+	.name                   = "connector-analog-tv",
+	.id                     = 0,
+	.dev.platform_data      = &rx51_tv_pdata,
 };
 
 static struct omap_dss_board_info rx51_dss_board_info = {
-	.num_devices	= ARRAY_SIZE(rx51_dss_devices),
-	.devices	= rx51_dss_devices,
-	.default_device	= &rx51_lcd_device,
+	.default_display_name = "lcd",
 };
 
 static int __init rx51_video_init(void)
@@ -71,6 +58,8 @@ static int __init rx51_video_init(void)
 
 	omap_display_init(&rx51_dss_board_info);
 
+	platform_device_register(&rx51_tv_connector_device);
+
 	return 0;
 }
 
diff --git a/arch/arm/mach-omap2/board-zoom-display.c b/arch/arm/mach-omap2/board-zoom-display.c
index c2a079cb76fc..3d8ecc1e05bd 100644
--- a/arch/arm/mach-omap2/board-zoom-display.c
+++ b/arch/arm/mach-omap2/board-zoom-display.c
@@ -25,32 +25,23 @@
 #define LCD_PANEL_RESET_GPIO_PILOT	55
 #define LCD_PANEL_QVGA_GPIO		56
 
-static struct panel_nec_nl8048_data zoom_lcd_data = {
-	/* res_gpio filled in code */
-	.qvga_gpio = LCD_PANEL_QVGA_GPIO,
-};
+static struct panel_nec_nl8048hl11_platform_data zoom_lcd_pdata = {
+	.name                   = "lcd",
+	.source                 = "dpi.0",
 
-static struct omap_dss_device zoom_lcd_device = {
-	.name			= "lcd",
-	.driver_name		= "NEC_8048_panel",
-	.type			= OMAP_DISPLAY_TYPE_DPI,
-	.phy.dpi.data_lines	= 24,
-	.data			= &zoom_lcd_data,
-};
+	.data_lines		= 24,
 
-static struct omap_dss_device *zoom_dss_devices[] = {
-	&zoom_lcd_device,
+	.res_gpio		= -1,	/* filled in code */
+	.qvga_gpio		= LCD_PANEL_QVGA_GPIO,
 };
 
 static struct omap_dss_board_info zoom_dss_data = {
-	.num_devices		= ARRAY_SIZE(zoom_dss_devices),
-	.devices		= zoom_dss_devices,
-	.default_device		= &zoom_lcd_device,
+	.default_display_name = "lcd",
 };
 
 static void __init zoom_lcd_panel_init(void)
 {
-	zoom_lcd_data.res_gpio = (omap_rev() > OMAP3430_REV_ES3_0) ?
+	zoom_lcd_pdata.res_gpio = (omap_rev() > OMAP3430_REV_ES3_0) ?
 			LCD_PANEL_RESET_GPIO_PROD :
 			LCD_PANEL_RESET_GPIO_PILOT;
 }
@@ -61,19 +52,20 @@ static struct omap2_mcspi_device_config dss_lcd_mcspi_config = {
 
 static struct spi_board_info nec_8048_spi_board_info[] __initdata = {
 	[0] = {
-		.modalias		= "nec_8048_spi",
+		.modalias		= "panel-nec-nl8048hl11",
 		.bus_num		= 1,
 		.chip_select		= 2,
 		.max_speed_hz		= 375000,
 		.controller_data	= &dss_lcd_mcspi_config,
+		.platform_data		= &zoom_lcd_pdata,
 	},
 };
 
 void __init zoom_display_init(void)
 {
 	omap_display_init(&zoom_dss_data);
+	zoom_lcd_panel_init();
 	spi_register_board_info(nec_8048_spi_board_info,
 				ARRAY_SIZE(nec_8048_spi_board_info));
-	zoom_lcd_panel_init();
 }
 
diff --git a/arch/arm/mach-omap2/cclock33xx_data.c b/arch/arm/mach-omap2/cclock33xx_data.c
index ba6534d7f155..865d30ee812f 100644
--- a/arch/arm/mach-omap2/cclock33xx_data.c
+++ b/arch/arm/mach-omap2/cclock33xx_data.c
@@ -421,6 +421,10 @@ static struct clk aes0_fck;
 DEFINE_STRUCT_CLK_HW_OMAP(aes0_fck, NULL);
 DEFINE_STRUCT_CLK(aes0_fck, dpll_core_ck_parents, clk_ops_null);
 
+static struct clk rng_fck;
+DEFINE_STRUCT_CLK_HW_OMAP(rng_fck, NULL);
+DEFINE_STRUCT_CLK(rng_fck, dpll_core_ck_parents, clk_ops_null);
+
 /*
  * Modules clock nodes
  *
@@ -966,6 +970,7 @@ static struct omap_clk am33xx_clks[] = {
 	CLK(NULL,	"smartreflex1_fck",	&smartreflex1_fck),
 	CLK(NULL,	"sha0_fck",		&sha0_fck),
 	CLK(NULL,	"aes0_fck",		&aes0_fck),
+	CLK(NULL,	"rng_fck",		&rng_fck),
 	CLK(NULL,	"timer1_fck",		&timer1_fck),
 	CLK(NULL,	"timer2_fck",		&timer2_fck),
 	CLK(NULL,	"timer3_fck",		&timer3_fck),
diff --git a/arch/arm/mach-omap2/cclock44xx_data.c b/arch/arm/mach-omap2/cclock44xx_data.c
index 88e37a474334..b237950eb8a3 100644
--- a/arch/arm/mach-omap2/cclock44xx_data.c
+++ b/arch/arm/mach-omap2/cclock44xx_data.c
@@ -1632,7 +1632,7 @@ static struct omap_clk omap44xx_clks[] = {
 	CLK(NULL,	"auxclk5_src_ck",		&auxclk5_src_ck),
 	CLK(NULL,	"auxclk5_ck",			&auxclk5_ck),
 	CLK(NULL,	"auxclkreq5_ck",		&auxclkreq5_ck),
-	CLK("omap-gpmc",	"fck",			&dummy_ck),
+	CLK("50000000.gpmc",	"fck",			&dummy_ck),
 	CLK("omap_i2c.1",	"ick",			&dummy_ck),
 	CLK("omap_i2c.2",	"ick",			&dummy_ck),
 	CLK("omap_i2c.3",	"ick",			&dummy_ck),
@@ -1707,6 +1707,18 @@ int __init omap4xxx_clk_init(void)
 	omap2_clk_disable_autoidle_all();
 
 	/*
+	 * A set rate of ABE DPLL inturn triggers a set rate of USB DPLL
+	 * when its in bypass. So always lock USB before ABE DPLL.
+	 */
+	/*
+	 * Lock USB DPLL on OMAP4 devices so that the L3INIT power
+	 * domain can transition to retention state when not in use.
+	 */
+	rc = clk_set_rate(&dpll_usb_ck, OMAP4_DPLL_USB_DEFFREQ);
+	if (rc)
+		pr_err("%s: failed to configure USB DPLL!\n", __func__);
+
+	/*
 	 * On OMAP4460 the ABE DPLL fails to turn on if in idle low-power
 	 * state when turning the ABE clock domain. Workaround this by
 	 * locking the ABE DPLL on boot.
@@ -1718,13 +1730,5 @@ int __init omap4xxx_clk_init(void)
 	if (rc)
 		pr_err("%s: failed to configure ABE DPLL!\n", __func__);
 
-	/*
-	 * Lock USB DPLL on OMAP4 devices so that the L3INIT power
-	 * domain can transition to retention state when not in use.
-	 */
-	rc = clk_set_rate(&dpll_usb_ck, OMAP4_DPLL_USB_DEFFREQ);
-	if (rc)
-		pr_err("%s: failed to configure USB DPLL!\n", __func__);
-
 	return 0;
 }
diff --git a/arch/arm/mach-omap2/clockdomain.h b/arch/arm/mach-omap2/clockdomain.h
index daeecf1b89fa..4b03394fa0c5 100644
--- a/arch/arm/mach-omap2/clockdomain.h
+++ b/arch/arm/mach-omap2/clockdomain.h
@@ -217,6 +217,7 @@ extern void __init omap3xxx_clockdomains_init(void);
 extern void __init am33xx_clockdomains_init(void);
 extern void __init omap44xx_clockdomains_init(void);
 extern void __init omap54xx_clockdomains_init(void);
+extern void __init dra7xx_clockdomains_init(void);
 
 extern void clkdm_add_autodeps(struct clockdomain *clkdm);
 extern void clkdm_del_autodeps(struct clockdomain *clkdm);
diff --git a/arch/arm/mach-omap2/clockdomains7xx_data.c b/arch/arm/mach-omap2/clockdomains7xx_data.c
new file mode 100644
index 000000000000..57d5df0c1fbd
--- /dev/null
+++ b/arch/arm/mach-omap2/clockdomains7xx_data.c
@@ -0,0 +1,740 @@
+/*
+ * DRA7xx Clock domains framework
+ *
+ * Copyright (C) 2009-2013 Texas Instruments, Inc.
+ * Copyright (C) 2009-2011 Nokia Corporation
+ *
+ * Generated by code originally written by:
+ * Abhijit Pagare (abhijitpagare@ti.com)
+ * Benoit Cousson (b-cousson@ti.com)
+ * Paul Walmsley (paul@pwsan.com)
+ *
+ * This file is automatically generated from the OMAP hardware databases.
+ * We respectfully ask that any modifications to this file be coordinated
+ * with the public linux-omap@vger.kernel.org mailing list and the
+ * authors above to ensure that the autogeneration scripts are kept
+ * up-to-date with the file contents.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/kernel.h>
+#include <linux/io.h>
+
+#include "clockdomain.h"
+#include "cm1_7xx.h"
+#include "cm2_7xx.h"
+
+#include "cm-regbits-7xx.h"
+#include "prm7xx.h"
+#include "prcm44xx.h"
+#include "prcm_mpu7xx.h"
+
+/* Static Dependencies for DRA7xx Clock Domains */
+
+static struct clkdm_dep cam_wkup_sleep_deps[] = {
+	{ .clkdm_name = "emif_clkdm" },
+	{ NULL },
+};
+
+static struct clkdm_dep dma_wkup_sleep_deps[] = {
+	{ .clkdm_name = "dss_clkdm" },
+	{ .clkdm_name = "emif_clkdm" },
+	{ .clkdm_name = "ipu_clkdm" },
+	{ .clkdm_name = "ipu1_clkdm" },
+	{ .clkdm_name = "ipu2_clkdm" },
+	{ .clkdm_name = "iva_clkdm" },
+	{ .clkdm_name = "l3init_clkdm" },
+	{ .clkdm_name = "l4cfg_clkdm" },
+	{ .clkdm_name = "l4per_clkdm" },
+	{ .clkdm_name = "l4per2_clkdm" },
+	{ .clkdm_name = "l4per3_clkdm" },
+	{ .clkdm_name = "l4sec_clkdm" },
+	{ .clkdm_name = "pcie_clkdm" },
+	{ .clkdm_name = "wkupaon_clkdm" },
+	{ NULL },
+};
+
+static struct clkdm_dep dsp1_wkup_sleep_deps[] = {
+	{ .clkdm_name = "atl_clkdm" },
+	{ .clkdm_name = "cam_clkdm" },
+	{ .clkdm_name = "dsp2_clkdm" },
+	{ .clkdm_name = "dss_clkdm" },
+	{ .clkdm_name = "emif_clkdm" },
+	{ .clkdm_name = "eve1_clkdm" },
+	{ .clkdm_name = "eve2_clkdm" },
+	{ .clkdm_name = "eve3_clkdm" },
+	{ .clkdm_name = "eve4_clkdm" },
+	{ .clkdm_name = "gmac_clkdm" },
+	{ .clkdm_name = "gpu_clkdm" },
+	{ .clkdm_name = "ipu_clkdm" },
+	{ .clkdm_name = "ipu1_clkdm" },
+	{ .clkdm_name = "ipu2_clkdm" },
+	{ .clkdm_name = "iva_clkdm" },
+	{ .clkdm_name = "l3init_clkdm" },
+	{ .clkdm_name = "l4per_clkdm" },
+	{ .clkdm_name = "l4per2_clkdm" },
+	{ .clkdm_name = "l4per3_clkdm" },
+	{ .clkdm_name = "l4sec_clkdm" },
+	{ .clkdm_name = "pcie_clkdm" },
+	{ .clkdm_name = "vpe_clkdm" },
+	{ .clkdm_name = "wkupaon_clkdm" },
+	{ NULL },
+};
+
+static struct clkdm_dep dsp2_wkup_sleep_deps[] = {
+	{ .clkdm_name = "atl_clkdm" },
+	{ .clkdm_name = "cam_clkdm" },
+	{ .clkdm_name = "dsp1_clkdm" },
+	{ .clkdm_name = "dss_clkdm" },
+	{ .clkdm_name = "emif_clkdm" },
+	{ .clkdm_name = "eve1_clkdm" },
+	{ .clkdm_name = "eve2_clkdm" },
+	{ .clkdm_name = "eve3_clkdm" },
+	{ .clkdm_name = "eve4_clkdm" },
+	{ .clkdm_name = "gmac_clkdm" },
+	{ .clkdm_name = "gpu_clkdm" },
+	{ .clkdm_name = "ipu_clkdm" },
+	{ .clkdm_name = "ipu1_clkdm" },
+	{ .clkdm_name = "ipu2_clkdm" },
+	{ .clkdm_name = "iva_clkdm" },
+	{ .clkdm_name = "l3init_clkdm" },
+	{ .clkdm_name = "l4per_clkdm" },
+	{ .clkdm_name = "l4per2_clkdm" },
+	{ .clkdm_name = "l4per3_clkdm" },
+	{ .clkdm_name = "l4sec_clkdm" },
+	{ .clkdm_name = "pcie_clkdm" },
+	{ .clkdm_name = "vpe_clkdm" },
+	{ .clkdm_name = "wkupaon_clkdm" },
+	{ NULL },
+};
+
+static struct clkdm_dep dss_wkup_sleep_deps[] = {
+	{ .clkdm_name = "emif_clkdm" },
+	{ .clkdm_name = "iva_clkdm" },
+	{ NULL },
+};
+
+static struct clkdm_dep eve1_wkup_sleep_deps[] = {
+	{ .clkdm_name = "emif_clkdm" },
+	{ .clkdm_name = "eve2_clkdm" },
+	{ .clkdm_name = "eve3_clkdm" },
+	{ .clkdm_name = "eve4_clkdm" },
+	{ .clkdm_name = "iva_clkdm" },
+	{ NULL },
+};
+
+static struct clkdm_dep eve2_wkup_sleep_deps[] = {
+	{ .clkdm_name = "emif_clkdm" },
+	{ .clkdm_name = "eve1_clkdm" },
+	{ .clkdm_name = "eve3_clkdm" },
+	{ .clkdm_name = "eve4_clkdm" },
+	{ .clkdm_name = "iva_clkdm" },
+	{ NULL },
+};
+
+static struct clkdm_dep eve3_wkup_sleep_deps[] = {
+	{ .clkdm_name = "emif_clkdm" },
+	{ .clkdm_name = "eve1_clkdm" },
+	{ .clkdm_name = "eve2_clkdm" },
+	{ .clkdm_name = "eve4_clkdm" },
+	{ .clkdm_name = "iva_clkdm" },
+	{ NULL },
+};
+
+static struct clkdm_dep eve4_wkup_sleep_deps[] = {
+	{ .clkdm_name = "emif_clkdm" },
+	{ .clkdm_name = "eve1_clkdm" },
+	{ .clkdm_name = "eve2_clkdm" },
+	{ .clkdm_name = "eve3_clkdm" },
+	{ .clkdm_name = "iva_clkdm" },
+	{ NULL },
+};
+
+static struct clkdm_dep gmac_wkup_sleep_deps[] = {
+	{ .clkdm_name = "emif_clkdm" },
+	{ .clkdm_name = "l4per2_clkdm" },
+	{ NULL },
+};
+
+static struct clkdm_dep gpu_wkup_sleep_deps[] = {
+	{ .clkdm_name = "emif_clkdm" },
+	{ .clkdm_name = "iva_clkdm" },
+	{ NULL },
+};
+
+static struct clkdm_dep ipu1_wkup_sleep_deps[] = {
+	{ .clkdm_name = "atl_clkdm" },
+	{ .clkdm_name = "dsp1_clkdm" },
+	{ .clkdm_name = "dsp2_clkdm" },
+	{ .clkdm_name = "dss_clkdm" },
+	{ .clkdm_name = "emif_clkdm" },
+	{ .clkdm_name = "eve1_clkdm" },
+	{ .clkdm_name = "eve2_clkdm" },
+	{ .clkdm_name = "eve3_clkdm" },
+	{ .clkdm_name = "eve4_clkdm" },
+	{ .clkdm_name = "gmac_clkdm" },
+	{ .clkdm_name = "gpu_clkdm" },
+	{ .clkdm_name = "ipu_clkdm" },
+	{ .clkdm_name = "ipu2_clkdm" },
+	{ .clkdm_name = "iva_clkdm" },
+	{ .clkdm_name = "l3init_clkdm" },
+	{ .clkdm_name = "l3main1_clkdm" },
+	{ .clkdm_name = "l4cfg_clkdm" },
+	{ .clkdm_name = "l4per_clkdm" },
+	{ .clkdm_name = "l4per2_clkdm" },
+	{ .clkdm_name = "l4per3_clkdm" },
+	{ .clkdm_name = "l4sec_clkdm" },
+	{ .clkdm_name = "pcie_clkdm" },
+	{ .clkdm_name = "vpe_clkdm" },
+	{ .clkdm_name = "wkupaon_clkdm" },
+	{ NULL },
+};
+
+static struct clkdm_dep ipu2_wkup_sleep_deps[] = {
+	{ .clkdm_name = "atl_clkdm" },
+	{ .clkdm_name = "dsp1_clkdm" },
+	{ .clkdm_name = "dsp2_clkdm" },
+	{ .clkdm_name = "dss_clkdm" },
+	{ .clkdm_name = "emif_clkdm" },
+	{ .clkdm_name = "eve1_clkdm" },
+	{ .clkdm_name = "eve2_clkdm" },
+	{ .clkdm_name = "eve3_clkdm" },
+	{ .clkdm_name = "eve4_clkdm" },
+	{ .clkdm_name = "gmac_clkdm" },
+	{ .clkdm_name = "gpu_clkdm" },
+	{ .clkdm_name = "ipu_clkdm" },
+	{ .clkdm_name = "ipu1_clkdm" },
+	{ .clkdm_name = "iva_clkdm" },
+	{ .clkdm_name = "l3init_clkdm" },
+	{ .clkdm_name = "l3main1_clkdm" },
+	{ .clkdm_name = "l4cfg_clkdm" },
+	{ .clkdm_name = "l4per_clkdm" },
+	{ .clkdm_name = "l4per2_clkdm" },
+	{ .clkdm_name = "l4per3_clkdm" },
+	{ .clkdm_name = "l4sec_clkdm" },
+	{ .clkdm_name = "pcie_clkdm" },
+	{ .clkdm_name = "vpe_clkdm" },
+	{ .clkdm_name = "wkupaon_clkdm" },
+	{ NULL },
+};
+
+static struct clkdm_dep iva_wkup_sleep_deps[] = {
+	{ .clkdm_name = "emif_clkdm" },
+	{ NULL },
+};
+
+static struct clkdm_dep l3init_wkup_sleep_deps[] = {
+	{ .clkdm_name = "emif_clkdm" },
+	{ .clkdm_name = "iva_clkdm" },
+	{ .clkdm_name = "l4cfg_clkdm" },
+	{ .clkdm_name = "l4per_clkdm" },
+	{ .clkdm_name = "l4per3_clkdm" },
+	{ .clkdm_name = "l4sec_clkdm" },
+	{ .clkdm_name = "wkupaon_clkdm" },
+	{ NULL },
+};
+
+static struct clkdm_dep l4per2_wkup_sleep_deps[] = {
+	{ .clkdm_name = "dsp1_clkdm" },
+	{ .clkdm_name = "dsp2_clkdm" },
+	{ .clkdm_name = "ipu1_clkdm" },
+	{ .clkdm_name = "ipu2_clkdm" },
+	{ NULL },
+};
+
+static struct clkdm_dep l4sec_wkup_sleep_deps[] = {
+	{ .clkdm_name = "emif_clkdm" },
+	{ .clkdm_name = "l4per_clkdm" },
+	{ NULL },
+};
+
+static struct clkdm_dep mpu_wkup_sleep_deps[] = {
+	{ .clkdm_name = "cam_clkdm" },
+	{ .clkdm_name = "dsp1_clkdm" },
+	{ .clkdm_name = "dsp2_clkdm" },
+	{ .clkdm_name = "dss_clkdm" },
+	{ .clkdm_name = "emif_clkdm" },
+	{ .clkdm_name = "eve1_clkdm" },
+	{ .clkdm_name = "eve2_clkdm" },
+	{ .clkdm_name = "eve3_clkdm" },
+	{ .clkdm_name = "eve4_clkdm" },
+	{ .clkdm_name = "gmac_clkdm" },
+	{ .clkdm_name = "gpu_clkdm" },
+	{ .clkdm_name = "ipu_clkdm" },
+	{ .clkdm_name = "ipu1_clkdm" },
+	{ .clkdm_name = "ipu2_clkdm" },
+	{ .clkdm_name = "iva_clkdm" },
+	{ .clkdm_name = "l3init_clkdm" },
+	{ .clkdm_name = "l3main1_clkdm" },
+	{ .clkdm_name = "l4cfg_clkdm" },
+	{ .clkdm_name = "l4per_clkdm" },
+	{ .clkdm_name = "l4per2_clkdm" },
+	{ .clkdm_name = "l4per3_clkdm" },
+	{ .clkdm_name = "l4sec_clkdm" },
+	{ .clkdm_name = "pcie_clkdm" },
+	{ .clkdm_name = "vpe_clkdm" },
+	{ .clkdm_name = "wkupaon_clkdm" },
+	{ NULL },
+};
+
+static struct clkdm_dep pcie_wkup_sleep_deps[] = {
+	{ .clkdm_name = "atl_clkdm" },
+	{ .clkdm_name = "cam_clkdm" },
+	{ .clkdm_name = "dsp1_clkdm" },
+	{ .clkdm_name = "dsp2_clkdm" },
+	{ .clkdm_name = "dss_clkdm" },
+	{ .clkdm_name = "emif_clkdm" },
+	{ .clkdm_name = "eve1_clkdm" },
+	{ .clkdm_name = "eve2_clkdm" },
+	{ .clkdm_name = "eve3_clkdm" },
+	{ .clkdm_name = "eve4_clkdm" },
+	{ .clkdm_name = "gmac_clkdm" },
+	{ .clkdm_name = "gpu_clkdm" },
+	{ .clkdm_name = "ipu_clkdm" },
+	{ .clkdm_name = "ipu1_clkdm" },
+	{ .clkdm_name = "iva_clkdm" },
+	{ .clkdm_name = "l3init_clkdm" },
+	{ .clkdm_name = "l4cfg_clkdm" },
+	{ .clkdm_name = "l4per_clkdm" },
+	{ .clkdm_name = "l4per2_clkdm" },
+	{ .clkdm_name = "l4per3_clkdm" },
+	{ .clkdm_name = "l4sec_clkdm" },
+	{ .clkdm_name = "vpe_clkdm" },
+	{ NULL },
+};
+
+static struct clkdm_dep vpe_wkup_sleep_deps[] = {
+	{ .clkdm_name = "emif_clkdm" },
+	{ .clkdm_name = "l4per3_clkdm" },
+	{ NULL },
+};
+
+static struct clockdomain l4per3_7xx_clkdm = {
+	.name		  = "l4per3_clkdm",
+	.pwrdm		  = { .name = "l4per_pwrdm" },
+	.prcm_partition	  = DRA7XX_CM_CORE_PARTITION,
+	.cm_inst	  = DRA7XX_CM_CORE_L4PER_INST,
+	.clkdm_offs	  = DRA7XX_CM_CORE_L4PER_L4PER3_CDOFFS,
+	.dep_bit	  = DRA7XX_L4PER3_STATDEP_SHIFT,
+	.flags		  = CLKDM_CAN_HWSUP_SWSUP,
+};
+
+static struct clockdomain l4per2_7xx_clkdm = {
+	.name		  = "l4per2_clkdm",
+	.pwrdm		  = { .name = "l4per_pwrdm" },
+	.prcm_partition	  = DRA7XX_CM_CORE_PARTITION,
+	.cm_inst	  = DRA7XX_CM_CORE_L4PER_INST,
+	.clkdm_offs	  = DRA7XX_CM_CORE_L4PER_L4PER2_CDOFFS,
+	.dep_bit	  = DRA7XX_L4PER2_STATDEP_SHIFT,
+	.wkdep_srcs	  = l4per2_wkup_sleep_deps,
+	.sleepdep_srcs	  = l4per2_wkup_sleep_deps,
+	.flags		  = CLKDM_CAN_HWSUP_SWSUP,
+};
+
+static struct clockdomain mpu0_7xx_clkdm = {
+	.name		  = "mpu0_clkdm",
+	.pwrdm		  = { .name = "cpu0_pwrdm" },
+	.prcm_partition	  = DRA7XX_MPU_PRCM_PARTITION,
+	.cm_inst	  = DRA7XX_MPU_PRCM_CM_C0_INST,
+	.clkdm_offs	  = DRA7XX_MPU_PRCM_CM_C0_CPU0_CDOFFS,
+	.flags		  = CLKDM_CAN_FORCE_WAKEUP | CLKDM_CAN_HWSUP,
+};
+
+static struct clockdomain iva_7xx_clkdm = {
+	.name		  = "iva_clkdm",
+	.pwrdm		  = { .name = "iva_pwrdm" },
+	.prcm_partition	  = DRA7XX_CM_CORE_PARTITION,
+	.cm_inst	  = DRA7XX_CM_CORE_IVA_INST,
+	.clkdm_offs	  = DRA7XX_CM_CORE_IVA_IVA_CDOFFS,
+	.dep_bit	  = DRA7XX_IVA_STATDEP_SHIFT,
+	.wkdep_srcs	  = iva_wkup_sleep_deps,
+	.sleepdep_srcs	  = iva_wkup_sleep_deps,
+	.flags		  = CLKDM_CAN_HWSUP_SWSUP,
+};
+
+static struct clockdomain coreaon_7xx_clkdm = {
+	.name		  = "coreaon_clkdm",
+	.pwrdm		  = { .name = "coreaon_pwrdm" },
+	.prcm_partition	  = DRA7XX_CM_CORE_PARTITION,
+	.cm_inst	  = DRA7XX_CM_CORE_COREAON_INST,
+	.clkdm_offs	  = DRA7XX_CM_CORE_COREAON_COREAON_CDOFFS,
+	.flags		  = CLKDM_CAN_FORCE_WAKEUP | CLKDM_CAN_HWSUP,
+};
+
+static struct clockdomain ipu1_7xx_clkdm = {
+	.name		  = "ipu1_clkdm",
+	.pwrdm		  = { .name = "ipu_pwrdm" },
+	.prcm_partition	  = DRA7XX_CM_CORE_AON_PARTITION,
+	.cm_inst	  = DRA7XX_CM_CORE_AON_IPU_INST,
+	.clkdm_offs	  = DRA7XX_CM_CORE_AON_IPU_IPU1_CDOFFS,
+	.dep_bit	  = DRA7XX_IPU1_STATDEP_SHIFT,
+	.wkdep_srcs	  = ipu1_wkup_sleep_deps,
+	.sleepdep_srcs	  = ipu1_wkup_sleep_deps,
+	.flags		  = CLKDM_CAN_HWSUP_SWSUP,
+};
+
+static struct clockdomain ipu2_7xx_clkdm = {
+	.name		  = "ipu2_clkdm",
+	.pwrdm		  = { .name = "core_pwrdm" },
+	.prcm_partition	  = DRA7XX_CM_CORE_PARTITION,
+	.cm_inst	  = DRA7XX_CM_CORE_CORE_INST,
+	.clkdm_offs	  = DRA7XX_CM_CORE_CORE_IPU2_CDOFFS,
+	.dep_bit	  = DRA7XX_IPU2_STATDEP_SHIFT,
+	.wkdep_srcs	  = ipu2_wkup_sleep_deps,
+	.sleepdep_srcs	  = ipu2_wkup_sleep_deps,
+	.flags		  = CLKDM_CAN_HWSUP_SWSUP,
+};
+
+static struct clockdomain l3init_7xx_clkdm = {
+	.name		  = "l3init_clkdm",
+	.pwrdm		  = { .name = "l3init_pwrdm" },
+	.prcm_partition	  = DRA7XX_CM_CORE_PARTITION,
+	.cm_inst	  = DRA7XX_CM_CORE_L3INIT_INST,
+	.clkdm_offs	  = DRA7XX_CM_CORE_L3INIT_L3INIT_CDOFFS,
+	.dep_bit	  = DRA7XX_L3INIT_STATDEP_SHIFT,
+	.wkdep_srcs	  = l3init_wkup_sleep_deps,
+	.sleepdep_srcs	  = l3init_wkup_sleep_deps,
+	.flags		  = CLKDM_CAN_HWSUP_SWSUP,
+};
+
+static struct clockdomain l4sec_7xx_clkdm = {
+	.name		  = "l4sec_clkdm",
+	.pwrdm		  = { .name = "l4per_pwrdm" },
+	.prcm_partition	  = DRA7XX_CM_CORE_PARTITION,
+	.cm_inst	  = DRA7XX_CM_CORE_L4PER_INST,
+	.clkdm_offs	  = DRA7XX_CM_CORE_L4PER_L4SEC_CDOFFS,
+	.dep_bit	  = DRA7XX_L4SEC_STATDEP_SHIFT,
+	.wkdep_srcs	  = l4sec_wkup_sleep_deps,
+	.sleepdep_srcs	  = l4sec_wkup_sleep_deps,
+	.flags		  = CLKDM_CAN_HWSUP_SWSUP,
+};
+
+static struct clockdomain l3main1_7xx_clkdm = {
+	.name		  = "l3main1_clkdm",
+	.pwrdm		  = { .name = "core_pwrdm" },
+	.prcm_partition	  = DRA7XX_CM_CORE_PARTITION,
+	.cm_inst	  = DRA7XX_CM_CORE_CORE_INST,
+	.clkdm_offs	  = DRA7XX_CM_CORE_CORE_L3MAIN1_CDOFFS,
+	.dep_bit	  = DRA7XX_L3MAIN1_STATDEP_SHIFT,
+	.flags		  = CLKDM_CAN_HWSUP,
+};
+
+static struct clockdomain vpe_7xx_clkdm = {
+	.name		  = "vpe_clkdm",
+	.pwrdm		  = { .name = "vpe_pwrdm" },
+	.prcm_partition	  = DRA7XX_CM_CORE_AON_PARTITION,
+	.cm_inst	  = DRA7XX_CM_CORE_AON_VPE_INST,
+	.clkdm_offs	  = DRA7XX_CM_CORE_AON_VPE_VPE_CDOFFS,
+	.dep_bit	  = DRA7XX_VPE_STATDEP_SHIFT,
+	.wkdep_srcs	  = vpe_wkup_sleep_deps,
+	.sleepdep_srcs	  = vpe_wkup_sleep_deps,
+	.flags		  = CLKDM_CAN_HWSUP_SWSUP,
+};
+
+static struct clockdomain mpu_7xx_clkdm = {
+	.name		  = "mpu_clkdm",
+	.pwrdm		  = { .name = "mpu_pwrdm" },
+	.prcm_partition	  = DRA7XX_CM_CORE_AON_PARTITION,
+	.cm_inst	  = DRA7XX_CM_CORE_AON_MPU_INST,
+	.clkdm_offs	  = DRA7XX_CM_CORE_AON_MPU_MPU_CDOFFS,
+	.wkdep_srcs	  = mpu_wkup_sleep_deps,
+	.sleepdep_srcs	  = mpu_wkup_sleep_deps,
+	.flags		  = CLKDM_CAN_FORCE_WAKEUP | CLKDM_CAN_HWSUP,
+};
+
+static struct clockdomain custefuse_7xx_clkdm = {
+	.name		  = "custefuse_clkdm",
+	.pwrdm		  = { .name = "custefuse_pwrdm" },
+	.prcm_partition	  = DRA7XX_CM_CORE_PARTITION,
+	.cm_inst	  = DRA7XX_CM_CORE_CUSTEFUSE_INST,
+	.clkdm_offs	  = DRA7XX_CM_CORE_CUSTEFUSE_CUSTEFUSE_CDOFFS,
+	.flags		  = CLKDM_CAN_FORCE_WAKEUP | CLKDM_CAN_HWSUP,
+};
+
+static struct clockdomain ipu_7xx_clkdm = {
+	.name		  = "ipu_clkdm",
+	.pwrdm		  = { .name = "ipu_pwrdm" },
+	.prcm_partition	  = DRA7XX_CM_CORE_AON_PARTITION,
+	.cm_inst	  = DRA7XX_CM_CORE_AON_IPU_INST,
+	.clkdm_offs	  = DRA7XX_CM_CORE_AON_IPU_IPU_CDOFFS,
+	.dep_bit	  = DRA7XX_IPU_STATDEP_SHIFT,
+	.flags		  = CLKDM_CAN_HWSUP_SWSUP,
+};
+
+static struct clockdomain mpu1_7xx_clkdm = {
+	.name		  = "mpu1_clkdm",
+	.pwrdm		  = { .name = "cpu1_pwrdm" },
+	.prcm_partition	  = DRA7XX_MPU_PRCM_PARTITION,
+	.cm_inst	  = DRA7XX_MPU_PRCM_CM_C1_INST,
+	.clkdm_offs	  = DRA7XX_MPU_PRCM_CM_C1_CPU1_CDOFFS,
+	.flags		  = CLKDM_CAN_FORCE_WAKEUP | CLKDM_CAN_HWSUP,
+};
+
+static struct clockdomain gmac_7xx_clkdm = {
+	.name		  = "gmac_clkdm",
+	.pwrdm		  = { .name = "l3init_pwrdm" },
+	.prcm_partition	  = DRA7XX_CM_CORE_PARTITION,
+	.cm_inst	  = DRA7XX_CM_CORE_L3INIT_INST,
+	.clkdm_offs	  = DRA7XX_CM_CORE_L3INIT_GMAC_CDOFFS,
+	.dep_bit	  = DRA7XX_GMAC_STATDEP_SHIFT,
+	.wkdep_srcs	  = gmac_wkup_sleep_deps,
+	.sleepdep_srcs	  = gmac_wkup_sleep_deps,
+	.flags		  = CLKDM_CAN_HWSUP_SWSUP,
+};
+
+static struct clockdomain l4cfg_7xx_clkdm = {
+	.name		  = "l4cfg_clkdm",
+	.pwrdm		  = { .name = "core_pwrdm" },
+	.prcm_partition	  = DRA7XX_CM_CORE_PARTITION,
+	.cm_inst	  = DRA7XX_CM_CORE_CORE_INST,
+	.clkdm_offs	  = DRA7XX_CM_CORE_CORE_L4CFG_CDOFFS,
+	.dep_bit	  = DRA7XX_L4CFG_STATDEP_SHIFT,
+	.flags		  = CLKDM_CAN_HWSUP,
+};
+
+static struct clockdomain dma_7xx_clkdm = {
+	.name		  = "dma_clkdm",
+	.pwrdm		  = { .name = "core_pwrdm" },
+	.prcm_partition	  = DRA7XX_CM_CORE_PARTITION,
+	.cm_inst	  = DRA7XX_CM_CORE_CORE_INST,
+	.clkdm_offs	  = DRA7XX_CM_CORE_CORE_DMA_CDOFFS,
+	.wkdep_srcs	  = dma_wkup_sleep_deps,
+	.sleepdep_srcs	  = dma_wkup_sleep_deps,
+	.flags		  = CLKDM_CAN_FORCE_WAKEUP | CLKDM_CAN_HWSUP,
+};
+
+static struct clockdomain rtc_7xx_clkdm = {
+	.name		  = "rtc_clkdm",
+	.pwrdm		  = { .name = "rtc_pwrdm" },
+	.prcm_partition	  = DRA7XX_CM_CORE_AON_PARTITION,
+	.cm_inst	  = DRA7XX_CM_CORE_AON_RTC_INST,
+	.clkdm_offs	  = DRA7XX_CM_CORE_AON_RTC_RTC_CDOFFS,
+	.flags		  = CLKDM_CAN_FORCE_WAKEUP | CLKDM_CAN_HWSUP,
+};
+
+static struct clockdomain pcie_7xx_clkdm = {
+	.name		  = "pcie_clkdm",
+	.pwrdm		  = { .name = "l3init_pwrdm" },
+	.prcm_partition	  = DRA7XX_CM_CORE_PARTITION,
+	.cm_inst	  = DRA7XX_CM_CORE_L3INIT_INST,
+	.clkdm_offs	  = DRA7XX_CM_CORE_L3INIT_PCIE_CDOFFS,
+	.dep_bit	  = DRA7XX_PCIE_STATDEP_SHIFT,
+	.wkdep_srcs	  = pcie_wkup_sleep_deps,
+	.sleepdep_srcs	  = pcie_wkup_sleep_deps,
+	.flags		  = CLKDM_CAN_HWSUP_SWSUP,
+};
+
+static struct clockdomain atl_7xx_clkdm = {
+	.name		  = "atl_clkdm",
+	.pwrdm		  = { .name = "core_pwrdm" },
+	.prcm_partition	  = DRA7XX_CM_CORE_PARTITION,
+	.cm_inst	  = DRA7XX_CM_CORE_CORE_INST,
+	.clkdm_offs	  = DRA7XX_CM_CORE_CORE_ATL_CDOFFS,
+	.dep_bit	  = DRA7XX_ATL_STATDEP_SHIFT,
+	.flags		  = CLKDM_CAN_FORCE_WAKEUP | CLKDM_CAN_HWSUP,
+};
+
+static struct clockdomain l3instr_7xx_clkdm = {
+	.name		  = "l3instr_clkdm",
+	.pwrdm		  = { .name = "core_pwrdm" },
+	.prcm_partition	  = DRA7XX_CM_CORE_PARTITION,
+	.cm_inst	  = DRA7XX_CM_CORE_CORE_INST,
+	.clkdm_offs	  = DRA7XX_CM_CORE_CORE_L3INSTR_CDOFFS,
+};
+
+static struct clockdomain dss_7xx_clkdm = {
+	.name		  = "dss_clkdm",
+	.pwrdm		  = { .name = "dss_pwrdm" },
+	.prcm_partition	  = DRA7XX_CM_CORE_PARTITION,
+	.cm_inst	  = DRA7XX_CM_CORE_DSS_INST,
+	.clkdm_offs	  = DRA7XX_CM_CORE_DSS_DSS_CDOFFS,
+	.dep_bit	  = DRA7XX_DSS_STATDEP_SHIFT,
+	.wkdep_srcs	  = dss_wkup_sleep_deps,
+	.sleepdep_srcs	  = dss_wkup_sleep_deps,
+	.flags		  = CLKDM_CAN_HWSUP_SWSUP,
+};
+
+static struct clockdomain emif_7xx_clkdm = {
+	.name		  = "emif_clkdm",
+	.pwrdm		  = { .name = "core_pwrdm" },
+	.prcm_partition	  = DRA7XX_CM_CORE_PARTITION,
+	.cm_inst	  = DRA7XX_CM_CORE_CORE_INST,
+	.clkdm_offs	  = DRA7XX_CM_CORE_CORE_EMIF_CDOFFS,
+	.dep_bit	  = DRA7XX_EMIF_STATDEP_SHIFT,
+	.flags		  = CLKDM_CAN_FORCE_WAKEUP | CLKDM_CAN_HWSUP,
+};
+
+static struct clockdomain emu_7xx_clkdm = {
+	.name		  = "emu_clkdm",
+	.pwrdm		  = { .name = "emu_pwrdm" },
+	.prcm_partition	  = DRA7XX_PRM_PARTITION,
+	.cm_inst	  = DRA7XX_PRM_EMU_CM_INST,
+	.clkdm_offs	  = DRA7XX_PRM_EMU_CM_EMU_CDOFFS,
+	.flags		  = CLKDM_CAN_FORCE_WAKEUP | CLKDM_CAN_HWSUP,
+};
+
+static struct clockdomain dsp2_7xx_clkdm = {
+	.name		  = "dsp2_clkdm",
+	.pwrdm		  = { .name = "dsp2_pwrdm" },
+	.prcm_partition	  = DRA7XX_CM_CORE_AON_PARTITION,
+	.cm_inst	  = DRA7XX_CM_CORE_AON_DSP2_INST,
+	.clkdm_offs	  = DRA7XX_CM_CORE_AON_DSP2_DSP2_CDOFFS,
+	.dep_bit	  = DRA7XX_DSP2_STATDEP_SHIFT,
+	.wkdep_srcs	  = dsp2_wkup_sleep_deps,
+	.sleepdep_srcs	  = dsp2_wkup_sleep_deps,
+	.flags		  = CLKDM_CAN_HWSUP_SWSUP,
+};
+
+static struct clockdomain dsp1_7xx_clkdm = {
+	.name		  = "dsp1_clkdm",
+	.pwrdm		  = { .name = "dsp1_pwrdm" },
+	.prcm_partition	  = DRA7XX_CM_CORE_AON_PARTITION,
+	.cm_inst	  = DRA7XX_CM_CORE_AON_DSP1_INST,
+	.clkdm_offs	  = DRA7XX_CM_CORE_AON_DSP1_DSP1_CDOFFS,
+	.dep_bit	  = DRA7XX_DSP1_STATDEP_SHIFT,
+	.wkdep_srcs	  = dsp1_wkup_sleep_deps,
+	.sleepdep_srcs	  = dsp1_wkup_sleep_deps,
+	.flags		  = CLKDM_CAN_HWSUP_SWSUP,
+};
+
+static struct clockdomain cam_7xx_clkdm = {
+	.name		  = "cam_clkdm",
+	.pwrdm		  = { .name = "cam_pwrdm" },
+	.prcm_partition	  = DRA7XX_CM_CORE_PARTITION,
+	.cm_inst	  = DRA7XX_CM_CORE_CAM_INST,
+	.clkdm_offs	  = DRA7XX_CM_CORE_CAM_CAM_CDOFFS,
+	.dep_bit	  = DRA7XX_CAM_STATDEP_SHIFT,
+	.wkdep_srcs	  = cam_wkup_sleep_deps,
+	.sleepdep_srcs	  = cam_wkup_sleep_deps,
+	.flags		  = CLKDM_CAN_HWSUP_SWSUP,
+};
+
+static struct clockdomain l4per_7xx_clkdm = {
+	.name		  = "l4per_clkdm",
+	.pwrdm		  = { .name = "l4per_pwrdm" },
+	.prcm_partition	  = DRA7XX_CM_CORE_PARTITION,
+	.cm_inst	  = DRA7XX_CM_CORE_L4PER_INST,
+	.clkdm_offs	  = DRA7XX_CM_CORE_L4PER_L4PER_CDOFFS,
+	.dep_bit	  = DRA7XX_L4PER_STATDEP_SHIFT,
+	.flags		  = CLKDM_CAN_HWSUP_SWSUP,
+};
+
+static struct clockdomain gpu_7xx_clkdm = {
+	.name		  = "gpu_clkdm",
+	.pwrdm		  = { .name = "gpu_pwrdm" },
+	.prcm_partition	  = DRA7XX_CM_CORE_PARTITION,
+	.cm_inst	  = DRA7XX_CM_CORE_GPU_INST,
+	.clkdm_offs	  = DRA7XX_CM_CORE_GPU_GPU_CDOFFS,
+	.dep_bit	  = DRA7XX_GPU_STATDEP_SHIFT,
+	.wkdep_srcs	  = gpu_wkup_sleep_deps,
+	.sleepdep_srcs	  = gpu_wkup_sleep_deps,
+	.flags		  = CLKDM_CAN_HWSUP_SWSUP,
+};
+
+static struct clockdomain eve4_7xx_clkdm = {
+	.name		  = "eve4_clkdm",
+	.pwrdm		  = { .name = "eve4_pwrdm" },
+	.prcm_partition	  = DRA7XX_CM_CORE_AON_PARTITION,
+	.cm_inst	  = DRA7XX_CM_CORE_AON_EVE4_INST,
+	.clkdm_offs	  = DRA7XX_CM_CORE_AON_EVE4_EVE4_CDOFFS,
+	.dep_bit	  = DRA7XX_EVE4_STATDEP_SHIFT,
+	.wkdep_srcs	  = eve4_wkup_sleep_deps,
+	.sleepdep_srcs	  = eve4_wkup_sleep_deps,
+	.flags		  = CLKDM_CAN_HWSUP_SWSUP,
+};
+
+static struct clockdomain eve2_7xx_clkdm = {
+	.name		  = "eve2_clkdm",
+	.pwrdm		  = { .name = "eve2_pwrdm" },
+	.prcm_partition	  = DRA7XX_CM_CORE_AON_PARTITION,
+	.cm_inst	  = DRA7XX_CM_CORE_AON_EVE2_INST,
+	.clkdm_offs	  = DRA7XX_CM_CORE_AON_EVE2_EVE2_CDOFFS,
+	.dep_bit	  = DRA7XX_EVE2_STATDEP_SHIFT,
+	.wkdep_srcs	  = eve2_wkup_sleep_deps,
+	.sleepdep_srcs	  = eve2_wkup_sleep_deps,
+	.flags		  = CLKDM_CAN_HWSUP_SWSUP,
+};
+
+static struct clockdomain eve3_7xx_clkdm = {
+	.name		  = "eve3_clkdm",
+	.pwrdm		  = { .name = "eve3_pwrdm" },
+	.prcm_partition	  = DRA7XX_CM_CORE_AON_PARTITION,
+	.cm_inst	  = DRA7XX_CM_CORE_AON_EVE3_INST,
+	.clkdm_offs	  = DRA7XX_CM_CORE_AON_EVE3_EVE3_CDOFFS,
+	.dep_bit	  = DRA7XX_EVE3_STATDEP_SHIFT,
+	.wkdep_srcs	  = eve3_wkup_sleep_deps,
+	.sleepdep_srcs	  = eve3_wkup_sleep_deps,
+	.flags		  = CLKDM_CAN_HWSUP_SWSUP,
+};
+
+static struct clockdomain wkupaon_7xx_clkdm = {
+	.name		  = "wkupaon_clkdm",
+	.pwrdm		  = { .name = "wkupaon_pwrdm" },
+	.prcm_partition	  = DRA7XX_PRM_PARTITION,
+	.cm_inst	  = DRA7XX_PRM_WKUPAON_CM_INST,
+	.clkdm_offs	  = DRA7XX_PRM_WKUPAON_CM_WKUPAON_CDOFFS,
+	.dep_bit	  = DRA7XX_WKUPAON_STATDEP_SHIFT,
+	.flags		  = CLKDM_CAN_FORCE_WAKEUP | CLKDM_CAN_HWSUP,
+};
+
+static struct clockdomain eve1_7xx_clkdm = {
+	.name		  = "eve1_clkdm",
+	.pwrdm		  = { .name = "eve1_pwrdm" },
+	.prcm_partition	  = DRA7XX_CM_CORE_AON_PARTITION,
+	.cm_inst	  = DRA7XX_CM_CORE_AON_EVE1_INST,
+	.clkdm_offs	  = DRA7XX_CM_CORE_AON_EVE1_EVE1_CDOFFS,
+	.dep_bit	  = DRA7XX_EVE1_STATDEP_SHIFT,
+	.wkdep_srcs	  = eve1_wkup_sleep_deps,
+	.sleepdep_srcs	  = eve1_wkup_sleep_deps,
+	.flags		  = CLKDM_CAN_HWSUP_SWSUP,
+};
+
+/* As clockdomains are added or removed above, this list must also be changed */
+static struct clockdomain *clockdomains_dra7xx[] __initdata = {
+	&l4per3_7xx_clkdm,
+	&l4per2_7xx_clkdm,
+	&mpu0_7xx_clkdm,
+	&iva_7xx_clkdm,
+	&coreaon_7xx_clkdm,
+	&ipu1_7xx_clkdm,
+	&ipu2_7xx_clkdm,
+	&l3init_7xx_clkdm,
+	&l4sec_7xx_clkdm,
+	&l3main1_7xx_clkdm,
+	&vpe_7xx_clkdm,
+	&mpu_7xx_clkdm,
+	&custefuse_7xx_clkdm,
+	&ipu_7xx_clkdm,
+	&mpu1_7xx_clkdm,
+	&gmac_7xx_clkdm,
+	&l4cfg_7xx_clkdm,
+	&dma_7xx_clkdm,
+	&rtc_7xx_clkdm,
+	&pcie_7xx_clkdm,
+	&atl_7xx_clkdm,
+	&l3instr_7xx_clkdm,
+	&dss_7xx_clkdm,
+	&emif_7xx_clkdm,
+	&emu_7xx_clkdm,
+	&dsp2_7xx_clkdm,
+	&dsp1_7xx_clkdm,
+	&cam_7xx_clkdm,
+	&l4per_7xx_clkdm,
+	&gpu_7xx_clkdm,
+	&eve4_7xx_clkdm,
+	&eve2_7xx_clkdm,
+	&eve3_7xx_clkdm,
+	&wkupaon_7xx_clkdm,
+	&eve1_7xx_clkdm,
+	NULL
+};
+
+void __init dra7xx_clockdomains_init(void)
+{
+	clkdm_register_platform_funcs(&omap4_clkdm_operations);
+	clkdm_register_clkdms(clockdomains_dra7xx);
+	clkdm_complete_init();
+}
diff --git a/arch/arm/mach-omap2/cm-regbits-24xx.h b/arch/arm/mach-omap2/cm-regbits-24xx.h
index 669ef51b17a8..8538669cc2ad 100644
--- a/arch/arm/mach-omap2/cm-regbits-24xx.h
+++ b/arch/arm/mach-omap2/cm-regbits-24xx.h
@@ -14,439 +14,121 @@
  * published by the Free Software Foundation.
  */
 
-/* Bits shared between registers */
-
-/* CM_FCLKEN1_CORE and CM_ICLKEN1_CORE shared bits */
 #define OMAP24XX_EN_CAM_SHIFT				31
-#define OMAP24XX_EN_CAM_MASK				(1 << 31)
 #define OMAP24XX_EN_WDT4_SHIFT				29
-#define OMAP24XX_EN_WDT4_MASK				(1 << 29)
 #define OMAP2420_EN_WDT3_SHIFT				28
-#define OMAP2420_EN_WDT3_MASK				(1 << 28)
 #define OMAP24XX_EN_MSPRO_SHIFT				27
-#define OMAP24XX_EN_MSPRO_MASK				(1 << 27)
 #define OMAP24XX_EN_FAC_SHIFT				25
-#define OMAP24XX_EN_FAC_MASK				(1 << 25)
 #define OMAP2420_EN_EAC_SHIFT				24
-#define OMAP2420_EN_EAC_MASK				(1 << 24)
 #define OMAP24XX_EN_HDQ_SHIFT				23
-#define OMAP24XX_EN_HDQ_MASK				(1 << 23)
 #define OMAP2420_EN_I2C2_SHIFT				20
-#define OMAP2420_EN_I2C2_MASK				(1 << 20)
 #define OMAP2420_EN_I2C1_SHIFT				19
-#define OMAP2420_EN_I2C1_MASK				(1 << 19)
-
-/* CM_FCLKEN2_CORE and CM_ICLKEN2_CORE shared bits */
 #define OMAP2430_EN_MCBSP5_SHIFT			5
-#define OMAP2430_EN_MCBSP5_MASK				(1 << 5)
 #define OMAP2430_EN_MCBSP4_SHIFT			4
-#define OMAP2430_EN_MCBSP4_MASK				(1 << 4)
 #define OMAP2430_EN_MCBSP3_SHIFT			3
-#define OMAP2430_EN_MCBSP3_MASK				(1 << 3)
 #define OMAP24XX_EN_SSI_SHIFT				1
-#define OMAP24XX_EN_SSI_MASK				(1 << 1)
-
-/* CM_FCLKEN_WKUP and CM_ICLKEN_WKUP shared bits */
 #define OMAP24XX_EN_MPU_WDT_SHIFT			3
-#define OMAP24XX_EN_MPU_WDT_MASK			(1 << 3)
-
-/* Bits specific to each register */
-
-/* CM_IDLEST_MPU */
-/* 2430 only */
-#define OMAP2430_ST_MPU_MASK				(1 << 0)
-
-/* CM_CLKSEL_MPU */
 #define OMAP24XX_CLKSEL_MPU_SHIFT			0
-#define OMAP24XX_CLKSEL_MPU_MASK			(0x1f << 0)
 #define OMAP24XX_CLKSEL_MPU_WIDTH			5
-
-/* CM_CLKSTCTRL_MPU */
-#define OMAP24XX_AUTOSTATE_MPU_SHIFT			0
 #define OMAP24XX_AUTOSTATE_MPU_MASK			(1 << 0)
-
-/* CM_FCLKEN1_CORE specific bits*/
 #define OMAP24XX_EN_TV_SHIFT				2
-#define OMAP24XX_EN_TV_MASK				(1 << 2)
 #define OMAP24XX_EN_DSS2_SHIFT				1
-#define OMAP24XX_EN_DSS2_MASK				(1 << 1)
 #define OMAP24XX_EN_DSS1_SHIFT				0
 #define OMAP24XX_EN_DSS1_MASK				(1 << 0)
-
-/* CM_FCLKEN2_CORE specific bits */
 #define OMAP2430_EN_I2CHS2_SHIFT			20
-#define OMAP2430_EN_I2CHS2_MASK				(1 << 20)
 #define OMAP2430_EN_I2CHS1_SHIFT			19
-#define OMAP2430_EN_I2CHS1_MASK				(1 << 19)
 #define OMAP2430_EN_MMCHSDB2_SHIFT			17
-#define OMAP2430_EN_MMCHSDB2_MASK			(1 << 17)
 #define OMAP2430_EN_MMCHSDB1_SHIFT			16
-#define OMAP2430_EN_MMCHSDB1_MASK			(1 << 16)
-
-/* CM_ICLKEN1_CORE specific bits */
 #define OMAP24XX_EN_MAILBOXES_SHIFT			30
-#define OMAP24XX_EN_MAILBOXES_MASK			(1 << 30)
-#define OMAP24XX_EN_DSS_SHIFT				0
-#define OMAP24XX_EN_DSS_MASK				(1 << 0)
-
-/* CM_ICLKEN2_CORE specific bits */
-
-/* CM_ICLKEN3_CORE */
-/* 2430 only */
 #define OMAP2430_EN_SDRC_SHIFT				2
-#define OMAP2430_EN_SDRC_MASK				(1 << 2)
-
-/* CM_ICLKEN4_CORE */
 #define OMAP24XX_EN_PKA_SHIFT				4
-#define OMAP24XX_EN_PKA_MASK				(1 << 4)
 #define OMAP24XX_EN_AES_SHIFT				3
-#define OMAP24XX_EN_AES_MASK				(1 << 3)
 #define OMAP24XX_EN_RNG_SHIFT				2
-#define OMAP24XX_EN_RNG_MASK				(1 << 2)
 #define OMAP24XX_EN_SHA_SHIFT				1
-#define OMAP24XX_EN_SHA_MASK				(1 << 1)
 #define OMAP24XX_EN_DES_SHIFT				0
-#define OMAP24XX_EN_DES_MASK				(1 << 0)
-
-/* CM_IDLEST1_CORE specific bits */
 #define OMAP24XX_ST_MAILBOXES_SHIFT			30
-#define OMAP24XX_ST_MAILBOXES_MASK			(1 << 30)
-#define OMAP24XX_ST_WDT4_SHIFT				29
-#define OMAP24XX_ST_WDT4_MASK				(1 << 29)
-#define OMAP2420_ST_WDT3_SHIFT				28
-#define OMAP2420_ST_WDT3_MASK				(1 << 28)
-#define OMAP24XX_ST_MSPRO_SHIFT				27
-#define OMAP24XX_ST_MSPRO_MASK				(1 << 27)
-#define OMAP24XX_ST_FAC_SHIFT				25
-#define OMAP24XX_ST_FAC_MASK				(1 << 25)
-#define OMAP2420_ST_EAC_SHIFT				24
-#define OMAP2420_ST_EAC_MASK				(1 << 24)
 #define OMAP24XX_ST_HDQ_SHIFT				23
-#define OMAP24XX_ST_HDQ_MASK				(1 << 23)
 #define OMAP2420_ST_I2C2_SHIFT				20
-#define OMAP2420_ST_I2C2_MASK				(1 << 20)
 #define OMAP2430_ST_I2CHS1_SHIFT			19
-#define OMAP2430_ST_I2CHS1_MASK				(1 << 19)
 #define OMAP2420_ST_I2C1_SHIFT				19
-#define OMAP2420_ST_I2C1_MASK				(1 << 19)
 #define OMAP2430_ST_I2CHS2_SHIFT			20
-#define OMAP2430_ST_I2CHS2_MASK				(1 << 20)
 #define OMAP24XX_ST_MCBSP2_SHIFT			16
-#define OMAP24XX_ST_MCBSP2_MASK				(1 << 16)
 #define OMAP24XX_ST_MCBSP1_SHIFT			15
-#define OMAP24XX_ST_MCBSP1_MASK				(1 << 15)
 #define OMAP24XX_ST_DSS_SHIFT				0
-#define OMAP24XX_ST_DSS_MASK				(1 << 0)
-
-/* CM_IDLEST2_CORE */
 #define OMAP2430_ST_MCBSP5_SHIFT			5
-#define OMAP2430_ST_MCBSP5_MASK				(1 << 5)
 #define OMAP2430_ST_MCBSP4_SHIFT			4
-#define OMAP2430_ST_MCBSP4_MASK				(1 << 4)
 #define OMAP2430_ST_MCBSP3_SHIFT			3
-#define OMAP2430_ST_MCBSP3_MASK				(1 << 3)
-#define OMAP24XX_ST_SSI_SHIFT				1
-#define OMAP24XX_ST_SSI_MASK				(1 << 1)
-
-/* CM_IDLEST3_CORE */
-/* 2430 only */
-#define OMAP2430_ST_SDRC_MASK				(1 << 2)
-
-/* CM_IDLEST4_CORE */
-#define OMAP24XX_ST_PKA_SHIFT				4
-#define OMAP24XX_ST_PKA_MASK				(1 << 4)
 #define OMAP24XX_ST_AES_SHIFT				3
-#define OMAP24XX_ST_AES_MASK				(1 << 3)
 #define OMAP24XX_ST_RNG_SHIFT				2
-#define OMAP24XX_ST_RNG_MASK				(1 << 2)
 #define OMAP24XX_ST_SHA_SHIFT				1
-#define OMAP24XX_ST_SHA_MASK				(1 << 1)
-#define OMAP24XX_ST_DES_SHIFT				0
-#define OMAP24XX_ST_DES_MASK				(1 << 0)
-
-/* CM_AUTOIDLE1_CORE */
-#define OMAP24XX_AUTO_CAM_MASK				(1 << 31)
-#define OMAP24XX_AUTO_MAILBOXES_MASK			(1 << 30)
-#define OMAP24XX_AUTO_WDT4_MASK				(1 << 29)
-#define OMAP2420_AUTO_WDT3_MASK				(1 << 28)
-#define OMAP24XX_AUTO_MSPRO_MASK			(1 << 27)
-#define OMAP2420_AUTO_MMC_MASK				(1 << 26)
-#define OMAP24XX_AUTO_FAC_MASK				(1 << 25)
-#define OMAP2420_AUTO_EAC_MASK				(1 << 24)
-#define OMAP24XX_AUTO_HDQ_MASK				(1 << 23)
-#define OMAP24XX_AUTO_UART2_MASK			(1 << 22)
-#define OMAP24XX_AUTO_UART1_MASK			(1 << 21)
-#define OMAP24XX_AUTO_I2C2_MASK				(1 << 20)
-#define OMAP24XX_AUTO_I2C1_MASK				(1 << 19)
-#define OMAP24XX_AUTO_MCSPI2_MASK			(1 << 18)
-#define OMAP24XX_AUTO_MCSPI1_MASK			(1 << 17)
-#define OMAP24XX_AUTO_MCBSP2_MASK			(1 << 16)
-#define OMAP24XX_AUTO_MCBSP1_MASK			(1 << 15)
-#define OMAP24XX_AUTO_GPT12_MASK			(1 << 14)
-#define OMAP24XX_AUTO_GPT11_MASK			(1 << 13)
-#define OMAP24XX_AUTO_GPT10_MASK			(1 << 12)
-#define OMAP24XX_AUTO_GPT9_MASK				(1 << 11)
-#define OMAP24XX_AUTO_GPT8_MASK				(1 << 10)
-#define OMAP24XX_AUTO_GPT7_MASK				(1 << 9)
-#define OMAP24XX_AUTO_GPT6_MASK				(1 << 8)
-#define OMAP24XX_AUTO_GPT5_MASK				(1 << 7)
-#define OMAP24XX_AUTO_GPT4_MASK				(1 << 6)
-#define OMAP24XX_AUTO_GPT3_MASK				(1 << 5)
-#define OMAP24XX_AUTO_GPT2_MASK				(1 << 4)
-#define OMAP2420_AUTO_VLYNQ_MASK			(1 << 3)
-#define OMAP24XX_AUTO_DSS_MASK				(1 << 0)
-
-/* CM_AUTOIDLE2_CORE */
-#define OMAP2430_AUTO_MDM_INTC_MASK			(1 << 11)
-#define OMAP2430_AUTO_GPIO5_MASK			(1 << 10)
-#define OMAP2430_AUTO_MCSPI3_MASK			(1 << 9)
-#define OMAP2430_AUTO_MMCHS2_MASK			(1 << 8)
-#define OMAP2430_AUTO_MMCHS1_MASK			(1 << 7)
-#define OMAP2430_AUTO_USBHS_MASK			(1 << 6)
-#define OMAP2430_AUTO_MCBSP5_MASK			(1 << 5)
-#define OMAP2430_AUTO_MCBSP4_MASK			(1 << 4)
-#define OMAP2430_AUTO_MCBSP3_MASK			(1 << 3)
-#define OMAP24XX_AUTO_UART3_MASK			(1 << 2)
-#define OMAP24XX_AUTO_SSI_MASK				(1 << 1)
-#define OMAP24XX_AUTO_USB_MASK				(1 << 0)
-
-/* CM_AUTOIDLE3_CORE */
 #define OMAP24XX_AUTO_SDRC_SHIFT			2
-#define OMAP24XX_AUTO_SDRC_MASK				(1 << 2)
 #define OMAP24XX_AUTO_GPMC_SHIFT			1
-#define OMAP24XX_AUTO_GPMC_MASK				(1 << 1)
 #define OMAP24XX_AUTO_SDMA_SHIFT			0
-#define OMAP24XX_AUTO_SDMA_MASK				(1 << 0)
-
-/* CM_AUTOIDLE4_CORE */
-#define OMAP24XX_AUTO_PKA_MASK				(1 << 4)
-#define OMAP24XX_AUTO_AES_MASK				(1 << 3)
-#define OMAP24XX_AUTO_RNG_MASK				(1 << 2)
-#define OMAP24XX_AUTO_SHA_MASK				(1 << 1)
-#define OMAP24XX_AUTO_DES_MASK				(1 << 0)
-
-/* CM_CLKSEL1_CORE */
-#define OMAP24XX_CLKSEL_USB_SHIFT			25
 #define OMAP24XX_CLKSEL_USB_MASK			(0x7 << 25)
-#define OMAP24XX_CLKSEL_SSI_SHIFT			20
 #define OMAP24XX_CLKSEL_SSI_MASK			(0x1f << 20)
-#define OMAP2420_CLKSEL_VLYNQ_SHIFT			15
 #define OMAP2420_CLKSEL_VLYNQ_MASK			(0x1f << 15)
-#define OMAP24XX_CLKSEL_DSS2_SHIFT			13
 #define OMAP24XX_CLKSEL_DSS2_MASK			(0x1 << 13)
-#define OMAP24XX_CLKSEL_DSS1_SHIFT			8
 #define OMAP24XX_CLKSEL_DSS1_MASK			(0x1f << 8)
 #define OMAP24XX_CLKSEL_L4_SHIFT			5
-#define OMAP24XX_CLKSEL_L4_MASK				(0x3 << 5)
 #define OMAP24XX_CLKSEL_L4_WIDTH			2
 #define OMAP24XX_CLKSEL_L3_SHIFT			0
-#define OMAP24XX_CLKSEL_L3_MASK				(0x1f << 0)
 #define OMAP24XX_CLKSEL_L3_WIDTH			5
-
-/* CM_CLKSEL2_CORE */
-#define OMAP24XX_CLKSEL_GPT12_SHIFT			22
 #define OMAP24XX_CLKSEL_GPT12_MASK			(0x3 << 22)
-#define OMAP24XX_CLKSEL_GPT11_SHIFT			20
 #define OMAP24XX_CLKSEL_GPT11_MASK			(0x3 << 20)
-#define OMAP24XX_CLKSEL_GPT10_SHIFT			18
 #define OMAP24XX_CLKSEL_GPT10_MASK			(0x3 << 18)
-#define OMAP24XX_CLKSEL_GPT9_SHIFT			16
 #define OMAP24XX_CLKSEL_GPT9_MASK			(0x3 << 16)
-#define OMAP24XX_CLKSEL_GPT8_SHIFT			14
 #define OMAP24XX_CLKSEL_GPT8_MASK			(0x3 << 14)
-#define OMAP24XX_CLKSEL_GPT7_SHIFT			12
 #define OMAP24XX_CLKSEL_GPT7_MASK			(0x3 << 12)
-#define OMAP24XX_CLKSEL_GPT6_SHIFT			10
 #define OMAP24XX_CLKSEL_GPT6_MASK			(0x3 << 10)
-#define OMAP24XX_CLKSEL_GPT5_SHIFT			8
 #define OMAP24XX_CLKSEL_GPT5_MASK			(0x3 << 8)
-#define OMAP24XX_CLKSEL_GPT4_SHIFT			6
 #define OMAP24XX_CLKSEL_GPT4_MASK			(0x3 << 6)
-#define OMAP24XX_CLKSEL_GPT3_SHIFT			4
 #define OMAP24XX_CLKSEL_GPT3_MASK			(0x3 << 4)
-#define OMAP24XX_CLKSEL_GPT2_SHIFT			2
 #define OMAP24XX_CLKSEL_GPT2_MASK			(0x3 << 2)
-
-/* CM_CLKSTCTRL_CORE */
-#define OMAP24XX_AUTOSTATE_DSS_SHIFT			2
 #define OMAP24XX_AUTOSTATE_DSS_MASK			(1 << 2)
-#define OMAP24XX_AUTOSTATE_L4_SHIFT			1
 #define OMAP24XX_AUTOSTATE_L4_MASK			(1 << 1)
-#define OMAP24XX_AUTOSTATE_L3_SHIFT			0
 #define OMAP24XX_AUTOSTATE_L3_MASK			(1 << 0)
-
-/* CM_FCLKEN_GFX */
 #define OMAP24XX_EN_3D_SHIFT				2
-#define OMAP24XX_EN_3D_MASK				(1 << 2)
 #define OMAP24XX_EN_2D_SHIFT				1
-#define OMAP24XX_EN_2D_MASK				(1 << 1)
-
-/* CM_ICLKEN_GFX specific bits */
-
-/* CM_IDLEST_GFX specific bits */
-
-/* CM_CLKSEL_GFX specific bits */
-
-/* CM_CLKSTCTRL_GFX */
-#define OMAP24XX_AUTOSTATE_GFX_SHIFT			0
 #define OMAP24XX_AUTOSTATE_GFX_MASK			(1 << 0)
-
-/* CM_FCLKEN_WKUP specific bits */
-
-/* CM_ICLKEN_WKUP specific bits */
 #define OMAP2430_EN_ICR_SHIFT				6
-#define OMAP2430_EN_ICR_MASK				(1 << 6)
 #define OMAP24XX_EN_OMAPCTRL_SHIFT			5
-#define OMAP24XX_EN_OMAPCTRL_MASK			(1 << 5)
 #define OMAP24XX_EN_WDT1_SHIFT				4
-#define OMAP24XX_EN_WDT1_MASK				(1 << 4)
 #define OMAP24XX_EN_32KSYNC_SHIFT			1
-#define OMAP24XX_EN_32KSYNC_MASK			(1 << 1)
-
-/* CM_IDLEST_WKUP specific bits */
-#define OMAP2430_ST_ICR_SHIFT				6
-#define OMAP2430_ST_ICR_MASK				(1 << 6)
-#define OMAP24XX_ST_OMAPCTRL_SHIFT			5
-#define OMAP24XX_ST_OMAPCTRL_MASK			(1 << 5)
-#define OMAP24XX_ST_WDT1_SHIFT				4
-#define OMAP24XX_ST_WDT1_MASK				(1 << 4)
 #define OMAP24XX_ST_MPU_WDT_SHIFT			3
-#define OMAP24XX_ST_MPU_WDT_MASK			(1 << 3)
 #define OMAP24XX_ST_32KSYNC_SHIFT			1
-#define OMAP24XX_ST_32KSYNC_MASK			(1 << 1)
-
-/* CM_AUTOIDLE_WKUP */
-#define OMAP24XX_AUTO_OMAPCTRL_MASK			(1 << 5)
-#define OMAP24XX_AUTO_WDT1_MASK				(1 << 4)
-#define OMAP24XX_AUTO_MPU_WDT_MASK			(1 << 3)
-#define OMAP24XX_AUTO_GPIOS_MASK			(1 << 2)
-#define OMAP24XX_AUTO_32KSYNC_MASK			(1 << 1)
-#define OMAP24XX_AUTO_GPT1_MASK				(1 << 0)
-
-/* CM_CLKSEL_WKUP */
-#define OMAP24XX_CLKSEL_GPT1_SHIFT			0
 #define OMAP24XX_CLKSEL_GPT1_MASK			(0x3 << 0)
-
-/* CM_CLKEN_PLL */
 #define OMAP24XX_EN_54M_PLL_SHIFT			6
-#define OMAP24XX_EN_54M_PLL_MASK			(0x3 << 6)
 #define OMAP24XX_EN_96M_PLL_SHIFT			2
-#define OMAP24XX_EN_96M_PLL_MASK			(0x3 << 2)
-#define OMAP24XX_EN_DPLL_SHIFT				0
 #define OMAP24XX_EN_DPLL_MASK				(0x3 << 0)
-
-/* CM_IDLEST_CKGEN */
 #define OMAP24XX_ST_54M_APLL_SHIFT			9
-#define OMAP24XX_ST_54M_APLL_MASK			(1 << 9)
 #define OMAP24XX_ST_96M_APLL_SHIFT			8
-#define OMAP24XX_ST_96M_APLL_MASK			(1 << 8)
-#define OMAP24XX_ST_54M_CLK_MASK			(1 << 6)
-#define OMAP24XX_ST_12M_CLK_MASK			(1 << 5)
-#define OMAP24XX_ST_48M_CLK_MASK			(1 << 4)
-#define OMAP24XX_ST_96M_CLK_MASK			(1 << 2)
-#define OMAP24XX_ST_CORE_CLK_SHIFT			0
-#define OMAP24XX_ST_CORE_CLK_MASK			(0x3 << 0)
-
-/* CM_AUTOIDLE_PLL */
-#define OMAP24XX_AUTO_54M_SHIFT				6
 #define OMAP24XX_AUTO_54M_MASK				(0x3 << 6)
-#define OMAP24XX_AUTO_96M_SHIFT				2
 #define OMAP24XX_AUTO_96M_MASK				(0x3 << 2)
 #define OMAP24XX_AUTO_DPLL_SHIFT			0
 #define OMAP24XX_AUTO_DPLL_MASK				(0x3 << 0)
-
-/* CM_CLKSEL1_PLL */
-#define OMAP2430_MAXDPLLFASTLOCK_SHIFT			28
-#define OMAP2430_MAXDPLLFASTLOCK_MASK			(0x7 << 28)
 #define OMAP24XX_APLLS_CLKIN_SHIFT			23
 #define OMAP24XX_APLLS_CLKIN_MASK			(0x7 << 23)
-#define OMAP24XX_DPLL_MULT_SHIFT			12
 #define OMAP24XX_DPLL_MULT_MASK				(0x3ff << 12)
-#define OMAP24XX_DPLL_DIV_SHIFT				8
 #define OMAP24XX_DPLL_DIV_MASK				(0xf << 8)
 #define OMAP24XX_54M_SOURCE_SHIFT			5
-#define OMAP24XX_54M_SOURCE_MASK			(1 << 5)
 #define OMAP24XX_54M_SOURCE_WIDTH			1
 #define OMAP2430_96M_SOURCE_SHIFT			4
-#define OMAP2430_96M_SOURCE_MASK			(1 << 4)
 #define OMAP2430_96M_SOURCE_WIDTH			1
-#define OMAP24XX_48M_SOURCE_SHIFT			3
 #define OMAP24XX_48M_SOURCE_MASK			(1 << 3)
-#define OMAP2430_ALTCLK_SOURCE_SHIFT			0
-#define OMAP2430_ALTCLK_SOURCE_MASK			(0x7 << 0)
-
-/* CM_CLKSEL2_PLL */
-#define OMAP24XX_CORE_CLK_SRC_SHIFT			0
 #define OMAP24XX_CORE_CLK_SRC_MASK			(0x3 << 0)
-
-/* CM_FCLKEN_DSP */
 #define OMAP2420_EN_IVA_COP_SHIFT			10
-#define OMAP2420_EN_IVA_COP_MASK			(1 << 10)
 #define OMAP2420_EN_IVA_MPU_SHIFT			8
-#define OMAP2420_EN_IVA_MPU_MASK			(1 << 8)
 #define OMAP24XX_CM_FCLKEN_DSP_EN_DSP_SHIFT		0
-#define OMAP24XX_CM_FCLKEN_DSP_EN_DSP_MASK		(1 << 0)
-
-/* CM_ICLKEN_DSP */
 #define OMAP2420_EN_DSP_IPI_SHIFT			1
-#define OMAP2420_EN_DSP_IPI_MASK			(1 << 1)
-
-/* CM_IDLEST_DSP */
-#define OMAP2420_ST_IVA_MASK				(1 << 8)
-#define OMAP2420_ST_IPI_MASK				(1 << 1)
-#define OMAP24XX_ST_DSP_MASK				(1 << 0)
-
-/* CM_AUTOIDLE_DSP */
-#define OMAP2420_AUTO_DSP_IPI_MASK			(1 << 1)
-
-/* CM_CLKSEL_DSP */
-#define OMAP2420_SYNC_IVA_MASK				(1 << 13)
-#define OMAP2420_CLKSEL_IVA_SHIFT			8
 #define OMAP2420_CLKSEL_IVA_MASK			(0x1f << 8)
-#define OMAP24XX_SYNC_DSP_MASK				(1 << 7)
-#define OMAP24XX_CLKSEL_DSP_IF_SHIFT			5
 #define OMAP24XX_CLKSEL_DSP_IF_MASK			(0x3 << 5)
-#define OMAP24XX_CLKSEL_DSP_SHIFT			0
 #define OMAP24XX_CLKSEL_DSP_MASK			(0x1f << 0)
-
-/* CM_CLKSTCTRL_DSP */
-#define OMAP2420_AUTOSTATE_IVA_SHIFT			8
 #define OMAP2420_AUTOSTATE_IVA_MASK			(1 << 8)
-#define OMAP24XX_AUTOSTATE_DSP_SHIFT			0
 #define OMAP24XX_AUTOSTATE_DSP_MASK			(1 << 0)
-
-/* CM_FCLKEN_MDM */
-/* 2430 only */
 #define OMAP2430_EN_OSC_SHIFT				1
-#define OMAP2430_EN_OSC_MASK				(1 << 1)
-
-/* CM_ICLKEN_MDM */
-/* 2430 only */
 #define OMAP2430_CM_ICLKEN_MDM_EN_MDM_SHIFT		0
-#define OMAP2430_CM_ICLKEN_MDM_EN_MDM_MASK		(1 << 0)
-
-/* CM_IDLEST_MDM specific bits */
-/* 2430 only */
-
-/* CM_AUTOIDLE_MDM */
-/* 2430 only */
-#define OMAP2430_AUTO_OSC_MASK				(1 << 1)
-#define OMAP2430_AUTO_MDM_MASK				(1 << 0)
-
-/* CM_CLKSEL_MDM */
-/* 2430 only */
-#define OMAP2430_SYNC_MDM_MASK				(1 << 4)
-#define OMAP2430_CLKSEL_MDM_SHIFT			0
 #define OMAP2430_CLKSEL_MDM_MASK			(0xf << 0)
-
-/* CM_CLKSTCTRL_MDM */
-/* 2430 only */
-#define OMAP2430_AUTOSTATE_MDM_SHIFT			0
 #define OMAP2430_AUTOSTATE_MDM_MASK			(1 << 0)
-
-/* OMAP24XX CM_CLKSTCTRL_*.AUTOSTATE_* register bit values */
 #define OMAP24XX_CLKSTCTRL_DISABLE_AUTO		0x0
 #define OMAP24XX_CLKSTCTRL_ENABLE_AUTO		0x1
-
-
 #endif
diff --git a/arch/arm/mach-omap2/cm-regbits-33xx.h b/arch/arm/mach-omap2/cm-regbits-33xx.h
index adf7bb79b18f..c0823fd6d5e0 100644
--- a/arch/arm/mach-omap2/cm-regbits-33xx.h
+++ b/arch/arm/mach-omap2/cm-regbits-33xx.h
@@ -20,798 +20,49 @@
 #ifndef __ARCH_ARM_MACH_OMAP2_CM_REGBITS_33XX_H
 #define __ARCH_ARM_MACH_OMAP2_CM_REGBITS_33XX_H
 
-/*
- * Used by CM_AUTOIDLE_DPLL_CORE, CM_AUTOIDLE_DPLL_DDR, CM_AUTOIDLE_DPLL_DISP,
- * CM_AUTOIDLE_DPLL_MPU, CM_AUTOIDLE_DPLL_PER
- */
-#define AM33XX_AUTO_DPLL_MODE_SHIFT			0
-#define AM33XX_AUTO_DPLL_MODE_WIDTH			3
-#define AM33XX_AUTO_DPLL_MODE_MASK			(0x7 << 0)
-
-/* Used by CM_WKUP_CLKSTCTRL */
-#define AM33XX_CLKACTIVITY_ADC_FCLK_SHIFT		14
-#define AM33XX_CLKACTIVITY_ADC_FCLK_WIDTH		1
-#define AM33XX_CLKACTIVITY_ADC_FCLK_MASK		(1 << 16)
-
-/* Used by CM_PER_L4LS_CLKSTCTRL */
-#define AM33XX_CLKACTIVITY_CAN_CLK_SHIFT		11
-#define AM33XX_CLKACTIVITY_CAN_CLK_WIDTH		1
-#define AM33XX_CLKACTIVITY_CAN_CLK_MASK			(1 << 11)
-
-/* Used by CM_PER_CLK_24MHZ_CLKSTCTRL */
-#define AM33XX_CLKACTIVITY_CLK_24MHZ_GCLK_SHIFT		4
-#define AM33XX_CLKACTIVITY_CLK_24MHZ_GCLK_WIDTH		1
-#define AM33XX_CLKACTIVITY_CLK_24MHZ_GCLK_MASK		(1 << 4)
-
-/* Used by CM_PER_CPSW_CLKSTCTRL */
-#define AM33XX_CLKACTIVITY_CPSW_125MHZ_GCLK_SHIFT	4
-#define AM33XX_CLKACTIVITY_CPSW_125MHZ_GCLK_WIDTH	1
-#define AM33XX_CLKACTIVITY_CPSW_125MHZ_GCLK_MASK	(1 << 4)
-
-/* Used by CM_PER_L4HS_CLKSTCTRL */
-#define AM33XX_CLKACTIVITY_CPSW_250MHZ_GCLK_SHIFT	4
-#define AM33XX_CLKACTIVITY_CPSW_250MHZ_GCLK_WIDTH	1
-#define AM33XX_CLKACTIVITY_CPSW_250MHZ_GCLK_MASK	(1 << 4)
-
-/* Used by CM_PER_L4HS_CLKSTCTRL */
-#define AM33XX_CLKACTIVITY_CPSW_50MHZ_GCLK_SHIFT	5
-#define AM33XX_CLKACTIVITY_CPSW_50MHZ_GCLK_WIDTH	1
-#define AM33XX_CLKACTIVITY_CPSW_50MHZ_GCLK_MASK		(1 << 5)
-
-/* Used by CM_PER_L4HS_CLKSTCTRL */
-#define AM33XX_CLKACTIVITY_CPSW_5MHZ_GCLK_SHIFT		6
-#define AM33XX_CLKACTIVITY_CPSW_5MHZ_GCLK_WIDTH		1
-#define AM33XX_CLKACTIVITY_CPSW_5MHZ_GCLK_MASK		(1 << 6)
-
-/* Used by CM_PER_L3_CLKSTCTRL */
-#define AM33XX_CLKACTIVITY_CPTS_RFT_GCLK_SHIFT		6
-#define AM33XX_CLKACTIVITY_CPTS_RFT_GCLK_WIDTH		1
-#define AM33XX_CLKACTIVITY_CPTS_RFT_GCLK_MASK		(1 << 6)
-
-/* Used by CM_CEFUSE_CLKSTCTRL */
-#define AM33XX_CLKACTIVITY_CUST_EFUSE_SYS_CLK_SHIFT	9
-#define AM33XX_CLKACTIVITY_CUST_EFUSE_SYS_CLK_WIDTH	1
-#define AM33XX_CLKACTIVITY_CUST_EFUSE_SYS_CLK_MASK	(1 << 9)
-
-/* Used by CM_L3_AON_CLKSTCTRL */
-#define AM33XX_CLKACTIVITY_DBGSYSCLK_SHIFT		2
-#define AM33XX_CLKACTIVITY_DBGSYSCLK_WIDTH		1
-#define AM33XX_CLKACTIVITY_DBGSYSCLK_MASK		(1 << 2)
-
-/* Used by CM_L3_AON_CLKSTCTRL */
-#define AM33XX_CLKACTIVITY_DEBUG_CLKA_SHIFT		4
-#define AM33XX_CLKACTIVITY_DEBUG_CLKA_WIDTH		1
-#define AM33XX_CLKACTIVITY_DEBUG_CLKA_MASK		(1 << 4)
-
-/* Used by CM_PER_L3_CLKSTCTRL */
-#define AM33XX_CLKACTIVITY_EMIF_GCLK_SHIFT		2
-#define AM33XX_CLKACTIVITY_EMIF_GCLK_WIDTH		1
-#define AM33XX_CLKACTIVITY_EMIF_GCLK_MASK		(1 << 2)
-
-/* Used by CM_GFX_L3_CLKSTCTRL */
-#define AM33XX_CLKACTIVITY_GFX_FCLK_SHIFT		9
-#define AM33XX_CLKACTIVITY_GFX_FCLK_WIDTH		1
-#define AM33XX_CLKACTIVITY_GFX_FCLK_MASK		(1 << 9)
-
-/* Used by CM_GFX_L3_CLKSTCTRL */
-#define AM33XX_CLKACTIVITY_GFX_L3_GCLK_SHIFT		8
-#define AM33XX_CLKACTIVITY_GFX_L3_GCLK_WIDTH		1
-#define AM33XX_CLKACTIVITY_GFX_L3_GCLK_MASK		(1 << 8)
-
-/* Used by CM_WKUP_CLKSTCTRL */
-#define AM33XX_CLKACTIVITY_GPIO0_GDBCLK_SHIFT		8
-#define AM33XX_CLKACTIVITY_GPIO0_GDBCLK_WIDTH		1
-#define AM33XX_CLKACTIVITY_GPIO0_GDBCLK_MASK		(1 << 8)
-
-/* Used by CM_PER_L4LS_CLKSTCTRL */
-#define AM33XX_CLKACTIVITY_GPIO_1_GDBCLK_SHIFT		19
-#define AM33XX_CLKACTIVITY_GPIO_1_GDBCLK_WIDTH		1
-#define AM33XX_CLKACTIVITY_GPIO_1_GDBCLK_MASK		(1 << 19)
-
-/* Used by CM_PER_L4LS_CLKSTCTRL */
-#define AM33XX_CLKACTIVITY_GPIO_2_GDBCLK_SHIFT		20
-#define AM33XX_CLKACTIVITY_GPIO_2_GDBCLK_WIDTH		1
-#define AM33XX_CLKACTIVITY_GPIO_2_GDBCLK_MASK		(1 << 20)
-
-/* Used by CM_PER_L4LS_CLKSTCTRL */
-#define AM33XX_CLKACTIVITY_GPIO_3_GDBCLK_SHIFT		21
-#define AM33XX_CLKACTIVITY_GPIO_3_GDBCLK_WIDTH		1
-#define AM33XX_CLKACTIVITY_GPIO_3_GDBCLK_MASK		(1 << 21)
-
-/* Used by CM_PER_L4LS_CLKSTCTRL */
-#define AM33XX_CLKACTIVITY_GPIO_4_GDBCLK_SHIFT		22
-#define AM33XX_CLKACTIVITY_GPIO_4_GDBCLK_WIDTH		1
-#define AM33XX_CLKACTIVITY_GPIO_4_GDBCLK_MASK		(1 << 22)
-
-/* Used by CM_PER_L4LS_CLKSTCTRL */
-#define AM33XX_CLKACTIVITY_GPIO_5_GDBCLK_SHIFT		26
-#define AM33XX_CLKACTIVITY_GPIO_5_GDBCLK_WIDTH		1
-#define AM33XX_CLKACTIVITY_GPIO_5_GDBCLK_MASK		(1 << 26)
-
-/* Used by CM_PER_L4LS_CLKSTCTRL */
-#define AM33XX_CLKACTIVITY_GPIO_6_GDBCLK_SHIFT		18
-#define AM33XX_CLKACTIVITY_GPIO_6_GDBCLK_WIDTH		1
-#define AM33XX_CLKACTIVITY_GPIO_6_GDBCLK_MASK		(1 << 18)
-
-/* Used by CM_WKUP_CLKSTCTRL */
-#define AM33XX_CLKACTIVITY_I2C0_GFCLK_SHIFT		11
-#define AM33XX_CLKACTIVITY_I2C0_GFCLK_WIDTH		1
-#define AM33XX_CLKACTIVITY_I2C0_GFCLK_MASK		(1 << 11)
-
-/* Used by CM_PER_L4LS_CLKSTCTRL */
-#define AM33XX_CLKACTIVITY_I2C_FCLK_SHIFT		24
-#define AM33XX_CLKACTIVITY_I2C_FCLK_WIDTH		1
-#define AM33XX_CLKACTIVITY_I2C_FCLK_MASK		(1 << 24)
-
-/* Used by CM_PER_PRUSS_CLKSTCTRL */
-#define AM33XX_CLKACTIVITY_PRUSS_IEP_GCLK_SHIFT		5
-#define AM33XX_CLKACTIVITY_PRUSS_IEP_GCLK_WIDTH		1
-#define AM33XX_CLKACTIVITY_PRUSS_IEP_GCLK_MASK		(1 << 5)
-
-/* Used by CM_PER_PRUSS_CLKSTCTRL */
-#define AM33XX_CLKACTIVITY_PRUSS_OCP_GCLK_SHIFT		4
-#define AM33XX_CLKACTIVITY_PRUSS_OCP_GCLK_WIDTH		1
-#define AM33XX_CLKACTIVITY_PRUSS_OCP_GCLK_MASK		(1 << 4)
-
-/* Used by CM_PER_PRUSS_CLKSTCTRL */
-#define AM33XX_CLKACTIVITY_PRUSS_UART_GCLK_SHIFT	6
-#define AM33XX_CLKACTIVITY_PRUSS_UART_GCLK_WIDTH	1
-#define AM33XX_CLKACTIVITY_PRUSS_UART_GCLK_MASK		(1 << 6)
-
-/* Used by CM_PER_L3S_CLKSTCTRL */
-#define AM33XX_CLKACTIVITY_L3S_GCLK_SHIFT		3
-#define AM33XX_CLKACTIVITY_L3S_GCLK_WIDTH		1
-#define AM33XX_CLKACTIVITY_L3S_GCLK_MASK		(1 << 3)
-
-/* Used by CM_L3_AON_CLKSTCTRL */
-#define AM33XX_CLKACTIVITY_L3_AON_GCLK_SHIFT		3
-#define AM33XX_CLKACTIVITY_L3_AON_GCLK_WIDTH		1
-#define AM33XX_CLKACTIVITY_L3_AON_GCLK_MASK		(1 << 3)
-
-/* Used by CM_PER_L3_CLKSTCTRL */
-#define AM33XX_CLKACTIVITY_L3_GCLK_SHIFT		4
-#define AM33XX_CLKACTIVITY_L3_GCLK_WIDTH		1
-#define AM33XX_CLKACTIVITY_L3_GCLK_MASK			(1 << 4)
-
-/* Used by CM_PER_L4FW_CLKSTCTRL */
-#define AM33XX_CLKACTIVITY_L4FW_GCLK_SHIFT		8
-#define AM33XX_CLKACTIVITY_L4FW_GCLK_WIDTH		1
-#define AM33XX_CLKACTIVITY_L4FW_GCLK_MASK		(1 << 8)
-
-/* Used by CM_PER_L4HS_CLKSTCTRL */
-#define AM33XX_CLKACTIVITY_L4HS_GCLK_SHIFT		3
-#define AM33XX_CLKACTIVITY_L4HS_GCLK_WIDTH		1
-#define AM33XX_CLKACTIVITY_L4HS_GCLK_MASK		(1 << 3)
-
-/* Used by CM_PER_L4LS_CLKSTCTRL */
-#define AM33XX_CLKACTIVITY_L4LS_GCLK_SHIFT		8
-#define AM33XX_CLKACTIVITY_L4LS_GCLK_WIDTH		1
-#define AM33XX_CLKACTIVITY_L4LS_GCLK_MASK		(1 << 8)
-
-/* Used by CM_GFX_L4LS_GFX_CLKSTCTRL__1 */
-#define AM33XX_CLKACTIVITY_L4LS_GFX_GCLK_SHIFT		8
-#define AM33XX_CLKACTIVITY_L4LS_GFX_GCLK_WIDTH		1
-#define AM33XX_CLKACTIVITY_L4LS_GFX_GCLK_MASK		(1 << 8)
-
-/* Used by CM_CEFUSE_CLKSTCTRL */
-#define AM33XX_CLKACTIVITY_L4_CEFUSE_GICLK_SHIFT	8
-#define AM33XX_CLKACTIVITY_L4_CEFUSE_GICLK_WIDTH	1
-#define AM33XX_CLKACTIVITY_L4_CEFUSE_GICLK_MASK		(1 << 8)
-
-/* Used by CM_RTC_CLKSTCTRL */
-#define AM33XX_CLKACTIVITY_L4_RTC_GCLK_SHIFT		8
-#define AM33XX_CLKACTIVITY_L4_RTC_GCLK_WIDTH		1
-#define AM33XX_CLKACTIVITY_L4_RTC_GCLK_MASK		(1 << 8)
-
-/* Used by CM_L4_WKUP_AON_CLKSTCTRL */
-#define AM33XX_CLKACTIVITY_L4_WKUP_AON_GCLK_SHIFT	2
-#define AM33XX_CLKACTIVITY_L4_WKUP_AON_GCLK_WIDTH	1
-#define AM33XX_CLKACTIVITY_L4_WKUP_AON_GCLK_MASK	(1 << 2)
-
-/* Used by CM_WKUP_CLKSTCTRL */
-#define AM33XX_CLKACTIVITY_L4_WKUP_GCLK_SHIFT		2
-#define AM33XX_CLKACTIVITY_L4_WKUP_GCLK_WIDTH		1
-#define AM33XX_CLKACTIVITY_L4_WKUP_GCLK_MASK		(1 << 2)
-
-/* Used by CM_PER_L4LS_CLKSTCTRL */
-#define AM33XX_CLKACTIVITY_LCDC_GCLK_SHIFT		17
-#define AM33XX_CLKACTIVITY_LCDC_GCLK_WIDTH		1
-#define AM33XX_CLKACTIVITY_LCDC_GCLK_MASK		(1 << 17)
-
-/* Used by CM_PER_LCDC_CLKSTCTRL */
-#define AM33XX_CLKACTIVITY_LCDC_L3_OCP_GCLK_SHIFT	4
-#define AM33XX_CLKACTIVITY_LCDC_L3_OCP_GCLK_WIDTH	1
-#define AM33XX_CLKACTIVITY_LCDC_L3_OCP_GCLK_MASK	(1 << 4)
-
-/* Used by CM_PER_LCDC_CLKSTCTRL */
-#define AM33XX_CLKACTIVITY_LCDC_L4_OCP_GCLK_SHIFT	5
-#define AM33XX_CLKACTIVITY_LCDC_L4_OCP_GCLK_WIDTH	1
-#define AM33XX_CLKACTIVITY_LCDC_L4_OCP_GCLK_MASK	(1 << 5)
-
-/* Used by CM_PER_L3_CLKSTCTRL */
-#define AM33XX_CLKACTIVITY_MCASP_GCLK_SHIFT		7
-#define AM33XX_CLKACTIVITY_MCASP_GCLK_WIDTH		1
-#define AM33XX_CLKACTIVITY_MCASP_GCLK_MASK		(1 << 7)
-
-/* Used by CM_PER_L3_CLKSTCTRL */
-#define AM33XX_CLKACTIVITY_MMC_FCLK_SHIFT		3
-#define AM33XX_CLKACTIVITY_MMC_FCLK_WIDTH		1
-#define AM33XX_CLKACTIVITY_MMC_FCLK_MASK		(1 << 3)
-
-/* Used by CM_MPU_CLKSTCTRL */
-#define AM33XX_CLKACTIVITY_MPU_CLK_SHIFT		2
-#define AM33XX_CLKACTIVITY_MPU_CLK_WIDTH		1
-#define AM33XX_CLKACTIVITY_MPU_CLK_MASK			(1 << 2)
-
-/* Used by CM_PER_OCPWP_L3_CLKSTCTRL */
-#define AM33XX_CLKACTIVITY_OCPWP_L3_GCLK_SHIFT		4
-#define AM33XX_CLKACTIVITY_OCPWP_L3_GCLK_WIDTH		1
-#define AM33XX_CLKACTIVITY_OCPWP_L3_GCLK_MASK		(1 << 4)
-
-/* Used by CM_PER_OCPWP_L3_CLKSTCTRL */
-#define AM33XX_CLKACTIVITY_OCPWP_L4_GCLK_SHIFT		5
-#define AM33XX_CLKACTIVITY_OCPWP_L4_GCLK_WIDTH		1
-#define AM33XX_CLKACTIVITY_OCPWP_L4_GCLK_MASK		(1 << 5)
-
-/* Used by CM_RTC_CLKSTCTRL */
-#define AM33XX_CLKACTIVITY_RTC_32KCLK_SHIFT		9
-#define AM33XX_CLKACTIVITY_RTC_32KCLK_WIDTH		1
-#define AM33XX_CLKACTIVITY_RTC_32KCLK_MASK		(1 << 9)
-
-/* Used by CM_PER_L4LS_CLKSTCTRL */
-#define AM33XX_CLKACTIVITY_SPI_GCLK_SHIFT		25
-#define AM33XX_CLKACTIVITY_SPI_GCLK_WIDTH		1
-#define AM33XX_CLKACTIVITY_SPI_GCLK_MASK		(1 << 25)
-
-/* Used by CM_WKUP_CLKSTCTRL */
-#define AM33XX_CLKACTIVITY_SR_SYSCLK_SHIFT		3
-#define AM33XX_CLKACTIVITY_SR_SYSCLK_WIDTH		1
-#define AM33XX_CLKACTIVITY_SR_SYSCLK_MASK		(1 << 3)
-
-/* Used by CM_WKUP_CLKSTCTRL */
-#define AM33XX_CLKACTIVITY_TIMER0_GCLK_SHIFT		10
-#define AM33XX_CLKACTIVITY_TIMER0_GCLK_WIDTH		1
-#define AM33XX_CLKACTIVITY_TIMER0_GCLK_MASK		(1 << 10)
-
-/* Used by CM_WKUP_CLKSTCTRL */
-#define AM33XX_CLKACTIVITY_TIMER1_GCLK_SHIFT		13
-#define AM33XX_CLKACTIVITY_TIMER1_GCLK_WIDTH		1
-#define AM33XX_CLKACTIVITY_TIMER1_GCLK_MASK		(1 << 13)
-
-/* Used by CM_PER_L4LS_CLKSTCTRL */
-#define AM33XX_CLKACTIVITY_TIMER2_GCLK_SHIFT		14
-#define AM33XX_CLKACTIVITY_TIMER2_GCLK_WIDTH		1
-#define AM33XX_CLKACTIVITY_TIMER2_GCLK_MASK		(1 << 14)
-
-/* Used by CM_PER_L4LS_CLKSTCTRL */
-#define AM33XX_CLKACTIVITY_TIMER3_GCLK_SHIFT		15
-#define AM33XX_CLKACTIVITY_TIMER3_GCLK_WIDTH		1
-#define AM33XX_CLKACTIVITY_TIMER3_GCLK_MASK		(1 << 15)
-
-/* Used by CM_PER_L4LS_CLKSTCTRL */
-#define AM33XX_CLKACTIVITY_TIMER4_GCLK_SHIFT		16
-#define AM33XX_CLKACTIVITY_TIMER4_GCLK_WIDTH		1
-#define AM33XX_CLKACTIVITY_TIMER4_GCLK_MASK		(1 << 16)
-
-/* Used by CM_PER_L4LS_CLKSTCTRL */
-#define AM33XX_CLKACTIVITY_TIMER5_GCLK_SHIFT		27
-#define AM33XX_CLKACTIVITY_TIMER5_GCLK_WIDTH		1
-#define AM33XX_CLKACTIVITY_TIMER5_GCLK_MASK		(1 << 27)
-
-/* Used by CM_PER_L4LS_CLKSTCTRL */
-#define AM33XX_CLKACTIVITY_TIMER6_GCLK_SHIFT		28
-#define AM33XX_CLKACTIVITY_TIMER6_GCLK_WIDTH		1
-#define AM33XX_CLKACTIVITY_TIMER6_GCLK_MASK		(1 << 28)
-
-/* Used by CM_PER_L4LS_CLKSTCTRL */
-#define AM33XX_CLKACTIVITY_TIMER7_GCLK_SHIFT		13
-#define AM33XX_CLKACTIVITY_TIMER7_GCLK_WIDTH		1
-#define AM33XX_CLKACTIVITY_TIMER7_GCLK_MASK		(1 << 13)
-
-/* Used by CM_WKUP_CLKSTCTRL */
-#define AM33XX_CLKACTIVITY_UART0_GFCLK_SHIFT		12
-#define AM33XX_CLKACTIVITY_UART0_GFCLK_WIDTH		1
-#define AM33XX_CLKACTIVITY_UART0_GFCLK_MASK		(1 << 12)
-
-/* Used by CM_PER_L4LS_CLKSTCTRL */
-#define AM33XX_CLKACTIVITY_UART_GFCLK_SHIFT		10
-#define AM33XX_CLKACTIVITY_UART_GFCLK_WIDTH		1
-#define AM33XX_CLKACTIVITY_UART_GFCLK_MASK		(1 << 10)
-
-/* Used by CM_WKUP_CLKSTCTRL */
-#define AM33XX_CLKACTIVITY_WDT0_GCLK_SHIFT		9
-#define AM33XX_CLKACTIVITY_WDT0_GCLK_WIDTH		1
-#define AM33XX_CLKACTIVITY_WDT0_GCLK_MASK		(1 << 9)
-
-/* Used by CM_WKUP_CLKSTCTRL */
-#define AM33XX_CLKACTIVITY_WDT1_GCLK_SHIFT		4
-#define AM33XX_CLKACTIVITY_WDT1_GCLK_WIDTH		1
-#define AM33XX_CLKACTIVITY_WDT1_GCLK_MASK		(1 << 4)
-
-/* Used by CLKSEL_GFX_FCLK */
-#define AM33XX_CLKDIV_SEL_GFX_FCLK_SHIFT		0
-#define AM33XX_CLKDIV_SEL_GFX_FCLK_WIDTH		1
-#define AM33XX_CLKDIV_SEL_GFX_FCLK_MASK			(1 << 0)
-
-/* Used by CM_CLKOUT_CTRL */
 #define AM33XX_CLKOUT2DIV_SHIFT				3
 #define AM33XX_CLKOUT2DIV_WIDTH				3
-#define AM33XX_CLKOUT2DIV_MASK				(0x7 << 3)
-
-/* Used by CM_CLKOUT_CTRL */
 #define AM33XX_CLKOUT2EN_SHIFT				7
-#define AM33XX_CLKOUT2EN_WIDTH				1
-#define AM33XX_CLKOUT2EN_MASK				(1 << 7)
-
-/* Used by CM_CLKOUT_CTRL */
-#define AM33XX_CLKOUT2SOURCE_SHIFT			0
-#define AM33XX_CLKOUT2SOURCE_WIDTH			3
 #define AM33XX_CLKOUT2SOURCE_MASK			(0x7 << 0)
-
-/*
- * Used by CLKSEL_GPIO0_DBCLK, CLKSEL_LCDC_PIXEL_CLK, CLKSEL_TIMER2_CLK,
- * CLKSEL_TIMER3_CLK, CLKSEL_TIMER4_CLK, CLKSEL_TIMER5_CLK, CLKSEL_TIMER6_CLK,
- * CLKSEL_TIMER7_CLK
- */
-#define AM33XX_CLKSEL_SHIFT				0
-#define AM33XX_CLKSEL_WIDTH				1
-#define AM33XX_CLKSEL_MASK				(0x01 << 0)
-
-/*
- * Renamed from CLKSEL Used by CLKSEL_PRUSS_OCP_CLK, CLKSEL_WDT1_CLK,
- * CM_CPTS_RFT_CLKSEL
- */
 #define AM33XX_CLKSEL_0_0_SHIFT				0
 #define AM33XX_CLKSEL_0_0_WIDTH				1
 #define AM33XX_CLKSEL_0_0_MASK				(1 << 0)
-
-#define AM33XX_CLKSEL_0_1_SHIFT				0
-#define AM33XX_CLKSEL_0_1_WIDTH				2
 #define AM33XX_CLKSEL_0_1_MASK				(3 << 0)
-
-/* Renamed from CLKSEL Used by CLKSEL_TIMER1MS_CLK */
-#define AM33XX_CLKSEL_0_2_SHIFT				0
-#define AM33XX_CLKSEL_0_2_WIDTH				3
 #define AM33XX_CLKSEL_0_2_MASK				(7 << 0)
-
-/* Used by CLKSEL_GFX_FCLK */
-#define AM33XX_CLKSEL_GFX_FCLK_SHIFT			1
-#define AM33XX_CLKSEL_GFX_FCLK_WIDTH			1
 #define AM33XX_CLKSEL_GFX_FCLK_MASK			(1 << 1)
-
-/*
- * Used by CM_MPU_CLKSTCTRL, CM_RTC_CLKSTCTRL, CM_PER_CLK_24MHZ_CLKSTCTRL,
- * CM_PER_CPSW_CLKSTCTRL, CM_PER_PRUSS_CLKSTCTRL, CM_PER_L3S_CLKSTCTRL,
- * CM_PER_L3_CLKSTCTRL, CM_PER_L4FW_CLKSTCTRL, CM_PER_L4HS_CLKSTCTRL,
- * CM_PER_L4LS_CLKSTCTRL, CM_PER_LCDC_CLKSTCTRL, CM_PER_OCPWP_L3_CLKSTCTRL,
- * CM_L3_AON_CLKSTCTRL, CM_L4_WKUP_AON_CLKSTCTRL, CM_WKUP_CLKSTCTRL,
- * CM_GFX_L3_CLKSTCTRL, CM_GFX_L4LS_GFX_CLKSTCTRL__1, CM_CEFUSE_CLKSTCTRL
- */
 #define AM33XX_CLKTRCTRL_SHIFT				0
-#define AM33XX_CLKTRCTRL_WIDTH				2
 #define AM33XX_CLKTRCTRL_MASK				(0x3 << 0)
-
-/*
- * Used by CM_SSC_DELTAMSTEP_DPLL_CORE, CM_SSC_DELTAMSTEP_DPLL_DDR,
- * CM_SSC_DELTAMSTEP_DPLL_DISP, CM_SSC_DELTAMSTEP_DPLL_MPU,
- * CM_SSC_DELTAMSTEP_DPLL_PER
- */
-#define AM33XX_DELTAMSTEP_SHIFT				0
-#define AM33XX_DELTAMSTEP_WIDTH				20
-#define AM33XX_DELTAMSTEP_MASK				(0xfffff << 0)
-
-/* Used by CM_CLKSEL_DPLL_DDR, CM_CLKSEL_DPLL_DISP, CM_CLKSEL_DPLL_MPU */
-#define AM33XX_DPLL_BYP_CLKSEL_SHIFT			23
-#define AM33XX_DPLL_BYP_CLKSEL_WIDTH			1
-#define AM33XX_DPLL_BYP_CLKSEL_MASK			(1 << 23)
-
-/* Used by CM_CLKDCOLDO_DPLL_PER */
-#define AM33XX_DPLL_CLKDCOLDO_GATE_CTRL_SHIFT		8
-#define AM33XX_DPLL_CLKDCOLDO_GATE_CTRL_WIDTH		1
-#define AM33XX_DPLL_CLKDCOLDO_GATE_CTRL_MASK		(1 << 8)
-
-/* Used by CM_CLKDCOLDO_DPLL_PER */
-#define AM33XX_DPLL_CLKDCOLDO_PWDN_SHIFT		12
-#define AM33XX_DPLL_CLKDCOLDO_PWDN_WIDTH		1
-#define AM33XX_DPLL_CLKDCOLDO_PWDN_MASK			(1 << 12)
-
-/* Used by CM_DIV_M2_DPLL_DDR, CM_DIV_M2_DPLL_DISP, CM_DIV_M2_DPLL_MPU */
 #define AM33XX_DPLL_CLKOUT_DIV_SHIFT			0
 #define AM33XX_DPLL_CLKOUT_DIV_WIDTH			5
-#define AM33XX_DPLL_CLKOUT_DIV_MASK			(0x1f << 0)
-
-/* Renamed from DPLL_CLKOUT_DIV Used by CM_DIV_M2_DPLL_PER */
-#define AM33XX_DPLL_CLKOUT_DIV_0_6_SHIFT		0
-#define AM33XX_DPLL_CLKOUT_DIV_0_6_WIDTH		7
-#define AM33XX_DPLL_CLKOUT_DIV_0_6_MASK			(0x7f << 0)
-
-/* Used by CM_DIV_M2_DPLL_DDR, CM_DIV_M2_DPLL_DISP, CM_DIV_M2_DPLL_MPU */
-#define AM33XX_DPLL_CLKOUT_DIVCHACK_SHIFT		5
-#define AM33XX_DPLL_CLKOUT_DIVCHACK_WIDTH		1
-#define AM33XX_DPLL_CLKOUT_DIVCHACK_MASK		(1 << 5)
-
-/* Renamed from DPLL_CLKOUT_DIVCHACK Used by CM_DIV_M2_DPLL_PER */
-#define AM33XX_DPLL_CLKOUT_DIVCHACK_M2_PER_SHIFT	7
-#define AM33XX_DPLL_CLKOUT_DIVCHACK_M2_PER_WIDTH	1
-#define AM33XX_DPLL_CLKOUT_DIVCHACK_M2_PER_MASK		(1 << 7)
-
-/*
- * Used by CM_DIV_M2_DPLL_DDR, CM_DIV_M2_DPLL_DISP, CM_DIV_M2_DPLL_MPU,
- * CM_DIV_M2_DPLL_PER
- */
-#define AM33XX_DPLL_CLKOUT_GATE_CTRL_SHIFT		8
-#define AM33XX_DPLL_CLKOUT_GATE_CTRL_WIDTH		1
-#define AM33XX_DPLL_CLKOUT_GATE_CTRL_MASK		(1 << 8)
-
-/*
- * Used by CM_CLKSEL_DPLL_CORE, CM_CLKSEL_DPLL_DDR, CM_CLKSEL_DPLL_DISP,
- * CM_CLKSEL_DPLL_MPU
- */
-#define AM33XX_DPLL_DIV_SHIFT				0
-#define AM33XX_DPLL_DIV_WIDTH				7
 #define AM33XX_DPLL_DIV_MASK				(0x7f << 0)
-
 #define AM33XX_DPLL_PER_DIV_MASK			(0xff << 0)
-
-/* Renamed from DPLL_DIV Used by CM_CLKSEL_DPLL_PERIPH */
-#define AM33XX_DPLL_DIV_0_7_SHIFT			0
-#define AM33XX_DPLL_DIV_0_7_WIDTH			8
-#define AM33XX_DPLL_DIV_0_7_MASK			(0xff << 0)
-
-/*
- * Used by CM_CLKMODE_DPLL_CORE, CM_CLKMODE_DPLL_DDR, CM_CLKMODE_DPLL_DISP,
- * CM_CLKMODE_DPLL_MPU
- */
-#define AM33XX_DPLL_DRIFTGUARD_EN_SHIFT			8
-#define AM33XX_DPLL_DRIFTGUARD_EN_WIDTH			1
-#define AM33XX_DPLL_DRIFTGUARD_EN_MASK			(1 << 8)
-
-/*
- * Used by CM_CLKMODE_DPLL_CORE, CM_CLKMODE_DPLL_DDR, CM_CLKMODE_DPLL_DISP,
- * CM_CLKMODE_DPLL_MPU, CM_CLKMODE_DPLL_PER
- */
-#define AM33XX_DPLL_EN_SHIFT				0
-#define AM33XX_DPLL_EN_WIDTH				3
 #define AM33XX_DPLL_EN_MASK				(0x7 << 0)
-
-/*
- * Used by CM_CLKMODE_DPLL_CORE, CM_CLKMODE_DPLL_DDR, CM_CLKMODE_DPLL_DISP,
- * CM_CLKMODE_DPLL_MPU
- */
-#define AM33XX_DPLL_LPMODE_EN_SHIFT			10
-#define AM33XX_DPLL_LPMODE_EN_WIDTH			1
-#define AM33XX_DPLL_LPMODE_EN_MASK			(1 << 10)
-
-/*
- * Used by CM_CLKSEL_DPLL_CORE, CM_CLKSEL_DPLL_DDR, CM_CLKSEL_DPLL_DISP,
- * CM_CLKSEL_DPLL_MPU
- */
-#define AM33XX_DPLL_MULT_SHIFT				8
-#define AM33XX_DPLL_MULT_WIDTH				11
 #define AM33XX_DPLL_MULT_MASK				(0x7ff << 8)
-
-/* Renamed from DPLL_MULT Used by CM_CLKSEL_DPLL_PERIPH */
-#define AM33XX_DPLL_MULT_PERIPH_SHIFT			8
-#define AM33XX_DPLL_MULT_PERIPH_WIDTH			12
 #define AM33XX_DPLL_MULT_PERIPH_MASK			(0xfff << 8)
-
-/*
- * Used by CM_CLKMODE_DPLL_CORE, CM_CLKMODE_DPLL_DDR, CM_CLKMODE_DPLL_DISP,
- * CM_CLKMODE_DPLL_MPU
- */
-#define AM33XX_DPLL_REGM4XEN_SHIFT			11
-#define AM33XX_DPLL_REGM4XEN_WIDTH			1
-#define AM33XX_DPLL_REGM4XEN_MASK			(1 << 11)
-
-/* Used by CM_CLKSEL_DPLL_PERIPH */
-#define AM33XX_DPLL_SD_DIV_SHIFT			24
-#define AM33XX_DPLL_SD_DIV_WIDTH			8
-#define AM33XX_DPLL_SD_DIV_MASK				(0xff << 24)
-
-/*
- * Used by CM_CLKMODE_DPLL_CORE, CM_CLKMODE_DPLL_DDR, CM_CLKMODE_DPLL_DISP,
- * CM_CLKMODE_DPLL_MPU, CM_CLKMODE_DPLL_PER
- */
-#define AM33XX_DPLL_SSC_ACK_SHIFT			13
-#define AM33XX_DPLL_SSC_ACK_WIDTH			1
-#define AM33XX_DPLL_SSC_ACK_MASK			(1 << 13)
-
-/*
- * Used by CM_CLKMODE_DPLL_CORE, CM_CLKMODE_DPLL_DDR, CM_CLKMODE_DPLL_DISP,
- * CM_CLKMODE_DPLL_MPU, CM_CLKMODE_DPLL_PER
- */
-#define AM33XX_DPLL_SSC_DOWNSPREAD_SHIFT		14
-#define AM33XX_DPLL_SSC_DOWNSPREAD_WIDTH		1
-#define AM33XX_DPLL_SSC_DOWNSPREAD_MASK			(1 << 14)
-
-/*
- * Used by CM_CLKMODE_DPLL_CORE, CM_CLKMODE_DPLL_DDR, CM_CLKMODE_DPLL_DISP,
- * CM_CLKMODE_DPLL_MPU, CM_CLKMODE_DPLL_PER
- */
-#define AM33XX_DPLL_SSC_EN_SHIFT			12
-#define AM33XX_DPLL_SSC_EN_WIDTH			1
-#define AM33XX_DPLL_SSC_EN_MASK				(1 << 12)
-
-/* Used by CM_DIV_M4_DPLL_CORE */
 #define AM33XX_HSDIVIDER_CLKOUT1_DIV_SHIFT		0
 #define AM33XX_HSDIVIDER_CLKOUT1_DIV_WIDTH		5
-#define AM33XX_HSDIVIDER_CLKOUT1_DIV_MASK		(0x1f << 0)
-
-/* Used by CM_DIV_M4_DPLL_CORE */
-#define AM33XX_HSDIVIDER_CLKOUT1_DIVCHACK_SHIFT		5
-#define AM33XX_HSDIVIDER_CLKOUT1_DIVCHACK_WIDTH		1
-#define AM33XX_HSDIVIDER_CLKOUT1_DIVCHACK_MASK		(1 << 5)
-
-/* Used by CM_DIV_M4_DPLL_CORE */
-#define AM33XX_HSDIVIDER_CLKOUT1_GATE_CTRL_SHIFT	8
-#define AM33XX_HSDIVIDER_CLKOUT1_GATE_CTRL_WIDTH	1
-#define AM33XX_HSDIVIDER_CLKOUT1_GATE_CTRL_MASK		(1 << 8)
-
-/* Used by CM_DIV_M4_DPLL_CORE */
-#define AM33XX_HSDIVIDER_CLKOUT1_PWDN_SHIFT		12
-#define AM33XX_HSDIVIDER_CLKOUT1_PWDN_WIDTH		1
-#define AM33XX_HSDIVIDER_CLKOUT1_PWDN_MASK		(1 << 12)
-
-/* Used by CM_DIV_M5_DPLL_CORE */
 #define AM33XX_HSDIVIDER_CLKOUT2_DIV_SHIFT		0
 #define AM33XX_HSDIVIDER_CLKOUT2_DIV_WIDTH		5
-#define AM33XX_HSDIVIDER_CLKOUT2_DIV_MASK		(0x1f << 0)
-
-/* Used by CM_DIV_M5_DPLL_CORE */
-#define AM33XX_HSDIVIDER_CLKOUT2_DIVCHACK_SHIFT		5
-#define AM33XX_HSDIVIDER_CLKOUT2_DIVCHACK_WIDTH		1
-#define AM33XX_HSDIVIDER_CLKOUT2_DIVCHACK_MASK		(1 << 5)
-
-/* Used by CM_DIV_M5_DPLL_CORE */
-#define AM33XX_HSDIVIDER_CLKOUT2_GATE_CTRL_SHIFT	8
-#define AM33XX_HSDIVIDER_CLKOUT2_GATE_CTRL_WIDTH	1
-#define AM33XX_HSDIVIDER_CLKOUT2_GATE_CTRL_MASK		(1 << 8)
-
-/* Used by CM_DIV_M5_DPLL_CORE */
-#define AM33XX_HSDIVIDER_CLKOUT2_PWDN_SHIFT		12
-#define AM33XX_HSDIVIDER_CLKOUT2_PWDN_WIDTH		1
-#define AM33XX_HSDIVIDER_CLKOUT2_PWDN_MASK		(1 << 12)
-
-/* Used by CM_DIV_M6_DPLL_CORE */
 #define AM33XX_HSDIVIDER_CLKOUT3_DIV_SHIFT		0
 #define AM33XX_HSDIVIDER_CLKOUT3_DIV_WIDTH		5
-#define AM33XX_HSDIVIDER_CLKOUT3_DIV_MASK		(0x1f << 0)
-
-/* Used by CM_DIV_M6_DPLL_CORE */
-#define AM33XX_HSDIVIDER_CLKOUT3_DIVCHACK_SHIFT		5
-#define AM33XX_HSDIVIDER_CLKOUT3_DIVCHACK_WIDTH		1
-#define AM33XX_HSDIVIDER_CLKOUT3_DIVCHACK_MASK		(1 << 5)
-
-/* Used by CM_DIV_M6_DPLL_CORE */
-#define AM33XX_HSDIVIDER_CLKOUT3_GATE_CTRL_SHIFT	8
-#define AM33XX_HSDIVIDER_CLKOUT3_GATE_CTRL_WIDTH	1
-#define AM33XX_HSDIVIDER_CLKOUT3_GATE_CTRL_MASK		(1 << 8)
-
-/* Used by CM_DIV_M6_DPLL_CORE */
-#define AM33XX_HSDIVIDER_CLKOUT3_PWDN_SHIFT		12
-#define AM33XX_HSDIVIDER_CLKOUT3_PWDN_WIDTH		1
-#define AM33XX_HSDIVIDER_CLKOUT3_PWDN_MASK		(1 << 12)
-
-/*
- * Used by CM_MPU_MPU_CLKCTRL, CM_RTC_RTC_CLKCTRL, CM_PER_AES0_CLKCTRL,
- * CM_PER_AES1_CLKCTRL, CM_PER_CLKDIV32K_CLKCTRL, CM_PER_CPGMAC0_CLKCTRL,
- * CM_PER_DCAN0_CLKCTRL, CM_PER_DCAN1_CLKCTRL, CM_PER_DES_CLKCTRL,
- * CM_PER_ELM_CLKCTRL, CM_PER_EMIF_CLKCTRL, CM_PER_EMIF_FW_CLKCTRL,
- * CM_PER_EPWMSS0_CLKCTRL, CM_PER_EPWMSS1_CLKCTRL, CM_PER_EPWMSS2_CLKCTRL,
- * CM_PER_GPIO1_CLKCTRL, CM_PER_GPIO2_CLKCTRL, CM_PER_GPIO3_CLKCTRL,
- * CM_PER_GPIO4_CLKCTRL, CM_PER_GPIO5_CLKCTRL, CM_PER_GPIO6_CLKCTRL,
- * CM_PER_GPMC_CLKCTRL, CM_PER_I2C1_CLKCTRL, CM_PER_I2C2_CLKCTRL,
- * CM_PER_PRUSS_CLKCTRL, CM_PER_IEEE5000_CLKCTRL, CM_PER_L3_CLKCTRL,
- * CM_PER_L3_INSTR_CLKCTRL, CM_PER_L4FW_CLKCTRL, CM_PER_L4HS_CLKCTRL,
- * CM_PER_L4LS_CLKCTRL, CM_PER_LCDC_CLKCTRL, CM_PER_MAILBOX0_CLKCTRL,
- * CM_PER_MAILBOX1_CLKCTRL, CM_PER_MCASP0_CLKCTRL, CM_PER_MCASP1_CLKCTRL,
- * CM_PER_MCASP2_CLKCTRL, CM_PER_MLB_CLKCTRL, CM_PER_MMC0_CLKCTRL,
- * CM_PER_MMC1_CLKCTRL, CM_PER_MMC2_CLKCTRL, CM_PER_MSTR_EXPS_CLKCTRL,
- * CM_PER_OCMCRAM_CLKCTRL, CM_PER_OCPWP_CLKCTRL, CM_PER_PCIE_CLKCTRL,
- * CM_PER_PKA_CLKCTRL, CM_PER_RNG_CLKCTRL, CM_PER_SHA0_CLKCTRL,
- * CM_PER_SLV_EXPS_CLKCTRL, CM_PER_SPARE0_CLKCTRL, CM_PER_SPARE1_CLKCTRL,
- * CM_PER_SPARE_CLKCTRL, CM_PER_SPI0_CLKCTRL, CM_PER_SPI1_CLKCTRL,
- * CM_PER_SPI2_CLKCTRL, CM_PER_SPI3_CLKCTRL, CM_PER_SPINLOCK_CLKCTRL,
- * CM_PER_TIMER2_CLKCTRL, CM_PER_TIMER3_CLKCTRL, CM_PER_TIMER4_CLKCTRL,
- * CM_PER_TIMER5_CLKCTRL, CM_PER_TIMER6_CLKCTRL, CM_PER_TIMER7_CLKCTRL,
- * CM_PER_TPCC_CLKCTRL, CM_PER_TPTC0_CLKCTRL, CM_PER_TPTC1_CLKCTRL,
- * CM_PER_TPTC2_CLKCTRL, CM_PER_UART1_CLKCTRL, CM_PER_UART2_CLKCTRL,
- * CM_PER_UART3_CLKCTRL, CM_PER_UART4_CLKCTRL, CM_PER_UART5_CLKCTRL,
- * CM_PER_USB0_CLKCTRL, CM_WKUP_ADC_TSC_CLKCTRL, CM_WKUP_CONTROL_CLKCTRL,
- * CM_WKUP_DEBUGSS_CLKCTRL, CM_WKUP_GPIO0_CLKCTRL, CM_WKUP_I2C0_CLKCTRL,
- * CM_WKUP_L4WKUP_CLKCTRL, CM_WKUP_SMARTREFLEX0_CLKCTRL,
- * CM_WKUP_SMARTREFLEX1_CLKCTRL, CM_WKUP_TIMER0_CLKCTRL,
- * CM_WKUP_TIMER1_CLKCTRL, CM_WKUP_UART0_CLKCTRL, CM_WKUP_WDT0_CLKCTRL,
- * CM_WKUP_WDT1_CLKCTRL, CM_GFX_BITBLT_CLKCTRL, CM_GFX_GFX_CLKCTRL,
- * CM_GFX_MMUCFG_CLKCTRL, CM_GFX_MMUDATA_CLKCTRL, CM_CEFUSE_CEFUSE_CLKCTRL
- */
 #define AM33XX_IDLEST_SHIFT				16
-#define AM33XX_IDLEST_WIDTH				2
 #define AM33XX_IDLEST_MASK				(0x3 << 16)
-
-/* Used by CM_MAC_CLKSEL */
-#define AM33XX_MII_CLK_SEL_SHIFT			2
-#define AM33XX_MII_CLK_SEL_WIDTH			1
-#define AM33XX_MII_CLK_SEL_MASK				(1 << 2)
-
-/*
- * Used by CM_SSC_MODFREQDIV_DPLL_CORE, CM_SSC_MODFREQDIV_DPLL_DDR,
- * CM_SSC_MODFREQDIV_DPLL_DISP, CM_SSC_MODFREQDIV_DPLL_MPU,
- * CM_SSC_MODFREQDIV_DPLL_PER
- */
-#define AM33XX_MODFREQDIV_EXPONENT_SHIFT		8
-#define AM33XX_MODFREQDIV_EXPONENT_WIDTH		3
-#define AM33XX_MODFREQDIV_EXPONENT_MASK			(0x7 << 8)
-
-/*
- * Used by CM_SSC_MODFREQDIV_DPLL_CORE, CM_SSC_MODFREQDIV_DPLL_DDR,
- * CM_SSC_MODFREQDIV_DPLL_DISP, CM_SSC_MODFREQDIV_DPLL_MPU,
- * CM_SSC_MODFREQDIV_DPLL_PER
- */
-#define AM33XX_MODFREQDIV_MANTISSA_SHIFT		0
-#define AM33XX_MODFREQDIV_MANTISSA_WIDTH		7
-#define AM33XX_MODFREQDIV_MANTISSA_MASK			(0x7f << 0)
-
-/*
- * Used by CM_MPU_MPU_CLKCTRL, CM_RTC_RTC_CLKCTRL, CM_PER_AES0_CLKCTRL,
- * CM_PER_AES1_CLKCTRL, CM_PER_CLKDIV32K_CLKCTRL, CM_PER_CPGMAC0_CLKCTRL,
- * CM_PER_DCAN0_CLKCTRL, CM_PER_DCAN1_CLKCTRL, CM_PER_DES_CLKCTRL,
- * CM_PER_ELM_CLKCTRL, CM_PER_EMIF_CLKCTRL, CM_PER_EMIF_FW_CLKCTRL,
- * CM_PER_EPWMSS0_CLKCTRL, CM_PER_EPWMSS1_CLKCTRL, CM_PER_EPWMSS2_CLKCTRL,
- * CM_PER_GPIO1_CLKCTRL, CM_PER_GPIO2_CLKCTRL, CM_PER_GPIO3_CLKCTRL,
- * CM_PER_GPIO4_CLKCTRL, CM_PER_GPIO5_CLKCTRL, CM_PER_GPIO6_CLKCTRL,
- * CM_PER_GPMC_CLKCTRL, CM_PER_I2C1_CLKCTRL, CM_PER_I2C2_CLKCTRL,
- * CM_PER_PRUSS_CLKCTRL, CM_PER_IEEE5000_CLKCTRL, CM_PER_L3_CLKCTRL,
- * CM_PER_L3_INSTR_CLKCTRL, CM_PER_L4FW_CLKCTRL, CM_PER_L4HS_CLKCTRL,
- * CM_PER_L4LS_CLKCTRL, CM_PER_LCDC_CLKCTRL, CM_PER_MAILBOX0_CLKCTRL,
- * CM_PER_MAILBOX1_CLKCTRL, CM_PER_MCASP0_CLKCTRL, CM_PER_MCASP1_CLKCTRL,
- * CM_PER_MCASP2_CLKCTRL, CM_PER_MLB_CLKCTRL, CM_PER_MMC0_CLKCTRL,
- * CM_PER_MMC1_CLKCTRL, CM_PER_MMC2_CLKCTRL, CM_PER_MSTR_EXPS_CLKCTRL,
- * CM_PER_OCMCRAM_CLKCTRL, CM_PER_OCPWP_CLKCTRL, CM_PER_PCIE_CLKCTRL,
- * CM_PER_PKA_CLKCTRL, CM_PER_RNG_CLKCTRL, CM_PER_SHA0_CLKCTRL,
- * CM_PER_SLV_EXPS_CLKCTRL, CM_PER_SPARE0_CLKCTRL, CM_PER_SPARE1_CLKCTRL,
- * CM_PER_SPARE_CLKCTRL, CM_PER_SPI0_CLKCTRL, CM_PER_SPI1_CLKCTRL,
- * CM_PER_SPI2_CLKCTRL, CM_PER_SPI3_CLKCTRL, CM_PER_SPINLOCK_CLKCTRL,
- * CM_PER_TIMER2_CLKCTRL, CM_PER_TIMER3_CLKCTRL, CM_PER_TIMER4_CLKCTRL,
- * CM_PER_TIMER5_CLKCTRL, CM_PER_TIMER6_CLKCTRL, CM_PER_TIMER7_CLKCTRL,
- * CM_PER_TPCC_CLKCTRL, CM_PER_TPTC0_CLKCTRL, CM_PER_TPTC1_CLKCTRL,
- * CM_PER_TPTC2_CLKCTRL, CM_PER_UART1_CLKCTRL, CM_PER_UART2_CLKCTRL,
- * CM_PER_UART3_CLKCTRL, CM_PER_UART4_CLKCTRL, CM_PER_UART5_CLKCTRL,
- * CM_PER_USB0_CLKCTRL, CM_WKUP_ADC_TSC_CLKCTRL, CM_WKUP_CONTROL_CLKCTRL,
- * CM_WKUP_DEBUGSS_CLKCTRL, CM_WKUP_GPIO0_CLKCTRL, CM_WKUP_I2C0_CLKCTRL,
- * CM_WKUP_L4WKUP_CLKCTRL, CM_WKUP_SMARTREFLEX0_CLKCTRL,
- * CM_WKUP_SMARTREFLEX1_CLKCTRL, CM_WKUP_TIMER0_CLKCTRL,
- * CM_WKUP_TIMER1_CLKCTRL, CM_WKUP_UART0_CLKCTRL, CM_WKUP_WDT0_CLKCTRL,
- * CM_WKUP_WDT1_CLKCTRL, CM_WKUP_WKUP_M3_CLKCTRL, CM_GFX_BITBLT_CLKCTRL,
- * CM_GFX_GFX_CLKCTRL, CM_GFX_MMUCFG_CLKCTRL, CM_GFX_MMUDATA_CLKCTRL,
- * CM_CEFUSE_CEFUSE_CLKCTRL
- */
 #define AM33XX_MODULEMODE_SHIFT				0
-#define AM33XX_MODULEMODE_WIDTH				2
 #define AM33XX_MODULEMODE_MASK				(0x3 << 0)
-
-/* Used by CM_WKUP_DEBUGSS_CLKCTRL */
 #define AM33XX_OPTCLK_DEBUG_CLKA_SHIFT			30
-#define AM33XX_OPTCLK_DEBUG_CLKA_WIDTH			1
-#define AM33XX_OPTCLK_DEBUG_CLKA_MASK			(1 << 30)
-
-/* Used by CM_WKUP_DEBUGSS_CLKCTRL */
 #define AM33XX_OPTFCLKEN_DBGSYSCLK_SHIFT		19
-#define AM33XX_OPTFCLKEN_DBGSYSCLK_WIDTH		1
-#define AM33XX_OPTFCLKEN_DBGSYSCLK_MASK			(1 << 19)
-
-/* Used by CM_WKUP_GPIO0_CLKCTRL */
 #define AM33XX_OPTFCLKEN_GPIO0_GDBCLK_SHIFT		18
-#define AM33XX_OPTFCLKEN_GPIO0_GDBCLK_WIDTH		1
-#define AM33XX_OPTFCLKEN_GPIO0_GDBCLK_MASK		(1 << 18)
-
-/* Used by CM_PER_GPIO1_CLKCTRL */
 #define AM33XX_OPTFCLKEN_GPIO_1_GDBCLK_SHIFT		18
-#define AM33XX_OPTFCLKEN_GPIO_1_GDBCLK_WIDTH		1
-#define AM33XX_OPTFCLKEN_GPIO_1_GDBCLK_MASK		(1 << 18)
-
-/* Used by CM_PER_GPIO2_CLKCTRL */
 #define AM33XX_OPTFCLKEN_GPIO_2_GDBCLK_SHIFT		18
-#define AM33XX_OPTFCLKEN_GPIO_2_GDBCLK_WIDTH		1
-#define AM33XX_OPTFCLKEN_GPIO_2_GDBCLK_MASK		(1 << 18)
-
-/* Used by CM_PER_GPIO3_CLKCTRL */
 #define AM33XX_OPTFCLKEN_GPIO_3_GDBCLK_SHIFT		18
-#define AM33XX_OPTFCLKEN_GPIO_3_GDBCLK_WIDTH		1
-#define AM33XX_OPTFCLKEN_GPIO_3_GDBCLK_MASK		(1 << 18)
-
-/* Used by CM_PER_GPIO4_CLKCTRL */
-#define AM33XX_OPTFCLKEN_GPIO_4_GDBCLK_SHIFT		18
-#define AM33XX_OPTFCLKEN_GPIO_4_GDBCLK_WIDTH		1
-#define AM33XX_OPTFCLKEN_GPIO_4_GDBCLK_MASK		(1 << 18)
-
-/* Used by CM_PER_GPIO5_CLKCTRL */
-#define AM33XX_OPTFCLKEN_GPIO_5_GDBCLK_SHIFT		18
-#define AM33XX_OPTFCLKEN_GPIO_5_GDBCLK_WIDTH		1
-#define AM33XX_OPTFCLKEN_GPIO_5_GDBCLK_MASK		(1 << 18)
-
-/* Used by CM_PER_GPIO6_CLKCTRL */
-#define AM33XX_OPTFCLKEN_GPIO_6_GDBCLK_SHIFT		18
-#define AM33XX_OPTFCLKEN_GPIO_6_GDBCLK_WIDTH		1
-#define AM33XX_OPTFCLKEN_GPIO_6_GDBCLK_MASK		(1 << 18)
-
-/*
- * Used by CM_MPU_MPU_CLKCTRL, CM_PER_CPGMAC0_CLKCTRL, CM_PER_PRUSS_CLKCTRL,
- * CM_PER_IEEE5000_CLKCTRL, CM_PER_LCDC_CLKCTRL, CM_PER_MLB_CLKCTRL,
- * CM_PER_MSTR_EXPS_CLKCTRL, CM_PER_OCPWP_CLKCTRL, CM_PER_PCIE_CLKCTRL,
- * CM_PER_SPARE_CLKCTRL, CM_PER_TPTC0_CLKCTRL, CM_PER_TPTC1_CLKCTRL,
- * CM_PER_TPTC2_CLKCTRL, CM_PER_USB0_CLKCTRL, CM_WKUP_DEBUGSS_CLKCTRL,
- * CM_WKUP_WKUP_M3_CLKCTRL, CM_GFX_BITBLT_CLKCTRL, CM_GFX_GFX_CLKCTRL
- */
-#define AM33XX_STBYST_SHIFT				18
-#define AM33XX_STBYST_WIDTH				1
-#define AM33XX_STBYST_MASK				(1 << 18)
-
-/* Used by CM_WKUP_DEBUGSS_CLKCTRL */
 #define AM33XX_STM_PMD_CLKDIVSEL_SHIFT			27
 #define AM33XX_STM_PMD_CLKDIVSEL_WIDTH			3
-#define AM33XX_STM_PMD_CLKDIVSEL_MASK			(0x7 << 27)
-
-/* Used by CM_WKUP_DEBUGSS_CLKCTRL */
 #define AM33XX_STM_PMD_CLKSEL_SHIFT			22
 #define AM33XX_STM_PMD_CLKSEL_WIDTH			2
-#define AM33XX_STM_PMD_CLKSEL_MASK			(0x3 << 22)
-
-/*
- * Used by CM_IDLEST_DPLL_CORE, CM_IDLEST_DPLL_DDR, CM_IDLEST_DPLL_DISP,
- * CM_IDLEST_DPLL_MPU, CM_IDLEST_DPLL_PER
- */
-#define AM33XX_ST_DPLL_CLK_SHIFT			0
-#define AM33XX_ST_DPLL_CLK_WIDTH			1
 #define AM33XX_ST_DPLL_CLK_MASK				(1 << 0)
-
-/* Used by CM_CLKDCOLDO_DPLL_PER */
 #define AM33XX_ST_DPLL_CLKDCOLDO_SHIFT			8
-#define AM33XX_ST_DPLL_CLKDCOLDO_WIDTH			1
-#define AM33XX_ST_DPLL_CLKDCOLDO_MASK			(1 << 8)
-
-/*
- * Used by CM_DIV_M2_DPLL_DDR, CM_DIV_M2_DPLL_DISP, CM_DIV_M2_DPLL_MPU,
- * CM_DIV_M2_DPLL_PER
- */
-#define AM33XX_ST_DPLL_CLKOUT_SHIFT			9
-#define AM33XX_ST_DPLL_CLKOUT_WIDTH			1
-#define AM33XX_ST_DPLL_CLKOUT_MASK			(1 << 9)
-
-/* Used by CM_DIV_M4_DPLL_CORE */
-#define AM33XX_ST_HSDIVIDER_CLKOUT1_SHIFT		9
-#define AM33XX_ST_HSDIVIDER_CLKOUT1_WIDTH		1
-#define AM33XX_ST_HSDIVIDER_CLKOUT1_MASK		(1 << 9)
-
-/* Used by CM_DIV_M5_DPLL_CORE */
-#define AM33XX_ST_HSDIVIDER_CLKOUT2_SHIFT		9
-#define AM33XX_ST_HSDIVIDER_CLKOUT2_WIDTH		1
-#define AM33XX_ST_HSDIVIDER_CLKOUT2_MASK		(1 << 9)
-
-/* Used by CM_DIV_M6_DPLL_CORE */
-#define AM33XX_ST_HSDIVIDER_CLKOUT3_SHIFT		9
-#define AM33XX_ST_HSDIVIDER_CLKOUT3_WIDTH		1
-#define AM33XX_ST_HSDIVIDER_CLKOUT3_MASK		(1 << 9)
-
-/*
- * Used by CM_IDLEST_DPLL_CORE, CM_IDLEST_DPLL_DDR, CM_IDLEST_DPLL_DISP,
- * CM_IDLEST_DPLL_MPU, CM_IDLEST_DPLL_PER
- */
-#define AM33XX_ST_MN_BYPASS_SHIFT			8
-#define AM33XX_ST_MN_BYPASS_WIDTH			1
-#define AM33XX_ST_MN_BYPASS_MASK			(1 << 8)
-
-/* Used by CM_WKUP_DEBUGSS_CLKCTRL */
 #define AM33XX_TRC_PMD_CLKDIVSEL_SHIFT			24
 #define AM33XX_TRC_PMD_CLKDIVSEL_WIDTH			3
-#define AM33XX_TRC_PMD_CLKDIVSEL_MASK			(0x7 << 24)
-
-/* Used by CM_WKUP_DEBUGSS_CLKCTRL */
 #define AM33XX_TRC_PMD_CLKSEL_SHIFT			20
 #define AM33XX_TRC_PMD_CLKSEL_WIDTH			2
-#define AM33XX_TRC_PMD_CLKSEL_MASK			(0x3 << 20)
-
-/* Used by CONTROL_SEC_CLK_CTRL */
-#define AM33XX_TIMER0_CLKSEL_WIDTH			2
-#define AM33XX_TIMER0_CLKSEL_MASK			(0x3 << 4)
 #endif
diff --git a/arch/arm/mach-omap2/cm-regbits-34xx.h b/arch/arm/mach-omap2/cm-regbits-34xx.h
index adf78d325804..04dab2fcf862 100644
--- a/arch/arm/mach-omap2/cm-regbits-34xx.h
+++ b/arch/arm/mach-omap2/cm-regbits-34xx.h
@@ -14,833 +14,201 @@
  * published by the Free Software Foundation.
  */
 
-/* Bits shared between registers */
-
-/* CM_FCLKEN1_CORE and CM_ICLKEN1_CORE shared bits */
-#define OMAP3430ES2_EN_MMC3_MASK			(1 << 30)
 #define OMAP3430ES2_EN_MMC3_SHIFT			30
-#define OMAP3430_EN_MSPRO_MASK				(1 << 23)
 #define OMAP3430_EN_MSPRO_SHIFT				23
-#define OMAP3430_EN_HDQ_MASK				(1 << 22)
 #define OMAP3430_EN_HDQ_SHIFT				22
-#define OMAP3430ES1_EN_FSHOSTUSB_MASK			(1 << 5)
 #define OMAP3430ES1_EN_FSHOSTUSB_SHIFT			5
-#define OMAP3430ES1_EN_D2D_MASK				(1 << 3)
 #define OMAP3430ES1_EN_D2D_SHIFT			3
-#define OMAP3430_EN_SSI_MASK				(1 << 0)
 #define OMAP3430_EN_SSI_SHIFT				0
-
-/* CM_FCLKEN3_CORE and CM_ICLKEN3_CORE shared bits */
 #define OMAP3430ES2_EN_USBTLL_SHIFT			2
-#define OMAP3430ES2_EN_USBTLL_MASK			(1 << 2)
-
-/* CM_FCLKEN_WKUP and CM_ICLKEN_WKUP shared bits */
-#define OMAP3430_EN_WDT2_MASK				(1 << 5)
 #define OMAP3430_EN_WDT2_SHIFT				5
-
-/* CM_ICLKEN_CAM, CM_FCLKEN_CAM shared bits */
-#define OMAP3430_EN_CAM_MASK				(1 << 0)
 #define OMAP3430_EN_CAM_SHIFT				0
-
-/* CM_FCLKEN_PER, CM_ICLKEN_PER shared bits */
-#define OMAP3430_EN_WDT3_MASK				(1 << 12)
 #define OMAP3430_EN_WDT3_SHIFT				12
-
-/* CM_CLKSEL2_EMU, CM_CLKSEL3_EMU shared bits */
-#define OMAP3430_OVERRIDE_ENABLE_MASK			(1 << 19)
-
-
-/* Bits specific to each register */
-
-/* CM_FCLKEN_IVA2 */
 #define OMAP3430_CM_FCLKEN_IVA2_EN_IVA2_MASK		(1 << 0)
 #define OMAP3430_CM_FCLKEN_IVA2_EN_IVA2_SHIFT		0
-
-/* CM_CLKEN_PLL_IVA2 */
-#define OMAP3430_IVA2_DPLL_RAMPTIME_SHIFT		8
-#define OMAP3430_IVA2_DPLL_RAMPTIME_MASK		(0x3 << 8)
-#define OMAP3430_IVA2_DPLL_FREQSEL_SHIFT		4
 #define OMAP3430_IVA2_DPLL_FREQSEL_MASK			(0xf << 4)
 #define OMAP3430_EN_IVA2_DPLL_DRIFTGUARD_SHIFT		3
-#define OMAP3430_EN_IVA2_DPLL_DRIFTGUARD_MASK		(1 << 3)
-#define OMAP3430_EN_IVA2_DPLL_SHIFT			0
 #define OMAP3430_EN_IVA2_DPLL_MASK			(0x7 << 0)
-
-/* CM_IDLEST_IVA2 */
 #define OMAP3430_ST_IVA2_SHIFT				0
-#define OMAP3430_ST_IVA2_MASK				(1 << 0)
-
-/* CM_IDLEST_PLL_IVA2 */
-#define OMAP3430_ST_IVA2_CLK_SHIFT			0
 #define OMAP3430_ST_IVA2_CLK_MASK			(1 << 0)
-
-/* CM_AUTOIDLE_PLL_IVA2 */
-#define OMAP3430_AUTO_IVA2_DPLL_SHIFT			0
 #define OMAP3430_AUTO_IVA2_DPLL_MASK			(0x7 << 0)
-
-/* CM_CLKSEL1_PLL_IVA2 */
 #define OMAP3430_IVA2_CLK_SRC_SHIFT			19
-#define OMAP3430_IVA2_CLK_SRC_MASK			(0x7 << 19)
 #define OMAP3430_IVA2_CLK_SRC_WIDTH			3
-#define OMAP3430_IVA2_DPLL_MULT_SHIFT			8
 #define OMAP3430_IVA2_DPLL_MULT_MASK			(0x7ff << 8)
-#define OMAP3430_IVA2_DPLL_DIV_SHIFT			0
 #define OMAP3430_IVA2_DPLL_DIV_MASK			(0x7f << 0)
-
-/* CM_CLKSEL2_PLL_IVA2 */
 #define OMAP3430_IVA2_DPLL_CLKOUT_DIV_SHIFT		0
-#define OMAP3430_IVA2_DPLL_CLKOUT_DIV_MASK		(0x1f << 0)
 #define OMAP3430_IVA2_DPLL_CLKOUT_DIV_WIDTH		5
-
-/* CM_CLKSTCTRL_IVA2 */
-#define OMAP3430_CLKTRCTRL_IVA2_SHIFT			0
 #define OMAP3430_CLKTRCTRL_IVA2_MASK			(0x3 << 0)
-
-/* CM_CLKSTST_IVA2 */
-#define OMAP3430_CLKACTIVITY_IVA2_SHIFT			0
 #define OMAP3430_CLKACTIVITY_IVA2_MASK			(1 << 0)
-
-/* CM_REVISION specific bits */
-
-/* CM_SYSCONFIG specific bits */
-
-/* CM_CLKEN_PLL_MPU */
-#define OMAP3430_MPU_DPLL_RAMPTIME_SHIFT		8
-#define OMAP3430_MPU_DPLL_RAMPTIME_MASK			(0x3 << 8)
-#define OMAP3430_MPU_DPLL_FREQSEL_SHIFT			4
 #define OMAP3430_MPU_DPLL_FREQSEL_MASK			(0xf << 4)
 #define OMAP3430_EN_MPU_DPLL_DRIFTGUARD_SHIFT		3
-#define OMAP3430_EN_MPU_DPLL_DRIFTGUARD_MASK		(1 << 3)
-#define OMAP3430_EN_MPU_DPLL_SHIFT			0
 #define OMAP3430_EN_MPU_DPLL_MASK			(0x7 << 0)
-
-/* CM_IDLEST_MPU */
-#define OMAP3430_ST_MPU_MASK				(1 << 0)
-
-/* CM_IDLEST_PLL_MPU */
 #define OMAP3430_ST_MPU_CLK_SHIFT			0
 #define OMAP3430_ST_MPU_CLK_MASK			(1 << 0)
 #define OMAP3430_ST_MPU_CLK_WIDTH			1
-
-/* CM_AUTOIDLE_PLL_MPU */
-#define OMAP3430_AUTO_MPU_DPLL_SHIFT			0
 #define OMAP3430_AUTO_MPU_DPLL_MASK			(0x7 << 0)
-
-/* CM_CLKSEL1_PLL_MPU */
 #define OMAP3430_MPU_CLK_SRC_SHIFT			19
-#define OMAP3430_MPU_CLK_SRC_MASK			(0x7 << 19)
 #define OMAP3430_MPU_CLK_SRC_WIDTH			3
-#define OMAP3430_MPU_DPLL_MULT_SHIFT			8
 #define OMAP3430_MPU_DPLL_MULT_MASK			(0x7ff << 8)
-#define OMAP3430_MPU_DPLL_DIV_SHIFT			0
 #define OMAP3430_MPU_DPLL_DIV_MASK			(0x7f << 0)
-
-/* CM_CLKSEL2_PLL_MPU */
 #define OMAP3430_MPU_DPLL_CLKOUT_DIV_SHIFT		0
-#define OMAP3430_MPU_DPLL_CLKOUT_DIV_MASK		(0x1f << 0)
 #define OMAP3430_MPU_DPLL_CLKOUT_DIV_WIDTH		5
-
-/* CM_CLKSTCTRL_MPU */
-#define OMAP3430_CLKTRCTRL_MPU_SHIFT			0
 #define OMAP3430_CLKTRCTRL_MPU_MASK			(0x3 << 0)
-
-/* CM_CLKSTST_MPU */
-#define OMAP3430_CLKACTIVITY_MPU_SHIFT			0
-#define OMAP3430_CLKACTIVITY_MPU_MASK			(1 << 0)
-
-/* CM_FCLKEN1_CORE specific bits */
-#define OMAP3430_EN_MODEM_MASK				(1 << 31)
 #define OMAP3430_EN_MODEM_SHIFT				31
-
-/* CM_ICLKEN1_CORE specific bits */
-#define OMAP3430_EN_ICR_MASK				(1 << 29)
 #define OMAP3430_EN_ICR_SHIFT				29
-#define OMAP3430_EN_AES2_MASK				(1 << 28)
 #define OMAP3430_EN_AES2_SHIFT				28
-#define OMAP3430_EN_SHA12_MASK				(1 << 27)
 #define OMAP3430_EN_SHA12_SHIFT				27
-#define OMAP3430_EN_DES2_MASK				(1 << 26)
 #define OMAP3430_EN_DES2_SHIFT				26
-#define OMAP3430ES1_EN_FAC_MASK				(1 << 8)
 #define OMAP3430ES1_EN_FAC_SHIFT			8
-#define OMAP3430_EN_MAILBOXES_MASK			(1 << 7)
 #define OMAP3430_EN_MAILBOXES_SHIFT			7
-#define OMAP3430_EN_OMAPCTRL_MASK			(1 << 6)
 #define OMAP3430_EN_OMAPCTRL_SHIFT			6
-#define OMAP3430_EN_SAD2D_MASK				(1 << 3)
 #define OMAP3430_EN_SAD2D_SHIFT				3
-#define OMAP3430_EN_SDRC_MASK				(1 << 1)
 #define OMAP3430_EN_SDRC_SHIFT				1
-
-/* AM35XX specific CM_ICLKEN1_CORE bits */
-#define AM35XX_EN_IPSS_MASK				(1 << 4)
 #define AM35XX_EN_IPSS_SHIFT				4
-
-/* CM_ICLKEN2_CORE */
-#define OMAP3430_EN_PKA_MASK				(1 << 4)
 #define OMAP3430_EN_PKA_SHIFT				4
-#define OMAP3430_EN_AES1_MASK				(1 << 3)
 #define OMAP3430_EN_AES1_SHIFT				3
-#define OMAP3430_EN_RNG_MASK				(1 << 2)
 #define OMAP3430_EN_RNG_SHIFT				2
-#define OMAP3430_EN_SHA11_MASK				(1 << 1)
 #define OMAP3430_EN_SHA11_SHIFT				1
-#define OMAP3430_EN_DES1_MASK				(1 << 0)
 #define OMAP3430_EN_DES1_SHIFT				0
-
-/* CM_ICLKEN3_CORE */
 #define OMAP3430_EN_MAD2D_SHIFT				3
-#define OMAP3430_EN_MAD2D_MASK				(1 << 3)
-
-/* CM_FCLKEN3_CORE specific bits */
 #define OMAP3430ES2_EN_TS_SHIFT				1
-#define OMAP3430ES2_EN_TS_MASK				(1 << 1)
 #define OMAP3430ES2_EN_CPEFUSE_SHIFT			0
-#define OMAP3430ES2_EN_CPEFUSE_MASK			(1 << 0)
-
-/* CM_IDLEST1_CORE specific bits */
-#define OMAP3430ES2_ST_MMC3_SHIFT			30
-#define OMAP3430ES2_ST_MMC3_MASK			(1 << 30)
-#define OMAP3430_ST_ICR_SHIFT				29
-#define OMAP3430_ST_ICR_MASK				(1 << 29)
 #define OMAP3430_ST_AES2_SHIFT				28
-#define OMAP3430_ST_AES2_MASK				(1 << 28)
 #define OMAP3430_ST_SHA12_SHIFT				27
-#define OMAP3430_ST_SHA12_MASK				(1 << 27)
-#define OMAP3430_ST_DES2_SHIFT				26
-#define OMAP3430_ST_DES2_MASK				(1 << 26)
-#define OMAP3430_ST_MSPRO_SHIFT				23
-#define OMAP3430_ST_MSPRO_MASK				(1 << 23)
 #define AM35XX_ST_UART4_SHIFT				23
-#define AM35XX_ST_UART4_MASK				(1 << 23)
 #define OMAP3430_ST_HDQ_SHIFT				22
-#define OMAP3430_ST_HDQ_MASK				(1 << 22)
-#define OMAP3430ES1_ST_FAC_SHIFT			8
-#define OMAP3430ES1_ST_FAC_MASK				(1 << 8)
 #define OMAP3430ES2_ST_SSI_IDLE_SHIFT			8
-#define OMAP3430ES2_ST_SSI_IDLE_MASK			(1 << 8)
 #define OMAP3430_ST_MAILBOXES_SHIFT			7
-#define OMAP3430_ST_MAILBOXES_MASK			(1 << 7)
-#define OMAP3430_ST_OMAPCTRL_SHIFT			6
-#define OMAP3430_ST_OMAPCTRL_MASK			(1 << 6)
 #define OMAP3430_ST_SAD2D_SHIFT				3
-#define OMAP3430_ST_SAD2D_MASK				(1 << 3)
 #define OMAP3430_ST_SDMA_SHIFT				2
-#define OMAP3430_ST_SDMA_MASK				(1 << 2)
-#define OMAP3430_ST_SDRC_SHIFT				1
-#define OMAP3430_ST_SDRC_MASK				(1 << 1)
-#define OMAP3430_ST_SSI_STDBY_SHIFT			0
-#define OMAP3430_ST_SSI_STDBY_MASK			(1 << 0)
-
-/* AM35xx specific CM_IDLEST1_CORE bits */
 #define AM35XX_ST_IPSS_SHIFT				5
-#define AM35XX_ST_IPSS_MASK 				(1 << 5)
-
-/* CM_IDLEST2_CORE */
-#define OMAP3430_ST_PKA_SHIFT				4
-#define OMAP3430_ST_PKA_MASK				(1 << 4)
-#define OMAP3430_ST_AES1_SHIFT				3
-#define OMAP3430_ST_AES1_MASK				(1 << 3)
-#define OMAP3430_ST_RNG_SHIFT				2
-#define OMAP3430_ST_RNG_MASK				(1 << 2)
-#define OMAP3430_ST_SHA11_SHIFT				1
-#define OMAP3430_ST_SHA11_MASK				(1 << 1)
-#define OMAP3430_ST_DES1_SHIFT				0
-#define OMAP3430_ST_DES1_MASK				(1 << 0)
-
-/* CM_IDLEST3_CORE */
 #define OMAP3430ES2_ST_USBTLL_SHIFT			2
-#define OMAP3430ES2_ST_USBTLL_MASK			(1 << 2)
-#define OMAP3430ES2_ST_CPEFUSE_SHIFT			0
-#define OMAP3430ES2_ST_CPEFUSE_MASK			(1 << 0)
-
-/* CM_AUTOIDLE1_CORE */
-#define OMAP3430_AUTO_MODEM_MASK			(1 << 31)
-#define OMAP3430_AUTO_MODEM_SHIFT			31
-#define OMAP3430ES2_AUTO_MMC3_MASK			(1 << 30)
-#define OMAP3430ES2_AUTO_MMC3_SHIFT			30
-#define OMAP3430ES2_AUTO_ICR_MASK			(1 << 29)
-#define OMAP3430ES2_AUTO_ICR_SHIFT			29
-#define OMAP3430_AUTO_AES2_MASK				(1 << 28)
-#define OMAP3430_AUTO_AES2_SHIFT			28
-#define OMAP3430_AUTO_SHA12_MASK			(1 << 27)
-#define OMAP3430_AUTO_SHA12_SHIFT			27
-#define OMAP3430_AUTO_DES2_MASK				(1 << 26)
-#define OMAP3430_AUTO_DES2_SHIFT			26
-#define OMAP3430_AUTO_MMC2_MASK				(1 << 25)
-#define OMAP3430_AUTO_MMC2_SHIFT			25
-#define OMAP3430_AUTO_MMC1_MASK				(1 << 24)
-#define OMAP3430_AUTO_MMC1_SHIFT			24
-#define OMAP3430_AUTO_MSPRO_MASK			(1 << 23)
-#define OMAP3430_AUTO_MSPRO_SHIFT			23
-#define OMAP3430_AUTO_HDQ_MASK				(1 << 22)
-#define OMAP3430_AUTO_HDQ_SHIFT				22
-#define OMAP3430_AUTO_MCSPI4_MASK			(1 << 21)
-#define OMAP3430_AUTO_MCSPI4_SHIFT			21
-#define OMAP3430_AUTO_MCSPI3_MASK			(1 << 20)
-#define OMAP3430_AUTO_MCSPI3_SHIFT			20
-#define OMAP3430_AUTO_MCSPI2_MASK			(1 << 19)
-#define OMAP3430_AUTO_MCSPI2_SHIFT			19
-#define OMAP3430_AUTO_MCSPI1_MASK			(1 << 18)
-#define OMAP3430_AUTO_MCSPI1_SHIFT			18
-#define OMAP3430_AUTO_I2C3_MASK				(1 << 17)
-#define OMAP3430_AUTO_I2C3_SHIFT			17
-#define OMAP3430_AUTO_I2C2_MASK				(1 << 16)
-#define OMAP3430_AUTO_I2C2_SHIFT			16
-#define OMAP3430_AUTO_I2C1_MASK				(1 << 15)
-#define OMAP3430_AUTO_I2C1_SHIFT			15
-#define OMAP3430_AUTO_UART2_MASK			(1 << 14)
-#define OMAP3430_AUTO_UART2_SHIFT			14
-#define OMAP3430_AUTO_UART1_MASK			(1 << 13)
-#define OMAP3430_AUTO_UART1_SHIFT			13
-#define OMAP3430_AUTO_GPT11_MASK			(1 << 12)
-#define OMAP3430_AUTO_GPT11_SHIFT			12
-#define OMAP3430_AUTO_GPT10_MASK			(1 << 11)
-#define OMAP3430_AUTO_GPT10_SHIFT			11
-#define OMAP3430_AUTO_MCBSP5_MASK			(1 << 10)
-#define OMAP3430_AUTO_MCBSP5_SHIFT			10
-#define OMAP3430_AUTO_MCBSP1_MASK			(1 << 9)
-#define OMAP3430_AUTO_MCBSP1_SHIFT			9
-#define OMAP3430ES1_AUTO_FAC_MASK			(1 << 8)
-#define OMAP3430ES1_AUTO_FAC_SHIFT			8
-#define OMAP3430_AUTO_MAILBOXES_MASK			(1 << 7)
-#define OMAP3430_AUTO_MAILBOXES_SHIFT			7
-#define OMAP3430_AUTO_OMAPCTRL_MASK			(1 << 6)
-#define OMAP3430_AUTO_OMAPCTRL_SHIFT			6
-#define OMAP3430ES1_AUTO_FSHOSTUSB_MASK			(1 << 5)
-#define OMAP3430ES1_AUTO_FSHOSTUSB_SHIFT		5
-#define OMAP3430_AUTO_HSOTGUSB_MASK			(1 << 4)
-#define OMAP3430_AUTO_HSOTGUSB_SHIFT			4
-#define OMAP3430ES1_AUTO_D2D_MASK			(1 << 3)
-#define OMAP3430ES1_AUTO_D2D_SHIFT			3
-#define OMAP3430_AUTO_SAD2D_MASK			(1 << 3)
-#define OMAP3430_AUTO_SAD2D_SHIFT			3
-#define OMAP3430_AUTO_SSI_MASK				(1 << 0)
-#define OMAP3430_AUTO_SSI_SHIFT				0
-
-/* CM_AUTOIDLE2_CORE */
-#define OMAP3430_AUTO_PKA_MASK				(1 << 4)
-#define OMAP3430_AUTO_PKA_SHIFT				4
-#define OMAP3430_AUTO_AES1_MASK				(1 << 3)
-#define OMAP3430_AUTO_AES1_SHIFT			3
-#define OMAP3430_AUTO_RNG_MASK				(1 << 2)
-#define OMAP3430_AUTO_RNG_SHIFT				2
-#define OMAP3430_AUTO_SHA11_MASK			(1 << 1)
-#define OMAP3430_AUTO_SHA11_SHIFT			1
-#define OMAP3430_AUTO_DES1_MASK				(1 << 0)
-#define OMAP3430_AUTO_DES1_SHIFT			0
-
-/* CM_AUTOIDLE3_CORE */
-#define	OMAP3430ES2_AUTO_USBHOST			(1 << 0)
-#define	OMAP3430ES2_AUTO_USBHOST_SHIFT			0
-#define	OMAP3430ES2_AUTO_USBTLL				(1 << 2)
-#define OMAP3430ES2_AUTO_USBTLL_SHIFT			2
-#define OMAP3430ES2_AUTO_USBTLL_MASK			(1 << 2)
-#define OMAP3430_AUTO_MAD2D_SHIFT			3
-#define OMAP3430_AUTO_MAD2D_MASK			(1 << 3)
-
-/* CM_CLKSEL_CORE */
-#define OMAP3430_CLKSEL_SSI_SHIFT			8
 #define OMAP3430_CLKSEL_SSI_MASK			(0xf << 8)
 #define OMAP3430_CLKSEL_GPT11_MASK			(1 << 7)
-#define OMAP3430_CLKSEL_GPT11_SHIFT			7
 #define OMAP3430_CLKSEL_GPT10_MASK			(1 << 6)
-#define OMAP3430_CLKSEL_GPT10_SHIFT			6
-#define OMAP3430ES1_CLKSEL_FSHOSTUSB_SHIFT		4
 #define OMAP3430ES1_CLKSEL_FSHOSTUSB_MASK		(0x3 << 4)
 #define OMAP3430_CLKSEL_L4_SHIFT			2
-#define OMAP3430_CLKSEL_L4_MASK				(0x3 << 2)
 #define OMAP3430_CLKSEL_L4_WIDTH			2
 #define OMAP3430_CLKSEL_L3_SHIFT			0
-#define OMAP3430_CLKSEL_L3_MASK				(0x3 << 0)
 #define OMAP3430_CLKSEL_L3_WIDTH			2
-#define OMAP3630_CLKSEL_96M_SHIFT			12
 #define OMAP3630_CLKSEL_96M_MASK			(0x3 << 12)
-#define OMAP3630_CLKSEL_96M_WIDTH			2
-
-/* CM_CLKSTCTRL_CORE */
-#define OMAP3430ES1_CLKTRCTRL_D2D_SHIFT			4
 #define OMAP3430ES1_CLKTRCTRL_D2D_MASK			(0x3 << 4)
-#define OMAP3430_CLKTRCTRL_L4_SHIFT			2
 #define OMAP3430_CLKTRCTRL_L4_MASK			(0x3 << 2)
-#define OMAP3430_CLKTRCTRL_L3_SHIFT			0
 #define OMAP3430_CLKTRCTRL_L3_MASK			(0x3 << 0)
-
-/* CM_CLKSTST_CORE */
-#define OMAP3430ES1_CLKACTIVITY_D2D_SHIFT		2
-#define OMAP3430ES1_CLKACTIVITY_D2D_MASK		(1 << 2)
-#define OMAP3430_CLKACTIVITY_L4_SHIFT			1
-#define OMAP3430_CLKACTIVITY_L4_MASK			(1 << 1)
-#define OMAP3430_CLKACTIVITY_L3_SHIFT			0
-#define OMAP3430_CLKACTIVITY_L3_MASK			(1 << 0)
-
-/* CM_FCLKEN_GFX */
-#define OMAP3430ES1_EN_3D_MASK				(1 << 2)
 #define OMAP3430ES1_EN_3D_SHIFT				2
-#define OMAP3430ES1_EN_2D_MASK				(1 << 1)
 #define OMAP3430ES1_EN_2D_SHIFT				1
-
-/* CM_ICLKEN_GFX specific bits */
-
-/* CM_IDLEST_GFX specific bits */
-
-/* CM_CLKSEL_GFX specific bits */
-
-/* CM_SLEEPDEP_GFX specific bits */
-
-/* CM_CLKSTCTRL_GFX */
-#define OMAP3430ES1_CLKTRCTRL_GFX_SHIFT			0
 #define OMAP3430ES1_CLKTRCTRL_GFX_MASK			(0x3 << 0)
-
-/* CM_CLKSTST_GFX */
-#define OMAP3430ES1_CLKACTIVITY_GFX_SHIFT		0
-#define OMAP3430ES1_CLKACTIVITY_GFX_MASK		(1 << 0)
-
-/* CM_FCLKEN_SGX */
 #define OMAP3430ES2_CM_FCLKEN_SGX_EN_SGX_SHIFT		1
-#define OMAP3430ES2_CM_FCLKEN_SGX_EN_SGX_MASK		(1 << 1)
-
-/* CM_IDLEST_SGX */
-#define OMAP3430ES2_ST_SGX_SHIFT			1
-#define OMAP3430ES2_ST_SGX_MASK				(1 << 1)
-
-/* CM_ICLKEN_SGX */
 #define OMAP3430ES2_CM_ICLKEN_SGX_EN_SGX_SHIFT		0
-#define OMAP3430ES2_CM_ICLKEN_SGX_EN_SGX_MASK		(1 << 0)
-
-/* CM_CLKSEL_SGX */
-#define OMAP3430ES2_CLKSEL_SGX_SHIFT			0
 #define OMAP3430ES2_CLKSEL_SGX_MASK			(0x7 << 0)
-
-/* CM_CLKSTCTRL_SGX */
-#define OMAP3430ES2_CLKTRCTRL_SGX_SHIFT			0
 #define OMAP3430ES2_CLKTRCTRL_SGX_MASK			(0x3 << 0)
-
-/* CM_CLKSTST_SGX */
-#define OMAP3430ES2_CLKACTIVITY_SGX_SHIFT		0
-#define OMAP3430ES2_CLKACTIVITY_SGX_MASK		(1 << 0)
-
-/* CM_FCLKEN_WKUP specific bits */
 #define OMAP3430ES2_EN_USIMOCP_SHIFT			9
-#define OMAP3430ES2_EN_USIMOCP_MASK			(1 << 9)
-
-/* CM_ICLKEN_WKUP specific bits */
-#define OMAP3430_EN_WDT1_MASK				(1 << 4)
 #define OMAP3430_EN_WDT1_SHIFT				4
-#define OMAP3430_EN_32KSYNC_MASK			(1 << 2)
 #define OMAP3430_EN_32KSYNC_SHIFT			2
-
-/* CM_IDLEST_WKUP specific bits */
-#define OMAP3430ES2_ST_USIMOCP_SHIFT			9
-#define OMAP3430ES2_ST_USIMOCP_MASK			(1 << 9)
 #define OMAP3430_ST_WDT2_SHIFT				5
-#define OMAP3430_ST_WDT2_MASK				(1 << 5)
-#define OMAP3430_ST_WDT1_SHIFT				4
-#define OMAP3430_ST_WDT1_MASK				(1 << 4)
 #define OMAP3430_ST_32KSYNC_SHIFT			2
-#define OMAP3430_ST_32KSYNC_MASK			(1 << 2)
-
-/* CM_AUTOIDLE_WKUP */
-#define OMAP3430ES2_AUTO_USIMOCP_MASK			(1 << 9)
-#define OMAP3430ES2_AUTO_USIMOCP_SHIFT			9
-#define OMAP3430_AUTO_WDT2_MASK				(1 << 5)
-#define OMAP3430_AUTO_WDT2_SHIFT			5
-#define OMAP3430_AUTO_WDT1_MASK				(1 << 4)
-#define OMAP3430_AUTO_WDT1_SHIFT			4
-#define OMAP3430_AUTO_GPIO1_MASK			(1 << 3)
-#define OMAP3430_AUTO_GPIO1_SHIFT			3
-#define OMAP3430_AUTO_32KSYNC_MASK			(1 << 2)
-#define OMAP3430_AUTO_32KSYNC_SHIFT			2
-#define OMAP3430_AUTO_GPT12_MASK			(1 << 1)
-#define OMAP3430_AUTO_GPT12_SHIFT			1
-#define OMAP3430_AUTO_GPT1_MASK				(1 << 0)
-#define OMAP3430_AUTO_GPT1_SHIFT			0
-
-/* CM_CLKSEL_WKUP */
 #define OMAP3430ES2_CLKSEL_USIMOCP_MASK			(0xf << 3)
 #define OMAP3430_CLKSEL_RM_SHIFT			1
-#define OMAP3430_CLKSEL_RM_MASK				(0x3 << 1)
 #define OMAP3430_CLKSEL_RM_WIDTH			2
-#define OMAP3430_CLKSEL_GPT1_SHIFT			0
 #define OMAP3430_CLKSEL_GPT1_MASK			(1 << 0)
-
-/* CM_CLKEN_PLL */
 #define OMAP3430_PWRDN_EMU_PERIPH_SHIFT			31
 #define OMAP3430_PWRDN_CAM_SHIFT			30
 #define OMAP3430_PWRDN_DSS1_SHIFT			29
 #define OMAP3430_PWRDN_TV_SHIFT				28
 #define OMAP3430_PWRDN_96M_SHIFT			27
-#define OMAP3430_PERIPH_DPLL_RAMPTIME_SHIFT		24
-#define OMAP3430_PERIPH_DPLL_RAMPTIME_MASK		(0x3 << 24)
-#define OMAP3430_PERIPH_DPLL_FREQSEL_SHIFT		20
 #define OMAP3430_PERIPH_DPLL_FREQSEL_MASK		(0xf << 20)
 #define OMAP3430_EN_PERIPH_DPLL_DRIFTGUARD_SHIFT	19
-#define OMAP3430_EN_PERIPH_DPLL_DRIFTGUARD_MASK		(1 << 19)
-#define OMAP3430_EN_PERIPH_DPLL_SHIFT			16
 #define OMAP3430_EN_PERIPH_DPLL_MASK			(0x7 << 16)
 #define OMAP3430_PWRDN_EMU_CORE_SHIFT			12
-#define OMAP3430_CORE_DPLL_RAMPTIME_SHIFT		8
-#define OMAP3430_CORE_DPLL_RAMPTIME_MASK		(0x3 << 8)
-#define OMAP3430_CORE_DPLL_FREQSEL_SHIFT		4
 #define OMAP3430_CORE_DPLL_FREQSEL_MASK			(0xf << 4)
 #define OMAP3430_EN_CORE_DPLL_DRIFTGUARD_SHIFT		3
-#define OMAP3430_EN_CORE_DPLL_DRIFTGUARD_MASK		(1 << 3)
-#define OMAP3430_EN_CORE_DPLL_SHIFT			0
 #define OMAP3430_EN_CORE_DPLL_MASK			(0x7 << 0)
-
-/* CM_CLKEN2_PLL */
-#define OMAP3430ES2_EN_PERIPH2_DPLL_LPMODE_SHIFT	10
-#define OMAP3430ES2_PERIPH2_DPLL_RAMPTIME_MASK		(0x3 << 8)
-#define OMAP3430ES2_PERIPH2_DPLL_FREQSEL_SHIFT		4
 #define OMAP3430ES2_PERIPH2_DPLL_FREQSEL_MASK		(0xf << 4)
 #define OMAP3430ES2_EN_PERIPH2_DPLL_DRIFTGUARD_SHIFT	3
-#define OMAP3430ES2_EN_PERIPH2_DPLL_SHIFT		0
 #define OMAP3430ES2_EN_PERIPH2_DPLL_MASK		(0x7 << 0)
-
-/* CM_IDLEST_CKGEN */
-#define OMAP3430_ST_54M_CLK_MASK			(1 << 5)
-#define OMAP3430_ST_12M_CLK_MASK			(1 << 4)
-#define OMAP3430_ST_48M_CLK_MASK			(1 << 3)
-#define OMAP3430_ST_96M_CLK_MASK			(1 << 2)
-#define OMAP3430_ST_PERIPH_CLK_SHIFT			1
 #define OMAP3430_ST_PERIPH_CLK_MASK			(1 << 1)
-#define OMAP3430_ST_CORE_CLK_SHIFT			0
 #define OMAP3430_ST_CORE_CLK_MASK			(1 << 0)
-
-/* CM_IDLEST2_CKGEN */
-#define OMAP3430ES2_ST_USIM_CLK_SHIFT			2
-#define OMAP3430ES2_ST_USIM_CLK_MASK			(1 << 2)
-#define OMAP3430ES2_ST_120M_CLK_SHIFT			1
-#define OMAP3430ES2_ST_120M_CLK_MASK			(1 << 1)
-#define OMAP3430ES2_ST_PERIPH2_CLK_SHIFT		0
 #define OMAP3430ES2_ST_PERIPH2_CLK_MASK			(1 << 0)
-
-/* CM_AUTOIDLE_PLL */
-#define OMAP3430_AUTO_PERIPH_DPLL_SHIFT			3
 #define OMAP3430_AUTO_PERIPH_DPLL_MASK			(0x7 << 3)
-#define OMAP3430_AUTO_CORE_DPLL_SHIFT			0
 #define OMAP3430_AUTO_CORE_DPLL_MASK			(0x7 << 0)
-
-/* CM_AUTOIDLE2_PLL */
-#define OMAP3430ES2_AUTO_PERIPH2_DPLL_SHIFT		0
 #define OMAP3430ES2_AUTO_PERIPH2_DPLL_MASK		(0x7 << 0)
-
-/* CM_CLKSEL1_PLL */
-/* Note that OMAP3430_CORE_DPLL_CLKOUT_DIV_MASK was (0x3 << 27) on 3430ES1 */
 #define OMAP3430_CORE_DPLL_CLKOUT_DIV_SHIFT		27
-#define OMAP3430_CORE_DPLL_CLKOUT_DIV_MASK		(0x1f << 27)
 #define OMAP3430_CORE_DPLL_CLKOUT_DIV_WIDTH		5
-#define OMAP3430_CORE_DPLL_MULT_SHIFT			16
 #define OMAP3430_CORE_DPLL_MULT_MASK			(0x7ff << 16)
-#define OMAP3430_CORE_DPLL_DIV_SHIFT			8
 #define OMAP3430_CORE_DPLL_DIV_MASK			(0x7f << 8)
 #define OMAP3430_SOURCE_96M_SHIFT			6
-#define OMAP3430_SOURCE_96M_MASK			(1 << 6)
 #define OMAP3430_SOURCE_96M_WIDTH			1
 #define OMAP3430_SOURCE_54M_SHIFT			5
-#define OMAP3430_SOURCE_54M_MASK			(1 << 5)
 #define OMAP3430_SOURCE_54M_WIDTH			1
-#define OMAP3430_SOURCE_48M_SHIFT			3
 #define OMAP3430_SOURCE_48M_MASK			(1 << 3)
-
-/* CM_CLKSEL2_PLL */
-#define OMAP3430_PERIPH_DPLL_MULT_SHIFT			8
 #define OMAP3430_PERIPH_DPLL_MULT_MASK			(0x7ff << 8)
 #define OMAP3630_PERIPH_DPLL_MULT_MASK			(0xfff << 8)
-#define OMAP3430_PERIPH_DPLL_DIV_SHIFT			0
 #define OMAP3430_PERIPH_DPLL_DIV_MASK			(0x7f << 0)
-#define OMAP3630_PERIPH_DPLL_DCO_SEL_SHIFT		21
 #define OMAP3630_PERIPH_DPLL_DCO_SEL_MASK		(0x7 << 21)
-#define OMAP3630_PERIPH_DPLL_SD_DIV_SHIFT		24
 #define OMAP3630_PERIPH_DPLL_SD_DIV_MASK		(0xff << 24)
-
-/* CM_CLKSEL3_PLL */
 #define OMAP3430_DIV_96M_SHIFT				0
-#define OMAP3430_DIV_96M_MASK				(0x1f << 0)
-#define OMAP3430_DIV_96M_WIDTH				5
-#define OMAP3630_DIV_96M_MASK				(0x3f << 0)
 #define OMAP3630_DIV_96M_WIDTH				6
-
-/* CM_CLKSEL4_PLL */
-#define OMAP3430ES2_PERIPH2_DPLL_MULT_SHIFT		8
 #define OMAP3430ES2_PERIPH2_DPLL_MULT_MASK		(0x7ff << 8)
-#define OMAP3430ES2_PERIPH2_DPLL_DIV_SHIFT		0
 #define OMAP3430ES2_PERIPH2_DPLL_DIV_MASK		(0x7f << 0)
-
-/* CM_CLKSEL5_PLL */
 #define OMAP3430ES2_DIV_120M_SHIFT			0
-#define OMAP3430ES2_DIV_120M_MASK			(0x1f << 0)
 #define OMAP3430ES2_DIV_120M_WIDTH			5
-
-/* CM_CLKOUT_CTRL */
 #define OMAP3430_CLKOUT2_EN_SHIFT			7
-#define OMAP3430_CLKOUT2_EN_MASK			(1 << 7)
 #define OMAP3430_CLKOUT2_DIV_SHIFT			3
-#define OMAP3430_CLKOUT2_DIV_MASK			(0x7 << 3)
 #define OMAP3430_CLKOUT2_DIV_WIDTH			3
-#define OMAP3430_CLKOUT2SOURCE_SHIFT			0
 #define OMAP3430_CLKOUT2SOURCE_MASK			(0x3 << 0)
-
-/* CM_FCLKEN_DSS */
-#define OMAP3430_EN_TV_MASK				(1 << 2)
 #define OMAP3430_EN_TV_SHIFT				2
-#define OMAP3430_EN_DSS2_MASK				(1 << 1)
 #define OMAP3430_EN_DSS2_SHIFT				1
-#define OMAP3430_EN_DSS1_MASK				(1 << 0)
 #define OMAP3430_EN_DSS1_SHIFT				0
-
-/* CM_ICLKEN_DSS */
-#define OMAP3430_CM_ICLKEN_DSS_EN_DSS_MASK		(1 << 0)
 #define OMAP3430_CM_ICLKEN_DSS_EN_DSS_SHIFT		0
-
-/* CM_IDLEST_DSS */
 #define OMAP3430ES2_ST_DSS_IDLE_SHIFT			1
-#define OMAP3430ES2_ST_DSS_IDLE_MASK			(1 << 1)
 #define OMAP3430ES2_ST_DSS_STDBY_SHIFT			0
-#define OMAP3430ES2_ST_DSS_STDBY_MASK			(1 << 0)
 #define OMAP3430ES1_ST_DSS_SHIFT			0
-#define OMAP3430ES1_ST_DSS_MASK				(1 << 0)
-
-/* CM_AUTOIDLE_DSS */
-#define OMAP3430_AUTO_DSS_MASK				(1 << 0)
-#define OMAP3430_AUTO_DSS_SHIFT				0
-
-/* CM_CLKSEL_DSS */
 #define OMAP3430_CLKSEL_TV_SHIFT			8
-#define OMAP3430_CLKSEL_TV_MASK				(0x1f << 8)
-#define OMAP3430_CLKSEL_TV_WIDTH			5
-#define OMAP3630_CLKSEL_TV_MASK				(0x3f << 8)
 #define OMAP3630_CLKSEL_TV_WIDTH			6
 #define OMAP3430_CLKSEL_DSS1_SHIFT			0
-#define OMAP3430_CLKSEL_DSS1_MASK			(0x1f << 0)
-#define OMAP3430_CLKSEL_DSS1_WIDTH			5
-#define OMAP3630_CLKSEL_DSS1_MASK			(0x3f << 0)
 #define OMAP3630_CLKSEL_DSS1_WIDTH			6
-
-/* CM_SLEEPDEP_DSS specific bits */
-
-/* CM_CLKSTCTRL_DSS */
-#define OMAP3430_CLKTRCTRL_DSS_SHIFT			0
 #define OMAP3430_CLKTRCTRL_DSS_MASK			(0x3 << 0)
-
-/* CM_CLKSTST_DSS */
-#define OMAP3430_CLKACTIVITY_DSS_SHIFT			0
-#define OMAP3430_CLKACTIVITY_DSS_MASK			(1 << 0)
-
-/* CM_FCLKEN_CAM specific bits */
-#define OMAP3430_EN_CSI2_MASK				(1 << 1)
 #define OMAP3430_EN_CSI2_SHIFT				1
-
-/* CM_ICLKEN_CAM specific bits */
-
-/* CM_IDLEST_CAM */
-#define OMAP3430_ST_CAM_MASK				(1 << 0)
-
-/* CM_AUTOIDLE_CAM */
-#define OMAP3430_AUTO_CAM_MASK				(1 << 0)
-#define OMAP3430_AUTO_CAM_SHIFT				0
-
-/* CM_CLKSEL_CAM */
 #define OMAP3430_CLKSEL_CAM_SHIFT			0
-#define OMAP3430_CLKSEL_CAM_MASK			(0x1f << 0)
-#define OMAP3430_CLKSEL_CAM_WIDTH			5
-#define OMAP3630_CLKSEL_CAM_MASK			(0x3f << 0)
 #define OMAP3630_CLKSEL_CAM_WIDTH			6
-
-/* CM_SLEEPDEP_CAM specific bits */
-
-/* CM_CLKSTCTRL_CAM */
-#define OMAP3430_CLKTRCTRL_CAM_SHIFT			0
 #define OMAP3430_CLKTRCTRL_CAM_MASK			(0x3 << 0)
-
-/* CM_CLKSTST_CAM */
-#define OMAP3430_CLKACTIVITY_CAM_SHIFT			0
-#define OMAP3430_CLKACTIVITY_CAM_MASK			(1 << 0)
-
-/* CM_FCLKEN_PER specific bits */
-
-/* CM_ICLKEN_PER specific bits */
-
-/* CM_IDLEST_PER */
-#define OMAP3430_ST_WDT3_SHIFT				12
-#define OMAP3430_ST_WDT3_MASK				(1 << 12)
 #define OMAP3430_ST_MCBSP4_SHIFT			2
-#define OMAP3430_ST_MCBSP4_MASK				(1 << 2)
 #define OMAP3430_ST_MCBSP3_SHIFT			1
-#define OMAP3430_ST_MCBSP3_MASK				(1 << 1)
 #define OMAP3430_ST_MCBSP2_SHIFT			0
-#define OMAP3430_ST_MCBSP2_MASK				(1 << 0)
-
-/* CM_AUTOIDLE_PER */
-#define OMAP3630_AUTO_UART4_MASK			(1 << 18)
-#define OMAP3630_AUTO_UART4_SHIFT			18
-#define OMAP3430_AUTO_GPIO6_MASK			(1 << 17)
-#define OMAP3430_AUTO_GPIO6_SHIFT			17
-#define OMAP3430_AUTO_GPIO5_MASK			(1 << 16)
-#define OMAP3430_AUTO_GPIO5_SHIFT			16
-#define OMAP3430_AUTO_GPIO4_MASK			(1 << 15)
-#define OMAP3430_AUTO_GPIO4_SHIFT			15
-#define OMAP3430_AUTO_GPIO3_MASK			(1 << 14)
-#define OMAP3430_AUTO_GPIO3_SHIFT			14
-#define OMAP3430_AUTO_GPIO2_MASK			(1 << 13)
-#define OMAP3430_AUTO_GPIO2_SHIFT			13
-#define OMAP3430_AUTO_WDT3_MASK				(1 << 12)
-#define OMAP3430_AUTO_WDT3_SHIFT			12
-#define OMAP3430_AUTO_UART3_MASK			(1 << 11)
-#define OMAP3430_AUTO_UART3_SHIFT			11
-#define OMAP3430_AUTO_GPT9_MASK				(1 << 10)
-#define OMAP3430_AUTO_GPT9_SHIFT			10
-#define OMAP3430_AUTO_GPT8_MASK				(1 << 9)
-#define OMAP3430_AUTO_GPT8_SHIFT			9
-#define OMAP3430_AUTO_GPT7_MASK				(1 << 8)
-#define OMAP3430_AUTO_GPT7_SHIFT			8
-#define OMAP3430_AUTO_GPT6_MASK				(1 << 7)
-#define OMAP3430_AUTO_GPT6_SHIFT			7
-#define OMAP3430_AUTO_GPT5_MASK				(1 << 6)
-#define OMAP3430_AUTO_GPT5_SHIFT			6
-#define OMAP3430_AUTO_GPT4_MASK				(1 << 5)
-#define OMAP3430_AUTO_GPT4_SHIFT			5
-#define OMAP3430_AUTO_GPT3_MASK				(1 << 4)
-#define OMAP3430_AUTO_GPT3_SHIFT			4
-#define OMAP3430_AUTO_GPT2_MASK				(1 << 3)
-#define OMAP3430_AUTO_GPT2_SHIFT			3
-#define OMAP3430_AUTO_MCBSP4_MASK			(1 << 2)
-#define OMAP3430_AUTO_MCBSP4_SHIFT			2
-#define OMAP3430_AUTO_MCBSP3_MASK			(1 << 1)
-#define OMAP3430_AUTO_MCBSP3_SHIFT			1
-#define OMAP3430_AUTO_MCBSP2_MASK			(1 << 0)
-#define OMAP3430_AUTO_MCBSP2_SHIFT			0
-
-/* CM_CLKSEL_PER */
 #define OMAP3430_CLKSEL_GPT9_MASK			(1 << 7)
-#define OMAP3430_CLKSEL_GPT9_SHIFT			7
 #define OMAP3430_CLKSEL_GPT8_MASK			(1 << 6)
-#define OMAP3430_CLKSEL_GPT8_SHIFT			6
 #define OMAP3430_CLKSEL_GPT7_MASK			(1 << 5)
-#define OMAP3430_CLKSEL_GPT7_SHIFT			5
 #define OMAP3430_CLKSEL_GPT6_MASK			(1 << 4)
-#define OMAP3430_CLKSEL_GPT6_SHIFT			4
 #define OMAP3430_CLKSEL_GPT5_MASK			(1 << 3)
-#define OMAP3430_CLKSEL_GPT5_SHIFT			3
 #define OMAP3430_CLKSEL_GPT4_MASK			(1 << 2)
-#define OMAP3430_CLKSEL_GPT4_SHIFT			2
 #define OMAP3430_CLKSEL_GPT3_MASK			(1 << 1)
-#define OMAP3430_CLKSEL_GPT3_SHIFT			1
 #define OMAP3430_CLKSEL_GPT2_MASK			(1 << 0)
-#define OMAP3430_CLKSEL_GPT2_SHIFT			0
-
-/* CM_SLEEPDEP_PER specific bits */
-#define OMAP3430_CM_SLEEPDEP_PER_EN_IVA2_MASK		(1 << 2)
-
-/* CM_CLKSTCTRL_PER */
-#define OMAP3430_CLKTRCTRL_PER_SHIFT			0
 #define OMAP3430_CLKTRCTRL_PER_MASK			(0x3 << 0)
-
-/* CM_CLKSTST_PER */
-#define OMAP3430_CLKACTIVITY_PER_SHIFT			0
-#define OMAP3430_CLKACTIVITY_PER_MASK			(1 << 0)
-
-/* CM_CLKSEL1_EMU */
 #define OMAP3430_DIV_DPLL4_SHIFT			24
-#define OMAP3430_DIV_DPLL4_MASK				(0x1f << 24)
-#define OMAP3430_DIV_DPLL4_WIDTH			5
-#define OMAP3630_DIV_DPLL4_MASK				(0x3f << 24)
 #define OMAP3630_DIV_DPLL4_WIDTH			6
 #define OMAP3430_DIV_DPLL3_SHIFT			16
-#define OMAP3430_DIV_DPLL3_MASK				(0x1f << 16)
 #define OMAP3430_DIV_DPLL3_WIDTH			5
 #define OMAP3430_CLKSEL_TRACECLK_SHIFT			11
-#define OMAP3430_CLKSEL_TRACECLK_MASK			(0x7 << 11)
 #define OMAP3430_CLKSEL_TRACECLK_WIDTH			3
 #define OMAP3430_CLKSEL_PCLK_SHIFT			8
-#define OMAP3430_CLKSEL_PCLK_MASK			(0x7 << 8)
 #define OMAP3430_CLKSEL_PCLK_WIDTH			3
 #define OMAP3430_CLKSEL_PCLKX2_SHIFT			6
-#define OMAP3430_CLKSEL_PCLKX2_MASK			(0x3 << 6)
 #define OMAP3430_CLKSEL_PCLKX2_WIDTH			2
 #define OMAP3430_CLKSEL_ATCLK_SHIFT			4
-#define OMAP3430_CLKSEL_ATCLK_MASK			(0x3 << 4)
 #define OMAP3430_CLKSEL_ATCLK_WIDTH			2
 #define OMAP3430_TRACE_MUX_CTRL_SHIFT			2
-#define OMAP3430_TRACE_MUX_CTRL_MASK			(0x3 << 2)
 #define OMAP3430_TRACE_MUX_CTRL_WIDTH			2
-#define OMAP3430_MUX_CTRL_SHIFT				0
 #define OMAP3430_MUX_CTRL_MASK				(0x3 << 0)
-#define OMAP3430_MUX_CTRL_WIDTH				2
-
-/* CM_CLKSTCTRL_EMU */
-#define OMAP3430_CLKTRCTRL_EMU_SHIFT			0
 #define OMAP3430_CLKTRCTRL_EMU_MASK			(0x3 << 0)
-
-/* CM_CLKSTST_EMU */
-#define OMAP3430_CLKACTIVITY_EMU_SHIFT			0
-#define OMAP3430_CLKACTIVITY_EMU_MASK			(1 << 0)
-
-/* CM_CLKSEL2_EMU specific bits */
-#define OMAP3430_CORE_DPLL_EMU_MULT_SHIFT		8
-#define OMAP3430_CORE_DPLL_EMU_MULT_MASK		(0x7ff << 8)
-#define OMAP3430_CORE_DPLL_EMU_DIV_SHIFT		0
-#define OMAP3430_CORE_DPLL_EMU_DIV_MASK			(0x7f << 0)
-
-/* CM_CLKSEL3_EMU specific bits */
-#define OMAP3430_PERIPH_DPLL_EMU_MULT_SHIFT		8
-#define OMAP3430_PERIPH_DPLL_EMU_MULT_MASK		(0x7ff << 8)
-#define OMAP3430_PERIPH_DPLL_EMU_DIV_SHIFT		0
-#define OMAP3430_PERIPH_DPLL_EMU_DIV_MASK		(0x7f << 0)
-
-/* CM_POLCTRL */
-#define OMAP3430_CLKOUT2_POL_MASK			(1 << 0)
-
-/* CM_IDLEST_NEON */
-#define OMAP3430_ST_NEON_MASK				(1 << 0)
-
-/* CM_CLKSTCTRL_NEON */
-#define OMAP3430_CLKTRCTRL_NEON_SHIFT			0
 #define OMAP3430_CLKTRCTRL_NEON_MASK			(0x3 << 0)
-
-/* CM_FCLKEN_USBHOST */
 #define OMAP3430ES2_EN_USBHOST2_SHIFT			1
-#define OMAP3430ES2_EN_USBHOST2_MASK			(1 << 1)
 #define OMAP3430ES2_EN_USBHOST1_SHIFT			0
-#define OMAP3430ES2_EN_USBHOST1_MASK			(1 << 0)
-
-/* CM_ICLKEN_USBHOST */
 #define OMAP3430ES2_EN_USBHOST_SHIFT			0
-#define OMAP3430ES2_EN_USBHOST_MASK			(1 << 0)
-
-/* CM_IDLEST_USBHOST */
 #define OMAP3430ES2_ST_USBHOST_IDLE_SHIFT		1
-#define OMAP3430ES2_ST_USBHOST_IDLE_MASK		(1 << 1)
 #define OMAP3430ES2_ST_USBHOST_STDBY_SHIFT		0
-#define OMAP3430ES2_ST_USBHOST_STDBY_MASK		(1 << 0)
-
-/* CM_AUTOIDLE_USBHOST */
-#define OMAP3430ES2_AUTO_USBHOST_SHIFT			0
-#define OMAP3430ES2_AUTO_USBHOST_MASK			(1 << 0)
-
-/* CM_SLEEPDEP_USBHOST */
-#define OMAP3430ES2_EN_MPU_SHIFT			1
-#define OMAP3430ES2_EN_MPU_MASK				(1 << 1)
-#define OMAP3430ES2_EN_IVA2_SHIFT			2
-#define OMAP3430ES2_EN_IVA2_MASK			(1 << 2)
-
-/* CM_CLKSTCTRL_USBHOST */
-#define OMAP3430ES2_CLKTRCTRL_USBHOST_SHIFT		0
 #define OMAP3430ES2_CLKTRCTRL_USBHOST_MASK		(3 << 0)
-
-/* CM_CLKSTST_USBHOST */
-#define OMAP3430ES2_CLKACTIVITY_USBHOST_SHIFT		0
-#define OMAP3430ES2_CLKACTIVITY_USBHOST_MASK		(1 << 0)
-
-/*
- *
- */
-
-/* OMAP3XXX CM_CLKSTCTRL_*.CLKTRCTRL_* register bit values */
 #define OMAP34XX_CLKSTCTRL_DISABLE_AUTO		0x0
 #define OMAP34XX_CLKSTCTRL_FORCE_SLEEP		0x1
 #define OMAP34XX_CLKSTCTRL_FORCE_WAKEUP		0x2
 #define OMAP34XX_CLKSTCTRL_ENABLE_AUTO		0x3
-
-
 #endif
diff --git a/arch/arm/mach-omap2/cm-regbits-44xx.h b/arch/arm/mach-omap2/cm-regbits-44xx.h
index 4c6c2f7de65b..4dbbd99b6e1e 100644
--- a/arch/arm/mach-omap2/cm-regbits-44xx.h
+++ b/arch/arm/mach-omap2/cm-regbits-44xx.h
@@ -22,1683 +22,125 @@
 #ifndef __ARCH_ARM_MACH_OMAP2_CM_REGBITS_44XX_H
 #define __ARCH_ARM_MACH_OMAP2_CM_REGBITS_44XX_H
 
-/* Used by CM_L3_1_DYNAMICDEP, CM_MPU_DYNAMICDEP, CM_TESLA_DYNAMICDEP */
-#define OMAP4430_ABE_DYNDEP_SHIFT				3
-#define OMAP4430_ABE_DYNDEP_WIDTH				0x1
-#define OMAP4430_ABE_DYNDEP_MASK				(1 << 3)
-
-/*
- * Used by CM_D2D_STATICDEP, CM_DUCATI_STATICDEP, CM_L3INIT_STATICDEP,
- * CM_MPU_STATICDEP, CM_SDMA_STATICDEP, CM_TESLA_STATICDEP
- */
 #define OMAP4430_ABE_STATDEP_SHIFT				3
-#define OMAP4430_ABE_STATDEP_WIDTH				0x1
-#define OMAP4430_ABE_STATDEP_MASK				(1 << 3)
-
-/* Used by CM_L4CFG_DYNAMICDEP */
-#define OMAP4430_ALWONCORE_DYNDEP_SHIFT				16
-#define OMAP4430_ALWONCORE_DYNDEP_WIDTH				0x1
-#define OMAP4430_ALWONCORE_DYNDEP_MASK				(1 << 16)
-
-/* Used by CM_DUCATI_STATICDEP, CM_MPU_STATICDEP, CM_TESLA_STATICDEP */
-#define OMAP4430_ALWONCORE_STATDEP_SHIFT			16
-#define OMAP4430_ALWONCORE_STATDEP_WIDTH			0x1
-#define OMAP4430_ALWONCORE_STATDEP_MASK				(1 << 16)
-
-/*
- * Used by CM_AUTOIDLE_DPLL_ABE, CM_AUTOIDLE_DPLL_CORE,
- * CM_AUTOIDLE_DPLL_DDRPHY, CM_AUTOIDLE_DPLL_IVA, CM_AUTOIDLE_DPLL_MPU,
- * CM_AUTOIDLE_DPLL_PER, CM_AUTOIDLE_DPLL_UNIPRO, CM_AUTOIDLE_DPLL_USB
- */
-#define OMAP4430_AUTO_DPLL_MODE_SHIFT				0
-#define OMAP4430_AUTO_DPLL_MODE_WIDTH				0x3
 #define OMAP4430_AUTO_DPLL_MODE_MASK				(0x7 << 0)
-
-/* Used by CM_L4CFG_DYNAMICDEP */
-#define OMAP4430_CEFUSE_DYNDEP_SHIFT				17
-#define OMAP4430_CEFUSE_DYNDEP_WIDTH				0x1
-#define OMAP4430_CEFUSE_DYNDEP_MASK				(1 << 17)
-
-/* Used by CM_DUCATI_STATICDEP, CM_MPU_STATICDEP, CM_TESLA_STATICDEP */
-#define OMAP4430_CEFUSE_STATDEP_SHIFT				17
-#define OMAP4430_CEFUSE_STATDEP_WIDTH				0x1
-#define OMAP4430_CEFUSE_STATDEP_MASK				(1 << 17)
-
-/* Used by CM1_ABE_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_ABE_24M_GFCLK_SHIFT		13
-#define OMAP4430_CLKACTIVITY_ABE_24M_GFCLK_WIDTH		0x1
-#define OMAP4430_CLKACTIVITY_ABE_24M_GFCLK_MASK			(1 << 13)
-
-/* Used by CM1_ABE_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_ABE_ALWON_32K_CLK_SHIFT		12
-#define OMAP4430_CLKACTIVITY_ABE_ALWON_32K_CLK_WIDTH		0x1
-#define OMAP4430_CLKACTIVITY_ABE_ALWON_32K_CLK_MASK		(1 << 12)
-
-/* Used by CM_WKUP_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_ABE_LP_CLK_SHIFT			9
-#define OMAP4430_CLKACTIVITY_ABE_LP_CLK_WIDTH			0x1
-#define OMAP4430_CLKACTIVITY_ABE_LP_CLK_MASK			(1 << 9)
-
-/* Used by CM1_ABE_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_ABE_SYSCLK_SHIFT			11
-#define OMAP4430_CLKACTIVITY_ABE_SYSCLK_WIDTH			0x1
-#define OMAP4430_CLKACTIVITY_ABE_SYSCLK_MASK			(1 << 11)
-
-/* Used by CM1_ABE_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_ABE_X2_CLK_SHIFT			8
-#define OMAP4430_CLKACTIVITY_ABE_X2_CLK_WIDTH			0x1
-#define OMAP4430_CLKACTIVITY_ABE_X2_CLK_MASK			(1 << 8)
-
-/* Used by CM_MEMIF_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_ASYNC_DLL_CLK_SHIFT		11
-#define OMAP4430_CLKACTIVITY_ASYNC_DLL_CLK_WIDTH		0x1
-#define OMAP4430_CLKACTIVITY_ASYNC_DLL_CLK_MASK			(1 << 11)
-
-/* Used by CM_MEMIF_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_ASYNC_PHY1_CLK_SHIFT		12
-#define OMAP4430_CLKACTIVITY_ASYNC_PHY1_CLK_WIDTH		0x1
-#define OMAP4430_CLKACTIVITY_ASYNC_PHY1_CLK_MASK		(1 << 12)
-
-/* Used by CM_MEMIF_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_ASYNC_PHY2_CLK_SHIFT		13
-#define OMAP4430_CLKACTIVITY_ASYNC_PHY2_CLK_WIDTH		0x1
-#define OMAP4430_CLKACTIVITY_ASYNC_PHY2_CLK_MASK		(1 << 13)
-
-/* Used by CM_CAM_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_CAM_PHY_CTRL_GCLK_SHIFT		9
-#define OMAP4430_CLKACTIVITY_CAM_PHY_CTRL_GCLK_WIDTH		0x1
-#define OMAP4430_CLKACTIVITY_CAM_PHY_CTRL_GCLK_MASK		(1 << 9)
-
-/* Used by CM_ALWON_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_CORE_ALWON_32K_GFCLK_SHIFT		12
-#define OMAP4430_CLKACTIVITY_CORE_ALWON_32K_GFCLK_WIDTH		0x1
-#define OMAP4430_CLKACTIVITY_CORE_ALWON_32K_GFCLK_MASK		(1 << 12)
-
-/* Used by CM_EMU_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_CORE_DPLL_EMU_CLK_SHIFT		9
-#define OMAP4430_CLKACTIVITY_CORE_DPLL_EMU_CLK_WIDTH		0x1
-#define OMAP4430_CLKACTIVITY_CORE_DPLL_EMU_CLK_MASK		(1 << 9)
-
-/* Used by CM_L4CFG_CLKSTCTRL */
-#define OMAP4460_CLKACTIVITY_CORE_TS_GFCLK_SHIFT		9
-#define OMAP4460_CLKACTIVITY_CORE_TS_GFCLK_WIDTH		0x1
-#define OMAP4460_CLKACTIVITY_CORE_TS_GFCLK_MASK			(1 << 9)
-
-/* Used by CM_CEFUSE_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_CUST_EFUSE_SYS_CLK_SHIFT		9
-#define OMAP4430_CLKACTIVITY_CUST_EFUSE_SYS_CLK_WIDTH		0x1
-#define OMAP4430_CLKACTIVITY_CUST_EFUSE_SYS_CLK_MASK		(1 << 9)
-
-/* Used by CM_MEMIF_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_DLL_CLK_SHIFT			9
-#define OMAP4430_CLKACTIVITY_DLL_CLK_WIDTH			0x1
-#define OMAP4430_CLKACTIVITY_DLL_CLK_MASK			(1 << 9)
-
-/* Used by CM_L4PER_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_DMT10_GFCLK_SHIFT			9
-#define OMAP4430_CLKACTIVITY_DMT10_GFCLK_WIDTH			0x1
-#define OMAP4430_CLKACTIVITY_DMT10_GFCLK_MASK			(1 << 9)
-
-/* Used by CM_L4PER_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_DMT11_GFCLK_SHIFT			10
-#define OMAP4430_CLKACTIVITY_DMT11_GFCLK_WIDTH			0x1
-#define OMAP4430_CLKACTIVITY_DMT11_GFCLK_MASK			(1 << 10)
-
-/* Used by CM_L4PER_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_DMT2_GFCLK_SHIFT			11
-#define OMAP4430_CLKACTIVITY_DMT2_GFCLK_WIDTH			0x1
-#define OMAP4430_CLKACTIVITY_DMT2_GFCLK_MASK			(1 << 11)
-
-/* Used by CM_L4PER_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_DMT3_GFCLK_SHIFT			12
-#define OMAP4430_CLKACTIVITY_DMT3_GFCLK_WIDTH			0x1
-#define OMAP4430_CLKACTIVITY_DMT3_GFCLK_MASK			(1 << 12)
-
-/* Used by CM_L4PER_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_DMT4_GFCLK_SHIFT			13
-#define OMAP4430_CLKACTIVITY_DMT4_GFCLK_WIDTH			0x1
-#define OMAP4430_CLKACTIVITY_DMT4_GFCLK_MASK			(1 << 13)
-
-/* Used by CM_L4PER_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_DMT9_GFCLK_SHIFT			14
-#define OMAP4430_CLKACTIVITY_DMT9_GFCLK_WIDTH			0x1
-#define OMAP4430_CLKACTIVITY_DMT9_GFCLK_MASK			(1 << 14)
-
-/* Used by CM_DSS_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_DSS_ALWON_SYS_CLK_SHIFT		10
-#define OMAP4430_CLKACTIVITY_DSS_ALWON_SYS_CLK_WIDTH		0x1
-#define OMAP4430_CLKACTIVITY_DSS_ALWON_SYS_CLK_MASK		(1 << 10)
-
-/* Used by CM_DSS_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_DSS_FCLK_SHIFT			9
-#define OMAP4430_CLKACTIVITY_DSS_FCLK_WIDTH			0x1
-#define OMAP4430_CLKACTIVITY_DSS_FCLK_MASK			(1 << 9)
-
-/* Used by CM_DUCATI_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_DUCATI_GCLK_SHIFT			8
-#define OMAP4430_CLKACTIVITY_DUCATI_GCLK_WIDTH			0x1
-#define OMAP4430_CLKACTIVITY_DUCATI_GCLK_MASK			(1 << 8)
-
-/* Used by CM_EMU_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_EMU_SYS_CLK_SHIFT			8
-#define OMAP4430_CLKACTIVITY_EMU_SYS_CLK_WIDTH			0x1
-#define OMAP4430_CLKACTIVITY_EMU_SYS_CLK_MASK			(1 << 8)
-
-/* Used by CM_CAM_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_FDIF_GFCLK_SHIFT			10
-#define OMAP4430_CLKACTIVITY_FDIF_GFCLK_WIDTH			0x1
-#define OMAP4430_CLKACTIVITY_FDIF_GFCLK_MASK			(1 << 10)
-
-/* Used by CM_L4PER_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_FUNC_12M_GFCLK_SHIFT		15
-#define OMAP4430_CLKACTIVITY_FUNC_12M_GFCLK_WIDTH		0x1
-#define OMAP4430_CLKACTIVITY_FUNC_12M_GFCLK_MASK		(1 << 15)
-
-/* Used by CM1_ABE_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_FUNC_24M_GFCLK_SHIFT		10
-#define OMAP4430_CLKACTIVITY_FUNC_24M_GFCLK_WIDTH		0x1
-#define OMAP4430_CLKACTIVITY_FUNC_24M_GFCLK_MASK		(1 << 10)
-
-/* Used by CM_DSS_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_HDMI_PHY_48MHZ_GFCLK_SHIFT		11
-#define OMAP4430_CLKACTIVITY_HDMI_PHY_48MHZ_GFCLK_WIDTH		0x1
-#define OMAP4430_CLKACTIVITY_HDMI_PHY_48MHZ_GFCLK_MASK		(1 << 11)
-
-/* Used by CM_L3INIT_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_HSIC_P1_480M_GFCLK_SHIFT		20
-#define OMAP4430_CLKACTIVITY_HSIC_P1_480M_GFCLK_WIDTH		0x1
-#define OMAP4430_CLKACTIVITY_HSIC_P1_480M_GFCLK_MASK		(1 << 20)
-
-/* Used by CM_L3INIT_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_HSIC_P1_GFCLK_SHIFT		26
-#define OMAP4430_CLKACTIVITY_HSIC_P1_GFCLK_WIDTH		0x1
-#define OMAP4430_CLKACTIVITY_HSIC_P1_GFCLK_MASK			(1 << 26)
-
-/* Used by CM_L3INIT_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_HSIC_P2_480M_GFCLK_SHIFT		21
-#define OMAP4430_CLKACTIVITY_HSIC_P2_480M_GFCLK_WIDTH		0x1
-#define OMAP4430_CLKACTIVITY_HSIC_P2_480M_GFCLK_MASK		(1 << 21)
-
-/* Used by CM_L3INIT_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_HSIC_P2_GFCLK_SHIFT		27
-#define OMAP4430_CLKACTIVITY_HSIC_P2_GFCLK_WIDTH		0x1
-#define OMAP4430_CLKACTIVITY_HSIC_P2_GFCLK_MASK			(1 << 27)
-
-/* Used by CM_L3INIT_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_INIT_48MC_GFCLK_SHIFT		13
-#define OMAP4430_CLKACTIVITY_INIT_48MC_GFCLK_WIDTH		0x1
-#define OMAP4430_CLKACTIVITY_INIT_48MC_GFCLK_MASK		(1 << 13)
-
-/* Used by CM_L3INIT_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_INIT_48M_GFCLK_SHIFT		12
-#define OMAP4430_CLKACTIVITY_INIT_48M_GFCLK_WIDTH		0x1
-#define OMAP4430_CLKACTIVITY_INIT_48M_GFCLK_MASK		(1 << 12)
-
-/* Used by CM_L3INIT_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_INIT_60M_P1_GFCLK_SHIFT		28
-#define OMAP4430_CLKACTIVITY_INIT_60M_P1_GFCLK_WIDTH		0x1
-#define OMAP4430_CLKACTIVITY_INIT_60M_P1_GFCLK_MASK		(1 << 28)
-
-/* Used by CM_L3INIT_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_INIT_60M_P2_GFCLK_SHIFT		29
-#define OMAP4430_CLKACTIVITY_INIT_60M_P2_GFCLK_WIDTH		0x1
-#define OMAP4430_CLKACTIVITY_INIT_60M_P2_GFCLK_MASK		(1 << 29)
-
-/* Used by CM_L3INIT_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_INIT_96M_GFCLK_SHIFT		11
-#define OMAP4430_CLKACTIVITY_INIT_96M_GFCLK_WIDTH		0x1
-#define OMAP4430_CLKACTIVITY_INIT_96M_GFCLK_MASK		(1 << 11)
-
-/* Used by CM_L3INIT_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_INIT_HSI_GFCLK_SHIFT		16
-#define OMAP4430_CLKACTIVITY_INIT_HSI_GFCLK_WIDTH		0x1
-#define OMAP4430_CLKACTIVITY_INIT_HSI_GFCLK_MASK		(1 << 16)
-
-/* Used by CM_L3INIT_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_INIT_HSMMC1_GFCLK_SHIFT		17
-#define OMAP4430_CLKACTIVITY_INIT_HSMMC1_GFCLK_WIDTH		0x1
-#define OMAP4430_CLKACTIVITY_INIT_HSMMC1_GFCLK_MASK		(1 << 17)
-
-/* Used by CM_L3INIT_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_INIT_HSMMC2_GFCLK_SHIFT		18
-#define OMAP4430_CLKACTIVITY_INIT_HSMMC2_GFCLK_WIDTH		0x1
-#define OMAP4430_CLKACTIVITY_INIT_HSMMC2_GFCLK_MASK		(1 << 18)
-
-/* Used by CM_L3INIT_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_INIT_HSMMC6_GFCLK_SHIFT		19
-#define OMAP4430_CLKACTIVITY_INIT_HSMMC6_GFCLK_WIDTH		0x1
-#define OMAP4430_CLKACTIVITY_INIT_HSMMC6_GFCLK_MASK		(1 << 19)
-
-/* Used by CM_CAM_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_ISS_GCLK_SHIFT			8
-#define OMAP4430_CLKACTIVITY_ISS_GCLK_WIDTH			0x1
-#define OMAP4430_CLKACTIVITY_ISS_GCLK_MASK			(1 << 8)
-
-/* Used by CM_IVAHD_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_IVAHD_ROOT_CLK_SHIFT		8
-#define OMAP4430_CLKACTIVITY_IVAHD_ROOT_CLK_WIDTH		0x1
-#define OMAP4430_CLKACTIVITY_IVAHD_ROOT_CLK_MASK		(1 << 8)
-
-/* Used by CM_D2D_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_L3X2_D2D_GICLK_SHIFT		10
-#define OMAP4430_CLKACTIVITY_L3X2_D2D_GICLK_WIDTH		0x1
-#define OMAP4430_CLKACTIVITY_L3X2_D2D_GICLK_MASK		(1 << 10)
-
-/* Used by CM_L3_1_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_L3_1_GICLK_SHIFT			8
-#define OMAP4430_CLKACTIVITY_L3_1_GICLK_WIDTH			0x1
-#define OMAP4430_CLKACTIVITY_L3_1_GICLK_MASK			(1 << 8)
-
-/* Used by CM_L3_2_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_L3_2_GICLK_SHIFT			8
-#define OMAP4430_CLKACTIVITY_L3_2_GICLK_WIDTH			0x1
-#define OMAP4430_CLKACTIVITY_L3_2_GICLK_MASK			(1 << 8)
-
-/* Used by CM_D2D_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_L3_D2D_GICLK_SHIFT			8
-#define OMAP4430_CLKACTIVITY_L3_D2D_GICLK_WIDTH			0x1
-#define OMAP4430_CLKACTIVITY_L3_D2D_GICLK_MASK			(1 << 8)
-
-/* Used by CM_SDMA_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_L3_DMA_GICLK_SHIFT			8
-#define OMAP4430_CLKACTIVITY_L3_DMA_GICLK_WIDTH			0x1
-#define OMAP4430_CLKACTIVITY_L3_DMA_GICLK_MASK			(1 << 8)
-
-/* Used by CM_DSS_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_L3_DSS_GICLK_SHIFT			8
-#define OMAP4430_CLKACTIVITY_L3_DSS_GICLK_WIDTH			0x1
-#define OMAP4430_CLKACTIVITY_L3_DSS_GICLK_MASK			(1 << 8)
-
-/* Used by CM_MEMIF_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_L3_EMIF_GICLK_SHIFT		8
-#define OMAP4430_CLKACTIVITY_L3_EMIF_GICLK_WIDTH		0x1
-#define OMAP4430_CLKACTIVITY_L3_EMIF_GICLK_MASK			(1 << 8)
-
-/* Used by CM_GFX_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_L3_GFX_GICLK_SHIFT			8
-#define OMAP4430_CLKACTIVITY_L3_GFX_GICLK_WIDTH			0x1
-#define OMAP4430_CLKACTIVITY_L3_GFX_GICLK_MASK			(1 << 8)
-
-/* Used by CM_L3INIT_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_L3_INIT_GICLK_SHIFT		8
-#define OMAP4430_CLKACTIVITY_L3_INIT_GICLK_WIDTH		0x1
-#define OMAP4430_CLKACTIVITY_L3_INIT_GICLK_MASK			(1 << 8)
-
-/* Used by CM_L3INSTR_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_L3_INSTR_GICLK_SHIFT		8
-#define OMAP4430_CLKACTIVITY_L3_INSTR_GICLK_WIDTH		0x1
-#define OMAP4430_CLKACTIVITY_L3_INSTR_GICLK_MASK		(1 << 8)
-
-/* Used by CM_L4SEC_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_L3_SECURE_GICLK_SHIFT		8
-#define OMAP4430_CLKACTIVITY_L3_SECURE_GICLK_WIDTH		0x1
-#define OMAP4430_CLKACTIVITY_L3_SECURE_GICLK_MASK		(1 << 8)
-
-/* Used by CM_ALWON_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_L4_AO_ICLK_SHIFT			8
-#define OMAP4430_CLKACTIVITY_L4_AO_ICLK_WIDTH			0x1
-#define OMAP4430_CLKACTIVITY_L4_AO_ICLK_MASK			(1 << 8)
-
-/* Used by CM_CEFUSE_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_L4_CEFUSE_GICLK_SHIFT		8
-#define OMAP4430_CLKACTIVITY_L4_CEFUSE_GICLK_WIDTH		0x1
-#define OMAP4430_CLKACTIVITY_L4_CEFUSE_GICLK_MASK		(1 << 8)
-
-/* Used by CM_L4CFG_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_L4_CFG_GICLK_SHIFT			8
-#define OMAP4430_CLKACTIVITY_L4_CFG_GICLK_WIDTH			0x1
-#define OMAP4430_CLKACTIVITY_L4_CFG_GICLK_MASK			(1 << 8)
-
-/* Used by CM_D2D_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_L4_D2D_GICLK_SHIFT			9
-#define OMAP4430_CLKACTIVITY_L4_D2D_GICLK_WIDTH			0x1
-#define OMAP4430_CLKACTIVITY_L4_D2D_GICLK_MASK			(1 << 9)
-
-/* Used by CM_L3INIT_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_L4_INIT_GICLK_SHIFT		9
-#define OMAP4430_CLKACTIVITY_L4_INIT_GICLK_WIDTH		0x1
-#define OMAP4430_CLKACTIVITY_L4_INIT_GICLK_MASK			(1 << 9)
-
-/* Used by CM_L4PER_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_L4_PER_GICLK_SHIFT			8
-#define OMAP4430_CLKACTIVITY_L4_PER_GICLK_WIDTH			0x1
-#define OMAP4430_CLKACTIVITY_L4_PER_GICLK_MASK			(1 << 8)
-
-/* Used by CM_L4SEC_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_L4_SECURE_GICLK_SHIFT		9
-#define OMAP4430_CLKACTIVITY_L4_SECURE_GICLK_WIDTH		0x1
-#define OMAP4430_CLKACTIVITY_L4_SECURE_GICLK_MASK		(1 << 9)
-
-/* Used by CM_WKUP_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_L4_WKUP_GICLK_SHIFT		12
-#define OMAP4430_CLKACTIVITY_L4_WKUP_GICLK_WIDTH		0x1
-#define OMAP4430_CLKACTIVITY_L4_WKUP_GICLK_MASK			(1 << 12)
-
-/* Used by CM_MPU_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_MPU_DPLL_CLK_SHIFT			8
-#define OMAP4430_CLKACTIVITY_MPU_DPLL_CLK_WIDTH			0x1
-#define OMAP4430_CLKACTIVITY_MPU_DPLL_CLK_MASK			(1 << 8)
-
-/* Used by CM1_ABE_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_OCP_ABE_GICLK_SHIFT		9
-#define OMAP4430_CLKACTIVITY_OCP_ABE_GICLK_WIDTH		0x1
-#define OMAP4430_CLKACTIVITY_OCP_ABE_GICLK_MASK			(1 << 9)
-
-/* Used by CM_L4PER_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_PER_24MC_GFCLK_SHIFT		16
-#define OMAP4430_CLKACTIVITY_PER_24MC_GFCLK_WIDTH		0x1
-#define OMAP4430_CLKACTIVITY_PER_24MC_GFCLK_MASK		(1 << 16)
-
-/* Used by CM_L4PER_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_PER_32K_GFCLK_SHIFT		17
-#define OMAP4430_CLKACTIVITY_PER_32K_GFCLK_WIDTH		0x1
-#define OMAP4430_CLKACTIVITY_PER_32K_GFCLK_MASK			(1 << 17)
-
-/* Used by CM_L4PER_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_PER_48M_GFCLK_SHIFT		18
-#define OMAP4430_CLKACTIVITY_PER_48M_GFCLK_WIDTH		0x1
-#define OMAP4430_CLKACTIVITY_PER_48M_GFCLK_MASK			(1 << 18)
-
-/* Used by CM_L4PER_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_PER_96M_GFCLK_SHIFT		19
-#define OMAP4430_CLKACTIVITY_PER_96M_GFCLK_WIDTH		0x1
-#define OMAP4430_CLKACTIVITY_PER_96M_GFCLK_MASK			(1 << 19)
-
-/* Used by CM_L4PER_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_PER_ABE_24M_GFCLK_SHIFT		25
-#define OMAP4430_CLKACTIVITY_PER_ABE_24M_GFCLK_WIDTH		0x1
-#define OMAP4430_CLKACTIVITY_PER_ABE_24M_GFCLK_MASK		(1 << 25)
-
-/* Used by CM_L4PER_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_PER_MCASP2_GFCLK_SHIFT		20
-#define OMAP4430_CLKACTIVITY_PER_MCASP2_GFCLK_WIDTH		0x1
-#define OMAP4430_CLKACTIVITY_PER_MCASP2_GFCLK_MASK		(1 << 20)
-
-/* Used by CM_L4PER_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_PER_MCASP3_GFCLK_SHIFT		21
-#define OMAP4430_CLKACTIVITY_PER_MCASP3_GFCLK_MASK		(1 << 21)
-
-/* Used by CM_L4PER_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_PER_MCBSP4_GFCLK_SHIFT		22
-#define OMAP4430_CLKACTIVITY_PER_MCBSP4_GFCLK_WIDTH		0x1
-#define OMAP4430_CLKACTIVITY_PER_MCBSP4_GFCLK_MASK		(1 << 22)
-
-/* Used by CM_L4PER_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_PER_SYS_GFCLK_SHIFT		24
-#define OMAP4430_CLKACTIVITY_PER_SYS_GFCLK_WIDTH		0x1
-#define OMAP4430_CLKACTIVITY_PER_SYS_GFCLK_MASK			(1 << 24)
-
-/* Used by CM_MEMIF_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_PHY_ROOT_CLK_SHIFT			10
-#define OMAP4430_CLKACTIVITY_PHY_ROOT_CLK_WIDTH			0x1
-#define OMAP4430_CLKACTIVITY_PHY_ROOT_CLK_MASK			(1 << 10)
-
-/* Used by CM_GFX_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_SGX_GFCLK_SHIFT			9
-#define OMAP4430_CLKACTIVITY_SGX_GFCLK_WIDTH			0x1
-#define OMAP4430_CLKACTIVITY_SGX_GFCLK_MASK			(1 << 9)
-
-/* Used by CM_ALWON_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_SR_CORE_SYSCLK_SHIFT		11
-#define OMAP4430_CLKACTIVITY_SR_CORE_SYSCLK_WIDTH		0x1
-#define OMAP4430_CLKACTIVITY_SR_CORE_SYSCLK_MASK		(1 << 11)
-
-/* Used by CM_ALWON_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_SR_IVA_SYSCLK_SHIFT		10
-#define OMAP4430_CLKACTIVITY_SR_IVA_SYSCLK_WIDTH		0x1
-#define OMAP4430_CLKACTIVITY_SR_IVA_SYSCLK_MASK			(1 << 10)
-
-/* Used by CM_ALWON_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_SR_MPU_SYSCLK_SHIFT		9
-#define OMAP4430_CLKACTIVITY_SR_MPU_SYSCLK_WIDTH		0x1
-#define OMAP4430_CLKACTIVITY_SR_MPU_SYSCLK_MASK			(1 << 9)
-
-/* Used by CM_WKUP_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_SYS_CLK_SHIFT			8
-#define OMAP4430_CLKACTIVITY_SYS_CLK_WIDTH			0x1
-#define OMAP4430_CLKACTIVITY_SYS_CLK_MASK			(1 << 8)
-
-/* Used by CM_TESLA_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_TESLA_ROOT_CLK_SHIFT		8
-#define OMAP4430_CLKACTIVITY_TESLA_ROOT_CLK_WIDTH		0x1
-#define OMAP4430_CLKACTIVITY_TESLA_ROOT_CLK_MASK		(1 << 8)
-
-/* Used by CM_L3INIT_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_TLL_CH0_GFCLK_SHIFT		22
-#define OMAP4430_CLKACTIVITY_TLL_CH0_GFCLK_WIDTH		0x1
-#define OMAP4430_CLKACTIVITY_TLL_CH0_GFCLK_MASK			(1 << 22)
-
-/* Used by CM_L3INIT_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_TLL_CH1_GFCLK_SHIFT		23
-#define OMAP4430_CLKACTIVITY_TLL_CH1_GFCLK_WIDTH		0x1
-#define OMAP4430_CLKACTIVITY_TLL_CH1_GFCLK_MASK			(1 << 23)
-
-/* Used by CM_L3INIT_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_TLL_CH2_GFCLK_SHIFT		24
-#define OMAP4430_CLKACTIVITY_TLL_CH2_GFCLK_WIDTH		0x1
-#define OMAP4430_CLKACTIVITY_TLL_CH2_GFCLK_MASK			(1 << 24)
-
-/* Used by CM_L3INIT_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_UNIPRO_DPLL_CLK_SHIFT		10
-#define OMAP4430_CLKACTIVITY_UNIPRO_DPLL_CLK_WIDTH		0x1
-#define OMAP4430_CLKACTIVITY_UNIPRO_DPLL_CLK_MASK		(1 << 10)
-
-/* Used by CM_L3INIT_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_USB_DPLL_CLK_SHIFT			14
-#define OMAP4430_CLKACTIVITY_USB_DPLL_CLK_WIDTH			0x1
-#define OMAP4430_CLKACTIVITY_USB_DPLL_CLK_MASK			(1 << 14)
-
-/* Used by CM_L3INIT_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_USB_DPLL_HS_CLK_SHIFT		15
-#define OMAP4430_CLKACTIVITY_USB_DPLL_HS_CLK_WIDTH		0x1
-#define OMAP4430_CLKACTIVITY_USB_DPLL_HS_CLK_MASK		(1 << 15)
-
-/* Used by CM_WKUP_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_USIM_GFCLK_SHIFT			10
-#define OMAP4430_CLKACTIVITY_USIM_GFCLK_WIDTH			0x1
-#define OMAP4430_CLKACTIVITY_USIM_GFCLK_MASK			(1 << 10)
-
-/* Used by CM_L3INIT_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_UTMI_P3_GFCLK_SHIFT		30
-#define OMAP4430_CLKACTIVITY_UTMI_P3_GFCLK_WIDTH		0x1
-#define OMAP4430_CLKACTIVITY_UTMI_P3_GFCLK_MASK			(1 << 30)
-
-/* Used by CM_L3INIT_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_UTMI_ROOT_GFCLK_SHIFT		25
-#define OMAP4430_CLKACTIVITY_UTMI_ROOT_GFCLK_WIDTH		0x1
-#define OMAP4430_CLKACTIVITY_UTMI_ROOT_GFCLK_MASK		(1 << 25)
-
-/* Used by CM_WKUP_CLKSTCTRL */
-#define OMAP4430_CLKACTIVITY_WKUP_32K_GFCLK_SHIFT		11
-#define OMAP4430_CLKACTIVITY_WKUP_32K_GFCLK_WIDTH		0x1
-#define OMAP4430_CLKACTIVITY_WKUP_32K_GFCLK_MASK		(1 << 11)
-
-/* Used by CM_WKUP_CLKSTCTRL */
-#define OMAP4460_CLKACTIVITY_WKUP_TS_GFCLK_SHIFT		13
-#define OMAP4460_CLKACTIVITY_WKUP_TS_GFCLK_WIDTH		0x1
-#define OMAP4460_CLKACTIVITY_WKUP_TS_GFCLK_MASK			(1 << 13)
-
-/*
- * Used by CM1_ABE_TIMER5_CLKCTRL, CM1_ABE_TIMER6_CLKCTRL,
- * CM1_ABE_TIMER7_CLKCTRL, CM1_ABE_TIMER8_CLKCTRL, CM_L3INIT_MMC1_CLKCTRL,
- * CM_L3INIT_MMC2_CLKCTRL, CM_L4PER_DMTIMER10_CLKCTRL,
- * CM_L4PER_DMTIMER11_CLKCTRL, CM_L4PER_DMTIMER2_CLKCTRL,
- * CM_L4PER_DMTIMER3_CLKCTRL, CM_L4PER_DMTIMER4_CLKCTRL,
- * CM_L4PER_DMTIMER9_CLKCTRL, CM_WKUP_TIMER1_CLKCTRL
- */
 #define OMAP4430_CLKSEL_SHIFT					24
 #define OMAP4430_CLKSEL_WIDTH					0x1
 #define OMAP4430_CLKSEL_MASK					(1 << 24)
-
-/*
- * Renamed from CLKSEL Used by CM_ABE_DSS_SYS_CLKSEL, CM_ABE_PLL_REF_CLKSEL,
- * CM_CLKSEL_DUCATI_ISS_ROOT, CM_CLKSEL_USB_60MHZ, CM_L4_WKUP_CLKSEL
- */
 #define OMAP4430_CLKSEL_0_0_SHIFT				0
 #define OMAP4430_CLKSEL_0_0_WIDTH				0x1
-#define OMAP4430_CLKSEL_0_0_MASK				(1 << 0)
-
-/* Renamed from CLKSEL Used by CM_BYPCLK_DPLL_IVA, CM_BYPCLK_DPLL_MPU */
 #define OMAP4430_CLKSEL_0_1_SHIFT				0
 #define OMAP4430_CLKSEL_0_1_WIDTH				0x2
-#define OMAP4430_CLKSEL_0_1_MASK				(0x3 << 0)
-
-/* Renamed from CLKSEL Used by CM_L3INIT_HSI_CLKCTRL */
 #define OMAP4430_CLKSEL_24_25_SHIFT				24
 #define OMAP4430_CLKSEL_24_25_WIDTH				0x2
-#define OMAP4430_CLKSEL_24_25_MASK				(0x3 << 24)
-
-/* Used by CM_L3INIT_USB_OTG_CLKCTRL */
 #define OMAP4430_CLKSEL_60M_SHIFT				24
 #define OMAP4430_CLKSEL_60M_WIDTH				0x1
-#define OMAP4430_CLKSEL_60M_MASK				(1 << 24)
-
-/* Used by CM_MPU_MPU_CLKCTRL */
-#define OMAP4460_CLKSEL_ABE_DIV_MODE_SHIFT			25
-#define OMAP4460_CLKSEL_ABE_DIV_MODE_WIDTH			0x1
-#define OMAP4460_CLKSEL_ABE_DIV_MODE_MASK			(1 << 25)
-
-/* Used by CM1_ABE_AESS_CLKCTRL */
 #define OMAP4430_CLKSEL_AESS_FCLK_SHIFT				24
 #define OMAP4430_CLKSEL_AESS_FCLK_WIDTH				0x1
-#define OMAP4430_CLKSEL_AESS_FCLK_MASK				(1 << 24)
-
-/* Used by CM_CLKSEL_CORE */
 #define OMAP4430_CLKSEL_CORE_SHIFT				0
 #define OMAP4430_CLKSEL_CORE_WIDTH				0x1
-#define OMAP4430_CLKSEL_CORE_MASK				(1 << 0)
-
-/* Renamed from CLKSEL_CORE Used by CM_SHADOW_FREQ_CONFIG2 */
-#define OMAP4430_CLKSEL_CORE_1_1_SHIFT				1
-#define OMAP4430_CLKSEL_CORE_1_1_WIDTH				0x1
-#define OMAP4430_CLKSEL_CORE_1_1_MASK				(1 << 1)
-
-/* Used by CM_WKUP_USIM_CLKCTRL */
 #define OMAP4430_CLKSEL_DIV_SHIFT				24
 #define OMAP4430_CLKSEL_DIV_WIDTH				0x1
-#define OMAP4430_CLKSEL_DIV_MASK				(1 << 24)
-
-/* Used by CM_MPU_MPU_CLKCTRL */
-#define OMAP4460_CLKSEL_EMIF_DIV_MODE_SHIFT			24
-#define OMAP4460_CLKSEL_EMIF_DIV_MODE_WIDTH			0x1
-#define OMAP4460_CLKSEL_EMIF_DIV_MODE_MASK			(1 << 24)
-
-/* Used by CM_CAM_FDIF_CLKCTRL */
 #define OMAP4430_CLKSEL_FCLK_SHIFT				24
 #define OMAP4430_CLKSEL_FCLK_WIDTH				0x2
-#define OMAP4430_CLKSEL_FCLK_MASK				(0x3 << 24)
-
-/* Used by CM_L4PER_MCBSP4_CLKCTRL */
 #define OMAP4430_CLKSEL_INTERNAL_SOURCE_SHIFT			25
 #define OMAP4430_CLKSEL_INTERNAL_SOURCE_WIDTH			0x1
-#define OMAP4430_CLKSEL_INTERNAL_SOURCE_MASK			(1 << 25)
-
-/*
- * Renamed from CLKSEL_INTERNAL_SOURCE Used by CM1_ABE_DMIC_CLKCTRL,
- * CM1_ABE_MCASP_CLKCTRL, CM1_ABE_MCBSP1_CLKCTRL, CM1_ABE_MCBSP2_CLKCTRL,
- * CM1_ABE_MCBSP3_CLKCTRL
- */
-#define OMAP4430_CLKSEL_INTERNAL_SOURCE_CM1_ABE_DMIC_SHIFT	26
-#define OMAP4430_CLKSEL_INTERNAL_SOURCE_CM1_ABE_DMIC_WIDTH	0x2
-#define OMAP4430_CLKSEL_INTERNAL_SOURCE_CM1_ABE_DMIC_MASK	(0x3 << 26)
-
-/* Used by CM_CLKSEL_CORE */
 #define OMAP4430_CLKSEL_L3_SHIFT				4
 #define OMAP4430_CLKSEL_L3_WIDTH				0x1
-#define OMAP4430_CLKSEL_L3_MASK					(1 << 4)
-
-/* Renamed from CLKSEL_L3 Used by CM_SHADOW_FREQ_CONFIG2 */
-#define OMAP4430_CLKSEL_L3_SHADOW_SHIFT				2
-#define OMAP4430_CLKSEL_L3_SHADOW_WIDTH				0x1
-#define OMAP4430_CLKSEL_L3_SHADOW_MASK				(1 << 2)
-
-/* Used by CM_CLKSEL_CORE */
 #define OMAP4430_CLKSEL_L4_SHIFT				8
 #define OMAP4430_CLKSEL_L4_WIDTH				0x1
-#define OMAP4430_CLKSEL_L4_MASK					(1 << 8)
-
-/* Used by CM_CLKSEL_ABE */
 #define OMAP4430_CLKSEL_OPP_SHIFT				0
 #define OMAP4430_CLKSEL_OPP_WIDTH				0x2
-#define OMAP4430_CLKSEL_OPP_MASK				(0x3 << 0)
-
-/* Used by CM_EMU_DEBUGSS_CLKCTRL */
 #define OMAP4430_CLKSEL_PMD_STM_CLK_SHIFT			27
 #define OMAP4430_CLKSEL_PMD_STM_CLK_WIDTH			0x3
-#define OMAP4430_CLKSEL_PMD_STM_CLK_MASK			(0x7 << 27)
-
-/* Used by CM_EMU_DEBUGSS_CLKCTRL */
-#define OMAP4430_CLKSEL_PMD_TRACE_CLK_SHIFT			24
-#define OMAP4430_CLKSEL_PMD_TRACE_CLK_WIDTH			0x3
 #define OMAP4430_CLKSEL_PMD_TRACE_CLK_MASK			(0x7 << 24)
-
-/* Used by CM_GFX_GFX_CLKCTRL */
-#define OMAP4430_CLKSEL_SGX_FCLK_SHIFT				24
-#define OMAP4430_CLKSEL_SGX_FCLK_WIDTH				0x1
 #define OMAP4430_CLKSEL_SGX_FCLK_MASK				(1 << 24)
-
-/*
- * Used by CM1_ABE_DMIC_CLKCTRL, CM1_ABE_MCASP_CLKCTRL, CM1_ABE_MCBSP1_CLKCTRL,
- * CM1_ABE_MCBSP2_CLKCTRL, CM1_ABE_MCBSP3_CLKCTRL
- */
-#define OMAP4430_CLKSEL_SOURCE_SHIFT				24
-#define OMAP4430_CLKSEL_SOURCE_WIDTH				0x2
 #define OMAP4430_CLKSEL_SOURCE_MASK				(0x3 << 24)
-
-/* Renamed from CLKSEL_SOURCE Used by CM_L4PER_MCBSP4_CLKCTRL */
-#define OMAP4430_CLKSEL_SOURCE_24_24_SHIFT			24
-#define OMAP4430_CLKSEL_SOURCE_24_24_WIDTH			0x1
 #define OMAP4430_CLKSEL_SOURCE_24_24_MASK			(1 << 24)
-
-/* Used by CM_L3INIT_USB_HOST_CLKCTRL */
 #define OMAP4430_CLKSEL_UTMI_P1_SHIFT				24
 #define OMAP4430_CLKSEL_UTMI_P1_WIDTH				0x1
-#define OMAP4430_CLKSEL_UTMI_P1_MASK				(1 << 24)
-
-/* Used by CM_L3INIT_USB_HOST_CLKCTRL */
 #define OMAP4430_CLKSEL_UTMI_P2_SHIFT				25
 #define OMAP4430_CLKSEL_UTMI_P2_WIDTH				0x1
-#define OMAP4430_CLKSEL_UTMI_P2_MASK				(1 << 25)
-
-/*
- * Used by CM1_ABE_CLKSTCTRL, CM_ALWON_CLKSTCTRL, CM_CAM_CLKSTCTRL,
- * CM_CEFUSE_CLKSTCTRL, CM_D2D_CLKSTCTRL, CM_DSS_CLKSTCTRL,
- * CM_DUCATI_CLKSTCTRL, CM_EMU_CLKSTCTRL, CM_GFX_CLKSTCTRL, CM_IVAHD_CLKSTCTRL,
- * CM_L3INIT_CLKSTCTRL, CM_L3INSTR_CLKSTCTRL, CM_L3_1_CLKSTCTRL,
- * CM_L3_2_CLKSTCTRL, CM_L4CFG_CLKSTCTRL, CM_L4PER_CLKSTCTRL,
- * CM_L4SEC_CLKSTCTRL, CM_MEMIF_CLKSTCTRL, CM_MPU_CLKSTCTRL, CM_SDMA_CLKSTCTRL,
- * CM_TESLA_CLKSTCTRL, CM_WKUP_CLKSTCTRL
- */
 #define OMAP4430_CLKTRCTRL_SHIFT				0
-#define OMAP4430_CLKTRCTRL_WIDTH				0x2
 #define OMAP4430_CLKTRCTRL_MASK					(0x3 << 0)
-
-/* Used by CM_EMU_OVERRIDE_DPLL_CORE */
-#define OMAP4430_CORE_DPLL_EMU_DIV_SHIFT			0
-#define OMAP4430_CORE_DPLL_EMU_DIV_WIDTH			0x7
-#define OMAP4430_CORE_DPLL_EMU_DIV_MASK				(0x7f << 0)
-
-/* Used by CM_EMU_OVERRIDE_DPLL_CORE */
-#define OMAP4430_CORE_DPLL_EMU_MULT_SHIFT			8
-#define OMAP4430_CORE_DPLL_EMU_MULT_WIDTH			0xb
-#define OMAP4430_CORE_DPLL_EMU_MULT_MASK			(0x7ff << 8)
-
-/* Used by REVISION_CM1, REVISION_CM2 */
-#define OMAP4430_CUSTOM_SHIFT					6
-#define OMAP4430_CUSTOM_WIDTH					0x2
-#define OMAP4430_CUSTOM_MASK					(0x3 << 6)
-
-/* Used by CM_L3_2_DYNAMICDEP, CM_L4CFG_DYNAMICDEP */
-#define OMAP4430_D2D_DYNDEP_SHIFT				18
-#define OMAP4430_D2D_DYNDEP_WIDTH				0x1
-#define OMAP4430_D2D_DYNDEP_MASK				(1 << 18)
-
-/* Used by CM_MPU_STATICDEP */
-#define OMAP4430_D2D_STATDEP_SHIFT				18
-#define OMAP4430_D2D_STATDEP_WIDTH				0x1
-#define OMAP4430_D2D_STATDEP_MASK				(1 << 18)
-
-/* Used by CM_CLKSEL_DPLL_MPU */
-#define OMAP4460_DCC_COUNT_MAX_SHIFT				24
-#define OMAP4460_DCC_COUNT_MAX_WIDTH				0x8
-#define OMAP4460_DCC_COUNT_MAX_MASK				(0xff << 24)
-
-/* Used by CM_CLKSEL_DPLL_MPU */
-#define OMAP4460_DCC_EN_SHIFT					22
-#define OMAP4460_DCC_EN_MASK					(1 << 22)
-
-/*
- * Used by CM_SSC_DELTAMSTEP_DPLL_ABE, CM_SSC_DELTAMSTEP_DPLL_CORE,
- * CM_SSC_DELTAMSTEP_DPLL_DDRPHY, CM_SSC_DELTAMSTEP_DPLL_IVA,
- * CM_SSC_DELTAMSTEP_DPLL_MPU, CM_SSC_DELTAMSTEP_DPLL_PER,
- * CM_SSC_DELTAMSTEP_DPLL_UNIPRO, CM_SSC_DELTAMSTEP_DPLL_USB
- */
-#define OMAP4430_DELTAMSTEP_SHIFT				0
-#define OMAP4430_DELTAMSTEP_WIDTH				0x14
-#define OMAP4430_DELTAMSTEP_MASK				(0xfffff << 0)
-
-/* Renamed from DELTAMSTEP Used by CM_SSC_DELTAMSTEP_DPLL_USB */
-#define OMAP4460_DELTAMSTEP_0_20_SHIFT				0
-#define OMAP4460_DELTAMSTEP_0_20_WIDTH				0x15
-#define OMAP4460_DELTAMSTEP_0_20_MASK				(0x1fffff << 0)
-
-/* Used by CM_DLL_CTRL */
-#define OMAP4430_DLL_OVERRIDE_SHIFT				0
-#define OMAP4430_DLL_OVERRIDE_WIDTH				0x1
-#define OMAP4430_DLL_OVERRIDE_MASK				(1 << 0)
-
-/* Renamed from DLL_OVERRIDE Used by CM_SHADOW_FREQ_CONFIG1 */
-#define OMAP4430_DLL_OVERRIDE_2_2_SHIFT				2
-#define OMAP4430_DLL_OVERRIDE_2_2_WIDTH				0x1
-#define OMAP4430_DLL_OVERRIDE_2_2_MASK				(1 << 2)
-
-/* Used by CM_SHADOW_FREQ_CONFIG1 */
-#define OMAP4430_DLL_RESET_SHIFT				3
-#define OMAP4430_DLL_RESET_WIDTH				0x1
-#define OMAP4430_DLL_RESET_MASK					(1 << 3)
-
-/*
- * Used by CM_CLKSEL_DPLL_ABE, CM_CLKSEL_DPLL_CORE, CM_CLKSEL_DPLL_DDRPHY,
- * CM_CLKSEL_DPLL_IVA, CM_CLKSEL_DPLL_MPU, CM_CLKSEL_DPLL_PER,
- * CM_CLKSEL_DPLL_UNIPRO, CM_CLKSEL_DPLL_USB
- */
 #define OMAP4430_DPLL_BYP_CLKSEL_SHIFT				23
 #define OMAP4430_DPLL_BYP_CLKSEL_WIDTH				0x1
-#define OMAP4430_DPLL_BYP_CLKSEL_MASK				(1 << 23)
-
-/* Used by CM_CLKDCOLDO_DPLL_USB */
-#define OMAP4430_DPLL_CLKDCOLDO_GATE_CTRL_SHIFT			8
-#define OMAP4430_DPLL_CLKDCOLDO_GATE_CTRL_WIDTH			0x1
-#define OMAP4430_DPLL_CLKDCOLDO_GATE_CTRL_MASK			(1 << 8)
-
-/* Used by CM_CLKSEL_DPLL_CORE */
-#define OMAP4430_DPLL_CLKOUTHIF_CLKSEL_SHIFT			20
-#define OMAP4430_DPLL_CLKOUTHIF_CLKSEL_WIDTH			0x1
-#define OMAP4430_DPLL_CLKOUTHIF_CLKSEL_MASK			(1 << 20)
-
-/* Used by CM_DIV_M3_DPLL_ABE, CM_DIV_M3_DPLL_CORE, CM_DIV_M3_DPLL_PER */
-#define OMAP4430_DPLL_CLKOUTHIF_DIV_SHIFT			0
-#define OMAP4430_DPLL_CLKOUTHIF_DIV_WIDTH			0x5
 #define OMAP4430_DPLL_CLKOUTHIF_DIV_MASK			(0x1f << 0)
-
-/* Used by CM_DIV_M3_DPLL_ABE, CM_DIV_M3_DPLL_CORE, CM_DIV_M3_DPLL_PER */
-#define OMAP4430_DPLL_CLKOUTHIF_DIVCHACK_SHIFT			5
-#define OMAP4430_DPLL_CLKOUTHIF_DIVCHACK_WIDTH			0x1
-#define OMAP4430_DPLL_CLKOUTHIF_DIVCHACK_MASK			(1 << 5)
-
-/* Used by CM_DIV_M3_DPLL_ABE, CM_DIV_M3_DPLL_CORE, CM_DIV_M3_DPLL_PER */
 #define OMAP4430_DPLL_CLKOUTHIF_GATE_CTRL_SHIFT			8
-#define OMAP4430_DPLL_CLKOUTHIF_GATE_CTRL_WIDTH			0x1
-#define OMAP4430_DPLL_CLKOUTHIF_GATE_CTRL_MASK			(1 << 8)
-
-/* Used by CM_DIV_M2_DPLL_ABE, CM_DIV_M2_DPLL_PER, CM_DIV_M2_DPLL_UNIPRO */
-#define OMAP4430_DPLL_CLKOUTX2_GATE_CTRL_SHIFT			10
-#define OMAP4430_DPLL_CLKOUTX2_GATE_CTRL_WIDTH			0x1
 #define OMAP4430_DPLL_CLKOUTX2_GATE_CTRL_MASK			(1 << 10)
-
-/*
- * Used by CM_DIV_M2_DPLL_ABE, CM_DIV_M2_DPLL_CORE, CM_DIV_M2_DPLL_DDRPHY,
- * CM_DIV_M2_DPLL_MPU, CM_DIV_M2_DPLL_PER, CM_DIV_M2_DPLL_UNIPRO
- */
 #define OMAP4430_DPLL_CLKOUT_DIV_SHIFT				0
 #define OMAP4430_DPLL_CLKOUT_DIV_WIDTH				0x5
 #define OMAP4430_DPLL_CLKOUT_DIV_MASK				(0x1f << 0)
-
-/* Renamed from DPLL_CLKOUT_DIV Used by CM_DIV_M2_DPLL_USB */
-#define OMAP4430_DPLL_CLKOUT_DIV_0_6_SHIFT			0
-#define OMAP4430_DPLL_CLKOUT_DIV_0_6_WIDTH			0x7
 #define OMAP4430_DPLL_CLKOUT_DIV_0_6_MASK			(0x7f << 0)
-
-/*
- * Used by CM_DIV_M2_DPLL_ABE, CM_DIV_M2_DPLL_CORE, CM_DIV_M2_DPLL_DDRPHY,
- * CM_DIV_M2_DPLL_MPU, CM_DIV_M2_DPLL_PER, CM_DIV_M2_DPLL_UNIPRO
- */
-#define OMAP4430_DPLL_CLKOUT_DIVCHACK_SHIFT			5
-#define OMAP4430_DPLL_CLKOUT_DIVCHACK_WIDTH			0x1
-#define OMAP4430_DPLL_CLKOUT_DIVCHACK_MASK			(1 << 5)
-
-/* Renamed from DPLL_CLKOUT_DIVCHACK Used by CM_DIV_M2_DPLL_USB */
-#define OMAP4430_DPLL_CLKOUT_DIVCHACK_M2_USB_SHIFT		7
-#define OMAP4430_DPLL_CLKOUT_DIVCHACK_M2_USB_WIDTH		0x1
-#define OMAP4430_DPLL_CLKOUT_DIVCHACK_M2_USB_MASK		(1 << 7)
-
-/*
- * Used by CM_DIV_M2_DPLL_ABE, CM_DIV_M2_DPLL_CORE, CM_DIV_M2_DPLL_DDRPHY,
- * CM_DIV_M2_DPLL_MPU, CM_DIV_M2_DPLL_PER, CM_DIV_M2_DPLL_USB
- */
-#define OMAP4430_DPLL_CLKOUT_GATE_CTRL_SHIFT			8
-#define OMAP4430_DPLL_CLKOUT_GATE_CTRL_WIDTH			0x1
 #define OMAP4430_DPLL_CLKOUT_GATE_CTRL_MASK			(1 << 8)
-
-/* Used by CM_SHADOW_FREQ_CONFIG1 */
-#define OMAP4430_DPLL_CORE_DPLL_EN_SHIFT			8
-#define OMAP4430_DPLL_CORE_DPLL_EN_WIDTH			0x3
-#define OMAP4430_DPLL_CORE_DPLL_EN_MASK				(0x7 << 8)
-
-/* Used by CM_SHADOW_FREQ_CONFIG1 */
-#define OMAP4430_DPLL_CORE_M2_DIV_SHIFT				11
-#define OMAP4430_DPLL_CORE_M2_DIV_WIDTH				0x5
-#define OMAP4430_DPLL_CORE_M2_DIV_MASK				(0x1f << 11)
-
-/* Used by CM_SHADOW_FREQ_CONFIG2 */
-#define OMAP4430_DPLL_CORE_M5_DIV_SHIFT				3
-#define OMAP4430_DPLL_CORE_M5_DIV_WIDTH				0x5
-#define OMAP4430_DPLL_CORE_M5_DIV_MASK				(0x1f << 3)
-
-/*
- * Used by CM_CLKSEL_DPLL_ABE, CM_CLKSEL_DPLL_CORE, CM_CLKSEL_DPLL_DDRPHY,
- * CM_CLKSEL_DPLL_IVA, CM_CLKSEL_DPLL_MPU, CM_CLKSEL_DPLL_PER,
- * CM_CLKSEL_DPLL_UNIPRO
- */
-#define OMAP4430_DPLL_DIV_SHIFT					0
-#define OMAP4430_DPLL_DIV_WIDTH					0x7
 #define OMAP4430_DPLL_DIV_MASK					(0x7f << 0)
-
-/* Renamed from DPLL_DIV Used by CM_CLKSEL_DPLL_USB */
-#define OMAP4430_DPLL_DIV_0_7_SHIFT				0
-#define OMAP4430_DPLL_DIV_0_7_WIDTH				0x8
 #define OMAP4430_DPLL_DIV_0_7_MASK				(0xff << 0)
-
-/*
- * Used by CM_CLKMODE_DPLL_ABE, CM_CLKMODE_DPLL_CORE, CM_CLKMODE_DPLL_DDRPHY,
- * CM_CLKMODE_DPLL_IVA, CM_CLKMODE_DPLL_MPU, CM_CLKMODE_DPLL_PER
- */
-#define OMAP4430_DPLL_DRIFTGUARD_EN_SHIFT			8
-#define OMAP4430_DPLL_DRIFTGUARD_EN_WIDTH			0x1
-#define OMAP4430_DPLL_DRIFTGUARD_EN_MASK			(1 << 8)
-
-/* Renamed from DPLL_DRIFTGUARD_EN Used by CM_CLKMODE_DPLL_UNIPRO */
-#define OMAP4430_DPLL_DRIFTGUARD_EN_3_3_SHIFT			3
-#define OMAP4430_DPLL_DRIFTGUARD_EN_3_3_WIDTH			0x1
-#define OMAP4430_DPLL_DRIFTGUARD_EN_3_3_MASK			(1 << 3)
-
-/*
- * Used by CM_CLKMODE_DPLL_ABE, CM_CLKMODE_DPLL_CORE, CM_CLKMODE_DPLL_DDRPHY,
- * CM_CLKMODE_DPLL_IVA, CM_CLKMODE_DPLL_MPU, CM_CLKMODE_DPLL_PER,
- * CM_CLKMODE_DPLL_UNIPRO, CM_CLKMODE_DPLL_USB
- */
-#define OMAP4430_DPLL_EN_SHIFT					0
-#define OMAP4430_DPLL_EN_WIDTH					0x3
 #define OMAP4430_DPLL_EN_MASK					(0x7 << 0)
-
-/*
- * Used by CM_CLKMODE_DPLL_ABE, CM_CLKMODE_DPLL_CORE, CM_CLKMODE_DPLL_DDRPHY,
- * CM_CLKMODE_DPLL_IVA, CM_CLKMODE_DPLL_MPU, CM_CLKMODE_DPLL_PER,
- * CM_CLKMODE_DPLL_UNIPRO
- */
-#define OMAP4430_DPLL_LPMODE_EN_SHIFT				10
-#define OMAP4430_DPLL_LPMODE_EN_WIDTH				0x1
 #define OMAP4430_DPLL_LPMODE_EN_MASK				(1 << 10)
-
-/*
- * Used by CM_CLKSEL_DPLL_ABE, CM_CLKSEL_DPLL_CORE, CM_CLKSEL_DPLL_DDRPHY,
- * CM_CLKSEL_DPLL_IVA, CM_CLKSEL_DPLL_MPU, CM_CLKSEL_DPLL_PER,
- * CM_CLKSEL_DPLL_UNIPRO
- */
-#define OMAP4430_DPLL_MULT_SHIFT				8
-#define OMAP4430_DPLL_MULT_WIDTH				0xb
 #define OMAP4430_DPLL_MULT_MASK					(0x7ff << 8)
-
-/* Renamed from DPLL_MULT Used by CM_CLKSEL_DPLL_USB */
-#define OMAP4430_DPLL_MULT_USB_SHIFT				8
-#define OMAP4430_DPLL_MULT_USB_WIDTH				0xc
 #define OMAP4430_DPLL_MULT_USB_MASK				(0xfff << 8)
-
-/*
- * Used by CM_CLKMODE_DPLL_ABE, CM_CLKMODE_DPLL_CORE, CM_CLKMODE_DPLL_DDRPHY,
- * CM_CLKMODE_DPLL_IVA, CM_CLKMODE_DPLL_MPU, CM_CLKMODE_DPLL_PER,
- * CM_CLKMODE_DPLL_UNIPRO
- */
-#define OMAP4430_DPLL_REGM4XEN_SHIFT				11
-#define OMAP4430_DPLL_REGM4XEN_WIDTH				0x1
 #define OMAP4430_DPLL_REGM4XEN_MASK				(1 << 11)
-
-/* Used by CM_CLKSEL_DPLL_USB */
-#define OMAP4430_DPLL_SD_DIV_SHIFT				24
-#define OMAP4430_DPLL_SD_DIV_WIDTH				0x8
 #define OMAP4430_DPLL_SD_DIV_MASK				(0xff << 24)
-
-/*
- * Used by CM_CLKMODE_DPLL_ABE, CM_CLKMODE_DPLL_CORE, CM_CLKMODE_DPLL_DDRPHY,
- * CM_CLKMODE_DPLL_IVA, CM_CLKMODE_DPLL_MPU, CM_CLKMODE_DPLL_PER,
- * CM_CLKMODE_DPLL_UNIPRO, CM_CLKMODE_DPLL_USB
- */
-#define OMAP4430_DPLL_SSC_ACK_SHIFT				13
-#define OMAP4430_DPLL_SSC_ACK_WIDTH				0x1
-#define OMAP4430_DPLL_SSC_ACK_MASK				(1 << 13)
-
-/*
- * Used by CM_CLKMODE_DPLL_ABE, CM_CLKMODE_DPLL_CORE, CM_CLKMODE_DPLL_DDRPHY,
- * CM_CLKMODE_DPLL_IVA, CM_CLKMODE_DPLL_MPU, CM_CLKMODE_DPLL_PER,
- * CM_CLKMODE_DPLL_UNIPRO, CM_CLKMODE_DPLL_USB
- */
-#define OMAP4430_DPLL_SSC_DOWNSPREAD_SHIFT			14
-#define OMAP4430_DPLL_SSC_DOWNSPREAD_WIDTH			0x1
-#define OMAP4430_DPLL_SSC_DOWNSPREAD_MASK			(1 << 14)
-
-/*
- * Used by CM_CLKMODE_DPLL_ABE, CM_CLKMODE_DPLL_CORE, CM_CLKMODE_DPLL_DDRPHY,
- * CM_CLKMODE_DPLL_IVA, CM_CLKMODE_DPLL_MPU, CM_CLKMODE_DPLL_PER,
- * CM_CLKMODE_DPLL_UNIPRO, CM_CLKMODE_DPLL_USB
- */
-#define OMAP4430_DPLL_SSC_EN_SHIFT				12
-#define OMAP4430_DPLL_SSC_EN_WIDTH				0x1
-#define OMAP4430_DPLL_SSC_EN_MASK				(1 << 12)
-
-/* Used by CM_L3_2_DYNAMICDEP, CM_L4CFG_DYNAMICDEP, CM_L4PER_DYNAMICDEP */
-#define OMAP4430_DSS_DYNDEP_SHIFT				8
-#define OMAP4430_DSS_DYNDEP_WIDTH				0x1
-#define OMAP4430_DSS_DYNDEP_MASK				(1 << 8)
-
-/* Used by CM_DUCATI_STATICDEP, CM_MPU_STATICDEP, CM_SDMA_STATICDEP */
 #define OMAP4430_DSS_STATDEP_SHIFT				8
-#define OMAP4430_DSS_STATDEP_WIDTH				0x1
-#define OMAP4430_DSS_STATDEP_MASK				(1 << 8)
-
-/* Used by CM_L3_2_DYNAMICDEP */
-#define OMAP4430_DUCATI_DYNDEP_SHIFT				0
-#define OMAP4430_DUCATI_DYNDEP_WIDTH				0x1
-#define OMAP4430_DUCATI_DYNDEP_MASK				(1 << 0)
-
-/* Used by CM_MPU_STATICDEP, CM_SDMA_STATICDEP */
 #define OMAP4430_DUCATI_STATDEP_SHIFT				0
-#define OMAP4430_DUCATI_STATDEP_WIDTH				0x1
-#define OMAP4430_DUCATI_STATDEP_MASK				(1 << 0)
-
-/* Used by CM_SHADOW_FREQ_CONFIG1 */
-#define OMAP4430_FREQ_UPDATE_SHIFT				0
-#define OMAP4430_FREQ_UPDATE_WIDTH				0x1
-#define OMAP4430_FREQ_UPDATE_MASK				(1 << 0)
-
-/* Used by REVISION_CM1, REVISION_CM2 */
-#define OMAP4430_FUNC_SHIFT					16
-#define OMAP4430_FUNC_WIDTH					0xc
-#define OMAP4430_FUNC_MASK					(0xfff << 16)
-
-/* Used by CM_L3_2_DYNAMICDEP */
-#define OMAP4430_GFX_DYNDEP_SHIFT				10
-#define OMAP4430_GFX_DYNDEP_WIDTH				0x1
-#define OMAP4430_GFX_DYNDEP_MASK				(1 << 10)
-
-/* Used by CM_DUCATI_STATICDEP, CM_MPU_STATICDEP */
 #define OMAP4430_GFX_STATDEP_SHIFT				10
-#define OMAP4430_GFX_STATDEP_WIDTH				0x1
-#define OMAP4430_GFX_STATDEP_MASK				(1 << 10)
-
-/* Used by CM_SHADOW_FREQ_CONFIG2 */
-#define OMAP4430_GPMC_FREQ_UPDATE_SHIFT				0
-#define OMAP4430_GPMC_FREQ_UPDATE_WIDTH				0x1
-#define OMAP4430_GPMC_FREQ_UPDATE_MASK				(1 << 0)
-
-/*
- * Used by CM_DIV_M4_DPLL_CORE, CM_DIV_M4_DPLL_DDRPHY, CM_DIV_M4_DPLL_IVA,
- * CM_DIV_M4_DPLL_PER
- */
-#define OMAP4430_HSDIVIDER_CLKOUT1_DIV_SHIFT			0
-#define OMAP4430_HSDIVIDER_CLKOUT1_DIV_WIDTH			0x5
 #define OMAP4430_HSDIVIDER_CLKOUT1_DIV_MASK			(0x1f << 0)
-
-/*
- * Used by CM_DIV_M4_DPLL_CORE, CM_DIV_M4_DPLL_DDRPHY, CM_DIV_M4_DPLL_IVA,
- * CM_DIV_M4_DPLL_PER
- */
-#define OMAP4430_HSDIVIDER_CLKOUT1_DIVCHACK_SHIFT		5
-#define OMAP4430_HSDIVIDER_CLKOUT1_DIVCHACK_WIDTH		0x1
-#define OMAP4430_HSDIVIDER_CLKOUT1_DIVCHACK_MASK		(1 << 5)
-
-/*
- * Used by CM_DIV_M4_DPLL_CORE, CM_DIV_M4_DPLL_DDRPHY, CM_DIV_M4_DPLL_IVA,
- * CM_DIV_M4_DPLL_PER
- */
-#define OMAP4430_HSDIVIDER_CLKOUT1_GATE_CTRL_SHIFT		8
-#define OMAP4430_HSDIVIDER_CLKOUT1_GATE_CTRL_WIDTH		0x1
-#define OMAP4430_HSDIVIDER_CLKOUT1_GATE_CTRL_MASK		(1 << 8)
-
-/*
- * Used by CM_DIV_M4_DPLL_CORE, CM_DIV_M4_DPLL_DDRPHY, CM_DIV_M4_DPLL_IVA,
- * CM_DIV_M4_DPLL_PER
- */
-#define OMAP4430_HSDIVIDER_CLKOUT1_PWDN_SHIFT			12
-#define OMAP4430_HSDIVIDER_CLKOUT1_PWDN_WIDTH			0x1
-#define OMAP4430_HSDIVIDER_CLKOUT1_PWDN_MASK			(1 << 12)
-
-/*
- * Used by CM_DIV_M5_DPLL_CORE, CM_DIV_M5_DPLL_DDRPHY, CM_DIV_M5_DPLL_IVA,
- * CM_DIV_M5_DPLL_PER
- */
-#define OMAP4430_HSDIVIDER_CLKOUT2_DIV_SHIFT			0
-#define OMAP4430_HSDIVIDER_CLKOUT2_DIV_WIDTH			0x5
 #define OMAP4430_HSDIVIDER_CLKOUT2_DIV_MASK			(0x1f << 0)
-
-/*
- * Used by CM_DIV_M5_DPLL_CORE, CM_DIV_M5_DPLL_DDRPHY, CM_DIV_M5_DPLL_IVA,
- * CM_DIV_M5_DPLL_PER
- */
-#define OMAP4430_HSDIVIDER_CLKOUT2_DIVCHACK_SHIFT		5
-#define OMAP4430_HSDIVIDER_CLKOUT2_DIVCHACK_WIDTH		0x1
-#define OMAP4430_HSDIVIDER_CLKOUT2_DIVCHACK_MASK		(1 << 5)
-
-/*
- * Used by CM_DIV_M5_DPLL_CORE, CM_DIV_M5_DPLL_DDRPHY, CM_DIV_M5_DPLL_IVA,
- * CM_DIV_M5_DPLL_PER
- */
-#define OMAP4430_HSDIVIDER_CLKOUT2_GATE_CTRL_SHIFT		8
-#define OMAP4430_HSDIVIDER_CLKOUT2_GATE_CTRL_WIDTH		0x1
-#define OMAP4430_HSDIVIDER_CLKOUT2_GATE_CTRL_MASK		(1 << 8)
-
-/*
- * Used by CM_DIV_M5_DPLL_CORE, CM_DIV_M5_DPLL_DDRPHY, CM_DIV_M5_DPLL_IVA,
- * CM_DIV_M5_DPLL_PER
- */
-#define OMAP4430_HSDIVIDER_CLKOUT2_PWDN_SHIFT			12
-#define OMAP4430_HSDIVIDER_CLKOUT2_PWDN_WIDTH			0x1
-#define OMAP4430_HSDIVIDER_CLKOUT2_PWDN_MASK			(1 << 12)
-
-/* Used by CM_DIV_M6_DPLL_CORE, CM_DIV_M6_DPLL_DDRPHY, CM_DIV_M6_DPLL_PER */
-#define OMAP4430_HSDIVIDER_CLKOUT3_DIV_SHIFT			0
-#define OMAP4430_HSDIVIDER_CLKOUT3_DIV_WIDTH			0x5
 #define OMAP4430_HSDIVIDER_CLKOUT3_DIV_MASK			(0x1f << 0)
-
-/* Used by CM_DIV_M6_DPLL_CORE, CM_DIV_M6_DPLL_DDRPHY, CM_DIV_M6_DPLL_PER */
-#define OMAP4430_HSDIVIDER_CLKOUT3_DIVCHACK_SHIFT		5
-#define OMAP4430_HSDIVIDER_CLKOUT3_DIVCHACK_WIDTH		0x1
-#define OMAP4430_HSDIVIDER_CLKOUT3_DIVCHACK_MASK		(1 << 5)
-
-/* Used by CM_DIV_M6_DPLL_CORE, CM_DIV_M6_DPLL_DDRPHY, CM_DIV_M6_DPLL_PER */
-#define OMAP4430_HSDIVIDER_CLKOUT3_GATE_CTRL_SHIFT		8
-#define OMAP4430_HSDIVIDER_CLKOUT3_GATE_CTRL_WIDTH		0x1
-#define OMAP4430_HSDIVIDER_CLKOUT3_GATE_CTRL_MASK		(1 << 8)
-
-/* Used by CM_DIV_M6_DPLL_CORE, CM_DIV_M6_DPLL_DDRPHY, CM_DIV_M6_DPLL_PER */
-#define OMAP4430_HSDIVIDER_CLKOUT3_PWDN_SHIFT			12
-#define OMAP4430_HSDIVIDER_CLKOUT3_PWDN_WIDTH			0x1
-#define OMAP4430_HSDIVIDER_CLKOUT3_PWDN_MASK			(1 << 12)
-
-/* Used by CM_DIV_M7_DPLL_CORE, CM_DIV_M7_DPLL_PER */
-#define OMAP4430_HSDIVIDER_CLKOUT4_DIV_SHIFT			0
-#define OMAP4430_HSDIVIDER_CLKOUT4_DIV_WIDTH			0x5
 #define OMAP4430_HSDIVIDER_CLKOUT4_DIV_MASK			(0x1f << 0)
-
-/* Used by CM_DIV_M7_DPLL_CORE, CM_DIV_M7_DPLL_PER */
-#define OMAP4430_HSDIVIDER_CLKOUT4_DIVCHACK_SHIFT		5
-#define OMAP4430_HSDIVIDER_CLKOUT4_DIVCHACK_WIDTH		0x1
-#define OMAP4430_HSDIVIDER_CLKOUT4_DIVCHACK_MASK		(1 << 5)
-
-/* Used by CM_DIV_M7_DPLL_CORE, CM_DIV_M7_DPLL_PER */
-#define OMAP4430_HSDIVIDER_CLKOUT4_GATE_CTRL_SHIFT		8
-#define OMAP4430_HSDIVIDER_CLKOUT4_GATE_CTRL_WIDTH		0x1
-#define OMAP4430_HSDIVIDER_CLKOUT4_GATE_CTRL_MASK		(1 << 8)
-
-/* Used by CM_DIV_M7_DPLL_CORE, CM_DIV_M7_DPLL_PER */
-#define OMAP4430_HSDIVIDER_CLKOUT4_PWDN_SHIFT			12
-#define OMAP4430_HSDIVIDER_CLKOUT4_PWDN_WIDTH			0x1
-#define OMAP4430_HSDIVIDER_CLKOUT4_PWDN_MASK			(1 << 12)
-
-/*
- * Used by CM1_ABE_AESS_CLKCTRL, CM1_ABE_DMIC_CLKCTRL, CM1_ABE_L4ABE_CLKCTRL,
- * CM1_ABE_MCASP_CLKCTRL, CM1_ABE_MCBSP1_CLKCTRL, CM1_ABE_MCBSP2_CLKCTRL,
- * CM1_ABE_MCBSP3_CLKCTRL, CM1_ABE_PDM_CLKCTRL, CM1_ABE_SLIMBUS_CLKCTRL,
- * CM1_ABE_TIMER5_CLKCTRL, CM1_ABE_TIMER6_CLKCTRL, CM1_ABE_TIMER7_CLKCTRL,
- * CM1_ABE_TIMER8_CLKCTRL, CM1_ABE_WDT3_CLKCTRL, CM_ALWON_SR_CORE_CLKCTRL,
- * CM_ALWON_SR_IVA_CLKCTRL, CM_ALWON_SR_MPU_CLKCTRL, CM_CAM_FDIF_CLKCTRL,
- * CM_CAM_ISS_CLKCTRL, CM_CEFUSE_CEFUSE_CLKCTRL, CM_CM1_PROFILING_CLKCTRL,
- * CM_CM2_PROFILING_CLKCTRL, CM_D2D_MODEM_ICR_CLKCTRL, CM_D2D_SAD2D_CLKCTRL,
- * CM_D2D_SAD2D_FW_CLKCTRL, CM_DSS_DSS_CLKCTRL, CM_DUCATI_DUCATI_CLKCTRL,
- * CM_EMU_DEBUGSS_CLKCTRL, CM_GFX_GFX_CLKCTRL, CM_IVAHD_IVAHD_CLKCTRL,
- * CM_IVAHD_SL2_CLKCTRL, CM_L3INIT_HSI_CLKCTRL, CM_L3INIT_MMC1_CLKCTRL,
- * CM_L3INIT_MMC2_CLKCTRL, CM_L3INIT_USBPHYOCP2SCP_CLKCTRL,
- * CM_L3INIT_USB_HOST_CLKCTRL, CM_L3INIT_USB_HOST_FS_CLKCTRL,
- * CM_L3INIT_USB_OTG_CLKCTRL, CM_L3INIT_USB_TLL_CLKCTRL,
- * CM_L3INSTR_L3_3_CLKCTRL, CM_L3INSTR_L3_INSTR_CLKCTRL,
- * CM_L3INSTR_OCP_WP1_CLKCTRL, CM_L3_1_L3_1_CLKCTRL, CM_L3_2_GPMC_CLKCTRL,
- * CM_L3_2_L3_2_CLKCTRL, CM_L3_2_OCMC_RAM_CLKCTRL, CM_L4CFG_HW_SEM_CLKCTRL,
- * CM_L4CFG_L4_CFG_CLKCTRL, CM_L4CFG_MAILBOX_CLKCTRL, CM_L4CFG_SAR_ROM_CLKCTRL,
- * CM_L4PER_DMTIMER10_CLKCTRL, CM_L4PER_DMTIMER11_CLKCTRL,
- * CM_L4PER_DMTIMER2_CLKCTRL, CM_L4PER_DMTIMER3_CLKCTRL,
- * CM_L4PER_DMTIMER4_CLKCTRL, CM_L4PER_DMTIMER9_CLKCTRL, CM_L4PER_ELM_CLKCTRL,
- * CM_L4PER_GPIO2_CLKCTRL, CM_L4PER_GPIO3_CLKCTRL, CM_L4PER_GPIO4_CLKCTRL,
- * CM_L4PER_GPIO5_CLKCTRL, CM_L4PER_GPIO6_CLKCTRL, CM_L4PER_HDQ1W_CLKCTRL,
- * CM_L4PER_I2C1_CLKCTRL, CM_L4PER_I2C2_CLKCTRL, CM_L4PER_I2C3_CLKCTRL,
- * CM_L4PER_I2C4_CLKCTRL, CM_L4PER_I2C5_CLKCTRL, CM_L4PER_L4PER_CLKCTRL,
- * CM_L4PER_MCBSP4_CLKCTRL, CM_L4PER_MCSPI1_CLKCTRL, CM_L4PER_MCSPI2_CLKCTRL,
- * CM_L4PER_MCSPI3_CLKCTRL, CM_L4PER_MCSPI4_CLKCTRL, CM_L4PER_MMCSD3_CLKCTRL,
- * CM_L4PER_MMCSD4_CLKCTRL, CM_L4PER_MMCSD5_CLKCTRL, CM_L4PER_SLIMBUS2_CLKCTRL,
- * CM_L4PER_UART1_CLKCTRL, CM_L4PER_UART2_CLKCTRL, CM_L4PER_UART3_CLKCTRL,
- * CM_L4PER_UART4_CLKCTRL, CM_L4SEC_AES1_CLKCTRL, CM_L4SEC_AES2_CLKCTRL,
- * CM_L4SEC_CRYPTODMA_CLKCTRL, CM_L4SEC_DES3DES_CLKCTRL,
- * CM_L4SEC_PKAEIP29_CLKCTRL, CM_L4SEC_RNG_CLKCTRL, CM_L4SEC_SHA2MD51_CLKCTRL,
- * CM_MEMIF_DMM_CLKCTRL, CM_MEMIF_EMIF_1_CLKCTRL, CM_MEMIF_EMIF_2_CLKCTRL,
- * CM_MEMIF_EMIF_FW_CLKCTRL, CM_MPU_MPU_CLKCTRL, CM_SDMA_SDMA_CLKCTRL,
- * CM_TESLA_TESLA_CLKCTRL, CM_WKUP_GPIO1_CLKCTRL, CM_WKUP_KEYBOARD_CLKCTRL,
- * CM_WKUP_L4WKUP_CLKCTRL, CM_WKUP_SARRAM_CLKCTRL, CM_WKUP_SYNCTIMER_CLKCTRL,
- * CM_WKUP_TIMER12_CLKCTRL, CM_WKUP_TIMER1_CLKCTRL, CM_WKUP_USIM_CLKCTRL,
- * CM_WKUP_WDT1_CLKCTRL, CM_WKUP_WDT2_CLKCTRL
- */
 #define OMAP4430_IDLEST_SHIFT					16
-#define OMAP4430_IDLEST_WIDTH					0x2
 #define OMAP4430_IDLEST_MASK					(0x3 << 16)
-
-/* Used by CM_DUCATI_DYNAMICDEP, CM_L3_2_DYNAMICDEP, CM_L4CFG_DYNAMICDEP */
-#define OMAP4430_ISS_DYNDEP_SHIFT				9
-#define OMAP4430_ISS_DYNDEP_WIDTH				0x1
-#define OMAP4430_ISS_DYNDEP_MASK				(1 << 9)
-
-/*
- * Used by CM_DUCATI_STATICDEP, CM_MPU_STATICDEP, CM_SDMA_STATICDEP,
- * CM_TESLA_STATICDEP
- */
-#define OMAP4430_ISS_STATDEP_SHIFT				9
-#define OMAP4430_ISS_STATDEP_WIDTH				0x1
-#define OMAP4430_ISS_STATDEP_MASK				(1 << 9)
-
-/* Used by CM_L3_2_DYNAMICDEP, CM_TESLA_DYNAMICDEP */
-#define OMAP4430_IVAHD_DYNDEP_SHIFT				2
-#define OMAP4430_IVAHD_DYNDEP_WIDTH				0x1
-#define OMAP4430_IVAHD_DYNDEP_MASK				(1 << 2)
-
-/*
- * Used by CM_CAM_STATICDEP, CM_D2D_STATICDEP, CM_DSS_STATICDEP,
- * CM_DUCATI_STATICDEP, CM_GFX_STATICDEP, CM_L3INIT_STATICDEP,
- * CM_MPU_STATICDEP, CM_SDMA_STATICDEP, CM_TESLA_STATICDEP
- */
 #define OMAP4430_IVAHD_STATDEP_SHIFT				2
-#define OMAP4430_IVAHD_STATDEP_WIDTH				0x1
-#define OMAP4430_IVAHD_STATDEP_MASK				(1 << 2)
-
-/* Used by CM_L3_2_DYNAMICDEP, CM_L4CFG_DYNAMICDEP, CM_L4PER_DYNAMICDEP */
-#define OMAP4430_L3INIT_DYNDEP_SHIFT				7
-#define OMAP4430_L3INIT_DYNDEP_WIDTH				0x1
-#define OMAP4430_L3INIT_DYNDEP_MASK				(1 << 7)
-
-/*
- * Used by CM_D2D_STATICDEP, CM_DUCATI_STATICDEP, CM_MPU_STATICDEP,
- * CM_SDMA_STATICDEP, CM_TESLA_STATICDEP
- */
 #define OMAP4430_L3INIT_STATDEP_SHIFT				7
-#define OMAP4430_L3INIT_STATDEP_WIDTH				0x1
-#define OMAP4430_L3INIT_STATDEP_MASK				(1 << 7)
-
-/*
- * Used by CM_DSS_DYNAMICDEP, CM_L3INIT_DYNAMICDEP, CM_L3_2_DYNAMICDEP,
- * CM_L4CFG_DYNAMICDEP, CM_MPU_DYNAMICDEP, CM_TESLA_DYNAMICDEP
- */
-#define OMAP4430_L3_1_DYNDEP_SHIFT				5
-#define OMAP4430_L3_1_DYNDEP_WIDTH				0x1
-#define OMAP4430_L3_1_DYNDEP_MASK				(1 << 5)
-
-/*
- * Used by CM_CAM_STATICDEP, CM_D2D_STATICDEP, CM_DSS_STATICDEP,
- * CM_DUCATI_STATICDEP, CM_GFX_STATICDEP, CM_IVAHD_STATICDEP,
- * CM_L3INIT_STATICDEP, CM_L4SEC_STATICDEP, CM_MPU_STATICDEP,
- * CM_SDMA_STATICDEP, CM_TESLA_STATICDEP
- */
 #define OMAP4430_L3_1_STATDEP_SHIFT				5
-#define OMAP4430_L3_1_STATDEP_WIDTH				0x1
-#define OMAP4430_L3_1_STATDEP_MASK				(1 << 5)
-
-/*
- * Used by CM_CAM_DYNAMICDEP, CM_D2D_DYNAMICDEP, CM_DUCATI_DYNAMICDEP,
- * CM_EMU_DYNAMICDEP, CM_GFX_DYNAMICDEP, CM_IVAHD_DYNAMICDEP,
- * CM_L3INIT_DYNAMICDEP, CM_L3_1_DYNAMICDEP, CM_L4CFG_DYNAMICDEP,
- * CM_L4SEC_DYNAMICDEP, CM_SDMA_DYNAMICDEP
- */
-#define OMAP4430_L3_2_DYNDEP_SHIFT				6
-#define OMAP4430_L3_2_DYNDEP_WIDTH				0x1
-#define OMAP4430_L3_2_DYNDEP_MASK				(1 << 6)
-
-/*
- * Used by CM_CAM_STATICDEP, CM_D2D_STATICDEP, CM_DSS_STATICDEP,
- * CM_DUCATI_STATICDEP, CM_GFX_STATICDEP, CM_IVAHD_STATICDEP,
- * CM_L3INIT_STATICDEP, CM_L4SEC_STATICDEP, CM_MPU_STATICDEP,
- * CM_SDMA_STATICDEP, CM_TESLA_STATICDEP
- */
 #define OMAP4430_L3_2_STATDEP_SHIFT				6
-#define OMAP4430_L3_2_STATDEP_WIDTH				0x1
-#define OMAP4430_L3_2_STATDEP_MASK				(1 << 6)
-
-/* Used by CM_L3_1_DYNAMICDEP */
-#define OMAP4430_L4CFG_DYNDEP_SHIFT				12
-#define OMAP4430_L4CFG_DYNDEP_WIDTH				0x1
-#define OMAP4430_L4CFG_DYNDEP_MASK				(1 << 12)
-
-/*
- * Used by CM_D2D_STATICDEP, CM_DUCATI_STATICDEP, CM_L3INIT_STATICDEP,
- * CM_MPU_STATICDEP, CM_SDMA_STATICDEP, CM_TESLA_STATICDEP
- */
 #define OMAP4430_L4CFG_STATDEP_SHIFT				12
-#define OMAP4430_L4CFG_STATDEP_WIDTH				0x1
-#define OMAP4430_L4CFG_STATDEP_MASK				(1 << 12)
-
-/* Used by CM_L3_2_DYNAMICDEP */
-#define OMAP4430_L4PER_DYNDEP_SHIFT				13
-#define OMAP4430_L4PER_DYNDEP_WIDTH				0x1
-#define OMAP4430_L4PER_DYNDEP_MASK				(1 << 13)
-
-/*
- * Used by CM_D2D_STATICDEP, CM_DUCATI_STATICDEP, CM_L3INIT_STATICDEP,
- * CM_L4SEC_STATICDEP, CM_MPU_STATICDEP, CM_SDMA_STATICDEP, CM_TESLA_STATICDEP
- */
 #define OMAP4430_L4PER_STATDEP_SHIFT				13
-#define OMAP4430_L4PER_STATDEP_WIDTH				0x1
-#define OMAP4430_L4PER_STATDEP_MASK				(1 << 13)
-
-/* Used by CM_L3_2_DYNAMICDEP, CM_L4PER_DYNAMICDEP */
-#define OMAP4430_L4SEC_DYNDEP_SHIFT				14
-#define OMAP4430_L4SEC_DYNDEP_WIDTH				0x1
-#define OMAP4430_L4SEC_DYNDEP_MASK				(1 << 14)
-
-/*
- * Used by CM_DUCATI_STATICDEP, CM_L3INIT_STATICDEP, CM_MPU_STATICDEP,
- * CM_SDMA_STATICDEP
- */
 #define OMAP4430_L4SEC_STATDEP_SHIFT				14
-#define OMAP4430_L4SEC_STATDEP_WIDTH				0x1
-#define OMAP4430_L4SEC_STATDEP_MASK				(1 << 14)
-
-/* Used by CM_L4CFG_DYNAMICDEP */
-#define OMAP4430_L4WKUP_DYNDEP_SHIFT				15
-#define OMAP4430_L4WKUP_DYNDEP_WIDTH				0x1
-#define OMAP4430_L4WKUP_DYNDEP_MASK				(1 << 15)
-
-/*
- * Used by CM_DUCATI_STATICDEP, CM_L3INIT_STATICDEP, CM_MPU_STATICDEP,
- * CM_SDMA_STATICDEP, CM_TESLA_STATICDEP
- */
 #define OMAP4430_L4WKUP_STATDEP_SHIFT				15
-#define OMAP4430_L4WKUP_STATDEP_WIDTH				0x1
-#define OMAP4430_L4WKUP_STATDEP_MASK				(1 << 15)
-
-/*
- * Used by CM_D2D_DYNAMICDEP, CM_L3_1_DYNAMICDEP, CM_L4CFG_DYNAMICDEP,
- * CM_MPU_DYNAMICDEP
- */
-#define OMAP4430_MEMIF_DYNDEP_SHIFT				4
-#define OMAP4430_MEMIF_DYNDEP_WIDTH				0x1
-#define OMAP4430_MEMIF_DYNDEP_MASK				(1 << 4)
-
-/*
- * Used by CM_CAM_STATICDEP, CM_D2D_STATICDEP, CM_DSS_STATICDEP,
- * CM_DUCATI_STATICDEP, CM_GFX_STATICDEP, CM_IVAHD_STATICDEP,
- * CM_L3INIT_STATICDEP, CM_L4SEC_STATICDEP, CM_MPU_STATICDEP,
- * CM_SDMA_STATICDEP, CM_TESLA_STATICDEP
- */
 #define OMAP4430_MEMIF_STATDEP_SHIFT				4
-#define OMAP4430_MEMIF_STATDEP_WIDTH				0x1
-#define OMAP4430_MEMIF_STATDEP_MASK				(1 << 4)
-
-/*
- * Used by CM_SSC_MODFREQDIV_DPLL_ABE, CM_SSC_MODFREQDIV_DPLL_CORE,
- * CM_SSC_MODFREQDIV_DPLL_DDRPHY, CM_SSC_MODFREQDIV_DPLL_IVA,
- * CM_SSC_MODFREQDIV_DPLL_MPU, CM_SSC_MODFREQDIV_DPLL_PER,
- * CM_SSC_MODFREQDIV_DPLL_UNIPRO, CM_SSC_MODFREQDIV_DPLL_USB
- */
-#define OMAP4430_MODFREQDIV_EXPONENT_SHIFT			8
-#define OMAP4430_MODFREQDIV_EXPONENT_WIDTH			0x3
-#define OMAP4430_MODFREQDIV_EXPONENT_MASK			(0x7 << 8)
-
-/*
- * Used by CM_SSC_MODFREQDIV_DPLL_ABE, CM_SSC_MODFREQDIV_DPLL_CORE,
- * CM_SSC_MODFREQDIV_DPLL_DDRPHY, CM_SSC_MODFREQDIV_DPLL_IVA,
- * CM_SSC_MODFREQDIV_DPLL_MPU, CM_SSC_MODFREQDIV_DPLL_PER,
- * CM_SSC_MODFREQDIV_DPLL_UNIPRO, CM_SSC_MODFREQDIV_DPLL_USB
- */
-#define OMAP4430_MODFREQDIV_MANTISSA_SHIFT			0
-#define OMAP4430_MODFREQDIV_MANTISSA_WIDTH			0x7
-#define OMAP4430_MODFREQDIV_MANTISSA_MASK			(0x7f << 0)
-
-/*
- * Used by CM1_ABE_AESS_CLKCTRL, CM1_ABE_DMIC_CLKCTRL, CM1_ABE_L4ABE_CLKCTRL,
- * CM1_ABE_MCASP_CLKCTRL, CM1_ABE_MCBSP1_CLKCTRL, CM1_ABE_MCBSP2_CLKCTRL,
- * CM1_ABE_MCBSP3_CLKCTRL, CM1_ABE_PDM_CLKCTRL, CM1_ABE_SLIMBUS_CLKCTRL,
- * CM1_ABE_TIMER5_CLKCTRL, CM1_ABE_TIMER6_CLKCTRL, CM1_ABE_TIMER7_CLKCTRL,
- * CM1_ABE_TIMER8_CLKCTRL, CM1_ABE_WDT3_CLKCTRL, CM_ALWON_SR_CORE_CLKCTRL,
- * CM_ALWON_SR_IVA_CLKCTRL, CM_ALWON_SR_MPU_CLKCTRL, CM_CAM_FDIF_CLKCTRL,
- * CM_CAM_ISS_CLKCTRL, CM_CEFUSE_CEFUSE_CLKCTRL, CM_CM1_PROFILING_CLKCTRL,
- * CM_CM2_PROFILING_CLKCTRL, CM_D2D_MODEM_ICR_CLKCTRL, CM_D2D_SAD2D_CLKCTRL,
- * CM_D2D_SAD2D_FW_CLKCTRL, CM_DSS_DSS_CLKCTRL, CM_DUCATI_DUCATI_CLKCTRL,
- * CM_EMU_DEBUGSS_CLKCTRL, CM_GFX_GFX_CLKCTRL, CM_IVAHD_IVAHD_CLKCTRL,
- * CM_IVAHD_SL2_CLKCTRL, CM_L3INIT_HSI_CLKCTRL, CM_L3INIT_MMC1_CLKCTRL,
- * CM_L3INIT_MMC2_CLKCTRL, CM_L3INIT_USBPHYOCP2SCP_CLKCTRL,
- * CM_L3INIT_USB_HOST_CLKCTRL, CM_L3INIT_USB_HOST_FS_CLKCTRL,
- * CM_L3INIT_USB_OTG_CLKCTRL, CM_L3INIT_USB_TLL_CLKCTRL,
- * CM_L3INSTR_L3_3_CLKCTRL, CM_L3INSTR_L3_INSTR_CLKCTRL,
- * CM_L3INSTR_OCP_WP1_CLKCTRL, CM_L3_1_L3_1_CLKCTRL, CM_L3_2_GPMC_CLKCTRL,
- * CM_L3_2_L3_2_CLKCTRL, CM_L3_2_OCMC_RAM_CLKCTRL, CM_L4CFG_HW_SEM_CLKCTRL,
- * CM_L4CFG_L4_CFG_CLKCTRL, CM_L4CFG_MAILBOX_CLKCTRL, CM_L4CFG_SAR_ROM_CLKCTRL,
- * CM_L4PER_DMTIMER10_CLKCTRL, CM_L4PER_DMTIMER11_CLKCTRL,
- * CM_L4PER_DMTIMER2_CLKCTRL, CM_L4PER_DMTIMER3_CLKCTRL,
- * CM_L4PER_DMTIMER4_CLKCTRL, CM_L4PER_DMTIMER9_CLKCTRL, CM_L4PER_ELM_CLKCTRL,
- * CM_L4PER_GPIO2_CLKCTRL, CM_L4PER_GPIO3_CLKCTRL, CM_L4PER_GPIO4_CLKCTRL,
- * CM_L4PER_GPIO5_CLKCTRL, CM_L4PER_GPIO6_CLKCTRL, CM_L4PER_HDQ1W_CLKCTRL,
- * CM_L4PER_I2C1_CLKCTRL, CM_L4PER_I2C2_CLKCTRL, CM_L4PER_I2C3_CLKCTRL,
- * CM_L4PER_I2C4_CLKCTRL, CM_L4PER_I2C5_CLKCTRL, CM_L4PER_L4PER_CLKCTRL,
- * CM_L4PER_MCBSP4_CLKCTRL, CM_L4PER_MCSPI1_CLKCTRL, CM_L4PER_MCSPI2_CLKCTRL,
- * CM_L4PER_MCSPI3_CLKCTRL, CM_L4PER_MCSPI4_CLKCTRL, CM_L4PER_MMCSD3_CLKCTRL,
- * CM_L4PER_MMCSD4_CLKCTRL, CM_L4PER_MMCSD5_CLKCTRL, CM_L4PER_SLIMBUS2_CLKCTRL,
- * CM_L4PER_UART1_CLKCTRL, CM_L4PER_UART2_CLKCTRL, CM_L4PER_UART3_CLKCTRL,
- * CM_L4PER_UART4_CLKCTRL, CM_L4SEC_AES1_CLKCTRL, CM_L4SEC_AES2_CLKCTRL,
- * CM_L4SEC_CRYPTODMA_CLKCTRL, CM_L4SEC_DES3DES_CLKCTRL,
- * CM_L4SEC_PKAEIP29_CLKCTRL, CM_L4SEC_RNG_CLKCTRL, CM_L4SEC_SHA2MD51_CLKCTRL,
- * CM_MEMIF_DMM_CLKCTRL, CM_MEMIF_EMIF_1_CLKCTRL, CM_MEMIF_EMIF_2_CLKCTRL,
- * CM_MEMIF_EMIF_FW_CLKCTRL, CM_MPU_MPU_CLKCTRL, CM_SDMA_SDMA_CLKCTRL,
- * CM_TESLA_TESLA_CLKCTRL, CM_WKUP_GPIO1_CLKCTRL, CM_WKUP_KEYBOARD_CLKCTRL,
- * CM_WKUP_L4WKUP_CLKCTRL, CM_WKUP_SARRAM_CLKCTRL, CM_WKUP_SYNCTIMER_CLKCTRL,
- * CM_WKUP_TIMER12_CLKCTRL, CM_WKUP_TIMER1_CLKCTRL, CM_WKUP_USIM_CLKCTRL,
- * CM_WKUP_WDT1_CLKCTRL, CM_WKUP_WDT2_CLKCTRL
- */
 #define OMAP4430_MODULEMODE_SHIFT				0
-#define OMAP4430_MODULEMODE_WIDTH				0x2
 #define OMAP4430_MODULEMODE_MASK				(0x3 << 0)
-
-/* Used by CM_L4CFG_DYNAMICDEP */
-#define OMAP4460_MPU_DYNDEP_SHIFT				19
-#define OMAP4460_MPU_DYNDEP_WIDTH				0x1
-#define OMAP4460_MPU_DYNDEP_MASK				(1 << 19)
-
-/* Used by CM_DSS_DSS_CLKCTRL */
 #define OMAP4430_OPTFCLKEN_48MHZ_CLK_SHIFT			9
-#define OMAP4430_OPTFCLKEN_48MHZ_CLK_WIDTH			0x1
-#define OMAP4430_OPTFCLKEN_48MHZ_CLK_MASK			(1 << 9)
-
-/* Used by CM_WKUP_BANDGAP_CLKCTRL */
 #define OMAP4430_OPTFCLKEN_BGAP_32K_SHIFT			8
-#define OMAP4430_OPTFCLKEN_BGAP_32K_WIDTH			0x1
-#define OMAP4430_OPTFCLKEN_BGAP_32K_MASK			(1 << 8)
-
-/* Used by CM_ALWON_USBPHY_CLKCTRL */
 #define OMAP4430_OPTFCLKEN_CLK32K_SHIFT				8
-#define OMAP4430_OPTFCLKEN_CLK32K_WIDTH				0x1
-#define OMAP4430_OPTFCLKEN_CLK32K_MASK				(1 << 8)
-
-/* Used by CM_CAM_ISS_CLKCTRL */
 #define OMAP4430_OPTFCLKEN_CTRLCLK_SHIFT			8
-#define OMAP4430_OPTFCLKEN_CTRLCLK_WIDTH			0x1
-#define OMAP4430_OPTFCLKEN_CTRLCLK_MASK				(1 << 8)
-
-/*
- * Used by CM_L4PER_GPIO2_CLKCTRL, CM_L4PER_GPIO3_CLKCTRL,
- * CM_L4PER_GPIO4_CLKCTRL, CM_L4PER_GPIO5_CLKCTRL, CM_L4PER_GPIO6_CLKCTRL,
- * CM_WKUP_GPIO1_CLKCTRL
- */
 #define OMAP4430_OPTFCLKEN_DBCLK_SHIFT				8
-#define OMAP4430_OPTFCLKEN_DBCLK_WIDTH				0x1
-#define OMAP4430_OPTFCLKEN_DBCLK_MASK				(1 << 8)
-
-/* Used by CM_MEMIF_DLL_CLKCTRL, CM_MEMIF_DLL_H_CLKCTRL */
-#define OMAP4430_OPTFCLKEN_DLL_CLK_SHIFT			8
-#define OMAP4430_OPTFCLKEN_DLL_CLK_WIDTH			0x1
-#define OMAP4430_OPTFCLKEN_DLL_CLK_MASK				(1 << 8)
-
-/* Used by CM_DSS_DSS_CLKCTRL */
 #define OMAP4430_OPTFCLKEN_DSSCLK_SHIFT				8
-#define OMAP4430_OPTFCLKEN_DSSCLK_WIDTH				0x1
-#define OMAP4430_OPTFCLKEN_DSSCLK_MASK				(1 << 8)
-
-/* Used by CM_WKUP_USIM_CLKCTRL */
 #define OMAP4430_OPTFCLKEN_FCLK_SHIFT				8
-#define OMAP4430_OPTFCLKEN_FCLK_WIDTH				0x1
-#define OMAP4430_OPTFCLKEN_FCLK_MASK				(1 << 8)
-
-/* Used by CM1_ABE_SLIMBUS_CLKCTRL */
 #define OMAP4430_OPTFCLKEN_FCLK0_SHIFT				8
-#define OMAP4430_OPTFCLKEN_FCLK0_WIDTH				0x1
-#define OMAP4430_OPTFCLKEN_FCLK0_MASK				(1 << 8)
-
-/* Used by CM1_ABE_SLIMBUS_CLKCTRL */
 #define OMAP4430_OPTFCLKEN_FCLK1_SHIFT				9
-#define OMAP4430_OPTFCLKEN_FCLK1_WIDTH				0x1
-#define OMAP4430_OPTFCLKEN_FCLK1_MASK				(1 << 9)
-
-/* Used by CM1_ABE_SLIMBUS_CLKCTRL */
 #define OMAP4430_OPTFCLKEN_FCLK2_SHIFT				10
-#define OMAP4430_OPTFCLKEN_FCLK2_WIDTH				0x1
-#define OMAP4430_OPTFCLKEN_FCLK2_MASK				(1 << 10)
-
-/* Used by CM_L3INIT_USB_HOST_CLKCTRL */
 #define OMAP4430_OPTFCLKEN_FUNC48MCLK_SHIFT			15
-#define OMAP4430_OPTFCLKEN_FUNC48MCLK_WIDTH			0x1
-#define OMAP4430_OPTFCLKEN_FUNC48MCLK_MASK			(1 << 15)
-
-/* Used by CM_L3INIT_USB_HOST_CLKCTRL */
 #define OMAP4430_OPTFCLKEN_HSIC480M_P1_CLK_SHIFT		13
-#define OMAP4430_OPTFCLKEN_HSIC480M_P1_CLK_WIDTH		0x1
-#define OMAP4430_OPTFCLKEN_HSIC480M_P1_CLK_MASK			(1 << 13)
-
-/* Used by CM_L3INIT_USB_HOST_CLKCTRL */
 #define OMAP4430_OPTFCLKEN_HSIC480M_P2_CLK_SHIFT		14
-#define OMAP4430_OPTFCLKEN_HSIC480M_P2_CLK_WIDTH		0x1
-#define OMAP4430_OPTFCLKEN_HSIC480M_P2_CLK_MASK			(1 << 14)
-
-/* Used by CM_L3INIT_USB_HOST_CLKCTRL */
 #define OMAP4430_OPTFCLKEN_HSIC60M_P1_CLK_SHIFT			11
-#define OMAP4430_OPTFCLKEN_HSIC60M_P1_CLK_WIDTH			0x1
-#define OMAP4430_OPTFCLKEN_HSIC60M_P1_CLK_MASK			(1 << 11)
-
-/* Used by CM_L3INIT_USB_HOST_CLKCTRL */
 #define OMAP4430_OPTFCLKEN_HSIC60M_P2_CLK_SHIFT			12
-#define OMAP4430_OPTFCLKEN_HSIC60M_P2_CLK_WIDTH			0x1
-#define OMAP4430_OPTFCLKEN_HSIC60M_P2_CLK_MASK			(1 << 12)
-
-/* Used by CM_L4PER_SLIMBUS2_CLKCTRL */
 #define OMAP4430_OPTFCLKEN_PER24MC_GFCLK_SHIFT			8
-#define OMAP4430_OPTFCLKEN_PER24MC_GFCLK_WIDTH			0x1
-#define OMAP4430_OPTFCLKEN_PER24MC_GFCLK_MASK			(1 << 8)
-
-/* Used by CM_L4PER_SLIMBUS2_CLKCTRL */
 #define OMAP4430_OPTFCLKEN_PERABE24M_GFCLK_SHIFT		9
-#define OMAP4430_OPTFCLKEN_PERABE24M_GFCLK_WIDTH		0x1
-#define OMAP4430_OPTFCLKEN_PERABE24M_GFCLK_MASK			(1 << 9)
-
-/* Used by CM_L3INIT_USBPHYOCP2SCP_CLKCTRL */
 #define OMAP4430_OPTFCLKEN_PHY_48M_SHIFT			8
-#define OMAP4430_OPTFCLKEN_PHY_48M_WIDTH			0x1
-#define OMAP4430_OPTFCLKEN_PHY_48M_MASK				(1 << 8)
-
-/* Used by CM_L4PER_SLIMBUS2_CLKCTRL */
 #define OMAP4430_OPTFCLKEN_SLIMBUS_CLK_SHIFT			10
-#define OMAP4430_OPTFCLKEN_SLIMBUS_CLK_WIDTH			0x1
-#define OMAP4430_OPTFCLKEN_SLIMBUS_CLK_MASK			(1 << 10)
-
-/* Renamed from OPTFCLKEN_SLIMBUS_CLK Used by CM1_ABE_SLIMBUS_CLKCTRL */
 #define OMAP4430_OPTFCLKEN_SLIMBUS_CLK_11_11_SHIFT		11
-#define OMAP4430_OPTFCLKEN_SLIMBUS_CLK_11_11_WIDTH		0x1
-#define OMAP4430_OPTFCLKEN_SLIMBUS_CLK_11_11_MASK		(1 << 11)
-
-/* Used by CM_DSS_DSS_CLKCTRL */
 #define OMAP4430_OPTFCLKEN_SYS_CLK_SHIFT			10
-#define OMAP4430_OPTFCLKEN_SYS_CLK_WIDTH			0x1
-#define OMAP4430_OPTFCLKEN_SYS_CLK_MASK				(1 << 10)
-
-/* Used by CM_WKUP_BANDGAP_CLKCTRL */
 #define OMAP4460_OPTFCLKEN_TS_FCLK_SHIFT			8
-#define OMAP4460_OPTFCLKEN_TS_FCLK_WIDTH			0x1
-#define OMAP4460_OPTFCLKEN_TS_FCLK_MASK				(1 << 8)
-
-/* Used by CM_DSS_DSS_CLKCTRL */
 #define OMAP4430_OPTFCLKEN_TV_CLK_SHIFT				11
-#define OMAP4430_OPTFCLKEN_TV_CLK_WIDTH				0x1
-#define OMAP4430_OPTFCLKEN_TV_CLK_MASK				(1 << 11)
-
-/* Used by CM_L3INIT_UNIPRO1_CLKCTRL */
-#define OMAP4430_OPTFCLKEN_TXPHYCLK_SHIFT			8
-#define OMAP4430_OPTFCLKEN_TXPHYCLK_WIDTH			0x1
-#define OMAP4430_OPTFCLKEN_TXPHYCLK_MASK			(1 << 8)
-
-/* Used by CM_L3INIT_USB_TLL_CLKCTRL */
 #define OMAP4430_OPTFCLKEN_USB_CH0_CLK_SHIFT			8
-#define OMAP4430_OPTFCLKEN_USB_CH0_CLK_WIDTH			0x1
-#define OMAP4430_OPTFCLKEN_USB_CH0_CLK_MASK			(1 << 8)
-
-/* Used by CM_L3INIT_USB_TLL_CLKCTRL */
 #define OMAP4430_OPTFCLKEN_USB_CH1_CLK_SHIFT			9
-#define OMAP4430_OPTFCLKEN_USB_CH1_CLK_WIDTH			0x1
-#define OMAP4430_OPTFCLKEN_USB_CH1_CLK_MASK			(1 << 9)
-
-/* Used by CM_L3INIT_USB_TLL_CLKCTRL */
 #define OMAP4430_OPTFCLKEN_USB_CH2_CLK_SHIFT			10
-#define OMAP4430_OPTFCLKEN_USB_CH2_CLK_WIDTH			0x1
-#define OMAP4430_OPTFCLKEN_USB_CH2_CLK_MASK			(1 << 10)
-
-/* Used by CM_L3INIT_USB_HOST_CLKCTRL */
 #define OMAP4430_OPTFCLKEN_UTMI_P1_CLK_SHIFT			8
-#define OMAP4430_OPTFCLKEN_UTMI_P1_CLK_WIDTH			0x1
-#define OMAP4430_OPTFCLKEN_UTMI_P1_CLK_MASK			(1 << 8)
-
-/* Used by CM_L3INIT_USB_HOST_CLKCTRL */
 #define OMAP4430_OPTFCLKEN_UTMI_P2_CLK_SHIFT			9
-#define OMAP4430_OPTFCLKEN_UTMI_P2_CLK_WIDTH			0x1
-#define OMAP4430_OPTFCLKEN_UTMI_P2_CLK_MASK			(1 << 9)
-
-/* Used by CM_L3INIT_USB_HOST_CLKCTRL */
 #define OMAP4430_OPTFCLKEN_UTMI_P3_CLK_SHIFT			10
-#define OMAP4430_OPTFCLKEN_UTMI_P3_CLK_WIDTH			0x1
-#define OMAP4430_OPTFCLKEN_UTMI_P3_CLK_MASK			(1 << 10)
-
-/* Used by CM_L3INIT_USB_OTG_CLKCTRL */
 #define OMAP4430_OPTFCLKEN_XCLK_SHIFT				8
-#define OMAP4430_OPTFCLKEN_XCLK_WIDTH				0x1
-#define OMAP4430_OPTFCLKEN_XCLK_MASK				(1 << 8)
-
-/* Used by CM_EMU_OVERRIDE_DPLL_CORE */
-#define OMAP4430_OVERRIDE_ENABLE_SHIFT				19
-#define OMAP4430_OVERRIDE_ENABLE_WIDTH				0x1
-#define OMAP4430_OVERRIDE_ENABLE_MASK				(1 << 19)
-
-/* Used by CM_CLKSEL_ABE */
 #define OMAP4430_PAD_CLKS_GATE_SHIFT				8
-#define OMAP4430_PAD_CLKS_GATE_WIDTH				0x1
-#define OMAP4430_PAD_CLKS_GATE_MASK				(1 << 8)
-
-/* Used by CM_CORE_DVFS_CURRENT, CM_IVA_DVFS_CURRENT */
-#define OMAP4430_PERF_CURRENT_SHIFT				0
-#define OMAP4430_PERF_CURRENT_WIDTH				0x8
-#define OMAP4430_PERF_CURRENT_MASK				(0xff << 0)
-
-/*
- * Used by CM_CORE_DVFS_PERF1, CM_CORE_DVFS_PERF2, CM_CORE_DVFS_PERF3,
- * CM_CORE_DVFS_PERF4, CM_IVA_DVFS_PERF_ABE, CM_IVA_DVFS_PERF_IVAHD,
- * CM_IVA_DVFS_PERF_TESLA
- */
-#define OMAP4430_PERF_REQ_SHIFT					0
-#define OMAP4430_PERF_REQ_WIDTH					0x8
-#define OMAP4430_PERF_REQ_MASK					(0xff << 0)
-
-/* Used by CM_RESTORE_ST */
-#define OMAP4430_PHASE1_COMPLETED_SHIFT				0
-#define OMAP4430_PHASE1_COMPLETED_WIDTH				0x1
-#define OMAP4430_PHASE1_COMPLETED_MASK				(1 << 0)
-
-/* Used by CM_RESTORE_ST */
-#define OMAP4430_PHASE2A_COMPLETED_SHIFT			1
-#define OMAP4430_PHASE2A_COMPLETED_WIDTH			0x1
-#define OMAP4430_PHASE2A_COMPLETED_MASK				(1 << 1)
-
-/* Used by CM_RESTORE_ST */
-#define OMAP4430_PHASE2B_COMPLETED_SHIFT			2
-#define OMAP4430_PHASE2B_COMPLETED_WIDTH			0x1
-#define OMAP4430_PHASE2B_COMPLETED_MASK				(1 << 2)
-
-/* Used by CM_EMU_DEBUGSS_CLKCTRL */
 #define OMAP4430_PMD_STM_MUX_CTRL_SHIFT				20
 #define OMAP4430_PMD_STM_MUX_CTRL_WIDTH				0x2
-#define OMAP4430_PMD_STM_MUX_CTRL_MASK				(0x3 << 20)
-
-/* Used by CM_EMU_DEBUGSS_CLKCTRL */
 #define OMAP4430_PMD_TRACE_MUX_CTRL_SHIFT			22
 #define OMAP4430_PMD_TRACE_MUX_CTRL_WIDTH			0x2
-#define OMAP4430_PMD_TRACE_MUX_CTRL_MASK			(0x3 << 22)
-
-/* Used by CM_DYN_DEP_PRESCAL */
-#define OMAP4430_PRESCAL_SHIFT					0
-#define OMAP4430_PRESCAL_WIDTH					0x6
-#define OMAP4430_PRESCAL_MASK					(0x3f << 0)
-
-/* Used by REVISION_CM1, REVISION_CM2 */
-#define OMAP4430_R_RTL_SHIFT					11
-#define OMAP4430_R_RTL_WIDTH					0x5
-#define OMAP4430_R_RTL_MASK					(0x1f << 11)
-
-/* Used by CM_L3INIT_USB_HOST_CLKCTRL, CM_L3INIT_USB_TLL_CLKCTRL */
-#define OMAP4430_SAR_MODE_SHIFT					4
-#define OMAP4430_SAR_MODE_WIDTH					0x1
-#define OMAP4430_SAR_MODE_MASK					(1 << 4)
-
-/* Used by CM_SCALE_FCLK */
 #define OMAP4430_SCALE_FCLK_SHIFT				0
 #define OMAP4430_SCALE_FCLK_WIDTH				0x1
-#define OMAP4430_SCALE_FCLK_MASK				(1 << 0)
-
-/* Used by REVISION_CM1, REVISION_CM2 */
-#define OMAP4430_SCHEME_SHIFT					30
-#define OMAP4430_SCHEME_WIDTH					0x2
-#define OMAP4430_SCHEME_MASK					(0x3 << 30)
-
-/* Used by CM_L4CFG_DYNAMICDEP */
-#define OMAP4430_SDMA_DYNDEP_SHIFT				11
-#define OMAP4430_SDMA_DYNDEP_WIDTH				0x1
-#define OMAP4430_SDMA_DYNDEP_MASK				(1 << 11)
-
-/* Used by CM_DUCATI_STATICDEP, CM_MPU_STATICDEP */
-#define OMAP4430_SDMA_STATDEP_SHIFT				11
-#define OMAP4430_SDMA_STATDEP_WIDTH				0x1
-#define OMAP4430_SDMA_STATDEP_MASK				(1 << 11)
-
-/* Used by CM_CLKSEL_ABE */
 #define OMAP4430_SLIMBUS_CLK_GATE_SHIFT				10
-#define OMAP4430_SLIMBUS_CLK_GATE_WIDTH				0x1
-#define OMAP4430_SLIMBUS_CLK_GATE_MASK				(1 << 10)
-
-/*
- * Used by CM1_ABE_AESS_CLKCTRL, CM_CAM_FDIF_CLKCTRL, CM_CAM_ISS_CLKCTRL,
- * CM_D2D_SAD2D_CLKCTRL, CM_DSS_DSS_CLKCTRL, CM_DUCATI_DUCATI_CLKCTRL,
- * CM_EMU_DEBUGSS_CLKCTRL, CM_GFX_GFX_CLKCTRL, CM_IVAHD_IVAHD_CLKCTRL,
- * CM_L3INIT_HSI_CLKCTRL, CM_L3INIT_MMC1_CLKCTRL, CM_L3INIT_MMC2_CLKCTRL,
- * CM_L3INIT_USB_HOST_CLKCTRL, CM_L3INIT_USB_HOST_FS_CLKCTRL,
- * CM_L3INIT_USB_OTG_CLKCTRL, CM_L4SEC_CRYPTODMA_CLKCTRL, CM_MPU_MPU_CLKCTRL,
- * CM_SDMA_SDMA_CLKCTRL, CM_TESLA_TESLA_CLKCTRL
- */
-#define OMAP4430_STBYST_SHIFT					18
-#define OMAP4430_STBYST_WIDTH					0x1
-#define OMAP4430_STBYST_MASK					(1 << 18)
-
-/*
- * Used by CM_IDLEST_DPLL_ABE, CM_IDLEST_DPLL_CORE, CM_IDLEST_DPLL_DDRPHY,
- * CM_IDLEST_DPLL_IVA, CM_IDLEST_DPLL_MPU, CM_IDLEST_DPLL_PER,
- * CM_IDLEST_DPLL_UNIPRO, CM_IDLEST_DPLL_USB
- */
-#define OMAP4430_ST_DPLL_CLK_SHIFT				0
-#define OMAP4430_ST_DPLL_CLK_WIDTH				0x1
 #define OMAP4430_ST_DPLL_CLK_MASK				(1 << 0)
-
-/* Used by CM_CLKDCOLDO_DPLL_USB */
-#define OMAP4430_ST_DPLL_CLKDCOLDO_SHIFT			9
-#define OMAP4430_ST_DPLL_CLKDCOLDO_WIDTH			0x1
-#define OMAP4430_ST_DPLL_CLKDCOLDO_MASK				(1 << 9)
-
-/*
- * Used by CM_DIV_M2_DPLL_ABE, CM_DIV_M2_DPLL_CORE, CM_DIV_M2_DPLL_DDRPHY,
- * CM_DIV_M2_DPLL_MPU, CM_DIV_M2_DPLL_PER, CM_DIV_M2_DPLL_USB
- */
-#define OMAP4430_ST_DPLL_CLKOUT_SHIFT				9
-#define OMAP4430_ST_DPLL_CLKOUT_WIDTH				0x1
-#define OMAP4430_ST_DPLL_CLKOUT_MASK				(1 << 9)
-
-/* Used by CM_DIV_M3_DPLL_ABE, CM_DIV_M3_DPLL_CORE, CM_DIV_M3_DPLL_PER */
-#define OMAP4430_ST_DPLL_CLKOUTHIF_SHIFT			9
-#define OMAP4430_ST_DPLL_CLKOUTHIF_WIDTH			0x1
-#define OMAP4430_ST_DPLL_CLKOUTHIF_MASK				(1 << 9)
-
-/* Used by CM_DIV_M2_DPLL_ABE, CM_DIV_M2_DPLL_PER, CM_DIV_M2_DPLL_UNIPRO */
-#define OMAP4430_ST_DPLL_CLKOUTX2_SHIFT				11
-#define OMAP4430_ST_DPLL_CLKOUTX2_WIDTH				0x1
-#define OMAP4430_ST_DPLL_CLKOUTX2_MASK				(1 << 11)
-
-/*
- * Used by CM_DIV_M4_DPLL_CORE, CM_DIV_M4_DPLL_DDRPHY, CM_DIV_M4_DPLL_IVA,
- * CM_DIV_M4_DPLL_PER
- */
-#define OMAP4430_ST_HSDIVIDER_CLKOUT1_SHIFT			9
-#define OMAP4430_ST_HSDIVIDER_CLKOUT1_WIDTH			0x1
-#define OMAP4430_ST_HSDIVIDER_CLKOUT1_MASK			(1 << 9)
-
-/*
- * Used by CM_DIV_M5_DPLL_CORE, CM_DIV_M5_DPLL_DDRPHY, CM_DIV_M5_DPLL_IVA,
- * CM_DIV_M5_DPLL_PER
- */
-#define OMAP4430_ST_HSDIVIDER_CLKOUT2_SHIFT			9
-#define OMAP4430_ST_HSDIVIDER_CLKOUT2_WIDTH			0x1
-#define OMAP4430_ST_HSDIVIDER_CLKOUT2_MASK			(1 << 9)
-
-/* Used by CM_DIV_M6_DPLL_CORE, CM_DIV_M6_DPLL_DDRPHY, CM_DIV_M6_DPLL_PER */
-#define OMAP4430_ST_HSDIVIDER_CLKOUT3_SHIFT			9
-#define OMAP4430_ST_HSDIVIDER_CLKOUT3_WIDTH			0x1
-#define OMAP4430_ST_HSDIVIDER_CLKOUT3_MASK			(1 << 9)
-
-/* Used by CM_DIV_M7_DPLL_CORE, CM_DIV_M7_DPLL_PER */
-#define OMAP4430_ST_HSDIVIDER_CLKOUT4_SHIFT			9
-#define OMAP4430_ST_HSDIVIDER_CLKOUT4_WIDTH			0x1
-#define OMAP4430_ST_HSDIVIDER_CLKOUT4_MASK			(1 << 9)
-
-/*
- * Used by CM_IDLEST_DPLL_ABE, CM_IDLEST_DPLL_CORE, CM_IDLEST_DPLL_DDRPHY,
- * CM_IDLEST_DPLL_IVA, CM_IDLEST_DPLL_MPU, CM_IDLEST_DPLL_PER,
- * CM_IDLEST_DPLL_UNIPRO, CM_IDLEST_DPLL_USB
- */
-#define OMAP4430_ST_MN_BYPASS_SHIFT				8
-#define OMAP4430_ST_MN_BYPASS_WIDTH				0x1
-#define OMAP4430_ST_MN_BYPASS_MASK				(1 << 8)
-
-/* Used by CM_SYS_CLKSEL */
 #define OMAP4430_SYS_CLKSEL_SHIFT				0
 #define OMAP4430_SYS_CLKSEL_WIDTH				0x3
-#define OMAP4430_SYS_CLKSEL_MASK				(0x7 << 0)
-
-/* Used by CM_L4CFG_DYNAMICDEP */
-#define OMAP4430_TESLA_DYNDEP_SHIFT				1
-#define OMAP4430_TESLA_DYNDEP_WIDTH				0x1
-#define OMAP4430_TESLA_DYNDEP_MASK				(1 << 1)
-
-/* Used by CM_DUCATI_STATICDEP, CM_MPU_STATICDEP */
 #define OMAP4430_TESLA_STATDEP_SHIFT				1
-#define OMAP4430_TESLA_STATDEP_WIDTH				0x1
-#define OMAP4430_TESLA_STATDEP_MASK				(1 << 1)
-
-/*
- * Used by CM_D2D_DYNAMICDEP, CM_DUCATI_DYNAMICDEP, CM_EMU_DYNAMICDEP,
- * CM_L3_1_DYNAMICDEP, CM_L3_2_DYNAMICDEP, CM_L4CFG_DYNAMICDEP,
- * CM_L4PER_DYNAMICDEP, CM_MPU_DYNAMICDEP, CM_TESLA_DYNAMICDEP
- */
-#define OMAP4430_WINDOWSIZE_SHIFT				24
-#define OMAP4430_WINDOWSIZE_WIDTH				0x4
-#define OMAP4430_WINDOWSIZE_MASK				(0xf << 24)
-
-/* Used by REVISION_CM1, REVISION_CM2 */
-#define OMAP4430_X_MAJOR_SHIFT					8
-#define OMAP4430_X_MAJOR_WIDTH					0x3
-#define OMAP4430_X_MAJOR_MASK					(0x7 << 8)
-
-/* Used by REVISION_CM1, REVISION_CM2 */
-#define OMAP4430_Y_MINOR_SHIFT					0
-#define OMAP4430_Y_MINOR_WIDTH					0x6
-#define OMAP4430_Y_MINOR_MASK					(0x3f << 0)
 #endif
diff --git a/arch/arm/mach-omap2/cm-regbits-54xx.h b/arch/arm/mach-omap2/cm-regbits-54xx.h
index e83b8e352b6e..896ae9fc4cfb 100644
--- a/arch/arm/mach-omap2/cm-regbits-54xx.h
+++ b/arch/arm/mach-omap2/cm-regbits-54xx.h
@@ -21,1717 +21,84 @@
 #ifndef __ARCH_ARM_MACH_OMAP2_CM_REGBITS_54XX_H
 #define __ARCH_ARM_MACH_OMAP2_CM_REGBITS_54XX_H
 
-/* Used by CM_DSP_DYNAMICDEP, CM_L3MAIN1_DYNAMICDEP, CM_MPU_DYNAMICDEP */
-#define OMAP54XX_ABE_DYNDEP_SHIFT					3
-#define OMAP54XX_ABE_DYNDEP_WIDTH					0x1
-#define OMAP54XX_ABE_DYNDEP_MASK					(1 << 3)
-
-/*
- * Used by CM_C2C_STATICDEP, CM_DMA_STATICDEP, CM_DSP_STATICDEP,
- * CM_IPU_STATICDEP, CM_L3INIT_STATICDEP, CM_MIPIEXT_STATICDEP, CM_MPU_STATICDEP
- */
 #define OMAP54XX_ABE_STATDEP_SHIFT					3
-#define OMAP54XX_ABE_STATDEP_WIDTH					0x1
-#define OMAP54XX_ABE_STATDEP_MASK					(1 << 3)
-
-/*
- * Used by CM_AUTOIDLE_DPLL_ABE, CM_AUTOIDLE_DPLL_CORE, CM_AUTOIDLE_DPLL_IVA,
- * CM_AUTOIDLE_DPLL_MPU, CM_AUTOIDLE_DPLL_PER, CM_AUTOIDLE_DPLL_UNIPRO1,
- * CM_AUTOIDLE_DPLL_UNIPRO2, CM_AUTOIDLE_DPLL_USB
- */
-#define OMAP54XX_AUTO_DPLL_MODE_SHIFT					0
-#define OMAP54XX_AUTO_DPLL_MODE_WIDTH					0x3
 #define OMAP54XX_AUTO_DPLL_MODE_MASK					(0x7 << 0)
-
-/* Used by CM_L3MAIN2_DYNAMICDEP, CM_L4CFG_DYNAMICDEP */
-#define OMAP54XX_C2C_DYNDEP_SHIFT					18
-#define OMAP54XX_C2C_DYNDEP_WIDTH					0x1
-#define OMAP54XX_C2C_DYNDEP_MASK					(1 << 18)
-
-/* Used by CM_MPU_STATICDEP */
-#define OMAP54XX_C2C_STATDEP_SHIFT					18
-#define OMAP54XX_C2C_STATDEP_WIDTH					0x1
-#define OMAP54XX_C2C_STATDEP_MASK					(1 << 18)
-
-/* Used by CM_IPU_DYNAMICDEP, CM_L3MAIN2_DYNAMICDEP, CM_L4CFG_DYNAMICDEP */
-#define OMAP54XX_CAM_DYNDEP_SHIFT					9
-#define OMAP54XX_CAM_DYNDEP_WIDTH					0x1
-#define OMAP54XX_CAM_DYNDEP_MASK					(1 << 9)
-
-/*
- * Used by CM_DMA_STATICDEP, CM_DSP_STATICDEP, CM_IPU_STATICDEP,
- * CM_MPU_STATICDEP
- */
-#define OMAP54XX_CAM_STATDEP_SHIFT					9
-#define OMAP54XX_CAM_STATDEP_WIDTH					0x1
-#define OMAP54XX_CAM_STATDEP_MASK					(1 << 9)
-
-/* Used by CM_ABE_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_ABE_24M_GFCLK_SHIFT			13
-#define OMAP54XX_CLKACTIVITY_ABE_24M_GFCLK_WIDTH			0x1
-#define OMAP54XX_CLKACTIVITY_ABE_24M_GFCLK_MASK				(1 << 13)
-
-/* Used by CM_ABE_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_ABE_32K_CLK_SHIFT				12
-#define OMAP54XX_CLKACTIVITY_ABE_32K_CLK_WIDTH				0x1
-#define OMAP54XX_CLKACTIVITY_ABE_32K_CLK_MASK				(1 << 12)
-
-/* Used by CM_ABE_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_ABE_GICLK_SHIFT				9
-#define OMAP54XX_CLKACTIVITY_ABE_GICLK_WIDTH				0x1
-#define OMAP54XX_CLKACTIVITY_ABE_GICLK_MASK				(1 << 9)
-
-/* Used by CM_WKUPAON_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_ABE_LP_CLK_SHIFT				9
-#define OMAP54XX_CLKACTIVITY_ABE_LP_CLK_WIDTH				0x1
-#define OMAP54XX_CLKACTIVITY_ABE_LP_CLK_MASK				(1 << 9)
-
-/* Used by CM_ABE_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_ABE_SYS_CLK_SHIFT				11
-#define OMAP54XX_CLKACTIVITY_ABE_SYS_CLK_WIDTH				0x1
-#define OMAP54XX_CLKACTIVITY_ABE_SYS_CLK_MASK				(1 << 11)
-
-/* Used by CM_ABE_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_ABE_X2_CLK_SHIFT				8
-#define OMAP54XX_CLKACTIVITY_ABE_X2_CLK_WIDTH				0x1
-#define OMAP54XX_CLKACTIVITY_ABE_X2_CLK_MASK				(1 << 8)
-
-/* Used by CM_DSS_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_BB2D_GFCLK_SHIFT				13
-#define OMAP54XX_CLKACTIVITY_BB2D_GFCLK_WIDTH				0x1
-#define OMAP54XX_CLKACTIVITY_BB2D_GFCLK_MASK				(1 << 13)
-
-/* Used by CM_C2C_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_C2C_GFCLK_SHIFT				9
-#define OMAP54XX_CLKACTIVITY_C2C_GFCLK_WIDTH				0x1
-#define OMAP54XX_CLKACTIVITY_C2C_GFCLK_MASK				(1 << 9)
-
-/* Used by CM_C2C_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_C2C_GICLK_SHIFT				10
-#define OMAP54XX_CLKACTIVITY_C2C_GICLK_WIDTH				0x1
-#define OMAP54XX_CLKACTIVITY_C2C_GICLK_MASK				(1 << 10)
-
-/* Used by CM_C2C_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_C2C_L4_GICLK_SHIFT				8
-#define OMAP54XX_CLKACTIVITY_C2C_L4_GICLK_WIDTH				0x1
-#define OMAP54XX_CLKACTIVITY_C2C_L4_GICLK_MASK				(1 << 8)
-
-/* Used by CM_CAM_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_CAM_BOOST_GCLK_SHIFT			11
-#define OMAP54XX_CLKACTIVITY_CAM_BOOST_GCLK_WIDTH			0x1
-#define OMAP54XX_CLKACTIVITY_CAM_BOOST_GCLK_MASK			(1 << 11)
-
-/* Used by CM_CAM_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_CAM_GCLK_SHIFT				8
-#define OMAP54XX_CLKACTIVITY_CAM_GCLK_WIDTH				0x1
-#define OMAP54XX_CLKACTIVITY_CAM_GCLK_MASK				(1 << 8)
-
-/* Used by CM_CAM_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_CAM_L3_GICLK_SHIFT				12
-#define OMAP54XX_CLKACTIVITY_CAM_L3_GICLK_WIDTH				0x1
-#define OMAP54XX_CLKACTIVITY_CAM_L3_GICLK_MASK				(1 << 12)
-
-/* Used by CM_COREAON_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_COREAON_32K_GFCLK_SHIFT			12
-#define OMAP54XX_CLKACTIVITY_COREAON_32K_GFCLK_WIDTH			0x1
-#define OMAP54XX_CLKACTIVITY_COREAON_32K_GFCLK_MASK			(1 << 12)
-
-/* Used by CM_COREAON_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_COREAON_IO_SRCOMP_GFCLK_SHIFT		14
-#define OMAP54XX_CLKACTIVITY_COREAON_IO_SRCOMP_GFCLK_WIDTH		0x1
-#define OMAP54XX_CLKACTIVITY_COREAON_IO_SRCOMP_GFCLK_MASK		(1 << 14)
-
-/* Used by CM_COREAON_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_COREAON_L4_GICLK_SHIFT			8
-#define OMAP54XX_CLKACTIVITY_COREAON_L4_GICLK_WIDTH			0x1
-#define OMAP54XX_CLKACTIVITY_COREAON_L4_GICLK_MASK			(1 << 8)
-
-/* Used by CM_CAM_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_CSI_PHY_GFCLK_SHIFT			9
-#define OMAP54XX_CLKACTIVITY_CSI_PHY_GFCLK_WIDTH			0x1
-#define OMAP54XX_CLKACTIVITY_CSI_PHY_GFCLK_MASK				(1 << 9)
-
-/* Used by CM_CUSTEFUSE_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_CUSTEFUSE_L4_GICLK_SHIFT			8
-#define OMAP54XX_CLKACTIVITY_CUSTEFUSE_L4_GICLK_WIDTH			0x1
-#define OMAP54XX_CLKACTIVITY_CUSTEFUSE_L4_GICLK_MASK			(1 << 8)
-
-/* Used by CM_CUSTEFUSE_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_CUSTEFUSE_SYS_GFCLK_SHIFT			9
-#define OMAP54XX_CLKACTIVITY_CUSTEFUSE_SYS_GFCLK_WIDTH			0x1
-#define OMAP54XX_CLKACTIVITY_CUSTEFUSE_SYS_GFCLK_MASK			(1 << 9)
-
-/* Used by CM_EMIF_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_DLL_GCLK_SHIFT				9
-#define OMAP54XX_CLKACTIVITY_DLL_GCLK_WIDTH				0x1
-#define OMAP54XX_CLKACTIVITY_DLL_GCLK_MASK				(1 << 9)
-
-/* Used by CM_DMA_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_DMA_L3_GICLK_SHIFT				8
-#define OMAP54XX_CLKACTIVITY_DMA_L3_GICLK_WIDTH				0x1
-#define OMAP54XX_CLKACTIVITY_DMA_L3_GICLK_MASK				(1 << 8)
-
-/* Used by CM_DSP_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_DSP_GCLK_SHIFT				8
-#define OMAP54XX_CLKACTIVITY_DSP_GCLK_WIDTH				0x1
-#define OMAP54XX_CLKACTIVITY_DSP_GCLK_MASK				(1 << 8)
-
-/* Used by CM_DSS_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_DSS_GFCLK_SHIFT				9
-#define OMAP54XX_CLKACTIVITY_DSS_GFCLK_WIDTH				0x1
-#define OMAP54XX_CLKACTIVITY_DSS_GFCLK_MASK				(1 << 9)
-
-/* Used by CM_DSS_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_DSS_L3_GICLK_SHIFT				8
-#define OMAP54XX_CLKACTIVITY_DSS_L3_GICLK_WIDTH				0x1
-#define OMAP54XX_CLKACTIVITY_DSS_L3_GICLK_MASK				(1 << 8)
-
-/* Used by CM_DSS_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_DSS_SYS_GFCLK_SHIFT			10
-#define OMAP54XX_CLKACTIVITY_DSS_SYS_GFCLK_WIDTH			0x1
-#define OMAP54XX_CLKACTIVITY_DSS_SYS_GFCLK_MASK				(1 << 10)
-
-/* Used by CM_EMIF_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_EMIF_L3_GICLK_SHIFT			8
-#define OMAP54XX_CLKACTIVITY_EMIF_L3_GICLK_WIDTH			0x1
-#define OMAP54XX_CLKACTIVITY_EMIF_L3_GICLK_MASK				(1 << 8)
-
-/* Used by CM_EMIF_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_EMIF_LL_GCLK_SHIFT				11
-#define OMAP54XX_CLKACTIVITY_EMIF_LL_GCLK_WIDTH				0x1
-#define OMAP54XX_CLKACTIVITY_EMIF_LL_GCLK_MASK				(1 << 11)
-
-/* Used by CM_EMIF_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_EMIF_PHY_GCLK_SHIFT			10
-#define OMAP54XX_CLKACTIVITY_EMIF_PHY_GCLK_WIDTH			0x1
-#define OMAP54XX_CLKACTIVITY_EMIF_PHY_GCLK_MASK				(1 << 10)
-
-/* Used by CM_EMU_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_EMU_SYS_GCLK_SHIFT				8
-#define OMAP54XX_CLKACTIVITY_EMU_SYS_GCLK_WIDTH				0x1
-#define OMAP54XX_CLKACTIVITY_EMU_SYS_GCLK_MASK				(1 << 8)
-
-/* Used by CM_CAM_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_FDIF_GCLK_SHIFT				10
-#define OMAP54XX_CLKACTIVITY_FDIF_GCLK_WIDTH				0x1
-#define OMAP54XX_CLKACTIVITY_FDIF_GCLK_MASK				(1 << 10)
-
-/* Used by CM_ABE_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_FUNC_24M_GFCLK_SHIFT			10
-#define OMAP54XX_CLKACTIVITY_FUNC_24M_GFCLK_WIDTH			0x1
-#define OMAP54XX_CLKACTIVITY_FUNC_24M_GFCLK_MASK			(1 << 10)
-
-/* Used by CM_GPU_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_GPU_CORE_GCLK_SHIFT			9
-#define OMAP54XX_CLKACTIVITY_GPU_CORE_GCLK_WIDTH			0x1
-#define OMAP54XX_CLKACTIVITY_GPU_CORE_GCLK_MASK				(1 << 9)
-
-/* Used by CM_GPU_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_GPU_HYD_GCLK_SHIFT				10
-#define OMAP54XX_CLKACTIVITY_GPU_HYD_GCLK_WIDTH				0x1
-#define OMAP54XX_CLKACTIVITY_GPU_HYD_GCLK_MASK				(1 << 10)
-
-/* Used by CM_GPU_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_GPU_SYS_GCLK_SHIFT				8
-#define OMAP54XX_CLKACTIVITY_GPU_SYS_GCLK_WIDTH				0x1
-#define OMAP54XX_CLKACTIVITY_GPU_SYS_GCLK_MASK				(1 << 8)
-
-/* Used by CM_DSS_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_HDMI_CEC_GFCLK_SHIFT			12
-#define OMAP54XX_CLKACTIVITY_HDMI_CEC_GFCLK_WIDTH			0x1
-#define OMAP54XX_CLKACTIVITY_HDMI_CEC_GFCLK_MASK			(1 << 12)
-
-/* Used by CM_DSS_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_HDMI_PHY_GFCLK_SHIFT			11
-#define OMAP54XX_CLKACTIVITY_HDMI_PHY_GFCLK_WIDTH			0x1
-#define OMAP54XX_CLKACTIVITY_HDMI_PHY_GFCLK_MASK			(1 << 11)
-
-/* Used by CM_L3INIT_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_HSIC_P1_480M_GFCLK_SHIFT			20
-#define OMAP54XX_CLKACTIVITY_HSIC_P1_480M_GFCLK_WIDTH			0x1
-#define OMAP54XX_CLKACTIVITY_HSIC_P1_480M_GFCLK_MASK			(1 << 20)
-
-/* Used by CM_L3INIT_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_HSIC_P1_GFCLK_SHIFT			26
-#define OMAP54XX_CLKACTIVITY_HSIC_P1_GFCLK_WIDTH			0x1
-#define OMAP54XX_CLKACTIVITY_HSIC_P1_GFCLK_MASK				(1 << 26)
-
-/* Used by CM_L3INIT_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_HSIC_P2_480M_GFCLK_SHIFT			21
-#define OMAP54XX_CLKACTIVITY_HSIC_P2_480M_GFCLK_WIDTH			0x1
-#define OMAP54XX_CLKACTIVITY_HSIC_P2_480M_GFCLK_MASK			(1 << 21)
-
-/* Used by CM_L3INIT_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_HSIC_P2_GFCLK_SHIFT			27
-#define OMAP54XX_CLKACTIVITY_HSIC_P2_GFCLK_WIDTH			0x1
-#define OMAP54XX_CLKACTIVITY_HSIC_P2_GFCLK_MASK				(1 << 27)
-
-/* Used by CM_L3INIT_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_HSIC_P3_480M_GFCLK_SHIFT			6
-#define OMAP54XX_CLKACTIVITY_HSIC_P3_480M_GFCLK_WIDTH			0x1
-#define OMAP54XX_CLKACTIVITY_HSIC_P3_480M_GFCLK_MASK			(1 << 6)
-
-/* Used by CM_L3INIT_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_HSIC_P3_GFCLK_SHIFT			7
-#define OMAP54XX_CLKACTIVITY_HSIC_P3_GFCLK_WIDTH			0x1
-#define OMAP54XX_CLKACTIVITY_HSIC_P3_GFCLK_MASK				(1 << 7)
-
-/* Used by CM_L3INIT_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_HSI_GFCLK_SHIFT				16
-#define OMAP54XX_CLKACTIVITY_HSI_GFCLK_WIDTH				0x1
-#define OMAP54XX_CLKACTIVITY_HSI_GFCLK_MASK				(1 << 16)
-
-/* Used by CM_IPU_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_IPU_GCLK_SHIFT				8
-#define OMAP54XX_CLKACTIVITY_IPU_GCLK_WIDTH				0x1
-#define OMAP54XX_CLKACTIVITY_IPU_GCLK_MASK				(1 << 8)
-
-/* Used by CM_IVA_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_IVA_GCLK_SHIFT				8
-#define OMAP54XX_CLKACTIVITY_IVA_GCLK_WIDTH				0x1
-#define OMAP54XX_CLKACTIVITY_IVA_GCLK_MASK				(1 << 8)
-
-/* Used by CM_L3INIT_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_L3INIT_48M_GFCLK_SHIFT			12
-#define OMAP54XX_CLKACTIVITY_L3INIT_48M_GFCLK_WIDTH			0x1
-#define OMAP54XX_CLKACTIVITY_L3INIT_48M_GFCLK_MASK			(1 << 12)
-
-/* Used by CM_L3INIT_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_L3INIT_60M_P1_GFCLK_SHIFT			28
-#define OMAP54XX_CLKACTIVITY_L3INIT_60M_P1_GFCLK_WIDTH			0x1
-#define OMAP54XX_CLKACTIVITY_L3INIT_60M_P1_GFCLK_MASK			(1 << 28)
-
-/* Used by CM_L3INIT_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_L3INIT_60M_P2_GFCLK_SHIFT			29
-#define OMAP54XX_CLKACTIVITY_L3INIT_60M_P2_GFCLK_WIDTH			0x1
-#define OMAP54XX_CLKACTIVITY_L3INIT_60M_P2_GFCLK_MASK			(1 << 29)
-
-/* Used by CM_L3INIT_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_L3INIT_L3_GICLK_SHIFT			8
-#define OMAP54XX_CLKACTIVITY_L3INIT_L3_GICLK_WIDTH			0x1
-#define OMAP54XX_CLKACTIVITY_L3INIT_L3_GICLK_MASK			(1 << 8)
-
-/* Used by CM_L3INIT_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_L3INIT_L4_GICLK_SHIFT			9
-#define OMAP54XX_CLKACTIVITY_L3INIT_L4_GICLK_WIDTH			0x1
-#define OMAP54XX_CLKACTIVITY_L3INIT_L4_GICLK_MASK			(1 << 9)
-
-/* Used by CM_L3INIT_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_L3INIT_USB_OTG_SS_LFPS_TX_GFCLK_SHIFT	11
-#define OMAP54XX_CLKACTIVITY_L3INIT_USB_OTG_SS_LFPS_TX_GFCLK_WIDTH	0x1
-#define OMAP54XX_CLKACTIVITY_L3INIT_USB_OTG_SS_LFPS_TX_GFCLK_MASK	(1 << 11)
-
-/* Used by CM_L3INSTR_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_L3INSTR_DLL_AGING_GCLK_SHIFT		9
-#define OMAP54XX_CLKACTIVITY_L3INSTR_DLL_AGING_GCLK_WIDTH		0x1
-#define OMAP54XX_CLKACTIVITY_L3INSTR_DLL_AGING_GCLK_MASK		(1 << 9)
-
-/* Used by CM_L3INSTR_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_L3INSTR_L3_GICLK_SHIFT			8
-#define OMAP54XX_CLKACTIVITY_L3INSTR_L3_GICLK_WIDTH			0x1
-#define OMAP54XX_CLKACTIVITY_L3INSTR_L3_GICLK_MASK			(1 << 8)
-
-/* Used by CM_L3INSTR_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_L3INSTR_TS_GCLK_SHIFT			10
-#define OMAP54XX_CLKACTIVITY_L3INSTR_TS_GCLK_WIDTH			0x1
-#define OMAP54XX_CLKACTIVITY_L3INSTR_TS_GCLK_MASK			(1 << 10)
-
-/* Used by CM_L3MAIN1_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_L3MAIN1_L3_GICLK_SHIFT			8
-#define OMAP54XX_CLKACTIVITY_L3MAIN1_L3_GICLK_WIDTH			0x1
-#define OMAP54XX_CLKACTIVITY_L3MAIN1_L3_GICLK_MASK			(1 << 8)
-
-/* Used by CM_L3MAIN2_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_L3MAIN2_L3_GICLK_SHIFT			8
-#define OMAP54XX_CLKACTIVITY_L3MAIN2_L3_GICLK_WIDTH			0x1
-#define OMAP54XX_CLKACTIVITY_L3MAIN2_L3_GICLK_MASK			(1 << 8)
-
-/* Used by CM_L4CFG_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_L4CFG_L4_GICLK_SHIFT			8
-#define OMAP54XX_CLKACTIVITY_L4CFG_L4_GICLK_WIDTH			0x1
-#define OMAP54XX_CLKACTIVITY_L4CFG_L4_GICLK_MASK			(1 << 8)
-
-/* Used by CM_L4PER_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_L4PER_L4_GICLK_SHIFT			8
-#define OMAP54XX_CLKACTIVITY_L4PER_L4_GICLK_WIDTH			0x1
-#define OMAP54XX_CLKACTIVITY_L4PER_L4_GICLK_MASK			(1 << 8)
-
-/* Used by CM_L4SEC_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_L4SEC_L3_GICLK_SHIFT			8
-#define OMAP54XX_CLKACTIVITY_L4SEC_L3_GICLK_WIDTH			0x1
-#define OMAP54XX_CLKACTIVITY_L4SEC_L3_GICLK_MASK			(1 << 8)
-
-/* Used by CM_L4SEC_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_L4SEC_L4_GICLK_SHIFT			9
-#define OMAP54XX_CLKACTIVITY_L4SEC_L4_GICLK_WIDTH			0x1
-#define OMAP54XX_CLKACTIVITY_L4SEC_L4_GICLK_MASK			(1 << 9)
-
-/* Used by CM_MIPIEXT_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_MIPIEXT_L3_GICLK_SHIFT			8
-#define OMAP54XX_CLKACTIVITY_MIPIEXT_L3_GICLK_WIDTH			0x1
-#define OMAP54XX_CLKACTIVITY_MIPIEXT_L3_GICLK_MASK			(1 << 8)
-
-/* Used by CM_MIPIEXT_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_MIPIEXT_PHY_REF_GFCLK_SHIFT		11
-#define OMAP54XX_CLKACTIVITY_MIPIEXT_PHY_REF_GFCLK_WIDTH		0x1
-#define OMAP54XX_CLKACTIVITY_MIPIEXT_PHY_REF_GFCLK_MASK			(1 << 11)
-
-/* Used by CM_L3INIT_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_MMC1_32K_GFCLK_SHIFT			2
-#define OMAP54XX_CLKACTIVITY_MMC1_32K_GFCLK_WIDTH			0x1
-#define OMAP54XX_CLKACTIVITY_MMC1_32K_GFCLK_MASK			(1 << 2)
-
-/* Used by CM_L3INIT_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_MMC1_GFCLK_SHIFT				17
-#define OMAP54XX_CLKACTIVITY_MMC1_GFCLK_WIDTH				0x1
-#define OMAP54XX_CLKACTIVITY_MMC1_GFCLK_MASK				(1 << 17)
-
-/* Used by CM_L3INIT_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_MMC2_GFCLK_SHIFT				18
-#define OMAP54XX_CLKACTIVITY_MMC2_GFCLK_WIDTH				0x1
-#define OMAP54XX_CLKACTIVITY_MMC2_GFCLK_MASK				(1 << 18)
-
-/* Used by CM_MPU_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_MPU_GCLK_SHIFT				8
-#define OMAP54XX_CLKACTIVITY_MPU_GCLK_WIDTH				0x1
-#define OMAP54XX_CLKACTIVITY_MPU_GCLK_MASK				(1 << 8)
-
-/* Used by CM_ABE_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_PAD_CLKS_SHIFT				14
-#define OMAP54XX_CLKACTIVITY_PAD_CLKS_WIDTH				0x1
-#define OMAP54XX_CLKACTIVITY_PAD_CLKS_MASK				(1 << 14)
-
-/* Used by CM_ABE_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_PAD_SLIMBUS1_CLK_SHIFT			15
-#define OMAP54XX_CLKACTIVITY_PAD_SLIMBUS1_CLK_WIDTH			0x1
-#define OMAP54XX_CLKACTIVITY_PAD_SLIMBUS1_CLK_MASK			(1 << 15)
-
-/* Used by CM_L3INIT_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_PAD_XCLK60MHSP1_SHIFT			3
-#define OMAP54XX_CLKACTIVITY_PAD_XCLK60MHSP1_WIDTH			0x1
-#define OMAP54XX_CLKACTIVITY_PAD_XCLK60MHSP1_MASK			(1 << 3)
-
-/* Used by CM_L3INIT_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_PAD_XCLK60MHSP2_SHIFT			4
-#define OMAP54XX_CLKACTIVITY_PAD_XCLK60MHSP2_WIDTH			0x1
-#define OMAP54XX_CLKACTIVITY_PAD_XCLK60MHSP2_MASK			(1 << 4)
-
-/* Used by CM_L4PER_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_PER_12M_GFCLK_SHIFT			15
-#define OMAP54XX_CLKACTIVITY_PER_12M_GFCLK_WIDTH			0x1
-#define OMAP54XX_CLKACTIVITY_PER_12M_GFCLK_MASK				(1 << 15)
-
-/* Used by CM_L4PER_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_PER_32K_GFCLK_SHIFT			17
-#define OMAP54XX_CLKACTIVITY_PER_32K_GFCLK_WIDTH			0x1
-#define OMAP54XX_CLKACTIVITY_PER_32K_GFCLK_MASK				(1 << 17)
-
-/* Used by CM_L4PER_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_PER_48M_GFCLK_SHIFT			18
-#define OMAP54XX_CLKACTIVITY_PER_48M_GFCLK_WIDTH			0x1
-#define OMAP54XX_CLKACTIVITY_PER_48M_GFCLK_MASK				(1 << 18)
-
-/* Used by CM_L4PER_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_PER_96M_GFCLK_SHIFT			19
-#define OMAP54XX_CLKACTIVITY_PER_96M_GFCLK_WIDTH			0x1
-#define OMAP54XX_CLKACTIVITY_PER_96M_GFCLK_MASK				(1 << 19)
-
-/* Used by CM_L3INIT_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_SATA_REF_GFCLK_SHIFT			19
-#define OMAP54XX_CLKACTIVITY_SATA_REF_GFCLK_WIDTH			0x1
-#define OMAP54XX_CLKACTIVITY_SATA_REF_GFCLK_MASK			(1 << 19)
-
-/* Used by CM_COREAON_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_SR_CORE_SYS_GFCLK_SHIFT			11
-#define OMAP54XX_CLKACTIVITY_SR_CORE_SYS_GFCLK_WIDTH			0x1
-#define OMAP54XX_CLKACTIVITY_SR_CORE_SYS_GFCLK_MASK			(1 << 11)
-
-/* Used by CM_COREAON_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_SR_MM_SYS_GFCLK_SHIFT			10
-#define OMAP54XX_CLKACTIVITY_SR_MM_SYS_GFCLK_WIDTH			0x1
-#define OMAP54XX_CLKACTIVITY_SR_MM_SYS_GFCLK_MASK			(1 << 10)
-
-/* Used by CM_COREAON_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_SR_MPU_SYS_GFCLK_SHIFT			9
-#define OMAP54XX_CLKACTIVITY_SR_MPU_SYS_GFCLK_WIDTH			0x1
-#define OMAP54XX_CLKACTIVITY_SR_MPU_SYS_GFCLK_MASK			(1 << 9)
-
-/* Used by CM_WKUPAON_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_SYS_CLK_SHIFT				8
-#define OMAP54XX_CLKACTIVITY_SYS_CLK_WIDTH				0x1
-#define OMAP54XX_CLKACTIVITY_SYS_CLK_MASK				(1 << 8)
-
-/* Used by CM_WKUPAON_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_SYS_CLK_ALL_SHIFT				15
-#define OMAP54XX_CLKACTIVITY_SYS_CLK_ALL_WIDTH				0x1
-#define OMAP54XX_CLKACTIVITY_SYS_CLK_ALL_MASK				(1 << 15)
-
-/* Used by CM_WKUPAON_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_SYS_CLK_FUNC_SHIFT				14
-#define OMAP54XX_CLKACTIVITY_SYS_CLK_FUNC_WIDTH				0x1
-#define OMAP54XX_CLKACTIVITY_SYS_CLK_FUNC_MASK				(1 << 14)
-
-/* Used by CM_L4PER_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_TIMER10_GFCLK_SHIFT			9
-#define OMAP54XX_CLKACTIVITY_TIMER10_GFCLK_WIDTH			0x1
-#define OMAP54XX_CLKACTIVITY_TIMER10_GFCLK_MASK				(1 << 9)
-
-/* Used by CM_L4PER_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_TIMER11_GFCLK_SHIFT			10
-#define OMAP54XX_CLKACTIVITY_TIMER11_GFCLK_WIDTH			0x1
-#define OMAP54XX_CLKACTIVITY_TIMER11_GFCLK_MASK				(1 << 10)
-
-/* Used by CM_L4PER_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_TIMER2_GFCLK_SHIFT				11
-#define OMAP54XX_CLKACTIVITY_TIMER2_GFCLK_WIDTH				0x1
-#define OMAP54XX_CLKACTIVITY_TIMER2_GFCLK_MASK				(1 << 11)
-
-/* Used by CM_L4PER_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_TIMER3_GFCLK_SHIFT				12
-#define OMAP54XX_CLKACTIVITY_TIMER3_GFCLK_WIDTH				0x1
-#define OMAP54XX_CLKACTIVITY_TIMER3_GFCLK_MASK				(1 << 12)
-
-/* Used by CM_L4PER_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_TIMER4_GFCLK_SHIFT				13
-#define OMAP54XX_CLKACTIVITY_TIMER4_GFCLK_WIDTH				0x1
-#define OMAP54XX_CLKACTIVITY_TIMER4_GFCLK_MASK				(1 << 13)
-
-/* Used by CM_L4PER_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_TIMER9_GFCLK_SHIFT				14
-#define OMAP54XX_CLKACTIVITY_TIMER9_GFCLK_WIDTH				0x1
-#define OMAP54XX_CLKACTIVITY_TIMER9_GFCLK_MASK				(1 << 14)
-
-/* Used by CM_L3INIT_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_TLL_CH0_GFCLK_SHIFT			22
-#define OMAP54XX_CLKACTIVITY_TLL_CH0_GFCLK_WIDTH			0x1
-#define OMAP54XX_CLKACTIVITY_TLL_CH0_GFCLK_MASK				(1 << 22)
-
-/* Used by CM_L3INIT_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_TLL_CH1_GFCLK_SHIFT			23
-#define OMAP54XX_CLKACTIVITY_TLL_CH1_GFCLK_WIDTH			0x1
-#define OMAP54XX_CLKACTIVITY_TLL_CH1_GFCLK_MASK				(1 << 23)
-
-/* Used by CM_L3INIT_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_TLL_CH2_GFCLK_SHIFT			24
-#define OMAP54XX_CLKACTIVITY_TLL_CH2_GFCLK_WIDTH			0x1
-#define OMAP54XX_CLKACTIVITY_TLL_CH2_GFCLK_MASK				(1 << 24)
-
-/* Used by CM_MIPIEXT_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_UNIPRO1_DPLL_CLK_SHIFT			10
-#define OMAP54XX_CLKACTIVITY_UNIPRO1_DPLL_CLK_WIDTH			0x1
-#define OMAP54XX_CLKACTIVITY_UNIPRO1_DPLL_CLK_MASK			(1 << 10)
-
-/* Used by CM_MIPIEXT_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_UNIPRO1_PHY_GFCLK_SHIFT			13
-#define OMAP54XX_CLKACTIVITY_UNIPRO1_PHY_GFCLK_WIDTH			0x1
-#define OMAP54XX_CLKACTIVITY_UNIPRO1_PHY_GFCLK_MASK			(1 << 13)
-
-/* Used by CM_MIPIEXT_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_UNIPRO1_TXPHY_LS_GFCLK_SHIFT		12
-#define OMAP54XX_CLKACTIVITY_UNIPRO1_TXPHY_LS_GFCLK_WIDTH		0x1
-#define OMAP54XX_CLKACTIVITY_UNIPRO1_TXPHY_LS_GFCLK_MASK		(1 << 12)
-
-/* Used by CM_L3INIT_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_UNIPRO2_DPLL_CLK_SHIFT			10
-#define OMAP54XX_CLKACTIVITY_UNIPRO2_DPLL_CLK_WIDTH			0x1
-#define OMAP54XX_CLKACTIVITY_UNIPRO2_DPLL_CLK_MASK			(1 << 10)
-
-/* Used by CM_L3INIT_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_UNIPRO2_PHY_GFCLK_SHIFT			13
-#define OMAP54XX_CLKACTIVITY_UNIPRO2_PHY_GFCLK_WIDTH			0x1
-#define OMAP54XX_CLKACTIVITY_UNIPRO2_PHY_GFCLK_MASK			(1 << 13)
-
-/* Used by CM_L3INIT_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_UNIPRO2_PHY_REF_GFCLK_SHIFT		5
-#define OMAP54XX_CLKACTIVITY_UNIPRO2_PHY_REF_GFCLK_WIDTH		0x1
-#define OMAP54XX_CLKACTIVITY_UNIPRO2_PHY_REF_GFCLK_MASK			(1 << 5)
-
-/* Used by CM_L3INIT_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_USB_DPLL_CLK_SHIFT				14
-#define OMAP54XX_CLKACTIVITY_USB_DPLL_CLK_WIDTH				0x1
-#define OMAP54XX_CLKACTIVITY_USB_DPLL_CLK_MASK				(1 << 14)
-
-/* Used by CM_L3INIT_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_USB_DPLL_HS_CLK_SHIFT			15
-#define OMAP54XX_CLKACTIVITY_USB_DPLL_HS_CLK_WIDTH			0x1
-#define OMAP54XX_CLKACTIVITY_USB_DPLL_HS_CLK_MASK			(1 << 15)
-
-/* Used by CM_L3INIT_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_USB_OTG_SS_REF_CLK_SHIFT			31
-#define OMAP54XX_CLKACTIVITY_USB_OTG_SS_REF_CLK_WIDTH			0x1
-#define OMAP54XX_CLKACTIVITY_USB_OTG_SS_REF_CLK_MASK			(1 << 31)
-
-/* Used by CM_L3INIT_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_UTMI_P3_GFCLK_SHIFT			30
-#define OMAP54XX_CLKACTIVITY_UTMI_P3_GFCLK_WIDTH			0x1
-#define OMAP54XX_CLKACTIVITY_UTMI_P3_GFCLK_MASK				(1 << 30)
-
-/* Used by CM_L3INIT_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_UTMI_ROOT_GFCLK_SHIFT			25
-#define OMAP54XX_CLKACTIVITY_UTMI_ROOT_GFCLK_WIDTH			0x1
-#define OMAP54XX_CLKACTIVITY_UTMI_ROOT_GFCLK_MASK			(1 << 25)
-
-/* Used by CM_WKUPAON_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_WKUPAON_32K_GFCLK_SHIFT			11
-#define OMAP54XX_CLKACTIVITY_WKUPAON_32K_GFCLK_WIDTH			0x1
-#define OMAP54XX_CLKACTIVITY_WKUPAON_32K_GFCLK_MASK			(1 << 11)
-
-/* Used by CM_WKUPAON_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_WKUPAON_GICLK_SHIFT			12
-#define OMAP54XX_CLKACTIVITY_WKUPAON_GICLK_WIDTH			0x1
-#define OMAP54XX_CLKACTIVITY_WKUPAON_GICLK_MASK				(1 << 12)
-
-/* Used by CM_WKUPAON_CLKSTCTRL */
-#define OMAP54XX_CLKACTIVITY_WKUPAON_IO_SRCOMP_GFCLK_SHIFT		13
-#define OMAP54XX_CLKACTIVITY_WKUPAON_IO_SRCOMP_GFCLK_WIDTH		0x1
-#define OMAP54XX_CLKACTIVITY_WKUPAON_IO_SRCOMP_GFCLK_MASK		(1 << 13)
-
-/* Used by CM_COREAON_IO_SRCOMP_CLKCTRL, CM_WKUPAON_IO_SRCOMP_CLKCTRL */
-#define OMAP54XX_CLKEN_SRCOMP_FCLK_SHIFT				8
-#define OMAP54XX_CLKEN_SRCOMP_FCLK_WIDTH				0x1
-#define OMAP54XX_CLKEN_SRCOMP_FCLK_MASK					(1 << 8)
-
-/*
- * Used by CM_ABE_TIMER5_CLKCTRL, CM_ABE_TIMER6_CLKCTRL, CM_ABE_TIMER7_CLKCTRL,
- * CM_ABE_TIMER8_CLKCTRL, CM_L3INIT_HSI_CLKCTRL, CM_L4PER_TIMER10_CLKCTRL,
- * CM_L4PER_TIMER11_CLKCTRL, CM_L4PER_TIMER2_CLKCTRL, CM_L4PER_TIMER3_CLKCTRL,
- * CM_L4PER_TIMER4_CLKCTRL, CM_L4PER_TIMER9_CLKCTRL, CM_WKUPAON_TIMER1_CLKCTRL
- */
 #define OMAP54XX_CLKSEL_SHIFT						24
 #define OMAP54XX_CLKSEL_WIDTH						0x1
-#define OMAP54XX_CLKSEL_MASK						(1 << 24)
-
-/*
- * Renamed from CLKSEL Used by CM_CLKSEL_ABE_DSS_SYS, CM_CLKSEL_ABE_PLL_REF,
- * CM_CLKSEL_USB_60MHZ, CM_CLKSEL_WKUPAON
- */
 #define OMAP54XX_CLKSEL_0_0_SHIFT					0
 #define OMAP54XX_CLKSEL_0_0_WIDTH					0x1
-#define OMAP54XX_CLKSEL_0_0_MASK					(1 << 0)
-
-/* Renamed from CLKSEL Used by CM_BYPCLK_DPLL_IVA, CM_BYPCLK_DPLL_MPU */
-#define OMAP54XX_CLKSEL_0_1_SHIFT					0
-#define OMAP54XX_CLKSEL_0_1_WIDTH					0x2
-#define OMAP54XX_CLKSEL_0_1_MASK					(0x3 << 0)
-
-/* Renamed from CLKSEL Used by CM_L3INSTR_CTRL_MODULE_BANDGAP_CLKCTRL */
-#define OMAP54XX_CLKSEL_24_25_SHIFT					24
-#define OMAP54XX_CLKSEL_24_25_WIDTH					0x2
-#define OMAP54XX_CLKSEL_24_25_MASK					(0x3 << 24)
-
-/* Used by CM_MPU_MPU_CLKCTRL */
-#define OMAP54XX_CLKSEL_ABE_DIV_MODE_SHIFT				26
-#define OMAP54XX_CLKSEL_ABE_DIV_MODE_WIDTH				0x1
-#define OMAP54XX_CLKSEL_ABE_DIV_MODE_MASK				(1 << 26)
-
-/* Used by CM_ABE_AESS_CLKCTRL */
 #define OMAP54XX_CLKSEL_AESS_FCLK_SHIFT					24
 #define OMAP54XX_CLKSEL_AESS_FCLK_WIDTH					0x1
-#define OMAP54XX_CLKSEL_AESS_FCLK_MASK					(1 << 24)
-
-/* Used by CM_L3INIT_MMC1_CLKCTRL, CM_L3INIT_MMC2_CLKCTRL */
 #define OMAP54XX_CLKSEL_DIV_SHIFT					25
 #define OMAP54XX_CLKSEL_DIV_WIDTH					0x1
-#define OMAP54XX_CLKSEL_DIV_MASK					(1 << 25)
-
-/* Used by CM_MPU_MPU_CLKCTRL */
-#define OMAP54XX_CLKSEL_EMIF_DIV_MODE_SHIFT				24
-#define OMAP54XX_CLKSEL_EMIF_DIV_MODE_WIDTH				0x2
-#define OMAP54XX_CLKSEL_EMIF_DIV_MODE_MASK				(0x3 << 24)
-
-/* Used by CM_CAM_FDIF_CLKCTRL */
 #define OMAP54XX_CLKSEL_FCLK_SHIFT					24
 #define OMAP54XX_CLKSEL_FCLK_WIDTH					0x1
-#define OMAP54XX_CLKSEL_FCLK_MASK					(1 << 24)
-
-/* Used by CM_GPU_GPU_CLKCTRL */
 #define OMAP54XX_CLKSEL_GPU_CORE_GCLK_SHIFT				24
 #define OMAP54XX_CLKSEL_GPU_CORE_GCLK_WIDTH				0x1
-#define OMAP54XX_CLKSEL_GPU_CORE_GCLK_MASK				(1 << 24)
-
-/* Used by CM_GPU_GPU_CLKCTRL */
 #define OMAP54XX_CLKSEL_GPU_HYD_GCLK_SHIFT				25
 #define OMAP54XX_CLKSEL_GPU_HYD_GCLK_WIDTH				0x1
-#define OMAP54XX_CLKSEL_GPU_HYD_GCLK_MASK				(1 << 25)
-
-/* Used by CM_GPU_GPU_CLKCTRL */
-#define OMAP54XX_CLKSEL_GPU_SYS_CLK_SHIFT				26
-#define OMAP54XX_CLKSEL_GPU_SYS_CLK_WIDTH				0x1
-#define OMAP54XX_CLKSEL_GPU_SYS_CLK_MASK				(1 << 26)
-
-/*
- * Used by CM_ABE_DMIC_CLKCTRL, CM_ABE_MCASP_CLKCTRL, CM_ABE_MCBSP1_CLKCTRL,
- * CM_ABE_MCBSP2_CLKCTRL, CM_ABE_MCBSP3_CLKCTRL
- */
 #define OMAP54XX_CLKSEL_INTERNAL_SOURCE_SHIFT				26
 #define OMAP54XX_CLKSEL_INTERNAL_SOURCE_WIDTH				0x2
-#define OMAP54XX_CLKSEL_INTERNAL_SOURCE_MASK				(0x3 << 26)
-
-/* Used by CM_CLKSEL_CORE */
-#define OMAP54XX_CLKSEL_L3_SHIFT					4
-#define OMAP54XX_CLKSEL_L3_WIDTH					0x1
-#define OMAP54XX_CLKSEL_L3_MASK						(1 << 4)
-
-/* Renamed from CLKSEL_L3 Used by CM_SHADOW_FREQ_CONFIG2 */
-#define OMAP54XX_CLKSEL_L3_1_1_SHIFT					1
-#define OMAP54XX_CLKSEL_L3_1_1_WIDTH					0x1
-#define OMAP54XX_CLKSEL_L3_1_1_MASK					(1 << 1)
-
-/* Used by CM_CLKSEL_CORE */
-#define OMAP54XX_CLKSEL_L4_SHIFT					8
-#define OMAP54XX_CLKSEL_L4_WIDTH					0x1
-#define OMAP54XX_CLKSEL_L4_MASK						(1 << 8)
-
-/* Used by CM_EMIF_EMIF1_CLKCTRL */
-#define OMAP54XX_CLKSEL_LL_SHIFT					24
-#define OMAP54XX_CLKSEL_LL_WIDTH					0x1
-#define OMAP54XX_CLKSEL_LL_MASK						(1 << 24)
-
-/* Used by CM_CLKSEL_ABE */
 #define OMAP54XX_CLKSEL_OPP_SHIFT					0
 #define OMAP54XX_CLKSEL_OPP_WIDTH					0x2
-#define OMAP54XX_CLKSEL_OPP_MASK					(0x3 << 0)
-
-/* Renamed from CLKSEL_OPP Used by CM_L3INIT_UNIPRO2_CLKCTRL */
-#define OMAP54XX_CLKSEL_OPP_24_24_SHIFT					24
-#define OMAP54XX_CLKSEL_OPP_24_24_WIDTH					0x1
-#define OMAP54XX_CLKSEL_OPP_24_24_MASK					(1 << 24)
-
-/*
- * Used by CM_ABE_DMIC_CLKCTRL, CM_ABE_MCASP_CLKCTRL, CM_ABE_MCBSP1_CLKCTRL,
- * CM_ABE_MCBSP2_CLKCTRL, CM_ABE_MCBSP3_CLKCTRL
- */
 #define OMAP54XX_CLKSEL_SOURCE_SHIFT					24
 #define OMAP54XX_CLKSEL_SOURCE_WIDTH					0x2
-#define OMAP54XX_CLKSEL_SOURCE_MASK					(0x3 << 24)
-
-/*
- * Renamed from CLKSEL_SOURCE Used by CM_L3INIT_MMC1_CLKCTRL,
- * CM_L3INIT_MMC2_CLKCTRL
- */
 #define OMAP54XX_CLKSEL_SOURCE_L3INIT_MMC1_SHIFT			24
 #define OMAP54XX_CLKSEL_SOURCE_L3INIT_MMC1_WIDTH			0x1
-#define OMAP54XX_CLKSEL_SOURCE_L3INIT_MMC1_MASK				(1 << 24)
-
-/* Used by CM_L3INIT_USB_HOST_HS_CLKCTRL */
 #define OMAP54XX_CLKSEL_UTMI_P1_SHIFT					24
 #define OMAP54XX_CLKSEL_UTMI_P1_WIDTH					0x1
-#define OMAP54XX_CLKSEL_UTMI_P1_MASK					(1 << 24)
-
-/* Used by CM_L3INIT_USB_HOST_HS_CLKCTRL */
 #define OMAP54XX_CLKSEL_UTMI_P2_SHIFT					25
 #define OMAP54XX_CLKSEL_UTMI_P2_WIDTH					0x1
-#define OMAP54XX_CLKSEL_UTMI_P2_MASK					(1 << 25)
-
-/*
- * Used by CM_DIV_H11_DPLL_CORE, CM_DIV_H11_DPLL_IVA, CM_DIV_H11_DPLL_PER,
- * CM_DIV_H12_DPLL_CORE, CM_DIV_H12_DPLL_IVA, CM_DIV_H12_DPLL_PER,
- * CM_DIV_H13_DPLL_CORE, CM_DIV_H13_DPLL_PER, CM_DIV_H14_DPLL_CORE,
- * CM_DIV_H14_DPLL_PER, CM_DIV_H21_DPLL_CORE, CM_DIV_H22_DPLL_CORE,
- * CM_DIV_H23_DPLL_CORE, CM_DIV_H24_DPLL_CORE, CM_DIV_M2_DPLL_ABE,
- * CM_DIV_M2_DPLL_CORE, CM_DIV_M2_DPLL_MPU, CM_DIV_M2_DPLL_PER,
- * CM_DIV_M2_DPLL_UNIPRO1, CM_DIV_M2_DPLL_UNIPRO2, CM_DIV_M2_DPLL_USB,
- * CM_DIV_M3_DPLL_ABE, CM_DIV_M3_DPLL_CORE, CM_DIV_M3_DPLL_PER
- */
-#define OMAP54XX_CLKST_SHIFT						9
-#define OMAP54XX_CLKST_WIDTH						0x1
-#define OMAP54XX_CLKST_MASK						(1 << 9)
-
-/*
- * Used by CM_ABE_CLKSTCTRL, CM_C2C_CLKSTCTRL, CM_CAM_CLKSTCTRL,
- * CM_COREAON_CLKSTCTRL, CM_CUSTEFUSE_CLKSTCTRL, CM_DMA_CLKSTCTRL,
- * CM_DSP_CLKSTCTRL, CM_DSS_CLKSTCTRL, CM_EMIF_CLKSTCTRL, CM_EMU_CLKSTCTRL,
- * CM_GPU_CLKSTCTRL, CM_IPU_CLKSTCTRL, CM_IVA_CLKSTCTRL, CM_L3INIT_CLKSTCTRL,
- * CM_L3INSTR_CLKSTCTRL, CM_L3MAIN1_CLKSTCTRL, CM_L3MAIN2_CLKSTCTRL,
- * CM_L4CFG_CLKSTCTRL, CM_L4PER_CLKSTCTRL, CM_L4SEC_CLKSTCTRL,
- * CM_MIPIEXT_CLKSTCTRL, CM_MPU_CLKSTCTRL, CM_WKUPAON_CLKSTCTRL
- */
-#define OMAP54XX_CLKTRCTRL_SHIFT					0
-#define OMAP54XX_CLKTRCTRL_WIDTH					0x2
-#define OMAP54XX_CLKTRCTRL_MASK						(0x3 << 0)
-
-/* Used by CM_DIV_M2_DPLL_ABE, CM_DIV_M2_DPLL_PER */
-#define OMAP54XX_CLKX2ST_SHIFT						11
-#define OMAP54XX_CLKX2ST_WIDTH						0x1
-#define OMAP54XX_CLKX2ST_MASK						(1 << 11)
-
-/* Used by CM_L4CFG_DYNAMICDEP */
-#define OMAP54XX_COREAON_DYNDEP_SHIFT					16
-#define OMAP54XX_COREAON_DYNDEP_WIDTH					0x1
-#define OMAP54XX_COREAON_DYNDEP_MASK					(1 << 16)
-
-/* Used by CM_DSP_STATICDEP, CM_IPU_STATICDEP, CM_MPU_STATICDEP */
-#define OMAP54XX_COREAON_STATDEP_SHIFT					16
-#define OMAP54XX_COREAON_STATDEP_WIDTH					0x1
-#define OMAP54XX_COREAON_STATDEP_MASK					(1 << 16)
-
-/* Used by CM_L4CFG_DYNAMICDEP */
-#define OMAP54XX_CUSTEFUSE_DYNDEP_SHIFT					17
-#define OMAP54XX_CUSTEFUSE_DYNDEP_WIDTH					0x1
-#define OMAP54XX_CUSTEFUSE_DYNDEP_MASK					(1 << 17)
-
-/* Used by CM_DSP_STATICDEP, CM_IPU_STATICDEP, CM_MPU_STATICDEP */
-#define OMAP54XX_CUSTEFUSE_STATDEP_SHIFT				17
-#define OMAP54XX_CUSTEFUSE_STATDEP_WIDTH				0x1
-#define OMAP54XX_CUSTEFUSE_STATDEP_MASK					(1 << 17)
-
-/* Used by REVISION_CM_CORE, REVISION_CM_CORE_AON */
-#define OMAP54XX_CUSTOM_SHIFT						6
-#define OMAP54XX_CUSTOM_WIDTH						0x2
-#define OMAP54XX_CUSTOM_MASK						(0x3 << 6)
-
-/*
- * Used by CM_CLKSEL_DPLL_ABE, CM_CLKSEL_DPLL_CORE, CM_CLKSEL_DPLL_IVA,
- * CM_CLKSEL_DPLL_MPU, CM_CLKSEL_DPLL_PER, CM_CLKSEL_DPLL_UNIPRO1,
- * CM_CLKSEL_DPLL_UNIPRO2, CM_CLKSEL_DPLL_USB
- */
-#define OMAP54XX_DCC_EN_SHIFT						22
-#define OMAP54XX_DCC_EN_WIDTH						0x1
-#define OMAP54XX_DCC_EN_MASK						(1 << 22)
-
-/*
- * Used by CM_CORE_AON_DEBUG_CM_CORE_AON_FD_TRANS,
- * CM_CORE_AON_DEBUG_DSS_FD_TRANS, CM_CORE_AON_DEBUG_EMIF_FD_TRANS,
- * CM_CORE_AON_DEBUG_L4SEC_FD_TRANS
- */
-#define OMAP54XX_CM_DEBUG_OUT_SHIFT					0
-#define OMAP54XX_CM_DEBUG_OUT_WIDTH					0xd
-#define OMAP54XX_CM_DEBUG_OUT_MASK					(0x1fff << 0)
-
-/*
- * Renamed from DEBUG_OUT Used by CM_CORE_AON_DEBUG_ABE_FD_TRANS,
- * CM_CORE_AON_DEBUG_L3INIT_FD_TRANS, CM_CORE_AON_DEBUG_L4PER_FD_TRANS
- */
-#define OMAP54XX_DEBUG_OUT_0_31_SHIFT					0
-#define OMAP54XX_DEBUG_OUT_0_31_WIDTH					0x20
-#define OMAP54XX_DEBUG_OUT_0_31_MASK					(0xffffffff << 0)
-
-/*
- * Renamed from DEBUG_OUT Used by CM_CORE_AON_DEBUG_C2C_FD_TRANS,
- * CM_CORE_AON_DEBUG_COREAON_FD_TRANS, CM_CORE_AON_DEBUG_L4CFG_FD_TRANS
- */
-#define OMAP54XX_DEBUG_OUT_0_8_SHIFT					0
-#define OMAP54XX_DEBUG_OUT_0_8_WIDTH					0x9
-#define OMAP54XX_DEBUG_OUT_0_8_MASK					(0x1ff << 0)
-
-/*
- * Renamed from DEBUG_OUT Used by CM_CORE_AON_DEBUG_CUSTEFUSE_FD_TRANS,
- * CM_CORE_AON_DEBUG_DMA_FD_TRANS, CM_CORE_AON_DEBUG_L3MAIN1_FD_TRANS
- */
-#define OMAP54XX_DEBUG_OUT_0_4_SHIFT					0
-#define OMAP54XX_DEBUG_OUT_0_4_WIDTH					0x5
-#define OMAP54XX_DEBUG_OUT_0_4_MASK					(0x1f << 0)
-
-/*
- * Renamed from DEBUG_OUT Used by CM_CORE_AON_DEBUG_DSP_FD_TRANS,
- * CM_CORE_AON_DEBUG_IPU_FD_TRANS, CM_CORE_AON_DEBUG_MPU_FD_TRANS
- */
-#define OMAP54XX_DEBUG_OUT_0_5_SHIFT					0
-#define OMAP54XX_DEBUG_OUT_0_5_WIDTH					0x6
-#define OMAP54XX_DEBUG_OUT_0_5_MASK					(0x3f << 0)
-
-/*
- * Renamed from DEBUG_OUT Used by CM_CORE_AON_DEBUG_CAM_FD_TRANS,
- * CM_CORE_AON_DEBUG_MIPIEXT_FD_TRANS
- */
-#define OMAP54XX_DEBUG_OUT_0_10_SHIFT					0
-#define OMAP54XX_DEBUG_OUT_0_10_WIDTH					0xb
-#define OMAP54XX_DEBUG_OUT_0_10_MASK					(0x7ff << 0)
-
-/*
- * Renamed from DEBUG_OUT Used by CM_CORE_AON_DEBUG_IVA_FD_TRANS,
- * CM_CORE_AON_DEBUG_L3MAIN2_FD_TRANS
- */
-#define OMAP54XX_DEBUG_OUT_0_6_SHIFT					0
-#define OMAP54XX_DEBUG_OUT_0_6_WIDTH					0x7
-#define OMAP54XX_DEBUG_OUT_0_6_MASK					(0x7f << 0)
-
-/* Renamed from DEBUG_OUT Used by CM_CORE_AON_DEBUG_ABE_FD_TRANS2 */
-#define OMAP54XX_DEBUG_OUT_0_19_SHIFT					0
-#define OMAP54XX_DEBUG_OUT_0_19_WIDTH					0x14
-#define OMAP54XX_DEBUG_OUT_0_19_MASK					(0xfffff << 0)
-
-/* Renamed from DEBUG_OUT Used by CM_CORE_AON_DEBUG_GPU_FD_TRANS */
-#define OMAP54XX_DEBUG_OUT_0_9_SHIFT					0
-#define OMAP54XX_DEBUG_OUT_0_9_WIDTH					0xa
-#define OMAP54XX_DEBUG_OUT_0_9_MASK					(0x3ff << 0)
-
-/* Renamed from DEBUG_OUT Used by CM_CORE_AON_DEBUG_L3INIT_FD_TRANS2 */
-#define OMAP54XX_DEBUG_OUT_0_26_SHIFT					0
-#define OMAP54XX_DEBUG_OUT_0_26_WIDTH					0x1b
-#define OMAP54XX_DEBUG_OUT_0_26_MASK					(0x7ffffff << 0)
-
-/* Renamed from DEBUG_OUT Used by CM_CORE_AON_DEBUG_L3INSTR_FD_TRANS */
-#define OMAP54XX_DEBUG_OUT_0_13_SHIFT					0
-#define OMAP54XX_DEBUG_OUT_0_13_WIDTH					0xe
-#define OMAP54XX_DEBUG_OUT_0_13_MASK					(0x3fff << 0)
-
-/* Renamed from DEBUG_OUT Used by CM_CORE_AON_DEBUG_L4PER_FD_TRANS2 */
-#define OMAP54XX_DEBUG_OUT_0_21_SHIFT					0
-#define OMAP54XX_DEBUG_OUT_0_21_WIDTH					0x16
-#define OMAP54XX_DEBUG_OUT_0_21_MASK					(0x3fffff << 0)
-
-/*
- * Used by CM_SSC_DELTAMSTEP_DPLL_ABE, CM_SSC_DELTAMSTEP_DPLL_CORE,
- * CM_SSC_DELTAMSTEP_DPLL_IVA, CM_SSC_DELTAMSTEP_DPLL_MPU,
- * CM_SSC_DELTAMSTEP_DPLL_PER
- */
-#define OMAP54XX_DELTAMSTEP_SHIFT					0
-#define OMAP54XX_DELTAMSTEP_WIDTH					0x14
-#define OMAP54XX_DELTAMSTEP_MASK					(0xfffff << 0)
-
-/*
- * Renamed from DELTAMSTEP Used by CM_SSC_DELTAMSTEP_DPLL_UNIPRO1,
- * CM_SSC_DELTAMSTEP_DPLL_UNIPRO2, CM_SSC_DELTAMSTEP_DPLL_USB
- */
-#define OMAP54XX_DELTAMSTEP_0_20_SHIFT					0
-#define OMAP54XX_DELTAMSTEP_0_20_WIDTH					0x15
-#define OMAP54XX_DELTAMSTEP_0_20_MASK					(0x1fffff << 0)
-
-/*
- * Used by CM_DIV_H11_DPLL_CORE, CM_DIV_H11_DPLL_IVA, CM_DIV_H11_DPLL_PER,
- * CM_DIV_H12_DPLL_CORE, CM_DIV_H12_DPLL_IVA, CM_DIV_H12_DPLL_PER,
- * CM_DIV_H13_DPLL_CORE, CM_DIV_H13_DPLL_PER, CM_DIV_H14_DPLL_CORE,
- * CM_DIV_H14_DPLL_PER, CM_DIV_H21_DPLL_CORE, CM_DIV_H22_DPLL_CORE,
- * CM_DIV_H23_DPLL_CORE, CM_DIV_H24_DPLL_CORE
- */
-#define OMAP54XX_DIVHS_SHIFT						0
-#define OMAP54XX_DIVHS_WIDTH						0x6
 #define OMAP54XX_DIVHS_MASK						(0x3f << 0)
-
-/*
- * Renamed from DIVHS Used by CM_DIV_M2_DPLL_ABE, CM_DIV_M2_DPLL_CORE,
- * CM_DIV_M2_DPLL_MPU, CM_DIV_M2_DPLL_PER, CM_DIV_M3_DPLL_ABE,
- * CM_DIV_M3_DPLL_CORE, CM_DIV_M3_DPLL_PER
- */
-#define OMAP54XX_DIVHS_0_4_SHIFT					0
-#define OMAP54XX_DIVHS_0_4_WIDTH					0x5
 #define OMAP54XX_DIVHS_0_4_MASK						(0x1f << 0)
-
-/*
- * Renamed from DIVHS Used by CM_DIV_M2_DPLL_UNIPRO1, CM_DIV_M2_DPLL_UNIPRO2,
- * CM_DIV_M2_DPLL_USB
- */
-#define OMAP54XX_DIVHS_0_6_SHIFT					0
-#define OMAP54XX_DIVHS_0_6_WIDTH					0x7
 #define OMAP54XX_DIVHS_0_6_MASK						(0x7f << 0)
-
-/* Used by CM_DLL_CTRL */
-#define OMAP54XX_DLL_OVERRIDE_SHIFT					0
-#define OMAP54XX_DLL_OVERRIDE_WIDTH					0x1
-#define OMAP54XX_DLL_OVERRIDE_MASK					(1 << 0)
-
-/* Renamed from DLL_OVERRIDE Used by CM_SHADOW_FREQ_CONFIG1 */
-#define OMAP54XX_DLL_OVERRIDE_2_2_SHIFT					2
-#define OMAP54XX_DLL_OVERRIDE_2_2_WIDTH					0x1
-#define OMAP54XX_DLL_OVERRIDE_2_2_MASK					(1 << 2)
-
-/* Used by CM_SHADOW_FREQ_CONFIG1 */
-#define OMAP54XX_DLL_RESET_SHIFT					3
-#define OMAP54XX_DLL_RESET_WIDTH					0x1
-#define OMAP54XX_DLL_RESET_MASK						(1 << 3)
-
-/*
- * Used by CM_CLKSEL_DPLL_ABE, CM_CLKSEL_DPLL_CORE, CM_CLKSEL_DPLL_IVA,
- * CM_CLKSEL_DPLL_MPU, CM_CLKSEL_DPLL_PER, CM_CLKSEL_DPLL_UNIPRO1,
- * CM_CLKSEL_DPLL_UNIPRO2, CM_CLKSEL_DPLL_USB
- */
-#define OMAP54XX_DPLL_BYP_CLKSEL_SHIFT					23
-#define OMAP54XX_DPLL_BYP_CLKSEL_WIDTH					0x1
-#define OMAP54XX_DPLL_BYP_CLKSEL_MASK					(1 << 23)
-
-/* Used by CM_CLKSEL_DPLL_CORE */
-#define OMAP54XX_DPLL_CLKOUTHIF_CLKSEL_SHIFT				20
-#define OMAP54XX_DPLL_CLKOUTHIF_CLKSEL_WIDTH				0x1
-#define OMAP54XX_DPLL_CLKOUTHIF_CLKSEL_MASK				(1 << 20)
-
-/* Used by CM_SHADOW_FREQ_CONFIG1 */
-#define OMAP54XX_DPLL_CORE_DPLL_EN_SHIFT				8
-#define OMAP54XX_DPLL_CORE_DPLL_EN_WIDTH				0x3
-#define OMAP54XX_DPLL_CORE_DPLL_EN_MASK					(0x7 << 8)
-
-/* Used by CM_SHADOW_FREQ_CONFIG2 */
-#define OMAP54XX_DPLL_CORE_H12_DIV_SHIFT				2
-#define OMAP54XX_DPLL_CORE_H12_DIV_WIDTH				0x6
-#define OMAP54XX_DPLL_CORE_H12_DIV_MASK					(0x3f << 2)
-
-/* Used by CM_SHADOW_FREQ_CONFIG1 */
-#define OMAP54XX_DPLL_CORE_M2_DIV_SHIFT					11
-#define OMAP54XX_DPLL_CORE_M2_DIV_WIDTH					0x5
-#define OMAP54XX_DPLL_CORE_M2_DIV_MASK					(0x1f << 11)
-
-/*
- * Used by CM_CLKSEL_DPLL_ABE, CM_CLKSEL_DPLL_CORE, CM_CLKSEL_DPLL_IVA,
- * CM_CLKSEL_DPLL_MPU, CM_CLKSEL_DPLL_PER
- */
-#define OMAP54XX_DPLL_DIV_SHIFT						0
-#define OMAP54XX_DPLL_DIV_WIDTH						0x7
 #define OMAP54XX_DPLL_DIV_MASK						(0x7f << 0)
-
-/*
- * Renamed from DPLL_DIV Used by CM_CLKSEL_DPLL_UNIPRO1,
- * CM_CLKSEL_DPLL_UNIPRO2, CM_CLKSEL_DPLL_USB
- */
-#define OMAP54XX_DPLL_DIV_0_7_SHIFT					0
-#define OMAP54XX_DPLL_DIV_0_7_WIDTH					0x8
-#define OMAP54XX_DPLL_DIV_0_7_MASK					(0xff << 0)
-
-/*
- * Used by CM_CLKMODE_DPLL_ABE, CM_CLKMODE_DPLL_CORE, CM_CLKMODE_DPLL_IVA,
- * CM_CLKMODE_DPLL_MPU, CM_CLKMODE_DPLL_PER
- */
-#define OMAP54XX_DPLL_DRIFTGUARD_EN_SHIFT				8
-#define OMAP54XX_DPLL_DRIFTGUARD_EN_WIDTH				0x1
-#define OMAP54XX_DPLL_DRIFTGUARD_EN_MASK				(1 << 8)
-
-/*
- * Used by CM_CLKMODE_DPLL_ABE, CM_CLKMODE_DPLL_CORE, CM_CLKMODE_DPLL_IVA,
- * CM_CLKMODE_DPLL_MPU, CM_CLKMODE_DPLL_PER, CM_CLKMODE_DPLL_UNIPRO1,
- * CM_CLKMODE_DPLL_UNIPRO2, CM_CLKMODE_DPLL_USB
- */
-#define OMAP54XX_DPLL_EN_SHIFT						0
-#define OMAP54XX_DPLL_EN_WIDTH						0x3
 #define OMAP54XX_DPLL_EN_MASK						(0x7 << 0)
-
-/*
- * Used by CM_CLKMODE_DPLL_ABE, CM_CLKMODE_DPLL_CORE, CM_CLKMODE_DPLL_IVA,
- * CM_CLKMODE_DPLL_MPU, CM_CLKMODE_DPLL_PER
- */
-#define OMAP54XX_DPLL_LPMODE_EN_SHIFT					10
-#define OMAP54XX_DPLL_LPMODE_EN_WIDTH					0x1
 #define OMAP54XX_DPLL_LPMODE_EN_MASK					(1 << 10)
-
-/*
- * Used by CM_CLKSEL_DPLL_ABE, CM_CLKSEL_DPLL_CORE, CM_CLKSEL_DPLL_IVA,
- * CM_CLKSEL_DPLL_MPU, CM_CLKSEL_DPLL_PER
- */
-#define OMAP54XX_DPLL_MULT_SHIFT					8
-#define OMAP54XX_DPLL_MULT_WIDTH					0xb
 #define OMAP54XX_DPLL_MULT_MASK						(0x7ff << 8)
-
-/*
- * Renamed from DPLL_MULT Used by CM_CLKSEL_DPLL_UNIPRO1,
- * CM_CLKSEL_DPLL_UNIPRO2, CM_CLKSEL_DPLL_USB
- */
-#define OMAP54XX_DPLL_MULT_UNIPRO1_SHIFT				8
-#define OMAP54XX_DPLL_MULT_UNIPRO1_WIDTH				0xc
-#define OMAP54XX_DPLL_MULT_UNIPRO1_MASK					(0xfff << 8)
-
-/*
- * Used by CM_CLKMODE_DPLL_ABE, CM_CLKMODE_DPLL_CORE, CM_CLKMODE_DPLL_IVA,
- * CM_CLKMODE_DPLL_MPU, CM_CLKMODE_DPLL_PER
- */
-#define OMAP54XX_DPLL_REGM4XEN_SHIFT					11
-#define OMAP54XX_DPLL_REGM4XEN_WIDTH					0x1
 #define OMAP54XX_DPLL_REGM4XEN_MASK					(1 << 11)
-
-/* Used by CM_CLKSEL_DPLL_UNIPRO1, CM_CLKSEL_DPLL_UNIPRO2, CM_CLKSEL_DPLL_USB */
-#define OMAP54XX_DPLL_SD_DIV_SHIFT					24
-#define OMAP54XX_DPLL_SD_DIV_WIDTH					0x8
 #define OMAP54XX_DPLL_SD_DIV_MASK					(0xff << 24)
-
-/* Used by CM_CLKSEL_DPLL_UNIPRO1, CM_CLKSEL_DPLL_UNIPRO2, CM_CLKSEL_DPLL_USB */
-#define OMAP54XX_DPLL_SELFREQDCO_SHIFT					21
-#define OMAP54XX_DPLL_SELFREQDCO_WIDTH					0x1
-#define OMAP54XX_DPLL_SELFREQDCO_MASK					(1 << 21)
-
-/*
- * Used by CM_CLKMODE_DPLL_ABE, CM_CLKMODE_DPLL_CORE, CM_CLKMODE_DPLL_IVA,
- * CM_CLKMODE_DPLL_MPU, CM_CLKMODE_DPLL_PER, CM_CLKMODE_DPLL_UNIPRO1,
- * CM_CLKMODE_DPLL_UNIPRO2, CM_CLKMODE_DPLL_USB
- */
-#define OMAP54XX_DPLL_SSC_ACK_SHIFT					13
-#define OMAP54XX_DPLL_SSC_ACK_WIDTH					0x1
-#define OMAP54XX_DPLL_SSC_ACK_MASK					(1 << 13)
-
-/*
- * Used by CM_CLKMODE_DPLL_ABE, CM_CLKMODE_DPLL_CORE, CM_CLKMODE_DPLL_IVA,
- * CM_CLKMODE_DPLL_MPU, CM_CLKMODE_DPLL_PER, CM_CLKMODE_DPLL_UNIPRO1,
- * CM_CLKMODE_DPLL_UNIPRO2, CM_CLKMODE_DPLL_USB
- */
-#define OMAP54XX_DPLL_SSC_DOWNSPREAD_SHIFT				14
-#define OMAP54XX_DPLL_SSC_DOWNSPREAD_WIDTH				0x1
-#define OMAP54XX_DPLL_SSC_DOWNSPREAD_MASK				(1 << 14)
-
-/*
- * Used by CM_CLKMODE_DPLL_ABE, CM_CLKMODE_DPLL_CORE, CM_CLKMODE_DPLL_IVA,
- * CM_CLKMODE_DPLL_MPU, CM_CLKMODE_DPLL_PER, CM_CLKMODE_DPLL_UNIPRO1,
- * CM_CLKMODE_DPLL_UNIPRO2, CM_CLKMODE_DPLL_USB
- */
-#define OMAP54XX_DPLL_SSC_EN_SHIFT					12
-#define OMAP54XX_DPLL_SSC_EN_WIDTH					0x1
-#define OMAP54XX_DPLL_SSC_EN_MASK					(1 << 12)
-
-/* Used by CM_L4CFG_DYNAMICDEP */
-#define OMAP54XX_DSP_DYNDEP_SHIFT					1
-#define OMAP54XX_DSP_DYNDEP_WIDTH					0x1
-#define OMAP54XX_DSP_DYNDEP_MASK					(1 << 1)
-
-/* Used by CM_IPU_STATICDEP, CM_MPU_STATICDEP */
 #define OMAP54XX_DSP_STATDEP_SHIFT					1
-#define OMAP54XX_DSP_STATDEP_WIDTH					0x1
-#define OMAP54XX_DSP_STATDEP_MASK					(1 << 1)
-
-/* Used by CM_L3MAIN2_DYNAMICDEP, CM_L4PER_DYNAMICDEP */
-#define OMAP54XX_DSS_DYNDEP_SHIFT					8
-#define OMAP54XX_DSS_DYNDEP_WIDTH					0x1
-#define OMAP54XX_DSS_DYNDEP_MASK					(1 << 8)
-
-/* Used by CM_DMA_STATICDEP, CM_IPU_STATICDEP, CM_MPU_STATICDEP */
 #define OMAP54XX_DSS_STATDEP_SHIFT					8
-#define OMAP54XX_DSS_STATDEP_WIDTH					0x1
-#define OMAP54XX_DSS_STATDEP_MASK					(1 << 8)
-
-/*
- * Used by CM_C2C_DYNAMICDEP, CM_L3MAIN1_DYNAMICDEP, CM_L4CFG_DYNAMICDEP,
- * CM_MIPIEXT_DYNAMICDEP, CM_MPU_DYNAMICDEP
- */
-#define OMAP54XX_EMIF_DYNDEP_SHIFT					4
-#define OMAP54XX_EMIF_DYNDEP_WIDTH					0x1
-#define OMAP54XX_EMIF_DYNDEP_MASK					(1 << 4)
-
-/*
- * Used by CM_C2C_STATICDEP, CM_CAM_STATICDEP, CM_DMA_STATICDEP,
- * CM_DSP_STATICDEP, CM_DSS_STATICDEP, CM_GPU_STATICDEP, CM_IPU_STATICDEP,
- * CM_IVA_STATICDEP, CM_L3INIT_STATICDEP, CM_L4SEC_STATICDEP,
- * CM_MIPIEXT_STATICDEP, CM_MPU_STATICDEP
- */
 #define OMAP54XX_EMIF_STATDEP_SHIFT					4
-#define OMAP54XX_EMIF_STATDEP_WIDTH					0x1
-#define OMAP54XX_EMIF_STATDEP_MASK					(1 << 4)
-
-/* Used by CM_SHADOW_FREQ_CONFIG1 */
-#define OMAP54XX_FREQ_UPDATE_SHIFT					0
-#define OMAP54XX_FREQ_UPDATE_WIDTH					0x1
-#define OMAP54XX_FREQ_UPDATE_MASK					(1 << 0)
-
-/* Used by REVISION_CM_CORE, REVISION_CM_CORE_AON */
-#define OMAP54XX_FUNC_SHIFT						16
-#define OMAP54XX_FUNC_WIDTH						0xc
-#define OMAP54XX_FUNC_MASK						(0xfff << 16)
-
-/* Used by CM_SHADOW_FREQ_CONFIG2 */
-#define OMAP54XX_GPMC_FREQ_UPDATE_SHIFT					0
-#define OMAP54XX_GPMC_FREQ_UPDATE_WIDTH					0x1
-#define OMAP54XX_GPMC_FREQ_UPDATE_MASK					(1 << 0)
-
-/* Used by CM_L3MAIN2_DYNAMICDEP */
-#define OMAP54XX_GPU_DYNDEP_SHIFT					10
-#define OMAP54XX_GPU_DYNDEP_WIDTH					0x1
-#define OMAP54XX_GPU_DYNDEP_MASK					(1 << 10)
-
-/* Used by CM_IPU_STATICDEP, CM_MPU_STATICDEP */
 #define OMAP54XX_GPU_STATDEP_SHIFT					10
-#define OMAP54XX_GPU_STATDEP_WIDTH					0x1
-#define OMAP54XX_GPU_STATDEP_MASK					(1 << 10)
-
-/*
- * Used by CM_ABE_AESS_CLKCTRL, CM_ABE_DMIC_CLKCTRL, CM_ABE_L4_ABE_CLKCTRL,
- * CM_ABE_MCASP_CLKCTRL, CM_ABE_MCBSP1_CLKCTRL, CM_ABE_MCBSP2_CLKCTRL,
- * CM_ABE_MCBSP3_CLKCTRL, CM_ABE_MCPDM_CLKCTRL, CM_ABE_SLIMBUS1_CLKCTRL,
- * CM_ABE_TIMER5_CLKCTRL, CM_ABE_TIMER6_CLKCTRL, CM_ABE_TIMER7_CLKCTRL,
- * CM_ABE_TIMER8_CLKCTRL, CM_ABE_WD_TIMER3_CLKCTRL, CM_C2C_C2C_CLKCTRL,
- * CM_C2C_C2C_OCP_FW_CLKCTRL, CM_C2C_MODEM_ICR_CLKCTRL, CM_CAM_CAL_CLKCTRL,
- * CM_CAM_FDIF_CLKCTRL, CM_CAM_ISS_CLKCTRL, CM_CM_CORE_AON_PROFILING_CLKCTRL,
- * CM_CM_CORE_PROFILING_CLKCTRL, CM_COREAON_SMARTREFLEX_CORE_CLKCTRL,
- * CM_COREAON_SMARTREFLEX_MM_CLKCTRL, CM_COREAON_SMARTREFLEX_MPU_CLKCTRL,
- * CM_CUSTEFUSE_EFUSE_CTRL_CUST_CLKCTRL, CM_DMA_DMA_SYSTEM_CLKCTRL,
- * CM_DSP_DSP_CLKCTRL, CM_DSS_BB2D_CLKCTRL, CM_DSS_DSS_CLKCTRL,
- * CM_EMIF_DMM_CLKCTRL, CM_EMIF_EMIF1_CLKCTRL, CM_EMIF_EMIF2_CLKCTRL,
- * CM_EMIF_EMIF_OCP_FW_CLKCTRL, CM_EMU_DEBUGSS_CLKCTRL,
- * CM_EMU_MPU_EMU_DBG_CLKCTRL, CM_GPU_GPU_CLKCTRL, CM_IPU_IPU_CLKCTRL,
- * CM_IVA_IVA_CLKCTRL, CM_IVA_SL2_CLKCTRL, CM_L3INIT_HSI_CLKCTRL,
- * CM_L3INIT_IEEE1500_2_OCP_CLKCTRL, CM_L3INIT_MMC1_CLKCTRL,
- * CM_L3INIT_MMC2_CLKCTRL, CM_L3INIT_MPHY_UNIPRO2_CLKCTRL,
- * CM_L3INIT_OCP2SCP1_CLKCTRL, CM_L3INIT_OCP2SCP3_CLKCTRL,
- * CM_L3INIT_SATA_CLKCTRL, CM_L3INIT_UNIPRO2_CLKCTRL,
- * CM_L3INIT_USB_HOST_HS_CLKCTRL, CM_L3INIT_USB_OTG_SS_CLKCTRL,
- * CM_L3INIT_USB_TLL_HS_CLKCTRL, CM_L3INSTR_CTRL_MODULE_BANDGAP_CLKCTRL,
- * CM_L3INSTR_DLL_AGING_CLKCTRL, CM_L3INSTR_L3_INSTR_CLKCTRL,
- * CM_L3INSTR_L3_MAIN_3_CLKCTRL, CM_L3INSTR_OCP_WP_NOC_CLKCTRL,
- * CM_L3MAIN1_L3_MAIN_1_CLKCTRL, CM_L3MAIN2_GPMC_CLKCTRL,
- * CM_L3MAIN2_L3_MAIN_2_CLKCTRL, CM_L3MAIN2_OCMC_RAM_CLKCTRL,
- * CM_L4CFG_L4_CFG_CLKCTRL, CM_L4CFG_MAILBOX_CLKCTRL,
- * CM_L4CFG_OCP2SCP2_CLKCTRL, CM_L4CFG_SAR_ROM_CLKCTRL,
- * CM_L4CFG_SPINLOCK_CLKCTRL, CM_L4PER_ELM_CLKCTRL, CM_L4PER_GPIO2_CLKCTRL,
- * CM_L4PER_GPIO3_CLKCTRL, CM_L4PER_GPIO4_CLKCTRL, CM_L4PER_GPIO5_CLKCTRL,
- * CM_L4PER_GPIO6_CLKCTRL, CM_L4PER_GPIO7_CLKCTRL, CM_L4PER_GPIO8_CLKCTRL,
- * CM_L4PER_HDQ1W_CLKCTRL, CM_L4PER_I2C1_CLKCTRL, CM_L4PER_I2C2_CLKCTRL,
- * CM_L4PER_I2C3_CLKCTRL, CM_L4PER_I2C4_CLKCTRL, CM_L4PER_I2C5_CLKCTRL,
- * CM_L4PER_L4_PER_CLKCTRL, CM_L4PER_MCSPI1_CLKCTRL, CM_L4PER_MCSPI2_CLKCTRL,
- * CM_L4PER_MCSPI3_CLKCTRL, CM_L4PER_MCSPI4_CLKCTRL, CM_L4PER_MMC3_CLKCTRL,
- * CM_L4PER_MMC4_CLKCTRL, CM_L4PER_MMC5_CLKCTRL, CM_L4PER_TIMER10_CLKCTRL,
- * CM_L4PER_TIMER11_CLKCTRL, CM_L4PER_TIMER2_CLKCTRL, CM_L4PER_TIMER3_CLKCTRL,
- * CM_L4PER_TIMER4_CLKCTRL, CM_L4PER_TIMER9_CLKCTRL, CM_L4PER_UART1_CLKCTRL,
- * CM_L4PER_UART2_CLKCTRL, CM_L4PER_UART3_CLKCTRL, CM_L4PER_UART4_CLKCTRL,
- * CM_L4PER_UART5_CLKCTRL, CM_L4PER_UART6_CLKCTRL, CM_L4SEC_AES1_CLKCTRL,
- * CM_L4SEC_AES2_CLKCTRL, CM_L4SEC_DES3DES_CLKCTRL,
- * CM_L4SEC_DMA_CRYPTO_CLKCTRL, CM_L4SEC_FPKA_CLKCTRL, CM_L4SEC_RNG_CLKCTRL,
- * CM_L4SEC_SHA2MD5_CLKCTRL, CM_MIPIEXT_LLI_CLKCTRL,
- * CM_MIPIEXT_LLI_OCP_FW_CLKCTRL, CM_MIPIEXT_MPHY_CLKCTRL, CM_MPU_MPU_CLKCTRL,
- * CM_MPU_MPU_MPU_DBG_CLKCTRL, CM_WKUPAON_COUNTER_32K_CLKCTRL,
- * CM_WKUPAON_GPIO1_CLKCTRL, CM_WKUPAON_KBD_CLKCTRL,
- * CM_WKUPAON_L4_WKUP_CLKCTRL, CM_WKUPAON_SAR_RAM_CLKCTRL,
- * CM_WKUPAON_TIMER12_CLKCTRL, CM_WKUPAON_TIMER1_CLKCTRL,
- * CM_WKUPAON_WD_TIMER1_CLKCTRL, CM_WKUPAON_WD_TIMER2_CLKCTRL
- */
-#define OMAP54XX_IDLEST_SHIFT						16
-#define OMAP54XX_IDLEST_WIDTH						0x2
-#define OMAP54XX_IDLEST_MASK						(0x3 << 16)
-
-/* Used by CM_L3MAIN2_DYNAMICDEP */
-#define OMAP54XX_IPU_DYNDEP_SHIFT					0
-#define OMAP54XX_IPU_DYNDEP_WIDTH					0x1
-#define OMAP54XX_IPU_DYNDEP_MASK					(1 << 0)
-
-/* Used by CM_DMA_STATICDEP, CM_MPU_STATICDEP */
 #define OMAP54XX_IPU_STATDEP_SHIFT					0
-#define OMAP54XX_IPU_STATDEP_WIDTH					0x1
-#define OMAP54XX_IPU_STATDEP_MASK					(1 << 0)
-
-/* Used by CM_DSP_DYNAMICDEP, CM_L3MAIN2_DYNAMICDEP */
-#define OMAP54XX_IVA_DYNDEP_SHIFT					2
-#define OMAP54XX_IVA_DYNDEP_WIDTH					0x1
-#define OMAP54XX_IVA_DYNDEP_MASK					(1 << 2)
-
-/*
- * Used by CM_C2C_STATICDEP, CM_CAM_STATICDEP, CM_DMA_STATICDEP,
- * CM_DSP_STATICDEP, CM_DSS_STATICDEP, CM_GPU_STATICDEP, CM_IPU_STATICDEP,
- * CM_L3INIT_STATICDEP, CM_MIPIEXT_STATICDEP, CM_MPU_STATICDEP
- */
 #define OMAP54XX_IVA_STATDEP_SHIFT					2
-#define OMAP54XX_IVA_STATDEP_WIDTH					0x1
-#define OMAP54XX_IVA_STATDEP_MASK					(1 << 2)
-
-/* Used by CM_L4CFG_DYNAMICDEP, CM_L4PER_DYNAMICDEP */
-#define OMAP54XX_L3INIT_DYNDEP_SHIFT					7
-#define OMAP54XX_L3INIT_DYNDEP_WIDTH					0x1
-#define OMAP54XX_L3INIT_DYNDEP_MASK					(1 << 7)
-
-/*
- * Used by CM_C2C_STATICDEP, CM_DMA_STATICDEP, CM_DSP_STATICDEP,
- * CM_IPU_STATICDEP, CM_MIPIEXT_STATICDEP, CM_MPU_STATICDEP
- */
 #define OMAP54XX_L3INIT_STATDEP_SHIFT					7
-#define OMAP54XX_L3INIT_STATDEP_WIDTH					0x1
-#define OMAP54XX_L3INIT_STATDEP_MASK					(1 << 7)
-
-/*
- * Used by CM_DSP_DYNAMICDEP, CM_DSS_DYNAMICDEP, CM_L3INIT_DYNAMICDEP,
- * CM_L3MAIN2_DYNAMICDEP, CM_L4CFG_DYNAMICDEP, CM_MPU_DYNAMICDEP
- */
-#define OMAP54XX_L3MAIN1_DYNDEP_SHIFT					5
-#define OMAP54XX_L3MAIN1_DYNDEP_WIDTH					0x1
-#define OMAP54XX_L3MAIN1_DYNDEP_MASK					(1 << 5)
-
-/*
- * Used by CM_C2C_STATICDEP, CM_CAM_STATICDEP, CM_DMA_STATICDEP,
- * CM_DSP_STATICDEP, CM_DSS_STATICDEP, CM_GPU_STATICDEP, CM_IPU_STATICDEP,
- * CM_IVA_STATICDEP, CM_L3INIT_STATICDEP, CM_L4SEC_STATICDEP,
- * CM_MIPIEXT_STATICDEP, CM_MPU_STATICDEP
- */
 #define OMAP54XX_L3MAIN1_STATDEP_SHIFT					5
-#define OMAP54XX_L3MAIN1_STATDEP_WIDTH					0x1
-#define OMAP54XX_L3MAIN1_STATDEP_MASK					(1 << 5)
-
-/*
- * Used by CM_C2C_DYNAMICDEP, CM_CAM_DYNAMICDEP, CM_DMA_DYNAMICDEP,
- * CM_DSS_DYNAMICDEP, CM_EMU_DYNAMICDEP, CM_GPU_DYNAMICDEP, CM_IPU_DYNAMICDEP,
- * CM_IVA_DYNAMICDEP, CM_L3INIT_DYNAMICDEP, CM_L3MAIN1_DYNAMICDEP,
- * CM_L4CFG_DYNAMICDEP, CM_L4SEC_DYNAMICDEP, CM_MIPIEXT_DYNAMICDEP
- */
-#define OMAP54XX_L3MAIN2_DYNDEP_SHIFT					6
-#define OMAP54XX_L3MAIN2_DYNDEP_WIDTH					0x1
-#define OMAP54XX_L3MAIN2_DYNDEP_MASK					(1 << 6)
-
-/*
- * Used by CM_C2C_STATICDEP, CM_CAM_STATICDEP, CM_DMA_STATICDEP,
- * CM_DSP_STATICDEP, CM_DSS_STATICDEP, CM_GPU_STATICDEP, CM_IPU_STATICDEP,
- * CM_IVA_STATICDEP, CM_L3INIT_STATICDEP, CM_L4SEC_STATICDEP,
- * CM_MIPIEXT_STATICDEP, CM_MPU_STATICDEP
- */
 #define OMAP54XX_L3MAIN2_STATDEP_SHIFT					6
-#define OMAP54XX_L3MAIN2_STATDEP_WIDTH					0x1
-#define OMAP54XX_L3MAIN2_STATDEP_MASK					(1 << 6)
-
-/* Used by CM_L3MAIN1_DYNAMICDEP */
-#define OMAP54XX_L4CFG_DYNDEP_SHIFT					12
-#define OMAP54XX_L4CFG_DYNDEP_WIDTH					0x1
-#define OMAP54XX_L4CFG_DYNDEP_MASK					(1 << 12)
-
-/*
- * Used by CM_C2C_STATICDEP, CM_DMA_STATICDEP, CM_DSP_STATICDEP,
- * CM_IPU_STATICDEP, CM_L3INIT_STATICDEP, CM_MIPIEXT_STATICDEP, CM_MPU_STATICDEP
- */
 #define OMAP54XX_L4CFG_STATDEP_SHIFT					12
-#define OMAP54XX_L4CFG_STATDEP_WIDTH					0x1
-#define OMAP54XX_L4CFG_STATDEP_MASK					(1 << 12)
-
-/* Used by CM_L3MAIN2_DYNAMICDEP */
-#define OMAP54XX_L4PER_DYNDEP_SHIFT					13
-#define OMAP54XX_L4PER_DYNDEP_WIDTH					0x1
-#define OMAP54XX_L4PER_DYNDEP_MASK					(1 << 13)
-
-/*
- * Used by CM_C2C_STATICDEP, CM_DMA_STATICDEP, CM_DSP_STATICDEP,
- * CM_IPU_STATICDEP, CM_L3INIT_STATICDEP, CM_L4SEC_STATICDEP,
- * CM_MIPIEXT_STATICDEP, CM_MPU_STATICDEP
- */
 #define OMAP54XX_L4PER_STATDEP_SHIFT					13
-#define OMAP54XX_L4PER_STATDEP_WIDTH					0x1
-#define OMAP54XX_L4PER_STATDEP_MASK					(1 << 13)
-
-/* Used by CM_L3MAIN2_DYNAMICDEP, CM_L4PER_DYNAMICDEP */
-#define OMAP54XX_L4SEC_DYNDEP_SHIFT					14
-#define OMAP54XX_L4SEC_DYNDEP_WIDTH					0x1
-#define OMAP54XX_L4SEC_DYNDEP_MASK					(1 << 14)
-
-/*
- * Used by CM_DMA_STATICDEP, CM_IPU_STATICDEP, CM_L3INIT_STATICDEP,
- * CM_MPU_STATICDEP
- */
 #define OMAP54XX_L4SEC_STATDEP_SHIFT					14
-#define OMAP54XX_L4SEC_STATDEP_WIDTH					0x1
-#define OMAP54XX_L4SEC_STATDEP_MASK					(1 << 14)
-
-/* Used by CM_L3MAIN2_DYNAMICDEP, CM_L4CFG_DYNAMICDEP */
-#define OMAP54XX_MIPIEXT_DYNDEP_SHIFT					21
-#define OMAP54XX_MIPIEXT_DYNDEP_WIDTH					0x1
-#define OMAP54XX_MIPIEXT_DYNDEP_MASK					(1 << 21)
-
-/* Used by CM_MPU_STATICDEP */
-#define OMAP54XX_MIPIEXT_STATDEP_SHIFT					21
-#define OMAP54XX_MIPIEXT_STATDEP_WIDTH					0x1
-#define OMAP54XX_MIPIEXT_STATDEP_MASK					(1 << 21)
-
-/*
- * Used by CM_SSC_MODFREQDIV_DPLL_ABE, CM_SSC_MODFREQDIV_DPLL_CORE,
- * CM_SSC_MODFREQDIV_DPLL_IVA, CM_SSC_MODFREQDIV_DPLL_MPU,
- * CM_SSC_MODFREQDIV_DPLL_PER, CM_SSC_MODFREQDIV_DPLL_UNIPRO1,
- * CM_SSC_MODFREQDIV_DPLL_UNIPRO2, CM_SSC_MODFREQDIV_DPLL_USB
- */
-#define OMAP54XX_MODFREQDIV_EXPONENT_SHIFT				8
-#define OMAP54XX_MODFREQDIV_EXPONENT_WIDTH				0x3
-#define OMAP54XX_MODFREQDIV_EXPONENT_MASK				(0x7 << 8)
-
-/*
- * Used by CM_SSC_MODFREQDIV_DPLL_ABE, CM_SSC_MODFREQDIV_DPLL_CORE,
- * CM_SSC_MODFREQDIV_DPLL_IVA, CM_SSC_MODFREQDIV_DPLL_MPU,
- * CM_SSC_MODFREQDIV_DPLL_PER, CM_SSC_MODFREQDIV_DPLL_UNIPRO1,
- * CM_SSC_MODFREQDIV_DPLL_UNIPRO2, CM_SSC_MODFREQDIV_DPLL_USB
- */
-#define OMAP54XX_MODFREQDIV_MANTISSA_SHIFT				0
-#define OMAP54XX_MODFREQDIV_MANTISSA_WIDTH				0x7
-#define OMAP54XX_MODFREQDIV_MANTISSA_MASK				(0x7f << 0)
-
-/*
- * Used by CM_ABE_AESS_CLKCTRL, CM_ABE_DMIC_CLKCTRL, CM_ABE_L4_ABE_CLKCTRL,
- * CM_ABE_MCASP_CLKCTRL, CM_ABE_MCBSP1_CLKCTRL, CM_ABE_MCBSP2_CLKCTRL,
- * CM_ABE_MCBSP3_CLKCTRL, CM_ABE_MCPDM_CLKCTRL, CM_ABE_SLIMBUS1_CLKCTRL,
- * CM_ABE_TIMER5_CLKCTRL, CM_ABE_TIMER6_CLKCTRL, CM_ABE_TIMER7_CLKCTRL,
- * CM_ABE_TIMER8_CLKCTRL, CM_ABE_WD_TIMER3_CLKCTRL, CM_C2C_C2C_CLKCTRL,
- * CM_C2C_C2C_OCP_FW_CLKCTRL, CM_C2C_MODEM_ICR_CLKCTRL, CM_CAM_CAL_CLKCTRL,
- * CM_CAM_FDIF_CLKCTRL, CM_CAM_ISS_CLKCTRL, CM_CM_CORE_AON_PROFILING_CLKCTRL,
- * CM_CM_CORE_PROFILING_CLKCTRL, CM_COREAON_SMARTREFLEX_CORE_CLKCTRL,
- * CM_COREAON_SMARTREFLEX_MM_CLKCTRL, CM_COREAON_SMARTREFLEX_MPU_CLKCTRL,
- * CM_CUSTEFUSE_EFUSE_CTRL_CUST_CLKCTRL, CM_DMA_DMA_SYSTEM_CLKCTRL,
- * CM_DSP_DSP_CLKCTRL, CM_DSS_BB2D_CLKCTRL, CM_DSS_DSS_CLKCTRL,
- * CM_EMIF_DMM_CLKCTRL, CM_EMIF_EMIF1_CLKCTRL, CM_EMIF_EMIF2_CLKCTRL,
- * CM_EMIF_EMIF_OCP_FW_CLKCTRL, CM_EMU_DEBUGSS_CLKCTRL,
- * CM_EMU_MPU_EMU_DBG_CLKCTRL, CM_GPU_GPU_CLKCTRL, CM_IPU_IPU_CLKCTRL,
- * CM_IVA_IVA_CLKCTRL, CM_IVA_SL2_CLKCTRL, CM_L3INIT_HSI_CLKCTRL,
- * CM_L3INIT_IEEE1500_2_OCP_CLKCTRL, CM_L3INIT_MMC1_CLKCTRL,
- * CM_L3INIT_MMC2_CLKCTRL, CM_L3INIT_MPHY_UNIPRO2_CLKCTRL,
- * CM_L3INIT_OCP2SCP1_CLKCTRL, CM_L3INIT_OCP2SCP3_CLKCTRL,
- * CM_L3INIT_SATA_CLKCTRL, CM_L3INIT_UNIPRO2_CLKCTRL,
- * CM_L3INIT_USB_HOST_HS_CLKCTRL, CM_L3INIT_USB_OTG_SS_CLKCTRL,
- * CM_L3INIT_USB_TLL_HS_CLKCTRL, CM_L3INSTR_CTRL_MODULE_BANDGAP_CLKCTRL,
- * CM_L3INSTR_DLL_AGING_CLKCTRL, CM_L3INSTR_L3_INSTR_CLKCTRL,
- * CM_L3INSTR_L3_MAIN_3_CLKCTRL, CM_L3INSTR_OCP_WP_NOC_CLKCTRL,
- * CM_L3MAIN1_L3_MAIN_1_CLKCTRL, CM_L3MAIN2_GPMC_CLKCTRL,
- * CM_L3MAIN2_L3_MAIN_2_CLKCTRL, CM_L3MAIN2_OCMC_RAM_CLKCTRL,
- * CM_L4CFG_L4_CFG_CLKCTRL, CM_L4CFG_MAILBOX_CLKCTRL,
- * CM_L4CFG_OCP2SCP2_CLKCTRL, CM_L4CFG_SAR_ROM_CLKCTRL,
- * CM_L4CFG_SPINLOCK_CLKCTRL, CM_L4PER_ELM_CLKCTRL, CM_L4PER_GPIO2_CLKCTRL,
- * CM_L4PER_GPIO3_CLKCTRL, CM_L4PER_GPIO4_CLKCTRL, CM_L4PER_GPIO5_CLKCTRL,
- * CM_L4PER_GPIO6_CLKCTRL, CM_L4PER_GPIO7_CLKCTRL, CM_L4PER_GPIO8_CLKCTRL,
- * CM_L4PER_HDQ1W_CLKCTRL, CM_L4PER_I2C1_CLKCTRL, CM_L4PER_I2C2_CLKCTRL,
- * CM_L4PER_I2C3_CLKCTRL, CM_L4PER_I2C4_CLKCTRL, CM_L4PER_I2C5_CLKCTRL,
- * CM_L4PER_L4_PER_CLKCTRL, CM_L4PER_MCSPI1_CLKCTRL, CM_L4PER_MCSPI2_CLKCTRL,
- * CM_L4PER_MCSPI3_CLKCTRL, CM_L4PER_MCSPI4_CLKCTRL, CM_L4PER_MMC3_CLKCTRL,
- * CM_L4PER_MMC4_CLKCTRL, CM_L4PER_MMC5_CLKCTRL, CM_L4PER_TIMER10_CLKCTRL,
- * CM_L4PER_TIMER11_CLKCTRL, CM_L4PER_TIMER2_CLKCTRL, CM_L4PER_TIMER3_CLKCTRL,
- * CM_L4PER_TIMER4_CLKCTRL, CM_L4PER_TIMER9_CLKCTRL, CM_L4PER_UART1_CLKCTRL,
- * CM_L4PER_UART2_CLKCTRL, CM_L4PER_UART3_CLKCTRL, CM_L4PER_UART4_CLKCTRL,
- * CM_L4PER_UART5_CLKCTRL, CM_L4PER_UART6_CLKCTRL, CM_L4SEC_AES1_CLKCTRL,
- * CM_L4SEC_AES2_CLKCTRL, CM_L4SEC_DES3DES_CLKCTRL,
- * CM_L4SEC_DMA_CRYPTO_CLKCTRL, CM_L4SEC_FPKA_CLKCTRL, CM_L4SEC_RNG_CLKCTRL,
- * CM_L4SEC_SHA2MD5_CLKCTRL, CM_MIPIEXT_LLI_CLKCTRL,
- * CM_MIPIEXT_LLI_OCP_FW_CLKCTRL, CM_MIPIEXT_MPHY_CLKCTRL, CM_MPU_MPU_CLKCTRL,
- * CM_MPU_MPU_MPU_DBG_CLKCTRL, CM_WKUPAON_COUNTER_32K_CLKCTRL,
- * CM_WKUPAON_GPIO1_CLKCTRL, CM_WKUPAON_KBD_CLKCTRL,
- * CM_WKUPAON_L4_WKUP_CLKCTRL, CM_WKUPAON_SAR_RAM_CLKCTRL,
- * CM_WKUPAON_TIMER12_CLKCTRL, CM_WKUPAON_TIMER1_CLKCTRL,
- * CM_WKUPAON_WD_TIMER1_CLKCTRL, CM_WKUPAON_WD_TIMER2_CLKCTRL
- */
-#define OMAP54XX_MODULEMODE_SHIFT					0
-#define OMAP54XX_MODULEMODE_WIDTH					0x2
-#define OMAP54XX_MODULEMODE_MASK					(0x3 << 0)
-
-/* Used by CM_L4CFG_DYNAMICDEP */
-#define OMAP54XX_MPU_DYNDEP_SHIFT					19
-#define OMAP54XX_MPU_DYNDEP_WIDTH					0x1
-#define OMAP54XX_MPU_DYNDEP_MASK					(1 << 19)
-
-/* Used by CM_DSS_DSS_CLKCTRL */
 #define OMAP54XX_OPTFCLKEN_32KHZ_CLK_SHIFT				11
-#define OMAP54XX_OPTFCLKEN_32KHZ_CLK_WIDTH				0x1
-#define OMAP54XX_OPTFCLKEN_32KHZ_CLK_MASK				(1 << 11)
-
-/* Renamed from OPTFCLKEN_32KHZ_CLK Used by CM_L3INIT_MMC1_CLKCTRL */
 #define OMAP54XX_OPTFCLKEN_32KHZ_CLK_8_8_SHIFT				8
-#define OMAP54XX_OPTFCLKEN_32KHZ_CLK_8_8_WIDTH				0x1
-#define OMAP54XX_OPTFCLKEN_32KHZ_CLK_8_8_MASK				(1 << 8)
-
-/* Used by CM_DSS_DSS_CLKCTRL */
 #define OMAP54XX_OPTFCLKEN_48MHZ_CLK_SHIFT				9
-#define OMAP54XX_OPTFCLKEN_48MHZ_CLK_WIDTH				0x1
-#define OMAP54XX_OPTFCLKEN_48MHZ_CLK_MASK				(1 << 9)
-
-/* Used by CM_COREAON_USB_PHY_CORE_CLKCTRL */
 #define OMAP54XX_OPTFCLKEN_CLK32K_SHIFT					8
-#define OMAP54XX_OPTFCLKEN_CLK32K_WIDTH					0x1
-#define OMAP54XX_OPTFCLKEN_CLK32K_MASK					(1 << 8)
-
-/* Used by CM_CAM_ISS_CLKCTRL */
 #define OMAP54XX_OPTFCLKEN_CTRLCLK_SHIFT				8
-#define OMAP54XX_OPTFCLKEN_CTRLCLK_WIDTH				0x1
-#define OMAP54XX_OPTFCLKEN_CTRLCLK_MASK					(1 << 8)
-
-/*
- * Used by CM_L4PER_GPIO2_CLKCTRL, CM_L4PER_GPIO3_CLKCTRL,
- * CM_L4PER_GPIO4_CLKCTRL, CM_L4PER_GPIO5_CLKCTRL, CM_L4PER_GPIO6_CLKCTRL,
- * CM_L4PER_GPIO7_CLKCTRL, CM_L4PER_GPIO8_CLKCTRL, CM_WKUPAON_GPIO1_CLKCTRL
- */
 #define OMAP54XX_OPTFCLKEN_DBCLK_SHIFT					8
-#define OMAP54XX_OPTFCLKEN_DBCLK_WIDTH					0x1
-#define OMAP54XX_OPTFCLKEN_DBCLK_MASK					(1 << 8)
-
-/* Used by CM_EMIF_EMIF_DLL_CLKCTRL */
-#define OMAP54XX_OPTFCLKEN_DLL_CLK_SHIFT				8
-#define OMAP54XX_OPTFCLKEN_DLL_CLK_WIDTH				0x1
-#define OMAP54XX_OPTFCLKEN_DLL_CLK_MASK					(1 << 8)
-
-/* Used by CM_DSS_DSS_CLKCTRL */
 #define OMAP54XX_OPTFCLKEN_DSSCLK_SHIFT					8
-#define OMAP54XX_OPTFCLKEN_DSSCLK_WIDTH					0x1
-#define OMAP54XX_OPTFCLKEN_DSSCLK_MASK					(1 << 8)
-
-/* Used by CM_ABE_SLIMBUS1_CLKCTRL */
-#define OMAP54XX_OPTFCLKEN_FCLK0_SHIFT					8
-#define OMAP54XX_OPTFCLKEN_FCLK0_WIDTH					0x1
-#define OMAP54XX_OPTFCLKEN_FCLK0_MASK					(1 << 8)
-
-/* Used by CM_ABE_SLIMBUS1_CLKCTRL */
-#define OMAP54XX_OPTFCLKEN_FCLK1_SHIFT					9
-#define OMAP54XX_OPTFCLKEN_FCLK1_WIDTH					0x1
-#define OMAP54XX_OPTFCLKEN_FCLK1_MASK					(1 << 9)
-
-/* Used by CM_ABE_SLIMBUS1_CLKCTRL */
-#define OMAP54XX_OPTFCLKEN_FCLK2_SHIFT					10
-#define OMAP54XX_OPTFCLKEN_FCLK2_WIDTH					0x1
-#define OMAP54XX_OPTFCLKEN_FCLK2_MASK					(1 << 10)
-
-/* Used by CM_L3INIT_USB_HOST_HS_CLKCTRL */
-#define OMAP54XX_OPTFCLKEN_FUNC48M_CLK_SHIFT				15
-#define OMAP54XX_OPTFCLKEN_FUNC48M_CLK_WIDTH				0x1
-#define OMAP54XX_OPTFCLKEN_FUNC48M_CLK_MASK				(1 << 15)
-
-/* Used by CM_L3INIT_USB_HOST_HS_CLKCTRL */
 #define OMAP54XX_OPTFCLKEN_HSIC480M_P1_CLK_SHIFT			13
-#define OMAP54XX_OPTFCLKEN_HSIC480M_P1_CLK_WIDTH			0x1
-#define OMAP54XX_OPTFCLKEN_HSIC480M_P1_CLK_MASK				(1 << 13)
-
-/* Used by CM_L3INIT_USB_HOST_HS_CLKCTRL */
 #define OMAP54XX_OPTFCLKEN_HSIC480M_P2_CLK_SHIFT			14
-#define OMAP54XX_OPTFCLKEN_HSIC480M_P2_CLK_WIDTH			0x1
-#define OMAP54XX_OPTFCLKEN_HSIC480M_P2_CLK_MASK				(1 << 14)
-
-/* Used by CM_L3INIT_USB_HOST_HS_CLKCTRL */
 #define OMAP54XX_OPTFCLKEN_HSIC480M_P3_CLK_SHIFT			7
-#define OMAP54XX_OPTFCLKEN_HSIC480M_P3_CLK_WIDTH			0x1
-#define OMAP54XX_OPTFCLKEN_HSIC480M_P3_CLK_MASK				(1 << 7)
-
-/* Used by CM_L3INIT_USB_HOST_HS_CLKCTRL */
 #define OMAP54XX_OPTFCLKEN_HSIC60M_P1_CLK_SHIFT				11
-#define OMAP54XX_OPTFCLKEN_HSIC60M_P1_CLK_WIDTH				0x1
-#define OMAP54XX_OPTFCLKEN_HSIC60M_P1_CLK_MASK				(1 << 11)
-
-/* Used by CM_L3INIT_USB_HOST_HS_CLKCTRL */
 #define OMAP54XX_OPTFCLKEN_HSIC60M_P2_CLK_SHIFT				12
-#define OMAP54XX_OPTFCLKEN_HSIC60M_P2_CLK_WIDTH				0x1
-#define OMAP54XX_OPTFCLKEN_HSIC60M_P2_CLK_MASK				(1 << 12)
-
-/* Used by CM_L3INIT_USB_HOST_HS_CLKCTRL */
 #define OMAP54XX_OPTFCLKEN_HSIC60M_P3_CLK_SHIFT				6
-#define OMAP54XX_OPTFCLKEN_HSIC60M_P3_CLK_WIDTH				0x1
-#define OMAP54XX_OPTFCLKEN_HSIC60M_P3_CLK_MASK				(1 << 6)
-
-/* Used by CM_L3INIT_USB_OTG_SS_CLKCTRL */
 #define OMAP54XX_OPTFCLKEN_REFCLK960M_SHIFT				8
-#define OMAP54XX_OPTFCLKEN_REFCLK960M_WIDTH				0x1
-#define OMAP54XX_OPTFCLKEN_REFCLK960M_MASK				(1 << 8)
-
-/* Used by CM_L3INIT_SATA_CLKCTRL */
 #define OMAP54XX_OPTFCLKEN_REF_CLK_SHIFT				8
-#define OMAP54XX_OPTFCLKEN_REF_CLK_WIDTH				0x1
-#define OMAP54XX_OPTFCLKEN_REF_CLK_MASK					(1 << 8)
-
-/* Used by CM_WKUPAON_SCRM_CLKCTRL */
-#define OMAP54XX_OPTFCLKEN_SCRM_CORE_SHIFT				8
-#define OMAP54XX_OPTFCLKEN_SCRM_CORE_WIDTH				0x1
-#define OMAP54XX_OPTFCLKEN_SCRM_CORE_MASK				(1 << 8)
-
-/* Used by CM_WKUPAON_SCRM_CLKCTRL */
-#define OMAP54XX_OPTFCLKEN_SCRM_PER_SHIFT				9
-#define OMAP54XX_OPTFCLKEN_SCRM_PER_WIDTH				0x1
-#define OMAP54XX_OPTFCLKEN_SCRM_PER_MASK				(1 << 9)
-
-/* Used by CM_ABE_SLIMBUS1_CLKCTRL */
 #define OMAP54XX_OPTFCLKEN_SLIMBUS_CLK_SHIFT				11
-#define OMAP54XX_OPTFCLKEN_SLIMBUS_CLK_WIDTH				0x1
-#define OMAP54XX_OPTFCLKEN_SLIMBUS_CLK_MASK				(1 << 11)
-
-/* Used by CM_DSS_DSS_CLKCTRL */
 #define OMAP54XX_OPTFCLKEN_SYS_CLK_SHIFT				10
-#define OMAP54XX_OPTFCLKEN_SYS_CLK_WIDTH				0x1
-#define OMAP54XX_OPTFCLKEN_SYS_CLK_MASK					(1 << 10)
-
-/* Used by CM_MIPIEXT_LLI_CLKCTRL */
 #define OMAP54XX_OPTFCLKEN_TXPHY_CLK_SHIFT				8
-#define OMAP54XX_OPTFCLKEN_TXPHY_CLK_WIDTH				0x1
-#define OMAP54XX_OPTFCLKEN_TXPHY_CLK_MASK				(1 << 8)
-
-/* Used by CM_MIPIEXT_LLI_CLKCTRL */
 #define OMAP54XX_OPTFCLKEN_TXPHY_LS_CLK_SHIFT				9
-#define OMAP54XX_OPTFCLKEN_TXPHY_LS_CLK_WIDTH				0x1
-#define OMAP54XX_OPTFCLKEN_TXPHY_LS_CLK_MASK				(1 << 9)
-
-/* Used by CM_L3INIT_USB_TLL_HS_CLKCTRL */
 #define OMAP54XX_OPTFCLKEN_USB_CH0_CLK_SHIFT				8
-#define OMAP54XX_OPTFCLKEN_USB_CH0_CLK_WIDTH				0x1
-#define OMAP54XX_OPTFCLKEN_USB_CH0_CLK_MASK				(1 << 8)
-
-/* Used by CM_L3INIT_USB_TLL_HS_CLKCTRL */
 #define OMAP54XX_OPTFCLKEN_USB_CH1_CLK_SHIFT				9
-#define OMAP54XX_OPTFCLKEN_USB_CH1_CLK_WIDTH				0x1
-#define OMAP54XX_OPTFCLKEN_USB_CH1_CLK_MASK				(1 << 9)
-
-/* Used by CM_L3INIT_USB_TLL_HS_CLKCTRL */
 #define OMAP54XX_OPTFCLKEN_USB_CH2_CLK_SHIFT				10
-#define OMAP54XX_OPTFCLKEN_USB_CH2_CLK_WIDTH				0x1
-#define OMAP54XX_OPTFCLKEN_USB_CH2_CLK_MASK				(1 << 10)
-
-/* Used by CM_L3INIT_USB_HOST_HS_CLKCTRL */
 #define OMAP54XX_OPTFCLKEN_UTMI_P1_CLK_SHIFT				8
-#define OMAP54XX_OPTFCLKEN_UTMI_P1_CLK_WIDTH				0x1
-#define OMAP54XX_OPTFCLKEN_UTMI_P1_CLK_MASK				(1 << 8)
-
-/* Used by CM_L3INIT_USB_HOST_HS_CLKCTRL */
 #define OMAP54XX_OPTFCLKEN_UTMI_P2_CLK_SHIFT				9
-#define OMAP54XX_OPTFCLKEN_UTMI_P2_CLK_WIDTH				0x1
-#define OMAP54XX_OPTFCLKEN_UTMI_P2_CLK_MASK				(1 << 9)
-
-/* Used by CM_L3INIT_USB_HOST_HS_CLKCTRL */
 #define OMAP54XX_OPTFCLKEN_UTMI_P3_CLK_SHIFT				10
-#define OMAP54XX_OPTFCLKEN_UTMI_P3_CLK_WIDTH				0x1
-#define OMAP54XX_OPTFCLKEN_UTMI_P3_CLK_MASK				(1 << 10)
-
-/* Used by CM_CORE_AON_DEBUG_OUT, CM_CORE_DEBUG_OUT */
-#define OMAP54XX_OUTPUT_SHIFT						0
-#define OMAP54XX_OUTPUT_WIDTH						0x20
-#define OMAP54XX_OUTPUT_MASK						(0xffffffff << 0)
-
-/* Used by CM_CLKSEL_ABE */
 #define OMAP54XX_PAD_CLKS_GATE_SHIFT					8
-#define OMAP54XX_PAD_CLKS_GATE_WIDTH					0x1
-#define OMAP54XX_PAD_CLKS_GATE_MASK					(1 << 8)
-
-/* Used by CM_RESTORE_ST */
-#define OMAP54XX_PHASE1_COMPLETED_SHIFT					0
-#define OMAP54XX_PHASE1_COMPLETED_WIDTH					0x1
-#define OMAP54XX_PHASE1_COMPLETED_MASK					(1 << 0)
-
-/* Used by CM_RESTORE_ST */
-#define OMAP54XX_PHASE2A_COMPLETED_SHIFT				1
-#define OMAP54XX_PHASE2A_COMPLETED_WIDTH				0x1
-#define OMAP54XX_PHASE2A_COMPLETED_MASK					(1 << 1)
-
-/* Used by CM_RESTORE_ST */
-#define OMAP54XX_PHASE2B_COMPLETED_SHIFT				2
-#define OMAP54XX_PHASE2B_COMPLETED_WIDTH				0x1
-#define OMAP54XX_PHASE2B_COMPLETED_MASK					(1 << 2)
-
-/* Used by CM_DYN_DEP_PRESCAL */
-#define OMAP54XX_PRESCAL_SHIFT						0
-#define OMAP54XX_PRESCAL_WIDTH						0x6
-#define OMAP54XX_PRESCAL_MASK						(0x3f << 0)
-
-/* Used by REVISION_CM_CORE, REVISION_CM_CORE_AON */
-#define OMAP54XX_R_RTL_SHIFT						11
-#define OMAP54XX_R_RTL_WIDTH						0x5
-#define OMAP54XX_R_RTL_MASK						(0x1f << 11)
-
-/* Used by CM_L3INIT_USB_HOST_HS_CLKCTRL, CM_L3INIT_USB_TLL_HS_CLKCTRL */
-#define OMAP54XX_SAR_MODE_SHIFT						4
-#define OMAP54XX_SAR_MODE_WIDTH						0x1
-#define OMAP54XX_SAR_MODE_MASK						(1 << 4)
-
-/* Used by REVISION_CM_CORE, REVISION_CM_CORE_AON */
-#define OMAP54XX_SCHEME_SHIFT						30
-#define OMAP54XX_SCHEME_WIDTH						0x2
-#define OMAP54XX_SCHEME_MASK						(0x3 << 30)
-
-/* Used by CM_L4CFG_DYNAMICDEP */
-#define OMAP54XX_SDMA_DYNDEP_SHIFT					11
-#define OMAP54XX_SDMA_DYNDEP_WIDTH					0x1
-#define OMAP54XX_SDMA_DYNDEP_MASK					(1 << 11)
-
-/* Used by CM_IPU_STATICDEP, CM_MPU_STATICDEP */
-#define OMAP54XX_SDMA_STATDEP_SHIFT					11
-#define OMAP54XX_SDMA_STATDEP_WIDTH					0x1
-#define OMAP54XX_SDMA_STATDEP_MASK					(1 << 11)
-
-/* Used by CM_CORE_AON_DEBUG_CFG */
-#define OMAP54XX_SEL0_SHIFT						0
-#define OMAP54XX_SEL0_WIDTH						0x7
-#define OMAP54XX_SEL0_MASK						(0x7f << 0)
-
-/* Renamed from SEL0 Used by CM_CORE_DEBUG_CFG */
-#define OMAP54XX_SEL0_0_7_SHIFT						0
-#define OMAP54XX_SEL0_0_7_WIDTH						0x8
-#define OMAP54XX_SEL0_0_7_MASK						(0xff << 0)
-
-/* Used by CM_CORE_AON_DEBUG_CFG */
-#define OMAP54XX_SEL1_SHIFT						8
-#define OMAP54XX_SEL1_WIDTH						0x7
-#define OMAP54XX_SEL1_MASK						(0x7f << 8)
-
-/* Renamed from SEL1 Used by CM_CORE_DEBUG_CFG */
-#define OMAP54XX_SEL1_CORE_DEBUG_CFG_SHIFT				8
-#define OMAP54XX_SEL1_CORE_DEBUG_CFG_WIDTH				0x8
-#define OMAP54XX_SEL1_CORE_DEBUG_CFG_MASK				(0xff << 8)
-
-/* Used by CM_CORE_AON_DEBUG_CFG */
-#define OMAP54XX_SEL2_SHIFT						16
-#define OMAP54XX_SEL2_WIDTH						0x7
-#define OMAP54XX_SEL2_MASK						(0x7f << 16)
-
-/* Renamed from SEL2 Used by CM_CORE_DEBUG_CFG */
-#define OMAP54XX_SEL2_CORE_DEBUG_CFG_SHIFT				16
-#define OMAP54XX_SEL2_CORE_DEBUG_CFG_WIDTH				0x8
-#define OMAP54XX_SEL2_CORE_DEBUG_CFG_MASK				(0xff << 16)
-
-/* Used by CM_CORE_AON_DEBUG_CFG */
-#define OMAP54XX_SEL3_SHIFT						24
-#define OMAP54XX_SEL3_WIDTH						0x7
-#define OMAP54XX_SEL3_MASK						(0x7f << 24)
-
-/* Renamed from SEL3 Used by CM_CORE_DEBUG_CFG */
-#define OMAP54XX_SEL3_CORE_DEBUG_CFG_SHIFT				24
-#define OMAP54XX_SEL3_CORE_DEBUG_CFG_WIDTH				0x8
-#define OMAP54XX_SEL3_CORE_DEBUG_CFG_MASK				(0xff << 24)
-
-/* Used by CM_CLKSEL_ABE */
 #define OMAP54XX_SLIMBUS1_CLK_GATE_SHIFT				10
-#define OMAP54XX_SLIMBUS1_CLK_GATE_WIDTH				0x1
-#define OMAP54XX_SLIMBUS1_CLK_GATE_MASK					(1 << 10)
-
-/*
- * Used by CM_ABE_AESS_CLKCTRL, CM_C2C_C2C_CLKCTRL, CM_CAM_FDIF_CLKCTRL,
- * CM_CAM_ISS_CLKCTRL, CM_DMA_DMA_SYSTEM_CLKCTRL, CM_DSP_DSP_CLKCTRL,
- * CM_DSS_BB2D_CLKCTRL, CM_DSS_DSS_CLKCTRL, CM_EMU_DEBUGSS_CLKCTRL,
- * CM_GPU_GPU_CLKCTRL, CM_IPU_IPU_CLKCTRL, CM_IVA_IVA_CLKCTRL,
- * CM_L3INIT_HSI_CLKCTRL, CM_L3INIT_IEEE1500_2_OCP_CLKCTRL,
- * CM_L3INIT_MMC1_CLKCTRL, CM_L3INIT_MMC2_CLKCTRL, CM_L3INIT_SATA_CLKCTRL,
- * CM_L3INIT_UNIPRO2_CLKCTRL, CM_L3INIT_USB_HOST_HS_CLKCTRL,
- * CM_L3INIT_USB_OTG_SS_CLKCTRL, CM_L4SEC_DMA_CRYPTO_CLKCTRL,
- * CM_MIPIEXT_LLI_CLKCTRL, CM_MPU_MPU_CLKCTRL
- */
-#define OMAP54XX_STBYST_SHIFT						18
-#define OMAP54XX_STBYST_WIDTH						0x1
-#define OMAP54XX_STBYST_MASK						(1 << 18)
-
-/*
- * Used by CM_IDLEST_DPLL_ABE, CM_IDLEST_DPLL_CORE, CM_IDLEST_DPLL_IVA,
- * CM_IDLEST_DPLL_MPU, CM_IDLEST_DPLL_PER, CM_IDLEST_DPLL_UNIPRO1,
- * CM_IDLEST_DPLL_UNIPRO2, CM_IDLEST_DPLL_USB
- */
-#define OMAP54XX_ST_DPLL_CLK_SHIFT					0
-#define OMAP54XX_ST_DPLL_CLK_WIDTH					0x1
 #define OMAP54XX_ST_DPLL_CLK_MASK					(1 << 0)
-
-/*
- * Used by CM_CLKDCOLDO_DPLL_UNIPRO1, CM_CLKDCOLDO_DPLL_UNIPRO2,
- * CM_CLKDCOLDO_DPLL_USB
- */
-#define OMAP54XX_ST_DPLL_CLKDCOLDO_SHIFT				9
-#define OMAP54XX_ST_DPLL_CLKDCOLDO_WIDTH				0x1
-#define OMAP54XX_ST_DPLL_CLKDCOLDO_MASK					(1 << 9)
-
-/*
- * Used by CM_IDLEST_DPLL_ABE, CM_IDLEST_DPLL_CORE, CM_IDLEST_DPLL_IVA,
- * CM_IDLEST_DPLL_MPU, CM_IDLEST_DPLL_PER, CM_IDLEST_DPLL_UNIPRO1,
- * CM_IDLEST_DPLL_UNIPRO2, CM_IDLEST_DPLL_USB
- */
-#define OMAP54XX_ST_DPLL_INIT_SHIFT					4
-#define OMAP54XX_ST_DPLL_INIT_WIDTH					0x1
-#define OMAP54XX_ST_DPLL_INIT_MASK					(1 << 4)
-
-/*
- * Used by CM_IDLEST_DPLL_ABE, CM_IDLEST_DPLL_CORE, CM_IDLEST_DPLL_IVA,
- * CM_IDLEST_DPLL_MPU, CM_IDLEST_DPLL_PER, CM_IDLEST_DPLL_UNIPRO1,
- * CM_IDLEST_DPLL_UNIPRO2, CM_IDLEST_DPLL_USB
- */
-#define OMAP54XX_ST_DPLL_MODE_SHIFT					1
-#define OMAP54XX_ST_DPLL_MODE_WIDTH					0x3
-#define OMAP54XX_ST_DPLL_MODE_MASK					(0x7 << 1)
-
-/* Used by CM_CLKSEL_SYS */
 #define OMAP54XX_SYS_CLKSEL_SHIFT					0
 #define OMAP54XX_SYS_CLKSEL_WIDTH					0x3
-#define OMAP54XX_SYS_CLKSEL_MASK					(0x7 << 0)
-
-/*
- * Used by CM_C2C_DYNAMICDEP, CM_DSP_DYNAMICDEP, CM_EMU_DYNAMICDEP,
- * CM_IPU_DYNAMICDEP, CM_L3MAIN1_DYNAMICDEP, CM_L3MAIN2_DYNAMICDEP,
- * CM_L4CFG_DYNAMICDEP, CM_L4PER_DYNAMICDEP, CM_MIPIEXT_DYNAMICDEP,
- * CM_MPU_DYNAMICDEP
- */
-#define OMAP54XX_WINDOWSIZE_SHIFT					24
-#define OMAP54XX_WINDOWSIZE_WIDTH					0x4
-#define OMAP54XX_WINDOWSIZE_MASK					(0xf << 24)
-
-/* Used by CM_L3MAIN1_DYNAMICDEP */
-#define OMAP54XX_WKUPAON_DYNDEP_SHIFT					15
-#define OMAP54XX_WKUPAON_DYNDEP_WIDTH					0x1
-#define OMAP54XX_WKUPAON_DYNDEP_MASK					(1 << 15)
-
-/*
- * Used by CM_DMA_STATICDEP, CM_DSP_STATICDEP, CM_IPU_STATICDEP,
- * CM_L3INIT_STATICDEP, CM_MPU_STATICDEP
- */
 #define OMAP54XX_WKUPAON_STATDEP_SHIFT					15
-#define OMAP54XX_WKUPAON_STATDEP_WIDTH					0x1
-#define OMAP54XX_WKUPAON_STATDEP_MASK					(1 << 15)
-
-/* Used by REVISION_CM_CORE, REVISION_CM_CORE_AON */
-#define OMAP54XX_X_MAJOR_SHIFT						8
-#define OMAP54XX_X_MAJOR_WIDTH						0x3
-#define OMAP54XX_X_MAJOR_MASK						(0x7 << 8)
-
-/* Used by REVISION_CM_CORE, REVISION_CM_CORE_AON */
-#define OMAP54XX_Y_MINOR_SHIFT						0
-#define OMAP54XX_Y_MINOR_WIDTH						0x6
-#define OMAP54XX_Y_MINOR_MASK						(0x3f << 0)
 #endif
diff --git a/arch/arm/mach-omap2/cm-regbits-7xx.h b/arch/arm/mach-omap2/cm-regbits-7xx.h
new file mode 100644
index 000000000000..ad8f81ce9b16
--- /dev/null
+++ b/arch/arm/mach-omap2/cm-regbits-7xx.h
@@ -0,0 +1,51 @@
+/*
+ * DRA7xx Clock Management register bits
+ *
+ * Copyright (C) 2013 Texas Instruments Incorporated - http://www.ti.com
+ *
+ * Generated by code originally written by:
+ * Paul Walmsley (paul@pwsan.com)
+ * Rajendra Nayak (rnayak@ti.com)
+ * Benoit Cousson (b-cousson@ti.com)
+ *
+ * This file is automatically generated from the OMAP hardware databases.
+ * We respectfully ask that any modifications to this file be coordinated
+ * with the public linux-omap@vger.kernel.org mailing list and the
+ * authors above to ensure that the autogeneration scripts are kept
+ * up-to-date with the file contents.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __ARCH_ARM_MACH_OMAP2_CM_REGBITS_7XX_H
+#define __ARCH_ARM_MACH_OMAP2_CM_REGBITS_7XX_H
+
+#define DRA7XX_ATL_STATDEP_SHIFT				30
+#define DRA7XX_CAM_STATDEP_SHIFT				9
+#define DRA7XX_DSP1_STATDEP_SHIFT				1
+#define DRA7XX_DSP2_STATDEP_SHIFT				18
+#define DRA7XX_DSS_STATDEP_SHIFT				8
+#define DRA7XX_EMIF_STATDEP_SHIFT				4
+#define DRA7XX_EVE1_STATDEP_SHIFT				19
+#define DRA7XX_EVE2_STATDEP_SHIFT				20
+#define DRA7XX_EVE3_STATDEP_SHIFT				21
+#define DRA7XX_EVE4_STATDEP_SHIFT				22
+#define DRA7XX_GMAC_STATDEP_SHIFT				25
+#define DRA7XX_GPU_STATDEP_SHIFT				10
+#define DRA7XX_IPU1_STATDEP_SHIFT				23
+#define DRA7XX_IPU2_STATDEP_SHIFT				0
+#define DRA7XX_IPU_STATDEP_SHIFT				24
+#define DRA7XX_IVA_STATDEP_SHIFT				2
+#define DRA7XX_L3INIT_STATDEP_SHIFT				7
+#define DRA7XX_L3MAIN1_STATDEP_SHIFT				5
+#define DRA7XX_L4CFG_STATDEP_SHIFT				12
+#define DRA7XX_L4PER2_STATDEP_SHIFT				26
+#define DRA7XX_L4PER3_STATDEP_SHIFT				27
+#define DRA7XX_L4PER_STATDEP_SHIFT				13
+#define DRA7XX_L4SEC_STATDEP_SHIFT				14
+#define DRA7XX_PCIE_STATDEP_SHIFT				29
+#define DRA7XX_VPE_STATDEP_SHIFT				28
+#define DRA7XX_WKUPAON_STATDEP_SHIFT				15
+#endif
diff --git a/arch/arm/mach-omap2/cm1_7xx.h b/arch/arm/mach-omap2/cm1_7xx.h
new file mode 100644
index 000000000000..ca6fa1febaac
--- /dev/null
+++ b/arch/arm/mach-omap2/cm1_7xx.h
@@ -0,0 +1,324 @@
+/*
+ * DRA7xx CM1 instance offset macros
+ *
+ * Copyright (C) 2013 Texas Instruments Incorporated - http://www.ti.com
+ *
+ * Generated by code originally written by:
+ * Paul Walmsley (paul@pwsan.com)
+ * Rajendra Nayak (rnayak@ti.com)
+ * Benoit Cousson (b-cousson@ti.com)
+ *
+ * This file is automatically generated from the OMAP hardware databases.
+ * We respectfully ask that any modifications to this file be coordinated
+ * with the public linux-omap@vger.kernel.org mailing list and the
+ * authors above to ensure that the autogeneration scripts are kept
+ * up-to-date with the file contents.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#ifndef __ARCH_ARM_MACH_OMAP2_CM1_7XX_H
+#define __ARCH_ARM_MACH_OMAP2_CM1_7XX_H
+
+#include "cm_44xx_54xx.h"
+
+/* CM1 base address */
+#define DRA7XX_CM_CORE_AON_BASE		0x4a005000
+
+#define DRA7XX_CM_CORE_AON_REGADDR(inst, reg)				\
+	OMAP2_L4_IO_ADDRESS(DRA7XX_CM_CORE_AON_BASE + (inst) + (reg))
+
+/* CM_CORE_AON instances */
+#define DRA7XX_CM_CORE_AON_OCP_SOCKET_INST	0x0000
+#define DRA7XX_CM_CORE_AON_CKGEN_INST		0x0100
+#define DRA7XX_CM_CORE_AON_MPU_INST		0x0300
+#define DRA7XX_CM_CORE_AON_DSP1_INST		0x0400
+#define DRA7XX_CM_CORE_AON_IPU_INST		0x0500
+#define DRA7XX_CM_CORE_AON_DSP2_INST		0x0600
+#define DRA7XX_CM_CORE_AON_EVE1_INST		0x0640
+#define DRA7XX_CM_CORE_AON_EVE2_INST		0x0680
+#define DRA7XX_CM_CORE_AON_EVE3_INST		0x06c0
+#define DRA7XX_CM_CORE_AON_EVE4_INST		0x0700
+#define DRA7XX_CM_CORE_AON_RTC_INST		0x0740
+#define DRA7XX_CM_CORE_AON_VPE_INST		0x0760
+#define DRA7XX_CM_CORE_AON_RESTORE_INST		0x0e00
+#define DRA7XX_CM_CORE_AON_INSTR_INST		0x0f00
+
+/* CM_CORE_AON clockdomain register offsets (from instance start) */
+#define DRA7XX_CM_CORE_AON_MPU_MPU_CDOFFS	0x0000
+#define DRA7XX_CM_CORE_AON_DSP1_DSP1_CDOFFS	0x0000
+#define DRA7XX_CM_CORE_AON_IPU_IPU1_CDOFFS	0x0000
+#define DRA7XX_CM_CORE_AON_IPU_IPU_CDOFFS	0x0040
+#define DRA7XX_CM_CORE_AON_DSP2_DSP2_CDOFFS	0x0000
+#define DRA7XX_CM_CORE_AON_EVE1_EVE1_CDOFFS	0x0000
+#define DRA7XX_CM_CORE_AON_EVE2_EVE2_CDOFFS	0x0000
+#define DRA7XX_CM_CORE_AON_EVE3_EVE3_CDOFFS	0x0000
+#define DRA7XX_CM_CORE_AON_EVE4_EVE4_CDOFFS	0x0000
+#define DRA7XX_CM_CORE_AON_RTC_RTC_CDOFFS	0x0000
+#define DRA7XX_CM_CORE_AON_VPE_VPE_CDOFFS	0x0000
+
+/* CM_CORE_AON */
+
+/* CM_CORE_AON.OCP_SOCKET_CM_CORE_AON register offsets */
+#define DRA7XX_REVISION_CM_CORE_AON_OFFSET		0x0000
+#define DRA7XX_CM_CM_CORE_AON_PROFILING_CLKCTRL_OFFSET	0x0040
+#define DRA7XX_CM_CM_CORE_AON_PROFILING_CLKCTRL		DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_OCP_SOCKET_INST, 0x0040)
+#define DRA7XX_CM_CORE_AON_DEBUG_OUT_OFFSET		0x00ec
+#define DRA7XX_CM_CORE_AON_DEBUG_CFG0_OFFSET		0x00f0
+#define DRA7XX_CM_CORE_AON_DEBUG_CFG1_OFFSET		0x00f4
+#define DRA7XX_CM_CORE_AON_DEBUG_CFG2_OFFSET		0x00f8
+#define DRA7XX_CM_CORE_AON_DEBUG_CFG3_OFFSET		0x00fc
+
+/* CM_CORE_AON.CKGEN_CM_CORE_AON register offsets */
+#define DRA7XX_CM_CLKSEL_CORE_OFFSET			0x0000
+#define DRA7XX_CM_CLKSEL_CORE				DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_CKGEN_INST, 0x0000)
+#define DRA7XX_CM_CLKSEL_ABE_OFFSET			0x0008
+#define DRA7XX_CM_CLKSEL_ABE				DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_CKGEN_INST, 0x0008)
+#define DRA7XX_CM_DLL_CTRL_OFFSET			0x0010
+#define DRA7XX_CM_CLKMODE_DPLL_CORE_OFFSET		0x0020
+#define DRA7XX_CM_CLKMODE_DPLL_CORE			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_CKGEN_INST, 0x0020)
+#define DRA7XX_CM_IDLEST_DPLL_CORE_OFFSET		0x0024
+#define DRA7XX_CM_IDLEST_DPLL_CORE			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_CKGEN_INST, 0x0024)
+#define DRA7XX_CM_AUTOIDLE_DPLL_CORE_OFFSET		0x0028
+#define DRA7XX_CM_AUTOIDLE_DPLL_CORE			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_CKGEN_INST, 0x0028)
+#define DRA7XX_CM_CLKSEL_DPLL_CORE_OFFSET		0x002c
+#define DRA7XX_CM_CLKSEL_DPLL_CORE			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_CKGEN_INST, 0x002c)
+#define DRA7XX_CM_DIV_M2_DPLL_CORE_OFFSET		0x0030
+#define DRA7XX_CM_DIV_M2_DPLL_CORE			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_CKGEN_INST, 0x0030)
+#define DRA7XX_CM_DIV_M3_DPLL_CORE_OFFSET		0x0034
+#define DRA7XX_CM_DIV_M3_DPLL_CORE			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_CKGEN_INST, 0x0034)
+#define DRA7XX_CM_DIV_H11_DPLL_CORE_OFFSET		0x0038
+#define DRA7XX_CM_DIV_H11_DPLL_CORE			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_CKGEN_INST, 0x0038)
+#define DRA7XX_CM_DIV_H12_DPLL_CORE_OFFSET		0x003c
+#define DRA7XX_CM_DIV_H12_DPLL_CORE			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_CKGEN_INST, 0x003c)
+#define DRA7XX_CM_DIV_H13_DPLL_CORE_OFFSET		0x0040
+#define DRA7XX_CM_DIV_H13_DPLL_CORE			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_CKGEN_INST, 0x0040)
+#define DRA7XX_CM_DIV_H14_DPLL_CORE_OFFSET		0x0044
+#define DRA7XX_CM_DIV_H14_DPLL_CORE			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_CKGEN_INST, 0x0044)
+#define DRA7XX_CM_SSC_DELTAMSTEP_DPLL_CORE_OFFSET	0x0048
+#define DRA7XX_CM_SSC_MODFREQDIV_DPLL_CORE_OFFSET	0x004c
+#define DRA7XX_CM_DIV_H21_DPLL_CORE_OFFSET		0x0050
+#define DRA7XX_CM_DIV_H21_DPLL_CORE			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_CKGEN_INST, 0x0050)
+#define DRA7XX_CM_DIV_H22_DPLL_CORE_OFFSET		0x0054
+#define DRA7XX_CM_DIV_H22_DPLL_CORE			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_CKGEN_INST, 0x0054)
+#define DRA7XX_CM_DIV_H23_DPLL_CORE_OFFSET		0x0058
+#define DRA7XX_CM_DIV_H23_DPLL_CORE			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_CKGEN_INST, 0x0058)
+#define DRA7XX_CM_DIV_H24_DPLL_CORE_OFFSET		0x005c
+#define DRA7XX_CM_DIV_H24_DPLL_CORE			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_CKGEN_INST, 0x005c)
+#define DRA7XX_CM_CLKMODE_DPLL_MPU_OFFSET		0x0060
+#define DRA7XX_CM_CLKMODE_DPLL_MPU			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_CKGEN_INST, 0x0060)
+#define DRA7XX_CM_IDLEST_DPLL_MPU_OFFSET		0x0064
+#define DRA7XX_CM_IDLEST_DPLL_MPU			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_CKGEN_INST, 0x0064)
+#define DRA7XX_CM_AUTOIDLE_DPLL_MPU_OFFSET		0x0068
+#define DRA7XX_CM_AUTOIDLE_DPLL_MPU			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_CKGEN_INST, 0x0068)
+#define DRA7XX_CM_CLKSEL_DPLL_MPU_OFFSET		0x006c
+#define DRA7XX_CM_CLKSEL_DPLL_MPU			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_CKGEN_INST, 0x006c)
+#define DRA7XX_CM_DIV_M2_DPLL_MPU_OFFSET		0x0070
+#define DRA7XX_CM_DIV_M2_DPLL_MPU			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_CKGEN_INST, 0x0070)
+#define DRA7XX_CM_SSC_DELTAMSTEP_DPLL_MPU_OFFSET	0x0088
+#define DRA7XX_CM_SSC_MODFREQDIV_DPLL_MPU_OFFSET	0x008c
+#define DRA7XX_CM_BYPCLK_DPLL_MPU_OFFSET		0x009c
+#define DRA7XX_CM_BYPCLK_DPLL_MPU			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_CKGEN_INST, 0x009c)
+#define DRA7XX_CM_CLKMODE_DPLL_IVA_OFFSET		0x00a0
+#define DRA7XX_CM_CLKMODE_DPLL_IVA			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_CKGEN_INST, 0x00a0)
+#define DRA7XX_CM_IDLEST_DPLL_IVA_OFFSET		0x00a4
+#define DRA7XX_CM_IDLEST_DPLL_IVA			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_CKGEN_INST, 0x00a4)
+#define DRA7XX_CM_AUTOIDLE_DPLL_IVA_OFFSET		0x00a8
+#define DRA7XX_CM_AUTOIDLE_DPLL_IVA			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_CKGEN_INST, 0x00a8)
+#define DRA7XX_CM_CLKSEL_DPLL_IVA_OFFSET		0x00ac
+#define DRA7XX_CM_CLKSEL_DPLL_IVA			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_CKGEN_INST, 0x00ac)
+#define DRA7XX_CM_DIV_M2_DPLL_IVA_OFFSET		0x00b0
+#define DRA7XX_CM_DIV_M2_DPLL_IVA			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_CKGEN_INST, 0x00b0)
+#define DRA7XX_CM_DIV_M3_DPLL_IVA_OFFSET		0x00b4
+#define DRA7XX_CM_DIV_M3_DPLL_IVA			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_CKGEN_INST, 0x00b4)
+#define DRA7XX_CM_SSC_DELTAMSTEP_DPLL_IVA_OFFSET	0x00c8
+#define DRA7XX_CM_SSC_MODFREQDIV_DPLL_IVA_OFFSET	0x00cc
+#define DRA7XX_CM_BYPCLK_DPLL_IVA_OFFSET		0x00dc
+#define DRA7XX_CM_BYPCLK_DPLL_IVA			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_CKGEN_INST, 0x00dc)
+#define DRA7XX_CM_CLKMODE_DPLL_ABE_OFFSET		0x00e0
+#define DRA7XX_CM_CLKMODE_DPLL_ABE			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_CKGEN_INST, 0x00e0)
+#define DRA7XX_CM_IDLEST_DPLL_ABE_OFFSET		0x00e4
+#define DRA7XX_CM_IDLEST_DPLL_ABE			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_CKGEN_INST, 0x00e4)
+#define DRA7XX_CM_AUTOIDLE_DPLL_ABE_OFFSET		0x00e8
+#define DRA7XX_CM_AUTOIDLE_DPLL_ABE			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_CKGEN_INST, 0x00e8)
+#define DRA7XX_CM_CLKSEL_DPLL_ABE_OFFSET		0x00ec
+#define DRA7XX_CM_CLKSEL_DPLL_ABE			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_CKGEN_INST, 0x00ec)
+#define DRA7XX_CM_DIV_M2_DPLL_ABE_OFFSET		0x00f0
+#define DRA7XX_CM_DIV_M2_DPLL_ABE			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_CKGEN_INST, 0x00f0)
+#define DRA7XX_CM_DIV_M3_DPLL_ABE_OFFSET		0x00f4
+#define DRA7XX_CM_DIV_M3_DPLL_ABE			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_CKGEN_INST, 0x00f4)
+#define DRA7XX_CM_SSC_DELTAMSTEP_DPLL_ABE_OFFSET	0x0108
+#define DRA7XX_CM_SSC_MODFREQDIV_DPLL_ABE_OFFSET	0x010c
+#define DRA7XX_CM_CLKMODE_DPLL_DDR_OFFSET		0x0110
+#define DRA7XX_CM_CLKMODE_DPLL_DDR			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_CKGEN_INST, 0x0110)
+#define DRA7XX_CM_IDLEST_DPLL_DDR_OFFSET		0x0114
+#define DRA7XX_CM_IDLEST_DPLL_DDR			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_CKGEN_INST, 0x0114)
+#define DRA7XX_CM_AUTOIDLE_DPLL_DDR_OFFSET		0x0118
+#define DRA7XX_CM_AUTOIDLE_DPLL_DDR			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_CKGEN_INST, 0x0118)
+#define DRA7XX_CM_CLKSEL_DPLL_DDR_OFFSET		0x011c
+#define DRA7XX_CM_CLKSEL_DPLL_DDR			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_CKGEN_INST, 0x011c)
+#define DRA7XX_CM_DIV_M2_DPLL_DDR_OFFSET		0x0120
+#define DRA7XX_CM_DIV_M2_DPLL_DDR			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_CKGEN_INST, 0x0120)
+#define DRA7XX_CM_DIV_M3_DPLL_DDR_OFFSET		0x0124
+#define DRA7XX_CM_DIV_M3_DPLL_DDR			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_CKGEN_INST, 0x0124)
+#define DRA7XX_CM_DIV_H11_DPLL_DDR_OFFSET		0x0128
+#define DRA7XX_CM_DIV_H11_DPLL_DDR			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_CKGEN_INST, 0x0128)
+#define DRA7XX_CM_SSC_DELTAMSTEP_DPLL_DDR_OFFSET	0x012c
+#define DRA7XX_CM_SSC_MODFREQDIV_DPLL_DDR_OFFSET	0x0130
+#define DRA7XX_CM_CLKMODE_DPLL_DSP_OFFSET		0x0134
+#define DRA7XX_CM_CLKMODE_DPLL_DSP			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_CKGEN_INST, 0x0134)
+#define DRA7XX_CM_IDLEST_DPLL_DSP_OFFSET		0x0138
+#define DRA7XX_CM_IDLEST_DPLL_DSP			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_CKGEN_INST, 0x0138)
+#define DRA7XX_CM_AUTOIDLE_DPLL_DSP_OFFSET		0x013c
+#define DRA7XX_CM_AUTOIDLE_DPLL_DSP			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_CKGEN_INST, 0x013c)
+#define DRA7XX_CM_CLKSEL_DPLL_DSP_OFFSET		0x0140
+#define DRA7XX_CM_CLKSEL_DPLL_DSP			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_CKGEN_INST, 0x0140)
+#define DRA7XX_CM_DIV_M2_DPLL_DSP_OFFSET		0x0144
+#define DRA7XX_CM_DIV_M2_DPLL_DSP			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_CKGEN_INST, 0x0144)
+#define DRA7XX_CM_DIV_M3_DPLL_DSP_OFFSET		0x0148
+#define DRA7XX_CM_DIV_M3_DPLL_DSP			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_CKGEN_INST, 0x0148)
+#define DRA7XX_CM_SSC_DELTAMSTEP_DPLL_DSP_OFFSET	0x014c
+#define DRA7XX_CM_SSC_MODFREQDIV_DPLL_DSP_OFFSET	0x0150
+#define DRA7XX_CM_BYPCLK_DPLL_DSP_OFFSET		0x0154
+#define DRA7XX_CM_BYPCLK_DPLL_DSP			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_CKGEN_INST, 0x0154)
+#define DRA7XX_CM_SHADOW_FREQ_CONFIG1_OFFSET		0x0160
+#define DRA7XX_CM_SHADOW_FREQ_CONFIG2_OFFSET		0x0164
+#define DRA7XX_CM_DYN_DEP_PRESCAL_OFFSET		0x0170
+#define DRA7XX_CM_RESTORE_ST_OFFSET			0x0180
+#define DRA7XX_CM_CLKMODE_DPLL_EVE_OFFSET		0x0184
+#define DRA7XX_CM_CLKMODE_DPLL_EVE			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_CKGEN_INST, 0x0184)
+#define DRA7XX_CM_IDLEST_DPLL_EVE_OFFSET		0x0188
+#define DRA7XX_CM_IDLEST_DPLL_EVE			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_CKGEN_INST, 0x0188)
+#define DRA7XX_CM_AUTOIDLE_DPLL_EVE_OFFSET		0x018c
+#define DRA7XX_CM_AUTOIDLE_DPLL_EVE			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_CKGEN_INST, 0x018c)
+#define DRA7XX_CM_CLKSEL_DPLL_EVE_OFFSET		0x0190
+#define DRA7XX_CM_CLKSEL_DPLL_EVE			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_CKGEN_INST, 0x0190)
+#define DRA7XX_CM_DIV_M2_DPLL_EVE_OFFSET		0x0194
+#define DRA7XX_CM_DIV_M2_DPLL_EVE			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_CKGEN_INST, 0x0194)
+#define DRA7XX_CM_DIV_M3_DPLL_EVE_OFFSET		0x0198
+#define DRA7XX_CM_DIV_M3_DPLL_EVE			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_CKGEN_INST, 0x0198)
+#define DRA7XX_CM_SSC_DELTAMSTEP_DPLL_EVE_OFFSET	0x019c
+#define DRA7XX_CM_SSC_MODFREQDIV_DPLL_EVE_OFFSET	0x01a0
+#define DRA7XX_CM_BYPCLK_DPLL_EVE_OFFSET		0x01a4
+#define DRA7XX_CM_BYPCLK_DPLL_EVE			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_CKGEN_INST, 0x01a4)
+#define DRA7XX_CM_CLKMODE_DPLL_GMAC_OFFSET		0x01a8
+#define DRA7XX_CM_CLKMODE_DPLL_GMAC			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_CKGEN_INST, 0x01a8)
+#define DRA7XX_CM_IDLEST_DPLL_GMAC_OFFSET		0x01ac
+#define DRA7XX_CM_IDLEST_DPLL_GMAC			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_CKGEN_INST, 0x01ac)
+#define DRA7XX_CM_AUTOIDLE_DPLL_GMAC_OFFSET		0x01b0
+#define DRA7XX_CM_AUTOIDLE_DPLL_GMAC			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_CKGEN_INST, 0x01b0)
+#define DRA7XX_CM_CLKSEL_DPLL_GMAC_OFFSET		0x01b4
+#define DRA7XX_CM_CLKSEL_DPLL_GMAC			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_CKGEN_INST, 0x01b4)
+#define DRA7XX_CM_DIV_M2_DPLL_GMAC_OFFSET		0x01b8
+#define DRA7XX_CM_DIV_M2_DPLL_GMAC			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_CKGEN_INST, 0x01b8)
+#define DRA7XX_CM_DIV_M3_DPLL_GMAC_OFFSET		0x01bc
+#define DRA7XX_CM_DIV_M3_DPLL_GMAC			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_CKGEN_INST, 0x01bc)
+#define DRA7XX_CM_DIV_H11_DPLL_GMAC_OFFSET		0x01c0
+#define DRA7XX_CM_DIV_H11_DPLL_GMAC			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_CKGEN_INST, 0x01c0)
+#define DRA7XX_CM_DIV_H12_DPLL_GMAC_OFFSET		0x01c4
+#define DRA7XX_CM_DIV_H12_DPLL_GMAC			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_CKGEN_INST, 0x01c4)
+#define DRA7XX_CM_DIV_H13_DPLL_GMAC_OFFSET		0x01c8
+#define DRA7XX_CM_DIV_H13_DPLL_GMAC			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_CKGEN_INST, 0x01c8)
+#define DRA7XX_CM_DIV_H14_DPLL_GMAC_OFFSET		0x01cc
+#define DRA7XX_CM_DIV_H14_DPLL_GMAC			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_CKGEN_INST, 0x01cc)
+#define DRA7XX_CM_SSC_DELTAMSTEP_DPLL_GMAC_OFFSET	0x01d0
+#define DRA7XX_CM_SSC_MODFREQDIV_DPLL_GMAC_OFFSET	0x01d4
+#define DRA7XX_CM_CLKMODE_DPLL_GPU_OFFSET		0x01d8
+#define DRA7XX_CM_CLKMODE_DPLL_GPU			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_CKGEN_INST, 0x01d8)
+#define DRA7XX_CM_IDLEST_DPLL_GPU_OFFSET		0x01dc
+#define DRA7XX_CM_IDLEST_DPLL_GPU			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_CKGEN_INST, 0x01dc)
+#define DRA7XX_CM_AUTOIDLE_DPLL_GPU_OFFSET		0x01e0
+#define DRA7XX_CM_AUTOIDLE_DPLL_GPU			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_CKGEN_INST, 0x01e0)
+#define DRA7XX_CM_CLKSEL_DPLL_GPU_OFFSET		0x01e4
+#define DRA7XX_CM_CLKSEL_DPLL_GPU			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_CKGEN_INST, 0x01e4)
+#define DRA7XX_CM_DIV_M2_DPLL_GPU_OFFSET		0x01e8
+#define DRA7XX_CM_DIV_M2_DPLL_GPU			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_CKGEN_INST, 0x01e8)
+#define DRA7XX_CM_DIV_M3_DPLL_GPU_OFFSET		0x01ec
+#define DRA7XX_CM_DIV_M3_DPLL_GPU			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_CKGEN_INST, 0x01ec)
+#define DRA7XX_CM_SSC_DELTAMSTEP_DPLL_GPU_OFFSET	0x01f0
+#define DRA7XX_CM_SSC_MODFREQDIV_DPLL_GPU_OFFSET	0x01f4
+
+/* CM_CORE_AON.MPU_CM_CORE_AON register offsets */
+#define DRA7XX_CM_MPU_CLKSTCTRL_OFFSET			0x0000
+#define DRA7XX_CM_MPU_STATICDEP_OFFSET			0x0004
+#define DRA7XX_CM_MPU_DYNAMICDEP_OFFSET			0x0008
+#define DRA7XX_CM_MPU_MPU_CLKCTRL_OFFSET		0x0020
+#define DRA7XX_CM_MPU_MPU_CLKCTRL			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_MPU_INST, 0x0020)
+#define DRA7XX_CM_MPU_MPU_MPU_DBG_CLKCTRL_OFFSET	0x0028
+#define DRA7XX_CM_MPU_MPU_MPU_DBG_CLKCTRL		DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_MPU_INST, 0x0028)
+
+/* CM_CORE_AON.DSP1_CM_CORE_AON register offsets */
+#define DRA7XX_CM_DSP1_CLKSTCTRL_OFFSET			0x0000
+#define DRA7XX_CM_DSP1_STATICDEP_OFFSET			0x0004
+#define DRA7XX_CM_DSP1_DYNAMICDEP_OFFSET		0x0008
+#define DRA7XX_CM_DSP1_DSP1_CLKCTRL_OFFSET		0x0020
+#define DRA7XX_CM_DSP1_DSP1_CLKCTRL			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_DSP1_INST, 0x0020)
+
+/* CM_CORE_AON.IPU_CM_CORE_AON register offsets */
+#define DRA7XX_CM_IPU1_CLKSTCTRL_OFFSET			0x0000
+#define DRA7XX_CM_IPU1_STATICDEP_OFFSET			0x0004
+#define DRA7XX_CM_IPU1_DYNAMICDEP_OFFSET		0x0008
+#define DRA7XX_CM_IPU1_IPU1_CLKCTRL_OFFSET		0x0020
+#define DRA7XX_CM_IPU1_IPU1_CLKCTRL			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_IPU_INST, 0x0020)
+#define DRA7XX_CM_IPU_CLKSTCTRL_OFFSET			0x0040
+#define DRA7XX_CM_IPU_MCASP1_CLKCTRL_OFFSET		0x0050
+#define DRA7XX_CM_IPU_MCASP1_CLKCTRL			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_IPU_INST, 0x0050)
+#define DRA7XX_CM_IPU_TIMER5_CLKCTRL_OFFSET		0x0058
+#define DRA7XX_CM_IPU_TIMER5_CLKCTRL			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_IPU_INST, 0x0058)
+#define DRA7XX_CM_IPU_TIMER6_CLKCTRL_OFFSET		0x0060
+#define DRA7XX_CM_IPU_TIMER6_CLKCTRL			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_IPU_INST, 0x0060)
+#define DRA7XX_CM_IPU_TIMER7_CLKCTRL_OFFSET		0x0068
+#define DRA7XX_CM_IPU_TIMER7_CLKCTRL			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_IPU_INST, 0x0068)
+#define DRA7XX_CM_IPU_TIMER8_CLKCTRL_OFFSET		0x0070
+#define DRA7XX_CM_IPU_TIMER8_CLKCTRL			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_IPU_INST, 0x0070)
+#define DRA7XX_CM_IPU_I2C5_CLKCTRL_OFFSET		0x0078
+#define DRA7XX_CM_IPU_I2C5_CLKCTRL			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_IPU_INST, 0x0078)
+#define DRA7XX_CM_IPU_UART6_CLKCTRL_OFFSET		0x0080
+#define DRA7XX_CM_IPU_UART6_CLKCTRL			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_IPU_INST, 0x0080)
+
+/* CM_CORE_AON.DSP2_CM_CORE_AON register offsets */
+#define DRA7XX_CM_DSP2_CLKSTCTRL_OFFSET			0x0000
+#define DRA7XX_CM_DSP2_STATICDEP_OFFSET			0x0004
+#define DRA7XX_CM_DSP2_DYNAMICDEP_OFFSET		0x0008
+#define DRA7XX_CM_DSP2_DSP2_CLKCTRL_OFFSET		0x0020
+#define DRA7XX_CM_DSP2_DSP2_CLKCTRL			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_DSP2_INST, 0x0020)
+
+/* CM_CORE_AON.EVE1_CM_CORE_AON register offsets */
+#define DRA7XX_CM_EVE1_CLKSTCTRL_OFFSET			0x0000
+#define DRA7XX_CM_EVE1_STATICDEP_OFFSET			0x0004
+#define DRA7XX_CM_EVE1_EVE1_CLKCTRL_OFFSET		0x0020
+#define DRA7XX_CM_EVE1_EVE1_CLKCTRL			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_EVE1_INST, 0x0020)
+
+/* CM_CORE_AON.EVE2_CM_CORE_AON register offsets */
+#define DRA7XX_CM_EVE2_CLKSTCTRL_OFFSET			0x0000
+#define DRA7XX_CM_EVE2_STATICDEP_OFFSET			0x0004
+#define DRA7XX_CM_EVE2_EVE2_CLKCTRL_OFFSET		0x0020
+#define DRA7XX_CM_EVE2_EVE2_CLKCTRL			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_EVE2_INST, 0x0020)
+
+/* CM_CORE_AON.EVE3_CM_CORE_AON register offsets */
+#define DRA7XX_CM_EVE3_CLKSTCTRL_OFFSET			0x0000
+#define DRA7XX_CM_EVE3_STATICDEP_OFFSET			0x0004
+#define DRA7XX_CM_EVE3_EVE3_CLKCTRL_OFFSET		0x0020
+#define DRA7XX_CM_EVE3_EVE3_CLKCTRL			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_EVE3_INST, 0x0020)
+
+/* CM_CORE_AON.EVE4_CM_CORE_AON register offsets */
+#define DRA7XX_CM_EVE4_CLKSTCTRL_OFFSET			0x0000
+#define DRA7XX_CM_EVE4_STATICDEP_OFFSET			0x0004
+#define DRA7XX_CM_EVE4_EVE4_CLKCTRL_OFFSET		0x0020
+#define DRA7XX_CM_EVE4_EVE4_CLKCTRL			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_EVE4_INST, 0x0020)
+
+/* CM_CORE_AON.RTC_CM_CORE_AON register offsets */
+#define DRA7XX_CM_RTC_CLKSTCTRL_OFFSET			0x0000
+#define DRA7XX_CM_RTC_RTCSS_CLKCTRL_OFFSET		0x0004
+#define DRA7XX_CM_RTC_RTCSS_CLKCTRL			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_RTC_INST, 0x0004)
+
+/* CM_CORE_AON.VPE_CM_CORE_AON register offsets */
+#define DRA7XX_CM_VPE_CLKSTCTRL_OFFSET			0x0000
+#define DRA7XX_CM_VPE_VPE_CLKCTRL_OFFSET		0x0004
+#define DRA7XX_CM_VPE_VPE_CLKCTRL			DRA7XX_CM_CORE_AON_REGADDR(DRA7XX_CM_CORE_AON_VPE_INST, 0x0004)
+#define DRA7XX_CM_VPE_STATICDEP_OFFSET			0x0008
+
+#endif
diff --git a/arch/arm/mach-omap2/cm2_7xx.h b/arch/arm/mach-omap2/cm2_7xx.h
new file mode 100644
index 000000000000..9ad7594e7622
--- /dev/null
+++ b/arch/arm/mach-omap2/cm2_7xx.h
@@ -0,0 +1,513 @@
+/*
+ * DRA7xx CM2 instance offset macros
+ *
+ * Copyright (C) 2013 Texas Instruments Incorporated - http://www.ti.com
+ *
+ * Generated by code originally written by:
+ * Paul Walmsley (paul@pwsan.com)
+ * Rajendra Nayak (rnayak@ti.com)
+ * Benoit Cousson (b-cousson@ti.com)
+ *
+ * This file is automatically generated from the OMAP hardware databases.
+ * We respectfully ask that any modifications to this file be coordinated
+ * with the public linux-omap@vger.kernel.org mailing list and the
+ * authors above to ensure that the autogeneration scripts are kept
+ * up-to-date with the file contents.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __ARCH_ARM_MACH_OMAP2_CM2_7XX_H
+#define __ARCH_ARM_MACH_OMAP2_CM2_7XX_H
+
+#include "cm_44xx_54xx.h"
+
+/* CM2 base address */
+#define DRA7XX_CM_CORE_BASE		0x4a008000
+
+#define DRA7XX_CM_CORE_REGADDR(inst, reg)				\
+	OMAP2_L4_IO_ADDRESS(DRA7XX_CM_CORE_BASE + (inst) + (reg))
+
+/* CM_CORE instances */
+#define DRA7XX_CM_CORE_OCP_SOCKET_INST	0x0000
+#define DRA7XX_CM_CORE_CKGEN_INST	0x0104
+#define DRA7XX_CM_CORE_COREAON_INST	0x0600
+#define DRA7XX_CM_CORE_CORE_INST	0x0700
+#define DRA7XX_CM_CORE_IVA_INST		0x0f00
+#define DRA7XX_CM_CORE_CAM_INST		0x1000
+#define DRA7XX_CM_CORE_DSS_INST		0x1100
+#define DRA7XX_CM_CORE_GPU_INST		0x1200
+#define DRA7XX_CM_CORE_L3INIT_INST	0x1300
+#define DRA7XX_CM_CORE_CUSTEFUSE_INST	0x1600
+#define DRA7XX_CM_CORE_L4PER_INST	0x1700
+#define DRA7XX_CM_CORE_RESTORE_INST	0x1e18
+
+/* CM_CORE clockdomain register offsets (from instance start) */
+#define DRA7XX_CM_CORE_COREAON_COREAON_CDOFFS		0x0000
+#define DRA7XX_CM_CORE_CORE_L3MAIN1_CDOFFS		0x0000
+#define DRA7XX_CM_CORE_CORE_IPU2_CDOFFS			0x0200
+#define DRA7XX_CM_CORE_CORE_DMA_CDOFFS			0x0300
+#define DRA7XX_CM_CORE_CORE_EMIF_CDOFFS			0x0400
+#define DRA7XX_CM_CORE_CORE_ATL_CDOFFS			0x0520
+#define DRA7XX_CM_CORE_CORE_L4CFG_CDOFFS		0x0600
+#define DRA7XX_CM_CORE_CORE_L3INSTR_CDOFFS		0x0700
+#define DRA7XX_CM_CORE_IVA_IVA_CDOFFS			0x0000
+#define DRA7XX_CM_CORE_CAM_CAM_CDOFFS			0x0000
+#define DRA7XX_CM_CORE_DSS_DSS_CDOFFS			0x0000
+#define DRA7XX_CM_CORE_GPU_GPU_CDOFFS			0x0000
+#define DRA7XX_CM_CORE_L3INIT_L3INIT_CDOFFS		0x0000
+#define DRA7XX_CM_CORE_L3INIT_PCIE_CDOFFS		0x00a0
+#define DRA7XX_CM_CORE_L3INIT_GMAC_CDOFFS		0x00c0
+#define DRA7XX_CM_CORE_CUSTEFUSE_CUSTEFUSE_CDOFFS	0x0000
+#define DRA7XX_CM_CORE_L4PER_L4PER_CDOFFS		0x0000
+#define DRA7XX_CM_CORE_L4PER_L4SEC_CDOFFS		0x0180
+#define DRA7XX_CM_CORE_L4PER_L4PER2_CDOFFS		0x01fc
+#define DRA7XX_CM_CORE_L4PER_L4PER3_CDOFFS		0x0210
+
+/* CM_CORE */
+
+/* CM_CORE.OCP_SOCKET_CM_CORE register offsets */
+#define DRA7XX_REVISION_CM_CORE_OFFSET				0x0000
+#define DRA7XX_CM_CM_CORE_PROFILING_CLKCTRL_OFFSET		0x0040
+#define DRA7XX_CM_CM_CORE_PROFILING_CLKCTRL			DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_OCP_SOCKET_INST, 0x0040)
+#define DRA7XX_CM_CORE_DEBUG_CFG_OFFSET				0x00f0
+
+/* CM_CORE.CKGEN_CM_CORE register offsets */
+#define DRA7XX_CM_CLKSEL_USB_60MHZ_OFFSET			0x0000
+#define DRA7XX_CM_CLKSEL_USB_60MHZ				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CKGEN_INST, 0x0000)
+#define DRA7XX_CM_CLKMODE_DPLL_PER_OFFSET			0x003c
+#define DRA7XX_CM_CLKMODE_DPLL_PER				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CKGEN_INST, 0x003c)
+#define DRA7XX_CM_IDLEST_DPLL_PER_OFFSET			0x0040
+#define DRA7XX_CM_IDLEST_DPLL_PER				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CKGEN_INST, 0x0040)
+#define DRA7XX_CM_AUTOIDLE_DPLL_PER_OFFSET			0x0044
+#define DRA7XX_CM_AUTOIDLE_DPLL_PER				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CKGEN_INST, 0x0044)
+#define DRA7XX_CM_CLKSEL_DPLL_PER_OFFSET			0x0048
+#define DRA7XX_CM_CLKSEL_DPLL_PER				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CKGEN_INST, 0x0048)
+#define DRA7XX_CM_DIV_M2_DPLL_PER_OFFSET			0x004c
+#define DRA7XX_CM_DIV_M2_DPLL_PER				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CKGEN_INST, 0x004c)
+#define DRA7XX_CM_DIV_M3_DPLL_PER_OFFSET			0x0050
+#define DRA7XX_CM_DIV_M3_DPLL_PER				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CKGEN_INST, 0x0050)
+#define DRA7XX_CM_DIV_H11_DPLL_PER_OFFSET			0x0054
+#define DRA7XX_CM_DIV_H11_DPLL_PER				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CKGEN_INST, 0x0054)
+#define DRA7XX_CM_DIV_H12_DPLL_PER_OFFSET			0x0058
+#define DRA7XX_CM_DIV_H12_DPLL_PER				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CKGEN_INST, 0x0058)
+#define DRA7XX_CM_DIV_H13_DPLL_PER_OFFSET			0x005c
+#define DRA7XX_CM_DIV_H13_DPLL_PER				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CKGEN_INST, 0x005c)
+#define DRA7XX_CM_DIV_H14_DPLL_PER_OFFSET			0x0060
+#define DRA7XX_CM_DIV_H14_DPLL_PER				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CKGEN_INST, 0x0060)
+#define DRA7XX_CM_SSC_DELTAMSTEP_DPLL_PER_OFFSET		0x0064
+#define DRA7XX_CM_SSC_MODFREQDIV_DPLL_PER_OFFSET		0x0068
+#define DRA7XX_CM_CLKMODE_DPLL_USB_OFFSET			0x007c
+#define DRA7XX_CM_CLKMODE_DPLL_USB				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CKGEN_INST, 0x007c)
+#define DRA7XX_CM_IDLEST_DPLL_USB_OFFSET			0x0080
+#define DRA7XX_CM_IDLEST_DPLL_USB				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CKGEN_INST, 0x0080)
+#define DRA7XX_CM_AUTOIDLE_DPLL_USB_OFFSET			0x0084
+#define DRA7XX_CM_AUTOIDLE_DPLL_USB				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CKGEN_INST, 0x0084)
+#define DRA7XX_CM_CLKSEL_DPLL_USB_OFFSET			0x0088
+#define DRA7XX_CM_CLKSEL_DPLL_USB				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CKGEN_INST, 0x0088)
+#define DRA7XX_CM_DIV_M2_DPLL_USB_OFFSET			0x008c
+#define DRA7XX_CM_DIV_M2_DPLL_USB				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CKGEN_INST, 0x008c)
+#define DRA7XX_CM_SSC_DELTAMSTEP_DPLL_USB_OFFSET		0x00a4
+#define DRA7XX_CM_SSC_MODFREQDIV_DPLL_USB_OFFSET		0x00a8
+#define DRA7XX_CM_CLKDCOLDO_DPLL_USB_OFFSET			0x00b0
+#define DRA7XX_CM_CLKDCOLDO_DPLL_USB				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CKGEN_INST, 0x00b0)
+#define DRA7XX_CM_CLKMODE_DPLL_PCIE_REF_OFFSET			0x00fc
+#define DRA7XX_CM_CLKMODE_DPLL_PCIE_REF				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CKGEN_INST, 0x00fc)
+#define DRA7XX_CM_IDLEST_DPLL_PCIE_REF_OFFSET			0x0100
+#define DRA7XX_CM_IDLEST_DPLL_PCIE_REF				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CKGEN_INST, 0x0100)
+#define DRA7XX_CM_AUTOIDLE_DPLL_PCIE_REF_OFFSET			0x0104
+#define DRA7XX_CM_AUTOIDLE_DPLL_PCIE_REF			DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CKGEN_INST, 0x0104)
+#define DRA7XX_CM_CLKSEL_DPLL_PCIE_REF_OFFSET			0x0108
+#define DRA7XX_CM_CLKSEL_DPLL_PCIE_REF				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CKGEN_INST, 0x0108)
+#define DRA7XX_CM_DIV_M2_DPLL_PCIE_REF_OFFSET			0x010c
+#define DRA7XX_CM_DIV_M2_DPLL_PCIE_REF				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CKGEN_INST, 0x010c)
+#define DRA7XX_CM_SSC_DELTAMSTEP_DPLL_PCIE_REF_OFFSET		0x0110
+#define DRA7XX_CM_SSC_MODFREQDIV_DPLL_PCIE_REF_OFFSET		0x0114
+#define DRA7XX_CM_CLKMODE_APLL_PCIE_OFFSET			0x0118
+#define DRA7XX_CM_CLKMODE_APLL_PCIE				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CKGEN_INST, 0x0118)
+#define DRA7XX_CM_IDLEST_APLL_PCIE_OFFSET			0x011c
+#define DRA7XX_CM_IDLEST_APLL_PCIE				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CKGEN_INST, 0x011c)
+#define DRA7XX_CM_DIV_M2_APLL_PCIE_OFFSET			0x0120
+#define DRA7XX_CM_DIV_M2_APLL_PCIE				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CKGEN_INST, 0x0120)
+#define DRA7XX_CM_CLKVCOLDO_APLL_PCIE_OFFSET			0x0124
+#define DRA7XX_CM_CLKVCOLDO_APLL_PCIE				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CKGEN_INST, 0x0124)
+
+/* CM_CORE.COREAON_CM_CORE register offsets */
+#define DRA7XX_CM_COREAON_CLKSTCTRL_OFFSET			0x0000
+#define DRA7XX_CM_COREAON_SMARTREFLEX_MPU_CLKCTRL_OFFSET	0x0028
+#define DRA7XX_CM_COREAON_SMARTREFLEX_MPU_CLKCTRL		DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_COREAON_INST, 0x0028)
+#define DRA7XX_CM_COREAON_SMARTREFLEX_CORE_CLKCTRL_OFFSET	0x0038
+#define DRA7XX_CM_COREAON_SMARTREFLEX_CORE_CLKCTRL		DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_COREAON_INST, 0x0038)
+#define DRA7XX_CM_COREAON_USB_PHY1_CORE_CLKCTRL_OFFSET		0x0040
+#define DRA7XX_CM_COREAON_USB_PHY1_CORE_CLKCTRL			DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_COREAON_INST, 0x0040)
+#define DRA7XX_CM_COREAON_IO_SRCOMP_CLKCTRL_OFFSET		0x0050
+#define DRA7XX_CM_COREAON_IO_SRCOMP_CLKCTRL			DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_COREAON_INST, 0x0050)
+#define DRA7XX_CM_COREAON_SMARTREFLEX_GPU_CLKCTRL_OFFSET	0x0058
+#define DRA7XX_CM_COREAON_SMARTREFLEX_GPU_CLKCTRL		DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_COREAON_INST, 0x0058)
+#define DRA7XX_CM_COREAON_SMARTREFLEX_DSPEVE_CLKCTRL_OFFSET	0x0068
+#define DRA7XX_CM_COREAON_SMARTREFLEX_DSPEVE_CLKCTRL		DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_COREAON_INST, 0x0068)
+#define DRA7XX_CM_COREAON_SMARTREFLEX_IVAHD_CLKCTRL_OFFSET	0x0078
+#define DRA7XX_CM_COREAON_SMARTREFLEX_IVAHD_CLKCTRL		DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_COREAON_INST, 0x0078)
+#define DRA7XX_CM_COREAON_USB_PHY2_CORE_CLKCTRL_OFFSET		0x0088
+#define DRA7XX_CM_COREAON_USB_PHY2_CORE_CLKCTRL			DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_COREAON_INST, 0x0088)
+#define DRA7XX_CM_COREAON_USB_PHY3_CORE_CLKCTRL_OFFSET		0x0098
+#define DRA7XX_CM_COREAON_USB_PHY3_CORE_CLKCTRL			DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_COREAON_INST, 0x0098)
+#define DRA7XX_CM_COREAON_DUMMY_MODULE1_CLKCTRL_OFFSET		0x00a0
+#define DRA7XX_CM_COREAON_DUMMY_MODULE1_CLKCTRL			DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_COREAON_INST, 0x00a0)
+#define DRA7XX_CM_COREAON_DUMMY_MODULE2_CLKCTRL_OFFSET		0x00b0
+#define DRA7XX_CM_COREAON_DUMMY_MODULE2_CLKCTRL			DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_COREAON_INST, 0x00b0)
+#define DRA7XX_CM_COREAON_DUMMY_MODULE3_CLKCTRL_OFFSET		0x00c0
+#define DRA7XX_CM_COREAON_DUMMY_MODULE3_CLKCTRL			DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_COREAON_INST, 0x00c0)
+#define DRA7XX_CM_COREAON_DUMMY_MODULE4_CLKCTRL_OFFSET		0x00d0
+#define DRA7XX_CM_COREAON_DUMMY_MODULE4_CLKCTRL			DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_COREAON_INST, 0x00d0)
+
+/* CM_CORE.CORE_CM_CORE register offsets */
+#define DRA7XX_CM_L3MAIN1_CLKSTCTRL_OFFSET			0x0000
+#define DRA7XX_CM_L3MAIN1_DYNAMICDEP_OFFSET			0x0008
+#define DRA7XX_CM_L3MAIN1_L3_MAIN_1_CLKCTRL_OFFSET		0x0020
+#define DRA7XX_CM_L3MAIN1_L3_MAIN_1_CLKCTRL			DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CORE_INST, 0x0020)
+#define DRA7XX_CM_L3MAIN1_GPMC_CLKCTRL_OFFSET			0x0028
+#define DRA7XX_CM_L3MAIN1_GPMC_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CORE_INST, 0x0028)
+#define DRA7XX_CM_L3MAIN1_MMU_EDMA_CLKCTRL_OFFSET		0x0030
+#define DRA7XX_CM_L3MAIN1_MMU_EDMA_CLKCTRL			DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CORE_INST, 0x0030)
+#define DRA7XX_CM_L3MAIN1_OCMC_RAM1_CLKCTRL_OFFSET		0x0050
+#define DRA7XX_CM_L3MAIN1_OCMC_RAM1_CLKCTRL			DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CORE_INST, 0x0050)
+#define DRA7XX_CM_L3MAIN1_OCMC_RAM2_CLKCTRL_OFFSET		0x0058
+#define DRA7XX_CM_L3MAIN1_OCMC_RAM2_CLKCTRL			DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CORE_INST, 0x0058)
+#define DRA7XX_CM_L3MAIN1_OCMC_RAM3_CLKCTRL_OFFSET		0x0060
+#define DRA7XX_CM_L3MAIN1_OCMC_RAM3_CLKCTRL			DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CORE_INST, 0x0060)
+#define DRA7XX_CM_L3MAIN1_OCMC_ROM_CLKCTRL_OFFSET		0x0068
+#define DRA7XX_CM_L3MAIN1_OCMC_ROM_CLKCTRL			DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CORE_INST, 0x0068)
+#define DRA7XX_CM_L3MAIN1_TPCC_CLKCTRL_OFFSET			0x0070
+#define DRA7XX_CM_L3MAIN1_TPCC_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CORE_INST, 0x0070)
+#define DRA7XX_CM_L3MAIN1_TPTC1_CLKCTRL_OFFSET			0x0078
+#define DRA7XX_CM_L3MAIN1_TPTC1_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CORE_INST, 0x0078)
+#define DRA7XX_CM_L3MAIN1_TPTC2_CLKCTRL_OFFSET			0x0080
+#define DRA7XX_CM_L3MAIN1_TPTC2_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CORE_INST, 0x0080)
+#define DRA7XX_CM_L3MAIN1_VCP1_CLKCTRL_OFFSET			0x0088
+#define DRA7XX_CM_L3MAIN1_VCP1_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CORE_INST, 0x0088)
+#define DRA7XX_CM_L3MAIN1_VCP2_CLKCTRL_OFFSET			0x0090
+#define DRA7XX_CM_L3MAIN1_VCP2_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CORE_INST, 0x0090)
+#define DRA7XX_CM_L3MAIN1_SPARE_CME_CLKCTRL_OFFSET		0x0098
+#define DRA7XX_CM_L3MAIN1_SPARE_CME_CLKCTRL			DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CORE_INST, 0x0098)
+#define DRA7XX_CM_L3MAIN1_SPARE_HDMI_CLKCTRL_OFFSET		0x00a0
+#define DRA7XX_CM_L3MAIN1_SPARE_HDMI_CLKCTRL			DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CORE_INST, 0x00a0)
+#define DRA7XX_CM_L3MAIN1_SPARE_ICM_CLKCTRL_OFFSET		0x00a8
+#define DRA7XX_CM_L3MAIN1_SPARE_ICM_CLKCTRL			DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CORE_INST, 0x00a8)
+#define DRA7XX_CM_L3MAIN1_SPARE_IVA2_CLKCTRL_OFFSET		0x00b0
+#define DRA7XX_CM_L3MAIN1_SPARE_IVA2_CLKCTRL			DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CORE_INST, 0x00b0)
+#define DRA7XX_CM_L3MAIN1_SPARE_SATA2_CLKCTRL_OFFSET		0x00b8
+#define DRA7XX_CM_L3MAIN1_SPARE_SATA2_CLKCTRL			DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CORE_INST, 0x00b8)
+#define DRA7XX_CM_L3MAIN1_SPARE_UNKNOWN4_CLKCTRL_OFFSET		0x00c0
+#define DRA7XX_CM_L3MAIN1_SPARE_UNKNOWN4_CLKCTRL		DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CORE_INST, 0x00c0)
+#define DRA7XX_CM_L3MAIN1_SPARE_UNKNOWN5_CLKCTRL_OFFSET		0x00c8
+#define DRA7XX_CM_L3MAIN1_SPARE_UNKNOWN5_CLKCTRL		DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CORE_INST, 0x00c8)
+#define DRA7XX_CM_L3MAIN1_SPARE_UNKNOWN6_CLKCTRL_OFFSET		0x00d0
+#define DRA7XX_CM_L3MAIN1_SPARE_UNKNOWN6_CLKCTRL		DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CORE_INST, 0x00d0)
+#define DRA7XX_CM_L3MAIN1_SPARE_VIDEOPLL1_CLKCTRL_OFFSET	0x00d8
+#define DRA7XX_CM_L3MAIN1_SPARE_VIDEOPLL1_CLKCTRL		DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CORE_INST, 0x00d8)
+#define DRA7XX_CM_L3MAIN1_SPARE_VIDEOPLL2_CLKCTRL_OFFSET	0x00f0
+#define DRA7XX_CM_L3MAIN1_SPARE_VIDEOPLL2_CLKCTRL		DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CORE_INST, 0x00f0)
+#define DRA7XX_CM_L3MAIN1_SPARE_VIDEOPLL3_CLKCTRL_OFFSET	0x00f8
+#define DRA7XX_CM_L3MAIN1_SPARE_VIDEOPLL3_CLKCTRL		DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CORE_INST, 0x00f8)
+#define DRA7XX_CM_IPU2_CLKSTCTRL_OFFSET				0x0200
+#define DRA7XX_CM_IPU2_STATICDEP_OFFSET				0x0204
+#define DRA7XX_CM_IPU2_DYNAMICDEP_OFFSET			0x0208
+#define DRA7XX_CM_IPU2_IPU2_CLKCTRL_OFFSET			0x0220
+#define DRA7XX_CM_IPU2_IPU2_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CORE_INST, 0x0220)
+#define DRA7XX_CM_DMA_CLKSTCTRL_OFFSET				0x0300
+#define DRA7XX_CM_DMA_STATICDEP_OFFSET				0x0304
+#define DRA7XX_CM_DMA_DYNAMICDEP_OFFSET				0x0308
+#define DRA7XX_CM_DMA_DMA_SYSTEM_CLKCTRL_OFFSET			0x0320
+#define DRA7XX_CM_DMA_DMA_SYSTEM_CLKCTRL			DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CORE_INST, 0x0320)
+#define DRA7XX_CM_EMIF_CLKSTCTRL_OFFSET				0x0400
+#define DRA7XX_CM_EMIF_DMM_CLKCTRL_OFFSET			0x0420
+#define DRA7XX_CM_EMIF_DMM_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CORE_INST, 0x0420)
+#define DRA7XX_CM_EMIF_EMIF_OCP_FW_CLKCTRL_OFFSET		0x0428
+#define DRA7XX_CM_EMIF_EMIF_OCP_FW_CLKCTRL			DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CORE_INST, 0x0428)
+#define DRA7XX_CM_EMIF_EMIF1_CLKCTRL_OFFSET			0x0430
+#define DRA7XX_CM_EMIF_EMIF1_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CORE_INST, 0x0430)
+#define DRA7XX_CM_EMIF_EMIF2_CLKCTRL_OFFSET			0x0438
+#define DRA7XX_CM_EMIF_EMIF2_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CORE_INST, 0x0438)
+#define DRA7XX_CM_EMIF_EMIF_DLL_CLKCTRL_OFFSET			0x0440
+#define DRA7XX_CM_EMIF_EMIF_DLL_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CORE_INST, 0x0440)
+#define DRA7XX_CM_ATL_ATL_CLKCTRL_OFFSET			0x0500
+#define DRA7XX_CM_ATL_ATL_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CORE_INST, 0x0500)
+#define DRA7XX_CM_ATL_CLKSTCTRL_OFFSET				0x0520
+#define DRA7XX_CM_L4CFG_CLKSTCTRL_OFFSET			0x0600
+#define DRA7XX_CM_L4CFG_DYNAMICDEP_OFFSET			0x0608
+#define DRA7XX_CM_L4CFG_L4_CFG_CLKCTRL_OFFSET			0x0620
+#define DRA7XX_CM_L4CFG_L4_CFG_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CORE_INST, 0x0620)
+#define DRA7XX_CM_L4CFG_SPINLOCK_CLKCTRL_OFFSET			0x0628
+#define DRA7XX_CM_L4CFG_SPINLOCK_CLKCTRL			DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CORE_INST, 0x0628)
+#define DRA7XX_CM_L4CFG_MAILBOX1_CLKCTRL_OFFSET			0x0630
+#define DRA7XX_CM_L4CFG_MAILBOX1_CLKCTRL			DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CORE_INST, 0x0630)
+#define DRA7XX_CM_L4CFG_SAR_ROM_CLKCTRL_OFFSET			0x0638
+#define DRA7XX_CM_L4CFG_SAR_ROM_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CORE_INST, 0x0638)
+#define DRA7XX_CM_L4CFG_OCP2SCP2_CLKCTRL_OFFSET			0x0640
+#define DRA7XX_CM_L4CFG_OCP2SCP2_CLKCTRL			DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CORE_INST, 0x0640)
+#define DRA7XX_CM_L4CFG_MAILBOX2_CLKCTRL_OFFSET			0x0648
+#define DRA7XX_CM_L4CFG_MAILBOX2_CLKCTRL			DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CORE_INST, 0x0648)
+#define DRA7XX_CM_L4CFG_MAILBOX3_CLKCTRL_OFFSET			0x0650
+#define DRA7XX_CM_L4CFG_MAILBOX3_CLKCTRL			DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CORE_INST, 0x0650)
+#define DRA7XX_CM_L4CFG_MAILBOX4_CLKCTRL_OFFSET			0x0658
+#define DRA7XX_CM_L4CFG_MAILBOX4_CLKCTRL			DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CORE_INST, 0x0658)
+#define DRA7XX_CM_L4CFG_MAILBOX5_CLKCTRL_OFFSET			0x0660
+#define DRA7XX_CM_L4CFG_MAILBOX5_CLKCTRL			DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CORE_INST, 0x0660)
+#define DRA7XX_CM_L4CFG_MAILBOX6_CLKCTRL_OFFSET			0x0668
+#define DRA7XX_CM_L4CFG_MAILBOX6_CLKCTRL			DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CORE_INST, 0x0668)
+#define DRA7XX_CM_L4CFG_MAILBOX7_CLKCTRL_OFFSET			0x0670
+#define DRA7XX_CM_L4CFG_MAILBOX7_CLKCTRL			DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CORE_INST, 0x0670)
+#define DRA7XX_CM_L4CFG_MAILBOX8_CLKCTRL_OFFSET			0x0678
+#define DRA7XX_CM_L4CFG_MAILBOX8_CLKCTRL			DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CORE_INST, 0x0678)
+#define DRA7XX_CM_L4CFG_MAILBOX9_CLKCTRL_OFFSET			0x0680
+#define DRA7XX_CM_L4CFG_MAILBOX9_CLKCTRL			DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CORE_INST, 0x0680)
+#define DRA7XX_CM_L4CFG_MAILBOX10_CLKCTRL_OFFSET		0x0688
+#define DRA7XX_CM_L4CFG_MAILBOX10_CLKCTRL			DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CORE_INST, 0x0688)
+#define DRA7XX_CM_L4CFG_MAILBOX11_CLKCTRL_OFFSET		0x0690
+#define DRA7XX_CM_L4CFG_MAILBOX11_CLKCTRL			DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CORE_INST, 0x0690)
+#define DRA7XX_CM_L4CFG_MAILBOX12_CLKCTRL_OFFSET		0x0698
+#define DRA7XX_CM_L4CFG_MAILBOX12_CLKCTRL			DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CORE_INST, 0x0698)
+#define DRA7XX_CM_L4CFG_MAILBOX13_CLKCTRL_OFFSET		0x06a0
+#define DRA7XX_CM_L4CFG_MAILBOX13_CLKCTRL			DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CORE_INST, 0x06a0)
+#define DRA7XX_CM_L4CFG_SPARE_SMARTREFLEX_RTC_CLKCTRL_OFFSET	0x06a8
+#define DRA7XX_CM_L4CFG_SPARE_SMARTREFLEX_RTC_CLKCTRL		DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CORE_INST, 0x06a8)
+#define DRA7XX_CM_L4CFG_SPARE_SMARTREFLEX_SDRAM_CLKCTRL_OFFSET	0x06b0
+#define DRA7XX_CM_L4CFG_SPARE_SMARTREFLEX_SDRAM_CLKCTRL		DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CORE_INST, 0x06b0)
+#define DRA7XX_CM_L4CFG_SPARE_SMARTREFLEX_WKUP_CLKCTRL_OFFSET	0x06b8
+#define DRA7XX_CM_L4CFG_SPARE_SMARTREFLEX_WKUP_CLKCTRL		DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CORE_INST, 0x06b8)
+#define DRA7XX_CM_L4CFG_IO_DELAY_BLOCK_CLKCTRL_OFFSET		0x06c0
+#define DRA7XX_CM_L4CFG_IO_DELAY_BLOCK_CLKCTRL			DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CORE_INST, 0x06c0)
+#define DRA7XX_CM_L3INSTR_CLKSTCTRL_OFFSET			0x0700
+#define DRA7XX_CM_L3INSTR_L3_MAIN_2_CLKCTRL_OFFSET		0x0720
+#define DRA7XX_CM_L3INSTR_L3_MAIN_2_CLKCTRL			DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CORE_INST, 0x0720)
+#define DRA7XX_CM_L3INSTR_L3_INSTR_CLKCTRL_OFFSET		0x0728
+#define DRA7XX_CM_L3INSTR_L3_INSTR_CLKCTRL			DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CORE_INST, 0x0728)
+#define DRA7XX_CM_L3INSTR_OCP_WP_NOC_CLKCTRL_OFFSET		0x0740
+#define DRA7XX_CM_L3INSTR_OCP_WP_NOC_CLKCTRL			DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CORE_INST, 0x0740)
+#define DRA7XX_CM_L3INSTR_DLL_AGING_CLKCTRL_OFFSET		0x0748
+#define DRA7XX_CM_L3INSTR_DLL_AGING_CLKCTRL			DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CORE_INST, 0x0748)
+#define DRA7XX_CM_L3INSTR_CTRL_MODULE_BANDGAP_CLKCTRL_OFFSET	0x0750
+#define DRA7XX_CM_L3INSTR_CTRL_MODULE_BANDGAP_CLKCTRL		DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CORE_INST, 0x0750)
+
+/* CM_CORE.IVA_CM_CORE register offsets */
+#define DRA7XX_CM_IVA_CLKSTCTRL_OFFSET				0x0000
+#define DRA7XX_CM_IVA_STATICDEP_OFFSET				0x0004
+#define DRA7XX_CM_IVA_DYNAMICDEP_OFFSET				0x0008
+#define DRA7XX_CM_IVA_IVA_CLKCTRL_OFFSET			0x0020
+#define DRA7XX_CM_IVA_IVA_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_IVA_INST, 0x0020)
+#define DRA7XX_CM_IVA_SL2_CLKCTRL_OFFSET			0x0028
+#define DRA7XX_CM_IVA_SL2_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_IVA_INST, 0x0028)
+
+/* CM_CORE.CAM_CM_CORE register offsets */
+#define DRA7XX_CM_CAM_CLKSTCTRL_OFFSET				0x0000
+#define DRA7XX_CM_CAM_STATICDEP_OFFSET				0x0004
+#define DRA7XX_CM_CAM_VIP1_CLKCTRL_OFFSET			0x0020
+#define DRA7XX_CM_CAM_VIP1_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CAM_INST, 0x0020)
+#define DRA7XX_CM_CAM_VIP2_CLKCTRL_OFFSET			0x0028
+#define DRA7XX_CM_CAM_VIP2_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CAM_INST, 0x0028)
+#define DRA7XX_CM_CAM_VIP3_CLKCTRL_OFFSET			0x0030
+#define DRA7XX_CM_CAM_VIP3_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CAM_INST, 0x0030)
+#define DRA7XX_CM_CAM_LVDSRX_CLKCTRL_OFFSET			0x0038
+#define DRA7XX_CM_CAM_LVDSRX_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CAM_INST, 0x0038)
+#define DRA7XX_CM_CAM_CSI1_CLKCTRL_OFFSET			0x0040
+#define DRA7XX_CM_CAM_CSI1_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CAM_INST, 0x0040)
+#define DRA7XX_CM_CAM_CSI2_CLKCTRL_OFFSET			0x0048
+#define DRA7XX_CM_CAM_CSI2_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CAM_INST, 0x0048)
+
+/* CM_CORE.DSS_CM_CORE register offsets */
+#define DRA7XX_CM_DSS_CLKSTCTRL_OFFSET				0x0000
+#define DRA7XX_CM_DSS_STATICDEP_OFFSET				0x0004
+#define DRA7XX_CM_DSS_DYNAMICDEP_OFFSET				0x0008
+#define DRA7XX_CM_DSS_DSS_CLKCTRL_OFFSET			0x0020
+#define DRA7XX_CM_DSS_DSS_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_DSS_INST, 0x0020)
+#define DRA7XX_CM_DSS_BB2D_CLKCTRL_OFFSET			0x0030
+#define DRA7XX_CM_DSS_BB2D_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_DSS_INST, 0x0030)
+#define DRA7XX_CM_DSS_SDVENC_CLKCTRL_OFFSET			0x003c
+#define DRA7XX_CM_DSS_SDVENC_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_DSS_INST, 0x003c)
+
+/* CM_CORE.GPU_CM_CORE register offsets */
+#define DRA7XX_CM_GPU_CLKSTCTRL_OFFSET				0x0000
+#define DRA7XX_CM_GPU_STATICDEP_OFFSET				0x0004
+#define DRA7XX_CM_GPU_DYNAMICDEP_OFFSET				0x0008
+#define DRA7XX_CM_GPU_GPU_CLKCTRL_OFFSET			0x0020
+#define DRA7XX_CM_GPU_GPU_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_GPU_INST, 0x0020)
+
+/* CM_CORE.L3INIT_CM_CORE register offsets */
+#define DRA7XX_CM_L3INIT_CLKSTCTRL_OFFSET			0x0000
+#define DRA7XX_CM_L3INIT_STATICDEP_OFFSET			0x0004
+#define DRA7XX_CM_L3INIT_DYNAMICDEP_OFFSET			0x0008
+#define DRA7XX_CM_L3INIT_MMC1_CLKCTRL_OFFSET			0x0028
+#define DRA7XX_CM_L3INIT_MMC1_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_L3INIT_INST, 0x0028)
+#define DRA7XX_CM_L3INIT_MMC2_CLKCTRL_OFFSET			0x0030
+#define DRA7XX_CM_L3INIT_MMC2_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_L3INIT_INST, 0x0030)
+#define DRA7XX_CM_L3INIT_USB_OTG_SS2_CLKCTRL_OFFSET		0x0040
+#define DRA7XX_CM_L3INIT_USB_OTG_SS2_CLKCTRL			DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_L3INIT_INST, 0x0040)
+#define DRA7XX_CM_L3INIT_USB_OTG_SS3_CLKCTRL_OFFSET		0x0048
+#define DRA7XX_CM_L3INIT_USB_OTG_SS3_CLKCTRL			DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_L3INIT_INST, 0x0048)
+#define DRA7XX_CM_L3INIT_USB_OTG_SS4_CLKCTRL_OFFSET		0x0050
+#define DRA7XX_CM_L3INIT_USB_OTG_SS4_CLKCTRL			DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_L3INIT_INST, 0x0050)
+#define DRA7XX_CM_L3INIT_MLB_SS_CLKCTRL_OFFSET			0x0058
+#define DRA7XX_CM_L3INIT_MLB_SS_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_L3INIT_INST, 0x0058)
+#define DRA7XX_CM_L3INIT_IEEE1500_2_OCP_CLKCTRL_OFFSET		0x0078
+#define DRA7XX_CM_L3INIT_IEEE1500_2_OCP_CLKCTRL			DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_L3INIT_INST, 0x0078)
+#define DRA7XX_CM_L3INIT_SATA_CLKCTRL_OFFSET			0x0088
+#define DRA7XX_CM_L3INIT_SATA_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_L3INIT_INST, 0x0088)
+#define DRA7XX_CM_PCIE_CLKSTCTRL_OFFSET				0x00a0
+#define DRA7XX_CM_PCIE_STATICDEP_OFFSET				0x00a4
+#define DRA7XX_CM_GMAC_CLKSTCTRL_OFFSET				0x00c0
+#define DRA7XX_CM_GMAC_STATICDEP_OFFSET				0x00c4
+#define DRA7XX_CM_GMAC_DYNAMICDEP_OFFSET			0x00c8
+#define DRA7XX_CM_GMAC_GMAC_CLKCTRL_OFFSET			0x00d0
+#define DRA7XX_CM_GMAC_GMAC_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_L3INIT_INST, 0x00d0)
+#define DRA7XX_CM_L3INIT_OCP2SCP1_CLKCTRL_OFFSET		0x00e0
+#define DRA7XX_CM_L3INIT_OCP2SCP1_CLKCTRL			DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_L3INIT_INST, 0x00e0)
+#define DRA7XX_CM_L3INIT_OCP2SCP3_CLKCTRL_OFFSET		0x00e8
+#define DRA7XX_CM_L3INIT_OCP2SCP3_CLKCTRL			DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_L3INIT_INST, 0x00e8)
+#define DRA7XX_CM_L3INIT_USB_OTG_SS1_CLKCTRL_OFFSET		0x00f0
+#define DRA7XX_CM_L3INIT_USB_OTG_SS1_CLKCTRL			DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_L3INIT_INST, 0x00f0)
+
+/* CM_CORE.CUSTEFUSE_CM_CORE register offsets */
+#define DRA7XX_CM_CUSTEFUSE_CLKSTCTRL_OFFSET			0x0000
+#define DRA7XX_CM_CUSTEFUSE_EFUSE_CTRL_CUST_CLKCTRL_OFFSET	0x0020
+#define DRA7XX_CM_CUSTEFUSE_EFUSE_CTRL_CUST_CLKCTRL		DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_CUSTEFUSE_INST, 0x0020)
+
+/* CM_CORE.L4PER_CM_CORE register offsets */
+#define DRA7XX_CM_L4PER_CLKSTCTRL_OFFSET			0x0000
+#define DRA7XX_CM_L4PER_DYNAMICDEP_OFFSET			0x0008
+#define DRA7XX_CM_L4PER2_L4_PER2_CLKCTRL_OFFSET			0x000c
+#define DRA7XX_CM_L4PER2_L4_PER2_CLKCTRL			DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_L4PER_INST, 0x000c)
+#define DRA7XX_CM_L4PER3_L4_PER3_CLKCTRL_OFFSET			0x0014
+#define DRA7XX_CM_L4PER3_L4_PER3_CLKCTRL			DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_L4PER_INST, 0x0014)
+#define DRA7XX_CM_L4PER2_PRUSS1_CLKCTRL_OFFSET			0x0018
+#define DRA7XX_CM_L4PER2_PRUSS1_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_L4PER_INST, 0x0018)
+#define DRA7XX_CM_L4PER2_PRUSS2_CLKCTRL_OFFSET			0x0020
+#define DRA7XX_CM_L4PER2_PRUSS2_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_L4PER_INST, 0x0020)
+#define DRA7XX_CM_L4PER_TIMER10_CLKCTRL_OFFSET			0x0028
+#define DRA7XX_CM_L4PER_TIMER10_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_L4PER_INST, 0x0028)
+#define DRA7XX_CM_L4PER_TIMER11_CLKCTRL_OFFSET			0x0030
+#define DRA7XX_CM_L4PER_TIMER11_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_L4PER_INST, 0x0030)
+#define DRA7XX_CM_L4PER_TIMER2_CLKCTRL_OFFSET			0x0038
+#define DRA7XX_CM_L4PER_TIMER2_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_L4PER_INST, 0x0038)
+#define DRA7XX_CM_L4PER_TIMER3_CLKCTRL_OFFSET			0x0040
+#define DRA7XX_CM_L4PER_TIMER3_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_L4PER_INST, 0x0040)
+#define DRA7XX_CM_L4PER_TIMER4_CLKCTRL_OFFSET			0x0048
+#define DRA7XX_CM_L4PER_TIMER4_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_L4PER_INST, 0x0048)
+#define DRA7XX_CM_L4PER_TIMER9_CLKCTRL_OFFSET			0x0050
+#define DRA7XX_CM_L4PER_TIMER9_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_L4PER_INST, 0x0050)
+#define DRA7XX_CM_L4PER_ELM_CLKCTRL_OFFSET			0x0058
+#define DRA7XX_CM_L4PER_ELM_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_L4PER_INST, 0x0058)
+#define DRA7XX_CM_L4PER_GPIO2_CLKCTRL_OFFSET			0x0060
+#define DRA7XX_CM_L4PER_GPIO2_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_L4PER_INST, 0x0060)
+#define DRA7XX_CM_L4PER_GPIO3_CLKCTRL_OFFSET			0x0068
+#define DRA7XX_CM_L4PER_GPIO3_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_L4PER_INST, 0x0068)
+#define DRA7XX_CM_L4PER_GPIO4_CLKCTRL_OFFSET			0x0070
+#define DRA7XX_CM_L4PER_GPIO4_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_L4PER_INST, 0x0070)
+#define DRA7XX_CM_L4PER_GPIO5_CLKCTRL_OFFSET			0x0078
+#define DRA7XX_CM_L4PER_GPIO5_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_L4PER_INST, 0x0078)
+#define DRA7XX_CM_L4PER_GPIO6_CLKCTRL_OFFSET			0x0080
+#define DRA7XX_CM_L4PER_GPIO6_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_L4PER_INST, 0x0080)
+#define DRA7XX_CM_L4PER_HDQ1W_CLKCTRL_OFFSET			0x0088
+#define DRA7XX_CM_L4PER_HDQ1W_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_L4PER_INST, 0x0088)
+#define DRA7XX_CM_L4PER2_PWMSS2_CLKCTRL_OFFSET			0x0090
+#define DRA7XX_CM_L4PER2_PWMSS2_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_L4PER_INST, 0x0090)
+#define DRA7XX_CM_L4PER2_PWMSS3_CLKCTRL_OFFSET			0x0098
+#define DRA7XX_CM_L4PER2_PWMSS3_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_L4PER_INST, 0x0098)
+#define DRA7XX_CM_L4PER_I2C1_CLKCTRL_OFFSET			0x00a0
+#define DRA7XX_CM_L4PER_I2C1_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_L4PER_INST, 0x00a0)
+#define DRA7XX_CM_L4PER_I2C2_CLKCTRL_OFFSET			0x00a8
+#define DRA7XX_CM_L4PER_I2C2_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_L4PER_INST, 0x00a8)
+#define DRA7XX_CM_L4PER_I2C3_CLKCTRL_OFFSET			0x00b0
+#define DRA7XX_CM_L4PER_I2C3_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_L4PER_INST, 0x00b0)
+#define DRA7XX_CM_L4PER_I2C4_CLKCTRL_OFFSET			0x00b8
+#define DRA7XX_CM_L4PER_I2C4_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_L4PER_INST, 0x00b8)
+#define DRA7XX_CM_L4PER_L4_PER1_CLKCTRL_OFFSET			0x00c0
+#define DRA7XX_CM_L4PER_L4_PER1_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_L4PER_INST, 0x00c0)
+#define DRA7XX_CM_L4PER2_PWMSS1_CLKCTRL_OFFSET			0x00c4
+#define DRA7XX_CM_L4PER2_PWMSS1_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_L4PER_INST, 0x00c4)
+#define DRA7XX_CM_L4PER3_TIMER13_CLKCTRL_OFFSET			0x00c8
+#define DRA7XX_CM_L4PER3_TIMER13_CLKCTRL			DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_L4PER_INST, 0x00c8)
+#define DRA7XX_CM_L4PER3_TIMER14_CLKCTRL_OFFSET			0x00d0
+#define DRA7XX_CM_L4PER3_TIMER14_CLKCTRL			DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_L4PER_INST, 0x00d0)
+#define DRA7XX_CM_L4PER3_TIMER15_CLKCTRL_OFFSET			0x00d8
+#define DRA7XX_CM_L4PER3_TIMER15_CLKCTRL			DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_L4PER_INST, 0x00d8)
+#define DRA7XX_CM_L4PER_MCSPI1_CLKCTRL_OFFSET			0x00f0
+#define DRA7XX_CM_L4PER_MCSPI1_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_L4PER_INST, 0x00f0)
+#define DRA7XX_CM_L4PER_MCSPI2_CLKCTRL_OFFSET			0x00f8
+#define DRA7XX_CM_L4PER_MCSPI2_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_L4PER_INST, 0x00f8)
+#define DRA7XX_CM_L4PER_MCSPI3_CLKCTRL_OFFSET			0x0100
+#define DRA7XX_CM_L4PER_MCSPI3_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_L4PER_INST, 0x0100)
+#define DRA7XX_CM_L4PER_MCSPI4_CLKCTRL_OFFSET			0x0108
+#define DRA7XX_CM_L4PER_MCSPI4_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_L4PER_INST, 0x0108)
+#define DRA7XX_CM_L4PER_GPIO7_CLKCTRL_OFFSET			0x0110
+#define DRA7XX_CM_L4PER_GPIO7_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_L4PER_INST, 0x0110)
+#define DRA7XX_CM_L4PER_GPIO8_CLKCTRL_OFFSET			0x0118
+#define DRA7XX_CM_L4PER_GPIO8_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_L4PER_INST, 0x0118)
+#define DRA7XX_CM_L4PER_MMC3_CLKCTRL_OFFSET			0x0120
+#define DRA7XX_CM_L4PER_MMC3_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_L4PER_INST, 0x0120)
+#define DRA7XX_CM_L4PER_MMC4_CLKCTRL_OFFSET			0x0128
+#define DRA7XX_CM_L4PER_MMC4_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_L4PER_INST, 0x0128)
+#define DRA7XX_CM_L4PER3_TIMER16_CLKCTRL_OFFSET			0x0130
+#define DRA7XX_CM_L4PER3_TIMER16_CLKCTRL			DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_L4PER_INST, 0x0130)
+#define DRA7XX_CM_L4PER2_QSPI_CLKCTRL_OFFSET			0x0138
+#define DRA7XX_CM_L4PER2_QSPI_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_L4PER_INST, 0x0138)
+#define DRA7XX_CM_L4PER_UART1_CLKCTRL_OFFSET			0x0140
+#define DRA7XX_CM_L4PER_UART1_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_L4PER_INST, 0x0140)
+#define DRA7XX_CM_L4PER_UART2_CLKCTRL_OFFSET			0x0148
+#define DRA7XX_CM_L4PER_UART2_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_L4PER_INST, 0x0148)
+#define DRA7XX_CM_L4PER_UART3_CLKCTRL_OFFSET			0x0150
+#define DRA7XX_CM_L4PER_UART3_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_L4PER_INST, 0x0150)
+#define DRA7XX_CM_L4PER_UART4_CLKCTRL_OFFSET			0x0158
+#define DRA7XX_CM_L4PER_UART4_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_L4PER_INST, 0x0158)
+#define DRA7XX_CM_L4PER2_MCASP2_CLKCTRL_OFFSET			0x0160
+#define DRA7XX_CM_L4PER2_MCASP2_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_L4PER_INST, 0x0160)
+#define DRA7XX_CM_L4PER2_MCASP3_CLKCTRL_OFFSET			0x0168
+#define DRA7XX_CM_L4PER2_MCASP3_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_L4PER_INST, 0x0168)
+#define DRA7XX_CM_L4PER_UART5_CLKCTRL_OFFSET			0x0170
+#define DRA7XX_CM_L4PER_UART5_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_L4PER_INST, 0x0170)
+#define DRA7XX_CM_L4PER2_MCASP5_CLKCTRL_OFFSET			0x0178
+#define DRA7XX_CM_L4PER2_MCASP5_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_L4PER_INST, 0x0178)
+#define DRA7XX_CM_L4SEC_CLKSTCTRL_OFFSET			0x0180
+#define DRA7XX_CM_L4SEC_STATICDEP_OFFSET			0x0184
+#define DRA7XX_CM_L4SEC_DYNAMICDEP_OFFSET			0x0188
+#define DRA7XX_CM_L4PER2_MCASP8_CLKCTRL_OFFSET			0x0190
+#define DRA7XX_CM_L4PER2_MCASP8_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_L4PER_INST, 0x0190)
+#define DRA7XX_CM_L4PER2_MCASP4_CLKCTRL_OFFSET			0x0198
+#define DRA7XX_CM_L4PER2_MCASP4_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_L4PER_INST, 0x0198)
+#define DRA7XX_CM_L4SEC_AES1_CLKCTRL_OFFSET			0x01a0
+#define DRA7XX_CM_L4SEC_AES1_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_L4PER_INST, 0x01a0)
+#define DRA7XX_CM_L4SEC_AES2_CLKCTRL_OFFSET			0x01a8
+#define DRA7XX_CM_L4SEC_AES2_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_L4PER_INST, 0x01a8)
+#define DRA7XX_CM_L4SEC_DES3DES_CLKCTRL_OFFSET			0x01b0
+#define DRA7XX_CM_L4SEC_DES3DES_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_L4PER_INST, 0x01b0)
+#define DRA7XX_CM_L4SEC_FPKA_CLKCTRL_OFFSET			0x01b8
+#define DRA7XX_CM_L4SEC_FPKA_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_L4PER_INST, 0x01b8)
+#define DRA7XX_CM_L4SEC_RNG_CLKCTRL_OFFSET			0x01c0
+#define DRA7XX_CM_L4SEC_RNG_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_L4PER_INST, 0x01c0)
+#define DRA7XX_CM_L4SEC_SHA2MD51_CLKCTRL_OFFSET			0x01c8
+#define DRA7XX_CM_L4SEC_SHA2MD51_CLKCTRL			DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_L4PER_INST, 0x01c8)
+#define DRA7XX_CM_L4PER2_UART7_CLKCTRL_OFFSET			0x01d0
+#define DRA7XX_CM_L4PER2_UART7_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_L4PER_INST, 0x01d0)
+#define DRA7XX_CM_L4SEC_DMA_CRYPTO_CLKCTRL_OFFSET		0x01d8
+#define DRA7XX_CM_L4SEC_DMA_CRYPTO_CLKCTRL			DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_L4PER_INST, 0x01d8)
+#define DRA7XX_CM_L4PER2_UART8_CLKCTRL_OFFSET			0x01e0
+#define DRA7XX_CM_L4PER2_UART8_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_L4PER_INST, 0x01e0)
+#define DRA7XX_CM_L4PER2_UART9_CLKCTRL_OFFSET			0x01e8
+#define DRA7XX_CM_L4PER2_UART9_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_L4PER_INST, 0x01e8)
+#define DRA7XX_CM_L4PER2_DCAN2_CLKCTRL_OFFSET			0x01f0
+#define DRA7XX_CM_L4PER2_DCAN2_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_L4PER_INST, 0x01f0)
+#define DRA7XX_CM_L4SEC_SHA2MD52_CLKCTRL_OFFSET			0x01f8
+#define DRA7XX_CM_L4SEC_SHA2MD52_CLKCTRL			DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_L4PER_INST, 0x01f8)
+#define DRA7XX_CM_L4PER2_CLKSTCTRL_OFFSET			0x01fc
+#define DRA7XX_CM_L4PER2_DYNAMICDEP_OFFSET			0x0200
+#define DRA7XX_CM_L4PER2_MCASP6_CLKCTRL_OFFSET			0x0204
+#define DRA7XX_CM_L4PER2_MCASP6_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_L4PER_INST, 0x0204)
+#define DRA7XX_CM_L4PER2_MCASP7_CLKCTRL_OFFSET			0x0208
+#define DRA7XX_CM_L4PER2_MCASP7_CLKCTRL				DRA7XX_CM_CORE_REGADDR(DRA7XX_CM_CORE_L4PER_INST, 0x0208)
+#define DRA7XX_CM_L4PER2_STATICDEP_OFFSET			0x020c
+#define DRA7XX_CM_L4PER3_CLKSTCTRL_OFFSET			0x0210
+#define DRA7XX_CM_L4PER3_DYNAMICDEP_OFFSET			0x0214
+
+#endif
diff --git a/arch/arm/mach-omap2/common.h b/arch/arm/mach-omap2/common.h
index dfcc182ecff9..4a5684b96492 100644
--- a/arch/arm/mach-omap2/common.h
+++ b/arch/arm/mach-omap2/common.h
@@ -110,6 +110,7 @@ void omap3630_init_late(void);
 void am35xx_init_late(void);
 void ti81xx_init_late(void);
 int omap2_common_pm_late_init(void);
+void dra7xx_init_early(void);
 
 #ifdef CONFIG_SOC_BUS
 void omap_soc_device_init(void);
diff --git a/arch/arm/mach-omap2/cpuidle44xx.c b/arch/arm/mach-omap2/cpuidle44xx.c
index c443f2e97e10..4c8982ae9529 100644
--- a/arch/arm/mach-omap2/cpuidle44xx.c
+++ b/arch/arm/mach-omap2/cpuidle44xx.c
@@ -143,7 +143,7 @@ static int omap_enter_idle_coupled(struct cpuidle_device *dev,
 	 * Call idle CPU cluster PM exit notifier chain
 	 * to restore GIC and wakeupgen context.
 	 */
-	if ((cx->mpu_state == PWRDM_POWER_RET) &&
+	if (dev->cpu == 0 && (cx->mpu_state == PWRDM_POWER_RET) &&
 		(cx->mpu_logic_state == PWRDM_POWER_OFF))
 		cpu_cluster_pm_exit();
 
diff --git a/arch/arm/mach-omap2/devices.c b/arch/arm/mach-omap2/devices.c
index 3c1279f27d1f..5c5315ba129b 100644
--- a/arch/arm/mach-omap2/devices.c
+++ b/arch/arm/mach-omap2/devices.c
@@ -327,44 +327,6 @@ static void omap_init_audio(void)
 static inline void omap_init_audio(void) {}
 #endif
 
-#if defined(CONFIG_SND_OMAP_SOC_MCPDM) || \
-		defined(CONFIG_SND_OMAP_SOC_MCPDM_MODULE)
-
-static void __init omap_init_mcpdm(void)
-{
-	struct omap_hwmod *oh;
-	struct platform_device *pdev;
-
-	oh = omap_hwmod_lookup("mcpdm");
-	if (!oh)
-		return;
-
-	pdev = omap_device_build("omap-mcpdm", -1, oh, NULL, 0);
-	WARN(IS_ERR(pdev), "Can't build omap_device for omap-mcpdm.\n");
-}
-#else
-static inline void omap_init_mcpdm(void) {}
-#endif
-
-#if defined(CONFIG_SND_OMAP_SOC_DMIC) || \
-		defined(CONFIG_SND_OMAP_SOC_DMIC_MODULE)
-
-static void __init omap_init_dmic(void)
-{
-	struct omap_hwmod *oh;
-	struct platform_device *pdev;
-
-	oh = omap_hwmod_lookup("dmic");
-	if (!oh)
-		return;
-
-	pdev = omap_device_build("omap-dmic", -1, oh, NULL, 0);
-	WARN(IS_ERR(pdev), "Can't build omap_device for omap-dmic.\n");
-}
-#else
-static inline void omap_init_dmic(void) {}
-#endif
-
 #if defined(CONFIG_SND_OMAP_SOC_OMAP_HDMI) || \
 		defined(CONFIG_SND_OMAP_SOC_OMAP_HDMI_MODULE)
 
@@ -565,17 +527,15 @@ static int __init omap2_init_devices(void)
 	omap_init_mbox();
 	/* If dtb is there, the devices will be created dynamically */
 	if (!of_have_populated_dt()) {
-		omap_init_dmic();
-		omap_init_mcpdm();
 		omap_init_mcspi();
 		omap_init_sham();
 		omap_init_aes();
+		omap_init_rng();
 	} else {
 		/* These can be removed when bindings are done */
 		omap_init_wl12xx_of();
 	}
 	omap_init_sti();
-	omap_init_rng();
 	omap_init_vout();
 
 	return 0;
diff --git a/arch/arm/mach-omap2/display.c b/arch/arm/mach-omap2/display.c
index ff37be1f6f93..03a0516c7f67 100644
--- a/arch/arm/mach-omap2/display.c
+++ b/arch/arm/mach-omap2/display.c
@@ -400,7 +400,7 @@ int __init omap_display_init(struct omap_dss_board_info *board_data)
 
 	/* Create devices for DPI and SDI */
 
-	pdev = create_simple_dss_pdev("omapdss_dpi", -1,
+	pdev = create_simple_dss_pdev("omapdss_dpi", 0,
 			board_data, sizeof(*board_data), dss_pdev);
 	if (IS_ERR(pdev)) {
 		pr_err("Could not build platform_device for omapdss_dpi\n");
@@ -408,7 +408,7 @@ int __init omap_display_init(struct omap_dss_board_info *board_data)
 	}
 
 	if (cpu_is_omap34xx()) {
-		pdev = create_simple_dss_pdev("omapdss_sdi", -1,
+		pdev = create_simple_dss_pdev("omapdss_sdi", 0,
 				board_data, sizeof(*board_data), dss_pdev);
 		if (IS_ERR(pdev)) {
 			pr_err("Could not build platform_device for omapdss_sdi\n");
diff --git a/arch/arm/mach-omap2/dss-common.c b/arch/arm/mach-omap2/dss-common.c
index 043e5705f2a6..bf89effa4c99 100644
--- a/arch/arm/mach-omap2/dss-common.c
+++ b/arch/arm/mach-omap2/dss-common.c
@@ -25,6 +25,7 @@
 
 #include <linux/kernel.h>
 #include <linux/gpio.h>
+#include <linux/platform_device.h>
 
 #include <video/omapdss.h>
 #include <video/omap-panel-data.h>
@@ -37,70 +38,76 @@
 #define HDMI_GPIO_LS_OE 41 /* Level shifter for HDMI */
 #define HDMI_GPIO_HPD  63 /* Hotplug detect */
 
-/* Display DVI */
 #define PANDA_DVI_TFP410_POWER_DOWN_GPIO	0
 
-/* Using generic display panel */
-static struct tfp410_platform_data omap4_dvi_panel = {
-	.i2c_bus_num		= 2,
-	.power_down_gpio	= PANDA_DVI_TFP410_POWER_DOWN_GPIO,
+/* DVI Connector */
+static struct connector_dvi_platform_data omap4_panda_dvi_connector_pdata = {
+	.name                   = "dvi",
+	.source                 = "tfp410.0",
+	.i2c_bus_num            = 2,
 };
 
-static struct omap_dss_device omap4_panda_dvi_device = {
-	.type			= OMAP_DISPLAY_TYPE_DPI,
-	.name			= "dvi",
-	.driver_name		= "tfp410",
-	.data			= &omap4_dvi_panel,
-	.phy.dpi.data_lines	= 24,
-	.channel		= OMAP_DSS_CHANNEL_LCD2,
+static struct platform_device omap4_panda_dvi_connector_device = {
+	.name                   = "connector-dvi",
+	.id                     = 0,
+	.dev.platform_data      = &omap4_panda_dvi_connector_pdata,
 };
 
-static struct omap_dss_hdmi_data omap4_panda_hdmi_data = {
+/* TFP410 DPI-to-DVI chip */
+static struct encoder_tfp410_platform_data omap4_panda_tfp410_pdata = {
+	.name                   = "tfp410.0",
+	.source                 = "dpi.0",
+	.data_lines             = 24,
+	.power_down_gpio        = PANDA_DVI_TFP410_POWER_DOWN_GPIO,
+};
+
+static struct platform_device omap4_panda_tfp410_device = {
+	.name                   = "tfp410",
+	.id                     = 0,
+	.dev.platform_data      = &omap4_panda_tfp410_pdata,
+};
+
+/* HDMI Connector */
+static struct connector_hdmi_platform_data omap4_panda_hdmi_connector_pdata = {
+	.name                   = "hdmi",
+	.source                 = "tpd12s015.0",
+};
+
+static struct platform_device omap4_panda_hdmi_connector_device = {
+	.name                   = "connector-hdmi",
+	.id                     = 0,
+	.dev.platform_data      = &omap4_panda_hdmi_connector_pdata,
+};
+
+/* TPD12S015 HDMI ESD protection & level shifter chip */
+static struct encoder_tpd12s015_platform_data omap4_panda_tpd_pdata = {
+	.name                   = "tpd12s015.0",
+	.source                 = "hdmi.0",
+
 	.ct_cp_hpd_gpio = HDMI_GPIO_CT_CP_HPD,
 	.ls_oe_gpio = HDMI_GPIO_LS_OE,
 	.hpd_gpio = HDMI_GPIO_HPD,
 };
 
-static struct omap_dss_device  omap4_panda_hdmi_device = {
-	.name = "hdmi",
-	.driver_name = "hdmi_panel",
-	.type = OMAP_DISPLAY_TYPE_HDMI,
-	.channel = OMAP_DSS_CHANNEL_DIGIT,
-	.data = &omap4_panda_hdmi_data,
-};
-
-static struct omap_dss_device *omap4_panda_dss_devices[] = {
-	&omap4_panda_dvi_device,
-	&omap4_panda_hdmi_device,
+static struct platform_device omap4_panda_tpd_device = {
+	.name                   = "tpd12s015",
+	.id                     = 0,
+	.dev.platform_data      = &omap4_panda_tpd_pdata,
 };
 
 static struct omap_dss_board_info omap4_panda_dss_data = {
-	.num_devices	= ARRAY_SIZE(omap4_panda_dss_devices),
-	.devices	= omap4_panda_dss_devices,
-	.default_device	= &omap4_panda_dvi_device,
+	.default_display_name = "dvi",
 };
 
-void __init omap4_panda_display_init(void)
+void __init omap4_panda_display_init_of(void)
 {
 	omap_display_init(&omap4_panda_dss_data);
 
-	/*
-	 * OMAP4460SDP/Blaze and OMAP4430 ES2.3 SDP/Blaze boards and
-	 * later have external pull up on the HDMI I2C lines
-	 */
-	if (cpu_is_omap446x() || omap_rev() > OMAP4430_REV_ES2_2)
-		omap_hdmi_init(OMAP_HDMI_SDA_SCL_EXTERNAL_PULLUP);
-	else
-		omap_hdmi_init(0);
-
-	omap_mux_init_gpio(HDMI_GPIO_LS_OE, OMAP_PIN_OUTPUT);
-	omap_mux_init_gpio(HDMI_GPIO_CT_CP_HPD, OMAP_PIN_OUTPUT);
-	omap_mux_init_gpio(HDMI_GPIO_HPD, OMAP_PIN_INPUT_PULLDOWN);
-}
+	platform_device_register(&omap4_panda_tfp410_device);
+	platform_device_register(&omap4_panda_dvi_connector_device);
 
-void __init omap4_panda_display_init_of(void)
-{
-	omap_display_init(&omap4_panda_dss_data);
+	platform_device_register(&omap4_panda_tpd_device);
+	platform_device_register(&omap4_panda_hdmi_connector_device);
 }
 
 
@@ -109,93 +116,73 @@ void __init omap4_panda_display_init_of(void)
 #define DISPLAY_SEL_GPIO	59	/* LCD2/PicoDLP switch */
 #define DLP_POWER_ON_GPIO	40
 
-static struct nokia_dsi_panel_data dsi1_panel = {
-		.name		= "taal",
-		.reset_gpio	= 102,
-		.use_ext_te	= false,
-		.ext_te_gpio	= 101,
-		.esd_interval	= 0,
-		.pin_config = {
-			.num_pins	= 6,
-			.pins		= { 0, 1, 2, 3, 4, 5 },
-		},
-};
-
-static struct omap_dss_device sdp4430_lcd_device = {
-	.name			= "lcd",
-	.driver_name		= "taal",
-	.type			= OMAP_DISPLAY_TYPE_DSI,
-	.data			= &dsi1_panel,
-	.phy.dsi		= {
-		.module		= 0,
+static struct panel_dsicm_platform_data dsi1_panel = {
+	.name		= "lcd",
+	.source		= "dsi.0",
+	.reset_gpio	= 102,
+	.use_ext_te	= false,
+	.ext_te_gpio	= 101,
+	.pin_config = {
+		.num_pins	= 6,
+		.pins		= { 0, 1, 2, 3, 4, 5 },
 	},
-	.channel		= OMAP_DSS_CHANNEL_LCD,
 };
 
-static struct nokia_dsi_panel_data dsi2_panel = {
-		.name		= "taal",
-		.reset_gpio	= 104,
-		.use_ext_te	= false,
-		.ext_te_gpio	= 103,
-		.esd_interval	= 0,
-		.pin_config = {
-			.num_pins	= 6,
-			.pins		= { 0, 1, 2, 3, 4, 5 },
-		},
+static struct platform_device sdp4430_lcd_device = {
+	.name                   = "panel-dsi-cm",
+	.id                     = 0,
+	.dev.platform_data	= &dsi1_panel,
 };
 
-static struct omap_dss_device sdp4430_lcd2_device = {
-	.name			= "lcd2",
-	.driver_name		= "taal",
-	.type			= OMAP_DISPLAY_TYPE_DSI,
-	.data			= &dsi2_panel,
-	.phy.dsi		= {
-
-		.module		= 1,
+static struct panel_dsicm_platform_data dsi2_panel = {
+	.name		= "lcd2",
+	.source		= "dsi.1",
+	.reset_gpio	= 104,
+	.use_ext_te	= false,
+	.ext_te_gpio	= 103,
+	.pin_config = {
+		.num_pins	= 6,
+		.pins		= { 0, 1, 2, 3, 4, 5 },
 	},
-	.channel		= OMAP_DSS_CHANNEL_LCD2,
 };
 
-static struct omap_dss_hdmi_data sdp4430_hdmi_data = {
-	.ct_cp_hpd_gpio = HDMI_GPIO_CT_CP_HPD,
-	.ls_oe_gpio = HDMI_GPIO_LS_OE,
-	.hpd_gpio = HDMI_GPIO_HPD,
+static struct platform_device sdp4430_lcd2_device = {
+	.name                   = "panel-dsi-cm",
+	.id                     = 1,
+	.dev.platform_data	= &dsi2_panel,
 };
 
-static struct omap_dss_device sdp4430_hdmi_device = {
-	.name = "hdmi",
-	.driver_name = "hdmi_panel",
-	.type = OMAP_DISPLAY_TYPE_HDMI,
-	.channel = OMAP_DSS_CHANNEL_DIGIT,
-	.data = &sdp4430_hdmi_data,
+/* HDMI Connector */
+static struct connector_hdmi_platform_data sdp4430_hdmi_connector_pdata = {
+	.name                   = "hdmi",
+	.source                 = "tpd12s015.0",
 };
 
-static struct picodlp_panel_data sdp4430_picodlp_pdata = {
-	.picodlp_adapter_id	= 2,
-	.emu_done_gpio		= 44,
-	.pwrgood_gpio		= 45,
+static struct platform_device sdp4430_hdmi_connector_device = {
+	.name                   = "connector-hdmi",
+	.id                     = 0,
+	.dev.platform_data      = &sdp4430_hdmi_connector_pdata,
 };
 
-static struct omap_dss_device sdp4430_picodlp_device = {
-	.name			= "picodlp",
-	.driver_name		= "picodlp_panel",
-	.type			= OMAP_DISPLAY_TYPE_DPI,
-	.phy.dpi.data_lines	= 24,
-	.channel		= OMAP_DSS_CHANNEL_LCD2,
-	.data			= &sdp4430_picodlp_pdata,
+/* TPD12S015 HDMI ESD protection & level shifter chip */
+static struct encoder_tpd12s015_platform_data sdp4430_tpd_pdata = {
+	.name                   = "tpd12s015.0",
+	.source                 = "hdmi.0",
+
+	.ct_cp_hpd_gpio = HDMI_GPIO_CT_CP_HPD,
+	.ls_oe_gpio = HDMI_GPIO_LS_OE,
+	.hpd_gpio = HDMI_GPIO_HPD,
 };
 
-static struct omap_dss_device *sdp4430_dss_devices[] = {
-	&sdp4430_lcd_device,
-	&sdp4430_lcd2_device,
-	&sdp4430_hdmi_device,
-	&sdp4430_picodlp_device,
+static struct platform_device sdp4430_tpd_device = {
+	.name                   = "tpd12s015",
+	.id                     = 0,
+	.dev.platform_data      = &sdp4430_tpd_pdata,
 };
 
+
 static struct omap_dss_board_info sdp4430_dss_data = {
-	.num_devices	= ARRAY_SIZE(sdp4430_dss_devices),
-	.devices	= sdp4430_dss_devices,
-	.default_device	= &sdp4430_lcd_device,
+	.default_display_name = "lcd",
 };
 
 /*
@@ -204,7 +191,7 @@ static struct omap_dss_board_info sdp4430_dss_data = {
  * used by picodlp on the 4430sdp platform. Keep this gpio disabled as LCD2 is
  * selected by default
  */
-void __init omap_4430sdp_display_init(void)
+void __init omap_4430sdp_display_init_of(void)
 {
 	int r;
 
@@ -219,33 +206,10 @@ void __init omap_4430sdp_display_init(void)
 		pr_err("%s: Could not get DLP POWER ON GPIO\n", __func__);
 
 	omap_display_init(&sdp4430_dss_data);
-	/*
-	 * OMAP4460SDP/Blaze and OMAP4430 ES2.3 SDP/Blaze boards and
-	 * later have external pull up on the HDMI I2C lines
-	 */
-	if (cpu_is_omap446x() || omap_rev() > OMAP4430_REV_ES2_2)
-		omap_hdmi_init(OMAP_HDMI_SDA_SCL_EXTERNAL_PULLUP);
-	else
-		omap_hdmi_init(0);
-
-	omap_mux_init_gpio(HDMI_GPIO_LS_OE, OMAP_PIN_OUTPUT);
-	omap_mux_init_gpio(HDMI_GPIO_CT_CP_HPD, OMAP_PIN_OUTPUT);
-	omap_mux_init_gpio(HDMI_GPIO_HPD, OMAP_PIN_INPUT_PULLDOWN);
-}
-
-void __init omap_4430sdp_display_init_of(void)
-{
-	int r;
 
-	r = gpio_request_one(DISPLAY_SEL_GPIO, GPIOF_OUT_INIT_HIGH,
-			"display_sel");
-	if (r)
-		pr_err("%s: Could not get display_sel GPIO\n", __func__);
-
-	r = gpio_request_one(DLP_POWER_ON_GPIO, GPIOF_OUT_INIT_LOW,
-		"DLP POWER ON");
-	if (r)
-		pr_err("%s: Could not get DLP POWER ON GPIO\n", __func__);
+	platform_device_register(&sdp4430_lcd_device);
+	platform_device_register(&sdp4430_lcd2_device);
 
-	omap_display_init(&sdp4430_dss_data);
+	platform_device_register(&sdp4430_tpd_device);
+	platform_device_register(&sdp4430_hdmi_connector_device);
 }
diff --git a/arch/arm/mach-omap2/dss-common.h b/arch/arm/mach-omap2/dss-common.h
index 915f6fff5106..c28fe3c03588 100644
--- a/arch/arm/mach-omap2/dss-common.h
+++ b/arch/arm/mach-omap2/dss-common.h
@@ -6,9 +6,7 @@
  * This file will be removed when DSS supports DT.
  */
 
-void __init omap4_panda_display_init(void);
 void __init omap4_panda_display_init_of(void);
-void __init omap_4430sdp_display_init(void);
 void __init omap_4430sdp_display_init_of(void);
 
 #endif
diff --git a/arch/arm/mach-omap2/gpmc-onenand.c b/arch/arm/mach-omap2/gpmc-onenand.c
index 64b5a8346982..8b6876c98ce1 100644
--- a/arch/arm/mach-omap2/gpmc-onenand.c
+++ b/arch/arm/mach-omap2/gpmc-onenand.c
@@ -272,9 +272,19 @@ static int omap2_onenand_setup_async(void __iomem *onenand_base)
 	struct gpmc_timings t;
 	int ret;
 
-	if (gpmc_onenand_data->of_node)
+	if (gpmc_onenand_data->of_node) {
 		gpmc_read_settings_dt(gpmc_onenand_data->of_node,
 				      &onenand_async);
+		if (onenand_async.sync_read || onenand_async.sync_write) {
+			if (onenand_async.sync_write)
+				gpmc_onenand_data->flags |=
+					ONENAND_SYNC_READWRITE;
+			else
+				gpmc_onenand_data->flags |= ONENAND_SYNC_READ;
+			onenand_async.sync_read = false;
+			onenand_async.sync_write = false;
+		}
+	}
 
 	omap2_onenand_set_async_mode(onenand_base);
 
diff --git a/arch/arm/mach-omap2/gpmc.c b/arch/arm/mach-omap2/gpmc.c
index f3fdd6afa213..579697adaae7 100644
--- a/arch/arm/mach-omap2/gpmc.c
+++ b/arch/arm/mach-omap2/gpmc.c
@@ -149,7 +149,7 @@ struct omap3_gpmc_regs {
 
 static struct gpmc_client_irq gpmc_client_irq[GPMC_NR_IRQ];
 static struct irq_chip gpmc_irq_chip;
-static unsigned gpmc_irq_start;
+static int gpmc_irq_start;
 
 static struct resource	gpmc_mem_root;
 static struct resource	gpmc_cs_mem[GPMC_CS_NUM];
@@ -1491,8 +1491,8 @@ static int gpmc_probe_generic_child(struct platform_device *pdev,
 	 */
 	ret = gpmc_cs_remap(cs, res.start);
 	if (ret < 0) {
-		dev_err(&pdev->dev, "cannot remap GPMC CS %d to 0x%x\n",
-			cs, res.start);
+		dev_err(&pdev->dev, "cannot remap GPMC CS %d to %pa\n",
+			cs, &res.start);
 		goto err;
 	}
 
diff --git a/arch/arm/mach-omap2/i2c.c b/arch/arm/mach-omap2/i2c.c
index d940e53dd9f2..b456b4471f35 100644
--- a/arch/arm/mach-omap2/i2c.c
+++ b/arch/arm/mach-omap2/i2c.c
@@ -181,7 +181,7 @@ int __init omap_i2c_add_bus(struct omap_i2c_bus_platform_data *i2c_pdata,
 				 sizeof(struct omap_i2c_bus_platform_data));
 	WARN(IS_ERR(pdev), "Could not build omap_device for %s\n", name);
 
-	return PTR_RET(pdev);
+	return PTR_ERR_OR_ZERO(pdev);
 }
 
 static  int __init omap_i2c_cmdline(void)
diff --git a/arch/arm/mach-omap2/id.c b/arch/arm/mach-omap2/id.c
index 2dc62a25f2c3..0289adcb6efb 100644
--- a/arch/arm/mach-omap2/id.c
+++ b/arch/arm/mach-omap2/id.c
@@ -61,7 +61,7 @@ int omap_type(void)
 		val = omap_ctrl_readl(OMAP343X_CONTROL_STATUS);
 	} else if (cpu_is_omap44xx()) {
 		val = omap_ctrl_readl(OMAP4_CTRL_MODULE_CORE_STATUS);
-	} else if (soc_is_omap54xx()) {
+	} else if (soc_is_omap54xx() || soc_is_dra7xx()) {
 		val = omap_ctrl_readl(OMAP5XXX_CONTROL_STATUS);
 		val &= OMAP5_DEVICETYPE_MASK;
 		val >>= 6;
@@ -116,7 +116,7 @@ static u16 tap_prod_id;
 
 void omap_get_die_id(struct omap_die_id *odi)
 {
-	if (cpu_is_omap44xx() || soc_is_omap54xx()) {
+	if (cpu_is_omap44xx() || soc_is_omap54xx() || soc_is_dra7xx()) {
 		odi->id_0 = read_tap_reg(OMAP_TAP_DIE_ID_44XX_0);
 		odi->id_1 = read_tap_reg(OMAP_TAP_DIE_ID_44XX_1);
 		odi->id_2 = read_tap_reg(OMAP_TAP_DIE_ID_44XX_2);
diff --git a/arch/arm/mach-omap2/io.c b/arch/arm/mach-omap2/io.c
index 4a3f06f02859..ff2113ce4014 100644
--- a/arch/arm/mach-omap2/io.c
+++ b/arch/arm/mach-omap2/io.c
@@ -251,7 +251,7 @@ static struct map_desc omap44xx_io_desc[] __initdata = {
 };
 #endif
 
-#ifdef	CONFIG_SOC_OMAP5
+#if defined(CONFIG_SOC_OMAP5) || defined(CONFIG_SOC_DRA7XX)
 static struct map_desc omap54xx_io_desc[] __initdata = {
 	{
 		.virtual	= L3_54XX_VIRT,
@@ -333,7 +333,7 @@ void __init omap4_map_io(void)
 }
 #endif
 
-#ifdef CONFIG_SOC_OMAP5
+#if defined(CONFIG_SOC_OMAP5) ||  defined(CONFIG_SOC_DRA7XX)
 void __init omap5_map_io(void)
 {
 	iotable_init(omap54xx_io_desc, ARRAY_SIZE(omap54xx_io_desc));
@@ -653,6 +653,27 @@ void __init omap5_init_early(void)
 }
 #endif
 
+#ifdef CONFIG_SOC_DRA7XX
+void __init dra7xx_init_early(void)
+{
+	omap2_set_globals_tap(-1, OMAP2_L4_IO_ADDRESS(DRA7XX_TAP_BASE));
+	omap2_set_globals_control(OMAP2_L4_IO_ADDRESS(OMAP54XX_SCM_BASE),
+				  OMAP2_L4_IO_ADDRESS(DRA7XX_CTRL_BASE));
+	omap2_set_globals_prm(OMAP2_L4_IO_ADDRESS(OMAP54XX_PRM_BASE));
+	omap2_set_globals_cm(OMAP2_L4_IO_ADDRESS(DRA7XX_CM_CORE_AON_BASE),
+			     OMAP2_L4_IO_ADDRESS(OMAP54XX_CM_CORE_BASE));
+	omap2_set_globals_prcm_mpu(OMAP2_L4_IO_ADDRESS(OMAP54XX_PRCM_MPU_BASE));
+	omap_prm_base_init();
+	omap_cm_base_init();
+	omap44xx_prm_init();
+	dra7xx_powerdomains_init();
+	dra7xx_clockdomains_init();
+	dra7xx_hwmod_init();
+	omap_hwmod_init_postsetup();
+}
+#endif
+
+
 void __init omap_sdrc_init(struct omap_sdrc_params *sdrc_cs0,
 				      struct omap_sdrc_params *sdrc_cs1)
 {
diff --git a/arch/arm/mach-omap2/mux.h b/arch/arm/mach-omap2/mux.h
index 5d2080ef7923..16f78a990d04 100644
--- a/arch/arm/mach-omap2/mux.h
+++ b/arch/arm/mach-omap2/mux.h
@@ -28,7 +28,7 @@
 #define OMAP_PULL_UP			(1 << 4)
 #define OMAP_ALTELECTRICALSEL		(1 << 5)
 
-/* 34xx specific mux bit defines */
+/* omap3/4/5 specific mux bit defines */
 #define OMAP_INPUT_EN			(1 << 8)
 #define OMAP_OFF_EN			(1 << 9)
 #define OMAP_OFFOUT_EN			(1 << 10)
@@ -36,8 +36,6 @@
 #define OMAP_OFF_PULL_EN		(1 << 12)
 #define OMAP_OFF_PULL_UP		(1 << 13)
 #define OMAP_WAKEUP_EN			(1 << 14)
-
-/* 44xx specific mux bit defines */
 #define OMAP_WAKEUP_EVENT		(1 << 15)
 
 /* Active pin states */
diff --git a/arch/arm/mach-omap2/mux34xx.c b/arch/arm/mach-omap2/mux34xx.c
index c53609f46294..be271f1d585b 100644
--- a/arch/arm/mach-omap2/mux34xx.c
+++ b/arch/arm/mach-omap2/mux34xx.c
@@ -620,7 +620,7 @@ static struct omap_mux __initdata omap3_muxmodes[] = {
 		"uart1_rts", "ssi1_flag_tx", NULL, NULL,
 		"gpio_149", NULL, NULL, "safe_mode"),
 	_OMAP3_MUXENTRY(UART1_RX, 151,
-		"uart1_rx", "ss1_wake_tx", "mcbsp1_clkr", "mcspi4_clk",
+		"uart1_rx", "ssi1_wake_tx", "mcbsp1_clkr", "mcspi4_clk",
 		"gpio_151", NULL, NULL, "safe_mode"),
 	_OMAP3_MUXENTRY(UART1_TX, 148,
 		"uart1_tx", "ssi1_dat_tx", NULL, NULL,
diff --git a/arch/arm/mach-omap2/omap-smp.c b/arch/arm/mach-omap2/omap-smp.c
index 8708b2a9da45..891211093295 100644
--- a/arch/arm/mach-omap2/omap-smp.c
+++ b/arch/arm/mach-omap2/omap-smp.c
@@ -1,5 +1,5 @@
 /*
- * OMAP4 SMP source file. It contains platform specific fucntions
+ * OMAP4 SMP source file. It contains platform specific functions
  * needed for the linux smp kernel.
  *
  * Copyright (C) 2009 Texas Instruments, Inc.
diff --git a/arch/arm/mach-omap2/omap54xx.h b/arch/arm/mach-omap2/omap54xx.h
index a086ba15868b..2d35c5709408 100644
--- a/arch/arm/mach-omap2/omap54xx.h
+++ b/arch/arm/mach-omap2/omap54xx.h
@@ -30,4 +30,8 @@
 #define OMAP54XX_CTRL_BASE		0x4a002800
 #define OMAP54XX_SAR_RAM_BASE		0x4ae26000
 
+#define DRA7XX_CM_CORE_AON_BASE		0x4a005000
+#define DRA7XX_CTRL_BASE		0x4a003400
+#define DRA7XX_TAP_BASE			0x4ae0c000
+
 #endif /* __ASM_SOC_OMAP555554XX_H */
diff --git a/arch/arm/mach-omap2/omap_device.c b/arch/arm/mach-omap2/omap_device.c
index f99f68e1e85b..b69dd9abb50a 100644
--- a/arch/arm/mach-omap2/omap_device.c
+++ b/arch/arm/mach-omap2/omap_device.c
@@ -158,7 +158,7 @@ static int omap_device_build_from_dt(struct platform_device *pdev)
 	}
 
 	od = omap_device_alloc(pdev, hwmods, oh_cnt);
-	if (!od) {
+	if (IS_ERR(od)) {
 		dev_err(&pdev->dev, "Cannot allocate omap_device for :%s\n",
 			oh_name);
 		ret = PTR_ERR(od);
diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c
index 7f4db12b1459..d9ee0ff094d4 100644
--- a/arch/arm/mach-omap2/omap_hwmod.c
+++ b/arch/arm/mach-omap2/omap_hwmod.c
@@ -1405,7 +1405,9 @@ static void _enable_sysc(struct omap_hwmod *oh)
 	    (sf & SYSC_HAS_CLOCKACTIVITY))
 		_set_clockactivity(oh, oh->class->sysc->clockact, &v);
 
-	_write_sysconfig(v, oh);
+	/* If the cached value is the same as the new value, skip the write */
+	if (oh->_sysc_cache != v)
+		_write_sysconfig(v, oh);
 
 	/*
 	 * Set the autoidle bit only after setting the smartidle bit
@@ -4113,7 +4115,7 @@ void __init omap_hwmod_init(void)
 		soc_ops.assert_hardreset = _omap2_assert_hardreset;
 		soc_ops.deassert_hardreset = _omap2_deassert_hardreset;
 		soc_ops.is_hardreset_asserted = _omap2_is_hardreset_asserted;
-	} else if (cpu_is_omap44xx() || soc_is_omap54xx()) {
+	} else if (cpu_is_omap44xx() || soc_is_omap54xx() || soc_is_dra7xx()) {
 		soc_ops.enable_module = _omap4_enable_module;
 		soc_ops.disable_module = _omap4_disable_module;
 		soc_ops.wait_target_ready = _omap4_wait_target_ready;
diff --git a/arch/arm/mach-omap2/omap_hwmod.h b/arch/arm/mach-omap2/omap_hwmod.h
index e1482a9b3bc2..d02acf9308d3 100644
--- a/arch/arm/mach-omap2/omap_hwmod.h
+++ b/arch/arm/mach-omap2/omap_hwmod.h
@@ -751,6 +751,7 @@ extern int omap3xxx_hwmod_init(void);
 extern int omap44xx_hwmod_init(void);
 extern int omap54xx_hwmod_init(void);
 extern int am33xx_hwmod_init(void);
+extern int dra7xx_hwmod_init(void);
 
 extern int __init omap_hwmod_register_links(struct omap_hwmod_ocp_if **ois);
 
diff --git a/arch/arm/mach-omap2/omap_hwmod_33xx_data.c b/arch/arm/mach-omap2/omap_hwmod_33xx_data.c
index eb2f3b93b51c..215894f8910d 100644
--- a/arch/arm/mach-omap2/omap_hwmod_33xx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_33xx_data.c
@@ -325,7 +325,6 @@ static struct omap_hwmod am33xx_adc_tsc_hwmod = {
  *
  *    - cEFUSE (doesn't fall under any ocp_if)
  *    - clkdiv32k
- *    - debugss
  *    - ocp watch point
  */
 #if 0
@@ -369,27 +368,6 @@ static struct omap_hwmod am33xx_clkdiv32k_hwmod = {
 	},
 };
 
-/*
- * 'debugss' class
- * debug sub system
- */
-static struct omap_hwmod_class am33xx_debugss_hwmod_class = {
-	.name		= "debugss",
-};
-
-static struct omap_hwmod am33xx_debugss_hwmod = {
-	.name		= "debugss",
-	.class		= &am33xx_debugss_hwmod_class,
-	.clkdm_name	= "l3_aon_clkdm",
-	.main_clk	= "debugss_ick",
-	.prcm		= {
-		.omap4	= {
-			.clkctrl_offs	= AM33XX_CM_WKUP_DEBUGSS_CLKCTRL_OFFSET,
-			.modulemode	= MODULEMODE_SWCTRL,
-		},
-	},
-};
-
 /* ocpwp */
 static struct omap_hwmod_class am33xx_ocpwp_hwmod_class = {
 	.name		= "ocpwp",
@@ -482,6 +460,34 @@ static struct omap_hwmod am33xx_ocmcram_hwmod = {
 	},
 };
 
+/*
+ * 'debugss' class
+ * debug sub system
+ */
+static struct omap_hwmod_opt_clk debugss_opt_clks[] = {
+	{ .role = "dbg_sysclk", .clk = "dbg_sysclk_ck" },
+	{ .role = "dbg_clka", .clk = "dbg_clka_ck" },
+};
+
+static struct omap_hwmod_class am33xx_debugss_hwmod_class = {
+	.name		= "debugss",
+};
+
+static struct omap_hwmod am33xx_debugss_hwmod = {
+	.name		= "debugss",
+	.class		= &am33xx_debugss_hwmod_class,
+	.clkdm_name	= "l3_aon_clkdm",
+	.main_clk	= "trace_clk_div_ck",
+	.prcm		= {
+		.omap4	= {
+			.clkctrl_offs	= AM33XX_CM_WKUP_DEBUGSS_CLKCTRL_OFFSET,
+			.modulemode	= MODULEMODE_SWCTRL,
+		},
+	},
+	.opt_clks	= debugss_opt_clks,
+	.opt_clks_cnt	= ARRAY_SIZE(debugss_opt_clks),
+};
+
 /* 'smartreflex' class */
 static struct omap_hwmod_class am33xx_smartreflex_hwmod_class = {
 	.name		= "smartreflex",
@@ -1796,6 +1802,24 @@ static struct omap_hwmod_ocp_if am33xx_l3_main__gfx = {
 	.user		= OCP_USER_MPU | OCP_USER_SDMA,
 };
 
+/* l3_main -> debugss */
+static struct omap_hwmod_addr_space am33xx_debugss_addrs[] = {
+	{
+		.pa_start	= 0x4b000000,
+		.pa_end		= 0x4b000000 + SZ_16M - 1,
+		.flags		= ADDR_TYPE_RT
+	},
+	{ }
+};
+
+static struct omap_hwmod_ocp_if am33xx_l3_main__debugss = {
+	.master		= &am33xx_l3_main_hwmod,
+	.slave		= &am33xx_debugss_hwmod,
+	.clk		= "dpll_core_m4_ck",
+	.addr		= am33xx_debugss_addrs,
+	.user		= OCP_USER_MPU,
+};
+
 /* l4 wkup -> smartreflex0 */
 static struct omap_hwmod_ocp_if am33xx_l4_wkup__smartreflex0 = {
 	.master		= &am33xx_l4_wkup_hwmod,
@@ -2470,6 +2494,7 @@ static struct omap_hwmod_ocp_if *am33xx_hwmod_ocp_ifs[] __initdata = {
 	&am33xx_pruss__l3_main,
 	&am33xx_wkup_m3__l4_wkup,
 	&am33xx_gfx__l3_main,
+	&am33xx_l3_main__debugss,
 	&am33xx_l4_wkup__wkup_m3,
 	&am33xx_l4_wkup__control,
 	&am33xx_l4_wkup__smartreflex0,
diff --git a/arch/arm/mach-omap2/omap_hwmod_54xx_data.c b/arch/arm/mach-omap2/omap_hwmod_54xx_data.c
index 3c70f5c1860f..cde415570e04 100644
--- a/arch/arm/mach-omap2/omap_hwmod_54xx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_54xx_data.c
@@ -32,7 +32,6 @@
 #include "cm1_54xx.h"
 #include "cm2_54xx.h"
 #include "prm54xx.h"
-#include "prm-regbits-54xx.h"
 #include "i2c.h"
 #include "mmc.h"
 #include "wd_timer.h"
@@ -741,6 +740,39 @@ static struct omap_hwmod omap54xx_kbd_hwmod = {
 };
 
 /*
+ * 'mailbox' class
+ * mailbox module allowing communication between the on-chip processors using a
+ * queued mailbox-interrupt mechanism.
+ */
+
+static struct omap_hwmod_class_sysconfig omap54xx_mailbox_sysc = {
+	.rev_offs	= 0x0000,
+	.sysc_offs	= 0x0010,
+	.sysc_flags	= (SYSC_HAS_RESET_STATUS | SYSC_HAS_SIDLEMODE |
+			   SYSC_HAS_SOFTRESET),
+	.idlemodes	= (SIDLE_FORCE | SIDLE_NO | SIDLE_SMART),
+	.sysc_fields	= &omap_hwmod_sysc_type2,
+};
+
+static struct omap_hwmod_class omap54xx_mailbox_hwmod_class = {
+	.name	= "mailbox",
+	.sysc	= &omap54xx_mailbox_sysc,
+};
+
+/* mailbox */
+static struct omap_hwmod omap54xx_mailbox_hwmod = {
+	.name		= "mailbox",
+	.class		= &omap54xx_mailbox_hwmod_class,
+	.clkdm_name	= "l4cfg_clkdm",
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = OMAP54XX_CM_L4CFG_MAILBOX_CLKCTRL_OFFSET,
+			.context_offs = OMAP54XX_RM_L4CFG_MAILBOX_CONTEXT_OFFSET,
+		},
+	},
+};
+
+/*
  * 'mcbsp' class
  * multi channel buffered serial port controller
  */
@@ -1808,6 +1840,14 @@ static struct omap_hwmod_ocp_if omap54xx_l4_wkup__kbd = {
 	.user		= OCP_USER_MPU | OCP_USER_SDMA,
 };
 
+/* l4_cfg -> mailbox */
+static struct omap_hwmod_ocp_if omap54xx_l4_cfg__mailbox = {
+	.master		= &omap54xx_l4_cfg_hwmod,
+	.slave		= &omap54xx_mailbox_hwmod,
+	.clk		= "l4_root_clk_div",
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
 /* l4_abe -> mcbsp1 */
 static struct omap_hwmod_ocp_if omap54xx_l4_abe__mcbsp1 = {
 	.master		= &omap54xx_l4_abe_hwmod,
@@ -2108,6 +2148,7 @@ static struct omap_hwmod_ocp_if *omap54xx_hwmod_ocp_ifs[] __initdata = {
 	&omap54xx_l4_per__i2c4,
 	&omap54xx_l4_per__i2c5,
 	&omap54xx_l4_wkup__kbd,
+	&omap54xx_l4_cfg__mailbox,
 	&omap54xx_l4_abe__mcbsp1,
 	&omap54xx_l4_abe__mcbsp2,
 	&omap54xx_l4_abe__mcbsp3,
diff --git a/arch/arm/mach-omap2/omap_hwmod_7xx_data.c b/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
new file mode 100644
index 000000000000..db32d5380b11
--- /dev/null
+++ b/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
@@ -0,0 +1,2724 @@
+/*
+ * Hardware modules present on the DRA7xx chips
+ *
+ * Copyright (C) 2013 Texas Instruments Incorporated - http://www.ti.com
+ *
+ * Paul Walmsley
+ * Benoit Cousson
+ *
+ * This file is automatically generated from the OMAP hardware databases.
+ * We respectfully ask that any modifications to this file be coordinated
+ * with the public linux-omap@vger.kernel.org mailing list and the
+ * authors above to ensure that the autogeneration scripts are kept
+ * up-to-date with the file contents.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/io.h>
+#include <linux/platform_data/gpio-omap.h>
+#include <linux/power/smartreflex.h>
+#include <linux/i2c-omap.h>
+
+#include <linux/omap-dma.h>
+#include <linux/platform_data/spi-omap2-mcspi.h>
+#include <linux/platform_data/asoc-ti-mcbsp.h>
+#include <plat/dmtimer.h>
+
+#include "omap_hwmod.h"
+#include "omap_hwmod_common_data.h"
+#include "cm1_7xx.h"
+#include "cm2_7xx.h"
+#include "prm7xx.h"
+#include "i2c.h"
+#include "mmc.h"
+#include "wd_timer.h"
+
+/* Base offset for all DRA7XX interrupts external to MPUSS */
+#define DRA7XX_IRQ_GIC_START	32
+
+/* Base offset for all DRA7XX dma requests */
+#define DRA7XX_DMA_REQ_START	1
+
+
+/*
+ * IP blocks
+ */
+
+/*
+ * 'l3' class
+ * instance(s): l3_instr, l3_main_1, l3_main_2
+ */
+static struct omap_hwmod_class dra7xx_l3_hwmod_class = {
+	.name	= "l3",
+};
+
+/* l3_instr */
+static struct omap_hwmod dra7xx_l3_instr_hwmod = {
+	.name		= "l3_instr",
+	.class		= &dra7xx_l3_hwmod_class,
+	.clkdm_name	= "l3instr_clkdm",
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = DRA7XX_CM_L3INSTR_L3_INSTR_CLKCTRL_OFFSET,
+			.context_offs = DRA7XX_RM_L3INSTR_L3_INSTR_CONTEXT_OFFSET,
+			.modulemode   = MODULEMODE_HWCTRL,
+		},
+	},
+};
+
+/* l3_main_1 */
+static struct omap_hwmod dra7xx_l3_main_1_hwmod = {
+	.name		= "l3_main_1",
+	.class		= &dra7xx_l3_hwmod_class,
+	.clkdm_name	= "l3main1_clkdm",
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = DRA7XX_CM_L3MAIN1_L3_MAIN_1_CLKCTRL_OFFSET,
+			.context_offs = DRA7XX_RM_L3MAIN1_L3_MAIN_1_CONTEXT_OFFSET,
+		},
+	},
+};
+
+/* l3_main_2 */
+static struct omap_hwmod dra7xx_l3_main_2_hwmod = {
+	.name		= "l3_main_2",
+	.class		= &dra7xx_l3_hwmod_class,
+	.clkdm_name	= "l3instr_clkdm",
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = DRA7XX_CM_L3INSTR_L3_MAIN_2_CLKCTRL_OFFSET,
+			.context_offs = DRA7XX_RM_L3INSTR_L3_MAIN_2_CONTEXT_OFFSET,
+			.modulemode   = MODULEMODE_HWCTRL,
+		},
+	},
+};
+
+/*
+ * 'l4' class
+ * instance(s): l4_cfg, l4_per1, l4_per2, l4_per3, l4_wkup
+ */
+static struct omap_hwmod_class dra7xx_l4_hwmod_class = {
+	.name	= "l4",
+};
+
+/* l4_cfg */
+static struct omap_hwmod dra7xx_l4_cfg_hwmod = {
+	.name		= "l4_cfg",
+	.class		= &dra7xx_l4_hwmod_class,
+	.clkdm_name	= "l4cfg_clkdm",
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = DRA7XX_CM_L4CFG_L4_CFG_CLKCTRL_OFFSET,
+			.context_offs = DRA7XX_RM_L4CFG_L4_CFG_CONTEXT_OFFSET,
+		},
+	},
+};
+
+/* l4_per1 */
+static struct omap_hwmod dra7xx_l4_per1_hwmod = {
+	.name		= "l4_per1",
+	.class		= &dra7xx_l4_hwmod_class,
+	.clkdm_name	= "l4per_clkdm",
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = DRA7XX_CM_L4PER_L4_PER1_CLKCTRL_OFFSET,
+			.flags = HWMOD_OMAP4_NO_CONTEXT_LOSS_BIT,
+		},
+	},
+};
+
+/* l4_per2 */
+static struct omap_hwmod dra7xx_l4_per2_hwmod = {
+	.name		= "l4_per2",
+	.class		= &dra7xx_l4_hwmod_class,
+	.clkdm_name	= "l4per2_clkdm",
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = DRA7XX_CM_L4PER2_L4_PER2_CLKCTRL_OFFSET,
+			.flags = HWMOD_OMAP4_NO_CONTEXT_LOSS_BIT,
+		},
+	},
+};
+
+/* l4_per3 */
+static struct omap_hwmod dra7xx_l4_per3_hwmod = {
+	.name		= "l4_per3",
+	.class		= &dra7xx_l4_hwmod_class,
+	.clkdm_name	= "l4per3_clkdm",
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = DRA7XX_CM_L4PER3_L4_PER3_CLKCTRL_OFFSET,
+			.flags = HWMOD_OMAP4_NO_CONTEXT_LOSS_BIT,
+		},
+	},
+};
+
+/* l4_wkup */
+static struct omap_hwmod dra7xx_l4_wkup_hwmod = {
+	.name		= "l4_wkup",
+	.class		= &dra7xx_l4_hwmod_class,
+	.clkdm_name	= "wkupaon_clkdm",
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = DRA7XX_CM_WKUPAON_L4_WKUP_CLKCTRL_OFFSET,
+			.context_offs = DRA7XX_RM_WKUPAON_L4_WKUP_CONTEXT_OFFSET,
+		},
+	},
+};
+
+/*
+ * 'atl' class
+ *
+ */
+
+static struct omap_hwmod_class dra7xx_atl_hwmod_class = {
+	.name	= "atl",
+};
+
+/* atl */
+static struct omap_hwmod dra7xx_atl_hwmod = {
+	.name		= "atl",
+	.class		= &dra7xx_atl_hwmod_class,
+	.clkdm_name	= "atl_clkdm",
+	.main_clk	= "atl_gfclk_mux",
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = DRA7XX_CM_ATL_ATL_CLKCTRL_OFFSET,
+			.context_offs = DRA7XX_RM_ATL_ATL_CONTEXT_OFFSET,
+			.modulemode   = MODULEMODE_SWCTRL,
+		},
+	},
+};
+
+/*
+ * 'bb2d' class
+ *
+ */
+
+static struct omap_hwmod_class dra7xx_bb2d_hwmod_class = {
+	.name	= "bb2d",
+};
+
+/* bb2d */
+static struct omap_hwmod dra7xx_bb2d_hwmod = {
+	.name		= "bb2d",
+	.class		= &dra7xx_bb2d_hwmod_class,
+	.clkdm_name	= "dss_clkdm",
+	.main_clk	= "dpll_core_h24x2_ck",
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = DRA7XX_CM_DSS_BB2D_CLKCTRL_OFFSET,
+			.context_offs = DRA7XX_RM_DSS_BB2D_CONTEXT_OFFSET,
+			.modulemode   = MODULEMODE_SWCTRL,
+		},
+	},
+};
+
+/*
+ * 'counter' class
+ *
+ */
+
+static struct omap_hwmod_class_sysconfig dra7xx_counter_sysc = {
+	.rev_offs	= 0x0000,
+	.sysc_offs	= 0x0010,
+	.sysc_flags	= SYSC_HAS_SIDLEMODE,
+	.idlemodes	= (SIDLE_FORCE | SIDLE_NO | SIDLE_SMART |
+			   SIDLE_SMART_WKUP),
+	.sysc_fields	= &omap_hwmod_sysc_type1,
+};
+
+static struct omap_hwmod_class dra7xx_counter_hwmod_class = {
+	.name	= "counter",
+	.sysc	= &dra7xx_counter_sysc,
+};
+
+/* counter_32k */
+static struct omap_hwmod dra7xx_counter_32k_hwmod = {
+	.name		= "counter_32k",
+	.class		= &dra7xx_counter_hwmod_class,
+	.clkdm_name	= "wkupaon_clkdm",
+	.flags		= HWMOD_SWSUP_SIDLE,
+	.main_clk	= "wkupaon_iclk_mux",
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = DRA7XX_CM_WKUPAON_COUNTER_32K_CLKCTRL_OFFSET,
+			.context_offs = DRA7XX_RM_WKUPAON_COUNTER_32K_CONTEXT_OFFSET,
+		},
+	},
+};
+
+/*
+ * 'ctrl_module' class
+ *
+ */
+
+static struct omap_hwmod_class dra7xx_ctrl_module_hwmod_class = {
+	.name	= "ctrl_module",
+};
+
+/* ctrl_module_wkup */
+static struct omap_hwmod dra7xx_ctrl_module_wkup_hwmod = {
+	.name		= "ctrl_module_wkup",
+	.class		= &dra7xx_ctrl_module_hwmod_class,
+	.clkdm_name	= "wkupaon_clkdm",
+	.prcm = {
+		.omap4 = {
+			.flags = HWMOD_OMAP4_NO_CONTEXT_LOSS_BIT,
+		},
+	},
+};
+
+/*
+ * 'dcan' class
+ *
+ */
+
+static struct omap_hwmod_class dra7xx_dcan_hwmod_class = {
+	.name	= "dcan",
+};
+
+/* dcan1 */
+static struct omap_hwmod dra7xx_dcan1_hwmod = {
+	.name		= "dcan1",
+	.class		= &dra7xx_dcan_hwmod_class,
+	.clkdm_name	= "wkupaon_clkdm",
+	.main_clk	= "dcan1_sys_clk_mux",
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = DRA7XX_CM_WKUPAON_DCAN1_CLKCTRL_OFFSET,
+			.context_offs = DRA7XX_RM_WKUPAON_DCAN1_CONTEXT_OFFSET,
+			.modulemode   = MODULEMODE_SWCTRL,
+		},
+	},
+};
+
+/* dcan2 */
+static struct omap_hwmod dra7xx_dcan2_hwmod = {
+	.name		= "dcan2",
+	.class		= &dra7xx_dcan_hwmod_class,
+	.clkdm_name	= "l4per2_clkdm",
+	.main_clk	= "sys_clkin1",
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = DRA7XX_CM_L4PER2_DCAN2_CLKCTRL_OFFSET,
+			.context_offs = DRA7XX_RM_L4PER2_DCAN2_CONTEXT_OFFSET,
+			.modulemode   = MODULEMODE_SWCTRL,
+		},
+	},
+};
+
+/*
+ * 'dma' class
+ *
+ */
+
+static struct omap_hwmod_class_sysconfig dra7xx_dma_sysc = {
+	.rev_offs	= 0x0000,
+	.sysc_offs	= 0x002c,
+	.syss_offs	= 0x0028,
+	.sysc_flags	= (SYSC_HAS_AUTOIDLE | SYSC_HAS_CLOCKACTIVITY |
+			   SYSC_HAS_EMUFREE | SYSC_HAS_MIDLEMODE |
+			   SYSC_HAS_SIDLEMODE | SYSC_HAS_SOFTRESET |
+			   SYSS_HAS_RESET_STATUS),
+	.idlemodes	= (SIDLE_FORCE | SIDLE_NO | SIDLE_SMART |
+			   SIDLE_SMART_WKUP | MSTANDBY_FORCE | MSTANDBY_NO |
+			   MSTANDBY_SMART | MSTANDBY_SMART_WKUP),
+	.sysc_fields	= &omap_hwmod_sysc_type1,
+};
+
+static struct omap_hwmod_class dra7xx_dma_hwmod_class = {
+	.name	= "dma",
+	.sysc	= &dra7xx_dma_sysc,
+};
+
+/* dma dev_attr */
+static struct omap_dma_dev_attr dma_dev_attr = {
+	.dev_caps	= RESERVE_CHANNEL | DMA_LINKED_LCH | GLOBAL_PRIORITY |
+			  IS_CSSA_32 | IS_CDSA_32 | IS_RW_PRIORITY,
+	.lch_count	= 32,
+};
+
+/* dma_system */
+static struct omap_hwmod_irq_info dra7xx_dma_system_irqs[] = {
+	{ .name = "0", .irq = 12 + DRA7XX_IRQ_GIC_START },
+	{ .name = "1", .irq = 13 + DRA7XX_IRQ_GIC_START },
+	{ .name = "2", .irq = 14 + DRA7XX_IRQ_GIC_START },
+	{ .name = "3", .irq = 15 + DRA7XX_IRQ_GIC_START },
+	{ .irq = -1 }
+};
+
+static struct omap_hwmod dra7xx_dma_system_hwmod = {
+	.name		= "dma_system",
+	.class		= &dra7xx_dma_hwmod_class,
+	.clkdm_name	= "dma_clkdm",
+	.mpu_irqs	= dra7xx_dma_system_irqs,
+	.main_clk	= "l3_iclk_div",
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = DRA7XX_CM_DMA_DMA_SYSTEM_CLKCTRL_OFFSET,
+			.context_offs = DRA7XX_RM_DMA_DMA_SYSTEM_CONTEXT_OFFSET,
+		},
+	},
+	.dev_attr	= &dma_dev_attr,
+};
+
+/*
+ * 'dss' class
+ *
+ */
+
+static struct omap_hwmod_class_sysconfig dra7xx_dss_sysc = {
+	.rev_offs	= 0x0000,
+	.syss_offs	= 0x0014,
+	.sysc_flags	= SYSS_HAS_RESET_STATUS,
+};
+
+static struct omap_hwmod_class dra7xx_dss_hwmod_class = {
+	.name	= "dss",
+	.sysc	= &dra7xx_dss_sysc,
+	.reset	= omap_dss_reset,
+};
+
+/* dss */
+static struct omap_hwmod_dma_info dra7xx_dss_sdma_reqs[] = {
+	{ .dma_req = 75 + DRA7XX_DMA_REQ_START },
+	{ .dma_req = -1 }
+};
+
+static struct omap_hwmod_opt_clk dss_opt_clks[] = {
+	{ .role = "dss_clk", .clk = "dss_dss_clk" },
+	{ .role = "hdmi_phy_clk", .clk = "dss_48mhz_clk" },
+	{ .role = "32khz_clk", .clk = "dss_32khz_clk" },
+	{ .role = "video2_clk", .clk = "dss_video2_clk" },
+	{ .role = "video1_clk", .clk = "dss_video1_clk" },
+	{ .role = "hdmi_clk", .clk = "dss_hdmi_clk" },
+};
+
+static struct omap_hwmod dra7xx_dss_hwmod = {
+	.name		= "dss_core",
+	.class		= &dra7xx_dss_hwmod_class,
+	.clkdm_name	= "dss_clkdm",
+	.flags		= HWMOD_CONTROL_OPT_CLKS_IN_RESET,
+	.sdma_reqs	= dra7xx_dss_sdma_reqs,
+	.main_clk	= "dss_dss_clk",
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = DRA7XX_CM_DSS_DSS_CLKCTRL_OFFSET,
+			.context_offs = DRA7XX_RM_DSS_DSS_CONTEXT_OFFSET,
+			.modulemode   = MODULEMODE_SWCTRL,
+		},
+	},
+	.opt_clks	= dss_opt_clks,
+	.opt_clks_cnt	= ARRAY_SIZE(dss_opt_clks),
+};
+
+/*
+ * 'dispc' class
+ * display controller
+ */
+
+static struct omap_hwmod_class_sysconfig dra7xx_dispc_sysc = {
+	.rev_offs	= 0x0000,
+	.sysc_offs	= 0x0010,
+	.syss_offs	= 0x0014,
+	.sysc_flags	= (SYSC_HAS_AUTOIDLE | SYSC_HAS_CLOCKACTIVITY |
+			   SYSC_HAS_ENAWAKEUP | SYSC_HAS_MIDLEMODE |
+			   SYSC_HAS_SIDLEMODE | SYSC_HAS_SOFTRESET |
+			   SYSS_HAS_RESET_STATUS),
+	.idlemodes	= (SIDLE_FORCE | SIDLE_NO | SIDLE_SMART |
+			   MSTANDBY_FORCE | MSTANDBY_NO | MSTANDBY_SMART),
+	.sysc_fields	= &omap_hwmod_sysc_type1,
+};
+
+static struct omap_hwmod_class dra7xx_dispc_hwmod_class = {
+	.name	= "dispc",
+	.sysc	= &dra7xx_dispc_sysc,
+};
+
+/* dss_dispc */
+/* dss_dispc dev_attr */
+static struct omap_dss_dispc_dev_attr dss_dispc_dev_attr = {
+	.has_framedonetv_irq	= 1,
+	.manager_count		= 4,
+};
+
+static struct omap_hwmod dra7xx_dss_dispc_hwmod = {
+	.name		= "dss_dispc",
+	.class		= &dra7xx_dispc_hwmod_class,
+	.clkdm_name	= "dss_clkdm",
+	.main_clk	= "dss_dss_clk",
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = DRA7XX_CM_DSS_DSS_CLKCTRL_OFFSET,
+			.flags = HWMOD_OMAP4_NO_CONTEXT_LOSS_BIT,
+		},
+	},
+	.dev_attr	= &dss_dispc_dev_attr,
+};
+
+/*
+ * 'hdmi' class
+ * hdmi controller
+ */
+
+static struct omap_hwmod_class_sysconfig dra7xx_hdmi_sysc = {
+	.rev_offs	= 0x0000,
+	.sysc_offs	= 0x0010,
+	.sysc_flags	= (SYSC_HAS_RESET_STATUS | SYSC_HAS_SIDLEMODE |
+			   SYSC_HAS_SOFTRESET),
+	.idlemodes	= (SIDLE_FORCE | SIDLE_NO | SIDLE_SMART |
+			   SIDLE_SMART_WKUP),
+	.sysc_fields	= &omap_hwmod_sysc_type2,
+};
+
+static struct omap_hwmod_class dra7xx_hdmi_hwmod_class = {
+	.name	= "hdmi",
+	.sysc	= &dra7xx_hdmi_sysc,
+};
+
+/* dss_hdmi */
+
+static struct omap_hwmod_opt_clk dss_hdmi_opt_clks[] = {
+	{ .role = "sys_clk", .clk = "dss_hdmi_clk" },
+};
+
+static struct omap_hwmod dra7xx_dss_hdmi_hwmod = {
+	.name		= "dss_hdmi",
+	.class		= &dra7xx_hdmi_hwmod_class,
+	.clkdm_name	= "dss_clkdm",
+	.main_clk	= "dss_48mhz_clk",
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = DRA7XX_CM_DSS_DSS_CLKCTRL_OFFSET,
+			.flags = HWMOD_OMAP4_NO_CONTEXT_LOSS_BIT,
+		},
+	},
+	.opt_clks	= dss_hdmi_opt_clks,
+	.opt_clks_cnt	= ARRAY_SIZE(dss_hdmi_opt_clks),
+};
+
+/*
+ * 'elm' class
+ *
+ */
+
+static struct omap_hwmod_class_sysconfig dra7xx_elm_sysc = {
+	.rev_offs	= 0x0000,
+	.sysc_offs	= 0x0010,
+	.syss_offs	= 0x0014,
+	.sysc_flags	= (SYSC_HAS_AUTOIDLE | SYSC_HAS_CLOCKACTIVITY |
+			   SYSC_HAS_SIDLEMODE | SYSC_HAS_SOFTRESET |
+			   SYSS_HAS_RESET_STATUS),
+	.idlemodes	= (SIDLE_FORCE | SIDLE_NO | SIDLE_SMART |
+			   SIDLE_SMART_WKUP),
+	.sysc_fields	= &omap_hwmod_sysc_type1,
+};
+
+static struct omap_hwmod_class dra7xx_elm_hwmod_class = {
+	.name	= "elm",
+	.sysc	= &dra7xx_elm_sysc,
+};
+
+/* elm */
+
+static struct omap_hwmod dra7xx_elm_hwmod = {
+	.name		= "elm",
+	.class		= &dra7xx_elm_hwmod_class,
+	.clkdm_name	= "l4per_clkdm",
+	.main_clk	= "l3_iclk_div",
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = DRA7XX_CM_L4PER_ELM_CLKCTRL_OFFSET,
+			.context_offs = DRA7XX_RM_L4PER_ELM_CONTEXT_OFFSET,
+		},
+	},
+};
+
+/*
+ * 'gpio' class
+ *
+ */
+
+static struct omap_hwmod_class_sysconfig dra7xx_gpio_sysc = {
+	.rev_offs	= 0x0000,
+	.sysc_offs	= 0x0010,
+	.syss_offs	= 0x0114,
+	.sysc_flags	= (SYSC_HAS_AUTOIDLE | SYSC_HAS_ENAWAKEUP |
+			   SYSC_HAS_SIDLEMODE | SYSC_HAS_SOFTRESET |
+			   SYSS_HAS_RESET_STATUS),
+	.idlemodes	= (SIDLE_FORCE | SIDLE_NO | SIDLE_SMART |
+			   SIDLE_SMART_WKUP),
+	.sysc_fields	= &omap_hwmod_sysc_type1,
+};
+
+static struct omap_hwmod_class dra7xx_gpio_hwmod_class = {
+	.name	= "gpio",
+	.sysc	= &dra7xx_gpio_sysc,
+	.rev	= 2,
+};
+
+/* gpio dev_attr */
+static struct omap_gpio_dev_attr gpio_dev_attr = {
+	.bank_width	= 32,
+	.dbck_flag	= true,
+};
+
+/* gpio1 */
+static struct omap_hwmod_opt_clk gpio1_opt_clks[] = {
+	{ .role = "dbclk", .clk = "gpio1_dbclk" },
+};
+
+static struct omap_hwmod dra7xx_gpio1_hwmod = {
+	.name		= "gpio1",
+	.class		= &dra7xx_gpio_hwmod_class,
+	.clkdm_name	= "wkupaon_clkdm",
+	.main_clk	= "wkupaon_iclk_mux",
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = DRA7XX_CM_WKUPAON_GPIO1_CLKCTRL_OFFSET,
+			.context_offs = DRA7XX_RM_WKUPAON_GPIO1_CONTEXT_OFFSET,
+			.modulemode   = MODULEMODE_HWCTRL,
+		},
+	},
+	.opt_clks	= gpio1_opt_clks,
+	.opt_clks_cnt	= ARRAY_SIZE(gpio1_opt_clks),
+	.dev_attr	= &gpio_dev_attr,
+};
+
+/* gpio2 */
+static struct omap_hwmod_opt_clk gpio2_opt_clks[] = {
+	{ .role = "dbclk", .clk = "gpio2_dbclk" },
+};
+
+static struct omap_hwmod dra7xx_gpio2_hwmod = {
+	.name		= "gpio2",
+	.class		= &dra7xx_gpio_hwmod_class,
+	.clkdm_name	= "l4per_clkdm",
+	.flags		= HWMOD_CONTROL_OPT_CLKS_IN_RESET,
+	.main_clk	= "l3_iclk_div",
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = DRA7XX_CM_L4PER_GPIO2_CLKCTRL_OFFSET,
+			.context_offs = DRA7XX_RM_L4PER_GPIO2_CONTEXT_OFFSET,
+			.modulemode   = MODULEMODE_HWCTRL,
+		},
+	},
+	.opt_clks	= gpio2_opt_clks,
+	.opt_clks_cnt	= ARRAY_SIZE(gpio2_opt_clks),
+	.dev_attr	= &gpio_dev_attr,
+};
+
+/* gpio3 */
+static struct omap_hwmod_opt_clk gpio3_opt_clks[] = {
+	{ .role = "dbclk", .clk = "gpio3_dbclk" },
+};
+
+static struct omap_hwmod dra7xx_gpio3_hwmod = {
+	.name		= "gpio3",
+	.class		= &dra7xx_gpio_hwmod_class,
+	.clkdm_name	= "l4per_clkdm",
+	.flags		= HWMOD_CONTROL_OPT_CLKS_IN_RESET,
+	.main_clk	= "l3_iclk_div",
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = DRA7XX_CM_L4PER_GPIO3_CLKCTRL_OFFSET,
+			.context_offs = DRA7XX_RM_L4PER_GPIO3_CONTEXT_OFFSET,
+			.modulemode   = MODULEMODE_HWCTRL,
+		},
+	},
+	.opt_clks	= gpio3_opt_clks,
+	.opt_clks_cnt	= ARRAY_SIZE(gpio3_opt_clks),
+	.dev_attr	= &gpio_dev_attr,
+};
+
+/* gpio4 */
+static struct omap_hwmod_opt_clk gpio4_opt_clks[] = {
+	{ .role = "dbclk", .clk = "gpio4_dbclk" },
+};
+
+static struct omap_hwmod dra7xx_gpio4_hwmod = {
+	.name		= "gpio4",
+	.class		= &dra7xx_gpio_hwmod_class,
+	.clkdm_name	= "l4per_clkdm",
+	.flags		= HWMOD_CONTROL_OPT_CLKS_IN_RESET,
+	.main_clk	= "l3_iclk_div",
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = DRA7XX_CM_L4PER_GPIO4_CLKCTRL_OFFSET,
+			.context_offs = DRA7XX_RM_L4PER_GPIO4_CONTEXT_OFFSET,
+			.modulemode   = MODULEMODE_HWCTRL,
+		},
+	},
+	.opt_clks	= gpio4_opt_clks,
+	.opt_clks_cnt	= ARRAY_SIZE(gpio4_opt_clks),
+	.dev_attr	= &gpio_dev_attr,
+};
+
+/* gpio5 */
+static struct omap_hwmod_opt_clk gpio5_opt_clks[] = {
+	{ .role = "dbclk", .clk = "gpio5_dbclk" },
+};
+
+static struct omap_hwmod dra7xx_gpio5_hwmod = {
+	.name		= "gpio5",
+	.class		= &dra7xx_gpio_hwmod_class,
+	.clkdm_name	= "l4per_clkdm",
+	.flags		= HWMOD_CONTROL_OPT_CLKS_IN_RESET,
+	.main_clk	= "l3_iclk_div",
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = DRA7XX_CM_L4PER_GPIO5_CLKCTRL_OFFSET,
+			.context_offs = DRA7XX_RM_L4PER_GPIO5_CONTEXT_OFFSET,
+			.modulemode   = MODULEMODE_HWCTRL,
+		},
+	},
+	.opt_clks	= gpio5_opt_clks,
+	.opt_clks_cnt	= ARRAY_SIZE(gpio5_opt_clks),
+	.dev_attr	= &gpio_dev_attr,
+};
+
+/* gpio6 */
+static struct omap_hwmod_opt_clk gpio6_opt_clks[] = {
+	{ .role = "dbclk", .clk = "gpio6_dbclk" },
+};
+
+static struct omap_hwmod dra7xx_gpio6_hwmod = {
+	.name		= "gpio6",
+	.class		= &dra7xx_gpio_hwmod_class,
+	.clkdm_name	= "l4per_clkdm",
+	.flags		= HWMOD_CONTROL_OPT_CLKS_IN_RESET,
+	.main_clk	= "l3_iclk_div",
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = DRA7XX_CM_L4PER_GPIO6_CLKCTRL_OFFSET,
+			.context_offs = DRA7XX_RM_L4PER_GPIO6_CONTEXT_OFFSET,
+			.modulemode   = MODULEMODE_HWCTRL,
+		},
+	},
+	.opt_clks	= gpio6_opt_clks,
+	.opt_clks_cnt	= ARRAY_SIZE(gpio6_opt_clks),
+	.dev_attr	= &gpio_dev_attr,
+};
+
+/* gpio7 */
+static struct omap_hwmod_opt_clk gpio7_opt_clks[] = {
+	{ .role = "dbclk", .clk = "gpio7_dbclk" },
+};
+
+static struct omap_hwmod dra7xx_gpio7_hwmod = {
+	.name		= "gpio7",
+	.class		= &dra7xx_gpio_hwmod_class,
+	.clkdm_name	= "l4per_clkdm",
+	.flags		= HWMOD_CONTROL_OPT_CLKS_IN_RESET,
+	.main_clk	= "l3_iclk_div",
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = DRA7XX_CM_L4PER_GPIO7_CLKCTRL_OFFSET,
+			.context_offs = DRA7XX_RM_L4PER_GPIO7_CONTEXT_OFFSET,
+			.modulemode   = MODULEMODE_HWCTRL,
+		},
+	},
+	.opt_clks	= gpio7_opt_clks,
+	.opt_clks_cnt	= ARRAY_SIZE(gpio7_opt_clks),
+	.dev_attr	= &gpio_dev_attr,
+};
+
+/* gpio8 */
+static struct omap_hwmod_opt_clk gpio8_opt_clks[] = {
+	{ .role = "dbclk", .clk = "gpio8_dbclk" },
+};
+
+static struct omap_hwmod dra7xx_gpio8_hwmod = {
+	.name		= "gpio8",
+	.class		= &dra7xx_gpio_hwmod_class,
+	.clkdm_name	= "l4per_clkdm",
+	.flags		= HWMOD_CONTROL_OPT_CLKS_IN_RESET,
+	.main_clk	= "l3_iclk_div",
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = DRA7XX_CM_L4PER_GPIO8_CLKCTRL_OFFSET,
+			.context_offs = DRA7XX_RM_L4PER_GPIO8_CONTEXT_OFFSET,
+			.modulemode   = MODULEMODE_HWCTRL,
+		},
+	},
+	.opt_clks	= gpio8_opt_clks,
+	.opt_clks_cnt	= ARRAY_SIZE(gpio8_opt_clks),
+	.dev_attr	= &gpio_dev_attr,
+};
+
+/*
+ * 'gpmc' class
+ *
+ */
+
+static struct omap_hwmod_class_sysconfig dra7xx_gpmc_sysc = {
+	.rev_offs	= 0x0000,
+	.sysc_offs	= 0x0010,
+	.syss_offs	= 0x0014,
+	.sysc_flags	= (SYSC_HAS_AUTOIDLE | SYSC_HAS_SIDLEMODE |
+			   SYSC_HAS_SOFTRESET | SYSS_HAS_RESET_STATUS),
+	.idlemodes	= (SIDLE_FORCE | SIDLE_NO | SIDLE_SMART |
+			   SIDLE_SMART_WKUP),
+	.sysc_fields	= &omap_hwmod_sysc_type1,
+};
+
+static struct omap_hwmod_class dra7xx_gpmc_hwmod_class = {
+	.name	= "gpmc",
+	.sysc	= &dra7xx_gpmc_sysc,
+};
+
+/* gpmc */
+
+static struct omap_hwmod dra7xx_gpmc_hwmod = {
+	.name		= "gpmc",
+	.class		= &dra7xx_gpmc_hwmod_class,
+	.clkdm_name	= "l3main1_clkdm",
+	.flags		= HWMOD_INIT_NO_IDLE | HWMOD_INIT_NO_RESET,
+	.main_clk	= "l3_iclk_div",
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = DRA7XX_CM_L3MAIN1_GPMC_CLKCTRL_OFFSET,
+			.context_offs = DRA7XX_RM_L3MAIN1_GPMC_CONTEXT_OFFSET,
+			.modulemode   = MODULEMODE_HWCTRL,
+		},
+	},
+};
+
+/*
+ * 'hdq1w' class
+ *
+ */
+
+static struct omap_hwmod_class_sysconfig dra7xx_hdq1w_sysc = {
+	.rev_offs	= 0x0000,
+	.sysc_offs	= 0x0014,
+	.syss_offs	= 0x0018,
+	.sysc_flags	= (SYSC_HAS_AUTOIDLE | SYSC_HAS_SOFTRESET |
+			   SYSS_HAS_RESET_STATUS),
+	.sysc_fields	= &omap_hwmod_sysc_type1,
+};
+
+static struct omap_hwmod_class dra7xx_hdq1w_hwmod_class = {
+	.name	= "hdq1w",
+	.sysc	= &dra7xx_hdq1w_sysc,
+};
+
+/* hdq1w */
+
+static struct omap_hwmod dra7xx_hdq1w_hwmod = {
+	.name		= "hdq1w",
+	.class		= &dra7xx_hdq1w_hwmod_class,
+	.clkdm_name	= "l4per_clkdm",
+	.flags		= HWMOD_INIT_NO_RESET,
+	.main_clk	= "func_12m_fclk",
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = DRA7XX_CM_L4PER_HDQ1W_CLKCTRL_OFFSET,
+			.context_offs = DRA7XX_RM_L4PER_HDQ1W_CONTEXT_OFFSET,
+			.modulemode   = MODULEMODE_SWCTRL,
+		},
+	},
+};
+
+/*
+ * 'i2c' class
+ *
+ */
+
+static struct omap_hwmod_class_sysconfig dra7xx_i2c_sysc = {
+	.sysc_offs	= 0x0010,
+	.syss_offs	= 0x0090,
+	.sysc_flags	= (SYSC_HAS_AUTOIDLE | SYSC_HAS_CLOCKACTIVITY |
+			   SYSC_HAS_ENAWAKEUP | SYSC_HAS_SIDLEMODE |
+			   SYSC_HAS_SOFTRESET | SYSS_HAS_RESET_STATUS),
+	.idlemodes	= (SIDLE_FORCE | SIDLE_NO | SIDLE_SMART |
+			   SIDLE_SMART_WKUP),
+	.clockact	= CLOCKACT_TEST_ICLK,
+	.sysc_fields	= &omap_hwmod_sysc_type1,
+};
+
+static struct omap_hwmod_class dra7xx_i2c_hwmod_class = {
+	.name	= "i2c",
+	.sysc	= &dra7xx_i2c_sysc,
+	.reset	= &omap_i2c_reset,
+	.rev	= OMAP_I2C_IP_VERSION_2,
+};
+
+/* i2c dev_attr */
+static struct omap_i2c_dev_attr i2c_dev_attr = {
+	.flags	= OMAP_I2C_FLAG_BUS_SHIFT_NONE,
+};
+
+/* i2c1 */
+static struct omap_hwmod dra7xx_i2c1_hwmod = {
+	.name		= "i2c1",
+	.class		= &dra7xx_i2c_hwmod_class,
+	.clkdm_name	= "l4per_clkdm",
+	.flags		= HWMOD_16BIT_REG | HWMOD_SET_DEFAULT_CLOCKACT,
+	.main_clk	= "func_96m_fclk",
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = DRA7XX_CM_L4PER_I2C1_CLKCTRL_OFFSET,
+			.context_offs = DRA7XX_RM_L4PER_I2C1_CONTEXT_OFFSET,
+			.modulemode   = MODULEMODE_SWCTRL,
+		},
+	},
+	.dev_attr	= &i2c_dev_attr,
+};
+
+/* i2c2 */
+static struct omap_hwmod dra7xx_i2c2_hwmod = {
+	.name		= "i2c2",
+	.class		= &dra7xx_i2c_hwmod_class,
+	.clkdm_name	= "l4per_clkdm",
+	.flags		= HWMOD_16BIT_REG | HWMOD_SET_DEFAULT_CLOCKACT,
+	.main_clk	= "func_96m_fclk",
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = DRA7XX_CM_L4PER_I2C2_CLKCTRL_OFFSET,
+			.context_offs = DRA7XX_RM_L4PER_I2C2_CONTEXT_OFFSET,
+			.modulemode   = MODULEMODE_SWCTRL,
+		},
+	},
+	.dev_attr	= &i2c_dev_attr,
+};
+
+/* i2c3 */
+static struct omap_hwmod dra7xx_i2c3_hwmod = {
+	.name		= "i2c3",
+	.class		= &dra7xx_i2c_hwmod_class,
+	.clkdm_name	= "l4per_clkdm",
+	.flags		= HWMOD_16BIT_REG | HWMOD_SET_DEFAULT_CLOCKACT,
+	.main_clk	= "func_96m_fclk",
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = DRA7XX_CM_L4PER_I2C3_CLKCTRL_OFFSET,
+			.context_offs = DRA7XX_RM_L4PER_I2C3_CONTEXT_OFFSET,
+			.modulemode   = MODULEMODE_SWCTRL,
+		},
+	},
+	.dev_attr	= &i2c_dev_attr,
+};
+
+/* i2c4 */
+static struct omap_hwmod dra7xx_i2c4_hwmod = {
+	.name		= "i2c4",
+	.class		= &dra7xx_i2c_hwmod_class,
+	.clkdm_name	= "l4per_clkdm",
+	.flags		= HWMOD_16BIT_REG | HWMOD_SET_DEFAULT_CLOCKACT,
+	.main_clk	= "func_96m_fclk",
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = DRA7XX_CM_L4PER_I2C4_CLKCTRL_OFFSET,
+			.context_offs = DRA7XX_RM_L4PER_I2C4_CONTEXT_OFFSET,
+			.modulemode   = MODULEMODE_SWCTRL,
+		},
+	},
+	.dev_attr	= &i2c_dev_attr,
+};
+
+/* i2c5 */
+static struct omap_hwmod dra7xx_i2c5_hwmod = {
+	.name		= "i2c5",
+	.class		= &dra7xx_i2c_hwmod_class,
+	.clkdm_name	= "ipu_clkdm",
+	.flags		= HWMOD_16BIT_REG | HWMOD_SET_DEFAULT_CLOCKACT,
+	.main_clk	= "func_96m_fclk",
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = DRA7XX_CM_IPU_I2C5_CLKCTRL_OFFSET,
+			.context_offs = DRA7XX_RM_IPU_I2C5_CONTEXT_OFFSET,
+			.modulemode   = MODULEMODE_SWCTRL,
+		},
+	},
+	.dev_attr	= &i2c_dev_attr,
+};
+
+/*
+ * 'mcspi' class
+ *
+ */
+
+static struct omap_hwmod_class_sysconfig dra7xx_mcspi_sysc = {
+	.rev_offs	= 0x0000,
+	.sysc_offs	= 0x0010,
+	.sysc_flags	= (SYSC_HAS_EMUFREE | SYSC_HAS_RESET_STATUS |
+			   SYSC_HAS_SIDLEMODE | SYSC_HAS_SOFTRESET),
+	.idlemodes	= (SIDLE_FORCE | SIDLE_NO | SIDLE_SMART |
+			   SIDLE_SMART_WKUP),
+	.sysc_fields	= &omap_hwmod_sysc_type2,
+};
+
+static struct omap_hwmod_class dra7xx_mcspi_hwmod_class = {
+	.name	= "mcspi",
+	.sysc	= &dra7xx_mcspi_sysc,
+	.rev	= OMAP4_MCSPI_REV,
+};
+
+/* mcspi1 */
+/* mcspi1 dev_attr */
+static struct omap2_mcspi_dev_attr mcspi1_dev_attr = {
+	.num_chipselect	= 4,
+};
+
+static struct omap_hwmod dra7xx_mcspi1_hwmod = {
+	.name		= "mcspi1",
+	.class		= &dra7xx_mcspi_hwmod_class,
+	.clkdm_name	= "l4per_clkdm",
+	.main_clk	= "func_48m_fclk",
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = DRA7XX_CM_L4PER_MCSPI1_CLKCTRL_OFFSET,
+			.context_offs = DRA7XX_RM_L4PER_MCSPI1_CONTEXT_OFFSET,
+			.modulemode   = MODULEMODE_SWCTRL,
+		},
+	},
+	.dev_attr	= &mcspi1_dev_attr,
+};
+
+/* mcspi2 */
+/* mcspi2 dev_attr */
+static struct omap2_mcspi_dev_attr mcspi2_dev_attr = {
+	.num_chipselect	= 2,
+};
+
+static struct omap_hwmod dra7xx_mcspi2_hwmod = {
+	.name		= "mcspi2",
+	.class		= &dra7xx_mcspi_hwmod_class,
+	.clkdm_name	= "l4per_clkdm",
+	.main_clk	= "func_48m_fclk",
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = DRA7XX_CM_L4PER_MCSPI2_CLKCTRL_OFFSET,
+			.context_offs = DRA7XX_RM_L4PER_MCSPI2_CONTEXT_OFFSET,
+			.modulemode   = MODULEMODE_SWCTRL,
+		},
+	},
+	.dev_attr	= &mcspi2_dev_attr,
+};
+
+/* mcspi3 */
+/* mcspi3 dev_attr */
+static struct omap2_mcspi_dev_attr mcspi3_dev_attr = {
+	.num_chipselect	= 2,
+};
+
+static struct omap_hwmod dra7xx_mcspi3_hwmod = {
+	.name		= "mcspi3",
+	.class		= &dra7xx_mcspi_hwmod_class,
+	.clkdm_name	= "l4per_clkdm",
+	.main_clk	= "func_48m_fclk",
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = DRA7XX_CM_L4PER_MCSPI3_CLKCTRL_OFFSET,
+			.context_offs = DRA7XX_RM_L4PER_MCSPI3_CONTEXT_OFFSET,
+			.modulemode   = MODULEMODE_SWCTRL,
+		},
+	},
+	.dev_attr	= &mcspi3_dev_attr,
+};
+
+/* mcspi4 */
+/* mcspi4 dev_attr */
+static struct omap2_mcspi_dev_attr mcspi4_dev_attr = {
+	.num_chipselect	= 1,
+};
+
+static struct omap_hwmod dra7xx_mcspi4_hwmod = {
+	.name		= "mcspi4",
+	.class		= &dra7xx_mcspi_hwmod_class,
+	.clkdm_name	= "l4per_clkdm",
+	.main_clk	= "func_48m_fclk",
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = DRA7XX_CM_L4PER_MCSPI4_CLKCTRL_OFFSET,
+			.context_offs = DRA7XX_RM_L4PER_MCSPI4_CONTEXT_OFFSET,
+			.modulemode   = MODULEMODE_SWCTRL,
+		},
+	},
+	.dev_attr	= &mcspi4_dev_attr,
+};
+
+/*
+ * 'mmc' class
+ *
+ */
+
+static struct omap_hwmod_class_sysconfig dra7xx_mmc_sysc = {
+	.rev_offs	= 0x0000,
+	.sysc_offs	= 0x0010,
+	.sysc_flags	= (SYSC_HAS_EMUFREE | SYSC_HAS_MIDLEMODE |
+			   SYSC_HAS_RESET_STATUS | SYSC_HAS_SIDLEMODE |
+			   SYSC_HAS_SOFTRESET),
+	.idlemodes	= (SIDLE_FORCE | SIDLE_NO | SIDLE_SMART |
+			   SIDLE_SMART_WKUP | MSTANDBY_FORCE | MSTANDBY_NO |
+			   MSTANDBY_SMART | MSTANDBY_SMART_WKUP),
+	.sysc_fields	= &omap_hwmod_sysc_type2,
+};
+
+static struct omap_hwmod_class dra7xx_mmc_hwmod_class = {
+	.name	= "mmc",
+	.sysc	= &dra7xx_mmc_sysc,
+};
+
+/* mmc1 */
+static struct omap_hwmod_opt_clk mmc1_opt_clks[] = {
+	{ .role = "clk32k", .clk = "mmc1_clk32k" },
+};
+
+/* mmc1 dev_attr */
+static struct omap_mmc_dev_attr mmc1_dev_attr = {
+	.flags	= OMAP_HSMMC_SUPPORTS_DUAL_VOLT,
+};
+
+static struct omap_hwmod dra7xx_mmc1_hwmod = {
+	.name		= "mmc1",
+	.class		= &dra7xx_mmc_hwmod_class,
+	.clkdm_name	= "l3init_clkdm",
+	.main_clk	= "mmc1_fclk_div",
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = DRA7XX_CM_L3INIT_MMC1_CLKCTRL_OFFSET,
+			.context_offs = DRA7XX_RM_L3INIT_MMC1_CONTEXT_OFFSET,
+			.modulemode   = MODULEMODE_SWCTRL,
+		},
+	},
+	.opt_clks	= mmc1_opt_clks,
+	.opt_clks_cnt	= ARRAY_SIZE(mmc1_opt_clks),
+	.dev_attr	= &mmc1_dev_attr,
+};
+
+/* mmc2 */
+static struct omap_hwmod_opt_clk mmc2_opt_clks[] = {
+	{ .role = "clk32k", .clk = "mmc2_clk32k" },
+};
+
+static struct omap_hwmod dra7xx_mmc2_hwmod = {
+	.name		= "mmc2",
+	.class		= &dra7xx_mmc_hwmod_class,
+	.clkdm_name	= "l3init_clkdm",
+	.main_clk	= "mmc2_fclk_div",
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = DRA7XX_CM_L3INIT_MMC2_CLKCTRL_OFFSET,
+			.context_offs = DRA7XX_RM_L3INIT_MMC2_CONTEXT_OFFSET,
+			.modulemode   = MODULEMODE_SWCTRL,
+		},
+	},
+	.opt_clks	= mmc2_opt_clks,
+	.opt_clks_cnt	= ARRAY_SIZE(mmc2_opt_clks),
+};
+
+/* mmc3 */
+static struct omap_hwmod_opt_clk mmc3_opt_clks[] = {
+	{ .role = "clk32k", .clk = "mmc3_clk32k" },
+};
+
+static struct omap_hwmod dra7xx_mmc3_hwmod = {
+	.name		= "mmc3",
+	.class		= &dra7xx_mmc_hwmod_class,
+	.clkdm_name	= "l4per_clkdm",
+	.main_clk	= "mmc3_gfclk_div",
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = DRA7XX_CM_L4PER_MMC3_CLKCTRL_OFFSET,
+			.context_offs = DRA7XX_RM_L4PER_MMC3_CONTEXT_OFFSET,
+			.modulemode   = MODULEMODE_SWCTRL,
+		},
+	},
+	.opt_clks	= mmc3_opt_clks,
+	.opt_clks_cnt	= ARRAY_SIZE(mmc3_opt_clks),
+};
+
+/* mmc4 */
+static struct omap_hwmod_opt_clk mmc4_opt_clks[] = {
+	{ .role = "clk32k", .clk = "mmc4_clk32k" },
+};
+
+static struct omap_hwmod dra7xx_mmc4_hwmod = {
+	.name		= "mmc4",
+	.class		= &dra7xx_mmc_hwmod_class,
+	.clkdm_name	= "l4per_clkdm",
+	.main_clk	= "mmc4_gfclk_div",
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = DRA7XX_CM_L4PER_MMC4_CLKCTRL_OFFSET,
+			.context_offs = DRA7XX_RM_L4PER_MMC4_CONTEXT_OFFSET,
+			.modulemode   = MODULEMODE_SWCTRL,
+		},
+	},
+	.opt_clks	= mmc4_opt_clks,
+	.opt_clks_cnt	= ARRAY_SIZE(mmc4_opt_clks),
+};
+
+/*
+ * 'mpu' class
+ *
+ */
+
+static struct omap_hwmod_class dra7xx_mpu_hwmod_class = {
+	.name	= "mpu",
+};
+
+/* mpu */
+static struct omap_hwmod dra7xx_mpu_hwmod = {
+	.name		= "mpu",
+	.class		= &dra7xx_mpu_hwmod_class,
+	.clkdm_name	= "mpu_clkdm",
+	.flags		= HWMOD_INIT_NO_IDLE | HWMOD_INIT_NO_RESET,
+	.main_clk	= "dpll_mpu_m2_ck",
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = DRA7XX_CM_MPU_MPU_CLKCTRL_OFFSET,
+			.context_offs = DRA7XX_RM_MPU_MPU_CONTEXT_OFFSET,
+		},
+	},
+};
+
+/*
+ * 'ocp2scp' class
+ *
+ */
+
+static struct omap_hwmod_class_sysconfig dra7xx_ocp2scp_sysc = {
+	.rev_offs	= 0x0000,
+	.sysc_offs	= 0x0010,
+	.syss_offs	= 0x0014,
+	.sysc_flags	= (SYSC_HAS_AUTOIDLE | SYSC_HAS_SIDLEMODE |
+			   SYSC_HAS_SOFTRESET | SYSS_HAS_RESET_STATUS),
+	.idlemodes	= (SIDLE_FORCE | SIDLE_NO | SIDLE_SMART |
+			   SIDLE_SMART_WKUP),
+	.sysc_fields	= &omap_hwmod_sysc_type1,
+};
+
+static struct omap_hwmod_class dra7xx_ocp2scp_hwmod_class = {
+	.name	= "ocp2scp",
+	.sysc	= &dra7xx_ocp2scp_sysc,
+};
+
+/* ocp2scp1 */
+static struct omap_hwmod dra7xx_ocp2scp1_hwmod = {
+	.name		= "ocp2scp1",
+	.class		= &dra7xx_ocp2scp_hwmod_class,
+	.clkdm_name	= "l3init_clkdm",
+	.main_clk	= "l4_root_clk_div",
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = DRA7XX_CM_L3INIT_OCP2SCP1_CLKCTRL_OFFSET,
+			.context_offs = DRA7XX_RM_L3INIT_OCP2SCP1_CONTEXT_OFFSET,
+			.modulemode   = MODULEMODE_HWCTRL,
+		},
+	},
+};
+
+/*
+ * 'qspi' class
+ *
+ */
+
+static struct omap_hwmod_class_sysconfig dra7xx_qspi_sysc = {
+	.sysc_offs	= 0x0010,
+	.sysc_flags	= SYSC_HAS_SIDLEMODE,
+	.idlemodes	= (SIDLE_FORCE | SIDLE_NO | SIDLE_SMART |
+			   SIDLE_SMART_WKUP),
+	.sysc_fields	= &omap_hwmod_sysc_type2,
+};
+
+static struct omap_hwmod_class dra7xx_qspi_hwmod_class = {
+	.name	= "qspi",
+	.sysc	= &dra7xx_qspi_sysc,
+};
+
+/* qspi */
+static struct omap_hwmod dra7xx_qspi_hwmod = {
+	.name		= "qspi",
+	.class		= &dra7xx_qspi_hwmod_class,
+	.clkdm_name	= "l4per2_clkdm",
+	.main_clk	= "qspi_gfclk_div",
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = DRA7XX_CM_L4PER2_QSPI_CLKCTRL_OFFSET,
+			.context_offs = DRA7XX_RM_L4PER2_QSPI_CONTEXT_OFFSET,
+			.modulemode   = MODULEMODE_SWCTRL,
+		},
+	},
+};
+
+/*
+ * 'sata' class
+ *
+ */
+
+static struct omap_hwmod_class_sysconfig dra7xx_sata_sysc = {
+	.sysc_offs	= 0x0000,
+	.sysc_flags	= (SYSC_HAS_MIDLEMODE | SYSC_HAS_SIDLEMODE),
+	.idlemodes	= (SIDLE_FORCE | SIDLE_NO | SIDLE_SMART |
+			   SIDLE_SMART_WKUP | MSTANDBY_FORCE | MSTANDBY_NO |
+			   MSTANDBY_SMART | MSTANDBY_SMART_WKUP),
+	.sysc_fields	= &omap_hwmod_sysc_type2,
+};
+
+static struct omap_hwmod_class dra7xx_sata_hwmod_class = {
+	.name	= "sata",
+	.sysc	= &dra7xx_sata_sysc,
+};
+
+/* sata */
+static struct omap_hwmod_opt_clk sata_opt_clks[] = {
+	{ .role = "ref_clk", .clk = "sata_ref_clk" },
+};
+
+static struct omap_hwmod dra7xx_sata_hwmod = {
+	.name		= "sata",
+	.class		= &dra7xx_sata_hwmod_class,
+	.clkdm_name	= "l3init_clkdm",
+	.flags		= HWMOD_SWSUP_SIDLE | HWMOD_SWSUP_MSTANDBY,
+	.main_clk	= "func_48m_fclk",
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = DRA7XX_CM_L3INIT_SATA_CLKCTRL_OFFSET,
+			.context_offs = DRA7XX_RM_L3INIT_SATA_CONTEXT_OFFSET,
+			.modulemode   = MODULEMODE_SWCTRL,
+		},
+	},
+	.opt_clks	= sata_opt_clks,
+	.opt_clks_cnt	= ARRAY_SIZE(sata_opt_clks),
+};
+
+/*
+ * 'smartreflex' class
+ *
+ */
+
+/* The IP is not compliant to type1 / type2 scheme */
+static struct omap_hwmod_sysc_fields omap_hwmod_sysc_type_smartreflex = {
+	.sidle_shift	= 24,
+	.enwkup_shift	= 26,
+};
+
+static struct omap_hwmod_class_sysconfig dra7xx_smartreflex_sysc = {
+	.sysc_offs	= 0x0038,
+	.sysc_flags	= (SYSC_HAS_ENAWAKEUP | SYSC_HAS_SIDLEMODE),
+	.idlemodes	= (SIDLE_FORCE | SIDLE_NO | SIDLE_SMART |
+			   SIDLE_SMART_WKUP),
+	.sysc_fields	= &omap_hwmod_sysc_type_smartreflex,
+};
+
+static struct omap_hwmod_class dra7xx_smartreflex_hwmod_class = {
+	.name	= "smartreflex",
+	.sysc	= &dra7xx_smartreflex_sysc,
+	.rev	= 2,
+};
+
+/* smartreflex_core */
+/* smartreflex_core dev_attr */
+static struct omap_smartreflex_dev_attr smartreflex_core_dev_attr = {
+	.sensor_voltdm_name	= "core",
+};
+
+static struct omap_hwmod dra7xx_smartreflex_core_hwmod = {
+	.name		= "smartreflex_core",
+	.class		= &dra7xx_smartreflex_hwmod_class,
+	.clkdm_name	= "coreaon_clkdm",
+	.main_clk	= "wkupaon_iclk_mux",
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = DRA7XX_CM_COREAON_SMARTREFLEX_CORE_CLKCTRL_OFFSET,
+			.context_offs = DRA7XX_RM_COREAON_SMARTREFLEX_CORE_CONTEXT_OFFSET,
+			.modulemode   = MODULEMODE_SWCTRL,
+		},
+	},
+	.dev_attr	= &smartreflex_core_dev_attr,
+};
+
+/* smartreflex_mpu */
+/* smartreflex_mpu dev_attr */
+static struct omap_smartreflex_dev_attr smartreflex_mpu_dev_attr = {
+	.sensor_voltdm_name	= "mpu",
+};
+
+static struct omap_hwmod dra7xx_smartreflex_mpu_hwmod = {
+	.name		= "smartreflex_mpu",
+	.class		= &dra7xx_smartreflex_hwmod_class,
+	.clkdm_name	= "coreaon_clkdm",
+	.main_clk	= "wkupaon_iclk_mux",
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = DRA7XX_CM_COREAON_SMARTREFLEX_MPU_CLKCTRL_OFFSET,
+			.context_offs = DRA7XX_RM_COREAON_SMARTREFLEX_MPU_CONTEXT_OFFSET,
+			.modulemode   = MODULEMODE_SWCTRL,
+		},
+	},
+	.dev_attr	= &smartreflex_mpu_dev_attr,
+};
+
+/*
+ * 'spinlock' class
+ *
+ */
+
+static struct omap_hwmod_class_sysconfig dra7xx_spinlock_sysc = {
+	.rev_offs	= 0x0000,
+	.sysc_offs	= 0x0010,
+	.syss_offs	= 0x0014,
+	.sysc_flags	= (SYSC_HAS_AUTOIDLE | SYSC_HAS_CLOCKACTIVITY |
+			   SYSC_HAS_ENAWAKEUP | SYSC_HAS_SIDLEMODE |
+			   SYSC_HAS_SOFTRESET | SYSS_HAS_RESET_STATUS),
+	.idlemodes	= (SIDLE_FORCE | SIDLE_NO | SIDLE_SMART |
+			   SIDLE_SMART_WKUP),
+	.sysc_fields	= &omap_hwmod_sysc_type1,
+};
+
+static struct omap_hwmod_class dra7xx_spinlock_hwmod_class = {
+	.name	= "spinlock",
+	.sysc	= &dra7xx_spinlock_sysc,
+};
+
+/* spinlock */
+static struct omap_hwmod dra7xx_spinlock_hwmod = {
+	.name		= "spinlock",
+	.class		= &dra7xx_spinlock_hwmod_class,
+	.clkdm_name	= "l4cfg_clkdm",
+	.main_clk	= "l3_iclk_div",
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = DRA7XX_CM_L4CFG_SPINLOCK_CLKCTRL_OFFSET,
+			.context_offs = DRA7XX_RM_L4CFG_SPINLOCK_CONTEXT_OFFSET,
+		},
+	},
+};
+
+/*
+ * 'timer' class
+ *
+ * This class contains several variants: ['timer_1ms', 'timer_secure',
+ * 'timer']
+ */
+
+static struct omap_hwmod_class_sysconfig dra7xx_timer_1ms_sysc = {
+	.rev_offs	= 0x0000,
+	.sysc_offs	= 0x0010,
+	.sysc_flags	= (SYSC_HAS_EMUFREE | SYSC_HAS_RESET_STATUS |
+			   SYSC_HAS_SIDLEMODE | SYSC_HAS_SOFTRESET),
+	.idlemodes	= (SIDLE_FORCE | SIDLE_NO | SIDLE_SMART |
+			   SIDLE_SMART_WKUP),
+	.sysc_fields	= &omap_hwmod_sysc_type2,
+};
+
+static struct omap_hwmod_class dra7xx_timer_1ms_hwmod_class = {
+	.name	= "timer",
+	.sysc	= &dra7xx_timer_1ms_sysc,
+};
+
+static struct omap_hwmod_class_sysconfig dra7xx_timer_secure_sysc = {
+	.rev_offs	= 0x0000,
+	.sysc_offs	= 0x0010,
+	.sysc_flags	= (SYSC_HAS_EMUFREE | SYSC_HAS_RESET_STATUS |
+			   SYSC_HAS_SIDLEMODE | SYSC_HAS_SOFTRESET),
+	.idlemodes	= (SIDLE_FORCE | SIDLE_NO | SIDLE_SMART |
+			   SIDLE_SMART_WKUP),
+	.sysc_fields	= &omap_hwmod_sysc_type2,
+};
+
+static struct omap_hwmod_class dra7xx_timer_secure_hwmod_class = {
+	.name	= "timer",
+	.sysc	= &dra7xx_timer_secure_sysc,
+};
+
+static struct omap_hwmod_class_sysconfig dra7xx_timer_sysc = {
+	.rev_offs	= 0x0000,
+	.sysc_offs	= 0x0010,
+	.sysc_flags	= (SYSC_HAS_EMUFREE | SYSC_HAS_RESET_STATUS |
+			   SYSC_HAS_SIDLEMODE | SYSC_HAS_SOFTRESET),
+	.idlemodes	= (SIDLE_FORCE | SIDLE_NO | SIDLE_SMART |
+			   SIDLE_SMART_WKUP),
+	.sysc_fields	= &omap_hwmod_sysc_type2,
+};
+
+static struct omap_hwmod_class dra7xx_timer_hwmod_class = {
+	.name	= "timer",
+	.sysc	= &dra7xx_timer_sysc,
+};
+
+/* timer1 */
+static struct omap_hwmod dra7xx_timer1_hwmod = {
+	.name		= "timer1",
+	.class		= &dra7xx_timer_1ms_hwmod_class,
+	.clkdm_name	= "wkupaon_clkdm",
+	.main_clk	= "timer1_gfclk_mux",
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = DRA7XX_CM_WKUPAON_TIMER1_CLKCTRL_OFFSET,
+			.context_offs = DRA7XX_RM_WKUPAON_TIMER1_CONTEXT_OFFSET,
+			.modulemode   = MODULEMODE_SWCTRL,
+		},
+	},
+};
+
+/* timer2 */
+static struct omap_hwmod dra7xx_timer2_hwmod = {
+	.name		= "timer2",
+	.class		= &dra7xx_timer_1ms_hwmod_class,
+	.clkdm_name	= "l4per_clkdm",
+	.main_clk	= "timer2_gfclk_mux",
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = DRA7XX_CM_L4PER_TIMER2_CLKCTRL_OFFSET,
+			.context_offs = DRA7XX_RM_L4PER_TIMER2_CONTEXT_OFFSET,
+			.modulemode   = MODULEMODE_SWCTRL,
+		},
+	},
+};
+
+/* timer3 */
+static struct omap_hwmod dra7xx_timer3_hwmod = {
+	.name		= "timer3",
+	.class		= &dra7xx_timer_hwmod_class,
+	.clkdm_name	= "l4per_clkdm",
+	.main_clk	= "timer3_gfclk_mux",
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = DRA7XX_CM_L4PER_TIMER3_CLKCTRL_OFFSET,
+			.context_offs = DRA7XX_RM_L4PER_TIMER3_CONTEXT_OFFSET,
+			.modulemode   = MODULEMODE_SWCTRL,
+		},
+	},
+};
+
+/* timer4 */
+static struct omap_hwmod dra7xx_timer4_hwmod = {
+	.name		= "timer4",
+	.class		= &dra7xx_timer_secure_hwmod_class,
+	.clkdm_name	= "l4per_clkdm",
+	.main_clk	= "timer4_gfclk_mux",
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = DRA7XX_CM_L4PER_TIMER4_CLKCTRL_OFFSET,
+			.context_offs = DRA7XX_RM_L4PER_TIMER4_CONTEXT_OFFSET,
+			.modulemode   = MODULEMODE_SWCTRL,
+		},
+	},
+};
+
+/* timer5 */
+static struct omap_hwmod dra7xx_timer5_hwmod = {
+	.name		= "timer5",
+	.class		= &dra7xx_timer_hwmod_class,
+	.clkdm_name	= "ipu_clkdm",
+	.main_clk	= "timer5_gfclk_mux",
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = DRA7XX_CM_IPU_TIMER5_CLKCTRL_OFFSET,
+			.context_offs = DRA7XX_RM_IPU_TIMER5_CONTEXT_OFFSET,
+			.modulemode   = MODULEMODE_SWCTRL,
+		},
+	},
+};
+
+/* timer6 */
+static struct omap_hwmod dra7xx_timer6_hwmod = {
+	.name		= "timer6",
+	.class		= &dra7xx_timer_hwmod_class,
+	.clkdm_name	= "ipu_clkdm",
+	.main_clk	= "timer6_gfclk_mux",
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = DRA7XX_CM_IPU_TIMER6_CLKCTRL_OFFSET,
+			.context_offs = DRA7XX_RM_IPU_TIMER6_CONTEXT_OFFSET,
+			.modulemode   = MODULEMODE_SWCTRL,
+		},
+	},
+};
+
+/* timer7 */
+static struct omap_hwmod dra7xx_timer7_hwmod = {
+	.name		= "timer7",
+	.class		= &dra7xx_timer_hwmod_class,
+	.clkdm_name	= "ipu_clkdm",
+	.main_clk	= "timer7_gfclk_mux",
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = DRA7XX_CM_IPU_TIMER7_CLKCTRL_OFFSET,
+			.context_offs = DRA7XX_RM_IPU_TIMER7_CONTEXT_OFFSET,
+			.modulemode   = MODULEMODE_SWCTRL,
+		},
+	},
+};
+
+/* timer8 */
+static struct omap_hwmod dra7xx_timer8_hwmod = {
+	.name		= "timer8",
+	.class		= &dra7xx_timer_hwmod_class,
+	.clkdm_name	= "ipu_clkdm",
+	.main_clk	= "timer8_gfclk_mux",
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = DRA7XX_CM_IPU_TIMER8_CLKCTRL_OFFSET,
+			.context_offs = DRA7XX_RM_IPU_TIMER8_CONTEXT_OFFSET,
+			.modulemode   = MODULEMODE_SWCTRL,
+		},
+	},
+};
+
+/* timer9 */
+static struct omap_hwmod dra7xx_timer9_hwmod = {
+	.name		= "timer9",
+	.class		= &dra7xx_timer_hwmod_class,
+	.clkdm_name	= "l4per_clkdm",
+	.main_clk	= "timer9_gfclk_mux",
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = DRA7XX_CM_L4PER_TIMER9_CLKCTRL_OFFSET,
+			.context_offs = DRA7XX_RM_L4PER_TIMER9_CONTEXT_OFFSET,
+			.modulemode   = MODULEMODE_SWCTRL,
+		},
+	},
+};
+
+/* timer10 */
+static struct omap_hwmod dra7xx_timer10_hwmod = {
+	.name		= "timer10",
+	.class		= &dra7xx_timer_1ms_hwmod_class,
+	.clkdm_name	= "l4per_clkdm",
+	.main_clk	= "timer10_gfclk_mux",
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = DRA7XX_CM_L4PER_TIMER10_CLKCTRL_OFFSET,
+			.context_offs = DRA7XX_RM_L4PER_TIMER10_CONTEXT_OFFSET,
+			.modulemode   = MODULEMODE_SWCTRL,
+		},
+	},
+};
+
+/* timer11 */
+static struct omap_hwmod dra7xx_timer11_hwmod = {
+	.name		= "timer11",
+	.class		= &dra7xx_timer_hwmod_class,
+	.clkdm_name	= "l4per_clkdm",
+	.main_clk	= "timer11_gfclk_mux",
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = DRA7XX_CM_L4PER_TIMER11_CLKCTRL_OFFSET,
+			.context_offs = DRA7XX_RM_L4PER_TIMER11_CONTEXT_OFFSET,
+			.modulemode   = MODULEMODE_SWCTRL,
+		},
+	},
+};
+
+/*
+ * 'uart' class
+ *
+ */
+
+static struct omap_hwmod_class_sysconfig dra7xx_uart_sysc = {
+	.rev_offs	= 0x0050,
+	.sysc_offs	= 0x0054,
+	.syss_offs	= 0x0058,
+	.sysc_flags	= (SYSC_HAS_AUTOIDLE | SYSC_HAS_ENAWAKEUP |
+			   SYSC_HAS_SIDLEMODE | SYSC_HAS_SOFTRESET |
+			   SYSS_HAS_RESET_STATUS),
+	.idlemodes	= (SIDLE_FORCE | SIDLE_NO | SIDLE_SMART |
+			   SIDLE_SMART_WKUP),
+	.sysc_fields	= &omap_hwmod_sysc_type1,
+};
+
+static struct omap_hwmod_class dra7xx_uart_hwmod_class = {
+	.name	= "uart",
+	.sysc	= &dra7xx_uart_sysc,
+};
+
+/* uart1 */
+static struct omap_hwmod dra7xx_uart1_hwmod = {
+	.name		= "uart1",
+	.class		= &dra7xx_uart_hwmod_class,
+	.clkdm_name	= "l4per_clkdm",
+	.main_clk	= "uart1_gfclk_mux",
+	.flags		= HWMOD_SWSUP_SIDLE_ACT,
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = DRA7XX_CM_L4PER_UART1_CLKCTRL_OFFSET,
+			.context_offs = DRA7XX_RM_L4PER_UART1_CONTEXT_OFFSET,
+			.modulemode   = MODULEMODE_SWCTRL,
+		},
+	},
+};
+
+/* uart2 */
+static struct omap_hwmod dra7xx_uart2_hwmod = {
+	.name		= "uart2",
+	.class		= &dra7xx_uart_hwmod_class,
+	.clkdm_name	= "l4per_clkdm",
+	.main_clk	= "uart2_gfclk_mux",
+	.flags		= HWMOD_SWSUP_SIDLE_ACT,
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = DRA7XX_CM_L4PER_UART2_CLKCTRL_OFFSET,
+			.context_offs = DRA7XX_RM_L4PER_UART2_CONTEXT_OFFSET,
+			.modulemode   = MODULEMODE_SWCTRL,
+		},
+	},
+};
+
+/* uart3 */
+static struct omap_hwmod dra7xx_uart3_hwmod = {
+	.name		= "uart3",
+	.class		= &dra7xx_uart_hwmod_class,
+	.clkdm_name	= "l4per_clkdm",
+	.main_clk	= "uart3_gfclk_mux",
+	.flags		= HWMOD_SWSUP_SIDLE_ACT,
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = DRA7XX_CM_L4PER_UART3_CLKCTRL_OFFSET,
+			.context_offs = DRA7XX_RM_L4PER_UART3_CONTEXT_OFFSET,
+			.modulemode   = MODULEMODE_SWCTRL,
+		},
+	},
+};
+
+/* uart4 */
+static struct omap_hwmod dra7xx_uart4_hwmod = {
+	.name		= "uart4",
+	.class		= &dra7xx_uart_hwmod_class,
+	.clkdm_name	= "l4per_clkdm",
+	.main_clk	= "uart4_gfclk_mux",
+	.flags		= HWMOD_SWSUP_SIDLE_ACT,
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = DRA7XX_CM_L4PER_UART4_CLKCTRL_OFFSET,
+			.context_offs = DRA7XX_RM_L4PER_UART4_CONTEXT_OFFSET,
+			.modulemode   = MODULEMODE_SWCTRL,
+		},
+	},
+};
+
+/* uart5 */
+static struct omap_hwmod dra7xx_uart5_hwmod = {
+	.name		= "uart5",
+	.class		= &dra7xx_uart_hwmod_class,
+	.clkdm_name	= "l4per_clkdm",
+	.main_clk	= "uart5_gfclk_mux",
+	.flags		= HWMOD_SWSUP_SIDLE_ACT,
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = DRA7XX_CM_L4PER_UART5_CLKCTRL_OFFSET,
+			.context_offs = DRA7XX_RM_L4PER_UART5_CONTEXT_OFFSET,
+			.modulemode   = MODULEMODE_SWCTRL,
+		},
+	},
+};
+
+/* uart6 */
+static struct omap_hwmod dra7xx_uart6_hwmod = {
+	.name		= "uart6",
+	.class		= &dra7xx_uart_hwmod_class,
+	.clkdm_name	= "ipu_clkdm",
+	.main_clk	= "uart6_gfclk_mux",
+	.flags		= HWMOD_SWSUP_SIDLE_ACT,
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = DRA7XX_CM_IPU_UART6_CLKCTRL_OFFSET,
+			.context_offs = DRA7XX_RM_IPU_UART6_CONTEXT_OFFSET,
+			.modulemode   = MODULEMODE_SWCTRL,
+		},
+	},
+};
+
+/*
+ * 'usb_otg_ss' class
+ *
+ */
+
+static struct omap_hwmod_class dra7xx_usb_otg_ss_hwmod_class = {
+	.name	= "usb_otg_ss",
+};
+
+/* usb_otg_ss1 */
+static struct omap_hwmod_opt_clk usb_otg_ss1_opt_clks[] = {
+	{ .role = "refclk960m", .clk = "usb_otg_ss1_refclk960m" },
+};
+
+static struct omap_hwmod dra7xx_usb_otg_ss1_hwmod = {
+	.name		= "usb_otg_ss1",
+	.class		= &dra7xx_usb_otg_ss_hwmod_class,
+	.clkdm_name	= "l3init_clkdm",
+	.main_clk	= "dpll_core_h13x2_ck",
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = DRA7XX_CM_L3INIT_USB_OTG_SS1_CLKCTRL_OFFSET,
+			.context_offs = DRA7XX_RM_L3INIT_USB_OTG_SS1_CONTEXT_OFFSET,
+			.modulemode   = MODULEMODE_HWCTRL,
+		},
+	},
+	.opt_clks	= usb_otg_ss1_opt_clks,
+	.opt_clks_cnt	= ARRAY_SIZE(usb_otg_ss1_opt_clks),
+};
+
+/* usb_otg_ss2 */
+static struct omap_hwmod_opt_clk usb_otg_ss2_opt_clks[] = {
+	{ .role = "refclk960m", .clk = "usb_otg_ss2_refclk960m" },
+};
+
+static struct omap_hwmod dra7xx_usb_otg_ss2_hwmod = {
+	.name		= "usb_otg_ss2",
+	.class		= &dra7xx_usb_otg_ss_hwmod_class,
+	.clkdm_name	= "l3init_clkdm",
+	.main_clk	= "dpll_core_h13x2_ck",
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = DRA7XX_CM_L3INIT_USB_OTG_SS2_CLKCTRL_OFFSET,
+			.context_offs = DRA7XX_RM_L3INIT_USB_OTG_SS2_CONTEXT_OFFSET,
+			.modulemode   = MODULEMODE_HWCTRL,
+		},
+	},
+	.opt_clks	= usb_otg_ss2_opt_clks,
+	.opt_clks_cnt	= ARRAY_SIZE(usb_otg_ss2_opt_clks),
+};
+
+/* usb_otg_ss3 */
+static struct omap_hwmod dra7xx_usb_otg_ss3_hwmod = {
+	.name		= "usb_otg_ss3",
+	.class		= &dra7xx_usb_otg_ss_hwmod_class,
+	.clkdm_name	= "l3init_clkdm",
+	.main_clk	= "dpll_core_h13x2_ck",
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = DRA7XX_CM_L3INIT_USB_OTG_SS3_CLKCTRL_OFFSET,
+			.context_offs = DRA7XX_RM_L3INIT_USB_OTG_SS3_CONTEXT_OFFSET,
+			.modulemode   = MODULEMODE_HWCTRL,
+		},
+	},
+};
+
+/* usb_otg_ss4 */
+static struct omap_hwmod dra7xx_usb_otg_ss4_hwmod = {
+	.name		= "usb_otg_ss4",
+	.class		= &dra7xx_usb_otg_ss_hwmod_class,
+	.clkdm_name	= "l3init_clkdm",
+	.main_clk	= "dpll_core_h13x2_ck",
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = DRA7XX_CM_L3INIT_USB_OTG_SS4_CLKCTRL_OFFSET,
+			.context_offs = DRA7XX_RM_L3INIT_USB_OTG_SS4_CONTEXT_OFFSET,
+			.modulemode   = MODULEMODE_HWCTRL,
+		},
+	},
+};
+
+/*
+ * 'vcp' class
+ *
+ */
+
+static struct omap_hwmod_class dra7xx_vcp_hwmod_class = {
+	.name	= "vcp",
+};
+
+/* vcp1 */
+static struct omap_hwmod dra7xx_vcp1_hwmod = {
+	.name		= "vcp1",
+	.class		= &dra7xx_vcp_hwmod_class,
+	.clkdm_name	= "l3main1_clkdm",
+	.main_clk	= "l3_iclk_div",
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = DRA7XX_CM_L3MAIN1_VCP1_CLKCTRL_OFFSET,
+			.context_offs = DRA7XX_RM_L3MAIN1_VCP1_CONTEXT_OFFSET,
+		},
+	},
+};
+
+/* vcp2 */
+static struct omap_hwmod dra7xx_vcp2_hwmod = {
+	.name		= "vcp2",
+	.class		= &dra7xx_vcp_hwmod_class,
+	.clkdm_name	= "l3main1_clkdm",
+	.main_clk	= "l3_iclk_div",
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = DRA7XX_CM_L3MAIN1_VCP2_CLKCTRL_OFFSET,
+			.context_offs = DRA7XX_RM_L3MAIN1_VCP2_CONTEXT_OFFSET,
+		},
+	},
+};
+
+/*
+ * 'wd_timer' class
+ *
+ */
+
+static struct omap_hwmod_class_sysconfig dra7xx_wd_timer_sysc = {
+	.rev_offs	= 0x0000,
+	.sysc_offs	= 0x0010,
+	.syss_offs	= 0x0014,
+	.sysc_flags	= (SYSC_HAS_EMUFREE | SYSC_HAS_SIDLEMODE |
+			   SYSC_HAS_SOFTRESET | SYSS_HAS_RESET_STATUS),
+	.idlemodes	= (SIDLE_FORCE | SIDLE_NO | SIDLE_SMART |
+			   SIDLE_SMART_WKUP),
+	.sysc_fields	= &omap_hwmod_sysc_type1,
+};
+
+static struct omap_hwmod_class dra7xx_wd_timer_hwmod_class = {
+	.name		= "wd_timer",
+	.sysc		= &dra7xx_wd_timer_sysc,
+	.pre_shutdown	= &omap2_wd_timer_disable,
+	.reset		= &omap2_wd_timer_reset,
+};
+
+/* wd_timer2 */
+static struct omap_hwmod dra7xx_wd_timer2_hwmod = {
+	.name		= "wd_timer2",
+	.class		= &dra7xx_wd_timer_hwmod_class,
+	.clkdm_name	= "wkupaon_clkdm",
+	.main_clk	= "sys_32k_ck",
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = DRA7XX_CM_WKUPAON_WD_TIMER2_CLKCTRL_OFFSET,
+			.context_offs = DRA7XX_RM_WKUPAON_WD_TIMER2_CONTEXT_OFFSET,
+			.modulemode   = MODULEMODE_SWCTRL,
+		},
+	},
+};
+
+
+/*
+ * Interfaces
+ */
+
+/* l3_main_2 -> l3_instr */
+static struct omap_hwmod_ocp_if dra7xx_l3_main_2__l3_instr = {
+	.master		= &dra7xx_l3_main_2_hwmod,
+	.slave		= &dra7xx_l3_instr_hwmod,
+	.clk		= "l3_iclk_div",
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+/* l4_cfg -> l3_main_1 */
+static struct omap_hwmod_ocp_if dra7xx_l4_cfg__l3_main_1 = {
+	.master		= &dra7xx_l4_cfg_hwmod,
+	.slave		= &dra7xx_l3_main_1_hwmod,
+	.clk		= "l3_iclk_div",
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+/* mpu -> l3_main_1 */
+static struct omap_hwmod_ocp_if dra7xx_mpu__l3_main_1 = {
+	.master		= &dra7xx_mpu_hwmod,
+	.slave		= &dra7xx_l3_main_1_hwmod,
+	.clk		= "l3_iclk_div",
+	.user		= OCP_USER_MPU,
+};
+
+/* l3_main_1 -> l3_main_2 */
+static struct omap_hwmod_ocp_if dra7xx_l3_main_1__l3_main_2 = {
+	.master		= &dra7xx_l3_main_1_hwmod,
+	.slave		= &dra7xx_l3_main_2_hwmod,
+	.clk		= "l3_iclk_div",
+	.user		= OCP_USER_MPU,
+};
+
+/* l4_cfg -> l3_main_2 */
+static struct omap_hwmod_ocp_if dra7xx_l4_cfg__l3_main_2 = {
+	.master		= &dra7xx_l4_cfg_hwmod,
+	.slave		= &dra7xx_l3_main_2_hwmod,
+	.clk		= "l3_iclk_div",
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+/* l3_main_1 -> l4_cfg */
+static struct omap_hwmod_ocp_if dra7xx_l3_main_1__l4_cfg = {
+	.master		= &dra7xx_l3_main_1_hwmod,
+	.slave		= &dra7xx_l4_cfg_hwmod,
+	.clk		= "l3_iclk_div",
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+/* l3_main_1 -> l4_per1 */
+static struct omap_hwmod_ocp_if dra7xx_l3_main_1__l4_per1 = {
+	.master		= &dra7xx_l3_main_1_hwmod,
+	.slave		= &dra7xx_l4_per1_hwmod,
+	.clk		= "l3_iclk_div",
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+/* l3_main_1 -> l4_per2 */
+static struct omap_hwmod_ocp_if dra7xx_l3_main_1__l4_per2 = {
+	.master		= &dra7xx_l3_main_1_hwmod,
+	.slave		= &dra7xx_l4_per2_hwmod,
+	.clk		= "l3_iclk_div",
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+/* l3_main_1 -> l4_per3 */
+static struct omap_hwmod_ocp_if dra7xx_l3_main_1__l4_per3 = {
+	.master		= &dra7xx_l3_main_1_hwmod,
+	.slave		= &dra7xx_l4_per3_hwmod,
+	.clk		= "l3_iclk_div",
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+/* l3_main_1 -> l4_wkup */
+static struct omap_hwmod_ocp_if dra7xx_l3_main_1__l4_wkup = {
+	.master		= &dra7xx_l3_main_1_hwmod,
+	.slave		= &dra7xx_l4_wkup_hwmod,
+	.clk		= "wkupaon_iclk_mux",
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+/* l4_per2 -> atl */
+static struct omap_hwmod_ocp_if dra7xx_l4_per2__atl = {
+	.master		= &dra7xx_l4_per2_hwmod,
+	.slave		= &dra7xx_atl_hwmod,
+	.clk		= "l3_iclk_div",
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+/* l3_main_1 -> bb2d */
+static struct omap_hwmod_ocp_if dra7xx_l3_main_1__bb2d = {
+	.master		= &dra7xx_l3_main_1_hwmod,
+	.slave		= &dra7xx_bb2d_hwmod,
+	.clk		= "l3_iclk_div",
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+/* l4_wkup -> counter_32k */
+static struct omap_hwmod_ocp_if dra7xx_l4_wkup__counter_32k = {
+	.master		= &dra7xx_l4_wkup_hwmod,
+	.slave		= &dra7xx_counter_32k_hwmod,
+	.clk		= "wkupaon_iclk_mux",
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+/* l4_wkup -> ctrl_module_wkup */
+static struct omap_hwmod_ocp_if dra7xx_l4_wkup__ctrl_module_wkup = {
+	.master		= &dra7xx_l4_wkup_hwmod,
+	.slave		= &dra7xx_ctrl_module_wkup_hwmod,
+	.clk		= "wkupaon_iclk_mux",
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+/* l4_wkup -> dcan1 */
+static struct omap_hwmod_ocp_if dra7xx_l4_wkup__dcan1 = {
+	.master		= &dra7xx_l4_wkup_hwmod,
+	.slave		= &dra7xx_dcan1_hwmod,
+	.clk		= "wkupaon_iclk_mux",
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+/* l4_per2 -> dcan2 */
+static struct omap_hwmod_ocp_if dra7xx_l4_per2__dcan2 = {
+	.master		= &dra7xx_l4_per2_hwmod,
+	.slave		= &dra7xx_dcan2_hwmod,
+	.clk		= "l3_iclk_div",
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+static struct omap_hwmod_addr_space dra7xx_dma_system_addrs[] = {
+	{
+		.pa_start	= 0x4a056000,
+		.pa_end		= 0x4a056fff,
+		.flags		= ADDR_TYPE_RT
+	},
+	{ }
+};
+
+/* l4_cfg -> dma_system */
+static struct omap_hwmod_ocp_if dra7xx_l4_cfg__dma_system = {
+	.master		= &dra7xx_l4_cfg_hwmod,
+	.slave		= &dra7xx_dma_system_hwmod,
+	.clk		= "l3_iclk_div",
+	.addr		= dra7xx_dma_system_addrs,
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+static struct omap_hwmod_addr_space dra7xx_dss_addrs[] = {
+	{
+		.name		= "family",
+		.pa_start	= 0x58000000,
+		.pa_end		= 0x5800007f,
+		.flags		= ADDR_TYPE_RT
+	},
+};
+
+/* l3_main_1 -> dss */
+static struct omap_hwmod_ocp_if dra7xx_l3_main_1__dss = {
+	.master		= &dra7xx_l3_main_1_hwmod,
+	.slave		= &dra7xx_dss_hwmod,
+	.clk		= "l3_iclk_div",
+	.addr		= dra7xx_dss_addrs,
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+static struct omap_hwmod_addr_space dra7xx_dss_dispc_addrs[] = {
+	{
+		.name		= "dispc",
+		.pa_start	= 0x58001000,
+		.pa_end		= 0x58001fff,
+		.flags		= ADDR_TYPE_RT
+	},
+};
+
+/* l3_main_1 -> dispc */
+static struct omap_hwmod_ocp_if dra7xx_l3_main_1__dispc = {
+	.master		= &dra7xx_l3_main_1_hwmod,
+	.slave		= &dra7xx_dss_dispc_hwmod,
+	.clk		= "l3_iclk_div",
+	.addr		= dra7xx_dss_dispc_addrs,
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+static struct omap_hwmod_addr_space dra7xx_dss_hdmi_addrs[] = {
+	{
+		.name		= "hdmi_wp",
+		.pa_start	= 0x58040000,
+		.pa_end		= 0x580400ff,
+		.flags		= ADDR_TYPE_RT
+	},
+	{ }
+};
+
+/* l3_main_1 -> dispc */
+static struct omap_hwmod_ocp_if dra7xx_l3_main_1__hdmi = {
+	.master		= &dra7xx_l3_main_1_hwmod,
+	.slave		= &dra7xx_dss_hdmi_hwmod,
+	.clk		= "l3_iclk_div",
+	.addr		= dra7xx_dss_hdmi_addrs,
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+static struct omap_hwmod_addr_space dra7xx_elm_addrs[] = {
+	{
+		.pa_start	= 0x48078000,
+		.pa_end		= 0x48078fff,
+		.flags		= ADDR_TYPE_RT
+	},
+	{ }
+};
+
+/* l4_per1 -> elm */
+static struct omap_hwmod_ocp_if dra7xx_l4_per1__elm = {
+	.master		= &dra7xx_l4_per1_hwmod,
+	.slave		= &dra7xx_elm_hwmod,
+	.clk		= "l3_iclk_div",
+	.addr		= dra7xx_elm_addrs,
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+/* l4_wkup -> gpio1 */
+static struct omap_hwmod_ocp_if dra7xx_l4_wkup__gpio1 = {
+	.master		= &dra7xx_l4_wkup_hwmod,
+	.slave		= &dra7xx_gpio1_hwmod,
+	.clk		= "wkupaon_iclk_mux",
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+/* l4_per1 -> gpio2 */
+static struct omap_hwmod_ocp_if dra7xx_l4_per1__gpio2 = {
+	.master		= &dra7xx_l4_per1_hwmod,
+	.slave		= &dra7xx_gpio2_hwmod,
+	.clk		= "l3_iclk_div",
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+/* l4_per1 -> gpio3 */
+static struct omap_hwmod_ocp_if dra7xx_l4_per1__gpio3 = {
+	.master		= &dra7xx_l4_per1_hwmod,
+	.slave		= &dra7xx_gpio3_hwmod,
+	.clk		= "l3_iclk_div",
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+/* l4_per1 -> gpio4 */
+static struct omap_hwmod_ocp_if dra7xx_l4_per1__gpio4 = {
+	.master		= &dra7xx_l4_per1_hwmod,
+	.slave		= &dra7xx_gpio4_hwmod,
+	.clk		= "l3_iclk_div",
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+/* l4_per1 -> gpio5 */
+static struct omap_hwmod_ocp_if dra7xx_l4_per1__gpio5 = {
+	.master		= &dra7xx_l4_per1_hwmod,
+	.slave		= &dra7xx_gpio5_hwmod,
+	.clk		= "l3_iclk_div",
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+/* l4_per1 -> gpio6 */
+static struct omap_hwmod_ocp_if dra7xx_l4_per1__gpio6 = {
+	.master		= &dra7xx_l4_per1_hwmod,
+	.slave		= &dra7xx_gpio6_hwmod,
+	.clk		= "l3_iclk_div",
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+/* l4_per1 -> gpio7 */
+static struct omap_hwmod_ocp_if dra7xx_l4_per1__gpio7 = {
+	.master		= &dra7xx_l4_per1_hwmod,
+	.slave		= &dra7xx_gpio7_hwmod,
+	.clk		= "l3_iclk_div",
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+/* l4_per1 -> gpio8 */
+static struct omap_hwmod_ocp_if dra7xx_l4_per1__gpio8 = {
+	.master		= &dra7xx_l4_per1_hwmod,
+	.slave		= &dra7xx_gpio8_hwmod,
+	.clk		= "l3_iclk_div",
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+static struct omap_hwmod_addr_space dra7xx_gpmc_addrs[] = {
+	{
+		.pa_start	= 0x50000000,
+		.pa_end		= 0x500003ff,
+		.flags		= ADDR_TYPE_RT
+	},
+	{ }
+};
+
+/* l3_main_1 -> gpmc */
+static struct omap_hwmod_ocp_if dra7xx_l3_main_1__gpmc = {
+	.master		= &dra7xx_l3_main_1_hwmod,
+	.slave		= &dra7xx_gpmc_hwmod,
+	.clk		= "l3_iclk_div",
+	.addr		= dra7xx_gpmc_addrs,
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+static struct omap_hwmod_addr_space dra7xx_hdq1w_addrs[] = {
+	{
+		.pa_start	= 0x480b2000,
+		.pa_end		= 0x480b201f,
+		.flags		= ADDR_TYPE_RT
+	},
+	{ }
+};
+
+/* l4_per1 -> hdq1w */
+static struct omap_hwmod_ocp_if dra7xx_l4_per1__hdq1w = {
+	.master		= &dra7xx_l4_per1_hwmod,
+	.slave		= &dra7xx_hdq1w_hwmod,
+	.clk		= "l3_iclk_div",
+	.addr		= dra7xx_hdq1w_addrs,
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+/* l4_per1 -> i2c1 */
+static struct omap_hwmod_ocp_if dra7xx_l4_per1__i2c1 = {
+	.master		= &dra7xx_l4_per1_hwmod,
+	.slave		= &dra7xx_i2c1_hwmod,
+	.clk		= "l3_iclk_div",
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+/* l4_per1 -> i2c2 */
+static struct omap_hwmod_ocp_if dra7xx_l4_per1__i2c2 = {
+	.master		= &dra7xx_l4_per1_hwmod,
+	.slave		= &dra7xx_i2c2_hwmod,
+	.clk		= "l3_iclk_div",
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+/* l4_per1 -> i2c3 */
+static struct omap_hwmod_ocp_if dra7xx_l4_per1__i2c3 = {
+	.master		= &dra7xx_l4_per1_hwmod,
+	.slave		= &dra7xx_i2c3_hwmod,
+	.clk		= "l3_iclk_div",
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+/* l4_per1 -> i2c4 */
+static struct omap_hwmod_ocp_if dra7xx_l4_per1__i2c4 = {
+	.master		= &dra7xx_l4_per1_hwmod,
+	.slave		= &dra7xx_i2c4_hwmod,
+	.clk		= "l3_iclk_div",
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+/* l4_per1 -> i2c5 */
+static struct omap_hwmod_ocp_if dra7xx_l4_per1__i2c5 = {
+	.master		= &dra7xx_l4_per1_hwmod,
+	.slave		= &dra7xx_i2c5_hwmod,
+	.clk		= "l3_iclk_div",
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+/* l4_per1 -> mcspi1 */
+static struct omap_hwmod_ocp_if dra7xx_l4_per1__mcspi1 = {
+	.master		= &dra7xx_l4_per1_hwmod,
+	.slave		= &dra7xx_mcspi1_hwmod,
+	.clk		= "l3_iclk_div",
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+/* l4_per1 -> mcspi2 */
+static struct omap_hwmod_ocp_if dra7xx_l4_per1__mcspi2 = {
+	.master		= &dra7xx_l4_per1_hwmod,
+	.slave		= &dra7xx_mcspi2_hwmod,
+	.clk		= "l3_iclk_div",
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+/* l4_per1 -> mcspi3 */
+static struct omap_hwmod_ocp_if dra7xx_l4_per1__mcspi3 = {
+	.master		= &dra7xx_l4_per1_hwmod,
+	.slave		= &dra7xx_mcspi3_hwmod,
+	.clk		= "l3_iclk_div",
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+/* l4_per1 -> mcspi4 */
+static struct omap_hwmod_ocp_if dra7xx_l4_per1__mcspi4 = {
+	.master		= &dra7xx_l4_per1_hwmod,
+	.slave		= &dra7xx_mcspi4_hwmod,
+	.clk		= "l3_iclk_div",
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+/* l4_per1 -> mmc1 */
+static struct omap_hwmod_ocp_if dra7xx_l4_per1__mmc1 = {
+	.master		= &dra7xx_l4_per1_hwmod,
+	.slave		= &dra7xx_mmc1_hwmod,
+	.clk		= "l3_iclk_div",
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+/* l4_per1 -> mmc2 */
+static struct omap_hwmod_ocp_if dra7xx_l4_per1__mmc2 = {
+	.master		= &dra7xx_l4_per1_hwmod,
+	.slave		= &dra7xx_mmc2_hwmod,
+	.clk		= "l3_iclk_div",
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+/* l4_per1 -> mmc3 */
+static struct omap_hwmod_ocp_if dra7xx_l4_per1__mmc3 = {
+	.master		= &dra7xx_l4_per1_hwmod,
+	.slave		= &dra7xx_mmc3_hwmod,
+	.clk		= "l3_iclk_div",
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+/* l4_per1 -> mmc4 */
+static struct omap_hwmod_ocp_if dra7xx_l4_per1__mmc4 = {
+	.master		= &dra7xx_l4_per1_hwmod,
+	.slave		= &dra7xx_mmc4_hwmod,
+	.clk		= "l3_iclk_div",
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+/* l4_cfg -> mpu */
+static struct omap_hwmod_ocp_if dra7xx_l4_cfg__mpu = {
+	.master		= &dra7xx_l4_cfg_hwmod,
+	.slave		= &dra7xx_mpu_hwmod,
+	.clk		= "l3_iclk_div",
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+static struct omap_hwmod_addr_space dra7xx_ocp2scp1_addrs[] = {
+	{
+		.pa_start	= 0x4a080000,
+		.pa_end		= 0x4a08001f,
+		.flags		= ADDR_TYPE_RT
+	},
+	{ }
+};
+
+/* l4_cfg -> ocp2scp1 */
+static struct omap_hwmod_ocp_if dra7xx_l4_cfg__ocp2scp1 = {
+	.master		= &dra7xx_l4_cfg_hwmod,
+	.slave		= &dra7xx_ocp2scp1_hwmod,
+	.clk		= "l4_root_clk_div",
+	.addr		= dra7xx_ocp2scp1_addrs,
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+static struct omap_hwmod_addr_space dra7xx_qspi_addrs[] = {
+	{
+		.pa_start	= 0x4b300000,
+		.pa_end		= 0x4b30007f,
+		.flags		= ADDR_TYPE_RT
+	},
+	{ }
+};
+
+/* l3_main_1 -> qspi */
+static struct omap_hwmod_ocp_if dra7xx_l3_main_1__qspi = {
+	.master		= &dra7xx_l3_main_1_hwmod,
+	.slave		= &dra7xx_qspi_hwmod,
+	.clk		= "l3_iclk_div",
+	.addr		= dra7xx_qspi_addrs,
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+static struct omap_hwmod_addr_space dra7xx_sata_addrs[] = {
+	{
+		.name		= "sysc",
+		.pa_start	= 0x4a141100,
+		.pa_end		= 0x4a141107,
+		.flags		= ADDR_TYPE_RT
+	},
+	{ }
+};
+
+/* l4_cfg -> sata */
+static struct omap_hwmod_ocp_if dra7xx_l4_cfg__sata = {
+	.master		= &dra7xx_l4_cfg_hwmod,
+	.slave		= &dra7xx_sata_hwmod,
+	.clk		= "l3_iclk_div",
+	.addr		= dra7xx_sata_addrs,
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+static struct omap_hwmod_addr_space dra7xx_smartreflex_core_addrs[] = {
+	{
+		.pa_start	= 0x4a0dd000,
+		.pa_end		= 0x4a0dd07f,
+		.flags		= ADDR_TYPE_RT
+	},
+	{ }
+};
+
+/* l4_cfg -> smartreflex_core */
+static struct omap_hwmod_ocp_if dra7xx_l4_cfg__smartreflex_core = {
+	.master		= &dra7xx_l4_cfg_hwmod,
+	.slave		= &dra7xx_smartreflex_core_hwmod,
+	.clk		= "l4_root_clk_div",
+	.addr		= dra7xx_smartreflex_core_addrs,
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+static struct omap_hwmod_addr_space dra7xx_smartreflex_mpu_addrs[] = {
+	{
+		.pa_start	= 0x4a0d9000,
+		.pa_end		= 0x4a0d907f,
+		.flags		= ADDR_TYPE_RT
+	},
+	{ }
+};
+
+/* l4_cfg -> smartreflex_mpu */
+static struct omap_hwmod_ocp_if dra7xx_l4_cfg__smartreflex_mpu = {
+	.master		= &dra7xx_l4_cfg_hwmod,
+	.slave		= &dra7xx_smartreflex_mpu_hwmod,
+	.clk		= "l4_root_clk_div",
+	.addr		= dra7xx_smartreflex_mpu_addrs,
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+static struct omap_hwmod_addr_space dra7xx_spinlock_addrs[] = {
+	{
+		.pa_start	= 0x4a0f6000,
+		.pa_end		= 0x4a0f6fff,
+		.flags		= ADDR_TYPE_RT
+	},
+	{ }
+};
+
+/* l4_cfg -> spinlock */
+static struct omap_hwmod_ocp_if dra7xx_l4_cfg__spinlock = {
+	.master		= &dra7xx_l4_cfg_hwmod,
+	.slave		= &dra7xx_spinlock_hwmod,
+	.clk		= "l3_iclk_div",
+	.addr		= dra7xx_spinlock_addrs,
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+/* l4_wkup -> timer1 */
+static struct omap_hwmod_ocp_if dra7xx_l4_wkup__timer1 = {
+	.master		= &dra7xx_l4_wkup_hwmod,
+	.slave		= &dra7xx_timer1_hwmod,
+	.clk		= "wkupaon_iclk_mux",
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+/* l4_per1 -> timer2 */
+static struct omap_hwmod_ocp_if dra7xx_l4_per1__timer2 = {
+	.master		= &dra7xx_l4_per1_hwmod,
+	.slave		= &dra7xx_timer2_hwmod,
+	.clk		= "l3_iclk_div",
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+/* l4_per1 -> timer3 */
+static struct omap_hwmod_ocp_if dra7xx_l4_per1__timer3 = {
+	.master		= &dra7xx_l4_per1_hwmod,
+	.slave		= &dra7xx_timer3_hwmod,
+	.clk		= "l3_iclk_div",
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+/* l4_per1 -> timer4 */
+static struct omap_hwmod_ocp_if dra7xx_l4_per1__timer4 = {
+	.master		= &dra7xx_l4_per1_hwmod,
+	.slave		= &dra7xx_timer4_hwmod,
+	.clk		= "l3_iclk_div",
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+/* l4_per3 -> timer5 */
+static struct omap_hwmod_ocp_if dra7xx_l4_per3__timer5 = {
+	.master		= &dra7xx_l4_per3_hwmod,
+	.slave		= &dra7xx_timer5_hwmod,
+	.clk		= "l3_iclk_div",
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+/* l4_per3 -> timer6 */
+static struct omap_hwmod_ocp_if dra7xx_l4_per3__timer6 = {
+	.master		= &dra7xx_l4_per3_hwmod,
+	.slave		= &dra7xx_timer6_hwmod,
+	.clk		= "l3_iclk_div",
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+/* l4_per3 -> timer7 */
+static struct omap_hwmod_ocp_if dra7xx_l4_per3__timer7 = {
+	.master		= &dra7xx_l4_per3_hwmod,
+	.slave		= &dra7xx_timer7_hwmod,
+	.clk		= "l3_iclk_div",
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+/* l4_per3 -> timer8 */
+static struct omap_hwmod_ocp_if dra7xx_l4_per3__timer8 = {
+	.master		= &dra7xx_l4_per3_hwmod,
+	.slave		= &dra7xx_timer8_hwmod,
+	.clk		= "l3_iclk_div",
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+/* l4_per1 -> timer9 */
+static struct omap_hwmod_ocp_if dra7xx_l4_per1__timer9 = {
+	.master		= &dra7xx_l4_per1_hwmod,
+	.slave		= &dra7xx_timer9_hwmod,
+	.clk		= "l3_iclk_div",
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+/* l4_per1 -> timer10 */
+static struct omap_hwmod_ocp_if dra7xx_l4_per1__timer10 = {
+	.master		= &dra7xx_l4_per1_hwmod,
+	.slave		= &dra7xx_timer10_hwmod,
+	.clk		= "l3_iclk_div",
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+/* l4_per1 -> timer11 */
+static struct omap_hwmod_ocp_if dra7xx_l4_per1__timer11 = {
+	.master		= &dra7xx_l4_per1_hwmod,
+	.slave		= &dra7xx_timer11_hwmod,
+	.clk		= "l3_iclk_div",
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+/* l4_per1 -> uart1 */
+static struct omap_hwmod_ocp_if dra7xx_l4_per1__uart1 = {
+	.master		= &dra7xx_l4_per1_hwmod,
+	.slave		= &dra7xx_uart1_hwmod,
+	.clk		= "l3_iclk_div",
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+/* l4_per1 -> uart2 */
+static struct omap_hwmod_ocp_if dra7xx_l4_per1__uart2 = {
+	.master		= &dra7xx_l4_per1_hwmod,
+	.slave		= &dra7xx_uart2_hwmod,
+	.clk		= "l3_iclk_div",
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+/* l4_per1 -> uart3 */
+static struct omap_hwmod_ocp_if dra7xx_l4_per1__uart3 = {
+	.master		= &dra7xx_l4_per1_hwmod,
+	.slave		= &dra7xx_uart3_hwmod,
+	.clk		= "l3_iclk_div",
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+/* l4_per1 -> uart4 */
+static struct omap_hwmod_ocp_if dra7xx_l4_per1__uart4 = {
+	.master		= &dra7xx_l4_per1_hwmod,
+	.slave		= &dra7xx_uart4_hwmod,
+	.clk		= "l3_iclk_div",
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+/* l4_per1 -> uart5 */
+static struct omap_hwmod_ocp_if dra7xx_l4_per1__uart5 = {
+	.master		= &dra7xx_l4_per1_hwmod,
+	.slave		= &dra7xx_uart5_hwmod,
+	.clk		= "l3_iclk_div",
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+/* l4_per1 -> uart6 */
+static struct omap_hwmod_ocp_if dra7xx_l4_per1__uart6 = {
+	.master		= &dra7xx_l4_per1_hwmod,
+	.slave		= &dra7xx_uart6_hwmod,
+	.clk		= "l3_iclk_div",
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+/* l4_per3 -> usb_otg_ss1 */
+static struct omap_hwmod_ocp_if dra7xx_l4_per3__usb_otg_ss1 = {
+	.master		= &dra7xx_l4_per3_hwmod,
+	.slave		= &dra7xx_usb_otg_ss1_hwmod,
+	.clk		= "dpll_core_h13x2_ck",
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+/* l4_per3 -> usb_otg_ss2 */
+static struct omap_hwmod_ocp_if dra7xx_l4_per3__usb_otg_ss2 = {
+	.master		= &dra7xx_l4_per3_hwmod,
+	.slave		= &dra7xx_usb_otg_ss2_hwmod,
+	.clk		= "dpll_core_h13x2_ck",
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+/* l4_per3 -> usb_otg_ss3 */
+static struct omap_hwmod_ocp_if dra7xx_l4_per3__usb_otg_ss3 = {
+	.master		= &dra7xx_l4_per3_hwmod,
+	.slave		= &dra7xx_usb_otg_ss3_hwmod,
+	.clk		= "dpll_core_h13x2_ck",
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+/* l4_per3 -> usb_otg_ss4 */
+static struct omap_hwmod_ocp_if dra7xx_l4_per3__usb_otg_ss4 = {
+	.master		= &dra7xx_l4_per3_hwmod,
+	.slave		= &dra7xx_usb_otg_ss4_hwmod,
+	.clk		= "dpll_core_h13x2_ck",
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+/* l3_main_1 -> vcp1 */
+static struct omap_hwmod_ocp_if dra7xx_l3_main_1__vcp1 = {
+	.master		= &dra7xx_l3_main_1_hwmod,
+	.slave		= &dra7xx_vcp1_hwmod,
+	.clk		= "l3_iclk_div",
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+/* l4_per2 -> vcp1 */
+static struct omap_hwmod_ocp_if dra7xx_l4_per2__vcp1 = {
+	.master		= &dra7xx_l4_per2_hwmod,
+	.slave		= &dra7xx_vcp1_hwmod,
+	.clk		= "l3_iclk_div",
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+/* l3_main_1 -> vcp2 */
+static struct omap_hwmod_ocp_if dra7xx_l3_main_1__vcp2 = {
+	.master		= &dra7xx_l3_main_1_hwmod,
+	.slave		= &dra7xx_vcp2_hwmod,
+	.clk		= "l3_iclk_div",
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+/* l4_per2 -> vcp2 */
+static struct omap_hwmod_ocp_if dra7xx_l4_per2__vcp2 = {
+	.master		= &dra7xx_l4_per2_hwmod,
+	.slave		= &dra7xx_vcp2_hwmod,
+	.clk		= "l3_iclk_div",
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+/* l4_wkup -> wd_timer2 */
+static struct omap_hwmod_ocp_if dra7xx_l4_wkup__wd_timer2 = {
+	.master		= &dra7xx_l4_wkup_hwmod,
+	.slave		= &dra7xx_wd_timer2_hwmod,
+	.clk		= "wkupaon_iclk_mux",
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+static struct omap_hwmod_ocp_if *dra7xx_hwmod_ocp_ifs[] __initdata = {
+	&dra7xx_l3_main_2__l3_instr,
+	&dra7xx_l4_cfg__l3_main_1,
+	&dra7xx_mpu__l3_main_1,
+	&dra7xx_l3_main_1__l3_main_2,
+	&dra7xx_l4_cfg__l3_main_2,
+	&dra7xx_l3_main_1__l4_cfg,
+	&dra7xx_l3_main_1__l4_per1,
+	&dra7xx_l3_main_1__l4_per2,
+	&dra7xx_l3_main_1__l4_per3,
+	&dra7xx_l3_main_1__l4_wkup,
+	&dra7xx_l4_per2__atl,
+	&dra7xx_l3_main_1__bb2d,
+	&dra7xx_l4_wkup__counter_32k,
+	&dra7xx_l4_wkup__ctrl_module_wkup,
+	&dra7xx_l4_wkup__dcan1,
+	&dra7xx_l4_per2__dcan2,
+	&dra7xx_l4_cfg__dma_system,
+	&dra7xx_l3_main_1__dss,
+	&dra7xx_l3_main_1__dispc,
+	&dra7xx_l3_main_1__hdmi,
+	&dra7xx_l4_per1__elm,
+	&dra7xx_l4_wkup__gpio1,
+	&dra7xx_l4_per1__gpio2,
+	&dra7xx_l4_per1__gpio3,
+	&dra7xx_l4_per1__gpio4,
+	&dra7xx_l4_per1__gpio5,
+	&dra7xx_l4_per1__gpio6,
+	&dra7xx_l4_per1__gpio7,
+	&dra7xx_l4_per1__gpio8,
+	&dra7xx_l3_main_1__gpmc,
+	&dra7xx_l4_per1__hdq1w,
+	&dra7xx_l4_per1__i2c1,
+	&dra7xx_l4_per1__i2c2,
+	&dra7xx_l4_per1__i2c3,
+	&dra7xx_l4_per1__i2c4,
+	&dra7xx_l4_per1__i2c5,
+	&dra7xx_l4_per1__mcspi1,
+	&dra7xx_l4_per1__mcspi2,
+	&dra7xx_l4_per1__mcspi3,
+	&dra7xx_l4_per1__mcspi4,
+	&dra7xx_l4_per1__mmc1,
+	&dra7xx_l4_per1__mmc2,
+	&dra7xx_l4_per1__mmc3,
+	&dra7xx_l4_per1__mmc4,
+	&dra7xx_l4_cfg__mpu,
+	&dra7xx_l4_cfg__ocp2scp1,
+	&dra7xx_l3_main_1__qspi,
+	&dra7xx_l4_cfg__sata,
+	&dra7xx_l4_cfg__smartreflex_core,
+	&dra7xx_l4_cfg__smartreflex_mpu,
+	&dra7xx_l4_cfg__spinlock,
+	&dra7xx_l4_wkup__timer1,
+	&dra7xx_l4_per1__timer2,
+	&dra7xx_l4_per1__timer3,
+	&dra7xx_l4_per1__timer4,
+	&dra7xx_l4_per3__timer5,
+	&dra7xx_l4_per3__timer6,
+	&dra7xx_l4_per3__timer7,
+	&dra7xx_l4_per3__timer8,
+	&dra7xx_l4_per1__timer9,
+	&dra7xx_l4_per1__timer10,
+	&dra7xx_l4_per1__timer11,
+	&dra7xx_l4_per1__uart1,
+	&dra7xx_l4_per1__uart2,
+	&dra7xx_l4_per1__uart3,
+	&dra7xx_l4_per1__uart4,
+	&dra7xx_l4_per1__uart5,
+	&dra7xx_l4_per1__uart6,
+	&dra7xx_l4_per3__usb_otg_ss1,
+	&dra7xx_l4_per3__usb_otg_ss2,
+	&dra7xx_l4_per3__usb_otg_ss3,
+	&dra7xx_l4_per3__usb_otg_ss4,
+	&dra7xx_l3_main_1__vcp1,
+	&dra7xx_l4_per2__vcp1,
+	&dra7xx_l3_main_1__vcp2,
+	&dra7xx_l4_per2__vcp2,
+	&dra7xx_l4_wkup__wd_timer2,
+	NULL,
+};
+
+int __init dra7xx_hwmod_init(void)
+{
+	omap_hwmod_init();
+	return omap_hwmod_register_links(dra7xx_hwmod_ocp_ifs);
+}
diff --git a/arch/arm/mach-omap2/powerdomain.h b/arch/arm/mach-omap2/powerdomain.h
index e4d7bd6f94b8..baf3d8bf6bea 100644
--- a/arch/arm/mach-omap2/powerdomain.h
+++ b/arch/arm/mach-omap2/powerdomain.h
@@ -256,6 +256,7 @@ extern void omap3xxx_powerdomains_init(void);
 extern void am33xx_powerdomains_init(void);
 extern void omap44xx_powerdomains_init(void);
 extern void omap54xx_powerdomains_init(void);
+extern void dra7xx_powerdomains_init(void);
 
 extern struct pwrdm_ops omap2_pwrdm_operations;
 extern struct pwrdm_ops omap3_pwrdm_operations;
diff --git a/arch/arm/mach-omap2/powerdomains3xxx_data.c b/arch/arm/mach-omap2/powerdomains3xxx_data.c
index e2d4bd804523..328c1037cb60 100644
--- a/arch/arm/mach-omap2/powerdomains3xxx_data.c
+++ b/arch/arm/mach-omap2/powerdomains3xxx_data.c
@@ -336,6 +336,13 @@ static struct powerdomain dpll5_pwrdm = {
 	.voltdm		  = { .name = "core" },
 };
 
+static struct powerdomain alwon_81xx_pwrdm = {
+	.name		  = "alwon_pwrdm",
+	.prcm_offs	  = TI81XX_PRM_ALWON_MOD,
+	.pwrsts		  = PWRSTS_OFF_ON,
+	.voltdm		  = { .name = "core" },
+};
+
 static struct powerdomain device_81xx_pwrdm = {
 	.name		  = "device_pwrdm",
 	.prcm_offs	  = TI81XX_PRM_DEVICE_MOD,
@@ -442,6 +449,7 @@ static struct powerdomain *powerdomains_am35x[] __initdata = {
 };
 
 static struct powerdomain *powerdomains_ti81xx[] __initdata = {
+	&alwon_81xx_pwrdm,
 	&device_81xx_pwrdm,
 	&active_816x_pwrdm,
 	&default_816x_pwrdm,
diff --git a/arch/arm/mach-omap2/powerdomains54xx_data.c b/arch/arm/mach-omap2/powerdomains54xx_data.c
index 81f8a7cc26ee..ce1d752af991 100644
--- a/arch/arm/mach-omap2/powerdomains54xx_data.c
+++ b/arch/arm/mach-omap2/powerdomains54xx_data.c
@@ -25,7 +25,6 @@
 
 #include "prcm-common.h"
 #include "prcm44xx.h"
-#include "prm-regbits-54xx.h"
 #include "prm54xx.h"
 #include "prcm_mpu54xx.h"
 
diff --git a/arch/arm/mach-omap2/powerdomains7xx_data.c b/arch/arm/mach-omap2/powerdomains7xx_data.c
new file mode 100644
index 000000000000..48151d1cfde0
--- /dev/null
+++ b/arch/arm/mach-omap2/powerdomains7xx_data.c
@@ -0,0 +1,454 @@
+/*
+ * DRA7xx Power domains framework
+ *
+ * Copyright (C) 2009-2013 Texas Instruments, Inc.
+ * Copyright (C) 2009-2011 Nokia Corporation
+ *
+ * Generated by code originally written by:
+ * Abhijit Pagare (abhijitpagare@ti.com)
+ * Benoit Cousson (b-cousson@ti.com)
+ * Paul Walmsley (paul@pwsan.com)
+ *
+ * This file is automatically generated from the OMAP hardware databases.
+ * We respectfully ask that any modifications to this file be coordinated
+ * with the public linux-omap@vger.kernel.org mailing list and the
+ * authors above to ensure that the autogeneration scripts are kept
+ * up-to-date with the file contents.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+
+#include "powerdomain.h"
+
+#include "prcm-common.h"
+#include "prcm44xx.h"
+#include "prm7xx.h"
+#include "prcm_mpu7xx.h"
+
+/* iva_7xx_pwrdm: IVA-HD power domain */
+static struct powerdomain iva_7xx_pwrdm = {
+	.name		  = "iva_pwrdm",
+	.prcm_offs	  = DRA7XX_PRM_IVA_INST,
+	.prcm_partition	  = DRA7XX_PRM_PARTITION,
+	.pwrsts		  = PWRSTS_OFF_RET_ON,
+	.pwrsts_logic_ret = PWRSTS_OFF,
+	.banks		  = 4,
+	.pwrsts_mem_ret	= {
+		[0] = PWRSTS_OFF_RET,	/* hwa_mem */
+		[1] = PWRSTS_OFF_RET,	/* sl2_mem */
+		[2] = PWRSTS_OFF_RET,	/* tcm1_mem */
+		[3] = PWRSTS_OFF_RET,	/* tcm2_mem */
+	},
+	.pwrsts_mem_on	= {
+		[0] = PWRSTS_OFF_RET,	/* hwa_mem */
+		[1] = PWRSTS_OFF_RET,	/* sl2_mem */
+		[2] = PWRSTS_OFF_RET,	/* tcm1_mem */
+		[3] = PWRSTS_OFF_RET,	/* tcm2_mem */
+	},
+	.flags		  = PWRDM_HAS_LOWPOWERSTATECHANGE,
+};
+
+/* rtc_7xx_pwrdm:  */
+static struct powerdomain rtc_7xx_pwrdm = {
+	.name		  = "rtc_pwrdm",
+	.prcm_offs	  = DRA7XX_PRM_RTC_INST,
+	.prcm_partition	  = DRA7XX_PRM_PARTITION,
+	.pwrsts		  = PWRSTS_ON,
+};
+
+/* custefuse_7xx_pwrdm: Customer efuse controller power domain */
+static struct powerdomain custefuse_7xx_pwrdm = {
+	.name		  = "custefuse_pwrdm",
+	.prcm_offs	  = DRA7XX_PRM_CUSTEFUSE_INST,
+	.prcm_partition	  = DRA7XX_PRM_PARTITION,
+	.pwrsts		  = PWRSTS_OFF_ON,
+	.flags		  = PWRDM_HAS_LOWPOWERSTATECHANGE,
+};
+
+/* ipu_7xx_pwrdm: Audio back end power domain */
+static struct powerdomain ipu_7xx_pwrdm = {
+	.name		  = "ipu_pwrdm",
+	.prcm_offs	  = DRA7XX_PRM_IPU_INST,
+	.prcm_partition	  = DRA7XX_PRM_PARTITION,
+	.pwrsts		  = PWRSTS_OFF_RET_ON,
+	.pwrsts_logic_ret = PWRSTS_OFF,
+	.banks		  = 2,
+	.pwrsts_mem_ret	= {
+		[0] = PWRSTS_OFF_RET,	/* aessmem */
+		[1] = PWRSTS_OFF_RET,	/* periphmem */
+	},
+	.pwrsts_mem_on	= {
+		[0] = PWRSTS_OFF_RET,	/* aessmem */
+		[1] = PWRSTS_OFF_RET,	/* periphmem */
+	},
+	.flags		  = PWRDM_HAS_LOWPOWERSTATECHANGE,
+};
+
+/* dss_7xx_pwrdm: Display subsystem power domain */
+static struct powerdomain dss_7xx_pwrdm = {
+	.name		  = "dss_pwrdm",
+	.prcm_offs	  = DRA7XX_PRM_DSS_INST,
+	.prcm_partition	  = DRA7XX_PRM_PARTITION,
+	.pwrsts		  = PWRSTS_OFF_RET_ON,
+	.pwrsts_logic_ret = PWRSTS_OFF,
+	.banks		  = 1,
+	.pwrsts_mem_ret	= {
+		[0] = PWRSTS_OFF_RET,	/* dss_mem */
+	},
+	.pwrsts_mem_on	= {
+		[0] = PWRSTS_OFF_RET,	/* dss_mem */
+	},
+	.flags		  = PWRDM_HAS_LOWPOWERSTATECHANGE,
+};
+
+/* l4per_7xx_pwrdm: Target peripherals power domain */
+static struct powerdomain l4per_7xx_pwrdm = {
+	.name		  = "l4per_pwrdm",
+	.prcm_offs	  = DRA7XX_PRM_L4PER_INST,
+	.prcm_partition	  = DRA7XX_PRM_PARTITION,
+	.pwrsts		  = PWRSTS_RET_ON,
+	.pwrsts_logic_ret = PWRSTS_OFF_RET,
+	.banks		  = 2,
+	.pwrsts_mem_ret	= {
+		[0] = PWRSTS_OFF_RET,	/* nonretained_bank */
+		[1] = PWRSTS_OFF_RET,	/* retained_bank */
+	},
+	.pwrsts_mem_on	= {
+		[0] = PWRSTS_OFF_RET,	/* nonretained_bank */
+		[1] = PWRSTS_OFF_RET,	/* retained_bank */
+	},
+	.flags		  = PWRDM_HAS_LOWPOWERSTATECHANGE,
+};
+
+/* gpu_7xx_pwrdm: 3D accelerator power domain */
+static struct powerdomain gpu_7xx_pwrdm = {
+	.name		  = "gpu_pwrdm",
+	.prcm_offs	  = DRA7XX_PRM_GPU_INST,
+	.prcm_partition	  = DRA7XX_PRM_PARTITION,
+	.pwrsts		  = PWRSTS_OFF_ON,
+	.banks		  = 1,
+	.pwrsts_mem_ret	= {
+		[0] = PWRSTS_OFF_RET,	/* gpu_mem */
+	},
+	.pwrsts_mem_on	= {
+		[0] = PWRSTS_OFF_RET,	/* gpu_mem */
+	},
+	.flags		  = PWRDM_HAS_LOWPOWERSTATECHANGE,
+};
+
+/* wkupaon_7xx_pwrdm: Wake-up power domain */
+static struct powerdomain wkupaon_7xx_pwrdm = {
+	.name		  = "wkupaon_pwrdm",
+	.prcm_offs	  = DRA7XX_PRM_WKUPAON_INST,
+	.prcm_partition	  = DRA7XX_PRM_PARTITION,
+	.pwrsts		  = PWRSTS_ON,
+	.banks		  = 1,
+	.pwrsts_mem_ret	= {
+	},
+	.pwrsts_mem_on	= {
+		[0] = PWRSTS_ON,	/* wkup_bank */
+	},
+};
+
+/* core_7xx_pwrdm: CORE power domain */
+static struct powerdomain core_7xx_pwrdm = {
+	.name		  = "core_pwrdm",
+	.prcm_offs	  = DRA7XX_PRM_CORE_INST,
+	.prcm_partition	  = DRA7XX_PRM_PARTITION,
+	.pwrsts		  = PWRSTS_RET_ON,
+	.pwrsts_logic_ret = PWRSTS_OFF_RET,
+	.banks		  = 5,
+	.pwrsts_mem_ret	= {
+		[0] = PWRSTS_OFF_RET,	/* core_nret_bank */
+		[1] = PWRSTS_OFF_RET,	/* core_ocmram */
+		[2] = PWRSTS_OFF_RET,	/* core_other_bank */
+		[3] = PWRSTS_OFF_RET,	/* ipu_l2ram */
+		[4] = PWRSTS_OFF_RET,	/* ipu_unicache */
+	},
+	.pwrsts_mem_on	= {
+		[0] = PWRSTS_OFF_RET,	/* core_nret_bank */
+		[1] = PWRSTS_OFF_RET,	/* core_ocmram */
+		[2] = PWRSTS_OFF_RET,	/* core_other_bank */
+		[3] = PWRSTS_OFF_RET,	/* ipu_l2ram */
+		[4] = PWRSTS_OFF_RET,	/* ipu_unicache */
+	},
+	.flags		  = PWRDM_HAS_LOWPOWERSTATECHANGE,
+};
+
+/* coreaon_7xx_pwrdm: Always ON logic that sits in VDD_CORE voltage domain */
+static struct powerdomain coreaon_7xx_pwrdm = {
+	.name		  = "coreaon_pwrdm",
+	.prcm_offs	  = DRA7XX_PRM_COREAON_INST,
+	.prcm_partition	  = DRA7XX_PRM_PARTITION,
+	.pwrsts		  = PWRSTS_ON,
+};
+
+/* cpu0_7xx_pwrdm: MPU0 processor and Neon coprocessor power domain */
+static struct powerdomain cpu0_7xx_pwrdm = {
+	.name		  = "cpu0_pwrdm",
+	.prcm_offs	  = DRA7XX_MPU_PRCM_PRM_C0_INST,
+	.prcm_partition	  = DRA7XX_MPU_PRCM_PARTITION,
+	.pwrsts		  = PWRSTS_OFF_RET_ON,
+	.pwrsts_logic_ret = PWRSTS_OFF_RET,
+	.banks		  = 1,
+	.pwrsts_mem_ret	= {
+		[0] = PWRSTS_OFF_RET,	/* cpu0_l1 */
+	},
+	.pwrsts_mem_on	= {
+		[0] = PWRSTS_ON,	/* cpu0_l1 */
+	},
+};
+
+/* cpu1_7xx_pwrdm: MPU1 processor and Neon coprocessor power domain */
+static struct powerdomain cpu1_7xx_pwrdm = {
+	.name		  = "cpu1_pwrdm",
+	.prcm_offs	  = DRA7XX_MPU_PRCM_PRM_C1_INST,
+	.prcm_partition	  = DRA7XX_MPU_PRCM_PARTITION,
+	.pwrsts		  = PWRSTS_OFF_RET_ON,
+	.pwrsts_logic_ret = PWRSTS_OFF_RET,
+	.banks		  = 1,
+	.pwrsts_mem_ret	= {
+		[0] = PWRSTS_OFF_RET,	/* cpu1_l1 */
+	},
+	.pwrsts_mem_on	= {
+		[0] = PWRSTS_ON,	/* cpu1_l1 */
+	},
+};
+
+/* vpe_7xx_pwrdm:  */
+static struct powerdomain vpe_7xx_pwrdm = {
+	.name		  = "vpe_pwrdm",
+	.prcm_offs	  = DRA7XX_PRM_VPE_INST,
+	.prcm_partition	  = DRA7XX_PRM_PARTITION,
+	.pwrsts		  = PWRSTS_OFF_RET_ON,
+	.pwrsts_logic_ret = PWRSTS_OFF_RET,
+	.banks		  = 1,
+	.pwrsts_mem_ret	= {
+		[0] = PWRSTS_OFF_RET,	/* vpe_bank */
+	},
+	.pwrsts_mem_on	= {
+		[0] = PWRSTS_OFF_RET,	/* vpe_bank */
+	},
+	.flags		  = PWRDM_HAS_LOWPOWERSTATECHANGE,
+};
+
+/* mpu_7xx_pwrdm: Modena processor and the Neon coprocessor power domain */
+static struct powerdomain mpu_7xx_pwrdm = {
+	.name		  = "mpu_pwrdm",
+	.prcm_offs	  = DRA7XX_PRM_MPU_INST,
+	.prcm_partition	  = DRA7XX_PRM_PARTITION,
+	.pwrsts		  = PWRSTS_RET_ON,
+	.pwrsts_logic_ret = PWRSTS_OFF_RET,
+	.banks		  = 2,
+	.pwrsts_mem_ret	= {
+		[0] = PWRSTS_OFF_RET,	/* mpu_l2 */
+		[1] = PWRSTS_RET,	/* mpu_ram */
+	},
+	.pwrsts_mem_on	= {
+		[0] = PWRSTS_OFF_RET,	/* mpu_l2 */
+		[1] = PWRSTS_OFF_RET,	/* mpu_ram */
+	},
+};
+
+/* l3init_7xx_pwrdm: L3 initators pheripherals power domain  */
+static struct powerdomain l3init_7xx_pwrdm = {
+	.name		  = "l3init_pwrdm",
+	.prcm_offs	  = DRA7XX_PRM_L3INIT_INST,
+	.prcm_partition	  = DRA7XX_PRM_PARTITION,
+	.pwrsts		  = PWRSTS_RET_ON,
+	.pwrsts_logic_ret = PWRSTS_OFF_RET,
+	.banks		  = 3,
+	.pwrsts_mem_ret	= {
+		[0] = PWRSTS_OFF_RET,	/* gmac_bank */
+		[1] = PWRSTS_OFF_RET,	/* l3init_bank1 */
+		[2] = PWRSTS_OFF_RET,	/* l3init_bank2 */
+	},
+	.pwrsts_mem_on	= {
+		[0] = PWRSTS_OFF_RET,	/* gmac_bank */
+		[1] = PWRSTS_OFF_RET,	/* l3init_bank1 */
+		[2] = PWRSTS_OFF_RET,	/* l3init_bank2 */
+	},
+	.flags		  = PWRDM_HAS_LOWPOWERSTATECHANGE,
+};
+
+/* eve3_7xx_pwrdm:  */
+static struct powerdomain eve3_7xx_pwrdm = {
+	.name		  = "eve3_pwrdm",
+	.prcm_offs	  = DRA7XX_PRM_EVE3_INST,
+	.prcm_partition	  = DRA7XX_PRM_PARTITION,
+	.pwrsts		  = PWRSTS_OFF_ON,
+	.banks		  = 1,
+	.pwrsts_mem_ret	= {
+		[0] = PWRSTS_OFF_RET,	/* eve3_bank */
+	},
+	.pwrsts_mem_on	= {
+		[0] = PWRSTS_OFF_RET,	/* eve3_bank */
+	},
+	.flags		  = PWRDM_HAS_LOWPOWERSTATECHANGE,
+};
+
+/* emu_7xx_pwrdm: Emulation power domain */
+static struct powerdomain emu_7xx_pwrdm = {
+	.name		  = "emu_pwrdm",
+	.prcm_offs	  = DRA7XX_PRM_EMU_INST,
+	.prcm_partition	  = DRA7XX_PRM_PARTITION,
+	.pwrsts		  = PWRSTS_OFF_ON,
+	.banks		  = 1,
+	.pwrsts_mem_ret	= {
+		[0] = PWRSTS_OFF_RET,	/* emu_bank */
+	},
+	.pwrsts_mem_on	= {
+		[0] = PWRSTS_OFF_RET,	/* emu_bank */
+	},
+};
+
+/* dsp2_7xx_pwrdm:  */
+static struct powerdomain dsp2_7xx_pwrdm = {
+	.name		  = "dsp2_pwrdm",
+	.prcm_offs	  = DRA7XX_PRM_DSP2_INST,
+	.prcm_partition	  = DRA7XX_PRM_PARTITION,
+	.pwrsts		  = PWRSTS_OFF_ON,
+	.banks		  = 3,
+	.pwrsts_mem_ret	= {
+		[0] = PWRSTS_OFF_RET,	/* dsp2_edma */
+		[1] = PWRSTS_OFF_RET,	/* dsp2_l1 */
+		[2] = PWRSTS_OFF_RET,	/* dsp2_l2 */
+	},
+	.pwrsts_mem_on	= {
+		[0] = PWRSTS_OFF_RET,	/* dsp2_edma */
+		[1] = PWRSTS_OFF_RET,	/* dsp2_l1 */
+		[2] = PWRSTS_OFF_RET,	/* dsp2_l2 */
+	},
+	.flags		  = PWRDM_HAS_LOWPOWERSTATECHANGE,
+};
+
+/* dsp1_7xx_pwrdm: Tesla processor power domain */
+static struct powerdomain dsp1_7xx_pwrdm = {
+	.name		  = "dsp1_pwrdm",
+	.prcm_offs	  = DRA7XX_PRM_DSP1_INST,
+	.prcm_partition	  = DRA7XX_PRM_PARTITION,
+	.pwrsts		  = PWRSTS_OFF_ON,
+	.banks		  = 3,
+	.pwrsts_mem_ret	= {
+		[0] = PWRSTS_OFF_RET,	/* dsp1_edma */
+		[1] = PWRSTS_OFF_RET,	/* dsp1_l1 */
+		[2] = PWRSTS_OFF_RET,	/* dsp1_l2 */
+	},
+	.pwrsts_mem_on	= {
+		[0] = PWRSTS_OFF_RET,	/* dsp1_edma */
+		[1] = PWRSTS_OFF_RET,	/* dsp1_l1 */
+		[2] = PWRSTS_OFF_RET,	/* dsp1_l2 */
+	},
+	.flags		  = PWRDM_HAS_LOWPOWERSTATECHANGE,
+};
+
+/* cam_7xx_pwrdm: Camera subsystem power domain */
+static struct powerdomain cam_7xx_pwrdm = {
+	.name		  = "cam_pwrdm",
+	.prcm_offs	  = DRA7XX_PRM_CAM_INST,
+	.prcm_partition	  = DRA7XX_PRM_PARTITION,
+	.pwrsts		  = PWRSTS_OFF_ON,
+	.banks		  = 1,
+	.pwrsts_mem_ret	= {
+		[0] = PWRSTS_OFF_RET,	/* vip_bank */
+	},
+	.pwrsts_mem_on	= {
+		[0] = PWRSTS_OFF_RET,	/* vip_bank */
+	},
+	.flags		  = PWRDM_HAS_LOWPOWERSTATECHANGE,
+};
+
+/* eve4_7xx_pwrdm:  */
+static struct powerdomain eve4_7xx_pwrdm = {
+	.name		  = "eve4_pwrdm",
+	.prcm_offs	  = DRA7XX_PRM_EVE4_INST,
+	.prcm_partition	  = DRA7XX_PRM_PARTITION,
+	.pwrsts		  = PWRSTS_OFF_ON,
+	.banks		  = 1,
+	.pwrsts_mem_ret	= {
+		[0] = PWRSTS_OFF_RET,	/* eve4_bank */
+	},
+	.pwrsts_mem_on	= {
+		[0] = PWRSTS_OFF_RET,	/* eve4_bank */
+	},
+	.flags		  = PWRDM_HAS_LOWPOWERSTATECHANGE,
+};
+
+/* eve2_7xx_pwrdm:  */
+static struct powerdomain eve2_7xx_pwrdm = {
+	.name		  = "eve2_pwrdm",
+	.prcm_offs	  = DRA7XX_PRM_EVE2_INST,
+	.prcm_partition	  = DRA7XX_PRM_PARTITION,
+	.pwrsts		  = PWRSTS_OFF_ON,
+	.banks		  = 1,
+	.pwrsts_mem_ret	= {
+		[0] = PWRSTS_OFF_RET,	/* eve2_bank */
+	},
+	.pwrsts_mem_on	= {
+		[0] = PWRSTS_OFF_RET,	/* eve2_bank */
+	},
+	.flags		  = PWRDM_HAS_LOWPOWERSTATECHANGE,
+};
+
+/* eve1_7xx_pwrdm:  */
+static struct powerdomain eve1_7xx_pwrdm = {
+	.name		  = "eve1_pwrdm",
+	.prcm_offs	  = DRA7XX_PRM_EVE1_INST,
+	.prcm_partition	  = DRA7XX_PRM_PARTITION,
+	.pwrsts		  = PWRSTS_OFF_ON,
+	.banks		  = 1,
+	.pwrsts_mem_ret	= {
+		[0] = PWRSTS_OFF_RET,	/* eve1_bank */
+	},
+	.pwrsts_mem_on	= {
+		[0] = PWRSTS_OFF_RET,	/* eve1_bank */
+	},
+	.flags		  = PWRDM_HAS_LOWPOWERSTATECHANGE,
+};
+
+/*
+ * The following power domains are not under SW control
+ *
+ * mpuaon
+ * mmaon
+ */
+
+/* As powerdomains are added or removed above, this list must also be changed */
+static struct powerdomain *powerdomains_dra7xx[] __initdata = {
+	&iva_7xx_pwrdm,
+	&rtc_7xx_pwrdm,
+	&custefuse_7xx_pwrdm,
+	&ipu_7xx_pwrdm,
+	&dss_7xx_pwrdm,
+	&l4per_7xx_pwrdm,
+	&gpu_7xx_pwrdm,
+	&wkupaon_7xx_pwrdm,
+	&core_7xx_pwrdm,
+	&coreaon_7xx_pwrdm,
+	&cpu0_7xx_pwrdm,
+	&cpu1_7xx_pwrdm,
+	&vpe_7xx_pwrdm,
+	&mpu_7xx_pwrdm,
+	&l3init_7xx_pwrdm,
+	&eve3_7xx_pwrdm,
+	&emu_7xx_pwrdm,
+	&dsp2_7xx_pwrdm,
+	&dsp1_7xx_pwrdm,
+	&cam_7xx_pwrdm,
+	&eve4_7xx_pwrdm,
+	&eve2_7xx_pwrdm,
+	&eve1_7xx_pwrdm,
+	NULL
+};
+
+void __init dra7xx_powerdomains_init(void)
+{
+	pwrdm_register_platform_funcs(&omap4_pwrdm_operations);
+	pwrdm_register_pwrdms(powerdomains_dra7xx);
+	pwrdm_complete_init();
+}
diff --git a/arch/arm/mach-omap2/prcm-common.h b/arch/arm/mach-omap2/prcm-common.h
index ff1ac4a82a04..0e841fd9498a 100644
--- a/arch/arm/mach-omap2/prcm-common.h
+++ b/arch/arm/mach-omap2/prcm-common.h
@@ -58,6 +58,7 @@
 #define TI816X_PRM_IVAHD1_MOD			0x0d00
 #define TI816X_PRM_IVAHD2_MOD			0x0e00
 #define TI816X_PRM_SGX_MOD				0x0f00
+#define TI81XX_PRM_ALWON_MOD			0x1800
 
 /* 24XX register bits shared between CM & PRM registers */
 
diff --git a/arch/arm/mach-omap2/prcm44xx.h b/arch/arm/mach-omap2/prcm44xx.h
index f429cdd5a118..4fea2cfdf2c3 100644
--- a/arch/arm/mach-omap2/prcm44xx.h
+++ b/arch/arm/mach-omap2/prcm44xx.h
@@ -38,6 +38,11 @@
 #define OMAP54XX_SCRM_PARTITION			4
 #define OMAP54XX_PRCM_MPU_PARTITION		5
 
+#define DRA7XX_PRM_PARTITION                   1
+#define DRA7XX_CM_CORE_AON_PARTITION           2
+#define DRA7XX_CM_CORE_PARTITION               3
+#define DRA7XX_MPU_PRCM_PARTITION              5
+
 /*
  * OMAP4_MAX_PRCM_PARTITIONS: set to the highest value of the PRCM partition
  * IDs, plus one
diff --git a/arch/arm/mach-omap2/prcm_mpu7xx.h b/arch/arm/mach-omap2/prcm_mpu7xx.h
new file mode 100644
index 000000000000..9ebb5ce0878f
--- /dev/null
+++ b/arch/arm/mach-omap2/prcm_mpu7xx.h
@@ -0,0 +1,78 @@
+/*
+ * DRA7xx PRCM MPU instance offset macros
+ *
+ * Copyright (C) 2013 Texas Instruments Incorporated - http://www.ti.com
+ *
+ * Generated by code originally written by:
+ * Paul Walmsley (paul@pwsan.com)
+ * Rajendra Nayak (rnayak@ti.com)
+ * Benoit Cousson (b-cousson@ti.com)
+ *
+ * This file is automatically generated from the OMAP hardware databases.
+ * We respectfully ask that any modifications to this file be coordinated
+ * with the public linux-omap@vger.kernel.org mailing list and the
+ * authors above to ensure that the autogeneration scripts are kept
+ * up-to-date with the file contents.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __ARCH_ARM_MACH_OMAP2_PRCM_MPU7XX_H
+#define __ARCH_ARM_MACH_OMAP2_PRCM_MPU7XX_H
+
+#include "prcm_mpu_44xx_54xx.h"
+
+#define DRA7XX_PRCM_MPU_BASE			0x48243000
+
+#define DRA7XX_PRCM_MPU_REGADDR(inst, reg)				\
+	OMAP2_L4_IO_ADDRESS(DRA7XX_PRCM_MPU_BASE + (inst) + (reg))
+
+/* MPU_PRCM instances */
+#define DRA7XX_MPU_PRCM_OCP_SOCKET_INST	0x0000
+#define DRA7XX_MPU_PRCM_DEVICE_INST	0x0200
+#define DRA7XX_MPU_PRCM_PRM_C0_INST	0x0400
+#define DRA7XX_MPU_PRCM_CM_C0_INST	0x0600
+#define DRA7XX_MPU_PRCM_PRM_C1_INST	0x0800
+#define DRA7XX_MPU_PRCM_CM_C1_INST	0x0a00
+
+/* PRCM_MPU clockdomain register offsets (from instance start) */
+#define DRA7XX_MPU_PRCM_CM_C0_CPU0_CDOFFS	0x0000
+#define DRA7XX_MPU_PRCM_CM_C1_CPU1_CDOFFS	0x0000
+
+
+/* MPU_PRCM */
+
+/* MPU_PRCM.PRCM_MPU_OCP_SOCKET register offsets */
+#define DRA7XX_REVISION_PRCM_MPU_OFFSET				0x0000
+
+/* MPU_PRCM.PRCM_MPU_DEVICE register offsets */
+#define DRA7XX_PRM_FRAC_INCREMENTER_NUMERATOR_OFFSET		0x0010
+#define DRA7XX_PRM_FRAC_INCREMENTER_DENUMERATOR_RELOAD_OFFSET	0x0014
+
+/* MPU_PRCM.PRCM_MPU_PRM_C0 register offsets */
+#define DRA7XX_PM_CPU0_PWRSTCTRL_OFFSET				0x0000
+#define DRA7XX_PM_CPU0_PWRSTST_OFFSET				0x0004
+#define DRA7XX_RM_CPU0_CPU0_RSTCTRL_OFFSET			0x0010
+#define DRA7XX_RM_CPU0_CPU0_RSTST_OFFSET			0x0014
+#define DRA7XX_RM_CPU0_CPU0_CONTEXT_OFFSET			0x0024
+
+/* MPU_PRCM.PRCM_MPU_CM_C0 register offsets */
+#define DRA7XX_CM_CPU0_CLKSTCTRL_OFFSET				0x0000
+#define DRA7XX_CM_CPU0_CPU0_CLKCTRL_OFFSET			0x0020
+#define DRA7XX_CM_CPU0_CPU0_CLKCTRL				DRA7XX_MPU_PRCM_REGADDR(DRA7XX_MPU_PRCM_CM_C0_INST, 0x0020)
+
+/* MPU_PRCM.PRCM_MPU_PRM_C1 register offsets */
+#define DRA7XX_PM_CPU1_PWRSTCTRL_OFFSET				0x0000
+#define DRA7XX_PM_CPU1_PWRSTST_OFFSET				0x0004
+#define DRA7XX_RM_CPU1_CPU1_RSTCTRL_OFFSET			0x0010
+#define DRA7XX_RM_CPU1_CPU1_RSTST_OFFSET			0x0014
+#define DRA7XX_RM_CPU1_CPU1_CONTEXT_OFFSET			0x0024
+
+/* MPU_PRCM.PRCM_MPU_CM_C1 register offsets */
+#define DRA7XX_CM_CPU1_CLKSTCTRL_OFFSET				0x0000
+#define DRA7XX_CM_CPU1_CPU1_CLKCTRL_OFFSET			0x0020
+#define DRA7XX_CM_CPU1_CPU1_CLKCTRL				DRA7XX_MPU_PRCM_REGADDR(DRA7XX_MPU_PRCM_CM_C1_INST, 0x0020)
+
+#endif
diff --git a/arch/arm/mach-omap2/prm-regbits-24xx.h b/arch/arm/mach-omap2/prm-regbits-24xx.h
index 91aa5106d637..37fc905c9636 100644
--- a/arch/arm/mach-omap2/prm-regbits-24xx.h
+++ b/arch/arm/mach-omap2/prm-regbits-24xx.h
@@ -16,274 +16,27 @@
 
 #include "prm2xxx.h"
 
-/* Bits shared between registers */
-
-/* PRCM_IRQSTATUS_MPU, PM_IRQSTATUS_DSP, PRCM_IRQSTATUS_IVA shared bits */
-#define OMAP24XX_VOLTTRANS_ST_MASK			(1 << 2)
-#define OMAP24XX_WKUP2_ST_MASK				(1 << 1)
-#define OMAP24XX_WKUP1_ST_MASK				(1 << 0)
-
-/* PRCM_IRQENABLE_MPU, PM_IRQENABLE_DSP, PRCM_IRQENABLE_IVA shared bits */
-#define OMAP24XX_VOLTTRANS_EN_MASK			(1 << 2)
-#define OMAP24XX_WKUP2_EN_MASK				(1 << 1)
-#define OMAP24XX_WKUP1_EN_MASK				(1 << 0)
-
-/* PM_WKDEP_GFX, PM_WKDEP_MPU, PM_WKDEP_DSP, PM_WKDEP_MDM shared bits */
-#define OMAP24XX_EN_MPU_SHIFT				1
-#define OMAP24XX_EN_MPU_MASK				(1 << 1)
 #define OMAP24XX_EN_CORE_SHIFT 				0
-#define OMAP24XX_EN_CORE_MASK				(1 << 0)
-
-/*
- * PM_PWSTCTRL_MPU, PM_PWSTCTRL_GFX, PM_PWSTCTRL_DSP, PM_PWSTCTRL_MDM
- * shared bits
- */
-#define OMAP24XX_MEMONSTATE_SHIFT			10
-#define OMAP24XX_MEMONSTATE_MASK			(0x3 << 10)
-#define OMAP24XX_MEMRETSTATE_MASK			(1 << 3)
-
-/* PM_PWSTCTRL_GFX, PM_PWSTCTRL_DSP, PM_PWSTCTRL_MDM shared bits */
 #define OMAP24XX_FORCESTATE_MASK			(1 << 18)
-
-/*
- * PM_PWSTST_CORE, PM_PWSTST_GFX, PM_PWSTST_MPU, PM_PWSTST_DSP,
- * PM_PWSTST_MDM shared bits
- */
-#define OMAP24XX_CLKACTIVITY_MASK			(1 << 19)
-
-/* PM_PWSTST_MPU, PM_PWSTST_CORE, PM_PWSTST_DSP shared bits */
-#define OMAP24XX_LASTSTATEENTERED_SHIFT			4
-#define OMAP24XX_LASTSTATEENTERED_MASK			(0x3 << 4)
-
-/* PM_PWSTST_MPU and PM_PWSTST_DSP shared bits */
-#define OMAP2430_MEMSTATEST_SHIFT			10
-#define OMAP2430_MEMSTATEST_MASK			(0x3 << 10)
-
-/* PM_PWSTST_GFX, PM_PWSTST_DSP, PM_PWSTST_MDM shared bits */
-#define OMAP24XX_POWERSTATEST_SHIFT			0
-#define OMAP24XX_POWERSTATEST_MASK			(0x3 << 0)
-
-
-/* Bits specific to each register */
-
-/* PRCM_REVISION */
-#define OMAP24XX_REV_SHIFT				0
-#define OMAP24XX_REV_MASK				(0xff << 0)
-
-/* PRCM_SYSCONFIG */
 #define OMAP24XX_AUTOIDLE_MASK				(1 << 0)
-
-/* PRCM_IRQSTATUS_MPU specific bits */
-#define OMAP2430_DPLL_RECAL_ST_MASK			(1 << 6)
-#define OMAP24XX_TRANSITION_ST_MASK			(1 << 5)
-#define OMAP24XX_EVGENOFF_ST_MASK			(1 << 4)
-#define OMAP24XX_EVGENON_ST_MASK			(1 << 3)
-
-/* PRCM_IRQENABLE_MPU specific bits */
-#define OMAP2430_DPLL_RECAL_EN_MASK			(1 << 6)
-#define OMAP24XX_TRANSITION_EN_MASK			(1 << 5)
-#define OMAP24XX_EVGENOFF_EN_MASK			(1 << 4)
-#define OMAP24XX_EVGENON_EN_MASK			(1 << 3)
-
-/* PRCM_VOLTCTRL */
 #define OMAP24XX_AUTO_EXTVOLT_MASK			(1 << 15)
-#define OMAP24XX_FORCE_EXTVOLT_MASK			(1 << 14)
 #define OMAP24XX_SETOFF_LEVEL_SHIFT			12
-#define OMAP24XX_SETOFF_LEVEL_MASK			(0x3 << 12)
 #define OMAP24XX_MEMRETCTRL_MASK			(1 << 8)
 #define OMAP24XX_SETRET_LEVEL_SHIFT			6
-#define OMAP24XX_SETRET_LEVEL_MASK			(0x3 << 6)
 #define OMAP24XX_VOLT_LEVEL_SHIFT			0
-#define OMAP24XX_VOLT_LEVEL_MASK			(0x3 << 0)
-
-/* PRCM_VOLTST */
-#define OMAP24XX_ST_VOLTLEVEL_SHIFT			0
-#define OMAP24XX_ST_VOLTLEVEL_MASK			(0x3 << 0)
-
-/* PRCM_CLKSRC_CTRL specific bits */
-
-/* PRCM_CLKOUT_CTRL */
 #define OMAP2420_CLKOUT2_EN_SHIFT			15
-#define OMAP2420_CLKOUT2_EN_MASK			(1 << 15)
 #define OMAP2420_CLKOUT2_DIV_SHIFT			11
-#define OMAP2420_CLKOUT2_DIV_MASK			(0x7 << 11)
 #define OMAP2420_CLKOUT2_DIV_WIDTH			3
-#define OMAP2420_CLKOUT2_SOURCE_SHIFT			8
 #define OMAP2420_CLKOUT2_SOURCE_MASK			(0x3 << 8)
 #define OMAP24XX_CLKOUT_EN_SHIFT			7
-#define OMAP24XX_CLKOUT_EN_MASK				(1 << 7)
 #define OMAP24XX_CLKOUT_DIV_SHIFT			3
-#define OMAP24XX_CLKOUT_DIV_MASK			(0x7 << 3)
 #define OMAP24XX_CLKOUT_DIV_WIDTH			3
-#define OMAP24XX_CLKOUT_SOURCE_SHIFT			0
 #define OMAP24XX_CLKOUT_SOURCE_MASK			(0x3 << 0)
-
-/* PRCM_CLKEMUL_CTRL */
 #define OMAP24XX_EMULATION_EN_SHIFT			0
-#define OMAP24XX_EMULATION_EN_MASK			(1 << 0)
-
-/* PRCM_CLKCFG_CTRL */
-#define OMAP24XX_VALID_CONFIG_MASK			(1 << 0)
-
-/* PRCM_CLKCFG_STATUS */
-#define OMAP24XX_CONFIG_STATUS_MASK			(1 << 0)
-
-/* PRCM_VOLTSETUP specific bits */
-
-/* PRCM_CLKSSETUP specific bits */
-
-/* PRCM_POLCTRL */
-#define OMAP2420_CLKOUT2_POL_MASK			(1 << 10)
-#define OMAP24XX_CLKOUT_POL_MASK			(1 << 9)
-#define OMAP24XX_CLKREQ_POL_MASK			(1 << 8)
-#define OMAP2430_USE_POWEROK_MASK			(1 << 2)
-#define OMAP2430_POWEROK_POL_MASK			(1 << 1)
-#define OMAP24XX_EXTVOL_POL_MASK			(1 << 0)
-
-/* RM_RSTST_MPU specific bits */
-/* 2430 calls GLOBALWMPU_RST "GLOBALWARM_RST" instead */
-
-/* PM_WKDEP_MPU specific bits */
 #define OMAP2430_PM_WKDEP_MPU_EN_MDM_SHIFT		5
-#define OMAP2430_PM_WKDEP_MPU_EN_MDM_MASK		(1 << 5)
 #define OMAP24XX_PM_WKDEP_MPU_EN_DSP_SHIFT		2
-#define OMAP24XX_PM_WKDEP_MPU_EN_DSP_MASK		(1 << 2)
-
-/* PM_EVGENCTRL_MPU specific bits */
-
-/* PM_EVEGENONTIM_MPU specific bits */
-
-/* PM_EVEGENOFFTIM_MPU specific bits */
-
-/* PM_PWSTCTRL_MPU specific bits */
-#define OMAP2430_FORCESTATE_MASK			(1 << 18)
-
-/* PM_PWSTST_MPU specific bits */
-/* INTRANSITION, CLKACTIVITY, POWERSTATE, MEMSTATEST are 2430 only */
-
-/* PM_WKEN1_CORE specific bits */
-
-/* PM_WKEN2_CORE specific bits */
-
-/* PM_WKST1_CORE specific bits*/
-
-/* PM_WKST2_CORE specific bits */
-
-/* PM_WKDEP_CORE specific bits*/
-#define OMAP2430_PM_WKDEP_CORE_EN_MDM_MASK		(1 << 5)
-#define OMAP24XX_PM_WKDEP_CORE_EN_GFX_MASK		(1 << 3)
-#define OMAP24XX_PM_WKDEP_CORE_EN_DSP_MASK		(1 << 2)
-
-/* PM_PWSTCTRL_CORE specific bits */
-#define OMAP24XX_MEMORYCHANGE_MASK			(1 << 20)
-#define OMAP24XX_MEM3ONSTATE_SHIFT			14
-#define OMAP24XX_MEM3ONSTATE_MASK			(0x3 << 14)
-#define OMAP24XX_MEM2ONSTATE_SHIFT			12
-#define OMAP24XX_MEM2ONSTATE_MASK			(0x3 << 12)
-#define OMAP24XX_MEM1ONSTATE_SHIFT			10
-#define OMAP24XX_MEM1ONSTATE_MASK			(0x3 << 10)
-#define OMAP24XX_MEM3RETSTATE_MASK			(1 << 5)
-#define OMAP24XX_MEM2RETSTATE_MASK			(1 << 4)
-#define OMAP24XX_MEM1RETSTATE_MASK			(1 << 3)
-
-/* PM_PWSTST_CORE specific bits */
-#define OMAP24XX_MEM3STATEST_SHIFT			14
-#define OMAP24XX_MEM3STATEST_MASK			(0x3 << 14)
-#define OMAP24XX_MEM2STATEST_SHIFT			12
-#define OMAP24XX_MEM2STATEST_MASK			(0x3 << 12)
-#define OMAP24XX_MEM1STATEST_SHIFT			10
-#define OMAP24XX_MEM1STATEST_MASK			(0x3 << 10)
-
-/* RM_RSTCTRL_GFX */
-#define OMAP24XX_GFX_RST_MASK				(1 << 0)
-
-/* RM_RSTST_GFX specific bits */
-#define OMAP24XX_GFX_SW_RST_MASK			(1 << 4)
-
-/* PM_PWSTCTRL_GFX specific bits */
-
-/* PM_WKDEP_GFX specific bits */
-/* 2430 often calls EN_WAKEUP "EN_WKUP" */
-
-/* RM_RSTCTRL_WKUP specific bits */
-
-/* RM_RSTTIME_WKUP specific bits */
-
-/* RM_RSTST_WKUP specific bits */
-/* 2430 calls EXTWMPU_RST "EXTWARM_RST" and GLOBALWMPU_RST "GLOBALWARM_RST" */
 #define OMAP24XX_EXTWMPU_RST_SHIFT			6
-#define OMAP24XX_EXTWMPU_RST_MASK			(1 << 6)
 #define OMAP24XX_SECU_WD_RST_SHIFT			5
-#define OMAP24XX_SECU_WD_RST_MASK			(1 << 5)
 #define OMAP24XX_MPU_WD_RST_SHIFT			4
-#define OMAP24XX_MPU_WD_RST_MASK			(1 << 4)
 #define OMAP24XX_SECU_VIOL_RST_SHIFT			3
-#define OMAP24XX_SECU_VIOL_RST_MASK			(1 << 3)
-
-/* PM_WKEN_WKUP specific bits */
-
-/* PM_WKST_WKUP specific bits */
-
-/* RM_RSTCTRL_DSP */
-#define OMAP2420_RST_IVA_MASK				(1 << 8)
-#define OMAP24XX_RST2_DSP_MASK				(1 << 1)
-#define OMAP24XX_RST1_DSP_MASK				(1 << 0)
-
-/* RM_RSTST_DSP specific bits */
-/* 2430 calls GLOBALWMPU_RST "GLOBALWARM_RST" */
-#define OMAP2420_IVA_SW_RST_MASK			(1 << 8)
-#define OMAP24XX_DSP_SW_RST2_MASK			(1 << 5)
-#define OMAP24XX_DSP_SW_RST1_MASK			(1 << 4)
-
-/* PM_WKDEP_DSP specific bits */
-
-/* PM_PWSTCTRL_DSP specific bits */
-/* 2430 only: MEMONSTATE, MEMRETSTATE */
-#define OMAP2420_MEMIONSTATE_SHIFT			12
-#define OMAP2420_MEMIONSTATE_MASK			(0x3 << 12)
-#define OMAP2420_MEMIRETSTATE_MASK			(1 << 4)
-
-/* PM_PWSTST_DSP specific bits */
-/* MEMSTATEST is 2430 only */
-#define OMAP2420_MEMISTATEST_SHIFT			12
-#define OMAP2420_MEMISTATEST_MASK			(0x3 << 12)
-
-/* PRCM_IRQSTATUS_DSP specific bits */
-
-/* PRCM_IRQENABLE_DSP specific bits */
-
-/* RM_RSTCTRL_MDM */
-/* 2430 only */
-#define OMAP2430_PWRON1_MDM_MASK			(1 << 1)
-#define OMAP2430_RST1_MDM_MASK				(1 << 0)
-
-/* RM_RSTST_MDM specific bits */
-/* 2430 only */
-#define OMAP2430_MDM_SECU_VIOL_MASK			(1 << 6)
-#define OMAP2430_MDM_SW_PWRON1_MASK			(1 << 5)
-#define OMAP2430_MDM_SW_RST1_MASK			(1 << 4)
-
-/* PM_WKEN_MDM */
-/* 2430 only */
-#define OMAP2430_PM_WKEN_MDM_EN_MDM_MASK		(1 << 0)
-
-/* PM_WKST_MDM specific bits */
-/* 2430 only */
-
-/* PM_WKDEP_MDM specific bits */
-/* 2430 only */
-
-/* PM_PWSTCTRL_MDM specific bits */
-/* 2430 only */
-#define OMAP2430_KILLDOMAINWKUP_MASK			(1 << 19)
-
-/* PM_PWSTST_MDM specific bits */
-/* 2430 only */
-
-/* PRCM_IRQSTATUS_IVA */
-/* 2420 only */
-
-/* PRCM_IRQENABLE_IVA */
-/* 2420 only */
-
 #endif
diff --git a/arch/arm/mach-omap2/prm-regbits-33xx.h b/arch/arm/mach-omap2/prm-regbits-33xx.h
index 0221b5c20e87..84feecee4fe6 100644
--- a/arch/arm/mach-omap2/prm-regbits-33xx.h
+++ b/arch/arm/mach-omap2/prm-regbits-33xx.h
@@ -18,340 +18,35 @@
 
 #include "prm.h"
 
-/* Used by PRM_LDO_SRAM_CORE_SETUP, PRM_LDO_SRAM_MPU_SETUP */
-#define AM33XX_ABBOFF_ACT_EXPORT_SHIFT			1
-#define AM33XX_ABBOFF_ACT_EXPORT_MASK			(1 << 1)
-
-/* Used by PRM_LDO_SRAM_CORE_SETUP, PRM_LDO_SRAM_MPU_SETUP */
-#define AM33XX_ABBOFF_SLEEP_EXPORT_SHIFT		2
-#define AM33XX_ABBOFF_SLEEP_EXPORT_MASK			(1 << 2)
-
-/* Used by PRM_LDO_SRAM_CORE_SETUP, PRM_LDO_SRAM_MPU_SETUP */
-#define AM33XX_AIPOFF_SHIFT				8
-#define AM33XX_AIPOFF_MASK				(1 << 8)
-
-/* Used by PM_WKUP_PWRSTST */
-#define AM33XX_DEBUGSS_MEM_STATEST_SHIFT		17
-#define AM33XX_DEBUGSS_MEM_STATEST_MASK			(0x3 << 17)
-
-/* Used by PRM_LDO_SRAM_CORE_SETUP, PRM_LDO_SRAM_MPU_SETUP */
-#define AM33XX_DISABLE_RTA_EXPORT_SHIFT			0
-#define AM33XX_DISABLE_RTA_EXPORT_MASK			(1 << 0)
-
-/* Used by PRM_IRQENABLE_M3, PRM_IRQENABLE_MPU */
-#define AM33XX_DPLL_CORE_RECAL_EN_SHIFT			12
-#define AM33XX_DPLL_CORE_RECAL_EN_MASK			(1 << 12)
-
-/* Used by PRM_IRQSTATUS_M3, PRM_IRQSTATUS_MPU */
-#define AM33XX_DPLL_CORE_RECAL_ST_SHIFT			12
-#define AM33XX_DPLL_CORE_RECAL_ST_MASK			(1 << 12)
-
-/* Used by PRM_IRQENABLE_M3, PRM_IRQENABLE_MPU */
-#define AM33XX_DPLL_DDR_RECAL_EN_SHIFT			14
-#define AM33XX_DPLL_DDR_RECAL_EN_MASK			(1 << 14)
-
-/* Used by PRM_IRQSTATUS_M3, PRM_IRQSTATUS_MPU */
-#define AM33XX_DPLL_DDR_RECAL_ST_SHIFT			14
-#define AM33XX_DPLL_DDR_RECAL_ST_MASK			(1 << 14)
-
-/* Used by PRM_IRQENABLE_M3, PRM_IRQENABLE_MPU */
-#define AM33XX_DPLL_DISP_RECAL_EN_SHIFT			15
-#define AM33XX_DPLL_DISP_RECAL_EN_MASK			(1 << 15)
-
-/* Used by PRM_IRQSTATUS_M3, PRM_IRQSTATUS_MPU */
-#define AM33XX_DPLL_DISP_RECAL_ST_SHIFT			13
-#define AM33XX_DPLL_DISP_RECAL_ST_MASK			(1 << 13)
-
-/* Used by PRM_IRQENABLE_M3, PRM_IRQENABLE_MPU */
-#define AM33XX_DPLL_MPU_RECAL_EN_SHIFT			11
-#define AM33XX_DPLL_MPU_RECAL_EN_MASK			(1 << 11)
-
-/* Used by PRM_IRQSTATUS_M3, PRM_IRQSTATUS_MPU */
-#define AM33XX_DPLL_MPU_RECAL_ST_SHIFT			11
-#define AM33XX_DPLL_MPU_RECAL_ST_MASK			(1 << 11)
-
-/* Used by PRM_IRQENABLE_M3, PRM_IRQENABLE_MPU */
-#define AM33XX_DPLL_PER_RECAL_EN_SHIFT			13
-#define AM33XX_DPLL_PER_RECAL_EN_MASK			(1 << 13)
-
-/* Used by PRM_IRQSTATUS_M3, PRM_IRQSTATUS_MPU */
-#define AM33XX_DPLL_PER_RECAL_ST_SHIFT			15
-#define AM33XX_DPLL_PER_RECAL_ST_MASK			(1 << 15)
-
-/* Used by RM_WKUP_RSTST */
-#define AM33XX_EMULATION_M3_RST_SHIFT			6
-#define AM33XX_EMULATION_M3_RST_MASK			(1 << 6)
-
-/* Used by RM_MPU_RSTST */
-#define AM33XX_EMULATION_MPU_RST_SHIFT			5
-#define AM33XX_EMULATION_MPU_RST_MASK			(1 << 5)
-
-/* Used by PRM_LDO_SRAM_CORE_SETUP, PRM_LDO_SRAM_MPU_SETUP */
-#define AM33XX_ENFUNC1_EXPORT_SHIFT			3
-#define AM33XX_ENFUNC1_EXPORT_MASK			(1 << 3)
-
-/* Used by PRM_LDO_SRAM_CORE_SETUP, PRM_LDO_SRAM_MPU_SETUP */
-#define AM33XX_ENFUNC3_EXPORT_SHIFT			5
-#define AM33XX_ENFUNC3_EXPORT_MASK			(1 << 5)
-
-/* Used by PRM_LDO_SRAM_CORE_SETUP, PRM_LDO_SRAM_MPU_SETUP */
-#define AM33XX_ENFUNC4_SHIFT				6
-#define AM33XX_ENFUNC4_MASK				(1 << 6)
-
-/* Used by PRM_LDO_SRAM_CORE_SETUP, PRM_LDO_SRAM_MPU_SETUP */
-#define AM33XX_ENFUNC5_SHIFT				7
-#define AM33XX_ENFUNC5_MASK				(1 << 7)
-
-/* Used by PRM_RSTST */
-#define AM33XX_EXTERNAL_WARM_RST_SHIFT			5
-#define AM33XX_EXTERNAL_WARM_RST_MASK			(1 << 5)
-
-/* Used by PRM_IRQENABLE_M3, PRM_IRQENABLE_MPU */
-#define AM33XX_FORCEWKUP_EN_SHIFT			10
-#define AM33XX_FORCEWKUP_EN_MASK			(1 << 10)
-
-/* Used by PRM_IRQSTATUS_M3, PRM_IRQSTATUS_MPU */
-#define AM33XX_FORCEWKUP_ST_SHIFT			10
-#define AM33XX_FORCEWKUP_ST_MASK			(1 << 10)
-
-/* Used by PM_GFX_PWRSTCTRL */
-#define AM33XX_GFX_MEM_ONSTATE_SHIFT			17
 #define AM33XX_GFX_MEM_ONSTATE_MASK			(0x3 << 17)
-
-/* Used by PM_GFX_PWRSTCTRL */
-#define AM33XX_GFX_MEM_RETSTATE_SHIFT			6
 #define AM33XX_GFX_MEM_RETSTATE_MASK			(1 << 6)
-
-/* Used by PM_GFX_PWRSTST */
-#define AM33XX_GFX_MEM_STATEST_SHIFT			4
 #define AM33XX_GFX_MEM_STATEST_MASK			(0x3 << 4)
-
-/* Used by RM_GFX_RSTCTRL, RM_GFX_RSTST */
-#define AM33XX_GFX_RST_SHIFT				0
-#define AM33XX_GFX_RST_MASK				(1 << 0)
-
-/* Used by PRM_RSTST */
-#define AM33XX_GLOBAL_COLD_RST_SHIFT			0
-#define AM33XX_GLOBAL_COLD_RST_MASK			(1 << 0)
-
-/* Used by PRM_RSTST */
-#define AM33XX_GLOBAL_WARM_SW_RST_SHIFT			1
 #define AM33XX_GLOBAL_WARM_SW_RST_MASK			(1 << 1)
-
-/* Used by RM_WKUP_RSTST */
-#define AM33XX_ICECRUSHER_M3_RST_SHIFT			7
-#define AM33XX_ICECRUSHER_M3_RST_MASK			(1 << 7)
-
-/* Used by RM_MPU_RSTST */
-#define AM33XX_ICECRUSHER_MPU_RST_SHIFT			6
-#define AM33XX_ICECRUSHER_MPU_RST_MASK			(1 << 6)
-
-/* Used by PRM_RSTST */
-#define AM33XX_ICEPICK_RST_SHIFT			9
-#define AM33XX_ICEPICK_RST_MASK				(1 << 9)
-
-/* Used by RM_PER_RSTCTRL */
-#define AM33XX_PRUSS_LRST_SHIFT				1
-#define AM33XX_PRUSS_LRST_MASK				(1 << 1)
-
-/* Used by PM_PER_PWRSTCTRL */
-#define AM33XX_PRUSS_MEM_ONSTATE_SHIFT			5
+#define AM33XX_RST_GLOBAL_WARM_SW_MASK			(1 << 0)
 #define AM33XX_PRUSS_MEM_ONSTATE_MASK			(0x3 << 5)
-
-/* Used by PM_PER_PWRSTCTRL */
-#define AM33XX_PRUSS_MEM_RETSTATE_SHIFT			7
 #define AM33XX_PRUSS_MEM_RETSTATE_MASK			(1 << 7)
-
-/* Used by PM_PER_PWRSTST */
-#define AM33XX_PRUSS_MEM_STATEST_SHIFT			23
 #define AM33XX_PRUSS_MEM_STATEST_MASK			(0x3 << 23)
-
-/*
- * Used by PM_GFX_PWRSTST, PM_CEFUSE_PWRSTST, PM_PER_PWRSTST, PM_MPU_PWRSTST,
- * PM_WKUP_PWRSTST, PM_RTC_PWRSTST
- */
-#define AM33XX_INTRANSITION_SHIFT			20
-#define AM33XX_INTRANSITION_MASK			(1 << 20)
-
-/* Used by PM_CEFUSE_PWRSTST */
 #define AM33XX_LASTPOWERSTATEENTERED_SHIFT		24
 #define AM33XX_LASTPOWERSTATEENTERED_MASK		(0x3 << 24)
-
-/* Used by PM_GFX_PWRSTCTRL, PM_MPU_PWRSTCTRL, PM_RTC_PWRSTCTRL */
-#define AM33XX_LOGICRETSTATE_SHIFT			2
 #define AM33XX_LOGICRETSTATE_MASK			(1 << 2)
-
-/* Renamed from LOGICRETSTATE Used by PM_PER_PWRSTCTRL, PM_WKUP_PWRSTCTRL */
-#define AM33XX_LOGICRETSTATE_3_3_SHIFT			3
 #define AM33XX_LOGICRETSTATE_3_3_MASK			(1 << 3)
-
-/*
- * Used by PM_GFX_PWRSTST, PM_CEFUSE_PWRSTST, PM_PER_PWRSTST, PM_MPU_PWRSTST,
- * PM_WKUP_PWRSTST, PM_RTC_PWRSTST
- */
 #define AM33XX_LOGICSTATEST_SHIFT			2
 #define AM33XX_LOGICSTATEST_MASK			(1 << 2)
-
-/*
- * Used by PM_GFX_PWRSTCTRL, PM_CEFUSE_PWRSTCTRL, PM_PER_PWRSTCTRL,
- * PM_MPU_PWRSTCTRL, PM_WKUP_PWRSTCTRL, PM_RTC_PWRSTCTRL
- */
 #define AM33XX_LOWPOWERSTATECHANGE_SHIFT		4
 #define AM33XX_LOWPOWERSTATECHANGE_MASK			(1 << 4)
-
-/* Used by PM_MPU_PWRSTCTRL */
-#define AM33XX_MPU_L1_ONSTATE_SHIFT			18
 #define AM33XX_MPU_L1_ONSTATE_MASK			(0x3 << 18)
-
-/* Used by PM_MPU_PWRSTCTRL */
-#define AM33XX_MPU_L1_RETSTATE_SHIFT			22
 #define AM33XX_MPU_L1_RETSTATE_MASK			(1 << 22)
-
-/* Used by PM_MPU_PWRSTST */
-#define AM33XX_MPU_L1_STATEST_SHIFT			6
 #define AM33XX_MPU_L1_STATEST_MASK			(0x3 << 6)
-
-/* Used by PM_MPU_PWRSTCTRL */
-#define AM33XX_MPU_L2_ONSTATE_SHIFT			20
 #define AM33XX_MPU_L2_ONSTATE_MASK			(0x3 << 20)
-
-/* Used by PM_MPU_PWRSTCTRL */
-#define AM33XX_MPU_L2_RETSTATE_SHIFT			23
 #define AM33XX_MPU_L2_RETSTATE_MASK			(1 << 23)
-
-/* Used by PM_MPU_PWRSTST */
-#define AM33XX_MPU_L2_STATEST_SHIFT			8
 #define AM33XX_MPU_L2_STATEST_MASK			(0x3 << 8)
-
-/* Used by PM_MPU_PWRSTCTRL */
-#define AM33XX_MPU_RAM_ONSTATE_SHIFT			16
 #define AM33XX_MPU_RAM_ONSTATE_MASK			(0x3 << 16)
-
-/* Used by PM_MPU_PWRSTCTRL */
-#define AM33XX_MPU_RAM_RETSTATE_SHIFT			24
 #define AM33XX_MPU_RAM_RETSTATE_MASK			(1 << 24)
-
-/* Used by PM_MPU_PWRSTST */
-#define AM33XX_MPU_RAM_STATEST_SHIFT			4
 #define AM33XX_MPU_RAM_STATEST_MASK			(0x3 << 4)
-
-/* Used by PRM_RSTST */
-#define AM33XX_MPU_SECURITY_VIOL_RST_SHIFT		2
-#define AM33XX_MPU_SECURITY_VIOL_RST_MASK		(1 << 2)
-
-/* Used by PRM_SRAM_COUNT */
-#define AM33XX_PCHARGECNT_VALUE_SHIFT			0
-#define AM33XX_PCHARGECNT_VALUE_MASK			(0x3f << 0)
-
-/* Used by RM_PER_RSTCTRL */
-#define AM33XX_PCI_LRST_SHIFT				0
-#define AM33XX_PCI_LRST_MASK				(1 << 0)
-
-/* Renamed from PCI_LRST Used by RM_PER_RSTST */
-#define AM33XX_PCI_LRST_5_5_SHIFT			5
-#define AM33XX_PCI_LRST_5_5_MASK			(1 << 5)
-
-/* Used by PM_PER_PWRSTCTRL */
-#define AM33XX_PER_MEM_ONSTATE_SHIFT			25
 #define AM33XX_PER_MEM_ONSTATE_MASK			(0x3 << 25)
-
-/* Used by PM_PER_PWRSTCTRL */
-#define AM33XX_PER_MEM_RETSTATE_SHIFT			29
 #define AM33XX_PER_MEM_RETSTATE_MASK			(1 << 29)
-
-/* Used by PM_PER_PWRSTST */
-#define AM33XX_PER_MEM_STATEST_SHIFT			17
 #define AM33XX_PER_MEM_STATEST_MASK			(0x3 << 17)
-
-/*
- * Used by PM_GFX_PWRSTCTRL, PM_CEFUSE_PWRSTCTRL, PM_PER_PWRSTCTRL,
- * PM_MPU_PWRSTCTRL
- */
-#define AM33XX_POWERSTATE_SHIFT				0
-#define AM33XX_POWERSTATE_MASK				(0x3 << 0)
-
-/* Used by PM_GFX_PWRSTST, PM_CEFUSE_PWRSTST, PM_PER_PWRSTST, PM_MPU_PWRSTST */
-#define AM33XX_POWERSTATEST_SHIFT			0
-#define AM33XX_POWERSTATEST_MASK			(0x3 << 0)
-
-/* Used by PM_PER_PWRSTCTRL */
-#define AM33XX_RAM_MEM_ONSTATE_SHIFT			30
 #define AM33XX_RAM_MEM_ONSTATE_MASK			(0x3 << 30)
-
-/* Used by PM_PER_PWRSTCTRL */
-#define AM33XX_RAM_MEM_RETSTATE_SHIFT			27
 #define AM33XX_RAM_MEM_RETSTATE_MASK			(1 << 27)
-
-/* Used by PM_PER_PWRSTST */
-#define AM33XX_RAM_MEM_STATEST_SHIFT			21
 #define AM33XX_RAM_MEM_STATEST_MASK			(0x3 << 21)
-
-/* Used by PRM_LDO_SRAM_CORE_CTRL, PRM_LDO_SRAM_MPU_CTRL */
-#define AM33XX_RETMODE_ENABLE_SHIFT			0
-#define AM33XX_RETMODE_ENABLE_MASK			(1 << 0)
-
-/* Used by REVISION_PRM */
-#define AM33XX_REV_SHIFT				0
-#define AM33XX_REV_MASK					(0xff << 0)
-
-/* Used by PRM_RSTTIME */
-#define AM33XX_RSTTIME1_SHIFT				0
-#define AM33XX_RSTTIME1_MASK				(0xff << 0)
-
-/* Used by PRM_RSTTIME */
-#define AM33XX_RSTTIME2_SHIFT				8
-#define AM33XX_RSTTIME2_MASK				(0x1f << 8)
-
-/* Used by PRM_RSTCTRL */
-#define AM33XX_RST_GLOBAL_COLD_SW_SHIFT			1
-#define AM33XX_RST_GLOBAL_COLD_SW_MASK			(1 << 1)
-
-/* Used by PRM_RSTCTRL */
-#define AM33XX_RST_GLOBAL_WARM_SW_SHIFT			0
-#define AM33XX_RST_GLOBAL_WARM_SW_MASK			(1 << 0)
-
-/* Used by PRM_SRAM_COUNT */
-#define AM33XX_SLPCNT_VALUE_SHIFT			16
-#define AM33XX_SLPCNT_VALUE_MASK			(0xff << 16)
-
-/* Used by PRM_LDO_SRAM_CORE_CTRL, PRM_LDO_SRAM_MPU_CTRL */
-#define AM33XX_SRAMLDO_STATUS_SHIFT			8
-#define AM33XX_SRAMLDO_STATUS_MASK			(1 << 8)
-
-/* Used by PRM_LDO_SRAM_CORE_CTRL, PRM_LDO_SRAM_MPU_CTRL */
-#define AM33XX_SRAM_IN_TRANSITION_SHIFT			9
-#define AM33XX_SRAM_IN_TRANSITION_MASK			(1 << 9)
-
-/* Used by PRM_SRAM_COUNT */
-#define AM33XX_STARTUP_COUNT_SHIFT			24
-#define AM33XX_STARTUP_COUNT_MASK			(0xff << 24)
-
-/* Used by PRM_IRQENABLE_M3, PRM_IRQENABLE_MPU */
-#define AM33XX_TRANSITION_EN_SHIFT			8
-#define AM33XX_TRANSITION_EN_MASK			(1 << 8)
-
-/* Used by PRM_IRQSTATUS_M3, PRM_IRQSTATUS_MPU */
-#define AM33XX_TRANSITION_ST_SHIFT			8
-#define AM33XX_TRANSITION_ST_MASK			(1 << 8)
-
-/* Used by PRM_SRAM_COUNT */
-#define AM33XX_VSETUPCNT_VALUE_SHIFT			8
-#define AM33XX_VSETUPCNT_VALUE_MASK			(0xff << 8)
-
-/* Used by PRM_RSTST */
-#define AM33XX_WDT0_RST_SHIFT				3
-#define AM33XX_WDT0_RST_MASK				(1 << 3)
-
-/* Used by PRM_RSTST */
-#define AM33XX_WDT1_RST_SHIFT				4
-#define AM33XX_WDT1_RST_MASK				(1 << 4)
-
-/* Used by RM_WKUP_RSTCTRL */
-#define AM33XX_WKUP_M3_LRST_SHIFT			3
-#define AM33XX_WKUP_M3_LRST_MASK			(1 << 3)
-
-/* Renamed from WKUP_M3_LRST Used by RM_WKUP_RSTST */
-#define AM33XX_WKUP_M3_LRST_5_5_SHIFT			5
-#define AM33XX_WKUP_M3_LRST_5_5_MASK			(1 << 5)
-
 #endif
diff --git a/arch/arm/mach-omap2/prm-regbits-34xx.h b/arch/arm/mach-omap2/prm-regbits-34xx.h
index b0a2142eeb91..cebad565ed37 100644
--- a/arch/arm/mach-omap2/prm-regbits-34xx.h
+++ b/arch/arm/mach-omap2/prm-regbits-34xx.h
@@ -16,115 +16,25 @@
 
 #include "prm3xxx.h"
 
-/* Shared register bits */
-
-/* PRM_VC_CMD_VAL_0, PRM_VC_CMD_VAL_1 shared bits */
-#define OMAP3430_ON_SHIFT				24
-#define OMAP3430_ON_MASK				(0xff << 24)
-#define OMAP3430_ONLP_SHIFT				16
-#define OMAP3430_ONLP_MASK				(0xff << 16)
-#define OMAP3430_RET_SHIFT				8
-#define OMAP3430_RET_MASK				(0xff << 8)
-#define OMAP3430_OFF_SHIFT				0
-#define OMAP3430_OFF_MASK				(0xff << 0)
-
-/* PRM_VP1_CONFIG, PRM_VP2_CONFIG shared bits */
-#define OMAP3430_ERROROFFSET_SHIFT			24
 #define OMAP3430_ERROROFFSET_MASK			(0xff << 24)
-#define OMAP3430_ERRORGAIN_SHIFT			16
 #define OMAP3430_ERRORGAIN_MASK				(0xff << 16)
-#define OMAP3430_INITVOLTAGE_SHIFT			8
 #define OMAP3430_INITVOLTAGE_MASK			(0xff << 8)
 #define OMAP3430_TIMEOUTEN_MASK				(1 << 3)
 #define OMAP3430_INITVDD_MASK				(1 << 2)
 #define OMAP3430_FORCEUPDATE_MASK			(1 << 1)
 #define OMAP3430_VPENABLE_MASK				(1 << 0)
-
-/* PRM_VP1_VSTEPMIN, PRM_VP2_VSTEPMIN shared bits */
 #define OMAP3430_SMPSWAITTIMEMIN_SHIFT			8
-#define OMAP3430_SMPSWAITTIMEMIN_MASK			(0xffff << 8)
 #define OMAP3430_VSTEPMIN_SHIFT				0
-#define OMAP3430_VSTEPMIN_MASK				(0xff << 0)
-
-/* PRM_VP1_VSTEPMAX, PRM_VP2_VSTEPMAX shared bits */
 #define OMAP3430_SMPSWAITTIMEMAX_SHIFT			8
-#define OMAP3430_SMPSWAITTIMEMAX_MASK			(0xffff << 8)
 #define OMAP3430_VSTEPMAX_SHIFT				0
-#define OMAP3430_VSTEPMAX_MASK				(0xff << 0)
-
-/* PRM_VP1_VLIMITTO, PRM_VP2_VLIMITTO shared bits */
 #define OMAP3430_VDDMAX_SHIFT				24
-#define OMAP3430_VDDMAX_MASK				(0xff << 24)
 #define OMAP3430_VDDMIN_SHIFT				16
-#define OMAP3430_VDDMIN_MASK				(0xff << 16)
 #define OMAP3430_TIMEOUT_SHIFT				0
-#define OMAP3430_TIMEOUT_MASK				(0xffff << 0)
-
-/* PRM_VP1_VOLTAGE, PRM_VP2_VOLTAGE shared bits */
-#define OMAP3430_VPVOLTAGE_SHIFT			0
 #define OMAP3430_VPVOLTAGE_MASK				(0xff << 0)
-
-/* PRM_VP1_STATUS, PRM_VP2_STATUS shared bits */
-#define OMAP3430_VPINIDLE_MASK				(1 << 0)
-
-/* PM_WKDEP_IVA2, PM_WKDEP_MPU shared bits */
 #define OMAP3430_EN_PER_SHIFT				7
-#define OMAP3430_EN_PER_MASK				(1 << 7)
-
-/* PM_PWSTCTRL_IVA2, PM_PWSTCTRL_MPU, PM_PWSTCTRL_CORE shared bits */
-#define OMAP3430_MEMORYCHANGE_MASK			(1 << 3)
-
-/* PM_PWSTST_IVA2, PM_PWSTST_CORE shared bits */
 #define OMAP3430_LOGICSTATEST_MASK			(1 << 2)
-
-/* PM_PREPWSTST_IVA2, PM_PREPWSTST_CORE shared bits */
 #define OMAP3430_LASTLOGICSTATEENTERED_MASK		(1 << 2)
-
-/*
- * PM_PREPWSTST_IVA2, PM_PREPWSTST_MPU, PM_PREPWSTST_CORE,
- * PM_PREPWSTST_GFX, PM_PREPWSTST_DSS, PM_PREPWSTST_CAM,
- * PM_PREPWSTST_PER, PM_PREPWSTST_NEON shared bits
- */
-#define OMAP3430_LASTPOWERSTATEENTERED_SHIFT		0
 #define OMAP3430_LASTPOWERSTATEENTERED_MASK		(0x3 << 0)
-
-/* PRM_IRQSTATUS_IVA2, PRM_IRQSTATUS_MPU shared bits */
-#define OMAP3430_WKUP_ST_MASK				(1 << 0)
-
-/* PRM_IRQENABLE_IVA2, PRM_IRQENABLE_MPU shared bits */
-#define OMAP3430_WKUP_EN_MASK				(1 << 0)
-
-/* PM_MPUGRPSEL1_CORE, PM_IVA2GRPSEL1_CORE shared bits */
-#define OMAP3430_GRPSEL_MMC2_MASK			(1 << 25)
-#define OMAP3430_GRPSEL_MMC1_MASK			(1 << 24)
-#define OMAP3430_GRPSEL_MCSPI4_MASK			(1 << 21)
-#define OMAP3430_GRPSEL_MCSPI3_MASK			(1 << 20)
-#define OMAP3430_GRPSEL_MCSPI2_MASK			(1 << 19)
-#define OMAP3430_GRPSEL_MCSPI1_MASK			(1 << 18)
-#define OMAP3430_GRPSEL_I2C3_SHIFT			17
-#define OMAP3430_GRPSEL_I2C3_MASK			(1 << 17)
-#define OMAP3430_GRPSEL_I2C2_SHIFT			16
-#define OMAP3430_GRPSEL_I2C2_MASK			(1 << 16)
-#define OMAP3430_GRPSEL_I2C1_SHIFT			15
-#define OMAP3430_GRPSEL_I2C1_MASK			(1 << 15)
-#define OMAP3430_GRPSEL_UART2_MASK			(1 << 14)
-#define OMAP3430_GRPSEL_UART1_MASK			(1 << 13)
-#define OMAP3430_GRPSEL_GPT11_MASK			(1 << 12)
-#define OMAP3430_GRPSEL_GPT10_MASK			(1 << 11)
-#define OMAP3430_GRPSEL_MCBSP5_MASK			(1 << 10)
-#define OMAP3430_GRPSEL_MCBSP1_MASK			(1 << 9)
-#define OMAP3430_GRPSEL_HSOTGUSB_MASK			(1 << 4)
-#define OMAP3430_GRPSEL_D2D_MASK			(1 << 3)
-
-/*
- * PM_PWSTCTRL_GFX, PM_PWSTCTRL_DSS, PM_PWSTCTRL_CAM,
- * PM_PWSTCTRL_PER shared bits
- */
-#define OMAP3430_MEMONSTATE_SHIFT			16
-#define OMAP3430_MEMONSTATE_MASK			(0x3 << 16)
-#define OMAP3430_MEMRETSTATE_MASK			(1 << 8)
-
-/* PM_MPUGRPSEL_PER, PM_IVA2GRPSEL_PER shared bits */
 #define OMAP3630_GRPSEL_UART4_MASK			(1 << 18)
 #define OMAP3430_GRPSEL_GPIO6_MASK			(1 << 17)
 #define OMAP3430_GRPSEL_GPIO5_MASK			(1 << 16)
@@ -132,480 +42,89 @@
 #define OMAP3430_GRPSEL_GPIO3_MASK			(1 << 14)
 #define OMAP3430_GRPSEL_GPIO2_MASK			(1 << 13)
 #define OMAP3430_GRPSEL_UART3_MASK			(1 << 11)
-#define OMAP3430_GRPSEL_GPT9_MASK			(1 << 10)
-#define OMAP3430_GRPSEL_GPT8_MASK			(1 << 9)
-#define OMAP3430_GRPSEL_GPT7_MASK			(1 << 8)
-#define OMAP3430_GRPSEL_GPT6_MASK			(1 << 7)
-#define OMAP3430_GRPSEL_GPT5_MASK			(1 << 6)
-#define OMAP3430_GRPSEL_GPT4_MASK			(1 << 5)
-#define OMAP3430_GRPSEL_GPT3_MASK			(1 << 4)
-#define OMAP3430_GRPSEL_GPT2_MASK			(1 << 3)
 #define OMAP3430_GRPSEL_MCBSP4_MASK			(1 << 2)
 #define OMAP3430_GRPSEL_MCBSP3_MASK			(1 << 1)
 #define OMAP3430_GRPSEL_MCBSP2_MASK			(1 << 0)
-
-/* PM_MPUGRPSEL_WKUP, PM_IVA2GRPSEL_WKUP shared bits */
-#define OMAP3430_GRPSEL_IO_MASK				(1 << 8)
-#define OMAP3430_GRPSEL_SR2_MASK			(1 << 7)
-#define OMAP3430_GRPSEL_SR1_MASK			(1 << 6)
 #define OMAP3430_GRPSEL_GPIO1_MASK			(1 << 3)
 #define OMAP3430_GRPSEL_GPT12_MASK			(1 << 1)
 #define OMAP3430_GRPSEL_GPT1_MASK			(1 << 0)
-
-/* Bits specific to each register */
-
-/* RM_RSTCTRL_IVA2 */
 #define OMAP3430_RST3_IVA2_MASK				(1 << 2)
 #define OMAP3430_RST2_IVA2_MASK				(1 << 1)
 #define OMAP3430_RST1_IVA2_MASK				(1 << 0)
-
-/* RM_RSTST_IVA2 specific bits */
-#define OMAP3430_EMULATION_VSEQ_RST_MASK		(1 << 13)
-#define OMAP3430_EMULATION_VHWA_RST_MASK		(1 << 12)
-#define OMAP3430_EMULATION_IVA2_RST_MASK		(1 << 11)
-#define OMAP3430_IVA2_SW_RST3_MASK			(1 << 10)
-#define OMAP3430_IVA2_SW_RST2_MASK			(1 << 9)
-#define OMAP3430_IVA2_SW_RST1_MASK			(1 << 8)
-
-/* PM_WKDEP_IVA2 specific bits */
-
-/* PM_PWSTCTRL_IVA2 specific bits */
-#define OMAP3430_L2FLATMEMONSTATE_SHIFT			22
 #define OMAP3430_L2FLATMEMONSTATE_MASK			(0x3 << 22)
-#define OMAP3430_SHAREDL2CACHEFLATONSTATE_SHIFT		20
 #define OMAP3430_SHAREDL2CACHEFLATONSTATE_MASK		(0x3 << 20)
-#define OMAP3430_L1FLATMEMONSTATE_SHIFT			18
 #define OMAP3430_L1FLATMEMONSTATE_MASK			(0x3 << 18)
-#define OMAP3430_SHAREDL1CACHEFLATONSTATE_SHIFT		16
 #define OMAP3430_SHAREDL1CACHEFLATONSTATE_MASK		(0x3 << 16)
 #define OMAP3430_L2FLATMEMRETSTATE_MASK			(1 << 11)
 #define OMAP3430_SHAREDL2CACHEFLATRETSTATE_MASK		(1 << 10)
 #define OMAP3430_L1FLATMEMRETSTATE_MASK			(1 << 9)
 #define OMAP3430_SHAREDL1CACHEFLATRETSTATE_MASK		(1 << 8)
-
-/* PM_PWSTST_IVA2 specific bits */
-#define OMAP3430_L2FLATMEMSTATEST_SHIFT			10
 #define OMAP3430_L2FLATMEMSTATEST_MASK			(0x3 << 10)
-#define OMAP3430_SHAREDL2CACHEFLATSTATEST_SHIFT		8
 #define OMAP3430_SHAREDL2CACHEFLATSTATEST_MASK		(0x3 << 8)
-#define OMAP3430_L1FLATMEMSTATEST_SHIFT			6
 #define OMAP3430_L1FLATMEMSTATEST_MASK			(0x3 << 6)
-#define OMAP3430_SHAREDL1CACHEFLATSTATEST_SHIFT		4
 #define OMAP3430_SHAREDL1CACHEFLATSTATEST_MASK		(0x3 << 4)
-
-/* PM_PREPWSTST_IVA2 specific bits */
-#define OMAP3430_LASTL2FLATMEMSTATEENTERED_SHIFT		10
 #define OMAP3430_LASTL2FLATMEMSTATEENTERED_MASK			(0x3 << 10)
-#define OMAP3430_LASTSHAREDL2CACHEFLATSTATEENTERED_SHIFT	8
 #define OMAP3430_LASTSHAREDL2CACHEFLATSTATEENTERED_MASK		(0x3 << 8)
-#define OMAP3430_LASTL1FLATMEMSTATEENTERED_SHIFT		6
-#define OMAP3430_LASTL1FLATMEMSTATEENTERED_MASK			(0x3 << 6)
-#define OMAP3430_LASTSHAREDL1CACHEFLATSTATEENTERED_SHIFT	4
-#define OMAP3430_LASTSHAREDL1CACHEFLATSTATEENTERED_MASK		(0x3 << 4)
-
-/* PRM_IRQSTATUS_IVA2 specific bits */
-#define OMAP3430_PRM_IRQSTATUS_IVA2_IVA2_DPLL_ST_MASK	(1 << 2)
-#define OMAP3430_FORCEWKUP_ST_MASK			(1 << 1)
-
-/* PRM_IRQENABLE_IVA2 specific bits */
-#define OMAP3430_PRM_IRQENABLE_IVA2_IVA2_DPLL_RECAL_EN_MASK	(1 << 2)
-#define OMAP3430_FORCEWKUP_EN_MASK				(1 << 1)
-
-/* PRM_REVISION specific bits */
-
-/* PRM_SYSCONFIG specific bits */
-
-/* PRM_IRQSTATUS_MPU specific bits */
 #define OMAP3430ES2_SND_PERIPH_DPLL_ST_SHIFT		25
-#define OMAP3430ES2_SND_PERIPH_DPLL_ST_MASK		(1 << 25)
-#define OMAP3430_VC_TIMEOUTERR_ST_MASK			(1 << 24)
-#define OMAP3430_VC_RAERR_ST_MASK			(1 << 23)
-#define OMAP3430_VC_SAERR_ST_MASK			(1 << 22)
 #define OMAP3430_VP2_TRANXDONE_ST_MASK			(1 << 21)
-#define OMAP3430_VP2_EQVALUE_ST_MASK			(1 << 20)
-#define OMAP3430_VP2_NOSMPSACK_ST_MASK			(1 << 19)
-#define OMAP3430_VP2_MAXVDD_ST_MASK			(1 << 18)
-#define OMAP3430_VP2_MINVDD_ST_MASK			(1 << 17)
-#define OMAP3430_VP2_OPPCHANGEDONE_ST_MASK		(1 << 16)
 #define OMAP3430_VP1_TRANXDONE_ST_MASK			(1 << 15)
-#define OMAP3430_VP1_EQVALUE_ST_MASK			(1 << 14)
-#define OMAP3430_VP1_NOSMPSACK_ST_MASK			(1 << 13)
-#define OMAP3430_VP1_MAXVDD_ST_MASK			(1 << 12)
-#define OMAP3430_VP1_MINVDD_ST_MASK			(1 << 11)
-#define OMAP3430_VP1_OPPCHANGEDONE_ST_MASK		(1 << 10)
-#define OMAP3430_IO_ST_MASK				(1 << 9)
-#define OMAP3430_PRM_IRQSTATUS_MPU_IVA2_DPLL_ST_MASK	(1 << 8)
 #define OMAP3430_PRM_IRQSTATUS_MPU_IVA2_DPLL_ST_SHIFT	8
-#define OMAP3430_MPU_DPLL_ST_MASK			(1 << 7)
 #define OMAP3430_MPU_DPLL_ST_SHIFT			7
-#define OMAP3430_PERIPH_DPLL_ST_MASK			(1 << 6)
 #define OMAP3430_PERIPH_DPLL_ST_SHIFT			6
-#define OMAP3430_CORE_DPLL_ST_MASK			(1 << 5)
 #define OMAP3430_CORE_DPLL_ST_SHIFT			5
-#define OMAP3430_TRANSITION_ST_MASK			(1 << 4)
-#define OMAP3430_EVGENOFF_ST_MASK			(1 << 3)
-#define OMAP3430_EVGENON_ST_MASK			(1 << 2)
-#define OMAP3430_FS_USB_WKUP_ST_MASK			(1 << 1)
-
-/* PRM_IRQENABLE_MPU specific bits */
 #define OMAP3430ES2_SND_PERIPH_DPLL_RECAL_EN_SHIFT		25
-#define OMAP3430ES2_SND_PERIPH_DPLL_RECAL_EN_MASK		(1 << 25)
-#define OMAP3430_VC_TIMEOUTERR_EN_MASK				(1 << 24)
-#define OMAP3430_VC_RAERR_EN_MASK				(1 << 23)
-#define OMAP3430_VC_SAERR_EN_MASK				(1 << 22)
-#define OMAP3430_VP2_TRANXDONE_EN_MASK				(1 << 21)
-#define OMAP3430_VP2_EQVALUE_EN_MASK				(1 << 20)
-#define OMAP3430_VP2_NOSMPSACK_EN_MASK				(1 << 19)
-#define OMAP3430_VP2_MAXVDD_EN_MASK				(1 << 18)
-#define OMAP3430_VP2_MINVDD_EN_MASK				(1 << 17)
-#define OMAP3430_VP2_OPPCHANGEDONE_EN_MASK			(1 << 16)
-#define OMAP3430_VP1_TRANXDONE_EN_MASK				(1 << 15)
-#define OMAP3430_VP1_EQVALUE_EN_MASK				(1 << 14)
-#define OMAP3430_VP1_NOSMPSACK_EN_MASK				(1 << 13)
-#define OMAP3430_VP1_MAXVDD_EN_MASK				(1 << 12)
-#define OMAP3430_VP1_MINVDD_EN_MASK				(1 << 11)
-#define OMAP3430_VP1_OPPCHANGEDONE_EN_MASK			(1 << 10)
-#define OMAP3430_IO_EN_MASK					(1 << 9)
-#define OMAP3430_PRM_IRQENABLE_MPU_IVA2_DPLL_RECAL_EN_MASK	(1 << 8)
 #define OMAP3430_PRM_IRQENABLE_MPU_IVA2_DPLL_RECAL_EN_SHIFT	8
-#define OMAP3430_MPU_DPLL_RECAL_EN_MASK				(1 << 7)
 #define OMAP3430_MPU_DPLL_RECAL_EN_SHIFT			7
-#define OMAP3430_PERIPH_DPLL_RECAL_EN_MASK			(1 << 6)
 #define OMAP3430_PERIPH_DPLL_RECAL_EN_SHIFT			6
-#define OMAP3430_CORE_DPLL_RECAL_EN_MASK			(1 << 5)
 #define OMAP3430_CORE_DPLL_RECAL_EN_SHIFT			5
-#define OMAP3430_TRANSITION_EN_MASK				(1 << 4)
-#define OMAP3430_EVGENOFF_EN_MASK				(1 << 3)
-#define OMAP3430_EVGENON_EN_MASK				(1 << 2)
-#define OMAP3430_FS_USB_WKUP_EN_MASK				(1 << 1)
-
-/* RM_RSTST_MPU specific bits */
-#define OMAP3430_EMULATION_MPU_RST_MASK			(1 << 11)
-
-/* PM_WKDEP_MPU specific bits */
 #define OMAP3430_PM_WKDEP_MPU_EN_DSS_SHIFT		5
-#define OMAP3430_PM_WKDEP_MPU_EN_DSS_MASK		(1 << 5)
 #define OMAP3430_PM_WKDEP_MPU_EN_IVA2_SHIFT		2
-#define OMAP3430_PM_WKDEP_MPU_EN_IVA2_MASK		(1 << 2)
-
-/* PM_EVGENCTRL_MPU */
-#define OMAP3430_OFFLOADMODE_SHIFT			3
-#define OMAP3430_OFFLOADMODE_MASK			(0x3 << 3)
-#define OMAP3430_ONLOADMODE_SHIFT			1
-#define OMAP3430_ONLOADMODE_MASK			(0x3 << 1)
-#define OMAP3430_ENABLE_MASK				(1 << 0)
-
-/* PM_EVGENONTIM_MPU */
-#define OMAP3430_ONTIMEVAL_SHIFT			0
-#define OMAP3430_ONTIMEVAL_MASK				(0xffffffff << 0)
-
-/* PM_EVGENOFFTIM_MPU */
-#define OMAP3430_OFFTIMEVAL_SHIFT			0
-#define OMAP3430_OFFTIMEVAL_MASK			(0xffffffff << 0)
-
-/* PM_PWSTCTRL_MPU specific bits */
-#define OMAP3430_L2CACHEONSTATE_SHIFT			16
-#define OMAP3430_L2CACHEONSTATE_MASK			(0x3 << 16)
-#define OMAP3430_L2CACHERETSTATE_MASK			(1 << 8)
-#define OMAP3430_LOGICL1CACHERETSTATE_MASK		(1 << 2)
-
-/* PM_PWSTST_MPU specific bits */
-#define OMAP3430_L2CACHESTATEST_SHIFT			6
-#define OMAP3430_L2CACHESTATEST_MASK			(0x3 << 6)
-#define OMAP3430_LOGICL1CACHESTATEST_MASK		(1 << 2)
-
-/* PM_PREPWSTST_MPU specific bits */
-#define OMAP3430_LASTL2CACHESTATEENTERED_SHIFT		6
-#define OMAP3430_LASTL2CACHESTATEENTERED_MASK		(0x3 << 6)
-#define OMAP3430_LASTLOGICL1CACHESTATEENTERED_MASK	(1 << 2)
-
-/* RM_RSTCTRL_CORE */
 #define OMAP3430_RM_RSTCTRL_CORE_MODEM_SW_RSTPWRON_MASK		(1 << 1)
 #define OMAP3430_RM_RSTCTRL_CORE_MODEM_SW_RST_MASK		(1 << 0)
-
-/* RM_RSTST_CORE specific bits */
-#define OMAP3430_MODEM_SECURITY_VIOL_RST_MASK		(1 << 10)
-#define OMAP3430_RM_RSTST_CORE_MODEM_SW_RSTPWRON_MASK	(1 << 9)
-#define OMAP3430_RM_RSTST_CORE_MODEM_SW_RST_MASK	(1 << 8)
-
-/* PM_WKEN1_CORE specific bits */
-
-/* PM_MPUGRPSEL1_CORE specific bits */
-#define OMAP3430_GRPSEL_FSHOSTUSB_MASK			(1 << 5)
-
-/* PM_IVA2GRPSEL1_CORE specific bits */
-
-/* PM_WKST1_CORE specific bits */
-
-/* PM_PWSTCTRL_CORE specific bits */
-#define OMAP3430_MEM2ONSTATE_SHIFT			18
-#define OMAP3430_MEM2ONSTATE_MASK			(0x3 << 18)
-#define OMAP3430_MEM1ONSTATE_SHIFT			16
-#define OMAP3430_MEM1ONSTATE_MASK			(0x3 << 16)
-#define OMAP3430_MEM2RETSTATE_MASK			(1 << 9)
-#define OMAP3430_MEM1RETSTATE_MASK			(1 << 8)
-
-/* PM_PWSTST_CORE specific bits */
-#define OMAP3430_MEM2STATEST_SHIFT			6
-#define OMAP3430_MEM2STATEST_MASK			(0x3 << 6)
-#define OMAP3430_MEM1STATEST_SHIFT			4
-#define OMAP3430_MEM1STATEST_MASK			(0x3 << 4)
-
-/* PM_PREPWSTST_CORE specific bits */
-#define OMAP3430_LASTMEM2STATEENTERED_SHIFT		6
 #define OMAP3430_LASTMEM2STATEENTERED_MASK		(0x3 << 6)
-#define OMAP3430_LASTMEM1STATEENTERED_SHIFT		4
 #define OMAP3430_LASTMEM1STATEENTERED_MASK		(0x3 << 4)
-
-/* RM_RSTST_GFX specific bits */
-
-/* PM_WKDEP_GFX specific bits */
-#define OMAP3430_PM_WKDEP_GFX_EN_IVA2_MASK		(1 << 2)
-
-/* PM_PWSTCTRL_GFX specific bits */
-
-/* PM_PWSTST_GFX specific bits */
-
-/* PM_PREPWSTST_GFX specific bits */
-
-/* PM_WKEN_WKUP specific bits */
 #define OMAP3430_EN_IO_CHAIN_MASK			(1 << 16)
 #define OMAP3430_EN_IO_MASK				(1 << 8)
 #define OMAP3430_EN_GPIO1_MASK				(1 << 3)
-
-/* PM_MPUGRPSEL_WKUP specific bits */
-
-/* PM_IVA2GRPSEL_WKUP specific bits */
-
-/* PM_WKST_WKUP specific bits */
 #define OMAP3430_ST_IO_CHAIN_MASK			(1 << 16)
 #define OMAP3430_ST_IO_MASK				(1 << 8)
-
-/* PRM_CLKSEL */
 #define OMAP3430_SYS_CLKIN_SEL_SHIFT			0
-#define OMAP3430_SYS_CLKIN_SEL_MASK			(0x7 << 0)
 #define OMAP3430_SYS_CLKIN_SEL_WIDTH			3
-
-/* PRM_CLKOUT_CTRL */
-#define OMAP3430_CLKOUT_EN_MASK				(1 << 7)
 #define OMAP3430_CLKOUT_EN_SHIFT			7
-
-/* RM_RSTST_DSS specific bits */
-
-/* PM_WKEN_DSS */
 #define OMAP3430_PM_WKEN_DSS_EN_DSS_MASK		(1 << 0)
-
-/* PM_WKDEP_DSS specific bits */
-#define OMAP3430_PM_WKDEP_DSS_EN_IVA2_MASK		(1 << 2)
-
-/* PM_PWSTCTRL_DSS specific bits */
-
-/* PM_PWSTST_DSS specific bits */
-
-/* PM_PREPWSTST_DSS specific bits */
-
-/* RM_RSTST_CAM specific bits */
-
-/* PM_WKDEP_CAM specific bits */
-#define OMAP3430_PM_WKDEP_CAM_EN_IVA2_MASK		(1 << 2)
-
-/* PM_PWSTCTRL_CAM specific bits */
-
-/* PM_PWSTST_CAM specific bits */
-
-/* PM_PREPWSTST_CAM specific bits */
-
-/* PM_PWSTCTRL_USBHOST specific bits */
 #define OMAP3430ES2_SAVEANDRESTORE_SHIFT		4
-
-/* RM_RSTST_PER specific bits */
-
-/* PM_WKEN_PER specific bits */
-
-/* PM_MPUGRPSEL_PER specific bits */
-
-/* PM_IVA2GRPSEL_PER specific bits */
-
-/* PM_WKST_PER specific bits */
-
-/* PM_WKDEP_PER specific bits */
-#define OMAP3430_PM_WKDEP_PER_EN_IVA2_MASK		(1 << 2)
-
-/* PM_PWSTCTRL_PER specific bits */
-
-/* PM_PWSTST_PER specific bits */
-
-/* PM_PREPWSTST_PER specific bits */
-
-/* RM_RSTST_EMU specific bits */
-
-/* PM_PWSTST_EMU specific bits */
-
-/* PRM_VC_SMPS_SA */
 #define OMAP3430_PRM_VC_SMPS_SA_SA1_SHIFT		16
 #define OMAP3430_PRM_VC_SMPS_SA_SA1_MASK		(0x7f << 16)
 #define OMAP3430_PRM_VC_SMPS_SA_SA0_SHIFT		0
 #define OMAP3430_PRM_VC_SMPS_SA_SA0_MASK		(0x7f << 0)
-
-/* PRM_VC_SMPS_VOL_RA */
-#define OMAP3430_VOLRA1_SHIFT				16
 #define OMAP3430_VOLRA1_MASK				(0xff << 16)
-#define OMAP3430_VOLRA0_SHIFT				0
 #define OMAP3430_VOLRA0_MASK				(0xff << 0)
-
-/* PRM_VC_SMPS_CMD_RA */
-#define OMAP3430_CMDRA1_SHIFT				16
 #define OMAP3430_CMDRA1_MASK				(0xff << 16)
-#define OMAP3430_CMDRA0_SHIFT				0
 #define OMAP3430_CMDRA0_MASK				(0xff << 0)
-
-/* PRM_VC_CMD_VAL_0 specific bits */
 #define OMAP3430_VC_CMD_ON_SHIFT			24
 #define OMAP3430_VC_CMD_ON_MASK				(0xFF << 24)
 #define OMAP3430_VC_CMD_ONLP_SHIFT			16
-#define OMAP3430_VC_CMD_ONLP_MASK			(0xFF << 16)
 #define OMAP3430_VC_CMD_RET_SHIFT			8
-#define OMAP3430_VC_CMD_RET_MASK			(0xFF << 8)
 #define OMAP3430_VC_CMD_OFF_SHIFT			0
-#define OMAP3430_VC_CMD_OFF_MASK			(0xFF << 0)
-
-/* PRM_VC_CMD_VAL_1 specific bits */
-
-/* PRM_VC_CH_CONF */
-#define OMAP3430_CMD1_MASK				(1 << 20)
-#define OMAP3430_RACEN1_MASK				(1 << 19)
-#define OMAP3430_RAC1_MASK				(1 << 18)
-#define OMAP3430_RAV1_MASK				(1 << 17)
-#define OMAP3430_PRM_VC_CH_CONF_SA1_MASK		(1 << 16)
-#define OMAP3430_CMD0_MASK				(1 << 4)
-#define OMAP3430_RACEN0_MASK				(1 << 3)
-#define OMAP3430_RAC0_MASK				(1 << 2)
-#define OMAP3430_RAV0_MASK				(1 << 1)
-#define OMAP3430_PRM_VC_CH_CONF_SA0_MASK		(1 << 0)
-
-/* PRM_VC_I2C_CFG */
-#define OMAP3430_HSMASTER_MASK				(1 << 5)
-#define OMAP3430_SREN_MASK				(1 << 4)
 #define OMAP3430_HSEN_MASK				(1 << 3)
-#define OMAP3430_MCODE_SHIFT				0
 #define OMAP3430_MCODE_MASK				(0x7 << 0)
-
-/* PRM_VC_BYPASS_VAL */
 #define OMAP3430_VALID_MASK				(1 << 24)
 #define OMAP3430_DATA_SHIFT				16
-#define OMAP3430_DATA_MASK				(0xff << 16)
 #define OMAP3430_REGADDR_SHIFT				8
-#define OMAP3430_REGADDR_MASK				(0xff << 8)
 #define OMAP3430_SLAVEADDR_SHIFT			0
-#define OMAP3430_SLAVEADDR_MASK				(0x7f << 0)
-
-/* PRM_RSTCTRL */
-#define OMAP3430_RST_DPLL3_MASK				(1 << 2)
-#define OMAP3430_RST_GS_MASK				(1 << 1)
-
-/* PRM_RSTTIME */
-#define OMAP3430_RSTTIME2_SHIFT				8
-#define OMAP3430_RSTTIME2_MASK				(0x1f << 8)
-#define OMAP3430_RSTTIME1_SHIFT				0
-#define OMAP3430_RSTTIME1_MASK				(0xff << 0)
-
-/* PRM_RSTST */
 #define OMAP3430_ICECRUSHER_RST_SHIFT			10
-#define OMAP3430_ICECRUSHER_RST_MASK			(1 << 10)
 #define OMAP3430_ICEPICK_RST_SHIFT			9
-#define OMAP3430_ICEPICK_RST_MASK			(1 << 9)
 #define OMAP3430_VDD2_VOLTAGE_MANAGER_RST_SHIFT		8
-#define OMAP3430_VDD2_VOLTAGE_MANAGER_RST_MASK		(1 << 8)
 #define OMAP3430_VDD1_VOLTAGE_MANAGER_RST_SHIFT		7
-#define OMAP3430_VDD1_VOLTAGE_MANAGER_RST_MASK		(1 << 7)
 #define OMAP3430_EXTERNAL_WARM_RST_SHIFT		6
-#define OMAP3430_EXTERNAL_WARM_RST_MASK			(1 << 6)
 #define OMAP3430_SECURE_WD_RST_SHIFT			5
-#define OMAP3430_SECURE_WD_RST_MASK			(1 << 5)
 #define OMAP3430_MPU_WD_RST_SHIFT			4
-#define OMAP3430_MPU_WD_RST_MASK			(1 << 4)
 #define OMAP3430_SECURITY_VIOL_RST_SHIFT		3
-#define OMAP3430_SECURITY_VIOL_RST_MASK			(1 << 3)
 #define OMAP3430_GLOBAL_SW_RST_SHIFT			1
-#define OMAP3430_GLOBAL_SW_RST_MASK			(1 << 1)
 #define OMAP3430_GLOBAL_COLD_RST_SHIFT			0
 #define OMAP3430_GLOBAL_COLD_RST_MASK			(1 << 0)
-
-/* PRM_VOLTCTRL */
-#define OMAP3430_SEL_VMODE_MASK				(1 << 4)
 #define OMAP3430_SEL_OFF_MASK				(1 << 3)
 #define OMAP3430_AUTO_OFF_MASK				(1 << 2)
-#define OMAP3430_AUTO_RET_MASK				(1 << 1)
-#define OMAP3430_AUTO_SLEEP_MASK			(1 << 0)
-
-/* PRM_SRAM_PCHARGE */
-#define OMAP3430_PCHARGE_TIME_SHIFT			0
-#define OMAP3430_PCHARGE_TIME_MASK			(0xff << 0)
-
-/* PRM_CLKSRC_CTRL */
-#define OMAP3430_SYSCLKDIV_SHIFT			6
-#define OMAP3430_SYSCLKDIV_MASK				(0x3 << 6)
-#define OMAP3430_AUTOEXTCLKMODE_SHIFT			3
-#define OMAP3430_AUTOEXTCLKMODE_MASK			(0x3 << 3)
-#define OMAP3430_SYSCLKSEL_SHIFT			0
-#define OMAP3430_SYSCLKSEL_MASK				(0x3 << 0)
-
-/* PRM_VOLTSETUP1 */
-#define OMAP3430_SETUP_TIME2_SHIFT			16
 #define OMAP3430_SETUP_TIME2_MASK			(0xffff << 16)
-#define OMAP3430_SETUP_TIME1_SHIFT			0
 #define OMAP3430_SETUP_TIME1_MASK			(0xffff << 0)
-
-/* PRM_VOLTOFFSET */
-#define OMAP3430_OFFSET_TIME_SHIFT			0
-#define OMAP3430_OFFSET_TIME_MASK			(0xffff << 0)
-
-/* PRM_CLKSETUP */
-#define OMAP3430_SETUP_TIME_SHIFT			0
-#define OMAP3430_SETUP_TIME_MASK			(0xffff << 0)
-
-/* PRM_POLCTRL */
-#define OMAP3430_OFFMODE_POL_MASK			(1 << 3)
-#define OMAP3430_CLKOUT_POL_MASK			(1 << 2)
-#define OMAP3430_CLKREQ_POL_MASK			(1 << 1)
-#define OMAP3430_EXTVOL_POL_MASK			(1 << 0)
-
-/* PRM_VOLTSETUP2 */
-#define OMAP3430_OFFMODESETUPTIME_SHIFT			0
-#define OMAP3430_OFFMODESETUPTIME_MASK			(0xffff << 0)
-
-/* PRM_VP1_CONFIG specific bits */
-
-/* PRM_VP1_VSTEPMIN specific bits */
-
-/* PRM_VP1_VSTEPMAX specific bits */
-
-/* PRM_VP1_VLIMITTO specific bits */
-
-/* PRM_VP1_VOLTAGE specific bits */
-
-/* PRM_VP1_STATUS specific bits */
-
-/* PRM_VP2_CONFIG specific bits */
-
-/* PRM_VP2_VSTEPMIN specific bits */
-
-/* PRM_VP2_VSTEPMAX specific bits */
-
-/* PRM_VP2_VLIMITTO specific bits */
-
-/* PRM_VP2_VOLTAGE specific bits */
-
-/* PRM_VP2_STATUS specific bits */
-
-/* RM_RSTST_NEON specific bits */
-
-/* PM_WKDEP_NEON specific bits */
-
-/* PM_PWSTCTRL_NEON specific bits */
-
-/* PM_PWSTST_NEON specific bits */
-
-/* PM_PREPWSTST_NEON specific bits */
-
 #endif
diff --git a/arch/arm/mach-omap2/prm-regbits-44xx.h b/arch/arm/mach-omap2/prm-regbits-44xx.h
index 3cb247bebdaa..b1c7a33e00e7 100644
--- a/arch/arm/mach-omap2/prm-regbits-44xx.h
+++ b/arch/arm/mach-omap2/prm-regbits-44xx.h
@@ -22,2306 +22,80 @@
 #ifndef __ARCH_ARM_MACH_OMAP2_PRM_REGBITS_44XX_H
 #define __ARCH_ARM_MACH_OMAP2_PRM_REGBITS_44XX_H
 
-
-/*
- * Used by PRM_LDO_SRAM_CORE_SETUP, PRM_LDO_SRAM_IVA_SETUP,
- * PRM_LDO_SRAM_MPU_SETUP
- */
-#define OMAP4430_ABBOFF_ACT_EXPORT_SHIFT				1
-#define OMAP4430_ABBOFF_ACT_EXPORT_MASK					(1 << 1)
-
-/*
- * Used by PRM_LDO_SRAM_CORE_SETUP, PRM_LDO_SRAM_IVA_SETUP,
- * PRM_LDO_SRAM_MPU_SETUP
- */
-#define OMAP4430_ABBOFF_SLEEP_EXPORT_SHIFT				2
-#define OMAP4430_ABBOFF_SLEEP_EXPORT_MASK				(1 << 2)
-
-/* Used by PRM_IRQENABLE_DUCATI, PRM_IRQENABLE_MPU */
-#define OMAP4430_ABB_IVA_DONE_EN_SHIFT					31
-#define OMAP4430_ABB_IVA_DONE_EN_MASK					(1 << 31)
-
-/* Used by PRM_IRQSTATUS_DUCATI, PRM_IRQSTATUS_MPU */
-#define OMAP4430_ABB_IVA_DONE_ST_SHIFT					31
-#define OMAP4430_ABB_IVA_DONE_ST_MASK					(1 << 31)
-
-/* Used by PRM_IRQENABLE_MPU_2 */
-#define OMAP4430_ABB_MPU_DONE_EN_SHIFT					7
-#define OMAP4430_ABB_MPU_DONE_EN_MASK					(1 << 7)
-
-/* Used by PRM_IRQSTATUS_MPU_2 */
-#define OMAP4430_ABB_MPU_DONE_ST_SHIFT					7
-#define OMAP4430_ABB_MPU_DONE_ST_MASK					(1 << 7)
-
-/* Used by PRM_LDO_ABB_IVA_SETUP, PRM_LDO_ABB_MPU_SETUP */
-#define OMAP4430_ACTIVE_FBB_SEL_SHIFT					2
-#define OMAP4430_ACTIVE_FBB_SEL_MASK					(1 << 2)
-
-/* Used by PRM_LDO_ABB_IVA_SETUP, PRM_LDO_ABB_MPU_SETUP */
-#define OMAP4430_ACTIVE_RBB_SEL_SHIFT					1
-#define OMAP4430_ACTIVE_RBB_SEL_MASK					(1 << 1)
-
-/* Used by PM_ABE_PWRSTCTRL */
-#define OMAP4430_AESSMEM_ONSTATE_SHIFT					16
-#define OMAP4430_AESSMEM_ONSTATE_MASK					(0x3 << 16)
-
-/* Used by PM_ABE_PWRSTCTRL */
-#define OMAP4430_AESSMEM_RETSTATE_SHIFT					8
-#define OMAP4430_AESSMEM_RETSTATE_MASK					(1 << 8)
-
-/* Used by PM_ABE_PWRSTST */
-#define OMAP4430_AESSMEM_STATEST_SHIFT					4
-#define OMAP4430_AESSMEM_STATEST_MASK					(0x3 << 4)
-
-/*
- * Used by PRM_LDO_SRAM_CORE_SETUP, PRM_LDO_SRAM_IVA_SETUP,
- * PRM_LDO_SRAM_MPU_SETUP
- */
-#define OMAP4430_AIPOFF_SHIFT						8
-#define OMAP4430_AIPOFF_MASK						(1 << 8)
-
-/* Used by PRM_VOLTCTRL */
-#define OMAP4430_AUTO_CTRL_VDD_CORE_L_SHIFT				0
-#define OMAP4430_AUTO_CTRL_VDD_CORE_L_MASK				(0x3 << 0)
-
-/* Used by PRM_VOLTCTRL */
-#define OMAP4430_AUTO_CTRL_VDD_IVA_L_SHIFT				4
-#define OMAP4430_AUTO_CTRL_VDD_IVA_L_MASK				(0x3 << 4)
-
-/* Used by PRM_VOLTCTRL */
-#define OMAP4430_AUTO_CTRL_VDD_MPU_L_SHIFT				2
-#define OMAP4430_AUTO_CTRL_VDD_MPU_L_MASK				(0x3 << 2)
-
-/* Used by PRM_VC_ERRST */
-#define OMAP4430_BYPS_RA_ERR_SHIFT					25
-#define OMAP4430_BYPS_RA_ERR_MASK					(1 << 25)
-
-/* Used by PRM_VC_ERRST */
-#define OMAP4430_BYPS_SA_ERR_SHIFT					24
-#define OMAP4430_BYPS_SA_ERR_MASK					(1 << 24)
-
-/* Used by PRM_VC_ERRST */
-#define OMAP4430_BYPS_TIMEOUT_ERR_SHIFT					26
-#define OMAP4430_BYPS_TIMEOUT_ERR_MASK					(1 << 26)
-
-/* Used by PRM_RSTST */
 #define OMAP4430_C2C_RST_SHIFT						10
-#define OMAP4430_C2C_RST_MASK						(1 << 10)
-
-/* Used by PM_CAM_PWRSTCTRL */
-#define OMAP4430_CAM_MEM_ONSTATE_SHIFT					16
-#define OMAP4430_CAM_MEM_ONSTATE_MASK					(0x3 << 16)
-
-/* Used by PM_CAM_PWRSTST */
-#define OMAP4430_CAM_MEM_STATEST_SHIFT					4
-#define OMAP4430_CAM_MEM_STATEST_MASK					(0x3 << 4)
-
-/* Used by PRM_CLKREQCTRL */
-#define OMAP4430_CLKREQ_COND_SHIFT					0
-#define OMAP4430_CLKREQ_COND_MASK					(0x7 << 0)
-
-/* Used by PRM_VC_VAL_SMPS_RA_CMD */
-#define OMAP4430_CMDRA_VDD_CORE_L_SHIFT					0
 #define OMAP4430_CMDRA_VDD_CORE_L_MASK					(0xff << 0)
-
-/* Used by PRM_VC_VAL_SMPS_RA_CMD */
-#define OMAP4430_CMDRA_VDD_IVA_L_SHIFT					8
 #define OMAP4430_CMDRA_VDD_IVA_L_MASK					(0xff << 8)
-
-/* Used by PRM_VC_VAL_SMPS_RA_CMD */
-#define OMAP4430_CMDRA_VDD_MPU_L_SHIFT					16
 #define OMAP4430_CMDRA_VDD_MPU_L_MASK					(0xff << 16)
-
-/* Used by PRM_VC_CFG_CHANNEL */
-#define OMAP4430_CMD_VDD_CORE_L_SHIFT					4
-#define OMAP4430_CMD_VDD_CORE_L_MASK					(1 << 4)
-
-/* Used by PRM_VC_CFG_CHANNEL */
-#define OMAP4430_CMD_VDD_IVA_L_SHIFT					12
-#define OMAP4430_CMD_VDD_IVA_L_MASK					(1 << 12)
-
-/* Used by PRM_VC_CFG_CHANNEL */
-#define OMAP4430_CMD_VDD_MPU_L_SHIFT					17
-#define OMAP4430_CMD_VDD_MPU_L_MASK					(1 << 17)
-
-/* Used by PM_CORE_PWRSTCTRL */
-#define OMAP4430_CORE_OCMRAM_ONSTATE_SHIFT				18
-#define OMAP4430_CORE_OCMRAM_ONSTATE_MASK				(0x3 << 18)
-
-/* Used by PM_CORE_PWRSTCTRL */
-#define OMAP4430_CORE_OCMRAM_RETSTATE_SHIFT				9
-#define OMAP4430_CORE_OCMRAM_RETSTATE_MASK				(1 << 9)
-
-/* Used by PM_CORE_PWRSTST */
-#define OMAP4430_CORE_OCMRAM_STATEST_SHIFT				6
-#define OMAP4430_CORE_OCMRAM_STATEST_MASK				(0x3 << 6)
-
-/* Used by PM_CORE_PWRSTCTRL */
-#define OMAP4430_CORE_OTHER_BANK_ONSTATE_SHIFT				16
-#define OMAP4430_CORE_OTHER_BANK_ONSTATE_MASK				(0x3 << 16)
-
-/* Used by PM_CORE_PWRSTCTRL */
-#define OMAP4430_CORE_OTHER_BANK_RETSTATE_SHIFT				8
-#define OMAP4430_CORE_OTHER_BANK_RETSTATE_MASK				(1 << 8)
-
-/* Used by PM_CORE_PWRSTST */
-#define OMAP4430_CORE_OTHER_BANK_STATEST_SHIFT				4
-#define OMAP4430_CORE_OTHER_BANK_STATEST_MASK				(0x3 << 4)
-
-/* Used by REVISION_PRM */
-#define OMAP4430_CUSTOM_SHIFT						6
-#define OMAP4430_CUSTOM_MASK						(0x3 << 6)
-
-/* Used by PRM_VC_VAL_BYPASS */
 #define OMAP4430_DATA_SHIFT						16
-#define OMAP4430_DATA_MASK						(0xff << 16)
-
-/* Used by PRM_DEVICE_OFF_CTRL */
-#define OMAP4430_DEVICE_OFF_ENABLE_SHIFT				0
-#define OMAP4430_DEVICE_OFF_ENABLE_MASK					(1 << 0)
-
-/* Used by PRM_VC_CFG_I2C_MODE */
-#define OMAP4430_DFILTEREN_SHIFT					6
-#define OMAP4430_DFILTEREN_MASK						(1 << 6)
-
-/*
- * Used by PRM_LDO_SRAM_CORE_SETUP, PRM_LDO_SRAM_IVA_SETUP,
- * PRM_LDO_SRAM_MPU_SETUP, PRM_SRAM_WKUP_SETUP
- */
-#define OMAP4430_DISABLE_RTA_EXPORT_SHIFT				0
-#define OMAP4430_DISABLE_RTA_EXPORT_MASK				(1 << 0)
-
-/* Used by PRM_IRQENABLE_DUCATI, PRM_IRQENABLE_MPU, PRM_IRQENABLE_TESLA */
-#define OMAP4430_DPLL_ABE_RECAL_EN_SHIFT				4
-#define OMAP4430_DPLL_ABE_RECAL_EN_MASK					(1 << 4)
-
-/* Used by PRM_IRQSTATUS_DUCATI, PRM_IRQSTATUS_MPU, PRM_IRQSTATUS_TESLA */
-#define OMAP4430_DPLL_ABE_RECAL_ST_SHIFT				4
-#define OMAP4430_DPLL_ABE_RECAL_ST_MASK					(1 << 4)
-
-/* Used by PRM_IRQENABLE_DUCATI, PRM_IRQENABLE_MPU */
-#define OMAP4430_DPLL_CORE_RECAL_EN_SHIFT				0
-#define OMAP4430_DPLL_CORE_RECAL_EN_MASK				(1 << 0)
-
-/* Used by PRM_IRQSTATUS_DUCATI, PRM_IRQSTATUS_MPU */
-#define OMAP4430_DPLL_CORE_RECAL_ST_SHIFT				0
-#define OMAP4430_DPLL_CORE_RECAL_ST_MASK				(1 << 0)
-
-/* Used by PRM_IRQENABLE_MPU */
-#define OMAP4430_DPLL_DDRPHY_RECAL_EN_SHIFT				6
-#define OMAP4430_DPLL_DDRPHY_RECAL_EN_MASK				(1 << 6)
-
-/* Used by PRM_IRQSTATUS_MPU */
-#define OMAP4430_DPLL_DDRPHY_RECAL_ST_SHIFT				6
-#define OMAP4430_DPLL_DDRPHY_RECAL_ST_MASK				(1 << 6)
-
-/* Used by PRM_IRQENABLE_DUCATI, PRM_IRQENABLE_MPU, PRM_IRQENABLE_TESLA */
-#define OMAP4430_DPLL_IVA_RECAL_EN_SHIFT				2
-#define OMAP4430_DPLL_IVA_RECAL_EN_MASK					(1 << 2)
-
-/* Used by PRM_IRQSTATUS_DUCATI, PRM_IRQSTATUS_MPU, PRM_IRQSTATUS_TESLA */
-#define OMAP4430_DPLL_IVA_RECAL_ST_SHIFT				2
-#define OMAP4430_DPLL_IVA_RECAL_ST_MASK					(1 << 2)
-
-/* Used by PRM_IRQENABLE_MPU */
-#define OMAP4430_DPLL_MPU_RECAL_EN_SHIFT				1
-#define OMAP4430_DPLL_MPU_RECAL_EN_MASK					(1 << 1)
-
-/* Used by PRM_IRQSTATUS_MPU */
-#define OMAP4430_DPLL_MPU_RECAL_ST_SHIFT				1
-#define OMAP4430_DPLL_MPU_RECAL_ST_MASK					(1 << 1)
-
-/* Used by PRM_IRQENABLE_DUCATI, PRM_IRQENABLE_MPU */
-#define OMAP4430_DPLL_PER_RECAL_EN_SHIFT				3
-#define OMAP4430_DPLL_PER_RECAL_EN_MASK					(1 << 3)
-
-/* Used by PRM_IRQSTATUS_DUCATI, PRM_IRQSTATUS_MPU */
-#define OMAP4430_DPLL_PER_RECAL_ST_SHIFT				3
-#define OMAP4430_DPLL_PER_RECAL_ST_MASK					(1 << 3)
-
-/* Used by PRM_IRQENABLE_DUCATI, PRM_IRQENABLE_MPU */
-#define OMAP4430_DPLL_UNIPRO_RECAL_EN_SHIFT				7
-#define OMAP4430_DPLL_UNIPRO_RECAL_EN_MASK				(1 << 7)
-
-/* Used by PRM_IRQSTATUS_DUCATI, PRM_IRQSTATUS_MPU */
-#define OMAP4430_DPLL_UNIPRO_RECAL_ST_SHIFT				7
-#define OMAP4430_DPLL_UNIPRO_RECAL_ST_MASK				(1 << 7)
-
-/* Used by PM_DSS_PWRSTCTRL */
-#define OMAP4430_DSS_MEM_ONSTATE_SHIFT					16
-#define OMAP4430_DSS_MEM_ONSTATE_MASK					(0x3 << 16)
-
-/* Used by PM_DSS_PWRSTCTRL */
-#define OMAP4430_DSS_MEM_RETSTATE_SHIFT					8
-#define OMAP4430_DSS_MEM_RETSTATE_MASK					(1 << 8)
-
-/* Used by PM_DSS_PWRSTST */
-#define OMAP4430_DSS_MEM_STATEST_SHIFT					4
-#define OMAP4430_DSS_MEM_STATEST_MASK					(0x3 << 4)
-
-/* Used by PM_CORE_PWRSTCTRL */
-#define OMAP4430_DUCATI_L2RAM_ONSTATE_SHIFT				20
-#define OMAP4430_DUCATI_L2RAM_ONSTATE_MASK				(0x3 << 20)
-
-/* Used by PM_CORE_PWRSTCTRL */
-#define OMAP4430_DUCATI_L2RAM_RETSTATE_SHIFT				10
-#define OMAP4430_DUCATI_L2RAM_RETSTATE_MASK				(1 << 10)
-
-/* Used by PM_CORE_PWRSTST */
-#define OMAP4430_DUCATI_L2RAM_STATEST_SHIFT				8
-#define OMAP4430_DUCATI_L2RAM_STATEST_MASK				(0x3 << 8)
-
-/* Used by PM_CORE_PWRSTCTRL */
-#define OMAP4430_DUCATI_UNICACHE_ONSTATE_SHIFT				22
-#define OMAP4430_DUCATI_UNICACHE_ONSTATE_MASK				(0x3 << 22)
-
-/* Used by PM_CORE_PWRSTCTRL */
-#define OMAP4430_DUCATI_UNICACHE_RETSTATE_SHIFT				11
-#define OMAP4430_DUCATI_UNICACHE_RETSTATE_MASK				(1 << 11)
-
-/* Used by PM_CORE_PWRSTST */
-#define OMAP4430_DUCATI_UNICACHE_STATEST_SHIFT				10
-#define OMAP4430_DUCATI_UNICACHE_STATEST_MASK				(0x3 << 10)
-
-/* Used by PRM_DEVICE_OFF_CTRL */
-#define OMAP4460_EMIF1_OFFWKUP_DISABLE_SHIFT				8
-#define OMAP4460_EMIF1_OFFWKUP_DISABLE_MASK				(1 << 8)
-
-/* Used by PRM_DEVICE_OFF_CTRL */
-#define OMAP4460_EMIF2_OFFWKUP_DISABLE_SHIFT				9
-#define OMAP4460_EMIF2_OFFWKUP_DISABLE_MASK				(1 << 9)
-
-/* Used by RM_MPU_RSTST */
-#define OMAP4430_EMULATION_RST_SHIFT					0
-#define OMAP4430_EMULATION_RST_MASK					(1 << 0)
-
-/* Used by RM_DUCATI_RSTST */
-#define OMAP4430_EMULATION_RST1ST_SHIFT					3
-#define OMAP4430_EMULATION_RST1ST_MASK					(1 << 3)
-
-/* Used by RM_DUCATI_RSTST */
-#define OMAP4430_EMULATION_RST2ST_SHIFT					4
-#define OMAP4430_EMULATION_RST2ST_MASK					(1 << 4)
-
-/* Used by RM_IVAHD_RSTST */
-#define OMAP4430_EMULATION_SEQ1_RST1ST_SHIFT				3
-#define OMAP4430_EMULATION_SEQ1_RST1ST_MASK				(1 << 3)
-
-/* Used by RM_IVAHD_RSTST */
-#define OMAP4430_EMULATION_SEQ2_RST2ST_SHIFT				4
-#define OMAP4430_EMULATION_SEQ2_RST2ST_MASK				(1 << 4)
-
-/* Used by PM_EMU_PWRSTCTRL */
-#define OMAP4430_EMU_BANK_ONSTATE_SHIFT					16
-#define OMAP4430_EMU_BANK_ONSTATE_MASK					(0x3 << 16)
-
-/* Used by PM_EMU_PWRSTST */
-#define OMAP4430_EMU_BANK_STATEST_SHIFT					4
-#define OMAP4430_EMU_BANK_STATEST_MASK					(0x3 << 4)
-
-/*
- * Used by PRM_LDO_SRAM_CORE_SETUP, PRM_LDO_SRAM_IVA_SETUP,
- * PRM_LDO_SRAM_MPU_SETUP
- */
-#define OMAP4430_ENFUNC1_EXPORT_SHIFT					3
-#define OMAP4430_ENFUNC1_EXPORT_MASK					(1 << 3)
-
-/*
- * Used by PRM_LDO_SRAM_CORE_SETUP, PRM_LDO_SRAM_IVA_SETUP,
- * PRM_LDO_SRAM_MPU_SETUP
- */
-#define OMAP4430_ENFUNC3_EXPORT_SHIFT					5
-#define OMAP4430_ENFUNC3_EXPORT_MASK					(1 << 5)
-
-/*
- * Used by PRM_LDO_SRAM_CORE_SETUP, PRM_LDO_SRAM_IVA_SETUP,
- * PRM_LDO_SRAM_MPU_SETUP
- */
-#define OMAP4430_ENFUNC4_SHIFT						6
-#define OMAP4430_ENFUNC4_MASK						(1 << 6)
-
-/*
- * Used by PRM_LDO_SRAM_CORE_SETUP, PRM_LDO_SRAM_IVA_SETUP,
- * PRM_LDO_SRAM_MPU_SETUP
- */
-#define OMAP4430_ENFUNC5_SHIFT						7
-#define OMAP4430_ENFUNC5_MASK						(1 << 7)
-
-/* Used by PRM_VP_CORE_CONFIG, PRM_VP_IVA_CONFIG, PRM_VP_MPU_CONFIG */
-#define OMAP4430_ERRORGAIN_SHIFT					16
 #define OMAP4430_ERRORGAIN_MASK						(0xff << 16)
-
-/* Used by PRM_VP_CORE_CONFIG, PRM_VP_IVA_CONFIG, PRM_VP_MPU_CONFIG */
-#define OMAP4430_ERROROFFSET_SHIFT					24
 #define OMAP4430_ERROROFFSET_MASK					(0xff << 24)
-
-/* Used by PRM_RSTST */
 #define OMAP4430_EXTERNAL_WARM_RST_SHIFT				5
-#define OMAP4430_EXTERNAL_WARM_RST_MASK					(1 << 5)
-
-/* Used by PRM_VP_CORE_CONFIG, PRM_VP_IVA_CONFIG, PRM_VP_MPU_CONFIG */
-#define OMAP4430_FORCEUPDATE_SHIFT					1
 #define OMAP4430_FORCEUPDATE_MASK					(1 << 1)
-
-/* Used by PRM_VP_CORE_VOLTAGE, PRM_VP_IVA_VOLTAGE, PRM_VP_MPU_VOLTAGE */
-#define OMAP4430_FORCEUPDATEWAIT_SHIFT					8
-#define OMAP4430_FORCEUPDATEWAIT_MASK					(0xffffff << 8)
-
-/* Used by PRM_IRQENABLE_DUCATI, PRM_IRQENABLE_TESLA */
-#define OMAP4430_FORCEWKUP_EN_SHIFT					10
-#define OMAP4430_FORCEWKUP_EN_MASK					(1 << 10)
-
-/* Used by PRM_IRQSTATUS_DUCATI, PRM_IRQSTATUS_TESLA */
-#define OMAP4430_FORCEWKUP_ST_SHIFT					10
-#define OMAP4430_FORCEWKUP_ST_MASK					(1 << 10)
-
-/* Used by REVISION_PRM */
-#define OMAP4430_FUNC_SHIFT						16
-#define OMAP4430_FUNC_MASK						(0xfff << 16)
-
-/* Used by PM_GFX_PWRSTCTRL */
-#define OMAP4430_GFX_MEM_ONSTATE_SHIFT					16
-#define OMAP4430_GFX_MEM_ONSTATE_MASK					(0x3 << 16)
-
-/* Used by PM_GFX_PWRSTST */
-#define OMAP4430_GFX_MEM_STATEST_SHIFT					4
-#define OMAP4430_GFX_MEM_STATEST_MASK					(0x3 << 4)
-
-/* Used by PRM_RSTST */
 #define OMAP4430_GLOBAL_COLD_RST_SHIFT					0
-#define OMAP4430_GLOBAL_COLD_RST_MASK					(1 << 0)
-
-/* Used by PRM_RSTST */
 #define OMAP4430_GLOBAL_WARM_SW_RST_SHIFT				1
-#define OMAP4430_GLOBAL_WARM_SW_RST_MASK				(1 << 1)
-
-/* Used by PRM_IO_PMCTRL */
-#define OMAP4430_GLOBAL_WUEN_SHIFT					16
 #define OMAP4430_GLOBAL_WUEN_MASK					(1 << 16)
-
-/* Used by PRM_VC_CFG_I2C_MODE */
-#define OMAP4430_HSMCODE_SHIFT						0
 #define OMAP4430_HSMCODE_MASK						(0x7 << 0)
-
-/* Used by PRM_VC_CFG_I2C_MODE */
-#define OMAP4430_HSMODEEN_SHIFT						3
 #define OMAP4430_HSMODEEN_MASK						(1 << 3)
-
-/* Used by PRM_VC_CFG_I2C_CLK */
-#define OMAP4430_HSSCLH_SHIFT						16
-#define OMAP4430_HSSCLH_MASK						(0xff << 16)
-
-/* Used by PRM_VC_CFG_I2C_CLK */
 #define OMAP4430_HSSCLL_SHIFT						24
-#define OMAP4430_HSSCLL_MASK						(0xff << 24)
-
-/* Used by PM_IVAHD_PWRSTCTRL */
-#define OMAP4430_HWA_MEM_ONSTATE_SHIFT					16
-#define OMAP4430_HWA_MEM_ONSTATE_MASK					(0x3 << 16)
-
-/* Used by PM_IVAHD_PWRSTCTRL */
-#define OMAP4430_HWA_MEM_RETSTATE_SHIFT					8
-#define OMAP4430_HWA_MEM_RETSTATE_MASK					(1 << 8)
-
-/* Used by PM_IVAHD_PWRSTST */
-#define OMAP4430_HWA_MEM_STATEST_SHIFT					4
-#define OMAP4430_HWA_MEM_STATEST_MASK					(0x3 << 4)
-
-/* Used by RM_MPU_RSTST */
-#define OMAP4430_ICECRUSHER_MPU_RST_SHIFT				1
-#define OMAP4430_ICECRUSHER_MPU_RST_MASK				(1 << 1)
-
-/* Used by RM_DUCATI_RSTST */
-#define OMAP4430_ICECRUSHER_RST1ST_SHIFT				5
-#define OMAP4430_ICECRUSHER_RST1ST_MASK					(1 << 5)
-
-/* Used by RM_DUCATI_RSTST */
-#define OMAP4430_ICECRUSHER_RST2ST_SHIFT				6
-#define OMAP4430_ICECRUSHER_RST2ST_MASK					(1 << 6)
-
-/* Used by RM_IVAHD_RSTST */
-#define OMAP4430_ICECRUSHER_SEQ1_RST1ST_SHIFT				5
-#define OMAP4430_ICECRUSHER_SEQ1_RST1ST_MASK				(1 << 5)
-
-/* Used by RM_IVAHD_RSTST */
-#define OMAP4430_ICECRUSHER_SEQ2_RST2ST_SHIFT				6
-#define OMAP4430_ICECRUSHER_SEQ2_RST2ST_MASK				(1 << 6)
-
-/* Used by PRM_RSTST */
 #define OMAP4430_ICEPICK_RST_SHIFT					9
-#define OMAP4430_ICEPICK_RST_MASK					(1 << 9)
-
-/* Used by PRM_VP_CORE_CONFIG, PRM_VP_IVA_CONFIG, PRM_VP_MPU_CONFIG */
-#define OMAP4430_INITVDD_SHIFT						2
 #define OMAP4430_INITVDD_MASK						(1 << 2)
-
-/* Used by PRM_VP_CORE_CONFIG, PRM_VP_IVA_CONFIG, PRM_VP_MPU_CONFIG */
-#define OMAP4430_INITVOLTAGE_SHIFT					8
 #define OMAP4430_INITVOLTAGE_MASK					(0xff << 8)
-
-/*
- * Used by PM_ABE_PWRSTST, PM_CAM_PWRSTST, PM_CEFUSE_PWRSTST, PM_CORE_PWRSTST,
- * PM_DSS_PWRSTST, PM_EMU_PWRSTST, PM_GFX_PWRSTST, PM_IVAHD_PWRSTST,
- * PM_L3INIT_PWRSTST, PM_L4PER_PWRSTST, PM_MPU_PWRSTST, PM_TESLA_PWRSTST
- */
-#define OMAP4430_INTRANSITION_SHIFT					20
-#define OMAP4430_INTRANSITION_MASK					(1 << 20)
-
-/* Used by PRM_IRQENABLE_DUCATI, PRM_IRQENABLE_MPU */
-#define OMAP4430_IO_EN_SHIFT						9
-#define OMAP4430_IO_EN_MASK						(1 << 9)
-
-/* Used by PRM_IO_PMCTRL */
-#define OMAP4430_IO_ON_STATUS_SHIFT					5
-#define OMAP4430_IO_ON_STATUS_MASK					(1 << 5)
-
-/* Used by PRM_IRQSTATUS_DUCATI, PRM_IRQSTATUS_MPU */
-#define OMAP4430_IO_ST_SHIFT						9
-#define OMAP4430_IO_ST_MASK						(1 << 9)
-
-/* Used by PRM_IO_PMCTRL */
-#define OMAP4430_ISOCLK_OVERRIDE_SHIFT					0
-#define OMAP4430_ISOCLK_OVERRIDE_MASK					(1 << 0)
-
-/* Used by PRM_IO_PMCTRL */
-#define OMAP4430_ISOCLK_STATUS_SHIFT					1
-#define OMAP4430_ISOCLK_STATUS_MASK					(1 << 1)
-
-/* Used by PRM_IO_PMCTRL */
-#define OMAP4430_ISOOVR_EXTEND_SHIFT					4
-#define OMAP4430_ISOOVR_EXTEND_MASK					(1 << 4)
-
-/* Used by PRM_IO_COUNT */
-#define OMAP4430_ISO_2_ON_TIME_SHIFT					0
-#define OMAP4430_ISO_2_ON_TIME_MASK					(0xff << 0)
-
-/* Used by PM_L3INIT_PWRSTCTRL */
-#define OMAP4430_L3INIT_BANK1_ONSTATE_SHIFT				16
-#define OMAP4430_L3INIT_BANK1_ONSTATE_MASK				(0x3 << 16)
-
-/* Used by PM_L3INIT_PWRSTCTRL */
-#define OMAP4430_L3INIT_BANK1_RETSTATE_SHIFT				8
-#define OMAP4430_L3INIT_BANK1_RETSTATE_MASK				(1 << 8)
-
-/* Used by PM_L3INIT_PWRSTST */
-#define OMAP4430_L3INIT_BANK1_STATEST_SHIFT				4
-#define OMAP4430_L3INIT_BANK1_STATEST_MASK				(0x3 << 4)
-
-/*
- * Used by PM_ABE_PWRSTST, PM_CORE_PWRSTST, PM_IVAHD_PWRSTST,
- * PM_L3INIT_PWRSTST, PM_L4PER_PWRSTST, PM_MPU_PWRSTST, PM_TESLA_PWRSTST
- */
 #define OMAP4430_LASTPOWERSTATEENTERED_SHIFT				24
 #define OMAP4430_LASTPOWERSTATEENTERED_MASK				(0x3 << 24)
-
-/*
- * Used by PM_ABE_PWRSTCTRL, PM_CORE_PWRSTCTRL, PM_DSS_PWRSTCTRL,
- * PM_IVAHD_PWRSTCTRL, PM_L3INIT_PWRSTCTRL, PM_L4PER_PWRSTCTRL,
- * PM_MPU_PWRSTCTRL, PM_TESLA_PWRSTCTRL
- */
 #define OMAP4430_LOGICRETSTATE_SHIFT					2
 #define OMAP4430_LOGICRETSTATE_MASK					(1 << 2)
-
-/*
- * Used by PM_ABE_PWRSTST, PM_CAM_PWRSTST, PM_CEFUSE_PWRSTST, PM_CORE_PWRSTST,
- * PM_DSS_PWRSTST, PM_EMU_PWRSTST, PM_GFX_PWRSTST, PM_IVAHD_PWRSTST,
- * PM_L3INIT_PWRSTST, PM_L4PER_PWRSTST, PM_MPU_PWRSTST, PM_TESLA_PWRSTST
- */
 #define OMAP4430_LOGICSTATEST_SHIFT					2
 #define OMAP4430_LOGICSTATEST_MASK					(1 << 2)
-
-/*
- * Used by RM_ABE_AESS_CONTEXT, RM_ABE_DMIC_CONTEXT, RM_ABE_MCASP_CONTEXT,
- * RM_ABE_MCBSP1_CONTEXT, RM_ABE_MCBSP2_CONTEXT, RM_ABE_MCBSP3_CONTEXT,
- * RM_ABE_PDM_CONTEXT, RM_ABE_SLIMBUS_CONTEXT, RM_ABE_TIMER5_CONTEXT,
- * RM_ABE_TIMER6_CONTEXT, RM_ABE_TIMER7_CONTEXT, RM_ABE_TIMER8_CONTEXT,
- * RM_ABE_WDT3_CONTEXT, RM_ALWON_MDMINTC_CONTEXT, RM_ALWON_SR_CORE_CONTEXT,
- * RM_ALWON_SR_IVA_CONTEXT, RM_ALWON_SR_MPU_CONTEXT, RM_CAM_FDIF_CONTEXT,
- * RM_CAM_ISS_CONTEXT, RM_CEFUSE_CEFUSE_CONTEXT, RM_D2D_SAD2D_CONTEXT,
- * RM_D2D_SAD2D_FW_CONTEXT, RM_DSS_DEISS_CONTEXT, RM_DSS_DSS_CONTEXT,
- * RM_DUCATI_DUCATI_CONTEXT, RM_EMU_DEBUGSS_CONTEXT, RM_GFX_GFX_CONTEXT,
- * RM_IVAHD_IVAHD_CONTEXT, RM_IVAHD_SL2_CONTEXT, RM_L3INIT_CCPTX_CONTEXT,
- * RM_L3INIT_EMAC_CONTEXT, RM_L3INIT_P1500_CONTEXT, RM_L3INIT_PCIESS_CONTEXT,
- * RM_L3INIT_SATA_CONTEXT, RM_L3INIT_TPPSS_CONTEXT, RM_L3INIT_UNIPRO1_CONTEXT,
- * RM_L3INIT_USBPHYOCP2SCP_CONTEXT, RM_L3INIT_XHPI_CONTEXT,
- * RM_L3INSTR_L3_3_CONTEXT, RM_L3INSTR_L3_INSTR_CONTEXT,
- * RM_L3INSTR_OCP_WP1_CONTEXT, RM_L3_1_L3_1_CONTEXT, RM_L3_2_L3_2_CONTEXT,
- * RM_L3_2_OCMC_RAM_CONTEXT, RM_L4CFG_L4_CFG_CONTEXT, RM_L4CFG_SAR_ROM_CONTEXT,
- * RM_L4PER_ADC_CONTEXT, RM_L4PER_DMTIMER10_CONTEXT,
- * RM_L4PER_DMTIMER11_CONTEXT, RM_L4PER_DMTIMER2_CONTEXT,
- * RM_L4PER_DMTIMER3_CONTEXT, RM_L4PER_DMTIMER4_CONTEXT,
- * RM_L4PER_DMTIMER9_CONTEXT, RM_L4PER_ELM_CONTEXT, RM_L4PER_HDQ1W_CONTEXT,
- * RM_L4PER_HECC1_CONTEXT, RM_L4PER_HECC2_CONTEXT, RM_L4PER_I2C2_CONTEXT,
- * RM_L4PER_I2C3_CONTEXT, RM_L4PER_I2C4_CONTEXT, RM_L4PER_I2C5_CONTEXT,
- * RM_L4PER_L4_PER_CONTEXT, RM_L4PER_MCASP2_CONTEXT, RM_L4PER_MCASP3_CONTEXT,
- * RM_L4PER_MCBSP4_CONTEXT, RM_L4PER_MCSPI1_CONTEXT, RM_L4PER_MCSPI2_CONTEXT,
- * RM_L4PER_MCSPI3_CONTEXT, RM_L4PER_MCSPI4_CONTEXT, RM_L4PER_MGATE_CONTEXT,
- * RM_L4PER_MMCSD3_CONTEXT, RM_L4PER_MMCSD4_CONTEXT, RM_L4PER_MMCSD5_CONTEXT,
- * RM_L4PER_MSPROHG_CONTEXT, RM_L4PER_SLIMBUS2_CONTEXT,
- * RM_L4SEC_PKAEIP29_CONTEXT, RM_MEMIF_DLL_CONTEXT, RM_MEMIF_DLL_H_CONTEXT,
- * RM_MEMIF_DMM_CONTEXT, RM_MEMIF_EMIF_1_CONTEXT, RM_MEMIF_EMIF_2_CONTEXT,
- * RM_MEMIF_EMIF_FW_CONTEXT, RM_MPU_MPU_CONTEXT, RM_TESLA_TESLA_CONTEXT,
- * RM_WKUP_GPIO1_CONTEXT, RM_WKUP_KEYBOARD_CONTEXT, RM_WKUP_L4WKUP_CONTEXT,
- * RM_WKUP_RTC_CONTEXT, RM_WKUP_SARRAM_CONTEXT, RM_WKUP_SYNCTIMER_CONTEXT,
- * RM_WKUP_TIMER12_CONTEXT, RM_WKUP_TIMER1_CONTEXT, RM_WKUP_USIM_CONTEXT,
- * RM_WKUP_WDT1_CONTEXT, RM_WKUP_WDT2_CONTEXT
- */
-#define OMAP4430_LOSTCONTEXT_DFF_SHIFT					0
 #define OMAP4430_LOSTCONTEXT_DFF_MASK					(1 << 0)
-
-/*
- * Used by RM_D2D_MODEM_ICR_CONTEXT, RM_D2D_SAD2D_CONTEXT,
- * RM_D2D_SAD2D_FW_CONTEXT, RM_DSS_DSS_CONTEXT, RM_DUCATI_DUCATI_CONTEXT,
- * RM_L3INIT_HSI_CONTEXT, RM_L3INIT_MMC1_CONTEXT, RM_L3INIT_MMC2_CONTEXT,
- * RM_L3INIT_MMC6_CONTEXT, RM_L3INIT_USB_HOST_CONTEXT,
- * RM_L3INIT_USB_HOST_FS_CONTEXT, RM_L3INIT_USB_OTG_CONTEXT,
- * RM_L3INIT_USB_TLL_CONTEXT, RM_L3INSTR_L3_3_CONTEXT,
- * RM_L3INSTR_OCP_WP1_CONTEXT, RM_L3_1_L3_1_CONTEXT, RM_L3_2_GPMC_CONTEXT,
- * RM_L3_2_L3_2_CONTEXT, RM_L4CFG_HW_SEM_CONTEXT, RM_L4CFG_L4_CFG_CONTEXT,
- * RM_L4CFG_MAILBOX_CONTEXT, RM_L4PER_GPIO2_CONTEXT, RM_L4PER_GPIO3_CONTEXT,
- * RM_L4PER_GPIO4_CONTEXT, RM_L4PER_GPIO5_CONTEXT, RM_L4PER_GPIO6_CONTEXT,
- * RM_L4PER_I2C1_CONTEXT, RM_L4PER_L4_PER_CONTEXT, RM_L4PER_UART1_CONTEXT,
- * RM_L4PER_UART2_CONTEXT, RM_L4PER_UART3_CONTEXT, RM_L4PER_UART4_CONTEXT,
- * RM_L4SEC_AES1_CONTEXT, RM_L4SEC_AES2_CONTEXT, RM_L4SEC_CRYPTODMA_CONTEXT,
- * RM_L4SEC_DES3DES_CONTEXT, RM_L4SEC_RNG_CONTEXT, RM_L4SEC_SHA2MD51_CONTEXT,
- * RM_MEMIF_DMM_CONTEXT, RM_MEMIF_EMIF_1_CONTEXT, RM_MEMIF_EMIF_2_CONTEXT,
- * RM_MEMIF_EMIF_FW_CONTEXT, RM_MEMIF_EMIF_H1_CONTEXT,
- * RM_MEMIF_EMIF_H2_CONTEXT, RM_SDMA_SDMA_CONTEXT, RM_TESLA_TESLA_CONTEXT
- */
-#define OMAP4430_LOSTCONTEXT_RFF_SHIFT					1
-#define OMAP4430_LOSTCONTEXT_RFF_MASK					(1 << 1)
-
-/* Used by RM_ABE_AESS_CONTEXT */
-#define OMAP4430_LOSTMEM_AESSMEM_SHIFT					8
 #define OMAP4430_LOSTMEM_AESSMEM_MASK					(1 << 8)
-
-/* Used by RM_CAM_FDIF_CONTEXT, RM_CAM_ISS_CONTEXT */
-#define OMAP4430_LOSTMEM_CAM_MEM_SHIFT					8
-#define OMAP4430_LOSTMEM_CAM_MEM_MASK					(1 << 8)
-
-/* Used by RM_L3INSTR_OCP_WP1_CONTEXT */
-#define OMAP4430_LOSTMEM_CORE_NRET_BANK_SHIFT				8
-#define OMAP4430_LOSTMEM_CORE_NRET_BANK_MASK				(1 << 8)
-
-/* Renamed from LOSTMEM_CORE_NRET_BANK Used by RM_MEMIF_DMM_CONTEXT */
-#define OMAP4430_LOSTMEM_CORE_NRET_BANK_9_9_SHIFT			9
-#define OMAP4430_LOSTMEM_CORE_NRET_BANK_9_9_MASK			(1 << 9)
-
-/* Used by RM_L3_2_OCMC_RAM_CONTEXT */
-#define OMAP4430_LOSTMEM_CORE_OCMRAM_SHIFT				8
-#define OMAP4430_LOSTMEM_CORE_OCMRAM_MASK				(1 << 8)
-
-/*
- * Used by RM_D2D_MODEM_ICR_CONTEXT, RM_MEMIF_DMM_CONTEXT,
- * RM_SDMA_SDMA_CONTEXT
- */
-#define OMAP4430_LOSTMEM_CORE_OTHER_BANK_SHIFT				8
-#define OMAP4430_LOSTMEM_CORE_OTHER_BANK_MASK				(1 << 8)
-
-/* Used by RM_DSS_DEISS_CONTEXT, RM_DSS_DSS_CONTEXT */
-#define OMAP4430_LOSTMEM_DSS_MEM_SHIFT					8
-#define OMAP4430_LOSTMEM_DSS_MEM_MASK					(1 << 8)
-
-/* Used by RM_DUCATI_DUCATI_CONTEXT */
-#define OMAP4430_LOSTMEM_DUCATI_L2RAM_SHIFT				9
-#define OMAP4430_LOSTMEM_DUCATI_L2RAM_MASK				(1 << 9)
-
-/* Used by RM_DUCATI_DUCATI_CONTEXT */
-#define OMAP4430_LOSTMEM_DUCATI_UNICACHE_SHIFT				8
-#define OMAP4430_LOSTMEM_DUCATI_UNICACHE_MASK				(1 << 8)
-
-/* Used by RM_EMU_DEBUGSS_CONTEXT */
-#define OMAP4430_LOSTMEM_EMU_BANK_SHIFT					8
-#define OMAP4430_LOSTMEM_EMU_BANK_MASK					(1 << 8)
-
-/* Used by RM_GFX_GFX_CONTEXT */
-#define OMAP4430_LOSTMEM_GFX_MEM_SHIFT					8
-#define OMAP4430_LOSTMEM_GFX_MEM_MASK					(1 << 8)
-
-/* Used by RM_IVAHD_IVAHD_CONTEXT */
-#define OMAP4430_LOSTMEM_HWA_MEM_SHIFT					10
-#define OMAP4430_LOSTMEM_HWA_MEM_MASK					(1 << 10)
-
-/*
- * Used by RM_L3INIT_CCPTX_CONTEXT, RM_L3INIT_EMAC_CONTEXT,
- * RM_L3INIT_HSI_CONTEXT, RM_L3INIT_MMC1_CONTEXT, RM_L3INIT_MMC2_CONTEXT,
- * RM_L3INIT_MMC6_CONTEXT, RM_L3INIT_PCIESS_CONTEXT, RM_L3INIT_SATA_CONTEXT,
- * RM_L3INIT_TPPSS_CONTEXT, RM_L3INIT_UNIPRO1_CONTEXT,
- * RM_L3INIT_USB_OTG_CONTEXT, RM_L3INIT_XHPI_CONTEXT
- */
-#define OMAP4430_LOSTMEM_L3INIT_BANK1_SHIFT				8
-#define OMAP4430_LOSTMEM_L3INIT_BANK1_MASK				(1 << 8)
-
-/* Used by RM_MPU_MPU_CONTEXT */
-#define OMAP4430_LOSTMEM_MPU_L1_SHIFT					8
-#define OMAP4430_LOSTMEM_MPU_L1_MASK					(1 << 8)
-
-/* Used by RM_MPU_MPU_CONTEXT */
-#define OMAP4430_LOSTMEM_MPU_L2_SHIFT					9
-#define OMAP4430_LOSTMEM_MPU_L2_MASK					(1 << 9)
-
-/* Used by RM_MPU_MPU_CONTEXT */
-#define OMAP4430_LOSTMEM_MPU_RAM_SHIFT					10
-#define OMAP4430_LOSTMEM_MPU_RAM_MASK					(1 << 10)
-
-/*
- * Used by RM_L4PER_HECC1_CONTEXT, RM_L4PER_HECC2_CONTEXT,
- * RM_L4PER_MCBSP4_CONTEXT, RM_L4PER_MMCSD3_CONTEXT, RM_L4PER_MMCSD4_CONTEXT,
- * RM_L4PER_MMCSD5_CONTEXT, RM_L4PER_SLIMBUS2_CONTEXT, RM_L4SEC_PKAEIP29_CONTEXT
- */
-#define OMAP4430_LOSTMEM_NONRETAINED_BANK_SHIFT				8
-#define OMAP4430_LOSTMEM_NONRETAINED_BANK_MASK				(1 << 8)
-
-/*
- * Used by RM_ABE_DMIC_CONTEXT, RM_ABE_MCBSP1_CONTEXT, RM_ABE_MCBSP2_CONTEXT,
- * RM_ABE_MCBSP3_CONTEXT, RM_ABE_PDM_CONTEXT, RM_ABE_SLIMBUS_CONTEXT
- */
-#define OMAP4430_LOSTMEM_PERIHPMEM_SHIFT				8
-#define OMAP4430_LOSTMEM_PERIHPMEM_MASK					(1 << 8)
-
-/*
- * Used by RM_L4PER_MSPROHG_CONTEXT, RM_L4PER_UART1_CONTEXT,
- * RM_L4PER_UART2_CONTEXT, RM_L4PER_UART3_CONTEXT, RM_L4PER_UART4_CONTEXT,
- * RM_L4SEC_CRYPTODMA_CONTEXT
- */
-#define OMAP4430_LOSTMEM_RETAINED_BANK_SHIFT				8
-#define OMAP4430_LOSTMEM_RETAINED_BANK_MASK				(1 << 8)
-
-/* Used by RM_IVAHD_SL2_CONTEXT */
-#define OMAP4430_LOSTMEM_SL2_MEM_SHIFT					8
-#define OMAP4430_LOSTMEM_SL2_MEM_MASK					(1 << 8)
-
-/* Used by RM_IVAHD_IVAHD_CONTEXT */
-#define OMAP4430_LOSTMEM_TCM1_MEM_SHIFT					8
-#define OMAP4430_LOSTMEM_TCM1_MEM_MASK					(1 << 8)
-
-/* Used by RM_IVAHD_IVAHD_CONTEXT */
-#define OMAP4430_LOSTMEM_TCM2_MEM_SHIFT					9
-#define OMAP4430_LOSTMEM_TCM2_MEM_MASK					(1 << 9)
-
-/* Used by RM_TESLA_TESLA_CONTEXT */
-#define OMAP4430_LOSTMEM_TESLA_EDMA_SHIFT				10
-#define OMAP4430_LOSTMEM_TESLA_EDMA_MASK				(1 << 10)
-
-/* Used by RM_TESLA_TESLA_CONTEXT */
-#define OMAP4430_LOSTMEM_TESLA_L1_SHIFT					8
-#define OMAP4430_LOSTMEM_TESLA_L1_MASK					(1 << 8)
-
-/* Used by RM_TESLA_TESLA_CONTEXT */
-#define OMAP4430_LOSTMEM_TESLA_L2_SHIFT					9
-#define OMAP4430_LOSTMEM_TESLA_L2_MASK					(1 << 9)
-
-/* Used by RM_WKUP_SARRAM_CONTEXT */
-#define OMAP4430_LOSTMEM_WKUP_BANK_SHIFT				8
-#define OMAP4430_LOSTMEM_WKUP_BANK_MASK					(1 << 8)
-
-/*
- * Used by PM_ABE_PWRSTCTRL, PM_CAM_PWRSTCTRL, PM_CEFUSE_PWRSTCTRL,
- * PM_CORE_PWRSTCTRL, PM_DSS_PWRSTCTRL, PM_GFX_PWRSTCTRL, PM_IVAHD_PWRSTCTRL,
- * PM_L3INIT_PWRSTCTRL, PM_L4PER_PWRSTCTRL, PM_MPU_PWRSTCTRL, PM_TESLA_PWRSTCTRL
- */
 #define OMAP4430_LOWPOWERSTATECHANGE_SHIFT				4
 #define OMAP4430_LOWPOWERSTATECHANGE_MASK				(1 << 4)
-
-/* Used by PRM_MODEM_IF_CTRL */
-#define OMAP4430_MODEM_READY_SHIFT					1
-#define OMAP4430_MODEM_READY_MASK					(1 << 1)
-
-/* Used by PRM_MODEM_IF_CTRL */
-#define OMAP4430_MODEM_SHUTDOWN_IRQ_SHIFT				9
-#define OMAP4430_MODEM_SHUTDOWN_IRQ_MASK				(1 << 9)
-
-/* Used by PRM_MODEM_IF_CTRL */
-#define OMAP4430_MODEM_SLEEP_ST_SHIFT					16
-#define OMAP4430_MODEM_SLEEP_ST_MASK					(1 << 16)
-
-/* Used by PRM_MODEM_IF_CTRL */
-#define OMAP4430_MODEM_WAKE_IRQ_SHIFT					8
-#define OMAP4430_MODEM_WAKE_IRQ_MASK					(1 << 8)
-
-/* Used by PM_MPU_PWRSTCTRL */
-#define OMAP4430_MPU_L1_ONSTATE_SHIFT					16
-#define OMAP4430_MPU_L1_ONSTATE_MASK					(0x3 << 16)
-
-/* Used by PM_MPU_PWRSTCTRL */
-#define OMAP4430_MPU_L1_RETSTATE_SHIFT					8
-#define OMAP4430_MPU_L1_RETSTATE_MASK					(1 << 8)
-
-/* Used by PM_MPU_PWRSTST */
-#define OMAP4430_MPU_L1_STATEST_SHIFT					4
-#define OMAP4430_MPU_L1_STATEST_MASK					(0x3 << 4)
-
-/* Used by PM_MPU_PWRSTCTRL */
-#define OMAP4430_MPU_L2_ONSTATE_SHIFT					18
-#define OMAP4430_MPU_L2_ONSTATE_MASK					(0x3 << 18)
-
-/* Used by PM_MPU_PWRSTCTRL */
-#define OMAP4430_MPU_L2_RETSTATE_SHIFT					9
-#define OMAP4430_MPU_L2_RETSTATE_MASK					(1 << 9)
-
-/* Used by PM_MPU_PWRSTST */
-#define OMAP4430_MPU_L2_STATEST_SHIFT					6
-#define OMAP4430_MPU_L2_STATEST_MASK					(0x3 << 6)
-
-/* Used by PM_MPU_PWRSTCTRL */
-#define OMAP4430_MPU_RAM_ONSTATE_SHIFT					20
-#define OMAP4430_MPU_RAM_ONSTATE_MASK					(0x3 << 20)
-
-/* Used by PM_MPU_PWRSTCTRL */
-#define OMAP4430_MPU_RAM_RETSTATE_SHIFT					10
-#define OMAP4430_MPU_RAM_RETSTATE_MASK					(1 << 10)
-
-/* Used by PM_MPU_PWRSTST */
-#define OMAP4430_MPU_RAM_STATEST_SHIFT					8
-#define OMAP4430_MPU_RAM_STATEST_MASK					(0x3 << 8)
-
-/* Used by PRM_RSTST */
 #define OMAP4430_MPU_SECURITY_VIOL_RST_SHIFT				2
-#define OMAP4430_MPU_SECURITY_VIOL_RST_MASK				(1 << 2)
-
-/* Used by PRM_RSTST */
 #define OMAP4430_MPU_WDT_RST_SHIFT					3
-#define OMAP4430_MPU_WDT_RST_MASK					(1 << 3)
-
-/* Used by PM_L4PER_PWRSTCTRL */
-#define OMAP4430_NONRETAINED_BANK_ONSTATE_SHIFT				18
-#define OMAP4430_NONRETAINED_BANK_ONSTATE_MASK				(0x3 << 18)
-
-/* Used by PM_L4PER_PWRSTCTRL */
-#define OMAP4430_NONRETAINED_BANK_RETSTATE_SHIFT			9
-#define OMAP4430_NONRETAINED_BANK_RETSTATE_MASK				(1 << 9)
-
-/* Used by PM_L4PER_PWRSTST */
-#define OMAP4430_NONRETAINED_BANK_STATEST_SHIFT				6
-#define OMAP4430_NONRETAINED_BANK_STATEST_MASK				(0x3 << 6)
-
-/* Used by PM_CORE_PWRSTCTRL */
-#define OMAP4430_OCP_NRET_BANK_ONSTATE_SHIFT				24
 #define OMAP4430_OCP_NRET_BANK_ONSTATE_MASK				(0x3 << 24)
-
-/* Used by PM_CORE_PWRSTCTRL */
-#define OMAP4430_OCP_NRET_BANK_RETSTATE_SHIFT				12
 #define OMAP4430_OCP_NRET_BANK_RETSTATE_MASK				(1 << 12)
-
-/* Used by PM_CORE_PWRSTST */
-#define OMAP4430_OCP_NRET_BANK_STATEST_SHIFT				12
 #define OMAP4430_OCP_NRET_BANK_STATEST_MASK				(0x3 << 12)
-
-/*
- * Used by PRM_VC_VAL_CMD_VDD_CORE_L, PRM_VC_VAL_CMD_VDD_IVA_L,
- * PRM_VC_VAL_CMD_VDD_MPU_L
- */
 #define OMAP4430_OFF_SHIFT						0
-#define OMAP4430_OFF_MASK						(0xff << 0)
-
-/*
- * Used by PRM_VC_VAL_CMD_VDD_CORE_L, PRM_VC_VAL_CMD_VDD_IVA_L,
- * PRM_VC_VAL_CMD_VDD_MPU_L
- */
 #define OMAP4430_ON_SHIFT						24
 #define OMAP4430_ON_MASK						(0xff << 24)
-
-/*
- * Used by PRM_VC_VAL_CMD_VDD_CORE_L, PRM_VC_VAL_CMD_VDD_IVA_L,
- * PRM_VC_VAL_CMD_VDD_MPU_L
- */
 #define OMAP4430_ONLP_SHIFT						16
-#define OMAP4430_ONLP_MASK						(0xff << 16)
-
-/* Used by PRM_LDO_ABB_IVA_CTRL, PRM_LDO_ABB_MPU_CTRL */
-#define OMAP4430_OPP_CHANGE_SHIFT					2
-#define OMAP4430_OPP_CHANGE_MASK					(1 << 2)
-
-/* Used by PRM_LDO_ABB_IVA_CTRL, PRM_LDO_ABB_MPU_CTRL */
-#define OMAP4430_OPP_SEL_SHIFT						0
-#define OMAP4430_OPP_SEL_MASK						(0x3 << 0)
-
-/* Used by PRM_SRAM_COUNT */
-#define OMAP4430_PCHARGECNT_VALUE_SHIFT					0
-#define OMAP4430_PCHARGECNT_VALUE_MASK					(0x3f << 0)
-
-/* Used by PRM_PSCON_COUNT */
-#define OMAP4430_PCHARGE_TIME_SHIFT					0
-#define OMAP4430_PCHARGE_TIME_MASK					(0xff << 0)
-
-/* Used by PM_ABE_PWRSTCTRL */
-#define OMAP4430_PERIPHMEM_ONSTATE_SHIFT				20
-#define OMAP4430_PERIPHMEM_ONSTATE_MASK					(0x3 << 20)
-
-/* Used by PM_ABE_PWRSTCTRL */
-#define OMAP4430_PERIPHMEM_RETSTATE_SHIFT				10
-#define OMAP4430_PERIPHMEM_RETSTATE_MASK				(1 << 10)
-
-/* Used by PM_ABE_PWRSTST */
-#define OMAP4430_PERIPHMEM_STATEST_SHIFT				8
-#define OMAP4430_PERIPHMEM_STATEST_MASK					(0x3 << 8)
-
-/* Used by PRM_PHASE1_CNDP */
-#define OMAP4430_PHASE1_CNDP_SHIFT					0
-#define OMAP4430_PHASE1_CNDP_MASK					(0xffffffff << 0)
-
-/* Used by PRM_PHASE2A_CNDP */
-#define OMAP4430_PHASE2A_CNDP_SHIFT					0
-#define OMAP4430_PHASE2A_CNDP_MASK					(0xffffffff << 0)
-
-/* Used by PRM_PHASE2B_CNDP */
-#define OMAP4430_PHASE2B_CNDP_SHIFT					0
-#define OMAP4430_PHASE2B_CNDP_MASK					(0xffffffff << 0)
-
-/* Used by PRM_PSCON_COUNT */
-#define OMAP4430_PONOUT_2_PGOODIN_TIME_SHIFT				8
-#define OMAP4430_PONOUT_2_PGOODIN_TIME_MASK				(0xff << 8)
-
-/*
- * Used by PM_ABE_PWRSTCTRL, PM_CAM_PWRSTCTRL, PM_CEFUSE_PWRSTCTRL,
- * PM_CORE_PWRSTCTRL, PM_DSS_PWRSTCTRL, PM_EMU_PWRSTCTRL, PM_GFX_PWRSTCTRL,
- * PM_IVAHD_PWRSTCTRL, PM_L3INIT_PWRSTCTRL, PM_L4PER_PWRSTCTRL,
- * PM_MPU_PWRSTCTRL, PM_TESLA_PWRSTCTRL
- */
-#define OMAP4430_POWERSTATE_SHIFT					0
-#define OMAP4430_POWERSTATE_MASK					(0x3 << 0)
-
-/*
- * Used by PM_ABE_PWRSTST, PM_CAM_PWRSTST, PM_CEFUSE_PWRSTST, PM_CORE_PWRSTST,
- * PM_DSS_PWRSTST, PM_EMU_PWRSTST, PM_GFX_PWRSTST, PM_IVAHD_PWRSTST,
- * PM_L3INIT_PWRSTST, PM_L4PER_PWRSTST, PM_MPU_PWRSTST, PM_TESLA_PWRSTST
- */
-#define OMAP4430_POWERSTATEST_SHIFT					0
-#define OMAP4430_POWERSTATEST_MASK					(0x3 << 0)
-
-/* Used by PRM_PWRREQCTRL */
-#define OMAP4430_PWRREQ_COND_SHIFT					0
-#define OMAP4430_PWRREQ_COND_MASK					(0x3 << 0)
-
-/* Used by PRM_VC_CFG_CHANNEL */
-#define OMAP4430_RACEN_VDD_CORE_L_SHIFT					3
-#define OMAP4430_RACEN_VDD_CORE_L_MASK					(1 << 3)
-
-/* Used by PRM_VC_CFG_CHANNEL */
-#define OMAP4430_RACEN_VDD_IVA_L_SHIFT					11
-#define OMAP4430_RACEN_VDD_IVA_L_MASK					(1 << 11)
-
-/* Used by PRM_VC_CFG_CHANNEL */
-#define OMAP4430_RACEN_VDD_MPU_L_SHIFT					20
-#define OMAP4430_RACEN_VDD_MPU_L_MASK					(1 << 20)
-
-/* Used by PRM_VC_CFG_CHANNEL */
-#define OMAP4430_RAC_VDD_CORE_L_SHIFT					2
-#define OMAP4430_RAC_VDD_CORE_L_MASK					(1 << 2)
-
-/* Used by PRM_VC_CFG_CHANNEL */
-#define OMAP4430_RAC_VDD_IVA_L_SHIFT					10
-#define OMAP4430_RAC_VDD_IVA_L_MASK					(1 << 10)
-
-/* Used by PRM_VC_CFG_CHANNEL */
-#define OMAP4430_RAC_VDD_MPU_L_SHIFT					19
-#define OMAP4430_RAC_VDD_MPU_L_MASK					(1 << 19)
-
-/*
- * Used by PRM_VOLTSETUP_CORE_OFF, PRM_VOLTSETUP_CORE_RET_SLEEP,
- * PRM_VOLTSETUP_IVA_OFF, PRM_VOLTSETUP_IVA_RET_SLEEP, PRM_VOLTSETUP_MPU_OFF,
- * PRM_VOLTSETUP_MPU_RET_SLEEP
- */
 #define OMAP4430_RAMP_DOWN_COUNT_SHIFT					16
-#define OMAP4430_RAMP_DOWN_COUNT_MASK					(0x3f << 16)
-
-/*
- * Used by PRM_VOLTSETUP_CORE_OFF, PRM_VOLTSETUP_CORE_RET_SLEEP,
- * PRM_VOLTSETUP_IVA_OFF, PRM_VOLTSETUP_IVA_RET_SLEEP, PRM_VOLTSETUP_MPU_OFF,
- * PRM_VOLTSETUP_MPU_RET_SLEEP
- */
-#define OMAP4430_RAMP_DOWN_PRESCAL_SHIFT				24
-#define OMAP4430_RAMP_DOWN_PRESCAL_MASK					(0x3 << 24)
-
-/*
- * Used by PRM_VOLTSETUP_CORE_OFF, PRM_VOLTSETUP_CORE_RET_SLEEP,
- * PRM_VOLTSETUP_IVA_OFF, PRM_VOLTSETUP_IVA_RET_SLEEP, PRM_VOLTSETUP_MPU_OFF,
- * PRM_VOLTSETUP_MPU_RET_SLEEP
- */
 #define OMAP4430_RAMP_UP_COUNT_SHIFT					0
-#define OMAP4430_RAMP_UP_COUNT_MASK					(0x3f << 0)
-
-/*
- * Used by PRM_VOLTSETUP_CORE_OFF, PRM_VOLTSETUP_CORE_RET_SLEEP,
- * PRM_VOLTSETUP_IVA_OFF, PRM_VOLTSETUP_IVA_RET_SLEEP, PRM_VOLTSETUP_MPU_OFF,
- * PRM_VOLTSETUP_MPU_RET_SLEEP
- */
 #define OMAP4430_RAMP_UP_PRESCAL_SHIFT					8
-#define OMAP4430_RAMP_UP_PRESCAL_MASK					(0x3 << 8)
-
-/* Used by PRM_VC_CFG_CHANNEL */
-#define OMAP4430_RAV_VDD_CORE_L_SHIFT					1
-#define OMAP4430_RAV_VDD_CORE_L_MASK					(1 << 1)
-
-/* Used by PRM_VC_CFG_CHANNEL */
-#define OMAP4430_RAV_VDD_IVA_L_SHIFT					9
-#define OMAP4430_RAV_VDD_IVA_L_MASK					(1 << 9)
-
-/* Used by PRM_VC_CFG_CHANNEL */
-#define OMAP4430_RAV_VDD_MPU_L_SHIFT					18
-#define OMAP4430_RAV_VDD_MPU_L_MASK					(1 << 18)
-
-/* Used by PRM_VC_VAL_BYPASS */
 #define OMAP4430_REGADDR_SHIFT						8
-#define OMAP4430_REGADDR_MASK						(0xff << 8)
-
-/*
- * Used by PRM_VC_VAL_CMD_VDD_CORE_L, PRM_VC_VAL_CMD_VDD_IVA_L,
- * PRM_VC_VAL_CMD_VDD_MPU_L
- */
 #define OMAP4430_RET_SHIFT						8
-#define OMAP4430_RET_MASK						(0xff << 8)
-
-/* Used by PM_L4PER_PWRSTCTRL */
-#define OMAP4430_RETAINED_BANK_ONSTATE_SHIFT				16
-#define OMAP4430_RETAINED_BANK_ONSTATE_MASK				(0x3 << 16)
-
-/* Used by PM_L4PER_PWRSTCTRL */
-#define OMAP4430_RETAINED_BANK_RETSTATE_SHIFT				8
-#define OMAP4430_RETAINED_BANK_RETSTATE_MASK				(1 << 8)
-
-/* Used by PM_L4PER_PWRSTST */
-#define OMAP4430_RETAINED_BANK_STATEST_SHIFT				4
-#define OMAP4430_RETAINED_BANK_STATEST_MASK				(0x3 << 4)
-
-/*
- * Used by PRM_LDO_SRAM_CORE_CTRL, PRM_LDO_SRAM_IVA_CTRL,
- * PRM_LDO_SRAM_MPU_CTRL
- */
-#define OMAP4430_RETMODE_ENABLE_SHIFT					0
-#define OMAP4430_RETMODE_ENABLE_MASK					(1 << 0)
-
-/* Used by RM_DUCATI_RSTCTRL, RM_IVAHD_RSTCTRL, RM_TESLA_RSTCTRL */
-#define OMAP4430_RST1_SHIFT						0
-#define OMAP4430_RST1_MASK						(1 << 0)
-
-/* Used by RM_DUCATI_RSTST, RM_IVAHD_RSTST, RM_TESLA_RSTST */
-#define OMAP4430_RST1ST_SHIFT						0
-#define OMAP4430_RST1ST_MASK						(1 << 0)
-
-/* Used by RM_DUCATI_RSTCTRL, RM_IVAHD_RSTCTRL, RM_TESLA_RSTCTRL */
-#define OMAP4430_RST2_SHIFT						1
-#define OMAP4430_RST2_MASK						(1 << 1)
-
-/* Used by RM_DUCATI_RSTST, RM_IVAHD_RSTST, RM_TESLA_RSTST */
-#define OMAP4430_RST2ST_SHIFT						1
-#define OMAP4430_RST2ST_MASK						(1 << 1)
-
-/* Used by RM_DUCATI_RSTCTRL, RM_IVAHD_RSTCTRL */
-#define OMAP4430_RST3_SHIFT						2
-#define OMAP4430_RST3_MASK						(1 << 2)
-
-/* Used by RM_DUCATI_RSTST, RM_IVAHD_RSTST */
-#define OMAP4430_RST3ST_SHIFT						2
-#define OMAP4430_RST3ST_MASK						(1 << 2)
-
-/* Used by PRM_RSTTIME */
-#define OMAP4430_RSTTIME1_SHIFT						0
-#define OMAP4430_RSTTIME1_MASK						(0x3ff << 0)
-
-/* Used by PRM_RSTTIME */
-#define OMAP4430_RSTTIME2_SHIFT						10
-#define OMAP4430_RSTTIME2_MASK						(0x1f << 10)
-
-/* Used by PRM_RSTCTRL */
-#define OMAP4430_RST_GLOBAL_COLD_SW_SHIFT				1
-#define OMAP4430_RST_GLOBAL_COLD_SW_MASK				(1 << 1)
-
-/* Used by PRM_RSTCTRL */
-#define OMAP4430_RST_GLOBAL_WARM_SW_SHIFT				0
 #define OMAP4430_RST_GLOBAL_WARM_SW_MASK				(1 << 0)
-
-/* Used by REVISION_PRM */
-#define OMAP4430_R_RTL_SHIFT						11
-#define OMAP4430_R_RTL_MASK						(0x1f << 11)
-
-/* Used by PRM_VC_CFG_CHANNEL */
 #define OMAP4430_SA_VDD_CORE_L_SHIFT					0
-#define OMAP4430_SA_VDD_CORE_L_MASK					(1 << 0)
-
-/* Renamed from SA_VDD_CORE_L Used by PRM_VC_SMPS_SA */
-#define OMAP4430_SA_VDD_CORE_L_0_6_SHIFT				0
 #define OMAP4430_SA_VDD_CORE_L_0_6_MASK					(0x7f << 0)
-
-/* Used by PRM_VC_CFG_CHANNEL */
 #define OMAP4430_SA_VDD_IVA_L_SHIFT					8
-#define OMAP4430_SA_VDD_IVA_L_MASK					(1 << 8)
-
-/* Renamed from SA_VDD_IVA_L Used by PRM_VC_SMPS_SA */
-#define OMAP4430_SA_VDD_IVA_L_PRM_VC_SMPS_SA_SHIFT			8
 #define OMAP4430_SA_VDD_IVA_L_PRM_VC_SMPS_SA_MASK			(0x7f << 8)
-
-/* Used by PRM_VC_CFG_CHANNEL */
 #define OMAP4430_SA_VDD_MPU_L_SHIFT					16
-#define OMAP4430_SA_VDD_MPU_L_MASK					(1 << 16)
-
-/* Renamed from SA_VDD_MPU_L Used by PRM_VC_SMPS_SA */
-#define OMAP4430_SA_VDD_MPU_L_PRM_VC_SMPS_SA_SHIFT			16
 #define OMAP4430_SA_VDD_MPU_L_PRM_VC_SMPS_SA_MASK			(0x7f << 16)
-
-/* Used by REVISION_PRM */
-#define OMAP4430_SCHEME_SHIFT						30
-#define OMAP4430_SCHEME_MASK						(0x3 << 30)
-
-/* Used by PRM_VC_CFG_I2C_CLK */
 #define OMAP4430_SCLH_SHIFT						0
-#define OMAP4430_SCLH_MASK						(0xff << 0)
-
-/* Used by PRM_VC_CFG_I2C_CLK */
 #define OMAP4430_SCLL_SHIFT						8
-#define OMAP4430_SCLL_MASK						(0xff << 8)
-
-/* Used by PRM_RSTST */
 #define OMAP4430_SECURE_WDT_RST_SHIFT					4
-#define OMAP4430_SECURE_WDT_RST_MASK					(1 << 4)
-
-/* Used by PM_IVAHD_PWRSTCTRL */
-#define OMAP4430_SL2_MEM_ONSTATE_SHIFT					18
-#define OMAP4430_SL2_MEM_ONSTATE_MASK					(0x3 << 18)
-
-/* Used by PM_IVAHD_PWRSTCTRL */
-#define OMAP4430_SL2_MEM_RETSTATE_SHIFT					9
-#define OMAP4430_SL2_MEM_RETSTATE_MASK					(1 << 9)
-
-/* Used by PM_IVAHD_PWRSTST */
-#define OMAP4430_SL2_MEM_STATEST_SHIFT					6
-#define OMAP4430_SL2_MEM_STATEST_MASK					(0x3 << 6)
-
-/* Used by PRM_VC_VAL_BYPASS */
 #define OMAP4430_SLAVEADDR_SHIFT					0
-#define OMAP4430_SLAVEADDR_MASK						(0x7f << 0)
-
-/* Used by PRM_LDO_ABB_IVA_SETUP, PRM_LDO_ABB_MPU_SETUP */
-#define OMAP4430_SLEEP_RBB_SEL_SHIFT					3
-#define OMAP4430_SLEEP_RBB_SEL_MASK					(1 << 3)
-
-/* Used by PRM_SRAM_COUNT */
-#define OMAP4430_SLPCNT_VALUE_SHIFT					16
-#define OMAP4430_SLPCNT_VALUE_MASK					(0xff << 16)
-
-/* Used by PRM_VP_CORE_VSTEPMAX, PRM_VP_IVA_VSTEPMAX, PRM_VP_MPU_VSTEPMAX */
 #define OMAP4430_SMPSWAITTIMEMAX_SHIFT					8
-#define OMAP4430_SMPSWAITTIMEMAX_MASK					(0xffff << 8)
-
-/* Used by PRM_VP_CORE_VSTEPMIN, PRM_VP_IVA_VSTEPMIN, PRM_VP_MPU_VSTEPMIN */
 #define OMAP4430_SMPSWAITTIMEMIN_SHIFT					8
-#define OMAP4430_SMPSWAITTIMEMIN_MASK					(0xffff << 8)
-
-/* Used by PRM_VC_ERRST */
-#define OMAP4430_SMPS_RA_ERR_CORE_SHIFT					1
-#define OMAP4430_SMPS_RA_ERR_CORE_MASK					(1 << 1)
-
-/* Used by PRM_VC_ERRST */
-#define OMAP4430_SMPS_RA_ERR_IVA_SHIFT					9
-#define OMAP4430_SMPS_RA_ERR_IVA_MASK					(1 << 9)
-
-/* Used by PRM_VC_ERRST */
-#define OMAP4430_SMPS_RA_ERR_MPU_SHIFT					17
-#define OMAP4430_SMPS_RA_ERR_MPU_MASK					(1 << 17)
-
-/* Used by PRM_VC_ERRST */
-#define OMAP4430_SMPS_SA_ERR_CORE_SHIFT					0
-#define OMAP4430_SMPS_SA_ERR_CORE_MASK					(1 << 0)
-
-/* Used by PRM_VC_ERRST */
-#define OMAP4430_SMPS_SA_ERR_IVA_SHIFT					8
-#define OMAP4430_SMPS_SA_ERR_IVA_MASK					(1 << 8)
-
-/* Used by PRM_VC_ERRST */
-#define OMAP4430_SMPS_SA_ERR_MPU_SHIFT					16
-#define OMAP4430_SMPS_SA_ERR_MPU_MASK					(1 << 16)
-
-/* Used by PRM_VC_ERRST */
-#define OMAP4430_SMPS_TIMEOUT_ERR_CORE_SHIFT				2
-#define OMAP4430_SMPS_TIMEOUT_ERR_CORE_MASK				(1 << 2)
-
-/* Used by PRM_VC_ERRST */
-#define OMAP4430_SMPS_TIMEOUT_ERR_IVA_SHIFT				10
-#define OMAP4430_SMPS_TIMEOUT_ERR_IVA_MASK				(1 << 10)
-
-/* Used by PRM_VC_ERRST */
-#define OMAP4430_SMPS_TIMEOUT_ERR_MPU_SHIFT				18
-#define OMAP4430_SMPS_TIMEOUT_ERR_MPU_MASK				(1 << 18)
-
-/* Used by PRM_LDO_ABB_IVA_SETUP, PRM_LDO_ABB_MPU_SETUP */
-#define OMAP4430_SR2EN_SHIFT						0
-#define OMAP4430_SR2EN_MASK						(1 << 0)
-
-/* Used by PRM_LDO_ABB_IVA_CTRL, PRM_LDO_ABB_MPU_CTRL */
-#define OMAP4430_SR2_IN_TRANSITION_SHIFT				6
-#define OMAP4430_SR2_IN_TRANSITION_MASK					(1 << 6)
-
-/* Used by PRM_LDO_ABB_IVA_CTRL, PRM_LDO_ABB_MPU_CTRL */
-#define OMAP4430_SR2_STATUS_SHIFT					3
-#define OMAP4430_SR2_STATUS_MASK					(0x3 << 3)
-
-/* Used by PRM_LDO_ABB_IVA_SETUP, PRM_LDO_ABB_MPU_SETUP */
-#define OMAP4430_SR2_WTCNT_VALUE_SHIFT					8
-#define OMAP4430_SR2_WTCNT_VALUE_MASK					(0xff << 8)
-
-/*
- * Used by PRM_LDO_SRAM_CORE_CTRL, PRM_LDO_SRAM_IVA_CTRL,
- * PRM_LDO_SRAM_MPU_CTRL
- */
-#define OMAP4430_SRAMLDO_STATUS_SHIFT					8
-#define OMAP4430_SRAMLDO_STATUS_MASK					(1 << 8)
-
-/*
- * Used by PRM_LDO_SRAM_CORE_CTRL, PRM_LDO_SRAM_IVA_CTRL,
- * PRM_LDO_SRAM_MPU_CTRL
- */
-#define OMAP4430_SRAM_IN_TRANSITION_SHIFT				9
-#define OMAP4430_SRAM_IN_TRANSITION_MASK				(1 << 9)
-
-/* Used by PRM_VC_CFG_I2C_MODE */
-#define OMAP4430_SRMODEEN_SHIFT						4
-#define OMAP4430_SRMODEEN_MASK						(1 << 4)
-
-/* Used by PRM_VOLTSETUP_WARMRESET */
-#define OMAP4430_STABLE_COUNT_SHIFT					0
-#define OMAP4430_STABLE_COUNT_MASK					(0x3f << 0)
-
-/* Used by PRM_VOLTSETUP_WARMRESET */
-#define OMAP4430_STABLE_PRESCAL_SHIFT					8
-#define OMAP4430_STABLE_PRESCAL_MASK					(0x3 << 8)
-
-/* Used by PRM_LDO_BANDGAP_SETUP */
-#define OMAP4430_STARTUP_COUNT_SHIFT					0
-#define OMAP4430_STARTUP_COUNT_MASK					(0xff << 0)
-
-/* Renamed from STARTUP_COUNT Used by PRM_SRAM_COUNT */
-#define OMAP4430_STARTUP_COUNT_24_31_SHIFT				24
-#define OMAP4430_STARTUP_COUNT_24_31_MASK				(0xff << 24)
-
-/* Used by PM_IVAHD_PWRSTCTRL */
-#define OMAP4430_TCM1_MEM_ONSTATE_SHIFT					20
-#define OMAP4430_TCM1_MEM_ONSTATE_MASK					(0x3 << 20)
-
-/* Used by PM_IVAHD_PWRSTCTRL */
-#define OMAP4430_TCM1_MEM_RETSTATE_SHIFT				10
-#define OMAP4430_TCM1_MEM_RETSTATE_MASK					(1 << 10)
-
-/* Used by PM_IVAHD_PWRSTST */
-#define OMAP4430_TCM1_MEM_STATEST_SHIFT					8
-#define OMAP4430_TCM1_MEM_STATEST_MASK					(0x3 << 8)
-
-/* Used by PM_IVAHD_PWRSTCTRL */
-#define OMAP4430_TCM2_MEM_ONSTATE_SHIFT					22
-#define OMAP4430_TCM2_MEM_ONSTATE_MASK					(0x3 << 22)
-
-/* Used by PM_IVAHD_PWRSTCTRL */
-#define OMAP4430_TCM2_MEM_RETSTATE_SHIFT				11
-#define OMAP4430_TCM2_MEM_RETSTATE_MASK					(1 << 11)
-
-/* Used by PM_IVAHD_PWRSTST */
-#define OMAP4430_TCM2_MEM_STATEST_SHIFT					10
-#define OMAP4430_TCM2_MEM_STATEST_MASK					(0x3 << 10)
-
-/* Used by RM_TESLA_RSTST */
-#define OMAP4430_TESLASS_EMU_RSTST_SHIFT				2
-#define OMAP4430_TESLASS_EMU_RSTST_MASK					(1 << 2)
-
-/* Used by RM_TESLA_RSTST */
-#define OMAP4430_TESLA_DSP_EMU_REQ_RSTST_SHIFT				3
-#define OMAP4430_TESLA_DSP_EMU_REQ_RSTST_MASK				(1 << 3)
-
-/* Used by PM_TESLA_PWRSTCTRL */
-#define OMAP4430_TESLA_EDMA_ONSTATE_SHIFT				20
-#define OMAP4430_TESLA_EDMA_ONSTATE_MASK				(0x3 << 20)
-
-/* Used by PM_TESLA_PWRSTCTRL */
-#define OMAP4430_TESLA_EDMA_RETSTATE_SHIFT				10
-#define OMAP4430_TESLA_EDMA_RETSTATE_MASK				(1 << 10)
-
-/* Used by PM_TESLA_PWRSTST */
-#define OMAP4430_TESLA_EDMA_STATEST_SHIFT				8
-#define OMAP4430_TESLA_EDMA_STATEST_MASK				(0x3 << 8)
-
-/* Used by PM_TESLA_PWRSTCTRL */
-#define OMAP4430_TESLA_L1_ONSTATE_SHIFT					16
-#define OMAP4430_TESLA_L1_ONSTATE_MASK					(0x3 << 16)
-
-/* Used by PM_TESLA_PWRSTCTRL */
-#define OMAP4430_TESLA_L1_RETSTATE_SHIFT				8
-#define OMAP4430_TESLA_L1_RETSTATE_MASK					(1 << 8)
-
-/* Used by PM_TESLA_PWRSTST */
-#define OMAP4430_TESLA_L1_STATEST_SHIFT					4
-#define OMAP4430_TESLA_L1_STATEST_MASK					(0x3 << 4)
-
-/* Used by PM_TESLA_PWRSTCTRL */
-#define OMAP4430_TESLA_L2_ONSTATE_SHIFT					18
-#define OMAP4430_TESLA_L2_ONSTATE_MASK					(0x3 << 18)
-
-/* Used by PM_TESLA_PWRSTCTRL */
-#define OMAP4430_TESLA_L2_RETSTATE_SHIFT				9
-#define OMAP4430_TESLA_L2_RETSTATE_MASK					(1 << 9)
-
-/* Used by PM_TESLA_PWRSTST */
-#define OMAP4430_TESLA_L2_STATEST_SHIFT					6
-#define OMAP4430_TESLA_L2_STATEST_MASK					(0x3 << 6)
-
-/* Used by PRM_VP_CORE_VLIMITTO, PRM_VP_IVA_VLIMITTO, PRM_VP_MPU_VLIMITTO */
 #define OMAP4430_TIMEOUT_SHIFT						0
-#define OMAP4430_TIMEOUT_MASK						(0xffff << 0)
-
-/* Used by PRM_VP_CORE_CONFIG, PRM_VP_IVA_CONFIG, PRM_VP_MPU_CONFIG */
-#define OMAP4430_TIMEOUTEN_SHIFT					3
 #define OMAP4430_TIMEOUTEN_MASK						(1 << 3)
-
-/* Used by PRM_IRQENABLE_DUCATI, PRM_IRQENABLE_MPU */
-#define OMAP4430_TRANSITION_EN_SHIFT					8
-#define OMAP4430_TRANSITION_EN_MASK					(1 << 8)
-
-/* Used by PRM_IRQSTATUS_DUCATI, PRM_IRQSTATUS_MPU */
-#define OMAP4430_TRANSITION_ST_SHIFT					8
-#define OMAP4430_TRANSITION_ST_MASK					(1 << 8)
-
-/* Used by PRM_VC_VAL_BYPASS */
-#define OMAP4430_VALID_SHIFT						24
 #define OMAP4430_VALID_MASK						(1 << 24)
-
-/* Used by PRM_IRQENABLE_DUCATI, PRM_IRQENABLE_MPU */
-#define OMAP4430_VC_BYPASSACK_EN_SHIFT					14
-#define OMAP4430_VC_BYPASSACK_EN_MASK					(1 << 14)
-
-/* Used by PRM_IRQSTATUS_DUCATI, PRM_IRQSTATUS_MPU */
-#define OMAP4430_VC_BYPASSACK_ST_SHIFT					14
-#define OMAP4430_VC_BYPASSACK_ST_MASK					(1 << 14)
-
-/* Used by PRM_IRQENABLE_DUCATI, PRM_IRQENABLE_MPU */
-#define OMAP4430_VC_CORE_VPACK_EN_SHIFT					22
-#define OMAP4430_VC_CORE_VPACK_EN_MASK					(1 << 22)
-
-/* Used by PRM_IRQSTATUS_DUCATI, PRM_IRQSTATUS_MPU */
-#define OMAP4430_VC_CORE_VPACK_ST_SHIFT					22
-#define OMAP4430_VC_CORE_VPACK_ST_MASK					(1 << 22)
-
-/* Used by PRM_IRQENABLE_DUCATI, PRM_IRQENABLE_MPU */
-#define OMAP4430_VC_IVA_VPACK_EN_SHIFT					30
-#define OMAP4430_VC_IVA_VPACK_EN_MASK					(1 << 30)
-
-/* Used by PRM_IRQSTATUS_DUCATI, PRM_IRQSTATUS_MPU */
-#define OMAP4430_VC_IVA_VPACK_ST_SHIFT					30
-#define OMAP4430_VC_IVA_VPACK_ST_MASK					(1 << 30)
-
-/* Used by PRM_IRQENABLE_MPU_2 */
-#define OMAP4430_VC_MPU_VPACK_EN_SHIFT					6
-#define OMAP4430_VC_MPU_VPACK_EN_MASK					(1 << 6)
-
-/* Used by PRM_IRQSTATUS_MPU_2 */
-#define OMAP4430_VC_MPU_VPACK_ST_SHIFT					6
-#define OMAP4430_VC_MPU_VPACK_ST_MASK					(1 << 6)
-
-/* Used by PRM_IRQENABLE_DUCATI, PRM_IRQENABLE_MPU */
-#define OMAP4430_VC_RAERR_EN_SHIFT					12
-#define OMAP4430_VC_RAERR_EN_MASK					(1 << 12)
-
-/* Used by PRM_IRQSTATUS_DUCATI, PRM_IRQSTATUS_MPU */
-#define OMAP4430_VC_RAERR_ST_SHIFT					12
-#define OMAP4430_VC_RAERR_ST_MASK					(1 << 12)
-
-/* Used by PRM_IRQENABLE_DUCATI, PRM_IRQENABLE_MPU */
-#define OMAP4430_VC_SAERR_EN_SHIFT					11
-#define OMAP4430_VC_SAERR_EN_MASK					(1 << 11)
-
-/* Used by PRM_IRQSTATUS_DUCATI, PRM_IRQSTATUS_MPU */
-#define OMAP4430_VC_SAERR_ST_SHIFT					11
-#define OMAP4430_VC_SAERR_ST_MASK					(1 << 11)
-
-/* Used by PRM_IRQENABLE_DUCATI, PRM_IRQENABLE_MPU */
-#define OMAP4430_VC_TOERR_EN_SHIFT					13
-#define OMAP4430_VC_TOERR_EN_MASK					(1 << 13)
-
-/* Used by PRM_IRQSTATUS_DUCATI, PRM_IRQSTATUS_MPU */
-#define OMAP4430_VC_TOERR_ST_SHIFT					13
-#define OMAP4430_VC_TOERR_ST_MASK					(1 << 13)
-
-/* Used by PRM_VP_CORE_VLIMITTO, PRM_VP_IVA_VLIMITTO, PRM_VP_MPU_VLIMITTO */
 #define OMAP4430_VDDMAX_SHIFT						24
-#define OMAP4430_VDDMAX_MASK						(0xff << 24)
-
-/* Used by PRM_VP_CORE_VLIMITTO, PRM_VP_IVA_VLIMITTO, PRM_VP_MPU_VLIMITTO */
 #define OMAP4430_VDDMIN_SHIFT						16
-#define OMAP4430_VDDMIN_MASK						(0xff << 16)
-
-/* Used by PRM_VOLTCTRL */
-#define OMAP4430_VDD_CORE_I2C_DISABLE_SHIFT				12
-#define OMAP4430_VDD_CORE_I2C_DISABLE_MASK				(1 << 12)
-
-/* Used by PRM_RSTST */
 #define OMAP4430_VDD_CORE_VOLT_MGR_RST_SHIFT				8
-#define OMAP4430_VDD_CORE_VOLT_MGR_RST_MASK				(1 << 8)
-
-/* Used by PRM_VOLTCTRL */
-#define OMAP4430_VDD_IVA_I2C_DISABLE_SHIFT				14
-#define OMAP4430_VDD_IVA_I2C_DISABLE_MASK				(1 << 14)
-
-/* Used by PRM_VOLTCTRL */
-#define OMAP4430_VDD_IVA_PRESENCE_SHIFT					9
-#define OMAP4430_VDD_IVA_PRESENCE_MASK					(1 << 9)
-
-/* Used by PRM_RSTST */
 #define OMAP4430_VDD_IVA_VOLT_MGR_RST_SHIFT				7
-#define OMAP4430_VDD_IVA_VOLT_MGR_RST_MASK				(1 << 7)
-
-/* Used by PRM_VOLTCTRL */
-#define OMAP4430_VDD_MPU_I2C_DISABLE_SHIFT				13
-#define OMAP4430_VDD_MPU_I2C_DISABLE_MASK				(1 << 13)
-
-/* Used by PRM_VOLTCTRL */
-#define OMAP4430_VDD_MPU_PRESENCE_SHIFT					8
-#define OMAP4430_VDD_MPU_PRESENCE_MASK					(1 << 8)
-
-/* Used by PRM_RSTST */
 #define OMAP4430_VDD_MPU_VOLT_MGR_RST_SHIFT				6
-#define OMAP4430_VDD_MPU_VOLT_MGR_RST_MASK				(1 << 6)
-
-/* Used by PRM_VC_ERRST */
-#define OMAP4430_VFSM_RA_ERR_CORE_SHIFT					4
-#define OMAP4430_VFSM_RA_ERR_CORE_MASK					(1 << 4)
-
-/* Used by PRM_VC_ERRST */
-#define OMAP4430_VFSM_RA_ERR_IVA_SHIFT					12
-#define OMAP4430_VFSM_RA_ERR_IVA_MASK					(1 << 12)
-
-/* Used by PRM_VC_ERRST */
-#define OMAP4430_VFSM_RA_ERR_MPU_SHIFT					20
-#define OMAP4430_VFSM_RA_ERR_MPU_MASK					(1 << 20)
-
-/* Used by PRM_VC_ERRST */
-#define OMAP4430_VFSM_SA_ERR_CORE_SHIFT					3
-#define OMAP4430_VFSM_SA_ERR_CORE_MASK					(1 << 3)
-
-/* Used by PRM_VC_ERRST */
-#define OMAP4430_VFSM_SA_ERR_IVA_SHIFT					11
-#define OMAP4430_VFSM_SA_ERR_IVA_MASK					(1 << 11)
-
-/* Used by PRM_VC_ERRST */
-#define OMAP4430_VFSM_SA_ERR_MPU_SHIFT					19
-#define OMAP4430_VFSM_SA_ERR_MPU_MASK					(1 << 19)
-
-/* Used by PRM_VC_ERRST */
-#define OMAP4430_VFSM_TIMEOUT_ERR_CORE_SHIFT				5
-#define OMAP4430_VFSM_TIMEOUT_ERR_CORE_MASK				(1 << 5)
-
-/* Used by PRM_VC_ERRST */
-#define OMAP4430_VFSM_TIMEOUT_ERR_IVA_SHIFT				13
-#define OMAP4430_VFSM_TIMEOUT_ERR_IVA_MASK				(1 << 13)
-
-/* Used by PRM_VC_ERRST */
-#define OMAP4430_VFSM_TIMEOUT_ERR_MPU_SHIFT				21
-#define OMAP4430_VFSM_TIMEOUT_ERR_MPU_MASK				(1 << 21)
-
-/* Used by PRM_VC_VAL_SMPS_RA_VOL */
-#define OMAP4430_VOLRA_VDD_CORE_L_SHIFT					0
 #define OMAP4430_VOLRA_VDD_CORE_L_MASK					(0xff << 0)
-
-/* Used by PRM_VC_VAL_SMPS_RA_VOL */
-#define OMAP4430_VOLRA_VDD_IVA_L_SHIFT					8
 #define OMAP4430_VOLRA_VDD_IVA_L_MASK					(0xff << 8)
-
-/* Used by PRM_VC_VAL_SMPS_RA_VOL */
-#define OMAP4430_VOLRA_VDD_MPU_L_SHIFT					16
 #define OMAP4430_VOLRA_VDD_MPU_L_MASK					(0xff << 16)
-
-/* Used by PRM_VP_CORE_CONFIG, PRM_VP_IVA_CONFIG, PRM_VP_MPU_CONFIG */
-#define OMAP4430_VPENABLE_SHIFT						0
 #define OMAP4430_VPENABLE_MASK						(1 << 0)
-
-/* Used by PRM_VP_CORE_STATUS, PRM_VP_IVA_STATUS, PRM_VP_MPU_STATUS */
-#define OMAP4430_VPINIDLE_SHIFT						0
-#define OMAP4430_VPINIDLE_MASK						(1 << 0)
-
-/* Used by PRM_VP_CORE_VOLTAGE, PRM_VP_IVA_VOLTAGE, PRM_VP_MPU_VOLTAGE */
-#define OMAP4430_VPVOLTAGE_SHIFT					0
 #define OMAP4430_VPVOLTAGE_MASK						(0xff << 0)
-
-/* Used by PRM_IRQENABLE_DUCATI, PRM_IRQENABLE_MPU */
-#define OMAP4430_VP_CORE_EQVALUE_EN_SHIFT				20
-#define OMAP4430_VP_CORE_EQVALUE_EN_MASK				(1 << 20)
-
-/* Used by PRM_IRQSTATUS_DUCATI, PRM_IRQSTATUS_MPU */
-#define OMAP4430_VP_CORE_EQVALUE_ST_SHIFT				20
-#define OMAP4430_VP_CORE_EQVALUE_ST_MASK				(1 << 20)
-
-/* Used by PRM_IRQENABLE_DUCATI, PRM_IRQENABLE_MPU */
-#define OMAP4430_VP_CORE_MAXVDD_EN_SHIFT				18
-#define OMAP4430_VP_CORE_MAXVDD_EN_MASK					(1 << 18)
-
-/* Used by PRM_IRQSTATUS_DUCATI, PRM_IRQSTATUS_MPU */
-#define OMAP4430_VP_CORE_MAXVDD_ST_SHIFT				18
-#define OMAP4430_VP_CORE_MAXVDD_ST_MASK					(1 << 18)
-
-/* Used by PRM_IRQENABLE_DUCATI, PRM_IRQENABLE_MPU */
-#define OMAP4430_VP_CORE_MINVDD_EN_SHIFT				17
-#define OMAP4430_VP_CORE_MINVDD_EN_MASK					(1 << 17)
-
-/* Used by PRM_IRQSTATUS_DUCATI, PRM_IRQSTATUS_MPU */
-#define OMAP4430_VP_CORE_MINVDD_ST_SHIFT				17
-#define OMAP4430_VP_CORE_MINVDD_ST_MASK					(1 << 17)
-
-/* Used by PRM_IRQENABLE_DUCATI, PRM_IRQENABLE_MPU */
-#define OMAP4430_VP_CORE_NOSMPSACK_EN_SHIFT				19
-#define OMAP4430_VP_CORE_NOSMPSACK_EN_MASK				(1 << 19)
-
-/* Used by PRM_IRQSTATUS_DUCATI, PRM_IRQSTATUS_MPU */
-#define OMAP4430_VP_CORE_NOSMPSACK_ST_SHIFT				19
-#define OMAP4430_VP_CORE_NOSMPSACK_ST_MASK				(1 << 19)
-
-/* Used by PRM_IRQENABLE_DUCATI, PRM_IRQENABLE_MPU */
-#define OMAP4430_VP_CORE_OPPCHANGEDONE_EN_SHIFT				16
-#define OMAP4430_VP_CORE_OPPCHANGEDONE_EN_MASK				(1 << 16)
-
-/* Used by PRM_IRQSTATUS_DUCATI, PRM_IRQSTATUS_MPU */
-#define OMAP4430_VP_CORE_OPPCHANGEDONE_ST_SHIFT				16
-#define OMAP4430_VP_CORE_OPPCHANGEDONE_ST_MASK				(1 << 16)
-
-/* Used by PRM_IRQENABLE_DUCATI, PRM_IRQENABLE_MPU */
-#define OMAP4430_VP_CORE_TRANXDONE_EN_SHIFT				21
-#define OMAP4430_VP_CORE_TRANXDONE_EN_MASK				(1 << 21)
-
-/* Used by PRM_IRQSTATUS_DUCATI, PRM_IRQSTATUS_MPU */
-#define OMAP4430_VP_CORE_TRANXDONE_ST_SHIFT				21
 #define OMAP4430_VP_CORE_TRANXDONE_ST_MASK				(1 << 21)
-
-/* Used by PRM_IRQENABLE_DUCATI, PRM_IRQENABLE_MPU */
-#define OMAP4430_VP_IVA_EQVALUE_EN_SHIFT				28
-#define OMAP4430_VP_IVA_EQVALUE_EN_MASK					(1 << 28)
-
-/* Used by PRM_IRQSTATUS_DUCATI, PRM_IRQSTATUS_MPU */
-#define OMAP4430_VP_IVA_EQVALUE_ST_SHIFT				28
-#define OMAP4430_VP_IVA_EQVALUE_ST_MASK					(1 << 28)
-
-/* Used by PRM_IRQENABLE_DUCATI, PRM_IRQENABLE_MPU */
-#define OMAP4430_VP_IVA_MAXVDD_EN_SHIFT					26
-#define OMAP4430_VP_IVA_MAXVDD_EN_MASK					(1 << 26)
-
-/* Used by PRM_IRQSTATUS_DUCATI, PRM_IRQSTATUS_MPU */
-#define OMAP4430_VP_IVA_MAXVDD_ST_SHIFT					26
-#define OMAP4430_VP_IVA_MAXVDD_ST_MASK					(1 << 26)
-
-/* Used by PRM_IRQENABLE_DUCATI, PRM_IRQENABLE_MPU */
-#define OMAP4430_VP_IVA_MINVDD_EN_SHIFT					25
-#define OMAP4430_VP_IVA_MINVDD_EN_MASK					(1 << 25)
-
-/* Used by PRM_IRQSTATUS_DUCATI, PRM_IRQSTATUS_MPU */
-#define OMAP4430_VP_IVA_MINVDD_ST_SHIFT					25
-#define OMAP4430_VP_IVA_MINVDD_ST_MASK					(1 << 25)
-
-/* Used by PRM_IRQENABLE_DUCATI, PRM_IRQENABLE_MPU */
-#define OMAP4430_VP_IVA_NOSMPSACK_EN_SHIFT				27
-#define OMAP4430_VP_IVA_NOSMPSACK_EN_MASK				(1 << 27)
-
-/* Used by PRM_IRQSTATUS_DUCATI, PRM_IRQSTATUS_MPU */
-#define OMAP4430_VP_IVA_NOSMPSACK_ST_SHIFT				27
-#define OMAP4430_VP_IVA_NOSMPSACK_ST_MASK				(1 << 27)
-
-/* Used by PRM_IRQENABLE_DUCATI, PRM_IRQENABLE_MPU */
-#define OMAP4430_VP_IVA_OPPCHANGEDONE_EN_SHIFT				24
-#define OMAP4430_VP_IVA_OPPCHANGEDONE_EN_MASK				(1 << 24)
-
-/* Used by PRM_IRQSTATUS_DUCATI, PRM_IRQSTATUS_MPU */
-#define OMAP4430_VP_IVA_OPPCHANGEDONE_ST_SHIFT				24
-#define OMAP4430_VP_IVA_OPPCHANGEDONE_ST_MASK				(1 << 24)
-
-/* Used by PRM_IRQENABLE_DUCATI, PRM_IRQENABLE_MPU */
-#define OMAP4430_VP_IVA_TRANXDONE_EN_SHIFT				29
-#define OMAP4430_VP_IVA_TRANXDONE_EN_MASK				(1 << 29)
-
-/* Used by PRM_IRQSTATUS_DUCATI, PRM_IRQSTATUS_MPU */
-#define OMAP4430_VP_IVA_TRANXDONE_ST_SHIFT				29
 #define OMAP4430_VP_IVA_TRANXDONE_ST_MASK				(1 << 29)
-
-/* Used by PRM_IRQENABLE_MPU_2 */
-#define OMAP4430_VP_MPU_EQVALUE_EN_SHIFT				4
-#define OMAP4430_VP_MPU_EQVALUE_EN_MASK					(1 << 4)
-
-/* Used by PRM_IRQSTATUS_MPU_2 */
-#define OMAP4430_VP_MPU_EQVALUE_ST_SHIFT				4
-#define OMAP4430_VP_MPU_EQVALUE_ST_MASK					(1 << 4)
-
-/* Used by PRM_IRQENABLE_MPU_2 */
-#define OMAP4430_VP_MPU_MAXVDD_EN_SHIFT					2
-#define OMAP4430_VP_MPU_MAXVDD_EN_MASK					(1 << 2)
-
-/* Used by PRM_IRQSTATUS_MPU_2 */
-#define OMAP4430_VP_MPU_MAXVDD_ST_SHIFT					2
-#define OMAP4430_VP_MPU_MAXVDD_ST_MASK					(1 << 2)
-
-/* Used by PRM_IRQENABLE_MPU_2 */
-#define OMAP4430_VP_MPU_MINVDD_EN_SHIFT					1
-#define OMAP4430_VP_MPU_MINVDD_EN_MASK					(1 << 1)
-
-/* Used by PRM_IRQSTATUS_MPU_2 */
-#define OMAP4430_VP_MPU_MINVDD_ST_SHIFT					1
-#define OMAP4430_VP_MPU_MINVDD_ST_MASK					(1 << 1)
-
-/* Used by PRM_IRQENABLE_MPU_2 */
-#define OMAP4430_VP_MPU_NOSMPSACK_EN_SHIFT				3
-#define OMAP4430_VP_MPU_NOSMPSACK_EN_MASK				(1 << 3)
-
-/* Used by PRM_IRQSTATUS_MPU_2 */
-#define OMAP4430_VP_MPU_NOSMPSACK_ST_SHIFT				3
-#define OMAP4430_VP_MPU_NOSMPSACK_ST_MASK				(1 << 3)
-
-/* Used by PRM_IRQENABLE_MPU_2 */
-#define OMAP4430_VP_MPU_OPPCHANGEDONE_EN_SHIFT				0
-#define OMAP4430_VP_MPU_OPPCHANGEDONE_EN_MASK				(1 << 0)
-
-/* Used by PRM_IRQSTATUS_MPU_2 */
-#define OMAP4430_VP_MPU_OPPCHANGEDONE_ST_SHIFT				0
-#define OMAP4430_VP_MPU_OPPCHANGEDONE_ST_MASK				(1 << 0)
-
-/* Used by PRM_IRQENABLE_MPU_2 */
-#define OMAP4430_VP_MPU_TRANXDONE_EN_SHIFT				5
-#define OMAP4430_VP_MPU_TRANXDONE_EN_MASK				(1 << 5)
-
-/* Used by PRM_IRQSTATUS_MPU_2 */
-#define OMAP4430_VP_MPU_TRANXDONE_ST_SHIFT				5
 #define OMAP4430_VP_MPU_TRANXDONE_ST_MASK				(1 << 5)
-
-/* Used by PRM_SRAM_COUNT */
-#define OMAP4430_VSETUPCNT_VALUE_SHIFT					8
-#define OMAP4430_VSETUPCNT_VALUE_MASK					(0xff << 8)
-
-/* Used by PRM_VP_CORE_VSTEPMAX, PRM_VP_IVA_VSTEPMAX, PRM_VP_MPU_VSTEPMAX */
 #define OMAP4430_VSTEPMAX_SHIFT						0
-#define OMAP4430_VSTEPMAX_MASK						(0xff << 0)
-
-/* Used by PRM_VP_CORE_VSTEPMIN, PRM_VP_IVA_VSTEPMIN, PRM_VP_MPU_VSTEPMIN */
 #define OMAP4430_VSTEPMIN_SHIFT						0
-#define OMAP4430_VSTEPMIN_MASK						(0xff << 0)
-
-/* Used by PRM_MODEM_IF_CTRL */
-#define OMAP4430_WAKE_MODEM_SHIFT					0
-#define OMAP4430_WAKE_MODEM_MASK					(1 << 0)
-
-/* Used by PM_DSS_DSS_WKDEP */
-#define OMAP4430_WKUPDEP_DISPC_DUCATI_SHIFT				1
-#define OMAP4430_WKUPDEP_DISPC_DUCATI_MASK				(1 << 1)
-
-/* Used by PM_DSS_DSS_WKDEP */
-#define OMAP4430_WKUPDEP_DISPC_MPU_SHIFT				0
-#define OMAP4430_WKUPDEP_DISPC_MPU_MASK					(1 << 0)
-
-/* Used by PM_DSS_DSS_WKDEP */
-#define OMAP4430_WKUPDEP_DISPC_SDMA_SHIFT				3
-#define OMAP4430_WKUPDEP_DISPC_SDMA_MASK				(1 << 3)
-
-/* Used by PM_DSS_DSS_WKDEP */
-#define OMAP4430_WKUPDEP_DISPC_TESLA_SHIFT				2
-#define OMAP4430_WKUPDEP_DISPC_TESLA_MASK				(1 << 2)
-
-/* Used by PM_ABE_DMIC_WKDEP */
-#define OMAP4430_WKUPDEP_DMIC_DMA_SDMA_SHIFT				7
-#define OMAP4430_WKUPDEP_DMIC_DMA_SDMA_MASK				(1 << 7)
-
-/* Used by PM_ABE_DMIC_WKDEP */
-#define OMAP4430_WKUPDEP_DMIC_DMA_TESLA_SHIFT				6
-#define OMAP4430_WKUPDEP_DMIC_DMA_TESLA_MASK				(1 << 6)
-
-/* Used by PM_ABE_DMIC_WKDEP */
-#define OMAP4430_WKUPDEP_DMIC_IRQ_MPU_SHIFT				0
-#define OMAP4430_WKUPDEP_DMIC_IRQ_MPU_MASK				(1 << 0)
-
-/* Used by PM_ABE_DMIC_WKDEP */
-#define OMAP4430_WKUPDEP_DMIC_IRQ_TESLA_SHIFT				2
-#define OMAP4430_WKUPDEP_DMIC_IRQ_TESLA_MASK				(1 << 2)
-
-/* Used by PM_L4PER_DMTIMER10_WKDEP */
-#define OMAP4430_WKUPDEP_DMTIMER10_MPU_SHIFT				0
-#define OMAP4430_WKUPDEP_DMTIMER10_MPU_MASK				(1 << 0)
-
-/* Used by PM_L4PER_DMTIMER11_WKDEP */
-#define OMAP4430_WKUPDEP_DMTIMER11_DUCATI_SHIFT				1
-#define OMAP4430_WKUPDEP_DMTIMER11_DUCATI_MASK				(1 << 1)
-
-/* Used by PM_L4PER_DMTIMER11_WKDEP */
-#define OMAP4430_WKUPDEP_DMTIMER11_MPU_SHIFT				0
-#define OMAP4430_WKUPDEP_DMTIMER11_MPU_MASK				(1 << 0)
-
-/* Used by PM_L4PER_DMTIMER2_WKDEP */
-#define OMAP4430_WKUPDEP_DMTIMER2_MPU_SHIFT				0
-#define OMAP4430_WKUPDEP_DMTIMER2_MPU_MASK				(1 << 0)
-
-/* Used by PM_L4PER_DMTIMER3_WKDEP */
-#define OMAP4430_WKUPDEP_DMTIMER3_DUCATI_SHIFT				1
-#define OMAP4430_WKUPDEP_DMTIMER3_DUCATI_MASK				(1 << 1)
-
-/* Used by PM_L4PER_DMTIMER3_WKDEP */
-#define OMAP4430_WKUPDEP_DMTIMER3_MPU_SHIFT				0
-#define OMAP4430_WKUPDEP_DMTIMER3_MPU_MASK				(1 << 0)
-
-/* Used by PM_L4PER_DMTIMER4_WKDEP */
-#define OMAP4430_WKUPDEP_DMTIMER4_DUCATI_SHIFT				1
-#define OMAP4430_WKUPDEP_DMTIMER4_DUCATI_MASK				(1 << 1)
-
-/* Used by PM_L4PER_DMTIMER4_WKDEP */
-#define OMAP4430_WKUPDEP_DMTIMER4_MPU_SHIFT				0
-#define OMAP4430_WKUPDEP_DMTIMER4_MPU_MASK				(1 << 0)
-
-/* Used by PM_L4PER_DMTIMER9_WKDEP */
-#define OMAP4430_WKUPDEP_DMTIMER9_DUCATI_SHIFT				1
-#define OMAP4430_WKUPDEP_DMTIMER9_DUCATI_MASK				(1 << 1)
-
-/* Used by PM_L4PER_DMTIMER9_WKDEP */
-#define OMAP4430_WKUPDEP_DMTIMER9_MPU_SHIFT				0
-#define OMAP4430_WKUPDEP_DMTIMER9_MPU_MASK				(1 << 0)
-
-/* Used by PM_DSS_DSS_WKDEP */
-#define OMAP4430_WKUPDEP_DSI1_DUCATI_SHIFT				5
-#define OMAP4430_WKUPDEP_DSI1_DUCATI_MASK				(1 << 5)
-
-/* Used by PM_DSS_DSS_WKDEP */
-#define OMAP4430_WKUPDEP_DSI1_MPU_SHIFT					4
-#define OMAP4430_WKUPDEP_DSI1_MPU_MASK					(1 << 4)
-
-/* Used by PM_DSS_DSS_WKDEP */
-#define OMAP4430_WKUPDEP_DSI1_SDMA_SHIFT				7
-#define OMAP4430_WKUPDEP_DSI1_SDMA_MASK					(1 << 7)
-
-/* Used by PM_DSS_DSS_WKDEP */
-#define OMAP4430_WKUPDEP_DSI1_TESLA_SHIFT				6
-#define OMAP4430_WKUPDEP_DSI1_TESLA_MASK				(1 << 6)
-
-/* Used by PM_DSS_DSS_WKDEP */
-#define OMAP4430_WKUPDEP_DSI2_DUCATI_SHIFT				9
-#define OMAP4430_WKUPDEP_DSI2_DUCATI_MASK				(1 << 9)
-
-/* Used by PM_DSS_DSS_WKDEP */
-#define OMAP4430_WKUPDEP_DSI2_MPU_SHIFT					8
-#define OMAP4430_WKUPDEP_DSI2_MPU_MASK					(1 << 8)
-
-/* Used by PM_DSS_DSS_WKDEP */
-#define OMAP4430_WKUPDEP_DSI2_SDMA_SHIFT				11
-#define OMAP4430_WKUPDEP_DSI2_SDMA_MASK					(1 << 11)
-
-/* Used by PM_DSS_DSS_WKDEP */
-#define OMAP4430_WKUPDEP_DSI2_TESLA_SHIFT				10
-#define OMAP4430_WKUPDEP_DSI2_TESLA_MASK				(1 << 10)
-
-/* Used by PM_WKUP_GPIO1_WKDEP */
-#define OMAP4430_WKUPDEP_GPIO1_IRQ1_DUCATI_SHIFT			1
-#define OMAP4430_WKUPDEP_GPIO1_IRQ1_DUCATI_MASK				(1 << 1)
-
-/* Used by PM_WKUP_GPIO1_WKDEP */
-#define OMAP4430_WKUPDEP_GPIO1_IRQ1_MPU_SHIFT				0
-#define OMAP4430_WKUPDEP_GPIO1_IRQ1_MPU_MASK				(1 << 0)
-
-/* Used by PM_WKUP_GPIO1_WKDEP */
-#define OMAP4430_WKUPDEP_GPIO1_IRQ2_TESLA_SHIFT				6
-#define OMAP4430_WKUPDEP_GPIO1_IRQ2_TESLA_MASK				(1 << 6)
-
-/* Used by PM_L4PER_GPIO2_WKDEP */
-#define OMAP4430_WKUPDEP_GPIO2_IRQ1_DUCATI_SHIFT			1
-#define OMAP4430_WKUPDEP_GPIO2_IRQ1_DUCATI_MASK				(1 << 1)
-
-/* Used by PM_L4PER_GPIO2_WKDEP */
-#define OMAP4430_WKUPDEP_GPIO2_IRQ1_MPU_SHIFT				0
-#define OMAP4430_WKUPDEP_GPIO2_IRQ1_MPU_MASK				(1 << 0)
-
-/* Used by PM_L4PER_GPIO2_WKDEP */
-#define OMAP4430_WKUPDEP_GPIO2_IRQ2_TESLA_SHIFT				6
-#define OMAP4430_WKUPDEP_GPIO2_IRQ2_TESLA_MASK				(1 << 6)
-
-/* Used by PM_L4PER_GPIO3_WKDEP */
-#define OMAP4430_WKUPDEP_GPIO3_IRQ1_MPU_SHIFT				0
-#define OMAP4430_WKUPDEP_GPIO3_IRQ1_MPU_MASK				(1 << 0)
-
-/* Used by PM_L4PER_GPIO3_WKDEP */
-#define OMAP4430_WKUPDEP_GPIO3_IRQ2_TESLA_SHIFT				6
-#define OMAP4430_WKUPDEP_GPIO3_IRQ2_TESLA_MASK				(1 << 6)
-
-/* Used by PM_L4PER_GPIO4_WKDEP */
-#define OMAP4430_WKUPDEP_GPIO4_IRQ1_MPU_SHIFT				0
-#define OMAP4430_WKUPDEP_GPIO4_IRQ1_MPU_MASK				(1 << 0)
-
-/* Used by PM_L4PER_GPIO4_WKDEP */
-#define OMAP4430_WKUPDEP_GPIO4_IRQ2_TESLA_SHIFT				6
-#define OMAP4430_WKUPDEP_GPIO4_IRQ2_TESLA_MASK				(1 << 6)
-
-/* Used by PM_L4PER_GPIO5_WKDEP */
-#define OMAP4430_WKUPDEP_GPIO5_IRQ1_MPU_SHIFT				0
-#define OMAP4430_WKUPDEP_GPIO5_IRQ1_MPU_MASK				(1 << 0)
-
-/* Used by PM_L4PER_GPIO5_WKDEP */
-#define OMAP4430_WKUPDEP_GPIO5_IRQ2_TESLA_SHIFT				6
-#define OMAP4430_WKUPDEP_GPIO5_IRQ2_TESLA_MASK				(1 << 6)
-
-/* Used by PM_L4PER_GPIO6_WKDEP */
-#define OMAP4430_WKUPDEP_GPIO6_IRQ1_MPU_SHIFT				0
-#define OMAP4430_WKUPDEP_GPIO6_IRQ1_MPU_MASK				(1 << 0)
-
-/* Used by PM_L4PER_GPIO6_WKDEP */
-#define OMAP4430_WKUPDEP_GPIO6_IRQ2_TESLA_SHIFT				6
-#define OMAP4430_WKUPDEP_GPIO6_IRQ2_TESLA_MASK				(1 << 6)
-
-/* Used by PM_DSS_DSS_WKDEP */
-#define OMAP4430_WKUPDEP_HDMIDMA_SDMA_SHIFT				19
-#define OMAP4430_WKUPDEP_HDMIDMA_SDMA_MASK				(1 << 19)
-
-/* Used by PM_DSS_DSS_WKDEP */
-#define OMAP4430_WKUPDEP_HDMIIRQ_DUCATI_SHIFT				13
-#define OMAP4430_WKUPDEP_HDMIIRQ_DUCATI_MASK				(1 << 13)
-
-/* Used by PM_DSS_DSS_WKDEP */
-#define OMAP4430_WKUPDEP_HDMIIRQ_MPU_SHIFT				12
-#define OMAP4430_WKUPDEP_HDMIIRQ_MPU_MASK				(1 << 12)
-
-/* Used by PM_DSS_DSS_WKDEP */
-#define OMAP4430_WKUPDEP_HDMIIRQ_TESLA_SHIFT				14
-#define OMAP4430_WKUPDEP_HDMIIRQ_TESLA_MASK				(1 << 14)
-
-/* Used by PM_L4PER_HECC1_WKDEP */
-#define OMAP4430_WKUPDEP_HECC1_MPU_SHIFT				0
-#define OMAP4430_WKUPDEP_HECC1_MPU_MASK					(1 << 0)
-
-/* Used by PM_L4PER_HECC2_WKDEP */
-#define OMAP4430_WKUPDEP_HECC2_MPU_SHIFT				0
-#define OMAP4430_WKUPDEP_HECC2_MPU_MASK					(1 << 0)
-
-/* Used by PM_L3INIT_HSI_WKDEP */
-#define OMAP4430_WKUPDEP_HSI_DSP_TESLA_SHIFT				6
-#define OMAP4430_WKUPDEP_HSI_DSP_TESLA_MASK				(1 << 6)
-
-/* Used by PM_L3INIT_HSI_WKDEP */
-#define OMAP4430_WKUPDEP_HSI_MCU_DUCATI_SHIFT				1
-#define OMAP4430_WKUPDEP_HSI_MCU_DUCATI_MASK				(1 << 1)
-
-/* Used by PM_L3INIT_HSI_WKDEP */
-#define OMAP4430_WKUPDEP_HSI_MCU_MPU_SHIFT				0
-#define OMAP4430_WKUPDEP_HSI_MCU_MPU_MASK				(1 << 0)
-
-/* Used by PM_L4PER_I2C1_WKDEP */
-#define OMAP4430_WKUPDEP_I2C1_DMA_SDMA_SHIFT				7
-#define OMAP4430_WKUPDEP_I2C1_DMA_SDMA_MASK				(1 << 7)
-
-/* Used by PM_L4PER_I2C1_WKDEP */
-#define OMAP4430_WKUPDEP_I2C1_IRQ_DUCATI_SHIFT				1
-#define OMAP4430_WKUPDEP_I2C1_IRQ_DUCATI_MASK				(1 << 1)
-
-/* Used by PM_L4PER_I2C1_WKDEP */
-#define OMAP4430_WKUPDEP_I2C1_IRQ_MPU_SHIFT				0
-#define OMAP4430_WKUPDEP_I2C1_IRQ_MPU_MASK				(1 << 0)
-
-/* Used by PM_L4PER_I2C2_WKDEP */
-#define OMAP4430_WKUPDEP_I2C2_DMA_SDMA_SHIFT				7
-#define OMAP4430_WKUPDEP_I2C2_DMA_SDMA_MASK				(1 << 7)
-
-/* Used by PM_L4PER_I2C2_WKDEP */
-#define OMAP4430_WKUPDEP_I2C2_IRQ_DUCATI_SHIFT				1
-#define OMAP4430_WKUPDEP_I2C2_IRQ_DUCATI_MASK				(1 << 1)
-
-/* Used by PM_L4PER_I2C2_WKDEP */
-#define OMAP4430_WKUPDEP_I2C2_IRQ_MPU_SHIFT				0
-#define OMAP4430_WKUPDEP_I2C2_IRQ_MPU_MASK				(1 << 0)
-
-/* Used by PM_L4PER_I2C3_WKDEP */
-#define OMAP4430_WKUPDEP_I2C3_DMA_SDMA_SHIFT				7
-#define OMAP4430_WKUPDEP_I2C3_DMA_SDMA_MASK				(1 << 7)
-
-/* Used by PM_L4PER_I2C3_WKDEP */
-#define OMAP4430_WKUPDEP_I2C3_IRQ_DUCATI_SHIFT				1
-#define OMAP4430_WKUPDEP_I2C3_IRQ_DUCATI_MASK				(1 << 1)
-
-/* Used by PM_L4PER_I2C3_WKDEP */
-#define OMAP4430_WKUPDEP_I2C3_IRQ_MPU_SHIFT				0
-#define OMAP4430_WKUPDEP_I2C3_IRQ_MPU_MASK				(1 << 0)
-
-/* Used by PM_L4PER_I2C4_WKDEP */
-#define OMAP4430_WKUPDEP_I2C4_DMA_SDMA_SHIFT				7
-#define OMAP4430_WKUPDEP_I2C4_DMA_SDMA_MASK				(1 << 7)
-
-/* Used by PM_L4PER_I2C4_WKDEP */
-#define OMAP4430_WKUPDEP_I2C4_IRQ_DUCATI_SHIFT				1
-#define OMAP4430_WKUPDEP_I2C4_IRQ_DUCATI_MASK				(1 << 1)
-
-/* Used by PM_L4PER_I2C4_WKDEP */
-#define OMAP4430_WKUPDEP_I2C4_IRQ_MPU_SHIFT				0
-#define OMAP4430_WKUPDEP_I2C4_IRQ_MPU_MASK				(1 << 0)
-
-/* Used by PM_L4PER_I2C5_WKDEP */
-#define OMAP4430_WKUPDEP_I2C5_DMA_SDMA_SHIFT				7
-#define OMAP4430_WKUPDEP_I2C5_DMA_SDMA_MASK				(1 << 7)
-
-/* Used by PM_L4PER_I2C5_WKDEP */
-#define OMAP4430_WKUPDEP_I2C5_IRQ_MPU_SHIFT				0
-#define OMAP4430_WKUPDEP_I2C5_IRQ_MPU_MASK				(1 << 0)
-
-/* Used by PM_WKUP_KEYBOARD_WKDEP */
-#define OMAP4430_WKUPDEP_KEYBOARD_MPU_SHIFT				0
-#define OMAP4430_WKUPDEP_KEYBOARD_MPU_MASK				(1 << 0)
-
-/* Used by PM_ABE_MCASP_WKDEP */
-#define OMAP4430_WKUPDEP_MCASP1_DMA_SDMA_SHIFT				7
-#define OMAP4430_WKUPDEP_MCASP1_DMA_SDMA_MASK				(1 << 7)
-
-/* Used by PM_ABE_MCASP_WKDEP */
-#define OMAP4430_WKUPDEP_MCASP1_DMA_TESLA_SHIFT				6
-#define OMAP4430_WKUPDEP_MCASP1_DMA_TESLA_MASK				(1 << 6)
-
-/* Used by PM_ABE_MCASP_WKDEP */
-#define OMAP4430_WKUPDEP_MCASP1_IRQ_MPU_SHIFT				0
-#define OMAP4430_WKUPDEP_MCASP1_IRQ_MPU_MASK				(1 << 0)
-
-/* Used by PM_ABE_MCASP_WKDEP */
-#define OMAP4430_WKUPDEP_MCASP1_IRQ_TESLA_SHIFT				2
-#define OMAP4430_WKUPDEP_MCASP1_IRQ_TESLA_MASK				(1 << 2)
-
-/* Used by PM_L4PER_MCASP2_WKDEP */
-#define OMAP4430_WKUPDEP_MCASP2_DMA_SDMA_SHIFT				7
-#define OMAP4430_WKUPDEP_MCASP2_DMA_SDMA_MASK				(1 << 7)
-
-/* Used by PM_L4PER_MCASP2_WKDEP */
-#define OMAP4430_WKUPDEP_MCASP2_DMA_TESLA_SHIFT				6
-#define OMAP4430_WKUPDEP_MCASP2_DMA_TESLA_MASK				(1 << 6)
-
-/* Used by PM_L4PER_MCASP2_WKDEP */
-#define OMAP4430_WKUPDEP_MCASP2_IRQ_MPU_SHIFT				0
-#define OMAP4430_WKUPDEP_MCASP2_IRQ_MPU_MASK				(1 << 0)
-
-/* Used by PM_L4PER_MCASP2_WKDEP */
-#define OMAP4430_WKUPDEP_MCASP2_IRQ_TESLA_SHIFT				2
-#define OMAP4430_WKUPDEP_MCASP2_IRQ_TESLA_MASK				(1 << 2)
-
-/* Used by PM_L4PER_MCASP3_WKDEP */
-#define OMAP4430_WKUPDEP_MCASP3_DMA_SDMA_SHIFT				7
-#define OMAP4430_WKUPDEP_MCASP3_DMA_SDMA_MASK				(1 << 7)
-
-/* Used by PM_L4PER_MCASP3_WKDEP */
-#define OMAP4430_WKUPDEP_MCASP3_DMA_TESLA_SHIFT				6
-#define OMAP4430_WKUPDEP_MCASP3_DMA_TESLA_MASK				(1 << 6)
-
-/* Used by PM_L4PER_MCASP3_WKDEP */
-#define OMAP4430_WKUPDEP_MCASP3_IRQ_MPU_SHIFT				0
-#define OMAP4430_WKUPDEP_MCASP3_IRQ_MPU_MASK				(1 << 0)
-
-/* Used by PM_L4PER_MCASP3_WKDEP */
-#define OMAP4430_WKUPDEP_MCASP3_IRQ_TESLA_SHIFT				2
-#define OMAP4430_WKUPDEP_MCASP3_IRQ_TESLA_MASK				(1 << 2)
-
-/* Used by PM_ABE_MCBSP1_WKDEP */
-#define OMAP4430_WKUPDEP_MCBSP1_MPU_SHIFT				0
-#define OMAP4430_WKUPDEP_MCBSP1_MPU_MASK				(1 << 0)
-
-/* Used by PM_ABE_MCBSP1_WKDEP */
-#define OMAP4430_WKUPDEP_MCBSP1_SDMA_SHIFT				3
-#define OMAP4430_WKUPDEP_MCBSP1_SDMA_MASK				(1 << 3)
-
-/* Used by PM_ABE_MCBSP1_WKDEP */
-#define OMAP4430_WKUPDEP_MCBSP1_TESLA_SHIFT				2
-#define OMAP4430_WKUPDEP_MCBSP1_TESLA_MASK				(1 << 2)
-
-/* Used by PM_ABE_MCBSP2_WKDEP */
-#define OMAP4430_WKUPDEP_MCBSP2_MPU_SHIFT				0
-#define OMAP4430_WKUPDEP_MCBSP2_MPU_MASK				(1 << 0)
-
-/* Used by PM_ABE_MCBSP2_WKDEP */
-#define OMAP4430_WKUPDEP_MCBSP2_SDMA_SHIFT				3
-#define OMAP4430_WKUPDEP_MCBSP2_SDMA_MASK				(1 << 3)
-
-/* Used by PM_ABE_MCBSP2_WKDEP */
-#define OMAP4430_WKUPDEP_MCBSP2_TESLA_SHIFT				2
-#define OMAP4430_WKUPDEP_MCBSP2_TESLA_MASK				(1 << 2)
-
-/* Used by PM_ABE_MCBSP3_WKDEP */
-#define OMAP4430_WKUPDEP_MCBSP3_MPU_SHIFT				0
-#define OMAP4430_WKUPDEP_MCBSP3_MPU_MASK				(1 << 0)
-
-/* Used by PM_ABE_MCBSP3_WKDEP */
-#define OMAP4430_WKUPDEP_MCBSP3_SDMA_SHIFT				3
-#define OMAP4430_WKUPDEP_MCBSP3_SDMA_MASK				(1 << 3)
-
-/* Used by PM_ABE_MCBSP3_WKDEP */
-#define OMAP4430_WKUPDEP_MCBSP3_TESLA_SHIFT				2
-#define OMAP4430_WKUPDEP_MCBSP3_TESLA_MASK				(1 << 2)
-
-/* Used by PM_L4PER_MCBSP4_WKDEP */
-#define OMAP4430_WKUPDEP_MCBSP4_MPU_SHIFT				0
-#define OMAP4430_WKUPDEP_MCBSP4_MPU_MASK				(1 << 0)
-
-/* Used by PM_L4PER_MCBSP4_WKDEP */
-#define OMAP4430_WKUPDEP_MCBSP4_SDMA_SHIFT				3
-#define OMAP4430_WKUPDEP_MCBSP4_SDMA_MASK				(1 << 3)
-
-/* Used by PM_L4PER_MCBSP4_WKDEP */
-#define OMAP4430_WKUPDEP_MCBSP4_TESLA_SHIFT				2
-#define OMAP4430_WKUPDEP_MCBSP4_TESLA_MASK				(1 << 2)
-
-/* Used by PM_L4PER_MCSPI1_WKDEP */
-#define OMAP4430_WKUPDEP_MCSPI1_DUCATI_SHIFT				1
-#define OMAP4430_WKUPDEP_MCSPI1_DUCATI_MASK				(1 << 1)
-
-/* Used by PM_L4PER_MCSPI1_WKDEP */
-#define OMAP4430_WKUPDEP_MCSPI1_MPU_SHIFT				0
-#define OMAP4430_WKUPDEP_MCSPI1_MPU_MASK				(1 << 0)
-
-/* Used by PM_L4PER_MCSPI1_WKDEP */
-#define OMAP4430_WKUPDEP_MCSPI1_SDMA_SHIFT				3
-#define OMAP4430_WKUPDEP_MCSPI1_SDMA_MASK				(1 << 3)
-
-/* Used by PM_L4PER_MCSPI1_WKDEP */
-#define OMAP4430_WKUPDEP_MCSPI1_TESLA_SHIFT				2
-#define OMAP4430_WKUPDEP_MCSPI1_TESLA_MASK				(1 << 2)
-
-/* Used by PM_L4PER_MCSPI2_WKDEP */
-#define OMAP4430_WKUPDEP_MCSPI2_DUCATI_SHIFT				1
-#define OMAP4430_WKUPDEP_MCSPI2_DUCATI_MASK				(1 << 1)
-
-/* Used by PM_L4PER_MCSPI2_WKDEP */
-#define OMAP4430_WKUPDEP_MCSPI2_MPU_SHIFT				0
-#define OMAP4430_WKUPDEP_MCSPI2_MPU_MASK				(1 << 0)
-
-/* Used by PM_L4PER_MCSPI2_WKDEP */
-#define OMAP4430_WKUPDEP_MCSPI2_SDMA_SHIFT				3
-#define OMAP4430_WKUPDEP_MCSPI2_SDMA_MASK				(1 << 3)
-
-/* Used by PM_L4PER_MCSPI3_WKDEP */
-#define OMAP4430_WKUPDEP_MCSPI3_MPU_SHIFT				0
-#define OMAP4430_WKUPDEP_MCSPI3_MPU_MASK				(1 << 0)
-
-/* Used by PM_L4PER_MCSPI3_WKDEP */
-#define OMAP4430_WKUPDEP_MCSPI3_SDMA_SHIFT				3
-#define OMAP4430_WKUPDEP_MCSPI3_SDMA_MASK				(1 << 3)
-
-/* Used by PM_L4PER_MCSPI4_WKDEP */
-#define OMAP4430_WKUPDEP_MCSPI4_MPU_SHIFT				0
-#define OMAP4430_WKUPDEP_MCSPI4_MPU_MASK				(1 << 0)
-
-/* Used by PM_L4PER_MCSPI4_WKDEP */
-#define OMAP4430_WKUPDEP_MCSPI4_SDMA_SHIFT				3
-#define OMAP4430_WKUPDEP_MCSPI4_SDMA_MASK				(1 << 3)
-
-/* Used by PM_L3INIT_MMC1_WKDEP */
-#define OMAP4430_WKUPDEP_MMC1_DUCATI_SHIFT				1
-#define OMAP4430_WKUPDEP_MMC1_DUCATI_MASK				(1 << 1)
-
-/* Used by PM_L3INIT_MMC1_WKDEP */
-#define OMAP4430_WKUPDEP_MMC1_MPU_SHIFT					0
-#define OMAP4430_WKUPDEP_MMC1_MPU_MASK					(1 << 0)
-
-/* Used by PM_L3INIT_MMC1_WKDEP */
-#define OMAP4430_WKUPDEP_MMC1_SDMA_SHIFT				3
-#define OMAP4430_WKUPDEP_MMC1_SDMA_MASK					(1 << 3)
-
-/* Used by PM_L3INIT_MMC1_WKDEP */
-#define OMAP4430_WKUPDEP_MMC1_TESLA_SHIFT				2
-#define OMAP4430_WKUPDEP_MMC1_TESLA_MASK				(1 << 2)
-
-/* Used by PM_L3INIT_MMC2_WKDEP */
-#define OMAP4430_WKUPDEP_MMC2_DUCATI_SHIFT				1
-#define OMAP4430_WKUPDEP_MMC2_DUCATI_MASK				(1 << 1)
-
-/* Used by PM_L3INIT_MMC2_WKDEP */
-#define OMAP4430_WKUPDEP_MMC2_MPU_SHIFT					0
-#define OMAP4430_WKUPDEP_MMC2_MPU_MASK					(1 << 0)
-
-/* Used by PM_L3INIT_MMC2_WKDEP */
-#define OMAP4430_WKUPDEP_MMC2_SDMA_SHIFT				3
-#define OMAP4430_WKUPDEP_MMC2_SDMA_MASK					(1 << 3)
-
-/* Used by PM_L3INIT_MMC2_WKDEP */
-#define OMAP4430_WKUPDEP_MMC2_TESLA_SHIFT				2
-#define OMAP4430_WKUPDEP_MMC2_TESLA_MASK				(1 << 2)
-
-/* Used by PM_L3INIT_MMC6_WKDEP */
-#define OMAP4430_WKUPDEP_MMC6_DUCATI_SHIFT				1
-#define OMAP4430_WKUPDEP_MMC6_DUCATI_MASK				(1 << 1)
-
-/* Used by PM_L3INIT_MMC6_WKDEP */
-#define OMAP4430_WKUPDEP_MMC6_MPU_SHIFT					0
-#define OMAP4430_WKUPDEP_MMC6_MPU_MASK					(1 << 0)
-
-/* Used by PM_L3INIT_MMC6_WKDEP */
-#define OMAP4430_WKUPDEP_MMC6_TESLA_SHIFT				2
-#define OMAP4430_WKUPDEP_MMC6_TESLA_MASK				(1 << 2)
-
-/* Used by PM_L4PER_MMCSD3_WKDEP */
-#define OMAP4430_WKUPDEP_MMCSD3_DUCATI_SHIFT				1
-#define OMAP4430_WKUPDEP_MMCSD3_DUCATI_MASK				(1 << 1)
-
-/* Used by PM_L4PER_MMCSD3_WKDEP */
-#define OMAP4430_WKUPDEP_MMCSD3_MPU_SHIFT				0
-#define OMAP4430_WKUPDEP_MMCSD3_MPU_MASK				(1 << 0)
-
-/* Used by PM_L4PER_MMCSD3_WKDEP */
-#define OMAP4430_WKUPDEP_MMCSD3_SDMA_SHIFT				3
-#define OMAP4430_WKUPDEP_MMCSD3_SDMA_MASK				(1 << 3)
-
-/* Used by PM_L4PER_MMCSD4_WKDEP */
-#define OMAP4430_WKUPDEP_MMCSD4_DUCATI_SHIFT				1
-#define OMAP4430_WKUPDEP_MMCSD4_DUCATI_MASK				(1 << 1)
-
-/* Used by PM_L4PER_MMCSD4_WKDEP */
-#define OMAP4430_WKUPDEP_MMCSD4_MPU_SHIFT				0
-#define OMAP4430_WKUPDEP_MMCSD4_MPU_MASK				(1 << 0)
-
-/* Used by PM_L4PER_MMCSD4_WKDEP */
-#define OMAP4430_WKUPDEP_MMCSD4_SDMA_SHIFT				3
-#define OMAP4430_WKUPDEP_MMCSD4_SDMA_MASK				(1 << 3)
-
-/* Used by PM_L4PER_MMCSD5_WKDEP */
-#define OMAP4430_WKUPDEP_MMCSD5_DUCATI_SHIFT				1
-#define OMAP4430_WKUPDEP_MMCSD5_DUCATI_MASK				(1 << 1)
-
-/* Used by PM_L4PER_MMCSD5_WKDEP */
-#define OMAP4430_WKUPDEP_MMCSD5_MPU_SHIFT				0
-#define OMAP4430_WKUPDEP_MMCSD5_MPU_MASK				(1 << 0)
-
-/* Used by PM_L4PER_MMCSD5_WKDEP */
-#define OMAP4430_WKUPDEP_MMCSD5_SDMA_SHIFT				3
-#define OMAP4430_WKUPDEP_MMCSD5_SDMA_MASK				(1 << 3)
-
-/* Used by PM_L3INIT_PCIESS_WKDEP */
-#define OMAP4430_WKUPDEP_PCIESS_MPU_SHIFT				0
-#define OMAP4430_WKUPDEP_PCIESS_MPU_MASK				(1 << 0)
-
-/* Used by PM_L3INIT_PCIESS_WKDEP */
-#define OMAP4430_WKUPDEP_PCIESS_TESLA_SHIFT				2
-#define OMAP4430_WKUPDEP_PCIESS_TESLA_MASK				(1 << 2)
-
-/* Used by PM_ABE_PDM_WKDEP */
-#define OMAP4430_WKUPDEP_PDM_DMA_SDMA_SHIFT				7
-#define OMAP4430_WKUPDEP_PDM_DMA_SDMA_MASK				(1 << 7)
-
-/* Used by PM_ABE_PDM_WKDEP */
-#define OMAP4430_WKUPDEP_PDM_DMA_TESLA_SHIFT				6
-#define OMAP4430_WKUPDEP_PDM_DMA_TESLA_MASK				(1 << 6)
-
-/* Used by PM_ABE_PDM_WKDEP */
-#define OMAP4430_WKUPDEP_PDM_IRQ_MPU_SHIFT				0
-#define OMAP4430_WKUPDEP_PDM_IRQ_MPU_MASK				(1 << 0)
-
-/* Used by PM_ABE_PDM_WKDEP */
-#define OMAP4430_WKUPDEP_PDM_IRQ_TESLA_SHIFT				2
-#define OMAP4430_WKUPDEP_PDM_IRQ_TESLA_MASK				(1 << 2)
-
-/* Used by PM_WKUP_RTC_WKDEP */
-#define OMAP4430_WKUPDEP_RTC_MPU_SHIFT					0
-#define OMAP4430_WKUPDEP_RTC_MPU_MASK					(1 << 0)
-
-/* Used by PM_L3INIT_SATA_WKDEP */
-#define OMAP4430_WKUPDEP_SATA_MPU_SHIFT					0
-#define OMAP4430_WKUPDEP_SATA_MPU_MASK					(1 << 0)
-
-/* Used by PM_L3INIT_SATA_WKDEP */
-#define OMAP4430_WKUPDEP_SATA_TESLA_SHIFT				2
-#define OMAP4430_WKUPDEP_SATA_TESLA_MASK				(1 << 2)
-
-/* Used by PM_ABE_SLIMBUS_WKDEP */
-#define OMAP4430_WKUPDEP_SLIMBUS1_DMA_SDMA_SHIFT			7
-#define OMAP4430_WKUPDEP_SLIMBUS1_DMA_SDMA_MASK				(1 << 7)
-
-/* Used by PM_ABE_SLIMBUS_WKDEP */
-#define OMAP4430_WKUPDEP_SLIMBUS1_DMA_TESLA_SHIFT			6
-#define OMAP4430_WKUPDEP_SLIMBUS1_DMA_TESLA_MASK			(1 << 6)
-
-/* Used by PM_ABE_SLIMBUS_WKDEP */
-#define OMAP4430_WKUPDEP_SLIMBUS1_IRQ_MPU_SHIFT				0
-#define OMAP4430_WKUPDEP_SLIMBUS1_IRQ_MPU_MASK				(1 << 0)
-
-/* Used by PM_ABE_SLIMBUS_WKDEP */
-#define OMAP4430_WKUPDEP_SLIMBUS1_IRQ_TESLA_SHIFT			2
-#define OMAP4430_WKUPDEP_SLIMBUS1_IRQ_TESLA_MASK			(1 << 2)
-
-/* Used by PM_L4PER_SLIMBUS2_WKDEP */
-#define OMAP4430_WKUPDEP_SLIMBUS2_DMA_SDMA_SHIFT			7
-#define OMAP4430_WKUPDEP_SLIMBUS2_DMA_SDMA_MASK				(1 << 7)
-
-/* Used by PM_L4PER_SLIMBUS2_WKDEP */
-#define OMAP4430_WKUPDEP_SLIMBUS2_DMA_TESLA_SHIFT			6
-#define OMAP4430_WKUPDEP_SLIMBUS2_DMA_TESLA_MASK			(1 << 6)
-
-/* Used by PM_L4PER_SLIMBUS2_WKDEP */
-#define OMAP4430_WKUPDEP_SLIMBUS2_IRQ_MPU_SHIFT				0
-#define OMAP4430_WKUPDEP_SLIMBUS2_IRQ_MPU_MASK				(1 << 0)
-
-/* Used by PM_L4PER_SLIMBUS2_WKDEP */
-#define OMAP4430_WKUPDEP_SLIMBUS2_IRQ_TESLA_SHIFT			2
-#define OMAP4430_WKUPDEP_SLIMBUS2_IRQ_TESLA_MASK			(1 << 2)
-
-/* Used by PM_ALWON_SR_CORE_WKDEP */
-#define OMAP4430_WKUPDEP_SR_CORE_DUCATI_SHIFT				1
-#define OMAP4430_WKUPDEP_SR_CORE_DUCATI_MASK				(1 << 1)
-
-/* Used by PM_ALWON_SR_CORE_WKDEP */
-#define OMAP4430_WKUPDEP_SR_CORE_MPU_SHIFT				0
-#define OMAP4430_WKUPDEP_SR_CORE_MPU_MASK				(1 << 0)
-
-/* Used by PM_ALWON_SR_IVA_WKDEP */
-#define OMAP4430_WKUPDEP_SR_IVA_DUCATI_SHIFT				1
-#define OMAP4430_WKUPDEP_SR_IVA_DUCATI_MASK				(1 << 1)
-
-/* Used by PM_ALWON_SR_IVA_WKDEP */
-#define OMAP4430_WKUPDEP_SR_IVA_MPU_SHIFT				0
-#define OMAP4430_WKUPDEP_SR_IVA_MPU_MASK				(1 << 0)
-
-/* Used by PM_ALWON_SR_MPU_WKDEP */
-#define OMAP4430_WKUPDEP_SR_MPU_MPU_SHIFT				0
-#define OMAP4430_WKUPDEP_SR_MPU_MPU_MASK				(1 << 0)
-
-/* Used by PM_WKUP_TIMER12_WKDEP */
-#define OMAP4430_WKUPDEP_TIMER12_MPU_SHIFT				0
-#define OMAP4430_WKUPDEP_TIMER12_MPU_MASK				(1 << 0)
-
-/* Used by PM_WKUP_TIMER1_WKDEP */
-#define OMAP4430_WKUPDEP_TIMER1_MPU_SHIFT				0
-#define OMAP4430_WKUPDEP_TIMER1_MPU_MASK				(1 << 0)
-
-/* Used by PM_ABE_TIMER5_WKDEP */
-#define OMAP4430_WKUPDEP_TIMER5_MPU_SHIFT				0
-#define OMAP4430_WKUPDEP_TIMER5_MPU_MASK				(1 << 0)
-
-/* Used by PM_ABE_TIMER5_WKDEP */
-#define OMAP4430_WKUPDEP_TIMER5_TESLA_SHIFT				2
-#define OMAP4430_WKUPDEP_TIMER5_TESLA_MASK				(1 << 2)
-
-/* Used by PM_ABE_TIMER6_WKDEP */
-#define OMAP4430_WKUPDEP_TIMER6_MPU_SHIFT				0
-#define OMAP4430_WKUPDEP_TIMER6_MPU_MASK				(1 << 0)
-
-/* Used by PM_ABE_TIMER6_WKDEP */
-#define OMAP4430_WKUPDEP_TIMER6_TESLA_SHIFT				2
-#define OMAP4430_WKUPDEP_TIMER6_TESLA_MASK				(1 << 2)
-
-/* Used by PM_ABE_TIMER7_WKDEP */
-#define OMAP4430_WKUPDEP_TIMER7_MPU_SHIFT				0
-#define OMAP4430_WKUPDEP_TIMER7_MPU_MASK				(1 << 0)
-
-/* Used by PM_ABE_TIMER7_WKDEP */
-#define OMAP4430_WKUPDEP_TIMER7_TESLA_SHIFT				2
-#define OMAP4430_WKUPDEP_TIMER7_TESLA_MASK				(1 << 2)
-
-/* Used by PM_ABE_TIMER8_WKDEP */
-#define OMAP4430_WKUPDEP_TIMER8_MPU_SHIFT				0
-#define OMAP4430_WKUPDEP_TIMER8_MPU_MASK				(1 << 0)
-
-/* Used by PM_ABE_TIMER8_WKDEP */
-#define OMAP4430_WKUPDEP_TIMER8_TESLA_SHIFT				2
-#define OMAP4430_WKUPDEP_TIMER8_TESLA_MASK				(1 << 2)
-
-/* Used by PM_L4PER_UART1_WKDEP */
-#define OMAP4430_WKUPDEP_UART1_MPU_SHIFT				0
-#define OMAP4430_WKUPDEP_UART1_MPU_MASK					(1 << 0)
-
-/* Used by PM_L4PER_UART1_WKDEP */
-#define OMAP4430_WKUPDEP_UART1_SDMA_SHIFT				3
-#define OMAP4430_WKUPDEP_UART1_SDMA_MASK				(1 << 3)
-
-/* Used by PM_L4PER_UART2_WKDEP */
-#define OMAP4430_WKUPDEP_UART2_MPU_SHIFT				0
-#define OMAP4430_WKUPDEP_UART2_MPU_MASK					(1 << 0)
-
-/* Used by PM_L4PER_UART2_WKDEP */
-#define OMAP4430_WKUPDEP_UART2_SDMA_SHIFT				3
-#define OMAP4430_WKUPDEP_UART2_SDMA_MASK				(1 << 3)
-
-/* Used by PM_L4PER_UART3_WKDEP */
-#define OMAP4430_WKUPDEP_UART3_DUCATI_SHIFT				1
-#define OMAP4430_WKUPDEP_UART3_DUCATI_MASK				(1 << 1)
-
-/* Used by PM_L4PER_UART3_WKDEP */
-#define OMAP4430_WKUPDEP_UART3_MPU_SHIFT				0
-#define OMAP4430_WKUPDEP_UART3_MPU_MASK					(1 << 0)
-
-/* Used by PM_L4PER_UART3_WKDEP */
-#define OMAP4430_WKUPDEP_UART3_SDMA_SHIFT				3
-#define OMAP4430_WKUPDEP_UART3_SDMA_MASK				(1 << 3)
-
-/* Used by PM_L4PER_UART3_WKDEP */
-#define OMAP4430_WKUPDEP_UART3_TESLA_SHIFT				2
-#define OMAP4430_WKUPDEP_UART3_TESLA_MASK				(1 << 2)
-
-/* Used by PM_L4PER_UART4_WKDEP */
-#define OMAP4430_WKUPDEP_UART4_MPU_SHIFT				0
-#define OMAP4430_WKUPDEP_UART4_MPU_MASK					(1 << 0)
-
-/* Used by PM_L4PER_UART4_WKDEP */
-#define OMAP4430_WKUPDEP_UART4_SDMA_SHIFT				3
-#define OMAP4430_WKUPDEP_UART4_SDMA_MASK				(1 << 3)
-
-/* Used by PM_L3INIT_UNIPRO1_WKDEP */
-#define OMAP4430_WKUPDEP_UNIPRO1_DUCATI_SHIFT				1
-#define OMAP4430_WKUPDEP_UNIPRO1_DUCATI_MASK				(1 << 1)
-
-/* Used by PM_L3INIT_UNIPRO1_WKDEP */
-#define OMAP4430_WKUPDEP_UNIPRO1_MPU_SHIFT				0
-#define OMAP4430_WKUPDEP_UNIPRO1_MPU_MASK				(1 << 0)
-
-/* Used by PM_L3INIT_USB_HOST_WKDEP */
-#define OMAP4430_WKUPDEP_USB_HOST_DUCATI_SHIFT				1
-#define OMAP4430_WKUPDEP_USB_HOST_DUCATI_MASK				(1 << 1)
-
-/* Used by PM_L3INIT_USB_HOST_FS_WKDEP */
-#define OMAP4430_WKUPDEP_USB_HOST_FS_DUCATI_SHIFT			1
-#define OMAP4430_WKUPDEP_USB_HOST_FS_DUCATI_MASK			(1 << 1)
-
-/* Used by PM_L3INIT_USB_HOST_FS_WKDEP */
-#define OMAP4430_WKUPDEP_USB_HOST_FS_MPU_SHIFT				0
-#define OMAP4430_WKUPDEP_USB_HOST_FS_MPU_MASK				(1 << 0)
-
-/* Used by PM_L3INIT_USB_HOST_WKDEP */
-#define OMAP4430_WKUPDEP_USB_HOST_MPU_SHIFT				0
-#define OMAP4430_WKUPDEP_USB_HOST_MPU_MASK				(1 << 0)
-
-/* Used by PM_L3INIT_USB_OTG_WKDEP */
-#define OMAP4430_WKUPDEP_USB_OTG_DUCATI_SHIFT				1
-#define OMAP4430_WKUPDEP_USB_OTG_DUCATI_MASK				(1 << 1)
-
-/* Used by PM_L3INIT_USB_OTG_WKDEP */
-#define OMAP4430_WKUPDEP_USB_OTG_MPU_SHIFT				0
-#define OMAP4430_WKUPDEP_USB_OTG_MPU_MASK				(1 << 0)
-
-/* Used by PM_L3INIT_USB_TLL_WKDEP */
-#define OMAP4430_WKUPDEP_USB_TLL_DUCATI_SHIFT				1
-#define OMAP4430_WKUPDEP_USB_TLL_DUCATI_MASK				(1 << 1)
-
-/* Used by PM_L3INIT_USB_TLL_WKDEP */
-#define OMAP4430_WKUPDEP_USB_TLL_MPU_SHIFT				0
-#define OMAP4430_WKUPDEP_USB_TLL_MPU_MASK				(1 << 0)
-
-/* Used by PM_WKUP_USIM_WKDEP */
-#define OMAP4430_WKUPDEP_USIM_MPU_SHIFT					0
-#define OMAP4430_WKUPDEP_USIM_MPU_MASK					(1 << 0)
-
-/* Used by PM_WKUP_USIM_WKDEP */
-#define OMAP4430_WKUPDEP_USIM_SDMA_SHIFT				3
-#define OMAP4430_WKUPDEP_USIM_SDMA_MASK					(1 << 3)
-
-/* Used by PM_WKUP_WDT2_WKDEP */
-#define OMAP4430_WKUPDEP_WDT2_DUCATI_SHIFT				1
-#define OMAP4430_WKUPDEP_WDT2_DUCATI_MASK				(1 << 1)
-
-/* Used by PM_WKUP_WDT2_WKDEP */
-#define OMAP4430_WKUPDEP_WDT2_MPU_SHIFT					0
-#define OMAP4430_WKUPDEP_WDT2_MPU_MASK					(1 << 0)
-
-/* Used by PM_ABE_WDT3_WKDEP */
-#define OMAP4430_WKUPDEP_WDT3_MPU_SHIFT					0
-#define OMAP4430_WKUPDEP_WDT3_MPU_MASK					(1 << 0)
-
-/* Used by PM_L3INIT_HSI_WKDEP */
-#define OMAP4430_WKUPDEP_WGM_HSI_WAKE_MPU_SHIFT				8
-#define OMAP4430_WKUPDEP_WGM_HSI_WAKE_MPU_MASK				(1 << 8)
-
-/* Used by PM_L3INIT_XHPI_WKDEP */
-#define OMAP4430_WKUPDEP_XHPI_DUCATI_SHIFT				1
-#define OMAP4430_WKUPDEP_XHPI_DUCATI_MASK				(1 << 1)
-
-/* Used by PRM_IO_PMCTRL */
-#define OMAP4430_WUCLK_CTRL_SHIFT					8
 #define OMAP4430_WUCLK_CTRL_MASK					(1 << 8)
-
-/* Used by PRM_IO_PMCTRL */
 #define OMAP4430_WUCLK_STATUS_SHIFT					9
 #define OMAP4430_WUCLK_STATUS_MASK					(1 << 9)
-
-/* Used by REVISION_PRM */
-#define OMAP4430_X_MAJOR_SHIFT						8
-#define OMAP4430_X_MAJOR_MASK						(0x7 << 8)
-
-/* Used by REVISION_PRM */
-#define OMAP4430_Y_MINOR_SHIFT						0
-#define OMAP4430_Y_MINOR_MASK						(0x3f << 0)
 #endif
diff --git a/arch/arm/mach-omap2/prm-regbits-54xx.h b/arch/arm/mach-omap2/prm-regbits-54xx.h
deleted file mode 100644
index be31b21aa9c6..000000000000
--- a/arch/arm/mach-omap2/prm-regbits-54xx.h
+++ /dev/null
@@ -1,2701 +0,0 @@
-/*
- * OMAP54xx Power Management register bits
- *
- * Copyright (C) 2013 Texas Instruments Incorporated - http://www.ti.com
- *
- * Paul Walmsley (paul@pwsan.com)
- * Rajendra Nayak (rnayak@ti.com)
- * Benoit Cousson (b-cousson@ti.com)
- *
- * This file is automatically generated from the OMAP hardware databases.
- * We respectfully ask that any modifications to this file be coordinated
- * with the public linux-omap@vger.kernel.org mailing list and the
- * authors above to ensure that the autogeneration scripts are kept
- * up-to-date with the file contents.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef __ARCH_ARM_MACH_OMAP2_PRM_REGBITS_54XX_H
-#define __ARCH_ARM_MACH_OMAP2_PRM_REGBITS_54XX_H
-
-/* Used by PRM_SLDO_CORE_SETUP, PRM_SLDO_MM_SETUP, PRM_SLDO_MPU_SETUP */
-#define OMAP54XX_ABBOFF_ACT_SHIFT						1
-#define OMAP54XX_ABBOFF_ACT_WIDTH						0x1
-#define OMAP54XX_ABBOFF_ACT_MASK						(1 << 1)
-
-/* Used by PRM_SLDO_CORE_SETUP, PRM_SLDO_MM_SETUP, PRM_SLDO_MPU_SETUP */
-#define OMAP54XX_ABBOFF_SLEEP_SHIFT						2
-#define OMAP54XX_ABBOFF_SLEEP_WIDTH						0x1
-#define OMAP54XX_ABBOFF_SLEEP_MASK						(1 << 2)
-
-/* Used by PRM_IRQENABLE_IPU, PRM_IRQENABLE_MPU */
-#define OMAP54XX_ABB_MM_DONE_EN_SHIFT						31
-#define OMAP54XX_ABB_MM_DONE_EN_WIDTH						0x1
-#define OMAP54XX_ABB_MM_DONE_EN_MASK						(1 << 31)
-
-/* Used by PRM_IRQSTATUS_IPU, PRM_IRQSTATUS_MPU */
-#define OMAP54XX_ABB_MM_DONE_ST_SHIFT						31
-#define OMAP54XX_ABB_MM_DONE_ST_WIDTH						0x1
-#define OMAP54XX_ABB_MM_DONE_ST_MASK						(1 << 31)
-
-/* Used by PRM_IRQENABLE_MPU_2 */
-#define OMAP54XX_ABB_MPU_DONE_EN_SHIFT						7
-#define OMAP54XX_ABB_MPU_DONE_EN_WIDTH						0x1
-#define OMAP54XX_ABB_MPU_DONE_EN_MASK						(1 << 7)
-
-/* Used by PRM_IRQSTATUS_MPU_2 */
-#define OMAP54XX_ABB_MPU_DONE_ST_SHIFT						7
-#define OMAP54XX_ABB_MPU_DONE_ST_WIDTH						0x1
-#define OMAP54XX_ABB_MPU_DONE_ST_MASK						(1 << 7)
-
-/* Used by PRM_ABBLDO_MM_SETUP, PRM_ABBLDO_MPU_SETUP */
-#define OMAP54XX_ACTIVE_FBB_SEL_SHIFT						2
-#define OMAP54XX_ACTIVE_FBB_SEL_WIDTH						0x1
-#define OMAP54XX_ACTIVE_FBB_SEL_MASK						(1 << 2)
-
-/* Used by PM_ABE_PWRSTCTRL */
-#define OMAP54XX_AESSMEM_ONSTATE_SHIFT						16
-#define OMAP54XX_AESSMEM_ONSTATE_WIDTH						0x2
-#define OMAP54XX_AESSMEM_ONSTATE_MASK						(0x3 << 16)
-
-/* Used by PM_ABE_PWRSTCTRL */
-#define OMAP54XX_AESSMEM_RETSTATE_SHIFT						8
-#define OMAP54XX_AESSMEM_RETSTATE_WIDTH						0x1
-#define OMAP54XX_AESSMEM_RETSTATE_MASK						(1 << 8)
-
-/* Used by PM_ABE_PWRSTST */
-#define OMAP54XX_AESSMEM_STATEST_SHIFT						4
-#define OMAP54XX_AESSMEM_STATEST_WIDTH						0x2
-#define OMAP54XX_AESSMEM_STATEST_MASK						(0x3 << 4)
-
-/* Used by PRM_SLDO_CORE_SETUP, PRM_SLDO_MM_SETUP, PRM_SLDO_MPU_SETUP */
-#define OMAP54XX_AIPOFF_SHIFT							8
-#define OMAP54XX_AIPOFF_WIDTH							0x1
-#define OMAP54XX_AIPOFF_MASK							(1 << 8)
-
-/* Used by PRM_VOLTCTRL */
-#define OMAP54XX_AUTO_CTRL_VDD_CORE_L_SHIFT					0
-#define OMAP54XX_AUTO_CTRL_VDD_CORE_L_WIDTH					0x2
-#define OMAP54XX_AUTO_CTRL_VDD_CORE_L_MASK					(0x3 << 0)
-
-/* Used by PRM_VOLTCTRL */
-#define OMAP54XX_AUTO_CTRL_VDD_MM_L_SHIFT					4
-#define OMAP54XX_AUTO_CTRL_VDD_MM_L_WIDTH					0x2
-#define OMAP54XX_AUTO_CTRL_VDD_MM_L_MASK					(0x3 << 4)
-
-/* Used by PRM_VOLTCTRL */
-#define OMAP54XX_AUTO_CTRL_VDD_MPU_L_SHIFT					2
-#define OMAP54XX_AUTO_CTRL_VDD_MPU_L_WIDTH					0x2
-#define OMAP54XX_AUTO_CTRL_VDD_MPU_L_MASK					(0x3 << 2)
-
-/* Used by PRM_VC_BYPASS_ERRST */
-#define OMAP54XX_BYPS_RA_ERR_SHIFT						1
-#define OMAP54XX_BYPS_RA_ERR_WIDTH						0x1
-#define OMAP54XX_BYPS_RA_ERR_MASK						(1 << 1)
-
-/* Used by PRM_VC_BYPASS_ERRST */
-#define OMAP54XX_BYPS_SA_ERR_SHIFT						0
-#define OMAP54XX_BYPS_SA_ERR_WIDTH						0x1
-#define OMAP54XX_BYPS_SA_ERR_MASK						(1 << 0)
-
-/* Used by PRM_VC_BYPASS_ERRST */
-#define OMAP54XX_BYPS_TIMEOUT_ERR_SHIFT						2
-#define OMAP54XX_BYPS_TIMEOUT_ERR_WIDTH						0x1
-#define OMAP54XX_BYPS_TIMEOUT_ERR_MASK						(1 << 2)
-
-/* Used by PRM_RSTST */
-#define OMAP54XX_C2C_RST_SHIFT							10
-#define OMAP54XX_C2C_RST_WIDTH							0x1
-#define OMAP54XX_C2C_RST_MASK							(1 << 10)
-
-/* Used by PM_CAM_PWRSTCTRL */
-#define OMAP54XX_CAM_MEM_ONSTATE_SHIFT						16
-#define OMAP54XX_CAM_MEM_ONSTATE_WIDTH						0x2
-#define OMAP54XX_CAM_MEM_ONSTATE_MASK						(0x3 << 16)
-
-/* Used by PM_CAM_PWRSTST */
-#define OMAP54XX_CAM_MEM_STATEST_SHIFT						4
-#define OMAP54XX_CAM_MEM_STATEST_WIDTH						0x2
-#define OMAP54XX_CAM_MEM_STATEST_MASK						(0x3 << 4)
-
-/* Used by PRM_CLKREQCTRL */
-#define OMAP54XX_CLKREQ_COND_SHIFT						0
-#define OMAP54XX_CLKREQ_COND_WIDTH						0x3
-#define OMAP54XX_CLKREQ_COND_MASK						(0x7 << 0)
-
-/* Used by PRM_VC_SMPS_CORE_CONFIG */
-#define OMAP54XX_CMDRA_VDD_CORE_L_SHIFT						16
-#define OMAP54XX_CMDRA_VDD_CORE_L_WIDTH						0x8
-#define OMAP54XX_CMDRA_VDD_CORE_L_MASK						(0xff << 16)
-
-/* Used by PRM_VC_SMPS_MM_CONFIG */
-#define OMAP54XX_CMDRA_VDD_MM_L_SHIFT						16
-#define OMAP54XX_CMDRA_VDD_MM_L_WIDTH						0x8
-#define OMAP54XX_CMDRA_VDD_MM_L_MASK						(0xff << 16)
-
-/* Used by PRM_VC_SMPS_MPU_CONFIG */
-#define OMAP54XX_CMDRA_VDD_MPU_L_SHIFT						16
-#define OMAP54XX_CMDRA_VDD_MPU_L_WIDTH						0x8
-#define OMAP54XX_CMDRA_VDD_MPU_L_MASK						(0xff << 16)
-
-/* Used by PRM_VC_SMPS_CORE_CONFIG */
-#define OMAP54XX_CMD_VDD_CORE_L_SHIFT						28
-#define OMAP54XX_CMD_VDD_CORE_L_WIDTH						0x1
-#define OMAP54XX_CMD_VDD_CORE_L_MASK						(1 << 28)
-
-/* Used by PRM_VC_SMPS_MM_CONFIG */
-#define OMAP54XX_CMD_VDD_MM_L_SHIFT						28
-#define OMAP54XX_CMD_VDD_MM_L_WIDTH						0x1
-#define OMAP54XX_CMD_VDD_MM_L_MASK						(1 << 28)
-
-/* Used by PRM_VC_SMPS_MPU_CONFIG */
-#define OMAP54XX_CMD_VDD_MPU_L_SHIFT						28
-#define OMAP54XX_CMD_VDD_MPU_L_WIDTH						0x1
-#define OMAP54XX_CMD_VDD_MPU_L_MASK						(1 << 28)
-
-/* Used by PM_CORE_PWRSTCTRL */
-#define OMAP54XX_CORE_OCMRAM_ONSTATE_SHIFT					18
-#define OMAP54XX_CORE_OCMRAM_ONSTATE_WIDTH					0x2
-#define OMAP54XX_CORE_OCMRAM_ONSTATE_MASK					(0x3 << 18)
-
-/* Used by PM_CORE_PWRSTCTRL */
-#define OMAP54XX_CORE_OCMRAM_RETSTATE_SHIFT					9
-#define OMAP54XX_CORE_OCMRAM_RETSTATE_WIDTH					0x1
-#define OMAP54XX_CORE_OCMRAM_RETSTATE_MASK					(1 << 9)
-
-/* Used by PM_CORE_PWRSTST */
-#define OMAP54XX_CORE_OCMRAM_STATEST_SHIFT					6
-#define OMAP54XX_CORE_OCMRAM_STATEST_WIDTH					0x2
-#define OMAP54XX_CORE_OCMRAM_STATEST_MASK					(0x3 << 6)
-
-/* Used by PM_CORE_PWRSTCTRL */
-#define OMAP54XX_CORE_OTHER_BANK_ONSTATE_SHIFT					16
-#define OMAP54XX_CORE_OTHER_BANK_ONSTATE_WIDTH					0x2
-#define OMAP54XX_CORE_OTHER_BANK_ONSTATE_MASK					(0x3 << 16)
-
-/* Used by PM_CORE_PWRSTCTRL */
-#define OMAP54XX_CORE_OTHER_BANK_RETSTATE_SHIFT					8
-#define OMAP54XX_CORE_OTHER_BANK_RETSTATE_WIDTH					0x1
-#define OMAP54XX_CORE_OTHER_BANK_RETSTATE_MASK					(1 << 8)
-
-/* Used by PM_CORE_PWRSTST */
-#define OMAP54XX_CORE_OTHER_BANK_STATEST_SHIFT					4
-#define OMAP54XX_CORE_OTHER_BANK_STATEST_WIDTH					0x2
-#define OMAP54XX_CORE_OTHER_BANK_STATEST_MASK					(0x3 << 4)
-
-/* Used by REVISION_PRM */
-#define OMAP54XX_CUSTOM_SHIFT							6
-#define OMAP54XX_CUSTOM_WIDTH							0x2
-#define OMAP54XX_CUSTOM_MASK							(0x3 << 6)
-
-/* Used by PRM_VC_VAL_BYPASS */
-#define OMAP54XX_DATA_SHIFT							16
-#define OMAP54XX_DATA_WIDTH							0x8
-#define OMAP54XX_DATA_MASK							(0xff << 16)
-
-/* Used by PRM_DEBUG_CORE_RET_TRANS */
-#define OMAP54XX_PRM_DEBUG_OUT_SHIFT						0
-#define OMAP54XX_PRM_DEBUG_OUT_WIDTH						0x1c
-#define OMAP54XX_PRM_DEBUG_OUT_MASK						(0xfffffff << 0)
-
-/* Renamed from DEBUG_OUT Used by PRM_DEBUG_MM_RET_TRANS */
-#define OMAP54XX_DEBUG_OUT_0_9_SHIFT						0
-#define OMAP54XX_DEBUG_OUT_0_9_WIDTH						0xa
-#define OMAP54XX_DEBUG_OUT_0_9_MASK						(0x3ff << 0)
-
-/* Renamed from DEBUG_OUT Used by PRM_DEBUG_MPU_RET_TRANS */
-#define OMAP54XX_DEBUG_OUT_0_6_SHIFT						0
-#define OMAP54XX_DEBUG_OUT_0_6_WIDTH						0x7
-#define OMAP54XX_DEBUG_OUT_0_6_MASK						(0x7f << 0)
-
-/* Renamed from DEBUG_OUT Used by PRM_DEBUG_OFF_TRANS */
-#define OMAP54XX_DEBUG_OUT_0_31_SHIFT						0
-#define OMAP54XX_DEBUG_OUT_0_31_WIDTH						0x20
-#define OMAP54XX_DEBUG_OUT_0_31_MASK						(0xffffffff << 0)
-
-/* Renamed from DEBUG_OUT Used by PRM_DEBUG_WKUPAON_FD_TRANS */
-#define OMAP54XX_DEBUG_OUT_0_11_SHIFT						0
-#define OMAP54XX_DEBUG_OUT_0_11_WIDTH						0xc
-#define OMAP54XX_DEBUG_OUT_0_11_MASK						(0xfff << 0)
-
-/* Used by PRM_DEVICE_OFF_CTRL */
-#define OMAP54XX_DEVICE_OFF_ENABLE_SHIFT					0
-#define OMAP54XX_DEVICE_OFF_ENABLE_WIDTH					0x1
-#define OMAP54XX_DEVICE_OFF_ENABLE_MASK						(1 << 0)
-
-/* Used by PRM_VC_CFG_I2C_MODE */
-#define OMAP54XX_DFILTEREN_SHIFT						6
-#define OMAP54XX_DFILTEREN_WIDTH						0x1
-#define OMAP54XX_DFILTEREN_MASK							(1 << 6)
-
-/* Used by PRM_IRQENABLE_DSP, PRM_IRQENABLE_IPU, PRM_IRQENABLE_MPU */
-#define OMAP54XX_DPLL_ABE_RECAL_EN_SHIFT					4
-#define OMAP54XX_DPLL_ABE_RECAL_EN_WIDTH					0x1
-#define OMAP54XX_DPLL_ABE_RECAL_EN_MASK						(1 << 4)
-
-/* Used by PRM_IRQSTATUS_DSP, PRM_IRQSTATUS_IPU, PRM_IRQSTATUS_MPU */
-#define OMAP54XX_DPLL_ABE_RECAL_ST_SHIFT					4
-#define OMAP54XX_DPLL_ABE_RECAL_ST_WIDTH					0x1
-#define OMAP54XX_DPLL_ABE_RECAL_ST_MASK						(1 << 4)
-
-/* Used by PRM_IRQENABLE_IPU, PRM_IRQENABLE_MPU */
-#define OMAP54XX_DPLL_CORE_RECAL_EN_SHIFT					0
-#define OMAP54XX_DPLL_CORE_RECAL_EN_WIDTH					0x1
-#define OMAP54XX_DPLL_CORE_RECAL_EN_MASK					(1 << 0)
-
-/* Used by PRM_IRQSTATUS_IPU, PRM_IRQSTATUS_MPU */
-#define OMAP54XX_DPLL_CORE_RECAL_ST_SHIFT					0
-#define OMAP54XX_DPLL_CORE_RECAL_ST_WIDTH					0x1
-#define OMAP54XX_DPLL_CORE_RECAL_ST_MASK					(1 << 0)
-
-/* Used by PRM_IRQENABLE_DSP, PRM_IRQENABLE_IPU, PRM_IRQENABLE_MPU */
-#define OMAP54XX_DPLL_IVA_RECAL_EN_SHIFT					2
-#define OMAP54XX_DPLL_IVA_RECAL_EN_WIDTH					0x1
-#define OMAP54XX_DPLL_IVA_RECAL_EN_MASK						(1 << 2)
-
-/* Used by PRM_IRQSTATUS_DSP, PRM_IRQSTATUS_IPU, PRM_IRQSTATUS_MPU */
-#define OMAP54XX_DPLL_IVA_RECAL_ST_SHIFT					2
-#define OMAP54XX_DPLL_IVA_RECAL_ST_WIDTH					0x1
-#define OMAP54XX_DPLL_IVA_RECAL_ST_MASK						(1 << 2)
-
-/* Used by PRM_IRQENABLE_MPU */
-#define OMAP54XX_DPLL_MPU_RECAL_EN_SHIFT					1
-#define OMAP54XX_DPLL_MPU_RECAL_EN_WIDTH					0x1
-#define OMAP54XX_DPLL_MPU_RECAL_EN_MASK						(1 << 1)
-
-/* Used by PRM_IRQSTATUS_MPU */
-#define OMAP54XX_DPLL_MPU_RECAL_ST_SHIFT					1
-#define OMAP54XX_DPLL_MPU_RECAL_ST_WIDTH					0x1
-#define OMAP54XX_DPLL_MPU_RECAL_ST_MASK						(1 << 1)
-
-/* Used by PRM_IRQENABLE_IPU, PRM_IRQENABLE_MPU */
-#define OMAP54XX_DPLL_PER_RECAL_EN_SHIFT					3
-#define OMAP54XX_DPLL_PER_RECAL_EN_WIDTH					0x1
-#define OMAP54XX_DPLL_PER_RECAL_EN_MASK						(1 << 3)
-
-/* Used by PRM_IRQSTATUS_IPU, PRM_IRQSTATUS_MPU */
-#define OMAP54XX_DPLL_PER_RECAL_ST_SHIFT					3
-#define OMAP54XX_DPLL_PER_RECAL_ST_WIDTH					0x1
-#define OMAP54XX_DPLL_PER_RECAL_ST_MASK						(1 << 3)
-
-/* Used by PM_DSP_PWRSTCTRL */
-#define OMAP54XX_DSP_EDMA_ONSTATE_SHIFT						20
-#define OMAP54XX_DSP_EDMA_ONSTATE_WIDTH						0x2
-#define OMAP54XX_DSP_EDMA_ONSTATE_MASK						(0x3 << 20)
-
-/* Used by PM_DSP_PWRSTCTRL */
-#define OMAP54XX_DSP_EDMA_RETSTATE_SHIFT					10
-#define OMAP54XX_DSP_EDMA_RETSTATE_WIDTH					0x1
-#define OMAP54XX_DSP_EDMA_RETSTATE_MASK						(1 << 10)
-
-/* Used by PM_DSP_PWRSTST */
-#define OMAP54XX_DSP_EDMA_STATEST_SHIFT						8
-#define OMAP54XX_DSP_EDMA_STATEST_WIDTH						0x2
-#define OMAP54XX_DSP_EDMA_STATEST_MASK						(0x3 << 8)
-
-/* Used by PM_DSP_PWRSTCTRL */
-#define OMAP54XX_DSP_L1_ONSTATE_SHIFT						16
-#define OMAP54XX_DSP_L1_ONSTATE_WIDTH						0x2
-#define OMAP54XX_DSP_L1_ONSTATE_MASK						(0x3 << 16)
-
-/* Used by PM_DSP_PWRSTCTRL */
-#define OMAP54XX_DSP_L1_RETSTATE_SHIFT						8
-#define OMAP54XX_DSP_L1_RETSTATE_WIDTH						0x1
-#define OMAP54XX_DSP_L1_RETSTATE_MASK						(1 << 8)
-
-/* Used by PM_DSP_PWRSTST */
-#define OMAP54XX_DSP_L1_STATEST_SHIFT						4
-#define OMAP54XX_DSP_L1_STATEST_WIDTH						0x2
-#define OMAP54XX_DSP_L1_STATEST_MASK						(0x3 << 4)
-
-/* Used by PM_DSP_PWRSTCTRL */
-#define OMAP54XX_DSP_L2_ONSTATE_SHIFT						18
-#define OMAP54XX_DSP_L2_ONSTATE_WIDTH						0x2
-#define OMAP54XX_DSP_L2_ONSTATE_MASK						(0x3 << 18)
-
-/* Used by PM_DSP_PWRSTCTRL */
-#define OMAP54XX_DSP_L2_RETSTATE_SHIFT						9
-#define OMAP54XX_DSP_L2_RETSTATE_WIDTH						0x1
-#define OMAP54XX_DSP_L2_RETSTATE_MASK						(1 << 9)
-
-/* Used by PM_DSP_PWRSTST */
-#define OMAP54XX_DSP_L2_STATEST_SHIFT						6
-#define OMAP54XX_DSP_L2_STATEST_WIDTH						0x2
-#define OMAP54XX_DSP_L2_STATEST_MASK						(0x3 << 6)
-
-/* Used by PM_DSS_PWRSTCTRL */
-#define OMAP54XX_DSS_MEM_ONSTATE_SHIFT						16
-#define OMAP54XX_DSS_MEM_ONSTATE_WIDTH						0x2
-#define OMAP54XX_DSS_MEM_ONSTATE_MASK						(0x3 << 16)
-
-/* Used by PM_DSS_PWRSTCTRL */
-#define OMAP54XX_DSS_MEM_RETSTATE_SHIFT						8
-#define OMAP54XX_DSS_MEM_RETSTATE_WIDTH						0x1
-#define OMAP54XX_DSS_MEM_RETSTATE_MASK						(1 << 8)
-
-/* Used by PM_DSS_PWRSTST */
-#define OMAP54XX_DSS_MEM_STATEST_SHIFT						4
-#define OMAP54XX_DSS_MEM_STATEST_WIDTH						0x2
-#define OMAP54XX_DSS_MEM_STATEST_MASK						(0x3 << 4)
-
-/* Used by PRM_DEVICE_OFF_CTRL */
-#define OMAP54XX_EMIF1_OFFWKUP_DISABLE_SHIFT					8
-#define OMAP54XX_EMIF1_OFFWKUP_DISABLE_WIDTH					0x1
-#define OMAP54XX_EMIF1_OFFWKUP_DISABLE_MASK					(1 << 8)
-
-/* Used by PRM_DEVICE_OFF_CTRL */
-#define OMAP54XX_EMIF2_OFFWKUP_DISABLE_SHIFT					9
-#define OMAP54XX_EMIF2_OFFWKUP_DISABLE_WIDTH					0x1
-#define OMAP54XX_EMIF2_OFFWKUP_DISABLE_MASK					(1 << 9)
-
-/* Used by PM_EMU_PWRSTCTRL */
-#define OMAP54XX_EMU_BANK_ONSTATE_SHIFT						16
-#define OMAP54XX_EMU_BANK_ONSTATE_WIDTH						0x2
-#define OMAP54XX_EMU_BANK_ONSTATE_MASK						(0x3 << 16)
-
-/* Used by PM_EMU_PWRSTST */
-#define OMAP54XX_EMU_BANK_STATEST_SHIFT						4
-#define OMAP54XX_EMU_BANK_STATEST_WIDTH						0x2
-#define OMAP54XX_EMU_BANK_STATEST_MASK						(0x3 << 4)
-
-/*
- * Used by PRM_SLDO_CORE_SETUP, PRM_SLDO_MM_SETUP, PRM_SLDO_MPU_SETUP,
- * PRM_SRAM_WKUP_SETUP
- */
-#define OMAP54XX_ENABLE_RTA_SHIFT						0
-#define OMAP54XX_ENABLE_RTA_WIDTH						0x1
-#define OMAP54XX_ENABLE_RTA_MASK						(1 << 0)
-
-/* Used by PRM_SLDO_CORE_SETUP, PRM_SLDO_MM_SETUP, PRM_SLDO_MPU_SETUP */
-#define OMAP54XX_ENFUNC1_SHIFT							3
-#define OMAP54XX_ENFUNC1_WIDTH							0x1
-#define OMAP54XX_ENFUNC1_MASK							(1 << 3)
-
-/* Used by PRM_SLDO_CORE_SETUP, PRM_SLDO_MM_SETUP, PRM_SLDO_MPU_SETUP */
-#define OMAP54XX_ENFUNC2_SHIFT							4
-#define OMAP54XX_ENFUNC2_WIDTH							0x1
-#define OMAP54XX_ENFUNC2_MASK							(1 << 4)
-
-/* Used by PRM_SLDO_CORE_SETUP, PRM_SLDO_MM_SETUP, PRM_SLDO_MPU_SETUP */
-#define OMAP54XX_ENFUNC3_SHIFT							5
-#define OMAP54XX_ENFUNC3_WIDTH							0x1
-#define OMAP54XX_ENFUNC3_MASK							(1 << 5)
-
-/* Used by PRM_SLDO_CORE_SETUP, PRM_SLDO_MM_SETUP, PRM_SLDO_MPU_SETUP */
-#define OMAP54XX_ENFUNC4_SHIFT							6
-#define OMAP54XX_ENFUNC4_WIDTH							0x1
-#define OMAP54XX_ENFUNC4_MASK							(1 << 6)
-
-/* Used by PRM_SLDO_CORE_SETUP, PRM_SLDO_MM_SETUP, PRM_SLDO_MPU_SETUP */
-#define OMAP54XX_ENFUNC5_SHIFT							7
-#define OMAP54XX_ENFUNC5_WIDTH							0x1
-#define OMAP54XX_ENFUNC5_MASK							(1 << 7)
-
-/* Used by PRM_VP_CORE_CONFIG, PRM_VP_MM_CONFIG, PRM_VP_MPU_CONFIG */
-#define OMAP54XX_ERRORGAIN_SHIFT						16
-#define OMAP54XX_ERRORGAIN_WIDTH						0x8
-#define OMAP54XX_ERRORGAIN_MASK							(0xff << 16)
-
-/* Used by PRM_VP_CORE_CONFIG, PRM_VP_MM_CONFIG, PRM_VP_MPU_CONFIG */
-#define OMAP54XX_ERROROFFSET_SHIFT						24
-#define OMAP54XX_ERROROFFSET_WIDTH						0x8
-#define OMAP54XX_ERROROFFSET_MASK						(0xff << 24)
-
-/* Used by PRM_RSTST */
-#define OMAP54XX_EXTERNAL_WARM_RST_SHIFT					5
-#define OMAP54XX_EXTERNAL_WARM_RST_WIDTH					0x1
-#define OMAP54XX_EXTERNAL_WARM_RST_MASK						(1 << 5)
-
-/* Used by PRM_VP_CORE_CONFIG, PRM_VP_MM_CONFIG, PRM_VP_MPU_CONFIG */
-#define OMAP54XX_FORCEUPDATE_SHIFT						1
-#define OMAP54XX_FORCEUPDATE_WIDTH						0x1
-#define OMAP54XX_FORCEUPDATE_MASK						(1 << 1)
-
-/* Used by PRM_VP_CORE_VOLTAGE, PRM_VP_MM_VOLTAGE, PRM_VP_MPU_VOLTAGE */
-#define OMAP54XX_FORCEUPDATEWAIT_SHIFT						8
-#define OMAP54XX_FORCEUPDATEWAIT_WIDTH						0x18
-#define OMAP54XX_FORCEUPDATEWAIT_MASK						(0xffffff << 8)
-
-/* Used by PRM_IRQENABLE_DSP, PRM_IRQENABLE_IPU */
-#define OMAP54XX_FORCEWKUP_EN_SHIFT						10
-#define OMAP54XX_FORCEWKUP_EN_WIDTH						0x1
-#define OMAP54XX_FORCEWKUP_EN_MASK						(1 << 10)
-
-/* Used by PRM_IRQSTATUS_DSP, PRM_IRQSTATUS_IPU */
-#define OMAP54XX_FORCEWKUP_ST_SHIFT						10
-#define OMAP54XX_FORCEWKUP_ST_WIDTH						0x1
-#define OMAP54XX_FORCEWKUP_ST_MASK						(1 << 10)
-
-/* Used by REVISION_PRM */
-#define OMAP54XX_FUNC_SHIFT							16
-#define OMAP54XX_FUNC_WIDTH							0xc
-#define OMAP54XX_FUNC_MASK							(0xfff << 16)
-
-/* Used by PRM_RSTST */
-#define OMAP54XX_GLOBAL_COLD_RST_SHIFT						0
-#define OMAP54XX_GLOBAL_COLD_RST_WIDTH						0x1
-#define OMAP54XX_GLOBAL_COLD_RST_MASK						(1 << 0)
-
-/* Used by PRM_RSTST */
-#define OMAP54XX_GLOBAL_WARM_SW_RST_SHIFT					1
-#define OMAP54XX_GLOBAL_WARM_SW_RST_WIDTH					0x1
-#define OMAP54XX_GLOBAL_WARM_SW_RST_MASK					(1 << 1)
-
-/* Used by PRM_IO_PMCTRL */
-#define OMAP54XX_GLOBAL_WUEN_SHIFT						16
-#define OMAP54XX_GLOBAL_WUEN_WIDTH						0x1
-#define OMAP54XX_GLOBAL_WUEN_MASK						(1 << 16)
-
-/* Used by PM_GPU_PWRSTCTRL */
-#define OMAP54XX_GPU_MEM_ONSTATE_SHIFT						16
-#define OMAP54XX_GPU_MEM_ONSTATE_WIDTH						0x2
-#define OMAP54XX_GPU_MEM_ONSTATE_MASK						(0x3 << 16)
-
-/* Used by PM_GPU_PWRSTST */
-#define OMAP54XX_GPU_MEM_STATEST_SHIFT						4
-#define OMAP54XX_GPU_MEM_STATEST_WIDTH						0x2
-#define OMAP54XX_GPU_MEM_STATEST_MASK						(0x3 << 4)
-
-/* Used by PRM_VC_CFG_I2C_MODE */
-#define OMAP54XX_HSMCODE_SHIFT							0
-#define OMAP54XX_HSMCODE_WIDTH							0x3
-#define OMAP54XX_HSMCODE_MASK							(0x7 << 0)
-
-/* Used by PRM_VC_CFG_I2C_MODE */
-#define OMAP54XX_HSMODEEN_SHIFT							3
-#define OMAP54XX_HSMODEEN_WIDTH							0x1
-#define OMAP54XX_HSMODEEN_MASK							(1 << 3)
-
-/* Used by PRM_VC_CFG_I2C_CLK */
-#define OMAP54XX_HSSCLH_SHIFT							16
-#define OMAP54XX_HSSCLH_WIDTH							0x8
-#define OMAP54XX_HSSCLH_MASK							(0xff << 16)
-
-/* Used by PRM_VC_CFG_I2C_CLK */
-#define OMAP54XX_HSSCLL_SHIFT							24
-#define OMAP54XX_HSSCLL_WIDTH							0x8
-#define OMAP54XX_HSSCLL_MASK							(0xff << 24)
-
-/* Used by PM_IVA_PWRSTCTRL */
-#define OMAP54XX_HWA_MEM_ONSTATE_SHIFT						16
-#define OMAP54XX_HWA_MEM_ONSTATE_WIDTH						0x2
-#define OMAP54XX_HWA_MEM_ONSTATE_MASK						(0x3 << 16)
-
-/* Used by PM_IVA_PWRSTCTRL */
-#define OMAP54XX_HWA_MEM_RETSTATE_SHIFT						8
-#define OMAP54XX_HWA_MEM_RETSTATE_WIDTH						0x1
-#define OMAP54XX_HWA_MEM_RETSTATE_MASK						(1 << 8)
-
-/* Used by PM_IVA_PWRSTST */
-#define OMAP54XX_HWA_MEM_STATEST_SHIFT						4
-#define OMAP54XX_HWA_MEM_STATEST_WIDTH						0x2
-#define OMAP54XX_HWA_MEM_STATEST_MASK						(0x3 << 4)
-
-/* Used by PRM_RSTST */
-#define OMAP54XX_ICEPICK_RST_SHIFT						9
-#define OMAP54XX_ICEPICK_RST_WIDTH						0x1
-#define OMAP54XX_ICEPICK_RST_MASK						(1 << 9)
-
-/* Used by PRM_VP_CORE_CONFIG, PRM_VP_MM_CONFIG, PRM_VP_MPU_CONFIG */
-#define OMAP54XX_INITVDD_SHIFT							2
-#define OMAP54XX_INITVDD_WIDTH							0x1
-#define OMAP54XX_INITVDD_MASK							(1 << 2)
-
-/* Used by PRM_VP_CORE_CONFIG, PRM_VP_MM_CONFIG, PRM_VP_MPU_CONFIG */
-#define OMAP54XX_INITVOLTAGE_SHIFT						8
-#define OMAP54XX_INITVOLTAGE_WIDTH						0x8
-#define OMAP54XX_INITVOLTAGE_MASK						(0xff << 8)
-
-/*
- * Used by PM_ABE_PWRSTST, PM_CAM_PWRSTST, PM_CORE_PWRSTST,
- * PM_CUSTEFUSE_PWRSTST, PM_DSP_PWRSTST, PM_DSS_PWRSTST, PM_EMU_PWRSTST,
- * PM_GPU_PWRSTST, PM_IVA_PWRSTST, PM_L3INIT_PWRSTST, PM_MPU_PWRSTST,
- * PRM_VOLTST_MM, PRM_VOLTST_MPU
- */
-#define OMAP54XX_INTRANSITION_SHIFT						20
-#define OMAP54XX_INTRANSITION_WIDTH						0x1
-#define OMAP54XX_INTRANSITION_MASK						(1 << 20)
-
-/* Used by PRM_IRQENABLE_IPU, PRM_IRQENABLE_MPU */
-#define OMAP54XX_IO_EN_SHIFT							9
-#define OMAP54XX_IO_EN_WIDTH							0x1
-#define OMAP54XX_IO_EN_MASK							(1 << 9)
-
-/* Used by PRM_IO_PMCTRL */
-#define OMAP54XX_IO_ON_STATUS_SHIFT						5
-#define OMAP54XX_IO_ON_STATUS_WIDTH						0x1
-#define OMAP54XX_IO_ON_STATUS_MASK						(1 << 5)
-
-/* Used by PRM_IRQSTATUS_IPU, PRM_IRQSTATUS_MPU */
-#define OMAP54XX_IO_ST_SHIFT							9
-#define OMAP54XX_IO_ST_WIDTH							0x1
-#define OMAP54XX_IO_ST_MASK							(1 << 9)
-
-/* Used by PM_CORE_PWRSTCTRL */
-#define OMAP54XX_IPU_L2RAM_ONSTATE_SHIFT					20
-#define OMAP54XX_IPU_L2RAM_ONSTATE_WIDTH					0x2
-#define OMAP54XX_IPU_L2RAM_ONSTATE_MASK						(0x3 << 20)
-
-/* Used by PM_CORE_PWRSTCTRL */
-#define OMAP54XX_IPU_L2RAM_RETSTATE_SHIFT					10
-#define OMAP54XX_IPU_L2RAM_RETSTATE_WIDTH					0x1
-#define OMAP54XX_IPU_L2RAM_RETSTATE_MASK					(1 << 10)
-
-/* Used by PM_CORE_PWRSTST */
-#define OMAP54XX_IPU_L2RAM_STATEST_SHIFT					8
-#define OMAP54XX_IPU_L2RAM_STATEST_WIDTH					0x2
-#define OMAP54XX_IPU_L2RAM_STATEST_MASK						(0x3 << 8)
-
-/* Used by PM_CORE_PWRSTCTRL */
-#define OMAP54XX_IPU_UNICACHE_ONSTATE_SHIFT					22
-#define OMAP54XX_IPU_UNICACHE_ONSTATE_WIDTH					0x2
-#define OMAP54XX_IPU_UNICACHE_ONSTATE_MASK					(0x3 << 22)
-
-/* Used by PM_CORE_PWRSTCTRL */
-#define OMAP54XX_IPU_UNICACHE_RETSTATE_SHIFT					11
-#define OMAP54XX_IPU_UNICACHE_RETSTATE_WIDTH					0x1
-#define OMAP54XX_IPU_UNICACHE_RETSTATE_MASK					(1 << 11)
-
-/* Used by PM_CORE_PWRSTST */
-#define OMAP54XX_IPU_UNICACHE_STATEST_SHIFT					10
-#define OMAP54XX_IPU_UNICACHE_STATEST_WIDTH					0x2
-#define OMAP54XX_IPU_UNICACHE_STATEST_MASK					(0x3 << 10)
-
-/* Used by PRM_IO_PMCTRL */
-#define OMAP54XX_ISOCLK_OVERRIDE_SHIFT						0
-#define OMAP54XX_ISOCLK_OVERRIDE_WIDTH						0x1
-#define OMAP54XX_ISOCLK_OVERRIDE_MASK						(1 << 0)
-
-/* Used by PRM_IO_PMCTRL */
-#define OMAP54XX_ISOCLK_STATUS_SHIFT						1
-#define OMAP54XX_ISOCLK_STATUS_WIDTH						0x1
-#define OMAP54XX_ISOCLK_STATUS_MASK						(1 << 1)
-
-/* Used by PRM_IO_PMCTRL */
-#define OMAP54XX_ISOOVR_EXTEND_SHIFT						4
-#define OMAP54XX_ISOOVR_EXTEND_WIDTH						0x1
-#define OMAP54XX_ISOOVR_EXTEND_MASK						(1 << 4)
-
-/* Used by PRM_IO_COUNT */
-#define OMAP54XX_ISO_2_ON_TIME_SHIFT						0
-#define OMAP54XX_ISO_2_ON_TIME_WIDTH						0x8
-#define OMAP54XX_ISO_2_ON_TIME_MASK						(0xff << 0)
-
-/* Used by PM_L3INIT_PWRSTCTRL */
-#define OMAP54XX_L3INIT_BANK1_ONSTATE_SHIFT					16
-#define OMAP54XX_L3INIT_BANK1_ONSTATE_WIDTH					0x2
-#define OMAP54XX_L3INIT_BANK1_ONSTATE_MASK					(0x3 << 16)
-
-/* Used by PM_L3INIT_PWRSTCTRL */
-#define OMAP54XX_L3INIT_BANK1_RETSTATE_SHIFT					8
-#define OMAP54XX_L3INIT_BANK1_RETSTATE_WIDTH					0x1
-#define OMAP54XX_L3INIT_BANK1_RETSTATE_MASK					(1 << 8)
-
-/* Used by PM_L3INIT_PWRSTST */
-#define OMAP54XX_L3INIT_BANK1_STATEST_SHIFT					4
-#define OMAP54XX_L3INIT_BANK1_STATEST_WIDTH					0x2
-#define OMAP54XX_L3INIT_BANK1_STATEST_MASK					(0x3 << 4)
-
-/* Used by PM_L3INIT_PWRSTCTRL */
-#define OMAP54XX_L3INIT_BANK2_ONSTATE_SHIFT					18
-#define OMAP54XX_L3INIT_BANK2_ONSTATE_WIDTH					0x2
-#define OMAP54XX_L3INIT_BANK2_ONSTATE_MASK					(0x3 << 18)
-
-/* Used by PM_L3INIT_PWRSTCTRL */
-#define OMAP54XX_L3INIT_BANK2_RETSTATE_SHIFT					9
-#define OMAP54XX_L3INIT_BANK2_RETSTATE_WIDTH					0x1
-#define OMAP54XX_L3INIT_BANK2_RETSTATE_MASK					(1 << 9)
-
-/* Used by PM_L3INIT_PWRSTST */
-#define OMAP54XX_L3INIT_BANK2_STATEST_SHIFT					6
-#define OMAP54XX_L3INIT_BANK2_STATEST_WIDTH					0x2
-#define OMAP54XX_L3INIT_BANK2_STATEST_MASK					(0x3 << 6)
-
-/*
- * Used by PM_ABE_PWRSTST, PM_CAM_PWRSTST, PM_CORE_PWRSTST,
- * PM_CUSTEFUSE_PWRSTST, PM_DSP_PWRSTST, PM_DSS_PWRSTST, PM_EMU_PWRSTST,
- * PM_GPU_PWRSTST, PM_IVA_PWRSTST, PM_L3INIT_PWRSTST, PM_MPU_PWRSTST
- */
-#define OMAP54XX_LASTPOWERSTATEENTERED_SHIFT					24
-#define OMAP54XX_LASTPOWERSTATEENTERED_WIDTH					0x2
-#define OMAP54XX_LASTPOWERSTATEENTERED_MASK					(0x3 << 24)
-
-/* Used by PRM_RSTST */
-#define OMAP54XX_LLI_RST_SHIFT							14
-#define OMAP54XX_LLI_RST_WIDTH							0x1
-#define OMAP54XX_LLI_RST_MASK							(1 << 14)
-
-/*
- * Used by PM_ABE_PWRSTCTRL, PM_CORE_PWRSTCTRL, PM_DSP_PWRSTCTRL,
- * PM_DSS_PWRSTCTRL, PM_IVA_PWRSTCTRL, PM_L3INIT_PWRSTCTRL, PM_MPU_PWRSTCTRL
- */
-#define OMAP54XX_LOGICRETSTATE_SHIFT						2
-#define OMAP54XX_LOGICRETSTATE_WIDTH						0x1
-#define OMAP54XX_LOGICRETSTATE_MASK						(1 << 2)
-
-/*
- * Used by PM_ABE_PWRSTST, PM_CAM_PWRSTST, PM_CORE_PWRSTST,
- * PM_CUSTEFUSE_PWRSTST, PM_DSP_PWRSTST, PM_DSS_PWRSTST, PM_EMU_PWRSTST,
- * PM_GPU_PWRSTST, PM_IVA_PWRSTST, PM_L3INIT_PWRSTST, PM_MPU_PWRSTST
- */
-#define OMAP54XX_LOGICSTATEST_SHIFT						2
-#define OMAP54XX_LOGICSTATEST_WIDTH						0x1
-#define OMAP54XX_LOGICSTATEST_MASK						(1 << 2)
-
-/*
- * Used by RM_ABE_AESS_CONTEXT, RM_ABE_DMIC_CONTEXT, RM_ABE_MCASP_CONTEXT,
- * RM_ABE_MCBSP1_CONTEXT, RM_ABE_MCBSP2_CONTEXT, RM_ABE_MCBSP3_CONTEXT,
- * RM_ABE_MCPDM_CONTEXT, RM_ABE_SLIMBUS1_CONTEXT, RM_ABE_TIMER5_CONTEXT,
- * RM_ABE_TIMER6_CONTEXT, RM_ABE_TIMER7_CONTEXT, RM_ABE_TIMER8_CONTEXT,
- * RM_ABE_WD_TIMER3_CONTEXT, RM_C2C_C2C_CONTEXT, RM_C2C_C2C_OCP_FW_CONTEXT,
- * RM_CAM_CAL_CONTEXT, RM_CAM_FDIF_CONTEXT, RM_CAM_ISS_CONTEXT,
- * RM_COREAON_SMARTREFLEX_CORE_CONTEXT, RM_COREAON_SMARTREFLEX_MM_CONTEXT,
- * RM_COREAON_SMARTREFLEX_MPU_CONTEXT, RM_CUSTEFUSE_EFUSE_CTRL_CUST_CONTEXT,
- * RM_DSP_DSP_CONTEXT, RM_DSS_BB2D_CONTEXT, RM_DSS_DSS_CONTEXT,
- * RM_EMIF_DMM_CONTEXT, RM_EMIF_EMIF1_CONTEXT, RM_EMIF_EMIF2_CONTEXT,
- * RM_EMIF_EMIF_DLL_CONTEXT, RM_EMIF_EMIF_OCP_FW_CONTEXT,
- * RM_EMU_DEBUGSS_CONTEXT, RM_GPU_GPU_CONTEXT, RM_IPU_IPU_CONTEXT,
- * RM_IVA_IVA_CONTEXT, RM_IVA_SL2_CONTEXT, RM_L3INIT_IEEE1500_2_OCP_CONTEXT,
- * RM_L3INIT_OCP2SCP1_CONTEXT, RM_L3INIT_OCP2SCP3_CONTEXT,
- * RM_L3INIT_SATA_CONTEXT, RM_L3INIT_UNIPRO2_CONTEXT,
- * RM_L3INSTR_L3_INSTR_CONTEXT, RM_L3INSTR_L3_MAIN_3_CONTEXT,
- * RM_L3INSTR_OCP_WP_NOC_CONTEXT, RM_L3MAIN1_L3_MAIN_1_CONTEXT,
- * RM_L3MAIN2_L3_MAIN_2_CONTEXT, RM_L3MAIN2_OCMC_RAM_CONTEXT,
- * RM_L4CFG_L4_CFG_CONTEXT, RM_L4CFG_OCP2SCP2_CONTEXT,
- * RM_L4CFG_SAR_ROM_CONTEXT, RM_L4PER_ELM_CONTEXT, RM_L4PER_HDQ1W_CONTEXT,
- * RM_L4PER_I2C2_CONTEXT, RM_L4PER_I2C3_CONTEXT, RM_L4PER_I2C4_CONTEXT,
- * RM_L4PER_I2C5_CONTEXT, RM_L4PER_L4_PER_CONTEXT, RM_L4PER_MCSPI1_CONTEXT,
- * RM_L4PER_MCSPI2_CONTEXT, RM_L4PER_MCSPI3_CONTEXT, RM_L4PER_MCSPI4_CONTEXT,
- * RM_L4PER_MMC3_CONTEXT, RM_L4PER_MMC4_CONTEXT, RM_L4PER_MMC5_CONTEXT,
- * RM_L4PER_TIMER10_CONTEXT, RM_L4PER_TIMER11_CONTEXT, RM_L4PER_TIMER2_CONTEXT,
- * RM_L4PER_TIMER3_CONTEXT, RM_L4PER_TIMER4_CONTEXT, RM_L4PER_TIMER9_CONTEXT,
- * RM_L4SEC_FPKA_CONTEXT, RM_MIPIEXT_LLI_CONTEXT,
- * RM_MIPIEXT_LLI_OCP_FW_CONTEXT, RM_MIPIEXT_MPHY_CONTEXT, RM_MPU_MPU_CONTEXT,
- * RM_WKUPAON_COUNTER_32K_CONTEXT, RM_WKUPAON_GPIO1_CONTEXT,
- * RM_WKUPAON_KBD_CONTEXT, RM_WKUPAON_L4_WKUP_CONTEXT,
- * RM_WKUPAON_SAR_RAM_CONTEXT, RM_WKUPAON_TIMER12_CONTEXT,
- * RM_WKUPAON_TIMER1_CONTEXT, RM_WKUPAON_WD_TIMER1_CONTEXT,
- * RM_WKUPAON_WD_TIMER2_CONTEXT
- */
-#define OMAP54XX_LOSTCONTEXT_DFF_SHIFT						0
-#define OMAP54XX_LOSTCONTEXT_DFF_WIDTH						0x1
-#define OMAP54XX_LOSTCONTEXT_DFF_MASK						(1 << 0)
-
-/*
- * Used by RM_C2C_C2C_CONTEXT, RM_C2C_C2C_OCP_FW_CONTEXT,
- * RM_C2C_MODEM_ICR_CONTEXT, RM_DMA_DMA_SYSTEM_CONTEXT, RM_DSP_DSP_CONTEXT,
- * RM_DSS_DSS_CONTEXT, RM_EMIF_DMM_CONTEXT, RM_EMIF_EMIF1_CONTEXT,
- * RM_EMIF_EMIF2_CONTEXT, RM_EMIF_EMIF_OCP_FW_CONTEXT, RM_IPU_IPU_CONTEXT,
- * RM_L3INIT_HSI_CONTEXT, RM_L3INIT_MMC1_CONTEXT, RM_L3INIT_MMC2_CONTEXT,
- * RM_L3INIT_USB_HOST_HS_CONTEXT, RM_L3INIT_USB_OTG_SS_CONTEXT,
- * RM_L3INIT_USB_TLL_HS_CONTEXT, RM_L3INSTR_L3_MAIN_3_CONTEXT,
- * RM_L3INSTR_OCP_WP_NOC_CONTEXT, RM_L3MAIN1_L3_MAIN_1_CONTEXT,
- * RM_L3MAIN2_GPMC_CONTEXT, RM_L3MAIN2_L3_MAIN_2_CONTEXT,
- * RM_L4CFG_L4_CFG_CONTEXT, RM_L4CFG_MAILBOX_CONTEXT,
- * RM_L4CFG_SPINLOCK_CONTEXT, RM_L4PER_GPIO2_CONTEXT, RM_L4PER_GPIO3_CONTEXT,
- * RM_L4PER_GPIO4_CONTEXT, RM_L4PER_GPIO5_CONTEXT, RM_L4PER_GPIO6_CONTEXT,
- * RM_L4PER_GPIO7_CONTEXT, RM_L4PER_GPIO8_CONTEXT, RM_L4PER_I2C1_CONTEXT,
- * RM_L4PER_L4_PER_CONTEXT, RM_L4PER_UART1_CONTEXT, RM_L4PER_UART2_CONTEXT,
- * RM_L4PER_UART3_CONTEXT, RM_L4PER_UART4_CONTEXT, RM_L4PER_UART5_CONTEXT,
- * RM_L4PER_UART6_CONTEXT, RM_L4SEC_AES1_CONTEXT, RM_L4SEC_AES2_CONTEXT,
- * RM_L4SEC_DES3DES_CONTEXT, RM_L4SEC_DMA_CRYPTO_CONTEXT, RM_L4SEC_RNG_CONTEXT,
- * RM_L4SEC_SHA2MD5_CONTEXT, RM_MIPIEXT_LLI_CONTEXT,
- * RM_MIPIEXT_LLI_OCP_FW_CONTEXT, RM_MIPIEXT_MPHY_CONTEXT, RM_MPU_MPU_CONTEXT
- */
-#define OMAP54XX_LOSTCONTEXT_RFF_SHIFT						1
-#define OMAP54XX_LOSTCONTEXT_RFF_WIDTH						0x1
-#define OMAP54XX_LOSTCONTEXT_RFF_MASK						(1 << 1)
-
-/* Used by RM_ABE_AESS_CONTEXT */
-#define OMAP54XX_LOSTMEM_AESSMEM_SHIFT						8
-#define OMAP54XX_LOSTMEM_AESSMEM_WIDTH						0x1
-#define OMAP54XX_LOSTMEM_AESSMEM_MASK						(1 << 8)
-
-/* Used by RM_CAM_CAL_CONTEXT */
-#define OMAP54XX_LOSTMEM_CAL_MEM_SHIFT						8
-#define OMAP54XX_LOSTMEM_CAL_MEM_WIDTH						0x1
-#define OMAP54XX_LOSTMEM_CAL_MEM_MASK						(1 << 8)
-
-/* Used by RM_CAM_FDIF_CONTEXT, RM_CAM_ISS_CONTEXT */
-#define OMAP54XX_LOSTMEM_CAM_MEM_SHIFT						8
-#define OMAP54XX_LOSTMEM_CAM_MEM_WIDTH						0x1
-#define OMAP54XX_LOSTMEM_CAM_MEM_MASK						(1 << 8)
-
-/* Used by RM_EMIF_DMM_CONTEXT */
-#define OMAP54XX_LOSTMEM_CORE_NRET_BANK_SHIFT					9
-#define OMAP54XX_LOSTMEM_CORE_NRET_BANK_WIDTH					0x1
-#define OMAP54XX_LOSTMEM_CORE_NRET_BANK_MASK					(1 << 9)
-
-/* Renamed from LOSTMEM_CORE_NRET_BANK Used by RM_L3INSTR_OCP_WP_NOC_CONTEXT */
-#define OMAP54XX_LOSTMEM_CORE_NRET_BANK_8_8_SHIFT				8
-#define OMAP54XX_LOSTMEM_CORE_NRET_BANK_8_8_WIDTH				0x1
-#define OMAP54XX_LOSTMEM_CORE_NRET_BANK_8_8_MASK				(1 << 8)
-
-/* Used by RM_L3MAIN2_OCMC_RAM_CONTEXT */
-#define OMAP54XX_LOSTMEM_CORE_OCMRAM_SHIFT					8
-#define OMAP54XX_LOSTMEM_CORE_OCMRAM_WIDTH					0x1
-#define OMAP54XX_LOSTMEM_CORE_OCMRAM_MASK					(1 << 8)
-
-/* Used by RM_DMA_DMA_SYSTEM_CONTEXT, RM_EMIF_DMM_CONTEXT */
-#define OMAP54XX_LOSTMEM_CORE_OTHER_BANK_SHIFT					8
-#define OMAP54XX_LOSTMEM_CORE_OTHER_BANK_WIDTH					0x1
-#define OMAP54XX_LOSTMEM_CORE_OTHER_BANK_MASK					(1 << 8)
-
-/* Used by RM_DSP_DSP_CONTEXT */
-#define OMAP54XX_LOSTMEM_DSP_EDMA_SHIFT						10
-#define OMAP54XX_LOSTMEM_DSP_EDMA_WIDTH						0x1
-#define OMAP54XX_LOSTMEM_DSP_EDMA_MASK						(1 << 10)
-
-/* Used by RM_DSP_DSP_CONTEXT */
-#define OMAP54XX_LOSTMEM_DSP_L1_SHIFT						8
-#define OMAP54XX_LOSTMEM_DSP_L1_WIDTH						0x1
-#define OMAP54XX_LOSTMEM_DSP_L1_MASK						(1 << 8)
-
-/* Used by RM_DSP_DSP_CONTEXT */
-#define OMAP54XX_LOSTMEM_DSP_L2_SHIFT						9
-#define OMAP54XX_LOSTMEM_DSP_L2_WIDTH						0x1
-#define OMAP54XX_LOSTMEM_DSP_L2_MASK						(1 << 9)
-
-/* Used by RM_DSS_BB2D_CONTEXT, RM_DSS_DSS_CONTEXT */
-#define OMAP54XX_LOSTMEM_DSS_MEM_SHIFT						8
-#define OMAP54XX_LOSTMEM_DSS_MEM_WIDTH						0x1
-#define OMAP54XX_LOSTMEM_DSS_MEM_MASK						(1 << 8)
-
-/* Used by RM_EMU_DEBUGSS_CONTEXT */
-#define OMAP54XX_LOSTMEM_EMU_BANK_SHIFT						8
-#define OMAP54XX_LOSTMEM_EMU_BANK_WIDTH						0x1
-#define OMAP54XX_LOSTMEM_EMU_BANK_MASK						(1 << 8)
-
-/* Used by RM_GPU_GPU_CONTEXT */
-#define OMAP54XX_LOSTMEM_GPU_MEM_SHIFT						8
-#define OMAP54XX_LOSTMEM_GPU_MEM_WIDTH						0x1
-#define OMAP54XX_LOSTMEM_GPU_MEM_MASK						(1 << 8)
-
-/* Used by RM_IVA_IVA_CONTEXT */
-#define OMAP54XX_LOSTMEM_HWA_MEM_SHIFT						10
-#define OMAP54XX_LOSTMEM_HWA_MEM_WIDTH						0x1
-#define OMAP54XX_LOSTMEM_HWA_MEM_MASK						(1 << 10)
-
-/* Used by RM_IPU_IPU_CONTEXT */
-#define OMAP54XX_LOSTMEM_IPU_L2RAM_SHIFT					9
-#define OMAP54XX_LOSTMEM_IPU_L2RAM_WIDTH					0x1
-#define OMAP54XX_LOSTMEM_IPU_L2RAM_MASK						(1 << 9)
-
-/* Used by RM_IPU_IPU_CONTEXT */
-#define OMAP54XX_LOSTMEM_IPU_UNICACHE_SHIFT					8
-#define OMAP54XX_LOSTMEM_IPU_UNICACHE_WIDTH					0x1
-#define OMAP54XX_LOSTMEM_IPU_UNICACHE_MASK					(1 << 8)
-
-/*
- * Used by RM_L3INIT_HSI_CONTEXT, RM_L3INIT_MMC1_CONTEXT,
- * RM_L3INIT_MMC2_CONTEXT, RM_L3INIT_SATA_CONTEXT, RM_L3INIT_UNIPRO2_CONTEXT,
- * RM_L3INIT_USB_OTG_SS_CONTEXT
- */
-#define OMAP54XX_LOSTMEM_L3INIT_BANK1_SHIFT					8
-#define OMAP54XX_LOSTMEM_L3INIT_BANK1_WIDTH					0x1
-#define OMAP54XX_LOSTMEM_L3INIT_BANK1_MASK					(1 << 8)
-
-/* Used by RM_MPU_MPU_CONTEXT */
-#define OMAP54XX_LOSTMEM_MPU_L2_SHIFT						9
-#define OMAP54XX_LOSTMEM_MPU_L2_WIDTH						0x1
-#define OMAP54XX_LOSTMEM_MPU_L2_MASK						(1 << 9)
-
-/* Used by RM_MPU_MPU_CONTEXT */
-#define OMAP54XX_LOSTMEM_MPU_RAM_SHIFT						10
-#define OMAP54XX_LOSTMEM_MPU_RAM_WIDTH						0x1
-#define OMAP54XX_LOSTMEM_MPU_RAM_MASK						(1 << 10)
-
-/*
- * Used by RM_L4PER_MMC3_CONTEXT, RM_L4PER_MMC4_CONTEXT, RM_L4PER_MMC5_CONTEXT,
- * RM_L4SEC_FPKA_CONTEXT
- */
-#define OMAP54XX_LOSTMEM_NONRETAINED_BANK_SHIFT					8
-#define OMAP54XX_LOSTMEM_NONRETAINED_BANK_WIDTH					0x1
-#define OMAP54XX_LOSTMEM_NONRETAINED_BANK_MASK					(1 << 8)
-
-/*
- * Used by RM_ABE_DMIC_CONTEXT, RM_ABE_MCBSP1_CONTEXT, RM_ABE_MCBSP2_CONTEXT,
- * RM_ABE_MCBSP3_CONTEXT, RM_ABE_MCPDM_CONTEXT, RM_ABE_SLIMBUS1_CONTEXT
- */
-#define OMAP54XX_LOSTMEM_PERIHPMEM_SHIFT					8
-#define OMAP54XX_LOSTMEM_PERIHPMEM_WIDTH					0x1
-#define OMAP54XX_LOSTMEM_PERIHPMEM_MASK						(1 << 8)
-
-/*
- * Used by RM_L4PER_UART1_CONTEXT, RM_L4PER_UART2_CONTEXT,
- * RM_L4PER_UART3_CONTEXT, RM_L4PER_UART4_CONTEXT, RM_L4PER_UART5_CONTEXT,
- * RM_L4PER_UART6_CONTEXT, RM_L4SEC_DMA_CRYPTO_CONTEXT
- */
-#define OMAP54XX_LOSTMEM_RETAINED_BANK_SHIFT					8
-#define OMAP54XX_LOSTMEM_RETAINED_BANK_WIDTH					0x1
-#define OMAP54XX_LOSTMEM_RETAINED_BANK_MASK					(1 << 8)
-
-/* Used by RM_IVA_SL2_CONTEXT */
-#define OMAP54XX_LOSTMEM_SL2_MEM_SHIFT						8
-#define OMAP54XX_LOSTMEM_SL2_MEM_WIDTH						0x1
-#define OMAP54XX_LOSTMEM_SL2_MEM_MASK						(1 << 8)
-
-/* Used by RM_IVA_IVA_CONTEXT */
-#define OMAP54XX_LOSTMEM_TCM1_MEM_SHIFT						8
-#define OMAP54XX_LOSTMEM_TCM1_MEM_WIDTH						0x1
-#define OMAP54XX_LOSTMEM_TCM1_MEM_MASK						(1 << 8)
-
-/* Used by RM_IVA_IVA_CONTEXT */
-#define OMAP54XX_LOSTMEM_TCM2_MEM_SHIFT						9
-#define OMAP54XX_LOSTMEM_TCM2_MEM_WIDTH						0x1
-#define OMAP54XX_LOSTMEM_TCM2_MEM_MASK						(1 << 9)
-
-/* Used by RM_WKUPAON_SAR_RAM_CONTEXT */
-#define OMAP54XX_LOSTMEM_WKUP_BANK_SHIFT					8
-#define OMAP54XX_LOSTMEM_WKUP_BANK_WIDTH					0x1
-#define OMAP54XX_LOSTMEM_WKUP_BANK_MASK						(1 << 8)
-
-/*
- * Used by PM_ABE_PWRSTCTRL, PM_CAM_PWRSTCTRL, PM_CORE_PWRSTCTRL,
- * PM_CUSTEFUSE_PWRSTCTRL, PM_DSP_PWRSTCTRL, PM_DSS_PWRSTCTRL,
- * PM_GPU_PWRSTCTRL, PM_IVA_PWRSTCTRL, PM_L3INIT_PWRSTCTRL, PM_MPU_PWRSTCTRL
- */
-#define OMAP54XX_LOWPOWERSTATECHANGE_SHIFT					4
-#define OMAP54XX_LOWPOWERSTATECHANGE_WIDTH					0x1
-#define OMAP54XX_LOWPOWERSTATECHANGE_MASK					(1 << 4)
-
-/* Used by PRM_DEBUG_TRANS_CFG */
-#define OMAP54XX_MODE_SHIFT							0
-#define OMAP54XX_MODE_WIDTH							0x2
-#define OMAP54XX_MODE_MASK							(0x3 << 0)
-
-/* Used by PRM_MODEM_IF_CTRL */
-#define OMAP54XX_MODEM_SHUTDOWN_IRQ_SHIFT					9
-#define OMAP54XX_MODEM_SHUTDOWN_IRQ_WIDTH					0x1
-#define OMAP54XX_MODEM_SHUTDOWN_IRQ_MASK					(1 << 9)
-
-/* Used by PRM_MODEM_IF_CTRL */
-#define OMAP54XX_MODEM_WAKE_IRQ_SHIFT						8
-#define OMAP54XX_MODEM_WAKE_IRQ_WIDTH						0x1
-#define OMAP54XX_MODEM_WAKE_IRQ_MASK						(1 << 8)
-
-/* Used by PM_MPU_PWRSTCTRL */
-#define OMAP54XX_MPU_L2_ONSTATE_SHIFT						18
-#define OMAP54XX_MPU_L2_ONSTATE_WIDTH						0x2
-#define OMAP54XX_MPU_L2_ONSTATE_MASK						(0x3 << 18)
-
-/* Used by PM_MPU_PWRSTCTRL */
-#define OMAP54XX_MPU_L2_RETSTATE_SHIFT						9
-#define OMAP54XX_MPU_L2_RETSTATE_WIDTH						0x1
-#define OMAP54XX_MPU_L2_RETSTATE_MASK						(1 << 9)
-
-/* Used by PM_MPU_PWRSTST */
-#define OMAP54XX_MPU_L2_STATEST_SHIFT						6
-#define OMAP54XX_MPU_L2_STATEST_WIDTH						0x2
-#define OMAP54XX_MPU_L2_STATEST_MASK						(0x3 << 6)
-
-/* Used by PM_MPU_PWRSTCTRL */
-#define OMAP54XX_MPU_RAM_ONSTATE_SHIFT						20
-#define OMAP54XX_MPU_RAM_ONSTATE_WIDTH						0x2
-#define OMAP54XX_MPU_RAM_ONSTATE_MASK						(0x3 << 20)
-
-/* Used by PM_MPU_PWRSTCTRL */
-#define OMAP54XX_MPU_RAM_RETSTATE_SHIFT						10
-#define OMAP54XX_MPU_RAM_RETSTATE_WIDTH						0x1
-#define OMAP54XX_MPU_RAM_RETSTATE_MASK						(1 << 10)
-
-/* Used by PM_MPU_PWRSTST */
-#define OMAP54XX_MPU_RAM_STATEST_SHIFT						8
-#define OMAP54XX_MPU_RAM_STATEST_WIDTH						0x2
-#define OMAP54XX_MPU_RAM_STATEST_MASK						(0x3 << 8)
-
-/* Used by PRM_RSTST */
-#define OMAP54XX_MPU_SECURITY_VIOL_RST_SHIFT					2
-#define OMAP54XX_MPU_SECURITY_VIOL_RST_WIDTH					0x1
-#define OMAP54XX_MPU_SECURITY_VIOL_RST_MASK					(1 << 2)
-
-/* Used by PRM_RSTST */
-#define OMAP54XX_MPU_WDT_RST_SHIFT						3
-#define OMAP54XX_MPU_WDT_RST_WIDTH						0x1
-#define OMAP54XX_MPU_WDT_RST_MASK						(1 << 3)
-
-/* Used by PRM_ABBLDO_MM_SETUP, PRM_ABBLDO_MPU_SETUP */
-#define OMAP54XX_NOCAP_SHIFT							4
-#define OMAP54XX_NOCAP_WIDTH							0x1
-#define OMAP54XX_NOCAP_MASK							(1 << 4)
-
-/* Used by PM_CORE_PWRSTCTRL */
-#define OMAP54XX_OCP_NRET_BANK_ONSTATE_SHIFT					24
-#define OMAP54XX_OCP_NRET_BANK_ONSTATE_WIDTH					0x2
-#define OMAP54XX_OCP_NRET_BANK_ONSTATE_MASK					(0x3 << 24)
-
-/* Used by PM_CORE_PWRSTCTRL */
-#define OMAP54XX_OCP_NRET_BANK_RETSTATE_SHIFT					12
-#define OMAP54XX_OCP_NRET_BANK_RETSTATE_WIDTH					0x1
-#define OMAP54XX_OCP_NRET_BANK_RETSTATE_MASK					(1 << 12)
-
-/* Used by PM_CORE_PWRSTST */
-#define OMAP54XX_OCP_NRET_BANK_STATEST_SHIFT					12
-#define OMAP54XX_OCP_NRET_BANK_STATEST_WIDTH					0x2
-#define OMAP54XX_OCP_NRET_BANK_STATEST_MASK					(0x3 << 12)
-
-/*
- * Used by PRM_VC_VAL_CMD_VDD_CORE_L, PRM_VC_VAL_CMD_VDD_MM_L,
- * PRM_VC_VAL_CMD_VDD_MPU_L
- */
-#define OMAP54XX_OFF_SHIFT							0
-#define OMAP54XX_OFF_WIDTH							0x8
-#define OMAP54XX_OFF_MASK							(0xff << 0)
-
-/*
- * Used by PRM_VC_VAL_CMD_VDD_CORE_L, PRM_VC_VAL_CMD_VDD_MM_L,
- * PRM_VC_VAL_CMD_VDD_MPU_L
- */
-#define OMAP54XX_ON_SHIFT							24
-#define OMAP54XX_ON_WIDTH							0x8
-#define OMAP54XX_ON_MASK							(0xff << 24)
-
-/*
- * Used by PRM_VC_VAL_CMD_VDD_CORE_L, PRM_VC_VAL_CMD_VDD_MM_L,
- * PRM_VC_VAL_CMD_VDD_MPU_L
- */
-#define OMAP54XX_ONLP_SHIFT							16
-#define OMAP54XX_ONLP_WIDTH							0x8
-#define OMAP54XX_ONLP_MASK							(0xff << 16)
-
-/* Used by PRM_ABBLDO_MM_CTRL, PRM_ABBLDO_MPU_CTRL */
-#define OMAP54XX_OPP_CHANGE_SHIFT						2
-#define OMAP54XX_OPP_CHANGE_WIDTH						0x1
-#define OMAP54XX_OPP_CHANGE_MASK						(1 << 2)
-
-/* Used by PRM_VC_VAL_BYPASS */
-#define OMAP54XX_OPP_CHANGE_EMIF_LVL_SHIFT					25
-#define OMAP54XX_OPP_CHANGE_EMIF_LVL_WIDTH					0x1
-#define OMAP54XX_OPP_CHANGE_EMIF_LVL_MASK					(1 << 25)
-
-/* Used by PRM_ABBLDO_MM_CTRL, PRM_ABBLDO_MPU_CTRL */
-#define OMAP54XX_OPP_SEL_SHIFT							0
-#define OMAP54XX_OPP_SEL_WIDTH							0x2
-#define OMAP54XX_OPP_SEL_MASK							(0x3 << 0)
-
-/* Used by PRM_DEBUG_OUT */
-#define OMAP54XX_OUTPUT_SHIFT							0
-#define OMAP54XX_OUTPUT_WIDTH							0x20
-#define OMAP54XX_OUTPUT_MASK							(0xffffffff << 0)
-
-/* Used by PRM_SRAM_COUNT */
-#define OMAP54XX_PCHARGECNT_VALUE_SHIFT						0
-#define OMAP54XX_PCHARGECNT_VALUE_WIDTH						0x6
-#define OMAP54XX_PCHARGECNT_VALUE_MASK						(0x3f << 0)
-
-/* Used by PRM_PSCON_COUNT */
-#define OMAP54XX_PCHARGE_TIME_SHIFT						0
-#define OMAP54XX_PCHARGE_TIME_WIDTH						0x8
-#define OMAP54XX_PCHARGE_TIME_MASK						(0xff << 0)
-
-/* Used by PM_ABE_PWRSTCTRL */
-#define OMAP54XX_PERIPHMEM_ONSTATE_SHIFT					20
-#define OMAP54XX_PERIPHMEM_ONSTATE_WIDTH					0x2
-#define OMAP54XX_PERIPHMEM_ONSTATE_MASK						(0x3 << 20)
-
-/* Used by PM_ABE_PWRSTCTRL */
-#define OMAP54XX_PERIPHMEM_RETSTATE_SHIFT					10
-#define OMAP54XX_PERIPHMEM_RETSTATE_WIDTH					0x1
-#define OMAP54XX_PERIPHMEM_RETSTATE_MASK					(1 << 10)
-
-/* Used by PM_ABE_PWRSTST */
-#define OMAP54XX_PERIPHMEM_STATEST_SHIFT					8
-#define OMAP54XX_PERIPHMEM_STATEST_WIDTH					0x2
-#define OMAP54XX_PERIPHMEM_STATEST_MASK						(0x3 << 8)
-
-/* Used by PRM_PHASE1_CNDP */
-#define OMAP54XX_PHASE1_CNDP_SHIFT						0
-#define OMAP54XX_PHASE1_CNDP_WIDTH						0x20
-#define OMAP54XX_PHASE1_CNDP_MASK						(0xffffffff << 0)
-
-/* Used by PRM_PHASE2A_CNDP */
-#define OMAP54XX_PHASE2A_CNDP_SHIFT						0
-#define OMAP54XX_PHASE2A_CNDP_WIDTH						0x20
-#define OMAP54XX_PHASE2A_CNDP_MASK						(0xffffffff << 0)
-
-/* Used by PRM_PHASE2B_CNDP */
-#define OMAP54XX_PHASE2B_CNDP_SHIFT						0
-#define OMAP54XX_PHASE2B_CNDP_WIDTH						0x20
-#define OMAP54XX_PHASE2B_CNDP_MASK						(0xffffffff << 0)
-
-/* Used by PRM_PSCON_COUNT */
-#define OMAP54XX_PONOUT_2_PGOODIN_TIME_SHIFT					8
-#define OMAP54XX_PONOUT_2_PGOODIN_TIME_WIDTH					0x8
-#define OMAP54XX_PONOUT_2_PGOODIN_TIME_MASK					(0xff << 8)
-
-/*
- * Used by PM_ABE_PWRSTCTRL, PM_CAM_PWRSTCTRL, PM_CORE_PWRSTCTRL,
- * PM_CUSTEFUSE_PWRSTCTRL, PM_DSP_PWRSTCTRL, PM_DSS_PWRSTCTRL,
- * PM_EMU_PWRSTCTRL, PM_GPU_PWRSTCTRL, PM_IVA_PWRSTCTRL, PM_L3INIT_PWRSTCTRL,
- * PM_MPU_PWRSTCTRL
- */
-#define OMAP54XX_POWERSTATE_SHIFT						0
-#define OMAP54XX_POWERSTATE_WIDTH						0x2
-#define OMAP54XX_POWERSTATE_MASK						(0x3 << 0)
-
-/*
- * Used by PM_ABE_PWRSTST, PM_CAM_PWRSTST, PM_CORE_PWRSTST,
- * PM_CUSTEFUSE_PWRSTST, PM_DSP_PWRSTST, PM_DSS_PWRSTST, PM_EMU_PWRSTST,
- * PM_GPU_PWRSTST, PM_IVA_PWRSTST, PM_L3INIT_PWRSTST, PM_MPU_PWRSTST
- */
-#define OMAP54XX_POWERSTATEST_SHIFT						0
-#define OMAP54XX_POWERSTATEST_WIDTH						0x2
-#define OMAP54XX_POWERSTATEST_MASK						(0x3 << 0)
-
-/* Used by PRM_PWRREQCTRL */
-#define OMAP54XX_PWRREQ_COND_SHIFT						0
-#define OMAP54XX_PWRREQ_COND_WIDTH						0x2
-#define OMAP54XX_PWRREQ_COND_MASK						(0x3 << 0)
-
-/* Used by PRM_VC_SMPS_CORE_CONFIG */
-#define OMAP54XX_RACEN_VDD_CORE_L_SHIFT						27
-#define OMAP54XX_RACEN_VDD_CORE_L_WIDTH						0x1
-#define OMAP54XX_RACEN_VDD_CORE_L_MASK						(1 << 27)
-
-/* Used by PRM_VC_SMPS_MM_CONFIG */
-#define OMAP54XX_RACEN_VDD_MM_L_SHIFT						27
-#define OMAP54XX_RACEN_VDD_MM_L_WIDTH						0x1
-#define OMAP54XX_RACEN_VDD_MM_L_MASK						(1 << 27)
-
-/* Used by PRM_VC_SMPS_MPU_CONFIG */
-#define OMAP54XX_RACEN_VDD_MPU_L_SHIFT						27
-#define OMAP54XX_RACEN_VDD_MPU_L_WIDTH						0x1
-#define OMAP54XX_RACEN_VDD_MPU_L_MASK						(1 << 27)
-
-/* Used by PRM_VC_SMPS_CORE_CONFIG */
-#define OMAP54XX_RAC_VDD_CORE_L_SHIFT						26
-#define OMAP54XX_RAC_VDD_CORE_L_WIDTH						0x1
-#define OMAP54XX_RAC_VDD_CORE_L_MASK						(1 << 26)
-
-/* Used by PRM_VC_SMPS_MM_CONFIG */
-#define OMAP54XX_RAC_VDD_MM_L_SHIFT						26
-#define OMAP54XX_RAC_VDD_MM_L_WIDTH						0x1
-#define OMAP54XX_RAC_VDD_MM_L_MASK						(1 << 26)
-
-/* Used by PRM_VC_SMPS_MPU_CONFIG */
-#define OMAP54XX_RAC_VDD_MPU_L_SHIFT						26
-#define OMAP54XX_RAC_VDD_MPU_L_WIDTH						0x1
-#define OMAP54XX_RAC_VDD_MPU_L_MASK						(1 << 26)
-
-/*
- * Used by PRM_VOLTSETUP_CORE_OFF, PRM_VOLTSETUP_CORE_RET_SLEEP,
- * PRM_VOLTSETUP_MM_OFF, PRM_VOLTSETUP_MM_RET_SLEEP, PRM_VOLTSETUP_MPU_OFF,
- * PRM_VOLTSETUP_MPU_RET_SLEEP
- */
-#define OMAP54XX_RAMP_DOWN_COUNT_SHIFT						16
-#define OMAP54XX_RAMP_DOWN_COUNT_WIDTH						0x6
-#define OMAP54XX_RAMP_DOWN_COUNT_MASK						(0x3f << 16)
-
-/*
- * Used by PRM_VOLTSETUP_CORE_OFF, PRM_VOLTSETUP_CORE_RET_SLEEP,
- * PRM_VOLTSETUP_MM_OFF, PRM_VOLTSETUP_MM_RET_SLEEP, PRM_VOLTSETUP_MPU_OFF,
- * PRM_VOLTSETUP_MPU_RET_SLEEP
- */
-#define OMAP54XX_RAMP_DOWN_PRESCAL_SHIFT					24
-#define OMAP54XX_RAMP_DOWN_PRESCAL_WIDTH					0x2
-#define OMAP54XX_RAMP_DOWN_PRESCAL_MASK						(0x3 << 24)
-
-/*
- * Used by PRM_VOLTSETUP_CORE_OFF, PRM_VOLTSETUP_CORE_RET_SLEEP,
- * PRM_VOLTSETUP_MM_OFF, PRM_VOLTSETUP_MM_RET_SLEEP, PRM_VOLTSETUP_MPU_OFF,
- * PRM_VOLTSETUP_MPU_RET_SLEEP
- */
-#define OMAP54XX_RAMP_UP_COUNT_SHIFT						0
-#define OMAP54XX_RAMP_UP_COUNT_WIDTH						0x6
-#define OMAP54XX_RAMP_UP_COUNT_MASK						(0x3f << 0)
-
-/*
- * Used by PRM_VOLTSETUP_CORE_OFF, PRM_VOLTSETUP_CORE_RET_SLEEP,
- * PRM_VOLTSETUP_MM_OFF, PRM_VOLTSETUP_MM_RET_SLEEP, PRM_VOLTSETUP_MPU_OFF,
- * PRM_VOLTSETUP_MPU_RET_SLEEP
- */
-#define OMAP54XX_RAMP_UP_PRESCAL_SHIFT						8
-#define OMAP54XX_RAMP_UP_PRESCAL_WIDTH						0x2
-#define OMAP54XX_RAMP_UP_PRESCAL_MASK						(0x3 << 8)
-
-/* Used by PRM_VC_SMPS_CORE_CONFIG */
-#define OMAP54XX_RAV_VDD_CORE_L_SHIFT						25
-#define OMAP54XX_RAV_VDD_CORE_L_WIDTH						0x1
-#define OMAP54XX_RAV_VDD_CORE_L_MASK						(1 << 25)
-
-/* Used by PRM_VC_SMPS_MM_CONFIG */
-#define OMAP54XX_RAV_VDD_MM_L_SHIFT						25
-#define OMAP54XX_RAV_VDD_MM_L_WIDTH						0x1
-#define OMAP54XX_RAV_VDD_MM_L_MASK						(1 << 25)
-
-/* Used by PRM_VC_SMPS_MPU_CONFIG */
-#define OMAP54XX_RAV_VDD_MPU_L_SHIFT						25
-#define OMAP54XX_RAV_VDD_MPU_L_WIDTH						0x1
-#define OMAP54XX_RAV_VDD_MPU_L_MASK						(1 << 25)
-
-/* Used by PRM_VC_VAL_BYPASS */
-#define OMAP54XX_REGADDR_SHIFT							8
-#define OMAP54XX_REGADDR_WIDTH							0x8
-#define OMAP54XX_REGADDR_MASK							(0xff << 8)
-
-/*
- * Used by PRM_VC_VAL_CMD_VDD_CORE_L, PRM_VC_VAL_CMD_VDD_MM_L,
- * PRM_VC_VAL_CMD_VDD_MPU_L
- */
-#define OMAP54XX_RET_SHIFT							8
-#define OMAP54XX_RET_WIDTH							0x8
-#define OMAP54XX_RET_MASK							(0xff << 8)
-
-/* Used by PRM_SLDO_CORE_CTRL, PRM_SLDO_MM_CTRL, PRM_SLDO_MPU_CTRL */
-#define OMAP54XX_RETMODE_ENABLE_SHIFT						0
-#define OMAP54XX_RETMODE_ENABLE_WIDTH						0x1
-#define OMAP54XX_RETMODE_ENABLE_MASK						(1 << 0)
-
-/* Used by PRM_RSTTIME */
-#define OMAP54XX_RSTTIME1_SHIFT							0
-#define OMAP54XX_RSTTIME1_WIDTH							0xa
-#define OMAP54XX_RSTTIME1_MASK							(0x3ff << 0)
-
-/* Used by PRM_RSTTIME */
-#define OMAP54XX_RSTTIME2_SHIFT							10
-#define OMAP54XX_RSTTIME2_WIDTH							0x5
-#define OMAP54XX_RSTTIME2_MASK							(0x1f << 10)
-
-/* Used by RM_IPU_RSTCTRL, RM_IPU_RSTST */
-#define OMAP54XX_RST_CPU0_SHIFT							0
-#define OMAP54XX_RST_CPU0_WIDTH							0x1
-#define OMAP54XX_RST_CPU0_MASK							(1 << 0)
-
-/* Used by RM_IPU_RSTCTRL, RM_IPU_RSTST */
-#define OMAP54XX_RST_CPU1_SHIFT							1
-#define OMAP54XX_RST_CPU1_WIDTH							0x1
-#define OMAP54XX_RST_CPU1_MASK							(1 << 1)
-
-/* Used by RM_DSP_RSTCTRL, RM_DSP_RSTST */
-#define OMAP54XX_RST_DSP_SHIFT							0
-#define OMAP54XX_RST_DSP_WIDTH							0x1
-#define OMAP54XX_RST_DSP_MASK							(1 << 0)
-
-/* Used by RM_DSP_RSTST */
-#define OMAP54XX_RST_DSP_EMU_SHIFT						2
-#define OMAP54XX_RST_DSP_EMU_WIDTH						0x1
-#define OMAP54XX_RST_DSP_EMU_MASK						(1 << 2)
-
-/* Used by RM_DSP_RSTST */
-#define OMAP54XX_RST_DSP_EMU_REQ_SHIFT						3
-#define OMAP54XX_RST_DSP_EMU_REQ_WIDTH						0x1
-#define OMAP54XX_RST_DSP_EMU_REQ_MASK						(1 << 3)
-
-/* Used by RM_DSP_RSTCTRL, RM_DSP_RSTST */
-#define OMAP54XX_RST_DSP_MMU_CACHE_SHIFT					1
-#define OMAP54XX_RST_DSP_MMU_CACHE_WIDTH					0x1
-#define OMAP54XX_RST_DSP_MMU_CACHE_MASK						(1 << 1)
-
-/* Used by RM_IPU_RSTST */
-#define OMAP54XX_RST_EMULATION_CPU0_SHIFT					3
-#define OMAP54XX_RST_EMULATION_CPU0_WIDTH					0x1
-#define OMAP54XX_RST_EMULATION_CPU0_MASK					(1 << 3)
-
-/* Used by RM_IPU_RSTST */
-#define OMAP54XX_RST_EMULATION_CPU1_SHIFT					4
-#define OMAP54XX_RST_EMULATION_CPU1_WIDTH					0x1
-#define OMAP54XX_RST_EMULATION_CPU1_MASK					(1 << 4)
-
-/* Used by RM_IVA_RSTST */
-#define OMAP54XX_RST_EMULATION_SEQ1_SHIFT					3
-#define OMAP54XX_RST_EMULATION_SEQ1_WIDTH					0x1
-#define OMAP54XX_RST_EMULATION_SEQ1_MASK					(1 << 3)
-
-/* Used by RM_IVA_RSTST */
-#define OMAP54XX_RST_EMULATION_SEQ2_SHIFT					4
-#define OMAP54XX_RST_EMULATION_SEQ2_WIDTH					0x1
-#define OMAP54XX_RST_EMULATION_SEQ2_MASK					(1 << 4)
-
-/* Used by PRM_RSTCTRL */
-#define OMAP54XX_RST_GLOBAL_COLD_SW_SHIFT					1
-#define OMAP54XX_RST_GLOBAL_COLD_SW_WIDTH					0x1
-#define OMAP54XX_RST_GLOBAL_COLD_SW_MASK					(1 << 1)
-
-/* Used by PRM_RSTCTRL */
-#define OMAP54XX_RST_GLOBAL_WARM_SW_SHIFT					0
-#define OMAP54XX_RST_GLOBAL_WARM_SW_WIDTH					0x1
-#define OMAP54XX_RST_GLOBAL_WARM_SW_MASK					(1 << 0)
-
-/* Used by RM_IPU_RSTST */
-#define OMAP54XX_RST_ICECRUSHER_CPU0_SHIFT					5
-#define OMAP54XX_RST_ICECRUSHER_CPU0_WIDTH					0x1
-#define OMAP54XX_RST_ICECRUSHER_CPU0_MASK					(1 << 5)
-
-/* Used by RM_IPU_RSTST */
-#define OMAP54XX_RST_ICECRUSHER_CPU1_SHIFT					6
-#define OMAP54XX_RST_ICECRUSHER_CPU1_WIDTH					0x1
-#define OMAP54XX_RST_ICECRUSHER_CPU1_MASK					(1 << 6)
-
-/* Used by RM_IVA_RSTST */
-#define OMAP54XX_RST_ICECRUSHER_SEQ1_SHIFT					5
-#define OMAP54XX_RST_ICECRUSHER_SEQ1_WIDTH					0x1
-#define OMAP54XX_RST_ICECRUSHER_SEQ1_MASK					(1 << 5)
-
-/* Used by RM_IVA_RSTST */
-#define OMAP54XX_RST_ICECRUSHER_SEQ2_SHIFT					6
-#define OMAP54XX_RST_ICECRUSHER_SEQ2_WIDTH					0x1
-#define OMAP54XX_RST_ICECRUSHER_SEQ2_MASK					(1 << 6)
-
-/* Used by RM_IPU_RSTCTRL, RM_IPU_RSTST */
-#define OMAP54XX_RST_IPU_MMU_CACHE_SHIFT					2
-#define OMAP54XX_RST_IPU_MMU_CACHE_WIDTH					0x1
-#define OMAP54XX_RST_IPU_MMU_CACHE_MASK						(1 << 2)
-
-/* Used by RM_IVA_RSTCTRL, RM_IVA_RSTST */
-#define OMAP54XX_RST_LOGIC_SHIFT						2
-#define OMAP54XX_RST_LOGIC_WIDTH						0x1
-#define OMAP54XX_RST_LOGIC_MASK							(1 << 2)
-
-/* Used by RM_IVA_RSTCTRL, RM_IVA_RSTST */
-#define OMAP54XX_RST_SEQ1_SHIFT							0
-#define OMAP54XX_RST_SEQ1_WIDTH							0x1
-#define OMAP54XX_RST_SEQ1_MASK							(1 << 0)
-
-/* Used by RM_IVA_RSTCTRL, RM_IVA_RSTST */
-#define OMAP54XX_RST_SEQ2_SHIFT							1
-#define OMAP54XX_RST_SEQ2_WIDTH							0x1
-#define OMAP54XX_RST_SEQ2_MASK							(1 << 1)
-
-/* Used by REVISION_PRM */
-#define OMAP54XX_R_RTL_SHIFT							11
-#define OMAP54XX_R_RTL_WIDTH							0x5
-#define OMAP54XX_R_RTL_MASK							(0x1f << 11)
-
-/* Used by PRM_VC_SMPS_CORE_CONFIG */
-#define OMAP54XX_SA_VDD_CORE_L_SHIFT						0
-#define OMAP54XX_SA_VDD_CORE_L_WIDTH						0x7
-#define OMAP54XX_SA_VDD_CORE_L_MASK						(0x7f << 0)
-
-/* Used by PRM_VC_SMPS_MM_CONFIG */
-#define OMAP54XX_SA_VDD_MM_L_SHIFT						0
-#define OMAP54XX_SA_VDD_MM_L_WIDTH						0x7
-#define OMAP54XX_SA_VDD_MM_L_MASK						(0x7f << 0)
-
-/* Used by PRM_VC_SMPS_MPU_CONFIG */
-#define OMAP54XX_SA_VDD_MPU_L_SHIFT						0
-#define OMAP54XX_SA_VDD_MPU_L_WIDTH						0x7
-#define OMAP54XX_SA_VDD_MPU_L_MASK						(0x7f << 0)
-
-/* Used by REVISION_PRM */
-#define OMAP54XX_SCHEME_SHIFT							30
-#define OMAP54XX_SCHEME_WIDTH							0x2
-#define OMAP54XX_SCHEME_MASK							(0x3 << 30)
-
-/* Used by PRM_VC_CFG_I2C_CLK */
-#define OMAP54XX_SCLH_SHIFT							0
-#define OMAP54XX_SCLH_WIDTH							0x8
-#define OMAP54XX_SCLH_MASK							(0xff << 0)
-
-/* Used by PRM_VC_CFG_I2C_CLK */
-#define OMAP54XX_SCLL_SHIFT							8
-#define OMAP54XX_SCLL_WIDTH							0x8
-#define OMAP54XX_SCLL_MASK							(0xff << 8)
-
-/* Used by PRM_RSTST */
-#define OMAP54XX_SECURE_WDT_RST_SHIFT						4
-#define OMAP54XX_SECURE_WDT_RST_WIDTH						0x1
-#define OMAP54XX_SECURE_WDT_RST_MASK						(1 << 4)
-
-/* Used by PRM_VC_SMPS_CORE_CONFIG */
-#define OMAP54XX_SEL_SA_VDD_CORE_L_SHIFT					24
-#define OMAP54XX_SEL_SA_VDD_CORE_L_WIDTH					0x1
-#define OMAP54XX_SEL_SA_VDD_CORE_L_MASK						(1 << 24)
-
-/* Used by PRM_VC_SMPS_MM_CONFIG */
-#define OMAP54XX_SEL_SA_VDD_MM_L_SHIFT						24
-#define OMAP54XX_SEL_SA_VDD_MM_L_WIDTH						0x1
-#define OMAP54XX_SEL_SA_VDD_MM_L_MASK						(1 << 24)
-
-/* Used by PRM_VC_SMPS_MPU_CONFIG */
-#define OMAP54XX_SEL_SA_VDD_MPU_L_SHIFT						24
-#define OMAP54XX_SEL_SA_VDD_MPU_L_WIDTH						0x1
-#define OMAP54XX_SEL_SA_VDD_MPU_L_MASK						(1 << 24)
-
-/* Used by PM_IVA_PWRSTCTRL */
-#define OMAP54XX_SL2_MEM_ONSTATE_SHIFT						18
-#define OMAP54XX_SL2_MEM_ONSTATE_WIDTH						0x2
-#define OMAP54XX_SL2_MEM_ONSTATE_MASK						(0x3 << 18)
-
-/* Used by PM_IVA_PWRSTCTRL */
-#define OMAP54XX_SL2_MEM_RETSTATE_SHIFT						9
-#define OMAP54XX_SL2_MEM_RETSTATE_WIDTH						0x1
-#define OMAP54XX_SL2_MEM_RETSTATE_MASK						(1 << 9)
-
-/* Used by PM_IVA_PWRSTST */
-#define OMAP54XX_SL2_MEM_STATEST_SHIFT						6
-#define OMAP54XX_SL2_MEM_STATEST_WIDTH						0x2
-#define OMAP54XX_SL2_MEM_STATEST_MASK						(0x3 << 6)
-
-/* Used by PRM_VC_VAL_BYPASS */
-#define OMAP54XX_SLAVEADDR_SHIFT						0
-#define OMAP54XX_SLAVEADDR_WIDTH						0x7
-#define OMAP54XX_SLAVEADDR_MASK							(0x7f << 0)
-
-/* Used by PRM_SRAM_COUNT */
-#define OMAP54XX_SLPCNT_VALUE_SHIFT						16
-#define OMAP54XX_SLPCNT_VALUE_WIDTH						0x8
-#define OMAP54XX_SLPCNT_VALUE_MASK						(0xff << 16)
-
-/* Used by PRM_VP_CORE_VSTEPMAX, PRM_VP_MM_VSTEPMAX, PRM_VP_MPU_VSTEPMAX */
-#define OMAP54XX_SMPSWAITTIMEMAX_SHIFT						8
-#define OMAP54XX_SMPSWAITTIMEMAX_WIDTH						0x10
-#define OMAP54XX_SMPSWAITTIMEMAX_MASK						(0xffff << 8)
-
-/* Used by PRM_VP_CORE_VSTEPMIN, PRM_VP_MM_VSTEPMIN, PRM_VP_MPU_VSTEPMIN */
-#define OMAP54XX_SMPSWAITTIMEMIN_SHIFT						8
-#define OMAP54XX_SMPSWAITTIMEMIN_WIDTH						0x10
-#define OMAP54XX_SMPSWAITTIMEMIN_MASK						(0xffff << 8)
-
-/* Used by PRM_VC_CORE_ERRST */
-#define OMAP54XX_SMPS_RA_ERR_CORE_SHIFT						1
-#define OMAP54XX_SMPS_RA_ERR_CORE_WIDTH						0x1
-#define OMAP54XX_SMPS_RA_ERR_CORE_MASK						(1 << 1)
-
-/* Used by PRM_VC_MM_ERRST */
-#define OMAP54XX_SMPS_RA_ERR_MM_SHIFT						1
-#define OMAP54XX_SMPS_RA_ERR_MM_WIDTH						0x1
-#define OMAP54XX_SMPS_RA_ERR_MM_MASK						(1 << 1)
-
-/* Used by PRM_VC_MPU_ERRST */
-#define OMAP54XX_SMPS_RA_ERR_MPU_SHIFT						1
-#define OMAP54XX_SMPS_RA_ERR_MPU_WIDTH						0x1
-#define OMAP54XX_SMPS_RA_ERR_MPU_MASK						(1 << 1)
-
-/* Used by PRM_VC_CORE_ERRST */
-#define OMAP54XX_SMPS_SA_ERR_CORE_SHIFT						0
-#define OMAP54XX_SMPS_SA_ERR_CORE_WIDTH						0x1
-#define OMAP54XX_SMPS_SA_ERR_CORE_MASK						(1 << 0)
-
-/* Used by PRM_VC_MM_ERRST */
-#define OMAP54XX_SMPS_SA_ERR_MM_SHIFT						0
-#define OMAP54XX_SMPS_SA_ERR_MM_WIDTH						0x1
-#define OMAP54XX_SMPS_SA_ERR_MM_MASK						(1 << 0)
-
-/* Used by PRM_VC_MPU_ERRST */
-#define OMAP54XX_SMPS_SA_ERR_MPU_SHIFT						0
-#define OMAP54XX_SMPS_SA_ERR_MPU_WIDTH						0x1
-#define OMAP54XX_SMPS_SA_ERR_MPU_MASK						(1 << 0)
-
-/* Used by PRM_VC_CORE_ERRST */
-#define OMAP54XX_SMPS_TIMEOUT_ERR_CORE_SHIFT					2
-#define OMAP54XX_SMPS_TIMEOUT_ERR_CORE_WIDTH					0x1
-#define OMAP54XX_SMPS_TIMEOUT_ERR_CORE_MASK					(1 << 2)
-
-/* Used by PRM_VC_MM_ERRST */
-#define OMAP54XX_SMPS_TIMEOUT_ERR_MM_SHIFT					2
-#define OMAP54XX_SMPS_TIMEOUT_ERR_MM_WIDTH					0x1
-#define OMAP54XX_SMPS_TIMEOUT_ERR_MM_MASK					(1 << 2)
-
-/* Used by PRM_VC_MPU_ERRST */
-#define OMAP54XX_SMPS_TIMEOUT_ERR_MPU_SHIFT					2
-#define OMAP54XX_SMPS_TIMEOUT_ERR_MPU_WIDTH					0x1
-#define OMAP54XX_SMPS_TIMEOUT_ERR_MPU_MASK					(1 << 2)
-
-/* Used by PRM_ABBLDO_MM_SETUP, PRM_ABBLDO_MPU_SETUP */
-#define OMAP54XX_SR2EN_SHIFT							0
-#define OMAP54XX_SR2EN_WIDTH							0x1
-#define OMAP54XX_SR2EN_MASK							(1 << 0)
-
-/* Used by PRM_ABBLDO_MM_CTRL, PRM_ABBLDO_MPU_CTRL */
-#define OMAP54XX_SR2_IN_TRANSITION_SHIFT					6
-#define OMAP54XX_SR2_IN_TRANSITION_WIDTH					0x1
-#define OMAP54XX_SR2_IN_TRANSITION_MASK						(1 << 6)
-
-/* Used by PRM_ABBLDO_MM_CTRL, PRM_ABBLDO_MPU_CTRL */
-#define OMAP54XX_SR2_STATUS_SHIFT						3
-#define OMAP54XX_SR2_STATUS_WIDTH						0x2
-#define OMAP54XX_SR2_STATUS_MASK						(0x3 << 3)
-
-/* Used by PRM_ABBLDO_MM_SETUP, PRM_ABBLDO_MPU_SETUP */
-#define OMAP54XX_SR2_WTCNT_VALUE_SHIFT						8
-#define OMAP54XX_SR2_WTCNT_VALUE_WIDTH						0x8
-#define OMAP54XX_SR2_WTCNT_VALUE_MASK						(0xff << 8)
-
-/* Used by PRM_SLDO_CORE_CTRL, PRM_SLDO_MM_CTRL, PRM_SLDO_MPU_CTRL */
-#define OMAP54XX_SRAMLDO_STATUS_SHIFT						8
-#define OMAP54XX_SRAMLDO_STATUS_WIDTH						0x1
-#define OMAP54XX_SRAMLDO_STATUS_MASK						(1 << 8)
-
-/* Used by PRM_SLDO_CORE_CTRL, PRM_SLDO_MM_CTRL, PRM_SLDO_MPU_CTRL */
-#define OMAP54XX_SRAM_IN_TRANSITION_SHIFT					9
-#define OMAP54XX_SRAM_IN_TRANSITION_WIDTH					0x1
-#define OMAP54XX_SRAM_IN_TRANSITION_MASK					(1 << 9)
-
-/* Used by PRM_VC_CFG_I2C_MODE */
-#define OMAP54XX_SRMODEEN_SHIFT							4
-#define OMAP54XX_SRMODEEN_WIDTH							0x1
-#define OMAP54XX_SRMODEEN_MASK							(1 << 4)
-
-/* Used by PRM_VOLTSETUP_WARMRESET */
-#define OMAP54XX_STABLE_COUNT_SHIFT						0
-#define OMAP54XX_STABLE_COUNT_WIDTH						0x6
-#define OMAP54XX_STABLE_COUNT_MASK						(0x3f << 0)
-
-/* Used by PRM_VOLTSETUP_WARMRESET */
-#define OMAP54XX_STABLE_PRESCAL_SHIFT						8
-#define OMAP54XX_STABLE_PRESCAL_WIDTH						0x2
-#define OMAP54XX_STABLE_PRESCAL_MASK						(0x3 << 8)
-
-/* Used by PRM_BANDGAP_SETUP */
-#define OMAP54XX_STARTUP_COUNT_SHIFT						0
-#define OMAP54XX_STARTUP_COUNT_WIDTH						0x8
-#define OMAP54XX_STARTUP_COUNT_MASK						(0xff << 0)
-
-/* Renamed from STARTUP_COUNT Used by PRM_SRAM_COUNT */
-#define OMAP54XX_STARTUP_COUNT_24_31_SHIFT					24
-#define OMAP54XX_STARTUP_COUNT_24_31_WIDTH					0x8
-#define OMAP54XX_STARTUP_COUNT_24_31_MASK					(0xff << 24)
-
-/* Used by PM_IVA_PWRSTCTRL */
-#define OMAP54XX_TCM1_MEM_ONSTATE_SHIFT						20
-#define OMAP54XX_TCM1_MEM_ONSTATE_WIDTH						0x2
-#define OMAP54XX_TCM1_MEM_ONSTATE_MASK						(0x3 << 20)
-
-/* Used by PM_IVA_PWRSTCTRL */
-#define OMAP54XX_TCM1_MEM_RETSTATE_SHIFT					10
-#define OMAP54XX_TCM1_MEM_RETSTATE_WIDTH					0x1
-#define OMAP54XX_TCM1_MEM_RETSTATE_MASK						(1 << 10)
-
-/* Used by PM_IVA_PWRSTST */
-#define OMAP54XX_TCM1_MEM_STATEST_SHIFT						8
-#define OMAP54XX_TCM1_MEM_STATEST_WIDTH						0x2
-#define OMAP54XX_TCM1_MEM_STATEST_MASK						(0x3 << 8)
-
-/* Used by PM_IVA_PWRSTCTRL */
-#define OMAP54XX_TCM2_MEM_ONSTATE_SHIFT						22
-#define OMAP54XX_TCM2_MEM_ONSTATE_WIDTH						0x2
-#define OMAP54XX_TCM2_MEM_ONSTATE_MASK						(0x3 << 22)
-
-/* Used by PM_IVA_PWRSTCTRL */
-#define OMAP54XX_TCM2_MEM_RETSTATE_SHIFT					11
-#define OMAP54XX_TCM2_MEM_RETSTATE_WIDTH					0x1
-#define OMAP54XX_TCM2_MEM_RETSTATE_MASK						(1 << 11)
-
-/* Used by PM_IVA_PWRSTST */
-#define OMAP54XX_TCM2_MEM_STATEST_SHIFT						10
-#define OMAP54XX_TCM2_MEM_STATEST_WIDTH						0x2
-#define OMAP54XX_TCM2_MEM_STATEST_MASK						(0x3 << 10)
-
-/* Used by PRM_VP_CORE_VLIMITTO, PRM_VP_MM_VLIMITTO, PRM_VP_MPU_VLIMITTO */
-#define OMAP54XX_TIMEOUT_SHIFT							0
-#define OMAP54XX_TIMEOUT_WIDTH							0x10
-#define OMAP54XX_TIMEOUT_MASK							(0xffff << 0)
-
-/* Used by PRM_VP_CORE_CONFIG, PRM_VP_MM_CONFIG, PRM_VP_MPU_CONFIG */
-#define OMAP54XX_TIMEOUTEN_SHIFT						3
-#define OMAP54XX_TIMEOUTEN_WIDTH						0x1
-#define OMAP54XX_TIMEOUTEN_MASK							(1 << 3)
-
-/* Used by PRM_IRQENABLE_IPU, PRM_IRQENABLE_MPU */
-#define OMAP54XX_TRANSITION_EN_SHIFT						8
-#define OMAP54XX_TRANSITION_EN_WIDTH						0x1
-#define OMAP54XX_TRANSITION_EN_MASK						(1 << 8)
-
-/* Used by PRM_IRQSTATUS_IPU, PRM_IRQSTATUS_MPU */
-#define OMAP54XX_TRANSITION_ST_SHIFT						8
-#define OMAP54XX_TRANSITION_ST_WIDTH						0x1
-#define OMAP54XX_TRANSITION_ST_MASK						(1 << 8)
-
-/* Used by PRM_DEBUG_TRANS_CFG */
-#define OMAP54XX_TRIGGER_CLEAR_SHIFT						2
-#define OMAP54XX_TRIGGER_CLEAR_WIDTH						0x1
-#define OMAP54XX_TRIGGER_CLEAR_MASK						(1 << 2)
-
-/* Used by PRM_RSTST */
-#define OMAP54XX_TSHUT_CORE_RST_SHIFT						13
-#define OMAP54XX_TSHUT_CORE_RST_WIDTH						0x1
-#define OMAP54XX_TSHUT_CORE_RST_MASK						(1 << 13)
-
-/* Used by PRM_RSTST */
-#define OMAP54XX_TSHUT_MM_RST_SHIFT						12
-#define OMAP54XX_TSHUT_MM_RST_WIDTH						0x1
-#define OMAP54XX_TSHUT_MM_RST_MASK						(1 << 12)
-
-/* Used by PRM_RSTST */
-#define OMAP54XX_TSHUT_MPU_RST_SHIFT						11
-#define OMAP54XX_TSHUT_MPU_RST_WIDTH						0x1
-#define OMAP54XX_TSHUT_MPU_RST_MASK						(1 << 11)
-
-/* Used by PRM_VC_VAL_BYPASS */
-#define OMAP54XX_VALID_SHIFT							24
-#define OMAP54XX_VALID_WIDTH							0x1
-#define OMAP54XX_VALID_MASK							(1 << 24)
-
-/* Used by PRM_IRQENABLE_IPU, PRM_IRQENABLE_MPU */
-#define OMAP54XX_VC_BYPASSACK_EN_SHIFT						14
-#define OMAP54XX_VC_BYPASSACK_EN_WIDTH						0x1
-#define OMAP54XX_VC_BYPASSACK_EN_MASK						(1 << 14)
-
-/* Used by PRM_IRQSTATUS_IPU, PRM_IRQSTATUS_MPU */
-#define OMAP54XX_VC_BYPASSACK_ST_SHIFT						14
-#define OMAP54XX_VC_BYPASSACK_ST_WIDTH						0x1
-#define OMAP54XX_VC_BYPASSACK_ST_MASK						(1 << 14)
-
-/* Used by PRM_IRQENABLE_IPU, PRM_IRQENABLE_MPU */
-#define OMAP54XX_VC_CORE_VPACK_EN_SHIFT						22
-#define OMAP54XX_VC_CORE_VPACK_EN_WIDTH						0x1
-#define OMAP54XX_VC_CORE_VPACK_EN_MASK						(1 << 22)
-
-/* Used by PRM_IRQSTATUS_IPU, PRM_IRQSTATUS_MPU */
-#define OMAP54XX_VC_CORE_VPACK_ST_SHIFT						22
-#define OMAP54XX_VC_CORE_VPACK_ST_WIDTH						0x1
-#define OMAP54XX_VC_CORE_VPACK_ST_MASK						(1 << 22)
-
-/* Used by PRM_IRQENABLE_IPU, PRM_IRQENABLE_MPU */
-#define OMAP54XX_VC_MM_VPACK_EN_SHIFT						30
-#define OMAP54XX_VC_MM_VPACK_EN_WIDTH						0x1
-#define OMAP54XX_VC_MM_VPACK_EN_MASK						(1 << 30)
-
-/* Used by PRM_IRQSTATUS_IPU, PRM_IRQSTATUS_MPU */
-#define OMAP54XX_VC_MM_VPACK_ST_SHIFT						30
-#define OMAP54XX_VC_MM_VPACK_ST_WIDTH						0x1
-#define OMAP54XX_VC_MM_VPACK_ST_MASK						(1 << 30)
-
-/* Used by PRM_IRQENABLE_MPU_2 */
-#define OMAP54XX_VC_MPU_VPACK_EN_SHIFT						6
-#define OMAP54XX_VC_MPU_VPACK_EN_WIDTH						0x1
-#define OMAP54XX_VC_MPU_VPACK_EN_MASK						(1 << 6)
-
-/* Used by PRM_IRQSTATUS_MPU_2 */
-#define OMAP54XX_VC_MPU_VPACK_ST_SHIFT						6
-#define OMAP54XX_VC_MPU_VPACK_ST_WIDTH						0x1
-#define OMAP54XX_VC_MPU_VPACK_ST_MASK						(1 << 6)
-
-/* Used by PRM_IRQENABLE_IPU, PRM_IRQENABLE_MPU */
-#define OMAP54XX_VC_RAERR_EN_SHIFT						12
-#define OMAP54XX_VC_RAERR_EN_WIDTH						0x1
-#define OMAP54XX_VC_RAERR_EN_MASK						(1 << 12)
-
-/* Used by PRM_IRQSTATUS_IPU, PRM_IRQSTATUS_MPU */
-#define OMAP54XX_VC_RAERR_ST_SHIFT						12
-#define OMAP54XX_VC_RAERR_ST_WIDTH						0x1
-#define OMAP54XX_VC_RAERR_ST_MASK						(1 << 12)
-
-/* Used by PRM_IRQENABLE_IPU, PRM_IRQENABLE_MPU */
-#define OMAP54XX_VC_SAERR_EN_SHIFT						11
-#define OMAP54XX_VC_SAERR_EN_WIDTH						0x1
-#define OMAP54XX_VC_SAERR_EN_MASK						(1 << 11)
-
-/* Used by PRM_IRQSTATUS_IPU, PRM_IRQSTATUS_MPU */
-#define OMAP54XX_VC_SAERR_ST_SHIFT						11
-#define OMAP54XX_VC_SAERR_ST_WIDTH						0x1
-#define OMAP54XX_VC_SAERR_ST_MASK						(1 << 11)
-
-/* Used by PRM_IRQENABLE_IPU, PRM_IRQENABLE_MPU */
-#define OMAP54XX_VC_TOERR_EN_SHIFT						13
-#define OMAP54XX_VC_TOERR_EN_WIDTH						0x1
-#define OMAP54XX_VC_TOERR_EN_MASK						(1 << 13)
-
-/* Used by PRM_IRQSTATUS_IPU, PRM_IRQSTATUS_MPU */
-#define OMAP54XX_VC_TOERR_ST_SHIFT						13
-#define OMAP54XX_VC_TOERR_ST_WIDTH						0x1
-#define OMAP54XX_VC_TOERR_ST_MASK						(1 << 13)
-
-/* Used by PRM_VP_CORE_VLIMITTO, PRM_VP_MM_VLIMITTO, PRM_VP_MPU_VLIMITTO */
-#define OMAP54XX_VDDMAX_SHIFT							24
-#define OMAP54XX_VDDMAX_WIDTH							0x8
-#define OMAP54XX_VDDMAX_MASK							(0xff << 24)
-
-/* Used by PRM_VP_CORE_VLIMITTO, PRM_VP_MM_VLIMITTO, PRM_VP_MPU_VLIMITTO */
-#define OMAP54XX_VDDMIN_SHIFT							16
-#define OMAP54XX_VDDMIN_WIDTH							0x8
-#define OMAP54XX_VDDMIN_MASK							(0xff << 16)
-
-/* Used by PRM_VOLTCTRL */
-#define OMAP54XX_VDD_CORE_I2C_DISABLE_SHIFT					12
-#define OMAP54XX_VDD_CORE_I2C_DISABLE_WIDTH					0x1
-#define OMAP54XX_VDD_CORE_I2C_DISABLE_MASK					(1 << 12)
-
-/* Used by PRM_RSTST */
-#define OMAP54XX_VDD_CORE_VOLT_MGR_RST_SHIFT					8
-#define OMAP54XX_VDD_CORE_VOLT_MGR_RST_WIDTH					0x1
-#define OMAP54XX_VDD_CORE_VOLT_MGR_RST_MASK					(1 << 8)
-
-/* Used by PRM_VOLTCTRL */
-#define OMAP54XX_VDD_MM_I2C_DISABLE_SHIFT					14
-#define OMAP54XX_VDD_MM_I2C_DISABLE_WIDTH					0x1
-#define OMAP54XX_VDD_MM_I2C_DISABLE_MASK					(1 << 14)
-
-/* Used by PRM_VOLTCTRL */
-#define OMAP54XX_VDD_MM_PRESENCE_SHIFT						9
-#define OMAP54XX_VDD_MM_PRESENCE_WIDTH						0x1
-#define OMAP54XX_VDD_MM_PRESENCE_MASK						(1 << 9)
-
-/* Used by PRM_RSTST */
-#define OMAP54XX_VDD_MM_VOLT_MGR_RST_SHIFT					7
-#define OMAP54XX_VDD_MM_VOLT_MGR_RST_WIDTH					0x1
-#define OMAP54XX_VDD_MM_VOLT_MGR_RST_MASK					(1 << 7)
-
-/* Used by PRM_VOLTCTRL */
-#define OMAP54XX_VDD_MPU_I2C_DISABLE_SHIFT					13
-#define OMAP54XX_VDD_MPU_I2C_DISABLE_WIDTH					0x1
-#define OMAP54XX_VDD_MPU_I2C_DISABLE_MASK					(1 << 13)
-
-/* Used by PRM_VOLTCTRL */
-#define OMAP54XX_VDD_MPU_PRESENCE_SHIFT						8
-#define OMAP54XX_VDD_MPU_PRESENCE_WIDTH						0x1
-#define OMAP54XX_VDD_MPU_PRESENCE_MASK						(1 << 8)
-
-/* Used by PRM_RSTST */
-#define OMAP54XX_VDD_MPU_VOLT_MGR_RST_SHIFT					6
-#define OMAP54XX_VDD_MPU_VOLT_MGR_RST_WIDTH					0x1
-#define OMAP54XX_VDD_MPU_VOLT_MGR_RST_MASK					(1 << 6)
-
-/* Used by PRM_VC_CORE_ERRST */
-#define OMAP54XX_VFSM_RA_ERR_CORE_SHIFT						4
-#define OMAP54XX_VFSM_RA_ERR_CORE_WIDTH						0x1
-#define OMAP54XX_VFSM_RA_ERR_CORE_MASK						(1 << 4)
-
-/* Used by PRM_VC_MM_ERRST */
-#define OMAP54XX_VFSM_RA_ERR_MM_SHIFT						4
-#define OMAP54XX_VFSM_RA_ERR_MM_WIDTH						0x1
-#define OMAP54XX_VFSM_RA_ERR_MM_MASK						(1 << 4)
-
-/* Used by PRM_VC_MPU_ERRST */
-#define OMAP54XX_VFSM_RA_ERR_MPU_SHIFT						4
-#define OMAP54XX_VFSM_RA_ERR_MPU_WIDTH						0x1
-#define OMAP54XX_VFSM_RA_ERR_MPU_MASK						(1 << 4)
-
-/* Used by PRM_VC_CORE_ERRST */
-#define OMAP54XX_VFSM_SA_ERR_CORE_SHIFT						3
-#define OMAP54XX_VFSM_SA_ERR_CORE_WIDTH						0x1
-#define OMAP54XX_VFSM_SA_ERR_CORE_MASK						(1 << 3)
-
-/* Used by PRM_VC_MM_ERRST */
-#define OMAP54XX_VFSM_SA_ERR_MM_SHIFT						3
-#define OMAP54XX_VFSM_SA_ERR_MM_WIDTH						0x1
-#define OMAP54XX_VFSM_SA_ERR_MM_MASK						(1 << 3)
-
-/* Used by PRM_VC_MPU_ERRST */
-#define OMAP54XX_VFSM_SA_ERR_MPU_SHIFT						3
-#define OMAP54XX_VFSM_SA_ERR_MPU_WIDTH						0x1
-#define OMAP54XX_VFSM_SA_ERR_MPU_MASK						(1 << 3)
-
-/* Used by PRM_VC_CORE_ERRST */
-#define OMAP54XX_VFSM_TIMEOUT_ERR_CORE_SHIFT					5
-#define OMAP54XX_VFSM_TIMEOUT_ERR_CORE_WIDTH					0x1
-#define OMAP54XX_VFSM_TIMEOUT_ERR_CORE_MASK					(1 << 5)
-
-/* Used by PRM_VC_MM_ERRST */
-#define OMAP54XX_VFSM_TIMEOUT_ERR_MM_SHIFT					5
-#define OMAP54XX_VFSM_TIMEOUT_ERR_MM_WIDTH					0x1
-#define OMAP54XX_VFSM_TIMEOUT_ERR_MM_MASK					(1 << 5)
-
-/* Used by PRM_VC_MPU_ERRST */
-#define OMAP54XX_VFSM_TIMEOUT_ERR_MPU_SHIFT					5
-#define OMAP54XX_VFSM_TIMEOUT_ERR_MPU_WIDTH					0x1
-#define OMAP54XX_VFSM_TIMEOUT_ERR_MPU_MASK					(1 << 5)
-
-/* Used by PRM_VC_SMPS_CORE_CONFIG */
-#define OMAP54XX_VOLRA_VDD_CORE_L_SHIFT						8
-#define OMAP54XX_VOLRA_VDD_CORE_L_WIDTH						0x8
-#define OMAP54XX_VOLRA_VDD_CORE_L_MASK						(0xff << 8)
-
-/* Used by PRM_VC_SMPS_MM_CONFIG */
-#define OMAP54XX_VOLRA_VDD_MM_L_SHIFT						8
-#define OMAP54XX_VOLRA_VDD_MM_L_WIDTH						0x8
-#define OMAP54XX_VOLRA_VDD_MM_L_MASK						(0xff << 8)
-
-/* Used by PRM_VC_SMPS_MPU_CONFIG */
-#define OMAP54XX_VOLRA_VDD_MPU_L_SHIFT						8
-#define OMAP54XX_VOLRA_VDD_MPU_L_WIDTH						0x8
-#define OMAP54XX_VOLRA_VDD_MPU_L_MASK						(0xff << 8)
-
-/* Used by PRM_VOLTST_MM, PRM_VOLTST_MPU */
-#define OMAP54XX_VOLTSTATEST_SHIFT						0
-#define OMAP54XX_VOLTSTATEST_WIDTH						0x2
-#define OMAP54XX_VOLTSTATEST_MASK						(0x3 << 0)
-
-/* Used by PRM_VP_CORE_CONFIG, PRM_VP_MM_CONFIG, PRM_VP_MPU_CONFIG */
-#define OMAP54XX_VPENABLE_SHIFT							0
-#define OMAP54XX_VPENABLE_WIDTH							0x1
-#define OMAP54XX_VPENABLE_MASK							(1 << 0)
-
-/* Used by PRM_VP_CORE_STATUS, PRM_VP_MM_STATUS, PRM_VP_MPU_STATUS */
-#define OMAP54XX_VPINIDLE_SHIFT							0
-#define OMAP54XX_VPINIDLE_WIDTH							0x1
-#define OMAP54XX_VPINIDLE_MASK							(1 << 0)
-
-/* Used by PRM_VP_CORE_VOLTAGE, PRM_VP_MM_VOLTAGE, PRM_VP_MPU_VOLTAGE */
-#define OMAP54XX_VPVOLTAGE_SHIFT						0
-#define OMAP54XX_VPVOLTAGE_WIDTH						0x8
-#define OMAP54XX_VPVOLTAGE_MASK							(0xff << 0)
-
-/* Used by PRM_IRQENABLE_IPU, PRM_IRQENABLE_MPU */
-#define OMAP54XX_VP_CORE_EQVALUE_EN_SHIFT					20
-#define OMAP54XX_VP_CORE_EQVALUE_EN_WIDTH					0x1
-#define OMAP54XX_VP_CORE_EQVALUE_EN_MASK					(1 << 20)
-
-/* Used by PRM_IRQSTATUS_IPU, PRM_IRQSTATUS_MPU */
-#define OMAP54XX_VP_CORE_EQVALUE_ST_SHIFT					20
-#define OMAP54XX_VP_CORE_EQVALUE_ST_WIDTH					0x1
-#define OMAP54XX_VP_CORE_EQVALUE_ST_MASK					(1 << 20)
-
-/* Used by PRM_IRQENABLE_IPU, PRM_IRQENABLE_MPU */
-#define OMAP54XX_VP_CORE_MAXVDD_EN_SHIFT					18
-#define OMAP54XX_VP_CORE_MAXVDD_EN_WIDTH					0x1
-#define OMAP54XX_VP_CORE_MAXVDD_EN_MASK						(1 << 18)
-
-/* Used by PRM_IRQSTATUS_IPU, PRM_IRQSTATUS_MPU */
-#define OMAP54XX_VP_CORE_MAXVDD_ST_SHIFT					18
-#define OMAP54XX_VP_CORE_MAXVDD_ST_WIDTH					0x1
-#define OMAP54XX_VP_CORE_MAXVDD_ST_MASK						(1 << 18)
-
-/* Used by PRM_IRQENABLE_IPU, PRM_IRQENABLE_MPU */
-#define OMAP54XX_VP_CORE_MINVDD_EN_SHIFT					17
-#define OMAP54XX_VP_CORE_MINVDD_EN_WIDTH					0x1
-#define OMAP54XX_VP_CORE_MINVDD_EN_MASK						(1 << 17)
-
-/* Used by PRM_IRQSTATUS_IPU, PRM_IRQSTATUS_MPU */
-#define OMAP54XX_VP_CORE_MINVDD_ST_SHIFT					17
-#define OMAP54XX_VP_CORE_MINVDD_ST_WIDTH					0x1
-#define OMAP54XX_VP_CORE_MINVDD_ST_MASK						(1 << 17)
-
-/* Used by PRM_IRQENABLE_IPU, PRM_IRQENABLE_MPU */
-#define OMAP54XX_VP_CORE_NOSMPSACK_EN_SHIFT					19
-#define OMAP54XX_VP_CORE_NOSMPSACK_EN_WIDTH					0x1
-#define OMAP54XX_VP_CORE_NOSMPSACK_EN_MASK					(1 << 19)
-
-/* Used by PRM_IRQSTATUS_IPU, PRM_IRQSTATUS_MPU */
-#define OMAP54XX_VP_CORE_NOSMPSACK_ST_SHIFT					19
-#define OMAP54XX_VP_CORE_NOSMPSACK_ST_WIDTH					0x1
-#define OMAP54XX_VP_CORE_NOSMPSACK_ST_MASK					(1 << 19)
-
-/* Used by PRM_IRQENABLE_IPU, PRM_IRQENABLE_MPU */
-#define OMAP54XX_VP_CORE_OPPCHANGEDONE_EN_SHIFT					16
-#define OMAP54XX_VP_CORE_OPPCHANGEDONE_EN_WIDTH					0x1
-#define OMAP54XX_VP_CORE_OPPCHANGEDONE_EN_MASK					(1 << 16)
-
-/* Used by PRM_IRQSTATUS_IPU, PRM_IRQSTATUS_MPU */
-#define OMAP54XX_VP_CORE_OPPCHANGEDONE_ST_SHIFT					16
-#define OMAP54XX_VP_CORE_OPPCHANGEDONE_ST_WIDTH					0x1
-#define OMAP54XX_VP_CORE_OPPCHANGEDONE_ST_MASK					(1 << 16)
-
-/* Used by PRM_IRQENABLE_IPU, PRM_IRQENABLE_MPU */
-#define OMAP54XX_VP_CORE_TRANXDONE_EN_SHIFT					21
-#define OMAP54XX_VP_CORE_TRANXDONE_EN_WIDTH					0x1
-#define OMAP54XX_VP_CORE_TRANXDONE_EN_MASK					(1 << 21)
-
-/* Used by PRM_IRQSTATUS_IPU, PRM_IRQSTATUS_MPU */
-#define OMAP54XX_VP_CORE_TRANXDONE_ST_SHIFT					21
-#define OMAP54XX_VP_CORE_TRANXDONE_ST_WIDTH					0x1
-#define OMAP54XX_VP_CORE_TRANXDONE_ST_MASK					(1 << 21)
-
-/* Used by PRM_IRQENABLE_IPU, PRM_IRQENABLE_MPU */
-#define OMAP54XX_VP_MM_EQVALUE_EN_SHIFT						28
-#define OMAP54XX_VP_MM_EQVALUE_EN_WIDTH						0x1
-#define OMAP54XX_VP_MM_EQVALUE_EN_MASK						(1 << 28)
-
-/* Used by PRM_IRQSTATUS_IPU, PRM_IRQSTATUS_MPU */
-#define OMAP54XX_VP_MM_EQVALUE_ST_SHIFT						28
-#define OMAP54XX_VP_MM_EQVALUE_ST_WIDTH						0x1
-#define OMAP54XX_VP_MM_EQVALUE_ST_MASK						(1 << 28)
-
-/* Used by PRM_IRQENABLE_IPU, PRM_IRQENABLE_MPU */
-#define OMAP54XX_VP_MM_MAXVDD_EN_SHIFT						26
-#define OMAP54XX_VP_MM_MAXVDD_EN_WIDTH						0x1
-#define OMAP54XX_VP_MM_MAXVDD_EN_MASK						(1 << 26)
-
-/* Used by PRM_IRQSTATUS_IPU, PRM_IRQSTATUS_MPU */
-#define OMAP54XX_VP_MM_MAXVDD_ST_SHIFT						26
-#define OMAP54XX_VP_MM_MAXVDD_ST_WIDTH						0x1
-#define OMAP54XX_VP_MM_MAXVDD_ST_MASK						(1 << 26)
-
-/* Used by PRM_IRQENABLE_IPU, PRM_IRQENABLE_MPU */
-#define OMAP54XX_VP_MM_MINVDD_EN_SHIFT						25
-#define OMAP54XX_VP_MM_MINVDD_EN_WIDTH						0x1
-#define OMAP54XX_VP_MM_MINVDD_EN_MASK						(1 << 25)
-
-/* Used by PRM_IRQSTATUS_IPU, PRM_IRQSTATUS_MPU */
-#define OMAP54XX_VP_MM_MINVDD_ST_SHIFT						25
-#define OMAP54XX_VP_MM_MINVDD_ST_WIDTH						0x1
-#define OMAP54XX_VP_MM_MINVDD_ST_MASK						(1 << 25)
-
-/* Used by PRM_IRQENABLE_IPU, PRM_IRQENABLE_MPU */
-#define OMAP54XX_VP_MM_NOSMPSACK_EN_SHIFT					27
-#define OMAP54XX_VP_MM_NOSMPSACK_EN_WIDTH					0x1
-#define OMAP54XX_VP_MM_NOSMPSACK_EN_MASK					(1 << 27)
-
-/* Used by PRM_IRQSTATUS_IPU, PRM_IRQSTATUS_MPU */
-#define OMAP54XX_VP_MM_NOSMPSACK_ST_SHIFT					27
-#define OMAP54XX_VP_MM_NOSMPSACK_ST_WIDTH					0x1
-#define OMAP54XX_VP_MM_NOSMPSACK_ST_MASK					(1 << 27)
-
-/* Used by PRM_IRQENABLE_IPU, PRM_IRQENABLE_MPU */
-#define OMAP54XX_VP_MM_OPPCHANGEDONE_EN_SHIFT					24
-#define OMAP54XX_VP_MM_OPPCHANGEDONE_EN_WIDTH					0x1
-#define OMAP54XX_VP_MM_OPPCHANGEDONE_EN_MASK					(1 << 24)
-
-/* Used by PRM_IRQSTATUS_IPU, PRM_IRQSTATUS_MPU */
-#define OMAP54XX_VP_MM_OPPCHANGEDONE_ST_SHIFT					24
-#define OMAP54XX_VP_MM_OPPCHANGEDONE_ST_WIDTH					0x1
-#define OMAP54XX_VP_MM_OPPCHANGEDONE_ST_MASK					(1 << 24)
-
-/* Used by PRM_IRQENABLE_IPU, PRM_IRQENABLE_MPU */
-#define OMAP54XX_VP_MM_TRANXDONE_EN_SHIFT					29
-#define OMAP54XX_VP_MM_TRANXDONE_EN_WIDTH					0x1
-#define OMAP54XX_VP_MM_TRANXDONE_EN_MASK					(1 << 29)
-
-/* Used by PRM_IRQSTATUS_IPU, PRM_IRQSTATUS_MPU */
-#define OMAP54XX_VP_MM_TRANXDONE_ST_SHIFT					29
-#define OMAP54XX_VP_MM_TRANXDONE_ST_WIDTH					0x1
-#define OMAP54XX_VP_MM_TRANXDONE_ST_MASK					(1 << 29)
-
-/* Used by PRM_IRQENABLE_MPU_2 */
-#define OMAP54XX_VP_MPU_EQVALUE_EN_SHIFT					4
-#define OMAP54XX_VP_MPU_EQVALUE_EN_WIDTH					0x1
-#define OMAP54XX_VP_MPU_EQVALUE_EN_MASK						(1 << 4)
-
-/* Used by PRM_IRQSTATUS_MPU_2 */
-#define OMAP54XX_VP_MPU_EQVALUE_ST_SHIFT					4
-#define OMAP54XX_VP_MPU_EQVALUE_ST_WIDTH					0x1
-#define OMAP54XX_VP_MPU_EQVALUE_ST_MASK						(1 << 4)
-
-/* Used by PRM_IRQENABLE_MPU_2 */
-#define OMAP54XX_VP_MPU_MAXVDD_EN_SHIFT						2
-#define OMAP54XX_VP_MPU_MAXVDD_EN_WIDTH						0x1
-#define OMAP54XX_VP_MPU_MAXVDD_EN_MASK						(1 << 2)
-
-/* Used by PRM_IRQSTATUS_MPU_2 */
-#define OMAP54XX_VP_MPU_MAXVDD_ST_SHIFT						2
-#define OMAP54XX_VP_MPU_MAXVDD_ST_WIDTH						0x1
-#define OMAP54XX_VP_MPU_MAXVDD_ST_MASK						(1 << 2)
-
-/* Used by PRM_IRQENABLE_MPU_2 */
-#define OMAP54XX_VP_MPU_MINVDD_EN_SHIFT						1
-#define OMAP54XX_VP_MPU_MINVDD_EN_WIDTH						0x1
-#define OMAP54XX_VP_MPU_MINVDD_EN_MASK						(1 << 1)
-
-/* Used by PRM_IRQSTATUS_MPU_2 */
-#define OMAP54XX_VP_MPU_MINVDD_ST_SHIFT						1
-#define OMAP54XX_VP_MPU_MINVDD_ST_WIDTH						0x1
-#define OMAP54XX_VP_MPU_MINVDD_ST_MASK						(1 << 1)
-
-/* Used by PRM_IRQENABLE_MPU_2 */
-#define OMAP54XX_VP_MPU_NOSMPSACK_EN_SHIFT					3
-#define OMAP54XX_VP_MPU_NOSMPSACK_EN_WIDTH					0x1
-#define OMAP54XX_VP_MPU_NOSMPSACK_EN_MASK					(1 << 3)
-
-/* Used by PRM_IRQSTATUS_MPU_2 */
-#define OMAP54XX_VP_MPU_NOSMPSACK_ST_SHIFT					3
-#define OMAP54XX_VP_MPU_NOSMPSACK_ST_WIDTH					0x1
-#define OMAP54XX_VP_MPU_NOSMPSACK_ST_MASK					(1 << 3)
-
-/* Used by PRM_IRQENABLE_MPU_2 */
-#define OMAP54XX_VP_MPU_OPPCHANGEDONE_EN_SHIFT					0
-#define OMAP54XX_VP_MPU_OPPCHANGEDONE_EN_WIDTH					0x1
-#define OMAP54XX_VP_MPU_OPPCHANGEDONE_EN_MASK					(1 << 0)
-
-/* Used by PRM_IRQSTATUS_MPU_2 */
-#define OMAP54XX_VP_MPU_OPPCHANGEDONE_ST_SHIFT					0
-#define OMAP54XX_VP_MPU_OPPCHANGEDONE_ST_WIDTH					0x1
-#define OMAP54XX_VP_MPU_OPPCHANGEDONE_ST_MASK					(1 << 0)
-
-/* Used by PRM_IRQENABLE_MPU_2 */
-#define OMAP54XX_VP_MPU_TRANXDONE_EN_SHIFT					5
-#define OMAP54XX_VP_MPU_TRANXDONE_EN_WIDTH					0x1
-#define OMAP54XX_VP_MPU_TRANXDONE_EN_MASK					(1 << 5)
-
-/* Used by PRM_IRQSTATUS_MPU_2 */
-#define OMAP54XX_VP_MPU_TRANXDONE_ST_SHIFT					5
-#define OMAP54XX_VP_MPU_TRANXDONE_ST_WIDTH					0x1
-#define OMAP54XX_VP_MPU_TRANXDONE_ST_MASK					(1 << 5)
-
-/* Used by PRM_SRAM_COUNT */
-#define OMAP54XX_VSETUPCNT_VALUE_SHIFT						8
-#define OMAP54XX_VSETUPCNT_VALUE_WIDTH						0x8
-#define OMAP54XX_VSETUPCNT_VALUE_MASK						(0xff << 8)
-
-/* Used by PRM_VP_CORE_VSTEPMAX, PRM_VP_MM_VSTEPMAX, PRM_VP_MPU_VSTEPMAX */
-#define OMAP54XX_VSTEPMAX_SHIFT							0
-#define OMAP54XX_VSTEPMAX_WIDTH							0x8
-#define OMAP54XX_VSTEPMAX_MASK							(0xff << 0)
-
-/* Used by PRM_VP_CORE_VSTEPMIN, PRM_VP_MM_VSTEPMIN, PRM_VP_MPU_VSTEPMIN */
-#define OMAP54XX_VSTEPMIN_SHIFT							0
-#define OMAP54XX_VSTEPMIN_WIDTH							0x8
-#define OMAP54XX_VSTEPMIN_MASK							(0xff << 0)
-
-/* Used by PM_DSS_DSS_WKDEP */
-#define OMAP54XX_WKUPDEP_DISPC_DSP_SHIFT					2
-#define OMAP54XX_WKUPDEP_DISPC_DSP_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_DISPC_DSP_MASK						(1 << 2)
-
-/* Used by PM_DSS_DSS_WKDEP */
-#define OMAP54XX_WKUPDEP_DISPC_IPU_SHIFT					1
-#define OMAP54XX_WKUPDEP_DISPC_IPU_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_DISPC_IPU_MASK						(1 << 1)
-
-/* Used by PM_DSS_DSS_WKDEP */
-#define OMAP54XX_WKUPDEP_DISPC_MPU_SHIFT					0
-#define OMAP54XX_WKUPDEP_DISPC_MPU_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_DISPC_MPU_MASK						(1 << 0)
-
-/* Used by PM_DSS_DSS_WKDEP */
-#define OMAP54XX_WKUPDEP_DISPC_SDMA_SHIFT					3
-#define OMAP54XX_WKUPDEP_DISPC_SDMA_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_DISPC_SDMA_MASK					(1 << 3)
-
-/* Used by PM_ABE_DMIC_WKDEP */
-#define OMAP54XX_WKUPDEP_DMIC_DMA_DSP_SHIFT					6
-#define OMAP54XX_WKUPDEP_DMIC_DMA_DSP_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_DMIC_DMA_DSP_MASK					(1 << 6)
-
-/* Used by PM_ABE_DMIC_WKDEP */
-#define OMAP54XX_WKUPDEP_DMIC_DMA_SDMA_SHIFT					7
-#define OMAP54XX_WKUPDEP_DMIC_DMA_SDMA_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_DMIC_DMA_SDMA_MASK					(1 << 7)
-
-/* Used by PM_ABE_DMIC_WKDEP */
-#define OMAP54XX_WKUPDEP_DMIC_IRQ_DSP_SHIFT					2
-#define OMAP54XX_WKUPDEP_DMIC_IRQ_DSP_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_DMIC_IRQ_DSP_MASK					(1 << 2)
-
-/* Used by PM_ABE_DMIC_WKDEP */
-#define OMAP54XX_WKUPDEP_DMIC_IRQ_MPU_SHIFT					0
-#define OMAP54XX_WKUPDEP_DMIC_IRQ_MPU_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_DMIC_IRQ_MPU_MASK					(1 << 0)
-
-/* Used by PM_DSS_DSS_WKDEP */
-#define OMAP54XX_WKUPDEP_DSI1_A_DSP_SHIFT					6
-#define OMAP54XX_WKUPDEP_DSI1_A_DSP_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_DSI1_A_DSP_MASK					(1 << 6)
-
-/* Used by PM_DSS_DSS_WKDEP */
-#define OMAP54XX_WKUPDEP_DSI1_A_IPU_SHIFT					5
-#define OMAP54XX_WKUPDEP_DSI1_A_IPU_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_DSI1_A_IPU_MASK					(1 << 5)
-
-/* Used by PM_DSS_DSS_WKDEP */
-#define OMAP54XX_WKUPDEP_DSI1_A_MPU_SHIFT					4
-#define OMAP54XX_WKUPDEP_DSI1_A_MPU_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_DSI1_A_MPU_MASK					(1 << 4)
-
-/* Used by PM_DSS_DSS_WKDEP */
-#define OMAP54XX_WKUPDEP_DSI1_A_SDMA_SHIFT					7
-#define OMAP54XX_WKUPDEP_DSI1_A_SDMA_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_DSI1_A_SDMA_MASK					(1 << 7)
-
-/* Used by PM_DSS_DSS_WKDEP */
-#define OMAP54XX_WKUPDEP_DSI1_B_DSP_SHIFT					10
-#define OMAP54XX_WKUPDEP_DSI1_B_DSP_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_DSI1_B_DSP_MASK					(1 << 10)
-
-/* Used by PM_DSS_DSS_WKDEP */
-#define OMAP54XX_WKUPDEP_DSI1_B_IPU_SHIFT					9
-#define OMAP54XX_WKUPDEP_DSI1_B_IPU_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_DSI1_B_IPU_MASK					(1 << 9)
-
-/* Used by PM_DSS_DSS_WKDEP */
-#define OMAP54XX_WKUPDEP_DSI1_B_MPU_SHIFT					8
-#define OMAP54XX_WKUPDEP_DSI1_B_MPU_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_DSI1_B_MPU_MASK					(1 << 8)
-
-/* Used by PM_DSS_DSS_WKDEP */
-#define OMAP54XX_WKUPDEP_DSI1_B_SDMA_SHIFT					11
-#define OMAP54XX_WKUPDEP_DSI1_B_SDMA_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_DSI1_B_SDMA_MASK					(1 << 11)
-
-/* Used by PM_DSS_DSS_WKDEP */
-#define OMAP54XX_WKUPDEP_DSI1_C_DSP_SHIFT					17
-#define OMAP54XX_WKUPDEP_DSI1_C_DSP_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_DSI1_C_DSP_MASK					(1 << 17)
-
-/* Used by PM_DSS_DSS_WKDEP */
-#define OMAP54XX_WKUPDEP_DSI1_C_IPU_SHIFT					16
-#define OMAP54XX_WKUPDEP_DSI1_C_IPU_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_DSI1_C_IPU_MASK					(1 << 16)
-
-/* Used by PM_DSS_DSS_WKDEP */
-#define OMAP54XX_WKUPDEP_DSI1_C_MPU_SHIFT					15
-#define OMAP54XX_WKUPDEP_DSI1_C_MPU_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_DSI1_C_MPU_MASK					(1 << 15)
-
-/* Used by PM_DSS_DSS_WKDEP */
-#define OMAP54XX_WKUPDEP_DSI1_C_SDMA_SHIFT					18
-#define OMAP54XX_WKUPDEP_DSI1_C_SDMA_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_DSI1_C_SDMA_MASK					(1 << 18)
-
-/* Used by PM_WKUPAON_GPIO1_WKDEP */
-#define OMAP54XX_WKUPDEP_GPIO1_IRQ1_IPU_SHIFT					1
-#define OMAP54XX_WKUPDEP_GPIO1_IRQ1_IPU_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_GPIO1_IRQ1_IPU_MASK					(1 << 1)
-
-/* Used by PM_WKUPAON_GPIO1_WKDEP */
-#define OMAP54XX_WKUPDEP_GPIO1_IRQ1_MPU_SHIFT					0
-#define OMAP54XX_WKUPDEP_GPIO1_IRQ1_MPU_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_GPIO1_IRQ1_MPU_MASK					(1 << 0)
-
-/* Used by PM_WKUPAON_GPIO1_WKDEP */
-#define OMAP54XX_WKUPDEP_GPIO1_IRQ2_DSP_SHIFT					6
-#define OMAP54XX_WKUPDEP_GPIO1_IRQ2_DSP_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_GPIO1_IRQ2_DSP_MASK					(1 << 6)
-
-/* Used by PM_L4PER_GPIO2_WKDEP */
-#define OMAP54XX_WKUPDEP_GPIO2_IRQ1_IPU_SHIFT					1
-#define OMAP54XX_WKUPDEP_GPIO2_IRQ1_IPU_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_GPIO2_IRQ1_IPU_MASK					(1 << 1)
-
-/* Used by PM_L4PER_GPIO2_WKDEP */
-#define OMAP54XX_WKUPDEP_GPIO2_IRQ1_MPU_SHIFT					0
-#define OMAP54XX_WKUPDEP_GPIO2_IRQ1_MPU_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_GPIO2_IRQ1_MPU_MASK					(1 << 0)
-
-/* Used by PM_L4PER_GPIO2_WKDEP */
-#define OMAP54XX_WKUPDEP_GPIO2_IRQ2_DSP_SHIFT					6
-#define OMAP54XX_WKUPDEP_GPIO2_IRQ2_DSP_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_GPIO2_IRQ2_DSP_MASK					(1 << 6)
-
-/* Used by PM_L4PER_GPIO3_WKDEP */
-#define OMAP54XX_WKUPDEP_GPIO3_IRQ1_MPU_SHIFT					0
-#define OMAP54XX_WKUPDEP_GPIO3_IRQ1_MPU_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_GPIO3_IRQ1_MPU_MASK					(1 << 0)
-
-/* Used by PM_L4PER_GPIO3_WKDEP */
-#define OMAP54XX_WKUPDEP_GPIO3_IRQ2_DSP_SHIFT					6
-#define OMAP54XX_WKUPDEP_GPIO3_IRQ2_DSP_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_GPIO3_IRQ2_DSP_MASK					(1 << 6)
-
-/* Used by PM_L4PER_GPIO4_WKDEP */
-#define OMAP54XX_WKUPDEP_GPIO4_IRQ1_MPU_SHIFT					0
-#define OMAP54XX_WKUPDEP_GPIO4_IRQ1_MPU_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_GPIO4_IRQ1_MPU_MASK					(1 << 0)
-
-/* Used by PM_L4PER_GPIO4_WKDEP */
-#define OMAP54XX_WKUPDEP_GPIO4_IRQ2_DSP_SHIFT					6
-#define OMAP54XX_WKUPDEP_GPIO4_IRQ2_DSP_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_GPIO4_IRQ2_DSP_MASK					(1 << 6)
-
-/* Used by PM_L4PER_GPIO5_WKDEP */
-#define OMAP54XX_WKUPDEP_GPIO5_IRQ1_MPU_SHIFT					0
-#define OMAP54XX_WKUPDEP_GPIO5_IRQ1_MPU_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_GPIO5_IRQ1_MPU_MASK					(1 << 0)
-
-/* Used by PM_L4PER_GPIO5_WKDEP */
-#define OMAP54XX_WKUPDEP_GPIO5_IRQ2_DSP_SHIFT					6
-#define OMAP54XX_WKUPDEP_GPIO5_IRQ2_DSP_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_GPIO5_IRQ2_DSP_MASK					(1 << 6)
-
-/* Used by PM_L4PER_GPIO6_WKDEP */
-#define OMAP54XX_WKUPDEP_GPIO6_IRQ1_MPU_SHIFT					0
-#define OMAP54XX_WKUPDEP_GPIO6_IRQ1_MPU_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_GPIO6_IRQ1_MPU_MASK					(1 << 0)
-
-/* Used by PM_L4PER_GPIO6_WKDEP */
-#define OMAP54XX_WKUPDEP_GPIO6_IRQ2_DSP_SHIFT					6
-#define OMAP54XX_WKUPDEP_GPIO6_IRQ2_DSP_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_GPIO6_IRQ2_DSP_MASK					(1 << 6)
-
-/* Used by PM_L4PER_GPIO7_WKDEP */
-#define OMAP54XX_WKUPDEP_GPIO7_IRQ1_MPU_SHIFT					0
-#define OMAP54XX_WKUPDEP_GPIO7_IRQ1_MPU_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_GPIO7_IRQ1_MPU_MASK					(1 << 0)
-
-/* Used by PM_L4PER_GPIO8_WKDEP */
-#define OMAP54XX_WKUPDEP_GPIO8_IRQ1_MPU_SHIFT					0
-#define OMAP54XX_WKUPDEP_GPIO8_IRQ1_MPU_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_GPIO8_IRQ1_MPU_MASK					(1 << 0)
-
-/* Used by PM_DSS_DSS_WKDEP */
-#define OMAP54XX_WKUPDEP_HDMIDMA_SDMA_SHIFT					19
-#define OMAP54XX_WKUPDEP_HDMIDMA_SDMA_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_HDMIDMA_SDMA_MASK					(1 << 19)
-
-/* Used by PM_DSS_DSS_WKDEP */
-#define OMAP54XX_WKUPDEP_HDMIIRQ_DSP_SHIFT					14
-#define OMAP54XX_WKUPDEP_HDMIIRQ_DSP_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_HDMIIRQ_DSP_MASK					(1 << 14)
-
-/* Used by PM_DSS_DSS_WKDEP */
-#define OMAP54XX_WKUPDEP_HDMIIRQ_IPU_SHIFT					13
-#define OMAP54XX_WKUPDEP_HDMIIRQ_IPU_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_HDMIIRQ_IPU_MASK					(1 << 13)
-
-/* Used by PM_DSS_DSS_WKDEP */
-#define OMAP54XX_WKUPDEP_HDMIIRQ_MPU_SHIFT					12
-#define OMAP54XX_WKUPDEP_HDMIIRQ_MPU_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_HDMIIRQ_MPU_MASK					(1 << 12)
-
-/* Used by PM_L3INIT_HSI_WKDEP */
-#define OMAP54XX_WKUPDEP_HSI_DSP_DSP_SHIFT					6
-#define OMAP54XX_WKUPDEP_HSI_DSP_DSP_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_HSI_DSP_DSP_MASK					(1 << 6)
-
-/* Used by PM_L3INIT_HSI_WKDEP */
-#define OMAP54XX_WKUPDEP_HSI_MCU_IPU_SHIFT					1
-#define OMAP54XX_WKUPDEP_HSI_MCU_IPU_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_HSI_MCU_IPU_MASK					(1 << 1)
-
-/* Used by PM_L3INIT_HSI_WKDEP */
-#define OMAP54XX_WKUPDEP_HSI_MCU_MPU_SHIFT					0
-#define OMAP54XX_WKUPDEP_HSI_MCU_MPU_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_HSI_MCU_MPU_MASK					(1 << 0)
-
-/* Used by PM_L4PER_I2C1_WKDEP */
-#define OMAP54XX_WKUPDEP_I2C1_DMA_SDMA_SHIFT					7
-#define OMAP54XX_WKUPDEP_I2C1_DMA_SDMA_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_I2C1_DMA_SDMA_MASK					(1 << 7)
-
-/* Used by PM_L4PER_I2C1_WKDEP */
-#define OMAP54XX_WKUPDEP_I2C1_IRQ_IPU_SHIFT					1
-#define OMAP54XX_WKUPDEP_I2C1_IRQ_IPU_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_I2C1_IRQ_IPU_MASK					(1 << 1)
-
-/* Used by PM_L4PER_I2C1_WKDEP */
-#define OMAP54XX_WKUPDEP_I2C1_IRQ_MPU_SHIFT					0
-#define OMAP54XX_WKUPDEP_I2C1_IRQ_MPU_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_I2C1_IRQ_MPU_MASK					(1 << 0)
-
-/* Used by PM_L4PER_I2C2_WKDEP */
-#define OMAP54XX_WKUPDEP_I2C2_DMA_SDMA_SHIFT					7
-#define OMAP54XX_WKUPDEP_I2C2_DMA_SDMA_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_I2C2_DMA_SDMA_MASK					(1 << 7)
-
-/* Used by PM_L4PER_I2C2_WKDEP */
-#define OMAP54XX_WKUPDEP_I2C2_IRQ_IPU_SHIFT					1
-#define OMAP54XX_WKUPDEP_I2C2_IRQ_IPU_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_I2C2_IRQ_IPU_MASK					(1 << 1)
-
-/* Used by PM_L4PER_I2C2_WKDEP */
-#define OMAP54XX_WKUPDEP_I2C2_IRQ_MPU_SHIFT					0
-#define OMAP54XX_WKUPDEP_I2C2_IRQ_MPU_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_I2C2_IRQ_MPU_MASK					(1 << 0)
-
-/* Used by PM_L4PER_I2C3_WKDEP */
-#define OMAP54XX_WKUPDEP_I2C3_DMA_SDMA_SHIFT					7
-#define OMAP54XX_WKUPDEP_I2C3_DMA_SDMA_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_I2C3_DMA_SDMA_MASK					(1 << 7)
-
-/* Used by PM_L4PER_I2C3_WKDEP */
-#define OMAP54XX_WKUPDEP_I2C3_IRQ_IPU_SHIFT					1
-#define OMAP54XX_WKUPDEP_I2C3_IRQ_IPU_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_I2C3_IRQ_IPU_MASK					(1 << 1)
-
-/* Used by PM_L4PER_I2C3_WKDEP */
-#define OMAP54XX_WKUPDEP_I2C3_IRQ_MPU_SHIFT					0
-#define OMAP54XX_WKUPDEP_I2C3_IRQ_MPU_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_I2C3_IRQ_MPU_MASK					(1 << 0)
-
-/* Used by PM_L4PER_I2C4_WKDEP */
-#define OMAP54XX_WKUPDEP_I2C4_DMA_SDMA_SHIFT					7
-#define OMAP54XX_WKUPDEP_I2C4_DMA_SDMA_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_I2C4_DMA_SDMA_MASK					(1 << 7)
-
-/* Used by PM_L4PER_I2C4_WKDEP */
-#define OMAP54XX_WKUPDEP_I2C4_IRQ_IPU_SHIFT					1
-#define OMAP54XX_WKUPDEP_I2C4_IRQ_IPU_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_I2C4_IRQ_IPU_MASK					(1 << 1)
-
-/* Used by PM_L4PER_I2C4_WKDEP */
-#define OMAP54XX_WKUPDEP_I2C4_IRQ_MPU_SHIFT					0
-#define OMAP54XX_WKUPDEP_I2C4_IRQ_MPU_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_I2C4_IRQ_MPU_MASK					(1 << 0)
-
-/* Used by PM_L4PER_I2C5_WKDEP */
-#define OMAP54XX_WKUPDEP_I2C5_IRQ_MPU_SHIFT					0
-#define OMAP54XX_WKUPDEP_I2C5_IRQ_MPU_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_I2C5_IRQ_MPU_MASK					(1 << 0)
-
-/* Used by PM_WKUPAON_KBD_WKDEP */
-#define OMAP54XX_WKUPDEP_KBD_MPU_SHIFT						0
-#define OMAP54XX_WKUPDEP_KBD_MPU_WIDTH						0x1
-#define OMAP54XX_WKUPDEP_KBD_MPU_MASK						(1 << 0)
-
-/* Used by PM_ABE_MCASP_WKDEP */
-#define OMAP54XX_WKUPDEP_MCASP_DMA_DSP_SHIFT					6
-#define OMAP54XX_WKUPDEP_MCASP_DMA_DSP_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_MCASP_DMA_DSP_MASK					(1 << 6)
-
-/* Used by PM_ABE_MCASP_WKDEP */
-#define OMAP54XX_WKUPDEP_MCASP_DMA_SDMA_SHIFT					7
-#define OMAP54XX_WKUPDEP_MCASP_DMA_SDMA_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_MCASP_DMA_SDMA_MASK					(1 << 7)
-
-/* Used by PM_ABE_MCASP_WKDEP */
-#define OMAP54XX_WKUPDEP_MCASP_IRQ_DSP_SHIFT					2
-#define OMAP54XX_WKUPDEP_MCASP_IRQ_DSP_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_MCASP_IRQ_DSP_MASK					(1 << 2)
-
-/* Used by PM_ABE_MCASP_WKDEP */
-#define OMAP54XX_WKUPDEP_MCASP_IRQ_MPU_SHIFT					0
-#define OMAP54XX_WKUPDEP_MCASP_IRQ_MPU_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_MCASP_IRQ_MPU_MASK					(1 << 0)
-
-/* Used by PM_ABE_MCBSP1_WKDEP */
-#define OMAP54XX_WKUPDEP_MCBSP1_DSP_SHIFT					2
-#define OMAP54XX_WKUPDEP_MCBSP1_DSP_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_MCBSP1_DSP_MASK					(1 << 2)
-
-/* Used by PM_ABE_MCBSP1_WKDEP */
-#define OMAP54XX_WKUPDEP_MCBSP1_MPU_SHIFT					0
-#define OMAP54XX_WKUPDEP_MCBSP1_MPU_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_MCBSP1_MPU_MASK					(1 << 0)
-
-/* Used by PM_ABE_MCBSP1_WKDEP */
-#define OMAP54XX_WKUPDEP_MCBSP1_SDMA_SHIFT					3
-#define OMAP54XX_WKUPDEP_MCBSP1_SDMA_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_MCBSP1_SDMA_MASK					(1 << 3)
-
-/* Used by PM_ABE_MCBSP2_WKDEP */
-#define OMAP54XX_WKUPDEP_MCBSP2_DSP_SHIFT					2
-#define OMAP54XX_WKUPDEP_MCBSP2_DSP_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_MCBSP2_DSP_MASK					(1 << 2)
-
-/* Used by PM_ABE_MCBSP2_WKDEP */
-#define OMAP54XX_WKUPDEP_MCBSP2_MPU_SHIFT					0
-#define OMAP54XX_WKUPDEP_MCBSP2_MPU_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_MCBSP2_MPU_MASK					(1 << 0)
-
-/* Used by PM_ABE_MCBSP2_WKDEP */
-#define OMAP54XX_WKUPDEP_MCBSP2_SDMA_SHIFT					3
-#define OMAP54XX_WKUPDEP_MCBSP2_SDMA_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_MCBSP2_SDMA_MASK					(1 << 3)
-
-/* Used by PM_ABE_MCBSP3_WKDEP */
-#define OMAP54XX_WKUPDEP_MCBSP3_DSP_SHIFT					2
-#define OMAP54XX_WKUPDEP_MCBSP3_DSP_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_MCBSP3_DSP_MASK					(1 << 2)
-
-/* Used by PM_ABE_MCBSP3_WKDEP */
-#define OMAP54XX_WKUPDEP_MCBSP3_MPU_SHIFT					0
-#define OMAP54XX_WKUPDEP_MCBSP3_MPU_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_MCBSP3_MPU_MASK					(1 << 0)
-
-/* Used by PM_ABE_MCBSP3_WKDEP */
-#define OMAP54XX_WKUPDEP_MCBSP3_SDMA_SHIFT					3
-#define OMAP54XX_WKUPDEP_MCBSP3_SDMA_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_MCBSP3_SDMA_MASK					(1 << 3)
-
-/* Used by PM_ABE_MCPDM_WKDEP */
-#define OMAP54XX_WKUPDEP_MCPDM_DMA_DSP_SHIFT					6
-#define OMAP54XX_WKUPDEP_MCPDM_DMA_DSP_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_MCPDM_DMA_DSP_MASK					(1 << 6)
-
-/* Used by PM_ABE_MCPDM_WKDEP */
-#define OMAP54XX_WKUPDEP_MCPDM_DMA_SDMA_SHIFT					7
-#define OMAP54XX_WKUPDEP_MCPDM_DMA_SDMA_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_MCPDM_DMA_SDMA_MASK					(1 << 7)
-
-/* Used by PM_ABE_MCPDM_WKDEP */
-#define OMAP54XX_WKUPDEP_MCPDM_IRQ_DSP_SHIFT					2
-#define OMAP54XX_WKUPDEP_MCPDM_IRQ_DSP_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_MCPDM_IRQ_DSP_MASK					(1 << 2)
-
-/* Used by PM_ABE_MCPDM_WKDEP */
-#define OMAP54XX_WKUPDEP_MCPDM_IRQ_MPU_SHIFT					0
-#define OMAP54XX_WKUPDEP_MCPDM_IRQ_MPU_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_MCPDM_IRQ_MPU_MASK					(1 << 0)
-
-/* Used by PM_L4PER_MCSPI1_WKDEP */
-#define OMAP54XX_WKUPDEP_MCSPI1_DSP_SHIFT					2
-#define OMAP54XX_WKUPDEP_MCSPI1_DSP_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_MCSPI1_DSP_MASK					(1 << 2)
-
-/* Used by PM_L4PER_MCSPI1_WKDEP */
-#define OMAP54XX_WKUPDEP_MCSPI1_IPU_SHIFT					1
-#define OMAP54XX_WKUPDEP_MCSPI1_IPU_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_MCSPI1_IPU_MASK					(1 << 1)
-
-/* Used by PM_L4PER_MCSPI1_WKDEP */
-#define OMAP54XX_WKUPDEP_MCSPI1_MPU_SHIFT					0
-#define OMAP54XX_WKUPDEP_MCSPI1_MPU_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_MCSPI1_MPU_MASK					(1 << 0)
-
-/* Used by PM_L4PER_MCSPI1_WKDEP */
-#define OMAP54XX_WKUPDEP_MCSPI1_SDMA_SHIFT					3
-#define OMAP54XX_WKUPDEP_MCSPI1_SDMA_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_MCSPI1_SDMA_MASK					(1 << 3)
-
-/* Used by PM_L4PER_MCSPI2_WKDEP */
-#define OMAP54XX_WKUPDEP_MCSPI2_IPU_SHIFT					1
-#define OMAP54XX_WKUPDEP_MCSPI2_IPU_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_MCSPI2_IPU_MASK					(1 << 1)
-
-/* Used by PM_L4PER_MCSPI2_WKDEP */
-#define OMAP54XX_WKUPDEP_MCSPI2_MPU_SHIFT					0
-#define OMAP54XX_WKUPDEP_MCSPI2_MPU_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_MCSPI2_MPU_MASK					(1 << 0)
-
-/* Used by PM_L4PER_MCSPI2_WKDEP */
-#define OMAP54XX_WKUPDEP_MCSPI2_SDMA_SHIFT					3
-#define OMAP54XX_WKUPDEP_MCSPI2_SDMA_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_MCSPI2_SDMA_MASK					(1 << 3)
-
-/* Used by PM_L4PER_MCSPI3_WKDEP */
-#define OMAP54XX_WKUPDEP_MCSPI3_MPU_SHIFT					0
-#define OMAP54XX_WKUPDEP_MCSPI3_MPU_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_MCSPI3_MPU_MASK					(1 << 0)
-
-/* Used by PM_L4PER_MCSPI3_WKDEP */
-#define OMAP54XX_WKUPDEP_MCSPI3_SDMA_SHIFT					3
-#define OMAP54XX_WKUPDEP_MCSPI3_SDMA_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_MCSPI3_SDMA_MASK					(1 << 3)
-
-/* Used by PM_L4PER_MCSPI4_WKDEP */
-#define OMAP54XX_WKUPDEP_MCSPI4_MPU_SHIFT					0
-#define OMAP54XX_WKUPDEP_MCSPI4_MPU_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_MCSPI4_MPU_MASK					(1 << 0)
-
-/* Used by PM_L4PER_MCSPI4_WKDEP */
-#define OMAP54XX_WKUPDEP_MCSPI4_SDMA_SHIFT					3
-#define OMAP54XX_WKUPDEP_MCSPI4_SDMA_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_MCSPI4_SDMA_MASK					(1 << 3)
-
-/* Used by PM_L3INIT_MMC1_WKDEP */
-#define OMAP54XX_WKUPDEP_MMC1_DSP_SHIFT						2
-#define OMAP54XX_WKUPDEP_MMC1_DSP_WIDTH						0x1
-#define OMAP54XX_WKUPDEP_MMC1_DSP_MASK						(1 << 2)
-
-/* Used by PM_L3INIT_MMC1_WKDEP */
-#define OMAP54XX_WKUPDEP_MMC1_IPU_SHIFT						1
-#define OMAP54XX_WKUPDEP_MMC1_IPU_WIDTH						0x1
-#define OMAP54XX_WKUPDEP_MMC1_IPU_MASK						(1 << 1)
-
-/* Used by PM_L3INIT_MMC1_WKDEP */
-#define OMAP54XX_WKUPDEP_MMC1_MPU_SHIFT						0
-#define OMAP54XX_WKUPDEP_MMC1_MPU_WIDTH						0x1
-#define OMAP54XX_WKUPDEP_MMC1_MPU_MASK						(1 << 0)
-
-/* Used by PM_L3INIT_MMC1_WKDEP */
-#define OMAP54XX_WKUPDEP_MMC1_SDMA_SHIFT					3
-#define OMAP54XX_WKUPDEP_MMC1_SDMA_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_MMC1_SDMA_MASK						(1 << 3)
-
-/* Used by PM_L3INIT_MMC2_WKDEP */
-#define OMAP54XX_WKUPDEP_MMC2_DSP_SHIFT						2
-#define OMAP54XX_WKUPDEP_MMC2_DSP_WIDTH						0x1
-#define OMAP54XX_WKUPDEP_MMC2_DSP_MASK						(1 << 2)
-
-/* Used by PM_L3INIT_MMC2_WKDEP */
-#define OMAP54XX_WKUPDEP_MMC2_IPU_SHIFT						1
-#define OMAP54XX_WKUPDEP_MMC2_IPU_WIDTH						0x1
-#define OMAP54XX_WKUPDEP_MMC2_IPU_MASK						(1 << 1)
-
-/* Used by PM_L3INIT_MMC2_WKDEP */
-#define OMAP54XX_WKUPDEP_MMC2_MPU_SHIFT						0
-#define OMAP54XX_WKUPDEP_MMC2_MPU_WIDTH						0x1
-#define OMAP54XX_WKUPDEP_MMC2_MPU_MASK						(1 << 0)
-
-/* Used by PM_L3INIT_MMC2_WKDEP */
-#define OMAP54XX_WKUPDEP_MMC2_SDMA_SHIFT					3
-#define OMAP54XX_WKUPDEP_MMC2_SDMA_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_MMC2_SDMA_MASK						(1 << 3)
-
-/* Used by PM_L4PER_MMC3_WKDEP */
-#define OMAP54XX_WKUPDEP_MMC3_IPU_SHIFT						1
-#define OMAP54XX_WKUPDEP_MMC3_IPU_WIDTH						0x1
-#define OMAP54XX_WKUPDEP_MMC3_IPU_MASK						(1 << 1)
-
-/* Used by PM_L4PER_MMC3_WKDEP */
-#define OMAP54XX_WKUPDEP_MMC3_MPU_SHIFT						0
-#define OMAP54XX_WKUPDEP_MMC3_MPU_WIDTH						0x1
-#define OMAP54XX_WKUPDEP_MMC3_MPU_MASK						(1 << 0)
-
-/* Used by PM_L4PER_MMC3_WKDEP */
-#define OMAP54XX_WKUPDEP_MMC3_SDMA_SHIFT					3
-#define OMAP54XX_WKUPDEP_MMC3_SDMA_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_MMC3_SDMA_MASK						(1 << 3)
-
-/* Used by PM_L4PER_MMC4_WKDEP */
-#define OMAP54XX_WKUPDEP_MMC4_MPU_SHIFT						0
-#define OMAP54XX_WKUPDEP_MMC4_MPU_WIDTH						0x1
-#define OMAP54XX_WKUPDEP_MMC4_MPU_MASK						(1 << 0)
-
-/* Used by PM_L4PER_MMC4_WKDEP */
-#define OMAP54XX_WKUPDEP_MMC4_SDMA_SHIFT					3
-#define OMAP54XX_WKUPDEP_MMC4_SDMA_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_MMC4_SDMA_MASK						(1 << 3)
-
-/* Used by PM_L4PER_MMC5_WKDEP */
-#define OMAP54XX_WKUPDEP_MMC5_MPU_SHIFT						0
-#define OMAP54XX_WKUPDEP_MMC5_MPU_WIDTH						0x1
-#define OMAP54XX_WKUPDEP_MMC5_MPU_MASK						(1 << 0)
-
-/* Used by PM_L4PER_MMC5_WKDEP */
-#define OMAP54XX_WKUPDEP_MMC5_SDMA_SHIFT					3
-#define OMAP54XX_WKUPDEP_MMC5_SDMA_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_MMC5_SDMA_MASK						(1 << 3)
-
-/* Used by PM_L3INIT_SATA_WKDEP */
-#define OMAP54XX_WKUPDEP_SATA_MPU_SHIFT						0
-#define OMAP54XX_WKUPDEP_SATA_MPU_WIDTH						0x1
-#define OMAP54XX_WKUPDEP_SATA_MPU_MASK						(1 << 0)
-
-/* Used by PM_ABE_SLIMBUS1_WKDEP */
-#define OMAP54XX_WKUPDEP_SLIMBUS1_DMA_DSP_SHIFT					6
-#define OMAP54XX_WKUPDEP_SLIMBUS1_DMA_DSP_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_SLIMBUS1_DMA_DSP_MASK					(1 << 6)
-
-/* Used by PM_ABE_SLIMBUS1_WKDEP */
-#define OMAP54XX_WKUPDEP_SLIMBUS1_DMA_SDMA_SHIFT				7
-#define OMAP54XX_WKUPDEP_SLIMBUS1_DMA_SDMA_WIDTH				0x1
-#define OMAP54XX_WKUPDEP_SLIMBUS1_DMA_SDMA_MASK					(1 << 7)
-
-/* Used by PM_ABE_SLIMBUS1_WKDEP */
-#define OMAP54XX_WKUPDEP_SLIMBUS1_IRQ_DSP_SHIFT					2
-#define OMAP54XX_WKUPDEP_SLIMBUS1_IRQ_DSP_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_SLIMBUS1_IRQ_DSP_MASK					(1 << 2)
-
-/* Used by PM_ABE_SLIMBUS1_WKDEP */
-#define OMAP54XX_WKUPDEP_SLIMBUS1_IRQ_MPU_SHIFT					0
-#define OMAP54XX_WKUPDEP_SLIMBUS1_IRQ_MPU_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_SLIMBUS1_IRQ_MPU_MASK					(1 << 0)
-
-/* Used by PM_COREAON_SMARTREFLEX_CORE_WKDEP */
-#define OMAP54XX_WKUPDEP_SMARTREFLEX_CORE_IPU_SHIFT				1
-#define OMAP54XX_WKUPDEP_SMARTREFLEX_CORE_IPU_WIDTH				0x1
-#define OMAP54XX_WKUPDEP_SMARTREFLEX_CORE_IPU_MASK				(1 << 1)
-
-/* Used by PM_COREAON_SMARTREFLEX_CORE_WKDEP */
-#define OMAP54XX_WKUPDEP_SMARTREFLEX_CORE_MPU_SHIFT				0
-#define OMAP54XX_WKUPDEP_SMARTREFLEX_CORE_MPU_WIDTH				0x1
-#define OMAP54XX_WKUPDEP_SMARTREFLEX_CORE_MPU_MASK				(1 << 0)
-
-/* Used by PM_COREAON_SMARTREFLEX_MM_WKDEP */
-#define OMAP54XX_WKUPDEP_SMARTREFLEX_MM_MPU_SHIFT				0
-#define OMAP54XX_WKUPDEP_SMARTREFLEX_MM_MPU_WIDTH				0x1
-#define OMAP54XX_WKUPDEP_SMARTREFLEX_MM_MPU_MASK				(1 << 0)
-
-/* Used by PM_COREAON_SMARTREFLEX_MPU_WKDEP */
-#define OMAP54XX_WKUPDEP_SMARTREFLEX_MPU_MPU_SHIFT				0
-#define OMAP54XX_WKUPDEP_SMARTREFLEX_MPU_MPU_WIDTH				0x1
-#define OMAP54XX_WKUPDEP_SMARTREFLEX_MPU_MPU_MASK				(1 << 0)
-
-/* Used by PM_L4PER_TIMER10_WKDEP */
-#define OMAP54XX_WKUPDEP_TIMER10_MPU_SHIFT					0
-#define OMAP54XX_WKUPDEP_TIMER10_MPU_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_TIMER10_MPU_MASK					(1 << 0)
-
-/* Used by PM_L4PER_TIMER11_WKDEP */
-#define OMAP54XX_WKUPDEP_TIMER11_IPU_SHIFT					1
-#define OMAP54XX_WKUPDEP_TIMER11_IPU_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_TIMER11_IPU_MASK					(1 << 1)
-
-/* Used by PM_L4PER_TIMER11_WKDEP */
-#define OMAP54XX_WKUPDEP_TIMER11_MPU_SHIFT					0
-#define OMAP54XX_WKUPDEP_TIMER11_MPU_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_TIMER11_MPU_MASK					(1 << 0)
-
-/* Used by PM_WKUPAON_TIMER12_WKDEP */
-#define OMAP54XX_WKUPDEP_TIMER12_MPU_SHIFT					0
-#define OMAP54XX_WKUPDEP_TIMER12_MPU_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_TIMER12_MPU_MASK					(1 << 0)
-
-/* Used by PM_WKUPAON_TIMER1_WKDEP */
-#define OMAP54XX_WKUPDEP_TIMER1_MPU_SHIFT					0
-#define OMAP54XX_WKUPDEP_TIMER1_MPU_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_TIMER1_MPU_MASK					(1 << 0)
-
-/* Used by PM_L4PER_TIMER2_WKDEP */
-#define OMAP54XX_WKUPDEP_TIMER2_MPU_SHIFT					0
-#define OMAP54XX_WKUPDEP_TIMER2_MPU_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_TIMER2_MPU_MASK					(1 << 0)
-
-/* Used by PM_L4PER_TIMER3_WKDEP */
-#define OMAP54XX_WKUPDEP_TIMER3_IPU_SHIFT					1
-#define OMAP54XX_WKUPDEP_TIMER3_IPU_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_TIMER3_IPU_MASK					(1 << 1)
-
-/* Used by PM_L4PER_TIMER3_WKDEP */
-#define OMAP54XX_WKUPDEP_TIMER3_MPU_SHIFT					0
-#define OMAP54XX_WKUPDEP_TIMER3_MPU_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_TIMER3_MPU_MASK					(1 << 0)
-
-/* Used by PM_L4PER_TIMER4_WKDEP */
-#define OMAP54XX_WKUPDEP_TIMER4_IPU_SHIFT					1
-#define OMAP54XX_WKUPDEP_TIMER4_IPU_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_TIMER4_IPU_MASK					(1 << 1)
-
-/* Used by PM_L4PER_TIMER4_WKDEP */
-#define OMAP54XX_WKUPDEP_TIMER4_MPU_SHIFT					0
-#define OMAP54XX_WKUPDEP_TIMER4_MPU_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_TIMER4_MPU_MASK					(1 << 0)
-
-/* Used by PM_ABE_TIMER5_WKDEP */
-#define OMAP54XX_WKUPDEP_TIMER5_DSP_SHIFT					2
-#define OMAP54XX_WKUPDEP_TIMER5_DSP_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_TIMER5_DSP_MASK					(1 << 2)
-
-/* Used by PM_ABE_TIMER5_WKDEP */
-#define OMAP54XX_WKUPDEP_TIMER5_MPU_SHIFT					0
-#define OMAP54XX_WKUPDEP_TIMER5_MPU_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_TIMER5_MPU_MASK					(1 << 0)
-
-/* Used by PM_ABE_TIMER6_WKDEP */
-#define OMAP54XX_WKUPDEP_TIMER6_DSP_SHIFT					2
-#define OMAP54XX_WKUPDEP_TIMER6_DSP_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_TIMER6_DSP_MASK					(1 << 2)
-
-/* Used by PM_ABE_TIMER6_WKDEP */
-#define OMAP54XX_WKUPDEP_TIMER6_MPU_SHIFT					0
-#define OMAP54XX_WKUPDEP_TIMER6_MPU_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_TIMER6_MPU_MASK					(1 << 0)
-
-/* Used by PM_ABE_TIMER7_WKDEP */
-#define OMAP54XX_WKUPDEP_TIMER7_DSP_SHIFT					2
-#define OMAP54XX_WKUPDEP_TIMER7_DSP_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_TIMER7_DSP_MASK					(1 << 2)
-
-/* Used by PM_ABE_TIMER7_WKDEP */
-#define OMAP54XX_WKUPDEP_TIMER7_MPU_SHIFT					0
-#define OMAP54XX_WKUPDEP_TIMER7_MPU_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_TIMER7_MPU_MASK					(1 << 0)
-
-/* Used by PM_ABE_TIMER8_WKDEP */
-#define OMAP54XX_WKUPDEP_TIMER8_DSP_SHIFT					2
-#define OMAP54XX_WKUPDEP_TIMER8_DSP_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_TIMER8_DSP_MASK					(1 << 2)
-
-/* Used by PM_ABE_TIMER8_WKDEP */
-#define OMAP54XX_WKUPDEP_TIMER8_MPU_SHIFT					0
-#define OMAP54XX_WKUPDEP_TIMER8_MPU_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_TIMER8_MPU_MASK					(1 << 0)
-
-/* Used by PM_L4PER_TIMER9_WKDEP */
-#define OMAP54XX_WKUPDEP_TIMER9_IPU_SHIFT					1
-#define OMAP54XX_WKUPDEP_TIMER9_IPU_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_TIMER9_IPU_MASK					(1 << 1)
-
-/* Used by PM_L4PER_TIMER9_WKDEP */
-#define OMAP54XX_WKUPDEP_TIMER9_MPU_SHIFT					0
-#define OMAP54XX_WKUPDEP_TIMER9_MPU_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_TIMER9_MPU_MASK					(1 << 0)
-
-/* Used by PM_L4PER_UART1_WKDEP */
-#define OMAP54XX_WKUPDEP_UART1_MPU_SHIFT					0
-#define OMAP54XX_WKUPDEP_UART1_MPU_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_UART1_MPU_MASK						(1 << 0)
-
-/* Used by PM_L4PER_UART1_WKDEP */
-#define OMAP54XX_WKUPDEP_UART1_SDMA_SHIFT					3
-#define OMAP54XX_WKUPDEP_UART1_SDMA_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_UART1_SDMA_MASK					(1 << 3)
-
-/* Used by PM_L4PER_UART2_WKDEP */
-#define OMAP54XX_WKUPDEP_UART2_MPU_SHIFT					0
-#define OMAP54XX_WKUPDEP_UART2_MPU_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_UART2_MPU_MASK						(1 << 0)
-
-/* Used by PM_L4PER_UART2_WKDEP */
-#define OMAP54XX_WKUPDEP_UART2_SDMA_SHIFT					3
-#define OMAP54XX_WKUPDEP_UART2_SDMA_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_UART2_SDMA_MASK					(1 << 3)
-
-/* Used by PM_L4PER_UART3_WKDEP */
-#define OMAP54XX_WKUPDEP_UART3_DSP_SHIFT					2
-#define OMAP54XX_WKUPDEP_UART3_DSP_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_UART3_DSP_MASK						(1 << 2)
-
-/* Used by PM_L4PER_UART3_WKDEP */
-#define OMAP54XX_WKUPDEP_UART3_IPU_SHIFT					1
-#define OMAP54XX_WKUPDEP_UART3_IPU_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_UART3_IPU_MASK						(1 << 1)
-
-/* Used by PM_L4PER_UART3_WKDEP */
-#define OMAP54XX_WKUPDEP_UART3_MPU_SHIFT					0
-#define OMAP54XX_WKUPDEP_UART3_MPU_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_UART3_MPU_MASK						(1 << 0)
-
-/* Used by PM_L4PER_UART3_WKDEP */
-#define OMAP54XX_WKUPDEP_UART3_SDMA_SHIFT					3
-#define OMAP54XX_WKUPDEP_UART3_SDMA_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_UART3_SDMA_MASK					(1 << 3)
-
-/* Used by PM_L4PER_UART4_WKDEP */
-#define OMAP54XX_WKUPDEP_UART4_MPU_SHIFT					0
-#define OMAP54XX_WKUPDEP_UART4_MPU_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_UART4_MPU_MASK						(1 << 0)
-
-/* Used by PM_L4PER_UART4_WKDEP */
-#define OMAP54XX_WKUPDEP_UART4_SDMA_SHIFT					3
-#define OMAP54XX_WKUPDEP_UART4_SDMA_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_UART4_SDMA_MASK					(1 << 3)
-
-/* Used by PM_L4PER_UART5_WKDEP */
-#define OMAP54XX_WKUPDEP_UART5_MPU_SHIFT					0
-#define OMAP54XX_WKUPDEP_UART5_MPU_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_UART5_MPU_MASK						(1 << 0)
-
-/* Used by PM_L4PER_UART5_WKDEP */
-#define OMAP54XX_WKUPDEP_UART5_SDMA_SHIFT					3
-#define OMAP54XX_WKUPDEP_UART5_SDMA_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_UART5_SDMA_MASK					(1 << 3)
-
-/* Used by PM_L4PER_UART6_WKDEP */
-#define OMAP54XX_WKUPDEP_UART6_MPU_SHIFT					0
-#define OMAP54XX_WKUPDEP_UART6_MPU_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_UART6_MPU_MASK						(1 << 0)
-
-/* Used by PM_L4PER_UART6_WKDEP */
-#define OMAP54XX_WKUPDEP_UART6_SDMA_SHIFT					3
-#define OMAP54XX_WKUPDEP_UART6_SDMA_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_UART6_SDMA_MASK					(1 << 3)
-
-/* Used by PM_L3INIT_UNIPRO2_WKDEP */
-#define OMAP54XX_WKUPDEP_UNIPRO2_MPU_SHIFT					0
-#define OMAP54XX_WKUPDEP_UNIPRO2_MPU_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_UNIPRO2_MPU_MASK					(1 << 0)
-
-/* Used by PM_L3INIT_USB_HOST_HS_WKDEP */
-#define OMAP54XX_WKUPDEP_USB_HOST_HS_IPU_SHIFT					1
-#define OMAP54XX_WKUPDEP_USB_HOST_HS_IPU_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_USB_HOST_HS_IPU_MASK					(1 << 1)
-
-/* Used by PM_L3INIT_USB_HOST_HS_WKDEP */
-#define OMAP54XX_WKUPDEP_USB_HOST_HS_MPU_SHIFT					0
-#define OMAP54XX_WKUPDEP_USB_HOST_HS_MPU_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_USB_HOST_HS_MPU_MASK					(1 << 0)
-
-/* Used by PM_L3INIT_USB_OTG_SS_WKDEP */
-#define OMAP54XX_WKUPDEP_USB_OTG_SS_IPU_SHIFT					1
-#define OMAP54XX_WKUPDEP_USB_OTG_SS_IPU_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_USB_OTG_SS_IPU_MASK					(1 << 1)
-
-/* Used by PM_L3INIT_USB_OTG_SS_WKDEP */
-#define OMAP54XX_WKUPDEP_USB_OTG_SS_MPU_SHIFT					0
-#define OMAP54XX_WKUPDEP_USB_OTG_SS_MPU_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_USB_OTG_SS_MPU_MASK					(1 << 0)
-
-/* Used by PM_L3INIT_USB_TLL_HS_WKDEP */
-#define OMAP54XX_WKUPDEP_USB_TLL_HS_IPU_SHIFT					1
-#define OMAP54XX_WKUPDEP_USB_TLL_HS_IPU_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_USB_TLL_HS_IPU_MASK					(1 << 1)
-
-/* Used by PM_L3INIT_USB_TLL_HS_WKDEP */
-#define OMAP54XX_WKUPDEP_USB_TLL_HS_MPU_SHIFT					0
-#define OMAP54XX_WKUPDEP_USB_TLL_HS_MPU_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_USB_TLL_HS_MPU_MASK					(1 << 0)
-
-/* Used by PM_WKUPAON_WD_TIMER2_WKDEP */
-#define OMAP54XX_WKUPDEP_WD_TIMER2_MPU_SHIFT					0
-#define OMAP54XX_WKUPDEP_WD_TIMER2_MPU_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_WD_TIMER2_MPU_MASK					(1 << 0)
-
-/* Used by PM_ABE_WD_TIMER3_WKDEP */
-#define OMAP54XX_WKUPDEP_WD_TIMER3_MPU_SHIFT					0
-#define OMAP54XX_WKUPDEP_WD_TIMER3_MPU_WIDTH					0x1
-#define OMAP54XX_WKUPDEP_WD_TIMER3_MPU_MASK					(1 << 0)
-
-/* Used by PRM_IO_PMCTRL */
-#define OMAP54XX_WUCLK_CTRL_SHIFT						8
-#define OMAP54XX_WUCLK_CTRL_WIDTH						0x1
-#define OMAP54XX_WUCLK_CTRL_MASK						(1 << 8)
-
-/* Used by PRM_IO_PMCTRL */
-#define OMAP54XX_WUCLK_STATUS_SHIFT						9
-#define OMAP54XX_WUCLK_STATUS_WIDTH						0x1
-#define OMAP54XX_WUCLK_STATUS_MASK						(1 << 9)
-
-/* Used by REVISION_PRM */
-#define OMAP54XX_X_MAJOR_SHIFT							8
-#define OMAP54XX_X_MAJOR_WIDTH							0x3
-#define OMAP54XX_X_MAJOR_MASK							(0x7 << 8)
-
-/* Used by REVISION_PRM */
-#define OMAP54XX_Y_MINOR_SHIFT							0
-#define OMAP54XX_Y_MINOR_WIDTH							0x6
-#define OMAP54XX_Y_MINOR_MASK							(0x3f << 0)
-#endif
diff --git a/arch/arm/mach-omap2/prm44xx.c b/arch/arm/mach-omap2/prm44xx.c
index 415c7e0c9393..03a603476cfc 100644
--- a/arch/arm/mach-omap2/prm44xx.c
+++ b/arch/arm/mach-omap2/prm44xx.c
@@ -620,6 +620,15 @@ static int omap4_pwrdm_wait_transition(struct powerdomain *pwrdm)
 	return 0;
 }
 
+static int omap4_check_vcvp(void)
+{
+	/* No VC/VP on dra7xx devices */
+	if (soc_is_dra7xx())
+		return 0;
+
+	return 1;
+}
+
 struct pwrdm_ops omap4_pwrdm_operations = {
 	.pwrdm_set_next_pwrst	= omap4_pwrdm_set_next_pwrst,
 	.pwrdm_read_next_pwrst	= omap4_pwrdm_read_next_pwrst,
@@ -637,6 +646,7 @@ struct pwrdm_ops omap4_pwrdm_operations = {
 	.pwrdm_set_mem_onst	= omap4_pwrdm_set_mem_onst,
 	.pwrdm_set_mem_retst	= omap4_pwrdm_set_mem_retst,
 	.pwrdm_wait_transition	= omap4_pwrdm_wait_transition,
+	.pwrdm_has_voltdm	= omap4_check_vcvp,
 };
 
 /*
@@ -650,7 +660,7 @@ static struct prm_ll_data omap44xx_prm_ll_data = {
 
 int __init omap44xx_prm_init(void)
 {
-	if (!cpu_is_omap44xx() && !soc_is_omap54xx())
+	if (!cpu_is_omap44xx() && !soc_is_omap54xx() && !soc_is_dra7xx())
 		return 0;
 
 	return prm_register(&omap44xx_prm_ll_data);
diff --git a/arch/arm/mach-omap2/prm7xx.h b/arch/arm/mach-omap2/prm7xx.h
new file mode 100644
index 000000000000..d92a8404edc7
--- /dev/null
+++ b/arch/arm/mach-omap2/prm7xx.h
@@ -0,0 +1,678 @@
+/*
+ * DRA7xx PRM instance offset macros
+ *
+ * Copyright (C) 2013 Texas Instruments Incorporated - http://www.ti.com
+ *
+ * Generated by code originally written by:
+ * Paul Walmsley (paul@pwsan.com)
+ * Rajendra Nayak (rnayak@ti.com)
+ * Benoit Cousson (b-cousson@ti.com)
+ *
+ * This file is automatically generated from the OMAP hardware databases.
+ * We respectfully ask that any modifications to this file be coordinated
+ * with the public linux-omap@vger.kernel.org mailing list and the
+ * authors above to ensure that the autogeneration scripts are kept
+ * up-to-date with the file contents.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __ARCH_ARM_MACH_OMAP2_PRM7XX_H
+#define __ARCH_ARM_MACH_OMAP2_PRM7XX_H
+
+#include "prm44xx_54xx.h"
+#include "prcm-common.h"
+#include "prm.h"
+
+#define DRA7XX_PRM_BASE		0x4ae06000
+
+#define DRA7XX_PRM_REGADDR(inst, reg)				\
+	OMAP2_L4_IO_ADDRESS(DRA7XX_PRM_BASE + (inst) + (reg))
+
+
+/* PRM instances */
+#define DRA7XX_PRM_OCP_SOCKET_INST	0x0000
+#define DRA7XX_PRM_CKGEN_INST		0x0100
+#define DRA7XX_PRM_MPU_INST		0x0300
+#define DRA7XX_PRM_DSP1_INST		0x0400
+#define DRA7XX_PRM_IPU_INST		0x0500
+#define DRA7XX_PRM_COREAON_INST		0x0628
+#define DRA7XX_PRM_CORE_INST		0x0700
+#define DRA7XX_PRM_IVA_INST		0x0f00
+#define DRA7XX_PRM_CAM_INST		0x1000
+#define DRA7XX_PRM_DSS_INST		0x1100
+#define DRA7XX_PRM_GPU_INST		0x1200
+#define DRA7XX_PRM_L3INIT_INST		0x1300
+#define DRA7XX_PRM_L4PER_INST		0x1400
+#define DRA7XX_PRM_CUSTEFUSE_INST	0x1600
+#define DRA7XX_PRM_WKUPAON_INST		0x1724
+#define DRA7XX_PRM_WKUPAON_CM_INST	0x1800
+#define DRA7XX_PRM_EMU_INST		0x1900
+#define DRA7XX_PRM_EMU_CM_INST		0x1a00
+#define DRA7XX_PRM_DSP2_INST		0x1b00
+#define DRA7XX_PRM_EVE1_INST		0x1b40
+#define DRA7XX_PRM_EVE2_INST		0x1b80
+#define DRA7XX_PRM_EVE3_INST		0x1bc0
+#define DRA7XX_PRM_EVE4_INST		0x1c00
+#define DRA7XX_PRM_RTC_INST		0x1c60
+#define DRA7XX_PRM_VPE_INST		0x1c80
+#define DRA7XX_PRM_DEVICE_INST		0x1d00
+#define DRA7XX_PRM_INSTR_INST		0x1f00
+
+/* PRM clockdomain register offsets (from instance start) */
+#define DRA7XX_PRM_WKUPAON_CM_WKUPAON_CDOFFS	0x0000
+#define DRA7XX_PRM_EMU_CM_EMU_CDOFFS		0x0000
+
+/* PRM */
+
+/* PRM.OCP_SOCKET_PRM register offsets */
+#define DRA7XX_REVISION_PRM_OFFSET				0x0000
+#define DRA7XX_PRM_IRQSTATUS_MPU_OFFSET				0x0010
+#define DRA7XX_PRM_IRQSTATUS_MPU_2_OFFSET			0x0014
+#define DRA7XX_PRM_IRQENABLE_MPU_OFFSET				0x0018
+#define DRA7XX_PRM_IRQENABLE_MPU_2_OFFSET			0x001c
+#define DRA7XX_PRM_IRQSTATUS_IPU2_OFFSET			0x0020
+#define DRA7XX_PRM_IRQENABLE_IPU2_OFFSET			0x0028
+#define DRA7XX_PRM_IRQSTATUS_DSP1_OFFSET			0x0030
+#define DRA7XX_PRM_IRQENABLE_DSP1_OFFSET			0x0038
+#define DRA7XX_CM_PRM_PROFILING_CLKCTRL_OFFSET			0x0040
+#define DRA7XX_CM_PRM_PROFILING_CLKCTRL				DRA7XX_PRM_REGADDR(DRA7XX_PRM_OCP_SOCKET_INST, 0x0040)
+#define DRA7XX_PRM_IRQENABLE_DSP2_OFFSET			0x0044
+#define DRA7XX_PRM_IRQENABLE_EVE1_OFFSET			0x0048
+#define DRA7XX_PRM_IRQENABLE_EVE2_OFFSET			0x004c
+#define DRA7XX_PRM_IRQENABLE_EVE3_OFFSET			0x0050
+#define DRA7XX_PRM_IRQENABLE_EVE4_OFFSET			0x0054
+#define DRA7XX_PRM_IRQENABLE_IPU1_OFFSET			0x0058
+#define DRA7XX_PRM_IRQSTATUS_DSP2_OFFSET			0x005c
+#define DRA7XX_PRM_IRQSTATUS_EVE1_OFFSET			0x0060
+#define DRA7XX_PRM_IRQSTATUS_EVE2_OFFSET			0x0064
+#define DRA7XX_PRM_IRQSTATUS_EVE3_OFFSET			0x0068
+#define DRA7XX_PRM_IRQSTATUS_EVE4_OFFSET			0x006c
+#define DRA7XX_PRM_IRQSTATUS_IPU1_OFFSET			0x0070
+#define DRA7XX_PRM_DEBUG_CFG1_OFFSET				0x00e4
+#define DRA7XX_PRM_DEBUG_CFG2_OFFSET				0x00e8
+#define DRA7XX_PRM_DEBUG_CFG3_OFFSET				0x00ec
+#define DRA7XX_PRM_DEBUG_OUT_OFFSET				0x00f4
+
+/* PRM.CKGEN_PRM register offsets */
+#define DRA7XX_CM_CLKSEL_SYSCLK1_OFFSET				0x0000
+#define DRA7XX_CM_CLKSEL_SYSCLK1				DRA7XX_PRM_REGADDR(DRA7XX_PRM_CKGEN_INST, 0x0000)
+#define DRA7XX_CM_CLKSEL_WKUPAON_OFFSET				0x0008
+#define DRA7XX_CM_CLKSEL_WKUPAON				DRA7XX_PRM_REGADDR(DRA7XX_PRM_CKGEN_INST, 0x0008)
+#define DRA7XX_CM_CLKSEL_ABE_PLL_REF_OFFSET			0x000c
+#define DRA7XX_CM_CLKSEL_ABE_PLL_REF				DRA7XX_PRM_REGADDR(DRA7XX_PRM_CKGEN_INST, 0x000c)
+#define DRA7XX_CM_CLKSEL_SYS_OFFSET				0x0010
+#define DRA7XX_CM_CLKSEL_SYS					DRA7XX_PRM_REGADDR(DRA7XX_PRM_CKGEN_INST, 0x0010)
+#define DRA7XX_CM_CLKSEL_ABE_PLL_BYPAS_OFFSET			0x0014
+#define DRA7XX_CM_CLKSEL_ABE_PLL_BYPAS				DRA7XX_PRM_REGADDR(DRA7XX_PRM_CKGEN_INST, 0x0014)
+#define DRA7XX_CM_CLKSEL_ABE_PLL_SYS_OFFSET			0x0018
+#define DRA7XX_CM_CLKSEL_ABE_PLL_SYS				DRA7XX_PRM_REGADDR(DRA7XX_PRM_CKGEN_INST, 0x0018)
+#define DRA7XX_CM_CLKSEL_ABE_24M_OFFSET				0x001c
+#define DRA7XX_CM_CLKSEL_ABE_24M				DRA7XX_PRM_REGADDR(DRA7XX_PRM_CKGEN_INST, 0x001c)
+#define DRA7XX_CM_CLKSEL_ABE_SYS_OFFSET				0x0020
+#define DRA7XX_CM_CLKSEL_ABE_SYS				DRA7XX_PRM_REGADDR(DRA7XX_PRM_CKGEN_INST, 0x0020)
+#define DRA7XX_CM_CLKSEL_HDMI_MCASP_AUX_OFFSET			0x0024
+#define DRA7XX_CM_CLKSEL_HDMI_MCASP_AUX				DRA7XX_PRM_REGADDR(DRA7XX_PRM_CKGEN_INST, 0x0024)
+#define DRA7XX_CM_CLKSEL_HDMI_TIMER_OFFSET			0x0028
+#define DRA7XX_CM_CLKSEL_HDMI_TIMER				DRA7XX_PRM_REGADDR(DRA7XX_PRM_CKGEN_INST, 0x0028)
+#define DRA7XX_CM_CLKSEL_MCASP_SYS_OFFSET			0x002c
+#define DRA7XX_CM_CLKSEL_MCASP_SYS				DRA7XX_PRM_REGADDR(DRA7XX_PRM_CKGEN_INST, 0x002c)
+#define DRA7XX_CM_CLKSEL_MLBP_MCASP_OFFSET			0x0030
+#define DRA7XX_CM_CLKSEL_MLBP_MCASP				DRA7XX_PRM_REGADDR(DRA7XX_PRM_CKGEN_INST, 0x0030)
+#define DRA7XX_CM_CLKSEL_MLB_MCASP_OFFSET			0x0034
+#define DRA7XX_CM_CLKSEL_MLB_MCASP				DRA7XX_PRM_REGADDR(DRA7XX_PRM_CKGEN_INST, 0x0034)
+#define DRA7XX_CM_CLKSEL_PER_ABE_X1_GFCLK_MCASP_AUX_OFFSET	0x0038
+#define DRA7XX_CM_CLKSEL_PER_ABE_X1_GFCLK_MCASP_AUX		DRA7XX_PRM_REGADDR(DRA7XX_PRM_CKGEN_INST, 0x0038)
+#define DRA7XX_CM_CLKSEL_SYS_CLK1_32K_OFFSET			0x0040
+#define DRA7XX_CM_CLKSEL_SYS_CLK1_32K				DRA7XX_PRM_REGADDR(DRA7XX_PRM_CKGEN_INST, 0x0040)
+#define DRA7XX_CM_CLKSEL_TIMER_SYS_OFFSET			0x0044
+#define DRA7XX_CM_CLKSEL_TIMER_SYS				DRA7XX_PRM_REGADDR(DRA7XX_PRM_CKGEN_INST, 0x0044)
+#define DRA7XX_CM_CLKSEL_VIDEO1_MCASP_AUX_OFFSET		0x0048
+#define DRA7XX_CM_CLKSEL_VIDEO1_MCASP_AUX			DRA7XX_PRM_REGADDR(DRA7XX_PRM_CKGEN_INST, 0x0048)
+#define DRA7XX_CM_CLKSEL_VIDEO1_TIMER_OFFSET			0x004c
+#define DRA7XX_CM_CLKSEL_VIDEO1_TIMER				DRA7XX_PRM_REGADDR(DRA7XX_PRM_CKGEN_INST, 0x004c)
+#define DRA7XX_CM_CLKSEL_VIDEO2_MCASP_AUX_OFFSET		0x0050
+#define DRA7XX_CM_CLKSEL_VIDEO2_MCASP_AUX			DRA7XX_PRM_REGADDR(DRA7XX_PRM_CKGEN_INST, 0x0050)
+#define DRA7XX_CM_CLKSEL_VIDEO2_TIMER_OFFSET			0x0054
+#define DRA7XX_CM_CLKSEL_VIDEO2_TIMER				DRA7XX_PRM_REGADDR(DRA7XX_PRM_CKGEN_INST, 0x0054)
+#define DRA7XX_CM_CLKSEL_CLKOUTMUX0_OFFSET			0x0058
+#define DRA7XX_CM_CLKSEL_CLKOUTMUX0				DRA7XX_PRM_REGADDR(DRA7XX_PRM_CKGEN_INST, 0x0058)
+#define DRA7XX_CM_CLKSEL_CLKOUTMUX1_OFFSET			0x005c
+#define DRA7XX_CM_CLKSEL_CLKOUTMUX1				DRA7XX_PRM_REGADDR(DRA7XX_PRM_CKGEN_INST, 0x005c)
+#define DRA7XX_CM_CLKSEL_CLKOUTMUX2_OFFSET			0x0060
+#define DRA7XX_CM_CLKSEL_CLKOUTMUX2				DRA7XX_PRM_REGADDR(DRA7XX_PRM_CKGEN_INST, 0x0060)
+#define DRA7XX_CM_CLKSEL_HDMI_PLL_SYS_OFFSET			0x0064
+#define DRA7XX_CM_CLKSEL_HDMI_PLL_SYS				DRA7XX_PRM_REGADDR(DRA7XX_PRM_CKGEN_INST, 0x0064)
+#define DRA7XX_CM_CLKSEL_VIDEO1_PLL_SYS_OFFSET			0x0068
+#define DRA7XX_CM_CLKSEL_VIDEO1_PLL_SYS				DRA7XX_PRM_REGADDR(DRA7XX_PRM_CKGEN_INST, 0x0068)
+#define DRA7XX_CM_CLKSEL_VIDEO2_PLL_SYS_OFFSET			0x006c
+#define DRA7XX_CM_CLKSEL_VIDEO2_PLL_SYS				DRA7XX_PRM_REGADDR(DRA7XX_PRM_CKGEN_INST, 0x006c)
+#define DRA7XX_CM_CLKSEL_ABE_CLK_DIV_OFFSET			0x0070
+#define DRA7XX_CM_CLKSEL_ABE_CLK_DIV				DRA7XX_PRM_REGADDR(DRA7XX_PRM_CKGEN_INST, 0x0070)
+#define DRA7XX_CM_CLKSEL_ABE_GICLK_DIV_OFFSET			0x0074
+#define DRA7XX_CM_CLKSEL_ABE_GICLK_DIV				DRA7XX_PRM_REGADDR(DRA7XX_PRM_CKGEN_INST, 0x0074)
+#define DRA7XX_CM_CLKSEL_AESS_FCLK_DIV_OFFSET			0x0078
+#define DRA7XX_CM_CLKSEL_AESS_FCLK_DIV				DRA7XX_PRM_REGADDR(DRA7XX_PRM_CKGEN_INST, 0x0078)
+#define DRA7XX_CM_CLKSEL_EVE_CLK_OFFSET				0x0080
+#define DRA7XX_CM_CLKSEL_EVE_CLK				DRA7XX_PRM_REGADDR(DRA7XX_PRM_CKGEN_INST, 0x0080)
+#define DRA7XX_CM_CLKSEL_USB_OTG_CLK_CLKOUTMUX_OFFSET		0x0084
+#define DRA7XX_CM_CLKSEL_USB_OTG_CLK_CLKOUTMUX			DRA7XX_PRM_REGADDR(DRA7XX_PRM_CKGEN_INST, 0x0084)
+#define DRA7XX_CM_CLKSEL_CORE_DPLL_OUT_CLK_CLKOUTMUX_OFFSET	0x0088
+#define DRA7XX_CM_CLKSEL_CORE_DPLL_OUT_CLK_CLKOUTMUX		DRA7XX_PRM_REGADDR(DRA7XX_PRM_CKGEN_INST, 0x0088)
+#define DRA7XX_CM_CLKSEL_DSP_GFCLK_CLKOUTMUX_OFFSET		0x008c
+#define DRA7XX_CM_CLKSEL_DSP_GFCLK_CLKOUTMUX			DRA7XX_PRM_REGADDR(DRA7XX_PRM_CKGEN_INST, 0x008c)
+#define DRA7XX_CM_CLKSEL_EMIF_PHY_GCLK_CLKOUTMUX_OFFSET		0x0090
+#define DRA7XX_CM_CLKSEL_EMIF_PHY_GCLK_CLKOUTMUX		DRA7XX_PRM_REGADDR(DRA7XX_PRM_CKGEN_INST, 0x0090)
+#define DRA7XX_CM_CLKSEL_EMU_CLK_CLKOUTMUX_OFFSET		0x0094
+#define DRA7XX_CM_CLKSEL_EMU_CLK_CLKOUTMUX			DRA7XX_PRM_REGADDR(DRA7XX_PRM_CKGEN_INST, 0x0094)
+#define DRA7XX_CM_CLKSEL_FUNC_96M_AON_CLK_CLKOUTMUX_OFFSET	0x0098
+#define DRA7XX_CM_CLKSEL_FUNC_96M_AON_CLK_CLKOUTMUX		DRA7XX_PRM_REGADDR(DRA7XX_PRM_CKGEN_INST, 0x0098)
+#define DRA7XX_CM_CLKSEL_GMAC_250M_CLK_CLKOUTMUX_OFFSET		0x009c
+#define DRA7XX_CM_CLKSEL_GMAC_250M_CLK_CLKOUTMUX		DRA7XX_PRM_REGADDR(DRA7XX_PRM_CKGEN_INST, 0x009c)
+#define DRA7XX_CM_CLKSEL_GPU_GCLK_CLKOUTMUX_OFFSET		0x00a0
+#define DRA7XX_CM_CLKSEL_GPU_GCLK_CLKOUTMUX			DRA7XX_PRM_REGADDR(DRA7XX_PRM_CKGEN_INST, 0x00a0)
+#define DRA7XX_CM_CLKSEL_HDMI_CLK_CLKOUTMUX_OFFSET		0x00a4
+#define DRA7XX_CM_CLKSEL_HDMI_CLK_CLKOUTMUX			DRA7XX_PRM_REGADDR(DRA7XX_PRM_CKGEN_INST, 0x00a4)
+#define DRA7XX_CM_CLKSEL_IVA_GCLK_CLKOUTMUX_OFFSET		0x00a8
+#define DRA7XX_CM_CLKSEL_IVA_GCLK_CLKOUTMUX			DRA7XX_PRM_REGADDR(DRA7XX_PRM_CKGEN_INST, 0x00a8)
+#define DRA7XX_CM_CLKSEL_L3INIT_480M_GFCLK_CLKOUTMUX_OFFSET	0x00ac
+#define DRA7XX_CM_CLKSEL_L3INIT_480M_GFCLK_CLKOUTMUX		DRA7XX_PRM_REGADDR(DRA7XX_PRM_CKGEN_INST, 0x00ac)
+#define DRA7XX_CM_CLKSEL_MPU_GCLK_CLKOUTMUX_OFFSET		0x00b0
+#define DRA7XX_CM_CLKSEL_MPU_GCLK_CLKOUTMUX			DRA7XX_PRM_REGADDR(DRA7XX_PRM_CKGEN_INST, 0x00b0)
+#define DRA7XX_CM_CLKSEL_PCIE1_CLK_CLKOUTMUX_OFFSET		0x00b4
+#define DRA7XX_CM_CLKSEL_PCIE1_CLK_CLKOUTMUX			DRA7XX_PRM_REGADDR(DRA7XX_PRM_CKGEN_INST, 0x00b4)
+#define DRA7XX_CM_CLKSEL_PCIE2_CLK_CLKOUTMUX_OFFSET		0x00b8
+#define DRA7XX_CM_CLKSEL_PCIE2_CLK_CLKOUTMUX			DRA7XX_PRM_REGADDR(DRA7XX_PRM_CKGEN_INST, 0x00b8)
+#define DRA7XX_CM_CLKSEL_PER_ABE_X1_CLK_CLKOUTMUX_OFFSET	0x00bc
+#define DRA7XX_CM_CLKSEL_PER_ABE_X1_CLK_CLKOUTMUX		DRA7XX_PRM_REGADDR(DRA7XX_PRM_CKGEN_INST, 0x00bc)
+#define DRA7XX_CM_CLKSEL_SATA_CLK_CLKOUTMUX_OFFSET		0x00c0
+#define DRA7XX_CM_CLKSEL_SATA_CLK_CLKOUTMUX			DRA7XX_PRM_REGADDR(DRA7XX_PRM_CKGEN_INST, 0x00c0)
+#define DRA7XX_CM_CLKSEL_SECURE_32K_CLK_CLKOUTMUX_OFFSET	0x00c4
+#define DRA7XX_CM_CLKSEL_SECURE_32K_CLK_CLKOUTMUX		DRA7XX_PRM_REGADDR(DRA7XX_PRM_CKGEN_INST, 0x00c4)
+#define DRA7XX_CM_CLKSEL_SYS_CLK1_CLKOUTMUX_OFFSET		0x00c8
+#define DRA7XX_CM_CLKSEL_SYS_CLK1_CLKOUTMUX			DRA7XX_PRM_REGADDR(DRA7XX_PRM_CKGEN_INST, 0x00c8)
+#define DRA7XX_CM_CLKSEL_SYS_CLK2_CLKOUTMUX_OFFSET		0x00cc
+#define DRA7XX_CM_CLKSEL_SYS_CLK2_CLKOUTMUX			DRA7XX_PRM_REGADDR(DRA7XX_PRM_CKGEN_INST, 0x00cc)
+#define DRA7XX_CM_CLKSEL_VIDEO1_CLK_CLKOUTMUX_OFFSET		0x00d0
+#define DRA7XX_CM_CLKSEL_VIDEO1_CLK_CLKOUTMUX			DRA7XX_PRM_REGADDR(DRA7XX_PRM_CKGEN_INST, 0x00d0)
+#define DRA7XX_CM_CLKSEL_VIDEO2_CLK_CLKOUTMUX_OFFSET		0x00d4
+#define DRA7XX_CM_CLKSEL_VIDEO2_CLK_CLKOUTMUX			DRA7XX_PRM_REGADDR(DRA7XX_PRM_CKGEN_INST, 0x00d4)
+#define DRA7XX_CM_CLKSEL_ABE_LP_CLK_OFFSET			0x00d8
+#define DRA7XX_CM_CLKSEL_ABE_LP_CLK				DRA7XX_PRM_REGADDR(DRA7XX_PRM_CKGEN_INST, 0x00d8)
+#define DRA7XX_CM_CLKSEL_ADC_GFCLK_OFFSET			0x00dc
+#define DRA7XX_CM_CLKSEL_ADC_GFCLK				DRA7XX_PRM_REGADDR(DRA7XX_PRM_CKGEN_INST, 0x00dc)
+#define DRA7XX_CM_CLKSEL_EVE_GFCLK_CLKOUTMUX_OFFSET		0x00e0
+#define DRA7XX_CM_CLKSEL_EVE_GFCLK_CLKOUTMUX			DRA7XX_PRM_REGADDR(DRA7XX_PRM_CKGEN_INST, 0x00e0)
+
+/* PRM.MPU_PRM register offsets */
+#define DRA7XX_PM_MPU_PWRSTCTRL_OFFSET				0x0000
+#define DRA7XX_PM_MPU_PWRSTST_OFFSET				0x0004
+#define DRA7XX_RM_MPU_MPU_CONTEXT_OFFSET			0x0024
+
+/* PRM.DSP1_PRM register offsets */
+#define DRA7XX_PM_DSP1_PWRSTCTRL_OFFSET				0x0000
+#define DRA7XX_PM_DSP1_PWRSTST_OFFSET				0x0004
+#define DRA7XX_RM_DSP1_RSTCTRL_OFFSET				0x0010
+#define DRA7XX_RM_DSP1_RSTST_OFFSET				0x0014
+#define DRA7XX_RM_DSP1_DSP1_CONTEXT_OFFSET			0x0024
+
+/* PRM.IPU_PRM register offsets */
+#define DRA7XX_PM_IPU_PWRSTCTRL_OFFSET				0x0000
+#define DRA7XX_PM_IPU_PWRSTST_OFFSET				0x0004
+#define DRA7XX_RM_IPU1_RSTCTRL_OFFSET				0x0010
+#define DRA7XX_RM_IPU1_RSTST_OFFSET				0x0014
+#define DRA7XX_RM_IPU1_IPU1_CONTEXT_OFFSET			0x0024
+#define DRA7XX_PM_IPU_MCASP1_WKDEP_OFFSET			0x0050
+#define DRA7XX_RM_IPU_MCASP1_CONTEXT_OFFSET			0x0054
+#define DRA7XX_PM_IPU_TIMER5_WKDEP_OFFSET			0x0058
+#define DRA7XX_RM_IPU_TIMER5_CONTEXT_OFFSET			0x005c
+#define DRA7XX_PM_IPU_TIMER6_WKDEP_OFFSET			0x0060
+#define DRA7XX_RM_IPU_TIMER6_CONTEXT_OFFSET			0x0064
+#define DRA7XX_PM_IPU_TIMER7_WKDEP_OFFSET			0x0068
+#define DRA7XX_RM_IPU_TIMER7_CONTEXT_OFFSET			0x006c
+#define DRA7XX_PM_IPU_TIMER8_WKDEP_OFFSET			0x0070
+#define DRA7XX_RM_IPU_TIMER8_CONTEXT_OFFSET			0x0074
+#define DRA7XX_PM_IPU_I2C5_WKDEP_OFFSET				0x0078
+#define DRA7XX_RM_IPU_I2C5_CONTEXT_OFFSET			0x007c
+#define DRA7XX_PM_IPU_UART6_WKDEP_OFFSET			0x0080
+#define DRA7XX_RM_IPU_UART6_CONTEXT_OFFSET			0x0084
+
+/* PRM.COREAON_PRM register offsets */
+#define DRA7XX_PM_COREAON_SMARTREFLEX_MPU_WKDEP_OFFSET		0x0000
+#define DRA7XX_RM_COREAON_SMARTREFLEX_MPU_CONTEXT_OFFSET	0x0004
+#define DRA7XX_PM_COREAON_SMARTREFLEX_CORE_WKDEP_OFFSET		0x0010
+#define DRA7XX_RM_COREAON_SMARTREFLEX_CORE_CONTEXT_OFFSET	0x0014
+#define DRA7XX_PM_COREAON_SMARTREFLEX_GPU_WKDEP_OFFSET		0x0030
+#define DRA7XX_RM_COREAON_SMARTREFLEX_GPU_CONTEXT_OFFSET	0x0034
+#define DRA7XX_PM_COREAON_SMARTREFLEX_DSPEVE_WKDEP_OFFSET	0x0040
+#define DRA7XX_RM_COREAON_SMARTREFLEX_DSPEVE_CONTEXT_OFFSET	0x0044
+#define DRA7XX_PM_COREAON_SMARTREFLEX_IVAHD_WKDEP_OFFSET	0x0050
+#define DRA7XX_RM_COREAON_SMARTREFLEX_IVAHD_CONTEXT_OFFSET	0x0054
+#define DRA7XX_RM_COREAON_DUMMY_MODULE1_CONTEXT_OFFSET		0x0084
+#define DRA7XX_RM_COREAON_DUMMY_MODULE2_CONTEXT_OFFSET		0x0094
+#define DRA7XX_RM_COREAON_DUMMY_MODULE3_CONTEXT_OFFSET		0x00a4
+#define DRA7XX_RM_COREAON_DUMMY_MODULE4_CONTEXT_OFFSET		0x00b4
+
+/* PRM.CORE_PRM register offsets */
+#define DRA7XX_PM_CORE_PWRSTCTRL_OFFSET				0x0000
+#define DRA7XX_PM_CORE_PWRSTST_OFFSET				0x0004
+#define DRA7XX_RM_L3MAIN1_L3_MAIN_1_CONTEXT_OFFSET		0x0024
+#define DRA7XX_RM_L3MAIN1_GPMC_CONTEXT_OFFSET			0x002c
+#define DRA7XX_RM_L3MAIN1_MMU_EDMA_CONTEXT_OFFSET		0x0034
+#define DRA7XX_PM_L3MAIN1_OCMC_RAM1_WKDEP_OFFSET		0x0050
+#define DRA7XX_RM_L3MAIN1_OCMC_RAM1_CONTEXT_OFFSET		0x0054
+#define DRA7XX_PM_L3MAIN1_OCMC_RAM2_WKDEP_OFFSET		0x0058
+#define DRA7XX_RM_L3MAIN1_OCMC_RAM2_CONTEXT_OFFSET		0x005c
+#define DRA7XX_PM_L3MAIN1_OCMC_RAM3_WKDEP_OFFSET		0x0060
+#define DRA7XX_RM_L3MAIN1_OCMC_RAM3_CONTEXT_OFFSET		0x0064
+#define DRA7XX_RM_L3MAIN1_OCMC_ROM_CONTEXT_OFFSET		0x006c
+#define DRA7XX_PM_L3MAIN1_TPCC_WKDEP_OFFSET			0x0070
+#define DRA7XX_RM_L3MAIN1_TPCC_CONTEXT_OFFSET			0x0074
+#define DRA7XX_PM_L3MAIN1_TPTC1_WKDEP_OFFSET			0x0078
+#define DRA7XX_RM_L3MAIN1_TPTC1_CONTEXT_OFFSET			0x007c
+#define DRA7XX_PM_L3MAIN1_TPTC2_WKDEP_OFFSET			0x0080
+#define DRA7XX_RM_L3MAIN1_TPTC2_CONTEXT_OFFSET			0x0084
+#define DRA7XX_RM_L3MAIN1_VCP1_CONTEXT_OFFSET			0x008c
+#define DRA7XX_RM_L3MAIN1_VCP2_CONTEXT_OFFSET			0x0094
+#define DRA7XX_RM_L3MAIN1_SPARE_CME_CONTEXT_OFFSET		0x009c
+#define DRA7XX_RM_L3MAIN1_SPARE_HDMI_CONTEXT_OFFSET		0x00a4
+#define DRA7XX_RM_L3MAIN1_SPARE_ICM_CONTEXT_OFFSET		0x00ac
+#define DRA7XX_RM_L3MAIN1_SPARE_IVA2_CONTEXT_OFFSET		0x00b4
+#define DRA7XX_RM_L3MAIN1_SPARE_SATA2_CONTEXT_OFFSET		0x00bc
+#define DRA7XX_RM_L3MAIN1_SPARE_UNKNOWN4_CONTEXT_OFFSET		0x00c4
+#define DRA7XX_RM_L3MAIN1_SPARE_UNKNOWN5_CONTEXT_OFFSET		0x00cc
+#define DRA7XX_RM_L3MAIN1_SPARE_UNKNOWN6_CONTEXT_OFFSET		0x00d4
+#define DRA7XX_RM_L3MAIN1_SPARE_VIDEOPLL1_CONTEXT_OFFSET	0x00dc
+#define DRA7XX_RM_L3MAIN1_SPARE_VIDEOPLL2_CONTEXT_OFFSET	0x00f4
+#define DRA7XX_RM_L3MAIN1_SPARE_VIDEOPLL3_CONTEXT_OFFSET	0x00fc
+#define DRA7XX_RM_IPU2_RSTCTRL_OFFSET				0x0210
+#define DRA7XX_RM_IPU2_RSTST_OFFSET				0x0214
+#define DRA7XX_RM_IPU2_IPU2_CONTEXT_OFFSET			0x0224
+#define DRA7XX_RM_DMA_DMA_SYSTEM_CONTEXT_OFFSET			0x0324
+#define DRA7XX_RM_EMIF_DMM_CONTEXT_OFFSET			0x0424
+#define DRA7XX_RM_EMIF_EMIF_OCP_FW_CONTEXT_OFFSET		0x042c
+#define DRA7XX_RM_EMIF_EMIF1_CONTEXT_OFFSET			0x0434
+#define DRA7XX_RM_EMIF_EMIF2_CONTEXT_OFFSET			0x043c
+#define DRA7XX_RM_EMIF_EMIF_DLL_CONTEXT_OFFSET			0x0444
+#define DRA7XX_RM_ATL_ATL_CONTEXT_OFFSET			0x0524
+#define DRA7XX_RM_L4CFG_L4_CFG_CONTEXT_OFFSET			0x0624
+#define DRA7XX_RM_L4CFG_SPINLOCK_CONTEXT_OFFSET			0x062c
+#define DRA7XX_RM_L4CFG_MAILBOX1_CONTEXT_OFFSET			0x0634
+#define DRA7XX_RM_L4CFG_SAR_ROM_CONTEXT_OFFSET			0x063c
+#define DRA7XX_RM_L4CFG_OCP2SCP2_CONTEXT_OFFSET			0x0644
+#define DRA7XX_RM_L4CFG_MAILBOX2_CONTEXT_OFFSET			0x064c
+#define DRA7XX_RM_L4CFG_MAILBOX3_CONTEXT_OFFSET			0x0654
+#define DRA7XX_RM_L4CFG_MAILBOX4_CONTEXT_OFFSET			0x065c
+#define DRA7XX_RM_L4CFG_MAILBOX5_CONTEXT_OFFSET			0x0664
+#define DRA7XX_RM_L4CFG_MAILBOX6_CONTEXT_OFFSET			0x066c
+#define DRA7XX_RM_L4CFG_MAILBOX7_CONTEXT_OFFSET			0x0674
+#define DRA7XX_RM_L4CFG_MAILBOX8_CONTEXT_OFFSET			0x067c
+#define DRA7XX_RM_L4CFG_MAILBOX9_CONTEXT_OFFSET			0x0684
+#define DRA7XX_RM_L4CFG_MAILBOX10_CONTEXT_OFFSET		0x068c
+#define DRA7XX_RM_L4CFG_MAILBOX11_CONTEXT_OFFSET		0x0694
+#define DRA7XX_RM_L4CFG_MAILBOX12_CONTEXT_OFFSET		0x069c
+#define DRA7XX_RM_L4CFG_MAILBOX13_CONTEXT_OFFSET		0x06a4
+#define DRA7XX_RM_L4CFG_SPARE_SMARTREFLEX_RTC_CONTEXT_OFFSET	0x06ac
+#define DRA7XX_RM_L4CFG_SPARE_SMARTREFLEX_SDRAM_CONTEXT_OFFSET	0x06b4
+#define DRA7XX_RM_L4CFG_SPARE_SMARTREFLEX_WKUP_CONTEXT_OFFSET	0x06bc
+#define DRA7XX_RM_L4CFG_IO_DELAY_BLOCK_CONTEXT_OFFSET		0x06c4
+#define DRA7XX_RM_L3INSTR_L3_MAIN_2_CONTEXT_OFFSET		0x0724
+#define DRA7XX_RM_L3INSTR_L3_INSTR_CONTEXT_OFFSET		0x072c
+#define DRA7XX_RM_L3INSTR_OCP_WP_NOC_CONTEXT_OFFSET		0x0744
+
+/* PRM.IVA_PRM register offsets */
+#define DRA7XX_PM_IVA_PWRSTCTRL_OFFSET				0x0000
+#define DRA7XX_PM_IVA_PWRSTST_OFFSET				0x0004
+#define DRA7XX_RM_IVA_RSTCTRL_OFFSET				0x0010
+#define DRA7XX_RM_IVA_RSTST_OFFSET				0x0014
+#define DRA7XX_RM_IVA_IVA_CONTEXT_OFFSET			0x0024
+#define DRA7XX_RM_IVA_SL2_CONTEXT_OFFSET			0x002c
+
+/* PRM.CAM_PRM register offsets */
+#define DRA7XX_PM_CAM_PWRSTCTRL_OFFSET				0x0000
+#define DRA7XX_PM_CAM_PWRSTST_OFFSET				0x0004
+#define DRA7XX_PM_CAM_VIP1_WKDEP_OFFSET				0x0020
+#define DRA7XX_RM_CAM_VIP1_CONTEXT_OFFSET			0x0024
+#define DRA7XX_PM_CAM_VIP2_WKDEP_OFFSET				0x0028
+#define DRA7XX_RM_CAM_VIP2_CONTEXT_OFFSET			0x002c
+#define DRA7XX_PM_CAM_VIP3_WKDEP_OFFSET				0x0030
+#define DRA7XX_RM_CAM_VIP3_CONTEXT_OFFSET			0x0034
+#define DRA7XX_RM_CAM_LVDSRX_CONTEXT_OFFSET			0x003c
+#define DRA7XX_RM_CAM_CSI1_CONTEXT_OFFSET			0x0044
+#define DRA7XX_RM_CAM_CSI2_CONTEXT_OFFSET			0x004c
+
+/* PRM.DSS_PRM register offsets */
+#define DRA7XX_PM_DSS_PWRSTCTRL_OFFSET				0x0000
+#define DRA7XX_PM_DSS_PWRSTST_OFFSET				0x0004
+#define DRA7XX_PM_DSS_DSS_WKDEP_OFFSET				0x0020
+#define DRA7XX_RM_DSS_DSS_CONTEXT_OFFSET			0x0024
+#define DRA7XX_PM_DSS_DSS2_WKDEP_OFFSET				0x0028
+#define DRA7XX_RM_DSS_BB2D_CONTEXT_OFFSET			0x0034
+#define DRA7XX_RM_DSS_SDVENC_CONTEXT_OFFSET			0x003c
+
+/* PRM.GPU_PRM register offsets */
+#define DRA7XX_PM_GPU_PWRSTCTRL_OFFSET				0x0000
+#define DRA7XX_PM_GPU_PWRSTST_OFFSET				0x0004
+#define DRA7XX_RM_GPU_GPU_CONTEXT_OFFSET			0x0024
+
+/* PRM.L3INIT_PRM register offsets */
+#define DRA7XX_PM_L3INIT_PWRSTCTRL_OFFSET			0x0000
+#define DRA7XX_PM_L3INIT_PWRSTST_OFFSET				0x0004
+#define DRA7XX_PM_L3INIT_MMC1_WKDEP_OFFSET			0x0028
+#define DRA7XX_RM_L3INIT_MMC1_CONTEXT_OFFSET			0x002c
+#define DRA7XX_PM_L3INIT_MMC2_WKDEP_OFFSET			0x0030
+#define DRA7XX_RM_L3INIT_MMC2_CONTEXT_OFFSET			0x0034
+#define DRA7XX_PM_L3INIT_USB_OTG_SS2_WKDEP_OFFSET		0x0040
+#define DRA7XX_RM_L3INIT_USB_OTG_SS2_CONTEXT_OFFSET		0x0044
+#define DRA7XX_PM_L3INIT_USB_OTG_SS3_WKDEP_OFFSET		0x0048
+#define DRA7XX_RM_L3INIT_USB_OTG_SS3_CONTEXT_OFFSET		0x004c
+#define DRA7XX_PM_L3INIT_USB_OTG_SS4_WKDEP_OFFSET		0x0050
+#define DRA7XX_RM_L3INIT_USB_OTG_SS4_CONTEXT_OFFSET		0x0054
+#define DRA7XX_RM_L3INIT_MLB_SS_CONTEXT_OFFSET			0x005c
+#define DRA7XX_RM_L3INIT_IEEE1500_2_OCP_CONTEXT_OFFSET		0x007c
+#define DRA7XX_PM_L3INIT_SATA_WKDEP_OFFSET			0x0088
+#define DRA7XX_RM_L3INIT_SATA_CONTEXT_OFFSET			0x008c
+#define DRA7XX_RM_GMAC_GMAC_CONTEXT_OFFSET			0x00d4
+#define DRA7XX_RM_L3INIT_OCP2SCP1_CONTEXT_OFFSET		0x00e4
+#define DRA7XX_RM_L3INIT_OCP2SCP3_CONTEXT_OFFSET		0x00ec
+#define DRA7XX_PM_L3INIT_USB_OTG_SS1_WKDEP_OFFSET		0x00f0
+#define DRA7XX_RM_L3INIT_USB_OTG_SS1_CONTEXT_OFFSET		0x00f4
+
+/* PRM.L4PER_PRM register offsets */
+#define DRA7XX_PM_L4PER_PWRSTCTRL_OFFSET			0x0000
+#define DRA7XX_PM_L4PER_PWRSTST_OFFSET				0x0004
+#define DRA7XX_RM_L4PER2_L4PER2_CONTEXT_OFFSET			0x000c
+#define DRA7XX_RM_L4PER3_L4PER3_CONTEXT_OFFSET			0x0014
+#define DRA7XX_RM_L4PER2_PRUSS1_CONTEXT_OFFSET			0x001c
+#define DRA7XX_RM_L4PER2_PRUSS2_CONTEXT_OFFSET			0x0024
+#define DRA7XX_PM_L4PER_TIMER10_WKDEP_OFFSET			0x0028
+#define DRA7XX_RM_L4PER_TIMER10_CONTEXT_OFFSET			0x002c
+#define DRA7XX_PM_L4PER_TIMER11_WKDEP_OFFSET			0x0030
+#define DRA7XX_RM_L4PER_TIMER11_CONTEXT_OFFSET			0x0034
+#define DRA7XX_PM_L4PER_TIMER2_WKDEP_OFFSET			0x0038
+#define DRA7XX_RM_L4PER_TIMER2_CONTEXT_OFFSET			0x003c
+#define DRA7XX_PM_L4PER_TIMER3_WKDEP_OFFSET			0x0040
+#define DRA7XX_RM_L4PER_TIMER3_CONTEXT_OFFSET			0x0044
+#define DRA7XX_PM_L4PER_TIMER4_WKDEP_OFFSET			0x0048
+#define DRA7XX_RM_L4PER_TIMER4_CONTEXT_OFFSET			0x004c
+#define DRA7XX_PM_L4PER_TIMER9_WKDEP_OFFSET			0x0050
+#define DRA7XX_RM_L4PER_TIMER9_CONTEXT_OFFSET			0x0054
+#define DRA7XX_RM_L4PER_ELM_CONTEXT_OFFSET			0x005c
+#define DRA7XX_PM_L4PER_GPIO2_WKDEP_OFFSET			0x0060
+#define DRA7XX_RM_L4PER_GPIO2_CONTEXT_OFFSET			0x0064
+#define DRA7XX_PM_L4PER_GPIO3_WKDEP_OFFSET			0x0068
+#define DRA7XX_RM_L4PER_GPIO3_CONTEXT_OFFSET			0x006c
+#define DRA7XX_PM_L4PER_GPIO4_WKDEP_OFFSET			0x0070
+#define DRA7XX_RM_L4PER_GPIO4_CONTEXT_OFFSET			0x0074
+#define DRA7XX_PM_L4PER_GPIO5_WKDEP_OFFSET			0x0078
+#define DRA7XX_RM_L4PER_GPIO5_CONTEXT_OFFSET			0x007c
+#define DRA7XX_PM_L4PER_GPIO6_WKDEP_OFFSET			0x0080
+#define DRA7XX_RM_L4PER_GPIO6_CONTEXT_OFFSET			0x0084
+#define DRA7XX_RM_L4PER_HDQ1W_CONTEXT_OFFSET			0x008c
+#define DRA7XX_RM_L4PER2_PWMSS2_CONTEXT_OFFSET			0x0094
+#define DRA7XX_RM_L4PER2_PWMSS3_CONTEXT_OFFSET			0x009c
+#define DRA7XX_PM_L4PER_I2C1_WKDEP_OFFSET			0x00a0
+#define DRA7XX_RM_L4PER_I2C1_CONTEXT_OFFSET			0x00a4
+#define DRA7XX_PM_L4PER_I2C2_WKDEP_OFFSET			0x00a8
+#define DRA7XX_RM_L4PER_I2C2_CONTEXT_OFFSET			0x00ac
+#define DRA7XX_PM_L4PER_I2C3_WKDEP_OFFSET			0x00b0
+#define DRA7XX_RM_L4PER_I2C3_CONTEXT_OFFSET			0x00b4
+#define DRA7XX_PM_L4PER_I2C4_WKDEP_OFFSET			0x00b8
+#define DRA7XX_RM_L4PER_I2C4_CONTEXT_OFFSET			0x00bc
+#define DRA7XX_RM_L4PER_L4PER1_CONTEXT_OFFSET			0x00c0
+#define DRA7XX_RM_L4PER2_PWMSS1_CONTEXT_OFFSET			0x00c4
+#define DRA7XX_PM_L4PER_TIMER13_WKDEP_OFFSET			0x00c8
+#define DRA7XX_RM_L4PER3_TIMER13_CONTEXT_OFFSET			0x00cc
+#define DRA7XX_PM_L4PER_TIMER14_WKDEP_OFFSET			0x00d0
+#define DRA7XX_RM_L4PER3_TIMER14_CONTEXT_OFFSET			0x00d4
+#define DRA7XX_PM_L4PER_TIMER15_WKDEP_OFFSET			0x00d8
+#define DRA7XX_RM_L4PER3_TIMER15_CONTEXT_OFFSET			0x00dc
+#define DRA7XX_PM_L4PER_MCSPI1_WKDEP_OFFSET			0x00f0
+#define DRA7XX_RM_L4PER_MCSPI1_CONTEXT_OFFSET			0x00f4
+#define DRA7XX_PM_L4PER_MCSPI2_WKDEP_OFFSET			0x00f8
+#define DRA7XX_RM_L4PER_MCSPI2_CONTEXT_OFFSET			0x00fc
+#define DRA7XX_PM_L4PER_MCSPI3_WKDEP_OFFSET			0x0100
+#define DRA7XX_RM_L4PER_MCSPI3_CONTEXT_OFFSET			0x0104
+#define DRA7XX_PM_L4PER_MCSPI4_WKDEP_OFFSET			0x0108
+#define DRA7XX_RM_L4PER_MCSPI4_CONTEXT_OFFSET			0x010c
+#define DRA7XX_PM_L4PER_GPIO7_WKDEP_OFFSET			0x0110
+#define DRA7XX_RM_L4PER_GPIO7_CONTEXT_OFFSET			0x0114
+#define DRA7XX_PM_L4PER_GPIO8_WKDEP_OFFSET			0x0118
+#define DRA7XX_RM_L4PER_GPIO8_CONTEXT_OFFSET			0x011c
+#define DRA7XX_PM_L4PER_MMC3_WKDEP_OFFSET			0x0120
+#define DRA7XX_RM_L4PER_MMC3_CONTEXT_OFFSET			0x0124
+#define DRA7XX_PM_L4PER_MMC4_WKDEP_OFFSET			0x0128
+#define DRA7XX_RM_L4PER_MMC4_CONTEXT_OFFSET			0x012c
+#define DRA7XX_PM_L4PER_TIMER16_WKDEP_OFFSET			0x0130
+#define DRA7XX_RM_L4PER3_TIMER16_CONTEXT_OFFSET			0x0134
+#define DRA7XX_PM_L4PER2_QSPI_WKDEP_OFFSET			0x0138
+#define DRA7XX_RM_L4PER2_QSPI_CONTEXT_OFFSET			0x013c
+#define DRA7XX_PM_L4PER_UART1_WKDEP_OFFSET			0x0140
+#define DRA7XX_RM_L4PER_UART1_CONTEXT_OFFSET			0x0144
+#define DRA7XX_PM_L4PER_UART2_WKDEP_OFFSET			0x0148
+#define DRA7XX_RM_L4PER_UART2_CONTEXT_OFFSET			0x014c
+#define DRA7XX_PM_L4PER_UART3_WKDEP_OFFSET			0x0150
+#define DRA7XX_RM_L4PER_UART3_CONTEXT_OFFSET			0x0154
+#define DRA7XX_PM_L4PER_UART4_WKDEP_OFFSET			0x0158
+#define DRA7XX_RM_L4PER_UART4_CONTEXT_OFFSET			0x015c
+#define DRA7XX_PM_L4PER2_MCASP2_WKDEP_OFFSET			0x0160
+#define DRA7XX_RM_L4PER2_MCASP2_CONTEXT_OFFSET			0x0164
+#define DRA7XX_PM_L4PER2_MCASP3_WKDEP_OFFSET			0x0168
+#define DRA7XX_RM_L4PER2_MCASP3_CONTEXT_OFFSET			0x016c
+#define DRA7XX_PM_L4PER_UART5_WKDEP_OFFSET			0x0170
+#define DRA7XX_RM_L4PER_UART5_CONTEXT_OFFSET			0x0174
+#define DRA7XX_PM_L4PER2_MCASP5_WKDEP_OFFSET			0x0178
+#define DRA7XX_RM_L4PER2_MCASP5_CONTEXT_OFFSET			0x017c
+#define DRA7XX_PM_L4PER2_MCASP6_WKDEP_OFFSET			0x0180
+#define DRA7XX_RM_L4PER2_MCASP6_CONTEXT_OFFSET			0x0184
+#define DRA7XX_PM_L4PER2_MCASP7_WKDEP_OFFSET			0x0188
+#define DRA7XX_RM_L4PER2_MCASP7_CONTEXT_OFFSET			0x018c
+#define DRA7XX_PM_L4PER2_MCASP8_WKDEP_OFFSET			0x0190
+#define DRA7XX_RM_L4PER2_MCASP8_CONTEXT_OFFSET			0x0194
+#define DRA7XX_PM_L4PER2_MCASP4_WKDEP_OFFSET			0x0198
+#define DRA7XX_RM_L4PER2_MCASP4_CONTEXT_OFFSET			0x019c
+#define DRA7XX_RM_L4SEC_AES1_CONTEXT_OFFSET			0x01a4
+#define DRA7XX_RM_L4SEC_AES2_CONTEXT_OFFSET			0x01ac
+#define DRA7XX_RM_L4SEC_DES3DES_CONTEXT_OFFSET			0x01b4
+#define DRA7XX_RM_L4SEC_FPKA_CONTEXT_OFFSET			0x01bc
+#define DRA7XX_RM_L4SEC_RNG_CONTEXT_OFFSET			0x01c4
+#define DRA7XX_RM_L4SEC_SHA2MD51_CONTEXT_OFFSET			0x01cc
+#define DRA7XX_PM_L4PER2_UART7_WKDEP_OFFSET			0x01d0
+#define DRA7XX_RM_L4PER2_UART7_CONTEXT_OFFSET			0x01d4
+#define DRA7XX_RM_L4SEC_DMA_CRYPTO_CONTEXT_OFFSET		0x01dc
+#define DRA7XX_PM_L4PER2_UART8_WKDEP_OFFSET			0x01e0
+#define DRA7XX_RM_L4PER2_UART8_CONTEXT_OFFSET			0x01e4
+#define DRA7XX_PM_L4PER2_UART9_WKDEP_OFFSET			0x01e8
+#define DRA7XX_RM_L4PER2_UART9_CONTEXT_OFFSET			0x01ec
+#define DRA7XX_PM_L4PER2_DCAN2_WKDEP_OFFSET			0x01f0
+#define DRA7XX_RM_L4PER2_DCAN2_CONTEXT_OFFSET			0x01f4
+#define DRA7XX_RM_L4SEC_SHA2MD52_CONTEXT_OFFSET			0x01fc
+
+/* PRM.CUSTEFUSE_PRM register offsets */
+#define DRA7XX_PM_CUSTEFUSE_PWRSTCTRL_OFFSET			0x0000
+#define DRA7XX_PM_CUSTEFUSE_PWRSTST_OFFSET			0x0004
+#define DRA7XX_RM_CUSTEFUSE_EFUSE_CTRL_CUST_CONTEXT_OFFSET	0x0024
+
+/* PRM.WKUPAON_PRM register offsets */
+#define DRA7XX_RM_WKUPAON_L4_WKUP_CONTEXT_OFFSET		0x0000
+#define DRA7XX_PM_WKUPAON_WD_TIMER1_WKDEP_OFFSET		0x0004
+#define DRA7XX_RM_WKUPAON_WD_TIMER1_CONTEXT_OFFSET		0x0008
+#define DRA7XX_PM_WKUPAON_WD_TIMER2_WKDEP_OFFSET		0x000c
+#define DRA7XX_RM_WKUPAON_WD_TIMER2_CONTEXT_OFFSET		0x0010
+#define DRA7XX_PM_WKUPAON_GPIO1_WKDEP_OFFSET			0x0014
+#define DRA7XX_RM_WKUPAON_GPIO1_CONTEXT_OFFSET			0x0018
+#define DRA7XX_PM_WKUPAON_TIMER1_WKDEP_OFFSET			0x001c
+#define DRA7XX_RM_WKUPAON_TIMER1_CONTEXT_OFFSET			0x0020
+#define DRA7XX_PM_WKUPAON_TIMER12_WKDEP_OFFSET			0x0024
+#define DRA7XX_RM_WKUPAON_TIMER12_CONTEXT_OFFSET		0x0028
+#define DRA7XX_RM_WKUPAON_COUNTER_32K_CONTEXT_OFFSET		0x0030
+#define DRA7XX_RM_WKUPAON_SAR_RAM_CONTEXT_OFFSET		0x0040
+#define DRA7XX_PM_WKUPAON_KBD_WKDEP_OFFSET			0x0054
+#define DRA7XX_RM_WKUPAON_KBD_CONTEXT_OFFSET			0x0058
+#define DRA7XX_PM_WKUPAON_UART10_WKDEP_OFFSET			0x005c
+#define DRA7XX_RM_WKUPAON_UART10_CONTEXT_OFFSET			0x0060
+#define DRA7XX_PM_WKUPAON_DCAN1_WKDEP_OFFSET			0x0064
+#define DRA7XX_RM_WKUPAON_DCAN1_CONTEXT_OFFSET			0x0068
+#define DRA7XX_PM_WKUPAON_ADC_WKDEP_OFFSET				0x007c
+#define DRA7XX_RM_WKUPAON_ADC_CONTEXT_OFFSET			0x0080
+#define DRA7XX_RM_WKUPAON_SPARE_SAFETY1_CONTEXT_OFFSET		0x0090
+#define DRA7XX_RM_WKUPAON_SPARE_SAFETY2_CONTEXT_OFFSET		0x0098
+#define DRA7XX_RM_WKUPAON_SPARE_SAFETY3_CONTEXT_OFFSET		0x00a0
+#define DRA7XX_RM_WKUPAON_SPARE_SAFETY4_CONTEXT_OFFSET		0x00a8
+#define DRA7XX_RM_WKUPAON_SPARE_UNKNOWN2_CONTEXT_OFFSET		0x00b0
+#define DRA7XX_RM_WKUPAON_SPARE_UNKNOWN3_CONTEXT_OFFSET		0x00b8
+
+/* PRM.WKUPAON_CM register offsets */
+#define DRA7XX_CM_WKUPAON_CLKSTCTRL_OFFSET			0x0000
+#define DRA7XX_CM_WKUPAON_L4_WKUP_CLKCTRL_OFFSET		0x0020
+#define DRA7XX_CM_WKUPAON_L4_WKUP_CLKCTRL			DRA7XX_PRM_REGADDR(DRA7XX_PRM_WKUPAON_CM_INST, 0x0020)
+#define DRA7XX_CM_WKUPAON_WD_TIMER1_CLKCTRL_OFFSET		0x0028
+#define DRA7XX_CM_WKUPAON_WD_TIMER1_CLKCTRL			DRA7XX_PRM_REGADDR(DRA7XX_PRM_WKUPAON_CM_INST, 0x0028)
+#define DRA7XX_CM_WKUPAON_WD_TIMER2_CLKCTRL_OFFSET		0x0030
+#define DRA7XX_CM_WKUPAON_WD_TIMER2_CLKCTRL			DRA7XX_PRM_REGADDR(DRA7XX_PRM_WKUPAON_CM_INST, 0x0030)
+#define DRA7XX_CM_WKUPAON_GPIO1_CLKCTRL_OFFSET			0x0038
+#define DRA7XX_CM_WKUPAON_GPIO1_CLKCTRL				DRA7XX_PRM_REGADDR(DRA7XX_PRM_WKUPAON_CM_INST, 0x0038)
+#define DRA7XX_CM_WKUPAON_TIMER1_CLKCTRL_OFFSET			0x0040
+#define DRA7XX_CM_WKUPAON_TIMER1_CLKCTRL			DRA7XX_PRM_REGADDR(DRA7XX_PRM_WKUPAON_CM_INST, 0x0040)
+#define DRA7XX_CM_WKUPAON_TIMER12_CLKCTRL_OFFSET		0x0048
+#define DRA7XX_CM_WKUPAON_TIMER12_CLKCTRL			DRA7XX_PRM_REGADDR(DRA7XX_PRM_WKUPAON_CM_INST, 0x0048)
+#define DRA7XX_CM_WKUPAON_COUNTER_32K_CLKCTRL_OFFSET		0x0050
+#define DRA7XX_CM_WKUPAON_COUNTER_32K_CLKCTRL			DRA7XX_PRM_REGADDR(DRA7XX_PRM_WKUPAON_CM_INST, 0x0050)
+#define DRA7XX_CM_WKUPAON_SAR_RAM_CLKCTRL_OFFSET		0x0060
+#define DRA7XX_CM_WKUPAON_SAR_RAM_CLKCTRL			DRA7XX_PRM_REGADDR(DRA7XX_PRM_WKUPAON_CM_INST, 0x0060)
+#define DRA7XX_CM_WKUPAON_KBD_CLKCTRL_OFFSET			0x0078
+#define DRA7XX_CM_WKUPAON_KBD_CLKCTRL				DRA7XX_PRM_REGADDR(DRA7XX_PRM_WKUPAON_CM_INST, 0x0078)
+#define DRA7XX_CM_WKUPAON_UART10_CLKCTRL_OFFSET			0x0080
+#define DRA7XX_CM_WKUPAON_UART10_CLKCTRL			DRA7XX_PRM_REGADDR(DRA7XX_PRM_WKUPAON_CM_INST, 0x0080)
+#define DRA7XX_CM_WKUPAON_DCAN1_CLKCTRL_OFFSET			0x0088
+#define DRA7XX_CM_WKUPAON_DCAN1_CLKCTRL				DRA7XX_PRM_REGADDR(DRA7XX_PRM_WKUPAON_CM_INST, 0x0088)
+#define DRA7XX_CM_WKUPAON_SCRM_CLKCTRL_OFFSET			0x0090
+#define DRA7XX_CM_WKUPAON_SCRM_CLKCTRL				DRA7XX_PRM_REGADDR(DRA7XX_PRM_WKUPAON_CM_INST, 0x0090)
+#define DRA7XX_CM_WKUPAON_IO_SRCOMP_CLKCTRL_OFFSET		0x0098
+#define DRA7XX_CM_WKUPAON_IO_SRCOMP_CLKCTRL			DRA7XX_PRM_REGADDR(DRA7XX_PRM_WKUPAON_CM_INST, 0x0098)
+#define DRA7XX_CM_WKUPAON_ADC_CLKCTRL_OFFSET			0x00a0
+#define DRA7XX_CM_WKUPAON_ADC_CLKCTRL				DRA7XX_PRM_REGADDR(DRA7XX_PRM_WKUPAON_CM_INST, 0x00a0)
+#define DRA7XX_CM_WKUPAON_SPARE_SAFETY1_CLKCTRL_OFFSET		0x00b0
+#define DRA7XX_CM_WKUPAON_SPARE_SAFETY1_CLKCTRL			DRA7XX_PRM_REGADDR(DRA7XX_PRM_WKUPAON_CM_INST, 0x00b0)
+#define DRA7XX_CM_WKUPAON_SPARE_SAFETY2_CLKCTRL_OFFSET		0x00b8
+#define DRA7XX_CM_WKUPAON_SPARE_SAFETY2_CLKCTRL			DRA7XX_PRM_REGADDR(DRA7XX_PRM_WKUPAON_CM_INST, 0x00b8)
+#define DRA7XX_CM_WKUPAON_SPARE_SAFETY3_CLKCTRL_OFFSET		0x00c0
+#define DRA7XX_CM_WKUPAON_SPARE_SAFETY3_CLKCTRL			DRA7XX_PRM_REGADDR(DRA7XX_PRM_WKUPAON_CM_INST, 0x00c0)
+#define DRA7XX_CM_WKUPAON_SPARE_SAFETY4_CLKCTRL_OFFSET		0x00c8
+#define DRA7XX_CM_WKUPAON_SPARE_SAFETY4_CLKCTRL			DRA7XX_PRM_REGADDR(DRA7XX_PRM_WKUPAON_CM_INST, 0x00c8)
+#define DRA7XX_CM_WKUPAON_SPARE_UNKNOWN2_CLKCTRL_OFFSET		0x00d0
+#define DRA7XX_CM_WKUPAON_SPARE_UNKNOWN2_CLKCTRL		DRA7XX_PRM_REGADDR(DRA7XX_PRM_WKUPAON_CM_INST, 0x00d0)
+#define DRA7XX_CM_WKUPAON_SPARE_UNKNOWN3_CLKCTRL_OFFSET		0x00d8
+#define DRA7XX_CM_WKUPAON_SPARE_UNKNOWN3_CLKCTRL		DRA7XX_PRM_REGADDR(DRA7XX_PRM_WKUPAON_CM_INST, 0x00d8)
+
+/* PRM.EMU_PRM register offsets */
+#define DRA7XX_PM_EMU_PWRSTCTRL_OFFSET				0x0000
+#define DRA7XX_PM_EMU_PWRSTST_OFFSET				0x0004
+#define DRA7XX_RM_EMU_DEBUGSS_CONTEXT_OFFSET			0x0024
+
+/* PRM.EMU_CM register offsets */
+#define DRA7XX_CM_EMU_CLKSTCTRL_OFFSET				0x0000
+#define DRA7XX_CM_EMU_DEBUGSS_CLKCTRL_OFFSET			0x0004
+#define DRA7XX_CM_EMU_DEBUGSS_CLKCTRL				DRA7XX_PRM_REGADDR(DRA7XX_PRM_EMU_CM_INST, 0x0004)
+#define DRA7XX_CM_EMU_DYNAMICDEP_OFFSET				0x0008
+#define DRA7XX_CM_EMU_MPU_EMU_DBG_CLKCTRL_OFFSET		0x000c
+#define DRA7XX_CM_EMU_MPU_EMU_DBG_CLKCTRL			DRA7XX_PRM_REGADDR(DRA7XX_PRM_EMU_CM_INST, 0x000c)
+
+/* PRM.DSP2_PRM register offsets */
+#define DRA7XX_PM_DSP2_PWRSTCTRL_OFFSET				0x0000
+#define DRA7XX_PM_DSP2_PWRSTST_OFFSET				0x0004
+#define DRA7XX_RM_DSP2_RSTCTRL_OFFSET				0x0010
+#define DRA7XX_RM_DSP2_RSTST_OFFSET				0x0014
+#define DRA7XX_RM_DSP2_DSP2_CONTEXT_OFFSET			0x0024
+
+/* PRM.EVE1_PRM register offsets */
+#define DRA7XX_PM_EVE1_PWRSTCTRL_OFFSET				0x0000
+#define DRA7XX_PM_EVE1_PWRSTST_OFFSET				0x0004
+#define DRA7XX_RM_EVE1_RSTCTRL_OFFSET				0x0010
+#define DRA7XX_RM_EVE1_RSTST_OFFSET				0x0014
+#define DRA7XX_PM_EVE1_EVE1_WKDEP_OFFSET			0x0020
+#define DRA7XX_RM_EVE1_EVE1_CONTEXT_OFFSET			0x0024
+
+/* PRM.EVE2_PRM register offsets */
+#define DRA7XX_PM_EVE2_PWRSTCTRL_OFFSET				0x0000
+#define DRA7XX_PM_EVE2_PWRSTST_OFFSET				0x0004
+#define DRA7XX_RM_EVE2_RSTCTRL_OFFSET				0x0010
+#define DRA7XX_RM_EVE2_RSTST_OFFSET				0x0014
+#define DRA7XX_PM_EVE2_EVE2_WKDEP_OFFSET			0x0020
+#define DRA7XX_RM_EVE2_EVE2_CONTEXT_OFFSET			0x0024
+
+/* PRM.EVE3_PRM register offsets */
+#define DRA7XX_PM_EVE3_PWRSTCTRL_OFFSET				0x0000
+#define DRA7XX_PM_EVE3_PWRSTST_OFFSET				0x0004
+#define DRA7XX_RM_EVE3_RSTCTRL_OFFSET				0x0010
+#define DRA7XX_RM_EVE3_RSTST_OFFSET				0x0014
+#define DRA7XX_PM_EVE3_EVE3_WKDEP_OFFSET			0x0020
+#define DRA7XX_RM_EVE3_EVE3_CONTEXT_OFFSET			0x0024
+
+/* PRM.EVE4_PRM register offsets */
+#define DRA7XX_PM_EVE4_PWRSTCTRL_OFFSET				0x0000
+#define DRA7XX_PM_EVE4_PWRSTST_OFFSET				0x0004
+#define DRA7XX_RM_EVE4_RSTCTRL_OFFSET				0x0010
+#define DRA7XX_RM_EVE4_RSTST_OFFSET				0x0014
+#define DRA7XX_PM_EVE4_EVE4_WKDEP_OFFSET			0x0020
+#define DRA7XX_RM_EVE4_EVE4_CONTEXT_OFFSET			0x0024
+
+/* PRM.RTC_PRM register offsets */
+#define DRA7XX_PM_RTC_RTCSS_WKDEP_OFFSET			0x0000
+#define DRA7XX_RM_RTC_RTCSS_CONTEXT_OFFSET			0x0004
+
+/* PRM.VPE_PRM register offsets */
+#define DRA7XX_PM_VPE_PWRSTCTRL_OFFSET				0x0000
+#define DRA7XX_PM_VPE_PWRSTST_OFFSET				0x0004
+#define DRA7XX_PM_VPE_VPE_WKDEP_OFFSET				0x0020
+#define DRA7XX_RM_VPE_VPE_CONTEXT_OFFSET			0x0024
+
+/* PRM.DEVICE_PRM register offsets */
+#define DRA7XX_PRM_RSTCTRL_OFFSET				0x0000
+#define DRA7XX_PRM_RSTST_OFFSET					0x0004
+#define DRA7XX_PRM_RSTTIME_OFFSET				0x0008
+#define DRA7XX_PRM_CLKREQCTRL_OFFSET				0x000c
+#define DRA7XX_PRM_VOLTCTRL_OFFSET				0x0010
+#define DRA7XX_PRM_PWRREQCTRL_OFFSET				0x0014
+#define DRA7XX_PRM_PSCON_COUNT_OFFSET				0x0018
+#define DRA7XX_PRM_IO_COUNT_OFFSET				0x001c
+#define DRA7XX_PRM_IO_PMCTRL_OFFSET				0x0020
+#define DRA7XX_PRM_VOLTSETUP_WARMRESET_OFFSET			0x0024
+#define DRA7XX_PRM_VOLTSETUP_CORE_OFF_OFFSET			0x0028
+#define DRA7XX_PRM_VOLTSETUP_MPU_OFF_OFFSET			0x002c
+#define DRA7XX_PRM_VOLTSETUP_MM_OFF_OFFSET			0x0030
+#define DRA7XX_PRM_VOLTSETUP_CORE_RET_SLEEP_OFFSET		0x0034
+#define DRA7XX_PRM_VOLTSETUP_MPU_RET_SLEEP_OFFSET		0x0038
+#define DRA7XX_PRM_VOLTSETUP_MM_RET_SLEEP_OFFSET		0x003c
+#define DRA7XX_PRM_SRAM_COUNT_OFFSET				0x00bc
+#define DRA7XX_PRM_SRAM_WKUP_SETUP_OFFSET			0x00c0
+#define DRA7XX_PRM_SLDO_CORE_SETUP_OFFSET			0x00c4
+#define DRA7XX_PRM_SLDO_CORE_CTRL_OFFSET			0x00c8
+#define DRA7XX_PRM_SLDO_MPU_SETUP_OFFSET			0x00cc
+#define DRA7XX_PRM_SLDO_MPU_CTRL_OFFSET				0x00d0
+#define DRA7XX_PRM_SLDO_GPU_SETUP_OFFSET			0x00d4
+#define DRA7XX_PRM_SLDO_GPU_CTRL_OFFSET				0x00d8
+#define DRA7XX_PRM_ABBLDO_MPU_SETUP_OFFSET			0x00dc
+#define DRA7XX_PRM_ABBLDO_MPU_CTRL_OFFSET			0x00e0
+#define DRA7XX_PRM_ABBLDO_GPU_SETUP_OFFSET			0x00e4
+#define DRA7XX_PRM_ABBLDO_GPU_CTRL_OFFSET			0x00e8
+#define DRA7XX_PRM_BANDGAP_SETUP_OFFSET				0x00ec
+#define DRA7XX_PRM_DEVICE_OFF_CTRL_OFFSET			0x00f0
+#define DRA7XX_PRM_PHASE1_CNDP_OFFSET				0x00f4
+#define DRA7XX_PRM_PHASE2A_CNDP_OFFSET				0x00f8
+#define DRA7XX_PRM_PHASE2B_CNDP_OFFSET				0x00fc
+#define DRA7XX_PRM_MODEM_IF_CTRL_OFFSET				0x0100
+#define DRA7XX_PRM_VOLTST_MPU_OFFSET				0x0110
+#define DRA7XX_PRM_VOLTST_MM_OFFSET				0x0114
+#define DRA7XX_PRM_SLDO_DSPEVE_SETUP_OFFSET			0x0118
+#define DRA7XX_PRM_SLDO_IVA_SETUP_OFFSET			0x011c
+#define DRA7XX_PRM_ABBLDO_DSPEVE_CTRL_OFFSET			0x0120
+#define DRA7XX_PRM_ABBLDO_IVA_CTRL_OFFSET			0x0124
+#define DRA7XX_PRM_SLDO_DSPEVE_CTRL_OFFSET			0x0128
+#define DRA7XX_PRM_SLDO_IVA_CTRL_OFFSET				0x012c
+#define DRA7XX_PRM_ABBLDO_DSPEVE_SETUP_OFFSET			0x0130
+#define DRA7XX_PRM_ABBLDO_IVA_SETUP_OFFSET			0x0134
+
+#endif
diff --git a/arch/arm/mach-omap2/prminst44xx.c b/arch/arm/mach-omap2/prminst44xx.c
index c12320c0ae95..6334b96b4097 100644
--- a/arch/arm/mach-omap2/prminst44xx.c
+++ b/arch/arm/mach-omap2/prminst44xx.c
@@ -20,10 +20,13 @@
 #include "common.h"
 #include "prcm-common.h"
 #include "prm44xx.h"
+#include "prm54xx.h"
+#include "prm7xx.h"
 #include "prminst44xx.h"
 #include "prm-regbits-44xx.h"
 #include "prcm44xx.h"
 #include "prcm_mpu44xx.h"
+#include "soc.h"
 
 static void __iomem *_prm_bases[OMAP4_MAX_PRCM_PARTITIONS];
 
@@ -165,10 +168,19 @@ int omap4_prminst_deassert_hardreset(u8 shift, u8 part, s16 inst,
 void omap4_prminst_global_warm_sw_reset(void)
 {
 	u32 v;
-
-	v = omap4_prminst_read_inst_reg(OMAP4430_PRM_PARTITION,
-				    OMAP4430_PRM_DEVICE_INST,
-				    OMAP4_PRM_RSTCTRL_OFFSET);
+	s16 dev_inst;
+
+	if (cpu_is_omap44xx())
+		dev_inst = OMAP4430_PRM_DEVICE_INST;
+	else if (soc_is_omap54xx())
+		dev_inst = OMAP54XX_PRM_DEVICE_INST;
+	else if (soc_is_dra7xx())
+		dev_inst = DRA7XX_PRM_DEVICE_INST;
+	else
+		return;
+
+	v = omap4_prminst_read_inst_reg(OMAP4430_PRM_PARTITION, dev_inst,
+					OMAP4_PRM_RSTCTRL_OFFSET);
 	v |= OMAP4430_RST_GLOBAL_WARM_SW_MASK;
 	omap4_prminst_write_inst_reg(v, OMAP4430_PRM_PARTITION,
 				 OMAP4430_PRM_DEVICE_INST,
diff --git a/arch/arm/mach-omap2/soc.h b/arch/arm/mach-omap2/soc.h
index 8c616e436bc7..4588df1447ed 100644
--- a/arch/arm/mach-omap2/soc.h
+++ b/arch/arm/mach-omap2/soc.h
@@ -8,6 +8,7 @@
  * Written by Tony Lindgren <tony.lindgren@nokia.com>
  *
  * Added OMAP4/5 specific defines - Santosh Shilimkar<santosh.shilimkar@ti.com>
+ * Added DRA7xxx specific defines - Sricharan R<r.sricharan@ti.com>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -35,6 +36,7 @@
 #ifndef __ASSEMBLY__
 
 #include <linux/bitops.h>
+#include <linux/of.h>
 
 /*
  * Test if multicore OMAP support is needed
@@ -105,6 +107,15 @@
 # endif
 #endif
 
+#ifdef CONFIG_SOC_DRA7XX
+# ifdef OMAP_NAME
+#  undef MULTI_OMAP2
+#  define MULTI_OMAP2
+# else
+#  define OMAP_NAME DRA7XX
+# endif
+#endif
+
 /*
  * Omap device type i.e. EMU/HS/TST/GP/BAD
  */
@@ -233,6 +244,7 @@ IS_AM_SUBCLASS(437x, 0x437)
 #define cpu_is_omap447x()		0
 #define soc_is_omap54xx()		0
 #define soc_is_omap543x()		0
+#define soc_is_dra7xx()			0
 
 #if defined(MULTI_OMAP2)
 # if defined(CONFIG_ARCH_OMAP2)
@@ -379,6 +391,11 @@ IS_OMAP_TYPE(3430, 0x3430)
 # define soc_is_omap543x()		is_omap543x()
 #endif
 
+#if defined(CONFIG_SOC_DRA7XX)
+#undef soc_is_dra7xx
+#define soc_is_dra7xx()	(of_machine_is_compatible("ti,dra7"))
+#endif
+
 /* Various silicon revisions for omap2 */
 #define OMAP242X_CLASS		0x24200024
 #define OMAP2420_REV_ES1_0	OMAP242X_CLASS
diff --git a/arch/arm/mach-omap2/timer.c b/arch/arm/mach-omap2/timer.c
index b37e1fcbad56..ead48fa5715e 100644
--- a/arch/arm/mach-omap2/timer.c
+++ b/arch/arm/mach-omap2/timer.c
@@ -537,7 +537,7 @@ static void __init realtime_counter_init(void)
 	reg |= num;
 	__raw_writel(reg, base + INCREMENTER_NUMERATOR_OFFSET);
 
-	reg = __raw_readl(base + INCREMENTER_NUMERATOR_OFFSET) &
+	reg = __raw_readl(base + INCREMENTER_DENUMERATOR_RELOAD_OFFSET) &
 			NUMERATOR_DENUMERATOR_MASK;
 	reg |= den;
 	__raw_writel(reg, base + INCREMENTER_DENUMERATOR_RELOAD_OFFSET);
@@ -594,13 +594,14 @@ OMAP_SYS_GP_TIMER_INIT(3, 2, "timer_sys_ck", NULL,
 		       1, "timer_sys_ck", "ti,timer-alwon");
 #endif
 
-#if defined(CONFIG_ARCH_OMAP4) || defined(CONFIG_SOC_OMAP5)
+#if defined(CONFIG_ARCH_OMAP4) || defined(CONFIG_SOC_OMAP5) || \
+	defined(CONFIG_SOC_DRA7XX)
 static OMAP_SYS_32K_TIMER_INIT(4, 1, "timer_32k_ck", "ti,timer-alwon",
 			       2, "sys_clkin_ck", NULL);
 #endif
 
 #ifdef CONFIG_ARCH_OMAP4
-#ifdef CONFIG_LOCAL_TIMERS
+#ifdef CONFIG_HAVE_ARM_TWD
 static DEFINE_TWD_LOCAL_TIMER(twd_local_timer, OMAP44XX_LOCAL_TWD_BASE, 29);
 void __init omap4_local_timer_init(void)
 {
@@ -619,15 +620,15 @@ void __init omap4_local_timer_init(void)
 			pr_err("twd_local_timer_register failed %d\n", err);
 	}
 }
-#else /* CONFIG_LOCAL_TIMERS */
+#else
 void __init omap4_local_timer_init(void)
 {
 	omap4_sync32k_timer_init();
 }
-#endif /* CONFIG_LOCAL_TIMERS */
+#endif /* CONFIG_HAVE_ARM_TWD */
 #endif /* CONFIG_ARCH_OMAP4 */
 
-#ifdef CONFIG_SOC_OMAP5
+#if defined(CONFIG_SOC_OMAP5) || defined(CONFIG_SOC_DRA7XX)
 void __init omap5_realtime_timer_init(void)
 {
 	omap4_sync32k_timer_init();
@@ -635,7 +636,7 @@ void __init omap5_realtime_timer_init(void)
 
 	clocksource_of_init();
 }
-#endif /* CONFIG_SOC_OMAP5 */
+#endif /* CONFIG_SOC_OMAP5 || CONFIG_SOC_DRA7XX */
 
 /**
  * omap_timer_init - build and register timer device with an
diff --git a/arch/arm/mach-omap2/usb-host.c b/arch/arm/mach-omap2/usb-host.c
index 2eb19d4d0aa1..e83a6a4b184a 100644
--- a/arch/arm/mach-omap2/usb-host.c
+++ b/arch/arm/mach-omap2/usb-host.c
@@ -28,7 +28,7 @@
 #include <linux/io.h>
 #include <linux/gpio.h>
 #include <linux/usb/phy.h>
-#include <linux/usb/nop-usb-xceiv.h>
+#include <linux/usb/usb_phy_gen_xceiv.h>
 
 #include "soc.h"
 #include "omap_device.h"
@@ -349,7 +349,7 @@ static struct fixed_voltage_config hsusb_reg_config = {
 	/* .init_data filled later */
 };
 
-static const char *nop_name = "nop_usb_xceiv"; /* NOP PHY driver */
+static const char *nop_name = "usb_phy_gen_xceiv"; /* NOP PHY driver */
 static const char *reg_name = "reg-fixed-voltage"; /* Regulator driver */
 
 /**
@@ -460,9 +460,9 @@ int usbhs_init_phys(struct usbhs_phy_data *phy, int num_phys)
 		pdevinfo.name = nop_name;
 		pdevinfo.id = phy->port;
 		pdevinfo.data = phy->platform_data;
-		pdevinfo.size_data = sizeof(struct nop_usb_xceiv_platform_data);
-
-		scnprintf(phy_id, MAX_STR, "nop_usb_xceiv.%d",
+		pdevinfo.size_data =
+			sizeof(struct usb_phy_gen_xceiv_platform_data);
+		scnprintf(phy_id, MAX_STR, "usb_phy_gen_xceiv.%d",
 					phy->port);
 		pdev = platform_device_register_full(&pdevinfo);
 		if (IS_ERR(pdev)) {
diff --git a/arch/arm/mach-orion5x/common.c b/arch/arm/mach-orion5x/common.c
index b41599f98a8e..91a5852b44f3 100644
--- a/arch/arm/mach-orion5x/common.c
+++ b/arch/arm/mach-orion5x/common.c
@@ -174,8 +174,10 @@ void __init orion5x_xor_init(void)
  ****************************************************************************/
 static void __init orion5x_crypto_init(void)
 {
-	mvebu_mbus_add_window("sram", ORION5X_SRAM_PHYS_BASE,
-			      ORION5X_SRAM_SIZE);
+	mvebu_mbus_add_window_by_id(ORION_MBUS_SRAM_TARGET,
+				    ORION_MBUS_SRAM_ATTR,
+				    ORION5X_SRAM_PHYS_BASE,
+				    ORION5X_SRAM_SIZE);
 	orion_crypto_init(ORION5X_CRYPTO_PHYS_BASE, ORION5X_SRAM_PHYS_BASE,
 			  SZ_8K, IRQ_ORION5X_CESA);
 }
@@ -222,22 +224,24 @@ void orion5x_setup_wins(void)
 	 * The PCIe windows will no longer be statically allocated
 	 * here once Orion5x is migrated to the pci-mvebu driver.
 	 */
-	mvebu_mbus_add_window_remap_flags("pcie0.0", ORION5X_PCIE_IO_PHYS_BASE,
+	mvebu_mbus_add_window_remap_by_id(ORION_MBUS_PCIE_IO_TARGET,
+					  ORION_MBUS_PCIE_IO_ATTR,
+					  ORION5X_PCIE_IO_PHYS_BASE,
 					  ORION5X_PCIE_IO_SIZE,
-					  ORION5X_PCIE_IO_BUS_BASE,
-					  MVEBU_MBUS_PCI_IO);
-	mvebu_mbus_add_window_remap_flags("pcie0.0", ORION5X_PCIE_MEM_PHYS_BASE,
-					  ORION5X_PCIE_MEM_SIZE,
-					  MVEBU_MBUS_NO_REMAP,
-					  MVEBU_MBUS_PCI_MEM);
-	mvebu_mbus_add_window_remap_flags("pci0.0", ORION5X_PCI_IO_PHYS_BASE,
+					  ORION5X_PCIE_IO_BUS_BASE);
+	mvebu_mbus_add_window_by_id(ORION_MBUS_PCIE_MEM_TARGET,
+				    ORION_MBUS_PCIE_MEM_ATTR,
+				    ORION5X_PCIE_MEM_PHYS_BASE,
+				    ORION5X_PCIE_MEM_SIZE);
+	mvebu_mbus_add_window_remap_by_id(ORION_MBUS_PCI_IO_TARGET,
+					  ORION_MBUS_PCI_IO_ATTR,
+					  ORION5X_PCI_IO_PHYS_BASE,
 					  ORION5X_PCI_IO_SIZE,
-					  ORION5X_PCI_IO_BUS_BASE,
-					  MVEBU_MBUS_PCI_IO);
-	mvebu_mbus_add_window_remap_flags("pci0.0", ORION5X_PCI_MEM_PHYS_BASE,
-					  ORION5X_PCI_MEM_SIZE,
-					  MVEBU_MBUS_NO_REMAP,
-					  MVEBU_MBUS_PCI_MEM);
+					  ORION5X_PCI_IO_BUS_BASE);
+	mvebu_mbus_add_window_by_id(ORION_MBUS_PCI_MEM_TARGET,
+				    ORION_MBUS_PCI_MEM_ATTR,
+				    ORION5X_PCI_MEM_PHYS_BASE,
+				    ORION5X_PCI_MEM_SIZE);
 }
 
 int orion5x_tclk;
diff --git a/arch/arm/mach-orion5x/common.h b/arch/arm/mach-orion5x/common.h
index a909afb384fb..f565f9944af2 100644
--- a/arch/arm/mach-orion5x/common.h
+++ b/arch/arm/mach-orion5x/common.h
@@ -7,6 +7,23 @@ struct dsa_platform_data;
 struct mv643xx_eth_platform_data;
 struct mv_sata_platform_data;
 
+#define ORION_MBUS_PCIE_MEM_TARGET    0x04
+#define ORION_MBUS_PCIE_MEM_ATTR      0x59
+#define ORION_MBUS_PCIE_IO_TARGET     0x04
+#define ORION_MBUS_PCIE_IO_ATTR       0x51
+#define ORION_MBUS_PCIE_WA_TARGET     0x04
+#define ORION_MBUS_PCIE_WA_ATTR       0x79
+#define ORION_MBUS_PCI_MEM_TARGET     0x03
+#define ORION_MBUS_PCI_MEM_ATTR       0x59
+#define ORION_MBUS_PCI_IO_TARGET      0x03
+#define ORION_MBUS_PCI_IO_ATTR        0x51
+#define ORION_MBUS_DEVBUS_BOOT_TARGET 0x01
+#define ORION_MBUS_DEVBUS_BOOT_ATTR   0x0f
+#define ORION_MBUS_DEVBUS_TARGET(cs)  0x01
+#define ORION_MBUS_DEVBUS_ATTR(cs)    (~(1 << cs))
+#define ORION_MBUS_SRAM_TARGET        0x00
+#define ORION_MBUS_SRAM_ATTR          0x00
+
 /*
  * Basic Orion init functions used early by machine-setup.
  */
diff --git a/arch/arm/mach-orion5x/d2net-setup.c b/arch/arm/mach-orion5x/d2net-setup.c
index 16c88bbabc98..8f68b745c1d5 100644
--- a/arch/arm/mach-orion5x/d2net-setup.c
+++ b/arch/arm/mach-orion5x/d2net-setup.c
@@ -317,8 +317,10 @@ static void __init d2net_init(void)
 	d2net_sata_power_init();
 	orion5x_sata_init(&d2net_sata_data);
 
-	mvebu_mbus_add_window("devbus-boot", D2NET_NOR_BOOT_BASE,
-			      D2NET_NOR_BOOT_SIZE);
+	mvebu_mbus_add_window_by_id(ORION_MBUS_DEVBUS_BOOT_TARGET,
+				    ORION_MBUS_DEVBUS_BOOT_ATTR,
+				    D2NET_NOR_BOOT_BASE,
+				    D2NET_NOR_BOOT_SIZE);
 	platform_device_register(&d2net_nor_flash);
 
 	platform_device_register(&d2net_gpio_buttons);
diff --git a/arch/arm/mach-orion5x/db88f5281-setup.c b/arch/arm/mach-orion5x/db88f5281-setup.c
index 4e1263da38bb..4b2aefd1d961 100644
--- a/arch/arm/mach-orion5x/db88f5281-setup.c
+++ b/arch/arm/mach-orion5x/db88f5281-setup.c
@@ -340,19 +340,27 @@ static void __init db88f5281_init(void)
 	orion5x_uart0_init();
 	orion5x_uart1_init();
 
-	mvebu_mbus_add_window("devbus-boot", DB88F5281_NOR_BOOT_BASE,
-			      DB88F5281_NOR_BOOT_SIZE);
+	mvebu_mbus_add_window_by_id(ORION_MBUS_DEVBUS_BOOT_TARGET,
+				    ORION_MBUS_DEVBUS_BOOT_ATTR,
+				    DB88F5281_NOR_BOOT_BASE,
+				    DB88F5281_NOR_BOOT_SIZE);
 	platform_device_register(&db88f5281_boot_flash);
 
-	mvebu_mbus_add_window("devbus-cs0", DB88F5281_7SEG_BASE,
-			      DB88F5281_7SEG_SIZE);
+	mvebu_mbus_add_window_by_id(ORION_MBUS_DEVBUS_TARGET(0),
+				    ORION_MBUS_DEVBUS_ATTR(0),
+				    DB88F5281_7SEG_BASE,
+				    DB88F5281_7SEG_SIZE);
 
-	mvebu_mbus_add_window("devbus-cs1", DB88F5281_NOR_BASE,
-			      DB88F5281_NOR_SIZE);
+	mvebu_mbus_add_window_by_id(ORION_MBUS_DEVBUS_TARGET(1),
+				    ORION_MBUS_DEVBUS_ATTR(1),
+				    DB88F5281_NOR_BASE,
+				    DB88F5281_NOR_SIZE);
 	platform_device_register(&db88f5281_nor_flash);
 
-	mvebu_mbus_add_window("devbus-cs2", DB88F5281_NAND_BASE,
-			      DB88F5281_NAND_SIZE);
+	mvebu_mbus_add_window_by_id(ORION_MBUS_DEVBUS_TARGET(2),
+				    ORION_MBUS_DEVBUS_ATTR(2),
+				    DB88F5281_NAND_BASE,
+				    DB88F5281_NAND_SIZE);
 	platform_device_register(&db88f5281_nand_flash);
 
 	i2c_register_board_info(0, &db88f5281_i2c_rtc, 1);
diff --git a/arch/arm/mach-orion5x/dns323-setup.c b/arch/arm/mach-orion5x/dns323-setup.c
index 9e6baf581ed3..70974732cbf0 100644
--- a/arch/arm/mach-orion5x/dns323-setup.c
+++ b/arch/arm/mach-orion5x/dns323-setup.c
@@ -611,8 +611,10 @@ static void __init dns323_init(void)
 	/* setup flash mapping
 	 * CS3 holds a 8 MB Spansion S29GL064M90TFIR4
 	 */
-	mvebu_mbus_add_window("devbus-boot", DNS323_NOR_BOOT_BASE,
-			      DNS323_NOR_BOOT_SIZE);
+	mvebu_mbus_add_window_by_id(ORION_MBUS_DEVBUS_BOOT_TARGET,
+				    ORION_MBUS_DEVBUS_BOOT_ATTR,
+				    DNS323_NOR_BOOT_BASE,
+				    DNS323_NOR_BOOT_SIZE);
 	platform_device_register(&dns323_nor_flash);
 
 	/* Sort out LEDs, Buttons and i2c devices */
diff --git a/arch/arm/mach-orion5x/edmini_v2-setup.c b/arch/arm/mach-orion5x/edmini_v2-setup.c
index 147615510dd0..f66c1b2ee8c1 100644
--- a/arch/arm/mach-orion5x/edmini_v2-setup.c
+++ b/arch/arm/mach-orion5x/edmini_v2-setup.c
@@ -23,8 +23,8 @@
 #include <linux/platform_device.h>
 #include <linux/pci.h>
 #include <linux/irq.h>
+#include <linux/mbus.h>
 #include <linux/mtd/physmap.h>
-#include <linux/mv643xx_eth.h>
 #include <linux/leds.h>
 #include <linux/gpio_keys.h>
 #include <linux/input.h>
@@ -96,14 +96,6 @@ static struct platform_device edmini_v2_nor_flash = {
 };
 
 /*****************************************************************************
- * Ethernet
- ****************************************************************************/
-
-static struct mv643xx_eth_platform_data edmini_v2_eth_data = {
-	.phy_addr	= 8,
-};
-
-/*****************************************************************************
  * RTC 5C372a on I2C bus
  ****************************************************************************/
 
@@ -152,10 +144,11 @@ void __init edmini_v2_init(void)
 	 * Configure peripherals.
 	 */
 	orion5x_ehci0_init();
-	orion5x_eth_init(&edmini_v2_eth_data);
 
-	mvebu_mbus_add_window("devbus-boot", EDMINI_V2_NOR_BOOT_BASE,
-			      EDMINI_V2_NOR_BOOT_SIZE);
+	mvebu_mbus_add_window_by_id(ORION_MBUS_DEVBUS_BOOT_TARGET,
+				    ORION_MBUS_DEVBUS_BOOT_ATTR,
+				    EDMINI_V2_NOR_BOOT_BASE,
+				    EDMINI_V2_NOR_BOOT_SIZE);
 	platform_device_register(&edmini_v2_nor_flash);
 
 	pr_notice("edmini_v2: USB device port, flash write and power-off "
diff --git a/arch/arm/mach-orion5x/include/mach/debug-macro.S b/arch/arm/mach-orion5x/include/mach/debug-macro.S
deleted file mode 100644
index f340ed8f8dd0..000000000000
--- a/arch/arm/mach-orion5x/include/mach/debug-macro.S
+++ /dev/null
@@ -1,21 +0,0 @@
-/*
- * arch/arm/mach-orion5x/include/mach/debug-macro.S
- *
- * Debugging macro include header
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
-
-#include <mach/orion5x.h>
-
-	.macro  addruart, rp, rv, tmp
-	ldr	\rp, =ORION5X_REGS_PHYS_BASE
-	ldr	\rv, =ORION5X_REGS_VIRT_BASE
-	orr	\rp, \rp, #0x00012000
-	orr	\rv, \rv, #0x00012000
-	.endm
-
-#define UART_SHIFT	2
-#include <asm/hardware/debug-8250.S>
diff --git a/arch/arm/mach-orion5x/kurobox_pro-setup.c b/arch/arm/mach-orion5x/kurobox_pro-setup.c
index aae10e4a917c..fe6a48a325e8 100644
--- a/arch/arm/mach-orion5x/kurobox_pro-setup.c
+++ b/arch/arm/mach-orion5x/kurobox_pro-setup.c
@@ -359,13 +359,17 @@ static void __init kurobox_pro_init(void)
 	orion5x_uart1_init();
 	orion5x_xor_init();
 
-	mvebu_mbus_add_window("devbus-boot", KUROBOX_PRO_NOR_BOOT_BASE,
-			      KUROBOX_PRO_NOR_BOOT_SIZE);
+	mvebu_mbus_add_window_by_id(ORION_MBUS_DEVBUS_BOOT_TARGET,
+				    ORION_MBUS_DEVBUS_BOOT_ATTR,
+				    KUROBOX_PRO_NOR_BOOT_BASE,
+				    KUROBOX_PRO_NOR_BOOT_SIZE);
 	platform_device_register(&kurobox_pro_nor_flash);
 
 	if (machine_is_kurobox_pro()) {
-		mvebu_mbus_add_window("devbus-cs0", KUROBOX_PRO_NAND_BASE,
-				      KUROBOX_PRO_NAND_SIZE);
+		mvebu_mbus_add_window_by_id(ORION_MBUS_DEVBUS_TARGET(0),
+					    ORION_MBUS_DEVBUS_ATTR(0),
+					    KUROBOX_PRO_NAND_BASE,
+					    KUROBOX_PRO_NAND_SIZE);
 		platform_device_register(&kurobox_pro_nand_flash);
 	}
 
diff --git a/arch/arm/mach-orion5x/ls-chl-setup.c b/arch/arm/mach-orion5x/ls-chl-setup.c
index 6234977b5aea..028ea038d404 100644
--- a/arch/arm/mach-orion5x/ls-chl-setup.c
+++ b/arch/arm/mach-orion5x/ls-chl-setup.c
@@ -294,8 +294,10 @@ static void __init lschl_init(void)
 	orion5x_uart0_init();
 	orion5x_xor_init();
 
-	mvebu_mbus_add_window("devbus-boot", LSCHL_NOR_BOOT_BASE,
-			      LSCHL_NOR_BOOT_SIZE);
+	mvebu_mbus_add_window_by_id(ORION_MBUS_DEVBUS_BOOT_TARGET,
+				    ORION_MBUS_DEVBUS_BOOT_ATTR,
+				    LSCHL_NOR_BOOT_BASE,
+				    LSCHL_NOR_BOOT_SIZE);
 	platform_device_register(&lschl_nor_flash);
 
 	platform_device_register(&lschl_leds);
diff --git a/arch/arm/mach-orion5x/ls_hgl-setup.c b/arch/arm/mach-orion5x/ls_hgl-setup.c
index fe04c4b64569..32b7129b767d 100644
--- a/arch/arm/mach-orion5x/ls_hgl-setup.c
+++ b/arch/arm/mach-orion5x/ls_hgl-setup.c
@@ -243,8 +243,10 @@ static void __init ls_hgl_init(void)
 	orion5x_uart0_init();
 	orion5x_xor_init();
 
-	mvebu_mbus_add_window("devbus-boot", LS_HGL_NOR_BOOT_BASE,
-			      LS_HGL_NOR_BOOT_SIZE);
+	mvebu_mbus_add_window_by_id(ORION_MBUS_DEVBUS_BOOT_TARGET,
+				    ORION_MBUS_DEVBUS_BOOT_ATTR,
+				    LS_HGL_NOR_BOOT_BASE,
+				    LS_HGL_NOR_BOOT_SIZE);
 	platform_device_register(&ls_hgl_nor_flash);
 
 	platform_device_register(&ls_hgl_button_device);
diff --git a/arch/arm/mach-orion5x/lsmini-setup.c b/arch/arm/mach-orion5x/lsmini-setup.c
index ca4dbe973daf..a6493e76f96d 100644
--- a/arch/arm/mach-orion5x/lsmini-setup.c
+++ b/arch/arm/mach-orion5x/lsmini-setup.c
@@ -244,8 +244,10 @@ static void __init lsmini_init(void)
 	orion5x_uart0_init();
 	orion5x_xor_init();
 
-	mvebu_mbus_add_window("devbus-boot", LSMINI_NOR_BOOT_BASE,
-			      LSMINI_NOR_BOOT_SIZE);
+	mvebu_mbus_add_window_by_id(ORION_MBUS_DEVBUS_BOOT_TARGET,
+				    ORION_MBUS_DEVBUS_BOOT_ATTR,
+				    LSMINI_NOR_BOOT_BASE,
+				    LSMINI_NOR_BOOT_SIZE);
 	platform_device_register(&lsmini_nor_flash);
 
 	platform_device_register(&lsmini_button_device);
diff --git a/arch/arm/mach-orion5x/mss2-setup.c b/arch/arm/mach-orion5x/mss2-setup.c
index 827acbafc9dc..e105130ba51c 100644
--- a/arch/arm/mach-orion5x/mss2-setup.c
+++ b/arch/arm/mach-orion5x/mss2-setup.c
@@ -241,8 +241,10 @@ static void __init mss2_init(void)
 	orion5x_uart0_init();
 	orion5x_xor_init();
 
-	mvebu_mbus_add_window("devbus-boot", MSS2_NOR_BOOT_BASE,
-			      MSS2_NOR_BOOT_SIZE);
+	mvebu_mbus_add_window_by_id(ORION_MBUS_DEVBUS_BOOT_TARGET,
+				    ORION_MBUS_DEVBUS_BOOT_ATTR,
+				    MSS2_NOR_BOOT_BASE,
+				    MSS2_NOR_BOOT_SIZE);
 	platform_device_register(&mss2_nor_flash);
 
 	platform_device_register(&mss2_button_device);
diff --git a/arch/arm/mach-orion5x/mv2120-setup.c b/arch/arm/mach-orion5x/mv2120-setup.c
index 92600ae2b4b6..e032f01da49e 100644
--- a/arch/arm/mach-orion5x/mv2120-setup.c
+++ b/arch/arm/mach-orion5x/mv2120-setup.c
@@ -204,8 +204,10 @@ static void __init mv2120_init(void)
 	orion5x_uart0_init();
 	orion5x_xor_init();
 
-	mvebu_mbus_add_window("devbus-boot", MV2120_NOR_BOOT_BASE,
-			      MV2120_NOR_BOOT_SIZE);
+	mvebu_mbus_add_window_by_id(ORION_MBUS_DEVBUS_BOOT_TARGET,
+				    ORION_MBUS_DEVBUS_BOOT_ATTR,
+				    MV2120_NOR_BOOT_BASE,
+				    MV2120_NOR_BOOT_SIZE);
 	platform_device_register(&mv2120_nor_flash);
 
 	platform_device_register(&mv2120_button_device);
diff --git a/arch/arm/mach-orion5x/net2big-setup.c b/arch/arm/mach-orion5x/net2big-setup.c
index dd0641a0d074..ba73dc7ffb9e 100644
--- a/arch/arm/mach-orion5x/net2big-setup.c
+++ b/arch/arm/mach-orion5x/net2big-setup.c
@@ -397,8 +397,10 @@ static void __init net2big_init(void)
 	net2big_sata_power_init();
 	orion5x_sata_init(&net2big_sata_data);
 
-	mvebu_mbus_add_window("devbus-boot", NET2BIG_NOR_BOOT_BASE,
-			      NET2BIG_NOR_BOOT_SIZE);
+	mvebu_mbus_add_window_by_id(ORION_MBUS_DEVBUS_BOOT_TARGET,
+				    ORION_MBUS_DEVBUS_BOOT_ATTR,
+				    NET2BIG_NOR_BOOT_BASE,
+				    NET2BIG_NOR_BOOT_SIZE);
 	platform_device_register(&net2big_nor_flash);
 
 	platform_device_register(&net2big_gpio_buttons);
diff --git a/arch/arm/mach-orion5x/pci.c b/arch/arm/mach-orion5x/pci.c
index 503368023bb1..7fab67053030 100644
--- a/arch/arm/mach-orion5x/pci.c
+++ b/arch/arm/mach-orion5x/pci.c
@@ -157,11 +157,10 @@ static int __init pcie_setup(struct pci_sys_data *sys)
 	if (dev == MV88F5181_DEV_ID || dev == MV88F5182_DEV_ID) {
 		printk(KERN_NOTICE "Applying Orion-1/Orion-NAS PCIe config "
 				   "read transaction workaround\n");
-		mvebu_mbus_add_window_remap_flags("pcie0.0",
-						  ORION5X_PCIE_WA_PHYS_BASE,
-						  ORION5X_PCIE_WA_SIZE,
-						  MVEBU_MBUS_NO_REMAP,
-						  MVEBU_MBUS_PCI_WA);
+		mvebu_mbus_add_window_by_id(ORION_MBUS_PCIE_WA_TARGET,
+					    ORION_MBUS_PCIE_WA_ATTR,
+					    ORION5X_PCIE_WA_PHYS_BASE,
+					    ORION5X_PCIE_WA_SIZE);
 		pcie_ops.read = pcie_rd_conf_wa;
 	}
 
diff --git a/arch/arm/mach-orion5x/rd88f5181l-fxo-setup.c b/arch/arm/mach-orion5x/rd88f5181l-fxo-setup.c
index 1c4498bf650a..213b3e143c57 100644
--- a/arch/arm/mach-orion5x/rd88f5181l-fxo-setup.c
+++ b/arch/arm/mach-orion5x/rd88f5181l-fxo-setup.c
@@ -123,8 +123,10 @@ static void __init rd88f5181l_fxo_init(void)
 	orion5x_eth_switch_init(&rd88f5181l_fxo_switch_plat_data, NO_IRQ);
 	orion5x_uart0_init();
 
-	mvebu_mbus_add_window("devbus-boot", RD88F5181L_FXO_NOR_BOOT_BASE,
-			      RD88F5181L_FXO_NOR_BOOT_SIZE);
+	mvebu_mbus_add_window_by_id(ORION_MBUS_DEVBUS_BOOT_TARGET,
+				    ORION_MBUS_DEVBUS_BOOT_ATTR,
+				    RD88F5181L_FXO_NOR_BOOT_BASE,
+				    RD88F5181L_FXO_NOR_BOOT_SIZE);
 	platform_device_register(&rd88f5181l_fxo_nor_boot_flash);
 }
 
diff --git a/arch/arm/mach-orion5x/rd88f5181l-ge-setup.c b/arch/arm/mach-orion5x/rd88f5181l-ge-setup.c
index adabe34c4fc6..594800e1d691 100644
--- a/arch/arm/mach-orion5x/rd88f5181l-ge-setup.c
+++ b/arch/arm/mach-orion5x/rd88f5181l-ge-setup.c
@@ -130,8 +130,10 @@ static void __init rd88f5181l_ge_init(void)
 	orion5x_i2c_init();
 	orion5x_uart0_init();
 
-	mvebu_mbus_add_window("devbus-boot", RD88F5181L_GE_NOR_BOOT_BASE,
-			      RD88F5181L_GE_NOR_BOOT_SIZE);
+	mvebu_mbus_add_window_by_id(ORION_MBUS_DEVBUS_BOOT_TARGET,
+				    ORION_MBUS_DEVBUS_BOOT_ATTR,
+				    RD88F5181L_GE_NOR_BOOT_BASE,
+				    RD88F5181L_GE_NOR_BOOT_SIZE);
 	platform_device_register(&rd88f5181l_ge_nor_boot_flash);
 
 	i2c_register_board_info(0, &rd88f5181l_ge_i2c_rtc, 1);
diff --git a/arch/arm/mach-orion5x/rd88f5182-setup.c b/arch/arm/mach-orion5x/rd88f5182-setup.c
index 66e77ec91532..b1cf68493ffc 100644
--- a/arch/arm/mach-orion5x/rd88f5182-setup.c
+++ b/arch/arm/mach-orion5x/rd88f5182-setup.c
@@ -264,11 +264,14 @@ static void __init rd88f5182_init(void)
 	orion5x_uart0_init();
 	orion5x_xor_init();
 
-	mvebu_mbus_add_window("devbus-boot", RD88F5182_NOR_BOOT_BASE,
-			      RD88F5182_NOR_BOOT_SIZE);
-
-	mvebu_mbus_add_window("devbus-cs1", RD88F5182_NOR_BASE,
-			      RD88F5182_NOR_SIZE);
+	mvebu_mbus_add_window_by_id(ORION_MBUS_DEVBUS_BOOT_TARGET,
+				    ORION_MBUS_DEVBUS_BOOT_ATTR,
+				    RD88F5182_NOR_BOOT_BASE,
+				    RD88F5182_NOR_BOOT_SIZE);
+	mvebu_mbus_add_window_by_id(ORION_MBUS_DEVBUS_TARGET(1),
+				    ORION_MBUS_DEVBUS_ATTR(1),
+				    RD88F5182_NOR_BASE,
+				    RD88F5182_NOR_SIZE);
 	platform_device_register(&rd88f5182_nor_flash);
 	platform_device_register(&rd88f5182_gpio_leds);
 
diff --git a/arch/arm/mach-orion5x/terastation_pro2-setup.c b/arch/arm/mach-orion5x/terastation_pro2-setup.c
index a0bfa53e7556..7e9064844698 100644
--- a/arch/arm/mach-orion5x/terastation_pro2-setup.c
+++ b/arch/arm/mach-orion5x/terastation_pro2-setup.c
@@ -329,8 +329,10 @@ static void __init tsp2_init(void)
 	/*
 	 * Configure peripherals.
 	 */
-	mvebu_mbus_add_window("devbus-boot", TSP2_NOR_BOOT_BASE,
-			      TSP2_NOR_BOOT_SIZE);
+	mvebu_mbus_add_window_by_id(ORION_MBUS_DEVBUS_BOOT_TARGET,
+				    ORION_MBUS_DEVBUS_BOOT_ATTR,
+				    TSP2_NOR_BOOT_BASE,
+				    TSP2_NOR_BOOT_SIZE);
 	platform_device_register(&tsp2_nor_flash);
 
 	orion5x_ehci0_init();
diff --git a/arch/arm/mach-orion5x/ts209-setup.c b/arch/arm/mach-orion5x/ts209-setup.c
index 80174f0f168e..e90c0618fdad 100644
--- a/arch/arm/mach-orion5x/ts209-setup.c
+++ b/arch/arm/mach-orion5x/ts209-setup.c
@@ -286,8 +286,10 @@ static void __init qnap_ts209_init(void)
 	/*
 	 * Configure peripherals.
 	 */
-	mvebu_mbus_add_window("devbus-boot", QNAP_TS209_NOR_BOOT_BASE,
-			      QNAP_TS209_NOR_BOOT_SIZE);
+	mvebu_mbus_add_window_by_id(ORION_MBUS_DEVBUS_BOOT_TARGET,
+				    ORION_MBUS_DEVBUS_BOOT_ATTR,
+				    QNAP_TS209_NOR_BOOT_BASE,
+				    QNAP_TS209_NOR_BOOT_SIZE);
 	platform_device_register(&qnap_ts209_nor_flash);
 
 	orion5x_ehci0_init();
diff --git a/arch/arm/mach-orion5x/ts409-setup.c b/arch/arm/mach-orion5x/ts409-setup.c
index 92592790d6da..5c079d312015 100644
--- a/arch/arm/mach-orion5x/ts409-setup.c
+++ b/arch/arm/mach-orion5x/ts409-setup.c
@@ -277,8 +277,10 @@ static void __init qnap_ts409_init(void)
 	/*
 	 * Configure peripherals.
 	 */
-	mvebu_mbus_add_window("devbus-boot", QNAP_TS409_NOR_BOOT_BASE,
-			      QNAP_TS409_NOR_BOOT_SIZE);
+	mvebu_mbus_add_window_by_id(ORION_MBUS_DEVBUS_BOOT_TARGET,
+				    ORION_MBUS_DEVBUS_BOOT_ATTR,
+				    QNAP_TS409_NOR_BOOT_BASE,
+				    QNAP_TS409_NOR_BOOT_SIZE);
 	platform_device_register(&qnap_ts409_nor_flash);
 
 	orion5x_ehci0_init();
diff --git a/arch/arm/mach-orion5x/wnr854t-setup.c b/arch/arm/mach-orion5x/wnr854t-setup.c
index 6b84863c018d..80a56ee245b3 100644
--- a/arch/arm/mach-orion5x/wnr854t-setup.c
+++ b/arch/arm/mach-orion5x/wnr854t-setup.c
@@ -127,8 +127,10 @@ static void __init wnr854t_init(void)
 	orion5x_eth_switch_init(&wnr854t_switch_plat_data, NO_IRQ);
 	orion5x_uart0_init();
 
-	mvebu_mbus_add_window("devbus-boot", WNR854T_NOR_BOOT_BASE,
-			      WNR854T_NOR_BOOT_SIZE);
+	mvebu_mbus_add_window_by_id(ORION_MBUS_DEVBUS_BOOT_TARGET,
+				    ORION_MBUS_DEVBUS_BOOT_ATTR,
+				    WNR854T_NOR_BOOT_BASE,
+				    WNR854T_NOR_BOOT_SIZE);
 	platform_device_register(&wnr854t_nor_flash);
 }
 
diff --git a/arch/arm/mach-orion5x/wrt350n-v2-setup.c b/arch/arm/mach-orion5x/wrt350n-v2-setup.c
index fae684bc54f2..670e30dc0d1b 100644
--- a/arch/arm/mach-orion5x/wrt350n-v2-setup.c
+++ b/arch/arm/mach-orion5x/wrt350n-v2-setup.c
@@ -213,8 +213,10 @@ static void __init wrt350n_v2_init(void)
 	orion5x_eth_switch_init(&wrt350n_v2_switch_plat_data, NO_IRQ);
 	orion5x_uart0_init();
 
-	mvebu_mbus_add_window("devbus-boot", WRT350N_V2_NOR_BOOT_BASE,
-			      WRT350N_V2_NOR_BOOT_SIZE);
+	mvebu_mbus_add_window_by_id(ORION_MBUS_DEVBUS_BOOT_TARGET,
+				    ORION_MBUS_DEVBUS_BOOT_ATTR,
+				    WRT350N_V2_NOR_BOOT_BASE,
+				    WRT350N_V2_NOR_BOOT_SIZE);
 	platform_device_register(&wrt350n_v2_nor_flash);
 	platform_device_register(&wrt350n_v2_leds);
 	platform_device_register(&wrt350n_v2_button_device);
diff --git a/arch/arm/mach-prima2/pm.c b/arch/arm/mach-prima2/pm.c
index 02cc34388b05..c4525a88e5da 100644
--- a/arch/arm/mach-prima2/pm.c
+++ b/arch/arm/mach-prima2/pm.c
@@ -34,7 +34,10 @@ static void sirfsoc_set_wakeup_source(void)
 	pwr_trigger_en_reg = sirfsoc_rtc_iobrg_readl(sirfsoc_pwrc_base +
 		SIRFSOC_PWRC_TRIGGER_EN);
 #define X_ON_KEY_B (1 << 0)
-	sirfsoc_rtc_iobrg_writel(pwr_trigger_en_reg | X_ON_KEY_B,
+#define RTC_ALARM0_B (1 << 2)
+#define RTC_ALARM1_B (1 << 3)
+	sirfsoc_rtc_iobrg_writel(pwr_trigger_en_reg | X_ON_KEY_B |
+		RTC_ALARM0_B | RTC_ALARM1_B,
 		sirfsoc_pwrc_base + SIRFSOC_PWRC_TRIGGER_EN);
 }
 
@@ -85,12 +88,6 @@ static const struct platform_suspend_ops sirfsoc_pm_ops = {
 	.valid = suspend_valid_only_mem,
 };
 
-int __init sirfsoc_pm_init(void)
-{
-	suspend_set_ops(&sirfsoc_pm_ops);
-	return 0;
-}
-
 static const struct of_device_id pwrc_ids[] = {
 	{ .compatible = "sirf,prima2-pwrc" },
 	{}
@@ -118,7 +115,6 @@ static int __init sirfsoc_of_pwrc_init(void)
 
 	return 0;
 }
-postcore_initcall(sirfsoc_of_pwrc_init);
 
 static const struct of_device_id memc_ids[] = {
 	{ .compatible = "sirf,prima2-memc" },
@@ -149,4 +145,11 @@ static int __init sirfsoc_memc_init(void)
 {
 	return platform_driver_register(&sirfsoc_memc_driver);
 }
-postcore_initcall(sirfsoc_memc_init);
+
+int __init sirfsoc_pm_init(void)
+{
+	sirfsoc_of_pwrc_init();
+	sirfsoc_memc_init();
+	suspend_set_ops(&sirfsoc_pm_ops);
+	return 0;
+}
diff --git a/arch/arm/mach-pxa/cm-x300.c b/arch/arm/mach-pxa/cm-x300.c
index 8091aac89edf..f9423493ed36 100644
--- a/arch/arm/mach-pxa/cm-x300.c
+++ b/arch/arm/mach-pxa/cm-x300.c
@@ -29,7 +29,7 @@
 #include <linux/pwm_backlight.h>
 
 #include <linux/i2c.h>
-#include <linux/i2c/pca953x.h>
+#include <linux/platform_data/pca953x.h>
 #include <linux/i2c/pxa-i2c.h>
 
 #include <linux/mfd/da903x.h>
diff --git a/arch/arm/mach-pxa/em-x270.c b/arch/arm/mach-pxa/em-x270.c
index 3a3362fa793e..8eb4e23c561d 100644
--- a/arch/arm/mach-pxa/em-x270.c
+++ b/arch/arm/mach-pxa/em-x270.c
@@ -30,7 +30,7 @@
 #include <linux/power_supply.h>
 #include <linux/apm-emulation.h>
 #include <linux/i2c.h>
-#include <linux/i2c/pca953x.h>
+#include <linux/platform_data/pca953x.h>
 #include <linux/i2c/pxa-i2c.h>
 #include <linux/regulator/userspace-consumer.h>
 
diff --git a/arch/arm/mach-pxa/icontrol.c b/arch/arm/mach-pxa/icontrol.c
index fe31bfcbb8df..c98511c5abd1 100644
--- a/arch/arm/mach-pxa/icontrol.c
+++ b/arch/arm/mach-pxa/icontrol.c
@@ -73,9 +73,6 @@ static struct pxa2xx_spi_chip mcp251x_chip_info4 = {
 
 static struct mcp251x_platform_data mcp251x_info = {
 	.oscillator_frequency = 16E6,
-	.board_specific_setup = NULL,
-	.power_enable         = NULL,
-	.transceiver_enable   = NULL
 };
 
 static struct spi_board_info mcp251x_board_info[] = {
diff --git a/arch/arm/mach-pxa/pcm990-baseboard.c b/arch/arm/mach-pxa/pcm990-baseboard.c
index 13e5b00eae90..3133ba82c508 100644
--- a/arch/arm/mach-pxa/pcm990-baseboard.c
+++ b/arch/arm/mach-pxa/pcm990-baseboard.c
@@ -408,7 +408,7 @@ struct pxacamera_platform_data pcm990_pxacamera_platform_data = {
 	.mclk_10khz = 1000,
 };
 
-#include <linux/i2c/pca953x.h>
+#include <linux/platform_data/pca953x.h>
 
 static struct pca953x_platform_data pca9536_data = {
 	.gpio_base	= PXA_NR_BUILTIN_GPIO,
diff --git a/arch/arm/mach-pxa/pxa-dt.c b/arch/arm/mach-pxa/pxa-dt.c
index 3835979a0dd3..f6a2c4b1c1dc 100644
--- a/arch/arm/mach-pxa/pxa-dt.c
+++ b/arch/arm/mach-pxa/pxa-dt.c
@@ -28,7 +28,7 @@ static const struct of_dev_auxdata pxa3xx_auxdata_lookup[] __initconst = {
 	OF_DEV_AUXDATA("mrvl,pxa-uart",		0x40700000, "pxa2xx-uart.2", NULL),
 	OF_DEV_AUXDATA("mrvl,pxa-uart",		0x41600000, "pxa2xx-uart.3", NULL),
 	OF_DEV_AUXDATA("marvell,pxa-mmc",	0x41100000, "pxa2xx-mci.0", NULL),
-	OF_DEV_AUXDATA("mrvl,pxa-gpio",		0x40e00000, "pxa-gpio", NULL),
+	OF_DEV_AUXDATA("intel,pxa3xx-gpio",	0x40e00000, "pxa3xx-gpio", NULL),
 	OF_DEV_AUXDATA("marvell,pxa-ohci",	0x4c000000, "pxa27x-ohci", NULL),
 	OF_DEV_AUXDATA("mrvl,pxa-i2c",		0x40301680, "pxa2xx-i2c.0", NULL),
 	OF_DEV_AUXDATA("mrvl,pwri2c",		0x40f500c0, "pxa3xx-i2c.1", NULL),
diff --git a/arch/arm/mach-pxa/spitz.c b/arch/arm/mach-pxa/spitz.c
index 4c29173026e8..0b11c1af51c4 100644
--- a/arch/arm/mach-pxa/spitz.c
+++ b/arch/arm/mach-pxa/spitz.c
@@ -20,7 +20,7 @@
 #include <linux/leds.h>
 #include <linux/i2c.h>
 #include <linux/i2c/pxa-i2c.h>
-#include <linux/i2c/pca953x.h>
+#include <linux/platform_data/pca953x.h>
 #include <linux/spi/spi.h>
 #include <linux/spi/ads7846.h>
 #include <linux/spi/corgi_lcd.h>
diff --git a/arch/arm/mach-pxa/zeus.c b/arch/arm/mach-pxa/zeus.c
index f5d436434566..b19d1c361cab 100644
--- a/arch/arm/mach-pxa/zeus.c
+++ b/arch/arm/mach-pxa/zeus.c
@@ -26,9 +26,11 @@
 #include <linux/mtd/physmap.h>
 #include <linux/i2c.h>
 #include <linux/i2c/pxa-i2c.h>
-#include <linux/i2c/pca953x.h>
+#include <linux/platform_data/pca953x.h>
 #include <linux/apm-emulation.h>
 #include <linux/can/platform/mcp251x.h>
+#include <linux/regulator/fixed.h>
+#include <linux/regulator/machine.h>
 
 #include <asm/mach-types.h>
 #include <asm/suspend.h>
@@ -391,33 +393,34 @@ static struct pxa2xx_spi_master pxa2xx_spi_ssp3_master_info = {
 };
 
 /* CAN bus on SPI */
-static int zeus_mcp2515_setup(struct spi_device *sdev)
-{
-	int err;
-
-	err = gpio_request(ZEUS_CAN_SHDN_GPIO, "CAN shutdown");
-	if (err)
-		return err;
+static struct regulator_consumer_supply can_regulator_consumer =
+	REGULATOR_SUPPLY("vdd", "spi3.0");
 
-	err = gpio_direction_output(ZEUS_CAN_SHDN_GPIO, 1);
-	if (err) {
-		gpio_free(ZEUS_CAN_SHDN_GPIO);
-		return err;
-	}
+static struct regulator_init_data can_regulator_init_data = {
+	.constraints	= {
+		.valid_ops_mask	= REGULATOR_CHANGE_STATUS,
+	},
+	.consumer_supplies	= &can_regulator_consumer,
+	.num_consumer_supplies	= 1,
+};
 
-	return 0;
-}
+static struct fixed_voltage_config can_regulator_pdata = {
+	.supply_name	= "CAN_SHDN",
+	.microvolts	= 3300000,
+	.gpio		= ZEUS_CAN_SHDN_GPIO,
+	.init_data	= &can_regulator_init_data,
+};
 
-static int zeus_mcp2515_transceiver_enable(int enable)
-{
-	gpio_set_value(ZEUS_CAN_SHDN_GPIO, !enable);
-	return 0;
-}
+static struct platform_device can_regulator_device = {
+	.name	= "reg-fixed-volage",
+	.id	= -1,
+	.dev	= {
+		.platform_data	= &can_regulator_pdata,
+	},
+};
 
 static struct mcp251x_platform_data zeus_mcp2515_pdata = {
 	.oscillator_frequency	= 16*1000*1000,
-	.board_specific_setup	= zeus_mcp2515_setup,
-	.power_enable		= zeus_mcp2515_transceiver_enable,
 };
 
 static struct spi_board_info zeus_spi_board_info[] = {
@@ -516,6 +519,7 @@ static struct platform_device *zeus_devices[] __initdata = {
 	&zeus_leds_device,
 	&zeus_pcmcia_device,
 	&zeus_max6369_device,
+	&can_regulator_device,
 };
 
 /* AC'97 */
diff --git a/arch/arm/mach-pxa/zylonite_pxa300.c b/arch/arm/mach-pxa/zylonite_pxa300.c
index 86e59c043de2..869bce7c3f24 100644
--- a/arch/arm/mach-pxa/zylonite_pxa300.c
+++ b/arch/arm/mach-pxa/zylonite_pxa300.c
@@ -18,7 +18,7 @@
 #include <linux/init.h>
 #include <linux/i2c.h>
 #include <linux/i2c/pxa-i2c.h>
-#include <linux/i2c/pca953x.h>
+#include <linux/platform_data/pca953x.h>
 #include <linux/gpio.h>
 
 #include <mach/pxa300.h>
diff --git a/arch/arm/mach-realview/Kconfig b/arch/arm/mach-realview/Kconfig
index d210c0f9c2c4..9db2029aa632 100644
--- a/arch/arm/mach-realview/Kconfig
+++ b/arch/arm/mach-realview/Kconfig
@@ -13,7 +13,7 @@ config REALVIEW_EB_A9MP
 	depends on MACH_REALVIEW_EB
 	select CPU_V7
 	select HAVE_ARM_SCU if SMP
-	select HAVE_ARM_TWD if LOCAL_TIMERS
+	select HAVE_ARM_TWD if SMP
 	select HAVE_SMP
 	select MIGHT_HAVE_CACHE_L2X0
 	help
@@ -26,7 +26,7 @@ config REALVIEW_EB_ARM11MP
 	select ARCH_HAS_BARRIERS if SMP
 	select CPU_V6K
 	select HAVE_ARM_SCU if SMP
-	select HAVE_ARM_TWD if LOCAL_TIMERS
+	select HAVE_ARM_TWD if SMP
 	select HAVE_SMP
 	select MIGHT_HAVE_CACHE_L2X0
 	help
@@ -48,7 +48,7 @@ config MACH_REALVIEW_PB11MP
 	select ARM_GIC
 	select CPU_V6K
 	select HAVE_ARM_SCU if SMP
-	select HAVE_ARM_TWD if LOCAL_TIMERS
+	select HAVE_ARM_TWD if SMP
 	select HAVE_PATA_PLATFORM
 	select HAVE_SMP
 	select MIGHT_HAVE_CACHE_L2X0
@@ -92,7 +92,7 @@ config MACH_REALVIEW_PBX
 	select ARCH_SPARSEMEM_ENABLE if CPU_V7 && !REALVIEW_HIGH_PHYS_OFFSET
 	select ARM_GIC
 	select HAVE_ARM_SCU if SMP
-	select HAVE_ARM_TWD if LOCAL_TIMERS
+	select HAVE_ARM_TWD if SMP
 	select HAVE_PATA_PLATFORM
 	select HAVE_SMP
 	select MIGHT_HAVE_CACHE_L2X0
diff --git a/arch/arm/mach-realview/include/mach/debug-macro.S b/arch/arm/mach-realview/include/mach/debug-macro.S
deleted file mode 100644
index 8cc372dc66a8..000000000000
--- a/arch/arm/mach-realview/include/mach/debug-macro.S
+++ /dev/null
@@ -1,29 +0,0 @@
-/* arch/arm/mach-realview/include/mach/debug-macro.S
- *
- * Debugging macro include header
- *
- *  Copyright (C) 1994-1999 Russell King
- *  Moved from linux/arch/arm/kernel/debug.S by Ben Dooks
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifdef CONFIG_DEBUG_REALVIEW_STD_PORT
-#define DEBUG_LL_UART_OFFSET	0x00009000
-#elif defined(CONFIG_DEBUG_REALVIEW_PB1176_PORT)
-#define DEBUG_LL_UART_OFFSET	0x0010c000
-#endif
-
-#ifndef DEBUG_LL_UART_OFFSET
-#error "Unknown RealView platform"
-#endif
-
-		.macro	addruart, rp, rv, tmp
-		mov	\rp, #DEBUG_LL_UART_OFFSET
-		orr	\rv, \rp, #0xfb000000	@ virtual base
-		orr	\rp, \rp, #0x10000000	@ physical base
-		.endm
-
-#include <asm/hardware/debug-pl01x.S>
diff --git a/arch/arm/mach-rpc/include/mach/debug-macro.S b/arch/arm/mach-rpc/include/mach/debug-macro.S
deleted file mode 100644
index 6d28cc99b124..000000000000
--- a/arch/arm/mach-rpc/include/mach/debug-macro.S
+++ /dev/null
@@ -1,23 +0,0 @@
-/* arch/arm/mach-rpc/include/mach/debug-macro.S
- *
- * Debugging macro include header
- *
- *  Copyright (C) 1994-1999 Russell King
- *  Moved from linux/arch/arm/kernel/debug.S by Ben Dooks
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
-*/
-
-		.macro	addruart, rp, rv, tmp
-		mov	\rp, #0x00010000
-		orr	\rp, \rp, #0x00000fe0
-		orr	\rv, \rp, #0xe0000000	@ virtual
-		orr	\rp, \rp, #0x03000000	@ physical
-		.endm
-
-#define UART_SHIFT	2
-#define FLOW_CONTROL
-#include <asm/hardware/debug-8250.S>
diff --git a/arch/arm/mach-s3c24xx/Kconfig b/arch/arm/mach-s3c24xx/Kconfig
index 7791ac76f945..dba2173e70f3 100644
--- a/arch/arm/mach-s3c24xx/Kconfig
+++ b/arch/arm/mach-s3c24xx/Kconfig
@@ -30,7 +30,6 @@ config CPU_S3C2410
 	select S3C2410_CLOCK
 	select ARM_S3C2410_CPUFREQ if ARM_S3C24XX_CPUFREQ
 	select S3C2410_PM if PM
-	select SAMSUNG_HRT
 	select SAMSUNG_WDT_RESET
 	help
 	  Support for S3C2410 and S3C2410A family from the S3C24XX line
@@ -42,7 +41,6 @@ config CPU_S3C2412
 	select CPU_LLSERIAL_S3C2440
 	select S3C2412_DMA if S3C24XX_DMA
 	select S3C2412_PM if PM
-	select SAMSUNG_HRT
 	help
 	  Support for the S3C2412 and S3C2413 SoCs from the S3C24XX line
 
@@ -54,7 +52,6 @@ config CPU_S3C2416
 	select S3C2443_COMMON
 	select S3C2443_DMA if S3C24XX_DMA
 	select SAMSUNG_CLKSRC
-	select SAMSUNG_HRT
 	help
 	  Support for the S3C2416 SoC from the S3C24XX line
 
@@ -65,7 +62,6 @@ config CPU_S3C2440
 	select S3C2410_CLOCK
 	select S3C2410_PM if PM
 	select S3C2440_DMA if S3C24XX_DMA
-	select SAMSUNG_HRT
 	help
 	  Support for S3C2440 Samsung Mobile CPU based systems.
 
@@ -75,7 +71,6 @@ config CPU_S3C2442
 	select CPU_LLSERIAL_S3C2440
 	select S3C2410_CLOCK
 	select S3C2410_PM if PM
-	select SAMSUNG_HRT
 	help
 	  Support for S3C2442 Samsung Mobile CPU based systems.
 
@@ -91,7 +86,6 @@ config CPU_S3C2443
 	select S3C2443_COMMON
 	select S3C2443_DMA if S3C24XX_DMA
 	select SAMSUNG_CLKSRC
-	select SAMSUNG_HRT
 	help
 	  Support for the S3C2443 SoC from the S3C24XX line
 
diff --git a/arch/arm/mach-s3c24xx/clock-s3c2410.c b/arch/arm/mach-s3c24xx/clock-s3c2410.c
index 564553694b54..d39d3c787580 100644
--- a/arch/arm/mach-s3c24xx/clock-s3c2410.c
+++ b/arch/arm/mach-s3c24xx/clock-s3c2410.c
@@ -281,6 +281,5 @@ int __init s3c2410_baseclk_add(void)
 	       (clkslow & S3C2410_CLKSLOW_MPLL_OFF) ? "off" : "on",
 	       (clkslow & S3C2410_CLKSLOW_UCLK_OFF) ? "off" : "on");
 
-	s3c_pwmclk_init();
 	return 0;
 }
diff --git a/arch/arm/mach-s3c24xx/clock-s3c2412.c b/arch/arm/mach-s3c24xx/clock-s3c2412.c
index 2cc017da88fe..d8f253f2b486 100644
--- a/arch/arm/mach-s3c24xx/clock-s3c2412.c
+++ b/arch/arm/mach-s3c24xx/clock-s3c2412.c
@@ -757,6 +757,5 @@ int __init s3c2412_baseclk_add(void)
 	}
 
 	clkdev_add_table(s3c2412_clk_lookup, ARRAY_SIZE(s3c2412_clk_lookup));
-	s3c_pwmclk_init();
 	return 0;
 }
diff --git a/arch/arm/mach-s3c24xx/clock-s3c2416.c b/arch/arm/mach-s3c24xx/clock-s3c2416.c
index 036056cea57c..d421a72920a5 100644
--- a/arch/arm/mach-s3c24xx/clock-s3c2416.c
+++ b/arch/arm/mach-s3c24xx/clock-s3c2416.c
@@ -168,6 +168,4 @@ void __init s3c2416_init_clocks(int xtal)
 	s3c24xx_register_clock(&hsmmc0_clk);
 	clkdev_add_table(s3c2416_clk_lookup, ARRAY_SIZE(s3c2416_clk_lookup));
 
-	s3c_pwmclk_init();
-
 }
diff --git a/arch/arm/mach-s3c24xx/clock-s3c2443.c b/arch/arm/mach-s3c24xx/clock-s3c2443.c
index 0a53051b0787..76cd31f7804e 100644
--- a/arch/arm/mach-s3c24xx/clock-s3c2443.c
+++ b/arch/arm/mach-s3c24xx/clock-s3c2443.c
@@ -209,6 +209,4 @@ void __init s3c2443_init_clocks(int xtal)
 	s3c_register_clocks(init_clocks_off, ARRAY_SIZE(init_clocks_off));
 	s3c_disable_clocks(init_clocks_off, ARRAY_SIZE(init_clocks_off));
 	clkdev_add_table(s3c2443_clk_lookup, ARRAY_SIZE(s3c2443_clk_lookup));
-
-	s3c_pwmclk_init();
 }
diff --git a/arch/arm/mach-s3c24xx/common.c b/arch/arm/mach-s3c24xx/common.c
index c157103ed8eb..457261c98433 100644
--- a/arch/arm/mach-s3c24xx/common.c
+++ b/arch/arm/mach-s3c24xx/common.c
@@ -27,6 +27,7 @@
 #include <linux/interrupt.h>
 #include <linux/ioport.h>
 #include <linux/serial_core.h>
+#include <clocksource/samsung_pwm.h>
 #include <linux/platform_device.h>
 #include <linux/delay.h>
 #include <linux/io.h>
@@ -49,6 +50,7 @@
 #include <plat/clock.h>
 #include <plat/cpu-freq.h>
 #include <plat/pll.h>
+#include <plat/pwm-core.h>
 
 #include "common.h"
 
@@ -216,6 +218,13 @@ static void s3c24xx_default_idle(void)
 		     S3C2410_CLKCON);
 }
 
+static struct samsung_pwm_variant s3c24xx_pwm_variant = {
+	.bits		= 16,
+	.div_base	= 1,
+	.has_tint_cstat	= false,
+	.tclk_mask	= (1 << 4),
+};
+
 void __init s3c24xx_init_io(struct map_desc *mach_desc, int size)
 {
 	arm_pm_idle = s3c24xx_default_idle;
@@ -232,6 +241,24 @@ void __init s3c24xx_init_io(struct map_desc *mach_desc, int size)
 	s3c24xx_init_cpu();
 
 	s3c_init_cpu(samsung_cpu_id, cpu_ids, ARRAY_SIZE(cpu_ids));
+
+	samsung_pwm_set_platdata(&s3c24xx_pwm_variant);
+}
+
+void __init samsung_set_timer_source(unsigned int event, unsigned int source)
+{
+	s3c24xx_pwm_variant.output_mask = BIT(SAMSUNG_PWM_NUM) - 1;
+	s3c24xx_pwm_variant.output_mask &= ~(BIT(event) | BIT(source));
+}
+
+void __init samsung_timer_init(void)
+{
+	unsigned int timer_irqs[SAMSUNG_PWM_NUM] = {
+		IRQ_TIMER0, IRQ_TIMER1, IRQ_TIMER2, IRQ_TIMER3, IRQ_TIMER4,
+	};
+
+	samsung_pwm_clocksource_init(S3C_VA_TIMER,
+					timer_irqs, &s3c24xx_pwm_variant);
 }
 
 /* Serial port registrations */
diff --git a/arch/arm/mach-s3c24xx/include/mach/map.h b/arch/arm/mach-s3c24xx/include/mach/map.h
index 8ba381f2dbe1..444793f0f5f1 100644
--- a/arch/arm/mach-s3c24xx/include/mach/map.h
+++ b/arch/arm/mach-s3c24xx/include/mach/map.h
@@ -167,4 +167,6 @@
 #define S3C_PA_SPI0		S3C2443_PA_SPI0
 #define S3C_PA_SPI1		S3C2443_PA_SPI1
 
+#define SAMSUNG_PA_TIMER	S3C2410_PA_TIMER
+
 #endif /* __ASM_ARCH_MAP_H */
diff --git a/arch/arm/mach-s3c24xx/mach-h1940.c b/arch/arm/mach-s3c24xx/mach-h1940.c
index af4334d6b4d5..74dd47988b41 100644
--- a/arch/arm/mach-s3c24xx/mach-h1940.c
+++ b/arch/arm/mach-s3c24xx/mach-h1940.c
@@ -512,7 +512,7 @@ static struct platform_pwm_backlight_data backlight_data = {
 static struct platform_device h1940_backlight = {
 	.name = "pwm-backlight",
 	.dev  = {
-		.parent = &s3c_device_timer[0].dev,
+		.parent = &samsung_device_pwm.dev,
 		.platform_data = &backlight_data,
 	},
 	.id   = -1,
@@ -632,7 +632,7 @@ static struct platform_device *h1940_devices[] __initdata = {
 	&h1940_device_bluetooth,
 	&s3c_device_sdi,
 	&s3c_device_rtc,
-	&s3c_device_timer[0],
+	&samsung_device_pwm,
 	&h1940_backlight,
 	&h1940_lcd_powerdev,
 	&s3c_device_adc,
diff --git a/arch/arm/mach-s3c24xx/mach-rx1950.c b/arch/arm/mach-s3c24xx/mach-rx1950.c
index 44ca018e1f96..206b1f7546d1 100644
--- a/arch/arm/mach-s3c24xx/mach-rx1950.c
+++ b/arch/arm/mach-s3c24xx/mach-rx1950.c
@@ -530,7 +530,7 @@ static struct platform_pwm_backlight_data rx1950_backlight_data = {
 static struct platform_device rx1950_backlight = {
 	.name = "pwm-backlight",
 	.dev = {
-		.parent = &s3c_device_timer[0].dev,
+		.parent = &samsung_device_pwm.dev,
 		.platform_data = &rx1950_backlight_data,
 	},
 };
@@ -717,8 +717,7 @@ static struct platform_device *rx1950_devices[] __initdata = {
 	&s3c_device_sdi,
 	&s3c_device_adc,
 	&s3c_device_ts,
-	&s3c_device_timer[0],
-	&s3c_device_timer[1],
+	&samsung_device_pwm,
 	&rx1950_backlight,
 	&rx1950_device_gpiokeys,
 	&power_supply,
diff --git a/arch/arm/mach-s3c64xx/Kconfig b/arch/arm/mach-s3c64xx/Kconfig
index 20578536aec7..041da5172423 100644
--- a/arch/arm/mach-s3c64xx/Kconfig
+++ b/arch/arm/mach-s3c64xx/Kconfig
@@ -17,13 +17,11 @@ config PLAT_S3C64XX
 # Configuration options for the S3C6410 CPU
 
 config CPU_S3C6400
-	select SAMSUNG_HRT
 	bool
 	help
 	  Enable S3C6400 CPU support
 
 config CPU_S3C6410
-	select SAMSUNG_HRT
 	bool
 	help
 	  Enable S3C6410 CPU support
diff --git a/arch/arm/mach-s3c64xx/clock.c b/arch/arm/mach-s3c64xx/clock.c
index 8499415be9cd..c1bcc4a6d3a8 100644
--- a/arch/arm/mach-s3c64xx/clock.c
+++ b/arch/arm/mach-s3c64xx/clock.c
@@ -1004,6 +1004,4 @@ void __init s3c64xx_register_clocks(unsigned long xtal,
 	for (cnt = 0; cnt < ARRAY_SIZE(clksrc_cdev); cnt++)
 		s3c_register_clksrc(clksrc_cdev[cnt], 1);
 	clkdev_add_table(s3c64xx_clk_lookup, ARRAY_SIZE(s3c64xx_clk_lookup));
-
-	s3c_pwmclk_init();
 }
diff --git a/arch/arm/mach-s3c64xx/common.c b/arch/arm/mach-s3c64xx/common.c
index 3f62e467b129..73d79cf5e141 100644
--- a/arch/arm/mach-s3c64xx/common.c
+++ b/arch/arm/mach-s3c64xx/common.c
@@ -27,6 +27,7 @@
 #include <linux/irq.h>
 #include <linux/gpio.h>
 #include <linux/irqchip/arm-vic.h>
+#include <clocksource/samsung_pwm.h>
 
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
@@ -42,7 +43,7 @@
 #include <plat/pm.h>
 #include <plat/gpio-cfg.h>
 #include <plat/irq-uart.h>
-#include <plat/irq-vic-timer.h>
+#include <plat/pwm-core.h>
 #include <plat/regs-irqtype.h>
 #include <plat/regs-serial.h>
 #include <plat/watchdog-reset.h>
@@ -149,6 +150,30 @@ static struct device s3c64xx_dev = {
 	.bus	= &s3c64xx_subsys,
 };
 
+static struct samsung_pwm_variant s3c64xx_pwm_variant = {
+	.bits		= 32,
+	.div_base	= 0,
+	.has_tint_cstat	= true,
+	.tclk_mask	= (1 << 7) | (1 << 6) | (1 << 5),
+};
+
+void __init samsung_set_timer_source(unsigned int event, unsigned int source)
+{
+	s3c64xx_pwm_variant.output_mask = BIT(SAMSUNG_PWM_NUM) - 1;
+	s3c64xx_pwm_variant.output_mask &= ~(BIT(event) | BIT(source));
+}
+
+void __init samsung_timer_init(void)
+{
+	unsigned int timer_irqs[SAMSUNG_PWM_NUM] = {
+		IRQ_TIMER0_VIC, IRQ_TIMER1_VIC, IRQ_TIMER2_VIC,
+		IRQ_TIMER3_VIC, IRQ_TIMER4_VIC,
+	};
+
+	samsung_pwm_clocksource_init(S3C_VA_TIMER,
+					timer_irqs, &s3c64xx_pwm_variant);
+}
+
 /* read cpu identification code */
 
 void __init s3c64xx_init_io(struct map_desc *mach_desc, int size)
@@ -161,6 +186,8 @@ void __init s3c64xx_init_io(struct map_desc *mach_desc, int size)
 	s3c64xx_init_cpu();
 
 	s3c_init_cpu(samsung_cpu_id, cpu_ids, ARRAY_SIZE(cpu_ids));
+
+	samsung_pwm_set_platdata(&s3c64xx_pwm_variant);
 }
 
 static __init int s3c64xx_dev_init(void)
@@ -195,9 +222,6 @@ void __init s3c64xx_init_irq(u32 vic0_valid, u32 vic1_valid)
 	/* initialise the pair of VICs */
 	vic_init(VA_VIC0, IRQ_VIC0_BASE, vic0_valid, IRQ_VIC0_RESUME);
 	vic_init(VA_VIC1, IRQ_VIC1_BASE, vic1_valid, IRQ_VIC1_RESUME);
-
-	/* add the timer sub-irqs */
-	s3c_init_vic_timer_irq(5, IRQ_TIMER0);
 }
 
 #define eint_offset(irq)	((irq) - IRQ_EINT(0))
diff --git a/arch/arm/mach-s3c64xx/include/mach/irqs.h b/arch/arm/mach-s3c64xx/include/mach/irqs.h
index 96d60e0d9372..67bbd1dd04c2 100644
--- a/arch/arm/mach-s3c64xx/include/mach/irqs.h
+++ b/arch/arm/mach-s3c64xx/include/mach/irqs.h
@@ -107,14 +107,6 @@
 #define IRQ_TC			IRQ_PENDN
 #define IRQ_ADC			S3C64XX_IRQ_VIC1(31)
 
-#define S3C64XX_TIMER_IRQ(x)	S3C_IRQ(64 + (x))
-
-#define IRQ_TIMER0		S3C64XX_TIMER_IRQ(0)
-#define IRQ_TIMER1		S3C64XX_TIMER_IRQ(1)
-#define IRQ_TIMER2		S3C64XX_TIMER_IRQ(2)
-#define IRQ_TIMER3		S3C64XX_TIMER_IRQ(3)
-#define IRQ_TIMER4		S3C64XX_TIMER_IRQ(4)
-
 /* compatibility for device defines */
 
 #define IRQ_IIC1		IRQ_S3C6410_IIC1
diff --git a/arch/arm/mach-s3c64xx/include/mach/map.h b/arch/arm/mach-s3c64xx/include/mach/map.h
index 8e2097bb208a..f55ccb1ce893 100644
--- a/arch/arm/mach-s3c64xx/include/mach/map.h
+++ b/arch/arm/mach-s3c64xx/include/mach/map.h
@@ -121,5 +121,6 @@
 #define SAMSUNG_PA_ADC		S3C64XX_PA_ADC
 #define SAMSUNG_PA_CFCON	S3C64XX_PA_CFCON
 #define SAMSUNG_PA_KEYPAD	S3C64XX_PA_KEYPAD
+#define SAMSUNG_PA_TIMER	S3C64XX_PA_TIMER
 
 #endif /* __ASM_ARCH_6400_MAP_H */
diff --git a/arch/arm/mach-s3c64xx/irq-pm.c b/arch/arm/mach-s3c64xx/irq-pm.c
index 0c7e1d960ca4..c3da1b68d03e 100644
--- a/arch/arm/mach-s3c64xx/irq-pm.c
+++ b/arch/arm/mach-s3c64xx/irq-pm.c
@@ -22,7 +22,6 @@
 #include <mach/map.h>
 
 #include <plat/regs-serial.h>
-#include <plat/regs-timer.h>
 #include <mach/regs-gpio.h>
 #include <plat/cpu.h>
 #include <plat/pm.h>
@@ -43,7 +42,6 @@ static struct sleep_save irq_save[] = {
 	SAVE_ITEM(S3C64XX_EINT0FLTCON2),
 	SAVE_ITEM(S3C64XX_EINT0FLTCON3),
 	SAVE_ITEM(S3C64XX_EINT0MASK),
-	SAVE_ITEM(S3C64XX_TINT_CSTAT),
 };
 
 static struct irq_grp_save {
diff --git a/arch/arm/mach-s3c64xx/mach-crag6410.c b/arch/arm/mach-s3c64xx/mach-crag6410.c
index 8ad88ace795a..eb8e5a1aca42 100644
--- a/arch/arm/mach-s3c64xx/mach-crag6410.c
+++ b/arch/arm/mach-s3c64xx/mach-crag6410.c
@@ -30,7 +30,7 @@
 #include <linux/basic_mmio_gpio.h>
 #include <linux/spi/spi.h>
 
-#include <linux/i2c/pca953x.h>
+#include <linux/platform_data/pca953x.h>
 #include <linux/platform_data/s3c-hsotg.h>
 
 #include <video/platform_lcd.h>
@@ -120,7 +120,7 @@ static struct platform_device crag6410_backlight_device = {
 	.name		= "pwm-backlight",
 	.id		= -1,
 	.dev		= {
-		.parent	= &s3c_device_timer[0].dev,
+		.parent	= &samsung_device_pwm.dev,
 		.platform_data = &crag6410_backlight_data,
 	},
 };
@@ -375,7 +375,7 @@ static struct platform_device *crag6410_devices[] __initdata = {
 	&s3c_device_fb,
 	&s3c_device_ohci,
 	&s3c_device_usb_hsotg,
-	&s3c_device_timer[0],
+	&samsung_device_pwm,
 	&s3c64xx_device_iis0,
 	&s3c64xx_device_iis1,
 	&samsung_device_keypad,
diff --git a/arch/arm/mach-s3c64xx/mach-hmt.c b/arch/arm/mach-s3c64xx/mach-hmt.c
index 5b7f357d8c22..f39569e0f2e6 100644
--- a/arch/arm/mach-s3c64xx/mach-hmt.c
+++ b/arch/arm/mach-s3c64xx/mach-hmt.c
@@ -123,7 +123,7 @@ static struct platform_pwm_backlight_data hmt_backlight_data = {
 static struct platform_device hmt_backlight_device = {
 	.name		= "pwm-backlight",
 	.dev		= {
-		.parent	= &s3c_device_timer[1].dev,
+		.parent	= &samsung_device_pwm.dev,
 		.platform_data = &hmt_backlight_data,
 	},
 };
@@ -239,7 +239,7 @@ static struct platform_device *hmt_devices[] __initdata = {
 	&s3c_device_nand,
 	&s3c_device_fb,
 	&s3c_device_ohci,
-	&s3c_device_timer[1],
+	&samsung_device_pwm,
 	&hmt_backlight_device,
 	&hmt_leds_device,
 };
diff --git a/arch/arm/mach-s3c64xx/mach-smartq.c b/arch/arm/mach-s3c64xx/mach-smartq.c
index 58ac99041274..86d980b448fd 100644
--- a/arch/arm/mach-s3c64xx/mach-smartq.c
+++ b/arch/arm/mach-s3c64xx/mach-smartq.c
@@ -157,7 +157,7 @@ static struct platform_pwm_backlight_data smartq_backlight_data = {
 static struct platform_device smartq_backlight_device = {
 	.name		= "pwm-backlight",
 	.dev		= {
-		.parent	= &s3c_device_timer[1].dev,
+		.parent	= &samsung_device_pwm.dev,
 		.platform_data = &smartq_backlight_data,
 	},
 };
@@ -246,7 +246,7 @@ static struct platform_device *smartq_devices[] __initdata = {
 	&s3c_device_i2c0,
 	&s3c_device_ohci,
 	&s3c_device_rtc,
-	&s3c_device_timer[1],
+	&samsung_device_pwm,
 	&s3c_device_ts,
 	&s3c_device_usb_hsotg,
 	&s3c64xx_device_iis0,
diff --git a/arch/arm/mach-s3c64xx/mach-smdk6410.c b/arch/arm/mach-s3c64xx/mach-smdk6410.c
index bd3295a19ad7..d90b450c5645 100644
--- a/arch/arm/mach-s3c64xx/mach-smdk6410.c
+++ b/arch/arm/mach-s3c64xx/mach-smdk6410.c
@@ -274,6 +274,7 @@ static struct platform_device *smdk6410_devices[] __initdata = {
 	&s3c_device_i2c1,
 	&s3c_device_fb,
 	&s3c_device_ohci,
+	&samsung_device_pwm,
 	&s3c_device_usb_hsotg,
 	&s3c64xx_device_iisv4,
 	&samsung_device_keypad,
@@ -691,9 +692,9 @@ static void __init smdk6410_machine_init(void)
 
 	s3c_ide_set_platdata(&smdk6410_ide_pdata);
 
-	samsung_bl_set(&smdk6410_bl_gpio_info, &smdk6410_bl_data);
-
 	platform_add_devices(smdk6410_devices, ARRAY_SIZE(smdk6410_devices));
+
+	samsung_bl_set(&smdk6410_bl_gpio_info, &smdk6410_bl_data);
 }
 
 MACHINE_START(SMDK6410, "SMDK6410")
diff --git a/arch/arm/mach-s5p64x0/Kconfig b/arch/arm/mach-s5p64x0/Kconfig
index 5a707bdb9ea0..bb2111b3751e 100644
--- a/arch/arm/mach-s5p64x0/Kconfig
+++ b/arch/arm/mach-s5p64x0/Kconfig
@@ -11,14 +11,12 @@ config CPU_S5P6440
 	bool
 	select S5P_SLEEP if PM
 	select SAMSUNG_DMADEV
-	select SAMSUNG_HRT
 	select SAMSUNG_WAKEMASK if PM
 	help
 	  Enable S5P6440 CPU support
 
 config CPU_S5P6450
 	bool
-	select SAMSUNG_HRT
 	select S5P_SLEEP if PM
 	select SAMSUNG_DMADEV
 	select SAMSUNG_WAKEMASK if PM
diff --git a/arch/arm/mach-s5p64x0/clock-s5p6440.c b/arch/arm/mach-s5p64x0/clock-s5p6440.c
index 3537815247f1..ae34a1d5e10a 100644
--- a/arch/arm/mach-s5p64x0/clock-s5p6440.c
+++ b/arch/arm/mach-s5p64x0/clock-s5p6440.c
@@ -629,6 +629,4 @@ void __init s5p6440_register_clocks(void)
 	clkdev_add_table(s5p6440_clk_lookup, ARRAY_SIZE(s5p6440_clk_lookup));
 
 	s3c24xx_register_clock(&dummy_apb_pclk);
-
-	s3c_pwmclk_init();
 }
diff --git a/arch/arm/mach-s5p64x0/clock-s5p6450.c b/arch/arm/mach-s5p64x0/clock-s5p6450.c
index af384ddd2dcf..0b3ca2ed53e9 100644
--- a/arch/arm/mach-s5p64x0/clock-s5p6450.c
+++ b/arch/arm/mach-s5p64x0/clock-s5p6450.c
@@ -698,6 +698,4 @@ void __init s5p6450_register_clocks(void)
 	clkdev_add_table(s5p6450_clk_lookup, ARRAY_SIZE(s5p6450_clk_lookup));
 
 	s3c24xx_register_clock(&dummy_apb_pclk);
-
-	s3c_pwmclk_init();
 }
diff --git a/arch/arm/mach-s5p64x0/common.c b/arch/arm/mach-s5p64x0/common.c
index dfdfdc320ce7..42e14f2e7ca7 100644
--- a/arch/arm/mach-s5p64x0/common.c
+++ b/arch/arm/mach-s5p64x0/common.c
@@ -19,6 +19,7 @@
 #include <linux/io.h>
 #include <linux/device.h>
 #include <linux/serial_core.h>
+#include <clocksource/samsung_pwm.h>
 #include <linux/platform_device.h>
 #include <linux/sched.h>
 #include <linux/dma-mapping.h>
@@ -47,6 +48,7 @@
 #include <plat/fb-core.h>
 #include <plat/spi-core.h>
 #include <plat/gpio-cfg.h>
+#include <plat/pwm-core.h>
 #include <plat/regs-irqtype.h>
 #include <plat/regs-serial.h>
 #include <plat/watchdog-reset.h>
@@ -157,6 +159,30 @@ static void s5p64x0_idle(void)
 	cpu_do_idle();
 }
 
+static struct samsung_pwm_variant s5p64x0_pwm_variant = {
+	.bits		= 32,
+	.div_base	= 0,
+	.has_tint_cstat	= true,
+	.tclk_mask	= 0,
+};
+
+void __init samsung_set_timer_source(unsigned int event, unsigned int source)
+{
+	s5p64x0_pwm_variant.output_mask = BIT(SAMSUNG_PWM_NUM) - 1;
+	s5p64x0_pwm_variant.output_mask &= ~(BIT(event) | BIT(source));
+}
+
+void __init samsung_timer_init(void)
+{
+	unsigned int timer_irqs[SAMSUNG_PWM_NUM] = {
+		IRQ_TIMER0_VIC, IRQ_TIMER1_VIC, IRQ_TIMER2_VIC,
+		IRQ_TIMER3_VIC, IRQ_TIMER4_VIC,
+	};
+
+	samsung_pwm_clocksource_init(S3C_VA_TIMER,
+					timer_irqs, &s5p64x0_pwm_variant);
+}
+
 /*
  * s5p64x0_map_io
  *
@@ -176,6 +202,7 @@ void __init s5p64x0_init_io(struct map_desc *mach_desc, int size)
 	s3c_init_cpu(samsung_cpu_id, cpu_ids, ARRAY_SIZE(cpu_ids));
 	samsung_wdt_reset_init(S3C_VA_WATCHDOG);
 
+	samsung_pwm_set_platdata(&s5p64x0_pwm_variant);
 }
 
 void __init s5p6440_map_io(void)
diff --git a/arch/arm/mach-s5p64x0/include/mach/irqs.h b/arch/arm/mach-s5p64x0/include/mach/irqs.h
index 5b845e849b30..53982db9d259 100644
--- a/arch/arm/mach-s5p64x0/include/mach/irqs.h
+++ b/arch/arm/mach-s5p64x0/include/mach/irqs.h
@@ -141,8 +141,6 @@
 
 #define IRQ_EINT_GROUP(grp, x)	(IRQ_EINT_GROUP##grp##_BASE + (x))
 
-#define IRQ_TIMER_BASE		(11)
-
 /* Set the default NR_IRQS */
 
 #define NR_IRQS			(IRQ_EINT_GROUP8_BASE + IRQ_EINT_GROUP8_NR + 1)
diff --git a/arch/arm/mach-s5p64x0/include/mach/map.h b/arch/arm/mach-s5p64x0/include/mach/map.h
index 0c0175dbfa34..50a6e96d6389 100644
--- a/arch/arm/mach-s5p64x0/include/mach/map.h
+++ b/arch/arm/mach-s5p64x0/include/mach/map.h
@@ -76,6 +76,7 @@
 #define S5P_PA_TIMER		S5P64X0_PA_TIMER
 
 #define SAMSUNG_PA_ADC		S5P64X0_PA_ADC
+#define SAMSUNG_PA_TIMER	S5P64X0_PA_TIMER
 
 /* UART */
 
diff --git a/arch/arm/mach-s5p64x0/mach-smdk6440.c b/arch/arm/mach-s5p64x0/mach-smdk6440.c
index 73f71a698a34..0b00304c1e91 100644
--- a/arch/arm/mach-s5p64x0/mach-smdk6440.c
+++ b/arch/arm/mach-s5p64x0/mach-smdk6440.c
@@ -162,6 +162,7 @@ static struct platform_device *smdk6440_devices[] __initdata = {
 	&s3c_device_rtc,
 	&s3c_device_i2c0,
 	&s3c_device_i2c1,
+	&samsung_device_pwm,
 	&s3c_device_ts,
 	&s3c_device_wdt,
 	&s5p6440_device_iis,
@@ -254,8 +255,6 @@ static void __init smdk6440_machine_init(void)
 	i2c_register_board_info(1, smdk6440_i2c_devs1,
 			ARRAY_SIZE(smdk6440_i2c_devs1));
 
-	samsung_bl_set(&smdk6440_bl_gpio_info, &smdk6440_bl_data);
-
 	s5p6440_set_lcd_interface();
 	s3c_fb_set_platdata(&smdk6440_lcd_pdata);
 
@@ -264,6 +263,8 @@ static void __init smdk6440_machine_init(void)
 	s3c_sdhci2_set_platdata(&smdk6440_hsmmc2_pdata);
 
 	platform_add_devices(smdk6440_devices, ARRAY_SIZE(smdk6440_devices));
+
+	samsung_bl_set(&smdk6440_bl_gpio_info, &smdk6440_bl_data);
 }
 
 MACHINE_START(SMDK6440, "SMDK6440")
diff --git a/arch/arm/mach-s5p64x0/mach-smdk6450.c b/arch/arm/mach-s5p64x0/mach-smdk6450.c
index 18303e12019f..5949296e88fd 100644
--- a/arch/arm/mach-s5p64x0/mach-smdk6450.c
+++ b/arch/arm/mach-s5p64x0/mach-smdk6450.c
@@ -180,6 +180,7 @@ static struct platform_device *smdk6450_devices[] __initdata = {
 	&s3c_device_rtc,
 	&s3c_device_i2c0,
 	&s3c_device_i2c1,
+	&samsung_device_pwm,
 	&s3c_device_ts,
 	&s3c_device_wdt,
 	&s5p6450_device_iis0,
@@ -273,8 +274,6 @@ static void __init smdk6450_machine_init(void)
 	i2c_register_board_info(1, smdk6450_i2c_devs1,
 			ARRAY_SIZE(smdk6450_i2c_devs1));
 
-	samsung_bl_set(&smdk6450_bl_gpio_info, &smdk6450_bl_data);
-
 	s5p6450_set_lcd_interface();
 	s3c_fb_set_platdata(&smdk6450_lcd_pdata);
 
@@ -283,6 +282,8 @@ static void __init smdk6450_machine_init(void)
 	s3c_sdhci2_set_platdata(&smdk6450_hsmmc2_pdata);
 
 	platform_add_devices(smdk6450_devices, ARRAY_SIZE(smdk6450_devices));
+
+	samsung_bl_set(&smdk6450_bl_gpio_info, &smdk6450_bl_data);
 }
 
 MACHINE_START(SMDK6450, "SMDK6450")
diff --git a/arch/arm/mach-s5p64x0/pm.c b/arch/arm/mach-s5p64x0/pm.c
index 97c2a08ad490..861e15cea691 100644
--- a/arch/arm/mach-s5p64x0/pm.c
+++ b/arch/arm/mach-s5p64x0/pm.c
@@ -18,7 +18,6 @@
 
 #include <plat/cpu.h>
 #include <plat/pm.h>
-#include <plat/regs-timer.h>
 #include <plat/wakeup-mask.h>
 
 #include <mach/regs-clock.h>
@@ -48,8 +47,6 @@ static struct sleep_save s5p64x0_misc_save[] = {
 	SAVE_ITEM(S5P64X0_MEM0CONSLP1),
 	SAVE_ITEM(S5P64X0_MEM0DRVCON),
 	SAVE_ITEM(S5P64X0_MEM1DRVCON),
-
-	SAVE_ITEM(S3C64XX_TINT_CSTAT),
 };
 
 /* DPLL is present only in S5P6450 */
diff --git a/arch/arm/mach-s5pc100/Kconfig b/arch/arm/mach-s5pc100/Kconfig
index 2f456a4533ba..15170be97a74 100644
--- a/arch/arm/mach-s5pc100/Kconfig
+++ b/arch/arm/mach-s5pc100/Kconfig
@@ -11,7 +11,6 @@ config CPU_S5PC100
 	bool
 	select S5P_EXT_INT
 	select SAMSUNG_DMADEV
-	select SAMSUNG_HRT
 	help
 	  Enable S5PC100 CPU support
 
diff --git a/arch/arm/mach-s5pc100/clock.c b/arch/arm/mach-s5pc100/clock.c
index a206dc35eff1..d0dc10ee7729 100644
--- a/arch/arm/mach-s5pc100/clock.c
+++ b/arch/arm/mach-s5pc100/clock.c
@@ -1358,6 +1358,4 @@ void __init s5pc100_register_clocks(void)
 		s3c_disable_clocks(clk_cdev[ptr], 1);
 
 	s3c24xx_register_clock(&dummy_apb_pclk);
-
-	s3c_pwmclk_init();
 }
diff --git a/arch/arm/mach-s5pc100/common.c b/arch/arm/mach-s5pc100/common.c
index 4bdfecf6d024..c5a8eeacf81c 100644
--- a/arch/arm/mach-s5pc100/common.c
+++ b/arch/arm/mach-s5pc100/common.c
@@ -22,6 +22,7 @@
 #include <linux/io.h>
 #include <linux/device.h>
 #include <linux/serial_core.h>
+#include <clocksource/samsung_pwm.h>
 #include <linux/platform_device.h>
 #include <linux/sched.h>
 #include <linux/reboot.h>
@@ -46,6 +47,7 @@
 #include <plat/fb-core.h>
 #include <plat/iic-core.h>
 #include <plat/onenand-core.h>
+#include <plat/pwm-core.h>
 #include <plat/spi-core.h>
 #include <plat/regs-serial.h>
 #include <plat/watchdog-reset.h>
@@ -132,6 +134,30 @@ static struct map_desc s5pc100_iodesc[] __initdata = {
 	}
 };
 
+static struct samsung_pwm_variant s5pc100_pwm_variant = {
+	.bits		= 32,
+	.div_base	= 0,
+	.has_tint_cstat	= true,
+	.tclk_mask	= (1 << 5),
+};
+
+void __init samsung_set_timer_source(unsigned int event, unsigned int source)
+{
+	s5pc100_pwm_variant.output_mask = BIT(SAMSUNG_PWM_NUM) - 1;
+	s5pc100_pwm_variant.output_mask &= ~(BIT(event) | BIT(source));
+}
+
+void __init samsung_timer_init(void)
+{
+	unsigned int timer_irqs[SAMSUNG_PWM_NUM] = {
+		IRQ_TIMER0_VIC, IRQ_TIMER1_VIC, IRQ_TIMER2_VIC,
+		IRQ_TIMER3_VIC, IRQ_TIMER4_VIC,
+	};
+
+	samsung_pwm_clocksource_init(S3C_VA_TIMER,
+					timer_irqs, &s5pc100_pwm_variant);
+}
+
 /*
  * s5pc100_map_io
  *
@@ -149,6 +175,8 @@ void __init s5pc100_init_io(struct map_desc *mach_desc, int size)
 	s5p_init_cpu(S5P_VA_CHIPID);
 
 	s3c_init_cpu(samsung_cpu_id, cpu_ids, ARRAY_SIZE(cpu_ids));
+
+	samsung_pwm_set_platdata(&s5pc100_pwm_variant);
 }
 
 void __init s5pc100_map_io(void)
diff --git a/arch/arm/mach-s5pc100/include/mach/irqs.h b/arch/arm/mach-s5pc100/include/mach/irqs.h
index 2870f12c7926..d2eb4757381f 100644
--- a/arch/arm/mach-s5pc100/include/mach/irqs.h
+++ b/arch/arm/mach-s5pc100/include/mach/irqs.h
@@ -97,8 +97,6 @@
 #define IRQ_SDMFIQ		S5P_IRQ_VIC2(31)
 #define IRQ_VIC_END		S5P_IRQ_VIC2(31)
 
-#define IRQ_TIMER_BASE		(11)
-
 #define S5P_EINT_BASE1		(S5P_IRQ_VIC0(0))
 #define S5P_EINT_BASE2		(IRQ_VIC_END + 1)
 
diff --git a/arch/arm/mach-s5pc100/include/mach/map.h b/arch/arm/mach-s5pc100/include/mach/map.h
index 54bc4f82e17a..2550b6112b82 100644
--- a/arch/arm/mach-s5pc100/include/mach/map.h
+++ b/arch/arm/mach-s5pc100/include/mach/map.h
@@ -116,6 +116,7 @@
 #define SAMSUNG_PA_ADC			S5PC100_PA_TSADC
 #define SAMSUNG_PA_CFCON		S5PC100_PA_CFCON
 #define SAMSUNG_PA_KEYPAD		S5PC100_PA_KEYPAD
+#define SAMSUNG_PA_TIMER		S5PC100_PA_TIMER
 
 #define S5PC100_VA_OTHERS		(S3C_VA_SYS + 0x10000)
 
diff --git a/arch/arm/mach-s5pc100/mach-smdkc100.c b/arch/arm/mach-s5pc100/mach-smdkc100.c
index 8c880f76f274..7c57a221785e 100644
--- a/arch/arm/mach-s5pc100/mach-smdkc100.c
+++ b/arch/arm/mach-s5pc100/mach-smdkc100.c
@@ -194,6 +194,7 @@ static struct platform_device *smdkc100_devices[] __initdata = {
 	&s3c_device_hsmmc0,
 	&s3c_device_hsmmc1,
 	&s3c_device_hsmmc2,
+	&samsung_device_pwm,
 	&s3c_device_ts,
 	&s3c_device_wdt,
 	&smdkc100_lcd_powerdev,
@@ -246,9 +247,9 @@ static void __init smdkc100_machine_init(void)
 	gpio_request(S5PC100_GPH0(6), "GPH0");
 	smdkc100_lcd_power_set(&smdkc100_lcd_power_data, 0);
 
-	samsung_bl_set(&smdkc100_bl_gpio_info, &smdkc100_bl_data);
-
 	platform_add_devices(smdkc100_devices, ARRAY_SIZE(smdkc100_devices));
+
+	samsung_bl_set(&smdkc100_bl_gpio_info, &smdkc100_bl_data);
 }
 
 MACHINE_START(SMDKC100, "SMDKC100")
diff --git a/arch/arm/mach-s5pv210/Kconfig b/arch/arm/mach-s5pv210/Kconfig
index 0963283a7c5d..caaedafbbf5f 100644
--- a/arch/arm/mach-s5pv210/Kconfig
+++ b/arch/arm/mach-s5pv210/Kconfig
@@ -15,7 +15,6 @@ config CPU_S5PV210
 	select S5P_PM if PM
 	select S5P_SLEEP if PM
 	select SAMSUNG_DMADEV
-	select SAMSUNG_HRT
 	help
 	  Enable S5PV210 CPU support
 
diff --git a/arch/arm/mach-s5pv210/clock.c b/arch/arm/mach-s5pv210/clock.c
index f051f53e35b7..ca463724a3df 100644
--- a/arch/arm/mach-s5pv210/clock.c
+++ b/arch/arm/mach-s5pv210/clock.c
@@ -1362,5 +1362,4 @@ void __init s5pv210_register_clocks(void)
 	for (ptr = 0; ptr < ARRAY_SIZE(clk_cdev); ptr++)
 		s3c_disable_clocks(clk_cdev[ptr], 1);
 
-	s3c_pwmclk_init();
 }
diff --git a/arch/arm/mach-s5pv210/common.c b/arch/arm/mach-s5pv210/common.c
index 023f1a796a9c..26027a29b8a1 100644
--- a/arch/arm/mach-s5pv210/common.c
+++ b/arch/arm/mach-s5pv210/common.c
@@ -19,6 +19,7 @@
 #include <linux/clk.h>
 #include <linux/io.h>
 #include <linux/device.h>
+#include <clocksource/samsung_pwm.h>
 #include <linux/platform_device.h>
 #include <linux/sched.h>
 #include <linux/dma-mapping.h>
@@ -42,6 +43,7 @@
 #include <plat/fimc-core.h>
 #include <plat/iic-core.h>
 #include <plat/keypad-core.h>
+#include <plat/pwm-core.h>
 #include <plat/tv-core.h>
 #include <plat/spi-core.h>
 #include <plat/regs-serial.h>
@@ -148,6 +150,30 @@ void s5pv210_restart(enum reboot_mode mode, const char *cmd)
 	__raw_writel(0x1, S5P_SWRESET);
 }
 
+static struct samsung_pwm_variant s5pv210_pwm_variant = {
+	.bits		= 32,
+	.div_base	= 0,
+	.has_tint_cstat	= true,
+	.tclk_mask	= (1 << 5),
+};
+
+void __init samsung_set_timer_source(unsigned int event, unsigned int source)
+{
+	s5pv210_pwm_variant.output_mask = BIT(SAMSUNG_PWM_NUM) - 1;
+	s5pv210_pwm_variant.output_mask &= ~(BIT(event) | BIT(source));
+}
+
+void __init samsung_timer_init(void)
+{
+	unsigned int timer_irqs[SAMSUNG_PWM_NUM] = {
+		IRQ_TIMER0_VIC, IRQ_TIMER1_VIC, IRQ_TIMER2_VIC,
+		IRQ_TIMER3_VIC, IRQ_TIMER4_VIC,
+	};
+
+	samsung_pwm_clocksource_init(S3C_VA_TIMER,
+					timer_irqs, &s5pv210_pwm_variant);
+}
+
 /*
  * s5pv210_map_io
  *
@@ -165,6 +191,8 @@ void __init s5pv210_init_io(struct map_desc *mach_desc, int size)
 	s5p_init_cpu(S5P_VA_CHIPID);
 
 	s3c_init_cpu(samsung_cpu_id, cpu_ids, ARRAY_SIZE(cpu_ids));
+
+	samsung_pwm_set_platdata(&s5pv210_pwm_variant);
 }
 
 void __init s5pv210_map_io(void)
diff --git a/arch/arm/mach-s5pv210/include/mach/irqs.h b/arch/arm/mach-s5pv210/include/mach/irqs.h
index e777e010ed2e..5e0de3a31f3d 100644
--- a/arch/arm/mach-s5pv210/include/mach/irqs.h
+++ b/arch/arm/mach-s5pv210/include/mach/irqs.h
@@ -118,8 +118,6 @@
 #define IRQ_MDNIE3		S5P_IRQ_VIC3(8)
 #define IRQ_VIC_END		S5P_IRQ_VIC3(31)
 
-#define IRQ_TIMER_BASE		(11)
-
 #define S5P_EINT_BASE1		(S5P_IRQ_VIC0(0))
 #define S5P_EINT_BASE2		(IRQ_VIC_END + 1)
 
diff --git a/arch/arm/mach-s5pv210/include/mach/map.h b/arch/arm/mach-s5pv210/include/mach/map.h
index b7c8a1917ffc..763929aca52d 100644
--- a/arch/arm/mach-s5pv210/include/mach/map.h
+++ b/arch/arm/mach-s5pv210/include/mach/map.h
@@ -139,6 +139,7 @@
 #define SAMSUNG_PA_ADC			S5PV210_PA_ADC
 #define SAMSUNG_PA_CFCON		S5PV210_PA_CFCON
 #define SAMSUNG_PA_KEYPAD		S5PV210_PA_KEYPAD
+#define SAMSUNG_PA_TIMER		S5PV210_PA_TIMER
 
 /* UART */
 
diff --git a/arch/arm/mach-s5pv210/mach-smdkv210.c b/arch/arm/mach-s5pv210/mach-smdkv210.c
index d50b6f124465..6d72bb992e38 100644
--- a/arch/arm/mach-s5pv210/mach-smdkv210.c
+++ b/arch/arm/mach-s5pv210/mach-smdkv210.c
@@ -218,6 +218,7 @@ static struct platform_device *smdkv210_devices[] __initdata = {
 	&s3c_device_i2c0,
 	&s3c_device_i2c1,
 	&s3c_device_i2c2,
+	&samsung_device_pwm,
 	&s3c_device_rtc,
 	&s3c_device_ts,
 	&s3c_device_usb_hsotg,
@@ -316,11 +317,11 @@ static void __init smdkv210_machine_init(void)
 
 	s3c_fb_set_platdata(&smdkv210_lcd0_pdata);
 
-	samsung_bl_set(&smdkv210_bl_gpio_info, &smdkv210_bl_data);
-
 	s3c_hsotg_set_platdata(&smdkv210_hsotg_pdata);
 
 	platform_add_devices(smdkv210_devices, ARRAY_SIZE(smdkv210_devices));
+
+	samsung_bl_set(&smdkv210_bl_gpio_info, &smdkv210_bl_data);
 }
 
 MACHINE_START(SMDKV210, "SMDKV210")
diff --git a/arch/arm/mach-s5pv210/pm.c b/arch/arm/mach-s5pv210/pm.c
index 2b68a67b6e95..3cf3f9c8ddd1 100644
--- a/arch/arm/mach-s5pv210/pm.c
+++ b/arch/arm/mach-s5pv210/pm.c
@@ -21,7 +21,6 @@
 
 #include <plat/cpu.h>
 #include <plat/pm.h>
-#include <plat/regs-timer.h>
 
 #include <mach/regs-irq.h>
 #include <mach/regs-clock.h>
@@ -77,15 +76,6 @@ static struct sleep_save s5pv210_core_save[] = {
 	/* Clock ETC */
 	SAVE_ITEM(S5P_CLK_OUT),
 	SAVE_ITEM(S5P_MDNIE_SEL),
-
-	/* PWM Register */
-	SAVE_ITEM(S3C2410_TCFG0),
-	SAVE_ITEM(S3C2410_TCFG1),
-	SAVE_ITEM(S3C64XX_TINT_CSTAT),
-	SAVE_ITEM(S3C2410_TCON),
-	SAVE_ITEM(S3C2410_TCNTB(0)),
-	SAVE_ITEM(S3C2410_TCMPB(0)),
-	SAVE_ITEM(S3C2410_TCNTO(0)),
 };
 
 static int s5pv210_cpu_suspend(unsigned long arg)
diff --git a/arch/arm/mach-sa1100/collie.c b/arch/arm/mach-sa1100/collie.c
index 612a45689770..7fb96ebdc0fb 100644
--- a/arch/arm/mach-sa1100/collie.c
+++ b/arch/arm/mach-sa1100/collie.c
@@ -289,7 +289,7 @@ static void collie_flash_exit(void)
 }
 
 static struct flash_platform_data collie_flash_data = {
-	.map_name	= "cfi_probe",
+	.map_name	= "jedec_probe",
 	.init		= collie_flash_init,
 	.set_vpp	= collie_set_vpp,
 	.exit		= collie_flash_exit,
diff --git a/arch/arm/mach-shmobile/Kconfig b/arch/arm/mach-shmobile/Kconfig
index 3912ce91fee4..1f94c310c477 100644
--- a/arch/arm/mach-shmobile/Kconfig
+++ b/arch/arm/mach-shmobile/Kconfig
@@ -1,3 +1,41 @@
+config ARCH_SHMOBILE_MULTI
+	bool "SH-Mobile Series" if ARCH_MULTI_V7
+	depends on MMU
+	select CPU_V7
+	select GENERIC_CLOCKEVENTS
+	select HAVE_ARM_SCU if SMP
+	select HAVE_ARM_TWD if LOCAL_TIMERS
+	select HAVE_SMP
+	select ARM_GIC
+	select MIGHT_HAVE_CACHE_L2X0
+	select NO_IOPORT
+	select PINCTRL
+	select ARCH_REQUIRE_GPIOLIB
+	select CLKDEV_LOOKUP
+
+if ARCH_SHMOBILE_MULTI
+
+comment "SH-Mobile System Type"
+
+config ARCH_EMEV2
+	bool "Emma Mobile EV2"
+
+comment "SH-Mobile Board Type"
+
+config MACH_KZM9D_REFERENCE
+	bool "KZM9D board - Reference Device Tree Implementation"
+	depends on ARCH_EMEV2
+	select REGULATOR_FIXED_VOLTAGE if REGULATOR
+	---help---
+	   Use reference implementation of KZM9D board support
+	   which makes a greater use of device tree at the expense
+	   of not supporting a number of devices.
+
+	   This is intended to aid developers
+
+comment "SH-Mobile System Configuration"
+endif
+
 if ARCH_SHMOBILE
 
 comment "SH-Mobile System Type"
@@ -23,9 +61,10 @@ config ARCH_R8A73A4
 	select ARCH_WANT_OPTIONAL_GPIOLIB
 	select ARM_GIC
 	select CPU_V7
-	select HAVE_ARM_ARCH_TIMER
 	select SH_CLK_CPG
 	select RENESAS_IRQC
+	select ARCH_HAS_CPUFREQ
+	select ARCH_HAS_OPP
 
 config ARCH_R8A7740
 	bool "R-Mobile A1 (R8A77400)"
@@ -59,7 +98,6 @@ config ARCH_R8A7790
 	select ARCH_WANT_OPTIONAL_GPIOLIB
 	select ARM_GIC
 	select CPU_V7
-	select HAVE_ARM_ARCH_TIMER
 	select SH_CLK_CPG
 	select RENESAS_IRQC
 
@@ -71,18 +109,22 @@ config ARCH_EMEV2
 
 comment "SH-Mobile Board Type"
 
-config MACH_AG5EVM
-	bool "AG5EVM board"
-	depends on ARCH_SH73A0
-	select ARCH_REQUIRE_GPIOLIB
-	select REGULATOR_FIXED_VOLTAGE if REGULATOR
-	select SH_LCD_MIPI_DSI
-
 config MACH_APE6EVM
 	bool "APE6EVM board"
 	depends on ARCH_R8A73A4
 	select USE_OF
 
+config MACH_APE6EVM_REFERENCE
+	bool "APE6EVM board - Reference Device Tree Implementation"
+	depends on ARCH_R8A73A4
+	select USE_OF
+	---help---
+	   Use reference implementation of APE6EVM board support
+	   which makes a greater use of device tree at the expense
+	   of not supporting a number of devices.
+
+	   This is intended to aid developers
+
 config MACH_MACKEREL
 	bool "mackerel board"
 	depends on ARCH_SH7372
@@ -91,12 +133,6 @@ config MACH_MACKEREL
 	select SND_SOC_AK4642 if SND_SIMPLE_CARD
 	select USE_OF
 
-config MACH_KOTA2
-	bool "KOTA2 board"
-	depends on ARCH_SH73A0
-	select ARCH_REQUIRE_GPIOLIB
-	select REGULATOR_FIXED_VOLTAGE if REGULATOR
-
 config MACH_ARMADILLO800EVA
 	bool "Armadillo-800 EVA board"
 	depends on ARCH_R8A7740
@@ -124,13 +160,29 @@ config MACH_BOCKW
 	depends on ARCH_R8A7778
 	select ARCH_REQUIRE_GPIOLIB
 	select RENESAS_INTC_IRQPIN
+	select REGULATOR_FIXED_VOLTAGE if REGULATOR
+	select USE_OF
+
+config MACH_BOCKW_REFERENCE
+	bool "BOCK-W  - Reference Device Tree Implementation"
+	depends on ARCH_R8A7778
+	select ARCH_REQUIRE_GPIOLIB
+	select RENESAS_INTC_IRQPIN
+	select REGULATOR_FIXED_VOLTAGE if REGULATOR
 	select USE_OF
+	---help---
+	   Use reference implementation of BockW board support
+	   which makes use of device tree at the expense
+	   of not supporting a number of devices.
+
+	   This is intended to aid developers
 
 config MACH_MARZEN
 	bool "MARZEN board"
 	depends on ARCH_R8A7779
 	select ARCH_REQUIRE_GPIOLIB
 	select REGULATOR_FIXED_VOLTAGE if REGULATOR
+	select USE_OF
 
 config MACH_MARZEN_REFERENCE
 	bool "MARZEN board - Reference Device Tree Implementation"
@@ -150,12 +202,35 @@ config MACH_LAGER
 	depends on ARCH_R8A7790
 	select USE_OF
 
+config MACH_LAGER_REFERENCE
+	bool "Lager board - Reference Device Tree Implementation"
+	depends on ARCH_R8A7790
+	select USE_OF
+	---help---
+	   Use reference implementation of Lager board support
+	   which makes use of device tree at the expense
+	   of not supporting a number of devices.
+
+	   This is intended to aid developers
+
 config MACH_KZM9D
 	bool "KZM9D board"
 	depends on ARCH_EMEV2
 	select REGULATOR_FIXED_VOLTAGE if REGULATOR
 	select USE_OF
 
+config MACH_KZM9D_REFERENCE
+	bool "KZM9D board - Reference Device Tree Implementation"
+	depends on ARCH_EMEV2
+	select REGULATOR_FIXED_VOLTAGE if REGULATOR
+	select USE_OF
+	---help---
+	   Use reference implementation of KZM9D board support
+	   which makes a greater use of device tree at the expense
+	   of not supporting a number of devices.
+
+	   This is intended to aid developers
+
 config MACH_KZM9G
 	bool "KZM-A9-GT board"
 	depends on ARCH_SH73A0
@@ -186,6 +261,15 @@ config CPU_HAS_INTEVT
         bool
 	default y
 
+config SH_CLK_CPG
+	bool
+
+source "drivers/sh/Kconfig"
+
+endif
+
+if ARCH_SHMOBILE || ARCH_SHMOBILE_MULTI
+
 menu "Timer and clock configuration"
 
 config SHMOBILE_TIMER_HZ
@@ -220,9 +304,4 @@ config EM_TIMER_STI
 
 endmenu
 
-config SH_CLK_CPG
-	bool
-
-source "drivers/sh/Kconfig"
-
 endif
diff --git a/arch/arm/mach-shmobile/Makefile b/arch/arm/mach-shmobile/Makefile
index 6165a517f580..2705bfa8c113 100644
--- a/arch/arm/mach-shmobile/Makefile
+++ b/arch/arm/mach-shmobile/Makefile
@@ -2,50 +2,65 @@
 # Makefile for the linux kernel.
 #
 
+ccflags-$(CONFIG_ARCH_MULTIPLATFORM) := -I$(srctree)/arch/arm/mach-shmobile/include
+
 # Common objects
-obj-y				:= timer.o console.o clock.o
+obj-y				:= timer.o console.o
 
 # CPU objects
-obj-$(CONFIG_ARCH_SH7372)	+= setup-sh7372.o clock-sh7372.o intc-sh7372.o
-obj-$(CONFIG_ARCH_SH73A0)	+= setup-sh73a0.o clock-sh73a0.o intc-sh73a0.o
-obj-$(CONFIG_ARCH_R8A73A4)	+= setup-r8a73a4.o clock-r8a73a4.o
-obj-$(CONFIG_ARCH_R8A7740)	+= setup-r8a7740.o clock-r8a7740.o intc-r8a7740.o
-obj-$(CONFIG_ARCH_R8A7778)	+= setup-r8a7778.o clock-r8a7778.o
-obj-$(CONFIG_ARCH_R8A7779)	+= setup-r8a7779.o clock-r8a7779.o intc-r8a7779.o
-obj-$(CONFIG_ARCH_R8A7790)	+= setup-r8a7790.o clock-r8a7790.o
-obj-$(CONFIG_ARCH_EMEV2)	+= setup-emev2.o clock-emev2.o
+obj-$(CONFIG_ARCH_SH7372)	+= setup-sh7372.o intc-sh7372.o
+obj-$(CONFIG_ARCH_SH73A0)	+= setup-sh73a0.o intc-sh73a0.o
+obj-$(CONFIG_ARCH_R8A73A4)	+= setup-r8a73a4.o
+obj-$(CONFIG_ARCH_R8A7740)	+= setup-r8a7740.o
+obj-$(CONFIG_ARCH_R8A7778)	+= setup-r8a7778.o
+obj-$(CONFIG_ARCH_R8A7779)	+= setup-r8a7779.o
+obj-$(CONFIG_ARCH_R8A7790)	+= setup-r8a7790.o
+obj-$(CONFIG_ARCH_EMEV2)	+= setup-emev2.o
+
+# Clock objects
+ifndef CONFIG_COMMON_CLK
+obj-y				+= clock.o
+obj-$(CONFIG_ARCH_SH7372)	+= clock-sh7372.o
+obj-$(CONFIG_ARCH_SH73A0)	+= clock-sh73a0.o
+obj-$(CONFIG_ARCH_R8A73A4)	+= clock-r8a73a4.o
+obj-$(CONFIG_ARCH_R8A7740)	+= clock-r8a7740.o
+obj-$(CONFIG_ARCH_R8A7778)	+= clock-r8a7778.o
+obj-$(CONFIG_ARCH_R8A7779)	+= clock-r8a7779.o
+obj-$(CONFIG_ARCH_R8A7790)	+= clock-r8a7790.o
+obj-$(CONFIG_ARCH_EMEV2)	+= clock-emev2.o
+endif
 
 # SMP objects
 smp-y				:= platsmp.o headsmp.o
-smp-$(CONFIG_ARCH_SH73A0)	+= smp-sh73a0.o headsmp-scu.o
-smp-$(CONFIG_ARCH_R8A7779)	+= smp-r8a7779.o headsmp-scu.o
-smp-$(CONFIG_ARCH_EMEV2)	+= smp-emev2.o headsmp-scu.o
+smp-$(CONFIG_ARCH_SH73A0)	+= smp-sh73a0.o headsmp-scu.o platsmp-scu.o
+smp-$(CONFIG_ARCH_R8A7779)	+= smp-r8a7779.o headsmp-scu.o platsmp-scu.o
+smp-$(CONFIG_ARCH_EMEV2)	+= smp-emev2.o headsmp-scu.o platsmp-scu.o
 
 # IRQ objects
 obj-$(CONFIG_ARCH_SH7372)	+= entry-intc.o
-obj-$(CONFIG_ARCH_R8A7740)	+= entry-intc.o
 
 # PM objects
 obj-$(CONFIG_SUSPEND)		+= suspend.o
 obj-$(CONFIG_CPU_IDLE)		+= cpuidle.o
-obj-$(CONFIG_ARCH_SHMOBILE)	+= pm-rmobile.o
-obj-$(CONFIG_ARCH_SH7372)	+= pm-sh7372.o sleep-sh7372.o
-obj-$(CONFIG_ARCH_R8A7740)	+= pm-r8a7740.o
-obj-$(CONFIG_ARCH_R8A7779)	+= pm-r8a7779.o
+obj-$(CONFIG_ARCH_SH7372)	+= pm-sh7372.o sleep-sh7372.o pm-rmobile.o
 obj-$(CONFIG_ARCH_SH73A0)	+= pm-sh73a0.o
+obj-$(CONFIG_ARCH_R8A7740)	+= pm-r8a7740.o pm-rmobile.o
+obj-$(CONFIG_ARCH_R8A7779)	+= pm-r8a7779.o
 
 # Board objects
-obj-$(CONFIG_MACH_AG5EVM)	+= board-ag5evm.o
 obj-$(CONFIG_MACH_APE6EVM)	+= board-ape6evm.o
+obj-$(CONFIG_MACH_APE6EVM_REFERENCE)	+= board-ape6evm-reference.o
 obj-$(CONFIG_MACH_MACKEREL)	+= board-mackerel.o
-obj-$(CONFIG_MACH_KOTA2)	+= board-kota2.o
 obj-$(CONFIG_MACH_BOCKW)	+= board-bockw.o
+obj-$(CONFIG_MACH_BOCKW_REFERENCE)	+= board-bockw-reference.o
 obj-$(CONFIG_MACH_MARZEN)	+= board-marzen.o
 obj-$(CONFIG_MACH_MARZEN_REFERENCE)	+= board-marzen-reference.o
 obj-$(CONFIG_MACH_LAGER)	+= board-lager.o
+obj-$(CONFIG_MACH_LAGER_REFERENCE)	+= board-lager-reference.o
 obj-$(CONFIG_MACH_ARMADILLO800EVA)	+= board-armadillo800eva.o
 obj-$(CONFIG_MACH_ARMADILLO800EVA_REFERENCE)	+= board-armadillo800eva-reference.o
 obj-$(CONFIG_MACH_KZM9D)	+= board-kzm9d.o
+obj-$(CONFIG_MACH_KZM9D_REFERENCE)	+= board-kzm9d-reference.o
 obj-$(CONFIG_MACH_KZM9G)	+= board-kzm9g.o
 obj-$(CONFIG_MACH_KZM9G_REFERENCE)	+= board-kzm9g-reference.o
 
diff --git a/arch/arm/mach-shmobile/Makefile.boot b/arch/arm/mach-shmobile/Makefile.boot
index 84c6868580f0..6a504fe7d86c 100644
--- a/arch/arm/mach-shmobile/Makefile.boot
+++ b/arch/arm/mach-shmobile/Makefile.boot
@@ -1,15 +1,17 @@
 # per-board load address for uImage
 loadaddr-y	:=
-loadaddr-$(CONFIG_MACH_AG5EVM) += 0x40008000
 loadaddr-$(CONFIG_MACH_APE6EVM) += 0x40008000
+loadaddr-$(CONFIG_MACH_APE6EVM_REFERENCE) += 0x40008000
 loadaddr-$(CONFIG_MACH_ARMADILLO800EVA) += 0x40008000
 loadaddr-$(CONFIG_MACH_ARMADILLO800EVA_REFERENCE) += 0x40008000
 loadaddr-$(CONFIG_MACH_BOCKW) += 0x60008000
-loadaddr-$(CONFIG_MACH_KOTA2) += 0x41008000
+loadaddr-$(CONFIG_MACH_BOCKW_REFERENCE) += 0x60008000
 loadaddr-$(CONFIG_MACH_KZM9D) += 0x40008000
+loadaddr-$(CONFIG_MACH_KZM9D_REFERENCE) += 0x40008000
 loadaddr-$(CONFIG_MACH_KZM9G) += 0x41008000
 loadaddr-$(CONFIG_MACH_KZM9G_REFERENCE) += 0x41008000
 loadaddr-$(CONFIG_MACH_LAGER) += 0x40008000
+loadaddr-$(CONFIG_MACH_LAGER_REFERENCE) += 0x40008000
 loadaddr-$(CONFIG_MACH_MACKEREL) += 0x40008000
 loadaddr-$(CONFIG_MACH_MARZEN) += 0x60008000
 loadaddr-$(CONFIG_MACH_MARZEN_REFERENCE) += 0x60008000
diff --git a/arch/arm/mach-shmobile/board-ag5evm.c b/arch/arm/mach-shmobile/board-ag5evm.c
deleted file mode 100644
index c7540710906f..000000000000
--- a/arch/arm/mach-shmobile/board-ag5evm.c
+++ /dev/null
@@ -1,672 +0,0 @@
-/*
- * arch/arm/mach-shmobile/board-ag5evm.c
- *
- * Copyright (C) 2010  Takashi Yoshii <yoshii.takashi.zj@renesas.com>
- * Copyright (C) 2009  Yoshihiro Shimoda <shimoda.yoshihiro@renesas.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; version 2 of the License.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
- *
- */
-
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/interrupt.h>
-#include <linux/irq.h>
-#include <linux/pinctrl/machine.h>
-#include <linux/pinctrl/pinconf-generic.h>
-#include <linux/platform_device.h>
-#include <linux/delay.h>
-#include <linux/io.h>
-#include <linux/dma-mapping.h>
-#include <linux/regulator/fixed.h>
-#include <linux/regulator/machine.h>
-#include <linux/serial_sci.h>
-#include <linux/smsc911x.h>
-#include <linux/gpio.h>
-#include <linux/videodev2.h>
-#include <linux/input.h>
-#include <linux/input/sh_keysc.h>
-#include <linux/mmc/host.h>
-#include <linux/mmc/sh_mmcif.h>
-#include <linux/mmc/sh_mobile_sdhi.h>
-#include <linux/mfd/tmio.h>
-#include <linux/sh_clk.h>
-#include <linux/irqchip/arm-gic.h>
-#include <video/sh_mobile_lcdc.h>
-#include <video/sh_mipi_dsi.h>
-#include <sound/sh_fsi.h>
-#include <mach/hardware.h>
-#include <mach/irqs.h>
-#include <mach/sh73a0.h>
-#include <mach/common.h>
-#include <asm/mach-types.h>
-#include <asm/mach/arch.h>
-#include <asm/hardware/cache-l2x0.h>
-#include <asm/traps.h>
-
-/* Dummy supplies, where voltage doesn't matter */
-static struct regulator_consumer_supply dummy_supplies[] = {
-	REGULATOR_SUPPLY("vddvario", "smsc911x"),
-	REGULATOR_SUPPLY("vdd33a", "smsc911x"),
-};
-
-static struct resource smsc9220_resources[] = {
-	[0] = {
-		.start		= 0x14000000,
-		.end		= 0x14000000 + SZ_64K - 1,
-		.flags		= IORESOURCE_MEM,
-	},
-	[1] = {
-		.start		= SH73A0_PINT0_IRQ(2), /* PINTA2 */
-		.flags		= IORESOURCE_IRQ,
-	},
-};
-
-static struct smsc911x_platform_config smsc9220_platdata = {
-	.flags		= SMSC911X_USE_32BIT | SMSC911X_SAVE_MAC_ADDRESS,
-	.phy_interface	= PHY_INTERFACE_MODE_MII,
-	.irq_polarity	= SMSC911X_IRQ_POLARITY_ACTIVE_LOW,
-	.irq_type	= SMSC911X_IRQ_TYPE_PUSH_PULL,
-};
-
-static struct platform_device eth_device = {
-	.name		= "smsc911x",
-	.id		= 0,
-	.dev  = {
-		.platform_data = &smsc9220_platdata,
-	},
-	.resource	= smsc9220_resources,
-	.num_resources	= ARRAY_SIZE(smsc9220_resources),
-};
-
-static struct sh_keysc_info keysc_platdata = {
-	.mode		= SH_KEYSC_MODE_6,
-	.scan_timing	= 3,
-	.delay		= 100,
-	.keycodes	= {
-		KEY_A, KEY_B, KEY_C, KEY_D, KEY_E, KEY_F, KEY_G,
-		KEY_H, KEY_I, KEY_J, KEY_K, KEY_L, KEY_M, KEY_N,
-		KEY_O, KEY_P, KEY_Q, KEY_R, KEY_S, KEY_T, KEY_U,
-		KEY_V, KEY_W, KEY_X, KEY_Y, KEY_Z, KEY_HOME, KEY_SLEEP,
-		KEY_SPACE, KEY_9, KEY_6, KEY_3, KEY_WAKEUP, KEY_RIGHT, \
-		KEY_COFFEE,
-		KEY_0, KEY_8, KEY_5, KEY_2, KEY_DOWN, KEY_ENTER, KEY_UP,
-		KEY_KPASTERISK, KEY_7, KEY_4, KEY_1, KEY_STOP, KEY_LEFT, \
-		KEY_COMPUTER,
-	},
-};
-
-static struct resource keysc_resources[] = {
-	[0] = {
-		.name	= "KEYSC",
-		.start	= 0xe61b0000,
-		.end	= 0xe61b0098 - 1,
-		.flags	= IORESOURCE_MEM,
-	},
-	[1] = {
-		.start	= gic_spi(71),
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-static struct platform_device keysc_device = {
-	.name		= "sh_keysc",
-	.id		= 0,
-	.num_resources	= ARRAY_SIZE(keysc_resources),
-	.resource	= keysc_resources,
-	.dev		= {
-		.platform_data	= &keysc_platdata,
-	},
-};
-
-/* FSI A */
-static struct resource fsi_resources[] = {
-	[0] = {
-		.name	= "FSI",
-		.start	= 0xEC230000,
-		.end	= 0xEC230400 - 1,
-		.flags	= IORESOURCE_MEM,
-	},
-	[1] = {
-		.start  = gic_spi(146),
-		.flags  = IORESOURCE_IRQ,
-	},
-};
-
-static struct platform_device fsi_device = {
-	.name		= "sh_fsi2",
-	.id		= -1,
-	.num_resources	= ARRAY_SIZE(fsi_resources),
-	.resource	= fsi_resources,
-};
-
-/* Fixed 1.8V regulator to be used by MMCIF */
-static struct regulator_consumer_supply fixed1v8_power_consumers[] =
-{
-	REGULATOR_SUPPLY("vmmc", "sh_mmcif.0"),
-	REGULATOR_SUPPLY("vqmmc", "sh_mmcif.0"),
-};
-
-static struct resource sh_mmcif_resources[] = {
-	[0] = {
-		.name	= "MMCIF",
-		.start	= 0xe6bd0000,
-		.end	= 0xe6bd00ff,
-		.flags	= IORESOURCE_MEM,
-	},
-	[1] = {
-		.start	= gic_spi(141),
-		.flags	= IORESOURCE_IRQ,
-	},
-	[2] = {
-		.start	= gic_spi(140),
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-static struct sh_mmcif_plat_data sh_mmcif_platdata = {
-	.sup_pclk	= 0,
-	.ocr		= MMC_VDD_165_195,
-	.caps		= MMC_CAP_8_BIT_DATA | MMC_CAP_NONREMOVABLE,
-	.slave_id_tx	= SHDMA_SLAVE_MMCIF_TX,
-	.slave_id_rx	= SHDMA_SLAVE_MMCIF_RX,
-};
-
-static struct platform_device mmc_device = {
-	.name		= "sh_mmcif",
-	.id		= 0,
-	.dev		= {
-		.dma_mask		= NULL,
-		.coherent_dma_mask	= 0xffffffff,
-		.platform_data		= &sh_mmcif_platdata,
-	},
-	.num_resources	= ARRAY_SIZE(sh_mmcif_resources),
-	.resource	= sh_mmcif_resources,
-};
-
-/* IrDA */
-static struct resource irda_resources[] = {
-	[0] = {
-		.start	= 0xE6D00000,
-		.end	= 0xE6D01FD4 - 1,
-		.flags  = IORESOURCE_MEM,
-	},
-	[1] = {
-		.start	= gic_spi(95),
-		.flags  = IORESOURCE_IRQ,
-	},
-};
-
-static struct platform_device irda_device = {
-	.name           = "sh_irda",
-	.id		= 0,
-	.resource       = irda_resources,
-	.num_resources  = ARRAY_SIZE(irda_resources),
-};
-
-/* MIPI-DSI */
-static struct resource mipidsi0_resources[] = {
-	[0] = {
-		.name	= "DSI0",
-		.start  = 0xfeab0000,
-		.end    = 0xfeab3fff,
-		.flags  = IORESOURCE_MEM,
-	},
-	[1] = {
-		.name	= "DSI0",
-		.start  = 0xfeab4000,
-		.end    = 0xfeab7fff,
-		.flags  = IORESOURCE_MEM,
-	},
-};
-
-static int sh_mipi_set_dot_clock(struct platform_device *pdev,
-				 void __iomem *base,
-				 int enable)
-{
-	struct clk *pck, *phy;
-	int ret;
-
-	pck = clk_get(&pdev->dev, "dsip_clk");
-	if (IS_ERR(pck)) {
-		ret = PTR_ERR(pck);
-		goto sh_mipi_set_dot_clock_pck_err;
-	}
-
-	phy = clk_get(&pdev->dev, "dsiphy_clk");
-	if (IS_ERR(phy)) {
-		ret = PTR_ERR(phy);
-		goto sh_mipi_set_dot_clock_phy_err;
-	}
-
-	if (enable) {
-		clk_set_rate(pck, clk_round_rate(pck,  24000000));
-		clk_set_rate(phy, clk_round_rate(pck, 510000000));
-		clk_enable(pck);
-		clk_enable(phy);
-	} else {
-		clk_disable(pck);
-		clk_disable(phy);
-	}
-
-	ret = 0;
-
-	clk_put(phy);
-sh_mipi_set_dot_clock_phy_err:
-	clk_put(pck);
-sh_mipi_set_dot_clock_pck_err:
-	return ret;
-}
-
-static struct sh_mipi_dsi_info mipidsi0_info = {
-	.data_format	= MIPI_RGB888,
-	.channel	= LCDC_CHAN_MAINLCD,
-	.lane		= 2,
-	.vsynw_offset	= 20,
-	.clksrc		= 1,
-	.flags		= SH_MIPI_DSI_HSABM		|
-			  SH_MIPI_DSI_SYNC_PULSES_MODE	|
-			  SH_MIPI_DSI_HSbyteCLK,
-	.set_dot_clock	= sh_mipi_set_dot_clock,
-};
-
-static struct platform_device mipidsi0_device = {
-	.name           = "sh-mipi-dsi",
-	.num_resources  = ARRAY_SIZE(mipidsi0_resources),
-	.resource       = mipidsi0_resources,
-	.id             = 0,
-	.dev	= {
-		.platform_data	= &mipidsi0_info,
-	},
-};
-
-static unsigned char lcd_backlight_seq[3][2] = {
-	{ 0x04, 0x07 },
-	{ 0x23, 0x80 },
-	{ 0x03, 0x01 },
-};
-
-static int lcd_backlight_set_brightness(int brightness)
-{
-	struct i2c_adapter *adap;
-	struct i2c_msg msg;
-	unsigned int i;
-	int ret;
-
-	if (brightness == 0) {
-		/* Reset the chip */
-		gpio_set_value(235, 0);
-		mdelay(24);
-		gpio_set_value(235, 1);
-		return 0;
-	}
-
-	adap = i2c_get_adapter(1);
-	if (adap == NULL)
-		return -ENODEV;
-
-	for (i = 0; i < ARRAY_SIZE(lcd_backlight_seq); i++) {
-		msg.addr = 0x6d;
-		msg.buf = &lcd_backlight_seq[i][0];
-		msg.len = 2;
-		msg.flags = 0;
-
-		ret = i2c_transfer(adap, &msg, 1);
-		if (ret < 0)
-			break;
-	}
-
-	i2c_put_adapter(adap);
-	return ret < 0 ? ret : 0;
-}
-
-/* LCDC0 */
-static const struct fb_videomode lcdc0_modes[] = {
-	{
-		.name		= "R63302(QHD)",
-		.xres		= 544,
-		.yres		= 961,
-		.left_margin	= 72,
-		.right_margin	= 600,
-		.hsync_len	= 16,
-		.upper_margin	= 8,
-		.lower_margin	= 8,
-		.vsync_len	= 2,
-		.sync		= FB_SYNC_VERT_HIGH_ACT | FB_SYNC_HOR_HIGH_ACT,
-	},
-};
-
-static struct sh_mobile_lcdc_info lcdc0_info = {
-	.clock_source = LCDC_CLK_PERIPHERAL,
-	.ch[0] = {
-		.chan = LCDC_CHAN_MAINLCD,
-		.interface_type = RGB24,
-		.clock_divider = 1,
-		.flags = LCDC_FLAGS_DWPOL,
-		.fourcc = V4L2_PIX_FMT_RGB565,
-		.lcd_modes = lcdc0_modes,
-		.num_modes = ARRAY_SIZE(lcdc0_modes),
-		.panel_cfg = {
-			.width = 44,
-			.height = 79,
-		},
-		.bl_info = {
-			.name = "sh_mobile_lcdc_bl",
-			.max_brightness = 1,
-			.set_brightness = lcd_backlight_set_brightness,
-		},
-		.tx_dev = &mipidsi0_device,
-	}
-};
-
-static struct resource lcdc0_resources[] = {
-	[0] = {
-		.name	= "LCDC0",
-		.start	= 0xfe940000, /* P4-only space */
-		.end	= 0xfe943fff,
-		.flags	= IORESOURCE_MEM,
-	},
-	[1] = {
-		.start	= intcs_evt2irq(0x580),
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-static struct platform_device lcdc0_device = {
-	.name		= "sh_mobile_lcdc_fb",
-	.num_resources	= ARRAY_SIZE(lcdc0_resources),
-	.resource	= lcdc0_resources,
-	.id             = 0,
-	.dev	= {
-		.platform_data	= &lcdc0_info,
-		.coherent_dma_mask = ~0,
-	},
-};
-
-/* Fixed 2.8V regulators to be used by SDHI0 */
-static struct regulator_consumer_supply fixed2v8_power_consumers[] =
-{
-	REGULATOR_SUPPLY("vmmc", "sh_mobile_sdhi.0"),
-	REGULATOR_SUPPLY("vqmmc", "sh_mobile_sdhi.0"),
-};
-
-/* SDHI0 */
-static struct sh_mobile_sdhi_info sdhi0_info = {
-	.dma_slave_tx	= SHDMA_SLAVE_SDHI0_TX,
-	.dma_slave_rx	= SHDMA_SLAVE_SDHI0_RX,
-	.tmio_flags	= TMIO_MMC_HAS_IDLE_WAIT | TMIO_MMC_USE_GPIO_CD,
-	.tmio_caps	= MMC_CAP_SD_HIGHSPEED,
-	.tmio_ocr_mask	= MMC_VDD_27_28 | MMC_VDD_28_29,
-	.cd_gpio	= 251,
-};
-
-static struct resource sdhi0_resources[] = {
-	[0] = {
-		.name	= "SDHI0",
-		.start	= 0xee100000,
-		.end	= 0xee1000ff,
-		.flags	= IORESOURCE_MEM,
-	},
-	[1] = {
-		.name	= SH_MOBILE_SDHI_IRQ_CARD_DETECT,
-		.start	= gic_spi(83),
-		.flags	= IORESOURCE_IRQ,
-	},
-	[2] = {
-		.name	= SH_MOBILE_SDHI_IRQ_SDCARD,
-		.start	= gic_spi(84),
-		.flags	= IORESOURCE_IRQ,
-	},
-	[3] = {
-		.name	= SH_MOBILE_SDHI_IRQ_SDIO,
-		.start	= gic_spi(85),
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-static struct platform_device sdhi0_device = {
-	.name		= "sh_mobile_sdhi",
-	.id		= 0,
-	.num_resources	= ARRAY_SIZE(sdhi0_resources),
-	.resource	= sdhi0_resources,
-	.dev	= {
-		.platform_data	= &sdhi0_info,
-	},
-};
-
-/* Fixed 3.3V regulator to be used by SDHI1 */
-static struct regulator_consumer_supply cn4_power_consumers[] =
-{
-	REGULATOR_SUPPLY("vmmc", "sh_mobile_sdhi.1"),
-	REGULATOR_SUPPLY("vqmmc", "sh_mobile_sdhi.1"),
-};
-
-static struct regulator_init_data cn4_power_init_data = {
-	.constraints = {
-		.valid_ops_mask = REGULATOR_CHANGE_STATUS,
-	},
-	.num_consumer_supplies  = ARRAY_SIZE(cn4_power_consumers),
-	.consumer_supplies      = cn4_power_consumers,
-};
-
-static struct fixed_voltage_config cn4_power_info = {
-	.supply_name = "CN4 SD/MMC Vdd",
-	.microvolts = 3300000,
-	.gpio = 114,
-	.enable_high = 1,
-	.init_data = &cn4_power_init_data,
-};
-
-static struct platform_device cn4_power = {
-	.name = "reg-fixed-voltage",
-	.id   = 2,
-	.dev  = {
-		.platform_data = &cn4_power_info,
-	},
-};
-
-static void ag5evm_sdhi1_set_pwr(struct platform_device *pdev, int state)
-{
-	static int power_gpio = -EINVAL;
-
-	if (power_gpio < 0) {
-		int ret = gpio_request_one(114, GPIOF_OUT_INIT_LOW,
-					   "sdhi1_power");
-		if (!ret)
-			power_gpio = 114;
-	}
-
-	/*
-	 * If requesting the GPIO above failed, it means, that the regulator got
-	 * probed and grabbed the GPIO, but we don't know, whether the sdhi
-	 * driver already uses the regulator. If it doesn't, we have to toggle
-	 * the GPIO ourselves, even though it is now owned by the fixed
-	 * regulator driver. We have to live with the race in case the driver
-	 * gets unloaded and the GPIO freed between these two steps.
-	 */
-	gpio_set_value(114, state);
-}
-
-static struct sh_mobile_sdhi_info sh_sdhi1_info = {
-	.tmio_flags	= TMIO_MMC_WRPROTECT_DISABLE | TMIO_MMC_HAS_IDLE_WAIT,
-	.tmio_caps	= MMC_CAP_NONREMOVABLE | MMC_CAP_SDIO_IRQ,
-	.tmio_ocr_mask	= MMC_VDD_32_33 | MMC_VDD_33_34,
-	.set_pwr	= ag5evm_sdhi1_set_pwr,
-};
-
-static struct resource sdhi1_resources[] = {
-	[0] = {
-		.name	= "SDHI1",
-		.start	= 0xee120000,
-		.end	= 0xee1200ff,
-		.flags	= IORESOURCE_MEM,
-	},
-	[1] = {
-		.name	= SH_MOBILE_SDHI_IRQ_CARD_DETECT,
-		.start	= gic_spi(87),
-		.flags	= IORESOURCE_IRQ,
-	},
-	[2] = {
-		.name	= SH_MOBILE_SDHI_IRQ_SDCARD,
-		.start	= gic_spi(88),
-		.flags	= IORESOURCE_IRQ,
-	},
-	[3] = {
-		.name	= SH_MOBILE_SDHI_IRQ_SDIO,
-		.start	= gic_spi(89),
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-static struct platform_device sdhi1_device = {
-	.name		= "sh_mobile_sdhi",
-	.id		= 1,
-	.dev		= {
-		.platform_data	= &sh_sdhi1_info,
-	},
-	.num_resources	= ARRAY_SIZE(sdhi1_resources),
-	.resource	= sdhi1_resources,
-};
-
-static struct platform_device *ag5evm_devices[] __initdata = {
-	&cn4_power,
-	&eth_device,
-	&keysc_device,
-	&fsi_device,
-	&mmc_device,
-	&irda_device,
-	&mipidsi0_device,
-	&lcdc0_device,
-	&sdhi0_device,
-	&sdhi1_device,
-};
-
-static unsigned long pin_pullup_conf[] = {
-	PIN_CONF_PACKED(PIN_CONFIG_BIAS_PULL_UP, 0),
-};
-
-static const struct pinctrl_map ag5evm_pinctrl_map[] = {
-	/* FSIA */
-	PIN_MAP_MUX_GROUP_DEFAULT("sh_fsi2.0", "pfc-sh73a0",
-				  "fsia_mclk_in", "fsia"),
-	PIN_MAP_MUX_GROUP_DEFAULT("sh_fsi2.0", "pfc-sh73a0",
-				  "fsia_sclk_in", "fsia"),
-	PIN_MAP_MUX_GROUP_DEFAULT("sh_fsi2.0", "pfc-sh73a0",
-				  "fsia_data_in", "fsia"),
-	PIN_MAP_MUX_GROUP_DEFAULT("sh_fsi2.0", "pfc-sh73a0",
-				  "fsia_data_out", "fsia"),
-	/* I2C2 & I2C3 */
-	PIN_MAP_MUX_GROUP_DEFAULT("i2c-sh_mobile.2", "pfc-sh73a0",
-				  "i2c2_0", "i2c2"),
-	PIN_MAP_MUX_GROUP_DEFAULT("i2c-sh_mobile.3", "pfc-sh73a0",
-				  "i2c3_0", "i2c3"),
-	/* IrDA */
-	PIN_MAP_MUX_GROUP_DEFAULT("sh_irda.0", "pfc-sh73a0",
-				  "irda_0", "irda"),
-	/* KEYSC */
-	PIN_MAP_MUX_GROUP_DEFAULT("sh_keysc.0", "pfc-sh73a0",
-				  "keysc_in8", "keysc"),
-	PIN_MAP_MUX_GROUP_DEFAULT("sh_keysc.0", "pfc-sh73a0",
-				  "keysc_out04", "keysc"),
-	PIN_MAP_MUX_GROUP_DEFAULT("sh_keysc.0", "pfc-sh73a0",
-				  "keysc_out5", "keysc"),
-	PIN_MAP_MUX_GROUP_DEFAULT("sh_keysc.0", "pfc-sh73a0",
-				  "keysc_out6_0", "keysc"),
-	PIN_MAP_MUX_GROUP_DEFAULT("sh_keysc.0", "pfc-sh73a0",
-				  "keysc_out7_0", "keysc"),
-	PIN_MAP_MUX_GROUP_DEFAULT("sh_keysc.0", "pfc-sh73a0",
-				  "keysc_out8_0", "keysc"),
-	PIN_MAP_MUX_GROUP_DEFAULT("sh_keysc.0", "pfc-sh73a0",
-				  "keysc_out9_2", "keysc"),
-	PIN_MAP_CONFIGS_GROUP_DEFAULT("sh_keysc.0", "pfc-sh73a0",
-				      "keysc_in8", pin_pullup_conf),
-	/* MMCIF */
-	PIN_MAP_MUX_GROUP_DEFAULT("sh_mmcif.0", "pfc-sh73a0",
-				  "mmc0_data8_0", "mmc0"),
-	PIN_MAP_MUX_GROUP_DEFAULT("sh_mmcif.0", "pfc-sh73a0",
-				  "mmc0_ctrl_0", "mmc0"),
-	PIN_MAP_CONFIGS_PIN_DEFAULT("sh_mmcif.0", "pfc-sh73a0",
-				    "PORT279", pin_pullup_conf),
-	PIN_MAP_CONFIGS_GROUP_DEFAULT("sh_mmcif.0", "pfc-sh73a0",
-				      "mmc0_data8_0", pin_pullup_conf),
-	/* SCIFA2 */
-	PIN_MAP_MUX_GROUP_DEFAULT("sh-sci.2", "pfc-sh73a0",
-				  "scifa2_data_0", "scifa2"),
-	PIN_MAP_MUX_GROUP_DEFAULT("sh-sci.2", "pfc-sh73a0",
-				  "scifa2_ctrl_0", "scifa2"),
-	/* SDHI0 (CN15 [SD I/F]) */
-	PIN_MAP_MUX_GROUP_DEFAULT("sh_mobile_sdhi.0", "pfc-sh73a0",
-				  "sdhi0_data4", "sdhi0"),
-	PIN_MAP_MUX_GROUP_DEFAULT("sh_mobile_sdhi.0", "pfc-sh73a0",
-				  "sdhi0_ctrl", "sdhi0"),
-	PIN_MAP_MUX_GROUP_DEFAULT("sh_mobile_sdhi.0", "pfc-sh73a0",
-				  "sdhi0_wp", "sdhi0"),
-	/* SDHI1 (CN4 [WLAN I/F]) */
-	PIN_MAP_MUX_GROUP_DEFAULT("sh_mobile_sdhi.1", "pfc-sh73a0",
-				  "sdhi1_data4", "sdhi1"),
-	PIN_MAP_MUX_GROUP_DEFAULT("sh_mobile_sdhi.1", "pfc-sh73a0",
-				  "sdhi1_ctrl", "sdhi1"),
-	PIN_MAP_CONFIGS_GROUP_DEFAULT("sh_mobile_sdhi.1", "pfc-sh73a0",
-				      "sdhi1_data4", pin_pullup_conf),
-	PIN_MAP_CONFIGS_PIN_DEFAULT("sh_mobile_sdhi.1", "pfc-sh73a0",
-				    "PORT263", pin_pullup_conf),
-};
-
-static void __init ag5evm_init(void)
-{
-	regulator_register_always_on(0, "fixed-1.8V", fixed1v8_power_consumers,
-				     ARRAY_SIZE(fixed1v8_power_consumers), 1800000);
-	regulator_register_always_on(1, "fixed-2.8V", fixed2v8_power_consumers,
-				     ARRAY_SIZE(fixed2v8_power_consumers), 3300000);
-	regulator_register_fixed(3, dummy_supplies, ARRAY_SIZE(dummy_supplies));
-
-	pinctrl_register_mappings(ag5evm_pinctrl_map,
-				  ARRAY_SIZE(ag5evm_pinctrl_map));
-	sh73a0_pinmux_init();
-
-	/* enable MMCIF */
-	gpio_request_one(208, GPIOF_OUT_INIT_HIGH, NULL); /* Reset */
-
-	/* enable SMSC911X */
-	gpio_request_one(144, GPIOF_IN, NULL); /* PINTA2 */
-	gpio_request_one(145, GPIOF_OUT_INIT_HIGH, NULL); /* RESET */
-
-	/* LCD panel */
-	gpio_request_one(217, GPIOF_OUT_INIT_LOW, NULL); /* RESET */
-	mdelay(1);
-	gpio_set_value(217, 1);
-	mdelay(100);
-
-	/* LCD backlight controller */
-	gpio_request_one(235, GPIOF_OUT_INIT_LOW, NULL); /* RESET */
-	lcd_backlight_set_brightness(0);
-
-#ifdef CONFIG_CACHE_L2X0
-	/* Shared attribute override enable, 64K*8way */
-	l2x0_init(IOMEM(0xf0100000), 0x00460000, 0xc2000fff);
-#endif
-	sh73a0_add_standard_devices();
-	platform_add_devices(ag5evm_devices, ARRAY_SIZE(ag5evm_devices));
-}
-
-MACHINE_START(AG5EVM, "ag5evm")
-	.smp		= smp_ops(sh73a0_smp_ops),
-	.map_io		= sh73a0_map_io,
-	.init_early	= sh73a0_add_early_devices,
-	.nr_irqs	= NR_IRQS_LEGACY,
-	.init_irq	= sh73a0_init_irq,
-	.init_machine	= ag5evm_init,
-	.init_late	= shmobile_init_late,
-	.init_time	= sh73a0_earlytimer_init,
-MACHINE_END
diff --git a/arch/arm/mach-shmobile/board-ape6evm-reference.c b/arch/arm/mach-shmobile/board-ape6evm-reference.c
new file mode 100644
index 000000000000..a23fa714f7ac
--- /dev/null
+++ b/arch/arm/mach-shmobile/board-ape6evm-reference.c
@@ -0,0 +1,63 @@
+/*
+ * APE6EVM board support
+ *
+ * Copyright (C) 2013  Renesas Solutions Corp.
+ * Copyright (C) 2013  Magnus Damm
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
+ */
+
+#include <linux/gpio.h>
+#include <linux/kernel.h>
+#include <linux/of_platform.h>
+#include <linux/pinctrl/machine.h>
+#include <linux/platform_device.h>
+#include <linux/sh_clk.h>
+#include <mach/common.h>
+#include <mach/r8a73a4.h>
+#include <asm/mach-types.h>
+#include <asm/mach/arch.h>
+
+static void __init ape6evm_add_standard_devices(void)
+{
+
+	struct clk *parent;
+	struct clk *mp;
+
+	r8a73a4_clock_init();
+
+	/* MP clock parent = extal2 */
+	parent      = clk_get(NULL, "extal2");
+	mp          = clk_get(NULL, "mp");
+	BUG_ON(IS_ERR(parent) || IS_ERR(mp));
+
+	clk_set_parent(mp, parent);
+	clk_put(parent);
+	clk_put(mp);
+
+	r8a73a4_add_dt_devices();
+	of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
+	platform_device_register_simple("cpufreq-cpu0", -1, NULL, 0);
+}
+
+static const char *ape6evm_boards_compat_dt[] __initdata = {
+	"renesas,ape6evm-reference",
+	NULL,
+};
+
+DT_MACHINE_START(APE6EVM_DT, "ape6evm")
+	.init_early	= r8a73a4_init_delay,
+	.init_machine	= ape6evm_add_standard_devices,
+	.dt_compat	= ape6evm_boards_compat_dt,
+MACHINE_END
diff --git a/arch/arm/mach-shmobile/board-ape6evm.c b/arch/arm/mach-shmobile/board-ape6evm.c
index 5eb0caa6a7d0..24b87eea9da3 100644
--- a/arch/arm/mach-shmobile/board-ape6evm.c
+++ b/arch/arm/mach-shmobile/board-ape6evm.c
@@ -19,9 +19,14 @@
  */
 
 #include <linux/gpio.h>
+#include <linux/gpio_keys.h>
+#include <linux/input.h>
 #include <linux/interrupt.h>
-#include <linux/irqchip.h>
 #include <linux/kernel.h>
+#include <linux/mfd/tmio.h>
+#include <linux/mmc/host.h>
+#include <linux/mmc/sh_mmcif.h>
+#include <linux/mmc/sh_mobile_sdhi.h>
 #include <linux/pinctrl/machine.h>
 #include <linux/platform_device.h>
 #include <linux/regulator/fixed.h>
@@ -34,6 +39,58 @@
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
 
+/* LEDS */
+static struct gpio_led ape6evm_leds[] = {
+	{
+		.name		= "gnss-en",
+		.gpio		= 28,
+		.default_state	= LEDS_GPIO_DEFSTATE_OFF,
+	}, {
+		.name		= "nfc-nrst",
+		.gpio		= 126,
+		.default_state	= LEDS_GPIO_DEFSTATE_OFF,
+	}, {
+		.name		= "gnss-nrst",
+		.gpio		= 132,
+		.default_state	= LEDS_GPIO_DEFSTATE_OFF,
+	}, {
+		.name		= "bt-wakeup",
+		.gpio		= 232,
+		.default_state	= LEDS_GPIO_DEFSTATE_OFF,
+	}, {
+		.name		= "strobe",
+		.gpio		= 250,
+		.default_state	= LEDS_GPIO_DEFSTATE_OFF,
+	}, {
+		.name		= "bbresetout",
+		.gpio		= 288,
+		.default_state	= LEDS_GPIO_DEFSTATE_OFF,
+	},
+};
+
+static __initdata struct gpio_led_platform_data ape6evm_leds_pdata = {
+	.leds		= ape6evm_leds,
+	.num_leds	= ARRAY_SIZE(ape6evm_leds),
+};
+
+/* GPIO KEY */
+#define GPIO_KEY(c, g, d, ...) \
+	{ .code = c, .gpio = g, .desc = d, .active_low = 1 }
+
+static struct gpio_keys_button gpio_buttons[] = {
+	GPIO_KEY(KEY_0,			324,	"S16"),
+	GPIO_KEY(KEY_MENU,		325,	"S17"),
+	GPIO_KEY(KEY_HOME,		326,	"S18"),
+	GPIO_KEY(KEY_BACK,		327,	"S19"),
+	GPIO_KEY(KEY_VOLUMEUP,		328,	"S20"),
+	GPIO_KEY(KEY_VOLUMEDOWN,	329,	"S21"),
+};
+
+static struct __initdata gpio_keys_platform_data ape6evm_keys_pdata = {
+	.buttons	= gpio_buttons,
+	.nbuttons	= ARRAY_SIZE(gpio_buttons),
+};
+
 /* Dummy supplies, where voltage doesn't matter */
 static struct regulator_consumer_supply dummy_supplies[] = {
 	REGULATOR_SUPPLY("vddvario", "smsc911x"),
@@ -41,7 +98,7 @@ static struct regulator_consumer_supply dummy_supplies[] = {
 };
 
 /* SMSC LAN9220 */
-static const struct resource lan9220_res[] = {
+static const struct resource lan9220_res[] __initconst = {
 	DEFINE_RES_MEM(0x08000000, 0x1000),
 	{
 		.start	= irq_pin(40), /* IRQ40 */
@@ -49,19 +106,83 @@ static const struct resource lan9220_res[] = {
 	},
 };
 
-static const struct smsc911x_platform_config lan9220_data = {
+static const struct smsc911x_platform_config lan9220_data __initconst = {
 	.flags		= SMSC911X_USE_32BIT,
 	.irq_type	= SMSC911X_IRQ_TYPE_PUSH_PULL,
 	.irq_polarity	= SMSC911X_IRQ_POLARITY_ACTIVE_HIGH,
 };
 
-static const struct pinctrl_map ape6evm_pinctrl_map[] = {
+/*
+ * On APE6EVM power is supplied to MMCIF by a tps80032 regulator. For now we
+ * model a VDD supply to MMCIF, using a fixed 3.3V regulator. Also use the
+ * static power supply for SDHI0 and SDHI1, whereas SDHI0's VccQ is also
+ * supplied by the same tps80032 regulator and thus can also be adjusted
+ * dynamically.
+ */
+static struct regulator_consumer_supply fixed3v3_power_consumers[] =
+{
+	REGULATOR_SUPPLY("vmmc", "sh_mmcif.0"),
+	REGULATOR_SUPPLY("vmmc", "sh_mobile_sdhi.0"),
+	REGULATOR_SUPPLY("vmmc", "sh_mobile_sdhi.1"),
+};
+
+/* MMCIF */
+static const struct sh_mmcif_plat_data mmcif0_pdata __initconst = {
+	.caps		= MMC_CAP_8_BIT_DATA | MMC_CAP_NONREMOVABLE,
+};
+
+static const struct resource mmcif0_resources[] __initconst = {
+	DEFINE_RES_MEM_NAMED(0xee200000, 0x100, "MMCIF0"),
+	DEFINE_RES_IRQ(gic_spi(169)),
+};
+
+/* SDHI0 */
+static const struct sh_mobile_sdhi_info sdhi0_pdata __initconst = {
+	.tmio_flags	= TMIO_MMC_HAS_IDLE_WAIT | TMIO_MMC_WRPROTECT_DISABLE,
+	.tmio_caps	= MMC_CAP_SD_HIGHSPEED | MMC_CAP_SDIO_IRQ,
+};
+
+static const struct resource sdhi0_resources[] __initconst = {
+	DEFINE_RES_MEM_NAMED(0xee100000, 0x100, "SDHI0"),
+	DEFINE_RES_IRQ(gic_spi(165)),
+};
+
+/* SDHI1 */
+static const struct sh_mobile_sdhi_info sdhi1_pdata __initconst = {
+	.tmio_flags	= TMIO_MMC_HAS_IDLE_WAIT | TMIO_MMC_WRPROTECT_DISABLE,
+	.tmio_caps	= MMC_CAP_SD_HIGHSPEED | MMC_CAP_SDIO_IRQ |
+			  MMC_CAP_NEEDS_POLL,
+};
+
+static const struct resource sdhi1_resources[] __initconst = {
+	DEFINE_RES_MEM_NAMED(0xee120000, 0x100, "SDHI1"),
+	DEFINE_RES_IRQ(gic_spi(166)),
+};
+
+static const struct pinctrl_map ape6evm_pinctrl_map[] __initconst = {
 	/* SCIFA0 console */
 	PIN_MAP_MUX_GROUP_DEFAULT("sh-sci.0", "pfc-r8a73a4",
 				  "scifa0_data", "scifa0"),
 	/* SMSC */
 	PIN_MAP_MUX_GROUP_DEFAULT("smsc911x", "pfc-r8a73a4",
 				  "irqc_irq40", "irqc"),
+	/* MMCIF0 */
+	PIN_MAP_MUX_GROUP_DEFAULT("sh_mmcif.0", "pfc-r8a73a4",
+				  "mmc0_data8", "mmc0"),
+	PIN_MAP_MUX_GROUP_DEFAULT("sh_mmcif.0", "pfc-r8a73a4",
+				  "mmc0_ctrl", "mmc0"),
+	/* SDHI0: uSD: no WP */
+	PIN_MAP_MUX_GROUP_DEFAULT("sh_mobile_sdhi.0", "pfc-r8a73a4",
+				  "sdhi0_data4", "sdhi0"),
+	PIN_MAP_MUX_GROUP_DEFAULT("sh_mobile_sdhi.0", "pfc-r8a73a4",
+				  "sdhi0_ctrl", "sdhi0"),
+	PIN_MAP_MUX_GROUP_DEFAULT("sh_mobile_sdhi.0", "pfc-r8a73a4",
+				  "sdhi0_cd", "sdhi0"),
+	/* SDHI1 */
+	PIN_MAP_MUX_GROUP_DEFAULT("sh_mobile_sdhi.1", "pfc-r8a73a4",
+				  "sdhi1_data4", "sdhi1"),
+	PIN_MAP_MUX_GROUP_DEFAULT("sh_mobile_sdhi.1", "pfc-r8a73a4",
+				  "sdhi1_ctrl", "sdhi1"),
 };
 
 static void __init ape6evm_add_standard_devices(void)
@@ -94,6 +215,23 @@ static void __init ape6evm_add_standard_devices(void)
 	platform_device_register_resndata(&platform_bus, "smsc911x", -1,
 					  lan9220_res, ARRAY_SIZE(lan9220_res),
 					  &lan9220_data, sizeof(lan9220_data));
+	regulator_register_always_on(1, "fixed-3.3V", fixed3v3_power_consumers,
+				     ARRAY_SIZE(fixed3v3_power_consumers), 3300000);
+	platform_device_register_resndata(&platform_bus, "sh_mmcif", 0,
+					  mmcif0_resources, ARRAY_SIZE(mmcif0_resources),
+					  &mmcif0_pdata, sizeof(mmcif0_pdata));
+	platform_device_register_resndata(&platform_bus, "sh_mobile_sdhi", 0,
+					  sdhi0_resources, ARRAY_SIZE(sdhi0_resources),
+					  &sdhi0_pdata, sizeof(sdhi0_pdata));
+	platform_device_register_resndata(&platform_bus, "sh_mobile_sdhi", 1,
+					  sdhi1_resources, ARRAY_SIZE(sdhi1_resources),
+					  &sdhi1_pdata, sizeof(sdhi1_pdata));
+	platform_device_register_data(&platform_bus, "gpio-keys", -1,
+				      &ape6evm_keys_pdata,
+				      sizeof(ape6evm_keys_pdata));
+	platform_device_register_data(&platform_bus, "leds-gpio", -1,
+				      &ape6evm_leds_pdata,
+				      sizeof(ape6evm_leds_pdata));
 }
 
 static const char *ape6evm_boards_compat_dt[] __initdata = {
@@ -102,8 +240,7 @@ static const char *ape6evm_boards_compat_dt[] __initdata = {
 };
 
 DT_MACHINE_START(APE6EVM_DT, "ape6evm")
-	.init_irq	= irqchip_init,
-	.init_time	= shmobile_timer_init,
+	.init_early	= r8a73a4_init_delay,
 	.init_machine	= ape6evm_add_standard_devices,
 	.dt_compat	= ape6evm_boards_compat_dt,
 MACHINE_END
diff --git a/arch/arm/mach-shmobile/board-armadillo800eva-reference.c b/arch/arm/mach-shmobile/board-armadillo800eva-reference.c
index 03b85fec2ddb..57d1a78367b6 100644
--- a/arch/arm/mach-shmobile/board-armadillo800eva-reference.c
+++ b/arch/arm/mach-shmobile/board-armadillo800eva-reference.c
@@ -24,7 +24,6 @@
 #include <linux/kernel.h>
 #include <linux/gpio.h>
 #include <linux/io.h>
-#include <linux/pinctrl/machine.h>
 #include <mach/common.h>
 #include <mach/r8a7740.h>
 #include <asm/mach/arch.h>
@@ -119,12 +118,6 @@
  *	usbhsf_power_ctrl()
  */
 
-static const struct pinctrl_map eva_pinctrl_map[] = {
-	/* SCIFA1 */
-	PIN_MAP_MUX_GROUP_DEFAULT("sh-sci.1", "pfc-r8a7740",
-				  "scifa1_data", "scifa1"),
-};
-
 static void __init eva_clock_init(void)
 {
 	struct clk *system	= clk_get(NULL, "system_clk");
@@ -165,35 +158,26 @@ clock_error:
  */
 static void __init eva_init(void)
 {
-
 	r8a7740_clock_init(MD_CK0 | MD_CK2);
 	eva_clock_init();
 
-	pinctrl_register_mappings(eva_pinctrl_map, ARRAY_SIZE(eva_pinctrl_map));
-	r8a7740_pinmux_init();
-
 	r8a7740_meram_workaround();
 
-	/*
-	 * Touchscreen
-	 * TODO: Move reset GPIO over to .dts when we can reference it
-	 */
-	gpio_request_one(166, GPIOF_OUT_INIT_HIGH, NULL); /* TP_RST_B */
-
 #ifdef CONFIG_CACHE_L2X0
 	/* Early BRESP enable, Shared attribute override enable, 32K*8way */
 	l2x0_init(IOMEM(0xf0002000), 0x40440000, 0x82000fff);
 #endif
 
 	r8a7740_add_standard_devices_dt();
+
 	r8a7740_pm_init();
 }
 
 #define RESCNT2 IOMEM(0xe6188020)
-static void eva_restart(char mode, const char *cmd)
+static void eva_restart(enum reboot_mode mode, const char *cmd)
 {
 	/* Do soft power on reset */
-	writel((1 << 31), RESCNT2);
+	writel(1 << 31, RESCNT2);
 }
 
 static const char *eva_boards_compat_dt[] __initdata = {
@@ -206,7 +190,6 @@ DT_MACHINE_START(ARMADILLO800EVA_DT, "armadillo800eva-reference")
 	.init_early	= r8a7740_init_delay,
 	.init_irq	= r8a7740_init_irq_of,
 	.init_machine	= eva_init,
-	.init_time	= shmobile_timer_init,
 	.init_late	= shmobile_init_late,
 	.dt_compat	= eva_boards_compat_dt,
 	.restart	= eva_restart,
diff --git a/arch/arm/mach-shmobile/board-armadillo800eva.c b/arch/arm/mach-shmobile/board-armadillo800eva.c
index c5be60d85e4b..7f8f6076d360 100644
--- a/arch/arm/mach-shmobile/board-armadillo800eva.c
+++ b/arch/arm/mach-shmobile/board-armadillo800eva.c
@@ -31,6 +31,8 @@
 #include <linux/gpio_keys.h>
 #include <linux/regulator/driver.h>
 #include <linux/pinctrl/machine.h>
+#include <linux/platform_data/pwm-renesas-tpu.h>
+#include <linux/pwm_backlight.h>
 #include <linux/regulator/fixed.h>
 #include <linux/regulator/gpio-regulator.h>
 #include <linux/regulator/machine.h>
@@ -358,7 +360,6 @@ static struct platform_device usbhsf_device = {
 static struct sh_eth_plat_data sh_eth_platdata = {
 	.phy			= 0x00, /* LAN8710A */
 	.edmac_endian		= EDMAC_LITTLE_ENDIAN,
-	.register_type		= SH_ETH_REG_GIGABIT,
 	.phy_interface		= PHY_INTERFACE_MODE_MII,
 };
 
@@ -387,7 +388,50 @@ static struct platform_device sh_eth_device = {
 	.num_resources = ARRAY_SIZE(sh_eth_resources),
 };
 
-/* LCDC */
+/* PWM */
+static struct resource pwm_resources[] = {
+	[0] = {
+		.start = 0xe6600000,
+		.end = 0xe66000ff,
+		.flags = IORESOURCE_MEM,
+	},
+};
+
+static struct tpu_pwm_platform_data pwm_device_data = {
+	.channels[2] = {
+		.polarity = PWM_POLARITY_INVERSED,
+	}
+};
+
+static struct platform_device pwm_device = {
+	.name = "renesas-tpu-pwm",
+	.id = -1,
+	.dev = {
+		.platform_data = &pwm_device_data,
+	},
+	.num_resources = ARRAY_SIZE(pwm_resources),
+	.resource = pwm_resources,
+};
+
+static struct pwm_lookup pwm_lookup[] = {
+	PWM_LOOKUP("renesas-tpu-pwm", 2, "pwm-backlight.0", NULL),
+};
+
+/* LCDC and backlight */
+static struct platform_pwm_backlight_data pwm_backlight_data = {
+	.lth_brightness = 50,
+	.max_brightness = 255,
+	.dft_brightness = 255,
+	.pwm_period_ns = 33333, /* 30kHz */
+};
+
+static struct platform_device pwm_backlight_device = {
+	.name = "pwm-backlight",
+	.dev = {
+		.platform_data = &pwm_backlight_data,
+	},
+};
+
 static struct fb_videomode lcdc0_mode = {
 	.name		= "AMPIER/AM-800480",
 	.xres		= 800,
@@ -679,15 +723,6 @@ static struct platform_device vcc_sdhi1 = {
 };
 
 /* SDHI0 */
-/*
- * FIXME
- *
- * It use polling mode here, since
- * CD (= Card Detect) pin is not connected to SDHI0_CD.
- * We can use IRQ31 as card detect irq,
- * but it needs chattering removal operation
- */
-#define IRQ31	irq_pin(31)
 static struct sh_mobile_sdhi_info sdhi0_info = {
 	.dma_slave_tx	= SHDMA_SLAVE_SDHI0_TX,
 	.dma_slave_rx	= SHDMA_SLAVE_SDHI0_RX,
@@ -788,6 +823,8 @@ static struct sh_mmcif_plat_data sh_mmcif_plat = {
 	.caps		= MMC_CAP_4_BIT_DATA |
 			  MMC_CAP_8_BIT_DATA |
 			  MMC_CAP_NONREMOVABLE,
+	.slave_id_tx	= SHDMA_SLAVE_MMCIF_TX,
+	.slave_id_rx	= SHDMA_SLAVE_MMCIF_RX,
 };
 
 static struct resource sh_mmcif_resources[] = {
@@ -1030,6 +1067,8 @@ static struct i2c_board_info i2c2_devices[] = {
  */
 static struct platform_device *eva_devices[] __initdata = {
 	&lcdc0_device,
+	&pwm_device,
+	&pwm_backlight_device,
 	&gpio_keys_device,
 	&sh_eth_device,
 	&vcc_sdhi0,
@@ -1069,9 +1108,9 @@ static const struct pinctrl_map eva_pinctrl_map[] = {
 	PIN_MAP_MUX_GROUP_DEFAULT("asoc-simple-card.1", "pfc-r8a7740",
 				  "fsib_mclk_in", "fsib"),
 	/* GETHER */
-	PIN_MAP_MUX_GROUP_DEFAULT("sh-eth", "pfc-r8a7740",
+	PIN_MAP_MUX_GROUP_DEFAULT("r8a7740-gether", "pfc-r8a7740",
 				  "gether_mii", "gether"),
-	PIN_MAP_MUX_GROUP_DEFAULT("sh-eth", "pfc-r8a7740",
+	PIN_MAP_MUX_GROUP_DEFAULT("r8a7740-gether", "pfc-r8a7740",
 				  "gether_int", "gether"),
 	/* HDMI */
 	PIN_MAP_MUX_GROUP_DEFAULT("sh-mobile-hdmi", "pfc-r8a7740",
@@ -1101,6 +1140,9 @@ static const struct pinctrl_map eva_pinctrl_map[] = {
 	/* ST1232 */
 	PIN_MAP_MUX_GROUP_DEFAULT("0-0055", "pfc-r8a7740",
 				  "intc_irq10", "intc"),
+	/* TPU0 */
+	PIN_MAP_MUX_GROUP_DEFAULT("renesas-tpu-pwm", "pfc-r8a7740",
+				  "tpu0_to2_1", "tpu0"),
 	/* USBHS */
 	PIN_MAP_MUX_GROUP_DEFAULT("renesas_usbhs", "pfc-r8a7740",
 				  "intc_irq7_1", "intc"),
@@ -1154,13 +1196,13 @@ static void __init eva_init(void)
 				     ARRAY_SIZE(fixed3v3_power_consumers), 3300000);
 
 	pinctrl_register_mappings(eva_pinctrl_map, ARRAY_SIZE(eva_pinctrl_map));
+	pwm_add_table(pwm_lookup, ARRAY_SIZE(pwm_lookup));
 
 	r8a7740_pinmux_init();
 	r8a7740_meram_workaround();
 
 	/* LCDC0 */
 	gpio_request_one(61, GPIOF_OUT_INIT_HIGH, NULL); /* LCDDON */
-	gpio_request_one(202, GPIOF_OUT_INIT_LOW, NULL); /* LCD0_LED_CONT */
 
 	/* GETHER */
 	gpio_request_one(18, GPIOF_OUT_INIT_HIGH, NULL); /* PHY_RST */
@@ -1271,7 +1313,7 @@ static const char *eva_boards_compat_dt[] __initdata = {
 DT_MACHINE_START(ARMADILLO800EVA_DT, "armadillo800eva")
 	.map_io		= r8a7740_map_io,
 	.init_early	= eva_add_early_devices,
-	.init_irq	= r8a7740_init_irq,
+	.init_irq	= r8a7740_init_irq_of,
 	.init_machine	= eva_init,
 	.init_late	= shmobile_init_late,
 	.init_time	= eva_earlytimer_init,
diff --git a/arch/arm/mach-shmobile/board-bockw-reference.c b/arch/arm/mach-shmobile/board-bockw-reference.c
new file mode 100644
index 000000000000..1a7c893e1a52
--- /dev/null
+++ b/arch/arm/mach-shmobile/board-bockw-reference.c
@@ -0,0 +1,61 @@
+/*
+ * Bock-W board support
+ *
+ * Copyright (C) 2013  Renesas Solutions Corp.
+ * Copyright (C) 2013  Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
+ */
+
+#include <linux/of_platform.h>
+#include <linux/pinctrl/machine.h>
+#include <mach/common.h>
+#include <mach/r8a7778.h>
+#include <asm/mach/arch.h>
+
+/*
+ *	see board-bock.c for checking detail of dip-switch
+ */
+
+static const struct pinctrl_map bockw_pinctrl_map[] = {
+	/* SCIF0 */
+	PIN_MAP_MUX_GROUP_DEFAULT("sh-sci.0", "pfc-r8a7778",
+				  "scif0_data_a", "scif0"),
+	PIN_MAP_MUX_GROUP_DEFAULT("sh-sci.0", "pfc-r8a7778",
+				  "scif0_ctrl", "scif0"),
+};
+
+static void __init bockw_init(void)
+{
+	r8a7778_clock_init();
+
+	pinctrl_register_mappings(bockw_pinctrl_map,
+				  ARRAY_SIZE(bockw_pinctrl_map));
+	r8a7778_pinmux_init();
+	r8a7778_add_dt_devices();
+
+	of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
+}
+
+static const char *bockw_boards_compat_dt[] __initdata = {
+	"renesas,bockw-reference",
+	NULL,
+};
+
+DT_MACHINE_START(BOCKW_DT, "bockw")
+	.init_early	= r8a7778_init_delay,
+	.init_irq	= r8a7778_init_irq_dt,
+	.init_machine	= bockw_init,
+	.dt_compat	= bockw_boards_compat_dt,
+MACHINE_END
diff --git a/arch/arm/mach-shmobile/board-bockw.c b/arch/arm/mach-shmobile/board-bockw.c
index 3354a85c90f7..6b9faf3908f7 100644
--- a/arch/arm/mach-shmobile/board-bockw.c
+++ b/arch/arm/mach-shmobile/board-bockw.c
@@ -3,6 +3,7 @@
  *
  * Copyright (C) 2013  Renesas Solutions Corp.
  * Copyright (C) 2013  Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
+ * Copyright (C) 2013  Cogent Embedded, Inc.
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -20,14 +21,18 @@
 
 #include <linux/mfd/tmio.h>
 #include <linux/mmc/host.h>
+#include <linux/mmc/sh_mobile_sdhi.h>
+#include <linux/mmc/sh_mmcif.h>
 #include <linux/mtd/partitions.h>
 #include <linux/pinctrl/machine.h>
+#include <linux/platform_data/usb-rcar-phy.h>
 #include <linux/platform_device.h>
 #include <linux/regulator/fixed.h>
 #include <linux/regulator/machine.h>
 #include <linux/smsc911x.h>
 #include <linux/spi/spi.h>
 #include <linux/spi/flash.h>
+#include <media/soc_camera.h>
 #include <mach/common.h>
 #include <mach/irqs.h>
 #include <mach/r8a7778.h>
@@ -64,32 +69,41 @@ static struct regulator_consumer_supply dummy_supplies[] = {
 	REGULATOR_SUPPLY("vdd33a", "smsc911x"),
 };
 
-static struct smsc911x_platform_config smsc911x_data = {
+static struct smsc911x_platform_config smsc911x_data __initdata = {
 	.irq_polarity	= SMSC911X_IRQ_POLARITY_ACTIVE_LOW,
 	.irq_type	= SMSC911X_IRQ_TYPE_PUSH_PULL,
 	.flags		= SMSC911X_USE_32BIT,
 	.phy_interface	= PHY_INTERFACE_MODE_MII,
 };
 
-static struct resource smsc911x_resources[] = {
+static struct resource smsc911x_resources[] __initdata = {
 	DEFINE_RES_MEM(0x18300000, 0x1000),
 	DEFINE_RES_IRQ(irq_pin(0)), /* IRQ 0 */
 };
 
 /* USB */
+static struct resource usb_phy_resources[] __initdata = {
+	DEFINE_RES_MEM(0xffe70800, 0x100),
+	DEFINE_RES_MEM(0xffe76000, 0x100),
+};
+
 static struct rcar_phy_platform_data usb_phy_platform_data __initdata;
 
 /* SDHI */
-static struct sh_mobile_sdhi_info sdhi0_info = {
+static struct sh_mobile_sdhi_info sdhi0_info __initdata = {
 	.tmio_caps	= MMC_CAP_SD_HIGHSPEED,
 	.tmio_ocr_mask	= MMC_VDD_165_195 | MMC_VDD_32_33 | MMC_VDD_33_34,
 	.tmio_flags	= TMIO_MMC_HAS_IDLE_WAIT,
 };
 
+static struct resource sdhi0_resources[] __initdata = {
+	DEFINE_RES_MEM(0xFFE4C000, 0x100),
+	DEFINE_RES_IRQ(gic_iid(0x77)),
+};
+
 static struct sh_eth_plat_data ether_platform_data __initdata = {
 	.phy		= 0x01,
 	.edmac_endian	= EDMAC_LITTLE_ENDIAN,
-	.register_type	= SH_ETH_REG_FAST_RCAR,
 	.phy_interface	= PHY_INTERFACE_MODE_RMII,
 	/*
 	 * Although the LINK signal is available on the board, it's connected to
@@ -135,7 +149,12 @@ static struct spi_board_info spi_board_info[] __initdata = {
 };
 
 /* MMC */
-static struct sh_mmcif_plat_data sh_mmcif_plat = {
+static struct resource mmc_resources[] __initdata = {
+	DEFINE_RES_MEM(0xffe4e000, 0x100),
+	DEFINE_RES_IRQ(gic_iid(0x5d)),
+};
+
+static struct sh_mmcif_plat_data sh_mmcif_plat __initdata = {
 	.sup_pclk	= 0,
 	.ocr		= MMC_VDD_165_195 | MMC_VDD_32_33 | MMC_VDD_33_34,
 	.caps		= MMC_CAP_4_BIT_DATA |
@@ -143,6 +162,25 @@ static struct sh_mmcif_plat_data sh_mmcif_plat = {
 			  MMC_CAP_NEEDS_POLL,
 };
 
+static struct rcar_vin_platform_data vin_platform_data __initdata = {
+	.flags	= RCAR_VIN_BT656,
+};
+
+/* In the default configuration both decoders reside on I2C bus 0 */
+#define BOCKW_CAMERA(idx)						\
+static struct i2c_board_info camera##idx##_info = {			\
+	I2C_BOARD_INFO("ml86v7667", 0x41 + 2 * (idx)),			\
+};									\
+									\
+static struct soc_camera_link iclink##idx##_ml86v7667 __initdata = {	\
+	.bus_id		= idx,						\
+	.i2c_adapter_id	= 0,						\
+	.board_info	= &camera##idx##_info,				\
+}
+
+BOCKW_CAMERA(0);
+BOCKW_CAMERA(1);
+
 static const struct pinctrl_map bockw_pinctrl_map[] = {
 	/* Ether */
 	PIN_MAP_MUX_GROUP_DEFAULT("r8a777x-ether", "pfc-r8a7778",
@@ -174,6 +212,16 @@ static const struct pinctrl_map bockw_pinctrl_map[] = {
 				  "sdhi0_cd", "sdhi0"),
 	PIN_MAP_MUX_GROUP_DEFAULT("sh_mobile_sdhi.0", "pfc-r8a7778",
 				  "sdhi0_wp", "sdhi0"),
+	/* VIN0 */
+	PIN_MAP_MUX_GROUP_DEFAULT("r8a7778-vin.0", "pfc-r8a7778",
+				  "vin0_clk", "vin0"),
+	PIN_MAP_MUX_GROUP_DEFAULT("r8a7778-vin.0", "pfc-r8a7778",
+				  "vin0_data8", "vin0"),
+	/* VIN1 */
+	PIN_MAP_MUX_GROUP_DEFAULT("r8a7778-vin.1", "pfc-r8a7778",
+				  "vin1_clk", "vin1"),
+	PIN_MAP_MUX_GROUP_DEFAULT("r8a7778-vin.1", "pfc-r8a7778",
+				  "vin1_data8", "vin1"),
 };
 
 #define FPGA	0x18200000
@@ -187,11 +235,17 @@ static void __init bockw_init(void)
 	r8a7778_clock_init();
 	r8a7778_init_irq_extpin(1);
 	r8a7778_add_standard_devices();
-	r8a7778_add_usb_phy_device(&usb_phy_platform_data);
 	r8a7778_add_ether_device(&ether_platform_data);
-	r8a7778_add_i2c_device(0);
-	r8a7778_add_hspi_device(0);
-	r8a7778_add_mmc_device(&sh_mmcif_plat);
+	r8a7778_add_vin_device(0, &vin_platform_data);
+	/* VIN1 has a pin conflict with Ether */
+	if (!IS_ENABLED(CONFIG_SH_ETH))
+		r8a7778_add_vin_device(1, &vin_platform_data);
+	platform_device_register_data(&platform_bus, "soc-camera-pdrv", 0,
+				      &iclink0_ml86v7667,
+				      sizeof(iclink0_ml86v7667));
+	platform_device_register_data(&platform_bus, "soc-camera-pdrv", 1,
+				      &iclink1_ml86v7667,
+				      sizeof(iclink1_ml86v7667));
 
 	i2c_register_board_info(0, i2c0_devices,
 				ARRAY_SIZE(i2c0_devices));
@@ -201,6 +255,19 @@ static void __init bockw_init(void)
 				  ARRAY_SIZE(bockw_pinctrl_map));
 	r8a7778_pinmux_init();
 
+	platform_device_register_resndata(
+		&platform_bus, "sh_mmcif", -1,
+		mmc_resources, ARRAY_SIZE(mmc_resources),
+		&sh_mmcif_plat, sizeof(struct sh_mmcif_plat_data));
+
+	platform_device_register_resndata(
+		&platform_bus, "rcar_usb_phy", -1,
+		usb_phy_resources,
+		ARRAY_SIZE(usb_phy_resources),
+		&usb_phy_platform_data,
+		sizeof(struct rcar_phy_platform_data));
+
+
 	/* for SMSC */
 	base = ioremap_nocache(FPGA, SZ_1M);
 	if (base) {
@@ -236,7 +303,10 @@ static void __init bockw_init(void)
 		iowrite32(ioread32(base + PUPR4) | (3 << 26), base + PUPR4);
 		iounmap(base);
 
-		r8a7778_sdhi_init(0, &sdhi0_info);
+		platform_device_register_resndata(
+			&platform_bus, "sh_mobile_sdhi", 0,
+			sdhi0_resources, ARRAY_SIZE(sdhi0_resources),
+			&sdhi0_info, sizeof(struct sh_mobile_sdhi_info));
 	}
 }
 
@@ -249,7 +319,6 @@ DT_MACHINE_START(BOCKW_DT, "bockw")
 	.init_early	= r8a7778_init_delay,
 	.init_irq	= r8a7778_init_irq_dt,
 	.init_machine	= bockw_init,
-	.init_time	= shmobile_timer_init,
 	.dt_compat	= bockw_boards_compat_dt,
 	.init_late      = r8a7778_init_late,
 MACHINE_END
diff --git a/arch/arm/mach-shmobile/board-kota2.c b/arch/arm/mach-shmobile/board-kota2.c
deleted file mode 100644
index ef5ca0ef0cb5..000000000000
--- a/arch/arm/mach-shmobile/board-kota2.c
+++ /dev/null
@@ -1,553 +0,0 @@
-/*
- * kota2 board support
- *
- * Copyright (C) 2011  Renesas Solutions Corp.
- * Copyright (C) 2011  Magnus Damm
- * Copyright (C) 2010  Takashi Yoshii <yoshii.takashi.zj@renesas.com>
- * Copyright (C) 2009  Yoshihiro Shimoda <shimoda.yoshihiro@renesas.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; version 2 of the License.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
- */
-
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/interrupt.h>
-#include <linux/irq.h>
-#include <linux/pinctrl/machine.h>
-#include <linux/pinctrl/pinconf-generic.h>
-#include <linux/platform_device.h>
-#include <linux/delay.h>
-#include <linux/io.h>
-#include <linux/regulator/fixed.h>
-#include <linux/regulator/machine.h>
-#include <linux/smsc911x.h>
-#include <linux/gpio.h>
-#include <linux/input.h>
-#include <linux/input/sh_keysc.h>
-#include <linux/gpio_keys.h>
-#include <linux/leds.h>
-#include <linux/irqchip/arm-gic.h>
-#include <linux/platform_data/leds-renesas-tpu.h>
-#include <linux/mmc/host.h>
-#include <linux/mmc/sh_mmcif.h>
-#include <linux/mfd/tmio.h>
-#include <linux/mmc/sh_mobile_sdhi.h>
-#include <mach/hardware.h>
-#include <mach/irqs.h>
-#include <mach/sh73a0.h>
-#include <mach/common.h>
-#include <asm/mach-types.h>
-#include <asm/mach/arch.h>
-#include <asm/mach/time.h>
-#include <asm/hardware/cache-l2x0.h>
-#include <asm/traps.h>
-
-/* Dummy supplies, where voltage doesn't matter */
-static struct regulator_consumer_supply dummy_supplies[] = {
-	REGULATOR_SUPPLY("vddvario", "smsc911x"),
-	REGULATOR_SUPPLY("vdd33a", "smsc911x"),
-};
-
-/* SMSC 9220 */
-static struct resource smsc9220_resources[] = {
-	[0] = {
-		.start		= 0x14000000, /* CS5A */
-		.end		= 0x140000ff, /* A1->A7 */
-		.flags		= IORESOURCE_MEM,
-	},
-	[1] = {
-		.start		= SH73A0_PINT0_IRQ(2), /* PINTA2 */
-		.flags		= IORESOURCE_IRQ,
-	},
-};
-
-static struct smsc911x_platform_config smsc9220_platdata = {
-	.flags		= SMSC911X_USE_32BIT, /* 32-bit SW on 16-bit HW bus */
-	.phy_interface	= PHY_INTERFACE_MODE_MII,
-	.irq_polarity	= SMSC911X_IRQ_POLARITY_ACTIVE_LOW,
-	.irq_type	= SMSC911X_IRQ_TYPE_PUSH_PULL,
-};
-
-static struct platform_device eth_device = {
-	.name		= "smsc911x",
-	.id		= 0,
-	.dev  = {
-		.platform_data = &smsc9220_platdata,
-	},
-	.resource	= smsc9220_resources,
-	.num_resources	= ARRAY_SIZE(smsc9220_resources),
-};
-
-/* KEYSC */
-static struct sh_keysc_info keysc_platdata = {
-	.mode		= SH_KEYSC_MODE_6,
-	.scan_timing	= 3,
-	.delay		= 100,
-	.keycodes	= {
-		KEY_NUMERIC_STAR, KEY_NUMERIC_0, KEY_NUMERIC_POUND,
-		0, 0, 0, 0, 0,
-		KEY_NUMERIC_7, KEY_NUMERIC_8, KEY_NUMERIC_9,
-		0, KEY_DOWN, 0, 0, 0,
-		KEY_NUMERIC_4, KEY_NUMERIC_5, KEY_NUMERIC_6,
-		KEY_LEFT, KEY_ENTER, KEY_RIGHT, 0, 0,
-		KEY_NUMERIC_1, KEY_NUMERIC_2, KEY_NUMERIC_3,
-		0, KEY_UP, 0, 0, 0,
-		0, 0, 0, 0, 0, 0, 0, 0,
-		0, 0, 0, 0, 0, 0, 0, 0,
-		0, 0, 0, 0, 0, 0, 0, 0,
-		0, 0, 0, 0, 0, 0, 0, 0,
-	},
-};
-
-static struct resource keysc_resources[] = {
-	[0] = {
-		.name	= "KEYSC",
-		.start	= 0xe61b0000,
-		.end	= 0xe61b0098 - 1,
-		.flags	= IORESOURCE_MEM,
-	},
-	[1] = {
-		.start	= gic_spi(71),
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-static struct platform_device keysc_device = {
-	.name		= "sh_keysc",
-	.id		= 0,
-	.num_resources	= ARRAY_SIZE(keysc_resources),
-	.resource	= keysc_resources,
-	.dev		= {
-		.platform_data	= &keysc_platdata,
-	},
-};
-
-/* GPIO KEY */
-#define GPIO_KEY(c, g, d) { .code = c, .gpio = g, .desc = d, .active_low = 1 }
-
-static struct gpio_keys_button gpio_buttons[] = {
-	GPIO_KEY(KEY_VOLUMEUP, 56, "+"), /* S2: VOL+ [IRQ9] */
-	GPIO_KEY(KEY_VOLUMEDOWN, 54, "-"), /* S3: VOL- [IRQ10] */
-	GPIO_KEY(KEY_MENU, 27, "Menu"), /* S4: MENU [IRQ30] */
-	GPIO_KEY(KEY_HOMEPAGE, 26, "Home"), /* S5: HOME [IRQ31] */
-	GPIO_KEY(KEY_BACK, 11, "Back"), /* S6: BACK [IRQ0] */
-	GPIO_KEY(KEY_PHONE, 238, "Tel"), /* S7: TEL [IRQ11] */
-	GPIO_KEY(KEY_POWER, 239, "C1"), /* S8: CAM [IRQ13] */
-	GPIO_KEY(KEY_MAIL, 224, "Mail"), /* S9: MAIL [IRQ3] */
-	/* Omitted button "C3?": 223 - S10: CUST [IRQ8] */
-	GPIO_KEY(KEY_CAMERA, 164, "C2"), /* S11: CAM_HALF [IRQ25] */
-	/* Omitted button "?": 152 - S12: CAM_FULL [No IRQ] */
-};
-
-static struct gpio_keys_platform_data gpio_key_info = {
-	.buttons        = gpio_buttons,
-	.nbuttons       = ARRAY_SIZE(gpio_buttons),
-};
-
-static struct platform_device gpio_keys_device = {
-	.name   = "gpio-keys",
-	.id     = -1,
-	.dev    = {
-		.platform_data  = &gpio_key_info,
-	},
-};
-
-/* GPIO LED */
-#define GPIO_LED(n, g) { .name = n, .gpio = g }
-
-static struct gpio_led gpio_leds[] = {
-	GPIO_LED("G", 20), /* PORT20 [GPO0] -> LED7 -> "G" */
-	GPIO_LED("H", 21), /* PORT21 [GPO1] -> LED8 -> "H" */
-	GPIO_LED("J", 22), /* PORT22 [GPO2] -> LED9 -> "J" */
-};
-
-static struct gpio_led_platform_data gpio_leds_info = {
-	.leds		= gpio_leds,
-	.num_leds	= ARRAY_SIZE(gpio_leds),
-};
-
-static struct platform_device gpio_leds_device = {
-	.name   = "leds-gpio",
-	.id     = -1,
-	.dev    = {
-		.platform_data  = &gpio_leds_info,
-	},
-};
-
-/* TPU LED */
-static struct led_renesas_tpu_config led_renesas_tpu12_pdata = {
-	.name		= "V2513",
-	.pin_gpio_fn	= GPIO_FN_TPU1TO2,
-	.pin_gpio	= 153,
-	.channel_offset = 0x90,
-	.timer_bit = 2,
-	.max_brightness = 1000,
-};
-
-static struct resource tpu12_resources[] = {
-	[0] = {
-		.name	= "TPU12",
-		.start	= 0xe6610090,
-		.end	= 0xe66100b5,
-		.flags	= IORESOURCE_MEM,
-	},
-};
-
-static struct platform_device leds_tpu12_device = {
-	.name = "leds-renesas-tpu",
-	.id = 12,
-	.dev = {
-		.platform_data  = &led_renesas_tpu12_pdata,
-	},
-	.num_resources	= ARRAY_SIZE(tpu12_resources),
-	.resource	= tpu12_resources,
-};
-
-static struct led_renesas_tpu_config led_renesas_tpu41_pdata = {
-	.name		= "V2514",
-	.pin_gpio_fn	= GPIO_FN_TPU4TO1,
-	.pin_gpio	= 199,
-	.channel_offset = 0x50,
-	.timer_bit = 1,
-	.max_brightness = 1000,
-};
-
-static struct resource tpu41_resources[] = {
-	[0] = {
-		.name	= "TPU41",
-		.start	= 0xe6640050,
-		.end	= 0xe6640075,
-		.flags	= IORESOURCE_MEM,
-	},
-};
-
-static struct platform_device leds_tpu41_device = {
-	.name = "leds-renesas-tpu",
-	.id = 41,
-	.dev = {
-		.platform_data  = &led_renesas_tpu41_pdata,
-	},
-	.num_resources	= ARRAY_SIZE(tpu41_resources),
-	.resource	= tpu41_resources,
-};
-
-static struct led_renesas_tpu_config led_renesas_tpu21_pdata = {
-	.name		= "V2515",
-	.pin_gpio_fn	= GPIO_FN_TPU2TO1,
-	.pin_gpio	= 197,
-	.channel_offset = 0x50,
-	.timer_bit = 1,
-	.max_brightness = 1000,
-};
-
-static struct resource tpu21_resources[] = {
-	[0] = {
-		.name	= "TPU21",
-		.start	= 0xe6620050,
-		.end	= 0xe6620075,
-		.flags	= IORESOURCE_MEM,
-	},
-};
-
-static struct platform_device leds_tpu21_device = {
-	.name = "leds-renesas-tpu",
-	.id = 21,
-	.dev = {
-		.platform_data  = &led_renesas_tpu21_pdata,
-	},
-	.num_resources	= ARRAY_SIZE(tpu21_resources),
-	.resource	= tpu21_resources,
-};
-
-static struct led_renesas_tpu_config led_renesas_tpu30_pdata = {
-	.name		= "KEYLED",
-	.pin_gpio_fn	= GPIO_FN_TPU3TO0,
-	.pin_gpio	= 163,
-	.channel_offset = 0x10,
-	.timer_bit = 0,
-	.max_brightness = 1000,
-};
-
-static struct resource tpu30_resources[] = {
-	[0] = {
-		.name	= "TPU30",
-		.start	= 0xe6630010,
-		.end	= 0xe6630035,
-		.flags	= IORESOURCE_MEM,
-	},
-};
-
-static struct platform_device leds_tpu30_device = {
-	.name = "leds-renesas-tpu",
-	.id = 30,
-	.dev = {
-		.platform_data  = &led_renesas_tpu30_pdata,
-	},
-	.num_resources	= ARRAY_SIZE(tpu30_resources),
-	.resource	= tpu30_resources,
-};
-
-/* Fixed 1.8V regulator to be used by MMCIF */
-static struct regulator_consumer_supply fixed1v8_power_consumers[] =
-{
-	REGULATOR_SUPPLY("vmmc", "sh_mmcif.0"),
-	REGULATOR_SUPPLY("vqmmc", "sh_mmcif.0"),
-};
-
-/* MMCIF */
-static struct resource mmcif_resources[] = {
-	[0] = {
-		.name   = "MMCIF",
-		.start  = 0xe6bd0000,
-		.end    = 0xe6bd00ff,
-		.flags  = IORESOURCE_MEM,
-	},
-	[1] = {
-		.start  = gic_spi(140),
-		.flags  = IORESOURCE_IRQ,
-	},
-	[2] = {
-		.start  = gic_spi(141),
-		.flags  = IORESOURCE_IRQ,
-	},
-};
-
-static struct sh_mmcif_plat_data mmcif_info = {
-	.ocr            = MMC_VDD_165_195,
-	.caps           = MMC_CAP_8_BIT_DATA | MMC_CAP_NONREMOVABLE,
-};
-
-static struct platform_device mmcif_device = {
-	.name           = "sh_mmcif",
-	.id             = 0,
-	.dev            = {
-		.platform_data          = &mmcif_info,
-	},
-	.num_resources  = ARRAY_SIZE(mmcif_resources),
-	.resource       = mmcif_resources,
-};
-
-/* Fixed 3.3V regulator to be used by SDHI0 and SDHI1 */
-static struct regulator_consumer_supply fixed3v3_power_consumers[] =
-{
-	REGULATOR_SUPPLY("vmmc", "sh_mobile_sdhi.0"),
-	REGULATOR_SUPPLY("vqmmc", "sh_mobile_sdhi.0"),
-	REGULATOR_SUPPLY("vmmc", "sh_mobile_sdhi.1"),
-	REGULATOR_SUPPLY("vqmmc", "sh_mobile_sdhi.1"),
-};
-
-/* SDHI0 */
-static struct sh_mobile_sdhi_info sdhi0_info = {
-	.tmio_caps      = MMC_CAP_SD_HIGHSPEED,
-	.tmio_flags     = TMIO_MMC_WRPROTECT_DISABLE | TMIO_MMC_HAS_IDLE_WAIT,
-};
-
-static struct resource sdhi0_resources[] = {
-	[0] = {
-		.name   = "SDHI0",
-		.start  = 0xee100000,
-		.end    = 0xee1000ff,
-		.flags  = IORESOURCE_MEM,
-	},
-	[1] = {
-		.start  = gic_spi(83),
-		.flags  = IORESOURCE_IRQ,
-	},
-	[2] = {
-		.start  = gic_spi(84),
-		.flags  = IORESOURCE_IRQ,
-	},
-	[3] = {
-		.start	= gic_spi(85),
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-static struct platform_device sdhi0_device = {
-	.name           = "sh_mobile_sdhi",
-	.id             = 0,
-	.num_resources  = ARRAY_SIZE(sdhi0_resources),
-	.resource       = sdhi0_resources,
-	.dev    = {
-		.platform_data  = &sdhi0_info,
-	},
-};
-
-/* SDHI1 */
-static struct sh_mobile_sdhi_info sdhi1_info = {
-	.tmio_caps      = MMC_CAP_NONREMOVABLE | MMC_CAP_SDIO_IRQ,
-	.tmio_flags     = TMIO_MMC_WRPROTECT_DISABLE | TMIO_MMC_HAS_IDLE_WAIT,
-};
-
-static struct resource sdhi1_resources[] = {
-	[0] = {
-		.name   = "SDHI1",
-		.start  = 0xee120000,
-		.end    = 0xee1200ff,
-		.flags  = IORESOURCE_MEM,
-	},
-	[1] = {
-		.start  = gic_spi(87),
-		.flags  = IORESOURCE_IRQ,
-	},
-	[2] = {
-		.start  = gic_spi(88),
-		.flags  = IORESOURCE_IRQ,
-	},
-	[3] = {
-		.start	= gic_spi(89),
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-static struct platform_device sdhi1_device = {
-	.name           = "sh_mobile_sdhi",
-	.id             = 1,
-	.num_resources  = ARRAY_SIZE(sdhi1_resources),
-	.resource       = sdhi1_resources,
-	.dev    = {
-		.platform_data  = &sdhi1_info,
-	},
-};
-
-static struct platform_device *kota2_devices[] __initdata = {
-	&eth_device,
-	&keysc_device,
-	&gpio_keys_device,
-	&gpio_leds_device,
-	&leds_tpu12_device,
-	&leds_tpu41_device,
-	&leds_tpu21_device,
-	&leds_tpu30_device,
-	&mmcif_device,
-	&sdhi0_device,
-	&sdhi1_device,
-};
-
-static unsigned long pin_pullup_conf[] = {
-	PIN_CONF_PACKED(PIN_CONFIG_BIAS_PULL_UP, 0),
-};
-
-static const struct pinctrl_map kota2_pinctrl_map[] = {
-	/* KEYSC */
-	PIN_MAP_MUX_GROUP_DEFAULT("sh_keysc.0", "pfc-sh73a0",
-				  "keysc_in8", "keysc"),
-	PIN_MAP_MUX_GROUP_DEFAULT("sh_keysc.0", "pfc-sh73a0",
-				  "keysc_out04", "keysc"),
-	PIN_MAP_MUX_GROUP_DEFAULT("sh_keysc.0", "pfc-sh73a0",
-				  "keysc_out5", "keysc"),
-	PIN_MAP_MUX_GROUP_DEFAULT("sh_keysc.0", "pfc-sh73a0",
-				  "keysc_out6_0", "keysc"),
-	PIN_MAP_MUX_GROUP_DEFAULT("sh_keysc.0", "pfc-sh73a0",
-				  "keysc_out7_0", "keysc"),
-	PIN_MAP_MUX_GROUP_DEFAULT("sh_keysc.0", "pfc-sh73a0",
-				  "keysc_out8_0", "keysc"),
-	PIN_MAP_CONFIGS_GROUP_DEFAULT("sh_keysc.0", "pfc-sh73a0",
-				      "keysc_in8", pin_pullup_conf),
-	/* MMCIF */
-	PIN_MAP_MUX_GROUP_DEFAULT("sh_mmcif.0", "pfc-sh73a0",
-				  "mmc0_data8_0", "mmc0"),
-	PIN_MAP_MUX_GROUP_DEFAULT("sh_mmcif.0", "pfc-sh73a0",
-				  "mmc0_ctrl_0", "mmc0"),
-	PIN_MAP_CONFIGS_PIN_DEFAULT("sh_mmcif.0", "pfc-sh73a0",
-				    "PORT279", pin_pullup_conf),
-	PIN_MAP_CONFIGS_GROUP_DEFAULT("sh_mmcif.0", "pfc-sh73a0",
-				      "mmc0_data8_0", pin_pullup_conf),
-	/* SCIFA2 (UART2) */
-	PIN_MAP_MUX_GROUP_DEFAULT("sh-sci.2", "pfc-sh73a0",
-				  "scifa2_data_0", "scifa2"),
-	PIN_MAP_MUX_GROUP_DEFAULT("sh-sci.2", "pfc-sh73a0",
-				  "scifa2_ctrl_0", "scifa2"),
-	/* SCIFA4 (UART1) */
-	PIN_MAP_MUX_GROUP_DEFAULT("sh-sci.4", "pfc-sh73a0",
-				  "scifa4_data", "scifa4"),
-	PIN_MAP_MUX_GROUP_DEFAULT("sh-sci.4", "pfc-sh73a0",
-				  "scifa4_ctrl", "scifa4"),
-	/* SCIFB (BT) */
-	PIN_MAP_MUX_GROUP_DEFAULT("sh-sci.8", "pfc-sh73a0",
-				  "scifb_data_0", "scifb"),
-	PIN_MAP_MUX_GROUP_DEFAULT("sh-sci.8", "pfc-sh73a0",
-				  "scifb_clk_0", "scifb"),
-	PIN_MAP_MUX_GROUP_DEFAULT("sh-sci.8", "pfc-sh73a0",
-				  "scifb_ctrl_0", "scifb"),
-	/* SDHI0 (microSD) */
-	PIN_MAP_MUX_GROUP_DEFAULT("sh_mobile_sdhi.0", "pfc-sh73a0",
-				  "sdhi0_data4", "sdhi0"),
-	PIN_MAP_MUX_GROUP_DEFAULT("sh_mobile_sdhi.0", "pfc-sh73a0",
-				  "sdhi0_ctrl", "sdhi0"),
-	PIN_MAP_MUX_GROUP_DEFAULT("sh_mobile_sdhi.0", "pfc-sh73a0",
-				  "sdhi0_cd", "sdhi0"),
-	PIN_MAP_CONFIGS_GROUP_DEFAULT("sh_mobile_sdhi.0", "pfc-sh73a0",
-				      "sdhi0_data4", pin_pullup_conf),
-	PIN_MAP_CONFIGS_PIN_DEFAULT("sh_mobile_sdhi.0", "pfc-sh73a0",
-				    "PORT256", pin_pullup_conf),
-	PIN_MAP_CONFIGS_PIN_DEFAULT("sh_mobile_sdhi.0", "pfc-sh73a0",
-				    "PORT251", pin_pullup_conf),
-	/* SDHI1 (BCM4330) */
-	PIN_MAP_MUX_GROUP_DEFAULT("sh_mobile_sdhi.1", "pfc-sh73a0",
-				  "sdhi1_data4", "sdhi1"),
-	PIN_MAP_MUX_GROUP_DEFAULT("sh_mobile_sdhi.1", "pfc-sh73a0",
-				  "sdhi1_ctrl", "sdhi1"),
-	PIN_MAP_CONFIGS_GROUP_DEFAULT("sh_mobile_sdhi.1", "pfc-sh73a0",
-				      "sdhi1_data4", pin_pullup_conf),
-	PIN_MAP_CONFIGS_PIN_DEFAULT("sh_mobile_sdhi.1", "pfc-sh73a0",
-				    "PORT263", pin_pullup_conf),
-	/* SMSC911X */
-	PIN_MAP_MUX_GROUP_DEFAULT("smsc911x.0", "pfc-sh73a0",
-				  "bsc_data_0_7", "bsc"),
-	PIN_MAP_MUX_GROUP_DEFAULT("smsc911x.0", "pfc-sh73a0",
-				  "bsc_data_8_15", "bsc"),
-	PIN_MAP_MUX_GROUP_DEFAULT("smsc911x.0", "pfc-sh73a0",
-				  "bsc_cs5_a", "bsc"),
-	PIN_MAP_MUX_GROUP_DEFAULT("smsc911x.0", "pfc-sh73a0",
-				  "bsc_we0", "bsc"),
-};
-
-static void __init kota2_init(void)
-{
-	regulator_register_always_on(0, "fixed-1.8V", fixed1v8_power_consumers,
-				     ARRAY_SIZE(fixed1v8_power_consumers), 1800000);
-	regulator_register_always_on(1, "fixed-3.3V", fixed3v3_power_consumers,
-				     ARRAY_SIZE(fixed3v3_power_consumers), 3300000);
-	regulator_register_fixed(2, dummy_supplies, ARRAY_SIZE(dummy_supplies));
-
-	pinctrl_register_mappings(kota2_pinctrl_map,
-				  ARRAY_SIZE(kota2_pinctrl_map));
-	sh73a0_pinmux_init();
-
-	/* SMSC911X */
-	gpio_request_one(144, GPIOF_IN, NULL); /* PINTA2 */
-	gpio_request_one(145, GPIOF_OUT_INIT_HIGH, NULL); /* RESET */
-
-	/* MMCIF */
-	gpio_request_one(208, GPIOF_OUT_INIT_HIGH, NULL); /* Reset */
-
-#ifdef CONFIG_CACHE_L2X0
-	/* Early BRESP enable, Shared attribute override enable, 64K*8way */
-	l2x0_init(IOMEM(0xf0100000), 0x40460000, 0x82000fff);
-#endif
-	sh73a0_add_standard_devices();
-	platform_add_devices(kota2_devices, ARRAY_SIZE(kota2_devices));
-}
-
-MACHINE_START(KOTA2, "kota2")
-	.smp		= smp_ops(sh73a0_smp_ops),
-	.map_io		= sh73a0_map_io,
-	.init_early	= sh73a0_add_early_devices,
-	.nr_irqs	= NR_IRQS_LEGACY,
-	.init_irq	= sh73a0_init_irq,
-	.init_machine	= kota2_init,
-	.init_late	= shmobile_init_late,
-	.init_time	= sh73a0_earlytimer_init,
-MACHINE_END
diff --git a/arch/arm/mach-shmobile/board-kzm9d-reference.c b/arch/arm/mach-shmobile/board-kzm9d-reference.c
new file mode 100644
index 000000000000..8f8bb2fab076
--- /dev/null
+++ b/arch/arm/mach-shmobile/board-kzm9d-reference.c
@@ -0,0 +1,47 @@
+/*
+ * kzm9d board support - Reference DT implementation
+ *
+ * Copyright (C) 2013  Renesas Solutions Corp.
+ * Copyright (C) 2013  Magnus Damm
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
+ */
+
+#include <linux/init.h>
+#include <linux/of_platform.h>
+#include <mach/emev2.h>
+#include <mach/common.h>
+#include <asm/mach/arch.h>
+
+static void __init kzm9d_add_standard_devices(void)
+{
+	if (!IS_ENABLED(CONFIG_COMMON_CLK))
+		emev2_clock_init();
+
+	of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
+}
+
+static const char *kzm9d_boards_compat_dt[] __initdata = {
+	"renesas,kzm9d-reference",
+	NULL,
+};
+
+DT_MACHINE_START(KZM9D_DT, "kzm9d")
+	.smp		= smp_ops(emev2_smp_ops),
+	.map_io		= emev2_map_io,
+	.init_early	= emev2_init_delay,
+	.init_machine	= kzm9d_add_standard_devices,
+	.init_late	= shmobile_init_late,
+	.dt_compat	= kzm9d_boards_compat_dt,
+MACHINE_END
diff --git a/arch/arm/mach-shmobile/board-kzm9d.c b/arch/arm/mach-shmobile/board-kzm9d.c
index 4368000e1127..30c2cc695b12 100644
--- a/arch/arm/mach-shmobile/board-kzm9d.c
+++ b/arch/arm/mach-shmobile/board-kzm9d.c
@@ -85,9 +85,7 @@ static const char *kzm9d_boards_compat_dt[] __initdata = {
 DT_MACHINE_START(KZM9D_DT, "kzm9d")
 	.smp		= smp_ops(emev2_smp_ops),
 	.map_io		= emev2_map_io,
-	.init_early	= emev2_add_early_devices,
-	.nr_irqs	= NR_IRQS_LEGACY,
-	.init_irq	= emev2_init_irq,
+	.init_early	= emev2_init_delay,
 	.init_machine	= kzm9d_add_standard_devices,
 	.init_late	= shmobile_init_late,
 	.dt_compat	= kzm9d_boards_compat_dt,
diff --git a/arch/arm/mach-shmobile/board-kzm9g-reference.c b/arch/arm/mach-shmobile/board-kzm9g-reference.c
index 44055fe8a45c..598e32488410 100644
--- a/arch/arm/mach-shmobile/board-kzm9g-reference.c
+++ b/arch/arm/mach-shmobile/board-kzm9g-reference.c
@@ -21,67 +21,19 @@
  */
 
 #include <linux/delay.h>
-#include <linux/gpio.h>
 #include <linux/io.h>
 #include <linux/irq.h>
-#include <linux/irqchip.h>
 #include <linux/input.h>
 #include <linux/of_platform.h>
-#include <linux/pinctrl/machine.h>
-#include <linux/pinctrl/pinconf-generic.h>
 #include <mach/sh73a0.h>
 #include <mach/common.h>
 #include <asm/hardware/cache-l2x0.h>
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
 
-static unsigned long pin_pullup_conf[] = {
-	PIN_CONF_PACKED(PIN_CONFIG_BIAS_PULL_UP, 0),
-};
-
-static const struct pinctrl_map kzm_pinctrl_map[] = {
-	PIN_MAP_MUX_GROUP_DEFAULT("e6826000.i2c", "pfc-sh73a0",
-				  "i2c3_1", "i2c3"),
-	/* MMCIF */
-	PIN_MAP_MUX_GROUP_DEFAULT("e6bd0000.mmcif", "pfc-sh73a0",
-				  "mmc0_data8_0", "mmc0"),
-	PIN_MAP_MUX_GROUP_DEFAULT("e6bd0000.mmcif", "pfc-sh73a0",
-				  "mmc0_ctrl_0", "mmc0"),
-	PIN_MAP_CONFIGS_PIN_DEFAULT("e6bd0000.mmcif", "pfc-sh73a0",
-				    "PORT279", pin_pullup_conf),
-	PIN_MAP_CONFIGS_GROUP_DEFAULT("e6bd0000.mmcif", "pfc-sh73a0",
-				      "mmc0_data8_0", pin_pullup_conf),
-	/* SCIFA4 */
-	PIN_MAP_MUX_GROUP_DEFAULT("sh-sci.4", "pfc-sh73a0",
-				  "scifa4_data", "scifa4"),
-	PIN_MAP_MUX_GROUP_DEFAULT("sh-sci.4", "pfc-sh73a0",
-				  "scifa4_ctrl", "scifa4"),
-	/* SDHI0 */
-	PIN_MAP_MUX_GROUP_DEFAULT("ee100000.sdhi", "pfc-sh73a0",
-				  "sdhi0_data4", "sdhi0"),
-	PIN_MAP_MUX_GROUP_DEFAULT("ee100000.sdhi", "pfc-sh73a0",
-				  "sdhi0_ctrl", "sdhi0"),
-	PIN_MAP_MUX_GROUP_DEFAULT("ee100000.sdhi", "pfc-sh73a0",
-				  "sdhi0_cd", "sdhi0"),
-	PIN_MAP_MUX_GROUP_DEFAULT("ee100000.sdhi", "pfc-sh73a0",
-				  "sdhi0_wp", "sdhi0"),
-	/* SDHI2 */
-	PIN_MAP_MUX_GROUP_DEFAULT("ee140000.sdhi", "pfc-sh73a0",
-				  "sdhi2_data4", "sdhi2"),
-	PIN_MAP_MUX_GROUP_DEFAULT("ee140000.sdhi", "pfc-sh73a0",
-				  "sdhi2_ctrl", "sdhi2"),
-};
-
 static void __init kzm_init(void)
 {
 	sh73a0_add_standard_devices_dt();
-	pinctrl_register_mappings(kzm_pinctrl_map, ARRAY_SIZE(kzm_pinctrl_map));
-	sh73a0_pinmux_init();
-
-	/* enable SD */
-	gpio_request_one(15, GPIOF_OUT_INIT_HIGH, NULL); /* power */
-
-	gpio_request_one(14, GPIOF_OUT_INIT_HIGH, NULL); /* power */
 
 #ifdef CONFIG_CACHE_L2X0
 	/* Early BRESP enable, Shared attribute override enable, 64K*8way */
@@ -99,8 +51,6 @@ DT_MACHINE_START(KZM9G_DT, "kzm9g-reference")
 	.map_io		= sh73a0_map_io,
 	.init_early	= sh73a0_init_delay,
 	.nr_irqs	= NR_IRQS_LEGACY,
-	.init_irq	= irqchip_init,
 	.init_machine	= kzm_init,
-	.init_time	= shmobile_timer_init,
 	.dt_compat	= kzm9g_boards_compat_dt,
 MACHINE_END
diff --git a/arch/arm/mach-shmobile/board-kzm9g.c b/arch/arm/mach-shmobile/board-kzm9g.c
index 1068120d339f..f1994968d303 100644
--- a/arch/arm/mach-shmobile/board-kzm9g.c
+++ b/arch/arm/mach-shmobile/board-kzm9g.c
@@ -54,14 +54,14 @@
 /*
  * external GPIO
  */
-#define GPIO_PCF8575_BASE	(GPIO_NR)
-#define GPIO_PCF8575_PORT10	(GPIO_NR + 8)
-#define GPIO_PCF8575_PORT11	(GPIO_NR + 9)
-#define GPIO_PCF8575_PORT12	(GPIO_NR + 10)
-#define GPIO_PCF8575_PORT13	(GPIO_NR + 11)
-#define GPIO_PCF8575_PORT14	(GPIO_NR + 12)
-#define GPIO_PCF8575_PORT15	(GPIO_NR + 13)
-#define GPIO_PCF8575_PORT16	(GPIO_NR + 14)
+#define GPIO_PCF8575_BASE	(310)
+#define GPIO_PCF8575_PORT10	(GPIO_PCF8575_BASE + 8)
+#define GPIO_PCF8575_PORT11	(GPIO_PCF8575_BASE + 9)
+#define GPIO_PCF8575_PORT12	(GPIO_PCF8575_BASE + 10)
+#define GPIO_PCF8575_PORT13	(GPIO_PCF8575_BASE + 11)
+#define GPIO_PCF8575_PORT14	(GPIO_PCF8575_BASE + 12)
+#define GPIO_PCF8575_PORT15	(GPIO_PCF8575_BASE + 13)
+#define GPIO_PCF8575_PORT16	(GPIO_PCF8575_BASE + 14)
 
 /* Dummy supplies, where voltage doesn't matter */
 static struct regulator_consumer_supply dummy_supplies[] = {
diff --git a/arch/arm/mach-shmobile/board-lager-reference.c b/arch/arm/mach-shmobile/board-lager-reference.c
new file mode 100644
index 000000000000..9c316a1b2e32
--- /dev/null
+++ b/arch/arm/mach-shmobile/board-lager-reference.c
@@ -0,0 +1,45 @@
+/*
+ * Lager board support - Reference DT implementation
+ *
+ * Copyright (C) 2013  Renesas Solutions Corp.
+ * Copyright (C) 2013  Simon Horman
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
+ */
+
+#include <linux/init.h>
+#include <linux/of_platform.h>
+#include <mach/r8a7790.h>
+#include <asm/mach/arch.h>
+
+static void __init lager_add_standard_devices(void)
+{
+	/* clocks are setup late during boot in the case of DT */
+	r8a7790_clock_init();
+
+	r8a7790_add_dt_devices();
+        of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
+}
+
+static const char *lager_boards_compat_dt[] __initdata = {
+	"renesas,lager-reference",
+	NULL,
+};
+
+DT_MACHINE_START(LAGER_DT, "lager")
+	.init_early	= r8a7790_init_delay,
+	.init_machine	= lager_add_standard_devices,
+	.init_time	= r8a7790_timer_init,
+	.dt_compat	= lager_boards_compat_dt,
+MACHINE_END
diff --git a/arch/arm/mach-shmobile/board-lager.c b/arch/arm/mach-shmobile/board-lager.c
index 8d6bd5c5efb9..5930af8d434f 100644
--- a/arch/arm/mach-shmobile/board-lager.c
+++ b/arch/arm/mach-shmobile/board-lager.c
@@ -22,13 +22,19 @@
 #include <linux/gpio_keys.h>
 #include <linux/input.h>
 #include <linux/interrupt.h>
-#include <linux/irqchip.h>
 #include <linux/kernel.h>
 #include <linux/leds.h>
+#include <linux/mmc/host.h>
+#include <linux/mmc/sh_mmcif.h>
 #include <linux/pinctrl/machine.h>
 #include <linux/platform_data/gpio-rcar.h>
 #include <linux/platform_device.h>
+#include <linux/phy.h>
+#include <linux/regulator/fixed.h>
+#include <linux/regulator/machine.h>
+#include <linux/sh_eth.h>
 #include <mach/common.h>
+#include <mach/irqs.h>
 #include <mach/r8a7790.h>
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
@@ -71,6 +77,35 @@ static __initdata struct gpio_keys_platform_data lager_keys_pdata = {
 	.nbuttons	= ARRAY_SIZE(gpio_buttons),
 };
 
+/* Fixed 3.3V regulator to be used by MMCIF */
+static struct regulator_consumer_supply fixed3v3_power_consumers[] =
+{
+	REGULATOR_SUPPLY("vmmc", "sh_mmcif.1"),
+};
+
+/* MMCIF */
+static struct sh_mmcif_plat_data mmcif1_pdata __initdata = {
+	.caps		= MMC_CAP_8_BIT_DATA | MMC_CAP_NONREMOVABLE,
+};
+
+static struct resource mmcif1_resources[] __initdata = {
+	DEFINE_RES_MEM_NAMED(0xee220000, 0x80, "MMCIF1"),
+	DEFINE_RES_IRQ(gic_spi(170)),
+};
+
+/* Ether */
+static struct sh_eth_plat_data ether_pdata __initdata = {
+	.phy			= 0x1,
+	.edmac_endian		= EDMAC_LITTLE_ENDIAN,
+	.phy_interface		= PHY_INTERFACE_MODE_RMII,
+	.ether_link_active_low	= 1,
+};
+
+static struct resource ether_resources[] __initdata = {
+	DEFINE_RES_MEM(0xee700000, 0x400),
+	DEFINE_RES_IRQ(gic_spi(162)),
+};
+
 static const struct pinctrl_map lager_pinctrl_map[] = {
 	/* SCIF0 (CN19: DEBUG SERIAL0) */
 	PIN_MAP_MUX_GROUP_DEFAULT("sh-sci.6", "pfc-r8a7790",
@@ -78,6 +113,20 @@ static const struct pinctrl_map lager_pinctrl_map[] = {
 	/* SCIF1 (CN20: DEBUG SERIAL1) */
 	PIN_MAP_MUX_GROUP_DEFAULT("sh-sci.7", "pfc-r8a7790",
 				  "scif1_data", "scif1"),
+	/* MMCIF1 */
+	PIN_MAP_MUX_GROUP_DEFAULT("sh_mmcif.1", "pfc-r8a7790",
+				  "mmc1_data8", "mmc1"),
+	PIN_MAP_MUX_GROUP_DEFAULT("sh_mmcif.1", "pfc-r8a7790",
+				  "mmc1_ctrl", "mmc1"),
+	/* Ether */
+	PIN_MAP_MUX_GROUP_DEFAULT("r8a7790-ether", "pfc-r8a7790",
+				  "eth_link", "eth"),
+	PIN_MAP_MUX_GROUP_DEFAULT("r8a7790-ether", "pfc-r8a7790",
+				  "eth_mdio", "eth"),
+	PIN_MAP_MUX_GROUP_DEFAULT("r8a7790-ether", "pfc-r8a7790",
+				  "eth_rmii", "eth"),
+	PIN_MAP_MUX_GROUP_DEFAULT("r8a7790-ether", "pfc-r8a7790",
+				  "intc_irq0", "intc"),
 };
 
 static void __init lager_add_standard_devices(void)
@@ -95,6 +144,40 @@ static void __init lager_add_standard_devices(void)
 	platform_device_register_data(&platform_bus, "gpio-keys", -1,
 				      &lager_keys_pdata,
 				      sizeof(lager_keys_pdata));
+	regulator_register_always_on(0, "fixed-3.3V", fixed3v3_power_consumers,
+				     ARRAY_SIZE(fixed3v3_power_consumers), 3300000);
+	platform_device_register_resndata(&platform_bus, "sh_mmcif", 1,
+					  mmcif1_resources, ARRAY_SIZE(mmcif1_resources),
+					  &mmcif1_pdata, sizeof(mmcif1_pdata));
+
+	platform_device_register_resndata(&platform_bus, "r8a7790-ether", -1,
+					  ether_resources,
+					  ARRAY_SIZE(ether_resources),
+					  &ether_pdata, sizeof(ether_pdata));
+}
+
+/*
+ * Ether LEDs on the Lager board are named LINK and ACTIVE which corresponds
+ * to non-default 01 setting of the Micrel KSZ8041 PHY control register 1 bits
+ * 14-15. We have to set them back to 01 from the default 00 value each time
+ * the PHY is reset. It's also important because the PHY's LED0 signal is
+ * connected to SoC's ETH_LINK signal and in the PHY's default mode it will
+ * bounce on and off after each packet, which we apparently want to avoid.
+ */
+static int lager_ksz8041_fixup(struct phy_device *phydev)
+{
+	u16 phyctrl1 = phy_read(phydev, 0x1e);
+
+	phyctrl1 &= ~0xc000;
+	phyctrl1 |= 0x4000;
+	return phy_write(phydev, 0x1e, phyctrl1);
+}
+
+static void __init lager_init(void)
+{
+	lager_add_standard_devices();
+
+	phy_register_fixup_for_id("r8a7790-ether-ff:01", lager_ksz8041_fixup);
 }
 
 static const char *lager_boards_compat_dt[] __initdata = {
@@ -103,8 +186,8 @@ static const char *lager_boards_compat_dt[] __initdata = {
 };
 
 DT_MACHINE_START(LAGER_DT, "lager")
-	.init_irq	= irqchip_init,
+	.init_early	= r8a7790_init_delay,
 	.init_time	= r8a7790_timer_init,
-	.init_machine	= lager_add_standard_devices,
+	.init_machine	= lager_init,
 	.dt_compat	= lager_boards_compat_dt,
 MACHINE_END
diff --git a/arch/arm/mach-shmobile/board-mackerel.c b/arch/arm/mach-shmobile/board-mackerel.c
index 85f51a849a50..af06753eb809 100644
--- a/arch/arm/mach-shmobile/board-mackerel.c
+++ b/arch/arm/mach-shmobile/board-mackerel.c
@@ -41,6 +41,7 @@
 #include <linux/mtd/physmap.h>
 #include <linux/mtd/sh_flctl.h>
 #include <linux/pinctrl/machine.h>
+#include <linux/platform_data/gpio_backlight.h>
 #include <linux/pm_clock.h>
 #include <linux/regulator/fixed.h>
 #include <linux/regulator/machine.h>
@@ -49,7 +50,6 @@
 #include <linux/tca6416_keypad.h>
 #include <linux/usb/renesas_usbhs.h>
 #include <linux/dma-mapping.h>
-
 #include <video/sh_mobile_hdmi.h>
 #include <video/sh_mobile_lcdc.h>
 #include <media/sh_mobile_ceu.h>
@@ -346,7 +346,7 @@ static struct platform_device meram_device = {
 	},
 };
 
-/* LCDC */
+/* LCDC and backlight */
 static struct fb_videomode mackerel_lcdc_modes[] = {
 	{
 		.name		= "WVGA Panel",
@@ -362,13 +362,6 @@ static struct fb_videomode mackerel_lcdc_modes[] = {
 	},
 };
 
-static int mackerel_set_brightness(int brightness)
-{
-	gpio_set_value(31, brightness);
-
-	return 0;
-}
-
 static const struct sh_mobile_meram_cfg lcd_meram_cfg = {
 	.icb[0] = {
 		.meram_size     = 0x40,
@@ -393,11 +386,6 @@ static struct sh_mobile_lcdc_info lcdc_info = {
 			.width		= 152,
 			.height		= 91,
 		},
-		.bl_info = {
-			.name = "sh_mobile_lcdc_bl",
-			.max_brightness = 1,
-			.set_brightness = mackerel_set_brightness,
-		},
 		.meram_cfg = &lcd_meram_cfg,
 	}
 };
@@ -425,6 +413,20 @@ static struct platform_device lcdc_device = {
 	},
 };
 
+static struct gpio_backlight_platform_data gpio_backlight_data = {
+	.fbdev = &lcdc_device.dev,
+	.gpio = 31,
+	.def_value = 1,
+	.name = "backlight",
+};
+
+static struct platform_device gpio_backlight_device = {
+	.name = "gpio-backlight",
+	.dev = {
+		.platform_data = &gpio_backlight_data,
+	},
+};
+
 /* HDMI */
 static struct sh_mobile_hdmi_info hdmi_info = {
 	.flags		= HDMI_SND_SRC_SPDIF,
@@ -1231,6 +1233,7 @@ static struct platform_device *mackerel_devices[] __initdata = {
 	&nor_flash_device,
 	&smc911x_device,
 	&lcdc_device,
+	&gpio_backlight_device,
 	&usbhs0_device,
 	&usbhs1_device,
 	&leds_device,
@@ -1441,9 +1444,6 @@ static void __init mackerel_init(void)
 				  ARRAY_SIZE(mackerel_pinctrl_map));
 	sh7372_pinmux_init();
 
-	/* backlight, off by default */
-	gpio_request_one(31, GPIOF_OUT_INIT_LOW, NULL);
-
 	gpio_request_one(151, GPIOF_OUT_INIT_HIGH, NULL); /* LCDDON */
 
 	/* USBHS0 */
diff --git a/arch/arm/mach-shmobile/board-marzen-reference.c b/arch/arm/mach-shmobile/board-marzen-reference.c
index 480d882e42c7..3f4250a2d4eb 100644
--- a/arch/arm/mach-shmobile/board-marzen-reference.c
+++ b/arch/arm/mach-shmobile/board-marzen-reference.c
@@ -19,42 +19,14 @@
  * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
  */
 
-#include <linux/pinctrl/machine.h>
 #include <mach/r8a7779.h>
 #include <mach/common.h>
 #include <mach/irqs.h>
 #include <asm/irq.h>
 #include <asm/mach/arch.h>
 
-static const struct pinctrl_map marzen_pinctrl_map[] = {
-	/* SCIF2 (CN18: DEBUG0) */
-	PIN_MAP_MUX_GROUP_DEFAULT("sh-sci.2", "pfc-r8a7779",
-				  "scif2_data_c", "scif2"),
-	/* SCIF4 (CN19: DEBUG1) */
-	PIN_MAP_MUX_GROUP_DEFAULT("sh-sci.4", "pfc-r8a7779",
-				  "scif4_data", "scif4"),
-	/* SDHI0 */
-	PIN_MAP_MUX_GROUP_DEFAULT("sh_mobile_sdhi.0", "pfc-r8a7779",
-				  "sdhi0_data4", "sdhi0"),
-	PIN_MAP_MUX_GROUP_DEFAULT("sh_mobile_sdhi.0", "pfc-r8a7779",
-				  "sdhi0_ctrl", "sdhi0"),
-	PIN_MAP_MUX_GROUP_DEFAULT("sh_mobile_sdhi.0", "pfc-r8a7779",
-				  "sdhi0_cd", "sdhi0"),
-	PIN_MAP_MUX_GROUP_DEFAULT("sh_mobile_sdhi.0", "pfc-r8a7779",
-				  "sdhi0_wp", "sdhi0"),
-	/* SMSC */
-	PIN_MAP_MUX_GROUP_DEFAULT("smsc911x", "pfc-r8a7779",
-				  "intc_irq1_b", "intc"),
-	PIN_MAP_MUX_GROUP_DEFAULT("smsc911x", "pfc-r8a7779",
-				  "lbsc_ex_cs0", "lbsc"),
-};
-
 static void __init marzen_init(void)
 {
-	pinctrl_register_mappings(marzen_pinctrl_map,
-				  ARRAY_SIZE(marzen_pinctrl_map));
-	r8a7779_pinmux_init();
-
 	r8a7779_add_standard_devices_dt();
 }
 
@@ -70,6 +42,5 @@ DT_MACHINE_START(MARZEN, "marzen")
 	.nr_irqs	= NR_IRQS_LEGACY,
 	.init_irq	= r8a7779_init_irq_dt,
 	.init_machine	= marzen_init,
-	.init_time	= shmobile_timer_init,
 	.dt_compat	= marzen_boards_compat_dt,
 MACHINE_END
diff --git a/arch/arm/mach-shmobile/board-marzen.c b/arch/arm/mach-shmobile/board-marzen.c
index a7d1010505bf..3f5044fda4e3 100644
--- a/arch/arm/mach-shmobile/board-marzen.c
+++ b/arch/arm/mach-shmobile/board-marzen.c
@@ -1,8 +1,9 @@
 /*
  * marzen board support
  *
- * Copyright (C) 2011  Renesas Solutions Corp.
+ * Copyright (C) 2011, 2013  Renesas Solutions Corp.
  * Copyright (C) 2011  Magnus Damm
+ * Copyright (C) 2013  Cogent Embedded, Inc.
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -29,6 +30,7 @@
 #include <linux/dma-mapping.h>
 #include <linux/pinctrl/machine.h>
 #include <linux/platform_data/gpio-rcar.h>
+#include <linux/platform_data/usb-rcar-phy.h>
 #include <linux/regulator/fixed.h>
 #include <linux/regulator/machine.h>
 #include <linux/smsc911x.h>
@@ -37,7 +39,7 @@
 #include <linux/mmc/host.h>
 #include <linux/mmc/sh_mobile_sdhi.h>
 #include <linux/mfd/tmio.h>
-#include <mach/hardware.h>
+#include <media/soc_camera.h>
 #include <mach/r8a7779.h>
 #include <mach/common.h>
 #include <mach/irqs.h>
@@ -57,7 +59,26 @@ static struct regulator_consumer_supply dummy_supplies[] = {
 	REGULATOR_SUPPLY("vdd33a", "smsc911x"),
 };
 
-static struct rcar_phy_platform_data usb_phy_platform_data __initdata;
+/* USB PHY */
+static struct resource usb_phy_resources[] = {
+	[0] = {
+		.start		= 0xffe70800,
+		.end		= 0xffe70900 - 1,
+		.flags		= IORESOURCE_MEM,
+	},
+};
+
+static struct rcar_phy_platform_data usb_phy_platform_data;
+
+static struct platform_device usb_phy = {
+	.name		= "rcar_usb_phy",
+	.id		= -1,
+	.dev  = {
+		.platform_data = &usb_phy_platform_data,
+	},
+	.resource	= usb_phy_resources,
+	.num_resources	= ARRAY_SIZE(usb_phy_resources),
+};
 
 /* SMSC LAN89218 */
 static struct resource smsc911x_resources[] = {
@@ -178,12 +199,41 @@ static struct platform_device leds_device = {
 	},
 };
 
+static struct rcar_vin_platform_data vin_platform_data __initdata = {
+	.flags	= RCAR_VIN_BT656,
+};
+
+#define MARZEN_CAMERA(idx)					\
+static struct i2c_board_info camera##idx##_info = {		\
+	I2C_BOARD_INFO("adv7180", 0x20 + (idx)),		\
+};								\
+								\
+static struct soc_camera_link iclink##idx##_adv7180 = {		\
+	.bus_id		= 1 + 2 * (idx),			\
+	.i2c_adapter_id	= 0,					\
+	.board_info	= &camera##idx##_info,			\
+};								\
+								\
+static struct platform_device camera##idx##_device = {		\
+	.name	= "soc-camera-pdrv",				\
+	.id	= idx,						\
+	.dev	= {						\
+		.platform_data	= &iclink##idx##_adv7180,	\
+	},							\
+};
+
+MARZEN_CAMERA(0);
+MARZEN_CAMERA(1);
+
 static struct platform_device *marzen_devices[] __initdata = {
 	&eth_device,
 	&sdhi0_device,
 	&thermal_device,
 	&hspi_device,
 	&leds_device,
+	&usb_phy,
+	&camera0_device,
+	&camera1_device,
 };
 
 static const struct pinctrl_map marzen_pinctrl_map[] = {
@@ -219,6 +269,16 @@ static const struct pinctrl_map marzen_pinctrl_map[] = {
 	/* USB2 */
 	PIN_MAP_MUX_GROUP_DEFAULT("ehci-platform.1", "pfc-r8a7779",
 				  "usb2", "usb2"),
+	/* VIN1 */
+	PIN_MAP_MUX_GROUP_DEFAULT("r8a7779-vin.1", "pfc-r8a7779",
+				  "vin1_clk", "vin1"),
+	PIN_MAP_MUX_GROUP_DEFAULT("r8a7779-vin.1", "pfc-r8a7779",
+				  "vin1_data8", "vin1"),
+	/* VIN3 */
+	PIN_MAP_MUX_GROUP_DEFAULT("r8a7779-vin.3", "pfc-r8a7779",
+				  "vin3_clk", "vin3"),
+	PIN_MAP_MUX_GROUP_DEFAULT("r8a7779-vin.3", "pfc-r8a7779",
+				  "vin3_data8", "vin3"),
 };
 
 static void __init marzen_init(void)
@@ -234,17 +294,23 @@ static void __init marzen_init(void)
 	r8a7779_init_irq_extpin(1); /* IRQ1 as individual interrupt */
 
 	r8a7779_add_standard_devices();
-	r8a7779_add_usb_phy_device(&usb_phy_platform_data);
+	r8a7779_add_vin_device(1, &vin_platform_data);
+	r8a7779_add_vin_device(3, &vin_platform_data);
 	platform_add_devices(marzen_devices, ARRAY_SIZE(marzen_devices));
 }
 
-MACHINE_START(MARZEN, "marzen")
+static const char *marzen_boards_compat_dt[] __initdata = {
+        "renesas,marzen",
+        NULL,
+};
+
+DT_MACHINE_START(MARZEN, "marzen")
 	.smp		= smp_ops(r8a7779_smp_ops),
 	.map_io		= r8a7779_map_io,
 	.init_early	= r8a7779_add_early_devices,
-	.nr_irqs	= NR_IRQS_LEGACY,
-	.init_irq	= r8a7779_init_irq,
+	.init_irq	= r8a7779_init_irq_dt,
 	.init_machine	= marzen_init,
 	.init_late	= r8a7779_init_late,
+	.dt_compat	= marzen_boards_compat_dt,
 	.init_time	= r8a7779_earlytimer_init,
 MACHINE_END
diff --git a/arch/arm/mach-shmobile/clock-emev2.c b/arch/arm/mach-shmobile/clock-emev2.c
index 4710f1847bb7..5ac13ba71d54 100644
--- a/arch/arm/mach-shmobile/clock-emev2.c
+++ b/arch/arm/mach-shmobile/clock-emev2.c
@@ -40,7 +40,6 @@
 #define USIB2SCLKDIV 0x65c
 #define USIB3SCLKDIV 0x660
 #define STI_CLKSEL 0x688
-#define SMU_GENERAL_REG0 0x7c0
 
 /* not pretty, but hey */
 static void __iomem *smu_base;
@@ -51,11 +50,6 @@ static void emev2_smu_write(unsigned long value, int offs)
 	iowrite32(value, smu_base + offs);
 }
 
-void emev2_set_boot_vector(unsigned long value)
-{
-	emev2_smu_write(value, SMU_GENERAL_REG0);
-}
-
 static struct clk_mapping smu_mapping = {
 	.phys	= EMEV2_SMU_BASE,
 	.len	= PAGE_SIZE,
@@ -205,23 +199,11 @@ static struct clk_lookup lookups[] = {
 void __init emev2_clock_init(void)
 {
 	int k, ret = 0;
-	static int is_setup;
-
-	/* yuck, this is ugly as hell, but the non-smp case of clocks
-	 * code is now designed to rely on ioremap() instead of static
-	 * entity maps. in the case of smp we need access to the SMU
-	 * register earlier than ioremap() is actually working without
-	 * any static maps. to enable SMP in ugly but with dynamic
-	 * mappings we have to call emev2_clock_init() from different
-	 * places depending on UP and SMP...
-	 */
-	if (is_setup++)
-		return;
 
 	smu_base = ioremap(EMEV2_SMU_BASE, PAGE_SIZE);
 	BUG_ON(!smu_base);
 
-	/* setup STI timer to run on 37.768 kHz and deassert reset */
+	/* setup STI timer to run on 32.768 kHz and deassert reset */
 	emev2_smu_write(0, STI_CLKSEL);
 	emev2_smu_write(1, STI_RSTCTRL);
 
diff --git a/arch/arm/mach-shmobile/clock-r8a73a4.c b/arch/arm/mach-shmobile/clock-r8a73a4.c
index 5f7fe628b8a1..5bd2e851e3c7 100644
--- a/arch/arm/mach-shmobile/clock-r8a73a4.c
+++ b/arch/arm/mach-shmobile/clock-r8a73a4.c
@@ -30,10 +30,12 @@
 
 #define SMSTPCR2 0xe6150138
 #define SMSTPCR3 0xe615013c
+#define SMSTPCR4 0xe6150140
 #define SMSTPCR5 0xe6150144
 
 #define FRQCRA		0xE6150000
 #define FRQCRB		0xE6150004
+#define FRQCRC		0xE61500E0
 #define VCLKCR1		0xE6150008
 #define VCLKCR2		0xE615000C
 #define VCLKCR3		0xE615001C
@@ -52,6 +54,7 @@
 #define HSICKCR		0xE615026C
 #define M4CKCR		0xE6150098
 #define PLLECR		0xE61500D0
+#define PLL0CR		0xE61500D8
 #define PLL1CR		0xE6150028
 #define PLL2CR		0xE615002C
 #define PLL2SCR		0xE61501F4
@@ -177,6 +180,7 @@ static struct sh_clk_ops pll_clk_ops = {
 		.mapping	= &cpg_mapping,		\
 	}
 
+PLL_CLOCK(pll0_clk,  &main_clk,      pll_parent_main,      1, 20, PLL0CR,  0);
 PLL_CLOCK(pll1_clk,  &main_clk,      pll_parent_main,       1, 7, PLL1CR,  1);
 PLL_CLOCK(pll2_clk,  &main_div2_clk, pll_parent_main_extal, 3, 5, PLL2CR,  2);
 PLL_CLOCK(pll2s_clk, &main_div2_clk, pll_parent_main_extal, 3, 5, PLL2SCR, 4);
@@ -184,6 +188,157 @@ PLL_CLOCK(pll2h_clk, &main_div2_clk, pll_parent_main_extal, 3, 5, PLL2HCR, 5);
 
 SH_FIXED_RATIO_CLK(pll1_div2_clk,	pll1_clk,	div2);
 
+static atomic_t frqcr_lock;
+
+/* Several clocks need to access FRQCRB, have to lock */
+static bool frqcr_kick_check(struct clk *clk)
+{
+	return !(ioread32(CPG_MAP(FRQCRB)) & BIT(31));
+}
+
+static int frqcr_kick_do(struct clk *clk)
+{
+	int i;
+
+	/* set KICK bit in FRQCRB to update hardware setting, check success */
+	iowrite32(ioread32(CPG_MAP(FRQCRB)) | BIT(31), CPG_MAP(FRQCRB));
+	for (i = 1000; i; i--)
+		if (ioread32(CPG_MAP(FRQCRB)) & BIT(31))
+			cpu_relax();
+		else
+			return 0;
+
+	return -ETIMEDOUT;
+}
+
+static int zclk_set_rate(struct clk *clk, unsigned long rate)
+{
+	void __iomem *frqcrc;
+	int ret;
+	unsigned long step, p_rate;
+	u32 val;
+
+	if (!clk->parent || !__clk_get(clk->parent))
+		return -ENODEV;
+
+	if (!atomic_inc_and_test(&frqcr_lock) || !frqcr_kick_check(clk)) {
+		ret = -EBUSY;
+		goto done;
+	}
+
+	/*
+	 * Users are supposed to first call clk_set_rate() only with
+	 * clk_round_rate() results. So, we don't fix wrong rates here, but
+	 * guard against them anyway
+	 */
+
+	p_rate = clk_get_rate(clk->parent);
+	if (rate == p_rate) {
+		val = 0;
+	} else {
+		step = DIV_ROUND_CLOSEST(p_rate, 32);
+
+		if (rate > p_rate || rate < step) {
+			ret = -EINVAL;
+			goto done;
+		}
+
+		val = 32 - rate / step;
+	}
+
+	frqcrc = clk->mapped_reg + (FRQCRC - (u32)clk->enable_reg);
+
+	iowrite32((ioread32(frqcrc) & ~(clk->div_mask << clk->enable_bit)) |
+		  (val << clk->enable_bit), frqcrc);
+
+	ret = frqcr_kick_do(clk);
+
+done:
+	atomic_dec(&frqcr_lock);
+	__clk_put(clk->parent);
+	return ret;
+}
+
+static long zclk_round_rate(struct clk *clk, unsigned long rate)
+{
+	/*
+	 * theoretical rate = parent rate * multiplier / 32,
+	 * where 1 <= multiplier <= 32. Therefore we should do
+	 * multiplier = rate * 32 / parent rate
+	 * rounded rate = parent rate * multiplier / 32.
+	 * However, multiplication before division won't fit in 32 bits, so
+	 * we sacrifice some precision by first dividing and then multiplying.
+	 * To find the nearest divisor we calculate both and pick up the best
+	 * one. This avoids 64-bit arithmetics.
+	 */
+	unsigned long step, mul_min, mul_max, rate_min, rate_max;
+
+	rate_max = clk_get_rate(clk->parent);
+
+	/* output freq <= parent */
+	if (rate >= rate_max)
+		return rate_max;
+
+	step = DIV_ROUND_CLOSEST(rate_max, 32);
+	/* output freq >= parent / 32 */
+	if (step >= rate)
+		return step;
+
+	mul_min = rate / step;
+	mul_max = DIV_ROUND_UP(rate, step);
+	rate_min = step * mul_min;
+	if (mul_max == mul_min)
+		return rate_min;
+
+	rate_max = step * mul_max;
+
+	if (rate_max - rate <  rate - rate_min)
+		return rate_max;
+
+	return rate_min;
+}
+
+static unsigned long zclk_recalc(struct clk *clk)
+{
+	void __iomem *frqcrc = FRQCRC - (u32)clk->enable_reg + clk->mapped_reg;
+	unsigned int max = clk->div_mask + 1;
+	unsigned long val = ((ioread32(frqcrc) >> clk->enable_bit) &
+			     clk->div_mask);
+
+	return DIV_ROUND_CLOSEST(clk_get_rate(clk->parent), max) *
+		(max - val);
+}
+
+static struct sh_clk_ops zclk_ops = {
+	.recalc = zclk_recalc,
+	.set_rate = zclk_set_rate,
+	.round_rate = zclk_round_rate,
+};
+
+static struct clk z_clk = {
+	.parent = &pll0_clk,
+	.div_mask = 0x1f,
+	.enable_bit = 8,
+	/* We'll need to access FRQCRB and FRQCRC */
+	.enable_reg = (void __iomem *)FRQCRB,
+	.ops = &zclk_ops,
+};
+
+/*
+ * It seems only 1/2 divider is usable in manual mode. 1/2 / 2/3
+ * switching is only available in auto-DVFS mode
+ */
+SH_FIXED_RATIO_CLK(pll0_div2_clk,	pll0_clk,		div2);
+
+static struct clk z2_clk = {
+	.parent = &pll0_div2_clk,
+	.div_mask = 0x1f,
+	.enable_bit = 0,
+	/* We'll need to access FRQCRB and FRQCRC */
+	.enable_reg = (void __iomem *)FRQCRB,
+	.ops = &zclk_ops,
+};
+
 static struct clk *main_clks[] = {
 	&extalr_clk,
 	&extal1_clk,
@@ -195,22 +350,23 @@ static struct clk *main_clks[] = {
 	&main_div2_clk,
 	&fsiack_clk,
 	&fsibck_clk,
+	&pll0_clk,
 	&pll1_clk,
 	&pll1_div2_clk,
 	&pll2_clk,
 	&pll2s_clk,
 	&pll2h_clk,
+	&z_clk,
+	&pll0_div2_clk,
+	&z2_clk,
 };
 
 /* DIV4 */
 static void div4_kick(struct clk *clk)
 {
-	unsigned long value;
-
-	/* set KICK bit in FRQCRB to update hardware setting */
-	value = ioread32(CPG_MAP(FRQCRB));
-	value |= (1 << 31);
-	iowrite32(value, CPG_MAP(FRQCRB));
+	if (!WARN(!atomic_inc_and_test(&frqcr_lock), "FRQCR* lock broken!\n"))
+		frqcr_kick_do(clk);
+	atomic_dec(&frqcr_lock);
 }
 
 static int divisors[] = { 2, 3, 4, 6, 8, 12, 16, 18, 24, 0, 36, 48, 10};
@@ -349,8 +505,10 @@ static struct clk div6_clks[DIV6_NR] = {
 /* MSTP */
 enum {
 	MSTP217, MSTP216, MSTP207, MSTP206, MSTP204, MSTP203,
-	MSTP315, MSTP314, MSTP313, MSTP312, MSTP305,
-	MSTP522,
+	MSTP329, MSTP323, MSTP318, MSTP317, MSTP316,
+	MSTP315, MSTP314, MSTP313, MSTP312, MSTP305, MSTP300,
+	MSTP411, MSTP410, MSTP409,
+	MSTP522, MSTP515,
 	MSTP_NR
 };
 
@@ -361,12 +519,22 @@ static struct clk mstp_clks[MSTP_NR] = {
 	[MSTP207] = SH_CLK_MSTP32(&div6_clks[DIV6_MP],	SMSTPCR2, 7, 0), /* SCIFB1 */
 	[MSTP216] = SH_CLK_MSTP32(&div6_clks[DIV6_MP],	SMSTPCR2, 16, 0), /* SCIFB2 */
 	[MSTP217] = SH_CLK_MSTP32(&div6_clks[DIV6_MP],	SMSTPCR2, 17, 0), /* SCIFB3 */
+	[MSTP300] = SH_CLK_MSTP32(&div4_clks[DIV4_HP],	SMSTPCR3, 0, 0), /* IIC2 */
 	[MSTP305] = SH_CLK_MSTP32(&div6_clks[DIV6_MMC1],SMSTPCR3, 5, 0), /* MMCIF1 */
 	[MSTP312] = SH_CLK_MSTP32(&div6_clks[DIV6_SDHI2],SMSTPCR3, 12, 0), /* SDHI2 */
 	[MSTP313] = SH_CLK_MSTP32(&div6_clks[DIV6_SDHI1],SMSTPCR3, 13, 0), /* SDHI1 */
 	[MSTP314] = SH_CLK_MSTP32(&div6_clks[DIV6_SDHI0],SMSTPCR3, 14, 0), /* SDHI0 */
 	[MSTP315] = SH_CLK_MSTP32(&div6_clks[DIV6_MMC0],SMSTPCR3, 15, 0), /* MMCIF0 */
+	[MSTP316] = SH_CLK_MSTP32(&div4_clks[DIV4_HP],	SMSTPCR3, 16, 0), /* IIC6 */
+	[MSTP317] = SH_CLK_MSTP32(&div4_clks[DIV4_HP],	SMSTPCR3, 17, 0), /* IIC7 */
+	[MSTP318] = SH_CLK_MSTP32(&div4_clks[DIV4_HP],	SMSTPCR3, 18, 0), /* IIC0 */
+	[MSTP323] = SH_CLK_MSTP32(&div4_clks[DIV4_HP],	SMSTPCR3, 23, 0), /* IIC1 */
+	[MSTP329] = SH_CLK_MSTP32(&extalr_clk, SMSTPCR3, 29, 0), /* CMT10 */
+	[MSTP409] = SH_CLK_MSTP32(&main_div2_clk,	SMSTPCR4, 9, 0), /* IIC5 */
+	[MSTP410] = SH_CLK_MSTP32(&div4_clks[DIV4_HP],	SMSTPCR4, 10, 0), /* IIC4 */
+	[MSTP411] = SH_CLK_MSTP32(&div4_clks[DIV4_HP],	SMSTPCR4, 11, 0), /* IIC3 */
 	[MSTP522] = SH_CLK_MSTP32(&extal2_clk, SMSTPCR5, 22, 0), /* Thermal */
+	[MSTP515] = SH_CLK_MSTP32(&div4_clks[DIV4_HP],	SMSTPCR5, 15, 0), /* IIC8 */
 };
 
 static struct clk_lookup lookups[] = {
@@ -386,6 +554,9 @@ static struct clk_lookup lookups[] = {
 	CLKDEV_CON_ID("pll2s",			&pll2s_clk),
 	CLKDEV_CON_ID("pll2h",			&pll2h_clk),
 
+	/* CPU clock */
+	CLKDEV_DEV_ID("cpu0",			&z_clk),
+
 	/* DIV6 */
 	CLKDEV_CON_ID("zb",			&div6_clks[DIV6_ZB]),
 	CLKDEV_CON_ID("vck1",			&div6_clks[DIV6_VCK1]),
@@ -408,6 +579,7 @@ static struct clk_lookup lookups[] = {
 	CLKDEV_DEV_ID("sh-sci.4", &mstp_clks[MSTP216]),
 	CLKDEV_DEV_ID("sh-sci.5", &mstp_clks[MSTP217]),
 	CLKDEV_DEV_ID("rcar_thermal", &mstp_clks[MSTP522]),
+	CLKDEV_DEV_ID("e6520000.i2c", &mstp_clks[MSTP300]),
 	CLKDEV_DEV_ID("sh_mmcif.1", &mstp_clks[MSTP305]),
 	CLKDEV_DEV_ID("ee220000.mmcif", &mstp_clks[MSTP305]),
 	CLKDEV_DEV_ID("sh_mobile_sdhi.2", &mstp_clks[MSTP312]),
@@ -418,6 +590,15 @@ static struct clk_lookup lookups[] = {
 	CLKDEV_DEV_ID("ee100000.sdhi", &mstp_clks[MSTP314]),
 	CLKDEV_DEV_ID("sh_mmcif.0", &mstp_clks[MSTP315]),
 	CLKDEV_DEV_ID("ee200000.mmcif", &mstp_clks[MSTP315]),
+	CLKDEV_DEV_ID("e6550000.i2c", &mstp_clks[MSTP316]),
+	CLKDEV_DEV_ID("e6560000.i2c", &mstp_clks[MSTP317]),
+	CLKDEV_DEV_ID("e6500000.i2c", &mstp_clks[MSTP318]),
+	CLKDEV_DEV_ID("e6510000.i2c", &mstp_clks[MSTP323]),
+	CLKDEV_DEV_ID("sh_cmt.10", &mstp_clks[MSTP329]),
+	CLKDEV_DEV_ID("e60b0000.i2c", &mstp_clks[MSTP409]),
+	CLKDEV_DEV_ID("e6540000.i2c", &mstp_clks[MSTP410]),
+	CLKDEV_DEV_ID("e6530000.i2c", &mstp_clks[MSTP411]),
+	CLKDEV_DEV_ID("e6570000.i2c", &mstp_clks[MSTP515]),
 
 	/* for DT */
 	CLKDEV_DEV_ID("e61f0000.thermal", &mstp_clks[MSTP522]),
@@ -429,6 +610,8 @@ void __init r8a73a4_clock_init(void)
 	int k, ret = 0;
 	u32 ckscr;
 
+	atomic_set(&frqcr_lock, -1);
+
 	reg = ioremap_nocache(CKSCR, PAGE_SIZE);
 	BUG_ON(!reg);
 	ckscr = ioread32(reg);
diff --git a/arch/arm/mach-shmobile/clock-r8a7740.c b/arch/arm/mach-shmobile/clock-r8a7740.c
index de10fd78bf2b..c826bca4024e 100644
--- a/arch/arm/mach-shmobile/clock-r8a7740.c
+++ b/arch/arm/mach-shmobile/clock-r8a7740.c
@@ -596,7 +596,8 @@ static struct clk_lookup lookups[] = {
 	CLKDEV_DEV_ID("e6bd0000.mmcif",         &mstp_clks[MSTP312]),
 	CLKDEV_DEV_ID("r8a7740-gether",		&mstp_clks[MSTP309]),
 	CLKDEV_DEV_ID("e9a00000.sh-eth",	&mstp_clks[MSTP309]),
-	CLKDEV_DEV_ID("renesas_tpu_pwm",	&mstp_clks[MSTP304]),
+	CLKDEV_DEV_ID("renesas-tpu-pwm",	&mstp_clks[MSTP304]),
+	CLKDEV_DEV_ID("e6600000.pwm",		&mstp_clks[MSTP304]),
 
 	CLKDEV_DEV_ID("sh_mobile_sdhi.2",	&mstp_clks[MSTP415]),
 	CLKDEV_DEV_ID("e6870000.sdhi",          &mstp_clks[MSTP415]),
diff --git a/arch/arm/mach-shmobile/clock-r8a7778.c b/arch/arm/mach-shmobile/clock-r8a7778.c
index a0e9eb72e46d..c4bf2d8fb111 100644
--- a/arch/arm/mach-shmobile/clock-r8a7778.c
+++ b/arch/arm/mach-shmobile/clock-r8a7778.c
@@ -106,6 +106,7 @@ enum {
 	MSTP331,
 	MSTP323, MSTP322, MSTP321,
 	MSTP114,
+	MSTP110, MSTP109,
 	MSTP100,
 	MSTP030,
 	MSTP029, MSTP028, MSTP027, MSTP026, MSTP025, MSTP024, MSTP023, MSTP022, MSTP021,
@@ -119,6 +120,8 @@ static struct clk mstp_clks[MSTP_NR] = {
 	[MSTP322] = SH_CLK_MSTP32(&p_clk, MSTPCR3, 22, 0), /* SDHI1 */
 	[MSTP321] = SH_CLK_MSTP32(&p_clk, MSTPCR3, 21, 0), /* SDHI2 */
 	[MSTP114] = SH_CLK_MSTP32(&p_clk, MSTPCR1, 14, 0), /* Ether */
+	[MSTP110] = SH_CLK_MSTP32(&s_clk, MSTPCR1, 10, 0), /* VIN0 */
+	[MSTP109] = SH_CLK_MSTP32(&s_clk, MSTPCR1,  9, 0), /* VIN1 */
 	[MSTP100] = SH_CLK_MSTP32(&p_clk, MSTPCR1,  0, 0), /* USB0/1 */
 	[MSTP030] = SH_CLK_MSTP32(&p_clk, MSTPCR0, 30, 0), /* I2C0 */
 	[MSTP029] = SH_CLK_MSTP32(&p_clk, MSTPCR0, 29, 0), /* I2C1 */
@@ -146,6 +149,8 @@ static struct clk_lookup lookups[] = {
 	CLKDEV_DEV_ID("sh_mobile_sdhi.1", &mstp_clks[MSTP322]), /* SDHI1 */
 	CLKDEV_DEV_ID("sh_mobile_sdhi.2", &mstp_clks[MSTP321]), /* SDHI2 */
 	CLKDEV_DEV_ID("r8a777x-ether", &mstp_clks[MSTP114]), /* Ether */
+	CLKDEV_DEV_ID("r8a7778-vin.0", &mstp_clks[MSTP110]), /* VIN0 */
+	CLKDEV_DEV_ID("r8a7778-vin.1", &mstp_clks[MSTP109]), /* VIN1 */
 	CLKDEV_DEV_ID("ehci-platform", &mstp_clks[MSTP100]), /* USB EHCI port0/1 */
 	CLKDEV_DEV_ID("ohci-platform", &mstp_clks[MSTP100]), /* USB OHCI port0/1 */
 	CLKDEV_DEV_ID("i2c-rcar.0", &mstp_clks[MSTP030]), /* I2C0 */
diff --git a/arch/arm/mach-shmobile/clock-r8a7779.c b/arch/arm/mach-shmobile/clock-r8a7779.c
index 10340f5becbb..bd6ad922eb7e 100644
--- a/arch/arm/mach-shmobile/clock-r8a7779.c
+++ b/arch/arm/mach-shmobile/clock-r8a7779.c
@@ -112,7 +112,9 @@ static struct clk *main_clks[] = {
 };
 
 enum { MSTP323, MSTP322, MSTP321, MSTP320,
+	MSTP120,
 	MSTP116, MSTP115, MSTP114,
+	MSTP110, MSTP109, MSTP108,
 	MSTP103, MSTP101, MSTP100,
 	MSTP030,
 	MSTP029, MSTP028, MSTP027, MSTP026, MSTP025, MSTP024, MSTP023, MSTP022, MSTP021,
@@ -125,9 +127,13 @@ static struct clk mstp_clks[MSTP_NR] = {
 	[MSTP322] = SH_CLK_MSTP32(&clkp_clk, MSTPCR3, 22, 0), /* SDHI1 */
 	[MSTP321] = SH_CLK_MSTP32(&clkp_clk, MSTPCR3, 21, 0), /* SDHI2 */
 	[MSTP320] = SH_CLK_MSTP32(&clkp_clk, MSTPCR3, 20, 0), /* SDHI3 */
+	[MSTP120] = SH_CLK_MSTP32(&clks_clk, MSTPCR1, 20, 0), /* VIN3 */
 	[MSTP116] = SH_CLK_MSTP32(&clkp_clk, MSTPCR1, 16, 0), /* PCIe */
 	[MSTP115] = SH_CLK_MSTP32(&clkp_clk, MSTPCR1, 15, 0), /* SATA */
 	[MSTP114] = SH_CLK_MSTP32(&clkp_clk, MSTPCR1, 14, 0), /* Ether */
+	[MSTP110] = SH_CLK_MSTP32(&clks_clk, MSTPCR1, 10, 0), /* VIN0 */
+	[MSTP109] = SH_CLK_MSTP32(&clks_clk, MSTPCR1,  9, 0), /* VIN1 */
+	[MSTP108] = SH_CLK_MSTP32(&clks_clk, MSTPCR1,  8, 0), /* VIN2 */
 	[MSTP103] = SH_CLK_MSTP32(&clks_clk, MSTPCR1,  3, 0), /* DU */
 	[MSTP101] = SH_CLK_MSTP32(&clkp_clk, MSTPCR1,  1, 0), /* USB2 */
 	[MSTP100] = SH_CLK_MSTP32(&clkp_clk, MSTPCR1,  0, 0), /* USB0/1 */
@@ -162,10 +168,14 @@ static struct clk_lookup lookups[] = {
 	CLKDEV_CON_ID("peripheral_clk",	&clkp_clk),
 
 	/* MSTP32 clocks */
+	CLKDEV_DEV_ID("r8a7779-vin.3", &mstp_clks[MSTP120]), /* VIN3 */
 	CLKDEV_DEV_ID("rcar-pcie", &mstp_clks[MSTP116]), /* PCIe */
 	CLKDEV_DEV_ID("sata_rcar", &mstp_clks[MSTP115]), /* SATA */
 	CLKDEV_DEV_ID("fc600000.sata", &mstp_clks[MSTP115]), /* SATA w/DT */
 	CLKDEV_DEV_ID("r8a777x-ether", &mstp_clks[MSTP114]), /* Ether */
+	CLKDEV_DEV_ID("r8a7779-vin.0", &mstp_clks[MSTP110]), /* VIN0 */
+	CLKDEV_DEV_ID("r8a7779-vin.1", &mstp_clks[MSTP109]), /* VIN1 */
+	CLKDEV_DEV_ID("r8a7779-vin.2", &mstp_clks[MSTP108]), /* VIN2 */
 	CLKDEV_DEV_ID("ehci-platform.1", &mstp_clks[MSTP101]), /* USB EHCI port2 */
 	CLKDEV_DEV_ID("ohci-platform.1", &mstp_clks[MSTP101]), /* USB OHCI port2 */
 	CLKDEV_DEV_ID("ehci-platform.0", &mstp_clks[MSTP100]), /* USB EHCI port0/1 */
diff --git a/arch/arm/mach-shmobile/clock-r8a7790.c b/arch/arm/mach-shmobile/clock-r8a7790.c
index 5d71313df52d..fc36d3db0b4d 100644
--- a/arch/arm/mach-shmobile/clock-r8a7790.c
+++ b/arch/arm/mach-shmobile/clock-r8a7790.c
@@ -24,6 +24,7 @@
 #include <linux/clkdev.h>
 #include <mach/clock.h>
 #include <mach/common.h>
+#include <mach/r8a7790.h>
 
 /*
  *   MD		EXTAL		PLL0	PLL1	PLL3
@@ -42,16 +43,16 @@
  *	see "p1 / 2" on R8A7790_CLOCK_ROOT() below
  */
 
-#define MD(nr)	(1 << nr)
-
 #define CPG_BASE 0xe6150000
 #define CPG_LEN 0x1000
 
+#define SMSTPCR1 0xe6150134
 #define SMSTPCR2 0xe6150138
 #define SMSTPCR3 0xe615013c
+#define SMSTPCR5 0xe6150144
 #define SMSTPCR7 0xe615014c
+#define SMSTPCR8 0xe6150990
 
-#define MODEMR		0xE6160060
 #define SDCKCR		0xE6150074
 #define SD2CKCR		0xE6150078
 #define SD3CKCR		0xE615007C
@@ -180,16 +181,23 @@ static struct clk div6_clks[DIV6_NR] = {
 
 /* MSTP */
 enum {
+	MSTP813,
 	MSTP721, MSTP720,
 	MSTP717, MSTP716,
+	MSTP522,
 	MSTP315, MSTP314, MSTP313, MSTP312, MSTP311, MSTP305, MSTP304,
 	MSTP216, MSTP207, MSTP206, MSTP204, MSTP203, MSTP202,
+	MSTP124,
 	MSTP_NR
 };
 
 static struct clk mstp_clks[MSTP_NR] = {
+	[MSTP813] = SH_CLK_MSTP32(&p_clk, SMSTPCR8, 13, 0), /* Ether */
 	[MSTP721] = SH_CLK_MSTP32(&p_clk, SMSTPCR7, 21, 0), /* SCIF0 */
 	[MSTP720] = SH_CLK_MSTP32(&p_clk, SMSTPCR7, 20, 0), /* SCIF1 */
+	[MSTP717] = SH_CLK_MSTP32(&zs_clk, SMSTPCR7, 17, 0), /* HSCIF0 */
+	[MSTP716] = SH_CLK_MSTP32(&zs_clk, SMSTPCR7, 16, 0), /* HSCIF1 */
+	[MSTP522] = SH_CLK_MSTP32(&extal_clk, SMSTPCR5, 22, 0), /* Thermal */
 	[MSTP315] = SH_CLK_MSTP32(&div6_clks[DIV6_MMC0], SMSTPCR3, 15, 0), /* MMC0 */
 	[MSTP314] = SH_CLK_MSTP32(&div4_clks[DIV4_SD0], SMSTPCR3, 14, 0), /* SDHI0 */
 	[MSTP313] = SH_CLK_MSTP32(&div4_clks[DIV4_SD1], SMSTPCR3, 13, 0), /* SDHI1 */
@@ -203,8 +211,7 @@ static struct clk mstp_clks[MSTP_NR] = {
 	[MSTP204] = SH_CLK_MSTP32(&mp_clk, SMSTPCR2, 4, 0), /* SCIFA0 */
 	[MSTP203] = SH_CLK_MSTP32(&mp_clk, SMSTPCR2, 3, 0), /* SCIFA1 */
 	[MSTP202] = SH_CLK_MSTP32(&mp_clk, SMSTPCR2, 2, 0), /* SCIFA2 */
-	[MSTP717] = SH_CLK_MSTP32(&zs_clk, SMSTPCR7, 17, 0), /* HSCIF0 */
-	[MSTP716] = SH_CLK_MSTP32(&zs_clk, SMSTPCR7, 16, 0), /* HSCIF1 */
+	[MSTP124] = SH_CLK_MSTP32(&rclk_clk, SMSTPCR1, 24, 0), /* CMT0 */
 };
 
 static struct clk_lookup lookups[] = {
@@ -254,6 +261,8 @@ static struct clk_lookup lookups[] = {
 	CLKDEV_DEV_ID("sh-sci.7", &mstp_clks[MSTP720]),
 	CLKDEV_DEV_ID("sh-sci.8", &mstp_clks[MSTP717]),
 	CLKDEV_DEV_ID("sh-sci.9", &mstp_clks[MSTP716]),
+	CLKDEV_DEV_ID("r8a7790-ether", &mstp_clks[MSTP813]),
+	CLKDEV_DEV_ID("rcar_thermal", &mstp_clks[MSTP522]),
 	CLKDEV_DEV_ID("ee200000.mmcif", &mstp_clks[MSTP315]),
 	CLKDEV_DEV_ID("sh_mmcif.0", &mstp_clks[MSTP315]),
 	CLKDEV_DEV_ID("ee100000.sdhi", &mstp_clks[MSTP314]),
@@ -266,6 +275,7 @@ static struct clk_lookup lookups[] = {
 	CLKDEV_DEV_ID("sh_mobile_sdhi.3", &mstp_clks[MSTP311]),
 	CLKDEV_DEV_ID("ee220000.mmcif", &mstp_clks[MSTP305]),
 	CLKDEV_DEV_ID("sh_mmcif.1", &mstp_clks[MSTP305]),
+	CLKDEV_DEV_ID("sh_cmt.0", &mstp_clks[MSTP124]),
 };
 
 #define R8A7790_CLOCK_ROOT(e, m, p0, p1, p30, p31)		\
@@ -280,14 +290,9 @@ static struct clk_lookup lookups[] = {
 
 void __init r8a7790_clock_init(void)
 {
-	void __iomem *modemr = ioremap_nocache(MODEMR, PAGE_SIZE);
-	u32 mode;
+	u32 mode = r8a7790_read_mode_pins();
 	int k, ret = 0;
 
-	BUG_ON(!modemr);
-	mode = ioread32(modemr);
-	iounmap(modemr);
-
 	switch (mode & (MD(14) | MD(13))) {
 	case 0:
 		R8A7790_CLOCK_ROOT(15, &extal_clk, 172, 208, 106, 88);
diff --git a/arch/arm/mach-shmobile/clock-sh73a0.c b/arch/arm/mach-shmobile/clock-sh73a0.c
index d9fd0336b910..c92c023f0d27 100644
--- a/arch/arm/mach-shmobile/clock-sh73a0.c
+++ b/arch/arm/mach-shmobile/clock-sh73a0.c
@@ -555,7 +555,7 @@ enum { MSTP001,
 	MSTP207, MSTP206, MSTP204, MSTP203, MSTP202, MSTP201, MSTP200,
 	MSTP331, MSTP329, MSTP328, MSTP325, MSTP323, MSTP322,
 	MSTP314, MSTP313, MSTP312, MSTP311,
-	MSTP303, MSTP302, MSTP301, MSTP300,
+	MSTP304, MSTP303, MSTP302, MSTP301, MSTP300,
 	MSTP411, MSTP410, MSTP403,
 	MSTP_NR };
 
@@ -593,6 +593,7 @@ static struct clk mstp_clks[MSTP_NR] = {
 	[MSTP313] = MSTP(&div6_clks[DIV6_SDHI1], SMSTPCR3, 13, 0), /* SDHI1 */
 	[MSTP312] = MSTP(&div4_clks[DIV4_HP], SMSTPCR3, 12, 0), /* MMCIF0 */
 	[MSTP311] = MSTP(&div6_clks[DIV6_SDHI2], SMSTPCR3, 11, 0), /* SDHI2 */
+	[MSTP304] = MSTP(&main_div2_clk, SMSTPCR3, 4, 0), /* TPU0 */
 	[MSTP303] = MSTP(&main_div2_clk, SMSTPCR3, 3, 0), /* TPU1 */
 	[MSTP302] = MSTP(&main_div2_clk, SMSTPCR3, 2, 0), /* TPU2 */
 	[MSTP301] = MSTP(&main_div2_clk, SMSTPCR3, 1, 0), /* TPU3 */
@@ -615,7 +616,7 @@ static struct clk_lookup lookups[] = {
 	CLKDEV_DEV_ID("smp_twd", &twd_clk), /* smp_twd */
 
 	/* DIV4 clocks */
-	CLKDEV_DEV_ID("cpufreq-cpu0", &div4_clks[DIV4_Z]),
+	CLKDEV_DEV_ID("cpu0", &div4_clks[DIV4_Z]),
 
 	/* DIV6 clocks */
 	CLKDEV_CON_ID("vck1_clk", &div6_clks[DIV6_VCK1]),
@@ -669,10 +670,11 @@ static struct clk_lookup lookups[] = {
 	CLKDEV_DEV_ID("e6bd0000.mmcif", &mstp_clks[MSTP312]), /* MMCIF0 */
 	CLKDEV_DEV_ID("sh_mobile_sdhi.2", &mstp_clks[MSTP311]), /* SDHI2 */
 	CLKDEV_DEV_ID("ee140000.sdhi", &mstp_clks[MSTP311]), /* SDHI2 */
-	CLKDEV_DEV_ID("leds-renesas-tpu.12", &mstp_clks[MSTP303]), /* TPU1 */
-	CLKDEV_DEV_ID("leds-renesas-tpu.21", &mstp_clks[MSTP302]), /* TPU2 */
-	CLKDEV_DEV_ID("leds-renesas-tpu.30", &mstp_clks[MSTP301]), /* TPU3 */
-	CLKDEV_DEV_ID("leds-renesas-tpu.41", &mstp_clks[MSTP300]), /* TPU4 */
+	CLKDEV_DEV_ID("renesas-tpu-pwm.0", &mstp_clks[MSTP304]), /* TPU0 */
+	CLKDEV_DEV_ID("renesas-tpu-pwm.1", &mstp_clks[MSTP303]), /* TPU1 */
+	CLKDEV_DEV_ID("renesas-tpu-pwm.2", &mstp_clks[MSTP302]), /* TPU2 */
+	CLKDEV_DEV_ID("renesas-tpu-pwm.3", &mstp_clks[MSTP301]), /* TPU3 */
+	CLKDEV_DEV_ID("renesas-tpu-pwm.4", &mstp_clks[MSTP300]), /* TPU4 */
 	CLKDEV_DEV_ID("i2c-sh_mobile.3", &mstp_clks[MSTP411]), /* I2C3 */
 	CLKDEV_DEV_ID("e6826000.i2c", &mstp_clks[MSTP411]), /* I2C3 */
 	CLKDEV_DEV_ID("i2c-sh_mobile.4", &mstp_clks[MSTP410]), /* I2C4 */
diff --git a/arch/arm/mach-shmobile/headsmp-scu.S b/arch/arm/mach-shmobile/headsmp-scu.S
index bfd920083a3b..f45dde701d7b 100644
--- a/arch/arm/mach-shmobile/headsmp-scu.S
+++ b/arch/arm/mach-shmobile/headsmp-scu.S
@@ -37,13 +37,15 @@ ENTRY(shmobile_boot_scu)
 	lsl	r1, r1, #3		@ we will shift by cpu_id * 8 bits
 	ldr	r2, [r0, #8]		@ SCU Power Status Register
 	mov	r3, #3
-	bic	r2, r2, r3, lsl r1	@ Clear bits of our CPU (Run Mode)
+	lsl	r3, r3, r1
+	bic	r2, r2, r3		@ Clear bits of our CPU (Run Mode)
 	str	r2, [r0, #8]		@ write back
 
 	b	shmobile_invalidate_start
 ENDPROC(shmobile_boot_scu)
 
 	.text
+	.align	2
 	.globl	shmobile_scu_base
 shmobile_scu_base:
 	.space	4
diff --git a/arch/arm/mach-shmobile/headsmp.S b/arch/arm/mach-shmobile/headsmp.S
index a9d212498987..f93751caf5cb 100644
--- a/arch/arm/mach-shmobile/headsmp.S
+++ b/arch/arm/mach-shmobile/headsmp.S
@@ -24,15 +24,68 @@ ENDPROC(shmobile_invalidate_start)
  * This will be mapped at address 0 by SBAR register.
  * We need _long_ jump to the physical address.
  */
+	.arm
 	.align  12
 ENTRY(shmobile_boot_vector)
 	ldr     r0, 2f
-	ldr     pc, 1f
+	ldr     r1, 1f
+	bx	r1
+
 ENDPROC(shmobile_boot_vector)
 
+	.align	2
 	.globl	shmobile_boot_fn
 shmobile_boot_fn:
 1:	.space	4
 	.globl	shmobile_boot_arg
 shmobile_boot_arg:
 2:	.space	4
+
+/*
+ * Per-CPU SMP boot function/argument selection code based on MPIDR
+ */
+
+ENTRY(shmobile_smp_boot)
+						@ r0 = MPIDR_HWID_BITMASK
+	mrc	p15, 0, r1, c0, c0, 5		@ r1 = MPIDR
+	and	r0, r1, r0			@ r0 = cpu_logical_map() value
+	mov	r1, #0				@ r1 = CPU index
+	adr	r5, 1f				@ array of per-cpu mpidr values
+	adr	r6, 2f				@ array of per-cpu functions
+	adr	r7, 3f				@ array of per-cpu arguments
+
+shmobile_smp_boot_find_mpidr:
+	ldr	r8, [r5, r1, lsl #2]
+	cmp	r8, r0
+	bne	shmobile_smp_boot_next
+
+	ldr	r9, [r6, r1, lsl #2]
+	cmp	r9, #0
+	bne	shmobile_smp_boot_found
+
+shmobile_smp_boot_next:
+	add	r1, r1, #1
+	cmp	r1, #CONFIG_NR_CPUS
+	blo	shmobile_smp_boot_find_mpidr
+
+	b	shmobile_smp_sleep
+
+shmobile_smp_boot_found:
+	ldr	r0, [r7, r1, lsl #2]
+	mov	pc, r9
+ENDPROC(shmobile_smp_boot)
+
+ENTRY(shmobile_smp_sleep)
+	wfi
+	b	shmobile_smp_boot
+ENDPROC(shmobile_smp_sleep)
+
+	.globl	shmobile_smp_mpidr
+shmobile_smp_mpidr:
+1:	.space	CONFIG_NR_CPUS * 4
+	.globl	shmobile_smp_fn
+shmobile_smp_fn:
+2:	.space	CONFIG_NR_CPUS * 4
+	.globl	shmobile_smp_arg
+shmobile_smp_arg:
+3:	.space	CONFIG_NR_CPUS * 4
diff --git a/arch/arm/mach-shmobile/include/mach/common.h b/arch/arm/mach-shmobile/include/mach/common.h
index e818f029d8e3..7b938681e756 100644
--- a/arch/arm/mach-shmobile/include/mach/common.h
+++ b/arch/arm/mach-shmobile/include/mach/common.h
@@ -2,7 +2,6 @@
 #define __ARCH_MACH_COMMON_H
 
 extern void shmobile_earlytimer_init(void);
-extern void shmobile_timer_init(void);
 extern void shmobile_setup_delay(unsigned int max_cpu_core_mhz,
 			 unsigned int mult, unsigned int div);
 struct twd_local_timer;
@@ -10,7 +9,16 @@ extern void shmobile_setup_console(void);
 extern void shmobile_boot_vector(void);
 extern unsigned long shmobile_boot_fn;
 extern unsigned long shmobile_boot_arg;
+extern void shmobile_smp_boot(void);
+extern void shmobile_smp_sleep(void);
+extern void shmobile_smp_hook(unsigned int cpu, unsigned long fn,
+			      unsigned long arg);
 extern void shmobile_boot_scu(void);
+extern void shmobile_smp_scu_prepare_cpus(unsigned int max_cpus);
+extern int shmobile_smp_scu_boot_secondary(unsigned int cpu,
+					   struct task_struct *idle);
+extern void shmobile_smp_scu_cpu_die(unsigned int cpu);
+extern int shmobile_smp_scu_cpu_kill(unsigned int cpu);
 struct clk;
 extern int shmobile_clk_init(void);
 extern void shmobile_handle_irq_intc(struct pt_regs *);
diff --git a/arch/arm/mach-shmobile/include/mach/dma.h b/arch/arm/mach-shmobile/include/mach/dma.h
deleted file mode 100644
index 40a8c178f10d..000000000000
--- a/arch/arm/mach-shmobile/include/mach/dma.h
+++ /dev/null
@@ -1 +0,0 @@
-/* empty */
diff --git a/arch/arm/mach-shmobile/include/mach/emev2.h b/arch/arm/mach-shmobile/include/mach/emev2.h
index ac3751705cab..c2eb7568d9be 100644
--- a/arch/arm/mach-shmobile/include/mach/emev2.h
+++ b/arch/arm/mach-shmobile/include/mach/emev2.h
@@ -2,11 +2,9 @@
 #define __ASM_EMEV2_H__
 
 extern void emev2_map_io(void);
-extern void emev2_init_irq(void);
-extern void emev2_add_early_devices(void);
+extern void emev2_init_delay(void);
 extern void emev2_add_standard_devices(void);
 extern void emev2_clock_init(void);
-extern void emev2_set_boot_vector(unsigned long value);
 
 #define EMEV2_GPIO_BASE 200
 #define EMEV2_GPIO_IRQ(n) (EMEV2_GPIO_BASE + (n))
diff --git a/arch/arm/mach-shmobile/include/mach/hardware.h b/arch/arm/mach-shmobile/include/mach/hardware.h
deleted file mode 100644
index 99264a5ce5e4..000000000000
--- a/arch/arm/mach-shmobile/include/mach/hardware.h
+++ /dev/null
@@ -1,4 +0,0 @@
-#ifndef __ASM_MACH_HARDWARE_H
-#define __ASM_MACH_HARDWARE_H
-
-#endif /* __ASM_MACH_HARDWARE_H */
diff --git a/arch/arm/mach-shmobile/include/mach/r8a73a4.h b/arch/arm/mach-shmobile/include/mach/r8a73a4.h
index f043103e32c9..f3a9b702da56 100644
--- a/arch/arm/mach-shmobile/include/mach/r8a73a4.h
+++ b/arch/arm/mach-shmobile/include/mach/r8a73a4.h
@@ -2,7 +2,9 @@
 #define __ASM_R8A73A4_H__
 
 void r8a73a4_add_standard_devices(void);
+void r8a73a4_add_dt_devices(void);
 void r8a73a4_clock_init(void);
 void r8a73a4_pinmux_init(void);
+void r8a73a4_init_delay(void);
 
 #endif /* __ASM_R8A73A4_H__ */
diff --git a/arch/arm/mach-shmobile/include/mach/r8a7740.h b/arch/arm/mach-shmobile/include/mach/r8a7740.h
index b34d19b5ca5c..d07932f872b6 100644
--- a/arch/arm/mach-shmobile/include/mach/r8a7740.h
+++ b/arch/arm/mach-shmobile/include/mach/r8a7740.h
@@ -42,11 +42,12 @@ enum {
 	SHDMA_SLAVE_FSIB_TX,
 	SHDMA_SLAVE_USBHS_TX,
 	SHDMA_SLAVE_USBHS_RX,
+	SHDMA_SLAVE_MMCIF_TX,
+	SHDMA_SLAVE_MMCIF_RX,
 };
 
 extern void r8a7740_meram_workaround(void);
 extern void r8a7740_init_delay(void);
-extern void r8a7740_init_irq(void);
 extern void r8a7740_init_irq_of(void);
 extern void r8a7740_map_io(void);
 extern void r8a7740_add_early_devices(void);
diff --git a/arch/arm/mach-shmobile/include/mach/r8a7778.h b/arch/arm/mach-shmobile/include/mach/r8a7778.h
index 851d027a2f06..adfcf51b163d 100644
--- a/arch/arm/mach-shmobile/include/mach/r8a7778.h
+++ b/arch/arm/mach-shmobile/include/mach/r8a7778.h
@@ -18,26 +18,21 @@
 #ifndef __ASM_R8A7778_H__
 #define __ASM_R8A7778_H__
 
-#include <linux/mmc/sh_mmcif.h>
-#include <linux/mmc/sh_mobile_sdhi.h>
 #include <linux/sh_eth.h>
-#include <linux/platform_data/usb-rcar-phy.h>
+#include <linux/platform_data/camera-rcar.h>
 
 extern void r8a7778_add_standard_devices(void);
 extern void r8a7778_add_standard_devices_dt(void);
 extern void r8a7778_add_ether_device(struct sh_eth_plat_data *pdata);
-extern void r8a7778_add_usb_phy_device(struct rcar_phy_platform_data *pdata);
-extern void r8a7778_add_i2c_device(int id);
-extern void r8a7778_add_hspi_device(int id);
-extern void r8a7778_add_mmc_device(struct sh_mmcif_plat_data *info);
+extern void r8a7778_add_vin_device(int id,
+				   struct rcar_vin_platform_data *pdata);
+extern void r8a7778_add_dt_devices(void);
 
 extern void r8a7778_init_late(void);
 extern void r8a7778_init_delay(void);
-extern void r8a7778_init_irq(void);
 extern void r8a7778_init_irq_dt(void);
 extern void r8a7778_clock_init(void);
 extern void r8a7778_init_irq_extpin(int irlm);
 extern void r8a7778_pinmux_init(void);
-extern void r8a7778_sdhi_init(int id, struct sh_mobile_sdhi_info *info);
 
 #endif /* __ASM_R8A7778_H__ */
diff --git a/arch/arm/mach-shmobile/include/mach/r8a7779.h b/arch/arm/mach-shmobile/include/mach/r8a7779.h
index fc47073c7ba9..11c740047e14 100644
--- a/arch/arm/mach-shmobile/include/mach/r8a7779.h
+++ b/arch/arm/mach-shmobile/include/mach/r8a7779.h
@@ -4,7 +4,7 @@
 #include <linux/sh_clk.h>
 #include <linux/pm_domain.h>
 #include <linux/sh_eth.h>
-#include <linux/platform_data/usb-rcar-phy.h>
+#include <linux/platform_data/camera-rcar.h>
 
 struct platform_device;
 
@@ -25,7 +25,6 @@ static inline struct r8a7779_pm_ch *to_r8a7779_ch(struct generic_pm_domain *d)
 }
 
 extern void r8a7779_init_delay(void);
-extern void r8a7779_init_irq(void);
 extern void r8a7779_init_irq_extpin(int irlm);
 extern void r8a7779_init_irq_dt(void);
 extern void r8a7779_map_io(void);
@@ -34,7 +33,8 @@ extern void r8a7779_add_early_devices(void);
 extern void r8a7779_add_standard_devices(void);
 extern void r8a7779_add_standard_devices_dt(void);
 extern void r8a7779_add_ether_device(struct sh_eth_plat_data *pdata);
-extern void r8a7779_add_usb_phy_device(struct rcar_phy_platform_data *pdata);
+extern void r8a7779_add_vin_device(int idx,
+				   struct rcar_vin_platform_data *pdata);
 extern void r8a7779_init_late(void);
 extern void r8a7779_clock_init(void);
 extern void r8a7779_pinmux_init(void);
diff --git a/arch/arm/mach-shmobile/include/mach/r8a7790.h b/arch/arm/mach-shmobile/include/mach/r8a7790.h
index 2e919e61fa0d..788d55952091 100644
--- a/arch/arm/mach-shmobile/include/mach/r8a7790.h
+++ b/arch/arm/mach-shmobile/include/mach/r8a7790.h
@@ -2,8 +2,13 @@
 #define __ASM_R8A7790_H__
 
 void r8a7790_add_standard_devices(void);
+void r8a7790_add_dt_devices(void);
 void r8a7790_clock_init(void);
 void r8a7790_pinmux_init(void);
+void r8a7790_init_delay(void);
 void r8a7790_timer_init(void);
 
+#define MD(nr) BIT(nr)
+u32 r8a7790_read_mode_pins(void);
+
 #endif /* __ASM_R8A7790_H__ */
diff --git a/arch/arm/mach-shmobile/include/mach/sh73a0.h b/arch/arm/mach-shmobile/include/mach/sh73a0.h
index eb7a4320d487..359b582dc270 100644
--- a/arch/arm/mach-shmobile/include/mach/sh73a0.h
+++ b/arch/arm/mach-shmobile/include/mach/sh73a0.h
@@ -1,379 +1,6 @@
 #ifndef __ASM_SH73A0_H__
 #define __ASM_SH73A0_H__
 
-/* Pin Function Controller:
- * GPIO_FN_xx - GPIO used to select pin function and MSEL switch
- * GPIO_PORTxx - GPIO mapped to real I/O pin on CPU
- */
-enum {
-	/* Hardware manual Table 25-1 (GPIO) */
-	GPIO_PORT0, GPIO_PORT1, GPIO_PORT2, GPIO_PORT3, GPIO_PORT4,
-	GPIO_PORT5, GPIO_PORT6, GPIO_PORT7, GPIO_PORT8, GPIO_PORT9,
-
-	GPIO_PORT10, GPIO_PORT11, GPIO_PORT12, GPIO_PORT13, GPIO_PORT14,
-	GPIO_PORT15, GPIO_PORT16, GPIO_PORT17, GPIO_PORT18, GPIO_PORT19,
-
-	GPIO_PORT20, GPIO_PORT21, GPIO_PORT22, GPIO_PORT23, GPIO_PORT24,
-	GPIO_PORT25, GPIO_PORT26, GPIO_PORT27, GPIO_PORT28, GPIO_PORT29,
-
-	GPIO_PORT30, GPIO_PORT31, GPIO_PORT32, GPIO_PORT33, GPIO_PORT34,
-	GPIO_PORT35, GPIO_PORT36, GPIO_PORT37, GPIO_PORT38, GPIO_PORT39,
-
-	GPIO_PORT40, GPIO_PORT41, GPIO_PORT42, GPIO_PORT43, GPIO_PORT44,
-	GPIO_PORT45, GPIO_PORT46, GPIO_PORT47, GPIO_PORT48, GPIO_PORT49,
-
-	GPIO_PORT50, GPIO_PORT51, GPIO_PORT52, GPIO_PORT53, GPIO_PORT54,
-	GPIO_PORT55, GPIO_PORT56, GPIO_PORT57, GPIO_PORT58, GPIO_PORT59,
-
-	GPIO_PORT60, GPIO_PORT61, GPIO_PORT62, GPIO_PORT63, GPIO_PORT64,
-	GPIO_PORT65, GPIO_PORT66, GPIO_PORT67, GPIO_PORT68, GPIO_PORT69,
-
-	GPIO_PORT70, GPIO_PORT71, GPIO_PORT72, GPIO_PORT73, GPIO_PORT74,
-	GPIO_PORT75, GPIO_PORT76, GPIO_PORT77, GPIO_PORT78, GPIO_PORT79,
-
-	GPIO_PORT80, GPIO_PORT81, GPIO_PORT82, GPIO_PORT83, GPIO_PORT84,
-	GPIO_PORT85, GPIO_PORT86, GPIO_PORT87, GPIO_PORT88, GPIO_PORT89,
-
-	GPIO_PORT90, GPIO_PORT91, GPIO_PORT92, GPIO_PORT93, GPIO_PORT94,
-	GPIO_PORT95, GPIO_PORT96, GPIO_PORT97, GPIO_PORT98, GPIO_PORT99,
-
-	GPIO_PORT100, GPIO_PORT101, GPIO_PORT102, GPIO_PORT103, GPIO_PORT104,
-	GPIO_PORT105, GPIO_PORT106, GPIO_PORT107, GPIO_PORT108, GPIO_PORT109,
-
-	GPIO_PORT110, GPIO_PORT111, GPIO_PORT112, GPIO_PORT113, GPIO_PORT114,
-	GPIO_PORT115, GPIO_PORT116, GPIO_PORT117, GPIO_PORT118,
-
-	GPIO_PORT128, GPIO_PORT129,
-
-	GPIO_PORT130, GPIO_PORT131, GPIO_PORT132, GPIO_PORT133, GPIO_PORT134,
-	GPIO_PORT135, GPIO_PORT136, GPIO_PORT137, GPIO_PORT138, GPIO_PORT139,
-
-	GPIO_PORT140, GPIO_PORT141, GPIO_PORT142, GPIO_PORT143, GPIO_PORT144,
-	GPIO_PORT145, GPIO_PORT146, GPIO_PORT147, GPIO_PORT148, GPIO_PORT149,
-
-	GPIO_PORT150, GPIO_PORT151, GPIO_PORT152, GPIO_PORT153, GPIO_PORT154,
-	GPIO_PORT155, GPIO_PORT156, GPIO_PORT157, GPIO_PORT158, GPIO_PORT159,
-
-	GPIO_PORT160, GPIO_PORT161, GPIO_PORT162, GPIO_PORT163, GPIO_PORT164,
-
-	GPIO_PORT192, GPIO_PORT193, GPIO_PORT194,
-	GPIO_PORT195, GPIO_PORT196, GPIO_PORT197, GPIO_PORT198, GPIO_PORT199,
-
-	GPIO_PORT200, GPIO_PORT201, GPIO_PORT202, GPIO_PORT203, GPIO_PORT204,
-	GPIO_PORT205, GPIO_PORT206, GPIO_PORT207, GPIO_PORT208, GPIO_PORT209,
-
-	GPIO_PORT210, GPIO_PORT211, GPIO_PORT212, GPIO_PORT213, GPIO_PORT214,
-	GPIO_PORT215, GPIO_PORT216, GPIO_PORT217, GPIO_PORT218, GPIO_PORT219,
-
-	GPIO_PORT220, GPIO_PORT221, GPIO_PORT222, GPIO_PORT223, GPIO_PORT224,
-	GPIO_PORT225, GPIO_PORT226, GPIO_PORT227, GPIO_PORT228, GPIO_PORT229,
-
-	GPIO_PORT230, GPIO_PORT231, GPIO_PORT232, GPIO_PORT233, GPIO_PORT234,
-	GPIO_PORT235, GPIO_PORT236, GPIO_PORT237, GPIO_PORT238, GPIO_PORT239,
-
-	GPIO_PORT240, GPIO_PORT241, GPIO_PORT242, GPIO_PORT243, GPIO_PORT244,
-	GPIO_PORT245, GPIO_PORT246, GPIO_PORT247, GPIO_PORT248, GPIO_PORT249,
-
-	GPIO_PORT250, GPIO_PORT251, GPIO_PORT252, GPIO_PORT253, GPIO_PORT254,
-	GPIO_PORT255, GPIO_PORT256, GPIO_PORT257, GPIO_PORT258, GPIO_PORT259,
-
-	GPIO_PORT260, GPIO_PORT261, GPIO_PORT262, GPIO_PORT263, GPIO_PORT264,
-	GPIO_PORT265, GPIO_PORT266, GPIO_PORT267, GPIO_PORT268, GPIO_PORT269,
-
-	GPIO_PORT270, GPIO_PORT271, GPIO_PORT272, GPIO_PORT273, GPIO_PORT274,
-	GPIO_PORT275, GPIO_PORT276, GPIO_PORT277, GPIO_PORT278, GPIO_PORT279,
-
-	GPIO_PORT280, GPIO_PORT281, GPIO_PORT282,
-
-	GPIO_PORT288, GPIO_PORT289,
-
-	GPIO_PORT290, GPIO_PORT291, GPIO_PORT292, GPIO_PORT293, GPIO_PORT294,
-	GPIO_PORT295, GPIO_PORT296, GPIO_PORT297, GPIO_PORT298, GPIO_PORT299,
-
-	GPIO_PORT300, GPIO_PORT301, GPIO_PORT302, GPIO_PORT303, GPIO_PORT304,
-	GPIO_PORT305, GPIO_PORT306, GPIO_PORT307, GPIO_PORT308, GPIO_PORT309,
-
-	/* Table 25-1 (Function 0-7) */
-	GPIO_FN_GPI0 = 310,
-	GPIO_FN_GPI1,
-	GPIO_FN_GPI2,
-	GPIO_FN_GPI3,
-	GPIO_FN_GPI4,
-	GPIO_FN_GPI5,
-	GPIO_FN_GPI6,
-	GPIO_FN_GPI7,
-	GPIO_FN_GPO7, GPIO_FN_MFG0_OUT2,
-	GPIO_FN_GPO6, GPIO_FN_MFG1_OUT2,
-	GPIO_FN_GPO5,
-	GPIO_FN_PORT16_VIO_CKOR,
-	GPIO_FN_PORT19_VIO_CKO2,
-	GPIO_FN_GPO0,
-	GPIO_FN_GPO1,
-	GPIO_FN_GPO2, GPIO_FN_STATUS0,
-	GPIO_FN_GPO3, GPIO_FN_STATUS1,
-	GPIO_FN_GPO4, GPIO_FN_STATUS2,
-	GPIO_FN_VINT,
-	GPIO_FN_TCKON,
-	GPIO_FN_XDVFS1,
-	GPIO_FN_MFG0_OUT1, GPIO_FN_PORT27_IROUT,
-	GPIO_FN_XDVFS2,
-	GPIO_FN_PORT28_TPU1TO1,
-	GPIO_FN_SIM_RST, GPIO_FN_PORT29_TPU1TO1,
-	GPIO_FN_SIM_CLK, GPIO_FN_PORT30_VIO_CKOR,
-	GPIO_FN_SIM_D, GPIO_FN_PORT31_IROUT,
-	GPIO_FN_XWUP,
-	GPIO_FN_VACK,
-	GPIO_FN_XTAL1L,
-	GPIO_FN_PORT49_IROUT,
-	GPIO_FN_BBIF2_TSYNC2, GPIO_FN_TPU2TO2,
-
-	GPIO_FN_BBIF2_TSCK2, GPIO_FN_TPU2TO3,
-	GPIO_FN_BBIF2_TXD2,
-	GPIO_FN_TPU3TO3,
-	GPIO_FN_TPU3TO2,
-	GPIO_FN_TPU0TO0,
-	GPIO_FN_A0, GPIO_FN_BS_,
-	GPIO_FN_A12, GPIO_FN_TPU4TO2,
-	GPIO_FN_A13, GPIO_FN_TPU0TO1,
-	GPIO_FN_A14,
-	GPIO_FN_A15,
-	GPIO_FN_A16, GPIO_FN_MSIOF0_SS1,
-	GPIO_FN_A17, GPIO_FN_MSIOF0_TSYNC,
-	GPIO_FN_A18, GPIO_FN_MSIOF0_TSCK,
-	GPIO_FN_A19, GPIO_FN_MSIOF0_TXD,
-	GPIO_FN_A20, GPIO_FN_MSIOF0_RSCK,
-	GPIO_FN_A21, GPIO_FN_MSIOF0_RSYNC,
-	GPIO_FN_A22, GPIO_FN_MSIOF0_MCK0,
-	GPIO_FN_A23, GPIO_FN_MSIOF0_MCK1,
-	GPIO_FN_A24, GPIO_FN_MSIOF0_RXD,
-	GPIO_FN_A25, GPIO_FN_MSIOF0_SS2,
-	GPIO_FN_A26,
-	GPIO_FN_FCE1_,
-	GPIO_FN_DACK0,
-	GPIO_FN_FCE0_,
-	GPIO_FN_WAIT_, GPIO_FN_DREQ0,
-	GPIO_FN_FRB,
-	GPIO_FN_CKO,
-	GPIO_FN_NBRSTOUT_,
-	GPIO_FN_NBRST_,
-	GPIO_FN_BBIF2_TXD,
-	GPIO_FN_BBIF2_RXD,
-	GPIO_FN_BBIF2_SYNC,
-	GPIO_FN_BBIF2_SCK,
-	GPIO_FN_MFG3_IN2,
-	GPIO_FN_MFG3_IN1,
-	GPIO_FN_BBIF1_SS2, GPIO_FN_MFG3_OUT1,
-	GPIO_FN_HSI_RX_DATA, GPIO_FN_BBIF1_RXD,
-	GPIO_FN_HSI_TX_WAKE, GPIO_FN_BBIF1_TSCK,
-	GPIO_FN_HSI_TX_DATA, GPIO_FN_BBIF1_TSYNC,
-	GPIO_FN_HSI_TX_READY, GPIO_FN_BBIF1_TXD,
-	GPIO_FN_HSI_RX_READY, GPIO_FN_BBIF1_RSCK,
-	GPIO_FN_HSI_RX_WAKE, GPIO_FN_BBIF1_RSYNC,
-	GPIO_FN_HSI_RX_FLAG, GPIO_FN_BBIF1_SS1, GPIO_FN_BBIF1_FLOW,
-	GPIO_FN_HSI_TX_FLAG,
-	GPIO_FN_VIO_VD, GPIO_FN_VIO2_VD,
-
-	GPIO_FN_VIO_HD,
-	GPIO_FN_VIO2_HD,
-	GPIO_FN_VIO_D0, GPIO_FN_PORT130_MSIOF2_RXD,
-	GPIO_FN_VIO_D1, GPIO_FN_PORT131_MSIOF2_SS1,
-	GPIO_FN_VIO_D2, GPIO_FN_PORT132_MSIOF2_SS2,
-	GPIO_FN_VIO_D3, GPIO_FN_MSIOF2_TSYNC,
-	GPIO_FN_VIO_D4, GPIO_FN_MSIOF2_TXD,
-	GPIO_FN_VIO_D5, GPIO_FN_MSIOF2_TSCK,
-	GPIO_FN_VIO_D6,
-	GPIO_FN_VIO_D7,
-	GPIO_FN_VIO_D8, GPIO_FN_VIO2_D0,
-	GPIO_FN_VIO_D9, GPIO_FN_VIO2_D1,
-	GPIO_FN_VIO_D10, GPIO_FN_TPU0TO2, GPIO_FN_VIO2_D2,
-	GPIO_FN_VIO_D11, GPIO_FN_TPU0TO3, GPIO_FN_VIO2_D3,
-	GPIO_FN_VIO_D12, GPIO_FN_VIO2_D4,
-	GPIO_FN_VIO_D13,
-	GPIO_FN_VIO2_D5,
-	GPIO_FN_VIO_D14, GPIO_FN_VIO2_D6,
-	GPIO_FN_VIO_D15, GPIO_FN_TPU1TO3,
-	GPIO_FN_VIO2_D7,
-	GPIO_FN_VIO_CLK,
-	GPIO_FN_VIO2_CLK,
-	GPIO_FN_VIO_FIELD, GPIO_FN_VIO2_FIELD,
-	GPIO_FN_VIO_CKO,
-	GPIO_FN_A27, GPIO_FN_MFG0_IN1,
-	GPIO_FN_MFG0_IN2,
-	GPIO_FN_TS_SPSYNC3, GPIO_FN_MSIOF2_RSCK,
-	GPIO_FN_TS_SDAT3, GPIO_FN_MSIOF2_RSYNC,
-	GPIO_FN_TPU1TO2, GPIO_FN_TS_SDEN3, GPIO_FN_PORT153_MSIOF2_SS1,
-	GPIO_FN_MSIOF2_MCK0,
-	GPIO_FN_MSIOF2_MCK1,
-	GPIO_FN_PORT156_MSIOF2_SS2,
-	GPIO_FN_PORT157_MSIOF2_RXD,
-	GPIO_FN_DINT_, GPIO_FN_TS_SCK3,
-	GPIO_FN_NMI,
-	GPIO_FN_TPU3TO0,
-	GPIO_FN_BBIF2_TSYNC1,
-	GPIO_FN_BBIF2_TSCK1,
-	GPIO_FN_BBIF2_TXD1,
-	GPIO_FN_MFG2_OUT2,
-	GPIO_FN_TPU2TO1,
-	GPIO_FN_TPU4TO1, GPIO_FN_MFG4_OUT2,
-	GPIO_FN_D16,
-	GPIO_FN_D17,
-	GPIO_FN_D18,
-	GPIO_FN_D19,
-	GPIO_FN_D20,
-	GPIO_FN_D21,
-	GPIO_FN_D22,
-	GPIO_FN_PORT207_MSIOF0L_SS1, GPIO_FN_D23,
-	GPIO_FN_PORT208_MSIOF0L_SS2, GPIO_FN_D24,
-	GPIO_FN_D25,
-	GPIO_FN_DREQ2, GPIO_FN_PORT210_MSIOF0L_SS1, GPIO_FN_D26,
-	GPIO_FN_PORT211_MSIOF0L_SS2, GPIO_FN_D27,
-	GPIO_FN_TS_SPSYNC1, GPIO_FN_MSIOF0L_MCK0, GPIO_FN_D28,
-	GPIO_FN_TS_SDAT1, GPIO_FN_MSIOF0L_MCK1, GPIO_FN_D29,
-	GPIO_FN_TS_SDEN1, GPIO_FN_MSIOF0L_RSCK, GPIO_FN_D30,
-	GPIO_FN_TS_SCK1, GPIO_FN_MSIOF0L_RSYNC, GPIO_FN_D31,
-	GPIO_FN_DACK2,
-	GPIO_FN_MSIOF0L_TSYNC, GPIO_FN_VIO2_FIELD3,
-	GPIO_FN_DACK3,
-	GPIO_FN_PORT218_VIO_CKOR,
-	GPIO_FN_DREQ3, GPIO_FN_MSIOF0L_TSCK, GPIO_FN_VIO2_CLK3, \
-	GPIO_FN_DREQ1,
-	GPIO_FN_PWEN, GPIO_FN_MSIOF0L_RXD, GPIO_FN_VIO2_HD3, \
-	GPIO_FN_DACK1, GPIO_FN_OVCN,
-	GPIO_FN_MSIOF0L_TXD, GPIO_FN_VIO2_VD3,
-
-	GPIO_FN_OVCN2,
-	GPIO_FN_EXTLP, GPIO_FN_PORT226_VIO_CKO2,
-	GPIO_FN_IDIN,
-	GPIO_FN_MFG1_IN1,
-	GPIO_FN_MSIOF1_TXD,
-	GPIO_FN_MSIOF1_TSYNC,
-	GPIO_FN_MSIOF1_TSCK,
-	GPIO_FN_MSIOF1_RXD,
-	GPIO_FN_MSIOF1_RSCK, GPIO_FN_VIO2_CLK2,
-	GPIO_FN_MSIOF1_RSYNC, GPIO_FN_MFG1_IN2, GPIO_FN_VIO2_VD2, \
-	GPIO_FN_MSIOF1_MCK0,
-	GPIO_FN_MSIOF1_MCK1,
-	GPIO_FN_MSIOF1_SS1, GPIO_FN_VIO2_FIELD2,
-	GPIO_FN_MSIOF1_SS2, GPIO_FN_VIO2_HD2,
-	GPIO_FN_PORT241_IROUT, GPIO_FN_MFG4_OUT1, \
-	GPIO_FN_TPU4TO0,
-	GPIO_FN_MFG4_IN2,
-	GPIO_FN_PORT243_VIO_CKO2,
-	GPIO_FN_MFG2_IN1,
-	GPIO_FN_MSIOF2R_RXD,
-	GPIO_FN_MFG2_IN2,
-	GPIO_FN_MSIOF2R_TXD,
-	GPIO_FN_MFG1_OUT1,
-	GPIO_FN_TPU1TO0,
-	GPIO_FN_MFG3_OUT2,
-	GPIO_FN_TPU3TO1,
-	GPIO_FN_MFG2_OUT1,
-	GPIO_FN_TPU2TO0,
-	GPIO_FN_MSIOF2R_TSCK,
-	GPIO_FN_PORT249_IROUT, GPIO_FN_MFG4_IN1, \
-	GPIO_FN_MSIOF2R_TSYNC,
-	GPIO_FN_SDHICLK0,
-	GPIO_FN_SDHICD0,
-	GPIO_FN_SDHID0_0,
-	GPIO_FN_SDHID0_1,
-	GPIO_FN_SDHID0_2,
-	GPIO_FN_SDHID0_3,
-	GPIO_FN_SDHICMD0,
-	GPIO_FN_SDHIWP0,
-	GPIO_FN_SDHICLK1,
-	GPIO_FN_SDHID1_0, GPIO_FN_TS_SPSYNC2,
-	GPIO_FN_SDHID1_1, GPIO_FN_TS_SDAT2,
-	GPIO_FN_SDHID1_2, GPIO_FN_TS_SDEN2,
-	GPIO_FN_SDHID1_3, GPIO_FN_TS_SCK2,
-	GPIO_FN_SDHICMD1,
-	GPIO_FN_SDHICLK2,
-	GPIO_FN_SDHID2_0, GPIO_FN_TS_SPSYNC4,
-	GPIO_FN_SDHID2_1, GPIO_FN_TS_SDAT4,
-	GPIO_FN_SDHID2_2, GPIO_FN_TS_SDEN4,
-	GPIO_FN_SDHID2_3, GPIO_FN_TS_SCK4,
-	GPIO_FN_SDHICMD2,
-	GPIO_FN_MMCCLK0,
-	GPIO_FN_MMCD0_0,
-	GPIO_FN_MMCD0_1,
-	GPIO_FN_MMCD0_2,
-	GPIO_FN_MMCD0_3,
-	GPIO_FN_MMCD0_4, GPIO_FN_TS_SPSYNC5,
-	GPIO_FN_MMCD0_5, GPIO_FN_TS_SDAT5,
-	GPIO_FN_MMCD0_6, GPIO_FN_TS_SDEN5,
-	GPIO_FN_MMCD0_7, GPIO_FN_TS_SCK5,
-	GPIO_FN_MMCCMD0,
-	GPIO_FN_RESETOUTS_, GPIO_FN_EXTAL2OUT,
-	GPIO_FN_MCP_WAIT__MCP_FRB,
-	GPIO_FN_MCP_CKO, GPIO_FN_MMCCLK1,
-	GPIO_FN_MCP_D15_MCP_NAF15,
-	GPIO_FN_MCP_D14_MCP_NAF14,
-	GPIO_FN_MCP_D13_MCP_NAF13,
-	GPIO_FN_MCP_D12_MCP_NAF12,
-	GPIO_FN_MCP_D11_MCP_NAF11,
-	GPIO_FN_MCP_D10_MCP_NAF10,
-	GPIO_FN_MCP_D9_MCP_NAF9,
-	GPIO_FN_MCP_D8_MCP_NAF8, GPIO_FN_MMCCMD1,
-	GPIO_FN_MCP_D7_MCP_NAF7, GPIO_FN_MMCD1_7,
-
-	GPIO_FN_MCP_D6_MCP_NAF6, GPIO_FN_MMCD1_6,
-	GPIO_FN_MCP_D5_MCP_NAF5, GPIO_FN_MMCD1_5,
-	GPIO_FN_MCP_D4_MCP_NAF4, GPIO_FN_MMCD1_4,
-	GPIO_FN_MCP_D3_MCP_NAF3, GPIO_FN_MMCD1_3,
-	GPIO_FN_MCP_D2_MCP_NAF2, GPIO_FN_MMCD1_2,
-	GPIO_FN_MCP_D1_MCP_NAF1, GPIO_FN_MMCD1_1,
-	GPIO_FN_MCP_D0_MCP_NAF0, GPIO_FN_MMCD1_0,
-	GPIO_FN_MCP_NBRSTOUT_,
-	GPIO_FN_MCP_WE0__MCP_FWE, GPIO_FN_MCP_RDWR_MCP_FWE,
-
-	/* MSEL2 special case */
-	GPIO_FN_TSIF2_TS_XX1,
-	GPIO_FN_TSIF2_TS_XX2,
-	GPIO_FN_TSIF2_TS_XX3,
-	GPIO_FN_TSIF2_TS_XX4,
-	GPIO_FN_TSIF2_TS_XX5,
-	GPIO_FN_TSIF1_TS_XX1,
-	GPIO_FN_TSIF1_TS_XX2,
-	GPIO_FN_TSIF1_TS_XX3,
-	GPIO_FN_TSIF1_TS_XX4,
-	GPIO_FN_TSIF1_TS_XX5,
-	GPIO_FN_TSIF0_TS_XX1,
-	GPIO_FN_TSIF0_TS_XX2,
-	GPIO_FN_TSIF0_TS_XX3,
-	GPIO_FN_TSIF0_TS_XX4,
-	GPIO_FN_TSIF0_TS_XX5,
-	GPIO_FN_MST1_TS_XX1,
-	GPIO_FN_MST1_TS_XX2,
-	GPIO_FN_MST1_TS_XX3,
-	GPIO_FN_MST1_TS_XX4,
-	GPIO_FN_MST1_TS_XX5,
-	GPIO_FN_MST0_TS_XX1,
-	GPIO_FN_MST0_TS_XX2,
-	GPIO_FN_MST0_TS_XX3,
-	GPIO_FN_MST0_TS_XX4,
-	GPIO_FN_MST0_TS_XX5,
-
-	/* MSEL3 special cases */
-	GPIO_FN_SDHI0_VCCQ_MC0_ON,
-	GPIO_FN_SDHI0_VCCQ_MC0_OFF,
-	GPIO_FN_DEBUG_MON_VIO,
-	GPIO_FN_DEBUG_MON_LCDD,
-	GPIO_FN_LCDC_LCDC0,
-	GPIO_FN_LCDC_LCDC1,
-
-	/* MSEL4 special cases */
-	GPIO_FN_IRQ9_MEM_INT,
-	GPIO_FN_IRQ9_MCP_INT,
-	GPIO_FN_A11,
-	GPIO_FN_TPU4TO3,
-	GPIO_FN_RESETA_N_PU_ON,
-	GPIO_FN_RESETA_N_PU_OFF,
-	GPIO_FN_EDBGREQ_PD,
-	GPIO_FN_EDBGREQ_PU,
-
-	/* end of GPIO */
-	GPIO_NR,
-};
-
 /* DMA slave IDs */
 enum {
 	SHDMA_SLAVE_INVALID,
diff --git a/arch/arm/mach-shmobile/include/mach/zboot.h b/arch/arm/mach-shmobile/include/mach/zboot.h
index f2d8744c1f14..c3c4669a2d72 100644
--- a/arch/arm/mach-shmobile/include/mach/zboot.h
+++ b/arch/arm/mach-shmobile/include/mach/zboot.h
@@ -1,7 +1,6 @@
 #ifndef ZBOOT_H
 #define ZBOOT_H
 
-#include <asm/mach-types.h>
 #include <mach/zboot_macros.h>
 
 /**************************************************
@@ -11,7 +10,6 @@
  **************************************************/
 
 #ifdef CONFIG_MACH_MACKEREL
-#define MACH_TYPE	MACH_TYPE_MACKEREL
 #define MEMORY_START	0x40000000
 #include "mach/head-mackerel.txt"
 #else
diff --git a/arch/arm/mach-shmobile/intc-r8a7740.c b/arch/arm/mach-shmobile/intc-r8a7740.c
deleted file mode 100644
index 8871f7717dc8..000000000000
--- a/arch/arm/mach-shmobile/intc-r8a7740.c
+++ /dev/null
@@ -1,68 +0,0 @@
-/*
- * R8A7740 processor support
- *
- * Copyright (C) 2011  Renesas Solutions Corp.
- * Copyright (C) 2011  Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; version 2 of the License.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
- */
-
-#include <linux/init.h>
-#include <linux/io.h>
-#include <linux/irqchip.h>
-#include <linux/irqchip/arm-gic.h>
-
-static void __init r8a7740_init_irq_common(void)
-{
-	void __iomem *intc_prio_base = ioremap_nocache(0xe6900010, 0x10);
-	void __iomem *intc_msk_base = ioremap_nocache(0xe6900040, 0x10);
-	void __iomem *pfc_inta_ctrl = ioremap_nocache(0xe605807c, 0x4);
-
-	/* route signals to GIC */
-	iowrite32(0x0, pfc_inta_ctrl);
-
-	/*
-	 * To mask the shared interrupt to SPI 149 we must ensure to set
-	 * PRIO *and* MASK. Else we run into IRQ floods when registering
-	 * the intc_irqpin devices
-	 */
-	iowrite32(0x0, intc_prio_base + 0x0);
-	iowrite32(0x0, intc_prio_base + 0x4);
-	iowrite32(0x0, intc_prio_base + 0x8);
-	iowrite32(0x0, intc_prio_base + 0xc);
-	iowrite8(0xff, intc_msk_base + 0x0);
-	iowrite8(0xff, intc_msk_base + 0x4);
-	iowrite8(0xff, intc_msk_base + 0x8);
-	iowrite8(0xff, intc_msk_base + 0xc);
-
-	iounmap(intc_prio_base);
-	iounmap(intc_msk_base);
-	iounmap(pfc_inta_ctrl);
-}
-
-void __init r8a7740_init_irq_of(void)
-{
-	irqchip_init();
-	r8a7740_init_irq_common();
-}
-
-void __init r8a7740_init_irq(void)
-{
-	void __iomem *gic_dist_base = ioremap_nocache(0xc2800000, 0x1000);
-	void __iomem *gic_cpu_base = ioremap_nocache(0xc2000000, 0x1000);
-
-	/* initialize the Generic Interrupt Controller PL390 r0p0 */
-	gic_init(0, 29, gic_dist_base, gic_cpu_base);
-	r8a7740_init_irq_common();
-}
diff --git a/arch/arm/mach-shmobile/intc-r8a7779.c b/arch/arm/mach-shmobile/intc-r8a7779.c
deleted file mode 100644
index b86dc8908724..000000000000
--- a/arch/arm/mach-shmobile/intc-r8a7779.c
+++ /dev/null
@@ -1,131 +0,0 @@
-/*
- * r8a7779 processor support - INTC hardware block
- *
- * Copyright (C) 2011  Renesas Solutions Corp.
- * Copyright (C) 2011  Magnus Damm
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; version 2 of the License.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
- */
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/platform_device.h>
-#include <linux/interrupt.h>
-#include <linux/irq.h>
-#include <linux/io.h>
-#include <linux/irqchip/arm-gic.h>
-#include <linux/platform_data/irq-renesas-intc-irqpin.h>
-#include <linux/irqchip.h>
-#include <mach/common.h>
-#include <mach/intc.h>
-#include <mach/irqs.h>
-#include <mach/r8a7779.h>
-#include <asm/mach-types.h>
-#include <asm/mach/arch.h>
-
-#define INT2SMSKCR0 IOMEM(0xfe7822a0)
-#define INT2SMSKCR1 IOMEM(0xfe7822a4)
-#define INT2SMSKCR2 IOMEM(0xfe7822a8)
-#define INT2SMSKCR3 IOMEM(0xfe7822ac)
-#define INT2SMSKCR4 IOMEM(0xfe7822b0)
-
-#define INT2NTSR0 IOMEM(0xfe700060)
-#define INT2NTSR1 IOMEM(0xfe700064)
-
-static struct renesas_intc_irqpin_config irqpin0_platform_data = {
-	.irq_base = irq_pin(0), /* IRQ0 -> IRQ3 */
-	.sense_bitfield_width = 2,
-};
-
-static struct resource irqpin0_resources[] = {
-	DEFINE_RES_MEM(0xfe78001c, 4), /* ICR1 */
-	DEFINE_RES_MEM(0xfe780010, 4), /* INTPRI */
-	DEFINE_RES_MEM(0xfe780024, 4), /* INTREQ */
-	DEFINE_RES_MEM(0xfe780044, 4), /* INTMSK0 */
-	DEFINE_RES_MEM(0xfe780064, 4), /* INTMSKCLR0 */
-	DEFINE_RES_IRQ(gic_spi(27)), /* IRQ0 */
-	DEFINE_RES_IRQ(gic_spi(28)), /* IRQ1 */
-	DEFINE_RES_IRQ(gic_spi(29)), /* IRQ2 */
-	DEFINE_RES_IRQ(gic_spi(30)), /* IRQ3 */
-};
-
-static struct platform_device irqpin0_device = {
-	.name		= "renesas_intc_irqpin",
-	.id		= 0,
-	.resource	= irqpin0_resources,
-	.num_resources	= ARRAY_SIZE(irqpin0_resources),
-	.dev		= {
-		.platform_data	= &irqpin0_platform_data,
-	},
-};
-
-void __init r8a7779_init_irq_extpin(int irlm)
-{
-	void __iomem *icr0 = ioremap_nocache(0xfe780000, PAGE_SIZE);
-	unsigned long tmp;
-
-	if (icr0) {
-		tmp = ioread32(icr0);
-		if (irlm)
-			tmp |= 1 << 23; /* IRQ0 -> IRQ3 as individual pins */
-		else
-			tmp &= ~(1 << 23); /* IRL mode - not supported */
-		tmp |= (1 << 21); /* LVLMODE = 1 */
-		iowrite32(tmp, icr0);
-		iounmap(icr0);
-
-		if (irlm)
-			platform_device_register(&irqpin0_device);
-	} else
-		pr_warn("r8a7779: unable to setup external irq pin mode\n");
-}
-
-static int r8a7779_set_wake(struct irq_data *data, unsigned int on)
-{
-	return 0; /* always allow wakeup */
-}
-
-static void __init r8a7779_init_irq_common(void)
-{
-	gic_arch_extn.irq_set_wake = r8a7779_set_wake;
-
-	/* route all interrupts to ARM */
-	__raw_writel(0xffffffff, INT2NTSR0);
-	__raw_writel(0x3fffffff, INT2NTSR1);
-
-	/* unmask all known interrupts in INTCS2 */
-	__raw_writel(0xfffffff0, INT2SMSKCR0);
-	__raw_writel(0xfff7ffff, INT2SMSKCR1);
-	__raw_writel(0xfffbffdf, INT2SMSKCR2);
-	__raw_writel(0xbffffffc, INT2SMSKCR3);
-	__raw_writel(0x003fee3f, INT2SMSKCR4);
-}
-
-void __init r8a7779_init_irq(void)
-{
-	void __iomem *gic_dist_base = IOMEM(0xf0001000);
-	void __iomem *gic_cpu_base = IOMEM(0xf0000100);
-
-	/* use GIC to handle interrupts */
-	gic_init(0, 29, gic_dist_base, gic_cpu_base);
-
-	r8a7779_init_irq_common();
-}
-
-#ifdef CONFIG_OF
-void __init r8a7779_init_irq_dt(void)
-{
-	irqchip_init();
-	r8a7779_init_irq_common();
-}
-#endif
diff --git a/arch/arm/mach-shmobile/platsmp-scu.c b/arch/arm/mach-shmobile/platsmp-scu.c
new file mode 100644
index 000000000000..c96f50160be6
--- /dev/null
+++ b/arch/arm/mach-shmobile/platsmp-scu.c
@@ -0,0 +1,81 @@
+/*
+ * SMP support for SoCs with SCU covered by mach-shmobile
+ *
+ * Copyright (C) 2013  Magnus Damm
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/delay.h>
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/smp.h>
+#include <asm/cacheflush.h>
+#include <asm/smp_plat.h>
+#include <asm/smp_scu.h>
+#include <mach/common.h>
+
+void __init shmobile_smp_scu_prepare_cpus(unsigned int max_cpus)
+{
+	/* install boot code shared by all CPUs */
+	shmobile_boot_fn = virt_to_phys(shmobile_smp_boot);
+	shmobile_boot_arg = MPIDR_HWID_BITMASK;
+
+	/* enable SCU and cache coherency on booting CPU */
+	scu_enable(shmobile_scu_base);
+	scu_power_mode(shmobile_scu_base, SCU_PM_NORMAL);
+}
+
+int shmobile_smp_scu_boot_secondary(unsigned int cpu, struct task_struct *idle)
+{
+	/* For this particular CPU register SCU boot vector */
+	shmobile_smp_hook(cpu, virt_to_phys(shmobile_boot_scu),
+			  (unsigned long)shmobile_scu_base);
+	return 0;
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+void shmobile_smp_scu_cpu_die(unsigned int cpu)
+{
+	/* For this particular CPU deregister boot vector */
+	shmobile_smp_hook(cpu, 0, 0);
+
+	dsb();
+	flush_cache_all();
+
+	/* disable cache coherency */
+	scu_power_mode(shmobile_scu_base, SCU_PM_POWEROFF);
+
+	/* jump to shared mach-shmobile sleep / reset code */
+	shmobile_smp_sleep();
+}
+
+static int shmobile_smp_scu_psr_core_disabled(int cpu)
+{
+	unsigned long mask = SCU_PM_POWEROFF << (cpu * 8);
+
+	if ((__raw_readl(shmobile_scu_base + 8) & mask) == mask)
+		return 1;
+
+	return 0;
+}
+
+int shmobile_smp_scu_cpu_kill(unsigned int cpu)
+{
+	int k;
+
+	/* this function is running on another CPU than the offline target,
+	 * here we need wait for shutdown code in platform_cpu_die() to
+	 * finish before asking SoC-specific code to power off the CPU core.
+	 */
+	for (k = 0; k < 1000; k++) {
+		if (shmobile_smp_scu_psr_core_disabled(cpu))
+			return 1;
+
+		mdelay(1);
+	}
+
+	return 0;
+}
+#endif
diff --git a/arch/arm/mach-shmobile/platsmp.c b/arch/arm/mach-shmobile/platsmp.c
index 1f958d7b0bac..d4ae616bcedb 100644
--- a/arch/arm/mach-shmobile/platsmp.c
+++ b/arch/arm/mach-shmobile/platsmp.c
@@ -12,6 +12,9 @@
  */
 #include <linux/init.h>
 #include <linux/smp.h>
+#include <asm/cacheflush.h>
+#include <asm/smp_plat.h>
+#include <mach/common.h>
 
 void __init shmobile_smp_init_cpus(unsigned int ncores)
 {
@@ -26,3 +29,18 @@ void __init shmobile_smp_init_cpus(unsigned int ncores)
 	for (i = 0; i < ncores; i++)
 		set_cpu_possible(i, true);
 }
+
+extern unsigned long shmobile_smp_fn[];
+extern unsigned long shmobile_smp_arg[];
+extern unsigned long shmobile_smp_mpidr[];
+
+void shmobile_smp_hook(unsigned int cpu, unsigned long fn, unsigned long arg)
+{
+	shmobile_smp_fn[cpu] = 0;
+	flush_cache_all();
+
+	shmobile_smp_mpidr[cpu] = cpu_logical_map(cpu);
+	shmobile_smp_fn[cpu] = fn;
+	shmobile_smp_arg[cpu] = arg;
+	flush_cache_all();
+}
diff --git a/arch/arm/mach-shmobile/setup-emev2.c b/arch/arm/mach-shmobile/setup-emev2.c
index 1ccddd228112..3ad531caf4f0 100644
--- a/arch/arm/mach-shmobile/setup-emev2.c
+++ b/arch/arm/mach-shmobile/setup-emev2.c
@@ -20,7 +20,6 @@
 #include <linux/init.h>
 #include <linux/interrupt.h>
 #include <linux/irq.h>
-#include <linux/irqchip.h>
 #include <linux/platform_device.h>
 #include <linux/platform_data/gpio-em.h>
 #include <linux/of_platform.h>
@@ -28,7 +27,6 @@
 #include <linux/input.h>
 #include <linux/io.h>
 #include <linux/irqchip/arm-gic.h>
-#include <mach/hardware.h>
 #include <mach/common.h>
 #include <mach/emev2.h>
 #include <mach/irqs.h>
@@ -39,13 +37,6 @@
 
 static struct map_desc emev2_io_desc[] __initdata = {
 #ifdef CONFIG_SMP
-	/* 128K entity map for 0xe0100000 (SMU) */
-	{
-		.virtual	= 0xe0100000,
-		.pfn		= __phys_to_pfn(0xe0100000),
-		.length		= SZ_128K,
-		.type		= MT_DEVICE
-	},
 	/* 2M mapping for SCU + L2 controller */
 	{
 		.virtual	= 0xf0000000,
@@ -63,102 +54,40 @@ void __init emev2_map_io(void)
 
 /* UART */
 static struct resource uart0_resources[] = {
-	[0]	= {
-		.start	= 0xe1020000,
-		.end	= 0xe1020037,
-		.flags	= IORESOURCE_MEM,
-	},
-	[1]	= {
-		.start	= 40,
-		.flags	= IORESOURCE_IRQ,
-	}
-};
-
-static struct platform_device uart0_device = {
-	.name		= "serial8250-em",
-	.id		= 0,
-	.num_resources	= ARRAY_SIZE(uart0_resources),
-	.resource	= uart0_resources,
+	DEFINE_RES_MEM(0xe1020000, 0x38),
+	DEFINE_RES_IRQ(40),
 };
 
 static struct resource uart1_resources[] = {
-	[0]	= {
-		.start	= 0xe1030000,
-		.end	= 0xe1030037,
-		.flags	= IORESOURCE_MEM,
-	},
-	[1]	= {
-		.start	= 41,
-		.flags	= IORESOURCE_IRQ,
-	}
-};
-
-static struct platform_device uart1_device = {
-	.name		= "serial8250-em",
-	.id		= 1,
-	.num_resources	= ARRAY_SIZE(uart1_resources),
-	.resource	= uart1_resources,
+	DEFINE_RES_MEM(0xe1030000, 0x38),
+	DEFINE_RES_IRQ(41),
 };
 
 static struct resource uart2_resources[] = {
-	[0]	= {
-		.start	= 0xe1040000,
-		.end	= 0xe1040037,
-		.flags	= IORESOURCE_MEM,
-	},
-	[1]	= {
-		.start	= 42,
-		.flags	= IORESOURCE_IRQ,
-	}
-};
-
-static struct platform_device uart2_device = {
-	.name		= "serial8250-em",
-	.id		= 2,
-	.num_resources	= ARRAY_SIZE(uart2_resources),
-	.resource	= uart2_resources,
+	DEFINE_RES_MEM(0xe1040000, 0x38),
+	DEFINE_RES_IRQ(42),
 };
 
 static struct resource uart3_resources[] = {
-	[0]	= {
-		.start	= 0xe1050000,
-		.end	= 0xe1050037,
-		.flags	= IORESOURCE_MEM,
-	},
-	[1]	= {
-		.start	= 43,
-		.flags	= IORESOURCE_IRQ,
-	}
+	DEFINE_RES_MEM(0xe1050000, 0x38),
+	DEFINE_RES_IRQ(43),
 };
 
-static struct platform_device uart3_device = {
-	.name		= "serial8250-em",
-	.id		= 3,
-	.num_resources	= ARRAY_SIZE(uart3_resources),
-	.resource	= uart3_resources,
-};
+#define emev2_register_uart(idx)					\
+	platform_device_register_simple("serial8250-em", idx,		\
+					uart##idx##_resources,		\
+					ARRAY_SIZE(uart##idx##_resources))
 
 /* STI */
 static struct resource sti_resources[] = {
-	[0] = {
-		.name	= "STI",
-		.start	= 0xe0180000,
-		.end	= 0xe0180053,
-		.flags	= IORESOURCE_MEM,
-	},
-	[1] = {
-		.start	= 157,
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-static struct platform_device sti_device = {
-	.name		= "em_sti",
-	.id		= 0,
-	.resource	= sti_resources,
-	.num_resources	= ARRAY_SIZE(sti_resources),
+	DEFINE_RES_MEM(0xe0180000, 0x54),
+	DEFINE_RES_IRQ(157),
 };
 
+#define emev2_register_sti()					\
+	platform_device_register_simple("em_sti", 0,		\
+					sti_resources,		\
+					ARRAY_SIZE(sti_resources))
 
 /* GIO */
 static struct gpio_em_config gio0_config = {
@@ -168,36 +97,10 @@ static struct gpio_em_config gio0_config = {
 };
 
 static struct resource gio0_resources[] = {
-	[0] = {
-		.name	= "GIO_000",
-		.start	= 0xe0050000,
-		.end	= 0xe005002b,
-		.flags	= IORESOURCE_MEM,
-	},
-	[1] = {
-		.name	= "GIO_000",
-		.start	= 0xe0050040,
-		.end	= 0xe005005f,
-		.flags	= IORESOURCE_MEM,
-	},
-	[2] = {
-		.start	= 99,
-		.flags	= IORESOURCE_IRQ,
-	},
-	[3] = {
-		.start	= 100,
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-static struct platform_device gio0_device = {
-	.name		= "em_gio",
-	.id		= 0,
-	.resource	= gio0_resources,
-	.num_resources	= ARRAY_SIZE(gio0_resources),
-	.dev		= {
-		.platform_data	= &gio0_config,
-	},
+	DEFINE_RES_MEM(0xe0050000, 0x2c),
+	DEFINE_RES_MEM(0xe0050040, 0x20),
+	DEFINE_RES_IRQ(99),
+	DEFINE_RES_IRQ(100),
 };
 
 static struct gpio_em_config gio1_config = {
@@ -207,36 +110,10 @@ static struct gpio_em_config gio1_config = {
 };
 
 static struct resource gio1_resources[] = {
-	[0] = {
-		.name	= "GIO_032",
-		.start	= 0xe0050080,
-		.end	= 0xe00500ab,
-		.flags	= IORESOURCE_MEM,
-	},
-	[1] = {
-		.name	= "GIO_032",
-		.start	= 0xe00500c0,
-		.end	= 0xe00500df,
-		.flags	= IORESOURCE_MEM,
-	},
-	[2] = {
-		.start	= 101,
-		.flags	= IORESOURCE_IRQ,
-	},
-	[3] = {
-		.start	= 102,
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-static struct platform_device gio1_device = {
-	.name		= "em_gio",
-	.id		= 1,
-	.resource	= gio1_resources,
-	.num_resources	= ARRAY_SIZE(gio1_resources),
-	.dev		= {
-		.platform_data	= &gio1_config,
-	},
+	DEFINE_RES_MEM(0xe0050080, 0x2c),
+	DEFINE_RES_MEM(0xe00500c0, 0x20),
+	DEFINE_RES_IRQ(101),
+	DEFINE_RES_IRQ(102),
 };
 
 static struct gpio_em_config gio2_config = {
@@ -246,36 +123,10 @@ static struct gpio_em_config gio2_config = {
 };
 
 static struct resource gio2_resources[] = {
-	[0] = {
-		.name	= "GIO_064",
-		.start	= 0xe0050100,
-		.end	= 0xe005012b,
-		.flags	= IORESOURCE_MEM,
-	},
-	[1] = {
-		.name	= "GIO_064",
-		.start	= 0xe0050140,
-		.end	= 0xe005015f,
-		.flags	= IORESOURCE_MEM,
-	},
-	[2] = {
-		.start	= 103,
-		.flags	= IORESOURCE_IRQ,
-	},
-	[3] = {
-		.start	= 104,
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-static struct platform_device gio2_device = {
-	.name		= "em_gio",
-	.id		= 2,
-	.resource	= gio2_resources,
-	.num_resources	= ARRAY_SIZE(gio2_resources),
-	.dev		= {
-		.platform_data	= &gio2_config,
-	},
+	DEFINE_RES_MEM(0xe0050100, 0x2c),
+	DEFINE_RES_MEM(0xe0050140, 0x20),
+	DEFINE_RES_IRQ(103),
+	DEFINE_RES_IRQ(104),
 };
 
 static struct gpio_em_config gio3_config = {
@@ -285,36 +136,10 @@ static struct gpio_em_config gio3_config = {
 };
 
 static struct resource gio3_resources[] = {
-	[0] = {
-		.name	= "GIO_096",
-		.start	= 0xe0050180,
-		.end	= 0xe00501ab,
-		.flags	= IORESOURCE_MEM,
-	},
-	[1] = {
-		.name	= "GIO_096",
-		.start	= 0xe00501c0,
-		.end	= 0xe00501df,
-		.flags	= IORESOURCE_MEM,
-	},
-	[2] = {
-		.start	= 105,
-		.flags	= IORESOURCE_IRQ,
-	},
-	[3] = {
-		.start	= 106,
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-static struct platform_device gio3_device = {
-	.name		= "em_gio",
-	.id		= 3,
-	.resource	= gio3_resources,
-	.num_resources	= ARRAY_SIZE(gio3_resources),
-	.dev		= {
-		.platform_data	= &gio3_config,
-	},
+	DEFINE_RES_MEM(0xe0050180, 0x2c),
+	DEFINE_RES_MEM(0xe00501c0, 0x20),
+	DEFINE_RES_IRQ(105),
+	DEFINE_RES_IRQ(106),
 };
 
 static struct gpio_em_config gio4_config = {
@@ -324,126 +149,53 @@ static struct gpio_em_config gio4_config = {
 };
 
 static struct resource gio4_resources[] = {
-	[0] = {
-		.name	= "GIO_128",
-		.start	= 0xe0050200,
-		.end	= 0xe005022b,
-		.flags	= IORESOURCE_MEM,
-	},
-	[1] = {
-		.name	= "GIO_128",
-		.start	= 0xe0050240,
-		.end	= 0xe005025f,
-		.flags	= IORESOURCE_MEM,
-	},
-	[2] = {
-		.start	= 107,
-		.flags	= IORESOURCE_IRQ,
-	},
-	[3] = {
-		.start	= 108,
-		.flags	= IORESOURCE_IRQ,
-	},
+	DEFINE_RES_MEM(0xe0050200, 0x2c),
+	DEFINE_RES_MEM(0xe0050240, 0x20),
+	DEFINE_RES_IRQ(107),
+	DEFINE_RES_IRQ(108),
 };
 
-static struct platform_device gio4_device = {
-	.name		= "em_gio",
-	.id		= 4,
-	.resource	= gio4_resources,
-	.num_resources	= ARRAY_SIZE(gio4_resources),
-	.dev		= {
-		.platform_data	= &gio4_config,
-	},
-};
+#define emev2_register_gio(idx)						\
+	platform_device_register_resndata(&platform_bus, "em_gio",	\
+					  idx, gio##idx##_resources,	\
+					  ARRAY_SIZE(gio##idx##_resources), \
+					  &gio##idx##_config,		\
+					  sizeof(struct gpio_em_config))
 
 static struct resource pmu_resources[] = {
-	[0] = {
-		.start	= 152,
-		.end	= 152,
-		.flags	= IORESOURCE_IRQ,
-	},
-	[1] = {
-		.start	= 153,
-		.end	= 153,
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-static struct platform_device pmu_device = {
-	.name		= "arm-pmu",
-	.id		= -1,
-	.num_resources	= ARRAY_SIZE(pmu_resources),
-	.resource	= pmu_resources,
+	DEFINE_RES_IRQ(152),
+	DEFINE_RES_IRQ(153),
 };
 
-static struct platform_device *emev2_early_devices[] __initdata = {
-	&uart0_device,
-	&uart1_device,
-	&uart2_device,
-	&uart3_device,
-};
-
-static struct platform_device *emev2_late_devices[] __initdata = {
-	&sti_device,
-	&gio0_device,
-	&gio1_device,
-	&gio2_device,
-	&gio3_device,
-	&gio4_device,
-	&pmu_device,
-};
+#define emev2_register_pmu()					\
+	platform_device_register_simple("arm-pmu", -1,		\
+					pmu_resources,		\
+					ARRAY_SIZE(pmu_resources))
 
 void __init emev2_add_standard_devices(void)
 {
-	emev2_clock_init();
-
-	platform_add_devices(emev2_early_devices,
-			     ARRAY_SIZE(emev2_early_devices));
-
-	platform_add_devices(emev2_late_devices,
-			     ARRAY_SIZE(emev2_late_devices));
+	if (!IS_ENABLED(CONFIG_COMMON_CLK))
+		emev2_clock_init();
+
+	emev2_register_uart(0);
+	emev2_register_uart(1);
+	emev2_register_uart(2);
+	emev2_register_uart(3);
+	emev2_register_sti();
+	emev2_register_gio(0);
+	emev2_register_gio(1);
+	emev2_register_gio(2);
+	emev2_register_gio(3);
+	emev2_register_gio(4);
+	emev2_register_pmu();
 }
 
-static void __init emev2_init_delay(void)
+void __init emev2_init_delay(void)
 {
 	shmobile_setup_delay(533, 1, 3); /* Cortex-A9 @ 533MHz */
 }
 
-void __init emev2_add_early_devices(void)
-{
-	emev2_init_delay();
-
-	early_platform_add_devices(emev2_early_devices,
-				   ARRAY_SIZE(emev2_early_devices));
-
-	/* setup early console here as well */
-	shmobile_setup_console();
-}
-
-void __init emev2_init_irq(void)
-{
-	void __iomem *gic_dist_base;
-	void __iomem *gic_cpu_base;
-
-	/* Static mappings, never released */
-	gic_dist_base = ioremap(0xe0028000, PAGE_SIZE);
-	gic_cpu_base = ioremap(0xe0020000, PAGE_SIZE);
-	BUG_ON(!gic_dist_base || !gic_cpu_base);
-
-	/* Use GIC to handle interrupts */
-	gic_init(0, 29, gic_dist_base, gic_cpu_base);
-}
-
 #ifdef CONFIG_USE_OF
-static const struct of_dev_auxdata emev2_auxdata_lookup[] __initconst = {
-	{ }
-};
-
-static void __init emev2_add_standard_devices_dt(void)
-{
-	of_platform_populate(NULL, of_default_bus_match_table,
-			     emev2_auxdata_lookup, NULL);
-}
 
 static const char *emev2_boards_compat_dt[] __initdata = {
 	"renesas,emev2",
@@ -452,10 +204,8 @@ static const char *emev2_boards_compat_dt[] __initdata = {
 
 DT_MACHINE_START(EMEV2_DT, "Generic Emma Mobile EV2 (Flattened Device Tree)")
 	.smp		= smp_ops(emev2_smp_ops),
+	.map_io		= emev2_map_io,
 	.init_early	= emev2_init_delay,
-	.nr_irqs	= NR_IRQS_LEGACY,
-	.init_irq	= irqchip_init,
-	.init_machine	= emev2_add_standard_devices_dt,
 	.dt_compat	= emev2_boards_compat_dt,
 MACHINE_END
 
diff --git a/arch/arm/mach-shmobile/setup-r8a73a4.c b/arch/arm/mach-shmobile/setup-r8a73a4.c
index 7f45c2edbca9..89491700afb7 100644
--- a/arch/arm/mach-shmobile/setup-r8a73a4.c
+++ b/arch/arm/mach-shmobile/setup-r8a73a4.c
@@ -18,11 +18,11 @@
  * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
  */
 #include <linux/irq.h>
-#include <linux/irqchip.h>
 #include <linux/kernel.h>
 #include <linux/of_platform.h>
 #include <linux/platform_data/irq-renesas-irqc.h>
 #include <linux/serial_sci.h>
+#include <linux/sh_timer.h>
 #include <mach/common.h>
 #include <mach/irqs.h>
 #include <mach/r8a73a4.h>
@@ -169,7 +169,26 @@ static const struct resource thermal0_resources[] = {
 					thermal0_resources,		\
 					ARRAY_SIZE(thermal0_resources))
 
-void __init r8a73a4_add_standard_devices(void)
+static struct sh_timer_config cmt10_platform_data = {
+	.name = "CMT10",
+	.timer_bit = 0,
+	.clockevent_rating = 80,
+};
+
+static struct resource cmt10_resources[] = {
+	DEFINE_RES_MEM(0xe6130010, 0x0c),
+	DEFINE_RES_MEM(0xe6130000, 0x04),
+	DEFINE_RES_IRQ(gic_spi(120)), /* CMT1_0 */
+};
+
+#define r8a7790_register_cmt(idx)					\
+	platform_device_register_resndata(&platform_bus, "sh_cmt",	\
+					  idx, cmt##idx##_resources,	\
+					  ARRAY_SIZE(cmt##idx##_resources), \
+					  &cmt##idx##_platform_data,	\
+					  sizeof(struct sh_timer_config))
+
+void __init r8a73a4_add_dt_devices(void)
 {
 	r8a73a4_register_scif(SCIFA0);
 	r8a73a4_register_scif(SCIFA1);
@@ -177,26 +196,33 @@ void __init r8a73a4_add_standard_devices(void)
 	r8a73a4_register_scif(SCIFB1);
 	r8a73a4_register_scif(SCIFB2);
 	r8a73a4_register_scif(SCIFB3);
+	r8a7790_register_cmt(10);
+}
+
+void __init r8a73a4_add_standard_devices(void)
+{
+	r8a73a4_add_dt_devices();
 	r8a73a4_register_irqc(0);
 	r8a73a4_register_irqc(1);
 	r8a73a4_register_thermal();
 }
 
-#ifdef CONFIG_USE_OF
-void __init r8a73a4_add_standard_devices_dt(void)
+void __init r8a73a4_init_delay(void)
 {
-	of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
+#ifndef CONFIG_ARM_ARCH_TIMER
+	shmobile_setup_delay(1500, 2, 4); /* Cortex-A15 @ 1500MHz */
+#endif
 }
 
+#ifdef CONFIG_USE_OF
+
 static const char *r8a73a4_boards_compat_dt[] __initdata = {
 	"renesas,r8a73a4",
 	NULL,
 };
 
 DT_MACHINE_START(R8A73A4_DT, "Generic R8A73A4 (Flattened Device Tree)")
-	.init_irq	= irqchip_init,
-	.init_machine	= r8a73a4_add_standard_devices_dt,
-	.init_time	= shmobile_timer_init,
+	.init_early	= r8a73a4_init_delay,
 	.dt_compat	= r8a73a4_boards_compat_dt,
 MACHINE_END
 #endif /* CONFIG_USE_OF */
diff --git a/arch/arm/mach-shmobile/setup-r8a7740.c b/arch/arm/mach-shmobile/setup-r8a7740.c
index 00c5a707238b..b7d4b2c3bc29 100644
--- a/arch/arm/mach-shmobile/setup-r8a7740.c
+++ b/arch/arm/mach-shmobile/setup-r8a7740.c
@@ -22,6 +22,8 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/io.h>
+#include <linux/irqchip.h>
+#include <linux/irqchip/arm-gic.h>
 #include <linux/platform_data/irq-renesas-intc-irqpin.h>
 #include <linux/platform_device.h>
 #include <linux/of_platform.h>
@@ -588,6 +590,16 @@ static const struct sh_dmae_slave_config r8a7740_dmae_slaves[] = {
 		.addr		= 0xfe1f0064,
 		.chcr		= CHCR_TX(XMIT_SZ_32BIT),
 		.mid_rid	= 0xb5,
+	}, {
+		.slave_id	= SHDMA_SLAVE_MMCIF_TX,
+		.addr		= 0xe6bd0034,
+		.chcr		= CHCR_TX(XMIT_SZ_32BIT),
+		.mid_rid	= 0xd1,
+	}, {
+		.slave_id	= SHDMA_SLAVE_MMCIF_RX,
+		.addr		= 0xe6bd0034,
+		.chcr		= CHCR_RX(XMIT_SZ_32BIT),
+		.mid_rid	= 0xd2,
 	},
 };
 
@@ -986,16 +998,22 @@ void __init r8a7740_add_early_devices(void)
 
 #ifdef CONFIG_USE_OF
 
-static const struct of_dev_auxdata r8a7740_auxdata_lookup[] __initconst = {
-	{ }
-};
+void __init r8a7740_add_early_devices_dt(void)
+{
+	shmobile_setup_delay(800, 1, 3); /* Cortex-A9 @ 800MHz */
+
+	early_platform_add_devices(r8a7740_early_devices,
+				   ARRAY_SIZE(r8a7740_early_devices));
+
+	/* setup early console here as well */
+	shmobile_setup_console();
+}
 
 void __init r8a7740_add_standard_devices_dt(void)
 {
 	platform_add_devices(r8a7740_devices_dt,
 			    ARRAY_SIZE(r8a7740_devices_dt));
-	of_platform_populate(NULL, of_default_bus_match_table,
-			     r8a7740_auxdata_lookup, NULL);
+	of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
 }
 
 void __init r8a7740_init_delay(void)
@@ -1003,6 +1021,36 @@ void __init r8a7740_init_delay(void)
 	shmobile_setup_delay(800, 1, 3); /* Cortex-A9 @ 800MHz */
 };
 
+void __init r8a7740_init_irq_of(void)
+{
+	void __iomem *intc_prio_base = ioremap_nocache(0xe6900010, 0x10);
+	void __iomem *intc_msk_base = ioremap_nocache(0xe6900040, 0x10);
+	void __iomem *pfc_inta_ctrl = ioremap_nocache(0xe605807c, 0x4);
+
+	irqchip_init();
+
+	/* route signals to GIC */
+	iowrite32(0x0, pfc_inta_ctrl);
+
+	/*
+	 * To mask the shared interrupt to SPI 149 we must ensure to set
+	 * PRIO *and* MASK. Else we run into IRQ floods when registering
+	 * the intc_irqpin devices
+	 */
+	iowrite32(0x0, intc_prio_base + 0x0);
+	iowrite32(0x0, intc_prio_base + 0x4);
+	iowrite32(0x0, intc_prio_base + 0x8);
+	iowrite32(0x0, intc_prio_base + 0xc);
+	iowrite8(0xff, intc_msk_base + 0x0);
+	iowrite8(0xff, intc_msk_base + 0x4);
+	iowrite8(0xff, intc_msk_base + 0x8);
+	iowrite8(0xff, intc_msk_base + 0xc);
+
+	iounmap(intc_prio_base);
+	iounmap(intc_msk_base);
+	iounmap(pfc_inta_ctrl);
+}
+
 static void __init r8a7740_generic_init(void)
 {
 	r8a7740_clock_init(0);
@@ -1019,7 +1067,6 @@ DT_MACHINE_START(R8A7740_DT, "Generic R8A7740 (Flattened Device Tree)")
 	.init_early	= r8a7740_init_delay,
 	.init_irq	= r8a7740_init_irq_of,
 	.init_machine	= r8a7740_generic_init,
-	.init_time	= shmobile_timer_init,
 	.dt_compat	= r8a7740_boards_compat_dt,
 MACHINE_END
 
diff --git a/arch/arm/mach-shmobile/setup-r8a7778.c b/arch/arm/mach-shmobile/setup-r8a7778.c
index 80c20392ad7c..6a2657ebd197 100644
--- a/arch/arm/mach-shmobile/setup-r8a7778.c
+++ b/arch/arm/mach-shmobile/setup-r8a7778.c
@@ -53,7 +53,7 @@
 	.irqs		= SCIx_IRQ_MUXED(irq),			\
 }
 
-static struct plat_sci_port scif_platform_data[] = {
+static struct plat_sci_port scif_platform_data[] __initdata = {
 	SCIF_INFO(0xffe40000, gic_iid(0x66)),
 	SCIF_INFO(0xffe41000, gic_iid(0x67)),
 	SCIF_INFO(0xffe42000, gic_iid(0x68)),
@@ -63,24 +63,24 @@ static struct plat_sci_port scif_platform_data[] = {
 };
 
 /* TMU */
-static struct resource sh_tmu0_resources[] = {
+static struct resource sh_tmu0_resources[] __initdata = {
 	DEFINE_RES_MEM(0xffd80008, 12),
 	DEFINE_RES_IRQ(gic_iid(0x40)),
 };
 
-static struct sh_timer_config sh_tmu0_platform_data = {
+static struct sh_timer_config sh_tmu0_platform_data __initdata = {
 	.name			= "TMU00",
 	.channel_offset		= 0x4,
 	.timer_bit		= 0,
 	.clockevent_rating	= 200,
 };
 
-static struct resource sh_tmu1_resources[] = {
+static struct resource sh_tmu1_resources[] __initdata = {
 	DEFINE_RES_MEM(0xffd80014, 12),
 	DEFINE_RES_IRQ(gic_iid(0x41)),
 };
 
-static struct sh_timer_config sh_tmu1_platform_data = {
+static struct sh_timer_config sh_tmu1_platform_data __initdata = {
 	.name			= "TMU01",
 	.channel_offset		= 0x10,
 	.timer_bit		= 1,
@@ -95,20 +95,6 @@ static struct sh_timer_config sh_tmu1_platform_data = {
 		&sh_tmu##idx##_platform_data,		\
 		sizeof(sh_tmu##idx##_platform_data))
 
-/* USB PHY */
-static struct resource usb_phy_resources[] __initdata = {
-	DEFINE_RES_MEM(0xffe70800, 0x100),
-	DEFINE_RES_MEM(0xffe76000, 0x100),
-};
-
-void __init r8a7778_add_usb_phy_device(struct rcar_phy_platform_data *pdata)
-{
-	platform_device_register_resndata(&platform_bus, "rcar_usb_phy", -1,
-					  usb_phy_resources,
-					  ARRAY_SIZE(usb_phy_resources),
-					  pdata, sizeof(*pdata));
-}
-
 /* USB */
 static struct usb_phy *phy;
 
@@ -189,7 +175,7 @@ USB_PLATFORM_INFO(ehci);
 USB_PLATFORM_INFO(ohci);
 
 /* Ether */
-static struct resource ether_resources[] = {
+static struct resource ether_resources[] __initdata = {
 	DEFINE_RES_MEM(0xfde00000, 0x400),
 	DEFINE_RES_IRQ(gic_iid(0x89)),
 };
@@ -203,17 +189,17 @@ void __init r8a7778_add_ether_device(struct sh_eth_plat_data *pdata)
 }
 
 /* PFC/GPIO */
-static struct resource pfc_resources[] = {
+static struct resource pfc_resources[] __initdata = {
 	DEFINE_RES_MEM(0xfffc0000, 0x118),
 };
 
 #define R8A7778_GPIO(idx)						\
-static struct resource r8a7778_gpio##idx##_resources[] = {		\
+static struct resource r8a7778_gpio##idx##_resources[] __initdata = {	\
 	DEFINE_RES_MEM(0xffc40000 + 0x1000 * (idx), 0x30),		\
 	DEFINE_RES_IRQ(gic_iid(0x87)),					\
 };									\
 									\
-static struct gpio_rcar_config r8a7778_gpio##idx##_platform_data = {	\
+static struct gpio_rcar_config r8a7778_gpio##idx##_platform_data __initdata = { \
 	.gpio_base	= 32 * (idx),					\
 	.irq_base	= GPIO_IRQ_BASE(idx),				\
 	.number_of_pins	= 32,						\
@@ -248,30 +234,6 @@ void __init r8a7778_pinmux_init(void)
 	r8a7778_register_gpio(4);
 };
 
-/* SDHI */
-static struct resource sdhi_resources[] = {
-	/* SDHI0 */
-	DEFINE_RES_MEM(0xFFE4C000, 0x100),
-	DEFINE_RES_IRQ(gic_iid(0x77)),
-	/* SDHI1 */
-	DEFINE_RES_MEM(0xFFE4D000, 0x100),
-	DEFINE_RES_IRQ(gic_iid(0x78)),
-	/* SDHI2 */
-	DEFINE_RES_MEM(0xFFE4F000, 0x100),
-	DEFINE_RES_IRQ(gic_iid(0x76)),
-};
-
-void __init r8a7778_sdhi_init(int id,
-			      struct sh_mobile_sdhi_info *info)
-{
-	BUG_ON(id < 0 || id > 2);
-
-	platform_device_register_resndata(
-		&platform_bus, "sh_mobile_sdhi", id,
-		sdhi_resources + (2 * id), 2,
-		info, sizeof(*info));
-}
-
 /* I2C */
 static struct resource i2c_resources[] __initdata = {
 	/* I2C0 */
@@ -288,7 +250,7 @@ static struct resource i2c_resources[] __initdata = {
 	DEFINE_RES_IRQ(gic_iid(0x6d)),
 };
 
-void __init r8a7778_add_i2c_device(int id)
+static void __init r8a7778_register_i2c(int id)
 {
 	BUG_ON(id < 0 || id > 3);
 
@@ -310,7 +272,7 @@ static struct resource hspi_resources[] __initdata = {
 	DEFINE_RES_IRQ(gic_iid(0x75)),
 };
 
-void __init r8a7778_add_hspi_device(int id)
+void __init r8a7778_register_hspi(int id)
 {
 	BUG_ON(id < 0 || id > 2);
 
@@ -319,21 +281,41 @@ void __init r8a7778_add_hspi_device(int id)
 		hspi_resources + (2 * id), 2);
 }
 
-/* MMC */
-static struct resource mmc_resources[] __initdata = {
-	DEFINE_RES_MEM(0xffe4e000, 0x100),
-	DEFINE_RES_IRQ(gic_iid(0x5d)),
+/* VIN */
+#define R8A7778_VIN(idx)						\
+static struct resource vin##idx##_resources[] __initdata = {		\
+	DEFINE_RES_MEM(0xffc50000 + 0x1000 * (idx), 0x1000),		\
+	DEFINE_RES_IRQ(gic_iid(0x5a)),					\
+};									\
+									\
+static struct platform_device_info vin##idx##_info __initdata = {	\
+	.parent		= &platform_bus,				\
+	.name		= "r8a7778-vin",				\
+	.id		= idx,						\
+	.res		= vin##idx##_resources,				\
+	.num_res	= ARRAY_SIZE(vin##idx##_resources),		\
+	.dma_mask	= DMA_BIT_MASK(32),				\
+}
+
+R8A7778_VIN(0);
+R8A7778_VIN(1);
+
+static struct platform_device_info *vin_info_table[] __initdata = {
+	&vin0_info,
+	&vin1_info,
 };
 
-void __init r8a7778_add_mmc_device(struct sh_mmcif_plat_data *info)
+void __init r8a7778_add_vin_device(int id, struct rcar_vin_platform_data *pdata)
 {
-	platform_device_register_resndata(
-		&platform_bus, "sh_mmcif", -1,
-		mmc_resources, ARRAY_SIZE(mmc_resources),
-		info, sizeof(*info));
+	BUG_ON(id < 0 || id > 1);
+
+	vin_info_table[id]->data = pdata;
+	vin_info_table[id]->size_data = sizeof(*pdata);
+
+	platform_device_register_full(vin_info_table[id]);
 }
 
-void __init r8a7778_add_standard_devices(void)
+void __init r8a7778_add_dt_devices(void)
 {
 	int i;
 
@@ -357,6 +339,18 @@ void __init r8a7778_add_standard_devices(void)
 	r8a7778_register_tmu(1);
 }
 
+void __init r8a7778_add_standard_devices(void)
+{
+	r8a7778_add_dt_devices();
+	r8a7778_register_i2c(0);
+	r8a7778_register_i2c(1);
+	r8a7778_register_i2c(2);
+	r8a7778_register_i2c(3);
+	r8a7778_register_hspi(0);
+	r8a7778_register_hspi(1);
+	r8a7778_register_hspi(2);
+}
+
 void __init r8a7778_init_late(void)
 {
 	phy = usb_get_phy(USB_PHY_TYPE_USB2);
@@ -365,12 +359,12 @@ void __init r8a7778_init_late(void)
 	platform_device_register_full(&ohci_info);
 }
 
-static struct renesas_intc_irqpin_config irqpin_platform_data = {
+static struct renesas_intc_irqpin_config irqpin_platform_data __initdata = {
 	.irq_base = irq_pin(0), /* IRQ0 -> IRQ3 */
 	.sense_bitfield_width = 2,
 };
 
-static struct resource irqpin_resources[] = {
+static struct resource irqpin_resources[] __initdata = {
 	DEFINE_RES_MEM(0xfe78001c, 4), /* ICR1 */
 	DEFINE_RES_MEM(0xfe780010, 4), /* INTPRI */
 	DEFINE_RES_MEM(0xfe780024, 4), /* INTREQ */
@@ -408,17 +402,25 @@ void __init r8a7778_init_irq_extpin(int irlm)
 			&irqpin_platform_data, sizeof(irqpin_platform_data));
 }
 
+void __init r8a7778_init_delay(void)
+{
+	shmobile_setup_delay(800, 1, 3); /* Cortex-A9 @ 800MHz */
+}
+
+#ifdef CONFIG_USE_OF
 #define INT2SMSKCR0	0x82288 /* 0xfe782288 */
 #define INT2SMSKCR1	0x8228c /* 0xfe78228c */
 
 #define INT2NTSR0	0x00018 /* 0xfe700018 */
 #define INT2NTSR1	0x0002c /* 0xfe70002c */
-static void __init r8a7778_init_irq_common(void)
+void __init r8a7778_init_irq_dt(void)
 {
 	void __iomem *base = ioremap_nocache(0xfe700000, 0x00100000);
 
 	BUG_ON(!base);
 
+	irqchip_init();
+
 	/* route all interrupts to ARM */
 	__raw_writel(0x73ffffff, base + INT2NTSR0);
 	__raw_writel(0xffffffff, base + INT2NTSR1);
@@ -430,43 +432,6 @@ static void __init r8a7778_init_irq_common(void)
 	iounmap(base);
 }
 
-void __init r8a7778_init_irq(void)
-{
-	void __iomem *gic_dist_base;
-	void __iomem *gic_cpu_base;
-
-	gic_dist_base = ioremap_nocache(0xfe438000, PAGE_SIZE);
-	gic_cpu_base  = ioremap_nocache(0xfe430000, PAGE_SIZE);
-	BUG_ON(!gic_dist_base || !gic_cpu_base);
-
-	/* use GIC to handle interrupts */
-	gic_init(0, 29, gic_dist_base, gic_cpu_base);
-
-	r8a7778_init_irq_common();
-}
-
-void __init r8a7778_init_delay(void)
-{
-	shmobile_setup_delay(800, 1, 3); /* Cortex-A9 @ 800MHz */
-}
-
-#ifdef CONFIG_USE_OF
-void __init r8a7778_init_irq_dt(void)
-{
-	irqchip_init();
-	r8a7778_init_irq_common();
-}
-
-static const struct of_dev_auxdata r8a7778_auxdata_lookup[] __initconst = {
-	{},
-};
-
-void __init r8a7778_add_standard_devices_dt(void)
-{
-	of_platform_populate(NULL, of_default_bus_match_table,
-			     r8a7778_auxdata_lookup, NULL);
-}
-
 static const char *r8a7778_compat_dt[] __initdata = {
 	"renesas,r8a7778",
 	NULL,
@@ -475,8 +440,6 @@ static const char *r8a7778_compat_dt[] __initdata = {
 DT_MACHINE_START(R8A7778_DT, "Generic R8A7778 (Flattened Device Tree)")
 	.init_early	= r8a7778_init_delay,
 	.init_irq	= r8a7778_init_irq_dt,
-	.init_machine	= r8a7778_add_standard_devices_dt,
-	.init_time	= shmobile_timer_init,
 	.dt_compat	= r8a7778_compat_dt,
 	.init_late      = r8a7778_init_late,
 MACHINE_END
diff --git a/arch/arm/mach-shmobile/setup-r8a7779.c b/arch/arm/mach-shmobile/setup-r8a7779.c
index 398687761f50..ecd0148ee1e1 100644
--- a/arch/arm/mach-shmobile/setup-r8a7779.c
+++ b/arch/arm/mach-shmobile/setup-r8a7779.c
@@ -22,14 +22,16 @@
 #include <linux/init.h>
 #include <linux/interrupt.h>
 #include <linux/irq.h>
+#include <linux/irqchip.h>
+#include <linux/irqchip/arm-gic.h>
 #include <linux/of_platform.h>
 #include <linux/platform_data/gpio-rcar.h>
+#include <linux/platform_data/irq-renesas-intc-irqpin.h>
 #include <linux/platform_device.h>
 #include <linux/delay.h>
 #include <linux/input.h>
 #include <linux/io.h>
 #include <linux/serial_sci.h>
-#include <linux/sh_intc.h>
 #include <linux/sh_timer.h>
 #include <linux/dma-mapping.h>
 #include <linux/usb/otg.h>
@@ -37,7 +39,6 @@
 #include <linux/usb/ehci_pdriver.h>
 #include <linux/usb/ohci_pdriver.h>
 #include <linux/pm_runtime.h>
-#include <mach/hardware.h>
 #include <mach/irqs.h>
 #include <mach/r8a7779.h>
 #include <mach/common.h>
@@ -69,6 +70,60 @@ void __init r8a7779_map_io(void)
 	iotable_init(r8a7779_io_desc, ARRAY_SIZE(r8a7779_io_desc));
 }
 
+/* IRQ */
+#define INT2SMSKCR0 IOMEM(0xfe7822a0)
+#define INT2SMSKCR1 IOMEM(0xfe7822a4)
+#define INT2SMSKCR2 IOMEM(0xfe7822a8)
+#define INT2SMSKCR3 IOMEM(0xfe7822ac)
+#define INT2SMSKCR4 IOMEM(0xfe7822b0)
+
+#define INT2NTSR0 IOMEM(0xfe700060)
+#define INT2NTSR1 IOMEM(0xfe700064)
+
+static struct renesas_intc_irqpin_config irqpin0_platform_data __initdata = {
+	.irq_base = irq_pin(0), /* IRQ0 -> IRQ3 */
+	.sense_bitfield_width = 2,
+};
+
+static struct resource irqpin0_resources[] __initdata = {
+	DEFINE_RES_MEM(0xfe78001c, 4), /* ICR1 */
+	DEFINE_RES_MEM(0xfe780010, 4), /* INTPRI */
+	DEFINE_RES_MEM(0xfe780024, 4), /* INTREQ */
+	DEFINE_RES_MEM(0xfe780044, 4), /* INTMSK0 */
+	DEFINE_RES_MEM(0xfe780064, 4), /* INTMSKCLR0 */
+	DEFINE_RES_IRQ(gic_spi(27)), /* IRQ0 */
+	DEFINE_RES_IRQ(gic_spi(28)), /* IRQ1 */
+	DEFINE_RES_IRQ(gic_spi(29)), /* IRQ2 */
+	DEFINE_RES_IRQ(gic_spi(30)), /* IRQ3 */
+};
+
+void __init r8a7779_init_irq_extpin(int irlm)
+{
+	void __iomem *icr0 = ioremap_nocache(0xfe780000, PAGE_SIZE);
+	u32 tmp;
+
+	if (!icr0) {
+		pr_warn("r8a7779: unable to setup external irq pin mode\n");
+		return;
+	}
+
+	tmp = ioread32(icr0);
+	if (irlm)
+		tmp |= 1 << 23; /* IRQ0 -> IRQ3 as individual pins */
+	else
+		tmp &= ~(1 << 23); /* IRL mode - not supported */
+	tmp |= (1 << 21); /* LVLMODE = 1 */
+	iowrite32(tmp, icr0);
+	iounmap(icr0);
+
+	if (irlm)
+		platform_device_register_resndata(
+			&platform_bus, "renesas_intc_irqpin", -1,
+			irqpin0_resources, ARRAY_SIZE(irqpin0_resources),
+			&irqpin0_platform_data, sizeof(irqpin0_platform_data));
+}
+
+/* PFC/GPIO */
 static struct resource r8a7779_pfc_resources[] = {
 	DEFINE_RES_MEM(0xfffc0000, 0x023c),
 };
@@ -388,15 +443,6 @@ static struct platform_device sata_device = {
 	},
 };
 
-/* USB PHY */
-static struct resource usb_phy_resources[] __initdata = {
-	[0] = {
-		.start		= 0xffe70800,
-		.end		= 0xffe70900 - 1,
-		.flags		= IORESOURCE_MEM,
-	},
-};
-
 /* USB */
 static struct usb_phy *phy;
 
@@ -548,7 +594,7 @@ static struct platform_device ohci1_device = {
 };
 
 /* Ether */
-static struct resource ether_resources[] = {
+static struct resource ether_resources[] __initdata = {
 	{
 		.start	= 0xfde00000,
 		.end	= 0xfde003ff,
@@ -559,6 +605,33 @@ static struct resource ether_resources[] = {
 	},
 };
 
+#define R8A7779_VIN(idx) \
+static struct resource vin##idx##_resources[] __initdata = {		\
+	DEFINE_RES_MEM(0xffc50000 + 0x1000 * (idx), 0x1000),		\
+	DEFINE_RES_IRQ(gic_iid(0x5f + (idx))),				\
+};									\
+									\
+static struct platform_device_info vin##idx##_info __initdata = {	\
+	.parent		= &platform_bus,				\
+	.name		= "r8a7779-vin",				\
+	.id		= idx,						\
+	.res		= vin##idx##_resources,				\
+	.num_res	= ARRAY_SIZE(vin##idx##_resources),		\
+	.dma_mask	= DMA_BIT_MASK(32),				\
+}
+
+R8A7779_VIN(0);
+R8A7779_VIN(1);
+R8A7779_VIN(2);
+R8A7779_VIN(3);
+
+static struct platform_device_info *vin_info_table[] __initdata = {
+	&vin0_info,
+	&vin1_info,
+	&vin2_info,
+	&vin3_info,
+};
+
 static struct platform_device *r8a7779_devices_dt[] __initdata = {
 	&scif0_device,
 	&scif1_device,
@@ -602,12 +675,14 @@ void __init r8a7779_add_ether_device(struct sh_eth_plat_data *pdata)
 					  pdata, sizeof(*pdata));
 }
 
-void __init r8a7779_add_usb_phy_device(struct rcar_phy_platform_data *pdata)
+void __init r8a7779_add_vin_device(int id, struct rcar_vin_platform_data *pdata)
 {
-	platform_device_register_resndata(&platform_bus, "rcar_usb_phy", -1,
-					  usb_phy_resources,
-					  ARRAY_SIZE(usb_phy_resources),
-					  pdata, sizeof(*pdata));
+	BUG_ON(id < 0 || id > 3);
+
+	vin_info_table[id]->data = pdata;
+	vin_info_table[id]->size_data = sizeof(*pdata);
+
+	platform_device_register_full(vin_info_table[id]);
 }
 
 /* do nothing for !CONFIG_SMP or !CONFIG_HAVE_TWD */
@@ -616,8 +691,8 @@ void __init __weak r8a7779_register_twd(void) { }
 void __init r8a7779_earlytimer_init(void)
 {
 	r8a7779_clock_init();
-	shmobile_earlytimer_init();
 	r8a7779_register_twd();
+	shmobile_earlytimer_init();
 }
 
 void __init r8a7779_add_early_devices(void)
@@ -660,15 +735,34 @@ void __init r8a7779_init_late(void)
 }
 
 #ifdef CONFIG_USE_OF
+static int r8a7779_set_wake(struct irq_data *data, unsigned int on)
+{
+	return 0; /* always allow wakeup */
+}
+
+void __init r8a7779_init_irq_dt(void)
+{
+	gic_arch_extn.irq_set_wake = r8a7779_set_wake;
+
+	irqchip_init();
+
+	/* route all interrupts to ARM */
+	__raw_writel(0xffffffff, INT2NTSR0);
+	__raw_writel(0x3fffffff, INT2NTSR1);
+
+	/* unmask all known interrupts in INTCS2 */
+	__raw_writel(0xfffffff0, INT2SMSKCR0);
+	__raw_writel(0xfff7ffff, INT2SMSKCR1);
+	__raw_writel(0xfffbffdf, INT2SMSKCR2);
+	__raw_writel(0xbffffffc, INT2SMSKCR3);
+	__raw_writel(0x003fee3f, INT2SMSKCR4);
+}
+
 void __init r8a7779_init_delay(void)
 {
 	shmobile_setup_delay(1000, 2, 4); /* Cortex-A9 @ 1000MHz */
 }
 
-static const struct of_dev_auxdata r8a7779_auxdata_lookup[] __initconst = {
-	{},
-};
-
 void __init r8a7779_add_standard_devices_dt(void)
 {
 	/* clocks are setup late during boot in the case of DT */
@@ -676,8 +770,7 @@ void __init r8a7779_add_standard_devices_dt(void)
 
 	platform_add_devices(r8a7779_devices_dt,
 			     ARRAY_SIZE(r8a7779_devices_dt));
-	of_platform_populate(NULL, of_default_bus_match_table,
-			     r8a7779_auxdata_lookup, NULL);
+	of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
 }
 
 static const char *r8a7779_compat_dt[] __initdata = {
@@ -691,7 +784,6 @@ DT_MACHINE_START(R8A7779_DT, "Generic R8A7779 (Flattened Device Tree)")
 	.nr_irqs	= NR_IRQS_LEGACY,
 	.init_irq	= r8a7779_init_irq_dt,
 	.init_machine	= r8a7779_add_standard_devices_dt,
-	.init_time	= shmobile_timer_init,
 	.init_late	= r8a7779_init_late,
 	.dt_compat	= r8a7779_compat_dt,
 MACHINE_END
diff --git a/arch/arm/mach-shmobile/setup-r8a7790.c b/arch/arm/mach-shmobile/setup-r8a7790.c
index 28f94752b8ff..d0f5c9f9349a 100644
--- a/arch/arm/mach-shmobile/setup-r8a7790.c
+++ b/arch/arm/mach-shmobile/setup-r8a7790.c
@@ -18,13 +18,14 @@
  * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
  */
 
+#include <linux/clocksource.h>
 #include <linux/irq.h>
-#include <linux/irqchip.h>
 #include <linux/kernel.h>
 #include <linux/of_platform.h>
-#include <linux/serial_sci.h>
 #include <linux/platform_data/gpio-rcar.h>
 #include <linux/platform_data/irq-renesas-irqc.h>
+#include <linux/serial_sci.h>
+#include <linux/sh_timer.h>
 #include <mach/common.h>
 #include <mach/irqs.h>
 #include <mach/r8a7790.h>
@@ -149,7 +150,37 @@ static struct resource irqc0_resources[] __initdata = {
 					  &irqc##idx##_data,		\
 					  sizeof(struct renesas_irqc_config))
 
-void __init r8a7790_add_standard_devices(void)
+static struct resource thermal_resources[] __initdata = {
+	DEFINE_RES_MEM(0xe61f0000, 0x14),
+	DEFINE_RES_MEM(0xe61f0100, 0x38),
+	DEFINE_RES_IRQ(gic_spi(69)),
+};
+
+#define r8a7790_register_thermal()					\
+	platform_device_register_simple("rcar_thermal", -1,		\
+					thermal_resources,		\
+					ARRAY_SIZE(thermal_resources))
+
+static struct sh_timer_config cmt00_platform_data __initdata = {
+	.name = "CMT00",
+	.timer_bit = 0,
+	.clockevent_rating = 80,
+};
+
+static struct resource cmt00_resources[] __initdata = {
+	DEFINE_RES_MEM(0xffca0510, 0x0c),
+	DEFINE_RES_MEM(0xffca0500, 0x04),
+	DEFINE_RES_IRQ(gic_spi(142)), /* CMT0_0 */
+};
+
+#define r8a7790_register_cmt(idx)					\
+	platform_device_register_resndata(&platform_bus, "sh_cmt",	\
+					  idx, cmt##idx##_resources,	\
+					  ARRAY_SIZE(cmt##idx##_resources), \
+					  &cmt##idx##_platform_data,	\
+					  sizeof(struct sh_timer_config))
+
+void __init r8a7790_add_dt_devices(void)
 {
 	r8a7790_register_scif(SCIFA0);
 	r8a7790_register_scif(SCIFA1);
@@ -161,35 +192,97 @@ void __init r8a7790_add_standard_devices(void)
 	r8a7790_register_scif(SCIF1);
 	r8a7790_register_scif(HSCIF0);
 	r8a7790_register_scif(HSCIF1);
+	r8a7790_register_cmt(00);
+}
+
+void __init r8a7790_add_standard_devices(void)
+{
+	r8a7790_add_dt_devices();
 	r8a7790_register_irqc(0);
+	r8a7790_register_thermal();
 }
 
+#define MODEMR 0xe6160060
+
+u32 __init r8a7790_read_mode_pins(void)
+{
+	void __iomem *modemr = ioremap_nocache(MODEMR, 4);
+	u32 mode;
+
+	BUG_ON(!modemr);
+	mode = ioread32(modemr);
+	iounmap(modemr);
+
+	return mode;
+}
+
+#define CNTCR 0
+#define CNTFID0 0x20
+
 void __init r8a7790_timer_init(void)
 {
-	void __iomem *cntcr;
+#ifdef CONFIG_ARM_ARCH_TIMER
+	u32 mode = r8a7790_read_mode_pins();
+	void __iomem *base;
+	int extal_mhz = 0;
+	u32 freq;
+
+	/* At Linux boot time the r8a7790 arch timer comes up
+	 * with the counter disabled. Moreover, it may also report
+	 * a potentially incorrect fixed 13 MHz frequency. To be
+	 * correct these registers need to be updated to use the
+	 * frequency EXTAL / 2 which can be determined by the MD pins.
+	 */
 
-	/* make sure arch timer is started by setting bit 0 of CNTCT */
-	cntcr = ioremap(0xe6080000, PAGE_SIZE);
-	iowrite32(1, cntcr);
-	iounmap(cntcr);
+	switch (mode & (MD(14) | MD(13))) {
+	case 0:
+		extal_mhz = 15;
+		break;
+	case MD(13):
+		extal_mhz = 20;
+		break;
+	case MD(14):
+		extal_mhz = 26;
+		break;
+	case MD(13) | MD(14):
+		extal_mhz = 30;
+		break;
+	}
 
-	shmobile_timer_init();
+	/* The arch timer frequency equals EXTAL / 2 */
+	freq = extal_mhz * (1000000 / 2);
+
+	/* Remap "armgcnt address map" space */
+	base = ioremap(0xe6080000, PAGE_SIZE);
+
+	/* Update registers with correct frequency */
+	iowrite32(freq, base + CNTFID0);
+	asm volatile("mcr p15, 0, %0, c14, c0, 0" : : "r" (freq));
+
+	/* make sure arch timer is started by setting bit 0 of CNTCR */
+	iowrite32(1, base + CNTCR);
+	iounmap(base);
+#endif /* CONFIG_ARM_ARCH_TIMER */
+
+	clocksource_of_init();
 }
 
-#ifdef CONFIG_USE_OF
-void __init r8a7790_add_standard_devices_dt(void)
+void __init r8a7790_init_delay(void)
 {
-	of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
+#ifndef CONFIG_ARM_ARCH_TIMER
+	shmobile_setup_delay(1300, 2, 4); /* Cortex-A15 @ 1300MHz */
+#endif
 }
 
+#ifdef CONFIG_USE_OF
+
 static const char *r8a7790_boards_compat_dt[] __initdata = {
 	"renesas,r8a7790",
 	NULL,
 };
 
 DT_MACHINE_START(R8A7790_DT, "Generic R8A7790 (Flattened Device Tree)")
-	.init_irq	= irqchip_init,
-	.init_machine	= r8a7790_add_standard_devices_dt,
+	.init_early	= r8a7790_init_delay,
 	.init_time	= r8a7790_timer_init,
 	.dt_compat	= r8a7790_boards_compat_dt,
 MACHINE_END
diff --git a/arch/arm/mach-shmobile/setup-sh7372.c b/arch/arm/mach-shmobile/setup-sh7372.c
index 5502d624aca6..311878391e18 100644
--- a/arch/arm/mach-shmobile/setup-sh7372.c
+++ b/arch/arm/mach-shmobile/setup-sh7372.c
@@ -35,7 +35,6 @@
 #include <linux/dma-mapping.h>
 #include <linux/platform_data/sh_ipmmu.h>
 #include <mach/dma-register.h>
-#include <mach/hardware.h>
 #include <mach/irqs.h>
 #include <mach/sh7372.h>
 #include <mach/common.h>
@@ -1147,10 +1146,6 @@ void __init sh7372_add_early_devices_dt(void)
 	shmobile_setup_console();
 }
 
-static const struct of_dev_auxdata sh7372_auxdata_lookup[] __initconst = {
-	{ }
-};
-
 void __init sh7372_add_standard_devices_dt(void)
 {
 	/* clocks are setup late during boot in the case of DT */
@@ -1159,8 +1154,7 @@ void __init sh7372_add_standard_devices_dt(void)
 	platform_add_devices(sh7372_early_devices,
 			    ARRAY_SIZE(sh7372_early_devices));
 
-	of_platform_populate(NULL, of_default_bus_match_table,
-			     sh7372_auxdata_lookup, NULL);
+	of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
 }
 
 static const char *sh7372_boards_compat_dt[] __initdata = {
diff --git a/arch/arm/mach-shmobile/setup-sh73a0.c b/arch/arm/mach-shmobile/setup-sh73a0.c
index 96e7ca1e4e11..22de17417fd7 100644
--- a/arch/arm/mach-shmobile/setup-sh73a0.c
+++ b/arch/arm/mach-shmobile/setup-sh73a0.c
@@ -22,7 +22,6 @@
 #include <linux/init.h>
 #include <linux/interrupt.h>
 #include <linux/irq.h>
-#include <linux/irqchip.h>
 #include <linux/platform_device.h>
 #include <linux/of_platform.h>
 #include <linux/delay.h>
@@ -35,7 +34,6 @@
 #include <linux/platform_data/sh_ipmmu.h>
 #include <linux/platform_data/irq-renesas-intc-irqpin.h>
 #include <mach/dma-register.h>
-#include <mach/hardware.h>
 #include <mach/irqs.h>
 #include <mach/sh73a0.h>
 #include <mach/common.h>
@@ -61,29 +59,16 @@ void __init sh73a0_map_io(void)
 	iotable_init(sh73a0_io_desc, ARRAY_SIZE(sh73a0_io_desc));
 }
 
-static struct resource sh73a0_pfc_resources[] = {
-	[0] = {
-		.start	= 0xe6050000,
-		.end	= 0xe6057fff,
-		.flags	= IORESOURCE_MEM,
-	},
-	[1] = {
-		.start	= 0xe605801c,
-		.end	= 0xe6058027,
-		.flags	= IORESOURCE_MEM,
-	}
-};
-
-static struct platform_device sh73a0_pfc_device = {
-	.name		= "pfc-sh73a0",
-	.id		= -1,
-	.resource	= sh73a0_pfc_resources,
-	.num_resources	= ARRAY_SIZE(sh73a0_pfc_resources),
+/* PFC */
+static struct resource pfc_resources[] __initdata = {
+	DEFINE_RES_MEM(0xe6050000, 0x8000),
+	DEFINE_RES_MEM(0xe605801c, 0x000c),
 };
 
 void __init sh73a0_pinmux_init(void)
 {
-	platform_device_register(&sh73a0_pfc_device);
+	platform_device_register_simple("pfc-sh73a0", -1, pfc_resources,
+					ARRAY_SIZE(pfc_resources));
 }
 
 static struct plat_sci_port scif0_platform_data = {
@@ -958,10 +943,6 @@ void __init sh73a0_add_early_devices(void)
 
 #ifdef CONFIG_USE_OF
 
-static const struct of_dev_auxdata sh73a0_auxdata_lookup[] __initconst = {
-	{},
-};
-
 void __init sh73a0_add_standard_devices_dt(void)
 {
 	struct platform_device_info devinfo = { .name = "cpufreq-cpu0", .id = -1, };
@@ -971,8 +952,7 @@ void __init sh73a0_add_standard_devices_dt(void)
 
 	platform_add_devices(sh73a0_devices_dt,
 			     ARRAY_SIZE(sh73a0_devices_dt));
-	of_platform_populate(NULL, of_default_bus_match_table,
-			     sh73a0_auxdata_lookup, NULL);
+	of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
 
 	/* Instantiate cpufreq-cpu0 */
 	platform_device_register_full(&devinfo);
@@ -988,7 +968,6 @@ DT_MACHINE_START(SH73A0_DT, "Generic SH73A0 (Flattened Device Tree)")
 	.map_io		= sh73a0_map_io,
 	.init_early	= sh73a0_init_delay,
 	.nr_irqs	= NR_IRQS_LEGACY,
-	.init_irq	= irqchip_init,
 	.init_machine	= sh73a0_add_standard_devices_dt,
 	.dt_compat	= sh73a0_boards_compat_dt,
 MACHINE_END
diff --git a/arch/arm/mach-shmobile/sleep-sh7372.S b/arch/arm/mach-shmobile/sleep-sh7372.S
index 53f4840e4949..9782862899e8 100644
--- a/arch/arm/mach-shmobile/sleep-sh7372.S
+++ b/arch/arm/mach-shmobile/sleep-sh7372.S
@@ -41,6 +41,7 @@
 sh7372_resume_core_standby_sysc:
 	ldr     pc, 1f
 
+	.align	2
 	.globl	sh7372_cpu_resume
 sh7372_cpu_resume:
 1:	.space	4
@@ -96,6 +97,7 @@ sh7372_do_idle_sysc:
 1:
 	b      1b
 
+	.align	2
 kernel_flush:
 	.word v7_flush_dcache_all
 #endif
diff --git a/arch/arm/mach-shmobile/smp-emev2.c b/arch/arm/mach-shmobile/smp-emev2.c
index 22a05a869d25..522de5ebb55f 100644
--- a/arch/arm/mach-shmobile/smp-emev2.c
+++ b/arch/arm/mach-shmobile/smp-emev2.c
@@ -29,41 +29,38 @@
 #include <asm/smp_scu.h>
 
 #define EMEV2_SCU_BASE 0x1e000000
+#define EMEV2_SMU_BASE 0xe0110000
+#define SMU_GENERAL_REG0 0x7c0
 
 static int emev2_boot_secondary(unsigned int cpu, struct task_struct *idle)
 {
+	int ret;
+
+	ret = shmobile_smp_scu_boot_secondary(cpu, idle);
+	if (ret)
+		return ret;
+
 	arch_send_wakeup_ipi_mask(cpumask_of(cpu_logical_map(cpu)));
 	return 0;
 }
 
 static void __init emev2_smp_prepare_cpus(unsigned int max_cpus)
 {
-	scu_enable(shmobile_scu_base);
-
-	/* Tell ROM loader about our vector (in headsmp-scu.S, headsmp.S) */
-	emev2_set_boot_vector(__pa(shmobile_boot_vector));
-	shmobile_boot_fn = virt_to_phys(shmobile_boot_scu);
-	shmobile_boot_arg = (unsigned long)shmobile_scu_base;
-
-	/* enable cache coherency on booting CPU */
-	scu_power_mode(shmobile_scu_base, SCU_PM_NORMAL);
-}
+	void __iomem *smu;
 
-static void __init emev2_smp_init_cpus(void)
-{
-	unsigned int ncores;
+	/* Tell ROM loader about our vector (in headsmp.S) */
+	smu = ioremap(EMEV2_SMU_BASE, PAGE_SIZE);
+	if (smu) {
+		iowrite32(__pa(shmobile_boot_vector), smu + SMU_GENERAL_REG0);
+		iounmap(smu);
+	}
 
-	/* setup EMEV2 specific SCU base */
+	/* setup EMEV2 specific SCU bits */
 	shmobile_scu_base = ioremap(EMEV2_SCU_BASE, PAGE_SIZE);
-	emev2_clock_init(); /* need ioremapped SMU */
-
-	ncores = shmobile_scu_base ? scu_get_core_count(shmobile_scu_base) : 1;
-
-	shmobile_smp_init_cpus(ncores);
+	shmobile_smp_scu_prepare_cpus(max_cpus);
 }
 
 struct smp_operations emev2_smp_ops __initdata = {
-	.smp_init_cpus		= emev2_smp_init_cpus,
 	.smp_prepare_cpus	= emev2_smp_prepare_cpus,
 	.smp_boot_secondary	= emev2_boot_secondary,
 };
diff --git a/arch/arm/mach-shmobile/smp-r8a7779.c b/arch/arm/mach-shmobile/smp-r8a7779.c
index 9bdf810f2a87..0f05e9fb722f 100644
--- a/arch/arm/mach-shmobile/smp-r8a7779.c
+++ b/arch/arm/mach-shmobile/smp-r8a7779.c
@@ -84,30 +84,34 @@ static int r8a7779_platform_cpu_kill(unsigned int cpu)
 static int r8a7779_boot_secondary(unsigned int cpu, struct task_struct *idle)
 {
 	struct r8a7779_pm_ch *ch = NULL;
-	int ret = -EIO;
+	unsigned int lcpu = cpu_logical_map(cpu);
+	int ret;
 
-	cpu = cpu_logical_map(cpu);
+	ret = shmobile_smp_scu_boot_secondary(cpu, idle);
+	if (ret)
+		return ret;
 
-	if (cpu < ARRAY_SIZE(r8a7779_ch_cpu))
-		ch = r8a7779_ch_cpu[cpu];
+	if (lcpu < ARRAY_SIZE(r8a7779_ch_cpu))
+		ch = r8a7779_ch_cpu[lcpu];
 
 	if (ch)
 		ret = r8a7779_sysc_power_up(ch);
+	else
+		ret = -EIO;
 
 	return ret;
 }
 
 static void __init r8a7779_smp_prepare_cpus(unsigned int max_cpus)
 {
-	scu_enable(shmobile_scu_base);
-
 	/* Map the reset vector (in headsmp-scu.S, headsmp.S) */
 	__raw_writel(__pa(shmobile_boot_vector), AVECR);
 	shmobile_boot_fn = virt_to_phys(shmobile_boot_scu);
 	shmobile_boot_arg = (unsigned long)shmobile_scu_base;
 
-	/* enable cache coherency on booting CPU */
-	scu_power_mode(shmobile_scu_base, SCU_PM_NORMAL);
+	/* setup r8a7779 specific SCU bits */
+	shmobile_scu_base = IOMEM(R8A7779_SCU_BASE);
+	shmobile_smp_scu_prepare_cpus(max_cpus);
 
 	r8a7779_pm_init();
 
@@ -117,56 +121,15 @@ static void __init r8a7779_smp_prepare_cpus(unsigned int max_cpus)
 	r8a7779_platform_cpu_kill(3);
 }
 
-static void __init r8a7779_smp_init_cpus(void)
-{
-	/* setup r8a7779 specific SCU base */
-	shmobile_scu_base = IOMEM(R8A7779_SCU_BASE);
-
-	shmobile_smp_init_cpus(scu_get_core_count(shmobile_scu_base));
-}
-
 #ifdef CONFIG_HOTPLUG_CPU
-static int r8a7779_scu_psr_core_disabled(int cpu)
-{
-	unsigned long mask = 3 << (cpu * 8);
-
-	if ((__raw_readl(shmobile_scu_base + 8) & mask) == mask)
-		return 1;
-
-	return 0;
-}
-
 static int r8a7779_cpu_kill(unsigned int cpu)
 {
-	int k;
-
-	/* this function is running on another CPU than the offline target,
-	 * here we need wait for shutdown code in platform_cpu_die() to
-	 * finish before asking SoC-specific code to power off the CPU core.
-	 */
-	for (k = 0; k < 1000; k++) {
-		if (r8a7779_scu_psr_core_disabled(cpu))
-			return r8a7779_platform_cpu_kill(cpu);
-
-		mdelay(1);
-	}
+	if (shmobile_smp_scu_cpu_kill(cpu))
+		return r8a7779_platform_cpu_kill(cpu);
 
 	return 0;
 }
 
-static void r8a7779_cpu_die(unsigned int cpu)
-{
-	dsb();
-	flush_cache_all();
-
-	/* disable cache coherency */
-	scu_power_mode(shmobile_scu_base, SCU_PM_POWEROFF);
-
-	/* Endless loop until power off from r8a7779_cpu_kill() */
-	while (1)
-		cpu_do_idle();
-}
-
 static int r8a7779_cpu_disable(unsigned int cpu)
 {
 	/* only CPU1->3 have power domains, do not allow hotplug of CPU0 */
@@ -175,12 +138,11 @@ static int r8a7779_cpu_disable(unsigned int cpu)
 #endif /* CONFIG_HOTPLUG_CPU */
 
 struct smp_operations r8a7779_smp_ops  __initdata = {
-	.smp_init_cpus		= r8a7779_smp_init_cpus,
 	.smp_prepare_cpus	= r8a7779_smp_prepare_cpus,
 	.smp_boot_secondary	= r8a7779_boot_secondary,
 #ifdef CONFIG_HOTPLUG_CPU
-	.cpu_kill		= r8a7779_cpu_kill,
-	.cpu_die		= r8a7779_cpu_die,
 	.cpu_disable		= r8a7779_cpu_disable,
+	.cpu_die		= shmobile_smp_scu_cpu_die,
+	.cpu_kill		= r8a7779_cpu_kill,
 #endif
 };
diff --git a/arch/arm/mach-shmobile/smp-sh73a0.c b/arch/arm/mach-shmobile/smp-sh73a0.c
index d5fc3ed4e315..0baa24443793 100644
--- a/arch/arm/mach-shmobile/smp-sh73a0.c
+++ b/arch/arm/mach-shmobile/smp-sh73a0.c
@@ -20,14 +20,11 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/smp.h>
-#include <linux/spinlock.h>
 #include <linux/io.h>
 #include <linux/delay.h>
 #include <mach/common.h>
-#include <asm/cacheflush.h>
-#include <asm/smp_plat.h>
 #include <mach/sh73a0.h>
-#include <asm/smp_scu.h>
+#include <asm/smp_plat.h>
 #include <asm/smp_twd.h>
 
 #define WUPCR		IOMEM(0xe6151010)
@@ -36,8 +33,6 @@
 #define SBAR		IOMEM(0xe6180020)
 #define APARMBAREA	IOMEM(0xe6f10020)
 
-#define PSTR_SHUTDOWN_MODE	3
-
 #define SH73A0_SCU_BASE 0xf0000000
 
 #ifdef CONFIG_HAVE_ARM_TWD
@@ -50,69 +45,33 @@ void __init sh73a0_register_twd(void)
 
 static int sh73a0_boot_secondary(unsigned int cpu, struct task_struct *idle)
 {
-	cpu = cpu_logical_map(cpu);
+	unsigned int lcpu = cpu_logical_map(cpu);
+	int ret;
 
-	if (((__raw_readl(PSTR) >> (4 * cpu)) & 3) == 3)
-		__raw_writel(1 << cpu, WUPCR);	/* wake up */
+	ret = shmobile_smp_scu_boot_secondary(cpu, idle);
+	if (ret)
+		return ret;
+
+	if (((__raw_readl(PSTR) >> (4 * lcpu)) & 3) == 3)
+		__raw_writel(1 << lcpu, WUPCR);	/* wake up */
 	else
-		__raw_writel(1 << cpu, SRESCR);	/* reset */
+		__raw_writel(1 << lcpu, SRESCR);	/* reset */
 
 	return 0;
 }
 
 static void __init sh73a0_smp_prepare_cpus(unsigned int max_cpus)
 {
-	scu_enable(shmobile_scu_base);
-
-	/* Map the reset vector (in headsmp-scu.S, headsmp.S) */
+	/* Map the reset vector (in headsmp.S) */
 	__raw_writel(0, APARMBAREA);      /* 4k */
 	__raw_writel(__pa(shmobile_boot_vector), SBAR);
-	shmobile_boot_fn = virt_to_phys(shmobile_boot_scu);
-	shmobile_boot_arg = (unsigned long)shmobile_scu_base;
 
-	/* enable cache coherency on booting CPU */
-	scu_power_mode(shmobile_scu_base, SCU_PM_NORMAL);
-}
-
-static void __init sh73a0_smp_init_cpus(void)
-{
-	/* setup sh73a0 specific SCU base */
+	/* setup sh73a0 specific SCU bits */
 	shmobile_scu_base = IOMEM(SH73A0_SCU_BASE);
-
-	shmobile_smp_init_cpus(scu_get_core_count(shmobile_scu_base));
+	shmobile_smp_scu_prepare_cpus(max_cpus);
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
-static int sh73a0_cpu_kill(unsigned int cpu)
-{
-
-	int k;
-	u32 pstr;
-
-	/*
-	 * wait until the power status register confirms the shutdown of the
-	 * offline target
-	 */
-	for (k = 0; k < 1000; k++) {
-		pstr = (__raw_readl(PSTR) >> (4 * cpu)) & 3;
-		if (pstr == PSTR_SHUTDOWN_MODE)
-			return 1;
-
-		mdelay(1);
-	}
-
-	return 0;
-}
-
-static void sh73a0_cpu_die(unsigned int cpu)
-{
-	/* Set power off mode. This takes the CPU out of the MP cluster */
-	scu_power_mode(shmobile_scu_base, SCU_PM_POWEROFF);
-
-	/* Enter shutdown mode */
-	cpu_do_idle();
-}
-
 static int sh73a0_cpu_disable(unsigned int cpu)
 {
 	return 0; /* CPU0 and CPU1 supported */
@@ -120,12 +79,11 @@ static int sh73a0_cpu_disable(unsigned int cpu)
 #endif /* CONFIG_HOTPLUG_CPU */
 
 struct smp_operations sh73a0_smp_ops __initdata = {
-	.smp_init_cpus		= sh73a0_smp_init_cpus,
 	.smp_prepare_cpus	= sh73a0_smp_prepare_cpus,
 	.smp_boot_secondary	= sh73a0_boot_secondary,
 #ifdef CONFIG_HOTPLUG_CPU
-	.cpu_kill		= sh73a0_cpu_kill,
-	.cpu_die		= sh73a0_cpu_die,
 	.cpu_disable		= sh73a0_cpu_disable,
+	.cpu_die		= shmobile_smp_scu_cpu_die,
+	.cpu_kill		= shmobile_smp_scu_cpu_kill,
 #endif
 };
diff --git a/arch/arm/mach-shmobile/timer.c b/arch/arm/mach-shmobile/timer.c
index f321dbeb2379..62d7052d6f21 100644
--- a/arch/arm/mach-shmobile/timer.c
+++ b/arch/arm/mach-shmobile/timer.c
@@ -59,7 +59,3 @@ void __init shmobile_earlytimer_init(void)
 	late_time_init = shmobile_late_time_init;
 }
 
-void __init shmobile_timer_init(void)
-{
-	clocksource_of_init();
-}
diff --git a/arch/arm/mach-spear/Kconfig b/arch/arm/mach-spear/Kconfig
index 442917eedff3..df0d59afeb40 100644
--- a/arch/arm/mach-spear/Kconfig
+++ b/arch/arm/mach-spear/Kconfig
@@ -23,7 +23,7 @@ config ARCH_SPEAR13XX
 	select CPU_V7
 	select GPIO_SPEAR_SPICS
 	select HAVE_ARM_SCU if SMP
-	select HAVE_ARM_TWD if LOCAL_TIMERS
+	select HAVE_ARM_TWD if SMP
 	select HAVE_SMP
 	select MIGHT_HAVE_CACHE_L2X0
 	select PINCTRL
diff --git a/arch/arm/mach-spear/include/mach/debug-macro.S b/arch/arm/mach-spear/include/mach/debug-macro.S
deleted file mode 100644
index 75b05ad0fbad..000000000000
--- a/arch/arm/mach-spear/include/mach/debug-macro.S
+++ /dev/null
@@ -1,36 +0,0 @@
-/*
- * arch/arm/plat-spear/include/plat/debug-macro.S
- *
- * Debugging macro include header for spear platform
- *
- * Copyright (C) 2009 ST Microelectronics
- * Viresh Kumar <viresh.linux@gmail.com>
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2. This program is licensed "as is" without any
- * warranty of any kind, whether express or implied.
- */
-
-#include <linux/amba/serial.h>
-#include <mach/spear.h>
-
-		.macro	addruart, rp, rv, tmp
-		mov	\rp, #SPEAR_DBG_UART_BASE		@ Physical base
-		mov	\rv, #VA_SPEAR_DBG_UART_BASE		@ Virtual base
-		.endm
-
-		.macro	senduart, rd, rx
-		strb	\rd, [\rx, #UART01x_DR]			@ ASC_TX_BUFFER
-		.endm
-
-		.macro	waituart, rd, rx
-1001:		ldr	\rd, [\rx, #UART01x_FR]			@ FLAG REGISTER
-		tst	\rd, #UART01x_FR_TXFF			@ TX_FULL
-		bne	1001b
-		.endm
-
-		.macro	busyuart, rd, rx
-1002:		ldr	\rd, [\rx, #UART01x_FR]			@ FLAG REGISTER
-		tst	\rd, #UART011_FR_TXFE			@ TX_EMPTY
-		beq	1002b
-		.endm
diff --git a/arch/arm/mach-spear/include/mach/spear.h b/arch/arm/mach-spear/include/mach/spear.h
index cf3a5369eeca..5cdc53d9b653 100644
--- a/arch/arm/mach-spear/include/mach/spear.h
+++ b/arch/arm/mach-spear/include/mach/spear.h
@@ -39,7 +39,6 @@
 
 /* Debug uart for linux, will be used for debug and uncompress messages */
 #define SPEAR_DBG_UART_BASE		SPEAR_ICM1_UART_BASE
-#define VA_SPEAR_DBG_UART_BASE		VA_SPEAR_ICM1_UART_BASE
 
 /* Sysctl base for spear platform */
 #define SPEAR_SYS_CTRL_BASE		SPEAR_ICM3_SYS_CTRL_BASE
@@ -86,7 +85,6 @@
 
 /* Debug uart for linux, will be used for debug and uncompress messages */
 #define SPEAR_DBG_UART_BASE			UART_BASE
-#define VA_SPEAR_DBG_UART_BASE			VA_UART_BASE
 
 #endif /* SPEAR13XX */
 
diff --git a/arch/arm/mach-sunxi/Kconfig b/arch/arm/mach-sunxi/Kconfig
index 5b045e302b43..3ab2f65f8a50 100644
--- a/arch/arm/mach-sunxi/Kconfig
+++ b/arch/arm/mach-sunxi/Kconfig
@@ -10,3 +10,5 @@ config ARCH_SUNXI
 	select SPARSE_IRQ
 	select SUN4I_TIMER
 	select PINCTRL_SUNXI
+	select ARM_GIC
+	select HAVE_SMP
diff --git a/arch/arm/mach-sunxi/Makefile.boot b/arch/arm/mach-sunxi/Makefile.boot
deleted file mode 100644
index 46d4cf0841c0..000000000000
--- a/arch/arm/mach-sunxi/Makefile.boot
+++ /dev/null
@@ -1 +0,0 @@
-zreladdr-$(CONFIG_ARCH_SUNXI)	+= 0x40008000
diff --git a/arch/arm/mach-sunxi/sunxi.c b/arch/arm/mach-sunxi/sunxi.c
index 38a3c55527c8..e79fb3469341 100644
--- a/arch/arm/mach-sunxi/sunxi.c
+++ b/arch/arm/mach-sunxi/sunxi.c
@@ -27,10 +27,19 @@
 #include <asm/system_misc.h>
 
 #define SUN4I_WATCHDOG_CTRL_REG		0x00
-#define SUN4I_WATCHDOG_CTRL_RESTART		(1 << 0)
+#define SUN4I_WATCHDOG_CTRL_RESTART		BIT(0)
 #define SUN4I_WATCHDOG_MODE_REG		0x04
-#define SUN4I_WATCHDOG_MODE_ENABLE		(1 << 0)
-#define SUN4I_WATCHDOG_MODE_RESET_ENABLE	(1 << 1)
+#define SUN4I_WATCHDOG_MODE_ENABLE		BIT(0)
+#define SUN4I_WATCHDOG_MODE_RESET_ENABLE	BIT(1)
+
+#define SUN6I_WATCHDOG1_IRQ_REG		0x00
+#define SUN6I_WATCHDOG1_CTRL_REG	0x10
+#define SUN6I_WATCHDOG1_CTRL_RESTART		BIT(0)
+#define SUN6I_WATCHDOG1_CONFIG_REG	0x14
+#define SUN6I_WATCHDOG1_CONFIG_RESTART		BIT(0)
+#define SUN6I_WATCHDOG1_CONFIG_IRQ		BIT(1)
+#define SUN6I_WATCHDOG1_MODE_REG	0x18
+#define SUN6I_WATCHDOG1_MODE_ENABLE		BIT(0)
 
 static void __iomem *wdt_base;
 
@@ -56,8 +65,36 @@ static void sun4i_restart(enum reboot_mode mode, const char *cmd)
 	}
 }
 
+static void sun6i_restart(enum reboot_mode mode, const char *cmd)
+{
+	if (!wdt_base)
+		return;
+
+	/* Disable interrupts */
+	writel(0, wdt_base + SUN6I_WATCHDOG1_IRQ_REG);
+
+	/* We want to disable the IRQ and just reset the whole system */
+	writel(SUN6I_WATCHDOG1_CONFIG_RESTART,
+		wdt_base + SUN6I_WATCHDOG1_CONFIG_REG);
+
+	/* Enable timer. The default and lowest interval value is 0.5s */
+	writel(SUN6I_WATCHDOG1_MODE_ENABLE,
+		wdt_base + SUN6I_WATCHDOG1_MODE_REG);
+
+	/* Restart the watchdog. */
+	writel(SUN6I_WATCHDOG1_CTRL_RESTART,
+		wdt_base + SUN6I_WATCHDOG1_CTRL_REG);
+
+	while (1) {
+		mdelay(5);
+		writel(SUN6I_WATCHDOG1_MODE_ENABLE,
+			wdt_base + SUN6I_WATCHDOG1_MODE_REG);
+	}
+}
+
 static struct of_device_id sunxi_restart_ids[] = {
 	{ .compatible = "allwinner,sun4i-wdt", .data = sun4i_restart },
+	{ .compatible = "allwinner,sun6i-wdt", .data = sun6i_restart },
 	{ /*sentinel*/ }
 };
 
@@ -96,6 +133,8 @@ static const char * const sunxi_board_dt_compat[] = {
 	"allwinner,sun4i-a10",
 	"allwinner,sun5i-a10s",
 	"allwinner,sun5i-a13",
+	"allwinner,sun6i-a31",
+	"allwinner,sun7i-a20",
 	NULL,
 };
 
diff --git a/arch/arm/mach-tegra/Kconfig b/arch/arm/mach-tegra/Kconfig
index ef3a8da49b2d..67a76f2dfb9f 100644
--- a/arch/arm/mach-tegra/Kconfig
+++ b/arch/arm/mach-tegra/Kconfig
@@ -2,18 +2,25 @@ config ARCH_TEGRA
 	bool "NVIDIA Tegra" if ARCH_MULTI_V7
 	select ARCH_HAS_CPUFREQ
 	select ARCH_REQUIRE_GPIOLIB
+	select ARM_GIC
 	select CLKDEV_LOOKUP
 	select CLKSRC_MMIO
 	select CLKSRC_OF
 	select COMMON_CLK
+	select CPU_V7
 	select GENERIC_CLOCKEVENTS
 	select HAVE_ARM_SCU if SMP
-	select HAVE_ARM_TWD if LOCAL_TIMERS
+	select HAVE_ARM_TWD if SMP
 	select HAVE_CLK
 	select HAVE_SMP
 	select MIGHT_HAVE_CACHE_L2X0
+	select MIGHT_HAVE_PCI
+	select PINCTRL
 	select SOC_BUS
 	select SPARSE_IRQ
+	select USB_ARCH_HAS_EHCI if USB_SUPPORT
+	select USB_ULPI if USB_PHY
+	select USB_ULPI_VIEWPORT if USB_PHY
 	select USE_OF
 	help
 	  This enables support for NVIDIA Tegra based systems.
@@ -27,15 +34,9 @@ config ARCH_TEGRA_2x_SOC
 	select ARM_ERRATA_720789
 	select ARM_ERRATA_754327 if SMP
 	select ARM_ERRATA_764369 if SMP
-	select ARM_GIC
-	select CPU_V7
-	select PINCTRL
 	select PINCTRL_TEGRA20
 	select PL310_ERRATA_727915 if CACHE_L2X0
 	select PL310_ERRATA_769419 if CACHE_L2X0
-	select USB_ARCH_HAS_EHCI if USB_SUPPORT
-	select USB_ULPI if USB_PHY
-	select USB_ULPI_VIEWPORT if USB_PHY
 	help
 	  Support for NVIDIA Tegra AP20 and T20 processors, based on the
 	  ARM CortexA9MP CPU and the ARM PL310 L2 cache controller
@@ -44,14 +45,8 @@ config ARCH_TEGRA_3x_SOC
 	bool "Enable support for Tegra30 family"
 	select ARM_ERRATA_754322
 	select ARM_ERRATA_764369 if SMP
-	select ARM_GIC
-	select CPU_V7
-	select PINCTRL
 	select PINCTRL_TEGRA30
 	select PL310_ERRATA_769419 if CACHE_L2X0
-	select USB_ARCH_HAS_EHCI if USB_SUPPORT
-	select USB_ULPI if USB_PHY
-	select USB_ULPI_VIEWPORT if USB_PHY
 	help
 	  Support for NVIDIA Tegra T30 processor family, based on the
 	  ARM CortexA9MP CPU and the ARM PL310 L2 cache controller
@@ -59,20 +54,13 @@ config ARCH_TEGRA_3x_SOC
 config ARCH_TEGRA_114_SOC
 	bool "Enable support for Tegra114 family"
 	select HAVE_ARM_ARCH_TIMER
-	select ARM_GIC
+	select ARM_ERRATA_798181
 	select ARM_L1_CACHE_SHIFT_6
-	select CPU_V7
-	select PINCTRL
 	select PINCTRL_TEGRA114
 	help
 	  Support for NVIDIA Tegra T114 processor family, based on the
 	  ARM CortexA15MP CPU
 
-config TEGRA_PCI
-	bool "PCI Express support"
-	depends on ARCH_TEGRA_2x_SOC
-	select PCI
-
 config TEGRA_AHB
 	bool "Enable AHB driver for NVIDIA Tegra SoCs"
 	default y
diff --git a/arch/arm/mach-tegra/Makefile b/arch/arm/mach-tegra/Makefile
index 98b184efc110..e7e5f45c6558 100644
--- a/arch/arm/mach-tegra/Makefile
+++ b/arch/arm/mach-tegra/Makefile
@@ -17,24 +17,24 @@ obj-$(CONFIG_CPU_IDLE)			+= cpuidle.o
 obj-$(CONFIG_ARCH_TEGRA_2x_SOC)		+= tegra20_speedo.o
 obj-$(CONFIG_ARCH_TEGRA_2x_SOC)		+= tegra2_emc.o
 obj-$(CONFIG_ARCH_TEGRA_2x_SOC)		+= sleep-tegra20.o
+obj-$(CONFIG_ARCH_TEGRA_2x_SOC)		+= pm-tegra20.o
 ifeq ($(CONFIG_CPU_IDLE),y)
 obj-$(CONFIG_ARCH_TEGRA_2x_SOC)		+= cpuidle-tegra20.o
 endif
 obj-$(CONFIG_ARCH_TEGRA_3x_SOC)		+= tegra30_speedo.o
 obj-$(CONFIG_ARCH_TEGRA_3x_SOC)		+= sleep-tegra30.o
+obj-$(CONFIG_ARCH_TEGRA_3x_SOC)		+= pm-tegra30.o
 ifeq ($(CONFIG_CPU_IDLE),y)
 obj-$(CONFIG_ARCH_TEGRA_3x_SOC)		+= cpuidle-tegra30.o
 endif
 obj-$(CONFIG_SMP)			+= platsmp.o headsmp.o
 obj-$(CONFIG_HOTPLUG_CPU)               += hotplug.o
-obj-$(CONFIG_TEGRA_PCI)			+= pcie.o
 
 obj-$(CONFIG_ARCH_TEGRA_114_SOC)	+= tegra114_speedo.o
 obj-$(CONFIG_ARCH_TEGRA_114_SOC)	+= sleep-tegra30.o
+obj-$(CONFIG_ARCH_TEGRA_114_SOC)	+= pm-tegra30.o
 ifeq ($(CONFIG_CPU_IDLE),y)
 obj-$(CONFIG_ARCH_TEGRA_114_SOC)	+= cpuidle-tegra114.o
 endif
 
-obj-$(CONFIG_ARCH_TEGRA_2x_SOC)		+= board-harmony-pcie.o
-
 obj-$(CONFIG_ARCH_TEGRA_2x_SOC)		+= board-paz00.o
diff --git a/arch/arm/mach-tegra/board-harmony-pcie.c b/arch/arm/mach-tegra/board-harmony-pcie.c
deleted file mode 100644
index 035b240b9e15..000000000000
--- a/arch/arm/mach-tegra/board-harmony-pcie.c
+++ /dev/null
@@ -1,89 +0,0 @@
-/*
- * arch/arm/mach-tegra/board-harmony-pcie.c
- *
- * Copyright (C) 2010 CompuLab, Ltd.
- * Mike Rapoport <mike@compulab.co.il>
- *
- * This software is licensed under the terms of the GNU General Public
- * License version 2, as published by the Free Software Foundation, and
- * may be copied, distributed, and modified under those terms.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- */
-
-#include <linux/kernel.h>
-#include <linux/gpio.h>
-#include <linux/err.h>
-#include <linux/of_gpio.h>
-#include <linux/regulator/consumer.h>
-
-#include <asm/mach-types.h>
-
-#include "board.h"
-
-#ifdef CONFIG_TEGRA_PCI
-
-int __init harmony_pcie_init(void)
-{
-	struct device_node *np;
-	int en_vdd_1v05;
-	struct regulator *regulator = NULL;
-	int err;
-
-	np = of_find_node_by_path("/regulators/regulator@3");
-	if (!np) {
-		pr_err("%s: of_find_node_by_path failed\n", __func__);
-		return -ENODEV;
-	}
-
-	en_vdd_1v05 = of_get_named_gpio(np, "gpio", 0);
-	if (en_vdd_1v05 < 0) {
-		pr_err("%s: of_get_named_gpio failed: %d\n", __func__,
-		       en_vdd_1v05);
-		return en_vdd_1v05;
-	}
-
-	err = gpio_request(en_vdd_1v05, "EN_VDD_1V05");
-	if (err) {
-		pr_err("%s: gpio_request failed: %d\n", __func__, err);
-		return err;
-	}
-
-	gpio_direction_output(en_vdd_1v05, 1);
-
-	regulator = regulator_get(NULL, "vdd_ldo0,vddio_pex_clk");
-	if (IS_ERR(regulator)) {
-		err = PTR_ERR(regulator);
-		pr_err("%s: regulator_get failed: %d\n", __func__, err);
-		goto err_reg;
-	}
-
-	err = regulator_enable(regulator);
-	if (err) {
-		pr_err("%s: regulator_enable failed: %d\n", __func__, err);
-		goto err_en;
-	}
-
-	err = tegra_pcie_init(true, true);
-	if (err) {
-		pr_err("%s: tegra_pcie_init failed: %d\n", __func__, err);
-		goto err_pcie;
-	}
-
-	return 0;
-
-err_pcie:
-	regulator_disable(regulator);
-err_en:
-	regulator_put(regulator);
-err_reg:
-	gpio_free(en_vdd_1v05);
-
-	return err;
-}
-
-#endif
diff --git a/arch/arm/mach-tegra/board.h b/arch/arm/mach-tegra/board.h
index 9a6659fe2dc2..db6810dc0b3d 100644
--- a/arch/arm/mach-tegra/board.h
+++ b/arch/arm/mach-tegra/board.h
@@ -31,7 +31,6 @@ void __init tegra_init_early(void);
 void __init tegra_map_common_io(void);
 void __init tegra_init_irq(void);
 void __init tegra_dt_init_irq(void);
-int __init tegra_pcie_init(bool init_port0, bool init_port1);
 
 void tegra_init_late(void);
 
@@ -48,13 +47,6 @@ int __init tegra_powergate_debugfs_init(void);
 static inline int tegra_powergate_debugfs_init(void) { return 0; }
 #endif
 
-int __init harmony_regulator_init(void);
-#ifdef CONFIG_TEGRA_PCI
-int __init harmony_pcie_init(void);
-#else
-static inline int harmony_pcie_init(void) { return 0; }
-#endif
-
 void __init tegra_paz00_wifikill_init(void);
 
 #endif
diff --git a/arch/arm/mach-tegra/common.h b/arch/arm/mach-tegra/common.h
index 32f8eb3fe344..5900cc44f780 100644
--- a/arch/arm/mach-tegra/common.h
+++ b/arch/arm/mach-tegra/common.h
@@ -2,4 +2,3 @@ extern struct smp_operations tegra_smp_ops;
 
 extern int tegra_cpu_kill(unsigned int cpu);
 extern void tegra_cpu_die(unsigned int cpu);
-extern int tegra_cpu_disable(unsigned int cpu);
diff --git a/arch/arm/mach-tegra/cpuidle-tegra114.c b/arch/arm/mach-tegra/cpuidle-tegra114.c
index 1d1c6023f4a2..e0b87300243d 100644
--- a/arch/arm/mach-tegra/cpuidle-tegra114.c
+++ b/arch/arm/mach-tegra/cpuidle-tegra114.c
@@ -17,15 +17,64 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/cpuidle.h>
+#include <linux/cpu_pm.h>
+#include <linux/clockchips.h>
 
 #include <asm/cpuidle.h>
+#include <asm/suspend.h>
+#include <asm/smp_plat.h>
+
+#include "pm.h"
+#include "sleep.h"
+
+#ifdef CONFIG_PM_SLEEP
+#define TEGRA114_MAX_STATES 2
+#else
+#define TEGRA114_MAX_STATES 1
+#endif
+
+#ifdef CONFIG_PM_SLEEP
+static int tegra114_idle_power_down(struct cpuidle_device *dev,
+				    struct cpuidle_driver *drv,
+				    int index)
+{
+	local_fiq_disable();
+
+	tegra_set_cpu_in_lp2();
+	cpu_pm_enter();
+
+	clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &dev->cpu);
+
+	cpu_suspend(0, tegra30_sleep_cpu_secondary_finish);
+
+	clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &dev->cpu);
+
+	cpu_pm_exit();
+	tegra_clear_cpu_in_lp2();
+
+	local_fiq_enable();
+
+	return index;
+}
+#endif
 
 static struct cpuidle_driver tegra_idle_driver = {
 	.name = "tegra_idle",
 	.owner = THIS_MODULE,
-	.state_count = 1,
+	.state_count = TEGRA114_MAX_STATES,
 	.states = {
 		[0] = ARM_CPUIDLE_WFI_STATE_PWR(600),
+#ifdef CONFIG_PM_SLEEP
+		[1] = {
+			.enter			= tegra114_idle_power_down,
+			.exit_latency		= 500,
+			.target_residency	= 1000,
+			.power_usage		= 0,
+			.flags			= CPUIDLE_FLAG_TIME_VALID,
+			.name			= "powered-down",
+			.desc			= "CPU power gated",
+		},
+#endif
 	},
 };
 
diff --git a/arch/arm/mach-tegra/cpuidle-tegra20.c b/arch/arm/mach-tegra/cpuidle-tegra20.c
index 706aa4215c36..b82dcaee2ef4 100644
--- a/arch/arm/mach-tegra/cpuidle-tegra20.c
+++ b/arch/arm/mach-tegra/cpuidle-tegra20.c
@@ -211,6 +211,18 @@ static int tegra20_idle_lp2_coupled(struct cpuidle_device *dev,
 }
 #endif
 
+/*
+ * Tegra20 HW appears to have a bug such that PCIe device interrupts, whether
+ * they are legacy IRQs or MSI, are lost when LP2 is enabled. To work around
+ * this, simply disable LP2 if the PCI driver and DT node are both enabled.
+ */
+void tegra20_cpuidle_pcie_irqs_in_use(void)
+{
+	pr_info_once(
+		"Disabling cpuidle LP2 state, since PCIe IRQs are in use\n");
+	tegra_idle_driver.states[1].disabled = true;
+}
+
 int __init tegra20_cpuidle_init(void)
 {
 	return cpuidle_register(&tegra_idle_driver, cpu_possible_mask);
diff --git a/arch/arm/mach-tegra/cpuidle.c b/arch/arm/mach-tegra/cpuidle.c
index e85973cef037..0961dfcf83a4 100644
--- a/arch/arm/mach-tegra/cpuidle.c
+++ b/arch/arm/mach-tegra/cpuidle.c
@@ -44,3 +44,13 @@ void __init tegra_cpuidle_init(void)
 		break;
 	}
 }
+
+void tegra_cpuidle_pcie_irqs_in_use(void)
+{
+	switch (tegra_chip_id) {
+	case TEGRA20:
+		if (IS_ENABLED(CONFIG_ARCH_TEGRA_2x_SOC))
+			tegra20_cpuidle_pcie_irqs_in_use();
+		break;
+	}
+}
diff --git a/arch/arm/mach-tegra/cpuidle.h b/arch/arm/mach-tegra/cpuidle.h
index 9ec2c1ab0fa4..c017dab60ffa 100644
--- a/arch/arm/mach-tegra/cpuidle.h
+++ b/arch/arm/mach-tegra/cpuidle.h
@@ -19,6 +19,7 @@
 
 #ifdef CONFIG_CPU_IDLE
 int tegra20_cpuidle_init(void);
+void tegra20_cpuidle_pcie_irqs_in_use(void);
 int tegra30_cpuidle_init(void);
 int tegra114_cpuidle_init(void);
 void tegra_cpuidle_init(void);
diff --git a/arch/arm/mach-tegra/flowctrl.c b/arch/arm/mach-tegra/flowctrl.c
index b477ef310dcd..5348543382bf 100644
--- a/arch/arm/mach-tegra/flowctrl.c
+++ b/arch/arm/mach-tegra/flowctrl.c
@@ -86,6 +86,7 @@ void flowctrl_cpu_suspend_enter(unsigned int cpuid)
 		reg |= TEGRA20_FLOW_CTRL_CSR_WFE_CPU0 << cpuid;
 		break;
 	case TEGRA30:
+	case TEGRA114:
 		/* clear wfe bitmap */
 		reg &= ~TEGRA30_FLOW_CTRL_CSR_WFE_BITMAP;
 		/* clear wfi bitmap */
@@ -123,6 +124,7 @@ void flowctrl_cpu_suspend_exit(unsigned int cpuid)
 		reg &= ~TEGRA20_FLOW_CTRL_CSR_WFI_BITMAP;
 		break;
 	case TEGRA30:
+	case TEGRA114:
 		/* clear wfe bitmap */
 		reg &= ~TEGRA30_FLOW_CTRL_CSR_WFE_BITMAP;
 		/* clear wfi bitmap */
diff --git a/arch/arm/mach-tegra/flowctrl.h b/arch/arm/mach-tegra/flowctrl.h
index 7a29bae799a7..c89aac60a143 100644
--- a/arch/arm/mach-tegra/flowctrl.h
+++ b/arch/arm/mach-tegra/flowctrl.h
@@ -28,9 +28,18 @@
 #define FLOW_CTRL_SCLK_RESUME		(1 << 27)
 #define FLOW_CTRL_HALT_CPU_IRQ		(1 << 10)
 #define	FLOW_CTRL_HALT_CPU_FIQ		(1 << 8)
+#define FLOW_CTRL_HALT_LIC_IRQ		(1 << 11)
+#define FLOW_CTRL_HALT_LIC_FIQ		(1 << 10)
+#define FLOW_CTRL_HALT_GIC_IRQ		(1 << 9)
+#define FLOW_CTRL_HALT_GIC_FIQ		(1 << 8)
 #define FLOW_CTRL_CPU0_CSR		0x8
 #define	FLOW_CTRL_CSR_INTR_FLAG		(1 << 15)
 #define FLOW_CTRL_CSR_EVENT_FLAG	(1 << 14)
+#define FLOW_CTRL_CSR_ENABLE_EXT_CRAIL	(1 << 13)
+#define FLOW_CTRL_CSR_ENABLE_EXT_NCPU	(1 << 12)
+#define FLOW_CTRL_CSR_ENABLE_EXT_MASK ( \
+		FLOW_CTRL_CSR_ENABLE_EXT_NCPU | \
+		FLOW_CTRL_CSR_ENABLE_EXT_CRAIL)
 #define FLOW_CTRL_CSR_ENABLE		(1 << 0)
 #define FLOW_CTRL_HALT_CPU1_EVENTS	0x14
 #define FLOW_CTRL_CPU1_CSR		0x18
diff --git a/arch/arm/mach-tegra/headsmp.S b/arch/arm/mach-tegra/headsmp.S
index 045c16f2dd51..2072e7322c39 100644
--- a/arch/arm/mach-tegra/headsmp.S
+++ b/arch/arm/mach-tegra/headsmp.S
@@ -6,6 +6,7 @@
         .section ".text.head", "ax"
 
 ENTRY(tegra_secondary_startup)
-        bl      v7_invalidate_l1
+        check_cpu_part_num 0xc09, r8, r9
+        bleq    v7_invalidate_l1
         b       secondary_startup
 ENDPROC(tegra_secondary_startup)
diff --git a/arch/arm/mach-tegra/hotplug.c b/arch/arm/mach-tegra/hotplug.c
index a52c10e0a857..04de2e860923 100644
--- a/arch/arm/mach-tegra/hotplug.c
+++ b/arch/arm/mach-tegra/hotplug.c
@@ -37,7 +37,7 @@ int tegra_cpu_kill(unsigned cpu)
 void __ref tegra_cpu_die(unsigned int cpu)
 {
 	/* Clean L1 data cache */
-	tegra_disable_clean_inv_dcache();
+	tegra_disable_clean_inv_dcache(TEGRA_FLUSH_CACHE_LOUIS);
 
 	/* Shut down the current CPU. */
 	tegra_hotplug_shutdown();
@@ -46,17 +46,6 @@ void __ref tegra_cpu_die(unsigned int cpu)
 	BUG();
 }
 
-int tegra_cpu_disable(unsigned int cpu)
-{
-	switch (tegra_chip_id) {
-	case TEGRA20:
-	case TEGRA30:
-		return cpu == 0 ? -EPERM : 0;
-	default:
-		return 0;
-	}
-}
-
 void __init tegra_hotplug_init(void)
 {
 	if (!IS_ENABLED(CONFIG_HOTPLUG_CPU))
diff --git a/arch/arm/mach-tegra/iomap.h b/arch/arm/mach-tegra/iomap.h
index 399fbca27102..3f5fa0749bde 100644
--- a/arch/arm/mach-tegra/iomap.h
+++ b/arch/arm/mach-tegra/iomap.h
@@ -24,6 +24,8 @@
 #define TEGRA_IRAM_BASE			0x40000000
 #define TEGRA_IRAM_SIZE			SZ_256K
 
+#define TEGRA_IRAM_CODE_AREA		(TEGRA_IRAM_BASE + SZ_4K)
+
 #define TEGRA_HOST1X_BASE		0x50000000
 #define TEGRA_HOST1X_SIZE		0x24000
 
@@ -237,6 +239,12 @@
 #define TEGRA_KFUSE_BASE		0x7000FC00
 #define TEGRA_KFUSE_SIZE		SZ_1K
 
+#define TEGRA_EMC0_BASE			0x7001A000
+#define TEGRA_EMC0_SIZE			SZ_2K
+
+#define TEGRA_EMC1_BASE			0x7001A800
+#define TEGRA_EMC1_SIZE			SZ_2K
+
 #define TEGRA_CSITE_BASE		0x70040000
 #define TEGRA_CSITE_SIZE		SZ_256K
 
@@ -278,9 +286,6 @@
 #define IO_APB_VIRT	IOMEM(0xFE300000)
 #define IO_APB_SIZE	SZ_1M
 
-#define TEGRA_PCIE_BASE		0x80000000
-#define TEGRA_PCIE_IO_BASE	(TEGRA_PCIE_BASE + SZ_4M)
-
 #define IO_TO_VIRT_BETWEEN(p, st, sz)	((p) >= (st) && (p) < ((st) + (sz)))
 #define IO_TO_VIRT_XLATE(p, pst, vst)	(((p) - (pst) + (vst)))
 
diff --git a/arch/arm/mach-tegra/irq.c b/arch/arm/mach-tegra/irq.c
index 0de4eed1493d..1a74d562dca1 100644
--- a/arch/arm/mach-tegra/irq.c
+++ b/arch/arm/mach-tegra/irq.c
@@ -18,10 +18,12 @@
  */
 
 #include <linux/kernel.h>
+#include <linux/cpu_pm.h>
 #include <linux/interrupt.h>
 #include <linux/irq.h>
 #include <linux/io.h>
 #include <linux/of.h>
+#include <linux/of_address.h>
 #include <linux/irqchip/arm-gic.h>
 #include <linux/syscore_ops.h>
 
@@ -65,6 +67,7 @@ static u32 cpu_ier[TEGRA_MAX_NUM_ICTLRS];
 static u32 cpu_iep[TEGRA_MAX_NUM_ICTLRS];
 
 static u32 ictlr_wake_mask[TEGRA_MAX_NUM_ICTLRS];
+static void __iomem *tegra_gic_cpu_base;
 #endif
 
 bool tegra_pending_sgi(void)
@@ -213,8 +216,43 @@ int tegra_legacy_irq_syscore_init(void)
 
 	return 0;
 }
+
+static int tegra_gic_notifier(struct notifier_block *self,
+			      unsigned long cmd, void *v)
+{
+	switch (cmd) {
+	case CPU_PM_ENTER:
+		writel_relaxed(0x1E0, tegra_gic_cpu_base + GIC_CPU_CTRL);
+		break;
+	}
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block tegra_gic_notifier_block = {
+	.notifier_call = tegra_gic_notifier,
+};
+
+static const struct of_device_id tegra114_dt_gic_match[] __initconst = {
+	{ .compatible = "arm,cortex-a15-gic" },
+	{ }
+};
+
+static void tegra114_gic_cpu_pm_registration(void)
+{
+	struct device_node *dn;
+
+	dn = of_find_matching_node(NULL, tegra114_dt_gic_match);
+	if (!dn)
+		return;
+
+	tegra_gic_cpu_base = of_iomap(dn, 1);
+
+	cpu_pm_register_notifier(&tegra_gic_notifier_block);
+}
 #else
 #define tegra_set_wake NULL
+static void tegra114_gic_cpu_pm_registration(void) { }
 #endif
 
 void __init tegra_init_irq(void)
@@ -252,4 +290,6 @@ void __init tegra_init_irq(void)
 	if (!of_have_populated_dt())
 		gic_init(0, 29, distbase,
 			IO_ADDRESS(TEGRA_ARM_PERIF_BASE + 0x100));
+
+	tegra114_gic_cpu_pm_registration();
 }
diff --git a/arch/arm/mach-tegra/pcie.c b/arch/arm/mach-tegra/pcie.c
deleted file mode 100644
index 46144a19a7e7..000000000000
--- a/arch/arm/mach-tegra/pcie.c
+++ /dev/null
@@ -1,886 +0,0 @@
-/*
- * arch/arm/mach-tegra/pci.c
- *
- * PCIe host controller driver for TEGRA(2) SOCs
- *
- * Copyright (c) 2010, CompuLab, Ltd.
- * Author: Mike Rapoport <mike@compulab.co.il>
- *
- * Based on NVIDIA PCIe driver
- * Copyright (c) 2008-2009, NVIDIA Corporation.
- *
- * Bits taken from arch/arm/mach-dove/pcie.c
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program; if not, write to the Free Software Foundation, Inc.,
- * 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
- */
-
-#include <linux/kernel.h>
-#include <linux/pci.h>
-#include <linux/interrupt.h>
-#include <linux/irq.h>
-#include <linux/clk.h>
-#include <linux/delay.h>
-#include <linux/export.h>
-#include <linux/clk/tegra.h>
-#include <linux/tegra-powergate.h>
-
-#include <asm/sizes.h>
-#include <asm/mach/pci.h>
-
-#include "board.h"
-#include "iomap.h"
-
-/* Hack - need to parse this from DT */
-#define INT_PCIE_INTR 130
-
-/* register definitions */
-#define AFI_OFFSET	0x3800
-#define PADS_OFFSET	0x3000
-#define RP0_OFFSET	0x0000
-#define RP1_OFFSET	0x1000
-
-#define AFI_AXI_BAR0_SZ	0x00
-#define AFI_AXI_BAR1_SZ	0x04
-#define AFI_AXI_BAR2_SZ	0x08
-#define AFI_AXI_BAR3_SZ	0x0c
-#define AFI_AXI_BAR4_SZ	0x10
-#define AFI_AXI_BAR5_SZ	0x14
-
-#define AFI_AXI_BAR0_START	0x18
-#define AFI_AXI_BAR1_START	0x1c
-#define AFI_AXI_BAR2_START	0x20
-#define AFI_AXI_BAR3_START	0x24
-#define AFI_AXI_BAR4_START	0x28
-#define AFI_AXI_BAR5_START	0x2c
-
-#define AFI_FPCI_BAR0	0x30
-#define AFI_FPCI_BAR1	0x34
-#define AFI_FPCI_BAR2	0x38
-#define AFI_FPCI_BAR3	0x3c
-#define AFI_FPCI_BAR4	0x40
-#define AFI_FPCI_BAR5	0x44
-
-#define AFI_CACHE_BAR0_SZ	0x48
-#define AFI_CACHE_BAR0_ST	0x4c
-#define AFI_CACHE_BAR1_SZ	0x50
-#define AFI_CACHE_BAR1_ST	0x54
-
-#define AFI_MSI_BAR_SZ		0x60
-#define AFI_MSI_FPCI_BAR_ST	0x64
-#define AFI_MSI_AXI_BAR_ST	0x68
-
-#define AFI_CONFIGURATION		0xac
-#define  AFI_CONFIGURATION_EN_FPCI	(1 << 0)
-
-#define AFI_FPCI_ERROR_MASKS	0xb0
-
-#define AFI_INTR_MASK		0xb4
-#define  AFI_INTR_MASK_INT_MASK	(1 << 0)
-#define  AFI_INTR_MASK_MSI_MASK	(1 << 8)
-
-#define AFI_INTR_CODE		0xb8
-#define  AFI_INTR_CODE_MASK	0xf
-#define  AFI_INTR_MASTER_ABORT	4
-#define  AFI_INTR_LEGACY	6
-
-#define AFI_INTR_SIGNATURE	0xbc
-#define AFI_SM_INTR_ENABLE	0xc4
-
-#define AFI_AFI_INTR_ENABLE		0xc8
-#define  AFI_INTR_EN_INI_SLVERR		(1 << 0)
-#define  AFI_INTR_EN_INI_DECERR		(1 << 1)
-#define  AFI_INTR_EN_TGT_SLVERR		(1 << 2)
-#define  AFI_INTR_EN_TGT_DECERR		(1 << 3)
-#define  AFI_INTR_EN_TGT_WRERR		(1 << 4)
-#define  AFI_INTR_EN_DFPCI_DECERR	(1 << 5)
-#define  AFI_INTR_EN_AXI_DECERR		(1 << 6)
-#define  AFI_INTR_EN_FPCI_TIMEOUT	(1 << 7)
-
-#define AFI_PCIE_CONFIG					0x0f8
-#define  AFI_PCIE_CONFIG_PCIEC0_DISABLE_DEVICE		(1 << 1)
-#define  AFI_PCIE_CONFIG_PCIEC1_DISABLE_DEVICE		(1 << 2)
-#define  AFI_PCIE_CONFIG_SM2TMS0_XBAR_CONFIG_MASK	(0xf << 20)
-#define  AFI_PCIE_CONFIG_SM2TMS0_XBAR_CONFIG_SINGLE	(0x0 << 20)
-#define  AFI_PCIE_CONFIG_SM2TMS0_XBAR_CONFIG_DUAL	(0x1 << 20)
-
-#define AFI_FUSE			0x104
-#define  AFI_FUSE_PCIE_T0_GEN2_DIS	(1 << 2)
-
-#define AFI_PEX0_CTRL			0x110
-#define AFI_PEX1_CTRL			0x118
-#define  AFI_PEX_CTRL_RST		(1 << 0)
-#define  AFI_PEX_CTRL_REFCLK_EN		(1 << 3)
-
-#define RP_VEND_XP	0x00000F00
-#define  RP_VEND_XP_DL_UP	(1 << 30)
-
-#define RP_LINK_CONTROL_STATUS			0x00000090
-#define  RP_LINK_CONTROL_STATUS_LINKSTAT_MASK	0x3fff0000
-
-#define PADS_CTL_SEL		0x0000009C
-
-#define PADS_CTL		0x000000A0
-#define  PADS_CTL_IDDQ_1L	(1 << 0)
-#define  PADS_CTL_TX_DATA_EN_1L	(1 << 6)
-#define  PADS_CTL_RX_DATA_EN_1L	(1 << 10)
-
-#define PADS_PLL_CTL				0x000000B8
-#define  PADS_PLL_CTL_RST_B4SM			(1 << 1)
-#define  PADS_PLL_CTL_LOCKDET			(1 << 8)
-#define  PADS_PLL_CTL_REFCLK_MASK		(0x3 << 16)
-#define  PADS_PLL_CTL_REFCLK_INTERNAL_CML	(0 << 16)
-#define  PADS_PLL_CTL_REFCLK_INTERNAL_CMOS	(1 << 16)
-#define  PADS_PLL_CTL_REFCLK_EXTERNAL		(2 << 16)
-#define  PADS_PLL_CTL_TXCLKREF_MASK		(0x1 << 20)
-#define  PADS_PLL_CTL_TXCLKREF_DIV10		(0 << 20)
-#define  PADS_PLL_CTL_TXCLKREF_DIV5		(1 << 20)
-
-/* PMC access is required for PCIE xclk (un)clamping */
-#define PMC_SCRATCH42		0x144
-#define PMC_SCRATCH42_PCX_CLAMP	(1 << 0)
-
-static void __iomem *reg_pmc_base = IO_ADDRESS(TEGRA_PMC_BASE);
-
-#define pmc_writel(value, reg) \
-	__raw_writel(value, reg_pmc_base + (reg))
-#define pmc_readl(reg) \
-	__raw_readl(reg_pmc_base + (reg))
-
-/*
- * Tegra2 defines 1GB in the AXI address map for PCIe.
- *
- * That address space is split into different regions, with sizes and
- * offsets as follows:
- *
- * 0x80000000 - 0x80003fff - PCI controller registers
- * 0x80004000 - 0x80103fff - PCI configuration space
- * 0x80104000 - 0x80203fff - PCI extended configuration space
- * 0x80203fff - 0x803fffff - unused
- * 0x80400000 - 0x8040ffff - downstream IO
- * 0x80410000 - 0x8fffffff - unused
- * 0x90000000 - 0x9fffffff - non-prefetchable memory
- * 0xa0000000 - 0xbfffffff - prefetchable memory
- */
-#define PCIE_REGS_SZ		SZ_16K
-#define PCIE_CFG_OFF		PCIE_REGS_SZ
-#define PCIE_CFG_SZ		SZ_1M
-#define PCIE_EXT_CFG_OFF	(PCIE_CFG_SZ + PCIE_CFG_OFF)
-#define PCIE_EXT_CFG_SZ		SZ_1M
-#define PCIE_IOMAP_SZ		(PCIE_REGS_SZ + PCIE_CFG_SZ + PCIE_EXT_CFG_SZ)
-
-#define MEM_BASE_0		(TEGRA_PCIE_BASE + SZ_256M)
-#define MEM_SIZE_0		SZ_128M
-#define MEM_BASE_1		(MEM_BASE_0 + MEM_SIZE_0)
-#define MEM_SIZE_1		SZ_128M
-#define PREFETCH_MEM_BASE_0	(MEM_BASE_1 + MEM_SIZE_1)
-#define PREFETCH_MEM_SIZE_0	SZ_128M
-#define PREFETCH_MEM_BASE_1	(PREFETCH_MEM_BASE_0 + PREFETCH_MEM_SIZE_0)
-#define PREFETCH_MEM_SIZE_1	SZ_128M
-
-#define  PCIE_CONF_BUS(b)	((b) << 16)
-#define  PCIE_CONF_DEV(d)	((d) << 11)
-#define  PCIE_CONF_FUNC(f)	((f) << 8)
-#define  PCIE_CONF_REG(r)	\
-	(((r) & ~0x3) | (((r) < 256) ? PCIE_CFG_OFF : PCIE_EXT_CFG_OFF))
-
-struct tegra_pcie_port {
-	int			index;
-	u8			root_bus_nr;
-	void __iomem		*base;
-
-	bool			link_up;
-
-	char			mem_space_name[16];
-	char			prefetch_space_name[20];
-	struct resource		res[2];
-};
-
-struct tegra_pcie_info {
-	struct tegra_pcie_port	port[2];
-	int			num_ports;
-
-	void __iomem		*regs;
-	struct resource		res_mmio;
-
-	struct clk		*pex_clk;
-	struct clk		*afi_clk;
-	struct clk		*pcie_xclk;
-	struct clk		*pll_e;
-};
-
-static struct tegra_pcie_info tegra_pcie;
-
-static inline void afi_writel(u32 value, unsigned long offset)
-{
-	writel(value, offset + AFI_OFFSET + tegra_pcie.regs);
-}
-
-static inline u32 afi_readl(unsigned long offset)
-{
-	return readl(offset + AFI_OFFSET + tegra_pcie.regs);
-}
-
-static inline void pads_writel(u32 value, unsigned long offset)
-{
-	writel(value, offset + PADS_OFFSET + tegra_pcie.regs);
-}
-
-static inline u32 pads_readl(unsigned long offset)
-{
-	return readl(offset + PADS_OFFSET + tegra_pcie.regs);
-}
-
-static struct tegra_pcie_port *bus_to_port(int bus)
-{
-	int i;
-
-	for (i = tegra_pcie.num_ports - 1; i >= 0; i--) {
-		int rbus = tegra_pcie.port[i].root_bus_nr;
-		if (rbus != -1 && rbus == bus)
-			break;
-	}
-
-	return i >= 0 ? tegra_pcie.port + i : NULL;
-}
-
-static int tegra_pcie_read_conf(struct pci_bus *bus, unsigned int devfn,
-				int where, int size, u32 *val)
-{
-	struct tegra_pcie_port *pp = bus_to_port(bus->number);
-	void __iomem *addr;
-
-	if (pp) {
-		if (devfn != 0) {
-			*val = 0xffffffff;
-			return PCIBIOS_DEVICE_NOT_FOUND;
-		}
-
-		addr = pp->base + (where & ~0x3);
-	} else {
-		addr = tegra_pcie.regs + (PCIE_CONF_BUS(bus->number) +
-					  PCIE_CONF_DEV(PCI_SLOT(devfn)) +
-					  PCIE_CONF_FUNC(PCI_FUNC(devfn)) +
-					  PCIE_CONF_REG(where));
-	}
-
-	*val = readl(addr);
-
-	if (size == 1)
-		*val = (*val >> (8 * (where & 3))) & 0xff;
-	else if (size == 2)
-		*val = (*val >> (8 * (where & 3))) & 0xffff;
-
-	return PCIBIOS_SUCCESSFUL;
-}
-
-static int tegra_pcie_write_conf(struct pci_bus *bus, unsigned int devfn,
-				 int where, int size, u32 val)
-{
-	struct tegra_pcie_port *pp = bus_to_port(bus->number);
-	void __iomem *addr;
-
-	u32 mask;
-	u32 tmp;
-
-	if (pp) {
-		if (devfn != 0)
-			return PCIBIOS_DEVICE_NOT_FOUND;
-
-		addr = pp->base + (where & ~0x3);
-	} else {
-		addr = tegra_pcie.regs + (PCIE_CONF_BUS(bus->number) +
-					  PCIE_CONF_DEV(PCI_SLOT(devfn)) +
-					  PCIE_CONF_FUNC(PCI_FUNC(devfn)) +
-					  PCIE_CONF_REG(where));
-	}
-
-	if (size == 4) {
-		writel(val, addr);
-		return PCIBIOS_SUCCESSFUL;
-	}
-
-	if (size == 2)
-		mask = ~(0xffff << ((where & 0x3) * 8));
-	else if (size == 1)
-		mask = ~(0xff << ((where & 0x3) * 8));
-	else
-		return PCIBIOS_BAD_REGISTER_NUMBER;
-
-	tmp = readl(addr) & mask;
-	tmp |= val << ((where & 0x3) * 8);
-	writel(tmp, addr);
-
-	return PCIBIOS_SUCCESSFUL;
-}
-
-static struct pci_ops tegra_pcie_ops = {
-	.read	= tegra_pcie_read_conf,
-	.write	= tegra_pcie_write_conf,
-};
-
-static void tegra_pcie_fixup_bridge(struct pci_dev *dev)
-{
-	u16 reg;
-
-	if ((dev->class >> 16) == PCI_BASE_CLASS_BRIDGE) {
-		pci_read_config_word(dev, PCI_COMMAND, &reg);
-		reg |= (PCI_COMMAND_IO | PCI_COMMAND_MEMORY |
-			PCI_COMMAND_MASTER | PCI_COMMAND_SERR);
-		pci_write_config_word(dev, PCI_COMMAND, reg);
-	}
-}
-DECLARE_PCI_FIXUP_FINAL(PCI_ANY_ID, PCI_ANY_ID, tegra_pcie_fixup_bridge);
-
-/* Tegra PCIE root complex wrongly reports device class */
-static void tegra_pcie_fixup_class(struct pci_dev *dev)
-{
-	dev->class = PCI_CLASS_BRIDGE_PCI << 8;
-}
-DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_NVIDIA, 0x0bf0, tegra_pcie_fixup_class);
-DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_NVIDIA, 0x0bf1, tegra_pcie_fixup_class);
-
-/* Tegra PCIE requires relaxed ordering */
-static void tegra_pcie_relax_enable(struct pci_dev *dev)
-{
-	pcie_capability_set_word(dev, PCI_EXP_DEVCTL, PCI_EXP_DEVCTL_RELAX_EN);
-}
-DECLARE_PCI_FIXUP_FINAL(PCI_ANY_ID, PCI_ANY_ID, tegra_pcie_relax_enable);
-
-static int tegra_pcie_setup(int nr, struct pci_sys_data *sys)
-{
-	struct tegra_pcie_port *pp;
-
-	if (nr >= tegra_pcie.num_ports)
-		return 0;
-
-	pp = tegra_pcie.port + nr;
-	pp->root_bus_nr = sys->busnr;
-
-	pci_ioremap_io(nr * SZ_64K, TEGRA_PCIE_IO_BASE);
-
-	/*
-	 * IORESOURCE_MEM
-	 */
-	snprintf(pp->mem_space_name, sizeof(pp->mem_space_name),
-		 "PCIe %d MEM", pp->index);
-	pp->mem_space_name[sizeof(pp->mem_space_name) - 1] = 0;
-	pp->res[0].name = pp->mem_space_name;
-	if (pp->index == 0) {
-		pp->res[0].start = MEM_BASE_0;
-		pp->res[0].end = pp->res[0].start + MEM_SIZE_0 - 1;
-	} else {
-		pp->res[0].start = MEM_BASE_1;
-		pp->res[0].end = pp->res[0].start + MEM_SIZE_1 - 1;
-	}
-	pp->res[0].flags = IORESOURCE_MEM;
-	if (request_resource(&iomem_resource, &pp->res[0]))
-		panic("Request PCIe Memory resource failed\n");
-	pci_add_resource_offset(&sys->resources, &pp->res[0], sys->mem_offset);
-
-	/*
-	 * IORESOURCE_MEM | IORESOURCE_PREFETCH
-	 */
-	snprintf(pp->prefetch_space_name, sizeof(pp->prefetch_space_name),
-		 "PCIe %d PREFETCH MEM", pp->index);
-	pp->prefetch_space_name[sizeof(pp->prefetch_space_name) - 1] = 0;
-	pp->res[1].name = pp->prefetch_space_name;
-	if (pp->index == 0) {
-		pp->res[1].start = PREFETCH_MEM_BASE_0;
-		pp->res[1].end = pp->res[1].start + PREFETCH_MEM_SIZE_0 - 1;
-	} else {
-		pp->res[1].start = PREFETCH_MEM_BASE_1;
-		pp->res[1].end = pp->res[1].start + PREFETCH_MEM_SIZE_1 - 1;
-	}
-	pp->res[1].flags = IORESOURCE_MEM | IORESOURCE_PREFETCH;
-	if (request_resource(&iomem_resource, &pp->res[1]))
-		panic("Request PCIe Prefetch Memory resource failed\n");
-	pci_add_resource_offset(&sys->resources, &pp->res[1], sys->mem_offset);
-
-	return 1;
-}
-
-static int tegra_pcie_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
-{
-	return INT_PCIE_INTR;
-}
-
-static struct pci_bus __init *tegra_pcie_scan_bus(int nr,
-						  struct pci_sys_data *sys)
-{
-	struct tegra_pcie_port *pp;
-
-	if (nr >= tegra_pcie.num_ports)
-		return NULL;
-
-	pp = tegra_pcie.port + nr;
-	pp->root_bus_nr = sys->busnr;
-
-	return pci_scan_root_bus(NULL, sys->busnr, &tegra_pcie_ops, sys,
-				 &sys->resources);
-}
-
-static struct hw_pci tegra_pcie_hw __initdata = {
-	.nr_controllers	= 2,
-	.setup		= tegra_pcie_setup,
-	.scan		= tegra_pcie_scan_bus,
-	.map_irq	= tegra_pcie_map_irq,
-};
-
-
-static irqreturn_t tegra_pcie_isr(int irq, void *arg)
-{
-	const char *err_msg[] = {
-		"Unknown",
-		"AXI slave error",
-		"AXI decode error",
-		"Target abort",
-		"Master abort",
-		"Invalid write",
-		"Response decoding error",
-		"AXI response decoding error",
-		"Transcation timeout",
-	};
-
-	u32 code, signature;
-
-	code = afi_readl(AFI_INTR_CODE) & AFI_INTR_CODE_MASK;
-	signature = afi_readl(AFI_INTR_SIGNATURE);
-	afi_writel(0, AFI_INTR_CODE);
-
-	if (code == AFI_INTR_LEGACY)
-		return IRQ_NONE;
-
-	if (code >= ARRAY_SIZE(err_msg))
-		code = 0;
-
-	/*
-	 * do not pollute kernel log with master abort reports since they
-	 * happen a lot during enumeration
-	 */
-	if (code == AFI_INTR_MASTER_ABORT)
-		pr_debug("PCIE: %s, signature: %08x\n", err_msg[code], signature);
-	else
-		pr_err("PCIE: %s, signature: %08x\n", err_msg[code], signature);
-
-	return IRQ_HANDLED;
-}
-
-static void tegra_pcie_setup_translations(void)
-{
-	u32 fpci_bar;
-	u32 size;
-	u32 axi_address;
-
-	/* Bar 0: config Bar */
-	fpci_bar = ((u32)0xfdff << 16);
-	size = PCIE_CFG_SZ;
-	axi_address = TEGRA_PCIE_BASE + PCIE_CFG_OFF;
-	afi_writel(axi_address, AFI_AXI_BAR0_START);
-	afi_writel(size >> 12, AFI_AXI_BAR0_SZ);
-	afi_writel(fpci_bar, AFI_FPCI_BAR0);
-
-	/* Bar 1: extended config Bar */
-	fpci_bar = ((u32)0xfe1 << 20);
-	size = PCIE_EXT_CFG_SZ;
-	axi_address = TEGRA_PCIE_BASE + PCIE_EXT_CFG_OFF;
-	afi_writel(axi_address, AFI_AXI_BAR1_START);
-	afi_writel(size >> 12, AFI_AXI_BAR1_SZ);
-	afi_writel(fpci_bar, AFI_FPCI_BAR1);
-
-	/* Bar 2: downstream IO bar */
-	fpci_bar = ((__u32)0xfdfc << 16);
-	size = SZ_128K;
-	axi_address = TEGRA_PCIE_IO_BASE;
-	afi_writel(axi_address, AFI_AXI_BAR2_START);
-	afi_writel(size >> 12, AFI_AXI_BAR2_SZ);
-	afi_writel(fpci_bar, AFI_FPCI_BAR2);
-
-	/* Bar 3: prefetchable memory BAR */
-	fpci_bar = (((PREFETCH_MEM_BASE_0 >> 12) & 0x0fffffff) << 4) | 0x1;
-	size =  PREFETCH_MEM_SIZE_0 +  PREFETCH_MEM_SIZE_1;
-	axi_address = PREFETCH_MEM_BASE_0;
-	afi_writel(axi_address, AFI_AXI_BAR3_START);
-	afi_writel(size >> 12, AFI_AXI_BAR3_SZ);
-	afi_writel(fpci_bar, AFI_FPCI_BAR3);
-
-	/* Bar 4: non prefetchable memory BAR */
-	fpci_bar = (((MEM_BASE_0 >> 12)	& 0x0FFFFFFF) << 4) | 0x1;
-	size = MEM_SIZE_0 + MEM_SIZE_1;
-	axi_address = MEM_BASE_0;
-	afi_writel(axi_address, AFI_AXI_BAR4_START);
-	afi_writel(size >> 12, AFI_AXI_BAR4_SZ);
-	afi_writel(fpci_bar, AFI_FPCI_BAR4);
-
-	/* Bar 5: NULL out the remaining BAR as it is not used */
-	fpci_bar = 0;
-	size = 0;
-	axi_address = 0;
-	afi_writel(axi_address, AFI_AXI_BAR5_START);
-	afi_writel(size >> 12, AFI_AXI_BAR5_SZ);
-	afi_writel(fpci_bar, AFI_FPCI_BAR5);
-
-	/* map all upstream transactions as uncached */
-	afi_writel(PHYS_OFFSET, AFI_CACHE_BAR0_ST);
-	afi_writel(0, AFI_CACHE_BAR0_SZ);
-	afi_writel(0, AFI_CACHE_BAR1_ST);
-	afi_writel(0, AFI_CACHE_BAR1_SZ);
-
-	/* No MSI */
-	afi_writel(0, AFI_MSI_FPCI_BAR_ST);
-	afi_writel(0, AFI_MSI_BAR_SZ);
-	afi_writel(0, AFI_MSI_AXI_BAR_ST);
-	afi_writel(0, AFI_MSI_BAR_SZ);
-}
-
-static int tegra_pcie_enable_controller(void)
-{
-	u32 val, reg;
-	int i, timeout;
-
-	/* Enable slot clock and pulse the reset signals */
-	for (i = 0, reg = AFI_PEX0_CTRL; i < 2; i++, reg += 0x8) {
-		val = afi_readl(reg) |  AFI_PEX_CTRL_REFCLK_EN;
-		afi_writel(val, reg);
-		val &= ~AFI_PEX_CTRL_RST;
-		afi_writel(val, reg);
-
-		val = afi_readl(reg) | AFI_PEX_CTRL_RST;
-		afi_writel(val, reg);
-	}
-
-	/* Enable dual controller and both ports */
-	val = afi_readl(AFI_PCIE_CONFIG);
-	val &= ~(AFI_PCIE_CONFIG_PCIEC0_DISABLE_DEVICE |
-		 AFI_PCIE_CONFIG_PCIEC1_DISABLE_DEVICE |
-		 AFI_PCIE_CONFIG_SM2TMS0_XBAR_CONFIG_MASK);
-	val |= AFI_PCIE_CONFIG_SM2TMS0_XBAR_CONFIG_DUAL;
-	afi_writel(val, AFI_PCIE_CONFIG);
-
-	val = afi_readl(AFI_FUSE) & ~AFI_FUSE_PCIE_T0_GEN2_DIS;
-	afi_writel(val, AFI_FUSE);
-
-	/* Initialze internal PHY, enable up to 16 PCIE lanes */
-	pads_writel(0x0, PADS_CTL_SEL);
-
-	/* override IDDQ to 1 on all 4 lanes */
-	val = pads_readl(PADS_CTL) | PADS_CTL_IDDQ_1L;
-	pads_writel(val, PADS_CTL);
-
-	/*
-	 * set up PHY PLL inputs select PLLE output as refclock,
-	 * set TX ref sel to div10 (not div5)
-	 */
-	val = pads_readl(PADS_PLL_CTL);
-	val &= ~(PADS_PLL_CTL_REFCLK_MASK | PADS_PLL_CTL_TXCLKREF_MASK);
-	val |= (PADS_PLL_CTL_REFCLK_INTERNAL_CML | PADS_PLL_CTL_TXCLKREF_DIV10);
-	pads_writel(val, PADS_PLL_CTL);
-
-	/* take PLL out of reset  */
-	val = pads_readl(PADS_PLL_CTL) | PADS_PLL_CTL_RST_B4SM;
-	pads_writel(val, PADS_PLL_CTL);
-
-	/*
-	 * Hack, set the clock voltage to the DEFAULT provided by hw folks.
-	 * This doesn't exist in the documentation
-	 */
-	pads_writel(0xfa5cfa5c, 0xc8);
-
-	/* Wait for the PLL to lock */
-	timeout = 300;
-	do {
-		val = pads_readl(PADS_PLL_CTL);
-		usleep_range(1000, 1000);
-		if (--timeout == 0) {
-			pr_err("Tegra PCIe error: timeout waiting for PLL\n");
-			return -EBUSY;
-		}
-	} while (!(val & PADS_PLL_CTL_LOCKDET));
-
-	/* turn off IDDQ override */
-	val = pads_readl(PADS_CTL) & ~PADS_CTL_IDDQ_1L;
-	pads_writel(val, PADS_CTL);
-
-	/* enable TX/RX data */
-	val = pads_readl(PADS_CTL);
-	val |= (PADS_CTL_TX_DATA_EN_1L | PADS_CTL_RX_DATA_EN_1L);
-	pads_writel(val, PADS_CTL);
-
-	/* Take the PCIe interface module out of reset */
-	tegra_periph_reset_deassert(tegra_pcie.pcie_xclk);
-
-	/* Finally enable PCIe */
-	val = afi_readl(AFI_CONFIGURATION) | AFI_CONFIGURATION_EN_FPCI;
-	afi_writel(val, AFI_CONFIGURATION);
-
-	val = (AFI_INTR_EN_INI_SLVERR | AFI_INTR_EN_INI_DECERR |
-	       AFI_INTR_EN_TGT_SLVERR | AFI_INTR_EN_TGT_DECERR |
-	       AFI_INTR_EN_TGT_WRERR | AFI_INTR_EN_DFPCI_DECERR);
-	afi_writel(val, AFI_AFI_INTR_ENABLE);
-	afi_writel(0xffffffff, AFI_SM_INTR_ENABLE);
-
-	/* FIXME: No MSI for now, only INT */
-	afi_writel(AFI_INTR_MASK_INT_MASK, AFI_INTR_MASK);
-
-	/* Disable all execptions */
-	afi_writel(0, AFI_FPCI_ERROR_MASKS);
-
-	return 0;
-}
-
-static void tegra_pcie_xclk_clamp(bool clamp)
-{
-	u32 reg;
-
-	reg = pmc_readl(PMC_SCRATCH42) & ~PMC_SCRATCH42_PCX_CLAMP;
-
-	if (clamp)
-		reg |= PMC_SCRATCH42_PCX_CLAMP;
-
-	pmc_writel(reg, PMC_SCRATCH42);
-}
-
-static void tegra_pcie_power_off(void)
-{
-	tegra_periph_reset_assert(tegra_pcie.pcie_xclk);
-	tegra_periph_reset_assert(tegra_pcie.afi_clk);
-	tegra_periph_reset_assert(tegra_pcie.pex_clk);
-
-	tegra_powergate_power_off(TEGRA_POWERGATE_PCIE);
-	tegra_pcie_xclk_clamp(true);
-}
-
-static int tegra_pcie_power_regate(void)
-{
-	int err;
-
-	tegra_pcie_power_off();
-
-	tegra_pcie_xclk_clamp(true);
-
-	tegra_periph_reset_assert(tegra_pcie.pcie_xclk);
-	tegra_periph_reset_assert(tegra_pcie.afi_clk);
-
-	err = tegra_powergate_sequence_power_up(TEGRA_POWERGATE_PCIE,
-						tegra_pcie.pex_clk);
-	if (err) {
-		pr_err("PCIE: powerup sequence failed: %d\n", err);
-		return err;
-	}
-
-	tegra_periph_reset_deassert(tegra_pcie.afi_clk);
-
-	tegra_pcie_xclk_clamp(false);
-
-	clk_prepare_enable(tegra_pcie.afi_clk);
-	clk_prepare_enable(tegra_pcie.pex_clk);
-	return clk_prepare_enable(tegra_pcie.pll_e);
-}
-
-static int tegra_pcie_clocks_get(void)
-{
-	int err;
-
-	tegra_pcie.pex_clk = clk_get(NULL, "pex");
-	if (IS_ERR(tegra_pcie.pex_clk))
-		return PTR_ERR(tegra_pcie.pex_clk);
-
-	tegra_pcie.afi_clk = clk_get(NULL, "afi");
-	if (IS_ERR(tegra_pcie.afi_clk)) {
-		err = PTR_ERR(tegra_pcie.afi_clk);
-		goto err_afi_clk;
-	}
-
-	tegra_pcie.pcie_xclk = clk_get(NULL, "pcie_xclk");
-	if (IS_ERR(tegra_pcie.pcie_xclk)) {
-		err =  PTR_ERR(tegra_pcie.pcie_xclk);
-		goto err_pcie_xclk;
-	}
-
-	tegra_pcie.pll_e = clk_get_sys(NULL, "pll_e");
-	if (IS_ERR(tegra_pcie.pll_e)) {
-		err = PTR_ERR(tegra_pcie.pll_e);
-		goto err_pll_e;
-	}
-
-	return 0;
-
-err_pll_e:
-	clk_put(tegra_pcie.pcie_xclk);
-err_pcie_xclk:
-	clk_put(tegra_pcie.afi_clk);
-err_afi_clk:
-	clk_put(tegra_pcie.pex_clk);
-
-	return err;
-}
-
-static void tegra_pcie_clocks_put(void)
-{
-	clk_put(tegra_pcie.pll_e);
-	clk_put(tegra_pcie.pcie_xclk);
-	clk_put(tegra_pcie.afi_clk);
-	clk_put(tegra_pcie.pex_clk);
-}
-
-static int __init tegra_pcie_get_resources(void)
-{
-	int err;
-
-	err = tegra_pcie_clocks_get();
-	if (err) {
-		pr_err("PCIE: failed to get clocks: %d\n", err);
-		return err;
-	}
-
-	err = tegra_pcie_power_regate();
-	if (err) {
-		pr_err("PCIE: failed to power up: %d\n", err);
-		goto err_pwr_on;
-	}
-
-	tegra_pcie.regs = ioremap_nocache(TEGRA_PCIE_BASE, PCIE_IOMAP_SZ);
-	if (tegra_pcie.regs == NULL) {
-		pr_err("PCIE: Failed to map PCI/AFI registers\n");
-		err = -ENOMEM;
-		goto err_map_reg;
-	}
-
-	err = request_irq(INT_PCIE_INTR, tegra_pcie_isr,
-			  IRQF_SHARED, "PCIE", &tegra_pcie);
-	if (err) {
-		pr_err("PCIE: Failed to register IRQ: %d\n", err);
-		goto err_req_io;
-	}
-	set_irq_flags(INT_PCIE_INTR, IRQF_VALID);
-
-	return 0;
-
-err_req_io:
-	iounmap(tegra_pcie.regs);
-err_map_reg:
-	tegra_pcie_power_off();
-err_pwr_on:
-	tegra_pcie_clocks_put();
-
-	return err;
-}
-
-/*
- * FIXME: If there are no PCIe cards attached, then calling this function
- * can result in the increase of the bootup time as there are big timeout
- * loops.
- */
-#define TEGRA_PCIE_LINKUP_TIMEOUT	200	/* up to 1.2 seconds */
-static bool tegra_pcie_check_link(struct tegra_pcie_port *pp, int idx,
-				  u32 reset_reg)
-{
-	u32 reg;
-	int retries = 3;
-	int timeout;
-
-	do {
-		timeout = TEGRA_PCIE_LINKUP_TIMEOUT;
-		while (timeout) {
-			reg = readl(pp->base + RP_VEND_XP);
-
-			if (reg & RP_VEND_XP_DL_UP)
-				break;
-
-			mdelay(1);
-			timeout--;
-		}
-
-		if (!timeout)  {
-			pr_err("PCIE: port %d: link down, retrying\n", idx);
-			goto retry;
-		}
-
-		timeout = TEGRA_PCIE_LINKUP_TIMEOUT;
-		while (timeout) {
-			reg = readl(pp->base + RP_LINK_CONTROL_STATUS);
-
-			if (reg & 0x20000000)
-				return true;
-
-			mdelay(1);
-			timeout--;
-		}
-
-retry:
-		/* Pulse the PEX reset */
-		reg = afi_readl(reset_reg) | AFI_PEX_CTRL_RST;
-		afi_writel(reg, reset_reg);
-		mdelay(1);
-		reg = afi_readl(reset_reg) & ~AFI_PEX_CTRL_RST;
-		afi_writel(reg, reset_reg);
-
-		retries--;
-	} while (retries);
-
-	return false;
-}
-
-static void __init tegra_pcie_add_port(int index, u32 offset, u32 reset_reg)
-{
-	struct tegra_pcie_port *pp;
-
-	pp = tegra_pcie.port + tegra_pcie.num_ports;
-
-	pp->index = -1;
-	pp->base = tegra_pcie.regs + offset;
-	pp->link_up = tegra_pcie_check_link(pp, index, reset_reg);
-
-	if (!pp->link_up) {
-		pp->base = NULL;
-		printk(KERN_INFO "PCIE: port %d: link down, ignoring\n", index);
-		return;
-	}
-
-	tegra_pcie.num_ports++;
-	pp->index = index;
-	pp->root_bus_nr = -1;
-	memset(pp->res, 0, sizeof(pp->res));
-}
-
-int __init tegra_pcie_init(bool init_port0, bool init_port1)
-{
-	int err;
-
-	if (!(init_port0 || init_port1))
-		return -ENODEV;
-
-	pcibios_min_mem = 0;
-
-	err = tegra_pcie_get_resources();
-	if (err)
-		return err;
-
-	err = tegra_pcie_enable_controller();
-	if (err)
-		return err;
-
-	/* setup the AFI address translations */
-	tegra_pcie_setup_translations();
-
-	if (init_port0)
-		tegra_pcie_add_port(0, RP0_OFFSET, AFI_PEX0_CTRL);
-
-	if (init_port1)
-		tegra_pcie_add_port(1, RP1_OFFSET, AFI_PEX1_CTRL);
-
-	pci_common_init(&tegra_pcie_hw);
-
-	return 0;
-}
diff --git a/arch/arm/mach-tegra/platsmp.c b/arch/arm/mach-tegra/platsmp.c
index 97b33a2a2d75..2d0203627fbb 100644
--- a/arch/arm/mach-tegra/platsmp.c
+++ b/arch/arm/mach-tegra/platsmp.c
@@ -196,6 +196,5 @@ struct smp_operations tegra_smp_ops __initdata = {
 #ifdef CONFIG_HOTPLUG_CPU
 	.cpu_kill		= tegra_cpu_kill,
 	.cpu_die		= tegra_cpu_die,
-	.cpu_disable		= tegra_cpu_disable,
 #endif
 };
diff --git a/arch/arm/mach-tegra/pm-tegra20.c b/arch/arm/mach-tegra/pm-tegra20.c
new file mode 100644
index 000000000000..d65e1d786400
--- /dev/null
+++ b/arch/arm/mach-tegra/pm-tegra20.c
@@ -0,0 +1,34 @@
+/*
+ * Copyright (c) 2013, NVIDIA Corporation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+#include <linux/kernel.h>
+
+#include "pm.h"
+
+#ifdef CONFIG_PM_SLEEP
+extern u32 tegra20_iram_start, tegra20_iram_end;
+extern void tegra20_sleep_core_finish(unsigned long);
+
+void tegra20_lp1_iram_hook(void)
+{
+	tegra_lp1_iram.start_addr = &tegra20_iram_start;
+	tegra_lp1_iram.end_addr = &tegra20_iram_end;
+}
+
+void tegra20_sleep_core_init(void)
+{
+	tegra_sleep_core_finish = tegra20_sleep_core_finish;
+}
+#endif
diff --git a/arch/arm/mach-tegra/pm-tegra30.c b/arch/arm/mach-tegra/pm-tegra30.c
new file mode 100644
index 000000000000..8fa326d6ff1a
--- /dev/null
+++ b/arch/arm/mach-tegra/pm-tegra30.c
@@ -0,0 +1,34 @@
+/*
+ * Copyright (c) 2013, NVIDIA Corporation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+#include <linux/kernel.h>
+
+#include "pm.h"
+
+#ifdef CONFIG_PM_SLEEP
+extern u32 tegra30_iram_start, tegra30_iram_end;
+extern void tegra30_sleep_core_finish(unsigned long);
+
+void tegra30_lp1_iram_hook(void)
+{
+	tegra_lp1_iram.start_addr = &tegra30_iram_start;
+	tegra_lp1_iram.end_addr = &tegra30_iram_end;
+}
+
+void tegra30_sleep_core_init(void)
+{
+	tegra_sleep_core_finish = tegra30_sleep_core_finish;
+}
+#endif
diff --git a/arch/arm/mach-tegra/pm.c b/arch/arm/mach-tegra/pm.c
index 261fec140c06..ed294a04e1d3 100644
--- a/arch/arm/mach-tegra/pm.c
+++ b/arch/arm/mach-tegra/pm.c
@@ -37,12 +37,18 @@
 #include "reset.h"
 #include "flowctrl.h"
 #include "fuse.h"
+#include "pm.h"
 #include "pmc.h"
 #include "sleep.h"
 
 #ifdef CONFIG_PM_SLEEP
 static DEFINE_SPINLOCK(tegra_lp2_lock);
+static u32 iram_save_size;
+static void *iram_save_addr;
+struct tegra_lp1_iram tegra_lp1_iram;
 void (*tegra_tear_down_cpu)(void);
+void (*tegra_sleep_core_finish)(unsigned long v2p);
+static int (*tegra_sleep_func)(unsigned long v2p);
 
 static void tegra_tear_down_cpu_init(void)
 {
@@ -52,7 +58,9 @@ static void tegra_tear_down_cpu_init(void)
 			tegra_tear_down_cpu = tegra20_tear_down_cpu;
 		break;
 	case TEGRA30:
-		if (IS_ENABLED(CONFIG_ARCH_TEGRA_3x_SOC))
+	case TEGRA114:
+		if (IS_ENABLED(CONFIG_ARCH_TEGRA_3x_SOC) ||
+		    IS_ENABLED(CONFIG_ARCH_TEGRA_114_SOC))
 			tegra_tear_down_cpu = tegra30_tear_down_cpu;
 		break;
 	}
@@ -171,19 +179,109 @@ void tegra_idle_lp2_last(void)
 enum tegra_suspend_mode tegra_pm_validate_suspend_mode(
 				enum tegra_suspend_mode mode)
 {
-	/* Tegra114 didn't support any suspending mode yet. */
-	if (tegra_chip_id == TEGRA114)
-		return TEGRA_SUSPEND_NONE;
-
 	/*
-	 * The Tegra devices only support suspending to LP2 currently.
+	 * The Tegra devices support suspending to LP1 or lower currently.
 	 */
-	if (mode > TEGRA_SUSPEND_LP2)
-		return TEGRA_SUSPEND_LP2;
+	if (mode > TEGRA_SUSPEND_LP1)
+		return TEGRA_SUSPEND_LP1;
 
 	return mode;
 }
 
+static int tegra_sleep_core(unsigned long v2p)
+{
+	setup_mm_for_reboot();
+	tegra_sleep_core_finish(v2p);
+
+	/* should never here */
+	BUG();
+
+	return 0;
+}
+
+/*
+ * tegra_lp1_iram_hook
+ *
+ * Hooking the address of LP1 reset vector and SDRAM self-refresh code in
+ * SDRAM. These codes not be copied to IRAM in this fuction. We need to
+ * copy these code to IRAM before LP0/LP1 suspend and restore the content
+ * of IRAM after resume.
+ */
+static bool tegra_lp1_iram_hook(void)
+{
+	switch (tegra_chip_id) {
+	case TEGRA20:
+		if (IS_ENABLED(CONFIG_ARCH_TEGRA_2x_SOC))
+			tegra20_lp1_iram_hook();
+		break;
+	case TEGRA30:
+	case TEGRA114:
+		if (IS_ENABLED(CONFIG_ARCH_TEGRA_3x_SOC) ||
+		    IS_ENABLED(CONFIG_ARCH_TEGRA_114_SOC))
+			tegra30_lp1_iram_hook();
+		break;
+	default:
+		break;
+	}
+
+	if (!tegra_lp1_iram.start_addr || !tegra_lp1_iram.end_addr)
+		return false;
+
+	iram_save_size = tegra_lp1_iram.end_addr - tegra_lp1_iram.start_addr;
+	iram_save_addr = kmalloc(iram_save_size, GFP_KERNEL);
+	if (!iram_save_addr)
+		return false;
+
+	return true;
+}
+
+static bool tegra_sleep_core_init(void)
+{
+	switch (tegra_chip_id) {
+	case TEGRA20:
+		if (IS_ENABLED(CONFIG_ARCH_TEGRA_2x_SOC))
+			tegra20_sleep_core_init();
+		break;
+	case TEGRA30:
+	case TEGRA114:
+		if (IS_ENABLED(CONFIG_ARCH_TEGRA_3x_SOC) ||
+		    IS_ENABLED(CONFIG_ARCH_TEGRA_114_SOC))
+			tegra30_sleep_core_init();
+		break;
+	default:
+		break;
+	}
+
+	if (!tegra_sleep_core_finish)
+		return false;
+
+	return true;
+}
+
+static void tegra_suspend_enter_lp1(void)
+{
+	tegra_pmc_suspend();
+
+	/* copy the reset vector & SDRAM shutdown code into IRAM */
+	memcpy(iram_save_addr, IO_ADDRESS(TEGRA_IRAM_CODE_AREA),
+		iram_save_size);
+	memcpy(IO_ADDRESS(TEGRA_IRAM_CODE_AREA), tegra_lp1_iram.start_addr,
+		iram_save_size);
+
+	*((u32 *)tegra_cpu_lp1_mask) = 1;
+}
+
+static void tegra_suspend_exit_lp1(void)
+{
+	tegra_pmc_resume();
+
+	/* restore IRAM */
+	memcpy(IO_ADDRESS(TEGRA_IRAM_CODE_AREA), iram_save_addr,
+		iram_save_size);
+
+	*(u32 *)tegra_cpu_lp1_mask = 0;
+}
+
 static const char *lp_state[TEGRA_MAX_SUSPEND_MODE] = {
 	[TEGRA_SUSPEND_NONE] = "none",
 	[TEGRA_SUSPEND_LP2] = "LP2",
@@ -207,6 +305,9 @@ static int tegra_suspend_enter(suspend_state_t state)
 
 	suspend_cpu_complex();
 	switch (mode) {
+	case TEGRA_SUSPEND_LP1:
+		tegra_suspend_enter_lp1();
+		break;
 	case TEGRA_SUSPEND_LP2:
 		tegra_set_cpu_in_lp2();
 		break;
@@ -214,9 +315,12 @@ static int tegra_suspend_enter(suspend_state_t state)
 		break;
 	}
 
-	cpu_suspend(PHYS_OFFSET - PAGE_OFFSET, &tegra_sleep_cpu);
+	cpu_suspend(PHYS_OFFSET - PAGE_OFFSET, tegra_sleep_func);
 
 	switch (mode) {
+	case TEGRA_SUSPEND_LP1:
+		tegra_suspend_exit_lp1();
+		break;
 	case TEGRA_SUSPEND_LP2:
 		tegra_clear_cpu_in_lp2();
 		break;
@@ -237,12 +341,36 @@ static const struct platform_suspend_ops tegra_suspend_ops = {
 
 void __init tegra_init_suspend(void)
 {
-	if (tegra_pmc_get_suspend_mode() == TEGRA_SUSPEND_NONE)
+	enum tegra_suspend_mode mode = tegra_pmc_get_suspend_mode();
+
+	if (mode == TEGRA_SUSPEND_NONE)
 		return;
 
 	tegra_tear_down_cpu_init();
 	tegra_pmc_suspend_init();
 
+	if (mode >= TEGRA_SUSPEND_LP1) {
+		if (!tegra_lp1_iram_hook() || !tegra_sleep_core_init()) {
+			pr_err("%s: unable to allocate memory for SDRAM"
+			       "self-refresh -- LP0/LP1 unavailable\n",
+			       __func__);
+			tegra_pmc_set_suspend_mode(TEGRA_SUSPEND_LP2);
+			mode = TEGRA_SUSPEND_LP2;
+		}
+	}
+
+	/* set up sleep function for cpu_suspend */
+	switch (mode) {
+	case TEGRA_SUSPEND_LP1:
+		tegra_sleep_func = tegra_sleep_core;
+		break;
+	case TEGRA_SUSPEND_LP2:
+		tegra_sleep_func = tegra_sleep_cpu;
+		break;
+	default:
+		break;
+	}
+
 	suspend_set_ops(&tegra_suspend_ops);
 }
 #endif
diff --git a/arch/arm/mach-tegra/pm.h b/arch/arm/mach-tegra/pm.h
index 94c4b9d9077c..fe204e5256e7 100644
--- a/arch/arm/mach-tegra/pm.h
+++ b/arch/arm/mach-tegra/pm.h
@@ -23,6 +23,18 @@
 
 #include "pmc.h"
 
+struct tegra_lp1_iram {
+	void	*start_addr;
+	void	*end_addr;
+};
+extern struct tegra_lp1_iram tegra_lp1_iram;
+extern void (*tegra_sleep_core_finish)(unsigned long v2p);
+
+void tegra20_lp1_iram_hook(void);
+void tegra20_sleep_core_init(void);
+void tegra30_lp1_iram_hook(void);
+void tegra30_sleep_core_init(void);
+
 extern unsigned long l2x0_saved_regs_addr;
 
 void save_cpu_arch_register(void);
diff --git a/arch/arm/mach-tegra/pmc.c b/arch/arm/mach-tegra/pmc.c
index eb3fa4aee0e4..8acb881f7cfe 100644
--- a/arch/arm/mach-tegra/pmc.c
+++ b/arch/arm/mach-tegra/pmc.c
@@ -21,11 +21,14 @@
 #include <linux/of.h>
 #include <linux/of_address.h>
 
+#include "flowctrl.h"
 #include "fuse.h"
 #include "pm.h"
 #include "pmc.h"
 #include "sleep.h"
 
+#define TEGRA_POWER_SYSCLK_POLARITY	(1 << 10)  /* sys clk polarity */
+#define TEGRA_POWER_SYSCLK_OE		(1 << 11)  /* system clock enable */
 #define TEGRA_POWER_EFFECT_LP0		(1 << 14)  /* LP0 when CPU pwr gated */
 #define TEGRA_POWER_CPU_PWRREQ_POLARITY	(1 << 15)  /* CPU pwr req polarity */
 #define TEGRA_POWER_CPU_PWRREQ_OE	(1 << 16)  /* CPU pwr req enable */
@@ -193,16 +196,50 @@ enum tegra_suspend_mode tegra_pmc_get_suspend_mode(void)
 	return pmc_pm_data.suspend_mode;
 }
 
+void tegra_pmc_set_suspend_mode(enum tegra_suspend_mode mode)
+{
+	if (mode < TEGRA_SUSPEND_NONE || mode >= TEGRA_MAX_SUSPEND_MODE)
+		return;
+
+	pmc_pm_data.suspend_mode = mode;
+}
+
+void tegra_pmc_suspend(void)
+{
+	tegra_pmc_writel(virt_to_phys(tegra_resume), PMC_SCRATCH41);
+}
+
+void tegra_pmc_resume(void)
+{
+	tegra_pmc_writel(0x0, PMC_SCRATCH41);
+}
+
 void tegra_pmc_pm_set(enum tegra_suspend_mode mode)
 {
-	u32 reg;
+	u32 reg, csr_reg;
 	unsigned long rate = 0;
 
 	reg = tegra_pmc_readl(PMC_CTRL);
 	reg |= TEGRA_POWER_CPU_PWRREQ_OE;
 	reg &= ~TEGRA_POWER_EFFECT_LP0;
 
+	switch (tegra_chip_id) {
+	case TEGRA20:
+	case TEGRA30:
+		break;
+	default:
+		/* Turn off CRAIL */
+		csr_reg = flowctrl_read_cpu_csr(0);
+		csr_reg &= ~FLOW_CTRL_CSR_ENABLE_EXT_MASK;
+		csr_reg |= FLOW_CTRL_CSR_ENABLE_EXT_CRAIL;
+		flowctrl_write_cpu_csr(0, csr_reg);
+		break;
+	}
+
 	switch (mode) {
+	case TEGRA_SUSPEND_LP1:
+		rate = 32768;
+		break;
 	case TEGRA_SUSPEND_LP2:
 		rate = clk_get_rate(tegra_pclk);
 		break;
@@ -224,6 +261,20 @@ void tegra_pmc_suspend_init(void)
 	reg = tegra_pmc_readl(PMC_CTRL);
 	reg |= TEGRA_POWER_CPU_PWRREQ_OE;
 	tegra_pmc_writel(reg, PMC_CTRL);
+
+	reg = tegra_pmc_readl(PMC_CTRL);
+
+	if (!pmc_pm_data.sysclkreq_high)
+		reg |= TEGRA_POWER_SYSCLK_POLARITY;
+	else
+		reg &= ~TEGRA_POWER_SYSCLK_POLARITY;
+
+	/* configure the output polarity while the request is tristated */
+	tegra_pmc_writel(reg, PMC_CTRL);
+
+	/* now enable the request */
+	reg |= TEGRA_POWER_SYSCLK_OE;
+	tegra_pmc_writel(reg, PMC_CTRL);
 }
 #endif
 
diff --git a/arch/arm/mach-tegra/pmc.h b/arch/arm/mach-tegra/pmc.h
index e1c2df272f7d..549f8c7b762c 100644
--- a/arch/arm/mach-tegra/pmc.h
+++ b/arch/arm/mach-tegra/pmc.h
@@ -28,6 +28,9 @@ enum tegra_suspend_mode {
 
 #ifdef CONFIG_PM_SLEEP
 enum tegra_suspend_mode tegra_pmc_get_suspend_mode(void);
+void tegra_pmc_set_suspend_mode(enum tegra_suspend_mode mode);
+void tegra_pmc_suspend(void);
+void tegra_pmc_resume(void);
 void tegra_pmc_pm_set(enum tegra_suspend_mode mode);
 void tegra_pmc_suspend_init(void);
 #endif
diff --git a/arch/arm/mach-tegra/reset-handler.S b/arch/arm/mach-tegra/reset-handler.S
index 39dc9e7834f3..f527b2c2dea7 100644
--- a/arch/arm/mach-tegra/reset-handler.S
+++ b/arch/arm/mach-tegra/reset-handler.S
@@ -40,9 +40,12 @@
  *	  re-enabling sdram.
  *
  *	r6: SoC ID
+ *	r8: CPU part number
  */
 ENTRY(tegra_resume)
-	bl	v7_invalidate_l1
+	check_cpu_part_num 0xc09, r8, r9
+	bleq	v7_invalidate_l1
+	blne	tegra_init_l2_for_a15
 
 	cpu_id	r0
 	tegra_get_soc_id TEGRA_APB_MISC_BASE, r6
@@ -70,7 +73,8 @@ no_cpu0_chk:
 	str	r1, [r2]
 1:
 
-	check_cpu_part_num 0xc09, r8, r9
+	mov32	r9, 0xc09
+	cmp	r8, r9
 	bne	not_ca9
 #ifdef CONFIG_HAVE_ARM_SCU
 	/* enable SCU */
@@ -178,6 +182,19 @@ after_errata:
 1:
 #endif
 
+	/* Waking up from LP1? */
+	ldr	r8, [r12, #RESET_DATA(MASK_LP1)]
+	tst	r8, r11				@ if in_lp1
+	beq	__is_not_lp1
+	cmp	r10, #0
+	bne	__die				@ only CPU0 can be here
+	ldr	lr, [r12, #RESET_DATA(STARTUP_LP1)]
+	cmp	lr, #0
+	bleq	__die				@ no LP1 startup handler
+ THUMB(	add	lr, lr, #1 )			@ switch to Thumb mode
+	bx	lr
+__is_not_lp1:
+
 	/* Waking up from LP2? */
 	ldr	r9, [r12, #RESET_DATA(MASK_LP2)]
 	tst	r9, r11				@ if in_lp2
diff --git a/arch/arm/mach-tegra/reset.c b/arch/arm/mach-tegra/reset.c
index 1ac434e0068f..fd0bbf8a6c94 100644
--- a/arch/arm/mach-tegra/reset.c
+++ b/arch/arm/mach-tegra/reset.c
@@ -81,6 +81,8 @@ void __init tegra_cpu_reset_handler_init(void)
 #endif
 
 #ifdef CONFIG_PM_SLEEP
+	__tegra_cpu_reset_handler_data[TEGRA_RESET_STARTUP_LP1] =
+		TEGRA_IRAM_CODE_AREA;
 	__tegra_cpu_reset_handler_data[TEGRA_RESET_STARTUP_LP2] =
 		virt_to_phys((void *)tegra_resume);
 #endif
diff --git a/arch/arm/mach-tegra/reset.h b/arch/arm/mach-tegra/reset.h
index c90d8e9c4ad2..76a93434c6ee 100644
--- a/arch/arm/mach-tegra/reset.h
+++ b/arch/arm/mach-tegra/reset.h
@@ -39,6 +39,10 @@ void __tegra_cpu_reset_handler_end(void);
 void tegra_secondary_startup(void);
 
 #ifdef CONFIG_PM_SLEEP
+#define tegra_cpu_lp1_mask \
+	(IO_ADDRESS(TEGRA_IRAM_BASE + TEGRA_IRAM_RESET_HANDLER_OFFSET + \
+	((u32)&__tegra_cpu_reset_handler_data[TEGRA_RESET_MASK_LP1] - \
+	 (u32)__tegra_cpu_reset_handler_start)))
 #define tegra_cpu_lp2_mask \
 	(IO_ADDRESS(TEGRA_IRAM_BASE + TEGRA_IRAM_RESET_HANDLER_OFFSET + \
 	((u32)&__tegra_cpu_reset_handler_data[TEGRA_RESET_MASK_LP2] - \
diff --git a/arch/arm/mach-tegra/sleep-tegra20.S b/arch/arm/mach-tegra/sleep-tegra20.S
index e3f2417c420e..5c3bd11c9838 100644
--- a/arch/arm/mach-tegra/sleep-tegra20.S
+++ b/arch/arm/mach-tegra/sleep-tegra20.S
@@ -23,10 +23,49 @@
 #include <asm/assembler.h>
 #include <asm/proc-fns.h>
 #include <asm/cp15.h>
+#include <asm/cache.h>
 
 #include "sleep.h"
 #include "flowctrl.h"
 
+#define EMC_CFG				0xc
+#define EMC_ADR_CFG			0x10
+#define EMC_REFRESH			0x70
+#define EMC_NOP				0xdc
+#define EMC_SELF_REF			0xe0
+#define EMC_REQ_CTRL			0x2b0
+#define EMC_EMC_STATUS			0x2b4
+
+#define CLK_RESET_CCLK_BURST		0x20
+#define CLK_RESET_CCLK_DIVIDER		0x24
+#define CLK_RESET_SCLK_BURST		0x28
+#define CLK_RESET_SCLK_DIVIDER		0x2c
+#define CLK_RESET_PLLC_BASE		0x80
+#define CLK_RESET_PLLM_BASE		0x90
+#define CLK_RESET_PLLP_BASE		0xa0
+
+#define APB_MISC_XM2CFGCPADCTRL		0x8c8
+#define APB_MISC_XM2CFGDPADCTRL		0x8cc
+#define APB_MISC_XM2CLKCFGPADCTRL	0x8d0
+#define APB_MISC_XM2COMPPADCTRL		0x8d4
+#define APB_MISC_XM2VTTGENPADCTRL	0x8d8
+#define APB_MISC_XM2CFGCPADCTRL2	0x8e4
+#define APB_MISC_XM2CFGDPADCTRL2	0x8e8
+
+.macro pll_enable, rd, r_car_base, pll_base
+	ldr	\rd, [\r_car_base, #\pll_base]
+	tst	\rd, #(1 << 30)
+	orreq	\rd, \rd, #(1 << 30)
+	streq	\rd, [\r_car_base, #\pll_base]
+.endm
+
+.macro emc_device_mask, rd, base
+	ldr	\rd, [\base, #EMC_ADR_CFG]
+	tst	\rd, #(0x3 << 24)
+	moveq	\rd, #(0x1 << 8)		@ just 1 device
+	movne	\rd, #(0x3 << 8)		@ 2 devices
+.endm
+
 #if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_PM_SLEEP)
 /*
  * tegra20_hotplug_shutdown(void)
@@ -181,6 +220,28 @@ ENTRY(tegra20_cpu_is_resettable_soon)
 ENDPROC(tegra20_cpu_is_resettable_soon)
 
 /*
+ * tegra20_sleep_core_finish(unsigned long v2p)
+ *
+ * Enters suspend in LP0 or LP1 by turning off the mmu and jumping to
+ * tegra20_tear_down_core in IRAM
+ */
+ENTRY(tegra20_sleep_core_finish)
+	/* Flush, disable the L1 data cache and exit SMP */
+	bl	tegra_disable_clean_inv_dcache
+
+	mov32	r3, tegra_shut_off_mmu
+	add	r3, r3, r0
+
+	mov32	r0, tegra20_tear_down_core
+	mov32	r1, tegra20_iram_start
+	sub	r0, r0, r1
+	mov32	r1, TEGRA_IRAM_CODE_AREA
+	add	r0, r0, r1
+
+	mov	pc, r3
+ENDPROC(tegra20_sleep_core_finish)
+
+/*
  * tegra20_sleep_cpu_secondary_finish(unsigned long v2p)
  *
  * Enters WFI on secondary CPU by exiting coherency.
@@ -191,6 +252,7 @@ ENTRY(tegra20_sleep_cpu_secondary_finish)
 	mrc	p15, 0, r11, c1, c0, 1  @ save actlr before exiting coherency
 
 	/* Flush and disable the L1 data cache */
+	mov	r0, #TEGRA_FLUSH_CACHE_LOUIS
 	bl	tegra_disable_clean_inv_dcache
 
 	mov32	r0, TEGRA_PMC_VIRT + PMC_SCRATCH41
@@ -250,6 +312,150 @@ ENTRY(tegra20_tear_down_cpu)
 	b	tegra20_enter_sleep
 ENDPROC(tegra20_tear_down_cpu)
 
+/* START OF ROUTINES COPIED TO IRAM */
+	.align L1_CACHE_SHIFT
+	.globl tegra20_iram_start
+tegra20_iram_start:
+
+/*
+ * tegra20_lp1_reset
+ *
+ * reset vector for LP1 restore; copied into IRAM during suspend.
+ * Brings the system back up to a safe staring point (SDRAM out of
+ * self-refresh, PLLC, PLLM and PLLP reenabled, CPU running on PLLP,
+ * system clock running on the same PLL that it suspended at), and
+ * jumps to tegra_resume to restore virtual addressing and PLLX.
+ * The physical address of tegra_resume expected to be stored in
+ * PMC_SCRATCH41.
+ *
+ * NOTE: THIS *MUST* BE RELOCATED TO TEGRA_IRAM_CODE_AREA.
+ */
+ENTRY(tegra20_lp1_reset)
+	/*
+	 * The CPU and system bus are running at 32KHz and executing from
+	 * IRAM when this code is executed; immediately switch to CLKM and
+	 * enable PLLM, PLLP, PLLC.
+	 */
+	mov32	r0, TEGRA_CLK_RESET_BASE
+
+	mov	r1, #(1 << 28)
+	str	r1, [r0, #CLK_RESET_SCLK_BURST]
+	str	r1, [r0, #CLK_RESET_CCLK_BURST]
+	mov	r1, #0
+	str	r1, [r0, #CLK_RESET_CCLK_DIVIDER]
+	str	r1, [r0, #CLK_RESET_SCLK_DIVIDER]
+
+	pll_enable r1, r0, CLK_RESET_PLLM_BASE
+	pll_enable r1, r0, CLK_RESET_PLLP_BASE
+	pll_enable r1, r0, CLK_RESET_PLLC_BASE
+
+	adr	r2, tegra20_sdram_pad_address
+	adr	r4, tegra20_sdram_pad_save
+	mov	r5, #0
+
+	ldr	r6, tegra20_sdram_pad_size
+padload:
+	ldr	r7, [r2, r5]		@ r7 is the addr in the pad_address
+
+	ldr	r1, [r4, r5]
+	str	r1, [r7]		@ restore the value in pad_save
+
+	add	r5, r5, #4
+	cmp	r6, r5
+	bne	padload
+
+padload_done:
+	/* 255uS delay for PLL stabilization */
+	mov32	r7, TEGRA_TMRUS_BASE
+	ldr	r1, [r7]
+	add	r1, r1, #0xff
+	wait_until r1, r7, r9
+
+	adr	r4, tegra20_sclk_save
+	ldr	r4, [r4]
+	str	r4, [r0, #CLK_RESET_SCLK_BURST]
+	mov32	r4, ((1 << 28) | (4))	@ burst policy is PLLP
+	str	r4, [r0, #CLK_RESET_CCLK_BURST]
+
+	mov32	r0, TEGRA_EMC_BASE
+	ldr	r1, [r0, #EMC_CFG]
+	bic	r1, r1, #(1 << 31)	@ disable DRAM_CLK_STOP
+	str	r1, [r0, #EMC_CFG]
+
+	mov	r1, #0
+	str	r1, [r0, #EMC_SELF_REF]	@ take DRAM out of self refresh
+	mov	r1, #1
+	str	r1, [r0, #EMC_NOP]
+	str	r1, [r0, #EMC_NOP]
+	str	r1, [r0, #EMC_REFRESH]
+
+	emc_device_mask r1, r0
+
+exit_selfrefresh_loop:
+	ldr	r2, [r0, #EMC_EMC_STATUS]
+	ands	r2, r2, r1
+	bne	exit_selfrefresh_loop
+
+	mov	r1, #0			@ unstall all transactions
+	str	r1, [r0, #EMC_REQ_CTRL]
+
+	mov32	r0, TEGRA_PMC_BASE
+	ldr	r0, [r0, #PMC_SCRATCH41]
+	mov	pc, r0			@ jump to tegra_resume
+ENDPROC(tegra20_lp1_reset)
+
+/*
+ * tegra20_tear_down_core
+ *
+ * copied into and executed from IRAM
+ * puts memory in self-refresh for LP0 and LP1
+ */
+tegra20_tear_down_core:
+	bl	tegra20_sdram_self_refresh
+	bl	tegra20_switch_cpu_to_clk32k
+	b	tegra20_enter_sleep
+
+/*
+ * tegra20_switch_cpu_to_clk32k
+ *
+ * In LP0 and LP1 all PLLs will be turned off. Switch the CPU and system clock
+ * to the 32KHz clock.
+ */
+tegra20_switch_cpu_to_clk32k:
+	/*
+	 * start by switching to CLKM to safely disable PLLs, then switch to
+	 * CLKS.
+	 */
+	mov	r0, #(1 << 28)
+	str	r0, [r5, #CLK_RESET_SCLK_BURST]
+	str	r0, [r5, #CLK_RESET_CCLK_BURST]
+	mov	r0, #0
+	str	r0, [r5, #CLK_RESET_CCLK_DIVIDER]
+	str	r0, [r5, #CLK_RESET_SCLK_DIVIDER]
+
+	/* 2uS delay delay between changing SCLK and disabling PLLs */
+	mov32	r7, TEGRA_TMRUS_BASE
+	ldr	r1, [r7]
+	add	r1, r1, #2
+	wait_until r1, r7, r9
+
+	/* disable PLLM, PLLP and PLLC */
+	ldr	r0, [r5, #CLK_RESET_PLLM_BASE]
+	bic	r0, r0, #(1 << 30)
+	str	r0, [r5, #CLK_RESET_PLLM_BASE]
+	ldr	r0, [r5, #CLK_RESET_PLLP_BASE]
+	bic	r0, r0, #(1 << 30)
+	str	r0, [r5, #CLK_RESET_PLLP_BASE]
+	ldr	r0, [r5, #CLK_RESET_PLLC_BASE]
+	bic	r0, r0, #(1 << 30)
+	str	r0, [r5, #CLK_RESET_PLLC_BASE]
+
+	/* switch to CLKS */
+	mov	r0, #0	/* brust policy = 32KHz */
+	str	r0, [r5, #CLK_RESET_SCLK_BURST]
+
+	mov	pc, lr
+
 /*
  * tegra20_enter_sleep
  *
@@ -274,4 +480,95 @@ halted:
 	isb
 	b	halted
 
+/*
+ * tegra20_sdram_self_refresh
+ *
+ * called with MMU off and caches disabled
+ * puts sdram in self refresh
+ * must be executed from IRAM
+ */
+tegra20_sdram_self_refresh:
+	mov32	r1, TEGRA_EMC_BASE	@ r1 reserved for emc base addr
+
+	mov	r2, #3
+	str	r2, [r1, #EMC_REQ_CTRL]	@ stall incoming DRAM requests
+
+emcidle:
+	ldr	r2, [r1, #EMC_EMC_STATUS]
+	tst	r2, #4
+	beq	emcidle
+
+	mov	r2, #1
+	str	r2, [r1, #EMC_SELF_REF]
+
+	emc_device_mask r2, r1
+
+emcself:
+	ldr	r3, [r1, #EMC_EMC_STATUS]
+	and	r3, r3, r2
+	cmp	r3, r2
+	bne	emcself			@ loop until DDR in self-refresh
+
+	adr	r2, tegra20_sdram_pad_address
+	adr	r3, tegra20_sdram_pad_safe
+	adr	r4, tegra20_sdram_pad_save
+	mov	r5, #0
+
+	ldr	r6, tegra20_sdram_pad_size
+padsave:
+	ldr	r0, [r2, r5]		@ r0 is the addr in the pad_address
+
+	ldr	r1, [r0]
+	str	r1, [r4, r5]		@ save the content of the addr
+
+	ldr	r1, [r3, r5]
+	str	r1, [r0]		@ set the save val to the addr
+
+	add	r5, r5, #4
+	cmp	r6, r5
+	bne	padsave
+padsave_done:
+
+	mov32	r5, TEGRA_CLK_RESET_BASE
+	ldr	r0, [r5, #CLK_RESET_SCLK_BURST]
+	adr	r2, tegra20_sclk_save
+	str	r0, [r2]
+	dsb
+	mov	pc, lr
+
+tegra20_sdram_pad_address:
+	.word	TEGRA_APB_MISC_BASE + APB_MISC_XM2CFGCPADCTRL
+	.word	TEGRA_APB_MISC_BASE + APB_MISC_XM2CFGDPADCTRL
+	.word	TEGRA_APB_MISC_BASE + APB_MISC_XM2CLKCFGPADCTRL
+	.word	TEGRA_APB_MISC_BASE + APB_MISC_XM2COMPPADCTRL
+	.word	TEGRA_APB_MISC_BASE + APB_MISC_XM2VTTGENPADCTRL
+	.word	TEGRA_APB_MISC_BASE + APB_MISC_XM2CFGCPADCTRL2
+	.word	TEGRA_APB_MISC_BASE + APB_MISC_XM2CFGDPADCTRL2
+
+tegra20_sdram_pad_size:
+	.word	tegra20_sdram_pad_size - tegra20_sdram_pad_address
+
+tegra20_sdram_pad_safe:
+	.word	0x8
+	.word	0x8
+	.word	0x0
+	.word	0x8
+	.word	0x5500
+	.word	0x08080040
+	.word	0x0
+
+tegra20_sclk_save:
+	.word	0x0
+
+tegra20_sdram_pad_save:
+	.rept (tegra20_sdram_pad_size - tegra20_sdram_pad_address) / 4
+	.long	0
+	.endr
+
+	.ltorg
+/* dummy symbol for end of IRAM */
+	.align L1_CACHE_SHIFT
+	.globl tegra20_iram_end
+tegra20_iram_end:
+	b	.
 #endif
diff --git a/arch/arm/mach-tegra/sleep-tegra30.S b/arch/arm/mach-tegra/sleep-tegra30.S
index ada8821b48be..63fa91b5fafb 100644
--- a/arch/arm/mach-tegra/sleep-tegra30.S
+++ b/arch/arm/mach-tegra/sleep-tegra30.S
@@ -18,13 +18,118 @@
 
 #include <asm/assembler.h>
 #include <asm/asm-offsets.h>
+#include <asm/cache.h>
 
 #include "fuse.h"
 #include "sleep.h"
 #include "flowctrl.h"
 
+#define EMC_CFG				0xc
+#define EMC_ADR_CFG			0x10
+#define EMC_TIMING_CONTROL		0x28
+#define EMC_REFRESH			0x70
+#define EMC_NOP				0xdc
+#define EMC_SELF_REF			0xe0
+#define EMC_MRW				0xe8
+#define EMC_FBIO_CFG5			0x104
+#define EMC_AUTO_CAL_CONFIG		0x2a4
+#define EMC_AUTO_CAL_INTERVAL		0x2a8
+#define EMC_AUTO_CAL_STATUS		0x2ac
+#define EMC_REQ_CTRL			0x2b0
+#define EMC_CFG_DIG_DLL			0x2bc
+#define EMC_EMC_STATUS			0x2b4
+#define EMC_ZCAL_INTERVAL		0x2e0
+#define EMC_ZQ_CAL			0x2ec
+#define EMC_XM2VTTGENPADCTRL		0x310
+#define EMC_XM2VTTGENPADCTRL2		0x314
+
+#define PMC_CTRL			0x0
+#define PMC_CTRL_SIDE_EFFECT_LP0 (1 << 14) /* enter LP0 when CPU pwr gated */
+
+#define PMC_PLLP_WB0_OVERRIDE		0xf8
+#define PMC_IO_DPD_REQ			0x1b8
+#define PMC_IO_DPD_STATUS		0x1bc
+
+#define CLK_RESET_CCLK_BURST		0x20
+#define CLK_RESET_CCLK_DIVIDER		0x24
+#define CLK_RESET_SCLK_BURST		0x28
+#define CLK_RESET_SCLK_DIVIDER		0x2c
+
+#define CLK_RESET_PLLC_BASE		0x80
+#define CLK_RESET_PLLC_MISC		0x8c
+#define CLK_RESET_PLLM_BASE		0x90
+#define CLK_RESET_PLLM_MISC		0x9c
+#define CLK_RESET_PLLP_BASE		0xa0
+#define CLK_RESET_PLLP_MISC		0xac
+#define CLK_RESET_PLLA_BASE		0xb0
+#define CLK_RESET_PLLA_MISC		0xbc
+#define CLK_RESET_PLLX_BASE		0xe0
+#define CLK_RESET_PLLX_MISC		0xe4
+#define CLK_RESET_PLLX_MISC3		0x518
+#define CLK_RESET_PLLX_MISC3_IDDQ	3
+#define CLK_RESET_PLLM_MISC_IDDQ	5
+#define CLK_RESET_PLLC_MISC_IDDQ	26
+
+#define CLK_RESET_CLK_SOURCE_MSELECT	0x3b4
+
+#define MSELECT_CLKM			(0x3 << 30)
+
+#define LOCK_DELAY 50 /* safety delay after lock is detected */
+
 #define TEGRA30_POWER_HOTPLUG_SHUTDOWN	(1 << 27) /* Hotplug shutdown */
 
+.macro emc_device_mask, rd, base
+	ldr	\rd, [\base, #EMC_ADR_CFG]
+	tst	\rd, #0x1
+	moveq	\rd, #(0x1 << 8)		@ just 1 device
+	movne	\rd, #(0x3 << 8)		@ 2 devices
+.endm
+
+.macro emc_timing_update, rd, base
+	mov	\rd, #1
+	str	\rd, [\base, #EMC_TIMING_CONTROL]
+1001:
+	ldr	\rd, [\base, #EMC_EMC_STATUS]
+	tst	\rd, #(0x1<<23)	@ wait EMC_STATUS_TIMING_UPDATE_STALLED is clear
+	bne	1001b
+.endm
+
+.macro pll_enable, rd, r_car_base, pll_base, pll_misc
+	ldr	\rd, [\r_car_base, #\pll_base]
+	tst	\rd, #(1 << 30)
+	orreq	\rd, \rd, #(1 << 30)
+	streq	\rd, [\r_car_base, #\pll_base]
+	/* Enable lock detector */
+	.if	\pll_misc
+	ldr	\rd, [\r_car_base, #\pll_misc]
+	bic	\rd, \rd, #(1 << 18)
+	str	\rd, [\r_car_base, #\pll_misc]
+	ldr	\rd, [\r_car_base, #\pll_misc]
+	ldr	\rd, [\r_car_base, #\pll_misc]
+	orr	\rd, \rd, #(1 << 18)
+	str	\rd, [\r_car_base, #\pll_misc]
+	.endif
+.endm
+
+.macro pll_locked, rd, r_car_base, pll_base
+1:
+	ldr	\rd, [\r_car_base, #\pll_base]
+	tst	\rd, #(1 << 27)
+	beq	1b
+.endm
+
+.macro pll_iddq_exit, rd, car, iddq, iddq_bit
+	ldr	\rd, [\car, #\iddq]
+	bic	\rd, \rd, #(1<<\iddq_bit)
+	str	\rd, [\car, #\iddq]
+.endm
+
+.macro pll_iddq_entry, rd, car, iddq, iddq_bit
+	ldr	\rd, [\car, #\iddq]
+	orr	\rd, \rd, #(1<<\iddq_bit)
+	str	\rd, [\car, #\iddq]
+.endm
+
 #if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_PM_SLEEP)
 /*
  * tegra30_hotplug_shutdown(void)
@@ -99,6 +204,8 @@ flow_ctrl_setting_for_lp2:
 	cmp	r10, #TEGRA30
 	moveq   r3, #FLOW_CTRL_WAIT_FOR_INTERRUPT	@ For LP2
 	movne	r3, #FLOW_CTRL_WAITEVENT
+	orrne	r3, r3, #FLOW_CTRL_HALT_GIC_IRQ
+	orrne	r3, r3, #FLOW_CTRL_HALT_GIC_FIQ
 flow_ctrl_done:
 	cmp	r10, #TEGRA30
 	str	r3, [r2]
@@ -127,6 +234,41 @@ ENDPROC(tegra30_cpu_shutdown)
 
 #ifdef CONFIG_PM_SLEEP
 /*
+ * tegra30_sleep_core_finish(unsigned long v2p)
+ *
+ * Enters suspend in LP0 or LP1 by turning off the MMU and jumping to
+ * tegra30_tear_down_core in IRAM
+ */
+ENTRY(tegra30_sleep_core_finish)
+	/* Flush, disable the L1 data cache and exit SMP */
+	bl	tegra_disable_clean_inv_dcache
+
+	/*
+	 * Preload all the address literals that are needed for the
+	 * CPU power-gating process, to avoid loading from SDRAM which
+	 * are not supported once SDRAM is put into self-refresh.
+	 * LP0 / LP1 use physical address, since the MMU needs to be
+	 * disabled before putting SDRAM into self-refresh to avoid
+	 * memory access due to page table walks.
+	 */
+	mov32	r4, TEGRA_PMC_BASE
+	mov32	r5, TEGRA_CLK_RESET_BASE
+	mov32	r6, TEGRA_FLOW_CTRL_BASE
+	mov32	r7, TEGRA_TMRUS_BASE
+
+	mov32	r3, tegra_shut_off_mmu
+	add	r3, r3, r0
+
+	mov32	r0, tegra30_tear_down_core
+	mov32	r1, tegra30_iram_start
+	sub	r0, r0, r1
+	mov32	r1, TEGRA_IRAM_CODE_AREA
+	add	r0, r0, r1
+
+	mov	pc, r3
+ENDPROC(tegra30_sleep_core_finish)
+
+/*
  * tegra30_sleep_cpu_secondary_finish(unsigned long v2p)
  *
  * Enters LP2 on secondary CPU by exiting coherency and powergating the CPU.
@@ -135,6 +277,7 @@ ENTRY(tegra30_sleep_cpu_secondary_finish)
 	mov	r7, lr
 
 	/* Flush and disable the L1 data cache */
+	mov 	r0, #TEGRA_FLUSH_CACHE_LOUIS
 	bl	tegra_disable_clean_inv_dcache
 
 	/* Powergate this CPU. */
@@ -155,6 +298,351 @@ ENTRY(tegra30_tear_down_cpu)
 	b	tegra30_enter_sleep
 ENDPROC(tegra30_tear_down_cpu)
 
+/* START OF ROUTINES COPIED TO IRAM */
+	.align L1_CACHE_SHIFT
+	.globl tegra30_iram_start
+tegra30_iram_start:
+
+/*
+ * tegra30_lp1_reset
+ *
+ * reset vector for LP1 restore; copied into IRAM during suspend.
+ * Brings the system back up to a safe staring point (SDRAM out of
+ * self-refresh, PLLC, PLLM and PLLP reenabled, CPU running on PLLX,
+ * system clock running on the same PLL that it suspended at), and
+ * jumps to tegra_resume to restore virtual addressing.
+ * The physical address of tegra_resume expected to be stored in
+ * PMC_SCRATCH41.
+ *
+ * NOTE: THIS *MUST* BE RELOCATED TO TEGRA_IRAM_CODE_AREA.
+ */
+ENTRY(tegra30_lp1_reset)
+	/*
+	 * The CPU and system bus are running at 32KHz and executing from
+	 * IRAM when this code is executed; immediately switch to CLKM and
+	 * enable PLLP, PLLM, PLLC, PLLA and PLLX.
+	 */
+	mov32	r0, TEGRA_CLK_RESET_BASE
+
+	mov	r1, #(1 << 28)
+	str	r1, [r0, #CLK_RESET_SCLK_BURST]
+	str	r1, [r0, #CLK_RESET_CCLK_BURST]
+	mov	r1, #0
+	str	r1, [r0, #CLK_RESET_CCLK_DIVIDER]
+	str	r1, [r0, #CLK_RESET_SCLK_DIVIDER]
+
+	tegra_get_soc_id TEGRA_APB_MISC_BASE, r10
+	cmp	r10, #TEGRA30
+	beq	_no_pll_iddq_exit
+
+	pll_iddq_exit r1, r0, CLK_RESET_PLLM_MISC, CLK_RESET_PLLM_MISC_IDDQ
+	pll_iddq_exit r1, r0, CLK_RESET_PLLC_MISC, CLK_RESET_PLLC_MISC_IDDQ
+	pll_iddq_exit r1, r0, CLK_RESET_PLLX_MISC3, CLK_RESET_PLLX_MISC3_IDDQ
+
+	mov32	r7, TEGRA_TMRUS_BASE
+	ldr	r1, [r7]
+	add	r1, r1, #2
+	wait_until r1, r7, r3
+
+	/* enable PLLM via PMC */
+	mov32	r2, TEGRA_PMC_BASE
+	ldr	r1, [r2, #PMC_PLLP_WB0_OVERRIDE]
+	orr	r1, r1, #(1 << 12)
+	str	r1, [r2, #PMC_PLLP_WB0_OVERRIDE]
+
+	pll_enable r1, r0, CLK_RESET_PLLM_BASE, 0
+	pll_enable r1, r0, CLK_RESET_PLLC_BASE, 0
+	pll_enable r1, r0, CLK_RESET_PLLX_BASE, 0
+
+	b	_pll_m_c_x_done
+
+_no_pll_iddq_exit:
+	/* enable PLLM via PMC */
+	mov32	r2, TEGRA_PMC_BASE
+	ldr	r1, [r2, #PMC_PLLP_WB0_OVERRIDE]
+	orr	r1, r1, #(1 << 12)
+	str	r1, [r2, #PMC_PLLP_WB0_OVERRIDE]
+
+	pll_enable r1, r0, CLK_RESET_PLLM_BASE, CLK_RESET_PLLM_MISC
+	pll_enable r1, r0, CLK_RESET_PLLC_BASE, CLK_RESET_PLLC_MISC
+	pll_enable r1, r0, CLK_RESET_PLLX_BASE, CLK_RESET_PLLX_MISC
+
+_pll_m_c_x_done:
+	pll_enable r1, r0, CLK_RESET_PLLP_BASE, CLK_RESET_PLLP_MISC
+	pll_enable r1, r0, CLK_RESET_PLLA_BASE, CLK_RESET_PLLA_MISC
+
+	pll_locked r1, r0, CLK_RESET_PLLM_BASE
+	pll_locked r1, r0, CLK_RESET_PLLP_BASE
+	pll_locked r1, r0, CLK_RESET_PLLA_BASE
+	pll_locked r1, r0, CLK_RESET_PLLC_BASE
+	pll_locked r1, r0, CLK_RESET_PLLX_BASE
+
+	mov32	r7, TEGRA_TMRUS_BASE
+	ldr	r1, [r7]
+	add	r1, r1, #LOCK_DELAY
+	wait_until r1, r7, r3
+
+	adr	r5, tegra30_sdram_pad_save
+
+	ldr	r4, [r5, #0x18]		@ restore CLK_SOURCE_MSELECT
+	str	r4, [r0, #CLK_RESET_CLK_SOURCE_MSELECT]
+
+	ldr	r4, [r5, #0x1C]		@ restore SCLK_BURST
+	str	r4, [r0, #CLK_RESET_SCLK_BURST]
+
+	cmp	r10, #TEGRA30
+	movweq	r4, #:lower16:((1 << 28) | (0x8))	@ burst policy is PLLX
+	movteq	r4, #:upper16:((1 << 28) | (0x8))
+	movwne	r4, #:lower16:((1 << 28) | (0xe))
+	movtne	r4, #:upper16:((1 << 28) | (0xe))
+	str	r4, [r0, #CLK_RESET_CCLK_BURST]
+
+	/* Restore pad power state to normal */
+	ldr	r1, [r5, #0x14]		@ PMC_IO_DPD_STATUS
+	mvn	r1, r1
+	bic	r1, r1, #(1 << 31)
+	orr	r1, r1, #(1 << 30)
+	str	r1, [r2, #PMC_IO_DPD_REQ]	@ DPD_OFF
+
+	cmp	r10, #TEGRA30
+	movweq	r0, #:lower16:TEGRA_EMC_BASE	@ r0 reserved for emc base
+	movteq	r0, #:upper16:TEGRA_EMC_BASE
+	movwne	r0, #:lower16:TEGRA_EMC0_BASE
+	movtne	r0, #:upper16:TEGRA_EMC0_BASE
+
+exit_self_refresh:
+	ldr	r1, [r5, #0xC]		@ restore EMC_XM2VTTGENPADCTRL
+	str	r1, [r0, #EMC_XM2VTTGENPADCTRL]
+	ldr	r1, [r5, #0x10]		@ restore EMC_XM2VTTGENPADCTRL2
+	str	r1, [r0, #EMC_XM2VTTGENPADCTRL2]
+	ldr	r1, [r5, #0x8]		@ restore EMC_AUTO_CAL_INTERVAL
+	str	r1, [r0, #EMC_AUTO_CAL_INTERVAL]
+
+	/* Relock DLL */
+	ldr	r1, [r0, #EMC_CFG_DIG_DLL]
+	orr	r1, r1, #(1 << 30)	@ set DLL_RESET
+	str	r1, [r0, #EMC_CFG_DIG_DLL]
+
+	emc_timing_update r1, r0
+
+	cmp	r10, #TEGRA114
+	movweq	r1, #:lower16:TEGRA_EMC1_BASE
+	movteq	r1, #:upper16:TEGRA_EMC1_BASE
+	cmpeq	r0, r1
+
+	ldr	r1, [r0, #EMC_AUTO_CAL_CONFIG]
+	orr	r1, r1, #(1 << 31)	@ set AUTO_CAL_ACTIVE
+	orreq	r1, r1, #(1 << 27)	@ set slave mode for channel 1
+	str	r1, [r0, #EMC_AUTO_CAL_CONFIG]
+
+emc_wait_auto_cal_onetime:
+	ldr	r1, [r0, #EMC_AUTO_CAL_STATUS]
+	tst	r1, #(1 << 31)		@ wait until AUTO_CAL_ACTIVE is cleared
+	bne	emc_wait_auto_cal_onetime
+
+	ldr	r1, [r0, #EMC_CFG]
+	bic	r1, r1, #(1 << 31)	@ disable DRAM_CLK_STOP_PD
+	str	r1, [r0, #EMC_CFG]
+
+	mov	r1, #0
+	str	r1, [r0, #EMC_SELF_REF]	@ take DRAM out of self refresh
+	mov	r1, #1
+	cmp	r10, #TEGRA30
+	streq	r1, [r0, #EMC_NOP]
+	streq	r1, [r0, #EMC_NOP]
+	streq	r1, [r0, #EMC_REFRESH]
+
+	emc_device_mask r1, r0
+
+exit_selfrefresh_loop:
+	ldr	r2, [r0, #EMC_EMC_STATUS]
+	ands	r2, r2, r1
+	bne	exit_selfrefresh_loop
+
+	lsr	r1, r1, #8		@ devSel, bit0:dev0, bit1:dev1
+
+	mov32	r7, TEGRA_TMRUS_BASE
+	ldr	r2, [r0, #EMC_FBIO_CFG5]
+
+	and	r2, r2,	#3		@ check DRAM_TYPE
+	cmp	r2, #2
+	beq	emc_lpddr2
+
+	/* Issue a ZQ_CAL for dev0 - DDR3 */
+	mov32	r2, 0x80000011		@ DEV_SELECTION=2, LENGTH=LONG, CMD=1
+	str	r2, [r0, #EMC_ZQ_CAL]
+	ldr	r2, [r7]
+	add	r2, r2, #10
+	wait_until r2, r7, r3
+
+	tst	r1, #2
+	beq	zcal_done
+
+	/* Issue a ZQ_CAL for dev1 - DDR3 */
+	mov32	r2, 0x40000011		@ DEV_SELECTION=1, LENGTH=LONG, CMD=1
+	str	r2, [r0, #EMC_ZQ_CAL]
+	ldr	r2, [r7]
+	add	r2, r2, #10
+	wait_until r2, r7, r3
+	b	zcal_done
+
+emc_lpddr2:
+	/* Issue a ZQ_CAL for dev0 - LPDDR2 */
+	mov32	r2, 0x800A00AB		@ DEV_SELECTION=2, MA=10, OP=0xAB
+	str	r2, [r0, #EMC_MRW]
+	ldr	r2, [r7]
+	add	r2, r2, #1
+	wait_until r2, r7, r3
+
+	tst	r1, #2
+	beq	zcal_done
+
+	/* Issue a ZQ_CAL for dev0 - LPDDR2 */
+	mov32	r2, 0x400A00AB		@ DEV_SELECTION=1, MA=10, OP=0xAB
+	str	r2, [r0, #EMC_MRW]
+	ldr	r2, [r7]
+	add	r2, r2, #1
+	wait_until r2, r7, r3
+
+zcal_done:
+	mov	r1, #0			@ unstall all transactions
+	str	r1, [r0, #EMC_REQ_CTRL]
+	ldr	r1, [r5, #0x4]		@ restore EMC_ZCAL_INTERVAL
+	str	r1, [r0, #EMC_ZCAL_INTERVAL]
+	ldr	r1, [r5, #0x0]		@ restore EMC_CFG
+	str	r1, [r0, #EMC_CFG]
+
+	/* Tegra114 had dual EMC channel, now config the other one */
+	cmp	r10, #TEGRA114
+	bne	__no_dual_emc_chanl
+	mov32	r1, TEGRA_EMC1_BASE
+	cmp	r0, r1
+	movne	r0, r1
+	addne	r5, r5, #0x20
+	bne	exit_self_refresh
+__no_dual_emc_chanl:
+
+	mov32	r0, TEGRA_PMC_BASE
+	ldr	r0, [r0, #PMC_SCRATCH41]
+	mov	pc, r0			@ jump to tegra_resume
+ENDPROC(tegra30_lp1_reset)
+
+	.align	L1_CACHE_SHIFT
+tegra30_sdram_pad_address:
+	.word	TEGRA_EMC_BASE + EMC_CFG				@0x0
+	.word	TEGRA_EMC_BASE + EMC_ZCAL_INTERVAL			@0x4
+	.word	TEGRA_EMC_BASE + EMC_AUTO_CAL_INTERVAL			@0x8
+	.word	TEGRA_EMC_BASE + EMC_XM2VTTGENPADCTRL			@0xc
+	.word	TEGRA_EMC_BASE + EMC_XM2VTTGENPADCTRL2			@0x10
+	.word	TEGRA_PMC_BASE + PMC_IO_DPD_STATUS			@0x14
+	.word	TEGRA_CLK_RESET_BASE + CLK_RESET_CLK_SOURCE_MSELECT	@0x18
+	.word	TEGRA_CLK_RESET_BASE + CLK_RESET_SCLK_BURST		@0x1c
+
+tegra114_sdram_pad_address:
+	.word	TEGRA_EMC0_BASE + EMC_CFG				@0x0
+	.word	TEGRA_EMC0_BASE + EMC_ZCAL_INTERVAL			@0x4
+	.word	TEGRA_EMC0_BASE + EMC_AUTO_CAL_INTERVAL			@0x8
+	.word	TEGRA_EMC0_BASE + EMC_XM2VTTGENPADCTRL			@0xc
+	.word	TEGRA_EMC0_BASE + EMC_XM2VTTGENPADCTRL2			@0x10
+	.word	TEGRA_PMC_BASE + PMC_IO_DPD_STATUS			@0x14
+	.word	TEGRA_CLK_RESET_BASE + CLK_RESET_CLK_SOURCE_MSELECT	@0x18
+	.word	TEGRA_CLK_RESET_BASE + CLK_RESET_SCLK_BURST		@0x1c
+	.word	TEGRA_EMC1_BASE + EMC_CFG				@0x20
+	.word	TEGRA_EMC1_BASE + EMC_ZCAL_INTERVAL			@0x24
+	.word	TEGRA_EMC1_BASE + EMC_AUTO_CAL_INTERVAL			@0x28
+	.word	TEGRA_EMC1_BASE + EMC_XM2VTTGENPADCTRL			@0x2c
+	.word	TEGRA_EMC1_BASE + EMC_XM2VTTGENPADCTRL2			@0x30
+
+tegra30_sdram_pad_size:
+	.word	tegra114_sdram_pad_address - tegra30_sdram_pad_address
+
+tegra114_sdram_pad_size:
+	.word	tegra30_sdram_pad_size - tegra114_sdram_pad_address
+
+	.type	tegra30_sdram_pad_save, %object
+tegra30_sdram_pad_save:
+	.rept (tegra30_sdram_pad_size - tegra114_sdram_pad_address) / 4
+	.long	0
+	.endr
+
+/*
+ * tegra30_tear_down_core
+ *
+ * copied into and executed from IRAM
+ * puts memory in self-refresh for LP0 and LP1
+ */
+tegra30_tear_down_core:
+	bl	tegra30_sdram_self_refresh
+	bl	tegra30_switch_cpu_to_clk32k
+	b	tegra30_enter_sleep
+
+/*
+ * tegra30_switch_cpu_to_clk32k
+ *
+ * In LP0 and LP1 all PLLs will be turned off. Switching the CPU and System CLK
+ * to the 32KHz clock.
+ * r4 = TEGRA_PMC_BASE
+ * r5 = TEGRA_CLK_RESET_BASE
+ * r6 = TEGRA_FLOW_CTRL_BASE
+ * r7 = TEGRA_TMRUS_BASE
+ * r10= SoC ID
+ */
+tegra30_switch_cpu_to_clk32k:
+	/*
+	 * start by jumping to CLKM to safely disable PLLs, then jump to
+	 * CLKS.
+	 */
+	mov	r0, #(1 << 28)
+	str	r0, [r5, #CLK_RESET_SCLK_BURST]
+	/* 2uS delay delay between changing SCLK and CCLK */
+	ldr	r1, [r7]
+	add	r1, r1, #2
+	wait_until r1, r7, r9
+	str	r0, [r5, #CLK_RESET_CCLK_BURST]
+	mov	r0, #0
+	str	r0, [r5, #CLK_RESET_CCLK_DIVIDER]
+	str	r0, [r5, #CLK_RESET_SCLK_DIVIDER]
+
+	/* switch the clock source of mselect to be CLK_M */
+	ldr	r0, [r5, #CLK_RESET_CLK_SOURCE_MSELECT]
+	orr	r0, r0, #MSELECT_CLKM
+	str	r0, [r5, #CLK_RESET_CLK_SOURCE_MSELECT]
+
+	/* 2uS delay delay between changing SCLK and disabling PLLs */
+	ldr	r1, [r7]
+	add	r1, r1, #2
+	wait_until r1, r7, r9
+
+	/* disable PLLM via PMC in LP1 */
+	ldr	r0, [r4, #PMC_PLLP_WB0_OVERRIDE]
+	bic	r0, r0, #(1 << 12)
+	str	r0, [r4, #PMC_PLLP_WB0_OVERRIDE]
+
+	/* disable PLLP, PLLA, PLLC and PLLX */
+	ldr	r0, [r5, #CLK_RESET_PLLP_BASE]
+	bic	r0, r0, #(1 << 30)
+	str	r0, [r5, #CLK_RESET_PLLP_BASE]
+	ldr	r0, [r5, #CLK_RESET_PLLA_BASE]
+	bic	r0, r0, #(1 << 30)
+	str	r0, [r5, #CLK_RESET_PLLA_BASE]
+	ldr	r0, [r5, #CLK_RESET_PLLC_BASE]
+	bic	r0, r0, #(1 << 30)
+	str	r0, [r5, #CLK_RESET_PLLC_BASE]
+	ldr	r0, [r5, #CLK_RESET_PLLX_BASE]
+	bic	r0, r0, #(1 << 30)
+	str	r0, [r5, #CLK_RESET_PLLX_BASE]
+
+	cmp	r10, #TEGRA30
+	beq	_no_pll_in_iddq
+	pll_iddq_entry r1, r5, CLK_RESET_PLLX_MISC3, CLK_RESET_PLLX_MISC3_IDDQ
+_no_pll_in_iddq:
+
+	/* switch to CLKS */
+	mov	r0, #0	/* brust policy = 32KHz */
+	str	r0, [r5, #CLK_RESET_SCLK_BURST]
+
+	mov	pc, lr
+
 /*
  * tegra30_enter_sleep
  *
@@ -172,8 +660,12 @@ tegra30_enter_sleep:
 	orr	r0, r0, #FLOW_CTRL_CSR_ENABLE
 	str	r0, [r6, r2]
 
+	tegra_get_soc_id TEGRA_APB_MISC_BASE, r10
+	cmp	r10, #TEGRA30
 	mov	r0, #FLOW_CTRL_WAIT_FOR_INTERRUPT
-	orr	r0, r0, #FLOW_CTRL_HALT_CPU_IRQ | FLOW_CTRL_HALT_CPU_FIQ
+	orreq	r0, r0, #FLOW_CTRL_HALT_CPU_IRQ | FLOW_CTRL_HALT_CPU_FIQ
+	orrne   r0, r0, #FLOW_CTRL_HALT_LIC_IRQ | FLOW_CTRL_HALT_LIC_FIQ
+
 	cpu_to_halt_reg r2, r1
 	str	r0, [r6, r2]
 	dsb
@@ -187,4 +679,126 @@ halted:
 	/* !!!FIXME!!! Implement halt failure handler */
 	b	halted
 
+/*
+ * tegra30_sdram_self_refresh
+ *
+ * called with MMU off and caches disabled
+ * must be executed from IRAM
+ * r4 = TEGRA_PMC_BASE
+ * r5 = TEGRA_CLK_RESET_BASE
+ * r6 = TEGRA_FLOW_CTRL_BASE
+ * r7 = TEGRA_TMRUS_BASE
+ * r10= SoC ID
+ */
+tegra30_sdram_self_refresh:
+
+	adr	r8, tegra30_sdram_pad_save
+	tegra_get_soc_id TEGRA_APB_MISC_BASE, r10
+	cmp	r10, #TEGRA30
+	adreq	r2, tegra30_sdram_pad_address
+	ldreq	r3, tegra30_sdram_pad_size
+	adrne	r2, tegra114_sdram_pad_address
+	ldrne	r3, tegra114_sdram_pad_size
+	mov	r9, #0
+
+padsave:
+	ldr	r0, [r2, r9]		@ r0 is the addr in the pad_address
+
+	ldr	r1, [r0]
+	str	r1, [r8, r9]		@ save the content of the addr
+
+	add	r9, r9, #4
+	cmp	r3, r9
+	bne	padsave
+padsave_done:
+
+	dsb
+
+	cmp	r10, #TEGRA30
+	ldreq	r0, =TEGRA_EMC_BASE	@ r0 reserved for emc base addr
+	ldrne	r0, =TEGRA_EMC0_BASE
+
+enter_self_refresh:
+	cmp	r10, #TEGRA30
+	mov	r1, #0
+	str	r1, [r0, #EMC_ZCAL_INTERVAL]
+	str	r1, [r0, #EMC_AUTO_CAL_INTERVAL]
+	ldr	r1, [r0, #EMC_CFG]
+	bic	r1, r1, #(1 << 28)
+	bicne	r1, r1, #(1 << 29)
+	str	r1, [r0, #EMC_CFG]	@ disable DYN_SELF_REF
+
+	emc_timing_update r1, r0
+
+	ldr	r1, [r7]
+	add	r1, r1, #5
+	wait_until r1, r7, r2
+
+emc_wait_auto_cal:
+	ldr	r1, [r0, #EMC_AUTO_CAL_STATUS]
+	tst	r1, #(1 << 31)		@ wait until AUTO_CAL_ACTIVE is cleared
+	bne	emc_wait_auto_cal
+
+	mov	r1, #3
+	str	r1, [r0, #EMC_REQ_CTRL]	@ stall incoming DRAM requests
+
+emcidle:
+	ldr	r1, [r0, #EMC_EMC_STATUS]
+	tst	r1, #4
+	beq	emcidle
+
+	mov	r1, #1
+	str	r1, [r0, #EMC_SELF_REF]
+
+	emc_device_mask r1, r0
+
+emcself:
+	ldr	r2, [r0, #EMC_EMC_STATUS]
+	and	r2, r2, r1
+	cmp	r2, r1
+	bne	emcself			@ loop until DDR in self-refresh
+
+	/* Put VTTGEN in the lowest power mode */
+	ldr	r1, [r0, #EMC_XM2VTTGENPADCTRL]
+	mov32	r2, 0xF8F8FFFF	@ clear XM2VTTGEN_DRVUP and XM2VTTGEN_DRVDN
+	and	r1, r1, r2
+	str	r1, [r0, #EMC_XM2VTTGENPADCTRL]
+	ldr	r1, [r0, #EMC_XM2VTTGENPADCTRL2]
+	cmp	r10, #TEGRA30
+	orreq	r1, r1, #7		@ set E_NO_VTTGEN
+	orrne	r1, r1, #0x3f
+	str	r1, [r0, #EMC_XM2VTTGENPADCTRL2]
+
+	emc_timing_update r1, r0
+
+	/* Tegra114 had dual EMC channel, now config the other one */
+	cmp	r10, #TEGRA114
+	bne	no_dual_emc_chanl
+	mov32	r1, TEGRA_EMC1_BASE
+	cmp	r0, r1
+	movne	r0, r1
+	bne	enter_self_refresh
+no_dual_emc_chanl:
+
+	ldr	r1, [r4, #PMC_CTRL]
+	tst	r1, #PMC_CTRL_SIDE_EFFECT_LP0
+	bne	pmc_io_dpd_skip
+	/*
+	 * Put DDR_DATA, DISC_ADDR_CMD, DDR_ADDR_CMD, POP_ADDR_CMD, POP_CLK
+	 * and COMP in the lowest power mode when LP1.
+	 */
+	mov32	r1, 0x8EC00000
+	str	r1, [r4, #PMC_IO_DPD_REQ]
+pmc_io_dpd_skip:
+
+	dsb
+
+	mov	pc, lr
+
+	.ltorg
+/* dummy symbol for end of IRAM */
+	.align L1_CACHE_SHIFT
+	.global tegra30_iram_end
+tegra30_iram_end:
+	b	.
 #endif
diff --git a/arch/arm/mach-tegra/sleep.S b/arch/arm/mach-tegra/sleep.S
index 9daaef26b0f6..8d06213fbc47 100644
--- a/arch/arm/mach-tegra/sleep.S
+++ b/arch/arm/mach-tegra/sleep.S
@@ -56,7 +56,9 @@ ENTRY(tegra_disable_clean_inv_dcache)
 	isb
 
 	/* Flush the D-cache */
-	bl	v7_flush_dcache_louis
+	cmp	r0, #TEGRA_FLUSH_CACHE_ALL
+	blne	v7_flush_dcache_louis
+	bleq	v7_flush_dcache_all
 
 	/* Trun off coherency */
 	exit_smp r4, r5
@@ -67,15 +69,40 @@ ENDPROC(tegra_disable_clean_inv_dcache)
 
 #ifdef CONFIG_PM_SLEEP
 /*
+ * tegra_init_l2_for_a15
+ *
+ * set up the correct L2 cache data RAM latency
+ */
+ENTRY(tegra_init_l2_for_a15)
+	mrc	p15, 0, r0, c0, c0, 5
+	ubfx	r0, r0, #8, #4
+	tst	r0, #1				@ only need for cluster 0
+	bne	_exit_init_l2_a15
+
+	mrc	p15, 0x1, r0, c9, c0, 2
+	and	r0, r0, #7
+	cmp	r0, #2
+	bicne	r0, r0, #7
+	orrne	r0, r0, #2
+	mcrne	p15, 0x1, r0, c9, c0, 2
+_exit_init_l2_a15:
+
+	mov	pc, lr
+ENDPROC(tegra_init_l2_for_a15)
+
+/*
  * tegra_sleep_cpu_finish(unsigned long v2p)
  *
  * enters suspend in LP2 by turning off the mmu and jumping to
  * tegra?_tear_down_cpu
  */
 ENTRY(tegra_sleep_cpu_finish)
+	mov	r4, r0
 	/* Flush and disable the L1 data cache */
+	mov	r0, #TEGRA_FLUSH_CACHE_ALL
 	bl	tegra_disable_clean_inv_dcache
 
+	mov	r0, r4
 	mov32	r6, tegra_tear_down_cpu
 	ldr	r1, [r6]
 	add	r1, r1, r0
@@ -107,10 +134,10 @@ ENTRY(tegra_shut_off_mmu)
 #ifdef CONFIG_CACHE_L2X0
 	/* Disable L2 cache */
 	check_cpu_part_num 0xc09, r9, r10
-	movweq	r4, #:lower16:(TEGRA_ARM_PERIF_BASE + 0x3000)
-	movteq	r4, #:upper16:(TEGRA_ARM_PERIF_BASE + 0x3000)
-	moveq	r5, #0
-	streq	r5, [r4, #L2X0_CTRL]
+	movweq	r2, #:lower16:(TEGRA_ARM_PERIF_BASE + 0x3000)
+	movteq	r2, #:upper16:(TEGRA_ARM_PERIF_BASE + 0x3000)
+	moveq	r3, #0
+	streq	r3, [r2, #L2X0_CTRL]
 #endif
 	mov	pc, r0
 ENDPROC(tegra_shut_off_mmu)
diff --git a/arch/arm/mach-tegra/sleep.h b/arch/arm/mach-tegra/sleep.h
index 98b7da698f2b..a4edbb3abd3d 100644
--- a/arch/arm/mach-tegra/sleep.h
+++ b/arch/arm/mach-tegra/sleep.h
@@ -41,7 +41,19 @@
 #define CPU_NOT_RESETTABLE	0
 #endif
 
+/* flag of tegra_disable_clean_inv_dcache to do LoUIS or all */
+#define TEGRA_FLUSH_CACHE_LOUIS	0
+#define TEGRA_FLUSH_CACHE_ALL	1
+
 #ifdef __ASSEMBLY__
+/* waits until the microsecond counter (base) is > rn */
+.macro wait_until, rn, base, tmp
+	add	\rn, \rn, #1
+1001:	ldr	\tmp, [\base]
+	cmp	\tmp, \rn
+	bmi	1001b
+.endm
+
 /* returns the offset of the flow controller halt register for a cpu */
 .macro cpu_to_halt_reg rd, rcpu
 	cmp	\rcpu, #0
@@ -144,7 +156,7 @@ void tegra_pen_lock(void);
 void tegra_pen_unlock(void);
 void tegra_resume(void);
 int tegra_sleep_cpu_finish(unsigned long);
-void tegra_disable_clean_inv_dcache(void);
+void tegra_disable_clean_inv_dcache(u32 flag);
 
 #ifdef CONFIG_HOTPLUG_CPU
 void tegra20_hotplug_shutdown(void);
diff --git a/arch/arm/mach-tegra/tegra.c b/arch/arm/mach-tegra/tegra.c
index 0d1e4128d460..5b8605547a09 100644
--- a/arch/arm/mach-tegra/tegra.c
+++ b/arch/arm/mach-tegra/tegra.c
@@ -29,7 +29,6 @@
 #include <linux/of_fdt.h>
 #include <linux/of_platform.h>
 #include <linux/pda_power.h>
-#include <linux/platform_data/tegra_usb.h>
 #include <linux/io.h>
 #include <linux/slab.h>
 #include <linux/sys_soc.h>
@@ -46,40 +45,6 @@
 #include "fuse.h"
 #include "iomap.h"
 
-static struct tegra_ehci_platform_data tegra_ehci1_pdata = {
-	.operating_mode = TEGRA_USB_OTG,
-	.power_down_on_bus_suspend = 1,
-	.vbus_gpio = -1,
-};
-
-static struct tegra_ulpi_config tegra_ehci2_ulpi_phy_config = {
-	.reset_gpio = -1,
-	.clk = "cdev2",
-};
-
-static struct tegra_ehci_platform_data tegra_ehci2_pdata = {
-	.phy_config = &tegra_ehci2_ulpi_phy_config,
-	.operating_mode = TEGRA_USB_HOST,
-	.power_down_on_bus_suspend = 1,
-	.vbus_gpio = -1,
-};
-
-static struct tegra_ehci_platform_data tegra_ehci3_pdata = {
-	.operating_mode = TEGRA_USB_HOST,
-	.power_down_on_bus_suspend = 1,
-	.vbus_gpio = -1,
-};
-
-static struct of_dev_auxdata tegra20_auxdata_lookup[] __initdata = {
-	OF_DEV_AUXDATA("nvidia,tegra20-ehci", 0xC5000000, "tegra-ehci.0",
-		       &tegra_ehci1_pdata),
-	OF_DEV_AUXDATA("nvidia,tegra20-ehci", 0xC5004000, "tegra-ehci.1",
-		       &tegra_ehci2_pdata),
-	OF_DEV_AUXDATA("nvidia,tegra20-ehci", 0xC5008000, "tegra-ehci.2",
-		       &tegra_ehci3_pdata),
-	{}
-};
-
 static void __init tegra_dt_init(void)
 {
 	struct soc_device_attribute *soc_dev_attr;
@@ -112,30 +77,7 @@ static void __init tegra_dt_init(void)
 	 * devices
 	 */
 out:
-	of_platform_populate(NULL, of_default_bus_match_table,
-				tegra20_auxdata_lookup, parent);
-}
-
-static void __init trimslice_init(void)
-{
-#ifdef CONFIG_TEGRA_PCI
-	int ret;
-
-	ret = tegra_pcie_init(true, true);
-	if (ret)
-		pr_err("tegra_pci_init() failed: %d\n", ret);
-#endif
-}
-
-static void __init harmony_init(void)
-{
-#ifdef CONFIG_TEGRA_PCI
-	int ret;
-
-	ret = harmony_pcie_init();
-	if (ret)
-		pr_err("harmony_pcie_init() failed: %d\n", ret);
-#endif
+	of_platform_populate(NULL, of_default_bus_match_table, NULL, parent);
 }
 
 static void __init paz00_init(void)
@@ -148,8 +90,6 @@ static struct {
 	char *machine;
 	void (*init)(void);
 } board_init_funcs[] = {
-	{ "compulab,trimslice", trimslice_init },
-	{ "nvidia,harmony", harmony_init },
 	{ "compal,paz00", paz00_init },
 };
 
diff --git a/arch/arm/mach-u300/Kconfig b/arch/arm/mach-u300/Kconfig
index a85adcd00882..a1659863bfd5 100644
--- a/arch/arm/mach-u300/Kconfig
+++ b/arch/arm/mach-u300/Kconfig
@@ -1,7 +1,3 @@
-menu "ST-Ericsson AB U300/U335 Platform"
-
-comment "ST-Ericsson Mobile Platform Products"
-
 config ARCH_U300
 	bool "ST-Ericsson U300 Series" if ARCH_MULTI_V5
 	depends on MMU
@@ -25,7 +21,9 @@ config ARCH_U300
 	help
 	  Support for ST-Ericsson U300 series mobile platforms.
 
-comment "ST-Ericsson U300/U335 Feature Selections"
+if ARCH_U300
+
+menu "ST-Ericsson AB U300/U335 Platform"
 
 config MACH_U300
 	depends on ARCH_U300
@@ -53,3 +51,5 @@ config MACH_U300_SPIDUMMY
 		SPI framework and ARM PL022 support.
 
 endmenu
+
+endif
diff --git a/arch/arm/mach-ux500/Kconfig b/arch/arm/mach-ux500/Kconfig
index b19b07204aaf..99a28d628297 100644
--- a/arch/arm/mach-ux500/Kconfig
+++ b/arch/arm/mach-ux500/Kconfig
@@ -8,7 +8,7 @@ config ARCH_U8500
 	select CPU_V7
 	select GENERIC_CLOCKEVENTS
 	select HAVE_ARM_SCU if SMP
-	select HAVE_ARM_TWD if LOCAL_TIMERS
+	select HAVE_ARM_TWD if SMP
 	select HAVE_SMP
 	select MIGHT_HAVE_CACHE_L2X0
 	help
diff --git a/arch/arm/mach-ux500/Makefile b/arch/arm/mach-ux500/Makefile
index bf9b6be5b180..fe1f3e26b88b 100644
--- a/arch/arm/mach-ux500/Makefile
+++ b/arch/arm/mach-ux500/Makefile
@@ -4,7 +4,6 @@
 
 obj-y				:= cpu.o devices.o devices-common.o \
 				   id.o usb.o timer.o pm.o
-obj-$(CONFIG_CPU_IDLE)          += cpuidle.o
 obj-$(CONFIG_CACHE_L2X0)	+= cache-l2x0.o
 obj-$(CONFIG_UX500_SOC_DB8500)	+= cpu-db8500.o devices-db8500.o
 obj-$(CONFIG_MACH_MOP500)	+= board-mop500.o board-mop500-sdi.o \
diff --git a/arch/arm/mach-ux500/board-mop500-audio.c b/arch/arm/mach-ux500/board-mop500-audio.c
index bfe443daf4b0..ec0807247e60 100644
--- a/arch/arm/mach-ux500/board-mop500-audio.c
+++ b/arch/arm/mach-ux500/board-mop500-audio.c
@@ -17,7 +17,6 @@
 #include "ste-dma40-db8500.h"
 #include "board-mop500.h"
 #include "devices-db8500.h"
-#include "pins-db8500.h"
 
 static struct stedma40_chan_cfg msp0_dma_rx = {
 	.high_priority = true,
diff --git a/arch/arm/mach-ux500/board-mop500-pins.c b/arch/arm/mach-ux500/board-mop500-pins.c
index 7936d40a5c37..0efb1560fc35 100644
--- a/arch/arm/mach-ux500/board-mop500-pins.c
+++ b/arch/arm/mach-ux500/board-mop500-pins.c
@@ -14,7 +14,6 @@
 
 #include <asm/mach-types.h>
 
-#include "pins-db8500.h"
 #include "board-mop500.h"
 
 enum custom_pin_cfg_t {
diff --git a/arch/arm/mach-ux500/board-mop500.c b/arch/arm/mach-ux500/board-mop500.c
index df5d27a532e9..ad0806eff762 100644
--- a/arch/arm/mach-ux500/board-mop500.c
+++ b/arch/arm/mach-ux500/board-mop500.c
@@ -42,7 +42,6 @@
 #include <linux/platform_data/dma-ste-dma40.h>
 
 #include <asm/mach-types.h>
-#include <asm/mach/arch.h>
 
 #include "setup.h"
 #include "devices.h"
@@ -325,21 +324,19 @@ static struct lp55xx_platform_data __initdata lp5521_sec_data = {
        .clock_mode     = LP55XX_CLOCK_EXT,
 };
 
+/* I2C0 devices only available on the first HREF/MOP500 */
 static struct i2c_board_info __initdata mop500_i2c0_devices[] = {
 	{
 		I2C_BOARD_INFO("tc3589x", 0x42),
 		.irq		= NOMADIK_GPIO_TO_IRQ(217),
 		.platform_data  = &mop500_tc35892_data,
 	},
-	/* I2C0 devices only available prior to HREFv60 */
 	{
 		I2C_BOARD_INFO("tps61052", 0x33),
 		.platform_data  = &mop500_tps61052_data,
 	},
 };
 
-#define NUM_PRE_V60_I2C0_DEVICES 1
-
 static struct i2c_board_info __initdata mop500_i2c2_devices[] = {
 	{
 		/* lp5521 LED driver, 1st device */
@@ -357,6 +354,17 @@ static struct i2c_board_info __initdata mop500_i2c2_devices[] = {
 	},
 };
 
+static int __init mop500_i2c_board_init(void)
+{
+	if (machine_is_u8500())
+		mop500_uib_i2c_add(0, mop500_i2c0_devices,
+				   ARRAY_SIZE(mop500_i2c0_devices));
+	mop500_uib_i2c_add(2, mop500_i2c2_devices,
+			   ARRAY_SIZE(mop500_i2c2_devices));
+	return 0;
+}
+device_initcall(mop500_i2c_board_init);
+
 static void __init mop500_i2c_init(struct device *parent)
 {
 	db8500_add_i2c0(parent, NULL);
@@ -565,7 +573,6 @@ static struct platform_device *snowball_platform_devs[] __initdata = {
 static void __init mop500_init_machine(void)
 {
 	struct device *parent = NULL;
-	int i2c0_devs;
 	int i;
 
 	platform_device_register(&db8500_prcmu_device);
@@ -588,19 +595,13 @@ static void __init mop500_init_machine(void)
 	mop500_spi_init(parent);
 	mop500_audio_init(parent);
 	mop500_uart_init(parent);
-
 	u8500_cryp1_hash1_init(parent);
 
-	i2c0_devs = ARRAY_SIZE(mop500_i2c0_devices);
-
-	i2c_register_board_info(0, mop500_i2c0_devices, i2c0_devs);
-	i2c_register_board_info(2, mop500_i2c2_devices,
-				ARRAY_SIZE(mop500_i2c2_devices));
-
 	/* This board has full regulator constraints */
 	regulator_has_full_constraints();
 }
 
+
 static void __init snowball_init_machine(void)
 {
 	struct device *parent = NULL;
@@ -635,7 +636,6 @@ static void __init snowball_init_machine(void)
 static void __init hrefv60_init_machine(void)
 {
 	struct device *parent = NULL;
-	int i2c0_devs;
 	int i;
 
 	platform_device_register(&db8500_prcmu_device);
@@ -664,14 +664,6 @@ static void __init hrefv60_init_machine(void)
 	mop500_audio_init(parent);
 	mop500_uart_init(parent);
 
-	i2c0_devs = ARRAY_SIZE(mop500_i2c0_devices);
-
-	i2c0_devs -= NUM_PRE_V60_I2C0_DEVICES;
-
-	i2c_register_board_info(0, mop500_i2c0_devices, i2c0_devs);
-	i2c_register_board_info(2, mop500_i2c2_devices,
-				ARRAY_SIZE(mop500_i2c2_devices));
-
 	/* This board has full regulator constraints */
 	regulator_has_full_constraints();
 }
@@ -686,6 +678,7 @@ MACHINE_START(U8500, "ST-Ericsson MOP500 platform")
 	.init_time	= ux500_timer_init,
 	.init_machine	= mop500_init_machine,
 	.init_late	= ux500_init_late,
+	.restart        = ux500_restart,
 MACHINE_END
 
 MACHINE_START(U8520, "ST-Ericsson U8520 Platform HREFP520")
@@ -695,6 +688,7 @@ MACHINE_START(U8520, "ST-Ericsson U8520 Platform HREFP520")
 	.init_time	= ux500_timer_init,
 	.init_machine	= mop500_init_machine,
 	.init_late	= ux500_init_late,
+	.restart        = ux500_restart,
 MACHINE_END
 
 MACHINE_START(HREFV60, "ST-Ericsson U8500 Platform HREFv60+")
@@ -705,6 +699,7 @@ MACHINE_START(HREFV60, "ST-Ericsson U8500 Platform HREFv60+")
 	.init_time	= ux500_timer_init,
 	.init_machine	= hrefv60_init_machine,
 	.init_late	= ux500_init_late,
+	.restart        = ux500_restart,
 MACHINE_END
 
 MACHINE_START(SNOWBALL, "Calao Systems Snowball platform")
@@ -716,4 +711,5 @@ MACHINE_START(SNOWBALL, "Calao Systems Snowball platform")
 	.init_time	= ux500_timer_init,
 	.init_machine	= snowball_init_machine,
 	.init_late	= NULL,
+	.restart        = ux500_restart,
 MACHINE_END
diff --git a/arch/arm/mach-ux500/cache-l2x0.c b/arch/arm/mach-ux500/cache-l2x0.c
index 82ccf1d98735..264f894c0e3d 100644
--- a/arch/arm/mach-ux500/cache-l2x0.c
+++ b/arch/arm/mach-ux500/cache-l2x0.c
@@ -69,6 +69,7 @@ static int __init ux500_l2x0_init(void)
 	 * some SMI service available.
 	 */
 	outer_cache.disable = NULL;
+	outer_cache.set_debug = NULL;
 
 	return 0;
 }
diff --git a/arch/arm/mach-ux500/cpu-db8500.c b/arch/arm/mach-ux500/cpu-db8500.c
index 12eee8167525..301c3460d96a 100644
--- a/arch/arm/mach-ux500/cpu-db8500.c
+++ b/arch/arm/mach-ux500/cpu-db8500.c
@@ -26,7 +26,6 @@
 
 #include <asm/pmu.h>
 #include <asm/mach/map.h>
-#include <asm/mach/arch.h>
 
 #include "setup.h"
 #include "devices.h"
@@ -157,7 +156,8 @@ static void __init db8500_add_gpios(struct device *parent)
 		.supports_sleepmode = true,
 	};
 
-	dbx500_add_gpios(parent, ARRAY_AND_SIZE(db8500_gpio_base),
+	dbx500_add_gpios(parent, db8500_gpio_base,
+			 ARRAY_SIZE(db8500_gpio_base),
 			 IRQ_DB8500_GPIO0, &pdata);
 	dbx500_add_pinctrl(parent, "pinctrl-db8500", U8500_PRCMU_BASE);
 }
@@ -223,10 +223,10 @@ static struct of_dev_auxdata u8500_auxdata_lookup[] __initdata = {
 	OF_DEV_AUXDATA("arm,pl011", 0x80121000, "uart1", NULL),
 	OF_DEV_AUXDATA("arm,pl011", 0x80007000, "uart2", NULL),
 	OF_DEV_AUXDATA("arm,pl022", 0x80002000, "ssp0",  &ssp0_plat),
-	OF_DEV_AUXDATA("arm,pl18x", 0x80126000, "sdi0",  &mop500_sdi0_data),
-	OF_DEV_AUXDATA("arm,pl18x", 0x80118000, "sdi1",  &mop500_sdi1_data),
-	OF_DEV_AUXDATA("arm,pl18x", 0x80005000, "sdi2",  &mop500_sdi2_data),
-	OF_DEV_AUXDATA("arm,pl18x", 0x80114000, "sdi4",  &mop500_sdi4_data),
+	OF_DEV_AUXDATA("arm,pl18x", 0x80126000, "sdi0",  NULL),
+	OF_DEV_AUXDATA("arm,pl18x", 0x80118000, "sdi1",  NULL),
+	OF_DEV_AUXDATA("arm,pl18x", 0x80005000, "sdi2",  NULL),
+	OF_DEV_AUXDATA("arm,pl18x", 0x80114000, "sdi4",  NULL),
 	/* Requires clock name bindings. */
 	OF_DEV_AUXDATA("st,nomadik-gpio", 0x8012e000, "gpio.0", NULL),
 	OF_DEV_AUXDATA("st,nomadik-gpio", 0x8012e080, "gpio.1", NULL),
@@ -325,6 +325,7 @@ DT_MACHINE_START(U8500_DT, "ST-Ericsson Ux5x0 platform (Device Tree Support)")
 	.init_machine	= u8500_init_machine,
 	.init_late	= NULL,
 	.dt_compat      = stericsson_dt_platform_compat,
+	.restart        = ux500_restart,
 MACHINE_END
 
 #endif
diff --git a/arch/arm/mach-ux500/cpu.c b/arch/arm/mach-ux500/cpu.c
index e6fb0239151b..5d7eebcabc63 100644
--- a/arch/arm/mach-ux500/cpu.c
+++ b/arch/arm/mach-ux500/cpu.c
@@ -31,6 +31,14 @@
 #include "db8500-regs.h"
 #include "id.h"
 
+void ux500_restart(enum reboot_mode mode, const char *cmd)
+{
+	local_irq_disable();
+	local_fiq_disable();
+
+	prcmu_system_reset(0);
+}
+
 /*
  * FIXME: Should we set up the GPIO domain here?
  *
diff --git a/arch/arm/mach-ux500/devices-db8500.c b/arch/arm/mach-ux500/devices-db8500.c
index 516a6f57d159..bc316062e0c2 100644
--- a/arch/arm/mach-ux500/devices-db8500.c
+++ b/arch/arm/mach-ux500/devices-db8500.c
@@ -49,6 +49,7 @@ struct stedma40_platform_data dma40_plat_data = {
 struct platform_device u8500_dma40_device = {
 	.dev = {
 		.platform_data = &dma40_plat_data,
+		.coherent_dma_mask = DMA_BIT_MASK(32),
 	},
 	.name = "dma40",
 	.id = 0,
diff --git a/arch/arm/mach-ux500/headsmp.S b/arch/arm/mach-ux500/headsmp.S
index 08da5589bcd8..9cdea049485d 100644
--- a/arch/arm/mach-ux500/headsmp.S
+++ b/arch/arm/mach-ux500/headsmp.S
@@ -11,8 +11,6 @@
 #include <linux/linkage.h>
 #include <linux/init.h>
 
-	__INIT
-
 /*
  * U8500 specific entry point for secondary CPUs.
  */
diff --git a/arch/arm/mach-ux500/pins-db8500.h b/arch/arm/mach-ux500/pins-db8500.h
deleted file mode 100644
index 062c7acf4576..000000000000
--- a/arch/arm/mach-ux500/pins-db8500.h
+++ /dev/null
@@ -1,746 +0,0 @@
-/*
- * Copyright (C) ST-Ericsson SA 2010
- *
- * License terms: GNU General Public License, version 2
- * Author: Rabin Vincent <rabin.vincent@stericsson.com>
- */
-
-#ifndef __MACH_PINS_DB8500_H
-#define __MACH_PINS_DB8500_H
-
-/*
- * TODO: Eventually encode all non-board specific pull up/down configuration
- * here.
- */
-
-#define GPIO0_GPIO		PIN_CFG(0, GPIO)
-#define GPIO0_U0_CTSn		PIN_CFG(0, ALT_A)
-#define GPIO0_TRIG_OUT		PIN_CFG(0, ALT_B)
-#define GPIO0_IP_TDO		PIN_CFG(0, ALT_C)
-
-#define GPIO1_GPIO		PIN_CFG(1, GPIO)
-#define GPIO1_U0_RTSn		PIN_CFG(1, ALT_A)
-#define GPIO1_TRIG_IN		PIN_CFG(1, ALT_B)
-#define GPIO1_IP_TDI		PIN_CFG(1, ALT_C)
-
-#define GPIO2_GPIO		PIN_CFG(2, GPIO)
-#define GPIO2_U0_RXD		PIN_CFG(2, ALT_A)
-#define GPIO2_NONE		PIN_CFG(2, ALT_B)
-#define GPIO2_IP_TMS		PIN_CFG(2, ALT_C)
-
-#define GPIO3_GPIO		PIN_CFG(3, GPIO)
-#define GPIO3_U0_TXD		PIN_CFG(3, ALT_A)
-#define GPIO3_NONE		PIN_CFG(3, ALT_B)
-#define GPIO3_IP_TCK		PIN_CFG(3, ALT_C)
-
-#define GPIO4_GPIO		PIN_CFG(4, GPIO)
-#define GPIO4_U1_RXD		PIN_CFG(4, ALT_A)
-#define GPIO4_I2C4_SCL		PIN_CFG(4, ALT_B)
-#define GPIO4_IP_TRSTn		PIN_CFG(4, ALT_C)
-
-#define GPIO5_GPIO		PIN_CFG(5, GPIO)
-#define GPIO5_U1_TXD		PIN_CFG(5, ALT_A)
-#define GPIO5_I2C4_SDA		PIN_CFG(5, ALT_B)
-#define GPIO5_IP_GPIO6		PIN_CFG(5, ALT_C)
-
-#define GPIO6_GPIO		PIN_CFG(6, GPIO)
-#define GPIO6_U1_CTSn		PIN_CFG(6, ALT_A)
-#define GPIO6_I2C1_SCL		PIN_CFG(6, ALT_B)
-#define GPIO6_IP_GPIO0		PIN_CFG(6, ALT_C)
-
-#define GPIO7_GPIO		PIN_CFG(7, GPIO)
-#define GPIO7_U1_RTSn		PIN_CFG(7, ALT_A)
-#define GPIO7_I2C1_SDA		PIN_CFG(7, ALT_B)
-#define GPIO7_IP_GPIO1		PIN_CFG(7, ALT_C)
-
-#define GPIO8_GPIO		PIN_CFG(8, GPIO)
-#define GPIO8_IPI2C_SDA		PIN_CFG(8, ALT_A)
-#define GPIO8_I2C2_SDA		PIN_CFG(8, ALT_B)
-
-#define GPIO9_GPIO		PIN_CFG(9, GPIO)
-#define GPIO9_IPI2C_SCL		PIN_CFG(9, ALT_A)
-#define GPIO9_I2C2_SCL		PIN_CFG(9, ALT_B)
-
-#define GPIO10_GPIO		PIN_CFG(10, GPIO)
-#define GPIO10_IPI2C_SDA	PIN_CFG(10, ALT_A)
-#define GPIO10_I2C2_SDA		PIN_CFG(10, ALT_B)
-#define GPIO10_IP_GPIO3		PIN_CFG(10, ALT_C)
-
-#define GPIO11_GPIO		PIN_CFG(11, GPIO)
-#define GPIO11_IPI2C_SCL	PIN_CFG(11, ALT_A)
-#define GPIO11_I2C2_SCL		PIN_CFG(11, ALT_B)
-#define GPIO11_IP_GPIO2		PIN_CFG(11, ALT_C)
-
-#define GPIO12_GPIO		PIN_CFG(12, GPIO)
-#define GPIO12_MSP0_TXD		PIN_CFG(12, ALT_A)
-#define GPIO12_MSP0_RXD		PIN_CFG(12, ALT_B)
-
-#define GPIO13_GPIO		PIN_CFG(13, GPIO)
-#define GPIO13_MSP0_TFS		PIN_CFG(13, ALT_A)
-
-#define GPIO14_GPIO		PIN_CFG(14, GPIO)
-#define GPIO14_MSP0_TCK		PIN_CFG(14, ALT_A)
-
-#define GPIO15_GPIO		PIN_CFG(15, GPIO)
-#define GPIO15_MSP0_RXD		PIN_CFG(15, ALT_A)
-#define GPIO15_MSP0_TXD		PIN_CFG(15, ALT_B)
-
-#define GPIO16_GPIO		PIN_CFG(16, GPIO)
-#define GPIO16_MSP0_RFS		PIN_CFG(16, ALT_A)
-#define GPIO16_I2C1_SCL		PIN_CFG(16, ALT_B)
-#define GPIO16_SLIM0_DAT	PIN_CFG(16, ALT_C)
-
-#define GPIO17_GPIO		PIN_CFG(17, GPIO)
-#define GPIO17_MSP0_RCK		PIN_CFG(17, ALT_A)
-#define GPIO17_I2C1_SDA		PIN_CFG(17, ALT_B)
-#define GPIO17_SLIM0_CLK	PIN_CFG(17, ALT_C)
-
-#define GPIO18_GPIO		PIN_CFG(18, GPIO)
-#define GPIO18_MC0_CMDDIR	PIN_CFG_INPUT(18, ALT_A, PULLUP)
-#define GPIO18_U2_RXD		PIN_CFG(18, ALT_B)
-#define GPIO18_MS_IEP		PIN_CFG(18, ALT_C)
-
-#define GPIO19_GPIO		PIN_CFG(19, GPIO)
-#define GPIO19_MC0_DAT0DIR	PIN_CFG_INPUT(19, ALT_A, PULLUP)
-#define GPIO19_U2_TXD		PIN_CFG(19, ALT_B)
-#define GPIO19_MS_DAT0DIR	PIN_CFG(19, ALT_C)
-
-#define GPIO20_GPIO		PIN_CFG(20, GPIO)
-#define GPIO20_MC0_DAT2DIR	PIN_CFG_INPUT(20, ALT_A, PULLUP)
-#define GPIO20_UARTMOD_TXD	PIN_CFG(20, ALT_B)
-#define GPIO20_IP_TRIGOUT	PIN_CFG(20, ALT_C)
-
-#define GPIO21_GPIO		PIN_CFG(21, GPIO)
-#define GPIO21_MC0_DAT31DIR	PIN_CFG_INPUT(21, ALT_A, PULLUP)
-#define GPIO21_MSP0_SCK		PIN_CFG(21, ALT_B)
-#define GPIO21_MS_DAT31DIR	PIN_CFG(21, ALT_C)
-
-#define GPIO22_GPIO		PIN_CFG(22, GPIO)
-#define GPIO22_MC0_FBCLK	PIN_CFG_INPUT(22, ALT_A, PULLUP)
-#define GPIO22_UARTMOD_RXD	PIN_CFG(22, ALT_B)
-#define GPIO22_MS_FBCLK		PIN_CFG(22, ALT_C)
-
-#define GPIO23_GPIO		PIN_CFG(23, GPIO)
-#define GPIO23_MC0_CLK		PIN_CFG_INPUT(23, ALT_A, PULLUP)
-#define GPIO23_STMMOD_CLK	PIN_CFG(23, ALT_B)
-#define GPIO23_MS_CLK		PIN_CFG(23, ALT_C)
-
-#define GPIO24_GPIO		PIN_CFG(24, GPIO)
-#define GPIO24_MC0_CMD		PIN_CFG_INPUT(24, ALT_A, PULLUP)
-#define GPIO24_UARTMOD_RXD	PIN_CFG(24, ALT_B)
-#define GPIO24_MS_BS		PIN_CFG(24, ALT_C)
-
-#define GPIO25_GPIO		PIN_CFG(25, GPIO)
-#define GPIO25_MC0_DAT0		PIN_CFG_INPUT(25, ALT_A, PULLUP)
-#define GPIO25_STMMOD_DAT0	PIN_CFG(25, ALT_B)
-#define GPIO25_MS_DAT0		PIN_CFG(25, ALT_C)
-
-#define GPIO26_GPIO		PIN_CFG(26, GPIO)
-#define GPIO26_MC0_DAT1		PIN_CFG_INPUT(26, ALT_A, PULLUP)
-#define GPIO26_STMMOD_DAT1	PIN_CFG(26, ALT_B)
-#define GPIO26_MS_DAT1		PIN_CFG(26, ALT_C)
-
-#define GPIO27_GPIO		PIN_CFG(27, GPIO)
-#define GPIO27_MC0_DAT2		PIN_CFG_INPUT(27, ALT_A, PULLUP)
-#define GPIO27_STMMOD_DAT2	PIN_CFG(27, ALT_B)
-#define GPIO27_MS_DAT2		PIN_CFG(27, ALT_C)
-
-#define GPIO28_GPIO		PIN_CFG(28, GPIO)
-#define GPIO28_MC0_DAT3		PIN_CFG_INPUT(28, ALT_A, PULLUP)
-#define GPIO28_STMMOD_DAT3	PIN_CFG(28, ALT_B)
-#define GPIO28_MS_DAT3		PIN_CFG(28, ALT_C)
-
-#define GPIO29_GPIO		PIN_CFG(29, GPIO)
-#define GPIO29_MC0_DAT4		PIN_CFG(29, ALT_A)
-#define GPIO29_SPI3_CLK		PIN_CFG(29, ALT_B)
-#define GPIO29_U2_RXD		PIN_CFG(29, ALT_C)
-
-#define GPIO30_GPIO		PIN_CFG(30, GPIO)
-#define GPIO30_MC0_DAT5		PIN_CFG(30, ALT_A)
-#define GPIO30_SPI3_RXD		PIN_CFG(30, ALT_B)
-#define GPIO30_U2_TXD		PIN_CFG(30, ALT_C)
-
-#define GPIO31_GPIO		PIN_CFG(31, GPIO)
-#define GPIO31_MC0_DAT6		PIN_CFG(31, ALT_A)
-#define GPIO31_SPI3_FRM		PIN_CFG(31, ALT_B)
-#define GPIO31_U2_CTSn		PIN_CFG(31, ALT_C)
-
-#define GPIO32_GPIO		PIN_CFG(32, GPIO)
-#define GPIO32_MC0_DAT7		PIN_CFG(32, ALT_A)
-#define GPIO32_SPI3_TXD		PIN_CFG(32, ALT_B)
-#define GPIO32_U2_RTSn		PIN_CFG(32, ALT_C)
-
-#define GPIO33_GPIO		PIN_CFG(33, GPIO)
-#define GPIO33_MSP1_TXD		PIN_CFG(33, ALT_A)
-#define GPIO33_MSP1_RXD		PIN_CFG(33, ALT_B)
-#define GPIO33_U0_DTRn		PIN_CFG(33, ALT_C)
-
-#define GPIO34_GPIO		PIN_CFG(34, GPIO)
-#define GPIO34_MSP1_TFS		PIN_CFG(34, ALT_A)
-#define GPIO34_NONE		PIN_CFG(34, ALT_B)
-#define GPIO34_U0_DCDn		PIN_CFG(34, ALT_C)
-
-#define GPIO35_GPIO		PIN_CFG(35, GPIO)
-#define GPIO35_MSP1_TCK		PIN_CFG(35, ALT_A)
-#define GPIO35_NONE		PIN_CFG(35, ALT_B)
-#define GPIO35_U0_DSRn		PIN_CFG(35, ALT_C)
-
-#define GPIO36_GPIO		PIN_CFG(36, GPIO)
-#define GPIO36_MSP1_RXD		PIN_CFG(36, ALT_A)
-#define GPIO36_MSP1_TXD		PIN_CFG(36, ALT_B)
-#define GPIO36_U0_RIn		PIN_CFG(36, ALT_C)
-
-#define GPIO64_GPIO		PIN_CFG(64, GPIO)
-#define GPIO64_LCDB_DE		PIN_CFG(64, ALT_A)
-#define GPIO64_KP_O1		PIN_CFG(64, ALT_B)
-#define GPIO64_IP_GPIO4		PIN_CFG(64, ALT_C)
-
-#define GPIO65_GPIO		PIN_CFG(65, GPIO)
-#define GPIO65_LCDB_HSO		PIN_CFG(65, ALT_A)
-#define GPIO65_KP_O0		PIN_CFG(65, ALT_B)
-#define GPIO65_IP_GPIO5		PIN_CFG(65, ALT_C)
-
-#define GPIO66_GPIO		PIN_CFG(66, GPIO)
-#define GPIO66_LCDB_VSO		PIN_CFG(66, ALT_A)
-#define GPIO66_KP_I1		PIN_CFG(66, ALT_B)
-#define GPIO66_IP_GPIO6		PIN_CFG(66, ALT_C)
-
-#define GPIO67_GPIO		PIN_CFG(67, GPIO)
-#define GPIO67_LCDB_CLK		PIN_CFG(67, ALT_A)
-#define GPIO67_KP_I0		PIN_CFG(67, ALT_B)
-#define GPIO67_IP_GPIO7		PIN_CFG(67, ALT_C)
-
-#define GPIO68_GPIO		PIN_CFG(68, GPIO)
-#define GPIO68_LCD_VSI0		PIN_CFG(68, ALT_A)
-#define GPIO68_KP_O7		PIN_CFG(68, ALT_B)
-#define GPIO68_SM_CLE		PIN_CFG(68, ALT_C)
-
-#define GPIO69_GPIO		PIN_CFG(69, GPIO)
-#define GPIO69_LCD_VSI1		PIN_CFG(69, ALT_A)
-#define GPIO69_KP_I7		PIN_CFG(69, ALT_B)
-#define GPIO69_SM_ALE		PIN_CFG(69, ALT_C)
-
-#define GPIO70_GPIO		PIN_CFG(70, GPIO)
-#define GPIO70_LCD_D0		PIN_CFG(70, ALT_A)
-#define GPIO70_KP_O5		PIN_CFG(70, ALT_B)
-#define GPIO70_STMAPE_CLK	PIN_CFG(70, ALT_C)
-
-#define GPIO71_GPIO		PIN_CFG(71, GPIO)
-#define GPIO71_LCD_D1		PIN_CFG(71, ALT_A)
-#define GPIO71_KP_O4		PIN_CFG(71, ALT_B)
-#define GPIO71_STMAPE_DAT3	PIN_CFG(71, ALT_C)
-
-#define GPIO72_GPIO		PIN_CFG(72, GPIO)
-#define GPIO72_LCD_D2		PIN_CFG(72, ALT_A)
-#define GPIO72_KP_O3		PIN_CFG(72, ALT_B)
-#define GPIO72_STMAPE_DAT2	PIN_CFG(72, ALT_C)
-
-#define GPIO73_GPIO		PIN_CFG(73, GPIO)
-#define GPIO73_LCD_D3		PIN_CFG(73, ALT_A)
-#define GPIO73_KP_O2		PIN_CFG(73, ALT_B)
-#define GPIO73_STMAPE_DAT1	PIN_CFG(73, ALT_C)
-
-#define GPIO74_GPIO		PIN_CFG(74, GPIO)
-#define GPIO74_LCD_D4		PIN_CFG(74, ALT_A)
-#define GPIO74_KP_I5		PIN_CFG(74, ALT_B)
-#define GPIO74_STMAPE_DAT0	PIN_CFG(74, ALT_C)
-
-#define GPIO75_GPIO		PIN_CFG(75, GPIO)
-#define GPIO75_LCD_D5		PIN_CFG(75, ALT_A)
-#define GPIO75_KP_I4		PIN_CFG(75, ALT_B)
-#define GPIO75_U2_RXD		PIN_CFG(75, ALT_C)
-
-#define GPIO76_GPIO		PIN_CFG(76, GPIO)
-#define GPIO76_LCD_D6		PIN_CFG(76, ALT_A)
-#define GPIO76_KP_I3		PIN_CFG(76, ALT_B)
-#define GPIO76_U2_TXD		PIN_CFG(76, ALT_C)
-
-#define GPIO77_GPIO		PIN_CFG(77, GPIO)
-#define GPIO77_LCD_D7		PIN_CFG(77, ALT_A)
-#define GPIO77_KP_I2		PIN_CFG(77, ALT_B)
-#define GPIO77_NONE		PIN_CFG(77, ALT_C)
-
-#define GPIO78_GPIO		PIN_CFG(78, GPIO)
-#define GPIO78_LCD_D8		PIN_CFG(78, ALT_A)
-#define GPIO78_KP_O6		PIN_CFG(78, ALT_B)
-#define GPIO78_IP_GPIO2		PIN_CFG(78, ALT_C)
-
-#define GPIO79_GPIO		PIN_CFG(79, GPIO)
-#define GPIO79_LCD_D9		PIN_CFG(79, ALT_A)
-#define GPIO79_KP_I6		PIN_CFG(79, ALT_B)
-#define GPIO79_IP_GPIO3		PIN_CFG(79, ALT_C)
-
-#define GPIO80_GPIO		PIN_CFG(80, GPIO)
-#define GPIO80_LCD_D10		PIN_CFG(80, ALT_A)
-#define GPIO80_KP_SKA0		PIN_CFG(80, ALT_B)
-#define GPIO80_IP_GPIO4		PIN_CFG(80, ALT_C)
-
-#define GPIO81_GPIO		PIN_CFG(81, GPIO)
-#define GPIO81_LCD_D11		PIN_CFG(81, ALT_A)
-#define GPIO81_KP_SKB0		PIN_CFG(81, ALT_B)
-#define GPIO81_IP_GPIO5		PIN_CFG(81, ALT_C)
-
-#define GPIO82_GPIO		PIN_CFG(82, GPIO)
-#define GPIO82_LCD_D12		PIN_CFG(82, ALT_A)
-#define GPIO82_KP_O5		PIN_CFG(82, ALT_B)
-
-#define GPIO83_GPIO		PIN_CFG(83, GPIO)
-#define GPIO83_LCD_D13		PIN_CFG(83, ALT_A)
-#define GPIO83_KP_O4		PIN_CFG(83, ALT_B)
-
-#define GPIO84_GPIO		PIN_CFG(84, GPIO)
-#define GPIO84_LCD_D14		PIN_CFG(84, ALT_A)
-#define GPIO84_KP_I5		PIN_CFG(84, ALT_B)
-
-#define GPIO85_GPIO		PIN_CFG(85, GPIO)
-#define GPIO85_LCD_D15		PIN_CFG(85, ALT_A)
-#define GPIO85_KP_I4		PIN_CFG(85, ALT_B)
-
-#define GPIO86_GPIO		PIN_CFG(86, GPIO)
-#define GPIO86_LCD_D16		PIN_CFG(86, ALT_A)
-#define GPIO86_SM_ADQ0		PIN_CFG(86, ALT_B)
-#define GPIO86_MC5_DAT0		PIN_CFG(86, ALT_C)
-
-#define GPIO87_GPIO		PIN_CFG(87, GPIO)
-#define GPIO87_LCD_D17		PIN_CFG(87, ALT_A)
-#define GPIO87_SM_ADQ1		PIN_CFG(87, ALT_B)
-#define GPIO87_MC5_DAT1		PIN_CFG(87, ALT_C)
-
-#define GPIO88_GPIO		PIN_CFG(88, GPIO)
-#define GPIO88_LCD_D18		PIN_CFG(88, ALT_A)
-#define GPIO88_SM_ADQ2		PIN_CFG(88, ALT_B)
-#define GPIO88_MC5_DAT2		PIN_CFG(88, ALT_C)
-
-#define GPIO89_GPIO		PIN_CFG(89, GPIO)
-#define GPIO89_LCD_D19		PIN_CFG(89, ALT_A)
-#define GPIO89_SM_ADQ3		PIN_CFG(89, ALT_B)
-#define GPIO89_MC5_DAT3		PIN_CFG(89, ALT_C)
-
-#define GPIO90_GPIO		PIN_CFG(90, GPIO)
-#define GPIO90_LCD_D20		PIN_CFG(90, ALT_A)
-#define GPIO90_SM_ADQ4		PIN_CFG(90, ALT_B)
-#define GPIO90_MC5_CMD		PIN_CFG(90, ALT_C)
-
-#define GPIO91_GPIO		PIN_CFG(91, GPIO)
-#define GPIO91_LCD_D21		PIN_CFG(91, ALT_A)
-#define GPIO91_SM_ADQ5		PIN_CFG(91, ALT_B)
-#define GPIO91_MC5_FBCLK	PIN_CFG(91, ALT_C)
-
-#define GPIO92_GPIO		PIN_CFG(92, GPIO)
-#define GPIO92_LCD_D22		PIN_CFG(92, ALT_A)
-#define GPIO92_SM_ADQ6		PIN_CFG(92, ALT_B)
-#define GPIO92_MC5_CLK		PIN_CFG(92, ALT_C)
-
-#define GPIO93_GPIO		PIN_CFG(93, GPIO)
-#define GPIO93_LCD_D23		PIN_CFG(93, ALT_A)
-#define GPIO93_SM_ADQ7		PIN_CFG(93, ALT_B)
-#define GPIO93_MC5_DAT4		PIN_CFG(93, ALT_C)
-
-#define GPIO94_GPIO		PIN_CFG(94, GPIO)
-#define GPIO94_KP_O7		PIN_CFG(94, ALT_A)
-#define GPIO94_SM_ADVn		PIN_CFG(94, ALT_B)
-#define GPIO94_MC5_DAT5		PIN_CFG(94, ALT_C)
-
-#define GPIO95_GPIO		PIN_CFG(95, GPIO)
-#define GPIO95_KP_I7		PIN_CFG(95, ALT_A)
-#define GPIO95_SM_CS0n		PIN_CFG(95, ALT_B)
-#define GPIO95_SM_PS0n		PIN_CFG(95, ALT_C)
-
-#define GPIO96_GPIO		PIN_CFG(96, GPIO)
-#define GPIO96_KP_O6		PIN_CFG(96, ALT_A)
-#define GPIO96_SM_OEn		PIN_CFG(96, ALT_B)
-#define GPIO96_MC5_DAT6		PIN_CFG(96, ALT_C)
-
-#define GPIO97_GPIO		PIN_CFG(97, GPIO)
-#define GPIO97_KP_I6		PIN_CFG(97, ALT_A)
-#define GPIO97_SM_WEn		PIN_CFG(97, ALT_B)
-#define GPIO97_MC5_DAT7		PIN_CFG(97, ALT_C)
-
-#define GPIO128_GPIO		PIN_CFG(128, GPIO)
-#define GPIO128_MC2_CLK		PIN_CFG_INPUT(128, ALT_A, PULLUP)
-#define GPIO128_SM_CKO		PIN_CFG(128, ALT_B)
-
-#define GPIO129_GPIO		PIN_CFG(129, GPIO)
-#define GPIO129_MC2_CMD		PIN_CFG_INPUT(129, ALT_A, PULLUP)
-#define GPIO129_SM_WAIT0n	PIN_CFG(129, ALT_B)
-
-#define GPIO130_GPIO		PIN_CFG(130, GPIO)
-#define GPIO130_MC2_FBCLK	PIN_CFG_INPUT(130, ALT_A, PULLUP)
-#define GPIO130_SM_FBCLK	PIN_CFG(130, ALT_B)
-#define GPIO130_MC2_RSTN	PIN_CFG(130, ALT_C)
-
-#define GPIO131_GPIO		PIN_CFG(131, GPIO)
-#define GPIO131_MC2_DAT0	PIN_CFG_INPUT(131, ALT_A, PULLUP)
-#define GPIO131_SM_ADQ8		PIN_CFG(131, ALT_B)
-
-#define GPIO132_GPIO		PIN_CFG(132, GPIO)
-#define GPIO132_MC2_DAT1	PIN_CFG_INPUT(132, ALT_A, PULLUP)
-#define GPIO132_SM_ADQ9		PIN_CFG(132, ALT_B)
-
-#define GPIO133_GPIO		PIN_CFG(133, GPIO)
-#define GPIO133_MC2_DAT2	PIN_CFG_INPUT(133, ALT_A, PULLUP)
-#define GPIO133_SM_ADQ10	PIN_CFG(133, ALT_B)
-
-#define GPIO134_GPIO		PIN_CFG(134, GPIO)
-#define GPIO134_MC2_DAT3	PIN_CFG_INPUT(134, ALT_A, PULLUP)
-#define GPIO134_SM_ADQ11	PIN_CFG(134, ALT_B)
-
-#define GPIO135_GPIO		PIN_CFG(135, GPIO)
-#define GPIO135_MC2_DAT4	PIN_CFG_INPUT(135, ALT_A, PULLUP)
-#define GPIO135_SM_ADQ12	PIN_CFG(135, ALT_B)
-
-#define GPIO136_GPIO		PIN_CFG(136, GPIO)
-#define GPIO136_MC2_DAT5	PIN_CFG_INPUT(136, ALT_A, PULLUP)
-#define GPIO136_SM_ADQ13	PIN_CFG(136, ALT_B)
-
-#define GPIO137_GPIO		PIN_CFG(137, GPIO)
-#define GPIO137_MC2_DAT6	PIN_CFG_INPUT(137, ALT_A, PULLUP)
-#define GPIO137_SM_ADQ14	PIN_CFG(137, ALT_B)
-
-#define GPIO138_GPIO		PIN_CFG(138, GPIO)
-#define GPIO138_MC2_DAT7	PIN_CFG_INPUT(138, ALT_A, PULLUP)
-#define GPIO138_SM_ADQ15	PIN_CFG(138, ALT_B)
-
-#define GPIO139_GPIO		PIN_CFG(139, GPIO)
-#define GPIO139_SSP1_RXD	PIN_CFG(139, ALT_A)
-#define GPIO139_SM_WAIT1n	PIN_CFG(139, ALT_B)
-#define GPIO139_KP_O8		PIN_CFG(139, ALT_C)
-
-#define GPIO140_GPIO		PIN_CFG(140, GPIO)
-#define GPIO140_SSP1_TXD	PIN_CFG(140, ALT_A)
-#define GPIO140_IP_GPIO7	PIN_CFG(140, ALT_B)
-#define GPIO140_KP_SKA1		PIN_CFG(140, ALT_C)
-
-#define GPIO141_GPIO		PIN_CFG(141, GPIO)
-#define GPIO141_SSP1_CLK	PIN_CFG(141, ALT_A)
-#define GPIO141_IP_GPIO2	PIN_CFG(141, ALT_B)
-#define GPIO141_KP_O9		PIN_CFG(141, ALT_C)
-
-#define GPIO142_GPIO		PIN_CFG(142, GPIO)
-#define GPIO142_SSP1_FRM	PIN_CFG(142, ALT_A)
-#define GPIO142_IP_GPIO3	PIN_CFG(142, ALT_B)
-#define GPIO142_KP_SKB1		PIN_CFG(142, ALT_C)
-
-#define GPIO143_GPIO		PIN_CFG(143, GPIO)
-#define GPIO143_SSP0_CLK	PIN_CFG(143, ALT_A)
-
-#define GPIO144_GPIO		PIN_CFG(144, GPIO)
-#define GPIO144_SSP0_FRM	PIN_CFG(144, ALT_A)
-
-#define GPIO145_GPIO		PIN_CFG(145, GPIO)
-#define GPIO145_SSP0_RXD	PIN_CFG(145, ALT_A)
-
-#define GPIO146_GPIO		PIN_CFG(146, GPIO)
-#define GPIO146_SSP0_TXD	PIN_CFG(146, ALT_A)
-
-#define GPIO147_GPIO		PIN_CFG(147, GPIO)
-#define GPIO147_I2C0_SCL	PIN_CFG(147, ALT_A)
-
-#define GPIO148_GPIO		PIN_CFG(148, GPIO)
-#define GPIO148_I2C0_SDA	PIN_CFG(148, ALT_A)
-
-#define GPIO149_GPIO		PIN_CFG(149, GPIO)
-#define GPIO149_IP_GPIO0	PIN_CFG(149, ALT_A)
-#define GPIO149_SM_CS1n		PIN_CFG(149, ALT_B)
-#define GPIO149_SM_PS1n		PIN_CFG(149, ALT_C)
-
-#define GPIO150_GPIO		PIN_CFG(150, GPIO)
-#define GPIO150_IP_GPIO1	PIN_CFG(150, ALT_A)
-#define GPIO150_LCDA_CLK	PIN_CFG(150, ALT_B)
-
-#define GPIO151_GPIO		PIN_CFG(151, GPIO)
-#define GPIO151_KP_SKA0		PIN_CFG(151, ALT_A)
-#define GPIO151_LCD_VSI0	PIN_CFG(151, ALT_B)
-#define GPIO151_KP_O8		PIN_CFG(151, ALT_C)
-
-#define GPIO152_GPIO		PIN_CFG(152, GPIO)
-#define GPIO152_KP_SKB0		PIN_CFG(152, ALT_A)
-#define GPIO152_LCD_VSI1	PIN_CFG(152, ALT_B)
-#define GPIO152_KP_O9		PIN_CFG(152, ALT_C)
-
-#define GPIO153_GPIO		PIN_CFG(153, GPIO)
-#define GPIO153_KP_I7		PIN_CFG(153, ALT_A)
-#define GPIO153_LCD_D24		PIN_CFG(153, ALT_B)
-#define GPIO153_U2_RXD		PIN_CFG(153, ALT_C)
-
-#define GPIO154_GPIO		PIN_CFG(154, GPIO)
-#define GPIO154_KP_I6		PIN_CFG(154, ALT_A)
-#define GPIO154_LCD_D25		PIN_CFG(154, ALT_B)
-#define GPIO154_U2_TXD		PIN_CFG(154, ALT_C)
-
-#define GPIO155_GPIO		PIN_CFG(155, GPIO)
-#define GPIO155_KP_I5		PIN_CFG(155, ALT_A)
-#define GPIO155_LCD_D26		PIN_CFG(155, ALT_B)
-#define GPIO155_STMAPE_CLK	PIN_CFG(155, ALT_C)
-
-#define GPIO156_GPIO		PIN_CFG(156, GPIO)
-#define GPIO156_KP_I4		PIN_CFG(156, ALT_A)
-#define GPIO156_LCD_D27		PIN_CFG(156, ALT_B)
-#define GPIO156_STMAPE_DAT3	PIN_CFG(156, ALT_C)
-
-#define GPIO157_GPIO		PIN_CFG(157, GPIO)
-#define GPIO157_KP_O7		PIN_CFG(157, ALT_A)
-#define GPIO157_LCD_D28		PIN_CFG(157, ALT_B)
-#define GPIO157_STMAPE_DAT2	PIN_CFG(157, ALT_C)
-
-#define GPIO158_GPIO		PIN_CFG(158, GPIO)
-#define GPIO158_KP_O6		PIN_CFG(158, ALT_A)
-#define GPIO158_LCD_D29		PIN_CFG(158, ALT_B)
-#define GPIO158_STMAPE_DAT1	PIN_CFG(158, ALT_C)
-
-#define GPIO159_GPIO		PIN_CFG(159, GPIO)
-#define GPIO159_KP_O5		PIN_CFG(159, ALT_A)
-#define GPIO159_LCD_D30		PIN_CFG(159, ALT_B)
-#define GPIO159_STMAPE_DAT0	PIN_CFG(159, ALT_C)
-
-#define GPIO160_GPIO		PIN_CFG(160, GPIO)
-#define GPIO160_KP_O4		PIN_CFG(160, ALT_A)
-#define GPIO160_LCD_D31		PIN_CFG(160, ALT_B)
-#define GPIO160_NONE		PIN_CFG(160, ALT_C)
-
-#define GPIO161_GPIO		PIN_CFG(161, GPIO)
-#define GPIO161_KP_I3		PIN_CFG(161, ALT_A)
-#define GPIO161_LCD_D32		PIN_CFG(161, ALT_B)
-#define GPIO161_UARTMOD_RXD	PIN_CFG(161, ALT_C)
-
-#define GPIO162_GPIO		PIN_CFG(162, GPIO)
-#define GPIO162_KP_I2		PIN_CFG(162, ALT_A)
-#define GPIO162_LCD_D33		PIN_CFG(162, ALT_B)
-#define GPIO162_UARTMOD_TXD	PIN_CFG(162, ALT_C)
-
-#define GPIO163_GPIO		PIN_CFG(163, GPIO)
-#define GPIO163_KP_I1		PIN_CFG(163, ALT_A)
-#define GPIO163_LCD_D34		PIN_CFG(163, ALT_B)
-#define GPIO163_STMMOD_CLK	PIN_CFG(163, ALT_C)
-
-#define GPIO164_GPIO		PIN_CFG(164, GPIO)
-#define GPIO164_KP_I0		PIN_CFG(164, ALT_A)
-#define GPIO164_LCD_D35		PIN_CFG(164, ALT_B)
-#define GPIO164_STMMOD_DAT3	PIN_CFG(164, ALT_C)
-
-#define GPIO165_GPIO		PIN_CFG(165, GPIO)
-#define GPIO165_KP_O3		PIN_CFG(165, ALT_A)
-#define GPIO165_LCD_D36		PIN_CFG(165, ALT_B)
-#define GPIO165_STMMOD_DAT2	PIN_CFG(165, ALT_C)
-
-#define GPIO166_GPIO		PIN_CFG(166, GPIO)
-#define GPIO166_KP_O2		PIN_CFG(166, ALT_A)
-#define GPIO166_LCD_D37		PIN_CFG(166, ALT_B)
-#define GPIO166_STMMOD_DAT1	PIN_CFG(166, ALT_C)
-
-#define GPIO167_GPIO		PIN_CFG(167, GPIO)
-#define GPIO167_KP_O1		PIN_CFG(167, ALT_A)
-#define GPIO167_LCD_D38		PIN_CFG(167, ALT_B)
-#define GPIO167_STMMOD_DAT0	PIN_CFG(167, ALT_C)
-
-#define GPIO168_GPIO		PIN_CFG(168, GPIO)
-#define GPIO168_KP_O0		PIN_CFG(168, ALT_A)
-#define GPIO168_LCD_D39		PIN_CFG(168, ALT_B)
-#define GPIO168_NONE		PIN_CFG(168, ALT_C)
-
-#define GPIO169_GPIO		PIN_CFG(169, GPIO)
-#define GPIO169_RF_PURn		PIN_CFG(169, ALT_A)
-#define GPIO169_LCDA_DE		PIN_CFG(169, ALT_B)
-#define GPIO169_USBSIM_PDC	PIN_CFG(169, ALT_C)
-
-#define GPIO170_GPIO		PIN_CFG(170, GPIO)
-#define GPIO170_MODEM_STATE	PIN_CFG(170, ALT_A)
-#define GPIO170_LCDA_VSO	PIN_CFG(170, ALT_B)
-#define GPIO170_KP_SKA1		PIN_CFG(170, ALT_C)
-
-#define GPIO171_GPIO		PIN_CFG(171, GPIO)
-#define GPIO171_MODEM_PWREN	PIN_CFG(171, ALT_A)
-#define GPIO171_LCDA_HSO	PIN_CFG(171, ALT_B)
-#define GPIO171_KP_SKB1		PIN_CFG(171, ALT_C)
-
-#define GPIO192_GPIO		PIN_CFG(192, GPIO)
-#define GPIO192_MSP2_SCK	PIN_CFG(192, ALT_A)
-
-#define GPIO193_GPIO		PIN_CFG(193, GPIO)
-#define GPIO193_MSP2_TXD	PIN_CFG(193, ALT_A)
-
-#define GPIO194_GPIO		PIN_CFG(194, GPIO)
-#define GPIO194_MSP2_TCK	PIN_CFG(194, ALT_A)
-
-#define GPIO195_GPIO		PIN_CFG(195, GPIO)
-#define GPIO195_MSP2_TFS	PIN_CFG(195, ALT_A)
-
-#define GPIO196_GPIO		PIN_CFG(196, GPIO)
-#define GPIO196_MSP2_RXD	PIN_CFG(196, ALT_A)
-
-#define GPIO197_GPIO		PIN_CFG(197, GPIO)
-#define GPIO197_MC4_DAT3	PIN_CFG_INPUT(197, ALT_A, PULLUP)
-
-#define GPIO198_GPIO		PIN_CFG(198, GPIO)
-#define GPIO198_MC4_DAT2	PIN_CFG_INPUT(198, ALT_A, PULLUP)
-
-#define GPIO199_GPIO		PIN_CFG(199, GPIO)
-#define GPIO199_MC4_DAT1	PIN_CFG_INPUT(199, ALT_A, PULLUP)
-
-#define GPIO200_GPIO		PIN_CFG(200, GPIO)
-#define GPIO200_MC4_DAT0	PIN_CFG_INPUT(200, ALT_A, PULLUP)
-
-#define GPIO201_GPIO		PIN_CFG(201, GPIO)
-#define GPIO201_MC4_CMD		PIN_CFG_INPUT(201, ALT_A, PULLUP)
-
-#define GPIO202_GPIO		PIN_CFG(202, GPIO)
-#define GPIO202_MC4_FBCLK	PIN_CFG_INPUT(202, ALT_A, PULLUP)
-#define GPIO202_PWL		PIN_CFG(202, ALT_B)
-#define GPIO202_MC4_RSTN	PIN_CFG(202, ALT_C)
-
-#define GPIO203_GPIO		PIN_CFG(203, GPIO)
-#define GPIO203_MC4_CLK		PIN_CFG_INPUT(203, ALT_A, PULLUP)
-
-#define GPIO204_GPIO		PIN_CFG(204, GPIO)
-#define GPIO204_MC4_DAT7	PIN_CFG_INPUT(204, ALT_A, PULLUP)
-
-#define GPIO205_GPIO		PIN_CFG(205, GPIO)
-#define GPIO205_MC4_DAT6	PIN_CFG_INPUT(205, ALT_A, PULLUP)
-
-#define GPIO206_GPIO		PIN_CFG(206, GPIO)
-#define GPIO206_MC4_DAT5	PIN_CFG_INPUT(206, ALT_A, PULLUP)
-
-#define GPIO207_GPIO		PIN_CFG(207, GPIO)
-#define GPIO207_MC4_DAT4	PIN_CFG_INPUT(207, ALT_A, PULLUP)
-
-#define GPIO208_GPIO		PIN_CFG(208, GPIO)
-#define GPIO208_MC1_CLK		PIN_CFG(208, ALT_A)
-
-#define GPIO209_GPIO		PIN_CFG(209, GPIO)
-#define GPIO209_MC1_FBCLK	PIN_CFG(209, ALT_A)
-#define GPIO209_SPI1_CLK	PIN_CFG(209, ALT_B)
-
-#define GPIO210_GPIO		PIN_CFG(210, GPIO)
-#define GPIO210_MC1_CMD		PIN_CFG(210, ALT_A)
-
-#define GPIO211_GPIO		PIN_CFG(211, GPIO)
-#define GPIO211_MC1_DAT0	PIN_CFG(211, ALT_A)
-
-#define GPIO212_GPIO		PIN_CFG(212, GPIO)
-#define GPIO212_MC1_DAT1	PIN_CFG(212, ALT_A)
-#define GPIO212_SPI1_FRM	PIN_CFG(212, ALT_B)
-
-#define GPIO213_GPIO		PIN_CFG(213, GPIO)
-#define GPIO213_MC1_DAT2	PIN_CFG(213, ALT_A)
-#define GPIO213_SPI1_TXD	PIN_CFG(213, ALT_B)
-
-#define GPIO214_GPIO		PIN_CFG(214, GPIO)
-#define GPIO214_MC1_DAT3	PIN_CFG(214, ALT_A)
-#define GPIO214_SPI1_RXD	PIN_CFG(214, ALT_B)
-
-#define GPIO215_GPIO		PIN_CFG(215, GPIO)
-#define GPIO215_MC1_CMDDIR	PIN_CFG(215, ALT_A)
-#define GPIO215_MC3_DAT2DIR	PIN_CFG(215, ALT_B)
-#define GPIO215_CLKOUT1		PIN_CFG(215, ALT_C)
-#define GPIO215_SPI2_TXD	PIN_CFG(215, ALT_C)
-
-#define GPIO216_GPIO		PIN_CFG(216, GPIO)
-#define GPIO216_MC1_DAT2DIR	PIN_CFG(216, ALT_A)
-#define GPIO216_MC3_CMDDIR	PIN_CFG(216, ALT_B)
-#define GPIO216_I2C3_SDA	PIN_CFG(216, ALT_C)
-#define GPIO216_SPI2_FRM	PIN_CFG(216, ALT_C)
-
-#define GPIO217_GPIO		PIN_CFG(217, GPIO)
-#define GPIO217_MC1_DAT0DIR	PIN_CFG(217, ALT_A)
-#define GPIO217_MC3_DAT31DIR	PIN_CFG(217, ALT_B)
-#define GPIO217_CLKOUT2		PIN_CFG(217, ALT_C)
-#define GPIO217_SPI2_CLK	PIN_CFG(217, ALT_C)
-
-#define GPIO218_GPIO		PIN_CFG(218, GPIO)
-#define GPIO218_MC1_DAT31DIR	PIN_CFG(218, ALT_A)
-#define GPIO218_MC3_DAT0DIR	PIN_CFG(218, ALT_B)
-#define GPIO218_I2C3_SCL	PIN_CFG(218, ALT_C)
-#define GPIO218_SPI2_RXD	PIN_CFG(218, ALT_C)
-
-#define GPIO219_GPIO		PIN_CFG(219, GPIO)
-#define GPIO219_HSIR_FLA0	PIN_CFG(219, ALT_A)
-#define GPIO219_MC3_CLK		PIN_CFG(219, ALT_B)
-
-#define GPIO220_GPIO		PIN_CFG(220, GPIO)
-#define GPIO220_HSIR_DAT0	PIN_CFG(220, ALT_A)
-#define GPIO220_MC3_FBCLK	PIN_CFG(220, ALT_B)
-#define GPIO220_SPI0_CLK	PIN_CFG(220, ALT_C)
-
-#define GPIO221_GPIO		PIN_CFG(221, GPIO)
-#define GPIO221_HSIR_RDY0	PIN_CFG(221, ALT_A)
-#define GPIO221_MC3_CMD		PIN_CFG(221, ALT_B)
-
-#define GPIO222_GPIO		PIN_CFG(222, GPIO)
-#define GPIO222_HSIT_FLA0	PIN_CFG(222, ALT_A)
-#define GPIO222_MC3_DAT0	PIN_CFG(222, ALT_B)
-
-#define GPIO223_GPIO		PIN_CFG(223, GPIO)
-#define GPIO223_HSIT_DAT0	PIN_CFG(223, ALT_A)
-#define GPIO223_MC3_DAT1	PIN_CFG(223, ALT_B)
-#define GPIO223_SPI0_FRM	PIN_CFG(223, ALT_C)
-
-#define GPIO224_GPIO		PIN_CFG(224, GPIO)
-#define GPIO224_HSIT_RDY0	PIN_CFG(224, ALT_A)
-#define GPIO224_MC3_DAT2	PIN_CFG(224, ALT_B)
-#define GPIO224_SPI0_TXD	PIN_CFG(224, ALT_C)
-
-#define GPIO225_GPIO		PIN_CFG(225, GPIO)
-#define GPIO225_HSIT_CAWAKE0	PIN_CFG(225, ALT_A)
-#define GPIO225_MC3_DAT3	PIN_CFG(225, ALT_B)
-#define GPIO225_SPI0_RXD	PIN_CFG(225, ALT_C)
-
-#define GPIO226_GPIO		PIN_CFG(226, GPIO)
-#define GPIO226_HSIT_ACWAKE0	PIN_CFG(226, ALT_A)
-#define GPIO226_PWL		PIN_CFG(226, ALT_B)
-#define GPIO226_USBSIM_PDC	PIN_CFG(226, ALT_C)
-
-#define GPIO227_GPIO		PIN_CFG(227, GPIO)
-#define GPIO227_CLKOUT1		PIN_CFG(227, ALT_A)
-
-#define GPIO228_GPIO		PIN_CFG(228, GPIO)
-#define GPIO228_CLKOUT2		PIN_CFG(228, ALT_A)
-
-#define GPIO229_GPIO		PIN_CFG(229, GPIO)
-#define GPIO229_CLKOUT1		PIN_CFG(229, ALT_A)
-#define GPIO229_PWL		PIN_CFG(229, ALT_B)
-#define GPIO229_I2C3_SDA	PIN_CFG(229, ALT_C)
-
-#define GPIO230_GPIO		PIN_CFG(230, GPIO)
-#define GPIO230_CLKOUT2		PIN_CFG(230, ALT_A)
-#define GPIO230_PWL		PIN_CFG(230, ALT_B)
-#define GPIO230_I2C3_SCL	PIN_CFG(230, ALT_C)
-
-#define GPIO256_GPIO		PIN_CFG(256, GPIO)
-#define GPIO256_USB_NXT		PIN_CFG(256, ALT_A)
-
-#define GPIO257_GPIO		PIN_CFG(257, GPIO)
-#define GPIO257_USB_STP		PIN_CFG(257, ALT_A)
-
-#define GPIO258_GPIO		PIN_CFG(258, GPIO)
-#define GPIO258_USB_XCLK	PIN_CFG(258, ALT_A)
-#define GPIO258_NONE		PIN_CFG(258, ALT_B)
-#define GPIO258_DDR_TRIG	PIN_CFG(258, ALT_C)
-
-#define GPIO259_GPIO		PIN_CFG(259, GPIO)
-#define GPIO259_USB_DIR		PIN_CFG(259, ALT_A)
-
-#define GPIO260_GPIO		PIN_CFG(260, GPIO)
-#define GPIO260_USB_DAT7	PIN_CFG(260, ALT_A)
-
-#define GPIO261_GPIO		PIN_CFG(261, GPIO)
-#define GPIO261_USB_DAT6	PIN_CFG(261, ALT_A)
-
-#define GPIO262_GPIO		PIN_CFG(262, GPIO)
-#define GPIO262_USB_DAT5	PIN_CFG(262, ALT_A)
-
-#define GPIO263_GPIO		PIN_CFG(263, GPIO)
-#define GPIO263_USB_DAT4	PIN_CFG(263, ALT_A)
-
-#define GPIO264_GPIO		PIN_CFG(264, GPIO)
-#define GPIO264_USB_DAT3	PIN_CFG(264, ALT_A)
-
-#define GPIO265_GPIO		PIN_CFG(265, GPIO)
-#define GPIO265_USB_DAT2	PIN_CFG(265, ALT_A)
-
-#define GPIO266_GPIO		PIN_CFG(266, GPIO)
-#define GPIO266_USB_DAT1	PIN_CFG(266, ALT_A)
-
-#define GPIO267_GPIO		PIN_CFG(267, GPIO)
-#define GPIO267_USB_DAT0	PIN_CFG(267, ALT_A)
-
-#endif
diff --git a/arch/arm/mach-ux500/setup.h b/arch/arm/mach-ux500/setup.h
index cad3ca86c540..656324aad18e 100644
--- a/arch/arm/mach-ux500/setup.h
+++ b/arch/arm/mach-ux500/setup.h
@@ -11,10 +11,13 @@
 #ifndef __ASM_ARCH_SETUP_H
 #define __ASM_ARCH_SETUP_H
 
+#include <asm/mach/arch.h>
 #include <asm/mach/time.h>
 #include <linux/init.h>
 #include <linux/mfd/abx500/ab8500.h>
 
+void ux500_restart(enum reboot_mode mode, const char *cmd);
+
 void __init ux500_map_io(void);
 extern void __init u8500_map_io(void);
 
diff --git a/arch/arm/mach-versatile/include/mach/debug-macro.S b/arch/arm/mach-versatile/include/mach/debug-macro.S
deleted file mode 100644
index d0fbd7f1cb00..000000000000
--- a/arch/arm/mach-versatile/include/mach/debug-macro.S
+++ /dev/null
@@ -1,21 +0,0 @@
-/* arch/arm/mach-versatile/include/mach/debug-macro.S
- *
- * Debugging macro include header
- *
- *  Copyright (C) 1994-1999 Russell King
- *  Moved from linux/arch/arm/kernel/debug.S by Ben Dooks
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
-*/
-
-		.macro	addruart, rp, rv, tmp
-		mov	\rp,      #0x001F0000
-		orr	\rp, \rp, #0x00001000
-		orr	\rv, \rp, #0xf1000000	@ virtual base
-		orr	\rp, \rp,  #0x10000000	@ physical base
-		.endm
-
-#include <asm/hardware/debug-pl01x.S>
diff --git a/arch/arm/mach-versatile/include/mach/platform.h b/arch/arm/mach-versatile/include/mach/platform.h
index ec087407b163..6f938ccb0c54 100644
--- a/arch/arm/mach-versatile/include/mach/platform.h
+++ b/arch/arm/mach-versatile/include/mach/platform.h
@@ -231,12 +231,14 @@
 /* PCI space */
 #define VERSATILE_PCI_BASE             0x41000000	/* PCI Interface */
 #define VERSATILE_PCI_CFG_BASE	       0x42000000
+#define VERSATILE_PCI_IO_BASE          0x43000000
 #define VERSATILE_PCI_MEM_BASE0        0x44000000
 #define VERSATILE_PCI_MEM_BASE1        0x50000000
 #define VERSATILE_PCI_MEM_BASE2        0x60000000
 /* Sizes of above maps */
 #define VERSATILE_PCI_BASE_SIZE	       0x01000000
 #define VERSATILE_PCI_CFG_BASE_SIZE    0x02000000
+#define VERSATILE_PCI_IO_BASE_SIZE     0x01000000
 #define VERSATILE_PCI_MEM_BASE0_SIZE   0x0c000000	/* 32Mb */
 #define VERSATILE_PCI_MEM_BASE1_SIZE   0x10000000	/* 256Mb */
 #define VERSATILE_PCI_MEM_BASE2_SIZE   0x10000000	/* 256Mb */
diff --git a/arch/arm/mach-versatile/pci.c b/arch/arm/mach-versatile/pci.c
index e92e5e0705bc..c97be4ea76d2 100644
--- a/arch/arm/mach-versatile/pci.c
+++ b/arch/arm/mach-versatile/pci.c
@@ -43,9 +43,9 @@
 #define PCI_IMAP0		__IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x0)
 #define PCI_IMAP1		__IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x4)
 #define PCI_IMAP2		__IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x8)
-#define PCI_SMAP0		__IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x10)
-#define PCI_SMAP1		__IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x14)
-#define PCI_SMAP2		__IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x18)
+#define PCI_SMAP0		__IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x14)
+#define PCI_SMAP1		__IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x18)
+#define PCI_SMAP2		__IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x1c)
 #define PCI_SELFID		__IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0xc)
 
 #define DEVICE_ID_OFFSET		0x00
@@ -170,8 +170,8 @@ static struct pci_ops pci_versatile_ops = {
 	.write	= versatile_write_config,
 };
 
-static struct resource io_mem = {
-	.name	= "PCI I/O space",
+static struct resource unused_mem = {
+	.name	= "PCI unused",
 	.start	= VERSATILE_PCI_MEM_BASE0,
 	.end	= VERSATILE_PCI_MEM_BASE0+VERSATILE_PCI_MEM_BASE0_SIZE-1,
 	.flags	= IORESOURCE_MEM,
@@ -195,9 +195,9 @@ static int __init pci_versatile_setup_resources(struct pci_sys_data *sys)
 {
 	int ret = 0;
 
-	ret = request_resource(&iomem_resource, &io_mem);
+	ret = request_resource(&iomem_resource, &unused_mem);
 	if (ret) {
-		printk(KERN_ERR "PCI: unable to allocate I/O "
+		printk(KERN_ERR "PCI: unable to allocate unused "
 		       "memory region (%d)\n", ret);
 		goto out;
 	}
@@ -205,7 +205,7 @@ static int __init pci_versatile_setup_resources(struct pci_sys_data *sys)
 	if (ret) {
 		printk(KERN_ERR "PCI: unable to allocate non-prefetchable "
 		       "memory region (%d)\n", ret);
-		goto release_io_mem;
+		goto release_unused_mem;
 	}
 	ret = request_resource(&iomem_resource, &pre_mem);
 	if (ret) {
@@ -225,8 +225,8 @@ static int __init pci_versatile_setup_resources(struct pci_sys_data *sys)
 
  release_non_mem:
 	release_resource(&non_mem);
- release_io_mem:
-	release_resource(&io_mem);
+ release_unused_mem:
+	release_resource(&unused_mem);
  out:
 	return ret;
 }
@@ -246,7 +246,7 @@ int __init pci_versatile_setup(int nr, struct pci_sys_data *sys)
 		goto out;
 	}
 
-	ret = pci_ioremap_io(0, VERSATILE_PCI_MEM_BASE0);
+	ret = pci_ioremap_io(0, VERSATILE_PCI_IO_BASE);
 	if (ret)
 		goto out;
 
@@ -295,6 +295,19 @@ int __init pci_versatile_setup(int nr, struct pci_sys_data *sys)
 	__raw_writel(PHYS_OFFSET, local_pci_cfg_base + PCI_BASE_ADDRESS_2);
 
 	/*
+	 * For many years the kernel and QEMU were symbiotically buggy
+	 * in that they both assumed the same broken IRQ mapping.
+	 * QEMU therefore attempts to auto-detect old broken kernels
+	 * so that they still work on newer QEMU as they did on old
+	 * QEMU. Since we now use the correct (ie matching-hardware)
+	 * IRQ mapping we write a definitely different value to a
+	 * PCI_INTERRUPT_LINE register to tell QEMU that we expect
+	 * real hardware behaviour and it need not be backwards
+	 * compatible for us. This write is harmless on real hardware.
+	 */
+	__raw_writel(0, VERSATILE_PCI_VIRT_BASE+PCI_INTERRUPT_LINE);
+
+	/*
 	 * Do not to map Versatile FPGA PCI device into memory space
 	 */
 	pci_slot_ignore |= (1 << myslot);
@@ -327,13 +340,13 @@ static int __init versatile_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
 	int irq;
 
-	/* slot,  pin,	irq
-	 *  24     1     IRQ_SIC_PCI0
-	 *  25     1     IRQ_SIC_PCI1
-	 *  26     1     IRQ_SIC_PCI2
-	 *  27     1     IRQ_SIC_PCI3
+	/*
+	 * Slot	INTA	INTB	INTC	INTD
+	 * 31	PCI1	PCI2	PCI3	PCI0
+	 * 30	PCI0	PCI1	PCI2	PCI3
+	 * 29	PCI3	PCI0	PCI1	PCI2
 	 */
-	irq = IRQ_SIC_PCI0 + ((slot - 24 + pin - 1) & 3);
+	irq = IRQ_SIC_PCI0 + ((slot + 2 + pin - 1) & 3);
 
 	return irq;
 }
diff --git a/arch/arm/mach-vexpress/Kconfig b/arch/arm/mach-vexpress/Kconfig
index b8bbabec6310..365795447804 100644
--- a/arch/arm/mach-vexpress/Kconfig
+++ b/arch/arm/mach-vexpress/Kconfig
@@ -10,7 +10,7 @@ config ARCH_VEXPRESS
 	select CPU_V7
 	select GENERIC_CLOCKEVENTS
 	select HAVE_ARM_SCU if SMP
-	select HAVE_ARM_TWD if LOCAL_TIMERS
+	select HAVE_ARM_TWD if SMP
 	select HAVE_CLK
 	select HAVE_PATA_PLATFORM
 	select HAVE_SMP
@@ -66,4 +66,12 @@ config ARCH_VEXPRESS_DCSCB
 	  This is needed to provide CPU and cluster power management
 	  on RTSM implementing big.LITTLE.
 
+config ARCH_VEXPRESS_TC2_PM
+	bool "Versatile Express TC2 power management"
+	depends on MCPM
+	select ARM_CCI
+	help
+	  Support for CPU and cluster power management on Versatile Express
+	  with a TC2 (A15x2 A7x3) big.LITTLE core tile.
+
 endmenu
diff --git a/arch/arm/mach-vexpress/Makefile b/arch/arm/mach-vexpress/Makefile
index 48ba89a8149f..505e64ab3eae 100644
--- a/arch/arm/mach-vexpress/Makefile
+++ b/arch/arm/mach-vexpress/Makefile
@@ -7,5 +7,8 @@ ccflags-$(CONFIG_ARCH_MULTIPLATFORM) := -I$(srctree)/$(src)/include \
 obj-y					:= v2m.o
 obj-$(CONFIG_ARCH_VEXPRESS_CA9X4)	+= ct-ca9x4.o
 obj-$(CONFIG_ARCH_VEXPRESS_DCSCB)	+= dcscb.o	dcscb_setup.o
+CFLAGS_dcscb.o				+= -march=armv7-a
+obj-$(CONFIG_ARCH_VEXPRESS_TC2_PM)	+= tc2_pm.o spc.o
+CFLAGS_tc2_pm.o				+= -march=armv7-a
 obj-$(CONFIG_SMP)			+= platsmp.o
 obj-$(CONFIG_HOTPLUG_CPU)		+= hotplug.o
diff --git a/arch/arm/mach-vexpress/dcscb.c b/arch/arm/mach-vexpress/dcscb.c
index 16d57a8a9d5a..3a6384c6c435 100644
--- a/arch/arm/mach-vexpress/dcscb.c
+++ b/arch/arm/mach-vexpress/dcscb.c
@@ -136,14 +136,35 @@ static void dcscb_power_down(void)
 		/*
 		 * Flush all cache levels for this cluster.
 		 *
-		 * A15/A7 can hit in the cache with SCTLR.C=0, so we don't need
-		 * a preliminary flush here for those CPUs.  At least, that's
-		 * the theory -- without the extra flush, Linux explodes on
-		 * RTSM (to be investigated).
+		 * To do so we do:
+		 * - Clear the SCTLR.C bit to prevent further cache allocations
+		 * - Flush the whole cache
+		 * - Clear the ACTLR "SMP" bit to disable local coherency
+		 *
+		 * Let's do it in the safest possible way i.e. with
+		 * no memory access within the following sequence
+		 * including to the stack.
+		 *
+		 * Note: fp is preserved to the stack explicitly prior doing
+		 * this since adding it to the clobber list is incompatible
+		 * with having CONFIG_FRAME_POINTER=y.
 		 */
-		flush_cache_all();
-		set_cr(get_cr() & ~CR_C);
-		flush_cache_all();
+		asm volatile(
+		"str	fp, [sp, #-4]! \n\t"
+		"mrc	p15, 0, r0, c1, c0, 0	@ get CR \n\t"
+		"bic	r0, r0, #"__stringify(CR_C)" \n\t"
+		"mcr	p15, 0, r0, c1, c0, 0	@ set CR \n\t"
+		"isb	\n\t"
+		"bl	v7_flush_dcache_all \n\t"
+		"clrex	\n\t"
+		"mrc	p15, 0, r0, c1, c0, 1	@ get AUXCR \n\t"
+		"bic	r0, r0, #(1 << 6)	@ disable local coherency \n\t"
+		"mcr	p15, 0, r0, c1, c0, 1	@ set AUXCR \n\t"
+		"isb	\n\t"
+		"dsb	\n\t"
+		"ldr	fp, [sp], #4"
+		: : : "r0","r1","r2","r3","r4","r5","r6","r7",
+		      "r9","r10","lr","memory");
 
 		/*
 		 * This is a harmless no-op.  On platforms with a real
@@ -152,9 +173,6 @@ static void dcscb_power_down(void)
 		 */
 		outer_flush_all();
 
-		/* Disable local coherency by clearing the ACTLR "SMP" bit: */
-		set_auxcr(get_auxcr() & ~(1 << 6));
-
 		/*
 		 * Disable cluster-level coherency by masking
 		 * incoming snoops and DVM messages:
@@ -167,18 +185,24 @@ static void dcscb_power_down(void)
 
 		/*
 		 * Flush the local CPU cache.
-		 *
-		 * A15/A7 can hit in the cache with SCTLR.C=0, so we don't need
-		 * a preliminary flush here for those CPUs.  At least, that's
-		 * the theory -- without the extra flush, Linux explodes on
-		 * RTSM (to be investigated).
+		 * Let's do it in the safest possible way as above.
 		 */
-		flush_cache_louis();
-		set_cr(get_cr() & ~CR_C);
-		flush_cache_louis();
-
-		/* Disable local coherency by clearing the ACTLR "SMP" bit: */
-		set_auxcr(get_auxcr() & ~(1 << 6));
+		asm volatile(
+		"str	fp, [sp, #-4]! \n\t"
+		"mrc	p15, 0, r0, c1, c0, 0	@ get CR \n\t"
+		"bic	r0, r0, #"__stringify(CR_C)" \n\t"
+		"mcr	p15, 0, r0, c1, c0, 0	@ set CR \n\t"
+		"isb	\n\t"
+		"bl	v7_flush_dcache_louis \n\t"
+		"clrex	\n\t"
+		"mrc	p15, 0, r0, c1, c0, 1	@ get AUXCR \n\t"
+		"bic	r0, r0, #(1 << 6)	@ disable local coherency \n\t"
+		"mcr	p15, 0, r0, c1, c0, 1	@ set AUXCR \n\t"
+		"isb	\n\t"
+		"dsb	\n\t"
+		"ldr	fp, [sp], #4"
+		: : : "r0","r1","r2","r3","r4","r5","r6","r7",
+		      "r9","r10","lr","memory");
 	}
 
 	__mcpm_cpu_down(cpu, cluster);
diff --git a/arch/arm/mach-vexpress/spc.c b/arch/arm/mach-vexpress/spc.c
new file mode 100644
index 000000000000..eefb029197ca
--- /dev/null
+++ b/arch/arm/mach-vexpress/spc.c
@@ -0,0 +1,180 @@
+/*
+ * Versatile Express Serial Power Controller (SPC) support
+ *
+ * Copyright (C) 2013 ARM Ltd.
+ *
+ * Authors: Sudeep KarkadaNagesha <sudeep.karkadanagesha@arm.com>
+ *          Achin Gupta           <achin.gupta@arm.com>
+ *          Lorenzo Pieralisi     <lorenzo.pieralisi@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any
+ * kind, whether express or implied; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/err.h>
+#include <linux/io.h>
+#include <linux/slab.h>
+
+#include <asm/cacheflush.h>
+
+#define SPCLOG "vexpress-spc: "
+
+/* SPC wake-up IRQs status and mask */
+#define WAKE_INT_MASK		0x24
+#define WAKE_INT_RAW		0x28
+#define WAKE_INT_STAT		0x2c
+/* SPC power down registers */
+#define A15_PWRDN_EN		0x30
+#define A7_PWRDN_EN		0x34
+/* SPC per-CPU mailboxes */
+#define A15_BX_ADDR0		0x68
+#define A7_BX_ADDR0		0x78
+
+/* wake-up interrupt masks */
+#define GBL_WAKEUP_INT_MSK	(0x3 << 10)
+
+/* TC2 static dual-cluster configuration */
+#define MAX_CLUSTERS		2
+
+struct ve_spc_drvdata {
+	void __iomem *baseaddr;
+	/*
+	 * A15s cluster identifier
+	 * It corresponds to A15 processors MPIDR[15:8] bitfield
+	 */
+	u32 a15_clusid;
+};
+
+static struct ve_spc_drvdata *info;
+
+static inline bool cluster_is_a15(u32 cluster)
+{
+	return cluster == info->a15_clusid;
+}
+
+/**
+ * ve_spc_global_wakeup_irq()
+ *
+ * Function to set/clear global wakeup IRQs. Not protected by locking since
+ * it might be used in code paths where normal cacheable locks are not
+ * working. Locking must be provided by the caller to ensure atomicity.
+ *
+ * @set: if true, global wake-up IRQs are set, if false they are cleared
+ */
+void ve_spc_global_wakeup_irq(bool set)
+{
+	u32 reg;
+
+	reg = readl_relaxed(info->baseaddr + WAKE_INT_MASK);
+
+	if (set)
+		reg |= GBL_WAKEUP_INT_MSK;
+	else
+		reg &= ~GBL_WAKEUP_INT_MSK;
+
+	writel_relaxed(reg, info->baseaddr + WAKE_INT_MASK);
+}
+
+/**
+ * ve_spc_cpu_wakeup_irq()
+ *
+ * Function to set/clear per-CPU wake-up IRQs. Not protected by locking since
+ * it might be used in code paths where normal cacheable locks are not
+ * working. Locking must be provided by the caller to ensure atomicity.
+ *
+ * @cluster: mpidr[15:8] bitfield describing cluster affinity level
+ * @cpu: mpidr[7:0] bitfield describing cpu affinity level
+ * @set: if true, wake-up IRQs are set, if false they are cleared
+ */
+void ve_spc_cpu_wakeup_irq(u32 cluster, u32 cpu, bool set)
+{
+	u32 mask, reg;
+
+	if (cluster >= MAX_CLUSTERS)
+		return;
+
+	mask = 1 << cpu;
+
+	if (!cluster_is_a15(cluster))
+		mask <<= 4;
+
+	reg = readl_relaxed(info->baseaddr + WAKE_INT_MASK);
+
+	if (set)
+		reg |= mask;
+	else
+		reg &= ~mask;
+
+	writel_relaxed(reg, info->baseaddr + WAKE_INT_MASK);
+}
+
+/**
+ * ve_spc_set_resume_addr() - set the jump address used for warm boot
+ *
+ * @cluster: mpidr[15:8] bitfield describing cluster affinity level
+ * @cpu: mpidr[7:0] bitfield describing cpu affinity level
+ * @addr: physical resume address
+ */
+void ve_spc_set_resume_addr(u32 cluster, u32 cpu, u32 addr)
+{
+	void __iomem *baseaddr;
+
+	if (cluster >= MAX_CLUSTERS)
+		return;
+
+	if (cluster_is_a15(cluster))
+		baseaddr = info->baseaddr + A15_BX_ADDR0 + (cpu << 2);
+	else
+		baseaddr = info->baseaddr + A7_BX_ADDR0 + (cpu << 2);
+
+	writel_relaxed(addr, baseaddr);
+}
+
+/**
+ * ve_spc_powerdown()
+ *
+ * Function to enable/disable cluster powerdown. Not protected by locking
+ * since it might be used in code paths where normal cacheable locks are not
+ * working. Locking must be provided by the caller to ensure atomicity.
+ *
+ * @cluster: mpidr[15:8] bitfield describing cluster affinity level
+ * @enable: if true enables powerdown, if false disables it
+ */
+void ve_spc_powerdown(u32 cluster, bool enable)
+{
+	u32 pwdrn_reg;
+
+	if (cluster >= MAX_CLUSTERS)
+		return;
+
+	pwdrn_reg = cluster_is_a15(cluster) ? A15_PWRDN_EN : A7_PWRDN_EN;
+	writel_relaxed(enable, info->baseaddr + pwdrn_reg);
+}
+
+int __init ve_spc_init(void __iomem *baseaddr, u32 a15_clusid)
+{
+	info = kzalloc(sizeof(*info), GFP_KERNEL);
+	if (!info) {
+		pr_err(SPCLOG "unable to allocate mem\n");
+		return -ENOMEM;
+	}
+
+	info->baseaddr = baseaddr;
+	info->a15_clusid = a15_clusid;
+
+	/*
+	 * Multi-cluster systems may need this data when non-coherent, during
+	 * cluster power-up/power-down. Make sure driver info reaches main
+	 * memory.
+	 */
+	sync_cache_w(info);
+	sync_cache_w(&info);
+
+	return 0;
+}
diff --git a/arch/arm/mach-vexpress/spc.h b/arch/arm/mach-vexpress/spc.h
new file mode 100644
index 000000000000..5f7e4a446a17
--- /dev/null
+++ b/arch/arm/mach-vexpress/spc.h
@@ -0,0 +1,24 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * Copyright (C) 2012 ARM Limited
+ */
+
+
+#ifndef __SPC_H_
+#define __SPC_H_
+
+int __init ve_spc_init(void __iomem *base, u32 a15_clusid);
+void ve_spc_global_wakeup_irq(bool set);
+void ve_spc_cpu_wakeup_irq(u32 cluster, u32 cpu, bool set);
+void ve_spc_set_resume_addr(u32 cluster, u32 cpu, u32 addr);
+void ve_spc_powerdown(u32 cluster, bool enable);
+
+#endif
diff --git a/arch/arm/mach-vexpress/tc2_pm.c b/arch/arm/mach-vexpress/tc2_pm.c
new file mode 100644
index 000000000000..e6eb48192912
--- /dev/null
+++ b/arch/arm/mach-vexpress/tc2_pm.c
@@ -0,0 +1,363 @@
+/*
+ * arch/arm/mach-vexpress/tc2_pm.c - TC2 power management support
+ *
+ * Created by:	Nicolas Pitre, October 2012
+ * Copyright:	(C) 2012-2013  Linaro Limited
+ *
+ * Some portions of this file were originally written by Achin Gupta
+ * Copyright:   (C) 2012  ARM Limited
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/of_address.h>
+#include <linux/spinlock.h>
+#include <linux/errno.h>
+#include <linux/irqchip/arm-gic.h>
+
+#include <asm/mcpm.h>
+#include <asm/proc-fns.h>
+#include <asm/cacheflush.h>
+#include <asm/cputype.h>
+#include <asm/cp15.h>
+
+#include <linux/arm-cci.h>
+
+#include "spc.h"
+
+/* SCC conf registers */
+#define A15_CONF		0x400
+#define A7_CONF			0x500
+#define SYS_INFO		0x700
+#define SPC_BASE		0xb00
+
+/*
+ * We can't use regular spinlocks. In the switcher case, it is possible
+ * for an outbound CPU to call power_down() after its inbound counterpart
+ * is already live using the same logical CPU number which trips lockdep
+ * debugging.
+ */
+static arch_spinlock_t tc2_pm_lock = __ARCH_SPIN_LOCK_UNLOCKED;
+
+#define TC2_CLUSTERS			2
+#define TC2_MAX_CPUS_PER_CLUSTER	3
+
+static unsigned int tc2_nr_cpus[TC2_CLUSTERS];
+
+/* Keep per-cpu usage count to cope with unordered up/down requests */
+static int tc2_pm_use_count[TC2_MAX_CPUS_PER_CLUSTER][TC2_CLUSTERS];
+
+#define tc2_cluster_unused(cluster) \
+	(!tc2_pm_use_count[0][cluster] && \
+	 !tc2_pm_use_count[1][cluster] && \
+	 !tc2_pm_use_count[2][cluster])
+
+static int tc2_pm_power_up(unsigned int cpu, unsigned int cluster)
+{
+	pr_debug("%s: cpu %u cluster %u\n", __func__, cpu, cluster);
+	if (cluster >= TC2_CLUSTERS || cpu >= tc2_nr_cpus[cluster])
+		return -EINVAL;
+
+	/*
+	 * Since this is called with IRQs enabled, and no arch_spin_lock_irq
+	 * variant exists, we need to disable IRQs manually here.
+	 */
+	local_irq_disable();
+	arch_spin_lock(&tc2_pm_lock);
+
+	if (tc2_cluster_unused(cluster))
+		ve_spc_powerdown(cluster, false);
+
+	tc2_pm_use_count[cpu][cluster]++;
+	if (tc2_pm_use_count[cpu][cluster] == 1) {
+		ve_spc_set_resume_addr(cluster, cpu,
+				       virt_to_phys(mcpm_entry_point));
+		ve_spc_cpu_wakeup_irq(cluster, cpu, true);
+	} else if (tc2_pm_use_count[cpu][cluster] != 2) {
+		/*
+		 * The only possible values are:
+		 * 0 = CPU down
+		 * 1 = CPU (still) up
+		 * 2 = CPU requested to be up before it had a chance
+		 *     to actually make itself down.
+		 * Any other value is a bug.
+		 */
+		BUG();
+	}
+
+	arch_spin_unlock(&tc2_pm_lock);
+	local_irq_enable();
+
+	return 0;
+}
+
+static void tc2_pm_down(u64 residency)
+{
+	unsigned int mpidr, cpu, cluster;
+	bool last_man = false, skip_wfi = false;
+
+	mpidr = read_cpuid_mpidr();
+	cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
+	cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);
+
+	pr_debug("%s: cpu %u cluster %u\n", __func__, cpu, cluster);
+	BUG_ON(cluster >= TC2_CLUSTERS || cpu >= TC2_MAX_CPUS_PER_CLUSTER);
+
+	__mcpm_cpu_going_down(cpu, cluster);
+
+	arch_spin_lock(&tc2_pm_lock);
+	BUG_ON(__mcpm_cluster_state(cluster) != CLUSTER_UP);
+	tc2_pm_use_count[cpu][cluster]--;
+	if (tc2_pm_use_count[cpu][cluster] == 0) {
+		ve_spc_cpu_wakeup_irq(cluster, cpu, true);
+		if (tc2_cluster_unused(cluster)) {
+			ve_spc_powerdown(cluster, true);
+			ve_spc_global_wakeup_irq(true);
+			last_man = true;
+		}
+	} else if (tc2_pm_use_count[cpu][cluster] == 1) {
+		/*
+		 * A power_up request went ahead of us.
+		 * Even if we do not want to shut this CPU down,
+		 * the caller expects a certain state as if the WFI
+		 * was aborted.  So let's continue with cache cleaning.
+		 */
+		skip_wfi = true;
+	} else
+		BUG();
+
+	/*
+	 * If the CPU is committed to power down, make sure
+	 * the power controller will be in charge of waking it
+	 * up upon IRQ, ie IRQ lines are cut from GIC CPU IF
+	 * to the CPU by disabling the GIC CPU IF to prevent wfi
+	 * from completing execution behind power controller back
+	 */
+	if (!skip_wfi)
+		gic_cpu_if_down();
+
+	if (last_man && __mcpm_outbound_enter_critical(cpu, cluster)) {
+		arch_spin_unlock(&tc2_pm_lock);
+
+		if (read_cpuid_part_number() == ARM_CPU_PART_CORTEX_A15) {
+			/*
+			 * On the Cortex-A15 we need to disable
+			 * L2 prefetching before flushing the cache.
+			 */
+			asm volatile(
+			"mcr	p15, 1, %0, c15, c0, 3 \n\t"
+			"isb	\n\t"
+			"dsb	"
+			: : "r" (0x400) );
+		}
+
+		/*
+		 * We need to disable and flush the whole (L1 and L2) cache.
+		 * Let's do it in the safest possible way i.e. with
+		 * no memory access within the following sequence
+		 * including the stack.
+		 *
+		 * Note: fp is preserved to the stack explicitly prior doing
+		 * this since adding it to the clobber list is incompatible
+		 * with having CONFIG_FRAME_POINTER=y.
+		 */
+		asm volatile(
+		"str	fp, [sp, #-4]! \n\t"
+		"mrc	p15, 0, r0, c1, c0, 0	@ get CR \n\t"
+		"bic	r0, r0, #"__stringify(CR_C)" \n\t"
+		"mcr	p15, 0, r0, c1, c0, 0	@ set CR \n\t"
+		"isb	\n\t"
+		"bl	v7_flush_dcache_all \n\t"
+		"clrex	\n\t"
+		"mrc	p15, 0, r0, c1, c0, 1	@ get AUXCR \n\t"
+		"bic	r0, r0, #(1 << 6)	@ disable local coherency \n\t"
+		"mcr	p15, 0, r0, c1, c0, 1	@ set AUXCR \n\t"
+		"isb	\n\t"
+		"dsb	\n\t"
+		"ldr	fp, [sp], #4"
+		: : : "r0","r1","r2","r3","r4","r5","r6","r7",
+		      "r9","r10","lr","memory");
+
+		cci_disable_port_by_cpu(mpidr);
+
+		__mcpm_outbound_leave_critical(cluster, CLUSTER_DOWN);
+	} else {
+		/*
+		 * If last man then undo any setup done previously.
+		 */
+		if (last_man) {
+			ve_spc_powerdown(cluster, false);
+			ve_spc_global_wakeup_irq(false);
+		}
+
+		arch_spin_unlock(&tc2_pm_lock);
+
+		/*
+		 * We need to disable and flush only the L1 cache.
+		 * Let's do it in the safest possible way as above.
+		 */
+		asm volatile(
+		"str	fp, [sp, #-4]! \n\t"
+		"mrc	p15, 0, r0, c1, c0, 0	@ get CR \n\t"
+		"bic	r0, r0, #"__stringify(CR_C)" \n\t"
+		"mcr	p15, 0, r0, c1, c0, 0	@ set CR \n\t"
+		"isb	\n\t"
+		"bl	v7_flush_dcache_louis \n\t"
+		"clrex	\n\t"
+		"mrc	p15, 0, r0, c1, c0, 1	@ get AUXCR \n\t"
+		"bic	r0, r0, #(1 << 6)	@ disable local coherency \n\t"
+		"mcr	p15, 0, r0, c1, c0, 1	@ set AUXCR \n\t"
+		"isb	\n\t"
+		"dsb	\n\t"
+		"ldr	fp, [sp], #4"
+		: : : "r0","r1","r2","r3","r4","r5","r6","r7",
+		      "r9","r10","lr","memory");
+	}
+
+	__mcpm_cpu_down(cpu, cluster);
+
+	/* Now we are prepared for power-down, do it: */
+	if (!skip_wfi)
+		wfi();
+
+	/* Not dead at this point?  Let our caller cope. */
+}
+
+static void tc2_pm_power_down(void)
+{
+	tc2_pm_down(0);
+}
+
+static void tc2_pm_suspend(u64 residency)
+{
+	unsigned int mpidr, cpu, cluster;
+
+	mpidr = read_cpuid_mpidr();
+	cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
+	cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);
+	ve_spc_set_resume_addr(cluster, cpu, virt_to_phys(mcpm_entry_point));
+	tc2_pm_down(residency);
+}
+
+static void tc2_pm_powered_up(void)
+{
+	unsigned int mpidr, cpu, cluster;
+	unsigned long flags;
+
+	mpidr = read_cpuid_mpidr();
+	cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
+	cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);
+
+	pr_debug("%s: cpu %u cluster %u\n", __func__, cpu, cluster);
+	BUG_ON(cluster >= TC2_CLUSTERS || cpu >= TC2_MAX_CPUS_PER_CLUSTER);
+
+	local_irq_save(flags);
+	arch_spin_lock(&tc2_pm_lock);
+
+	if (tc2_cluster_unused(cluster)) {
+		ve_spc_powerdown(cluster, false);
+		ve_spc_global_wakeup_irq(false);
+	}
+
+	if (!tc2_pm_use_count[cpu][cluster])
+		tc2_pm_use_count[cpu][cluster] = 1;
+
+	ve_spc_cpu_wakeup_irq(cluster, cpu, false);
+	ve_spc_set_resume_addr(cluster, cpu, 0);
+
+	arch_spin_unlock(&tc2_pm_lock);
+	local_irq_restore(flags);
+}
+
+static const struct mcpm_platform_ops tc2_pm_power_ops = {
+	.power_up	= tc2_pm_power_up,
+	.power_down	= tc2_pm_power_down,
+	.suspend	= tc2_pm_suspend,
+	.powered_up	= tc2_pm_powered_up,
+};
+
+static bool __init tc2_pm_usage_count_init(void)
+{
+	unsigned int mpidr, cpu, cluster;
+
+	mpidr = read_cpuid_mpidr();
+	cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
+	cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);
+
+	pr_debug("%s: cpu %u cluster %u\n", __func__, cpu, cluster);
+	if (cluster >= TC2_CLUSTERS || cpu >= tc2_nr_cpus[cluster]) {
+		pr_err("%s: boot CPU is out of bound!\n", __func__);
+		return false;
+	}
+	tc2_pm_use_count[cpu][cluster] = 1;
+	return true;
+}
+
+/*
+ * Enable cluster-level coherency, in preparation for turning on the MMU.
+ */
+static void __naked tc2_pm_power_up_setup(unsigned int affinity_level)
+{
+	asm volatile (" \n"
+"	cmp	r0, #1 \n"
+"	bxne	lr \n"
+"	b	cci_enable_port_for_self ");
+}
+
+static int __init tc2_pm_init(void)
+{
+	int ret;
+	void __iomem *scc;
+	u32 a15_cluster_id, a7_cluster_id, sys_info;
+	struct device_node *np;
+
+	/*
+	 * The power management-related features are hidden behind
+	 * SCC registers. We need to extract runtime information like
+	 * cluster ids and number of CPUs really available in clusters.
+	 */
+	np = of_find_compatible_node(NULL, NULL,
+			"arm,vexpress-scc,v2p-ca15_a7");
+	scc = of_iomap(np, 0);
+	if (!scc)
+		return -ENODEV;
+
+	a15_cluster_id = readl_relaxed(scc + A15_CONF) & 0xf;
+	a7_cluster_id = readl_relaxed(scc + A7_CONF) & 0xf;
+	if (a15_cluster_id >= TC2_CLUSTERS || a7_cluster_id >= TC2_CLUSTERS)
+		return -EINVAL;
+
+	sys_info = readl_relaxed(scc + SYS_INFO);
+	tc2_nr_cpus[a15_cluster_id] = (sys_info >> 16) & 0xf;
+	tc2_nr_cpus[a7_cluster_id] = (sys_info >> 20) & 0xf;
+
+	/*
+	 * A subset of the SCC registers is also used to communicate
+	 * with the SPC (power controller). We need to be able to
+	 * drive it very early in the boot process to power up
+	 * processors, so we initialize the SPC driver here.
+	 */
+	ret = ve_spc_init(scc + SPC_BASE, a15_cluster_id);
+	if (ret)
+		return ret;
+
+	if (!cci_probed())
+		return -ENODEV;
+
+	if (!tc2_pm_usage_count_init())
+		return -EINVAL;
+
+	ret = mcpm_platform_register(&tc2_pm_power_ops);
+	if (!ret) {
+		mcpm_sync_init(tc2_pm_power_up_setup);
+		pr_info("TC2 power management initialized\n");
+	}
+	return ret;
+}
+
+early_initcall(tc2_pm_init);
diff --git a/arch/arm/mach-zynq/Kconfig b/arch/arm/mach-zynq/Kconfig
index c1d61f281e68..04f8a4a6e755 100644
--- a/arch/arm/mach-zynq/Kconfig
+++ b/arch/arm/mach-zynq/Kconfig
@@ -6,7 +6,7 @@ config ARCH_ZYNQ
 	select CPU_V7
 	select GENERIC_CLOCKEVENTS
 	select HAVE_ARM_SCU if SMP
-	select HAVE_ARM_TWD if LOCAL_TIMERS
+	select HAVE_ARM_TWD if SMP
 	select ICST
 	select MIGHT_HAVE_CACHE_L2X0
 	select USE_OF
diff --git a/arch/arm/mach-zynq/hotplug.c b/arch/arm/mach-zynq/hotplug.c
index c89672bd1de2..5052c70326e4 100644
--- a/arch/arm/mach-zynq/hotplug.c
+++ b/arch/arm/mach-zynq/hotplug.c
@@ -40,44 +40,6 @@ static inline void zynq_cpu_enter_lowpower(void)
 	  : "cc");
 }
 
-static inline void zynq_cpu_leave_lowpower(void)
-{
-	unsigned int v;
-
-	asm volatile(
-	"	mrc	p15, 0, %0, c1, c0, 0\n"
-	"	orr	%0, %0, %1\n"
-	"	mcr	p15, 0, %0, c1, c0, 0\n"
-	"	mrc	p15, 0, %0, c1, c0, 1\n"
-	"	orr	%0, %0, #0x40\n"
-	"	mcr	p15, 0, %0, c1, c0, 1\n"
-	  : "=&r" (v)
-	  : "Ir" (CR_C)
-	  : "cc");
-}
-
-static inline void zynq_platform_do_lowpower(unsigned int cpu, int *spurious)
-{
-	/*
-	 * there is no power-control hardware on this platform, so all
-	 * we can do is put the core into WFI; this is safe as the calling
-	 * code will have already disabled interrupts
-	 */
-	for (;;) {
-		dsb();
-		wfi();
-
-		/*
-		 * Getting here, means that we have come out of WFI without
-		 * having been woken up - this shouldn't happen
-		 *
-		 * Just note it happening - when we're woken, we can report
-		 * its occurrence.
-		 */
-		(*spurious)++;
-	}
-}
-
 /*
  * platform-specific code to shutdown a CPU
  *
@@ -85,20 +47,13 @@ static inline void zynq_platform_do_lowpower(unsigned int cpu, int *spurious)
  */
 void zynq_platform_cpu_die(unsigned int cpu)
 {
-	int spurious = 0;
-
-	/*
-	 * we're ready for shutdown now, so do it
-	 */
 	zynq_cpu_enter_lowpower();
-	zynq_platform_do_lowpower(cpu, &spurious);
 
 	/*
-	 * bring this CPU back into the world of cache
-	 * coherency, and then restore interrupts
+	 * there is no power-control hardware on this platform, so all
+	 * we can do is put the core into WFI; this is safe as the calling
+	 * code will have already disabled interrupts
 	 */
-	zynq_cpu_leave_lowpower();
-
-	if (spurious)
-		pr_warn("CPU%u: %u spurious wakeup calls\n", cpu, spurious);
+	for (;;)
+		cpu_do_idle();
 }
diff --git a/arch/arm/mach-zynq/slcr.c b/arch/arm/mach-zynq/slcr.c
index 50d008d8f87f..1836d5a34606 100644
--- a/arch/arm/mach-zynq/slcr.c
+++ b/arch/arm/mach-zynq/slcr.c
@@ -14,32 +14,21 @@
  * 02139, USA.
  */
 
-#include <linux/export.h>
 #include <linux/io.h>
-#include <linux/fs.h>
-#include <linux/interrupt.h>
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
 #include <linux/of_address.h>
-#include <linux/uaccess.h>
-#include <linux/platform_device.h>
-#include <linux/slab.h>
-#include <linux/string.h>
 #include <linux/clk/zynq.h>
 #include "common.h"
 
-#define SLCR_UNLOCK_MAGIC		0xDF0D
-#define SLCR_UNLOCK			0x8   /* SCLR unlock register */
-
+/* register offsets */
+#define SLCR_UNLOCK_OFFSET		0x8   /* SCLR unlock register */
 #define SLCR_PS_RST_CTRL_OFFSET		0x200 /* PS Software Reset Control */
+#define SLCR_A9_CPU_RST_CTRL_OFFSET	0x244 /* CPU Software Reset Control */
+#define SLCR_REBOOT_STATUS_OFFSET	0x258 /* PS Reboot Status */
 
+#define SLCR_UNLOCK_MAGIC		0xDF0D
 #define SLCR_A9_CPU_CLKSTOP		0x10
 #define SLCR_A9_CPU_RST			0x1
 
-#define SLCR_A9_CPU_RST_CTRL		0x244 /* CPU Software Reset Control */
-#define SLCR_REBOOT_STATUS		0x258 /* PS Reboot Status */
-
 void __iomem *zynq_slcr_base;
 
 /**
@@ -54,15 +43,15 @@ void zynq_slcr_system_reset(void)
 	 * Note that this seems to require raw i/o
 	 * functions or there's a lockup?
 	 */
-	writel(SLCR_UNLOCK_MAGIC, zynq_slcr_base + SLCR_UNLOCK);
+	writel(SLCR_UNLOCK_MAGIC, zynq_slcr_base + SLCR_UNLOCK_OFFSET);
 
 	/*
 	 * Clear 0x0F000000 bits of reboot status register to workaround
 	 * the FSBL not loading the bitstream after soft-reboot
 	 * This is a temporary solution until we know more.
 	 */
-	reboot = readl(zynq_slcr_base + SLCR_REBOOT_STATUS);
-	writel(reboot & 0xF0FFFFFF, zynq_slcr_base + SLCR_REBOOT_STATUS);
+	reboot = readl(zynq_slcr_base + SLCR_REBOOT_STATUS_OFFSET);
+	writel(reboot & 0xF0FFFFFF, zynq_slcr_base + SLCR_REBOOT_STATUS_OFFSET);
 	writel(1, zynq_slcr_base + SLCR_PS_RST_CTRL_OFFSET);
 }
 
@@ -72,11 +61,11 @@ void zynq_slcr_system_reset(void)
  */
 void zynq_slcr_cpu_start(int cpu)
 {
-	/* enable CPUn */
-	writel(SLCR_A9_CPU_CLKSTOP << cpu,
-	       zynq_slcr_base + SLCR_A9_CPU_RST_CTRL);
-	/* enable CLK for CPUn */
-	writel(0x0 << cpu, zynq_slcr_base + SLCR_A9_CPU_RST_CTRL);
+	u32 reg = readl(zynq_slcr_base + SLCR_A9_CPU_RST_CTRL_OFFSET);
+	reg &= ~(SLCR_A9_CPU_RST << cpu);
+	writel(reg, zynq_slcr_base + SLCR_A9_CPU_RST_CTRL_OFFSET);
+	reg &= ~(SLCR_A9_CPU_CLKSTOP << cpu);
+	writel(reg, zynq_slcr_base + SLCR_A9_CPU_RST_CTRL_OFFSET);
 }
 
 /**
@@ -85,9 +74,9 @@ void zynq_slcr_cpu_start(int cpu)
  */
 void zynq_slcr_cpu_stop(int cpu)
 {
-	/* stop CLK and reset CPUn */
-	writel((SLCR_A9_CPU_CLKSTOP | SLCR_A9_CPU_RST) << cpu,
-	       zynq_slcr_base + SLCR_A9_CPU_RST_CTRL);
+	u32 reg = readl(zynq_slcr_base + SLCR_A9_CPU_RST_CTRL_OFFSET);
+	reg |= (SLCR_A9_CPU_CLKSTOP | SLCR_A9_CPU_RST) << cpu;
+	writel(reg, zynq_slcr_base + SLCR_A9_CPU_RST_CTRL_OFFSET);
 }
 
 /**
@@ -113,7 +102,7 @@ int __init zynq_slcr_init(void)
 	}
 
 	/* unlock the SLCR so that registers can be changed */
-	writel(SLCR_UNLOCK_MAGIC, zynq_slcr_base + SLCR_UNLOCK);
+	writel(SLCR_UNLOCK_MAGIC, zynq_slcr_base + SLCR_UNLOCK_OFFSET);
 
 	pr_info("%s mapped to %p\n", np->name, zynq_slcr_base);
 
diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c
index d70e0aba0c9d..447da6ffadd5 100644
--- a/arch/arm/mm/cache-l2x0.c
+++ b/arch/arm/mm/cache-l2x0.c
@@ -290,7 +290,7 @@ static void l2x0_disable(void)
 	raw_spin_lock_irqsave(&l2x0_lock, flags);
 	__l2x0_flush_all();
 	writel_relaxed(0, l2x0_base + L2X0_CTRL);
-	dsb();
+	dsb(st);
 	raw_spin_unlock_irqrestore(&l2x0_lock, flags);
 }
 
@@ -417,9 +417,9 @@ void __init l2x0_init(void __iomem *base, u32 aux_val, u32 aux_mask)
 		outer_cache.disable = l2x0_disable;
 	}
 
-	printk(KERN_INFO "%s cache controller enabled\n", type);
-	printk(KERN_INFO "l2x0: %d ways, CACHE_ID 0x%08x, AUX_CTRL 0x%08x, Cache size: %d B\n",
-			ways, cache_id, aux, l2x0_size);
+	pr_info("%s cache controller enabled\n", type);
+	pr_info("l2x0: %d ways, CACHE_ID 0x%08x, AUX_CTRL 0x%08x, Cache size: %d kB\n",
+		ways, cache_id, aux, l2x0_size >> 10);
 }
 
 #ifdef CONFIG_OF
@@ -929,7 +929,9 @@ static const struct of_device_id l2x0_ids[] __initconst = {
 	  .data = (void *)&aurora_no_outer_data},
 	{ .compatible = "marvell,aurora-outer-cache",
 	  .data = (void *)&aurora_with_outer_data},
-	{ .compatible = "bcm,bcm11351-a2-pl310-cache",
+	{ .compatible = "brcm,bcm11351-a2-pl310-cache",
+	  .data = (void *)&bcm_l2x0_data},
+	{ .compatible = "bcm,bcm11351-a2-pl310-cache", /* deprecated name */
 	  .data = (void *)&bcm_l2x0_data},
 	{}
 };
diff --git a/arch/arm/mm/cache-v7.S b/arch/arm/mm/cache-v7.S
index 515b00064da8..b5c467a65c27 100644
--- a/arch/arm/mm/cache-v7.S
+++ b/arch/arm/mm/cache-v7.S
@@ -282,7 +282,7 @@ ENTRY(v7_coherent_user_range)
 	add	r12, r12, r2
 	cmp	r12, r1
 	blo	1b
-	dsb
+	dsb	ishst
 	icache_line_size r2, r3
 	sub	r3, r2, #1
 	bic	r12, r0, r3
@@ -294,7 +294,7 @@ ENTRY(v7_coherent_user_range)
 	mov	r0, #0
 	ALT_SMP(mcr	p15, 0, r0, c7, c1, 6)	@ invalidate BTB Inner Shareable
 	ALT_UP(mcr	p15, 0, r0, c7, c5, 6)	@ invalidate BTB
-	dsb
+	dsb	ishst
 	isb
 	mov	pc, lr
 
diff --git a/arch/arm/mm/context.c b/arch/arm/mm/context.c
index 4a0544492f10..84e6f772e204 100644
--- a/arch/arm/mm/context.c
+++ b/arch/arm/mm/context.c
@@ -162,10 +162,7 @@ static void flush_context(unsigned int cpu)
 	}
 
 	/* Queue a TLB invalidate and flush the I-cache if necessary. */
-	if (!tlb_ops_need_broadcast())
-		cpumask_set_cpu(cpu, &tlb_flush_pending);
-	else
-		cpumask_setall(&tlb_flush_pending);
+	cpumask_setall(&tlb_flush_pending);
 
 	if (icache_is_vivt_asid_tagged())
 		__flush_icache_all();
@@ -245,8 +242,6 @@ void check_and_switch_context(struct mm_struct *mm, struct task_struct *tsk)
 	if (cpumask_test_and_clear_cpu(cpu, &tlb_flush_pending)) {
 		local_flush_bp_all();
 		local_flush_tlb_all();
-		if (erratum_a15_798181())
-			dummy_flush_tlb_a15_erratum();
 	}
 
 	atomic64_set(&per_cpu(active_asids, cpu), asid);
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 7f9b1798c6cf..1272ed202dde 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -358,7 +358,7 @@ static int __init atomic_pool_init(void)
 	if (!pages)
 		goto no_pages;
 
-	if (IS_ENABLED(CONFIG_CMA))
+	if (IS_ENABLED(CONFIG_DMA_CMA))
 		ptr = __alloc_from_contiguous(NULL, pool->size, prot, &page,
 					      atomic_pool_init);
 	else
@@ -455,7 +455,6 @@ static void __dma_remap(struct page *page, size_t size, pgprot_t prot)
 	unsigned end = start + size;
 
 	apply_to_page_range(&init_mm, start, size, __dma_update_pte, &prot);
-	dsb();
 	flush_tlb_kernel_range(start, end);
 }
 
@@ -670,7 +669,7 @@ static void *__dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
 		addr = __alloc_simple_buffer(dev, size, gfp, &page);
 	else if (!(gfp & __GFP_WAIT))
 		addr = __alloc_from_pool(size, &page);
-	else if (!IS_ENABLED(CONFIG_CMA))
+	else if (!IS_ENABLED(CONFIG_DMA_CMA))
 		addr = __alloc_remap_buffer(dev, size, gfp, prot, &page, caller);
 	else
 		addr = __alloc_from_contiguous(dev, size, prot, &page, caller);
@@ -759,7 +758,7 @@ static void __arm_dma_free(struct device *dev, size_t size, void *cpu_addr,
 		__dma_free_buffer(page, size);
 	} else if (__free_from_pool(cpu_addr, size)) {
 		return;
-	} else if (!IS_ENABLED(CONFIG_CMA)) {
+	} else if (!IS_ENABLED(CONFIG_DMA_CMA)) {
 		__dma_free_remap(cpu_addr, size);
 		__dma_free_buffer(page, size);
 	} else {
@@ -1233,7 +1232,8 @@ __iommu_create_mapping(struct device *dev, struct page **pages, size_t size)
 				break;
 
 		len = (j - i) << PAGE_SHIFT;
-		ret = iommu_map(mapping->domain, iova, phys, len, 0);
+		ret = iommu_map(mapping->domain, iova, phys, len,
+				IOMMU_READ|IOMMU_WRITE);
 		if (ret < 0)
 			goto fail;
 		iova += len;
@@ -1432,6 +1432,27 @@ static int arm_iommu_get_sgtable(struct device *dev, struct sg_table *sgt,
 					 GFP_KERNEL);
 }
 
+static int __dma_direction_to_prot(enum dma_data_direction dir)
+{
+	int prot;
+
+	switch (dir) {
+	case DMA_BIDIRECTIONAL:
+		prot = IOMMU_READ | IOMMU_WRITE;
+		break;
+	case DMA_TO_DEVICE:
+		prot = IOMMU_READ;
+		break;
+	case DMA_FROM_DEVICE:
+		prot = IOMMU_WRITE;
+		break;
+	default:
+		prot = 0;
+	}
+
+	return prot;
+}
+
 /*
  * Map a part of the scatter-gather list into contiguous io address space
  */
@@ -1445,6 +1466,7 @@ static int __map_sg_chunk(struct device *dev, struct scatterlist *sg,
 	int ret = 0;
 	unsigned int count;
 	struct scatterlist *s;
+	int prot;
 
 	size = PAGE_ALIGN(size);
 	*handle = DMA_ERROR_CODE;
@@ -1461,7 +1483,9 @@ static int __map_sg_chunk(struct device *dev, struct scatterlist *sg,
 			!dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs))
 			__dma_page_cpu_to_dev(sg_page(s), s->offset, s->length, dir);
 
-		ret = iommu_map(mapping->domain, iova, phys, len, 0);
+		prot = __dma_direction_to_prot(dir);
+
+		ret = iommu_map(mapping->domain, iova, phys, len, prot);
 		if (ret < 0)
 			goto fail;
 		count += len >> PAGE_SHIFT;
@@ -1666,19 +1690,7 @@ static dma_addr_t arm_coherent_iommu_map_page(struct device *dev, struct page *p
 	if (dma_addr == DMA_ERROR_CODE)
 		return dma_addr;
 
-	switch (dir) {
-	case DMA_BIDIRECTIONAL:
-		prot = IOMMU_READ | IOMMU_WRITE;
-		break;
-	case DMA_TO_DEVICE:
-		prot = IOMMU_READ;
-		break;
-	case DMA_FROM_DEVICE:
-		prot = IOMMU_WRITE;
-		break;
-	default:
-		prot = 0;
-	}
+	prot = __dma_direction_to_prot(dir);
 
 	ret = iommu_map(mapping->domain, dma_addr, page_to_phys(page), len, prot);
 	if (ret < 0)
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index c97f7940cb95..eb8830a4c5ed 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -261,9 +261,7 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 	struct task_struct *tsk;
 	struct mm_struct *mm;
 	int fault, sig, code;
-	int write = fsr & FSR_WRITE;
-	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
-				(write ? FAULT_FLAG_WRITE : 0);
+	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
 
 	if (notify_page_fault(regs, fsr))
 		return 0;
@@ -282,6 +280,11 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 	if (in_atomic() || !mm)
 		goto no_context;
 
+	if (user_mode(regs))
+		flags |= FAULT_FLAG_USER;
+	if (fsr & FSR_WRITE)
+		flags |= FAULT_FLAG_WRITE;
+
 	/*
 	 * As per x86, we may deadlock here.  However, since the kernel only
 	 * validly references user space from well defined areas of the code,
@@ -349,6 +352,13 @@ retry:
 	if (likely(!(fault & (VM_FAULT_ERROR | VM_FAULT_BADMAP | VM_FAULT_BADACCESS))))
 		return 0;
 
+	/*
+	 * If we are in kernel mode at this point, we
+	 * have no context to handle this fault with.
+	 */
+	if (!user_mode(regs))
+		goto no_context;
+
 	if (fault & VM_FAULT_OOM) {
 		/*
 		 * We ran out of memory, call the OOM killer, and return to
@@ -359,13 +369,6 @@ retry:
 		return 0;
 	}
 
-	/*
-	 * If we are in kernel mode at this point, we
-	 * have no context to handle this fault with.
-	 */
-	if (!user_mode(regs))
-		goto no_context;
-
 	if (fault & VM_FAULT_SIGBUS) {
 		/*
 		 * We had some memory, but were unable to
diff --git a/arch/arm/mm/hugetlbpage.c b/arch/arm/mm/hugetlbpage.c
index 3d1e4a205b0b..54ee6163c181 100644
--- a/arch/arm/mm/hugetlbpage.c
+++ b/arch/arm/mm/hugetlbpage.c
@@ -36,22 +36,6 @@
  * of type casting from pmd_t * to pte_t *.
  */
 
-pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
-{
-	pgd_t *pgd;
-	pud_t *pud;
-	pmd_t *pmd = NULL;
-
-	pgd = pgd_offset(mm, addr);
-	if (pgd_present(*pgd)) {
-		pud = pud_offset(pgd, addr);
-		if (pud_present(*pud))
-			pmd = pmd_offset(pud, addr);
-	}
-
-	return (pte_t *)pmd;
-}
-
 struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address,
 			      int write)
 {
@@ -68,34 +52,12 @@ int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep)
 	return 0;
 }
 
-pte_t *huge_pte_alloc(struct mm_struct *mm,
-			unsigned long addr, unsigned long sz)
-{
-	pgd_t *pgd;
-	pud_t *pud;
-	pte_t *pte = NULL;
-
-	pgd = pgd_offset(mm, addr);
-	pud = pud_alloc(mm, pgd, addr);
-	if (pud)
-		pte = (pte_t *)pmd_alloc(mm, pud, addr);
-
-	return pte;
-}
-
-struct page *
-follow_huge_pmd(struct mm_struct *mm, unsigned long address,
-		pmd_t *pmd, int write)
+int pmd_huge(pmd_t pmd)
 {
-	struct page *page;
-
-	page = pte_page(*(pte_t *)pmd);
-	if (page)
-		page += ((address & ~PMD_MASK) >> PAGE_SHIFT);
-	return page;
+	return pmd_val(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT);
 }
 
-int pmd_huge(pmd_t pmd)
+int pmd_huge_support(void)
 {
-	return pmd_val(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT);
+	return 1;
 }
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index 15225d829d71..18ec4c504abf 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -77,7 +77,7 @@ static int __init parse_tag_initrd2(const struct tag *tag)
 __tagtable(ATAG_INITRD2, parse_tag_initrd2);
 
 #ifdef CONFIG_OF_FLATTREE
-void __init early_init_dt_setup_initrd_arch(unsigned long start, unsigned long end)
+void __init early_init_dt_setup_initrd_arch(u64 start, u64 end)
 {
 	phys_initrd_start = start;
 	phys_initrd_size = end - start;
@@ -207,7 +207,7 @@ static void __init arm_bootmem_init(unsigned long start_pfn,
 
 #ifdef CONFIG_ZONE_DMA
 
-unsigned long arm_dma_zone_size __read_mostly;
+phys_addr_t arm_dma_zone_size __read_mostly;
 EXPORT_SYMBOL(arm_dma_zone_size);
 
 /*
@@ -231,7 +231,7 @@ static void __init arm_adjust_dma_zone(unsigned long *size, unsigned long *hole,
 }
 #endif
 
-void __init setup_dma_zone(struct machine_desc *mdesc)
+void __init setup_dma_zone(const struct machine_desc *mdesc)
 {
 #ifdef CONFIG_ZONE_DMA
 	if (mdesc->dma_zone_size) {
@@ -335,7 +335,8 @@ phys_addr_t __init arm_memblock_steal(phys_addr_t size, phys_addr_t align)
 	return phys;
 }
 
-void __init arm_memblock_init(struct meminfo *mi, struct machine_desc *mdesc)
+void __init arm_memblock_init(struct meminfo *mi,
+	const struct machine_desc *mdesc)
 {
 	int i;
 
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index 53cdbd39ec8e..b1d17eeb59b8 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -1186,7 +1186,7 @@ void __init arm_mm_memblock_reserve(void)
  * called function.  This means you can't use any function or debugging
  * method which may touch any device, otherwise the kernel _will_ crash.
  */
-static void __init devicemaps_init(struct machine_desc *mdesc)
+static void __init devicemaps_init(const struct machine_desc *mdesc)
 {
 	struct map_desc map;
 	unsigned long addr;
@@ -1319,7 +1319,7 @@ static void __init map_lowmem(void)
  * paging_init() sets up the page tables, initialises the zone memory
  * maps, and sets up the zero page, bad page and bad page tables.
  */
-void __init paging_init(struct machine_desc *mdesc)
+void __init paging_init(const struct machine_desc *mdesc)
 {
 	void *zero_page;
 
diff --git a/arch/arm/mm/nommu.c b/arch/arm/mm/nommu.c
index 1fa50100ab6a..34d4ab217bab 100644
--- a/arch/arm/mm/nommu.c
+++ b/arch/arm/mm/nommu.c
@@ -299,7 +299,7 @@ void __init sanity_check_meminfo(void)
  * paging_init() sets up the page tables, initialises the zone memory
  * maps, and sets up the zero page, bad page and bad page tables.
  */
-void __init paging_init(struct machine_desc *mdesc)
+void __init paging_init(const struct machine_desc *mdesc)
 {
 	early_trap_init((void *)CONFIG_VECTORS_BASE);
 	mpu_setup();
diff --git a/arch/arm/mm/proc-feroceon.S b/arch/arm/mm/proc-feroceon.S
index d5146b98c8d1..db79b62c92fb 100644
--- a/arch/arm/mm/proc-feroceon.S
+++ b/arch/arm/mm/proc-feroceon.S
@@ -514,6 +514,32 @@ ENTRY(cpu_feroceon_set_pte_ext)
 #endif
 	mov	pc, lr
 
+/* Suspend/resume support: taken from arch/arm/mm/proc-arm926.S */
+.globl	cpu_feroceon_suspend_size
+.equ	cpu_feroceon_suspend_size, 4 * 3
+#ifdef CONFIG_ARM_CPU_SUSPEND
+ENTRY(cpu_feroceon_do_suspend)
+	stmfd	sp!, {r4 - r6, lr}
+	mrc	p15, 0, r4, c13, c0, 0	@ PID
+	mrc	p15, 0, r5, c3, c0, 0	@ Domain ID
+	mrc	p15, 0, r6, c1, c0, 0	@ Control register
+	stmia	r0, {r4 - r6}
+	ldmfd	sp!, {r4 - r6, pc}
+ENDPROC(cpu_feroceon_do_suspend)
+
+ENTRY(cpu_feroceon_do_resume)
+	mov	ip, #0
+	mcr	p15, 0, ip, c8, c7, 0	@ invalidate I+D TLBs
+	mcr	p15, 0, ip, c7, c7, 0	@ invalidate I+D caches
+	ldmia	r0, {r4 - r6}
+	mcr	p15, 0, r4, c13, c0, 0	@ PID
+	mcr	p15, 0, r5, c3, c0, 0	@ Domain ID
+	mcr	p15, 0, r1, c2, c0, 0	@ TTB address
+	mov	r0, r6			@ control register
+	b	cpu_resume_mmu
+ENDPROC(cpu_feroceon_do_resume)
+#endif
+
 	.type	__feroceon_setup, #function
 __feroceon_setup:
 	mov	r0, #0
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index 73398bcf9bd8..c63d9bdee51e 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -83,7 +83,7 @@ ENTRY(cpu_v7_dcache_clean_area)
 	add	r0, r0, r2
 	subs	r1, r1, r2
 	bhi	2b
-	dsb
+	dsb	ishst
 	mov	pc, lr
 ENDPROC(cpu_v7_dcache_clean_area)
 
@@ -330,7 +330,19 @@ __v7_setup:
 1:
 #endif
 
-3:	mov	r10, #0
+	/* Cortex-A15 Errata */
+3:	ldr	r10, =0x00000c0f		@ Cortex-A15 primary part number
+	teq	r0, r10
+	bne	4f
+
+#ifdef CONFIG_ARM_ERRATA_773022
+	cmp	r6, #0x4			@ only present up to r0p4
+	mrcle	p15, 0, r10, c1, c0, 1		@ read aux control register
+	orrle	r10, r10, #1 << 1		@ disable loop buffer
+	mcrle	p15, 0, r10, c1, c0, 1		@ write aux control register
+#endif
+
+4:	mov	r10, #0
 	mcr	p15, 0, r10, c7, c5, 0		@ I+BTB cache invalidate
 	dsb
 #ifdef CONFIG_MMU
diff --git a/arch/arm/mm/tlb-v7.S b/arch/arm/mm/tlb-v7.S
index ea94765acf9a..355308767bae 100644
--- a/arch/arm/mm/tlb-v7.S
+++ b/arch/arm/mm/tlb-v7.S
@@ -35,7 +35,7 @@
 ENTRY(v7wbi_flush_user_tlb_range)
 	vma_vm_mm r3, r2			@ get vma->vm_mm
 	mmid	r3, r3				@ get vm_mm->context.id
-	dsb
+	dsb	ish
 	mov	r0, r0, lsr #PAGE_SHIFT		@ align address
 	mov	r1, r1, lsr #PAGE_SHIFT
 	asid	r3, r3				@ mask ASID
@@ -56,7 +56,7 @@ ENTRY(v7wbi_flush_user_tlb_range)
 	add	r0, r0, #PAGE_SZ
 	cmp	r0, r1
 	blo	1b
-	dsb
+	dsb	ish
 	mov	pc, lr
 ENDPROC(v7wbi_flush_user_tlb_range)
 
@@ -69,7 +69,7 @@ ENDPROC(v7wbi_flush_user_tlb_range)
  *	- end   - end address (exclusive, may not be aligned)
  */
 ENTRY(v7wbi_flush_kern_tlb_range)
-	dsb
+	dsb	ish
 	mov	r0, r0, lsr #PAGE_SHIFT		@ align address
 	mov	r1, r1, lsr #PAGE_SHIFT
 	mov	r0, r0, lsl #PAGE_SHIFT
@@ -84,7 +84,7 @@ ENTRY(v7wbi_flush_kern_tlb_range)
 	add	r0, r0, #PAGE_SZ
 	cmp	r0, r1
 	blo	1b
-	dsb
+	dsb	ish
 	isb
 	mov	pc, lr
 ENDPROC(v7wbi_flush_kern_tlb_range)
diff --git a/arch/arm/plat-omap/Kconfig b/arch/arm/plat-omap/Kconfig
index f82bae2171eb..436ea97074cd 100644
--- a/arch/arm/plat-omap/Kconfig
+++ b/arch/arm/plat-omap/Kconfig
@@ -106,7 +106,7 @@ config OMAP_32K_TIMER
 	  This timer saves power compared to the OMAP_MPU_TIMER, and has
 	  support for no tick during idle. The 32KHz timer provides less
 	  intra-tick resolution than OMAP_MPU_TIMER. The 32KHz timer is
-	  currently only available for OMAP16XX, 24XX, 34XX and OMAP4/5.
+	  currently only available for OMAP16XX, 24XX, 34XX, OMAP4/5 and DRA7XX.
 
 	  On OMAP2PLUS this value is only used for CONFIG_HZ and
 	  CLOCK_TICK_RATE compile time calculation.
diff --git a/arch/arm/plat-omap/dma.c b/arch/arm/plat-omap/dma.c
index 4d463ca6821f..037660633fa4 100644
--- a/arch/arm/plat-omap/dma.c
+++ b/arch/arm/plat-omap/dma.c
@@ -2083,6 +2083,7 @@ static int omap_system_dma_probe(struct platform_device *pdev)
 		dma_irq = platform_get_irq_byname(pdev, irq_name);
 		if (dma_irq < 0) {
 			dev_err(&pdev->dev, "failed: request IRQ %d", dma_irq);
+			ret = dma_irq;
 			goto exit_dma_lch_fail;
 		}
 		ret = setup_irq(dma_irq, &omap24xx_dma_irq);
diff --git a/arch/arm/plat-orion/irq.c b/arch/arm/plat-orion/irq.c
index 8db0b981ca64..c492e1b3dfdb 100644
--- a/arch/arm/plat-orion/irq.c
+++ b/arch/arm/plat-orion/irq.c
@@ -47,7 +47,7 @@ static int __init orion_add_irq_domain(struct device_node *np,
 	do {
 		base = of_iomap(np, i);
 		if (base) {
-			orion_irq_init(i * 32, base);
+			orion_irq_init(i * 32, base + 0x04);
 			i++;
 		}
 	} while (base);
diff --git a/arch/arm/plat-pxa/ssp.c b/arch/arm/plat-pxa/ssp.c
index 8e11e96eab5e..3ea02903d75a 100644
--- a/arch/arm/plat-pxa/ssp.c
+++ b/arch/arm/plat-pxa/ssp.c
@@ -30,6 +30,8 @@
 #include <linux/platform_device.h>
 #include <linux/spi/pxa2xx_spi.h>
 #include <linux/io.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
 
 #include <asm/irq.h>
 #include <mach/hardware.h>
@@ -60,6 +62,30 @@ struct ssp_device *pxa_ssp_request(int port, const char *label)
 }
 EXPORT_SYMBOL(pxa_ssp_request);
 
+struct ssp_device *pxa_ssp_request_of(const struct device_node *of_node,
+				      const char *label)
+{
+	struct ssp_device *ssp = NULL;
+
+	mutex_lock(&ssp_lock);
+
+	list_for_each_entry(ssp, &ssp_list, node) {
+		if (ssp->of_node == of_node && ssp->use_count == 0) {
+			ssp->use_count++;
+			ssp->label = label;
+			break;
+		}
+	}
+
+	mutex_unlock(&ssp_lock);
+
+	if (&ssp->node == &ssp_list)
+		return NULL;
+
+	return ssp;
+}
+EXPORT_SYMBOL(pxa_ssp_request_of);
+
 void pxa_ssp_free(struct ssp_device *ssp)
 {
 	mutex_lock(&ssp_lock);
@@ -72,96 +98,136 @@ void pxa_ssp_free(struct ssp_device *ssp)
 }
 EXPORT_SYMBOL(pxa_ssp_free);
 
+#ifdef CONFIG_OF
+static const struct of_device_id pxa_ssp_of_ids[] = {
+	{ .compatible = "mrvl,pxa25x-ssp",	.data = (void *) PXA25x_SSP },
+	{ .compatible = "mvrl,pxa25x-nssp",	.data = (void *) PXA25x_NSSP },
+	{ .compatible = "mrvl,pxa27x-ssp",	.data = (void *) PXA27x_SSP },
+	{ .compatible = "mrvl,pxa3xx-ssp",	.data = (void *) PXA3xx_SSP },
+	{ .compatible = "mvrl,pxa168-ssp",	.data = (void *) PXA168_SSP },
+	{ .compatible = "mrvl,pxa910-ssp",	.data = (void *) PXA910_SSP },
+	{ .compatible = "mrvl,ce4100-ssp",	.data = (void *) CE4100_SSP },
+	{ .compatible = "mrvl,lpss-ssp",	.data = (void *) LPSS_SSP },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, pxa_ssp_of_ids);
+#endif
+
 static int pxa_ssp_probe(struct platform_device *pdev)
 {
-	const struct platform_device_id *id = platform_get_device_id(pdev);
 	struct resource *res;
 	struct ssp_device *ssp;
-	int ret = 0;
+	struct device *dev = &pdev->dev;
 
-	ssp = kzalloc(sizeof(struct ssp_device), GFP_KERNEL);
-	if (ssp == NULL) {
-		dev_err(&pdev->dev, "failed to allocate memory");
+	ssp = devm_kzalloc(dev, sizeof(struct ssp_device), GFP_KERNEL);
+	if (ssp == NULL)
 		return -ENOMEM;
-	}
+
 	ssp->pdev = pdev;
 
-	ssp->clk = clk_get(&pdev->dev, NULL);
-	if (IS_ERR(ssp->clk)) {
-		ret = PTR_ERR(ssp->clk);
-		goto err_free;
-	}
+	ssp->clk = devm_clk_get(dev, NULL);
+	if (IS_ERR(ssp->clk))
+		return PTR_ERR(ssp->clk);
 
-	res = platform_get_resource(pdev, IORESOURCE_DMA, 0);
-	if (res == NULL) {
-		dev_err(&pdev->dev, "no SSP RX DRCMR defined\n");
-		ret = -ENODEV;
-		goto err_free_clk;
-	}
-	ssp->drcmr_rx = res->start;
+	if (dev->of_node) {
+		struct of_phandle_args dma_spec;
+		struct device_node *np = dev->of_node;
+		int ret;
 
-	res = platform_get_resource(pdev, IORESOURCE_DMA, 1);
-	if (res == NULL) {
-		dev_err(&pdev->dev, "no SSP TX DRCMR defined\n");
-		ret = -ENODEV;
-		goto err_free_clk;
+		/*
+		 * FIXME: we should allocate the DMA channel from this
+		 * context and pass the channel down to the ssp users.
+		 * For now, we lookup the rx and tx indices manually
+		 */
+
+		/* rx */
+		ret = of_parse_phandle_with_args(np, "dmas", "#dma-cells",
+						 0, &dma_spec);
+
+		if (ret) {
+			dev_err(dev, "Can't parse dmas property\n");
+			return -ENODEV;
+		}
+		ssp->drcmr_rx = dma_spec.args[0];
+		of_node_put(dma_spec.np);
+
+		/* tx */
+		ret = of_parse_phandle_with_args(np, "dmas", "#dma-cells",
+						 1, &dma_spec);
+		if (ret) {
+			dev_err(dev, "Can't parse dmas property\n");
+			return -ENODEV;
+		}
+		ssp->drcmr_tx = dma_spec.args[0];
+		of_node_put(dma_spec.np);
+	} else {
+		res = platform_get_resource(pdev, IORESOURCE_DMA, 0);
+		if (res == NULL) {
+			dev_err(dev, "no SSP RX DRCMR defined\n");
+			return -ENODEV;
+		}
+		ssp->drcmr_rx = res->start;
+
+		res = platform_get_resource(pdev, IORESOURCE_DMA, 1);
+		if (res == NULL) {
+			dev_err(dev, "no SSP TX DRCMR defined\n");
+			return -ENODEV;
+		}
+		ssp->drcmr_tx = res->start;
 	}
-	ssp->drcmr_tx = res->start;
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	if (res == NULL) {
-		dev_err(&pdev->dev, "no memory resource defined\n");
-		ret = -ENODEV;
-		goto err_free_clk;
+		dev_err(dev, "no memory resource defined\n");
+		return -ENODEV;
 	}
 
-	res = request_mem_region(res->start, resource_size(res),
-			pdev->name);
+	res = devm_request_mem_region(dev, res->start, resource_size(res),
+				      pdev->name);
 	if (res == NULL) {
-		dev_err(&pdev->dev, "failed to request memory resource\n");
-		ret = -EBUSY;
-		goto err_free_clk;
+		dev_err(dev, "failed to request memory resource\n");
+		return -EBUSY;
 	}
 
 	ssp->phys_base = res->start;
 
-	ssp->mmio_base = ioremap(res->start, resource_size(res));
+	ssp->mmio_base = devm_ioremap(dev, res->start, resource_size(res));
 	if (ssp->mmio_base == NULL) {
-		dev_err(&pdev->dev, "failed to ioremap() registers\n");
-		ret = -ENODEV;
-		goto err_free_mem;
+		dev_err(dev, "failed to ioremap() registers\n");
+		return -ENODEV;
 	}
 
 	ssp->irq = platform_get_irq(pdev, 0);
 	if (ssp->irq < 0) {
-		dev_err(&pdev->dev, "no IRQ resource defined\n");
-		ret = -ENODEV;
-		goto err_free_io;
+		dev_err(dev, "no IRQ resource defined\n");
+		return -ENODEV;
+	}
+
+	if (dev->of_node) {
+		const struct of_device_id *id =
+			of_match_device(of_match_ptr(pxa_ssp_of_ids), dev);
+		ssp->type = (int) id->data;
+	} else {
+		const struct platform_device_id *id =
+			platform_get_device_id(pdev);
+		ssp->type = (int) id->driver_data;
+
+		/* PXA2xx/3xx SSP ports starts from 1 and the internal pdev->id
+		 * starts from 0, do a translation here
+		 */
+		ssp->port_id = pdev->id + 1;
 	}
 
-	/* PXA2xx/3xx SSP ports starts from 1 and the internal pdev->id
-	 * starts from 0, do a translation here
-	 */
-	ssp->port_id = pdev->id + 1;
 	ssp->use_count = 0;
-	ssp->type = (int)id->driver_data;
+	ssp->of_node = dev->of_node;
 
 	mutex_lock(&ssp_lock);
 	list_add(&ssp->node, &ssp_list);
 	mutex_unlock(&ssp_lock);
 
 	platform_set_drvdata(pdev, ssp);
-	return 0;
 
-err_free_io:
-	iounmap(ssp->mmio_base);
-err_free_mem:
-	release_mem_region(res->start, resource_size(res));
-err_free_clk:
-	clk_put(ssp->clk);
-err_free:
-	kfree(ssp);
-	return ret;
+	return 0;
 }
 
 static int pxa_ssp_remove(struct platform_device *pdev)
@@ -201,8 +267,9 @@ static struct platform_driver pxa_ssp_driver = {
 	.probe		= pxa_ssp_probe,
 	.remove		= pxa_ssp_remove,
 	.driver		= {
-		.owner	= THIS_MODULE,
-		.name	= "pxa2xx-ssp",
+		.owner		= THIS_MODULE,
+		.name		= "pxa2xx-ssp",
+		.of_match_table	= of_match_ptr(pxa_ssp_of_ids),
 	},
 	.id_table	= ssp_id_table,
 };
diff --git a/arch/arm/plat-samsung/Kconfig b/arch/arm/plat-samsung/Kconfig
index a5b5ff6e68d2..7dfba937d8fc 100644
--- a/arch/arm/plat-samsung/Kconfig
+++ b/arch/arm/plat-samsung/Kconfig
@@ -25,7 +25,6 @@ config PLAT_S5P
 	select S5P_GPIO_DRVSTR
 	select SAMSUNG_CLKSRC if !COMMON_CLK
 	select SAMSUNG_GPIOLIB_4BIT
-	select SAMSUNG_IRQ_VIC_TIMER
 	help
 	  Base platform code for Samsung's S5P series SoC.
 
@@ -79,14 +78,6 @@ config SAMSUNG_ATAGS
 
 if SAMSUNG_ATAGS
 
-# timer options
-
-config SAMSUNG_HRT
-	bool
-	select SAMSUNG_DEV_PWM
-	help
-	  Use the High Resolution timer support
-
 # clock options
 
 config SAMSUNG_CLOCK
@@ -106,11 +97,6 @@ config S5P_CLOCK
 
 # options for IRQ support
 
-config SAMSUNG_IRQ_VIC_TIMER
-       bool
-       help
-         Internal configuration to build the VIC timer interrupt code.
-
 config S5P_IRQ
 	def_bool (ARCH_S5P64X0 || ARCH_S5PC100 || ARCH_S5PV210)
 	help
diff --git a/arch/arm/plat-samsung/Makefile b/arch/arm/plat-samsung/Makefile
index 199bbe304d02..498c7c23e9f4 100644
--- a/arch/arm/plat-samsung/Makefile
+++ b/arch/arm/plat-samsung/Makefile
@@ -12,15 +12,12 @@ obj-				:=
 # Objects we always build independent of SoC choice
 
 obj-y				+= init.o cpu.o
-obj-$(CONFIG_SAMSUNG_HRT) 	+= samsung-time.o
 
 obj-$(CONFIG_SAMSUNG_CLOCK)	+= clock.o
-obj-$(CONFIG_SAMSUNG_CLOCK)	+= pwm-clock.o
 
 obj-$(CONFIG_SAMSUNG_CLKSRC)	+= clock-clksrc.o
 obj-$(CONFIG_S5P_CLOCK)		+= s5p-clock.o
 
-obj-$(CONFIG_SAMSUNG_IRQ_VIC_TIMER) += irq-vic-timer.o
 obj-$(CONFIG_S5P_IRQ)		+= s5p-irq.o
 obj-$(CONFIG_S5P_EXT_INT)	+= s5p-irq-eint.o
 obj-$(CONFIG_S5P_GPIO_INT)	+= s5p-irq-gpioint.o
diff --git a/arch/arm/plat-samsung/dev-backlight.c b/arch/arm/plat-samsung/dev-backlight.c
index 5f197dcaf10c..d51f9565567c 100644
--- a/arch/arm/plat-samsung/dev-backlight.c
+++ b/arch/arm/plat-samsung/dev-backlight.c
@@ -20,13 +20,18 @@
 #include <plat/gpio-cfg.h>
 #include <plat/backlight.h>
 
+struct samsung_bl_drvdata {
+	struct platform_pwm_backlight_data plat_data;
+	struct samsung_bl_gpio_info *gpio_info;
+};
+
 static int samsung_bl_init(struct device *dev)
 {
 	int ret = 0;
-	struct platform_device *timer_dev =
-			container_of(dev->parent, struct platform_device, dev);
-	struct samsung_bl_gpio_info *bl_gpio_info =
-			timer_dev->dev.platform_data;
+	struct platform_pwm_backlight_data *pdata = dev->platform_data;
+	struct samsung_bl_drvdata *drvdata = container_of(pdata,
+					struct samsung_bl_drvdata, plat_data);
+	struct samsung_bl_gpio_info *bl_gpio_info = drvdata->gpio_info;
 
 	ret = gpio_request(bl_gpio_info->no, "Backlight");
 	if (ret) {
@@ -42,10 +47,10 @@ static int samsung_bl_init(struct device *dev)
 
 static void samsung_bl_exit(struct device *dev)
 {
-	struct platform_device *timer_dev =
-			container_of(dev->parent, struct platform_device, dev);
-	struct samsung_bl_gpio_info *bl_gpio_info =
-			timer_dev->dev.platform_data;
+	struct platform_pwm_backlight_data *pdata = dev->platform_data;
+	struct samsung_bl_drvdata *drvdata = container_of(pdata,
+					struct samsung_bl_drvdata, plat_data);
+	struct samsung_bl_gpio_info *bl_gpio_info = drvdata->gpio_info;
 
 	s3c_gpio_cfgpin(bl_gpio_info->no, S3C_GPIO_OUTPUT);
 	gpio_free(bl_gpio_info->no);
@@ -60,12 +65,14 @@ static void samsung_bl_exit(struct device *dev)
  * for their specific boards
  */
 
-static struct platform_pwm_backlight_data samsung_dfl_bl_data __initdata = {
-	.max_brightness = 255,
-	.dft_brightness = 255,
-	.pwm_period_ns  = 78770,
-	.init           = samsung_bl_init,
-	.exit           = samsung_bl_exit,
+static struct samsung_bl_drvdata samsung_dfl_bl_data __initdata = {
+	.plat_data = {
+		.max_brightness = 255,
+		.dft_brightness = 255,
+		.pwm_period_ns  = 78770,
+		.init           = samsung_bl_init,
+		.exit           = samsung_bl_exit,
+	},
 };
 
 static struct platform_device samsung_dfl_bl_device __initdata = {
@@ -82,6 +89,7 @@ void __init samsung_bl_set(struct samsung_bl_gpio_info *gpio_info,
 {
 	int ret = 0;
 	struct platform_device *samsung_bl_device;
+	struct samsung_bl_drvdata *samsung_bl_drvdata;
 	struct platform_pwm_backlight_data *samsung_bl_data;
 
 	samsung_bl_device = kmemdup(&samsung_dfl_bl_device,
@@ -91,17 +99,19 @@ void __init samsung_bl_set(struct samsung_bl_gpio_info *gpio_info,
 		return;
 	}
 
-	samsung_bl_data = s3c_set_platdata(&samsung_dfl_bl_data,
-		sizeof(struct platform_pwm_backlight_data), samsung_bl_device);
-	if (!samsung_bl_data) {
+	samsung_bl_drvdata = kmemdup(&samsung_dfl_bl_data,
+				sizeof(samsung_dfl_bl_data), GFP_KERNEL);
+	if (!samsung_bl_drvdata) {
 		printk(KERN_ERR "%s: no memory for platform dev\n", __func__);
 		goto err_data;
 	}
+	samsung_bl_device->dev.platform_data = &samsung_bl_drvdata->plat_data;
+	samsung_bl_drvdata->gpio_info = gpio_info;
+	samsung_bl_data = &samsung_bl_drvdata->plat_data;
 
 	/* Copy board specific data provided by user */
 	samsung_bl_data->pwm_id = bl_data->pwm_id;
-	samsung_bl_device->dev.parent =
-			&s3c_device_timer[samsung_bl_data->pwm_id].dev;
+	samsung_bl_device->dev.parent = &samsung_device_pwm.dev;
 
 	if (bl_data->max_brightness)
 		samsung_bl_data->max_brightness = bl_data->max_brightness;
@@ -122,17 +132,6 @@ void __init samsung_bl_set(struct samsung_bl_gpio_info *gpio_info,
 	if (bl_data->check_fb)
 		samsung_bl_data->check_fb = bl_data->check_fb;
 
-	/* Keep the GPIO info for future use */
-	s3c_device_timer[samsung_bl_data->pwm_id].dev.platform_data = gpio_info;
-
-	/* Register the specific PWM timer dev for Backlight control */
-	ret = platform_device_register(
-			&s3c_device_timer[samsung_bl_data->pwm_id]);
-	if (ret) {
-		printk(KERN_ERR "failed to register pwm timer for backlight: %d\n", ret);
-		goto err_plat_reg1;
-	}
-
 	/* Register the Backlight dev */
 	ret = platform_device_register(samsung_bl_device);
 	if (ret) {
@@ -143,8 +142,6 @@ void __init samsung_bl_set(struct samsung_bl_gpio_info *gpio_info,
 	return;
 
 err_plat_reg2:
-	platform_device_unregister(&s3c_device_timer[samsung_bl_data->pwm_id]);
-err_plat_reg1:
 	kfree(samsung_bl_data);
 err_data:
 	kfree(samsung_bl_device);
diff --git a/arch/arm/plat-samsung/devs.c b/arch/arm/plat-samsung/devs.c
index 0f9c3f431a5f..8ce0ac007eb9 100644
--- a/arch/arm/plat-samsung/devs.c
+++ b/arch/arm/plat-samsung/devs.c
@@ -58,6 +58,7 @@
 #include <plat/keypad.h>
 #include <linux/platform_data/mmc-s3cmci.h>
 #include <linux/platform_data/mtd-nand-s3c2410.h>
+#include <plat/pwm-core.h>
 #include <plat/sdhci.h>
 #include <linux/platform_data/touchscreen-s3c2410.h>
 #include <linux/platform_data/usb-s3c2410_udc.h>
@@ -1097,36 +1098,21 @@ arch_initcall(s5p_pmu_init);
 /* PWM Timer */
 
 #ifdef CONFIG_SAMSUNG_DEV_PWM
+static struct resource samsung_pwm_resource[] = {
+	DEFINE_RES_MEM(SAMSUNG_PA_TIMER, SZ_4K),
+};
 
-#define TIMER_RESOURCE_SIZE (1)
-
-#define TIMER_RESOURCE(_tmr, _irq)			\
-	(struct resource [TIMER_RESOURCE_SIZE]) {	\
-		[0] = {					\
-			.start	= _irq,			\
-			.end	= _irq,			\
-			.flags	= IORESOURCE_IRQ	\
-		}					\
-	}
-
-#define DEFINE_S3C_TIMER(_tmr_no, _irq)			\
-	.name		= "s3c24xx-pwm",		\
-	.id		= _tmr_no,			\
-	.num_resources	= TIMER_RESOURCE_SIZE,		\
-	.resource	= TIMER_RESOURCE(_tmr_no, _irq),	\
-
-/*
- * since we already have an static mapping for the timer,
- * we do not bother setting any IO resource for the base.
- */
-
-struct platform_device s3c_device_timer[] = {
-	[0] = { DEFINE_S3C_TIMER(0, IRQ_TIMER0) },
-	[1] = { DEFINE_S3C_TIMER(1, IRQ_TIMER1) },
-	[2] = { DEFINE_S3C_TIMER(2, IRQ_TIMER2) },
-	[3] = { DEFINE_S3C_TIMER(3, IRQ_TIMER3) },
-	[4] = { DEFINE_S3C_TIMER(4, IRQ_TIMER4) },
+struct platform_device samsung_device_pwm = {
+	.name		= "samsung-pwm",
+	.id		= -1,
+	.num_resources	= ARRAY_SIZE(samsung_pwm_resource),
+	.resource	= samsung_pwm_resource,
 };
+
+void __init samsung_pwm_set_platdata(struct samsung_pwm_variant *pd)
+{
+	samsung_device_pwm.dev.platform_data = pd;
+}
 #endif /* CONFIG_SAMSUNG_DEV_PWM */
 
 /* RTC */
diff --git a/arch/arm/plat-samsung/include/plat/clock.h b/arch/arm/plat-samsung/include/plat/clock.h
index df45d6edc98d..63239f409807 100644
--- a/arch/arm/plat-samsung/include/plat/clock.h
+++ b/arch/arm/plat-samsung/include/plat/clock.h
@@ -145,10 +145,6 @@ extern int s3c2443_clkcon_enable_s(struct clk *clk, int enable);
 
 extern int s3c64xx_sclk_ctrl(struct clk *clk, int enable);
 
-/* Init for pwm clock code */
-
-extern void s3c_pwmclk_init(void);
-
 /* Global watchdog clock used by arch_wtd_reset() callback */
 
 extern struct clk *s3c2410_wdtclk;
diff --git a/arch/arm/plat-samsung/include/plat/devs.h b/arch/arm/plat-samsung/include/plat/devs.h
index 87d501ff3328..0dc4ac4909b0 100644
--- a/arch/arm/plat-samsung/include/plat/devs.h
+++ b/arch/arm/plat-samsung/include/plat/devs.h
@@ -134,6 +134,7 @@ extern struct platform_device exynos4_device_spdif;
 
 extern struct platform_device samsung_asoc_idma;
 extern struct platform_device samsung_device_keypad;
+extern struct platform_device samsung_device_pwm;
 
 /* s3c2440 specific devices */
 
diff --git a/arch/arm/plat-samsung/include/plat/irq-vic-timer.h b/arch/arm/plat-samsung/include/plat/irq-vic-timer.h
deleted file mode 100644
index 5b9c42fd32d7..000000000000
--- a/arch/arm/plat-samsung/include/plat/irq-vic-timer.h
+++ /dev/null
@@ -1,13 +0,0 @@
-/* arch/arm/plat-samsung/include/plat/irq-vic-timer.h
- *
- * Copyright (c) 2010 Simtec Electronics
- *	Ben Dooks <ben@simtec.co.uk>
- *
- * Header file for Samsung SoC IRQ VIC timer
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
-
-extern void s3c_init_vic_timer_irq(unsigned int num, unsigned int timer_irq);
diff --git a/arch/arm/plat-samsung/include/plat/irqs.h b/arch/arm/plat-samsung/include/plat/irqs.h
index df46b776976a..039001c0ef05 100644
--- a/arch/arm/plat-samsung/include/plat/irqs.h
+++ b/arch/arm/plat-samsung/include/plat/irqs.h
@@ -44,15 +44,6 @@
 #define S5P_IRQ_VIC2(x)		(S5P_VIC2_BASE + (x))
 #define S5P_IRQ_VIC3(x)		(S5P_VIC3_BASE + (x))
 
-#define S5P_TIMER_IRQ(x)	(IRQ_TIMER_BASE + (x))
-
-#define IRQ_TIMER0		S5P_TIMER_IRQ(0)
-#define IRQ_TIMER1		S5P_TIMER_IRQ(1)
-#define IRQ_TIMER2		S5P_TIMER_IRQ(2)
-#define IRQ_TIMER3		S5P_TIMER_IRQ(3)
-#define IRQ_TIMER4		S5P_TIMER_IRQ(4)
-#define IRQ_TIMER_COUNT		(5)
-
 #define IRQ_EINT(x)		((x) < 16 ? ((x) + S5P_EINT_BASE1) \
 					: ((x) - 16 + S5P_EINT_BASE2))
 
diff --git a/arch/arm/plat-samsung/include/plat/pwm-clock.h b/arch/arm/plat-samsung/include/plat/pwm-clock.h
deleted file mode 100644
index bf6a60eb6237..000000000000
--- a/arch/arm/plat-samsung/include/plat/pwm-clock.h
+++ /dev/null
@@ -1,81 +0,0 @@
-/* linux/arch/arm/plat-samsung/include/plat/pwm-clock.h
- *
- * Copyright (c) 2010-2011 Samsung Electronics Co., Ltd.
- *		http://www.samsung.com
- *
- * Copyright 2008 Openmoko, Inc.
- * Copyright 2008 Simtec Electronics
- *      Ben Dooks <ben@simtec.co.uk>
- *      http://armlinux.simtec.co.uk/
- *
- * SAMSUNG - pwm clock and timer support
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
-
-#ifndef __ASM_PLAT_PWM_CLOCK_H
-#define __ASM_PLAT_PWM_CLOCK_H __FILE__
-
-/**
- * pwm_cfg_src_is_tclk() - return whether the given mux config is a tclk
- * @tcfg: The timer TCFG1 register bits shifted down to 0.
- *
- * Return true if the given configuration from TCFG1 is a TCLK instead
- * any of the TDIV clocks.
- */
-static inline int pwm_cfg_src_is_tclk(unsigned long tcfg)
-{
-	if (soc_is_s3c24xx())
-		return tcfg == S3C2410_TCFG1_MUX_TCLK;
-	else if (soc_is_s3c64xx() || soc_is_s5pc100())
-		return tcfg >= S3C64XX_TCFG1_MUX_TCLK;
-	else if (soc_is_s5p6440() || soc_is_s5p6450())
-		return 0;
-	else
-		return tcfg == S3C64XX_TCFG1_MUX_TCLK;
-}
-
-/**
- * tcfg_to_divisor() - convert tcfg1 setting to a divisor
- * @tcfg1: The tcfg1 setting, shifted down.
- *
- * Get the divisor value for the given tcfg1 setting. We assume the
- * caller has already checked to see if this is not a TCLK source.
- */
-static inline unsigned long tcfg_to_divisor(unsigned long tcfg1)
-{
-	if (soc_is_s3c24xx())
-		return 1 << (tcfg1 + 1);
-	else
-		return 1 << tcfg1;
-}
-
-/**
- * pwm_tdiv_has_div1() - does the tdiv setting have a /1
- *
- * Return true if we have a /1 in the tdiv setting.
- */
-static inline unsigned int pwm_tdiv_has_div1(void)
-{
-	if (soc_is_s3c24xx())
-		return 0;
-	else
-		return 1;
-}
-
-/**
- * pwm_tdiv_div_bits() - calculate TCFG1 divisor value.
- * @div: The divisor to calculate the bit information for.
- *
- * Turn a divisor into the necessary bit field for TCFG1.
- */
-static inline unsigned long pwm_tdiv_div_bits(unsigned int div)
-{
-	if (soc_is_s3c24xx())
-		return ilog2(div) - 1;
-	else
-		return ilog2(div);
-}
-#endif /* __ASM_PLAT_PWM_CLOCK_H */
diff --git a/arch/arm/plat-samsung/include/plat/pwm-core.h b/arch/arm/plat-samsung/include/plat/pwm-core.h
new file mode 100644
index 000000000000..5bff1facb672
--- /dev/null
+++ b/arch/arm/plat-samsung/include/plat/pwm-core.h
@@ -0,0 +1,22 @@
+/*
+ * Copyright 2013 Tomasz Figa <tomasz.figa@gmail.com>
+ *
+ * Samsung PWM controller platform data helpers.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __ASM_ARCH_PWM_CORE_H
+#define __ASM_ARCH_PWM_CORE_H __FILE__
+
+#include <clocksource/samsung_pwm.h>
+
+#ifdef CONFIG_SAMSUNG_DEV_PWM
+extern void samsung_pwm_set_platdata(struct samsung_pwm_variant *pd);
+#else
+static inline void samsung_pwm_set_platdata(struct samsung_pwm_variant *pd) { }
+#endif
+
+#endif /* __ASM_ARCH_PWM_CORE_H */
diff --git a/arch/arm/plat-samsung/include/plat/regs-timer.h b/arch/arm/plat-samsung/include/plat/regs-timer.h
deleted file mode 100644
index d097d92f8cc7..000000000000
--- a/arch/arm/plat-samsung/include/plat/regs-timer.h
+++ /dev/null
@@ -1,124 +0,0 @@
-/* arch/arm/mach-s3c2410/include/mach/regs-timer.h
- *
- * Copyright (c) 2003 Simtec Electronics <linux@simtec.co.uk>
- *		      http://www.simtec.co.uk/products/SWLINUX/
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * S3C2410 Timer configuration
-*/
-
-#ifndef __ASM_ARCH_REGS_TIMER_H
-#define __ASM_ARCH_REGS_TIMER_H
-
-#define S3C_TIMERREG(x) (S3C_VA_TIMER + (x))
-#define S3C_TIMERREG2(tmr,reg) S3C_TIMERREG((reg)+0x0c+((tmr)*0x0c))
-
-#define S3C2410_TCFG0	      S3C_TIMERREG(0x00)
-#define S3C2410_TCFG1	      S3C_TIMERREG(0x04)
-#define S3C2410_TCON	      S3C_TIMERREG(0x08)
-
-#define S3C64XX_TINT_CSTAT    S3C_TIMERREG(0x44)
-
-#define S3C2410_TCFG_PRESCALER0_MASK (255<<0)
-#define S3C2410_TCFG_PRESCALER1_MASK (255<<8)
-#define S3C2410_TCFG_PRESCALER1_SHIFT (8)
-#define S3C2410_TCFG_DEADZONE_MASK   (255<<16)
-#define S3C2410_TCFG_DEADZONE_SHIFT  (16)
-
-#define S3C2410_TCFG1_MUX4_DIV2	  (0<<16)
-#define S3C2410_TCFG1_MUX4_DIV4	  (1<<16)
-#define S3C2410_TCFG1_MUX4_DIV8	  (2<<16)
-#define S3C2410_TCFG1_MUX4_DIV16  (3<<16)
-#define S3C2410_TCFG1_MUX4_TCLK1  (4<<16)
-#define S3C2410_TCFG1_MUX4_MASK	  (15<<16)
-#define S3C2410_TCFG1_MUX4_SHIFT  (16)
-
-#define S3C2410_TCFG1_MUX3_DIV2	  (0<<12)
-#define S3C2410_TCFG1_MUX3_DIV4	  (1<<12)
-#define S3C2410_TCFG1_MUX3_DIV8	  (2<<12)
-#define S3C2410_TCFG1_MUX3_DIV16  (3<<12)
-#define S3C2410_TCFG1_MUX3_TCLK1  (4<<12)
-#define S3C2410_TCFG1_MUX3_MASK	  (15<<12)
-
-
-#define S3C2410_TCFG1_MUX2_DIV2	  (0<<8)
-#define S3C2410_TCFG1_MUX2_DIV4	  (1<<8)
-#define S3C2410_TCFG1_MUX2_DIV8	  (2<<8)
-#define S3C2410_TCFG1_MUX2_DIV16  (3<<8)
-#define S3C2410_TCFG1_MUX2_TCLK1  (4<<8)
-#define S3C2410_TCFG1_MUX2_MASK	  (15<<8)
-
-
-#define S3C2410_TCFG1_MUX1_DIV2	  (0<<4)
-#define S3C2410_TCFG1_MUX1_DIV4	  (1<<4)
-#define S3C2410_TCFG1_MUX1_DIV8	  (2<<4)
-#define S3C2410_TCFG1_MUX1_DIV16  (3<<4)
-#define S3C2410_TCFG1_MUX1_TCLK0  (4<<4)
-#define S3C2410_TCFG1_MUX1_MASK	  (15<<4)
-
-#define S3C2410_TCFG1_MUX0_DIV2	  (0<<0)
-#define S3C2410_TCFG1_MUX0_DIV4	  (1<<0)
-#define S3C2410_TCFG1_MUX0_DIV8	  (2<<0)
-#define S3C2410_TCFG1_MUX0_DIV16  (3<<0)
-#define S3C2410_TCFG1_MUX0_TCLK0  (4<<0)
-#define S3C2410_TCFG1_MUX0_MASK	  (15<<0)
-
-#define S3C2410_TCFG1_MUX_DIV2	  (0<<0)
-#define S3C2410_TCFG1_MUX_DIV4	  (1<<0)
-#define S3C2410_TCFG1_MUX_DIV8	  (2<<0)
-#define S3C2410_TCFG1_MUX_DIV16   (3<<0)
-#define S3C2410_TCFG1_MUX_TCLK    (4<<0)
-#define S3C2410_TCFG1_MUX_MASK	  (15<<0)
-
-#define S3C64XX_TCFG1_MUX_DIV1	  (0<<0)
-#define S3C64XX_TCFG1_MUX_DIV2	  (1<<0)
-#define S3C64XX_TCFG1_MUX_DIV4	  (2<<0)
-#define S3C64XX_TCFG1_MUX_DIV8    (3<<0)
-#define S3C64XX_TCFG1_MUX_DIV16   (4<<0)
-#define S3C64XX_TCFG1_MUX_TCLK    (5<<0)  /* 3 sets of TCLK */
-#define S3C64XX_TCFG1_MUX_MASK	  (15<<0)
-
-#define S3C2410_TCFG1_SHIFT(x)	  ((x) * 4)
-
-/* for each timer, we have an count buffer, an compare buffer and
- * an observation buffer
-*/
-
-/* WARNING - timer 4 has no buffer reg, and it's observation is at +4 */
-
-#define S3C2410_TCNTB(tmr)    S3C_TIMERREG2(tmr, 0x00)
-#define S3C2410_TCMPB(tmr)    S3C_TIMERREG2(tmr, 0x04)
-#define S3C2410_TCNTO(tmr)    S3C_TIMERREG2(tmr, (((tmr) == 4) ? 0x04 : 0x08))
-
-#define S3C2410_TCON_T4RELOAD	  (1<<22)
-#define S3C2410_TCON_T4MANUALUPD  (1<<21)
-#define S3C2410_TCON_T4START	  (1<<20)
-
-#define S3C2410_TCON_T3RELOAD	  (1<<19)
-#define S3C2410_TCON_T3INVERT	  (1<<18)
-#define S3C2410_TCON_T3MANUALUPD  (1<<17)
-#define S3C2410_TCON_T3START	  (1<<16)
-
-#define S3C2410_TCON_T2RELOAD	  (1<<15)
-#define S3C2410_TCON_T2INVERT	  (1<<14)
-#define S3C2410_TCON_T2MANUALUPD  (1<<13)
-#define S3C2410_TCON_T2START	  (1<<12)
-
-#define S3C2410_TCON_T1RELOAD	  (1<<11)
-#define S3C2410_TCON_T1INVERT	  (1<<10)
-#define S3C2410_TCON_T1MANUALUPD  (1<<9)
-#define S3C2410_TCON_T1START	  (1<<8)
-
-#define S3C2410_TCON_T0DEADZONE	  (1<<4)
-#define S3C2410_TCON_T0RELOAD	  (1<<3)
-#define S3C2410_TCON_T0INVERT	  (1<<2)
-#define S3C2410_TCON_T0MANUALUPD  (1<<1)
-#define S3C2410_TCON_T0START	  (1<<0)
-
-#endif /*  __ASM_ARCH_REGS_TIMER_H */
-
-
-
diff --git a/arch/arm/plat-samsung/include/plat/samsung-time.h b/arch/arm/plat-samsung/include/plat/samsung-time.h
index 4cc99bb1f176..209464adef97 100644
--- a/arch/arm/plat-samsung/include/plat/samsung-time.h
+++ b/arch/arm/plat-samsung/include/plat/samsung-time.h
@@ -22,29 +22,6 @@ enum samsung_timer_mode {
 	SAMSUNG_PWM4,
 };
 
-struct samsung_timer_source {
-	unsigned int event_id;
-	unsigned int source_id;
-};
-
-/* Be able to sleep for atleast 4 seconds (usually more) */
-#define SAMSUNG_TIMER_MIN_RANGE	4
-
-#if defined(CONFIG_ARCH_S3C24XX) || defined(CONFIG_ARCH_S5PC100)
-#define TCNT_MAX		0xffff
-#define TSCALER_DIV		25
-#define TDIV			50
-#define TSIZE			16
-#else
-#define TCNT_MAX		0xffffffff
-#define TSCALER_DIV		2
-#define TDIV			2
-#define TSIZE			32
-#endif
-
-#define NON_PERIODIC		0
-#define PERIODIC		1
-
 extern void __init samsung_set_timer_source(enum samsung_timer_mode event,
 					enum samsung_timer_mode source);
 
diff --git a/arch/arm/plat-samsung/include/plat/sdhci.h b/arch/arm/plat-samsung/include/plat/sdhci.h
index ce1d0f785efd..bf650218b40e 100644
--- a/arch/arm/plat-samsung/include/plat/sdhci.h
+++ b/arch/arm/plat-samsung/include/plat/sdhci.h
@@ -260,44 +260,6 @@ static inline void s5pv210_default_sdhci3(void) { }
 
 #endif /* CONFIG_S5PV210_SETUP_SDHCI */
 
-/* EXYNOS4 SDHCI setup */
-#ifdef CONFIG_EXYNOS4_SETUP_SDHCI
-static inline void exynos4_default_sdhci0(void)
-{
-#ifdef CONFIG_S3C_DEV_HSMMC
-	s3c_hsmmc0_def_platdata.cfg_gpio = exynos4_setup_sdhci0_cfg_gpio;
-#endif
-}
-
-static inline void exynos4_default_sdhci1(void)
-{
-#ifdef CONFIG_S3C_DEV_HSMMC1
-	s3c_hsmmc1_def_platdata.cfg_gpio = exynos4_setup_sdhci1_cfg_gpio;
-#endif
-}
-
-static inline void exynos4_default_sdhci2(void)
-{
-#ifdef CONFIG_S3C_DEV_HSMMC2
-	s3c_hsmmc2_def_platdata.cfg_gpio = exynos4_setup_sdhci2_cfg_gpio;
-#endif
-}
-
-static inline void exynos4_default_sdhci3(void)
-{
-#ifdef CONFIG_S3C_DEV_HSMMC3
-	s3c_hsmmc3_def_platdata.cfg_gpio = exynos4_setup_sdhci3_cfg_gpio;
-#endif
-}
-
-#else
-static inline void exynos4_default_sdhci0(void) { }
-static inline void exynos4_default_sdhci1(void) { }
-static inline void exynos4_default_sdhci2(void) { }
-static inline void exynos4_default_sdhci3(void) { }
-
-#endif /* CONFIG_EXYNOS4_SETUP_SDHCI */
-
 static inline void s3c_sdhci_setname(int id, char *name)
 {
 	switch (id) {
diff --git a/arch/arm/plat-samsung/irq-vic-timer.c b/arch/arm/plat-samsung/irq-vic-timer.c
deleted file mode 100644
index 0fceb4273824..000000000000
--- a/arch/arm/plat-samsung/irq-vic-timer.c
+++ /dev/null
@@ -1,98 +0,0 @@
-/* arch/arm/plat-samsung/irq-vic-timer.c
- *	originally part of arch/arm/plat-s3c64xx/irq.c
- *
- * Copyright 2008 Openmoko, Inc.
- * Copyright 2008 Simtec Electronics
- *      Ben Dooks <ben@simtec.co.uk>
- *      http://armlinux.simtec.co.uk/
- *
- * S3C64XX - Interrupt handling
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/kernel.h>
-#include <linux/interrupt.h>
-#include <linux/irq.h>
-#include <linux/irqchip/chained_irq.h>
-#include <linux/io.h>
-
-#include <mach/map.h>
-#include <mach/irqs.h>
-#include <plat/cpu.h>
-#include <plat/irq-vic-timer.h>
-#include <plat/regs-timer.h>
-
-static void s3c_irq_demux_vic_timer(unsigned int irq, struct irq_desc *desc)
-{
-	struct irq_chip *chip = irq_get_chip(irq);
-	chained_irq_enter(chip, desc);
-	generic_handle_irq((int)desc->irq_data.handler_data);
-	chained_irq_exit(chip, desc);
-}
-
-/* We assume the IRQ_TIMER0..IRQ_TIMER4 range is continuous. */
-static void s3c_irq_timer_ack(struct irq_data *d)
-{
-	struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d);
-	u32 mask = (1 << 5) << (d->irq - gc->irq_base);
-
-	irq_reg_writel(mask | gc->mask_cache, gc->reg_base);
-}
-
-/**
- * s3c_init_vic_timer_irq() - initialise timer irq chanined off VIC.\
- * @num: Number of timers to initialize
- * @timer_irq: Base IRQ number to be used for the timers.
- *
- * Register the necessary IRQ chaining and support for the timer IRQs
- * chained of the VIC.
- */
-void __init s3c_init_vic_timer_irq(unsigned int num, unsigned int timer_irq)
-{
-	unsigned int pirq[5] = { IRQ_TIMER0_VIC, IRQ_TIMER1_VIC, IRQ_TIMER2_VIC,
-				 IRQ_TIMER3_VIC, IRQ_TIMER4_VIC };
-	struct irq_chip_generic *s3c_tgc;
-	struct irq_chip_type *ct;
-	unsigned int i;
-
-#ifdef CONFIG_ARCH_EXYNOS
-	if (soc_is_exynos5250()) {
-		pirq[0] = EXYNOS5_IRQ_TIMER0_VIC;
-		pirq[1] = EXYNOS5_IRQ_TIMER1_VIC;
-		pirq[2] = EXYNOS5_IRQ_TIMER2_VIC;
-		pirq[3] = EXYNOS5_IRQ_TIMER3_VIC;
-		pirq[4] = EXYNOS5_IRQ_TIMER4_VIC;
-	} else {
-		pirq[0] = EXYNOS4_IRQ_TIMER0_VIC;
-		pirq[1] = EXYNOS4_IRQ_TIMER1_VIC;
-		pirq[2] = EXYNOS4_IRQ_TIMER2_VIC;
-		pirq[3] = EXYNOS4_IRQ_TIMER3_VIC;
-		pirq[4] = EXYNOS4_IRQ_TIMER4_VIC;
-	}
-#endif
-	s3c_tgc = irq_alloc_generic_chip("s3c-timer", 1, timer_irq,
-					 S3C64XX_TINT_CSTAT, handle_level_irq);
-
-	if (!s3c_tgc) {
-		pr_err("%s: irq_alloc_generic_chip for IRQ %d failed\n",
-		       __func__, timer_irq);
-		return;
-	}
-
-	ct = s3c_tgc->chip_types;
-	ct->chip.irq_mask = irq_gc_mask_clr_bit;
-	ct->chip.irq_unmask = irq_gc_mask_set_bit;
-	ct->chip.irq_ack = s3c_irq_timer_ack;
-	irq_setup_generic_chip(s3c_tgc, IRQ_MSK(num), IRQ_GC_INIT_MASK_CACHE,
-			       IRQ_NOREQUEST | IRQ_NOPROBE, 0);
-	/* Clear the upper bits of the mask_cache*/
-	s3c_tgc->mask_cache &= 0x1f;
-
-	for (i = 0; i < num; i++, timer_irq++) {
-		irq_set_chained_handler(pirq[i], s3c_irq_demux_vic_timer);
-		irq_set_handler_data(pirq[i], (void *)timer_irq);
-	}
-}
diff --git a/arch/arm/plat-samsung/pwm-clock.c b/arch/arm/plat-samsung/pwm-clock.c
deleted file mode 100644
index a35ff3bcffe4..000000000000
--- a/arch/arm/plat-samsung/pwm-clock.c
+++ /dev/null
@@ -1,474 +0,0 @@
-/* linux/arch/arm/plat-s3c24xx/pwm-clock.c
- *
- * Copyright (c) 2007 Simtec Electronics
- * Copyright (c) 2007, 2008 Ben Dooks
- *	Ben Dooks <ben-linux@fluff.org>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License.
-*/
-
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/list.h>
-#include <linux/errno.h>
-#include <linux/log2.h>
-#include <linux/clk.h>
-#include <linux/err.h>
-#include <linux/io.h>
-
-#include <mach/hardware.h>
-#include <mach/map.h>
-#include <asm/irq.h>
-
-#include <plat/clock.h>
-#include <plat/cpu.h>
-
-#include <plat/regs-timer.h>
-#include <plat/pwm-clock.h>
-
-/* Each of the timers 0 through 5 go through the following
- * clock tree, with the inputs depending on the timers.
- *
- * pclk ---- [ prescaler 0 ] -+---> timer 0
- *			      +---> timer 1
- *
- * pclk ---- [ prescaler 1 ] -+---> timer 2
- *			      +---> timer 3
- *			      \---> timer 4
- *
- * Which are fed into the timers as so:
- *
- * prescaled 0 ---- [ div 2,4,8,16 ] ---\
- *				       [mux] -> timer 0
- * tclk 0 ------------------------------/
- *
- * prescaled 0 ---- [ div 2,4,8,16 ] ---\
- *				       [mux] -> timer 1
- * tclk 0 ------------------------------/
- *
- *
- * prescaled 1 ---- [ div 2,4,8,16 ] ---\
- *				       [mux] -> timer 2
- * tclk 1 ------------------------------/
- *
- * prescaled 1 ---- [ div 2,4,8,16 ] ---\
- *				       [mux] -> timer 3
- * tclk 1 ------------------------------/
- *
- * prescaled 1 ---- [ div 2,4,8, 16 ] --\
- *				       [mux] -> timer 4
- * tclk 1 ------------------------------/
- *
- * Since the mux and the divider are tied together in the
- * same register space, it is impossible to set the parent
- * and the rate at the same time. To avoid this, we add an
- * intermediate 'prescaled-and-divided' clock to select
- * as the parent for the timer input clock called tdiv.
- *
- * prescaled clk --> pwm-tdiv ---\
- *                             [ mux ] --> timer X
- * tclk -------------------------/
-*/
-
-static struct clk clk_timer_scaler[];
-
-static unsigned long clk_pwm_scaler_get_rate(struct clk *clk)
-{
-	unsigned long tcfg0 = __raw_readl(S3C2410_TCFG0);
-
-	if (clk == &clk_timer_scaler[1]) {
-		tcfg0 &= S3C2410_TCFG_PRESCALER1_MASK;
-		tcfg0 >>= S3C2410_TCFG_PRESCALER1_SHIFT;
-	} else {
-		tcfg0 &= S3C2410_TCFG_PRESCALER0_MASK;
-	}
-
-	return clk_get_rate(clk->parent) / (tcfg0 + 1);
-}
-
-static unsigned long clk_pwm_scaler_round_rate(struct clk *clk,
-					       unsigned long rate)
-{
-	unsigned long parent_rate = clk_get_rate(clk->parent);
-	unsigned long divisor = parent_rate / rate;
-
-	if (divisor > 256)
-		divisor = 256;
-	else if (divisor < 2)
-		divisor = 2;
-
-	return parent_rate / divisor;
-}
-
-static int clk_pwm_scaler_set_rate(struct clk *clk, unsigned long rate)
-{
-	unsigned long round = clk_pwm_scaler_round_rate(clk, rate);
-	unsigned long tcfg0;
-	unsigned long divisor;
-	unsigned long flags;
-
-	divisor = clk_get_rate(clk->parent) / round;
-	divisor--;
-
-	local_irq_save(flags);
-	tcfg0 = __raw_readl(S3C2410_TCFG0);
-
-	if (clk == &clk_timer_scaler[1]) {
-		tcfg0 &= ~S3C2410_TCFG_PRESCALER1_MASK;
-		tcfg0 |= divisor << S3C2410_TCFG_PRESCALER1_SHIFT;
-	} else {
-		tcfg0 &= ~S3C2410_TCFG_PRESCALER0_MASK;
-		tcfg0 |= divisor;
-	}
-
-	__raw_writel(tcfg0, S3C2410_TCFG0);
-	local_irq_restore(flags);
-
-	return 0;
-}
-
-static struct clk_ops clk_pwm_scaler_ops = {
-	.get_rate	= clk_pwm_scaler_get_rate,
-	.set_rate	= clk_pwm_scaler_set_rate,
-	.round_rate	= clk_pwm_scaler_round_rate,
-};
-
-static struct clk clk_timer_scaler[] = {
-	[0]	= {
-		.name		= "pwm-scaler0",
-		.id		= -1,
-		.ops		= &clk_pwm_scaler_ops,
-	},
-	[1]	= {
-		.name		= "pwm-scaler1",
-		.id		= -1,
-		.ops		= &clk_pwm_scaler_ops,
-	},
-};
-
-static struct clk clk_timer_tclk[] = {
-	[0]	= {
-		.name		= "pwm-tclk0",
-		.id		= -1,
-	},
-	[1]	= {
-		.name		= "pwm-tclk1",
-		.id		= -1,
-	},
-};
-
-struct pwm_tdiv_clk {
-	struct clk	clk;
-	unsigned int	divisor;
-};
-
-static inline struct pwm_tdiv_clk *to_tdiv(struct clk *clk)
-{
-	return container_of(clk, struct pwm_tdiv_clk, clk);
-}
-
-static unsigned long clk_pwm_tdiv_get_rate(struct clk *clk)
-{
-	unsigned long tcfg1 = __raw_readl(S3C2410_TCFG1);
-	unsigned int divisor;
-
-	tcfg1 >>= S3C2410_TCFG1_SHIFT(clk->id);
-	tcfg1 &= S3C2410_TCFG1_MUX_MASK;
-
-	if (pwm_cfg_src_is_tclk(tcfg1))
-		divisor = to_tdiv(clk)->divisor;
-	else
-		divisor = tcfg_to_divisor(tcfg1);
-
-	return clk_get_rate(clk->parent) / divisor;
-}
-
-static unsigned long clk_pwm_tdiv_round_rate(struct clk *clk,
-					     unsigned long rate)
-{
-	unsigned long parent_rate;
-	unsigned long divisor;
-
-	parent_rate = clk_get_rate(clk->parent);
-	divisor = parent_rate / rate;
-
-	if (divisor <= 1 && pwm_tdiv_has_div1())
-		divisor = 1;
-	else if (divisor <= 2)
-		divisor = 2;
-	else if (divisor <= 4)
-		divisor = 4;
-	else if (divisor <= 8)
-		divisor = 8;
-	else
-		divisor = 16;
-
-	return parent_rate / divisor;
-}
-
-static unsigned long clk_pwm_tdiv_bits(struct pwm_tdiv_clk *divclk)
-{
-	return pwm_tdiv_div_bits(divclk->divisor);
-}
-
-static void clk_pwm_tdiv_update(struct pwm_tdiv_clk *divclk)
-{
-	unsigned long tcfg1 = __raw_readl(S3C2410_TCFG1);
-	unsigned long bits = clk_pwm_tdiv_bits(divclk);
-	unsigned long flags;
-	unsigned long shift =  S3C2410_TCFG1_SHIFT(divclk->clk.id);
-
-	local_irq_save(flags);
-
-	tcfg1 = __raw_readl(S3C2410_TCFG1);
-	tcfg1 &= ~(S3C2410_TCFG1_MUX_MASK << shift);
-	tcfg1 |= bits << shift;
-	__raw_writel(tcfg1, S3C2410_TCFG1);
-
-	local_irq_restore(flags);
-}
-
-static int clk_pwm_tdiv_set_rate(struct clk *clk, unsigned long rate)
-{
-	struct pwm_tdiv_clk *divclk = to_tdiv(clk);
-	unsigned long tcfg1 = __raw_readl(S3C2410_TCFG1);
-	unsigned long parent_rate = clk_get_rate(clk->parent);
-	unsigned long divisor;
-
-	tcfg1 >>= S3C2410_TCFG1_SHIFT(clk->id);
-	tcfg1 &= S3C2410_TCFG1_MUX_MASK;
-
-	rate = clk_round_rate(clk, rate);
-	divisor = parent_rate / rate;
-
-	if (divisor > 16)
-		return -EINVAL;
-
-	divclk->divisor = divisor;
-
-	/* Update the current MUX settings if we are currently
-	 * selected as the clock source for this clock. */
-
-	if (!pwm_cfg_src_is_tclk(tcfg1))
-		clk_pwm_tdiv_update(divclk);
-
-	return 0;
-}
-
-static struct clk_ops clk_tdiv_ops = {
-	.get_rate	= clk_pwm_tdiv_get_rate,
-	.set_rate	= clk_pwm_tdiv_set_rate,
-	.round_rate	= clk_pwm_tdiv_round_rate,
-};
-
-static struct pwm_tdiv_clk clk_timer_tdiv[] = {
-	[0]	= {
-		.clk	= {
-			.name	= "pwm-tdiv",
-			.devname	= "s3c24xx-pwm.0",
-			.ops	= &clk_tdiv_ops,
-			.parent	= &clk_timer_scaler[0],
-		},
-	},
-	[1]	= {
-		.clk	= {
-			.name	= "pwm-tdiv",
-			.devname	= "s3c24xx-pwm.1",
-			.ops	= &clk_tdiv_ops,
-			.parent	= &clk_timer_scaler[0],
-		}
-	},
-	[2]	= {
-		.clk	= {
-			.name	= "pwm-tdiv",
-			.devname	= "s3c24xx-pwm.2",
-			.ops	= &clk_tdiv_ops,
-			.parent	= &clk_timer_scaler[1],
-		},
-	},
-	[3]	= {
-		.clk	= {
-			.name	= "pwm-tdiv",
-			.devname	= "s3c24xx-pwm.3",
-			.ops	= &clk_tdiv_ops,
-			.parent	= &clk_timer_scaler[1],
-		},
-	},
-	[4]	= {
-		.clk	= {
-			.name	= "pwm-tdiv",
-			.devname	= "s3c24xx-pwm.4",
-			.ops	= &clk_tdiv_ops,
-			.parent	= &clk_timer_scaler[1],
-		},
-	},
-};
-
-static int __init clk_pwm_tdiv_register(unsigned int id)
-{
-	struct pwm_tdiv_clk *divclk = &clk_timer_tdiv[id];
-	unsigned long tcfg1 = __raw_readl(S3C2410_TCFG1);
-
-	tcfg1 >>= S3C2410_TCFG1_SHIFT(id);
-	tcfg1 &= S3C2410_TCFG1_MUX_MASK;
-
-	divclk->clk.id = id;
-	divclk->divisor = tcfg_to_divisor(tcfg1);
-
-	return s3c24xx_register_clock(&divclk->clk);
-}
-
-static inline struct clk *s3c24xx_pwmclk_tclk(unsigned int id)
-{
-	return (id >= 2) ? &clk_timer_tclk[1] : &clk_timer_tclk[0];
-}
-
-static inline struct clk *s3c24xx_pwmclk_tdiv(unsigned int id)
-{
-	return &clk_timer_tdiv[id].clk;
-}
-
-static int clk_pwm_tin_set_parent(struct clk *clk, struct clk *parent)
-{
-	unsigned int id = clk->id;
-	unsigned long tcfg1;
-	unsigned long flags;
-	unsigned long bits;
-	unsigned long shift = S3C2410_TCFG1_SHIFT(id);
-
-	unsigned long mux_tclk;
-
-	if (soc_is_s3c24xx())
-		mux_tclk = S3C2410_TCFG1_MUX_TCLK;
-	else if (soc_is_s5p6440() || soc_is_s5p6450())
-		mux_tclk = 0;
-	else
-		mux_tclk = S3C64XX_TCFG1_MUX_TCLK;
-
-	if (parent == s3c24xx_pwmclk_tclk(id))
-		bits = mux_tclk << shift;
-	else if (parent == s3c24xx_pwmclk_tdiv(id))
-		bits = clk_pwm_tdiv_bits(to_tdiv(parent)) << shift;
-	else
-		return -EINVAL;
-
-	clk->parent = parent;
-
-	local_irq_save(flags);
-
-	tcfg1 = __raw_readl(S3C2410_TCFG1);
-	tcfg1 &= ~(S3C2410_TCFG1_MUX_MASK << shift);
-	__raw_writel(tcfg1 | bits, S3C2410_TCFG1);
-
-	local_irq_restore(flags);
-
-	return 0;
-}
-
-static struct clk_ops clk_tin_ops = {
-	.set_parent	= clk_pwm_tin_set_parent,
-};
-
-static struct clk clk_tin[] = {
-	[0]	= {
-		.name	= "pwm-tin",
-		.devname	= "s3c24xx-pwm.0",
-		.id	= 0,
-		.ops	= &clk_tin_ops,
-	},
-	[1]	= {
-		.name	= "pwm-tin",
-		.devname	= "s3c24xx-pwm.1",
-		.id	= 1,
-		.ops	= &clk_tin_ops,
-	},
-	[2]	= {
-		.name	= "pwm-tin",
-		.devname	= "s3c24xx-pwm.2",
-		.id	= 2,
-		.ops	= &clk_tin_ops,
-	},
-	[3]	= {
-		.name	= "pwm-tin",
-		.devname	= "s3c24xx-pwm.3",
-		.id	= 3,
-		.ops	= &clk_tin_ops,
-	},
-	[4]	= {
-		.name	= "pwm-tin",
-		.devname	= "s3c24xx-pwm.4",
-		.id	= 4,
-		.ops	= &clk_tin_ops,
-	},
-};
-
-static __init int clk_pwm_tin_register(struct clk *pwm)
-{
-	unsigned long tcfg1 = __raw_readl(S3C2410_TCFG1);
-	unsigned int id = pwm->id;
-
-	struct clk *parent;
-	int ret;
-
-	ret = s3c24xx_register_clock(pwm);
-	if (ret < 0)
-		return ret;
-
-	tcfg1 >>= S3C2410_TCFG1_SHIFT(id);
-	tcfg1 &= S3C2410_TCFG1_MUX_MASK;
-
-	if (pwm_cfg_src_is_tclk(tcfg1))
-		parent = s3c24xx_pwmclk_tclk(id);
-	else
-		parent = s3c24xx_pwmclk_tdiv(id);
-
-	return clk_set_parent(pwm, parent);
-}
-
-/**
- * s3c_pwmclk_init() - initialise pwm clocks
- *
- * Initialise and register the clocks which provide the inputs for the
- * pwm timer blocks.
- *
- * Note, this call is required by the time core, so must be called after
- * the base clocks are added and before any of the initcalls are run.
- */
-__init void s3c_pwmclk_init(void)
-{
-	struct clk *clk_timers;
-	unsigned int clk;
-	int ret;
-
-	clk_timers = clk_get(NULL, "timers");
-	if (IS_ERR(clk_timers)) {
-		printk(KERN_ERR "%s: no parent clock\n", __func__);
-		return;
-	}
-
-	for (clk = 0; clk < ARRAY_SIZE(clk_timer_scaler); clk++)
-		clk_timer_scaler[clk].parent = clk_timers;
-
-	s3c_register_clocks(clk_timer_scaler, ARRAY_SIZE(clk_timer_scaler));
-	s3c_register_clocks(clk_timer_tclk, ARRAY_SIZE(clk_timer_tclk));
-
-	for (clk = 0; clk < ARRAY_SIZE(clk_timer_tdiv); clk++) {
-		ret = clk_pwm_tdiv_register(clk);
-
-		if (ret < 0) {
-			printk(KERN_ERR "error adding pwm%d tdiv clock\n", clk);
-			return;
-		}
-	}
-
-	for (clk = 0; clk < ARRAY_SIZE(clk_tin); clk++) {
-		ret = clk_pwm_tin_register(&clk_tin[clk]);
-		if (ret < 0) {
-			printk(KERN_ERR "error adding pwm%d tin clock\n", clk);
-			return;
-		}
-	}
-}
diff --git a/arch/arm/plat-samsung/s3c-dma-ops.c b/arch/arm/plat-samsung/s3c-dma-ops.c
index 0cc40aea3f5a..98b10ba67dc7 100644
--- a/arch/arm/plat-samsung/s3c-dma-ops.c
+++ b/arch/arm/plat-samsung/s3c-dma-ops.c
@@ -82,7 +82,8 @@ static int s3c_dma_config(unsigned ch, struct samsung_dma_config *param)
 static int s3c_dma_prepare(unsigned ch, struct samsung_dma_prep *param)
 {
 	struct cb_data *data;
-	int len = (param->cap == DMA_CYCLIC) ? param->period : param->len;
+	dma_addr_t pos = param->buf;
+	dma_addr_t end = param->buf + param->len;
 
 	list_for_each_entry(data, &dma_list, node)
 		if (data->ch == ch)
@@ -94,7 +95,15 @@ static int s3c_dma_prepare(unsigned ch, struct samsung_dma_prep *param)
 		data->fp_param = param->fp_param;
 	}
 
-	s3c2410_dma_enqueue(ch, (void *)data, param->buf, len);
+	if (param->cap != DMA_CYCLIC) {
+		s3c2410_dma_enqueue(ch, (void *)data, param->buf, param->len);
+		return 0;
+	}
+
+	while (pos < end) {
+		s3c2410_dma_enqueue(ch, (void *)data, pos, param->period);
+		pos += param->period;
+	}
 
 	return 0;
 }
diff --git a/arch/arm/plat-samsung/s5p-irq.c b/arch/arm/plat-samsung/s5p-irq.c
index ff1a76011b1e..ddfaca9c79d8 100644
--- a/arch/arm/plat-samsung/s5p-irq.c
+++ b/arch/arm/plat-samsung/s5p-irq.c
@@ -17,9 +17,7 @@
 
 #include <mach/irqs.h>
 #include <mach/map.h>
-#include <plat/regs-timer.h>
 #include <plat/cpu.h>
-#include <plat/irq-vic-timer.h>
 
 void __init s5p_init_irq(u32 *vic, u32 num_vic)
 {
@@ -30,6 +28,4 @@ void __init s5p_init_irq(u32 *vic, u32 num_vic)
 	for (irq = 0; irq < num_vic; irq++)
 		vic_init(VA_VIC(irq), VIC_BASE(irq), vic[irq], 0);
 #endif
-
-	s3c_init_vic_timer_irq(5, IRQ_TIMER0);
 }
diff --git a/arch/arm/plat-samsung/samsung-time.c b/arch/arm/plat-samsung/samsung-time.c
deleted file mode 100644
index 2957075ca836..000000000000
--- a/arch/arm/plat-samsung/samsung-time.c
+++ /dev/null
@@ -1,394 +0,0 @@
-/*
- * Copyright (c) 2011 Samsung Electronics Co., Ltd.
- *		http://www.samsung.com/
- *
- * samsung - Common hr-timer support (s3c and s5p)
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
-
-#include <linux/interrupt.h>
-#include <linux/irq.h>
-#include <linux/err.h>
-#include <linux/clk.h>
-#include <linux/clockchips.h>
-#include <linux/platform_device.h>
-#include <linux/sched_clock.h>
-
-#include <asm/smp_twd.h>
-#include <asm/mach/time.h>
-#include <asm/mach/arch.h>
-#include <asm/mach/map.h>
-
-#include <mach/map.h>
-#include <plat/devs.h>
-#include <plat/regs-timer.h>
-#include <plat/samsung-time.h>
-
-static struct clk *tin_event;
-static struct clk *tin_source;
-static struct clk *tdiv_event;
-static struct clk *tdiv_source;
-static struct clk *timerclk;
-static struct samsung_timer_source timer_source;
-static unsigned long clock_count_per_tick;
-static void samsung_timer_resume(void);
-
-static void samsung_time_stop(enum samsung_timer_mode mode)
-{
-	unsigned long tcon;
-
-	tcon = __raw_readl(S3C2410_TCON);
-
-	switch (mode) {
-	case SAMSUNG_PWM0:
-		tcon &= ~S3C2410_TCON_T0START;
-		break;
-
-	case SAMSUNG_PWM1:
-		tcon &= ~S3C2410_TCON_T1START;
-		break;
-
-	case SAMSUNG_PWM2:
-		tcon &= ~S3C2410_TCON_T2START;
-		break;
-
-	case SAMSUNG_PWM3:
-		tcon &= ~S3C2410_TCON_T3START;
-		break;
-
-	case SAMSUNG_PWM4:
-		tcon &= ~S3C2410_TCON_T4START;
-		break;
-
-	default:
-		printk(KERN_ERR "Invalid Timer %d\n", mode);
-		break;
-	}
-	__raw_writel(tcon, S3C2410_TCON);
-}
-
-static void samsung_time_setup(enum samsung_timer_mode mode, unsigned long tcnt)
-{
-	unsigned long tcon;
-
-	tcon = __raw_readl(S3C2410_TCON);
-
-	tcnt--;
-
-	switch (mode) {
-	case SAMSUNG_PWM0:
-		tcon &= ~(0x0f << 0);
-		tcon |= S3C2410_TCON_T0MANUALUPD;
-		break;
-
-	case SAMSUNG_PWM1:
-		tcon &= ~(0x0f << 8);
-		tcon |= S3C2410_TCON_T1MANUALUPD;
-		break;
-
-	case SAMSUNG_PWM2:
-		tcon &= ~(0x0f << 12);
-		tcon |= S3C2410_TCON_T2MANUALUPD;
-		break;
-
-	case SAMSUNG_PWM3:
-		tcon &= ~(0x0f << 16);
-		tcon |= S3C2410_TCON_T3MANUALUPD;
-		break;
-
-	case SAMSUNG_PWM4:
-		tcon &= ~(0x07 << 20);
-		tcon |= S3C2410_TCON_T4MANUALUPD;
-		break;
-
-	default:
-		printk(KERN_ERR "Invalid Timer %d\n", mode);
-		break;
-	}
-
-	__raw_writel(tcnt, S3C2410_TCNTB(mode));
-	__raw_writel(tcnt, S3C2410_TCMPB(mode));
-	__raw_writel(tcon, S3C2410_TCON);
-}
-
-static void samsung_time_start(enum samsung_timer_mode mode, bool periodic)
-{
-	unsigned long tcon;
-
-	tcon  = __raw_readl(S3C2410_TCON);
-
-	switch (mode) {
-	case SAMSUNG_PWM0:
-		tcon |= S3C2410_TCON_T0START;
-		tcon &= ~S3C2410_TCON_T0MANUALUPD;
-
-		if (periodic)
-			tcon |= S3C2410_TCON_T0RELOAD;
-		else
-			tcon &= ~S3C2410_TCON_T0RELOAD;
-		break;
-
-	case SAMSUNG_PWM1:
-		tcon |= S3C2410_TCON_T1START;
-		tcon &= ~S3C2410_TCON_T1MANUALUPD;
-
-		if (periodic)
-			tcon |= S3C2410_TCON_T1RELOAD;
-		else
-			tcon &= ~S3C2410_TCON_T1RELOAD;
-		break;
-
-	case SAMSUNG_PWM2:
-		tcon |= S3C2410_TCON_T2START;
-		tcon &= ~S3C2410_TCON_T2MANUALUPD;
-
-		if (periodic)
-			tcon |= S3C2410_TCON_T2RELOAD;
-		else
-			tcon &= ~S3C2410_TCON_T2RELOAD;
-		break;
-
-	case SAMSUNG_PWM3:
-		tcon |= S3C2410_TCON_T3START;
-		tcon &= ~S3C2410_TCON_T3MANUALUPD;
-
-		if (periodic)
-			tcon |= S3C2410_TCON_T3RELOAD;
-		else
-			tcon &= ~S3C2410_TCON_T3RELOAD;
-		break;
-
-	case SAMSUNG_PWM4:
-		tcon |= S3C2410_TCON_T4START;
-		tcon &= ~S3C2410_TCON_T4MANUALUPD;
-
-		if (periodic)
-			tcon |= S3C2410_TCON_T4RELOAD;
-		else
-			tcon &= ~S3C2410_TCON_T4RELOAD;
-		break;
-
-	default:
-		printk(KERN_ERR "Invalid Timer %d\n", mode);
-		break;
-	}
-	__raw_writel(tcon, S3C2410_TCON);
-}
-
-static int samsung_set_next_event(unsigned long cycles,
-				struct clock_event_device *evt)
-{
-	samsung_time_setup(timer_source.event_id, cycles);
-	samsung_time_start(timer_source.event_id, NON_PERIODIC);
-
-	return 0;
-}
-
-static void samsung_set_mode(enum clock_event_mode mode,
-				struct clock_event_device *evt)
-{
-	samsung_time_stop(timer_source.event_id);
-
-	switch (mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
-		samsung_time_setup(timer_source.event_id, clock_count_per_tick);
-		samsung_time_start(timer_source.event_id, PERIODIC);
-		break;
-
-	case CLOCK_EVT_MODE_ONESHOT:
-		break;
-
-	case CLOCK_EVT_MODE_UNUSED:
-	case CLOCK_EVT_MODE_SHUTDOWN:
-		break;
-
-	case CLOCK_EVT_MODE_RESUME:
-		samsung_timer_resume();
-		break;
-	}
-}
-
-static void samsung_timer_resume(void)
-{
-	/* event timer restart */
-	samsung_time_setup(timer_source.event_id, clock_count_per_tick);
-	samsung_time_start(timer_source.event_id, PERIODIC);
-
-	/* source timer restart */
-	samsung_time_setup(timer_source.source_id, TCNT_MAX);
-	samsung_time_start(timer_source.source_id, PERIODIC);
-}
-
-void __init samsung_set_timer_source(enum samsung_timer_mode event,
-				 enum samsung_timer_mode source)
-{
-	s3c_device_timer[event].dev.bus = &platform_bus_type;
-	s3c_device_timer[source].dev.bus = &platform_bus_type;
-
-	timer_source.event_id = event;
-	timer_source.source_id = source;
-}
-
-static struct clock_event_device time_event_device = {
-	.name		= "samsung_event_timer",
-	.features	= CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT,
-	.rating		= 200,
-	.set_next_event	= samsung_set_next_event,
-	.set_mode	= samsung_set_mode,
-};
-
-static irqreturn_t samsung_clock_event_isr(int irq, void *dev_id)
-{
-	struct clock_event_device *evt = dev_id;
-
-	evt->event_handler(evt);
-
-	return IRQ_HANDLED;
-}
-
-static struct irqaction samsung_clock_event_irq = {
-	.name		= "samsung_time_irq",
-	.flags		= IRQF_DISABLED | IRQF_TIMER | IRQF_IRQPOLL,
-	.handler	= samsung_clock_event_isr,
-	.dev_id		= &time_event_device,
-};
-
-static void __init samsung_clockevent_init(void)
-{
-	unsigned long pclk;
-	unsigned long clock_rate;
-	unsigned int irq_number;
-	struct clk *tscaler;
-
-	pclk = clk_get_rate(timerclk);
-
-	tscaler = clk_get_parent(tdiv_event);
-
-	clk_set_rate(tscaler, pclk / TSCALER_DIV);
-	clk_set_rate(tdiv_event, pclk / TDIV);
-	clk_set_parent(tin_event, tdiv_event);
-
-	clock_rate = clk_get_rate(tin_event);
-	clock_count_per_tick = clock_rate / HZ;
-
-	time_event_device.cpumask = cpumask_of(0);
-	clockevents_config_and_register(&time_event_device, clock_rate, 1, -1);
-
-	irq_number = timer_source.event_id + IRQ_TIMER0;
-	setup_irq(irq_number, &samsung_clock_event_irq);
-}
-
-static void __iomem *samsung_timer_reg(void)
-{
-	unsigned long offset = 0;
-
-	switch (timer_source.source_id) {
-	case SAMSUNG_PWM0:
-	case SAMSUNG_PWM1:
-	case SAMSUNG_PWM2:
-	case SAMSUNG_PWM3:
-		offset = (timer_source.source_id * 0x0c) + 0x14;
-		break;
-
-	case SAMSUNG_PWM4:
-		offset = 0x40;
-		break;
-
-	default:
-		printk(KERN_ERR "Invalid Timer %d\n", timer_source.source_id);
-		return NULL;
-	}
-
-	return S3C_TIMERREG(offset);
-}
-
-/*
- * Override the global weak sched_clock symbol with this
- * local implementation which uses the clocksource to get some
- * better resolution when scheduling the kernel. We accept that
- * this wraps around for now, since it is just a relative time
- * stamp. (Inspired by U300 implementation.)
- */
-static u32 notrace samsung_read_sched_clock(void)
-{
-	void __iomem *reg = samsung_timer_reg();
-
-	if (!reg)
-		return 0;
-
-	return ~__raw_readl(reg);
-}
-
-static void __init samsung_clocksource_init(void)
-{
-	unsigned long pclk;
-	unsigned long clock_rate;
-
-	pclk = clk_get_rate(timerclk);
-
-	clk_set_rate(tdiv_source, pclk / TDIV);
-	clk_set_parent(tin_source, tdiv_source);
-
-	clock_rate = clk_get_rate(tin_source);
-
-	samsung_time_setup(timer_source.source_id, TCNT_MAX);
-	samsung_time_start(timer_source.source_id, PERIODIC);
-
-	setup_sched_clock(samsung_read_sched_clock, TSIZE, clock_rate);
-
-	if (clocksource_mmio_init(samsung_timer_reg(), "samsung_clocksource_timer",
-			clock_rate, 250, TSIZE, clocksource_mmio_readl_down))
-		panic("samsung_clocksource_timer: can't register clocksource\n");
-}
-
-static void __init samsung_timer_resources(void)
-{
-
-	unsigned long event_id = timer_source.event_id;
-	unsigned long source_id = timer_source.source_id;
-	char devname[15];
-
-	timerclk = clk_get(NULL, "timers");
-	if (IS_ERR(timerclk))
-		panic("failed to get timers clock for timer");
-
-	clk_enable(timerclk);
-
-	sprintf(devname, "s3c24xx-pwm.%lu", event_id);
-	s3c_device_timer[event_id].id = event_id;
-	s3c_device_timer[event_id].dev.init_name = devname;
-
-	tin_event = clk_get(&s3c_device_timer[event_id].dev, "pwm-tin");
-	if (IS_ERR(tin_event))
-		panic("failed to get pwm-tin clock for event timer");
-
-	tdiv_event = clk_get(&s3c_device_timer[event_id].dev, "pwm-tdiv");
-	if (IS_ERR(tdiv_event))
-		panic("failed to get pwm-tdiv clock for event timer");
-
-	clk_enable(tin_event);
-
-	sprintf(devname, "s3c24xx-pwm.%lu", source_id);
-	s3c_device_timer[source_id].id = source_id;
-	s3c_device_timer[source_id].dev.init_name = devname;
-
-	tin_source = clk_get(&s3c_device_timer[source_id].dev, "pwm-tin");
-	if (IS_ERR(tin_source))
-		panic("failed to get pwm-tin clock for source timer");
-
-	tdiv_source = clk_get(&s3c_device_timer[source_id].dev, "pwm-tdiv");
-	if (IS_ERR(tdiv_source))
-		panic("failed to get pwm-tdiv clock for source timer");
-
-	clk_enable(tin_source);
-}
-
-void __init samsung_timer_init(void)
-{
-	samsung_timer_resources();
-	samsung_clockevent_init();
-	samsung_clocksource_init();
-}
diff --git a/arch/arm/vfp/vfphw.S b/arch/arm/vfp/vfphw.S
index 8d10dc8a1e17..3e5d3115a2a6 100644
--- a/arch/arm/vfp/vfphw.S
+++ b/arch/arm/vfp/vfphw.S
@@ -78,6 +78,11 @@
 ENTRY(vfp_support_entry)
 	DBGSTR3	"instr %08x pc %08x state %p", r0, r2, r10
 
+	ldr	r3, [sp, #S_PSR]	@ Neither lazy restore nor FP exceptions
+	and	r3, r3, #MODE_MASK	@ are supported in kernel mode
+	teq	r3, #USR_MODE
+	bne	vfp_kmode_exception	@ Returns through lr
+
 	VFPFMRX	r1, FPEXC		@ Is the VFP enabled?
 	DBGSTR1	"fpexc %08x", r1
 	tst	r1, #FPEXC_EN
diff --git a/arch/arm/vfp/vfpmodule.c b/arch/arm/vfp/vfpmodule.c
index 5dfbb0b8e7f4..52b8f40b1c73 100644
--- a/arch/arm/vfp/vfpmodule.c
+++ b/arch/arm/vfp/vfpmodule.c
@@ -20,6 +20,7 @@
 #include <linux/init.h>
 #include <linux/uaccess.h>
 #include <linux/user.h>
+#include <linux/export.h>
 
 #include <asm/cp15.h>
 #include <asm/cputype.h>
@@ -648,6 +649,72 @@ static int vfp_hotplug(struct notifier_block *b, unsigned long action,
 	return NOTIFY_OK;
 }
 
+void vfp_kmode_exception(void)
+{
+	/*
+	 * If we reach this point, a floating point exception has been raised
+	 * while running in kernel mode. If the NEON/VFP unit was enabled at the
+	 * time, it means a VFP instruction has been issued that requires
+	 * software assistance to complete, something which is not currently
+	 * supported in kernel mode.
+	 * If the NEON/VFP unit was disabled, and the location pointed to below
+	 * is properly preceded by a call to kernel_neon_begin(), something has
+	 * caused the task to be scheduled out and back in again. In this case,
+	 * rebuilding and running with CONFIG_DEBUG_ATOMIC_SLEEP enabled should
+	 * be helpful in localizing the problem.
+	 */
+	if (fmrx(FPEXC) & FPEXC_EN)
+		pr_crit("BUG: unsupported FP instruction in kernel mode\n");
+	else
+		pr_crit("BUG: FP instruction issued in kernel mode with FP unit disabled\n");
+}
+
+#ifdef CONFIG_KERNEL_MODE_NEON
+
+/*
+ * Kernel-side NEON support functions
+ */
+void kernel_neon_begin(void)
+{
+	struct thread_info *thread = current_thread_info();
+	unsigned int cpu;
+	u32 fpexc;
+
+	/*
+	 * Kernel mode NEON is only allowed outside of interrupt context
+	 * with preemption disabled. This will make sure that the kernel
+	 * mode NEON register contents never need to be preserved.
+	 */
+	BUG_ON(in_interrupt());
+	cpu = get_cpu();
+
+	fpexc = fmrx(FPEXC) | FPEXC_EN;
+	fmxr(FPEXC, fpexc);
+
+	/*
+	 * Save the userland NEON/VFP state. Under UP,
+	 * the owner could be a task other than 'current'
+	 */
+	if (vfp_state_in_hw(cpu, thread))
+		vfp_save_state(&thread->vfpstate, fpexc);
+#ifndef CONFIG_SMP
+	else if (vfp_current_hw_state[cpu] != NULL)
+		vfp_save_state(vfp_current_hw_state[cpu], fpexc);
+#endif
+	vfp_current_hw_state[cpu] = NULL;
+}
+EXPORT_SYMBOL(kernel_neon_begin);
+
+void kernel_neon_end(void)
+{
+	/* Disable the NEON/VFP unit. */
+	fmxr(FPEXC, fmrx(FPEXC) & ~FPEXC_EN);
+	put_cpu();
+}
+EXPORT_SYMBOL(kernel_neon_end);
+
+#endif /* CONFIG_KERNEL_MODE_NEON */
+
 /*
  * VFP support code initialisation.
  */
@@ -731,4 +798,4 @@ static int __init vfp_init(void)
 	return 0;
 }
 
-late_initcall(vfp_init);
+core_initcall(vfp_init);
diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c
index 8a6295c86209..83e4f959ee47 100644
--- a/arch/arm/xen/enlighten.c
+++ b/arch/arm/xen/enlighten.c
@@ -21,6 +21,8 @@
 #include <linux/of.h>
 #include <linux/of_irq.h>
 #include <linux/of_address.h>
+#include <linux/cpuidle.h>
+#include <linux/cpufreq.h>
 
 #include <linux/mm.h>
 
@@ -267,18 +269,28 @@ static int __init xen_guest_init(void)
 	if (!xen_initial_domain())
 		xenbus_probe(NULL);
 
+	/*
+	 * Making sure board specific code will not set up ops for
+	 * cpu idle and cpu freq.
+	 */
+	disable_cpuidle();
+	disable_cpufreq();
+
 	return 0;
 }
 core_initcall(xen_guest_init);
 
 static int __init xen_pm_init(void)
 {
+	if (!xen_domain())
+		return -ENODEV;
+
 	pm_power_off = xen_power_off;
 	arm_pm_restart = xen_restart;
 
 	return 0;
 }
-subsys_initcall(xen_pm_init);
+late_initcall(xen_pm_init);
 
 static irqreturn_t xen_arm_callback(int irq, void *arg)
 {
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 9737e97f9f38..c04454876bcb 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -23,7 +23,6 @@ config ARM64
 	select HAVE_DMA_API_DEBUG
 	select HAVE_DMA_ATTRS
 	select HAVE_GENERIC_DMA_COHERENT
-	select HAVE_GENERIC_HARDIRQS
 	select HAVE_HW_BREAKPOINT if PERF_EVENTS
 	select HAVE_MEMBLOCK
 	select HAVE_PERF_EVENTS
@@ -96,6 +95,9 @@ config SWIOTLB
 config IOMMU_HELPER
 	def_bool SWIOTLB
 
+config KERNEL_MODE_NEON
+	def_bool y
+
 source "init/Kconfig"
 
 source "kernel/Kconfig.freezer"
diff --git a/arch/arm64/Kconfig.debug b/arch/arm64/Kconfig.debug
index 1a6bfe954d49..835c559786bd 100644
--- a/arch/arm64/Kconfig.debug
+++ b/arch/arm64/Kconfig.debug
@@ -6,13 +6,6 @@ config FRAME_POINTER
 	bool
 	default y
 
-config DEBUG_STACK_USAGE
-	bool "Enable stack utilization instrumentation"
-	depends on DEBUG_KERNEL
-	help
-	  Enables the display of the minimum amount of free stack which each
-	  task has ever had available in the sysrq-T output.
-
 config EARLY_PRINTK
 	bool "Early printk support"
 	default y
diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig
index 5b3e83217b03..31c81e9b792e 100644
--- a/arch/arm64/configs/defconfig
+++ b/arch/arm64/configs/defconfig
@@ -42,7 +42,7 @@ CONFIG_IP_PNP_BOOTP=y
 # CONFIG_WIRELESS is not set
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_DEVTMPFS=y
-# CONFIG_BLK_DEV is not set
+CONFIG_BLK_DEV=y
 CONFIG_SCSI=y
 # CONFIG_SCSI_PROC_FS is not set
 CONFIG_BLK_DEV_SD=y
@@ -72,6 +72,7 @@ CONFIG_LOGO=y
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_EXT2_FS=y
 CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
 # CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 # CONFIG_EXT3_FS_XATTR is not set
 CONFIG_FUSE_FS=y
@@ -90,3 +91,5 @@ CONFIG_DEBUG_KERNEL=y
 CONFIG_DEBUG_INFO=y
 # CONFIG_FTRACE is not set
 CONFIG_ATOMIC64_SELFTEST=y
+CONFIG_VIRTIO_MMIO=y
+CONFIG_VIRTIO_BLK=y
diff --git a/arch/arm64/include/asm/arch_timer.h b/arch/arm64/include/asm/arch_timer.h
index 98abd476992d..c9f1d2816c2b 100644
--- a/arch/arm64/include/asm/arch_timer.h
+++ b/arch/arm64/include/asm/arch_timer.h
@@ -26,7 +26,13 @@
 
 #include <clocksource/arm_arch_timer.h>
 
-static inline void arch_timer_reg_write(int access, int reg, u32 val)
+/*
+ * These register accessors are marked inline so the compiler can
+ * nicely work out which register we want, and chuck away the rest of
+ * the code.
+ */
+static __always_inline
+void arch_timer_reg_write_cp15(int access, enum arch_timer_reg reg, u32 val)
 {
 	if (access == ARCH_TIMER_PHYS_ACCESS) {
 		switch (reg) {
@@ -36,8 +42,6 @@ static inline void arch_timer_reg_write(int access, int reg, u32 val)
 		case ARCH_TIMER_REG_TVAL:
 			asm volatile("msr cntp_tval_el0, %0" : : "r" (val));
 			break;
-		default:
-			BUILD_BUG();
 		}
 	} else if (access == ARCH_TIMER_VIRT_ACCESS) {
 		switch (reg) {
@@ -47,17 +51,14 @@ static inline void arch_timer_reg_write(int access, int reg, u32 val)
 		case ARCH_TIMER_REG_TVAL:
 			asm volatile("msr cntv_tval_el0, %0" : : "r" (val));
 			break;
-		default:
-			BUILD_BUG();
 		}
-	} else {
-		BUILD_BUG();
 	}
 
 	isb();
 }
 
-static inline u32 arch_timer_reg_read(int access, int reg)
+static __always_inline
+u32 arch_timer_reg_read_cp15(int access, enum arch_timer_reg reg)
 {
 	u32 val;
 
@@ -69,8 +70,6 @@ static inline u32 arch_timer_reg_read(int access, int reg)
 		case ARCH_TIMER_REG_TVAL:
 			asm volatile("mrs %0, cntp_tval_el0" : "=r" (val));
 			break;
-		default:
-			BUILD_BUG();
 		}
 	} else if (access == ARCH_TIMER_VIRT_ACCESS) {
 		switch (reg) {
@@ -80,11 +79,7 @@ static inline u32 arch_timer_reg_read(int access, int reg)
 		case ARCH_TIMER_REG_TVAL:
 			asm volatile("mrs %0, cntv_tval_el0" : "=r" (val));
 			break;
-		default:
-			BUILD_BUG();
 		}
-	} else {
-		BUILD_BUG();
 	}
 
 	return val;
diff --git a/arch/arm64/include/asm/elf.h b/arch/arm64/include/asm/elf.h
index fe32c0e4ac01..e7fa87f9201b 100644
--- a/arch/arm64/include/asm/elf.h
+++ b/arch/arm64/include/asm/elf.h
@@ -33,8 +33,6 @@ typedef unsigned long elf_greg_t;
 typedef elf_greg_t elf_gregset_t[ELF_NGREG];
 typedef struct user_fpsimd_state elf_fpregset_t;
 
-#define EM_AARCH64		183
-
 /*
  * AArch64 static relocation types.
  */
@@ -151,7 +149,6 @@ extern unsigned long arch_randomize_brk(struct mm_struct *mm);
 #define arch_randomize_brk arch_randomize_brk
 
 #ifdef CONFIG_COMPAT
-#define EM_ARM				40
 #define COMPAT_ELF_PLATFORM		("v8l")
 
 #define COMPAT_ELF_ET_DYN_BASE		(randomize_et_dyn(2 * TASK_SIZE_32 / 3))
diff --git a/arch/arm64/include/asm/hwcap.h b/arch/arm64/include/asm/hwcap.h
index 6d4482fa35bc..e2950b098e76 100644
--- a/arch/arm64/include/asm/hwcap.h
+++ b/arch/arm64/include/asm/hwcap.h
@@ -43,6 +43,6 @@
 				 COMPAT_HWCAP_VFPv3|COMPAT_HWCAP_VFPv4|\
 				 COMPAT_HWCAP_NEON|COMPAT_HWCAP_IDIV)
 
-extern unsigned int elf_hwcap;
+extern unsigned long elf_hwcap;
 #endif
 #endif
diff --git a/arch/arm64/include/asm/neon.h b/arch/arm64/include/asm/neon.h
new file mode 100644
index 000000000000..b0cc58a97780
--- /dev/null
+++ b/arch/arm64/include/asm/neon.h
@@ -0,0 +1,14 @@
+/*
+ * linux/arch/arm64/include/asm/neon.h
+ *
+ * Copyright (C) 2013 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#define cpu_has_neon()		(1)
+
+void kernel_neon_begin(void);
+void kernel_neon_end(void);
diff --git a/arch/arm64/include/asm/pgtable-2level-types.h b/arch/arm64/include/asm/pgtable-2level-types.h
index 3c3ca7d361e4..5f101e63dfc1 100644
--- a/arch/arm64/include/asm/pgtable-2level-types.h
+++ b/arch/arm64/include/asm/pgtable-2level-types.h
@@ -16,6 +16,8 @@
 #ifndef __ASM_PGTABLE_2LEVEL_TYPES_H
 #define __ASM_PGTABLE_2LEVEL_TYPES_H
 
+#include <asm/types.h>
+
 typedef u64 pteval_t;
 typedef u64 pgdval_t;
 typedef pgdval_t pmdval_t;
diff --git a/arch/arm64/include/asm/pgtable-3level-types.h b/arch/arm64/include/asm/pgtable-3level-types.h
index 4489615f14a9..4e94424938a4 100644
--- a/arch/arm64/include/asm/pgtable-3level-types.h
+++ b/arch/arm64/include/asm/pgtable-3level-types.h
@@ -16,6 +16,8 @@
 #ifndef __ASM_PGTABLE_3LEVEL_TYPES_H
 #define __ASM_PGTABLE_3LEVEL_TYPES_H
 
+#include <asm/types.h>
+
 typedef u64 pteval_t;
 typedef u64 pmdval_t;
 typedef u64 pgdval_t;
diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h
index e182a356c979..d57e66845c86 100644
--- a/arch/arm64/include/asm/pgtable-hwdef.h
+++ b/arch/arm64/include/asm/pgtable-hwdef.h
@@ -122,5 +122,6 @@
 #define TCR_TG1_64K		(UL(1) << 30)
 #define TCR_IPS_40BIT		(UL(2) << 32)
 #define TCR_ASID16		(UL(1) << 36)
+#define TCR_TBI0		(UL(1) << 37)
 
 #endif
diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h
index edb3d5c73a32..7ecc2b23882e 100644
--- a/arch/arm64/include/asm/uaccess.h
+++ b/arch/arm64/include/asm/uaccess.h
@@ -166,9 +166,10 @@ do {									\
 
 #define get_user(x, ptr)						\
 ({									\
+	__typeof__(*(ptr)) __user *__p = (ptr);				\
 	might_fault();							\
-	access_ok(VERIFY_READ, (ptr), sizeof(*(ptr))) ?			\
-		__get_user((x), (ptr)) :				\
+	access_ok(VERIFY_READ, __p, sizeof(*__p)) ?			\
+		__get_user((x), __p) :					\
 		((x) = 0, -EFAULT);					\
 })
 
@@ -227,9 +228,10 @@ do {									\
 
 #define put_user(x, ptr)						\
 ({									\
+	__typeof__(*(ptr)) __user *__p = (ptr);				\
 	might_fault();							\
-	access_ok(VERIFY_WRITE, (ptr), sizeof(*(ptr))) ?		\
-		__put_user((x), (ptr)) :				\
+	access_ok(VERIFY_WRITE, __p, sizeof(*__p)) ?			\
+		__put_user((x), __p) :					\
 		-EFAULT;						\
 })
 
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 6ad781b21c08..3881fd115ebb 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -423,6 +423,7 @@ el0_da:
 	 * Data abort handling
 	 */
 	mrs	x0, far_el1
+	bic	x0, x0, #(0xff << 56)
 	disable_step x1
 	isb
 	enable_dbg
@@ -476,6 +477,8 @@ el0_undef:
 	 * Undefined instruction
 	 */
 	mov	x0, sp
+	// enable interrupts before calling the main handler
+	enable_irq
 	b	do_undefinstr
 el0_dbg:
 	/*
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index e8b8357aedb4..bb785d23dbde 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -21,6 +21,7 @@
 #include <linux/init.h>
 #include <linux/sched.h>
 #include <linux/signal.h>
+#include <linux/hardirq.h>
 
 #include <asm/fpsimd.h>
 #include <asm/cputype.h>
@@ -79,10 +80,39 @@ void fpsimd_thread_switch(struct task_struct *next)
 
 void fpsimd_flush_thread(void)
 {
+	preempt_disable();
 	memset(&current->thread.fpsimd_state, 0, sizeof(struct fpsimd_state));
 	fpsimd_load_state(&current->thread.fpsimd_state);
+	preempt_enable();
 }
 
+#ifdef CONFIG_KERNEL_MODE_NEON
+
+/*
+ * Kernel-side NEON support functions
+ */
+void kernel_neon_begin(void)
+{
+	/* Avoid using the NEON in interrupt context */
+	BUG_ON(in_interrupt());
+	preempt_disable();
+
+	if (current->mm)
+		fpsimd_save_state(&current->thread.fpsimd_state);
+}
+EXPORT_SYMBOL(kernel_neon_begin);
+
+void kernel_neon_end(void)
+{
+	if (current->mm)
+		fpsimd_load_state(&current->thread.fpsimd_state);
+
+	preempt_enable();
+}
+EXPORT_SYMBOL(kernel_neon_end);
+
+#endif /* CONFIG_KERNEL_MODE_NEON */
+
 /*
  * FP/SIMD support code initialisation.
  */
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 53dcae49e729..7090c126797c 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -112,6 +112,14 @@
 	.quad	TEXT_OFFSET			// Image load offset from start of RAM
 	.quad	0				// reserved
 	.quad	0				// reserved
+	.quad	0				// reserved
+	.quad	0				// reserved
+	.quad	0				// reserved
+	.byte	0x41				// Magic number, "ARM\x64"
+	.byte	0x52
+	.byte	0x4d
+	.byte	0x64
+	.word	0				// reserved
 
 ENTRY(stext)
 	mov	x21, x0				// x21=FDT
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index 12e6ccb88691..cea1594ff933 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -325,7 +325,10 @@ validate_event(struct pmu_hw_events *hw_events,
 	if (is_software_event(event))
 		return 1;
 
-	if (event->pmu != leader_pmu || event->state <= PERF_EVENT_STATE_OFF)
+	if (event->pmu != leader_pmu || event->state < PERF_EVENT_STATE_OFF)
+		return 1;
+
+	if (event->state == PERF_EVENT_STATE_OFF && !event->attr.enable_on_exec)
 		return 1;
 
 	return armpmu->get_event_idx(hw_events, &fake_event) >= 0;
@@ -781,7 +784,7 @@ static const unsigned armv8_pmuv3_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
 /*
  * PMXEVTYPER: Event selection reg
  */
-#define	ARMV8_EVTYPE_MASK	0xc00000ff	/* Mask for writable bits */
+#define	ARMV8_EVTYPE_MASK	0xc80000ff	/* Mask for writable bits */
 #define	ARMV8_EVTYPE_EVENT	0xff		/* Mask for EVENT bits */
 
 /*
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 57fb55c44c90..7ae8a1f00c3c 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -143,15 +143,26 @@ void machine_restart(char *cmd)
 
 void __show_regs(struct pt_regs *regs)
 {
-	int i;
+	int i, top_reg;
+	u64 lr, sp;
+
+	if (compat_user_mode(regs)) {
+		lr = regs->compat_lr;
+		sp = regs->compat_sp;
+		top_reg = 12;
+	} else {
+		lr = regs->regs[30];
+		sp = regs->sp;
+		top_reg = 29;
+	}
 
 	show_regs_print_info(KERN_DEFAULT);
 	print_symbol("PC is at %s\n", instruction_pointer(regs));
-	print_symbol("LR is at %s\n", regs->regs[30]);
+	print_symbol("LR is at %s\n", lr);
 	printk("pc : [<%016llx>] lr : [<%016llx>] pstate: %08llx\n",
-	       regs->pc, regs->regs[30], regs->pstate);
-	printk("sp : %016llx\n", regs->sp);
-	for (i = 29; i >= 0; i--) {
+	       regs->pc, lr, regs->pstate);
+	printk("sp : %016llx\n", sp);
+	for (i = top_reg; i >= 0; i--) {
 		printk("x%-2d: %016llx ", i, regs->regs[i]);
 		if (i % 2 == 0)
 			printk("\n");
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index add6ea616843..055cfb80e05c 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -57,7 +57,7 @@
 unsigned int processor_id;
 EXPORT_SYMBOL(processor_id);
 
-unsigned int elf_hwcap __read_mostly;
+unsigned long elf_hwcap __read_mostly;
 EXPORT_SYMBOL_GPL(elf_hwcap);
 
 static const char *cpu_name;
@@ -190,11 +190,6 @@ void __init early_init_dt_add_memory_arch(u64 base, u64 size)
 	memblock_add(base, size);
 }
 
-void * __init early_init_dt_alloc_memory_arch(u64 size, u64 align)
-{
-	return __va(memblock_alloc(size, align));
-}
-
 /*
  * Limit the memory size that was specified via FDT.
  */
@@ -328,9 +323,6 @@ static int c_show(struct seq_file *m, void *v)
 #ifdef CONFIG_SMP
 		seq_printf(m, "processor\t: %d\n", i);
 #endif
-		seq_printf(m, "BogoMIPS\t: %lu.%02lu\n\n",
-			   loops_per_jiffy / (500000UL/HZ),
-			   loops_per_jiffy / (5000UL/HZ) % 100);
 	}
 
 	/* dump out the processor features */
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index fee5cce83450..78db90dcc910 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -223,11 +223,7 @@ asmlinkage void secondary_start_kernel(void)
 
 void __init smp_cpus_done(unsigned int max_cpus)
 {
-	unsigned long bogosum = loops_per_jiffy * num_online_cpus();
-
-	pr_info("SMP: Total of %d processors activated (%lu.%02lu BogoMIPS).\n",
-		num_online_cpus(), bogosum / (500000/HZ),
-		(bogosum / (5000/HZ)) % 100);
+	pr_info("SMP: Total of %d processors activated.\n", num_online_cpus());
 }
 
 void __init smp_prepare_boot_cpu(void)
diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S
index f5e55747242f..f8ab9d8e2ea3 100644
--- a/arch/arm64/kernel/vmlinux.lds.S
+++ b/arch/arm64/kernel/vmlinux.lds.S
@@ -71,6 +71,7 @@ SECTIONS
 
 	RO_DATA(PAGE_SIZE)
 	EXCEPTION_TABLE(8)
+	NOTES
 	_etext = .;			/* End of text and rodata section */
 
 	. = ALIGN(PAGE_SIZE);
@@ -122,8 +123,6 @@ SECTIONS
 	}
 	_edata_loc = __data_loc + SIZEOF(.data);
 
-	NOTES
-
 	BSS_SECTION(0, 0, 0)
 	_end = .;
 
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 6c8ba25bf6bb..c23751b06120 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -130,7 +130,7 @@ static void __do_user_fault(struct task_struct *tsk, unsigned long addr,
 	force_sig_info(sig, &si, tsk);
 }
 
-void do_bad_area(unsigned long addr, unsigned int esr, struct pt_regs *regs)
+static void do_bad_area(unsigned long addr, unsigned int esr, struct pt_regs *regs)
 {
 	struct task_struct *tsk = current;
 	struct mm_struct *mm = tsk->active_mm;
@@ -199,13 +199,6 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
 	unsigned long vm_flags = VM_READ | VM_WRITE | VM_EXEC;
 	unsigned int mm_flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
 
-	if (esr & ESR_LNX_EXEC) {
-		vm_flags = VM_EXEC;
-	} else if ((esr & ESR_WRITE) && !(esr & ESR_CM)) {
-		vm_flags = VM_WRITE;
-		mm_flags |= FAULT_FLAG_WRITE;
-	}
-
 	tsk = current;
 	mm  = tsk->mm;
 
@@ -220,6 +213,16 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
 	if (in_atomic() || !mm)
 		goto no_context;
 
+	if (user_mode(regs))
+		mm_flags |= FAULT_FLAG_USER;
+
+	if (esr & ESR_LNX_EXEC) {
+		vm_flags = VM_EXEC;
+	} else if ((esr & ESR_WRITE) && !(esr & ESR_CM)) {
+		vm_flags = VM_WRITE;
+		mm_flags |= FAULT_FLAG_WRITE;
+	}
+
 	/*
 	 * As per x86, we may deadlock here. However, since the kernel only
 	 * validly references user space from well defined areas of the code,
@@ -288,6 +291,13 @@ retry:
 			      VM_FAULT_BADACCESS))))
 		return 0;
 
+	/*
+	 * If we are in kernel mode at this point, we have no context to
+	 * handle this fault with.
+	 */
+	if (!user_mode(regs))
+		goto no_context;
+
 	if (fault & VM_FAULT_OOM) {
 		/*
 		 * We ran out of memory, call the OOM killer, and return to
@@ -298,13 +308,6 @@ retry:
 		return 0;
 	}
 
-	/*
-	 * If we are in kernel mode at this point, we have no context to
-	 * handle this fault with.
-	 */
-	if (!user_mode(regs))
-		goto no_context;
-
 	if (fault & VM_FAULT_SIGBUS) {
 		/*
 		 * We had some memory, but were unable to successfully fix up
diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index 2fc8258bab2d..5e9aec358306 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -54,6 +54,11 @@ int pud_huge(pud_t pud)
 	return !(pud_val(pud) & PUD_TABLE_BIT);
 }
 
+int pmd_huge_support(void)
+{
+	return 1;
+}
+
 static __init int setup_hugepagesz(char *opt)
 {
 	unsigned long ps = memparse(opt, &opt);
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 67e8d7ce3fe7..de2de5db628d 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -44,8 +44,7 @@ static unsigned long phys_initrd_size __initdata = 0;
 
 phys_addr_t memstart_addr __read_mostly = 0;
 
-void __init early_init_dt_setup_initrd_arch(unsigned long start,
-					    unsigned long end)
+void __init early_init_dt_setup_initrd_arch(u64 start, u64 end)
 {
 	phys_initrd_start = start;
 	phys_initrd_size = end - start;
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index a8d1059b91b2..f557ebbe7013 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -296,6 +296,7 @@ void __iomem * __init early_io_map(phys_addr_t phys, unsigned long virt)
 static void __init map_mem(void)
 {
 	struct memblock_region *reg;
+	phys_addr_t limit;
 
 	/*
 	 * Temporarily limit the memblock range. We need to do this as
@@ -303,9 +304,11 @@ static void __init map_mem(void)
 	 * memory addressable from the initial direct kernel mapping.
 	 *
 	 * The initial direct kernel mapping, located at swapper_pg_dir,
-	 * gives us PGDIR_SIZE memory starting from PHYS_OFFSET (aligned).
+	 * gives us PGDIR_SIZE memory starting from PHYS_OFFSET (which must be
+	 * aligned to 2MB as per Documentation/arm64/booting.txt).
 	 */
-	memblock_set_current_limit((PHYS_OFFSET & PGDIR_MASK) + PGDIR_SIZE);
+	limit = PHYS_OFFSET + PGDIR_SIZE;
+	memblock_set_current_limit(limit);
 
 	/* map all the memory banks */
 	for_each_memblock(memory, reg) {
@@ -315,6 +318,22 @@ static void __init map_mem(void)
 		if (start >= end)
 			break;
 
+#ifndef CONFIG_ARM64_64K_PAGES
+		/*
+		 * For the first memory bank align the start address and
+		 * current memblock limit to prevent create_mapping() from
+		 * allocating pte page tables from unmapped memory.
+		 * When 64K pages are enabled, the pte page table for the
+		 * first PGDIR_SIZE is already present in swapper_pg_dir.
+		 */
+		if (start < limit)
+			start = ALIGN(start, PMD_SIZE);
+		if (end < limit) {
+			limit = end & PMD_MASK;
+			memblock_set_current_limit(limit);
+		}
+#endif
+
 		create_mapping(start, __phys_to_virt(start), end - start);
 	}
 
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index a82ae8868077..b1b31bbc967b 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -95,10 +95,6 @@ ENTRY(cpu_do_switch_mm)
 	ret
 ENDPROC(cpu_do_switch_mm)
 
-cpu_name:
-	.ascii	"AArch64 Processor"
-	.align
-
 	.section ".text.init", #alloc, #execinstr
 
 /*
@@ -151,7 +147,7 @@ ENTRY(__cpu_setup)
 	 * both user and kernel.
 	 */
 	ldr	x10, =TCR_TxSZ(VA_BITS) | TCR_FLAGS | TCR_IPS_40BIT | \
-		      TCR_ASID16 | (1 << 31)
+		      TCR_ASID16 | TCR_TBI0 | (1 << 31)
 #ifdef CONFIG_ARM64_64K_PAGES
 	orr	x10, x10, TCR_TG0_64K
 	orr	x10, x10, TCR_TG1_64K
diff --git a/arch/arm64/mm/tlb.S b/arch/arm64/mm/tlb.S
index 8ae80a18e8ec..19da91e0cd27 100644
--- a/arch/arm64/mm/tlb.S
+++ b/arch/arm64/mm/tlb.S
@@ -35,7 +35,7 @@
  */
 ENTRY(__cpu_flush_user_tlb_range)
 	vma_vm_mm x3, x2			// get vma->vm_mm
-	mmid	x3, x3				// get vm_mm->context.id
+	mmid	w3, x3				// get vm_mm->context.id
 	dsb	sy
 	lsr	x0, x0, #12			// align address
 	lsr	x1, x1, #12
diff --git a/arch/avr32/Kconfig b/arch/avr32/Kconfig
index 549903cfc2cb..b6878eb64884 100644
--- a/arch/avr32/Kconfig
+++ b/arch/avr32/Kconfig
@@ -6,7 +6,6 @@ config AVR32
 	select HAVE_CLK
 	select HAVE_OPROFILE
 	select HAVE_KPROBES
-	select HAVE_GENERIC_HARDIRQS
 	select VIRT_TO_BUS
 	select GENERIC_IRQ_PROBE
 	select GENERIC_ATOMIC64
diff --git a/arch/avr32/include/asm/Kbuild b/arch/avr32/include/asm/Kbuild
index d22af851f3f6..fd7980743890 100644
--- a/arch/avr32/include/asm/Kbuild
+++ b/arch/avr32/include/asm/Kbuild
@@ -1,5 +1,19 @@
 
 generic-y	+= clkdev.h
+generic-y       += cputime.h
+generic-y       += delay.h
+generic-y       += device.h
+generic-y       += div64.h
+generic-y       += emergency-restart.h
 generic-y	+= exec.h
-generic-y	+= trace_clock.h
+generic-y       += futex.h
+generic-y       += irq_regs.h
 generic-y	+= param.h
+generic-y       += local.h
+generic-y       += local64.h
+generic-y       += percpu.h
+generic-y       += scatterlist.h
+generic-y       += sections.h
+generic-y       += topology.h
+generic-y	+= trace_clock.h
+generic-y       += xor.h
diff --git a/arch/avr32/include/asm/cputime.h b/arch/avr32/include/asm/cputime.h
deleted file mode 100644
index e87e0f81cbeb..000000000000
--- a/arch/avr32/include/asm/cputime.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __ASM_AVR32_CPUTIME_H
-#define __ASM_AVR32_CPUTIME_H
-
-#include <asm-generic/cputime.h>
-
-#endif /* __ASM_AVR32_CPUTIME_H */
diff --git a/arch/avr32/include/asm/delay.h b/arch/avr32/include/asm/delay.h
deleted file mode 100644
index 9670e127b7b2..000000000000
--- a/arch/avr32/include/asm/delay.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/delay.h>
diff --git a/arch/avr32/include/asm/device.h b/arch/avr32/include/asm/device.h
deleted file mode 100644
index d8f9872b0e2d..000000000000
--- a/arch/avr32/include/asm/device.h
+++ /dev/null
@@ -1,7 +0,0 @@
-/*
- * Arch specific extensions to struct device
- *
- * This file is released under the GPLv2
- */
-#include <asm-generic/device.h>
-
diff --git a/arch/avr32/include/asm/div64.h b/arch/avr32/include/asm/div64.h
deleted file mode 100644
index d7ddd4fdeca6..000000000000
--- a/arch/avr32/include/asm/div64.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __ASM_AVR32_DIV64_H
-#define __ASM_AVR32_DIV64_H
-
-#include <asm-generic/div64.h>
-
-#endif /* __ASM_AVR32_DIV64_H */
diff --git a/arch/avr32/include/asm/emergency-restart.h b/arch/avr32/include/asm/emergency-restart.h
deleted file mode 100644
index 3e7e014776ba..000000000000
--- a/arch/avr32/include/asm/emergency-restart.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __ASM_AVR32_EMERGENCY_RESTART_H
-#define __ASM_AVR32_EMERGENCY_RESTART_H
-
-#include <asm-generic/emergency-restart.h>
-
-#endif /* __ASM_AVR32_EMERGENCY_RESTART_H */
diff --git a/arch/avr32/include/asm/futex.h b/arch/avr32/include/asm/futex.h
deleted file mode 100644
index 10419f14a68a..000000000000
--- a/arch/avr32/include/asm/futex.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __ASM_AVR32_FUTEX_H
-#define __ASM_AVR32_FUTEX_H
-
-#include <asm-generic/futex.h>
-
-#endif /* __ASM_AVR32_FUTEX_H */
diff --git a/arch/avr32/include/asm/irq_regs.h b/arch/avr32/include/asm/irq_regs.h
deleted file mode 100644
index 3dd9c0b70270..000000000000
--- a/arch/avr32/include/asm/irq_regs.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/irq_regs.h>
diff --git a/arch/avr32/include/asm/local.h b/arch/avr32/include/asm/local.h
deleted file mode 100644
index 1c1619694da3..000000000000
--- a/arch/avr32/include/asm/local.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __ASM_AVR32_LOCAL_H
-#define __ASM_AVR32_LOCAL_H
-
-#include <asm-generic/local.h>
-
-#endif /* __ASM_AVR32_LOCAL_H */
diff --git a/arch/avr32/include/asm/local64.h b/arch/avr32/include/asm/local64.h
deleted file mode 100644
index 36c93b5cc239..000000000000
--- a/arch/avr32/include/asm/local64.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/local64.h>
diff --git a/arch/avr32/include/asm/percpu.h b/arch/avr32/include/asm/percpu.h
deleted file mode 100644
index 69227b4cd0d4..000000000000
--- a/arch/avr32/include/asm/percpu.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __ASM_AVR32_PERCPU_H
-#define __ASM_AVR32_PERCPU_H
-
-#include <asm-generic/percpu.h>
-
-#endif /* __ASM_AVR32_PERCPU_H */
diff --git a/arch/avr32/include/asm/scatterlist.h b/arch/avr32/include/asm/scatterlist.h
deleted file mode 100644
index a5902d9834e8..000000000000
--- a/arch/avr32/include/asm/scatterlist.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __ASM_AVR32_SCATTERLIST_H
-#define __ASM_AVR32_SCATTERLIST_H
-
-#include <asm-generic/scatterlist.h>
-
-#endif /* __ASM_AVR32_SCATTERLIST_H */
diff --git a/arch/avr32/include/asm/sections.h b/arch/avr32/include/asm/sections.h
deleted file mode 100644
index aa14252e4181..000000000000
--- a/arch/avr32/include/asm/sections.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __ASM_AVR32_SECTIONS_H
-#define __ASM_AVR32_SECTIONS_H
-
-#include <asm-generic/sections.h>
-
-#endif /* __ASM_AVR32_SECTIONS_H */
diff --git a/arch/avr32/include/asm/topology.h b/arch/avr32/include/asm/topology.h
deleted file mode 100644
index 5b766cbb4806..000000000000
--- a/arch/avr32/include/asm/topology.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __ASM_AVR32_TOPOLOGY_H
-#define __ASM_AVR32_TOPOLOGY_H
-
-#include <asm-generic/topology.h>
-
-#endif /* __ASM_AVR32_TOPOLOGY_H */
diff --git a/arch/avr32/include/asm/xor.h b/arch/avr32/include/asm/xor.h
deleted file mode 100644
index 99c87aa0af4f..000000000000
--- a/arch/avr32/include/asm/xor.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef _ASM_XOR_H
-#define _ASM_XOR_H
-
-#include <asm-generic/xor.h>
-
-#endif
diff --git a/arch/avr32/kernel/process.c b/arch/avr32/kernel/process.c
index c2731003edef..42a53e740a7e 100644
--- a/arch/avr32/kernel/process.c
+++ b/arch/avr32/kernel/process.c
@@ -289,7 +289,7 @@ int copy_thread(unsigned long clone_flags, unsigned long usp,
 		memset(childregs, 0, sizeof(struct pt_regs));
 		p->thread.cpu_context.r0 = arg;
 		p->thread.cpu_context.r1 = usp; /* fn */
-		p->thread.cpu_context.r2 = syscall_return;
+		p->thread.cpu_context.r2 = (unsigned long)syscall_return;
 		p->thread.cpu_context.pc = (unsigned long)ret_from_kernel_thread;
 		childregs->sr = MODE_SUPERVISOR;
 	} else {
diff --git a/arch/avr32/kernel/time.c b/arch/avr32/kernel/time.c
index 869a1c6ffeee..12f828ad5058 100644
--- a/arch/avr32/kernel/time.c
+++ b/arch/avr32/kernel/time.c
@@ -98,7 +98,14 @@ static void comparator_mode(enum clock_event_mode mode,
 	case CLOCK_EVT_MODE_SHUTDOWN:
 		sysreg_write(COMPARE, 0);
 		pr_debug("%s: stop\n", evdev->name);
-		cpu_idle_poll_ctrl(false);
+		if (evdev->mode == CLOCK_EVT_MODE_ONESHOT ||
+		    evdev->mode == CLOCK_EVT_MODE_RESUME) {
+			/*
+			 * Only disable idle poll if we have forced that
+			 * in a previous call.
+			 */
+			cpu_idle_poll_ctrl(false);
+		}
 		break;
 	default:
 		BUG();
diff --git a/arch/avr32/mach-at32ap/at32ap700x.c b/arch/avr32/mach-at32ap/at32ap700x.c
index 7f8759a8a92a..a68f3cf7c3c1 100644
--- a/arch/avr32/mach-at32ap/at32ap700x.c
+++ b/arch/avr32/mach-at32ap/at32ap700x.c
@@ -1983,6 +1983,9 @@ at32_add_device_nand(unsigned int id, struct atmel_nand_data *data)
 				ARRAY_SIZE(smc_cs3_resource)))
 		goto fail;
 
+	/* For at32ap7000, we use the reset workaround for nand driver */
+	data->need_reset_workaround = true;
+
 	if (platform_device_add_data(pdev, data,
 				sizeof(struct atmel_nand_data)))
 		goto fail;
diff --git a/arch/avr32/mm/fault.c b/arch/avr32/mm/fault.c
index b2f2d2d66849..0eca93327195 100644
--- a/arch/avr32/mm/fault.c
+++ b/arch/avr32/mm/fault.c
@@ -86,6 +86,8 @@ asmlinkage void do_page_fault(unsigned long ecr, struct pt_regs *regs)
 
 	local_irq_enable();
 
+	if (user_mode(regs))
+		flags |= FAULT_FLAG_USER;
 retry:
 	down_read(&mm->mmap_sem);
 
@@ -228,9 +230,9 @@ no_context:
 	 */
 out_of_memory:
 	up_read(&mm->mmap_sem);
-	pagefault_out_of_memory();
 	if (!user_mode(regs))
 		goto no_context;
+	pagefault_out_of_memory();
 	return;
 
 do_sigbus:
diff --git a/arch/avr32/oprofile/op_model_avr32.c b/arch/avr32/oprofile/op_model_avr32.c
index f74b7809e089..08308be2c02c 100644
--- a/arch/avr32/oprofile/op_model_avr32.c
+++ b/arch/avr32/oprofile/op_model_avr32.c
@@ -97,8 +97,7 @@ static irqreturn_t avr32_perf_counter_interrupt(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
-static int avr32_perf_counter_create_files(struct super_block *sb,
-		struct dentry *root)
+static int avr32_perf_counter_create_files(struct dentry *root)
 {
 	struct dentry *dir;
 	unsigned int i;
@@ -106,21 +105,21 @@ static int avr32_perf_counter_create_files(struct super_block *sb,
 
 	for (i = 0; i < NR_counter; i++) {
 		snprintf(filename, sizeof(filename), "%u", i);
-		dir = oprofilefs_mkdir(sb, root, filename);
+		dir = oprofilefs_mkdir(root, filename);
 
-		oprofilefs_create_ulong(sb, dir, "enabled",
+		oprofilefs_create_ulong(dir, "enabled",
 				&counter[i].enabled);
-		oprofilefs_create_ulong(sb, dir, "event",
+		oprofilefs_create_ulong(dir, "event",
 				&counter[i].event);
-		oprofilefs_create_ulong(sb, dir, "count",
+		oprofilefs_create_ulong(dir, "count",
 				&counter[i].count);
 
 		/* Dummy entries */
-		oprofilefs_create_ulong(sb, dir, "kernel",
+		oprofilefs_create_ulong(dir, "kernel",
 				&counter[i].kernel);
-		oprofilefs_create_ulong(sb, dir, "user",
+		oprofilefs_create_ulong(dir, "user",
 				&counter[i].user);
-		oprofilefs_create_ulong(sb, dir, "unit_mask",
+		oprofilefs_create_ulong(dir, "unit_mask",
 				&counter[i].unit_mask);
 	}
 
diff --git a/arch/blackfin/Kconfig b/arch/blackfin/Kconfig
index 3b6abc54b015..f78c9a2c7e28 100644
--- a/arch/blackfin/Kconfig
+++ b/arch/blackfin/Kconfig
@@ -32,7 +32,6 @@ config BLACKFIN
 	select HAVE_UNDERSCORE_SYMBOL_PREFIX
 	select VIRT_TO_BUS
 	select ARCH_WANT_IPC_PARSE_VERSION
-	select HAVE_GENERIC_HARDIRQS
 	select GENERIC_ATOMIC64
 	select GENERIC_IRQ_PROBE
 	select USE_GENERIC_SMP_HELPERS if SMP
diff --git a/arch/blackfin/boot/.gitignore b/arch/blackfin/boot/.gitignore
index 229e50808677..1287a5487e7d 100644
--- a/arch/blackfin/boot/.gitignore
+++ b/arch/blackfin/boot/.gitignore
@@ -1,2 +1,3 @@
 vmImage*
 vmlinux*
+uImage*
diff --git a/arch/blackfin/include/asm/scb.h b/arch/blackfin/include/asm/scb.h
new file mode 100644
index 000000000000..a294cc0d1a4a
--- /dev/null
+++ b/arch/blackfin/include/asm/scb.h
@@ -0,0 +1,21 @@
+/*
+ * arch/blackfin/mach-common/scb-init.c - reprogram system cross bar priority
+ *
+ * Copyright 2012 Analog Devices Inc.
+ *
+ * Licensed under the GPL-2 or later.
+ */
+
+#define SCB_SLOT_OFFSET	24
+#define SCB_MI_MAX_SLOT 32
+
+struct scb_mi_prio {
+	unsigned long scb_mi_arbr;
+	unsigned long scb_mi_arbw;
+	unsigned char scb_mi_slots;
+	unsigned char scb_mi_prio[SCB_MI_MAX_SLOT];
+};
+
+extern struct scb_mi_prio scb_data[];
+
+extern void init_scb(void);
diff --git a/arch/blackfin/kernel/setup.c b/arch/blackfin/kernel/setup.c
index 19ad0637e8ff..396193042127 100644
--- a/arch/blackfin/kernel/setup.c
+++ b/arch/blackfin/kernel/setup.c
@@ -35,6 +35,9 @@
 #ifdef CONFIG_BF60x
 #include <mach/pm.h>
 #endif
+#ifdef CONFIG_SCB_PRIORITY
+#include <asm/scb.h>
+#endif
 
 u16 _bfin_swrst;
 EXPORT_SYMBOL(_bfin_swrst);
@@ -1101,6 +1104,9 @@ void __init setup_arch(char **cmdline_p)
 #endif
 	init_exception_vectors();
 	bfin_cache_init();	/* Initialize caches for the boot CPU */
+#ifdef CONFIG_SCB_PRIORITY
+	init_scb();
+#endif
 }
 
 static int __init topology_init(void)
diff --git a/arch/blackfin/mach-bf609/Kconfig b/arch/blackfin/mach-bf609/Kconfig
index 95a4f1b676ce..2bcbf94b1edf 100644
--- a/arch/blackfin/mach-bf609/Kconfig
+++ b/arch/blackfin/mach-bf609/Kconfig
@@ -59,6 +59,1661 @@ config SEC_IRQ_PRIORITY_LEVELS
 	  Divide the total number of interrupt priority levels into sub-levels.
 	  There is 2 ^ (SEC_IRQ_PRIORITY_LEVELS + 1) different levels.
 
+
+comment "System Cross Bar Priority Assignment"
+
+config SCB_PRIORITY
+	bool "Init System Cross Bar Priority"
+	default n
+
+menuconfig	SCB0_MI0
+	bool "SCB0 Master Interface 0 (DDR)"
+	default n
+	depends on SCB_PRIORITY
+	help
+	The slave interface id of each slot should be set according following table.
+	Core 0	-- 0
+	Core 1	-- 2
+	SCB1	-- 9
+	SCB2	-- 10
+	SCB3	-- 11
+	SCB4	-- 12
+	SCB5	-- 5
+	SCB6	-- 6
+	SCB7	-- 8
+	SCB8	-- 7
+	SCB9	-- 4
+	USB	-- 13
+
+if SCB0_MI0
+
+config SCB0_MI0_SLOT0
+	int "Slot 0 slave interface id"
+	default 0
+	range 0 13
+
+config SCB0_MI0_SLOT1
+	int "Slot 1 slave interface id"
+	default 2
+	range 0 13
+
+config SCB0_MI0_SLOT2
+	int "Slot 2 slave interface id"
+	default 4
+	range 0 13
+
+config SCB0_MI0_SLOT3
+	int "Slot 3 slave interface id"
+	default 5
+	range 0 13
+
+config SCB0_MI0_SLOT4
+	int "Slot 4 slave interface id"
+	default 6
+	range 0 13
+
+config SCB0_MI0_SLOT5
+	int "Slot 5 slave interface id"
+	default 7
+	range 0 13
+
+config SCB0_MI0_SLOT6
+	int "Slot 6 slave interface id"
+	default 8
+	range 0 13
+
+config SCB0_MI0_SLOT7
+	int "Slot 7 slave interface id"
+	default 9
+	range 0 13
+
+config SCB0_MI0_SLOT8
+	int "Slot 8 slave interface id"
+	default 10
+	range 0 13
+
+config SCB0_MI0_SLOT9
+	int "Slot 9 slave interface id"
+	default 11
+	range 0 13
+
+config SCB0_MI0_SLOT10
+	int "Slot 10 slave interface id"
+	default 13
+	range 0 13
+
+config SCB0_MI0_SLOT11
+	int "Slot 11 slave interface id"
+	default 12
+	range 0 13
+
+config SCB0_MI0_SLOT12
+	int "Slot 12 slave interface id"
+	default 0
+	range 0 13
+
+config SCB0_MI0_SLOT13
+	int "Slot 13 slave interface id"
+	default 2
+	range 0 13
+
+config SCB0_MI0_SLOT14
+	int "Slot 14 slave interface id"
+	default 4
+	range 0 13
+
+config SCB0_MI0_SLOT15
+	int "Slot 15 slave interface id"
+	default 5
+	range 0 13
+
+config SCB0_MI0_SLOT16
+	int "Slot 16 slave interface id"
+	default 6
+	range 0 13
+
+config SCB0_MI0_SLOT17
+	int "Slot 17 slave interface id"
+	default 7
+	range 0 13
+
+config SCB0_MI0_SLOT18
+	int "Slot 18 slave interface id"
+	default 8
+	range 0 13
+
+config SCB0_MI0_SLOT19
+	int "Slot 19 slave interface id"
+	default 9
+	range 0 13
+
+config SCB0_MI0_SLOT20
+	int "Slot 20 slave interface id"
+	default 10
+	range 0 13
+
+config SCB0_MI0_SLOT21
+	int "Slot 21 slave interface id"
+	default 11
+	range 0 13
+
+config SCB0_MI0_SLOT22
+	int "Slot 22 slave interface id"
+	default 13
+	range 0 13
+
+config SCB0_MI0_SLOT23
+	int "Slot 23 slave interface id"
+	default 12
+	range 0 13
+
+config SCB0_MI0_SLOT24
+	int "Slot 24 slave interface id"
+	default 0
+	range 0 13
+
+config SCB0_MI0_SLOT25
+	int "Slot 25 slave interface id"
+	default 2
+	range 0 13
+
+config SCB0_MI0_SLOT26
+	int "Slot 26 slave interface id"
+	default 4
+	range 0 13
+
+config SCB0_MI0_SLOT27
+	int "Slot 27 slave interface id"
+	default 5
+	range 0 13
+
+config SCB0_MI0_SLOT28
+	int "Slot 28 slave interface id"
+	default 6
+	range 0 13
+
+config SCB0_MI0_SLOT29
+	int "Slot 29 slave interface id"
+	default 7
+	range 0 13
+
+config SCB0_MI0_SLOT30
+	int "Slot 30 slave interface id"
+	default 8
+	range 0 13
+
+config SCB0_MI0_SLOT31
+	int "Slot 31 slave interface id"
+	default 13
+	range 0 13
+
+endif # SCB0_MI0
+
+menuconfig	SCB0_MI1
+	bool "SCB0 Master Interface 1 (SMC)"
+	default n
+	depends on SCB_PRIORITY
+	help
+	The slave interface id of each slot should be set according following table.
+	Core 0	-- 0
+	Core 1	-- 2
+	SCB1	-- 9
+	SCB2	-- 10
+	SCB3	-- 11
+	SCB4	-- 12
+	SCB5	-- 5
+	SCB6	-- 6
+	SCB7	-- 8
+	SCB8	-- 7
+	SCB9	-- 4
+	USB	-- 13
+
+if SCB0_MI1
+
+config SCB0_MI1_SLOT0
+	int "Slot 0 slave interface id"
+	default 0
+	range 0 13
+
+config SCB0_MI1_SLOT1
+	int "Slot 1 slave interface id"
+	default 2
+	range 0 13
+
+config SCB0_MI1_SLOT2
+	int "Slot 2 slave interface id"
+	default 4
+	range 0 13
+
+config SCB0_MI1_SLOT3
+	int "Slot 3 slave interface id"
+	default 5
+	range 0 13
+
+config SCB0_MI1_SLOT4
+	int "Slot 4 slave interface id"
+	default 6
+	range 0 13
+
+config SCB0_MI1_SLOT5
+	int "Slot 5 slave interface id"
+	default 7
+	range 0 13
+
+config SCB0_MI1_SLOT6
+	int "Slot 6 slave interface id"
+	default 8
+	range 0 13
+
+config SCB0_MI1_SLOT7
+	int "Slot 7 slave interface id"
+	default 9
+	range 0 13
+
+config SCB0_MI1_SLOT8
+	int "Slot 8 slave interface id"
+	default 10
+	range 0 13
+
+config SCB0_MI1_SLOT9
+	int "Slot 9 slave interface id"
+	default 11
+	range 0 13
+
+config SCB0_MI1_SLOT10
+	int "Slot 10 slave interface id"
+	default 13
+	range 0 13
+
+config SCB0_MI1_SLOT11
+	int "Slot 11 slave interface id"
+	default 12
+	range 0 13
+
+config SCB0_MI1_SLOT12
+	int "Slot 12 slave interface id"
+	default 0
+	range 0 13
+
+config SCB0_MI1_SLOT13
+	int "Slot 13 slave interface id"
+	default 2
+	range 0 13
+
+config SCB0_MI1_SLOT14
+	int "Slot 14 slave interface id"
+	default 4
+	range 0 13
+
+config SCB0_MI1_SLOT15
+	int "Slot 15 slave interface id"
+	default 5
+	range 0 13
+
+config SCB0_MI1_SLOT16
+	int "Slot 16 slave interface id"
+	default 6
+	range 0 13
+
+config SCB0_MI1_SLOT17
+	int "Slot 17 slave interface id"
+	default 7
+	range 0 13
+
+config SCB0_MI1_SLOT18
+	int "Slot 18 slave interface id"
+	default 8
+	range 0 13
+
+config SCB0_MI1_SLOT19
+	int "Slot 19 slave interface id"
+	default 9
+	range 0 13
+
+config SCB0_MI1_SLOT20
+	int "Slot 20 slave interface id"
+	default 10
+	range 0 13
+
+config SCB0_MI1_SLOT21
+	int "Slot 21 slave interface id"
+	default 11
+	range 0 13
+
+config SCB0_MI1_SLOT22
+	int "Slot 22 slave interface id"
+	default 13
+	range 0 13
+
+config SCB0_MI1_SLOT23
+	int "Slot 23 slave interface id"
+	default 12
+	range 0 13
+
+config SCB0_MI1_SLOT24
+	int "Slot 24 slave interface id"
+	default 0
+	range 0 13
+
+config SCB0_MI1_SLOT25
+	int "Slot 25 slave interface id"
+	default 2
+	range 0 13
+
+config SCB0_MI1_SLOT26
+	int "Slot 26 slave interface id"
+	default 4
+	range 0 13
+
+config SCB0_MI1_SLOT27
+	int "Slot 27 slave interface id"
+	default 5
+	range 0 13
+
+config SCB0_MI1_SLOT28
+	int "Slot 28 slave interface id"
+	default 6
+	range 0 13
+
+config SCB0_MI1_SLOT29
+	int "Slot 29 slave interface id"
+	default 7
+	range 0 13
+
+config SCB0_MI1_SLOT30
+	int "Slot 30 slave interface id"
+	default 8
+	range 0 13
+
+config SCB0_MI1_SLOT31
+	int "Slot 31 slave interface id"
+	default 13
+	range 0 13
+
+endif # SCB0_MI1
+
+menuconfig	SCB0_MI2
+	bool "SCB0 Master Interface 2 (Data L2)"
+	default n
+	depends on SCB_PRIORITY
+	help
+	The slave interface id of each slot should be set according following table.
+	Core 0	-- 0
+	Core 1	-- 2
+	SCB1	-- 9
+	SCB2	-- 10
+	SCB3	-- 11
+	SCB4	-- 12
+	SCB5	-- 5
+	SCB6	-- 6
+	SCB7	-- 8
+	SCB8	-- 7
+	SCB9	-- 4
+	USB	-- 13
+
+if SCB0_MI2
+
+config SCB0_MI2_SLOT0
+	int "Slot 0 slave interface id"
+	default 4
+	range 0 13
+
+config SCB0_MI2_SLOT1
+	int "Slot 1 slave interface id"
+	default 5
+	range 0 13
+
+config SCB0_MI2_SLOT2
+	int "Slot 2 slave interface id"
+	default 6
+	range 0 13
+
+config SCB0_MI2_SLOT3
+	int "Slot 3 slave interface id"
+	default 7
+	range 0 13
+
+config SCB0_MI2_SLOT4
+	int "Slot 4 slave interface id"
+	default 8
+	range 0 13
+
+config SCB0_MI2_SLOT5
+	int "Slot 5 slave interface id"
+	default 9
+	range 0 13
+
+config SCB0_MI2_SLOT6
+	int "Slot 6 slave interface id"
+	default 10
+	range 0 13
+
+config SCB0_MI2_SLOT7
+	int "Slot 7 slave interface id"
+	default 11
+	range 0 13
+
+config SCB0_MI2_SLOT8
+	int "Slot 8 slave interface id"
+	default 13
+	range 0 13
+
+config SCB0_MI2_SLOT9
+	int "Slot 9 slave interface id"
+	default 12
+	range 0 13
+
+config SCB0_MI2_SLOT10
+	int "Slot 10 slave interface id"
+	default 4
+	range 0 13
+
+config SCB0_MI2_SLOT11
+	int "Slot 11 slave interface id"
+	default 5
+	range 0 13
+
+config SCB0_MI2_SLOT12
+	int "Slot 12 slave interface id"
+	default 6
+	range 0 13
+
+config SCB0_MI2_SLOT13
+	int "Slot 13 slave interface id"
+	default 7
+	range 0 13
+
+config SCB0_MI2_SLOT14
+	int "Slot 14 slave interface id"
+	default 8
+	range 0 13
+
+config SCB0_MI2_SLOT15
+	int "Slot 15 slave interface id"
+	default 9
+	range 0 13
+
+config SCB0_MI2_SLOT16
+	int "Slot 16 slave interface id"
+	default 10
+	range 0 13
+
+config SCB0_MI2_SLOT17
+	int "Slot 17 slave interface id"
+	default 11
+	range 0 13
+
+config SCB0_MI2_SLOT18
+	int "Slot 18 slave interface id"
+	default 13
+	range 0 13
+
+config SCB0_MI2_SLOT19
+	int "Slot 19 slave interface id"
+	default 12
+	range 0 13
+
+config SCB0_MI2_SLOT20
+	int "Slot 20 slave interface id"
+	default 4
+	range 0 13
+
+config SCB0_MI2_SLOT21
+	int "Slot 21 slave interface id"
+	default 5
+	range 0 13
+
+config SCB0_MI2_SLOT22
+	int "Slot 22 slave interface id"
+	default 6
+	range 0 13
+
+config SCB0_MI2_SLOT23
+	int "Slot 23 slave interface id"
+	default 7
+	range 0 13
+
+config SCB0_MI2_SLOT24
+	int "Slot 24 slave interface id"
+	default 8
+	range 0 13
+
+config SCB0_MI2_SLOT25
+	int "Slot 25 slave interface id"
+	default 9
+	range 0 13
+
+config SCB0_MI2_SLOT26
+	int "Slot 26 slave interface id"
+	default 10
+	range 0 13
+
+config SCB0_MI2_SLOT27
+	int "Slot 27 slave interface id"
+	default 11
+	range 0 13
+
+config SCB0_MI2_SLOT28
+	int "Slot 28 slave interface id"
+	default 13
+	range 0 13
+
+config SCB0_MI2_SLOT29
+	int "Slot 29 slave interface id"
+	default 12
+	range 0 13
+
+config SCB0_MI2_SLOT30
+	int "Slot 30 slave interface id"
+	default 4
+	range 0 13
+
+config SCB0_MI2_SLOT31
+	int "Slot 31 slave interface id"
+	default 7
+	range 0 13
+
+endif # SCB0_MI2
+
+menuconfig	SCB0_MI3
+	bool "SCB0 Master Interface 3 (L1A)"
+	default n
+	depends on SCB_PRIORITY
+	help
+	The slave interface id of each slot should be set according following table.
+	Core 0	-- 0
+	Core 1	-- 2
+	SCB1	-- 9
+	SCB2	-- 10
+	SCB3	-- 11
+	SCB4	-- 12
+	SCB5	-- 5
+	SCB6	-- 6
+	SCB7	-- 8
+	SCB8	-- 7
+	SCB9	-- 4
+	USB	-- 13
+
+if SCB0_MI3
+
+config SCB0_MI3_SLOT0
+	int "Slot 0 slave interface id"
+	default 4
+	range 0 13
+
+config SCB0_MI3_SLOT1
+	int "Slot 1 slave interface id"
+	default 5
+	range 0 13
+
+config SCB0_MI3_SLOT2
+	int "Slot 2 slave interface id"
+	default 6
+	range 0 13
+
+config SCB0_MI3_SLOT3
+	int "Slot 3 slave interface id"
+	default 7
+	range 0 13
+
+config SCB0_MI3_SLOT4
+	int "Slot 4 slave interface id"
+	default 8
+	range 0 13
+
+config SCB0_MI3_SLOT5
+	int "Slot 5 slave interface id"
+	default 9
+	range 0 13
+
+config SCB0_MI3_SLOT6
+	int "Slot 6 slave interface id"
+	default 10
+	range 0 13
+
+config SCB0_MI3_SLOT7
+	int "Slot 7 slave interface id"
+	default 11
+	range 0 13
+
+config SCB0_MI3_SLOT8
+	int "Slot 8 slave interface id"
+	default 13
+	range 0 13
+
+config SCB0_MI3_SLOT9
+	int "Slot 9 slave interface id"
+	default 12
+	range 0 13
+
+config SCB0_MI3_SLOT10
+	int "Slot 10 slave interface id"
+	default 4
+	range 0 13
+
+config SCB0_MI3_SLOT11
+	int "Slot 11 slave interface id"
+	default 5
+	range 0 13
+
+config SCB0_MI3_SLOT12
+	int "Slot 12 slave interface id"
+	default 6
+	range 0 13
+
+config SCB0_MI3_SLOT13
+	int "Slot 13 slave interface id"
+	default 7
+	range 0 13
+
+config SCB0_MI3_SLOT14
+	int "Slot 14 slave interface id"
+	default 8
+	range 0 13
+
+config SCB0_MI3_SLOT15
+	int "Slot 15 slave interface id"
+	default 9
+	range 0 13
+
+config SCB0_MI3_SLOT16
+	int "Slot 16 slave interface id"
+	default 10
+	range 0 13
+
+config SCB0_MI3_SLOT17
+	int "Slot 17 slave interface id"
+	default 11
+	range 0 13
+
+config SCB0_MI3_SLOT18
+	int "Slot 18 slave interface id"
+	default 13
+	range 0 13
+
+config SCB0_MI3_SLOT19
+	int "Slot 19 slave interface id"
+	default 12
+	range 0 13
+
+config SCB0_MI3_SLOT20
+	int "Slot 20 slave interface id"
+	default 4
+	range 0 13
+
+config SCB0_MI3_SLOT21
+	int "Slot 21 slave interface id"
+	default 5
+	range 0 13
+
+config SCB0_MI3_SLOT22
+	int "Slot 22 slave interface id"
+	default 6
+	range 0 13
+
+config SCB0_MI3_SLOT23
+	int "Slot 23 slave interface id"
+	default 7
+	range 0 13
+
+config SCB0_MI3_SLOT24
+	int "Slot 24 slave interface id"
+	default 8
+	range 0 13
+
+config SCB0_MI3_SLOT25
+	int "Slot 25 slave interface id"
+	default 9
+	range 0 13
+
+config SCB0_MI3_SLOT26
+	int "Slot 26 slave interface id"
+	default 10
+	range 0 13
+
+config SCB0_MI3_SLOT27
+	int "Slot 27 slave interface id"
+	default 11
+	range 0 13
+
+config SCB0_MI3_SLOT28
+	int "Slot 28 slave interface id"
+	default 13
+	range 0 13
+
+config SCB0_MI3_SLOT29
+	int "Slot 29 slave interface id"
+	default 12
+	range 0 13
+
+config SCB0_MI3_SLOT30
+	int "Slot 30 slave interface id"
+	default 4
+	range 0 13
+
+config SCB0_MI3_SLOT31
+	int "Slot 31 slave interface id"
+	default 7
+	range 0 13
+
+endif # SCB0_MI3
+
+menuconfig	SCB0_MI4
+	bool "SCB0 Master Interface 4 (L1B)"
+	default n
+	depends on SCB_PRIORITY
+	help
+	The slave interface id of each slot should be set according following table.
+	Core 0	-- 0
+	Core 1	-- 2
+	SCB1	-- 9
+	SCB2	-- 10
+	SCB3	-- 11
+	SCB4	-- 12
+	SCB5	-- 5
+	SCB6	-- 6
+	SCB7	-- 8
+	SCB8	-- 7
+	SCB9	-- 4
+	USB	-- 13
+
+if SCB0_MI4
+
+config SCB0_MI4_SLOT0
+	int "Slot 0 slave interface id"
+	default 4
+	range 0 13
+
+config SCB0_MI4_SLOT1
+	int "Slot 1 slave interface id"
+	default 5
+	range 0 13
+
+config SCB0_MI4_SLOT2
+	int "Slot 2 slave interface id"
+	default 6
+	range 0 13
+
+config SCB0_MI4_SLOT3
+	int "Slot 3 slave interface id"
+	default 7
+	range 0 13
+
+config SCB0_MI4_SLOT4
+	int "Slot 4 slave interface id"
+	default 8
+	range 0 13
+
+config SCB0_MI4_SLOT5
+	int "Slot 5 slave interface id"
+	default 9
+	range 0 13
+
+config SCB0_MI4_SLOT6
+	int "Slot 6 slave interface id"
+	default 10
+	range 0 13
+
+config SCB0_MI4_SLOT7
+	int "Slot 7 slave interface id"
+	default 11
+	range 0 13
+
+config SCB0_MI4_SLOT8
+	int "Slot 8 slave interface id"
+	default 13
+	range 0 13
+
+config SCB0_MI4_SLOT9
+	int "Slot 9 slave interface id"
+	default 12
+	range 0 13
+
+config SCB0_MI4_SLOT10
+	int "Slot 10 slave interface id"
+	default 4
+	range 0 13
+
+config SCB0_MI4_SLOT11
+	int "Slot 11 slave interface id"
+	default 5
+	range 0 13
+
+config SCB0_MI4_SLOT12
+	int "Slot 12 slave interface id"
+	default 6
+	range 0 13
+
+config SCB0_MI4_SLOT13
+	int "Slot 13 slave interface id"
+	default 7
+	range 0 13
+
+config SCB0_MI4_SLOT14
+	int "Slot 14 slave interface id"
+	default 8
+	range 0 13
+
+config SCB0_MI4_SLOT15
+	int "Slot 15 slave interface id"
+	default 9
+	range 0 13
+
+config SCB0_MI4_SLOT16
+	int "Slot 16 slave interface id"
+	default 10
+	range 0 13
+
+config SCB0_MI4_SLOT17
+	int "Slot 17 slave interface id"
+	default 11
+	range 0 13
+
+config SCB0_MI4_SLOT18
+	int "Slot 18 slave interface id"
+	default 13
+	range 0 13
+
+config SCB0_MI4_SLOT19
+	int "Slot 19 slave interface id"
+	default 12
+	range 0 13
+
+config SCB0_MI4_SLOT20
+	int "Slot 20 slave interface id"
+	default 4
+	range 0 13
+
+config SCB0_MI4_SLOT21
+	int "Slot 21 slave interface id"
+	default 5
+	range 0 13
+
+config SCB0_MI4_SLOT22
+	int "Slot 22 slave interface id"
+	default 6
+	range 0 13
+
+config SCB0_MI4_SLOT23
+	int "Slot 23 slave interface id"
+	default 7
+	range 0 13
+
+config SCB0_MI4_SLOT24
+	int "Slot 24 slave interface id"
+	default 8
+	range 0 13
+
+config SCB0_MI4_SLOT25
+	int "Slot 25 slave interface id"
+	default 9
+	range 0 13
+
+config SCB0_MI4_SLOT26
+	int "Slot 26 slave interface id"
+	default 10
+	range 0 13
+
+config SCB0_MI4_SLOT27
+	int "Slot 27 slave interface id"
+	default 11
+	range 0 13
+
+config SCB0_MI4_SLOT28
+	int "Slot 28 slave interface id"
+	default 13
+	range 0 13
+
+config SCB0_MI4_SLOT29
+	int "Slot 29 slave interface id"
+	default 12
+	range 0 13
+
+config SCB0_MI4_SLOT30
+	int "Slot 30 slave interface id"
+	default 4
+	range 0 13
+
+config SCB0_MI4_SLOT31
+	int "Slot 31 slave interface id"
+	default 7
+	range 0 13
+
+endif # SCB0_MI4
+
+menuconfig	SCB0_MI5
+	bool "SCB0 Master Interface 5 (SMMR)"
+	default n
+	depends on SCB_PRIORITY
+	help
+	The slave interface id of each slot should be set according following table.
+	MMR0	-- 1
+	MMR1	-- 3
+	SCB2	-- 10
+	SCB4	-- 12
+
+if SCB0_MI5
+
+config SCB0_MI5_SLOT0
+	int "Slot 0 slave interface id"
+	default 1
+	range 0 13
+
+config SCB0_MI5_SLOT1
+	int "Slot 1 slave interface id"
+	default 3
+	range 0 13
+
+config SCB0_MI5_SLOT2
+	int "Slot 2 slave interface id"
+	default 10
+	range 0 13
+
+config SCB0_MI5_SLOT3
+	int "Slot 3 slave interface id"
+	default 12
+	range 0 13
+
+config SCB0_MI5_SLOT4
+	int "Slot 4 slave interface id"
+	default 1
+	range 0 13
+
+config SCB0_MI5_SLOT5
+	int "Slot 5 slave interface id"
+	default 3
+	range 0 13
+
+config SCB0_MI5_SLOT6
+	int "Slot 6 slave interface id"
+	default 10
+	range 0 13
+
+config SCB0_MI5_SLOT7
+	int "Slot 7 slave interface id"
+	default 12
+	range 0 13
+
+config SCB0_MI5_SLOT8
+	int "Slot 8 slave interface id"
+	default 1
+	range 0 13
+
+config SCB0_MI5_SLOT9
+	int "Slot 9 slave interface id"
+	default 3
+	range 0 13
+
+config SCB0_MI5_SLOT10
+	int "Slot 10 slave interface id"
+	default 10
+	range 0 13
+
+config SCB0_MI5_SLOT11
+	int "Slot 11 slave interface id"
+	default 12
+	range 0 13
+
+config SCB0_MI5_SLOT12
+	int "Slot 12 slave interface id"
+	default 1
+	range 0 13
+
+config SCB0_MI5_SLOT13
+	int "Slot 13 slave interface id"
+	default 3
+	range 0 13
+
+config SCB0_MI5_SLOT14
+	int "Slot 14 slave interface id"
+	default 10
+	range 0 13
+
+config SCB0_MI5_SLOT15
+	int "Slot 15 slave interface id"
+	default 12
+	range 0 13
+
+endif # SCB0_MI5
+
+menuconfig	SCB1_MI0
+	bool "SCB1 Master Interface 0"
+	default n
+	depends on SCB_PRIORITY
+	help
+	The slave interface id of each slot should be set according following table.
+	SPORT0A	-- 0
+	SPORT0B	-- 1
+	SPORT1A	-- 2
+	SPORT1B	-- 3
+	SPORT2A	-- 4
+	SPORT2B	-- 5
+	SPI0TX	-- 6
+	SPI0RX	-- 7
+	SPI1TX	-- 8
+	SPI1RX	-- 9
+
+if SCB1_MI0
+
+config SCB1_MI0_SLOT0
+	int "Slot 0 slave interface id"
+	default 0
+	range 0 9
+
+config SCB1_MI0_SLOT1
+	int "Slot 1 slave interface id"
+	default 1
+	range 0 9
+
+config SCB1_MI0_SLOT2
+	int "Slot 2 slave interface id"
+	default 2
+	range 0 9
+
+config SCB1_MI0_SLOT3
+	int "Slot 3 slave interface id"
+	default 3
+	range 0 9
+
+config SCB1_MI0_SLOT4
+	int "Slot 4 slave interface id"
+	default 4
+	range 0 9
+
+config SCB1_MI0_SLOT5
+	int "Slot 5 slave interface id"
+	default 5
+	range 0 9
+
+config SCB1_MI0_SLOT6
+	int "Slot 6 slave interface id"
+	default 6
+	range 0 9
+
+config SCB1_MI0_SLOT7
+	int "Slot 7 slave interface id"
+	default 7
+	range 0 9
+
+config SCB1_MI0_SLOT8
+	int "Slot 8 slave interface id"
+	default 8
+	range 0 9
+
+config SCB1_MI0_SLOT9
+	int "Slot 9 slave interface id"
+	default 9
+	range 0 9
+
+config SCB1_MI0_SLOT10
+	int "Slot 10 slave interface id"
+	default 0
+	range 0 9
+
+config SCB1_MI0_SLOT11
+	int "Slot 11 slave interface id"
+	default 1
+	range 0 9
+
+config SCB1_MI0_SLOT12
+	int "Slot 12 slave interface id"
+	default 2
+	range 0 9
+
+config SCB1_MI0_SLOT13
+	int "Slot 13 slave interface id"
+	default 3
+	range 0 9
+
+config SCB1_MI0_SLOT14
+	int "Slot 14 slave interface id"
+	default 4
+	range 0 9
+
+config SCB1_MI0_SLOT15
+	int "Slot 15 slave interface id"
+	default 5
+	range 0 9
+
+config SCB1_MI0_SLOT16
+	int "Slot 16 slave interface id"
+	default 6
+	range 0 13
+
+config SCB1_MI0_SLOT17
+	int "Slot 17 slave interface id"
+	default 7
+	range 0 13
+
+config SCB1_MI0_SLOT18
+	int "Slot 18 slave interface id"
+	default 8
+	range 0 13
+
+config SCB1_MI0_SLOT19
+	int "Slot 19 slave interface id"
+	default 9
+	range 0 13
+
+endif # SCB1_MI0
+
+menuconfig	SCB2_MI0
+	bool "SCB2 Master Interface 0"
+	default n
+	depends on SCB_PRIORITY
+	help
+	The slave interface id of each slot should be set according following table.
+	RSI	-- 0
+	SDU DMA	-- 1
+	SDU	-- 2
+	EMAC0	-- 3
+	EMAC1	-- 4
+
+if SCB2_MI0
+
+config SCB2_MI0_SLOT0
+	int "Slot 0 slave interface id"
+	default 0
+	range 0 4
+
+config SCB2_MI0_SLOT1
+	int "Slot 1 slave interface id"
+	default 1
+	range 0 4
+
+config SCB2_MI0_SLOT2
+	int "Slot 2 slave interface id"
+	default 2
+	range 0 4
+
+config SCB2_MI0_SLOT3
+	int "Slot 3 slave interface id"
+	default 3
+	range 0 4
+
+config SCB2_MI0_SLOT4
+	int "Slot 4 slave interface id"
+	default 4
+	range 0 4
+
+config SCB2_MI0_SLOT5
+	int "Slot 5 slave interface id"
+	default 0
+	range 0 4
+
+config SCB2_MI0_SLOT6
+	int "Slot 6 slave interface id"
+	default 1
+	range 0 4
+
+config SCB2_MI0_SLOT7
+	int "Slot 7 slave interface id"
+	default 2
+	range 0 4
+
+config SCB2_MI0_SLOT8
+	int "Slot 8 slave interface id"
+	default 3
+	range 0 4
+
+config SCB2_MI0_SLOT9
+	int "Slot 9 slave interface id"
+	default 4
+	range 0 4
+
+endif # SCB2_MI0
+
+menuconfig	SCB3_MI0
+	bool "SCB3 Master Interface 0"
+	default n
+	depends on SCB_PRIORITY
+	help
+	The slave interface id of each slot should be set according following table.
+	LP0	-- 0
+	LP1	-- 1
+	LP2	-- 2
+	LP3	-- 3
+	UART0TX	-- 4
+	UART0RX	-- 5
+	UART1TX	-- 4
+	UART1RX	-- 5
+
+if SCB3_MI0
+
+config SCB3_MI0_SLOT0
+	int "Slot 0 slave interface id"
+	default 0
+	range 0 7
+
+config SCB3_MI0_SLOT1
+	int "Slot 1 slave interface id"
+	default 1
+	range 0 7
+
+config SCB3_MI0_SLOT2
+	int "Slot 2 slave interface id"
+	default 2
+	range 0 7
+
+config SCB3_MI0_SLOT3
+	int "Slot 3 slave interface id"
+	default 3
+	range 0 7
+
+config SCB3_MI0_SLOT4
+	int "Slot 4 slave interface id"
+	default 4
+	range 0 7
+
+config SCB3_MI0_SLOT5
+	int "Slot 5 slave interface id"
+	default 5
+	range 0 7
+
+config SCB3_MI0_SLOT6
+	int "Slot 6 slave interface id"
+	default 6
+	range 0 7
+
+config SCB3_MI0_SLOT7
+	int "Slot 7 slave interface id"
+	default 7
+	range 0 7
+
+config SCB3_MI0_SLOT8
+	int "Slot 8 slave interface id"
+	default 0
+	range 0 7
+
+config SCB3_MI0_SLOT9
+	int "Slot 9 slave interface id"
+	default 1
+	range 0 7
+
+config SCB3_MI0_SLOT10
+	int "Slot 10 slave interface id"
+	default 2
+	range 0 7
+
+config SCB3_MI0_SLOT11
+	int "Slot 11 slave interface id"
+	default 3
+	range 0 7
+
+config SCB3_MI0_SLOT12
+	int "Slot 12 slave interface id"
+	default 4
+	range 0 7
+
+config SCB3_MI0_SLOT13
+	int "Slot 13 slave interface id"
+	default 5
+	range 0 7
+
+config SCB3_MI0_SLOT14
+	int "Slot 14 slave interface id"
+	default 6
+	range 0 7
+
+config SCB3_MI0_SLOT15
+	int "Slot 15 slave interface id"
+	default 7
+	range 0 7
+
+endif # SCB3_MI0
+
+menuconfig	SCB4_MI0
+	bool "SCB4 Master Interface 0"
+	default n
+	depends on SCB_PRIORITY
+	help
+	The slave interface id of each slot should be set according following table.
+	MDA21	-- 0
+	MDA22	-- 1
+	MDA23	-- 2
+	MDA24	-- 3
+	MDA25	-- 4
+	MDA26	-- 5
+	MDA27	-- 6
+	MDA28	-- 7
+
+if SCB4_MI0
+
+config SCB4_MI0_SLOT0
+	int "Slot 0 slave interface id"
+	default 0
+	range 0 7
+
+config SCB4_MI0_SLOT1
+	int "Slot 1 slave interface id"
+	default 1
+	range 0 7
+
+config SCB4_MI0_SLOT2
+	int "Slot 2 slave interface id"
+	default 2
+	range 0 7
+
+config SCB4_MI0_SLOT3
+	int "Slot 3 slave interface id"
+	default 3
+	range 0 7
+
+config SCB4_MI0_SLOT4
+	int "Slot 4 slave interface id"
+	default 4
+	range 0 7
+
+config SCB4_MI0_SLOT5
+	int "Slot 5 slave interface id"
+	default 5
+	range 0 7
+
+config SCB4_MI0_SLOT6
+	int "Slot 6 slave interface id"
+	default 6
+	range 0 7
+
+config SCB4_MI0_SLOT7
+	int "Slot 7 slave interface id"
+	default 7
+	range 0 7
+
+config SCB4_MI0_SLOT8
+	int "Slot 8 slave interface id"
+	default 0
+	range 0 7
+
+config SCB4_MI0_SLOT9
+	int "Slot 9 slave interface id"
+	default 1
+	range 0 7
+
+config SCB4_MI0_SLOT10
+	int "Slot 10 slave interface id"
+	default 2
+	range 0 7
+
+config SCB4_MI0_SLOT11
+	int "Slot 11 slave interface id"
+	default 3
+	range 0 7
+
+config SCB4_MI0_SLOT12
+	int "Slot 12 slave interface id"
+	default 4
+	range 0 7
+
+config SCB4_MI0_SLOT13
+	int "Slot 13 slave interface id"
+	default 5
+	range 0 7
+
+config SCB4_MI0_SLOT14
+	int "Slot 14 slave interface id"
+	default 6
+	range 0 7
+
+config SCB4_MI0_SLOT15
+	int "Slot 15 slave interface id"
+	default 7
+	range 0 7
+
+endif # SCB4_MI0
+
+menuconfig	SCB5_MI0
+	bool "SCB5 Master Interface 0"
+	default n
+	depends on SCB_PRIORITY
+	help
+	The slave interface id of each slot should be set according following table.
+	PPI0 MDA29	-- 0
+	PPI0 MDA30	-- 1
+	PPI2 MDA31	-- 2
+	PPI2 MDA32	-- 3
+
+if SCB5_MI0
+
+config SCB5_MI0_SLOT0
+	int "Slot 0 slave interface id"
+	default 0
+	range 0 3
+
+config SCB5_MI0_SLOT1
+	int "Slot 1 slave interface id"
+	default 1
+	range 0 3
+
+config SCB5_MI0_SLOT2
+	int "Slot 2 slave interface id"
+	default 2
+	range 0 3
+
+config SCB5_MI0_SLOT3
+	int "Slot 3 slave interface id"
+	default 3
+	range 0 3
+
+config SCB5_MI0_SLOT4
+	int "Slot 4 slave interface id"
+	default 0
+	range 0 3
+
+config SCB5_MI0_SLOT5
+	int "Slot 5 slave interface id"
+	default 1
+	range 0 3
+
+config SCB5_MI0_SLOT6
+	int "Slot 6 slave interface id"
+	default 2
+	range 0 3
+
+config SCB5_MI0_SLOT7
+	int "Slot 7 slave interface id"
+	default 3
+	range 0 3
+
+endif # SCB5_MI0
+
+menuconfig	SCB6_MI0
+	bool "SCB6 Master Interface 0"
+	default n
+	depends on SCB_PRIORITY
+	help
+	The slave interface id of each slot should be set according following table.
+	PPI1 MDA33	-- 0
+	PPI1 MDA34	-- 1
+
+if SCB6_MI0
+
+config SCB6_MI0_SLOT0
+	int "Slot 0 slave interface id"
+	default 0
+	range 0 1
+
+config SCB6_MI0_SLOT1
+	int "Slot 1 slave interface id"
+	default 1
+	range 0 1
+
+config SCB6_MI0_SLOT2
+	int "Slot 2 slave interface id"
+	default 0
+	range 0 1
+
+config SCB6_MI0_SLOT3
+	int "Slot 3 slave interface id"
+	default 1
+	range 0 1
+
+endif # SCB6_MI0
+
+menuconfig	SCB7_MI0
+	bool "SCB7 Master Interface 0"
+	default n
+	depends on SCB_PRIORITY
+	help
+	The slave interface id of each slot should be set according following table.
+	PIXC0	-- 0
+	PIXC1	-- 1
+	PIXC2	-- 2
+
+if SCB7_MI0
+
+config SCB7_MI0_SLOT0
+	int "Slot 0 slave interface id"
+	default 0
+	range 0 2
+
+config SCB7_MI0_SLOT1
+	int "Slot 1 slave interface id"
+	default 1
+	range 0 2
+
+config SCB7_MI0_SLOT2
+	int "Slot 2 slave interface id"
+	default 2
+	range 0 2
+
+config SCB7_MI0_SLOT3
+	int "Slot 3 slave interface id"
+	default 0
+	range 0 2
+
+config SCB7_MI0_SLOT4
+	int "Slot 4 slave interface id"
+	default 1
+	range 0 2
+
+config SCB7_MI0_SLOT5
+	int "Slot 5 slave interface id"
+	default 2
+	range 0 2
+
+endif # SCB7_MI0
+
+menuconfig	SCB8_MI0
+	bool "SCB8 Master Interface 0"
+	default n
+	depends on SCB_PRIORITY
+	help
+	The slave interface id of each slot should be set according following table.
+	PVP CPDOB	-- 0
+	PVP CPDOC	-- 1
+	PVP CPCO	-- 2
+	PVP CPCI	-- 3
+
+if SCB8_MI0
+
+config SCB8_MI0_SLOT0
+	int "Slot 0 slave interface id"
+	default 0
+	range 0 3
+
+config SCB8_MI0_SLOT1
+	int "Slot 1 slave interface id"
+	default 1
+	range 0 3
+
+config SCB8_MI0_SLOT2
+	int "Slot 2 slave interface id"
+	default 2
+	range 0 3
+
+config SCB8_MI0_SLOT3
+	int "Slot 3 slave interface id"
+	default 3
+	range 0 3
+
+config SCB8_MI0_SLOT4
+	int "Slot 4 slave interface id"
+	default 0
+	range 0 3
+
+config SCB8_MI0_SLOT5
+	int "Slot 5 slave interface id"
+	default 1
+	range 0 3
+
+config SCB8_MI0_SLOT6
+	int "Slot 6 slave interface id"
+	default 2
+	range 0 3
+
+config SCB8_MI0_SLOT7
+	int "Slot 7 slave interface id"
+	default 3
+	range 0 3
+
+endif # SCB8_MI0
+
+menuconfig	SCB9_MI0
+	bool "SCB9 Master Interface 0"
+	default n
+	depends on SCB_PRIORITY
+	help
+	The slave interface id of each slot should be set according following table.
+	PVP MPDO	-- 0
+	PVP MPDI	-- 1
+	PVP MPCO	-- 2
+	PVP MPCI	-- 3
+	PVP CPDOA	-- 4
+
+if SCB9_MI0
+
+config SCB9_MI0_SLOT0
+	int "Slot 0 slave interface id"
+	default 0
+	range 0 4
+
+config SCB9_MI0_SLOT1
+	int "Slot 1 slave interface id"
+	default 1
+	range 0 4
+
+config SCB9_MI0_SLOT2
+	int "Slot 2 slave interface id"
+	default 2
+	range 0 4
+
+config SCB9_MI0_SLOT3
+	int "Slot 3 slave interface id"
+	default 3
+	range 0 4
+
+config SCB9_MI0_SLOT4
+	int "Slot 4 slave interface id"
+	default 4
+	range 0 4
+
+config SCB9_MI0_SLOT5
+	int "Slot 5 slave interface id"
+	default 0
+	range 0 4
+
+config SCB9_MI0_SLOT6
+	int "Slot 6 slave interface id"
+	default 1
+	range 0 4
+
+config SCB9_MI0_SLOT7
+	int "Slot 7 slave interface id"
+	default 2
+	range 0 4
+
+config SCB9_MI0_SLOT8
+	int "Slot 8 slave interface id"
+	default 3
+	range 0 4
+
+config SCB9_MI0_SLOT9
+	int "Slot 9 slave interface id"
+	default 4
+	range 0 4
+
+endif # SCB9_MI0
+
 endmenu
 
 endif
diff --git a/arch/blackfin/mach-bf609/Makefile b/arch/blackfin/mach-bf609/Makefile
index 234fe1b4bb0e..60ffaf85d303 100644
--- a/arch/blackfin/mach-bf609/Makefile
+++ b/arch/blackfin/mach-bf609/Makefile
@@ -4,3 +4,4 @@
 
 obj-y := dma.o clock.o ints-priority.o
 obj-$(CONFIG_PM) += pm.o dpm.o
+obj-$(CONFIG_SCB_PRIORITY) += scb.o
diff --git a/arch/blackfin/mach-bf609/boards/ezkit.c b/arch/blackfin/mach-bf609/boards/ezkit.c
index 0bc47231540b..d56a55ad83a7 100644
--- a/arch/blackfin/mach-bf609/boards/ezkit.c
+++ b/arch/blackfin/mach-bf609/boards/ezkit.c
@@ -104,6 +104,7 @@ static struct platform_device bfin_rotary_device = {
 
 #if defined(CONFIG_STMMAC_ETH) || defined(CONFIG_STMMAC_ETH_MODULE)
 #include <linux/stmmac.h>
+#include <linux/phy.h>
 
 static unsigned short pins[] = P_RMII0;
 
@@ -111,11 +112,26 @@ static struct stmmac_mdio_bus_data phy_private_data = {
 	.phy_mask = 1,
 };
 
+static struct stmmac_dma_cfg eth_dma_cfg = {
+	.pbl	= 2,
+};
+
+int stmmac_ptp_clk_init(struct platform_device *pdev)
+{
+	bfin_write32(PADS0_EMAC_PTP_CLKSEL, 0);
+	return 0;
+}
+
 static struct plat_stmmacenet_data eth_private_data = {
+	.has_gmac = 1,
 	.bus_id   = 0,
 	.enh_desc = 1,
 	.phy_addr = 1,
 	.mdio_bus_data = &phy_private_data,
+	.dma_cfg  = &eth_dma_cfg,
+	.force_thresh_dma_mode = 1,
+	.interface = PHY_INTERFACE_MODE_RMII,
+	.init = stmmac_ptp_clk_init,
 };
 
 static struct platform_device bfin_eth_device = {
@@ -1107,6 +1123,81 @@ static struct bfin_display_config bfin_display_data = {
 };
 #endif
 
+#if IS_ENABLED(CONFIG_VIDEO_ADV7343)
+#include <media/adv7343.h>
+
+static struct v4l2_output adv7343_outputs[] = {
+	{
+		.index = 0,
+		.name = "Composite",
+		.type = V4L2_OUTPUT_TYPE_ANALOG,
+		.std = V4L2_STD_ALL,
+		.capabilities = V4L2_OUT_CAP_STD,
+	},
+	{
+		.index = 1,
+		.name = "S-Video",
+		.type = V4L2_OUTPUT_TYPE_ANALOG,
+		.std = V4L2_STD_ALL,
+		.capabilities = V4L2_OUT_CAP_STD,
+	},
+	{
+		.index = 2,
+		.name = "Component",
+		.type = V4L2_OUTPUT_TYPE_ANALOG,
+		.std = V4L2_STD_ALL,
+		.capabilities = V4L2_OUT_CAP_STD,
+	},
+
+};
+
+static struct disp_route adv7343_routes[] = {
+	{
+		.output = ADV7343_COMPOSITE_ID,
+	},
+	{
+		.output = ADV7343_SVIDEO_ID,
+	},
+	{
+		.output = ADV7343_COMPONENT_ID,
+	},
+};
+
+static struct adv7343_platform_data adv7343_data = {
+	.mode_config = {
+		.sleep_mode = false,
+		.pll_control = false,
+		.dac_1 = true,
+		.dac_2 = true,
+		.dac_3 = true,
+		.dac_4 = true,
+		.dac_5 = true,
+		.dac_6 = true,
+	},
+	.sd_config = {
+		.sd_dac_out1 = false,
+		.sd_dac_out2 = false,
+	},
+};
+
+static struct bfin_display_config bfin_display_data = {
+	.card_name = "BF609",
+	.outputs = adv7343_outputs,
+	.num_outputs = ARRAY_SIZE(adv7343_outputs),
+	.routes = adv7343_routes,
+	.i2c_adapter_id = 0,
+	.board_info = {
+		.type = "adv7343",
+		.addr = 0x2b,
+		.platform_data = (void *)&adv7343_data,
+	},
+	.ppi_info = &ppi_info_disp,
+	.ppi_control = (PACK_EN | DLEN_8 | EPPI_CTL_FS1LO_FS2LO
+			| EPPI_CTL_POLC3 | EPPI_CTL_BLANKGEN | EPPI_CTL_SYNC2
+			| EPPI_CTL_NON656 | EPPI_CTL_DIR),
+};
+#endif
+
 static struct platform_device bfin_display_device = {
 	.name = "bfin_display",
 	.dev = {
diff --git a/arch/blackfin/mach-bf609/clock.c b/arch/blackfin/mach-bf609/clock.c
index 437d56c82281..dab8849af884 100644
--- a/arch/blackfin/mach-bf609/clock.c
+++ b/arch/blackfin/mach-bf609/clock.c
@@ -220,6 +220,12 @@ unsigned long sys_clk_get_rate(struct clk *clk)
 	}
 }
 
+unsigned long dummy_get_rate(struct clk *clk)
+{
+	clk->parent->rate = clk_get_rate(clk->parent);
+	return clk->parent->rate;
+}
+
 unsigned long sys_clk_round_rate(struct clk *clk, unsigned long rate)
 {
 	unsigned long max_rate;
@@ -283,6 +289,10 @@ static struct clk_ops sys_clk_ops = {
 	.round_rate = sys_clk_round_rate,
 };
 
+static struct clk_ops dummy_clk_ops = {
+	.get_rate = dummy_get_rate,
+};
+
 static struct clk sys_clkin = {
 	.name       = "SYS_CLKIN",
 	.rate       = CONFIG_CLKIN_HZ,
@@ -364,6 +374,12 @@ static struct clk oclk = {
 	.parent     = &pll_clk,
 };
 
+static struct clk ethclk = {
+	.name       = "stmmaceth",
+	.parent     = &sclk0,
+	.ops	    = &dummy_clk_ops,
+};
+
 static struct clk_lookup bf609_clks[] = {
 	CLK(sys_clkin, NULL, "SYS_CLKIN"),
 	CLK(pll_clk, NULL, "PLLCLK"),
@@ -375,6 +391,7 @@ static struct clk_lookup bf609_clks[] = {
 	CLK(sclk1, NULL, "SCLK1"),
 	CLK(dclk, NULL, "DCLK"),
 	CLK(oclk, NULL, "OCLK"),
+	CLK(ethclk, NULL, "stmmaceth"),
 };
 
 int __init clk_init(void)
diff --git a/arch/blackfin/mach-bf609/include/mach/defBF60x_base.h b/arch/blackfin/mach-bf609/include/mach/defBF60x_base.h
index f1a6afae1a71..35caa7bc192c 100644
--- a/arch/blackfin/mach-bf609/include/mach/defBF60x_base.h
+++ b/arch/blackfin/mach-bf609/include/mach/defBF60x_base.h
@@ -839,6 +839,16 @@
 #define PORTG_LOCK                  0xFFC03344         /* PORTG Port x GPIO Lock Register */
 #define PORTG_REVID                 0xFFC0337C         /* PORTG Port x GPIO Revision ID */
 
+/* ==================================================
+        Pads Controller Registers
+   ================================================== */
+
+/* =========================
+        PADS0
+   ========================= */
+#define PADS0_EMAC_PTP_CLKSEL	    0xFFC03404         /* PADS0 Clock Selection for EMAC and PTP */
+#define PADS0_TWI_VSEL		    0xFFC03408         /* PADS0 TWI Voltage Selection */
+#define PADS0_PORTS_HYST	    0xFFC03440         /* PADS0 Hysteresis Enable Register */
 
 /* =========================
         PINT Registers
diff --git a/arch/blackfin/mach-bf609/scb.c b/arch/blackfin/mach-bf609/scb.c
new file mode 100644
index 000000000000..ac1f07c33594
--- /dev/null
+++ b/arch/blackfin/mach-bf609/scb.c
@@ -0,0 +1,363 @@
+/*
+ * arch/blackfin/mach-common/scb-init.c - reprogram system cross bar priority
+ *
+ * Copyright 2012 Analog Devices Inc.
+ *
+ * Licensed under the GPL-2 or later.
+ */
+
+#include <asm/blackfin.h>
+#include <asm/scb.h>
+
+struct scb_mi_prio scb_data[] = {
+#ifdef CONFIG_SCB0_MI0
+	{ REG_SCB0_ARBR0, REG_SCB0_ARBW0, 32, {
+		CONFIG_SCB0_MI0_SLOT0,
+		CONFIG_SCB0_MI0_SLOT1,
+		CONFIG_SCB0_MI0_SLOT2,
+		CONFIG_SCB0_MI0_SLOT3,
+		CONFIG_SCB0_MI0_SLOT4,
+		CONFIG_SCB0_MI0_SLOT5,
+		CONFIG_SCB0_MI0_SLOT6,
+		CONFIG_SCB0_MI0_SLOT7,
+		CONFIG_SCB0_MI0_SLOT8,
+		CONFIG_SCB0_MI0_SLOT9,
+		CONFIG_SCB0_MI0_SLOT10,
+		CONFIG_SCB0_MI0_SLOT11,
+		CONFIG_SCB0_MI0_SLOT12,
+		CONFIG_SCB0_MI0_SLOT13,
+		CONFIG_SCB0_MI0_SLOT14,
+		CONFIG_SCB0_MI0_SLOT15,
+		CONFIG_SCB0_MI0_SLOT16,
+		CONFIG_SCB0_MI0_SLOT17,
+		CONFIG_SCB0_MI0_SLOT18,
+		CONFIG_SCB0_MI0_SLOT19,
+		CONFIG_SCB0_MI0_SLOT20,
+		CONFIG_SCB0_MI0_SLOT21,
+		CONFIG_SCB0_MI0_SLOT22,
+		CONFIG_SCB0_MI0_SLOT23,
+		CONFIG_SCB0_MI0_SLOT24,
+		CONFIG_SCB0_MI0_SLOT25,
+		CONFIG_SCB0_MI0_SLOT26,
+		CONFIG_SCB0_MI0_SLOT27,
+		CONFIG_SCB0_MI0_SLOT28,
+		CONFIG_SCB0_MI0_SLOT29,
+		CONFIG_SCB0_MI0_SLOT30,
+		CONFIG_SCB0_MI0_SLOT31
+		},
+	},
+#endif
+#ifdef CONFIG_SCB0_MI1
+	{ REG_SCB0_ARBR1, REG_SCB0_ARBW1, 32, {
+		CONFIG_SCB0_MI1_SLOT0,
+		CONFIG_SCB0_MI1_SLOT1,
+		CONFIG_SCB0_MI1_SLOT2,
+		CONFIG_SCB0_MI1_SLOT3,
+		CONFIG_SCB0_MI1_SLOT4,
+		CONFIG_SCB0_MI1_SLOT5,
+		CONFIG_SCB0_MI1_SLOT6,
+		CONFIG_SCB0_MI1_SLOT7,
+		CONFIG_SCB0_MI1_SLOT8,
+		CONFIG_SCB0_MI1_SLOT9,
+		CONFIG_SCB0_MI1_SLOT10,
+		CONFIG_SCB0_MI1_SLOT11,
+		CONFIG_SCB0_MI1_SLOT12,
+		CONFIG_SCB0_MI1_SLOT13,
+		CONFIG_SCB0_MI1_SLOT14,
+		CONFIG_SCB0_MI1_SLOT15,
+		CONFIG_SCB0_MI1_SLOT16,
+		CONFIG_SCB0_MI1_SLOT17,
+		CONFIG_SCB0_MI1_SLOT18,
+		CONFIG_SCB0_MI1_SLOT19,
+		CONFIG_SCB0_MI1_SLOT20,
+		CONFIG_SCB0_MI1_SLOT21,
+		CONFIG_SCB0_MI1_SLOT22,
+		CONFIG_SCB0_MI1_SLOT23,
+		CONFIG_SCB0_MI1_SLOT24,
+		CONFIG_SCB0_MI1_SLOT25,
+		CONFIG_SCB0_MI1_SLOT26,
+		CONFIG_SCB0_MI1_SLOT27,
+		CONFIG_SCB0_MI1_SLOT28,
+		CONFIG_SCB0_MI1_SLOT29,
+		CONFIG_SCB0_MI1_SLOT30,
+		CONFIG_SCB0_MI1_SLOT31
+		},
+	},
+#endif
+#ifdef CONFIG_SCB0_MI2
+	{ REG_SCB0_ARBR2, REG_SCB0_ARBW2, 32, {
+		CONFIG_SCB0_MI2_SLOT0,
+		CONFIG_SCB0_MI2_SLOT1,
+		CONFIG_SCB0_MI2_SLOT2,
+		CONFIG_SCB0_MI2_SLOT3,
+		CONFIG_SCB0_MI2_SLOT4,
+		CONFIG_SCB0_MI2_SLOT5,
+		CONFIG_SCB0_MI2_SLOT6,
+		CONFIG_SCB0_MI2_SLOT7,
+		CONFIG_SCB0_MI2_SLOT8,
+		CONFIG_SCB0_MI2_SLOT9,
+		CONFIG_SCB0_MI2_SLOT10,
+		CONFIG_SCB0_MI2_SLOT11,
+		CONFIG_SCB0_MI2_SLOT12,
+		CONFIG_SCB0_MI2_SLOT13,
+		CONFIG_SCB0_MI2_SLOT14,
+		CONFIG_SCB0_MI2_SLOT15,
+		CONFIG_SCB0_MI2_SLOT16,
+		CONFIG_SCB0_MI2_SLOT17,
+		CONFIG_SCB0_MI2_SLOT18,
+		CONFIG_SCB0_MI2_SLOT19,
+		CONFIG_SCB0_MI2_SLOT20,
+		CONFIG_SCB0_MI2_SLOT21,
+		CONFIG_SCB0_MI2_SLOT22,
+		CONFIG_SCB0_MI2_SLOT23,
+		CONFIG_SCB0_MI2_SLOT24,
+		CONFIG_SCB0_MI2_SLOT25,
+		CONFIG_SCB0_MI2_SLOT26,
+		CONFIG_SCB0_MI2_SLOT27,
+		CONFIG_SCB0_MI2_SLOT28,
+		CONFIG_SCB0_MI2_SLOT29,
+		CONFIG_SCB0_MI2_SLOT30,
+		CONFIG_SCB0_MI2_SLOT31
+		},
+	},
+#endif
+#ifdef CONFIG_SCB0_MI3
+	{ REG_SCB0_ARBR3, REG_SCB0_ARBW3, 32, {
+		CONFIG_SCB0_MI3_SLOT0,
+		CONFIG_SCB0_MI3_SLOT1,
+		CONFIG_SCB0_MI3_SLOT2,
+		CONFIG_SCB0_MI3_SLOT3,
+		CONFIG_SCB0_MI3_SLOT4,
+		CONFIG_SCB0_MI3_SLOT5,
+		CONFIG_SCB0_MI3_SLOT6,
+		CONFIG_SCB0_MI3_SLOT7,
+		CONFIG_SCB0_MI3_SLOT8,
+		CONFIG_SCB0_MI3_SLOT9,
+		CONFIG_SCB0_MI3_SLOT10,
+		CONFIG_SCB0_MI3_SLOT11,
+		CONFIG_SCB0_MI3_SLOT12,
+		CONFIG_SCB0_MI3_SLOT13,
+		CONFIG_SCB0_MI3_SLOT14,
+		CONFIG_SCB0_MI3_SLOT15,
+		CONFIG_SCB0_MI3_SLOT16,
+		CONFIG_SCB0_MI3_SLOT17,
+		CONFIG_SCB0_MI3_SLOT18,
+		CONFIG_SCB0_MI3_SLOT19,
+		CONFIG_SCB0_MI3_SLOT20,
+		CONFIG_SCB0_MI3_SLOT21,
+		CONFIG_SCB0_MI3_SLOT22,
+		CONFIG_SCB0_MI3_SLOT23,
+		CONFIG_SCB0_MI3_SLOT24,
+		CONFIG_SCB0_MI3_SLOT25,
+		CONFIG_SCB0_MI3_SLOT26,
+		CONFIG_SCB0_MI3_SLOT27,
+		CONFIG_SCB0_MI3_SLOT28,
+		CONFIG_SCB0_MI3_SLOT29,
+		CONFIG_SCB0_MI3_SLOT30,
+		CONFIG_SCB0_MI3_SLOT31
+		},
+	},
+#endif
+#ifdef CONFIG_SCB0_MI4
+	{ REG_SCB0_ARBR4, REG_SCB4_ARBW0, 32, {
+		CONFIG_SCB0_MI4_SLOT0,
+		CONFIG_SCB0_MI4_SLOT1,
+		CONFIG_SCB0_MI4_SLOT2,
+		CONFIG_SCB0_MI4_SLOT3,
+		CONFIG_SCB0_MI4_SLOT4,
+		CONFIG_SCB0_MI4_SLOT5,
+		CONFIG_SCB0_MI4_SLOT6,
+		CONFIG_SCB0_MI4_SLOT7,
+		CONFIG_SCB0_MI4_SLOT8,
+		CONFIG_SCB0_MI4_SLOT9,
+		CONFIG_SCB0_MI4_SLOT10,
+		CONFIG_SCB0_MI4_SLOT11,
+		CONFIG_SCB0_MI4_SLOT12,
+		CONFIG_SCB0_MI4_SLOT13,
+		CONFIG_SCB0_MI4_SLOT14,
+		CONFIG_SCB0_MI4_SLOT15,
+		CONFIG_SCB0_MI4_SLOT16,
+		CONFIG_SCB0_MI4_SLOT17,
+		CONFIG_SCB0_MI4_SLOT18,
+		CONFIG_SCB0_MI4_SLOT19,
+		CONFIG_SCB0_MI4_SLOT20,
+		CONFIG_SCB0_MI4_SLOT21,
+		CONFIG_SCB0_MI4_SLOT22,
+		CONFIG_SCB0_MI4_SLOT23,
+		CONFIG_SCB0_MI4_SLOT24,
+		CONFIG_SCB0_MI4_SLOT25,
+		CONFIG_SCB0_MI4_SLOT26,
+		CONFIG_SCB0_MI4_SLOT27,
+		CONFIG_SCB0_MI4_SLOT28,
+		CONFIG_SCB0_MI4_SLOT29,
+		CONFIG_SCB0_MI4_SLOT30,
+		CONFIG_SCB0_MI4_SLOT31
+		},
+	},
+#endif
+#ifdef CONFIG_SCB0_MI5
+	{ REG_SCB0_ARBR5, REG_SCB0_ARBW5, 16, {
+		CONFIG_SCB0_MI5_SLOT0,
+		CONFIG_SCB0_MI5_SLOT1,
+		CONFIG_SCB0_MI5_SLOT2,
+		CONFIG_SCB0_MI5_SLOT3,
+		CONFIG_SCB0_MI5_SLOT4,
+		CONFIG_SCB0_MI5_SLOT5,
+		CONFIG_SCB0_MI5_SLOT6,
+		CONFIG_SCB0_MI5_SLOT7,
+		CONFIG_SCB0_MI5_SLOT8,
+		CONFIG_SCB0_MI5_SLOT9,
+		CONFIG_SCB0_MI5_SLOT10,
+		CONFIG_SCB0_MI5_SLOT11,
+		CONFIG_SCB0_MI5_SLOT12,
+		CONFIG_SCB0_MI5_SLOT13,
+		CONFIG_SCB0_MI5_SLOT14,
+		CONFIG_SCB0_MI5_SLOT15
+		},
+	},
+#endif
+#ifdef CONFIG_SCB1_MI0
+	{ REG_SCB1_ARBR0, REG_SCB1_ARBW0, 20, {
+		CONFIG_SCB1_MI0_SLOT0,
+		CONFIG_SCB1_MI0_SLOT1,
+		CONFIG_SCB1_MI0_SLOT2,
+		CONFIG_SCB1_MI0_SLOT3,
+		CONFIG_SCB1_MI0_SLOT4,
+		CONFIG_SCB1_MI0_SLOT5,
+		CONFIG_SCB1_MI0_SLOT6,
+		CONFIG_SCB1_MI0_SLOT7,
+		CONFIG_SCB1_MI0_SLOT8,
+		CONFIG_SCB1_MI0_SLOT9,
+		CONFIG_SCB1_MI0_SLOT10,
+		CONFIG_SCB1_MI0_SLOT11,
+		CONFIG_SCB1_MI0_SLOT12,
+		CONFIG_SCB1_MI0_SLOT13,
+		CONFIG_SCB1_MI0_SLOT14,
+		CONFIG_SCB1_MI0_SLOT15,
+		CONFIG_SCB1_MI0_SLOT16,
+		CONFIG_SCB1_MI0_SLOT17,
+		CONFIG_SCB1_MI0_SLOT18,
+		CONFIG_SCB1_MI0_SLOT19
+		},
+	},
+#endif
+#ifdef CONFIG_SCB2_MI0
+	{ REG_SCB2_ARBR0, REG_SCB2_ARBW0, 10, {
+		CONFIG_SCB2_MI0_SLOT0,
+		CONFIG_SCB2_MI0_SLOT1,
+		CONFIG_SCB2_MI0_SLOT2,
+		CONFIG_SCB2_MI0_SLOT3,
+		CONFIG_SCB2_MI0_SLOT4,
+		CONFIG_SCB2_MI0_SLOT5,
+		CONFIG_SCB2_MI0_SLOT6,
+		CONFIG_SCB2_MI0_SLOT7,
+		CONFIG_SCB2_MI0_SLOT8,
+		CONFIG_SCB2_MI0_SLOT9
+		},
+	},
+#endif
+#ifdef CONFIG_SCB3_MI0
+	{ REG_SCB3_ARBR0, REG_SCB3_ARBW0, 16, {
+		CONFIG_SCB3_MI0_SLOT0,
+		CONFIG_SCB3_MI0_SLOT1,
+		CONFIG_SCB3_MI0_SLOT2,
+		CONFIG_SCB3_MI0_SLOT3,
+		CONFIG_SCB3_MI0_SLOT4,
+		CONFIG_SCB3_MI0_SLOT5,
+		CONFIG_SCB3_MI0_SLOT6,
+		CONFIG_SCB3_MI0_SLOT7,
+		CONFIG_SCB3_MI0_SLOT8,
+		CONFIG_SCB3_MI0_SLOT9,
+		CONFIG_SCB3_MI0_SLOT10,
+		CONFIG_SCB3_MI0_SLOT11,
+		CONFIG_SCB3_MI0_SLOT12,
+		CONFIG_SCB3_MI0_SLOT13,
+		CONFIG_SCB3_MI0_SLOT14,
+		CONFIG_SCB3_MI0_SLOT15
+		},
+	},
+#endif
+#ifdef CONFIG_SCB4_MI0
+	{ REG_SCB4_ARBR0, REG_SCB4_ARBW0, 16, {
+		CONFIG_SCB4_MI0_SLOT0,
+		CONFIG_SCB4_MI0_SLOT1,
+		CONFIG_SCB4_MI0_SLOT2,
+		CONFIG_SCB4_MI0_SLOT3,
+		CONFIG_SCB4_MI0_SLOT4,
+		CONFIG_SCB4_MI0_SLOT5,
+		CONFIG_SCB4_MI0_SLOT6,
+		CONFIG_SCB4_MI0_SLOT7,
+		CONFIG_SCB4_MI0_SLOT8,
+		CONFIG_SCB4_MI0_SLOT9,
+		CONFIG_SCB4_MI0_SLOT10,
+		CONFIG_SCB4_MI0_SLOT11,
+		CONFIG_SCB4_MI0_SLOT12,
+		CONFIG_SCB4_MI0_SLOT13,
+		CONFIG_SCB4_MI0_SLOT14,
+		CONFIG_SCB4_MI0_SLOT15
+		},
+	},
+#endif
+#ifdef CONFIG_SCB5_MI0
+	{ REG_SCB5_ARBR0, REG_SCB5_ARBW0, 8, {
+		CONFIG_SCB5_MI0_SLOT0,
+		CONFIG_SCB5_MI0_SLOT1,
+		CONFIG_SCB5_MI0_SLOT2,
+		CONFIG_SCB5_MI0_SLOT3,
+		CONFIG_SCB5_MI0_SLOT4,
+		CONFIG_SCB5_MI0_SLOT5,
+		CONFIG_SCB5_MI0_SLOT6,
+		CONFIG_SCB5_MI0_SLOT7
+		},
+	},
+#endif
+#ifdef CONFIG_SCB6_MI0
+	{ REG_SCB6_ARBR0, REG_SCB6_ARBW0, 4, {
+		CONFIG_SCB6_MI0_SLOT0,
+		CONFIG_SCB6_MI0_SLOT1,
+		CONFIG_SCB6_MI0_SLOT2,
+		CONFIG_SCB6_MI0_SLOT3
+		},
+	},
+#endif
+#ifdef CONFIG_SCB7_MI0
+	{ REG_SCB7_ARBR0, REG_SCB7_ARBW0, 6, {
+		CONFIG_SCB7_MI0_SLOT0,
+		CONFIG_SCB7_MI0_SLOT1,
+		CONFIG_SCB7_MI0_SLOT2,
+		CONFIG_SCB7_MI0_SLOT3,
+		CONFIG_SCB7_MI0_SLOT4,
+		CONFIG_SCB7_MI0_SLOT5
+		},
+	},
+#endif
+#ifdef CONFIG_SCB8_MI0
+	{ REG_SCB8_ARBR0, REG_SCB8_ARBW0, 8, {
+		CONFIG_SCB8_MI0_SLOT0,
+		CONFIG_SCB8_MI0_SLOT1,
+		CONFIG_SCB8_MI0_SLOT2,
+		CONFIG_SCB8_MI0_SLOT3,
+		CONFIG_SCB8_MI0_SLOT4,
+		CONFIG_SCB8_MI0_SLOT5,
+		CONFIG_SCB8_MI0_SLOT6,
+		CONFIG_SCB8_MI0_SLOT7
+		},
+	},
+#endif
+#ifdef CONFIG_SCB9_MI0
+	{ REG_SCB9_ARBR0, REG_SCB9_ARBW0, 10, {
+		CONFIG_SCB9_MI0_SLOT0,
+		CONFIG_SCB9_MI0_SLOT1,
+		CONFIG_SCB9_MI0_SLOT2,
+		CONFIG_SCB9_MI0_SLOT3,
+		CONFIG_SCB9_MI0_SLOT4,
+		CONFIG_SCB9_MI0_SLOT5,
+		CONFIG_SCB9_MI0_SLOT6,
+		CONFIG_SCB9_MI0_SLOT7,
+		CONFIG_SCB9_MI0_SLOT8,
+		CONFIG_SCB9_MI0_SLOT9
+		},
+	},
+#endif
+	{ 0, }
+};
diff --git a/arch/blackfin/mach-common/Makefile b/arch/blackfin/mach-common/Makefile
index 675466d490d4..f09979204040 100644
--- a/arch/blackfin/mach-common/Makefile
+++ b/arch/blackfin/mach-common/Makefile
@@ -10,6 +10,7 @@ obj-$(CONFIG_PM)          += pm.o
 ifneq ($(CONFIG_BF60x),y)
 obj-$(CONFIG_PM)	  += dpmc_modes.o
 endif
+obj-$(CONFIG_SCB_PRIORITY)	+= scb-init.o
 obj-$(CONFIG_CPU_VOLTAGE) += dpmc.o
 obj-$(CONFIG_SMP)         += smp.o
 obj-$(CONFIG_BFIN_KERNEL_CLOCK) += clocks-init.o
diff --git a/arch/blackfin/mach-common/scb-init.c b/arch/blackfin/mach-common/scb-init.c
new file mode 100644
index 000000000000..2cbfb0b5679e
--- /dev/null
+++ b/arch/blackfin/mach-common/scb-init.c
@@ -0,0 +1,53 @@
+/*
+ * arch/blackfin/mach-common/scb-init.c - reprogram system cross bar priority
+ *
+ * Copyright 2012 Analog Devices Inc.
+ *
+ * Licensed under the GPL-2 or later.
+ */
+
+#include <linux/init.h>
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <asm/scb.h>
+
+__attribute__((l1_text))
+inline void scb_mi_write(unsigned long scb_mi_arbw, unsigned int slots,
+		unsigned char *scb_mi_prio)
+{
+	unsigned int i;
+
+	for (i = 0; i < slots; ++i)
+		bfin_write32(scb_mi_arbw, (i << SCB_SLOT_OFFSET) | scb_mi_prio[i]);
+}
+
+__attribute__((l1_text))
+inline void scb_mi_read(unsigned long scb_mi_arbw, unsigned int slots,
+		unsigned char *scb_mi_prio)
+{
+	unsigned int i;
+
+	for (i = 0; i < slots; ++i) {
+		bfin_write32(scb_mi_arbw, (0xFF << SCB_SLOT_OFFSET) | i);
+		scb_mi_prio[i] = bfin_read32(scb_mi_arbw);
+	}
+}
+
+__attribute__((l1_text))
+void init_scb(void)
+{
+	unsigned int i, j;
+	unsigned char scb_tmp_prio[32];
+
+	pr_info("Init System Crossbar\n");
+	for (i = 0; scb_data[i].scb_mi_arbr > 0; ++i) {
+
+		scb_mi_write(scb_data[i].scb_mi_arbw, scb_data[i].scb_mi_slots, scb_data[i].scb_mi_prio);
+
+		pr_debug("scb priority at 0x%lx:\n", scb_data[i].scb_mi_arbr);
+		scb_mi_read(scb_data[i].scb_mi_arbw, scb_data[i].scb_mi_slots, scb_tmp_prio);
+		for (j = 0; j < scb_data[i].scb_mi_slots; ++j)
+			pr_debug("slot %d = %d\n", j, scb_tmp_prio[j]);
+	}
+
+}
diff --git a/arch/c6x/Kconfig b/arch/c6x/Kconfig
index f6a3648f5ec3..957dd00ea561 100644
--- a/arch/c6x/Kconfig
+++ b/arch/c6x/Kconfig
@@ -10,7 +10,6 @@ config C6X
 	select GENERIC_IRQ_SHOW
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_DMA_API_DEBUG
-	select HAVE_GENERIC_HARDIRQS
 	select HAVE_MEMBLOCK
 	select SPARSE_IRQ
 	select IRQ_DOMAIN
diff --git a/arch/c6x/kernel/devicetree.c b/arch/c6x/kernel/devicetree.c
index bdb56f09d0ac..9e15ab9199b2 100644
--- a/arch/c6x/kernel/devicetree.c
+++ b/arch/c6x/kernel/devicetree.c
@@ -33,8 +33,7 @@ void __init early_init_devtree(void *params)
 
 
 #ifdef CONFIG_BLK_DEV_INITRD
-void __init early_init_dt_setup_initrd_arch(unsigned long start,
-		unsigned long end)
+void __init early_init_dt_setup_initrd_arch(u64 start, u64 end)
 {
 	initrd_start = (unsigned long)__va(start);
 	initrd_end = (unsigned long)__va(end);
@@ -46,8 +45,3 @@ void __init early_init_dt_add_memory_arch(u64 base, u64 size)
 {
 	c6x_add_memory(base, size);
 }
-
-void * __init early_init_dt_alloc_memory_arch(u64 size, u64 align)
-{
-	return __va(memblock_alloc(size, align));
-}
diff --git a/arch/cris/Kconfig b/arch/cris/Kconfig
index 3201ddb8da6a..02380bed189c 100644
--- a/arch/cris/Kconfig
+++ b/arch/cris/Kconfig
@@ -41,7 +41,6 @@ config CRIS
 	default y
 	select HAVE_IDE
 	select GENERIC_ATOMIC64
-	select HAVE_GENERIC_HARDIRQS
 	select HAVE_UID16
 	select VIRT_TO_BUS
 	select ARCH_WANT_IPC_PARSE_VERSION
@@ -99,9 +98,6 @@ config ETRAX_KMALLOCED_MODULES
 	help
 	  Enable module allocation with kmalloc instead of vmalloc.
 
-config OOM_REBOOT
-       bool "Enable reboot at out of memory"
-
 source "kernel/Kconfig.preempt"
 
 source mm/Kconfig
@@ -175,12 +171,6 @@ config ETRAX_FLASH_BUSWIDTH
 	help
 	  Width in bytes of the NOR Flash bus (1, 2 or 4). Is usually 2.
 
-config ETRAX_NANDFLASH_BUSWIDTH
-	int "Buswidth of NAND flash in bytes"
-	default "1"
-	help
-	  Width in bytes of the NAND flash (1 or 2).
-
 config ETRAX_FLASH1_SIZE
        int "FLASH1 size (dec, in MB. 0 = Unknown)"
        default "0"
@@ -272,38 +262,6 @@ config ETRAX_AXISFLASHMAP
 	  This option enables MTD mapping of flash devices.  Needed to use
 	  flash memories.  If unsure, say Y.
 
-config ETRAX_RTC
-	bool "Real Time Clock support"
-	depends on ETRAX_I2C
-	help
-	  Enables drivers for the Real-Time Clock battery-backed chips on
-	  some products. The kernel reads the time when booting, and
-	  the date can be set using ioctl(fd, RTC_SET_TIME, &rt) with rt a
-	  rtc_time struct (see <file:arch/cris/include/asm/rtc.h>) on the
-	  /dev/rtc device.  You can check the time with cat /proc/rtc, but
-	  normal time reading should be done using libc function time and
-	  friends.
-
-choice
-	prompt "RTC chip"
-	depends on ETRAX_RTC
-	default ETRAX_DS1302
-
-config ETRAX_DS1302
-	depends on ETRAX_ARCH_V10
-	bool "DS1302"
-	help
-	  Enables the driver for the DS1302 Real-Time Clock battery-backed
-	  chip on some products.
-
-config ETRAX_PCF8563
-	bool "PCF8563"
-	help
-	  Enables the driver for the PCF8563 Real-Time Clock battery-backed
-	  chip on some products.
-
-endchoice
-
 config ETRAX_SYNCHRONOUS_SERIAL
 	bool "Synchronous serial-port support"
 	help
@@ -578,26 +536,6 @@ config ETRAX_SERIAL_PORT3_DMA5_IN
 	depends on ETRAX_ARCH_V10
 	bool "DMA 5"
 
-config ETRAX_SERIAL_PORT3_DMA9_IN
-	bool "Ser3 uses DMA9 for input"
-	depends on ETRAXFS
-	help
-	  Enables the DMA9 input channel for ser3 (ttyS3).
-	  If you do not enable DMA, an interrupt for each character will be
-	  used when receiving data.
-	  Normally you want to use DMA, unless you use the DMA channel for
-	  something else.
-
-config ETRAX_SERIAL_PORT3_DMA3_IN
-	bool "Ser3 uses DMA3 for input"
-	depends on CRIS_MACH_ARTPEC3
-	help
-	  Enables the DMA3 input channel for ser3 (ttyS3).
-	  If you do not enable DMA, an interrupt for each character will be
-	  used when receiving data.
-	  Normally you want to use DMA, unless you use the DMA channel for
-	  something else.
-
 endchoice
 
 choice
@@ -615,26 +553,6 @@ config ETRAX_SERIAL_PORT3_DMA4_OUT
 	depends on ETRAX_ARCH_V10
 	bool "DMA 4"
 
-config ETRAX_SERIAL_PORT3_DMA8_OUT
-	bool "Ser3 uses DMA8 for output"
-	depends on ETRAXFS
-	help
-	  Enables the DMA8 output channel for ser3 (ttyS3).
-	  If you do not enable DMA, an interrupt for each character will be
-	  used when transmitting data.
-	  Normally you want to use DMA, unless you use the DMA channel for
-	  something else.
-
-config ETRAX_SERIAL_PORT3_DMA2_OUT
-	bool "Ser3 uses DMA2 for output"
-	depends on CRIS_MACH_ARTPEC3
-	help
-	  Enables the DMA2 output channel for ser3 (ttyS3).
-	  If you do not enable DMA, an interrupt for each character will be
-	  used when transmitting data.
-	  Normally you want to use DMA, unless you use the DMA channel for
-	  something else.
-
 endchoice
 
 endmenu
diff --git a/arch/cris/arch-v10/drivers/Kconfig b/arch/cris/arch-v10/drivers/Kconfig
index daf5f19b61a1..239dab0b95c1 100644
--- a/arch/cris/arch-v10/drivers/Kconfig
+++ b/arch/cris/arch-v10/drivers/Kconfig
@@ -417,16 +417,6 @@ config ETRAX_USB_HOST
 	   for CTRL and BULK traffic only, INTR traffic may work as well
 	   however (depending on the requirements of timeliness).
 
-config ETRAX_USB_HOST_PORT1
-	bool "USB port 1 enabled"
-	depends on ETRAX_USB_HOST
-	default n
-
-config ETRAX_USB_HOST_PORT2
-	bool "USB port 2 enabled"
-	depends on ETRAX_USB_HOST
-	default n
-
 config ETRAX_PTABLE_SECTOR
 	int "Byte-offset of partition table sector"
 	depends on ETRAX_AXISFLASHMAP
@@ -527,19 +517,6 @@ config ETRAX_GPIO
 	  Remember that you need to setup the port directions appropriately in
 	  the General configuration.
 
-config ETRAX_PA_BUTTON_BITMASK
-	hex "PA-buttons bitmask"
-	depends on ETRAX_GPIO
-	default "02"
-	help
-	  This is a bitmask with information about what bits on PA that
-	  are used for buttons.
-	  Most products has a so called TEST button on PA1, if that's true
-	  use 02 here.
-	  Use 00 if there are no buttons on PA.
-	  If the bitmask is <> 00 a button driver will be included in the gpio
-	  driver. ETRAX general I/O support must be enabled.
-
 config ETRAX_PA_CHANGEABLE_DIR
 	hex "PA user changeable dir mask"
 	depends on ETRAX_GPIO
@@ -580,51 +557,4 @@ config ETRAX_PB_CHANGEABLE_BITS
 	  Bit set = changeable.
 	  You probably want 00 here.
 
-config ETRAX_DS1302_RST_ON_GENERIC_PORT
-	bool "DS1302 RST on Generic Port"
-	depends on ETRAX_DS1302
-	help
-	  If your product has the RST signal line for the DS1302 RTC on the
-	  Generic Port then say Y here, otherwise leave it as N in which
-	  case the RST signal line is assumed to be connected to Port PB
-	  (just like the SCL and SDA lines).
-
-config ETRAX_DS1302_RSTBIT
-	int "DS1302 RST bit number"
-	depends on ETRAX_DS1302
-	default "2"
-	help
-	  This is the bit number for the RST signal line of the DS1302 RTC on
-	  the selected port. If you have selected the generic port then it
-	  should be bit 27, otherwise your best bet is bit 5.
-
-config ETRAX_DS1302_SCLBIT
-	int "DS1302 SCL bit number"
-	depends on ETRAX_DS1302
-	default "1"
-	help
-	  This is the bit number for the SCL signal line of the DS1302 RTC on
-	  Port PB. This is probably best left at 3.
-
-config ETRAX_DS1302_SDABIT
-	int "DS1302 SDA bit number"
-	depends on ETRAX_DS1302
-	default "0"
-	help
-	  This is the bit number for the SDA signal line of the DS1302 RTC on
-	  Port PB. This is probably best left at 2.
-
-config ETRAX_DS1302_TRICKLE_CHARGE
-	int "DS1302 Trickle charger value"
-	depends on ETRAX_DS1302
-	default "0"
-	help
-	  This controls the initial value of the trickle charge register.
-	  0 = disabled (use this if you are unsure or have a non rechargeable battery)
-	  Otherwise the following values can be OR:ed together to control the
-	  charge current:
-	  1 = 2kohm, 2 = 4kohm, 3 = 4kohm
-	  4 = 1 diode, 8 = 2 diodes
-	  Allowed values are (increasing current): 0, 11, 10, 9, 7, 6, 5
-
 endif
diff --git a/arch/cris/arch-v10/drivers/Makefile b/arch/cris/arch-v10/drivers/Makefile
index 44bf2e88c26e..e5c13183b97c 100644
--- a/arch/cris/arch-v10/drivers/Makefile
+++ b/arch/cris/arch-v10/drivers/Makefile
@@ -6,7 +6,5 @@ obj-$(CONFIG_ETRAX_AXISFLASHMAP)	+= axisflashmap.o
 obj-$(CONFIG_ETRAX_I2C)			+= i2c.o
 obj-$(CONFIG_ETRAX_I2C_EEPROM)		+= eeprom.o
 obj-$(CONFIG_ETRAX_GPIO)		+= gpio.o
-obj-$(CONFIG_ETRAX_DS1302)		+= ds1302.o
-obj-$(CONFIG_ETRAX_PCF8563)		+= pcf8563.o
 obj-$(CONFIG_ETRAX_SYNCHRONOUS_SERIAL)	+= sync_serial.o
 
diff --git a/arch/cris/arch-v32/drivers/Kconfig b/arch/cris/arch-v32/drivers/Kconfig
index 1d866d3ee2f8..6792503aaf79 100644
--- a/arch/cris/arch-v32/drivers/Kconfig
+++ b/arch/cris/arch-v32/drivers/Kconfig
@@ -19,64 +19,6 @@ config ETRAX_NO_PHY
 	  switch. This option should normally be disabled. If enabled,
 	  speed and duplex will be locked to 100 Mbit and full duplex.
 
-config ETRAX_ETHERNET_IFACE0
-	depends on ETRAX_ETHERNET
-	bool "Enable network interface 0"
-
-config ETRAX_ETHERNET_IFACE1
-	depends on (ETRAX_ETHERNET && ETRAXFS)
-	bool "Enable network interface 1 (uses DMA6 and DMA7)"
-
-config ETRAX_ETHERNET_GBIT
-	depends on (ETRAX_ETHERNET && CRIS_MACH_ARTPEC3)
-	bool "Enable gigabit Ethernet support"
-
-choice
-	prompt "Eth0 led group"
-	depends on ETRAX_ETHERNET_IFACE0
-	default ETRAX_ETH0_USE_LEDGRP0
-
-config ETRAX_ETH0_USE_LEDGRP0
-	bool "Use LED grp 0"
-	depends on ETRAX_NBR_LED_GRP_ONE || ETRAX_NBR_LED_GRP_TWO
-	help
-	  Use LED grp 0 for eth0
-
-config ETRAX_ETH0_USE_LEDGRP1
-	bool "Use LED grp 1"
-	depends on ETRAX_NBR_LED_GRP_TWO
-	help
-	  Use LED grp 1 for eth0
-
-config ETRAX_ETH0_USE_LEDGRPNULL
-	bool "Use no LEDs for eth0"
-	help
-	  Use no LEDs for eth0
-endchoice
-
-choice
-	prompt "Eth1 led group"
-	depends on ETRAX_ETHERNET_IFACE1
-	default ETRAX_ETH1_USE_LEDGRP1
-
-config ETRAX_ETH1_USE_LEDGRP0
-	bool "Use LED grp 0"
-	depends on ETRAX_NBR_LED_GRP_ONE || ETRAX_NBR_LED_GRP_TWO
-	help
-	  Use LED grp 0 for eth1
-
-config ETRAX_ETH1_USE_LEDGRP1
-	bool "Use LED grp 1"
-	depends on ETRAX_NBR_LED_GRP_TWO
-	help
-	  Use LED grp 1 for eth1
-
-config ETRAX_ETH1_USE_LEDGRPNULL
-	bool "Use no LEDs for eth1"
-	help
-	  Use no LEDs for eth1
-endchoice
-
 config ETRAXFS_SERIAL
 	bool "Serial-port support"
 	depends on ETRAX_ARCH_V32
@@ -108,261 +50,24 @@ config ETRAX_SERIAL_PORT0
 	  if you do not need DMA to something else.
 	  ser0 can use dma4 or dma6 for output and dma5 or dma7 for input.
 
-choice
-	prompt "Ser0 default port type "
-	depends on ETRAX_SERIAL_PORT0
-	default ETRAX_SERIAL_PORT0_TYPE_232
-	help
-	  Type of serial port.
-
-config ETRAX_SERIAL_PORT0_TYPE_232
-	bool "Ser0 is a RS-232 port"
-	help
-	  Configure serial port 0 to be a RS-232 port.
-
-config ETRAX_SERIAL_PORT0_TYPE_485HD
-	bool "Ser0 is a half duplex RS-485 port"
-	depends on ETRAX_RS485
-	help
-	  Configure serial port 0 to be a half duplex (two wires) RS-485 port.
-
-config ETRAX_SERIAL_PORT0_TYPE_485FD
-	bool "Ser0 is a full duplex RS-485 port"
-	depends on ETRAX_RS485
-	help
-	  Configure serial port 0 to be a full duplex (four wires) RS-485 port.
-endchoice
-
-config ETRAX_SER0_DTR_BIT
-	string "Ser 0 DTR bit (empty = not used)"
-	depends on ETRAX_SERIAL_PORT0
-
-config ETRAX_SER0_RI_BIT
-	string "Ser 0 RI bit (empty = not used)"
-	depends on ETRAX_SERIAL_PORT0
-
-config ETRAX_SER0_DSR_BIT
-	string "Ser 0 DSR bit (empty = not used)"
-	depends on ETRAX_SERIAL_PORT0
-
-config ETRAX_SER0_CD_BIT
-	string "Ser 0 CD bit (empty = not used)"
-	depends on ETRAX_SERIAL_PORT0
-
 config ETRAX_SERIAL_PORT1
 	bool "Serial port 1 enabled"
 	depends on ETRAXFS_SERIAL
 	help
 	  Enables the ETRAX FS serial driver for ser1 (ttyS1).
 
-choice
-	prompt "Ser1 default port type"
-	depends on ETRAX_SERIAL_PORT1
-	default ETRAX_SERIAL_PORT1_TYPE_232
-	help
-	  Type of serial port.
-
-config ETRAX_SERIAL_PORT1_TYPE_232
-	bool "Ser1 is a RS-232 port"
-	help
-	  Configure serial port 1 to be a RS-232 port.
-
-config ETRAX_SERIAL_PORT1_TYPE_485HD
-	bool "Ser1 is a half duplex RS-485 port"
-	depends on ETRAX_RS485
-	help
-	  Configure serial port 1 to be a half duplex (two wires) RS-485 port.
-
-config ETRAX_SERIAL_PORT1_TYPE_485FD
-	bool "Ser1 is a full duplex RS-485 port"
-	depends on ETRAX_RS485
-	help
-	  Configure serial port 1 to be a full duplex (four wires) RS-485 port.
-endchoice
-
-config ETRAX_SER1_DTR_BIT
-	string "Ser 1 DTR bit (empty = not used)"
-	depends on ETRAX_SERIAL_PORT1
-
-config ETRAX_SER1_RI_BIT
-	string "Ser 1 RI bit (empty = not used)"
-	depends on ETRAX_SERIAL_PORT1
-
-config ETRAX_SER1_DSR_BIT
-	string "Ser 1 DSR bit (empty = not used)"
-	depends on ETRAX_SERIAL_PORT1
-
-config ETRAX_SER1_CD_BIT
-	string "Ser 1 CD bit (empty = not used)"
-	depends on ETRAX_SERIAL_PORT1
-
 config ETRAX_SERIAL_PORT2
 	bool "Serial port 2 enabled"
 	depends on ETRAXFS_SERIAL
 	help
 	  Enables the ETRAX FS serial driver for ser2 (ttyS2).
 
-choice
-	prompt "Ser2 default port type"
-	depends on ETRAX_SERIAL_PORT2
-	default ETRAX_SERIAL_PORT2_TYPE_232
-	help
-	  What DMA channel to use for ser2
-
-config ETRAX_SERIAL_PORT2_TYPE_232
-	bool "Ser2 is a RS-232 port"
-	help
-	  Configure serial port 2 to be a RS-232 port.
-
-config ETRAX_SERIAL_PORT2_TYPE_485HD
-	bool "Ser2 is a half duplex RS-485 port"
-	depends on ETRAX_RS485
-	help
-	  Configure serial port 2 to be a half duplex (two wires) RS-485 port.
-
-config ETRAX_SERIAL_PORT2_TYPE_485FD
-	bool "Ser2 is a full duplex RS-485 port"
-	depends on ETRAX_RS485
-	help
-	  Configure serial port 2 to be a full duplex (four wires) RS-485 port.
-endchoice
-
-
-config ETRAX_SER2_DTR_BIT
-	string "Ser 2 DTR bit (empty = not used)"
-	depends on ETRAX_SERIAL_PORT2
-
-config ETRAX_SER2_RI_BIT
-	string "Ser 2 RI bit (empty = not used)"
-	depends on ETRAX_SERIAL_PORT2
-
-config ETRAX_SER2_DSR_BIT
-	string "Ser 2 DSR bit (empty = not used)"
-	depends on ETRAX_SERIAL_PORT2
-
-config ETRAX_SER2_CD_BIT
-	string "Ser 2 CD bit (empty = not used)"
-	depends on ETRAX_SERIAL_PORT2
-
 config ETRAX_SERIAL_PORT3
 	bool "Serial port 3 enabled"
 	depends on ETRAXFS_SERIAL
 	help
 	  Enables the ETRAX FS serial driver for ser3 (ttyS3).
 
-choice
-	prompt "Ser3 default port type"
-	depends on ETRAX_SERIAL_PORT3
-	default ETRAX_SERIAL_PORT3_TYPE_232
-	help
-	  What DMA channel to use for ser3.
-
-config ETRAX_SERIAL_PORT3_TYPE_232
-	bool "Ser3 is a RS-232 port"
-	help
-	  Configure serial port 3 to be a RS-232 port.
-
-config ETRAX_SERIAL_PORT3_TYPE_485HD
-	bool "Ser3 is a half duplex RS-485 port"
-	depends on ETRAX_RS485
-	help
-	  Configure serial port 3 to be a half duplex (two wires) RS-485 port.
-
-config ETRAX_SERIAL_PORT3_TYPE_485FD
-	bool "Ser3 is a full duplex RS-485 port"
-	depends on ETRAX_RS485
-	help
-	  Configure serial port 3 to be a full duplex (four wires) RS-485 port.
-endchoice
-
-config ETRAX_SER3_DTR_BIT
-	string "Ser 3 DTR bit (empty = not used)"
-	depends on ETRAX_SERIAL_PORT3
-
-config ETRAX_SER3_RI_BIT
-	string "Ser 3 RI bit (empty = not used)"
-	depends on ETRAX_SERIAL_PORT3
-
-config ETRAX_SER3_DSR_BIT
-	string "Ser 3 DSR bit (empty = not used)"
-	depends on ETRAX_SERIAL_PORT3
-
-config ETRAX_SER3_CD_BIT
-	string "Ser 3 CD bit (empty = not used)"
-	depends on ETRAX_SERIAL_PORT3
-
-config ETRAX_SERIAL_PORT4
-	bool "Serial port 4 enabled"
-	depends on ETRAXFS_SERIAL && CRIS_MACH_ARTPEC3
-	help
-	  Enables the ETRAX FS serial driver for ser4 (ttyS4).
-
-choice
-	prompt "Ser4 default port type"
-	depends on ETRAX_SERIAL_PORT4
-	default ETRAX_SERIAL_PORT4_TYPE_232
-	help
-	  What DMA channel to use for ser4.
-
-config ETRAX_SERIAL_PORT4_TYPE_232
-	bool "Ser4 is a RS-232 port"
-	help
-	  Configure serial port 4 to be a RS-232 port.
-
-config ETRAX_SERIAL_PORT4_TYPE_485HD
-	bool "Ser4 is a half duplex RS-485 port"
-	depends on ETRAX_RS485
-	help
-	  Configure serial port 4 to be a half duplex (two wires) RS-485 port.
-
-config ETRAX_SERIAL_PORT4_TYPE_485FD
-	bool "Ser4 is a full duplex RS-485 port"
-	depends on ETRAX_RS485
-	help
-	  Configure serial port 4 to be a full duplex (four wires) RS-485 port.
-endchoice
-
-choice
-	prompt "Ser4 DMA in channel "
-	depends on ETRAX_SERIAL_PORT4
-	default ETRAX_SERIAL_PORT4_NO_DMA_IN
-	help
-	  What DMA channel to use for ser4.
-
-
-config ETRAX_SERIAL_PORT4_NO_DMA_IN
-	bool "Ser4 uses no DMA for input"
-	help
-	  Do not use DMA for ser4 input.
-
-config ETRAX_SERIAL_PORT4_DMA9_IN
-	bool "Ser4 uses DMA9 for input"
-	depends on ETRAX_SERIAL_PORT4
-	help
-	  Enables the DMA9 input channel for ser4 (ttyS4).
-	  If you do not enable DMA, an interrupt for each character will be
-	  used when receiving data.
-	  Normally you want to use DMA, unless you use the DMA channel for
-	  something else.
-
-endchoice
-
-config ETRAX_SER4_DTR_BIT
-	string "Ser 4 DTR bit (empty = not used)"
-	depends on ETRAX_SERIAL_PORT4
-
-config ETRAX_SER4_RI_BIT
-	string "Ser 4 RI bit (empty = not used)"
-	depends on ETRAX_SERIAL_PORT4
-
-config ETRAX_SER4_DSR_BIT
-	string "Ser 4 DSR bit (empty = not used)"
-	depends on ETRAX_SERIAL_PORT4
-
-config ETRAX_SER4_CD_BIT
-	string "Ser 4 CD bit (empty = not used)"
-	depends on ETRAX_SERIAL_PORT4
-
 config ETRAX_SYNCHRONOUS_SERIAL
 	bool "Synchronous serial-port support"
 	depends on ETRAX_ARCH_V32
@@ -703,32 +408,6 @@ config ETRAX_SPI_SSER0
 	  want to build it as a module, which will be named spi_crisv32_sser.
 	  (You need to select MMC separately.)
 
-config ETRAX_SPI_SSER0_DMA
-	bool "DMA for SPI on sser0 enabled"
-	depends on ETRAX_SPI_SSER0
-	depends on !ETRAX_SERIAL_PORT1_DMA4_OUT && !ETRAX_SERIAL_PORT1_DMA5_IN
-	default y
-	help
-	  Say Y if using DMA (dma4/dma5) for SPI on synchronous serial port 0.
-
-config ETRAX_SPI_MMC_CD_SSER0_PIN
-	string "MMC/SD card detect pin for SPI on sser0"
-	depends on ETRAX_SPI_SSER0 && MMC_SPI
-	default "pd11"
-	help
-	  The pin to use for SD/MMC card detect.  This pin should be pulled up
-	  and grounded when a card is present.  If defined as " " (space), no
-	  pin is selected.  A card must then always be inserted for proper
-	  action.
-
-config ETRAX_SPI_MMC_WP_SSER0_PIN
-	string "MMC/SD card write-protect pin for SPI on sser0"
-	depends on ETRAX_SPI_SSER0 && MMC_SPI
-	default "pd10"
-	help
-	  The pin to use for the SD/MMC write-protect signal for a memory
-	  card.  If defined as " " (space), the card is considered writable.
-
 config ETRAX_SPI_SSER1
 	tristate "SPI using synchronous serial port 1 (sser1)"
 	depends on ETRAX_SPI_MMC
@@ -742,32 +421,6 @@ config ETRAX_SPI_SSER1
 	  want to build it as a module, which will be named spi_crisv32_sser.
 	  (You need to select MMC separately.)
 
-config ETRAX_SPI_SSER1_DMA
-	bool "DMA for SPI on sser1 enabled"
-	depends on ETRAX_SPI_SSER1 && !ETRAX_ETHERNET_IFACE1
-	depends on !ETRAX_SERIAL_PORT0_DMA6_OUT && !ETRAX_SERIAL_PORT0_DMA7_IN
-	default y
-	help
-	  Say Y if using DMA (dma6/dma7) for SPI on synchronous serial port 1.
-
-config ETRAX_SPI_MMC_CD_SSER1_PIN
-	string "MMC/SD card detect pin for SPI on sser1"
-	depends on ETRAX_SPI_SSER1 && MMC_SPI
-	default "pd12"
-	help
-	  The pin to use for SD/MMC card detect.  This pin should be pulled up
-	  and grounded when a card is present.  If defined as " " (space), no
-	  pin is selected.  A card must then always be inserted for proper
-	  action.
-
-config ETRAX_SPI_MMC_WP_SSER1_PIN
-	string "MMC/SD card write-protect pin for SPI on sser1"
-	depends on ETRAX_SPI_SSER1 && MMC_SPI
-	default "pd9"
-	help
-	  The pin to use for the SD/MMC write-protect signal for a memory
-	  card.  If defined as " " (space), the card is considered writable.
-
 config ETRAX_SPI_GPIO
 	tristate "Bitbanged SPI using gpio pins"
 	depends on ETRAX_SPI_MMC
@@ -782,51 +435,4 @@ config ETRAX_SPI_GPIO
 	  Say m to build it as a module, which will be called spi_crisv32_gpio.
 	  (You need to select MMC separately.)
 
-# The default match that of sser0, only because that's how it was tested.
-config ETRAX_SPI_CS_PIN
-	string "SPI chip select pin"
-	depends on ETRAX_SPI_GPIO
-	default "pc3"
-	help
-	  The pin to use for SPI chip select.
-
-config ETRAX_SPI_CLK_PIN
-	string "SPI clock pin"
-	depends on ETRAX_SPI_GPIO
-	default "pc1"
-	help
-	  The pin to use for the SPI clock.
-
-config ETRAX_SPI_DATAIN_PIN
-	string "SPI MISO (data in) pin"
-	depends on ETRAX_SPI_GPIO
-	default "pc16"
-	help
-	  The pin to use for SPI data in from the device.
-
-config ETRAX_SPI_DATAOUT_PIN
-	string "SPI MOSI (data out) pin"
-	depends on ETRAX_SPI_GPIO
-	default "pc0"
-	help
-	  The pin to use for SPI data out to the device.
-
-config ETRAX_SPI_MMC_CD_GPIO_PIN
-	string "MMC/SD card detect pin for SPI using gpio (space for none)"
-	depends on ETRAX_SPI_GPIO && MMC_SPI
-	default "pd11"
-	help
-	  The pin to use for SD/MMC card detect.  This pin should be pulled up
-	  and grounded when a card is present.  If defined as " " (space), no
-	  pin is selected.  A card must then always be inserted for proper
-	  action.
-
-config ETRAX_SPI_MMC_WP_GPIO_PIN
-	string "MMC/SD card write-protect pin for SPI using gpio (space for none)"
-	depends on ETRAX_SPI_GPIO && MMC_SPI
-	default "pd10"
-	help
-	  The pin to use for the SD/MMC write-protect signal for a memory
-	  card.  If defined as " " (space), the card is considered writable.
-
 endif
diff --git a/arch/cris/arch-v32/mach-a3/Kconfig b/arch/cris/arch-v32/mach-a3/Kconfig
index 7796aafc711e..87547271a595 100644
--- a/arch/cris/arch-v32/mach-a3/Kconfig
+++ b/arch/cris/arch-v32/mach-a3/Kconfig
@@ -15,10 +15,6 @@ config ETRAX_SERIAL_PORTS
        int
        default 5
 
-config ETRAX_DDR
-       bool
-       default y
-
 config ETRAX_DDR2_MRS
 	hex "DDR2 MRS"
 	default "0"
diff --git a/arch/cris/include/asm/processor.h b/arch/cris/include/asm/processor.h
index c0a29b96b92b..15b815df29c1 100644
--- a/arch/cris/include/asm/processor.h
+++ b/arch/cris/include/asm/processor.h
@@ -47,7 +47,6 @@ struct task_struct;
  */
 
 #define task_pt_regs(task) user_regs(task_thread_info(task))
-#define current_regs() task_pt_regs(current)
 
 unsigned long get_wchan(struct task_struct *p);
 
diff --git a/arch/cris/include/uapi/asm/kvm_para.h b/arch/cris/include/uapi/asm/kvm_para.h
new file mode 100644
index 000000000000..14fab8f0b957
--- /dev/null
+++ b/arch/cris/include/uapi/asm/kvm_para.h
@@ -0,0 +1 @@
+#include <asm-generic/kvm_para.h>
diff --git a/arch/cris/mm/fault.c b/arch/cris/mm/fault.c
index 73312ab6c696..1790f22e71a2 100644
--- a/arch/cris/mm/fault.c
+++ b/arch/cris/mm/fault.c
@@ -58,8 +58,7 @@ do_page_fault(unsigned long address, struct pt_regs *regs,
 	struct vm_area_struct * vma;
 	siginfo_t info;
 	int fault;
-	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
-				((writeaccess & 1) ? FAULT_FLAG_WRITE : 0);
+	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
 
 	D(printk(KERN_DEBUG
 		 "Page fault for %lX on %X at %lX, prot %d write %d\n",
@@ -117,6 +116,8 @@ do_page_fault(unsigned long address, struct pt_regs *regs,
 	if (in_atomic() || !mm)
 		goto no_context;
 
+	if (user_mode(regs))
+		flags |= FAULT_FLAG_USER;
 retry:
 	down_read(&mm->mmap_sem);
 	vma = find_vma(mm, address);
@@ -155,6 +156,7 @@ retry:
 	} else if (writeaccess == 1) {
 		if (!(vma->vm_flags & VM_WRITE))
 			goto bad_area;
+		flags |= FAULT_FLAG_WRITE;
 	} else {
 		if (!(vma->vm_flags & (VM_READ | VM_EXEC)))
 			goto bad_area;
diff --git a/arch/frv/Kconfig b/arch/frv/Kconfig
index 4b6628ea381e..34aa19352dc1 100644
--- a/arch/frv/Kconfig
+++ b/arch/frv/Kconfig
@@ -5,7 +5,6 @@ config FRV
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_PERF_EVENTS
 	select HAVE_UID16
-	select HAVE_GENERIC_HARDIRQS
 	select VIRT_TO_BUS
 	select GENERIC_IRQ_SHOW
 	select HAVE_DEBUG_BUGVERBOSE
diff --git a/arch/frv/mb93090-mb00/pci-vdk.c b/arch/frv/mb93090-mb00/pci-vdk.c
index 0aa35f0eb0db..deb67843693c 100644
--- a/arch/frv/mb93090-mb00/pci-vdk.c
+++ b/arch/frv/mb93090-mb00/pci-vdk.c
@@ -320,7 +320,7 @@ DECLARE_PCI_FIXUP_HEADER(PCI_ANY_ID, PCI_ANY_ID, pci_fixup_ide_bases);
  *  are examined.
  */
 
-void __init pcibios_fixup_bus(struct pci_bus *bus)
+void pcibios_fixup_bus(struct pci_bus *bus)
 {
 #if 0
 	printk("### PCIBIOS_FIXUP_BUS(%d)\n",bus->number);
diff --git a/arch/frv/mm/fault.c b/arch/frv/mm/fault.c
index 331c1e2cfb67..9a66372fc7c7 100644
--- a/arch/frv/mm/fault.c
+++ b/arch/frv/mm/fault.c
@@ -34,11 +34,11 @@ asmlinkage void do_page_fault(int datammu, unsigned long esr0, unsigned long ear
 	struct vm_area_struct *vma;
 	struct mm_struct *mm;
 	unsigned long _pme, lrai, lrad, fixup;
+	unsigned long flags = 0;
 	siginfo_t info;
 	pgd_t *pge;
 	pud_t *pue;
 	pte_t *pte;
-	int write;
 	int fault;
 
 #if 0
@@ -81,6 +81,9 @@ asmlinkage void do_page_fault(int datammu, unsigned long esr0, unsigned long ear
 	if (in_atomic() || !mm)
 		goto no_context;
 
+	if (user_mode(__frame))
+		flags |= FAULT_FLAG_USER;
+
 	down_read(&mm->mmap_sem);
 
 	vma = find_vma(mm, ear0);
@@ -129,7 +132,6 @@ asmlinkage void do_page_fault(int datammu, unsigned long esr0, unsigned long ear
  */
  good_area:
 	info.si_code = SEGV_ACCERR;
-	write = 0;
 	switch (esr0 & ESR0_ATXC) {
 	default:
 		/* handle write to write protected page */
@@ -140,7 +142,7 @@ asmlinkage void do_page_fault(int datammu, unsigned long esr0, unsigned long ear
 #endif
 		if (!(vma->vm_flags & VM_WRITE))
 			goto bad_area;
-		write = 1;
+		flags |= FAULT_FLAG_WRITE;
 		break;
 
 		 /* handle read from protected page */
@@ -162,7 +164,7 @@ asmlinkage void do_page_fault(int datammu, unsigned long esr0, unsigned long ear
 	 * make sure we exit gracefully rather than endlessly redo
 	 * the fault.
 	 */
-	fault = handle_mm_fault(mm, vma, ear0, write ? FAULT_FLAG_WRITE : 0);
+	fault = handle_mm_fault(mm, vma, ear0, flags);
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
diff --git a/arch/h8300/Kconfig b/arch/h8300/Kconfig
index 3d6759ee382f..24b1dc2564f1 100644
--- a/arch/h8300/Kconfig
+++ b/arch/h8300/Kconfig
@@ -2,7 +2,6 @@ config H8300
 	bool
 	default y
 	select HAVE_IDE
-	select HAVE_GENERIC_HARDIRQS
 	select GENERIC_ATOMIC64
 	select HAVE_UID16
 	select VIRT_TO_BUS
diff --git a/arch/hexagon/Kconfig b/arch/hexagon/Kconfig
index 77d442ab28c8..99041b07e610 100644
--- a/arch/hexagon/Kconfig
+++ b/arch/hexagon/Kconfig
@@ -15,7 +15,6 @@ config HEXAGON
 	# select GENERIC_PENDING_IRQ if SMP
 	select GENERIC_ATOMIC64
 	select HAVE_PERF_EVENTS
-	select HAVE_GENERIC_HARDIRQS
 	# GENERIC_ALLOCATOR is used by dma_alloc_coherent()
 	select GENERIC_ALLOCATOR
 	select GENERIC_IRQ_SHOW
diff --git a/arch/hexagon/mm/vm_fault.c b/arch/hexagon/mm/vm_fault.c
index 1bd276dbec7d..8704c9320032 100644
--- a/arch/hexagon/mm/vm_fault.c
+++ b/arch/hexagon/mm/vm_fault.c
@@ -53,8 +53,7 @@ void do_page_fault(unsigned long address, long cause, struct pt_regs *regs)
 	int si_code = SEGV_MAPERR;
 	int fault;
 	const struct exception_table_entry *fixup;
-	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
-				 (cause > 0 ? FAULT_FLAG_WRITE : 0);
+	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
 
 	/*
 	 * If we're in an interrupt or have no user context,
@@ -65,6 +64,8 @@ void do_page_fault(unsigned long address, long cause, struct pt_regs *regs)
 
 	local_irq_enable();
 
+	if (user_mode(regs))
+		flags |= FAULT_FLAG_USER;
 retry:
 	down_read(&mm->mmap_sem);
 	vma = find_vma(mm, address);
@@ -96,6 +97,7 @@ good_area:
 	case FLT_STORE:
 		if (!(vma->vm_flags & VM_WRITE))
 			goto bad_area;
+		flags |= FAULT_FLAG_WRITE;
 		break;
 	}
 
diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index 5a768ad8e893..7740ab10a171 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -9,7 +9,6 @@ config IA64
 	select PCI if (!IA64_HP_SIM)
 	select ACPI if (!IA64_HP_SIM)
 	select PM if (!IA64_HP_SIM)
-	select ARCH_SUPPORTS_MSI
 	select HAVE_UNSTABLE_SCHED_CLOCK
 	select HAVE_IDE
 	select HAVE_OPROFILE
@@ -22,7 +21,6 @@ config IA64
 	select HAVE_KVM
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_DMA_API_DEBUG
-	select HAVE_GENERIC_HARDIRQS
 	select HAVE_MEMBLOCK
 	select HAVE_MEMBLOCK_NODE_MAP
 	select HAVE_VIRT_CPU_ACCOUNTING
@@ -43,6 +41,7 @@ config IA64
 	select SYSCTL_ARCH_UNALIGN_NO_WARN
 	select HAVE_MOD_ARCH_SPECIFIC
 	select MODULES_USE_ELF_RELA
+	select ARCH_USE_CMPXCHG_LOCKREF
 	default y
 	help
 	  The Itanium Processor Family is Intel's 64-bit successor to
@@ -565,9 +564,9 @@ config KEXEC
 
 	  It is an ongoing process to be certain the hardware in a machine
 	  is properly shutdown, so do not be surprised if this code does not
-	  initially work for you.  It may help to enable device hotplugging
-	  support.  As of this writing the exact hardware interface is
-	  strongly in flux, so no good recommendation can be made.
+	  initially work for you.  As of this writing the exact hardware
+	  interface is strongly in flux, so no good recommendation can be
+	  made.
 
 config CRASH_DUMP
 	  bool "kernel crash dumps"
diff --git a/arch/ia64/include/asm/Kbuild b/arch/ia64/include/asm/Kbuild
index 05b03ecd7933..a3456f34f672 100644
--- a/arch/ia64/include/asm/Kbuild
+++ b/arch/ia64/include/asm/Kbuild
@@ -3,3 +3,4 @@ generic-y += clkdev.h
 generic-y += exec.h
 generic-y += kvm_para.h
 generic-y += trace_clock.h
+generic-y += vtime.h
+\ No newline at end of file
diff --git a/arch/ia64/include/asm/bitops.h b/arch/ia64/include/asm/bitops.h
index 8e20bff39f79..c27eccd33349 100644
--- a/arch/ia64/include/asm/bitops.h
+++ b/arch/ia64/include/asm/bitops.h
@@ -425,13 +425,7 @@ __fls (unsigned long x)
 
 #include <asm-generic/bitops/fls64.h>
 
-/*
- * ffs: find first bit set. This is defined the same way as the libc and
- * compiler builtin ffs routines, therefore differs in spirit from the above
- * ffz (man ffs): it operates on "int" values only and the result value is the
- * bit number + 1.  ffs(0) is defined to return zero.
- */
-#define ffs(x)	__builtin_ffs(x)
+#include <asm-generic/bitops/builtin-ffs.h>
 
 /*
  * hweightN: returns the hamming weight (i.e. the number
diff --git a/arch/ia64/include/asm/dmi.h b/arch/ia64/include/asm/dmi.h
index 1ed4c8fedb83..185d3d18d0ec 100644
--- a/arch/ia64/include/asm/dmi.h
+++ b/arch/ia64/include/asm/dmi.h
@@ -7,6 +7,6 @@
 /* Use normal IO mappings for DMI */
 #define dmi_ioremap ioremap
 #define dmi_iounmap(x,l) iounmap(x)
-#define dmi_alloc(l) kmalloc(l, GFP_ATOMIC)
+#define dmi_alloc(l) kzalloc(l, GFP_ATOMIC)
 
 #endif
diff --git a/arch/ia64/include/asm/spinlock.h b/arch/ia64/include/asm/spinlock.h
index 54ff557d474e..45698cd15b7b 100644
--- a/arch/ia64/include/asm/spinlock.h
+++ b/arch/ia64/include/asm/spinlock.h
@@ -102,6 +102,11 @@ static inline int __ticket_spin_is_contended(arch_spinlock_t *lock)
 	return ((tmp - (tmp >> TICKET_SHIFT)) & TICKET_MASK) > 1;
 }
 
+static __always_inline int arch_spin_value_unlocked(arch_spinlock_t lock)
+{
+	return !(((lock.lock >> TICKET_SHIFT) ^ lock.lock) & TICKET_MASK);
+}
+
 static inline int arch_spin_is_locked(arch_spinlock_t *lock)
 {
 	return __ticket_spin_is_locked(lock);
diff --git a/arch/ia64/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c
index 5b2dc0d10c8f..bdfd8789b376 100644
--- a/arch/ia64/kvm/kvm-ia64.c
+++ b/arch/ia64/kvm/kvm-ia64.c
@@ -1560,6 +1560,10 @@ int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages)
 	return 0;
 }
 
+void kvm_arch_memslots_updated(struct kvm *kvm)
+{
+}
+
 int kvm_arch_prepare_memory_region(struct kvm *kvm,
 		struct kvm_memory_slot *memslot,
 		struct kvm_userspace_memory_region *mem,
diff --git a/arch/ia64/mm/fault.c b/arch/ia64/mm/fault.c
index 6cf0341f978e..7225dad87094 100644
--- a/arch/ia64/mm/fault.c
+++ b/arch/ia64/mm/fault.c
@@ -90,8 +90,6 @@ ia64_do_page_fault (unsigned long address, unsigned long isr, struct pt_regs *re
 	mask = ((((isr >> IA64_ISR_X_BIT) & 1UL) << VM_EXEC_BIT)
 		| (((isr >> IA64_ISR_W_BIT) & 1UL) << VM_WRITE_BIT));
 
-	flags |= ((mask & VM_WRITE) ? FAULT_FLAG_WRITE : 0);
-
 	/* mmap_sem is performance critical.... */
 	prefetchw(&mm->mmap_sem);
 
@@ -119,6 +117,10 @@ ia64_do_page_fault (unsigned long address, unsigned long isr, struct pt_regs *re
 	if (notify_page_fault(regs, TRAP_BRKPT))
 		return;
 
+	if (user_mode(regs))
+		flags |= FAULT_FLAG_USER;
+	if (mask & VM_WRITE)
+		flags |= FAULT_FLAG_WRITE;
 retry:
 	down_read(&mm->mmap_sem);
 
diff --git a/arch/ia64/mm/hugetlbpage.c b/arch/ia64/mm/hugetlbpage.c
index 76069c18ee42..68232db98baa 100644
--- a/arch/ia64/mm/hugetlbpage.c
+++ b/arch/ia64/mm/hugetlbpage.c
@@ -114,6 +114,11 @@ int pud_huge(pud_t pud)
 	return 0;
 }
 
+int pmd_huge_support(void)
+{
+	return 0;
+}
+
 struct page *
 follow_huge_pmd(struct mm_struct *mm, unsigned long address, pmd_t *pmd, int write)
 {
diff --git a/arch/m32r/Kconfig b/arch/m32r/Kconfig
index 29a7ef4e448b..75661fbf4529 100644
--- a/arch/m32r/Kconfig
+++ b/arch/m32r/Kconfig
@@ -9,7 +9,6 @@ config M32R
 	select HAVE_KERNEL_LZMA
 	select ARCH_WANT_IPC_PARSE_VERSION
 	select HAVE_DEBUG_BUGVERBOSE
-	select HAVE_GENERIC_HARDIRQS
 	select VIRT_TO_BUS
 	select GENERIC_IRQ_PROBE
 	select GENERIC_IRQ_SHOW
diff --git a/arch/m32r/mm/fault.c b/arch/m32r/mm/fault.c
index 3cdfa9c1d091..e9c6a8014bd6 100644
--- a/arch/m32r/mm/fault.c
+++ b/arch/m32r/mm/fault.c
@@ -78,7 +78,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long error_code,
 	struct mm_struct *mm;
 	struct vm_area_struct * vma;
 	unsigned long page, addr;
-	int write;
+	unsigned long flags = 0;
 	int fault;
 	siginfo_t info;
 
@@ -117,6 +117,9 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long error_code,
 	if (in_atomic() || !mm)
 		goto bad_area_nosemaphore;
 
+	if (error_code & ACE_USERMODE)
+		flags |= FAULT_FLAG_USER;
+
 	/* When running in the kernel we expect faults to occur only to
 	 * addresses in user space.  All other faults represent errors in the
 	 * kernel and should generate an OOPS.  Unfortunately, in the case of an
@@ -166,14 +169,13 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long error_code,
  */
 good_area:
 	info.si_code = SEGV_ACCERR;
-	write = 0;
 	switch (error_code & (ACE_WRITE|ACE_PROTECTION)) {
 		default:	/* 3: write, present */
 			/* fall through */
 		case ACE_WRITE:	/* write, not present */
 			if (!(vma->vm_flags & VM_WRITE))
 				goto bad_area;
-			write++;
+			flags |= FAULT_FLAG_WRITE;
 			break;
 		case ACE_PROTECTION:	/* read, present */
 		case 0:		/* read, not present */
@@ -194,7 +196,7 @@ good_area:
 	 */
 	addr = (address & PAGE_MASK);
 	set_thread_fault_code(error_code);
-	fault = handle_mm_fault(mm, vma, addr, write ? FAULT_FLAG_WRITE : 0);
+	fault = handle_mm_fault(mm, vma, addr, flags);
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
diff --git a/arch/m68k/Kconfig b/arch/m68k/Kconfig
index 821170e5f6ed..311a300d48cc 100644
--- a/arch/m68k/Kconfig
+++ b/arch/m68k/Kconfig
@@ -4,13 +4,13 @@ config M68K
 	select HAVE_IDE
 	select HAVE_AOUT if MMU
 	select HAVE_DEBUG_BUGVERBOSE
-	select HAVE_GENERIC_HARDIRQS
 	select GENERIC_IRQ_SHOW
 	select GENERIC_ATOMIC64
 	select HAVE_UID16
 	select VIRT_TO_BUS
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG if RMW_INSNS
 	select GENERIC_CPU_DEVICES
+	select GENERIC_IOMAP
 	select GENERIC_STRNCPY_FROM_USER if MMU
 	select GENERIC_STRNLEN_USER if MMU
 	select FPU if MMU
@@ -72,7 +72,6 @@ source "kernel/Kconfig.freezer"
 config MMU
 	bool "MMU-based Paged Memory Management Support"
 	default y
-	select GENERIC_IOMAP
 	help
 	  Select if you want MMU-based virtualised addressing space
 	  support by paged memory management. If unsure, say 'Y'.
diff --git a/arch/m68k/Kconfig.machine b/arch/m68k/Kconfig.machine
index b9ab0a69561c..61dc643c0b05 100644
--- a/arch/m68k/Kconfig.machine
+++ b/arch/m68k/Kconfig.machine
@@ -150,18 +150,6 @@ config XCOPILOT_BUGS
 	help
 	  Support the bugs of Xcopilot.
 
-config UC5272
-	bool "Arcturus Networks uC5272 dimm board support"
-	depends on M5272
-	help
-	  Support for the Arcturus Networks uC5272 dimm board.
-
-config UC5282
-	bool "Arcturus Networks uC5282 board support"
-	depends on M528x
-	help
-	  Support for the Arcturus Networks uC5282 dimm board.
-
 config UCSIMM
 	bool "uCsimm module support"
 	depends on M68EZ328
@@ -205,23 +193,15 @@ config UCQUICC
 	help
 	  Support for the Lineo uCquicc board.
 
-config ARNEWSH
-	bool
-
 config ARN5206
 	bool "Arnewsh 5206 board support"
 	depends on M5206
-	select ARNEWSH
 	help
 	  Support for the Arnewsh 5206 board.
 
-config FREESCALE
-	bool
-
 config M5206eC3
 	bool "Motorola M5206eC3 board support"
 	depends on M5206e
-	select FREESCALE
 	help
 	  Support for the Motorola M5206eC3 board.
 
@@ -231,88 +211,24 @@ config ELITE
 	help
 	  Support for the Motorola M5206eLITE board.
 
-config M5208EVB
-	bool "Freescale M5208EVB board support"
-	depends on M520x
-	select FREESCALE
-	help
-	  Support for the Freescale Coldfire M5208EVB.
-
 config M5235EVB
 	bool "Freescale M5235EVB support"
 	depends on M523x
-	select FREESCALE
 	help
 	  Support for the Freescale M5235EVB board.
 
 config M5249C3
 	bool "Motorola M5249C3 board support"
 	depends on M5249
-	select FREESCALE
 	help
 	  Support for the Motorola M5249C3 board.
 
-config M5271EVB
-	bool "Freescale (Motorola) M5271EVB board support"
-	depends on M5271
-	select FREESCALE
-	help
-	  Support for the Freescale (Motorola) M5271EVB board.
-
-config M5275EVB
-	bool "Freescale (Motorola) M5275EVB board support"
-	depends on M5275
-	select FREESCALE
-	help
-	  Support for the Freescale (Motorola) M5275EVB board.
-
 config M5272C3
 	bool "Motorola M5272C3 board support"
 	depends on M5272
-	select FREESCALE
 	help
 	  Support for the Motorola M5272C3 board.
 
-config senTec
-	bool
-
-config COBRA5272
-	bool "senTec COBRA5272 board support"
-	depends on M5272
-	select senTec
-	help
-	  Support for the senTec COBRA5272 board.
-
-config AVNET
-	bool
-
-config AVNET5282
-	bool "Avnet 5282 board support"
-	depends on M528x
-	select AVNET
-	help
-	  Support for the Avnet 5282 board.
-
-config M5282EVB
-	bool "Motorola M5282EVB board support"
-	depends on M528x
-	select FREESCALE
-	help
-	  Support for the Motorola M5282EVB board.
-
-config COBRA5282
-	bool "senTec COBRA5282 board support"
-	depends on M528x
-	select senTec
-	help
-	  Support for the senTec COBRA5282 board.
-
-config SOM5282EM
-	bool "EMAC.Inc SOM5282EM board support"
-	depends on M528x
-	help
-	  Support for the EMAC.Inc SOM5282EM module.
-
 config WILDFIRE
 	bool "Intec Automation Inc. WildFire board support"
 	depends on M528x
@@ -328,14 +244,12 @@ config WILDFIREMOD
 config ARN5307
 	bool "Arnewsh 5307 board support"
 	depends on M5307
-	select ARNEWSH
 	help
 	  Support for the Arnewsh 5307 board.
 
 config M5307C3
 	bool "Motorola M5307C3 board support"
 	depends on M5307
-	select FREESCALE
 	help
 	  Support for the Motorola M5307C3 board.
 
@@ -345,30 +259,9 @@ config SECUREEDGEMP3
 	help
 	  Support for the SnapGear SecureEdge/MP3 platform.
 
-config M5329EVB
-	bool "Freescale (Motorola) M5329EVB board support"
-	depends on M532x
-	select FREESCALE
-	help
-	  Support for the Freescale (Motorola) M5329EVB board.
-
-config COBRA5329
-	bool "senTec COBRA5329 board support"
-	depends on M532x
-	help
-	  Support for the senTec COBRA5329 board.
-
-config M5373EVB
-	bool "Freescale M5373EVB board support"
-	depends on M537x
-	select FREESCALE
-	help
-	  Support for the Freescale M5373EVB board.
-
 config M5407C3
 	bool "Motorola M5407C3 board support"
 	depends on M5407
-	select FREESCALE
 	help
 	  Support for the Motorola M5407C3 board.
 
@@ -402,39 +295,12 @@ config NETtel
 	help
 	  Support for the SnapGear NETtel/SecureEdge/SnapGear boards.
 
-config SNAPGEAR
-	bool "SnapGear router board support"
-	depends on NETtel
-	help
-	  Special additional support for SnapGear router boards.
-
-config SNEHA
-	bool
-
-config CPU16B
-	bool "Sneha Technologies S.L. Sarasvati board support"
-	depends on M5272
-	select SNEHA
-	help
-	  Support for the SNEHA CPU16B board.
-
 config MOD5272
 	bool "Netburner MOD-5272 board support"
 	depends on M5272
 	help
 	  Support for the Netburner MOD-5272 board.
 
-config SAVANT
-	bool
-
-config SAVANTrosie1
-	bool "Savant Rosie1 board support"
-	depends on M523x
-	select SAVANT
-	help
-	  Support for the Savant Rosie1 board.
-
-
 if !MMU || COLDFIRE
 
 comment "Machine Options"
diff --git a/arch/m68k/amiga/platform.c b/arch/m68k/amiga/platform.c
index 6083088c0cca..dacd9f911f71 100644
--- a/arch/m68k/amiga/platform.c
+++ b/arch/m68k/amiga/platform.c
@@ -56,7 +56,7 @@ static int __init amiga_init_bus(void)
 	n = AMIGAHW_PRESENT(ZORRO3) ? 4 : 2;
 	pdev = platform_device_register_simple("amiga-zorro", -1,
 					       zorro_resources, n);
-	return PTR_RET(pdev);
+	return PTR_ERR_OR_ZERO(pdev);
 }
 
 subsys_initcall(amiga_init_bus);
diff --git a/arch/m68k/emu/natfeat.c b/arch/m68k/emu/natfeat.c
index fa277aecfb78..121a6660ad4e 100644
--- a/arch/m68k/emu/natfeat.c
+++ b/arch/m68k/emu/natfeat.c
@@ -18,11 +18,11 @@
 #include <asm/machdep.h>
 #include <asm/natfeat.h>
 
-extern long nf_get_id2(const char *feature_name);
+extern long nf_get_id_phys(unsigned long feature_name);
 
 asm("\n"
-"	.global nf_get_id2,nf_call\n"
-"nf_get_id2:\n"
+"	.global nf_get_id_phys,nf_call\n"
+"nf_get_id_phys:\n"
 "	.short	0x7300\n"
 "	rts\n"
 "nf_call:\n"
@@ -31,7 +31,7 @@ asm("\n"
 "1:	moveq.l	#0,%d0\n"
 "	rts\n"
 "	.section __ex_table,\"a\"\n"
-"	.long	nf_get_id2,1b\n"
+"	.long	nf_get_id_phys,1b\n"
 "	.long	nf_call,1b\n"
 "	.previous");
 EXPORT_SYMBOL_GPL(nf_call);
@@ -46,7 +46,7 @@ long nf_get_id(const char *feature_name)
 	if (n >= sizeof(name_copy))
 		return 0;
 
-	return nf_get_id2(name_copy);
+	return nf_get_id_phys(virt_to_phys(name_copy));
 }
 EXPORT_SYMBOL_GPL(nf_get_id);
 
@@ -58,7 +58,7 @@ void nfprint(const char *fmt, ...)
 
 	va_start(ap, fmt);
 	n = vsnprintf(buf, 256, fmt, ap);
-	nf_call(nf_get_id("NF_STDERR"), buf);
+	nf_call(nf_get_id("NF_STDERR"), virt_to_phys(buf));
 	va_end(ap);
 }
 
@@ -83,7 +83,7 @@ void nf_init(void)
 	id = nf_get_id("NF_NAME");
 	if (!id)
 		return;
-	nf_call(id, buf, 256);
+	nf_call(id, virt_to_phys(buf), 256);
 	buf[255] = 0;
 
 	pr_info("NatFeats found (%s, %lu.%lu)\n", buf, version >> 16,
diff --git a/arch/m68k/emu/nfblock.c b/arch/m68k/emu/nfblock.c
index e3011338ab40..0721858fbd1e 100644
--- a/arch/m68k/emu/nfblock.c
+++ b/arch/m68k/emu/nfblock.c
@@ -41,8 +41,8 @@ static inline s32 nfhd_read_write(u32 major, u32 minor, u32 rwflag, u32 recno,
 static inline s32 nfhd_get_capacity(u32 major, u32 minor, u32 *blocks,
 				    u32 *blocksize)
 {
-	return nf_call(nfhd_id + NFHD_GET_CAPACITY, major, minor, blocks,
-		       blocksize);
+	return nf_call(nfhd_id + NFHD_GET_CAPACITY, major, minor,
+		       virt_to_phys(blocks), virt_to_phys(blocksize));
 }
 
 static LIST_HEAD(nfhd_list);
diff --git a/arch/m68k/emu/nfcon.c b/arch/m68k/emu/nfcon.c
index 6685bf45c2c3..57e8c8fb5eba 100644
--- a/arch/m68k/emu/nfcon.c
+++ b/arch/m68k/emu/nfcon.c
@@ -15,6 +15,7 @@
 #include <linux/slab.h>
 #include <linux/err.h>
 #include <linux/uaccess.h>
+#include <linux/io.h>
 
 #include <asm/natfeat.h>
 
@@ -25,17 +26,18 @@ static struct tty_driver *nfcon_tty_driver;
 static void nfputs(const char *str, unsigned int count)
 {
 	char buf[68];
+	unsigned long phys = virt_to_phys(buf);
 
 	buf[64] = 0;
 	while (count > 64) {
 		memcpy(buf, str, 64);
-		nf_call(stderr_id, buf);
+		nf_call(stderr_id, phys);
 		str += 64;
 		count -= 64;
 	}
 	memcpy(buf, str, count);
 	buf[count] = 0;
-	nf_call(stderr_id, buf);
+	nf_call(stderr_id, phys);
 }
 
 static void nfcon_write(struct console *con, const char *str,
@@ -79,7 +81,7 @@ static int nfcon_tty_put_char(struct tty_struct *tty, unsigned char ch)
 {
 	char temp[2] = { ch, 0 };
 
-	nf_call(stderr_id, temp);
+	nf_call(stderr_id, virt_to_phys(temp));
 	return 1;
 }
 
diff --git a/arch/m68k/emu/nfeth.c b/arch/m68k/emu/nfeth.c
index 695cd737a42e..a0985fd088d1 100644
--- a/arch/m68k/emu/nfeth.c
+++ b/arch/m68k/emu/nfeth.c
@@ -195,7 +195,8 @@ static struct net_device * __init nfeth_probe(int unit)
 	char mac[ETH_ALEN], host_ip[32], local_ip[32];
 	int err;
 
-	if (!nf_call(nfEtherID + XIF_GET_MAC, unit, mac, ETH_ALEN))
+	if (!nf_call(nfEtherID + XIF_GET_MAC, unit, virt_to_phys(mac),
+		     ETH_ALEN))
 		return NULL;
 
 	dev = alloc_etherdev(sizeof(struct nfeth_private));
@@ -217,9 +218,9 @@ static struct net_device * __init nfeth_probe(int unit)
 	}
 
 	nf_call(nfEtherID + XIF_GET_IPHOST, unit,
-		host_ip, sizeof(host_ip));
+		virt_to_phys(host_ip), sizeof(host_ip));
 	nf_call(nfEtherID + XIF_GET_IPATARI, unit,
-		local_ip, sizeof(local_ip));
+		virt_to_phys(local_ip), sizeof(local_ip));
 
 	netdev_info(dev, KBUILD_MODNAME " addr:%s (%s) HWaddr:%pM\n", host_ip,
 		    local_ip, mac);
diff --git a/arch/m68k/include/asm/io_no.h b/arch/m68k/include/asm/io_no.h
index 353bf754a972..e1534783e94e 100644
--- a/arch/m68k/include/asm/io_no.h
+++ b/arch/m68k/include/asm/io_no.h
@@ -4,6 +4,7 @@
 #ifdef __KERNEL__
 
 #include <asm/virtconvert.h>
+#include <asm-generic/iomap.h>
 
 /*
  * These are for ISA/PCI shared memory _only_ and should never be used
diff --git a/arch/m68k/include/asm/irqflags.h b/arch/m68k/include/asm/irqflags.h
index 7ef4115b8c4a..a823cd73dc09 100644
--- a/arch/m68k/include/asm/irqflags.h
+++ b/arch/m68k/include/asm/irqflags.h
@@ -3,7 +3,7 @@
 
 #include <linux/types.h>
 #ifdef CONFIG_MMU
-#include <linux/hardirq.h>
+#include <linux/preempt_mask.h>
 #endif
 #include <linux/preempt.h>
 #include <asm/thread_info.h>
@@ -67,6 +67,10 @@ static inline void arch_local_irq_restore(unsigned long flags)
 
 static inline bool arch_irqs_disabled_flags(unsigned long flags)
 {
+	if (MACH_IS_ATARI) {
+		/* Ignore HSYNC = ipl 2 on Atari */
+		return (flags & ~(ALLOWINT | 0x200)) != 0;
+	}
 	return (flags & ~ALLOWINT) != 0;
 }
 
diff --git a/arch/m68k/include/asm/page.h b/arch/m68k/include/asm/page.h
index 7c360dac00b7..38b024a0b045 100644
--- a/arch/m68k/include/asm/page.h
+++ b/arch/m68k/include/asm/page.h
@@ -48,6 +48,9 @@ extern unsigned long _ramend;
 #include <asm/page_no.h>
 #endif
 
+#define VM_DATA_DEFAULT_FLAGS	(VM_READ | VM_WRITE | VM_EXEC | \
+				 VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
+
 #include <asm-generic/getorder.h>
 
 #endif /* _M68K_PAGE_H */
diff --git a/arch/m68k/include/asm/page_mm.h b/arch/m68k/include/asm/page_mm.h
index 89f201434b5a..5029f73e6294 100644
--- a/arch/m68k/include/asm/page_mm.h
+++ b/arch/m68k/include/asm/page_mm.h
@@ -173,7 +173,4 @@ static inline __attribute_const__ int __virt_to_node_shift(void)
 
 #endif /* __ASSEMBLY__ */
 
-#define VM_DATA_DEFAULT_FLAGS	(VM_READ | VM_WRITE | VM_EXEC | \
-				 VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
-
 #endif /* _M68K_PAGE_MM_H */
diff --git a/arch/m68k/kernel/setup_no.c b/arch/m68k/kernel/setup_no.c
index 911ba472e6c4..5b16f5d61b44 100644
--- a/arch/m68k/kernel/setup_no.c
+++ b/arch/m68k/kernel/setup_no.c
@@ -118,7 +118,7 @@ void (*mach_power_off)(void);
  *
  * Returns:
  */
-void parse_uboot_commandline(char *commandp, int size)
+static void __init parse_uboot_commandline(char *commandp, int size)
 {
 	extern unsigned long _init_sp;
 	unsigned long *sp;
diff --git a/arch/m68k/kernel/signal.c b/arch/m68k/kernel/signal.c
index 2a16df3d9312..57fd286e4b0b 100644
--- a/arch/m68k/kernel/signal.c
+++ b/arch/m68k/kernel/signal.c
@@ -50,6 +50,7 @@
 #include <asm/pgtable.h>
 #include <asm/traps.h>
 #include <asm/ucontext.h>
+#include <asm/cacheflush.h>
 
 #ifdef CONFIG_MMU
 
@@ -181,6 +182,13 @@ static inline void push_cache (unsigned long vaddr)
 		asm volatile ("movec %0,%%caar\n\t"
 			      "movec %1,%%cacr"
 			      : : "r" (vaddr + 4), "r" (temp));
+	} else {
+		/* CPU_IS_COLDFIRE */
+#if defined(CONFIG_CACHE_COPYBACK)
+		flush_cf_dcache(0, DCACHE_MAX_ADDR);
+#endif
+		/* Invalidate instruction cache for the pushed bytes */
+		clear_cf_icache(vaddr, vaddr + 8);
 	}
 }
 
diff --git a/arch/m68k/kernel/time.c b/arch/m68k/kernel/time.c
index bea6bcf8f9b8..7eb9792009f8 100644
--- a/arch/m68k/kernel/time.c
+++ b/arch/m68k/kernel/time.c
@@ -90,7 +90,7 @@ static int __init rtc_init(void)
 		return -ENODEV;
 
 	pdev = platform_device_register_simple("rtc-generic", -1, NULL, 0);
-	return PTR_RET(pdev);
+	return PTR_ERR_OR_ZERO(pdev);
 }
 
 module_init(rtc_init);
diff --git a/arch/m68k/mm/fault.c b/arch/m68k/mm/fault.c
index a563727806bf..eb1d61f68725 100644
--- a/arch/m68k/mm/fault.c
+++ b/arch/m68k/mm/fault.c
@@ -88,6 +88,8 @@ int do_page_fault(struct pt_regs *regs, unsigned long address,
 	if (in_atomic() || !mm)
 		goto no_context;
 
+	if (user_mode(regs))
+		flags |= FAULT_FLAG_USER;
 retry:
 	down_read(&mm->mmap_sem);
 
diff --git a/arch/m68k/platform/68000/m68328.c b/arch/m68k/platform/68000/m68328.c
index a86eb66835aa..e53caf4c3bfb 100644
--- a/arch/m68k/platform/68000/m68328.c
+++ b/arch/m68k/platform/68000/m68328.c
@@ -15,6 +15,7 @@
 
 /***************************************************************************/
 
+#include <linux/init.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/rtc.h>
@@ -42,7 +43,7 @@ void m68328_reset (void)
 
 /***************************************************************************/
 
-void config_BSP(char *command, int len)
+void __init config_BSP(char *command, int len)
 {
   printk(KERN_INFO "\n68328 support D. Jeff Dionne <jeff@uclinux.org>\n");
   printk(KERN_INFO "68328 support Kenneth Albanowski <kjahds@kjshds.com>\n");
diff --git a/arch/m68k/platform/68000/m68EZ328.c b/arch/m68k/platform/68000/m68EZ328.c
index a6eb72d75008..332b5e8605fc 100644
--- a/arch/m68k/platform/68000/m68EZ328.c
+++ b/arch/m68k/platform/68000/m68EZ328.c
@@ -13,6 +13,7 @@
 
 /***************************************************************************/
 
+#include <linux/init.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/rtc.h>
@@ -52,7 +53,7 @@ _bsc1(unsigned char *, gethwaddr, int, a)
 _bsc1(char *, getbenv, char *, a)
 #endif
 
-void config_BSP(char *command, int len)
+void __init config_BSP(char *command, int len)
 {
   unsigned char *p;
 
diff --git a/arch/m68k/platform/68000/m68VZ328.c b/arch/m68k/platform/68000/m68VZ328.c
index eb6964fbec09..fd6658358af1 100644
--- a/arch/m68k/platform/68000/m68VZ328.c
+++ b/arch/m68k/platform/68000/m68VZ328.c
@@ -14,6 +14,7 @@
 
 /***************************************************************************/
 
+#include <linux/init.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/kd.h>
@@ -59,7 +60,7 @@ static void m68vz328_reset(void)
 	);
 }
 
-static void init_hardware(char *command, int size)
+static void __init init_hardware(char *command, int size)
 {
 #ifdef CONFIG_DIRECT_IO_ACCESS
 	SCR = 0x10;					/* allow user access to internal registers */
@@ -145,7 +146,7 @@ _bsc0(char *, getserialnum)
 _bsc1(unsigned char *, gethwaddr, int, a)
 _bsc1(char *, getbenv, char *, a)
 
-static void init_hardware(char *command, int size)
+static void __init init_hardware(char *command, int size)
 {
 	char *p;
 
@@ -167,7 +168,7 @@ static void m68vz328_reset(void)
 {
 }
 
-static void init_hardware(char *command, int size)
+static void __init init_hardware(char *command, int size)
 {
 }
 
@@ -175,7 +176,7 @@ static void init_hardware(char *command, int size)
 #endif
 /***************************************************************************/
 
-void config_BSP(char *command, int size)
+void __init config_BSP(char *command, int size)
 {
 	printk(KERN_INFO "68VZ328 DragonBallVZ support (c) 2001 Lineo, Inc.\n");
 
diff --git a/arch/m68k/platform/68360/commproc.c b/arch/m68k/platform/68360/commproc.c
index 8e4e10cc0080..315727b7ff40 100644
--- a/arch/m68k/platform/68360/commproc.c
+++ b/arch/m68k/platform/68360/commproc.c
@@ -31,6 +31,7 @@
  */
 
 #include <linux/errno.h>
+#include <linux/init.h>
 #include <linux/sched.h>
 #include <linux/kernel.h>
 #include <linux/param.h>
@@ -77,7 +78,7 @@ void m360_cpm_reset(void);
 
 
 
-void m360_cpm_reset()
+void __init m360_cpm_reset()
 {
 /* 	pte_t		   *pte; */
 
diff --git a/arch/m68k/platform/68360/config.c b/arch/m68k/platform/68360/config.c
index 9877cefad1e7..0570741e5500 100644
--- a/arch/m68k/platform/68360/config.c
+++ b/arch/m68k/platform/68360/config.c
@@ -11,6 +11,7 @@
  */
 
 #include <stdarg.h>
+#include <linux/init.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
@@ -140,7 +141,7 @@ _bsc1(char *, getbenv, char *, a)
 #endif
 
 
-void config_BSP(char *command, int len)
+void __init config_BSP(char *command, int len)
 {
   unsigned char *p;
 
diff --git a/arch/m68k/platform/coldfire/pci.c b/arch/m68k/platform/coldfire/pci.c
index b33f97a13e6d..df9679238b6d 100644
--- a/arch/m68k/platform/coldfire/pci.c
+++ b/arch/m68k/platform/coldfire/pci.c
@@ -319,7 +319,6 @@ static int __init mcf_pci_init(void)
 	pci_fixup_irqs(pci_common_swizzle, mcf_pci_map_irq);
 	pci_bus_size_bridges(rootbus);
 	pci_bus_assign_resources(rootbus);
-	pci_enable_bridges(rootbus);
 	return 0;
 }
 
diff --git a/arch/m68k/q40/config.c b/arch/m68k/q40/config.c
index 658542b914fc..078bb744b5fe 100644
--- a/arch/m68k/q40/config.c
+++ b/arch/m68k/q40/config.c
@@ -338,6 +338,6 @@ static __init int q40_add_kbd_device(void)
 		return -ENODEV;
 
 	pdev = platform_device_register_simple("q40kbd", -1, NULL, 0);
-	return PTR_RET(pdev);
+	return PTR_ERR_OR_ZERO(pdev);
 }
 arch_initcall(q40_add_kbd_device);
diff --git a/arch/metag/Kconfig b/arch/metag/Kconfig
index cfd831c29824..36368eb07e13 100644
--- a/arch/metag/Kconfig
+++ b/arch/metag/Kconfig
@@ -13,7 +13,6 @@ config METAG
 	select HAVE_FTRACE_MCOUNT_RECORD
 	select HAVE_FUNCTION_TRACER
 	select HAVE_FUNCTION_TRACE_MCOUNT_TEST
-	select HAVE_GENERIC_HARDIRQS
 	select HAVE_KERNEL_BZIP2
 	select HAVE_KERNEL_GZIP
 	select HAVE_KERNEL_LZO
diff --git a/arch/metag/Kconfig.soc b/arch/metag/Kconfig.soc
index 2a3c860c7525..973640f46752 100644
--- a/arch/metag/Kconfig.soc
+++ b/arch/metag/Kconfig.soc
@@ -16,6 +16,8 @@ config META21_FPGA
 
 config SOC_TZ1090
 	bool "Toumaz Xenif TZ1090 SoC (Comet)"
+	select ARCH_WANT_OPTIONAL_GPIOLIB
+	select IMGPDC_IRQ
 	select METAG_LNKGET_AROUND_CACHE
 	select METAG_META21
 	select METAG_SMP_WRITE_REORDERING
diff --git a/arch/metag/boot/dts/tz1090.dtsi b/arch/metag/boot/dts/tz1090.dtsi
index 853744652b93..24ea7d2e9138 100644
--- a/arch/metag/boot/dts/tz1090.dtsi
+++ b/arch/metag/boot/dts/tz1090.dtsi
@@ -8,6 +8,8 @@
 
 #include "skeleton.dtsi"
 
+#include <dt-bindings/interrupt-controller/irq.h>
+
 / {
 	compatible = "toumaz,tz1090", "img,meta";
 
@@ -26,6 +28,22 @@
 		#size-cells = <1>;
 		ranges;
 
+		pdc: pdc@0x02006000 {
+			interrupt-controller;
+			#interrupt-cells = <2>;
+
+			reg = <0x02006000 0x1000>;
+			compatible = "img,pdc-intc";
+
+			num-perips = <3>;
+			num-syswakes = <3>;
+
+			interrupts = <18 IRQ_TYPE_LEVEL_HIGH>, /* Syswakes */
+			             <30 IRQ_TYPE_LEVEL_HIGH>, /* Perip 0 (RTC) */
+			             <29 IRQ_TYPE_LEVEL_HIGH>, /* Perip 1 (IR) */
+			             <31 IRQ_TYPE_LEVEL_HIGH>; /* Perip 2 (WDT) */
+		};
+
 		pinctrl: pinctrl@02005800 {
 			#gpio-range-cells = <3>;
 			compatible = "img,tz1090-pinctrl";
@@ -37,5 +55,54 @@
 			compatible = "img,tz1090-pdc-pinctrl";
 			reg = <0x02006500 0x100>;
 		};
+
+		gpios: gpios@02005800 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			compatible = "img,tz1090-gpio";
+			reg = <0x02005800 0x90>;
+
+			gpios0: bank@0 {
+				gpio-controller;
+				interrupt-controller;
+				#gpio-cells = <2>;
+				#interrupt-cells = <2>;
+				reg = <0>;
+				interrupts = <13 IRQ_TYPE_LEVEL_HIGH>;
+				gpio-ranges = <&pinctrl 0 0 30>;
+			};
+			gpios1: bank@1 {
+				gpio-controller;
+				interrupt-controller;
+				#gpio-cells = <2>;
+				#interrupt-cells = <2>;
+				reg = <1>;
+				interrupts = <14 IRQ_TYPE_LEVEL_HIGH>;
+				gpio-ranges = <&pinctrl 0 30 30>;
+			};
+			gpios2: bank@2 {
+				gpio-controller;
+				interrupt-controller;
+				#gpio-cells = <2>;
+				#interrupt-cells = <2>;
+				reg = <2>;
+				interrupts = <15 IRQ_TYPE_LEVEL_HIGH>;
+				gpio-ranges = <&pinctrl 0 60 30>;
+			};
+		};
+
+		pdc_gpios: gpios@02006500 {
+			gpio-controller;
+			#gpio-cells = <2>;
+
+			compatible = "img,tz1090-pdc-gpio";
+			reg = <0x02006500 0x100>;
+
+			interrupt-parent = <&pdc>;
+			interrupts =	<8  IRQ_TYPE_NONE>,
+					<9  IRQ_TYPE_NONE>,
+					<10 IRQ_TYPE_NONE>;
+			gpio-ranges = <&pdc_pinctrl 0 0 7>;
+		};
 	};
 };
diff --git a/arch/metag/mm/fault.c b/arch/metag/mm/fault.c
index 8fddf46e6c62..332680e5ebf2 100644
--- a/arch/metag/mm/fault.c
+++ b/arch/metag/mm/fault.c
@@ -53,8 +53,7 @@ int do_page_fault(struct pt_regs *regs, unsigned long address,
 	struct vm_area_struct *vma, *prev_vma;
 	siginfo_t info;
 	int fault;
-	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
-				(write_access ? FAULT_FLAG_WRITE : 0);
+	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
 
 	tsk = current;
 
@@ -109,6 +108,8 @@ int do_page_fault(struct pt_regs *regs, unsigned long address,
 	if (in_atomic() || !mm)
 		goto no_context;
 
+	if (user_mode(regs))
+		flags |= FAULT_FLAG_USER;
 retry:
 	down_read(&mm->mmap_sem);
 
@@ -121,6 +122,7 @@ good_area:
 	if (write_access) {
 		if (!(vma->vm_flags & VM_WRITE))
 			goto bad_area;
+		flags |= FAULT_FLAG_WRITE;
 	} else {
 		if (!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE)))
 			goto bad_area;
diff --git a/arch/metag/mm/hugetlbpage.c b/arch/metag/mm/hugetlbpage.c
index 3c52fa6d0f8e..042431509b56 100644
--- a/arch/metag/mm/hugetlbpage.c
+++ b/arch/metag/mm/hugetlbpage.c
@@ -110,6 +110,11 @@ int pud_huge(pud_t pud)
 	return 0;
 }
 
+int pmd_huge_support(void)
+{
+	return 1;
+}
+
 struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address,
 			     pmd_t *pmd, int write)
 {
diff --git a/arch/metag/mm/init.c b/arch/metag/mm/init.c
index 28813f164730..123919534b80 100644
--- a/arch/metag/mm/init.c
+++ b/arch/metag/mm/init.c
@@ -407,10 +407,9 @@ void free_initrd_mem(unsigned long start, unsigned long end)
 #endif
 
 #ifdef CONFIG_OF_FLATTREE
-void __init early_init_dt_setup_initrd_arch(unsigned long start,
-					    unsigned long end)
+void __init early_init_dt_setup_initrd_arch(u64 start, u64 end)
 {
-	pr_err("%s(%lx, %lx)\n",
+	pr_err("%s(%llx, %llx)\n",
 	       __func__, start, end);
 }
 #endif /* CONFIG_OF_FLATTREE */
diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig
index 4fab52294d98..b82f82b74319 100644
--- a/arch/microblaze/Kconfig
+++ b/arch/microblaze/Kconfig
@@ -18,7 +18,6 @@ config MICROBLAZE
 	select ARCH_WANT_IPC_PARSE_VERSION
 	select HAVE_DEBUG_KMEMLEAK
 	select IRQ_DOMAIN
-	select HAVE_GENERIC_HARDIRQS
 	select VIRT_TO_BUS
 	select GENERIC_IRQ_PROBE
 	select GENERIC_IRQ_SHOW
@@ -29,6 +28,7 @@ config MICROBLAZE
 	select GENERIC_IDLE_POLL_SETUP
 	select MODULES_USE_ELF_RELA
 	select CLONE_BACKWARDS3
+	select CLKSRC_OF
 
 config SWAP
 	def_bool n
diff --git a/arch/microblaze/Makefile b/arch/microblaze/Makefile
index 0a603d3ecf24..40350a3c24e9 100644
--- a/arch/microblaze/Makefile
+++ b/arch/microblaze/Makefile
@@ -72,7 +72,7 @@ all: linux.bin
 archclean:
 	$(Q)$(MAKE) $(clean)=$(boot)
 
-linux.bin linux.bin.gz: vmlinux
+linux.bin linux.bin.gz linux.bin.ub: vmlinux
 	$(Q)$(MAKE) $(build)=$(boot) $(boot)/$@
 
 simpleImage.%: vmlinux
@@ -81,6 +81,7 @@ simpleImage.%: vmlinux
 define archhelp
   echo '* linux.bin    - Create raw binary'
   echo '  linux.bin.gz - Create compressed raw binary'
+  echo '  linux.bin.ub - Create U-Boot wrapped raw binary'
   echo '  simpleImage.<dt> - ELF image with $(arch)/boot/dts/<dt>.dts linked in'
   echo '                   - stripped elf with fdt blob'
   echo '  simpleImage.<dt>.unstrip - full ELF image with fdt blob'
diff --git a/arch/microblaze/boot/Makefile b/arch/microblaze/boot/Makefile
index 80fe54fb7ca3..8e211cc28dac 100644
--- a/arch/microblaze/boot/Makefile
+++ b/arch/microblaze/boot/Makefile
@@ -2,12 +2,15 @@
 # arch/microblaze/boot/Makefile
 #
 
-targets := linux.bin linux.bin.gz simpleImage.%
+targets := linux.bin linux.bin.gz linux.bin.ub simpleImage.%
 
 OBJCOPYFLAGS := -R .note -R .comment -R .note.gnu.build-id -O binary
 
 $(obj)/linux.bin: vmlinux FORCE
 	$(call if_changed,objcopy)
+	@echo 'Kernel: $@ is ready' ' (#'`cat .version`')'
+
+$(obj)/linux.bin.ub: $(obj)/linux.bin FORCE
 	$(call if_changed,uimage)
 	@echo 'Kernel: $@ is ready' ' (#'`cat .version`')'
 
@@ -22,8 +25,6 @@ quiet_cmd_strip = STRIP   $@
 	cmd_strip = $(STRIP) -K microblaze_start -K _end -K __log_buf \
 				-K _fdt_start vmlinux -o $@
 
-UIMAGE_IN = $@
-UIMAGE_OUT = $@.ub
 UIMAGE_LOADADDR = $(CONFIG_KERNEL_BASE_ADDR)
 
 $(obj)/simpleImage.%: vmlinux FORCE
diff --git a/arch/microblaze/include/asm/prom.h b/arch/microblaze/include/asm/prom.h
index 20c5e8e5121b..9977816c5ad3 100644
--- a/arch/microblaze/include/asm/prom.h
+++ b/arch/microblaze/include/asm/prom.h
@@ -50,9 +50,6 @@ void of_parse_dma_window(struct device_node *dn, const void *dma_window_prop,
 
 extern void kdump_move_device_tree(void);
 
-/* CPU OF node matching */
-struct device_node *of_get_cpu_node(int cpu, unsigned int *thread);
-
 #endif /* __ASSEMBLY__ */
 #endif /* __KERNEL__ */
 
diff --git a/arch/microblaze/include/asm/selfmod.h b/arch/microblaze/include/asm/selfmod.h
deleted file mode 100644
index c42aff2e6cd0..000000000000
--- a/arch/microblaze/include/asm/selfmod.h
+++ /dev/null
@@ -1,24 +0,0 @@
-/*
- * Copyright (C) 2007-2008 Michal Simek <monstr@monstr.eu>
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License. See the file "COPYING" in the main directory of this archive
- * for more details.
- */
-
-#ifndef _ASM_MICROBLAZE_SELFMOD_H
-#define _ASM_MICROBLAZE_SELFMOD_H
-
-/*
- * BARRIER_BASE_ADDR is constant address for selfmod function.
- * do not change this value - selfmod function is in
- * arch/microblaze/kernel/selfmod.c: selfmod_function()
- *
- * last 16 bits is used for storing register offset
- */
-
-#define BARRIER_BASE_ADDR	0x1234ff00
-
-void selfmod_function(const int *arr_fce, const unsigned int base);
-
-#endif /* _ASM_MICROBLAZE_SELFMOD_H */
diff --git a/arch/microblaze/kernel/Makefile b/arch/microblaze/kernel/Makefile
index 928c950fc14c..5b0e512c78e5 100644
--- a/arch/microblaze/kernel/Makefile
+++ b/arch/microblaze/kernel/Makefile
@@ -7,7 +7,6 @@ ifdef CONFIG_FUNCTION_TRACER
 CFLAGS_REMOVE_timer.o = -pg
 CFLAGS_REMOVE_intc.o = -pg
 CFLAGS_REMOVE_early_printk.o = -pg
-CFLAGS_REMOVE_selfmod.o = -pg
 CFLAGS_REMOVE_heartbeat.o = -pg
 CFLAGS_REMOVE_ftrace.o = -pg
 CFLAGS_REMOVE_process.o = -pg
@@ -23,7 +22,6 @@ obj-y += dma.o exceptions.o \
 obj-y += cpu/
 
 obj-$(CONFIG_EARLY_PRINTK)	+= early_printk.o
-obj-$(CONFIG_SELFMOD)		+= selfmod.o
 obj-$(CONFIG_HEART_BEAT)	+= heartbeat.o
 obj-$(CONFIG_MODULES)		+= microblaze_ksyms.o module.o
 obj-$(CONFIG_MMU)		+= misc.o
diff --git a/arch/microblaze/kernel/cpu/cpuinfo.c b/arch/microblaze/kernel/cpu/cpuinfo.c
index 410398f6db55..c9203b1007aa 100644
--- a/arch/microblaze/kernel/cpu/cpuinfo.c
+++ b/arch/microblaze/kernel/cpu/cpuinfo.c
@@ -39,6 +39,8 @@ const struct cpu_ver_key cpu_ver_lookup[] = {
 	{"8.30.a", 0x17},
 	{"8.40.a", 0x18},
 	{"8.40.b", 0x19},
+	{"9.0", 0x1b},
+	{"9.1", 0x1d},
 	{NULL, 0},
 };
 
diff --git a/arch/microblaze/kernel/intc.c b/arch/microblaze/kernel/intc.c
index d85fa3a2b0f8..581451ad4687 100644
--- a/arch/microblaze/kernel/intc.c
+++ b/arch/microblaze/kernel/intc.c
@@ -1,5 +1,6 @@
 /*
- * Copyright (C) 2007-2009 Michal Simek <monstr@monstr.eu>
+ * Copyright (C) 2007-2013 Michal Simek <monstr@monstr.eu>
+ * Copyright (C) 2012-2013 Xilinx, Inc.
  * Copyright (C) 2007-2009 PetaLogix
  * Copyright (C) 2006 Atmark Techno, Inc.
  *
@@ -8,23 +9,15 @@
  * for more details.
  */
 
-#include <linux/init.h>
 #include <linux/irqdomain.h>
 #include <linux/irq.h>
-#include <asm/page.h>
+#include <linux/of_address.h>
 #include <linux/io.h>
 #include <linux/bug.h>
 
-#include <asm/prom.h>
-#include <asm/irq.h>
+#include "../../drivers/irqchip/irqchip.h"
 
-#ifdef CONFIG_SELFMOD_INTC
-#include <asm/selfmod.h>
-#define INTC_BASE	BARRIER_BASE_ADDR
-#else
-static unsigned int intc_baseaddr;
-#define INTC_BASE	intc_baseaddr
-#endif
+static void __iomem *intc_baseaddr;
 
 /* No one else should require these constants, so define them locally here. */
 #define ISR 0x00			/* Interrupt Status Register */
@@ -50,21 +43,21 @@ static void intc_enable_or_unmask(struct irq_data *d)
 	 * acks the irq before calling the interrupt handler
 	 */
 	if (irqd_is_level_type(d))
-		out_be32(INTC_BASE + IAR, mask);
+		out_be32(intc_baseaddr + IAR, mask);
 
-	out_be32(INTC_BASE + SIE, mask);
+	out_be32(intc_baseaddr + SIE, mask);
 }
 
 static void intc_disable_or_mask(struct irq_data *d)
 {
 	pr_debug("disable: %ld\n", d->hwirq);
-	out_be32(INTC_BASE + CIE, 1 << d->hwirq);
+	out_be32(intc_baseaddr + CIE, 1 << d->hwirq);
 }
 
 static void intc_ack(struct irq_data *d)
 {
 	pr_debug("ack: %ld\n", d->hwirq);
-	out_be32(INTC_BASE + IAR, 1 << d->hwirq);
+	out_be32(intc_baseaddr + IAR, 1 << d->hwirq);
 }
 
 static void intc_mask_ack(struct irq_data *d)
@@ -72,8 +65,8 @@ static void intc_mask_ack(struct irq_data *d)
 	unsigned long mask = 1 << d->hwirq;
 
 	pr_debug("disable_and_ack: %ld\n", d->hwirq);
-	out_be32(INTC_BASE + CIE, mask);
-	out_be32(INTC_BASE + IAR, mask);
+	out_be32(intc_baseaddr + CIE, mask);
+	out_be32(intc_baseaddr + IAR, mask);
 }
 
 static struct irq_chip intc_dev = {
@@ -90,7 +83,7 @@ unsigned int get_irq(void)
 {
 	unsigned int hwirq, irq = -1;
 
-	hwirq = in_be32(INTC_BASE + IVR);
+	hwirq = in_be32(intc_baseaddr + IVR);
 	if (hwirq != -1U)
 		irq = irq_find_mapping(root_domain, hwirq);
 
@@ -120,40 +113,32 @@ static const struct irq_domain_ops xintc_irq_domain_ops = {
 	.map = xintc_map,
 };
 
-void __init init_IRQ(void)
+static int __init xilinx_intc_of_init(struct device_node *intc,
+					     struct device_node *parent)
 {
 	u32 nr_irq, intr_mask;
-	struct device_node *intc = NULL;
-#ifdef CONFIG_SELFMOD_INTC
-	unsigned int intc_baseaddr = 0;
-	static int arr_func[] = {
-				(int)&get_irq,
-				(int)&intc_enable_or_unmask,
-				(int)&intc_disable_or_mask,
-				(int)&intc_mask_ack,
-				(int)&intc_ack,
-				(int)&intc_end,
-				0
-			};
-#endif
-	intc = of_find_compatible_node(NULL, NULL, "xlnx,xps-intc-1.00.a");
-	BUG_ON(!intc);
-
-	intc_baseaddr = be32_to_cpup(of_get_property(intc, "reg", NULL));
-	intc_baseaddr = (unsigned long) ioremap(intc_baseaddr, PAGE_SIZE);
-	nr_irq = be32_to_cpup(of_get_property(intc,
-						"xlnx,num-intr-inputs", NULL));
-
-	intr_mask =
-		be32_to_cpup(of_get_property(intc, "xlnx,kind-of-intr", NULL));
+	int ret;
+
+	intc_baseaddr = of_iomap(intc, 0);
+	BUG_ON(!intc_baseaddr);
+
+	ret = of_property_read_u32(intc, "xlnx,num-intr-inputs", &nr_irq);
+	if (ret < 0) {
+		pr_err("%s: unable to read xlnx,num-intr-inputs\n", __func__);
+		return -EINVAL;
+	}
+
+	ret = of_property_read_u32(intc, "xlnx,kind-of-intr", &intr_mask);
+	if (ret < 0) {
+		pr_err("%s: unable to read xlnx,kind-of-intr\n", __func__);
+		return -EINVAL;
+	}
+
 	if (intr_mask > (u32)((1ULL << nr_irq) - 1))
 		pr_info(" ERROR: Mismatch in kind-of-intr param\n");
 
-#ifdef CONFIG_SELFMOD_INTC
-	selfmod_function((int *) arr_func, intc_baseaddr);
-#endif
-	pr_info("%s #0 at 0x%08x, num_irq=%d, edge=0x%x\n",
-		intc->name, intc_baseaddr, nr_irq, intr_mask);
+	pr_info("%s: num_irq=%d, edge=0x%x\n",
+		intc->full_name, nr_irq, intr_mask);
 
 	/*
 	 * Disable all external interrupts until they are
@@ -174,4 +159,8 @@ void __init init_IRQ(void)
 							(void *)intr_mask);
 
 	irq_set_default_host(root_domain);
+
+	return 0;
 }
+
+IRQCHIP_DECLARE(xilinx_intc, "xlnx,xps-intc-1.00.a", xilinx_intc_of_init);
diff --git a/arch/microblaze/kernel/irq.c b/arch/microblaze/kernel/irq.c
index ace700afbfdf..11e24de91aa4 100644
--- a/arch/microblaze/kernel/irq.c
+++ b/arch/microblaze/kernel/irq.c
@@ -17,10 +17,8 @@
 #include <linux/seq_file.h>
 #include <linux/kernel_stat.h>
 #include <linux/irq.h>
+#include <linux/irqchip.h>
 #include <linux/of_irq.h>
-#include <linux/export.h>
-
-#include <asm/prom.h>
 
 static u32 concurrent_irq;
 
@@ -47,3 +45,9 @@ next_irq:
 	set_irq_regs(old_regs);
 	trace_hardirqs_on();
 }
+
+void __init init_IRQ(void)
+{
+	/* process the entire interrupt tree in one go */
+	irqchip_init();
+}
diff --git a/arch/microblaze/kernel/prom.c b/arch/microblaze/kernel/prom.c
index 0a2c68f9f9b0..0c4453f134cb 100644
--- a/arch/microblaze/kernel/prom.c
+++ b/arch/microblaze/kernel/prom.c
@@ -46,11 +46,6 @@ void __init early_init_dt_add_memory_arch(u64 base, u64 size)
 	memblock_add(base, size);
 }
 
-void * __init early_init_dt_alloc_memory_arch(u64 size, u64 align)
-{
-	return __va(memblock_alloc(size, align));
-}
-
 #ifdef CONFIG_EARLY_PRINTK
 static char *stdout;
 
@@ -136,8 +131,7 @@ void __init early_init_devtree(void *params)
 }
 
 #ifdef CONFIG_BLK_DEV_INITRD
-void __init early_init_dt_setup_initrd_arch(unsigned long start,
-		unsigned long end)
+void __init early_init_dt_setup_initrd_arch(u64 start, u64 end)
 {
 	initrd_start = (unsigned long)__va(start);
 	initrd_end = (unsigned long)__va(end);
diff --git a/arch/microblaze/kernel/reset.c b/arch/microblaze/kernel/reset.c
index 2e5079ab53d2..fbe58c6554a8 100644
--- a/arch/microblaze/kernel/reset.c
+++ b/arch/microblaze/kernel/reset.c
@@ -67,7 +67,11 @@ static void gpio_system_reset(void)
 		pr_notice("Reset GPIO unavailable - halting!\n");
 }
 #else
-#define gpio_system_reset() do {} while (0)
+static void gpio_system_reset(void)
+{
+	pr_notice("No reset GPIO present - halting!\n");
+}
+
 void of_platform_reset_gpio_probe(void)
 {
 	return;
diff --git a/arch/microblaze/kernel/selfmod.c b/arch/microblaze/kernel/selfmod.c
deleted file mode 100644
index 89508bdc9f3c..000000000000
--- a/arch/microblaze/kernel/selfmod.c
+++ /dev/null
@@ -1,81 +0,0 @@
-/*
- * Copyright (C) 2007-2009 Michal Simek <monstr@monstr.eu>
- * Copyright (C) 2009 PetaLogix
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License. See the file "COPYING" in the main directory of this archive
- * for more details.
- */
-
-#include <linux/interrupt.h>
-#include <asm/selfmod.h>
-
-#undef DEBUG
-
-#if __GNUC__ > 3
-#error GCC 4 unsupported SELFMOD. Please disable SELFMOD from menuconfig.
-#endif
-
-#define OPCODE_IMM		0xB0000000
-#define OPCODE_LWI		0xE8000000
-#define OPCODE_LWI_MASK		0xEC000000
-#define OPCODE_RTSD		0xB60F0008 /* return from func: rtsd r15, 8 */
-#define OPCODE_ADDIK		0x30000000
-#define OPCODE_ADDIK_MASK	0xFC000000
-
-#define IMM_BASE	(OPCODE_IMM | (BARRIER_BASE_ADDR >> 16))
-#define LWI_BASE	(OPCODE_LWI | (BARRIER_BASE_ADDR & 0x0000ff00))
-#define LWI_BASE_MASK	(OPCODE_LWI_MASK | (BARRIER_BASE_ADDR & 0x0000ff00))
-#define ADDIK_BASE	(OPCODE_ADDIK | (BARRIER_BASE_ADDR & 0x0000ff00))
-#define ADDIK_BASE_MASK	(OPCODE_ADDIK_MASK | (BARRIER_BASE_ADDR & 0x0000ff00))
-
-#define MODIFY_INSTR {						\
-	pr_debug("%s: curr instr, (%d):0x%x, next(%d):0x%x\n",		\
-		__func__, i, addr[i], i + 1, addr[i + 1]);		\
-	addr[i] = OPCODE_IMM + (base >> 16);				\
-	/* keep instruction opcode and add only last 16bits */		\
-	addr[i + 1] = (addr[i + 1] & 0xffff00ff) + (base & 0xffff);	\
-	__invalidate_icache(addr[i]);					\
-	__invalidate_icache(addr[i + 1]);				\
-	pr_debug("%s: hack instr, (%d):0x%x, next(%d):0x%x\n",		\
-		__func__, i, addr[i], i + 1, addr[i + 1]); }
-
-/* NOTE
- * self-modified part of code for improvement of interrupt controller
- * save instruction in interrupt rutine
- */
-void selfmod_function(const int *arr_fce, const unsigned int base)
-{
-	unsigned int flags, i, j, *addr = NULL;
-
-	local_irq_save(flags);
-	__disable_icache();
-
-	/* zero terminated array */
-	for (j = 0; arr_fce[j] != 0; j++) {
-		/* get start address of function */
-		addr = (unsigned int *) arr_fce[j];
-		pr_debug("%s: func(%d) at 0x%x\n",
-					__func__, j, (unsigned int) addr);
-		for (i = 0; ; i++) {
-			pr_debug("%s: instruction code at %d: 0x%x\n",
-						__func__, i, addr[i]);
-			if (addr[i] == IMM_BASE) {
-				/* detecting of lwi (0xE8) or swi (0xF8) instr
-				 * I can detect both opcode with one mask */
-				if ((addr[i + 1] & LWI_BASE_MASK) == LWI_BASE) {
-					MODIFY_INSTR;
-				} else /* detection addik for ack */
-				if ((addr[i + 1] & ADDIK_BASE_MASK) ==
-								ADDIK_BASE) {
-					MODIFY_INSTR;
-				}
-			} else if (addr[i] == OPCODE_RTSD) {
-				/* return from function means end of function */
-				pr_debug("%s: end of array %d\n", __func__, i);
-				break;
-			}
-		}
-	}
-	local_irq_restore(flags);
-} /* end of self-modified code */
diff --git a/arch/microblaze/kernel/setup.c b/arch/microblaze/kernel/setup.c
index 0263da7b83dd..0775e036c526 100644
--- a/arch/microblaze/kernel/setup.c
+++ b/arch/microblaze/kernel/setup.c
@@ -9,6 +9,7 @@
  */
 
 #include <linux/init.h>
+#include <linux/clocksource.h>
 #include <linux/string.h>
 #include <linux/seq_file.h>
 #include <linux/cpu.h>
@@ -68,10 +69,6 @@ void __init setup_arch(char **cmdline_p)
 
 	xilinx_pci_init();
 
-#if defined(CONFIG_SELFMOD_INTC) || defined(CONFIG_SELFMOD_TIMER)
-	pr_notice("Self modified code enable\n");
-#endif
-
 #ifdef CONFIG_VT
 #if defined(CONFIG_XILINX_CONSOLE)
 	conswitchp = &xil_con;
@@ -196,6 +193,11 @@ void __init machine_early_init(const char *cmdline, unsigned int ram,
 	per_cpu(CURRENT_SAVE, 0) = (unsigned long)current;
 }
 
+void __init time_init(void)
+{
+	clocksource_of_init();
+}
+
 #ifdef CONFIG_DEBUG_FS
 struct dentry *of_debugfs_root;
 
diff --git a/arch/microblaze/kernel/timer.c b/arch/microblaze/kernel/timer.c
index aec5020a6e31..e4b3f33ef34c 100644
--- a/arch/microblaze/kernel/timer.c
+++ b/arch/microblaze/kernel/timer.c
@@ -1,5 +1,6 @@
 /*
- * Copyright (C) 2007-2009 Michal Simek <monstr@monstr.eu>
+ * Copyright (C) 2007-2013 Michal Simek <monstr@monstr.eu>
+ * Copyright (C) 2012-2013 Xilinx, Inc.
  * Copyright (C) 2007-2009 PetaLogix
  * Copyright (C) 2006 Atmark Techno, Inc.
  *
@@ -8,34 +9,16 @@
  * for more details.
  */
 
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/param.h>
 #include <linux/interrupt.h>
-#include <linux/profile.h>
-#include <linux/irq.h>
 #include <linux/delay.h>
 #include <linux/sched.h>
-#include <linux/spinlock.h>
-#include <linux/err.h>
 #include <linux/clk.h>
-#include <linux/clocksource.h>
 #include <linux/clockchips.h>
-#include <linux/io.h>
-#include <linux/bug.h>
+#include <linux/of_address.h>
 #include <asm/cpuinfo.h>
-#include <asm/setup.h>
-#include <asm/prom.h>
-#include <asm/irq.h>
 #include <linux/cnt32_to_63.h>
 
-#ifdef CONFIG_SELFMOD_TIMER
-#include <asm/selfmod.h>
-#define TIMER_BASE	BARRIER_BASE_ADDR
-#else
-static unsigned int timer_baseaddr;
-#define TIMER_BASE	timer_baseaddr
-#endif
+static void __iomem *timer_baseaddr;
 
 static unsigned int freq_div_hz;
 static unsigned int timer_clock_freq;
@@ -59,19 +42,21 @@ static unsigned int timer_clock_freq;
 #define TCSR_PWMA	(1<<9)
 #define TCSR_ENALL	(1<<10)
 
-static inline void microblaze_timer0_stop(void)
+static inline void xilinx_timer0_stop(void)
 {
-	out_be32(TIMER_BASE + TCSR0, in_be32(TIMER_BASE + TCSR0) & ~TCSR_ENT);
+	out_be32(timer_baseaddr + TCSR0,
+		 in_be32(timer_baseaddr + TCSR0) & ~TCSR_ENT);
 }
 
-static inline void microblaze_timer0_start_periodic(unsigned long load_val)
+static inline void xilinx_timer0_start_periodic(unsigned long load_val)
 {
 	if (!load_val)
 		load_val = 1;
-	out_be32(TIMER_BASE + TLR0, load_val); /* loading value to timer reg */
+	/* loading value to timer reg */
+	out_be32(timer_baseaddr + TLR0, load_val);
 
 	/* load the initial value */
-	out_be32(TIMER_BASE + TCSR0, TCSR_LOAD);
+	out_be32(timer_baseaddr + TCSR0, TCSR_LOAD);
 
 	/* see timer data sheet for detail
 	 * !ENALL - don't enable 'em all
@@ -86,38 +71,39 @@ static inline void microblaze_timer0_start_periodic(unsigned long load_val)
 	 * UDT - set the timer as down counter
 	 * !MDT0 - generate mode
 	 */
-	out_be32(TIMER_BASE + TCSR0,
+	out_be32(timer_baseaddr + TCSR0,
 			TCSR_TINT|TCSR_ENIT|TCSR_ENT|TCSR_ARHT|TCSR_UDT);
 }
 
-static inline void microblaze_timer0_start_oneshot(unsigned long load_val)
+static inline void xilinx_timer0_start_oneshot(unsigned long load_val)
 {
 	if (!load_val)
 		load_val = 1;
-	out_be32(TIMER_BASE + TLR0, load_val); /* loading value to timer reg */
+	/* loading value to timer reg */
+	out_be32(timer_baseaddr + TLR0, load_val);
 
 	/* load the initial value */
-	out_be32(TIMER_BASE + TCSR0, TCSR_LOAD);
+	out_be32(timer_baseaddr + TCSR0, TCSR_LOAD);
 
-	out_be32(TIMER_BASE + TCSR0,
+	out_be32(timer_baseaddr + TCSR0,
 			TCSR_TINT|TCSR_ENIT|TCSR_ENT|TCSR_ARHT|TCSR_UDT);
 }
 
-static int microblaze_timer_set_next_event(unsigned long delta,
+static int xilinx_timer_set_next_event(unsigned long delta,
 					struct clock_event_device *dev)
 {
 	pr_debug("%s: next event, delta %x\n", __func__, (u32)delta);
-	microblaze_timer0_start_oneshot(delta);
+	xilinx_timer0_start_oneshot(delta);
 	return 0;
 }
 
-static void microblaze_timer_set_mode(enum clock_event_mode mode,
+static void xilinx_timer_set_mode(enum clock_event_mode mode,
 				struct clock_event_device *evt)
 {
 	switch (mode) {
 	case CLOCK_EVT_MODE_PERIODIC:
 		pr_info("%s: periodic\n", __func__);
-		microblaze_timer0_start_periodic(freq_div_hz);
+		xilinx_timer0_start_periodic(freq_div_hz);
 		break;
 	case CLOCK_EVT_MODE_ONESHOT:
 		pr_info("%s: oneshot\n", __func__);
@@ -127,7 +113,7 @@ static void microblaze_timer_set_mode(enum clock_event_mode mode,
 		break;
 	case CLOCK_EVT_MODE_SHUTDOWN:
 		pr_info("%s: shutdown\n", __func__);
-		microblaze_timer0_stop();
+		xilinx_timer0_stop();
 		break;
 	case CLOCK_EVT_MODE_RESUME:
 		pr_info("%s: resume\n", __func__);
@@ -135,23 +121,23 @@ static void microblaze_timer_set_mode(enum clock_event_mode mode,
 	}
 }
 
-static struct clock_event_device clockevent_microblaze_timer = {
-	.name		= "microblaze_clockevent",
+static struct clock_event_device clockevent_xilinx_timer = {
+	.name		= "xilinx_clockevent",
 	.features       = CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_FEAT_PERIODIC,
 	.shift		= 8,
 	.rating		= 300,
-	.set_next_event	= microblaze_timer_set_next_event,
-	.set_mode	= microblaze_timer_set_mode,
+	.set_next_event	= xilinx_timer_set_next_event,
+	.set_mode	= xilinx_timer_set_mode,
 };
 
 static inline void timer_ack(void)
 {
-	out_be32(TIMER_BASE + TCSR0, in_be32(TIMER_BASE + TCSR0));
+	out_be32(timer_baseaddr + TCSR0, in_be32(timer_baseaddr + TCSR0));
 }
 
 static irqreturn_t timer_interrupt(int irq, void *dev_id)
 {
-	struct clock_event_device *evt = &clockevent_microblaze_timer;
+	struct clock_event_device *evt = &clockevent_xilinx_timer;
 #ifdef CONFIG_HEART_BEAT
 	heartbeat();
 #endif
@@ -164,73 +150,74 @@ static struct irqaction timer_irqaction = {
 	.handler = timer_interrupt,
 	.flags = IRQF_DISABLED | IRQF_TIMER,
 	.name = "timer",
-	.dev_id = &clockevent_microblaze_timer,
+	.dev_id = &clockevent_xilinx_timer,
 };
 
-static __init void microblaze_clockevent_init(void)
+static __init void xilinx_clockevent_init(void)
 {
-	clockevent_microblaze_timer.mult =
+	clockevent_xilinx_timer.mult =
 		div_sc(timer_clock_freq, NSEC_PER_SEC,
-				clockevent_microblaze_timer.shift);
-	clockevent_microblaze_timer.max_delta_ns =
-		clockevent_delta2ns((u32)~0, &clockevent_microblaze_timer);
-	clockevent_microblaze_timer.min_delta_ns =
-		clockevent_delta2ns(1, &clockevent_microblaze_timer);
-	clockevent_microblaze_timer.cpumask = cpumask_of(0);
-	clockevents_register_device(&clockevent_microblaze_timer);
+				clockevent_xilinx_timer.shift);
+	clockevent_xilinx_timer.max_delta_ns =
+		clockevent_delta2ns((u32)~0, &clockevent_xilinx_timer);
+	clockevent_xilinx_timer.min_delta_ns =
+		clockevent_delta2ns(1, &clockevent_xilinx_timer);
+	clockevent_xilinx_timer.cpumask = cpumask_of(0);
+	clockevents_register_device(&clockevent_xilinx_timer);
 }
 
-static cycle_t microblaze_read(struct clocksource *cs)
+static cycle_t xilinx_read(struct clocksource *cs)
 {
 	/* reading actual value of timer 1 */
-	return (cycle_t) (in_be32(TIMER_BASE + TCR1));
+	return (cycle_t) (in_be32(timer_baseaddr + TCR1));
 }
 
-static struct timecounter microblaze_tc = {
+static struct timecounter xilinx_tc = {
 	.cc = NULL,
 };
 
-static cycle_t microblaze_cc_read(const struct cyclecounter *cc)
+static cycle_t xilinx_cc_read(const struct cyclecounter *cc)
 {
-	return microblaze_read(NULL);
+	return xilinx_read(NULL);
 }
 
-static struct cyclecounter microblaze_cc = {
-	.read = microblaze_cc_read,
+static struct cyclecounter xilinx_cc = {
+	.read = xilinx_cc_read,
 	.mask = CLOCKSOURCE_MASK(32),
 	.shift = 8,
 };
 
-static int __init init_microblaze_timecounter(void)
+static int __init init_xilinx_timecounter(void)
 {
-	microblaze_cc.mult = div_sc(timer_clock_freq, NSEC_PER_SEC,
-				microblaze_cc.shift);
+	xilinx_cc.mult = div_sc(timer_clock_freq, NSEC_PER_SEC,
+				xilinx_cc.shift);
 
-	timecounter_init(&microblaze_tc, &microblaze_cc, sched_clock());
+	timecounter_init(&xilinx_tc, &xilinx_cc, sched_clock());
 
 	return 0;
 }
 
 static struct clocksource clocksource_microblaze = {
-	.name		= "microblaze_clocksource",
+	.name		= "xilinx_clocksource",
 	.rating		= 300,
-	.read		= microblaze_read,
+	.read		= xilinx_read,
 	.mask		= CLOCKSOURCE_MASK(32),
 	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
 };
 
-static int __init microblaze_clocksource_init(void)
+static int __init xilinx_clocksource_init(void)
 {
 	if (clocksource_register_hz(&clocksource_microblaze, timer_clock_freq))
 		panic("failed to register clocksource");
 
 	/* stop timer1 */
-	out_be32(TIMER_BASE + TCSR1, in_be32(TIMER_BASE + TCSR1) & ~TCSR_ENT);
+	out_be32(timer_baseaddr + TCSR1,
+		 in_be32(timer_baseaddr + TCSR1) & ~TCSR_ENT);
 	/* start timer1 - up counting without interrupt */
-	out_be32(TIMER_BASE + TCSR1, TCSR_TINT|TCSR_ENT|TCSR_ARHT);
+	out_be32(timer_baseaddr + TCSR1, TCSR_TINT|TCSR_ENT|TCSR_ARHT);
 
 	/* register timecounter - for ftrace support */
-	init_microblaze_timecounter();
+	init_xilinx_timecounter();
 	return 0;
 }
 
@@ -240,55 +227,31 @@ static int __init microblaze_clocksource_init(void)
  */
 static int timer_initialized;
 
-void __init time_init(void)
+static void __init xilinx_timer_init(struct device_node *timer)
 {
 	u32 irq;
 	u32 timer_num = 1;
-	struct device_node *timer = NULL;
-	const void *prop;
-#ifdef CONFIG_SELFMOD_TIMER
-	unsigned int timer_baseaddr = 0;
-	int arr_func[] = {
-				(int)&microblaze_read,
-				(int)&timer_interrupt,
-				(int)&microblaze_clocksource_init,
-				(int)&microblaze_timer_set_mode,
-				(int)&microblaze_timer_set_next_event,
-				0
-			};
-#endif
-	prop = of_get_property(of_chosen, "system-timer", NULL);
-	if (prop)
-		timer = of_find_node_by_phandle(be32_to_cpup(prop));
-	else
-		pr_info("No chosen timer found, using default\n");
-
-	if (!timer)
-		timer = of_find_compatible_node(NULL, NULL,
-						"xlnx,xps-timer-1.00.a");
-	BUG_ON(!timer);
-
-	timer_baseaddr = be32_to_cpup(of_get_property(timer, "reg", NULL));
-	timer_baseaddr = (unsigned long) ioremap(timer_baseaddr, PAGE_SIZE);
+	int ret;
+
+	timer_baseaddr = of_iomap(timer, 0);
+	if (!timer_baseaddr) {
+		pr_err("ERROR: invalid timer base address\n");
+		BUG();
+	}
+
 	irq = irq_of_parse_and_map(timer, 0);
-	timer_num = be32_to_cpup(of_get_property(timer,
-						"xlnx,one-timer-only", NULL));
+
+	of_property_read_u32(timer, "xlnx,one-timer-only", &timer_num);
 	if (timer_num) {
-		pr_emerg("Please   enable two timers in HW\n");
+		pr_emerg("Please enable two timers in HW\n");
 		BUG();
 	}
 
-#ifdef CONFIG_SELFMOD_TIMER
-	selfmod_function((int *) arr_func, timer_baseaddr);
-#endif
-	pr_info("%s #0 at 0x%08x, irq=%d\n",
-		timer->name, timer_baseaddr, irq);
+	pr_info("%s: irq=%d\n", timer->full_name, irq);
 
 	/* If there is clock-frequency property than use it */
-	prop = of_get_property(timer, "clock-frequency", NULL);
-	if (prop)
-		timer_clock_freq = be32_to_cpup(prop);
-	else
+	ret = of_property_read_u32(timer, "clock-frequency", &timer_clock_freq);
+	if (ret < 0)
 		timer_clock_freq = cpuinfo.cpu_clock_freq;
 
 	freq_div_hz = timer_clock_freq / HZ;
@@ -297,8 +260,8 @@ void __init time_init(void)
 #ifdef CONFIG_HEART_BEAT
 	setup_heartbeat();
 #endif
-	microblaze_clocksource_init();
-	microblaze_clockevent_init();
+	xilinx_clocksource_init();
+	xilinx_clockevent_init();
 	timer_initialized = 1;
 }
 
@@ -312,3 +275,6 @@ unsigned long long notrace sched_clock(void)
 	}
 	return 0;
 }
+
+CLOCKSOURCE_OF_DECLARE(xilinx_timer, "xlnx,xps-timer-1.00.a",
+		       xilinx_timer_init);
diff --git a/arch/microblaze/mm/fault.c b/arch/microblaze/mm/fault.c
index 731f739d17a1..fa4cf52aa7a6 100644
--- a/arch/microblaze/mm/fault.c
+++ b/arch/microblaze/mm/fault.c
@@ -92,8 +92,7 @@ void do_page_fault(struct pt_regs *regs, unsigned long address,
 	int code = SEGV_MAPERR;
 	int is_write = error_code & ESR_S;
 	int fault;
-	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
-					 (is_write ? FAULT_FLAG_WRITE : 0);
+	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
 
 	regs->ear = address;
 	regs->esr = error_code;
@@ -121,6 +120,9 @@ void do_page_fault(struct pt_regs *regs, unsigned long address,
 		die("Weird page fault", regs, SIGSEGV);
 	}
 
+	if (user_mode(regs))
+		flags |= FAULT_FLAG_USER;
+
 	/* When running in the kernel we expect faults to occur only to
 	 * addresses in user space.  All other faults represent errors in the
 	 * kernel and should generate an OOPS.  Unfortunately, in the case of an
@@ -199,6 +201,7 @@ good_area:
 	if (unlikely(is_write)) {
 		if (unlikely(!(vma->vm_flags & VM_WRITE)))
 			goto bad_area;
+		flags |= FAULT_FLAG_WRITE;
 	/* a read */
 	} else {
 		/* protection fault */
diff --git a/arch/microblaze/pci/pci-common.c b/arch/microblaze/pci/pci-common.c
index bdb8ea100e73..1b93bf0892a0 100644
--- a/arch/microblaze/pci/pci-common.c
+++ b/arch/microblaze/pci/pci-common.c
@@ -657,67 +657,42 @@ void pci_resource_to_user(const struct pci_dev *dev, int bar,
 void pci_process_bridge_OF_ranges(struct pci_controller *hose,
 				  struct device_node *dev, int primary)
 {
-	const u32 *ranges;
-	int rlen;
-	int pna = of_n_addr_cells(dev);
-	int np = pna + 5;
 	int memno = 0, isa_hole = -1;
-	u32 pci_space;
-	unsigned long long pci_addr, cpu_addr, pci_next, cpu_next, size;
 	unsigned long long isa_mb = 0;
 	struct resource *res;
+	struct of_pci_range range;
+	struct of_pci_range_parser parser;
 
 	pr_info("PCI host bridge %s %s ranges:\n",
 	       dev->full_name, primary ? "(primary)" : "");
 
-	/* Get ranges property */
-	ranges = of_get_property(dev, "ranges", &rlen);
-	if (ranges == NULL)
+	/* Check for ranges property */
+	if (of_pci_range_parser_init(&parser, dev))
 		return;
 
-	/* Parse it */
 	pr_debug("Parsing ranges property...\n");
-	while ((rlen -= np * 4) >= 0) {
+	for_each_of_pci_range(&parser, &range) {
 		/* Read next ranges element */
-		pci_space = ranges[0];
-		pci_addr = of_read_number(ranges + 1, 2);
-		cpu_addr = of_translate_address(dev, ranges + 3);
-		size = of_read_number(ranges + pna + 3, 2);
-
 		pr_debug("pci_space: 0x%08x pci_addr:0x%016llx ",
-				pci_space, pci_addr);
+				range.pci_space, range.pci_addr);
 		pr_debug("cpu_addr:0x%016llx size:0x%016llx\n",
-					cpu_addr, size);
-
-		ranges += np;
+					range.cpu_addr, range.size);
 
 		/* If we failed translation or got a zero-sized region
 		 * (some FW try to feed us with non sensical zero sized regions
 		 * such as power3 which look like some kind of attempt
 		 * at exposing the VGA memory hole)
 		 */
-		if (cpu_addr == OF_BAD_ADDR || size == 0)
+		if (range.cpu_addr == OF_BAD_ADDR || range.size == 0)
 			continue;
 
-		/* Now consume following elements while they are contiguous */
-		for (; rlen >= np * sizeof(u32);
-		     ranges += np, rlen -= np * 4) {
-			if (ranges[0] != pci_space)
-				break;
-			pci_next = of_read_number(ranges + 1, 2);
-			cpu_next = of_translate_address(dev, ranges + 3);
-			if (pci_next != pci_addr + size ||
-			    cpu_next != cpu_addr + size)
-				break;
-			size += of_read_number(ranges + pna + 3, 2);
-		}
-
 		/* Act based on address space type */
 		res = NULL;
-		switch ((pci_space >> 24) & 0x3) {
-		case 1:		/* PCI IO space */
+		switch (range.flags & IORESOURCE_TYPE_BITS) {
+		case IORESOURCE_IO:
 			pr_info("  IO 0x%016llx..0x%016llx -> 0x%016llx\n",
-			       cpu_addr, cpu_addr + size - 1, pci_addr);
+				range.cpu_addr, range.cpu_addr + range.size - 1,
+				range.pci_addr);
 
 			/* We support only one IO range */
 			if (hose->pci_io_size) {
@@ -725,11 +700,12 @@ void pci_process_bridge_OF_ranges(struct pci_controller *hose,
 				continue;
 			}
 			/* On 32 bits, limit I/O space to 16MB */
-			if (size > 0x01000000)
-				size = 0x01000000;
+			if (range.size > 0x01000000)
+				range.size = 0x01000000;
 
 			/* 32 bits needs to map IOs here */
-			hose->io_base_virt = ioremap(cpu_addr, size);
+			hose->io_base_virt = ioremap(range.cpu_addr,
+						range.size);
 
 			/* Expect trouble if pci_addr is not 0 */
 			if (primary)
@@ -738,19 +714,20 @@ void pci_process_bridge_OF_ranges(struct pci_controller *hose,
 			/* pci_io_size and io_base_phys always represent IO
 			 * space starting at 0 so we factor in pci_addr
 			 */
-			hose->pci_io_size = pci_addr + size;
-			hose->io_base_phys = cpu_addr - pci_addr;
+			hose->pci_io_size = range.pci_addr + range.size;
+			hose->io_base_phys = range.cpu_addr - range.pci_addr;
 
 			/* Build resource */
 			res = &hose->io_resource;
-			res->flags = IORESOURCE_IO;
-			res->start = pci_addr;
+			range.cpu_addr = range.pci_addr;
+
 			break;
-		case 2:		/* PCI Memory space */
-		case 3:		/* PCI 64 bits Memory space */
+		case IORESOURCE_MEM:
 			pr_info(" MEM 0x%016llx..0x%016llx -> 0x%016llx %s\n",
-			       cpu_addr, cpu_addr + size - 1, pci_addr,
-			       (pci_space & 0x40000000) ? "Prefetch" : "");
+				range.cpu_addr, range.cpu_addr + range.size - 1,
+				range.pci_addr,
+				(range.pci_space & 0x40000000) ?
+				"Prefetch" : "");
 
 			/* We support only 3 memory ranges */
 			if (memno >= 3) {
@@ -758,13 +735,13 @@ void pci_process_bridge_OF_ranges(struct pci_controller *hose,
 				continue;
 			}
 			/* Handles ISA memory hole space here */
-			if (pci_addr == 0) {
-				isa_mb = cpu_addr;
+			if (range.pci_addr == 0) {
+				isa_mb = range.cpu_addr;
 				isa_hole = memno;
 				if (primary || isa_mem_base == 0)
-					isa_mem_base = cpu_addr;
-				hose->isa_mem_phys = cpu_addr;
-				hose->isa_mem_size = size;
+					isa_mem_base = range.cpu_addr;
+				hose->isa_mem_phys = range.cpu_addr;
+				hose->isa_mem_size = range.size;
 			}
 
 			/* We get the PCI/Mem offset from the first range or
@@ -772,30 +749,23 @@ void pci_process_bridge_OF_ranges(struct pci_controller *hose,
 			 * hole. If they don't match, bugger.
 			 */
 			if (memno == 0 ||
-			    (isa_hole >= 0 && pci_addr != 0 &&
+			    (isa_hole >= 0 && range.pci_addr != 0 &&
 			     hose->pci_mem_offset == isa_mb))
-				hose->pci_mem_offset = cpu_addr - pci_addr;
-			else if (pci_addr != 0 &&
-				 hose->pci_mem_offset != cpu_addr - pci_addr) {
+				hose->pci_mem_offset = range.cpu_addr -
+							range.pci_addr;
+			else if (range.pci_addr != 0 &&
+				 hose->pci_mem_offset != range.cpu_addr -
+							range.pci_addr) {
 				pr_info(" \\--> Skipped (offset mismatch) !\n");
 				continue;
 			}
 
 			/* Build resource */
 			res = &hose->mem_resources[memno++];
-			res->flags = IORESOURCE_MEM;
-			if (pci_space & 0x40000000)
-				res->flags |= IORESOURCE_PREFETCH;
-			res->start = cpu_addr;
 			break;
 		}
-		if (res != NULL) {
-			res->name = dev->full_name;
-			res->end = res->start + size - 1;
-			res->parent = NULL;
-			res->sibling = NULL;
-			res->child = NULL;
-		}
+		if (res != NULL)
+			of_pci_range_to_resource(&range, dev, res);
 	}
 
 	/* If there's an ISA hole and the pci_mem_offset is -not- matching
diff --git a/arch/microblaze/platform/Kconfig.platform b/arch/microblaze/platform/Kconfig.platform
index b1747211b8b1..db1aa5c22cea 100644
--- a/arch/microblaze/platform/Kconfig.platform
+++ b/arch/microblaze/platform/Kconfig.platform
@@ -18,28 +18,6 @@ config PLATFORM_GENERIC
 
 endchoice
 
-config SELFMOD
-	bool "Use self modified code for intc/timer"
-	depends on NO_MMU
-	default n
-	help
-	  This choice enables self-modified code for interrupt controller
-	  and timer.
-
-config SELFMOD_INTC
-	bool "Use self modified code for intc"
-	depends on SELFMOD
-	default y
-	help
-	  This choice enables self-modified code for interrupt controller.
-
-config SELFMOD_TIMER
-	bool "Use self modified code for timer"
-	depends on SELFMOD
-	default y
-	help
-	  This choice enables self-modified code for timer.
-
 config OPT_LIB_FUNCTION
 	bool "Optimalized lib function"
 	default y
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index e12764c2a9d0..f75ab4a2f246 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -25,7 +25,6 @@ config MIPS
 	select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
 	select HAVE_DMA_ATTRS
 	select HAVE_DMA_API_DEBUG
-	select HAVE_GENERIC_HARDIRQS
 	select GENERIC_IRQ_PROBE
 	select GENERIC_IRQ_SHOW
 	select GENERIC_PCI_IOMAP
@@ -95,6 +94,7 @@ config ATH79
 	select CSRC_R4K
 	select DMA_NONCOHERENT
 	select HAVE_CLK
+	select CLKDEV_LOOKUP
 	select IRQ_CPU
 	select MIPS_MACHINE
 	select SYS_HAS_CPU_MIPS32_R2
@@ -131,7 +131,6 @@ config BCM63XX
 	select IRQ_CPU
 	select SYS_HAS_CPU_MIPS32_R1
 	select SYS_HAS_CPU_BMIPS4350 if !BCM63XX_CPU_6338 && !BCM63XX_CPU_6345 && !BCM63XX_CPU_6348
-	select NR_CPUS_DEFAULT_2
 	select SYS_SUPPORTS_32BIT_KERNEL
 	select SYS_SUPPORTS_BIG_ENDIAN
 	select SYS_HAS_EARLY_PRINTK
@@ -445,6 +444,8 @@ config RALINK
 	select SYS_HAS_EARLY_PRINTK
 	select HAVE_MACH_CLKDEV
 	select CLKDEV_LOOKUP
+	select ARCH_HAS_RESET_CONTROLLER
+	select RESET_CONTROLLER
 
 config SGI_IP22
 	bool "SGI IP22 (Indy/Indigo2)"
@@ -609,7 +610,6 @@ config SIBYTE_SWARM
 	select BOOT_ELF32
 	select DMA_COHERENT
 	select HAVE_PATA_PLATFORM
-	select NR_CPUS_DEFAULT_2
 	select SIBYTE_SB1250
 	select SWAP_IO_SPACE
 	select SYS_HAS_CPU_SB1
@@ -623,7 +623,6 @@ config SIBYTE_LITTLESUR
 	select BOOT_ELF32
 	select DMA_COHERENT
 	select HAVE_PATA_PLATFORM
-	select NR_CPUS_DEFAULT_2
 	select SIBYTE_SB1250
 	select SWAP_IO_SPACE
 	select SYS_HAS_CPU_SB1
@@ -635,7 +634,6 @@ config SIBYTE_SENTOSA
 	bool "Sibyte BCM91250E-Sentosa"
 	select BOOT_ELF32
 	select DMA_COHERENT
-	select NR_CPUS_DEFAULT_2
 	select SIBYTE_SB1250
 	select SWAP_IO_SPACE
 	select SYS_HAS_CPU_SB1
@@ -727,11 +725,11 @@ config CAVIUM_OCTEON_SOC
 	select SYS_HAS_CPU_CAVIUM_OCTEON
 	select SWAP_IO_SPACE
 	select HW_HAS_PCI
-	select ARCH_SUPPORTS_MSI
 	select ZONE_DMA32
 	select USB_ARCH_HAS_OHCI
 	select USB_ARCH_HAS_EHCI
 	select HOLES_IN_ZONE
+	select ARCH_REQUIRE_GPIOLIB
 	help
 	  This option supports all of the Octeon reference boards from Cavium
 	  Networks. It builds a kernel that dynamically determines the Octeon
@@ -763,7 +761,6 @@ config NLM_XLR_BOARD
 	select CEVT_R4K
 	select CSRC_R4K
 	select IRQ_CPU
-	select ARCH_SUPPORTS_MSI
 	select ZONE_DMA32 if 64BIT
 	select SYNC_R4K
 	select SYS_HAS_EARLY_PRINTK
@@ -1862,7 +1859,6 @@ config MIPS_MT_SMP
 	select CPU_MIPSR2_IRQ_VI
 	select CPU_MIPSR2_IRQ_EI
 	select MIPS_MT
-	select NR_CPUS_DEFAULT_2
 	select SMP
 	select SYS_SUPPORTS_SCHED_SMT if SMP
 	select SYS_SUPPORTS_SMP
@@ -2173,12 +2169,6 @@ config SYS_SUPPORTS_MIPS_CMP
 config SYS_SUPPORTS_SMP
 	bool
 
-config NR_CPUS_DEFAULT_1
-	bool
-
-config NR_CPUS_DEFAULT_2
-	bool
-
 config NR_CPUS_DEFAULT_4
 	bool
 
@@ -2196,10 +2186,8 @@ config NR_CPUS_DEFAULT_64
 
 config NR_CPUS
 	int "Maximum number of CPUs (2-64)"
-	range 1 64 if NR_CPUS_DEFAULT_1
+	range 2 64
 	depends on SMP
-	default "1" if NR_CPUS_DEFAULT_1
-	default "2" if NR_CPUS_DEFAULT_2
 	default "4" if NR_CPUS_DEFAULT_4
 	default "8" if NR_CPUS_DEFAULT_8
 	default "16" if NR_CPUS_DEFAULT_16
@@ -2305,9 +2293,9 @@ config KEXEC
 
 	  It is an ongoing process to be certain the hardware in a machine
 	  is properly shutdown, so do not be surprised if this code does not
-	  initially work for you.  It may help to enable device hotplugging
-	  support.  As of this writing the exact hardware interface is
-	  strongly in flux, so no good recommendation can be made.
+	  initially work for you.  As of this writing the exact hardware
+	  interface is strongly in flux, so no good recommendation can be
+	  made.
 
 config CRASH_DUMP
 	  bool "Kernel crash dumps"
diff --git a/arch/mips/Makefile b/arch/mips/Makefile
index 37f9ef324f2f..ca8f8340d75f 100644
--- a/arch/mips/Makefile
+++ b/arch/mips/Makefile
@@ -194,6 +194,8 @@ include $(srctree)/arch/mips/Kbuild.platforms
 ifdef CONFIG_PHYSICAL_START
 load-y					= $(CONFIG_PHYSICAL_START)
 endif
+entry-y				= 0x$(shell $(NM) vmlinux 2>/dev/null \
+					| grep "\bkernel_entry\b" | cut -f1 -d \ )
 
 cflags-y			+= -I$(srctree)/arch/mips/include/asm/mach-generic
 drivers-$(CONFIG_PCI)		+= arch/mips/pci/
@@ -225,6 +227,9 @@ KBUILD_CFLAGS	+= $(cflags-y)
 KBUILD_CPPFLAGS += -DVMLINUX_LOAD_ADDRESS=$(load-y)
 KBUILD_CPPFLAGS += -DDATAOFFSET=$(if $(dataoffset-y),$(dataoffset-y),0)
 
+bootvars-y	= VMLINUX_LOAD_ADDRESS=$(load-y) \
+		  VMLINUX_ENTRY_ADDRESS=$(entry-y)
+
 LDFLAGS			+= -m $(ld-emul)
 
 ifdef CONFIG_CC_STACKPROTECTOR
@@ -254,9 +259,25 @@ drivers-$(CONFIG_OPROFILE)	+= arch/mips/oprofile/
 # suspend and hibernation support
 drivers-$(CONFIG_PM)	+= arch/mips/power/
 
+# boot image targets (arch/mips/boot/)
+boot-y			:= vmlinux.bin
+boot-y			+= vmlinux.ecoff
+boot-y			+= vmlinux.srec
+ifeq ($(shell expr $(load-y) \< 0xffffffff80000000 2> /dev/null), 0)
+boot-y			+= uImage
+boot-y			+= uImage.gz
+endif
+
+# compressed boot image targets (arch/mips/boot/compressed/)
+bootz-y			:= vmlinuz
+bootz-y			+= vmlinuz.bin
+bootz-y			+= vmlinuz.ecoff
+bootz-y			+= vmlinuz.srec
+
 ifdef CONFIG_LASAT
 rom.bin rom.sw: vmlinux
-	$(Q)$(MAKE) $(build)=arch/mips/lasat/image $@
+	$(Q)$(MAKE) $(build)=arch/mips/lasat/image \
+		$(bootvars-y) $@
 endif
 
 #
@@ -267,9 +288,6 @@ endif
 vmlinux.32: vmlinux
 	$(OBJCOPY) -O $(32bit-bfd) $(OBJCOPYFLAGS) $< $@
 
-
-#obj-$(CONFIG_KPROBES)		+= kprobes.o
-
 #
 # The 64-bit ELF tools are pretty broken so at this time we generate 64-bit
 # ELF files from 32-bit files by conversion.
@@ -280,13 +298,14 @@ vmlinux.64: vmlinux
 all:	$(all-y)
 
 # boot
-vmlinux.bin vmlinux.ecoff vmlinux.srec: $(vmlinux-32) FORCE
-	$(Q)$(MAKE) $(build)=arch/mips/boot VMLINUX=$(vmlinux-32) arch/mips/boot/$@
+$(boot-y): $(vmlinux-32) FORCE
+	$(Q)$(MAKE) $(build)=arch/mips/boot VMLINUX=$(vmlinux-32) \
+		$(bootvars-y) arch/mips/boot/$@
 
 # boot/compressed
-vmlinuz vmlinuz.bin vmlinuz.ecoff vmlinuz.srec: $(vmlinux-32) FORCE
+$(bootz-y): $(vmlinux-32) FORCE
 	$(Q)$(MAKE) $(build)=arch/mips/boot/compressed \
-	   VMLINUX_LOAD_ADDRESS=$(load-y) 32bit-bfd=$(32bit-bfd) $@
+		$(bootvars-y) 32bit-bfd=$(32bit-bfd) $@
 
 
 CLEAN_FILES += vmlinux.32 vmlinux.64
@@ -323,6 +342,8 @@ define archhelp
 	echo '  vmlinuz.ecoff        - ECOFF zboot image'
 	echo '  vmlinuz.bin          - Raw binary zboot image'
 	echo '  vmlinuz.srec         - SREC zboot image'
+	echo '  uImage               - U-Boot image'
+	echo '  uImage.gz            - U-Boot image (gzip)'
 	echo
 	echo '  These will be default as appropriate for a configured platform.'
 endef
diff --git a/arch/mips/alchemy/board-mtx1.c b/arch/mips/alchemy/board-mtx1.c
index 4a9baa9f6330..9969dbab19e3 100644
--- a/arch/mips/alchemy/board-mtx1.c
+++ b/arch/mips/alchemy/board-mtx1.c
@@ -276,7 +276,7 @@ static struct platform_device mtx1_pci_host = {
 	.resource	= alchemy_pci_host_res,
 };
 
-static struct __initdata platform_device * mtx1_devs[] = {
+static struct platform_device *mtx1_devs[] __initdata = {
 	&mtx1_pci_host,
 	&mtx1_gpio_leds,
 	&mtx1_wdt,
diff --git a/arch/mips/alchemy/common/usb.c b/arch/mips/alchemy/common/usb.c
index fcc695626117..2adc7edda49c 100644
--- a/arch/mips/alchemy/common/usb.c
+++ b/arch/mips/alchemy/common/usb.c
@@ -14,6 +14,7 @@
 #include <linux/module.h>
 #include <linux/spinlock.h>
 #include <linux/syscore_ops.h>
+#include <asm/cpu.h>
 #include <asm/mach-au1x00/au1000.h>
 
 /* control register offsets */
@@ -358,7 +359,7 @@ static inline int au1200_coherency_bug(void)
 {
 #if defined(CONFIG_DMA_COHERENT)
 	/* Au1200 AB USB does not support coherent memory */
-	if (!(read_c0_prid() & 0xff)) {
+	if (!(read_c0_prid() & PRID_REV_MASK)) {
 		printk(KERN_INFO "Au1200 USB: this is chip revision AB !!\n");
 		printk(KERN_INFO "Au1200 USB: update your board or re-configure"
 				 " the kernel\n");
diff --git a/arch/mips/ath79/clock.c b/arch/mips/ath79/clock.c
index 765ef30e3e1c..26479f437675 100644
--- a/arch/mips/ath79/clock.c
+++ b/arch/mips/ath79/clock.c
@@ -16,6 +16,7 @@
 #include <linux/init.h>
 #include <linux/err.h>
 #include <linux/clk.h>
+#include <linux/clkdev.h>
 
 #include <asm/div64.h>
 
@@ -31,92 +32,132 @@ struct clk {
 	unsigned long rate;
 };
 
-static struct clk ath79_ref_clk;
-static struct clk ath79_cpu_clk;
-static struct clk ath79_ddr_clk;
-static struct clk ath79_ahb_clk;
-static struct clk ath79_wdt_clk;
-static struct clk ath79_uart_clk;
+static void __init ath79_add_sys_clkdev(const char *id, unsigned long rate)
+{
+	struct clk *clk;
+	int err;
+
+	clk = kzalloc(sizeof(*clk), GFP_KERNEL);
+	if (!clk)
+		panic("failed to allocate %s clock structure", id);
+
+	clk->rate = rate;
+
+	err = clk_register_clkdev(clk, id, NULL);
+	if (err)
+		panic("unable to register %s clock device", id);
+}
 
 static void __init ar71xx_clocks_init(void)
 {
+	unsigned long ref_rate;
+	unsigned long cpu_rate;
+	unsigned long ddr_rate;
+	unsigned long ahb_rate;
 	u32 pll;
 	u32 freq;
 	u32 div;
 
-	ath79_ref_clk.rate = AR71XX_BASE_FREQ;
+	ref_rate = AR71XX_BASE_FREQ;
 
 	pll = ath79_pll_rr(AR71XX_PLL_REG_CPU_CONFIG);
 
 	div = ((pll >> AR71XX_PLL_DIV_SHIFT) & AR71XX_PLL_DIV_MASK) + 1;
-	freq = div * ath79_ref_clk.rate;
+	freq = div * ref_rate;
 
 	div = ((pll >> AR71XX_CPU_DIV_SHIFT) & AR71XX_CPU_DIV_MASK) + 1;
-	ath79_cpu_clk.rate = freq / div;
+	cpu_rate = freq / div;
 
 	div = ((pll >> AR71XX_DDR_DIV_SHIFT) & AR71XX_DDR_DIV_MASK) + 1;
-	ath79_ddr_clk.rate = freq / div;
+	ddr_rate = freq / div;
 
 	div = (((pll >> AR71XX_AHB_DIV_SHIFT) & AR71XX_AHB_DIV_MASK) + 1) * 2;
-	ath79_ahb_clk.rate = ath79_cpu_clk.rate / div;
+	ahb_rate = cpu_rate / div;
+
+	ath79_add_sys_clkdev("ref", ref_rate);
+	ath79_add_sys_clkdev("cpu", cpu_rate);
+	ath79_add_sys_clkdev("ddr", ddr_rate);
+	ath79_add_sys_clkdev("ahb", ahb_rate);
 
-	ath79_wdt_clk.rate = ath79_ahb_clk.rate;
-	ath79_uart_clk.rate = ath79_ahb_clk.rate;
+	clk_add_alias("wdt", NULL, "ahb", NULL);
+	clk_add_alias("uart", NULL, "ahb", NULL);
 }
 
 static void __init ar724x_clocks_init(void)
 {
+	unsigned long ref_rate;
+	unsigned long cpu_rate;
+	unsigned long ddr_rate;
+	unsigned long ahb_rate;
 	u32 pll;
 	u32 freq;
 	u32 div;
 
-	ath79_ref_clk.rate = AR724X_BASE_FREQ;
+	ref_rate = AR724X_BASE_FREQ;
 	pll = ath79_pll_rr(AR724X_PLL_REG_CPU_CONFIG);
 
 	div = ((pll >> AR724X_PLL_DIV_SHIFT) & AR724X_PLL_DIV_MASK);
-	freq = div * ath79_ref_clk.rate;
+	freq = div * ref_rate;
 
 	div = ((pll >> AR724X_PLL_REF_DIV_SHIFT) & AR724X_PLL_REF_DIV_MASK);
 	freq *= div;
 
-	ath79_cpu_clk.rate = freq;
+	cpu_rate = freq;
 
 	div = ((pll >> AR724X_DDR_DIV_SHIFT) & AR724X_DDR_DIV_MASK) + 1;
-	ath79_ddr_clk.rate = freq / div;
+	ddr_rate = freq / div;
 
 	div = (((pll >> AR724X_AHB_DIV_SHIFT) & AR724X_AHB_DIV_MASK) + 1) * 2;
-	ath79_ahb_clk.rate = ath79_cpu_clk.rate / div;
+	ahb_rate = cpu_rate / div;
+
+	ath79_add_sys_clkdev("ref", ref_rate);
+	ath79_add_sys_clkdev("cpu", cpu_rate);
+	ath79_add_sys_clkdev("ddr", ddr_rate);
+	ath79_add_sys_clkdev("ahb", ahb_rate);
 
-	ath79_wdt_clk.rate = ath79_ahb_clk.rate;
-	ath79_uart_clk.rate = ath79_ahb_clk.rate;
+	clk_add_alias("wdt", NULL, "ahb", NULL);
+	clk_add_alias("uart", NULL, "ahb", NULL);
 }
 
 static void __init ar913x_clocks_init(void)
 {
+	unsigned long ref_rate;
+	unsigned long cpu_rate;
+	unsigned long ddr_rate;
+	unsigned long ahb_rate;
 	u32 pll;
 	u32 freq;
 	u32 div;
 
-	ath79_ref_clk.rate = AR913X_BASE_FREQ;
+	ref_rate = AR913X_BASE_FREQ;
 	pll = ath79_pll_rr(AR913X_PLL_REG_CPU_CONFIG);
 
 	div = ((pll >> AR913X_PLL_DIV_SHIFT) & AR913X_PLL_DIV_MASK);
-	freq = div * ath79_ref_clk.rate;
+	freq = div * ref_rate;
 
-	ath79_cpu_clk.rate = freq;
+	cpu_rate = freq;
 
 	div = ((pll >> AR913X_DDR_DIV_SHIFT) & AR913X_DDR_DIV_MASK) + 1;
-	ath79_ddr_clk.rate = freq / div;
+	ddr_rate = freq / div;
 
 	div = (((pll >> AR913X_AHB_DIV_SHIFT) & AR913X_AHB_DIV_MASK) + 1) * 2;
-	ath79_ahb_clk.rate = ath79_cpu_clk.rate / div;
+	ahb_rate = cpu_rate / div;
 
-	ath79_wdt_clk.rate = ath79_ahb_clk.rate;
-	ath79_uart_clk.rate = ath79_ahb_clk.rate;
+	ath79_add_sys_clkdev("ref", ref_rate);
+	ath79_add_sys_clkdev("cpu", cpu_rate);
+	ath79_add_sys_clkdev("ddr", ddr_rate);
+	ath79_add_sys_clkdev("ahb", ahb_rate);
+
+	clk_add_alias("wdt", NULL, "ahb", NULL);
+	clk_add_alias("uart", NULL, "ahb", NULL);
 }
 
 static void __init ar933x_clocks_init(void)
 {
+	unsigned long ref_rate;
+	unsigned long cpu_rate;
+	unsigned long ddr_rate;
+	unsigned long ahb_rate;
 	u32 clock_ctrl;
 	u32 cpu_config;
 	u32 freq;
@@ -124,21 +165,21 @@ static void __init ar933x_clocks_init(void)
 
 	t = ath79_reset_rr(AR933X_RESET_REG_BOOTSTRAP);
 	if (t & AR933X_BOOTSTRAP_REF_CLK_40)
-		ath79_ref_clk.rate = (40 * 1000 * 1000);
+		ref_rate = (40 * 1000 * 1000);
 	else
-		ath79_ref_clk.rate = (25 * 1000 * 1000);
+		ref_rate = (25 * 1000 * 1000);
 
 	clock_ctrl = ath79_pll_rr(AR933X_PLL_CLOCK_CTRL_REG);
 	if (clock_ctrl & AR933X_PLL_CLOCK_CTRL_BYPASS) {
-		ath79_cpu_clk.rate = ath79_ref_clk.rate;
-		ath79_ahb_clk.rate = ath79_ref_clk.rate;
-		ath79_ddr_clk.rate = ath79_ref_clk.rate;
+		cpu_rate = ref_rate;
+		ahb_rate = ref_rate;
+		ddr_rate = ref_rate;
 	} else {
 		cpu_config = ath79_pll_rr(AR933X_PLL_CPU_CONFIG_REG);
 
 		t = (cpu_config >> AR933X_PLL_CPU_CONFIG_REFDIV_SHIFT) &
 		    AR933X_PLL_CPU_CONFIG_REFDIV_MASK;
-		freq = ath79_ref_clk.rate / t;
+		freq = ref_rate / t;
 
 		t = (cpu_config >> AR933X_PLL_CPU_CONFIG_NINT_SHIFT) &
 		    AR933X_PLL_CPU_CONFIG_NINT_MASK;
@@ -153,19 +194,24 @@ static void __init ar933x_clocks_init(void)
 
 		t = ((clock_ctrl >> AR933X_PLL_CLOCK_CTRL_CPU_DIV_SHIFT) &
 		     AR933X_PLL_CLOCK_CTRL_CPU_DIV_MASK) + 1;
-		ath79_cpu_clk.rate = freq / t;
+		cpu_rate = freq / t;
 
 		t = ((clock_ctrl >> AR933X_PLL_CLOCK_CTRL_DDR_DIV_SHIFT) &
 		      AR933X_PLL_CLOCK_CTRL_DDR_DIV_MASK) + 1;
-		ath79_ddr_clk.rate = freq / t;
+		ddr_rate = freq / t;
 
 		t = ((clock_ctrl >> AR933X_PLL_CLOCK_CTRL_AHB_DIV_SHIFT) &
 		     AR933X_PLL_CLOCK_CTRL_AHB_DIV_MASK) + 1;
-		ath79_ahb_clk.rate = freq / t;
+		ahb_rate = freq / t;
 	}
 
-	ath79_wdt_clk.rate = ath79_ref_clk.rate;
-	ath79_uart_clk.rate = ath79_ref_clk.rate;
+	ath79_add_sys_clkdev("ref", ref_rate);
+	ath79_add_sys_clkdev("cpu", cpu_rate);
+	ath79_add_sys_clkdev("ddr", ddr_rate);
+	ath79_add_sys_clkdev("ahb", ahb_rate);
+
+	clk_add_alias("wdt", NULL, "ahb", NULL);
+	clk_add_alias("uart", NULL, "ref", NULL);
 }
 
 static u32 __init ar934x_get_pll_freq(u32 ref, u32 ref_div, u32 nint, u32 nfrac,
@@ -174,12 +220,12 @@ static u32 __init ar934x_get_pll_freq(u32 ref, u32 ref_div, u32 nint, u32 nfrac,
 	u64 t;
 	u32 ret;
 
-	t = ath79_ref_clk.rate;
+	t = ref;
 	t *= nint;
 	do_div(t, ref_div);
 	ret = t;
 
-	t = ath79_ref_clk.rate;
+	t = ref;
 	t *= nfrac;
 	do_div(t, ref_div * frac);
 	ret += t;
@@ -190,6 +236,10 @@ static u32 __init ar934x_get_pll_freq(u32 ref, u32 ref_div, u32 nint, u32 nfrac,
 
 static void __init ar934x_clocks_init(void)
 {
+	unsigned long ref_rate;
+	unsigned long cpu_rate;
+	unsigned long ddr_rate;
+	unsigned long ahb_rate;
 	u32 pll, out_div, ref_div, nint, nfrac, frac, clk_ctrl, postdiv;
 	u32 cpu_pll, ddr_pll;
 	u32 bootstrap;
@@ -199,9 +249,9 @@ static void __init ar934x_clocks_init(void)
 
 	bootstrap = ath79_reset_rr(AR934X_RESET_REG_BOOTSTRAP);
 	if (bootstrap & AR934X_BOOTSTRAP_REF_CLK_40)
-		ath79_ref_clk.rate = 40 * 1000 * 1000;
+		ref_rate = 40 * 1000 * 1000;
 	else
-		ath79_ref_clk.rate = 25 * 1000 * 1000;
+		ref_rate = 25 * 1000 * 1000;
 
 	pll = __raw_readl(dpll_base + AR934X_SRIF_CPU_DPLL2_REG);
 	if (pll & AR934X_SRIF_DPLL2_LOCAL_PLL) {
@@ -227,7 +277,7 @@ static void __init ar934x_clocks_init(void)
 		frac = 1 << 6;
 	}
 
-	cpu_pll = ar934x_get_pll_freq(ath79_ref_clk.rate, ref_div, nint,
+	cpu_pll = ar934x_get_pll_freq(ref_rate, ref_div, nint,
 				      nfrac, frac, out_div);
 
 	pll = __raw_readl(dpll_base + AR934X_SRIF_DDR_DPLL2_REG);
@@ -254,7 +304,7 @@ static void __init ar934x_clocks_init(void)
 		frac = 1 << 10;
 	}
 
-	ddr_pll = ar934x_get_pll_freq(ath79_ref_clk.rate, ref_div, nint,
+	ddr_pll = ar934x_get_pll_freq(ref_rate, ref_div, nint,
 				      nfrac, frac, out_div);
 
 	clk_ctrl = ath79_pll_rr(AR934X_PLL_CPU_DDR_CLK_CTRL_REG);
@@ -263,49 +313,58 @@ static void __init ar934x_clocks_init(void)
 		  AR934X_PLL_CPU_DDR_CLK_CTRL_CPU_POST_DIV_MASK;
 
 	if (clk_ctrl & AR934X_PLL_CPU_DDR_CLK_CTRL_CPU_PLL_BYPASS)
-		ath79_cpu_clk.rate = ath79_ref_clk.rate;
+		cpu_rate = ref_rate;
 	else if (clk_ctrl & AR934X_PLL_CPU_DDR_CLK_CTRL_CPUCLK_FROM_CPUPLL)
-		ath79_cpu_clk.rate = cpu_pll / (postdiv + 1);
+		cpu_rate = cpu_pll / (postdiv + 1);
 	else
-		ath79_cpu_clk.rate = ddr_pll / (postdiv + 1);
+		cpu_rate = ddr_pll / (postdiv + 1);
 
 	postdiv = (clk_ctrl >> AR934X_PLL_CPU_DDR_CLK_CTRL_DDR_POST_DIV_SHIFT) &
 		  AR934X_PLL_CPU_DDR_CLK_CTRL_DDR_POST_DIV_MASK;
 
 	if (clk_ctrl & AR934X_PLL_CPU_DDR_CLK_CTRL_DDR_PLL_BYPASS)
-		ath79_ddr_clk.rate = ath79_ref_clk.rate;
+		ddr_rate = ref_rate;
 	else if (clk_ctrl & AR934X_PLL_CPU_DDR_CLK_CTRL_DDRCLK_FROM_DDRPLL)
-		ath79_ddr_clk.rate = ddr_pll / (postdiv + 1);
+		ddr_rate = ddr_pll / (postdiv + 1);
 	else
-		ath79_ddr_clk.rate = cpu_pll / (postdiv + 1);
+		ddr_rate = cpu_pll / (postdiv + 1);
 
 	postdiv = (clk_ctrl >> AR934X_PLL_CPU_DDR_CLK_CTRL_AHB_POST_DIV_SHIFT) &
 		  AR934X_PLL_CPU_DDR_CLK_CTRL_AHB_POST_DIV_MASK;
 
 	if (clk_ctrl & AR934X_PLL_CPU_DDR_CLK_CTRL_AHB_PLL_BYPASS)
-		ath79_ahb_clk.rate = ath79_ref_clk.rate;
+		ahb_rate = ref_rate;
 	else if (clk_ctrl & AR934X_PLL_CPU_DDR_CLK_CTRL_AHBCLK_FROM_DDRPLL)
-		ath79_ahb_clk.rate = ddr_pll / (postdiv + 1);
+		ahb_rate = ddr_pll / (postdiv + 1);
 	else
-		ath79_ahb_clk.rate = cpu_pll / (postdiv + 1);
+		ahb_rate = cpu_pll / (postdiv + 1);
+
+	ath79_add_sys_clkdev("ref", ref_rate);
+	ath79_add_sys_clkdev("cpu", cpu_rate);
+	ath79_add_sys_clkdev("ddr", ddr_rate);
+	ath79_add_sys_clkdev("ahb", ahb_rate);
 
-	ath79_wdt_clk.rate = ath79_ref_clk.rate;
-	ath79_uart_clk.rate = ath79_ref_clk.rate;
+	clk_add_alias("wdt", NULL, "ref", NULL);
+	clk_add_alias("uart", NULL, "ref", NULL);
 
 	iounmap(dpll_base);
 }
 
 static void __init qca955x_clocks_init(void)
 {
+	unsigned long ref_rate;
+	unsigned long cpu_rate;
+	unsigned long ddr_rate;
+	unsigned long ahb_rate;
 	u32 pll, out_div, ref_div, nint, frac, clk_ctrl, postdiv;
 	u32 cpu_pll, ddr_pll;
 	u32 bootstrap;
 
 	bootstrap = ath79_reset_rr(QCA955X_RESET_REG_BOOTSTRAP);
 	if (bootstrap &	QCA955X_BOOTSTRAP_REF_CLK_40)
-		ath79_ref_clk.rate = 40 * 1000 * 1000;
+		ref_rate = 40 * 1000 * 1000;
 	else
-		ath79_ref_clk.rate = 25 * 1000 * 1000;
+		ref_rate = 25 * 1000 * 1000;
 
 	pll = ath79_pll_rr(QCA955X_PLL_CPU_CONFIG_REG);
 	out_div = (pll >> QCA955X_PLL_CPU_CONFIG_OUTDIV_SHIFT) &
@@ -317,8 +376,8 @@ static void __init qca955x_clocks_init(void)
 	frac = (pll >> QCA955X_PLL_CPU_CONFIG_NFRAC_SHIFT) &
 	       QCA955X_PLL_CPU_CONFIG_NFRAC_MASK;
 
-	cpu_pll = nint * ath79_ref_clk.rate / ref_div;
-	cpu_pll += frac * ath79_ref_clk.rate / (ref_div * (1 << 6));
+	cpu_pll = nint * ref_rate / ref_div;
+	cpu_pll += frac * ref_rate / (ref_div * (1 << 6));
 	cpu_pll /= (1 << out_div);
 
 	pll = ath79_pll_rr(QCA955X_PLL_DDR_CONFIG_REG);
@@ -331,8 +390,8 @@ static void __init qca955x_clocks_init(void)
 	frac = (pll >> QCA955X_PLL_DDR_CONFIG_NFRAC_SHIFT) &
 	       QCA955X_PLL_DDR_CONFIG_NFRAC_MASK;
 
-	ddr_pll = nint * ath79_ref_clk.rate / ref_div;
-	ddr_pll += frac * ath79_ref_clk.rate / (ref_div * (1 << 10));
+	ddr_pll = nint * ref_rate / ref_div;
+	ddr_pll += frac * ref_rate / (ref_div * (1 << 10));
 	ddr_pll /= (1 << out_div);
 
 	clk_ctrl = ath79_pll_rr(QCA955X_PLL_CLK_CTRL_REG);
@@ -341,34 +400,39 @@ static void __init qca955x_clocks_init(void)
 		  QCA955X_PLL_CLK_CTRL_CPU_POST_DIV_MASK;
 
 	if (clk_ctrl & QCA955X_PLL_CLK_CTRL_CPU_PLL_BYPASS)
-		ath79_cpu_clk.rate = ath79_ref_clk.rate;
+		cpu_rate = ref_rate;
 	else if (clk_ctrl & QCA955X_PLL_CLK_CTRL_CPUCLK_FROM_CPUPLL)
-		ath79_cpu_clk.rate = ddr_pll / (postdiv + 1);
+		cpu_rate = ddr_pll / (postdiv + 1);
 	else
-		ath79_cpu_clk.rate = cpu_pll / (postdiv + 1);
+		cpu_rate = cpu_pll / (postdiv + 1);
 
 	postdiv = (clk_ctrl >> QCA955X_PLL_CLK_CTRL_DDR_POST_DIV_SHIFT) &
 		  QCA955X_PLL_CLK_CTRL_DDR_POST_DIV_MASK;
 
 	if (clk_ctrl & QCA955X_PLL_CLK_CTRL_DDR_PLL_BYPASS)
-		ath79_ddr_clk.rate = ath79_ref_clk.rate;
+		ddr_rate = ref_rate;
 	else if (clk_ctrl & QCA955X_PLL_CLK_CTRL_DDRCLK_FROM_DDRPLL)
-		ath79_ddr_clk.rate = cpu_pll / (postdiv + 1);
+		ddr_rate = cpu_pll / (postdiv + 1);
 	else
-		ath79_ddr_clk.rate = ddr_pll / (postdiv + 1);
+		ddr_rate = ddr_pll / (postdiv + 1);
 
 	postdiv = (clk_ctrl >> QCA955X_PLL_CLK_CTRL_AHB_POST_DIV_SHIFT) &
 		  QCA955X_PLL_CLK_CTRL_AHB_POST_DIV_MASK;
 
 	if (clk_ctrl & QCA955X_PLL_CLK_CTRL_AHB_PLL_BYPASS)
-		ath79_ahb_clk.rate = ath79_ref_clk.rate;
+		ahb_rate = ref_rate;
 	else if (clk_ctrl & QCA955X_PLL_CLK_CTRL_AHBCLK_FROM_DDRPLL)
-		ath79_ahb_clk.rate = ddr_pll / (postdiv + 1);
+		ahb_rate = ddr_pll / (postdiv + 1);
 	else
-		ath79_ahb_clk.rate = cpu_pll / (postdiv + 1);
+		ahb_rate = cpu_pll / (postdiv + 1);
 
-	ath79_wdt_clk.rate = ath79_ref_clk.rate;
-	ath79_uart_clk.rate = ath79_ref_clk.rate;
+	ath79_add_sys_clkdev("ref", ref_rate);
+	ath79_add_sys_clkdev("cpu", cpu_rate);
+	ath79_add_sys_clkdev("ddr", ddr_rate);
+	ath79_add_sys_clkdev("ahb", ahb_rate);
+
+	clk_add_alias("wdt", NULL, "ref", NULL);
+	clk_add_alias("uart", NULL, "ref", NULL);
 }
 
 void __init ath79_clocks_init(void)
@@ -387,46 +451,27 @@ void __init ath79_clocks_init(void)
 		qca955x_clocks_init();
 	else
 		BUG();
-
-	pr_info("Clocks: CPU:%lu.%03luMHz, DDR:%lu.%03luMHz, AHB:%lu.%03luMHz, "
-		"Ref:%lu.%03luMHz",
-		ath79_cpu_clk.rate / 1000000,
-		(ath79_cpu_clk.rate / 1000) % 1000,
-		ath79_ddr_clk.rate / 1000000,
-		(ath79_ddr_clk.rate / 1000) % 1000,
-		ath79_ahb_clk.rate / 1000000,
-		(ath79_ahb_clk.rate / 1000) % 1000,
-		ath79_ref_clk.rate / 1000000,
-		(ath79_ref_clk.rate / 1000) % 1000);
 }
 
-/*
- * Linux clock API
- */
-struct clk *clk_get(struct device *dev, const char *id)
+unsigned long __init
+ath79_get_sys_clk_rate(const char *id)
 {
-	if (!strcmp(id, "ref"))
-		return &ath79_ref_clk;
-
-	if (!strcmp(id, "cpu"))
-		return &ath79_cpu_clk;
-
-	if (!strcmp(id, "ddr"))
-		return &ath79_ddr_clk;
-
-	if (!strcmp(id, "ahb"))
-		return &ath79_ahb_clk;
+	struct clk *clk;
+	unsigned long rate;
 
-	if (!strcmp(id, "wdt"))
-		return &ath79_wdt_clk;
+	clk = clk_get(NULL, id);
+	if (IS_ERR(clk))
+		panic("unable to get %s clock, err=%d", id, (int) PTR_ERR(clk));
 
-	if (!strcmp(id, "uart"))
-		return &ath79_uart_clk;
+	rate = clk_get_rate(clk);
+	clk_put(clk);
 
-	return ERR_PTR(-ENOENT);
+	return rate;
 }
-EXPORT_SYMBOL(clk_get);
 
+/*
+ * Linux clock API
+ */
 int clk_enable(struct clk *clk)
 {
 	return 0;
@@ -443,8 +488,3 @@ unsigned long clk_get_rate(struct clk *clk)
 	return clk->rate;
 }
 EXPORT_SYMBOL(clk_get_rate);
-
-void clk_put(struct clk *clk)
-{
-}
-EXPORT_SYMBOL(clk_put);
diff --git a/arch/mips/ath79/common.h b/arch/mips/ath79/common.h
index 561906c2345e..648d2dafbc56 100644
--- a/arch/mips/ath79/common.h
+++ b/arch/mips/ath79/common.h
@@ -21,6 +21,8 @@
 #define ATH79_MEM_SIZE_MAX	(128 * 1024 * 1024)
 
 void ath79_clocks_init(void);
+unsigned long ath79_get_sys_clk_rate(const char *id);
+
 void ath79_ddr_wb_flush(unsigned int reg);
 
 void ath79_gpio_function_enable(u32 mask);
diff --git a/arch/mips/ath79/dev-common.c b/arch/mips/ath79/dev-common.c
index a3a2741d0688..c3b04c929f29 100644
--- a/arch/mips/ath79/dev-common.c
+++ b/arch/mips/ath79/dev-common.c
@@ -81,21 +81,19 @@ static struct platform_device ar933x_uart_device = {
 
 void __init ath79_register_uart(void)
 {
-	struct clk *clk;
+	unsigned long uart_clk_rate;
 
-	clk = clk_get(NULL, "uart");
-	if (IS_ERR(clk))
-		panic("unable to get UART clock, err=%ld", PTR_ERR(clk));
+	uart_clk_rate = ath79_get_sys_clk_rate("uart");
 
 	if (soc_is_ar71xx() ||
 	    soc_is_ar724x() ||
 	    soc_is_ar913x() ||
 	    soc_is_ar934x() ||
 	    soc_is_qca955x()) {
-		ath79_uart_data[0].uartclk = clk_get_rate(clk);
+		ath79_uart_data[0].uartclk = uart_clk_rate;
 		platform_device_register(&ath79_uart_device);
 	} else if (soc_is_ar933x()) {
-		ar933x_uart_data.uartclk = clk_get_rate(clk);
+		ar933x_uart_data.uartclk = uart_clk_rate;
 		platform_device_register(&ar933x_uart_device);
 	} else {
 		BUG();
diff --git a/arch/mips/ath79/setup.c b/arch/mips/ath79/setup.c
index 80f4ecd42b0d..64807a4809d0 100644
--- a/arch/mips/ath79/setup.c
+++ b/arch/mips/ath79/setup.c
@@ -200,7 +200,6 @@ void __init plat_mem_setup(void)
 
 	ath79_detect_sys_type();
 	detect_memory_region(0, ATH79_MEM_SIZE_MIN, ATH79_MEM_SIZE_MAX);
-	ath79_clocks_init();
 
 	_machine_restart = ath79_restart;
 	_machine_halt = ath79_halt;
@@ -209,13 +208,25 @@ void __init plat_mem_setup(void)
 
 void __init plat_time_init(void)
 {
-	struct clk *clk;
+	unsigned long cpu_clk_rate;
+	unsigned long ahb_clk_rate;
+	unsigned long ddr_clk_rate;
+	unsigned long ref_clk_rate;
+
+	ath79_clocks_init();
+
+	cpu_clk_rate = ath79_get_sys_clk_rate("cpu");
+	ahb_clk_rate = ath79_get_sys_clk_rate("ahb");
+	ddr_clk_rate = ath79_get_sys_clk_rate("ddr");
+	ref_clk_rate = ath79_get_sys_clk_rate("ref");
 
-	clk = clk_get(NULL, "cpu");
-	if (IS_ERR(clk))
-		panic("unable to get CPU clock, err=%ld", PTR_ERR(clk));
+	pr_info("Clocks: CPU:%lu.%03luMHz, DDR:%lu.%03luMHz, AHB:%lu.%03luMHz, Ref:%lu.%03luMHz",
+		cpu_clk_rate / 1000000, (cpu_clk_rate / 1000) % 1000,
+		ddr_clk_rate / 1000000, (ddr_clk_rate / 1000) % 1000,
+		ahb_clk_rate / 1000000, (ahb_clk_rate / 1000) % 1000,
+		ref_clk_rate / 1000000, (ref_clk_rate / 1000) % 1000);
 
-	mips_hpt_frequency = clk_get_rate(clk) / 2;
+	mips_hpt_frequency = cpu_clk_rate / 2;
 }
 
 static int __init ath79_setup(void)
diff --git a/arch/mips/bcm63xx/cpu.c b/arch/mips/bcm63xx/cpu.c
index 7e17374a9ae8..b713cd64b087 100644
--- a/arch/mips/bcm63xx/cpu.c
+++ b/arch/mips/bcm63xx/cpu.c
@@ -306,14 +306,14 @@ void __init bcm63xx_cpu_init(void)
 
 	switch (c->cputype) {
 	case CPU_BMIPS3300:
-		if ((read_c0_prid() & 0xff00) != PRID_IMP_BMIPS3300_ALT)
+		if ((read_c0_prid() & PRID_IMP_MASK) != PRID_IMP_BMIPS3300_ALT)
 			__cpu_name[cpu] = "Broadcom BCM6338";
 		/* fall-through */
 	case CPU_BMIPS32:
 		chipid_reg = BCM_6345_PERF_BASE;
 		break;
 	case CPU_BMIPS4350:
-		switch ((read_c0_prid() & 0xff)) {
+		switch ((read_c0_prid() & PRID_REV_MASK)) {
 		case 0x04:
 			chipid_reg = BCM_3368_PERF_BASE;
 			break;
diff --git a/arch/mips/bcm63xx/nvram.c b/arch/mips/bcm63xx/nvram.c
index e652e578a679..4b50d40f7451 100644
--- a/arch/mips/bcm63xx/nvram.c
+++ b/arch/mips/bcm63xx/nvram.c
@@ -35,6 +35,8 @@ struct bcm963xx_nvram {
 	u32	checksum_high;
 };
 
+#define BCM63XX_DEFAULT_PSI_SIZE	64
+
 static struct bcm963xx_nvram nvram;
 static int mac_addr_used;
 
@@ -114,3 +116,12 @@ int bcm63xx_nvram_get_mac_address(u8 *mac)
 	return 0;
 }
 EXPORT_SYMBOL(bcm63xx_nvram_get_mac_address);
+
+int bcm63xx_nvram_get_psi_size(void)
+{
+	if (nvram.psi_size > 0)
+		return nvram.psi_size;
+
+	return BCM63XX_DEFAULT_PSI_SIZE;
+}
+EXPORT_SYMBOL(bcm63xx_nvram_get_psi_size);
diff --git a/arch/mips/boot/.gitignore b/arch/mips/boot/.gitignore
index f210b09ececc..a73d6e2c4f64 100644
--- a/arch/mips/boot/.gitignore
+++ b/arch/mips/boot/.gitignore
@@ -4,3 +4,4 @@ vmlinux.*
 zImage
 zImage.tmp
 calc_vmlinuz_load_addr
+uImage
diff --git a/arch/mips/boot/Makefile b/arch/mips/boot/Makefile
index 851261e9fdc0..1466c0026093 100644
--- a/arch/mips/boot/Makefile
+++ b/arch/mips/boot/Makefile
@@ -40,3 +40,18 @@ quiet_cmd_srec = OBJCOPY $@
       cmd_srec = $(OBJCOPY) -S -O srec $(strip-flags) $(VMLINUX) $@
 $(obj)/vmlinux.srec: $(VMLINUX) FORCE
 	$(call if_changed,srec)
+
+UIMAGE_LOADADDR  = $(VMLINUX_LOAD_ADDRESS)
+UIMAGE_ENTRYADDR = $(VMLINUX_ENTRY_ADDRESS)
+
+$(obj)/vmlinux.bin.gz: $(obj)/vmlinux.bin FORCE
+	$(call if_changed,gzip)
+
+targets += uImage.gz
+$(obj)/uImage.gz: $(obj)/vmlinux.bin.gz FORCE
+	$(call if_changed,uimage,gzip)
+
+targets += uImage
+$(obj)/uImage: $(obj)/uImage.gz FORCE
+	@ln -sf $(notdir $<) $@
+	@echo '  Image $@ is ready'
diff --git a/arch/mips/boot/compressed/Makefile b/arch/mips/boot/compressed/Makefile
index bb1dbf4abb9d..0048c0897896 100644
--- a/arch/mips/boot/compressed/Makefile
+++ b/arch/mips/boot/compressed/Makefile
@@ -25,7 +25,7 @@ KBUILD_CFLAGS := $(LINUXINCLUDE) $(KBUILD_CFLAGS) -D__KERNEL__ \
 
 KBUILD_AFLAGS := $(LINUXINCLUDE) $(KBUILD_AFLAGS) -D__ASSEMBLY__ \
 	-DBOOT_HEAP_SIZE=$(BOOT_HEAP_SIZE) \
-	-DKERNEL_ENTRY=0x$(shell $(NM) $(objtree)/$(KBUILD_IMAGE) 2>/dev/null | grep " kernel_entry" | cut -f1 -d \ )
+	-DKERNEL_ENTRY=$(VMLINUX_ENTRY_ADDRESS)
 
 targets := head.o decompress.o dbg.o uart-16550.o uart-alchemy.o
 
diff --git a/arch/mips/boot/dts/include/dt-bindings b/arch/mips/boot/dts/include/dt-bindings
new file mode 120000
index 000000000000..08c00e4972fa
--- /dev/null
+++ b/arch/mips/boot/dts/include/dt-bindings
@@ -0,0 +1 @@
+../../../../../include/dt-bindings
+\ No newline at end of file
diff --git a/arch/mips/cavium-octeon/csrc-octeon.c b/arch/mips/cavium-octeon/csrc-octeon.c
index 02193953eb9e..b752c4ed0b79 100644
--- a/arch/mips/cavium-octeon/csrc-octeon.c
+++ b/arch/mips/cavium-octeon/csrc-octeon.c
@@ -12,6 +12,7 @@
 #include <linux/smp.h>
 
 #include <asm/cpu-info.h>
+#include <asm/cpu-type.h>
 #include <asm/time.h>
 
 #include <asm/octeon/octeon.h>
diff --git a/arch/mips/cavium-octeon/octeon-irq.c b/arch/mips/cavium-octeon/octeon-irq.c
index 9d36774bded1..25fbfae06c1f 100644
--- a/arch/mips/cavium-octeon/octeon-irq.c
+++ b/arch/mips/cavium-octeon/octeon-irq.c
@@ -1776,7 +1776,7 @@ asmlinkage void plat_irq_dispatch(void)
 
 #ifdef CONFIG_HOTPLUG_CPU
 
-void fixup_irqs(void)
+void octeon_fixup_irqs(void)
 {
 	irq_cpu_offline();
 }
diff --git a/arch/mips/cavium-octeon/setup.c b/arch/mips/cavium-octeon/setup.c
index 48b08eb9d9e4..b212ae12e5ac 100644
--- a/arch/mips/cavium-octeon/setup.c
+++ b/arch/mips/cavium-octeon/setup.c
@@ -8,6 +8,7 @@
  *   written by Ralf Baechle <ralf@linux-mips.org>
  */
 #include <linux/compiler.h>
+#include <linux/vmalloc.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/console.h>
@@ -1139,3 +1140,30 @@ static int __init edac_devinit(void)
 	return err;
 }
 device_initcall(edac_devinit);
+
+static void __initdata *octeon_dummy_iospace;
+
+static int __init octeon_no_pci_init(void)
+{
+	/*
+	 * Initially assume there is no PCI. The PCI/PCIe platform code will
+	 * later re-initialize these to correct values if they are present.
+	 */
+	octeon_dummy_iospace = vzalloc(IO_SPACE_LIMIT);
+	set_io_port_base((unsigned long)octeon_dummy_iospace);
+	ioport_resource.start = MAX_RESOURCE;
+	ioport_resource.end = 0;
+	return 0;
+}
+core_initcall(octeon_no_pci_init);
+
+static int __init octeon_no_pci_release(void)
+{
+	/*
+	 * Release the allocated memory if a real IO space is there.
+	 */
+	if ((unsigned long)octeon_dummy_iospace != mips_io_port_base)
+		vfree(octeon_dummy_iospace);
+	return 0;
+}
+late_initcall(octeon_no_pci_release);
diff --git a/arch/mips/cavium-octeon/smp.c b/arch/mips/cavium-octeon/smp.c
index 138cc80c5928..24a2167db778 100644
--- a/arch/mips/cavium-octeon/smp.c
+++ b/arch/mips/cavium-octeon/smp.c
@@ -255,8 +255,6 @@ static void octeon_cpus_done(void)
 /* State of each CPU. */
 DEFINE_PER_CPU(int, cpu_state);
 
-extern void fixup_irqs(void);
-
 static int octeon_cpu_disable(void)
 {
 	unsigned int cpu = smp_processor_id();
@@ -267,7 +265,7 @@ static int octeon_cpu_disable(void)
 	set_cpu_online(cpu, false);
 	cpu_clear(cpu, cpu_callin_map);
 	local_irq_disable();
-	fixup_irqs();
+	octeon_fixup_irqs();
 	local_irq_enable();
 
 	flush_cache_all();
diff --git a/arch/mips/configs/xway_defconfig b/arch/mips/configs/xway_defconfig
new file mode 100644
index 000000000000..8987846240f7
--- /dev/null
+++ b/arch/mips/configs/xway_defconfig
@@ -0,0 +1,159 @@
+CONFIG_LANTIQ=y
+CONFIG_XRX200_PHY_FW=y
+CONFIG_CPU_MIPS32_R2=y
+# CONFIG_COMPACTION is not set
+# CONFIG_CROSS_MEMORY_ATTACH is not set
+CONFIG_HZ_100=y
+# CONFIG_SECCOMP is not set
+# CONFIG_LOCALVERSION_AUTO is not set
+CONFIG_SYSVIPC=y
+CONFIG_HIGH_RES_TIMERS=y
+CONFIG_BLK_DEV_INITRD=y
+# CONFIG_RD_GZIP is not set
+CONFIG_CC_OPTIMIZE_FOR_SIZE=y
+CONFIG_KALLSYMS_ALL=y
+# CONFIG_AIO is not set
+CONFIG_EMBEDDED=y
+# CONFIG_VM_EVENT_COUNTERS is not set
+# CONFIG_SLUB_DEBUG is not set
+# CONFIG_COMPAT_BRK is not set
+CONFIG_MODULES=y
+CONFIG_MODULE_UNLOAD=y
+# CONFIG_BLK_DEV_BSG is not set
+CONFIG_PARTITION_ADVANCED=y
+# CONFIG_IOSCHED_CFQ is not set
+# CONFIG_COREDUMP is not set
+# CONFIG_SUSPEND is not set
+CONFIG_NET=y
+CONFIG_PACKET=y
+CONFIG_UNIX=y
+CONFIG_INET=y
+CONFIG_IP_MULTICAST=y
+CONFIG_IP_ADVANCED_ROUTER=y
+CONFIG_IP_MULTIPLE_TABLES=y
+CONFIG_IP_ROUTE_MULTIPATH=y
+CONFIG_IP_ROUTE_VERBOSE=y
+CONFIG_IP_MROUTE=y
+CONFIG_IP_MROUTE_MULTIPLE_TABLES=y
+CONFIG_ARPD=y
+CONFIG_SYN_COOKIES=y
+# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
+# CONFIG_INET_XFRM_MODE_TUNNEL is not set
+# CONFIG_INET_XFRM_MODE_BEET is not set
+# CONFIG_INET_LRO is not set
+# CONFIG_INET_DIAG is not set
+CONFIG_TCP_CONG_ADVANCED=y
+# CONFIG_TCP_CONG_BIC is not set
+# CONFIG_TCP_CONG_WESTWOOD is not set
+# CONFIG_TCP_CONG_HTCP is not set
+# CONFIG_IPV6 is not set
+CONFIG_NETFILTER=y
+# CONFIG_BRIDGE_NETFILTER is not set
+CONFIG_NF_CONNTRACK=m
+CONFIG_NF_CONNTRACK_FTP=m
+CONFIG_NF_CONNTRACK_IRC=m
+CONFIG_NETFILTER_XT_TARGET_CT=m
+CONFIG_NETFILTER_XT_TARGET_LOG=m
+CONFIG_NETFILTER_XT_TARGET_TCPMSS=m
+CONFIG_NETFILTER_XT_MATCH_COMMENT=m
+CONFIG_NETFILTER_XT_MATCH_CONNTRACK=m
+CONFIG_NETFILTER_XT_MATCH_LIMIT=m
+CONFIG_NETFILTER_XT_MATCH_MAC=m
+CONFIG_NETFILTER_XT_MATCH_MULTIPORT=m
+CONFIG_NETFILTER_XT_MATCH_STATE=m
+CONFIG_NF_CONNTRACK_IPV4=m
+# CONFIG_NF_CONNTRACK_PROC_COMPAT is not set
+CONFIG_IP_NF_IPTABLES=m
+CONFIG_IP_NF_FILTER=m
+CONFIG_IP_NF_TARGET_REJECT=m
+CONFIG_IP_NF_MANGLE=m
+CONFIG_IP_NF_RAW=m
+CONFIG_BRIDGE=y
+# CONFIG_BRIDGE_IGMP_SNOOPING is not set
+CONFIG_VLAN_8021Q=y
+CONFIG_NET_SCHED=y
+CONFIG_HAMRADIO=y
+CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
+# CONFIG_FIRMWARE_IN_KERNEL is not set
+CONFIG_MTD=y
+CONFIG_MTD_CMDLINE_PARTS=y
+CONFIG_MTD_BLOCK=y
+CONFIG_MTD_CFI=y
+CONFIG_MTD_CFI_AMDSTD=y
+CONFIG_MTD_COMPLEX_MAPPINGS=y
+CONFIG_MTD_PHYSMAP=y
+CONFIG_MTD_PHYSMAP_OF=y
+CONFIG_MTD_LANTIQ=y
+CONFIG_EEPROM_93CX6=m
+CONFIG_SCSI=y
+CONFIG_BLK_DEV_SD=y
+CONFIG_NETDEVICES=y
+CONFIG_LANTIQ_ETOP=y
+# CONFIG_NET_VENDOR_WIZNET is not set
+CONFIG_PHYLIB=y
+CONFIG_PPP=m
+CONFIG_PPP_FILTER=y
+CONFIG_PPP_MULTILINK=y
+CONFIG_PPPOE=m
+CONFIG_PPP_ASYNC=m
+CONFIG_ISDN=y
+CONFIG_INPUT=m
+CONFIG_INPUT_POLLDEV=m
+# CONFIG_INPUT_MOUSEDEV is not set
+# CONFIG_KEYBOARD_ATKBD is not set
+# CONFIG_INPUT_MOUSE is not set
+CONFIG_INPUT_MISC=y
+# CONFIG_SERIO is not set
+# CONFIG_VT is not set
+# CONFIG_LEGACY_PTYS is not set
+# CONFIG_DEVKMEM is not set
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_SERIAL_8250_RUNTIME_UARTS=2
+CONFIG_SERIAL_OF_PLATFORM=y
+CONFIG_SPI=y
+CONFIG_GPIO_MM_LANTIQ=y
+CONFIG_GPIO_STP_XWAY=y
+# CONFIG_HWMON is not set
+CONFIG_WATCHDOG=y
+# CONFIG_HID is not set
+# CONFIG_USB_HID is not set
+CONFIG_USB=y
+CONFIG_USB_ANNOUNCE_NEW_DEVICES=y
+CONFIG_USB_STORAGE=y
+CONFIG_USB_STORAGE_DEBUG=y
+CONFIG_NEW_LEDS=y
+CONFIG_LEDS_CLASS=y
+CONFIG_LEDS_TRIGGERS=y
+CONFIG_LEDS_TRIGGER_TIMER=y
+CONFIG_LEDS_TRIGGER_DEFAULT_ON=y
+CONFIG_STAGING=y
+# CONFIG_IOMMU_SUPPORT is not set
+# CONFIG_DNOTIFY is not set
+# CONFIG_PROC_PAGE_MONITOR is not set
+CONFIG_TMPFS=y
+CONFIG_TMPFS_XATTR=y
+CONFIG_JFFS2_FS=y
+CONFIG_JFFS2_SUMMARY=y
+CONFIG_JFFS2_FS_XATTR=y
+# CONFIG_JFFS2_FS_POSIX_ACL is not set
+# CONFIG_JFFS2_FS_SECURITY is not set
+CONFIG_JFFS2_COMPRESSION_OPTIONS=y
+# CONFIG_JFFS2_ZLIB is not set
+CONFIG_SQUASHFS=y
+# CONFIG_SQUASHFS_ZLIB is not set
+CONFIG_SQUASHFS_XZ=y
+CONFIG_PRINTK_TIME=y
+# CONFIG_ENABLE_MUST_CHECK is not set
+CONFIG_STRIP_ASM_SYMS=y
+CONFIG_DEBUG_FS=y
+CONFIG_MAGIC_SYSRQ=y
+# CONFIG_SCHED_DEBUG is not set
+# CONFIG_FTRACE is not set
+CONFIG_CMDLINE_BOOL=y
+CONFIG_CRYPTO_MANAGER=m
+CONFIG_CRYPTO_ARC4=m
+# CONFIG_CRYPTO_ANSI_CPRNG is not set
+CONFIG_CRC_ITU_T=m
+CONFIG_CRC32_SARWATE=y
+CONFIG_AVERAGE=y
diff --git a/arch/mips/dec/ioasic-irq.c b/arch/mips/dec/ioasic-irq.c
index 824e08c73798..4b3e3a4375a6 100644
--- a/arch/mips/dec/ioasic-irq.c
+++ b/arch/mips/dec/ioasic-irq.c
@@ -51,6 +51,14 @@ static struct irq_chip ioasic_irq_type = {
 	.irq_unmask = unmask_ioasic_irq,
 };
 
+void clear_ioasic_dma_irq(unsigned int irq)
+{
+	u32 sir;
+
+	sir = ~(1 << (irq - ioasic_irq_base));
+	ioasic_write(IO_REG_SIR, sir);
+}
+
 static struct irq_chip ioasic_dma_irq_type = {
 	.name = "IO-ASIC-DMA",
 	.irq_ack = ack_ioasic_irq,
diff --git a/arch/mips/dec/prom/init.c b/arch/mips/dec/prom/init.c
index ab169046e442..468f665de7bb 100644
--- a/arch/mips/dec/prom/init.c
+++ b/arch/mips/dec/prom/init.c
@@ -13,6 +13,7 @@
 
 #include <asm/bootinfo.h>
 #include <asm/cpu.h>
+#include <asm/cpu-type.h>
 #include <asm/processor.h>
 
 #include <asm/dec/prom.h>
diff --git a/arch/mips/dec/time.c b/arch/mips/dec/time.c
index ea57f39e6736..1914e56f0d96 100644
--- a/arch/mips/dec/time.c
+++ b/arch/mips/dec/time.c
@@ -125,13 +125,18 @@ int rtc_mips_set_mmss(unsigned long nowtime)
 
 void __init plat_time_init(void)
 {
+	int ioasic_clock = 0;
 	u32 start, end;
-	int i = HZ / 10;
+	int i = HZ / 8;
 
 	/* Set up the rate of periodic DS1287 interrupts. */
 	ds1287_set_base_clock(HZ);
 
+	/* On some I/O ASIC systems we have the I/O ASIC's counter.  */
+	if (IOASIC)
+		ioasic_clock = dec_ioasic_clocksource_init() == 0;
 	if (cpu_has_counter) {
+		ds1287_timer_state();
 		while (!ds1287_timer_state())
 			;
 
@@ -143,12 +148,24 @@ void __init plat_time_init(void)
 
 		end = read_c0_count();
 
-		mips_hpt_frequency = (end - start) * 10;
+		mips_hpt_frequency = (end - start) * 8;
 		printk(KERN_INFO "MIPS counter frequency %dHz\n",
 			mips_hpt_frequency);
-	} else if (IOASIC)
-		/* For pre-R4k systems we use the I/O ASIC's counter.  */
-		dec_ioasic_clocksource_init();
+
+		/*
+		 * All R4k DECstations suffer from the CP0 Count erratum,
+		 * so we can't use the timer as a clock source, and a clock
+		 * event both at a time.  An accurate wall clock is more
+		 * important than a high-precision interval timer so only
+		 * use the timer as a clock source, and not a clock event
+		 * if there's no I/O ASIC counter available to serve as a
+		 * clock source.
+		 */
+		if (!ioasic_clock) {
+			init_r4k_clocksource();
+			mips_hpt_frequency = 0;
+		}
+	}
 
 	ds1287_clockevent_init(dec_interrupt[DEC_IRQ_RTC]);
 }
diff --git a/arch/mips/include/asm/Kbuild b/arch/mips/include/asm/Kbuild
index 9b54b7a403d4..454ddf9bb76f 100644
--- a/arch/mips/include/asm/Kbuild
+++ b/arch/mips/include/asm/Kbuild
@@ -1,2 +1,15 @@
 # MIPS headers
+generic-y += cputime.h
+generic-y += current.h
+generic-y += emergency-restart.h
+generic-y += local64.h
+generic-y += mutex.h
+generic-y += parport.h
+generic-y += percpu.h
+generic-y += scatterlist.h
+generic-y += sections.h
+generic-y += segment.h
+generic-y += serial.h
 generic-y += trace_clock.h
+generic-y += ucontext.h
+generic-y += xor.h
diff --git a/arch/mips/include/asm/bmips.h b/arch/mips/include/asm/bmips.h
index 552a65a0cf2b..27bd060d716e 100644
--- a/arch/mips/include/asm/bmips.h
+++ b/arch/mips/include/asm/bmips.h
@@ -65,44 +65,33 @@ static inline unsigned long bmips_read_zscm_reg(unsigned int offset)
 {
 	unsigned long ret;
 
-	__asm__ __volatile__(
-		".set push\n"
-		".set noreorder\n"
-		"cache %1, 0(%2)\n"
-		"sync\n"
-		"_ssnop\n"
-		"_ssnop\n"
-		"_ssnop\n"
-		"_ssnop\n"
-		"_ssnop\n"
-		"_ssnop\n"
-		"_ssnop\n"
-		"mfc0 %0, $28, 3\n"
-		"_ssnop\n"
-		".set pop\n"
-		: "=&r" (ret)
-		: "i" (Index_Load_Tag_S), "r" (ZSCM_REG_BASE + offset)
-		: "memory");
+	barrier();
+	cache_op(Index_Load_Tag_S, ZSCM_REG_BASE + offset);
+	__sync();
+	_ssnop();
+	_ssnop();
+	_ssnop();
+	_ssnop();
+	_ssnop();
+	_ssnop();
+	_ssnop();
+	ret = read_c0_ddatalo();
+	_ssnop();
+
 	return ret;
 }
 
 static inline void bmips_write_zscm_reg(unsigned int offset, unsigned long data)
 {
-	__asm__ __volatile__(
-		".set push\n"
-		".set noreorder\n"
-		"mtc0 %0, $28, 3\n"
-		"_ssnop\n"
-		"_ssnop\n"
-		"_ssnop\n"
-		"cache %1, 0(%2)\n"
-		"_ssnop\n"
-		"_ssnop\n"
-		"_ssnop\n"
-		: /* no outputs */
-		: "r" (data),
-		  "i" (Index_Store_Tag_S), "r" (ZSCM_REG_BASE + offset)
-		: "memory");
+	write_c0_ddatalo(data);
+	_ssnop();
+	_ssnop();
+	_ssnop();
+	cache_op(Index_Store_Tag_S, ZSCM_REG_BASE + offset);
+	_ssnop();
+	_ssnop();
+	_ssnop();
+	barrier();
 }
 
 #endif /* !defined(__ASSEMBLY__) */
diff --git a/arch/mips/include/asm/cpu-features.h b/arch/mips/include/asm/cpu-features.h
index fa44f3ec5302..d445d060e346 100644
--- a/arch/mips/include/asm/cpu-features.h
+++ b/arch/mips/include/asm/cpu-features.h
@@ -13,12 +13,6 @@
 #include <asm/cpu-info.h>
 #include <cpu-feature-overrides.h>
 
-#ifndef current_cpu_type
-#define current_cpu_type()	current_cpu_data.cputype
-#endif
-
-#define boot_cpu_type()		cpu_data[0].cputype
-
 /*
  * SMP assumption: Options of CPU 0 are a superset of all processors.
  * This is true for all known MIPS systems.
@@ -193,7 +187,7 @@
 
 /*
  * MIPS32, MIPS64, VR5500, IDT32332, IDT32334 and maybe a few other
- * pre-MIPS32/MIPS53 processors have CLO, CLZ.	The IDT RC64574 is 64-bit and
+ * pre-MIPS32/MIPS64 processors have CLO, CLZ.	The IDT RC64574 is 64-bit and
  * has CLO and CLZ but not DCLO nor DCLZ.  For 64-bit kernels
  * cpu_has_clo_clz also indicates the availability of DCLO and DCLZ.
  */
diff --git a/arch/mips/include/asm/cpu-info.h b/arch/mips/include/asm/cpu-info.h
index 41401d8eb7d1..21c8e29c8f91 100644
--- a/arch/mips/include/asm/cpu-info.h
+++ b/arch/mips/include/asm/cpu-info.h
@@ -84,6 +84,7 @@ struct cpuinfo_mips {
 extern struct cpuinfo_mips cpu_data[];
 #define current_cpu_data cpu_data[smp_processor_id()]
 #define raw_current_cpu_data cpu_data[raw_smp_processor_id()]
+#define boot_cpu_data cpu_data[0]
 
 extern void cpu_probe(void);
 extern void cpu_report(void);
diff --git a/arch/mips/include/asm/cpu-type.h b/arch/mips/include/asm/cpu-type.h
new file mode 100644
index 000000000000..4a402cc60c03
--- /dev/null
+++ b/arch/mips/include/asm/cpu-type.h
@@ -0,0 +1,203 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 2003, 2004 Ralf Baechle
+ * Copyright (C) 2004  Maciej W. Rozycki
+ */
+#ifndef __ASM_CPU_TYPE_H
+#define __ASM_CPU_TYPE_H
+
+#include <linux/smp.h>
+#include <linux/compiler.h>
+
+static inline int __pure __get_cpu_type(const int cpu_type)
+{
+	switch (cpu_type) {
+#if defined(CONFIG_SYS_HAS_CPU_LOONGSON2E) || \
+    defined(CONFIG_SYS_HAS_CPU_LOONGSON2F)
+	case CPU_LOONGSON2:
+#endif
+
+#ifdef CONFIG_SYS_HAS_CPU_LOONGSON1B
+	case CPU_LOONGSON1:
+#endif
+
+#ifdef CONFIG_SYS_HAS_CPU_MIPS32_R1
+	case CPU_4KC:
+	case CPU_ALCHEMY:
+	case CPU_BMIPS3300:
+	case CPU_BMIPS4350:
+	case CPU_PR4450:
+	case CPU_BMIPS32:
+	case CPU_JZRISC:
+#endif
+
+#if defined(CONFIG_SYS_HAS_CPU_MIPS32_R1) || \
+    defined(CONFIG_SYS_HAS_CPU_MIPS32_R2)
+	case CPU_4KEC:
+#endif
+
+#ifdef CONFIG_SYS_HAS_CPU_MIPS32_R2
+	case CPU_4KSC:
+	case CPU_24K:
+	case CPU_34K:
+	case CPU_1004K:
+	case CPU_74K:
+	case CPU_M14KC:
+	case CPU_M14KEC:
+#endif
+
+#ifdef CONFIG_SYS_HAS_CPU_MIPS64_R1
+	case CPU_5KC:
+	case CPU_5KE:
+	case CPU_20KC:
+	case CPU_25KF:
+	case CPU_SB1:
+	case CPU_SB1A:
+#endif
+
+#ifdef CONFIG_SYS_HAS_CPU_MIPS64_R2
+	/*
+	 * All MIPS64 R2 processors have their own special symbols.  That is,
+	 * there currently is no pure R2 core
+	 */
+#endif
+
+#ifdef CONFIG_SYS_HAS_CPU_R3000
+	case CPU_R2000:
+	case CPU_R3000:
+	case CPU_R3000A:
+	case CPU_R3041:
+	case CPU_R3051:
+	case CPU_R3052:
+	case CPU_R3081:
+	case CPU_R3081E:
+#endif
+
+#ifdef CONFIG_SYS_HAS_CPU_TX39XX
+	case CPU_TX3912:
+	case CPU_TX3922:
+	case CPU_TX3927:
+#endif
+
+#ifdef CONFIG_SYS_HAS_CPU_VR41XX
+	case CPU_VR41XX:
+	case CPU_VR4111:
+	case CPU_VR4121:
+	case CPU_VR4122:
+	case CPU_VR4131:
+	case CPU_VR4133:
+	case CPU_VR4181:
+	case CPU_VR4181A:
+#endif
+
+#ifdef CONFIG_SYS_HAS_CPU_R4300
+	case CPU_R4300:
+	case CPU_R4310:
+#endif
+
+#ifdef CONFIG_SYS_HAS_CPU_R4X00
+	case CPU_R4000PC:
+	case CPU_R4000SC:
+	case CPU_R4000MC:
+	case CPU_R4200:
+	case CPU_R4400PC:
+	case CPU_R4400SC:
+	case CPU_R4400MC:
+	case CPU_R4600:
+	case CPU_R4700:
+	case CPU_R4640:
+	case CPU_R4650:
+#endif
+
+#ifdef CONFIG_SYS_HAS_CPU_TX49XX
+	case CPU_TX49XX:
+#endif
+
+#ifdef CONFIG_SYS_HAS_CPU_R5000
+	case CPU_R5000:
+#endif
+
+#ifdef CONFIG_SYS_HAS_CPU_R5432
+	case CPU_R5432:
+#endif
+
+#ifdef CONFIG_SYS_HAS_CPU_R5500
+	case CPU_R5500:
+#endif
+
+#ifdef CONFIG_SYS_HAS_CPU_R6000
+	case CPU_R6000:
+	case CPU_R6000A:
+#endif
+
+#ifdef CONFIG_SYS_HAS_CPU_NEVADA
+	case CPU_NEVADA:
+#endif
+
+#ifdef CONFIG_SYS_HAS_CPU_R8000
+	case CPU_R8000:
+#endif
+
+#ifdef CONFIG_SYS_HAS_CPU_R10000
+	case CPU_R10000:
+	case CPU_R12000:
+	case CPU_R14000:
+#endif
+#ifdef CONFIG_SYS_HAS_CPU_RM7000
+	case CPU_RM7000:
+	case CPU_SR71000:
+#endif
+#ifdef CONFIG_SYS_HAS_CPU_RM9000
+	case CPU_RM9000:
+#endif
+#ifdef CONFIG_SYS_HAS_CPU_SB1
+	case CPU_SB1:
+	case CPU_SB1A:
+#endif
+#ifdef CONFIG_SYS_HAS_CPU_CAVIUM_OCTEON
+	case CPU_CAVIUM_OCTEON:
+	case CPU_CAVIUM_OCTEON_PLUS:
+	case CPU_CAVIUM_OCTEON2:
+#endif
+
+#ifdef CONFIG_SYS_HAS_CPU_BMIPS4380
+	case CPU_BMIPS4380:
+#endif
+
+#ifdef CONFIG_SYS_HAS_CPU_BMIPS5000
+	case CPU_BMIPS5000:
+#endif
+
+#ifdef CONFIG_SYS_HAS_CPU_XLP
+	case CPU_XLP:
+#endif
+
+#ifdef CONFIG_SYS_HAS_CPU_XLR
+	case CPU_XLR:
+#endif
+		break;
+	default:
+		unreachable();
+	}
+
+	return cpu_type;
+}
+
+static inline int __pure current_cpu_type(void)
+{
+	const int cpu_type = current_cpu_data.cputype;
+
+	return __get_cpu_type(cpu_type);
+}
+
+static inline int __pure boot_cpu_type(void)
+{
+	const int cpu_type = cpu_data[0].cputype;
+
+	return __get_cpu_type(cpu_type);
+}
+
+#endif /* __ASM_CPU_TYPE_H */
diff --git a/arch/mips/include/asm/cpu.h b/arch/mips/include/asm/cpu.h
index 632bbe5a79ea..d2035e16502a 100644
--- a/arch/mips/include/asm/cpu.h
+++ b/arch/mips/include/asm/cpu.h
@@ -3,15 +3,14 @@
  *	  various MIPS cpu types.
  *
  * Copyright (C) 1996 David S. Miller (davem@davemloft.net)
- * Copyright (C) 2004  Maciej W. Rozycki
+ * Copyright (C) 2004, 2013  Maciej W. Rozycki
  */
 #ifndef _ASM_CPU_H
 #define _ASM_CPU_H
 
-/* Assigned Company values for bits 23:16 of the PRId Register
-   (CP0 register 15, select 0).	 As of the MIPS32 and MIPS64 specs from
-   MTI, the PRId register is defined in this (backwards compatible)
-   way:
+/*
+   As of the MIPS32 and MIPS64 specs from MTI, the PRId register (CP0
+   register 15, select 0) is defined in this (backwards compatible) way:
 
   +----------------+----------------+----------------+----------------+
   | Company Options| Company ID	    | Processor ID   | Revision	      |
@@ -23,6 +22,14 @@
    spec.
 */
 
+#define PRID_OPT_MASK		0xff000000
+
+/*
+ * Assigned Company values for bits 23:16 of the PRId register.
+ */
+
+#define PRID_COMP_MASK		0xff0000
+
 #define PRID_COMP_LEGACY	0x000000
 #define PRID_COMP_MIPS		0x010000
 #define PRID_COMP_BROADCOM	0x020000
@@ -38,10 +45,17 @@
 #define PRID_COMP_INGENIC	0xd00000
 
 /*
- * Assigned values for the product ID register.	 In order to detect a
- * certain CPU type exactly eventually additional registers may need to
- * be examined.	 These are valid when 23:16 == PRID_COMP_LEGACY
+ * Assigned Processor ID (implementation) values for bits 15:8 of the PRId
+ * register.  In order to detect a certain CPU type exactly eventually
+ * additional registers may need to be examined.
  */
+
+#define PRID_IMP_MASK		0xff00
+
+/*
+ * These are valid when 23:16 == PRID_COMP_LEGACY
+ */
+
 #define PRID_IMP_R2000		0x0100
 #define PRID_IMP_AU1_REV1	0x0100
 #define PRID_IMP_AU1_REV2	0x0200
@@ -141,6 +155,9 @@
 #define PRID_IMP_CAVIUM_CN68XX 0x9100
 #define PRID_IMP_CAVIUM_CN66XX 0x9200
 #define PRID_IMP_CAVIUM_CN61XX 0x9300
+#define PRID_IMP_CAVIUM_CNF71XX 0x9400
+#define PRID_IMP_CAVIUM_CN78XX 0x9500
+#define PRID_IMP_CAVIUM_CN70XX 0x9600
 
 /*
  * These are the PRID's for when 23:16 == PRID_COMP_INGENIC
@@ -176,13 +193,18 @@
 
 #define PRID_IMP_NETLOGIC_XLP8XX	0x1000
 #define PRID_IMP_NETLOGIC_XLP3XX	0x1100
+#define PRID_IMP_NETLOGIC_XLP2XX	0x1200
 
 /*
- * Definitions for 7:0 on legacy processors
+ * Particular Revision values for bits 7:0 of the PRId register.
  */
 
 #define PRID_REV_MASK		0x00ff
 
+/*
+ * Definitions for 7:0 on legacy processors
+ */
+
 #define PRID_REV_TX4927		0x0022
 #define PRID_REV_TX4937		0x0030
 #define PRID_REV_R4400		0x0040
@@ -223,6 +245,8 @@
  *  31				   16 15	     8 7	      0
  */
 
+#define FPIR_IMP_MASK		0xff00
+
 #define FPIR_IMP_NONE		0x0000
 
 enum cpu_type_enum {
@@ -272,7 +296,7 @@ enum cpu_type_enum {
 	 */
 	CPU_5KC, CPU_5KE, CPU_20KC, CPU_25KF, CPU_SB1, CPU_SB1A, CPU_LOONGSON2,
 	CPU_CAVIUM_OCTEON, CPU_CAVIUM_OCTEON_PLUS, CPU_CAVIUM_OCTEON2,
-	CPU_XLR, CPU_XLP,
+	CPU_CAVIUM_OCTEON3, CPU_XLR, CPU_XLP,
 
 	CPU_LAST
 };
diff --git a/arch/mips/include/asm/cputime.h b/arch/mips/include/asm/cputime.h
deleted file mode 100644
index c00eacbdd979..000000000000
--- a/arch/mips/include/asm/cputime.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __MIPS_CPUTIME_H
-#define __MIPS_CPUTIME_H
-
-#include <asm-generic/cputime.h>
-
-#endif /* __MIPS_CPUTIME_H */
diff --git a/arch/mips/include/asm/current.h b/arch/mips/include/asm/current.h
deleted file mode 100644
index 4c51401b5537..000000000000
--- a/arch/mips/include/asm/current.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/current.h>
diff --git a/arch/mips/include/asm/dec/ioasic.h b/arch/mips/include/asm/dec/ioasic.h
index 98badd6bf22d..a6e505a0e44b 100644
--- a/arch/mips/include/asm/dec/ioasic.h
+++ b/arch/mips/include/asm/dec/ioasic.h
@@ -31,8 +31,10 @@ static inline u32 ioasic_read(unsigned int reg)
 	return ioasic_base[reg / 4];
 }
 
+extern void clear_ioasic_dma_irq(unsigned int irq);
+
 extern void init_ioasic_irqs(int base);
 
-extern void dec_ioasic_clocksource_init(void);
+extern int dec_ioasic_clocksource_init(void);
 
 #endif /* __ASM_DEC_IOASIC_H */
diff --git a/arch/mips/include/asm/emergency-restart.h b/arch/mips/include/asm/emergency-restart.h
deleted file mode 100644
index 108d8c48e42e..000000000000
--- a/arch/mips/include/asm/emergency-restart.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef _ASM_EMERGENCY_RESTART_H
-#define _ASM_EMERGENCY_RESTART_H
-
-#include <asm-generic/emergency-restart.h>
-
-#endif /* _ASM_EMERGENCY_RESTART_H */
diff --git a/arch/mips/include/asm/jump_label.h b/arch/mips/include/asm/jump_label.h
index 4d6d77ed9b9d..e194f957ca8c 100644
--- a/arch/mips/include/asm/jump_label.h
+++ b/arch/mips/include/asm/jump_label.h
@@ -22,7 +22,7 @@
 
 static __always_inline bool arch_static_branch(struct static_key *key)
 {
-	asm goto("1:\tnop\n\t"
+	asm_volatile_goto("1:\tnop\n\t"
 		"nop\n\t"
 		".pushsection __jump_table,  \"aw\"\n\t"
 		WORD_INSN " 1b, %l[l_yes], %0\n\t"
diff --git a/arch/mips/include/asm/local64.h b/arch/mips/include/asm/local64.h
deleted file mode 100644
index 36c93b5cc239..000000000000
--- a/arch/mips/include/asm/local64.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/local64.h>
diff --git a/arch/mips/include/asm/mach-ath79/cpu-feature-overrides.h b/arch/mips/include/asm/mach-ath79/cpu-feature-overrides.h
index ddb947e9221f..0089a740e5ae 100644
--- a/arch/mips/include/asm/mach-ath79/cpu-feature-overrides.h
+++ b/arch/mips/include/asm/mach-ath79/cpu-feature-overrides.h
@@ -42,8 +42,6 @@
 #define cpu_has_mips64r1	0
 #define cpu_has_mips64r2	0
 
-#define cpu_has_dsp		0
-#define cpu_has_dsp2		0
 #define cpu_has_mipsmt		0
 
 #define cpu_has_64bits		0
diff --git a/arch/mips/include/asm/mach-au1x00/au1000.h b/arch/mips/include/asm/mach-au1x00/au1000.h
index 3e11a468cdf8..54f9e84db8ac 100644
--- a/arch/mips/include/asm/mach-au1x00/au1000.h
+++ b/arch/mips/include/asm/mach-au1x00/au1000.h
@@ -43,6 +43,8 @@
 #include <linux/io.h>
 #include <linux/irq.h>
 
+#include <asm/cpu.h>
+
 /* cpu pipeline flush */
 void static inline au_sync(void)
 {
@@ -140,7 +142,7 @@ static inline int au1xxx_cpu_needs_config_od(void)
 
 static inline int alchemy_get_cputype(void)
 {
-	switch (read_c0_prid() & 0xffff0000) {
+	switch (read_c0_prid() & (PRID_OPT_MASK | PRID_COMP_MASK)) {
 	case 0x00030000:
 		return ALCHEMY_CPU_AU1000;
 		break;
diff --git a/arch/mips/include/asm/mach-bcm63xx/bcm63xx_nvram.h b/arch/mips/include/asm/mach-bcm63xx/bcm63xx_nvram.h
index 4e0b6bc1165e..348df49dcc9f 100644
--- a/arch/mips/include/asm/mach-bcm63xx/bcm63xx_nvram.h
+++ b/arch/mips/include/asm/mach-bcm63xx/bcm63xx_nvram.h
@@ -30,4 +30,6 @@ u8 *bcm63xx_nvram_get_name(void);
  */
 int bcm63xx_nvram_get_mac_address(u8 *mac);
 
+int bcm63xx_nvram_get_psi_size(void);
+
 #endif /* BCM63XX_NVRAM_H */
diff --git a/arch/mips/include/asm/mach-cavium-octeon/gpio.h b/arch/mips/include/asm/mach-cavium-octeon/gpio.h
new file mode 100644
index 000000000000..34e9f7aabab4
--- /dev/null
+++ b/arch/mips/include/asm/mach-cavium-octeon/gpio.h
@@ -0,0 +1,21 @@
+#ifndef __ASM_MACH_CAVIUM_OCTEON_GPIO_H
+#define __ASM_MACH_CAVIUM_OCTEON_GPIO_H
+
+#ifdef CONFIG_GPIOLIB
+#define gpio_get_value	__gpio_get_value
+#define gpio_set_value	__gpio_set_value
+#define gpio_cansleep	__gpio_cansleep
+#else
+int gpio_request(unsigned gpio, const char *label);
+void gpio_free(unsigned gpio);
+int gpio_direction_input(unsigned gpio);
+int gpio_direction_output(unsigned gpio, int value);
+int gpio_get_value(unsigned gpio);
+void gpio_set_value(unsigned gpio, int value);
+#endif
+
+#include <asm-generic/gpio.h>
+
+#define gpio_to_irq	__gpio_to_irq
+
+#endif /* __ASM_MACH_GENERIC_GPIO_H */
diff --git a/arch/mips/include/asm/mach-ip22/cpu-feature-overrides.h b/arch/mips/include/asm/mach-ip22/cpu-feature-overrides.h
index f4caacd25552..1bcb6421205e 100644
--- a/arch/mips/include/asm/mach-ip22/cpu-feature-overrides.h
+++ b/arch/mips/include/asm/mach-ip22/cpu-feature-overrides.h
@@ -8,6 +8,8 @@
 #ifndef __ASM_MACH_IP22_CPU_FEATURE_OVERRIDES_H
 #define __ASM_MACH_IP22_CPU_FEATURE_OVERRIDES_H
 
+#include <asm/cpu.h>
+
 /*
  * IP22 with a variety of processors so we can't use defaults for everything.
  */
diff --git a/arch/mips/include/asm/mach-ip27/cpu-feature-overrides.h b/arch/mips/include/asm/mach-ip27/cpu-feature-overrides.h
index 1d2b6ff60d33..d6111aa2e886 100644
--- a/arch/mips/include/asm/mach-ip27/cpu-feature-overrides.h
+++ b/arch/mips/include/asm/mach-ip27/cpu-feature-overrides.h
@@ -8,6 +8,8 @@
 #ifndef __ASM_MACH_IP27_CPU_FEATURE_OVERRIDES_H
 #define __ASM_MACH_IP27_CPU_FEATURE_OVERRIDES_H
 
+#include <asm/cpu.h>
+
 /*
  * IP27 only comes with R10000 family processors all using the same config
  */
diff --git a/arch/mips/include/asm/mach-ip28/cpu-feature-overrides.h b/arch/mips/include/asm/mach-ip28/cpu-feature-overrides.h
index 65e9c856390d..4cec06d133db 100644
--- a/arch/mips/include/asm/mach-ip28/cpu-feature-overrides.h
+++ b/arch/mips/include/asm/mach-ip28/cpu-feature-overrides.h
@@ -9,6 +9,8 @@
 #ifndef __ASM_MACH_IP28_CPU_FEATURE_OVERRIDES_H
 #define __ASM_MACH_IP28_CPU_FEATURE_OVERRIDES_H
 
+#include <asm/cpu.h>
+
 /*
  * IP28 only comes with R10000 family processors all using the same config
  */
diff --git a/arch/mips/include/asm/mach-lantiq/falcon/cpu-feature-overrides.h b/arch/mips/include/asm/mach-lantiq/falcon/cpu-feature-overrides.h
new file mode 100644
index 000000000000..096a10072430
--- /dev/null
+++ b/arch/mips/include/asm/mach-lantiq/falcon/cpu-feature-overrides.h
@@ -0,0 +1,58 @@
+/*
+ *  Lantiq FALCON specific CPU feature overrides
+ *
+ *  Copyright (C) 2013 Thomas Langer, Lantiq Deutschland
+ *
+ *  This file was derived from: include/asm-mips/cpu-features.h
+ *	Copyright (C) 2003, 2004 Ralf Baechle
+ *	Copyright (C) 2004 Maciej W. Rozycki
+ *
+ *  This program is free software; you can redistribute it and/or modify it
+ *  under the terms of the GNU General Public License version 2 as published
+ *  by the Free Software Foundation.
+ *
+ */
+#ifndef __ASM_MACH_FALCON_CPU_FEATURE_OVERRIDES_H
+#define __ASM_MACH_FALCON_CPU_FEATURE_OVERRIDES_H
+
+#define cpu_has_tlb		1
+#define cpu_has_4kex		1
+#define cpu_has_3k_cache	0
+#define cpu_has_4k_cache	1
+#define cpu_has_tx39_cache	0
+#define cpu_has_sb1_cache	0
+#define cpu_has_fpu		0
+#define cpu_has_32fpr		0
+#define cpu_has_counter		1
+#define cpu_has_watch		1
+#define cpu_has_divec		1
+
+#define cpu_has_prefetch	1
+#define cpu_has_ejtag		1
+#define cpu_has_llsc		1
+
+#define cpu_has_mips16		1
+#define cpu_has_mdmx		0
+#define cpu_has_mips3d		0
+#define cpu_has_smartmips	0
+
+#define cpu_has_mips32r1	1
+#define cpu_has_mips32r2	1
+#define cpu_has_mips64r1	0
+#define cpu_has_mips64r2	0
+
+#define cpu_has_dsp		1
+#define cpu_has_mipsmt		1
+
+#define cpu_has_vint		1
+#define cpu_has_veic		1
+
+#define cpu_has_64bits		0
+#define cpu_has_64bit_zero_reg	0
+#define cpu_has_64bit_gp_regs	0
+#define cpu_has_64bit_addresses	0
+
+#define cpu_dcache_line_size()	32
+#define cpu_icache_line_size()	32
+
+#endif /* __ASM_MACH_FALCON_CPU_FEATURE_OVERRIDES_H */
diff --git a/arch/mips/include/asm/mach-ralink/mt7620.h b/arch/mips/include/asm/mach-ralink/mt7620.h
index 9809972ea882..6f9b24f51157 100644
--- a/arch/mips/include/asm/mach-ralink/mt7620.h
+++ b/arch/mips/include/asm/mach-ralink/mt7620.h
@@ -20,6 +20,8 @@
 #define SYSC_REG_CHIP_REV		0x0c
 #define SYSC_REG_SYSTEM_CONFIG0		0x10
 #define SYSC_REG_SYSTEM_CONFIG1		0x14
+#define SYSC_REG_CLKCFG0		0x2c
+#define SYSC_REG_CPU_SYS_CLKCFG		0x3c
 #define SYSC_REG_CPLL_CONFIG0		0x54
 #define SYSC_REG_CPLL_CONFIG1		0x58
 
@@ -29,20 +31,42 @@
 #define MT7620A_CHIP_NAME0		0x3637544d
 #define MT7620A_CHIP_NAME1		0x20203032
 
+#define SYSCFG0_XTAL_FREQ_SEL		BIT(6)
+
 #define CHIP_REV_PKG_MASK		0x1
 #define CHIP_REV_PKG_SHIFT		16
 #define CHIP_REV_VER_MASK		0xf
 #define CHIP_REV_VER_SHIFT		8
 #define CHIP_REV_ECO_MASK		0xf
 
-#define CPLL_SW_CONFIG_SHIFT		31
-#define CPLL_SW_CONFIG_MASK		0x1
-#define CPLL_CPU_CLK_SHIFT		24
-#define CPLL_CPU_CLK_MASK		0x1
-#define CPLL_MULT_RATIO_SHIFT           16
-#define CPLL_MULT_RATIO                 0x7
-#define CPLL_DIV_RATIO_SHIFT            10
-#define CPLL_DIV_RATIO                  0x3
+#define CLKCFG0_PERI_CLK_SEL		BIT(4)
+
+#define CPU_SYS_CLKCFG_OCP_RATIO_SHIFT	16
+#define CPU_SYS_CLKCFG_OCP_RATIO_MASK	0xf
+#define CPU_SYS_CLKCFG_OCP_RATIO_1	0	/* 1:1   (Reserved) */
+#define CPU_SYS_CLKCFG_OCP_RATIO_1_5	1	/* 1:1.5 (Reserved) */
+#define CPU_SYS_CLKCFG_OCP_RATIO_2	2	/* 1:2   */
+#define CPU_SYS_CLKCFG_OCP_RATIO_2_5	3       /* 1:2.5 (Reserved) */
+#define CPU_SYS_CLKCFG_OCP_RATIO_3	4	/* 1:3   */
+#define CPU_SYS_CLKCFG_OCP_RATIO_3_5	5	/* 1:3.5 (Reserved) */
+#define CPU_SYS_CLKCFG_OCP_RATIO_4	6	/* 1:4   */
+#define CPU_SYS_CLKCFG_OCP_RATIO_5	7	/* 1:5   */
+#define CPU_SYS_CLKCFG_OCP_RATIO_10	8	/* 1:10  */
+#define CPU_SYS_CLKCFG_CPU_FDIV_SHIFT	8
+#define CPU_SYS_CLKCFG_CPU_FDIV_MASK	0x1f
+#define CPU_SYS_CLKCFG_CPU_FFRAC_SHIFT	0
+#define CPU_SYS_CLKCFG_CPU_FFRAC_MASK	0x1f
+
+#define CPLL_CFG0_SW_CFG		BIT(31)
+#define CPLL_CFG0_PLL_MULT_RATIO_SHIFT	16
+#define CPLL_CFG0_PLL_MULT_RATIO_MASK   0x7
+#define CPLL_CFG0_LC_CURFCK		BIT(15)
+#define CPLL_CFG0_BYPASS_REF_CLK	BIT(14)
+#define CPLL_CFG0_PLL_DIV_RATIO_SHIFT	10
+#define CPLL_CFG0_PLL_DIV_RATIO_MASK	0x3
+
+#define CPLL_CFG1_CPU_AUX1		BIT(25)
+#define CPLL_CFG1_CPU_AUX0		BIT(24)
 
 #define SYSCFG0_DRAM_TYPE_MASK		0x3
 #define SYSCFG0_DRAM_TYPE_SHIFT		4
diff --git a/arch/mips/include/asm/mach-ralink/mt7620/cpu-feature-overrides.h b/arch/mips/include/asm/mach-ralink/mt7620/cpu-feature-overrides.h
new file mode 100644
index 000000000000..f7bb8cfc5eb1
--- /dev/null
+++ b/arch/mips/include/asm/mach-ralink/mt7620/cpu-feature-overrides.h
@@ -0,0 +1,57 @@
+/*
+ * Ralink MT7620 specific CPU feature overrides
+ *
+ * Copyright (C) 2008-2009 Gabor Juhos <juhosg@openwrt.org>
+ * Copyright (C) 2008 Imre Kaloz <kaloz@openwrt.org>
+ *
+ * This file was derived from: include/asm-mips/cpu-features.h
+ *	Copyright (C) 2003, 2004 Ralf Baechle
+ *	Copyright (C) 2004 Maciej W. Rozycki
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ *
+ */
+#ifndef _MT7620_CPU_FEATURE_OVERRIDES_H
+#define _MT7620_CPU_FEATURE_OVERRIDES_H
+
+#define cpu_has_tlb		1
+#define cpu_has_4kex		1
+#define cpu_has_3k_cache	0
+#define cpu_has_4k_cache	1
+#define cpu_has_tx39_cache	0
+#define cpu_has_sb1_cache	0
+#define cpu_has_fpu		0
+#define cpu_has_32fpr		0
+#define cpu_has_counter		1
+#define cpu_has_watch		1
+#define cpu_has_divec		1
+
+#define cpu_has_prefetch	1
+#define cpu_has_ejtag		1
+#define cpu_has_llsc		1
+
+#define cpu_has_mips16		1
+#define cpu_has_mdmx		0
+#define cpu_has_mips3d		0
+#define cpu_has_smartmips	0
+
+#define cpu_has_mips32r1	1
+#define cpu_has_mips32r2	1
+#define cpu_has_mips64r1	0
+#define cpu_has_mips64r2	0
+
+#define cpu_has_dsp		1
+#define cpu_has_dsp2		0
+#define cpu_has_mipsmt		0
+
+#define cpu_has_64bits		0
+#define cpu_has_64bit_zero_reg	0
+#define cpu_has_64bit_gp_regs	0
+#define cpu_has_64bit_addresses	0
+
+#define cpu_dcache_line_size()	32
+#define cpu_icache_line_size()	32
+
+#endif /* _MT7620_CPU_FEATURE_OVERRIDES_H */
diff --git a/arch/mips/include/asm/mipsregs.h b/arch/mips/include/asm/mipsregs.h
index fed1c3e9b486..e0331414c7d6 100644
--- a/arch/mips/include/asm/mipsregs.h
+++ b/arch/mips/include/asm/mipsregs.h
@@ -603,6 +603,13 @@
 #define MIPS_CONF4_MMUEXTDEF	(_ULCAST_(3) << 14)
 #define MIPS_CONF4_MMUEXTDEF_MMUSIZEEXT (_ULCAST_(1) << 14)
 
+#define MIPS_CONF5_NF		(_ULCAST_(1) << 0)
+#define MIPS_CONF5_UFR		(_ULCAST_(1) << 2)
+#define MIPS_CONF5_MSAEN	(_ULCAST_(1) << 27)
+#define MIPS_CONF5_EVA		(_ULCAST_(1) << 28)
+#define MIPS_CONF5_CV		(_ULCAST_(1) << 29)
+#define MIPS_CONF5_K		(_ULCAST_(1) << 30)
+
 #define MIPS_CONF6_SYND		(_ULCAST_(1) << 13)
 
 #define MIPS_CONF7_WII		(_ULCAST_(1) << 31)
diff --git a/arch/mips/include/asm/mutex.h b/arch/mips/include/asm/mutex.h
deleted file mode 100644
index 458c1f7fbc18..000000000000
--- a/arch/mips/include/asm/mutex.h
+++ /dev/null
@@ -1,9 +0,0 @@
-/*
- * Pull in the generic implementation for the mutex fastpath.
- *
- * TODO: implement optimized primitives instead, or leave the generic
- * implementation in place, or pick the atomic_xchg() based generic
- * implementation. (see asm-generic/mutex-xchg.h for details)
- */
-
-#include <asm-generic/mutex-dec.h>
diff --git a/arch/mips/include/asm/netlogic/xlp-hal/bridge.h b/arch/mips/include/asm/netlogic/xlp-hal/bridge.h
index 790f0f1e55c6..4e8eacb9588a 100644
--- a/arch/mips/include/asm/netlogic/xlp-hal/bridge.h
+++ b/arch/mips/include/asm/netlogic/xlp-hal/bridge.h
@@ -88,6 +88,7 @@
 #define BRIDGE_DRAM_LIMIT6		0x22
 #define BRIDGE_DRAM_LIMIT7		0x23
 
+#define BRIDGE_DRAM_NODE_TRANSLN(i)	(0x24 + (i))
 #define BRIDGE_DRAM_NODE_TRANSLN0	0x24
 #define BRIDGE_DRAM_NODE_TRANSLN1	0x25
 #define BRIDGE_DRAM_NODE_TRANSLN2	0x26
@@ -96,6 +97,8 @@
 #define BRIDGE_DRAM_NODE_TRANSLN5	0x29
 #define BRIDGE_DRAM_NODE_TRANSLN6	0x2a
 #define BRIDGE_DRAM_NODE_TRANSLN7	0x2b
+
+#define BRIDGE_DRAM_CHNL_TRANSLN(i)	(0x2c + (i))
 #define BRIDGE_DRAM_CHNL_TRANSLN0	0x2c
 #define BRIDGE_DRAM_CHNL_TRANSLN1	0x2d
 #define BRIDGE_DRAM_CHNL_TRANSLN2	0x2e
@@ -104,6 +107,7 @@
 #define BRIDGE_DRAM_CHNL_TRANSLN5	0x31
 #define BRIDGE_DRAM_CHNL_TRANSLN6	0x32
 #define BRIDGE_DRAM_CHNL_TRANSLN7	0x33
+
 #define BRIDGE_PCIEMEM_BASE0		0x34
 #define BRIDGE_PCIEMEM_BASE1		0x35
 #define BRIDGE_PCIEMEM_BASE2		0x36
diff --git a/arch/mips/include/asm/netlogic/xlp-hal/iomap.h b/arch/mips/include/asm/netlogic/xlp-hal/iomap.h
index 9fac46fb7913..55eee77adaca 100644
--- a/arch/mips/include/asm/netlogic/xlp-hal/iomap.h
+++ b/arch/mips/include/asm/netlogic/xlp-hal/iomap.h
@@ -72,6 +72,12 @@
 #define XLP_IO_USB_OHCI2_OFFSET(node)	XLP_HDR_OFFSET(node, 0, 2, 4)
 #define XLP_IO_USB_OHCI3_OFFSET(node)	XLP_HDR_OFFSET(node, 0, 2, 5)
 
+/* XLP2xx has an updated USB block */
+#define XLP2XX_IO_USB_OFFSET(node, i)	XLP_HDR_OFFSET(node, 0, 4, i)
+#define XLP2XX_IO_USB_XHCI0_OFFSET(node)	XLP_HDR_OFFSET(node, 0, 4, 1)
+#define XLP2XX_IO_USB_XHCI1_OFFSET(node)	XLP_HDR_OFFSET(node, 0, 4, 2)
+#define XLP2XX_IO_USB_XHCI2_OFFSET(node)	XLP_HDR_OFFSET(node, 0, 4, 3)
+
 #define XLP_IO_NAE_OFFSET(node)		XLP_HDR_OFFSET(node, 0, 3, 0)
 #define XLP_IO_POE_OFFSET(node)		XLP_HDR_OFFSET(node, 0, 3, 1)
 
@@ -88,6 +94,9 @@
 #define XLP_IO_I2C0_OFFSET(node)	XLP_HDR_OFFSET(node, 0, 6, 2)
 #define XLP_IO_I2C1_OFFSET(node)	XLP_HDR_OFFSET(node, 0, 6, 3)
 #define XLP_IO_GPIO_OFFSET(node)	XLP_HDR_OFFSET(node, 0, 6, 4)
+/* on 2XX, all I2C busses are on the same block */
+#define XLP2XX_IO_I2C_OFFSET(node)	XLP_HDR_OFFSET(node, 0, 6, 7)
+
 /* system management */
 #define XLP_IO_SYS_OFFSET(node)		XLP_HDR_OFFSET(node, 0, 6, 5)
 #define XLP_IO_JTAG_OFFSET(node)	XLP_HDR_OFFSET(node, 0, 6, 6)
@@ -145,6 +154,7 @@
 #define PCI_DEVICE_ID_NLM_NOR		0x1015
 #define PCI_DEVICE_ID_NLM_NAND		0x1016
 #define PCI_DEVICE_ID_NLM_MMC		0x1018
+#define PCI_DEVICE_ID_NLM_XHCI		0x101d
 
 #ifndef __ASSEMBLY__
 
diff --git a/arch/mips/include/asm/netlogic/xlp-hal/pic.h b/arch/mips/include/asm/netlogic/xlp-hal/pic.h
index 4b5108dfaa16..105389b79f09 100644
--- a/arch/mips/include/asm/netlogic/xlp-hal/pic.h
+++ b/arch/mips/include/asm/netlogic/xlp-hal/pic.h
@@ -208,13 +208,14 @@
 #define PIC_LOCAL_SCHEDULING		1
 #define PIC_GLOBAL_SCHEDULING		0
 
-#define PIC_CLK_HZ			133333333
-
 #define nlm_read_pic_reg(b, r)	nlm_read_reg64(b, r)
 #define nlm_write_pic_reg(b, r, v) nlm_write_reg64(b, r, v)
 #define nlm_get_pic_pcibase(node) nlm_pcicfg_base(XLP_IO_PIC_OFFSET(node))
 #define nlm_get_pic_regbase(node) (nlm_get_pic_pcibase(node) + XLP_IO_PCI_HDRSZ)
 
+/* We use PIC on node 0 as a timer */
+#define pic_timer_freq()		nlm_get_pic_frequency(0)
+
 /* IRT and h/w interrupt routines */
 static inline int
 nlm_pic_read_irt(uint64_t base, int irt_index)
diff --git a/arch/mips/include/asm/netlogic/xlp-hal/sys.h b/arch/mips/include/asm/netlogic/xlp-hal/sys.h
index 470e52bfc061..fcf2833c16ca 100644
--- a/arch/mips/include/asm/netlogic/xlp-hal/sys.h
+++ b/arch/mips/include/asm/netlogic/xlp-hal/sys.h
@@ -117,6 +117,36 @@
 #define SYS_SCRTCH2				0x4b
 #define SYS_SCRTCH3				0x4c
 
+/* PLL registers XLP2XX */
+#define SYS_PLL_CTRL0				0x240
+#define SYS_PLL_CTRL1				0x241
+#define SYS_PLL_CTRL2				0x242
+#define SYS_PLL_CTRL3				0x243
+#define SYS_DMC_PLL_CTRL0			0x244
+#define SYS_DMC_PLL_CTRL1			0x245
+#define SYS_DMC_PLL_CTRL2			0x246
+#define SYS_DMC_PLL_CTRL3			0x247
+
+#define SYS_PLL_CTRL0_DEVX(x)			(0x248 + (x) * 4)
+#define SYS_PLL_CTRL1_DEVX(x)			(0x249 + (x) * 4)
+#define SYS_PLL_CTRL2_DEVX(x)			(0x24a + (x) * 4)
+#define SYS_PLL_CTRL3_DEVX(x)			(0x24b + (x) * 4)
+
+#define SYS_CPU_PLL_CHG_CTRL			0x288
+#define SYS_PLL_CHG_CTRL			0x289
+#define SYS_CLK_DEV_DIS				0x28a
+#define SYS_CLK_DEV_SEL				0x28b
+#define SYS_CLK_DEV_DIV				0x28c
+#define SYS_CLK_DEV_CHG				0x28d
+#define SYS_CLK_DEV_SEL_REG			0x28e
+#define SYS_CLK_DEV_DIV_REG			0x28f
+#define SYS_CPU_PLL_LOCK			0x29f
+#define SYS_SYS_PLL_LOCK			0x2a0
+#define SYS_PLL_MEM_CMD				0x2a1
+#define SYS_CPU_PLL_MEM_REQ			0x2a2
+#define SYS_SYS_PLL_MEM_REQ			0x2a3
+#define SYS_PLL_MEM_STAT			0x2a4
+
 #ifndef __ASSEMBLY__
 
 #define nlm_read_sys_reg(b, r)		nlm_read_reg(b, r)
@@ -124,5 +154,6 @@
 #define nlm_get_sys_pcibase(node) nlm_pcicfg_base(XLP_IO_SYS_OFFSET(node))
 #define nlm_get_sys_regbase(node) (nlm_get_sys_pcibase(node) + XLP_IO_PCI_HDRSZ)
 
+unsigned int nlm_get_pic_frequency(int node);
 #endif
 #endif
diff --git a/arch/mips/include/asm/netlogic/xlp-hal/xlp.h b/arch/mips/include/asm/netlogic/xlp-hal/xlp.h
index f4ea0f7f3965..17daffb280a3 100644
--- a/arch/mips/include/asm/netlogic/xlp-hal/xlp.h
+++ b/arch/mips/include/asm/netlogic/xlp-hal/xlp.h
@@ -41,15 +41,22 @@
 #define PIC_PCIE_LINK_1_IRQ		20
 #define PIC_PCIE_LINK_2_IRQ		21
 #define PIC_PCIE_LINK_3_IRQ		22
+
 #define PIC_EHCI_0_IRQ			23
 #define PIC_EHCI_1_IRQ			24
 #define PIC_OHCI_0_IRQ			25
 #define PIC_OHCI_1_IRQ			26
 #define PIC_OHCI_2_IRQ			27
 #define PIC_OHCI_3_IRQ			28
+#define PIC_2XX_XHCI_0_IRQ		23
+#define PIC_2XX_XHCI_1_IRQ		24
+#define PIC_2XX_XHCI_2_IRQ		25
+
 #define PIC_MMC_IRQ			29
 #define PIC_I2C_0_IRQ			30
 #define PIC_I2C_1_IRQ			31
+#define PIC_I2C_2_IRQ			32
+#define PIC_I2C_3_IRQ			33
 
 #ifndef __ASSEMBLY__
 
@@ -59,7 +66,17 @@ void xlp_wakeup_secondary_cpus(void);
 
 void xlp_mmu_init(void);
 void nlm_hal_init(void);
+int xlp_get_dram_map(int n, uint64_t *dram_map);
+
+/* Device tree related */
 void *xlp_dt_init(void *fdtp);
 
+static inline int cpu_is_xlpii(void)
+{
+	int chip = read_c0_prid() & 0xff00;
+
+	return chip == PRID_IMP_NETLOGIC_XLP2XX;
+}
+
 #endif /* !__ASSEMBLY__ */
 #endif /* _ASM_NLM_XLP_H */
diff --git a/arch/mips/include/asm/netlogic/xlr/pic.h b/arch/mips/include/asm/netlogic/xlr/pic.h
index 63c99176dffe..3c80a75233bd 100644
--- a/arch/mips/include/asm/netlogic/xlr/pic.h
+++ b/arch/mips/include/asm/netlogic/xlr/pic.h
@@ -36,6 +36,8 @@
 #define _ASM_NLM_XLR_PIC_H
 
 #define PIC_CLK_HZ			66666666
+#define pic_timer_freq()		PIC_CLK_HZ
+
 /* PIC hardware interrupt numbers */
 #define PIC_IRT_WD_INDEX		0
 #define PIC_IRT_TIMER_0_INDEX		1
diff --git a/arch/mips/include/asm/octeon/octeon.h b/arch/mips/include/asm/octeon/octeon.h
index a2eed23c49a9..f5d77b91537f 100644
--- a/arch/mips/include/asm/octeon/octeon.h
+++ b/arch/mips/include/asm/octeon/octeon.h
@@ -251,4 +251,6 @@ extern void (*octeon_irq_setup_secondary)(void);
 typedef void (*octeon_irq_ip4_handler_t)(void);
 void octeon_irq_set_ip4_handler(octeon_irq_ip4_handler_t);
 
+extern void octeon_fixup_irqs(void);
+
 #endif /* __ASM_OCTEON_OCTEON_H */
diff --git a/arch/mips/include/asm/parport.h b/arch/mips/include/asm/parport.h
deleted file mode 100644
index cf252af64590..000000000000
--- a/arch/mips/include/asm/parport.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/parport.h>
diff --git a/arch/mips/include/asm/pci.h b/arch/mips/include/asm/pci.h
index fa8e0aa250ca..12d6842962be 100644
--- a/arch/mips/include/asm/pci.h
+++ b/arch/mips/include/asm/pci.h
@@ -83,6 +83,18 @@ static inline void pcibios_penalize_isa_irq(int irq, int active)
 extern int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
 	enum pci_mmap_state mmap_state, int write_combine);
 
+#define HAVE_ARCH_PCI_RESOURCE_TO_USER
+
+static inline void pci_resource_to_user(const struct pci_dev *dev, int bar,
+		const struct resource *rsrc, resource_size_t *start,
+		resource_size_t *end)
+{
+	phys_t size = resource_size(rsrc);
+
+	*start = fixup_bigphys_addr(rsrc->start, size);
+	*end = rsrc->start + size;
+}
+
 /*
  * Dynamic DMA mapping stuff.
  * MIPS has everything mapped statically.
@@ -136,11 +148,6 @@ static inline int pci_get_legacy_ide_irq(struct pci_dev *dev, int channel)
 	return channel ? 15 : 14;
 }
 
-#ifdef CONFIG_CPU_CAVIUM_OCTEON
-/* MSI arch hook for OCTEON */
-#define arch_setup_msi_irqs arch_setup_msi_irqs
-#endif
-
 extern char * (*pcibios_plat_setup)(char *str);
 
 #ifdef CONFIG_OF
diff --git a/arch/mips/include/asm/percpu.h b/arch/mips/include/asm/percpu.h
deleted file mode 100644
index 844e763e9332..000000000000
--- a/arch/mips/include/asm/percpu.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __ASM_PERCPU_H
-#define __ASM_PERCPU_H
-
-#include <asm-generic/percpu.h>
-
-#endif /* __ASM_PERCPU_H */
diff --git a/arch/mips/include/asm/scatterlist.h b/arch/mips/include/asm/scatterlist.h
deleted file mode 100644
index 7ee0e646d82c..000000000000
--- a/arch/mips/include/asm/scatterlist.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __ASM_SCATTERLIST_H
-#define __ASM_SCATTERLIST_H
-
-#include <asm-generic/scatterlist.h>
-
-#endif /* __ASM_SCATTERLIST_H */
diff --git a/arch/mips/include/asm/sections.h b/arch/mips/include/asm/sections.h
deleted file mode 100644
index b7e37262c246..000000000000
--- a/arch/mips/include/asm/sections.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef _ASM_SECTIONS_H
-#define _ASM_SECTIONS_H
-
-#include <asm-generic/sections.h>
-
-#endif /* _ASM_SECTIONS_H */
diff --git a/arch/mips/include/asm/segment.h b/arch/mips/include/asm/segment.h
deleted file mode 100644
index 92ac001fc483..000000000000
--- a/arch/mips/include/asm/segment.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef _ASM_SEGMENT_H
-#define _ASM_SEGMENT_H
-
-/* Only here because we have some old header files that expect it.. */
-
-#endif /* _ASM_SEGMENT_H */
diff --git a/arch/mips/include/asm/serial.h b/arch/mips/include/asm/serial.h
deleted file mode 100644
index a0cb0caff152..000000000000
--- a/arch/mips/include/asm/serial.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/serial.h>
diff --git a/arch/mips/include/asm/timex.h b/arch/mips/include/asm/timex.h
index 6529704aa73a..c5424757da65 100644
--- a/arch/mips/include/asm/timex.h
+++ b/arch/mips/include/asm/timex.h
@@ -10,7 +10,9 @@
 
 #ifdef __KERNEL__
 
+#include <asm/cpu-features.h>
 #include <asm/mipsregs.h>
+#include <asm/cpu-type.h>
 
 /*
  * This is the clock rate of the i8253 PIT.  A MIPS system may not have
@@ -33,9 +35,38 @@
 
 typedef unsigned int cycles_t;
 
+/*
+ * On R4000/R4400 before version 5.0 an erratum exists such that if the
+ * cycle counter is read in the exact moment that it is matching the
+ * compare register, no interrupt will be generated.
+ *
+ * There is a suggested workaround and also the erratum can't strike if
+ * the compare interrupt isn't being used as the clock source device.
+ * However for now the implementaton of this function doesn't get these
+ * fine details right.
+ */
 static inline cycles_t get_cycles(void)
 {
-	return 0;
+	switch (boot_cpu_type()) {
+	case CPU_R4400PC:
+	case CPU_R4400SC:
+	case CPU_R4400MC:
+		if ((read_c0_prid() & 0xff) >= 0x0050)
+			return read_c0_count();
+		break;
+
+        case CPU_R4000PC:
+        case CPU_R4000SC:
+        case CPU_R4000MC:
+		break;
+
+	default:
+		if (cpu_has_counter)
+			return read_c0_count();
+		break;
+	}
+
+	return 0;	/* no usable counter */
 }
 
 #endif /* __KERNEL__ */
diff --git a/arch/mips/include/asm/ucontext.h b/arch/mips/include/asm/ucontext.h
deleted file mode 100644
index 9bc07b9f30fb..000000000000
--- a/arch/mips/include/asm/ucontext.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/ucontext.h>
diff --git a/arch/mips/include/asm/vga.h b/arch/mips/include/asm/vga.h
index f4cff7e4fa8a..f82c83749a08 100644
--- a/arch/mips/include/asm/vga.h
+++ b/arch/mips/include/asm/vga.h
@@ -6,6 +6,7 @@
 #ifndef _ASM_VGA_H
 #define _ASM_VGA_H
 
+#include <asm/addrspace.h>
 #include <asm/byteorder.h>
 
 /*
@@ -13,7 +14,7 @@
  *	access the videoram directly without any black magic.
  */
 
-#define VGA_MAP_MEM(x, s)	(0xb0000000L + (unsigned long)(x))
+#define VGA_MAP_MEM(x, s)	CKSEG1ADDR(0x10000000L + (unsigned long)(x))
 
 #define vga_readb(x)	(*(x))
 #define vga_writeb(x, y)	(*(y) = (x))
diff --git a/arch/mips/include/asm/xor.h b/arch/mips/include/asm/xor.h
deleted file mode 100644
index c82eb12a5b18..000000000000
--- a/arch/mips/include/asm/xor.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/xor.h>
diff --git a/arch/mips/include/uapi/asm/Kbuild b/arch/mips/include/uapi/asm/Kbuild
index 350ccccadcb9..be7196eacb88 100644
--- a/arch/mips/include/uapi/asm/Kbuild
+++ b/arch/mips/include/uapi/asm/Kbuild
@@ -1,7 +1,9 @@
 # UAPI Header export list
 include include/uapi/asm-generic/Kbuild.asm
 
-header-y += auxvec.h
+generic-y += auxvec.h
+generic-y += ipcbuf.h
+
 header-y += bitsperlong.h
 header-y += break.h
 header-y += byteorder.h
@@ -11,7 +13,6 @@ header-y += fcntl.h
 header-y += inst.h
 header-y += ioctl.h
 header-y += ioctls.h
-header-y += ipcbuf.h
 header-y += kvm_para.h
 header-y += mman.h
 header-y += msgbuf.h
diff --git a/arch/mips/include/uapi/asm/auxvec.h b/arch/mips/include/uapi/asm/auxvec.h
deleted file mode 100644
index 7cf7f2d21943..000000000000
--- a/arch/mips/include/uapi/asm/auxvec.h
+++ /dev/null
@@ -1,4 +0,0 @@
-#ifndef _ASM_AUXVEC_H
-#define _ASM_AUXVEC_H
-
-#endif /* _ASM_AUXVEC_H */
diff --git a/arch/mips/include/uapi/asm/ipcbuf.h b/arch/mips/include/uapi/asm/ipcbuf.h
deleted file mode 100644
index 84c7e51cb6d0..000000000000
--- a/arch/mips/include/uapi/asm/ipcbuf.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/ipcbuf.h>
diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c
index 4c6167a17875..5465dc183e5a 100644
--- a/arch/mips/kernel/cpu-probe.c
+++ b/arch/mips/kernel/cpu-probe.c
@@ -20,6 +20,7 @@
 
 #include <asm/bugs.h>
 #include <asm/cpu.h>
+#include <asm/cpu-type.h>
 #include <asm/fpu.h>
 #include <asm/mipsregs.h>
 #include <asm/watch.h>
@@ -55,7 +56,7 @@ static inline void check_errata(void)
 {
 	struct cpuinfo_mips *c = &current_cpu_data;
 
-	switch (c->cputype) {
+	switch (current_cpu_type()) {
 	case CPU_34K:
 		/*
 		 * Erratum "RPS May Cause Incorrect Instruction Execution"
@@ -122,7 +123,7 @@ static inline unsigned long cpu_get_fpu_id(void)
  */
 static inline int __cpu_has_fpu(void)
 {
-	return ((cpu_get_fpu_id() & 0xff00) != FPIR_IMP_NONE);
+	return ((cpu_get_fpu_id() & FPIR_IMP_MASK) != FPIR_IMP_NONE);
 }
 
 static inline void cpu_probe_vmbits(struct cpuinfo_mips *c)
@@ -290,6 +291,17 @@ static inline unsigned int decode_config4(struct cpuinfo_mips *c)
 	return config4 & MIPS_CONF_M;
 }
 
+static inline unsigned int decode_config5(struct cpuinfo_mips *c)
+{
+	unsigned int config5;
+
+	config5 = read_c0_config5();
+	config5 &= ~MIPS_CONF5_UFR;
+	write_c0_config5(config5);
+
+	return config5 & MIPS_CONF_M;
+}
+
 static void decode_configs(struct cpuinfo_mips *c)
 {
 	int ok;
@@ -310,6 +322,8 @@ static void decode_configs(struct cpuinfo_mips *c)
 		ok = decode_config3(c);
 	if (ok)
 		ok = decode_config4(c);
+	if (ok)
+		ok = decode_config5(c);
 
 	mips_probe_watch_registers(c);
 
@@ -322,7 +336,7 @@ static void decode_configs(struct cpuinfo_mips *c)
 
 static inline void cpu_probe_legacy(struct cpuinfo_mips *c, unsigned int cpu)
 {
-	switch (c->processor_id & 0xff00) {
+	switch (c->processor_id & PRID_IMP_MASK) {
 	case PRID_IMP_R2000:
 		c->cputype = CPU_R2000;
 		__cpu_name[cpu] = "R2000";
@@ -333,7 +347,7 @@ static inline void cpu_probe_legacy(struct cpuinfo_mips *c, unsigned int cpu)
 		c->tlbsize = 64;
 		break;
 	case PRID_IMP_R3000:
-		if ((c->processor_id & 0xff) == PRID_REV_R3000A) {
+		if ((c->processor_id & PRID_REV_MASK) == PRID_REV_R3000A) {
 			if (cpu_has_confreg()) {
 				c->cputype = CPU_R3081E;
 				__cpu_name[cpu] = "R3081";
@@ -353,7 +367,8 @@ static inline void cpu_probe_legacy(struct cpuinfo_mips *c, unsigned int cpu)
 		break;
 	case PRID_IMP_R4000:
 		if (read_c0_config() & CONF_SC) {
-			if ((c->processor_id & 0xff) >= PRID_REV_R4400) {
+			if ((c->processor_id & PRID_REV_MASK) >=
+			    PRID_REV_R4400) {
 				c->cputype = CPU_R4400PC;
 				__cpu_name[cpu] = "R4400PC";
 			} else {
@@ -361,7 +376,8 @@ static inline void cpu_probe_legacy(struct cpuinfo_mips *c, unsigned int cpu)
 				__cpu_name[cpu] = "R4000PC";
 			}
 		} else {
-			if ((c->processor_id & 0xff) >= PRID_REV_R4400) {
+			if ((c->processor_id & PRID_REV_MASK) >=
+			    PRID_REV_R4400) {
 				c->cputype = CPU_R4400SC;
 				__cpu_name[cpu] = "R4400SC";
 			} else {
@@ -454,7 +470,7 @@ static inline void cpu_probe_legacy(struct cpuinfo_mips *c, unsigned int cpu)
 			__cpu_name[cpu] = "TX3927";
 			c->tlbsize = 64;
 		} else {
-			switch (c->processor_id & 0xff) {
+			switch (c->processor_id & PRID_REV_MASK) {
 			case PRID_REV_TX3912:
 				c->cputype = CPU_TX3912;
 				__cpu_name[cpu] = "TX3912";
@@ -640,7 +656,7 @@ static inline void cpu_probe_legacy(struct cpuinfo_mips *c, unsigned int cpu)
 static inline void cpu_probe_mips(struct cpuinfo_mips *c, unsigned int cpu)
 {
 	decode_configs(c);
-	switch (c->processor_id & 0xff00) {
+	switch (c->processor_id & PRID_IMP_MASK) {
 	case PRID_IMP_4KC:
 		c->cputype = CPU_4KC;
 		__cpu_name[cpu] = "MIPS 4Kc";
@@ -711,7 +727,7 @@ static inline void cpu_probe_mips(struct cpuinfo_mips *c, unsigned int cpu)
 static inline void cpu_probe_alchemy(struct cpuinfo_mips *c, unsigned int cpu)
 {
 	decode_configs(c);
-	switch (c->processor_id & 0xff00) {
+	switch (c->processor_id & PRID_IMP_MASK) {
 	case PRID_IMP_AU1_REV1:
 	case PRID_IMP_AU1_REV2:
 		c->cputype = CPU_ALCHEMY;
@@ -730,7 +746,7 @@ static inline void cpu_probe_alchemy(struct cpuinfo_mips *c, unsigned int cpu)
 			break;
 		case 4:
 			__cpu_name[cpu] = "Au1200";
-			if ((c->processor_id & 0xff) == 2)
+			if ((c->processor_id & PRID_REV_MASK) == 2)
 				__cpu_name[cpu] = "Au1250";
 			break;
 		case 5:
@@ -748,12 +764,12 @@ static inline void cpu_probe_sibyte(struct cpuinfo_mips *c, unsigned int cpu)
 {
 	decode_configs(c);
 
-	switch (c->processor_id & 0xff00) {
+	switch (c->processor_id & PRID_IMP_MASK) {
 	case PRID_IMP_SB1:
 		c->cputype = CPU_SB1;
 		__cpu_name[cpu] = "SiByte SB1";
 		/* FPU in pass1 is known to have issues. */
-		if ((c->processor_id & 0xff) < 0x02)
+		if ((c->processor_id & PRID_REV_MASK) < 0x02)
 			c->options &= ~(MIPS_CPU_FPU | MIPS_CPU_32FPR);
 		break;
 	case PRID_IMP_SB1A:
@@ -766,7 +782,7 @@ static inline void cpu_probe_sibyte(struct cpuinfo_mips *c, unsigned int cpu)
 static inline void cpu_probe_sandcraft(struct cpuinfo_mips *c, unsigned int cpu)
 {
 	decode_configs(c);
-	switch (c->processor_id & 0xff00) {
+	switch (c->processor_id & PRID_IMP_MASK) {
 	case PRID_IMP_SR71000:
 		c->cputype = CPU_SR71000;
 		__cpu_name[cpu] = "Sandcraft SR71000";
@@ -779,7 +795,7 @@ static inline void cpu_probe_sandcraft(struct cpuinfo_mips *c, unsigned int cpu)
 static inline void cpu_probe_nxp(struct cpuinfo_mips *c, unsigned int cpu)
 {
 	decode_configs(c);
-	switch (c->processor_id & 0xff00) {
+	switch (c->processor_id & PRID_IMP_MASK) {
 	case PRID_IMP_PR4450:
 		c->cputype = CPU_PR4450;
 		__cpu_name[cpu] = "Philips PR4450";
@@ -791,7 +807,7 @@ static inline void cpu_probe_nxp(struct cpuinfo_mips *c, unsigned int cpu)
 static inline void cpu_probe_broadcom(struct cpuinfo_mips *c, unsigned int cpu)
 {
 	decode_configs(c);
-	switch (c->processor_id & 0xff00) {
+	switch (c->processor_id & PRID_IMP_MASK) {
 	case PRID_IMP_BMIPS32_REV4:
 	case PRID_IMP_BMIPS32_REV8:
 		c->cputype = CPU_BMIPS32;
@@ -806,7 +822,7 @@ static inline void cpu_probe_broadcom(struct cpuinfo_mips *c, unsigned int cpu)
 		set_elf_platform(cpu, "bmips3300");
 		break;
 	case PRID_IMP_BMIPS43XX: {
-		int rev = c->processor_id & 0xff;
+		int rev = c->processor_id & PRID_REV_MASK;
 
 		if (rev >= PRID_REV_BMIPS4380_LO &&
 				rev <= PRID_REV_BMIPS4380_HI) {
@@ -832,7 +848,7 @@ static inline void cpu_probe_broadcom(struct cpuinfo_mips *c, unsigned int cpu)
 static inline void cpu_probe_cavium(struct cpuinfo_mips *c, unsigned int cpu)
 {
 	decode_configs(c);
-	switch (c->processor_id & 0xff00) {
+	switch (c->processor_id & PRID_IMP_MASK) {
 	case PRID_IMP_CAVIUM_CN38XX:
 	case PRID_IMP_CAVIUM_CN31XX:
 	case PRID_IMP_CAVIUM_CN30XX:
@@ -852,10 +868,17 @@ platform:
 	case PRID_IMP_CAVIUM_CN63XX:
 	case PRID_IMP_CAVIUM_CN66XX:
 	case PRID_IMP_CAVIUM_CN68XX:
+	case PRID_IMP_CAVIUM_CNF71XX:
 		c->cputype = CPU_CAVIUM_OCTEON2;
 		__cpu_name[cpu] = "Cavium Octeon II";
 		set_elf_platform(cpu, "octeon2");
 		break;
+	case PRID_IMP_CAVIUM_CN70XX:
+	case PRID_IMP_CAVIUM_CN78XX:
+		c->cputype = CPU_CAVIUM_OCTEON3;
+		__cpu_name[cpu] = "Cavium Octeon III";
+		set_elf_platform(cpu, "octeon3");
+		break;
 	default:
 		printk(KERN_INFO "Unknown Octeon chip!\n");
 		c->cputype = CPU_UNKNOWN;
@@ -868,7 +891,7 @@ static inline void cpu_probe_ingenic(struct cpuinfo_mips *c, unsigned int cpu)
 	decode_configs(c);
 	/* JZRISC does not implement the CP0 counter. */
 	c->options &= ~MIPS_CPU_COUNTER;
-	switch (c->processor_id & 0xff00) {
+	switch (c->processor_id & PRID_IMP_MASK) {
 	case PRID_IMP_JZRISC:
 		c->cputype = CPU_JZRISC;
 		__cpu_name[cpu] = "Ingenic JZRISC";
@@ -883,7 +906,7 @@ static inline void cpu_probe_netlogic(struct cpuinfo_mips *c, int cpu)
 {
 	decode_configs(c);
 
-	if ((c->processor_id & 0xff00) == PRID_IMP_NETLOGIC_AU13XX) {
+	if ((c->processor_id & PRID_IMP_MASK) == PRID_IMP_NETLOGIC_AU13XX) {
 		c->cputype = CPU_ALCHEMY;
 		__cpu_name[cpu] = "Au1300";
 		/* following stuff is not for Alchemy */
@@ -898,7 +921,12 @@ static inline void cpu_probe_netlogic(struct cpuinfo_mips *c, int cpu)
 			MIPS_CPU_EJTAG	 |
 			MIPS_CPU_LLSC);
 
-	switch (c->processor_id & 0xff00) {
+	switch (c->processor_id & PRID_IMP_MASK) {
+	case PRID_IMP_NETLOGIC_XLP2XX:
+		c->cputype = CPU_XLP;
+		__cpu_name[cpu] = "Broadcom XLPII";
+		break;
+
 	case PRID_IMP_NETLOGIC_XLP8XX:
 	case PRID_IMP_NETLOGIC_XLP3XX:
 		c->cputype = CPU_XLP;
@@ -972,7 +1000,7 @@ void cpu_probe(void)
 	c->cputype	= CPU_UNKNOWN;
 
 	c->processor_id = read_c0_prid();
-	switch (c->processor_id & 0xff0000) {
+	switch (c->processor_id & PRID_COMP_MASK) {
 	case PRID_COMP_LEGACY:
 		cpu_probe_legacy(c, cpu);
 		break;
diff --git a/arch/mips/kernel/csrc-ioasic.c b/arch/mips/kernel/csrc-ioasic.c
index 0654bff9b69c..6cbbf6e106b9 100644
--- a/arch/mips/kernel/csrc-ioasic.c
+++ b/arch/mips/kernel/csrc-ioasic.c
@@ -37,13 +37,13 @@ static struct clocksource clocksource_dec = {
 	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
 };
 
-void __init dec_ioasic_clocksource_init(void)
+int __init dec_ioasic_clocksource_init(void)
 {
 	unsigned int freq;
 	u32 start, end;
-	int i = HZ / 10;
-
+	int i = HZ / 8;
 
+	ds1287_timer_state();
 	while (!ds1287_timer_state())
 		;
 
@@ -55,9 +55,15 @@ void __init dec_ioasic_clocksource_init(void)
 
 	end = dec_ioasic_hpt_read(&clocksource_dec);
 
-	freq = (end - start) * 10;
+	freq = (end - start) * 8;
+
+	/* An early revision of the I/O ASIC didn't have the counter.  */
+	if (!freq)
+		return -ENXIO;
+
 	printk(KERN_INFO "I/O ASIC clock frequency %dHz\n", freq);
 
 	clocksource_dec.rating = 200 + freq / 10000000;
 	clocksource_register_hz(&clocksource_dec, freq);
+	return 0;
 }
diff --git a/arch/mips/kernel/idle.c b/arch/mips/kernel/idle.c
index 0c655deeea4a..f7991d95bff9 100644
--- a/arch/mips/kernel/idle.c
+++ b/arch/mips/kernel/idle.c
@@ -18,6 +18,7 @@
 #include <linux/sched.h>
 #include <asm/cpu.h>
 #include <asm/cpu-info.h>
+#include <asm/cpu-type.h>
 #include <asm/idle.h>
 #include <asm/mipsregs.h>
 
@@ -136,7 +137,7 @@ void __init check_wait(void)
 		return;
 	}
 
-	switch (c->cputype) {
+	switch (current_cpu_type()) {
 	case CPU_R3081:
 	case CPU_R3081E:
 		cpu_wait = r3081_wait;
@@ -166,6 +167,7 @@ void __init check_wait(void)
 	case CPU_CAVIUM_OCTEON:
 	case CPU_CAVIUM_OCTEON_PLUS:
 	case CPU_CAVIUM_OCTEON2:
+	case CPU_CAVIUM_OCTEON3:
 	case CPU_JZRISC:
 	case CPU_LOONGSON1:
 	case CPU_XLR:
diff --git a/arch/mips/kernel/mcount.S b/arch/mips/kernel/mcount.S
index a03e93c4a946..539b6294b613 100644
--- a/arch/mips/kernel/mcount.S
+++ b/arch/mips/kernel/mcount.S
@@ -83,7 +83,7 @@ _mcount:
 	PTR_S	MCOUNT_RA_ADDRESS_REG, PT_R12(sp)
 #endif
 
-	move	a0, ra		/* arg1: self return address */
+	PTR_SUBU a0, ra, 8	/* arg1: self address */
 	.globl ftrace_call
 ftrace_call:
 	nop	/* a placeholder for the call to a real tracing function */
diff --git a/arch/mips/kernel/octeon_switch.S b/arch/mips/kernel/octeon_switch.S
index 4204d76af854..029e002a4ea0 100644
--- a/arch/mips/kernel/octeon_switch.S
+++ b/arch/mips/kernel/octeon_switch.S
@@ -73,7 +73,7 @@
 3:
 
 #if defined(CONFIG_CC_STACKPROTECTOR) && !defined(CONFIG_SMP)
-	PTR_L	t8, __stack_chk_guard
+	PTR_LA	t8, __stack_chk_guard
 	LONG_L	t9, TASK_STACK_CANARY(a1)
 	LONG_S	t9, 0(t8)
 #endif
diff --git a/arch/mips/kernel/prom.c b/arch/mips/kernel/prom.c
index 7e954042f252..0fa0b69cdd53 100644
--- a/arch/mips/kernel/prom.c
+++ b/arch/mips/kernel/prom.c
@@ -58,8 +58,7 @@ void * __init early_init_dt_alloc_memory_arch(u64 size, u64 align)
 }
 
 #ifdef CONFIG_BLK_DEV_INITRD
-void __init early_init_dt_setup_initrd_arch(unsigned long start,
-					    unsigned long end)
+void __init early_init_dt_setup_initrd_arch(u64 start, u64 end)
 {
 	initrd_start = (unsigned long)__va(start);
 	initrd_end = (unsigned long)__va(end);
diff --git a/arch/mips/kernel/r2300_switch.S b/arch/mips/kernel/r2300_switch.S
index 38af83f84c4a..20b7b040e76f 100644
--- a/arch/mips/kernel/r2300_switch.S
+++ b/arch/mips/kernel/r2300_switch.S
@@ -67,7 +67,7 @@ LEAF(resume)
 1:
 
 #if defined(CONFIG_CC_STACKPROTECTOR) && !defined(CONFIG_SMP)
-	PTR_L	t8, __stack_chk_guard
+	PTR_LA	t8, __stack_chk_guard
 	LONG_L	t9, TASK_STACK_CANARY(a1)
 	LONG_S	t9, 0(t8)
 #endif
diff --git a/arch/mips/kernel/r4k_switch.S b/arch/mips/kernel/r4k_switch.S
index 921238a6bd26..078de5eaca8f 100644
--- a/arch/mips/kernel/r4k_switch.S
+++ b/arch/mips/kernel/r4k_switch.S
@@ -69,7 +69,7 @@
 1:
 
 #if defined(CONFIG_CC_STACKPROTECTOR) && !defined(CONFIG_SMP)
-	PTR_L	t8, __stack_chk_guard
+	PTR_LA	t8, __stack_chk_guard
 	LONG_L	t9, TASK_STACK_CANARY(a1)
 	LONG_S	t9, 0(t8)
 #endif
diff --git a/arch/mips/kernel/relocate_kernel.S b/arch/mips/kernel/relocate_kernel.S
index 43d2d78d3287..74bab9ddd0e1 100644
--- a/arch/mips/kernel/relocate_kernel.S
+++ b/arch/mips/kernel/relocate_kernel.S
@@ -26,6 +26,12 @@ process_entry:
 	PTR_L		s2, (s0)
 	PTR_ADD		s0, s0, SZREG
 
+	/*
+	 * In case of a kdump/crash kernel, the indirection page is not
+	 * populated as the kernel is directly copied to a reserved location
+	 */
+	beqz		s2, done
+
 	/* destination page */
 	and		s3, s2, 0x1
 	beq		s3, zero, 1f
diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c
index c7f90519e58c..c538d6e01b7b 100644
--- a/arch/mips/kernel/setup.c
+++ b/arch/mips/kernel/setup.c
@@ -552,6 +552,52 @@ static void __init arch_mem_addpart(phys_t mem, phys_t end, int type)
 	add_memory_region(mem, size, type);
 }
 
+#ifdef CONFIG_KEXEC
+static inline unsigned long long get_total_mem(void)
+{
+	unsigned long long total;
+
+	total = max_pfn - min_low_pfn;
+	return total << PAGE_SHIFT;
+}
+
+static void __init mips_parse_crashkernel(void)
+{
+	unsigned long long total_mem;
+	unsigned long long crash_size, crash_base;
+	int ret;
+
+	total_mem = get_total_mem();
+	ret = parse_crashkernel(boot_command_line, total_mem,
+				&crash_size, &crash_base);
+	if (ret != 0 || crash_size <= 0)
+		return;
+
+	crashk_res.start = crash_base;
+	crashk_res.end	 = crash_base + crash_size - 1;
+}
+
+static void __init request_crashkernel(struct resource *res)
+{
+	int ret;
+
+	ret = request_resource(res, &crashk_res);
+	if (!ret)
+		pr_info("Reserving %ldMB of memory at %ldMB for crashkernel\n",
+			(unsigned long)((crashk_res.end -
+					 crashk_res.start + 1) >> 20),
+			(unsigned long)(crashk_res.start  >> 20));
+}
+#else /* !defined(CONFIG_KEXEC)		*/
+static void __init mips_parse_crashkernel(void)
+{
+}
+
+static void __init request_crashkernel(struct resource *res)
+{
+}
+#endif /* !defined(CONFIG_KEXEC)  */
+
 static void __init arch_mem_init(char **cmdline_p)
 {
 	extern void plat_mem_setup(void);
@@ -608,6 +654,8 @@ static void __init arch_mem_init(char **cmdline_p)
 				BOOTMEM_DEFAULT);
 	}
 #endif
+
+	mips_parse_crashkernel();
 #ifdef CONFIG_KEXEC
 	if (crashk_res.start != crashk_res.end)
 		reserve_bootmem(crashk_res.start,
@@ -620,52 +668,6 @@ static void __init arch_mem_init(char **cmdline_p)
 	paging_init();
 }
 
-#ifdef CONFIG_KEXEC
-static inline unsigned long long get_total_mem(void)
-{
-	unsigned long long total;
-
-	total = max_pfn - min_low_pfn;
-	return total << PAGE_SHIFT;
-}
-
-static void __init mips_parse_crashkernel(void)
-{
-	unsigned long long total_mem;
-	unsigned long long crash_size, crash_base;
-	int ret;
-
-	total_mem = get_total_mem();
-	ret = parse_crashkernel(boot_command_line, total_mem,
-				&crash_size, &crash_base);
-	if (ret != 0 || crash_size <= 0)
-		return;
-
-	crashk_res.start = crash_base;
-	crashk_res.end	 = crash_base + crash_size - 1;
-}
-
-static void __init request_crashkernel(struct resource *res)
-{
-	int ret;
-
-	ret = request_resource(res, &crashk_res);
-	if (!ret)
-		pr_info("Reserving %ldMB of memory at %ldMB for crashkernel\n",
-			(unsigned long)((crashk_res.end -
-				crashk_res.start + 1) >> 20),
-			(unsigned long)(crashk_res.start  >> 20));
-}
-#else /* !defined(CONFIG_KEXEC)	 */
-static void __init mips_parse_crashkernel(void)
-{
-}
-
-static void __init request_crashkernel(struct resource *res)
-{
-}
-#endif /* !defined(CONFIG_KEXEC)  */
-
 static void __init resource_init(void)
 {
 	int i;
@@ -678,11 +680,6 @@ static void __init resource_init(void)
 	data_resource.start = __pa_symbol(&_etext);
 	data_resource.end = __pa_symbol(&_edata) - 1;
 
-	/*
-	 * Request address space for all standard RAM.
-	 */
-	mips_parse_crashkernel();
-
 	for (i = 0; i < boot_mem_map.nr_map; i++) {
 		struct resource *res;
 		unsigned long start, end;
diff --git a/arch/mips/kernel/smp-cmp.c b/arch/mips/kernel/smp-cmp.c
index c2e5d74739b4..5969f1e9b62a 100644
--- a/arch/mips/kernel/smp-cmp.c
+++ b/arch/mips/kernel/smp-cmp.c
@@ -99,7 +99,9 @@ static void cmp_init_secondary(void)
 
 	c->core = (read_c0_ebase() >> 1) & 0x1ff;
 #if defined(CONFIG_MIPS_MT_SMP) || defined(CONFIG_MIPS_MT_SMTC)
-	c->vpe_id = (read_c0_tcbind() >> TCBIND_CURVPE_SHIFT) & TCBIND_CURVPE;
+	if (cpu_has_mipsmt)
+		c->vpe_id = (read_c0_tcbind() >> TCBIND_CURVPE_SHIFT) &
+			TCBIND_CURVPE;
 #endif
 #ifdef CONFIG_MIPS_MT_SMTC
 	c->tc_id  = (read_c0_tcbind() & TCBIND_CURTC) >> TCBIND_CURTC_SHIFT;
@@ -177,9 +179,16 @@ void __init cmp_smp_setup(void)
 	}
 
 	if (cpu_has_mipsmt) {
-		unsigned int nvpe, mvpconf0 = read_c0_mvpconf0();
+		unsigned int nvpe = 1;
+#ifdef CONFIG_MIPS_MT_SMP
+		unsigned int mvpconf0 = read_c0_mvpconf0();
+
+		nvpe = ((mvpconf0 & MVPCONF0_PVPE) >> MVPCONF0_PVPE_SHIFT) + 1;
+#elif defined(CONFIG_MIPS_MT_SMTC)
+		unsigned int mvpconf0 = read_c0_mvpconf0();
 
 		nvpe = ((mvpconf0 & MVPCONF0_PTC) >> MVPCONF0_PTC_SHIFT) + 1;
+#endif
 		smp_num_siblings = nvpe;
 	}
 	pr_info("Detected %i available secondary CPU(s)\n", ncpu);
diff --git a/arch/mips/kernel/time.c b/arch/mips/kernel/time.c
index 9d686bf97b0e..dcb8e5d3bb8a 100644
--- a/arch/mips/kernel/time.c
+++ b/arch/mips/kernel/time.c
@@ -24,6 +24,7 @@
 #include <linux/export.h>
 
 #include <asm/cpu-features.h>
+#include <asm/cpu-type.h>
 #include <asm/div64.h>
 #include <asm/smtc_ipi.h>
 #include <asm/time.h>
@@ -121,6 +122,14 @@ void __init time_init(void)
 {
 	plat_time_init();
 
-	if (!mips_clockevent_init() || !cpu_has_mfc0_count_bug())
+	/*
+	 * The use of the R4k timer as a clock event takes precedence;
+	 * if reading the Count register might interfere with the timer
+	 * interrupt, then we don't use the timer as a clock source.
+	 * We may still use the timer as a clock source though if the
+	 * timer interrupt isn't reliable; the interference doesn't
+	 * matter then, because we don't use the interrupt.
+	 */
+	if (mips_clockevent_init() != 0 || !cpu_has_mfc0_count_bug())
 		init_mips_clocksource();
 }
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index aec3408edd4b..524841f02803 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -39,6 +39,7 @@
 #include <asm/break.h>
 #include <asm/cop2.h>
 #include <asm/cpu.h>
+#include <asm/cpu-type.h>
 #include <asm/dsp.h>
 #include <asm/fpu.h>
 #include <asm/fpu_emulator.h>
@@ -622,7 +623,7 @@ static int simulate_rdhwr(struct pt_regs *regs, int rd, int rt)
 		regs->regs[rt] = read_c0_count();
 		return 0;
 	case 3:		/* Count register resolution */
-		switch (current_cpu_data.cputype) {
+		switch (current_cpu_type()) {
 		case CPU_20KC:
 		case CPU_25KF:
 			regs->regs[rt] = 1;
diff --git a/arch/mips/kernel/vmlinux.lds.S b/arch/mips/kernel/vmlinux.lds.S
index 05826d20a792..3b46f7ce9ca7 100644
--- a/arch/mips/kernel/vmlinux.lds.S
+++ b/arch/mips/kernel/vmlinux.lds.S
@@ -179,5 +179,6 @@ SECTIONS
 		*(.options)
 		*(.pdr)
 		*(.reginfo)
+		*(.eh_frame)
 	}
 }
diff --git a/arch/mips/kernel/vpe.c b/arch/mips/kernel/vpe.c
index 1765bab000a0..59b2b3cd7885 100644
--- a/arch/mips/kernel/vpe.c
+++ b/arch/mips/kernel/vpe.c
@@ -1335,8 +1335,9 @@ static ssize_t store_kill(struct device *dev, struct device_attribute *attr,
 
 	return len;
 }
+static DEVICE_ATTR(kill, S_IWUSR, NULL, store_kill);
 
-static ssize_t show_ntcs(struct device *cd, struct device_attribute *attr,
+static ssize_t ntcs_show(struct device *cd, struct device_attribute *attr,
 			 char *buf)
 {
 	struct vpe *vpe = get_vpe(tclimit);
@@ -1344,7 +1345,7 @@ static ssize_t show_ntcs(struct device *cd, struct device_attribute *attr,
 	return sprintf(buf, "%d\n", vpe->ntcs);
 }
 
-static ssize_t store_ntcs(struct device *dev, struct device_attribute *attr,
+static ssize_t ntcs_store(struct device *dev, struct device_attribute *attr,
 			  const char *buf, size_t len)
 {
 	struct vpe *vpe = get_vpe(tclimit);
@@ -1365,12 +1366,14 @@ static ssize_t store_ntcs(struct device *dev, struct device_attribute *attr,
 out_einval:
 	return -EINVAL;
 }
+static DEVICE_ATTR_RW(ntcs);
 
-static struct device_attribute vpe_class_attributes[] = {
-	__ATTR(kill, S_IWUSR, NULL, store_kill),
-	__ATTR(ntcs, S_IRUGO | S_IWUSR, show_ntcs, store_ntcs),
-	{}
+static struct attribute *vpe_attrs[] = {
+	&dev_attr_kill.attr,
+	&dev_attr_ntcs.attr,
+	NULL,
 };
+ATTRIBUTE_GROUPS(vpe);
 
 static void vpe_device_release(struct device *cd)
 {
@@ -1381,7 +1384,7 @@ struct class vpe_class = {
 	.name = "vpe",
 	.owner = THIS_MODULE,
 	.dev_release = vpe_device_release,
-	.dev_attrs = vpe_class_attributes,
+	.dev_groups = vpe_groups,
 };
 
 struct device vpe_device;
diff --git a/arch/mips/kvm/kvm_locore.S b/arch/mips/kvm/kvm_locore.S
index dca2aa665993..bbace092ad0a 100644
--- a/arch/mips/kvm/kvm_locore.S
+++ b/arch/mips/kvm/kvm_locore.S
@@ -1,13 +1,13 @@
 /*
-* This file is subject to the terms and conditions of the GNU General Public
-* License.  See the file "COPYING" in the main directory of this archive
-* for more details.
-*
-* Main entry point for the guest, exception handling.
-*
-* Copyright (C) 2012  MIPS Technologies, Inc.  All rights reserved.
-* Authors: Sanjay Lal <sanjayl@kymasys.com>
-*/
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Main entry point for the guest, exception handling.
+ *
+ * Copyright (C) 2012  MIPS Technologies, Inc.  All rights reserved.
+ * Authors: Sanjay Lal <sanjayl@kymasys.com>
+ */
 
 #include <asm/asm.h>
 #include <asm/asmmacro.h>
@@ -55,195 +55,193 @@
  * a0: run
  * a1: vcpu
  */
+	.set	noreorder
+	.set	noat
 
 FEXPORT(__kvm_mips_vcpu_run)
-    .set    push
-    .set    noreorder
-    .set    noat
-
-    /* k0/k1 not being used in host kernel context */
-	addiu  		k1,sp, -PT_SIZE
-    LONG_S	    $0, PT_R0(k1)
-    LONG_S     	$1, PT_R1(k1)
-    LONG_S     	$2, PT_R2(k1)
-    LONG_S     	$3, PT_R3(k1)
-
-    LONG_S     	$4, PT_R4(k1)
-    LONG_S     	$5, PT_R5(k1)
-    LONG_S     	$6, PT_R6(k1)
-    LONG_S     	$7, PT_R7(k1)
-
-    LONG_S     	$8,  PT_R8(k1)
-    LONG_S     	$9,  PT_R9(k1)
-    LONG_S     	$10, PT_R10(k1)
-    LONG_S     	$11, PT_R11(k1)
-    LONG_S     	$12, PT_R12(k1)
-    LONG_S     	$13, PT_R13(k1)
-    LONG_S     	$14, PT_R14(k1)
-    LONG_S     	$15, PT_R15(k1)
-    LONG_S     	$16, PT_R16(k1)
-    LONG_S     	$17, PT_R17(k1)
-
-    LONG_S     	$18, PT_R18(k1)
-    LONG_S     	$19, PT_R19(k1)
-    LONG_S     	$20, PT_R20(k1)
-    LONG_S     	$21, PT_R21(k1)
-    LONG_S     	$22, PT_R22(k1)
-    LONG_S     	$23, PT_R23(k1)
-    LONG_S     	$24, PT_R24(k1)
-    LONG_S     	$25, PT_R25(k1)
+	/* k0/k1 not being used in host kernel context */
+	INT_ADDIU k1, sp, -PT_SIZE
+	LONG_S	$0, PT_R0(k1)
+	LONG_S	$1, PT_R1(k1)
+	LONG_S	$2, PT_R2(k1)
+	LONG_S	$3, PT_R3(k1)
+
+	LONG_S	$4, PT_R4(k1)
+	LONG_S	$5, PT_R5(k1)
+	LONG_S	$6, PT_R6(k1)
+	LONG_S	$7, PT_R7(k1)
+
+	LONG_S	$8,  PT_R8(k1)
+	LONG_S	$9,  PT_R9(k1)
+	LONG_S	$10, PT_R10(k1)
+	LONG_S	$11, PT_R11(k1)
+	LONG_S	$12, PT_R12(k1)
+	LONG_S	$13, PT_R13(k1)
+	LONG_S	$14, PT_R14(k1)
+	LONG_S	$15, PT_R15(k1)
+	LONG_S	$16, PT_R16(k1)
+	LONG_S	$17, PT_R17(k1)
+
+	LONG_S	$18, PT_R18(k1)
+	LONG_S	$19, PT_R19(k1)
+	LONG_S	$20, PT_R20(k1)
+	LONG_S	$21, PT_R21(k1)
+	LONG_S	$22, PT_R22(k1)
+	LONG_S	$23, PT_R23(k1)
+	LONG_S	$24, PT_R24(k1)
+	LONG_S	$25, PT_R25(k1)
 
 	/* XXXKYMA k0/k1 not saved, not being used if we got here through an ioctl() */
 
-    LONG_S     	$28, PT_R28(k1)
-    LONG_S     	$29, PT_R29(k1)
-    LONG_S     	$30, PT_R30(k1)
-    LONG_S     	$31, PT_R31(k1)
+	LONG_S	$28, PT_R28(k1)
+	LONG_S	$29, PT_R29(k1)
+	LONG_S	$30, PT_R30(k1)
+	LONG_S	$31, PT_R31(k1)
 
-    /* Save hi/lo */
-	mflo		v0
-	LONG_S		v0, PT_LO(k1)
-	mfhi   		v1
-	LONG_S		v1, PT_HI(k1)
+	/* Save hi/lo */
+	mflo	v0
+	LONG_S	v0, PT_LO(k1)
+	mfhi	v1
+	LONG_S	v1, PT_HI(k1)
 
 	/* Save host status */
-	mfc0		v0, CP0_STATUS
-	LONG_S		v0, PT_STATUS(k1)
+	mfc0	v0, CP0_STATUS
+	LONG_S	v0, PT_STATUS(k1)
 
 	/* Save host ASID, shove it into the BVADDR location */
-	mfc0 		v1,CP0_ENTRYHI
-	andi		v1, 0xff
-	LONG_S		v1, PT_HOST_ASID(k1)
+	mfc0	v1, CP0_ENTRYHI
+	andi	v1, 0xff
+	LONG_S	v1, PT_HOST_ASID(k1)
 
-    /* Save DDATA_LO, will be used to store pointer to vcpu */
-    mfc0        v1, CP0_DDATA_LO
-    LONG_S      v1, PT_HOST_USERLOCAL(k1)
+	/* Save DDATA_LO, will be used to store pointer to vcpu */
+	mfc0	v1, CP0_DDATA_LO
+	LONG_S	v1, PT_HOST_USERLOCAL(k1)
 
-    /* DDATA_LO has pointer to vcpu */
-    mtc0        a1,CP0_DDATA_LO
+	/* DDATA_LO has pointer to vcpu */
+	mtc0	a1, CP0_DDATA_LO
 
-    /* Offset into vcpu->arch */
-	addiu		k1, a1, VCPU_HOST_ARCH
+	/* Offset into vcpu->arch */
+	INT_ADDIU k1, a1, VCPU_HOST_ARCH
 
-    /* Save the host stack to VCPU, used for exception processing when we exit from the Guest */
-    LONG_S      sp, VCPU_HOST_STACK(k1)
+	/*
+	 * Save the host stack to VCPU, used for exception processing
+	 * when we exit from the Guest
+	 */
+	LONG_S	sp, VCPU_HOST_STACK(k1)
 
-    /* Save the kernel gp as well */
-    LONG_S      gp, VCPU_HOST_GP(k1)
+	/* Save the kernel gp as well */
+	LONG_S	gp, VCPU_HOST_GP(k1)
 
 	/* Setup status register for running the guest in UM, interrupts are disabled */
-	li			k0,(ST0_EXL | KSU_USER| ST0_BEV)
-	mtc0		k0,CP0_STATUS
-    ehb
-
-    /* load up the new EBASE */
-    LONG_L      k0, VCPU_GUEST_EBASE(k1)
-    mtc0        k0,CP0_EBASE
-
-    /* Now that the new EBASE has been loaded, unset BEV, set interrupt mask as it was
-     * but make sure that timer interrupts are enabled
-     */
-    li          k0,(ST0_EXL | KSU_USER | ST0_IE)
-    andi        v0, v0, ST0_IM
-    or          k0, k0, v0
-    mtc0        k0,CP0_STATUS
-    ehb
+	li	k0, (ST0_EXL | KSU_USER | ST0_BEV)
+	mtc0	k0, CP0_STATUS
+	ehb
+
+	/* load up the new EBASE */
+	LONG_L	k0, VCPU_GUEST_EBASE(k1)
+	mtc0	k0, CP0_EBASE
+
+	/*
+	 * Now that the new EBASE has been loaded, unset BEV, set
+	 * interrupt mask as it was but make sure that timer interrupts
+	 * are enabled
+	 */
+	li	k0, (ST0_EXL | KSU_USER | ST0_IE)
+	andi	v0, v0, ST0_IM
+	or	k0, k0, v0
+	mtc0	k0, CP0_STATUS
+	ehb
 
 
 	/* Set Guest EPC */
-	LONG_L		t0, VCPU_PC(k1)
-	mtc0		t0, CP0_EPC
+	LONG_L	t0, VCPU_PC(k1)
+	mtc0	t0, CP0_EPC
 
 FEXPORT(__kvm_mips_load_asid)
-    /* Set the ASID for the Guest Kernel */
-    sll         t0, t0, 1                       /* with kseg0 @ 0x40000000, kernel */
-                                                /* addresses shift to 0x80000000 */
-    bltz        t0, 1f                          /* If kernel */
-	addiu       t1, k1, VCPU_GUEST_KERNEL_ASID  /* (BD)  */
-    addiu       t1, k1, VCPU_GUEST_USER_ASID    /* else user */
+	/* Set the ASID for the Guest Kernel */
+	INT_SLL	t0, t0, 1	/* with kseg0 @ 0x40000000, kernel */
+			        /* addresses shift to 0x80000000 */
+	bltz	t0, 1f		/* If kernel */
+	 INT_ADDIU t1, k1, VCPU_GUEST_KERNEL_ASID  /* (BD)  */
+	INT_ADDIU t1, k1, VCPU_GUEST_USER_ASID    /* else user */
 1:
-    /* t1: contains the base of the ASID array, need to get the cpu id  */
-    LONG_L      t2, TI_CPU($28)             /* smp_processor_id */
-    sll         t2, t2, 2                   /* x4 */
-    addu        t3, t1, t2
-    LONG_L      k0, (t3)
-    andi        k0, k0, 0xff
-	mtc0		k0,CP0_ENTRYHI
-    ehb
-
-    /* Disable RDHWR access */
-    mtc0    zero,  CP0_HWRENA
-
-    /* Now load up the Guest Context from VCPU */
-    LONG_L     	$1, VCPU_R1(k1)
-    LONG_L     	$2, VCPU_R2(k1)
-    LONG_L     	$3, VCPU_R3(k1)
-
-    LONG_L     	$4, VCPU_R4(k1)
-    LONG_L     	$5, VCPU_R5(k1)
-    LONG_L     	$6, VCPU_R6(k1)
-    LONG_L     	$7, VCPU_R7(k1)
-
-    LONG_L     	$8,  VCPU_R8(k1)
-    LONG_L     	$9,  VCPU_R9(k1)
-    LONG_L     	$10, VCPU_R10(k1)
-    LONG_L     	$11, VCPU_R11(k1)
-    LONG_L     	$12, VCPU_R12(k1)
-    LONG_L     	$13, VCPU_R13(k1)
-    LONG_L     	$14, VCPU_R14(k1)
-    LONG_L     	$15, VCPU_R15(k1)
-    LONG_L     	$16, VCPU_R16(k1)
-    LONG_L     	$17, VCPU_R17(k1)
-    LONG_L     	$18, VCPU_R18(k1)
-    LONG_L     	$19, VCPU_R19(k1)
-    LONG_L     	$20, VCPU_R20(k1)
-    LONG_L     	$21, VCPU_R21(k1)
-    LONG_L     	$22, VCPU_R22(k1)
-    LONG_L     	$23, VCPU_R23(k1)
-    LONG_L     	$24, VCPU_R24(k1)
-    LONG_L     	$25, VCPU_R25(k1)
-
-    /* k0/k1 loaded up later */
-
-    LONG_L     	$28, VCPU_R28(k1)
-    LONG_L     	$29, VCPU_R29(k1)
-    LONG_L     	$30, VCPU_R30(k1)
-    LONG_L     	$31, VCPU_R31(k1)
-
-    /* Restore hi/lo */
-	LONG_L		k0, VCPU_LO(k1)
-	mtlo		k0
-
-	LONG_L		k0, VCPU_HI(k1)
-	mthi   		k0
+	     /* t1: contains the base of the ASID array, need to get the cpu id  */
+	LONG_L	t2, TI_CPU($28)             /* smp_processor_id */
+	INT_SLL	t2, t2, 2                   /* x4 */
+	REG_ADDU t3, t1, t2
+	LONG_L	k0, (t3)
+	andi	k0, k0, 0xff
+	mtc0	k0, CP0_ENTRYHI
+	ehb
+
+	/* Disable RDHWR access */
+	mtc0	zero, CP0_HWRENA
+
+	/* Now load up the Guest Context from VCPU */
+	LONG_L	$1, VCPU_R1(k1)
+	LONG_L	$2, VCPU_R2(k1)
+	LONG_L	$3, VCPU_R3(k1)
+
+	LONG_L	$4, VCPU_R4(k1)
+	LONG_L	$5, VCPU_R5(k1)
+	LONG_L	$6, VCPU_R6(k1)
+	LONG_L	$7, VCPU_R7(k1)
+
+	LONG_L	$8, VCPU_R8(k1)
+	LONG_L	$9, VCPU_R9(k1)
+	LONG_L	$10, VCPU_R10(k1)
+	LONG_L	$11, VCPU_R11(k1)
+	LONG_L	$12, VCPU_R12(k1)
+	LONG_L	$13, VCPU_R13(k1)
+	LONG_L	$14, VCPU_R14(k1)
+	LONG_L	$15, VCPU_R15(k1)
+	LONG_L	$16, VCPU_R16(k1)
+	LONG_L	$17, VCPU_R17(k1)
+	LONG_L	$18, VCPU_R18(k1)
+	LONG_L	$19, VCPU_R19(k1)
+	LONG_L	$20, VCPU_R20(k1)
+	LONG_L	$21, VCPU_R21(k1)
+	LONG_L	$22, VCPU_R22(k1)
+	LONG_L	$23, VCPU_R23(k1)
+	LONG_L	$24, VCPU_R24(k1)
+	LONG_L	$25, VCPU_R25(k1)
+
+	/* k0/k1 loaded up later */
+
+	LONG_L	$28, VCPU_R28(k1)
+	LONG_L	$29, VCPU_R29(k1)
+	LONG_L	$30, VCPU_R30(k1)
+	LONG_L	$31, VCPU_R31(k1)
+
+	/* Restore hi/lo */
+	LONG_L	k0, VCPU_LO(k1)
+	mtlo	k0
+
+	LONG_L	k0, VCPU_HI(k1)
+	mthi	k0
 
 FEXPORT(__kvm_mips_load_k0k1)
 	/* Restore the guest's k0/k1 registers */
-    LONG_L     	k0, VCPU_R26(k1)
-    LONG_L     	k1, VCPU_R27(k1)
+	LONG_L	k0, VCPU_R26(k1)
+	LONG_L	k1, VCPU_R27(k1)
 
-    /* Jump to guest */
+	/* Jump to guest */
 	eret
-	.set	pop
 
 VECTOR(MIPSX(exception), unknown)
 /*
  * Find out what mode we came from and jump to the proper handler.
  */
-    .set    push
-	.set	noat
-    .set    noreorder
-    mtc0    k0, CP0_ERROREPC    #01: Save guest k0
-    ehb                         #02:
-
-    mfc0    k0, CP0_EBASE       #02: Get EBASE
-    srl     k0, k0, 10          #03: Get rid of CPUNum
-    sll     k0, k0, 10          #04
-    LONG_S  k1, 0x3000(k0)      #05: Save k1 @ offset 0x3000
-    addiu   k0, k0, 0x2000      #06: Exception handler is installed @ offset 0x2000
-	j	k0				        #07: jump to the function
-	nop				        	#08: branch delay slot
-	.set	push
+	mtc0	k0, CP0_ERROREPC	#01: Save guest k0
+	ehb				#02:
+
+	mfc0	k0, CP0_EBASE		#02: Get EBASE
+	INT_SRL	k0, k0, 10		#03: Get rid of CPUNum
+	INT_SLL	k0, k0, 10		#04
+	LONG_S	k1, 0x3000(k0)		#05: Save k1 @ offset 0x3000
+	INT_ADDIU k0, k0, 0x2000		#06: Exception handler is installed @ offset 0x2000
+	j	k0			#07: jump to the function
+	 nop				#08: branch delay slot
 VECTOR_END(MIPSX(exceptionEnd))
 .end MIPSX(exception)
 
@@ -253,329 +251,327 @@ VECTOR_END(MIPSX(exceptionEnd))
  *
  */
 NESTED (MIPSX(GuestException), CALLFRAME_SIZ, ra)
-    .set    push
-    .set    noat
-    .set    noreorder
-
-    /* Get the VCPU pointer from DDTATA_LO */
-    mfc0        k1, CP0_DDATA_LO
-	addiu		k1, k1, VCPU_HOST_ARCH
-
-    /* Start saving Guest context to VCPU */
-    LONG_S  $0, VCPU_R0(k1)
-    LONG_S  $1, VCPU_R1(k1)
-    LONG_S  $2, VCPU_R2(k1)
-    LONG_S  $3, VCPU_R3(k1)
-    LONG_S  $4, VCPU_R4(k1)
-    LONG_S  $5, VCPU_R5(k1)
-    LONG_S  $6, VCPU_R6(k1)
-    LONG_S  $7, VCPU_R7(k1)
-    LONG_S  $8, VCPU_R8(k1)
-    LONG_S  $9, VCPU_R9(k1)
-    LONG_S  $10, VCPU_R10(k1)
-    LONG_S  $11, VCPU_R11(k1)
-    LONG_S  $12, VCPU_R12(k1)
-    LONG_S  $13, VCPU_R13(k1)
-    LONG_S  $14, VCPU_R14(k1)
-    LONG_S  $15, VCPU_R15(k1)
-    LONG_S  $16, VCPU_R16(k1)
-    LONG_S  $17,VCPU_R17(k1)
-    LONG_S  $18, VCPU_R18(k1)
-    LONG_S  $19, VCPU_R19(k1)
-    LONG_S  $20, VCPU_R20(k1)
-    LONG_S  $21, VCPU_R21(k1)
-    LONG_S  $22, VCPU_R22(k1)
-    LONG_S  $23, VCPU_R23(k1)
-    LONG_S  $24, VCPU_R24(k1)
-    LONG_S  $25, VCPU_R25(k1)
-
-    /* Guest k0/k1 saved later */
-
-    LONG_S  $28, VCPU_R28(k1)
-    LONG_S  $29, VCPU_R29(k1)
-    LONG_S  $30, VCPU_R30(k1)
-    LONG_S  $31, VCPU_R31(k1)
-
-    /* We need to save hi/lo and restore them on
-     * the way out
-     */
-    mfhi    t0
-    LONG_S  t0, VCPU_HI(k1)
-
-    mflo    t0
-    LONG_S  t0, VCPU_LO(k1)
-
-    /* Finally save guest k0/k1 to VCPU */
-    mfc0    t0, CP0_ERROREPC
-    LONG_S  t0, VCPU_R26(k1)
-
-    /* Get GUEST k1 and save it in VCPU */
-    la      t1, ~0x2ff
-    mfc0    t0, CP0_EBASE
-    and     t0, t0, t1
-    LONG_L  t0, 0x3000(t0)
-    LONG_S  t0, VCPU_R27(k1)
-
-    /* Now that context has been saved, we can use other registers */
-
-    /* Restore vcpu */
-    mfc0        a1, CP0_DDATA_LO
-    move        s1, a1
-
-   /* Restore run (vcpu->run) */
-    LONG_L      a0, VCPU_RUN(a1)
-    /* Save pointer to run in s0, will be saved by the compiler */
-    move        s0, a0
-
-
-    /* Save Host level EPC, BadVaddr and Cause to VCPU, useful to process the exception */
-    mfc0    k0,CP0_EPC
-    LONG_S  k0, VCPU_PC(k1)
-
-    mfc0    k0, CP0_BADVADDR
-    LONG_S  k0, VCPU_HOST_CP0_BADVADDR(k1)
-
-    mfc0    k0, CP0_CAUSE
-    LONG_S  k0, VCPU_HOST_CP0_CAUSE(k1)
-
-    mfc0    k0, CP0_ENTRYHI
-    LONG_S  k0, VCPU_HOST_ENTRYHI(k1)
-
-    /* Now restore the host state just enough to run the handlers */
-
-    /* Swtich EBASE to the one used by Linux */
-    /* load up the host EBASE */
-    mfc0        v0, CP0_STATUS
-
-    .set at
-	or          k0, v0, ST0_BEV
-    .set noat
-
-    mtc0        k0, CP0_STATUS
-    ehb
-
-    LONG_L      k0, VCPU_HOST_EBASE(k1)
-    mtc0        k0,CP0_EBASE
-
-
-    /* Now that the new EBASE has been loaded, unset BEV and KSU_USER */
-    .set at
-	and         v0, v0, ~(ST0_EXL | KSU_USER | ST0_IE)
-    or          v0, v0, ST0_CU0
-    .set noat
-    mtc0        v0, CP0_STATUS
-    ehb
-
-    /* Load up host GP */
-    LONG_L  gp, VCPU_HOST_GP(k1)
-
-    /* Need a stack before we can jump to "C" */
-    LONG_L  sp, VCPU_HOST_STACK(k1)
-
-    /* Saved host state */
-    addiu   sp,sp, -PT_SIZE
+	/* Get the VCPU pointer from DDTATA_LO */
+	mfc0	k1, CP0_DDATA_LO
+	INT_ADDIU k1, k1, VCPU_HOST_ARCH
+
+	/* Start saving Guest context to VCPU */
+	LONG_S	$0, VCPU_R0(k1)
+	LONG_S	$1, VCPU_R1(k1)
+	LONG_S	$2, VCPU_R2(k1)
+	LONG_S	$3, VCPU_R3(k1)
+	LONG_S	$4, VCPU_R4(k1)
+	LONG_S	$5, VCPU_R5(k1)
+	LONG_S	$6, VCPU_R6(k1)
+	LONG_S	$7, VCPU_R7(k1)
+	LONG_S	$8, VCPU_R8(k1)
+	LONG_S	$9, VCPU_R9(k1)
+	LONG_S	$10, VCPU_R10(k1)
+	LONG_S	$11, VCPU_R11(k1)
+	LONG_S	$12, VCPU_R12(k1)
+	LONG_S	$13, VCPU_R13(k1)
+	LONG_S	$14, VCPU_R14(k1)
+	LONG_S	$15, VCPU_R15(k1)
+	LONG_S	$16, VCPU_R16(k1)
+	LONG_S	$17, VCPU_R17(k1)
+	LONG_S	$18, VCPU_R18(k1)
+	LONG_S	$19, VCPU_R19(k1)
+	LONG_S	$20, VCPU_R20(k1)
+	LONG_S	$21, VCPU_R21(k1)
+	LONG_S	$22, VCPU_R22(k1)
+	LONG_S	$23, VCPU_R23(k1)
+	LONG_S	$24, VCPU_R24(k1)
+	LONG_S	$25, VCPU_R25(k1)
+
+	/* Guest k0/k1 saved later */
+
+	LONG_S	$28, VCPU_R28(k1)
+	LONG_S	$29, VCPU_R29(k1)
+	LONG_S	$30, VCPU_R30(k1)
+	LONG_S	$31, VCPU_R31(k1)
+
+	/* We need to save hi/lo and restore them on
+	 * the way out
+	 */
+	mfhi	t0
+	LONG_S	t0, VCPU_HI(k1)
+
+	mflo	t0
+	LONG_S	t0, VCPU_LO(k1)
+
+	/* Finally save guest k0/k1 to VCPU */
+	mfc0	t0, CP0_ERROREPC
+	LONG_S	t0, VCPU_R26(k1)
+
+	/* Get GUEST k1 and save it in VCPU */
+	PTR_LI	t1, ~0x2ff
+	mfc0	t0, CP0_EBASE
+	and	t0, t0, t1
+	LONG_L	t0, 0x3000(t0)
+	LONG_S	t0, VCPU_R27(k1)
+
+	/* Now that context has been saved, we can use other registers */
+
+	/* Restore vcpu */
+	mfc0	a1, CP0_DDATA_LO
+	move	s1, a1
+
+	/* Restore run (vcpu->run) */
+	LONG_L	a0, VCPU_RUN(a1)
+	/* Save pointer to run in s0, will be saved by the compiler */
+	move	s0, a0
+
+	/* Save Host level EPC, BadVaddr and Cause to VCPU, useful to
+	 * process the exception */
+	mfc0	k0,CP0_EPC
+	LONG_S	k0, VCPU_PC(k1)
+
+	mfc0	k0, CP0_BADVADDR
+	LONG_S	k0, VCPU_HOST_CP0_BADVADDR(k1)
+
+	mfc0	k0, CP0_CAUSE
+	LONG_S	k0, VCPU_HOST_CP0_CAUSE(k1)
+
+	mfc0	k0, CP0_ENTRYHI
+	LONG_S	k0, VCPU_HOST_ENTRYHI(k1)
+
+	/* Now restore the host state just enough to run the handlers */
+
+	/* Swtich EBASE to the one used by Linux */
+	/* load up the host EBASE */
+	mfc0	v0, CP0_STATUS
+
+	.set	at
+	or	k0, v0, ST0_BEV
+	.set	noat
+
+	mtc0	k0, CP0_STATUS
+	ehb
+
+	LONG_L	k0, VCPU_HOST_EBASE(k1)
+	mtc0	k0,CP0_EBASE
+
 
-    /* XXXKYMA do we need to load the host ASID, maybe not because the
-     * kernel entries are marked GLOBAL, need to verify
-     */
+	/* Now that the new EBASE has been loaded, unset BEV and KSU_USER */
+	.set	at
+	and	v0, v0, ~(ST0_EXL | KSU_USER | ST0_IE)
+	or	v0, v0, ST0_CU0
+	.set	noat
+	mtc0	v0, CP0_STATUS
+	ehb
+
+	/* Load up host GP */
+	LONG_L	gp, VCPU_HOST_GP(k1)
+
+	/* Need a stack before we can jump to "C" */
+	LONG_L	sp, VCPU_HOST_STACK(k1)
+
+	/* Saved host state */
+	INT_ADDIU sp, sp, -PT_SIZE
 
-    /* Restore host DDATA_LO */
-    LONG_L      k0, PT_HOST_USERLOCAL(sp)
-    mtc0        k0, CP0_DDATA_LO
+	/* XXXKYMA do we need to load the host ASID, maybe not because the
+	 * kernel entries are marked GLOBAL, need to verify
+	 */
 
-    /* Restore RDHWR access */
-    la      k0, 0x2000000F
-    mtc0    k0,  CP0_HWRENA
+	/* Restore host DDATA_LO */
+	LONG_L	k0, PT_HOST_USERLOCAL(sp)
+	mtc0	k0, CP0_DDATA_LO
 
-    /* Jump to handler */
+	/* Restore RDHWR access */
+	PTR_LI	k0, 0x2000000F
+	mtc0	k0, CP0_HWRENA
+
+	/* Jump to handler */
 FEXPORT(__kvm_mips_jump_to_handler)
-    /* XXXKYMA: not sure if this is safe, how large is the stack?? */
-    /* Now jump to the kvm_mips_handle_exit() to see if we can deal with this in the kernel */
-    la          t9,kvm_mips_handle_exit
-    jalr.hb     t9
-    addiu       sp,sp, -CALLFRAME_SIZ           /* BD Slot */
-
-    /* Return from handler Make sure interrupts are disabled */
-    di
-    ehb
-
-    /* XXXKYMA: k0/k1 could have been blown away if we processed an exception
-     * while we were handling the exception from the guest, reload k1
-     */
-    move        k1, s1
-	addiu		k1, k1, VCPU_HOST_ARCH
-
-    /* Check return value, should tell us if we are returning to the host (handle I/O etc)
-     * or resuming the guest
-     */
-    andi        t0, v0, RESUME_HOST
-    bnez        t0, __kvm_mips_return_to_host
-    nop
+	/* XXXKYMA: not sure if this is safe, how large is the stack??
+	 * Now jump to the kvm_mips_handle_exit() to see if we can deal
+	 * with this in the kernel */
+	PTR_LA	t9, kvm_mips_handle_exit
+	jalr.hb	t9
+	 INT_ADDIU sp, sp, -CALLFRAME_SIZ           /* BD Slot */
+
+	/* Return from handler Make sure interrupts are disabled */
+	di
+	ehb
+
+	/* XXXKYMA: k0/k1 could have been blown away if we processed
+	 * an exception while we were handling the exception from the
+	 * guest, reload k1
+	 */
+
+	move	k1, s1
+	INT_ADDIU k1, k1, VCPU_HOST_ARCH
+
+	/* Check return value, should tell us if we are returning to the
+	 * host (handle I/O etc)or resuming the guest
+	 */
+	andi	t0, v0, RESUME_HOST
+	bnez	t0, __kvm_mips_return_to_host
+	 nop
 
 __kvm_mips_return_to_guest:
-    /* Put the saved pointer to vcpu (s1) back into the DDATA_LO Register */
-    mtc0        s1, CP0_DDATA_LO
-
-    /* Load up the Guest EBASE to minimize the window where BEV is set */
-    LONG_L      t0, VCPU_GUEST_EBASE(k1)
-
-    /* Switch EBASE back to the one used by KVM */
-    mfc0        v1, CP0_STATUS
-    .set at
-	or          k0, v1, ST0_BEV
-    .set noat
-    mtc0        k0, CP0_STATUS
-    ehb
-    mtc0        t0,CP0_EBASE
-
-    /* Setup status register for running guest in UM */
-    .set at
-    or     v1, v1, (ST0_EXL | KSU_USER | ST0_IE)
-    and     v1, v1, ~ST0_CU0
-    .set noat
-    mtc0    v1, CP0_STATUS
-    ehb
+	/* Put the saved pointer to vcpu (s1) back into the DDATA_LO Register */
+	mtc0	s1, CP0_DDATA_LO
 
+	/* Load up the Guest EBASE to minimize the window where BEV is set */
+	LONG_L	t0, VCPU_GUEST_EBASE(k1)
+
+	/* Switch EBASE back to the one used by KVM */
+	mfc0	v1, CP0_STATUS
+	.set	at
+	or	k0, v1, ST0_BEV
+	.set	noat
+	mtc0	k0, CP0_STATUS
+	ehb
+	mtc0	t0, CP0_EBASE
+
+	/* Setup status register for running guest in UM */
+	.set	at
+	or	v1, v1, (ST0_EXL | KSU_USER | ST0_IE)
+	and	v1, v1, ~ST0_CU0
+	.set	noat
+	mtc0	v1, CP0_STATUS
+	ehb
 
 	/* Set Guest EPC */
-	LONG_L		t0, VCPU_PC(k1)
-	mtc0		t0, CP0_EPC
-
-    /* Set the ASID for the Guest Kernel */
-    sll         t0, t0, 1                       /* with kseg0 @ 0x40000000, kernel */
-                                                /* addresses shift to 0x80000000 */
-    bltz        t0, 1f                          /* If kernel */
-	addiu       t1, k1, VCPU_GUEST_KERNEL_ASID  /* (BD)  */
-    addiu       t1, k1, VCPU_GUEST_USER_ASID    /* else user */
+	LONG_L	t0, VCPU_PC(k1)
+	mtc0	t0, CP0_EPC
+
+	/* Set the ASID for the Guest Kernel */
+	INT_SLL	t0, t0, 1	/* with kseg0 @ 0x40000000, kernel */
+				/* addresses shift to 0x80000000 */
+	bltz	t0, 1f		/* If kernel */
+	 INT_ADDIU t1, k1, VCPU_GUEST_KERNEL_ASID  /* (BD)  */
+	INT_ADDIU t1, k1, VCPU_GUEST_USER_ASID    /* else user */
 1:
-    /* t1: contains the base of the ASID array, need to get the cpu id  */
-    LONG_L      t2, TI_CPU($28)             /* smp_processor_id */
-    sll         t2, t2, 2                   /* x4 */
-    addu        t3, t1, t2
-    LONG_L      k0, (t3)
-    andi        k0, k0, 0xff
-	mtc0		k0,CP0_ENTRYHI
-    ehb
-
-    /* Disable RDHWR access */
-    mtc0    zero,  CP0_HWRENA
-
-    /* load the guest context from VCPU and return */
-    LONG_L  $0, VCPU_R0(k1)
-    LONG_L  $1, VCPU_R1(k1)
-    LONG_L  $2, VCPU_R2(k1)
-    LONG_L  $3, VCPU_R3(k1)
-    LONG_L  $4, VCPU_R4(k1)
-    LONG_L  $5, VCPU_R5(k1)
-    LONG_L  $6, VCPU_R6(k1)
-    LONG_L  $7, VCPU_R7(k1)
-    LONG_L  $8, VCPU_R8(k1)
-    LONG_L  $9, VCPU_R9(k1)
-    LONG_L  $10, VCPU_R10(k1)
-    LONG_L  $11, VCPU_R11(k1)
-    LONG_L  $12, VCPU_R12(k1)
-    LONG_L  $13, VCPU_R13(k1)
-    LONG_L  $14, VCPU_R14(k1)
-    LONG_L  $15, VCPU_R15(k1)
-    LONG_L  $16, VCPU_R16(k1)
-    LONG_L  $17, VCPU_R17(k1)
-    LONG_L  $18, VCPU_R18(k1)
-    LONG_L  $19, VCPU_R19(k1)
-    LONG_L  $20, VCPU_R20(k1)
-    LONG_L  $21, VCPU_R21(k1)
-    LONG_L  $22, VCPU_R22(k1)
-    LONG_L  $23, VCPU_R23(k1)
-    LONG_L  $24, VCPU_R24(k1)
-    LONG_L  $25, VCPU_R25(k1)
-
-    /* $/k1 loaded later */
-    LONG_L  $28, VCPU_R28(k1)
-    LONG_L  $29, VCPU_R29(k1)
-    LONG_L  $30, VCPU_R30(k1)
-    LONG_L  $31, VCPU_R31(k1)
+	/* t1: contains the base of the ASID array, need to get the cpu id  */
+	LONG_L	t2, TI_CPU($28)		/* smp_processor_id */
+	INT_SLL	t2, t2, 2		/* x4 */
+	REG_ADDU t3, t1, t2
+	LONG_L	k0, (t3)
+	andi	k0, k0, 0xff
+	mtc0	k0,CP0_ENTRYHI
+	ehb
+
+	/* Disable RDHWR access */
+	mtc0    zero,  CP0_HWRENA
+
+	/* load the guest context from VCPU and return */
+	LONG_L	$0, VCPU_R0(k1)
+	LONG_L	$1, VCPU_R1(k1)
+	LONG_L	$2, VCPU_R2(k1)
+	LONG_L	$3, VCPU_R3(k1)
+	LONG_L	$4, VCPU_R4(k1)
+	LONG_L	$5, VCPU_R5(k1)
+	LONG_L	$6, VCPU_R6(k1)
+	LONG_L	$7, VCPU_R7(k1)
+	LONG_L	$8, VCPU_R8(k1)
+	LONG_L	$9, VCPU_R9(k1)
+	LONG_L	$10, VCPU_R10(k1)
+	LONG_L	$11, VCPU_R11(k1)
+	LONG_L	$12, VCPU_R12(k1)
+	LONG_L	$13, VCPU_R13(k1)
+	LONG_L	$14, VCPU_R14(k1)
+	LONG_L	$15, VCPU_R15(k1)
+	LONG_L	$16, VCPU_R16(k1)
+	LONG_L	$17, VCPU_R17(k1)
+	LONG_L	$18, VCPU_R18(k1)
+	LONG_L	$19, VCPU_R19(k1)
+	LONG_L	$20, VCPU_R20(k1)
+	LONG_L	$21, VCPU_R21(k1)
+	LONG_L	$22, VCPU_R22(k1)
+	LONG_L	$23, VCPU_R23(k1)
+	LONG_L	$24, VCPU_R24(k1)
+	LONG_L	$25, VCPU_R25(k1)
+
+	/* $/k1 loaded later */
+	LONG_L	$28, VCPU_R28(k1)
+	LONG_L	$29, VCPU_R29(k1)
+	LONG_L	$30, VCPU_R30(k1)
+	LONG_L	$31, VCPU_R31(k1)
 
 FEXPORT(__kvm_mips_skip_guest_restore)
-    LONG_L  k0, VCPU_HI(k1)
-    mthi    k0
+	LONG_L	k0, VCPU_HI(k1)
+	mthi	k0
 
-    LONG_L  k0, VCPU_LO(k1)
-    mtlo    k0
+	LONG_L	k0, VCPU_LO(k1)
+	mtlo	k0
 
-    LONG_L  k0, VCPU_R26(k1)
-    LONG_L  k1, VCPU_R27(k1)
+	LONG_L	k0, VCPU_R26(k1)
+	LONG_L	k1, VCPU_R27(k1)
 
-    eret
+	eret
 
 __kvm_mips_return_to_host:
-    /* EBASE is already pointing to Linux */
-    LONG_L  k1, VCPU_HOST_STACK(k1)
-	addiu  	k1,k1, -PT_SIZE
-
-    /* Restore host DDATA_LO */
-    LONG_L      k0, PT_HOST_USERLOCAL(k1)
-    mtc0        k0, CP0_DDATA_LO
-
-    /* Restore host ASID */
-    LONG_L      k0, PT_HOST_ASID(sp)
-    andi        k0, 0xff
-    mtc0        k0,CP0_ENTRYHI
-    ehb
-
-    /* Load context saved on the host stack */
-    LONG_L  $0, PT_R0(k1)
-    LONG_L  $1, PT_R1(k1)
-
-    /* r2/v0 is the return code, shift it down by 2 (arithmetic) to recover the err code  */
-    sra     k0, v0, 2
-    move    $2, k0
-
-    LONG_L  $3, PT_R3(k1)
-    LONG_L  $4, PT_R4(k1)
-    LONG_L  $5, PT_R5(k1)
-    LONG_L  $6, PT_R6(k1)
-    LONG_L  $7, PT_R7(k1)
-    LONG_L  $8, PT_R8(k1)
-    LONG_L  $9, PT_R9(k1)
-    LONG_L  $10, PT_R10(k1)
-    LONG_L  $11, PT_R11(k1)
-    LONG_L  $12, PT_R12(k1)
-    LONG_L  $13, PT_R13(k1)
-    LONG_L  $14, PT_R14(k1)
-    LONG_L  $15, PT_R15(k1)
-    LONG_L  $16, PT_R16(k1)
-    LONG_L  $17, PT_R17(k1)
-    LONG_L  $18, PT_R18(k1)
-    LONG_L  $19, PT_R19(k1)
-    LONG_L  $20, PT_R20(k1)
-    LONG_L  $21, PT_R21(k1)
-    LONG_L  $22, PT_R22(k1)
-    LONG_L  $23, PT_R23(k1)
-    LONG_L  $24, PT_R24(k1)
-    LONG_L  $25, PT_R25(k1)
-
-    /* Host k0/k1 were not saved */
-
-    LONG_L  $28, PT_R28(k1)
-    LONG_L  $29, PT_R29(k1)
-    LONG_L  $30, PT_R30(k1)
-
-    LONG_L  k0, PT_HI(k1)
-    mthi    k0
-
-    LONG_L  k0, PT_LO(k1)
-    mtlo    k0
-
-    /* Restore RDHWR access */
-    la      k0, 0x2000000F
-    mtc0    k0,  CP0_HWRENA
-
-
-    /* Restore RA, which is the address we will return to */
-    LONG_L  ra, PT_R31(k1)
-    j       ra
-    nop
-
-    .set    pop
+	/* EBASE is already pointing to Linux */
+	LONG_L	k1, VCPU_HOST_STACK(k1)
+	INT_ADDIU k1,k1, -PT_SIZE
+
+	/* Restore host DDATA_LO */
+	LONG_L	k0, PT_HOST_USERLOCAL(k1)
+	mtc0	k0, CP0_DDATA_LO
+
+	/* Restore host ASID */
+	LONG_L	k0, PT_HOST_ASID(sp)
+	andi	k0, 0xff
+	mtc0	k0,CP0_ENTRYHI
+	ehb
+
+	/* Load context saved on the host stack */
+	LONG_L	$0, PT_R0(k1)
+	LONG_L	$1, PT_R1(k1)
+
+	/* r2/v0 is the return code, shift it down by 2 (arithmetic)
+	 * to recover the err code  */
+	INT_SRA	k0, v0, 2
+	move	$2, k0
+
+	LONG_L	$3, PT_R3(k1)
+	LONG_L	$4, PT_R4(k1)
+	LONG_L	$5, PT_R5(k1)
+	LONG_L	$6, PT_R6(k1)
+	LONG_L	$7, PT_R7(k1)
+	LONG_L	$8, PT_R8(k1)
+	LONG_L	$9, PT_R9(k1)
+	LONG_L	$10, PT_R10(k1)
+	LONG_L	$11, PT_R11(k1)
+	LONG_L	$12, PT_R12(k1)
+	LONG_L	$13, PT_R13(k1)
+	LONG_L	$14, PT_R14(k1)
+	LONG_L	$15, PT_R15(k1)
+	LONG_L	$16, PT_R16(k1)
+	LONG_L	$17, PT_R17(k1)
+	LONG_L	$18, PT_R18(k1)
+	LONG_L	$19, PT_R19(k1)
+	LONG_L	$20, PT_R20(k1)
+	LONG_L	$21, PT_R21(k1)
+	LONG_L	$22, PT_R22(k1)
+	LONG_L	$23, PT_R23(k1)
+	LONG_L	$24, PT_R24(k1)
+	LONG_L	$25, PT_R25(k1)
+
+	/* Host k0/k1 were not saved */
+
+	LONG_L	$28, PT_R28(k1)
+	LONG_L	$29, PT_R29(k1)
+	LONG_L	$30, PT_R30(k1)
+
+	LONG_L	k0, PT_HI(k1)
+	mthi	k0
+
+	LONG_L	k0, PT_LO(k1)
+	mtlo	k0
+
+	/* Restore RDHWR access */
+	PTR_LI	k0, 0x2000000F
+	mtc0	k0,  CP0_HWRENA
+
+
+	/* Restore RA, which is the address we will return to */
+	LONG_L  ra, PT_R31(k1)
+	j       ra
+	 nop
+
 VECTOR_END(MIPSX(GuestExceptionEnd))
 .end MIPSX(GuestException)
 
@@ -627,24 +623,23 @@ MIPSX(exceptions):
 
 #define HW_SYNCI_Step       $1
 LEAF(MIPSX(SyncICache))
-    .set    push
+	.set	push
 	.set	mips32r2
-    beq     a1, zero, 20f
-    nop
-    addu    a1, a0, a1
-    rdhwr   v0, HW_SYNCI_Step
-    beq     v0, zero, 20f
-    nop
-
+	beq	a1, zero, 20f
+	 nop
+	REG_ADDU a1, a0, a1
+	rdhwr	v0, HW_SYNCI_Step
+	beq	v0, zero, 20f
+	 nop
 10:
-    synci   0(a0)
-    addu    a0, a0, v0
-    sltu    v1, a0, a1
-    bne     v1, zero, 10b
-    nop
-    sync
+	synci	0(a0)
+	REG_ADDU a0, a0, v0
+	sltu	v1, a0, a1
+	bne	v1, zero, 10b
+	 nop
+	sync
 20:
-    jr.hb   ra
-    nop
-    .set pop
+	jr.hb	ra
+	 nop
+	.set	pop
 END(MIPSX(SyncICache))
diff --git a/arch/mips/kvm/kvm_mips.c b/arch/mips/kvm/kvm_mips.c
index dd203e59e6fd..a7b044536de4 100644
--- a/arch/mips/kvm/kvm_mips.c
+++ b/arch/mips/kvm/kvm_mips.c
@@ -208,6 +208,10 @@ int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages)
 	return 0;
 }
 
+void kvm_arch_memslots_updated(struct kvm *kvm)
+{
+}
+
 int kvm_arch_prepare_memory_region(struct kvm *kvm,
                                 struct kvm_memory_slot *memslot,
                                 struct kvm_userspace_memory_region *mem,
diff --git a/arch/mips/lantiq/falcon/sysctrl.c b/arch/mips/lantiq/falcon/sysctrl.c
index ff4894a833ee..8f1866d8124d 100644
--- a/arch/mips/lantiq/falcon/sysctrl.c
+++ b/arch/mips/lantiq/falcon/sysctrl.c
@@ -48,6 +48,7 @@
 #define CPU0CC_CPUDIV		0x0001
 
 /* Activation Status Register */
+#define ACTS_ASC0_ACT	0x00001000
 #define ACTS_ASC1_ACT	0x00000800
 #define ACTS_I2C_ACT	0x00004000
 #define ACTS_P0		0x00010000
@@ -108,6 +109,7 @@ static void sysctl_deactivate(struct clk *clk)
 static int sysctl_clken(struct clk *clk)
 {
 	sysctl_w32(clk->module, clk->bits, SYSCTL_CLKEN);
+	sysctl_w32(clk->module, clk->bits, SYSCTL_ACT);
 	sysctl_wait(clk, clk->bits, SYSCTL_CLKS);
 	return 0;
 }
@@ -256,6 +258,7 @@ void __init ltq_soc_init(void)
 	clkdev_add_sys("1e800400.pad", SYSCTL_SYS1, ACTS_PADCTRL1);
 	clkdev_add_sys("1e800500.pad", SYSCTL_SYS1, ACTS_PADCTRL3);
 	clkdev_add_sys("1e800600.pad", SYSCTL_SYS1, ACTS_PADCTRL4);
-	clkdev_add_sys("1e100C00.serial", SYSCTL_SYS1, ACTS_ASC1_ACT);
+	clkdev_add_sys("1e100b00.serial", SYSCTL_SYS1, ACTS_ASC1_ACT);
+	clkdev_add_sys("1e100c00.serial", SYSCTL_SYS1, ACTS_ASC0_ACT);
 	clkdev_add_sys("1e200000.i2c", SYSCTL_SYS1, ACTS_I2C_ACT);
 }
diff --git a/arch/mips/lantiq/xway/Makefile b/arch/mips/lantiq/xway/Makefile
index 7a13660d630d..087497d97357 100644
--- a/arch/mips/lantiq/xway/Makefile
+++ b/arch/mips/lantiq/xway/Makefile
@@ -1,3 +1,3 @@
-obj-y := prom.o sysctrl.o clk.o reset.o dma.o gptu.o
+obj-y := prom.o sysctrl.o clk.o reset.o dma.o gptu.o dcdc.o
 
 obj-$(CONFIG_XRX200_PHY_FW) += xrx200_phy_fw.o
diff --git a/arch/mips/lantiq/xway/dcdc.c b/arch/mips/lantiq/xway/dcdc.c
new file mode 100644
index 000000000000..7688ac0f06d0
--- /dev/null
+++ b/arch/mips/lantiq/xway/dcdc.c
@@ -0,0 +1,63 @@
+/*
+ *  This program is free software; you can redistribute it and/or modify it
+ *  under the terms of the GNU General Public License version 2 as published
+ *  by the Free Software Foundation.
+ *
+ *  Copyright (C) 2012 John Crispin <blogic@openwrt.org>
+ *  Copyright (C) 2010 Sameer Ahmad, Lantiq GmbH
+ */
+
+#include <linux/ioport.h>
+#include <linux/of_platform.h>
+
+#include <lantiq_soc.h>
+
+/* Bias and regulator Setup Register */
+#define DCDC_BIAS_VREG0	0xa
+/* Bias and regulator Setup Register */
+#define DCDC_BIAS_VREG1	0xb
+
+#define dcdc_w8(x, y)	ltq_w8((x), dcdc_membase + (y))
+#define dcdc_r8(x)	ltq_r8(dcdc_membase + (x))
+
+static void __iomem *dcdc_membase;
+
+static int dcdc_probe(struct platform_device *pdev)
+{
+	struct resource *res;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	dcdc_membase = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(dcdc_membase))
+		return PTR_ERR(dcdc_membase);
+
+	dev_info(&pdev->dev, "Core Voltage : %d mV\n",
+		dcdc_r8(DCDC_BIAS_VREG1) * 8);
+
+	return 0;
+}
+
+static const struct of_device_id dcdc_match[] = {
+	{ .compatible = "lantiq,dcdc-xrx200" },
+	{},
+};
+
+static struct platform_driver dcdc_driver = {
+	.probe = dcdc_probe,
+	.driver = {
+		.name = "dcdc-xrx200",
+		.owner = THIS_MODULE,
+		.of_match_table = dcdc_match,
+	},
+};
+
+int __init dcdc_init(void)
+{
+	int ret = platform_driver_register(&dcdc_driver);
+
+	if (ret)
+		pr_info("dcdc: Error registering platform driver\n");
+	return ret;
+}
+
+arch_initcall(dcdc_init);
diff --git a/arch/mips/lasat/image/Makefile b/arch/mips/lasat/image/Makefile
index dfb509d21d8e..fd32075679c6 100644
--- a/arch/mips/lasat/image/Makefile
+++ b/arch/mips/lasat/image/Makefile
@@ -13,13 +13,11 @@ endif
 MKLASATIMG = mklasatimg
 MKLASATIMG_ARCH = mq2,mqpro,sp100,sp200
 KERNEL_IMAGE = vmlinux
-KERNEL_START = $(shell $(NM) $(KERNEL_IMAGE) | grep " _text" | cut -f1 -d\ )
-KERNEL_ENTRY = $(shell $(NM) $(KERNEL_IMAGE) | grep kernel_entry | cut -f1 -d\ )
 
 LDSCRIPT= -L$(srctree)/$(src) -Tromscript.normal
 
-HEAD_DEFINES := -D_kernel_start=0x$(KERNEL_START) \
-		-D_kernel_entry=0x$(KERNEL_ENTRY) \
+HEAD_DEFINES := -D_kernel_start=$(VMLINUX_LOAD_ADDRESS) \
+		-D_kernel_entry=$(VMLINUX_ENTRY_ADDRESS) \
 		-D VERSION="\"$(Version)\"" \
 		-D TIMESTAMP=$(shell date +%s)
 
diff --git a/arch/mips/loongson/common/Makefile b/arch/mips/loongson/common/Makefile
index 4c57b3e5743f..9e4484ccbb03 100644
--- a/arch/mips/loongson/common/Makefile
+++ b/arch/mips/loongson/common/Makefile
@@ -3,8 +3,9 @@
 #
 
 obj-y += setup.o init.o cmdline.o env.o time.o reset.o irq.o \
-    pci.o bonito-irq.o mem.o machtype.o platform.o
+    bonito-irq.o mem.o machtype.o platform.o
 obj-$(CONFIG_GPIOLIB) += gpio.o
+obj-$(CONFIG_PCI) += pci.o
 
 #
 # Serial port support
diff --git a/arch/mips/math-emu/cp1emu.c b/arch/mips/math-emu/cp1emu.c
index 46048d24328c..efe008846ed0 100644
--- a/arch/mips/math-emu/cp1emu.c
+++ b/arch/mips/math-emu/cp1emu.c
@@ -436,7 +436,6 @@ static int microMIPS32_to_MIPS32(union mips_instruction *insn_ptr)
 				break;
 			default:
 				return SIGILL;
-				break;
 			}
 			break;
 		case mm_32f_74_op:	/* c.cond.fmt */
@@ -451,12 +450,10 @@ static int microMIPS32_to_MIPS32(union mips_instruction *insn_ptr)
 			break;
 		default:
 			return SIGILL;
-			break;
 		}
 		break;
 	default:
 		return SIGILL;
-		break;
 	}
 
 	*insn_ptr = mips32_insn;
@@ -491,7 +488,6 @@ int mm_isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn,
 						dec_insn.next_pc_inc;
 				*contpc = regs->regs[insn.mm_i_format.rs];
 				return 1;
-				break;
 			}
 		}
 		break;
@@ -513,7 +509,6 @@ int mm_isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn,
 					dec_insn.pc_inc +
 					dec_insn.next_pc_inc;
 			return 1;
-			break;
 		case mm_bgezals_op:
 		case mm_bgezal_op:
 			regs->regs[31] = regs->cp0_epc +
@@ -530,7 +525,6 @@ int mm_isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn,
 					dec_insn.pc_inc +
 					dec_insn.next_pc_inc;
 			return 1;
-			break;
 		case mm_blez_op:
 			if ((long)regs->regs[insn.mm_i_format.rs] <= 0)
 				*contpc = regs->cp0_epc +
@@ -541,7 +535,6 @@ int mm_isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn,
 					dec_insn.pc_inc +
 					dec_insn.next_pc_inc;
 			return 1;
-			break;
 		case mm_bgtz_op:
 			if ((long)regs->regs[insn.mm_i_format.rs] <= 0)
 				*contpc = regs->cp0_epc +
@@ -552,7 +545,6 @@ int mm_isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn,
 					dec_insn.pc_inc +
 					dec_insn.next_pc_inc;
 			return 1;
-			break;
 		case mm_bc2f_op:
 		case mm_bc1f_op:
 			bc_false = 1;
@@ -580,7 +572,6 @@ int mm_isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn,
 				*contpc = regs->cp0_epc +
 					dec_insn.pc_inc + dec_insn.next_pc_inc;
 			return 1;
-			break;
 		}
 		break;
 	case mm_pool16c_op:
@@ -593,7 +584,6 @@ int mm_isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn,
 		case mm_jr16_op:
 			*contpc = regs->regs[insn.mm_i_format.rs];
 			return 1;
-			break;
 		}
 		break;
 	case mm_beqz16_op:
@@ -605,7 +595,6 @@ int mm_isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn,
 			*contpc = regs->cp0_epc +
 				dec_insn.pc_inc + dec_insn.next_pc_inc;
 		return 1;
-		break;
 	case mm_bnez16_op:
 		if ((long)regs->regs[reg16to32map[insn.mm_b1_format.rs]] != 0)
 			*contpc = regs->cp0_epc +
@@ -615,12 +604,10 @@ int mm_isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn,
 			*contpc = regs->cp0_epc +
 				dec_insn.pc_inc + dec_insn.next_pc_inc;
 		return 1;
-		break;
 	case mm_b16_op:
 		*contpc = regs->cp0_epc + dec_insn.pc_inc +
 			 (insn.mm_b0_format.simmediate << 1);
 		return 1;
-		break;
 	case mm_beq32_op:
 		if (regs->regs[insn.mm_i_format.rs] ==
 		    regs->regs[insn.mm_i_format.rt])
@@ -632,7 +619,6 @@ int mm_isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn,
 				dec_insn.pc_inc +
 				dec_insn.next_pc_inc;
 		return 1;
-		break;
 	case mm_bne32_op:
 		if (regs->regs[insn.mm_i_format.rs] !=
 		    regs->regs[insn.mm_i_format.rt])
@@ -643,7 +629,6 @@ int mm_isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn,
 			*contpc = regs->cp0_epc +
 				dec_insn.pc_inc + dec_insn.next_pc_inc;
 		return 1;
-		break;
 	case mm_jalx32_op:
 		regs->regs[31] = regs->cp0_epc +
 			dec_insn.pc_inc + dec_insn.next_pc_inc;
@@ -652,7 +637,6 @@ int mm_isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn,
 		*contpc <<= 28;
 		*contpc |= (insn.j_format.target << 2);
 		return 1;
-		break;
 	case mm_jals32_op:
 	case mm_jal32_op:
 		regs->regs[31] = regs->cp0_epc +
@@ -665,7 +649,6 @@ int mm_isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn,
 		*contpc |= (insn.j_format.target << 1);
 		set_isa16_mode(*contpc);
 		return 1;
-		break;
 	}
 	return 0;
 }
@@ -694,7 +677,6 @@ static int isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn,
 		case jr_op:
 			*contpc = regs->regs[insn.r_format.rs];
 			return 1;
-			break;
 		}
 		break;
 	case bcond_op:
@@ -716,7 +698,6 @@ static int isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn,
 					dec_insn.pc_inc +
 					dec_insn.next_pc_inc;
 			return 1;
-			break;
 		case bgezal_op:
 		case bgezall_op:
 			regs->regs[31] = regs->cp0_epc +
@@ -734,7 +715,6 @@ static int isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn,
 					dec_insn.pc_inc +
 					dec_insn.next_pc_inc;
 			return 1;
-			break;
 		}
 		break;
 	case jalx_op:
@@ -752,7 +732,6 @@ static int isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn,
 		/* Set microMIPS mode bit: XOR for jalx. */
 		*contpc ^= bit;
 		return 1;
-		break;
 	case beq_op:
 	case beql_op:
 		if (regs->regs[insn.i_format.rs] ==
@@ -765,7 +744,6 @@ static int isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn,
 				dec_insn.pc_inc +
 				dec_insn.next_pc_inc;
 		return 1;
-		break;
 	case bne_op:
 	case bnel_op:
 		if (regs->regs[insn.i_format.rs] !=
@@ -778,7 +756,6 @@ static int isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn,
 				dec_insn.pc_inc +
 				dec_insn.next_pc_inc;
 		return 1;
-		break;
 	case blez_op:
 	case blezl_op:
 		if ((long)regs->regs[insn.i_format.rs] <= 0)
@@ -790,7 +767,6 @@ static int isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn,
 				dec_insn.pc_inc +
 				dec_insn.next_pc_inc;
 		return 1;
-		break;
 	case bgtz_op:
 	case bgtzl_op:
 		if ((long)regs->regs[insn.i_format.rs] > 0)
@@ -802,7 +778,6 @@ static int isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn,
 				dec_insn.pc_inc +
 				dec_insn.next_pc_inc;
 		return 1;
-		break;
 #ifdef CONFIG_CPU_CAVIUM_OCTEON
 	case lwc2_op: /* This is bbit0 on Octeon */
 		if ((regs->regs[insn.i_format.rs] & (1ull<<insn.i_format.rt)) == 0)
@@ -856,7 +831,6 @@ static int isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn,
 						dec_insn.pc_inc +
 						dec_insn.next_pc_inc;
 				return 1;
-				break;
 			case 1:	/* bc1t */
 			case 3:	/* bc1tl */
 				if (fcr31 & (1 << bit))
@@ -868,7 +842,6 @@ static int isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn,
 						dec_insn.pc_inc +
 						dec_insn.next_pc_inc;
 				return 1;
-				break;
 			}
 		}
 		break;
diff --git a/arch/mips/mm/c-octeon.c b/arch/mips/mm/c-octeon.c
index a0bcdbb81d41..c8efdb5b6ee0 100644
--- a/arch/mips/mm/c-octeon.c
+++ b/arch/mips/mm/c-octeon.c
@@ -19,6 +19,7 @@
 #include <asm/bootinfo.h>
 #include <asm/cacheops.h>
 #include <asm/cpu-features.h>
+#include <asm/cpu-type.h>
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/r4kcache.h>
@@ -186,9 +187,10 @@ static void probe_octeon(void)
 	unsigned long dcache_size;
 	unsigned int config1;
 	struct cpuinfo_mips *c = &current_cpu_data;
+	int cputype = current_cpu_type();
 
 	config1 = read_c0_config1();
-	switch (c->cputype) {
+	switch (cputype) {
 	case CPU_CAVIUM_OCTEON:
 	case CPU_CAVIUM_OCTEON_PLUS:
 		c->icache.linesz = 2 << ((config1 >> 19) & 7);
@@ -199,7 +201,7 @@ static void probe_octeon(void)
 			c->icache.sets * c->icache.ways * c->icache.linesz;
 		c->icache.waybit = ffs(icache_size / c->icache.ways) - 1;
 		c->dcache.linesz = 128;
-		if (c->cputype == CPU_CAVIUM_OCTEON_PLUS)
+		if (cputype == CPU_CAVIUM_OCTEON_PLUS)
 			c->dcache.sets = 2; /* CN5XXX has two Dcache sets */
 		else
 			c->dcache.sets = 1; /* CN3XXX has one Dcache set */
@@ -224,6 +226,20 @@ static void probe_octeon(void)
 		c->options |= MIPS_CPU_PREFETCH;
 		break;
 
+	case CPU_CAVIUM_OCTEON3:
+		c->icache.linesz = 128;
+		c->icache.sets = 16;
+		c->icache.ways = 39;
+		c->icache.flags |= MIPS_CACHE_VTAG;
+		icache_size = c->icache.sets * c->icache.ways * c->icache.linesz;
+
+		c->dcache.linesz = 128;
+		c->dcache.ways = 32;
+		c->dcache.sets = 8;
+		dcache_size = c->dcache.sets * c->dcache.ways * c->dcache.linesz;
+		c->options |= MIPS_CPU_PREFETCH;
+		break;
+
 	default:
 		panic("Unsupported Cavium Networks CPU type");
 		break;
diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c
index f749f687ee87..bc6f96fcb529 100644
--- a/arch/mips/mm/c-r4k.c
+++ b/arch/mips/mm/c-r4k.c
@@ -12,6 +12,7 @@
 #include <linux/highmem.h>
 #include <linux/kernel.h>
 #include <linux/linkage.h>
+#include <linux/preempt.h>
 #include <linux/sched.h>
 #include <linux/smp.h>
 #include <linux/mm.h>
@@ -24,6 +25,7 @@
 #include <asm/cacheops.h>
 #include <asm/cpu.h>
 #include <asm/cpu-features.h>
+#include <asm/cpu-type.h>
 #include <asm/io.h>
 #include <asm/page.h>
 #include <asm/pgtable.h>
@@ -601,11 +603,13 @@ static void r4k_dma_cache_wback_inv(unsigned long addr, unsigned long size)
 	/* Catch bad driver code */
 	BUG_ON(size == 0);
 
+	preempt_disable();
 	if (cpu_has_inclusive_pcaches) {
 		if (size >= scache_size)
 			r4k_blast_scache();
 		else
 			blast_scache_range(addr, addr + size);
+		preempt_enable();
 		__sync();
 		return;
 	}
@@ -621,6 +625,7 @@ static void r4k_dma_cache_wback_inv(unsigned long addr, unsigned long size)
 		R4600_HIT_CACHEOP_WAR_IMPL;
 		blast_dcache_range(addr, addr + size);
 	}
+	preempt_enable();
 
 	bc_wback_inv(addr, size);
 	__sync();
@@ -631,6 +636,7 @@ static void r4k_dma_cache_inv(unsigned long addr, unsigned long size)
 	/* Catch bad driver code */
 	BUG_ON(size == 0);
 
+	preempt_disable();
 	if (cpu_has_inclusive_pcaches) {
 		if (size >= scache_size)
 			r4k_blast_scache();
@@ -645,6 +651,7 @@ static void r4k_dma_cache_inv(unsigned long addr, unsigned long size)
 			 */
 			blast_inv_scache_range(addr, addr + size);
 		}
+		preempt_enable();
 		__sync();
 		return;
 	}
@@ -655,6 +662,7 @@ static void r4k_dma_cache_inv(unsigned long addr, unsigned long size)
 		R4600_HIT_CACHEOP_WAR_IMPL;
 		blast_inv_dcache_range(addr, addr + size);
 	}
+	preempt_enable();
 
 	bc_inv(addr, size);
 	__sync();
@@ -780,20 +788,30 @@ static inline void rm7k_erratum31(void)
 
 static inline void alias_74k_erratum(struct cpuinfo_mips *c)
 {
+	unsigned int imp = c->processor_id & PRID_IMP_MASK;
+	unsigned int rev = c->processor_id & PRID_REV_MASK;
+
 	/*
 	 * Early versions of the 74K do not update the cache tags on a
 	 * vtag miss/ptag hit which can occur in the case of KSEG0/KUSEG
 	 * aliases. In this case it is better to treat the cache as always
 	 * having aliases.
 	 */
-	if ((c->processor_id & 0xff) <= PRID_REV_ENCODE_332(2, 4, 0))
-		c->dcache.flags |= MIPS_CACHE_VTAG;
-	if ((c->processor_id & 0xff) == PRID_REV_ENCODE_332(2, 4, 0))
-		write_c0_config6(read_c0_config6() | MIPS_CONF6_SYND);
-	if (((c->processor_id & 0xff00) == PRID_IMP_1074K) &&
-	    ((c->processor_id & 0xff) <= PRID_REV_ENCODE_332(1, 1, 0))) {
-		c->dcache.flags |= MIPS_CACHE_VTAG;
-		write_c0_config6(read_c0_config6() | MIPS_CONF6_SYND);
+	switch (imp) {
+	case PRID_IMP_74K:
+		if (rev <= PRID_REV_ENCODE_332(2, 4, 0))
+			c->dcache.flags |= MIPS_CACHE_VTAG;
+		if (rev == PRID_REV_ENCODE_332(2, 4, 0))
+			write_c0_config6(read_c0_config6() | MIPS_CONF6_SYND);
+		break;
+	case PRID_IMP_1074K:
+		if (rev <= PRID_REV_ENCODE_332(1, 1, 0)) {
+			c->dcache.flags |= MIPS_CACHE_VTAG;
+			write_c0_config6(read_c0_config6() | MIPS_CONF6_SYND);
+		}
+		break;
+	default:
+		BUG();
 	}
 }
 
@@ -809,7 +827,7 @@ static void probe_pcache(void)
 	unsigned long config1;
 	unsigned int lsize;
 
-	switch (c->cputype) {
+	switch (current_cpu_type()) {
 	case CPU_R4600:			/* QED style two way caches? */
 	case CPU_R4700:
 	case CPU_R5000:
@@ -1025,7 +1043,8 @@ static void probe_pcache(void)
 	 * presumably no vendor is shipping his hardware in the "bad"
 	 * configuration.
 	 */
-	if ((prid & 0xff00) == PRID_IMP_R4000 && (prid & 0xff) < 0x40 &&
+	if ((prid & PRID_IMP_MASK) == PRID_IMP_R4000 &&
+	    (prid & PRID_REV_MASK) < PRID_REV_R4400 &&
 	    !(config & CONF_SC) && c->icache.linesz != 16 &&
 	    PAGE_SIZE <= 0x8000)
 		panic("Improper R4000SC processor configuration detected");
@@ -1045,7 +1064,7 @@ static void probe_pcache(void)
 	 * normally they'd suffer from aliases but magic in the hardware deals
 	 * with that for us so we don't need to take care ourselves.
 	 */
-	switch (c->cputype) {
+	switch (current_cpu_type()) {
 	case CPU_20KC:
 	case CPU_25KF:
 	case CPU_SB1:
@@ -1065,7 +1084,7 @@ static void probe_pcache(void)
 	case CPU_34K:
 	case CPU_74K:
 	case CPU_1004K:
-		if (c->cputype == CPU_74K)
+		if (current_cpu_type() == CPU_74K)
 			alias_74k_erratum(c);
 		if ((read_c0_config7() & (1 << 16))) {
 			/* effectively physically indexed dcache,
@@ -1078,7 +1097,7 @@ static void probe_pcache(void)
 			c->dcache.flags |= MIPS_CACHE_ALIASES;
 	}
 
-	switch (c->cputype) {
+	switch (current_cpu_type()) {
 	case CPU_20KC:
 		/*
 		 * Some older 20Kc chips doesn't have the 'VI' bit in
@@ -1207,7 +1226,7 @@ static void setup_scache(void)
 	 * processors don't have a S-cache that would be relevant to the
 	 * Linux memory management.
 	 */
-	switch (c->cputype) {
+	switch (current_cpu_type()) {
 	case CPU_R4000SC:
 	case CPU_R4000MC:
 	case CPU_R4400SC:
@@ -1384,9 +1403,8 @@ static void r4k_cache_error_setup(void)
 {
 	extern char __weak except_vec2_generic;
 	extern char __weak except_vec2_sb1;
-	struct cpuinfo_mips *c = &current_cpu_data;
 
-	switch (c->cputype) {
+	switch (current_cpu_type()) {
 	case CPU_SB1:
 	case CPU_SB1A:
 		set_uncached_handler(0x100, &except_vec2_sb1, 0x80);
diff --git a/arch/mips/mm/dma-default.c b/arch/mips/mm/dma-default.c
index aaccf1c10699..5f8b95512580 100644
--- a/arch/mips/mm/dma-default.c
+++ b/arch/mips/mm/dma-default.c
@@ -18,6 +18,7 @@
 #include <linux/highmem.h>
 
 #include <asm/cache.h>
+#include <asm/cpu-type.h>
 #include <asm/io.h>
 
 #include <dma-coherence.h>
@@ -50,16 +51,20 @@ static inline struct page *dma_addr_to_page(struct device *dev,
 }
 
 /*
+ * The affected CPUs below in 'cpu_needs_post_dma_flush()' can
+ * speculatively fill random cachelines with stale data at any time,
+ * requiring an extra flush post-DMA.
+ *
  * Warning on the terminology - Linux calls an uncached area coherent;
  * MIPS terminology calls memory areas with hardware maintained coherency
  * coherent.
  */
-
-static inline int cpu_is_noncoherent_r10000(struct device *dev)
+static inline int cpu_needs_post_dma_flush(struct device *dev)
 {
 	return !plat_device_is_coherent(dev) &&
-	       (current_cpu_type() == CPU_R10000 ||
-	       current_cpu_type() == CPU_R12000);
+	       (boot_cpu_type() == CPU_R10000 ||
+		boot_cpu_type() == CPU_R12000 ||
+		boot_cpu_type() == CPU_BMIPS5000);
 }
 
 static gfp_t massage_gfp_flags(const struct device *dev, gfp_t gfp)
@@ -230,7 +235,7 @@ static inline void __dma_sync(struct page *page,
 static void mips_dma_unmap_page(struct device *dev, dma_addr_t dma_addr,
 	size_t size, enum dma_data_direction direction, struct dma_attrs *attrs)
 {
-	if (cpu_is_noncoherent_r10000(dev))
+	if (cpu_needs_post_dma_flush(dev))
 		__dma_sync(dma_addr_to_page(dev, dma_addr),
 			   dma_addr & ~PAGE_MASK, size, direction);
 
@@ -284,7 +289,7 @@ static void mips_dma_unmap_sg(struct device *dev, struct scatterlist *sg,
 static void mips_dma_sync_single_for_cpu(struct device *dev,
 	dma_addr_t dma_handle, size_t size, enum dma_data_direction direction)
 {
-	if (cpu_is_noncoherent_r10000(dev))
+	if (cpu_needs_post_dma_flush(dev))
 		__dma_sync(dma_addr_to_page(dev, dma_handle),
 			   dma_handle & ~PAGE_MASK, size, direction);
 }
@@ -303,12 +308,10 @@ static void mips_dma_sync_sg_for_cpu(struct device *dev,
 {
 	int i;
 
-	/* Make sure that gcc doesn't leave the empty loop body.  */
-	for (i = 0; i < nelems; i++, sg++) {
-		if (cpu_is_noncoherent_r10000(dev))
+	if (cpu_needs_post_dma_flush(dev))
+		for (i = 0; i < nelems; i++, sg++)
 			__dma_sync(sg_page(sg), sg->offset, sg->length,
 				   direction);
-	}
 }
 
 static void mips_dma_sync_sg_for_device(struct device *dev,
@@ -316,12 +319,10 @@ static void mips_dma_sync_sg_for_device(struct device *dev,
 {
 	int i;
 
-	/* Make sure that gcc doesn't leave the empty loop body.  */
-	for (i = 0; i < nelems; i++, sg++) {
-		if (!plat_device_is_coherent(dev))
+	if (!plat_device_is_coherent(dev))
+		for (i = 0; i < nelems; i++, sg++)
 			__dma_sync(sg_page(sg), sg->offset, sg->length,
 				   direction);
-	}
 }
 
 int mips_dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
diff --git a/arch/mips/mm/fault.c b/arch/mips/mm/fault.c
index 85df1cd8d446..becc42bb1849 100644
--- a/arch/mips/mm/fault.c
+++ b/arch/mips/mm/fault.c
@@ -42,8 +42,7 @@ static void __kprobes __do_page_fault(struct pt_regs *regs, unsigned long write,
 	const int field = sizeof(unsigned long) * 2;
 	siginfo_t info;
 	int fault;
-	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
-						 (write ? FAULT_FLAG_WRITE : 0);
+	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
 
 #if 0
 	printk("Cpu%d[%s:%d:%0*lx:%ld:%0*lx]\n", raw_smp_processor_id(),
@@ -93,6 +92,8 @@ static void __kprobes __do_page_fault(struct pt_regs *regs, unsigned long write,
 	if (in_atomic() || !mm)
 		goto bad_area_nosemaphore;
 
+	if (user_mode(regs))
+		flags |= FAULT_FLAG_USER;
 retry:
 	down_read(&mm->mmap_sem);
 	vma = find_vma(mm, address);
@@ -114,6 +115,7 @@ good_area:
 	if (write) {
 		if (!(vma->vm_flags & VM_WRITE))
 			goto bad_area;
+		flags |= FAULT_FLAG_WRITE;
 	} else {
 		if (cpu_has_rixi) {
 			if (address == regs->cp0_epc && !(vma->vm_flags & VM_EXEC)) {
@@ -241,6 +243,8 @@ out_of_memory:
 	 * (which will retry the fault, or kill us if we got oom-killed).
 	 */
 	up_read(&mm->mmap_sem);
+	if (!user_mode(regs))
+		goto no_context;
 	pagefault_out_of_memory();
 	return;
 
diff --git a/arch/mips/mm/gup.c b/arch/mips/mm/gup.c
index d4ea5c9c4a93..06ce17c2a905 100644
--- a/arch/mips/mm/gup.c
+++ b/arch/mips/mm/gup.c
@@ -12,6 +12,7 @@
 #include <linux/swap.h>
 #include <linux/hugetlb.h>
 
+#include <asm/cpu-features.h>
 #include <asm/pgtable.h>
 
 static inline pte_t gup_get_pte(pte_t *ptep)
@@ -273,7 +274,7 @@ int get_user_pages_fast(unsigned long start, int nr_pages, int write,
 	len = (unsigned long) nr_pages << PAGE_SHIFT;
 
 	end = start + len;
-	if (end < start)
+	if (end < start || cpu_has_dc_aliases)
 		goto slow_irqon;
 
 	/* XXX: batch / limit 'nr' */
diff --git a/arch/mips/mm/hugetlbpage.c b/arch/mips/mm/hugetlbpage.c
index a7fee0dfb7a9..01fda4419ed0 100644
--- a/arch/mips/mm/hugetlbpage.c
+++ b/arch/mips/mm/hugetlbpage.c
@@ -85,6 +85,11 @@ int pud_huge(pud_t pud)
 	return (pud_val(pud) & _PAGE_HUGE) != 0;
 }
 
+int pmd_huge_support(void)
+{
+	return 1;
+}
+
 struct page *
 follow_huge_pmd(struct mm_struct *mm, unsigned long address,
 		pmd_t *pmd, int write)
diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c
index 4e73f10a7519..e205ef598e97 100644
--- a/arch/mips/mm/init.c
+++ b/arch/mips/mm/init.c
@@ -254,6 +254,7 @@ void copy_from_user_page(struct vm_area_struct *vma,
 			SetPageDcacheDirty(page);
 	}
 }
+EXPORT_SYMBOL_GPL(copy_from_user_page);
 
 void __init fixrange_init(unsigned long start, unsigned long end,
 	pgd_t *pgd_base)
diff --git a/arch/mips/mm/page.c b/arch/mips/mm/page.c
index 218c2109a55d..cbd81d17793a 100644
--- a/arch/mips/mm/page.c
+++ b/arch/mips/mm/page.c
@@ -18,6 +18,7 @@
 
 #include <asm/bugs.h>
 #include <asm/cacheops.h>
+#include <asm/cpu-type.h>
 #include <asm/inst.h>
 #include <asm/io.h>
 #include <asm/page.h>
diff --git a/arch/mips/mm/sc-mips.c b/arch/mips/mm/sc-mips.c
index 5d01392e3518..08d05aee8788 100644
--- a/arch/mips/mm/sc-mips.c
+++ b/arch/mips/mm/sc-mips.c
@@ -6,6 +6,7 @@
 #include <linux/sched.h>
 #include <linux/mm.h>
 
+#include <asm/cpu-type.h>
 #include <asm/mipsregs.h>
 #include <asm/bcache.h>
 #include <asm/cacheops.h>
@@ -71,7 +72,7 @@ static inline int mips_sc_is_activated(struct cpuinfo_mips *c)
 	unsigned int tmp;
 
 	/* Check the bypass bit (L2B) */
-	switch (c->cputype) {
+	switch (current_cpu_type()) {
 	case CPU_34K:
 	case CPU_74K:
 	case CPU_1004K:
diff --git a/arch/mips/mm/tlb-funcs.S b/arch/mips/mm/tlb-funcs.S
index 30a494db99c2..79bca3130bd1 100644
--- a/arch/mips/mm/tlb-funcs.S
+++ b/arch/mips/mm/tlb-funcs.S
@@ -16,10 +16,12 @@
 
 #define FASTPATH_SIZE	128
 
+#ifdef CONFIG_MIPS_PGD_C0_CONTEXT
 LEAF(tlbmiss_handler_setup_pgd)
 	.space		16 * 4
 END(tlbmiss_handler_setup_pgd)
 EXPORT(tlbmiss_handler_setup_pgd_end)
+#endif
 
 LEAF(handle_tlbm)
 	.space		FASTPATH_SIZE * 4
diff --git a/arch/mips/mm/tlb-r4k.c b/arch/mips/mm/tlb-r4k.c
index 00b26a67a06d..bb3a5f643e97 100644
--- a/arch/mips/mm/tlb-r4k.c
+++ b/arch/mips/mm/tlb-r4k.c
@@ -16,6 +16,7 @@
 #include <linux/module.h>
 
 #include <asm/cpu.h>
+#include <asm/cpu-type.h>
 #include <asm/bootinfo.h>
 #include <asm/mmu_context.h>
 #include <asm/pgtable.h>
diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c
index 556cb4815770..9bb3a9363b06 100644
--- a/arch/mips/mm/tlbex.c
+++ b/arch/mips/mm/tlbex.c
@@ -30,6 +30,7 @@
 #include <linux/cache.h>
 
 #include <asm/cacheflush.h>
+#include <asm/cpu-type.h>
 #include <asm/pgtable.h>
 #include <asm/war.h>
 #include <asm/uasm.h>
@@ -85,6 +86,7 @@ static int use_bbit_insns(void)
 	case CPU_CAVIUM_OCTEON:
 	case CPU_CAVIUM_OCTEON_PLUS:
 	case CPU_CAVIUM_OCTEON2:
+	case CPU_CAVIUM_OCTEON3:
 		return 1;
 	default:
 		return 0;
@@ -95,6 +97,7 @@ static int use_lwx_insns(void)
 {
 	switch (current_cpu_type()) {
 	case CPU_CAVIUM_OCTEON2:
+	case CPU_CAVIUM_OCTEON3:
 		return 1;
 	default:
 		return 0;
diff --git a/arch/mips/mti-malta/malta-time.c b/arch/mips/mti-malta/malta-time.c
index 53aad4a35375..a18af5fce67e 100644
--- a/arch/mips/mti-malta/malta-time.c
+++ b/arch/mips/mti-malta/malta-time.c
@@ -27,6 +27,7 @@
 #include <linux/timex.h>
 #include <linux/mc146818rtc.h>
 
+#include <asm/cpu.h>
 #include <asm/mipsregs.h>
 #include <asm/mipsmtregs.h>
 #include <asm/hardirq.h>
@@ -76,7 +77,7 @@ static void __init estimate_frequencies(void)
 #endif
 
 #if defined (CONFIG_KVM_GUEST) && defined (CONFIG_KVM_HOST_FREQ)
-	unsigned int prid = read_c0_prid() & 0xffff00;
+	unsigned int prid = read_c0_prid() & (PRID_COMP_MASK | PRID_IMP_MASK);
 
 	/*
 	 * XXXKYMA: hardwire the CPU frequency to Host Freq/4
@@ -169,7 +170,7 @@ unsigned int get_c0_compare_int(void)
 
 void __init plat_time_init(void)
 {
-	unsigned int prid = read_c0_prid() & 0xffff00;
+	unsigned int prid = read_c0_prid() & (PRID_COMP_MASK | PRID_IMP_MASK);
 	unsigned int freq;
 
 	estimate_frequencies();
diff --git a/arch/mips/mti-sead3/sead3-time.c b/arch/mips/mti-sead3/sead3-time.c
index a43ea3cc0a3b..552d26c34386 100644
--- a/arch/mips/mti-sead3/sead3-time.c
+++ b/arch/mips/mti-sead3/sead3-time.c
@@ -7,6 +7,7 @@
  */
 #include <linux/init.h>
 
+#include <asm/cpu.h>
 #include <asm/setup.h>
 #include <asm/time.h>
 #include <asm/irq.h>
@@ -34,7 +35,7 @@ static void __iomem *status_reg = (void __iomem *)0xbf000410;
  */
 static unsigned int __init estimate_cpu_frequency(void)
 {
-	unsigned int prid = read_c0_prid() & 0xffff00;
+	unsigned int prid = read_c0_prid() & (PRID_COMP_MASK | PRID_IMP_MASK);
 	unsigned int tick = 0;
 	unsigned int freq;
 	unsigned int orig;
diff --git a/arch/mips/netlogic/Kconfig b/arch/mips/netlogic/Kconfig
index 2447bf97d35a..852a4ee09954 100644
--- a/arch/mips/netlogic/Kconfig
+++ b/arch/mips/netlogic/Kconfig
@@ -19,6 +19,15 @@ config DT_XLP_SVP
 	  pointer to the kernel.  The corresponding DTS file is at
 	  arch/mips/netlogic/dts/xlp_svp.dts
 
+config DT_XLP_FVP
+	bool "Built-in device tree for XLP FVP boards"
+	default y
+	help
+	  Add an FDT blob for XLP FVP board into the kernel.
+	  This DTB will be used if the firmware does not pass in a DTB
+	  pointer to the kernel.  The corresponding DTS file is at
+	  arch/mips/netlogic/dts/xlp_fvp.dts
+
 config NLM_MULTINODE
 	bool "Support for multi-chip boards"
 	depends on NLM_XLP_BOARD
diff --git a/arch/mips/netlogic/common/smp.c b/arch/mips/netlogic/common/smp.c
index 4e35d9c453e2..6f8feb9efcff 100644
--- a/arch/mips/netlogic/common/smp.c
+++ b/arch/mips/netlogic/common/smp.c
@@ -106,9 +106,7 @@ void nlm_early_init_secondary(int cpu)
 {
 	change_c0_config(CONF_CM_CMASK, 0x3);
 #ifdef CONFIG_CPU_XLP
-	/* mmu init, once per core */
-	if (cpu % NLM_THREADS_PER_CORE == 0)
-		xlp_mmu_init();
+	xlp_mmu_init();
 #endif
 	write_c0_ebase(nlm_current_node()->ebase);
 }
diff --git a/arch/mips/netlogic/common/time.c b/arch/mips/netlogic/common/time.c
index 045a396c57ce..13391b8a6031 100644
--- a/arch/mips/netlogic/common/time.c
+++ b/arch/mips/netlogic/common/time.c
@@ -45,6 +45,7 @@
 #if defined(CONFIG_CPU_XLP)
 #include <asm/netlogic/xlp-hal/iomap.h>
 #include <asm/netlogic/xlp-hal/xlp.h>
+#include <asm/netlogic/xlp-hal/sys.h>
 #include <asm/netlogic/xlp-hal/pic.h>
 #elif defined(CONFIG_CPU_XLR)
 #include <asm/netlogic/xlr/iomap.h>
@@ -91,7 +92,7 @@ static void nlm_init_pic_timer(void)
 		csrc_pic.read	= nlm_get_pic_timer;
 	}
 	csrc_pic.rating = 1000;
-	clocksource_register_hz(&csrc_pic, PIC_CLK_HZ);
+	clocksource_register_hz(&csrc_pic, pic_timer_freq());
 }
 
 void __init plat_time_init(void)
diff --git a/arch/mips/netlogic/dts/Makefile b/arch/mips/netlogic/dts/Makefile
index aecb6fa9a9c3..0b9be5fd2e46 100644
--- a/arch/mips/netlogic/dts/Makefile
+++ b/arch/mips/netlogic/dts/Makefile
@@ -1,2 +1,3 @@
 obj-$(CONFIG_DT_XLP_EVP) := xlp_evp.dtb.o
 obj-$(CONFIG_DT_XLP_SVP) += xlp_svp.dtb.o
+obj-$(CONFIG_DT_XLP_FVP) += xlp_fvp.dtb.o
diff --git a/arch/mips/netlogic/dts/xlp_evp.dts b/arch/mips/netlogic/dts/xlp_evp.dts
index 06407033678e..89ad04808c02 100644
--- a/arch/mips/netlogic/dts/xlp_evp.dts
+++ b/arch/mips/netlogic/dts/xlp_evp.dts
@@ -9,19 +9,12 @@
 	#address-cells = <2>;
 	#size-cells = <2>;
 
-	memory {
-		device_type = "memory";
-		reg =  <0 0x00100000 0 0x0FF00000	// 255M at 1M
-			0 0x20000000 0 0xa0000000	// 2560M at 512M
-			0 0xe0000000 1 0x00000000>;
-	};
-
 	soc {
 		#address-cells = <2>;
 		#size-cells = <1>;
 		compatible = "simple-bus";
 		ranges = <0 0  0 0x18000000  0x04000000   // PCIe CFG
-			  1 0  0 0x16000000  0x01000000>; // GBU chipselects
+			  1 0  0 0x16000000  0x02000000>; // GBU chipselects
 
 		serial0: serial@30000 {
 			device_type = "serial";
diff --git a/arch/mips/netlogic/dts/xlp_fvp.dts b/arch/mips/netlogic/dts/xlp_fvp.dts
new file mode 100644
index 000000000000..63e62b7bd758
--- /dev/null
+++ b/arch/mips/netlogic/dts/xlp_fvp.dts
@@ -0,0 +1,118 @@
+/*
+ * XLP2XX Device Tree Source for FVP boards
+ */
+
+/dts-v1/;
+/ {
+	model = "netlogic,XLP-FVP";
+	compatible = "netlogic,xlp";
+	#address-cells = <2>;
+	#size-cells = <2>;
+
+	soc {
+		#address-cells = <2>;
+		#size-cells = <1>;
+		compatible = "simple-bus";
+		ranges = <0 0  0 0x18000000  0x04000000   // PCIe CFG
+			  1 0  0 0x16000000  0x02000000>; // GBU chipselects
+
+		serial0: serial@30000 {
+			device_type = "serial";
+			compatible = "ns16550";
+			reg = <0 0x30100 0xa00>;
+			reg-shift = <2>;
+			reg-io-width = <4>;
+			clock-frequency = <133333333>;
+			interrupt-parent = <&pic>;
+			interrupts = <17>;
+		};
+		serial1: serial@31000 {
+			device_type = "serial";
+			compatible = "ns16550";
+			reg = <0 0x31100 0xa00>;
+			reg-shift = <2>;
+			reg-io-width = <4>;
+			clock-frequency = <133333333>;
+			interrupt-parent = <&pic>;
+			interrupts = <18>;
+		};
+		i2c0: ocores@37100 {
+			compatible = "opencores,i2c-ocores";
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0 0x37100 0x20>;
+			reg-shift = <2>;
+			reg-io-width = <4>;
+			clock-frequency = <32000000>;
+			interrupt-parent = <&pic>;
+			interrupts = <30>;
+		};
+		i2c1: ocores@37120 {
+			compatible = "opencores,i2c-ocores";
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0 0x37120 0x20>;
+			reg-shift = <2>;
+			reg-io-width = <4>;
+			clock-frequency = <32000000>;
+			interrupt-parent = <&pic>;
+			interrupts = <31>;
+
+			rtc@68 {
+				compatible = "dallas,ds1374";
+				reg = <0x68>;
+			};
+
+			dtt@4c {
+				compatible = "national,lm90";
+				reg = <0x4c>;
+			};
+		};
+		pic: pic@4000 {
+			compatible = "netlogic,xlp-pic";
+			#address-cells = <0>;
+			#interrupt-cells = <1>;
+			reg = <0 0x4000 0x200>;
+			interrupt-controller;
+		};
+
+		nor_flash@1,0 {
+			compatible = "cfi-flash";
+			#address-cells = <1>;
+			#size-cells = <1>;
+			bank-width = <2>;
+			reg = <1 0 0x1000000>;
+
+			partition@0 {
+				label = "x-loader";
+				reg = <0x0 0x100000>; /* 1M */
+				read-only;
+			};
+
+			partition@100000 {
+				label = "u-boot";
+				reg = <0x100000 0x100000>; /* 1M */
+			};
+
+			partition@200000 {
+				label = "kernel";
+				reg = <0x200000 0x500000>; /* 5M */
+			};
+
+			partition@700000 {
+				label = "rootfs";
+				reg = <0x700000 0x800000>; /* 8M */
+			};
+
+			partition@f00000 {
+				label = "env";
+				reg = <0xf00000 0x100000>; /* 1M */
+				read-only;
+			};
+		};
+	};
+
+	chosen {
+		bootargs = "console=ttyS0,115200 rdinit=/sbin/init";
+	};
+};
diff --git a/arch/mips/netlogic/dts/xlp_svp.dts b/arch/mips/netlogic/dts/xlp_svp.dts
index 9c5db102df53..1ebd00edaacc 100644
--- a/arch/mips/netlogic/dts/xlp_svp.dts
+++ b/arch/mips/netlogic/dts/xlp_svp.dts
@@ -9,19 +9,12 @@
 	#address-cells = <2>;
 	#size-cells = <2>;
 
-	memory {
-		device_type = "memory";
-		reg =  <0 0x00100000 0 0x0FF00000	// 255M at 1M
-			0 0x20000000 0 0xa0000000	// 2560M at 512M
-			0 0xe0000000 0 0x40000000>;
-	};
-
 	soc {
 		#address-cells = <2>;
 		#size-cells = <1>;
 		compatible = "simple-bus";
 		ranges = <0 0  0 0x18000000  0x04000000   // PCIe CFG
-			  1 0  0 0x16000000  0x01000000>; // GBU chipselects
+			  1 0  0 0x16000000  0x02000000>; // GBU chipselects
 
 		serial0: serial@30000 {
 			device_type = "serial";
diff --git a/arch/mips/netlogic/xlp/Makefile b/arch/mips/netlogic/xlp/Makefile
index 85ac4a892ced..ed9a93c04650 100644
--- a/arch/mips/netlogic/xlp/Makefile
+++ b/arch/mips/netlogic/xlp/Makefile
@@ -1,3 +1,4 @@
 obj-y				+= setup.o nlm_hal.o cop2-ex.o dt.o
 obj-$(CONFIG_SMP)		+= wakeup.o
 obj-$(CONFIG_USB)		+= usb-init.o
+obj-$(CONFIG_USB)		+= usb-init-xlp2.o
diff --git a/arch/mips/netlogic/xlp/dt.c b/arch/mips/netlogic/xlp/dt.c
index a15cdbb8d0bd..88df445dda76 100644
--- a/arch/mips/netlogic/xlp/dt.c
+++ b/arch/mips/netlogic/xlp/dt.c
@@ -39,12 +39,18 @@
 #include <linux/of_platform.h>
 #include <linux/of_device.h>
 
-extern u32 __dtb_xlp_evp_begin[], __dtb_xlp_svp_begin[], __dtb_start[];
+extern u32 __dtb_xlp_evp_begin[], __dtb_xlp_svp_begin[],
+	__dtb_xlp_fvp_begin[], __dtb_start[];
 
 void __init *xlp_dt_init(void *fdtp)
 {
 	if (!fdtp) {
 		switch (current_cpu_data.processor_id & 0xff00) {
+#ifdef CONFIG_DT_XLP_FVP
+		case PRID_IMP_NETLOGIC_XLP2XX:
+			fdtp = __dtb_xlp_fvp_begin;
+			break;
+#endif
 #ifdef CONFIG_DT_XLP_SVP
 		case PRID_IMP_NETLOGIC_XLP3XX:
 			fdtp = __dtb_xlp_svp_begin;
diff --git a/arch/mips/netlogic/xlp/nlm_hal.c b/arch/mips/netlogic/xlp/nlm_hal.c
index 87560e4db35f..56c50ba43c9b 100644
--- a/arch/mips/netlogic/xlp/nlm_hal.c
+++ b/arch/mips/netlogic/xlp/nlm_hal.c
@@ -44,6 +44,7 @@
 #include <asm/netlogic/haldefs.h>
 #include <asm/netlogic/xlp-hal/iomap.h>
 #include <asm/netlogic/xlp-hal/xlp.h>
+#include <asm/netlogic/xlp-hal/bridge.h>
 #include <asm/netlogic/xlp-hal/pic.h>
 #include <asm/netlogic/xlp-hal/sys.h>
 
@@ -64,6 +65,7 @@ int nlm_irq_to_irt(int irq)
 	uint64_t pcibase;
 	int devoff, irt;
 
+	devoff = 0;
 	switch (irq) {
 	case PIC_UART_0_IRQ:
 		devoff = XLP_IO_UART0_OFFSET(0);
@@ -71,44 +73,68 @@ int nlm_irq_to_irt(int irq)
 	case PIC_UART_1_IRQ:
 		devoff = XLP_IO_UART1_OFFSET(0);
 		break;
-	case PIC_EHCI_0_IRQ:
-		devoff = XLP_IO_USB_EHCI0_OFFSET(0);
-		break;
-	case PIC_EHCI_1_IRQ:
-		devoff = XLP_IO_USB_EHCI1_OFFSET(0);
-		break;
-	case PIC_OHCI_0_IRQ:
-		devoff = XLP_IO_USB_OHCI0_OFFSET(0);
-		break;
-	case PIC_OHCI_1_IRQ:
-		devoff = XLP_IO_USB_OHCI1_OFFSET(0);
-		break;
-	case PIC_OHCI_2_IRQ:
-		devoff = XLP_IO_USB_OHCI2_OFFSET(0);
-		break;
-	case PIC_OHCI_3_IRQ:
-		devoff = XLP_IO_USB_OHCI3_OFFSET(0);
-		break;
 	case PIC_MMC_IRQ:
 		devoff = XLP_IO_SD_OFFSET(0);
 		break;
-	case PIC_I2C_0_IRQ:
-		devoff = XLP_IO_I2C0_OFFSET(0);
-		break;
+	case PIC_I2C_0_IRQ:	/* I2C will be fixed up */
 	case PIC_I2C_1_IRQ:
-		devoff = XLP_IO_I2C1_OFFSET(0);
+	case PIC_I2C_2_IRQ:
+	case PIC_I2C_3_IRQ:
+		if (cpu_is_xlpii())
+			devoff = XLP2XX_IO_I2C_OFFSET(0);
+		else
+			devoff = XLP_IO_I2C0_OFFSET(0);
 		break;
 	default:
-		devoff = 0;
-		break;
+		if (cpu_is_xlpii()) {
+			switch (irq) {
+				/* XLP2XX has three XHCI USB controller */
+			case PIC_2XX_XHCI_0_IRQ:
+				devoff = XLP2XX_IO_USB_XHCI0_OFFSET(0);
+				break;
+			case PIC_2XX_XHCI_1_IRQ:
+				devoff = XLP2XX_IO_USB_XHCI1_OFFSET(0);
+				break;
+			case PIC_2XX_XHCI_2_IRQ:
+				devoff = XLP2XX_IO_USB_XHCI2_OFFSET(0);
+				break;
+			}
+		} else {
+			switch (irq) {
+			case PIC_EHCI_0_IRQ:
+				devoff = XLP_IO_USB_EHCI0_OFFSET(0);
+				break;
+			case PIC_EHCI_1_IRQ:
+				devoff = XLP_IO_USB_EHCI1_OFFSET(0);
+				break;
+			case PIC_OHCI_0_IRQ:
+				devoff = XLP_IO_USB_OHCI0_OFFSET(0);
+				break;
+			case PIC_OHCI_1_IRQ:
+				devoff = XLP_IO_USB_OHCI1_OFFSET(0);
+				break;
+			case PIC_OHCI_2_IRQ:
+				devoff = XLP_IO_USB_OHCI2_OFFSET(0);
+				break;
+			case PIC_OHCI_3_IRQ:
+				devoff = XLP_IO_USB_OHCI3_OFFSET(0);
+				break;
+			}
+		}
 	}
 
 	if (devoff != 0) {
 		pcibase = nlm_pcicfg_base(devoff);
 		irt = nlm_read_reg(pcibase, XLP_PCI_IRTINFO_REG) & 0xffff;
-		/* HW bug, I2C 1 irt entry is off by one */
-		if (irq == PIC_I2C_1_IRQ)
-			irt = irt + 1;
+		/* HW weirdness, I2C IRT entry has to be fixed up */
+		switch (irq) {
+		case PIC_I2C_1_IRQ:
+			irt = irt + 1; break;
+		case PIC_I2C_2_IRQ:
+			irt = irt + 2; break;
+		case PIC_I2C_3_IRQ:
+			irt = irt + 3; break;
+		}
 	} else if (irq >= PIC_PCIE_LINK_0_IRQ && irq <= PIC_PCIE_LINK_3_IRQ) {
 		/* HW bug, PCI IRT entries are bad on early silicon, fix */
 		irt = PIC_IRT_PCIE_LINK_INDEX(irq - PIC_PCIE_LINK_0_IRQ);
@@ -126,19 +152,160 @@ unsigned int nlm_get_core_frequency(int node, int core)
 
 	sysbase = nlm_get_node(node)->sysbase;
 	rstval = nlm_read_sys_reg(sysbase, SYS_POWER_ON_RESET_CFG);
-	dfsval = nlm_read_sys_reg(sysbase, SYS_CORE_DFS_DIV_VALUE);
-	pll_divf = ((rstval >> 10) & 0x7f) + 1;
-	pll_divr = ((rstval >> 8)  & 0x3) + 1;
-	ext_div	 = ((rstval >> 30) & 0x3) + 1;
-	dfs_div	 = ((dfsval >> (core * 4)) & 0xf) + 1;
-
-	num = 800000000ULL * pll_divf;
-	denom = 3 * pll_divr * ext_div * dfs_div;
+	if (cpu_is_xlpii()) {
+		num = 1000000ULL * (400 * 3 + 100 * (rstval >> 26));
+		denom = 3;
+	} else {
+		dfsval = nlm_read_sys_reg(sysbase, SYS_CORE_DFS_DIV_VALUE);
+		pll_divf = ((rstval >> 10) & 0x7f) + 1;
+		pll_divr = ((rstval >> 8)  & 0x3) + 1;
+		ext_div  = ((rstval >> 30) & 0x3) + 1;
+		dfs_div  = ((dfsval >> (core * 4)) & 0xf) + 1;
+
+		num = 800000000ULL * pll_divf;
+		denom = 3 * pll_divr * ext_div * dfs_div;
+	}
 	do_div(num, denom);
 	return (unsigned int)num;
 }
 
+/* Calculate Frequency to the PIC from PLL.
+ * freq_out = ( ref_freq/2 * (6 + ctrl2[7:0]) + ctrl2[20:8]/2^13 ) /
+ * ((2^ctrl0[7:5]) * Table(ctrl0[26:24]))
+ */
+static unsigned int nlm_2xx_get_pic_frequency(int node)
+{
+	u32 ctrl_val0, ctrl_val2, vco_post_div, pll_post_div;
+	u32 mdiv, fdiv, pll_out_freq_den, reg_select, ref_div, pic_div;
+	u64 ref_clk, sysbase, pll_out_freq_num, ref_clk_select;
+
+	sysbase = nlm_get_node(node)->sysbase;
+
+	/* Find ref_clk_base */
+	ref_clk_select =
+		(nlm_read_sys_reg(sysbase, SYS_POWER_ON_RESET_CFG) >> 18) & 0x3;
+	switch (ref_clk_select) {
+	case 0:
+		ref_clk = 200000000ULL;
+		ref_div = 3;
+		break;
+	case 1:
+		ref_clk = 100000000ULL;
+		ref_div = 1;
+		break;
+	case 2:
+		ref_clk = 125000000ULL;
+		ref_div = 1;
+		break;
+	case 3:
+		ref_clk = 400000000ULL;
+		ref_div = 3;
+		break;
+	}
+
+	/* Find the clock source PLL device for PIC */
+	reg_select = (nlm_read_sys_reg(sysbase, SYS_CLK_DEV_SEL) >> 22) & 0x3;
+	switch (reg_select) {
+	case 0:
+		ctrl_val0 = nlm_read_sys_reg(sysbase, SYS_PLL_CTRL0);
+		ctrl_val2 = nlm_read_sys_reg(sysbase, SYS_PLL_CTRL2);
+		break;
+	case 1:
+		ctrl_val0 = nlm_read_sys_reg(sysbase, SYS_PLL_CTRL0_DEVX(0));
+		ctrl_val2 = nlm_read_sys_reg(sysbase, SYS_PLL_CTRL2_DEVX(0));
+		break;
+	case 2:
+		ctrl_val0 = nlm_read_sys_reg(sysbase, SYS_PLL_CTRL0_DEVX(1));
+		ctrl_val2 = nlm_read_sys_reg(sysbase, SYS_PLL_CTRL2_DEVX(1));
+		break;
+	case 3:
+		ctrl_val0 = nlm_read_sys_reg(sysbase, SYS_PLL_CTRL0_DEVX(2));
+		ctrl_val2 = nlm_read_sys_reg(sysbase, SYS_PLL_CTRL2_DEVX(2));
+		break;
+	}
+
+	vco_post_div = (ctrl_val0 >> 5) & 0x7;
+	pll_post_div = (ctrl_val0 >> 24) & 0x7;
+	mdiv = ctrl_val2 & 0xff;
+	fdiv = (ctrl_val2 >> 8) & 0xfff;
+
+	/* Find PLL post divider value */
+	switch (pll_post_div) {
+	case 1:
+		pll_post_div = 2;
+		break;
+	case 3:
+		pll_post_div = 4;
+		break;
+	case 7:
+		pll_post_div = 8;
+		break;
+	case 6:
+		pll_post_div = 16;
+		break;
+	case 0:
+	default:
+		pll_post_div = 1;
+		break;
+	}
+
+	fdiv = fdiv/(1 << 13);
+	pll_out_freq_num = ((ref_clk >> 1) * (6 + mdiv)) + fdiv;
+	pll_out_freq_den = (1 << vco_post_div) * pll_post_div * 3;
+
+	if (pll_out_freq_den > 0)
+		do_div(pll_out_freq_num, pll_out_freq_den);
+
+	/* PIC post divider, which happens after PLL */
+	pic_div = (nlm_read_sys_reg(sysbase, SYS_CLK_DEV_DIV) >> 22) & 0x3;
+	do_div(pll_out_freq_num, 1 << pic_div);
+
+	return pll_out_freq_num;
+}
+
+unsigned int nlm_get_pic_frequency(int node)
+{
+	if (cpu_is_xlpii())
+		return nlm_2xx_get_pic_frequency(node);
+	else
+		return 133333333;
+}
+
 unsigned int nlm_get_cpu_frequency(void)
 {
 	return nlm_get_core_frequency(0, 0);
 }
+
+/*
+ * Fills upto 8 pairs of entries containing the DRAM map of a node
+ * if n < 0, get dram map for all nodes
+ */
+int xlp_get_dram_map(int n, uint64_t *dram_map)
+{
+	uint64_t bridgebase, base, lim;
+	uint32_t val;
+	int i, node, rv;
+
+	/* Look only at mapping on Node 0, we don't handle crazy configs */
+	bridgebase = nlm_get_bridge_regbase(0);
+	rv = 0;
+	for (i = 0; i < 8; i++) {
+		val = nlm_read_bridge_reg(bridgebase,
+					BRIDGE_DRAM_NODE_TRANSLN(i));
+		node = (val >> 1) & 0x3;
+		if (n >= 0 && n != node)
+			continue;
+		val = nlm_read_bridge_reg(bridgebase, BRIDGE_DRAM_BAR(i));
+		val = (val >>  12) & 0xfffff;
+		base = (uint64_t) val << 20;
+		val = nlm_read_bridge_reg(bridgebase, BRIDGE_DRAM_LIMIT(i));
+		val = (val >>  12) & 0xfffff;
+		if (val == 0)   /* BAR not used */
+			continue;
+		lim = ((uint64_t)val + 1) << 20;
+		dram_map[rv] = base;
+		dram_map[rv + 1] = lim;
+		rv += 2;
+	}
+	return rv;
+}
diff --git a/arch/mips/netlogic/xlp/setup.c b/arch/mips/netlogic/xlp/setup.c
index 7b638f7be491..76a7131e486e 100644
--- a/arch/mips/netlogic/xlp/setup.c
+++ b/arch/mips/netlogic/xlp/setup.c
@@ -73,6 +73,23 @@ static void nlm_fixup_mem(void)
 	}
 }
 
+static void __init xlp_init_mem_from_bars(void)
+{
+	uint64_t map[16];
+	int i, n;
+
+	n = xlp_get_dram_map(-1, map);	/* -1: info for all nodes */
+	for (i = 0; i < n; i += 2) {
+		/* exclude 0x1000_0000-0x2000_0000, u-boot device */
+		if (map[i] <= 0x10000000 && map[i+1] > 0x10000000)
+			map[i+1] = 0x10000000;
+		if (map[i] > 0x10000000 && map[i] < 0x20000000)
+			map[i] = 0x20000000;
+
+		add_memory_region(map[i], map[i+1] - map[i], BOOT_MEM_RAM);
+	}
+}
+
 void __init plat_mem_setup(void)
 {
 	panic_timeout	= 5;
@@ -82,12 +99,23 @@ void __init plat_mem_setup(void)
 
 	/* memory and bootargs from DT */
 	early_init_devtree(initial_boot_params);
+
+	if (boot_mem_map.nr_map == 0) {
+		pr_info("Using DRAM BARs for memory map.\n");
+		xlp_init_mem_from_bars();
+	}
+	/* Calculate and setup wired entries for mapped kernel */
 	nlm_fixup_mem();
 }
 
 const char *get_system_type(void)
 {
-	return "Netlogic XLP Series";
+	switch (read_c0_prid() & 0xff00) {
+	case PRID_IMP_NETLOGIC_XLP2XX:
+		return "Broadcom XLPII Series";
+	default:
+		return "Netlogic XLP Series";
+	}
 }
 
 void __init prom_free_prom_memory(void)
@@ -97,12 +125,20 @@ void __init prom_free_prom_memory(void)
 
 void xlp_mmu_init(void)
 {
-	/* enable extended TLB and Large Fixed TLB */
-	write_c0_config6(read_c0_config6() | 0x24);
-
-	/* set page mask of Fixed TLB in config7 */
-	write_c0_config7(PM_DEFAULT_MASK >>
-		(13 + (ffz(PM_DEFAULT_MASK >> 13) / 2)));
+	u32 conf4;
+
+	if (cpu_is_xlpii()) {
+		/* XLPII series has extended pagesize in config 4 */
+		conf4 = read_c0_config4() & ~0x1f00u;
+		write_c0_config4(conf4 | ((PAGE_SHIFT - 10) / 2 << 8));
+	} else {
+		/* enable extended TLB and Large Fixed TLB */
+		write_c0_config6(read_c0_config6() | 0x24);
+
+		/* set page mask of extended Fixed TLB in config7 */
+		write_c0_config7(PM_DEFAULT_MASK >>
+			(13 + (ffz(PM_DEFAULT_MASK >> 13) / 2)));
+	}
 }
 
 void nlm_percpu_init(int hwcpuid)
diff --git a/arch/mips/netlogic/xlp/usb-init-xlp2.c b/arch/mips/netlogic/xlp/usb-init-xlp2.c
new file mode 100644
index 000000000000..36e9c22afc46
--- /dev/null
+++ b/arch/mips/netlogic/xlp/usb-init-xlp2.c
@@ -0,0 +1,218 @@
+/*
+ * Copyright (c) 2003-2013 Broadcom Corporation
+ * All Rights Reserved
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the Broadcom
+ * license below:
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in
+ *    the documentation and/or other materials provided with the
+ *    distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY BROADCOM ``AS IS'' AND ANY EXPRESS OR
+ * IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL BROADCOM OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+ * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE
+ * OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN
+ * IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/dma-mapping.h>
+#include <linux/kernel.h>
+#include <linux/delay.h>
+#include <linux/init.h>
+#include <linux/pci.h>
+#include <linux/platform_device.h>
+#include <linux/irq.h>
+
+#include <asm/netlogic/common.h>
+#include <asm/netlogic/haldefs.h>
+#include <asm/netlogic/xlp-hal/iomap.h>
+#include <asm/netlogic/xlp-hal/xlp.h>
+
+#define XLPII_USB3_CTL_0		0xc0
+#define XLPII_VAUXRST			BIT(0)
+#define XLPII_VCCRST			BIT(1)
+#define XLPII_NUM2PORT			9
+#define XLPII_NUM3PORT			13
+#define XLPII_RTUNEREQ			BIT(20)
+#define XLPII_MS_CSYSREQ		BIT(21)
+#define XLPII_XS_CSYSREQ		BIT(22)
+#define XLPII_RETENABLEN		BIT(23)
+#define XLPII_TX2RX			BIT(24)
+#define XLPII_XHCIREV			BIT(25)
+#define XLPII_ECCDIS			BIT(26)
+
+#define XLPII_USB3_INT_REG		0xc2
+#define XLPII_USB3_INT_MASK		0xc3
+
+#define XLPII_USB_PHY_TEST		0xc6
+#define XLPII_PRESET			BIT(0)
+#define XLPII_ATERESET			BIT(1)
+#define XLPII_LOOPEN			BIT(2)
+#define XLPII_TESTPDHSP			BIT(3)
+#define XLPII_TESTPDSSP			BIT(4)
+#define XLPII_TESTBURNIN		BIT(5)
+
+#define XLPII_USB_PHY_LOS_LV		0xc9
+#define XLPII_LOSLEV			0
+#define XLPII_LOSBIAS			5
+#define XLPII_SQRXTX			8
+#define XLPII_TXBOOST			11
+#define XLPII_RSLKSEL			16
+#define XLPII_FSEL			20
+
+#define XLPII_USB_RFCLK_REG		0xcc
+#define XLPII_VVLD			30
+
+#define nlm_read_usb_reg(b, r)		nlm_read_reg(b, r)
+#define nlm_write_usb_reg(b, r, v)	nlm_write_reg(b, r, v)
+
+#define nlm_xlpii_get_usb_pcibase(node, inst)		\
+	nlm_pcicfg_base(XLP2XX_IO_USB_OFFSET(node, inst))
+#define nlm_xlpii_get_usb_regbase(node, inst)		\
+	(nlm_xlpii_get_usb_pcibase(node, inst) + XLP_IO_PCI_HDRSZ)
+
+static void xlpii_usb_ack(struct irq_data *data)
+{
+	u64 port_addr;
+
+	switch (data->irq) {
+	case PIC_2XX_XHCI_0_IRQ:
+		port_addr = nlm_xlpii_get_usb_regbase(0, 1);
+		break;
+	case PIC_2XX_XHCI_1_IRQ:
+		port_addr = nlm_xlpii_get_usb_regbase(0, 2);
+		break;
+	case PIC_2XX_XHCI_2_IRQ:
+		port_addr = nlm_xlpii_get_usb_regbase(0, 3);
+		break;
+	default:
+		pr_err("No matching USB irq!\n");
+		return;
+	}
+	nlm_write_usb_reg(port_addr, XLPII_USB3_INT_REG, 0xffffffff);
+}
+
+static void nlm_xlpii_usb_hw_reset(int node, int port)
+{
+	u64 port_addr, xhci_base, pci_base;
+	void __iomem *corebase;
+	u32 val;
+
+	port_addr = nlm_xlpii_get_usb_regbase(node, port);
+
+	/* Set frequency */
+	val = nlm_read_usb_reg(port_addr, XLPII_USB_PHY_LOS_LV);
+	val &= ~(0x3f << XLPII_FSEL);
+	val |= (0x27 << XLPII_FSEL);
+	nlm_write_usb_reg(port_addr, XLPII_USB_PHY_LOS_LV, val);
+
+	val = nlm_read_usb_reg(port_addr, XLPII_USB_RFCLK_REG);
+	val |= (1 << XLPII_VVLD);
+	nlm_write_usb_reg(port_addr, XLPII_USB_RFCLK_REG, val);
+
+	/* PHY reset */
+	val = nlm_read_usb_reg(port_addr, XLPII_USB_PHY_TEST);
+	val &= (XLPII_ATERESET | XLPII_LOOPEN | XLPII_TESTPDHSP
+		| XLPII_TESTPDSSP | XLPII_TESTBURNIN);
+	nlm_write_usb_reg(port_addr, XLPII_USB_PHY_TEST, val);
+
+	/* Setup control register */
+	val =  XLPII_VAUXRST | XLPII_VCCRST | (1 << XLPII_NUM2PORT)
+		| (1 << XLPII_NUM3PORT) | XLPII_MS_CSYSREQ | XLPII_XS_CSYSREQ
+		| XLPII_RETENABLEN | XLPII_XHCIREV;
+	nlm_write_usb_reg(port_addr, XLPII_USB3_CTL_0, val);
+
+	/* Enable interrupts */
+	nlm_write_usb_reg(port_addr, XLPII_USB3_INT_MASK, 0x00000001);
+
+	/* Clear all interrupts */
+	nlm_write_usb_reg(port_addr, XLPII_USB3_INT_REG, 0xffffffff);
+
+	udelay(2000);
+
+	/* XHCI configuration at PCI mem */
+	pci_base = nlm_xlpii_get_usb_pcibase(node, port);
+	xhci_base = nlm_read_usb_reg(pci_base, 0x4) & ~0xf;
+	corebase = ioremap(xhci_base, 0x10000);
+	if (!corebase)
+		return;
+
+	writel(0x240002, corebase + 0xc2c0);
+	/* GCTL 0xc110 */
+	val = readl(corebase + 0xc110);
+	val &= ~(0x3 << 12);
+	val |= (1 << 12);
+	writel(val, corebase + 0xc110);
+	udelay(100);
+
+	/* PHYCFG 0xc200 */
+	val = readl(corebase + 0xc200);
+	val &= ~(1 << 6);
+	writel(val, corebase + 0xc200);
+	udelay(100);
+
+	/* PIPECTL 0xc2c0 */
+	val = readl(corebase + 0xc2c0);
+	val &= ~(1 << 17);
+	writel(val, corebase + 0xc2c0);
+
+	iounmap(corebase);
+}
+
+static int __init nlm_platform_xlpii_usb_init(void)
+{
+	if (!cpu_is_xlpii())
+		return 0;
+
+	pr_info("Initializing 2XX USB Interface\n");
+	nlm_xlpii_usb_hw_reset(0, 1);
+	nlm_xlpii_usb_hw_reset(0, 2);
+	nlm_xlpii_usb_hw_reset(0, 3);
+	nlm_set_pic_extra_ack(0, PIC_2XX_XHCI_0_IRQ, xlpii_usb_ack);
+	nlm_set_pic_extra_ack(0, PIC_2XX_XHCI_1_IRQ, xlpii_usb_ack);
+	nlm_set_pic_extra_ack(0, PIC_2XX_XHCI_2_IRQ, xlpii_usb_ack);
+
+	return 0;
+}
+
+arch_initcall(nlm_platform_xlpii_usb_init);
+
+static u64 xlp_usb_dmamask = ~(u32)0;
+
+/* Fixup IRQ for USB devices on XLP the SoC PCIe bus */
+static void nlm_usb_fixup_final(struct pci_dev *dev)
+{
+	dev->dev.dma_mask		= &xlp_usb_dmamask;
+	dev->dev.coherent_dma_mask	= DMA_BIT_MASK(32);
+	switch (dev->devfn) {
+	case 0x21:
+		dev->irq = PIC_2XX_XHCI_0_IRQ;
+		break;
+	case 0x22:
+		dev->irq = PIC_2XX_XHCI_1_IRQ;
+		break;
+	case 0x23:
+		dev->irq = PIC_2XX_XHCI_2_IRQ;
+		break;
+	}
+}
+
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_NETLOGIC, PCI_DEVICE_ID_NLM_XHCI,
+		nlm_usb_fixup_final);
diff --git a/arch/mips/netlogic/xlp/usb-init.c b/arch/mips/netlogic/xlp/usb-init.c
index ef3897ef0dc7..f8117985f0f8 100644
--- a/arch/mips/netlogic/xlp/usb-init.c
+++ b/arch/mips/netlogic/xlp/usb-init.c
@@ -75,8 +75,7 @@ static void nlm_usb_intr_en(int node, int port)
 	port_addr = nlm_get_usb_regbase(node, port);
 	val = nlm_read_usb_reg(port_addr, USB_INT_EN);
 	val = USB_CTRL_INTERRUPT_EN  | USB_OHCI_INTERRUPT_EN |
-		USB_OHCI_INTERRUPT1_EN | USB_CTRL_INTERRUPT_EN	|
-		USB_OHCI_INTERRUPT_EN | USB_OHCI_INTERRUPT2_EN;
+		USB_OHCI_INTERRUPT1_EN | USB_OHCI_INTERRUPT2_EN;
 	nlm_write_usb_reg(port_addr, USB_INT_EN, val);
 }
 
@@ -100,6 +99,9 @@ static void nlm_usb_hw_reset(int node, int port)
 
 static int __init nlm_platform_usb_init(void)
 {
+	if (cpu_is_xlpii())
+		return 0;
+
 	pr_info("Initializing USB Interface\n");
 	nlm_usb_hw_reset(0, 0);
 	nlm_usb_hw_reset(0, 3);
diff --git a/arch/mips/netlogic/xlp/wakeup.c b/arch/mips/netlogic/xlp/wakeup.c
index 0cce37cbffef..682d5638dc01 100644
--- a/arch/mips/netlogic/xlp/wakeup.c
+++ b/arch/mips/netlogic/xlp/wakeup.c
@@ -58,10 +58,12 @@ static int xlp_wakeup_core(uint64_t sysbase, int node, int core)
 
 	coremask = (1 << core);
 
-	/* Enable CPU clock */
-	value = nlm_read_sys_reg(sysbase, SYS_CORE_DFS_DIS_CTRL);
-	value &= ~coremask;
-	nlm_write_sys_reg(sysbase, SYS_CORE_DFS_DIS_CTRL, value);
+	/* Enable CPU clock in case of 8xx/3xx */
+	if (!cpu_is_xlpii()) {
+		value = nlm_read_sys_reg(sysbase, SYS_CORE_DFS_DIS_CTRL);
+		value &= ~coremask;
+		nlm_write_sys_reg(sysbase, SYS_CORE_DFS_DIS_CTRL, value);
+	}
 
 	/* Remove CPU Reset */
 	value = nlm_read_sys_reg(sysbase, SYS_CPU_RESET);
diff --git a/arch/mips/netlogic/xlr/fmn-config.c b/arch/mips/netlogic/xlr/fmn-config.c
index ed3bf0e3f309..c7622c6e5f67 100644
--- a/arch/mips/netlogic/xlr/fmn-config.c
+++ b/arch/mips/netlogic/xlr/fmn-config.c
@@ -36,6 +36,7 @@
 #include <linux/irq.h>
 #include <linux/interrupt.h>
 
+#include <asm/cpu.h>
 #include <asm/mipsregs.h>
 #include <asm/netlogic/xlr/fmn.h>
 #include <asm/netlogic/xlr/xlr.h>
@@ -187,7 +188,7 @@ void xlr_board_info_setup(void)
 	int processor_id, num_core;
 
 	num_core = hweight32(nlm_current_node()->coremask);
-	processor_id = read_c0_prid() & 0xff00;
+	processor_id = read_c0_prid() & PRID_IMP_MASK;
 
 	setup_cpu_fmninfo(cpu, num_core);
 	switch (processor_id) {
diff --git a/arch/mips/oprofile/common.c b/arch/mips/oprofile/common.c
index af763e838fdd..4d1736fc1955 100644
--- a/arch/mips/oprofile/common.c
+++ b/arch/mips/oprofile/common.c
@@ -12,6 +12,7 @@
 #include <linux/oprofile.h>
 #include <linux/smp.h>
 #include <asm/cpu-info.h>
+#include <asm/cpu-type.h>
 
 #include "op_impl.h"
 
@@ -33,7 +34,7 @@ static int op_mips_setup(void)
 	return 0;
 }
 
-static int op_mips_create_files(struct super_block *sb, struct dentry *root)
+static int op_mips_create_files(struct dentry *root)
 {
 	int i;
 
@@ -42,16 +43,16 @@ static int op_mips_create_files(struct super_block *sb, struct dentry *root)
 		char buf[4];
 
 		snprintf(buf, sizeof buf, "%d", i);
-		dir = oprofilefs_mkdir(sb, root, buf);
-
-		oprofilefs_create_ulong(sb, dir, "enabled", &ctr[i].enabled);
-		oprofilefs_create_ulong(sb, dir, "event", &ctr[i].event);
-		oprofilefs_create_ulong(sb, dir, "count", &ctr[i].count);
-		oprofilefs_create_ulong(sb, dir, "kernel", &ctr[i].kernel);
-		oprofilefs_create_ulong(sb, dir, "user", &ctr[i].user);
-		oprofilefs_create_ulong(sb, dir, "exl", &ctr[i].exl);
+		dir = oprofilefs_mkdir(root, buf);
+
+		oprofilefs_create_ulong(dir, "enabled", &ctr[i].enabled);
+		oprofilefs_create_ulong(dir, "event", &ctr[i].event);
+		oprofilefs_create_ulong(dir, "count", &ctr[i].count);
+		oprofilefs_create_ulong(dir, "kernel", &ctr[i].kernel);
+		oprofilefs_create_ulong(dir, "user", &ctr[i].user);
+		oprofilefs_create_ulong(dir, "exl", &ctr[i].exl);
 		/* Dummy.  */
-		oprofilefs_create_ulong(sb, dir, "unit_mask", &ctr[i].unit_mask);
+		oprofilefs_create_ulong(dir, "unit_mask", &ctr[i].unit_mask);
 	}
 
 	return 0;
diff --git a/arch/mips/pci/Makefile b/arch/mips/pci/Makefile
index c382042911dd..719e4557e22e 100644
--- a/arch/mips/pci/Makefile
+++ b/arch/mips/pci/Makefile
@@ -41,6 +41,7 @@ obj-$(CONFIG_SIBYTE_BCM1x80)	+= pci-bcm1480.o pci-bcm1480ht.o
 obj-$(CONFIG_SNI_RM)		+= fixup-sni.o ops-sni.o
 obj-$(CONFIG_LANTIQ)		+= fixup-lantiq.o
 obj-$(CONFIG_PCI_LANTIQ)	+= pci-lantiq.o ops-lantiq.o
+obj-$(CONFIG_SOC_RT3883)	+= pci-rt3883.o
 obj-$(CONFIG_TANBAC_TB0219)	+= fixup-tb0219.o
 obj-$(CONFIG_TANBAC_TB0226)	+= fixup-tb0226.o
 obj-$(CONFIG_TANBAC_TB0287)	+= fixup-tb0287.o
diff --git a/arch/mips/pci/pci-bcm1480.c b/arch/mips/pci/pci-bcm1480.c
index 44dd5aa2e36f..5ec2a7bae02c 100644
--- a/arch/mips/pci/pci-bcm1480.c
+++ b/arch/mips/pci/pci-bcm1480.c
@@ -39,6 +39,7 @@
 #include <linux/mm.h>
 #include <linux/console.h>
 #include <linux/tty.h>
+#include <linux/vt.h>
 
 #include <asm/sibyte/bcm1480_regs.h>
 #include <asm/sibyte/bcm1480_scd.h>
diff --git a/arch/mips/pci/pci-octeon.c b/arch/mips/pci/pci-octeon.c
index 95c2ea815cac..59cccd95688b 100644
--- a/arch/mips/pci/pci-octeon.c
+++ b/arch/mips/pci/pci-octeon.c
@@ -586,15 +586,16 @@ static int __init octeon_pci_setup(void)
 	else
 		octeon_dma_bar_type = OCTEON_DMA_BAR_TYPE_BIG;
 
-	/* PCI I/O and PCI MEM values */
-	set_io_port_base(OCTEON_PCI_IOSPACE_BASE);
-	ioport_resource.start = 0;
-	ioport_resource.end = OCTEON_PCI_IOSPACE_SIZE - 1;
 	if (!octeon_is_pci_host()) {
 		pr_notice("Not in host mode, PCI Controller not initialized\n");
 		return 0;
 	}
 
+	/* PCI I/O and PCI MEM values */
+	set_io_port_base(OCTEON_PCI_IOSPACE_BASE);
+	ioport_resource.start = 0;
+	ioport_resource.end = OCTEON_PCI_IOSPACE_SIZE - 1;
+
 	pr_notice("%s Octeon big bar support\n",
 		  (octeon_dma_bar_type ==
 		  OCTEON_DMA_BAR_TYPE_BIG) ? "Enabling" : "Disabling");
diff --git a/arch/mips/pci/pci-rt3883.c b/arch/mips/pci/pci-rt3883.c
new file mode 100644
index 000000000000..95c9d41382e7
--- /dev/null
+++ b/arch/mips/pci/pci-rt3883.c
@@ -0,0 +1,636 @@
+/*
+ *  Ralink RT3662/RT3883 SoC PCI support
+ *
+ *  Copyright (C) 2011-2013 Gabor Juhos <juhosg@openwrt.org>
+ *
+ *  Parts of this file are based on Ralink's 2.6.21 BSP
+ *
+ *  This program is free software; you can redistribute it and/or modify it
+ *  under the terms of the GNU General Public License version 2 as published
+ *  by the Free Software Foundation.
+ */
+
+#include <linux/types.h>
+#include <linux/pci.h>
+#include <linux/io.h>
+#include <linux/init.h>
+#include <linux/delay.h>
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_irq.h>
+#include <linux/of_pci.h>
+#include <linux/platform_device.h>
+
+#include <asm/mach-ralink/rt3883.h>
+#include <asm/mach-ralink/ralink_regs.h>
+
+#define RT3883_MEMORY_BASE		0x00000000
+#define RT3883_MEMORY_SIZE		0x02000000
+
+#define RT3883_PCI_REG_PCICFG		0x00
+#define   RT3883_PCICFG_P2P_BR_DEVNUM_M 0xf
+#define   RT3883_PCICFG_P2P_BR_DEVNUM_S 16
+#define   RT3883_PCICFG_PCIRST		BIT(1)
+#define RT3883_PCI_REG_PCIRAW		0x04
+#define RT3883_PCI_REG_PCIINT		0x08
+#define RT3883_PCI_REG_PCIENA		0x0c
+
+#define RT3883_PCI_REG_CFGADDR		0x20
+#define RT3883_PCI_REG_CFGDATA		0x24
+#define RT3883_PCI_REG_MEMBASE		0x28
+#define RT3883_PCI_REG_IOBASE		0x2c
+#define RT3883_PCI_REG_ARBCTL		0x80
+
+#define RT3883_PCI_REG_BASE(_x)		(0x1000 + (_x) * 0x1000)
+#define RT3883_PCI_REG_BAR0SETUP(_x)	(RT3883_PCI_REG_BASE((_x)) + 0x10)
+#define RT3883_PCI_REG_IMBASEBAR0(_x)	(RT3883_PCI_REG_BASE((_x)) + 0x18)
+#define RT3883_PCI_REG_ID(_x)		(RT3883_PCI_REG_BASE((_x)) + 0x30)
+#define RT3883_PCI_REG_CLASS(_x)	(RT3883_PCI_REG_BASE((_x)) + 0x34)
+#define RT3883_PCI_REG_SUBID(_x)	(RT3883_PCI_REG_BASE((_x)) + 0x38)
+#define RT3883_PCI_REG_STATUS(_x)	(RT3883_PCI_REG_BASE((_x)) + 0x50)
+
+#define RT3883_PCI_MODE_NONE	0
+#define RT3883_PCI_MODE_PCI	BIT(0)
+#define RT3883_PCI_MODE_PCIE	BIT(1)
+#define RT3883_PCI_MODE_BOTH	(RT3883_PCI_MODE_PCI | RT3883_PCI_MODE_PCIE)
+
+#define RT3883_PCI_IRQ_COUNT	32
+
+#define RT3883_P2P_BR_DEVNUM	1
+
+struct rt3883_pci_controller {
+	void __iomem *base;
+	spinlock_t lock;
+
+	struct device_node *intc_of_node;
+	struct irq_domain *irq_domain;
+
+	struct pci_controller pci_controller;
+	struct resource io_res;
+	struct resource mem_res;
+
+	bool pcie_ready;
+};
+
+static inline struct rt3883_pci_controller *
+pci_bus_to_rt3883_controller(struct pci_bus *bus)
+{
+	struct pci_controller *hose;
+
+	hose = (struct pci_controller *) bus->sysdata;
+	return container_of(hose, struct rt3883_pci_controller, pci_controller);
+}
+
+static inline u32 rt3883_pci_r32(struct rt3883_pci_controller *rpc,
+				 unsigned reg)
+{
+	return ioread32(rpc->base + reg);
+}
+
+static inline void rt3883_pci_w32(struct rt3883_pci_controller *rpc,
+				  u32 val, unsigned reg)
+{
+	iowrite32(val, rpc->base + reg);
+}
+
+static inline u32 rt3883_pci_get_cfgaddr(unsigned int bus, unsigned int slot,
+					 unsigned int func, unsigned int where)
+{
+	return (bus << 16) | (slot << 11) | (func << 8) | (where & 0xfc) |
+	       0x80000000;
+}
+
+static u32 rt3883_pci_read_cfg32(struct rt3883_pci_controller *rpc,
+			       unsigned bus, unsigned slot,
+			       unsigned func, unsigned reg)
+{
+	unsigned long flags;
+	u32 address;
+	u32 ret;
+
+	address = rt3883_pci_get_cfgaddr(bus, slot, func, reg);
+
+	spin_lock_irqsave(&rpc->lock, flags);
+	rt3883_pci_w32(rpc, address, RT3883_PCI_REG_CFGADDR);
+	ret = rt3883_pci_r32(rpc, RT3883_PCI_REG_CFGDATA);
+	spin_unlock_irqrestore(&rpc->lock, flags);
+
+	return ret;
+}
+
+static void rt3883_pci_write_cfg32(struct rt3883_pci_controller *rpc,
+				 unsigned bus, unsigned slot,
+				 unsigned func, unsigned reg, u32 val)
+{
+	unsigned long flags;
+	u32 address;
+
+	address = rt3883_pci_get_cfgaddr(bus, slot, func, reg);
+
+	spin_lock_irqsave(&rpc->lock, flags);
+	rt3883_pci_w32(rpc, address, RT3883_PCI_REG_CFGADDR);
+	rt3883_pci_w32(rpc, val, RT3883_PCI_REG_CFGDATA);
+	spin_unlock_irqrestore(&rpc->lock, flags);
+}
+
+static void rt3883_pci_irq_handler(unsigned int irq, struct irq_desc *desc)
+{
+	struct rt3883_pci_controller *rpc;
+	u32 pending;
+
+	rpc = irq_get_handler_data(irq);
+
+	pending = rt3883_pci_r32(rpc, RT3883_PCI_REG_PCIINT) &
+		  rt3883_pci_r32(rpc, RT3883_PCI_REG_PCIENA);
+
+	if (!pending) {
+		spurious_interrupt();
+		return;
+	}
+
+	while (pending) {
+		unsigned bit = __ffs(pending);
+
+		irq = irq_find_mapping(rpc->irq_domain, bit);
+		generic_handle_irq(irq);
+
+		pending &= ~BIT(bit);
+	}
+}
+
+static void rt3883_pci_irq_unmask(struct irq_data *d)
+{
+	struct rt3883_pci_controller *rpc;
+	u32 t;
+
+	rpc = irq_data_get_irq_chip_data(d);
+
+	t = rt3883_pci_r32(rpc, RT3883_PCI_REG_PCIENA);
+	rt3883_pci_w32(rpc, t | BIT(d->hwirq), RT3883_PCI_REG_PCIENA);
+	/* flush write */
+	rt3883_pci_r32(rpc, RT3883_PCI_REG_PCIENA);
+}
+
+static void rt3883_pci_irq_mask(struct irq_data *d)
+{
+	struct rt3883_pci_controller *rpc;
+	u32 t;
+
+	rpc = irq_data_get_irq_chip_data(d);
+
+	t = rt3883_pci_r32(rpc, RT3883_PCI_REG_PCIENA);
+	rt3883_pci_w32(rpc, t & ~BIT(d->hwirq), RT3883_PCI_REG_PCIENA);
+	/* flush write */
+	rt3883_pci_r32(rpc, RT3883_PCI_REG_PCIENA);
+}
+
+static struct irq_chip rt3883_pci_irq_chip = {
+	.name		= "RT3883 PCI",
+	.irq_mask	= rt3883_pci_irq_mask,
+	.irq_unmask	= rt3883_pci_irq_unmask,
+	.irq_mask_ack	= rt3883_pci_irq_mask,
+};
+
+static int rt3883_pci_irq_map(struct irq_domain *d, unsigned int irq,
+			      irq_hw_number_t hw)
+{
+	irq_set_chip_and_handler(irq, &rt3883_pci_irq_chip, handle_level_irq);
+	irq_set_chip_data(irq, d->host_data);
+
+	return 0;
+}
+
+static const struct irq_domain_ops rt3883_pci_irq_domain_ops = {
+	.map = rt3883_pci_irq_map,
+	.xlate = irq_domain_xlate_onecell,
+};
+
+static int rt3883_pci_irq_init(struct device *dev,
+			       struct rt3883_pci_controller *rpc)
+{
+	int irq;
+
+	irq = irq_of_parse_and_map(rpc->intc_of_node, 0);
+	if (irq == 0) {
+		dev_err(dev, "%s has no IRQ",
+			of_node_full_name(rpc->intc_of_node));
+		return -EINVAL;
+	}
+
+	/* disable all interrupts */
+	rt3883_pci_w32(rpc, 0, RT3883_PCI_REG_PCIENA);
+
+	rpc->irq_domain =
+		irq_domain_add_linear(rpc->intc_of_node, RT3883_PCI_IRQ_COUNT,
+				      &rt3883_pci_irq_domain_ops,
+				      rpc);
+	if (!rpc->irq_domain) {
+		dev_err(dev, "unable to add IRQ domain\n");
+		return -ENODEV;
+	}
+
+	irq_set_handler_data(irq, rpc);
+	irq_set_chained_handler(irq, rt3883_pci_irq_handler);
+
+	return 0;
+}
+
+static int rt3883_pci_config_read(struct pci_bus *bus, unsigned int devfn,
+				  int where, int size, u32 *val)
+{
+	struct rt3883_pci_controller *rpc;
+	unsigned long flags;
+	u32 address;
+	u32 data;
+
+	rpc = pci_bus_to_rt3883_controller(bus);
+
+	if (!rpc->pcie_ready && bus->number == 1)
+		return PCIBIOS_DEVICE_NOT_FOUND;
+
+	address = rt3883_pci_get_cfgaddr(bus->number, PCI_SLOT(devfn),
+					 PCI_FUNC(devfn), where);
+
+	spin_lock_irqsave(&rpc->lock, flags);
+	rt3883_pci_w32(rpc, address, RT3883_PCI_REG_CFGADDR);
+	data = rt3883_pci_r32(rpc, RT3883_PCI_REG_CFGDATA);
+	spin_unlock_irqrestore(&rpc->lock, flags);
+
+	switch (size) {
+	case 1:
+		*val = (data >> ((where & 3) << 3)) & 0xff;
+		break;
+	case 2:
+		*val = (data >> ((where & 3) << 3)) & 0xffff;
+		break;
+	case 4:
+		*val = data;
+		break;
+	}
+
+	return PCIBIOS_SUCCESSFUL;
+}
+
+static int rt3883_pci_config_write(struct pci_bus *bus, unsigned int devfn,
+				   int where, int size, u32 val)
+{
+	struct rt3883_pci_controller *rpc;
+	unsigned long flags;
+	u32 address;
+	u32 data;
+
+	rpc = pci_bus_to_rt3883_controller(bus);
+
+	if (!rpc->pcie_ready && bus->number == 1)
+		return PCIBIOS_DEVICE_NOT_FOUND;
+
+	address = rt3883_pci_get_cfgaddr(bus->number, PCI_SLOT(devfn),
+					 PCI_FUNC(devfn), where);
+
+	spin_lock_irqsave(&rpc->lock, flags);
+	rt3883_pci_w32(rpc, address, RT3883_PCI_REG_CFGADDR);
+	data = rt3883_pci_r32(rpc, RT3883_PCI_REG_CFGDATA);
+
+	switch (size) {
+	case 1:
+		data = (data & ~(0xff << ((where & 3) << 3))) |
+		       (val << ((where & 3) << 3));
+		break;
+	case 2:
+		data = (data & ~(0xffff << ((where & 3) << 3))) |
+		       (val << ((where & 3) << 3));
+		break;
+	case 4:
+		data = val;
+		break;
+	}
+
+	rt3883_pci_w32(rpc, data, RT3883_PCI_REG_CFGDATA);
+	spin_unlock_irqrestore(&rpc->lock, flags);
+
+	return PCIBIOS_SUCCESSFUL;
+}
+
+static struct pci_ops rt3883_pci_ops = {
+	.read	= rt3883_pci_config_read,
+	.write	= rt3883_pci_config_write,
+};
+
+static void rt3883_pci_preinit(struct rt3883_pci_controller *rpc, unsigned mode)
+{
+	u32 syscfg1;
+	u32 rstctrl;
+	u32 clkcfg1;
+	u32 t;
+
+	rstctrl = rt_sysc_r32(RT3883_SYSC_REG_RSTCTRL);
+	syscfg1 = rt_sysc_r32(RT3883_SYSC_REG_SYSCFG1);
+	clkcfg1 = rt_sysc_r32(RT3883_SYSC_REG_CLKCFG1);
+
+	if (mode & RT3883_PCI_MODE_PCIE) {
+		rstctrl |= RT3883_RSTCTRL_PCIE;
+		rt_sysc_w32(rstctrl, RT3883_SYSC_REG_RSTCTRL);
+
+		/* setup PCI PAD drive mode */
+		syscfg1 &= ~(0x30);
+		syscfg1 |= (2 << 4);
+		rt_sysc_w32(syscfg1, RT3883_SYSC_REG_SYSCFG1);
+
+		t = rt_sysc_r32(RT3883_SYSC_REG_PCIE_CLK_GEN0);
+		t &= ~BIT(31);
+		rt_sysc_w32(t, RT3883_SYSC_REG_PCIE_CLK_GEN0);
+
+		t = rt_sysc_r32(RT3883_SYSC_REG_PCIE_CLK_GEN1);
+		t &= 0x80ffffff;
+		rt_sysc_w32(t, RT3883_SYSC_REG_PCIE_CLK_GEN1);
+
+		t = rt_sysc_r32(RT3883_SYSC_REG_PCIE_CLK_GEN1);
+		t |= 0xa << 24;
+		rt_sysc_w32(t, RT3883_SYSC_REG_PCIE_CLK_GEN1);
+
+		t = rt_sysc_r32(RT3883_SYSC_REG_PCIE_CLK_GEN0);
+		t |= BIT(31);
+		rt_sysc_w32(t, RT3883_SYSC_REG_PCIE_CLK_GEN0);
+
+		msleep(50);
+
+		rstctrl &= ~RT3883_RSTCTRL_PCIE;
+		rt_sysc_w32(rstctrl, RT3883_SYSC_REG_RSTCTRL);
+	}
+
+	syscfg1 |= (RT3883_SYSCFG1_PCIE_RC_MODE | RT3883_SYSCFG1_PCI_HOST_MODE);
+
+	clkcfg1 &= ~(RT3883_CLKCFG1_PCI_CLK_EN | RT3883_CLKCFG1_PCIE_CLK_EN);
+
+	if (mode & RT3883_PCI_MODE_PCI) {
+		clkcfg1 |= RT3883_CLKCFG1_PCI_CLK_EN;
+		rstctrl &= ~RT3883_RSTCTRL_PCI;
+	}
+
+	if (mode & RT3883_PCI_MODE_PCIE) {
+		clkcfg1 |= RT3883_CLKCFG1_PCIE_CLK_EN;
+		rstctrl &= ~RT3883_RSTCTRL_PCIE;
+	}
+
+	rt_sysc_w32(syscfg1, RT3883_SYSC_REG_SYSCFG1);
+	rt_sysc_w32(rstctrl, RT3883_SYSC_REG_RSTCTRL);
+	rt_sysc_w32(clkcfg1, RT3883_SYSC_REG_CLKCFG1);
+
+	msleep(500);
+
+	/*
+	 * setup the device number of the P2P bridge
+	 * and de-assert the reset line
+	 */
+	t = (RT3883_P2P_BR_DEVNUM << RT3883_PCICFG_P2P_BR_DEVNUM_S);
+	rt3883_pci_w32(rpc, t, RT3883_PCI_REG_PCICFG);
+
+	/* flush write */
+	rt3883_pci_r32(rpc, RT3883_PCI_REG_PCICFG);
+	msleep(500);
+
+	if (mode & RT3883_PCI_MODE_PCIE) {
+		msleep(500);
+
+		t = rt3883_pci_r32(rpc, RT3883_PCI_REG_STATUS(1));
+
+		rpc->pcie_ready = t & BIT(0);
+
+		if (!rpc->pcie_ready) {
+			/* reset the PCIe block */
+			t = rt_sysc_r32(RT3883_SYSC_REG_RSTCTRL);
+			t |= RT3883_RSTCTRL_PCIE;
+			rt_sysc_w32(t, RT3883_SYSC_REG_RSTCTRL);
+			t &= ~RT3883_RSTCTRL_PCIE;
+			rt_sysc_w32(t, RT3883_SYSC_REG_RSTCTRL);
+
+			/* turn off PCIe clock */
+			t = rt_sysc_r32(RT3883_SYSC_REG_CLKCFG1);
+			t &= ~RT3883_CLKCFG1_PCIE_CLK_EN;
+			rt_sysc_w32(t, RT3883_SYSC_REG_CLKCFG1);
+
+			t = rt_sysc_r32(RT3883_SYSC_REG_PCIE_CLK_GEN0);
+			t &= ~0xf000c080;
+			rt_sysc_w32(t, RT3883_SYSC_REG_PCIE_CLK_GEN0);
+		}
+	}
+
+	/* enable PCI arbiter */
+	rt3883_pci_w32(rpc, 0x79, RT3883_PCI_REG_ARBCTL);
+}
+
+static int rt3883_pci_probe(struct platform_device *pdev)
+{
+	struct rt3883_pci_controller *rpc;
+	struct device *dev = &pdev->dev;
+	struct device_node *np = dev->of_node;
+	struct resource *res;
+	struct device_node *child;
+	u32 val;
+	int err;
+	int mode;
+
+	rpc = devm_kzalloc(dev, sizeof(*rpc), GFP_KERNEL);
+	if (!rpc)
+		return -ENOMEM;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!res)
+		return -EINVAL;
+
+	rpc->base = devm_ioremap_resource(dev, res);
+	if (IS_ERR(rpc->base))
+		return PTR_ERR(rpc->base);
+
+	/* find the interrupt controller child node */
+	for_each_child_of_node(np, child) {
+		if (of_get_property(child, "interrupt-controller", NULL) &&
+		    of_node_get(child)) {
+			rpc->intc_of_node = child;
+			break;
+		}
+	}
+
+	if (!rpc->intc_of_node) {
+		dev_err(dev, "%s has no %s child node",
+			of_node_full_name(rpc->intc_of_node),
+			"interrupt controller");
+		return -EINVAL;
+	}
+
+	/* find the PCI host bridge child node */
+	for_each_child_of_node(np, child) {
+		if (child->type &&
+		    of_node_cmp(child->type, "pci") == 0 &&
+		    of_node_get(child)) {
+			rpc->pci_controller.of_node = child;
+			break;
+		}
+	}
+
+	if (!rpc->pci_controller.of_node) {
+		dev_err(dev, "%s has no %s child node",
+			of_node_full_name(rpc->intc_of_node),
+			"PCI host bridge");
+		err = -EINVAL;
+		goto err_put_intc_node;
+	}
+
+	mode = RT3883_PCI_MODE_NONE;
+	for_each_available_child_of_node(rpc->pci_controller.of_node, child) {
+		int devfn;
+
+		if (!child->type ||
+		    of_node_cmp(child->type, "pci") != 0)
+			continue;
+
+		devfn = of_pci_get_devfn(child);
+		if (devfn < 0)
+			continue;
+
+		switch (PCI_SLOT(devfn)) {
+		case 1:
+			mode |= RT3883_PCI_MODE_PCIE;
+			break;
+
+		case 17:
+		case 18:
+			mode |= RT3883_PCI_MODE_PCI;
+			break;
+		}
+	}
+
+	if (mode == RT3883_PCI_MODE_NONE) {
+		dev_err(dev, "unable to determine PCI mode\n");
+		err = -EINVAL;
+		goto err_put_hb_node;
+	}
+
+	dev_info(dev, "mode:%s%s\n",
+		 (mode & RT3883_PCI_MODE_PCI) ? " PCI" : "",
+		 (mode & RT3883_PCI_MODE_PCIE) ? " PCIe" : "");
+
+	rt3883_pci_preinit(rpc, mode);
+
+	rpc->pci_controller.pci_ops = &rt3883_pci_ops;
+	rpc->pci_controller.io_resource = &rpc->io_res;
+	rpc->pci_controller.mem_resource = &rpc->mem_res;
+
+	/* Load PCI I/O and memory resources from DT */
+	pci_load_of_ranges(&rpc->pci_controller,
+			   rpc->pci_controller.of_node);
+
+	rt3883_pci_w32(rpc, rpc->mem_res.start, RT3883_PCI_REG_MEMBASE);
+	rt3883_pci_w32(rpc, rpc->io_res.start, RT3883_PCI_REG_IOBASE);
+
+	ioport_resource.start = rpc->io_res.start;
+	ioport_resource.end = rpc->io_res.end;
+
+	/* PCI */
+	rt3883_pci_w32(rpc, 0x03ff0000, RT3883_PCI_REG_BAR0SETUP(0));
+	rt3883_pci_w32(rpc, RT3883_MEMORY_BASE, RT3883_PCI_REG_IMBASEBAR0(0));
+	rt3883_pci_w32(rpc, 0x08021814, RT3883_PCI_REG_ID(0));
+	rt3883_pci_w32(rpc, 0x00800001, RT3883_PCI_REG_CLASS(0));
+	rt3883_pci_w32(rpc, 0x28801814, RT3883_PCI_REG_SUBID(0));
+
+	/* PCIe */
+	rt3883_pci_w32(rpc, 0x03ff0000, RT3883_PCI_REG_BAR0SETUP(1));
+	rt3883_pci_w32(rpc, RT3883_MEMORY_BASE, RT3883_PCI_REG_IMBASEBAR0(1));
+	rt3883_pci_w32(rpc, 0x08021814, RT3883_PCI_REG_ID(1));
+	rt3883_pci_w32(rpc, 0x06040001, RT3883_PCI_REG_CLASS(1));
+	rt3883_pci_w32(rpc, 0x28801814, RT3883_PCI_REG_SUBID(1));
+
+	err = rt3883_pci_irq_init(dev, rpc);
+	if (err)
+		goto err_put_hb_node;
+
+	/* PCIe */
+	val = rt3883_pci_read_cfg32(rpc, 0, 0x01, 0, PCI_COMMAND);
+	val |= PCI_COMMAND_IO | PCI_COMMAND_MEMORY | PCI_COMMAND_MASTER;
+	rt3883_pci_write_cfg32(rpc, 0, 0x01, 0, PCI_COMMAND, val);
+
+	/* PCI */
+	val = rt3883_pci_read_cfg32(rpc, 0, 0x00, 0, PCI_COMMAND);
+	val |= PCI_COMMAND_IO | PCI_COMMAND_MEMORY | PCI_COMMAND_MASTER;
+	rt3883_pci_write_cfg32(rpc, 0, 0x00, 0, PCI_COMMAND, val);
+
+	if (mode == RT3883_PCI_MODE_PCIE) {
+		rt3883_pci_w32(rpc, 0x03ff0001, RT3883_PCI_REG_BAR0SETUP(0));
+		rt3883_pci_w32(rpc, 0x03ff0001, RT3883_PCI_REG_BAR0SETUP(1));
+
+		rt3883_pci_write_cfg32(rpc, 0, RT3883_P2P_BR_DEVNUM, 0,
+				       PCI_BASE_ADDRESS_0,
+				       RT3883_MEMORY_BASE);
+		/* flush write */
+		rt3883_pci_read_cfg32(rpc, 0, RT3883_P2P_BR_DEVNUM, 0,
+				      PCI_BASE_ADDRESS_0);
+	} else {
+		rt3883_pci_write_cfg32(rpc, 0, RT3883_P2P_BR_DEVNUM, 0,
+				       PCI_IO_BASE, 0x00000101);
+	}
+
+	register_pci_controller(&rpc->pci_controller);
+
+	return 0;
+
+err_put_hb_node:
+	of_node_put(rpc->pci_controller.of_node);
+err_put_intc_node:
+	of_node_put(rpc->intc_of_node);
+	return err;
+}
+
+int __init pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+{
+	struct of_irq dev_irq;
+	int err;
+	int irq;
+
+	err = of_irq_map_pci(dev, &dev_irq);
+	if (err) {
+		pr_err("pci %s: unable to get irq map, err=%d\n",
+		       pci_name((struct pci_dev *) dev), err);
+		return 0;
+	}
+
+	irq = irq_create_of_mapping(dev_irq.controller,
+				    dev_irq.specifier,
+				    dev_irq.size);
+
+	if (irq == 0)
+		pr_crit("pci %s: no irq found for pin %u\n",
+			pci_name((struct pci_dev *) dev), pin);
+	else
+		pr_info("pci %s: using irq %d for pin %u\n",
+			pci_name((struct pci_dev *) dev), irq, pin);
+
+	return irq;
+}
+
+int pcibios_plat_dev_init(struct pci_dev *dev)
+{
+	return 0;
+}
+
+static const struct of_device_id rt3883_pci_ids[] = {
+	{ .compatible = "ralink,rt3883-pci" },
+	{},
+};
+MODULE_DEVICE_TABLE(of, rt3883_pci_ids);
+
+static struct platform_driver rt3883_pci_driver = {
+	.probe = rt3883_pci_probe,
+	.driver = {
+		.name = "rt3883-pci",
+		.owner = THIS_MODULE,
+		.of_match_table = of_match_ptr(rt3883_pci_ids),
+	},
+};
+
+static int __init rt3883_pci_init(void)
+{
+	return platform_driver_register(&rt3883_pci_driver);
+}
+
+postcore_initcall(rt3883_pci_init);
diff --git a/arch/mips/pci/pci.c b/arch/mips/pci/pci.c
index 594e60d6a43b..33e7aa52d9c4 100644
--- a/arch/mips/pci/pci.c
+++ b/arch/mips/pci/pci.c
@@ -113,7 +113,6 @@ static void pcibios_scanbus(struct pci_controller *hose)
 		if (!pci_has_flag(PCI_PROBE_ONLY)) {
 			pci_bus_size_bridges(bus);
 			pci_bus_assign_resources(bus);
-			pci_enable_bridges(bus);
 		}
 	}
 }
diff --git a/arch/mips/powertv/Kconfig b/arch/mips/powertv/Kconfig
index 1a1b03ea6398..dd91fbacbcba 100644
--- a/arch/mips/powertv/Kconfig
+++ b/arch/mips/powertv/Kconfig
@@ -1,14 +1,7 @@
-config BOOTLOADER_DRIVER
-	bool "PowerTV Bootloader Driver Support"
-	default n
-	depends on POWERTV
-	help
-	  Use this option if you want to load bootloader driver.
-
 config BOOTLOADER_FAMILY
 	string "POWERTV Bootloader Family string"
 	default "85"
-	depends on POWERTV && !BOOTLOADER_DRIVER
+	depends on POWERTV
 	help
 	  This value should be specified when the bootloader driver is disabled
 	  and must be exactly two characters long. Families supported are:
diff --git a/arch/mips/powertv/asic/asic_devices.c b/arch/mips/powertv/asic/asic_devices.c
index 0238af1ba503..8380605d597d 100644
--- a/arch/mips/powertv/asic/asic_devices.c
+++ b/arch/mips/powertv/asic/asic_devices.c
@@ -147,20 +147,10 @@ static __init noinline void platform_set_family(void)
 	if (check_forcefamily(forced_family) == 0)
 		bootldr_family = BOOTLDRFAMILY(forced_family[0],
 			forced_family[1]);
-	else {
-
-#ifdef CONFIG_BOOTLOADER_DRIVER
-		bootldr_family = (unsigned short) kbldr_GetSWFamily();
-#else
-#if defined(CONFIG_BOOTLOADER_FAMILY)
+	else
 		bootldr_family = (unsigned short) BOOTLDRFAMILY(
 			CONFIG_BOOTLOADER_FAMILY[0],
 			CONFIG_BOOTLOADER_FAMILY[1]);
-#else
-#error "Unknown Bootloader Family"
-#endif
-#endif
-	}
 
 	pr_info("Bootloader Family = 0x%04X\n", bootldr_family);
 
diff --git a/arch/mips/powertv/init.c b/arch/mips/powertv/init.c
index a01baff52cae..498926377e51 100644
--- a/arch/mips/powertv/init.c
+++ b/arch/mips/powertv/init.c
@@ -87,8 +87,4 @@ void __init prom_init(void)
 
 	configure_platform();
 	prom_meminit();
-
-#ifndef CONFIG_BOOTLOADER_DRIVER
-	pr_info("\nBootloader driver isn't loaded...\n");
-#endif
 }
diff --git a/arch/mips/powertv/reset.c b/arch/mips/powertv/reset.c
index 0007652cb774..11c32fbf2784 100644
--- a/arch/mips/powertv/reset.c
+++ b/arch/mips/powertv/reset.c
@@ -21,24 +21,12 @@
 #include <linux/io.h>
 #include <asm/reboot.h>			/* Not included by linux/reboot.h */
 
-#ifdef CONFIG_BOOTLOADER_DRIVER
-#include <asm/mach-powertv/kbldr.h>
-#endif
-
 #include <asm/mach-powertv/asic_regs.h>
 #include "reset.h"
 
 static void mips_machine_restart(char *command)
 {
-#ifdef CONFIG_BOOTLOADER_DRIVER
-	/*
-	 * Call the bootloader's reset function to ensure
-	 * that persistent data is flushed before hard reset
-	 */
-	kbldr_SetCauseAndReset();
-#else
 	writel(0x1, asic_reg_addr(watchdog));
-#endif
 }
 
 void mips_reboot_setup(void)
diff --git a/arch/mips/ralink/Kconfig b/arch/mips/ralink/Kconfig
index 026e823d871d..424f03496d14 100644
--- a/arch/mips/ralink/Kconfig
+++ b/arch/mips/ralink/Kconfig
@@ -1,5 +1,12 @@
 if RALINK
 
+config CLKEVT_RT3352
+	bool
+	depends on SOC_RT305X || SOC_MT7620
+	default y
+	select CLKSRC_OF
+	select CLKSRC_MMIO
+
 choice
 	prompt "Ralink SoC selection"
 	default SOC_RT305X
@@ -19,9 +26,12 @@ choice
 		bool "RT3883"
 		select USB_ARCH_HAS_OHCI
 		select USB_ARCH_HAS_EHCI
+		select HW_HAS_PCI
 
 	config SOC_MT7620
 		bool "MT7620"
+		select USB_ARCH_HAS_OHCI
+		select USB_ARCH_HAS_EHCI
 
 endchoice
 
diff --git a/arch/mips/ralink/Makefile b/arch/mips/ralink/Makefile
index 38cf1a880aaa..98ae349827be 100644
--- a/arch/mips/ralink/Makefile
+++ b/arch/mips/ralink/Makefile
@@ -6,7 +6,9 @@
 # Copyright (C) 2009-2011 Gabor Juhos <juhosg@openwrt.org>
 # Copyright (C) 2013 John Crispin <blogic@openwrt.org>
 
-obj-y := prom.o of.o reset.o clk.o irq.o
+obj-y := prom.o of.o reset.o clk.o irq.o timer.o
+
+obj-$(CONFIG_CLKEVT_RT3352) += cevt-rt3352.o
 
 obj-$(CONFIG_SOC_RT288X) += rt288x.o
 obj-$(CONFIG_SOC_RT305X) += rt305x.o
diff --git a/arch/mips/ralink/Platform b/arch/mips/ralink/Platform
index cda4b6645c50..6d9c8c499f98 100644
--- a/arch/mips/ralink/Platform
+++ b/arch/mips/ralink/Platform
@@ -26,3 +26,4 @@ cflags-$(CONFIG_SOC_RT3883)	+= -I$(srctree)/arch/mips/include/asm/mach-ralink/rt
 # Ralink MT7620
 #
 load-$(CONFIG_SOC_MT7620)	+= 0xffffffff80000000
+cflags-$(CONFIG_SOC_MT7620)	+= -I$(srctree)/arch/mips/include/asm/mach-ralink/mt7620
diff --git a/arch/mips/ralink/cevt-rt3352.c b/arch/mips/ralink/cevt-rt3352.c
new file mode 100644
index 000000000000..cc17566d1934
--- /dev/null
+++ b/arch/mips/ralink/cevt-rt3352.c
@@ -0,0 +1,145 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 2013 by John Crispin <blogic@openwrt.org>
+ */
+
+#include <linux/clockchips.h>
+#include <linux/clocksource.h>
+#include <linux/interrupt.h>
+#include <linux/reset.h>
+#include <linux/init.h>
+#include <linux/time.h>
+#include <linux/of.h>
+#include <linux/of_irq.h>
+#include <linux/of_address.h>
+
+#include <asm/mach-ralink/ralink_regs.h>
+
+#define SYSTICK_FREQ		(50 * 1000)
+
+#define SYSTICK_CONFIG		0x00
+#define SYSTICK_COMPARE		0x04
+#define SYSTICK_COUNT		0x08
+
+/* route systick irq to mips irq 7 instead of the r4k-timer */
+#define CFG_EXT_STK_EN		0x2
+/* enable the counter */
+#define CFG_CNT_EN		0x1
+
+struct systick_device {
+	void __iomem *membase;
+	struct clock_event_device dev;
+	int irq_requested;
+	int freq_scale;
+};
+
+static void systick_set_clock_mode(enum clock_event_mode mode,
+				struct clock_event_device *evt);
+
+static int systick_next_event(unsigned long delta,
+				struct clock_event_device *evt)
+{
+	struct systick_device *sdev;
+	u32 count;
+
+	sdev = container_of(evt, struct systick_device, dev);
+	count = ioread32(sdev->membase + SYSTICK_COUNT);
+	count = (count + delta) % SYSTICK_FREQ;
+	iowrite32(count + delta, sdev->membase + SYSTICK_COMPARE);
+
+	return 0;
+}
+
+static void systick_event_handler(struct clock_event_device *dev)
+{
+	/* noting to do here */
+}
+
+static irqreturn_t systick_interrupt(int irq, void *dev_id)
+{
+	struct clock_event_device *dev = (struct clock_event_device *) dev_id;
+
+	dev->event_handler(dev);
+
+	return IRQ_HANDLED;
+}
+
+static struct systick_device systick = {
+	.dev = {
+		/*
+		 * cevt-r4k uses 300, make sure systick
+		 * gets used if available
+		 */
+		.rating		= 310,
+		.features	= CLOCK_EVT_FEAT_ONESHOT,
+		.set_next_event	= systick_next_event,
+		.set_mode	= systick_set_clock_mode,
+		.event_handler	= systick_event_handler,
+	},
+};
+
+static struct irqaction systick_irqaction = {
+	.handler = systick_interrupt,
+	.flags = IRQF_PERCPU | IRQF_TIMER,
+	.dev_id = &systick.dev,
+};
+
+static void systick_set_clock_mode(enum clock_event_mode mode,
+				struct clock_event_device *evt)
+{
+	struct systick_device *sdev;
+
+	sdev = container_of(evt, struct systick_device, dev);
+
+	switch (mode) {
+	case CLOCK_EVT_MODE_ONESHOT:
+		if (!sdev->irq_requested)
+			setup_irq(systick.dev.irq, &systick_irqaction);
+		sdev->irq_requested = 1;
+		iowrite32(CFG_EXT_STK_EN | CFG_CNT_EN,
+				systick.membase + SYSTICK_CONFIG);
+		break;
+
+	case CLOCK_EVT_MODE_SHUTDOWN:
+		if (sdev->irq_requested)
+			free_irq(systick.dev.irq, &systick_irqaction);
+		sdev->irq_requested = 0;
+		iowrite32(0, systick.membase + SYSTICK_CONFIG);
+		break;
+
+	default:
+		pr_err("%s: Unhandeled mips clock_mode\n", systick.dev.name);
+		break;
+	}
+}
+
+static void __init ralink_systick_init(struct device_node *np)
+{
+	systick.membase = of_iomap(np, 0);
+	if (!systick.membase)
+		return;
+
+	systick_irqaction.name = np->name;
+	systick.dev.name = np->name;
+	clockevents_calc_mult_shift(&systick.dev, SYSTICK_FREQ, 60);
+	systick.dev.max_delta_ns = clockevent_delta2ns(0x7fff, &systick.dev);
+	systick.dev.min_delta_ns = clockevent_delta2ns(0x3, &systick.dev);
+	systick.dev.irq = irq_of_parse_and_map(np, 0);
+	if (!systick.dev.irq) {
+		pr_err("%s: request_irq failed", np->name);
+		return;
+	}
+
+	clocksource_mmio_init(systick.membase + SYSTICK_COUNT, np->name,
+			SYSTICK_FREQ, 301, 16, clocksource_mmio_readl_up);
+
+	clockevents_register_device(&systick.dev);
+
+	pr_info("%s: runing - mult: %d, shift: %d\n",
+			np->name, systick.dev.mult, systick.dev.shift);
+}
+
+CLOCKSOURCE_OF_DECLARE(systick, "ralink,cevt-systick", ralink_systick_init);
diff --git a/arch/mips/ralink/clk.c b/arch/mips/ralink/clk.c
index 8dfa22ff300b..bba0cdfd83bc 100644
--- a/arch/mips/ralink/clk.c
+++ b/arch/mips/ralink/clk.c
@@ -69,4 +69,5 @@ void __init plat_time_init(void)
 	pr_info("CPU Clock: %ldMHz\n", clk_get_rate(clk) / 1000000);
 	mips_hpt_frequency = clk_get_rate(clk) / 2;
 	clk_put(clk);
+	clocksource_of_init();
 }
diff --git a/arch/mips/ralink/common.h b/arch/mips/ralink/common.h
index 83144c3fc5ac..42dfd6100a2d 100644
--- a/arch/mips/ralink/common.h
+++ b/arch/mips/ralink/common.h
@@ -46,6 +46,8 @@ extern void ralink_of_remap(void);
 extern void ralink_clk_init(void);
 extern void ralink_clk_add(const char *dev, unsigned long rate);
 
+extern void ralink_rst_init(void);
+
 extern void prom_soc_init(struct ralink_soc_info *soc_info);
 
 __iomem void *plat_of_remap_node(const char *node);
diff --git a/arch/mips/ralink/mt7620.c b/arch/mips/ralink/mt7620.c
index 0018b1a661f6..d217509e5300 100644
--- a/arch/mips/ralink/mt7620.c
+++ b/arch/mips/ralink/mt7620.c
@@ -23,9 +23,6 @@
 /* does the board have sdram or ddram */
 static int dram_type;
 
-/* the pll dividers */
-static u32 mt7620_clk_divider[] = { 2, 3, 4, 8 };
-
 static struct ralink_pinmux_grp mode_mux[] = {
 	{
 		.name = "i2c",
@@ -140,34 +137,189 @@ struct ralink_pinmux rt_gpio_pinmux = {
 	.uart_mask = MT7620_GPIO_MODE_UART0_MASK,
 };
 
-void __init ralink_clk_init(void)
+static __init u32
+mt7620_calc_rate(u32 ref_rate, u32 mul, u32 div)
 {
-	unsigned long cpu_rate, sys_rate;
-	u32 c0 = rt_sysc_r32(SYSC_REG_CPLL_CONFIG0);
-	u32 c1 = rt_sysc_r32(SYSC_REG_CPLL_CONFIG1);
-	u32 swconfig = (c0 >> CPLL_SW_CONFIG_SHIFT) & CPLL_SW_CONFIG_MASK;
-	u32 cpu_clk = (c1 >> CPLL_CPU_CLK_SHIFT) & CPLL_CPU_CLK_MASK;
-
-	if (cpu_clk) {
-		cpu_rate = 480000000;
-	} else if (!swconfig) {
-		cpu_rate = 600000000;
-	} else {
-		u32 m = (c0 >> CPLL_MULT_RATIO_SHIFT) & CPLL_MULT_RATIO;
-		u32 d = (c0 >> CPLL_DIV_RATIO_SHIFT) & CPLL_DIV_RATIO;
+	u64 t;
 
-		cpu_rate = ((40 * (m + 24)) / mt7620_clk_divider[d]) * 1000000;
-	}
+	t = ref_rate;
+	t *= mul;
+	do_div(t, div);
+
+	return t;
+}
+
+#define MHZ(x)		((x) * 1000 * 1000)
+
+static __init unsigned long
+mt7620_get_xtal_rate(void)
+{
+	u32 reg;
+
+	reg = rt_sysc_r32(SYSC_REG_SYSTEM_CONFIG0);
+	if (reg & SYSCFG0_XTAL_FREQ_SEL)
+		return MHZ(40);
+
+	return MHZ(20);
+}
+
+static __init unsigned long
+mt7620_get_periph_rate(unsigned long xtal_rate)
+{
+	u32 reg;
+
+	reg = rt_sysc_r32(SYSC_REG_CLKCFG0);
+	if (reg & CLKCFG0_PERI_CLK_SEL)
+		return xtal_rate;
+
+	return MHZ(40);
+}
+
+static const u32 mt7620_clk_divider[] __initconst = { 2, 3, 4, 8 };
+
+static __init unsigned long
+mt7620_get_cpu_pll_rate(unsigned long xtal_rate)
+{
+	u32 reg;
+	u32 mul;
+	u32 div;
+
+	reg = rt_sysc_r32(SYSC_REG_CPLL_CONFIG0);
+	if (reg & CPLL_CFG0_BYPASS_REF_CLK)
+		return xtal_rate;
+
+	if ((reg & CPLL_CFG0_SW_CFG) == 0)
+		return MHZ(600);
+
+	mul = (reg >> CPLL_CFG0_PLL_MULT_RATIO_SHIFT) &
+	      CPLL_CFG0_PLL_MULT_RATIO_MASK;
+	mul += 24;
+	if (reg & CPLL_CFG0_LC_CURFCK)
+		mul *= 2;
+
+	div = (reg >> CPLL_CFG0_PLL_DIV_RATIO_SHIFT) &
+	      CPLL_CFG0_PLL_DIV_RATIO_MASK;
+
+	WARN_ON(div >= ARRAY_SIZE(mt7620_clk_divider));
+
+	return mt7620_calc_rate(xtal_rate, mul, mt7620_clk_divider[div]);
+}
+
+static __init unsigned long
+mt7620_get_pll_rate(unsigned long xtal_rate, unsigned long cpu_pll_rate)
+{
+	u32 reg;
+
+	reg = rt_sysc_r32(SYSC_REG_CPLL_CONFIG1);
+	if (reg & CPLL_CFG1_CPU_AUX1)
+		return xtal_rate;
+
+	if (reg & CPLL_CFG1_CPU_AUX0)
+		return MHZ(480);
 
+	return cpu_pll_rate;
+}
+
+static __init unsigned long
+mt7620_get_cpu_rate(unsigned long pll_rate)
+{
+	u32 reg;
+	u32 mul;
+	u32 div;
+
+	reg = rt_sysc_r32(SYSC_REG_CPU_SYS_CLKCFG);
+
+	mul = reg & CPU_SYS_CLKCFG_CPU_FFRAC_MASK;
+	div = (reg >> CPU_SYS_CLKCFG_CPU_FDIV_SHIFT) &
+	      CPU_SYS_CLKCFG_CPU_FDIV_MASK;
+
+	return mt7620_calc_rate(pll_rate, mul, div);
+}
+
+static const u32 mt7620_ocp_dividers[16] __initconst = {
+	[CPU_SYS_CLKCFG_OCP_RATIO_2] = 2,
+	[CPU_SYS_CLKCFG_OCP_RATIO_3] = 3,
+	[CPU_SYS_CLKCFG_OCP_RATIO_4] = 4,
+	[CPU_SYS_CLKCFG_OCP_RATIO_5] = 5,
+	[CPU_SYS_CLKCFG_OCP_RATIO_10] = 10,
+};
+
+static __init unsigned long
+mt7620_get_dram_rate(unsigned long pll_rate)
+{
 	if (dram_type == SYSCFG0_DRAM_TYPE_SDRAM)
-		sys_rate = cpu_rate / 4;
-	else
-		sys_rate = cpu_rate / 3;
+		return pll_rate / 4;
+
+	return pll_rate / 3;
+}
+
+static __init unsigned long
+mt7620_get_sys_rate(unsigned long cpu_rate)
+{
+	u32 reg;
+	u32 ocp_ratio;
+	u32 div;
+
+	reg = rt_sysc_r32(SYSC_REG_CPU_SYS_CLKCFG);
+
+	ocp_ratio = (reg >> CPU_SYS_CLKCFG_OCP_RATIO_SHIFT) &
+		    CPU_SYS_CLKCFG_OCP_RATIO_MASK;
+
+	if (WARN_ON(ocp_ratio >= ARRAY_SIZE(mt7620_ocp_dividers)))
+		return cpu_rate;
+
+	div = mt7620_ocp_dividers[ocp_ratio];
+	if (WARN(!div, "invalid divider for OCP ratio %u", ocp_ratio))
+		return cpu_rate;
+
+	return cpu_rate / div;
+}
+
+void __init ralink_clk_init(void)
+{
+	unsigned long xtal_rate;
+	unsigned long cpu_pll_rate;
+	unsigned long pll_rate;
+	unsigned long cpu_rate;
+	unsigned long sys_rate;
+	unsigned long dram_rate;
+	unsigned long periph_rate;
+
+	xtal_rate = mt7620_get_xtal_rate();
+
+	cpu_pll_rate = mt7620_get_cpu_pll_rate(xtal_rate);
+	pll_rate = mt7620_get_pll_rate(xtal_rate, cpu_pll_rate);
+
+	cpu_rate = mt7620_get_cpu_rate(pll_rate);
+	dram_rate = mt7620_get_dram_rate(pll_rate);
+	sys_rate = mt7620_get_sys_rate(cpu_rate);
+	periph_rate = mt7620_get_periph_rate(xtal_rate);
+
+#define RFMT(label)	label ":%lu.%03luMHz "
+#define RINT(x)		((x) / 1000000)
+#define RFRAC(x)	(((x) / 1000) % 1000)
+
+	pr_debug(RFMT("XTAL") RFMT("CPU_PLL") RFMT("PLL"),
+		 RINT(xtal_rate), RFRAC(xtal_rate),
+		 RINT(cpu_pll_rate), RFRAC(cpu_pll_rate),
+		 RINT(pll_rate), RFRAC(pll_rate));
+
+	pr_debug(RFMT("CPU") RFMT("DRAM") RFMT("SYS") RFMT("PERIPH"),
+		 RINT(cpu_rate), RFRAC(cpu_rate),
+		 RINT(dram_rate), RFRAC(dram_rate),
+		 RINT(sys_rate), RFRAC(sys_rate),
+		 RINT(periph_rate), RFRAC(periph_rate));
+
+#undef RFRAC
+#undef RINT
+#undef RFMT
 
 	ralink_clk_add("cpu", cpu_rate);
-	ralink_clk_add("10000100.timer", 40000000);
-	ralink_clk_add("10000500.uart", 40000000);
-	ralink_clk_add("10000c00.uartlite", 40000000);
+	ralink_clk_add("10000100.timer", periph_rate);
+	ralink_clk_add("10000120.watchdog", periph_rate);
+	ralink_clk_add("10000500.uart", periph_rate);
+	ralink_clk_add("10000b00.spi", sys_rate);
+	ralink_clk_add("10000c00.uartlite", periph_rate);
 }
 
 void __init ralink_of_remap(void)
@@ -214,16 +366,19 @@ void prom_soc_init(struct ralink_soc_info *soc_info)
 
 	switch (dram_type) {
 	case SYSCFG0_DRAM_TYPE_SDRAM:
+		pr_info("Board has SDRAM\n");
 		soc_info->mem_size_min = MT7620_SDRAM_SIZE_MIN;
 		soc_info->mem_size_max = MT7620_SDRAM_SIZE_MAX;
 		break;
 
 	case SYSCFG0_DRAM_TYPE_DDR1:
+		pr_info("Board has DDR1\n");
 		soc_info->mem_size_min = MT7620_DDR1_SIZE_MIN;
 		soc_info->mem_size_max = MT7620_DDR1_SIZE_MAX;
 		break;
 
 	case SYSCFG0_DRAM_TYPE_DDR2:
+		pr_info("Board has DDR2\n");
 		soc_info->mem_size_min = MT7620_DDR2_SIZE_MIN;
 		soc_info->mem_size_max = MT7620_DDR2_SIZE_MAX;
 		break;
diff --git a/arch/mips/ralink/of.c b/arch/mips/ralink/of.c
index f25ea5b45051..ce38d11f9da5 100644
--- a/arch/mips/ralink/of.c
+++ b/arch/mips/ralink/of.c
@@ -110,6 +110,9 @@ static int __init plat_of_setup(void)
 	if (of_platform_populate(NULL, of_ids, NULL, NULL))
 		panic("failed to populate DT\n");
 
+	/* make sure ithat the reset controller is setup early */
+	ralink_rst_init();
+
 	return 0;
 }
 
diff --git a/arch/mips/ralink/reset.c b/arch/mips/ralink/reset.c
index 22120e512e7e..55c7ec59df3c 100644
--- a/arch/mips/ralink/reset.c
+++ b/arch/mips/ralink/reset.c
@@ -10,6 +10,8 @@
 
 #include <linux/pm.h>
 #include <linux/io.h>
+#include <linux/of.h>
+#include <linux/reset-controller.h>
 
 #include <asm/reboot.h>
 
@@ -19,6 +21,66 @@
 #define SYSC_REG_RESET_CTRL     0x034
 #define RSTCTL_RESET_SYSTEM     BIT(0)
 
+static int ralink_assert_device(struct reset_controller_dev *rcdev,
+				unsigned long id)
+{
+	u32 val;
+
+	if (id < 8)
+		return -1;
+
+	val = rt_sysc_r32(SYSC_REG_RESET_CTRL);
+	val |= BIT(id);
+	rt_sysc_w32(val, SYSC_REG_RESET_CTRL);
+
+	return 0;
+}
+
+static int ralink_deassert_device(struct reset_controller_dev *rcdev,
+				  unsigned long id)
+{
+	u32 val;
+
+	if (id < 8)
+		return -1;
+
+	val = rt_sysc_r32(SYSC_REG_RESET_CTRL);
+	val &= ~BIT(id);
+	rt_sysc_w32(val, SYSC_REG_RESET_CTRL);
+
+	return 0;
+}
+
+static int ralink_reset_device(struct reset_controller_dev *rcdev,
+			       unsigned long id)
+{
+	ralink_assert_device(rcdev, id);
+	return ralink_deassert_device(rcdev, id);
+}
+
+static struct reset_control_ops reset_ops = {
+	.reset = ralink_reset_device,
+	.assert = ralink_assert_device,
+	.deassert = ralink_deassert_device,
+};
+
+static struct reset_controller_dev reset_dev = {
+	.ops			= &reset_ops,
+	.owner			= THIS_MODULE,
+	.nr_resets		= 32,
+	.of_reset_n_cells	= 1,
+};
+
+void ralink_rst_init(void)
+{
+	reset_dev.of_node = of_find_compatible_node(NULL, NULL,
+						"ralink,rt2880-reset");
+	if (!reset_dev.of_node)
+		pr_err("Failed to find reset controller node");
+	else
+		reset_controller_register(&reset_dev);
+}
+
 static void ralink_restart(char *command)
 {
 	local_irq_disable();
diff --git a/arch/mips/ralink/timer.c b/arch/mips/ralink/timer.c
new file mode 100644
index 000000000000..e49241a2c39a
--- /dev/null
+++ b/arch/mips/ralink/timer.c
@@ -0,0 +1,185 @@
+/*
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ *
+ * Copyright (C) 2013 John Crispin <blogic@openwrt.org>
+*/
+
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/interrupt.h>
+#include <linux/timer.h>
+#include <linux/of_gpio.h>
+#include <linux/clk.h>
+
+#include <asm/mach-ralink/ralink_regs.h>
+
+#define TIMER_REG_TMRSTAT		0x00
+#define TIMER_REG_TMR0LOAD		0x10
+#define TIMER_REG_TMR0CTL		0x18
+
+#define TMRSTAT_TMR0INT			BIT(0)
+
+#define TMR0CTL_ENABLE			BIT(7)
+#define TMR0CTL_MODE_PERIODIC		BIT(4)
+#define TMR0CTL_PRESCALER		1
+#define TMR0CTL_PRESCALE_VAL		(0xf - TMR0CTL_PRESCALER)
+#define TMR0CTL_PRESCALE_DIV		(65536 / BIT(TMR0CTL_PRESCALER))
+
+struct rt_timer {
+	struct device	*dev;
+	void __iomem	*membase;
+	int		irq;
+	unsigned long	timer_freq;
+	unsigned long	timer_div;
+};
+
+static inline void rt_timer_w32(struct rt_timer *rt, u8 reg, u32 val)
+{
+	__raw_writel(val, rt->membase + reg);
+}
+
+static inline u32 rt_timer_r32(struct rt_timer *rt, u8 reg)
+{
+	return __raw_readl(rt->membase + reg);
+}
+
+static irqreturn_t rt_timer_irq(int irq, void *_rt)
+{
+	struct rt_timer *rt =  (struct rt_timer *) _rt;
+
+	rt_timer_w32(rt, TIMER_REG_TMR0LOAD, rt->timer_freq / rt->timer_div);
+	rt_timer_w32(rt, TIMER_REG_TMRSTAT, TMRSTAT_TMR0INT);
+
+	return IRQ_HANDLED;
+}
+
+
+static int rt_timer_request(struct rt_timer *rt)
+{
+	int err = request_irq(rt->irq, rt_timer_irq, IRQF_DISABLED,
+						dev_name(rt->dev), rt);
+	if (err) {
+		dev_err(rt->dev, "failed to request irq\n");
+	} else {
+		u32 t = TMR0CTL_MODE_PERIODIC | TMR0CTL_PRESCALE_VAL;
+		rt_timer_w32(rt, TIMER_REG_TMR0CTL, t);
+	}
+	return err;
+}
+
+static void rt_timer_free(struct rt_timer *rt)
+{
+	free_irq(rt->irq, rt);
+}
+
+static int rt_timer_config(struct rt_timer *rt, unsigned long divisor)
+{
+	if (rt->timer_freq < divisor)
+		rt->timer_div = rt->timer_freq;
+	else
+		rt->timer_div = divisor;
+
+	rt_timer_w32(rt, TIMER_REG_TMR0LOAD, rt->timer_freq / rt->timer_div);
+
+	return 0;
+}
+
+static int rt_timer_enable(struct rt_timer *rt)
+{
+	u32 t;
+
+	rt_timer_w32(rt, TIMER_REG_TMR0LOAD, rt->timer_freq / rt->timer_div);
+
+	t = rt_timer_r32(rt, TIMER_REG_TMR0CTL);
+	t |= TMR0CTL_ENABLE;
+	rt_timer_w32(rt, TIMER_REG_TMR0CTL, t);
+
+	return 0;
+}
+
+static void rt_timer_disable(struct rt_timer *rt)
+{
+	u32 t;
+
+	t = rt_timer_r32(rt, TIMER_REG_TMR0CTL);
+	t &= ~TMR0CTL_ENABLE;
+	rt_timer_w32(rt, TIMER_REG_TMR0CTL, t);
+}
+
+static int rt_timer_probe(struct platform_device *pdev)
+{
+	struct resource *res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	struct rt_timer *rt;
+	struct clk *clk;
+
+	rt = devm_kzalloc(&pdev->dev, sizeof(*rt), GFP_KERNEL);
+	if (!rt) {
+		dev_err(&pdev->dev, "failed to allocate memory\n");
+		return -ENOMEM;
+	}
+
+	rt->irq = platform_get_irq(pdev, 0);
+	if (!rt->irq) {
+		dev_err(&pdev->dev, "failed to load irq\n");
+		return -ENOENT;
+	}
+
+	rt->membase = devm_request_and_ioremap(&pdev->dev, res);
+	if (IS_ERR(rt->membase))
+		return PTR_ERR(rt->membase);
+
+	clk = devm_clk_get(&pdev->dev, NULL);
+	if (IS_ERR(clk)) {
+		dev_err(&pdev->dev, "failed get clock rate\n");
+		return PTR_ERR(clk);
+	}
+
+	rt->timer_freq = clk_get_rate(clk) / TMR0CTL_PRESCALE_DIV;
+	if (!rt->timer_freq)
+		return -EINVAL;
+
+	rt->dev = &pdev->dev;
+	platform_set_drvdata(pdev, rt);
+
+	rt_timer_request(rt);
+	rt_timer_config(rt, 2);
+	rt_timer_enable(rt);
+
+	dev_info(&pdev->dev, "maximum frequncy is %luHz\n", rt->timer_freq);
+
+	return 0;
+}
+
+static int rt_timer_remove(struct platform_device *pdev)
+{
+	struct rt_timer *rt = platform_get_drvdata(pdev);
+
+	rt_timer_disable(rt);
+	rt_timer_free(rt);
+
+	return 0;
+}
+
+static const struct of_device_id rt_timer_match[] = {
+	{ .compatible = "ralink,rt2880-timer" },
+	{},
+};
+MODULE_DEVICE_TABLE(of, rt_timer_match);
+
+static struct platform_driver rt_timer_driver = {
+	.probe = rt_timer_probe,
+	.remove = rt_timer_remove,
+	.driver = {
+		.name		= "rt-timer",
+		.owner          = THIS_MODULE,
+		.of_match_table	= rt_timer_match
+	},
+};
+
+module_platform_driver(rt_timer_driver);
+
+MODULE_DESCRIPTION("Ralink RT2880 timer");
+MODULE_AUTHOR("John Crispin <blogic@openwrt.org");
+MODULE_LICENSE("GPL");
diff --git a/arch/mips/sibyte/bcm1480/setup.c b/arch/mips/sibyte/bcm1480/setup.c
index 05ed92c92b69..8e2e04f77870 100644
--- a/arch/mips/sibyte/bcm1480/setup.c
+++ b/arch/mips/sibyte/bcm1480/setup.c
@@ -22,6 +22,7 @@
 #include <linux/string.h>
 
 #include <asm/bootinfo.h>
+#include <asm/cpu.h>
 #include <asm/mipsregs.h>
 #include <asm/io.h>
 #include <asm/sibyte/sb1250.h>
@@ -119,7 +120,7 @@ void __init bcm1480_setup(void)
 	uint64_t sys_rev;
 	int plldiv;
 
-	sb1_pass = read_c0_prid() & 0xff;
+	sb1_pass = read_c0_prid() & PRID_REV_MASK;
 	sys_rev = __raw_readq(IOADDR(A_SCD_SYSTEM_REVISION));
 	soc_type = SYS_SOC_TYPE(sys_rev);
 	part_type = G_SYS_PART(sys_rev);
diff --git a/arch/mips/sibyte/sb1250/setup.c b/arch/mips/sibyte/sb1250/setup.c
index a14bd4cb0bc0..3c02b2a77ae9 100644
--- a/arch/mips/sibyte/sb1250/setup.c
+++ b/arch/mips/sibyte/sb1250/setup.c
@@ -22,6 +22,7 @@
 #include <linux/string.h>
 
 #include <asm/bootinfo.h>
+#include <asm/cpu.h>
 #include <asm/mipsregs.h>
 #include <asm/io.h>
 #include <asm/sibyte/sb1250.h>
@@ -182,7 +183,7 @@ void __init sb1250_setup(void)
 	int plldiv;
 	int bad_config = 0;
 
-	sb1_pass = read_c0_prid() & 0xff;
+	sb1_pass = read_c0_prid() & PRID_REV_MASK;
 	sys_rev = __raw_readq(IOADDR(A_SCD_SYSTEM_REVISION));
 	soc_type = SYS_SOC_TYPE(sys_rev);
 	soc_pass = G_SYS_REVISION(sys_rev);
diff --git a/arch/mips/sni/a20r.c b/arch/mips/sni/a20r.c
index dd0ab982d77e..f9407e170476 100644
--- a/arch/mips/sni/a20r.c
+++ b/arch/mips/sni/a20r.c
@@ -122,7 +122,6 @@ static struct resource sc26xx_rsrc[] = {
 
 static struct sccnxp_pdata sccnxp_data = {
 	.reg_shift	= 2,
-	.frequency	= 3686400,
 	.mctrl_cfg[0]	= MCTRL_SIG(DTR_OP, LINE_OP7) |
 			  MCTRL_SIG(RTS_OP, LINE_OP3) |
 			  MCTRL_SIG(DSR_IP, LINE_IP5) |
diff --git a/arch/mips/sni/setup.c b/arch/mips/sni/setup.c
index 5b09b3544edd..efad85c8c823 100644
--- a/arch/mips/sni/setup.c
+++ b/arch/mips/sni/setup.c
@@ -25,6 +25,7 @@
 #endif
 
 #include <asm/bootinfo.h>
+#include <asm/cpu.h>
 #include <asm/io.h>
 #include <asm/reboot.h>
 #include <asm/sni.h>
@@ -173,7 +174,7 @@ void __init plat_mem_setup(void)
 		system_type = "RM300-Cxx";
 		break;
 	case SNI_BRD_PCI_DESKTOP:
-		switch (read_c0_prid() & 0xff00) {
+		switch (read_c0_prid() & PRID_IMP_MASK) {
 		case PRID_IMP_R4600:
 		case PRID_IMP_R4700:
 			system_type = "RM200-C20";
diff --git a/arch/mips/txx9/generic/setup.c b/arch/mips/txx9/generic/setup.c
index 681e7f86c080..2b0b83c171e0 100644
--- a/arch/mips/txx9/generic/setup.c
+++ b/arch/mips/txx9/generic/setup.c
@@ -350,7 +350,7 @@ static void __init select_board(void)
 	}
 
 	/* select "default" board */
-#ifdef CONFIG_CPU_TX39XX
+#ifdef CONFIG_TOSHIBA_JMR3927
 	txx9_board_vec = &jmr3927_vec;
 #endif
 #ifdef CONFIG_CPU_TX49XX
diff --git a/arch/mn10300/Kconfig b/arch/mn10300/Kconfig
index 70e4f663ebd2..6aaa1607001a 100644
--- a/arch/mn10300/Kconfig
+++ b/arch/mn10300/Kconfig
@@ -1,7 +1,6 @@
 config MN10300
 	def_bool y
 	select HAVE_OPROFILE
-	select HAVE_GENERIC_HARDIRQS
 	select GENERIC_IRQ_SHOW
 	select ARCH_WANT_IPC_PARSE_VERSION
 	select HAVE_ARCH_TRACEHOOK
diff --git a/arch/mn10300/kernel/entry.S b/arch/mn10300/kernel/entry.S
index 222152a3f751..177d61de51c9 100644
--- a/arch/mn10300/kernel/entry.S
+++ b/arch/mn10300/kernel/entry.S
@@ -171,10 +171,10 @@ ret_from_intr:
 	mov	(REG_EPSW,fp),d0	# need to deliver signals before
 					# returning to userspace
 	and	EPSW_nSL,d0
-	beq	resume_kernel		# returning to supervisor mode
+	bne	resume_userspace	# returning to userspace
 
 #ifdef CONFIG_PREEMPT
-ENTRY(resume_kernel)
+resume_kernel:
 	LOCAL_IRQ_DISABLE
 	mov	(TI_preempt_count,a2),d0	# non-zero preempt_count ?
 	cmp	0,d0
@@ -189,6 +189,8 @@ need_resched:
 	bne	restore_all
 	call	preempt_schedule_irq[],0
 	jmp	need_resched
+#else
+	jmp	resume_kernel
 #endif
 
 
diff --git a/arch/mn10300/mm/fault.c b/arch/mn10300/mm/fault.c
index 8a2e6ded9a44..3516cbdf1ee9 100644
--- a/arch/mn10300/mm/fault.c
+++ b/arch/mn10300/mm/fault.c
@@ -171,6 +171,8 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long fault_code,
 	if (in_atomic() || !mm)
 		goto no_context;
 
+	if ((fault_code & MMUFCR_xFC_ACCESS) == MMUFCR_xFC_ACCESS_USR)
+		flags |= FAULT_FLAG_USER;
 retry:
 	down_read(&mm->mmap_sem);
 
diff --git a/arch/openrisc/Kconfig b/arch/openrisc/Kconfig
index d60bf98fa5cf..9488209a5253 100644
--- a/arch/openrisc/Kconfig
+++ b/arch/openrisc/Kconfig
@@ -11,7 +11,6 @@ config OPENRISC
 	select HAVE_MEMBLOCK
 	select ARCH_REQUIRE_GPIOLIB
         select HAVE_ARCH_TRACEHOOK
-	select HAVE_GENERIC_HARDIRQS
 	select GENERIC_IRQ_CHIP
 	select GENERIC_IRQ_PROBE
 	select GENERIC_IRQ_SHOW
diff --git a/arch/openrisc/include/asm/prom.h b/arch/openrisc/include/asm/prom.h
index bbb34e5343a2..93c9980e1b6b 100644
--- a/arch/openrisc/include/asm/prom.h
+++ b/arch/openrisc/include/asm/prom.h
@@ -14,56 +14,9 @@
  * the Free Software Foundation; either version 2 of the License, or
  * (at your option) any later version.
  */
-
-#include <linux/of.h>	/* linux/of.h gets to determine #include ordering */
-
 #ifndef _ASM_OPENRISC_PROM_H
 #define _ASM_OPENRISC_PROM_H
-#ifdef __KERNEL__
-#ifndef __ASSEMBLY__
 
-#include <linux/types.h>
-#include <asm/irq.h>
-#include <linux/irqdomain.h>
-#include <linux/atomic.h>
-#include <linux/of_irq.h>
-#include <linux/of_fdt.h>
-#include <linux/of_address.h>
-#include <linux/proc_fs.h>
-#include <linux/platform_device.h>
 #define HAVE_ARCH_DEVTREE_FIXUPS
 
-/* Other Prototypes */
-extern int early_uartlite_console(void);
-
-/* Parse the ibm,dma-window property of an OF node into the busno, phys and
- * size parameters.
- */
-void of_parse_dma_window(struct device_node *dn, const void *dma_window_prop,
-		unsigned long *busno, unsigned long *phys, unsigned long *size);
-
-extern void kdump_move_device_tree(void);
-
-/* CPU OF node matching */
-struct device_node *of_get_cpu_node(int cpu, unsigned int *thread);
-
-/* Get the MAC address */
-extern const void *of_get_mac_address(struct device_node *np);
-
-/**
- * of_irq_map_pci - Resolve the interrupt for a PCI device
- * @pdev:	the device whose interrupt is to be resolved
- * @out_irq:	structure of_irq filled by this function
- *
- * This function resolves the PCI interrupt for a given PCI device. If a
- * device-node exists for a given pci_dev, it will use normal OF tree
- * walking. If not, it will implement standard swizzling and walk up the
- * PCI tree until an device-node is found, at which point it will finish
- * resolving using the OF tree walking.
- */
-struct pci_dev;
-extern int of_irq_map_pci(struct pci_dev *pdev, struct of_irq *out_irq);
-
-#endif /* __ASSEMBLY__ */
-#endif /* __KERNEL__ */
 #endif /* _ASM_OPENRISC_PROM_H */
diff --git a/arch/openrisc/kernel/prom.c b/arch/openrisc/kernel/prom.c
index 5869e3fa5dd3..a63e76872f84 100644
--- a/arch/openrisc/kernel/prom.c
+++ b/arch/openrisc/kernel/prom.c
@@ -55,11 +55,6 @@ void __init early_init_dt_add_memory_arch(u64 base, u64 size)
 	memblock_add(base, size);
 }
 
-void * __init early_init_dt_alloc_memory_arch(u64 size, u64 align)
-{
-	return __va(memblock_alloc(size, align));
-}
-
 void __init early_init_devtree(void *params)
 {
 	void *alloc;
@@ -96,8 +91,7 @@ void __init early_init_devtree(void *params)
 }
 
 #ifdef CONFIG_BLK_DEV_INITRD
-void __init early_init_dt_setup_initrd_arch(unsigned long start,
-		unsigned long end)
+void __init early_init_dt_setup_initrd_arch(u64 start, u64 end)
 {
 	initrd_start = (unsigned long)__va(start);
 	initrd_end = (unsigned long)__va(end);
diff --git a/arch/openrisc/mm/fault.c b/arch/openrisc/mm/fault.c
index 4a41f8493ab0..0703acf7d327 100644
--- a/arch/openrisc/mm/fault.c
+++ b/arch/openrisc/mm/fault.c
@@ -86,6 +86,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long address,
 	if (user_mode(regs)) {
 		/* Exception was in userspace: reenable interrupts */
 		local_irq_enable();
+		flags |= FAULT_FLAG_USER;
 	} else {
 		/* If exception was in a syscall, then IRQ's may have
 		 * been enabled or disabled.  If they were enabled,
diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig
index aa399a5259b6..ad2ce8dab996 100644
--- a/arch/parisc/Kconfig
+++ b/arch/parisc/Kconfig
@@ -14,7 +14,6 @@ config PARISC
 	select HAVE_PERF_EVENTS
 	select GENERIC_ATOMIC64 if !64BIT
 	select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
-	select HAVE_GENERIC_HARDIRQS
 	select BROKEN_RODATA
 	select GENERIC_IRQ_PROBE
 	select GENERIC_PCI_IOMAP
diff --git a/arch/parisc/include/asm/traps.h b/arch/parisc/include/asm/traps.h
index 1945f995f2df..4736020ba5ea 100644
--- a/arch/parisc/include/asm/traps.h
+++ b/arch/parisc/include/asm/traps.h
@@ -6,7 +6,7 @@ struct pt_regs;
 
 /* traps.c */
 void parisc_terminate(char *msg, struct pt_regs *regs,
-		int code, unsigned long offset);
+		int code, unsigned long offset) __noreturn __cold;
 
 /* mm/fault.c */
 void do_page_fault(struct pt_regs *regs, unsigned long code,
diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c
index c035673209f7..b521c0adf4ec 100644
--- a/arch/parisc/kernel/cache.c
+++ b/arch/parisc/kernel/cache.c
@@ -602,6 +602,7 @@ flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, unsigned long
 		__flush_cache_page(vma, vmaddr, PFN_PHYS(pfn));
 	}
 }
+EXPORT_SYMBOL_GPL(flush_cache_page);
 
 #ifdef CONFIG_PARISC_TMPALIAS
 
diff --git a/arch/parisc/kernel/signal.c b/arch/parisc/kernel/signal.c
index 07349b002687..1cba8f29bb49 100644
--- a/arch/parisc/kernel/signal.c
+++ b/arch/parisc/kernel/signal.c
@@ -78,7 +78,7 @@ restore_sigcontext(struct sigcontext __user *sc, struct pt_regs *regs)
 	err |= __copy_from_user(regs->iaoq, sc->sc_iaoq, sizeof(regs->iaoq));
 	err |= __copy_from_user(regs->iasq, sc->sc_iasq, sizeof(regs->iasq));
 	err |= __get_user(regs->sar, &sc->sc_sar);
-	DBG(2,"restore_sigcontext: iaoq is 0x%#lx / 0x%#lx\n", 
+	DBG(2,"restore_sigcontext: iaoq is %#lx / %#lx\n",
 			regs->iaoq[0],regs->iaoq[1]);
 	DBG(2,"restore_sigcontext: r28 is %ld\n", regs->gr[28]);
 	return err;
diff --git a/arch/parisc/kernel/smp.c b/arch/parisc/kernel/smp.c
index 8a252f2d6c08..2b96602e812f 100644
--- a/arch/parisc/kernel/smp.c
+++ b/arch/parisc/kernel/smp.c
@@ -72,7 +72,6 @@ enum ipi_message_type {
 	IPI_NOP=0,
 	IPI_RESCHEDULE=1,
 	IPI_CALL_FUNC,
-	IPI_CALL_FUNC_SINGLE,
 	IPI_CPU_START,
 	IPI_CPU_STOP,
 	IPI_CPU_TEST
@@ -164,11 +163,6 @@ ipi_interrupt(int irq, void *dev_id)
 				generic_smp_call_function_interrupt();
 				break;
 
-			case IPI_CALL_FUNC_SINGLE:
-				smp_debug(100, KERN_DEBUG "CPU%d IPI_CALL_FUNC_SINGLE\n", this_cpu);
-				generic_smp_call_function_single_interrupt();
-				break;
-
 			case IPI_CPU_START:
 				smp_debug(100, KERN_DEBUG "CPU%d IPI_CPU_START\n", this_cpu);
 				break;
@@ -260,7 +254,7 @@ void arch_send_call_function_ipi_mask(const struct cpumask *mask)
 
 void arch_send_call_function_single_ipi(int cpu)
 {
-	send_IPI_single(cpu, IPI_CALL_FUNC_SINGLE);
+	send_IPI_single(cpu, IPI_CALL_FUNC);
 }
 
 /*
diff --git a/arch/parisc/kernel/traps.c b/arch/parisc/kernel/traps.c
index 04e47c6a4562..1cd1d0c83b6d 100644
--- a/arch/parisc/kernel/traps.c
+++ b/arch/parisc/kernel/traps.c
@@ -291,11 +291,6 @@ void die_if_kernel(char *str, struct pt_regs *regs, long err)
 	do_exit(SIGSEGV);
 }
 
-int syscall_ipi(int (*syscall) (struct pt_regs *), struct pt_regs *regs)
-{
-	return syscall(regs);
-}
-
 /* gdb uses break 4,8 */
 #define GDB_BREAK_INSN 0x10004
 static void handle_gdb_break(struct pt_regs *regs, int wot)
@@ -805,14 +800,14 @@ void notrace handle_interruption(int code, struct pt_regs *regs)
 	else {
 
 	    /*
-	     * The kernel should never fault on its own address space.
+	     * The kernel should never fault on its own address space,
+	     * unless pagefault_disable() was called before.
 	     */
 
-	    if (fault_space == 0) 
+	    if (fault_space == 0 && !in_atomic())
 	    {
 		pdc_chassis_send_status(PDC_CHASSIS_DIRECT_PANIC);
 		parisc_terminate("Kernel Fault", regs, code, fault_address);
-	
 	    }
 	}
 
diff --git a/arch/parisc/lib/memcpy.c b/arch/parisc/lib/memcpy.c
index ac4370b1ca40..b5507ec06b84 100644
--- a/arch/parisc/lib/memcpy.c
+++ b/arch/parisc/lib/memcpy.c
@@ -56,7 +56,7 @@
 #ifdef __KERNEL__
 #include <linux/module.h>
 #include <linux/compiler.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #define s_space "%%sr1"
 #define d_space "%%sr2"
 #else
@@ -524,4 +524,17 @@ EXPORT_SYMBOL(copy_to_user);
 EXPORT_SYMBOL(copy_from_user);
 EXPORT_SYMBOL(copy_in_user);
 EXPORT_SYMBOL(memcpy);
+
+long probe_kernel_read(void *dst, const void *src, size_t size)
+{
+	unsigned long addr = (unsigned long)src;
+
+	if (size < 0 || addr < PAGE_SIZE)
+		return -EFAULT;
+
+	/* check for I/O space F_EXTEND(0xfff00000) access as well? */
+
+	return __probe_kernel_read(dst, src, size);
+}
+
 #endif
diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c
index f247a3480e8e..0293588d5b8c 100644
--- a/arch/parisc/mm/fault.c
+++ b/arch/parisc/mm/fault.c
@@ -171,15 +171,27 @@ void do_page_fault(struct pt_regs *regs, unsigned long code,
 			      unsigned long address)
 {
 	struct vm_area_struct *vma, *prev_vma;
-	struct task_struct *tsk = current;
-	struct mm_struct *mm = tsk->mm;
+	struct task_struct *tsk;
+	struct mm_struct *mm;
 	unsigned long acc_type;
 	int fault;
-	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
+	unsigned int flags;
 
-	if (in_atomic() || !mm)
+	if (in_atomic())
 		goto no_context;
 
+	tsk = current;
+	mm = tsk->mm;
+	if (!mm)
+		goto no_context;
+
+	flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
+	if (user_mode(regs))
+		flags |= FAULT_FLAG_USER;
+
+	acc_type = parisc_acctyp(code, regs->iir);
+	if (acc_type & VM_WRITE)
+		flags |= FAULT_FLAG_WRITE;
 retry:
 	down_read(&mm->mmap_sem);
 	vma = find_vma_prev(mm, address, &prev_vma);
@@ -192,8 +204,6 @@ retry:
 
 good_area:
 
-	acc_type = parisc_acctyp(code,regs->iir);
-
 	if ((vma->vm_flags & acc_type) != acc_type)
 		goto bad_area;
 
@@ -203,8 +213,7 @@ good_area:
 	 * fault.
 	 */
 
-	fault = handle_mm_fault(mm, vma, address,
-			flags | ((acc_type & VM_WRITE) ? FAULT_FLAG_WRITE : 0));
+	fault = handle_mm_fault(mm, vma, address, flags);
 
 	if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
 		return;
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 9cf59816d3e9..38f3b7e47ec5 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -114,7 +114,6 @@ config PPC
 	select HAVE_PERF_EVENTS
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_HW_BREAKPOINT if PERF_EVENTS && PPC_BOOK3S_64
-	select HAVE_GENERIC_HARDIRQS
 	select ARCH_WANT_IPC_PARSE_VERSION
 	select SPARSE_IRQ
 	select IRQ_DOMAIN
@@ -312,6 +311,26 @@ config MATH_EMULATION
 	  such as fsqrt on cores that do have an FPU but do not implement
 	  them (such as Freescale BookE).
 
+choice
+	prompt "Math emulation options"
+	default MATH_EMULATION_FULL
+	depends on MATH_EMULATION
+
+config	MATH_EMULATION_FULL
+	bool "Emulate all the floating point instructions"
+	---help---
+	  Select this option will enable the kernel to support to emulate
+	  all the floating point instructions. If your SoC doesn't have
+	  a FPU, you should select this.
+
+config MATH_EMULATION_HW_UNIMPLEMENTED
+	bool "Just emulate the FPU unimplemented instructions"
+	---help---
+	  Select this if you know there does have a hardware FPU on your
+	  SoC, but some floating point instructions are not implemented by that.
+
+endchoice
+
 config PPC_TRANSACTIONAL_MEM
        bool "Transactional Memory support for POWERPC"
        depends on PPC_BOOK3S_64
@@ -369,9 +388,9 @@ config KEXEC
 
 	  It is an ongoing process to be certain the hardware in a machine
 	  is properly shutdown, so do not be surprised if this code does not
-	  initially work for you.  It may help to enable device hotplugging
-	  support.  As of this writing the exact hardware interface is
-	  strongly in flux, so no good recommendation can be made.
+	  initially work for you.  As of this writing the exact hardware
+	  interface is strongly in flux, so no good recommendation can be
+	  made.
 
 config CRASH_DUMP
 	bool "Build a kdump crash kernel"
@@ -727,7 +746,6 @@ config PCI
 	default y if !40x && !CPM2 && !8xx && !PPC_83xx \
 		&& !PPC_85xx && !PPC_86xx && !GAMECUBE_COMMON
 	default PCI_QSPAN if !4xx && !CPM2 && 8xx
-	select ARCH_SUPPORTS_MSI
 	select GENERIC_PCI_IOMAP
 	help
 	  Find out whether your system includes a PCI bus. PCI is the name of
diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile
index 967fd23ace78..51cfb78d4061 100644
--- a/arch/powerpc/Makefile
+++ b/arch/powerpc/Makefile
@@ -88,13 +88,30 @@ CFLAGS-$(CONFIG_PPC64)	+= $(call cc-option,-mcmodel=medium,-mminimal-toc)
 CFLAGS-$(CONFIG_PPC64)	+= $(call cc-option,-mno-pointers-to-nested-functions)
 CFLAGS-$(CONFIG_PPC32)	:= -ffixed-r2 -mmultiple
 
+ifeq ($(CONFIG_PPC_BOOK3S_64),y)
 CFLAGS-$(CONFIG_GENERIC_CPU) += $(call cc-option,-mtune=power7,-mtune=power4)
+else
+CFLAGS-$(CONFIG_GENERIC_CPU) += -mcpu=powerpc64
+endif
+
 CFLAGS-$(CONFIG_CELL_CPU) += $(call cc-option,-mcpu=cell)
 CFLAGS-$(CONFIG_POWER4_CPU) += $(call cc-option,-mcpu=power4)
 CFLAGS-$(CONFIG_POWER5_CPU) += $(call cc-option,-mcpu=power5)
 CFLAGS-$(CONFIG_POWER6_CPU) += $(call cc-option,-mcpu=power6)
 CFLAGS-$(CONFIG_POWER7_CPU) += $(call cc-option,-mcpu=power7)
 
+E5500_CPU := $(call cc-option,-mcpu=e500mc64,-mcpu=powerpc64)
+CFLAGS-$(CONFIG_E5500_CPU) += $(E5500_CPU)
+CFLAGS-$(CONFIG_E6500_CPU) += $(call cc-option,-mcpu=e6500,$(E5500_CPU))
+
+ifeq ($(CONFIG_PPC32),y)
+ifeq ($(CONFIG_PPC_E500MC),y)
+CFLAGS-y += $(call cc-option,-mcpu=e500mc,-mcpu=powerpc)
+else
+CFLAGS-$(CONFIG_E500) += $(call cc-option,-mcpu=8540 -msoft-float,-mcpu=powerpc)
+endif
+endif
+
 CFLAGS-$(CONFIG_TUNE_CELL) += $(call cc-option,-mtune=cell)
 
 KBUILD_CPPFLAGS	+= -Iarch/$(ARCH)
@@ -139,7 +156,6 @@ endif
 
 cpu-as-$(CONFIG_4xx)		+= -Wa,-m405
 cpu-as-$(CONFIG_ALTIVEC)	+= -Wa,-maltivec
-cpu-as-$(CONFIG_E500)		+= -Wa,-me500
 cpu-as-$(CONFIG_E200)		+= -Wa,-me200
 
 KBUILD_AFLAGS += $(cpu-as-y)
diff --git a/arch/powerpc/boot/.gitignore b/arch/powerpc/boot/.gitignore
index c32ae5ce9fff..554734ff302e 100644
--- a/arch/powerpc/boot/.gitignore
+++ b/arch/powerpc/boot/.gitignore
@@ -22,6 +22,7 @@ zImage.initrd
 zImage.bin.*
 zImage.chrp
 zImage.coff
+zImage.epapr
 zImage.holly
 zImage.*lds
 zImage.miboot
diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile
index 6a15c968d214..15ca2255f438 100644
--- a/arch/powerpc/boot/Makefile
+++ b/arch/powerpc/boot/Makefile
@@ -74,7 +74,7 @@ src-wlib-$(CONFIG_8xx) += mpc8xx.c planetcore.c
 src-wlib-$(CONFIG_PPC_82xx) += pq2.c fsl-soc.c planetcore.c
 src-wlib-$(CONFIG_EMBEDDED6xx) += mv64x60.c mv64x60_i2c.c ugecon.c
 
-src-plat-y := of.c
+src-plat-y := of.c epapr.c
 src-plat-$(CONFIG_40x) += fixed-head.S ep405.c cuboot-hotfoot.c \
 				treeboot-walnut.c cuboot-acadia.c \
 				cuboot-kilauea.c simpleboot.c \
@@ -97,7 +97,7 @@ src-plat-$(CONFIG_EMBEDDED6xx) += cuboot-pq2.c cuboot-mpc7448hpc2.c \
 					prpmc2800.c
 src-plat-$(CONFIG_AMIGAONE) += cuboot-amigaone.c
 src-plat-$(CONFIG_PPC_PS3) += ps3-head.S ps3-hvcall.S ps3.c
-src-plat-$(CONFIG_EPAPR_BOOT) += epapr.c
+src-plat-$(CONFIG_EPAPR_BOOT) += epapr.c epapr-wrapper.c
 
 src-wlib := $(sort $(src-wlib-y))
 src-plat := $(sort $(src-plat-y))
diff --git a/arch/powerpc/boot/dts/ac14xx.dts b/arch/powerpc/boot/dts/ac14xx.dts
index a27a4609bb42..a543c4088cba 100644
--- a/arch/powerpc/boot/dts/ac14xx.dts
+++ b/arch/powerpc/boot/dts/ac14xx.dts
@@ -10,7 +10,7 @@
  */
 
 
-/include/ "mpc5121.dtsi"
+#include <mpc5121.dtsi>
 
 / {
 	model = "ac14xx";
diff --git a/arch/powerpc/boot/dts/b4420qds.dts b/arch/powerpc/boot/dts/b4420qds.dts
index 923156d03b30..508dbdf33c81 100644
--- a/arch/powerpc/boot/dts/b4420qds.dts
+++ b/arch/powerpc/boot/dts/b4420qds.dts
@@ -33,7 +33,7 @@
  */
 
 /include/ "fsl/b4420si-pre.dtsi"
-/include/ "b4qds.dts"
+/include/ "b4qds.dtsi"
 
 / {
 	model = "fsl,B4420QDS";
diff --git a/arch/powerpc/boot/dts/b4860qds.dts b/arch/powerpc/boot/dts/b4860qds.dts
index 78907f38bb77..6bb3707ffe3d 100644
--- a/arch/powerpc/boot/dts/b4860qds.dts
+++ b/arch/powerpc/boot/dts/b4860qds.dts
@@ -33,7 +33,7 @@
  */
 
 /include/ "fsl/b4860si-pre.dtsi"
-/include/ "b4qds.dts"
+/include/ "b4qds.dtsi"
 
 / {
 	model = "fsl,B4860QDS";
diff --git a/arch/powerpc/boot/dts/b4qds.dts b/arch/powerpc/boot/dts/b4qds.dtsi
index e6d2f8f90544..e6d2f8f90544 100644
--- a/arch/powerpc/boot/dts/b4qds.dts
+++ b/arch/powerpc/boot/dts/b4qds.dtsi
diff --git a/arch/powerpc/boot/dts/c293pcie.dts b/arch/powerpc/boot/dts/c293pcie.dts
new file mode 100644
index 000000000000..1238bda8901f
--- /dev/null
+++ b/arch/powerpc/boot/dts/c293pcie.dts
@@ -0,0 +1,223 @@
+/*
+ * C293 PCIE Device Tree Source
+ *
+ * Copyright 2013 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in the
+ *       documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Freescale Semiconductor nor the
+ *       names of its contributors may be used to endorse or promote products
+ *       derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor "AS IS" AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+/include/ "fsl/c293si-pre.dtsi"
+
+/ {
+	model = "fsl,C293PCIE";
+	compatible = "fsl,C293PCIE";
+
+	memory {
+		device_type = "memory";
+	};
+
+	ifc: ifc@fffe1e000 {
+		reg = <0xf 0xffe1e000 0 0x2000>;
+		ranges = <0x0 0x0 0xf 0xec000000 0x04000000
+			  0x2 0x0 0xf 0xffdf0000 0x00010000>;
+
+	};
+
+	soc: soc@fffe00000 {
+		ranges = <0x0 0xf 0xffe00000 0x100000>;
+	};
+
+	pci0: pcie@fffe0a000 {
+		reg = <0xf 0xffe0a000 0 0x1000>;
+		ranges = <0x2000000 0x0 0x80000000 0xc 0x00000000 0x0 0x20000000
+			  0x1000000 0x0 0x00000000 0xf 0xffc00000 0x0 0x10000>;
+		pcie@0 {
+			ranges = <0x2000000 0x0 0x80000000
+				  0x2000000 0x0 0x80000000
+				  0x0 0x20000000
+
+				  0x1000000 0x0 0x0
+				  0x1000000 0x0 0x0
+				  0x0 0x100000>;
+		};
+	};
+};
+
+&ifc {
+	nor@0,0 {
+		#address-cells = <1>;
+		#size-cells = <1>;
+		compatible = "cfi-flash";
+		reg = <0x0 0x0 0x4000000>;
+		bank-width = <2>;
+		device-width = <1>;
+
+		partition@0 {
+			/* 1MB for DTB Image */
+			reg = <0x0 0x00100000>;
+			label = "NOR DTB Image";
+		};
+
+		partition@100000 {
+			/* 8 MB for Linux Kernel Image */
+			reg = <0x00100000 0x00800000>;
+			label = "NOR Linux Kernel Image";
+		};
+
+		partition@900000 {
+			/* 53MB for rootfs */
+			reg = <0x00900000 0x03500000>;
+			label = "NOR Rootfs Image";
+		};
+
+		partition@3e00000 {
+			/* 1MB for blob encrypted key */
+			reg = <0x03e00000 0x00100000>;
+			label = "NOR blob encrypted key";
+		};
+
+		partition@3f00000 {
+			/* 512KB for u-boot Bootloader Image and evn */
+			reg = <0x03f00000 0x00100000>;
+			label = "NOR U-Boot Image";
+			read-only;
+		};
+	};
+
+	nand@1,0 {
+		#address-cells = <1>;
+		#size-cells = <1>;
+		compatible = "fsl,ifc-nand";
+		reg = <0x1 0x0 0x10000>;
+
+		partition@0 {
+			/* This location must not be altered  */
+			/* 1MB for u-boot Bootloader Image */
+			reg = <0x0 0x00100000>;
+			label = "NAND U-Boot Image";
+			read-only;
+		};
+
+		partition@100000 {
+			/* 1MB for DTB Image */
+			reg = <0x00100000 0x00100000>;
+			label = "NAND DTB Image";
+		};
+
+		partition@200000 {
+			/* 16MB for Linux Kernel Image */
+			reg = <0x00200000 0x01000000>;
+			label = "NAND Linux Kernel Image";
+		};
+
+		partition@1200000 {
+			/* 4078MB for Root file System Image */
+			reg = <0x00600000 0xfee00000>;
+			label = "NAND RFS Image";
+		};
+	};
+
+	cpld@2,0 {
+		compatible = "fsl,c293pcie-cpld";
+		reg = <0x2 0x0 0x20>;
+	};
+};
+
+&soc {
+	i2c@3000 {
+		eeprom@50 {
+			compatible = "st,24c1024";
+			reg = <0x50>;
+		};
+
+		adt7461@4c {
+			compatible = "adi,adt7461";
+			reg = <0x4c>;
+		};
+	};
+
+	spi@7000 {
+		flash@0 {
+			#address-cells = <1>;
+			#size-cells = <1>;
+			compatible = "spansion,s25sl12801";
+			reg = <0>;
+			spi-max-frequency = <50000000>;
+
+			partition@0 {
+				/* 1MB for u-boot Bootloader Image */
+				/* 1MB for Environment */
+				reg = <0x0 0x00100000>;
+				label = "SPI Flash U-Boot Image";
+				read-only;
+			};
+
+			partition@100000 {
+				/* 512KB for DTB Image */
+				reg = <0x00100000 0x00080000>;
+				label = "SPI Flash DTB Image";
+			};
+
+			partition@180000 {
+				/* 4MB for Linux Kernel Image */
+				reg = <0x00180000 0x00400000>;
+				label = "SPI Flash Linux Kernel Image";
+			};
+
+			partition@580000 {
+				/* 10.5MB for RFS Image */
+				reg = <0x00580000 0x00a80000>;
+				label = "SPI Flash RFS Image";
+			};
+		};
+	};
+
+	mdio@24000 {
+		phy0: ethernet-phy@0 {
+			interrupts = <2 1 0 0>;
+			reg = <0x0>;
+		};
+
+		phy1: ethernet-phy@1 {
+			interrupts = <2 1 0 0>;
+			reg = <0x2>;
+		};
+	};
+
+	enet0: ethernet@b0000 {
+		phy-handle = <&phy0>;
+		phy-connection-type = "rgmii-id";
+	};
+
+	enet1: ethernet@b1000 {
+		phy-handle = <&phy1>;
+		phy-connection-type = "rgmii-id";
+	};
+};
+/include/ "fsl/c293si-post.dtsi"
diff --git a/arch/powerpc/boot/dts/fsl/b4si-post.dtsi b/arch/powerpc/boot/dts/fsl/b4si-post.dtsi
index 73991547c69b..4c617bf8cdb2 100644
--- a/arch/powerpc/boot/dts/fsl/b4si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/b4si-post.dtsi
@@ -204,7 +204,7 @@
 		};
 	};
 
-/include/ "qoriq-mpic.dtsi"
+/include/ "qoriq-mpic4.3.dtsi"
 
 	guts: global-utilities@e0000 {
 		compatible = "fsl,b4-device-config";
diff --git a/arch/powerpc/boot/dts/fsl/c293si-post.dtsi b/arch/powerpc/boot/dts/fsl/c293si-post.dtsi
new file mode 100644
index 000000000000..bd208320bff5
--- /dev/null
+++ b/arch/powerpc/boot/dts/fsl/c293si-post.dtsi
@@ -0,0 +1,193 @@
+/*
+ * C293 Silicon/SoC Device Tree Source (post include)
+ *
+ * Copyright 2012 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in the
+ *       documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Freescale Semiconductor nor the
+ *       names of its contributors may be used to endorse or promote products
+ *       derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+&ifc {
+	#address-cells = <2>;
+	#size-cells = <1>;
+	compatible = "fsl,ifc", "simple-bus";
+	interrupts = <19 2 0 0>;
+};
+
+/* controller at 0xa000 */
+&pci0 {
+	compatible = "fsl,qoriq-pcie-v2.2", "fsl,qoriq-pcie";
+	device_type = "pci";
+	#size-cells = <2>;
+	#address-cells = <3>;
+	bus-range = <0 255>;
+	clock-frequency = <33333333>;
+	interrupts = <16 2 0 0>;
+
+	pcie@0 {
+		reg = <0 0 0 0 0>;
+		#interrupt-cells = <1>;
+		#size-cells = <2>;
+		#address-cells = <3>;
+		device_type = "pci";
+		interrupts = <16 2 0 0>;
+		interrupt-map-mask = <0xf800 0 0 7>;
+		interrupt-map = <
+			/* IDSEL 0x0 */
+			0000 0x0 0x0 0x1 &mpic 0x0 0x1 0x0 0x0
+			0000 0x0 0x0 0x2 &mpic 0x1 0x1 0x0 0x0
+			0000 0x0 0x0 0x3 &mpic 0x2 0x1 0x0 0x0
+			0000 0x0 0x0 0x4 &mpic 0x3 0x1 0x0 0x0
+			>;
+	};
+};
+
+&soc {
+	#address-cells = <1>;
+	#size-cells = <1>;
+	device_type = "soc";
+	compatible = "simple-bus";
+	bus-frequency = <0>;		// Filled out by uboot.
+
+	ecm-law@0 {
+		compatible = "fsl,ecm-law";
+		reg = <0x0 0x1000>;
+		fsl,num-laws = <12>;
+	};
+
+	ecm@1000 {
+		compatible = "fsl,c293-ecm", "fsl,ecm";
+		reg = <0x1000 0x1000>;
+		interrupts = <16 2 0 0>;
+	};
+
+	memory-controller@2000 {
+		compatible = "fsl,c293-memory-controller";
+		reg = <0x2000 0x1000>;
+		interrupts = <16 2 0 0>;
+	};
+
+/include/ "pq3-i2c-0.dtsi"
+/include/ "pq3-i2c-1.dtsi"
+/include/ "pq3-duart-0.dtsi"
+/include/ "pq3-espi-0.dtsi"
+	spi0: spi@7000 {
+		fsl,espi-num-chipselects = <1>;
+	};
+
+/include/ "pq3-gpio-0.dtsi"
+	L2: l2-cache-controller@20000 {
+		compatible = "fsl,c293-l2-cache-controller";
+		reg = <0x20000 0x1000>;
+		cache-line-size = <32>;	// 32 bytes
+		cache-size = <0x80000>; // L2,512K
+		interrupts = <16 2 0 0>;
+	};
+
+/include/ "pq3-dma-0.dtsi"
+/include/ "pq3-esdhc-0.dtsi"
+	sdhc@2e000 {
+		compatible = "fsl,c293-esdhc", "fsl,esdhc";
+		sdhci,auto-cmd12;
+	};
+
+	crypto@80000 {
+/include/ "qoriq-sec6.0-0.dtsi"
+	};
+
+	crypto@80000 {
+		reg = <0x80000 0x20000>;
+		ranges = <0x0 0x80000 0x20000>;
+
+		jr@1000{
+			interrupts = <45 2 0 0>;
+		};
+		jr@2000{
+			interrupts = <57 2 0 0>;
+		};
+	};
+
+	crypto@a0000 {
+/include/ "qoriq-sec6.0-0.dtsi"
+	};
+
+	crypto@a0000 {
+		reg = <0xa0000 0x20000>;
+		ranges = <0x0 0xa0000 0x20000>;
+
+		jr@1000{
+			interrupts = <49 2 0 0>;
+		};
+		jr@2000{
+			interrupts = <50 2 0 0>;
+		};
+	};
+
+	crypto@c0000 {
+/include/ "qoriq-sec6.0-0.dtsi"
+	};
+
+	crypto@c0000 {
+		reg = <0xc0000 0x20000>;
+		ranges = <0x0 0xc0000 0x20000>;
+
+		jr@1000{
+			interrupts = <55 2 0 0>;
+		};
+		jr@2000{
+			interrupts = <56 2 0 0>;
+		};
+	};
+
+/include/ "pq3-mpic.dtsi"
+/include/ "pq3-mpic-timer-B.dtsi"
+
+/include/ "pq3-etsec2-0.dtsi"
+	enet0: ethernet@b0000 {
+		queue-group@b0000 {
+			reg = <0x10000 0x1000>;
+			fsl,rx-bit-map = <0xff>;
+			fsl,tx-bit-map = <0xff>;
+		};
+	};
+
+/include/ "pq3-etsec2-1.dtsi"
+	enet1: ethernet@b1000 {
+		queue-group@b1000 {
+			reg = <0x11000 0x1000>;
+			fsl,rx-bit-map = <0xff>;
+			fsl,tx-bit-map = <0xff>;
+		};
+	};
+
+	global-utilities@e0000 {
+		compatible = "fsl,c293-guts";
+		reg = <0xe0000 0x1000>;
+		fsl,has-rstcr;
+	};
+};
diff --git a/arch/powerpc/boot/dts/fsl/c293si-pre.dtsi b/arch/powerpc/boot/dts/fsl/c293si-pre.dtsi
new file mode 100644
index 000000000000..065049d76245
--- /dev/null
+++ b/arch/powerpc/boot/dts/fsl/c293si-pre.dtsi
@@ -0,0 +1,63 @@
+/*
+ * C293 Silicon/SoC Device Tree Source (pre include)
+ *
+ * Copyright 2012 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in the
+ *       documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Freescale Semiconductor nor the
+ *       names of its contributors may be used to endorse or promote products
+ *       derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+/dts-v1/;
+
+/include/ "e500v2_power_isa.dtsi"
+
+/ {
+	compatible = "fsl,C293";
+	#address-cells = <2>;
+	#size-cells = <2>;
+	interrupt-parent = <&mpic>;
+
+	aliases {
+		serial0 = &serial0;
+		serial1 = &serial1;
+		ethernet0 = &enet0;
+		ethernet1 = &enet1;
+		pci0 = &pci0;
+	};
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		PowerPC,e500v2@0 {
+			device_type = "cpu";
+			reg = <0x0>;
+			next-level-cache = <&L2>;
+		};
+	};
+};
diff --git a/arch/powerpc/boot/dts/fsl/qoriq-mpic4.3.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-mpic4.3.dtsi
new file mode 100644
index 000000000000..64f713c24825
--- /dev/null
+++ b/arch/powerpc/boot/dts/fsl/qoriq-mpic4.3.dtsi
@@ -0,0 +1,149 @@
+/*
+ * QorIQ MPIC device tree stub [ controller @ offset 0x40000 ]
+ *
+ * Copyright 2013 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in the
+ *       documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Freescale Semiconductor nor the
+ *       names of its contributors may be used to endorse or promote products
+ *       derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+mpic: pic@40000 {
+	interrupt-controller;
+	#address-cells = <0>;
+	#interrupt-cells = <4>;
+	reg = <0x40000 0x40000>;
+	compatible = "fsl,mpic";
+	device_type = "open-pic";
+	clock-frequency = <0x0>;
+};
+
+timer@41100 {
+	compatible = "fsl,mpic-global-timer";
+	reg = <0x41100 0x100 0x41300 4>;
+	interrupts = <0 0 3 0
+		      1 0 3 0
+		      2 0 3 0
+		      3 0 3 0>;
+};
+
+msi0: msi@41600 {
+	compatible = "fsl,mpic-msi-v4.3";
+	reg = <0x41600 0x200 0x44148 4>;
+	interrupts = <
+		0xe0 0 0 0
+		0xe1 0 0 0
+		0xe2 0 0 0
+		0xe3 0 0 0
+		0xe4 0 0 0
+		0xe5 0 0 0
+		0xe6 0 0 0
+		0xe7 0 0 0
+		0x100 0 0 0
+		0x101 0 0 0
+		0x102 0 0 0
+		0x103 0 0 0
+		0x104 0 0 0
+		0x105 0 0 0
+		0x106 0 0 0
+		0x107 0 0 0>;
+};
+
+msi1: msi@41800 {
+	compatible = "fsl,mpic-msi-v4.3";
+	reg = <0x41800 0x200 0x45148 4>;
+	interrupts = <
+		0xe8 0 0 0
+		0xe9 0 0 0
+		0xea 0 0 0
+		0xeb 0 0 0
+		0xec 0 0 0
+		0xed 0 0 0
+		0xee 0 0 0
+		0xef 0 0 0
+		0x108 0 0 0
+		0x109 0 0 0
+		0x10a 0 0 0
+		0x10b 0 0 0
+		0x10c 0 0 0
+		0x10d 0 0 0
+		0x10e 0 0 0
+		0x10f 0 0 0>;
+};
+
+msi2: msi@41a00 {
+	compatible = "fsl,mpic-msi-v4.3";
+	reg = <0x41a00 0x200 0x46148 4>;
+	interrupts = <
+		0xf0 0 0 0
+		0xf1 0 0 0
+		0xf2 0 0 0
+		0xf3 0 0 0
+		0xf4 0 0 0
+		0xf5 0 0 0
+		0xf6 0 0 0
+		0xf7 0 0 0
+		0x110 0 0 0
+		0x111 0 0 0
+		0x112 0 0 0
+		0x113 0 0 0
+		0x114 0 0 0
+		0x115 0 0 0
+		0x116 0 0 0
+		0x117 0 0 0>;
+};
+
+msi3: msi@41c00 {
+	compatible = "fsl,mpic-msi-v4.3";
+	reg = <0x41c00 0x200 0x47148 4>;
+	interrupts = <
+		0xf8 0 0 0
+		0xf9 0 0 0
+		0xfa 0 0 0
+		0xfb 0 0 0
+		0xfc 0 0 0
+		0xfd 0 0 0
+		0xfe 0 0 0
+		0xff 0 0 0
+		0x118 0 0 0
+		0x119 0 0 0
+		0x11a 0 0 0
+		0x11b 0 0 0
+		0x11c 0 0 0
+		0x11d 0 0 0
+		0x11e 0 0 0
+		0x11f 0 0 0>;
+};
+
+timer@42100 {
+	compatible = "fsl,mpic-global-timer";
+	reg = <0x42100 0x100 0x42300 4>;
+	interrupts = <4 0 3 0
+		      5 0 3 0
+		      6 0 3 0
+		      7 0 3 0>;
+};
diff --git a/arch/powerpc/boot/dts/fsl/qoriq-sec6.0-0.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-sec6.0-0.dtsi
new file mode 100644
index 000000000000..f75b4f820c3c
--- /dev/null
+++ b/arch/powerpc/boot/dts/fsl/qoriq-sec6.0-0.dtsi
@@ -0,0 +1,56 @@
+/*
+ * QorIQ Sec/Crypto 6.0 device tree stub
+ *
+ * Copyright 2013 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in the
+ *       documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Freescale Semiconductor nor the
+ *       names of its contributors may be used to endorse or promote products
+ *       derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+	compatible = "fsl,sec-v6.0";
+	fsl,sec-era = <6>;
+	#address-cells = <1>;
+	#size-cells = <1>;
+
+	jr@1000 {
+		compatible = "fsl,sec-v6.0-job-ring",
+			     "fsl,sec-v5.2-job-ring",
+			     "fsl,sec-v5.0-job-ring",
+			     "fsl,sec-v4.4-job-ring",
+			     "fsl,sec-v4.0-job-ring";
+		reg	   = <0x1000 0x1000>;
+	};
+
+	jr@2000 {
+		compatible = "fsl,sec-v6.0-job-ring",
+			     "fsl,sec-v5.2-job-ring",
+			     "fsl,sec-v5.0-job-ring",
+			     "fsl,sec-v4.4-job-ring",
+			     "fsl,sec-v4.0-job-ring";
+		reg	   = <0x2000 0x1000>;
+	};
diff --git a/arch/powerpc/boot/dts/fsl/t4240si-post.dtsi b/arch/powerpc/boot/dts/fsl/t4240si-post.dtsi
index bd611a9cad32..510afa362de1 100644
--- a/arch/powerpc/boot/dts/fsl/t4240si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/t4240si-post.dtsi
@@ -358,7 +358,7 @@
 			16 2 1 30>;
 	};
 
-/include/ "qoriq-mpic.dtsi"
+/include/ "qoriq-mpic4.3.dtsi"
 
 	guts: global-utilities@e0000 {
 		compatible = "fsl,t4240-device-config", "fsl,qoriq-device-config-2.0";
diff --git a/arch/powerpc/boot/dts/include/dt-bindings b/arch/powerpc/boot/dts/include/dt-bindings
new file mode 120000
index 000000000000..08c00e4972fa
--- /dev/null
+++ b/arch/powerpc/boot/dts/include/dt-bindings
@@ -0,0 +1 @@
+../../../../../include/dt-bindings
+\ No newline at end of file
diff --git a/arch/powerpc/boot/dts/mpc5121ads.dts b/arch/powerpc/boot/dts/mpc5121ads.dts
index 7d3cb79185cb..c228a0a232a6 100644
--- a/arch/powerpc/boot/dts/mpc5121ads.dts
+++ b/arch/powerpc/boot/dts/mpc5121ads.dts
@@ -9,7 +9,7 @@
  * option) any later version.
  */
 
-/include/ "mpc5121.dtsi"
+#include <mpc5121.dtsi>
 
 / {
 	model = "mpc5121ads";
diff --git a/arch/powerpc/boot/dts/p1020rdb-pd.dts b/arch/powerpc/boot/dts/p1020rdb-pd.dts
new file mode 100644
index 000000000000..987017ea36b6
--- /dev/null
+++ b/arch/powerpc/boot/dts/p1020rdb-pd.dts
@@ -0,0 +1,280 @@
+/*
+ * P1020 RDB-PD Device Tree Source (32-bit address map)
+ *
+ * Copyright 2013 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in the
+ *       documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Freescale Semiconductor nor the
+ *       names of its contributors may be used to endorse or promote products
+ *       derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+/include/ "fsl/p1020si-pre.dtsi"
+/ {
+	model = "fsl,P1020RDB-PD";
+	compatible = "fsl,P1020RDB-PD";
+
+	memory {
+		device_type = "memory";
+	};
+
+	lbc: localbus@ffe05000 {
+		reg = <0x0 0xffe05000 0x0 0x1000>;
+
+		/* NOR, NAND flash, L2 switch and CPLD */
+		ranges = <0x0 0x0 0x0 0xec000000 0x04000000
+			  0x1 0x0 0x0 0xff800000 0x00040000
+			  0x2 0x0 0x0 0xffa00000 0x00020000
+			  0x3 0x0 0x0 0xffb00000 0x00020000>;
+
+		nor@0,0 {
+			#address-cells = <1>;
+			#size-cells = <1>;
+			compatible = "cfi-flash";
+			reg = <0x0 0x0 0x4000000>;
+			bank-width = <2>;
+			device-width = <1>;
+
+			partition@0 {
+				/* 128KB for DTB Image */
+				reg = <0x0 0x00020000>;
+				label = "NOR DTB Image";
+			};
+
+			partition@20000 {
+				/* 3.875 MB for Linux Kernel Image */
+				reg = <0x00020000 0x003e0000>;
+				label = "NOR Linux Kernel Image";
+			};
+
+			partition@400000 {
+				/* 58MB for Root file System */
+				reg = <0x00400000 0x03a00000>;
+				label = "NOR Root File System";
+			};
+
+			partition@3e00000 {
+				/* This location must not be altered  */
+				/* 1M for Vitesse 7385 Switch firmware */
+				reg = <0x3e00000 0x00100000>;
+				label = "NOR Vitesse-7385 Firmware";
+				read-only;
+			};
+
+			partition@3f00000 {
+				/* This location must not be altered  */
+				/* 512KB for u-boot Bootloader Image */
+				/* 512KB for u-boot Environment Variables */
+				reg = <0x03f00000 0x00100000>;
+				label = "NOR U-Boot Image";
+				read-only;
+			};
+		};
+
+		nand@1,0 {
+			#address-cells = <1>;
+			#size-cells = <1>;
+			compatible = "fsl,p1020-fcm-nand",
+				     "fsl,elbc-fcm-nand";
+			reg = <0x1 0x0 0x40000>;
+
+			partition@0 {
+				/* This location must not be altered  */
+				/* 1MB for u-boot Bootloader Image */
+				reg = <0x0 0x00100000>;
+				label = "NAND U-Boot Image";
+				read-only;
+			};
+
+			partition@100000 {
+				/* 1MB for DTB Image */
+				reg = <0x00100000 0x00100000>;
+				label = "NAND DTB Image";
+			};
+
+			partition@200000 {
+				/* 4MB for Linux Kernel Image */
+				reg = <0x00200000 0x00400000>;
+				label = "NAND Linux Kernel Image";
+			};
+
+			partition@600000 {
+				/* 122MB for File System Image */
+				reg = <0x00600000 0x07a00000>;
+				label = "NAND File System Image";
+			};
+		};
+
+		cpld@2,0 {
+			compatible = "fsl,p1020rdb-pd-cpld";
+			reg = <0x2 0x0 0x20000>;
+		};
+
+		L2switch@3,0 {
+			#address-cells = <1>;
+			#size-cells = <1>;
+			compatible = "vitesse-7385";
+			reg = <0x3 0x0 0x20000>;
+		};
+	};
+
+	soc: soc@ffe00000 {
+		ranges = <0x0 0x0 0xffe00000 0x100000>;
+
+		i2c@3000 {
+			rtc@68 {
+				compatible = "dallas,ds1339";
+				reg = <0x68>;
+			};
+		};
+
+		spi@7000 {
+			flash@0 {
+				#address-cells = <1>;
+				#size-cells = <1>;
+				compatible = "spansion,s25sl12801";
+				reg = <0>;
+				/* input clock */
+				spi-max-frequency = <40000000>;
+
+				partition@0 {
+					/* 512KB for u-boot Bootloader Image */
+					reg = <0x0 0x00080000>;
+					label = "SPI U-Boot Image";
+					read-only;
+				};
+
+				partition@80000 {
+					/* 512KB for DTB Image*/
+					reg = <0x00080000 0x00080000>;
+					label = "SPI DTB Image";
+				};
+
+				partition@100000 {
+					/* 4MB for Linux Kernel Image */
+					reg = <0x00100000 0x00400000>;
+					label = "SPI Linux Kernel Image";
+				};
+
+				partition@500000 {
+					/* 11MB for FS System Image */
+					reg = <0x00500000 0x00b00000>;
+					label = "SPI File System Image";
+				};
+			};
+
+			slic@0 {
+				compatible = "zarlink,le88266";
+				reg = <1>;
+				spi-max-frequency = <8000000>;
+			};
+
+			slic@1 {
+				compatible = "zarlink,le88266";
+				reg = <2>;
+				spi-max-frequency = <8000000>;
+			};
+		};
+
+		mdio@24000 {
+			phy0: ethernet-phy@0 {
+				interrupts = <3 1 0 0>;
+				reg = <0x0>;
+			};
+
+			phy1: ethernet-phy@1 {
+				interrupts = <2 1 0 0>;
+				reg = <0x1>;
+			};
+		};
+
+		mdio@25000 {
+			tbi1: tbi-phy@11 {
+				reg = <0x11>;
+				device_type = "tbi-phy";
+			};
+		};
+
+		mdio@26000 {
+			tbi2: tbi-phy@11 {
+				reg = <0x11>;
+				device_type = "tbi-phy";
+			};
+		};
+
+		enet0: ethernet@b0000 {
+			fixed-link = <1 1 1000 0 0>;
+			phy-connection-type = "rgmii-id";
+		};
+
+		enet1: ethernet@b1000 {
+			phy-handle = <&phy0>;
+			tbi-handle = <&tbi1>;
+			phy-connection-type = "sgmii";
+		};
+
+		enet2: ethernet@b2000 {
+			phy-handle = <&phy1>;
+			phy-connection-type = "rgmii-id";
+		};
+
+		usb@22000 {
+			phy_type = "ulpi";
+		};
+	};
+
+	pci0: pcie@ffe09000 {
+		reg = <0x0 0xffe09000 0x0 0x1000>;
+		ranges = <0x2000000 0x0 0xa0000000 0x0 0xa0000000 0x0 0x20000000
+			  0x1000000 0x0 0x00000000 0x0 0xffc10000 0x0 0x10000>;
+		pcie@0 {
+			ranges = <0x2000000 0x0 0xa0000000
+				  0x2000000 0x0 0xa0000000
+				  0x0 0x20000000
+
+				  0x1000000 0x0 0x0
+				  0x1000000 0x0 0x0
+				  0x0 0x100000>;
+		};
+	};
+
+	pci1: pcie@ffe0a000 {
+		reg = <0x0 0xffe0a000 0x0 0x1000>;
+		ranges = <0x2000000 0x0 0x80000000 0x0 0x80000000 0x0 0x20000000
+			  0x1000000 0x0 0x00000000 0x0 0xffc00000 0x0 0x10000>;
+		pcie@0 {
+			ranges = <0x2000000 0x0 0x80000000
+				  0x2000000 0x0 0x80000000
+				  0x0 0x20000000
+
+				  0x1000000 0x0 0x0
+				  0x1000000 0x0 0x0
+				  0x0 0x100000>;
+		};
+	};
+};
+
+/include/ "fsl/p1020si-post.dtsi"
diff --git a/arch/powerpc/boot/dts/p1023rdb.dts b/arch/powerpc/boot/dts/p1023rdb.dts
new file mode 100644
index 000000000000..0a06a88ddbd5
--- /dev/null
+++ b/arch/powerpc/boot/dts/p1023rdb.dts
@@ -0,0 +1,234 @@
+/*
+ * P1023 RDB Device Tree Source
+ *
+ *    Copyright 2013 Freescale Semiconductor Inc.
+ *
+ * Author: Chunhe Lan <Chunhe.Lan@freescale.com>
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in the
+ *       documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Freescale Semiconductor nor the
+ *       names of its contributors may be used to endorse or promote products
+ *       derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+/include/ "fsl/p1023si-pre.dtsi"
+
+/ {
+	model = "fsl,P1023";
+	compatible = "fsl,P1023RDB";
+	#address-cells = <2>;
+	#size-cells = <2>;
+	interrupt-parent = <&mpic>;
+
+	memory {
+		device_type = "memory";
+	};
+
+	soc: soc@ff600000 {
+		ranges = <0x0 0x0 0xff600000 0x200000>;
+
+		i2c@3000 {
+			eeprom@53 {
+				compatible = "at24,24c04";
+				reg = <0x53>;
+			};
+
+			rtc@6f {
+				compatible = "microchip,mcp7941x";
+				reg = <0x6f>;
+			};
+		};
+
+		usb@22000 {
+			dr_mode = "host";
+			phy_type = "ulpi";
+		};
+	};
+
+	lbc: localbus@ff605000 {
+		reg = <0 0xff605000 0 0x1000>;
+
+		/* NOR, NAND Flashes */
+		ranges = <0x0 0x0 0x0 0xec000000 0x04000000
+			  0x1 0x0 0x0 0xffa00000 0x08000000>;
+
+		nor@0,0 {
+			#address-cells = <1>;
+			#size-cells = <1>;
+			compatible = "cfi-flash";
+			reg = <0x0 0x0 0x04000000>;
+			bank-width = <2>;
+			device-width = <1>;
+
+			partition@0 {
+				/* 48MB for Root File System */
+				reg = <0x00000000 0x03000000>;
+				label = "NOR Root File System";
+			};
+
+			partition@3000000 {
+				/* 1MB for DTB Image */
+				reg = <0x03000000 0x00100000>;
+				label = "NOR DTB Image";
+			};
+
+			partition@3100000 {
+				/* 14MB for Linux Kernel Image */
+				reg = <0x03100000 0x00e00000>;
+				label = "NOR Linux Kernel Image";
+			};
+
+			partition@3f00000 {
+				/* This location must not be altered  */
+				/* 512KB for u-boot Bootloader Image */
+				/* 512KB for u-boot Environment Variables */
+				reg = <0x03f00000 0x00100000>;
+				label = "NOR U-Boot Image";
+				read-only;
+			};
+		};
+
+		nand@1,0 {
+			#address-cells = <1>;
+			#size-cells = <1>;
+			compatible = "fsl,elbc-fcm-nand";
+			reg = <0x1 0x0 0x40000>;
+
+			partition@0 {
+				/* This location must not be altered  */
+				/* 1MB for u-boot Bootloader Image */
+				reg = <0x0 0x00100000>;
+				label = "NAND U-Boot Image";
+				read-only;
+			};
+
+			partition@100000 {
+				/* 1MB for DTB Image */
+				reg = <0x00100000 0x00100000>;
+				label = "NAND DTB Image";
+			};
+
+			partition@200000 {
+				/* 14MB for Linux Kernel Image */
+				reg = <0x00200000 0x00e00000>;
+				label = "NAND Linux Kernel Image";
+			};
+
+			partition@1000000 {
+				/* 96MB for Root File System Image */
+				reg = <0x01000000 0x06000000>;
+				label = "NAND Root File System";
+			};
+
+			partition@7000000 {
+				/* 16MB for User Writable Area */
+				reg = <0x07000000 0x01000000>;
+				label = "NAND Writable User area";
+			};
+		};
+	};
+
+	pci0: pcie@ff60a000 {
+		reg = <0 0xff60a000 0 0x1000>;
+		ranges = <0x2000000 0x0 0xc0000000 0 0xc0000000 0x0 0x20000000
+			  0x1000000 0x0 0x00000000 0 0xffc20000 0x0 0x10000>;
+		pcie@0 {
+			/* IRQ[0:3] are pulled up on board, set to active-low */
+			interrupt-map-mask = <0xf800 0 0 7>;
+			interrupt-map = <
+				/* IDSEL 0x0 */
+				0000 0 0 1 &mpic 0 1 0 0
+				0000 0 0 2 &mpic 1 1 0 0
+				0000 0 0 3 &mpic 2 1 0 0
+				0000 0 0 4 &mpic 3 1 0 0
+				>;
+			ranges = <0x2000000 0x0 0xc0000000
+				  0x2000000 0x0 0xc0000000
+				  0x0 0x20000000
+
+				  0x1000000 0x0 0x0
+				  0x1000000 0x0 0x0
+				  0x0 0x100000>;
+		};
+	};
+
+	board_pci1: pci1: pcie@ff609000 {
+		reg = <0 0xff609000 0 0x1000>;
+		ranges = <0x2000000 0x0 0xa0000000 0 0xa0000000 0x0 0x20000000
+			  0x1000000 0x0 0x00000000 0 0xffc10000 0x0 0x10000>;
+		pcie@0 {
+			/*
+			 * IRQ[4:6] only for PCIe, set to active-high,
+			 * IRQ[7] is pulled up on board, set to active-low
+			 */
+			interrupt-map-mask = <0xf800 0 0 7>;
+			interrupt-map = <
+				/* IDSEL 0x0 */
+				0000 0 0 1 &mpic 4 2 0 0
+				0000 0 0 2 &mpic 5 2 0 0
+				0000 0 0 3 &mpic 6 2 0 0
+				0000 0 0 4 &mpic 7 1 0 0
+				>;
+			ranges = <0x2000000 0x0 0xa0000000
+				  0x2000000 0x0 0xa0000000
+				  0x0 0x20000000
+
+				  0x1000000 0x0 0x0
+				  0x1000000 0x0 0x0
+				  0x0 0x100000>;
+		};
+	};
+
+	pci2: pcie@ff60b000 {
+		reg = <0 0xff60b000 0 0x1000>;
+		ranges = <0x2000000 0x0 0x80000000 0 0x80000000 0x0 0x20000000
+			  0x1000000 0x0 0x00000000 0 0xffc00000 0x0 0x10000>;
+		pcie@0 {
+			/*
+			 * IRQ[8:10] are pulled up on board, set to active-low
+			 * IRQ[11] only for PCIe, set to active-high,
+			 */
+			interrupt-map-mask = <0xf800 0 0 7>;
+			interrupt-map = <
+				/* IDSEL 0x0 */
+				0000 0 0 1 &mpic 8 1 0 0
+				0000 0 0 2 &mpic 9 1 0 0
+				0000 0 0 3 &mpic 10 1 0 0
+				0000 0 0 4 &mpic 11 2 0 0
+				>;
+			ranges = <0x2000000 0x0 0x80000000
+				  0x2000000 0x0 0x80000000
+				  0x0 0x20000000
+
+				  0x1000000 0x0 0x0
+				  0x1000000 0x0 0x0
+				  0x0 0x100000>;
+		};
+	};
+
+};
+
+/include/ "fsl/p1023si-post.dtsi"
diff --git a/arch/powerpc/boot/dts/pdm360ng.dts b/arch/powerpc/boot/dts/pdm360ng.dts
index 74337403faee..871c16d1ad5e 100644
--- a/arch/powerpc/boot/dts/pdm360ng.dts
+++ b/arch/powerpc/boot/dts/pdm360ng.dts
@@ -13,7 +13,7 @@
  * option) any later version.
  */
 
-/include/ "mpc5121.dtsi"
+#include <mpc5121.dtsi>
 
 / {
 	model = "pdm360ng";
diff --git a/arch/powerpc/boot/epapr-wrapper.c b/arch/powerpc/boot/epapr-wrapper.c
new file mode 100644
index 000000000000..c10191006673
--- /dev/null
+++ b/arch/powerpc/boot/epapr-wrapper.c
@@ -0,0 +1,9 @@
+extern void epapr_platform_init(unsigned long r3, unsigned long r4,
+				unsigned long r5, unsigned long r6,
+				unsigned long r7);
+
+void platform_init(unsigned long r3, unsigned long r4, unsigned long r5,
+		   unsigned long r6, unsigned long r7)
+{
+	epapr_platform_init(r3, r4, r5, r6, r7);
+}
diff --git a/arch/powerpc/boot/epapr.c b/arch/powerpc/boot/epapr.c
index 06c1961bd124..02e91aa2194a 100644
--- a/arch/powerpc/boot/epapr.c
+++ b/arch/powerpc/boot/epapr.c
@@ -48,8 +48,8 @@ static void platform_fixups(void)
 		       fdt_addr, fdt_totalsize((void *)fdt_addr), ima_size);
 }
 
-void platform_init(unsigned long r3, unsigned long r4, unsigned long r5,
-		   unsigned long r6, unsigned long r7)
+void epapr_platform_init(unsigned long r3, unsigned long r4, unsigned long r5,
+			 unsigned long r6, unsigned long r7)
 {
 	epapr_magic = r6;
 	ima_size = r7;
diff --git a/arch/powerpc/boot/of.c b/arch/powerpc/boot/of.c
index 61d9899aa0d0..62e2f43ec1df 100644
--- a/arch/powerpc/boot/of.c
+++ b/arch/powerpc/boot/of.c
@@ -26,6 +26,9 @@
 
 static unsigned long claim_base;
 
+void epapr_platform_init(unsigned long r3, unsigned long r4, unsigned long r5,
+			 unsigned long r6, unsigned long r7);
+
 static void *of_try_claim(unsigned long size)
 {
 	unsigned long addr = 0;
@@ -61,7 +64,7 @@ static void of_image_hdr(const void *hdr)
 	}
 }
 
-void platform_init(unsigned long a1, unsigned long a2, void *promptr)
+static void of_platform_init(unsigned long a1, unsigned long a2, void *promptr)
 {
 	platform_ops.image_hdr = of_image_hdr;
 	platform_ops.malloc = of_try_claim;
@@ -81,3 +84,14 @@ void platform_init(unsigned long a1, unsigned long a2, void *promptr)
 		loader_info.initrd_size = a2;
 	}
 }
+
+void platform_init(unsigned long r3, unsigned long r4, unsigned long r5,
+		   unsigned long r6, unsigned long r7)
+{
+	/* Detect OF vs. ePAPR boot */
+	if (r5)
+		of_platform_init(r3, r4, (void *)r5);
+	else
+		epapr_platform_init(r3, r4, r5, r6, r7);
+}
+
diff --git a/arch/powerpc/boot/ppc_asm.h b/arch/powerpc/boot/ppc_asm.h
index 1c2c2817f9b7..eb0e98be69e0 100644
--- a/arch/powerpc/boot/ppc_asm.h
+++ b/arch/powerpc/boot/ppc_asm.h
@@ -59,4 +59,7 @@
 #define	r30	30
 #define	r31	31
 
+#define SPRN_TBRL	268
+#define SPRN_TBRU	269
+
 #endif /* _PPC64_PPC_ASM_H */
diff --git a/arch/powerpc/boot/util.S b/arch/powerpc/boot/util.S
index 427ddfc11991..5143228e3e5f 100644
--- a/arch/powerpc/boot/util.S
+++ b/arch/powerpc/boot/util.S
@@ -71,18 +71,18 @@ udelay:
 	add	r4,r4,r5
 	addi	r4,r4,-1
 	divw	r4,r4,r5	/* BUS ticks */
-1:	mftbu	r5
-	mftb	r6
-	mftbu	r7
+1:	mfspr	r5, SPRN_TBRU
+	mfspr	r6, SPRN_TBRL
+	mfspr	r7, SPRN_TBRU
 	cmpw	0,r5,r7
 	bne	1b		/* Get [synced] base time */
 	addc	r9,r6,r4	/* Compute end time */
 	addze	r8,r5
-2:	mftbu	r5
+2:	mfspr	r5, SPRN_TBRU
 	cmpw	0,r5,r8
 	blt	2b
 	bgt	3f
-	mftb	r6
+	mfspr	r6, SPRN_TBRL
 	cmpw	0,r6,r9
 	blt	2b
 3:	blr
diff --git a/arch/powerpc/boot/wrapper b/arch/powerpc/boot/wrapper
index 6761c746048d..cd7af841ba05 100755
--- a/arch/powerpc/boot/wrapper
+++ b/arch/powerpc/boot/wrapper
@@ -148,18 +148,18 @@ make_space=y
 
 case "$platform" in
 pseries)
-    platformo=$object/of.o
+    platformo="$object/of.o $object/epapr.o"
     link_address='0x4000000'
     ;;
 maple)
-    platformo=$object/of.o
+    platformo="$object/of.o $object/epapr.o"
     link_address='0x400000'
     ;;
 pmac|chrp)
-    platformo=$object/of.o
+    platformo="$object/of.o $object/epapr.o"
     ;;
 coff)
-    platformo="$object/crt0.o $object/of.o"
+    platformo="$object/crt0.o $object/of.o $object/epapr.o"
     lds=$object/zImage.coff.lds
     link_address='0x500000'
     pie=
@@ -253,6 +253,7 @@ treeboot-iss4xx-mpic)
     platformo="$object/treeboot-iss4xx.o"
     ;;
 epapr)
+    platformo="$object/epapr.o $object/epapr-wrapper.o"
     link_address='0x20000000'
     pie=-pie
     ;;
diff --git a/arch/powerpc/configs/85xx/p1023rds_defconfig b/arch/powerpc/configs/85xx/p1023_defconfig
index b80bcc69d1f7..b06d37da44f4 100644
--- a/arch/powerpc/configs/85xx/p1023rds_defconfig
+++ b/arch/powerpc/configs/85xx/p1023_defconfig
@@ -1,14 +1,13 @@
 CONFIG_PPC_85xx=y
 CONFIG_SMP=y
 CONFIG_NR_CPUS=2
-CONFIG_EXPERIMENTAL=y
 CONFIG_SYSVIPC=y
 CONFIG_POSIX_MQUEUE=y
 CONFIG_BSD_PROCESS_ACCT=y
 CONFIG_AUDIT=y
-CONFIG_IRQ_DOMAIN_DEBUG=y
 CONFIG_NO_HZ=y
 CONFIG_HIGH_RES_TIMERS=y
+CONFIG_RCU_FANOUT=32
 CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
 CONFIG_LOG_BUF_SHIFT=14
@@ -22,6 +21,8 @@ CONFIG_MODVERSIONS=y
 # CONFIG_BLK_DEV_BSG is not set
 CONFIG_PARTITION_ADVANCED=y
 CONFIG_MAC_PARTITION=y
+CONFIG_PHYSICAL_START=0x00000000
+CONFIG_P1023_RDB=y
 CONFIG_P1023_RDS=y
 CONFIG_QUICC_ENGINE=y
 CONFIG_QE_GPIO=y
@@ -63,10 +64,21 @@ CONFIG_IPV6=y
 CONFIG_IP_SCTP=m
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_DEVTMPFS=y
+CONFIG_DEVTMPFS_MOUNT=y
+CONFIG_MTD=y
+CONFIG_MTD_CMDLINE_PARTS=y
+CONFIG_MTD_CHAR=y
+CONFIG_MTD_BLOCK=y
+CONFIG_MTD_CFI=y
+CONFIG_MTD_CFI_AMDSTD=y
+CONFIG_MTD_PHYSMAP_OF=y
+CONFIG_MTD_NAND=y
+CONFIG_MTD_NAND_FSL_ELBC=y
 CONFIG_PROC_DEVICETREE=y
 CONFIG_BLK_DEV_LOOP=y
 CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_RAM_SIZE=131072
+CONFIG_EEPROM_AT24=y
 CONFIG_EEPROM_LEGACY=y
 CONFIG_BLK_DEV_SD=y
 CONFIG_CHR_DEV_ST=y
@@ -82,6 +94,8 @@ CONFIG_DUMMY=y
 CONFIG_FS_ENET=y
 CONFIG_FSL_PQ_MDIO=y
 CONFIG_E1000E=y
+CONFIG_PHYLIB=y
+CONFIG_AT803X_PHY=y
 CONFIG_MARVELL_PHY=y
 CONFIG_DAVICOM_PHY=y
 CONFIG_CICADA_PHY=y
@@ -96,12 +110,15 @@ CONFIG_SERIAL_8250=y
 CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_SERIAL_8250_NR_UARTS=2
 CONFIG_SERIAL_8250_RUNTIME_UARTS=2
+CONFIG_SERIAL_8250_EXTENDED=y
 CONFIG_SERIAL_8250_MANY_PORTS=y
+CONFIG_SERIAL_8250_SHARE_IRQ=y
 CONFIG_SERIAL_8250_DETECT_IRQ=y
 CONFIG_SERIAL_8250_RSA=y
-CONFIG_SERIAL_QE=m
+CONFIG_HW_RANDOM=y
 CONFIG_NVRAM=y
 CONFIG_I2C=y
+CONFIG_I2C_CHARDEV=y
 CONFIG_I2C_CPM=m
 CONFIG_I2C_MPC=y
 CONFIG_GPIO_MPC8XXX=y
@@ -121,6 +138,7 @@ CONFIG_USB_STORAGE=y
 CONFIG_EDAC=y
 CONFIG_EDAC_MM_EDAC=y
 CONFIG_RTC_CLASS=y
+CONFIG_RTC_DRV_DS1307=y
 CONFIG_RTC_DRV_CMOS=y
 CONFIG_DMADEVICES=y
 CONFIG_FSL_DMA=y
@@ -161,6 +179,7 @@ CONFIG_DEBUG_FS=y
 CONFIG_DETECT_HUNG_TASK=y
 # CONFIG_DEBUG_BUGVERBOSE is not set
 CONFIG_DEBUG_INFO=y
+CONFIG_STRICT_DEVMEM=y
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_SHA256=y
 CONFIG_CRYPTO_SHA512=y
diff --git a/arch/powerpc/configs/corenet32_smp_defconfig b/arch/powerpc/configs/corenet32_smp_defconfig
index 60027c2a7034..3dfab4c40c76 100644
--- a/arch/powerpc/configs/corenet32_smp_defconfig
+++ b/arch/powerpc/configs/corenet32_smp_defconfig
@@ -70,6 +70,7 @@ CONFIG_IPV6=y
 CONFIG_IP_SCTP=m
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_DEVTMPFS=y
+CONFIG_DEVTMPFS_MOUNT=y
 CONFIG_MTD=y
 CONFIG_MTD_CMDLINE_PARTS=y
 CONFIG_MTD_CHAR=y
diff --git a/arch/powerpc/configs/corenet64_smp_defconfig b/arch/powerpc/configs/corenet64_smp_defconfig
index 6c8b020806ff..fa94fb3bb44d 100644
--- a/arch/powerpc/configs/corenet64_smp_defconfig
+++ b/arch/powerpc/configs/corenet64_smp_defconfig
@@ -27,6 +27,8 @@ CONFIG_P5040_DS=y
 CONFIG_T4240_QDS=y
 # CONFIG_PPC_OF_BOOT_TRAMPOLINE is not set
 CONFIG_BINFMT_MISC=m
+CONFIG_MATH_EMULATION=y
+CONFIG_MATH_EMULATION_HW_UNIMPLEMENTED=y
 CONFIG_FSL_IFC=y
 CONFIG_PCIEPORTBUS=y
 CONFIG_PCI_MSI=y
@@ -59,6 +61,7 @@ CONFIG_IPV6=y
 CONFIG_IP_SCTP=m
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_DEVTMPFS=y
+CONFIG_DEVTMPFS_MOUNT=y
 CONFIG_MTD=y
 CONFIG_MTD_PARTITIONS=y
 CONFIG_MTD_OF_PARTS=y
diff --git a/arch/powerpc/configs/mpc83xx_defconfig b/arch/powerpc/configs/mpc83xx_defconfig
index 09116c6a6719..23fec79964cf 100644
--- a/arch/powerpc/configs/mpc83xx_defconfig
+++ b/arch/powerpc/configs/mpc83xx_defconfig
@@ -42,6 +42,7 @@ CONFIG_INET_ESP=y
 # CONFIG_IPV6 is not set
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_DEVTMPFS=y
+CONFIG_DEVTMPFS_MOUNT=y
 # CONFIG_FW_LOADER is not set
 CONFIG_MTD=y
 CONFIG_MTD_CHAR=y
diff --git a/arch/powerpc/configs/mpc85xx_defconfig b/arch/powerpc/configs/mpc85xx_defconfig
index 5a58882e351e..dc098d988211 100644
--- a/arch/powerpc/configs/mpc85xx_defconfig
+++ b/arch/powerpc/configs/mpc85xx_defconfig
@@ -27,6 +27,7 @@ CONFIG_MPC85xx_MDS=y
 CONFIG_MPC8536_DS=y
 CONFIG_MPC85xx_DS=y
 CONFIG_MPC85xx_RDB=y
+CONFIG_C293_PCIE=y
 CONFIG_P1010_RDB=y
 CONFIG_P1022_DS=y
 CONFIG_P1022_RDK=y
@@ -78,6 +79,7 @@ CONFIG_IPV6=y
 CONFIG_IP_SCTP=m
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_DEVTMPFS=y
+CONFIG_DEVTMPFS_MOUNT=y
 CONFIG_MTD=y
 CONFIG_MTD_PARTITIONS=y
 CONFIG_MTD_OF_PARTS=y
diff --git a/arch/powerpc/configs/mpc85xx_smp_defconfig b/arch/powerpc/configs/mpc85xx_smp_defconfig
index 152fa05b15e4..5bca60161bb3 100644
--- a/arch/powerpc/configs/mpc85xx_smp_defconfig
+++ b/arch/powerpc/configs/mpc85xx_smp_defconfig
@@ -30,6 +30,7 @@ CONFIG_MPC85xx_MDS=y
 CONFIG_MPC8536_DS=y
 CONFIG_MPC85xx_DS=y
 CONFIG_MPC85xx_RDB=y
+CONFIG_C293_PCIE=y
 CONFIG_P1010_RDB=y
 CONFIG_P1022_DS=y
 CONFIG_P1022_RDK=y
@@ -81,6 +82,7 @@ CONFIG_IPV6=y
 CONFIG_IP_SCTP=m
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_DEVTMPFS=y
+CONFIG_DEVTMPFS_MOUNT=y
 CONFIG_MTD=y
 CONFIG_MTD_PARTITIONS=y
 CONFIG_MTD_OF_PARTS=y
diff --git a/arch/powerpc/include/asm/Kbuild b/arch/powerpc/include/asm/Kbuild
index 650757c300db..704e6f10ae80 100644
--- a/arch/powerpc/include/asm/Kbuild
+++ b/arch/powerpc/include/asm/Kbuild
@@ -2,3 +2,4 @@
 generic-y += clkdev.h
 generic-y += rwsem.h
 generic-y += trace_clock.h
+generic-y += vtime.h
+\ No newline at end of file
diff --git a/arch/powerpc/include/asm/asm-compat.h b/arch/powerpc/include/asm/asm-compat.h
index 6e82f5f9a6fd..4b237aa35660 100644
--- a/arch/powerpc/include/asm/asm-compat.h
+++ b/arch/powerpc/include/asm/asm-compat.h
@@ -32,6 +32,15 @@
 #define PPC_MTOCRF(FXM, RS) MTOCRF((FXM), RS)
 #define PPC_LR_STKOFF	16
 #define PPC_MIN_STKFRM	112
+
+#ifdef __BIG_ENDIAN__
+#define LDX_BE	stringify_in_c(ldx)
+#define STDX_BE	stringify_in_c(stdx)
+#else
+#define LDX_BE	stringify_in_c(ldbrx)
+#define STDX_BE	stringify_in_c(stdbrx)
+#endif
+
 #else /* 32-bit */
 
 /* operations for longs and pointers */
diff --git a/arch/powerpc/include/asm/btext.h b/arch/powerpc/include/asm/btext.h
index 906f46e31006..89fc382648bc 100644
--- a/arch/powerpc/include/asm/btext.h
+++ b/arch/powerpc/include/asm/btext.h
@@ -13,6 +13,7 @@ extern void btext_update_display(unsigned long phys, int width, int height,
 extern void btext_setup_display(int width, int height, int depth, int pitch,
 				unsigned long address);
 extern void btext_prepare_BAT(void);
+extern void btext_map(void);
 extern void btext_unmap(void);
 
 extern void btext_drawchar(char c);
diff --git a/arch/powerpc/include/asm/cacheflush.h b/arch/powerpc/include/asm/cacheflush.h
index b843e35122e8..5b9312220e84 100644
--- a/arch/powerpc/include/asm/cacheflush.h
+++ b/arch/powerpc/include/asm/cacheflush.h
@@ -32,13 +32,7 @@ extern void flush_dcache_page(struct page *page);
 
 extern void __flush_disable_L1(void);
 
-extern void __flush_icache_range(unsigned long, unsigned long);
-static inline void flush_icache_range(unsigned long start, unsigned long stop)
-{
-	if (!cpu_has_feature(CPU_FTR_COHERENT_ICACHE))
-		__flush_icache_range(start, stop);
-}
-
+extern void flush_icache_range(unsigned long, unsigned long);
 extern void flush_icache_user_range(struct vm_area_struct *vma,
 				    struct page *page, unsigned long addr,
 				    int len);
diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h
index 6f3887d884d2..0d4939ba48e7 100644
--- a/arch/powerpc/include/asm/cputable.h
+++ b/arch/powerpc/include/asm/cputable.h
@@ -371,14 +371,19 @@ extern const char *powerpc_base_platform;
 #define CPU_FTRS_E500MC	(CPU_FTR_USE_TB | CPU_FTR_NODSISRALIGN | \
 	    CPU_FTR_L2CSR | CPU_FTR_LWSYNC | CPU_FTR_NOEXECUTE | \
 	    CPU_FTR_DBELL | CPU_FTR_DEBUG_LVL_EXC | CPU_FTR_EMB_HV)
+/*
+ * e5500/e6500 erratum A-006958 is a timebase bug that can use the
+ * same workaround as CPU_FTR_CELL_TB_BUG.
+ */
 #define CPU_FTRS_E5500	(CPU_FTR_USE_TB | CPU_FTR_NODSISRALIGN | \
 	    CPU_FTR_L2CSR | CPU_FTR_LWSYNC | CPU_FTR_NOEXECUTE | \
 	    CPU_FTR_DBELL | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \
-	    CPU_FTR_DEBUG_LVL_EXC | CPU_FTR_EMB_HV)
+	    CPU_FTR_DEBUG_LVL_EXC | CPU_FTR_EMB_HV | CPU_FTR_CELL_TB_BUG)
 #define CPU_FTRS_E6500	(CPU_FTR_USE_TB | CPU_FTR_NODSISRALIGN | \
 	    CPU_FTR_L2CSR | CPU_FTR_LWSYNC | CPU_FTR_NOEXECUTE | \
 	    CPU_FTR_DBELL | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \
-	    CPU_FTR_DEBUG_LVL_EXC | CPU_FTR_EMB_HV | CPU_FTR_ALTIVEC_COMP)
+	    CPU_FTR_DEBUG_LVL_EXC | CPU_FTR_EMB_HV | CPU_FTR_ALTIVEC_COMP | \
+	    CPU_FTR_CELL_TB_BUG)
 #define CPU_FTRS_GENERIC_32	(CPU_FTR_COMMON | CPU_FTR_NODSISRALIGN)
 
 /* 64-bit CPUs */
diff --git a/arch/powerpc/include/asm/device.h b/arch/powerpc/include/asm/device.h
index 77e97dd0c15d..38faeded7d59 100644
--- a/arch/powerpc/include/asm/device.h
+++ b/arch/powerpc/include/asm/device.h
@@ -28,6 +28,9 @@ struct dev_archdata {
 		void		*iommu_table_base;
 	} dma_data;
 
+#ifdef CONFIG_IOMMU_API
+	void			*iommu_domain;
+#endif
 #ifdef CONFIG_SWIOTLB
 	dma_addr_t		max_direct_dma_addr;
 #endif
diff --git a/arch/powerpc/include/asm/emulated_ops.h b/arch/powerpc/include/asm/emulated_ops.h
index 63f2a22e9954..5a8b82aa7241 100644
--- a/arch/powerpc/include/asm/emulated_ops.h
+++ b/arch/powerpc/include/asm/emulated_ops.h
@@ -46,8 +46,6 @@ extern struct ppc_emulated {
 	struct ppc_emulated_entry unaligned;
 #ifdef CONFIG_MATH_EMULATION
 	struct ppc_emulated_entry math;
-#elif defined(CONFIG_8XX_MINIMAL_FPEMU)
-	struct ppc_emulated_entry 8xx;
 #endif
 #ifdef CONFIG_VSX
 	struct ppc_emulated_entry vsx;
diff --git a/arch/powerpc/include/asm/epapr_hcalls.h b/arch/powerpc/include/asm/epapr_hcalls.h
index d3d634274d2c..86b0ac79990c 100644
--- a/arch/powerpc/include/asm/epapr_hcalls.h
+++ b/arch/powerpc/include/asm/epapr_hcalls.h
@@ -105,6 +105,12 @@
 extern bool epapr_paravirt_enabled;
 extern u32 epapr_hypercall_start[];
 
+#ifdef CONFIG_EPAPR_PARAVIRT
+int __init epapr_paravirt_early_init(void);
+#else
+static inline int epapr_paravirt_early_init(void) { return 0; }
+#endif
+
 /*
  * We use "uintptr_t" to define a register because it's guaranteed to be a
  * 32-bit integer on a 32-bit platform, and a 64-bit integer on a 64-bit
diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h
index 07ca627e52c0..cca12f084842 100644
--- a/arch/powerpc/include/asm/exception-64s.h
+++ b/arch/powerpc/include/asm/exception-64s.h
@@ -48,17 +48,18 @@
 #define EX_LR		72
 #define EX_CFAR		80
 #define EX_PPR		88	/* SMT thread status register (priority) */
+#define EX_CTR		96
 
 #ifdef CONFIG_RELOCATABLE
 #define __EXCEPTION_RELON_PROLOG_PSERIES_1(label, h)			\
 	ld	r12,PACAKBASE(r13);	/* get high part of &label */	\
 	mfspr	r11,SPRN_##h##SRR0;	/* save SRR0 */			\
 	LOAD_HANDLER(r12,label);					\
-	mtlr	r12;							\
+	mtctr	r12;							\
 	mfspr	r12,SPRN_##h##SRR1;	/* and SRR1 */			\
 	li	r10,MSR_RI;						\
 	mtmsrd 	r10,1;			/* Set RI (EE=0) */		\
-	blr;
+	bctr;
 #else
 /* If not relocatable, we can jump directly -- and save messing with LR */
 #define __EXCEPTION_RELON_PROLOG_PSERIES_1(label, h)			\
@@ -97,18 +98,18 @@
 
 #if defined(CONFIG_RELOCATABLE)
 /*
- * If we support interrupts with relocation on AND we're a relocatable
- * kernel, we need to use LR to get to the 2nd level handler.  So, save/restore
- * it when required.
+ * If we support interrupts with relocation on AND we're a relocatable kernel,
+ * we need to use CTR to get to the 2nd level handler.  So, save/restore it
+ * when required.
  */
-#define SAVE_LR(reg, area)	mflr	reg ; 	std	reg,area+EX_LR(r13)
-#define GET_LR(reg, area) 			ld	reg,area+EX_LR(r13)
-#define RESTORE_LR(reg, area)	ld	reg,area+EX_LR(r13) ; mtlr reg
+#define SAVE_CTR(reg, area)	mfctr	reg ; 	std	reg,area+EX_CTR(r13)
+#define GET_CTR(reg, area) 			ld	reg,area+EX_CTR(r13)
+#define RESTORE_CTR(reg, area)	ld	reg,area+EX_CTR(r13) ; mtctr reg
 #else
-/* ...else LR is unused and in register. */
-#define SAVE_LR(reg, area)
-#define GET_LR(reg, area) 	mflr	reg
-#define RESTORE_LR(reg, area)
+/* ...else CTR is unused and in register. */
+#define SAVE_CTR(reg, area)
+#define GET_CTR(reg, area) 	mfctr	reg
+#define RESTORE_CTR(reg, area)
 #endif
 
 /*
@@ -164,7 +165,7 @@ END_FTR_SECTION_NESTED(ftr,ftr,943)
 #define __EXCEPTION_PROLOG_1(area, extra, vec)				\
 	OPT_SAVE_REG_TO_PACA(area+EX_PPR, r9, CPU_FTR_HAS_PPR);		\
 	OPT_SAVE_REG_TO_PACA(area+EX_CFAR, r10, CPU_FTR_CFAR);		\
-	SAVE_LR(r10, area);						\
+	SAVE_CTR(r10, area);						\
 	mfcr	r9;							\
 	extra(vec);							\
 	std	r11,area+EX_R11(r13);					\
@@ -270,7 +271,7 @@ do_kvm_##n:								\
 	sth	r1,PACA_TRAP_SAVE(r13);					   \
 	std	r3,area+EX_R3(r13);					   \
 	addi	r3,r13,area;		/* r3 -> where regs are saved*/	   \
-	RESTORE_LR(r1, area);						   \
+	RESTORE_CTR(r1, area);						   \
 	b	bad_stack;						   \
 3:	std	r9,_CCR(r1);		/* save CR in stackframe	*/ \
 	std	r11,_NIP(r1);		/* save SRR0 in stackframe	*/ \
@@ -298,10 +299,10 @@ do_kvm_##n:								\
 	ld	r10,area+EX_CFAR(r13);					   \
 	std	r10,ORIG_GPR3(r1);					   \
 	END_FTR_SECTION_NESTED(CPU_FTR_CFAR, CPU_FTR_CFAR, 66);		   \
-	GET_LR(r9,area);		/* Get LR, later save to stack	*/ \
+	mflr	r9;			/* Get LR, later save to stack	*/ \
 	ld	r2,PACATOC(r13);	/* get kernel TOC into r2	*/ \
 	std	r9,_LINK(r1);						   \
-	mfctr	r10;			/* save CTR in stackframe	*/ \
+	GET_CTR(r10, area);						   \
 	std	r10,_CTR(r1);						   \
 	lbz	r10,PACASOFTIRQEN(r13);				   \
 	mfspr	r11,SPRN_XER;		/* save XER in stackframe	*/ \
@@ -479,7 +480,7 @@ label##_relon_hv:							\
  */
 
 /* Exception addition: Hard disable interrupts */
-#define DISABLE_INTS	SOFT_DISABLE_INTS(r10,r11)
+#define DISABLE_INTS	RECONCILE_IRQ_STATE(r10,r11)
 
 #define ADD_NVGPRS				\
 	bl	.save_nvgprs
diff --git a/arch/powerpc/include/asm/fsl_pamu_stash.h b/arch/powerpc/include/asm/fsl_pamu_stash.h
new file mode 100644
index 000000000000..caa1b21c25cd
--- /dev/null
+++ b/arch/powerpc/include/asm/fsl_pamu_stash.h
@@ -0,0 +1,39 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ *
+ * Copyright (C) 2013 Freescale Semiconductor, Inc.
+ *
+ */
+
+#ifndef __FSL_PAMU_STASH_H
+#define __FSL_PAMU_STASH_H
+
+/* cache stash targets */
+enum pamu_stash_target {
+	PAMU_ATTR_CACHE_L1 = 1,
+	PAMU_ATTR_CACHE_L2,
+	PAMU_ATTR_CACHE_L3,
+};
+
+/*
+ * This attribute allows configuring stashig specific parameters
+ * in the PAMU hardware.
+ */
+
+struct pamu_stash_attribute {
+	u32 	cpu;	/* cpu number */
+	u32 	cache;	/* cache to stash to: L1,L2,L3 */
+};
+
+#endif  /* __FSL_PAMU_STASH_H */
diff --git a/arch/powerpc/include/asm/io.h b/arch/powerpc/include/asm/io.h
index dd15e5e37d6d..5a64757dc0d1 100644
--- a/arch/powerpc/include/asm/io.h
+++ b/arch/powerpc/include/asm/io.h
@@ -69,8 +69,18 @@ extern unsigned long pci_dram_offset;
 
 extern resource_size_t isa_mem_base;
 
-#if defined(CONFIG_PPC32) && defined(CONFIG_PPC_INDIRECT_IO)
-#error CONFIG_PPC_INDIRECT_IO is not yet supported on 32 bits
+/* Boolean set by platform if PIO accesses are suppored while _IO_BASE
+ * is not set or addresses cannot be translated to MMIO. This is typically
+ * set when the platform supports "special" PIO accesses via a non memory
+ * mapped mechanism, and allows things like the early udbg UART code to
+ * function.
+ */
+extern bool isa_io_special;
+
+#ifdef CONFIG_PPC32
+#if defined(CONFIG_PPC_INDIRECT_PIO) || defined(CONFIG_PPC_INDIRECT_MMIO)
+#error CONFIG_PPC_INDIRECT_{PIO,MMIO} are not yet supported on 32 bits
+#endif
 #endif
 
 /*
@@ -222,9 +232,9 @@ extern void _memcpy_toio(volatile void __iomem *dest, const void *src,
  * for PowerPC is as close as possible to the x86 version of these, and thus
  * provides fairly heavy weight barriers for the non-raw versions
  *
- * In addition, they support a hook mechanism when CONFIG_PPC_INDIRECT_IO
- * allowing the platform to provide its own implementation of some or all
- * of the accessors.
+ * In addition, they support a hook mechanism when CONFIG_PPC_INDIRECT_MMIO
+ * or CONFIG_PPC_INDIRECT_PIO are set allowing the platform to provide its
+ * own implementation of some or all of the accessors.
  */
 
 /*
@@ -240,8 +250,8 @@ extern void _memcpy_toio(volatile void __iomem *dest, const void *src,
 
 /* Indirect IO address tokens:
  *
- * When CONFIG_PPC_INDIRECT_IO is set, the platform can provide hooks
- * on all IOs. (Note that this is all 64 bits only for now)
+ * When CONFIG_PPC_INDIRECT_MMIO is set, the platform can provide hooks
+ * on all MMIOs. (Note that this is all 64 bits only for now)
  *
  * To help platforms who may need to differenciate MMIO addresses in
  * their hooks, a bitfield is reserved for use by the platform near the
@@ -263,11 +273,14 @@ extern void _memcpy_toio(volatile void __iomem *dest, const void *src,
  *
  * The direct IO mapping operations will then mask off those bits
  * before doing the actual access, though that only happen when
- * CONFIG_PPC_INDIRECT_IO is set, thus be careful when you use that
+ * CONFIG_PPC_INDIRECT_MMIO is set, thus be careful when you use that
  * mechanism
+ *
+ * For PIO, there is a separate CONFIG_PPC_INDIRECT_PIO which makes
+ * all PIO functions call through a hook.
  */
 
-#ifdef CONFIG_PPC_INDIRECT_IO
+#ifdef CONFIG_PPC_INDIRECT_MMIO
 #define PCI_IO_IND_TOKEN_MASK	0x0fff000000000000ul
 #define PCI_IO_IND_TOKEN_SHIFT	48
 #define PCI_FIX_ADDR(addr)						\
@@ -672,7 +685,7 @@ extern void __iomem * __ioremap_at(phys_addr_t pa, void *ea,
 extern void __iounmap_at(void *ea, unsigned long size);
 
 /*
- * When CONFIG_PPC_INDIRECT_IO is set, we use the generic iomap implementation
+ * When CONFIG_PPC_INDIRECT_PIO is set, we use the generic iomap implementation
  * which needs some additional definitions here. They basically allow PIO
  * space overall to be 1GB. This will work as long as we never try to use
  * iomap to map MMIO below 1GB which should be fine on ppc64
diff --git a/arch/powerpc/include/asm/irq.h b/arch/powerpc/include/asm/irq.h
index 0e40843a1c6e..41f13cec8a8f 100644
--- a/arch/powerpc/include/asm/irq.h
+++ b/arch/powerpc/include/asm/irq.h
@@ -69,9 +69,9 @@ extern struct thread_info *softirq_ctx[NR_CPUS];
 
 extern void irq_ctx_init(void);
 extern void call_do_softirq(struct thread_info *tp);
-extern int call_handle_irq(int irq, void *p1,
-			   struct thread_info *tp, void *func);
+extern void call_do_irq(struct pt_regs *regs, struct thread_info *tp);
 extern void do_IRQ(struct pt_regs *regs);
+extern void __do_irq(struct pt_regs *regs);
 
 int irq_choose_cpu(const struct cpumask *mask);
 
diff --git a/arch/powerpc/include/asm/irqflags.h b/arch/powerpc/include/asm/irqflags.h
index 6f9b6e23dc5a..f51a5580bfd0 100644
--- a/arch/powerpc/include/asm/irqflags.h
+++ b/arch/powerpc/include/asm/irqflags.h
@@ -40,9 +40,10 @@
 #define TRACE_DISABLE_INTS	TRACE_WITH_FRAME_BUFFER(.trace_hardirqs_off)
 
 /*
- * This is used by assembly code to soft-disable interrupts
+ * This is used by assembly code to soft-disable interrupts first and
+ * reconcile irq state.
  */
-#define SOFT_DISABLE_INTS(__rA, __rB)		\
+#define RECONCILE_IRQ_STATE(__rA, __rB)		\
 	lbz	__rA,PACASOFTIRQEN(r13);	\
 	lbz	__rB,PACAIRQHAPPENED(r13);	\
 	cmpwi	cr0,__rA,0;			\
@@ -58,7 +59,7 @@
 #define TRACE_ENABLE_INTS
 #define TRACE_DISABLE_INTS
 
-#define SOFT_DISABLE_INTS(__rA, __rB)		\
+#define RECONCILE_IRQ_STATE(__rA, __rB)		\
 	lbz	__rA,PACAIRQHAPPENED(r13);	\
 	li	__rB,0;				\
 	ori	__rA,__rA,PACA_IRQ_HARD_DIS;	\
diff --git a/arch/powerpc/include/asm/jump_label.h b/arch/powerpc/include/asm/jump_label.h
index ae098c438f00..f016bb699b5f 100644
--- a/arch/powerpc/include/asm/jump_label.h
+++ b/arch/powerpc/include/asm/jump_label.h
@@ -19,7 +19,7 @@
 
 static __always_inline bool arch_static_branch(struct static_key *key)
 {
-	asm goto("1:\n\t"
+	asm_volatile_goto("1:\n\t"
 		 "nop\n\t"
 		 ".pushsection __jump_table,  \"aw\"\n\t"
 		 JUMP_ENTRY_TYPE "1b, %l[l_yes], %c0\n\t"
diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h
index 08891d07aeb6..fa19e2f1a874 100644
--- a/arch/powerpc/include/asm/kvm_book3s.h
+++ b/arch/powerpc/include/asm/kvm_book3s.h
@@ -334,6 +334,27 @@ static inline u32 kvmppc_get_last_inst(struct kvm_vcpu *vcpu)
 	return r;
 }
 
+/*
+ * Like kvmppc_get_last_inst(), but for fetching a sc instruction.
+ * Because the sc instruction sets SRR0 to point to the following
+ * instruction, we have to fetch from pc - 4.
+ */
+static inline u32 kvmppc_get_last_sc(struct kvm_vcpu *vcpu)
+{
+	ulong pc = kvmppc_get_pc(vcpu) - 4;
+	struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
+	u32 r;
+
+	/* Load the instruction manually if it failed to do so in the
+	 * exit path */
+	if (svcpu->last_inst == KVM_INST_FETCH_FAILED)
+		kvmppc_ld(vcpu, &pc, sizeof(u32), &svcpu->last_inst, false);
+
+	r = svcpu->last_inst;
+	svcpu_put(svcpu);
+	return r;
+}
+
 static inline ulong kvmppc_get_fault_dar(struct kvm_vcpu *vcpu)
 {
 	struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
@@ -446,6 +467,23 @@ static inline u32 kvmppc_get_last_inst(struct kvm_vcpu *vcpu)
 	return vcpu->arch.last_inst;
 }
 
+/*
+ * Like kvmppc_get_last_inst(), but for fetching a sc instruction.
+ * Because the sc instruction sets SRR0 to point to the following
+ * instruction, we have to fetch from pc - 4.
+ */
+static inline u32 kvmppc_get_last_sc(struct kvm_vcpu *vcpu)
+{
+	ulong pc = kvmppc_get_pc(vcpu) - 4;
+
+	/* Load the instruction manually if it failed to do so in the
+	 * exit path */
+	if (vcpu->arch.last_inst == KVM_INST_FETCH_FAILED)
+		kvmppc_ld(vcpu, &pc, sizeof(u32), &vcpu->arch.last_inst, false);
+
+	return vcpu->arch.last_inst;
+}
+
 static inline ulong kvmppc_get_fault_dar(struct kvm_vcpu *vcpu)
 {
 	return vcpu->arch.fault_dar;
diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h
index a1ecb14e4442..86d638a3b359 100644
--- a/arch/powerpc/include/asm/kvm_book3s_64.h
+++ b/arch/powerpc/include/asm/kvm_book3s_64.h
@@ -37,7 +37,7 @@ static inline void svcpu_put(struct kvmppc_book3s_shadow_vcpu *svcpu)
 
 #ifdef CONFIG_KVM_BOOK3S_64_HV
 #define KVM_DEFAULT_HPT_ORDER	24	/* 16MB HPT by default */
-extern int kvm_hpt_order;		/* order of preallocated HPTs */
+extern unsigned long kvm_rma_pages;
 #endif
 
 #define VRMA_VSID	0x1ffffffUL	/* 1TB VSID reserved for VRMA */
@@ -100,7 +100,7 @@ static inline unsigned long compute_tlbie_rb(unsigned long v, unsigned long r,
 			/* (masks depend on page size) */
 			rb |= 0x1000;		/* page encoding in LP field */
 			rb |= (va_low & 0x7f) << 16; /* 7b of VA in AVA/LP field */
-			rb |= (va_low & 0xfe);	/* AVAL field (P7 doesn't seem to care) */
+			rb |= ((va_low << 4) & 0xf0);	/* AVAL field (P7 doesn't seem to care) */
 		}
 	} else {
 		/* 4kB page */
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index af326cde7cb6..33283532e9d8 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -183,13 +183,9 @@ struct kvmppc_spapr_tce_table {
 	struct page *pages[0];
 };
 
-struct kvmppc_linear_info {
-	void		*base_virt;
-	unsigned long	 base_pfn;
-	unsigned long	 npages;
-	struct list_head list;
-	atomic_t	 use_count;
-	int		 type;
+struct kvm_rma_info {
+	atomic_t use_count;
+	unsigned long base_pfn;
 };
 
 /* XICS components, defined in book3s_xics.c */
@@ -246,7 +242,7 @@ struct kvm_arch {
 	int tlbie_lock;
 	unsigned long lpcr;
 	unsigned long rmor;
-	struct kvmppc_linear_info *rma;
+	struct kvm_rma_info *rma;
 	unsigned long vrma_slb_v;
 	int rma_setup_done;
 	int using_mmu_notifiers;
@@ -259,7 +255,7 @@ struct kvm_arch {
 	spinlock_t slot_phys_lock;
 	cpumask_t need_tlb_flush;
 	struct kvmppc_vcore *vcores[KVM_MAX_VCORES];
-	struct kvmppc_linear_info *hpt_li;
+	int hpt_cma_alloc;
 #endif /* CONFIG_KVM_BOOK3S_64_HV */
 #ifdef CONFIG_PPC_BOOK3S_64
 	struct list_head spapr_tce_tables;
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index a5287fe03d77..b15554a26c20 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -137,10 +137,10 @@ extern long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
 			     unsigned long ioba, unsigned long tce);
 extern long kvm_vm_ioctl_allocate_rma(struct kvm *kvm,
 				struct kvm_allocate_rma *rma);
-extern struct kvmppc_linear_info *kvm_alloc_rma(void);
-extern void kvm_release_rma(struct kvmppc_linear_info *ri);
-extern struct kvmppc_linear_info *kvm_alloc_hpt(void);
-extern void kvm_release_hpt(struct kvmppc_linear_info *li);
+extern struct kvm_rma_info *kvm_alloc_rma(void);
+extern void kvm_release_rma(struct kvm_rma_info *ri);
+extern struct page *kvm_alloc_hpt(unsigned long nr_pages);
+extern void kvm_release_hpt(struct page *page, unsigned long nr_pages);
 extern int kvmppc_core_init_vm(struct kvm *kvm);
 extern void kvmppc_core_destroy_vm(struct kvm *kvm);
 extern void kvmppc_core_free_memslot(struct kvm_memory_slot *free,
@@ -261,6 +261,7 @@ void kvmppc_set_pid(struct kvm_vcpu *vcpu, u32 pid);
 struct openpic;
 
 #ifdef CONFIG_KVM_BOOK3S_64_HV
+extern void kvm_cma_reserve(void) __init;
 static inline void kvmppc_set_xics_phys(int cpu, unsigned long addr)
 {
 	paca[cpu].kvm_hstate.xics_phys = addr;
@@ -281,13 +282,12 @@ static inline void kvmppc_set_host_ipi(int cpu, u8 host_ipi)
 }
 
 extern void kvmppc_fast_vcpu_kick(struct kvm_vcpu *vcpu);
-extern void kvm_linear_init(void);
 
 #else
-static inline void kvmppc_set_xics_phys(int cpu, unsigned long addr)
+static inline void __init kvm_cma_reserve(void)
 {}
 
-static inline void kvm_linear_init(void)
+static inline void kvmppc_set_xics_phys(int cpu, unsigned long addr)
 {}
 
 static inline u32 kvmppc_get_xics_latch(void)
@@ -394,10 +394,15 @@ static inline void kvmppc_mmu_flush_icache(pfn_t pfn)
 	}
 }
 
-/* Please call after prepare_to_enter. This function puts the lazy ee state
-   back to normal mode, without actually enabling interrupts. */
-static inline void kvmppc_lazy_ee_enable(void)
+/*
+ * Please call after prepare_to_enter. This function puts the lazy ee and irq
+ * disabled tracking state back to normal mode, without actually enabling
+ * interrupts.
+ */
+static inline void kvmppc_fix_ee_before_entry(void)
 {
+	trace_hardirqs_on();
+
 #ifdef CONFIG_PPC64
 	/* Only need to enable IRQs by hard enabling them after this */
 	local_paca->irq_happened = 0;
diff --git a/arch/powerpc/include/asm/lppaca.h b/arch/powerpc/include/asm/lppaca.h
index 9b12f88d4adb..4470d1e34d23 100644
--- a/arch/powerpc/include/asm/lppaca.h
+++ b/arch/powerpc/include/asm/lppaca.h
@@ -48,15 +48,13 @@
 struct lppaca {
 	/* cacheline 1 contains read-only data */
 
-	u32	desc;			/* Eye catcher 0xD397D781 */
-	u16	size;			/* Size of this struct */
-	u16	reserved1;
-	u16	reserved2:14;
-	u8	shared_proc:1;		/* Shared processor indicator */
-	u8	secondary_thread:1;	/* Secondary thread indicator */
+	__be32	desc;			/* Eye catcher 0xD397D781 */
+	__be16	size;			/* Size of this struct */
+	u8	reserved1[3];
+	u8	__old_status;		/* Old status, including shared proc */
 	u8	reserved3[14];
-	volatile u32 dyn_hw_node_id;	/* Dynamic hardware node id */
-	volatile u32 dyn_hw_proc_id;	/* Dynamic hardware proc id */
+	volatile __be32 dyn_hw_node_id;	/* Dynamic hardware node id */
+	volatile __be32 dyn_hw_proc_id;	/* Dynamic hardware proc id */
 	u8	reserved4[56];
 	volatile u8 vphn_assoc_counts[8]; /* Virtual processor home node */
 					  /* associativity change counters */
@@ -73,9 +71,9 @@ struct lppaca {
 	u8	fpregs_in_use;
 	u8	pmcregs_in_use;
 	u8	reserved8[28];
-	u64	wait_state_cycles;	/* Wait cycles for this proc */
+	__be64	wait_state_cycles;	/* Wait cycles for this proc */
 	u8	reserved9[28];
-	u16	slb_count;		/* # of SLBs to maintain */
+	__be16	slb_count;		/* # of SLBs to maintain */
 	u8	idle;			/* Indicate OS is idle */
 	u8	vmxregs_in_use;
 
@@ -89,17 +87,17 @@ struct lppaca {
 	 * NOTE: This value will ALWAYS be zero for dedicated processors and
 	 * will NEVER be zero for shared processors (ie, initialized to a 1).
 	 */
-	volatile u32 yield_count;
-	volatile u32 dispersion_count;	/* dispatch changed physical cpu */
-	volatile u64 cmo_faults;	/* CMO page fault count */
-	volatile u64 cmo_fault_time;	/* CMO page fault time */
+	volatile __be32 yield_count;
+	volatile __be32 dispersion_count; /* dispatch changed physical cpu */
+	volatile __be64 cmo_faults;	/* CMO page fault count */
+	volatile __be64 cmo_fault_time;	/* CMO page fault time */
 	u8	reserved10[104];
 
 	/* cacheline 4-5 */
 
-	u32	page_ins;		/* CMO Hint - # page ins by OS */
+	__be32	page_ins;		/* CMO Hint - # page ins by OS */
 	u8	reserved11[148];
-	volatile u64 dtl_idx;		/* Dispatch Trace Log head index */
+	volatile __be64 dtl_idx;		/* Dispatch Trace Log head index */
 	u8	reserved12[96];
 } __attribute__((__aligned__(0x400)));
 
@@ -108,17 +106,29 @@ extern struct lppaca lppaca[];
 #define lppaca_of(cpu)	(*paca[cpu].lppaca_ptr)
 
 /*
+ * Old kernels used a reserved bit in the VPA to determine if it was running
+ * in shared processor mode. New kernels look for a non zero yield count
+ * but KVM still needs to set the bit to keep the old stuff happy.
+ */
+#define LPPACA_OLD_SHARED_PROC		2
+
+static inline bool lppaca_shared_proc(struct lppaca *l)
+{
+	return l->yield_count != 0;
+}
+
+/*
  * SLB shadow buffer structure as defined in the PAPR.  The save_area
  * contains adjacent ESID and VSID pairs for each shadowed SLB.  The
  * ESID is stored in the lower 64bits, then the VSID.
  */
 struct slb_shadow {
-	u32	persistent;		/* Number of persistent SLBs */
-	u32	buffer_length;		/* Total shadow buffer length */
-	u64	reserved;
+	__be32	persistent;		/* Number of persistent SLBs */
+	__be32	buffer_length;		/* Total shadow buffer length */
+	__be64	reserved;
 	struct	{
-		u64     esid;
-		u64	vsid;
+		__be64     esid;
+		__be64	vsid;
 	} save_area[SLB_NUM_BOLTED];
 } ____cacheline_aligned;
 
@@ -130,14 +140,14 @@ extern struct slb_shadow slb_shadow[];
 struct dtl_entry {
 	u8	dispatch_reason;
 	u8	preempt_reason;
-	u16	processor_id;
-	u32	enqueue_to_dispatch_time;
-	u32	ready_to_enqueue_time;
-	u32	waiting_to_ready_time;
-	u64	timebase;
-	u64	fault_addr;
-	u64	srr0;
-	u64	srr1;
+	__be16	processor_id;
+	__be32	enqueue_to_dispatch_time;
+	__be32	ready_to_enqueue_time;
+	__be32	waiting_to_ready_time;
+	__be64	timebase;
+	__be64	fault_addr;
+	__be64	srr0;
+	__be64	srr1;
 };
 
 #define DISPATCH_LOG_BYTES	4096	/* bytes per cpu */
diff --git a/arch/powerpc/include/asm/mpc5121.h b/arch/powerpc/include/asm/mpc5121.h
index 8ae133eaf9fa..887d3d6133e3 100644
--- a/arch/powerpc/include/asm/mpc5121.h
+++ b/arch/powerpc/include/asm/mpc5121.h
@@ -32,25 +32,11 @@ struct mpc512x_ccm {
 	u32	scfr2;	/* System Clock Frequency Register 2 */
 	u32	scfr2s;	/* System Clock Frequency Shadow Register 2 */
 	u32	bcr;	/* Bread Crumb Register */
-	u32	p0ccr;	/* PSC0 Clock Control Register */
-	u32	p1ccr;	/* PSC1 CCR */
-	u32	p2ccr;	/* PSC2 CCR */
-	u32	p3ccr;	/* PSC3 CCR */
-	u32	p4ccr;	/* PSC4 CCR */
-	u32	p5ccr;	/* PSC5 CCR */
-	u32	p6ccr;	/* PSC6 CCR */
-	u32	p7ccr;	/* PSC7 CCR */
-	u32	p8ccr;	/* PSC8 CCR */
-	u32	p9ccr;	/* PSC9 CCR */
-	u32	p10ccr;	/* PSC10 CCR */
-	u32	p11ccr;	/* PSC11 CCR */
+	u32	psc_ccr[12];	/* PSC Clock Control Registers */
 	u32	spccr;	/* SPDIF Clock Control Register */
 	u32	cccr;	/* CFM Clock Control Register */
 	u32	dccr;	/* DIU Clock Control Register */
-	u32	m1ccr;	/* MSCAN1 CCR */
-	u32	m2ccr;	/* MSCAN2 CCR */
-	u32	m3ccr;	/* MSCAN3 CCR */
-	u32	m4ccr;	/* MSCAN4 CCR */
+	u32	mscan_ccr[4];	/* MSCAN Clock Control Registers */
 	u8	res[0x98]; /* Reserved */
 };
 
diff --git a/arch/powerpc/include/asm/mpc85xx.h b/arch/powerpc/include/asm/mpc85xx.h
new file mode 100644
index 000000000000..736d4acc05a8
--- /dev/null
+++ b/arch/powerpc/include/asm/mpc85xx.h
@@ -0,0 +1,92 @@
+/*
+ * MPC85xx cpu type detection
+ *
+ * Copyright 2011-2012 Freescale Semiconductor, Inc.
+ *
+ * This is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#ifndef __ASM_PPC_MPC85XX_H
+#define __ASM_PPC_MPC85XX_H
+
+#define SVR_REV(svr)	((svr) & 0xFF)		/* SOC design resision */
+#define SVR_MAJ(svr)	(((svr) >>  4) & 0xF)	/* Major revision field*/
+#define SVR_MIN(svr)	(((svr) >>  0) & 0xF)	/* Minor revision field*/
+
+/* Some parts define SVR[0:23] as the SOC version */
+#define SVR_SOC_VER(svr) (((svr) >> 8) & 0xFFF7FF)	/* SOC Version fields */
+
+#define SVR_8533	0x803400
+#define SVR_8535	0x803701
+#define SVR_8536	0x803700
+#define SVR_8540	0x803000
+#define SVR_8541	0x807200
+#define SVR_8543	0x803200
+#define SVR_8544	0x803401
+#define SVR_8545	0x803102
+#define SVR_8547	0x803101
+#define SVR_8548	0x803100
+#define SVR_8555	0x807100
+#define SVR_8560	0x807000
+#define SVR_8567	0x807501
+#define SVR_8568	0x807500
+#define SVR_8569	0x808000
+#define SVR_8572	0x80E000
+#define SVR_P1010	0x80F100
+#define SVR_P1011	0x80E500
+#define SVR_P1012	0x80E501
+#define SVR_P1013	0x80E700
+#define SVR_P1014	0x80F101
+#define SVR_P1017	0x80F700
+#define SVR_P1020	0x80E400
+#define SVR_P1021	0x80E401
+#define SVR_P1022	0x80E600
+#define SVR_P1023	0x80F600
+#define SVR_P1024	0x80E402
+#define SVR_P1025	0x80E403
+#define SVR_P2010	0x80E300
+#define SVR_P2020	0x80E200
+#define SVR_P2040	0x821000
+#define SVR_P2041	0x821001
+#define SVR_P3041	0x821103
+#define SVR_P4040	0x820100
+#define SVR_P4080	0x820000
+#define SVR_P5010	0x822100
+#define SVR_P5020	0x822000
+#define SVR_P5021	0X820500
+#define SVR_P5040	0x820400
+#define SVR_T4240	0x824000
+#define SVR_T4120	0x824001
+#define SVR_T4160	0x824100
+#define SVR_C291	0x850000
+#define SVR_C292	0x850020
+#define SVR_C293	0x850030
+#define SVR_B4860	0X868000
+#define SVR_G4860	0x868001
+#define SVR_G4060	0x868003
+#define SVR_B4440	0x868100
+#define SVR_G4440	0x868101
+#define SVR_B4420	0x868102
+#define SVR_B4220	0x868103
+#define SVR_T1040	0x852000
+#define SVR_T1041	0x852001
+#define SVR_T1042	0x852002
+#define SVR_T1020	0x852100
+#define SVR_T1021	0x852101
+#define SVR_T1022	0x852102
+
+#define SVR_8610	0x80A000
+#define SVR_8641	0x809000
+#define SVR_8641D	0x809001
+
+#define SVR_9130	0x860001
+#define SVR_9131	0x860000
+#define SVR_9132	0x861000
+#define SVR_9232	0x861400
+
+#define SVR_Unknown	0xFFFFFF
+
+#endif
diff --git a/arch/powerpc/include/asm/mpic.h b/arch/powerpc/include/asm/mpic.h
index 4a1ac9fbf186..754f93d208fa 100644
--- a/arch/powerpc/include/asm/mpic.h
+++ b/arch/powerpc/include/asm/mpic.h
@@ -396,7 +396,14 @@ extern struct bus_type mpic_subsys;
 #define	MPIC_REGSET_TSI108		MPIC_REGSET(1)	/* Tsi108/109 PIC */
 
 /* Get the version of primary MPIC */
+#ifdef CONFIG_MPIC
 extern u32 fsl_mpic_primary_get_version(void);
+#else
+static inline u32 fsl_mpic_primary_get_version(void)
+{
+	return 0;
+}
+#endif
 
 /* Allocate the controller structure and setup the linux irq descs
  * for the range if interrupts passed in. No HW initialization is
diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h
index 029fe85722aa..c5cd72833d6e 100644
--- a/arch/powerpc/include/asm/opal.h
+++ b/arch/powerpc/include/asm/opal.h
@@ -124,6 +124,11 @@ extern int opal_enter_rtas(struct rtas_args *args,
 #define OPAL_PCI_POLL				62
 #define OPAL_PCI_MSI_EOI			63
 #define OPAL_PCI_GET_PHB_DIAG_DATA2		64
+#define OPAL_XSCOM_READ				65
+#define OPAL_XSCOM_WRITE			66
+#define OPAL_LPC_READ				67
+#define OPAL_LPC_WRITE				68
+#define OPAL_RETURN_CPU				69
 
 #ifndef __ASSEMBLY__
 
@@ -337,6 +342,17 @@ enum OpalEpowStatus {
 	OPAL_EPOW_OVER_INTERNAL_TEMP = 3
 };
 
+/*
+ * Address cycle types for LPC accesses. These also correspond
+ * to the content of the first cell of the "reg" property for
+ * device nodes on the LPC bus
+ */
+enum OpalLPCAddressType {
+	OPAL_LPC_MEM	= 0,
+	OPAL_LPC_IO	= 1,
+	OPAL_LPC_FW	= 2,
+};
+
 struct opal_machine_check_event {
 	enum OpalMCE_Version	version:8;	/* 0x00 */
 	uint8_t			in_use;		/* 0x01 */
@@ -631,6 +647,15 @@ int64_t opal_set_system_attention_led(uint8_t led_action);
 int64_t opal_pci_next_error(uint64_t phb_id, uint64_t *first_frozen_pe,
 			    uint16_t *pci_error_type, uint16_t *severity);
 int64_t opal_pci_poll(uint64_t phb_id);
+int64_t opal_return_cpu(void);
+
+int64_t opal_xscom_read(uint32_t gcid, uint32_t pcb_addr, uint64_t *val);
+int64_t opal_xscom_write(uint32_t gcid, uint32_t pcb_addr, uint64_t val);
+
+int64_t opal_lpc_write(uint32_t chip_id, enum OpalLPCAddressType addr_type,
+		       uint32_t addr, uint32_t data, uint32_t sz);
+int64_t opal_lpc_read(uint32_t chip_id, enum OpalLPCAddressType addr_type,
+		      uint32_t addr, uint32_t *data, uint32_t sz);
 
 /* Internal functions */
 extern int early_init_dt_scan_opal(unsigned long node, const char *uname, int depth, void *data);
@@ -664,6 +689,8 @@ extern int opal_machine_check(struct pt_regs *regs);
 
 extern void opal_shutdown(void);
 
+extern void opal_lpc_init(void);
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* __OPAL_H */
diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h
index 77c91e74b612..a5954cebbc55 100644
--- a/arch/powerpc/include/asm/paca.h
+++ b/arch/powerpc/include/asm/paca.h
@@ -68,8 +68,13 @@ struct paca_struct {
 	 * instruction.  They must travel together and be properly
 	 * aligned.
 	 */
+#ifdef __BIG_ENDIAN__
 	u16 lock_token;			/* Constant 0x8000, used in locks */
 	u16 paca_index;			/* Logical processor number */
+#else
+	u16 paca_index;			/* Logical processor number */
+	u16 lock_token;			/* Constant 0x8000, used in locks */
+#endif
 
 	u64 kernel_toc;			/* Kernel TOC address */
 	u64 kernelbase;			/* Base address of kernel */
@@ -93,9 +98,9 @@ struct paca_struct {
 	 * Now, starting in cacheline 2, the exception save areas
 	 */
 	/* used for most interrupts/exceptions */
-	u64 exgen[12] __attribute__((aligned(0x80)));
-	u64 exmc[12];		/* used for machine checks */
-	u64 exslb[12];		/* used for SLB/segment table misses
+	u64 exgen[13] __attribute__((aligned(0x80)));
+	u64 exmc[13];		/* used for machine checks */
+	u64 exslb[13];		/* used for SLB/segment table misses
  				 * on the linear mapping */
 	/* SLB related definitions */
 	u16 vmalloc_sllp;
diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h
index 32d0d2018faf..4ca90a39d6d0 100644
--- a/arch/powerpc/include/asm/pci-bridge.h
+++ b/arch/powerpc/include/asm/pci-bridge.h
@@ -159,7 +159,7 @@ struct pci_dn {
 
 	int	pci_ext_config_space;	/* for pci devices */
 
-	int	force_32bit_msi:1;
+	bool	force_32bit_msi;
 
 	struct	pci_dev *pcidev;	/* back-pointer to the pci device */
 #ifdef CONFIG_EEH
diff --git a/arch/powerpc/include/asm/pci.h b/arch/powerpc/include/asm/pci.h
index 6653f2743c4e..95145a15c708 100644
--- a/arch/powerpc/include/asm/pci.h
+++ b/arch/powerpc/include/asm/pci.h
@@ -113,11 +113,6 @@ extern int pci_domain_nr(struct pci_bus *bus);
 /* Decide whether to display the domain number in /proc */
 extern int pci_proc_domain(struct pci_bus *bus);
 
-/* MSI arch hooks */
-#define arch_setup_msi_irqs arch_setup_msi_irqs
-#define arch_teardown_msi_irqs arch_teardown_msi_irqs
-#define arch_msi_check_device arch_msi_check_device
-
 struct vm_area_struct;
 /* Map a range of PCI memory or I/O space for a device into user space */
 int pci_mmap_page_range(struct pci_dev *pdev, struct vm_area_struct *vma,
diff --git a/arch/powerpc/include/asm/perf_event_fsl_emb.h b/arch/powerpc/include/asm/perf_event_fsl_emb.h
index 718a9fa94e68..a58165450f6f 100644
--- a/arch/powerpc/include/asm/perf_event_fsl_emb.h
+++ b/arch/powerpc/include/asm/perf_event_fsl_emb.h
@@ -13,7 +13,7 @@
 #include <linux/types.h>
 #include <asm/hw_irq.h>
 
-#define MAX_HWEVENTS 4
+#define MAX_HWEVENTS 6
 
 /* event flags */
 #define FSL_EMB_EVENT_VALID      1
diff --git a/arch/powerpc/include/asm/perf_event_server.h b/arch/powerpc/include/asm/perf_event_server.h
index 8b2492644754..3fd2f1b6f906 100644
--- a/arch/powerpc/include/asm/perf_event_server.h
+++ b/arch/powerpc/include/asm/perf_event_server.h
@@ -138,11 +138,11 @@ extern ssize_t power_events_sysfs_show(struct device *dev,
 #define	EVENT_PTR(_id, _suffix)		&EVENT_VAR(_id, _suffix).attr.attr
 
 #define	EVENT_ATTR(_name, _id, _suffix)					\
-	PMU_EVENT_ATTR(_name, EVENT_VAR(_id, _suffix), PME_PM_##_id,	\
+	PMU_EVENT_ATTR(_name, EVENT_VAR(_id, _suffix), PME_##_id,	\
 			power_events_sysfs_show)
 
 #define	GENERIC_EVENT_ATTR(_name, _id)	EVENT_ATTR(_name, _id, _g)
 #define	GENERIC_EVENT_PTR(_id)		EVENT_PTR(_id, _g)
 
-#define	POWER_EVENT_ATTR(_name, _id)	EVENT_ATTR(PM_##_name, _id, _p)
+#define	POWER_EVENT_ATTR(_name, _id)	EVENT_ATTR(_name, _id, _p)
 #define	POWER_EVENT_PTR(_id)		EVENT_PTR(_id, _p)
diff --git a/arch/powerpc/platforms/pseries/plpar_wrappers.h b/arch/powerpc/include/asm/plpar_wrappers.h
index f35787b6a5e0..a63b045e707c 100644
--- a/arch/powerpc/platforms/pseries/plpar_wrappers.h
+++ b/arch/powerpc/include/asm/plpar_wrappers.h
@@ -1,5 +1,5 @@
-#ifndef _PSERIES_PLPAR_WRAPPERS_H
-#define _PSERIES_PLPAR_WRAPPERS_H
+#ifndef _ASM_POWERPC_PLPAR_WRAPPERS_H
+#define _ASM_POWERPC_PLPAR_WRAPPERS_H
 
 #include <linux/string.h>
 #include <linux/irqflags.h>
@@ -256,30 +256,6 @@ static inline long plpar_tce_stuff(unsigned long liobn, unsigned long ioba,
 	return plpar_hcall_norets(H_STUFF_TCE, liobn, ioba, tceval, count);
 }
 
-static inline long plpar_get_term_char(unsigned long termno,
-		unsigned long *len_ret, char *buf_ret)
-{
-	long rc;
-	unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
-	unsigned long *lbuf = (unsigned long *)buf_ret;	/* TODO: alignment? */
-
-	rc = plpar_hcall(H_GET_TERM_CHAR, retbuf, termno);
-
-	*len_ret = retbuf[0];
-	lbuf[0] = retbuf[1];
-	lbuf[1] = retbuf[2];
-
-	return rc;
-}
-
-static inline long plpar_put_term_char(unsigned long termno, unsigned long len,
-		const char *buffer)
-{
-	unsigned long *lbuf = (unsigned long *)buffer;	/* TODO: alignment? */
-	return plpar_hcall_norets(H_PUT_TERM_CHAR, termno, len, lbuf[0],
-			lbuf[1]);
-}
-
 /* Set various resource mode parameters */
 static inline long plpar_set_mode(unsigned long mflags, unsigned long resource,
 		unsigned long value1, unsigned long value2)
@@ -321,4 +297,4 @@ static inline long plapr_set_watchpoint0(unsigned long dawr0, unsigned long dawr
 	return plpar_set_mode(0, 2, dawr0, dawrx0);
 }
 
-#endif /* _PSERIES_PLPAR_WRAPPERS_H */
+#endif /* _ASM_POWERPC_PLPAR_WRAPPERS_H */
diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h
index eccfc161e58e..d7fe9f5b46d4 100644
--- a/arch/powerpc/include/asm/ppc-opcode.h
+++ b/arch/powerpc/include/asm/ppc-opcode.h
@@ -81,6 +81,53 @@
 #define	__REGA0_R30	30
 #define	__REGA0_R31	31
 
+/* opcode and xopcode for instructions */
+#define OP_TRAP 3
+#define OP_TRAP_64 2
+
+#define OP_31_XOP_TRAP      4
+#define OP_31_XOP_LWZX      23
+#define OP_31_XOP_DCBST     54
+#define OP_31_XOP_LWZUX     55
+#define OP_31_XOP_TRAP_64   68
+#define OP_31_XOP_DCBF      86
+#define OP_31_XOP_LBZX      87
+#define OP_31_XOP_STWX      151
+#define OP_31_XOP_STBX      215
+#define OP_31_XOP_LBZUX     119
+#define OP_31_XOP_STBUX     247
+#define OP_31_XOP_LHZX      279
+#define OP_31_XOP_LHZUX     311
+#define OP_31_XOP_MFSPR     339
+#define OP_31_XOP_LHAX      343
+#define OP_31_XOP_LHAUX     375
+#define OP_31_XOP_STHX      407
+#define OP_31_XOP_STHUX     439
+#define OP_31_XOP_MTSPR     467
+#define OP_31_XOP_DCBI      470
+#define OP_31_XOP_LWBRX     534
+#define OP_31_XOP_TLBSYNC   566
+#define OP_31_XOP_STWBRX    662
+#define OP_31_XOP_LHBRX     790
+#define OP_31_XOP_STHBRX    918
+
+#define OP_LWZ  32
+#define OP_LD   58
+#define OP_LWZU 33
+#define OP_LBZ  34
+#define OP_LBZU 35
+#define OP_STW  36
+#define OP_STWU 37
+#define OP_STD  62
+#define OP_STB  38
+#define OP_STBU 39
+#define OP_LHZ  40
+#define OP_LHZU 41
+#define OP_LHA  42
+#define OP_LHAU 43
+#define OP_STH  44
+#define OP_STHU 45
+
 /* sorted alphabetically */
 #define PPC_INST_BHRBE			0x7c00025c
 #define PPC_INST_CLRBHRB		0x7c00035c
diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h
index 2f1b6c5f8174..599545738af3 100644
--- a/arch/powerpc/include/asm/ppc_asm.h
+++ b/arch/powerpc/include/asm/ppc_asm.h
@@ -54,7 +54,8 @@ BEGIN_FW_FTR_SECTION;							\
 	/* from user - see if there are any DTL entries to process */	\
 	ld	r10,PACALPPACAPTR(r13);	/* get ptr to VPA */		\
 	ld	r11,PACA_DTL_RIDX(r13);	/* get log read index */	\
-	ld	r10,LPPACA_DTLIDX(r10);	/* get log write index */	\
+	addi	r10,r10,LPPACA_DTLIDX;					\
+	LDX_BE	r10,0,r10;		/* get log write index */	\
 	cmpd	cr1,r11,r10;						\
 	beq+	cr1,33f;						\
 	bl	.accumulate_stolen_time;				\
@@ -219,19 +220,6 @@ END_FW_FTR_SECTION_IFSET(FW_FEATURE_SPLPAR)
 #define REST_8VSRS(n,b,base)	REST_4VSRS(n,b,base); REST_4VSRS(n+4,b,base)
 #define REST_16VSRS(n,b,base)	REST_8VSRS(n,b,base); REST_8VSRS(n+8,b,base)
 #define REST_32VSRS(n,b,base)	REST_16VSRS(n,b,base); REST_16VSRS(n+16,b,base)
-/* Save the upper 32 VSRs (32-63) in the thread VSX region (0-31) */
-#define SAVE_VSRU(n,b,base)	li b,THREAD_VR0+(16*(n));  STXVD2X(n+32,R##base,R##b)
-#define SAVE_2VSRSU(n,b,base)	SAVE_VSRU(n,b,base); SAVE_VSRU(n+1,b,base)
-#define SAVE_4VSRSU(n,b,base)	SAVE_2VSRSU(n,b,base); SAVE_2VSRSU(n+2,b,base)
-#define SAVE_8VSRSU(n,b,base)	SAVE_4VSRSU(n,b,base); SAVE_4VSRSU(n+4,b,base)
-#define SAVE_16VSRSU(n,b,base)	SAVE_8VSRSU(n,b,base); SAVE_8VSRSU(n+8,b,base)
-#define SAVE_32VSRSU(n,b,base)	SAVE_16VSRSU(n,b,base); SAVE_16VSRSU(n+16,b,base)
-#define REST_VSRU(n,b,base)	li b,THREAD_VR0+(16*(n)); LXVD2X(n+32,R##base,R##b)
-#define REST_2VSRSU(n,b,base)	REST_VSRU(n,b,base); REST_VSRU(n+1,b,base)
-#define REST_4VSRSU(n,b,base)	REST_2VSRSU(n,b,base); REST_2VSRSU(n+2,b,base)
-#define REST_8VSRSU(n,b,base)	REST_4VSRSU(n,b,base); REST_4VSRSU(n+4,b,base)
-#define REST_16VSRSU(n,b,base)	REST_8VSRSU(n,b,base); REST_8VSRSU(n+8,b,base)
-#define REST_32VSRSU(n,b,base)	REST_16VSRSU(n,b,base); REST_16VSRSU(n+16,b,base)
 
 /*
  * b = base register for addressing, o = base offset from register of 1st EVR
@@ -443,15 +431,15 @@ END_FTR_SECTION_IFSET(CPU_FTR_601)
 #define ISYNC_601
 #endif
 
-#ifdef CONFIG_PPC_CELL
+#if defined(CONFIG_PPC_CELL) || defined(CONFIG_PPC_FSL_BOOK3E)
 #define MFTB(dest)			\
-90:	mftb  dest;			\
+90:	mfspr dest, SPRN_TBRL;		\
 BEGIN_FTR_SECTION_NESTED(96);		\
 	cmpwi dest,0;			\
 	beq-  90b;			\
 END_FTR_SECTION_NESTED(CPU_FTR_CELL_TB_BUG, CPU_FTR_CELL_TB_BUG, 96)
 #else
-#define MFTB(dest)			mftb dest
+#define MFTB(dest)			mfspr dest, SPRN_TBRL
 #endif
 
 #ifndef CONFIG_SMP
diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index e378cccfca55..ce4de5aed7b5 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -149,8 +149,6 @@ typedef struct {
 
 struct thread_struct {
 	unsigned long	ksp;		/* Kernel stack pointer */
-	unsigned long	ksp_limit;	/* if ksp <= ksp_limit stack overflow */
-
 #ifdef CONFIG_PPC64
 	unsigned long	ksp_vsid;
 #endif
@@ -162,6 +160,7 @@ struct thread_struct {
 #endif
 #ifdef CONFIG_PPC32
 	void		*pgdir;		/* root of page-table tree */
+	unsigned long	ksp_limit;	/* if ksp <= ksp_limit stack overflow */
 #endif
 #ifdef CONFIG_PPC_ADV_DEBUG_REGS
 	/*
@@ -321,7 +320,6 @@ struct thread_struct {
 #else
 #define INIT_THREAD  { \
 	.ksp = INIT_SP, \
-	.ksp_limit = INIT_SP_LIMIT, \
 	.regs = (struct pt_regs *)INIT_SP - 1, /* XXX bogus, I think */ \
 	.fs = KERNEL_DS, \
 	.fpr = {{0}}, \
diff --git a/arch/powerpc/include/asm/prom.h b/arch/powerpc/include/asm/prom.h
index bc2da154f68b..7d0c7f3a7171 100644
--- a/arch/powerpc/include/asm/prom.h
+++ b/arch/powerpc/include/asm/prom.h
@@ -38,14 +38,12 @@ extern unsigned long pci_address_to_pio(phys_addr_t address);
 /* Parse the ibm,dma-window property of an OF node into the busno, phys and
  * size parameters.
  */
-void of_parse_dma_window(struct device_node *dn, const void *dma_window_prop,
-		unsigned long *busno, unsigned long *phys, unsigned long *size);
+void of_parse_dma_window(struct device_node *dn, const __be32 *dma_window,
+			 unsigned long *busno, unsigned long *phys,
+			 unsigned long *size);
 
 extern void kdump_move_device_tree(void);
 
-/* CPU OF node matching */
-struct device_node *of_get_cpu_node(int cpu, unsigned int *thread);
-
 /* cache lookup */
 struct device_node *of_find_next_cache_node(struct device_node *np);
 
@@ -58,6 +56,8 @@ static inline int of_node_to_nid(struct device_node *device) { return 0; }
 
 extern void of_instantiate_rtc(void);
 
+extern int of_get_ibm_chip_id(struct device_node *np);
+
 /* The of_drconf_cell struct defines the layout of the LMB array
  * specified in the device tree property
  * ibm,dynamic-reconfiguration-memory/ibm,dynamic-memory
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index 99222e27f173..10d1ef016bf1 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -115,10 +115,10 @@
 #define MSR_64BIT	MSR_SF
 
 /* Server variant */
-#define MSR_		MSR_ME | MSR_RI | MSR_IR | MSR_DR | MSR_ISF |MSR_HV
-#define MSR_KERNEL	MSR_ | MSR_64BIT
-#define MSR_USER32	MSR_ | MSR_PR | MSR_EE
-#define MSR_USER64	MSR_USER32 | MSR_64BIT
+#define MSR_		(MSR_ME | MSR_RI | MSR_IR | MSR_DR | MSR_ISF |MSR_HV)
+#define MSR_KERNEL	(MSR_ | MSR_64BIT)
+#define MSR_USER32	(MSR_ | MSR_PR | MSR_EE)
+#define MSR_USER64	(MSR_USER32 | MSR_64BIT)
 #elif defined(CONFIG_PPC_BOOK3S_32) || defined(CONFIG_8xx)
 /* Default MSR for kernel mode. */
 #define MSR_KERNEL	(MSR_ME|MSR_RI|MSR_IR|MSR_DR)
@@ -258,8 +258,8 @@
 #define FSCR_TAR_LG	8	/* Enable Target Address Register */
 #define FSCR_EBB_LG	7	/* Enable Event Based Branching */
 #define FSCR_TM_LG	5	/* Enable Transactional Memory */
-#define FSCR_PM_LG	4	/* Enable prob/priv access to PMU SPRs */
-#define FSCR_BHRB_LG	3	/* Enable Branch History Rolling Buffer*/
+#define FSCR_BHRB_LG	4	/* Enable Branch History Rolling Buffer*/
+#define FSCR_PM_LG	3	/* Enable prob/priv access to PMU SPRs */
 #define FSCR_DSCR_LG	2	/* Enable Data Stream Control Register */
 #define FSCR_VECVSX_LG	1	/* Enable VMX/VSX  */
 #define FSCR_FP_LG	0	/* Enable Floating Point */
@@ -1126,10 +1126,10 @@
 				     : "memory")
 
 #ifdef __powerpc64__
-#ifdef CONFIG_PPC_CELL
+#if defined(CONFIG_PPC_CELL) || defined(CONFIG_PPC_FSL_BOOK3E)
 #define mftb()		({unsigned long rval;				\
 			asm volatile(					\
-				"90:	mftb %0;\n"			\
+				"90:	mfspr %0, %2;\n"		\
 				"97:	cmpwi %0,0;\n"			\
 				"	beq- 90b;\n"			\
 				"99:\n"					\
@@ -1143,18 +1143,23 @@
 				"	.llong 0\n"			\
 				"	.llong 0\n"			\
 				".previous"				\
-			: "=r" (rval) : "i" (CPU_FTR_CELL_TB_BUG)); rval;})
+			: "=r" (rval) \
+			: "i" (CPU_FTR_CELL_TB_BUG), "i" (SPRN_TBRL)); \
+			rval;})
 #else
 #define mftb()		({unsigned long rval;	\
-			asm volatile("mftb %0" : "=r" (rval)); rval;})
+			asm volatile("mfspr %0, %1" : \
+				     "=r" (rval) : "i" (SPRN_TBRL)); rval;})
 #endif /* !CONFIG_PPC_CELL */
 
 #else /* __powerpc64__ */
 
 #define mftbl()		({unsigned long rval;	\
-			asm volatile("mftbl %0" : "=r" (rval)); rval;})
+			asm volatile("mfspr %0, %1" : "=r" (rval) : \
+				"i" (SPRN_TBRL)); rval;})
 #define mftbu()		({unsigned long rval;	\
-			asm volatile("mftbu %0" : "=r" (rval)); rval;})
+			asm volatile("mfspr %0, %1" : "=r" (rval) : \
+				"i" (SPRN_TBRU)); rval;})
 #endif /* !__powerpc64__ */
 
 #define mttbl(v)	asm volatile("mttbl %0":: "r"(v))
diff --git a/arch/powerpc/include/asm/reg_booke.h b/arch/powerpc/include/asm/reg_booke.h
index b417de3cc2c4..ed8f836da094 100644
--- a/arch/powerpc/include/asm/reg_booke.h
+++ b/arch/powerpc/include/asm/reg_booke.h
@@ -29,10 +29,10 @@
 #if defined(CONFIG_PPC_BOOK3E_64)
 #define MSR_64BIT	MSR_CM
 
-#define MSR_		MSR_ME | MSR_CE
-#define MSR_KERNEL	MSR_ | MSR_64BIT
-#define MSR_USER32	MSR_ | MSR_PR | MSR_EE
-#define MSR_USER64	MSR_USER32 | MSR_64BIT
+#define MSR_		(MSR_ME | MSR_CE)
+#define MSR_KERNEL	(MSR_ | MSR_64BIT)
+#define MSR_USER32	(MSR_ | MSR_PR | MSR_EE)
+#define MSR_USER64	(MSR_USER32 | MSR_64BIT)
 #elif defined (CONFIG_40x)
 #define MSR_KERNEL	(MSR_ME|MSR_RI|MSR_IR|MSR_DR|MSR_CE)
 #define MSR_USER	(MSR_KERNEL|MSR_PR|MSR_EE)
diff --git a/arch/powerpc/include/asm/reg_fsl_emb.h b/arch/powerpc/include/asm/reg_fsl_emb.h
index 77bb71cfd991..0e3ddf5177f6 100644
--- a/arch/powerpc/include/asm/reg_fsl_emb.h
+++ b/arch/powerpc/include/asm/reg_fsl_emb.h
@@ -17,12 +17,16 @@
 /* Freescale Book E Performance Monitor APU Registers */
 #define PMRN_PMC0	0x010	/* Performance Monitor Counter 0 */
 #define PMRN_PMC1	0x011	/* Performance Monitor Counter 1 */
-#define PMRN_PMC2	0x012	/* Performance Monitor Counter 1 */
-#define PMRN_PMC3	0x013	/* Performance Monitor Counter 1 */
+#define PMRN_PMC2	0x012	/* Performance Monitor Counter 2 */
+#define PMRN_PMC3	0x013	/* Performance Monitor Counter 3 */
+#define PMRN_PMC4	0x014	/* Performance Monitor Counter 4 */
+#define PMRN_PMC5	0x015	/* Performance Monitor Counter 5 */
 #define PMRN_PMLCA0	0x090	/* PM Local Control A0 */
 #define PMRN_PMLCA1	0x091	/* PM Local Control A1 */
 #define PMRN_PMLCA2	0x092	/* PM Local Control A2 */
 #define PMRN_PMLCA3	0x093	/* PM Local Control A3 */
+#define PMRN_PMLCA4	0x094	/* PM Local Control A4 */
+#define PMRN_PMLCA5	0x095	/* PM Local Control A5 */
 
 #define PMLCA_FC	0x80000000	/* Freeze Counter */
 #define PMLCA_FCS	0x40000000	/* Freeze in Supervisor */
@@ -30,14 +34,18 @@
 #define PMLCA_FCM1	0x10000000	/* Freeze when PMM==1 */
 #define PMLCA_FCM0	0x08000000	/* Freeze when PMM==0 */
 #define PMLCA_CE	0x04000000	/* Condition Enable */
+#define PMLCA_FGCS1	0x00000002	/* Freeze in guest state */
+#define PMLCA_FGCS0	0x00000001	/* Freeze in hypervisor state */
 
-#define PMLCA_EVENT_MASK 0x00ff0000	/* Event field */
+#define PMLCA_EVENT_MASK 0x01ff0000	/* Event field */
 #define PMLCA_EVENT_SHIFT	16
 
 #define PMRN_PMLCB0	0x110	/* PM Local Control B0 */
 #define PMRN_PMLCB1	0x111	/* PM Local Control B1 */
 #define PMRN_PMLCB2	0x112	/* PM Local Control B2 */
 #define PMRN_PMLCB3	0x113	/* PM Local Control B3 */
+#define PMRN_PMLCB4	0x114	/* PM Local Control B4 */
+#define PMRN_PMLCB5	0x115	/* PM Local Control B5 */
 
 #define PMLCB_THRESHMUL_MASK	0x0700	/* Threshold Multiple Field */
 #define PMLCB_THRESHMUL_SHIFT	8
@@ -55,16 +63,22 @@
 
 #define PMRN_UPMC0	0x000	/* User Performance Monitor Counter 0 */
 #define PMRN_UPMC1	0x001	/* User Performance Monitor Counter 1 */
-#define PMRN_UPMC2	0x002	/* User Performance Monitor Counter 1 */
-#define PMRN_UPMC3	0x003	/* User Performance Monitor Counter 1 */
+#define PMRN_UPMC2	0x002	/* User Performance Monitor Counter 2 */
+#define PMRN_UPMC3	0x003	/* User Performance Monitor Counter 3 */
+#define PMRN_UPMC4	0x004	/* User Performance Monitor Counter 4 */
+#define PMRN_UPMC5	0x005	/* User Performance Monitor Counter 5 */
 #define PMRN_UPMLCA0	0x080	/* User PM Local Control A0 */
 #define PMRN_UPMLCA1	0x081	/* User PM Local Control A1 */
 #define PMRN_UPMLCA2	0x082	/* User PM Local Control A2 */
 #define PMRN_UPMLCA3	0x083	/* User PM Local Control A3 */
+#define PMRN_UPMLCA4	0x084	/* User PM Local Control A4 */
+#define PMRN_UPMLCA5	0x085	/* User PM Local Control A5 */
 #define PMRN_UPMLCB0	0x100	/* User PM Local Control B0 */
 #define PMRN_UPMLCB1	0x101	/* User PM Local Control B1 */
 #define PMRN_UPMLCB2	0x102	/* User PM Local Control B2 */
 #define PMRN_UPMLCB3	0x103	/* User PM Local Control B3 */
+#define PMRN_UPMLCB4	0x104	/* User PM Local Control B4 */
+#define PMRN_UPMLCB5	0x105	/* User PM Local Control B5 */
 #define PMRN_UPMGC0	0x180	/* User PM Global Control 0 */
 
 
diff --git a/arch/powerpc/include/asm/rtas.h b/arch/powerpc/include/asm/rtas.h
index c7a8bfc9f6f5..9bd52c65e66f 100644
--- a/arch/powerpc/include/asm/rtas.h
+++ b/arch/powerpc/include/asm/rtas.h
@@ -44,12 +44,12 @@
  *
  */
 
-typedef u32 rtas_arg_t;
+typedef __be32 rtas_arg_t;
 
 struct rtas_args {
-	u32 token;
-	u32 nargs;
-	u32 nret; 
+	__be32 token;
+	__be32 nargs;
+	__be32 nret; 
 	rtas_arg_t args[16];
 	rtas_arg_t *rets;     /* Pointer to return values in args[]. */
 };  
diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h
index 48cfc858abd6..98da78e0c2c0 100644
--- a/arch/powerpc/include/asm/smp.h
+++ b/arch/powerpc/include/asm/smp.h
@@ -112,6 +112,7 @@ static inline struct cpumask *cpu_core_mask(int cpu)
 }
 
 extern int cpu_to_core_id(int cpu);
+extern int cpu_to_chip_id(int cpu);
 
 /* Since OpenPIC has only 4 IPIs, we use slightly different message numbers.
  *
@@ -186,6 +187,8 @@ extern int smt_enabled_at_boot;
 extern int smp_mpic_probe(void);
 extern void smp_mpic_setup_cpu(int cpu);
 extern int smp_generic_kick_cpu(int nr);
+extern int smp_generic_cpu_bootable(unsigned int nr);
+
 
 extern void smp_generic_give_timebase(void);
 extern void smp_generic_take_timebase(void);
diff --git a/arch/powerpc/include/asm/spinlock.h b/arch/powerpc/include/asm/spinlock.h
index 5b23f910ee57..5f54a744dcc5 100644
--- a/arch/powerpc/include/asm/spinlock.h
+++ b/arch/powerpc/include/asm/spinlock.h
@@ -32,8 +32,12 @@
 
 #ifdef CONFIG_PPC64
 /* use 0x800000yy when locked, where yy == CPU number */
+#ifdef __BIG_ENDIAN__
 #define LOCK_TOKEN	(*(u32 *)(&get_paca()->lock_token))
 #else
+#define LOCK_TOKEN	(*(u32 *)(&get_paca()->paca_index))
+#endif
+#else
 #define LOCK_TOKEN	1
 #endif
 
@@ -96,7 +100,7 @@ static inline int arch_spin_trylock(arch_spinlock_t *lock)
 
 #if defined(CONFIG_PPC_SPLPAR)
 /* We only yield to the hypervisor if we are in shared processor mode */
-#define SHARED_PROCESSOR (local_paca->lppaca_ptr->shared_proc)
+#define SHARED_PROCESSOR (lppaca_shared_proc(local_paca->lppaca_ptr))
 extern void __spin_yield(arch_spinlock_t *lock);
 extern void __rw_yield(arch_rwlock_t *lock);
 #else /* SPLPAR */
diff --git a/arch/powerpc/include/asm/switch_to.h b/arch/powerpc/include/asm/switch_to.h
index 294c2cedcf7a..2be5618cdec6 100644
--- a/arch/powerpc/include/asm/switch_to.h
+++ b/arch/powerpc/include/asm/switch_to.h
@@ -25,11 +25,8 @@ static inline void save_tar(struct thread_struct *prev)
 static inline void save_tar(struct thread_struct *prev) {}
 #endif
 
-extern void giveup_fpu(struct task_struct *);
 extern void load_up_fpu(void);
-extern void disable_kernel_fp(void);
 extern void enable_kernel_fp(void);
-extern void flush_fp_to_thread(struct task_struct *);
 extern void enable_kernel_altivec(void);
 extern void load_up_altivec(struct task_struct *);
 extern int emulate_altivec(struct pt_regs *);
@@ -47,6 +44,14 @@ static inline void discard_lazy_cpu_state(void)
 }
 #endif
 
+#ifdef CONFIG_PPC_FPU
+extern void flush_fp_to_thread(struct task_struct *);
+extern void giveup_fpu(struct task_struct *);
+#else
+static inline void flush_fp_to_thread(struct task_struct *t) { }
+static inline void giveup_fpu(struct task_struct *t) { }
+#endif
+
 #ifdef CONFIG_ALTIVEC
 extern void flush_altivec_to_thread(struct task_struct *);
 extern void giveup_altivec(struct task_struct *);
diff --git a/arch/powerpc/include/asm/timex.h b/arch/powerpc/include/asm/timex.h
index c55e14f7ef44..18908caa1f3b 100644
--- a/arch/powerpc/include/asm/timex.h
+++ b/arch/powerpc/include/asm/timex.h
@@ -29,7 +29,7 @@ static inline cycles_t get_cycles(void)
 	ret = 0;
 
 	__asm__ __volatile__(
-		"97:	mftb %0\n"
+		"97:	mfspr %0, %2\n"
 		"99:\n"
 		".section __ftr_fixup,\"a\"\n"
 		".align 2\n"
@@ -41,7 +41,7 @@ static inline cycles_t get_cycles(void)
 		"	.long 0\n"
 		"	.long 0\n"
 		".previous"
-		: "=r" (ret) : "i" (CPU_FTR_601));
+		: "=r" (ret) : "i" (CPU_FTR_601), "i" (SPRN_TBRL));
 	return ret;
 #endif
 }
diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h
index 161ab662843b..89e3ef2496ac 100644
--- a/arch/powerpc/include/asm/topology.h
+++ b/arch/powerpc/include/asm/topology.h
@@ -96,6 +96,7 @@ static inline int prrn_is_enabled(void)
 #ifdef CONFIG_PPC64
 #include <asm/smp.h>
 
+#define topology_physical_package_id(cpu)	(cpu_to_chip_id(cpu))
 #define topology_thread_cpumask(cpu)	(per_cpu(cpu_sibling_map, cpu))
 #define topology_core_cpumask(cpu)	(per_cpu(cpu_core_map, cpu))
 #define topology_core_id(cpu)		(cpu_to_core_id(cpu))
diff --git a/arch/powerpc/include/asm/udbg.h b/arch/powerpc/include/asm/udbg.h
index dc590919f8eb..b51fba10e733 100644
--- a/arch/powerpc/include/asm/udbg.h
+++ b/arch/powerpc/include/asm/udbg.h
@@ -27,10 +27,11 @@ extern void udbg_printf(const char *fmt, ...)
 	__attribute__ ((format (printf, 1, 2)));
 extern void udbg_progress(char *s, unsigned short hex);
 
-extern void udbg_init_uart(void __iomem *comport, unsigned int speed,
-			   unsigned int clock);
-extern unsigned int udbg_probe_uart_speed(void __iomem *comport,
-					  unsigned int clock);
+extern void udbg_uart_init_mmio(void __iomem *addr, unsigned int stride);
+extern void udbg_uart_init_pio(unsigned long port, unsigned int stride);
+
+extern void udbg_uart_setup(unsigned int speed, unsigned int clock);
+extern unsigned int udbg_probe_uart_speed(unsigned int clock);
 
 struct device_node;
 extern void udbg_scc_init(int force_scc);
diff --git a/arch/powerpc/include/uapi/asm/elf.h b/arch/powerpc/include/uapi/asm/elf.h
index 05b8d560cfba..7e39c9146a71 100644
--- a/arch/powerpc/include/uapi/asm/elf.h
+++ b/arch/powerpc/include/uapi/asm/elf.h
@@ -107,26 +107,25 @@ typedef elf_gregset_t32 compat_elf_gregset_t;
 # define ELF_NVRREG	34	/* includes vscr & vrsave in split vectors */
 # define ELF_NVSRHALFREG 32	/* Half the vsx registers */
 # define ELF_GREG_TYPE	elf_greg_t64
+# define ELF_ARCH	EM_PPC64
+# define ELF_CLASS	ELFCLASS64
+typedef elf_greg_t64 elf_greg_t;
+typedef elf_gregset_t64 elf_gregset_t;
 #else
 # define ELF_NEVRREG	34	/* includes acc (as 2) */
 # define ELF_NVRREG	33	/* includes vscr */
 # define ELF_GREG_TYPE	elf_greg_t32
 # define ELF_ARCH	EM_PPC
 # define ELF_CLASS	ELFCLASS32
-# define ELF_DATA	ELFDATA2MSB
+typedef elf_greg_t32 elf_greg_t;
+typedef elf_gregset_t32 elf_gregset_t;
 #endif /* __powerpc64__ */
 
-#ifndef ELF_ARCH
-# define ELF_ARCH	EM_PPC64
-# define ELF_CLASS	ELFCLASS64
-# define ELF_DATA	ELFDATA2MSB
-  typedef elf_greg_t64 elf_greg_t;
-  typedef elf_gregset_t64 elf_gregset_t;
+#ifdef __BIG_ENDIAN__
+#define ELF_DATA	ELFDATA2MSB
 #else
-  /* Assumption: ELF_ARCH == EM_PPC and ELF_CLASS == ELFCLASS32 */
-  typedef elf_greg_t32 elf_greg_t;
-  typedef elf_gregset_t32 elf_gregset_t;
-#endif /* ELF_ARCH */
+#define ELF_DATA	ELFDATA2LSB
+#endif
 
 /* Floating point registers */
 typedef double elf_fpreg_t;
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index a8619bfe879e..445cb6e39d5b 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -55,7 +55,6 @@ obj-$(CONFIG_PPC_RTAS)		+= rtas.o rtas-rtc.o $(rtaspci-y-y)
 obj-$(CONFIG_PPC_RTAS_DAEMON)	+= rtasd.o
 obj-$(CONFIG_RTAS_FLASH)	+= rtas_flash.o
 obj-$(CONFIG_RTAS_PROC)		+= rtas-proc.o
-obj-$(CONFIG_LPARCFG)		+= lparcfg.o
 obj-$(CONFIG_IBMVIO)		+= vio.o
 obj-$(CONFIG_IBMEBUS)           += ibmebus.o
 obj-$(CONFIG_EEH)              += eeh.o eeh_pe.o eeh_dev.o eeh_cache.o \
@@ -117,9 +116,7 @@ obj-$(CONFIG_DYNAMIC_FTRACE)	+= ftrace.o
 obj-$(CONFIG_FUNCTION_GRAPH_TRACER)	+= ftrace.o
 obj-$(CONFIG_FTRACE_SYSCALLS)	+= ftrace.o
 
-obj-$(CONFIG_8XX_MINIMAL_FPEMU) += softemu8xx.o
-
-ifneq ($(CONFIG_PPC_INDIRECT_IO),y)
+ifneq ($(CONFIG_PPC_INDIRECT_PIO),y)
 obj-y				+= iomap.o
 endif
 
diff --git a/arch/powerpc/kernel/align.c b/arch/powerpc/kernel/align.c
index ee5b690a0bed..a27ccd5dc6b9 100644
--- a/arch/powerpc/kernel/align.c
+++ b/arch/powerpc/kernel/align.c
@@ -651,6 +651,10 @@ static int emulate_vsx(unsigned char __user *addr, unsigned int reg,
 	int sw = 0;
 	int i, j;
 
+	/* userland only */
+	if (unlikely(!user_mode(regs)))
+		return 0;
+
 	flush_vsx_to_thread(current);
 
 	if (reg < 32)
@@ -764,6 +768,16 @@ int fix_alignment(struct pt_regs *regs)
 	nb = aligninfo[instr].len;
 	flags = aligninfo[instr].flags;
 
+	/* ldbrx/stdbrx overlap lfs/stfs in the DSISR unfortunately */
+	if (IS_XFORM(instruction) && ((instruction >> 1) & 0x3ff) == 532) {
+		nb = 8;
+		flags = LD+SW;
+	} else if (IS_XFORM(instruction) &&
+		   ((instruction >> 1) & 0x3ff) == 660) {
+		nb = 8;
+		flags = ST+SW;
+	}
+
 	/* Byteswap little endian loads and stores */
 	swiz = 0;
 	if (regs->msr & MSR_LE) {
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 8207459efe56..502c7a4e73f7 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -80,10 +80,11 @@ int main(void)
 	DEFINE(TASKTHREADPPR, offsetof(struct task_struct, thread.ppr));
 #else
 	DEFINE(THREAD_INFO, offsetof(struct task_struct, stack));
+	DEFINE(THREAD_INFO_GAP, _ALIGN_UP(sizeof(struct thread_info), 16));
+	DEFINE(KSP_LIMIT, offsetof(struct thread_struct, ksp_limit));
 #endif /* CONFIG_PPC64 */
 
 	DEFINE(KSP, offsetof(struct thread_struct, ksp));
-	DEFINE(KSP_LIMIT, offsetof(struct thread_struct, ksp_limit));
 	DEFINE(PT_REGS, offsetof(struct thread_struct, regs));
 #ifdef CONFIG_BOOKE
 	DEFINE(THREAD_NORMSAVES, offsetof(struct thread_struct, normsave[0]));
@@ -454,6 +455,7 @@ int main(void)
 	DEFINE(VCPU_SPRG2, offsetof(struct kvm_vcpu, arch.shregs.sprg2));
 	DEFINE(VCPU_SPRG3, offsetof(struct kvm_vcpu, arch.shregs.sprg3));
 #endif
+	DEFINE(VCPU_SHARED_SPRG3, offsetof(struct kvm_vcpu_arch_shared, sprg3));
 	DEFINE(VCPU_SHARED_SPRG4, offsetof(struct kvm_vcpu_arch_shared, sprg4));
 	DEFINE(VCPU_SHARED_SPRG5, offsetof(struct kvm_vcpu_arch_shared, sprg5));
 	DEFINE(VCPU_SHARED_SPRG6, offsetof(struct kvm_vcpu_arch_shared, sprg6));
diff --git a/arch/powerpc/kernel/btext.c b/arch/powerpc/kernel/btext.c
index ac8f52732fde..41c011cb6070 100644
--- a/arch/powerpc/kernel/btext.c
+++ b/arch/powerpc/kernel/btext.c
@@ -25,11 +25,6 @@
 static void scrollscreen(void);
 #endif
 
-static void draw_byte(unsigned char c, long locX, long locY);
-static void draw_byte_32(unsigned char *bits, unsigned int *base, int rb);
-static void draw_byte_16(unsigned char *bits, unsigned int *base, int rb);
-static void draw_byte_8(unsigned char *bits, unsigned int *base, int rb);
-
 #define __force_data __attribute__((__section__(".data")))
 
 static int g_loc_X __force_data;
@@ -52,6 +47,26 @@ static unsigned char vga_font[cmapsz];
 int boot_text_mapped __force_data = 0;
 int force_printk_to_btext = 0;
 
+extern void rmci_on(void);
+extern void rmci_off(void);
+
+static inline void rmci_maybe_on(void)
+{
+#if defined(CONFIG_PPC_EARLY_DEBUG_BOOTX) && defined(CONFIG_PPC64)
+	if (!(mfmsr() & MSR_DR))
+		rmci_on();
+#endif
+}
+
+static inline void rmci_maybe_off(void)
+{
+#if defined(CONFIG_PPC_EARLY_DEBUG_BOOTX) && defined(CONFIG_PPC64)
+	if (!(mfmsr() & MSR_DR))
+		rmci_off();
+#endif
+}
+
+
 #ifdef CONFIG_PPC32
 /* Calc BAT values for mapping the display and store them
  * in disp_BAT.  Those values are then used from head.S to map
@@ -134,7 +149,7 @@ void __init btext_unmap(void)
  *    changes.
  */
 
-static void map_boot_text(void)
+void btext_map(void)
 {
 	unsigned long base, offset, size;
 	unsigned char *vbase;
@@ -209,7 +224,7 @@ int btext_initialize(struct device_node *np)
 	dispDeviceRect[2] = width;
 	dispDeviceRect[3] = height;
 
-	map_boot_text();
+	btext_map();
 
 	return 0;
 }
@@ -283,7 +298,7 @@ void btext_update_display(unsigned long phys, int width, int height,
 		iounmap(logicalDisplayBase);
 		boot_text_mapped = 0;
 	}
-	map_boot_text();
+	btext_map();
 	g_loc_X = 0;
 	g_loc_Y = 0;
 	g_max_loc_X = width / 8;
@@ -298,6 +313,7 @@ void btext_clearscreen(void)
 					(dispDeviceDepth >> 3)) >> 2;
 	int i,j;
 
+	rmci_maybe_on();
 	for (i=0; i<(dispDeviceRect[3] - dispDeviceRect[1]); i++)
 	{
 		unsigned int *ptr = base;
@@ -305,6 +321,7 @@ void btext_clearscreen(void)
 			*(ptr++) = 0;
 		base += (dispDeviceRowBytes >> 2);
 	}
+	rmci_maybe_off();
 }
 
 void btext_flushscreen(void)
@@ -355,6 +372,8 @@ static void scrollscreen(void)
 				   (dispDeviceDepth >> 3)) >> 2;
 	int i,j;
 
+	rmci_maybe_on();
+
 	for (i=0; i<(dispDeviceRect[3] - dispDeviceRect[1] - 16); i++)
 	{
 		unsigned int *src_ptr = src;
@@ -371,9 +390,116 @@ static void scrollscreen(void)
 			*(dst_ptr++) = 0;
 		dst += (dispDeviceRowBytes >> 2);
 	}
+
+	rmci_maybe_off();
 }
 #endif /* ndef NO_SCROLL */
 
+static unsigned int expand_bits_8[16] = {
+	0x00000000,
+	0x000000ff,
+	0x0000ff00,
+	0x0000ffff,
+	0x00ff0000,
+	0x00ff00ff,
+	0x00ffff00,
+	0x00ffffff,
+	0xff000000,
+	0xff0000ff,
+	0xff00ff00,
+	0xff00ffff,
+	0xffff0000,
+	0xffff00ff,
+	0xffffff00,
+	0xffffffff
+};
+
+static unsigned int expand_bits_16[4] = {
+	0x00000000,
+	0x0000ffff,
+	0xffff0000,
+	0xffffffff
+};
+
+
+static void draw_byte_32(unsigned char *font, unsigned int *base, int rb)
+{
+	int l, bits;
+	int fg = 0xFFFFFFFFUL;
+	int bg = 0x00000000UL;
+
+	for (l = 0; l < 16; ++l)
+	{
+		bits = *font++;
+		base[0] = (-(bits >> 7) & fg) ^ bg;
+		base[1] = (-((bits >> 6) & 1) & fg) ^ bg;
+		base[2] = (-((bits >> 5) & 1) & fg) ^ bg;
+		base[3] = (-((bits >> 4) & 1) & fg) ^ bg;
+		base[4] = (-((bits >> 3) & 1) & fg) ^ bg;
+		base[5] = (-((bits >> 2) & 1) & fg) ^ bg;
+		base[6] = (-((bits >> 1) & 1) & fg) ^ bg;
+		base[7] = (-(bits & 1) & fg) ^ bg;
+		base = (unsigned int *) ((char *)base + rb);
+	}
+}
+
+static inline void draw_byte_16(unsigned char *font, unsigned int *base, int rb)
+{
+	int l, bits;
+	int fg = 0xFFFFFFFFUL;
+	int bg = 0x00000000UL;
+	unsigned int *eb = (int *)expand_bits_16;
+
+	for (l = 0; l < 16; ++l)
+	{
+		bits = *font++;
+		base[0] = (eb[bits >> 6] & fg) ^ bg;
+		base[1] = (eb[(bits >> 4) & 3] & fg) ^ bg;
+		base[2] = (eb[(bits >> 2) & 3] & fg) ^ bg;
+		base[3] = (eb[bits & 3] & fg) ^ bg;
+		base = (unsigned int *) ((char *)base + rb);
+	}
+}
+
+static inline void draw_byte_8(unsigned char *font, unsigned int *base, int rb)
+{
+	int l, bits;
+	int fg = 0x0F0F0F0FUL;
+	int bg = 0x00000000UL;
+	unsigned int *eb = (int *)expand_bits_8;
+
+	for (l = 0; l < 16; ++l)
+	{
+		bits = *font++;
+		base[0] = (eb[bits >> 4] & fg) ^ bg;
+		base[1] = (eb[bits & 0xf] & fg) ^ bg;
+		base = (unsigned int *) ((char *)base + rb);
+	}
+}
+
+static noinline void draw_byte(unsigned char c, long locX, long locY)
+{
+	unsigned char *base	= calc_base(locX << 3, locY << 4);
+	unsigned char *font	= &vga_font[((unsigned int)c) * 16];
+	int rb			= dispDeviceRowBytes;
+
+	rmci_maybe_on();
+	switch(dispDeviceDepth) {
+	case 24:
+	case 32:
+		draw_byte_32(font, (unsigned int *)base, rb);
+		break;
+	case 15:
+	case 16:
+		draw_byte_16(font, (unsigned int *)base, rb);
+		break;
+	case 8:
+		draw_byte_8(font, (unsigned int *)base, rb);
+		break;
+	}
+	rmci_maybe_off();
+}
+
 void btext_drawchar(char c)
 {
 	int cline = 0;
@@ -465,107 +591,12 @@ void btext_drawhex(unsigned long v)
 	btext_drawchar(' ');
 }
 
-static void draw_byte(unsigned char c, long locX, long locY)
-{
-	unsigned char *base	= calc_base(locX << 3, locY << 4);
-	unsigned char *font	= &vga_font[((unsigned int)c) * 16];
-	int rb			= dispDeviceRowBytes;
-
-	switch(dispDeviceDepth) {
-	case 24:
-	case 32:
-		draw_byte_32(font, (unsigned int *)base, rb);
-		break;
-	case 15:
-	case 16:
-		draw_byte_16(font, (unsigned int *)base, rb);
-		break;
-	case 8:
-		draw_byte_8(font, (unsigned int *)base, rb);
-		break;
-	}
-}
-
-static unsigned int expand_bits_8[16] = {
-	0x00000000,
-	0x000000ff,
-	0x0000ff00,
-	0x0000ffff,
-	0x00ff0000,
-	0x00ff00ff,
-	0x00ffff00,
-	0x00ffffff,
-	0xff000000,
-	0xff0000ff,
-	0xff00ff00,
-	0xff00ffff,
-	0xffff0000,
-	0xffff00ff,
-	0xffffff00,
-	0xffffffff
-};
-
-static unsigned int expand_bits_16[4] = {
-	0x00000000,
-	0x0000ffff,
-	0xffff0000,
-	0xffffffff
-};
-
-
-static void draw_byte_32(unsigned char *font, unsigned int *base, int rb)
-{
-	int l, bits;
-	int fg = 0xFFFFFFFFUL;
-	int bg = 0x00000000UL;
-
-	for (l = 0; l < 16; ++l)
-	{
-		bits = *font++;
-		base[0] = (-(bits >> 7) & fg) ^ bg;
-		base[1] = (-((bits >> 6) & 1) & fg) ^ bg;
-		base[2] = (-((bits >> 5) & 1) & fg) ^ bg;
-		base[3] = (-((bits >> 4) & 1) & fg) ^ bg;
-		base[4] = (-((bits >> 3) & 1) & fg) ^ bg;
-		base[5] = (-((bits >> 2) & 1) & fg) ^ bg;
-		base[6] = (-((bits >> 1) & 1) & fg) ^ bg;
-		base[7] = (-(bits & 1) & fg) ^ bg;
-		base = (unsigned int *) ((char *)base + rb);
-	}
-}
-
-static void draw_byte_16(unsigned char *font, unsigned int *base, int rb)
-{
-	int l, bits;
-	int fg = 0xFFFFFFFFUL;
-	int bg = 0x00000000UL;
-	unsigned int *eb = (int *)expand_bits_16;
-
-	for (l = 0; l < 16; ++l)
-	{
-		bits = *font++;
-		base[0] = (eb[bits >> 6] & fg) ^ bg;
-		base[1] = (eb[(bits >> 4) & 3] & fg) ^ bg;
-		base[2] = (eb[(bits >> 2) & 3] & fg) ^ bg;
-		base[3] = (eb[bits & 3] & fg) ^ bg;
-		base = (unsigned int *) ((char *)base + rb);
-	}
-}
-
-static void draw_byte_8(unsigned char *font, unsigned int *base, int rb)
+void __init udbg_init_btext(void)
 {
-	int l, bits;
-	int fg = 0x0F0F0F0FUL;
-	int bg = 0x00000000UL;
-	unsigned int *eb = (int *)expand_bits_8;
-
-	for (l = 0; l < 16; ++l)
-	{
-		bits = *font++;
-		base[0] = (eb[bits >> 4] & fg) ^ bg;
-		base[1] = (eb[bits & 0xf] & fg) ^ bg;
-		base = (unsigned int *) ((char *)base + rb);
-	}
+	/* If btext is enabled, we might have a BAT setup for early display,
+	 * thus we do enable some very basic udbg output
+	 */
+	udbg_putc = btext_drawchar;
 }
 
 static unsigned char vga_font[cmapsz] = {
@@ -913,10 +944,3 @@ static unsigned char vga_font[cmapsz] = {
 0x00, 0x00, 0x00, 0x00,
 };
 
-void __init udbg_init_btext(void)
-{
-	/* If btext is enabled, we might have a BAT setup for early display,
-	 * thus we do enable some very basic udbg output
-	 */
-	udbg_putc = btext_drawchar;
-}
diff --git a/arch/powerpc/kernel/cacheinfo.c b/arch/powerpc/kernel/cacheinfo.c
index 9262cf2bec4b..654932727873 100644
--- a/arch/powerpc/kernel/cacheinfo.c
+++ b/arch/powerpc/kernel/cacheinfo.c
@@ -196,7 +196,7 @@ static void cache_cpu_set(struct cache *cache, int cpu)
 static int cache_size(const struct cache *cache, unsigned int *ret)
 {
 	const char *propname;
-	const u32 *cache_size;
+	const __be32 *cache_size;
 
 	propname = cache_type_info[cache->type].size_prop;
 
@@ -204,7 +204,7 @@ static int cache_size(const struct cache *cache, unsigned int *ret)
 	if (!cache_size)
 		return -ENODEV;
 
-	*ret = *cache_size;
+	*ret = of_read_number(cache_size, 1);
 	return 0;
 }
 
@@ -222,7 +222,7 @@ static int cache_size_kb(const struct cache *cache, unsigned int *ret)
 /* not cache_line_size() because that's a macro in include/linux/cache.h */
 static int cache_get_line_size(const struct cache *cache, unsigned int *ret)
 {
-	const u32 *line_size;
+	const __be32 *line_size;
 	int i, lim;
 
 	lim = ARRAY_SIZE(cache_type_info[cache->type].line_size_props);
@@ -239,14 +239,14 @@ static int cache_get_line_size(const struct cache *cache, unsigned int *ret)
 	if (!line_size)
 		return -ENODEV;
 
-	*ret = *line_size;
+	*ret = of_read_number(line_size, 1);
 	return 0;
 }
 
 static int cache_nr_sets(const struct cache *cache, unsigned int *ret)
 {
 	const char *propname;
-	const u32 *nr_sets;
+	const __be32 *nr_sets;
 
 	propname = cache_type_info[cache->type].nr_sets_prop;
 
@@ -254,7 +254,7 @@ static int cache_nr_sets(const struct cache *cache, unsigned int *ret)
 	if (!nr_sets)
 		return -ENODEV;
 
-	*ret = *nr_sets;
+	*ret = of_read_number(nr_sets, 1);
 	return 0;
 }
 
diff --git a/arch/powerpc/kernel/cpu_setup_fsl_booke.S b/arch/powerpc/kernel/cpu_setup_fsl_booke.S
index 0b9af015bedc..bfb18c7290b7 100644
--- a/arch/powerpc/kernel/cpu_setup_fsl_booke.S
+++ b/arch/powerpc/kernel/cpu_setup_fsl_booke.S
@@ -75,7 +75,7 @@ _GLOBAL(__setup_cpu_e500v2)
 	bl	__e500_icache_setup
 	bl	__e500_dcache_setup
 	bl	__setup_e500_ivors
-#ifdef CONFIG_FSL_RIO
+#if defined(CONFIG_FSL_RIO) || defined(CONFIG_FSL_PCI)
 	/* Ensure that RFXE is set */
 	mfspr	r3,SPRN_HID1
 	oris	r3,r3,HID1_RFXE@h
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index 22973a74df73..597d954e5860 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -2105,7 +2105,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 			MMU_FTR_USE_TLBILX,
 		.icache_bsize		= 64,
 		.dcache_bsize		= 64,
-		.num_pmcs		= 4,
+		.num_pmcs		= 6,
 		.oprofile_cpu_type	= "ppc/e6500",
 		.oprofile_type		= PPC_OPROFILE_FSL_EMB,
 		.cpu_setup		= __setup_cpu_e6500,
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 2bd0b885b0fe..c04cdf70d487 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -102,7 +102,8 @@ BEGIN_FW_FTR_SECTION
 	/* if from user, see if there are any DTL entries to process */
 	ld	r10,PACALPPACAPTR(r13)	/* get ptr to VPA */
 	ld	r11,PACA_DTL_RIDX(r13)	/* get log read index */
-	ld	r10,LPPACA_DTLIDX(r10)	/* get log write index */
+	addi	r10,r10,LPPACA_DTLIDX
+	LDX_BE	r10,0,r10		/* get log write index */
 	cmpd	cr1,r11,r10
 	beq+	cr1,33f
 	bl	.accumulate_stolen_time
@@ -522,9 +523,11 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT)
 	 */
 	ld	r9,PACA_SLBSHADOWPTR(r13)
 	li	r12,0
-	std	r12,SLBSHADOW_STACKESID(r9) /* Clear ESID */
-	std	r7,SLBSHADOW_STACKVSID(r9)  /* Save VSID */
-	std	r0,SLBSHADOW_STACKESID(r9)  /* Save ESID */
+	std	r12,SLBSHADOW_STACKESID(r9)	/* Clear ESID */
+	li	r12,SLBSHADOW_STACKVSID
+	STDX_BE	r7,r12,r9			/* Save VSID */
+	li	r12,SLBSHADOW_STACKESID
+	STDX_BE	r0,r12,r9			/* Save ESID */
 
 	/* No need to check for MMU_FTR_NO_SLBIE_B here, since when
 	 * we have 1TB segments, the only CPUs known to have the errata
@@ -575,34 +578,15 @@ BEGIN_FTR_SECTION
 	ld	r7,DSCR_DEFAULT@toc(2)
 	ld	r0,THREAD_DSCR(r4)
 	cmpwi	r6,0
-	li	r8, FSCR_DSCR
 	bne	1f
 	ld	r0,0(r7)
-	b	3f
 1:
-  BEGIN_FTR_SECTION_NESTED(70)
-	mfspr	r6, SPRN_FSCR
-	or	r6, r6, r8
-	mtspr	SPRN_FSCR, r6
-    BEGIN_FTR_SECTION_NESTED(69)
-	mfspr	r6, SPRN_HFSCR
-	or	r6, r6, r8
-	mtspr	SPRN_HFSCR, r6
-    END_FTR_SECTION_NESTED(CPU_FTR_HVMODE, CPU_FTR_HVMODE, 69)
-	b	4f
-  END_FTR_SECTION_NESTED(CPU_FTR_ARCH_207S, CPU_FTR_ARCH_207S, 70)
-3:
-  BEGIN_FTR_SECTION_NESTED(70)
-	mfspr	r6, SPRN_FSCR
-	andc	r6, r6, r8
-	mtspr	SPRN_FSCR, r6
-    BEGIN_FTR_SECTION_NESTED(69)
-	mfspr	r6, SPRN_HFSCR
-	andc	r6, r6, r8
-	mtspr	SPRN_HFSCR, r6
-    END_FTR_SECTION_NESTED(CPU_FTR_HVMODE, CPU_FTR_HVMODE, 69)
-  END_FTR_SECTION_NESTED(CPU_FTR_ARCH_207S, CPU_FTR_ARCH_207S, 70)
-4:	cmpd	r0,r25
+BEGIN_FTR_SECTION_NESTED(70)
+	mfspr	r8, SPRN_FSCR
+	rldimi	r8, r6, FSCR_DSCR_LG, (63 - FSCR_DSCR_LG)
+	mtspr	SPRN_FSCR, r8
+END_FTR_SECTION_NESTED(CPU_FTR_ARCH_207S, CPU_FTR_ARCH_207S, 70)
+	cmpd	r0,r25
 	beq	2f
 	mtspr	SPRN_DSCR,r0
 2:
@@ -737,9 +721,9 @@ resume_kernel:
 
 	/*
 	 * Here we are preempting the current task. We want to make
-	 * sure we are soft-disabled first
+	 * sure we are soft-disabled first and reconcile irq state.
 	 */
-	SOFT_DISABLE_INTS(r3,r4)
+	RECONCILE_IRQ_STATE(r3,r4)
 1:	bl	.preempt_schedule_irq
 
 	/* Re-test flags and eventually loop */
diff --git a/arch/powerpc/kernel/epapr_paravirt.c b/arch/powerpc/kernel/epapr_paravirt.c
index d44a571e45a7..6300c13bbde4 100644
--- a/arch/powerpc/kernel/epapr_paravirt.c
+++ b/arch/powerpc/kernel/epapr_paravirt.c
@@ -30,22 +30,20 @@ extern u32 epapr_ev_idle_start[];
 
 bool epapr_paravirt_enabled;
 
-static int __init epapr_paravirt_init(void)
+static int __init early_init_dt_scan_epapr(unsigned long node,
+					   const char *uname,
+					   int depth, void *data)
 {
-	struct device_node *hyper_node;
 	const u32 *insts;
-	int len, i;
+	unsigned long len;
+	int i;
 
-	hyper_node = of_find_node_by_path("/hypervisor");
-	if (!hyper_node)
-		return -ENODEV;
-
-	insts = of_get_property(hyper_node, "hcall-instructions", &len);
+	insts = of_get_flat_dt_prop(node, "hcall-instructions", &len);
 	if (!insts)
-		return -ENODEV;
+		return 0;
 
 	if (len % 4 || len > (4 * 4))
-		return -ENODEV;
+		return -1;
 
 	for (i = 0; i < (len / 4); i++) {
 		patch_instruction(epapr_hypercall_start + i, insts[i]);
@@ -55,13 +53,19 @@ static int __init epapr_paravirt_init(void)
 	}
 
 #if !defined(CONFIG_64BIT) || defined(CONFIG_PPC_BOOK3E_64)
-	if (of_get_property(hyper_node, "has-idle", NULL))
+	if (of_get_flat_dt_prop(node, "has-idle", NULL))
 		ppc_md.power_save = epapr_ev_idle;
 #endif
 
 	epapr_paravirt_enabled = true;
 
+	return 1;
+}
+
+int __init epapr_paravirt_early_init(void)
+{
+	of_scan_flat_dt(early_init_dt_scan_epapr, NULL);
+
 	return 0;
 }
 
-early_initcall(epapr_paravirt_init);
diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S
index 645170a07ada..2d067049db27 100644
--- a/arch/powerpc/kernel/exceptions-64e.S
+++ b/arch/powerpc/kernel/exceptions-64e.S
@@ -198,9 +198,9 @@ exc_##n##_common:							    \
 /* This second version is meant for exceptions that don't immediately
  * hard-enable. We set a bit in paca->irq_happened to ensure that
  * a subsequent call to arch_local_irq_restore() will properly
- * hard-enable and avoid the fast-path
+ * hard-enable and avoid the fast-path, and then reconcile irq state.
  */
-#define INTS_DISABLE	SOFT_DISABLE_INTS(r3,r4)
+#define INTS_DISABLE	RECONCILE_IRQ_STATE(r3,r4)
 
 /* This is called by exceptions that used INTS_KEEP (that did not touch
  * irq indicators in the PACA). This will restore MSR:EE to it's previous
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 902ca3c6b4b6..3a9ed6ac224b 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -293,27 +293,31 @@ system_call_pSeries:
 	 * out of line to handle them
 	 */
 	. = 0xe00
-hv_exception_trampoline:
+hv_data_storage_trampoline:
 	SET_SCRATCH0(r13)
 	EXCEPTION_PROLOG_0(PACA_EXGEN)
 	b	h_data_storage_hv
 
 	. = 0xe20
+hv_instr_storage_trampoline:
 	SET_SCRATCH0(r13)
 	EXCEPTION_PROLOG_0(PACA_EXGEN)
 	b	h_instr_storage_hv
 
 	. = 0xe40
+emulation_assist_trampoline:
 	SET_SCRATCH0(r13)
 	EXCEPTION_PROLOG_0(PACA_EXGEN)
 	b	emulation_assist_hv
 
 	. = 0xe60
+hv_exception_trampoline:
 	SET_SCRATCH0(r13)
 	EXCEPTION_PROLOG_0(PACA_EXGEN)
 	b	hmi_exception_hv
 
 	. = 0xe80
+hv_doorbell_trampoline:
 	SET_SCRATCH0(r13)
 	EXCEPTION_PROLOG_0(PACA_EXGEN)
 	b	h_doorbell_hv
@@ -323,32 +327,32 @@ hv_exception_trampoline:
 	 * prolog code of the PerformanceMonitor one. A little
 	 * trickery is thus necessary
 	 */
-performance_monitor_pSeries_1:
 	. = 0xf00
+performance_monitor_pseries_trampoline:
 	SET_SCRATCH0(r13)
 	EXCEPTION_PROLOG_0(PACA_EXGEN)
 	b	performance_monitor_pSeries
 
-altivec_unavailable_pSeries_1:
 	. = 0xf20
+altivec_unavailable_pseries_trampoline:
 	SET_SCRATCH0(r13)
 	EXCEPTION_PROLOG_0(PACA_EXGEN)
 	b	altivec_unavailable_pSeries
 
-vsx_unavailable_pSeries_1:
 	. = 0xf40
+vsx_unavailable_pseries_trampoline:
 	SET_SCRATCH0(r13)
 	EXCEPTION_PROLOG_0(PACA_EXGEN)
 	b	vsx_unavailable_pSeries
 
-facility_unavailable_trampoline:
 	. = 0xf60
+facility_unavailable_trampoline:
 	SET_SCRATCH0(r13)
 	EXCEPTION_PROLOG_0(PACA_EXGEN)
 	b	facility_unavailable_pSeries
 
-hv_facility_unavailable_trampoline:
 	. = 0xf80
+hv_facility_unavailable_trampoline:
 	SET_SCRATCH0(r13)
 	EXCEPTION_PROLOG_0(PACA_EXGEN)
 	b	facility_unavailable_hv
@@ -367,11 +371,7 @@ denorm_exception_hv:
 	HMT_MEDIUM_PPR_DISCARD
 	mtspr	SPRN_SPRG_HSCRATCH0,r13
 	EXCEPTION_PROLOG_0(PACA_EXGEN)
-	std	r11,PACA_EXGEN+EX_R11(r13)
-	std	r12,PACA_EXGEN+EX_R12(r13)
-	mfspr	r9,SPRN_SPRG_HSCRATCH0
-	std	r9,PACA_EXGEN+EX_R13(r13)
-	mfcr	r9
+	EXCEPTION_PROLOG_1(PACA_EXGEN, NOTEST, 0x1500)
 
 #ifdef CONFIG_PPC_DENORMALISATION
 	mfspr	r10,SPRN_HSRR1
@@ -381,6 +381,7 @@ denorm_exception_hv:
 	bne+	denorm_assist
 #endif
 
+	KVMTEST(0x1500)
 	EXCEPTION_PROLOG_PSERIES_1(denorm_common, EXC_HV)
 	KVM_HANDLER_SKIP(PACA_EXGEN, EXC_STD, 0x1500)
 
@@ -501,6 +502,10 @@ denorm_done:
 	mtcrf	0x80,r9
 	ld	r9,PACA_EXGEN+EX_R9(r13)
 	RESTORE_PPR_PACA(PACA_EXGEN, r10)
+BEGIN_FTR_SECTION
+	ld	r10,PACA_EXGEN+EX_CFAR(r13)
+	mtspr	SPRN_CFAR,r10
+END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
 	ld	r10,PACA_EXGEN+EX_R10(r13)
 	ld	r11,PACA_EXGEN+EX_R11(r13)
 	ld	r12,PACA_EXGEN+EX_R12(r13)
@@ -808,6 +813,7 @@ system_call_relon_pSeries:
 	b	.	/* Can't happen, see v2.07 Book III-S section 6.5 */
 
 	. = 0x4e40
+emulation_assist_relon_trampoline:
 	SET_SCRATCH0(r13)
 	EXCEPTION_PROLOG_0(PACA_EXGEN)
 	b	emulation_assist_relon_hv
@@ -816,36 +822,37 @@ system_call_relon_pSeries:
 	b	.	/* Can't happen, see v2.07 Book III-S section 6.5 */
 
 	. = 0x4e80
+h_doorbell_relon_trampoline:
 	SET_SCRATCH0(r13)
 	EXCEPTION_PROLOG_0(PACA_EXGEN)
 	b	h_doorbell_relon_hv
 
-performance_monitor_relon_pSeries_1:
 	. = 0x4f00
+performance_monitor_relon_pseries_trampoline:
 	SET_SCRATCH0(r13)
 	EXCEPTION_PROLOG_0(PACA_EXGEN)
 	b	performance_monitor_relon_pSeries
 
-altivec_unavailable_relon_pSeries_1:
 	. = 0x4f20
+altivec_unavailable_relon_pseries_trampoline:
 	SET_SCRATCH0(r13)
 	EXCEPTION_PROLOG_0(PACA_EXGEN)
 	b	altivec_unavailable_relon_pSeries
 
-vsx_unavailable_relon_pSeries_1:
 	. = 0x4f40
+vsx_unavailable_relon_pseries_trampoline:
 	SET_SCRATCH0(r13)
 	EXCEPTION_PROLOG_0(PACA_EXGEN)
 	b	vsx_unavailable_relon_pSeries
 
-facility_unavailable_relon_trampoline:
 	. = 0x4f60
+facility_unavailable_relon_trampoline:
 	SET_SCRATCH0(r13)
 	EXCEPTION_PROLOG_0(PACA_EXGEN)
 	b	facility_unavailable_relon_pSeries
 
-hv_facility_unavailable_relon_trampoline:
 	. = 0x4f80
+hv_facility_unavailable_relon_trampoline:
 	SET_SCRATCH0(r13)
 	EXCEPTION_PROLOG_0(PACA_EXGEN)
 	b	hv_facility_unavailable_relon_hv
diff --git a/arch/powerpc/kernel/head_40x.S b/arch/powerpc/kernel/head_40x.S
index 8a9b6f59822d..67ee0d6c1070 100644
--- a/arch/powerpc/kernel/head_40x.S
+++ b/arch/powerpc/kernel/head_40x.S
@@ -822,14 +822,6 @@ finish_tlb_load:
 	rfi			/* Should sync shadow TLBs */
 	b	.		/* prevent prefetch past rfi */
 
-/* extern void giveup_fpu(struct task_struct *prev)
- *
- * The PowerPC 4xx family of processors do not have an FPU, so this just
- * returns.
- */
-_ENTRY(giveup_fpu)
-	blr
-
 /* This is where the main kernel code starts.
  */
 start_here:
diff --git a/arch/powerpc/kernel/head_44x.S b/arch/powerpc/kernel/head_44x.S
index 97e2671cde7f..c334f53453f7 100644
--- a/arch/powerpc/kernel/head_44x.S
+++ b/arch/powerpc/kernel/head_44x.S
@@ -784,16 +784,6 @@ _GLOBAL(__fixup_440A_mcheck)
 	sync
 	blr
 
-/*
- * extern void giveup_fpu(struct task_struct *prev)
- *
- * The 44x core does not have an FPU.
- */
-#ifndef CONFIG_PPC_FPU
-_GLOBAL(giveup_fpu)
-	blr
-#endif
-
 _GLOBAL(set_context)
 
 #ifdef CONFIG_BDI_SWITCH
diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S
index b61363d557b5..3d11d8038dee 100644
--- a/arch/powerpc/kernel/head_64.S
+++ b/arch/powerpc/kernel/head_64.S
@@ -703,6 +703,7 @@ _GLOBAL(relative_toc)
 	mtlr	r0
 	blr
 
+.balign 8
 p_toc:	.llong	__toc_start + 0x8000 - 0b
 
 /*
diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S
index b2a5860accfb..1b92a97b1b04 100644
--- a/arch/powerpc/kernel/head_8xx.S
+++ b/arch/powerpc/kernel/head_8xx.S
@@ -691,10 +691,6 @@ modified_instr:
 	b	151b
 #endif
 
-	.globl	giveup_fpu
-giveup_fpu:
-	blr
-
 /*
  * This is where the main kernel code starts.
  */
diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S
index d10a7cacccd2..289afaffbbb5 100644
--- a/arch/powerpc/kernel/head_fsl_booke.S
+++ b/arch/powerpc/kernel/head_fsl_booke.S
@@ -948,16 +948,6 @@ _GLOBAL(giveup_spe)
 #endif /* CONFIG_SPE */
 
 /*
- * extern void giveup_fpu(struct task_struct *prev)
- *
- * Not all FSL Book-E cores have an FPU
- */
-#ifndef CONFIG_PPC_FPU
-_GLOBAL(giveup_fpu)
-	blr
-#endif
-
-/*
  * extern void abort(void)
  *
  * At present, this routine just applies a system reset.
diff --git a/arch/powerpc/kernel/io-workarounds.c b/arch/powerpc/kernel/io-workarounds.c
index fa0b54b2a362..24b968f8e4d8 100644
--- a/arch/powerpc/kernel/io-workarounds.c
+++ b/arch/powerpc/kernel/io-workarounds.c
@@ -53,6 +53,7 @@ static struct iowa_bus *iowa_pci_find(unsigned long vaddr, unsigned long paddr)
 	return NULL;
 }
 
+#ifdef CONFIG_PPC_INDIRECT_MMIO
 struct iowa_bus *iowa_mem_find_bus(const PCI_IO_ADDR addr)
 {
 	unsigned hugepage_shift;
@@ -90,13 +91,25 @@ struct iowa_bus *iowa_mem_find_bus(const PCI_IO_ADDR addr)
 
 	return bus;
 }
+#else /* CONFIG_PPC_INDIRECT_MMIO */
+struct iowa_bus *iowa_mem_find_bus(const PCI_IO_ADDR addr)
+{
+	return NULL;
+}
+#endif /* !CONFIG_PPC_INDIRECT_MMIO */
 
+#ifdef CONFIG_PPC_INDIRECT_PIO
 struct iowa_bus *iowa_pio_find_bus(unsigned long port)
 {
 	unsigned long vaddr = (unsigned long)pci_io_base + port;
 	return iowa_pci_find(vaddr, 0);
 }
-
+#else
+struct iowa_bus *iowa_pio_find_bus(unsigned long port)
+{
+	return NULL;
+}
+#endif
 
 #define DEF_PCI_AC_RET(name, ret, at, al, space, aa)		\
 static ret iowa_##name at					\
@@ -137,6 +150,7 @@ static const struct ppc_pci_io iowa_pci_io = {
 
 };
 
+#ifdef CONFIG_PPC_INDIRECT_MMIO
 static void __iomem *iowa_ioremap(phys_addr_t addr, unsigned long size,
 				  unsigned long flags, void *caller)
 {
@@ -151,6 +165,9 @@ static void __iomem *iowa_ioremap(phys_addr_t addr, unsigned long size,
 	}
 	return res;
 }
+#else /* CONFIG_PPC_INDIRECT_MMIO */
+#define iowa_ioremap NULL
+#endif /* !CONFIG_PPC_INDIRECT_MMIO */
 
 /* Enable IO workaround */
 static void io_workaround_init(void)
diff --git a/arch/powerpc/kernel/io.c b/arch/powerpc/kernel/io.c
index 886381f32c3d..2a2b4aeab80f 100644
--- a/arch/powerpc/kernel/io.c
+++ b/arch/powerpc/kernel/io.c
@@ -25,6 +25,9 @@
 #include <asm/firmware.h>
 #include <asm/bug.h>
 
+/* See definition in io.h */
+bool isa_io_special;
+
 void _insb(const volatile u8 __iomem *port, void *buf, long count)
 {
 	u8 *tbuf = buf;
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index b20ff173a671..572bb5b95f35 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -105,7 +105,7 @@ static int __init fail_iommu_debugfs(void)
 	struct dentry *dir = fault_create_debugfs_attr("fail_iommu",
 						       NULL, &fail_iommu);
 
-	return PTR_RET(dir);
+	return PTR_ERR_OR_ZERO(dir);
 }
 late_initcall(fail_iommu_debugfs);
 
@@ -661,7 +661,7 @@ struct iommu_table *iommu_init_table(struct iommu_table *tbl, int nid)
 	/* number of bytes needed for the bitmap */
 	sz = BITS_TO_LONGS(tbl->it_size) * sizeof(unsigned long);
 
-	page = alloc_pages_node(nid, GFP_ATOMIC, get_order(sz));
+	page = alloc_pages_node(nid, GFP_KERNEL, get_order(sz));
 	if (!page)
 		panic("iommu_init_table: Can't allocate %ld bytes\n", sz);
 	tbl->it_map = page_address(page);
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index c69440cef7af..c7cb8c232d2f 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -441,50 +441,6 @@ void migrate_irqs(void)
 }
 #endif
 
-static inline void handle_one_irq(unsigned int irq)
-{
-	struct thread_info *curtp, *irqtp;
-	unsigned long saved_sp_limit;
-	struct irq_desc *desc;
-
-	desc = irq_to_desc(irq);
-	if (!desc)
-		return;
-
-	/* Switch to the irq stack to handle this */
-	curtp = current_thread_info();
-	irqtp = hardirq_ctx[smp_processor_id()];
-
-	if (curtp == irqtp) {
-		/* We're already on the irq stack, just handle it */
-		desc->handle_irq(irq, desc);
-		return;
-	}
-
-	saved_sp_limit = current->thread.ksp_limit;
-
-	irqtp->task = curtp->task;
-	irqtp->flags = 0;
-
-	/* Copy the softirq bits in preempt_count so that the
-	 * softirq checks work in the hardirq context. */
-	irqtp->preempt_count = (irqtp->preempt_count & ~SOFTIRQ_MASK) |
-			       (curtp->preempt_count & SOFTIRQ_MASK);
-
-	current->thread.ksp_limit = (unsigned long)irqtp +
-		_ALIGN_UP(sizeof(struct thread_info), 16);
-
-	call_handle_irq(irq, desc, irqtp, desc->handle_irq);
-	current->thread.ksp_limit = saved_sp_limit;
-	irqtp->task = NULL;
-
-	/* Set any flag that may have been set on the
-	 * alternate stack
-	 */
-	if (irqtp->flags)
-		set_bits(irqtp->flags, &curtp->flags);
-}
-
 static inline void check_stack_overflow(void)
 {
 #ifdef CONFIG_DEBUG_STACKOVERFLOW
@@ -501,9 +457,9 @@ static inline void check_stack_overflow(void)
 #endif
 }
 
-void do_IRQ(struct pt_regs *regs)
+void __do_irq(struct pt_regs *regs)
 {
-	struct pt_regs *old_regs = set_irq_regs(regs);
+	struct irq_desc *desc;
 	unsigned int irq;
 
 	irq_enter();
@@ -519,18 +475,57 @@ void do_IRQ(struct pt_regs *regs)
 	 */
 	irq = ppc_md.get_irq();
 
-	/* We can hard enable interrupts now */
+	/* We can hard enable interrupts now to allow perf interrupts */
 	may_hard_irq_enable();
 
 	/* And finally process it */
-	if (irq != NO_IRQ)
-		handle_one_irq(irq);
-	else
+	if (unlikely(irq == NO_IRQ))
 		__get_cpu_var(irq_stat).spurious_irqs++;
+	else {
+		desc = irq_to_desc(irq);
+		if (likely(desc))
+			desc->handle_irq(irq, desc);
+	}
 
 	trace_irq_exit(regs);
 
 	irq_exit();
+}
+
+void do_IRQ(struct pt_regs *regs)
+{
+	struct pt_regs *old_regs = set_irq_regs(regs);
+	struct thread_info *curtp, *irqtp, *sirqtp;
+
+	/* Switch to the irq stack to handle this */
+	curtp = current_thread_info();
+	irqtp = hardirq_ctx[raw_smp_processor_id()];
+	sirqtp = softirq_ctx[raw_smp_processor_id()];
+
+	/* Already there ? */
+	if (unlikely(curtp == irqtp || curtp == sirqtp)) {
+		__do_irq(regs);
+		set_irq_regs(old_regs);
+		return;
+	}
+
+	/* Prepare the thread_info in the irq stack */
+	irqtp->task = curtp->task;
+	irqtp->flags = 0;
+
+	/* Copy the preempt_count so that the [soft]irq checks work. */
+	irqtp->preempt_count = curtp->preempt_count;
+
+	/* Switch stack and call */
+	call_do_irq(regs, irqtp);
+
+	/* Restore stack limit */
+	irqtp->task = NULL;
+
+	/* Copy back updates to the thread_info */
+	if (irqtp->flags)
+		set_bits(irqtp->flags, &curtp->flags);
+
 	set_irq_regs(old_regs);
 }
 
@@ -592,28 +587,22 @@ void irq_ctx_init(void)
 		memset((void *)softirq_ctx[i], 0, THREAD_SIZE);
 		tp = softirq_ctx[i];
 		tp->cpu = i;
-		tp->preempt_count = 0;
 
 		memset((void *)hardirq_ctx[i], 0, THREAD_SIZE);
 		tp = hardirq_ctx[i];
 		tp->cpu = i;
-		tp->preempt_count = HARDIRQ_OFFSET;
 	}
 }
 
 static inline void do_softirq_onstack(void)
 {
 	struct thread_info *curtp, *irqtp;
-	unsigned long saved_sp_limit = current->thread.ksp_limit;
 
 	curtp = current_thread_info();
 	irqtp = softirq_ctx[smp_processor_id()];
 	irqtp->task = curtp->task;
 	irqtp->flags = 0;
-	current->thread.ksp_limit = (unsigned long)irqtp +
-				    _ALIGN_UP(sizeof(struct thread_info), 16);
 	call_do_softirq(irqtp);
-	current->thread.ksp_limit = saved_sp_limit;
 	irqtp->task = NULL;
 
 	/* Set any flag that may have been set on the
diff --git a/arch/powerpc/kernel/legacy_serial.c b/arch/powerpc/kernel/legacy_serial.c
index 0733b05eb856..22e88dd2f34a 100644
--- a/arch/powerpc/kernel/legacy_serial.c
+++ b/arch/powerpc/kernel/legacy_serial.c
@@ -99,7 +99,7 @@ static int __init add_legacy_port(struct device_node *np, int want_index,
 		legacy_serial_count = index + 1;
 
 	/* Check if there is a port who already claimed our slot */
-	if (legacy_serial_infos[index].np != 0) {
+	if (legacy_serial_infos[index].np != NULL) {
 		/* if we still have some room, move it, else override */
 		if (legacy_serial_count < MAX_LEGACY_SERIAL_PORTS) {
 			printk(KERN_DEBUG "Moved legacy port %d -> %d\n",
@@ -152,7 +152,7 @@ static int __init add_legacy_soc_port(struct device_node *np,
 				      struct device_node *soc_dev)
 {
 	u64 addr;
-	const u32 *addrp;
+	const __be32 *addrp;
 	upf_t flags = UPF_BOOT_AUTOCONF | UPF_SKIP_TEST | UPF_SHARE_IRQ
 		| UPF_FIXED_PORT;
 	struct device_node *tsi = of_get_parent(np);
@@ -221,14 +221,19 @@ static int __init add_legacy_isa_port(struct device_node *np,
 	/* Translate ISA address. If it fails, we still register the port
 	 * with no translated address so that it can be picked up as an IO
 	 * port later by the serial driver
+	 *
+	 * Note: Don't even try on P8 lpc, we know it's not directly mapped
 	 */
-	taddr = of_translate_address(np, reg);
-	if (taddr == OF_BAD_ADDR)
+	if (!of_device_is_compatible(isa_brg, "ibm,power8-lpc")) {
+		taddr = of_translate_address(np, reg);
+		if (taddr == OF_BAD_ADDR)
+			taddr = 0;
+	} else
 		taddr = 0;
 
 	/* Add port, irq will be dealt with later */
-	return add_legacy_port(np, index, UPIO_PORT, be32_to_cpu(reg[1]), taddr,
-			       NO_IRQ, UPF_BOOT_AUTOCONF, 0);
+	return add_legacy_port(np, index, UPIO_PORT, be32_to_cpu(reg[1]),
+			       taddr, NO_IRQ, UPF_BOOT_AUTOCONF, 0);
 
 }
 
@@ -237,7 +242,7 @@ static int __init add_legacy_pci_port(struct device_node *np,
 				      struct device_node *pci_dev)
 {
 	u64 addr, base;
-	const u32 *addrp;
+	const __be32 *addrp;
 	unsigned int flags;
 	int iotype, index = -1, lindex = 0;
 
@@ -270,7 +275,7 @@ static int __init add_legacy_pci_port(struct device_node *np,
 	if (iotype == UPIO_MEM)
 		base = addr;
 	else
-		base = addrp[2];
+		base = of_read_number(&addrp[2], 1);
 
 	/* Try to guess an index... If we have subdevices of the pci dev,
 	 * we get to their "reg" property
@@ -307,19 +312,31 @@ static int __init add_legacy_pci_port(struct device_node *np,
 
 static void __init setup_legacy_serial_console(int console)
 {
-	struct legacy_serial_info *info =
-		&legacy_serial_infos[console];
+	struct legacy_serial_info *info = &legacy_serial_infos[console];
+	struct plat_serial8250_port *port = &legacy_serial_ports[console];
 	void __iomem *addr;
 
-	if (info->taddr == 0)
-		return;
-	addr = ioremap(info->taddr, 0x1000);
-	if (addr == NULL)
-		return;
+	/* Check if a translated MMIO address has been found */
+	if (info->taddr) {
+		addr = ioremap(info->taddr, 0x1000);
+		if (addr == NULL)
+			return;
+		udbg_uart_init_mmio(addr, 1);
+	} else {
+		/* Check if it's PIO and we support untranslated PIO */
+		if (port->iotype == UPIO_PORT && isa_io_special)
+			udbg_uart_init_pio(port->iobase, 1);
+		else
+			return;
+	}
+
+	/* Try to query the current speed */
 	if (info->speed == 0)
-		info->speed = udbg_probe_uart_speed(addr, info->clock);
+		info->speed = udbg_probe_uart_speed(info->clock);
+
+	/* Set it up */
 	DBG("default console speed = %d\n", info->speed);
-	udbg_init_uart(addr, info->speed, info->clock);
+	udbg_uart_setup(info->speed, info->clock);
 }
 
 /*
@@ -367,10 +384,13 @@ void __init find_legacy_serial_ports(void)
 	/* Next, fill our array with ISA ports */
 	for_each_node_by_type(np, "serial") {
 		struct device_node *isa = of_get_parent(np);
-		if (isa && !strcmp(isa->name, "isa")) {
-			index = add_legacy_isa_port(np, isa);
-			if (index >= 0 && np == stdout)
-				legacy_serial_console = index;
+		if (isa && (!strcmp(isa->name, "isa") ||
+			    !strcmp(isa->name, "lpc"))) {
+			if (of_device_is_available(np)) {
+				index = add_legacy_isa_port(np, isa);
+				if (index >= 0 && np == stdout)
+					legacy_serial_console = index;
+			}
 		}
 		of_node_put(isa);
 	}
diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S
index e469f30e6eeb..2b0ad9845363 100644
--- a/arch/powerpc/kernel/misc_32.S
+++ b/arch/powerpc/kernel/misc_32.S
@@ -36,26 +36,41 @@
 
 	.text
 
+/*
+ * We store the saved ksp_limit in the unused part
+ * of the STACK_FRAME_OVERHEAD
+ */
 _GLOBAL(call_do_softirq)
 	mflr	r0
 	stw	r0,4(r1)
+	lwz	r10,THREAD+KSP_LIMIT(r2)
+	addi	r11,r3,THREAD_INFO_GAP
 	stwu	r1,THREAD_SIZE-STACK_FRAME_OVERHEAD(r3)
 	mr	r1,r3
+	stw	r10,8(r1)
+	stw	r11,THREAD+KSP_LIMIT(r2)
 	bl	__do_softirq
+	lwz	r10,8(r1)
 	lwz	r1,0(r1)
 	lwz	r0,4(r1)
+	stw	r10,THREAD+KSP_LIMIT(r2)
 	mtlr	r0
 	blr
 
-_GLOBAL(call_handle_irq)
+_GLOBAL(call_do_irq)
 	mflr	r0
 	stw	r0,4(r1)
-	mtctr	r6
-	stwu	r1,THREAD_SIZE-STACK_FRAME_OVERHEAD(r5)
-	mr	r1,r5
-	bctrl
+	lwz	r10,THREAD+KSP_LIMIT(r2)
+	addi	r11,r3,THREAD_INFO_GAP
+	stwu	r1,THREAD_SIZE-STACK_FRAME_OVERHEAD(r4)
+	mr	r1,r4
+	stw	r10,8(r1)
+	stw	r11,THREAD+KSP_LIMIT(r2)
+	bl	__do_irq
+	lwz	r10,8(r1)
 	lwz	r1,0(r1)
 	lwz	r0,4(r1)
+	stw	r10,THREAD+KSP_LIMIT(r2)
 	mtlr	r0
 	blr
 
@@ -327,8 +342,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_UNIFIED_ID_CACHE)
  *
  * flush_icache_range(unsigned long start, unsigned long stop)
  */
-_KPROBE(__flush_icache_range)
+_KPROBE(flush_icache_range)
 BEGIN_FTR_SECTION
+	isync
 	blr				/* for 601, do nothing */
 END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE)
 	li	r5,L1_CACHE_BYTES-1
diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S
index 6820e45f557b..e59caf874d05 100644
--- a/arch/powerpc/kernel/misc_64.S
+++ b/arch/powerpc/kernel/misc_64.S
@@ -40,14 +40,12 @@ _GLOBAL(call_do_softirq)
 	mtlr	r0
 	blr
 
-_GLOBAL(call_handle_irq)
-	ld	r8,0(r6)
+_GLOBAL(call_do_irq)
 	mflr	r0
 	std	r0,16(r1)
-	mtctr	r8
-	stdu	r1,THREAD_SIZE-STACK_FRAME_OVERHEAD(r5)
-	mr	r1,r5
-	bctrl
+	stdu	r1,THREAD_SIZE-STACK_FRAME_OVERHEAD(r4)
+	mr	r1,r4
+	bl	.__do_irq
 	ld	r1,0(r1)
 	ld	r0,16(r1)
 	mtlr	r0
@@ -67,8 +65,10 @@ PPC64_CACHES:
  *   flush all bytes from start through stop-1 inclusive
  */
 
-_KPROBE(__flush_icache_range)
-
+_KPROBE(flush_icache_range)
+BEGIN_FTR_SECTION
+	blr
+END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE)
 /*
  * Flush the data cache to memory 
  * 
@@ -247,6 +247,37 @@ _GLOBAL(__bswapdi2)
 	blr
 
 #if defined(CONFIG_PPC_PMAC) || defined(CONFIG_PPC_MAPLE)
+
+_GLOBAL(rmci_on)
+	sync
+	isync
+	li	r3,0x100
+	rldicl	r3,r3,32,0
+	mfspr	r5,SPRN_HID4
+	or	r5,r5,r3
+	sync
+	mtspr	SPRN_HID4,r5
+	isync
+	slbia
+	isync
+	sync
+	blr
+
+_GLOBAL(rmci_off)
+	sync
+	isync
+	li	r3,0x100
+	rldicl	r3,r3,32,0
+	mfspr	r5,SPRN_HID4
+	andc	r5,r5,r3
+	sync
+	mtspr	SPRN_HID4,r5
+	isync
+	slbia
+	isync
+	sync
+	blr
+
 /*
  * Do an IO access in real mode
  */
@@ -416,19 +447,6 @@ _GLOBAL(scom970_write)
 	blr
 #endif /* CONFIG_CPU_FREQ_PMAC64 || CONFIG_CPU_FREQ_MAPLE */
 
-
-/*
- * disable_kernel_fp()
- * Disable the FPU.
- */
-_GLOBAL(disable_kernel_fp)
-	mfmsr	r3
-	rldicl	r0,r3,(63-MSR_FP_LG),1
-	rldicl	r3,r0,(MSR_FP_LG+1),0
-	mtmsrd	r3			/* disable use of fpu now */
-	isync
-	blr
-
 /* kexec_wait(phys_cpu)
  *
  * wait for the flag to change, indicating this kernel is going away but
diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c
index f8f24685f10a..3fc16e3beb9f 100644
--- a/arch/powerpc/kernel/paca.c
+++ b/arch/powerpc/kernel/paca.c
@@ -34,10 +34,10 @@ extern unsigned long __toc_start;
  */
 struct lppaca lppaca[] = {
 	[0 ... (NR_LPPACAS-1)] = {
-		.desc = 0xd397d781,	/* "LpPa" */
-		.size = sizeof(struct lppaca),
+		.desc = cpu_to_be32(0xd397d781),	/* "LpPa" */
+		.size = cpu_to_be16(sizeof(struct lppaca)),
 		.fpregs_in_use = 1,
-		.slb_count = 64,
+		.slb_count = cpu_to_be16(64),
 		.vmxregs_in_use = 0,
 		.page_ins = 0,
 	},
@@ -101,8 +101,8 @@ static inline void free_lppacas(void) { }
  */
 struct slb_shadow slb_shadow[] __cacheline_aligned = {
 	[0 ... (NR_CPUS-1)] = {
-		.persistent = SLB_NUM_BOLTED,
-		.buffer_length = sizeof(struct slb_shadow),
+		.persistent = cpu_to_be32(SLB_NUM_BOLTED),
+		.buffer_length = cpu_to_be32(sizeof(struct slb_shadow)),
 	},
 };
 
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index 7d22a675fe1a..905a24bb7acc 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -306,7 +306,7 @@ static struct resource *__pci_mmap_make_offset(struct pci_dev *dev,
 	unsigned long io_offset = 0;
 	int i, res_bit;
 
-	if (hose == 0)
+	if (hose == NULL)
 		return NULL;		/* should never happen */
 
 	/* If memory, add on the PCI bridge address offset */
@@ -667,7 +667,7 @@ void pci_resource_to_user(const struct pci_dev *dev, int bar,
 void pci_process_bridge_OF_ranges(struct pci_controller *hose,
 				  struct device_node *dev, int primary)
 {
-	const u32 *ranges;
+	const __be32 *ranges;
 	int rlen;
 	int pna = of_n_addr_cells(dev);
 	int np = pna + 5;
@@ -687,7 +687,7 @@ void pci_process_bridge_OF_ranges(struct pci_controller *hose,
 	/* Parse it */
 	while ((rlen -= np * 4) >= 0) {
 		/* Read next ranges element */
-		pci_space = ranges[0];
+		pci_space = of_read_number(ranges, 1);
 		pci_addr = of_read_number(ranges + 1, 2);
 		cpu_addr = of_translate_address(dev, ranges + 3);
 		size = of_read_number(ranges + pna + 3, 2);
@@ -704,7 +704,7 @@ void pci_process_bridge_OF_ranges(struct pci_controller *hose,
 		/* Now consume following elements while they are contiguous */
 		for (; rlen >= np * sizeof(u32);
 		     ranges += np, rlen -= np * 4) {
-			if (ranges[0] != pci_space)
+			if (of_read_number(ranges, 1) != pci_space)
 				break;
 			pci_next = of_read_number(ranges + 1, 2);
 			cpu_next = of_translate_address(dev, ranges + 3);
@@ -1055,8 +1055,7 @@ void pcibios_fixup_bus(struct pci_bus *bus)
 	 * bases. This is -not- called when generating the PCI tree from
 	 * the OF device-tree.
 	 */
-	if (bus->self != NULL)
-		pci_read_bridge_bases(bus);
+	pci_read_bridge_bases(bus);
 
 	/* Now fixup the bus bus */
 	pcibios_setup_bus_self(bus);
@@ -1578,7 +1577,7 @@ fake_pci_bus(struct pci_controller *hose, int busnr)
 {
 	static struct pci_bus bus;
 
-	if (hose == 0) {
+	if (hose == NULL) {
 		printk(KERN_ERR "Can't find hose for PCI bus %d!\n", busnr);
 	}
 	bus.number = busnr;
@@ -1674,12 +1673,8 @@ void pcibios_scan_phb(struct pci_controller *hose)
 	/* Configure PCI Express settings */
 	if (bus && !pci_has_flag(PCI_PROBE_ONLY)) {
 		struct pci_bus *child;
-		list_for_each_entry(child, &bus->children, node) {
-			struct pci_dev *self = child->self;
-			if (!self)
-				continue;
-			pcie_bus_configure_settings(child, self->pcie_mpss);
-		}
+		list_for_each_entry(child, &bus->children, node)
+			pcie_bus_configure_settings(child);
 	}
 }
 
diff --git a/arch/powerpc/kernel/pci_64.c b/arch/powerpc/kernel/pci_64.c
index 2e8629654ca8..a9e311f7a9dd 100644
--- a/arch/powerpc/kernel/pci_64.c
+++ b/arch/powerpc/kernel/pci_64.c
@@ -109,7 +109,7 @@ int pcibios_unmap_io_space(struct pci_bus *bus)
 	hose = pci_bus_to_host(bus);
 
 	/* Check if we have IOs allocated */
-	if (hose->io_base_alloc == 0)
+	if (hose->io_base_alloc == NULL)
 		return 0;
 
 	pr_debug("IO unmapping for PHB %s\n", hose->dn->full_name);
@@ -272,7 +272,7 @@ static void quirk_radeon_32bit_msi(struct pci_dev *dev)
 	struct pci_dn *pdn = pci_get_pdn(dev);
 
 	if (pdn)
-		pdn->force_32bit_msi = 1;
+		pdn->force_32bit_msi = true;
 }
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x68f2, quirk_radeon_32bit_msi);
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0xaa68, quirk_radeon_32bit_msi);
diff --git a/arch/powerpc/kernel/pci_dn.c b/arch/powerpc/kernel/pci_dn.c
index df038442548a..1f61fab59d9b 100644
--- a/arch/powerpc/kernel/pci_dn.c
+++ b/arch/powerpc/kernel/pci_dn.c
@@ -47,9 +47,8 @@ struct pci_dn *pci_get_pdn(struct pci_dev *pdev)
 void *update_dn_pci_info(struct device_node *dn, void *data)
 {
 	struct pci_controller *phb = data;
-	const int *type =
-		of_get_property(dn, "ibm,pci-config-space-type", NULL);
-	const u32 *regs;
+	const __be32 *type = of_get_property(dn, "ibm,pci-config-space-type", NULL);
+	const __be32 *regs;
 	struct pci_dn *pdn;
 
 	pdn = zalloc_maybe_bootmem(sizeof(*pdn), GFP_KERNEL);
@@ -63,12 +62,14 @@ void *update_dn_pci_info(struct device_node *dn, void *data)
 #endif
 	regs = of_get_property(dn, "reg", NULL);
 	if (regs) {
+		u32 addr = of_read_number(regs, 1);
+
 		/* First register entry is addr (00BBSS00)  */
-		pdn->busno = (regs[0] >> 16) & 0xff;
-		pdn->devfn = (regs[0] >> 8) & 0xff;
+		pdn->busno = (addr >> 16) & 0xff;
+		pdn->devfn = (addr >> 8) & 0xff;
 	}
 
-	pdn->pci_ext_config_space = (type && *type == 1);
+	pdn->pci_ext_config_space = (type && of_read_number(type, 1) == 1);
 	return NULL;
 }
 
@@ -98,12 +99,13 @@ void *traverse_pci_devices(struct device_node *start, traverse_func pre,
 
 	/* We started with a phb, iterate all childs */
 	for (dn = start->child; dn; dn = nextdn) {
-		const u32 *classp;
-		u32 class;
+		const __be32 *classp;
+		u32 class = 0;
 
 		nextdn = NULL;
 		classp = of_get_property(dn, "class-code", NULL);
-		class = classp ? *classp : 0;
+		if (classp)
+			class = of_read_number(classp, 1);
 
 		if (pre && ((ret = pre(dn, data)) != NULL))
 			return ret;
diff --git a/arch/powerpc/kernel/pci_of_scan.c b/arch/powerpc/kernel/pci_of_scan.c
index 15d9105323bf..4368ec6fdc8c 100644
--- a/arch/powerpc/kernel/pci_of_scan.c
+++ b/arch/powerpc/kernel/pci_of_scan.c
@@ -24,12 +24,12 @@
  */
 static u32 get_int_prop(struct device_node *np, const char *name, u32 def)
 {
-	const u32 *prop;
+	const __be32 *prop;
 	int len;
 
 	prop = of_get_property(np, name, &len);
 	if (prop && len >= 4)
-		return *prop;
+		return of_read_number(prop, 1);
 	return def;
 }
 
@@ -77,7 +77,7 @@ static void of_pci_parse_addrs(struct device_node *node, struct pci_dev *dev)
 	unsigned int flags;
 	struct pci_bus_region region;
 	struct resource *res;
-	const u32 *addrs;
+	const __be32 *addrs;
 	u32 i;
 	int proplen;
 
@@ -86,14 +86,14 @@ static void of_pci_parse_addrs(struct device_node *node, struct pci_dev *dev)
 		return;
 	pr_debug("    parse addresses (%d bytes) @ %p\n", proplen, addrs);
 	for (; proplen >= 20; proplen -= 20, addrs += 5) {
-		flags = pci_parse_of_flags(addrs[0], 0);
+		flags = pci_parse_of_flags(of_read_number(addrs, 1), 0);
 		if (!flags)
 			continue;
 		base = of_read_number(&addrs[1], 2);
 		size = of_read_number(&addrs[3], 2);
 		if (!size)
 			continue;
-		i = addrs[0] & 0xff;
+		i = of_read_number(addrs, 1) & 0xff;
 		pr_debug("  base: %llx, size: %llx, i: %x\n",
 			 (unsigned long long)base,
 			 (unsigned long long)size, i);
@@ -207,7 +207,7 @@ void of_scan_pci_bridge(struct pci_dev *dev)
 {
 	struct device_node *node = dev->dev.of_node;
 	struct pci_bus *bus;
-	const u32 *busrange, *ranges;
+	const __be32 *busrange, *ranges;
 	int len, i, mode;
 	struct pci_bus_region region;
 	struct resource *res;
@@ -230,9 +230,11 @@ void of_scan_pci_bridge(struct pci_dev *dev)
 		return;
 	}
 
-	bus = pci_find_bus(pci_domain_nr(dev->bus), busrange[0]);
+	bus = pci_find_bus(pci_domain_nr(dev->bus),
+			   of_read_number(busrange, 1));
 	if (!bus) {
-		bus = pci_add_new_bus(dev->bus, dev, busrange[0]);
+		bus = pci_add_new_bus(dev->bus, dev,
+				      of_read_number(busrange, 1));
 		if (!bus) {
 			printk(KERN_ERR "Failed to create pci bus for %s\n",
 			       node->full_name);
@@ -241,7 +243,8 @@ void of_scan_pci_bridge(struct pci_dev *dev)
 	}
 
 	bus->primary = dev->bus->number;
-	pci_bus_insert_busn_res(bus, busrange[0], busrange[1]);
+	pci_bus_insert_busn_res(bus, of_read_number(busrange, 1),
+				of_read_number(busrange+1, 1));
 	bus->bridge_ctl = 0;
 
 	/* parse ranges property */
@@ -254,7 +257,7 @@ void of_scan_pci_bridge(struct pci_dev *dev)
 	}
 	i = 1;
 	for (; len >= 32; len -= 32, ranges += 8) {
-		flags = pci_parse_of_flags(ranges[0], 1);
+		flags = pci_parse_of_flags(of_read_number(ranges, 1), 1);
 		size = of_read_number(&ranges[6], 2);
 		if (flags == 0 || size == 0)
 			continue;
diff --git a/arch/powerpc/kernel/ppc_ksyms.c b/arch/powerpc/kernel/ppc_ksyms.c
index c29666586998..21646dbe1bb3 100644
--- a/arch/powerpc/kernel/ppc_ksyms.c
+++ b/arch/powerpc/kernel/ppc_ksyms.c
@@ -96,7 +96,9 @@ EXPORT_SYMBOL(pci_dram_offset);
 
 EXPORT_SYMBOL(start_thread);
 
+#ifdef CONFIG_PPC_FPU
 EXPORT_SYMBOL(giveup_fpu);
+#endif
 #ifdef CONFIG_ALTIVEC
 EXPORT_SYMBOL(giveup_altivec);
 #endif /* CONFIG_ALTIVEC */
@@ -111,7 +113,6 @@ EXPORT_SYMBOL(giveup_spe);
 #ifndef CONFIG_PPC64
 EXPORT_SYMBOL(flush_instruction_cache);
 #endif
-EXPORT_SYMBOL(__flush_icache_range);
 EXPORT_SYMBOL(flush_dcache_range);
 
 #ifdef CONFIG_SMP
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 8083be20fe5e..96d2fdf3aa9e 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -74,6 +74,7 @@ struct task_struct *last_task_used_vsx = NULL;
 struct task_struct *last_task_used_spe = NULL;
 #endif
 
+#ifdef CONFIG_PPC_FPU
 /*
  * Make sure the floating-point register state in the
  * the thread_struct is up to date for task tsk.
@@ -107,6 +108,7 @@ void flush_fp_to_thread(struct task_struct *tsk)
 	}
 }
 EXPORT_SYMBOL_GPL(flush_fp_to_thread);
+#endif
 
 void enable_kernel_fp(void)
 {
@@ -998,9 +1000,10 @@ int copy_thread(unsigned long clone_flags, unsigned long usp,
 	kregs = (struct pt_regs *) sp;
 	sp -= STACK_FRAME_OVERHEAD;
 	p->thread.ksp = sp;
+#ifdef CONFIG_PPC32
 	p->thread.ksp_limit = (unsigned long)task_stack_page(p) +
 				_ALIGN_UP(sizeof(struct thread_info), 16);
-
+#endif
 #ifdef CONFIG_HAVE_HW_BREAKPOINT
 	p->thread.ptrace_bps[0] = NULL;
 #endif
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index eb23ac92abb9..b7634ce41dbc 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -215,16 +215,16 @@ static void __init check_cpu_pa_features(unsigned long node)
 #ifdef CONFIG_PPC_STD_MMU_64
 static void __init check_cpu_slb_size(unsigned long node)
 {
-	u32 *slb_size_ptr;
+	__be32 *slb_size_ptr;
 
 	slb_size_ptr = of_get_flat_dt_prop(node, "slb-size", NULL);
 	if (slb_size_ptr != NULL) {
-		mmu_slb_size = *slb_size_ptr;
+		mmu_slb_size = be32_to_cpup(slb_size_ptr);
 		return;
 	}
 	slb_size_ptr = of_get_flat_dt_prop(node, "ibm,slb-size", NULL);
 	if (slb_size_ptr != NULL) {
-		mmu_slb_size = *slb_size_ptr;
+		mmu_slb_size = be32_to_cpup(slb_size_ptr);
 	}
 }
 #else
@@ -279,11 +279,11 @@ static void __init check_cpu_feature_properties(unsigned long node)
 {
 	unsigned long i;
 	struct feature_property *fp = feature_properties;
-	const u32 *prop;
+	const __be32 *prop;
 
 	for (i = 0; i < ARRAY_SIZE(feature_properties); ++i, ++fp) {
 		prop = of_get_flat_dt_prop(node, fp->name, NULL);
-		if (prop && *prop >= fp->min_value) {
+		if (prop && be32_to_cpup(prop) >= fp->min_value) {
 			cur_cpu_spec->cpu_features |= fp->cpu_feature;
 			cur_cpu_spec->cpu_user_features |= fp->cpu_user_ftr;
 		}
@@ -295,8 +295,8 @@ static int __init early_init_dt_scan_cpus(unsigned long node,
 					  void *data)
 {
 	char *type = of_get_flat_dt_prop(node, "device_type", NULL);
-	const u32 *prop;
-	const u32 *intserv;
+	const __be32 *prop;
+	const __be32 *intserv;
 	int i, nthreads;
 	unsigned long len;
 	int found = -1;
@@ -324,8 +324,9 @@ static int __init early_init_dt_scan_cpus(unsigned long node,
 		 * version 2 of the kexec param format adds the phys cpuid of
 		 * booted proc.
 		 */
-		if (initial_boot_params->version >= 2) {
-			if (intserv[i] == initial_boot_params->boot_cpuid_phys) {
+		if (be32_to_cpu(initial_boot_params->version) >= 2) {
+			if (be32_to_cpu(intserv[i]) ==
+			    be32_to_cpu(initial_boot_params->boot_cpuid_phys)) {
 				found = boot_cpu_count;
 				found_thread = i;
 			}
@@ -347,9 +348,10 @@ static int __init early_init_dt_scan_cpus(unsigned long node,
 
 	if (found >= 0) {
 		DBG("boot cpu: logical %d physical %d\n", found,
-			intserv[found_thread]);
+			be32_to_cpu(intserv[found_thread]));
 		boot_cpuid = found;
-		set_hard_smp_processor_id(found, intserv[found_thread]);
+		set_hard_smp_processor_id(found,
+			be32_to_cpu(intserv[found_thread]));
 
 		/*
 		 * PAPR defines "logical" PVR values for cpus that
@@ -366,8 +368,8 @@ static int __init early_init_dt_scan_cpus(unsigned long node,
 		 * it uses 0x0f000001.
 		 */
 		prop = of_get_flat_dt_prop(node, "cpu-version", NULL);
-		if (prop && (*prop & 0xff000000) == 0x0f000000)
-			identify_cpu(0, *prop);
+		if (prop && (be32_to_cpup(prop) & 0xff000000) == 0x0f000000)
+			identify_cpu(0, be32_to_cpup(prop));
 
 		identical_pvr_fixup(node);
 	}
@@ -389,7 +391,7 @@ static int __init early_init_dt_scan_cpus(unsigned long node,
 int __init early_init_dt_scan_chosen_ppc(unsigned long node, const char *uname,
 					 int depth, void *data)
 {
-	unsigned long *lprop;
+	unsigned long *lprop; /* All these set by kernel, so no need to convert endian */
 
 	/* Use common scan routine to determine if this is the chosen node */
 	if (early_init_dt_scan_chosen(node, uname, depth, data) == 0)
@@ -454,7 +456,7 @@ static int __init early_init_dt_scan_drconf_memory(unsigned long node)
 	if (dm == NULL || l < sizeof(__be32))
 		return 0;
 
-	n = *dm++;	/* number of entries */
+	n = of_read_number(dm++, 1);	/* number of entries */
 	if (l < (n * (dt_root_addr_cells + 4) + 1) * sizeof(__be32))
 		return 0;
 
@@ -466,7 +468,7 @@ static int __init early_init_dt_scan_drconf_memory(unsigned long node)
 
 	for (; n != 0; --n) {
 		base = dt_mem_next_cell(dt_root_addr_cells, &dm);
-		flags = dm[3];
+		flags = of_read_number(&dm[3], 1);
 		/* skip DRC index, pad, assoc. list index, flags */
 		dm += 4;
 		/* skip this block if the reserved bit is set in flags (0x80)
@@ -544,14 +546,8 @@ void __init early_init_dt_add_memory_arch(u64 base, u64 size)
 	memblock_add(base, size);
 }
 
-void * __init early_init_dt_alloc_memory_arch(u64 size, u64 align)
-{
-	return __va(memblock_alloc(size, align));
-}
-
 #ifdef CONFIG_BLK_DEV_INITRD
-void __init early_init_dt_setup_initrd_arch(unsigned long start,
-		unsigned long end)
+void __init early_init_dt_setup_initrd_arch(u64 start, u64 end)
 {
 	initrd_start = (unsigned long)__va(start);
 	initrd_end = (unsigned long)__va(end);
@@ -591,16 +587,16 @@ static void __init early_reserve_mem_dt(void)
 static void __init early_reserve_mem(void)
 {
 	u64 base, size;
-	u64 *reserve_map;
+	__be64 *reserve_map;
 	unsigned long self_base;
 	unsigned long self_size;
 
-	reserve_map = (u64 *)(((unsigned long)initial_boot_params) +
-					initial_boot_params->off_mem_rsvmap);
+	reserve_map = (__be64 *)(((unsigned long)initial_boot_params) +
+			be32_to_cpu(initial_boot_params->off_mem_rsvmap));
 
 	/* before we do anything, lets reserve the dt blob */
 	self_base = __pa((unsigned long)initial_boot_params);
-	self_size = initial_boot_params->totalsize;
+	self_size = be32_to_cpu(initial_boot_params->totalsize);
 	memblock_reserve(self_base, self_size);
 
 	/* Look for the new "reserved-regions" property in the DT */
@@ -620,15 +616,15 @@ static void __init early_reserve_mem(void)
 	 * Handle the case where we might be booting from an old kexec
 	 * image that setup the mem_rsvmap as pairs of 32-bit values
 	 */
-	if (*reserve_map > 0xffffffffull) {
+	if (be64_to_cpup(reserve_map) > 0xffffffffull) {
 		u32 base_32, size_32;
-		u32 *reserve_map_32 = (u32 *)reserve_map;
+		__be32 *reserve_map_32 = (__be32 *)reserve_map;
 
 		DBG("Found old 32-bit reserve map\n");
 
 		while (1) {
-			base_32 = *(reserve_map_32++);
-			size_32 = *(reserve_map_32++);
+			base_32 = be32_to_cpup(reserve_map_32++);
+			size_32 = be32_to_cpup(reserve_map_32++);
 			if (size_32 == 0)
 				break;
 			/* skip if the reservation is for the blob */
@@ -644,8 +640,8 @@ static void __init early_reserve_mem(void)
 
 	/* Handle the reserve map in the fdt blob if it exists */
 	while (1) {
-		base = *(reserve_map++);
-		size = *(reserve_map++);
+		base = be64_to_cpup(reserve_map++);
+		size = be64_to_cpup(reserve_map++);
 		if (size == 0)
 			break;
 		DBG("reserving: %llx -> %llx\n", base, size);
@@ -795,6 +791,32 @@ struct device_node *of_find_next_cache_node(struct device_node *np)
 	return NULL;
 }
 
+/**
+ * of_get_ibm_chip_id - Returns the IBM "chip-id" of a device
+ * @np: device node of the device
+ *
+ * This looks for a property "ibm,chip-id" in the node or any
+ * of its parents and returns its content, or -1 if it cannot
+ * be found.
+ */
+int of_get_ibm_chip_id(struct device_node *np)
+{
+	of_node_get(np);
+	while(np) {
+		struct device_node *old = np;
+		const __be32 *prop;
+
+		prop = of_get_property(np, "ibm,chip-id", NULL);
+		if (prop) {
+			of_node_put(np);
+			return be32_to_cpup(prop);
+		}
+		np = of_get_parent(np);
+		of_node_put(old);
+	}
+	return -1;
+}
+
 #ifdef CONFIG_PPC_PSERIES
 /*
  * Fix up the uninitialized fields in a new device node:
@@ -865,49 +887,10 @@ static int __init prom_reconfig_setup(void)
 __initcall(prom_reconfig_setup);
 #endif
 
-/* Find the device node for a given logical cpu number, also returns the cpu
- * local thread number (index in ibm,interrupt-server#s) if relevant and
- * asked for (non NULL)
- */
-struct device_node *of_get_cpu_node(int cpu, unsigned int *thread)
+bool arch_match_cpu_phys_id(int cpu, u64 phys_id)
 {
-	int hardid;
-	struct device_node *np;
-
-	hardid = get_hard_smp_processor_id(cpu);
-
-	for_each_node_by_type(np, "cpu") {
-		const u32 *intserv;
-		unsigned int plen, t;
-
-		/* Check for ibm,ppc-interrupt-server#s. If it doesn't exist
-		 * fallback to "reg" property and assume no threads
-		 */
-		intserv = of_get_property(np, "ibm,ppc-interrupt-server#s",
-				&plen);
-		if (intserv == NULL) {
-			const u32 *reg = of_get_property(np, "reg", NULL);
-			if (reg == NULL)
-				continue;
-			if (*reg == hardid) {
-				if (thread)
-					*thread = 0;
-				return np;
-			}
-		} else {
-			plen /= sizeof(u32);
-			for (t = 0; t < plen; t++) {
-				if (hardid == intserv[t]) {
-					if (thread)
-						*thread = t;
-					return np;
-				}
-			}
-		}
-	}
-	return NULL;
+	return (int)phys_id == get_hard_smp_processor_id(cpu);
 }
-EXPORT_SYMBOL(of_get_cpu_node);
 
 #if defined(CONFIG_DEBUG_FS) && defined(DEBUG)
 static struct debugfs_blob_wrapper flat_dt_blob;
@@ -917,7 +900,7 @@ static int __init export_flat_device_tree(void)
 	struct dentry *d;
 
 	flat_dt_blob.data = initial_boot_params;
-	flat_dt_blob.size = initial_boot_params->totalsize;
+	flat_dt_blob.size = be32_to_cpu(initial_boot_params->totalsize);
 
 	d = debugfs_create_blob("flat-device-tree", S_IFREG | S_IRUSR,
 				powerpc_debugfs_root, &flat_dt_blob);
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index 607902424e73..5fe2842e8bab 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -107,10 +107,10 @@ int of_workarounds;
 typedef u32 prom_arg_t;
 
 struct prom_args {
-        u32 service;
-        u32 nargs;
-        u32 nret;
-        prom_arg_t args[10];
+        __be32 service;
+        __be32 nargs;
+        __be32 nret;
+        __be32 args[10];
 };
 
 struct prom_t {
@@ -123,11 +123,11 @@ struct prom_t {
 };
 
 struct mem_map_entry {
-	u64	base;
-	u64	size;
+	__be64	base;
+	__be64	size;
 };
 
-typedef u32 cell_t;
+typedef __be32 cell_t;
 
 extern void __start(unsigned long r3, unsigned long r4, unsigned long r5,
 		    unsigned long r6, unsigned long r7, unsigned long r8,
@@ -196,6 +196,8 @@ static int __initdata mem_reserve_cnt;
 
 static cell_t __initdata regbuf[1024];
 
+static bool rtas_has_query_cpu_stopped;
+
 
 /*
  * Error results ... some OF calls will return "-1" on error, some
@@ -219,13 +221,13 @@ static int __init call_prom(const char *service, int nargs, int nret, ...)
 	struct prom_args args;
 	va_list list;
 
-	args.service = ADDR(service);
-	args.nargs = nargs;
-	args.nret = nret;
+	args.service = cpu_to_be32(ADDR(service));
+	args.nargs = cpu_to_be32(nargs);
+	args.nret = cpu_to_be32(nret);
 
 	va_start(list, nret);
 	for (i = 0; i < nargs; i++)
-		args.args[i] = va_arg(list, prom_arg_t);
+		args.args[i] = cpu_to_be32(va_arg(list, prom_arg_t));
 	va_end(list);
 
 	for (i = 0; i < nret; i++)
@@ -234,7 +236,7 @@ static int __init call_prom(const char *service, int nargs, int nret, ...)
 	if (enter_prom(&args, prom_entry) < 0)
 		return PROM_ERROR;
 
-	return (nret > 0) ? args.args[nargs] : 0;
+	return (nret > 0) ? be32_to_cpu(args.args[nargs]) : 0;
 }
 
 static int __init call_prom_ret(const char *service, int nargs, int nret,
@@ -244,13 +246,13 @@ static int __init call_prom_ret(const char *service, int nargs, int nret,
 	struct prom_args args;
 	va_list list;
 
-	args.service = ADDR(service);
-	args.nargs = nargs;
-	args.nret = nret;
+	args.service = cpu_to_be32(ADDR(service));
+	args.nargs = cpu_to_be32(nargs);
+	args.nret = cpu_to_be32(nret);
 
 	va_start(list, rets);
 	for (i = 0; i < nargs; i++)
-		args.args[i] = va_arg(list, prom_arg_t);
+		args.args[i] = cpu_to_be32(va_arg(list, prom_arg_t));
 	va_end(list);
 
 	for (i = 0; i < nret; i++)
@@ -261,9 +263,9 @@ static int __init call_prom_ret(const char *service, int nargs, int nret,
 
 	if (rets != NULL)
 		for (i = 1; i < nret; ++i)
-			rets[i-1] = args.args[nargs+i];
+			rets[i-1] = be32_to_cpu(args.args[nargs+i]);
 
-	return (nret > 0) ? args.args[nargs] : 0;
+	return (nret > 0) ? be32_to_cpu(args.args[nargs]) : 0;
 }
 
 
@@ -527,7 +529,7 @@ static int __init prom_setprop(phandle node, const char *nodename,
 #define islower(c)	('a' <= (c) && (c) <= 'z')
 #define toupper(c)	(islower(c) ? ((c) - 'a' + 'A') : (c))
 
-unsigned long prom_strtoul(const char *cp, const char **endp)
+static unsigned long prom_strtoul(const char *cp, const char **endp)
 {
 	unsigned long result = 0, base = 10, value;
 
@@ -552,7 +554,7 @@ unsigned long prom_strtoul(const char *cp, const char **endp)
 	return result;
 }
 
-unsigned long prom_memparse(const char *ptr, const char **retptr)
+static unsigned long prom_memparse(const char *ptr, const char **retptr)
 {
 	unsigned long ret = prom_strtoul(ptr, retptr);
 	int shift = 0;
@@ -724,7 +726,8 @@ unsigned char ibm_architecture_vec[] = {
 
 };
 
-/* Old method - ELF header with PT_NOTE sections */
+/* Old method - ELF header with PT_NOTE sections only works on BE */
+#ifdef __BIG_ENDIAN__
 static struct fake_elf {
 	Elf32_Ehdr	elfhdr;
 	Elf32_Phdr	phdr[2];
@@ -810,6 +813,7 @@ static struct fake_elf {
 		}
 	}
 };
+#endif /* __BIG_ENDIAN__ */
 
 static int __init prom_count_smt_threads(void)
 {
@@ -852,9 +856,9 @@ static int __init prom_count_smt_threads(void)
 
 static void __init prom_send_capabilities(void)
 {
-	ihandle elfloader, root;
+	ihandle root;
 	prom_arg_t ret;
-	u32 *cores;
+	__be32 *cores;
 
 	root = call_prom("open", 1, 1, ADDR("/"));
 	if (root != 0) {
@@ -864,15 +868,15 @@ static void __init prom_send_capabilities(void)
 		 * (we assume this is the same for all cores) and use it to
 		 * divide NR_CPUS.
 		 */
-		cores = (u32 *)&ibm_architecture_vec[IBM_ARCH_VEC_NRCORES_OFFSET];
-		if (*cores != NR_CPUS) {
+		cores = (__be32 *)&ibm_architecture_vec[IBM_ARCH_VEC_NRCORES_OFFSET];
+		if (be32_to_cpup(cores) != NR_CPUS) {
 			prom_printf("WARNING ! "
 				    "ibm_architecture_vec structure inconsistent: %lu!\n",
-				    *cores);
+				    be32_to_cpup(cores));
 		} else {
-			*cores = DIV_ROUND_UP(NR_CPUS, prom_count_smt_threads());
+			*cores = cpu_to_be32(DIV_ROUND_UP(NR_CPUS, prom_count_smt_threads()));
 			prom_printf("Max number of cores passed to firmware: %lu (NR_CPUS = %lu)\n",
-				    *cores, NR_CPUS);
+				    be32_to_cpup(cores), NR_CPUS);
 		}
 
 		/* try calling the ibm,client-architecture-support method */
@@ -893,17 +897,24 @@ static void __init prom_send_capabilities(void)
 		prom_printf(" not implemented\n");
 	}
 
-	/* no ibm,client-architecture-support call, try the old way */
-	elfloader = call_prom("open", 1, 1, ADDR("/packages/elf-loader"));
-	if (elfloader == 0) {
-		prom_printf("couldn't open /packages/elf-loader\n");
-		return;
+#ifdef __BIG_ENDIAN__
+	{
+		ihandle elfloader;
+
+		/* no ibm,client-architecture-support call, try the old way */
+		elfloader = call_prom("open", 1, 1,
+				      ADDR("/packages/elf-loader"));
+		if (elfloader == 0) {
+			prom_printf("couldn't open /packages/elf-loader\n");
+			return;
+		}
+		call_prom("call-method", 3, 1, ADDR("process-elf-header"),
+			  elfloader, ADDR(&fake_elf));
+		call_prom("close", 1, 0, elfloader);
 	}
-	call_prom("call-method", 3, 1, ADDR("process-elf-header"),
-			elfloader, ADDR(&fake_elf));
-	call_prom("close", 1, 0, elfloader);
+#endif /* __BIG_ENDIAN__ */
 }
-#endif
+#endif /* #if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV) */
 
 /*
  * Memory allocation strategy... our layout is normally:
@@ -1050,11 +1061,11 @@ static unsigned long __init prom_next_cell(int s, cell_t **cellp)
 		p++;
 		s--;
 	}
-	r = *p++;
+	r = be32_to_cpu(*p++);
 #ifdef CONFIG_PPC64
 	if (s > 1) {
 		r <<= 32;
-		r |= *(p++);
+		r |= be32_to_cpu(*(p++));
 	}
 #endif
 	*cellp = p;
@@ -1087,8 +1098,8 @@ static void __init reserve_mem(u64 base, u64 size)
 
 	if (cnt >= (MEM_RESERVE_MAP_SIZE - 1))
 		prom_panic("Memory reserve map exhausted !\n");
-	mem_reserve_map[cnt].base = base;
-	mem_reserve_map[cnt].size = size;
+	mem_reserve_map[cnt].base = cpu_to_be64(base);
+	mem_reserve_map[cnt].size = cpu_to_be64(size);
 	mem_reserve_cnt = cnt + 1;
 }
 
@@ -1102,6 +1113,7 @@ static void __init prom_init_mem(void)
 	char *path, type[64];
 	unsigned int plen;
 	cell_t *p, *endp;
+	__be32 val;
 	u32 rac, rsc;
 
 	/*
@@ -1109,12 +1121,14 @@ static void __init prom_init_mem(void)
 	 * 1) top of RMO (first node)
 	 * 2) top of memory
 	 */
-	rac = 2;
-	prom_getprop(prom.root, "#address-cells", &rac, sizeof(rac));
-	rsc = 1;
-	prom_getprop(prom.root, "#size-cells", &rsc, sizeof(rsc));
-	prom_debug("root_addr_cells: %x\n", (unsigned long) rac);
-	prom_debug("root_size_cells: %x\n", (unsigned long) rsc);
+	val = cpu_to_be32(2);
+	prom_getprop(prom.root, "#address-cells", &val, sizeof(val));
+	rac = be32_to_cpu(val);
+	val = cpu_to_be32(1);
+	prom_getprop(prom.root, "#size-cells", &val, sizeof(rsc));
+	rsc = be32_to_cpu(val);
+	prom_debug("root_addr_cells: %x\n", rac);
+	prom_debug("root_size_cells: %x\n", rsc);
 
 	prom_debug("scanning memory:\n");
 	path = prom_scratch;
@@ -1222,25 +1236,23 @@ static void __init prom_init_mem(void)
 
 static void __init prom_close_stdin(void)
 {
-	ihandle val;
+	__be32 val;
+	ihandle stdin;
 
-	if (prom_getprop(prom.chosen, "stdin", &val, sizeof(val)) > 0)
-		call_prom("close", 1, 0, val);
+	if (prom_getprop(prom.chosen, "stdin", &val, sizeof(val)) > 0) {
+		stdin = be32_to_cpu(val);
+		call_prom("close", 1, 0, stdin);
+	}
 }
 
 #ifdef CONFIG_PPC_POWERNV
 
-static u64 __initdata prom_opal_size;
-static u64 __initdata prom_opal_align;
-static int __initdata prom_rtas_start_cpu;
-static u64 __initdata prom_rtas_data;
-static u64 __initdata prom_rtas_entry;
-
 #ifdef CONFIG_PPC_EARLY_DEBUG_OPAL
 static u64 __initdata prom_opal_base;
 static u64 __initdata prom_opal_entry;
 #endif
 
+#ifdef __BIG_ENDIAN__
 /* XXX Don't change this structure without updating opal-takeover.S */
 static struct opal_secondary_data {
 	s64				ack;	/*  0 */
@@ -1248,6 +1260,12 @@ static struct opal_secondary_data {
 	struct opal_takeover_args	args;	/* 16 */
 } opal_secondary_data;
 
+static u64 __initdata prom_opal_align;
+static u64 __initdata prom_opal_size;
+static int __initdata prom_rtas_start_cpu;
+static u64 __initdata prom_rtas_data;
+static u64 __initdata prom_rtas_entry;
+
 extern char opal_secondary_entry;
 
 static void __init prom_query_opal(void)
@@ -1265,6 +1283,7 @@ static void __init prom_query_opal(void)
 	}
 
 	prom_printf("Querying for OPAL presence... ");
+
 	rc = opal_query_takeover(&prom_opal_size,
 				 &prom_opal_align);
 	prom_debug("(rc = %ld) ", rc);
@@ -1280,7 +1299,8 @@ static void __init prom_query_opal(void)
 		prom_opal_align = 0x10000;
 }
 
-static int prom_rtas_call(int token, int nargs, int nret, int *outputs, ...)
+static int __init prom_rtas_call(int token, int nargs, int nret,
+				 int *outputs, ...)
 {
 	struct rtas_args rtas_args;
 	va_list list;
@@ -1425,6 +1445,7 @@ static void __init prom_opal_takeover(void)
 	for (;;)
 		opal_do_takeover(args);
 }
+#endif /* __BIG_ENDIAN__ */
 
 /*
  * Allocate room for and instantiate OPAL
@@ -1435,6 +1456,7 @@ static void __init prom_instantiate_opal(void)
 	ihandle opal_inst;
 	u64 base, entry;
 	u64 size = 0, align = 0x10000;
+	__be64 val64;
 	u32 rets[2];
 
 	prom_debug("prom_instantiate_opal: start...\n");
@@ -1444,11 +1466,14 @@ static void __init prom_instantiate_opal(void)
 	if (!PHANDLE_VALID(opal_node))
 		return;
 
-	prom_getprop(opal_node, "opal-runtime-size", &size, sizeof(size));
+	val64 = 0;
+	prom_getprop(opal_node, "opal-runtime-size", &val64, sizeof(val64));
+	size = be64_to_cpu(val64);
 	if (size == 0)
 		return;
-	prom_getprop(opal_node, "opal-runtime-alignment", &align,
-		     sizeof(align));
+	val64 = 0;
+	prom_getprop(opal_node, "opal-runtime-alignment", &val64,sizeof(val64));
+	align = be64_to_cpu(val64);
 
 	base = alloc_down(size, align, 0);
 	if (base == 0) {
@@ -1505,6 +1530,7 @@ static void __init prom_instantiate_rtas(void)
 	phandle rtas_node;
 	ihandle rtas_inst;
 	u32 base, entry = 0;
+	__be32 val;
 	u32 size = 0;
 
 	prom_debug("prom_instantiate_rtas: start...\n");
@@ -1514,7 +1540,9 @@ static void __init prom_instantiate_rtas(void)
 	if (!PHANDLE_VALID(rtas_node))
 		return;
 
-	prom_getprop(rtas_node, "rtas-size", &size, sizeof(size));
+	val = 0;
+	prom_getprop(rtas_node, "rtas-size", &val, sizeof(size));
+	size = be32_to_cpu(val);
 	if (size == 0)
 		return;
 
@@ -1541,12 +1569,19 @@ static void __init prom_instantiate_rtas(void)
 
 	reserve_mem(base, size);
 
+	val = cpu_to_be32(base);
 	prom_setprop(rtas_node, "/rtas", "linux,rtas-base",
-		     &base, sizeof(base));
+		     &val, sizeof(val));
+	val = cpu_to_be32(entry);
 	prom_setprop(rtas_node, "/rtas", "linux,rtas-entry",
-		     &entry, sizeof(entry));
+		     &val, sizeof(val));
 
-#ifdef CONFIG_PPC_POWERNV
+	/* Check if it supports "query-cpu-stopped-state" */
+	if (prom_getprop(rtas_node, "query-cpu-stopped-state",
+			 &val, sizeof(val)) != PROM_ERROR)
+		rtas_has_query_cpu_stopped = true;
+
+#if defined(CONFIG_PPC_POWERNV) && defined(__BIG_ENDIAN__)
 	/* PowerVN takeover hack */
 	prom_rtas_data = base;
 	prom_rtas_entry = entry;
@@ -1620,6 +1655,7 @@ static void __init prom_instantiate_sml(void)
 /*
  * Allocate room for and initialize TCE tables
  */
+#ifdef __BIG_ENDIAN__
 static void __init prom_initialize_tce_table(void)
 {
 	phandle node;
@@ -1748,7 +1784,8 @@ static void __init prom_initialize_tce_table(void)
 	/* Flag the first invalid entry */
 	prom_debug("ending prom_initialize_tce_table\n");
 }
-#endif
+#endif /* __BIG_ENDIAN__ */
+#endif /* CONFIG_PPC64 */
 
 /*
  * With CHRP SMP we need to use the OF to start the other processors.
@@ -1777,7 +1814,6 @@ static void __init prom_initialize_tce_table(void)
 static void __init prom_hold_cpus(void)
 {
 	unsigned long i;
-	unsigned int reg;
 	phandle node;
 	char type[64];
 	unsigned long *spinloop
@@ -1786,6 +1822,18 @@ static void __init prom_hold_cpus(void)
 		= (void *) LOW_ADDR(__secondary_hold_acknowledge);
 	unsigned long secondary_hold = LOW_ADDR(__secondary_hold);
 
+	/*
+	 * On pseries, if RTAS supports "query-cpu-stopped-state",
+	 * we skip this stage, the CPUs will be started by the
+	 * kernel using RTAS.
+	 */
+	if ((of_platform == PLATFORM_PSERIES ||
+	     of_platform == PLATFORM_PSERIES_LPAR) &&
+	    rtas_has_query_cpu_stopped) {
+		prom_printf("prom_hold_cpus: skipped\n");
+		return;
+	}
+
 	prom_debug("prom_hold_cpus: start...\n");
 	prom_debug("    1) spinloop       = 0x%x\n", (unsigned long)spinloop);
 	prom_debug("    1) *spinloop      = 0x%x\n", *spinloop);
@@ -1803,6 +1851,9 @@ static void __init prom_hold_cpus(void)
 
 	/* look for cpus */
 	for (node = 0; prom_next_node(&node); ) {
+		unsigned int cpu_no;
+		__be32 reg;
+
 		type[0] = 0;
 		prom_getprop(node, "device_type", type, sizeof(type));
 		if (strcmp(type, "cpu") != 0)
@@ -1813,10 +1864,11 @@ static void __init prom_hold_cpus(void)
 			if (strcmp(type, "okay") != 0)
 				continue;
 
-		reg = -1;
+		reg = cpu_to_be32(-1); /* make sparse happy */
 		prom_getprop(node, "reg", &reg, sizeof(reg));
+		cpu_no = be32_to_cpu(reg);
 
-		prom_debug("cpu hw idx   = %lu\n", reg);
+		prom_debug("cpu hw idx   = %lu\n", cpu_no);
 
 		/* Init the acknowledge var which will be reset by
 		 * the secondary cpu when it awakens from its OF
@@ -1824,24 +1876,24 @@ static void __init prom_hold_cpus(void)
 		 */
 		*acknowledge = (unsigned long)-1;
 
-		if (reg != prom.cpu) {
+		if (cpu_no != prom.cpu) {
 			/* Primary Thread of non-boot cpu or any thread */
-			prom_printf("starting cpu hw idx %lu... ", reg);
+			prom_printf("starting cpu hw idx %lu... ", cpu_no);
 			call_prom("start-cpu", 3, 0, node,
-				  secondary_hold, reg);
+				  secondary_hold, cpu_no);
 
 			for (i = 0; (i < 100000000) && 
 			     (*acknowledge == ((unsigned long)-1)); i++ )
 				mb();
 
-			if (*acknowledge == reg)
+			if (*acknowledge == cpu_no)
 				prom_printf("done\n");
 			else
 				prom_printf("failed: %x\n", *acknowledge);
 		}
 #ifdef CONFIG_SMP
 		else
-			prom_printf("boot cpu hw idx %lu\n", reg);
+			prom_printf("boot cpu hw idx %lu\n", cpu_no);
 #endif /* CONFIG_SMP */
 	}
 
@@ -1895,6 +1947,7 @@ static void __init prom_find_mmu(void)
 	prom.memory = call_prom("open", 1, 1, ADDR("/memory"));
 	prom_getprop(prom.chosen, "mmu", &prom.mmumap,
 		     sizeof(prom.mmumap));
+	prom.mmumap = be32_to_cpu(prom.mmumap);
 	if (!IHANDLE_VALID(prom.memory) || !IHANDLE_VALID(prom.mmumap))
 		of_workarounds &= ~OF_WA_CLAIM;		/* hmmm */
 }
@@ -1906,17 +1959,19 @@ static void __init prom_init_stdout(void)
 {
 	char *path = of_stdout_device;
 	char type[16];
-	u32 val;
+	phandle stdout_node;
+	__be32 val;
 
 	if (prom_getprop(prom.chosen, "stdout", &val, sizeof(val)) <= 0)
 		prom_panic("cannot find stdout");
 
-	prom.stdout = val;
+	prom.stdout = be32_to_cpu(val);
 
 	/* Get the full OF pathname of the stdout device */
 	memset(path, 0, 256);
 	call_prom("instance-to-path", 3, 1, prom.stdout, path, 255);
-	val = call_prom("instance-to-package", 1, 1, prom.stdout);
+	stdout_node = call_prom("instance-to-package", 1, 1, prom.stdout);
+	val = cpu_to_be32(stdout_node);
 	prom_setprop(prom.chosen, "/chosen", "linux,stdout-package",
 		     &val, sizeof(val));
 	prom_printf("OF stdout device is: %s\n", of_stdout_device);
@@ -1925,9 +1980,9 @@ static void __init prom_init_stdout(void)
 
 	/* If it's a display, note it */
 	memset(type, 0, sizeof(type));
-	prom_getprop(val, "device_type", type, sizeof(type));
+	prom_getprop(stdout_node, "device_type", type, sizeof(type));
 	if (strcmp(type, "display") == 0)
-		prom_setprop(val, path, "linux,boot-display", NULL, 0);
+		prom_setprop(stdout_node, path, "linux,boot-display", NULL, 0);
 }
 
 static int __init prom_find_machine_type(void)
@@ -2082,6 +2137,22 @@ static void __init prom_check_displays(void)
 					   clut[2]) != 0)
 				break;
 #endif /* CONFIG_LOGO_LINUX_CLUT224 */
+
+#ifdef CONFIG_PPC_EARLY_DEBUG_BOOTX
+		if (prom_getprop(node, "linux,boot-display", NULL, 0) !=
+		    PROM_ERROR) {
+			u32 width, height, pitch, addr;
+
+			prom_printf("Setting btext !\n");
+			prom_getprop(node, "width", &width, 4);
+			prom_getprop(node, "height", &height, 4);
+			prom_getprop(node, "linebytes", &pitch, 4);
+			prom_getprop(node, "address", &addr, 4);
+			prom_printf("W=%d H=%d LB=%d addr=0x%x\n",
+				    width, height, pitch, addr);
+			btext_setup_display(width, height, 8, pitch, addr);
+		}
+#endif /* CONFIG_PPC_EARLY_DEBUG_BOOTX */
 	}
 }
 
@@ -2117,8 +2188,10 @@ static void __init *make_room(unsigned long *mem_start, unsigned long *mem_end,
 	return ret;
 }
 
-#define dt_push_token(token, mem_start, mem_end) \
-	do { *((u32 *)make_room(mem_start, mem_end, 4, 4)) = token; } while(0)
+#define dt_push_token(token, mem_start, mem_end) do { 			\
+		void *room = make_room(mem_start, mem_end, 4, 4);	\
+		*(__be32 *)room = cpu_to_be32(token);			\
+	} while(0)
 
 static unsigned long __init dt_find_string(char *str)
 {
@@ -2291,7 +2364,7 @@ static void __init scan_dt_build_struct(phandle node, unsigned long *mem_start,
 			dt_push_token(4, mem_start, mem_end);
 			dt_push_token(soff, mem_start, mem_end);
 			valp = make_room(mem_start, mem_end, 4, 4);
-			*(u32 *)valp = node;
+			*(__be32 *)valp = cpu_to_be32(node);
 		}
 	}
 
@@ -2364,16 +2437,16 @@ static void __init flatten_device_tree(void)
 	dt_struct_end = PAGE_ALIGN(mem_start);
 
 	/* Finish header */
-	hdr->boot_cpuid_phys = prom.cpu;
-	hdr->magic = OF_DT_HEADER;
-	hdr->totalsize = dt_struct_end - dt_header_start;
-	hdr->off_dt_struct = dt_struct_start - dt_header_start;
-	hdr->off_dt_strings = dt_string_start - dt_header_start;
-	hdr->dt_strings_size = dt_string_end - dt_string_start;
-	hdr->off_mem_rsvmap = ((unsigned long)rsvmap) - dt_header_start;
-	hdr->version = OF_DT_VERSION;
+	hdr->boot_cpuid_phys = cpu_to_be32(prom.cpu);
+	hdr->magic = cpu_to_be32(OF_DT_HEADER);
+	hdr->totalsize = cpu_to_be32(dt_struct_end - dt_header_start);
+	hdr->off_dt_struct = cpu_to_be32(dt_struct_start - dt_header_start);
+	hdr->off_dt_strings = cpu_to_be32(dt_string_start - dt_header_start);
+	hdr->dt_strings_size = cpu_to_be32(dt_string_end - dt_string_start);
+	hdr->off_mem_rsvmap = cpu_to_be32(((unsigned long)rsvmap) - dt_header_start);
+	hdr->version = cpu_to_be32(OF_DT_VERSION);
 	/* Version 16 is not backward compatible */
-	hdr->last_comp_version = 0x10;
+	hdr->last_comp_version = cpu_to_be32(0x10);
 
 	/* Copy the reserve map in */
 	memcpy(rsvmap, mem_reserve_map, sizeof(mem_reserve_map));
@@ -2384,8 +2457,8 @@ static void __init flatten_device_tree(void)
 		prom_printf("reserved memory map:\n");
 		for (i = 0; i < mem_reserve_cnt; i++)
 			prom_printf("  %x - %x\n",
-				    mem_reserve_map[i].base,
-				    mem_reserve_map[i].size);
+				    be64_to_cpu(mem_reserve_map[i].base),
+				    be64_to_cpu(mem_reserve_map[i].size));
 	}
 #endif
 	/* Bump mem_reserve_cnt to cause further reservations to fail
@@ -2397,7 +2470,6 @@ static void __init flatten_device_tree(void)
 		    dt_string_start, dt_string_end);
 	prom_printf("Device tree struct  0x%x -> 0x%x\n",
 		    dt_struct_start, dt_struct_end);
-
 }
 
 #ifdef CONFIG_PPC_MAPLE
@@ -2730,18 +2802,19 @@ static void __init fixup_device_tree(void)
 
 static void __init prom_find_boot_cpu(void)
 {
-	u32 getprop_rval;
+	__be32 rval;
 	ihandle prom_cpu;
 	phandle cpu_pkg;
 
-	prom.cpu = 0;
-	if (prom_getprop(prom.chosen, "cpu", &prom_cpu, sizeof(prom_cpu)) <= 0)
+	rval = 0;
+	if (prom_getprop(prom.chosen, "cpu", &rval, sizeof(rval)) <= 0)
 		return;
+	prom_cpu = be32_to_cpu(rval);
 
 	cpu_pkg = call_prom("instance-to-package", 1, 1, prom_cpu);
 
-	prom_getprop(cpu_pkg, "reg", &getprop_rval, sizeof(getprop_rval));
-	prom.cpu = getprop_rval;
+	prom_getprop(cpu_pkg, "reg", &rval, sizeof(rval));
+	prom.cpu = be32_to_cpu(rval);
 
 	prom_debug("Booting CPU hw index = %lu\n", prom.cpu);
 }
@@ -2750,15 +2823,15 @@ static void __init prom_check_initrd(unsigned long r3, unsigned long r4)
 {
 #ifdef CONFIG_BLK_DEV_INITRD
 	if (r3 && r4 && r4 != 0xdeadbeef) {
-		unsigned long val;
+		__be64 val;
 
 		prom_initrd_start = is_kernel_addr(r3) ? __pa(r3) : r3;
 		prom_initrd_end = prom_initrd_start + r4;
 
-		val = prom_initrd_start;
+		val = cpu_to_be64(prom_initrd_start);
 		prom_setprop(prom.chosen, "/chosen", "linux,initrd-start",
 			     &val, sizeof(val));
-		val = prom_initrd_end;
+		val = cpu_to_be64(prom_initrd_end);
 		prom_setprop(prom.chosen, "/chosen", "linux,initrd-end",
 			     &val, sizeof(val));
 
@@ -2915,7 +2988,7 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4,
 	 */
 	prom_check_displays();
 
-#ifdef CONFIG_PPC64
+#if defined(CONFIG_PPC64) && defined(__BIG_ENDIAN__)
 	/*
 	 * Initialize IOMMU (TCE tables) on pSeries. Do that before anything else
 	 * that uses the allocator, we need to make sure we get the top of memory
@@ -2934,6 +3007,7 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4,
 		prom_instantiate_rtas();
 
 #ifdef CONFIG_PPC_POWERNV
+#ifdef __BIG_ENDIAN__
 	/* Detect HAL and try instanciating it & doing takeover */
 	if (of_platform == PLATFORM_PSERIES_LPAR) {
 		prom_query_opal();
@@ -2941,9 +3015,11 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4,
 			prom_opal_hold_cpus();
 			prom_opal_takeover();
 		}
-	} else if (of_platform == PLATFORM_OPAL)
+	} else
+#endif /* __BIG_ENDIAN__ */
+	if (of_platform == PLATFORM_OPAL)
 		prom_instantiate_opal();
-#endif
+#endif /* CONFIG_PPC_POWERNV */
 
 #ifdef CONFIG_PPC64
 	/* instantiate sml */
@@ -2954,6 +3030,8 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4,
 	 * On non-powermacs, put all CPUs in spin-loops.
 	 *
 	 * PowerMacs use a different mechanism to spin CPUs
+	 *
+	 * (This must be done after instanciating RTAS)
 	 */
 	if (of_platform != PLATFORM_POWERMAC &&
 	    of_platform != PLATFORM_OPAL)
@@ -2962,10 +3040,11 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4,
 	/*
 	 * Fill in some infos for use by the kernel later on
 	 */
-	if (prom_memory_limit)
+	if (prom_memory_limit) {
+		__be64 val = cpu_to_be64(prom_memory_limit);
 		prom_setprop(prom.chosen, "/chosen", "linux,memory-limit",
-			     &prom_memory_limit,
-			     sizeof(prom_memory_limit));
+			     &val, sizeof(val));
+	}
 #ifdef CONFIG_PPC64
 	if (prom_iommu_off)
 		prom_setprop(prom.chosen, "/chosen", "linux,iommu-off",
diff --git a/arch/powerpc/kernel/prom_init_check.sh b/arch/powerpc/kernel/prom_init_check.sh
index 3765da6be4f2..b0c263da219a 100644
--- a/arch/powerpc/kernel/prom_init_check.sh
+++ b/arch/powerpc/kernel/prom_init_check.sh
@@ -22,7 +22,8 @@ __secondary_hold_acknowledge __secondary_hold_spinloop __start
 strcmp strcpy strlcpy strlen strncmp strstr logo_linux_clut224
 reloc_got2 kernstart_addr memstart_addr linux_banner _stext
 opal_query_takeover opal_do_takeover opal_enter_rtas opal_secondary_entry
-boot_command_line __prom_init_toc_start __prom_init_toc_end"
+boot_command_line __prom_init_toc_start __prom_init_toc_end
+btext_setup_display"
 
 NM="$1"
 OBJ="$2"
diff --git a/arch/powerpc/kernel/prom_parse.c b/arch/powerpc/kernel/prom_parse.c
index 4e1331b8eb33..6295e646f78c 100644
--- a/arch/powerpc/kernel/prom_parse.c
+++ b/arch/powerpc/kernel/prom_parse.c
@@ -7,28 +7,27 @@
 #include <linux/of_address.h>
 #include <asm/prom.h>
 
-void of_parse_dma_window(struct device_node *dn, const void *dma_window_prop,
-		unsigned long *busno, unsigned long *phys, unsigned long *size)
+void of_parse_dma_window(struct device_node *dn, const __be32 *dma_window,
+			 unsigned long *busno, unsigned long *phys,
+			 unsigned long *size)
 {
-	const u32 *dma_window;
 	u32 cells;
-	const unsigned char *prop;
-
-	dma_window = dma_window_prop;
+	const __be32 *prop;
 
 	/* busno is always one cell */
-	*busno = *(dma_window++);
+	*busno = of_read_number(dma_window, 1);
+	dma_window++;
 
 	prop = of_get_property(dn, "ibm,#dma-address-cells", NULL);
 	if (!prop)
 		prop = of_get_property(dn, "#address-cells", NULL);
 
-	cells = prop ? *(u32 *)prop : of_n_addr_cells(dn);
+	cells = prop ? of_read_number(prop, 1) : of_n_addr_cells(dn);
 	*phys = of_read_number(dma_window, cells);
 
 	dma_window += cells;
 
 	prop = of_get_property(dn, "ibm,#dma-size-cells", NULL);
-	cells = prop ? *(u32 *)prop : of_n_size_cells(dn);
+	cells = prop ? of_read_number(prop, 1) : of_n_size_cells(dn);
 	*size = of_read_number(dma_window, cells);
 }
diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c
index 80b5ef403f68..4cf674d7d5ae 100644
--- a/arch/powerpc/kernel/rtas.c
+++ b/arch/powerpc/kernel/rtas.c
@@ -91,7 +91,7 @@ static void unlock_rtas(unsigned long flags)
  * are designed only for very early low-level debugging, which
  * is why the token is hard-coded to 10.
  */
-static void call_rtas_display_status(char c)
+static void call_rtas_display_status(unsigned char c)
 {
 	struct rtas_args *args = &rtas.args;
 	unsigned long s;
@@ -100,11 +100,11 @@ static void call_rtas_display_status(char c)
 		return;
 	s = lock_rtas();
 
-	args->token = 10;
-	args->nargs = 1;
-	args->nret  = 1;
-	args->rets  = (rtas_arg_t *)&(args->args[1]);
-	args->args[0] = (unsigned char)c;
+	args->token = cpu_to_be32(10);
+	args->nargs = cpu_to_be32(1);
+	args->nret  = cpu_to_be32(1);
+	args->rets  = &(args->args[1]);
+	args->args[0] = cpu_to_be32(c);
 
 	enter_rtas(__pa(args));
 
@@ -204,7 +204,7 @@ void rtas_progress(char *s, unsigned short hex)
 {
 	struct device_node *root;
 	int width;
-	const int *p;
+	const __be32 *p;
 	char *os;
 	static int display_character, set_indicator;
 	static int display_width, display_lines, form_feed;
@@ -221,13 +221,13 @@ void rtas_progress(char *s, unsigned short hex)
 		if ((root = of_find_node_by_path("/rtas"))) {
 			if ((p = of_get_property(root,
 					"ibm,display-line-length", NULL)))
-				display_width = *p;
+				display_width = be32_to_cpu(*p);
 			if ((p = of_get_property(root,
 					"ibm,form-feed", NULL)))
-				form_feed = *p;
+				form_feed = be32_to_cpu(*p);
 			if ((p = of_get_property(root,
 					"ibm,display-number-of-lines", NULL)))
-				display_lines = *p;
+				display_lines = be32_to_cpu(*p);
 			row_width = of_get_property(root,
 					"ibm,display-truncation-length", NULL);
 			of_node_put(root);
@@ -322,11 +322,11 @@ EXPORT_SYMBOL(rtas_progress);		/* needed by rtas_flash module */
 
 int rtas_token(const char *service)
 {
-	const int *tokp;
+	const __be32 *tokp;
 	if (rtas.dev == NULL)
 		return RTAS_UNKNOWN_SERVICE;
 	tokp = of_get_property(rtas.dev, service, NULL);
-	return tokp ? *tokp : RTAS_UNKNOWN_SERVICE;
+	return tokp ? be32_to_cpu(*tokp) : RTAS_UNKNOWN_SERVICE;
 }
 EXPORT_SYMBOL(rtas_token);
 
@@ -380,11 +380,11 @@ static char *__fetch_rtas_last_error(char *altbuf)
 
 	bufsz = rtas_get_error_log_max();
 
-	err_args.token = rtas_last_error_token;
-	err_args.nargs = 2;
-	err_args.nret = 1;
-	err_args.args[0] = (rtas_arg_t)__pa(rtas_err_buf);
-	err_args.args[1] = bufsz;
+	err_args.token = cpu_to_be32(rtas_last_error_token);
+	err_args.nargs = cpu_to_be32(2);
+	err_args.nret = cpu_to_be32(1);
+	err_args.args[0] = cpu_to_be32(__pa(rtas_err_buf));
+	err_args.args[1] = cpu_to_be32(bufsz);
 	err_args.args[2] = 0;
 
 	save_args = rtas.args;
@@ -433,13 +433,13 @@ int rtas_call(int token, int nargs, int nret, int *outputs, ...)
 	s = lock_rtas();
 	rtas_args = &rtas.args;
 
-	rtas_args->token = token;
-	rtas_args->nargs = nargs;
-	rtas_args->nret  = nret;
-	rtas_args->rets  = (rtas_arg_t *)&(rtas_args->args[nargs]);
+	rtas_args->token = cpu_to_be32(token);
+	rtas_args->nargs = cpu_to_be32(nargs);
+	rtas_args->nret  = cpu_to_be32(nret);
+	rtas_args->rets  = &(rtas_args->args[nargs]);
 	va_start(list, outputs);
 	for (i = 0; i < nargs; ++i)
-		rtas_args->args[i] = va_arg(list, rtas_arg_t);
+		rtas_args->args[i] = cpu_to_be32(va_arg(list, __u32));
 	va_end(list);
 
 	for (i = 0; i < nret; ++i)
@@ -449,13 +449,13 @@ int rtas_call(int token, int nargs, int nret, int *outputs, ...)
 
 	/* A -1 return code indicates that the last command couldn't
 	   be completed due to a hardware error. */
-	if (rtas_args->rets[0] == -1)
+	if (be32_to_cpu(rtas_args->rets[0]) == -1)
 		buff_copy = __fetch_rtas_last_error(NULL);
 
 	if (nret > 1 && outputs != NULL)
 		for (i = 0; i < nret-1; ++i)
-			outputs[i] = rtas_args->rets[i+1];
-	ret = (nret > 0)? rtas_args->rets[0]: 0;
+			outputs[i] = be32_to_cpu(rtas_args->rets[i+1]);
+	ret = (nret > 0)? be32_to_cpu(rtas_args->rets[0]): 0;
 
 	unlock_rtas(s);
 
@@ -588,8 +588,8 @@ bool rtas_indicator_present(int token, int *maxindex)
 {
 	int proplen, count, i;
 	const struct indicator_elem {
-		u32 token;
-		u32 maxindex;
+		__be32 token;
+		__be32 maxindex;
 	} *indicators;
 
 	indicators = of_get_property(rtas.dev, "rtas-indicators", &proplen);
@@ -599,10 +599,10 @@ bool rtas_indicator_present(int token, int *maxindex)
 	count = proplen / sizeof(struct indicator_elem);
 
 	for (i = 0; i < count; i++) {
-		if (indicators[i].token != token)
+		if (__be32_to_cpu(indicators[i].token) != token)
 			continue;
 		if (maxindex)
-			*maxindex = indicators[i].maxindex;
+			*maxindex = __be32_to_cpu(indicators[i].maxindex);
 		return true;
 	}
 
@@ -1097,19 +1097,19 @@ void __init rtas_initialize(void)
 	 */
 	rtas.dev = of_find_node_by_name(NULL, "rtas");
 	if (rtas.dev) {
-		const u32 *basep, *entryp, *sizep;
+		const __be32 *basep, *entryp, *sizep;
 
 		basep = of_get_property(rtas.dev, "linux,rtas-base", NULL);
 		sizep = of_get_property(rtas.dev, "rtas-size", NULL);
 		if (basep != NULL && sizep != NULL) {
-			rtas.base = *basep;
-			rtas.size = *sizep;
+			rtas.base = __be32_to_cpu(*basep);
+			rtas.size = __be32_to_cpu(*sizep);
 			entryp = of_get_property(rtas.dev,
 					"linux,rtas-entry", NULL);
 			if (entryp == NULL) /* Ugh */
 				rtas.entry = rtas.base;
 			else
-				rtas.entry = *entryp;
+				rtas.entry = __be32_to_cpu(*entryp);
 		} else
 			rtas.dev = NULL;
 	}
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index 63d051f5b7a5..3d261c071fc8 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -436,7 +436,8 @@ void __init smp_setup_cpu_maps(void)
 	DBG("smp_setup_cpu_maps()\n");
 
 	while ((dn = of_find_node_by_type(dn, "cpu")) && cpu < nr_cpu_ids) {
-		const int *intserv;
+		const __be32 *intserv;
+		__be32 cpu_be;
 		int j, len;
 
 		DBG("  * %s...\n", dn->full_name);
@@ -450,15 +451,17 @@ void __init smp_setup_cpu_maps(void)
 		} else {
 			DBG("    no ibm,ppc-interrupt-server#s -> 1 thread\n");
 			intserv = of_get_property(dn, "reg", NULL);
-			if (!intserv)
-				intserv = &cpu;	/* assume logical == phys */
+			if (!intserv) {
+				cpu_be = cpu_to_be32(cpu);
+				intserv = &cpu_be;	/* assume logical == phys */
+			}
 		}
 
 		for (j = 0; j < nthreads && cpu < nr_cpu_ids; j++) {
 			DBG("    thread %d -> cpu %d (hard id %d)\n",
-			    j, cpu, intserv[j]);
+			    j, cpu, be32_to_cpu(intserv[j]));
 			set_cpu_present(cpu, true);
-			set_hard_smp_processor_id(cpu, intserv[j]);
+			set_hard_smp_processor_id(cpu, be32_to_cpu(intserv[j]));
 			set_cpu_possible(cpu, true);
 			cpu++;
 		}
diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c
index a8f54ecb091f..a4bbcae72578 100644
--- a/arch/powerpc/kernel/setup_32.c
+++ b/arch/powerpc/kernel/setup_32.c
@@ -38,6 +38,7 @@
 #include <asm/serial.h>
 #include <asm/udbg.h>
 #include <asm/mmu_context.h>
+#include <asm/epapr_hcalls.h>
 
 #include "setup.h"
 
@@ -128,6 +129,8 @@ notrace void __init machine_init(u64 dt_ptr)
 	/* Do some early initialization based on the flat device tree */
 	early_init_devtree(__va(dt_ptr));
 
+	epapr_paravirt_early_init();
+
 	early_init_mmu();
 
 	probe_machine();
@@ -326,5 +329,4 @@ void __init setup_arch(char **cmdline_p)
 
 	/* Initialize the MMU context management stuff */
 	mmu_context_init();
-
 }
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 389fb8077cc9..278ca93e1f28 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -10,7 +10,7 @@
  *      2 of the License, or (at your option) any later version.
  */
 
-#undef DEBUG
+#define DEBUG
 
 #include <linux/export.h>
 #include <linux/string.h>
@@ -66,6 +66,7 @@
 #include <asm/code-patching.h>
 #include <asm/kvm_ppc.h>
 #include <asm/hugetlb.h>
+#include <asm/epapr_hcalls.h>
 
 #include "setup.h"
 
@@ -215,6 +216,8 @@ void __init early_setup(unsigned long dt_ptr)
 	 */
 	early_init_devtree(__va(dt_ptr));
 
+	epapr_paravirt_early_init();
+
 	/* Now we know the logical id of our boot cpu, setup the paca. */
 	setup_paca(&paca[boot_cpuid]);
 	fixup_boot_paca();
@@ -229,6 +232,8 @@ void __init early_setup(unsigned long dt_ptr)
 	/* Initialize the hash table or TLB handling */
 	early_init_mmu();
 
+	kvm_cma_reserve();
+
 	/*
 	 * Reserve any gigantic pages requested on the command line.
 	 * memblock needs to have been initialized by the time this is
@@ -237,6 +242,18 @@ void __init early_setup(unsigned long dt_ptr)
 	reserve_hugetlb_gpages();
 
 	DBG(" <- early_setup()\n");
+
+#ifdef CONFIG_PPC_EARLY_DEBUG_BOOTX
+	/*
+	 * This needs to be done *last* (after the above DBG() even)
+	 *
+	 * Right after we return from this function, we turn on the MMU
+	 * which means the real-mode access trick that btext does will
+	 * no longer work, it needs to switch to using a real MMU
+	 * mapping. This call will ensure that it does
+	 */
+	btext_map();
+#endif /* CONFIG_PPC_EARLY_DEBUG_BOOTX */
 }
 
 #ifdef CONFIG_SMP
@@ -305,14 +322,14 @@ static void __init initialize_cache_info(void)
 		 * d-cache and i-cache sizes... -Peter
 		 */
 		if (num_cpus == 1) {
-			const u32 *sizep, *lsizep;
+			const __be32 *sizep, *lsizep;
 			u32 size, lsize;
 
 			size = 0;
 			lsize = cur_cpu_spec->dcache_bsize;
 			sizep = of_get_property(np, "d-cache-size", NULL);
 			if (sizep != NULL)
-				size = *sizep;
+				size = be32_to_cpu(*sizep);
 			lsizep = of_get_property(np, "d-cache-block-size",
 						 NULL);
 			/* fallback if block size missing */
@@ -321,8 +338,8 @@ static void __init initialize_cache_info(void)
 							 "d-cache-line-size",
 							 NULL);
 			if (lsizep != NULL)
-				lsize = *lsizep;
-			if (sizep == 0 || lsizep == 0)
+				lsize = be32_to_cpu(*lsizep);
+			if (sizep == NULL || lsizep == NULL)
 				DBG("Argh, can't find dcache properties ! "
 				    "sizep: %p, lsizep: %p\n", sizep, lsizep);
 
@@ -335,7 +352,7 @@ static void __init initialize_cache_info(void)
 			lsize = cur_cpu_spec->icache_bsize;
 			sizep = of_get_property(np, "i-cache-size", NULL);
 			if (sizep != NULL)
-				size = *sizep;
+				size = be32_to_cpu(*sizep);
 			lsizep = of_get_property(np, "i-cache-block-size",
 						 NULL);
 			if (lsizep == NULL)
@@ -343,8 +360,8 @@ static void __init initialize_cache_info(void)
 							 "i-cache-line-size",
 							 NULL);
 			if (lsizep != NULL)
-				lsize = *lsizep;
-			if (sizep == 0 || lsizep == 0)
+				lsize = be32_to_cpu(*lsizep);
+			if (sizep == NULL || lsizep == NULL)
 				DBG("Argh, can't find icache properties ! "
 				    "sizep: %p, lsizep: %p\n", sizep, lsizep);
 
@@ -609,8 +626,6 @@ void __init setup_arch(char **cmdline_p)
 	/* Initialize the MMU context management stuff */
 	mmu_context_init();
 
-	kvm_linear_init();
-
 	/* Interrupt code needs to be 64K-aligned */
 	if ((unsigned long)_stext & 0xffff)
 		panic("Kernelbase not 64K-aligned (0x%lx)!\n",
@@ -701,8 +716,7 @@ void __init setup_per_cpu_areas(void)
 #endif
 
 
-#ifdef CONFIG_PPC_INDIRECT_IO
+#if defined(CONFIG_PPC_INDIRECT_PIO) || defined(CONFIG_PPC_INDIRECT_MMIO)
 struct ppc_pci_io ppc_pci_io;
 EXPORT_SYMBOL(ppc_pci_io);
-#endif /* CONFIG_PPC_INDIRECT_IO */
-
+#endif
diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c
index 0f83122e6676..bebdf1a1a540 100644
--- a/arch/powerpc/kernel/signal_32.c
+++ b/arch/powerpc/kernel/signal_32.c
@@ -436,7 +436,10 @@ static int save_user_regs(struct pt_regs *regs, struct mcontext __user *frame,
 	 * use altivec. Since VSCR only contains 32 bits saved in the least
 	 * significant bits of a vector, we "cheat" and stuff VRSAVE in the
 	 * most significant bits of that same vector. --BenH
+	 * Note that the current VRSAVE value is in the SPR at this point.
 	 */
+	if (cpu_has_feature(CPU_FTR_ALTIVEC))
+		current->thread.vrsave = mfspr(SPRN_VRSAVE);
 	if (__put_user(current->thread.vrsave, (u32 __user *)&frame->mc_vregs[32]))
 		return 1;
 #endif /* CONFIG_ALTIVEC */
@@ -557,6 +560,8 @@ static int save_tm_user_regs(struct pt_regs *regs,
 	 * significant bits of a vector, we "cheat" and stuff VRSAVE in the
 	 * most significant bits of that same vector. --BenH
 	 */
+	if (cpu_has_feature(CPU_FTR_ALTIVEC))
+		current->thread.vrsave = mfspr(SPRN_VRSAVE);
 	if (__put_user(current->thread.vrsave,
 		       (u32 __user *)&frame->mc_vregs[32]))
 		return 1;
@@ -696,6 +701,8 @@ static long restore_user_regs(struct pt_regs *regs,
 	/* Always get VRSAVE back */
 	if (__get_user(current->thread.vrsave, (u32 __user *)&sr->mc_vregs[32]))
 		return 1;
+	if (cpu_has_feature(CPU_FTR_ALTIVEC))
+		mtspr(SPRN_VRSAVE, current->thread.vrsave);
 #endif /* CONFIG_ALTIVEC */
 	if (copy_fpr_from_user(current, &sr->mc_fregs))
 		return 1;
@@ -809,6 +816,8 @@ static long restore_tm_user_regs(struct pt_regs *regs,
 	    __get_user(current->thread.transact_vrsave,
 		       (u32 __user *)&tm_sr->mc_vregs[32]))
 		return 1;
+	if (cpu_has_feature(CPU_FTR_ALTIVEC))
+		mtspr(SPRN_VRSAVE, current->thread.vrsave);
 #endif /* CONFIG_ALTIVEC */
 
 	regs->msr &= ~(MSR_FP | MSR_FE0 | MSR_FE1);
diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c
index 887e99d85bc2..f93ec2835a13 100644
--- a/arch/powerpc/kernel/signal_64.c
+++ b/arch/powerpc/kernel/signal_64.c
@@ -96,8 +96,6 @@ static long setup_sigcontext(struct sigcontext __user *sc, struct pt_regs *regs,
 	unsigned long msr = regs->msr;
 	long err = 0;
 
-	flush_fp_to_thread(current);
-
 #ifdef CONFIG_ALTIVEC
 	err |= __put_user(v_regs, &sc->v_regs);
 
@@ -114,6 +112,8 @@ static long setup_sigcontext(struct sigcontext __user *sc, struct pt_regs *regs,
 	/* We always copy to/from vrsave, it's 0 if we don't have or don't
 	 * use altivec.
 	 */
+	if (cpu_has_feature(CPU_FTR_ALTIVEC))
+		current->thread.vrsave = mfspr(SPRN_VRSAVE);
 	err |= __put_user(current->thread.vrsave, (u32 __user *)&v_regs[33]);
 #else /* CONFIG_ALTIVEC */
 	err |= __put_user(0, &sc->v_regs);
@@ -217,6 +217,8 @@ static long setup_tm_sigcontexts(struct sigcontext __user *sc,
 	/* We always copy to/from vrsave, it's 0 if we don't have or don't
 	 * use altivec.
 	 */
+	if (cpu_has_feature(CPU_FTR_ALTIVEC))
+		current->thread.vrsave = mfspr(SPRN_VRSAVE);
 	err |= __put_user(current->thread.vrsave, (u32 __user *)&v_regs[33]);
 	if (msr & MSR_VEC)
 		err |= __put_user(current->thread.transact_vrsave,
@@ -346,16 +348,18 @@ static long restore_sigcontext(struct pt_regs *regs, sigset_t *set, int sig,
 	if (v_regs && !access_ok(VERIFY_READ, v_regs, 34 * sizeof(vector128)))
 		return -EFAULT;
 	/* Copy 33 vec registers (vr0..31 and vscr) from the stack */
-	if (v_regs != 0 && (msr & MSR_VEC) != 0)
+	if (v_regs != NULL && (msr & MSR_VEC) != 0)
 		err |= __copy_from_user(current->thread.vr, v_regs,
 					33 * sizeof(vector128));
 	else if (current->thread.used_vr)
 		memset(current->thread.vr, 0, 33 * sizeof(vector128));
 	/* Always get VRSAVE back */
-	if (v_regs != 0)
+	if (v_regs != NULL)
 		err |= __get_user(current->thread.vrsave, (u32 __user *)&v_regs[33]);
 	else
 		current->thread.vrsave = 0;
+	if (cpu_has_feature(CPU_FTR_ALTIVEC))
+		mtspr(SPRN_VRSAVE, current->thread.vrsave);
 #endif /* CONFIG_ALTIVEC */
 	/* restore floating point */
 	err |= copy_fpr_from_user(current, &sc->fp_regs);
@@ -463,7 +467,7 @@ static long restore_tm_sigcontexts(struct pt_regs *regs,
 				    tm_v_regs, 34 * sizeof(vector128)))
 		return -EFAULT;
 	/* Copy 33 vec registers (vr0..31 and vscr) from the stack */
-	if (v_regs != 0 && tm_v_regs != 0 && (msr & MSR_VEC) != 0) {
+	if (v_regs != NULL && tm_v_regs != NULL && (msr & MSR_VEC) != 0) {
 		err |= __copy_from_user(current->thread.vr, v_regs,
 					33 * sizeof(vector128));
 		err |= __copy_from_user(current->thread.transact_vr, tm_v_regs,
@@ -474,7 +478,7 @@ static long restore_tm_sigcontexts(struct pt_regs *regs,
 		memset(current->thread.transact_vr, 0, 33 * sizeof(vector128));
 	}
 	/* Always get VRSAVE back */
-	if (v_regs != 0 && tm_v_regs != 0) {
+	if (v_regs != NULL && tm_v_regs != NULL) {
 		err |= __get_user(current->thread.vrsave,
 				  (u32 __user *)&v_regs[33]);
 		err |= __get_user(current->thread.transact_vrsave,
@@ -484,6 +488,8 @@ static long restore_tm_sigcontexts(struct pt_regs *regs,
 		current->thread.vrsave = 0;
 		current->thread.transact_vrsave = 0;
 	}
+	if (cpu_has_feature(CPU_FTR_ALTIVEC))
+		mtspr(SPRN_VRSAVE, current->thread.vrsave);
 #endif /* CONFIG_ALTIVEC */
 	/* restore floating point */
 	err |= copy_fpr_from_user(current, &sc->fp_regs);
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 38b0ba65a735..8e59abc237d7 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -81,6 +81,28 @@ int smt_enabled_at_boot = 1;
 
 static void (*crash_ipi_function_ptr)(struct pt_regs *) = NULL;
 
+/*
+ * Returns 1 if the specified cpu should be brought up during boot.
+ * Used to inhibit booting threads if they've been disabled or
+ * limited on the command line
+ */
+int smp_generic_cpu_bootable(unsigned int nr)
+{
+	/* Special case - we inhibit secondary thread startup
+	 * during boot if the user requests it.
+	 */
+	if (system_state == SYSTEM_BOOTING && cpu_has_feature(CPU_FTR_SMT)) {
+		if (!smt_enabled_at_boot && cpu_thread_in_core(nr) != 0)
+			return 0;
+		if (smt_enabled_at_boot
+		    && cpu_thread_in_core(nr) >= smt_enabled_at_boot)
+			return 0;
+	}
+
+	return 1;
+}
+
+
 #ifdef CONFIG_PPC64
 int smp_generic_kick_cpu(int nr)
 {
@@ -172,7 +194,7 @@ int smp_request_message_ipi(int virq, int msg)
 #endif
 	err = request_irq(virq, smp_ipi_action[msg],
 			  IRQF_PERCPU | IRQF_NO_THREAD | IRQF_NO_SUSPEND,
-			  smp_ipi_name[msg], 0);
+			  smp_ipi_name[msg], NULL);
 	WARN(err < 0, "unable to request_irq %d for %s (rc %d)\n",
 		virq, smp_ipi_name[msg], err);
 
@@ -210,6 +232,12 @@ void smp_muxed_ipi_message_pass(int cpu, int msg)
 	smp_ops->cause_ipi(cpu, info->data);
 }
 
+#ifdef __BIG_ENDIAN__
+#define IPI_MESSAGE(A) (1 << (24 - 8 * (A)))
+#else
+#define IPI_MESSAGE(A) (1 << (8 * (A)))
+#endif
+
 irqreturn_t smp_ipi_demux(void)
 {
 	struct cpu_messages *info = &__get_cpu_var(ipi_message);
@@ -219,19 +247,14 @@ irqreturn_t smp_ipi_demux(void)
 
 	do {
 		all = xchg(&info->messages, 0);
-
-#ifdef __BIG_ENDIAN
-		if (all & (1 << (24 - 8 * PPC_MSG_CALL_FUNCTION)))
+		if (all & IPI_MESSAGE(PPC_MSG_CALL_FUNCTION))
 			generic_smp_call_function_interrupt();
-		if (all & (1 << (24 - 8 * PPC_MSG_RESCHEDULE)))
+		if (all & IPI_MESSAGE(PPC_MSG_RESCHEDULE))
 			scheduler_ipi();
-		if (all & (1 << (24 - 8 * PPC_MSG_CALL_FUNC_SINGLE)))
+		if (all & IPI_MESSAGE(PPC_MSG_CALL_FUNC_SINGLE))
 			generic_smp_call_function_single_interrupt();
-		if (all & (1 << (24 - 8 * PPC_MSG_DEBUGGER_BREAK)))
+		if (all & IPI_MESSAGE(PPC_MSG_DEBUGGER_BREAK))
 			debug_ipi_action(0, NULL);
-#else
-#error Unsupported ENDIAN
-#endif
 	} while (info->messages);
 
 	return IRQ_HANDLED;
@@ -574,6 +597,22 @@ out:
 	return id;
 }
 
+/* Return the value of the chip-id property corresponding
+ * to the given logical cpu.
+ */
+int cpu_to_chip_id(int cpu)
+{
+	struct device_node *np;
+
+	np = of_get_cpu_node(cpu, NULL);
+	if (!np)
+		return -1;
+
+	of_node_put(np);
+	return of_get_ibm_chip_id(np);
+}
+EXPORT_SYMBOL(cpu_to_chip_id);
+
 /* Helper routines for cpu to core mapping */
 int cpu_core_index_of_thread(int cpu)
 {
@@ -587,6 +626,33 @@ int cpu_first_thread_of_core(int core)
 }
 EXPORT_SYMBOL_GPL(cpu_first_thread_of_core);
 
+static void traverse_siblings_chip_id(int cpu, bool add, int chipid)
+{
+	const struct cpumask *mask;
+	struct device_node *np;
+	int i, plen;
+	const __be32 *prop;
+
+	mask = add ? cpu_online_mask : cpu_present_mask;
+	for_each_cpu(i, mask) {
+		np = of_get_cpu_node(i, NULL);
+		if (!np)
+			continue;
+		prop = of_get_property(np, "ibm,chip-id", &plen);
+		if (prop && plen == sizeof(int) &&
+		    of_read_number(prop, 1) == chipid) {
+			if (add) {
+				cpumask_set_cpu(cpu, cpu_core_mask(i));
+				cpumask_set_cpu(i, cpu_core_mask(cpu));
+			} else {
+				cpumask_clear_cpu(cpu, cpu_core_mask(i));
+				cpumask_clear_cpu(i, cpu_core_mask(cpu));
+			}
+		}
+		of_node_put(np);
+	}
+}
+
 /* Must be called when no change can occur to cpu_present_mask,
  * i.e. during cpu online or offline.
  */
@@ -609,11 +675,51 @@ static struct device_node *cpu_to_l2cache(int cpu)
 	return cache;
 }
 
+static void traverse_core_siblings(int cpu, bool add)
+{
+	struct device_node *l2_cache, *np;
+	const struct cpumask *mask;
+	int i, chip, plen;
+	const __be32 *prop;
+
+	/* First see if we have ibm,chip-id properties in cpu nodes */
+	np = of_get_cpu_node(cpu, NULL);
+	if (np) {
+		chip = -1;
+		prop = of_get_property(np, "ibm,chip-id", &plen);
+		if (prop && plen == sizeof(int))
+			chip = of_read_number(prop, 1);
+		of_node_put(np);
+		if (chip >= 0) {
+			traverse_siblings_chip_id(cpu, add, chip);
+			return;
+		}
+	}
+
+	l2_cache = cpu_to_l2cache(cpu);
+	mask = add ? cpu_online_mask : cpu_present_mask;
+	for_each_cpu(i, mask) {
+		np = cpu_to_l2cache(i);
+		if (!np)
+			continue;
+		if (np == l2_cache) {
+			if (add) {
+				cpumask_set_cpu(cpu, cpu_core_mask(i));
+				cpumask_set_cpu(i, cpu_core_mask(cpu));
+			} else {
+				cpumask_clear_cpu(cpu, cpu_core_mask(i));
+				cpumask_clear_cpu(i, cpu_core_mask(cpu));
+			}
+		}
+		of_node_put(np);
+	}
+	of_node_put(l2_cache);
+}
+
 /* Activate a secondary processor. */
 void start_secondary(void *unused)
 {
 	unsigned int cpu = smp_processor_id();
-	struct device_node *l2_cache;
 	int i, base;
 
 	atomic_inc(&init_mm.mm_count);
@@ -652,18 +758,7 @@ void start_secondary(void *unused)
 		cpumask_set_cpu(cpu, cpu_core_mask(base + i));
 		cpumask_set_cpu(base + i, cpu_core_mask(cpu));
 	}
-	l2_cache = cpu_to_l2cache(cpu);
-	for_each_online_cpu(i) {
-		struct device_node *np = cpu_to_l2cache(i);
-		if (!np)
-			continue;
-		if (np == l2_cache) {
-			cpumask_set_cpu(cpu, cpu_core_mask(i));
-			cpumask_set_cpu(i, cpu_core_mask(cpu));
-		}
-		of_node_put(np);
-	}
-	of_node_put(l2_cache);
+	traverse_core_siblings(cpu, true);
 
 	smp_wmb();
 	notify_cpu_starting(cpu);
@@ -719,7 +814,6 @@ int arch_sd_sibling_asym_packing(void)
 #ifdef CONFIG_HOTPLUG_CPU
 int __cpu_disable(void)
 {
-	struct device_node *l2_cache;
 	int cpu = smp_processor_id();
 	int base, i;
 	int err;
@@ -739,20 +833,7 @@ int __cpu_disable(void)
 		cpumask_clear_cpu(cpu, cpu_core_mask(base + i));
 		cpumask_clear_cpu(base + i, cpu_core_mask(cpu));
 	}
-
-	l2_cache = cpu_to_l2cache(cpu);
-	for_each_present_cpu(i) {
-		struct device_node *np = cpu_to_l2cache(i);
-		if (!np)
-			continue;
-		if (np == l2_cache) {
-			cpumask_clear_cpu(cpu, cpu_core_mask(i));
-			cpumask_clear_cpu(i, cpu_core_mask(cpu));
-		}
-		of_node_put(np);
-	}
-	of_node_put(l2_cache);
-
+	traverse_core_siblings(cpu, false);
 
 	return 0;
 }
diff --git a/arch/powerpc/kernel/softemu8xx.c b/arch/powerpc/kernel/softemu8xx.c
deleted file mode 100644
index 29b2f81dd709..000000000000
--- a/arch/powerpc/kernel/softemu8xx.c
+++ /dev/null
@@ -1,199 +0,0 @@
-/*
- * Software emulation of some PPC instructions for the 8xx core.
- *
- * Copyright (C) 1998 Dan Malek (dmalek@jlc.net)
- *
- * Software floating emuation for the MPC8xx processor.  I did this mostly
- * because it was easier than trying to get the libraries compiled for
- * software floating point.  The goal is still to get the libraries done,
- * but I lost patience and needed some hacks to at least get init and
- * shells running.  The first problem is the setjmp/longjmp that save
- * and restore the floating point registers.
- *
- * For this emulation, our working registers are found on the register
- * save area.
- */
-
-#include <linux/errno.h>
-#include <linux/sched.h>
-#include <linux/kernel.h>
-#include <linux/mm.h>
-#include <linux/stddef.h>
-#include <linux/unistd.h>
-#include <linux/ptrace.h>
-#include <linux/user.h>
-#include <linux/interrupt.h>
-
-#include <asm/pgtable.h>
-#include <asm/uaccess.h>
-#include <asm/io.h>
-
-/* Eventually we may need a look-up table, but this works for now.
-*/
-#define LFS	48
-#define LFD	50
-#define LFDU	51
-#define STFD	54
-#define STFDU	55
-#define FMR	63
-
-void print_8xx_pte(struct mm_struct *mm, unsigned long addr)
-{
-	pgd_t *pgd;
-	pmd_t *pmd;
-	pte_t *pte;
-
-	printk(" pte @ 0x%8lx: ", addr);
-	pgd = pgd_offset(mm, addr & PAGE_MASK);
-	if (pgd) {
-		pmd = pmd_offset(pud_offset(pgd, addr & PAGE_MASK),
-		                 addr & PAGE_MASK);
-		if (pmd && pmd_present(*pmd)) {
-			pte = pte_offset_kernel(pmd, addr & PAGE_MASK);
-			if (pte) {
-				printk(" (0x%08lx)->(0x%08lx)->0x%08lx\n",
-				        (long)pgd, (long)pte, (long)pte_val(*pte));
-#define pp ((long)pte_val(*pte))
-				printk(" RPN: %05lx PP: %lx SPS: %lx SH: %lx "
-				       "CI: %lx v: %lx\n",
-				       pp>>12,    /* rpn */
-				       (pp>>10)&3, /* pp */
-				       (pp>>3)&1, /* small */
-				       (pp>>2)&1, /* shared */
-				       (pp>>1)&1, /* cache inhibit */
-				       pp&1       /* valid */
-				       );
-#undef pp
-			}
-			else {
-				printk("no pte\n");
-			}
-		}
-		else {
-			printk("no pmd\n");
-		}
-	}
-	else {
-		printk("no pgd\n");
-	}
-}
-
-int get_8xx_pte(struct mm_struct *mm, unsigned long addr)
-{
-	pgd_t *pgd;
-	pmd_t *pmd;
-	pte_t *pte;
-	int retval = 0;
-
-	pgd = pgd_offset(mm, addr & PAGE_MASK);
-	if (pgd) {
-		pmd = pmd_offset(pud_offset(pgd, addr & PAGE_MASK),
-		                 addr & PAGE_MASK);
-		if (pmd && pmd_present(*pmd)) {
-			pte = pte_offset_kernel(pmd, addr & PAGE_MASK);
-			if (pte) {
-				retval = (int)pte_val(*pte);
-			}
-		}
-	}
-	return retval;
-}
-
-/*
- * We return 0 on success, 1 on unimplemented instruction, and EFAULT
- * if a load/store faulted.
- */
-int Soft_emulate_8xx(struct pt_regs *regs)
-{
-	u32 inst, instword;
-	u32 flreg, idxreg, disp;
-	int retval;
-	s16 sdisp;
-	u32 *ea, *ip;
-
-	retval = 0;
-
-	instword = *((u32 *)regs->nip);
-	inst = instword >> 26;
-
-	flreg = (instword >> 21) & 0x1f;
-	idxreg = (instword >> 16) & 0x1f;
-	disp = instword & 0xffff;
-
-	ea = (u32 *)(regs->gpr[idxreg] + disp);
-	ip = (u32 *)&current->thread.TS_FPR(flreg);
-
-	switch ( inst )
-	{
-	case LFD:
-		/* this is a 16 bit quantity that is sign extended
-		 * so use a signed short here -- Cort
-		 */
-		sdisp = (instword & 0xffff);
-		ea = (u32 *)(regs->gpr[idxreg] + sdisp);
-		if (copy_from_user(ip, ea, sizeof(double)))
-			retval = -EFAULT;
-		break;
-
-	case LFDU:
-		if (copy_from_user(ip, ea, sizeof(double)))
-			retval = -EFAULT;
-		else
-			regs->gpr[idxreg] = (u32)ea;
-		break;
-	case LFS:
-		sdisp = (instword & 0xffff);
-		ea = (u32 *)(regs->gpr[idxreg] + sdisp);
-		if (copy_from_user(ip, ea, sizeof(float)))
-			retval = -EFAULT;
-		break;
-	case STFD:
-		/* this is a 16 bit quantity that is sign extended
-		 * so use a signed short here -- Cort
-		 */
-		sdisp = (instword & 0xffff);
-		ea = (u32 *)(regs->gpr[idxreg] + sdisp);
-		if (copy_to_user(ea, ip, sizeof(double)))
-			retval = -EFAULT;
-		break;
-
-	case STFDU:
-		if (copy_to_user(ea, ip, sizeof(double)))
-			retval = -EFAULT;
-		else
-			regs->gpr[idxreg] = (u32)ea;
-		break;
-	case FMR:
-		/* assume this is a fp move -- Cort */
-		memcpy(ip, &current->thread.TS_FPR((instword>>11)&0x1f),
-		       sizeof(double));
-		break;
-	default:
-		retval = 1;
-		printk("Bad emulation %s/%d\n"
-		       " NIP: %08lx instruction: %08x opcode: %x "
-		       "A: %x B: %x C: %x code: %x rc: %x\n",
-		       current->comm,current->pid,
-		       regs->nip,
-		       instword,inst,
-		       (instword>>16)&0x1f,
-		       (instword>>11)&0x1f,
-		       (instword>>6)&0x1f,
-		       (instword>>1)&0x3ff,
-		       instword&1);
-		{
-			int pa;
-			print_8xx_pte(current->mm,regs->nip);
-			pa = get_8xx_pte(current->mm,regs->nip) & PAGE_MASK;
-			pa |= (regs->nip & ~PAGE_MASK);
-			pa = (unsigned long)__va(pa);
-			printk("Kernel VA for NIP %x ", pa);
-			print_8xx_pte(current->mm,pa);
-		}
-	}
-
-	if (retval == 0)
-		regs->nip += 4;
-
-	return retval;
-}
diff --git a/arch/powerpc/kernel/swsusp_asm64.S b/arch/powerpc/kernel/swsusp_asm64.S
index 86ac1d90d02b..22045984835f 100644
--- a/arch/powerpc/kernel/swsusp_asm64.S
+++ b/arch/powerpc/kernel/swsusp_asm64.S
@@ -46,10 +46,19 @@
 #define SL_r29		0xe8
 #define SL_r30		0xf0
 #define SL_r31		0xf8
-#define SL_SIZE		SL_r31+8
+#define SL_SPRG1	0x100
+#define SL_TCR		0x108
+#define SL_SIZE		SL_TCR+8
 
 /* these macros rely on the save area being
  * pointed to by r11 */
+
+#define SAVE_SPR(register)		\
+	mfspr	r0, SPRN_##register	;\
+	std	r0, SL_##register(r11)
+#define RESTORE_SPR(register)		\
+	ld	r0, SL_##register(r11)	;\
+	mtspr	SPRN_##register, r0
 #define SAVE_SPECIAL(special)		\
 	mf##special	r0		;\
 	std	r0, SL_##special(r11)
@@ -103,8 +112,15 @@ _GLOBAL(swsusp_arch_suspend)
 	SAVE_REGISTER(r30)
 	SAVE_REGISTER(r31)
 	SAVE_SPECIAL(MSR)
-	SAVE_SPECIAL(SDR1)
 	SAVE_SPECIAL(XER)
+#ifdef CONFIG_PPC_BOOK3S_64
+	SAVE_SPECIAL(SDR1)
+#else
+	SAVE_SPR(TCR)
+
+	/* Save SPRG1, SPRG1 be used save paca */
+	SAVE_SPR(SPRG1)
+#endif
 
 	/* we push the stack up 128 bytes but don't store the
 	 * stack pointer on the stack like a real stackframe */
@@ -151,6 +167,7 @@ copy_page_loop:
 	bne+	copyloop
 nothing_to_copy:
 
+#ifdef CONFIG_PPC_BOOK3S_64
 	/* flush caches */
 	lis	r3, 0x10
 	mtctr	r3
@@ -167,6 +184,7 @@ nothing_to_copy:
 	sync
 
 	tlbia
+#endif
 
 	ld	r11,swsusp_save_area_ptr@toc(r2)
 
@@ -208,16 +226,39 @@ nothing_to_copy:
 	RESTORE_REGISTER(r29)
 	RESTORE_REGISTER(r30)
 	RESTORE_REGISTER(r31)
+
+#ifdef CONFIG_PPC_BOOK3S_64
 	/* can't use RESTORE_SPECIAL(MSR) */
 	ld	r0, SL_MSR(r11)
 	mtmsrd	r0, 0
 	RESTORE_SPECIAL(SDR1)
+#else
+	/* Restore SPRG1, be used to save paca */
+	ld	r0, SL_SPRG1(r11)
+	mtsprg	1, r0
+
+	RESTORE_SPECIAL(MSR)
+
+	/* Restore TCR and clear any pending bits in TSR. */
+	RESTORE_SPR(TCR)
+	lis	r0, (TSR_ENW | TSR_WIS | TSR_DIS | TSR_FIS)@h
+	mtspr	SPRN_TSR, r0
+
+	/* Kick decrementer */
+	li	r0, 1
+	mtdec	r0
+
+	/* Invalidate all tlbs */
+	bl	_tlbil_all
+#endif
 	RESTORE_SPECIAL(XER)
 
 	sync
 
 	addi	r1,r1,-128
+#ifdef CONFIG_PPC_BOOK3S_64
 	bl	slb_flush_and_rebolt
+#endif
 	bl	do_after_copyback
 	addi	r1,r1,128
 
diff --git a/arch/powerpc/kernel/swsusp_booke.S b/arch/powerpc/kernel/swsusp_booke.S
index 11a39307dd71..0f204053e5b5 100644
--- a/arch/powerpc/kernel/swsusp_booke.S
+++ b/arch/powerpc/kernel/swsusp_booke.S
@@ -141,6 +141,14 @@ _GLOBAL(swsusp_arch_resume)
 	lis	r11,swsusp_save_area@h
 	ori	r11,r11,swsusp_save_area@l
 
+	/*
+	 * Mappings from virtual addresses to physical addresses may be
+	 * different than they were prior to restoring hibernation state. 
+	 * Invalidate the TLB so that the boot CPU is using the new
+	 * mappings.
+	 */
+	bl	_tlbil_all
+
 	lwz	r4,SL_SPRG0(r11)
 	mtsprg	0,r4
 	lwz	r4,SL_SPRG1(r11)
diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c
index 27a90b99ef67..b4e667663d9b 100644
--- a/arch/powerpc/kernel/sysfs.c
+++ b/arch/powerpc/kernel/sysfs.c
@@ -17,6 +17,7 @@
 #include <asm/machdep.h>
 #include <asm/smp.h>
 #include <asm/pmc.h>
+#include <asm/firmware.h>
 
 #include "cacheinfo.h"
 
@@ -179,15 +180,25 @@ SYSFS_PMCSETUP(spurr, SPRN_SPURR);
 SYSFS_PMCSETUP(dscr, SPRN_DSCR);
 SYSFS_PMCSETUP(pir, SPRN_PIR);
 
+/*
+  Lets only enable read for phyp resources and
+  enable write when needed with a separate function.
+  Lets be conservative and default to pseries.
+*/
 static DEVICE_ATTR(mmcra, 0600, show_mmcra, store_mmcra);
 static DEVICE_ATTR(spurr, 0400, show_spurr, NULL);
 static DEVICE_ATTR(dscr, 0600, show_dscr, store_dscr);
-static DEVICE_ATTR(purr, 0600, show_purr, store_purr);
+static DEVICE_ATTR(purr, 0400, show_purr, store_purr);
 static DEVICE_ATTR(pir, 0400, show_pir, NULL);
 
 unsigned long dscr_default = 0;
 EXPORT_SYMBOL(dscr_default);
 
+static void add_write_permission_dev_attr(struct device_attribute *attr)
+{
+	attr->attr.mode |= 0200;
+}
+
 static ssize_t show_dscr_default(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
@@ -394,8 +405,11 @@ static void register_cpu_online(unsigned int cpu)
 	if (cpu_has_feature(CPU_FTR_MMCRA))
 		device_create_file(s, &dev_attr_mmcra);
 
-	if (cpu_has_feature(CPU_FTR_PURR))
+	if (cpu_has_feature(CPU_FTR_PURR)) {
+		if (!firmware_has_feature(FW_FEATURE_LPAR))
+			add_write_permission_dev_attr(&dev_attr_purr);
 		device_create_file(s, &dev_attr_purr);
+	}
 
 	if (cpu_has_feature(CPU_FTR_SPURR))
 		device_create_file(s, &dev_attr_spurr);
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 65ab9e909377..192b051df97e 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -210,18 +210,18 @@ static u64 scan_dispatch_log(u64 stop_tb)
 	if (!dtl)
 		return 0;
 
-	if (i == vpa->dtl_idx)
+	if (i == be64_to_cpu(vpa->dtl_idx))
 		return 0;
-	while (i < vpa->dtl_idx) {
+	while (i < be64_to_cpu(vpa->dtl_idx)) {
 		if (dtl_consumer)
 			dtl_consumer(dtl, i);
-		dtb = dtl->timebase;
-		tb_delta = dtl->enqueue_to_dispatch_time +
-			dtl->ready_to_enqueue_time;
+		dtb = be64_to_cpu(dtl->timebase);
+		tb_delta = be32_to_cpu(dtl->enqueue_to_dispatch_time) +
+			be32_to_cpu(dtl->ready_to_enqueue_time);
 		barrier();
-		if (i + N_DISPATCH_LOG < vpa->dtl_idx) {
+		if (i + N_DISPATCH_LOG < be64_to_cpu(vpa->dtl_idx)) {
 			/* buffer has overflowed */
-			i = vpa->dtl_idx - N_DISPATCH_LOG;
+			i = be64_to_cpu(vpa->dtl_idx) - N_DISPATCH_LOG;
 			dtl = local_paca->dispatch_log + (i % N_DISPATCH_LOG);
 			continue;
 		}
@@ -269,7 +269,7 @@ static inline u64 calculate_stolen_time(u64 stop_tb)
 {
 	u64 stolen = 0;
 
-	if (get_paca()->dtl_ridx != get_paca()->lppaca_ptr->dtl_idx) {
+	if (get_paca()->dtl_ridx != be64_to_cpu(get_lppaca()->dtl_idx)) {
 		stolen = scan_dispatch_log(stop_tb);
 		get_paca()->system_time -= stolen;
 	}
@@ -612,7 +612,7 @@ unsigned long long sched_clock(void)
 static int __init get_freq(char *name, int cells, unsigned long *val)
 {
 	struct device_node *cpu;
-	const unsigned int *fp;
+	const __be32 *fp;
 	int found = 0;
 
 	/* The cpu node should have timebase and clock frequency properties */
@@ -1049,7 +1049,7 @@ static int __init rtc_init(void)
 
 	pdev = platform_device_register_simple("rtc-generic", -1, NULL, 0);
 
-	return PTR_RET(pdev);
+	return PTR_ERR_OR_ZERO(pdev);
 }
 
 module_init(rtc_init);
diff --git a/arch/powerpc/kernel/tm.S b/arch/powerpc/kernel/tm.S
index 0554d1f6d70d..cd809eaa8b5c 100644
--- a/arch/powerpc/kernel/tm.S
+++ b/arch/powerpc/kernel/tm.S
@@ -79,6 +79,11 @@ _GLOBAL(tm_abort)
 	TABORT(R3)
 	blr
 
+	.section	".toc","aw"
+DSCR_DEFAULT:
+	.tc dscr_default[TC],dscr_default
+
+	.section	".text"
 
 /* void tm_reclaim(struct thread_struct *thread,
  *                 unsigned long orig_msr,
@@ -123,6 +128,7 @@ _GLOBAL(tm_reclaim)
 	mr	r15, r14
 	ori	r15, r15, MSR_FP
 	li	r16, MSR_RI
+	ori	r16, r16, MSR_EE /* IRQs hard off */
 	andc	r15, r15, r16
 	oris	r15, r15, MSR_VEC@h
 #ifdef CONFIG_VSX
@@ -155,10 +161,10 @@ _GLOBAL(tm_reclaim)
 	mfvscr	vr0
 	li	r6, THREAD_TRANSACT_VSCR
 	stvx	vr0, r3, r6
+dont_backup_vec:
 	mfspr	r0, SPRN_VRSAVE
 	std	r0, THREAD_TRANSACT_VRSAVE(r3)
 
-dont_backup_vec:
 	andi.	r0, r4, MSR_FP
 	beq	dont_backup_fp
 
@@ -187,11 +193,18 @@ dont_backup_fp:
 	std	r1, PACATMSCRATCH(r13)
 	ld	r1, PACAR1(r13)
 
+	/* Store the PPR in r11 and reset to decent value */
+	std	r11, GPR11(r1)			/* Temporary stash */
+	mfspr	r11, SPRN_PPR
+	HMT_MEDIUM
+
 	/* Now get some more GPRS free */
 	std	r7, GPR7(r1)			/* Temporary stash */
 	std	r12, GPR12(r1)			/* ''   ''    ''   */
 	ld	r12, STACK_PARAM(0)(r1)		/* Param 0, thread_struct * */
 
+	std	r11, THREAD_TM_PPR(r12)		/* Store PPR and free r11 */
+
 	addi	r7, r12, PT_CKPT_REGS		/* Thread's ckpt_regs */
 
 	/* Make r7 look like an exception frame so that we
@@ -203,15 +216,19 @@ dont_backup_fp:
 	SAVE_GPR(0, r7)				/* user r0 */
 	SAVE_GPR(2, r7)			/* user r2 */
 	SAVE_4GPRS(3, r7)			/* user r3-r6 */
-	SAVE_4GPRS(8, r7)			/* user r8-r11 */
+	SAVE_GPR(8, r7)				/* user r8 */
+	SAVE_GPR(9, r7)				/* user r9 */
+	SAVE_GPR(10, r7)			/* user r10 */
 	ld	r3, PACATMSCRATCH(r13)		/* user r1 */
 	ld	r4, GPR7(r1)			/* user r7 */
-	ld	r5, GPR12(r1)			/* user r12 */
-	GET_SCRATCH0(6)				/* user r13 */
+	ld	r5, GPR11(r1)			/* user r11 */
+	ld	r6, GPR12(r1)			/* user r12 */
+	GET_SCRATCH0(8)				/* user r13 */
 	std	r3, GPR1(r7)
 	std	r4, GPR7(r7)
-	std	r5, GPR12(r7)
-	std	r6, GPR13(r7)
+	std	r5, GPR11(r7)
+	std	r6, GPR12(r7)
+	std	r8, GPR13(r7)
 
 	SAVE_NVGPRS(r7)				/* user r14-r31 */
 
@@ -234,14 +251,12 @@ dont_backup_fp:
 	std	r6, _XER(r7)
 
 
-	/* ******************** TAR, PPR, DSCR ********** */
+	/* ******************** TAR, DSCR ********** */
 	mfspr	r3, SPRN_TAR
-	mfspr	r4, SPRN_PPR
-	mfspr	r5, SPRN_DSCR
+	mfspr	r4, SPRN_DSCR
 
 	std	r3, THREAD_TM_TAR(r12)
-	std	r4, THREAD_TM_PPR(r12)
-	std	r5, THREAD_TM_DSCR(r12)
+	std	r4, THREAD_TM_DSCR(r12)
 
 	/* MSR and flags:  We don't change CRs, and we don't need to alter
 	 * MSR.
@@ -258,7 +273,7 @@ dont_backup_fp:
 	std	r3, THREAD_TM_TFHAR(r12)
 	std	r4, THREAD_TM_TFIAR(r12)
 
-	/* AMR and PPR are checkpointed too, but are unsupported by Linux. */
+	/* AMR is checkpointed too, but is unsupported by Linux. */
 
 	/* Restore original MSR/IRQ state & clear TM mode */
 	ld	r14, TM_FRAME_L0(r1)		/* Orig MSR */
@@ -274,6 +289,12 @@ dont_backup_fp:
 	mtcr	r4
 	mtlr	r0
 	ld	r2, 40(r1)
+
+	/* Load system default DSCR */
+	ld	r4, DSCR_DEFAULT@toc(r2)
+	ld	r0, 0(r4)
+	mtspr	SPRN_DSCR, r0
+
 	blr
 
 
@@ -341,11 +362,11 @@ _GLOBAL(tm_recheckpoint)
 	lvx	vr0, r3, r5
 	mtvscr	vr0
 	REST_32VRS(0, r5, r3)			/* r5 scratch, r3 THREAD ptr */
+dont_restore_vec:
 	ld	r5, THREAD_VRSAVE(r3)
 	mtspr	SPRN_VRSAVE, r5
 #endif
 
-dont_restore_vec:
 	andi.	r0, r4, MSR_FP
 	beq	dont_restore_fp
 
@@ -358,25 +379,24 @@ dont_restore_fp:
 
 restore_gprs:
 
-	/* ******************** TAR, PPR, DSCR ********** */
-	ld	r4, THREAD_TM_TAR(r3)
-	ld	r5, THREAD_TM_PPR(r3)
-	ld	r6, THREAD_TM_DSCR(r3)
+	/* ******************** CR,LR,CCR,MSR ********** */
+	ld	r4, _CTR(r7)
+	ld	r5, _LINK(r7)
+	ld	r6, _CCR(r7)
+	ld	r8, _XER(r7)
 
-	mtspr	SPRN_TAR,	r4
-	mtspr	SPRN_PPR,	r5
-	mtspr	SPRN_DSCR,	r6
+	mtctr	r4
+	mtlr	r5
+	mtcr	r6
+	mtxer	r8
 
-	/* ******************** CR,LR,CCR,MSR ********** */
-	ld	r3, _CTR(r7)
-	ld	r4, _LINK(r7)
-	ld	r5, _CCR(r7)
-	ld	r6, _XER(r7)
+	/* ******************** TAR ******************** */
+	ld	r4, THREAD_TM_TAR(r3)
+	mtspr	SPRN_TAR,	r4
 
-	mtctr	r3
-	mtlr	r4
-	mtcr	r5
-	mtxer	r6
+	/* Load up the PPR and DSCR in GPRs only at this stage */
+	ld	r5, THREAD_TM_DSCR(r3)
+	ld	r6, THREAD_TM_PPR(r3)
 
 	/* Clear the MSR RI since we are about to change R1.  EE is already off
 	 */
@@ -384,19 +404,26 @@ restore_gprs:
 	mtmsrd	r4, 1
 
 	REST_4GPRS(0, r7)			/* GPR0-3 */
-	REST_GPR(4, r7)				/* GPR4-6 */
-	REST_GPR(5, r7)
-	REST_GPR(6, r7)
+	REST_GPR(4, r7)				/* GPR4 */
 	REST_4GPRS(8, r7)			/* GPR8-11 */
 	REST_2GPRS(12, r7)			/* GPR12-13 */
 
 	REST_NVGPRS(r7)				/* GPR14-31 */
 
-	ld	r7, GPR7(r7)			/* GPR7 */
+	/* Load up PPR and DSCR here so we don't run with user values for long
+	 */
+	mtspr	SPRN_DSCR, r5
+	mtspr	SPRN_PPR, r6
+
+	REST_GPR(5, r7)				/* GPR5-7 */
+	REST_GPR(6, r7)
+	ld	r7, GPR7(r7)
 
 	/* Commit register state as checkpointed state: */
 	TRECHKPT
 
+	HMT_MEDIUM
+
 	/* Our transactional state has now changed.
 	 *
 	 * Now just get out of here.  Transactional (current) state will be
@@ -419,6 +446,12 @@ restore_gprs:
 	mtcr	r4
 	mtlr	r0
 	ld	r2, 40(r1)
+
+	/* Load system default DSCR */
+	ld	r4, DSCR_DEFAULT@toc(r2)
+	ld	r0, 0(r4)
+	mtspr	SPRN_DSCR, r0
+
 	blr
 
 	/* ****************************************************************** */
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index e435bc089ea3..f783c932faeb 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -60,6 +60,7 @@
 #include <asm/switch_to.h>
 #include <asm/tm.h>
 #include <asm/debug.h>
+#include <sysdev/fsl_pci.h>
 
 #if defined(CONFIG_DEBUGGER) || defined(CONFIG_KEXEC)
 int (*__debugger)(struct pt_regs *regs) __read_mostly;
@@ -565,6 +566,8 @@ int machine_check_e500(struct pt_regs *regs)
 	if (reason & MCSR_BUS_RBERR) {
 		if (fsl_rio_mcheck_exception(regs))
 			return 1;
+		if (fsl_pci_mcheck_exception(regs))
+			return 1;
 	}
 
 	printk("Machine check in kernel mode.\n");
@@ -962,7 +965,7 @@ static int emulate_instruction(struct pt_regs *regs)
 	u32 instword;
 	u32 rd;
 
-	if (!user_mode(regs) || (regs->msr & MSR_LE))
+	if (!user_mode(regs))
 		return -EINVAL;
 	CHECK_FULL_REGS(regs);
 
@@ -1050,11 +1053,41 @@ int is_valid_bugaddr(unsigned long addr)
 	return is_kernel_addr(addr);
 }
 
+#ifdef CONFIG_MATH_EMULATION
+static int emulate_math(struct pt_regs *regs)
+{
+	int ret;
+	extern int do_mathemu(struct pt_regs *regs);
+
+	ret = do_mathemu(regs);
+	if (ret >= 0)
+		PPC_WARN_EMULATED(math, regs);
+
+	switch (ret) {
+	case 0:
+		emulate_single_step(regs);
+		return 0;
+	case 1: {
+			int code = 0;
+			code = __parse_fpscr(current->thread.fpscr.val);
+			_exception(SIGFPE, regs, code, regs->nip);
+			return 0;
+		}
+	case -EFAULT:
+		_exception(SIGSEGV, regs, SEGV_MAPERR, regs->nip);
+		return 0;
+	}
+
+	return -1;
+}
+#else
+static inline int emulate_math(struct pt_regs *regs) { return -1; }
+#endif
+
 void __kprobes program_check_exception(struct pt_regs *regs)
 {
 	enum ctx_state prev_state = exception_enter();
 	unsigned int reason = get_reason(regs);
-	extern int do_mathemu(struct pt_regs *regs);
 
 	/* We can now get here via a FP Unavailable exception if the core
 	 * has no FPU, in that case the reason flags will be 0 */
@@ -1116,11 +1149,20 @@ void __kprobes program_check_exception(struct pt_regs *regs)
 	}
 #endif
 
+	/*
+	 * If we took the program check in the kernel skip down to sending a
+	 * SIGILL. The subsequent cases all relate to emulating instructions
+	 * which we should only do for userspace. We also do not want to enable
+	 * interrupts for kernel faults because that might lead to further
+	 * faults, and loose the context of the original exception.
+	 */
+	if (!user_mode(regs))
+		goto sigill;
+
 	/* We restore the interrupt state now */
 	if (!arch_irq_disabled_regs(regs))
 		local_irq_enable();
 
-#ifdef CONFIG_MATH_EMULATION
 	/* (reason & REASON_ILLEGAL) would be the obvious thing here,
 	 * but there seems to be a hardware bug on the 405GP (RevD)
 	 * that means ESR is sometimes set incorrectly - either to
@@ -1129,31 +1171,8 @@ void __kprobes program_check_exception(struct pt_regs *regs)
 	 * instruction or only on FP instructions, whether there is a
 	 * pattern to occurrences etc. -dgibson 31/Mar/2003
 	 */
-
-	/*
-	 * If we support a HW FPU, we need to ensure the FP state
-	 * if flushed into the thread_struct before attempting
-	 * emulation
-	 */
-#ifdef CONFIG_PPC_FPU
-	flush_fp_to_thread(current);
-#endif
-	switch (do_mathemu(regs)) {
-	case 0:
-		emulate_single_step(regs);
-		goto bail;
-	case 1: {
-			int code = 0;
-			code = __parse_fpscr(current->thread.fpscr.val);
-			_exception(SIGFPE, regs, code, regs->nip);
-			goto bail;
-		}
-	case -EFAULT:
-		_exception(SIGSEGV, regs, SEGV_MAPERR, regs->nip);
+	if (!emulate_math(regs))
 		goto bail;
-	}
-	/* fall through on any other errors */
-#endif /* CONFIG_MATH_EMULATION */
 
 	/* Try to emulate it if we should. */
 	if (reason & (REASON_ILLEGAL | REASON_PRIVILEGED)) {
@@ -1168,6 +1187,7 @@ void __kprobes program_check_exception(struct pt_regs *regs)
 		}
 	}
 
+sigill:
 	if (reason & REASON_PRIVILEGED)
 		_exception(SIGILL, regs, ILL_PRVOPC, regs->nip);
 	else
@@ -1322,13 +1342,10 @@ void facility_unavailable_exception(struct pt_regs *regs)
 	if (status == FSCR_DSCR_LG) {
 		/* User is acessing the DSCR.  Set the inherit bit and allow
 		 * the user to set it directly in future by setting via the
-		 * H/FSCR DSCR bit.
+		 * FSCR DSCR bit.  We always leave HFSCR DSCR set.
 		 */
 		current->thread.dscr_inherit = 1;
-		if (hv)
-			mtspr(SPRN_HFSCR, value | HFSCR_DSCR);
-		else
-			mtspr(SPRN_FSCR,  value | FSCR_DSCR);
+		mtspr(SPRN_FSCR, value | FSCR_DSCR);
 		return;
 	}
 
@@ -1444,11 +1461,6 @@ void performance_monitor_exception(struct pt_regs *regs)
 #ifdef CONFIG_8xx
 void SoftwareEmulation(struct pt_regs *regs)
 {
-	extern int do_mathemu(struct pt_regs *);
-#if defined(CONFIG_MATH_EMULATION)
-	int errcode;
-#endif
-
 	CHECK_FULL_REGS(regs);
 
 	if (!user_mode(regs)) {
@@ -1456,31 +1468,10 @@ void SoftwareEmulation(struct pt_regs *regs)
 		die("Kernel Mode Software FPU Emulation", regs, SIGFPE);
 	}
 
-#ifdef CONFIG_MATH_EMULATION
-	errcode = do_mathemu(regs);
-	if (errcode >= 0)
-		PPC_WARN_EMULATED(math, regs);
-
-	switch (errcode) {
-	case 0:
-		emulate_single_step(regs);
+	if (!emulate_math(regs))
 		return;
-	case 1: {
-			int code = 0;
-			code = __parse_fpscr(current->thread.fpscr.val);
-			_exception(SIGFPE, regs, code, regs->nip);
-			return;
-		}
-	case -EFAULT:
-		_exception(SIGSEGV, regs, SEGV_MAPERR, regs->nip);
-		return;
-	default:
-		_exception(SIGILL, regs, ILL_ILLOPC, regs->nip);
-		return;
-	}
-#else
+
 	_exception(SIGILL, regs, ILL_ILLOPC, regs->nip);
-#endif
 }
 #endif /* CONFIG_8xx */
 
diff --git a/arch/powerpc/kernel/udbg_16550.c b/arch/powerpc/kernel/udbg_16550.c
index 6837f839ab78..75702e207b29 100644
--- a/arch/powerpc/kernel/udbg_16550.c
+++ b/arch/powerpc/kernel/udbg_16550.c
@@ -18,23 +18,19 @@ extern void real_writeb(u8 data, volatile u8 __iomem *addr);
 extern u8 real_205_readb(volatile u8 __iomem  *addr);
 extern void real_205_writeb(u8 data, volatile u8 __iomem *addr);
 
-struct NS16550 {
-	/* this struct must be packed */
-	unsigned char rbr;  /* 0 */
-	unsigned char ier;  /* 1 */
-	unsigned char fcr;  /* 2 */
-	unsigned char lcr;  /* 3 */
-	unsigned char mcr;  /* 4 */
-	unsigned char lsr;  /* 5 */
-	unsigned char msr;  /* 6 */
-	unsigned char scr;  /* 7 */
-};
-
-#define thr rbr
-#define iir fcr
-#define dll rbr
-#define dlm ier
-#define dlab lcr
+#define UART_RBR	0
+#define UART_IER	1
+#define UART_FCR	2
+#define UART_LCR	3
+#define UART_MCR	4
+#define UART_LSR	5
+#define UART_MSR	6
+#define UART_SCR	7
+#define UART_THR	UART_RBR
+#define UART_IIR	UART_FCR
+#define UART_DLL	UART_RBR
+#define UART_DLM	UART_IER
+#define UART_DLAB	UART_LCR
 
 #define LSR_DR   0x01  /* Data ready */
 #define LSR_OE   0x02  /* Overrun */
@@ -47,52 +43,62 @@ struct NS16550 {
 
 #define LCR_DLAB 0x80
 
-static struct NS16550 __iomem *udbg_comport;
+static u8 (*udbg_uart_in)(unsigned int reg);
+static void (*udbg_uart_out)(unsigned int reg, u8 data);
 
-static void udbg_550_flush(void)
+static void udbg_uart_flush(void)
 {
-	if (udbg_comport) {
-		while ((in_8(&udbg_comport->lsr) & LSR_THRE) == 0)
-			/* wait for idle */;
-	}
+	if (!udbg_uart_in)
+		return;
+
+	/* wait for idle */
+	while ((udbg_uart_in(UART_LSR) & LSR_THRE) == 0)
+		cpu_relax();
 }
 
-static void udbg_550_putc(char c)
+static void udbg_uart_putc(char c)
 {
-	if (udbg_comport) {
-		if (c == '\n')
-			udbg_550_putc('\r');
-		udbg_550_flush();
-		out_8(&udbg_comport->thr, c);
-	}
+	if (!udbg_uart_out)
+		return;
+
+	if (c == '\n')
+		udbg_uart_putc('\r');
+	udbg_uart_flush();
+	udbg_uart_out(UART_THR, c);
 }
 
-static int udbg_550_getc_poll(void)
+static int udbg_uart_getc_poll(void)
 {
-	if (udbg_comport) {
-		if ((in_8(&udbg_comport->lsr) & LSR_DR) != 0)
-			return in_8(&udbg_comport->rbr);
-		else
-			return -1;
-	}
+	if (!udbg_uart_in || !(udbg_uart_in(UART_LSR) & LSR_DR))
+		return udbg_uart_in(UART_RBR);
 	return -1;
 }
 
-static int udbg_550_getc(void)
+static int udbg_uart_getc(void)
 {
-	if (udbg_comport) {
-		while ((in_8(&udbg_comport->lsr) & LSR_DR) == 0)
-			/* wait for char */;
-		return in_8(&udbg_comport->rbr);
-	}
-	return -1;
+	if (!udbg_uart_in)
+		return -1;
+	/* wait for char */
+	while (!(udbg_uart_in(UART_LSR) & LSR_DR))
+		cpu_relax();
+	return udbg_uart_in(UART_RBR);
+}
+
+static void udbg_use_uart(void)
+{
+	udbg_putc = udbg_uart_putc;
+	udbg_flush = udbg_uart_flush;
+	udbg_getc = udbg_uart_getc;
+	udbg_getc_poll = udbg_uart_getc_poll;
 }
 
-void udbg_init_uart(void __iomem *comport, unsigned int speed,
-		    unsigned int clock)
+void udbg_uart_setup(unsigned int speed, unsigned int clock)
 {
 	unsigned int dll, base_bauds;
 
+	if (!udbg_uart_out)
+		return;
+
 	if (clock == 0)
 		clock = 1843200;
 	if (speed == 0)
@@ -101,51 +107,43 @@ void udbg_init_uart(void __iomem *comport, unsigned int speed,
 	base_bauds = clock / 16;
 	dll = base_bauds / speed;
 
-	if (comport) {
-		udbg_comport = (struct NS16550 __iomem *)comport;
-		out_8(&udbg_comport->lcr, 0x00);
-		out_8(&udbg_comport->ier, 0xff);
-		out_8(&udbg_comport->ier, 0x00);
-		out_8(&udbg_comport->lcr, LCR_DLAB);
-		out_8(&udbg_comport->dll, dll & 0xff);
-		out_8(&udbg_comport->dlm, dll >> 8);
-		/* 8 data, 1 stop, no parity */
-		out_8(&udbg_comport->lcr, 0x03);
-		/* RTS/DTR */
-		out_8(&udbg_comport->mcr, 0x03);
-		/* Clear & enable FIFOs */
-		out_8(&udbg_comport->fcr ,0x07);
-		udbg_putc = udbg_550_putc;
-		udbg_flush = udbg_550_flush;
-		udbg_getc = udbg_550_getc;
-		udbg_getc_poll = udbg_550_getc_poll;
-	}
+	udbg_uart_out(UART_LCR, 0x00);
+	udbg_uart_out(UART_IER, 0xff);
+	udbg_uart_out(UART_IER, 0x00);
+	udbg_uart_out(UART_LCR, LCR_DLAB);
+	udbg_uart_out(UART_DLL, dll & 0xff);
+	udbg_uart_out(UART_DLM, dll >> 8);
+	/* 8 data, 1 stop, no parity */
+	udbg_uart_out(UART_LCR, 0x3);
+	/* RTS/DTR */
+	udbg_uart_out(UART_MCR, 0x3);
+	/* Clear & enable FIFOs */
+	udbg_uart_out(UART_FCR, 0x7);
 }
 
-unsigned int udbg_probe_uart_speed(void __iomem *comport, unsigned int clock)
+unsigned int udbg_probe_uart_speed(unsigned int clock)
 {
 	unsigned int dll, dlm, divisor, prescaler, speed;
 	u8 old_lcr;
-	struct NS16550 __iomem *port = comport;
 
-	old_lcr = in_8(&port->lcr);
+	old_lcr = udbg_uart_in(UART_LCR);
 
 	/* select divisor latch registers.  */
-	out_8(&port->lcr, LCR_DLAB);
+	udbg_uart_out(UART_LCR, old_lcr | LCR_DLAB);
 
 	/* now, read the divisor */
-	dll = in_8(&port->dll);
-	dlm = in_8(&port->dlm);
+	dll = udbg_uart_in(UART_DLL);
+	dlm = udbg_uart_in(UART_DLM);
 	divisor = dlm << 8 | dll;
 
 	/* check prescaling */
-	if (in_8(&port->mcr) & 0x80)
+	if (udbg_uart_in(UART_MCR) & 0x80)
 		prescaler = 4;
 	else
 		prescaler = 1;
 
 	/* restore the LCR */
-	out_8(&port->lcr, old_lcr);
+	udbg_uart_out(UART_LCR, old_lcr);
 
 	/* calculate speed */
 	speed = (clock / prescaler) / (divisor * 16);
@@ -157,195 +155,155 @@ unsigned int udbg_probe_uart_speed(void __iomem *comport, unsigned int clock)
 	return speed;
 }
 
-#ifdef CONFIG_PPC_MAPLE
-void udbg_maple_real_flush(void)
+static union {
+	unsigned char __iomem *mmio_base;
+	unsigned long pio_base;
+} udbg_uart;
+
+static unsigned int udbg_uart_stride = 1;
+
+static u8 udbg_uart_in_pio(unsigned int reg)
 {
-	if (udbg_comport) {
-		while ((real_readb(&udbg_comport->lsr) & LSR_THRE) == 0)
-			/* wait for idle */;
-	}
+	return inb(udbg_uart.pio_base + (reg * udbg_uart_stride));
 }
 
-void udbg_maple_real_putc(char c)
+static void udbg_uart_out_pio(unsigned int reg, u8 data)
 {
-	if (udbg_comport) {
-		if (c == '\n')
-			udbg_maple_real_putc('\r');
-		udbg_maple_real_flush();
-		real_writeb(c, &udbg_comport->thr); eieio();
-	}
+	outb(data, udbg_uart.pio_base + (reg * udbg_uart_stride));
 }
 
-void __init udbg_init_maple_realmode(void)
+void udbg_uart_init_pio(unsigned long port, unsigned int stride)
 {
-	udbg_comport = (struct NS16550 __iomem *)0xf40003f8;
-
-	udbg_putc = udbg_maple_real_putc;
-	udbg_flush = udbg_maple_real_flush;
-	udbg_getc = NULL;
-	udbg_getc_poll = NULL;
+	if (!port)
+		return;
+	udbg_uart.pio_base = port;
+	udbg_uart_stride = stride;
+	udbg_uart_in = udbg_uart_in_pio;
+	udbg_uart_out = udbg_uart_out_pio;
+	udbg_use_uart();
 }
-#endif /* CONFIG_PPC_MAPLE */
 
-#ifdef CONFIG_PPC_PASEMI
-void udbg_pas_real_flush(void)
+static u8 udbg_uart_in_mmio(unsigned int reg)
 {
-	if (udbg_comport) {
-		while ((real_205_readb(&udbg_comport->lsr) & LSR_THRE) == 0)
-			/* wait for idle */;
-	}
+	return in_8(udbg_uart.mmio_base + (reg * udbg_uart_stride));
 }
 
-void udbg_pas_real_putc(char c)
+static void udbg_uart_out_mmio(unsigned int reg, u8 data)
 {
-	if (udbg_comport) {
-		if (c == '\n')
-			udbg_pas_real_putc('\r');
-		udbg_pas_real_flush();
-		real_205_writeb(c, &udbg_comport->thr); eieio();
-	}
+	out_8(udbg_uart.mmio_base + (reg * udbg_uart_stride), data);
 }
 
-void udbg_init_pas_realmode(void)
-{
-	udbg_comport = (struct NS16550 __iomem *)0xfcff03f8UL;
 
-	udbg_putc = udbg_pas_real_putc;
-	udbg_flush = udbg_pas_real_flush;
-	udbg_getc = NULL;
-	udbg_getc_poll = NULL;
+void udbg_uart_init_mmio(void __iomem *addr, unsigned int stride)
+{
+	if (!addr)
+		return;
+	udbg_uart.mmio_base = addr;
+	udbg_uart_stride = stride;
+	udbg_uart_in = udbg_uart_in_mmio;
+	udbg_uart_out = udbg_uart_out_mmio;
+	udbg_use_uart();
 }
-#endif /* CONFIG_PPC_MAPLE */
 
-#ifdef CONFIG_PPC_EARLY_DEBUG_44x
-#include <platforms/44x/44x.h>
+#ifdef CONFIG_PPC_MAPLE
+
+#define UDBG_UART_MAPLE_ADDR	((void __iomem *)0xf40003f8)
 
-static void udbg_44x_as1_flush(void)
+static u8 udbg_uart_in_maple(unsigned int reg)
 {
-	if (udbg_comport) {
-		while ((as1_readb(&udbg_comport->lsr) & LSR_THRE) == 0)
-			/* wait for idle */;
-	}
+	return real_readb(UDBG_UART_MAPLE_ADDR + reg);
 }
 
-static void udbg_44x_as1_putc(char c)
+static void udbg_uart_out_maple(unsigned int reg, u8 val)
 {
-	if (udbg_comport) {
-		if (c == '\n')
-			udbg_44x_as1_putc('\r');
-		udbg_44x_as1_flush();
-		as1_writeb(c, &udbg_comport->thr); eieio();
-	}
+	real_writeb(val, UDBG_UART_MAPLE_ADDR + reg);
 }
 
-static int udbg_44x_as1_getc(void)
+void __init udbg_init_maple_realmode(void)
 {
-	if (udbg_comport) {
-		while ((as1_readb(&udbg_comport->lsr) & LSR_DR) == 0)
-			; /* wait for char */
-		return as1_readb(&udbg_comport->rbr);
-	}
-	return -1;
+	udbg_uart_in = udbg_uart_in_maple;
+	udbg_uart_out = udbg_uart_out_maple;
+	udbg_use_uart();
 }
 
-void __init udbg_init_44x_as1(void)
-{
-	udbg_comport =
-		(struct NS16550 __iomem *)PPC44x_EARLY_DEBUG_VIRTADDR;
+#endif /* CONFIG_PPC_MAPLE */
 
-	udbg_putc = udbg_44x_as1_putc;
-	udbg_flush = udbg_44x_as1_flush;
-	udbg_getc = udbg_44x_as1_getc;
-}
-#endif /* CONFIG_PPC_EARLY_DEBUG_44x */
+#ifdef CONFIG_PPC_PASEMI
 
-#ifdef CONFIG_PPC_EARLY_DEBUG_40x
-static void udbg_40x_real_flush(void)
+#define UDBG_UART_PAS_ADDR	((void __iomem *)0xfcff03f8UL)
+
+static u8 udbg_uart_in_pas(unsigned int reg)
 {
-	if (udbg_comport) {
-		while ((real_readb(&udbg_comport->lsr) & LSR_THRE) == 0)
-			/* wait for idle */;
-	}
+	return real_205_readb(UDBG_UART_PAS_ADDR + reg);
 }
 
-static void udbg_40x_real_putc(char c)
+static void udbg_uart_out_pas(unsigned int reg, u8 val)
 {
-	if (udbg_comport) {
-		if (c == '\n')
-			udbg_40x_real_putc('\r');
-		udbg_40x_real_flush();
-		real_writeb(c, &udbg_comport->thr); eieio();
-	}
+	real_205_writeb(val, UDBG_UART_PAS_ADDR + reg);
 }
 
-static int udbg_40x_real_getc(void)
+void __init udbg_init_pas_realmode(void)
 {
-	if (udbg_comport) {
-		while ((real_readb(&udbg_comport->lsr) & LSR_DR) == 0)
-			; /* wait for char */
-		return real_readb(&udbg_comport->rbr);
-	}
-	return -1;
+	udbg_uart_in = udbg_uart_in_pas;
+	udbg_uart_out = udbg_uart_out_pas;
+	udbg_use_uart();
 }
 
-void __init udbg_init_40x_realmode(void)
-{
-	udbg_comport = (struct NS16550 __iomem *)
-		CONFIG_PPC_EARLY_DEBUG_40x_PHYSADDR;
+#endif /* CONFIG_PPC_PASEMI */
+
+#ifdef CONFIG_PPC_EARLY_DEBUG_44x
 
-	udbg_putc = udbg_40x_real_putc;
-	udbg_flush = udbg_40x_real_flush;
-	udbg_getc = udbg_40x_real_getc;
-	udbg_getc_poll = NULL;
+#include <platforms/44x/44x.h>
+
+static u8 udbg_uart_in_44x_as1(unsigned int reg)
+{
+	return as1_readb((void __iomem *)PPC44x_EARLY_DEBUG_VIRTADDR + reg);
 }
-#endif /* CONFIG_PPC_EARLY_DEBUG_40x */
 
-#ifdef CONFIG_PPC_EARLY_DEBUG_WSP
-static void udbg_wsp_flush(void)
+static void udbg_uart_out_44x_as1(unsigned int reg, u8 val)
 {
-	if (udbg_comport) {
-		while ((readb(&udbg_comport->lsr) & LSR_THRE) == 0)
-			/* wait for idle */;
-	}
+	as1_writeb(val, (void __iomem *)PPC44x_EARLY_DEBUG_VIRTADDR + reg);
 }
 
-static void udbg_wsp_putc(char c)
+void __init udbg_init_44x_as1(void)
 {
-	if (udbg_comport) {
-		if (c == '\n')
-			udbg_wsp_putc('\r');
-		udbg_wsp_flush();
-		writeb(c, &udbg_comport->thr); eieio();
-	}
+	udbg_uart_in = udbg_uart_in_44x_as1;
+	udbg_uart_out = udbg_uart_out_44x_as1;
+	udbg_use_uart();
 }
 
-static int udbg_wsp_getc(void)
+#endif /* CONFIG_PPC_EARLY_DEBUG_44x */
+
+#ifdef CONFIG_PPC_EARLY_DEBUG_40x
+
+static u8 udbg_uart_in_40x(unsigned int reg)
 {
-	if (udbg_comport) {
-		while ((readb(&udbg_comport->lsr) & LSR_DR) == 0)
-			; /* wait for char */
-		return readb(&udbg_comport->rbr);
-	}
-	return -1;
+	return real_readb((void __iomem *)CONFIG_PPC_EARLY_DEBUG_40x_PHYSADDR
+			  + reg);
 }
 
-static int udbg_wsp_getc_poll(void)
+static void udbg_uart_out_40x(unsigned int reg, u8 val)
 {
-	if (udbg_comport)
-		if (readb(&udbg_comport->lsr) & LSR_DR)
-			return readb(&udbg_comport->rbr);
-	return -1;
+	real_writeb(val, (void __iomem *)CONFIG_PPC_EARLY_DEBUG_40x_PHYSADDR
+		    + reg);
 }
 
-void __init udbg_init_wsp(void)
+void __init udbg_init_40x_realmode(void)
 {
-	udbg_comport = (struct NS16550 __iomem *)WSP_UART_VIRT;
+	udbg_uart_in = udbg_uart_in_40x;
+	udbg_uart_out = udbg_uart_out_40x;
+	udbg_use_uart();
+}
 
-	udbg_init_uart(udbg_comport, 57600, 50000000);
+#endif /* CONFIG_PPC_EARLY_DEBUG_40x */
+
+
+#ifdef CONFIG_PPC_EARLY_DEBUG_WSP
 
-	udbg_putc = udbg_wsp_putc;
-	udbg_flush = udbg_wsp_flush;
-	udbg_getc = udbg_wsp_getc;
-	udbg_getc_poll = udbg_wsp_getc_poll;
+void __init udbg_init_wsp(void)
+{
+	udbg_uart_init_mmio((void *)WSP_UART_VIRT, 1);
+	udbg_uart_setup(57600, 50000000);
 }
+
 #endif /* CONFIG_PPC_EARLY_DEBUG_WSP */
diff --git a/arch/powerpc/kernel/vdso32/gettimeofday.S b/arch/powerpc/kernel/vdso32/gettimeofday.S
index 27e2f623210b..6b1f2a6d5517 100644
--- a/arch/powerpc/kernel/vdso32/gettimeofday.S
+++ b/arch/powerpc/kernel/vdso32/gettimeofday.S
@@ -232,9 +232,9 @@ __do_get_tspec:
 	lwz	r6,(CFG_TB_ORIG_STAMP+4)(r9)
 
 	/* Get a stable TB value */
-2:	mftbu	r3
-	mftbl	r4
-	mftbu	r0
+2:	mfspr	r3, SPRN_TBRU
+	mfspr	r4, SPRN_TBRL
+	mfspr	r0, SPRN_TBRU
 	cmplw	cr0,r3,r0
 	bne-	2b
 
diff --git a/arch/powerpc/kernel/vio.c b/arch/powerpc/kernel/vio.c
index 536016d792ba..d38cc08b16c7 100644
--- a/arch/powerpc/kernel/vio.c
+++ b/arch/powerpc/kernel/vio.c
@@ -1153,7 +1153,7 @@ EXPORT_SYMBOL(vio_h_cop_sync);
 
 static struct iommu_table *vio_build_iommu_table(struct vio_dev *dev)
 {
-	const unsigned char *dma_window;
+	const __be32 *dma_window;
 	struct iommu_table *tbl;
 	unsigned long offset, size;
 
@@ -1312,8 +1312,7 @@ struct vio_dev *vio_register_device_node(struct device_node *of_node)
 {
 	struct vio_dev *viodev;
 	struct device_node *parent_node;
-	const unsigned int *unit_address;
-	const unsigned int *pfo_resid = NULL;
+	const __be32 *prop;
 	enum vio_dev_family family;
 	const char *of_node_name = of_node->name ? of_node->name : "<unknown>";
 
@@ -1360,6 +1359,8 @@ struct vio_dev *vio_register_device_node(struct device_node *of_node)
 	/* we need the 'device_type' property, in order to match with drivers */
 	viodev->family = family;
 	if (viodev->family == VDEVICE) {
+		unsigned int unit_address;
+
 		if (of_node->type != NULL)
 			viodev->type = of_node->type;
 		else {
@@ -1368,24 +1369,24 @@ struct vio_dev *vio_register_device_node(struct device_node *of_node)
 			goto out;
 		}
 
-		unit_address = of_get_property(of_node, "reg", NULL);
-		if (unit_address == NULL) {
+		prop = of_get_property(of_node, "reg", NULL);
+		if (prop == NULL) {
 			pr_warn("%s: node %s missing 'reg'\n",
 					__func__, of_node_name);
 			goto out;
 		}
-		dev_set_name(&viodev->dev, "%x", *unit_address);
+		unit_address = of_read_number(prop, 1);
+		dev_set_name(&viodev->dev, "%x", unit_address);
 		viodev->irq = irq_of_parse_and_map(of_node, 0);
-		viodev->unit_address = *unit_address;
+		viodev->unit_address = unit_address;
 	} else {
 		/* PFO devices need their resource_id for submitting COP_OPs
 		 * This is an optional field for devices, but is required when
 		 * performing synchronous ops */
-		pfo_resid = of_get_property(of_node, "ibm,resource-id", NULL);
-		if (pfo_resid != NULL)
-			viodev->resource_id = *pfo_resid;
+		prop = of_get_property(of_node, "ibm,resource-id", NULL);
+		if (prop != NULL)
+			viodev->resource_id = of_read_number(prop, 1);
 
-		unit_address = NULL;
 		dev_set_name(&viodev->dev, "%s", of_node_name);
 		viodev->type = of_node_name;
 		viodev->irq = 0;
@@ -1529,11 +1530,15 @@ static ssize_t modalias_show(struct device *dev, struct device_attribute *attr,
 	const char *cp;
 
 	dn = dev->of_node;
-	if (!dn)
-		return -ENODEV;
+	if (!dn) {
+		strcat(buf, "\n");
+		return strlen(buf);
+	}
 	cp = of_get_property(dn, "compatible", NULL);
-	if (!cp)
-		return -ENODEV;
+	if (!cp) {
+		strcat(buf, "\n");
+		return strlen(buf);
+	}
 
 	return sprintf(buf, "vio:T%sS%s\n", vio_dev->type, cp);
 }
@@ -1622,7 +1627,6 @@ static struct vio_dev *vio_find_name(const char *name)
  */
 struct vio_dev *vio_find_node(struct device_node *vnode)
 {
-	const uint32_t *unit_address;
 	char kobj_name[20];
 	struct device_node *vnode_parent;
 	const char *dev_type;
@@ -1638,10 +1642,13 @@ struct vio_dev *vio_find_node(struct device_node *vnode)
 
 	/* construct the kobject name from the device node */
 	if (!strcmp(dev_type, "vdevice")) {
-		unit_address = of_get_property(vnode, "reg", NULL);
-		if (!unit_address)
+		const __be32 *prop;
+		
+		prop = of_get_property(vnode, "reg", NULL);
+		if (!prop)
 			return NULL;
-		snprintf(kobj_name, sizeof(kobj_name), "%x", *unit_address);
+		snprintf(kobj_name, sizeof(kobj_name), "%x",
+			 (uint32_t)of_read_number(prop, 1));
 	} else if (!strcmp(dev_type, "ibm,platform-facilities"))
 		snprintf(kobj_name, sizeof(kobj_name), "%s", vnode->name);
 	else
diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
index eb643f862579..ffaef2cb101a 100644
--- a/arch/powerpc/kvm/Kconfig
+++ b/arch/powerpc/kvm/Kconfig
@@ -72,6 +72,7 @@ config KVM_BOOK3S_64_HV
 	bool "KVM support for POWER7 and PPC970 using hypervisor mode in host"
 	depends on KVM_BOOK3S_64
 	select MMU_NOTIFIER
+	select CMA
 	---help---
 	  Support running unmodified book3s_64 guest kernels in
 	  virtual machines on POWER7 and PPC970 processors that have
diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile
index 008cd856c5b5..6646c952c5e3 100644
--- a/arch/powerpc/kvm/Makefile
+++ b/arch/powerpc/kvm/Makefile
@@ -81,6 +81,7 @@ kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_HV) := \
 	book3s_64_vio_hv.o \
 	book3s_hv_ras.o \
 	book3s_hv_builtin.o \
+	book3s_hv_cma.o \
 	$(kvm-book3s_64-builtin-xics-objs-y)
 
 kvm-book3s_64-objs-$(CONFIG_KVM_XICS) += \
diff --git a/arch/powerpc/kvm/book3s_64_mmu.c b/arch/powerpc/kvm/book3s_64_mmu.c
index 739bfbadb85e..7e345e00661a 100644
--- a/arch/powerpc/kvm/book3s_64_mmu.c
+++ b/arch/powerpc/kvm/book3s_64_mmu.c
@@ -182,10 +182,13 @@ static int kvmppc_mmu_book3s_64_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
 	hva_t ptegp;
 	u64 pteg[16];
 	u64 avpn = 0;
+	u64 v, r;
+	u64 v_val, v_mask;
+	u64 eaddr_mask;
 	int i;
-	u8 key = 0;
+	u8 pp, key = 0;
 	bool found = false;
-	int second = 0;
+	bool second = false;
 	ulong mp_ea = vcpu->arch.magic_page_ea;
 
 	/* Magic page override */
@@ -208,8 +211,16 @@ static int kvmppc_mmu_book3s_64_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
 		goto no_seg_found;
 
 	avpn = kvmppc_mmu_book3s_64_get_avpn(slbe, eaddr);
+	v_val = avpn & HPTE_V_AVPN;
+
 	if (slbe->tb)
-		avpn |= SLB_VSID_B_1T;
+		v_val |= SLB_VSID_B_1T;
+	if (slbe->large)
+		v_val |= HPTE_V_LARGE;
+	v_val |= HPTE_V_VALID;
+
+	v_mask = SLB_VSID_B | HPTE_V_AVPN | HPTE_V_LARGE | HPTE_V_VALID |
+		HPTE_V_SECONDARY;
 
 do_second:
 	ptegp = kvmppc_mmu_book3s_64_get_pteg(vcpu_book3s, slbe, eaddr, second);
@@ -227,91 +238,74 @@ do_second:
 		key = 4;
 
 	for (i=0; i<16; i+=2) {
-		u64 v = pteg[i];
-		u64 r = pteg[i+1];
-
-		/* Valid check */
-		if (!(v & HPTE_V_VALID))
-			continue;
-		/* Hash check */
-		if ((v & HPTE_V_SECONDARY) != second)
-			continue;
-
-		/* AVPN compare */
-		if (HPTE_V_COMPARE(avpn, v)) {
-			u8 pp = (r & HPTE_R_PP) | key;
-			int eaddr_mask = 0xFFF;
-
-			gpte->eaddr = eaddr;
-			gpte->vpage = kvmppc_mmu_book3s_64_ea_to_vp(vcpu,
-								    eaddr,
-								    data);
-			if (slbe->large)
-				eaddr_mask = 0xFFFFFF;
-			gpte->raddr = (r & HPTE_R_RPN) | (eaddr & eaddr_mask);
-			gpte->may_execute = ((r & HPTE_R_N) ? false : true);
-			gpte->may_read = false;
-			gpte->may_write = false;
-
-			switch (pp) {
-			case 0:
-			case 1:
-			case 2:
-			case 6:
-				gpte->may_write = true;
-				/* fall through */
-			case 3:
-			case 5:
-			case 7:
-				gpte->may_read = true;
-				break;
-			}
-
-			dprintk("KVM MMU: Translated 0x%lx [0x%llx] -> 0x%llx "
-				"-> 0x%lx\n",
-				eaddr, avpn, gpte->vpage, gpte->raddr);
+		/* Check all relevant fields of 1st dword */
+		if ((pteg[i] & v_mask) == v_val) {
 			found = true;
 			break;
 		}
 	}
 
-	/* Update PTE R and C bits, so the guest's swapper knows we used the
-	 * page */
-	if (found) {
-		u32 oldr = pteg[i+1];
+	if (!found) {
+		if (second)
+			goto no_page_found;
+		v_val |= HPTE_V_SECONDARY;
+		second = true;
+		goto do_second;
+	}
 
-		if (gpte->may_read) {
-			/* Set the accessed flag */
-			pteg[i+1] |= HPTE_R_R;
-		}
-		if (gpte->may_write) {
-			/* Set the dirty flag */
-			pteg[i+1] |= HPTE_R_C;
-		} else {
-			dprintk("KVM: Mapping read-only page!\n");
-		}
+	v = pteg[i];
+	r = pteg[i+1];
+	pp = (r & HPTE_R_PP) | key;
+	eaddr_mask = 0xFFF;
+
+	gpte->eaddr = eaddr;
+	gpte->vpage = kvmppc_mmu_book3s_64_ea_to_vp(vcpu, eaddr, data);
+	if (slbe->large)
+		eaddr_mask = 0xFFFFFF;
+	gpte->raddr = (r & HPTE_R_RPN & ~eaddr_mask) | (eaddr & eaddr_mask);
+	gpte->may_execute = ((r & HPTE_R_N) ? false : true);
+	gpte->may_read = false;
+	gpte->may_write = false;
+
+	switch (pp) {
+	case 0:
+	case 1:
+	case 2:
+	case 6:
+		gpte->may_write = true;
+		/* fall through */
+	case 3:
+	case 5:
+	case 7:
+		gpte->may_read = true;
+		break;
+	}
 
-		/* Write back into the PTEG */
-		if (pteg[i+1] != oldr)
-			copy_to_user((void __user *)ptegp, pteg, sizeof(pteg));
+	dprintk("KVM MMU: Translated 0x%lx [0x%llx] -> 0x%llx "
+		"-> 0x%lx\n",
+		eaddr, avpn, gpte->vpage, gpte->raddr);
 
-		if (!gpte->may_read)
-			return -EPERM;
-		return 0;
-	} else {
-		dprintk("KVM MMU: No PTE found (ea=0x%lx sdr1=0x%llx "
-			"ptegp=0x%lx)\n",
-			eaddr, to_book3s(vcpu)->sdr1, ptegp);
-		for (i = 0; i < 16; i += 2)
-			dprintk("   %02d: 0x%llx - 0x%llx (0x%llx)\n",
-				i, pteg[i], pteg[i+1], avpn);
-
-		if (!second) {
-			second = HPTE_V_SECONDARY;
-			goto do_second;
-		}
+	/* Update PTE R and C bits, so the guest's swapper knows we used the
+	 * page */
+	if (gpte->may_read) {
+		/* Set the accessed flag */
+		r |= HPTE_R_R;
+	}
+	if (data && gpte->may_write) {
+		/* Set the dirty flag -- XXX even if not writing */
+		r |= HPTE_R_C;
+	}
+
+	/* Write back into the PTEG */
+	if (pteg[i+1] != r) {
+		pteg[i+1] = r;
+		copy_to_user((void __user *)ptegp, pteg, sizeof(pteg));
 	}
 
+	if (!gpte->may_read)
+		return -EPERM;
+	return 0;
+
 no_page_found:
 	return -ENOENT;
 
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index 710d31317d81..043eec8461e7 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -37,6 +37,8 @@
 #include <asm/ppc-opcode.h>
 #include <asm/cputable.h>
 
+#include "book3s_hv_cma.h"
+
 /* POWER7 has 10-bit LPIDs, PPC970 has 6-bit LPIDs */
 #define MAX_LPID_970	63
 
@@ -52,8 +54,8 @@ long kvmppc_alloc_hpt(struct kvm *kvm, u32 *htab_orderp)
 {
 	unsigned long hpt;
 	struct revmap_entry *rev;
-	struct kvmppc_linear_info *li;
-	long order = kvm_hpt_order;
+	struct page *page = NULL;
+	long order = KVM_DEFAULT_HPT_ORDER;
 
 	if (htab_orderp) {
 		order = *htab_orderp;
@@ -61,26 +63,23 @@ long kvmppc_alloc_hpt(struct kvm *kvm, u32 *htab_orderp)
 			order = PPC_MIN_HPT_ORDER;
 	}
 
+	kvm->arch.hpt_cma_alloc = 0;
 	/*
-	 * If the user wants a different size from default,
 	 * try first to allocate it from the kernel page allocator.
+	 * We keep the CMA reserved for failed allocation.
 	 */
-	hpt = 0;
-	if (order != kvm_hpt_order) {
-		hpt = __get_free_pages(GFP_KERNEL|__GFP_ZERO|__GFP_REPEAT|
-				       __GFP_NOWARN, order - PAGE_SHIFT);
-		if (!hpt)
-			--order;
-	}
+	hpt = __get_free_pages(GFP_KERNEL | __GFP_ZERO | __GFP_REPEAT |
+			       __GFP_NOWARN, order - PAGE_SHIFT);
 
 	/* Next try to allocate from the preallocated pool */
 	if (!hpt) {
-		li = kvm_alloc_hpt();
-		if (li) {
-			hpt = (ulong)li->base_virt;
-			kvm->arch.hpt_li = li;
-			order = kvm_hpt_order;
-		}
+		VM_BUG_ON(order < KVM_CMA_CHUNK_ORDER);
+		page = kvm_alloc_hpt(1 << (order - PAGE_SHIFT));
+		if (page) {
+			hpt = (unsigned long)pfn_to_kaddr(page_to_pfn(page));
+			kvm->arch.hpt_cma_alloc = 1;
+		} else
+			--order;
 	}
 
 	/* Lastly try successively smaller sizes from the page allocator */
@@ -118,8 +117,8 @@ long kvmppc_alloc_hpt(struct kvm *kvm, u32 *htab_orderp)
 	return 0;
 
  out_freehpt:
-	if (kvm->arch.hpt_li)
-		kvm_release_hpt(kvm->arch.hpt_li);
+	if (kvm->arch.hpt_cma_alloc)
+		kvm_release_hpt(page, 1 << (order - PAGE_SHIFT));
 	else
 		free_pages(hpt, order - PAGE_SHIFT);
 	return -ENOMEM;
@@ -165,8 +164,9 @@ void kvmppc_free_hpt(struct kvm *kvm)
 {
 	kvmppc_free_lpid(kvm->arch.lpid);
 	vfree(kvm->arch.revmap);
-	if (kvm->arch.hpt_li)
-		kvm_release_hpt(kvm->arch.hpt_li);
+	if (kvm->arch.hpt_cma_alloc)
+		kvm_release_hpt(virt_to_page(kvm->arch.hpt_virt),
+				1 << (kvm->arch.hpt_order - PAGE_SHIFT));
 	else
 		free_pages(kvm->arch.hpt_virt,
 			   kvm->arch.hpt_order - PAGE_SHIFT);
@@ -1579,7 +1579,7 @@ int kvm_vm_ioctl_get_htab_fd(struct kvm *kvm, struct kvm_get_htab_fd *ghf)
 	ctx->first_pass = 1;
 
 	rwflag = (ghf->flags & KVM_GET_HTAB_WRITE) ? O_WRONLY : O_RDONLY;
-	ret = anon_inode_getfd("kvm-htab", &kvm_htab_fops, ctx, rwflag);
+	ret = anon_inode_getfd("kvm-htab", &kvm_htab_fops, ctx, rwflag | O_CLOEXEC);
 	if (ret < 0) {
 		kvm_put_kvm(kvm);
 		return ret;
diff --git a/arch/powerpc/kvm/book3s_64_slb.S b/arch/powerpc/kvm/book3s_64_slb.S
index 4f0caecc0f9d..4f12e8f0c718 100644
--- a/arch/powerpc/kvm/book3s_64_slb.S
+++ b/arch/powerpc/kvm/book3s_64_slb.S
@@ -17,6 +17,10 @@
  * Authors: Alexander Graf <agraf@suse.de>
  */
 
+#ifdef __LITTLE_ENDIAN__
+#error Need to fix SLB shadow accesses in little endian mode
+#endif
+
 #define SHADOW_SLB_ESID(num)	(SLBSHADOW_SAVEAREA + (num * 0x10))
 #define SHADOW_SLB_VSID(num)	(SLBSHADOW_SAVEAREA + (num * 0x10) + 0x8)
 #define UNBOLT_SLB_ENTRY(num) \
diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c
index b2d3f3b2de72..54cf9bc94dad 100644
--- a/arch/powerpc/kvm/book3s_64_vio.c
+++ b/arch/powerpc/kvm/book3s_64_vio.c
@@ -136,7 +136,7 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
 	mutex_unlock(&kvm->lock);
 
 	return anon_inode_getfd("kvm-spapr-tce", &kvm_spapr_tce_fops,
-				stt, O_RDWR);
+				stt, O_RDWR | O_CLOEXEC);
 
 fail:
 	if (stt) {
diff --git a/arch/powerpc/kvm/book3s_emulate.c b/arch/powerpc/kvm/book3s_emulate.c
index 1f6344c4408d..360ce68c9809 100644
--- a/arch/powerpc/kvm/book3s_emulate.c
+++ b/arch/powerpc/kvm/book3s_emulate.c
@@ -458,6 +458,7 @@ int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, ulong spr_val)
 	case SPRN_PMC4_GEKKO:
 	case SPRN_WPAR_GEKKO:
 	case SPRN_MSSSR0:
+	case SPRN_DABR:
 		break;
 unprivileged:
 	default:
@@ -555,6 +556,7 @@ int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, ulong *spr_val)
 	case SPRN_PMC4_GEKKO:
 	case SPRN_WPAR_GEKKO:
 	case SPRN_MSSSR0:
+	case SPRN_DABR:
 		*spr_val = 0;
 		break;
 	default:
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 7629cd3eb91a..62a2b5ab08ed 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -217,7 +217,7 @@ struct kvm_vcpu *kvmppc_find_vcpu(struct kvm *kvm, int id)
 
 static void init_vpa(struct kvm_vcpu *vcpu, struct lppaca *vpa)
 {
-	vpa->shared_proc = 1;
+	vpa->__old_status |= LPPACA_OLD_SHARED_PROC;
 	vpa->yield_count = 1;
 }
 
@@ -680,13 +680,12 @@ static int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 }
 
 int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
-                                  struct kvm_sregs *sregs)
+				  struct kvm_sregs *sregs)
 {
 	int i;
 
-	sregs->pvr = vcpu->arch.pvr;
-
 	memset(sregs, 0, sizeof(struct kvm_sregs));
+	sregs->pvr = vcpu->arch.pvr;
 	for (i = 0; i < vcpu->arch.slb_max; i++) {
 		sregs->u.s.ppc64.slb[i].slbe = vcpu->arch.slb[i].orige;
 		sregs->u.s.ppc64.slb[i].slbv = vcpu->arch.slb[i].origv;
@@ -696,7 +695,7 @@ int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
 }
 
 int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
-                                  struct kvm_sregs *sregs)
+				  struct kvm_sregs *sregs)
 {
 	int i, j;
 
@@ -1511,10 +1510,10 @@ static inline int lpcr_rmls(unsigned long rma_size)
 
 static int kvm_rma_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
-	struct kvmppc_linear_info *ri = vma->vm_file->private_data;
 	struct page *page;
+	struct kvm_rma_info *ri = vma->vm_file->private_data;
 
-	if (vmf->pgoff >= ri->npages)
+	if (vmf->pgoff >= kvm_rma_pages)
 		return VM_FAULT_SIGBUS;
 
 	page = pfn_to_page(ri->base_pfn + vmf->pgoff);
@@ -1536,7 +1535,7 @@ static int kvm_rma_mmap(struct file *file, struct vm_area_struct *vma)
 
 static int kvm_rma_release(struct inode *inode, struct file *filp)
 {
-	struct kvmppc_linear_info *ri = filp->private_data;
+	struct kvm_rma_info *ri = filp->private_data;
 
 	kvm_release_rma(ri);
 	return 0;
@@ -1549,18 +1548,27 @@ static const struct file_operations kvm_rma_fops = {
 
 long kvm_vm_ioctl_allocate_rma(struct kvm *kvm, struct kvm_allocate_rma *ret)
 {
-	struct kvmppc_linear_info *ri;
 	long fd;
+	struct kvm_rma_info *ri;
+	/*
+	 * Only do this on PPC970 in HV mode
+	 */
+	if (!cpu_has_feature(CPU_FTR_HVMODE) ||
+	    !cpu_has_feature(CPU_FTR_ARCH_201))
+		return -EINVAL;
+
+	if (!kvm_rma_pages)
+		return -EINVAL;
 
 	ri = kvm_alloc_rma();
 	if (!ri)
 		return -ENOMEM;
 
-	fd = anon_inode_getfd("kvm-rma", &kvm_rma_fops, ri, O_RDWR);
+	fd = anon_inode_getfd("kvm-rma", &kvm_rma_fops, ri, O_RDWR | O_CLOEXEC);
 	if (fd < 0)
 		kvm_release_rma(ri);
 
-	ret->rma_size = ri->npages << PAGE_SHIFT;
+	ret->rma_size = kvm_rma_pages << PAGE_SHIFT;
 	return fd;
 }
 
@@ -1725,7 +1733,7 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
 {
 	int err = 0;
 	struct kvm *kvm = vcpu->kvm;
-	struct kvmppc_linear_info *ri = NULL;
+	struct kvm_rma_info *ri = NULL;
 	unsigned long hva;
 	struct kvm_memory_slot *memslot;
 	struct vm_area_struct *vma;
@@ -1803,7 +1811,7 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
 
 	} else {
 		/* Set up to use an RMO region */
-		rma_size = ri->npages;
+		rma_size = kvm_rma_pages;
 		if (rma_size > memslot->npages)
 			rma_size = memslot->npages;
 		rma_size <<= PAGE_SHIFT;
@@ -1831,14 +1839,14 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
 			/* POWER7 */
 			lpcr &= ~(LPCR_VPM0 | LPCR_VRMA_L);
 			lpcr |= rmls << LPCR_RMLS_SH;
-			kvm->arch.rmor = kvm->arch.rma->base_pfn << PAGE_SHIFT;
+			kvm->arch.rmor = ri->base_pfn << PAGE_SHIFT;
 		}
 		kvm->arch.lpcr = lpcr;
 		pr_info("KVM: Using RMO at %lx size %lx (LPCR = %lx)\n",
 			ri->base_pfn << PAGE_SHIFT, rma_size, lpcr);
 
 		/* Initialize phys addrs of pages in RMO */
-		npages = ri->npages;
+		npages = kvm_rma_pages;
 		porder = __ilog2(npages);
 		physp = memslot->arch.slot_phys;
 		if (physp) {
diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c
index ec0a9e5de100..8cd0daebb82d 100644
--- a/arch/powerpc/kvm/book3s_hv_builtin.c
+++ b/arch/powerpc/kvm/book3s_hv_builtin.c
@@ -13,33 +13,34 @@
 #include <linux/spinlock.h>
 #include <linux/bootmem.h>
 #include <linux/init.h>
+#include <linux/memblock.h>
+#include <linux/sizes.h>
 
 #include <asm/cputable.h>
 #include <asm/kvm_ppc.h>
 #include <asm/kvm_book3s.h>
 
-#define KVM_LINEAR_RMA		0
-#define KVM_LINEAR_HPT		1
-
-static void __init kvm_linear_init_one(ulong size, int count, int type);
-static struct kvmppc_linear_info *kvm_alloc_linear(int type);
-static void kvm_release_linear(struct kvmppc_linear_info *ri);
-
-int kvm_hpt_order = KVM_DEFAULT_HPT_ORDER;
-EXPORT_SYMBOL_GPL(kvm_hpt_order);
-
-/*************** RMA *************/
-
+#include "book3s_hv_cma.h"
+/*
+ * Hash page table alignment on newer cpus(CPU_FTR_ARCH_206)
+ * should be power of 2.
+ */
+#define HPT_ALIGN_PAGES		((1 << 18) >> PAGE_SHIFT) /* 256k */
+/*
+ * By default we reserve 5% of memory for hash pagetable allocation.
+ */
+static unsigned long kvm_cma_resv_ratio = 5;
 /*
- * This maintains a list of RMAs (real mode areas) for KVM guests to use.
+ * We allocate RMAs (real mode areas) for KVM guests from the KVM CMA area.
  * Each RMA has to be physically contiguous and of a size that the
  * hardware supports.  PPC970 and POWER7 support 64MB, 128MB and 256MB,
  * and other larger sizes.  Since we are unlikely to be allocate that
  * much physically contiguous memory after the system is up and running,
- * we preallocate a set of RMAs in early boot for KVM to use.
+ * we preallocate a set of RMAs in early boot using CMA.
+ * should be power of 2.
  */
-static unsigned long kvm_rma_size = 64 << 20;	/* 64MB */
-static unsigned long kvm_rma_count;
+unsigned long kvm_rma_pages = (1 << 27) >> PAGE_SHIFT;	/* 128MB */
+EXPORT_SYMBOL_GPL(kvm_rma_pages);
 
 /* Work out RMLS (real mode limit selector) field value for a given RMA size.
    Assumes POWER7 or PPC970. */
@@ -69,165 +70,114 @@ static inline int lpcr_rmls(unsigned long rma_size)
 
 static int __init early_parse_rma_size(char *p)
 {
-	if (!p)
-		return 1;
+	unsigned long kvm_rma_size;
 
+	pr_debug("%s(%s)\n", __func__, p);
+	if (!p)
+		return -EINVAL;
 	kvm_rma_size = memparse(p, &p);
-
+	/*
+	 * Check that the requested size is one supported in hardware
+	 */
+	if (lpcr_rmls(kvm_rma_size) < 0) {
+		pr_err("RMA size of 0x%lx not supported\n", kvm_rma_size);
+		return -EINVAL;
+	}
+	kvm_rma_pages = kvm_rma_size >> PAGE_SHIFT;
 	return 0;
 }
 early_param("kvm_rma_size", early_parse_rma_size);
 
-static int __init early_parse_rma_count(char *p)
+struct kvm_rma_info *kvm_alloc_rma()
 {
-	if (!p)
-		return 1;
-
-	kvm_rma_count = simple_strtoul(p, NULL, 0);
-
-	return 0;
-}
-early_param("kvm_rma_count", early_parse_rma_count);
-
-struct kvmppc_linear_info *kvm_alloc_rma(void)
-{
-	return kvm_alloc_linear(KVM_LINEAR_RMA);
+	struct page *page;
+	struct kvm_rma_info *ri;
+
+	ri = kmalloc(sizeof(struct kvm_rma_info), GFP_KERNEL);
+	if (!ri)
+		return NULL;
+	page = kvm_alloc_cma(kvm_rma_pages, kvm_rma_pages);
+	if (!page)
+		goto err_out;
+	atomic_set(&ri->use_count, 1);
+	ri->base_pfn = page_to_pfn(page);
+	return ri;
+err_out:
+	kfree(ri);
+	return NULL;
 }
 EXPORT_SYMBOL_GPL(kvm_alloc_rma);
 
-void kvm_release_rma(struct kvmppc_linear_info *ri)
+void kvm_release_rma(struct kvm_rma_info *ri)
 {
-	kvm_release_linear(ri);
+	if (atomic_dec_and_test(&ri->use_count)) {
+		kvm_release_cma(pfn_to_page(ri->base_pfn), kvm_rma_pages);
+		kfree(ri);
+	}
 }
 EXPORT_SYMBOL_GPL(kvm_release_rma);
 
-/*************** HPT *************/
-
-/*
- * This maintains a list of big linear HPT tables that contain the GVA->HPA
- * memory mappings. If we don't reserve those early on, we might not be able
- * to get a big (usually 16MB) linear memory region from the kernel anymore.
- */
-
-static unsigned long kvm_hpt_count;
-
-static int __init early_parse_hpt_count(char *p)
+static int __init early_parse_kvm_cma_resv(char *p)
 {
+	pr_debug("%s(%s)\n", __func__, p);
 	if (!p)
-		return 1;
-
-	kvm_hpt_count = simple_strtoul(p, NULL, 0);
-
-	return 0;
+		return -EINVAL;
+	return kstrtoul(p, 0, &kvm_cma_resv_ratio);
 }
-early_param("kvm_hpt_count", early_parse_hpt_count);
+early_param("kvm_cma_resv_ratio", early_parse_kvm_cma_resv);
 
-struct kvmppc_linear_info *kvm_alloc_hpt(void)
+struct page *kvm_alloc_hpt(unsigned long nr_pages)
 {
-	return kvm_alloc_linear(KVM_LINEAR_HPT);
+	unsigned long align_pages = HPT_ALIGN_PAGES;
+
+	/* Old CPUs require HPT aligned on a multiple of its size */
+	if (!cpu_has_feature(CPU_FTR_ARCH_206))
+		align_pages = nr_pages;
+	return kvm_alloc_cma(nr_pages, align_pages);
 }
 EXPORT_SYMBOL_GPL(kvm_alloc_hpt);
 
-void kvm_release_hpt(struct kvmppc_linear_info *li)
+void kvm_release_hpt(struct page *page, unsigned long nr_pages)
 {
-	kvm_release_linear(li);
+	kvm_release_cma(page, nr_pages);
 }
 EXPORT_SYMBOL_GPL(kvm_release_hpt);
 
-/*************** generic *************/
-
-static LIST_HEAD(free_linears);
-static DEFINE_SPINLOCK(linear_lock);
-
-static void __init kvm_linear_init_one(ulong size, int count, int type)
-{
-	unsigned long i;
-	unsigned long j, npages;
-	void *linear;
-	struct page *pg;
-	const char *typestr;
-	struct kvmppc_linear_info *linear_info;
-
-	if (!count)
-		return;
-
-	typestr = (type == KVM_LINEAR_RMA) ? "RMA" : "HPT";
-
-	npages = size >> PAGE_SHIFT;
-	linear_info = alloc_bootmem(count * sizeof(struct kvmppc_linear_info));
-	for (i = 0; i < count; ++i) {
-		linear = alloc_bootmem_align(size, size);
-		pr_debug("Allocated KVM %s at %p (%ld MB)\n", typestr, linear,
-			 size >> 20);
-		linear_info[i].base_virt = linear;
-		linear_info[i].base_pfn = __pa(linear) >> PAGE_SHIFT;
-		linear_info[i].npages = npages;
-		linear_info[i].type = type;
-		list_add_tail(&linear_info[i].list, &free_linears);
-		atomic_set(&linear_info[i].use_count, 0);
-
-		pg = pfn_to_page(linear_info[i].base_pfn);
-		for (j = 0; j < npages; ++j) {
-			atomic_inc(&pg->_count);
-			++pg;
-		}
-	}
-}
-
-static struct kvmppc_linear_info *kvm_alloc_linear(int type)
-{
-	struct kvmppc_linear_info *ri, *ret;
-
-	ret = NULL;
-	spin_lock(&linear_lock);
-	list_for_each_entry(ri, &free_linears, list) {
-		if (ri->type != type)
-			continue;
-
-		list_del(&ri->list);
-		atomic_inc(&ri->use_count);
-		memset(ri->base_virt, 0, ri->npages << PAGE_SHIFT);
-		ret = ri;
-		break;
-	}
-	spin_unlock(&linear_lock);
-	return ret;
-}
-
-static void kvm_release_linear(struct kvmppc_linear_info *ri)
-{
-	if (atomic_dec_and_test(&ri->use_count)) {
-		spin_lock(&linear_lock);
-		list_add_tail(&ri->list, &free_linears);
-		spin_unlock(&linear_lock);
-
-	}
-}
-
-/*
- * Called at boot time while the bootmem allocator is active,
- * to allocate contiguous physical memory for the hash page
- * tables for guests.
+/**
+ * kvm_cma_reserve() - reserve area for kvm hash pagetable
+ *
+ * This function reserves memory from early allocator. It should be
+ * called by arch specific code once the early allocator (memblock or bootmem)
+ * has been activated and all other subsystems have already allocated/reserved
+ * memory.
  */
-void __init kvm_linear_init(void)
+void __init kvm_cma_reserve(void)
 {
-	/* HPT */
-	kvm_linear_init_one(1 << kvm_hpt_order, kvm_hpt_count, KVM_LINEAR_HPT);
-
-	/* RMA */
-	/* Only do this on PPC970 in HV mode */
-	if (!cpu_has_feature(CPU_FTR_HVMODE) ||
-	    !cpu_has_feature(CPU_FTR_ARCH_201))
-		return;
-
-	if (!kvm_rma_size || !kvm_rma_count)
-		return;
-
-	/* Check that the requested size is one supported in hardware */
-	if (lpcr_rmls(kvm_rma_size) < 0) {
-		pr_err("RMA size of 0x%lx not supported\n", kvm_rma_size);
-		return;
+	unsigned long align_size;
+	struct memblock_region *reg;
+	phys_addr_t selected_size = 0;
+	/*
+	 * We cannot use memblock_phys_mem_size() here, because
+	 * memblock_analyze() has not been called yet.
+	 */
+	for_each_memblock(memory, reg)
+		selected_size += memblock_region_memory_end_pfn(reg) -
+				 memblock_region_memory_base_pfn(reg);
+
+	selected_size = (selected_size * kvm_cma_resv_ratio / 100) << PAGE_SHIFT;
+	if (selected_size) {
+		pr_debug("%s: reserving %ld MiB for global area\n", __func__,
+			 (unsigned long)selected_size / SZ_1M);
+		/*
+		 * Old CPUs require HPT aligned on a multiple of its size. So for them
+		 * make the alignment as max size we could request.
+		 */
+		if (!cpu_has_feature(CPU_FTR_ARCH_206))
+			align_size = __rounddown_pow_of_two(selected_size);
+		else
+			align_size = HPT_ALIGN_PAGES << PAGE_SHIFT;
+
+		align_size = max(kvm_rma_pages << PAGE_SHIFT, align_size);
+		kvm_cma_declare_contiguous(selected_size, align_size);
 	}
-
-	kvm_linear_init_one(kvm_rma_size, kvm_rma_count, KVM_LINEAR_RMA);
 }
diff --git a/arch/powerpc/kvm/book3s_hv_cma.c b/arch/powerpc/kvm/book3s_hv_cma.c
new file mode 100644
index 000000000000..d9d3d8553d51
--- /dev/null
+++ b/arch/powerpc/kvm/book3s_hv_cma.c
@@ -0,0 +1,240 @@
+/*
+ * Contiguous Memory Allocator for ppc KVM hash pagetable  based on CMA
+ * for DMA mapping framework
+ *
+ * Copyright IBM Corporation, 2013
+ * Author Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation; either version 2 of the
+ * License or (at your optional) any later version of the license.
+ *
+ */
+#define pr_fmt(fmt) "kvm_cma: " fmt
+
+#ifdef CONFIG_CMA_DEBUG
+#ifndef DEBUG
+#  define DEBUG
+#endif
+#endif
+
+#include <linux/memblock.h>
+#include <linux/mutex.h>
+#include <linux/sizes.h>
+#include <linux/slab.h>
+
+#include "book3s_hv_cma.h"
+
+struct kvm_cma {
+	unsigned long	base_pfn;
+	unsigned long	count;
+	unsigned long	*bitmap;
+};
+
+static DEFINE_MUTEX(kvm_cma_mutex);
+static struct kvm_cma kvm_cma_area;
+
+/**
+ * kvm_cma_declare_contiguous() - reserve area for contiguous memory handling
+ *			          for kvm hash pagetable
+ * @size:  Size of the reserved memory.
+ * @alignment:  Alignment for the contiguous memory area
+ *
+ * This function reserves memory for kvm cma area. It should be
+ * called by arch code when early allocator (memblock or bootmem)
+ * is still activate.
+ */
+long __init kvm_cma_declare_contiguous(phys_addr_t size, phys_addr_t alignment)
+{
+	long base_pfn;
+	phys_addr_t addr;
+	struct kvm_cma *cma = &kvm_cma_area;
+
+	pr_debug("%s(size %lx)\n", __func__, (unsigned long)size);
+
+	if (!size)
+		return -EINVAL;
+	/*
+	 * Sanitise input arguments.
+	 * We should be pageblock aligned for CMA.
+	 */
+	alignment = max(alignment, (phys_addr_t)(PAGE_SIZE << pageblock_order));
+	size = ALIGN(size, alignment);
+	/*
+	 * Reserve memory
+	 * Use __memblock_alloc_base() since
+	 * memblock_alloc_base() panic()s.
+	 */
+	addr = __memblock_alloc_base(size, alignment, 0);
+	if (!addr) {
+		base_pfn = -ENOMEM;
+		goto err;
+	} else
+		base_pfn = PFN_DOWN(addr);
+
+	/*
+	 * Each reserved area must be initialised later, when more kernel
+	 * subsystems (like slab allocator) are available.
+	 */
+	cma->base_pfn = base_pfn;
+	cma->count    = size >> PAGE_SHIFT;
+	pr_info("CMA: reserved %ld MiB\n", (unsigned long)size / SZ_1M);
+	return 0;
+err:
+	pr_err("CMA: failed to reserve %ld MiB\n", (unsigned long)size / SZ_1M);
+	return base_pfn;
+}
+
+/**
+ * kvm_alloc_cma() - allocate pages from contiguous area
+ * @nr_pages: Requested number of pages.
+ * @align_pages: Requested alignment in number of pages
+ *
+ * This function allocates memory buffer for hash pagetable.
+ */
+struct page *kvm_alloc_cma(unsigned long nr_pages, unsigned long align_pages)
+{
+	int ret;
+	struct page *page = NULL;
+	struct kvm_cma *cma = &kvm_cma_area;
+	unsigned long chunk_count, nr_chunk;
+	unsigned long mask, pfn, pageno, start = 0;
+
+
+	if (!cma || !cma->count)
+		return NULL;
+
+	pr_debug("%s(cma %p, count %lu, align pages %lu)\n", __func__,
+		 (void *)cma, nr_pages, align_pages);
+
+	if (!nr_pages)
+		return NULL;
+	/*
+	 * align mask with chunk size. The bit tracks pages in chunk size
+	 */
+	VM_BUG_ON(!is_power_of_2(align_pages));
+	mask = (align_pages >> (KVM_CMA_CHUNK_ORDER - PAGE_SHIFT)) - 1;
+	BUILD_BUG_ON(PAGE_SHIFT > KVM_CMA_CHUNK_ORDER);
+
+	chunk_count = cma->count >>  (KVM_CMA_CHUNK_ORDER - PAGE_SHIFT);
+	nr_chunk = nr_pages >> (KVM_CMA_CHUNK_ORDER - PAGE_SHIFT);
+
+	mutex_lock(&kvm_cma_mutex);
+	for (;;) {
+		pageno = bitmap_find_next_zero_area(cma->bitmap, chunk_count,
+						    start, nr_chunk, mask);
+		if (pageno >= chunk_count)
+			break;
+
+		pfn = cma->base_pfn + (pageno << (KVM_CMA_CHUNK_ORDER - PAGE_SHIFT));
+		ret = alloc_contig_range(pfn, pfn + nr_pages, MIGRATE_CMA);
+		if (ret == 0) {
+			bitmap_set(cma->bitmap, pageno, nr_chunk);
+			page = pfn_to_page(pfn);
+			memset(pfn_to_kaddr(pfn), 0, nr_pages << PAGE_SHIFT);
+			break;
+		} else if (ret != -EBUSY) {
+			break;
+		}
+		pr_debug("%s(): memory range at %p is busy, retrying\n",
+			 __func__, pfn_to_page(pfn));
+		/* try again with a bit different memory target */
+		start = pageno + mask + 1;
+	}
+	mutex_unlock(&kvm_cma_mutex);
+	pr_debug("%s(): returned %p\n", __func__, page);
+	return page;
+}
+
+/**
+ * kvm_release_cma() - release allocated pages for hash pagetable
+ * @pages: Allocated pages.
+ * @nr_pages: Number of allocated pages.
+ *
+ * This function releases memory allocated by kvm_alloc_cma().
+ * It returns false when provided pages do not belong to contiguous area and
+ * true otherwise.
+ */
+bool kvm_release_cma(struct page *pages, unsigned long nr_pages)
+{
+	unsigned long pfn;
+	unsigned long nr_chunk;
+	struct kvm_cma *cma = &kvm_cma_area;
+
+	if (!cma || !pages)
+		return false;
+
+	pr_debug("%s(page %p count %lu)\n", __func__, (void *)pages, nr_pages);
+
+	pfn = page_to_pfn(pages);
+
+	if (pfn < cma->base_pfn || pfn >= cma->base_pfn + cma->count)
+		return false;
+
+	VM_BUG_ON(pfn + nr_pages > cma->base_pfn + cma->count);
+	nr_chunk = nr_pages >>  (KVM_CMA_CHUNK_ORDER - PAGE_SHIFT);
+
+	mutex_lock(&kvm_cma_mutex);
+	bitmap_clear(cma->bitmap,
+		     (pfn - cma->base_pfn) >> (KVM_CMA_CHUNK_ORDER - PAGE_SHIFT),
+		     nr_chunk);
+	free_contig_range(pfn, nr_pages);
+	mutex_unlock(&kvm_cma_mutex);
+
+	return true;
+}
+
+static int __init kvm_cma_activate_area(unsigned long base_pfn,
+					unsigned long count)
+{
+	unsigned long pfn = base_pfn;
+	unsigned i = count >> pageblock_order;
+	struct zone *zone;
+
+	WARN_ON_ONCE(!pfn_valid(pfn));
+	zone = page_zone(pfn_to_page(pfn));
+	do {
+		unsigned j;
+		base_pfn = pfn;
+		for (j = pageblock_nr_pages; j; --j, pfn++) {
+			WARN_ON_ONCE(!pfn_valid(pfn));
+			/*
+			 * alloc_contig_range requires the pfn range
+			 * specified to be in the same zone. Make this
+			 * simple by forcing the entire CMA resv range
+			 * to be in the same zone.
+			 */
+			if (page_zone(pfn_to_page(pfn)) != zone)
+				return -EINVAL;
+		}
+		init_cma_reserved_pageblock(pfn_to_page(base_pfn));
+	} while (--i);
+	return 0;
+}
+
+static int __init kvm_cma_init_reserved_areas(void)
+{
+	int bitmap_size, ret;
+	unsigned long chunk_count;
+	struct kvm_cma *cma = &kvm_cma_area;
+
+	pr_debug("%s()\n", __func__);
+	if (!cma->count)
+		return 0;
+	chunk_count = cma->count >> (KVM_CMA_CHUNK_ORDER - PAGE_SHIFT);
+	bitmap_size = BITS_TO_LONGS(chunk_count) * sizeof(long);
+	cma->bitmap = kzalloc(bitmap_size, GFP_KERNEL);
+	if (!cma->bitmap)
+		return -ENOMEM;
+
+	ret = kvm_cma_activate_area(cma->base_pfn, cma->count);
+	if (ret)
+		goto error;
+	return 0;
+
+error:
+	kfree(cma->bitmap);
+	return ret;
+}
+core_initcall(kvm_cma_init_reserved_areas);
diff --git a/arch/powerpc/kvm/book3s_hv_cma.h b/arch/powerpc/kvm/book3s_hv_cma.h
new file mode 100644
index 000000000000..655144f75fa5
--- /dev/null
+++ b/arch/powerpc/kvm/book3s_hv_cma.h
@@ -0,0 +1,27 @@
+/*
+ * Contiguous Memory Allocator for ppc KVM hash pagetable  based on CMA
+ * for DMA mapping framework
+ *
+ * Copyright IBM Corporation, 2013
+ * Author Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation; either version 2 of the
+ * License or (at your optional) any later version of the license.
+ *
+ */
+
+#ifndef __POWERPC_KVM_CMA_ALLOC_H__
+#define __POWERPC_KVM_CMA_ALLOC_H__
+/*
+ * Both RMA and Hash page allocation will be multiple of 256K.
+ */
+#define KVM_CMA_CHUNK_ORDER	18
+
+extern struct page *kvm_alloc_cma(unsigned long nr_pages,
+				  unsigned long align_pages);
+extern bool kvm_release_cma(struct page *pages, unsigned long nr_pages);
+extern long kvm_cma_declare_contiguous(phys_addr_t size,
+				       phys_addr_t alignment) __init;
+#endif
diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
index fc25689a9f35..9c515440ad1a 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
@@ -363,7 +363,11 @@ long kvmppc_h_enter(struct kvm_vcpu *vcpu, unsigned long flags,
 				 vcpu->arch.pgdir, true, &vcpu->arch.gpr[4]);
 }
 
+#ifdef __BIG_ENDIAN__
 #define LOCK_TOKEN	(*(u32 *)(&get_paca()->lock_token))
+#else
+#define LOCK_TOKEN	(*(u32 *)(&get_paca()->paca_index))
+#endif
 
 static inline int try_lock_tlbie(unsigned int *lock)
 {
@@ -383,6 +387,80 @@ static inline int try_lock_tlbie(unsigned int *lock)
 	return old == 0;
 }
 
+/*
+ * tlbie/tlbiel is a bit different on the PPC970 compared to later
+ * processors such as POWER7; the large page bit is in the instruction
+ * not RB, and the top 16 bits and the bottom 12 bits of the VA
+ * in RB must be 0.
+ */
+static void do_tlbies_970(struct kvm *kvm, unsigned long *rbvalues,
+			  long npages, int global, bool need_sync)
+{
+	long i;
+
+	if (global) {
+		while (!try_lock_tlbie(&kvm->arch.tlbie_lock))
+			cpu_relax();
+		if (need_sync)
+			asm volatile("ptesync" : : : "memory");
+		for (i = 0; i < npages; ++i) {
+			unsigned long rb = rbvalues[i];
+
+			if (rb & 1)		/* large page */
+				asm volatile("tlbie %0,1" : :
+					     "r" (rb & 0x0000fffffffff000ul));
+			else
+				asm volatile("tlbie %0,0" : :
+					     "r" (rb & 0x0000fffffffff000ul));
+		}
+		asm volatile("eieio; tlbsync; ptesync" : : : "memory");
+		kvm->arch.tlbie_lock = 0;
+	} else {
+		if (need_sync)
+			asm volatile("ptesync" : : : "memory");
+		for (i = 0; i < npages; ++i) {
+			unsigned long rb = rbvalues[i];
+
+			if (rb & 1)		/* large page */
+				asm volatile("tlbiel %0,1" : :
+					     "r" (rb & 0x0000fffffffff000ul));
+			else
+				asm volatile("tlbiel %0,0" : :
+					     "r" (rb & 0x0000fffffffff000ul));
+		}
+		asm volatile("ptesync" : : : "memory");
+	}
+}
+
+static void do_tlbies(struct kvm *kvm, unsigned long *rbvalues,
+		      long npages, int global, bool need_sync)
+{
+	long i;
+
+	if (cpu_has_feature(CPU_FTR_ARCH_201)) {
+		/* PPC970 tlbie instruction is a bit different */
+		do_tlbies_970(kvm, rbvalues, npages, global, need_sync);
+		return;
+	}
+	if (global) {
+		while (!try_lock_tlbie(&kvm->arch.tlbie_lock))
+			cpu_relax();
+		if (need_sync)
+			asm volatile("ptesync" : : : "memory");
+		for (i = 0; i < npages; ++i)
+			asm volatile(PPC_TLBIE(%1,%0) : :
+				     "r" (rbvalues[i]), "r" (kvm->arch.lpid));
+		asm volatile("eieio; tlbsync; ptesync" : : : "memory");
+		kvm->arch.tlbie_lock = 0;
+	} else {
+		if (need_sync)
+			asm volatile("ptesync" : : : "memory");
+		for (i = 0; i < npages; ++i)
+			asm volatile("tlbiel %0" : : "r" (rbvalues[i]));
+		asm volatile("ptesync" : : : "memory");
+	}
+}
+
 long kvmppc_do_h_remove(struct kvm *kvm, unsigned long flags,
 			unsigned long pte_index, unsigned long avpn,
 			unsigned long *hpret)
@@ -408,19 +486,7 @@ long kvmppc_do_h_remove(struct kvm *kvm, unsigned long flags,
 	if (v & HPTE_V_VALID) {
 		hpte[0] &= ~HPTE_V_VALID;
 		rb = compute_tlbie_rb(v, hpte[1], pte_index);
-		if (global_invalidates(kvm, flags)) {
-			while (!try_lock_tlbie(&kvm->arch.tlbie_lock))
-				cpu_relax();
-			asm volatile("ptesync" : : : "memory");
-			asm volatile(PPC_TLBIE(%1,%0)"; eieio; tlbsync"
-				     : : "r" (rb), "r" (kvm->arch.lpid));
-			asm volatile("ptesync" : : : "memory");
-			kvm->arch.tlbie_lock = 0;
-		} else {
-			asm volatile("ptesync" : : : "memory");
-			asm volatile("tlbiel %0" : : "r" (rb));
-			asm volatile("ptesync" : : : "memory");
-		}
+		do_tlbies(kvm, &rb, 1, global_invalidates(kvm, flags), true);
 		/* Read PTE low word after tlbie to get final R/C values */
 		remove_revmap_chain(kvm, pte_index, rev, v, hpte[1]);
 	}
@@ -448,12 +514,11 @@ long kvmppc_h_bulk_remove(struct kvm_vcpu *vcpu)
 	unsigned long *hp, *hptes[4], tlbrb[4];
 	long int i, j, k, n, found, indexes[4];
 	unsigned long flags, req, pte_index, rcbits;
-	long int local = 0;
+	int global;
 	long int ret = H_SUCCESS;
 	struct revmap_entry *rev, *revs[4];
 
-	if (atomic_read(&kvm->online_vcpus) == 1)
-		local = 1;
+	global = global_invalidates(kvm, 0);
 	for (i = 0; i < 4 && ret == H_SUCCESS; ) {
 		n = 0;
 		for (; i < 4; ++i) {
@@ -529,22 +594,7 @@ long kvmppc_h_bulk_remove(struct kvm_vcpu *vcpu)
 			break;
 
 		/* Now that we've collected a batch, do the tlbies */
-		if (!local) {
-			while(!try_lock_tlbie(&kvm->arch.tlbie_lock))
-				cpu_relax();
-			asm volatile("ptesync" : : : "memory");
-			for (k = 0; k < n; ++k)
-				asm volatile(PPC_TLBIE(%1,%0) : :
-					     "r" (tlbrb[k]),
-					     "r" (kvm->arch.lpid));
-			asm volatile("eieio; tlbsync; ptesync" : : : "memory");
-			kvm->arch.tlbie_lock = 0;
-		} else {
-			asm volatile("ptesync" : : : "memory");
-			for (k = 0; k < n; ++k)
-				asm volatile("tlbiel %0" : : "r" (tlbrb[k]));
-			asm volatile("ptesync" : : : "memory");
-		}
+		do_tlbies(kvm, tlbrb, n, global, true);
 
 		/* Read PTE low words after tlbie to get final R/C values */
 		for (k = 0; k < n; ++k) {
@@ -603,19 +653,7 @@ long kvmppc_h_protect(struct kvm_vcpu *vcpu, unsigned long flags,
 	if (v & HPTE_V_VALID) {
 		rb = compute_tlbie_rb(v, r, pte_index);
 		hpte[0] = v & ~HPTE_V_VALID;
-		if (global_invalidates(kvm, flags)) {
-			while(!try_lock_tlbie(&kvm->arch.tlbie_lock))
-				cpu_relax();
-			asm volatile("ptesync" : : : "memory");
-			asm volatile(PPC_TLBIE(%1,%0)"; eieio; tlbsync"
-				     : : "r" (rb), "r" (kvm->arch.lpid));
-			asm volatile("ptesync" : : : "memory");
-			kvm->arch.tlbie_lock = 0;
-		} else {
-			asm volatile("ptesync" : : : "memory");
-			asm volatile("tlbiel %0" : : "r" (rb));
-			asm volatile("ptesync" : : : "memory");
-		}
+		do_tlbies(kvm, &rb, 1, global_invalidates(kvm, flags), true);
 		/*
 		 * If the host has this page as readonly but the guest
 		 * wants to make it read/write, reduce the permissions.
@@ -686,13 +724,7 @@ void kvmppc_invalidate_hpte(struct kvm *kvm, unsigned long *hptep,
 
 	hptep[0] &= ~HPTE_V_VALID;
 	rb = compute_tlbie_rb(hptep[0], hptep[1], pte_index);
-	while (!try_lock_tlbie(&kvm->arch.tlbie_lock))
-		cpu_relax();
-	asm volatile("ptesync" : : : "memory");
-	asm volatile(PPC_TLBIE(%1,%0)"; eieio; tlbsync"
-		     : : "r" (rb), "r" (kvm->arch.lpid));
-	asm volatile("ptesync" : : : "memory");
-	kvm->arch.tlbie_lock = 0;
+	do_tlbies(kvm, &rb, 1, 1, true);
 }
 EXPORT_SYMBOL_GPL(kvmppc_invalidate_hpte);
 
@@ -706,12 +738,7 @@ void kvmppc_clear_ref_hpte(struct kvm *kvm, unsigned long *hptep,
 	rbyte = (hptep[1] & ~HPTE_R_R) >> 8;
 	/* modify only the second-last byte, which contains the ref bit */
 	*((char *)hptep + 14) = rbyte;
-	while (!try_lock_tlbie(&kvm->arch.tlbie_lock))
-		cpu_relax();
-	asm volatile(PPC_TLBIE(%1,%0)"; eieio; tlbsync"
-		     : : "r" (rb), "r" (kvm->arch.lpid));
-	asm volatile("ptesync" : : : "memory");
-	kvm->arch.tlbie_lock = 0;
+	do_tlbies(kvm, &rb, 1, 1, false);
 }
 EXPORT_SYMBOL_GPL(kvmppc_clear_ref_hpte);
 
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index b02f91e4c70d..c71103b8a748 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -29,6 +29,10 @@
 #include <asm/kvm_book3s_asm.h>
 #include <asm/mmu-hash64.h>
 
+#ifdef __LITTLE_ENDIAN__
+#error Need to fix lppaca and SLB shadow accesses in little endian mode
+#endif
+
 /*****************************************************************************
  *                                                                           *
  *        Real Mode handlers that need to be in the linear mapping           *
@@ -389,7 +393,11 @@ toc_tlbie_lock:
 	.tc	native_tlbie_lock[TC],native_tlbie_lock
 	.previous
 	ld	r3,toc_tlbie_lock@toc(2)
+#ifdef __BIG_ENDIAN__
 	lwz	r8,PACA_LOCK_TOKEN(r13)
+#else
+	lwz	r8,PACAPACAINDEX(r13)
+#endif
 24:	lwarx	r0,0,r3
 	cmpwi	r0,0
 	bne	24b
@@ -964,7 +972,11 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
 32:	ld	r4,VCPU_KVM(r9)		/* pointer to struct kvm */
 
 	/* Take the guest's tlbie_lock */
+#ifdef __BIG_ENDIAN__
 	lwz	r8,PACA_LOCK_TOKEN(r13)
+#else
+	lwz	r8,PACAPACAINDEX(r13)
+#endif
 	addi	r3,r4,KVM_TLBIE_LOCK
 24:	lwarx	r0,0,r3
 	cmpwi	r0,0
@@ -1054,7 +1066,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
 BEGIN_FTR_SECTION
 	mfspr	r8, SPRN_DSCR
 	ld	r7, HSTATE_DSCR(r13)
-	std	r8, VCPU_DSCR(r7)
+	std	r8, VCPU_DSCR(r9)
 	mtspr	SPRN_DSCR, r7
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
 
@@ -1381,7 +1393,7 @@ hcall_try_real_mode:
 	cmpldi	r3,hcall_real_table_end - hcall_real_table
 	bge	guest_exit_cont
 	LOAD_REG_ADDR(r4, hcall_real_table)
-	lwzx	r3,r3,r4
+	lwax	r3,r3,r4
 	cmpwi	r3,0
 	beq	guest_exit_cont
 	add	r3,r3,r4
diff --git a/arch/powerpc/kvm/book3s_interrupts.S b/arch/powerpc/kvm/book3s_interrupts.S
index 48cbbf862958..17cfae5497a3 100644
--- a/arch/powerpc/kvm/book3s_interrupts.S
+++ b/arch/powerpc/kvm/book3s_interrupts.S
@@ -92,6 +92,11 @@ kvm_start_lightweight:
 	PPC_LL	r3, VCPU_HFLAGS(r4)
 	rldicl	r3, r3, 0, 63		/* r3 &= 1 */
 	stb	r3, HSTATE_RESTORE_HID5(r13)
+
+	/* Load up guest SPRG3 value, since it's user readable */
+	ld	r3, VCPU_SHARED(r4)
+	ld	r3, VCPU_SHARED_SPRG3(r3)
+	mtspr	SPRN_SPRG3, r3
 #endif /* CONFIG_PPC_BOOK3S_64 */
 
 	PPC_LL	r4, VCPU_SHADOW_MSR(r4)	/* get shadow_msr */
@@ -123,6 +128,15 @@ kvmppc_handler_highmem:
 	/* R7 = vcpu */
 	PPC_LL	r7, GPR4(r1)
 
+#ifdef CONFIG_PPC_BOOK3S_64
+	/*
+	 * Reload kernel SPRG3 value.
+	 * No need to save guest value as usermode can't modify SPRG3.
+	 */
+	ld	r3, PACA_SPRG3(r13)
+	mtspr	SPRN_SPRG3, r3
+#endif /* CONFIG_PPC_BOOK3S_64 */
+
 	PPC_STL	r14, VCPU_GPR(R14)(r7)
 	PPC_STL	r15, VCPU_GPR(R15)(r7)
 	PPC_STL	r16, VCPU_GPR(R16)(r7)
diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index c6e13d9a9e15..27db1e665959 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -468,7 +468,8 @@ void kvmppc_giveup_ext(struct kvm_vcpu *vcpu, ulong msr)
 		 * both the traditional FP registers and the added VSX
 		 * registers into thread.fpr[].
 		 */
-		giveup_fpu(current);
+		if (current->thread.regs->msr & MSR_FP)
+			giveup_fpu(current);
 		for (i = 0; i < ARRAY_SIZE(vcpu->arch.fpr); i++)
 			vcpu_fpr[i] = thread_fpr[get_fpr_index(i)];
 
@@ -483,7 +484,8 @@ void kvmppc_giveup_ext(struct kvm_vcpu *vcpu, ulong msr)
 
 #ifdef CONFIG_ALTIVEC
 	if (msr & MSR_VEC) {
-		giveup_altivec(current);
+		if (current->thread.regs->msr & MSR_VEC)
+			giveup_altivec(current);
 		memcpy(vcpu->arch.vr, t->vr, sizeof(vcpu->arch.vr));
 		vcpu->arch.vscr = t->vscr;
 	}
@@ -575,8 +577,6 @@ static int kvmppc_handle_ext(struct kvm_vcpu *vcpu, unsigned int exit_nr,
 	printk(KERN_INFO "Loading up ext 0x%lx\n", msr);
 #endif
 
-	current->thread.regs->msr |= msr;
-
 	if (msr & MSR_FP) {
 		for (i = 0; i < ARRAY_SIZE(vcpu->arch.fpr); i++)
 			thread_fpr[get_fpr_index(i)] = vcpu_fpr[i];
@@ -598,12 +598,32 @@ static int kvmppc_handle_ext(struct kvm_vcpu *vcpu, unsigned int exit_nr,
 #endif
 	}
 
+	current->thread.regs->msr |= msr;
 	vcpu->arch.guest_owned_ext |= msr;
 	kvmppc_recalc_shadow_msr(vcpu);
 
 	return RESUME_GUEST;
 }
 
+/*
+ * Kernel code using FP or VMX could have flushed guest state to
+ * the thread_struct; if so, get it back now.
+ */
+static void kvmppc_handle_lost_ext(struct kvm_vcpu *vcpu)
+{
+	unsigned long lost_ext;
+
+	lost_ext = vcpu->arch.guest_owned_ext & ~current->thread.regs->msr;
+	if (!lost_ext)
+		return;
+
+	if (lost_ext & MSR_FP)
+		kvmppc_load_up_fpu();
+	if (lost_ext & MSR_VEC)
+		kvmppc_load_up_altivec();
+	current->thread.regs->msr |= lost_ext;
+}
+
 int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
                        unsigned int exit_nr)
 {
@@ -772,7 +792,7 @@ program_interrupt:
 	}
 	case BOOK3S_INTERRUPT_SYSCALL:
 		if (vcpu->arch.papr_enabled &&
-		    (kvmppc_get_last_inst(vcpu) == 0x44000022) &&
+		    (kvmppc_get_last_sc(vcpu) == 0x44000022) &&
 		    !(vcpu->arch.shared->msr & MSR_PR)) {
 			/* SC 1 papr hypercalls */
 			ulong cmd = kvmppc_get_gpr(vcpu, 3);
@@ -890,8 +910,9 @@ program_interrupt:
 			local_irq_enable();
 			r = s;
 		} else {
-			kvmppc_lazy_ee_enable();
+			kvmppc_fix_ee_before_entry();
 		}
+		kvmppc_handle_lost_ext(vcpu);
 	}
 
 	trace_kvm_book3s_reenter(r, vcpu);
@@ -1162,7 +1183,7 @@ int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 	if (vcpu->arch.shared->msr & MSR_FP)
 		kvmppc_handle_ext(vcpu, BOOK3S_INTERRUPT_FP_UNAVAIL, MSR_FP);
 
-	kvmppc_lazy_ee_enable();
+	kvmppc_fix_ee_before_entry();
 
 	ret = __kvmppc_vcpu_run(kvm_run, vcpu);
 
diff --git a/arch/powerpc/kvm/book3s_xics.c b/arch/powerpc/kvm/book3s_xics.c
index 94c1dd46b83d..a3a5cb8ee7ea 100644
--- a/arch/powerpc/kvm/book3s_xics.c
+++ b/arch/powerpc/kvm/book3s_xics.c
@@ -19,6 +19,7 @@
 #include <asm/hvcall.h>
 #include <asm/xics.h>
 #include <asm/debug.h>
+#include <asm/time.h>
 
 #include <linux/debugfs.h>
 #include <linux/seq_file.h>
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index dcc94f016007..17722d82f1d1 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -674,8 +674,6 @@ int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 		goto out;
 	}
 
-	kvm_guest_enter();
-
 #ifdef CONFIG_PPC_FPU
 	/* Save userspace FPU state in stack */
 	enable_kernel_fp();
@@ -698,7 +696,7 @@ int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 	kvmppc_load_guest_fp(vcpu);
 #endif
 
-	kvmppc_lazy_ee_enable();
+	kvmppc_fix_ee_before_entry();
 
 	ret = __kvmppc_vcpu_run(kvm_run, vcpu);
 
@@ -1168,7 +1166,7 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			local_irq_enable();
 			r = (s << 2) | RESUME_HOST | (r & RESUME_FLAG_NV);
 		} else {
-			kvmppc_lazy_ee_enable();
+			kvmppc_fix_ee_before_entry();
 		}
 	}
 
diff --git a/arch/powerpc/kvm/e500_mmu_host.c b/arch/powerpc/kvm/e500_mmu_host.c
index 1c6a9d729df4..c65593abae8e 100644
--- a/arch/powerpc/kvm/e500_mmu_host.c
+++ b/arch/powerpc/kvm/e500_mmu_host.c
@@ -332,6 +332,13 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
 	unsigned long hva;
 	int pfnmap = 0;
 	int tsize = BOOK3E_PAGESZ_4K;
+	int ret = 0;
+	unsigned long mmu_seq;
+	struct kvm *kvm = vcpu_e500->vcpu.kvm;
+
+	/* used to check for invalidations in progress */
+	mmu_seq = kvm->mmu_notifier_seq;
+	smp_rmb();
 
 	/*
 	 * Translate guest physical to true physical, acquiring
@@ -449,6 +456,12 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
 		gvaddr &= ~((tsize_pages << PAGE_SHIFT) - 1);
 	}
 
+	spin_lock(&kvm->mmu_lock);
+	if (mmu_notifier_retry(kvm, mmu_seq)) {
+		ret = -EAGAIN;
+		goto out;
+	}
+
 	kvmppc_e500_ref_setup(ref, gtlbe, pfn);
 
 	kvmppc_e500_setup_stlbe(&vcpu_e500->vcpu, gtlbe, tsize,
@@ -457,10 +470,13 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
 	/* Clear i-cache for new pages */
 	kvmppc_mmu_flush_icache(pfn);
 
+out:
+	spin_unlock(&kvm->mmu_lock);
+
 	/* Drop refcount on page, so that mmu notifiers can clear it */
 	kvm_release_pfn_clean(pfn);
 
-	return 0;
+	return ret;
 }
 
 /* XXX only map the one-one case, for now use TLB0 */
diff --git a/arch/powerpc/kvm/emulate.c b/arch/powerpc/kvm/emulate.c
index 2c52ada30775..751cd45f65a0 100644
--- a/arch/powerpc/kvm/emulate.c
+++ b/arch/powerpc/kvm/emulate.c
@@ -30,53 +30,10 @@
 #include <asm/byteorder.h>
 #include <asm/kvm_ppc.h>
 #include <asm/disassemble.h>
+#include <asm/ppc-opcode.h>
 #include "timing.h"
 #include "trace.h"
 
-#define OP_TRAP 3
-#define OP_TRAP_64 2
-
-#define OP_31_XOP_TRAP      4
-#define OP_31_XOP_LWZX      23
-#define OP_31_XOP_DCBST     54
-#define OP_31_XOP_TRAP_64   68
-#define OP_31_XOP_DCBF      86
-#define OP_31_XOP_LBZX      87
-#define OP_31_XOP_STWX      151
-#define OP_31_XOP_STBX      215
-#define OP_31_XOP_LBZUX     119
-#define OP_31_XOP_STBUX     247
-#define OP_31_XOP_LHZX      279
-#define OP_31_XOP_LHZUX     311
-#define OP_31_XOP_MFSPR     339
-#define OP_31_XOP_LHAX      343
-#define OP_31_XOP_STHX      407
-#define OP_31_XOP_STHUX     439
-#define OP_31_XOP_MTSPR     467
-#define OP_31_XOP_DCBI      470
-#define OP_31_XOP_LWBRX     534
-#define OP_31_XOP_TLBSYNC   566
-#define OP_31_XOP_STWBRX    662
-#define OP_31_XOP_LHBRX     790
-#define OP_31_XOP_STHBRX    918
-
-#define OP_LWZ  32
-#define OP_LD   58
-#define OP_LWZU 33
-#define OP_LBZ  34
-#define OP_LBZU 35
-#define OP_STW  36
-#define OP_STWU 37
-#define OP_STD  62
-#define OP_STB  38
-#define OP_STBU 39
-#define OP_LHZ  40
-#define OP_LHZU 41
-#define OP_LHA  42
-#define OP_LHAU 43
-#define OP_STH  44
-#define OP_STHU 45
-
 void kvmppc_emulate_dec(struct kvm_vcpu *vcpu)
 {
 	unsigned long dec_nsec;
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 6316ee336e88..07c0106fab76 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -117,8 +117,6 @@ int kvmppc_prepare_to_enter(struct kvm_vcpu *vcpu)
 			kvm_guest_exit();
 			continue;
 		}
-
-		trace_hardirqs_on();
 #endif
 
 		kvm_guest_enter();
@@ -420,6 +418,10 @@ int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages)
 	return kvmppc_core_create_memslot(slot, npages);
 }
 
+void kvm_arch_memslots_updated(struct kvm *kvm)
+{
+}
+
 int kvm_arch_prepare_memory_region(struct kvm *kvm,
 				   struct kvm_memory_slot *memslot,
 				   struct kvm_userspace_memory_region *mem,
@@ -823,39 +825,39 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
 #endif
 #ifdef CONFIG_KVM_MPIC
 	case KVM_CAP_IRQ_MPIC: {
-		struct file *filp;
+		struct fd f;
 		struct kvm_device *dev;
 
 		r = -EBADF;
-		filp = fget(cap->args[0]);
-		if (!filp)
+		f = fdget(cap->args[0]);
+		if (!f.file)
 			break;
 
 		r = -EPERM;
-		dev = kvm_device_from_filp(filp);
+		dev = kvm_device_from_filp(f.file);
 		if (dev)
 			r = kvmppc_mpic_connect_vcpu(dev, vcpu, cap->args[1]);
 
-		fput(filp);
+		fdput(f);
 		break;
 	}
 #endif
 #ifdef CONFIG_KVM_XICS
 	case KVM_CAP_IRQ_XICS: {
-		struct file *filp;
+		struct fd f;
 		struct kvm_device *dev;
 
 		r = -EBADF;
-		filp = fget(cap->args[0]);
-		if (!filp)
+		f = fdget(cap->args[0]);
+		if (!f.file)
 			break;
 
 		r = -EPERM;
-		dev = kvm_device_from_filp(filp);
+		dev = kvm_device_from_filp(f.file);
 		if (dev)
 			r = kvmppc_xics_connect_vcpu(dev, vcpu, cap->args[1]);
 
-		fput(filp);
+		fdput(f);
 		break;
 	}
 #endif /* CONFIG_KVM_XICS */
diff --git a/arch/powerpc/lib/checksum_64.S b/arch/powerpc/lib/checksum_64.S
index 167f72555d60..57a072065057 100644
--- a/arch/powerpc/lib/checksum_64.S
+++ b/arch/powerpc/lib/checksum_64.S
@@ -226,19 +226,35 @@ _GLOBAL(csum_partial)
 	blr
 
 
-	.macro source
+	.macro srcnr
 100:
 	.section __ex_table,"a"
 	.align 3
-	.llong 100b,.Lsrc_error
+	.llong 100b,.Lsrc_error_nr
 	.previous
 	.endm
 
-	.macro dest
+	.macro source
+150:
+	.section __ex_table,"a"
+	.align 3
+	.llong 150b,.Lsrc_error
+	.previous
+	.endm
+
+	.macro dstnr
 200:
 	.section __ex_table,"a"
 	.align 3
-	.llong 200b,.Ldest_error
+	.llong 200b,.Ldest_error_nr
+	.previous
+	.endm
+
+	.macro dest
+250:
+	.section __ex_table,"a"
+	.align 3
+	.llong 250b,.Ldest_error
 	.previous
 	.endm
 
@@ -269,16 +285,16 @@ _GLOBAL(csum_partial_copy_generic)
 	rldicl. r6,r3,64-1,64-2		/* r6 = (r3 & 0x3) >> 1 */
 	beq	.Lcopy_aligned
 
-	li	r7,4
-	sub	r6,r7,r6
+	li	r9,4
+	sub	r6,r9,r6
 	mtctr	r6
 
 1:
-source;	lhz	r6,0(r3)		/* align to doubleword */
+srcnr;	lhz	r6,0(r3)		/* align to doubleword */
 	subi	r5,r5,2
 	addi	r3,r3,2
 	adde	r0,r0,r6
-dest;	sth	r6,0(r4)
+dstnr;	sth	r6,0(r4)
 	addi	r4,r4,2
 	bdnz	1b
 
@@ -392,10 +408,10 @@ dest;	std	r16,56(r4)
 
 	mtctr	r6
 3:
-source;	ld	r6,0(r3)
+srcnr;	ld	r6,0(r3)
 	addi	r3,r3,8
 	adde	r0,r0,r6
-dest;	std	r6,0(r4)
+dstnr;	std	r6,0(r4)
 	addi	r4,r4,8
 	bdnz	3b
 
@@ -405,10 +421,10 @@ dest;	std	r6,0(r4)
 	srdi.	r6,r5,2
 	beq	.Lcopy_tail_halfword
 
-source;	lwz	r6,0(r3)
+srcnr;	lwz	r6,0(r3)
 	addi	r3,r3,4
 	adde	r0,r0,r6
-dest;	stw	r6,0(r4)
+dstnr;	stw	r6,0(r4)
 	addi	r4,r4,4
 	subi	r5,r5,4
 
@@ -416,10 +432,10 @@ dest;	stw	r6,0(r4)
 	srdi.	r6,r5,1
 	beq	.Lcopy_tail_byte
 
-source;	lhz	r6,0(r3)
+srcnr;	lhz	r6,0(r3)
 	addi	r3,r3,2
 	adde	r0,r0,r6
-dest;	sth	r6,0(r4)
+dstnr;	sth	r6,0(r4)
 	addi	r4,r4,2
 	subi	r5,r5,2
 
@@ -427,10 +443,10 @@ dest;	sth	r6,0(r4)
 	andi.	r6,r5,1
 	beq	.Lcopy_finish
 
-source;	lbz	r6,0(r3)
+srcnr;	lbz	r6,0(r3)
 	sldi	r9,r6,8			/* Pad the byte out to 16 bits */
 	adde	r0,r0,r9
-dest;	stb	r6,0(r4)
+dstnr;	stb	r6,0(r4)
 
 .Lcopy_finish:
 	addze	r0,r0			/* add in final carry */
@@ -440,6 +456,11 @@ dest;	stb	r6,0(r4)
 	blr
 
 .Lsrc_error:
+	ld	r14,STK_REG(R14)(r1)
+	ld	r15,STK_REG(R15)(r1)
+	ld	r16,STK_REG(R16)(r1)
+	addi	r1,r1,STACKFRAMESIZE
+.Lsrc_error_nr:
 	cmpdi	0,r7,0
 	beqlr
 	li	r6,-EFAULT
@@ -447,6 +468,11 @@ dest;	stb	r6,0(r4)
 	blr
 
 .Ldest_error:
+	ld	r14,STK_REG(R14)(r1)
+	ld	r15,STK_REG(R15)(r1)
+	ld	r16,STK_REG(R16)(r1)
+	addi	r1,r1,STACKFRAMESIZE
+.Ldest_error_nr:
 	cmpdi	0,r8,0
 	beqlr
 	li	r6,-EFAULT
diff --git a/arch/powerpc/lib/locks.c b/arch/powerpc/lib/locks.c
index bb7cfecf2788..0c9c8d7d0734 100644
--- a/arch/powerpc/lib/locks.c
+++ b/arch/powerpc/lib/locks.c
@@ -32,7 +32,7 @@ void __spin_yield(arch_spinlock_t *lock)
 		return;
 	holder_cpu = lock_value & 0xffff;
 	BUG_ON(holder_cpu >= NR_CPUS);
-	yield_count = lppaca_of(holder_cpu).yield_count;
+	yield_count = be32_to_cpu(lppaca_of(holder_cpu).yield_count);
 	if ((yield_count & 1) == 0)
 		return;		/* virtual cpu is currently running */
 	rmb();
@@ -57,7 +57,7 @@ void __rw_yield(arch_rwlock_t *rw)
 		return;		/* no write lock at present */
 	holder_cpu = lock_value & 0xffff;
 	BUG_ON(holder_cpu >= NR_CPUS);
-	yield_count = lppaca_of(holder_cpu).yield_count;
+	yield_count = be32_to_cpu(lppaca_of(holder_cpu).yield_count);
 	if ((yield_count & 1) == 0)
 		return;		/* virtual cpu is currently running */
 	rmb();
diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c
index 99c7fc16dc0d..b1faa1593c90 100644
--- a/arch/powerpc/lib/sstep.c
+++ b/arch/powerpc/lib/sstep.c
@@ -100,8 +100,10 @@ static unsigned long __kprobes dform_ea(unsigned int instr, struct pt_regs *regs
 	ea = (signed short) instr;		/* sign-extend */
 	if (ra) {
 		ea += regs->gpr[ra];
-		if (instr & 0x04000000)		/* update forms */
-			regs->gpr[ra] = ea;
+		if (instr & 0x04000000) {		/* update forms */
+			if ((instr>>26) != 47) 		/* stmw is not an update form */
+				regs->gpr[ra] = ea;
+		}
 	}
 
 	return truncate_if_32bit(regs->msr, ea);
@@ -279,7 +281,7 @@ static int __kprobes write_mem_unaligned(unsigned long val, unsigned long ea,
 		err = write_mem_aligned(val >> (nb - c) * 8, ea, c);
 		if (err)
 			return err;
-		++ea;
+		ea += c;
 	}
 	return 0;
 }
@@ -1503,6 +1505,7 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 		 */
 		if ((ra == 1) && !(regs->msr & MSR_PR) \
 			&& (val3 >= (regs->gpr[1] - STACK_INT_FRAME_SIZE))) {
+#ifdef CONFIG_PPC32
 			/*
 			 * Check if we will touch kernel sack overflow
 			 */
@@ -1511,7 +1514,7 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 				err = -EINVAL;
 				break;
 			}
-
+#endif /* CONFIG_PPC32 */
 			/*
 			 * Check if we already set since that means we'll
 			 * lose the previous value.
diff --git a/arch/powerpc/math-emu/Makefile b/arch/powerpc/math-emu/Makefile
index 8d035d2d42a6..1b46ab4f6417 100644
--- a/arch/powerpc/math-emu/Makefile
+++ b/arch/powerpc/math-emu/Makefile
@@ -1,15 +1,15 @@
-
-obj-$(CONFIG_MATH_EMULATION)	+= fabs.o fadd.o fadds.o fcmpo.o fcmpu.o \
-					fctiw.o fctiwz.o fdiv.o fdivs.o \
-					fmadd.o fmadds.o fmsub.o fmsubs.o \
-					fmul.o fmuls.o fnabs.o fneg.o \
-					fnmadd.o fnmadds.o fnmsub.o fnmsubs.o \
-					fres.o fre.o frsp.o fsel.o lfs.o \
-					frsqrte.o frsqrtes.o \
-					fsqrt.o	fsqrts.o fsub.o fsubs.o \
-					mcrfs.o mffs.o mtfsb0.o mtfsb1.o \
-					mtfsf.o mtfsfi.o stfiwx.o stfs.o \
-					math.o fmr.o lfd.o stfd.o
+math-emu-common-objs = math.o fre.o fsqrt.o fsqrts.o frsqrtes.o mtfsf.o mtfsfi.o
+obj-$(CONFIG_MATH_EMULATION_HW_UNIMPLEMENTED) += $(math-emu-common-objs)
+obj-$(CONFIG_MATH_EMULATION_FULL) += $(math-emu-common-objs) fabs.o fadd.o \
+					fadds.o fcmpo.o fcmpu.o fctiw.o \
+					fctiwz.o fdiv.o fdivs.o  fmadd.o \
+					fmadds.o fmsub.o fmsubs.o fmul.o \
+					fmuls.o fnabs.o fneg.o fnmadd.o \
+					fnmadds.o fnmsub.o fnmsubs.o fres.o \
+					frsp.o fsel.o lfs.o frsqrte.o fsub.o \
+					fsubs.o  mcrfs.o mffs.o mtfsb0.o \
+					mtfsb1.o stfiwx.o stfs.o math.o \
+					fmr.o lfd.o stfd.o
 
 obj-$(CONFIG_SPE)		+= math_efp.o
 
diff --git a/arch/powerpc/math-emu/math.c b/arch/powerpc/math-emu/math.c
index 0328e66e0799..ab151f040502 100644
--- a/arch/powerpc/math-emu/math.c
+++ b/arch/powerpc/math-emu/math.c
@@ -7,12 +7,27 @@
 
 #include <asm/uaccess.h>
 #include <asm/reg.h>
+#include <asm/switch_to.h>
 
 #include <asm/sfp-machine.h>
 #include <math-emu/double.h>
 
 #define FLOATFUNC(x)	extern int x(void *, void *, void *, void *)
 
+/* The instructions list which may be not implemented by a hardware FPU */
+FLOATFUNC(fre);
+FLOATFUNC(frsqrtes);
+FLOATFUNC(fsqrt);
+FLOATFUNC(fsqrts);
+FLOATFUNC(mtfsf);
+FLOATFUNC(mtfsfi);
+
+#ifdef CONFIG_MATH_EMULATION_HW_UNIMPLEMENTED
+#undef FLOATFUNC(x)
+#define FLOATFUNC(x)	static inline int x(void *op1, void *op2, void *op3, \
+						 void *op4) { }
+#endif
+
 FLOATFUNC(fadd);
 FLOATFUNC(fadds);
 FLOATFUNC(fdiv);
@@ -42,8 +57,6 @@ FLOATFUNC(mcrfs);
 FLOATFUNC(mffs);
 FLOATFUNC(mtfsb0);
 FLOATFUNC(mtfsb1);
-FLOATFUNC(mtfsf);
-FLOATFUNC(mtfsfi);
 
 FLOATFUNC(lfd);
 FLOATFUNC(lfs);
@@ -58,13 +71,9 @@ FLOATFUNC(fnabs);
 FLOATFUNC(fneg);
 
 /* Optional */
-FLOATFUNC(fre);
 FLOATFUNC(fres);
 FLOATFUNC(frsqrte);
-FLOATFUNC(frsqrtes);
 FLOATFUNC(fsel);
-FLOATFUNC(fsqrt);
-FLOATFUNC(fsqrts);
 
 
 #define OP31		0x1f		/*   31 */
@@ -154,7 +163,6 @@ FLOATFUNC(fsqrts);
 #define XEU	15
 #define XFLB	10
 
-#ifdef CONFIG_MATH_EMULATION
 static int
 record_exception(struct pt_regs *regs, int eflag)
 {
@@ -212,7 +220,6 @@ record_exception(struct pt_regs *regs, int eflag)
 
 	return (fpscr & FPSCR_FEX) ? 1 : 0;
 }
-#endif /* CONFIG_MATH_EMULATION */
 
 int
 do_mathemu(struct pt_regs *regs)
@@ -222,56 +229,13 @@ do_mathemu(struct pt_regs *regs)
 	signed short sdisp;
 	u32 insn = 0;
 	int idx = 0;
-#ifdef CONFIG_MATH_EMULATION
 	int (*func)(void *, void *, void *, void *);
 	int type = 0;
 	int eflag, trap;
-#endif
 
 	if (get_user(insn, (u32 *)pc))
 		return -EFAULT;
 
-#ifndef CONFIG_MATH_EMULATION
-	switch (insn >> 26) {
-	case LFD:
-		idx = (insn >> 16) & 0x1f;
-		sdisp = (insn & 0xffff);
-		op0 = (void *)&current->thread.TS_FPR((insn >> 21) & 0x1f);
-		op1 = (void *)((idx ? regs->gpr[idx] : 0) + sdisp);
-		lfd(op0, op1, op2, op3);
-		break;
-	case LFDU:
-		idx = (insn >> 16) & 0x1f;
-		sdisp = (insn & 0xffff);
-		op0 = (void *)&current->thread.TS_FPR((insn >> 21) & 0x1f);
-		op1 = (void *)((idx ? regs->gpr[idx] : 0) + sdisp);
-		lfd(op0, op1, op2, op3);
-		regs->gpr[idx] = (unsigned long)op1;
-		break;
-	case STFD:
-		idx = (insn >> 16) & 0x1f;
-		sdisp = (insn & 0xffff);
-		op0 = (void *)&current->thread.TS_FPR((insn >> 21) & 0x1f);
-		op1 = (void *)((idx ? regs->gpr[idx] : 0) + sdisp);
-		stfd(op0, op1, op2, op3);
-		break;
-	case STFDU:
-		idx = (insn >> 16) & 0x1f;
-		sdisp = (insn & 0xffff);
-		op0 = (void *)&current->thread.TS_FPR((insn >> 21) & 0x1f);
-		op1 = (void *)((idx ? regs->gpr[idx] : 0) + sdisp);
-		stfd(op0, op1, op2, op3);
-		regs->gpr[idx] = (unsigned long)op1;
-		break;
-	case OP63:
-		op0 = (void *)&current->thread.TS_FPR((insn >> 21) & 0x1f);
-		op1 = (void *)&current->thread.TS_FPR((insn >> 11) & 0x1f);
-		fmr(op0, op1, op2, op3);
-		break;
-	default:
-		goto illegal;
-	}
-#else /* CONFIG_MATH_EMULATION */
 	switch (insn >> 26) {
 	case LFS:	func = lfs;	type = D;	break;
 	case LFSU:	func = lfs;	type = DU;	break;
@@ -416,21 +380,16 @@ do_mathemu(struct pt_regs *regs)
 	case XE:
 		idx = (insn >> 16) & 0x1f;
 		op0 = (void *)&current->thread.TS_FPR((insn >> 21) & 0x1f);
-		if (!idx) {
-			if (((insn >> 1) & 0x3ff) == STFIWX)
-				op1 = (void *)(regs->gpr[(insn >> 11) & 0x1f]);
-			else
-				goto illegal;
-		} else {
-			op1 = (void *)(regs->gpr[idx] + regs->gpr[(insn >> 11) & 0x1f]);
-		}
-
+		op1 = (void *)((idx ? regs->gpr[idx] : 0)
+				+ regs->gpr[(insn >> 11) & 0x1f]);
 		break;
 
 	case XEU:
 		idx = (insn >> 16) & 0x1f;
+		if (!idx)
+			goto illegal;
 		op0 = (void *)&current->thread.TS_FPR((insn >> 21) & 0x1f);
-		op1 = (void *)((idx ? regs->gpr[idx] : 0)
+		op1 = (void *)(regs->gpr[idx]
 				+ regs->gpr[(insn >> 11) & 0x1f]);
 		break;
 
@@ -465,6 +424,13 @@ do_mathemu(struct pt_regs *regs)
 		goto illegal;
 	}
 
+	/*
+	 * If we support a HW FPU, we need to ensure the FP state
+	 * is flushed into the thread_struct before attempting
+	 * emulation
+	 */
+	flush_fp_to_thread(current);
+
 	eflag = func(op0, op1, op2, op3);
 
 	if (insn & 1) {
@@ -485,7 +451,6 @@ do_mathemu(struct pt_regs *regs)
 	default:
 		break;
 	}
-#endif /* CONFIG_MATH_EMULATION */
 
 	regs->nip += 4;
 	return 0;
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 8726779e1409..51ab9e7e6c39 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -206,7 +206,7 @@ int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address,
 	int trap = TRAP(regs);
  	int is_exec = trap == 0x400;
 	int fault;
-	int rc = 0;
+	int rc = 0, store_update_sp = 0;
 
 #if !(defined(CONFIG_4xx) || defined(CONFIG_BOOKE))
 	/*
@@ -223,9 +223,6 @@ int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address,
 	is_write = error_code & ESR_DST;
 #endif /* CONFIG_4xx || CONFIG_BOOKE */
 
-	if (is_write)
-		flags |= FAULT_FLAG_WRITE;
-
 #ifdef CONFIG_PPC_ICSWX
 	/*
 	 * we need to do this early because this "data storage
@@ -280,6 +277,17 @@ int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address,
 
 	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
 
+	/*
+	 * We want to do this outside mmap_sem, because reading code around nip
+	 * can result in fault, which will cause a deadlock when called with
+	 * mmap_sem held
+	 */
+	if (user_mode(regs))
+		store_update_sp = store_updates_sp(regs);
+
+	if (user_mode(regs))
+		flags |= FAULT_FLAG_USER;
+
 	/* When running in the kernel we expect faults to occur only to
 	 * addresses in user space.  All other faults represent errors in the
 	 * kernel and should generate an OOPS.  Unfortunately, in the case of an
@@ -345,8 +353,7 @@ retry:
 		 * between the last mapped region and the stack will
 		 * expand the stack rather than segfaulting.
 		 */
-		if (address + 2048 < uregs->gpr[1]
-		    && (!user_mode(regs) || !store_updates_sp(regs)))
+		if (address + 2048 < uregs->gpr[1] && !store_update_sp)
 			goto bad_area;
 	}
 	if (expand_stack(vma, address))
@@ -408,6 +415,7 @@ good_area:
 	} else if (is_write) {
 		if (!(vma->vm_flags & VM_WRITE))
 			goto bad_area;
+		flags |= FAULT_FLAG_WRITE;
 	/* a read */
 	} else {
 		/* protection fault */
@@ -443,8 +451,12 @@ good_area:
 				      regs, address);
 #ifdef CONFIG_PPC_SMLPAR
 			if (firmware_has_feature(FW_FEATURE_CMO)) {
+				u32 page_ins;
+
 				preempt_disable();
-				get_lppaca()->page_ins += (1 << PAGE_FACTOR);
+				page_ins = be32_to_cpu(get_lppaca()->page_ins);
+				page_ins += 1 << PAGE_FACTOR;
+				get_lppaca()->page_ins = cpu_to_be32(page_ins);
 				preempt_enable();
 			}
 #endif /* CONFIG_PPC_SMLPAR */
diff --git a/arch/powerpc/mm/gup.c b/arch/powerpc/mm/gup.c
index 49822d90ea96..6936547018b8 100644
--- a/arch/powerpc/mm/gup.c
+++ b/arch/powerpc/mm/gup.c
@@ -117,8 +117,8 @@ static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end,
 	return 1;
 }
 
-int get_user_pages_fast(unsigned long start, int nr_pages, int write,
-			struct page **pages)
+int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
+			  struct page **pages)
 {
 	struct mm_struct *mm = current->mm;
 	unsigned long addr, len, end;
@@ -135,7 +135,7 @@ int get_user_pages_fast(unsigned long start, int nr_pages, int write,
 
 	if (unlikely(!access_ok(write ? VERIFY_WRITE : VERIFY_READ,
 					start, len)))
-		goto slow_irqon;
+		return 0;
 
 	pr_devel("  aligned: %lx .. %lx\n", start, end);
 
@@ -166,30 +166,35 @@ int get_user_pages_fast(unsigned long start, int nr_pages, int write,
 			 (void *)pgd_val(pgd));
 		next = pgd_addr_end(addr, end);
 		if (pgd_none(pgd))
-			goto slow;
+			break;
 		if (pgd_huge(pgd)) {
 			if (!gup_hugepte((pte_t *)pgdp, PGDIR_SIZE, addr, next,
 					 write, pages, &nr))
-				goto slow;
+				break;
 		} else if (is_hugepd(pgdp)) {
 			if (!gup_hugepd((hugepd_t *)pgdp, PGDIR_SHIFT,
 					addr, next, write, pages, &nr))
-				goto slow;
+				break;
 		} else if (!gup_pud_range(pgd, addr, next, write, pages, &nr))
-			goto slow;
+			break;
 	} while (pgdp++, addr = next, addr != end);
 
 	local_irq_enable();
 
-	VM_BUG_ON(nr != (end - start) >> PAGE_SHIFT);
 	return nr;
+}
 
-	{
-		int ret;
+int get_user_pages_fast(unsigned long start, int nr_pages, int write,
+			struct page **pages)
+{
+	struct mm_struct *mm = current->mm;
+	int nr, ret;
+
+	start &= PAGE_MASK;
+	nr = __get_user_pages_fast(start, nr_pages, write, pages);
+	ret = nr;
 
-slow:
-		local_irq_enable();
-slow_irqon:
+	if (nr < nr_pages) {
 		pr_devel("  slow path ! nr = %d\n", nr);
 
 		/* Try to get the remaining pages with get_user_pages */
@@ -198,7 +203,7 @@ slow_irqon:
 
 		down_read(&mm->mmap_sem);
 		ret = get_user_pages(current, mm, start,
-			(end - start) >> PAGE_SHIFT, write, 0, pages, NULL);
+				     nr_pages - nr, write, 0, pages, NULL);
 		up_read(&mm->mmap_sem);
 
 		/* Have to be a bit careful with return values */
@@ -208,9 +213,9 @@ slow_irqon:
 			else
 				ret += nr;
 		}
-
-		return ret;
 	}
+
+	return ret;
 }
 
 #endif /* __HAVE_ARCH_PTE_SPECIAL */
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index 6ecc38bd5b24..bde8b5589755 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -907,7 +907,7 @@ static int subpage_protection(struct mm_struct *mm, unsigned long ea)
 
 	if (ea >= spt->maxaddr)
 		return 0;
-	if (ea < 0x100000000) {
+	if (ea < 0x100000000UL) {
 		/* addresses below 4GB use spt->low_prot */
 		sbpm = spt->low_prot;
 	} else {
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index 834ca8eb38f2..d67db4bd672d 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -86,6 +86,11 @@ int pgd_huge(pgd_t pgd)
 	 */
 	return ((pgd_val(pgd) & 0x3) != 0x0);
 }
+
+int pmd_huge_support(void)
+{
+	return 1;
+}
 #else
 int pmd_huge(pmd_t pmd)
 {
@@ -101,6 +106,11 @@ int pgd_huge(pgd_t pgd)
 {
 	return 0;
 }
+
+int pmd_huge_support(void)
+{
+	return 0;
+}
 #endif
 
 pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
diff --git a/arch/powerpc/mm/init_32.c b/arch/powerpc/mm/init_32.c
index 01e2db97a210..d47d3dab4870 100644
--- a/arch/powerpc/mm/init_32.c
+++ b/arch/powerpc/mm/init_32.c
@@ -52,7 +52,7 @@
 #if defined(CONFIG_KERNEL_START_BOOL) || defined(CONFIG_LOWMEM_SIZE_BOOL)
 /* The amount of lowmem must be within 0xF0000000 - KERNELBASE. */
 #if (CONFIG_LOWMEM_SIZE > (0xF0000000 - PAGE_OFFSET))
-#error "You must adjust CONFIG_LOWMEM_SIZE or CONFIG_START_KERNEL"
+#error "You must adjust CONFIG_LOWMEM_SIZE or CONFIG_KERNEL_START"
 #endif
 #endif
 #define MAX_LOW_MEM	CONFIG_LOWMEM_SIZE
diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c
index d0cd9e4c6837..8ed035d2edb5 100644
--- a/arch/powerpc/mm/init_64.c
+++ b/arch/powerpc/mm/init_64.c
@@ -300,5 +300,9 @@ void vmemmap_free(unsigned long start, unsigned long end)
 {
 }
 
+void register_page_bootmem_memmap(unsigned long section_nr,
+				  struct page *start_page, unsigned long size)
+{
+}
 #endif /* CONFIG_SPARSEMEM_VMEMMAP */
 
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index 7f4bea162026..3fa93dc7fe75 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -297,12 +297,21 @@ void __init paging_init(void)
 }
 #endif /* ! CONFIG_NEED_MULTIPLE_NODES */
 
+static void __init register_page_bootmem_info(void)
+{
+	int i;
+
+	for_each_online_node(i)
+		register_page_bootmem_info_node(NODE_DATA(i));
+}
+
 void __init mem_init(void)
 {
 #ifdef CONFIG_SWIOTLB
 	swiotlb_init(0);
 #endif
 
+	register_page_bootmem_info();
 	high_memory = (void *) __va(max_low_pfn * PAGE_SIZE);
 	set_max_mapnr(max_pfn);
 	free_all_bootmem();
@@ -514,7 +523,7 @@ static int add_system_ram_resources(void)
 			res->name = "System RAM";
 			res->start = base;
 			res->end = base + size - 1;
-			res->flags = IORESOURCE_MEM;
+			res->flags = IORESOURCE_MEM | IORESOURCE_BUSY;
 			WARN_ON(request_resource(&iomem_resource, res) < 0);
 		}
 	}
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 5850798826cd..c916127f10c3 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -58,7 +58,7 @@ static int form1_affinity;
 
 #define MAX_DISTANCE_REF_POINTS 4
 static int distance_ref_points_depth;
-static const unsigned int *distance_ref_points;
+static const __be32 *distance_ref_points;
 static int distance_lookup_table[MAX_NUMNODES][MAX_DISTANCE_REF_POINTS];
 
 /*
@@ -179,7 +179,7 @@ static void unmap_cpu_from_node(unsigned long cpu)
 #endif /* CONFIG_HOTPLUG_CPU || CONFIG_PPC_SPLPAR */
 
 /* must hold reference to node during call */
-static const int *of_get_associativity(struct device_node *dev)
+static const __be32 *of_get_associativity(struct device_node *dev)
 {
 	return of_get_property(dev, "ibm,associativity", NULL);
 }
@@ -189,9 +189,9 @@ static const int *of_get_associativity(struct device_node *dev)
  * it exists (the property exists only in kexec/kdump kernels,
  * added by kexec-tools)
  */
-static const u32 *of_get_usable_memory(struct device_node *memory)
+static const __be32 *of_get_usable_memory(struct device_node *memory)
 {
-	const u32 *prop;
+	const __be32 *prop;
 	u32 len;
 	prop = of_get_property(memory, "linux,drconf-usable-memory", &len);
 	if (!prop || len < sizeof(unsigned int))
@@ -219,7 +219,7 @@ int __node_distance(int a, int b)
 }
 
 static void initialize_distance_lookup_table(int nid,
-		const unsigned int *associativity)
+		const __be32 *associativity)
 {
 	int i;
 
@@ -227,29 +227,32 @@ static void initialize_distance_lookup_table(int nid,
 		return;
 
 	for (i = 0; i < distance_ref_points_depth; i++) {
-		distance_lookup_table[nid][i] =
-			associativity[distance_ref_points[i]];
+		const __be32 *entry;
+
+		entry = &associativity[be32_to_cpu(distance_ref_points[i])];
+		distance_lookup_table[nid][i] = of_read_number(entry, 1);
 	}
 }
 
 /* Returns nid in the range [0..MAX_NUMNODES-1], or -1 if no useful numa
  * info is found.
  */
-static int associativity_to_nid(const unsigned int *associativity)
+static int associativity_to_nid(const __be32 *associativity)
 {
 	int nid = -1;
 
 	if (min_common_depth == -1)
 		goto out;
 
-	if (associativity[0] >= min_common_depth)
-		nid = associativity[min_common_depth];
+	if (of_read_number(associativity, 1) >= min_common_depth)
+		nid = of_read_number(&associativity[min_common_depth], 1);
 
 	/* POWER4 LPAR uses 0xffff as invalid node */
 	if (nid == 0xffff || nid >= MAX_NUMNODES)
 		nid = -1;
 
-	if (nid > 0 && associativity[0] >= distance_ref_points_depth)
+	if (nid > 0 &&
+	    of_read_number(associativity, 1) >= distance_ref_points_depth)
 		initialize_distance_lookup_table(nid, associativity);
 
 out:
@@ -262,7 +265,7 @@ out:
 static int of_node_to_nid_single(struct device_node *device)
 {
 	int nid = -1;
-	const unsigned int *tmp;
+	const __be32 *tmp;
 
 	tmp = of_get_associativity(device);
 	if (tmp)
@@ -334,7 +337,7 @@ static int __init find_min_common_depth(void)
 	}
 
 	if (form1_affinity) {
-		depth = distance_ref_points[0];
+		depth = of_read_number(distance_ref_points, 1);
 	} else {
 		if (distance_ref_points_depth < 2) {
 			printk(KERN_WARNING "NUMA: "
@@ -342,7 +345,7 @@ static int __init find_min_common_depth(void)
 			goto err;
 		}
 
-		depth = distance_ref_points[1];
+		depth = of_read_number(&distance_ref_points[1], 1);
 	}
 
 	/*
@@ -376,12 +379,12 @@ static void __init get_n_mem_cells(int *n_addr_cells, int *n_size_cells)
 	of_node_put(memory);
 }
 
-static unsigned long read_n_cells(int n, const unsigned int **buf)
+static unsigned long read_n_cells(int n, const __be32 **buf)
 {
 	unsigned long result = 0;
 
 	while (n--) {
-		result = (result << 32) | **buf;
+		result = (result << 32) | of_read_number(*buf, 1);
 		(*buf)++;
 	}
 	return result;
@@ -391,17 +394,17 @@ static unsigned long read_n_cells(int n, const unsigned int **buf)
  * Read the next memblock list entry from the ibm,dynamic-memory property
  * and return the information in the provided of_drconf_cell structure.
  */
-static void read_drconf_cell(struct of_drconf_cell *drmem, const u32 **cellp)
+static void read_drconf_cell(struct of_drconf_cell *drmem, const __be32 **cellp)
 {
-	const u32 *cp;
+	const __be32 *cp;
 
 	drmem->base_addr = read_n_cells(n_mem_addr_cells, cellp);
 
 	cp = *cellp;
-	drmem->drc_index = cp[0];
-	drmem->reserved = cp[1];
-	drmem->aa_index = cp[2];
-	drmem->flags = cp[3];
+	drmem->drc_index = of_read_number(cp, 1);
+	drmem->reserved = of_read_number(&cp[1], 1);
+	drmem->aa_index = of_read_number(&cp[2], 1);
+	drmem->flags = of_read_number(&cp[3], 1);
 
 	*cellp = cp + 4;
 }
@@ -413,16 +416,16 @@ static void read_drconf_cell(struct of_drconf_cell *drmem, const u32 **cellp)
  * list entries followed by N memblock list entries.  Each memblock list entry
  * contains information as laid out in the of_drconf_cell struct above.
  */
-static int of_get_drconf_memory(struct device_node *memory, const u32 **dm)
+static int of_get_drconf_memory(struct device_node *memory, const __be32 **dm)
 {
-	const u32 *prop;
+	const __be32 *prop;
 	u32 len, entries;
 
 	prop = of_get_property(memory, "ibm,dynamic-memory", &len);
 	if (!prop || len < sizeof(unsigned int))
 		return 0;
 
-	entries = *prop++;
+	entries = of_read_number(prop++, 1);
 
 	/* Now that we know the number of entries, revalidate the size
 	 * of the property read in to ensure we have everything
@@ -440,7 +443,7 @@ static int of_get_drconf_memory(struct device_node *memory, const u32 **dm)
  */
 static u64 of_get_lmb_size(struct device_node *memory)
 {
-	const u32 *prop;
+	const __be32 *prop;
 	u32 len;
 
 	prop = of_get_property(memory, "ibm,lmb-size", &len);
@@ -453,7 +456,7 @@ static u64 of_get_lmb_size(struct device_node *memory)
 struct assoc_arrays {
 	u32	n_arrays;
 	u32	array_sz;
-	const u32 *arrays;
+	const __be32 *arrays;
 };
 
 /*
@@ -469,15 +472,15 @@ struct assoc_arrays {
 static int of_get_assoc_arrays(struct device_node *memory,
 			       struct assoc_arrays *aa)
 {
-	const u32 *prop;
+	const __be32 *prop;
 	u32 len;
 
 	prop = of_get_property(memory, "ibm,associativity-lookup-arrays", &len);
 	if (!prop || len < 2 * sizeof(unsigned int))
 		return -1;
 
-	aa->n_arrays = *prop++;
-	aa->array_sz = *prop++;
+	aa->n_arrays = of_read_number(prop++, 1);
+	aa->array_sz = of_read_number(prop++, 1);
 
 	/* Now that we know the number of arrays and size of each array,
 	 * revalidate the size of the property read in.
@@ -504,7 +507,7 @@ static int of_drconf_to_nid_single(struct of_drconf_cell *drmem,
 	    !(drmem->flags & DRCONF_MEM_AI_INVALID) &&
 	    drmem->aa_index < aa->n_arrays) {
 		index = drmem->aa_index * aa->array_sz + min_common_depth - 1;
-		nid = aa->arrays[index];
+		nid = of_read_number(&aa->arrays[index], 1);
 
 		if (nid == 0xffff || nid >= MAX_NUMNODES)
 			nid = default_nid;
@@ -595,7 +598,7 @@ static unsigned long __init numa_enforce_memory_limit(unsigned long start,
  * Reads the counter for a given entry in
  * linux,drconf-usable-memory property
  */
-static inline int __init read_usm_ranges(const u32 **usm)
+static inline int __init read_usm_ranges(const __be32 **usm)
 {
 	/*
 	 * For each lmb in ibm,dynamic-memory a corresponding
@@ -612,7 +615,7 @@ static inline int __init read_usm_ranges(const u32 **usm)
  */
 static void __init parse_drconf_memory(struct device_node *memory)
 {
-	const u32 *uninitialized_var(dm), *usm;
+	const __be32 *uninitialized_var(dm), *usm;
 	unsigned int n, rc, ranges, is_kexec_kdump = 0;
 	unsigned long lmb_size, base, size, sz;
 	int nid;
@@ -721,7 +724,7 @@ static int __init parse_numa_properties(void)
 		unsigned long size;
 		int nid;
 		int ranges;
-		const unsigned int *memcell_buf;
+		const __be32 *memcell_buf;
 		unsigned int len;
 
 		memcell_buf = of_get_property(memory,
@@ -1106,7 +1109,7 @@ early_param("numa", early_numa);
 static int hot_add_drconf_scn_to_nid(struct device_node *memory,
 				     unsigned long scn_addr)
 {
-	const u32 *dm;
+	const __be32 *dm;
 	unsigned int drconf_cell_cnt, rc;
 	unsigned long lmb_size;
 	struct assoc_arrays aa;
@@ -1159,7 +1162,7 @@ int hot_add_node_scn_to_nid(unsigned long scn_addr)
 	for_each_node_by_type(memory, "memory") {
 		unsigned long start, size;
 		int ranges;
-		const unsigned int *memcell_buf;
+		const __be32 *memcell_buf;
 		unsigned int len;
 
 		memcell_buf = of_get_property(memory, "reg", &len);
@@ -1232,7 +1235,7 @@ static u64 hot_add_drconf_memory_max(void)
         struct device_node *memory = NULL;
         unsigned int drconf_cell_cnt = 0;
         u64 lmb_size = 0;
-        const u32 *dm = 0;
+	const __be32 *dm = 0;
 
         memory = of_find_node_by_path("/ibm,dynamic-reconfiguration-memory");
         if (memory) {
@@ -1337,40 +1340,41 @@ static int update_cpu_associativity_changes_mask(void)
  * Convert the associativity domain numbers returned from the hypervisor
  * to the sequence they would appear in the ibm,associativity property.
  */
-static int vphn_unpack_associativity(const long *packed, unsigned int *unpacked)
+static int vphn_unpack_associativity(const long *packed, __be32 *unpacked)
 {
 	int i, nr_assoc_doms = 0;
-	const u16 *field = (const u16*) packed;
+	const __be16 *field = (const __be16 *) packed;
 
 #define VPHN_FIELD_UNUSED	(0xffff)
 #define VPHN_FIELD_MSB		(0x8000)
 #define VPHN_FIELD_MASK		(~VPHN_FIELD_MSB)
 
 	for (i = 1; i < VPHN_ASSOC_BUFSIZE; i++) {
-		if (*field == VPHN_FIELD_UNUSED) {
+		if (be16_to_cpup(field) == VPHN_FIELD_UNUSED) {
 			/* All significant fields processed, and remaining
 			 * fields contain the reserved value of all 1's.
 			 * Just store them.
 			 */
-			unpacked[i] = *((u32*)field);
+			unpacked[i] = *((__be32 *)field);
 			field += 2;
-		} else if (*field & VPHN_FIELD_MSB) {
+		} else if (be16_to_cpup(field) & VPHN_FIELD_MSB) {
 			/* Data is in the lower 15 bits of this field */
-			unpacked[i] = *field & VPHN_FIELD_MASK;
+			unpacked[i] = cpu_to_be32(
+				be16_to_cpup(field) & VPHN_FIELD_MASK);
 			field++;
 			nr_assoc_doms++;
 		} else {
 			/* Data is in the lower 15 bits of this field
 			 * concatenated with the next 16 bit field
 			 */
-			unpacked[i] = *((u32*)field);
+			unpacked[i] = *((__be32 *)field);
 			field += 2;
 			nr_assoc_doms++;
 		}
 	}
 
 	/* The first cell contains the length of the property */
-	unpacked[0] = nr_assoc_doms;
+	unpacked[0] = cpu_to_be32(nr_assoc_doms);
 
 	return nr_assoc_doms;
 }
@@ -1379,7 +1383,7 @@ static int vphn_unpack_associativity(const long *packed, unsigned int *unpacked)
  * Retrieve the new associativity information for a virtual processor's
  * home node.
  */
-static long hcall_vphn(unsigned long cpu, unsigned int *associativity)
+static long hcall_vphn(unsigned long cpu, __be32 *associativity)
 {
 	long rc;
 	long retbuf[PLPAR_HCALL9_BUFSIZE] = {0};
@@ -1393,7 +1397,7 @@ static long hcall_vphn(unsigned long cpu, unsigned int *associativity)
 }
 
 static long vphn_get_associativity(unsigned long cpu,
-					unsigned int *associativity)
+					__be32 *associativity)
 {
 	long rc;
 
@@ -1450,7 +1454,7 @@ int arch_update_cpu_topology(void)
 {
 	unsigned int cpu, sibling, changed = 0;
 	struct topology_update_data *updates, *ud;
-	unsigned int associativity[VPHN_ASSOC_BUFSIZE] = {0};
+	__be32 associativity[VPHN_ASSOC_BUFSIZE] = {0};
 	cpumask_t updated_cpus;
 	struct device *dev;
 	int weight, new_nid, i = 0;
@@ -1609,7 +1613,7 @@ int start_topology_update(void)
 #endif
 		}
 	} else if (firmware_has_feature(FW_FEATURE_VPHN) &&
-		   get_lppaca()->shared_proc) {
+		   lppaca_shared_proc(get_lppaca())) {
 		if (!vphn_enabled) {
 			prrn_enabled = 0;
 			vphn_enabled = 1;
diff --git a/arch/powerpc/mm/slb.c b/arch/powerpc/mm/slb.c
index a538c80db2df..9d1d33cd2be5 100644
--- a/arch/powerpc/mm/slb.c
+++ b/arch/powerpc/mm/slb.c
@@ -66,8 +66,10 @@ static inline void slb_shadow_update(unsigned long ea, int ssize,
 	 * we only update the current CPU's SLB shadow buffer.
 	 */
 	get_slb_shadow()->save_area[entry].esid = 0;
-	get_slb_shadow()->save_area[entry].vsid = mk_vsid_data(ea, ssize, flags);
-	get_slb_shadow()->save_area[entry].esid = mk_esid_data(ea, ssize, entry);
+	get_slb_shadow()->save_area[entry].vsid =
+				cpu_to_be64(mk_vsid_data(ea, ssize, flags));
+	get_slb_shadow()->save_area[entry].esid =
+				cpu_to_be64(mk_esid_data(ea, ssize, entry));
 }
 
 static inline void slb_shadow_clear(unsigned long entry)
@@ -112,7 +114,8 @@ static void __slb_flush_and_rebolt(void)
 	} else {
 		/* Update stack entry; others don't change */
 		slb_shadow_update(get_paca()->kstack, mmu_kernel_ssize, lflags, 2);
-		ksp_vsid_data = get_slb_shadow()->save_area[2].vsid;
+		ksp_vsid_data =
+			be64_to_cpu(get_slb_shadow()->save_area[2].vsid);
 	}
 
 	/* We need to do this all in asm, so we're sure we don't touch
diff --git a/arch/powerpc/mm/subpage-prot.c b/arch/powerpc/mm/subpage-prot.c
index aa74acb0fdfc..a770df2dae70 100644
--- a/arch/powerpc/mm/subpage-prot.c
+++ b/arch/powerpc/mm/subpage-prot.c
@@ -105,7 +105,7 @@ static void subpage_prot_clear(unsigned long addr, unsigned long len)
 		limit = spt->maxaddr;
 	for (; addr < limit; addr = next) {
 		next = pmd_addr_end(addr, limit);
-		if (addr < 0x100000000) {
+		if (addr < 0x100000000UL) {
 			spm = spt->low_prot;
 		} else {
 			spm = spt->protptrs[addr >> SBP_L3_SHIFT];
@@ -219,7 +219,7 @@ long sys_subpage_prot(unsigned long addr, unsigned long len, u32 __user *map)
 	for (limit = addr + len; addr < limit; addr = next) {
 		next = pmd_addr_end(addr, limit);
 		err = -ENOMEM;
-		if (addr < 0x100000000) {
+		if (addr < 0x100000000UL) {
 			spm = spt->low_prot;
 		} else {
 			spm = spt->protptrs[addr >> SBP_L3_SHIFT];
diff --git a/arch/powerpc/oprofile/common.c b/arch/powerpc/oprofile/common.c
index 4f51025f5b00..c77348c5d463 100644
--- a/arch/powerpc/oprofile/common.c
+++ b/arch/powerpc/oprofile/common.c
@@ -119,7 +119,7 @@ static void op_powerpc_stop(void)
                 model->global_stop();
 }
 
-static int op_powerpc_create_files(struct super_block *sb, struct dentry *root)
+static int op_powerpc_create_files(struct dentry *root)
 {
 	int i;
 
@@ -128,9 +128,9 @@ static int op_powerpc_create_files(struct super_block *sb, struct dentry *root)
 	 * There is one mmcr0, mmcr1 and mmcra for setting the events for
 	 * all of the counters.
 	 */
-	oprofilefs_create_ulong(sb, root, "mmcr0", &sys.mmcr0);
-	oprofilefs_create_ulong(sb, root, "mmcr1", &sys.mmcr1);
-	oprofilefs_create_ulong(sb, root, "mmcra", &sys.mmcra);
+	oprofilefs_create_ulong(root, "mmcr0", &sys.mmcr0);
+	oprofilefs_create_ulong(root, "mmcr1", &sys.mmcr1);
+	oprofilefs_create_ulong(root, "mmcra", &sys.mmcra);
 #ifdef CONFIG_OPROFILE_CELL
 	/* create a file the user tool can check to see what level of profiling
 	 * support exits with this kernel. Initialize bit mask to indicate
@@ -142,7 +142,7 @@ static int op_powerpc_create_files(struct super_block *sb, struct dentry *root)
 	 * If the file does not exist, then the kernel only supports SPU
 	 * cycle profiling, PPU event and cycle profiling.
 	 */
-	oprofilefs_create_ulong(sb, root, "cell_support", &sys.cell_support);
+	oprofilefs_create_ulong(root, "cell_support", &sys.cell_support);
 	sys.cell_support = 0x1; /* Note, the user OProfile tool must check
 				 * that this bit is set before attempting to
 				 * user SPU event profiling.  Older kernels
@@ -160,11 +160,11 @@ static int op_powerpc_create_files(struct super_block *sb, struct dentry *root)
 		char buf[4];
 
 		snprintf(buf, sizeof buf, "%d", i);
-		dir = oprofilefs_mkdir(sb, root, buf);
+		dir = oprofilefs_mkdir(root, buf);
 
-		oprofilefs_create_ulong(sb, dir, "enabled", &ctr[i].enabled);
-		oprofilefs_create_ulong(sb, dir, "event", &ctr[i].event);
-		oprofilefs_create_ulong(sb, dir, "count", &ctr[i].count);
+		oprofilefs_create_ulong(dir, "enabled", &ctr[i].enabled);
+		oprofilefs_create_ulong(dir, "event", &ctr[i].event);
+		oprofilefs_create_ulong(dir, "count", &ctr[i].count);
 
 		/*
 		 * Classic PowerPC doesn't support per-counter
@@ -173,14 +173,14 @@ static int op_powerpc_create_files(struct super_block *sb, struct dentry *root)
 		 * Book-E style performance monitors, we do
 		 * support them.
 		 */
-		oprofilefs_create_ulong(sb, dir, "kernel", &ctr[i].kernel);
-		oprofilefs_create_ulong(sb, dir, "user", &ctr[i].user);
+		oprofilefs_create_ulong(dir, "kernel", &ctr[i].kernel);
+		oprofilefs_create_ulong(dir, "user", &ctr[i].user);
 
-		oprofilefs_create_ulong(sb, dir, "unit_mask", &ctr[i].unit_mask);
+		oprofilefs_create_ulong(dir, "unit_mask", &ctr[i].unit_mask);
 	}
 
-	oprofilefs_create_ulong(sb, root, "enable_kernel", &sys.enable_kernel);
-	oprofilefs_create_ulong(sb, root, "enable_user", &sys.enable_user);
+	oprofilefs_create_ulong(root, "enable_kernel", &sys.enable_kernel);
+	oprofilefs_create_ulong(root, "enable_user", &sys.enable_user);
 
 	/* Default to tracing both kernel and user */
 	sys.enable_kernel = 1;
diff --git a/arch/powerpc/oprofile/op_model_fsl_emb.c b/arch/powerpc/oprofile/op_model_fsl_emb.c
index ccc1daa33aed..2a82d3ed464d 100644
--- a/arch/powerpc/oprofile/op_model_fsl_emb.c
+++ b/arch/powerpc/oprofile/op_model_fsl_emb.c
@@ -46,6 +46,12 @@ static inline u32 get_pmlca(int ctr)
 		case 3:
 			pmlca = mfpmr(PMRN_PMLCA3);
 			break;
+		case 4:
+			pmlca = mfpmr(PMRN_PMLCA4);
+			break;
+		case 5:
+			pmlca = mfpmr(PMRN_PMLCA5);
+			break;
 		default:
 			panic("Bad ctr number\n");
 	}
@@ -68,6 +74,12 @@ static inline void set_pmlca(int ctr, u32 pmlca)
 		case 3:
 			mtpmr(PMRN_PMLCA3, pmlca);
 			break;
+		case 4:
+			mtpmr(PMRN_PMLCA4, pmlca);
+			break;
+		case 5:
+			mtpmr(PMRN_PMLCA5, pmlca);
+			break;
 		default:
 			panic("Bad ctr number\n");
 	}
@@ -84,6 +96,10 @@ static inline unsigned int ctr_read(unsigned int i)
 			return mfpmr(PMRN_PMC2);
 		case 3:
 			return mfpmr(PMRN_PMC3);
+		case 4:
+			return mfpmr(PMRN_PMC4);
+		case 5:
+			return mfpmr(PMRN_PMC5);
 		default:
 			return 0;
 	}
@@ -104,6 +120,12 @@ static inline void ctr_write(unsigned int i, unsigned int val)
 		case 3:
 			mtpmr(PMRN_PMC3, val);
 			break;
+		case 4:
+			mtpmr(PMRN_PMC4, val);
+			break;
+		case 5:
+			mtpmr(PMRN_PMC5, val);
+			break;
 		default:
 			break;
 	}
@@ -133,6 +155,14 @@ static void init_pmc_stop(int ctr)
 			mtpmr(PMRN_PMLCA3, pmlca);
 			mtpmr(PMRN_PMLCB3, pmlcb);
 			break;
+		case 4:
+			mtpmr(PMRN_PMLCA4, pmlca);
+			mtpmr(PMRN_PMLCB4, pmlcb);
+			break;
+		case 5:
+			mtpmr(PMRN_PMLCA5, pmlca);
+			mtpmr(PMRN_PMLCB5, pmlcb);
+			break;
 		default:
 			panic("Bad ctr number!\n");
 	}
diff --git a/arch/powerpc/perf/Makefile b/arch/powerpc/perf/Makefile
index 510fae10513d..60d71eea919c 100644
--- a/arch/powerpc/perf/Makefile
+++ b/arch/powerpc/perf/Makefile
@@ -9,7 +9,7 @@ obj64-$(CONFIG_PPC_PERF_CTRS)	+= power4-pmu.o ppc970-pmu.o power5-pmu.o \
 obj32-$(CONFIG_PPC_PERF_CTRS)	+= mpc7450-pmu.o
 
 obj-$(CONFIG_FSL_EMB_PERF_EVENT) += core-fsl-emb.o
-obj-$(CONFIG_FSL_EMB_PERF_EVENT_E500) += e500-pmu.o
+obj-$(CONFIG_FSL_EMB_PERF_EVENT_E500) += e500-pmu.o e6500-pmu.o
 
 obj-$(CONFIG_PPC64)		+= $(obj64-y)
 obj-$(CONFIG_PPC32)		+= $(obj32-y)
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index eeae308cf982..29b89e863d7c 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -24,7 +24,7 @@
 #define BHRB_MAX_ENTRIES	32
 #define BHRB_TARGET		0x0000000000000002
 #define BHRB_PREDICTION		0x0000000000000001
-#define BHRB_EA			0xFFFFFFFFFFFFFFFC
+#define BHRB_EA			0xFFFFFFFFFFFFFFFCUL
 
 struct cpu_hw_events {
 	int n_events;
diff --git a/arch/powerpc/perf/core-fsl-emb.c b/arch/powerpc/perf/core-fsl-emb.c
index 106c53354675..d35ae52c69dc 100644
--- a/arch/powerpc/perf/core-fsl-emb.c
+++ b/arch/powerpc/perf/core-fsl-emb.c
@@ -70,6 +70,12 @@ static unsigned long read_pmc(int idx)
 	case 3:
 		val = mfpmr(PMRN_PMC3);
 		break;
+	case 4:
+		val = mfpmr(PMRN_PMC4);
+		break;
+	case 5:
+		val = mfpmr(PMRN_PMC5);
+		break;
 	default:
 		printk(KERN_ERR "oops trying to read PMC%d\n", idx);
 		val = 0;
@@ -95,6 +101,12 @@ static void write_pmc(int idx, unsigned long val)
 	case 3:
 		mtpmr(PMRN_PMC3, val);
 		break;
+	case 4:
+		mtpmr(PMRN_PMC4, val);
+		break;
+	case 5:
+		mtpmr(PMRN_PMC5, val);
+		break;
 	default:
 		printk(KERN_ERR "oops trying to write PMC%d\n", idx);
 	}
@@ -120,6 +132,12 @@ static void write_pmlca(int idx, unsigned long val)
 	case 3:
 		mtpmr(PMRN_PMLCA3, val);
 		break;
+	case 4:
+		mtpmr(PMRN_PMLCA4, val);
+		break;
+	case 5:
+		mtpmr(PMRN_PMLCA5, val);
+		break;
 	default:
 		printk(KERN_ERR "oops trying to write PMLCA%d\n", idx);
 	}
@@ -145,6 +163,12 @@ static void write_pmlcb(int idx, unsigned long val)
 	case 3:
 		mtpmr(PMRN_PMLCB3, val);
 		break;
+	case 4:
+		mtpmr(PMRN_PMLCB4, val);
+		break;
+	case 5:
+		mtpmr(PMRN_PMLCB5, val);
+		break;
 	default:
 		printk(KERN_ERR "oops trying to write PMLCB%d\n", idx);
 	}
@@ -462,6 +486,12 @@ static int fsl_emb_pmu_event_init(struct perf_event *event)
 	int num_restricted;
 	int i;
 
+	if (ppmu->n_counter > MAX_HWEVENTS) {
+		WARN(1, "No. of perf counters (%d) is higher than max array size(%d)\n",
+			ppmu->n_counter, MAX_HWEVENTS);
+		ppmu->n_counter = MAX_HWEVENTS;
+	}
+
 	switch (event->attr.type) {
 	case PERF_TYPE_HARDWARE:
 		ev = event->attr.config;
diff --git a/arch/powerpc/perf/e6500-pmu.c b/arch/powerpc/perf/e6500-pmu.c
new file mode 100644
index 000000000000..3d877aa777b5
--- /dev/null
+++ b/arch/powerpc/perf/e6500-pmu.c
@@ -0,0 +1,121 @@
+/*
+ * Performance counter support for e6500 family processors.
+ *
+ * Author: Priyanka Jain, Priyanka.Jain@freescale.com
+ * Based on e500-pmu.c
+ * Copyright 2013 Freescale Semiconductor, Inc.
+ * Copyright 2008-2009 Paul Mackerras, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/string.h>
+#include <linux/perf_event.h>
+#include <asm/reg.h>
+#include <asm/cputable.h>
+
+/*
+ * Map of generic hardware event types to hardware events
+ * Zero if unsupported
+ */
+static int e6500_generic_events[] = {
+	[PERF_COUNT_HW_CPU_CYCLES] = 1,
+	[PERF_COUNT_HW_INSTRUCTIONS] = 2,
+	[PERF_COUNT_HW_CACHE_MISSES] = 221,
+	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 12,
+	[PERF_COUNT_HW_BRANCH_MISSES] = 15,
+};
+
+#define C(x)	PERF_COUNT_HW_CACHE_##x
+
+/*
+ * Table of generalized cache-related events.
+ * 0 means not supported, -1 means nonsensical, other values
+ * are event codes.
+ */
+static int e6500_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
+	[C(L1D)] = {
+				/*RESULT_ACCESS		RESULT_MISS */
+		[C(OP_READ)] = {	27,		222	},
+		[C(OP_WRITE)] = {	28,		223	},
+		[C(OP_PREFETCH)] = {	29,		0	},
+	},
+	[C(L1I)] = {
+				/*RESULT_ACCESS		RESULT_MISS */
+		[C(OP_READ)] = {	2,		254	},
+		[C(OP_WRITE)] = {	-1,		-1	},
+		[C(OP_PREFETCH)] = {	37,		0	},
+	},
+	/*
+	 * Assuming LL means L2, it's not a good match for this model.
+	 * It does not have separate read/write events (but it does have
+	 * separate instruction/data events).
+	 */
+	[C(LL)] = {
+				/*RESULT_ACCESS		RESULT_MISS */
+		[C(OP_READ)] = {	0,		0	},
+		[C(OP_WRITE)] = {	0,		0	},
+		[C(OP_PREFETCH)] = {	0,		0	},
+	},
+	/*
+	 * There are data/instruction MMU misses, but that's a miss on
+	 * the chip's internal level-one TLB which is probably not
+	 * what the user wants.  Instead, unified level-two TLB misses
+	 * are reported here.
+	 */
+	[C(DTLB)] = {
+				/*RESULT_ACCESS		RESULT_MISS */
+		[C(OP_READ)] = {	26,		66	},
+		[C(OP_WRITE)] = {	-1,		-1	},
+		[C(OP_PREFETCH)] = {	-1,		-1	},
+	},
+	[C(BPU)] = {
+				/*RESULT_ACCESS		RESULT_MISS */
+		[C(OP_READ)] = {	12,		15	},
+		[C(OP_WRITE)] = {	-1,		-1	},
+		[C(OP_PREFETCH)] = {	-1,		-1	},
+	},
+	[C(NODE)] = {
+				/* RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	-1,		-1	},
+		[C(OP_WRITE)] = {	-1,		-1	},
+		[C(OP_PREFETCH)] = {	-1,		-1	},
+	},
+};
+
+static int num_events = 512;
+
+/* Upper half of event id is PMLCb, for threshold events */
+static u64 e6500_xlate_event(u64 event_id)
+{
+	u32 event_low = (u32)event_id;
+	if (event_low >= num_events ||
+		(event_id & (FSL_EMB_EVENT_THRESHMUL | FSL_EMB_EVENT_THRESH)))
+		return 0;
+
+	return FSL_EMB_EVENT_VALID;
+}
+
+static struct fsl_emb_pmu e6500_pmu = {
+	.name			= "e6500 family",
+	.n_counter		= 6,
+	.n_restricted		= 0,
+	.xlate_event		= e6500_xlate_event,
+	.n_generic		= ARRAY_SIZE(e6500_generic_events),
+	.generic_events		= e6500_generic_events,
+	.cache_events		= &e6500_cache_events,
+};
+
+static int init_e6500_pmu(void)
+{
+	if (!cur_cpu_spec->oprofile_cpu_type ||
+		strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc/e6500"))
+		return -ENODEV;
+
+	return register_fsl_emb_pmu(&e6500_pmu);
+}
+
+early_initcall(init_e6500_pmu);
diff --git a/arch/powerpc/perf/power7-events-list.h b/arch/powerpc/perf/power7-events-list.h
new file mode 100644
index 000000000000..687790a2c0b8
--- /dev/null
+++ b/arch/powerpc/perf/power7-events-list.h
@@ -0,0 +1,548 @@
+/*
+ * Performance counter support for POWER7 processors.
+ *
+ * Copyright 2013 Runzhen Wang, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+EVENT(PM_IC_DEMAND_L2_BR_ALL,                 0x04898)
+EVENT(PM_GCT_UTIL_7_TO_10_SLOTS,              0x020a0)
+EVENT(PM_PMC2_SAVED,                          0x10022)
+EVENT(PM_CMPLU_STALL_DFU,                     0x2003c)
+EVENT(PM_VSU0_16FLOP,                         0x0a0a4)
+EVENT(PM_MRK_LSU_DERAT_MISS,                  0x3d05a)
+EVENT(PM_MRK_ST_CMPL,                         0x10034)
+EVENT(PM_NEST_PAIR3_ADD,                      0x40881)
+EVENT(PM_L2_ST_DISP,                          0x46180)
+EVENT(PM_L2_CASTOUT_MOD,                      0x16180)
+EVENT(PM_ISEG,                                0x020a4)
+EVENT(PM_MRK_INST_TIMEO,                      0x40034)
+EVENT(PM_L2_RCST_DISP_FAIL_ADDR,              0x36282)
+EVENT(PM_LSU1_DC_PREF_STREAM_CONFIRM,         0x0d0b6)
+EVENT(PM_IERAT_WR_64K,                        0x040be)
+EVENT(PM_MRK_DTLB_MISS_16M,                   0x4d05e)
+EVENT(PM_IERAT_MISS,                          0x100f6)
+EVENT(PM_MRK_PTEG_FROM_LMEM,                  0x4d052)
+EVENT(PM_FLOP,                                0x100f4)
+EVENT(PM_THRD_PRIO_4_5_CYC,                   0x040b4)
+EVENT(PM_BR_PRED_TA,                          0x040aa)
+EVENT(PM_CMPLU_STALL_FXU,                     0x20014)
+EVENT(PM_EXT_INT,                             0x200f8)
+EVENT(PM_VSU_FSQRT_FDIV,                      0x0a888)
+EVENT(PM_MRK_LD_MISS_EXPOSED_CYC,             0x1003e)
+EVENT(PM_LSU1_LDF,                            0x0c086)
+EVENT(PM_IC_WRITE_ALL,                        0x0488c)
+EVENT(PM_LSU0_SRQ_STFWD,                      0x0c0a0)
+EVENT(PM_PTEG_FROM_RL2L3_MOD,                 0x1c052)
+EVENT(PM_MRK_DATA_FROM_L31_SHR,               0x1d04e)
+EVENT(PM_DATA_FROM_L21_MOD,                   0x3c046)
+EVENT(PM_VSU1_SCAL_DOUBLE_ISSUED,             0x0b08a)
+EVENT(PM_VSU0_8FLOP,                          0x0a0a0)
+EVENT(PM_POWER_EVENT1,                        0x1006e)
+EVENT(PM_DISP_CLB_HELD_BAL,                   0x02092)
+EVENT(PM_VSU1_2FLOP,                          0x0a09a)
+EVENT(PM_LWSYNC_HELD,                         0x0209a)
+EVENT(PM_PTEG_FROM_DL2L3_SHR,                 0x3c054)
+EVENT(PM_INST_FROM_L21_MOD,                   0x34046)
+EVENT(PM_IERAT_XLATE_WR_16MPLUS,              0x040bc)
+EVENT(PM_IC_REQ_ALL,                          0x04888)
+EVENT(PM_DSLB_MISS,                           0x0d090)
+EVENT(PM_L3_MISS,                             0x1f082)
+EVENT(PM_LSU0_L1_PREF,                        0x0d0b8)
+EVENT(PM_VSU_SCALAR_SINGLE_ISSUED,            0x0b884)
+EVENT(PM_LSU1_DC_PREF_STREAM_CONFIRM_STRIDE,  0x0d0be)
+EVENT(PM_L2_INST,                             0x36080)
+EVENT(PM_VSU0_FRSP,                           0x0a0b4)
+EVENT(PM_FLUSH_DISP,                          0x02082)
+EVENT(PM_PTEG_FROM_L2MISS,                    0x4c058)
+EVENT(PM_VSU1_DQ_ISSUED,                      0x0b09a)
+EVENT(PM_CMPLU_STALL_LSU,                     0x20012)
+EVENT(PM_MRK_DATA_FROM_DMEM,                  0x1d04a)
+EVENT(PM_LSU_FLUSH_ULD,                       0x0c8b0)
+EVENT(PM_PTEG_FROM_LMEM,                      0x4c052)
+EVENT(PM_MRK_DERAT_MISS_16M,                  0x3d05c)
+EVENT(PM_THRD_ALL_RUN_CYC,                    0x2000c)
+EVENT(PM_MEM0_PREFETCH_DISP,                  0x20083)
+EVENT(PM_MRK_STALL_CMPLU_CYC_COUNT,           0x3003f)
+EVENT(PM_DATA_FROM_DL2L3_MOD,                 0x3c04c)
+EVENT(PM_VSU_FRSP,                            0x0a8b4)
+EVENT(PM_MRK_DATA_FROM_L21_MOD,               0x3d046)
+EVENT(PM_PMC1_OVERFLOW,                       0x20010)
+EVENT(PM_VSU0_SINGLE,                         0x0a0a8)
+EVENT(PM_MRK_PTEG_FROM_L3MISS,                0x2d058)
+EVENT(PM_MRK_PTEG_FROM_L31_SHR,               0x2d056)
+EVENT(PM_VSU0_VECTOR_SP_ISSUED,               0x0b090)
+EVENT(PM_VSU1_FEST,                           0x0a0ba)
+EVENT(PM_MRK_INST_DISP,                       0x20030)
+EVENT(PM_VSU0_COMPLEX_ISSUED,                 0x0b096)
+EVENT(PM_LSU1_FLUSH_UST,                      0x0c0b6)
+EVENT(PM_INST_CMPL,                           0x00002)
+EVENT(PM_FXU_IDLE,                            0x1000e)
+EVENT(PM_LSU0_FLUSH_ULD,                      0x0c0b0)
+EVENT(PM_MRK_DATA_FROM_DL2L3_MOD,             0x3d04c)
+EVENT(PM_LSU_LMQ_SRQ_EMPTY_ALL_CYC,           0x3001c)
+EVENT(PM_LSU1_REJECT_LMQ_FULL,                0x0c0a6)
+EVENT(PM_INST_PTEG_FROM_L21_MOD,              0x3e056)
+EVENT(PM_INST_FROM_RL2L3_MOD,                 0x14042)
+EVENT(PM_SHL_CREATED,                         0x05082)
+EVENT(PM_L2_ST_HIT,                           0x46182)
+EVENT(PM_DATA_FROM_DMEM,                      0x1c04a)
+EVENT(PM_L3_LD_MISS,                          0x2f082)
+EVENT(PM_FXU1_BUSY_FXU0_IDLE,                 0x4000e)
+EVENT(PM_DISP_CLB_HELD_RES,                   0x02094)
+EVENT(PM_L2_SN_SX_I_DONE,                     0x36382)
+EVENT(PM_GRP_CMPL,                            0x30004)
+EVENT(PM_STCX_CMPL,                           0x0c098)
+EVENT(PM_VSU0_2FLOP,                          0x0a098)
+EVENT(PM_L3_PREF_MISS,                        0x3f082)
+EVENT(PM_LSU_SRQ_SYNC_CYC,                    0x0d096)
+EVENT(PM_LSU_REJECT_ERAT_MISS,                0x20064)
+EVENT(PM_L1_ICACHE_MISS,                      0x200fc)
+EVENT(PM_LSU1_FLUSH_SRQ,                      0x0c0be)
+EVENT(PM_LD_REF_L1_LSU0,                      0x0c080)
+EVENT(PM_VSU0_FEST,                           0x0a0b8)
+EVENT(PM_VSU_VECTOR_SINGLE_ISSUED,            0x0b890)
+EVENT(PM_FREQ_UP,                             0x4000c)
+EVENT(PM_DATA_FROM_LMEM,                      0x3c04a)
+EVENT(PM_LSU1_LDX,                            0x0c08a)
+EVENT(PM_PMC3_OVERFLOW,                       0x40010)
+EVENT(PM_MRK_BR_MPRED,                        0x30036)
+EVENT(PM_SHL_MATCH,                           0x05086)
+EVENT(PM_MRK_BR_TAKEN,                        0x10036)
+EVENT(PM_CMPLU_STALL_BRU,                     0x4004e)
+EVENT(PM_ISLB_MISS,                           0x0d092)
+EVENT(PM_CYC,                                 0x0001e)
+EVENT(PM_DISP_HELD_THERMAL,                   0x30006)
+EVENT(PM_INST_PTEG_FROM_RL2L3_SHR,            0x2e054)
+EVENT(PM_LSU1_SRQ_STFWD,                      0x0c0a2)
+EVENT(PM_GCT_NOSLOT_BR_MPRED,                 0x4001a)
+EVENT(PM_1PLUS_PPC_CMPL,                      0x100f2)
+EVENT(PM_PTEG_FROM_DMEM,                      0x2c052)
+EVENT(PM_VSU_2FLOP,                           0x0a898)
+EVENT(PM_GCT_FULL_CYC,                        0x04086)
+EVENT(PM_MRK_DATA_FROM_L3_CYC,                0x40020)
+EVENT(PM_LSU_SRQ_S0_ALLOC,                    0x0d09d)
+EVENT(PM_MRK_DERAT_MISS_4K,                   0x1d05c)
+EVENT(PM_BR_MPRED_TA,                         0x040ae)
+EVENT(PM_INST_PTEG_FROM_L2MISS,               0x4e058)
+EVENT(PM_DPU_HELD_POWER,                      0x20006)
+EVENT(PM_RUN_INST_CMPL,                       0x400fa)
+EVENT(PM_MRK_VSU_FIN,                         0x30032)
+EVENT(PM_LSU_SRQ_S0_VALID,                    0x0d09c)
+EVENT(PM_GCT_EMPTY_CYC,                       0x20008)
+EVENT(PM_IOPS_DISP,                           0x30014)
+EVENT(PM_RUN_SPURR,                           0x10008)
+EVENT(PM_PTEG_FROM_L21_MOD,                   0x3c056)
+EVENT(PM_VSU0_1FLOP,                          0x0a080)
+EVENT(PM_SNOOP_TLBIE,                         0x0d0b2)
+EVENT(PM_DATA_FROM_L3MISS,                    0x2c048)
+EVENT(PM_VSU_SINGLE,                          0x0a8a8)
+EVENT(PM_DTLB_MISS_16G,                       0x1c05e)
+EVENT(PM_CMPLU_STALL_VECTOR,                  0x2001c)
+EVENT(PM_FLUSH,                               0x400f8)
+EVENT(PM_L2_LD_HIT,                           0x36182)
+EVENT(PM_NEST_PAIR2_AND,                      0x30883)
+EVENT(PM_VSU1_1FLOP,                          0x0a082)
+EVENT(PM_IC_PREF_REQ,                         0x0408a)
+EVENT(PM_L3_LD_HIT,                           0x2f080)
+EVENT(PM_GCT_NOSLOT_IC_MISS,                  0x2001a)
+EVENT(PM_DISP_HELD,                           0x10006)
+EVENT(PM_L2_LD,                               0x16080)
+EVENT(PM_LSU_FLUSH_SRQ,                       0x0c8bc)
+EVENT(PM_BC_PLUS_8_CONV,                      0x040b8)
+EVENT(PM_MRK_DATA_FROM_L31_MOD_CYC,           0x40026)
+EVENT(PM_CMPLU_STALL_VECTOR_LONG,             0x4004a)
+EVENT(PM_L2_RCST_BUSY_RC_FULL,                0x26282)
+EVENT(PM_TB_BIT_TRANS,                        0x300f8)
+EVENT(PM_THERMAL_MAX,                         0x40006)
+EVENT(PM_LSU1_FLUSH_ULD,                      0x0c0b2)
+EVENT(PM_LSU1_REJECT_LHS,                     0x0c0ae)
+EVENT(PM_LSU_LRQ_S0_ALLOC,                    0x0d09f)
+EVENT(PM_L3_CO_L31,                           0x4f080)
+EVENT(PM_POWER_EVENT4,                        0x4006e)
+EVENT(PM_DATA_FROM_L31_SHR,                   0x1c04e)
+EVENT(PM_BR_UNCOND,                           0x0409e)
+EVENT(PM_LSU1_DC_PREF_STREAM_ALLOC,           0x0d0aa)
+EVENT(PM_PMC4_REWIND,                         0x10020)
+EVENT(PM_L2_RCLD_DISP,                        0x16280)
+EVENT(PM_THRD_PRIO_2_3_CYC,                   0x040b2)
+EVENT(PM_MRK_PTEG_FROM_L2MISS,                0x4d058)
+EVENT(PM_IC_DEMAND_L2_BHT_REDIRECT,           0x04098)
+EVENT(PM_LSU_DERAT_MISS,                      0x200f6)
+EVENT(PM_IC_PREF_CANCEL_L2,                   0x04094)
+EVENT(PM_MRK_FIN_STALL_CYC_COUNT,             0x1003d)
+EVENT(PM_BR_PRED_CCACHE,                      0x040a0)
+EVENT(PM_GCT_UTIL_1_TO_2_SLOTS,               0x0209c)
+EVENT(PM_MRK_ST_CMPL_INT,                     0x30034)
+EVENT(PM_LSU_TWO_TABLEWALK_CYC,               0x0d0a6)
+EVENT(PM_MRK_DATA_FROM_L3MISS,                0x2d048)
+EVENT(PM_GCT_NOSLOT_CYC,                      0x100f8)
+EVENT(PM_LSU_SET_MPRED,                       0x0c0a8)
+EVENT(PM_FLUSH_DISP_TLBIE,                    0x0208a)
+EVENT(PM_VSU1_FCONV,                          0x0a0b2)
+EVENT(PM_DERAT_MISS_16G,                      0x4c05c)
+EVENT(PM_INST_FROM_LMEM,                      0x3404a)
+EVENT(PM_IC_DEMAND_L2_BR_REDIRECT,            0x0409a)
+EVENT(PM_CMPLU_STALL_SCALAR_LONG,             0x20018)
+EVENT(PM_INST_PTEG_FROM_L2,                   0x1e050)
+EVENT(PM_PTEG_FROM_L2,                        0x1c050)
+EVENT(PM_MRK_DATA_FROM_L21_SHR_CYC,           0x20024)
+EVENT(PM_MRK_DTLB_MISS_4K,                    0x2d05a)
+EVENT(PM_VSU0_FPSCR,                          0x0b09c)
+EVENT(PM_VSU1_VECT_DOUBLE_ISSUED,             0x0b082)
+EVENT(PM_MRK_PTEG_FROM_RL2L3_MOD,             0x1d052)
+EVENT(PM_MEM0_RQ_DISP,                        0x10083)
+EVENT(PM_L2_LD_MISS,                          0x26080)
+EVENT(PM_VMX_RESULT_SAT_1,                    0x0b0a0)
+EVENT(PM_L1_PREF,                             0x0d8b8)
+EVENT(PM_MRK_DATA_FROM_LMEM_CYC,              0x2002c)
+EVENT(PM_GRP_IC_MISS_NONSPEC,                 0x1000c)
+EVENT(PM_PB_NODE_PUMP,                        0x10081)
+EVENT(PM_SHL_MERGED,                          0x05084)
+EVENT(PM_NEST_PAIR1_ADD,                      0x20881)
+EVENT(PM_DATA_FROM_L3,                        0x1c048)
+EVENT(PM_LSU_FLUSH,                           0x0208e)
+EVENT(PM_LSU_SRQ_SYNC_COUNT,                  0x0d097)
+EVENT(PM_PMC2_OVERFLOW,                       0x30010)
+EVENT(PM_LSU_LDF,                             0x0c884)
+EVENT(PM_POWER_EVENT3,                        0x3006e)
+EVENT(PM_DISP_WT,                             0x30008)
+EVENT(PM_CMPLU_STALL_REJECT,                  0x40016)
+EVENT(PM_IC_BANK_CONFLICT,                    0x04082)
+EVENT(PM_BR_MPRED_CR_TA,                      0x048ae)
+EVENT(PM_L2_INST_MISS,                        0x36082)
+EVENT(PM_CMPLU_STALL_ERAT_MISS,               0x40018)
+EVENT(PM_NEST_PAIR2_ADD,                      0x30881)
+EVENT(PM_MRK_LSU_FLUSH,                       0x0d08c)
+EVENT(PM_L2_LDST,                             0x16880)
+EVENT(PM_INST_FROM_L31_SHR,                   0x1404e)
+EVENT(PM_VSU0_FIN,                            0x0a0bc)
+EVENT(PM_LARX_LSU,                            0x0c894)
+EVENT(PM_INST_FROM_RMEM,                      0x34042)
+EVENT(PM_DISP_CLB_HELD_TLBIE,                 0x02096)
+EVENT(PM_MRK_DATA_FROM_DMEM_CYC,              0x2002e)
+EVENT(PM_BR_PRED_CR,                          0x040a8)
+EVENT(PM_LSU_REJECT,                          0x10064)
+EVENT(PM_GCT_UTIL_3_TO_6_SLOTS,               0x0209e)
+EVENT(PM_CMPLU_STALL_END_GCT_NOSLOT,          0x10028)
+EVENT(PM_LSU0_REJECT_LMQ_FULL,                0x0c0a4)
+EVENT(PM_VSU_FEST,                            0x0a8b8)
+EVENT(PM_NEST_PAIR0_AND,                      0x10883)
+EVENT(PM_PTEG_FROM_L3,                        0x2c050)
+EVENT(PM_POWER_EVENT2,                        0x2006e)
+EVENT(PM_IC_PREF_CANCEL_PAGE,                 0x04090)
+EVENT(PM_VSU0_FSQRT_FDIV,                     0x0a088)
+EVENT(PM_MRK_GRP_CMPL,                        0x40030)
+EVENT(PM_VSU0_SCAL_DOUBLE_ISSUED,             0x0b088)
+EVENT(PM_GRP_DISP,                            0x3000a)
+EVENT(PM_LSU0_LDX,                            0x0c088)
+EVENT(PM_DATA_FROM_L2,                        0x1c040)
+EVENT(PM_MRK_DATA_FROM_RL2L3_MOD,             0x1d042)
+EVENT(PM_LD_REF_L1,                           0x0c880)
+EVENT(PM_VSU0_VECT_DOUBLE_ISSUED,             0x0b080)
+EVENT(PM_VSU1_2FLOP_DOUBLE,                   0x0a08e)
+EVENT(PM_THRD_PRIO_6_7_CYC,                   0x040b6)
+EVENT(PM_BC_PLUS_8_RSLV_TAKEN,                0x040ba)
+EVENT(PM_BR_MPRED_CR,                         0x040ac)
+EVENT(PM_L3_CO_MEM,                           0x4f082)
+EVENT(PM_LD_MISS_L1,                          0x400f0)
+EVENT(PM_DATA_FROM_RL2L3_MOD,                 0x1c042)
+EVENT(PM_LSU_SRQ_FULL_CYC,                    0x1001a)
+EVENT(PM_TABLEWALK_CYC,                       0x10026)
+EVENT(PM_MRK_PTEG_FROM_RMEM,                  0x3d052)
+EVENT(PM_LSU_SRQ_STFWD,                       0x0c8a0)
+EVENT(PM_INST_PTEG_FROM_RMEM,                 0x3e052)
+EVENT(PM_FXU0_FIN,                            0x10004)
+EVENT(PM_LSU1_L1_SW_PREF,                     0x0c09e)
+EVENT(PM_PTEG_FROM_L31_MOD,                   0x1c054)
+EVENT(PM_PMC5_OVERFLOW,                       0x10024)
+EVENT(PM_LD_REF_L1_LSU1,                      0x0c082)
+EVENT(PM_INST_PTEG_FROM_L21_SHR,              0x4e056)
+EVENT(PM_CMPLU_STALL_THRD,                    0x1001c)
+EVENT(PM_DATA_FROM_RMEM,                      0x3c042)
+EVENT(PM_VSU0_SCAL_SINGLE_ISSUED,             0x0b084)
+EVENT(PM_BR_MPRED_LSTACK,                     0x040a6)
+EVENT(PM_MRK_DATA_FROM_RL2L3_MOD_CYC,         0x40028)
+EVENT(PM_LSU0_FLUSH_UST,                      0x0c0b4)
+EVENT(PM_LSU_NCST,                            0x0c090)
+EVENT(PM_BR_TAKEN,                            0x20004)
+EVENT(PM_INST_PTEG_FROM_LMEM,                 0x4e052)
+EVENT(PM_GCT_NOSLOT_BR_MPRED_IC_MISS,         0x4001c)
+EVENT(PM_DTLB_MISS_4K,                        0x2c05a)
+EVENT(PM_PMC4_SAVED,                          0x30022)
+EVENT(PM_VSU1_PERMUTE_ISSUED,                 0x0b092)
+EVENT(PM_SLB_MISS,                            0x0d890)
+EVENT(PM_LSU1_FLUSH_LRQ,                      0x0c0ba)
+EVENT(PM_DTLB_MISS,                           0x300fc)
+EVENT(PM_VSU1_FRSP,                           0x0a0b6)
+EVENT(PM_VSU_VECTOR_DOUBLE_ISSUED,            0x0b880)
+EVENT(PM_L2_CASTOUT_SHR,                      0x16182)
+EVENT(PM_DATA_FROM_DL2L3_SHR,                 0x3c044)
+EVENT(PM_VSU1_STF,                            0x0b08e)
+EVENT(PM_ST_FIN,                              0x200f0)
+EVENT(PM_PTEG_FROM_L21_SHR,                   0x4c056)
+EVENT(PM_L2_LOC_GUESS_WRONG,                  0x26480)
+EVENT(PM_MRK_STCX_FAIL,                       0x0d08e)
+EVENT(PM_LSU0_REJECT_LHS,                     0x0c0ac)
+EVENT(PM_IC_PREF_CANCEL_HIT,                  0x04092)
+EVENT(PM_L3_PREF_BUSY,                        0x4f080)
+EVENT(PM_MRK_BRU_FIN,                         0x2003a)
+EVENT(PM_LSU1_NCLD,                           0x0c08e)
+EVENT(PM_INST_PTEG_FROM_L31_MOD,              0x1e054)
+EVENT(PM_LSU_NCLD,                            0x0c88c)
+EVENT(PM_LSU_LDX,                             0x0c888)
+EVENT(PM_L2_LOC_GUESS_CORRECT,                0x16480)
+EVENT(PM_THRESH_TIMEO,                        0x10038)
+EVENT(PM_L3_PREF_ST,                          0x0d0ae)
+EVENT(PM_DISP_CLB_HELD_SYNC,                  0x02098)
+EVENT(PM_VSU_SIMPLE_ISSUED,                   0x0b894)
+EVENT(PM_VSU1_SINGLE,                         0x0a0aa)
+EVENT(PM_DATA_TABLEWALK_CYC,                  0x3001a)
+EVENT(PM_L2_RC_ST_DONE,                       0x36380)
+EVENT(PM_MRK_PTEG_FROM_L21_MOD,               0x3d056)
+EVENT(PM_LARX_LSU1,                           0x0c096)
+EVENT(PM_MRK_DATA_FROM_RMEM,                  0x3d042)
+EVENT(PM_DISP_CLB_HELD,                       0x02090)
+EVENT(PM_DERAT_MISS_4K,                       0x1c05c)
+EVENT(PM_L2_RCLD_DISP_FAIL_ADDR,              0x16282)
+EVENT(PM_SEG_EXCEPTION,                       0x028a4)
+EVENT(PM_FLUSH_DISP_SB,                       0x0208c)
+EVENT(PM_L2_DC_INV,                           0x26182)
+EVENT(PM_PTEG_FROM_DL2L3_MOD,                 0x4c054)
+EVENT(PM_DSEG,                                0x020a6)
+EVENT(PM_BR_PRED_LSTACK,                      0x040a2)
+EVENT(PM_VSU0_STF,                            0x0b08c)
+EVENT(PM_LSU_FX_FIN,                          0x10066)
+EVENT(PM_DERAT_MISS_16M,                      0x3c05c)
+EVENT(PM_MRK_PTEG_FROM_DL2L3_MOD,             0x4d054)
+EVENT(PM_GCT_UTIL_11_PLUS_SLOTS,              0x020a2)
+EVENT(PM_INST_FROM_L3,                        0x14048)
+EVENT(PM_MRK_IFU_FIN,                         0x3003a)
+EVENT(PM_ITLB_MISS,                           0x400fc)
+EVENT(PM_VSU_STF,                             0x0b88c)
+EVENT(PM_LSU_FLUSH_UST,                       0x0c8b4)
+EVENT(PM_L2_LDST_MISS,                        0x26880)
+EVENT(PM_FXU1_FIN,                            0x40004)
+EVENT(PM_SHL_DEALLOCATED,                     0x05080)
+EVENT(PM_L2_SN_M_WR_DONE,                     0x46382)
+EVENT(PM_LSU_REJECT_SET_MPRED,                0x0c8a8)
+EVENT(PM_L3_PREF_LD,                          0x0d0ac)
+EVENT(PM_L2_SN_M_RD_DONE,                     0x46380)
+EVENT(PM_MRK_DERAT_MISS_16G,                  0x4d05c)
+EVENT(PM_VSU_FCONV,                           0x0a8b0)
+EVENT(PM_ANY_THRD_RUN_CYC,                    0x100fa)
+EVENT(PM_LSU_LMQ_FULL_CYC,                    0x0d0a4)
+EVENT(PM_MRK_LSU_REJECT_LHS,                  0x0d082)
+EVENT(PM_MRK_LD_MISS_L1_CYC,                  0x4003e)
+EVENT(PM_MRK_DATA_FROM_L2_CYC,                0x20020)
+EVENT(PM_INST_IMC_MATCH_DISP,                 0x30016)
+EVENT(PM_MRK_DATA_FROM_RMEM_CYC,              0x4002c)
+EVENT(PM_VSU0_SIMPLE_ISSUED,                  0x0b094)
+EVENT(PM_CMPLU_STALL_DIV,                     0x40014)
+EVENT(PM_MRK_PTEG_FROM_RL2L3_SHR,             0x2d054)
+EVENT(PM_VSU_FMA_DOUBLE,                      0x0a890)
+EVENT(PM_VSU_4FLOP,                           0x0a89c)
+EVENT(PM_VSU1_FIN,                            0x0a0be)
+EVENT(PM_NEST_PAIR1_AND,                      0x20883)
+EVENT(PM_INST_PTEG_FROM_RL2L3_MOD,            0x1e052)
+EVENT(PM_RUN_CYC,                             0x200f4)
+EVENT(PM_PTEG_FROM_RMEM,                      0x3c052)
+EVENT(PM_LSU_LRQ_S0_VALID,                    0x0d09e)
+EVENT(PM_LSU0_LDF,                            0x0c084)
+EVENT(PM_FLUSH_COMPLETION,                    0x30012)
+EVENT(PM_ST_MISS_L1,                          0x300f0)
+EVENT(PM_L2_NODE_PUMP,                        0x36480)
+EVENT(PM_INST_FROM_DL2L3_SHR,                 0x34044)
+EVENT(PM_MRK_STALL_CMPLU_CYC,                 0x3003e)
+EVENT(PM_VSU1_DENORM,                         0x0a0ae)
+EVENT(PM_MRK_DATA_FROM_L31_SHR_CYC,           0x20026)
+EVENT(PM_NEST_PAIR0_ADD,                      0x10881)
+EVENT(PM_INST_FROM_L3MISS,                    0x24048)
+EVENT(PM_EE_OFF_EXT_INT,                      0x02080)
+EVENT(PM_INST_PTEG_FROM_DMEM,                 0x2e052)
+EVENT(PM_INST_FROM_DL2L3_MOD,                 0x3404c)
+EVENT(PM_PMC6_OVERFLOW,                       0x30024)
+EVENT(PM_VSU_2FLOP_DOUBLE,                    0x0a88c)
+EVENT(PM_TLB_MISS,                            0x20066)
+EVENT(PM_FXU_BUSY,                            0x2000e)
+EVENT(PM_L2_RCLD_DISP_FAIL_OTHER,             0x26280)
+EVENT(PM_LSU_REJECT_LMQ_FULL,                 0x0c8a4)
+EVENT(PM_IC_RELOAD_SHR,                       0x04096)
+EVENT(PM_GRP_MRK,                             0x10031)
+EVENT(PM_MRK_ST_NEST,                         0x20034)
+EVENT(PM_VSU1_FSQRT_FDIV,                     0x0a08a)
+EVENT(PM_LSU0_FLUSH_LRQ,                      0x0c0b8)
+EVENT(PM_LARX_LSU0,                           0x0c094)
+EVENT(PM_IBUF_FULL_CYC,                       0x04084)
+EVENT(PM_MRK_DATA_FROM_DL2L3_SHR_CYC,         0x2002a)
+EVENT(PM_LSU_DC_PREF_STREAM_ALLOC,            0x0d8a8)
+EVENT(PM_GRP_MRK_CYC,                         0x10030)
+EVENT(PM_MRK_DATA_FROM_RL2L3_SHR_CYC,         0x20028)
+EVENT(PM_L2_GLOB_GUESS_CORRECT,               0x16482)
+EVENT(PM_LSU_REJECT_LHS,                      0x0c8ac)
+EVENT(PM_MRK_DATA_FROM_LMEM,                  0x3d04a)
+EVENT(PM_INST_PTEG_FROM_L3,                   0x2e050)
+EVENT(PM_FREQ_DOWN,                           0x3000c)
+EVENT(PM_PB_RETRY_NODE_PUMP,                  0x30081)
+EVENT(PM_INST_FROM_RL2L3_SHR,                 0x1404c)
+EVENT(PM_MRK_INST_ISSUED,                     0x10032)
+EVENT(PM_PTEG_FROM_L3MISS,                    0x2c058)
+EVENT(PM_RUN_PURR,                            0x400f4)
+EVENT(PM_MRK_GRP_IC_MISS,                     0x40038)
+EVENT(PM_MRK_DATA_FROM_L3,                    0x1d048)
+EVENT(PM_CMPLU_STALL_DCACHE_MISS,             0x20016)
+EVENT(PM_PTEG_FROM_RL2L3_SHR,                 0x2c054)
+EVENT(PM_LSU_FLUSH_LRQ,                       0x0c8b8)
+EVENT(PM_MRK_DERAT_MISS_64K,                  0x2d05c)
+EVENT(PM_INST_PTEG_FROM_DL2L3_MOD,            0x4e054)
+EVENT(PM_L2_ST_MISS,                          0x26082)
+EVENT(PM_MRK_PTEG_FROM_L21_SHR,               0x4d056)
+EVENT(PM_LWSYNC,                              0x0d094)
+EVENT(PM_LSU0_DC_PREF_STREAM_CONFIRM_STRIDE,  0x0d0bc)
+EVENT(PM_MRK_LSU_FLUSH_LRQ,                   0x0d088)
+EVENT(PM_INST_IMC_MATCH_CMPL,                 0x100f0)
+EVENT(PM_NEST_PAIR3_AND,                      0x40883)
+EVENT(PM_PB_RETRY_SYS_PUMP,                   0x40081)
+EVENT(PM_MRK_INST_FIN,                        0x30030)
+EVENT(PM_MRK_PTEG_FROM_DL2L3_SHR,             0x3d054)
+EVENT(PM_INST_FROM_L31_MOD,                   0x14044)
+EVENT(PM_MRK_DTLB_MISS_64K,                   0x3d05e)
+EVENT(PM_LSU_FIN,                             0x30066)
+EVENT(PM_MRK_LSU_REJECT,                      0x40064)
+EVENT(PM_L2_CO_FAIL_BUSY,                     0x16382)
+EVENT(PM_MEM0_WQ_DISP,                        0x40083)
+EVENT(PM_DATA_FROM_L31_MOD,                   0x1c044)
+EVENT(PM_THERMAL_WARN,                        0x10016)
+EVENT(PM_VSU0_4FLOP,                          0x0a09c)
+EVENT(PM_BR_MPRED_CCACHE,                     0x040a4)
+EVENT(PM_CMPLU_STALL_IFU,                     0x4004c)
+EVENT(PM_L1_DEMAND_WRITE,                     0x0408c)
+EVENT(PM_FLUSH_BR_MPRED,                      0x02084)
+EVENT(PM_MRK_DTLB_MISS_16G,                   0x1d05e)
+EVENT(PM_MRK_PTEG_FROM_DMEM,                  0x2d052)
+EVENT(PM_L2_RCST_DISP,                        0x36280)
+EVENT(PM_CMPLU_STALL,                         0x4000a)
+EVENT(PM_LSU_PARTIAL_CDF,                     0x0c0aa)
+EVENT(PM_DISP_CLB_HELD_SB,                    0x020a8)
+EVENT(PM_VSU0_FMA_DOUBLE,                     0x0a090)
+EVENT(PM_FXU0_BUSY_FXU1_IDLE,                 0x3000e)
+EVENT(PM_IC_DEMAND_CYC,                       0x10018)
+EVENT(PM_MRK_DATA_FROM_L21_SHR,               0x3d04e)
+EVENT(PM_MRK_LSU_FLUSH_UST,                   0x0d086)
+EVENT(PM_INST_PTEG_FROM_L3MISS,               0x2e058)
+EVENT(PM_VSU_DENORM,                          0x0a8ac)
+EVENT(PM_MRK_LSU_PARTIAL_CDF,                 0x0d080)
+EVENT(PM_INST_FROM_L21_SHR,                   0x3404e)
+EVENT(PM_IC_PREF_WRITE,                       0x0408e)
+EVENT(PM_BR_PRED,                             0x0409c)
+EVENT(PM_INST_FROM_DMEM,                      0x1404a)
+EVENT(PM_IC_PREF_CANCEL_ALL,                  0x04890)
+EVENT(PM_LSU_DC_PREF_STREAM_CONFIRM,          0x0d8b4)
+EVENT(PM_MRK_LSU_FLUSH_SRQ,                   0x0d08a)
+EVENT(PM_MRK_FIN_STALL_CYC,                   0x1003c)
+EVENT(PM_L2_RCST_DISP_FAIL_OTHER,             0x46280)
+EVENT(PM_VSU1_DD_ISSUED,                      0x0b098)
+EVENT(PM_PTEG_FROM_L31_SHR,                   0x2c056)
+EVENT(PM_DATA_FROM_L21_SHR,                   0x3c04e)
+EVENT(PM_LSU0_NCLD,                           0x0c08c)
+EVENT(PM_VSU1_4FLOP,                          0x0a09e)
+EVENT(PM_VSU1_8FLOP,                          0x0a0a2)
+EVENT(PM_VSU_8FLOP,                           0x0a8a0)
+EVENT(PM_LSU_LMQ_SRQ_EMPTY_CYC,               0x2003e)
+EVENT(PM_DTLB_MISS_64K,                       0x3c05e)
+EVENT(PM_THRD_CONC_RUN_INST,                  0x300f4)
+EVENT(PM_MRK_PTEG_FROM_L2,                    0x1d050)
+EVENT(PM_PB_SYS_PUMP,                         0x20081)
+EVENT(PM_VSU_FIN,                             0x0a8bc)
+EVENT(PM_MRK_DATA_FROM_L31_MOD,               0x1d044)
+EVENT(PM_THRD_PRIO_0_1_CYC,                   0x040b0)
+EVENT(PM_DERAT_MISS_64K,                      0x2c05c)
+EVENT(PM_PMC2_REWIND,                         0x30020)
+EVENT(PM_INST_FROM_L2,                        0x14040)
+EVENT(PM_GRP_BR_MPRED_NONSPEC,                0x1000a)
+EVENT(PM_INST_DISP,                           0x200f2)
+EVENT(PM_MEM0_RD_CANCEL_TOTAL,                0x30083)
+EVENT(PM_LSU0_DC_PREF_STREAM_CONFIRM,         0x0d0b4)
+EVENT(PM_L1_DCACHE_RELOAD_VALID,              0x300f6)
+EVENT(PM_VSU_SCALAR_DOUBLE_ISSUED,            0x0b888)
+EVENT(PM_L3_PREF_HIT,                         0x3f080)
+EVENT(PM_MRK_PTEG_FROM_L31_MOD,               0x1d054)
+EVENT(PM_CMPLU_STALL_STORE,                   0x2004a)
+EVENT(PM_MRK_FXU_FIN,                         0x20038)
+EVENT(PM_PMC4_OVERFLOW,                       0x10010)
+EVENT(PM_MRK_PTEG_FROM_L3,                    0x2d050)
+EVENT(PM_LSU0_LMQ_LHR_MERGE,                  0x0d098)
+EVENT(PM_BTAC_HIT,                            0x0508a)
+EVENT(PM_L3_RD_BUSY,                          0x4f082)
+EVENT(PM_LSU0_L1_SW_PREF,                     0x0c09c)
+EVENT(PM_INST_FROM_L2MISS,                    0x44048)
+EVENT(PM_LSU0_DC_PREF_STREAM_ALLOC,           0x0d0a8)
+EVENT(PM_L2_ST,                               0x16082)
+EVENT(PM_VSU0_DENORM,                         0x0a0ac)
+EVENT(PM_MRK_DATA_FROM_DL2L3_SHR,             0x3d044)
+EVENT(PM_BR_PRED_CR_TA,                       0x048aa)
+EVENT(PM_VSU0_FCONV,                          0x0a0b0)
+EVENT(PM_MRK_LSU_FLUSH_ULD,                   0x0d084)
+EVENT(PM_BTAC_MISS,                           0x05088)
+EVENT(PM_MRK_LD_MISS_EXPOSED_CYC_COUNT,       0x1003f)
+EVENT(PM_MRK_DATA_FROM_L2,                    0x1d040)
+EVENT(PM_LSU_DCACHE_RELOAD_VALID,             0x0d0a2)
+EVENT(PM_VSU_FMA,                             0x0a884)
+EVENT(PM_LSU0_FLUSH_SRQ,                      0x0c0bc)
+EVENT(PM_LSU1_L1_PREF,                        0x0d0ba)
+EVENT(PM_IOPS_CMPL,                           0x10014)
+EVENT(PM_L2_SYS_PUMP,                         0x36482)
+EVENT(PM_L2_RCLD_BUSY_RC_FULL,                0x46282)
+EVENT(PM_LSU_LMQ_S0_ALLOC,                    0x0d0a1)
+EVENT(PM_FLUSH_DISP_SYNC,                     0x02088)
+EVENT(PM_MRK_DATA_FROM_DL2L3_MOD_CYC,         0x4002a)
+EVENT(PM_L2_IC_INV,                           0x26180)
+EVENT(PM_MRK_DATA_FROM_L21_MOD_CYC,           0x40024)
+EVENT(PM_L3_PREF_LDST,                        0x0d8ac)
+EVENT(PM_LSU_SRQ_EMPTY_CYC,                   0x40008)
+EVENT(PM_LSU_LMQ_S0_VALID,                    0x0d0a0)
+EVENT(PM_FLUSH_PARTIAL,                       0x02086)
+EVENT(PM_VSU1_FMA_DOUBLE,                     0x0a092)
+EVENT(PM_1PLUS_PPC_DISP,                      0x400f2)
+EVENT(PM_DATA_FROM_L2MISS,                    0x200fe)
+EVENT(PM_SUSPENDED,                           0x00000)
+EVENT(PM_VSU0_FMA,                            0x0a084)
+EVENT(PM_CMPLU_STALL_SCALAR,                  0x40012)
+EVENT(PM_STCX_FAIL,                           0x0c09a)
+EVENT(PM_VSU0_FSQRT_FDIV_DOUBLE,              0x0a094)
+EVENT(PM_DC_PREF_DST,                         0x0d0b0)
+EVENT(PM_VSU1_SCAL_SINGLE_ISSUED,             0x0b086)
+EVENT(PM_L3_HIT,                              0x1f080)
+EVENT(PM_L2_GLOB_GUESS_WRONG,                 0x26482)
+EVENT(PM_MRK_DFU_FIN,                         0x20032)
+EVENT(PM_INST_FROM_L1,                        0x04080)
+EVENT(PM_BRU_FIN,                             0x10068)
+EVENT(PM_IC_DEMAND_REQ,                       0x04088)
+EVENT(PM_VSU1_FSQRT_FDIV_DOUBLE,              0x0a096)
+EVENT(PM_VSU1_FMA,                            0x0a086)
+EVENT(PM_MRK_LD_MISS_L1,                      0x20036)
+EVENT(PM_VSU0_2FLOP_DOUBLE,                   0x0a08c)
+EVENT(PM_LSU_DC_PREF_STRIDED_STREAM_CONFIRM,  0x0d8bc)
+EVENT(PM_INST_PTEG_FROM_L31_SHR,              0x2e056)
+EVENT(PM_MRK_LSU_REJECT_ERAT_MISS,            0x30064)
+EVENT(PM_MRK_DATA_FROM_L2MISS,                0x4d048)
+EVENT(PM_DATA_FROM_RL2L3_SHR,                 0x1c04c)
+EVENT(PM_INST_FROM_PREF,                      0x14046)
+EVENT(PM_VSU1_SQ,                             0x0b09e)
+EVENT(PM_L2_LD_DISP,                          0x36180)
+EVENT(PM_L2_DISP_ALL,                         0x46080)
+EVENT(PM_THRD_GRP_CMPL_BOTH_CYC,              0x10012)
+EVENT(PM_VSU_FSQRT_FDIV_DOUBLE,               0x0a894)
+EVENT(PM_BR_MPRED,                            0x400f6)
+EVENT(PM_INST_PTEG_FROM_DL2L3_SHR,            0x3e054)
+EVENT(PM_VSU_1FLOP,                           0x0a880)
+EVENT(PM_HV_CYC,                              0x2000a)
+EVENT(PM_MRK_LSU_FIN,                         0x40032)
+EVENT(PM_MRK_DATA_FROM_RL2L3_SHR,             0x1d04c)
+EVENT(PM_DTLB_MISS_16M,                       0x4c05e)
+EVENT(PM_LSU1_LMQ_LHR_MERGE,                  0x0d09a)
+EVENT(PM_IFU_FIN,                             0x40066)
diff --git a/arch/powerpc/perf/power7-pmu.c b/arch/powerpc/perf/power7-pmu.c
index d1821b8bbc4c..56c67bca2f75 100644
--- a/arch/powerpc/perf/power7-pmu.c
+++ b/arch/powerpc/perf/power7-pmu.c
@@ -53,37 +53,13 @@
 /*
  * Power7 event codes.
  */
-#define	PME_PM_CYC			0x1e
-#define	PME_PM_GCT_NOSLOT_CYC		0x100f8
-#define	PME_PM_CMPLU_STALL		0x4000a
-#define	PME_PM_INST_CMPL		0x2
-#define	PME_PM_LD_REF_L1		0xc880
-#define	PME_PM_LD_MISS_L1		0x400f0
-#define	PME_PM_BRU_FIN			0x10068
-#define	PME_PM_BR_MPRED			0x400f6
-
-#define PME_PM_CMPLU_STALL_FXU			0x20014
-#define PME_PM_CMPLU_STALL_DIV			0x40014
-#define PME_PM_CMPLU_STALL_SCALAR		0x40012
-#define PME_PM_CMPLU_STALL_SCALAR_LONG		0x20018
-#define PME_PM_CMPLU_STALL_VECTOR		0x2001c
-#define PME_PM_CMPLU_STALL_VECTOR_LONG		0x4004a
-#define PME_PM_CMPLU_STALL_LSU			0x20012
-#define PME_PM_CMPLU_STALL_REJECT		0x40016
-#define PME_PM_CMPLU_STALL_ERAT_MISS		0x40018
-#define PME_PM_CMPLU_STALL_DCACHE_MISS		0x20016
-#define PME_PM_CMPLU_STALL_STORE		0x2004a
-#define PME_PM_CMPLU_STALL_THRD			0x1001c
-#define PME_PM_CMPLU_STALL_IFU			0x4004c
-#define PME_PM_CMPLU_STALL_BRU			0x4004e
-#define PME_PM_GCT_NOSLOT_IC_MISS		0x2001a
-#define PME_PM_GCT_NOSLOT_BR_MPRED		0x4001a
-#define PME_PM_GCT_NOSLOT_BR_MPRED_IC_MISS	0x4001c
-#define PME_PM_GRP_CMPL				0x30004
-#define PME_PM_1PLUS_PPC_CMPL			0x100f2
-#define PME_PM_CMPLU_STALL_DFU			0x2003c
-#define PME_PM_RUN_CYC				0x200f4
-#define PME_PM_RUN_INST_CMPL			0x400fa
+#define EVENT(_name, _code) \
+	PME_##_name = _code,
+
+enum {
+#include "power7-events-list.h"
+};
+#undef EVENT
 
 /*
  * Layout of constraint bits:
@@ -398,96 +374,36 @@ static int power7_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
 };
 
 
-GENERIC_EVENT_ATTR(cpu-cycles,			CYC);
-GENERIC_EVENT_ATTR(stalled-cycles-frontend,	GCT_NOSLOT_CYC);
-GENERIC_EVENT_ATTR(stalled-cycles-backend,	CMPLU_STALL);
-GENERIC_EVENT_ATTR(instructions,		INST_CMPL);
-GENERIC_EVENT_ATTR(cache-references,		LD_REF_L1);
-GENERIC_EVENT_ATTR(cache-misses,		LD_MISS_L1);
-GENERIC_EVENT_ATTR(branch-instructions,		BRU_FIN);
-GENERIC_EVENT_ATTR(branch-misses,		BR_MPRED);
-
-POWER_EVENT_ATTR(CYC,				CYC);
-POWER_EVENT_ATTR(GCT_NOSLOT_CYC,		GCT_NOSLOT_CYC);
-POWER_EVENT_ATTR(CMPLU_STALL,			CMPLU_STALL);
-POWER_EVENT_ATTR(INST_CMPL,			INST_CMPL);
-POWER_EVENT_ATTR(LD_REF_L1,			LD_REF_L1);
-POWER_EVENT_ATTR(LD_MISS_L1,			LD_MISS_L1);
-POWER_EVENT_ATTR(BRU_FIN,			BRU_FIN)
-POWER_EVENT_ATTR(BR_MPRED,			BR_MPRED);
-
-POWER_EVENT_ATTR(CMPLU_STALL_FXU,		CMPLU_STALL_FXU);
-POWER_EVENT_ATTR(CMPLU_STALL_DIV,		CMPLU_STALL_DIV);
-POWER_EVENT_ATTR(CMPLU_STALL_SCALAR,		CMPLU_STALL_SCALAR);
-POWER_EVENT_ATTR(CMPLU_STALL_SCALAR_LONG,	CMPLU_STALL_SCALAR_LONG);
-POWER_EVENT_ATTR(CMPLU_STALL_VECTOR,		CMPLU_STALL_VECTOR);
-POWER_EVENT_ATTR(CMPLU_STALL_VECTOR_LONG,	CMPLU_STALL_VECTOR_LONG);
-POWER_EVENT_ATTR(CMPLU_STALL_LSU,		CMPLU_STALL_LSU);
-POWER_EVENT_ATTR(CMPLU_STALL_REJECT,		CMPLU_STALL_REJECT);
-
-POWER_EVENT_ATTR(CMPLU_STALL_ERAT_MISS,		CMPLU_STALL_ERAT_MISS);
-POWER_EVENT_ATTR(CMPLU_STALL_DCACHE_MISS,	CMPLU_STALL_DCACHE_MISS);
-POWER_EVENT_ATTR(CMPLU_STALL_STORE,		CMPLU_STALL_STORE);
-POWER_EVENT_ATTR(CMPLU_STALL_THRD,		CMPLU_STALL_THRD);
-POWER_EVENT_ATTR(CMPLU_STALL_IFU,		CMPLU_STALL_IFU);
-POWER_EVENT_ATTR(CMPLU_STALL_BRU,		CMPLU_STALL_BRU);
-POWER_EVENT_ATTR(GCT_NOSLOT_IC_MISS,		GCT_NOSLOT_IC_MISS);
-
-POWER_EVENT_ATTR(GCT_NOSLOT_BR_MPRED,		GCT_NOSLOT_BR_MPRED);
-POWER_EVENT_ATTR(GCT_NOSLOT_BR_MPRED_IC_MISS,	GCT_NOSLOT_BR_MPRED_IC_MISS);
-POWER_EVENT_ATTR(GRP_CMPL,			GRP_CMPL);
-POWER_EVENT_ATTR(1PLUS_PPC_CMPL,		1PLUS_PPC_CMPL);
-POWER_EVENT_ATTR(CMPLU_STALL_DFU,		CMPLU_STALL_DFU);
-POWER_EVENT_ATTR(RUN_CYC,			RUN_CYC);
-POWER_EVENT_ATTR(RUN_INST_CMPL,			RUN_INST_CMPL);
+GENERIC_EVENT_ATTR(cpu-cycles,			PM_CYC);
+GENERIC_EVENT_ATTR(stalled-cycles-frontend,	PM_GCT_NOSLOT_CYC);
+GENERIC_EVENT_ATTR(stalled-cycles-backend,	PM_CMPLU_STALL);
+GENERIC_EVENT_ATTR(instructions,		PM_INST_CMPL);
+GENERIC_EVENT_ATTR(cache-references,		PM_LD_REF_L1);
+GENERIC_EVENT_ATTR(cache-misses,		PM_LD_MISS_L1);
+GENERIC_EVENT_ATTR(branch-instructions,		PM_BRU_FIN);
+GENERIC_EVENT_ATTR(branch-misses,		PM_BR_MPRED);
+
+#define EVENT(_name, _code)     POWER_EVENT_ATTR(_name, _name);
+#include "power7-events-list.h"
+#undef EVENT
+
+#define EVENT(_name, _code)     POWER_EVENT_PTR(_name),
 
 static struct attribute *power7_events_attr[] = {
-	GENERIC_EVENT_PTR(CYC),
-	GENERIC_EVENT_PTR(GCT_NOSLOT_CYC),
-	GENERIC_EVENT_PTR(CMPLU_STALL),
-	GENERIC_EVENT_PTR(INST_CMPL),
-	GENERIC_EVENT_PTR(LD_REF_L1),
-	GENERIC_EVENT_PTR(LD_MISS_L1),
-	GENERIC_EVENT_PTR(BRU_FIN),
-	GENERIC_EVENT_PTR(BR_MPRED),
-
-	POWER_EVENT_PTR(CYC),
-	POWER_EVENT_PTR(GCT_NOSLOT_CYC),
-	POWER_EVENT_PTR(CMPLU_STALL),
-	POWER_EVENT_PTR(INST_CMPL),
-	POWER_EVENT_PTR(LD_REF_L1),
-	POWER_EVENT_PTR(LD_MISS_L1),
-	POWER_EVENT_PTR(BRU_FIN),
-	POWER_EVENT_PTR(BR_MPRED),
-
-	POWER_EVENT_PTR(CMPLU_STALL_FXU),
-	POWER_EVENT_PTR(CMPLU_STALL_DIV),
-	POWER_EVENT_PTR(CMPLU_STALL_SCALAR),
-	POWER_EVENT_PTR(CMPLU_STALL_SCALAR_LONG),
-	POWER_EVENT_PTR(CMPLU_STALL_VECTOR),
-	POWER_EVENT_PTR(CMPLU_STALL_VECTOR_LONG),
-	POWER_EVENT_PTR(CMPLU_STALL_LSU),
-	POWER_EVENT_PTR(CMPLU_STALL_REJECT),
-
-	POWER_EVENT_PTR(CMPLU_STALL_ERAT_MISS),
-	POWER_EVENT_PTR(CMPLU_STALL_DCACHE_MISS),
-	POWER_EVENT_PTR(CMPLU_STALL_STORE),
-	POWER_EVENT_PTR(CMPLU_STALL_THRD),
-	POWER_EVENT_PTR(CMPLU_STALL_IFU),
-	POWER_EVENT_PTR(CMPLU_STALL_BRU),
-	POWER_EVENT_PTR(GCT_NOSLOT_IC_MISS),
-	POWER_EVENT_PTR(GCT_NOSLOT_BR_MPRED),
-
-	POWER_EVENT_PTR(GCT_NOSLOT_BR_MPRED_IC_MISS),
-	POWER_EVENT_PTR(GRP_CMPL),
-	POWER_EVENT_PTR(1PLUS_PPC_CMPL),
-	POWER_EVENT_PTR(CMPLU_STALL_DFU),
-	POWER_EVENT_PTR(RUN_CYC),
-	POWER_EVENT_PTR(RUN_INST_CMPL),
+	GENERIC_EVENT_PTR(PM_CYC),
+	GENERIC_EVENT_PTR(PM_GCT_NOSLOT_CYC),
+	GENERIC_EVENT_PTR(PM_CMPLU_STALL),
+	GENERIC_EVENT_PTR(PM_INST_CMPL),
+	GENERIC_EVENT_PTR(PM_LD_REF_L1),
+	GENERIC_EVENT_PTR(PM_LD_MISS_L1),
+	GENERIC_EVENT_PTR(PM_BRU_FIN),
+	GENERIC_EVENT_PTR(PM_BR_MPRED),
+
+	#include "power7-events-list.h"
+	#undef EVENT
 	NULL
 };
 
-
 static struct attribute_group power7_pmu_events_group = {
 	.name = "events",
 	.attrs = power7_events_attr,
diff --git a/arch/powerpc/perf/power8-pmu.c b/arch/powerpc/perf/power8-pmu.c
index 2ee4a707f0df..a3f7abd2f13f 100644
--- a/arch/powerpc/perf/power8-pmu.c
+++ b/arch/powerpc/perf/power8-pmu.c
@@ -199,6 +199,7 @@
 #define MMCR1_UNIT_SHIFT(pmc)		(60 - (4 * ((pmc) - 1)))
 #define MMCR1_COMBINE_SHIFT(pmc)	(35 - ((pmc) - 1))
 #define MMCR1_PMCSEL_SHIFT(pmc)		(24 - (((pmc) - 1)) * 8)
+#define MMCR1_FAB_SHIFT			36
 #define MMCR1_DC_QUAL_SHIFT		47
 #define MMCR1_IC_QUAL_SHIFT		46
 
@@ -388,8 +389,8 @@ static int power8_compute_mmcr(u64 event[], int n_ev,
 		 * the threshold bits are used for the match value.
 		 */
 		if (event_is_fab_match(event[i])) {
-			mmcr1 |= (event[i] >> EVENT_THR_CTL_SHIFT) &
-				  EVENT_THR_CTL_MASK;
+			mmcr1 |= ((event[i] >> EVENT_THR_CTL_SHIFT) &
+				  EVENT_THR_CTL_MASK) << MMCR1_FAB_SHIFT;
 		} else {
 			val = (event[i] >> EVENT_THR_CTL_SHIFT) & EVENT_THR_CTL_MASK;
 			mmcra |= val << MMCRA_THR_CTL_SHIFT;
diff --git a/arch/powerpc/platforms/44x/warp.c b/arch/powerpc/platforms/44x/warp.c
index 4cfa49901c02..534574a97ec9 100644
--- a/arch/powerpc/platforms/44x/warp.c
+++ b/arch/powerpc/platforms/44x/warp.c
@@ -16,7 +16,6 @@
 #include <linux/interrupt.h>
 #include <linux/delay.h>
 #include <linux/of_gpio.h>
-#include <linux/of_i2c.h>
 #include <linux/slab.h>
 #include <linux/export.h>
 
diff --git a/arch/powerpc/platforms/52xx/mpc52xx_pic.c b/arch/powerpc/platforms/52xx/mpc52xx_pic.c
index b89ef65392dc..b69221ba07fd 100644
--- a/arch/powerpc/platforms/52xx/mpc52xx_pic.c
+++ b/arch/powerpc/platforms/52xx/mpc52xx_pic.c
@@ -373,8 +373,9 @@ static int mpc52xx_irqhost_map(struct irq_domain *h, unsigned int virq,
 	case MPC52xx_IRQ_L1_PERP: irqchip = &mpc52xx_periph_irqchip; break;
 	case MPC52xx_IRQ_L1_SDMA: irqchip = &mpc52xx_sdma_irqchip; break;
 	case MPC52xx_IRQ_L1_CRIT:
+	default:
 		pr_warn("%s: Critical IRQ #%d is unsupported! Nopping it.\n",
-			__func__, l2irq);
+			__func__, l1irq);
 		irq_set_chip(virq, &no_irq_chip);
 		return 0;
 	}
diff --git a/arch/powerpc/platforms/85xx/Kconfig b/arch/powerpc/platforms/85xx/Kconfig
index efdd37c775ad..de2eb9320993 100644
--- a/arch/powerpc/platforms/85xx/Kconfig
+++ b/arch/powerpc/platforms/85xx/Kconfig
@@ -32,6 +32,12 @@ config BSC9131_RDB
 	  StarCore SC3850 DSP
 	  Manufacturer : Freescale Semiconductor, Inc
 
+config C293_PCIE
+	  bool "Freescale C293PCIE"
+	  select DEFAULT_UIMAGE
+	  help
+	  This option enables support for the C293PCIE board
+
 config MPC8540_ADS
 	bool "Freescale MPC8540 ADS"
 	select DEFAULT_UIMAGE
@@ -112,10 +118,10 @@ config P1022_RDK
 	  reference board.
 
 config P1023_RDS
-	bool "Freescale P1023 RDS"
+	bool "Freescale P1023 RDS/RDB"
 	select DEFAULT_UIMAGE
 	help
-	  This option enables support for the P1023 RDS board
+	  This option enables support for the P1023 RDS and RDB boards
 
 config SOCRATES
 	bool "Socrates"
diff --git a/arch/powerpc/platforms/85xx/Makefile b/arch/powerpc/platforms/85xx/Makefile
index 2eab37ea4a9d..53c9f75a6907 100644
--- a/arch/powerpc/platforms/85xx/Makefile
+++ b/arch/powerpc/platforms/85xx/Makefile
@@ -6,6 +6,7 @@ obj-$(CONFIG_SMP) += smp.o
 obj-y += common.o
 
 obj-$(CONFIG_BSC9131_RDB) += bsc913x_rdb.o
+obj-$(CONFIG_C293_PCIE)   += c293pcie.o
 obj-$(CONFIG_MPC8540_ADS) += mpc85xx_ads.o
 obj-$(CONFIG_MPC8560_ADS) += mpc85xx_ads.o
 obj-$(CONFIG_MPC85xx_CDS) += mpc85xx_cds.o
diff --git a/arch/powerpc/platforms/85xx/c293pcie.c b/arch/powerpc/platforms/85xx/c293pcie.c
new file mode 100644
index 000000000000..6208e49142bf
--- /dev/null
+++ b/arch/powerpc/platforms/85xx/c293pcie.c
@@ -0,0 +1,75 @@
+/*
+ * C293PCIE Board Setup
+ *
+ * Copyright 2013 Freescale Semiconductor Inc.
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ */
+
+#include <linux/stddef.h>
+#include <linux/kernel.h>
+#include <linux/of_platform.h>
+
+#include <asm/machdep.h>
+#include <asm/udbg.h>
+#include <asm/mpic.h>
+
+#include <sysdev/fsl_soc.h>
+#include <sysdev/fsl_pci.h>
+
+#include "mpc85xx.h"
+
+void __init c293_pcie_pic_init(void)
+{
+	struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN |
+	  MPIC_SINGLE_DEST_CPU, 0, 256, " OpenPIC  ");
+
+	BUG_ON(mpic == NULL);
+
+	mpic_init(mpic);
+}
+
+
+/*
+ * Setup the architecture
+ */
+static void __init c293_pcie_setup_arch(void)
+{
+	if (ppc_md.progress)
+		ppc_md.progress("c293_pcie_setup_arch()", 0);
+
+	fsl_pci_assign_primary();
+
+	printk(KERN_INFO "C293 PCIE board from Freescale Semiconductor\n");
+}
+
+machine_arch_initcall(c293_pcie, mpc85xx_common_publish_devices);
+
+/*
+ * Called very early, device-tree isn't unflattened
+ */
+static int __init c293_pcie_probe(void)
+{
+	unsigned long root = of_get_flat_dt_root();
+
+	if (of_flat_dt_is_compatible(root, "fsl,C293PCIE"))
+		return 1;
+	return 0;
+}
+
+define_machine(c293_pcie) {
+	.name			= "C293 PCIE",
+	.probe			= c293_pcie_probe,
+	.setup_arch		= c293_pcie_setup_arch,
+	.init_IRQ		= c293_pcie_pic_init,
+#ifdef CONFIG_PCI
+	.pcibios_fixup_bus	= fsl_pcibios_fixup_bus,
+#endif
+	.get_irq		= mpic_get_irq,
+	.restart		= fsl_rstcr_restart,
+	.calibrate_decr		= generic_calibrate_decr,
+	.progress		= udbg_progress,
+};
diff --git a/arch/powerpc/platforms/85xx/corenet_ds.c b/arch/powerpc/platforms/85xx/corenet_ds.c
index c59c617eee93..aa3690bae415 100644
--- a/arch/powerpc/platforms/85xx/corenet_ds.c
+++ b/arch/powerpc/platforms/85xx/corenet_ds.c
@@ -53,12 +53,6 @@ void __init corenet_ds_setup_arch(void)
 {
 	mpc85xx_smp_init();
 
-#if defined(CONFIG_PCI) && defined(CONFIG_PPC64)
-	pci_devs_phb_init();
-#endif
-
-	fsl_pci_assign_primary();
-
 	swiotlb_detect_4g();
 
 	pr_info("%s board from Freescale Semiconductor\n", ppc_md.name);
diff --git a/arch/powerpc/platforms/85xx/mpc85xx_rdb.c b/arch/powerpc/platforms/85xx/mpc85xx_rdb.c
index ede8771d6f02..53b6fb0a3d56 100644
--- a/arch/powerpc/platforms/85xx/mpc85xx_rdb.c
+++ b/arch/powerpc/platforms/85xx/mpc85xx_rdb.c
@@ -160,6 +160,7 @@ machine_arch_initcall(p2020_rdb_pc, mpc85xx_common_publish_devices);
 machine_arch_initcall(p1020_mbg_pc, mpc85xx_common_publish_devices);
 machine_arch_initcall(p1020_rdb, mpc85xx_common_publish_devices);
 machine_arch_initcall(p1020_rdb_pc, mpc85xx_common_publish_devices);
+machine_arch_initcall(p1020_rdb_pd, mpc85xx_common_publish_devices);
 machine_arch_initcall(p1020_utm_pc, mpc85xx_common_publish_devices);
 machine_arch_initcall(p1021_rdb_pc, mpc85xx_common_publish_devices);
 machine_arch_initcall(p1025_rdb, mpc85xx_common_publish_devices);
@@ -193,6 +194,13 @@ static int __init p1020_rdb_pc_probe(void)
 	return of_flat_dt_is_compatible(root, "fsl,P1020RDB-PC");
 }
 
+static int __init p1020_rdb_pd_probe(void)
+{
+	unsigned long root = of_get_flat_dt_root();
+
+	return of_flat_dt_is_compatible(root, "fsl,P1020RDB-PD");
+}
+
 static int __init p1021_rdb_pc_probe(void)
 {
 	unsigned long root = of_get_flat_dt_root();
@@ -351,6 +359,20 @@ define_machine(p1020_rdb_pc) {
 	.progress		= udbg_progress,
 };
 
+define_machine(p1020_rdb_pd) {
+	.name			= "P1020RDB-PD",
+	.probe			= p1020_rdb_pd_probe,
+	.setup_arch		= mpc85xx_rdb_setup_arch,
+	.init_IRQ		= mpc85xx_rdb_pic_init,
+#ifdef CONFIG_PCI
+	.pcibios_fixup_bus	= fsl_pcibios_fixup_bus,
+#endif
+	.get_irq		= mpic_get_irq,
+	.restart		= fsl_rstcr_restart,
+	.calibrate_decr		= generic_calibrate_decr,
+	.progress		= udbg_progress,
+};
+
 define_machine(p1024_rdb) {
 	.name			= "P1024 RDB",
 	.probe			= p1024_rdb_probe,
diff --git a/arch/powerpc/platforms/85xx/p1023_rds.c b/arch/powerpc/platforms/85xx/p1023_rds.c
index 9cc60a738834..2ae9d490c3d9 100644
--- a/arch/powerpc/platforms/85xx/p1023_rds.c
+++ b/arch/powerpc/platforms/85xx/p1023_rds.c
@@ -1,5 +1,5 @@
 /*
- * Copyright 2010-2011 Freescale Semiconductor, Inc.
+ * Copyright 2010-2011, 2013 Freescale Semiconductor, Inc.
  *
  * Author: Roy Zang <tie-fei.zang@freescale.com>
  *
@@ -86,6 +86,7 @@ static void __init mpc85xx_rds_setup_arch(void)
 }
 
 machine_arch_initcall(p1023_rds, mpc85xx_common_publish_devices);
+machine_arch_initcall(p1023_rdb, mpc85xx_common_publish_devices);
 
 static void __init mpc85xx_rds_pic_init(void)
 {
@@ -106,6 +107,14 @@ static int __init p1023_rds_probe(void)
 
 }
 
+static int __init p1023_rdb_probe(void)
+{
+	unsigned long root = of_get_flat_dt_root();
+
+	return of_flat_dt_is_compatible(root, "fsl,P1023RDB");
+
+}
+
 define_machine(p1023_rds) {
 	.name			= "P1023 RDS",
 	.probe			= p1023_rds_probe,
@@ -120,3 +129,16 @@ define_machine(p1023_rds) {
 #endif
 };
 
+define_machine(p1023_rdb) {
+	.name			= "P1023 RDB",
+	.probe			= p1023_rdb_probe,
+	.setup_arch		= mpc85xx_rds_setup_arch,
+	.init_IRQ		= mpc85xx_rds_pic_init,
+	.get_irq		= mpic_get_irq,
+	.restart		= fsl_rstcr_restart,
+	.calibrate_decr		= generic_calibrate_decr,
+	.progress		= udbg_progress,
+#ifdef CONFIG_PCI
+	.pcibios_fixup_bus	= fsl_pcibios_fixup_bus,
+#endif
+};
diff --git a/arch/powerpc/platforms/85xx/smp.c b/arch/powerpc/platforms/85xx/smp.c
index 5ced4f5bb2b2..281b7f01df63 100644
--- a/arch/powerpc/platforms/85xx/smp.c
+++ b/arch/powerpc/platforms/85xx/smp.c
@@ -69,7 +69,32 @@ static void mpc85xx_give_timebase(void)
 	tb_req = 0;
 
 	mpc85xx_timebase_freeze(1);
+#ifdef CONFIG_PPC64
+	/*
+	 * e5500/e6500 have a workaround for erratum A-006958 in place
+	 * that will reread the timebase until TBL is non-zero.
+	 * That would be a bad thing when the timebase is frozen.
+	 *
+	 * Thus, we read it manually, and instead of checking that
+	 * TBL is non-zero, we ensure that TB does not change.  We don't
+	 * do that for the main mftb implementation, because it requires
+	 * a scratch register
+	 */
+	{
+		u64 prev;
+
+		asm volatile("mfspr %0, %1" : "=r" (timebase) :
+			     "i" (SPRN_TBRL));
+
+		do {
+			prev = timebase;
+			asm volatile("mfspr %0, %1" : "=r" (timebase) :
+				     "i" (SPRN_TBRL));
+		} while (prev != timebase);
+	}
+#else
 	timebase = get_tb();
+#endif
 	mb();
 	tb_valid = 1;
 
@@ -255,6 +280,7 @@ out:
 
 struct smp_ops_t smp_85xx_ops = {
 	.kick_cpu = smp_85xx_kick_cpu,
+	.cpu_bootable = smp_generic_cpu_bootable,
 #ifdef CONFIG_HOTPLUG_CPU
 	.cpu_disable	= generic_cpu_disable,
 	.cpu_die	= generic_cpu_die,
diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig
index d703775bda30..bf9c6d4cd26c 100644
--- a/arch/powerpc/platforms/Kconfig
+++ b/arch/powerpc/platforms/Kconfig
@@ -202,17 +202,12 @@ config PPC_P7_NAP
 	bool
 	default n
 
-config PPC_INDIRECT_IO
-	bool
-	select GENERIC_IOMAP
-
 config PPC_INDIRECT_PIO
 	bool
-	select PPC_INDIRECT_IO
+	select GENERIC_IOMAP
 
 config PPC_INDIRECT_MMIO
 	bool
-	select PPC_INDIRECT_IO
 
 config PPC_IO_WORKAROUNDS
 	bool
diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
index 47d9a03dd415..6704e2e20e6b 100644
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -96,18 +96,31 @@ config GENERIC_CPU
 
 config CELL_CPU
 	bool "Cell Broadband Engine"
+	depends on PPC_BOOK3S_64
 
 config POWER4_CPU
 	bool "POWER4"
+	depends on PPC_BOOK3S_64
 
 config POWER5_CPU
 	bool "POWER5"
+	depends on PPC_BOOK3S_64
 
 config POWER6_CPU
 	bool "POWER6"
+	depends on PPC_BOOK3S_64
 
 config POWER7_CPU
 	bool "POWER7"
+	depends on PPC_BOOK3S_64
+
+config E5500_CPU
+	bool "Freescale e5500"
+	depends on E500
+
+config E6500_CPU
+	bool "Freescale e6500"
+	depends on E500
 
 endchoice
 
diff --git a/arch/powerpc/platforms/cell/iommu.c b/arch/powerpc/platforms/cell/iommu.c
index 946306b1bb4e..b53560660b72 100644
--- a/arch/powerpc/platforms/cell/iommu.c
+++ b/arch/powerpc/platforms/cell/iommu.c
@@ -697,7 +697,7 @@ static int __init cell_iommu_get_window(struct device_node *np,
 					 unsigned long *base,
 					 unsigned long *size)
 {
-	const void *dma_window;
+	const __be32 *dma_window;
 	unsigned long index;
 
 	/* Use ibm,dma-window if available, else, hard code ! */
diff --git a/arch/powerpc/platforms/cell/smp.c b/arch/powerpc/platforms/cell/smp.c
index f75f6fcac729..90745eaa45fe 100644
--- a/arch/powerpc/platforms/cell/smp.c
+++ b/arch/powerpc/platforms/cell/smp.c
@@ -136,25 +136,12 @@ static int smp_cell_kick_cpu(int nr)
 	return 0;
 }
 
-static int smp_cell_cpu_bootable(unsigned int nr)
-{
-	/* Special case - we inhibit secondary thread startup
-	 * during boot if the user requests it.  Odd-numbered
-	 * cpus are assumed to be secondary threads.
-	 */
-	if (system_state == SYSTEM_BOOTING &&
-	    cpu_has_feature(CPU_FTR_SMT) &&
-	    !smt_enabled_at_boot && cpu_thread_in_core(nr) != 0)
-		return 0;
-
-	return 1;
-}
 static struct smp_ops_t bpa_iic_smp_ops = {
 	.message_pass	= iic_message_pass,
 	.probe		= smp_iic_probe,
 	.kick_cpu	= smp_cell_kick_cpu,
 	.setup_cpu	= smp_cell_setup_cpu,
-	.cpu_bootable	= smp_cell_cpu_bootable,
+	.cpu_bootable	= smp_generic_cpu_bootable,
 };
 
 /* This is called very early */
diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c
index f3900427ffab..87ba7cf99cd7 100644
--- a/arch/powerpc/platforms/cell/spufs/inode.c
+++ b/arch/powerpc/platforms/cell/spufs/inode.c
@@ -620,12 +620,16 @@ spufs_parse_options(struct super_block *sb, char *options, struct inode *root)
 		case Opt_uid:
 			if (match_int(&args[0], &option))
 				return 0;
-			root->i_uid = option;
+			root->i_uid = make_kuid(current_user_ns(), option);
+			if (!uid_valid(root->i_uid))
+				return 0;
 			break;
 		case Opt_gid:
 			if (match_int(&args[0], &option))
 				return 0;
-			root->i_gid = option;
+			root->i_gid = make_kgid(current_user_ns(), option);
+			if (!gid_valid(root->i_gid))
+				return 0;
 			break;
 		case Opt_mode:
 			if (match_octal(&args[0], &option))
diff --git a/arch/powerpc/platforms/powernv/Kconfig b/arch/powerpc/platforms/powernv/Kconfig
index c24684c818ab..6fae5eb99ea6 100644
--- a/arch/powerpc/platforms/powernv/Kconfig
+++ b/arch/powerpc/platforms/powernv/Kconfig
@@ -7,6 +7,8 @@ config PPC_POWERNV
 	select PPC_P7_NAP
 	select PPC_PCI_CHOICE if EMBEDDED
 	select EPAPR_BOOT
+	select PPC_INDIRECT_PIO
+	select PPC_UDBG_16550
 	default y
 
 config POWERNV_MSI
diff --git a/arch/powerpc/platforms/powernv/Makefile b/arch/powerpc/platforms/powernv/Makefile
index 7fe595152478..300c437d713c 100644
--- a/arch/powerpc/platforms/powernv/Makefile
+++ b/arch/powerpc/platforms/powernv/Makefile
@@ -1,5 +1,5 @@
 obj-y			+= setup.o opal-takeover.o opal-wrappers.o opal.o
-obj-y			+= opal-rtc.o opal-nvram.o
+obj-y			+= opal-rtc.o opal-nvram.o opal-lpc.o
 
 obj-$(CONFIG_SMP)	+= smp.o
 obj-$(CONFIG_PCI)	+= pci.o pci-p5ioc2.o pci-ioda.o
diff --git a/arch/powerpc/platforms/powernv/eeh-ioda.c b/arch/powerpc/platforms/powernv/eeh-ioda.c
index 0cd1c4a71755..cf42e74514fa 100644
--- a/arch/powerpc/platforms/powernv/eeh-ioda.c
+++ b/arch/powerpc/platforms/powernv/eeh-ioda.c
@@ -36,13 +36,6 @@
 #include "powernv.h"
 #include "pci.h"
 
-/* Debugging option */
-#ifdef IODA_EEH_DBG_ON
-#define IODA_EEH_DBG(args...)	pr_info(args)
-#else
-#define IODA_EEH_DBG(args...)
-#endif
-
 static char *hub_diag = NULL;
 static int ioda_eeh_nb_init = 0;
 
@@ -823,17 +816,17 @@ static int ioda_eeh_next_error(struct eeh_pe **pe)
 
 		/* If OPAL API returns error, we needn't proceed */
 		if (rc != OPAL_SUCCESS) {
-			IODA_EEH_DBG("%s: Invalid return value on "
-				     "PHB#%x (0x%lx) from opal_pci_next_error",
-				     __func__, hose->global_number, rc);
+			pr_devel("%s: Invalid return value on "
+				 "PHB#%x (0x%lx) from opal_pci_next_error",
+				 __func__, hose->global_number, rc);
 			continue;
 		}
 
 		/* If the PHB doesn't have error, stop processing */
 		if (err_type == OPAL_EEH_NO_ERROR ||
 		    severity == OPAL_EEH_SEV_NO_ERROR) {
-			IODA_EEH_DBG("%s: No error found on PHB#%x\n",
-				     __func__, hose->global_number);
+			pr_devel("%s: No error found on PHB#%x\n",
+				 __func__, hose->global_number);
 			continue;
 		}
 
@@ -842,8 +835,9 @@ static int ioda_eeh_next_error(struct eeh_pe **pe)
 		 * highest priority reported upon multiple errors on the
 		 * specific PHB.
 		 */
-		IODA_EEH_DBG("%s: Error (%d, %d, %d) on PHB#%x\n",
-			err_type, severity, pe_no, hose->global_number);
+		pr_devel("%s: Error (%d, %d, %llu) on PHB#%x\n",
+			 __func__, err_type, severity,
+			 frozen_pe_no, hose->global_number);
 		switch (err_type) {
 		case OPAL_EEH_IOC_ERROR:
 			if (severity == OPAL_EEH_SEV_IOC_DEAD) {
diff --git a/arch/powerpc/platforms/powernv/opal-lpc.c b/arch/powerpc/platforms/powernv/opal-lpc.c
new file mode 100644
index 000000000000..a7614bb14e17
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/opal-lpc.c
@@ -0,0 +1,203 @@
+/*
+ * PowerNV LPC bus handling.
+ *
+ * Copyright 2013 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/of.h>
+#include <linux/bug.h>
+
+#include <asm/machdep.h>
+#include <asm/firmware.h>
+#include <asm/xics.h>
+#include <asm/opal.h>
+
+static int opal_lpc_chip_id = -1;
+
+static u8 opal_lpc_inb(unsigned long port)
+{
+	int64_t rc;
+	uint32_t data;
+
+	if (opal_lpc_chip_id < 0 || port > 0xffff)
+		return 0xff;
+	rc = opal_lpc_read(opal_lpc_chip_id, OPAL_LPC_IO, port, &data, 1);
+	return rc ? 0xff : data;
+}
+
+static __le16 __opal_lpc_inw(unsigned long port)
+{
+	int64_t rc;
+	uint32_t data;
+
+	if (opal_lpc_chip_id < 0 || port > 0xfffe)
+		return 0xffff;
+	if (port & 1)
+		return (__le16)opal_lpc_inb(port) << 8 | opal_lpc_inb(port + 1);
+	rc = opal_lpc_read(opal_lpc_chip_id, OPAL_LPC_IO, port, &data, 2);
+	return rc ? 0xffff : data;
+}
+static u16 opal_lpc_inw(unsigned long port)
+{
+	return le16_to_cpu(__opal_lpc_inw(port));
+}
+
+static __le32 __opal_lpc_inl(unsigned long port)
+{
+	int64_t rc;
+	uint32_t data;
+
+	if (opal_lpc_chip_id < 0 || port > 0xfffc)
+		return 0xffffffff;
+	if (port & 3)
+		return (__le32)opal_lpc_inb(port    ) << 24 |
+		       (__le32)opal_lpc_inb(port + 1) << 16 |
+		       (__le32)opal_lpc_inb(port + 2) <<  8 |
+			       opal_lpc_inb(port + 3);
+	rc = opal_lpc_read(opal_lpc_chip_id, OPAL_LPC_IO, port, &data, 4);
+	return rc ? 0xffffffff : data;
+}
+
+static u32 opal_lpc_inl(unsigned long port)
+{
+	return le32_to_cpu(__opal_lpc_inl(port));
+}
+
+static void opal_lpc_outb(u8 val, unsigned long port)
+{
+	if (opal_lpc_chip_id < 0 || port > 0xffff)
+		return;
+	opal_lpc_write(opal_lpc_chip_id, OPAL_LPC_IO, port, val, 1);
+}
+
+static void __opal_lpc_outw(__le16 val, unsigned long port)
+{
+	if (opal_lpc_chip_id < 0 || port > 0xfffe)
+		return;
+	if (port & 1) {
+		opal_lpc_outb(val >> 8, port);
+		opal_lpc_outb(val     , port + 1);
+		return;
+	}
+	opal_lpc_write(opal_lpc_chip_id, OPAL_LPC_IO, port, val, 2);
+}
+
+static void opal_lpc_outw(u16 val, unsigned long port)
+{
+	__opal_lpc_outw(cpu_to_le16(val), port);
+}
+
+static void __opal_lpc_outl(__le32 val, unsigned long port)
+{
+	if (opal_lpc_chip_id < 0 || port > 0xfffc)
+		return;
+	if (port & 3) {
+		opal_lpc_outb(val >> 24, port);
+		opal_lpc_outb(val >> 16, port + 1);
+		opal_lpc_outb(val >>  8, port + 2);
+		opal_lpc_outb(val      , port + 3);
+		return;
+	}
+	opal_lpc_write(opal_lpc_chip_id, OPAL_LPC_IO, port, val, 4);
+}
+
+static void opal_lpc_outl(u32 val, unsigned long port)
+{
+	__opal_lpc_outl(cpu_to_le32(val), port);
+}
+
+static void opal_lpc_insb(unsigned long p, void *b, unsigned long c)
+{
+	u8 *ptr = b;
+
+	while(c--)
+		*(ptr++) = opal_lpc_inb(p);
+}
+
+static void opal_lpc_insw(unsigned long p, void *b, unsigned long c)
+{
+	__le16 *ptr = b;
+
+	while(c--)
+		*(ptr++) = __opal_lpc_inw(p);
+}
+
+static void opal_lpc_insl(unsigned long p, void *b, unsigned long c)
+{
+	__le32 *ptr = b;
+
+	while(c--)
+		*(ptr++) = __opal_lpc_inl(p);
+}
+
+static void opal_lpc_outsb(unsigned long p, const void *b, unsigned long c)
+{
+	const u8 *ptr = b;
+
+	while(c--)
+		opal_lpc_outb(*(ptr++), p);
+}
+
+static void opal_lpc_outsw(unsigned long p, const void *b, unsigned long c)
+{
+	const __le16 *ptr = b;
+
+	while(c--)
+		__opal_lpc_outw(*(ptr++), p);
+}
+
+static void opal_lpc_outsl(unsigned long p, const void *b, unsigned long c)
+{
+	const __le32 *ptr = b;
+
+	while(c--)
+		__opal_lpc_outl(*(ptr++), p);
+}
+
+static const struct ppc_pci_io opal_lpc_io = {
+	.inb	= opal_lpc_inb,
+	.inw	= opal_lpc_inw,
+	.inl	= opal_lpc_inl,
+	.outb	= opal_lpc_outb,
+	.outw	= opal_lpc_outw,
+	.outl	= opal_lpc_outl,
+	.insb	= opal_lpc_insb,
+	.insw	= opal_lpc_insw,
+	.insl	= opal_lpc_insl,
+	.outsb	= opal_lpc_outsb,
+	.outsw	= opal_lpc_outsw,
+	.outsl	= opal_lpc_outsl,
+};
+
+void opal_lpc_init(void)
+{
+	struct device_node *np;
+
+	/*
+	 * Look for a Power8 LPC bus tagged as "primary",
+	 * we currently support only one though the OPAL APIs
+	 * support any number.
+	 */
+	for_each_compatible_node(np, NULL, "ibm,power8-lpc") {
+		if (!of_device_is_available(np))
+			continue;
+		if (!of_get_property(np, "primary", NULL))
+			continue;
+		opal_lpc_chip_id = of_get_ibm_chip_id(np);
+		break;
+	}
+	if (opal_lpc_chip_id < 0)
+		return;
+
+	/* Setup special IO ops */
+	ppc_pci_io = opal_lpc_io;
+	isa_io_special = true;
+
+	pr_info("OPAL: Power8 LPC bus found, chip ID %d\n", opal_lpc_chip_id);
+}
diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S
index e88863ffb135..8f3844535fbb 100644
--- a/arch/powerpc/platforms/powernv/opal-wrappers.S
+++ b/arch/powerpc/platforms/powernv/opal-wrappers.S
@@ -111,3 +111,8 @@ OPAL_CALL(opal_pci_next_error,			OPAL_PCI_NEXT_ERROR);
 OPAL_CALL(opal_pci_poll,			OPAL_PCI_POLL);
 OPAL_CALL(opal_pci_msi_eoi,			OPAL_PCI_MSI_EOI);
 OPAL_CALL(opal_pci_get_phb_diag_data2,		OPAL_PCI_GET_PHB_DIAG_DATA2);
+OPAL_CALL(opal_xscom_read,			OPAL_XSCOM_READ);
+OPAL_CALL(opal_xscom_write,			OPAL_XSCOM_WRITE);
+OPAL_CALL(opal_lpc_read,			OPAL_LPC_READ);
+OPAL_CALL(opal_lpc_write,			OPAL_LPC_WRITE);
+OPAL_CALL(opal_return_cpu,			OPAL_RETURN_CPU);
diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
index 106301fd2fa5..2911abe550f1 100644
--- a/arch/powerpc/platforms/powernv/opal.c
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -380,18 +380,20 @@ static int __init opal_init(void)
 		pr_warn("opal: Node not found\n");
 		return -ENODEV;
 	}
+
+	/* Register OPAL consoles if any ports */
 	if (firmware_has_feature(FW_FEATURE_OPALv2))
 		consoles = of_find_node_by_path("/ibm,opal/consoles");
 	else
 		consoles = of_node_get(opal_node);
-
-	/* Register serial ports */
-	for_each_child_of_node(consoles, np) {
-		if (strcmp(np->name, "serial"))
-			continue;
-		of_platform_device_create(np, NULL, NULL);
+	if (consoles) {
+		for_each_child_of_node(consoles, np) {
+			if (strcmp(np->name, "serial"))
+				continue;
+			of_platform_device_create(np, NULL, NULL);
+		}
+		of_node_put(consoles);
 	}
-	of_node_put(consoles);
 
 	/* Find all OPAL interrupts and request them */
 	irqs = of_get_property(opal_node, "opal-interrupts", &irqlen);
@@ -422,7 +424,7 @@ void opal_shutdown(void)
 
 	for (i = 0; i < opal_irq_count; i++) {
 		if (opal_irqs[i])
-			free_irq(opal_irqs[i], 0);
+			free_irq(opal_irqs[i], NULL);
 		opal_irqs[i] = 0;
 	}
 }
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index d8140b125e62..74a5a5773b1f 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -1104,16 +1104,16 @@ void __init pnv_pci_init_ioda_phb(struct device_node *np,
 				  u64 hub_id, int ioda_type)
 {
 	struct pci_controller *hose;
-	static int primary = 1;
 	struct pnv_phb *phb;
 	unsigned long size, m32map_off, iomap_off, pemap_off;
 	const u64 *prop64;
 	const u32 *prop32;
+	int len;
 	u64 phb_id;
 	void *aux;
 	long rc;
 
-	pr_info(" Initializing IODA%d OPAL PHB %s\n", ioda_type, np->full_name);
+	pr_info("Initializing IODA%d OPAL PHB %s\n", ioda_type, np->full_name);
 
 	prop64 = of_get_property(np, "ibm,opal-phbid", NULL);
 	if (!prop64) {
@@ -1124,20 +1124,31 @@ void __init pnv_pci_init_ioda_phb(struct device_node *np,
 	pr_debug("  PHB-ID  : 0x%016llx\n", phb_id);
 
 	phb = alloc_bootmem(sizeof(struct pnv_phb));
-	if (phb) {
-		memset(phb, 0, sizeof(struct pnv_phb));
-		phb->hose = hose = pcibios_alloc_controller(np);
+	if (!phb) {
+		pr_err("  Out of memory !\n");
+		return;
 	}
-	if (!phb || !phb->hose) {
-		pr_err("PCI: Failed to allocate PCI controller for %s\n",
+
+	/* Allocate PCI controller */
+	memset(phb, 0, sizeof(struct pnv_phb));
+	phb->hose = hose = pcibios_alloc_controller(np);
+	if (!phb->hose) {
+		pr_err("  Can't allocate PCI controller for %s\n",
 		       np->full_name);
+		free_bootmem((unsigned long)phb, sizeof(struct pnv_phb));
 		return;
 	}
 
 	spin_lock_init(&phb->lock);
-	/* XXX Use device-tree */
-	hose->first_busno = 0;
-	hose->last_busno = 0xff;
+	prop32 = of_get_property(np, "bus-range", &len);
+	if (prop32 && len == 8) {
+		hose->first_busno = prop32[0];
+		hose->last_busno = prop32[1];
+	} else {
+		pr_warn("  Broken <bus-range> on %s\n", np->full_name);
+		hose->first_busno = 0;
+		hose->last_busno = 0xff;
+	}
 	hose->private_data = phb;
 	phb->hub_id = hub_id;
 	phb->opal_id = phb_id;
@@ -1152,8 +1163,7 @@ void __init pnv_pci_init_ioda_phb(struct device_node *np,
 		phb->model = PNV_PHB_MODEL_UNKNOWN;
 
 	/* Parse 32-bit and IO ranges (if any) */
-	pci_process_bridge_OF_ranges(phb->hose, np, primary);
-	primary = 0;
+	pci_process_bridge_OF_ranges(hose, np, !hose->global_number);
 
 	/* Get registers */
 	phb->regs = of_iomap(np, 0);
@@ -1177,22 +1187,23 @@ void __init pnv_pci_init_ioda_phb(struct device_node *np,
 	phb->ioda.io_segsize = phb->ioda.io_size / phb->ioda.total_pe;
 	phb->ioda.io_pci_base = 0; /* XXX calculate this ? */
 
-	/* Allocate aux data & arrays
-	 *
-	 * XXX TODO: Don't allocate io segmap on PHB3
-	 */
+	/* Allocate aux data & arrays. We don't have IO ports on PHB3 */
 	size = _ALIGN_UP(phb->ioda.total_pe / 8, sizeof(unsigned long));
 	m32map_off = size;
 	size += phb->ioda.total_pe * sizeof(phb->ioda.m32_segmap[0]);
 	iomap_off = size;
-	size += phb->ioda.total_pe * sizeof(phb->ioda.io_segmap[0]);
+	if (phb->type == PNV_PHB_IODA1) {
+		iomap_off = size;
+		size += phb->ioda.total_pe * sizeof(phb->ioda.io_segmap[0]);
+	}
 	pemap_off = size;
 	size += phb->ioda.total_pe * sizeof(struct pnv_ioda_pe);
 	aux = alloc_bootmem(size);
 	memset(aux, 0, size);
 	phb->ioda.pe_alloc = aux;
 	phb->ioda.m32_segmap = aux + m32map_off;
-	phb->ioda.io_segmap = aux + iomap_off;
+	if (phb->type == PNV_PHB_IODA1)
+		phb->ioda.io_segmap = aux + iomap_off;
 	phb->ioda.pe_array = aux + pemap_off;
 	set_bit(0, phb->ioda.pe_alloc);
 
diff --git a/arch/powerpc/platforms/powernv/powernv.h b/arch/powerpc/platforms/powernv/powernv.h
index a1c6f83fc391..de6819be1f95 100644
--- a/arch/powerpc/platforms/powernv/powernv.h
+++ b/arch/powerpc/platforms/powernv/powernv.h
@@ -15,4 +15,6 @@ static inline void pnv_pci_init(void) { }
 static inline void pnv_pci_shutdown(void) { }
 #endif
 
+extern void pnv_lpc_init(void);
+
 #endif /* _POWERNV_H */
diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c
index 84438af96c05..e239dcfa224c 100644
--- a/arch/powerpc/platforms/powernv/setup.c
+++ b/arch/powerpc/platforms/powernv/setup.c
@@ -31,6 +31,7 @@
 #include <asm/xics.h>
 #include <asm/rtas.h>
 #include <asm/opal.h>
+#include <asm/kexec.h>
 
 #include "powernv.h"
 
@@ -54,6 +55,12 @@ static void __init pnv_setup_arch(void)
 
 static void __init pnv_init_early(void)
 {
+	/*
+	 * Initialize the LPC bus now so that legacy serial
+	 * ports can be found on it
+	 */
+	opal_lpc_init();
+
 #ifdef CONFIG_HVC_OPAL
 	if (firmware_has_feature(FW_FEATURE_OPAL))
 		hvc_opal_init_early();
@@ -147,6 +154,16 @@ static void pnv_shutdown(void)
 static void pnv_kexec_cpu_down(int crash_shutdown, int secondary)
 {
 	xics_kexec_teardown_cpu(secondary);
+
+	/* Return secondary CPUs to firmware on OPAL v3 */
+	if (firmware_has_feature(FW_FEATURE_OPALv3) && secondary) {
+		mb();
+		get_paca()->kexec_state = KEXEC_STATE_REAL_MODE;
+		mb();
+
+		/* Return the CPU to OPAL */
+		opal_return_cpu();
+	}
 }
 #endif /* CONFIG_KEXEC */
 
diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c
index 89e3857af4e0..908672bdcea6 100644
--- a/arch/powerpc/platforms/powernv/smp.c
+++ b/arch/powerpc/platforms/powernv/smp.c
@@ -46,22 +46,6 @@ static void pnv_smp_setup_cpu(int cpu)
 		xics_setup_cpu();
 }
 
-static int pnv_smp_cpu_bootable(unsigned int nr)
-{
-	/* Special case - we inhibit secondary thread startup
-	 * during boot if the user requests it.
-	 */
-	if (system_state == SYSTEM_BOOTING && cpu_has_feature(CPU_FTR_SMT)) {
-		if (!smt_enabled_at_boot && cpu_thread_in_core(nr) != 0)
-			return 0;
-		if (smt_enabled_at_boot
-		    && cpu_thread_in_core(nr) >= smt_enabled_at_boot)
-			return 0;
-	}
-
-	return 1;
-}
-
 int pnv_smp_kick_cpu(int nr)
 {
 	unsigned int pcpu = get_hard_smp_processor_id(nr);
@@ -195,7 +179,7 @@ static struct smp_ops_t pnv_smp_ops = {
 	.probe		= xics_smp_probe,
 	.kick_cpu	= pnv_smp_kick_cpu,
 	.setup_cpu	= pnv_smp_setup_cpu,
-	.cpu_bootable	= pnv_smp_cpu_bootable,
+	.cpu_bootable	= smp_generic_cpu_bootable,
 #ifdef CONFIG_HOTPLUG_CPU
 	.cpu_disable	= pnv_smp_cpu_disable,
 	.cpu_die	= generic_cpu_die,
diff --git a/arch/powerpc/platforms/ps3/time.c b/arch/powerpc/platforms/ps3/time.c
index cba1e6be68e5..ce73ce865613 100644
--- a/arch/powerpc/platforms/ps3/time.c
+++ b/arch/powerpc/platforms/ps3/time.c
@@ -90,7 +90,7 @@ static int __init ps3_rtc_init(void)
 
 	pdev = platform_device_register_simple("rtc-ps3", -1, NULL, 0);
 
-	return PTR_RET(pdev);
+	return PTR_ERR_OR_ZERO(pdev);
 }
 
 module_init(ps3_rtc_init);
diff --git a/arch/powerpc/platforms/pseries/Makefile b/arch/powerpc/platforms/pseries/Makefile
index 8ae010381316..6c61ec5ee914 100644
--- a/arch/powerpc/platforms/pseries/Makefile
+++ b/arch/powerpc/platforms/pseries/Makefile
@@ -22,6 +22,7 @@ obj-$(CONFIG_CMM)		+= cmm.o
 obj-$(CONFIG_DTL)		+= dtl.o
 obj-$(CONFIG_IO_EVENT_IRQ)	+= io_event_irq.o
 obj-$(CONFIG_PSERIES_IDLE)	+= processor_idle.o
+obj-$(CONFIG_LPARCFG)		+= lparcfg.o
 
 ifeq ($(CONFIG_PPC_PSERIES),y)
 obj-$(CONFIG_SUSPEND)		+= suspend.o
diff --git a/arch/powerpc/platforms/pseries/cmm.c b/arch/powerpc/platforms/pseries/cmm.c
index c638535753df..1e561bef459b 100644
--- a/arch/powerpc/platforms/pseries/cmm.c
+++ b/arch/powerpc/platforms/pseries/cmm.c
@@ -40,8 +40,7 @@
 #include <asm/pgalloc.h>
 #include <asm/uaccess.h>
 #include <linux/memory.h>
-
-#include "plpar_wrappers.h"
+#include <asm/plpar_wrappers.h>
 
 #define CMM_DRIVER_VERSION	"1.0.0"
 #define CMM_DEFAULT_DELAY	1
diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c
index a1a7b9a67ffd..7cfdaae1721a 100644
--- a/arch/powerpc/platforms/pseries/dlpar.c
+++ b/arch/powerpc/platforms/pseries/dlpar.c
@@ -63,26 +63,32 @@ static struct property *dlpar_parse_cc_property(struct cc_workarea *ccwa)
 	return prop;
 }
 
-static struct device_node *dlpar_parse_cc_node(struct cc_workarea *ccwa)
+static struct device_node *dlpar_parse_cc_node(struct cc_workarea *ccwa,
+					       const char *path)
 {
 	struct device_node *dn;
 	char *name;
 
+	/* If parent node path is "/" advance path to NULL terminator to
+	 * prevent double leading slashs in full_name.
+	 */
+	if (!path[1])
+		path++;
+
 	dn = kzalloc(sizeof(*dn), GFP_KERNEL);
 	if (!dn)
 		return NULL;
 
-	/* The configure connector reported name does not contain a
-	 * preceding '/', so we allocate a buffer large enough to
-	 * prepend this to the full_name.
-	 */
 	name = (char *)ccwa + ccwa->name_offset;
-	dn->full_name = kasprintf(GFP_KERNEL, "/%s", name);
+	dn->full_name = kasprintf(GFP_KERNEL, "%s/%s", path, name);
 	if (!dn->full_name) {
 		kfree(dn);
 		return NULL;
 	}
 
+	of_node_set_flag(dn, OF_DYNAMIC);
+	kref_init(&dn->kref);
+
 	return dn;
 }
 
@@ -120,7 +126,8 @@ void dlpar_free_cc_nodes(struct device_node *dn)
 #define CALL_AGAIN	-2
 #define ERR_CFG_USE     -9003
 
-struct device_node *dlpar_configure_connector(u32 drc_index)
+struct device_node *dlpar_configure_connector(u32 drc_index,
+					      struct device_node *parent)
 {
 	struct device_node *dn;
 	struct device_node *first_dn = NULL;
@@ -129,6 +136,7 @@ struct device_node *dlpar_configure_connector(u32 drc_index)
 	struct property *last_property = NULL;
 	struct cc_workarea *ccwa;
 	char *data_buf;
+	const char *parent_path = parent->full_name;
 	int cc_token;
 	int rc = -1;
 
@@ -162,7 +170,7 @@ struct device_node *dlpar_configure_connector(u32 drc_index)
 			break;
 
 		case NEXT_SIBLING:
-			dn = dlpar_parse_cc_node(ccwa);
+			dn = dlpar_parse_cc_node(ccwa, parent_path);
 			if (!dn)
 				goto cc_error;
 
@@ -172,13 +180,17 @@ struct device_node *dlpar_configure_connector(u32 drc_index)
 			break;
 
 		case NEXT_CHILD:
-			dn = dlpar_parse_cc_node(ccwa);
+			if (first_dn)
+				parent_path = last_dn->full_name;
+
+			dn = dlpar_parse_cc_node(ccwa, parent_path);
 			if (!dn)
 				goto cc_error;
 
-			if (!first_dn)
+			if (!first_dn) {
+				dn->parent = parent;
 				first_dn = dn;
-			else {
+			} else {
 				dn->parent = last_dn;
 				if (last_dn)
 					last_dn->child = dn;
@@ -202,6 +214,7 @@ struct device_node *dlpar_configure_connector(u32 drc_index)
 
 		case PREV_PARENT:
 			last_dn = last_dn->parent;
+			parent_path = last_dn->parent->full_name;
 			break;
 
 		case CALL_AGAIN:
@@ -256,8 +269,6 @@ int dlpar_attach_node(struct device_node *dn)
 {
 	int rc;
 
-	of_node_set_flag(dn, OF_DYNAMIC);
-	kref_init(&dn->kref);
 	dn->parent = derive_parent(dn->full_name);
 	if (!dn->parent)
 		return -ENOMEM;
@@ -275,8 +286,15 @@ int dlpar_attach_node(struct device_node *dn)
 
 int dlpar_detach_node(struct device_node *dn)
 {
+	struct device_node *child;
 	int rc;
 
+	child = of_get_next_child(dn, NULL);
+	while (child) {
+		dlpar_detach_node(child);
+		child = of_get_next_child(dn, child);
+	}
+
 	rc = of_detach_node(dn);
 	if (rc)
 		return rc;
@@ -382,9 +400,8 @@ out:
 
 static ssize_t dlpar_cpu_probe(const char *buf, size_t count)
 {
-	struct device_node *dn;
+	struct device_node *dn, *parent;
 	unsigned long drc_index;
-	char *cpu_name;
 	int rc;
 
 	cpu_hotplug_driver_lock();
@@ -394,25 +411,19 @@ static ssize_t dlpar_cpu_probe(const char *buf, size_t count)
 		goto out;
 	}
 
-	dn = dlpar_configure_connector(drc_index);
-	if (!dn) {
-		rc = -EINVAL;
+	parent = of_find_node_by_path("/cpus");
+	if (!parent) {
+		rc = -ENODEV;
 		goto out;
 	}
 
-	/* configure-connector reports cpus as living in the base
-	 * directory of the device tree.  CPUs actually live in the
-	 * cpus directory so we need to fixup the full_name.
-	 */
-	cpu_name = kasprintf(GFP_KERNEL, "/cpus%s", dn->full_name);
-	if (!cpu_name) {
-		dlpar_free_cc_nodes(dn);
-		rc = -ENOMEM;
+	dn = dlpar_configure_connector(drc_index, parent);
+	if (!dn) {
+		rc = -EINVAL;
 		goto out;
 	}
 
-	kfree(dn->full_name);
-	dn->full_name = cpu_name;
+	of_node_put(parent);
 
 	rc = dlpar_acquire_drc(drc_index);
 	if (rc) {
diff --git a/arch/powerpc/platforms/pseries/dtl.c b/arch/powerpc/platforms/pseries/dtl.c
index 0cc0ac07a55d..5db66f1fbc26 100644
--- a/arch/powerpc/platforms/pseries/dtl.c
+++ b/arch/powerpc/platforms/pseries/dtl.c
@@ -29,8 +29,7 @@
 #include <asm/firmware.h>
 #include <asm/lppaca.h>
 #include <asm/debug.h>
-
-#include "plpar_wrappers.h"
+#include <asm/plpar_wrappers.h>
 
 struct dtl {
 	struct dtl_entry	*buf;
@@ -87,7 +86,7 @@ static void consume_dtle(struct dtl_entry *dtle, u64 index)
 	barrier();
 
 	/* check for hypervisor ring buffer overflow, ignore this entry if so */
-	if (index + N_DISPATCH_LOG < vpa->dtl_idx)
+	if (index + N_DISPATCH_LOG < be64_to_cpu(vpa->dtl_idx))
 		return;
 
 	++wp;
diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c
index 217ca5c75b20..82789e79e539 100644
--- a/arch/powerpc/platforms/pseries/hotplug-cpu.c
+++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c
@@ -30,7 +30,8 @@
 #include <asm/machdep.h>
 #include <asm/vdso_datapage.h>
 #include <asm/xics.h>
-#include "plpar_wrappers.h"
+#include <asm/plpar_wrappers.h>
+
 #include "offline_states.h"
 
 /* This version can't take the spinlock, because it never returns */
@@ -123,7 +124,7 @@ static void pseries_mach_cpu_die(void)
 		cede_latency_hint = 2;
 
 		get_lppaca()->idle = 1;
-		if (!get_lppaca()->shared_proc)
+		if (!lppaca_shared_proc(get_lppaca()))
 			get_lppaca()->donate_dedicated_cpu = 1;
 
 		while (get_preferred_offline_state(cpu) == CPU_STATE_INACTIVE) {
@@ -137,7 +138,7 @@ static void pseries_mach_cpu_die(void)
 
 		local_irq_disable();
 
-		if (!get_lppaca()->shared_proc)
+		if (!lppaca_shared_proc(get_lppaca()))
 			get_lppaca()->donate_dedicated_cpu = 0;
 		get_lppaca()->idle = 0;
 
diff --git a/arch/powerpc/platforms/pseries/hvconsole.c b/arch/powerpc/platforms/pseries/hvconsole.c
index b344f94b0400..849b29b3e9ae 100644
--- a/arch/powerpc/platforms/pseries/hvconsole.c
+++ b/arch/powerpc/platforms/pseries/hvconsole.c
@@ -28,7 +28,7 @@
 #include <linux/errno.h>
 #include <asm/hvcall.h>
 #include <asm/hvconsole.h>
-#include "plpar_wrappers.h"
+#include <asm/plpar_wrappers.h>
 
 /**
  * hvc_get_chars - retrieve characters from firmware for denoted vterm adatper
@@ -40,10 +40,16 @@
  */
 int hvc_get_chars(uint32_t vtermno, char *buf, int count)
 {
-	unsigned long got;
+	long ret;
+	unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
+	unsigned long *lbuf = (unsigned long *)buf;
+
+	ret = plpar_hcall(H_GET_TERM_CHAR, retbuf, vtermno);
+	lbuf[0] = be64_to_cpu(retbuf[1]);
+	lbuf[1] = be64_to_cpu(retbuf[2]);
 
-	if (plpar_get_term_char(vtermno, &got, buf) == H_SUCCESS)
-		return got;
+	if (ret == H_SUCCESS)
+		return retbuf[0];
 
 	return 0;
 }
@@ -69,8 +75,9 @@ int hvc_put_chars(uint32_t vtermno, const char *buf, int count)
 	if (count > MAX_VIO_PUT_CHARS)
 		count = MAX_VIO_PUT_CHARS;
 
-	ret = plpar_hcall_norets(H_PUT_TERM_CHAR, vtermno, count, lbuf[0],
-				 lbuf[1]);
+	ret = plpar_hcall_norets(H_PUT_TERM_CHAR, vtermno, count,
+				 cpu_to_be64(lbuf[0]),
+				 cpu_to_be64(lbuf[1]));
 	if (ret == H_SUCCESS)
 		return count;
 	if (ret == H_BUSY)
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index 23fc1dcf4434..0307901e4132 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -48,8 +48,7 @@
 #include <asm/ppc-pci.h>
 #include <asm/udbg.h>
 #include <asm/mmzone.h>
-
-#include "plpar_wrappers.h"
+#include <asm/plpar_wrappers.h>
 
 
 static void tce_invalidate_pSeries_sw(struct iommu_table *tbl,
@@ -530,7 +529,7 @@ static void iommu_table_setparms(struct pci_controller *phb,
 static void iommu_table_setparms_lpar(struct pci_controller *phb,
 				      struct device_node *dn,
 				      struct iommu_table *tbl,
-				      const void *dma_window)
+				      const __be32 *dma_window)
 {
 	unsigned long offset, size;
 
@@ -630,7 +629,7 @@ static void pci_dma_bus_setup_pSeriesLP(struct pci_bus *bus)
 	struct iommu_table *tbl;
 	struct device_node *dn, *pdn;
 	struct pci_dn *ppci;
-	const void *dma_window = NULL;
+	const __be32 *dma_window = NULL;
 
 	dn = pci_bus_to_OF_node(bus);
 
@@ -1152,7 +1151,7 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev)
 {
 	struct device_node *pdn, *dn;
 	struct iommu_table *tbl;
-	const void *dma_window = NULL;
+	const __be32 *dma_window = NULL;
 	struct pci_dn *pci;
 
 	pr_debug("pci_dma_dev_setup_pSeriesLP: %s\n", pci_name(dev));
@@ -1201,7 +1200,7 @@ static int dma_set_mask_pSeriesLP(struct device *dev, u64 dma_mask)
 	bool ddw_enabled = false;
 	struct device_node *pdn, *dn;
 	struct pci_dev *pdev;
-	const void *dma_window = NULL;
+	const __be32 *dma_window = NULL;
 	u64 dma_offset;
 
 	if (!dev->dma_mask)
diff --git a/arch/powerpc/platforms/pseries/kexec.c b/arch/powerpc/platforms/pseries/kexec.c
index 7d94bdc63d50..13fa95b3aa8b 100644
--- a/arch/powerpc/platforms/pseries/kexec.c
+++ b/arch/powerpc/platforms/pseries/kexec.c
@@ -17,9 +17,9 @@
 #include <asm/mpic.h>
 #include <asm/xics.h>
 #include <asm/smp.h>
+#include <asm/plpar_wrappers.h>
 
 #include "pseries.h"
-#include "plpar_wrappers.h"
 
 static void pseries_kexec_cpu_down(int crash_shutdown, int secondary)
 {
diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index 8bad880bd177..356bc75ca74f 100644
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -41,8 +41,8 @@
 #include <asm/smp.h>
 #include <asm/trace.h>
 #include <asm/firmware.h>
+#include <asm/plpar_wrappers.h>
 
-#include "plpar_wrappers.h"
 #include "pseries.h"
 
 /* Flag bits for H_BULK_REMOVE */
@@ -68,6 +68,12 @@ void vpa_init(int cpu)
 	struct paca_struct *pp;
 	struct dtl_entry *dtl;
 
+	/*
+	 * The spec says it "may be problematic" if CPU x registers the VPA of
+	 * CPU y. We should never do that, but wail if we ever do.
+	 */
+	WARN_ON(cpu != smp_processor_id());
+
 	if (cpu_has_feature(CPU_FTR_ALTIVEC))
 		lppaca_of(cpu).vmxregs_in_use = 1;
 
@@ -106,7 +112,7 @@ void vpa_init(int cpu)
 		lppaca_of(cpu).dtl_idx = 0;
 
 		/* hypervisor reads buffer length from this field */
-		dtl->enqueue_to_dispatch_time = DISPATCH_LOG_BYTES;
+		dtl->enqueue_to_dispatch_time = cpu_to_be32(DISPATCH_LOG_BYTES);
 		ret = register_dtl(hwcpu, __pa(dtl));
 		if (ret)
 			pr_err("WARNING: DTL registration of cpu %d (hw %d) "
@@ -724,7 +730,7 @@ int h_get_mpp(struct hvcall_mpp_data *mpp_data)
 
 	mpp_data->mem_weight = (retbuf[3] >> 7 * 8) & 0xff;
 	mpp_data->unallocated_mem_weight = (retbuf[3] >> 6 * 8) & 0xff;
-	mpp_data->unallocated_entitlement = retbuf[3] & 0xffffffffffff;
+	mpp_data->unallocated_entitlement = retbuf[3] & 0xffffffffffffUL;
 
 	mpp_data->pool_size = retbuf[4];
 	mpp_data->loan_request = retbuf[5];
diff --git a/arch/powerpc/kernel/lparcfg.c b/arch/powerpc/platforms/pseries/lparcfg.c
index e2a0a162299b..e738007eae64 100644
--- a/arch/powerpc/kernel/lparcfg.c
+++ b/arch/powerpc/platforms/pseries/lparcfg.c
@@ -171,7 +171,7 @@ static void parse_ppp_data(struct seq_file *m)
 	           ppp_data.active_system_procs);
 
 	/* pool related entries are appropriate for shared configs */
-	if (lppaca_of(0).shared_proc) {
+	if (lppaca_shared_proc(get_lppaca())) {
 		unsigned long pool_idle_time, pool_procs;
 
 		seq_printf(m, "pool=%d\n", ppp_data.pool_num);
@@ -393,8 +393,8 @@ static void pseries_cmo_data(struct seq_file *m)
 		return;
 
 	for_each_possible_cpu(cpu) {
-		cmo_faults += lppaca_of(cpu).cmo_faults;
-		cmo_fault_time += lppaca_of(cpu).cmo_fault_time;
+		cmo_faults += be64_to_cpu(lppaca_of(cpu).cmo_faults);
+		cmo_fault_time += be64_to_cpu(lppaca_of(cpu).cmo_fault_time);
 	}
 
 	seq_printf(m, "cmo_faults=%lu\n", cmo_faults);
@@ -412,8 +412,9 @@ static void splpar_dispatch_data(struct seq_file *m)
 	unsigned long dispatch_dispersions = 0;
 
 	for_each_possible_cpu(cpu) {
-		dispatches += lppaca_of(cpu).yield_count;
-		dispatch_dispersions += lppaca_of(cpu).dispersion_count;
+		dispatches += be32_to_cpu(lppaca_of(cpu).yield_count);
+		dispatch_dispersions +=
+			be32_to_cpu(lppaca_of(cpu).dispersion_count);
 	}
 
 	seq_printf(m, "dispatches=%lu\n", dispatches);
@@ -480,7 +481,8 @@ static int pseries_lparcfg_data(struct seq_file *m, void *v)
 	seq_printf(m, "partition_potential_processors=%d\n",
 		   partition_potential_processors);
 
-	seq_printf(m, "shared_processor_mode=%d\n", lppaca_of(0).shared_proc);
+	seq_printf(m, "shared_processor_mode=%d\n",
+		   lppaca_shared_proc(get_lppaca()));
 
 	seq_printf(m, "slb_size=%d\n", mmu_slb_size);
 
diff --git a/arch/powerpc/platforms/pseries/mobility.c b/arch/powerpc/platforms/pseries/mobility.c
index 3d01eee9ffb1..cde4e0a095ae 100644
--- a/arch/powerpc/platforms/pseries/mobility.c
+++ b/arch/powerpc/platforms/pseries/mobility.c
@@ -28,7 +28,7 @@ struct update_props_workarea {
 	u32 state;
 	u64 reserved;
 	u32 nprops;
-};
+} __packed;
 
 #define NODE_ACTION_MASK	0xff000000
 #define NODE_COUNT_MASK		0x00ffffff
@@ -62,6 +62,7 @@ static int delete_dt_node(u32 phandle)
 		return -ENOENT;
 
 	dlpar_detach_node(dn);
+	of_node_put(dn);
 	return 0;
 }
 
@@ -119,7 +120,7 @@ static int update_dt_property(struct device_node *dn, struct property **prop,
 
 	if (!more) {
 		of_update_property(dn, new_prop);
-		new_prop = NULL;
+		*prop = NULL;
 	}
 
 	return 0;
@@ -130,7 +131,7 @@ static int update_dt_node(u32 phandle, s32 scope)
 	struct update_props_workarea *upwa;
 	struct device_node *dn;
 	struct property *prop = NULL;
-	int i, rc;
+	int i, rc, rtas_rc;
 	char *prop_data;
 	char *rtas_buf;
 	int update_properties_token;
@@ -154,25 +155,26 @@ static int update_dt_node(u32 phandle, s32 scope)
 	upwa->phandle = phandle;
 
 	do {
-		rc = mobility_rtas_call(update_properties_token, rtas_buf,
+		rtas_rc = mobility_rtas_call(update_properties_token, rtas_buf,
 					scope);
-		if (rc < 0)
+		if (rtas_rc < 0)
 			break;
 
 		prop_data = rtas_buf + sizeof(*upwa);
 
-		/* The first element of the buffer is the path of the node
-		 * being updated in the form of a 8 byte string length
-		 * followed by the string. Skip past this to get to the
-		 * properties being updated.
+		/* On the first call to ibm,update-properties for a node the
+		 * the first property value descriptor contains an empty
+		 * property name, the property value length encoded as u32,
+		 * and the property value is the node path being updated.
 		 */
-		vd = *prop_data++;
-		prop_data += vd;
+		if (*prop_data == 0) {
+			prop_data++;
+			vd = *(u32 *)prop_data;
+			prop_data += vd + sizeof(vd);
+			upwa->nprops--;
+		}
 
-		/* The path we skipped over is counted as one of the elements
-		 * returned so start counting at one.
-		 */
-		for (i = 1; i < upwa->nprops; i++) {
+		for (i = 0; i < upwa->nprops; i++) {
 			char *prop_name;
 
 			prop_name = prop_data;
@@ -202,7 +204,7 @@ static int update_dt_node(u32 phandle, s32 scope)
 				prop_data += vd;
 			}
 		}
-	} while (rc == 1);
+	} while (rtas_rc == 1);
 
 	of_node_put(dn);
 	kfree(rtas_buf);
@@ -215,17 +217,14 @@ static int add_dt_node(u32 parent_phandle, u32 drc_index)
 	struct device_node *parent_dn;
 	int rc;
 
-	dn = dlpar_configure_connector(drc_index);
-	if (!dn)
+	parent_dn = of_find_node_by_phandle(parent_phandle);
+	if (!parent_dn)
 		return -ENOENT;
 
-	parent_dn = of_find_node_by_phandle(parent_phandle);
-	if (!parent_dn) {
-		dlpar_free_cc_nodes(dn);
+	dn = dlpar_configure_connector(drc_index, parent_dn);
+	if (!dn)
 		return -ENOENT;
-	}
 
-	dn->parent = parent_dn;
 	rc = dlpar_attach_node(dn);
 	if (rc)
 		dlpar_free_cc_nodes(dn);
diff --git a/arch/powerpc/platforms/pseries/nvram.c b/arch/powerpc/platforms/pseries/nvram.c
index 6a5f2b1f32ca..d276cd3edd8f 100644
--- a/arch/powerpc/platforms/pseries/nvram.c
+++ b/arch/powerpc/platforms/pseries/nvram.c
@@ -539,36 +539,6 @@ static int zip_oops(size_t text_len)
 }
 
 #ifdef CONFIG_PSTORE
-/* Derived from logfs_uncompress */
-int nvram_decompress(void *in, void *out, size_t inlen, size_t outlen)
-{
-	int err, ret;
-
-	ret = -EIO;
-	err = zlib_inflateInit(&stream);
-	if (err != Z_OK)
-		goto error;
-
-	stream.next_in = in;
-	stream.avail_in = inlen;
-	stream.total_in = 0;
-	stream.next_out = out;
-	stream.avail_out = outlen;
-	stream.total_out = 0;
-
-	err = zlib_inflate(&stream, Z_FINISH);
-	if (err != Z_STREAM_END)
-		goto error;
-
-	err = zlib_inflateEnd(&stream);
-	if (err != Z_OK)
-		goto error;
-
-	ret = stream.total_out;
-error:
-	return ret;
-}
-
 static int nvram_pstore_open(struct pstore_info *psi)
 {
 	/* Reset the iterator to start reading partitions again */
@@ -584,7 +554,7 @@ static int nvram_pstore_open(struct pstore_info *psi)
  * @part:               pstore writes data to registered buffer in parts,
  *                      part number will indicate the same.
  * @count:              Indicates oops count
- * @hsize:              Size of header added by pstore
+ * @compressed:         Flag to indicate the log is compressed
  * @size:               number of bytes written to the registered buffer
  * @psi:                registered pstore_info structure
  *
@@ -595,7 +565,7 @@ static int nvram_pstore_open(struct pstore_info *psi)
 static int nvram_pstore_write(enum pstore_type_id type,
 				enum kmsg_dump_reason reason,
 				u64 *id, unsigned int part, int count,
-				size_t hsize, size_t size,
+				bool compressed, size_t size,
 				struct pstore_info *psi)
 {
 	int rc;
@@ -611,30 +581,11 @@ static int nvram_pstore_write(enum pstore_type_id type,
 	oops_hdr->report_length = (u16) size;
 	oops_hdr->timestamp = get_seconds();
 
-	if (big_oops_buf) {
-		rc = zip_oops(size);
-		/*
-		 * If compression fails copy recent log messages from
-		 * big_oops_buf to oops_data.
-		 */
-		if (rc != 0) {
-			size_t diff = size - oops_data_sz + hsize;
-
-			if (size > oops_data_sz) {
-				memcpy(oops_data, big_oops_buf, hsize);
-				memcpy(oops_data + hsize, big_oops_buf + diff,
-					oops_data_sz - hsize);
-
-				oops_hdr->report_length = (u16) oops_data_sz;
-			} else
-				memcpy(oops_data, big_oops_buf, size);
-		} else
-			err_type = ERR_TYPE_KERNEL_PANIC_GZ;
-	}
+	if (compressed)
+		err_type = ERR_TYPE_KERNEL_PANIC_GZ;
 
 	rc = nvram_write_os_partition(&oops_log_partition, oops_buf,
-		(int) (sizeof(*oops_hdr) + oops_hdr->report_length), err_type,
-		count);
+		(int) (sizeof(*oops_hdr) + size), err_type, count);
 
 	if (rc != 0)
 		return rc;
@@ -650,12 +601,12 @@ static int nvram_pstore_write(enum pstore_type_id type,
  */
 static ssize_t nvram_pstore_read(u64 *id, enum pstore_type_id *type,
 				int *count, struct timespec *time, char **buf,
-				struct pstore_info *psi)
+				bool *compressed, struct pstore_info *psi)
 {
 	struct oops_log_info *oops_hdr;
 	unsigned int err_type, id_no, size = 0;
 	struct nvram_os_partition *part = NULL;
-	char *buff = NULL, *big_buff = NULL;
+	char *buff = NULL;
 	int sig = 0;
 	loff_t p;
 
@@ -719,8 +670,7 @@ static ssize_t nvram_pstore_read(u64 *id, enum pstore_type_id *type,
 		*id = id_no;
 
 	if (nvram_type_ids[read_type] == PSTORE_TYPE_DMESG) {
-		int length, unzipped_len;
-		size_t hdr_size;
+		size_t length, hdr_size;
 
 		oops_hdr = (struct oops_log_info *)buff;
 		if (oops_hdr->version < OOPS_HDR_VERSION) {
@@ -741,23 +691,10 @@ static ssize_t nvram_pstore_read(u64 *id, enum pstore_type_id *type,
 		memcpy(*buf, buff + hdr_size, length);
 		kfree(buff);
 
-		if (err_type == ERR_TYPE_KERNEL_PANIC_GZ) {
-			big_buff = kmalloc(big_oops_buf_sz, GFP_KERNEL);
-			if (!big_buff)
-				return -ENOMEM;
-
-			unzipped_len = nvram_decompress(*buf, big_buff,
-						length, big_oops_buf_sz);
-
-			if (unzipped_len < 0) {
-				pr_err("nvram: decompression failed, returned "
-					"rc %d\n", unzipped_len);
-				kfree(big_buff);
-			} else {
-				*buf = big_buff;
-				length = unzipped_len;
-			}
-		}
+		if (err_type == ERR_TYPE_KERNEL_PANIC_GZ)
+			*compressed = true;
+		else
+			*compressed = false;
 		return length;
 	}
 
@@ -777,13 +714,8 @@ static int nvram_pstore_init(void)
 {
 	int rc = 0;
 
-	if (big_oops_buf) {
-		nvram_pstore_info.buf = big_oops_buf;
-		nvram_pstore_info.bufsize = big_oops_buf_sz;
-	} else {
-		nvram_pstore_info.buf = oops_data;
-		nvram_pstore_info.bufsize = oops_data_sz;
-	}
+	nvram_pstore_info.buf = oops_data;
+	nvram_pstore_info.bufsize = oops_data_sz;
 
 	rc = pstore_register(&nvram_pstore_info);
 	if (rc != 0)
@@ -802,7 +734,6 @@ static int nvram_pstore_init(void)
 static void __init nvram_init_oops_partition(int rtas_partition_exists)
 {
 	int rc;
-	size_t size;
 
 	rc = pseries_nvram_init_os_partition(&oops_log_partition);
 	if (rc != 0) {
@@ -823,6 +754,11 @@ static void __init nvram_init_oops_partition(int rtas_partition_exists)
 	oops_data = oops_buf + sizeof(struct oops_log_info);
 	oops_data_sz = oops_log_partition.size - sizeof(struct oops_log_info);
 
+	rc = nvram_pstore_init();
+
+	if (!rc)
+		return;
+
 	/*
 	 * Figure compression (preceded by elimination of each line's <n>
 	 * severity prefix) will reduce the oops/panic report to at most
@@ -831,9 +767,8 @@ static void __init nvram_init_oops_partition(int rtas_partition_exists)
 	big_oops_buf_sz = (oops_data_sz * 100) / 45;
 	big_oops_buf = kmalloc(big_oops_buf_sz, GFP_KERNEL);
 	if (big_oops_buf) {
-		size = max(zlib_deflate_workspacesize(WINDOW_BITS, MEM_LEVEL),
-			zlib_inflate_workspacesize());
-		stream.workspace = kmalloc(size, GFP_KERNEL);
+		stream.workspace =  kmalloc(zlib_deflate_workspacesize(
+					WINDOW_BITS, MEM_LEVEL), GFP_KERNEL);
 		if (!stream.workspace) {
 			pr_err("nvram: No memory for compression workspace; "
 				"skipping compression of %s partition data\n",
@@ -847,11 +782,6 @@ static void __init nvram_init_oops_partition(int rtas_partition_exists)
 		stream.workspace = NULL;
 	}
 
-	rc = nvram_pstore_init();
-
-	if (!rc)
-		return;
-
 	rc = kmsg_dump_register(&nvram_kmsg_dumper);
 	if (rc != 0) {
 		pr_err("nvram: kmsg_dump_register() failed; returned %d\n", rc);
diff --git a/arch/powerpc/platforms/pseries/processor_idle.c b/arch/powerpc/platforms/pseries/processor_idle.c
index 4644efa06941..a166e38bd683 100644
--- a/arch/powerpc/platforms/pseries/processor_idle.c
+++ b/arch/powerpc/platforms/pseries/processor_idle.c
@@ -18,9 +18,7 @@
 #include <asm/machdep.h>
 #include <asm/firmware.h>
 #include <asm/runlatch.h>
-
-#include "plpar_wrappers.h"
-#include "pseries.h"
+#include <asm/plpar_wrappers.h>
 
 struct cpuidle_driver pseries_idle_driver = {
 	.name             = "pseries_idle",
@@ -45,7 +43,11 @@ static inline void idle_loop_prolog(unsigned long *in_purr)
 
 static inline void idle_loop_epilog(unsigned long in_purr)
 {
-	get_lppaca()->wait_state_cycles += mfspr(SPRN_PURR) - in_purr;
+	u64 wait_cycles;
+
+	wait_cycles = be64_to_cpu(get_lppaca()->wait_state_cycles);
+	wait_cycles += mfspr(SPRN_PURR) - in_purr;
+	get_lppaca()->wait_state_cycles = cpu_to_be64(wait_cycles);
 	get_lppaca()->idle = 0;
 }
 
@@ -308,7 +310,7 @@ static int pseries_idle_probe(void)
 		return -EPERM;
 	}
 
-	if (get_lppaca()->shared_proc)
+	if (lppaca_shared_proc(get_lppaca()))
 		cpuidle_state_table = shared_states;
 	else
 		cpuidle_state_table = dedicated_states;
diff --git a/arch/powerpc/platforms/pseries/pseries.h b/arch/powerpc/platforms/pseries/pseries.h
index c2a3a258001c..99219530ea4a 100644
--- a/arch/powerpc/platforms/pseries/pseries.h
+++ b/arch/powerpc/platforms/pseries/pseries.h
@@ -56,13 +56,10 @@ extern void hvc_vio_init_early(void);
 /* Dynamic logical Partitioning/Mobility */
 extern void dlpar_free_cc_nodes(struct device_node *);
 extern void dlpar_free_cc_property(struct property *);
-extern struct device_node *dlpar_configure_connector(u32);
+extern struct device_node *dlpar_configure_connector(u32, struct device_node *);
 extern int dlpar_attach_node(struct device_node *);
 extern int dlpar_detach_node(struct device_node *);
 
-/* Snooze Delay, pseries_idle */
-DECLARE_PER_CPU(long, smt_snooze_delay);
-
 /* PCI root bridge prepare function override for pseries */
 struct pci_host_bridge;
 int pseries_root_bridge_prepare(struct pci_host_bridge *bridge);
diff --git a/arch/powerpc/platforms/pseries/pseries_energy.c b/arch/powerpc/platforms/pseries/pseries_energy.c
index a91e6dadda2c..92767791f93b 100644
--- a/arch/powerpc/platforms/pseries/pseries_energy.c
+++ b/arch/powerpc/platforms/pseries/pseries_energy.c
@@ -108,8 +108,8 @@ err:
  * energy consumption.
  */
 
-#define FLAGS_MODE1	0x004E200000080E01
-#define FLAGS_MODE2	0x004E200000080401
+#define FLAGS_MODE1	0x004E200000080E01UL
+#define FLAGS_MODE2	0x004E200000080401UL
 #define FLAGS_ACTIVATE  0x100
 
 static ssize_t get_best_energy_list(char *page, int activate)
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index c11c8238797c..1f97e2b87a62 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -66,8 +66,8 @@
 #include <asm/firmware.h>
 #include <asm/eeh.h>
 #include <asm/reg.h>
+#include <asm/plpar_wrappers.h>
 
-#include "plpar_wrappers.h"
 #include "pseries.h"
 
 int CMO_PrPSP = -1;
@@ -183,7 +183,7 @@ static void __init pseries_mpic_init_IRQ(void)
 	np = of_find_node_by_path("/");
 	naddr = of_n_addr_cells(np);
 	opprop = of_get_property(np, "platform-open-pic", &opplen);
-	if (opprop != 0) {
+	if (opprop != NULL) {
 		openpic_addr = of_read_number(opprop, naddr);
 		printk(KERN_DEBUG "OpenPIC addr: %lx\n", openpic_addr);
 	}
@@ -323,7 +323,7 @@ static int alloc_dispatch_logs(void)
 	get_paca()->lppaca_ptr->dtl_idx = 0;
 
 	/* hypervisor reads buffer length from this field */
-	dtl->enqueue_to_dispatch_time = DISPATCH_LOG_BYTES;
+	dtl->enqueue_to_dispatch_time = cpu_to_be32(DISPATCH_LOG_BYTES);
 	ret = register_dtl(hard_smp_processor_id(), __pa(dtl));
 	if (ret)
 		pr_err("WARNING: DTL registration of cpu %d (hw %d) failed "
@@ -354,7 +354,7 @@ static int alloc_dispatch_log_kmem_cache(void)
 }
 early_initcall(alloc_dispatch_log_kmem_cache);
 
-static void pSeries_idle(void)
+static void pseries_lpar_idle(void)
 {
 	/* This would call on the cpuidle framework, and the back-end pseries
 	 * driver to  go to idle states
@@ -362,10 +362,22 @@ static void pSeries_idle(void)
 	if (cpuidle_idle_call()) {
 		/* On error, execute default handler
 		 * to go into low thread priority and possibly
-		 * low power mode.
+		 * low power mode by cedeing processor to hypervisor
 		 */
-		HMT_low();
-		HMT_very_low();
+
+		/* Indicate to hypervisor that we are idle. */
+		get_lppaca()->idle = 1;
+
+		/*
+		 * Yield the processor to the hypervisor.  We return if
+		 * an external interrupt occurs (which are driven prior
+		 * to returning here) or if a prod occurs from another
+		 * processor. When returning here, external interrupts
+		 * are enabled.
+		 */
+		cede_processor();
+
+		get_lppaca()->idle = 0;
 	}
 }
 
@@ -456,15 +468,14 @@ static void __init pSeries_setup_arch(void)
 
 	pSeries_nvram_init();
 
-	if (firmware_has_feature(FW_FEATURE_SPLPAR)) {
+	if (firmware_has_feature(FW_FEATURE_LPAR)) {
 		vpa_init(boot_cpuid);
-		ppc_md.power_save = pSeries_idle;
-	}
-
-	if (firmware_has_feature(FW_FEATURE_LPAR))
+		ppc_md.power_save = pseries_lpar_idle;
 		ppc_md.enable_pmcs = pseries_lpar_enable_pmcs;
-	else
+	} else {
+		/* No special idle routine */
 		ppc_md.enable_pmcs = power4_enable_pmcs;
+	}
 
 	ppc_md.pcibios_root_bridge_prepare = pseries_root_bridge_prepare;
 
diff --git a/arch/powerpc/platforms/pseries/smp.c b/arch/powerpc/platforms/pseries/smp.c
index 306643cc9dbc..24f58cb0a543 100644
--- a/arch/powerpc/platforms/pseries/smp.c
+++ b/arch/powerpc/platforms/pseries/smp.c
@@ -43,8 +43,8 @@
 #include <asm/cputhreads.h>
 #include <asm/xics.h>
 #include <asm/dbell.h>
+#include <asm/plpar_wrappers.h>
 
-#include "plpar_wrappers.h"
 #include "pseries.h"
 #include "offline_states.h"
 
@@ -187,22 +187,6 @@ static int smp_pSeries_kick_cpu(int nr)
 	return 0;
 }
 
-static int smp_pSeries_cpu_bootable(unsigned int nr)
-{
-	/* Special case - we inhibit secondary thread startup
-	 * during boot if the user requests it.
-	 */
-	if (system_state == SYSTEM_BOOTING && cpu_has_feature(CPU_FTR_SMT)) {
-		if (!smt_enabled_at_boot && cpu_thread_in_core(nr) != 0)
-			return 0;
-		if (smt_enabled_at_boot
-		    && cpu_thread_in_core(nr) >= smt_enabled_at_boot)
-			return 0;
-	}
-
-	return 1;
-}
-
 /* Only used on systems that support multiple IPI mechanisms */
 static void pSeries_cause_ipi_mux(int cpu, unsigned long data)
 {
@@ -237,7 +221,7 @@ static struct smp_ops_t pSeries_xics_smp_ops = {
 	.probe		= pSeries_smp_probe,
 	.kick_cpu	= smp_pSeries_kick_cpu,
 	.setup_cpu	= smp_xics_setup_cpu,
-	.cpu_bootable	= smp_pSeries_cpu_bootable,
+	.cpu_bootable	= smp_generic_cpu_bootable,
 };
 
 /* This is called very early */
@@ -249,18 +233,24 @@ static void __init smp_init_pseries(void)
 
 	alloc_bootmem_cpumask_var(&of_spin_mask);
 
-	/* Mark threads which are still spinning in hold loops. */
-	if (cpu_has_feature(CPU_FTR_SMT)) {
-		for_each_present_cpu(i) { 
-			if (cpu_thread_in_core(i) == 0)
-				cpumask_set_cpu(i, of_spin_mask);
-		}
-	} else {
-		cpumask_copy(of_spin_mask, cpu_present_mask);
+	/*
+	 * Mark threads which are still spinning in hold loops
+	 *
+	 * We know prom_init will not have started them if RTAS supports
+	 * query-cpu-stopped-state.
+	 */
+	if (rtas_token("query-cpu-stopped-state") == RTAS_UNKNOWN_SERVICE) {
+		if (cpu_has_feature(CPU_FTR_SMT)) {
+			for_each_present_cpu(i) {
+				if (cpu_thread_in_core(i) == 0)
+					cpumask_set_cpu(i, of_spin_mask);
+			}
+		} else
+			cpumask_copy(of_spin_mask, cpu_present_mask);
+
+		cpumask_clear_cpu(boot_cpuid, of_spin_mask);
 	}
 
-	cpumask_clear_cpu(boot_cpuid, of_spin_mask);
-
 	/* Non-lpar has additional take/give timebase */
 	if (rtas_token("freeze-time-base") != RTAS_UNKNOWN_SERVICE) {
 		smp_ops->give_timebase = rtas_give_timebase;
diff --git a/arch/powerpc/platforms/wsp/wsp.h b/arch/powerpc/platforms/wsp/wsp.h
index 62ef21afb89a..a563a8aaf812 100644
--- a/arch/powerpc/platforms/wsp/wsp.h
+++ b/arch/powerpc/platforms/wsp/wsp.h
@@ -17,7 +17,6 @@ extern void scom_init_wsp(void);
 extern void a2_setup_smp(void);
 extern int a2_scom_startup_cpu(unsigned int lcpu, int thr_idx,
 			       struct device_node *np);
-extern int smp_a2_cpu_bootable(unsigned int nr);
 extern int smp_a2_kick_cpu(int nr);
 
 extern void opb_pic_init(void);
diff --git a/arch/powerpc/sysdev/fsl_msi.c b/arch/powerpc/sysdev/fsl_msi.c
index ab02db3d02d8..77efbaec7b9c 100644
--- a/arch/powerpc/sysdev/fsl_msi.c
+++ b/arch/powerpc/sysdev/fsl_msi.c
@@ -28,6 +28,18 @@
 #include "fsl_msi.h"
 #include "fsl_pci.h"
 
+#define MSIIR_OFFSET_MASK	0xfffff
+#define MSIIR_IBS_SHIFT		0
+#define MSIIR_SRS_SHIFT		5
+#define MSIIR1_IBS_SHIFT	4
+#define MSIIR1_SRS_SHIFT	0
+#define MSI_SRS_MASK		0xf
+#define MSI_IBS_MASK		0x1f
+
+#define msi_hwirq(msi, msir_index, intr_index) \
+		((msir_index) << (msi)->srs_shift | \
+		 ((intr_index) << (msi)->ibs_shift))
+
 static LIST_HEAD(msi_head);
 
 struct fsl_msi_feature {
@@ -80,18 +92,19 @@ static const struct irq_domain_ops fsl_msi_host_ops = {
 
 static int fsl_msi_init_allocator(struct fsl_msi *msi_data)
 {
-	int rc;
+	int rc, hwirq;
 
-	rc = msi_bitmap_alloc(&msi_data->bitmap, NR_MSI_IRQS,
+	rc = msi_bitmap_alloc(&msi_data->bitmap, NR_MSI_IRQS_MAX,
 			      msi_data->irqhost->of_node);
 	if (rc)
 		return rc;
 
-	rc = msi_bitmap_reserve_dt_hwirqs(&msi_data->bitmap);
-	if (rc < 0) {
-		msi_bitmap_free(&msi_data->bitmap);
-		return rc;
-	}
+	/*
+	 * Reserve all the hwirqs
+	 * The available hwirqs will be released in fsl_msi_setup_hwirq()
+	 */
+	for (hwirq = 0; hwirq < NR_MSI_IRQS_MAX; hwirq++)
+		msi_bitmap_reserve_hwirq(&msi_data->bitmap, hwirq);
 
 	return 0;
 }
@@ -144,8 +157,9 @@ static void fsl_compose_msi_msg(struct pci_dev *pdev, int hwirq,
 
 	msg->data = hwirq;
 
-	pr_debug("%s: allocated srs: %d, ibs: %d\n",
-		__func__, hwirq / IRQS_PER_MSI_REG, hwirq % IRQS_PER_MSI_REG);
+	pr_debug("%s: allocated srs: %d, ibs: %d\n", __func__,
+		 (hwirq >> msi_data->srs_shift) & MSI_SRS_MASK,
+		 (hwirq >> msi_data->ibs_shift) & MSI_IBS_MASK);
 }
 
 static int fsl_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
@@ -255,7 +269,7 @@ static void fsl_msi_cascade(unsigned int irq, struct irq_desc *desc)
 
 	msir_index = cascade_data->index;
 
-	if (msir_index >= NR_MSI_REG)
+	if (msir_index >= NR_MSI_REG_MAX)
 		cascade_irq = NO_IRQ;
 
 	irqd_set_chained_irq_inprogress(idata);
@@ -285,8 +299,8 @@ static void fsl_msi_cascade(unsigned int irq, struct irq_desc *desc)
 		intr_index = ffs(msir_value) - 1;
 
 		cascade_irq = irq_linear_revmap(msi_data->irqhost,
-				msir_index * IRQS_PER_MSI_REG +
-					intr_index + have_shift);
+				msi_hwirq(msi_data, msir_index,
+					  intr_index + have_shift));
 		if (cascade_irq != NO_IRQ)
 			generic_handle_irq(cascade_irq);
 		have_shift += intr_index + 1;
@@ -316,7 +330,7 @@ static int fsl_of_msi_remove(struct platform_device *ofdev)
 
 	if (msi->list.prev != NULL)
 		list_del(&msi->list);
-	for (i = 0; i < NR_MSI_REG; i++) {
+	for (i = 0; i < NR_MSI_REG_MAX; i++) {
 		virq = msi->msi_virqs[i];
 		if (virq != NO_IRQ) {
 			cascade_data = irq_get_handler_data(virq);
@@ -339,7 +353,7 @@ static int fsl_msi_setup_hwirq(struct fsl_msi *msi, struct platform_device *dev,
 			       int offset, int irq_index)
 {
 	struct fsl_msi_cascade_data *cascade_data = NULL;
-	int virt_msir;
+	int virt_msir, i;
 
 	virt_msir = irq_of_parse_and_map(dev->dev.of_node, irq_index);
 	if (virt_msir == NO_IRQ) {
@@ -360,6 +374,11 @@ static int fsl_msi_setup_hwirq(struct fsl_msi *msi, struct platform_device *dev,
 	irq_set_handler_data(virt_msir, cascade_data);
 	irq_set_chained_handler(virt_msir, fsl_msi_cascade);
 
+	/* Release the hwirqs corresponding to this MSI register */
+	for (i = 0; i < IRQS_PER_MSI_REG; i++)
+		msi_bitmap_free_hwirqs(&msi->bitmap,
+				       msi_hwirq(msi, offset, i), 1);
+
 	return 0;
 }
 
@@ -368,14 +387,12 @@ static int fsl_of_msi_probe(struct platform_device *dev)
 {
 	const struct of_device_id *match;
 	struct fsl_msi *msi;
-	struct resource res;
+	struct resource res, msiir;
 	int err, i, j, irq_index, count;
-	int rc;
 	const u32 *p;
 	const struct fsl_msi_feature *features;
 	int len;
 	u32 offset;
-	static const u32 all_avail[] = { 0, NR_MSI_IRQS };
 
 	match = of_match_device(fsl_of_msi_ids, &dev->dev);
 	if (!match)
@@ -392,7 +409,7 @@ static int fsl_of_msi_probe(struct platform_device *dev)
 	platform_set_drvdata(dev, msi);
 
 	msi->irqhost = irq_domain_add_linear(dev->dev.of_node,
-				      NR_MSI_IRQS, &fsl_msi_host_ops, msi);
+				      NR_MSI_IRQS_MAX, &fsl_msi_host_ops, msi);
 
 	if (msi->irqhost == NULL) {
 		dev_err(&dev->dev, "No memory for MSI irqhost\n");
@@ -421,6 +438,16 @@ static int fsl_of_msi_probe(struct platform_device *dev)
 		}
 		msi->msiir_offset =
 			features->msiir_offset + (res.start & 0xfffff);
+
+		/*
+		 * First read the MSIIR/MSIIR1 offset from dts
+		 * On failure use the hardcode MSIIR offset
+		 */
+		if (of_address_to_resource(dev->dev.of_node, 1, &msiir))
+			msi->msiir_offset = features->msiir_offset +
+					    (res.start & MSIIR_OFFSET_MASK);
+		else
+			msi->msiir_offset = msiir.start & MSIIR_OFFSET_MASK;
 	}
 
 	msi->feature = features->fsl_pic_ip;
@@ -431,42 +458,66 @@ static int fsl_of_msi_probe(struct platform_device *dev)
 	 */
 	msi->phandle = dev->dev.of_node->phandle;
 
-	rc = fsl_msi_init_allocator(msi);
-	if (rc) {
+	err = fsl_msi_init_allocator(msi);
+	if (err) {
 		dev_err(&dev->dev, "Error allocating MSI bitmap\n");
 		goto error_out;
 	}
 
 	p = of_get_property(dev->dev.of_node, "msi-available-ranges", &len);
-	if (p && len % (2 * sizeof(u32)) != 0) {
-		dev_err(&dev->dev, "%s: Malformed msi-available-ranges property\n",
-			__func__);
-		err = -EINVAL;
-		goto error_out;
-	}
 
-	if (!p) {
-		p = all_avail;
-		len = sizeof(all_avail);
-	}
+	if (of_device_is_compatible(dev->dev.of_node, "fsl,mpic-msi-v4.3")) {
+		msi->srs_shift = MSIIR1_SRS_SHIFT;
+		msi->ibs_shift = MSIIR1_IBS_SHIFT;
+		if (p)
+			dev_warn(&dev->dev, "%s: dose not support msi-available-ranges property\n",
+				__func__);
+
+		for (irq_index = 0; irq_index < NR_MSI_REG_MSIIR1;
+		     irq_index++) {
+			err = fsl_msi_setup_hwirq(msi, dev,
+						  irq_index, irq_index);
+			if (err)
+				goto error_out;
+		}
+	} else {
+		static const u32 all_avail[] =
+			{ 0, NR_MSI_REG_MSIIR * IRQS_PER_MSI_REG };
 
-	for (irq_index = 0, i = 0; i < len / (2 * sizeof(u32)); i++) {
-		if (p[i * 2] % IRQS_PER_MSI_REG ||
-		    p[i * 2 + 1] % IRQS_PER_MSI_REG) {
-			printk(KERN_WARNING "%s: %s: msi available range of %u at %u is not IRQ-aligned\n",
-			       __func__, dev->dev.of_node->full_name,
-			       p[i * 2 + 1], p[i * 2]);
+		msi->srs_shift = MSIIR_SRS_SHIFT;
+		msi->ibs_shift = MSIIR_IBS_SHIFT;
+
+		if (p && len % (2 * sizeof(u32)) != 0) {
+			dev_err(&dev->dev, "%s: Malformed msi-available-ranges property\n",
+				__func__);
 			err = -EINVAL;
 			goto error_out;
 		}
 
-		offset = p[i * 2] / IRQS_PER_MSI_REG;
-		count = p[i * 2 + 1] / IRQS_PER_MSI_REG;
+		if (!p) {
+			p = all_avail;
+			len = sizeof(all_avail);
+		}
 
-		for (j = 0; j < count; j++, irq_index++) {
-			err = fsl_msi_setup_hwirq(msi, dev, offset + j, irq_index);
-			if (err)
+		for (irq_index = 0, i = 0; i < len / (2 * sizeof(u32)); i++) {
+			if (p[i * 2] % IRQS_PER_MSI_REG ||
+			    p[i * 2 + 1] % IRQS_PER_MSI_REG) {
+				pr_warn("%s: %s: msi available range of %u at %u is not IRQ-aligned\n",
+				       __func__, dev->dev.of_node->full_name,
+				       p[i * 2 + 1], p[i * 2]);
+				err = -EINVAL;
 				goto error_out;
+			}
+
+			offset = p[i * 2] / IRQS_PER_MSI_REG;
+			count = p[i * 2 + 1] / IRQS_PER_MSI_REG;
+
+			for (j = 0; j < count; j++, irq_index++) {
+				err = fsl_msi_setup_hwirq(msi, dev, offset + j,
+							  irq_index);
+				if (err)
+					goto error_out;
+			}
 		}
 	}
 
@@ -509,6 +560,10 @@ static const struct of_device_id fsl_of_msi_ids[] = {
 		.data = &mpic_msi_feature,
 	},
 	{
+		.compatible = "fsl,mpic-msi-v4.3",
+		.data = &mpic_msi_feature,
+	},
+	{
 		.compatible = "fsl,ipic-msi",
 		.data = &ipic_msi_feature,
 	},
diff --git a/arch/powerpc/sysdev/fsl_msi.h b/arch/powerpc/sysdev/fsl_msi.h
index 8225f8653f78..df9aa9fe0933 100644
--- a/arch/powerpc/sysdev/fsl_msi.h
+++ b/arch/powerpc/sysdev/fsl_msi.h
@@ -16,9 +16,11 @@
 #include <linux/of.h>
 #include <asm/msi_bitmap.h>
 
-#define NR_MSI_REG		8
+#define NR_MSI_REG_MSIIR	8  /* MSIIR can index 8 MSI registers */
+#define NR_MSI_REG_MSIIR1	16 /* MSIIR1 can index 16 MSI registers */
+#define NR_MSI_REG_MAX		NR_MSI_REG_MSIIR1
 #define IRQS_PER_MSI_REG	32
-#define NR_MSI_IRQS	(NR_MSI_REG * IRQS_PER_MSI_REG)
+#define NR_MSI_IRQS_MAX	(NR_MSI_REG_MAX * IRQS_PER_MSI_REG)
 
 #define FSL_PIC_IP_MASK   0x0000000F
 #define FSL_PIC_IP_MPIC   0x00000001
@@ -31,9 +33,11 @@ struct fsl_msi {
 	unsigned long cascade_irq;
 
 	u32 msiir_offset; /* Offset of MSIIR, relative to start of CCSR */
+	u32 ibs_shift; /* Shift of interrupt bit select */
+	u32 srs_shift; /* Shift of the shared interrupt register select */
 	void __iomem *msi_regs;
 	u32 feature;
-	int msi_virqs[NR_MSI_REG];
+	int msi_virqs[NR_MSI_REG_MAX];
 
 	struct msi_bitmap bitmap;
 
diff --git a/arch/powerpc/sysdev/fsl_pci.c b/arch/powerpc/sysdev/fsl_pci.c
index 46ac1ddea683..ccfb50ddfe38 100644
--- a/arch/powerpc/sysdev/fsl_pci.c
+++ b/arch/powerpc/sysdev/fsl_pci.c
@@ -26,11 +26,15 @@
 #include <linux/memblock.h>
 #include <linux/log2.h>
 #include <linux/slab.h>
+#include <linux/uaccess.h>
 
 #include <asm/io.h>
 #include <asm/prom.h>
 #include <asm/pci-bridge.h>
+#include <asm/ppc-pci.h>
 #include <asm/machdep.h>
+#include <asm/disassemble.h>
+#include <asm/ppc-opcode.h>
 #include <sysdev/fsl_soc.h>
 #include <sysdev/fsl_pci.h>
 
@@ -64,7 +68,7 @@ static int fsl_pcie_check_link(struct pci_controller *hose)
 	if (hose->indirect_type & PPC_INDIRECT_TYPE_FSL_CFG_REG_LINK) {
 		if (hose->ops->read == fsl_indirect_read_config) {
 			struct pci_bus bus;
-			bus.number = 0;
+			bus.number = hose->first_busno;
 			bus.sysdata = hose;
 			bus.ops = hose->ops;
 			indirect_read_config(&bus, 0, PCIE_LTSSM, 4, &val);
@@ -297,10 +301,10 @@ static void setup_pci_atmu(struct pci_controller *hose)
 	if (early_find_capability(hose, 0, 0, PCI_CAP_ID_EXP)) {
 		/* Size window to exact size if power-of-two or one size up */
 		if ((1ull << mem_log) != mem) {
+			mem_log++;
 			if ((1ull << mem_log) > mem)
 				pr_info("%s: Setting PCI inbound window "
 					"greater than memory size\n", name);
-			mem_log++;
 		}
 
 		piwar |= ((mem_log - 1) & PIWAR_SZ_MASK);
@@ -373,7 +377,9 @@ static void setup_pci_atmu(struct pci_controller *hose)
 	}
 
 	if (hose->dma_window_size < mem) {
-#ifndef CONFIG_SWIOTLB
+#ifdef CONFIG_SWIOTLB
+		ppc_swiotlb_enable = 1;
+#else
 		pr_err("%s: ERROR: Memory size exceeds PCI ATMU ability to "
 			"map - enable CONFIG_SWIOTLB to avoid dma errors.\n",
 			 name);
@@ -868,6 +874,160 @@ u64 fsl_pci_immrbar_base(struct pci_controller *hose)
 	return 0;
 }
 
+#ifdef CONFIG_E500
+static int mcheck_handle_load(struct pt_regs *regs, u32 inst)
+{
+	unsigned int rd, ra, rb, d;
+
+	rd = get_rt(inst);
+	ra = get_ra(inst);
+	rb = get_rb(inst);
+	d = get_d(inst);
+
+	switch (get_op(inst)) {
+	case 31:
+		switch (get_xop(inst)) {
+		case OP_31_XOP_LWZX:
+		case OP_31_XOP_LWBRX:
+			regs->gpr[rd] = 0xffffffff;
+			break;
+
+		case OP_31_XOP_LWZUX:
+			regs->gpr[rd] = 0xffffffff;
+			regs->gpr[ra] += regs->gpr[rb];
+			break;
+
+		case OP_31_XOP_LBZX:
+			regs->gpr[rd] = 0xff;
+			break;
+
+		case OP_31_XOP_LBZUX:
+			regs->gpr[rd] = 0xff;
+			regs->gpr[ra] += regs->gpr[rb];
+			break;
+
+		case OP_31_XOP_LHZX:
+		case OP_31_XOP_LHBRX:
+			regs->gpr[rd] = 0xffff;
+			break;
+
+		case OP_31_XOP_LHZUX:
+			regs->gpr[rd] = 0xffff;
+			regs->gpr[ra] += regs->gpr[rb];
+			break;
+
+		case OP_31_XOP_LHAX:
+			regs->gpr[rd] = ~0UL;
+			break;
+
+		case OP_31_XOP_LHAUX:
+			regs->gpr[rd] = ~0UL;
+			regs->gpr[ra] += regs->gpr[rb];
+			break;
+
+		default:
+			return 0;
+		}
+		break;
+
+	case OP_LWZ:
+		regs->gpr[rd] = 0xffffffff;
+		break;
+
+	case OP_LWZU:
+		regs->gpr[rd] = 0xffffffff;
+		regs->gpr[ra] += (s16)d;
+		break;
+
+	case OP_LBZ:
+		regs->gpr[rd] = 0xff;
+		break;
+
+	case OP_LBZU:
+		regs->gpr[rd] = 0xff;
+		regs->gpr[ra] += (s16)d;
+		break;
+
+	case OP_LHZ:
+		regs->gpr[rd] = 0xffff;
+		break;
+
+	case OP_LHZU:
+		regs->gpr[rd] = 0xffff;
+		regs->gpr[ra] += (s16)d;
+		break;
+
+	case OP_LHA:
+		regs->gpr[rd] = ~0UL;
+		break;
+
+	case OP_LHAU:
+		regs->gpr[rd] = ~0UL;
+		regs->gpr[ra] += (s16)d;
+		break;
+
+	default:
+		return 0;
+	}
+
+	return 1;
+}
+
+static int is_in_pci_mem_space(phys_addr_t addr)
+{
+	struct pci_controller *hose;
+	struct resource *res;
+	int i;
+
+	list_for_each_entry(hose, &hose_list, list_node) {
+		if (!(hose->indirect_type & PPC_INDIRECT_TYPE_EXT_REG))
+			continue;
+
+		for (i = 0; i < 3; i++) {
+			res = &hose->mem_resources[i];
+			if ((res->flags & IORESOURCE_MEM) &&
+				addr >= res->start && addr <= res->end)
+				return 1;
+		}
+	}
+	return 0;
+}
+
+int fsl_pci_mcheck_exception(struct pt_regs *regs)
+{
+	u32 inst;
+	int ret;
+	phys_addr_t addr = 0;
+
+	/* Let KVM/QEMU deal with the exception */
+	if (regs->msr & MSR_GS)
+		return 0;
+
+#ifdef CONFIG_PHYS_64BIT
+	addr = mfspr(SPRN_MCARU);
+	addr <<= 32;
+#endif
+	addr += mfspr(SPRN_MCAR);
+
+	if (is_in_pci_mem_space(addr)) {
+		if (user_mode(regs)) {
+			pagefault_disable();
+			ret = get_user(regs->nip, &inst);
+			pagefault_enable();
+		} else {
+			ret = probe_kernel_address(regs->nip, inst);
+		}
+
+		if (mcheck_handle_load(regs, inst)) {
+			regs->nip += 4;
+			return 1;
+		}
+	}
+
+	return 0;
+}
+#endif
+
 #if defined(CONFIG_FSL_SOC_BOOKE) || defined(CONFIG_PPC_86xx)
 static const struct of_device_id pci_ids[] = {
 	{ .compatible = "fsl,mpc8540-pci", },
@@ -928,28 +1088,10 @@ static int fsl_pci_probe(struct platform_device *pdev)
 {
 	int ret;
 	struct device_node *node;
-#ifdef CONFIG_SWIOTLB
-	struct pci_controller *hose;
-#endif
 
 	node = pdev->dev.of_node;
 	ret = fsl_add_bridge(pdev, fsl_pci_primary == node);
 
-#ifdef CONFIG_SWIOTLB
-	if (ret == 0) {
-		hose = pci_find_hose_for_OF_device(pdev->dev.of_node);
-
-		/*
-		 * if we couldn't map all of DRAM via the dma windows
-		 * we need SWIOTLB to handle buffers located outside of
-		 * dma capable memory region
-		 */
-		if (memblock_end_of_DRAM() - 1 > hose->dma_window_base_cur +
-				hose->dma_window_size)
-			ppc_swiotlb_enable = 1;
-	}
-#endif
-
 	mpc85xx_pci_err_probe(pdev);
 
 	return 0;
diff --git a/arch/powerpc/sysdev/fsl_pci.h b/arch/powerpc/sysdev/fsl_pci.h
index 72b5625330e2..8d455df58471 100644
--- a/arch/powerpc/sysdev/fsl_pci.h
+++ b/arch/powerpc/sysdev/fsl_pci.h
@@ -16,6 +16,11 @@
 
 struct platform_device;
 
+
+/* FSL PCI controller BRR1 register */
+#define PCI_FSL_BRR1      0xbf8
+#define PCI_FSL_BRR1_VER 0xffff
+
 #define PCIE_LTSSM	0x0404		/* PCIE Link Training and Status */
 #define PCIE_LTSSM_L0	0x16		/* L0 state */
 #define PCIE_IP_REV_2_2		0x02080202 /* PCIE IP block version Rev2.2 */
@@ -126,5 +131,11 @@ static inline int mpc85xx_pci_err_probe(struct platform_device *op)
 }
 #endif
 
+#ifdef CONFIG_FSL_PCI
+extern int fsl_pci_mcheck_exception(struct pt_regs *);
+#else
+static inline int fsl_pci_mcheck_exception(struct pt_regs *regs) {return 0; }
+#endif
+
 #endif /* __POWERPC_FSL_PCI_H */
 #endif /* __KERNEL__ */
diff --git a/arch/powerpc/sysdev/rtc_cmos_setup.c b/arch/powerpc/sysdev/rtc_cmos_setup.c
index af79e1ea74b6..af0f9beddca9 100644
--- a/arch/powerpc/sysdev/rtc_cmos_setup.c
+++ b/arch/powerpc/sysdev/rtc_cmos_setup.c
@@ -62,7 +62,7 @@ static int  __init add_rtc(void)
 	pd = platform_device_register_simple("rtc_cmos", -1,
 					     &res[0], num_res);
 
-	return PTR_RET(pd);
+	return PTR_ERR_OR_ZERO(pd);
 }
 fs_initcall(add_rtc);
 
diff --git a/arch/powerpc/sysdev/xics/icp-native.c b/arch/powerpc/sysdev/xics/icp-native.c
index 7cd728b3b5e4..9dee47071af8 100644
--- a/arch/powerpc/sysdev/xics/icp-native.c
+++ b/arch/powerpc/sysdev/xics/icp-native.c
@@ -216,7 +216,7 @@ static int __init icp_native_init_one_node(struct device_node *np,
 					   unsigned int *indx)
 {
 	unsigned int ilen;
-	const u32 *ireg;
+	const __be32 *ireg;
 	int i;
 	int reg_tuple_size;
 	int num_servers = 0;
diff --git a/arch/powerpc/sysdev/xics/xics-common.c b/arch/powerpc/sysdev/xics/xics-common.c
index 9049d9f44485..fe0cca477164 100644
--- a/arch/powerpc/sysdev/xics/xics-common.c
+++ b/arch/powerpc/sysdev/xics/xics-common.c
@@ -49,7 +49,7 @@ void xics_update_irq_servers(void)
 	int i, j;
 	struct device_node *np;
 	u32 ilen;
-	const u32 *ireg;
+	const __be32 *ireg;
 	u32 hcpuid;
 
 	/* Find the server numbers for the boot cpu. */
@@ -75,8 +75,8 @@ void xics_update_irq_servers(void)
 	 * default distribution server
 	 */
 	for (j = 0; j < i; j += 2) {
-		if (ireg[j] == hcpuid) {
-			xics_default_distrib_server = ireg[j+1];
+		if (be32_to_cpu(ireg[j]) == hcpuid) {
+			xics_default_distrib_server = be32_to_cpu(ireg[j+1]);
 			break;
 		}
 	}
@@ -383,7 +383,7 @@ void __init xics_register_ics(struct ics *ics)
 static void __init xics_get_server_size(void)
 {
 	struct device_node *np;
-	const u32 *isize;
+	const __be32 *isize;
 
 	/* We fetch the interrupt server size from the first ICS node
 	 * we find if any
@@ -394,7 +394,7 @@ static void __init xics_get_server_size(void)
 	isize = of_get_property(np, "ibm,interrupt-server#-size", NULL);
 	if (!isize)
 		return;
-	xics_interrupt_server_size = *isize;
+	xics_interrupt_server_size = be32_to_cpu(*isize);
 	of_node_put(np);
 }
 
diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
index 96bf5bd30fbc..af9d3469fb99 100644
--- a/arch/powerpc/xmon/xmon.c
+++ b/arch/powerpc/xmon/xmon.c
@@ -972,27 +972,27 @@ static void bootcmds(void)
 static int cpu_cmd(void)
 {
 #ifdef CONFIG_SMP
-	unsigned long cpu;
+	unsigned long cpu, first_cpu, last_cpu;
 	int timeout;
-	int count;
 
 	if (!scanhex(&cpu)) {
 		/* print cpus waiting or in xmon */
 		printf("cpus stopped:");
-		count = 0;
+		last_cpu = first_cpu = NR_CPUS;
 		for_each_possible_cpu(cpu) {
 			if (cpumask_test_cpu(cpu, &cpus_in_xmon)) {
-				if (count == 0)
-					printf(" %x", cpu);
-				++count;
-			} else {
-				if (count > 1)
-					printf("-%x", cpu - 1);
-				count = 0;
+				if (cpu == last_cpu + 1) {
+					last_cpu = cpu;
+				} else {
+					if (last_cpu != first_cpu)
+						printf("-%lx", last_cpu);
+					last_cpu = first_cpu = cpu;
+					printf(" %lx", cpu);
+				}
 			}
 		}
-		if (count > 1)
-			printf("-%x", NR_CPUS - 1);
+		if (last_cpu != first_cpu)
+			printf("-%lx", last_cpu);
 		printf("\n");
 		return 0;
 	}
@@ -1256,11 +1256,18 @@ const char *getvecname(unsigned long vec)
 	case 0x700:	ret = "(Program Check)"; break;
 	case 0x800:	ret = "(FPU Unavailable)"; break;
 	case 0x900:	ret = "(Decrementer)"; break;
+	case 0x980:	ret = "(Hypervisor Decrementer)"; break;
+	case 0xa00:	ret = "(Doorbell)"; break;
 	case 0xc00:	ret = "(System Call)"; break;
 	case 0xd00:	ret = "(Single Step)"; break;
+	case 0xe40:	ret = "(Emulation Assist)"; break;
+	case 0xe60:	ret = "(HMI)"; break;
+	case 0xe80:	ret = "(Hypervisor Doorbell)"; break;
 	case 0xf00:	ret = "(Performance Monitor)"; break;
 	case 0xf20:	ret = "(Altivec Unavailable)"; break;
 	case 0x1300:	ret = "(Instruction Breakpoint)"; break;
+	case 0x1500:	ret = "(Denormalisation)"; break;
+	case 0x1700:	ret = "(Altivec Assist)"; break;
 	default: ret = "";
 	}
 	return ret;
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 8a4cae78f03c..7143793859fa 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -62,6 +62,7 @@ config S390
 	def_bool y
 	select ARCH_DISCARD_MEMBLOCK
 	select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
+	select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG
 	select ARCH_INLINE_READ_LOCK
 	select ARCH_INLINE_READ_LOCK_BH
@@ -91,8 +92,8 @@ config S390
 	select ARCH_INLINE_WRITE_UNLOCK_BH
 	select ARCH_INLINE_WRITE_UNLOCK_IRQ
 	select ARCH_INLINE_WRITE_UNLOCK_IRQRESTORE
-	select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS
 	select ARCH_SAVE_PAGE_KEYS if HIBERNATION
+	select ARCH_USE_CMPXCHG_LOCKREF
 	select ARCH_WANT_IPC_PARSE_VERSION
 	select BUILDTIME_EXTABLE_SORT
 	select CLONE_BACKWARDS2
@@ -102,7 +103,6 @@ config S390
 	select GENERIC_TIME_VSYSCALL_OLD
 	select HAVE_ALIGNED_STRUCT_PAGE if SLUB
 	select HAVE_ARCH_JUMP_LABEL if !MARCH_G5
-	select HAVE_ARCH_MUTEX_CPU_RELAX
 	select HAVE_ARCH_SECCOMP_FILTER
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_ARCH_TRANSPARENT_HUGEPAGE if 64BIT
@@ -134,15 +134,15 @@ config S390
 	select HAVE_SYSCALL_TRACEPOINTS
 	select HAVE_UID16 if 32BIT
 	select HAVE_VIRT_CPU_ACCOUNTING
-	select VIRT_TO_BUS
 	select INIT_ALL_POSSIBLE
 	select KTIME_SCALAR if 32BIT
 	select MODULES_USE_ELF_RELA
-	select OLD_SIGSUSPEND3
 	select OLD_SIGACTION
+	select OLD_SIGSUSPEND3
 	select SYSCTL_EXCEPTION_TRACE
 	select USE_GENERIC_SMP_HELPERS if SMP
 	select VIRT_CPU_ACCOUNTING
+	select VIRT_TO_BUS
 
 config SCHED_OMIT_FRAME_POINTER
 	def_bool y
@@ -430,7 +430,6 @@ menuconfig PCI
 	bool "PCI support"
 	default n
 	depends on 64BIT
-	select ARCH_SUPPORTS_MSI
 	select PCI_MSI
 	help
 	  Enable PCI support.
@@ -445,6 +444,16 @@ config PCI_NR_FUNCTIONS
 	  This allows you to specify the maximum number of PCI functions which
 	  this kernel will support.
 
+config PCI_NR_MSI
+	int "Maximum number of MSI interrupts (64-32768)"
+	range 64 32768
+	default "256"
+	help
+	  This defines the number of virtual interrupts the kernel will
+	  provide for MSI interrupts. If you configure your system to have
+	  too few drivers will fail to allocate MSI interrupts for all
+	  PCI devices.
+
 source "drivers/pci/Kconfig"
 source "drivers/pci/pcie/Kconfig"
 source "drivers/pci/hotplug/Kconfig"
@@ -516,6 +525,7 @@ config CRASH_DUMP
 	bool "kernel crash dumps"
 	depends on 64BIT && SMP
 	select KEXEC
+	select ZFCPDUMP
 	help
 	  Generate crash dump after being started by kexec.
 	  Crash dump kernels are loaded in the main kernel with kexec-tools
@@ -526,7 +536,7 @@ config CRASH_DUMP
 config ZFCPDUMP
 	def_bool n
 	prompt "zfcpdump support"
-	select SMP
+	depends on SMP
 	help
 	  Select this option if you want to build an zfcpdump enabled kernel.
 	  Refer to <file:Documentation/s390/zfcpdump.txt> for more details on this.
diff --git a/arch/s390/defconfig b/arch/s390/defconfig
index b74400e3e035..d204c65bf722 100644
--- a/arch/s390/defconfig
+++ b/arch/s390/defconfig
@@ -1,14 +1,13 @@
-CONFIG_EXPERIMENTAL=y
 CONFIG_SYSVIPC=y
 CONFIG_POSIX_MQUEUE=y
 CONFIG_FHANDLE=y
+CONFIG_AUDIT=y
+CONFIG_NO_HZ=y
+CONFIG_HIGH_RES_TIMERS=y
 CONFIG_TASKSTATS=y
 CONFIG_TASK_DELAY_ACCT=y
 CONFIG_TASK_XACCT=y
 CONFIG_TASK_IO_ACCOUNTING=y
-CONFIG_AUDIT=y
-CONFIG_NO_HZ=y
-CONFIG_HIGH_RES_TIMERS=y
 CONFIG_RCU_FAST_NO_HZ=y
 CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
@@ -27,6 +26,7 @@ CONFIG_RD_BZIP2=y
 CONFIG_RD_LZMA=y
 CONFIG_RD_XZ=y
 CONFIG_RD_LZO=y
+CONFIG_RD_LZ4=y
 CONFIG_EXPERT=y
 # CONFIG_COMPAT_BRK is not set
 CONFIG_PROFILING=y
@@ -38,11 +38,13 @@ CONFIG_MODULE_UNLOAD=y
 CONFIG_MODVERSIONS=y
 CONFIG_PARTITION_ADVANCED=y
 CONFIG_IBM_PARTITION=y
+# CONFIG_EFI_PARTITION is not set
 CONFIG_DEFAULT_DEADLINE=y
 CONFIG_HZ_100=y
 CONFIG_MEMORY_HOTPLUG=y
 CONFIG_MEMORY_HOTREMOVE=y
 CONFIG_KSM=y
+CONFIG_TRANSPARENT_HUGEPAGE=y
 CONFIG_CRASH_DUMP=y
 CONFIG_BINFMT_MISC=m
 CONFIG_HIBERNATION=y
@@ -92,40 +94,49 @@ CONFIG_SCSI_CONSTANTS=y
 CONFIG_SCSI_LOGGING=y
 CONFIG_SCSI_SCAN_ASYNC=y
 CONFIG_ZFCP=y
+CONFIG_SCSI_VIRTIO=y
 CONFIG_NETDEVICES=y
 CONFIG_BONDING=m
 CONFIG_DUMMY=m
 CONFIG_EQUALIZER=m
 CONFIG_TUN=m
 CONFIG_VIRTIO_NET=y
+# CONFIG_INPUT is not set
+# CONFIG_SERIO is not set
 CONFIG_RAW_DRIVER=m
 CONFIG_VIRTIO_BALLOON=y
-CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 CONFIG_EXT4_FS=y
 CONFIG_EXT4_FS_POSIX_ACL=y
 CONFIG_EXT4_FS_SECURITY=y
+CONFIG_XFS_FS=y
+CONFIG_XFS_QUOTA=y
+CONFIG_XFS_POSIX_ACL=y
+CONFIG_XFS_RT=y
+CONFIG_BTRFS_FS=y
+CONFIG_BTRFS_FS_POSIX_ACL=y
+CONFIG_FANOTIFY=y
+CONFIG_FUSE_FS=y
 CONFIG_PROC_KCORE=y
 CONFIG_TMPFS=y
 CONFIG_TMPFS_POSIX_ACL=y
+CONFIG_HUGETLBFS=y
 # CONFIG_NETWORK_FILESYSTEMS is not set
+CONFIG_DEBUG_FORCE_WEAK_PER_CPU=y
 CONFIG_MAGIC_SYSRQ=y
+CONFIG_DEBUG_PAGEALLOC=y
 CONFIG_TIMER_STATS=y
 CONFIG_PROVE_LOCKING=y
-CONFIG_PROVE_RCU=y
 CONFIG_LOCK_STAT=y
 CONFIG_DEBUG_LOCKDEP=y
 CONFIG_DEBUG_LIST=y
 CONFIG_DEBUG_NOTIFIERS=y
+CONFIG_PROVE_RCU=y
+CONFIG_RCU_CPU_STALL_TIMEOUT=60
 CONFIG_RCU_TRACE=y
-CONFIG_KPROBES_SANITY_TEST=y
-CONFIG_DEBUG_FORCE_WEAK_PER_CPU=y
 CONFIG_LATENCYTOP=y
-CONFIG_DEBUG_PAGEALLOC=y
 CONFIG_BLK_DEV_IO_TRACE=y
+CONFIG_KPROBES_SANITY_TEST=y
 # CONFIG_STRICT_DEVMEM is not set
-CONFIG_CRYPTO_NULL=m
 CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_AUTHENC=m
 CONFIG_CRYPTO_TEST=m
@@ -137,8 +148,10 @@ CONFIG_CRYPTO_ECB=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_XTS=m
+CONFIG_CRYPTO_CMAC=m
 CONFIG_CRYPTO_XCBC=m
 CONFIG_CRYPTO_VMAC=m
+CONFIG_CRYPTO_CRC32=m
 CONFIG_CRYPTO_MD4=m
 CONFIG_CRYPTO_MICHAEL_MIC=m
 CONFIG_CRYPTO_RMD128=m
@@ -165,6 +178,8 @@ CONFIG_CRYPTO_TWOFISH=m
 CONFIG_CRYPTO_DEFLATE=m
 CONFIG_CRYPTO_ZLIB=m
 CONFIG_CRYPTO_LZO=m
+CONFIG_CRYPTO_LZ4=m
+CONFIG_CRYPTO_LZ4HC=m
 CONFIG_ZCRYPT=m
 CONFIG_CRYPTO_SHA1_S390=m
 CONFIG_CRYPTO_SHA256_S390=m
diff --git a/arch/s390/hypfs/hypfs.h b/arch/s390/hypfs/hypfs.h
index f41e0ef7fdf9..79f2ac55253f 100644
--- a/arch/s390/hypfs/hypfs.h
+++ b/arch/s390/hypfs/hypfs.h
@@ -18,26 +18,23 @@
 #define UPDATE_FILE_MODE 0220
 #define DIR_MODE         0550
 
-extern struct dentry *hypfs_mkdir(struct super_block *sb, struct dentry *parent,
-				  const char *name);
+extern struct dentry *hypfs_mkdir(struct dentry *parent, const char *name);
 
-extern struct dentry *hypfs_create_u64(struct super_block *sb,
-				       struct dentry *dir, const char *name,
+extern struct dentry *hypfs_create_u64(struct dentry *dir, const char *name,
 				       __u64 value);
 
-extern struct dentry *hypfs_create_str(struct super_block *sb,
-				       struct dentry *dir, const char *name,
+extern struct dentry *hypfs_create_str(struct dentry *dir, const char *name,
 				       char *string);
 
 /* LPAR Hypervisor */
 extern int hypfs_diag_init(void);
 extern void hypfs_diag_exit(void);
-extern int hypfs_diag_create_files(struct super_block *sb, struct dentry *root);
+extern int hypfs_diag_create_files(struct dentry *root);
 
 /* VM Hypervisor */
 extern int hypfs_vm_init(void);
 extern void hypfs_vm_exit(void);
-extern int hypfs_vm_create_files(struct super_block *sb, struct dentry *root);
+extern int hypfs_vm_create_files(struct dentry *root);
 
 /* debugfs interface */
 struct hypfs_dbfs_file;
diff --git a/arch/s390/hypfs/hypfs_dbfs.c b/arch/s390/hypfs/hypfs_dbfs.c
index bb5dd496614f..17ab8b7b53cc 100644
--- a/arch/s390/hypfs/hypfs_dbfs.c
+++ b/arch/s390/hypfs/hypfs_dbfs.c
@@ -105,7 +105,7 @@ void hypfs_dbfs_remove_file(struct hypfs_dbfs_file *df)
 int hypfs_dbfs_init(void)
 {
 	dbfs_dir = debugfs_create_dir("s390_hypfs", NULL);
-	return PTR_RET(dbfs_dir);
+	return PTR_ERR_OR_ZERO(dbfs_dir);
 }
 
 void hypfs_dbfs_exit(void)
diff --git a/arch/s390/hypfs/hypfs_diag.c b/arch/s390/hypfs/hypfs_diag.c
index 138893e5f736..5eeffeefae06 100644
--- a/arch/s390/hypfs/hypfs_diag.c
+++ b/arch/s390/hypfs/hypfs_diag.c
@@ -623,8 +623,7 @@ void hypfs_diag_exit(void)
  * *******************************************
  */
 
-static int hypfs_create_cpu_files(struct super_block *sb,
-				  struct dentry *cpus_dir, void *cpu_info)
+static int hypfs_create_cpu_files(struct dentry *cpus_dir, void *cpu_info)
 {
 	struct dentry *cpu_dir;
 	char buffer[TMP_SIZE];
@@ -632,30 +631,29 @@ static int hypfs_create_cpu_files(struct super_block *sb,
 
 	snprintf(buffer, TMP_SIZE, "%d", cpu_info__cpu_addr(diag204_info_type,
 							    cpu_info));
-	cpu_dir = hypfs_mkdir(sb, cpus_dir, buffer);
-	rc = hypfs_create_u64(sb, cpu_dir, "mgmtime",
+	cpu_dir = hypfs_mkdir(cpus_dir, buffer);
+	rc = hypfs_create_u64(cpu_dir, "mgmtime",
 			      cpu_info__acc_time(diag204_info_type, cpu_info) -
 			      cpu_info__lp_time(diag204_info_type, cpu_info));
 	if (IS_ERR(rc))
 		return PTR_ERR(rc);
-	rc = hypfs_create_u64(sb, cpu_dir, "cputime",
+	rc = hypfs_create_u64(cpu_dir, "cputime",
 			      cpu_info__lp_time(diag204_info_type, cpu_info));
 	if (IS_ERR(rc))
 		return PTR_ERR(rc);
 	if (diag204_info_type == INFO_EXT) {
-		rc = hypfs_create_u64(sb, cpu_dir, "onlinetime",
+		rc = hypfs_create_u64(cpu_dir, "onlinetime",
 				      cpu_info__online_time(diag204_info_type,
 							    cpu_info));
 		if (IS_ERR(rc))
 			return PTR_ERR(rc);
 	}
 	diag224_idx2name(cpu_info__ctidx(diag204_info_type, cpu_info), buffer);
-	rc = hypfs_create_str(sb, cpu_dir, "type", buffer);
+	rc = hypfs_create_str(cpu_dir, "type", buffer);
 	return PTR_RET(rc);
 }
 
-static void *hypfs_create_lpar_files(struct super_block *sb,
-				     struct dentry *systems_dir, void *part_hdr)
+static void *hypfs_create_lpar_files(struct dentry *systems_dir, void *part_hdr)
 {
 	struct dentry *cpus_dir;
 	struct dentry *lpar_dir;
@@ -665,16 +663,16 @@ static void *hypfs_create_lpar_files(struct super_block *sb,
 
 	part_hdr__part_name(diag204_info_type, part_hdr, lpar_name);
 	lpar_name[LPAR_NAME_LEN] = 0;
-	lpar_dir = hypfs_mkdir(sb, systems_dir, lpar_name);
+	lpar_dir = hypfs_mkdir(systems_dir, lpar_name);
 	if (IS_ERR(lpar_dir))
 		return lpar_dir;
-	cpus_dir = hypfs_mkdir(sb, lpar_dir, "cpus");
+	cpus_dir = hypfs_mkdir(lpar_dir, "cpus");
 	if (IS_ERR(cpus_dir))
 		return cpus_dir;
 	cpu_info = part_hdr + part_hdr__size(diag204_info_type);
 	for (i = 0; i < part_hdr__rcpus(diag204_info_type, part_hdr); i++) {
 		int rc;
-		rc = hypfs_create_cpu_files(sb, cpus_dir, cpu_info);
+		rc = hypfs_create_cpu_files(cpus_dir, cpu_info);
 		if (rc)
 			return ERR_PTR(rc);
 		cpu_info += cpu_info__size(diag204_info_type);
@@ -682,8 +680,7 @@ static void *hypfs_create_lpar_files(struct super_block *sb,
 	return cpu_info;
 }
 
-static int hypfs_create_phys_cpu_files(struct super_block *sb,
-				       struct dentry *cpus_dir, void *cpu_info)
+static int hypfs_create_phys_cpu_files(struct dentry *cpus_dir, void *cpu_info)
 {
 	struct dentry *cpu_dir;
 	char buffer[TMP_SIZE];
@@ -691,32 +688,31 @@ static int hypfs_create_phys_cpu_files(struct super_block *sb,
 
 	snprintf(buffer, TMP_SIZE, "%i", phys_cpu__cpu_addr(diag204_info_type,
 							    cpu_info));
-	cpu_dir = hypfs_mkdir(sb, cpus_dir, buffer);
+	cpu_dir = hypfs_mkdir(cpus_dir, buffer);
 	if (IS_ERR(cpu_dir))
 		return PTR_ERR(cpu_dir);
-	rc = hypfs_create_u64(sb, cpu_dir, "mgmtime",
+	rc = hypfs_create_u64(cpu_dir, "mgmtime",
 			      phys_cpu__mgm_time(diag204_info_type, cpu_info));
 	if (IS_ERR(rc))
 		return PTR_ERR(rc);
 	diag224_idx2name(phys_cpu__ctidx(diag204_info_type, cpu_info), buffer);
-	rc = hypfs_create_str(sb, cpu_dir, "type", buffer);
+	rc = hypfs_create_str(cpu_dir, "type", buffer);
 	return PTR_RET(rc);
 }
 
-static void *hypfs_create_phys_files(struct super_block *sb,
-				     struct dentry *parent_dir, void *phys_hdr)
+static void *hypfs_create_phys_files(struct dentry *parent_dir, void *phys_hdr)
 {
 	int i;
 	void *cpu_info;
 	struct dentry *cpus_dir;
 
-	cpus_dir = hypfs_mkdir(sb, parent_dir, "cpus");
+	cpus_dir = hypfs_mkdir(parent_dir, "cpus");
 	if (IS_ERR(cpus_dir))
 		return cpus_dir;
 	cpu_info = phys_hdr + phys_hdr__size(diag204_info_type);
 	for (i = 0; i < phys_hdr__cpus(diag204_info_type, phys_hdr); i++) {
 		int rc;
-		rc = hypfs_create_phys_cpu_files(sb, cpus_dir, cpu_info);
+		rc = hypfs_create_phys_cpu_files(cpus_dir, cpu_info);
 		if (rc)
 			return ERR_PTR(rc);
 		cpu_info += phys_cpu__size(diag204_info_type);
@@ -724,7 +720,7 @@ static void *hypfs_create_phys_files(struct super_block *sb,
 	return cpu_info;
 }
 
-int hypfs_diag_create_files(struct super_block *sb, struct dentry *root)
+int hypfs_diag_create_files(struct dentry *root)
 {
 	struct dentry *systems_dir, *hyp_dir;
 	void *time_hdr, *part_hdr;
@@ -735,7 +731,7 @@ int hypfs_diag_create_files(struct super_block *sb, struct dentry *root)
 	if (IS_ERR(buffer))
 		return PTR_ERR(buffer);
 
-	systems_dir = hypfs_mkdir(sb, root, "systems");
+	systems_dir = hypfs_mkdir(root, "systems");
 	if (IS_ERR(systems_dir)) {
 		rc = PTR_ERR(systems_dir);
 		goto err_out;
@@ -743,25 +739,25 @@ int hypfs_diag_create_files(struct super_block *sb, struct dentry *root)
 	time_hdr = (struct x_info_blk_hdr *)buffer;
 	part_hdr = time_hdr + info_blk_hdr__size(diag204_info_type);
 	for (i = 0; i < info_blk_hdr__npar(diag204_info_type, time_hdr); i++) {
-		part_hdr = hypfs_create_lpar_files(sb, systems_dir, part_hdr);
+		part_hdr = hypfs_create_lpar_files(systems_dir, part_hdr);
 		if (IS_ERR(part_hdr)) {
 			rc = PTR_ERR(part_hdr);
 			goto err_out;
 		}
 	}
 	if (info_blk_hdr__flags(diag204_info_type, time_hdr) & LPAR_PHYS_FLG) {
-		ptr = hypfs_create_phys_files(sb, root, part_hdr);
+		ptr = hypfs_create_phys_files(root, part_hdr);
 		if (IS_ERR(ptr)) {
 			rc = PTR_ERR(ptr);
 			goto err_out;
 		}
 	}
-	hyp_dir = hypfs_mkdir(sb, root, "hyp");
+	hyp_dir = hypfs_mkdir(root, "hyp");
 	if (IS_ERR(hyp_dir)) {
 		rc = PTR_ERR(hyp_dir);
 		goto err_out;
 	}
-	ptr = hypfs_create_str(sb, hyp_dir, "type", "LPAR Hypervisor");
+	ptr = hypfs_create_str(hyp_dir, "type", "LPAR Hypervisor");
 	if (IS_ERR(ptr)) {
 		rc = PTR_ERR(ptr);
 		goto err_out;
diff --git a/arch/s390/hypfs/hypfs_vm.c b/arch/s390/hypfs/hypfs_vm.c
index f364dcf77e8e..24908ce149f1 100644
--- a/arch/s390/hypfs/hypfs_vm.c
+++ b/arch/s390/hypfs/hypfs_vm.c
@@ -107,16 +107,15 @@ static void diag2fc_free(const void *data)
 	vfree(data);
 }
 
-#define ATTRIBUTE(sb, dir, name, member) \
+#define ATTRIBUTE(dir, name, member) \
 do { \
 	void *rc; \
-	rc = hypfs_create_u64(sb, dir, name, member); \
+	rc = hypfs_create_u64(dir, name, member); \
 	if (IS_ERR(rc)) \
 		return PTR_ERR(rc); \
 } while(0)
 
-static int hpyfs_vm_create_guest(struct super_block *sb,
-				 struct dentry *systems_dir,
+static int hpyfs_vm_create_guest(struct dentry *systems_dir,
 				 struct diag2fc_data *data)
 {
 	char guest_name[NAME_LEN + 1] = {};
@@ -130,46 +129,46 @@ static int hpyfs_vm_create_guest(struct super_block *sb,
 	memcpy(guest_name, data->guest_name, NAME_LEN);
 	EBCASC(guest_name, NAME_LEN);
 	strim(guest_name);
-	guest_dir = hypfs_mkdir(sb, systems_dir, guest_name);
+	guest_dir = hypfs_mkdir(systems_dir, guest_name);
 	if (IS_ERR(guest_dir))
 		return PTR_ERR(guest_dir);
-	ATTRIBUTE(sb, guest_dir, "onlinetime_us", data->el_time);
+	ATTRIBUTE(guest_dir, "onlinetime_us", data->el_time);
 
 	/* logical cpu information */
-	cpus_dir = hypfs_mkdir(sb, guest_dir, "cpus");
+	cpus_dir = hypfs_mkdir(guest_dir, "cpus");
 	if (IS_ERR(cpus_dir))
 		return PTR_ERR(cpus_dir);
-	ATTRIBUTE(sb, cpus_dir, "cputime_us", data->used_cpu);
-	ATTRIBUTE(sb, cpus_dir, "capped", capped_value);
-	ATTRIBUTE(sb, cpus_dir, "dedicated", dedicated_flag);
-	ATTRIBUTE(sb, cpus_dir, "count", data->vcpus);
-	ATTRIBUTE(sb, cpus_dir, "weight_min", data->cpu_min);
-	ATTRIBUTE(sb, cpus_dir, "weight_max", data->cpu_max);
-	ATTRIBUTE(sb, cpus_dir, "weight_cur", data->cpu_shares);
+	ATTRIBUTE(cpus_dir, "cputime_us", data->used_cpu);
+	ATTRIBUTE(cpus_dir, "capped", capped_value);
+	ATTRIBUTE(cpus_dir, "dedicated", dedicated_flag);
+	ATTRIBUTE(cpus_dir, "count", data->vcpus);
+	ATTRIBUTE(cpus_dir, "weight_min", data->cpu_min);
+	ATTRIBUTE(cpus_dir, "weight_max", data->cpu_max);
+	ATTRIBUTE(cpus_dir, "weight_cur", data->cpu_shares);
 
 	/* memory information */
-	mem_dir = hypfs_mkdir(sb, guest_dir, "mem");
+	mem_dir = hypfs_mkdir(guest_dir, "mem");
 	if (IS_ERR(mem_dir))
 		return PTR_ERR(mem_dir);
-	ATTRIBUTE(sb, mem_dir, "min_KiB", data->mem_min_kb);
-	ATTRIBUTE(sb, mem_dir, "max_KiB", data->mem_max_kb);
-	ATTRIBUTE(sb, mem_dir, "used_KiB", data->mem_used_kb);
-	ATTRIBUTE(sb, mem_dir, "share_KiB", data->mem_share_kb);
+	ATTRIBUTE(mem_dir, "min_KiB", data->mem_min_kb);
+	ATTRIBUTE(mem_dir, "max_KiB", data->mem_max_kb);
+	ATTRIBUTE(mem_dir, "used_KiB", data->mem_used_kb);
+	ATTRIBUTE(mem_dir, "share_KiB", data->mem_share_kb);
 
 	/* samples */
-	samples_dir = hypfs_mkdir(sb, guest_dir, "samples");
+	samples_dir = hypfs_mkdir(guest_dir, "samples");
 	if (IS_ERR(samples_dir))
 		return PTR_ERR(samples_dir);
-	ATTRIBUTE(sb, samples_dir, "cpu_using", data->cpu_use_samp);
-	ATTRIBUTE(sb, samples_dir, "cpu_delay", data->cpu_delay_samp);
-	ATTRIBUTE(sb, samples_dir, "mem_delay", data->page_wait_samp);
-	ATTRIBUTE(sb, samples_dir, "idle", data->idle_samp);
-	ATTRIBUTE(sb, samples_dir, "other", data->other_samp);
-	ATTRIBUTE(sb, samples_dir, "total", data->total_samp);
+	ATTRIBUTE(samples_dir, "cpu_using", data->cpu_use_samp);
+	ATTRIBUTE(samples_dir, "cpu_delay", data->cpu_delay_samp);
+	ATTRIBUTE(samples_dir, "mem_delay", data->page_wait_samp);
+	ATTRIBUTE(samples_dir, "idle", data->idle_samp);
+	ATTRIBUTE(samples_dir, "other", data->other_samp);
+	ATTRIBUTE(samples_dir, "total", data->total_samp);
 	return 0;
 }
 
-int hypfs_vm_create_files(struct super_block *sb, struct dentry *root)
+int hypfs_vm_create_files(struct dentry *root)
 {
 	struct dentry *dir, *file;
 	struct diag2fc_data *data;
@@ -181,38 +180,38 @@ int hypfs_vm_create_files(struct super_block *sb, struct dentry *root)
 		return PTR_ERR(data);
 
 	/* Hpervisor Info */
-	dir = hypfs_mkdir(sb, root, "hyp");
+	dir = hypfs_mkdir(root, "hyp");
 	if (IS_ERR(dir)) {
 		rc = PTR_ERR(dir);
 		goto failed;
 	}
-	file = hypfs_create_str(sb, dir, "type", "z/VM Hypervisor");
+	file = hypfs_create_str(dir, "type", "z/VM Hypervisor");
 	if (IS_ERR(file)) {
 		rc = PTR_ERR(file);
 		goto failed;
 	}
 
 	/* physical cpus */
-	dir = hypfs_mkdir(sb, root, "cpus");
+	dir = hypfs_mkdir(root, "cpus");
 	if (IS_ERR(dir)) {
 		rc = PTR_ERR(dir);
 		goto failed;
 	}
-	file = hypfs_create_u64(sb, dir, "count", data->lcpus);
+	file = hypfs_create_u64(dir, "count", data->lcpus);
 	if (IS_ERR(file)) {
 		rc = PTR_ERR(file);
 		goto failed;
 	}
 
 	/* guests */
-	dir = hypfs_mkdir(sb, root, "systems");
+	dir = hypfs_mkdir(root, "systems");
 	if (IS_ERR(dir)) {
 		rc = PTR_ERR(dir);
 		goto failed;
 	}
 
 	for (i = 0; i < count; i++) {
-		rc = hpyfs_vm_create_guest(sb, dir, &(data[i]));
+		rc = hpyfs_vm_create_guest(dir, &(data[i]));
 		if (rc)
 			goto failed;
 	}
diff --git a/arch/s390/hypfs/inode.c b/arch/s390/hypfs/inode.c
index 7a539f4f5e30..ddfe09b45134 100644
--- a/arch/s390/hypfs/inode.c
+++ b/arch/s390/hypfs/inode.c
@@ -28,8 +28,7 @@
 #define HYPFS_MAGIC 0x687970	/* ASCII 'hyp' */
 #define TMP_SIZE 64		/* size of temporary buffers */
 
-static struct dentry *hypfs_create_update_file(struct super_block *sb,
-					       struct dentry *dir);
+static struct dentry *hypfs_create_update_file(struct dentry *dir);
 
 struct hypfs_sb_info {
 	kuid_t uid;			/* uid used for files and dirs */
@@ -193,9 +192,9 @@ static ssize_t hypfs_aio_write(struct kiocb *iocb, const struct iovec *iov,
 	}
 	hypfs_delete_tree(sb->s_root);
 	if (MACHINE_IS_VM)
-		rc = hypfs_vm_create_files(sb, sb->s_root);
+		rc = hypfs_vm_create_files(sb->s_root);
 	else
-		rc = hypfs_diag_create_files(sb, sb->s_root);
+		rc = hypfs_diag_create_files(sb->s_root);
 	if (rc) {
 		pr_err("Updating the hypfs tree failed\n");
 		hypfs_delete_tree(sb->s_root);
@@ -302,12 +301,12 @@ static int hypfs_fill_super(struct super_block *sb, void *data, int silent)
 	if (!root_dentry)
 		return -ENOMEM;
 	if (MACHINE_IS_VM)
-		rc = hypfs_vm_create_files(sb, root_dentry);
+		rc = hypfs_vm_create_files(root_dentry);
 	else
-		rc = hypfs_diag_create_files(sb, root_dentry);
+		rc = hypfs_diag_create_files(root_dentry);
 	if (rc)
 		return rc;
-	sbi->update_file = hypfs_create_update_file(sb, root_dentry);
+	sbi->update_file = hypfs_create_update_file(root_dentry);
 	if (IS_ERR(sbi->update_file))
 		return PTR_ERR(sbi->update_file);
 	hypfs_update_update(sb);
@@ -334,8 +333,7 @@ static void hypfs_kill_super(struct super_block *sb)
 	kill_litter_super(sb);
 }
 
-static struct dentry *hypfs_create_file(struct super_block *sb,
-					struct dentry *parent, const char *name,
+static struct dentry *hypfs_create_file(struct dentry *parent, const char *name,
 					char *data, umode_t mode)
 {
 	struct dentry *dentry;
@@ -347,7 +345,7 @@ static struct dentry *hypfs_create_file(struct super_block *sb,
 		dentry = ERR_PTR(-ENOMEM);
 		goto fail;
 	}
-	inode = hypfs_make_inode(sb, mode);
+	inode = hypfs_make_inode(parent->d_sb, mode);
 	if (!inode) {
 		dput(dentry);
 		dentry = ERR_PTR(-ENOMEM);
@@ -373,24 +371,22 @@ fail:
 	return dentry;
 }
 
-struct dentry *hypfs_mkdir(struct super_block *sb, struct dentry *parent,
-			   const char *name)
+struct dentry *hypfs_mkdir(struct dentry *parent, const char *name)
 {
 	struct dentry *dentry;
 
-	dentry = hypfs_create_file(sb, parent, name, NULL, S_IFDIR | DIR_MODE);
+	dentry = hypfs_create_file(parent, name, NULL, S_IFDIR | DIR_MODE);
 	if (IS_ERR(dentry))
 		return dentry;
 	hypfs_add_dentry(dentry);
 	return dentry;
 }
 
-static struct dentry *hypfs_create_update_file(struct super_block *sb,
-					       struct dentry *dir)
+static struct dentry *hypfs_create_update_file(struct dentry *dir)
 {
 	struct dentry *dentry;
 
-	dentry = hypfs_create_file(sb, dir, "update", NULL,
+	dentry = hypfs_create_file(dir, "update", NULL,
 				   S_IFREG | UPDATE_FILE_MODE);
 	/*
 	 * We do not put the update file on the 'delete' list with
@@ -400,7 +396,7 @@ static struct dentry *hypfs_create_update_file(struct super_block *sb,
 	return dentry;
 }
 
-struct dentry *hypfs_create_u64(struct super_block *sb, struct dentry *dir,
+struct dentry *hypfs_create_u64(struct dentry *dir,
 				const char *name, __u64 value)
 {
 	char *buffer;
@@ -412,7 +408,7 @@ struct dentry *hypfs_create_u64(struct super_block *sb, struct dentry *dir,
 	if (!buffer)
 		return ERR_PTR(-ENOMEM);
 	dentry =
-	    hypfs_create_file(sb, dir, name, buffer, S_IFREG | REG_FILE_MODE);
+	    hypfs_create_file(dir, name, buffer, S_IFREG | REG_FILE_MODE);
 	if (IS_ERR(dentry)) {
 		kfree(buffer);
 		return ERR_PTR(-ENOMEM);
@@ -421,7 +417,7 @@ struct dentry *hypfs_create_u64(struct super_block *sb, struct dentry *dir,
 	return dentry;
 }
 
-struct dentry *hypfs_create_str(struct super_block *sb, struct dentry *dir,
+struct dentry *hypfs_create_str(struct dentry *dir,
 				const char *name, char *string)
 {
 	char *buffer;
@@ -432,7 +428,7 @@ struct dentry *hypfs_create_str(struct super_block *sb, struct dentry *dir,
 		return ERR_PTR(-ENOMEM);
 	sprintf(buffer, "%s\n", string);
 	dentry =
-	    hypfs_create_file(sb, dir, name, buffer, S_IFREG | REG_FILE_MODE);
+	    hypfs_create_file(dir, name, buffer, S_IFREG | REG_FILE_MODE);
 	if (IS_ERR(dentry)) {
 		kfree(buffer);
 		return ERR_PTR(-ENOMEM);
diff --git a/arch/s390/include/asm/airq.h b/arch/s390/include/asm/airq.h
index 4066cee0c2d2..4bbb5957ed1b 100644
--- a/arch/s390/include/asm/airq.h
+++ b/arch/s390/include/asm/airq.h
@@ -9,6 +9,8 @@
 #ifndef _ASM_S390_AIRQ_H
 #define _ASM_S390_AIRQ_H
 
+#include <linux/bit_spinlock.h>
+
 struct airq_struct {
 	struct hlist_node list;		/* Handler queueing. */
 	void (*handler)(struct airq_struct *);	/* Thin-interrupt handler */
@@ -23,4 +25,69 @@ struct airq_struct {
 int register_adapter_interrupt(struct airq_struct *airq);
 void unregister_adapter_interrupt(struct airq_struct *airq);
 
+/* Adapter interrupt bit vector */
+struct airq_iv {
+	unsigned long *vector;	/* Adapter interrupt bit vector */
+	unsigned long *avail;	/* Allocation bit mask for the bit vector */
+	unsigned long *bitlock;	/* Lock bit mask for the bit vector */
+	unsigned long *ptr;	/* Pointer associated with each bit */
+	unsigned int *data;	/* 32 bit value associated with each bit */
+	unsigned long bits;	/* Number of bits in the vector */
+	unsigned long end;	/* Number of highest allocated bit + 1 */
+	spinlock_t lock;	/* Lock to protect alloc & free */
+};
+
+#define AIRQ_IV_ALLOC	1	/* Use an allocation bit mask */
+#define AIRQ_IV_BITLOCK	2	/* Allocate the lock bit mask */
+#define AIRQ_IV_PTR	4	/* Allocate the ptr array */
+#define AIRQ_IV_DATA	8	/* Allocate the data array */
+
+struct airq_iv *airq_iv_create(unsigned long bits, unsigned long flags);
+void airq_iv_release(struct airq_iv *iv);
+unsigned long airq_iv_alloc_bit(struct airq_iv *iv);
+void airq_iv_free_bit(struct airq_iv *iv, unsigned long bit);
+unsigned long airq_iv_scan(struct airq_iv *iv, unsigned long start,
+			   unsigned long end);
+
+static inline unsigned long airq_iv_end(struct airq_iv *iv)
+{
+	return iv->end;
+}
+
+static inline void airq_iv_lock(struct airq_iv *iv, unsigned long bit)
+{
+	const unsigned long be_to_le = BITS_PER_LONG - 1;
+	bit_spin_lock(bit ^ be_to_le, iv->bitlock);
+}
+
+static inline void airq_iv_unlock(struct airq_iv *iv, unsigned long bit)
+{
+	const unsigned long be_to_le = BITS_PER_LONG - 1;
+	bit_spin_unlock(bit ^ be_to_le, iv->bitlock);
+}
+
+static inline void airq_iv_set_data(struct airq_iv *iv, unsigned long bit,
+				    unsigned int data)
+{
+	iv->data[bit] = data;
+}
+
+static inline unsigned int airq_iv_get_data(struct airq_iv *iv,
+					    unsigned long bit)
+{
+	return iv->data[bit];
+}
+
+static inline void airq_iv_set_ptr(struct airq_iv *iv, unsigned long bit,
+				   unsigned long ptr)
+{
+	iv->ptr[bit] = ptr;
+}
+
+static inline unsigned long airq_iv_get_ptr(struct airq_iv *iv,
+					    unsigned long bit)
+{
+	return iv->ptr[bit];
+}
+
 #endif /* _ASM_S390_AIRQ_H */
diff --git a/arch/s390/include/asm/bitops.h b/arch/s390/include/asm/bitops.h
index 7d4676758733..10135a38673c 100644
--- a/arch/s390/include/asm/bitops.h
+++ b/arch/s390/include/asm/bitops.h
@@ -216,7 +216,7 @@ static inline void __set_bit(unsigned long nr, volatile unsigned long *ptr)
 	addr = (unsigned long) ptr + ((nr ^ (BITS_PER_LONG - 8)) >> 3);
 	asm volatile(
 		"	oc	%O0(1,%R0),%1"
-		: "=Q" (*(char *) addr) : "Q" (_oi_bitmap[nr & 7]) : "cc" );
+		: "+Q" (*(char *) addr) : "Q" (_oi_bitmap[nr & 7]) : "cc");
 }
 
 static inline void 
@@ -244,7 +244,7 @@ __clear_bit(unsigned long nr, volatile unsigned long *ptr)
 	addr = (unsigned long) ptr + ((nr ^ (BITS_PER_LONG - 8)) >> 3);
 	asm volatile(
 		"	nc	%O0(1,%R0),%1"
-		: "=Q" (*(char *) addr) : "Q" (_ni_bitmap[nr & 7]) : "cc" );
+		: "+Q" (*(char *) addr) : "Q" (_ni_bitmap[nr & 7]) : "cc");
 }
 
 static inline void 
@@ -271,7 +271,7 @@ static inline void __change_bit(unsigned long nr, volatile unsigned long *ptr)
 	addr = (unsigned long) ptr + ((nr ^ (BITS_PER_LONG - 8)) >> 3);
 	asm volatile(
 		"	xc	%O0(1,%R0),%1"
-		: "=Q" (*(char *) addr) : "Q" (_oi_bitmap[nr & 7]) : "cc" );
+		: "+Q" (*(char *) addr) : "Q" (_oi_bitmap[nr & 7]) : "cc");
 }
 
 static inline void 
@@ -301,7 +301,7 @@ test_and_set_bit_simple(unsigned long nr, volatile unsigned long *ptr)
 	ch = *(unsigned char *) addr;
 	asm volatile(
 		"	oc	%O0(1,%R0),%1"
-		: "=Q" (*(char *) addr)	: "Q" (_oi_bitmap[nr & 7])
+		: "+Q" (*(char *) addr)	: "Q" (_oi_bitmap[nr & 7])
 		: "cc", "memory");
 	return (ch >> (nr & 7)) & 1;
 }
@@ -320,7 +320,7 @@ test_and_clear_bit_simple(unsigned long nr, volatile unsigned long *ptr)
 	ch = *(unsigned char *) addr;
 	asm volatile(
 		"	nc	%O0(1,%R0),%1"
-		: "=Q" (*(char *) addr)	: "Q" (_ni_bitmap[nr & 7])
+		: "+Q" (*(char *) addr)	: "Q" (_ni_bitmap[nr & 7])
 		: "cc", "memory");
 	return (ch >> (nr & 7)) & 1;
 }
@@ -339,7 +339,7 @@ test_and_change_bit_simple(unsigned long nr, volatile unsigned long *ptr)
 	ch = *(unsigned char *) addr;
 	asm volatile(
 		"	xc	%O0(1,%R0),%1"
-		: "=Q" (*(char *) addr)	: "Q" (_oi_bitmap[nr & 7])
+		: "+Q" (*(char *) addr)	: "Q" (_oi_bitmap[nr & 7])
 		: "cc", "memory");
 	return (ch >> (nr & 7)) & 1;
 }
diff --git a/arch/s390/include/asm/cio.h b/arch/s390/include/asm/cio.h
index ffb898961c8d..d42625053c37 100644
--- a/arch/s390/include/asm/cio.h
+++ b/arch/s390/include/asm/cio.h
@@ -296,6 +296,7 @@ static inline int ccw_dev_id_is_equal(struct ccw_dev_id *dev_id1,
 	return 0;
 }
 
+void channel_subsystem_reinit(void);
 extern void css_schedule_reprobe(void);
 
 extern void reipl_ccw_dev(struct ccw_dev_id *id);
diff --git a/arch/s390/include/asm/cputime.h b/arch/s390/include/asm/cputime.h
index d2ff41370c0c..f65bd3634519 100644
--- a/arch/s390/include/asm/cputime.h
+++ b/arch/s390/include/asm/cputime.h
@@ -13,9 +13,6 @@
 #include <asm/div64.h>
 
 
-#define __ARCH_HAS_VTIME_ACCOUNT
-#define __ARCH_HAS_VTIME_TASK_SWITCH
-
 /* We want to use full resolution of the CPU timer: 2**-12 micro-seconds. */
 
 typedef unsigned long long __nocast cputime_t;
diff --git a/arch/s390/include/asm/hardirq.h b/arch/s390/include/asm/hardirq.h
index 0c82ba86e997..a908d2941c5d 100644
--- a/arch/s390/include/asm/hardirq.h
+++ b/arch/s390/include/asm/hardirq.h
@@ -20,4 +20,9 @@
 
 #define HARDIRQ_BITS	8
 
+static inline void ack_bad_irq(unsigned int irq)
+{
+	printk(KERN_CRIT "unexpected IRQ trap at vector %02x\n", irq);
+}
+
 #endif /* __ASM_HARDIRQ_H */
diff --git a/arch/s390/include/asm/hugetlb.h b/arch/s390/include/asm/hugetlb.h
index bd90359d6d22..11eae5f55b70 100644
--- a/arch/s390/include/asm/hugetlb.h
+++ b/arch/s390/include/asm/hugetlb.h
@@ -17,6 +17,9 @@
 
 void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 		     pte_t *ptep, pte_t pte);
+pte_t huge_ptep_get(pte_t *ptep);
+pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
+			      unsigned long addr, pte_t *ptep);
 
 /*
  * If the arch doesn't supply something else, assume that hugepage
@@ -38,147 +41,75 @@ static inline int prepare_hugepage_range(struct file *file,
 int arch_prepare_hugepage(struct page *page);
 void arch_release_hugepage(struct page *page);
 
-static inline pte_t huge_pte_wrprotect(pte_t pte)
+static inline void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
+				  pte_t *ptep)
 {
-	pte_val(pte) |= _PAGE_RO;
-	return pte;
+	pte_val(*ptep) = _SEGMENT_ENTRY_EMPTY;
 }
 
-static inline int huge_pte_none(pte_t pte)
+static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
+					 unsigned long address, pte_t *ptep)
 {
-	return (pte_val(pte) & _SEGMENT_ENTRY_INV) &&
-		!(pte_val(pte) & _SEGMENT_ENTRY_RO);
+	huge_ptep_get_and_clear(vma->vm_mm, address, ptep);
 }
 
-static inline pte_t huge_ptep_get(pte_t *ptep)
+static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
+					     unsigned long addr, pte_t *ptep,
+					     pte_t pte, int dirty)
 {
-	pte_t pte = *ptep;
-	unsigned long mask;
-
-	if (!MACHINE_HAS_HPAGE) {
-		ptep = (pte_t *) (pte_val(pte) & _SEGMENT_ENTRY_ORIGIN);
-		if (ptep) {
-			mask = pte_val(pte) &
-				(_SEGMENT_ENTRY_INV | _SEGMENT_ENTRY_RO);
-			pte = pte_mkhuge(*ptep);
-			pte_val(pte) |= mask;
-		}
+	int changed = !pte_same(huge_ptep_get(ptep), pte);
+	if (changed) {
+		huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
+		set_huge_pte_at(vma->vm_mm, addr, ptep, pte);
 	}
-	return pte;
+	return changed;
 }
 
-static inline void __pmd_csp(pmd_t *pmdp)
+static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
+					   unsigned long addr, pte_t *ptep)
 {
-	register unsigned long reg2 asm("2") = pmd_val(*pmdp);
-	register unsigned long reg3 asm("3") = pmd_val(*pmdp) |
-					       _SEGMENT_ENTRY_INV;
-	register unsigned long reg4 asm("4") = ((unsigned long) pmdp) + 5;
-
-	asm volatile(
-		"	csp %1,%3"
-		: "=m" (*pmdp)
-		: "d" (reg2), "d" (reg3), "d" (reg4), "m" (*pmdp) : "cc");
+	pte_t pte = huge_ptep_get_and_clear(mm, addr, ptep);
+	set_huge_pte_at(mm, addr, ptep, pte_wrprotect(pte));
 }
 
-static inline void huge_ptep_invalidate(struct mm_struct *mm,
-					unsigned long address, pte_t *ptep)
-{
-	pmd_t *pmdp = (pmd_t *) ptep;
-
-	if (MACHINE_HAS_IDTE)
-		__pmd_idte(address, pmdp);
-	else
-		__pmd_csp(pmdp);
-	pmd_val(*pmdp) = _SEGMENT_ENTRY_INV | _SEGMENT_ENTRY;
-}
-
-static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
-					    unsigned long addr, pte_t *ptep)
-{
-	pte_t pte = huge_ptep_get(ptep);
-
-	huge_ptep_invalidate(mm, addr, ptep);
-	return pte;
-}
-
-#define huge_ptep_set_access_flags(__vma, __addr, __ptep, __entry, __dirty) \
-({									    \
-	int __changed = !pte_same(huge_ptep_get(__ptep), __entry);	    \
-	if (__changed) {						    \
-		huge_ptep_invalidate((__vma)->vm_mm, __addr, __ptep);	    \
-		set_huge_pte_at((__vma)->vm_mm, __addr, __ptep, __entry);   \
-	}								    \
-	__changed;							    \
-})
-
-#define huge_ptep_set_wrprotect(__mm, __addr, __ptep)			\
-({									\
-	pte_t __pte = huge_ptep_get(__ptep);				\
-	if (huge_pte_write(__pte)) {					\
-		huge_ptep_invalidate(__mm, __addr, __ptep);		\
-		set_huge_pte_at(__mm, __addr, __ptep,			\
-				huge_pte_wrprotect(__pte));		\
-	}								\
-})
-
-static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
-					 unsigned long address, pte_t *ptep)
+static inline pte_t mk_huge_pte(struct page *page, pgprot_t pgprot)
 {
-	huge_ptep_invalidate(vma->vm_mm, address, ptep);
+	return mk_pte(page, pgprot);
 }
 
-static inline pte_t mk_huge_pte(struct page *page, pgprot_t pgprot)
+static inline int huge_pte_none(pte_t pte)
 {
-	pte_t pte;
-	pmd_t pmd;
-
-	pmd = mk_pmd_phys(page_to_phys(page), pgprot);
-	pte_val(pte) = pmd_val(pmd);
-	return pte;
+	return pte_none(pte);
 }
 
 static inline int huge_pte_write(pte_t pte)
 {
-	pmd_t pmd;
-
-	pmd_val(pmd) = pte_val(pte);
-	return pmd_write(pmd);
+	return pte_write(pte);
 }
 
 static inline int huge_pte_dirty(pte_t pte)
 {
-	/* No dirty bit in the segment table entry. */
-	return 0;
+	return pte_dirty(pte);
 }
 
 static inline pte_t huge_pte_mkwrite(pte_t pte)
 {
-	pmd_t pmd;
-
-	pmd_val(pmd) = pte_val(pte);
-	pte_val(pte) = pmd_val(pmd_mkwrite(pmd));
-	return pte;
+	return pte_mkwrite(pte);
 }
 
 static inline pte_t huge_pte_mkdirty(pte_t pte)
 {
-	/* No dirty bit in the segment table entry. */
-	return pte;
+	return pte_mkdirty(pte);
 }
 
-static inline pte_t huge_pte_modify(pte_t pte, pgprot_t newprot)
+static inline pte_t huge_pte_wrprotect(pte_t pte)
 {
-	pmd_t pmd;
-
-	pmd_val(pmd) = pte_val(pte);
-	pte_val(pte) = pmd_val(pmd_modify(pmd, newprot));
-	return pte;
+	return pte_wrprotect(pte);
 }
 
-static inline void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
-				  pte_t *ptep)
+static inline pte_t huge_pte_modify(pte_t pte, pgprot_t newprot)
 {
-	pmd_clear((pmd_t *) ptep);
+	return pte_modify(pte, newprot);
 }
 
 #endif /* _ASM_S390_HUGETLB_H */
diff --git a/arch/s390/include/asm/hw_irq.h b/arch/s390/include/asm/hw_irq.h
index 7e3d2586c1ff..ee96a8b697f9 100644
--- a/arch/s390/include/asm/hw_irq.h
+++ b/arch/s390/include/asm/hw_irq.h
@@ -4,19 +4,8 @@
 #include <linux/msi.h>
 #include <linux/pci.h>
 
-static inline struct msi_desc *irq_get_msi_desc(unsigned int irq)
-{
-	return __irq_get_msi_desc(irq);
-}
-
-/* Must be called with msi map lock held */
-static inline int irq_set_msi_desc(unsigned int irq, struct msi_desc *msi)
-{
-	if (!msi)
-		return -EINVAL;
-
-	msi->irq = irq;
-	return 0;
-}
+void __init init_airq_interrupts(void);
+void __init init_cio_interrupts(void);
+void __init init_ext_interrupts(void);
 
 #endif
diff --git a/arch/s390/include/asm/irq.h b/arch/s390/include/asm/irq.h
index 87c17bfb2968..5f8bcc5fe423 100644
--- a/arch/s390/include/asm/irq.h
+++ b/arch/s390/include/asm/irq.h
@@ -1,17 +1,28 @@
 #ifndef _ASM_IRQ_H
 #define _ASM_IRQ_H
 
+#define EXT_INTERRUPT	1
+#define IO_INTERRUPT	2
+#define THIN_INTERRUPT	3
+
+#define NR_IRQS_BASE	4
+
+#ifdef CONFIG_PCI_NR_MSI
+# define NR_IRQS	(NR_IRQS_BASE + CONFIG_PCI_NR_MSI)
+#else
+# define NR_IRQS	NR_IRQS_BASE
+#endif
+
+/* This number is used when no interrupt has been assigned */
+#define NO_IRQ		0
+
+#ifndef __ASSEMBLY__
+
 #include <linux/hardirq.h>
 #include <linux/percpu.h>
 #include <linux/cache.h>
 #include <linux/types.h>
 
-enum interruption_main_class {
-	EXTERNAL_INTERRUPT,
-	IO_INTERRUPT,
-	NR_IRQS
-};
-
 enum interruption_class {
 	IRQEXT_CLK,
 	IRQEXT_EXC,
@@ -67,19 +78,17 @@ typedef void (*ext_int_handler_t)(struct ext_code, unsigned int, unsigned long);
 
 int register_external_interrupt(u16 code, ext_int_handler_t handler);
 int unregister_external_interrupt(u16 code, ext_int_handler_t handler);
-void service_subclass_irq_register(void);
-void service_subclass_irq_unregister(void);
-void measurement_alert_subclass_register(void);
-void measurement_alert_subclass_unregister(void);
-
-#ifdef CONFIG_LOCKDEP
-#  define disable_irq_nosync_lockdep(irq)	disable_irq_nosync(irq)
-#  define disable_irq_nosync_lockdep_irqsave(irq, flags) \
-						disable_irq_nosync(irq)
-#  define disable_irq_lockdep(irq)		disable_irq(irq)
-#  define enable_irq_lockdep(irq)		enable_irq(irq)
-#  define enable_irq_lockdep_irqrestore(irq, flags) \
-						enable_irq(irq)
-#endif
+
+enum irq_subclass {
+	IRQ_SUBCLASS_MEASUREMENT_ALERT = 5,
+	IRQ_SUBCLASS_SERVICE_SIGNAL = 9,
+};
+
+void irq_subclass_register(enum irq_subclass subclass);
+void irq_subclass_unregister(enum irq_subclass subclass);
+
+#define irq_canonicalize(irq)  (irq)
+
+#endif /* __ASSEMBLY__ */
 
 #endif /* _ASM_IRQ_H */
diff --git a/arch/s390/include/asm/jump_label.h b/arch/s390/include/asm/jump_label.h
index 6c32190dc73e..346b1c85ffb4 100644
--- a/arch/s390/include/asm/jump_label.h
+++ b/arch/s390/include/asm/jump_label.h
@@ -15,7 +15,7 @@
 
 static __always_inline bool arch_static_branch(struct static_key *key)
 {
-	asm goto("0:	brcl 0,0\n"
+	asm_volatile_goto("0:	brcl 0,0\n"
 		".pushsection __jump_table, \"aw\"\n"
 		ASM_ALIGN "\n"
 		ASM_PTR " 0b, %l[label], %0\n"
diff --git a/arch/s390/include/asm/kprobes.h b/arch/s390/include/asm/kprobes.h
index dcf6948a875c..4176dfe0fba1 100644
--- a/arch/s390/include/asm/kprobes.h
+++ b/arch/s390/include/asm/kprobes.h
@@ -31,6 +31,8 @@
 #include <linux/ptrace.h>
 #include <linux/percpu.h>
 
+#define __ARCH_WANT_KPROBES_INSN_SLOT
+
 struct pt_regs;
 struct kprobe;
 
@@ -57,7 +59,7 @@ typedef u16 kprobe_opcode_t;
 /* Architecture specific copy of original instruction */
 struct arch_specific_insn {
 	/* copy of original instruction */
-	kprobe_opcode_t insn[MAX_INSN_SIZE];
+	kprobe_opcode_t *insn;
 };
 
 struct prev_kprobe {
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index 3238d4004e84..e87ecaa2c569 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -274,6 +274,14 @@ struct kvm_arch{
 	int css_support;
 };
 
+#define KVM_HVA_ERR_BAD		(-1UL)
+#define KVM_HVA_ERR_RO_BAD	(-2UL)
+
+static inline bool kvm_is_error_hva(unsigned long addr)
+{
+	return IS_ERR_VALUE(addr);
+}
+
 extern int sie64a(struct kvm_s390_sie_block *, u64 *);
 extern char sie_exit;
 #endif
diff --git a/arch/s390/include/asm/mmu.h b/arch/s390/include/asm/mmu.h
index 6340178748bf..ff132ac64ddd 100644
--- a/arch/s390/include/asm/mmu.h
+++ b/arch/s390/include/asm/mmu.h
@@ -12,8 +12,6 @@ typedef struct {
 	unsigned long asce_bits;
 	unsigned long asce_limit;
 	unsigned long vdso_base;
-	/* Cloned contexts will be created with extended page tables. */
-	unsigned int alloc_pgste:1;
 	/* The mmu context has extended page tables. */
 	unsigned int has_pgste:1;
 } mm_context_t;
diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h
index 084e7755ed9b..9f973d8de90e 100644
--- a/arch/s390/include/asm/mmu_context.h
+++ b/arch/s390/include/asm/mmu_context.h
@@ -21,24 +21,7 @@ static inline int init_new_context(struct task_struct *tsk,
 #ifdef CONFIG_64BIT
 	mm->context.asce_bits |= _ASCE_TYPE_REGION3;
 #endif
-	if (current->mm && current->mm->context.alloc_pgste) {
-		/*
-		 * alloc_pgste indicates, that any NEW context will be created
-		 * with extended page tables. The old context is unchanged. The
-		 * page table allocation and the page table operations will
-		 * look at has_pgste to distinguish normal and extended page
-		 * tables. The only way to create extended page tables is to
-		 * set alloc_pgste and then create a new context (e.g. dup_mm).
-		 * The page table allocation is called after init_new_context
-		 * and if has_pgste is set, it will create extended page
-		 * tables.
-		 */
-		mm->context.has_pgste = 1;
-		mm->context.alloc_pgste = 1;
-	} else {
-		mm->context.has_pgste = 0;
-		mm->context.alloc_pgste = 0;
-	}
+	mm->context.has_pgste = 0;
 	mm->context.asce_limit = STACK_TOP_MAX;
 	crst_table_init((unsigned long *) mm->pgd, pgd_entry_type(mm));
 	return 0;
@@ -77,8 +60,7 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 	WARN_ON(atomic_read(&prev->context.attach_count) < 0);
 	atomic_inc(&next->context.attach_count);
 	/* Check for TLBs not flushed yet */
-	if (next->context.flush_mm)
-		__tlb_flush_mm(next);
+	__tlb_flush_mm_lazy(next);
 }
 
 #define enter_lazy_tlb(mm,tsk)	do { } while (0)
diff --git a/arch/s390/include/asm/mutex.h b/arch/s390/include/asm/mutex.h
index 688271f5f2e4..458c1f7fbc18 100644
--- a/arch/s390/include/asm/mutex.h
+++ b/arch/s390/include/asm/mutex.h
@@ -7,5 +7,3 @@
  */
 
 #include <asm-generic/mutex-dec.h>
-
-#define arch_mutex_cpu_relax()	barrier()
diff --git a/arch/s390/include/asm/page.h b/arch/s390/include/asm/page.h
index 5d64fb7619cc..1e51f2915b2e 100644
--- a/arch/s390/include/asm/page.h
+++ b/arch/s390/include/asm/page.h
@@ -32,16 +32,6 @@
 
 void storage_key_init_range(unsigned long start, unsigned long end);
 
-static inline unsigned long pfmf(unsigned long function, unsigned long address)
-{
-	asm volatile(
-		"	.insn	rre,0xb9af0000,%[function],%[address]"
-		: [address] "+a" (address)
-		: [function] "d" (function)
-		: "memory");
-	return address;
-}
-
 static inline void clear_page(void *page)
 {
 	register unsigned long reg1 asm ("1") = 0;
@@ -150,15 +140,6 @@ static inline int page_reset_referenced(unsigned long addr)
 #define _PAGE_FP_BIT		0x08	/* HW fetch protection bit	*/
 #define _PAGE_ACC_BITS		0xf0	/* HW access control bits	*/
 
-/*
- * Test and clear referenced bit in storage key.
- */
-#define __HAVE_ARCH_PAGE_TEST_AND_CLEAR_YOUNG
-static inline int page_test_and_clear_young(unsigned long pfn)
-{
-	return page_reset_referenced(pfn << PAGE_SHIFT);
-}
-
 struct page;
 void arch_free_page(struct page *page, int order);
 void arch_alloc_page(struct page *page, int order);
diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h
index 6e577ba0e5da..1cc185da9d38 100644
--- a/arch/s390/include/asm/pci.h
+++ b/arch/s390/include/asm/pci.h
@@ -6,6 +6,7 @@
 /* must be set before including pci_clp.h */
 #define PCI_BAR_COUNT	6
 
+#include <linux/pci.h>
 #include <asm-generic/pci.h>
 #include <asm-generic/pci-dma-compat.h>
 #include <asm/pci_clp.h>
@@ -21,10 +22,6 @@ void pci_iounmap(struct pci_dev *, void __iomem *);
 int pci_domain_nr(struct pci_bus *);
 int pci_proc_domain(struct pci_bus *);
 
-/* MSI arch hooks */
-#define arch_setup_msi_irqs	arch_setup_msi_irqs
-#define arch_teardown_msi_irqs	arch_teardown_msi_irqs
-
 #define ZPCI_BUS_NR			0	/* default bus number */
 #define ZPCI_DEVFN			0	/* default device number */
 
@@ -53,14 +50,9 @@ struct zpci_fmb {
 	atomic64_t unmapped_pages;
 } __packed __aligned(16);
 
-struct msi_map {
-	unsigned long irq;
-	struct msi_desc *msi;
-	struct hlist_node msi_chain;
-};
-
-#define ZPCI_NR_MSI_VECS	64
-#define ZPCI_MSI_MASK		(ZPCI_NR_MSI_VECS - 1)
+#define ZPCI_MSI_VEC_BITS	11
+#define ZPCI_MSI_VEC_MAX	(1 << ZPCI_MSI_VEC_BITS)
+#define ZPCI_MSI_VEC_MASK	(ZPCI_MSI_VEC_MAX - 1)
 
 enum zpci_state {
 	ZPCI_FN_STATE_RESERVED,
@@ -91,8 +83,7 @@ struct zpci_dev {
 
 	/* IRQ stuff */
 	u64		msi_addr;	/* MSI address */
-	struct zdev_irq_map *irq_map;
-	struct msi_map *msi_map[ZPCI_NR_MSI_VECS];
+	struct airq_iv *aibv;		/* adapter interrupt bit vector */
 	unsigned int	aisb;		/* number of the summary bit */
 
 	/* DMA stuff */
@@ -122,11 +113,6 @@ struct zpci_dev {
 	struct dentry	*debugfs_perf;
 };
 
-struct pci_hp_callback_ops {
-	int (*create_slot)	(struct zpci_dev *zdev);
-	void (*remove_slot)	(struct zpci_dev *zdev);
-};
-
 static inline bool zdev_enabled(struct zpci_dev *zdev)
 {
 	return (zdev->fh & (1UL << 31)) ? true : false;
@@ -146,32 +132,38 @@ int zpci_register_ioat(struct zpci_dev *, u8, u64, u64, u64);
 int zpci_unregister_ioat(struct zpci_dev *, u8);
 
 /* CLP */
-int clp_find_pci_devices(void);
+int clp_scan_pci_devices(void);
+int clp_rescan_pci_devices(void);
+int clp_rescan_pci_devices_simple(void);
 int clp_add_pci_device(u32, u32, int);
 int clp_enable_fh(struct zpci_dev *, u8);
 int clp_disable_fh(struct zpci_dev *);
 
-/* MSI */
-struct msi_desc *__irq_get_msi_desc(unsigned int);
-int zpci_msi_set_mask_bits(struct msi_desc *, u32, u32);
-int zpci_setup_msi_irq(struct zpci_dev *, struct msi_desc *, unsigned int, int);
-void zpci_teardown_msi_irq(struct zpci_dev *, struct msi_desc *);
-int zpci_msihash_init(void);
-void zpci_msihash_exit(void);
-
 #ifdef CONFIG_PCI
 /* Error handling and recovery */
 void zpci_event_error(void *);
 void zpci_event_availability(void *);
+void zpci_rescan(void);
 #else /* CONFIG_PCI */
 static inline void zpci_event_error(void *e) {}
 static inline void zpci_event_availability(void *e) {}
+static inline void zpci_rescan(void) {}
 #endif /* CONFIG_PCI */
 
+#ifdef CONFIG_HOTPLUG_PCI_S390
+int zpci_init_slot(struct zpci_dev *);
+void zpci_exit_slot(struct zpci_dev *);
+#else /* CONFIG_HOTPLUG_PCI_S390 */
+static inline int zpci_init_slot(struct zpci_dev *zdev)
+{
+	return 0;
+}
+static inline void zpci_exit_slot(struct zpci_dev *zdev) {}
+#endif /* CONFIG_HOTPLUG_PCI_S390 */
+
 /* Helpers */
 struct zpci_dev *get_zdev(struct pci_dev *);
 struct zpci_dev *get_zdev_by_fid(u32);
-bool zpci_fid_present(u32);
 
 /* sysfs */
 int zpci_sysfs_add_device(struct device *);
@@ -181,14 +173,6 @@ void zpci_sysfs_remove_device(struct device *);
 int zpci_dma_init(void);
 void zpci_dma_exit(void);
 
-/* Hotplug */
-extern struct mutex zpci_list_lock;
-extern struct list_head zpci_list;
-extern unsigned int s390_pci_probe;
-
-void zpci_register_hp_ops(struct pci_hp_callback_ops *);
-void zpci_deregister_hp_ops(void);
-
 /* FMB */
 int zpci_fmb_enable_device(struct zpci_dev *);
 int zpci_fmb_disable_device(struct zpci_dev *);
diff --git a/arch/s390/include/asm/pci_insn.h b/arch/s390/include/asm/pci_insn.h
index e6a2bdd4d705..df6eac9f0cb4 100644
--- a/arch/s390/include/asm/pci_insn.h
+++ b/arch/s390/include/asm/pci_insn.h
@@ -79,11 +79,11 @@ struct zpci_fib {
 } __packed;
 
 
-int s390pci_mod_fc(u64 req, struct zpci_fib *fib);
-int s390pci_refresh_trans(u64 fn, u64 addr, u64 range);
-int s390pci_load(u64 *data, u64 req, u64 offset);
-int s390pci_store(u64 data, u64 req, u64 offset);
-int s390pci_store_block(const u64 *data, u64 req, u64 offset);
-void set_irq_ctrl(u16 ctl, char *unused, u8 isc);
+int zpci_mod_fc(u64 req, struct zpci_fib *fib);
+int zpci_refresh_trans(u64 fn, u64 addr, u64 range);
+int zpci_load(u64 *data, u64 req, u64 offset);
+int zpci_store(u64 data, u64 req, u64 offset);
+int zpci_store_block(const u64 *data, u64 req, u64 offset);
+void zpci_set_irq_ctrl(u16 ctl, char *unused, u8 isc);
 
 #endif
diff --git a/arch/s390/include/asm/pci_io.h b/arch/s390/include/asm/pci_io.h
index 83a9caa6ae53..d194d544d694 100644
--- a/arch/s390/include/asm/pci_io.h
+++ b/arch/s390/include/asm/pci_io.h
@@ -36,7 +36,7 @@ static inline RETTYPE zpci_read_##RETTYPE(const volatile void __iomem *addr)	\
 	u64 data;								\
 	int rc;									\
 										\
-	rc = s390pci_load(&data, req, ZPCI_OFFSET(addr));			\
+	rc = zpci_load(&data, req, ZPCI_OFFSET(addr));				\
 	if (rc)									\
 		data = -1ULL;							\
 	return (RETTYPE) data;							\
@@ -50,7 +50,7 @@ static inline void zpci_write_##VALTYPE(VALTYPE val,				\
 	u64 req = ZPCI_CREATE_REQ(entry->fh, entry->bar, LENGTH);		\
 	u64 data = (VALTYPE) val;						\
 										\
-	s390pci_store(data, req, ZPCI_OFFSET(addr));				\
+	zpci_store(data, req, ZPCI_OFFSET(addr));				\
 }
 
 zpci_read(8, u64)
@@ -83,7 +83,7 @@ static inline int zpci_write_single(u64 req, const u64 *data, u64 offset, u8 len
 		val = 0;		/* let FW report error */
 		break;
 	}
-	return s390pci_store(val, req, offset);
+	return zpci_store(val, req, offset);
 }
 
 static inline int zpci_read_single(u64 req, u64 *dst, u64 offset, u8 len)
@@ -91,7 +91,7 @@ static inline int zpci_read_single(u64 req, u64 *dst, u64 offset, u8 len)
 	u64 data;
 	int cc;
 
-	cc = s390pci_load(&data, req, offset);
+	cc = zpci_load(&data, req, offset);
 	if (cc)
 		goto out;
 
@@ -115,7 +115,7 @@ out:
 
 static inline int zpci_write_block(u64 req, const u64 *data, u64 offset)
 {
-	return s390pci_store_block(data, req, offset);
+	return zpci_store_block(data, req, offset);
 }
 
 static inline u8 zpci_get_max_write_size(u64 src, u64 dst, int len, int max)
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 75fb726de91f..9b60a36c348d 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -217,63 +217,57 @@ extern unsigned long MODULES_END;
 
 /* Hardware bits in the page table entry */
 #define _PAGE_CO	0x100		/* HW Change-bit override */
-#define _PAGE_RO	0x200		/* HW read-only bit  */
+#define _PAGE_PROTECT	0x200		/* HW read-only bit  */
 #define _PAGE_INVALID	0x400		/* HW invalid bit    */
+#define _PAGE_LARGE	0x800		/* Bit to mark a large pte */
 
 /* Software bits in the page table entry */
-#define _PAGE_SWT	0x001		/* SW pte type bit t */
-#define _PAGE_SWX	0x002		/* SW pte type bit x */
-#define _PAGE_SWC	0x004		/* SW pte changed bit */
-#define _PAGE_SWR	0x008		/* SW pte referenced bit */
-#define _PAGE_SWW	0x010		/* SW pte write bit */
-#define _PAGE_SPECIAL	0x020		/* SW associated with special page */
+#define _PAGE_PRESENT	0x001		/* SW pte present bit */
+#define _PAGE_TYPE	0x002		/* SW pte type bit */
+#define _PAGE_YOUNG	0x004		/* SW pte young bit */
+#define _PAGE_DIRTY	0x008		/* SW pte dirty bit */
+#define _PAGE_READ	0x010		/* SW pte read bit */
+#define _PAGE_WRITE	0x020		/* SW pte write bit */
+#define _PAGE_SPECIAL	0x040		/* SW associated with special page */
 #define __HAVE_ARCH_PTE_SPECIAL
 
 /* Set of bits not changed in pte_modify */
 #define _PAGE_CHG_MASK		(PAGE_MASK | _PAGE_SPECIAL | _PAGE_CO | \
-				 _PAGE_SWC | _PAGE_SWR)
-
-/* Six different types of pages. */
-#define _PAGE_TYPE_EMPTY	0x400
-#define _PAGE_TYPE_NONE		0x401
-#define _PAGE_TYPE_SWAP		0x403
-#define _PAGE_TYPE_FILE		0x601	/* bit 0x002 is used for offset !! */
-#define _PAGE_TYPE_RO		0x200
-#define _PAGE_TYPE_RW		0x000
-
-/*
- * Only four types for huge pages, using the invalid bit and protection bit
- * of a segment table entry.
- */
-#define _HPAGE_TYPE_EMPTY	0x020	/* _SEGMENT_ENTRY_INV */
-#define _HPAGE_TYPE_NONE	0x220
-#define _HPAGE_TYPE_RO		0x200	/* _SEGMENT_ENTRY_RO  */
-#define _HPAGE_TYPE_RW		0x000
+				 _PAGE_DIRTY | _PAGE_YOUNG)
 
 /*
- * PTE type bits are rather complicated. handle_pte_fault uses pte_present,
- * pte_none and pte_file to find out the pte type WITHOUT holding the page
- * table lock. ptep_clear_flush on the other hand uses ptep_clear_flush to
- * invalidate a given pte. ipte sets the hw invalid bit and clears all tlbs
- * for the page. The page table entry is set to _PAGE_TYPE_EMPTY afterwards.
- * This change is done while holding the lock, but the intermediate step
- * of a previously valid pte with the hw invalid bit set can be observed by
- * handle_pte_fault. That makes it necessary that all valid pte types with
- * the hw invalid bit set must be distinguishable from the four pte types
- * empty, none, swap and file.
+ * handle_pte_fault uses pte_present, pte_none and pte_file to find out the
+ * pte type WITHOUT holding the page table lock. The _PAGE_PRESENT bit
+ * is used to distinguish present from not-present ptes. It is changed only
+ * with the page table lock held.
+ *
+ * The following table gives the different possible bit combinations for
+ * the pte hardware and software bits in the last 12 bits of a pte:
  *
- *			irxt  ipte  irxt
- * _PAGE_TYPE_EMPTY	1000   ->   1000
- * _PAGE_TYPE_NONE	1001   ->   1001
- * _PAGE_TYPE_SWAP	1011   ->   1011
- * _PAGE_TYPE_FILE	11?1   ->   11?1
- * _PAGE_TYPE_RO	0100   ->   1100
- * _PAGE_TYPE_RW	0000   ->   1000
+ *				842100000000
+ *				000084210000
+ *				000000008421
+ *				.IR...wrdytp
+ * empty			.10...000000
+ * swap				.10...xxxx10
+ * file				.11...xxxxx0
+ * prot-none, clean, old	.11...000001
+ * prot-none, clean, young	.11...000101
+ * prot-none, dirty, old	.10...001001
+ * prot-none, dirty, young	.10...001101
+ * read-only, clean, old	.11...010001
+ * read-only, clean, young	.01...010101
+ * read-only, dirty, old	.11...011001
+ * read-only, dirty, young	.01...011101
+ * read-write, clean, old	.11...110001
+ * read-write, clean, young	.01...110101
+ * read-write, dirty, old	.10...111001
+ * read-write, dirty, young	.00...111101
  *
- * pte_none is true for bits combinations 1000, 1010, 1100, 1110
- * pte_present is true for bits combinations 0000, 0010, 0100, 0110, 1001
- * pte_file is true for bits combinations 1101, 1111
- * swap pte is 1011 and 0001, 0011, 0101, 0111 are invalid.
+ * pte_present is true for the bit pattern .xx...xxxxx1, (pte & 0x001) == 0x001
+ * pte_none    is true for the bit pattern .10...xxxx00, (pte & 0x603) == 0x400
+ * pte_file    is true for the bit pattern .11...xxxxx0, (pte & 0x601) == 0x600
+ * pte_swap    is true for the bit pattern .10...xxxx10, (pte & 0x603) == 0x402
  */
 
 #ifndef CONFIG_64BIT
@@ -286,14 +280,25 @@ extern unsigned long MODULES_END;
 #define _ASCE_TABLE_LENGTH	0x7f	/* 128 x 64 entries = 8k	    */
 
 /* Bits in the segment table entry */
+#define _SEGMENT_ENTRY_BITS	0x7fffffffUL	/* Valid segment table bits */
 #define _SEGMENT_ENTRY_ORIGIN	0x7fffffc0UL	/* page table origin	    */
-#define _SEGMENT_ENTRY_RO	0x200	/* page protection bit		    */
-#define _SEGMENT_ENTRY_INV	0x20	/* invalid segment table entry	    */
+#define _SEGMENT_ENTRY_PROTECT	0x200	/* page protection bit		    */
+#define _SEGMENT_ENTRY_INVALID	0x20	/* invalid segment table entry	    */
 #define _SEGMENT_ENTRY_COMMON	0x10	/* common segment bit		    */
 #define _SEGMENT_ENTRY_PTL	0x0f	/* page table length		    */
+#define _SEGMENT_ENTRY_NONE	_SEGMENT_ENTRY_PROTECT
 
 #define _SEGMENT_ENTRY		(_SEGMENT_ENTRY_PTL)
-#define _SEGMENT_ENTRY_EMPTY	(_SEGMENT_ENTRY_INV)
+#define _SEGMENT_ENTRY_EMPTY	(_SEGMENT_ENTRY_INVALID)
+
+/*
+ * Segment table entry encoding (I = invalid, R = read-only bit):
+ *		..R...I.....
+ * prot-none	..1...1.....
+ * read-only	..1...0.....
+ * read-write	..0...0.....
+ * empty	..0...1.....
+ */
 
 /* Page status table bits for virtualization */
 #define PGSTE_ACC_BITS	0xf0000000UL
@@ -303,9 +308,7 @@ extern unsigned long MODULES_END;
 #define PGSTE_HC_BIT	0x00200000UL
 #define PGSTE_GR_BIT	0x00040000UL
 #define PGSTE_GC_BIT	0x00020000UL
-#define PGSTE_UR_BIT	0x00008000UL
-#define PGSTE_UC_BIT	0x00004000UL	/* user dirty (migration) */
-#define PGSTE_IN_BIT	0x00002000UL	/* IPTE notify bit */
+#define PGSTE_IN_BIT	0x00008000UL	/* IPTE notify bit */
 
 #else /* CONFIG_64BIT */
 
@@ -324,8 +327,8 @@ extern unsigned long MODULES_END;
 
 /* Bits in the region table entry */
 #define _REGION_ENTRY_ORIGIN	~0xfffUL/* region/segment table origin	    */
-#define _REGION_ENTRY_RO	0x200	/* region protection bit	    */
-#define _REGION_ENTRY_INV	0x20	/* invalid region table entry	    */
+#define _REGION_ENTRY_PROTECT	0x200	/* region protection bit	    */
+#define _REGION_ENTRY_INVALID	0x20	/* invalid region table entry	    */
 #define _REGION_ENTRY_TYPE_MASK	0x0c	/* region/segment table type mask   */
 #define _REGION_ENTRY_TYPE_R1	0x0c	/* region first table type	    */
 #define _REGION_ENTRY_TYPE_R2	0x08	/* region second table type	    */
@@ -333,29 +336,47 @@ extern unsigned long MODULES_END;
 #define _REGION_ENTRY_LENGTH	0x03	/* region third length		    */
 
 #define _REGION1_ENTRY		(_REGION_ENTRY_TYPE_R1 | _REGION_ENTRY_LENGTH)
-#define _REGION1_ENTRY_EMPTY	(_REGION_ENTRY_TYPE_R1 | _REGION_ENTRY_INV)
+#define _REGION1_ENTRY_EMPTY	(_REGION_ENTRY_TYPE_R1 | _REGION_ENTRY_INVALID)
 #define _REGION2_ENTRY		(_REGION_ENTRY_TYPE_R2 | _REGION_ENTRY_LENGTH)
-#define _REGION2_ENTRY_EMPTY	(_REGION_ENTRY_TYPE_R2 | _REGION_ENTRY_INV)
+#define _REGION2_ENTRY_EMPTY	(_REGION_ENTRY_TYPE_R2 | _REGION_ENTRY_INVALID)
 #define _REGION3_ENTRY		(_REGION_ENTRY_TYPE_R3 | _REGION_ENTRY_LENGTH)
-#define _REGION3_ENTRY_EMPTY	(_REGION_ENTRY_TYPE_R3 | _REGION_ENTRY_INV)
+#define _REGION3_ENTRY_EMPTY	(_REGION_ENTRY_TYPE_R3 | _REGION_ENTRY_INVALID)
 
 #define _REGION3_ENTRY_LARGE	0x400	/* RTTE-format control, large page  */
 #define _REGION3_ENTRY_RO	0x200	/* page protection bit		    */
 #define _REGION3_ENTRY_CO	0x100	/* change-recording override	    */
 
 /* Bits in the segment table entry */
+#define _SEGMENT_ENTRY_BITS	0xfffffffffffffe33UL
+#define _SEGMENT_ENTRY_BITS_LARGE 0xfffffffffff1ff33UL
 #define _SEGMENT_ENTRY_ORIGIN_LARGE ~0xfffffUL /* large page address	    */
 #define _SEGMENT_ENTRY_ORIGIN	~0x7ffUL/* segment table origin		    */
-#define _SEGMENT_ENTRY_RO	0x200	/* page protection bit		    */
-#define _SEGMENT_ENTRY_INV	0x20	/* invalid segment table entry	    */
+#define _SEGMENT_ENTRY_PROTECT	0x200	/* page protection bit		    */
+#define _SEGMENT_ENTRY_INVALID	0x20	/* invalid segment table entry	    */
 
 #define _SEGMENT_ENTRY		(0)
-#define _SEGMENT_ENTRY_EMPTY	(_SEGMENT_ENTRY_INV)
+#define _SEGMENT_ENTRY_EMPTY	(_SEGMENT_ENTRY_INVALID)
 
 #define _SEGMENT_ENTRY_LARGE	0x400	/* STE-format control, large page   */
 #define _SEGMENT_ENTRY_CO	0x100	/* change-recording override   */
+#define _SEGMENT_ENTRY_SPLIT	0x001	/* THP splitting bit */
+#define _SEGMENT_ENTRY_YOUNG	0x002	/* SW segment young bit */
+#define _SEGMENT_ENTRY_NONE	_SEGMENT_ENTRY_YOUNG
+
+/*
+ * Segment table entry encoding (R = read-only, I = invalid, y = young bit):
+ *			..R...I...y.
+ * prot-none, old	..0...1...1.
+ * prot-none, young	..1...1...1.
+ * read-only, old	..1...1...0.
+ * read-only, young	..1...0...1.
+ * read-write, old	..0...1...0.
+ * read-write, young	..0...0...1.
+ * The segment table origin is used to distinguish empty (origin==0) from
+ * read-write, old segment table entries (origin!=0)
+ */
+
 #define _SEGMENT_ENTRY_SPLIT_BIT 0	/* THP splitting bit number */
-#define _SEGMENT_ENTRY_SPLIT	(1UL << _SEGMENT_ENTRY_SPLIT_BIT)
 
 /* Set of bits not changed in pmd_modify */
 #define _SEGMENT_CHG_MASK	(_SEGMENT_ENTRY_ORIGIN | _SEGMENT_ENTRY_LARGE \
@@ -369,9 +390,7 @@ extern unsigned long MODULES_END;
 #define PGSTE_HC_BIT	0x0020000000000000UL
 #define PGSTE_GR_BIT	0x0004000000000000UL
 #define PGSTE_GC_BIT	0x0002000000000000UL
-#define PGSTE_UR_BIT	0x0000800000000000UL
-#define PGSTE_UC_BIT	0x0000400000000000UL	/* user dirty (migration) */
-#define PGSTE_IN_BIT	0x0000200000000000UL	/* IPTE notify bit */
+#define PGSTE_IN_BIT	0x0000800000000000UL	/* IPTE notify bit */
 
 #endif /* CONFIG_64BIT */
 
@@ -386,14 +405,18 @@ extern unsigned long MODULES_END;
 /*
  * Page protection definitions.
  */
-#define PAGE_NONE	__pgprot(_PAGE_TYPE_NONE)
-#define PAGE_RO		__pgprot(_PAGE_TYPE_RO)
-#define PAGE_RW		__pgprot(_PAGE_TYPE_RO | _PAGE_SWW)
-#define PAGE_RWC	__pgprot(_PAGE_TYPE_RW | _PAGE_SWW | _PAGE_SWC)
-
-#define PAGE_KERNEL	PAGE_RWC
-#define PAGE_SHARED	PAGE_KERNEL
-#define PAGE_COPY	PAGE_RO
+#define PAGE_NONE	__pgprot(_PAGE_PRESENT | _PAGE_INVALID)
+#define PAGE_READ	__pgprot(_PAGE_PRESENT | _PAGE_READ | \
+				 _PAGE_INVALID | _PAGE_PROTECT)
+#define PAGE_WRITE	__pgprot(_PAGE_PRESENT | _PAGE_READ | _PAGE_WRITE | \
+				 _PAGE_INVALID | _PAGE_PROTECT)
+
+#define PAGE_SHARED	__pgprot(_PAGE_PRESENT | _PAGE_READ | _PAGE_WRITE | \
+				 _PAGE_YOUNG | _PAGE_DIRTY)
+#define PAGE_KERNEL	__pgprot(_PAGE_PRESENT | _PAGE_READ | _PAGE_WRITE | \
+				 _PAGE_YOUNG | _PAGE_DIRTY)
+#define PAGE_KERNEL_RO	__pgprot(_PAGE_PRESENT | _PAGE_READ | _PAGE_YOUNG | \
+				 _PAGE_PROTECT)
 
 /*
  * On s390 the page table entry has an invalid bit and a read-only bit.
@@ -402,35 +425,31 @@ extern unsigned long MODULES_END;
  */
          /*xwr*/
 #define __P000	PAGE_NONE
-#define __P001	PAGE_RO
-#define __P010	PAGE_RO
-#define __P011	PAGE_RO
-#define __P100	PAGE_RO
-#define __P101	PAGE_RO
-#define __P110	PAGE_RO
-#define __P111	PAGE_RO
+#define __P001	PAGE_READ
+#define __P010	PAGE_READ
+#define __P011	PAGE_READ
+#define __P100	PAGE_READ
+#define __P101	PAGE_READ
+#define __P110	PAGE_READ
+#define __P111	PAGE_READ
 
 #define __S000	PAGE_NONE
-#define __S001	PAGE_RO
-#define __S010	PAGE_RW
-#define __S011	PAGE_RW
-#define __S100	PAGE_RO
-#define __S101	PAGE_RO
-#define __S110	PAGE_RW
-#define __S111	PAGE_RW
+#define __S001	PAGE_READ
+#define __S010	PAGE_WRITE
+#define __S011	PAGE_WRITE
+#define __S100	PAGE_READ
+#define __S101	PAGE_READ
+#define __S110	PAGE_WRITE
+#define __S111	PAGE_WRITE
 
 /*
  * Segment entry (large page) protection definitions.
  */
-#define SEGMENT_NONE	__pgprot(_HPAGE_TYPE_NONE)
-#define SEGMENT_RO	__pgprot(_HPAGE_TYPE_RO)
-#define SEGMENT_RW	__pgprot(_HPAGE_TYPE_RW)
-
-static inline int mm_exclusive(struct mm_struct *mm)
-{
-	return likely(mm == current->active_mm &&
-		      atomic_read(&mm->context.attach_count) <= 1);
-}
+#define SEGMENT_NONE	__pgprot(_SEGMENT_ENTRY_INVALID | \
+				 _SEGMENT_ENTRY_NONE)
+#define SEGMENT_READ	__pgprot(_SEGMENT_ENTRY_INVALID | \
+				 _SEGMENT_ENTRY_PROTECT)
+#define SEGMENT_WRITE	__pgprot(_SEGMENT_ENTRY_INVALID)
 
 static inline int mm_has_pgste(struct mm_struct *mm)
 {
@@ -467,7 +486,7 @@ static inline int pgd_none(pgd_t pgd)
 {
 	if ((pgd_val(pgd) & _REGION_ENTRY_TYPE_MASK) < _REGION_ENTRY_TYPE_R2)
 		return 0;
-	return (pgd_val(pgd) & _REGION_ENTRY_INV) != 0UL;
+	return (pgd_val(pgd) & _REGION_ENTRY_INVALID) != 0UL;
 }
 
 static inline int pgd_bad(pgd_t pgd)
@@ -478,7 +497,7 @@ static inline int pgd_bad(pgd_t pgd)
 	 * invalid for either table entry.
 	 */
 	unsigned long mask =
-		~_SEGMENT_ENTRY_ORIGIN & ~_REGION_ENTRY_INV &
+		~_SEGMENT_ENTRY_ORIGIN & ~_REGION_ENTRY_INVALID &
 		~_REGION_ENTRY_TYPE_MASK & ~_REGION_ENTRY_LENGTH;
 	return (pgd_val(pgd) & mask) != 0;
 }
@@ -494,7 +513,7 @@ static inline int pud_none(pud_t pud)
 {
 	if ((pud_val(pud) & _REGION_ENTRY_TYPE_MASK) < _REGION_ENTRY_TYPE_R3)
 		return 0;
-	return (pud_val(pud) & _REGION_ENTRY_INV) != 0UL;
+	return (pud_val(pud) & _REGION_ENTRY_INVALID) != 0UL;
 }
 
 static inline int pud_large(pud_t pud)
@@ -512,7 +531,7 @@ static inline int pud_bad(pud_t pud)
 	 * invalid for either table entry.
 	 */
 	unsigned long mask =
-		~_SEGMENT_ENTRY_ORIGIN & ~_REGION_ENTRY_INV &
+		~_SEGMENT_ENTRY_ORIGIN & ~_REGION_ENTRY_INVALID &
 		~_REGION_ENTRY_TYPE_MASK & ~_REGION_ENTRY_LENGTH;
 	return (pud_val(pud) & mask) != 0;
 }
@@ -521,30 +540,36 @@ static inline int pud_bad(pud_t pud)
 
 static inline int pmd_present(pmd_t pmd)
 {
-	unsigned long mask = _SEGMENT_ENTRY_INV | _SEGMENT_ENTRY_RO;
-	return (pmd_val(pmd) & mask) == _HPAGE_TYPE_NONE ||
-	       !(pmd_val(pmd) & _SEGMENT_ENTRY_INV);
+	return pmd_val(pmd) != _SEGMENT_ENTRY_INVALID;
 }
 
 static inline int pmd_none(pmd_t pmd)
 {
-	return (pmd_val(pmd) & _SEGMENT_ENTRY_INV) &&
-	       !(pmd_val(pmd) & _SEGMENT_ENTRY_RO);
+	return pmd_val(pmd) == _SEGMENT_ENTRY_INVALID;
 }
 
 static inline int pmd_large(pmd_t pmd)
 {
 #ifdef CONFIG_64BIT
-	return !!(pmd_val(pmd) & _SEGMENT_ENTRY_LARGE);
+	return (pmd_val(pmd) & _SEGMENT_ENTRY_LARGE) != 0;
 #else
 	return 0;
 #endif
 }
 
+static inline int pmd_prot_none(pmd_t pmd)
+{
+	return (pmd_val(pmd) & _SEGMENT_ENTRY_INVALID) &&
+		(pmd_val(pmd) & _SEGMENT_ENTRY_NONE);
+}
+
 static inline int pmd_bad(pmd_t pmd)
 {
-	unsigned long mask = ~_SEGMENT_ENTRY_ORIGIN & ~_SEGMENT_ENTRY_INV;
-	return (pmd_val(pmd) & mask) != _SEGMENT_ENTRY;
+#ifdef CONFIG_64BIT
+	if (pmd_large(pmd))
+		return (pmd_val(pmd) & ~_SEGMENT_ENTRY_BITS_LARGE) != 0;
+#endif
+	return (pmd_val(pmd) & ~_SEGMENT_ENTRY_BITS) != 0;
 }
 
 #define __HAVE_ARCH_PMDP_SPLITTING_FLUSH
@@ -563,31 +588,40 @@ extern int pmdp_clear_flush_young(struct vm_area_struct *vma,
 #define __HAVE_ARCH_PMD_WRITE
 static inline int pmd_write(pmd_t pmd)
 {
-	return (pmd_val(pmd) & _SEGMENT_ENTRY_RO) == 0;
+	if (pmd_prot_none(pmd))
+		return 0;
+	return (pmd_val(pmd) & _SEGMENT_ENTRY_PROTECT) == 0;
 }
 
 static inline int pmd_young(pmd_t pmd)
 {
-	return 0;
+	int young = 0;
+#ifdef CONFIG_64BIT
+	if (pmd_prot_none(pmd))
+		young = (pmd_val(pmd) & _SEGMENT_ENTRY_PROTECT) != 0;
+	else
+		young = (pmd_val(pmd) & _SEGMENT_ENTRY_YOUNG) != 0;
+#endif
+	return young;
 }
 
-static inline int pte_none(pte_t pte)
+static inline int pte_present(pte_t pte)
 {
-	return (pte_val(pte) & _PAGE_INVALID) && !(pte_val(pte) & _PAGE_SWT);
+	/* Bit pattern: (pte & 0x001) == 0x001 */
+	return (pte_val(pte) & _PAGE_PRESENT) != 0;
 }
 
-static inline int pte_present(pte_t pte)
+static inline int pte_none(pte_t pte)
 {
-	unsigned long mask = _PAGE_RO | _PAGE_INVALID | _PAGE_SWT | _PAGE_SWX;
-	return (pte_val(pte) & mask) == _PAGE_TYPE_NONE ||
-		(!(pte_val(pte) & _PAGE_INVALID) &&
-		 !(pte_val(pte) & _PAGE_SWT));
+	/* Bit pattern: pte == 0x400 */
+	return pte_val(pte) == _PAGE_INVALID;
 }
 
 static inline int pte_file(pte_t pte)
 {
-	unsigned long mask = _PAGE_RO | _PAGE_INVALID | _PAGE_SWT;
-	return (pte_val(pte) & mask) == _PAGE_TYPE_FILE;
+	/* Bit pattern: (pte & 0x601) == 0x600 */
+	return (pte_val(pte) & (_PAGE_INVALID | _PAGE_PROTECT | _PAGE_PRESENT))
+		== (_PAGE_INVALID | _PAGE_PROTECT);
 }
 
 static inline int pte_special(pte_t pte)
@@ -634,6 +668,15 @@ static inline void pgste_set_unlock(pte_t *ptep, pgste_t pgste)
 #endif
 }
 
+static inline pgste_t pgste_get(pte_t *ptep)
+{
+	unsigned long pgste = 0;
+#ifdef CONFIG_PGSTE
+	pgste = *(unsigned long *)(ptep + PTRS_PER_PTE);
+#endif
+	return __pgste(pgste);
+}
+
 static inline void pgste_set(pte_t *ptep, pgste_t pgste)
 {
 #ifdef CONFIG_PGSTE
@@ -644,33 +687,28 @@ static inline void pgste_set(pte_t *ptep, pgste_t pgste)
 static inline pgste_t pgste_update_all(pte_t *ptep, pgste_t pgste)
 {
 #ifdef CONFIG_PGSTE
-	unsigned long address, bits;
-	unsigned char skey;
+	unsigned long address, bits, skey;
 
 	if (pte_val(*ptep) & _PAGE_INVALID)
 		return pgste;
 	address = pte_val(*ptep) & PAGE_MASK;
-	skey = page_get_storage_key(address);
+	skey = (unsigned long) page_get_storage_key(address);
 	bits = skey & (_PAGE_CHANGED | _PAGE_REFERENCED);
-	/* Clear page changed & referenced bit in the storage key */
-	if (bits & _PAGE_CHANGED)
+	if (!(pgste_val(pgste) & PGSTE_HC_BIT) && (bits & _PAGE_CHANGED)) {
+		/* Transfer dirty + referenced bit to host bits in pgste */
+		pgste_val(pgste) |= bits << 52;
 		page_set_storage_key(address, skey ^ bits, 0);
-	else if (bits)
+	} else if (!(pgste_val(pgste) & PGSTE_HR_BIT) &&
+		   (bits & _PAGE_REFERENCED)) {
+		/* Transfer referenced bit to host bit in pgste */
+		pgste_val(pgste) |= PGSTE_HR_BIT;
 		page_reset_referenced(address);
+	}
 	/* Transfer page changed & referenced bit to guest bits in pgste */
 	pgste_val(pgste) |= bits << 48;		/* GR bit & GC bit */
-	/* Get host changed & referenced bits from pgste */
-	bits |= (pgste_val(pgste) & (PGSTE_HR_BIT | PGSTE_HC_BIT)) >> 52;
-	/* Transfer page changed & referenced bit to kvm user bits */
-	pgste_val(pgste) |= bits << 45;		/* PGSTE_UR_BIT & PGSTE_UC_BIT */
-	/* Clear relevant host bits in pgste. */
-	pgste_val(pgste) &= ~(PGSTE_HR_BIT | PGSTE_HC_BIT);
-	pgste_val(pgste) &= ~(PGSTE_ACC_BITS | PGSTE_FP_BIT);
 	/* Copy page access key and fetch protection bit to pgste */
-	pgste_val(pgste) |=
-		(unsigned long) (skey & (_PAGE_ACC_BITS | _PAGE_FP_BIT)) << 56;
-	/* Transfer referenced bit to pte */
-	pte_val(*ptep) |= (bits & _PAGE_REFERENCED) << 1;
+	pgste_val(pgste) &= ~(PGSTE_ACC_BITS | PGSTE_FP_BIT);
+	pgste_val(pgste) |= (skey & (_PAGE_ACC_BITS | _PAGE_FP_BIT)) << 56;
 #endif
 	return pgste;
 
@@ -679,24 +717,11 @@ static inline pgste_t pgste_update_all(pte_t *ptep, pgste_t pgste)
 static inline pgste_t pgste_update_young(pte_t *ptep, pgste_t pgste)
 {
 #ifdef CONFIG_PGSTE
-	int young;
-
 	if (pte_val(*ptep) & _PAGE_INVALID)
 		return pgste;
 	/* Get referenced bit from storage key */
-	young = page_reset_referenced(pte_val(*ptep) & PAGE_MASK);
-	if (young)
-		pgste_val(pgste) |= PGSTE_GR_BIT;
-	/* Get host referenced bit from pgste */
-	if (pgste_val(pgste) & PGSTE_HR_BIT) {
-		pgste_val(pgste) &= ~PGSTE_HR_BIT;
-		young = 1;
-	}
-	/* Transfer referenced bit to kvm user bits and pte */
-	if (young) {
-		pgste_val(pgste) |= PGSTE_UR_BIT;
-		pte_val(*ptep) |= _PAGE_SWR;
-	}
+	if (page_reset_referenced(pte_val(*ptep) & PAGE_MASK))
+		pgste_val(pgste) |= PGSTE_HR_BIT | PGSTE_GR_BIT;
 #endif
 	return pgste;
 }
@@ -723,13 +748,13 @@ static inline void pgste_set_key(pte_t *ptep, pgste_t pgste, pte_t entry)
 
 static inline void pgste_set_pte(pte_t *ptep, pte_t entry)
 {
-	if (!MACHINE_HAS_ESOP && (pte_val(entry) & _PAGE_SWW)) {
+	if (!MACHINE_HAS_ESOP && (pte_val(entry) & _PAGE_WRITE)) {
 		/*
 		 * Without enhanced suppression-on-protection force
 		 * the dirty bit on for all writable ptes.
 		 */
-		pte_val(entry) |= _PAGE_SWC;
-		pte_val(entry) &= ~_PAGE_RO;
+		pte_val(entry) |= _PAGE_DIRTY;
+		pte_val(entry) &= ~_PAGE_PROTECT;
 	}
 	*ptep = entry;
 }
@@ -841,21 +866,17 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
  */
 static inline int pte_write(pte_t pte)
 {
-	return (pte_val(pte) & _PAGE_SWW) != 0;
+	return (pte_val(pte) & _PAGE_WRITE) != 0;
 }
 
 static inline int pte_dirty(pte_t pte)
 {
-	return (pte_val(pte) & _PAGE_SWC) != 0;
+	return (pte_val(pte) & _PAGE_DIRTY) != 0;
 }
 
 static inline int pte_young(pte_t pte)
 {
-#ifdef CONFIG_PGSTE
-	if (pte_val(pte) & _PAGE_SWR)
-		return 1;
-#endif
-	return 0;
+	return (pte_val(pte) & _PAGE_YOUNG) != 0;
 }
 
 /*
@@ -880,12 +901,12 @@ static inline void pud_clear(pud_t *pud)
 
 static inline void pmd_clear(pmd_t *pmdp)
 {
-	pmd_val(*pmdp) = _SEGMENT_ENTRY_EMPTY;
+	pmd_val(*pmdp) = _SEGMENT_ENTRY_INVALID;
 }
 
 static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
 {
-	pte_val(*ptep) = _PAGE_TYPE_EMPTY;
+	pte_val(*ptep) = _PAGE_INVALID;
 }
 
 /*
@@ -896,55 +917,63 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 {
 	pte_val(pte) &= _PAGE_CHG_MASK;
 	pte_val(pte) |= pgprot_val(newprot);
-	if ((pte_val(pte) & _PAGE_SWC) && (pte_val(pte) & _PAGE_SWW))
-		pte_val(pte) &= ~_PAGE_RO;
+	/*
+	 * newprot for PAGE_NONE, PAGE_READ and PAGE_WRITE has the
+	 * invalid bit set, clear it again for readable, young pages
+	 */
+	if ((pte_val(pte) & _PAGE_YOUNG) && (pte_val(pte) & _PAGE_READ))
+		pte_val(pte) &= ~_PAGE_INVALID;
+	/*
+	 * newprot for PAGE_READ and PAGE_WRITE has the page protection
+	 * bit set, clear it again for writable, dirty pages
+	 */
+	if ((pte_val(pte) & _PAGE_DIRTY) && (pte_val(pte) & _PAGE_WRITE))
+		pte_val(pte) &= ~_PAGE_PROTECT;
 	return pte;
 }
 
 static inline pte_t pte_wrprotect(pte_t pte)
 {
-	pte_val(pte) &= ~_PAGE_SWW;
-	/* Do not clobber _PAGE_TYPE_NONE pages!  */
-	if (!(pte_val(pte) & _PAGE_INVALID))
-		pte_val(pte) |= _PAGE_RO;
+	pte_val(pte) &= ~_PAGE_WRITE;
+	pte_val(pte) |= _PAGE_PROTECT;
 	return pte;
 }
 
 static inline pte_t pte_mkwrite(pte_t pte)
 {
-	pte_val(pte) |= _PAGE_SWW;
-	if (pte_val(pte) & _PAGE_SWC)
-		pte_val(pte) &= ~_PAGE_RO;
+	pte_val(pte) |= _PAGE_WRITE;
+	if (pte_val(pte) & _PAGE_DIRTY)
+		pte_val(pte) &= ~_PAGE_PROTECT;
 	return pte;
 }
 
 static inline pte_t pte_mkclean(pte_t pte)
 {
-	pte_val(pte) &= ~_PAGE_SWC;
-	/* Do not clobber _PAGE_TYPE_NONE pages!  */
-	if (!(pte_val(pte) & _PAGE_INVALID))
-		pte_val(pte) |= _PAGE_RO;
+	pte_val(pte) &= ~_PAGE_DIRTY;
+	pte_val(pte) |= _PAGE_PROTECT;
 	return pte;
 }
 
 static inline pte_t pte_mkdirty(pte_t pte)
 {
-	pte_val(pte) |= _PAGE_SWC;
-	if (pte_val(pte) & _PAGE_SWW)
-		pte_val(pte) &= ~_PAGE_RO;
+	pte_val(pte) |= _PAGE_DIRTY;
+	if (pte_val(pte) & _PAGE_WRITE)
+		pte_val(pte) &= ~_PAGE_PROTECT;
 	return pte;
 }
 
 static inline pte_t pte_mkold(pte_t pte)
 {
-#ifdef CONFIG_PGSTE
-	pte_val(pte) &= ~_PAGE_SWR;
-#endif
+	pte_val(pte) &= ~_PAGE_YOUNG;
+	pte_val(pte) |= _PAGE_INVALID;
 	return pte;
 }
 
 static inline pte_t pte_mkyoung(pte_t pte)
 {
+	pte_val(pte) |= _PAGE_YOUNG;
+	if (pte_val(pte) & _PAGE_READ)
+		pte_val(pte) &= ~_PAGE_INVALID;
 	return pte;
 }
 
@@ -957,7 +986,7 @@ static inline pte_t pte_mkspecial(pte_t pte)
 #ifdef CONFIG_HUGETLB_PAGE
 static inline pte_t pte_mkhuge(pte_t pte)
 {
-	pte_val(pte) |= (_SEGMENT_ENTRY_LARGE | _SEGMENT_ENTRY_CO);
+	pte_val(pte) |= _PAGE_LARGE;
 	return pte;
 }
 #endif
@@ -974,8 +1003,8 @@ static inline int ptep_test_and_clear_user_dirty(struct mm_struct *mm,
 	if (mm_has_pgste(mm)) {
 		pgste = pgste_get_lock(ptep);
 		pgste = pgste_update_all(ptep, pgste);
-		dirty = !!(pgste_val(pgste) & PGSTE_UC_BIT);
-		pgste_val(pgste) &= ~PGSTE_UC_BIT;
+		dirty = !!(pgste_val(pgste) & PGSTE_HC_BIT);
+		pgste_val(pgste) &= ~PGSTE_HC_BIT;
 		pgste_set_unlock(ptep, pgste);
 		return dirty;
 	}
@@ -994,59 +1023,75 @@ static inline int ptep_test_and_clear_user_young(struct mm_struct *mm,
 	if (mm_has_pgste(mm)) {
 		pgste = pgste_get_lock(ptep);
 		pgste = pgste_update_young(ptep, pgste);
-		young = !!(pgste_val(pgste) & PGSTE_UR_BIT);
-		pgste_val(pgste) &= ~PGSTE_UR_BIT;
+		young = !!(pgste_val(pgste) & PGSTE_HR_BIT);
+		pgste_val(pgste) &= ~PGSTE_HR_BIT;
 		pgste_set_unlock(ptep, pgste);
 	}
 	return young;
 }
 
+static inline void __ptep_ipte(unsigned long address, pte_t *ptep)
+{
+	if (!(pte_val(*ptep) & _PAGE_INVALID)) {
+#ifndef CONFIG_64BIT
+		/* pto must point to the start of the segment table */
+		pte_t *pto = (pte_t *) (((unsigned long) ptep) & 0x7ffffc00);
+#else
+		/* ipte in zarch mode can do the math */
+		pte_t *pto = ptep;
+#endif
+		asm volatile(
+			"	ipte	%2,%3"
+			: "=m" (*ptep) : "m" (*ptep),
+			  "a" (pto), "a" (address));
+	}
+}
+
+static inline void ptep_flush_lazy(struct mm_struct *mm,
+				   unsigned long address, pte_t *ptep)
+{
+	int active = (mm == current->active_mm) ? 1 : 0;
+
+	if (atomic_read(&mm->context.attach_count) > active)
+		__ptep_ipte(address, ptep);
+	else
+		mm->context.flush_mm = 1;
+}
+
 #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
 static inline int ptep_test_and_clear_young(struct vm_area_struct *vma,
 					    unsigned long addr, pte_t *ptep)
 {
 	pgste_t pgste;
 	pte_t pte;
+	int young;
 
 	if (mm_has_pgste(vma->vm_mm)) {
 		pgste = pgste_get_lock(ptep);
-		pgste = pgste_update_young(ptep, pgste);
-		pte = *ptep;
-		*ptep = pte_mkold(pte);
-		pgste_set_unlock(ptep, pgste);
-		return pte_young(pte);
+		pgste = pgste_ipte_notify(vma->vm_mm, addr, ptep, pgste);
 	}
-	return 0;
+
+	pte = *ptep;
+	__ptep_ipte(addr, ptep);
+	young = pte_young(pte);
+	pte = pte_mkold(pte);
+
+	if (mm_has_pgste(vma->vm_mm)) {
+		pgste_set_pte(ptep, pte);
+		pgste_set_unlock(ptep, pgste);
+	} else
+		*ptep = pte;
+
+	return young;
 }
 
 #define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH
 static inline int ptep_clear_flush_young(struct vm_area_struct *vma,
 					 unsigned long address, pte_t *ptep)
 {
-	/* No need to flush TLB
-	 * On s390 reference bits are in storage key and never in TLB
-	 * With virtualization we handle the reference bit, without we
-	 * we can simply return */
 	return ptep_test_and_clear_young(vma, address, ptep);
 }
 
-static inline void __ptep_ipte(unsigned long address, pte_t *ptep)
-{
-	if (!(pte_val(*ptep) & _PAGE_INVALID)) {
-#ifndef CONFIG_64BIT
-		/* pto must point to the start of the segment table */
-		pte_t *pto = (pte_t *) (((unsigned long) ptep) & 0x7ffffc00);
-#else
-		/* ipte in zarch mode can do the math */
-		pte_t *pto = ptep;
-#endif
-		asm volatile(
-			"	ipte	%2,%3"
-			: "=m" (*ptep) : "m" (*ptep),
-			  "a" (pto), "a" (address));
-	}
-}
-
 /*
  * This is hard to understand. ptep_get_and_clear and ptep_clear_flush
  * both clear the TLB for the unmapped pte. The reason is that
@@ -1067,16 +1112,14 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
 	pgste_t pgste;
 	pte_t pte;
 
-	mm->context.flush_mm = 1;
 	if (mm_has_pgste(mm)) {
 		pgste = pgste_get_lock(ptep);
 		pgste = pgste_ipte_notify(mm, address, ptep, pgste);
 	}
 
 	pte = *ptep;
-	if (!mm_exclusive(mm))
-		__ptep_ipte(address, ptep);
-	pte_val(*ptep) = _PAGE_TYPE_EMPTY;
+	ptep_flush_lazy(mm, address, ptep);
+	pte_val(*ptep) = _PAGE_INVALID;
 
 	if (mm_has_pgste(mm)) {
 		pgste = pgste_update_all(&pte, pgste);
@@ -1093,15 +1136,14 @@ static inline pte_t ptep_modify_prot_start(struct mm_struct *mm,
 	pgste_t pgste;
 	pte_t pte;
 
-	mm->context.flush_mm = 1;
 	if (mm_has_pgste(mm)) {
 		pgste = pgste_get_lock(ptep);
 		pgste_ipte_notify(mm, address, ptep, pgste);
 	}
 
 	pte = *ptep;
-	if (!mm_exclusive(mm))
-		__ptep_ipte(address, ptep);
+	ptep_flush_lazy(mm, address, ptep);
+	pte_val(*ptep) |= _PAGE_INVALID;
 
 	if (mm_has_pgste(mm)) {
 		pgste = pgste_update_all(&pte, pgste);
@@ -1117,7 +1159,7 @@ static inline void ptep_modify_prot_commit(struct mm_struct *mm,
 	pgste_t pgste;
 
 	if (mm_has_pgste(mm)) {
-		pgste = *(pgste_t *)(ptep + PTRS_PER_PTE);
+		pgste = pgste_get(ptep);
 		pgste_set_key(ptep, pgste, pte);
 		pgste_set_pte(ptep, pte);
 		pgste_set_unlock(ptep, pgste);
@@ -1139,7 +1181,7 @@ static inline pte_t ptep_clear_flush(struct vm_area_struct *vma,
 
 	pte = *ptep;
 	__ptep_ipte(address, ptep);
-	pte_val(*ptep) = _PAGE_TYPE_EMPTY;
+	pte_val(*ptep) = _PAGE_INVALID;
 
 	if (mm_has_pgste(vma->vm_mm)) {
 		pgste = pgste_update_all(&pte, pgste);
@@ -1163,18 +1205,17 @@ static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm,
 	pgste_t pgste;
 	pte_t pte;
 
-	if (mm_has_pgste(mm)) {
+	if (!full && mm_has_pgste(mm)) {
 		pgste = pgste_get_lock(ptep);
-		if (!full)
-			pgste = pgste_ipte_notify(mm, address, ptep, pgste);
+		pgste = pgste_ipte_notify(mm, address, ptep, pgste);
 	}
 
 	pte = *ptep;
 	if (!full)
-		__ptep_ipte(address, ptep);
-	pte_val(*ptep) = _PAGE_TYPE_EMPTY;
+		ptep_flush_lazy(mm, address, ptep);
+	pte_val(*ptep) = _PAGE_INVALID;
 
-	if (mm_has_pgste(mm)) {
+	if (!full && mm_has_pgste(mm)) {
 		pgste = pgste_update_all(&pte, pgste);
 		pgste_set_unlock(ptep, pgste);
 	}
@@ -1189,14 +1230,12 @@ static inline pte_t ptep_set_wrprotect(struct mm_struct *mm,
 	pte_t pte = *ptep;
 
 	if (pte_write(pte)) {
-		mm->context.flush_mm = 1;
 		if (mm_has_pgste(mm)) {
 			pgste = pgste_get_lock(ptep);
 			pgste = pgste_ipte_notify(mm, address, ptep, pgste);
 		}
 
-		if (!mm_exclusive(mm))
-			__ptep_ipte(address, ptep);
+		ptep_flush_lazy(mm, address, ptep);
 		pte = pte_wrprotect(pte);
 
 		if (mm_has_pgste(mm)) {
@@ -1240,7 +1279,7 @@ static inline pte_t mk_pte_phys(unsigned long physpage, pgprot_t pgprot)
 {
 	pte_t __pte;
 	pte_val(__pte) = physpage + pgprot_val(pgprot);
-	return __pte;
+	return pte_mkyoung(__pte);
 }
 
 static inline pte_t mk_pte(struct page *page, pgprot_t pgprot)
@@ -1248,10 +1287,8 @@ static inline pte_t mk_pte(struct page *page, pgprot_t pgprot)
 	unsigned long physpage = page_to_phys(page);
 	pte_t __pte = mk_pte_phys(physpage, pgprot);
 
-	if ((pte_val(__pte) & _PAGE_SWW) && PageDirty(page)) {
-		pte_val(__pte) |= _PAGE_SWC;
-		pte_val(__pte) &= ~_PAGE_RO;
-	}
+	if (pte_write(__pte) && PageDirty(page))
+		__pte = pte_mkdirty(__pte);
 	return __pte;
 }
 
@@ -1313,7 +1350,7 @@ static inline void __pmd_idte(unsigned long address, pmd_t *pmdp)
 	unsigned long sto = (unsigned long) pmdp -
 			    pmd_index(address) * sizeof(pmd_t);
 
-	if (!(pmd_val(*pmdp) & _SEGMENT_ENTRY_INV)) {
+	if (!(pmd_val(*pmdp) & _SEGMENT_ENTRY_INVALID)) {
 		asm volatile(
 			"	.insn	rrf,0xb98e0000,%2,%3,0,0"
 			: "=m" (*pmdp)
@@ -1324,24 +1361,68 @@ static inline void __pmd_idte(unsigned long address, pmd_t *pmdp)
 	}
 }
 
+static inline void __pmd_csp(pmd_t *pmdp)
+{
+	register unsigned long reg2 asm("2") = pmd_val(*pmdp);
+	register unsigned long reg3 asm("3") = pmd_val(*pmdp) |
+					       _SEGMENT_ENTRY_INVALID;
+	register unsigned long reg4 asm("4") = ((unsigned long) pmdp) + 5;
+
+	asm volatile(
+		"	csp %1,%3"
+		: "=m" (*pmdp)
+		: "d" (reg2), "d" (reg3), "d" (reg4), "m" (*pmdp) : "cc");
+}
+
 #if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLB_PAGE)
 static inline unsigned long massage_pgprot_pmd(pgprot_t pgprot)
 {
 	/*
-	 * pgprot is PAGE_NONE, PAGE_RO, or PAGE_RW (see __Pxxx / __Sxxx)
+	 * pgprot is PAGE_NONE, PAGE_READ, or PAGE_WRITE (see __Pxxx / __Sxxx)
 	 * Convert to segment table entry format.
 	 */
 	if (pgprot_val(pgprot) == pgprot_val(PAGE_NONE))
 		return pgprot_val(SEGMENT_NONE);
-	if (pgprot_val(pgprot) == pgprot_val(PAGE_RO))
-		return pgprot_val(SEGMENT_RO);
-	return pgprot_val(SEGMENT_RW);
+	if (pgprot_val(pgprot) == pgprot_val(PAGE_READ))
+		return pgprot_val(SEGMENT_READ);
+	return pgprot_val(SEGMENT_WRITE);
+}
+
+static inline pmd_t pmd_mkyoung(pmd_t pmd)
+{
+#ifdef CONFIG_64BIT
+	if (pmd_prot_none(pmd)) {
+		pmd_val(pmd) |= _SEGMENT_ENTRY_PROTECT;
+	} else {
+		pmd_val(pmd) |= _SEGMENT_ENTRY_YOUNG;
+		pmd_val(pmd) &= ~_SEGMENT_ENTRY_INVALID;
+	}
+#endif
+	return pmd;
+}
+
+static inline pmd_t pmd_mkold(pmd_t pmd)
+{
+#ifdef CONFIG_64BIT
+	if (pmd_prot_none(pmd)) {
+		pmd_val(pmd) &= ~_SEGMENT_ENTRY_PROTECT;
+	} else {
+		pmd_val(pmd) &= ~_SEGMENT_ENTRY_YOUNG;
+		pmd_val(pmd) |= _SEGMENT_ENTRY_INVALID;
+	}
+#endif
+	return pmd;
 }
 
 static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
 {
+	int young;
+
+	young = pmd_young(pmd);
 	pmd_val(pmd) &= _SEGMENT_CHG_MASK;
 	pmd_val(pmd) |= massage_pgprot_pmd(newprot);
+	if (young)
+		pmd = pmd_mkyoung(pmd);
 	return pmd;
 }
 
@@ -1349,18 +1430,29 @@ static inline pmd_t mk_pmd_phys(unsigned long physpage, pgprot_t pgprot)
 {
 	pmd_t __pmd;
 	pmd_val(__pmd) = physpage + massage_pgprot_pmd(pgprot);
-	return __pmd;
+	return pmd_mkyoung(__pmd);
 }
 
 static inline pmd_t pmd_mkwrite(pmd_t pmd)
 {
-	/* Do not clobber _HPAGE_TYPE_NONE pages! */
-	if (!(pmd_val(pmd) & _SEGMENT_ENTRY_INV))
-		pmd_val(pmd) &= ~_SEGMENT_ENTRY_RO;
+	/* Do not clobber PROT_NONE segments! */
+	if (!pmd_prot_none(pmd))
+		pmd_val(pmd) &= ~_SEGMENT_ENTRY_PROTECT;
 	return pmd;
 }
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLB_PAGE */
 
+static inline void pmdp_flush_lazy(struct mm_struct *mm,
+				   unsigned long address, pmd_t *pmdp)
+{
+	int active = (mm == current->active_mm) ? 1 : 0;
+
+	if ((atomic_read(&mm->context.attach_count) & 0xffff) > active)
+		__pmd_idte(address, pmdp);
+	else
+		mm->context.flush_mm = 1;
+}
+
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 
 #define __HAVE_ARCH_PGTABLE_DEPOSIT
@@ -1378,7 +1470,7 @@ static inline int pmd_trans_splitting(pmd_t pmd)
 static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr,
 			      pmd_t *pmdp, pmd_t entry)
 {
-	if (!(pmd_val(entry) & _SEGMENT_ENTRY_INV) && MACHINE_HAS_EDAT1)
+	if (!(pmd_val(entry) & _SEGMENT_ENTRY_INVALID) && MACHINE_HAS_EDAT1)
 		pmd_val(entry) |= _SEGMENT_ENTRY_CO;
 	*pmdp = entry;
 }
@@ -1391,7 +1483,9 @@ static inline pmd_t pmd_mkhuge(pmd_t pmd)
 
 static inline pmd_t pmd_wrprotect(pmd_t pmd)
 {
-	pmd_val(pmd) |= _SEGMENT_ENTRY_RO;
+	/* Do not clobber PROT_NONE segments! */
+	if (!pmd_prot_none(pmd))
+		pmd_val(pmd) |= _SEGMENT_ENTRY_PROTECT;
 	return pmd;
 }
 
@@ -1401,50 +1495,16 @@ static inline pmd_t pmd_mkdirty(pmd_t pmd)
 	return pmd;
 }
 
-static inline pmd_t pmd_mkold(pmd_t pmd)
-{
-	/* No referenced bit in the segment table entry. */
-	return pmd;
-}
-
-static inline pmd_t pmd_mkyoung(pmd_t pmd)
-{
-	/* No referenced bit in the segment table entry. */
-	return pmd;
-}
-
 #define __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG
 static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma,
 					    unsigned long address, pmd_t *pmdp)
 {
-	unsigned long pmd_addr = pmd_val(*pmdp) & HPAGE_MASK;
-	long tmp, rc;
-	int counter;
+	pmd_t pmd;
 
-	rc = 0;
-	if (MACHINE_HAS_RRBM) {
-		counter = PTRS_PER_PTE >> 6;
-		asm volatile(
-			"0:	.insn	rre,0xb9ae0000,%0,%3\n"	/* rrbm */
-			"	ogr	%1,%0\n"
-			"	la	%3,0(%4,%3)\n"
-			"	brct	%2,0b\n"
-			: "=&d" (tmp), "+&d" (rc), "+d" (counter),
-			  "+a" (pmd_addr)
-			: "a" (64 * 4096UL) : "cc");
-		rc = !!rc;
-	} else {
-		counter = PTRS_PER_PTE;
-		asm volatile(
-			"0:	rrbe	0,%2\n"
-			"	la	%2,0(%3,%2)\n"
-			"	brc	12,1f\n"
-			"	lhi	%0,1\n"
-			"1:	brct	%1,0b\n"
-			: "+d" (rc), "+d" (counter), "+a" (pmd_addr)
-			: "a" (4096UL) : "cc");
-	}
-	return rc;
+	pmd = *pmdp;
+	__pmd_idte(address, pmdp);
+	*pmdp = pmd_mkold(pmd);
+	return pmd_young(pmd);
 }
 
 #define __HAVE_ARCH_PMDP_GET_AND_CLEAR
@@ -1510,10 +1570,8 @@ static inline unsigned long pmd_pfn(pmd_t pmd)
  * exception will occur instead of a page translation exception. The
  * specifiation exception has the bad habit not to store necessary
  * information in the lowcore.
- * Bit 21 and bit 22 are the page invalid bit and the page protection
- * bit. We set both to indicate a swapped page.
- * Bit 30 and 31 are used to distinguish the different page types. For
- * a swapped page these bits need to be zero.
+ * Bits 21, 22, 30 and 31 are used to indicate the page type.
+ * A swap pte is indicated by bit pattern (pte & 0x603) == 0x402
  * This leaves the bits 1-19 and bits 24-29 to store type and offset.
  * We use the 5 bits from 25-29 for the type and the 20 bits from 1-19
  * plus 24 for the offset.
@@ -1527,10 +1585,8 @@ static inline unsigned long pmd_pfn(pmd_t pmd)
  * exception will occur instead of a page translation exception. The
  * specifiation exception has the bad habit not to store necessary
  * information in the lowcore.
- * Bit 53 and bit 54 are the page invalid bit and the page protection
- * bit. We set both to indicate a swapped page.
- * Bit 62 and 63 are used to distinguish the different page types. For
- * a swapped page these bits need to be zero.
+ * Bits 53, 54, 62 and 63 are used to indicate the page type.
+ * A swap pte is indicated by bit pattern (pte & 0x603) == 0x402
  * This leaves the bits 0-51 and bits 56-61 to store type and offset.
  * We use the 5 bits from 57-61 for the type and the 53 bits from 0-51
  * plus 56 for the offset.
@@ -1547,7 +1603,7 @@ static inline pte_t mk_swap_pte(unsigned long type, unsigned long offset)
 {
 	pte_t pte;
 	offset &= __SWP_OFFSET_MASK;
-	pte_val(pte) = _PAGE_TYPE_SWAP | ((type & 0x1f) << 2) |
+	pte_val(pte) = _PAGE_INVALID | _PAGE_TYPE | ((type & 0x1f) << 2) |
 		((offset & 1UL) << 7) | ((offset & ~1UL) << 11);
 	return pte;
 }
@@ -1570,7 +1626,7 @@ static inline pte_t mk_swap_pte(unsigned long type, unsigned long offset)
 
 #define pgoff_to_pte(__off) \
 	((pte_t) { ((((__off) & 0x7f) << 1) + (((__off) >> 7) << 12)) \
-		   | _PAGE_TYPE_FILE })
+		   | _PAGE_INVALID | _PAGE_PROTECT })
 
 #endif /* !__ASSEMBLY__ */
 
diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h
index b0e6435b2f02..ca7821f07260 100644
--- a/arch/s390/include/asm/processor.h
+++ b/arch/s390/include/asm/processor.h
@@ -43,6 +43,7 @@ extern void execve_tail(void);
 #ifndef CONFIG_64BIT
 
 #define TASK_SIZE		(1UL << 31)
+#define TASK_MAX_SIZE		(1UL << 31)
 #define TASK_UNMAPPED_BASE	(1UL << 30)
 
 #else /* CONFIG_64BIT */
@@ -51,6 +52,7 @@ extern void execve_tail(void);
 #define TASK_UNMAPPED_BASE	(test_thread_flag(TIF_31BIT) ? \
 					(1UL << 30) : (1UL << 41))
 #define TASK_SIZE		TASK_SIZE_OF(current)
+#define TASK_MAX_SIZE		(1UL << 53)
 
 #endif /* CONFIG_64BIT */
 
@@ -196,6 +198,8 @@ static inline void cpu_relax(void)
 	barrier();
 }
 
+#define arch_mutex_cpu_relax()  barrier()
+
 static inline void psw_set_key(unsigned int key)
 {
 	asm volatile("spka 0(%0)" : : "d" (key));
diff --git a/arch/s390/include/asm/sclp.h b/arch/s390/include/asm/sclp.h
index 06a136136047..7dc7f9c63b65 100644
--- a/arch/s390/include/asm/sclp.h
+++ b/arch/s390/include/asm/sclp.h
@@ -56,5 +56,6 @@ bool sclp_has_linemode(void);
 bool sclp_has_vt220(void);
 int sclp_pci_configure(u32 fid);
 int sclp_pci_deconfigure(u32 fid);
+int memcpy_hsa(void *dest, unsigned long src, size_t count, int mode);
 
 #endif /* _ASM_S390_SCLP_H */
diff --git a/arch/s390/include/asm/serial.h b/arch/s390/include/asm/serial.h
new file mode 100644
index 000000000000..5b3e48ef534b
--- /dev/null
+++ b/arch/s390/include/asm/serial.h
@@ -0,0 +1,6 @@
+#ifndef _ASM_S390_SERIAL_H
+#define _ASM_S390_SERIAL_H
+
+#define BASE_BAUD 0
+
+#endif /* _ASM_S390_SERIAL_H */
diff --git a/arch/s390/include/asm/spinlock.h b/arch/s390/include/asm/spinlock.h
index 701fe8c59e1f..83e5d216105e 100644
--- a/arch/s390/include/asm/spinlock.h
+++ b/arch/s390/include/asm/spinlock.h
@@ -44,6 +44,11 @@ extern void arch_spin_lock_wait_flags(arch_spinlock_t *, unsigned long flags);
 extern int arch_spin_trylock_retry(arch_spinlock_t *);
 extern void arch_spin_relax(arch_spinlock_t *lock);
 
+static inline int arch_spin_value_unlocked(arch_spinlock_t lock)
+{
+	return lock.owner_cpu == 0;
+}
+
 static inline void arch_spin_lock(arch_spinlock_t *lp)
 {
 	int old;
diff --git a/arch/s390/include/asm/switch_to.h b/arch/s390/include/asm/switch_to.h
index 80b6f11263c4..6dbd559763c9 100644
--- a/arch/s390/include/asm/switch_to.h
+++ b/arch/s390/include/asm/switch_to.h
@@ -8,6 +8,7 @@
 #define __ASM_SWITCH_TO_H
 
 #include <linux/thread_info.h>
+#include <asm/ptrace.h>
 
 extern struct task_struct *__switch_to(void *, void *);
 extern void update_cr_regs(struct task_struct *task);
@@ -68,12 +69,16 @@ static inline void restore_fp_regs(s390_fp_regs *fpregs)
 
 static inline void save_access_regs(unsigned int *acrs)
 {
-	asm volatile("stam 0,15,%0" : "=Q" (*acrs));
+	typedef struct { int _[NUM_ACRS]; } acrstype;
+
+	asm volatile("stam 0,15,%0" : "=Q" (*(acrstype *)acrs));
 }
 
 static inline void restore_access_regs(unsigned int *acrs)
 {
-	asm volatile("lam 0,15,%0" : : "Q" (*acrs));
+	typedef struct { int _[NUM_ACRS]; } acrstype;
+
+	asm volatile("lam 0,15,%0" : : "Q" (*(acrstype *)acrs));
 }
 
 #define switch_to(prev,next,last) do {					\
diff --git a/arch/s390/include/asm/tlb.h b/arch/s390/include/asm/tlb.h
index 6d6d92b4ea11..2cb846c4b37f 100644
--- a/arch/s390/include/asm/tlb.h
+++ b/arch/s390/include/asm/tlb.h
@@ -63,13 +63,14 @@ static inline void tlb_gather_mmu(struct mmu_gather *tlb,
 
 static inline void tlb_flush_mmu(struct mmu_gather *tlb)
 {
+	__tlb_flush_mm_lazy(tlb->mm);
 	tlb_table_flush(tlb);
 }
 
 static inline void tlb_finish_mmu(struct mmu_gather *tlb,
 				  unsigned long start, unsigned long end)
 {
-	tlb_table_flush(tlb);
+	tlb_flush_mmu(tlb);
 }
 
 /*
diff --git a/arch/s390/include/asm/tlbflush.h b/arch/s390/include/asm/tlbflush.h
index 6b32af30878c..f9fef0425fee 100644
--- a/arch/s390/include/asm/tlbflush.h
+++ b/arch/s390/include/asm/tlbflush.h
@@ -86,7 +86,7 @@ static inline void __tlb_flush_mm(struct mm_struct * mm)
 		__tlb_flush_full(mm);
 }
 
-static inline void __tlb_flush_mm_cond(struct mm_struct * mm)
+static inline void __tlb_flush_mm_lazy(struct mm_struct * mm)
 {
 	if (mm->context.flush_mm) {
 		__tlb_flush_mm(mm);
@@ -118,13 +118,13 @@ static inline void __tlb_flush_mm_cond(struct mm_struct * mm)
 
 static inline void flush_tlb_mm(struct mm_struct *mm)
 {
-	__tlb_flush_mm_cond(mm);
+	__tlb_flush_mm_lazy(mm);
 }
 
 static inline void flush_tlb_range(struct vm_area_struct *vma,
 				   unsigned long start, unsigned long end)
 {
-	__tlb_flush_mm_cond(vma->vm_mm);
+	__tlb_flush_mm_lazy(vma->vm_mm);
 }
 
 static inline void flush_tlb_kernel_range(unsigned long start,
diff --git a/arch/s390/include/asm/vtime.h b/arch/s390/include/asm/vtime.h
new file mode 100644
index 000000000000..af9896c53eb3
--- /dev/null
+++ b/arch/s390/include/asm/vtime.h
@@ -0,0 +1,7 @@
+#ifndef _S390_VTIME_H
+#define _S390_VTIME_H
+
+#define __ARCH_HAS_VTIME_ACCOUNT
+#define __ARCH_HAS_VTIME_TASK_SWITCH
+
+#endif /* _S390_VTIME_H */
diff --git a/arch/s390/kernel/compat_linux.c b/arch/s390/kernel/compat_linux.c
index 8b6e4f5288a2..1f1b8c70ab97 100644
--- a/arch/s390/kernel/compat_linux.c
+++ b/arch/s390/kernel/compat_linux.c
@@ -221,25 +221,26 @@ static int groups16_from_user(struct group_info *group_info, u16 __user *groupli
 
 asmlinkage long sys32_getgroups16(int gidsetsize, u16 __user *grouplist)
 {
+	const struct cred *cred = current_cred();
 	int i;
 
 	if (gidsetsize < 0)
 		return -EINVAL;
 
-	get_group_info(current->cred->group_info);
-	i = current->cred->group_info->ngroups;
+	get_group_info(cred->group_info);
+	i = cred->group_info->ngroups;
 	if (gidsetsize) {
 		if (i > gidsetsize) {
 			i = -EINVAL;
 			goto out;
 		}
-		if (groups16_to_user(grouplist, current->cred->group_info)) {
+		if (groups16_to_user(grouplist, cred->group_info)) {
 			i = -EFAULT;
 			goto out;
 		}
 	}
 out:
-	put_group_info(current->cred->group_info);
+	put_group_info(cred->group_info);
 	return i;
 }
 
diff --git a/arch/s390/kernel/compat_signal.c b/arch/s390/kernel/compat_signal.c
index c439ac9ced09..1389b637dae5 100644
--- a/arch/s390/kernel/compat_signal.c
+++ b/arch/s390/kernel/compat_signal.c
@@ -332,9 +332,9 @@ static int setup_frame32(int sig, struct k_sigaction *ka,
 	/* Set up to return from userspace.  If provided, use a stub
 	   already in userspace.  */
 	if (ka->sa.sa_flags & SA_RESTORER) {
-		regs->gprs[14] = (__u64) ka->sa.sa_restorer | PSW32_ADDR_AMODE;
+		regs->gprs[14] = (__u64 __force) ka->sa.sa_restorer | PSW32_ADDR_AMODE;
 	} else {
-		regs->gprs[14] = (__u64) frame->retcode | PSW32_ADDR_AMODE;
+		regs->gprs[14] = (__u64 __force) frame->retcode | PSW32_ADDR_AMODE;
 		if (__put_user(S390_SYSCALL_OPCODE | __NR_sigreturn,
 			       (u16 __force __user *)(frame->retcode)))
 			goto give_sigsegv;
@@ -400,9 +400,9 @@ static int setup_rt_frame32(int sig, struct k_sigaction *ka, siginfo_t *info,
 	/* Set up to return from userspace.  If provided, use a stub
 	   already in userspace.  */
 	if (ka->sa.sa_flags & SA_RESTORER) {
-		regs->gprs[14] = (__u64) ka->sa.sa_restorer | PSW32_ADDR_AMODE;
+		regs->gprs[14] = (__u64 __force) ka->sa.sa_restorer | PSW32_ADDR_AMODE;
 	} else {
-		regs->gprs[14] = (__u64) frame->retcode | PSW32_ADDR_AMODE;
+		regs->gprs[14] = (__u64 __force) frame->retcode | PSW32_ADDR_AMODE;
 		err |= __put_user(S390_SYSCALL_OPCODE | __NR_rt_sigreturn,
 				  (u16 __force __user *)(frame->retcode));
 	}
@@ -417,7 +417,7 @@ static int setup_rt_frame32(int sig, struct k_sigaction *ka, siginfo_t *info,
 	regs->psw.mask = PSW_MASK_BA |
 		(psw_user_bits & PSW_MASK_ASC) |
 		(regs->psw.mask & ~PSW_MASK_ASC);
-	regs->psw.addr = (__u64) ka->sa.sa_handler;
+	regs->psw.addr = (__u64 __force) ka->sa.sa_handler;
 
 	regs->gprs[2] = map_signal(sig);
 	regs->gprs[3] = (__force __u64) &frame->info;
diff --git a/arch/s390/kernel/crash_dump.c b/arch/s390/kernel/crash_dump.c
index d8f355657171..7dd21720e5b0 100644
--- a/arch/s390/kernel/crash_dump.c
+++ b/arch/s390/kernel/crash_dump.c
@@ -16,6 +16,7 @@
 #include <asm/os_info.h>
 #include <asm/elf.h>
 #include <asm/ipl.h>
+#include <asm/sclp.h>
 
 #define PTR_ADD(x, y) (((char *) (x)) + ((unsigned long) (y)))
 #define PTR_SUB(x, y) (((char *) (x)) - ((unsigned long) (y)))
@@ -39,47 +40,69 @@ static inline void *load_real_addr(void *addr)
 }
 
 /*
- * Copy up to one page to vmalloc or real memory
+ * Copy real to virtual or real memory
  */
-static ssize_t copy_page_real(void *buf, void *src, size_t csize)
+static int copy_from_realmem(void *dest, void *src, size_t count)
 {
-	size_t size;
+	unsigned long size;
+	int rc;
 
-	if (is_vmalloc_addr(buf)) {
-		BUG_ON(csize >= PAGE_SIZE);
-		/* If buf is not page aligned, copy first part */
-		size = min(roundup(__pa(buf), PAGE_SIZE) - __pa(buf), csize);
-		if (size) {
-			if (memcpy_real(load_real_addr(buf), src, size))
-				return -EFAULT;
-			buf += size;
-			src += size;
-		}
-		/* Copy second part */
-		size = csize - size;
-		return (size) ? memcpy_real(load_real_addr(buf), src, size) : 0;
+	if (!count)
+		return 0;
+	if (!is_vmalloc_or_module_addr(dest))
+		return memcpy_real(dest, src, count);
+	do {
+		size = min(count, PAGE_SIZE - (__pa(dest) & ~PAGE_MASK));
+		if (memcpy_real(load_real_addr(dest), src, size))
+			return -EFAULT;
+		count -= size;
+		dest += size;
+		src += size;
+	} while (count);
+	return 0;
+}
+
+/*
+ * Pointer to ELF header in new kernel
+ */
+static void *elfcorehdr_newmem;
+
+/*
+ * Copy one page from zfcpdump "oldmem"
+ *
+ * For pages below ZFCPDUMP_HSA_SIZE memory from the HSA is copied. Otherwise
+ * real memory copy is used.
+ */
+static ssize_t copy_oldmem_page_zfcpdump(char *buf, size_t csize,
+					 unsigned long src, int userbuf)
+{
+	int rc;
+
+	if (src < ZFCPDUMP_HSA_SIZE) {
+		rc = memcpy_hsa(buf, src, csize, userbuf);
 	} else {
-		return memcpy_real(buf, src, csize);
+		if (userbuf)
+			rc = copy_to_user_real((void __force __user *) buf,
+					       (void *) src, csize);
+		else
+			rc = memcpy_real(buf, (void *) src, csize);
 	}
+	return rc ? rc : csize;
 }
 
 /*
- * Copy one page from "oldmem"
+ * Copy one page from kdump "oldmem"
  *
  * For the kdump reserved memory this functions performs a swap operation:
  *  - [OLDMEM_BASE - OLDMEM_BASE + OLDMEM_SIZE] is mapped to [0 - OLDMEM_SIZE].
  *  - [0 - OLDMEM_SIZE] is mapped to [OLDMEM_BASE - OLDMEM_BASE + OLDMEM_SIZE]
  */
-ssize_t copy_oldmem_page(unsigned long pfn, char *buf,
-			 size_t csize, unsigned long offset, int userbuf)
+static ssize_t copy_oldmem_page_kdump(char *buf, size_t csize,
+				      unsigned long src, int userbuf)
+
 {
-	unsigned long src;
 	int rc;
 
-	if (!csize)
-		return 0;
-
-	src = (pfn << PAGE_SHIFT) + offset;
 	if (src < OLDMEM_SIZE)
 		src += OLDMEM_BASE;
 	else if (src > OLDMEM_BASE &&
@@ -89,8 +112,89 @@ ssize_t copy_oldmem_page(unsigned long pfn, char *buf,
 		rc = copy_to_user_real((void __force __user *) buf,
 				       (void *) src, csize);
 	else
-		rc = copy_page_real(buf, (void *) src, csize);
-	return (rc == 0) ? csize : rc;
+		rc = copy_from_realmem(buf, (void *) src, csize);
+	return (rc == 0) ? rc : csize;
+}
+
+/*
+ * Copy one page from "oldmem"
+ */
+ssize_t copy_oldmem_page(unsigned long pfn, char *buf, size_t csize,
+			 unsigned long offset, int userbuf)
+{
+	unsigned long src;
+
+	if (!csize)
+		return 0;
+	src = (pfn << PAGE_SHIFT) + offset;
+	if (OLDMEM_BASE)
+		return copy_oldmem_page_kdump(buf, csize, src, userbuf);
+	else
+		return copy_oldmem_page_zfcpdump(buf, csize, src, userbuf);
+}
+
+/*
+ * Remap "oldmem" for kdump
+ *
+ * For the kdump reserved memory this functions performs a swap operation:
+ * [0 - OLDMEM_SIZE] is mapped to [OLDMEM_BASE - OLDMEM_BASE + OLDMEM_SIZE]
+ */
+static int remap_oldmem_pfn_range_kdump(struct vm_area_struct *vma,
+					unsigned long from, unsigned long pfn,
+					unsigned long size, pgprot_t prot)
+{
+	unsigned long size_old;
+	int rc;
+
+	if (pfn < OLDMEM_SIZE >> PAGE_SHIFT) {
+		size_old = min(size, OLDMEM_SIZE - (pfn << PAGE_SHIFT));
+		rc = remap_pfn_range(vma, from,
+				     pfn + (OLDMEM_BASE >> PAGE_SHIFT),
+				     size_old, prot);
+		if (rc || size == size_old)
+			return rc;
+		size -= size_old;
+		from += size_old;
+		pfn += size_old >> PAGE_SHIFT;
+	}
+	return remap_pfn_range(vma, from, pfn, size, prot);
+}
+
+/*
+ * Remap "oldmem" for zfcpdump
+ *
+ * We only map available memory above ZFCPDUMP_HSA_SIZE. Memory below
+ * ZFCPDUMP_HSA_SIZE is read on demand using the copy_oldmem_page() function.
+ */
+static int remap_oldmem_pfn_range_zfcpdump(struct vm_area_struct *vma,
+					   unsigned long from,
+					   unsigned long pfn,
+					   unsigned long size, pgprot_t prot)
+{
+	unsigned long size_hsa;
+
+	if (pfn < ZFCPDUMP_HSA_SIZE >> PAGE_SHIFT) {
+		size_hsa = min(size, ZFCPDUMP_HSA_SIZE - (pfn << PAGE_SHIFT));
+		if (size == size_hsa)
+			return 0;
+		size -= size_hsa;
+		from += size_hsa;
+		pfn += size_hsa >> PAGE_SHIFT;
+	}
+	return remap_pfn_range(vma, from, pfn, size, prot);
+}
+
+/*
+ * Remap "oldmem" for kdump or zfcpdump
+ */
+int remap_oldmem_pfn_range(struct vm_area_struct *vma, unsigned long from,
+			   unsigned long pfn, unsigned long size, pgprot_t prot)
+{
+	if (OLDMEM_BASE)
+		return remap_oldmem_pfn_range_kdump(vma, from, pfn, size, prot);
+	else
+		return remap_oldmem_pfn_range_zfcpdump(vma, from, pfn, size,
+						       prot);
 }
 
 /*
@@ -101,13 +205,23 @@ int copy_from_oldmem(void *dest, void *src, size_t count)
 	unsigned long copied = 0;
 	int rc;
 
-	if ((unsigned long) src < OLDMEM_SIZE) {
-		copied = min(count, OLDMEM_SIZE - (unsigned long) src);
-		rc = memcpy_real(dest, src + OLDMEM_BASE, copied);
-		if (rc)
-			return rc;
+	if (OLDMEM_BASE) {
+		if ((unsigned long) src < OLDMEM_SIZE) {
+			copied = min(count, OLDMEM_SIZE - (unsigned long) src);
+			rc = copy_from_realmem(dest, src + OLDMEM_BASE, copied);
+			if (rc)
+				return rc;
+		}
+	} else {
+		if ((unsigned long) src < ZFCPDUMP_HSA_SIZE) {
+			copied = min(count,
+				     ZFCPDUMP_HSA_SIZE - (unsigned long) src);
+			rc = memcpy_hsa(dest, (unsigned long) src, copied, 0);
+			if (rc)
+				return rc;
+		}
 	}
-	return memcpy_real(dest + copied, src + copied, count - copied);
+	return copy_from_realmem(dest + copied, src + copied, count - copied);
 }
 
 /*
@@ -368,14 +482,6 @@ static int get_mem_chunk_cnt(void)
 }
 
 /*
- * Relocate pointer in order to allow vmcore code access the data
- */
-static inline unsigned long relocate(unsigned long addr)
-{
-	return OLDMEM_BASE + addr;
-}
-
-/*
  * Initialize ELF loads (new kernel)
  */
 static int loads_init(Elf64_Phdr *phdr, u64 loads_offset)
@@ -426,7 +532,7 @@ static void *notes_init(Elf64_Phdr *phdr, void *ptr, u64 notes_offset)
 	ptr = nt_vmcoreinfo(ptr);
 	memset(phdr, 0, sizeof(*phdr));
 	phdr->p_type = PT_NOTE;
-	phdr->p_offset = relocate(notes_offset);
+	phdr->p_offset = notes_offset;
 	phdr->p_filesz = (unsigned long) PTR_SUB(ptr, ptr_start);
 	phdr->p_memsz = phdr->p_filesz;
 	return ptr;
@@ -435,7 +541,7 @@ static void *notes_init(Elf64_Phdr *phdr, void *ptr, u64 notes_offset)
 /*
  * Create ELF core header (new kernel)
  */
-static void s390_elf_corehdr_create(char **elfcorebuf, size_t *elfcorebuf_sz)
+int elfcorehdr_alloc(unsigned long long *addr, unsigned long long *size)
 {
 	Elf64_Phdr *phdr_notes, *phdr_loads;
 	int mem_chunk_cnt;
@@ -443,6 +549,12 @@ static void s390_elf_corehdr_create(char **elfcorebuf, size_t *elfcorebuf_sz)
 	u32 alloc_size;
 	u64 hdr_off;
 
+	/* If we are not in kdump or zfcpdump mode return */
+	if (!OLDMEM_BASE && ipl_info.type != IPL_TYPE_FCP_DUMP)
+		return 0;
+	/* If elfcorehdr= has been passed via cmdline, we use that one */
+	if (elfcorehdr_addr != ELFCORE_ADDR_MAX)
+		return 0;
 	mem_chunk_cnt = get_mem_chunk_cnt();
 
 	alloc_size = 0x1000 + get_cpu_cnt() * 0x300 +
@@ -460,27 +572,52 @@ static void s390_elf_corehdr_create(char **elfcorebuf, size_t *elfcorebuf_sz)
 	ptr = notes_init(phdr_notes, ptr, ((unsigned long) hdr) + hdr_off);
 	/* Init loads */
 	hdr_off = PTR_DIFF(ptr, hdr);
-	loads_init(phdr_loads, ((unsigned long) hdr) + hdr_off);
-	*elfcorebuf_sz = hdr_off;
-	*elfcorebuf = (void *) relocate((unsigned long) hdr);
-	BUG_ON(*elfcorebuf_sz > alloc_size);
+	loads_init(phdr_loads, hdr_off);
+	*addr = (unsigned long long) hdr;
+	elfcorehdr_newmem = hdr;
+	*size = (unsigned long long) hdr_off;
+	BUG_ON(elfcorehdr_size > alloc_size);
+	return 0;
 }
 
 /*
- * Create kdump ELF core header in new kernel, if it has not been passed via
- * the "elfcorehdr" kernel parameter
+ * Free ELF core header (new kernel)
  */
-static int setup_kdump_elfcorehdr(void)
+void elfcorehdr_free(unsigned long long addr)
 {
-	size_t elfcorebuf_sz;
-	char *elfcorebuf;
+	if (!elfcorehdr_newmem)
+		return;
+	kfree((void *)(unsigned long)addr);
+}
 
-	if (!OLDMEM_BASE || is_kdump_kernel())
-		return -EINVAL;
-	s390_elf_corehdr_create(&elfcorebuf, &elfcorebuf_sz);
-	elfcorehdr_addr = (unsigned long long) elfcorebuf;
-	elfcorehdr_size = elfcorebuf_sz;
-	return 0;
+/*
+ * Read from ELF header
+ */
+ssize_t elfcorehdr_read(char *buf, size_t count, u64 *ppos)
+{
+	void *src = (void *)(unsigned long)*ppos;
+
+	src = elfcorehdr_newmem ? src : src - OLDMEM_BASE;
+	memcpy(buf, src, count);
+	*ppos += count;
+	return count;
 }
 
-subsys_initcall(setup_kdump_elfcorehdr);
+/*
+ * Read from ELF notes data
+ */
+ssize_t elfcorehdr_read_notes(char *buf, size_t count, u64 *ppos)
+{
+	void *src = (void *)(unsigned long)*ppos;
+	int rc;
+
+	if (elfcorehdr_newmem) {
+		memcpy(buf, src, count);
+	} else {
+		rc = copy_from_oldmem(buf, src, count);
+		if (rc)
+			return rc;
+	}
+	*ppos += count;
+	return count;
+}
diff --git a/arch/s390/kernel/dumpstack.c b/arch/s390/kernel/dumpstack.c
index 87acc38f73c6..99e7f6035895 100644
--- a/arch/s390/kernel/dumpstack.c
+++ b/arch/s390/kernel/dumpstack.c
@@ -40,14 +40,15 @@ __show_trace(unsigned long sp, unsigned long low, unsigned long high)
 {
 	struct stack_frame *sf;
 	struct pt_regs *regs;
+	unsigned long addr;
 
 	while (1) {
 		sp = sp & PSW_ADDR_INSN;
 		if (sp < low || sp > high - sizeof(*sf))
 			return sp;
 		sf = (struct stack_frame *) sp;
-		printk("([<%016lx>] ", sf->gprs[8] & PSW_ADDR_INSN);
-		print_symbol("%s)\n", sf->gprs[8] & PSW_ADDR_INSN);
+		addr = sf->gprs[8] & PSW_ADDR_INSN;
+		printk("([<%016lx>] %pSR)\n", addr, (void *)addr);
 		/* Follow the backchain. */
 		while (1) {
 			low = sp;
@@ -57,16 +58,16 @@ __show_trace(unsigned long sp, unsigned long low, unsigned long high)
 			if (sp <= low || sp > high - sizeof(*sf))
 				return sp;
 			sf = (struct stack_frame *) sp;
-			printk(" [<%016lx>] ", sf->gprs[8] & PSW_ADDR_INSN);
-			print_symbol("%s\n", sf->gprs[8] & PSW_ADDR_INSN);
+			addr = sf->gprs[8] & PSW_ADDR_INSN;
+			printk(" [<%016lx>] %pSR\n", addr, (void *)addr);
 		}
 		/* Zero backchain detected, check for interrupt frame. */
 		sp = (unsigned long) (sf + 1);
 		if (sp <= low || sp > high - sizeof(*regs))
 			return sp;
 		regs = (struct pt_regs *) sp;
-		printk(" [<%016lx>] ", regs->psw.addr & PSW_ADDR_INSN);
-		print_symbol("%s\n", regs->psw.addr & PSW_ADDR_INSN);
+		addr = regs->psw.addr & PSW_ADDR_INSN;
+		printk(" [<%016lx>] %pSR\n", addr, (void *)addr);
 		low = sp;
 		sp = regs->gprs[15];
 	}
@@ -128,8 +129,7 @@ static void show_last_breaking_event(struct pt_regs *regs)
 {
 #ifdef CONFIG_64BIT
 	printk("Last Breaking-Event-Address:\n");
-	printk(" [<%016lx>] ", regs->args[0] & PSW_ADDR_INSN);
-	print_symbol("%s\n", regs->args[0] & PSW_ADDR_INSN);
+	printk(" [<%016lx>] %pSR\n", regs->args[0], (void *)regs->args[0]);
 #endif
 }
 
@@ -143,10 +143,10 @@ void show_registers(struct pt_regs *regs)
 	char *mode;
 
 	mode = user_mode(regs) ? "User" : "Krnl";
-	printk("%s PSW : %p %p",
+	printk("%s PSW : %p %p (%pSR)\n",
 	       mode, (void *) regs->psw.mask,
+	       (void *) regs->psw.addr,
 	       (void *) regs->psw.addr);
-	print_symbol(" (%s)\n", regs->psw.addr & PSW_ADDR_INSN);
 	printk("           R:%x T:%x IO:%x EX:%x Key:%x M:%x W:%x "
 	       "P:%x AS:%x CC:%x PM:%x", mask_bits(regs, PSW_MASK_PER),
 	       mask_bits(regs, PSW_MASK_DAT), mask_bits(regs, PSW_MASK_IO),
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index be7a408be7a1..0dc2b6d0a1ec 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -18,6 +18,7 @@
 #include <asm/unistd.h>
 #include <asm/page.h>
 #include <asm/sigp.h>
+#include <asm/irq.h>
 
 __PT_R0      =	__PT_GPRS
 __PT_R1      =	__PT_GPRS + 4
@@ -265,6 +266,7 @@ sysc_sigpending:
 	tm	__TI_flags+3(%r12),_TIF_SYSCALL
 	jno	sysc_return
 	lm	%r2,%r7,__PT_R2(%r11)	# load svc arguments
+	l	%r10,__TI_sysc_table(%r12)	# 31 bit system call table
 	xr	%r8,%r8			# svc 0 returns -ENOSYS
 	clc	__PT_INT_CODE+2(2,%r11),BASED(.Lnr_syscalls+2)
 	jnl	sysc_nr_ok		# invalid svc number -> do svc 0
@@ -435,6 +437,11 @@ io_skip:
 io_loop:
 	l	%r1,BASED(.Ldo_IRQ)
 	lr	%r2,%r11		# pass pointer to pt_regs
+	lhi	%r3,IO_INTERRUPT
+	tm	__PT_INT_CODE+8(%r11),0x80	# adapter interrupt ?
+	jz	io_call
+	lhi	%r3,THIN_INTERRUPT
+io_call:
 	basr	%r14,%r1		# call do_IRQ
 	tm	__LC_MACHINE_FLAGS+2,0x10	# MACHINE_FLAG_LPAR
 	jz	io_return
@@ -584,9 +591,10 @@ ext_skip:
 	mvc	__PT_INT_CODE(4,%r11),__LC_EXT_CPU_ADDR
 	mvc	__PT_INT_PARM(4,%r11),__LC_EXT_PARAMS
 	TRACE_IRQS_OFF
+	l	%r1,BASED(.Ldo_IRQ)
 	lr	%r2,%r11		# pass pointer to pt_regs
-	l	%r1,BASED(.Ldo_extint)
-	basr	%r14,%r1		# call do_extint
+	lhi	%r3,EXT_INTERRUPT
+	basr	%r14,%r1		# call do_IRQ
 	j	io_return
 
 /*
@@ -879,13 +887,13 @@ cleanup_idle:
 	stm	%r9,%r10,__LC_SYSTEM_TIMER
 	mvc	__LC_LAST_UPDATE_TIMER(8),__TIMER_IDLE_EXIT(%r2)
 	# prepare return psw
-	n	%r8,BASED(cleanup_idle_wait)	# clear wait state bit
+	n	%r8,BASED(cleanup_idle_wait)	# clear irq & wait state bits
 	l	%r9,24(%r11)			# return from psw_idle
 	br	%r14
 cleanup_idle_insn:
 	.long	psw_idle_lpsw + 0x80000000
 cleanup_idle_wait:
-	.long	0xfffdffff
+	.long	0xfcfdffff
 
 /*
  * Integer constants
@@ -902,7 +910,6 @@ cleanup_idle_wait:
 .Ldo_machine_check:	.long	s390_do_machine_check
 .Lhandle_mcck:		.long	s390_handle_mcck
 .Ldo_IRQ:		.long	do_IRQ
-.Ldo_extint:		.long	do_extint
 .Ldo_signal:		.long	do_signal
 .Ldo_notify_resume:	.long	do_notify_resume
 .Ldo_per_trap:		.long	do_per_trap
diff --git a/arch/s390/kernel/entry.h b/arch/s390/kernel/entry.h
index 3ddbc26d246e..e9b04c33d383 100644
--- a/arch/s390/kernel/entry.h
+++ b/arch/s390/kernel/entry.h
@@ -53,27 +53,21 @@ void handle_signal32(unsigned long sig, struct k_sigaction *ka,
 		    siginfo_t *info, sigset_t *oldset, struct pt_regs *regs);
 void do_notify_resume(struct pt_regs *regs);
 
-struct ext_code;
-void do_extint(struct pt_regs *regs);
+void __init init_IRQ(void);
+void do_IRQ(struct pt_regs *regs, int irq);
 void do_restart(void);
 void __init startup_init(void);
 void die(struct pt_regs *regs, const char *str);
-
+int setup_profiling_timer(unsigned int multiplier);
 void __init time_init(void);
+int pfn_is_nosave(unsigned long);
+void s390_early_resume(void);
+unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip);
 
 struct s390_mmap_arg_struct;
 struct fadvise64_64_args;
 struct old_sigaction;
 
-long sys_mmap2(struct s390_mmap_arg_struct __user  *arg);
-long sys_s390_ipc(uint call, int first, unsigned long second,
-	     unsigned long third, void __user *ptr);
-long sys_s390_personality(unsigned int personality);
-long sys_s390_fadvise64(int fd, u32 offset_high, u32 offset_low,
-		    size_t len, int advice);
-long sys_s390_fadvise64_64(struct fadvise64_64_args __user *args);
-long sys_s390_fallocate(int fd, int mode, loff_t offset, u32 len_high,
-			u32 len_low);
 long sys_sigreturn(void);
 long sys_rt_sigreturn(void);
 long sys32_sigreturn(void);
diff --git a/arch/s390/kernel/entry64.S b/arch/s390/kernel/entry64.S
index 1c039d0c24c7..e5b43c97a834 100644
--- a/arch/s390/kernel/entry64.S
+++ b/arch/s390/kernel/entry64.S
@@ -19,6 +19,7 @@
 #include <asm/unistd.h>
 #include <asm/page.h>
 #include <asm/sigp.h>
+#include <asm/irq.h>
 
 __PT_R0      =	__PT_GPRS
 __PT_R1      =	__PT_GPRS + 8
@@ -296,6 +297,7 @@ sysc_sigpending:
 	tm	__TI_flags+7(%r12),_TIF_SYSCALL
 	jno	sysc_return
 	lmg	%r2,%r7,__PT_R2(%r11)	# load svc arguments
+	lg	%r10,__TI_sysc_table(%r12)	# address of system call table
 	lghi	%r8,0			# svc 0 returns -ENOSYS
 	llgh	%r1,__PT_INT_CODE+2(%r11)	# load new svc number
 	cghi	%r1,NR_syscalls
@@ -468,6 +470,11 @@ io_skip:
 	xc	__SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
 io_loop:
 	lgr	%r2,%r11		# pass pointer to pt_regs
+	lghi	%r3,IO_INTERRUPT
+	tm	__PT_INT_CODE+8(%r11),0x80	# adapter interrupt ?
+	jz	io_call
+	lghi	%r3,THIN_INTERRUPT
+io_call:
 	brasl	%r14,do_IRQ
 	tm	__LC_MACHINE_FLAGS+6,0x10	# MACHINE_FLAG_LPAR
 	jz	io_return
@@ -623,7 +630,8 @@ ext_skip:
 	TRACE_IRQS_OFF
 	xc	__SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
 	lgr	%r2,%r11		# pass pointer to pt_regs
-	brasl	%r14,do_extint
+	lghi	%r3,EXT_INTERRUPT
+	brasl	%r14,do_IRQ
 	j	io_return
 
 /*
@@ -922,7 +930,7 @@ cleanup_idle:
 	stg	%r9,__LC_SYSTEM_TIMER
 	mvc	__LC_LAST_UPDATE_TIMER(8),__TIMER_IDLE_EXIT(%r2)
 	# prepare return psw
-	nihh	%r8,0xfffd		# clear wait state bit
+	nihh	%r8,0xfcfd		# clear irq & wait state bits
 	lg	%r9,48(%r11)		# return from psw_idle
 	br	%r14
 cleanup_idle_insn:
diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c
index e3043aef87a9..1014ad5f7693 100644
--- a/arch/s390/kernel/ftrace.c
+++ b/arch/s390/kernel/ftrace.c
@@ -15,6 +15,7 @@
 #include <linux/kprobes.h>
 #include <trace/syscall.h>
 #include <asm/asm-offsets.h>
+#include "entry.h"
 
 #ifdef CONFIG_DYNAMIC_FTRACE
 
@@ -177,7 +178,7 @@ int ftrace_enable_ftrace_graph_caller(void)
 
 	offset = ((void *) prepare_ftrace_return -
 		  (void *) ftrace_graph_caller) / 2;
-	return probe_kernel_write(ftrace_graph_caller + 2,
+	return probe_kernel_write((void *) ftrace_graph_caller + 2,
 				  &offset, sizeof(offset));
 }
 
@@ -185,7 +186,7 @@ int ftrace_disable_ftrace_graph_caller(void)
 {
 	static unsigned short offset = 0x0002;
 
-	return probe_kernel_write(ftrace_graph_caller + 2,
+	return probe_kernel_write((void *) ftrace_graph_caller + 2,
 				  &offset, sizeof(offset));
 }
 
diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c
index 54b0995514e8..8ac2097f13d4 100644
--- a/arch/s390/kernel/irq.c
+++ b/arch/s390/kernel/irq.c
@@ -22,6 +22,7 @@
 #include <asm/cputime.h>
 #include <asm/lowcore.h>
 #include <asm/irq.h>
+#include <asm/hw_irq.h>
 #include "entry.h"
 
 DEFINE_PER_CPU_SHARED_ALIGNED(struct irq_stat, irq_stat);
@@ -42,9 +43,10 @@ struct irq_class {
  * Since the external and I/O interrupt fields are already sums we would end
  * up with having a sum which accounts each interrupt twice.
  */
-static const struct irq_class irqclass_main_desc[NR_IRQS] = {
-	[EXTERNAL_INTERRUPT] = {.name = "EXT"},
-	[IO_INTERRUPT]	     = {.name = "I/O"}
+static const struct irq_class irqclass_main_desc[NR_IRQS_BASE] = {
+	[EXT_INTERRUPT]  = {.name = "EXT"},
+	[IO_INTERRUPT]	 = {.name = "I/O"},
+	[THIN_INTERRUPT] = {.name = "AIO"},
 };
 
 /*
@@ -86,6 +88,28 @@ static const struct irq_class irqclass_sub_desc[NR_ARCH_IRQS] = {
 	[CPU_RST]    = {.name = "RST", .desc = "[CPU] CPU Restart"},
 };
 
+void __init init_IRQ(void)
+{
+	irq_reserve_irqs(0, THIN_INTERRUPT);
+	init_cio_interrupts();
+	init_airq_interrupts();
+	init_ext_interrupts();
+}
+
+void do_IRQ(struct pt_regs *regs, int irq)
+{
+	struct pt_regs *old_regs;
+
+	old_regs = set_irq_regs(regs);
+	irq_enter();
+	if (S390_lowcore.int_clock >= S390_lowcore.clock_comparator)
+		/* Serve timer interrupts first. */
+		clock_comparator_work();
+	generic_handle_irq(irq);
+	irq_exit();
+	set_irq_regs(old_regs);
+}
+
 /*
  * show_interrupts is needed by /proc/interrupts.
  */
@@ -100,27 +124,36 @@ int show_interrupts(struct seq_file *p, void *v)
 		for_each_online_cpu(cpu)
 			seq_printf(p, "CPU%d       ", cpu);
 		seq_putc(p, '\n');
+		goto out;
 	}
 	if (irq < NR_IRQS) {
+		if (irq >= NR_IRQS_BASE)
+			goto out;
 		seq_printf(p, "%s: ", irqclass_main_desc[irq].name);
 		for_each_online_cpu(cpu)
-			seq_printf(p, "%10u ", kstat_cpu(cpu).irqs[irq]);
+			seq_printf(p, "%10u ", kstat_irqs_cpu(irq, cpu));
 		seq_putc(p, '\n');
-		goto skip_arch_irqs;
+		goto out;
 	}
 	for (irq = 0; irq < NR_ARCH_IRQS; irq++) {
 		seq_printf(p, "%s: ", irqclass_sub_desc[irq].name);
 		for_each_online_cpu(cpu)
-			seq_printf(p, "%10u ", per_cpu(irq_stat, cpu).irqs[irq]);
+			seq_printf(p, "%10u ",
+				   per_cpu(irq_stat, cpu).irqs[irq]);
 		if (irqclass_sub_desc[irq].desc)
 			seq_printf(p, "  %s", irqclass_sub_desc[irq].desc);
 		seq_putc(p, '\n');
 	}
-skip_arch_irqs:
+out:
 	put_online_cpus();
 	return 0;
 }
 
+int arch_show_interrupts(struct seq_file *p, int prec)
+{
+	return 0;
+}
+
 /*
  * Switch to the asynchronous interrupt stack for softirq execution.
  */
@@ -159,41 +192,27 @@ asmlinkage void do_softirq(void)
 	local_irq_restore(flags);
 }
 
-#ifdef CONFIG_PROC_FS
-void init_irq_proc(void)
-{
-	if (proc_mkdir("irq", NULL))
-		create_prof_cpu_mask();
-}
-#endif
-
 /*
  * ext_int_hash[index] is the list head for all external interrupts that hash
  * to this index.
  */
-static struct list_head ext_int_hash[256];
+static struct hlist_head ext_int_hash[32] ____cacheline_aligned;
 
 struct ext_int_info {
 	ext_int_handler_t handler;
-	u16 code;
-	struct list_head entry;
+	struct hlist_node entry;
 	struct rcu_head rcu;
+	u16 code;
 };
 
 /* ext_int_hash_lock protects the handler lists for external interrupts */
-DEFINE_SPINLOCK(ext_int_hash_lock);
-
-static void __init init_external_interrupts(void)
-{
-	int idx;
-
-	for (idx = 0; idx < ARRAY_SIZE(ext_int_hash); idx++)
-		INIT_LIST_HEAD(&ext_int_hash[idx]);
-}
+static DEFINE_SPINLOCK(ext_int_hash_lock);
 
 static inline int ext_hash(u16 code)
 {
-	return (code + (code >> 9)) & 0xff;
+	BUILD_BUG_ON(!is_power_of_2(ARRAY_SIZE(ext_int_hash)));
+
+	return (code + (code >> 9)) & (ARRAY_SIZE(ext_int_hash) - 1);
 }
 
 int register_external_interrupt(u16 code, ext_int_handler_t handler)
@@ -210,7 +229,7 @@ int register_external_interrupt(u16 code, ext_int_handler_t handler)
 	index = ext_hash(code);
 
 	spin_lock_irqsave(&ext_int_hash_lock, flags);
-	list_add_rcu(&p->entry, &ext_int_hash[index]);
+	hlist_add_head_rcu(&p->entry, &ext_int_hash[index]);
 	spin_unlock_irqrestore(&ext_int_hash_lock, flags);
 	return 0;
 }
@@ -223,9 +242,9 @@ int unregister_external_interrupt(u16 code, ext_int_handler_t handler)
 	int index = ext_hash(code);
 
 	spin_lock_irqsave(&ext_int_hash_lock, flags);
-	list_for_each_entry_rcu(p, &ext_int_hash[index], entry) {
+	hlist_for_each_entry_rcu(p, &ext_int_hash[index], entry) {
 		if (p->code == code && p->handler == handler) {
-			list_del_rcu(&p->entry);
+			hlist_del_rcu(&p->entry);
 			kfree_rcu(p, rcu);
 		}
 	}
@@ -234,148 +253,64 @@ int unregister_external_interrupt(u16 code, ext_int_handler_t handler)
 }
 EXPORT_SYMBOL(unregister_external_interrupt);
 
-void __irq_entry do_extint(struct pt_regs *regs)
+static irqreturn_t do_ext_interrupt(int irq, void *dummy)
 {
+	struct pt_regs *regs = get_irq_regs();
 	struct ext_code ext_code;
-	struct pt_regs *old_regs;
 	struct ext_int_info *p;
 	int index;
 
-	old_regs = set_irq_regs(regs);
-	irq_enter();
-	if (S390_lowcore.int_clock >= S390_lowcore.clock_comparator) {
-		/* Serve timer interrupts first. */
-		clock_comparator_work();
-	}
-	kstat_incr_irqs_this_cpu(EXTERNAL_INTERRUPT, NULL);
 	ext_code = *(struct ext_code *) &regs->int_code;
 	if (ext_code.code != 0x1004)
 		__get_cpu_var(s390_idle).nohz_delay = 1;
 
 	index = ext_hash(ext_code.code);
 	rcu_read_lock();
-	list_for_each_entry_rcu(p, &ext_int_hash[index], entry)
-		if (likely(p->code == ext_code.code))
-			p->handler(ext_code, regs->int_parm,
-				   regs->int_parm_long);
+	hlist_for_each_entry_rcu(p, &ext_int_hash[index], entry) {
+		if (unlikely(p->code != ext_code.code))
+			continue;
+		p->handler(ext_code, regs->int_parm, regs->int_parm_long);
+	}
 	rcu_read_unlock();
-	irq_exit();
-	set_irq_regs(old_regs);
+	return IRQ_HANDLED;
 }
 
-void __init init_IRQ(void)
-{
-	init_external_interrupts();
-}
-
-static DEFINE_SPINLOCK(sc_irq_lock);
-static int sc_irq_refcount;
-
-void service_subclass_irq_register(void)
-{
-	spin_lock(&sc_irq_lock);
-	if (!sc_irq_refcount)
-		ctl_set_bit(0, 9);
-	sc_irq_refcount++;
-	spin_unlock(&sc_irq_lock);
-}
-EXPORT_SYMBOL(service_subclass_irq_register);
-
-void service_subclass_irq_unregister(void)
-{
-	spin_lock(&sc_irq_lock);
-	sc_irq_refcount--;
-	if (!sc_irq_refcount)
-		ctl_clear_bit(0, 9);
-	spin_unlock(&sc_irq_lock);
-}
-EXPORT_SYMBOL(service_subclass_irq_unregister);
-
-static DEFINE_SPINLOCK(ma_subclass_lock);
-static int ma_subclass_refcount;
-
-void measurement_alert_subclass_register(void)
-{
-	spin_lock(&ma_subclass_lock);
-	if (!ma_subclass_refcount)
-		ctl_set_bit(0, 5);
-	ma_subclass_refcount++;
-	spin_unlock(&ma_subclass_lock);
-}
-EXPORT_SYMBOL(measurement_alert_subclass_register);
-
-void measurement_alert_subclass_unregister(void)
-{
-	spin_lock(&ma_subclass_lock);
-	ma_subclass_refcount--;
-	if (!ma_subclass_refcount)
-		ctl_clear_bit(0, 5);
-	spin_unlock(&ma_subclass_lock);
-}
-EXPORT_SYMBOL(measurement_alert_subclass_unregister);
-
-#ifdef CONFIG_SMP
-void synchronize_irq(unsigned int irq)
-{
-	/*
-	 * Not needed, the handler is protected by a lock and IRQs that occur
-	 * after the handler is deleted are just NOPs.
-	 */
-}
-EXPORT_SYMBOL_GPL(synchronize_irq);
-#endif
-
-#ifndef CONFIG_PCI
-
-/* Only PCI devices have dynamically-defined IRQ handlers */
-
-int request_irq(unsigned int irq, irq_handler_t handler,
-		unsigned long irqflags, const char *devname, void *dev_id)
-{
-	return -EINVAL;
-}
-EXPORT_SYMBOL_GPL(request_irq);
-
-void free_irq(unsigned int irq, void *dev_id)
-{
-	WARN_ON(1);
-}
-EXPORT_SYMBOL_GPL(free_irq);
-
-void enable_irq(unsigned int irq)
-{
-	WARN_ON(1);
-}
-EXPORT_SYMBOL_GPL(enable_irq);
+static struct irqaction external_interrupt = {
+	.name	 = "EXT",
+	.handler = do_ext_interrupt,
+};
 
-void disable_irq(unsigned int irq)
+void __init init_ext_interrupts(void)
 {
-	WARN_ON(1);
-}
-EXPORT_SYMBOL_GPL(disable_irq);
+	int idx;
 
-#endif /* !CONFIG_PCI */
+	for (idx = 0; idx < ARRAY_SIZE(ext_int_hash); idx++)
+		INIT_HLIST_HEAD(&ext_int_hash[idx]);
 
-void disable_irq_nosync(unsigned int irq)
-{
-	disable_irq(irq);
+	irq_set_chip_and_handler(EXT_INTERRUPT,
+				 &dummy_irq_chip, handle_percpu_irq);
+	setup_irq(EXT_INTERRUPT, &external_interrupt);
 }
-EXPORT_SYMBOL_GPL(disable_irq_nosync);
 
-unsigned long probe_irq_on(void)
-{
-	return 0;
-}
-EXPORT_SYMBOL_GPL(probe_irq_on);
+static DEFINE_SPINLOCK(irq_subclass_lock);
+static unsigned char irq_subclass_refcount[64];
 
-int probe_irq_off(unsigned long val)
+void irq_subclass_register(enum irq_subclass subclass)
 {
-	return 0;
+	spin_lock(&irq_subclass_lock);
+	if (!irq_subclass_refcount[subclass])
+		ctl_set_bit(0, subclass);
+	irq_subclass_refcount[subclass]++;
+	spin_unlock(&irq_subclass_lock);
 }
-EXPORT_SYMBOL_GPL(probe_irq_off);
+EXPORT_SYMBOL(irq_subclass_register);
 
-unsigned int probe_irq_mask(unsigned long val)
+void irq_subclass_unregister(enum irq_subclass subclass)
 {
-	return val;
+	spin_lock(&irq_subclass_lock);
+	irq_subclass_refcount[subclass]--;
+	if (!irq_subclass_refcount[subclass])
+		ctl_clear_bit(0, subclass);
+	spin_unlock(&irq_subclass_lock);
 }
-EXPORT_SYMBOL_GPL(probe_irq_mask);
+EXPORT_SYMBOL(irq_subclass_unregister);
diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c
index 3388b2b2a07d..d86e64eddb42 100644
--- a/arch/s390/kernel/kprobes.c
+++ b/arch/s390/kernel/kprobes.c
@@ -37,6 +37,26 @@ DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);
 
 struct kretprobe_blackpoint kretprobe_blacklist[] = { };
 
+DEFINE_INSN_CACHE_OPS(dmainsn);
+
+static void *alloc_dmainsn_page(void)
+{
+	return (void *)__get_free_page(GFP_KERNEL | GFP_DMA);
+}
+
+static void free_dmainsn_page(void *page)
+{
+	free_page((unsigned long)page);
+}
+
+struct kprobe_insn_cache kprobe_dmainsn_slots = {
+	.mutex = __MUTEX_INITIALIZER(kprobe_dmainsn_slots.mutex),
+	.alloc = alloc_dmainsn_page,
+	.free = free_dmainsn_page,
+	.pages = LIST_HEAD_INIT(kprobe_dmainsn_slots.pages),
+	.insn_size = MAX_INSN_SIZE,
+};
+
 static int __kprobes is_prohibited_opcode(kprobe_opcode_t *insn)
 {
 	switch (insn[0] >> 8) {
@@ -47,6 +67,11 @@ static int __kprobes is_prohibited_opcode(kprobe_opcode_t *insn)
 	case 0xac:	/* stnsm */
 	case 0xad:	/* stosm */
 		return -EINVAL;
+	case 0xc6:
+		switch (insn[0] & 0x0f) {
+		case 0x00: /* exrl   */
+			return -EINVAL;
+		}
 	}
 	switch (insn[0]) {
 	case 0x0101:	/* pr	 */
@@ -100,35 +125,160 @@ static int __kprobes get_fixup_type(kprobe_opcode_t *insn)
 			fixup |= FIXUP_RETURN_REGISTER;
 		break;
 	case 0xc0:
-		if ((insn[0] & 0x0f) == 0x00 ||	/* larl  */
-		    (insn[0] & 0x0f) == 0x05)	/* brasl */
-		fixup |= FIXUP_RETURN_REGISTER;
+		if ((insn[0] & 0x0f) == 0x05)	/* brasl */
+			fixup |= FIXUP_RETURN_REGISTER;
 		break;
 	case 0xeb:
-		if ((insn[2] & 0xff) == 0x44 ||	/* bxhg  */
-		    (insn[2] & 0xff) == 0x45)	/* bxleg */
+		switch (insn[2] & 0xff) {
+		case 0x44: /* bxhg  */
+		case 0x45: /* bxleg */
 			fixup = FIXUP_BRANCH_NOT_TAKEN;
+			break;
+		}
 		break;
 	case 0xe3:	/* bctg	*/
 		if ((insn[2] & 0xff) == 0x46)
 			fixup = FIXUP_BRANCH_NOT_TAKEN;
 		break;
+	case 0xec:
+		switch (insn[2] & 0xff) {
+		case 0xe5: /* clgrb */
+		case 0xe6: /* cgrb  */
+		case 0xf6: /* crb   */
+		case 0xf7: /* clrb  */
+		case 0xfc: /* cgib  */
+		case 0xfd: /* cglib */
+		case 0xfe: /* cib   */
+		case 0xff: /* clib  */
+			fixup = FIXUP_BRANCH_NOT_TAKEN;
+			break;
+		}
+		break;
 	}
 	return fixup;
 }
 
+static int __kprobes is_insn_relative_long(kprobe_opcode_t *insn)
+{
+	/* Check if we have a RIL-b or RIL-c format instruction which
+	 * we need to modify in order to avoid instruction emulation. */
+	switch (insn[0] >> 8) {
+	case 0xc0:
+		if ((insn[0] & 0x0f) == 0x00) /* larl */
+			return true;
+		break;
+	case 0xc4:
+		switch (insn[0] & 0x0f) {
+		case 0x02: /* llhrl  */
+		case 0x04: /* lghrl  */
+		case 0x05: /* lhrl   */
+		case 0x06: /* llghrl */
+		case 0x07: /* sthrl  */
+		case 0x08: /* lgrl   */
+		case 0x0b: /* stgrl  */
+		case 0x0c: /* lgfrl  */
+		case 0x0d: /* lrl    */
+		case 0x0e: /* llgfrl */
+		case 0x0f: /* strl   */
+			return true;
+		}
+		break;
+	case 0xc6:
+		switch (insn[0] & 0x0f) {
+		case 0x02: /* pfdrl  */
+		case 0x04: /* cghrl  */
+		case 0x05: /* chrl   */
+		case 0x06: /* clghrl */
+		case 0x07: /* clhrl  */
+		case 0x08: /* cgrl   */
+		case 0x0a: /* clgrl  */
+		case 0x0c: /* cgfrl  */
+		case 0x0d: /* crl    */
+		case 0x0e: /* clgfrl */
+		case 0x0f: /* clrl   */
+			return true;
+		}
+		break;
+	}
+	return false;
+}
+
+static void __kprobes copy_instruction(struct kprobe *p)
+{
+	s64 disp, new_disp;
+	u64 addr, new_addr;
+
+	memcpy(p->ainsn.insn, p->addr, ((p->opcode >> 14) + 3) & -2);
+	if (!is_insn_relative_long(p->ainsn.insn))
+		return;
+	/*
+	 * For pc-relative instructions in RIL-b or RIL-c format patch the
+	 * RI2 displacement field. We have already made sure that the insn
+	 * slot for the patched instruction is within the same 2GB area
+	 * as the original instruction (either kernel image or module area).
+	 * Therefore the new displacement will always fit.
+	 */
+	disp = *(s32 *)&p->ainsn.insn[1];
+	addr = (u64)(unsigned long)p->addr;
+	new_addr = (u64)(unsigned long)p->ainsn.insn;
+	new_disp = ((addr + (disp * 2)) - new_addr) / 2;
+	*(s32 *)&p->ainsn.insn[1] = new_disp;
+}
+
+static inline int is_kernel_addr(void *addr)
+{
+	return addr < (void *)_end;
+}
+
+static inline int is_module_addr(void *addr)
+{
+#ifdef CONFIG_64BIT
+	BUILD_BUG_ON(MODULES_LEN > (1UL << 31));
+	if (addr < (void *)MODULES_VADDR)
+		return 0;
+	if (addr > (void *)MODULES_END)
+		return 0;
+#endif
+	return 1;
+}
+
+static int __kprobes s390_get_insn_slot(struct kprobe *p)
+{
+	/*
+	 * Get an insn slot that is within the same 2GB area like the original
+	 * instruction. That way instructions with a 32bit signed displacement
+	 * field can be patched and executed within the insn slot.
+	 */
+	p->ainsn.insn = NULL;
+	if (is_kernel_addr(p->addr))
+		p->ainsn.insn = get_dmainsn_slot();
+	if (is_module_addr(p->addr))
+		p->ainsn.insn = get_insn_slot();
+	return p->ainsn.insn ? 0 : -ENOMEM;
+}
+
+static void __kprobes s390_free_insn_slot(struct kprobe *p)
+{
+	if (!p->ainsn.insn)
+		return;
+	if (is_kernel_addr(p->addr))
+		free_dmainsn_slot(p->ainsn.insn, 0);
+	else
+		free_insn_slot(p->ainsn.insn, 0);
+	p->ainsn.insn = NULL;
+}
+
 int __kprobes arch_prepare_kprobe(struct kprobe *p)
 {
 	if ((unsigned long) p->addr & 0x01)
 		return -EINVAL;
-
 	/* Make sure the probe isn't going on a difficult instruction */
 	if (is_prohibited_opcode(p->addr))
 		return -EINVAL;
-
+	if (s390_get_insn_slot(p))
+		return -ENOMEM;
 	p->opcode = *p->addr;
-	memcpy(p->ainsn.insn, p->addr, ((p->opcode >> 14) + 3) & -2);
-
+	copy_instruction(p);
 	return 0;
 }
 
@@ -169,6 +319,7 @@ void __kprobes arch_disarm_kprobe(struct kprobe *p)
 
 void __kprobes arch_remove_kprobe(struct kprobe *p)
 {
+	s390_free_insn_slot(p);
 }
 
 static void __kprobes enable_singlestep(struct kprobe_ctlblk *kcb,
diff --git a/arch/s390/kernel/machine_kexec.c b/arch/s390/kernel/machine_kexec.c
index ac2178161ec3..719e27b2cf22 100644
--- a/arch/s390/kernel/machine_kexec.c
+++ b/arch/s390/kernel/machine_kexec.c
@@ -50,7 +50,7 @@ static void add_elf_notes(int cpu)
 /*
  * Initialize CPU ELF notes
  */
-void setup_regs(void)
+static void setup_regs(void)
 {
 	unsigned long sa = S390_lowcore.prefixreg_save_area + SAVE_AREA_BASE;
 	int cpu, this_cpu;
diff --git a/arch/s390/kernel/nmi.c b/arch/s390/kernel/nmi.c
index 504175ebf8b0..c4c033819879 100644
--- a/arch/s390/kernel/nmi.c
+++ b/arch/s390/kernel/nmi.c
@@ -214,10 +214,7 @@ static int notrace s390_revalidate_registers(struct mci *mci)
 			: "0", "cc");
 #endif
 	/* Revalidate clock comparator register */
-	if (S390_lowcore.clock_comparator == -1)
-		set_clock_comparator(S390_lowcore.mcck_clock);
-	else
-		set_clock_comparator(S390_lowcore.clock_comparator);
+	set_clock_comparator(S390_lowcore.clock_comparator);
 	/* Check if old PSW is valid */
 	if (!mci->wp)
 		/*
diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c
index fb99c2057b85..1105502bf6e9 100644
--- a/arch/s390/kernel/perf_cpum_cf.c
+++ b/arch/s390/kernel/perf_cpum_cf.c
@@ -274,7 +274,7 @@ static int reserve_pmc_hardware(void)
 	int flags = PMC_INIT;
 
 	on_each_cpu(setup_pmc_cpu, &flags, 1);
-	measurement_alert_subclass_register();
+	irq_subclass_register(IRQ_SUBCLASS_MEASUREMENT_ALERT);
 
 	return 0;
 }
@@ -285,7 +285,7 @@ static void release_pmc_hardware(void)
 	int flags = PMC_RELEASE;
 
 	on_each_cpu(setup_pmc_cpu, &flags, 1);
-	measurement_alert_subclass_unregister();
+	irq_subclass_unregister(IRQ_SUBCLASS_MEASUREMENT_ALERT);
 }
 
 /* Release the PMU if event is the last perf event */
diff --git a/arch/s390/kernel/perf_event.c b/arch/s390/kernel/perf_event.c
index 500aa1029bcb..2343c218b8f9 100644
--- a/arch/s390/kernel/perf_event.c
+++ b/arch/s390/kernel/perf_event.c
@@ -105,13 +105,10 @@ void perf_event_print_debug(void)
 
 	cpu = smp_processor_id();
 	memset(&cf_info, 0, sizeof(cf_info));
-	if (!qctri(&cf_info)) {
+	if (!qctri(&cf_info))
 		pr_info("CPU[%i] CPUM_CF: ver=%u.%u A=%04x E=%04x C=%04x\n",
 			cpu, cf_info.cfvn, cf_info.csvn,
 			cf_info.auth_ctl, cf_info.enable_ctl, cf_info.act_ctl);
-		print_hex_dump_bytes("CPUMF Query: ", DUMP_PREFIX_OFFSET,
-				     &cf_info, sizeof(cf_info));
-	}
 
 	local_irq_restore(flags);
 }
diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c
index 2bc3eddae34a..c5dbb335716d 100644
--- a/arch/s390/kernel/process.c
+++ b/arch/s390/kernel/process.c
@@ -71,6 +71,7 @@ void arch_cpu_idle(void)
 	}
 	/* Halt the cpu and keep track of cpu time accounting. */
 	vtime_stop_cpu();
+	local_irq_enable();
 }
 
 void arch_cpu_idle_exit(void)
diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c
index e9fadb04e3c6..9556905bd3ce 100644
--- a/arch/s390/kernel/ptrace.c
+++ b/arch/s390/kernel/ptrace.c
@@ -60,11 +60,11 @@ void update_cr_regs(struct task_struct *task)
 
 		__ctl_store(cr, 0, 2);
 		cr_new[1] = cr[1];
-		/* Set or clear transaction execution TXC/PIFO bits 8 and 9. */
+		/* Set or clear transaction execution TXC bit 8. */
 		if (task->thread.per_flags & PER_FLAG_NO_TE)
-			cr_new[0] = cr[0] & ~(3UL << 54);
+			cr_new[0] = cr[0] & ~(1UL << 55);
 		else
-			cr_new[0] = cr[0] | (3UL << 54);
+			cr_new[0] = cr[0] | (1UL << 55);
 		/* Set or clear transaction execution TDC bits 62 and 63. */
 		cr_new[2] = cr[2] & ~3UL;
 		if (task->thread.per_flags & PER_FLAG_TE_ABORT_RAND) {
@@ -1299,7 +1299,7 @@ int regs_query_register_offset(const char *name)
 
 	if (!name || *name != 'r')
 		return -EINVAL;
-	if (strict_strtoul(name + 1, 10, &offset))
+	if (kstrtoul(name + 1, 10, &offset))
 		return -EINVAL;
 	if (offset >= NUM_GPRS)
 		return -EINVAL;
diff --git a/arch/s390/kernel/runtime_instr.c b/arch/s390/kernel/runtime_instr.c
index 077a99389b07..e1c9d1c292fa 100644
--- a/arch/s390/kernel/runtime_instr.c
+++ b/arch/s390/kernel/runtime_instr.c
@@ -139,10 +139,10 @@ static int __init runtime_instr_init(void)
 	if (!runtime_instr_avail())
 		return 0;
 
-	measurement_alert_subclass_register();
+	irq_subclass_register(IRQ_SUBCLASS_MEASUREMENT_ALERT);
 	rc = register_external_interrupt(0x1407, runtime_instr_int_handler);
 	if (rc)
-		measurement_alert_subclass_unregister();
+		irq_subclass_unregister(IRQ_SUBCLASS_MEASUREMENT_ALERT);
 	else
 		pr_info("Runtime instrumentation facility initialized\n");
 	return rc;
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index d386c4e9d2e5..1a4313a1b60f 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -362,7 +362,7 @@ void smp_yield_cpu(int cpu)
  * Send cpus emergency shutdown signal. This gives the cpus the
  * opportunity to complete outstanding interrupts.
  */
-void smp_emergency_stop(cpumask_t *cpumask)
+static void smp_emergency_stop(cpumask_t *cpumask)
 {
 	u64 end;
 	int cpu;
diff --git a/arch/s390/kernel/suspend.c b/arch/s390/kernel/suspend.c
index c479d2f9605b..a7a7537ce1e7 100644
--- a/arch/s390/kernel/suspend.c
+++ b/arch/s390/kernel/suspend.c
@@ -10,6 +10,10 @@
 #include <linux/suspend.h>
 #include <linux/mm.h>
 #include <asm/ctl_reg.h>
+#include <asm/ipl.h>
+#include <asm/cio.h>
+#include <asm/pci.h>
+#include "entry.h"
 
 /*
  * References to section boundaries
@@ -211,3 +215,11 @@ void restore_processor_state(void)
 	__ctl_set_bit(0,28);
 	local_mcck_enable();
 }
+
+/* Called at the end of swsusp_arch_resume */
+void s390_early_resume(void)
+{
+	lgr_info_log();
+	channel_subsystem_reinit();
+	zpci_rescan();
+}
diff --git a/arch/s390/kernel/swsusp_asm64.S b/arch/s390/kernel/swsusp_asm64.S
index c487be4cfc81..6b09fdffbd2f 100644
--- a/arch/s390/kernel/swsusp_asm64.S
+++ b/arch/s390/kernel/swsusp_asm64.S
@@ -281,11 +281,8 @@ restore_registers:
 	lghi	%r2,0
 	brasl	%r14,arch_set_page_states
 
-	/* Log potential guest relocation */
-	brasl	%r14,lgr_info_log
-
-	/* Reinitialize the channel subsystem */
-	brasl	%r14,channel_subsystem_reinit
+	/* Call arch specific early resume code */
+	brasl	%r14,s390_early_resume
 
 	/* Return 0 */
 	lmg	%r6,%r15,STACK_FRAME_OVERHEAD + __SF_GPRS(%r15)
diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c
index 876546b9cfa1..064c3082ab33 100644
--- a/arch/s390/kernel/time.c
+++ b/arch/s390/kernel/time.c
@@ -92,7 +92,6 @@ void clock_comparator_work(void)
 	struct clock_event_device *cd;
 
 	S390_lowcore.clock_comparator = -1ULL;
-	set_clock_comparator(S390_lowcore.clock_comparator);
 	cd = &__get_cpu_var(comparators);
 	cd->event_handler(cd);
 }
diff --git a/arch/s390/kernel/vdso.c b/arch/s390/kernel/vdso.c
index d7776281cb60..05d75c413137 100644
--- a/arch/s390/kernel/vdso.c
+++ b/arch/s390/kernel/vdso.c
@@ -63,7 +63,7 @@ static int __init vdso_setup(char *s)
 	else if (strncmp(s, "off", 4) == 0)
 		vdso_enabled = 0;
 	else {
-		rc = strict_strtoul(s, 0, &val);
+		rc = kstrtoul(s, 0, &val);
 		vdso_enabled = rc ? 0 : !!val;
 	}
 	return !rc;
@@ -113,11 +113,11 @@ int vdso_alloc_per_cpu(struct _lowcore *lowcore)
 
 	clear_table((unsigned long *) segment_table, _SEGMENT_ENTRY_EMPTY,
 		    PAGE_SIZE << SEGMENT_ORDER);
-	clear_table((unsigned long *) page_table, _PAGE_TYPE_EMPTY,
+	clear_table((unsigned long *) page_table, _PAGE_INVALID,
 		    256*sizeof(unsigned long));
 
 	*(unsigned long *) segment_table = _SEGMENT_ENTRY + page_table;
-	*(unsigned long *) page_table = _PAGE_RO + page_frame;
+	*(unsigned long *) page_table = _PAGE_PROTECT + page_frame;
 
 	psal = (u32 *) (page_table + 256*sizeof(unsigned long));
 	aste = psal + 32;
diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c
index 9b9c1b78ec67..abcfab55f99b 100644
--- a/arch/s390/kernel/vtime.c
+++ b/arch/s390/kernel/vtime.c
@@ -19,6 +19,7 @@
 #include <asm/irq_regs.h>
 #include <asm/cputime.h>
 #include <asm/vtimer.h>
+#include <asm/vtime.h>
 #include <asm/irq.h>
 #include "entry.h"
 
diff --git a/arch/s390/kvm/diag.c b/arch/s390/kvm/diag.c
index 3074475c8ae0..3a74d8af0d69 100644
--- a/arch/s390/kvm/diag.c
+++ b/arch/s390/kvm/diag.c
@@ -119,12 +119,21 @@ static int __diag_virtio_hypercall(struct kvm_vcpu *vcpu)
 	 * The layout is as follows:
 	 * - gpr 2 contains the subchannel id (passed as addr)
 	 * - gpr 3 contains the virtqueue index (passed as datamatch)
+	 * - gpr 4 contains the index on the bus (optionally)
 	 */
-	ret = kvm_io_bus_write(vcpu->kvm, KVM_VIRTIO_CCW_NOTIFY_BUS,
-				vcpu->run->s.regs.gprs[2],
-				8, &vcpu->run->s.regs.gprs[3]);
+	ret = kvm_io_bus_write_cookie(vcpu->kvm, KVM_VIRTIO_CCW_NOTIFY_BUS,
+				      vcpu->run->s.regs.gprs[2],
+				      8, &vcpu->run->s.regs.gprs[3],
+				      vcpu->run->s.regs.gprs[4]);
 	srcu_read_unlock(&vcpu->kvm->srcu, idx);
-	/* kvm_io_bus_write returns -EOPNOTSUPP if it found no match. */
+
+	/*
+	 * Return cookie in gpr 2, but don't overwrite the register if the
+	 * diagnose will be handled by userspace.
+	 */
+	if (ret != -EOPNOTSUPP)
+		vcpu->run->s.regs.gprs[2] = ret;
+	/* kvm_io_bus_write_cookie returns -EOPNOTSUPP if it found no match. */
 	return ret < 0 ? ret : 0;
 }
 
diff --git a/arch/s390/kvm/gaccess.h b/arch/s390/kvm/gaccess.h
index 302e0e52b009..99d789e8a018 100644
--- a/arch/s390/kvm/gaccess.h
+++ b/arch/s390/kvm/gaccess.h
@@ -42,9 +42,11 @@ static inline void __user *__gptr_to_uptr(struct kvm_vcpu *vcpu,
 ({								\
 	__typeof__(gptr) __uptr = __gptr_to_uptr(vcpu, gptr, 1);\
 	int __mask = sizeof(__typeof__(*(gptr))) - 1;		\
-	int __ret = PTR_RET((void __force *)__uptr);		\
+	int __ret;						\
 								\
-	if (!__ret) {						\
+	if (IS_ERR((void __force *)__uptr)) {			\
+		__ret = PTR_ERR((void __force *)__uptr);	\
+	} else {						\
 		BUG_ON((unsigned long)__uptr & __mask);		\
 		__ret = get_user(x, __uptr);			\
 	}							\
@@ -55,9 +57,11 @@ static inline void __user *__gptr_to_uptr(struct kvm_vcpu *vcpu,
 ({								\
 	__typeof__(gptr) __uptr = __gptr_to_uptr(vcpu, gptr, 1);\
 	int __mask = sizeof(__typeof__(*(gptr))) - 1;		\
-	int __ret = PTR_RET((void __force *)__uptr);		\
+	int __ret;						\
 								\
-	if (!__ret) {						\
+	if (IS_ERR((void __force *)__uptr)) {			\
+		__ret = PTR_ERR((void __force *)__uptr);	\
+	} else {						\
 		BUG_ON((unsigned long)__uptr & __mask);		\
 		__ret = put_user(x, __uptr);			\
 	}							\
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 34c1c9a90be2..776dafe918db 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -28,6 +28,7 @@
 #include <asm/pgtable.h>
 #include <asm/nmi.h>
 #include <asm/switch_to.h>
+#include <asm/facility.h>
 #include <asm/sclp.h>
 #include "kvm-s390.h"
 #include "gaccess.h"
@@ -84,9 +85,15 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 	{ NULL }
 };
 
-static unsigned long long *facilities;
+unsigned long *vfacilities;
 static struct gmap_notifier gmap_notifier;
 
+/* test availability of vfacility */
+static inline int test_vfacility(unsigned long nr)
+{
+	return __test_facility(nr, (void *) vfacilities);
+}
+
 /* Section: not file related */
 int kvm_arch_hardware_enable(void *garbage)
 {
@@ -387,7 +394,7 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 	vcpu->arch.sie_block->ecb   = 6;
 	vcpu->arch.sie_block->ecb2  = 8;
 	vcpu->arch.sie_block->eca   = 0xC1002001U;
-	vcpu->arch.sie_block->fac   = (int) (long) facilities;
+	vcpu->arch.sie_block->fac   = (int) (long) vfacilities;
 	hrtimer_init(&vcpu->arch.ckc_timer, CLOCK_REALTIME, HRTIMER_MODE_ABS);
 	tasklet_init(&vcpu->arch.tasklet, kvm_s390_tasklet,
 		     (unsigned long) vcpu);
@@ -1063,6 +1070,10 @@ int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages)
 	return 0;
 }
 
+void kvm_arch_memslots_updated(struct kvm *kvm)
+{
+}
+
 /* Section: memory related */
 int kvm_arch_prepare_memory_region(struct kvm *kvm,
 				   struct kvm_memory_slot *memslot,
@@ -1129,20 +1140,20 @@ static int __init kvm_s390_init(void)
 	 * to hold the maximum amount of facilities. On the other hand, we
 	 * only set facilities that are known to work in KVM.
 	 */
-	facilities = (unsigned long long *) get_zeroed_page(GFP_KERNEL|GFP_DMA);
-	if (!facilities) {
+	vfacilities = (unsigned long *) get_zeroed_page(GFP_KERNEL|GFP_DMA);
+	if (!vfacilities) {
 		kvm_exit();
 		return -ENOMEM;
 	}
-	memcpy(facilities, S390_lowcore.stfle_fac_list, 16);
-	facilities[0] &= 0xff82fff3f47c0000ULL;
-	facilities[1] &= 0x001c000000000000ULL;
+	memcpy(vfacilities, S390_lowcore.stfle_fac_list, 16);
+	vfacilities[0] &= 0xff82fff3f47c0000UL;
+	vfacilities[1] &= 0x001c000000000000UL;
 	return 0;
 }
 
 static void __exit kvm_s390_exit(void)
 {
-	free_page((unsigned long) facilities);
+	free_page((unsigned long) vfacilities);
 	kvm_exit();
 }
 
diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
index 028ca9fd2158..dc99f1ca4267 100644
--- a/arch/s390/kvm/kvm-s390.h
+++ b/arch/s390/kvm/kvm-s390.h
@@ -24,6 +24,9 @@
 
 typedef int (*intercept_handler_t)(struct kvm_vcpu *vcpu);
 
+/* declare vfacilities extern */
+extern unsigned long *vfacilities;
+
 /* negativ values are error codes, positive values for internal conditions */
 #define SIE_INTERCEPT_RERUNVCPU		(1<<0)
 #define SIE_INTERCEPT_UCONTROL		(1<<1)
@@ -112,6 +115,13 @@ static inline u64 kvm_s390_get_base_disp_rs(struct kvm_vcpu *vcpu)
 	return (base2 ? vcpu->run->s.regs.gprs[base2] : 0) + disp2;
 }
 
+/* Set the condition code in the guest program status word */
+static inline void kvm_s390_set_psw_cc(struct kvm_vcpu *vcpu, unsigned long cc)
+{
+	vcpu->arch.sie_block->gpsw.mask &= ~(3UL << 44);
+	vcpu->arch.sie_block->gpsw.mask |= cc << 44;
+}
+
 int kvm_s390_handle_wait(struct kvm_vcpu *vcpu);
 enum hrtimer_restart kvm_s390_idle_wakeup(struct hrtimer *timer);
 void kvm_s390_tasklet(unsigned long parm);
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index 4cdc54e63ebc..59200ee275e5 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -164,8 +164,7 @@ static int handle_tpi(struct kvm_vcpu *vcpu)
 	kfree(inti);
 no_interrupt:
 	/* Set condition code and we're done. */
-	vcpu->arch.sie_block->gpsw.mask &= ~(3ul << 44);
-	vcpu->arch.sie_block->gpsw.mask |= (cc & 3ul) << 44;
+	kvm_s390_set_psw_cc(vcpu, cc);
 	return 0;
 }
 
@@ -220,15 +219,13 @@ static int handle_io_inst(struct kvm_vcpu *vcpu)
 		 * Set condition code 3 to stop the guest from issueing channel
 		 * I/O instructions.
 		 */
-		vcpu->arch.sie_block->gpsw.mask &= ~(3ul << 44);
-		vcpu->arch.sie_block->gpsw.mask |= (3 & 3ul) << 44;
+		kvm_s390_set_psw_cc(vcpu, 3);
 		return 0;
 	}
 }
 
 static int handle_stfl(struct kvm_vcpu *vcpu)
 {
-	unsigned int facility_list;
 	int rc;
 
 	vcpu->stat.instruction_stfl++;
@@ -236,15 +233,13 @@ static int handle_stfl(struct kvm_vcpu *vcpu)
 	if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
 		return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
 
-	/* only pass the facility bits, which we can handle */
-	facility_list = S390_lowcore.stfl_fac_list & 0xff82fff3;
-
 	rc = copy_to_guest(vcpu, offsetof(struct _lowcore, stfl_fac_list),
-			   &facility_list, sizeof(facility_list));
+			   vfacilities, 4);
 	if (rc)
 		return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
-	VCPU_EVENT(vcpu, 5, "store facility list value %x", facility_list);
-	trace_kvm_s390_handle_stfl(vcpu, facility_list);
+	VCPU_EVENT(vcpu, 5, "store facility list value %x",
+		   *(unsigned int *) vfacilities);
+	trace_kvm_s390_handle_stfl(vcpu, *(unsigned int *) vfacilities);
 	return 0;
 }
 
@@ -387,7 +382,7 @@ static int handle_stsi(struct kvm_vcpu *vcpu)
 		return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
 
 	if (fc > 3) {
-		vcpu->arch.sie_block->gpsw.mask |= 3ul << 44;	  /* cc 3 */
+		kvm_s390_set_psw_cc(vcpu, 3);
 		return 0;
 	}
 
@@ -397,7 +392,7 @@ static int handle_stsi(struct kvm_vcpu *vcpu)
 
 	if (fc == 0) {
 		vcpu->run->s.regs.gprs[0] = 3 << 28;
-		vcpu->arch.sie_block->gpsw.mask &= ~(3ul << 44);  /* cc 0 */
+		kvm_s390_set_psw_cc(vcpu, 0);
 		return 0;
 	}
 
@@ -431,12 +426,11 @@ static int handle_stsi(struct kvm_vcpu *vcpu)
 	}
 	trace_kvm_s390_handle_stsi(vcpu, fc, sel1, sel2, operand2);
 	free_page(mem);
-	vcpu->arch.sie_block->gpsw.mask &= ~(3ul << 44);
+	kvm_s390_set_psw_cc(vcpu, 0);
 	vcpu->run->s.regs.gprs[0] = 0;
 	return 0;
 out_no_data:
-	/* condition code 3 */
-	vcpu->arch.sie_block->gpsw.mask |= 3ul << 44;
+	kvm_s390_set_psw_cc(vcpu, 3);
 out_exception:
 	free_page(mem);
 	return rc;
@@ -494,12 +488,12 @@ static int handle_epsw(struct kvm_vcpu *vcpu)
 	kvm_s390_get_regs_rre(vcpu, &reg1, &reg2);
 
 	/* This basically extracts the mask half of the psw. */
-	vcpu->run->s.regs.gprs[reg1] &= 0xffffffff00000000;
+	vcpu->run->s.regs.gprs[reg1] &= 0xffffffff00000000UL;
 	vcpu->run->s.regs.gprs[reg1] |= vcpu->arch.sie_block->gpsw.mask >> 32;
 	if (reg2) {
-		vcpu->run->s.regs.gprs[reg2] &= 0xffffffff00000000;
+		vcpu->run->s.regs.gprs[reg2] &= 0xffffffff00000000UL;
 		vcpu->run->s.regs.gprs[reg2] |=
-			vcpu->arch.sie_block->gpsw.mask & 0x00000000ffffffff;
+			vcpu->arch.sie_block->gpsw.mask & 0x00000000ffffffffUL;
 	}
 	return 0;
 }
diff --git a/arch/s390/lib/delay.c b/arch/s390/lib/delay.c
index c61b9fad43cc..57c87d7d7ede 100644
--- a/arch/s390/lib/delay.c
+++ b/arch/s390/lib/delay.c
@@ -44,7 +44,6 @@ static void __udelay_disabled(unsigned long long usecs)
 	do {
 		set_clock_comparator(end);
 		vtime_stop_cpu();
-		local_irq_disable();
 	} while (get_tod_clock() < end);
 	lockdep_on();
 	__ctl_load(cr0, 0, 0);
@@ -64,7 +63,6 @@ static void __udelay_enabled(unsigned long long usecs)
 			set_clock_comparator(end);
 		}
 		vtime_stop_cpu();
-		local_irq_disable();
 		if (clock_saved)
 			local_tick_enable(clock_saved);
 	} while (get_tod_clock() < end);
diff --git a/arch/s390/lib/uaccess_pt.c b/arch/s390/lib/uaccess_pt.c
index 50ea137a2d3c..1694d738b175 100644
--- a/arch/s390/lib/uaccess_pt.c
+++ b/arch/s390/lib/uaccess_pt.c
@@ -86,28 +86,28 @@ static unsigned long follow_table(struct mm_struct *mm,
 	switch (mm->context.asce_bits & _ASCE_TYPE_MASK) {
 	case _ASCE_TYPE_REGION1:
 		table = table + ((address >> 53) & 0x7ff);
-		if (unlikely(*table & _REGION_ENTRY_INV))
+		if (unlikely(*table & _REGION_ENTRY_INVALID))
 			return -0x39UL;
 		table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
 		/* fallthrough */
 	case _ASCE_TYPE_REGION2:
 		table = table + ((address >> 42) & 0x7ff);
-		if (unlikely(*table & _REGION_ENTRY_INV))
+		if (unlikely(*table & _REGION_ENTRY_INVALID))
 			return -0x3aUL;
 		table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
 		/* fallthrough */
 	case _ASCE_TYPE_REGION3:
 		table = table + ((address >> 31) & 0x7ff);
-		if (unlikely(*table & _REGION_ENTRY_INV))
+		if (unlikely(*table & _REGION_ENTRY_INVALID))
 			return -0x3bUL;
 		table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
 		/* fallthrough */
 	case _ASCE_TYPE_SEGMENT:
 		table = table + ((address >> 20) & 0x7ff);
-		if (unlikely(*table & _SEGMENT_ENTRY_INV))
+		if (unlikely(*table & _SEGMENT_ENTRY_INVALID))
 			return -0x10UL;
 		if (unlikely(*table & _SEGMENT_ENTRY_LARGE)) {
-			if (write && (*table & _SEGMENT_ENTRY_RO))
+			if (write && (*table & _SEGMENT_ENTRY_PROTECT))
 				return -0x04UL;
 			return (*table & _SEGMENT_ENTRY_ORIGIN_LARGE) +
 				(address & ~_SEGMENT_ENTRY_ORIGIN_LARGE);
@@ -117,7 +117,7 @@ static unsigned long follow_table(struct mm_struct *mm,
 	table = table + ((address >> 12) & 0xff);
 	if (unlikely(*table & _PAGE_INVALID))
 		return -0x11UL;
-	if (write && (*table & _PAGE_RO))
+	if (write && (*table & _PAGE_PROTECT))
 		return -0x04UL;
 	return (*table & PAGE_MASK) + (address & ~PAGE_MASK);
 }
@@ -130,13 +130,13 @@ static unsigned long follow_table(struct mm_struct *mm,
 	unsigned long *table = (unsigned long *)__pa(mm->pgd);
 
 	table = table + ((address >> 20) & 0x7ff);
-	if (unlikely(*table & _SEGMENT_ENTRY_INV))
+	if (unlikely(*table & _SEGMENT_ENTRY_INVALID))
 		return -0x10UL;
 	table = (unsigned long *)(*table & _SEGMENT_ENTRY_ORIGIN);
 	table = table + ((address >> 12) & 0xff);
 	if (unlikely(*table & _PAGE_INVALID))
 		return -0x11UL;
-	if (write && (*table & _PAGE_RO))
+	if (write && (*table & _PAGE_PROTECT))
 		return -0x04UL;
 	return (*table & PAGE_MASK) + (address & ~PAGE_MASK);
 }
diff --git a/arch/s390/mm/dump_pagetables.c b/arch/s390/mm/dump_pagetables.c
index 3ad65b04ac15..46d517c3c763 100644
--- a/arch/s390/mm/dump_pagetables.c
+++ b/arch/s390/mm/dump_pagetables.c
@@ -53,7 +53,7 @@ static void print_prot(struct seq_file *m, unsigned int pr, int level)
 		seq_printf(m, "I\n");
 		return;
 	}
-	seq_printf(m, "%s", pr & _PAGE_RO ? "RO " : "RW ");
+	seq_printf(m, "%s", pr & _PAGE_PROTECT ? "RO " : "RW ");
 	seq_printf(m, "%s", pr & _PAGE_CO ? "CO " : "   ");
 	seq_putc(m, '\n');
 }
@@ -105,12 +105,12 @@ static void note_page(struct seq_file *m, struct pg_state *st,
 }
 
 /*
- * The actual page table walker functions. In order to keep the implementation
- * of print_prot() short, we only check and pass _PAGE_INVALID and _PAGE_RO
- * flags to note_page() if a region, segment or page table entry is invalid or
- * read-only.
- * After all it's just a hint that the current level being walked contains an
- * invalid or read-only entry.
+ * The actual page table walker functions. In order to keep the
+ * implementation of print_prot() short, we only check and pass
+ * _PAGE_INVALID and _PAGE_PROTECT flags to note_page() if a region,
+ * segment or page table entry is invalid or read-only.
+ * After all it's just a hint that the current level being walked
+ * contains an invalid or read-only entry.
  */
 static void walk_pte_level(struct seq_file *m, struct pg_state *st,
 			   pmd_t *pmd, unsigned long addr)
@@ -122,14 +122,14 @@ static void walk_pte_level(struct seq_file *m, struct pg_state *st,
 	for (i = 0; i < PTRS_PER_PTE && addr < max_addr; i++) {
 		st->current_address = addr;
 		pte = pte_offset_kernel(pmd, addr);
-		prot = pte_val(*pte) & (_PAGE_RO | _PAGE_INVALID);
+		prot = pte_val(*pte) & (_PAGE_PROTECT | _PAGE_INVALID);
 		note_page(m, st, prot, 4);
 		addr += PAGE_SIZE;
 	}
 }
 
 #ifdef CONFIG_64BIT
-#define _PMD_PROT_MASK (_SEGMENT_ENTRY_RO | _SEGMENT_ENTRY_CO)
+#define _PMD_PROT_MASK (_SEGMENT_ENTRY_PROTECT | _SEGMENT_ENTRY_CO)
 #else
 #define _PMD_PROT_MASK 0
 #endif
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index f00aefb66a4e..fc6679210d83 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -302,6 +302,8 @@ static inline int do_exception(struct pt_regs *regs, int access)
 	address = trans_exc_code & __FAIL_ADDR_MASK;
 	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
 	flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
+	if (user_mode(regs))
+		flags |= FAULT_FLAG_USER;
 	if (access == VM_WRITE || (trans_exc_code & store_indication) == 0x400)
 		flags |= FAULT_FLAG_WRITE;
 	down_read(&mm->mmap_sem);
@@ -673,7 +675,7 @@ static int __init pfault_irq_init(void)
 	rc = pfault_init() == 0 ? 0 : -EOPNOTSUPP;
 	if (rc)
 		goto out_pfault;
-	service_subclass_irq_register();
+	irq_subclass_register(IRQ_SUBCLASS_SERVICE_SIGNAL);
 	hotcpu_notifier(pfault_cpu_notify, 0);
 	return 0;
 
diff --git a/arch/s390/mm/gup.c b/arch/s390/mm/gup.c
index 1f5315d1215c..5d758db27bdc 100644
--- a/arch/s390/mm/gup.c
+++ b/arch/s390/mm/gup.c
@@ -24,7 +24,7 @@ static inline int gup_pte_range(pmd_t *pmdp, pmd_t pmd, unsigned long addr,
 	pte_t *ptep, pte;
 	struct page *page;
 
-	mask = (write ? _PAGE_RO : 0) | _PAGE_INVALID | _PAGE_SPECIAL;
+	mask = (write ? _PAGE_PROTECT : 0) | _PAGE_INVALID | _PAGE_SPECIAL;
 
 	ptep = ((pte_t *) pmd_deref(pmd)) + pte_index(addr);
 	do {
@@ -55,8 +55,8 @@ static inline int gup_huge_pmd(pmd_t *pmdp, pmd_t pmd, unsigned long addr,
 	struct page *head, *page, *tail;
 	int refs;
 
-	result = write ? 0 : _SEGMENT_ENTRY_RO;
-	mask = result | _SEGMENT_ENTRY_INV;
+	result = write ? 0 : _SEGMENT_ENTRY_PROTECT;
+	mask = result | _SEGMENT_ENTRY_INVALID;
 	if ((pmd_val(pmd) & mask) != result)
 		return 0;
 	VM_BUG_ON(!pfn_valid(pmd_val(pmd) >> PAGE_SHIFT));
diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c
index 121089d57802..d261c62e40a6 100644
--- a/arch/s390/mm/hugetlbpage.c
+++ b/arch/s390/mm/hugetlbpage.c
@@ -8,21 +8,127 @@
 #include <linux/mm.h>
 #include <linux/hugetlb.h>
 
+static inline pmd_t __pte_to_pmd(pte_t pte)
+{
+	int none, young, prot;
+	pmd_t pmd;
+
+	/*
+	 * Convert encoding		  pte bits	  pmd bits
+	 *				.IR...wrdytp	..R...I...y.
+	 * empty			.10...000000 -> ..0...1...0.
+	 * prot-none, clean, old	.11...000001 -> ..0...1...1.
+	 * prot-none, clean, young	.11...000101 -> ..1...1...1.
+	 * prot-none, dirty, old	.10...001001 -> ..0...1...1.
+	 * prot-none, dirty, young	.10...001101 -> ..1...1...1.
+	 * read-only, clean, old	.11...010001 -> ..1...1...0.
+	 * read-only, clean, young	.01...010101 -> ..1...0...1.
+	 * read-only, dirty, old	.11...011001 -> ..1...1...0.
+	 * read-only, dirty, young	.01...011101 -> ..1...0...1.
+	 * read-write, clean, old	.11...110001 -> ..0...1...0.
+	 * read-write, clean, young	.01...110101 -> ..0...0...1.
+	 * read-write, dirty, old	.10...111001 -> ..0...1...0.
+	 * read-write, dirty, young	.00...111101 -> ..0...0...1.
+	 * Huge ptes are dirty by definition, a clean pte is made dirty
+	 * by the conversion.
+	 */
+	if (pte_present(pte)) {
+		pmd_val(pmd) = pte_val(pte) & PAGE_MASK;
+		if (pte_val(pte) & _PAGE_INVALID)
+			pmd_val(pmd) |= _SEGMENT_ENTRY_INVALID;
+		none = (pte_val(pte) & _PAGE_PRESENT) &&
+			!(pte_val(pte) & _PAGE_READ) &&
+			!(pte_val(pte) & _PAGE_WRITE);
+		prot = (pte_val(pte) & _PAGE_PROTECT) &&
+			!(pte_val(pte) & _PAGE_WRITE);
+		young = pte_val(pte) & _PAGE_YOUNG;
+		if (none || young)
+			pmd_val(pmd) |= _SEGMENT_ENTRY_YOUNG;
+		if (prot || (none && young))
+			pmd_val(pmd) |= _SEGMENT_ENTRY_PROTECT;
+	} else
+		pmd_val(pmd) = _SEGMENT_ENTRY_INVALID;
+	return pmd;
+}
+
+static inline pte_t __pmd_to_pte(pmd_t pmd)
+{
+	pte_t pte;
+
+	/*
+	 * Convert encoding	  pmd bits	  pte bits
+	 *			..R...I...y.	.IR...wrdytp
+	 * empty		..0...1...0. -> .10...000000
+	 * prot-none, old	..0...1...1. -> .10...001001
+	 * prot-none, young	..1...1...1. -> .10...001101
+	 * read-only, old	..1...1...0. -> .11...011001
+	 * read-only, young	..1...0...1. -> .01...011101
+	 * read-write, old	..0...1...0. -> .10...111001
+	 * read-write, young	..0...0...1. -> .00...111101
+	 * Huge ptes are dirty by definition
+	 */
+	if (pmd_present(pmd)) {
+		pte_val(pte) = _PAGE_PRESENT | _PAGE_LARGE | _PAGE_DIRTY |
+			(pmd_val(pmd) & PAGE_MASK);
+		if (pmd_val(pmd) & _SEGMENT_ENTRY_INVALID)
+			pte_val(pte) |= _PAGE_INVALID;
+		if (pmd_prot_none(pmd)) {
+			if (pmd_val(pmd) & _SEGMENT_ENTRY_PROTECT)
+				pte_val(pte) |= _PAGE_YOUNG;
+		} else {
+			pte_val(pte) |= _PAGE_READ;
+			if (pmd_val(pmd) & _SEGMENT_ENTRY_PROTECT)
+				pte_val(pte) |= _PAGE_PROTECT;
+			else
+				pte_val(pte) |= _PAGE_WRITE;
+			if (pmd_val(pmd) & _SEGMENT_ENTRY_YOUNG)
+				pte_val(pte) |= _PAGE_YOUNG;
+		}
+	} else
+		pte_val(pte) = _PAGE_INVALID;
+	return pte;
+}
 
 void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
-				   pte_t *pteptr, pte_t pteval)
+		     pte_t *ptep, pte_t pte)
 {
-	pmd_t *pmdp = (pmd_t *) pteptr;
-	unsigned long mask;
+	pmd_t pmd;
 
+	pmd = __pte_to_pmd(pte);
 	if (!MACHINE_HAS_HPAGE) {
-		pteptr = (pte_t *) pte_page(pteval)[1].index;
-		mask = pte_val(pteval) &
-				(_SEGMENT_ENTRY_INV | _SEGMENT_ENTRY_RO);
-		pte_val(pteval) = (_SEGMENT_ENTRY + __pa(pteptr)) | mask;
+		pmd_val(pmd) &= ~_SEGMENT_ENTRY_ORIGIN;
+		pmd_val(pmd) |= pte_page(pte)[1].index;
+	} else
+		pmd_val(pmd) |= _SEGMENT_ENTRY_LARGE | _SEGMENT_ENTRY_CO;
+	*(pmd_t *) ptep = pmd;
+}
+
+pte_t huge_ptep_get(pte_t *ptep)
+{
+	unsigned long origin;
+	pmd_t pmd;
+
+	pmd = *(pmd_t *) ptep;
+	if (!MACHINE_HAS_HPAGE && pmd_present(pmd)) {
+		origin = pmd_val(pmd) & _SEGMENT_ENTRY_ORIGIN;
+		pmd_val(pmd) &= ~_SEGMENT_ENTRY_ORIGIN;
+		pmd_val(pmd) |= *(unsigned long *) origin;
 	}
+	return __pmd_to_pte(pmd);
+}
 
-	pmd_val(*pmdp) = pte_val(pteval);
+pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
+			      unsigned long addr, pte_t *ptep)
+{
+	pmd_t *pmdp = (pmd_t *) ptep;
+	pte_t pte = huge_ptep_get(ptep);
+
+	if (MACHINE_HAS_IDTE)
+		__pmd_idte(addr, pmdp);
+	else
+		__pmd_csp(pmdp);
+	pmd_val(*pmdp) = _SEGMENT_ENTRY_EMPTY;
+	return pte;
 }
 
 int arch_prepare_hugepage(struct page *page)
@@ -58,7 +164,7 @@ void arch_release_hugepage(struct page *page)
 	ptep = (pte_t *) page[1].index;
 	if (!ptep)
 		return;
-	clear_table((unsigned long *) ptep, _PAGE_TYPE_EMPTY,
+	clear_table((unsigned long *) ptep, _PAGE_INVALID,
 		    PTRS_PER_PTE * sizeof(pte_t));
 	page_table_free(&init_mm, (unsigned long *) ptep);
 	page[1].index = 0;
@@ -117,6 +223,11 @@ int pud_huge(pud_t pud)
 	return 0;
 }
 
+int pmd_huge_support(void)
+{
+	return 1;
+}
+
 struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address,
 			     pmd_t *pmdp, int write)
 {
diff --git a/arch/s390/mm/maccess.c b/arch/s390/mm/maccess.c
index 921fa541dc04..d1e0e0c7a7e2 100644
--- a/arch/s390/mm/maccess.c
+++ b/arch/s390/mm/maccess.c
@@ -14,6 +14,7 @@
 #include <linux/gfp.h>
 #include <linux/cpu.h>
 #include <asm/ctl_reg.h>
+#include <asm/io.h>
 
 /*
  * This function writes to kernel memory bypassing DAT and possible
diff --git a/arch/s390/mm/pageattr.c b/arch/s390/mm/pageattr.c
index 80adfbf75065..990397420e6b 100644
--- a/arch/s390/mm/pageattr.c
+++ b/arch/s390/mm/pageattr.c
@@ -118,7 +118,7 @@ void kernel_map_pages(struct page *page, int numpages, int enable)
 		pte = pte_offset_kernel(pmd, address);
 		if (!enable) {
 			__ptep_ipte(address, pte);
-			pte_val(*pte) = _PAGE_TYPE_EMPTY;
+			pte_val(*pte) = _PAGE_INVALID;
 			continue;
 		}
 		pte_val(*pte) = __pa(address);
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index a8154a1a2c94..de8cbc30dcd1 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -161,7 +161,7 @@ static int gmap_unlink_segment(struct gmap *gmap, unsigned long *table)
 	struct gmap_rmap *rmap;
 	struct page *page;
 
-	if (*table & _SEGMENT_ENTRY_INV)
+	if (*table & _SEGMENT_ENTRY_INVALID)
 		return 0;
 	page = pfn_to_page(*table >> PAGE_SHIFT);
 	mp = (struct gmap_pgtable *) page->index;
@@ -172,7 +172,7 @@ static int gmap_unlink_segment(struct gmap *gmap, unsigned long *table)
 		kfree(rmap);
 		break;
 	}
-	*table = _SEGMENT_ENTRY_INV | _SEGMENT_ENTRY_RO | mp->vmaddr;
+	*table = mp->vmaddr | _SEGMENT_ENTRY_INVALID | _SEGMENT_ENTRY_PROTECT;
 	return 1;
 }
 
@@ -245,7 +245,9 @@ EXPORT_SYMBOL_GPL(gmap_disable);
  * gmap_alloc_table is assumed to be called with mmap_sem held
  */
 static int gmap_alloc_table(struct gmap *gmap,
-			       unsigned long *table, unsigned long init)
+			    unsigned long *table, unsigned long init)
+	__releases(&gmap->mm->page_table_lock)
+	__acquires(&gmap->mm->page_table_lock)
 {
 	struct page *page;
 	unsigned long *new;
@@ -258,7 +260,7 @@ static int gmap_alloc_table(struct gmap *gmap,
 		return -ENOMEM;
 	new = (unsigned long *) page_to_phys(page);
 	crst_table_init(new, init);
-	if (*table & _REGION_ENTRY_INV) {
+	if (*table & _REGION_ENTRY_INVALID) {
 		list_add(&page->lru, &gmap->crst_list);
 		*table = (unsigned long) new | _REGION_ENTRY_LENGTH |
 			(*table & _REGION_ENTRY_TYPE_MASK);
@@ -292,22 +294,22 @@ int gmap_unmap_segment(struct gmap *gmap, unsigned long to, unsigned long len)
 	for (off = 0; off < len; off += PMD_SIZE) {
 		/* Walk the guest addr space page table */
 		table = gmap->table + (((to + off) >> 53) & 0x7ff);
-		if (*table & _REGION_ENTRY_INV)
+		if (*table & _REGION_ENTRY_INVALID)
 			goto out;
 		table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
 		table = table + (((to + off) >> 42) & 0x7ff);
-		if (*table & _REGION_ENTRY_INV)
+		if (*table & _REGION_ENTRY_INVALID)
 			goto out;
 		table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
 		table = table + (((to + off) >> 31) & 0x7ff);
-		if (*table & _REGION_ENTRY_INV)
+		if (*table & _REGION_ENTRY_INVALID)
 			goto out;
 		table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
 		table = table + (((to + off) >> 20) & 0x7ff);
 
 		/* Clear segment table entry in guest address space. */
 		flush |= gmap_unlink_segment(gmap, table);
-		*table = _SEGMENT_ENTRY_INV;
+		*table = _SEGMENT_ENTRY_INVALID;
 	}
 out:
 	spin_unlock(&gmap->mm->page_table_lock);
@@ -335,7 +337,7 @@ int gmap_map_segment(struct gmap *gmap, unsigned long from,
 
 	if ((from | to | len) & (PMD_SIZE - 1))
 		return -EINVAL;
-	if (len == 0 || from + len > PGDIR_SIZE ||
+	if (len == 0 || from + len > TASK_MAX_SIZE ||
 	    from + len < from || to + len < to)
 		return -EINVAL;
 
@@ -345,17 +347,17 @@ int gmap_map_segment(struct gmap *gmap, unsigned long from,
 	for (off = 0; off < len; off += PMD_SIZE) {
 		/* Walk the gmap address space page table */
 		table = gmap->table + (((to + off) >> 53) & 0x7ff);
-		if ((*table & _REGION_ENTRY_INV) &&
+		if ((*table & _REGION_ENTRY_INVALID) &&
 		    gmap_alloc_table(gmap, table, _REGION2_ENTRY_EMPTY))
 			goto out_unmap;
 		table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
 		table = table + (((to + off) >> 42) & 0x7ff);
-		if ((*table & _REGION_ENTRY_INV) &&
+		if ((*table & _REGION_ENTRY_INVALID) &&
 		    gmap_alloc_table(gmap, table, _REGION3_ENTRY_EMPTY))
 			goto out_unmap;
 		table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
 		table = table + (((to + off) >> 31) & 0x7ff);
-		if ((*table & _REGION_ENTRY_INV) &&
+		if ((*table & _REGION_ENTRY_INVALID) &&
 		    gmap_alloc_table(gmap, table, _SEGMENT_ENTRY_EMPTY))
 			goto out_unmap;
 		table = (unsigned long *) (*table & _REGION_ENTRY_ORIGIN);
@@ -363,7 +365,8 @@ int gmap_map_segment(struct gmap *gmap, unsigned long from,
 
 		/* Store 'from' address in an invalid segment table entry. */
 		flush |= gmap_unlink_segment(gmap, table);
-		*table = _SEGMENT_ENTRY_INV | _SEGMENT_ENTRY_RO | (from + off);
+		*table =  (from + off) | (_SEGMENT_ENTRY_INVALID |
+					  _SEGMENT_ENTRY_PROTECT);
 	}
 	spin_unlock(&gmap->mm->page_table_lock);
 	up_read(&gmap->mm->mmap_sem);
@@ -384,15 +387,15 @@ static unsigned long *gmap_table_walk(unsigned long address, struct gmap *gmap)
 	unsigned long *table;
 
 	table = gmap->table + ((address >> 53) & 0x7ff);
-	if (unlikely(*table & _REGION_ENTRY_INV))
+	if (unlikely(*table & _REGION_ENTRY_INVALID))
 		return ERR_PTR(-EFAULT);
 	table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
 	table = table + ((address >> 42) & 0x7ff);
-	if (unlikely(*table & _REGION_ENTRY_INV))
+	if (unlikely(*table & _REGION_ENTRY_INVALID))
 		return ERR_PTR(-EFAULT);
 	table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
 	table = table + ((address >> 31) & 0x7ff);
-	if (unlikely(*table & _REGION_ENTRY_INV))
+	if (unlikely(*table & _REGION_ENTRY_INVALID))
 		return ERR_PTR(-EFAULT);
 	table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
 	table = table + ((address >> 20) & 0x7ff);
@@ -422,11 +425,11 @@ unsigned long __gmap_translate(unsigned long address, struct gmap *gmap)
 		return PTR_ERR(segment_ptr);
 	/* Convert the gmap address to an mm address. */
 	segment = *segment_ptr;
-	if (!(segment & _SEGMENT_ENTRY_INV)) {
+	if (!(segment & _SEGMENT_ENTRY_INVALID)) {
 		page = pfn_to_page(segment >> PAGE_SHIFT);
 		mp = (struct gmap_pgtable *) page->index;
 		return mp->vmaddr | (address & ~PMD_MASK);
-	} else if (segment & _SEGMENT_ENTRY_RO) {
+	} else if (segment & _SEGMENT_ENTRY_PROTECT) {
 		vmaddr = segment & _SEGMENT_ENTRY_ORIGIN;
 		return vmaddr | (address & ~PMD_MASK);
 	}
@@ -517,8 +520,8 @@ static void gmap_disconnect_pgtable(struct mm_struct *mm, unsigned long *table)
 	page = pfn_to_page(__pa(table) >> PAGE_SHIFT);
 	mp = (struct gmap_pgtable *) page->index;
 	list_for_each_entry_safe(rmap, next, &mp->mapper, list) {
-		*rmap->entry =
-			_SEGMENT_ENTRY_INV | _SEGMENT_ENTRY_RO | mp->vmaddr;
+		*rmap->entry = mp->vmaddr | (_SEGMENT_ENTRY_INVALID |
+					     _SEGMENT_ENTRY_PROTECT);
 		list_del(&rmap->list);
 		kfree(rmap);
 		flush = 1;
@@ -545,13 +548,13 @@ unsigned long __gmap_fault(unsigned long address, struct gmap *gmap)
 	/* Convert the gmap address to an mm address. */
 	while (1) {
 		segment = *segment_ptr;
-		if (!(segment & _SEGMENT_ENTRY_INV)) {
+		if (!(segment & _SEGMENT_ENTRY_INVALID)) {
 			/* Page table is present */
 			page = pfn_to_page(segment >> PAGE_SHIFT);
 			mp = (struct gmap_pgtable *) page->index;
 			return mp->vmaddr | (address & ~PMD_MASK);
 		}
-		if (!(segment & _SEGMENT_ENTRY_RO))
+		if (!(segment & _SEGMENT_ENTRY_PROTECT))
 			/* Nothing mapped in the gmap address space. */
 			break;
 		rc = gmap_connect_pgtable(address, segment, segment_ptr, gmap);
@@ -586,25 +589,25 @@ void gmap_discard(unsigned long from, unsigned long to, struct gmap *gmap)
 	while (address < to) {
 		/* Walk the gmap address space page table */
 		table = gmap->table + ((address >> 53) & 0x7ff);
-		if (unlikely(*table & _REGION_ENTRY_INV)) {
+		if (unlikely(*table & _REGION_ENTRY_INVALID)) {
 			address = (address + PMD_SIZE) & PMD_MASK;
 			continue;
 		}
 		table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
 		table = table + ((address >> 42) & 0x7ff);
-		if (unlikely(*table & _REGION_ENTRY_INV)) {
+		if (unlikely(*table & _REGION_ENTRY_INVALID)) {
 			address = (address + PMD_SIZE) & PMD_MASK;
 			continue;
 		}
 		table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
 		table = table + ((address >> 31) & 0x7ff);
-		if (unlikely(*table & _REGION_ENTRY_INV)) {
+		if (unlikely(*table & _REGION_ENTRY_INVALID)) {
 			address = (address + PMD_SIZE) & PMD_MASK;
 			continue;
 		}
 		table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
 		table = table + ((address >> 20) & 0x7ff);
-		if (unlikely(*table & _SEGMENT_ENTRY_INV)) {
+		if (unlikely(*table & _SEGMENT_ENTRY_INVALID)) {
 			address = (address + PMD_SIZE) & PMD_MASK;
 			continue;
 		}
@@ -687,7 +690,7 @@ int gmap_ipte_notify(struct gmap *gmap, unsigned long start, unsigned long len)
 			continue;
 		/* Set notification bit in the pgste of the pte */
 		entry = *ptep;
-		if ((pte_val(entry) & (_PAGE_INVALID | _PAGE_RO)) == 0) {
+		if ((pte_val(entry) & (_PAGE_INVALID | _PAGE_PROTECT)) == 0) {
 			pgste = pgste_get_lock(ptep);
 			pgste_val(pgste) |= PGSTE_IN_BIT;
 			pgste_set_unlock(ptep, pgste);
@@ -731,6 +734,11 @@ void gmap_do_ipte_notify(struct mm_struct *mm, unsigned long addr, pte_t *pte)
 	spin_unlock(&gmap_notifier_lock);
 }
 
+static inline int page_table_with_pgste(struct page *page)
+{
+	return atomic_read(&page->_mapcount) == 0;
+}
+
 static inline unsigned long *page_table_alloc_pgste(struct mm_struct *mm,
 						    unsigned long vmaddr)
 {
@@ -750,10 +758,11 @@ static inline unsigned long *page_table_alloc_pgste(struct mm_struct *mm,
 	mp->vmaddr = vmaddr & PMD_MASK;
 	INIT_LIST_HEAD(&mp->mapper);
 	page->index = (unsigned long) mp;
-	atomic_set(&page->_mapcount, 3);
+	atomic_set(&page->_mapcount, 0);
 	table = (unsigned long *) page_to_phys(page);
-	clear_table(table, _PAGE_TYPE_EMPTY, PAGE_SIZE/2);
-	clear_table(table + PTRS_PER_PTE, 0, PAGE_SIZE/2);
+	clear_table(table, _PAGE_INVALID, PAGE_SIZE/2);
+	clear_table(table + PTRS_PER_PTE, PGSTE_HR_BIT | PGSTE_HC_BIT,
+		    PAGE_SIZE/2);
 	return table;
 }
 
@@ -791,26 +800,21 @@ int set_guest_storage_key(struct mm_struct *mm, unsigned long addr,
 	pgste_val(new) |= (key & (_PAGE_CHANGED | _PAGE_REFERENCED)) << 48;
 	pgste_val(new) |= (key & (_PAGE_ACC_BITS | _PAGE_FP_BIT)) << 56;
 	if (!(pte_val(*ptep) & _PAGE_INVALID)) {
-		unsigned long address, bits;
-		unsigned char skey;
+		unsigned long address, bits, skey;
 
 		address = pte_val(*ptep) & PAGE_MASK;
-		skey = page_get_storage_key(address);
+		skey = (unsigned long) page_get_storage_key(address);
 		bits = skey & (_PAGE_CHANGED | _PAGE_REFERENCED);
+		skey = key & (_PAGE_ACC_BITS | _PAGE_FP_BIT);
 		/* Set storage key ACC and FP */
-		page_set_storage_key(address,
-				(key & (_PAGE_ACC_BITS | _PAGE_FP_BIT)),
-				!nq);
-
+		page_set_storage_key(address, skey, !nq);
 		/* Merge host changed & referenced into pgste  */
 		pgste_val(new) |= bits << 52;
-		/* Transfer skey changed & referenced bit to kvm user bits */
-		pgste_val(new) |= bits << 45;	/* PGSTE_UR_BIT & PGSTE_UC_BIT */
 	}
 	/* changing the guest storage key is considered a change of the page */
 	if ((pgste_val(new) ^ pgste_val(old)) &
 	    (PGSTE_ACC_BITS | PGSTE_FP_BIT | PGSTE_GR_BIT | PGSTE_GC_BIT))
-		pgste_val(new) |= PGSTE_UC_BIT;
+		pgste_val(new) |= PGSTE_HC_BIT;
 
 	pgste_set_unlock(ptep, new);
 	pte_unmap_unlock(*ptep, ptl);
@@ -821,6 +825,11 @@ EXPORT_SYMBOL(set_guest_storage_key);
 
 #else /* CONFIG_PGSTE */
 
+static inline int page_table_with_pgste(struct page *page)
+{
+	return 0;
+}
+
 static inline unsigned long *page_table_alloc_pgste(struct mm_struct *mm,
 						    unsigned long vmaddr)
 {
@@ -878,7 +887,7 @@ unsigned long *page_table_alloc(struct mm_struct *mm, unsigned long vmaddr)
 		pgtable_page_ctor(page);
 		atomic_set(&page->_mapcount, 1);
 		table = (unsigned long *) page_to_phys(page);
-		clear_table(table, _PAGE_TYPE_EMPTY, PAGE_SIZE);
+		clear_table(table, _PAGE_INVALID, PAGE_SIZE);
 		spin_lock_bh(&mm->context.list_lock);
 		list_add(&page->lru, &mm->context.pgtable_list);
 	} else {
@@ -897,12 +906,12 @@ void page_table_free(struct mm_struct *mm, unsigned long *table)
 	struct page *page;
 	unsigned int bit, mask;
 
-	if (mm_has_pgste(mm)) {
+	page = pfn_to_page(__pa(table) >> PAGE_SHIFT);
+	if (page_table_with_pgste(page)) {
 		gmap_disconnect_pgtable(mm, table);
 		return page_table_free_pgste(table);
 	}
 	/* Free 1K/2K page table fragment of a 4K page */
-	page = pfn_to_page(__pa(table) >> PAGE_SHIFT);
 	bit = 1 << ((__pa(table) & ~PAGE_MASK)/(PTRS_PER_PTE*sizeof(pte_t)));
 	spin_lock_bh(&mm->context.list_lock);
 	if ((atomic_read(&page->_mapcount) & FRAG_MASK) != FRAG_MASK)
@@ -940,14 +949,14 @@ void page_table_free_rcu(struct mmu_gather *tlb, unsigned long *table)
 	unsigned int bit, mask;
 
 	mm = tlb->mm;
-	if (mm_has_pgste(mm)) {
+	page = pfn_to_page(__pa(table) >> PAGE_SHIFT);
+	if (page_table_with_pgste(page)) {
 		gmap_disconnect_pgtable(mm, table);
 		table = (unsigned long *) (__pa(table) | FRAG_MASK);
 		tlb_remove_table(tlb, table);
 		return;
 	}
 	bit = 1 << ((__pa(table) & ~PAGE_MASK) / (PTRS_PER_PTE*sizeof(pte_t)));
-	page = pfn_to_page(__pa(table) >> PAGE_SHIFT);
 	spin_lock_bh(&mm->context.list_lock);
 	if ((atomic_read(&page->_mapcount) & FRAG_MASK) != FRAG_MASK)
 		list_del(&page->lru);
@@ -959,7 +968,7 @@ void page_table_free_rcu(struct mmu_gather *tlb, unsigned long *table)
 	tlb_remove_table(tlb, table);
 }
 
-void __tlb_remove_table(void *_table)
+static void __tlb_remove_table(void *_table)
 {
 	const unsigned long mask = (FRAG_MASK << 4) | FRAG_MASK;
 	void *table = (void *)((unsigned long) _table & ~mask);
@@ -1007,7 +1016,6 @@ void tlb_table_flush(struct mmu_gather *tlb)
 	struct mmu_table_batch **batch = &tlb->batch;
 
 	if (*batch) {
-		__tlb_flush_mm(tlb->mm);
 		call_rcu_sched(&(*batch)->rcu, tlb_remove_table_rcu);
 		*batch = NULL;
 	}
@@ -1017,11 +1025,12 @@ void tlb_remove_table(struct mmu_gather *tlb, void *table)
 {
 	struct mmu_table_batch **batch = &tlb->batch;
 
+	tlb->mm->context.flush_mm = 1;
 	if (*batch == NULL) {
 		*batch = (struct mmu_table_batch *)
 			__get_free_page(GFP_NOWAIT | __GFP_NOWARN);
 		if (*batch == NULL) {
-			__tlb_flush_mm(tlb->mm);
+			__tlb_flush_mm_lazy(tlb->mm);
 			tlb_remove_table_one(table);
 			return;
 		}
@@ -1029,40 +1038,124 @@ void tlb_remove_table(struct mmu_gather *tlb, void *table)
 	}
 	(*batch)->tables[(*batch)->nr++] = table;
 	if ((*batch)->nr == MAX_TABLE_BATCH)
-		tlb_table_flush(tlb);
+		tlb_flush_mmu(tlb);
 }
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
-void thp_split_vma(struct vm_area_struct *vma)
+static inline void thp_split_vma(struct vm_area_struct *vma)
 {
 	unsigned long addr;
-	struct page *page;
 
-	for (addr = vma->vm_start; addr < vma->vm_end; addr += PAGE_SIZE) {
-		page = follow_page(vma, addr, FOLL_SPLIT);
-	}
+	for (addr = vma->vm_start; addr < vma->vm_end; addr += PAGE_SIZE)
+		follow_page(vma, addr, FOLL_SPLIT);
 }
 
-void thp_split_mm(struct mm_struct *mm)
+static inline void thp_split_mm(struct mm_struct *mm)
 {
-	struct vm_area_struct *vma = mm->mmap;
+	struct vm_area_struct *vma;
 
-	while (vma != NULL) {
+	for (vma = mm->mmap; vma != NULL; vma = vma->vm_next) {
 		thp_split_vma(vma);
 		vma->vm_flags &= ~VM_HUGEPAGE;
 		vma->vm_flags |= VM_NOHUGEPAGE;
-		vma = vma->vm_next;
 	}
+	mm->def_flags |= VM_NOHUGEPAGE;
+}
+#else
+static inline void thp_split_mm(struct mm_struct *mm)
+{
 }
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
+static unsigned long page_table_realloc_pmd(struct mmu_gather *tlb,
+				struct mm_struct *mm, pud_t *pud,
+				unsigned long addr, unsigned long end)
+{
+	unsigned long next, *table, *new;
+	struct page *page;
+	pmd_t *pmd;
+
+	pmd = pmd_offset(pud, addr);
+	do {
+		next = pmd_addr_end(addr, end);
+again:
+		if (pmd_none_or_clear_bad(pmd))
+			continue;
+		table = (unsigned long *) pmd_deref(*pmd);
+		page = pfn_to_page(__pa(table) >> PAGE_SHIFT);
+		if (page_table_with_pgste(page))
+			continue;
+		/* Allocate new page table with pgstes */
+		new = page_table_alloc_pgste(mm, addr);
+		if (!new) {
+			mm->context.has_pgste = 0;
+			continue;
+		}
+		spin_lock(&mm->page_table_lock);
+		if (likely((unsigned long *) pmd_deref(*pmd) == table)) {
+			/* Nuke pmd entry pointing to the "short" page table */
+			pmdp_flush_lazy(mm, addr, pmd);
+			pmd_clear(pmd);
+			/* Copy ptes from old table to new table */
+			memcpy(new, table, PAGE_SIZE/2);
+			clear_table(table, _PAGE_INVALID, PAGE_SIZE/2);
+			/* Establish new table */
+			pmd_populate(mm, pmd, (pte_t *) new);
+			/* Free old table with rcu, there might be a walker! */
+			page_table_free_rcu(tlb, table);
+			new = NULL;
+		}
+		spin_unlock(&mm->page_table_lock);
+		if (new) {
+			page_table_free_pgste(new);
+			goto again;
+		}
+	} while (pmd++, addr = next, addr != end);
+
+	return addr;
+}
+
+static unsigned long page_table_realloc_pud(struct mmu_gather *tlb,
+				   struct mm_struct *mm, pgd_t *pgd,
+				   unsigned long addr, unsigned long end)
+{
+	unsigned long next;
+	pud_t *pud;
+
+	pud = pud_offset(pgd, addr);
+	do {
+		next = pud_addr_end(addr, end);
+		if (pud_none_or_clear_bad(pud))
+			continue;
+		next = page_table_realloc_pmd(tlb, mm, pud, addr, next);
+	} while (pud++, addr = next, addr != end);
+
+	return addr;
+}
+
+static void page_table_realloc(struct mmu_gather *tlb, struct mm_struct *mm,
+			       unsigned long addr, unsigned long end)
+{
+	unsigned long next;
+	pgd_t *pgd;
+
+	pgd = pgd_offset(mm, addr);
+	do {
+		next = pgd_addr_end(addr, end);
+		if (pgd_none_or_clear_bad(pgd))
+			continue;
+		next = page_table_realloc_pud(tlb, mm, pgd, addr, next);
+	} while (pgd++, addr = next, addr != end);
+}
+
 /*
  * switch on pgstes for its userspace process (for kvm)
  */
 int s390_enable_sie(void)
 {
 	struct task_struct *tsk = current;
-	struct mm_struct *mm, *old_mm;
+	struct mm_struct *mm = tsk->mm;
+	struct mmu_gather tlb;
 
 	/* Do we have switched amode? If no, we cannot do sie */
 	if (s390_user_mode == HOME_SPACE_MODE)
@@ -1072,57 +1165,16 @@ int s390_enable_sie(void)
 	if (mm_has_pgste(tsk->mm))
 		return 0;
 
-	/* lets check if we are allowed to replace the mm */
-	task_lock(tsk);
-	if (!tsk->mm || atomic_read(&tsk->mm->mm_users) > 1 ||
-#ifdef CONFIG_AIO
-	    !hlist_empty(&tsk->mm->ioctx_list) ||
-#endif
-	    tsk->mm != tsk->active_mm) {
-		task_unlock(tsk);
-		return -EINVAL;
-	}
-	task_unlock(tsk);
-
-	/* we copy the mm and let dup_mm create the page tables with_pgstes */
-	tsk->mm->context.alloc_pgste = 1;
-	/* make sure that both mms have a correct rss state */
-	sync_mm_rss(tsk->mm);
-	mm = dup_mm(tsk);
-	tsk->mm->context.alloc_pgste = 0;
-	if (!mm)
-		return -ENOMEM;
-
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	down_write(&mm->mmap_sem);
 	/* split thp mappings and disable thp for future mappings */
 	thp_split_mm(mm);
-	mm->def_flags |= VM_NOHUGEPAGE;
-#endif
-
-	/* Now lets check again if something happened */
-	task_lock(tsk);
-	if (!tsk->mm || atomic_read(&tsk->mm->mm_users) > 1 ||
-#ifdef CONFIG_AIO
-	    !hlist_empty(&tsk->mm->ioctx_list) ||
-#endif
-	    tsk->mm != tsk->active_mm) {
-		mmput(mm);
-		task_unlock(tsk);
-		return -EINVAL;
-	}
-
-	/* ok, we are alone. No ptrace, no threads, etc. */
-	old_mm = tsk->mm;
-	tsk->mm = tsk->active_mm = mm;
-	preempt_disable();
-	update_mm(mm, tsk);
-	atomic_inc(&mm->context.attach_count);
-	atomic_dec(&old_mm->context.attach_count);
-	cpumask_set_cpu(smp_processor_id(), mm_cpumask(mm));
-	preempt_enable();
-	task_unlock(tsk);
-	mmput(old_mm);
-	return 0;
+	/* Reallocate the page tables with pgstes */
+	mm->context.has_pgste = 1;
+	tlb_gather_mmu(&tlb, mm, 0, TASK_SIZE);
+	page_table_realloc(&tlb, mm, 0, TASK_SIZE);
+	tlb_finish_mmu(&tlb, 0, TASK_SIZE);
+	up_write(&mm->mmap_sem);
+	return mm->context.has_pgste ? 0 : -ENOMEM;
 }
 EXPORT_SYMBOL_GPL(s390_enable_sie);
 
@@ -1198,9 +1250,9 @@ pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp)
 		list_del(lh);
 	}
 	ptep = (pte_t *) pgtable;
-	pte_val(*ptep) = _PAGE_TYPE_EMPTY;
+	pte_val(*ptep) = _PAGE_INVALID;
 	ptep++;
-	pte_val(*ptep) = _PAGE_TYPE_EMPTY;
+	pte_val(*ptep) = _PAGE_INVALID;
 	return pgtable;
 }
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c
index 8b268fcc4612..bcfb70b60be6 100644
--- a/arch/s390/mm/vmem.c
+++ b/arch/s390/mm/vmem.c
@@ -69,7 +69,7 @@ static pte_t __ref *vmem_pte_alloc(unsigned long address)
 		pte = alloc_bootmem(PTRS_PER_PTE * sizeof(pte_t));
 	if (!pte)
 		return NULL;
-	clear_table((unsigned long *) pte, _PAGE_TYPE_EMPTY,
+	clear_table((unsigned long *) pte, _PAGE_INVALID,
 		    PTRS_PER_PTE * sizeof(pte_t));
 	return pte;
 }
@@ -101,7 +101,7 @@ static int vmem_add_mem(unsigned long start, unsigned long size, int ro)
 		    !(address & ~PUD_MASK) && (address + PUD_SIZE <= end)) {
 			pud_val(*pu_dir) = __pa(address) |
 				_REGION_ENTRY_TYPE_R3 | _REGION3_ENTRY_LARGE |
-				(ro ? _REGION_ENTRY_RO : 0);
+				(ro ? _REGION_ENTRY_PROTECT : 0);
 			address += PUD_SIZE;
 			continue;
 		}
@@ -118,7 +118,8 @@ static int vmem_add_mem(unsigned long start, unsigned long size, int ro)
 		    !(address & ~PMD_MASK) && (address + PMD_SIZE <= end)) {
 			pmd_val(*pm_dir) = __pa(address) |
 				_SEGMENT_ENTRY | _SEGMENT_ENTRY_LARGE |
-				(ro ? _SEGMENT_ENTRY_RO : 0);
+				_SEGMENT_ENTRY_YOUNG |
+				(ro ? _SEGMENT_ENTRY_PROTECT : 0);
 			address += PMD_SIZE;
 			continue;
 		}
@@ -131,7 +132,8 @@ static int vmem_add_mem(unsigned long start, unsigned long size, int ro)
 		}
 
 		pt_dir = pte_offset_kernel(pm_dir, address);
-		pte_val(*pt_dir) = __pa(address) | (ro ? _PAGE_RO : 0);
+		pte_val(*pt_dir) = __pa(address) |
+			pgprot_val(ro ? PAGE_KERNEL_RO : PAGE_KERNEL);
 		address += PAGE_SIZE;
 	}
 	ret = 0;
@@ -154,7 +156,7 @@ static void vmem_remove_range(unsigned long start, unsigned long size)
 	pte_t *pt_dir;
 	pte_t  pte;
 
-	pte_val(pte) = _PAGE_TYPE_EMPTY;
+	pte_val(pte) = _PAGE_INVALID;
 	while (address < end) {
 		pg_dir = pgd_offset_k(address);
 		if (pgd_none(*pg_dir)) {
@@ -255,7 +257,8 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node)
 			new_page =__pa(vmem_alloc_pages(0));
 			if (!new_page)
 				goto out;
-			pte_val(*pt_dir) = __pa(new_page);
+			pte_val(*pt_dir) =
+				__pa(new_page) | pgprot_val(PAGE_KERNEL);
 		}
 		address += PAGE_SIZE;
 	}
diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index d5f10a43a58f..709239285869 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -805,7 +805,7 @@ static struct bpf_binary_header *bpf_alloc_binary(unsigned int bpfsize,
 		return NULL;
 	memset(header, 0, sz);
 	header->pages = sz / PAGE_SIZE;
-	hole = sz - bpfsize + sizeof(*header);
+	hole = sz - (bpfsize + sizeof(*header));
 	/* Insert random number of illegal instructions before BPF code
 	 * and make sure the first instruction starts at an even address.
 	 */
diff --git a/arch/s390/oprofile/hwsampler.c b/arch/s390/oprofile/hwsampler.c
index b5b2916895e0..231cecafc2f1 100644
--- a/arch/s390/oprofile/hwsampler.c
+++ b/arch/s390/oprofile/hwsampler.c
@@ -1001,7 +1001,7 @@ int hwsampler_deallocate(void)
 	if (hws_state != HWS_STOPPED)
 		goto deallocate_exit;
 
-	measurement_alert_subclass_unregister();
+	irq_subclass_unregister(IRQ_SUBCLASS_MEASUREMENT_ALERT);
 	deallocate_sdbt();
 
 	hws_state = HWS_DEALLOCATED;
@@ -1115,7 +1115,7 @@ int hwsampler_shutdown(void)
 		mutex_lock(&hws_sem);
 
 		if (hws_state == HWS_STOPPED) {
-			measurement_alert_subclass_unregister();
+			irq_subclass_unregister(IRQ_SUBCLASS_MEASUREMENT_ALERT);
 			deallocate_sdbt();
 		}
 		if (hws_wq) {
@@ -1190,7 +1190,7 @@ start_all_exit:
 	hws_oom = 1;
 	hws_flush_all = 0;
 	/* now let them in, 1407 CPUMF external interrupts */
-	measurement_alert_subclass_register();
+	irq_subclass_register(IRQ_SUBCLASS_MEASUREMENT_ALERT);
 
 	return 0;
 }
diff --git a/arch/s390/oprofile/init.c b/arch/s390/oprofile/init.c
index 930783d2c99b..04e1b6a85362 100644
--- a/arch/s390/oprofile/init.c
+++ b/arch/s390/oprofile/init.c
@@ -346,16 +346,15 @@ static const struct file_operations timer_enabled_fops = {
 };
 
 
-static int oprofile_create_hwsampling_files(struct super_block *sb,
-					    struct dentry *root)
+static int oprofile_create_hwsampling_files(struct dentry *root)
 {
 	struct dentry *dir;
 
-	dir = oprofilefs_mkdir(sb, root, "timer");
+	dir = oprofilefs_mkdir(root, "timer");
 	if (!dir)
 		return -EINVAL;
 
-	oprofilefs_create_file(sb, dir, "enabled", &timer_enabled_fops);
+	oprofilefs_create_file(dir, "enabled", &timer_enabled_fops);
 
 	if (!hwsampler_available)
 		return 0;
@@ -376,17 +375,17 @@ static int oprofile_create_hwsampling_files(struct super_block *sb,
 		 * and can only be set to 0.
 		 */
 
-		dir = oprofilefs_mkdir(sb, root, "0");
+		dir = oprofilefs_mkdir(root, "0");
 		if (!dir)
 			return -EINVAL;
 
-		oprofilefs_create_file(sb, dir, "enabled", &hwsampler_fops);
-		oprofilefs_create_file(sb, dir, "event", &zero_fops);
-		oprofilefs_create_file(sb, dir, "count", &hw_interval_fops);
-		oprofilefs_create_file(sb, dir, "unit_mask", &zero_fops);
-		oprofilefs_create_file(sb, dir, "kernel", &kernel_fops);
-		oprofilefs_create_file(sb, dir, "user", &user_fops);
-		oprofilefs_create_ulong(sb, dir, "hw_sdbt_blocks",
+		oprofilefs_create_file(dir, "enabled", &hwsampler_fops);
+		oprofilefs_create_file(dir, "event", &zero_fops);
+		oprofilefs_create_file(dir, "count", &hw_interval_fops);
+		oprofilefs_create_file(dir, "unit_mask", &zero_fops);
+		oprofilefs_create_file(dir, "kernel", &kernel_fops);
+		oprofilefs_create_file(dir, "user", &user_fops);
+		oprofilefs_create_ulong(dir, "hw_sdbt_blocks",
 					&oprofile_sdbt_blocks);
 
 	} else {
@@ -396,19 +395,19 @@ static int oprofile_create_hwsampling_files(struct super_block *sb,
 		 * space tools.  The /dev/oprofile/hwsampling fs is
 		 * provided in that case.
 		 */
-		dir = oprofilefs_mkdir(sb, root, "hwsampling");
+		dir = oprofilefs_mkdir(root, "hwsampling");
 		if (!dir)
 			return -EINVAL;
 
-		oprofilefs_create_file(sb, dir, "hwsampler",
+		oprofilefs_create_file(dir, "hwsampler",
 				       &hwsampler_fops);
-		oprofilefs_create_file(sb, dir, "hw_interval",
+		oprofilefs_create_file(dir, "hw_interval",
 				       &hw_interval_fops);
-		oprofilefs_create_ro_ulong(sb, dir, "hw_min_interval",
+		oprofilefs_create_ro_ulong(dir, "hw_min_interval",
 					   &oprofile_min_interval);
-		oprofilefs_create_ro_ulong(sb, dir, "hw_max_interval",
+		oprofilefs_create_ro_ulong(dir, "hw_max_interval",
 					   &oprofile_max_interval);
-		oprofilefs_create_ulong(sb, dir, "hw_sdbt_blocks",
+		oprofilefs_create_ulong(dir, "hw_sdbt_blocks",
 					&oprofile_sdbt_blocks);
 	}
 	return 0;
diff --git a/arch/s390/pci/Makefile b/arch/s390/pci/Makefile
index 086a2e37935d..a9e1dc4ae442 100644
--- a/arch/s390/pci/Makefile
+++ b/arch/s390/pci/Makefile
@@ -2,5 +2,5 @@
 # Makefile for the s390 PCI subsystem.
 #
 
-obj-$(CONFIG_PCI)	+= pci.o pci_dma.o pci_clp.o pci_msi.o pci_sysfs.o \
+obj-$(CONFIG_PCI)	+= pci.o pci_dma.o pci_clp.o pci_sysfs.o \
 			   pci_event.o pci_debug.o pci_insn.o
diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c
index e2956ad39a4f..f17a8343e360 100644
--- a/arch/s390/pci/pci.c
+++ b/arch/s390/pci/pci.c
@@ -42,45 +42,26 @@
 #define	SIC_IRQ_MODE_SINGLE		1
 
 #define ZPCI_NR_DMA_SPACES		1
-#define ZPCI_MSI_VEC_BITS		6
 #define ZPCI_NR_DEVICES			CONFIG_PCI_NR_FUNCTIONS
 
 /* list of all detected zpci devices */
-LIST_HEAD(zpci_list);
-EXPORT_SYMBOL_GPL(zpci_list);
-DEFINE_MUTEX(zpci_list_lock);
-EXPORT_SYMBOL_GPL(zpci_list_lock);
+static LIST_HEAD(zpci_list);
+static DEFINE_SPINLOCK(zpci_list_lock);
 
-static struct pci_hp_callback_ops *hotplug_ops;
+static void zpci_enable_irq(struct irq_data *data);
+static void zpci_disable_irq(struct irq_data *data);
 
-static DECLARE_BITMAP(zpci_domain, ZPCI_NR_DEVICES);
-static DEFINE_SPINLOCK(zpci_domain_lock);
-
-struct callback {
-	irq_handler_t	handler;
-	void		*data;
+static struct irq_chip zpci_irq_chip = {
+	.name = "zPCI",
+	.irq_unmask = zpci_enable_irq,
+	.irq_mask = zpci_disable_irq,
 };
 
-struct zdev_irq_map {
-	unsigned long	aibv;		/* AI bit vector */
-	int		msi_vecs;	/* consecutive MSI-vectors used */
-	int		__unused;
-	struct callback	cb[ZPCI_NR_MSI_VECS]; /* callback handler array */
-	spinlock_t	lock;		/* protect callbacks against de-reg */
-};
-
-struct intr_bucket {
-	/* amap of adapters, one bit per dev, corresponds to one irq nr */
-	unsigned long	*alloc;
-	/* AI summary bit, global page for all devices */
-	unsigned long	*aisb;
-	/* pointer to aibv and callback data in zdev */
-	struct zdev_irq_map *imap[ZPCI_NR_DEVICES];
-	/* protects the whole bucket struct */
-	spinlock_t	lock;
-};
+static DECLARE_BITMAP(zpci_domain, ZPCI_NR_DEVICES);
+static DEFINE_SPINLOCK(zpci_domain_lock);
 
-static struct intr_bucket *bucket;
+static struct airq_iv *zpci_aisb_iv;
+static struct airq_iv *zpci_aibv[ZPCI_NR_DEVICES];
 
 /* Adapter interrupt definitions */
 static void zpci_irq_handler(struct airq_struct *airq);
@@ -96,27 +77,8 @@ static DECLARE_BITMAP(zpci_iomap, ZPCI_IOMAP_MAX_ENTRIES);
 struct zpci_iomap_entry *zpci_iomap_start;
 EXPORT_SYMBOL_GPL(zpci_iomap_start);
 
-/* highest irq summary bit */
-static int __read_mostly aisb_max;
-
-static struct kmem_cache *zdev_irq_cache;
 static struct kmem_cache *zdev_fmb_cache;
 
-static inline int irq_to_msi_nr(unsigned int irq)
-{
-	return irq & ZPCI_MSI_MASK;
-}
-
-static inline int irq_to_dev_nr(unsigned int irq)
-{
-	return irq >> ZPCI_MSI_VEC_BITS;
-}
-
-static inline struct zdev_irq_map *get_imap(unsigned int irq)
-{
-	return bucket->imap[irq_to_dev_nr(irq)];
-}
-
 struct zpci_dev *get_zdev(struct pci_dev *pdev)
 {
 	return (struct zpci_dev *) pdev->sysdata;
@@ -126,22 +88,17 @@ struct zpci_dev *get_zdev_by_fid(u32 fid)
 {
 	struct zpci_dev *tmp, *zdev = NULL;
 
-	mutex_lock(&zpci_list_lock);
+	spin_lock(&zpci_list_lock);
 	list_for_each_entry(tmp, &zpci_list, entry) {
 		if (tmp->fid == fid) {
 			zdev = tmp;
 			break;
 		}
 	}
-	mutex_unlock(&zpci_list_lock);
+	spin_unlock(&zpci_list_lock);
 	return zdev;
 }
 
-bool zpci_fid_present(u32 fid)
-{
-	return (get_zdev_by_fid(fid) != NULL) ? true : false;
-}
-
 static struct zpci_dev *get_zdev_by_bus(struct pci_bus *bus)
 {
 	return (bus && bus->sysdata) ? (struct zpci_dev *) bus->sysdata : NULL;
@@ -160,8 +117,7 @@ int pci_proc_domain(struct pci_bus *bus)
 EXPORT_SYMBOL_GPL(pci_proc_domain);
 
 /* Modify PCI: Register adapter interruptions */
-static int zpci_register_airq(struct zpci_dev *zdev, unsigned int aisb,
-			      u64 aibv)
+static int zpci_set_airq(struct zpci_dev *zdev)
 {
 	u64 req = ZPCI_CREATE_REQ(zdev->fh, 0, ZPCI_MOD_FC_REG_INT);
 	struct zpci_fib *fib;
@@ -172,14 +128,14 @@ static int zpci_register_airq(struct zpci_dev *zdev, unsigned int aisb,
 		return -ENOMEM;
 
 	fib->isc = PCI_ISC;
-	fib->noi = zdev->irq_map->msi_vecs;
 	fib->sum = 1;		/* enable summary notifications */
-	fib->aibv = aibv;
-	fib->aibvo = 0;		/* every function has its own page */
-	fib->aisb = (u64) bucket->aisb + aisb / 8;
-	fib->aisbo = aisb & ZPCI_MSI_MASK;
+	fib->noi = airq_iv_end(zdev->aibv);
+	fib->aibv = (unsigned long) zdev->aibv->vector;
+	fib->aibvo = 0;		/* each zdev has its own interrupt vector */
+	fib->aisb = (unsigned long) zpci_aisb_iv->vector + (zdev->aisb/64)*8;
+	fib->aisbo = zdev->aisb & 63;
 
-	rc = s390pci_mod_fc(req, fib);
+	rc = zpci_mod_fc(req, fib);
 	pr_debug("%s mpcifc returned noi: %d\n", __func__, fib->noi);
 
 	free_page((unsigned long) fib);
@@ -209,7 +165,7 @@ static int mod_pci(struct zpci_dev *zdev, int fn, u8 dmaas, struct mod_pci_args
 	fib->iota = args->iota;
 	fib->fmb_addr = args->fmb_addr;
 
-	rc = s390pci_mod_fc(req, fib);
+	rc = zpci_mod_fc(req, fib);
 	free_page((unsigned long) fib);
 	return rc;
 }
@@ -234,7 +190,7 @@ int zpci_unregister_ioat(struct zpci_dev *zdev, u8 dmaas)
 }
 
 /* Modify PCI: Unregister adapter interruptions */
-static int zpci_unregister_airq(struct zpci_dev *zdev)
+static int zpci_clear_airq(struct zpci_dev *zdev)
 {
 	struct mod_pci_args args = { 0, 0, 0, 0 };
 
@@ -283,7 +239,7 @@ static int zpci_cfg_load(struct zpci_dev *zdev, int offset, u32 *val, u8 len)
 	u64 data;
 	int rc;
 
-	rc = s390pci_load(&data, req, offset);
+	rc = zpci_load(&data, req, offset);
 	if (!rc) {
 		data = data << ((8 - len) * 8);
 		data = le64_to_cpu(data);
@@ -301,25 +257,46 @@ static int zpci_cfg_store(struct zpci_dev *zdev, int offset, u32 val, u8 len)
 
 	data = cpu_to_le64(data);
 	data = data >> ((8 - len) * 8);
-	rc = s390pci_store(data, req, offset);
+	rc = zpci_store(data, req, offset);
 	return rc;
 }
 
-void enable_irq(unsigned int irq)
+static int zpci_msi_set_mask_bits(struct msi_desc *msi, u32 mask, u32 flag)
+{
+	int offset, pos;
+	u32 mask_bits;
+
+	if (msi->msi_attrib.is_msix) {
+		offset = msi->msi_attrib.entry_nr * PCI_MSIX_ENTRY_SIZE +
+			PCI_MSIX_ENTRY_VECTOR_CTRL;
+		msi->masked = readl(msi->mask_base + offset);
+		writel(flag, msi->mask_base + offset);
+	} else if (msi->msi_attrib.maskbit) {
+		pos = (long) msi->mask_base;
+		pci_read_config_dword(msi->dev, pos, &mask_bits);
+		mask_bits &= ~(mask);
+		mask_bits |= flag & mask;
+		pci_write_config_dword(msi->dev, pos, mask_bits);
+	} else
+		return 0;
+
+	msi->msi_attrib.maskbit = !!flag;
+	return 1;
+}
+
+static void zpci_enable_irq(struct irq_data *data)
 {
-	struct msi_desc *msi = irq_get_msi_desc(irq);
+	struct msi_desc *msi = irq_get_msi_desc(data->irq);
 
 	zpci_msi_set_mask_bits(msi, 1, 0);
 }
-EXPORT_SYMBOL_GPL(enable_irq);
 
-void disable_irq(unsigned int irq)
+static void zpci_disable_irq(struct irq_data *data)
 {
-	struct msi_desc *msi = irq_get_msi_desc(irq);
+	struct msi_desc *msi = irq_get_msi_desc(data->irq);
 
 	zpci_msi_set_mask_bits(msi, 1, 1);
 }
-EXPORT_SYMBOL_GPL(disable_irq);
 
 void pcibios_fixup_bus(struct pci_bus *bus)
 {
@@ -404,152 +381,147 @@ static struct pci_ops pci_root_ops = {
 	.write = pci_write,
 };
 
-/* store the last handled bit to implement fair scheduling of devices */
-static DEFINE_PER_CPU(unsigned long, next_sbit);
-
 static void zpci_irq_handler(struct airq_struct *airq)
 {
-	unsigned long sbit, mbit, last = 0, start = __get_cpu_var(next_sbit);
-	int rescan = 0, max = aisb_max;
-	struct zdev_irq_map *imap;
+	unsigned long si, ai;
+	struct airq_iv *aibv;
+	int irqs_on = 0;
 
 	inc_irq_stat(IRQIO_PCI);
-	sbit = start;
-
-scan:
-	/* find summary_bit */
-	for_each_set_bit_left_cont(sbit, bucket->aisb, max) {
-		clear_bit(63 - (sbit & 63), bucket->aisb + (sbit >> 6));
-		last = sbit;
+	for (si = 0;;) {
+		/* Scan adapter summary indicator bit vector */
+		si = airq_iv_scan(zpci_aisb_iv, si, airq_iv_end(zpci_aisb_iv));
+		if (si == -1UL) {
+			if (irqs_on++)
+				/* End of second scan with interrupts on. */
+				break;
+			/* First scan complete, reenable interrupts. */
+			zpci_set_irq_ctrl(SIC_IRQ_MODE_SINGLE, NULL, PCI_ISC);
+			si = 0;
+			continue;
+		}
 
-		/* find vector bit */
-		imap = bucket->imap[sbit];
-		for_each_set_bit_left(mbit, &imap->aibv, imap->msi_vecs) {
+		/* Scan the adapter interrupt vector for this device. */
+		aibv = zpci_aibv[si];
+		for (ai = 0;;) {
+			ai = airq_iv_scan(aibv, ai, airq_iv_end(aibv));
+			if (ai == -1UL)
+				break;
 			inc_irq_stat(IRQIO_MSI);
-			clear_bit(63 - mbit, &imap->aibv);
-
-			spin_lock(&imap->lock);
-			if (imap->cb[mbit].handler)
-				imap->cb[mbit].handler(mbit,
-					imap->cb[mbit].data);
-			spin_unlock(&imap->lock);
+			airq_iv_lock(aibv, ai);
+			generic_handle_irq(airq_iv_get_data(aibv, ai));
+			airq_iv_unlock(aibv, ai);
 		}
 	}
-
-	if (rescan)
-		goto out;
-
-	/* scan the skipped bits */
-	if (start > 0) {
-		sbit = 0;
-		max = start;
-		start = 0;
-		goto scan;
-	}
-
-	/* enable interrupts again */
-	set_irq_ctrl(SIC_IRQ_MODE_SINGLE, NULL, PCI_ISC);
-
-	/* check again to not lose initiative */
-	rmb();
-	max = aisb_max;
-	sbit = find_first_bit_left(bucket->aisb, max);
-	if (sbit != max) {
-		rescan++;
-		goto scan;
-	}
-out:
-	/* store next device bit to scan */
-	__get_cpu_var(next_sbit) = (++last >= aisb_max) ? 0 : last;
 }
 
-/* msi_vecs - number of requested interrupts, 0 place function to error state */
-static int zpci_setup_msi(struct pci_dev *pdev, int msi_vecs)
+int arch_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
 {
 	struct zpci_dev *zdev = get_zdev(pdev);
-	unsigned int aisb, msi_nr;
+	unsigned int hwirq, irq, msi_vecs;
+	unsigned long aisb;
 	struct msi_desc *msi;
+	struct msi_msg msg;
 	int rc;
 
-	/* store the number of used MSI vectors */
-	zdev->irq_map->msi_vecs = min(msi_vecs, ZPCI_NR_MSI_VECS);
-
-	spin_lock(&bucket->lock);
-	aisb = find_first_zero_bit(bucket->alloc, PAGE_SIZE);
-	/* alloc map exhausted? */
-	if (aisb == PAGE_SIZE) {
-		spin_unlock(&bucket->lock);
-		return -EIO;
-	}
-	set_bit(aisb, bucket->alloc);
-	spin_unlock(&bucket->lock);
+	pr_debug("%s: requesting %d MSI-X interrupts...", __func__, nvec);
+	if (type != PCI_CAP_ID_MSIX && type != PCI_CAP_ID_MSI)
+		return -EINVAL;
+	msi_vecs = min(nvec, ZPCI_MSI_VEC_MAX);
+	msi_vecs = min_t(unsigned int, msi_vecs, CONFIG_PCI_NR_MSI);
 
+	/* Allocate adapter summary indicator bit */
+	rc = -EIO;
+	aisb = airq_iv_alloc_bit(zpci_aisb_iv);
+	if (aisb == -1UL)
+		goto out;
 	zdev->aisb = aisb;
-	if (aisb + 1 > aisb_max)
-		aisb_max = aisb + 1;
 
-	/* wire up IRQ shortcut pointer */
-	bucket->imap[zdev->aisb] = zdev->irq_map;
-	pr_debug("%s: imap[%u] linked to %p\n", __func__, zdev->aisb, zdev->irq_map);
+	/* Create adapter interrupt vector */
+	rc = -ENOMEM;
+	zdev->aibv = airq_iv_create(msi_vecs, AIRQ_IV_DATA | AIRQ_IV_BITLOCK);
+	if (!zdev->aibv)
+		goto out_si;
 
-	/* TODO: irq number 0 wont be found if we return less than requested MSIs.
-	 * ignore it for now and fix in common code.
-	 */
-	msi_nr = aisb << ZPCI_MSI_VEC_BITS;
+	/* Wire up shortcut pointer */
+	zpci_aibv[aisb] = zdev->aibv;
 
+	/* Request MSI interrupts */
+	hwirq = 0;
 	list_for_each_entry(msi, &pdev->msi_list, list) {
-		rc = zpci_setup_msi_irq(zdev, msi, msi_nr,
-					  aisb << ZPCI_MSI_VEC_BITS);
+		rc = -EIO;
+		irq = irq_alloc_desc(0);	/* Alloc irq on node 0 */
+		if (irq == NO_IRQ)
+			goto out_msi;
+		rc = irq_set_msi_desc(irq, msi);
 		if (rc)
-			return rc;
-		msi_nr++;
+			goto out_msi;
+		irq_set_chip_and_handler(irq, &zpci_irq_chip,
+					 handle_simple_irq);
+		msg.data = hwirq;
+		msg.address_lo = zdev->msi_addr & 0xffffffff;
+		msg.address_hi = zdev->msi_addr >> 32;
+		write_msi_msg(irq, &msg);
+		airq_iv_set_data(zdev->aibv, hwirq, irq);
+		hwirq++;
 	}
 
-	rc = zpci_register_airq(zdev, aisb, (u64) &zdev->irq_map->aibv);
-	if (rc) {
-		clear_bit(aisb, bucket->alloc);
-		dev_err(&pdev->dev, "register MSI failed with: %d\n", rc);
-		return rc;
+	/* Enable adapter interrupts */
+	rc = zpci_set_airq(zdev);
+	if (rc)
+		goto out_msi;
+
+	return (msi_vecs == nvec) ? 0 : msi_vecs;
+
+out_msi:
+	list_for_each_entry(msi, &pdev->msi_list, list) {
+		if (hwirq-- == 0)
+			break;
+		irq_set_msi_desc(msi->irq, NULL);
+		irq_free_desc(msi->irq);
+		msi->msg.address_lo = 0;
+		msi->msg.address_hi = 0;
+		msi->msg.data = 0;
+		msi->irq = 0;
 	}
-	return (zdev->irq_map->msi_vecs == msi_vecs) ?
-		0 : zdev->irq_map->msi_vecs;
+	zpci_aibv[aisb] = NULL;
+	airq_iv_release(zdev->aibv);
+out_si:
+	airq_iv_free_bit(zpci_aisb_iv, aisb);
+out:
+	dev_err(&pdev->dev, "register MSI failed with: %d\n", rc);
+	return rc;
 }
 
-static void zpci_teardown_msi(struct pci_dev *pdev)
+void arch_teardown_msi_irqs(struct pci_dev *pdev)
 {
 	struct zpci_dev *zdev = get_zdev(pdev);
 	struct msi_desc *msi;
-	int aisb, rc;
+	int rc;
 
-	rc = zpci_unregister_airq(zdev);
+	pr_info("%s: on pdev: %p\n", __func__, pdev);
+
+	/* Disable adapter interrupts */
+	rc = zpci_clear_airq(zdev);
 	if (rc) {
 		dev_err(&pdev->dev, "deregister MSI failed with: %d\n", rc);
 		return;
 	}
 
-	msi = list_first_entry(&pdev->msi_list, struct msi_desc, list);
-	aisb = irq_to_dev_nr(msi->irq);
-
-	list_for_each_entry(msi, &pdev->msi_list, list)
-		zpci_teardown_msi_irq(zdev, msi);
-
-	clear_bit(aisb, bucket->alloc);
-	if (aisb + 1 == aisb_max)
-		aisb_max--;
-}
-
-int arch_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
-{
-	pr_debug("%s: requesting %d MSI-X interrupts...", __func__, nvec);
-	if (type != PCI_CAP_ID_MSIX && type != PCI_CAP_ID_MSI)
-		return -EINVAL;
-	return zpci_setup_msi(pdev, nvec);
-}
+	/* Release MSI interrupts */
+	list_for_each_entry(msi, &pdev->msi_list, list) {
+		zpci_msi_set_mask_bits(msi, 1, 1);
+		irq_set_msi_desc(msi->irq, NULL);
+		irq_free_desc(msi->irq);
+		msi->msg.address_lo = 0;
+		msi->msg.address_hi = 0;
+		msi->msg.data = 0;
+		msi->irq = 0;
+	}
 
-void arch_teardown_msi_irqs(struct pci_dev *pdev)
-{
-	pr_info("%s: on pdev: %p\n", __func__, pdev);
-	zpci_teardown_msi(pdev);
+	zpci_aibv[zdev->aisb] = NULL;
+	airq_iv_release(zdev->aibv);
+	airq_iv_free_bit(zpci_aisb_iv, zdev->aisb);
 }
 
 static void zpci_map_resources(struct zpci_dev *zdev)
@@ -564,8 +536,6 @@ static void zpci_map_resources(struct zpci_dev *zdev)
 			continue;
 		pdev->resource[i].start = (resource_size_t) pci_iomap(pdev, i, 0);
 		pdev->resource[i].end = pdev->resource[i].start + len - 1;
-		pr_debug("BAR%i: -> start: %Lx  end: %Lx\n",
-			i, pdev->resource[i].start, pdev->resource[i].end);
 	}
 }
 
@@ -589,162 +559,47 @@ struct zpci_dev *zpci_alloc_device(void)
 
 	/* Alloc memory for our private pci device data */
 	zdev = kzalloc(sizeof(*zdev), GFP_KERNEL);
-	if (!zdev)
-		return ERR_PTR(-ENOMEM);
-
-	/* Alloc aibv & callback space */
-	zdev->irq_map = kmem_cache_zalloc(zdev_irq_cache, GFP_KERNEL);
-	if (!zdev->irq_map)
-		goto error;
-	WARN_ON((u64) zdev->irq_map & 0xff);
-	return zdev;
-
-error:
-	kfree(zdev);
-	return ERR_PTR(-ENOMEM);
+	return zdev ? : ERR_PTR(-ENOMEM);
 }
 
 void zpci_free_device(struct zpci_dev *zdev)
 {
-	kmem_cache_free(zdev_irq_cache, zdev->irq_map);
 	kfree(zdev);
 }
 
-/*
- * Too late for any s390 specific setup, since interrupts must be set up
- * already which requires DMA setup too and the pci scan will access the
- * config space, which only works if the function handle is enabled.
- */
-int pcibios_enable_device(struct pci_dev *pdev, int mask)
-{
-	struct resource *res;
-	u16 cmd;
-	int i;
-
-	pci_read_config_word(pdev, PCI_COMMAND, &cmd);
-
-	for (i = 0; i < PCI_BAR_COUNT; i++) {
-		res = &pdev->resource[i];
-
-		if (res->flags & IORESOURCE_IO)
-			return -EINVAL;
-
-		if (res->flags & IORESOURCE_MEM)
-			cmd |= PCI_COMMAND_MEMORY;
-	}
-	pci_write_config_word(pdev, PCI_COMMAND, cmd);
-	return 0;
-}
-
 int pcibios_add_platform_entries(struct pci_dev *pdev)
 {
 	return zpci_sysfs_add_device(&pdev->dev);
 }
 
-int zpci_request_irq(unsigned int irq, irq_handler_t handler, void *data)
-{
-	int msi_nr = irq_to_msi_nr(irq);
-	struct zdev_irq_map *imap;
-	struct msi_desc *msi;
-
-	msi = irq_get_msi_desc(irq);
-	if (!msi)
-		return -EIO;
-
-	imap = get_imap(irq);
-	spin_lock_init(&imap->lock);
-
-	pr_debug("%s: register handler for IRQ:MSI %d:%d\n", __func__, irq >> 6, msi_nr);
-	imap->cb[msi_nr].handler = handler;
-	imap->cb[msi_nr].data = data;
-
-	/*
-	 * The generic MSI code returns with the interrupt disabled on the
-	 * card, using the MSI mask bits. Firmware doesn't appear to unmask
-	 * at that level, so we do it here by hand.
-	 */
-	zpci_msi_set_mask_bits(msi, 1, 0);
-	return 0;
-}
-
-void zpci_free_irq(unsigned int irq)
-{
-	struct zdev_irq_map *imap = get_imap(irq);
-	int msi_nr = irq_to_msi_nr(irq);
-	unsigned long flags;
-
-	pr_debug("%s: for irq: %d\n", __func__, irq);
-
-	spin_lock_irqsave(&imap->lock, flags);
-	imap->cb[msi_nr].handler = NULL;
-	imap->cb[msi_nr].data = NULL;
-	spin_unlock_irqrestore(&imap->lock, flags);
-}
-
-int request_irq(unsigned int irq, irq_handler_t handler,
-		unsigned long irqflags, const char *devname, void *dev_id)
-{
-	pr_debug("%s: irq: %d  handler: %p  flags: %lx  dev: %s\n",
-		__func__, irq, handler, irqflags, devname);
-
-	return zpci_request_irq(irq, handler, dev_id);
-}
-EXPORT_SYMBOL_GPL(request_irq);
-
-void free_irq(unsigned int irq, void *dev_id)
-{
-	zpci_free_irq(irq);
-}
-EXPORT_SYMBOL_GPL(free_irq);
-
 static int __init zpci_irq_init(void)
 {
-	int cpu, rc;
-
-	bucket = kzalloc(sizeof(*bucket), GFP_KERNEL);
-	if (!bucket)
-		return -ENOMEM;
-
-	bucket->aisb = (unsigned long *) get_zeroed_page(GFP_KERNEL);
-	if (!bucket->aisb) {
-		rc = -ENOMEM;
-		goto out_aisb;
-	}
-
-	bucket->alloc = (unsigned long *) get_zeroed_page(GFP_KERNEL);
-	if (!bucket->alloc) {
-		rc = -ENOMEM;
-		goto out_alloc;
-	}
+	int rc;
 
 	rc = register_adapter_interrupt(&zpci_airq);
 	if (rc)
-		goto out_ai;
+		goto out;
 	/* Set summary to 1 to be called every time for the ISC. */
 	*zpci_airq.lsi_ptr = 1;
 
-	for_each_online_cpu(cpu)
-		per_cpu(next_sbit, cpu) = 0;
+	rc = -ENOMEM;
+	zpci_aisb_iv = airq_iv_create(ZPCI_NR_DEVICES, AIRQ_IV_ALLOC);
+	if (!zpci_aisb_iv)
+		goto out_airq;
 
-	spin_lock_init(&bucket->lock);
-	set_irq_ctrl(SIC_IRQ_MODE_SINGLE, NULL, PCI_ISC);
+	zpci_set_irq_ctrl(SIC_IRQ_MODE_SINGLE, NULL, PCI_ISC);
 	return 0;
 
-out_ai:
-	free_page((unsigned long) bucket->alloc);
-out_alloc:
-	free_page((unsigned long) bucket->aisb);
-out_aisb:
-	kfree(bucket);
+out_airq:
+	unregister_adapter_interrupt(&zpci_airq);
+out:
 	return rc;
 }
 
 static void zpci_irq_exit(void)
 {
-	free_page((unsigned long) bucket->alloc);
-	free_page((unsigned long) bucket->aisb);
+	airq_iv_release(zpci_aisb_iv);
 	unregister_adapter_interrupt(&zpci_airq);
-	kfree(bucket);
 }
 
 static struct resource *zpci_alloc_bus_resource(unsigned long start, unsigned long size,
@@ -801,16 +656,49 @@ static void zpci_free_iomap(struct zpci_dev *zdev, int entry)
 int pcibios_add_device(struct pci_dev *pdev)
 {
 	struct zpci_dev *zdev = get_zdev(pdev);
+	struct resource *res;
+	int i;
+
+	zdev->pdev = pdev;
+	zpci_map_resources(zdev);
+
+	for (i = 0; i < PCI_BAR_COUNT; i++) {
+		res = &pdev->resource[i];
+		if (res->parent || !res->flags)
+			continue;
+		pci_claim_resource(pdev, i);
+	}
+
+	return 0;
+}
+
+int pcibios_enable_device(struct pci_dev *pdev, int mask)
+{
+	struct zpci_dev *zdev = get_zdev(pdev);
+	struct resource *res;
+	u16 cmd;
+	int i;
 
 	zdev->pdev = pdev;
 	zpci_debug_init_device(zdev);
 	zpci_fmb_enable_device(zdev);
 	zpci_map_resources(zdev);
 
+	pci_read_config_word(pdev, PCI_COMMAND, &cmd);
+	for (i = 0; i < PCI_BAR_COUNT; i++) {
+		res = &pdev->resource[i];
+
+		if (res->flags & IORESOURCE_IO)
+			return -EINVAL;
+
+		if (res->flags & IORESOURCE_MEM)
+			cmd |= PCI_COMMAND_MEMORY;
+	}
+	pci_write_config_word(pdev, PCI_COMMAND, cmd);
 	return 0;
 }
 
-void pcibios_release_device(struct pci_dev *pdev)
+void pcibios_disable_device(struct pci_dev *pdev)
 {
 	struct zpci_dev *zdev = get_zdev(pdev);
 
@@ -898,6 +786,8 @@ int zpci_enable_device(struct zpci_dev *zdev)
 	rc = zpci_dma_init_device(zdev);
 	if (rc)
 		goto out_dma;
+
+	zdev->state = ZPCI_FN_STATE_ONLINE;
 	return 0;
 
 out_dma:
@@ -926,18 +816,16 @@ int zpci_create_device(struct zpci_dev *zdev)
 		rc = zpci_enable_device(zdev);
 		if (rc)
 			goto out_free;
-
-		zdev->state = ZPCI_FN_STATE_ONLINE;
 	}
 	rc = zpci_scan_bus(zdev);
 	if (rc)
 		goto out_disable;
 
-	mutex_lock(&zpci_list_lock);
+	spin_lock(&zpci_list_lock);
 	list_add_tail(&zdev->entry, &zpci_list);
-	if (hotplug_ops)
-		hotplug_ops->create_slot(zdev);
-	mutex_unlock(&zpci_list_lock);
+	spin_unlock(&zpci_list_lock);
+
+	zpci_init_slot(zdev);
 
 	return 0;
 
@@ -967,15 +855,10 @@ static inline int barsize(u8 size)
 
 static int zpci_mem_init(void)
 {
-	zdev_irq_cache = kmem_cache_create("PCI_IRQ_cache", sizeof(struct zdev_irq_map),
-				L1_CACHE_BYTES, SLAB_HWCACHE_ALIGN, NULL);
-	if (!zdev_irq_cache)
-		goto error_zdev;
-
 	zdev_fmb_cache = kmem_cache_create("PCI_FMB_cache", sizeof(struct zpci_fmb),
 				16, 0, NULL);
 	if (!zdev_fmb_cache)
-		goto error_fmb;
+		goto error_zdev;
 
 	/* TODO: use realloc */
 	zpci_iomap_start = kzalloc(ZPCI_IOMAP_MAX_ENTRIES * sizeof(*zpci_iomap_start),
@@ -986,8 +869,6 @@ static int zpci_mem_init(void)
 
 error_iomap:
 	kmem_cache_destroy(zdev_fmb_cache);
-error_fmb:
-	kmem_cache_destroy(zdev_irq_cache);
 error_zdev:
 	return -ENOMEM;
 }
@@ -995,28 +876,10 @@ error_zdev:
 static void zpci_mem_exit(void)
 {
 	kfree(zpci_iomap_start);
-	kmem_cache_destroy(zdev_irq_cache);
 	kmem_cache_destroy(zdev_fmb_cache);
 }
 
-void zpci_register_hp_ops(struct pci_hp_callback_ops *ops)
-{
-	mutex_lock(&zpci_list_lock);
-	hotplug_ops = ops;
-	mutex_unlock(&zpci_list_lock);
-}
-EXPORT_SYMBOL_GPL(zpci_register_hp_ops);
-
-void zpci_deregister_hp_ops(void)
-{
-	mutex_lock(&zpci_list_lock);
-	hotplug_ops = NULL;
-	mutex_unlock(&zpci_list_lock);
-}
-EXPORT_SYMBOL_GPL(zpci_deregister_hp_ops);
-
-unsigned int s390_pci_probe;
-EXPORT_SYMBOL_GPL(s390_pci_probe);
+static unsigned int s390_pci_probe;
 
 char * __init pcibios_setup(char *str)
 {
@@ -1044,16 +907,12 @@ static int __init pci_base_init(void)
 
 	rc = zpci_debug_init();
 	if (rc)
-		return rc;
+		goto out;
 
 	rc = zpci_mem_init();
 	if (rc)
 		goto out_mem;
 
-	rc = zpci_msihash_init();
-	if (rc)
-		goto out_hash;
-
 	rc = zpci_irq_init();
 	if (rc)
 		goto out_irq;
@@ -1062,7 +921,7 @@ static int __init pci_base_init(void)
 	if (rc)
 		goto out_dma;
 
-	rc = clp_find_pci_devices();
+	rc = clp_scan_pci_devices();
 	if (rc)
 		goto out_find;
 
@@ -1073,11 +932,15 @@ out_find:
 out_dma:
 	zpci_irq_exit();
 out_irq:
-	zpci_msihash_exit();
-out_hash:
 	zpci_mem_exit();
 out_mem:
 	zpci_debug_exit();
+out:
 	return rc;
 }
-subsys_initcall(pci_base_init);
+subsys_initcall_sync(pci_base_init);
+
+void zpci_rescan(void)
+{
+	clp_rescan_pci_devices_simple();
+}
diff --git a/arch/s390/pci/pci_clp.c b/arch/s390/pci/pci_clp.c
index 2e9539625d93..475563c3d1e4 100644
--- a/arch/s390/pci/pci_clp.c
+++ b/arch/s390/pci/pci_clp.c
@@ -36,9 +36,9 @@ static inline u8 clp_instr(void *data)
 	return cc;
 }
 
-static void *clp_alloc_block(void)
+static void *clp_alloc_block(gfp_t gfp_mask)
 {
-	return (void *) __get_free_pages(GFP_KERNEL, get_order(CLP_BLK_SIZE));
+	return (void *) __get_free_pages(gfp_mask, get_order(CLP_BLK_SIZE));
 }
 
 static void clp_free_block(void *ptr)
@@ -70,7 +70,7 @@ static int clp_query_pci_fngrp(struct zpci_dev *zdev, u8 pfgid)
 	struct clp_req_rsp_query_pci_grp *rrb;
 	int rc;
 
-	rrb = clp_alloc_block();
+	rrb = clp_alloc_block(GFP_KERNEL);
 	if (!rrb)
 		return -ENOMEM;
 
@@ -113,7 +113,7 @@ static int clp_query_pci_fn(struct zpci_dev *zdev, u32 fh)
 	struct clp_req_rsp_query_pci *rrb;
 	int rc;
 
-	rrb = clp_alloc_block();
+	rrb = clp_alloc_block(GFP_KERNEL);
 	if (!rrb)
 		return -ENOMEM;
 
@@ -179,9 +179,9 @@ error:
 static int clp_set_pci_fn(u32 *fh, u8 nr_dma_as, u8 command)
 {
 	struct clp_req_rsp_set_pci *rrb;
-	int rc, retries = 1000;
+	int rc, retries = 100;
 
-	rrb = clp_alloc_block();
+	rrb = clp_alloc_block(GFP_KERNEL);
 	if (!rrb)
 		return -ENOMEM;
 
@@ -199,7 +199,7 @@ static int clp_set_pci_fn(u32 *fh, u8 nr_dma_as, u8 command)
 			retries--;
 			if (retries < 0)
 				break;
-			msleep(1);
+			msleep(20);
 		}
 	} while (rrb->response.hdr.rsp == CLP_RC_SETPCIFN_BUSY);
 
@@ -245,49 +245,12 @@ int clp_disable_fh(struct zpci_dev *zdev)
 	return rc;
 }
 
-static void clp_check_pcifn_entry(struct clp_fh_list_entry *entry)
+static int clp_list_pci(struct clp_req_rsp_list_pci *rrb,
+			void (*cb)(struct clp_fh_list_entry *entry))
 {
-	int present, rc;
-
-	if (!entry->vendor_id)
-		return;
-
-	/* TODO: be a little bit more scalable */
-	present = zpci_fid_present(entry->fid);
-
-	if (present)
-		pr_debug("%s: device %x already present\n", __func__, entry->fid);
-
-	/* skip already used functions */
-	if (present && entry->config_state)
-		return;
-
-	/* aev 306: function moved to stand-by state */
-	if (present && !entry->config_state) {
-		/*
-		 * The handle is already disabled, that means no iota/irq freeing via
-		 * the firmware interfaces anymore. Need to free resources manually
-		 * (DMA memory, debug, sysfs)...
-		 */
-		zpci_stop_device(get_zdev_by_fid(entry->fid));
-		return;
-	}
-
-	rc = clp_add_pci_device(entry->fid, entry->fh, entry->config_state);
-	if (rc)
-		pr_err("Failed to add fid: 0x%x\n", entry->fid);
-}
-
-int clp_find_pci_devices(void)
-{
-	struct clp_req_rsp_list_pci *rrb;
 	u64 resume_token = 0;
 	int entries, i, rc;
 
-	rrb = clp_alloc_block();
-	if (!rrb)
-		return -ENOMEM;
-
 	do {
 		memset(rrb, 0, sizeof(*rrb));
 		rrb->request.hdr.len = sizeof(rrb->request);
@@ -316,12 +279,101 @@ int clp_find_pci_devices(void)
 		resume_token = rrb->response.resume_token;
 
 		for (i = 0; i < entries; i++)
-			clp_check_pcifn_entry(&rrb->response.fh_list[i]);
+			cb(&rrb->response.fh_list[i]);
 	} while (resume_token);
 
 	pr_debug("Maximum number of supported PCI functions: %u\n",
 		rrb->response.max_fn);
 out:
+	return rc;
+}
+
+static void __clp_add(struct clp_fh_list_entry *entry)
+{
+	if (!entry->vendor_id)
+		return;
+
+	clp_add_pci_device(entry->fid, entry->fh, entry->config_state);
+}
+
+static void __clp_rescan(struct clp_fh_list_entry *entry)
+{
+	struct zpci_dev *zdev;
+
+	if (!entry->vendor_id)
+		return;
+
+	zdev = get_zdev_by_fid(entry->fid);
+	if (!zdev) {
+		clp_add_pci_device(entry->fid, entry->fh, entry->config_state);
+		return;
+	}
+
+	if (!entry->config_state) {
+		/*
+		 * The handle is already disabled, that means no iota/irq freeing via
+		 * the firmware interfaces anymore. Need to free resources manually
+		 * (DMA memory, debug, sysfs)...
+		 */
+		zpci_stop_device(zdev);
+	}
+}
+
+static void __clp_update(struct clp_fh_list_entry *entry)
+{
+	struct zpci_dev *zdev;
+
+	if (!entry->vendor_id)
+		return;
+
+	zdev = get_zdev_by_fid(entry->fid);
+	if (!zdev)
+		return;
+
+	zdev->fh = entry->fh;
+}
+
+int clp_scan_pci_devices(void)
+{
+	struct clp_req_rsp_list_pci *rrb;
+	int rc;
+
+	rrb = clp_alloc_block(GFP_KERNEL);
+	if (!rrb)
+		return -ENOMEM;
+
+	rc = clp_list_pci(rrb, __clp_add);
+
+	clp_free_block(rrb);
+	return rc;
+}
+
+int clp_rescan_pci_devices(void)
+{
+	struct clp_req_rsp_list_pci *rrb;
+	int rc;
+
+	rrb = clp_alloc_block(GFP_KERNEL);
+	if (!rrb)
+		return -ENOMEM;
+
+	rc = clp_list_pci(rrb, __clp_rescan);
+
+	clp_free_block(rrb);
+	return rc;
+}
+
+int clp_rescan_pci_devices_simple(void)
+{
+	struct clp_req_rsp_list_pci *rrb;
+	int rc;
+
+	rrb = clp_alloc_block(GFP_NOWAIT);
+	if (!rrb)
+		return -ENOMEM;
+
+	rc = clp_list_pci(rrb, __clp_update);
+
 	clp_free_block(rrb);
 	return rc;
 }
diff --git a/arch/s390/pci/pci_dma.c b/arch/s390/pci/pci_dma.c
index a2343c1f6e04..7e5573acb063 100644
--- a/arch/s390/pci/pci_dma.c
+++ b/arch/s390/pci/pci_dma.c
@@ -10,6 +10,7 @@
 #include <linux/export.h>
 #include <linux/iommu-helper.h>
 #include <linux/dma-mapping.h>
+#include <linux/vmalloc.h>
 #include <linux/pci.h>
 #include <asm/pci_dma.h>
 
@@ -170,8 +171,8 @@ static int dma_update_trans(struct zpci_dev *zdev, unsigned long pa,
 		 */
 		goto no_refresh;
 
-	rc = s390pci_refresh_trans((u64) zdev->fh << 32, start_dma_addr,
-				   nr_pages * PAGE_SIZE);
+	rc = zpci_refresh_trans((u64) zdev->fh << 32, start_dma_addr,
+				nr_pages * PAGE_SIZE);
 
 no_refresh:
 	spin_unlock_irqrestore(&zdev->dma_table_lock, irq_flags);
@@ -407,7 +408,6 @@ static void s390_dma_unmap_sg(struct device *dev, struct scatterlist *sg,
 
 int zpci_dma_init_device(struct zpci_dev *zdev)
 {
-	unsigned int bitmap_order;
 	int rc;
 
 	spin_lock_init(&zdev->iommu_bitmap_lock);
@@ -421,12 +421,7 @@ int zpci_dma_init_device(struct zpci_dev *zdev)
 
 	zdev->iommu_size = (unsigned long) high_memory - PAGE_OFFSET;
 	zdev->iommu_pages = zdev->iommu_size >> PAGE_SHIFT;
-	bitmap_order = get_order(zdev->iommu_pages / 8);
-	pr_info("iommu_size: 0x%lx  iommu_pages: 0x%lx  bitmap_order: %i\n",
-		 zdev->iommu_size, zdev->iommu_pages, bitmap_order);
-
-	zdev->iommu_bitmap = (void *) __get_free_pages(GFP_KERNEL | __GFP_ZERO,
-						       bitmap_order);
+	zdev->iommu_bitmap = vzalloc(zdev->iommu_pages / 8);
 	if (!zdev->iommu_bitmap) {
 		rc = -ENOMEM;
 		goto out_reg;
@@ -451,8 +446,7 @@ void zpci_dma_exit_device(struct zpci_dev *zdev)
 {
 	zpci_unregister_ioat(zdev, 0);
 	dma_cleanup_tables(zdev);
-	free_pages((unsigned long) zdev->iommu_bitmap,
-		   get_order(zdev->iommu_pages / 8));
+	vfree(zdev->iommu_bitmap);
 	zdev->iommu_bitmap = NULL;
 	zdev->next_bit = 0;
 }
diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c
index ec62e3a0dc09..0aecaf954845 100644
--- a/arch/s390/pci/pci_event.c
+++ b/arch/s390/pci/pci_event.c
@@ -69,7 +69,7 @@ static void zpci_event_log_avail(struct zpci_ccdf_avail *ccdf)
 		clp_add_pci_device(ccdf->fid, ccdf->fh, 0);
 		break;
 	case 0x0306:
-		clp_find_pci_devices();
+		clp_rescan_pci_devices();
 		break;
 	default:
 		break;
diff --git a/arch/s390/pci/pci_insn.c b/arch/s390/pci/pci_insn.c
index 22eeb9d7ffeb..85267c058af8 100644
--- a/arch/s390/pci/pci_insn.c
+++ b/arch/s390/pci/pci_insn.c
@@ -27,7 +27,7 @@ static inline u8 __mpcifc(u64 req, struct zpci_fib *fib, u8 *status)
 	return cc;
 }
 
-int s390pci_mod_fc(u64 req, struct zpci_fib *fib)
+int zpci_mod_fc(u64 req, struct zpci_fib *fib)
 {
 	u8 cc, status;
 
@@ -61,7 +61,7 @@ static inline u8 __rpcit(u64 fn, u64 addr, u64 range, u8 *status)
 	return cc;
 }
 
-int s390pci_refresh_trans(u64 fn, u64 addr, u64 range)
+int zpci_refresh_trans(u64 fn, u64 addr, u64 range)
 {
 	u8 cc, status;
 
@@ -78,7 +78,7 @@ int s390pci_refresh_trans(u64 fn, u64 addr, u64 range)
 }
 
 /* Set Interruption Controls */
-void set_irq_ctrl(u16 ctl, char *unused, u8 isc)
+void zpci_set_irq_ctrl(u16 ctl, char *unused, u8 isc)
 {
 	asm volatile (
 		"	.insn	rsy,0xeb00000000d1,%[ctl],%[isc],%[u]\n"
@@ -109,7 +109,7 @@ static inline int __pcilg(u64 *data, u64 req, u64 offset, u8 *status)
 	return cc;
 }
 
-int s390pci_load(u64 *data, u64 req, u64 offset)
+int zpci_load(u64 *data, u64 req, u64 offset)
 {
 	u8 status;
 	int cc;
@@ -125,7 +125,7 @@ int s390pci_load(u64 *data, u64 req, u64 offset)
 			    __func__, cc, status, req, offset);
 	return (cc > 0) ? -EIO : cc;
 }
-EXPORT_SYMBOL_GPL(s390pci_load);
+EXPORT_SYMBOL_GPL(zpci_load);
 
 /* PCI Store */
 static inline int __pcistg(u64 data, u64 req, u64 offset, u8 *status)
@@ -147,7 +147,7 @@ static inline int __pcistg(u64 data, u64 req, u64 offset, u8 *status)
 	return cc;
 }
 
-int s390pci_store(u64 data, u64 req, u64 offset)
+int zpci_store(u64 data, u64 req, u64 offset)
 {
 	u8 status;
 	int cc;
@@ -163,7 +163,7 @@ int s390pci_store(u64 data, u64 req, u64 offset)
 			__func__, cc, status, req, offset);
 	return (cc > 0) ? -EIO : cc;
 }
-EXPORT_SYMBOL_GPL(s390pci_store);
+EXPORT_SYMBOL_GPL(zpci_store);
 
 /* PCI Store Block */
 static inline int __pcistb(const u64 *data, u64 req, u64 offset, u8 *status)
@@ -183,7 +183,7 @@ static inline int __pcistb(const u64 *data, u64 req, u64 offset, u8 *status)
 	return cc;
 }
 
-int s390pci_store_block(const u64 *data, u64 req, u64 offset)
+int zpci_store_block(const u64 *data, u64 req, u64 offset)
 {
 	u8 status;
 	int cc;
@@ -199,4 +199,4 @@ int s390pci_store_block(const u64 *data, u64 req, u64 offset)
 			    __func__, cc, status, req, offset);
 	return (cc > 0) ? -EIO : cc;
 }
-EXPORT_SYMBOL_GPL(s390pci_store_block);
+EXPORT_SYMBOL_GPL(zpci_store_block);
diff --git a/arch/s390/pci/pci_msi.c b/arch/s390/pci/pci_msi.c
deleted file mode 100644
index b097aed05a9b..000000000000
--- a/arch/s390/pci/pci_msi.c
+++ /dev/null
@@ -1,142 +0,0 @@
-/*
- * Copyright IBM Corp. 2012
- *
- * Author(s):
- *   Jan Glauber <jang@linux.vnet.ibm.com>
- */
-
-#define COMPONENT "zPCI"
-#define pr_fmt(fmt) COMPONENT ": " fmt
-
-#include <linux/kernel.h>
-#include <linux/err.h>
-#include <linux/rculist.h>
-#include <linux/hash.h>
-#include <linux/pci.h>
-#include <linux/msi.h>
-#include <asm/hw_irq.h>
-
-/* mapping of irq numbers to msi_desc */
-static struct hlist_head *msi_hash;
-static const unsigned int msi_hash_bits = 8;
-#define MSI_HASH_BUCKETS (1U << msi_hash_bits)
-#define msi_hashfn(nr)	hash_long(nr, msi_hash_bits)
-
-static DEFINE_SPINLOCK(msi_map_lock);
-
-struct msi_desc *__irq_get_msi_desc(unsigned int irq)
-{
-	struct msi_map *map;
-
-	hlist_for_each_entry_rcu(map,
-			&msi_hash[msi_hashfn(irq)], msi_chain)
-		if (map->irq == irq)
-			return map->msi;
-	return NULL;
-}
-
-int zpci_msi_set_mask_bits(struct msi_desc *msi, u32 mask, u32 flag)
-{
-	if (msi->msi_attrib.is_msix) {
-		int offset = msi->msi_attrib.entry_nr * PCI_MSIX_ENTRY_SIZE +
-			PCI_MSIX_ENTRY_VECTOR_CTRL;
-		msi->masked = readl(msi->mask_base + offset);
-		writel(flag, msi->mask_base + offset);
-	} else {
-		if (msi->msi_attrib.maskbit) {
-			int pos;
-			u32 mask_bits;
-
-			pos = (long) msi->mask_base;
-			pci_read_config_dword(msi->dev, pos, &mask_bits);
-			mask_bits &= ~(mask);
-			mask_bits |= flag & mask;
-			pci_write_config_dword(msi->dev, pos, mask_bits);
-		} else {
-			return 0;
-		}
-	}
-
-	msi->msi_attrib.maskbit = !!flag;
-	return 1;
-}
-
-int zpci_setup_msi_irq(struct zpci_dev *zdev, struct msi_desc *msi,
-			unsigned int nr, int offset)
-{
-	struct msi_map *map;
-	struct msi_msg msg;
-	int rc;
-
-	map = kmalloc(sizeof(*map), GFP_KERNEL);
-	if (map == NULL)
-		return -ENOMEM;
-
-	map->irq = nr;
-	map->msi = msi;
-	zdev->msi_map[nr & ZPCI_MSI_MASK] = map;
-	INIT_HLIST_NODE(&map->msi_chain);
-
-	pr_debug("%s hashing irq: %u  to bucket nr: %llu\n",
-		__func__, nr, msi_hashfn(nr));
-	hlist_add_head_rcu(&map->msi_chain, &msi_hash[msi_hashfn(nr)]);
-
-	spin_lock(&msi_map_lock);
-	rc = irq_set_msi_desc(nr, msi);
-	if (rc) {
-		spin_unlock(&msi_map_lock);
-		hlist_del_rcu(&map->msi_chain);
-		kfree(map);
-		zdev->msi_map[nr & ZPCI_MSI_MASK] = NULL;
-		return rc;
-	}
-	spin_unlock(&msi_map_lock);
-
-	msg.data = nr - offset;
-	msg.address_lo = zdev->msi_addr & 0xffffffff;
-	msg.address_hi = zdev->msi_addr >> 32;
-	write_msi_msg(nr, &msg);
-	return 0;
-}
-
-void zpci_teardown_msi_irq(struct zpci_dev *zdev, struct msi_desc *msi)
-{
-	int irq = msi->irq & ZPCI_MSI_MASK;
-	struct msi_map *map;
-
-	msi->msg.address_lo = 0;
-	msi->msg.address_hi = 0;
-	msi->msg.data = 0;
-	msi->irq = 0;
-	zpci_msi_set_mask_bits(msi, 1, 1);
-
-	spin_lock(&msi_map_lock);
-	map = zdev->msi_map[irq];
-	hlist_del_rcu(&map->msi_chain);
-	kfree(map);
-	zdev->msi_map[irq] = NULL;
-	spin_unlock(&msi_map_lock);
-}
-
-/*
- * The msi hash table has 256 entries which is good for 4..20
- * devices (a typical device allocates 10 + CPUs MSI's). Maybe make
- * the hash table size adjustable later.
- */
-int __init zpci_msihash_init(void)
-{
-	unsigned int i;
-
-	msi_hash = kmalloc(MSI_HASH_BUCKETS * sizeof(*msi_hash), GFP_KERNEL);
-	if (!msi_hash)
-		return -ENOMEM;
-
-	for (i = 0; i < MSI_HASH_BUCKETS; i++)
-		INIT_HLIST_HEAD(&msi_hash[i]);
-	return 0;
-}
-
-void __init zpci_msihash_exit(void)
-{
-	kfree(msi_hash);
-}
diff --git a/arch/s390/pci/pci_sysfs.c b/arch/s390/pci/pci_sysfs.c
index e99a2557f186..cf8a12ff733b 100644
--- a/arch/s390/pci/pci_sysfs.c
+++ b/arch/s390/pci/pci_sysfs.c
@@ -48,11 +48,38 @@ static ssize_t show_pfgid(struct device *dev, struct device_attribute *attr,
 }
 static DEVICE_ATTR(pfgid, S_IRUGO, show_pfgid, NULL);
 
+static void recover_callback(struct device *dev)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct zpci_dev *zdev = get_zdev(pdev);
+	int ret;
+
+	pci_stop_and_remove_bus_device(pdev);
+	ret = zpci_disable_device(zdev);
+	if (ret)
+		return;
+
+	ret = zpci_enable_device(zdev);
+	if (ret)
+		return;
+
+	pci_rescan_bus(zdev->bus);
+}
+
+static ssize_t store_recover(struct device *dev, struct device_attribute *attr,
+			     const char *buf, size_t count)
+{
+	int rc = device_schedule_callback(dev, recover_callback);
+	return rc ? rc : count;
+}
+static DEVICE_ATTR(recover, S_IWUSR, NULL, store_recover);
+
 static struct device_attribute *zpci_dev_attrs[] = {
 	&dev_attr_function_id,
 	&dev_attr_function_handle,
 	&dev_attr_pchid,
 	&dev_attr_pfgid,
+	&dev_attr_recover,
 	NULL,
 };
 
diff --git a/arch/score/Kconfig b/arch/score/Kconfig
index 5fc237581caf..305f7ee1f382 100644
--- a/arch/score/Kconfig
+++ b/arch/score/Kconfig
@@ -111,3 +111,6 @@ source "security/Kconfig"
 source "crypto/Kconfig"
 
 source "lib/Kconfig"
+
+config NO_IOMEM
+       def_bool y
diff --git a/arch/score/Makefile b/arch/score/Makefile
index 974aefe86123..9e3e060290e0 100644
--- a/arch/score/Makefile
+++ b/arch/score/Makefile
@@ -20,8 +20,8 @@ cflags-y += -G0 -pipe -mel -mnhwloop -D__SCOREEL__ \
 #
 KBUILD_AFLAGS += $(cflags-y)
 KBUILD_CFLAGS += $(cflags-y)
-KBUILD_AFLAGS_MODULE += -mlong-calls
-KBUILD_CFLAGS_MODULE += -mlong-calls
+KBUILD_AFLAGS_MODULE +=
+KBUILD_CFLAGS_MODULE +=
 LDFLAGS += --oformat elf32-littlescore
 LDFLAGS_vmlinux	+= -G0 -static -nostdlib
 
diff --git a/arch/score/include/asm/checksum.h b/arch/score/include/asm/checksum.h
index f909ac3144a4..961bd64015a8 100644
--- a/arch/score/include/asm/checksum.h
+++ b/arch/score/include/asm/checksum.h
@@ -184,48 +184,57 @@ static inline __sum16 csum_ipv6_magic(const struct in6_addr *saddr,
 				__wsum sum)
 {
 	__asm__ __volatile__(
-		".set\tnoreorder\t\t\t# csum_ipv6_magic\n\t"
-		".set\tnoat\n\t"
-		"addu\t%0, %5\t\t\t# proto (long in network byte order)\n\t"
-		"sltu\t$1, %0, %5\n\t"
-		"addu\t%0, $1\n\t"
-		"addu\t%0, %6\t\t\t# csum\n\t"
-		"sltu\t$1, %0, %6\n\t"
-		"lw\t%1, 0(%2)\t\t\t# four words source address\n\t"
-		"addu\t%0, $1\n\t"
-		"addu\t%0, %1\n\t"
-		"sltu\t$1, %0, %1\n\t"
-		"lw\t%1, 4(%2)\n\t"
-		"addu\t%0, $1\n\t"
-		"addu\t%0, %1\n\t"
-		"sltu\t$1, %0, %1\n\t"
-		"lw\t%1, 8(%2)\n\t"
-		"addu\t%0, $1\n\t"
-		"addu\t%0, %1\n\t"
-		"sltu\t$1, %0, %1\n\t"
-		"lw\t%1, 12(%2)\n\t"
-		"addu\t%0, $1\n\t"
-		"addu\t%0, %1\n\t"
-		"sltu\t$1, %0, %1\n\t"
-		"lw\t%1, 0(%3)\n\t"
-		"addu\t%0, $1\n\t"
-		"addu\t%0, %1\n\t"
-		"sltu\t$1, %0, %1\n\t"
-		"lw\t%1, 4(%3)\n\t"
-		"addu\t%0, $1\n\t"
-		"addu\t%0, %1\n\t"
-		"sltu\t$1, %0, %1\n\t"
-		"lw\t%1, 8(%3)\n\t"
-		"addu\t%0, $1\n\t"
-		"addu\t%0, %1\n\t"
-		"sltu\t$1, %0, %1\n\t"
-		"lw\t%1, 12(%3)\n\t"
-		"addu\t%0, $1\n\t"
-		"addu\t%0, %1\n\t"
-		"sltu\t$1, %0, %1\n\t"
-		"addu\t%0, $1\t\t\t# Add final carry\n\t"
-		".set\tnoat\n\t"
-		".set\tnoreorder"
+		".set\tvolatile\t\t\t# csum_ipv6_magic\n\t"
+		"add\t%0, %0, %5\t\t\t# proto (long in network byte order)\n\t"
+		"cmp.c\t%5, %0\n\t"
+		"bleu 1f\n\t"
+		"addi\t%0, 0x1\n\t"
+		"1:add\t%0, %0, %6\t\t\t# csum\n\t"
+		"cmp.c\t%6, %0\n\t"
+		"lw\t%1, [%2, 0]\t\t\t# four words source address\n\t"
+		"bleu 1f\n\t"
+		"addi\t%0, 0x1\n\t"
+		"1:add\t%0, %0, %1\n\t"
+		"cmp.c\t%1, %0\n\t"
+		"1:lw\t%1, [%2, 4]\n\t"
+		"bleu 1f\n\t"
+		"addi\t%0, 0x1\n\t"
+		"1:add\t%0, %0, %1\n\t"
+		"cmp.c\t%1, %0\n\t"
+		"lw\t%1, [%2,8]\n\t"
+		"bleu 1f\n\t"
+		"addi\t%0, 0x1\n\t"
+		"1:add\t%0, %0, %1\n\t"
+		"cmp.c\t%1, %0\n\t"
+		"lw\t%1, [%2, 12]\n\t"
+		"bleu 1f\n\t"
+		"addi\t%0, 0x1\n\t"
+		"1:add\t%0, %0,%1\n\t"
+		"cmp.c\t%1, %0\n\t"
+		"lw\t%1, [%3, 0]\n\t"
+		"bleu 1f\n\t"
+		"addi\t%0, 0x1\n\t"
+		"1:add\t%0, %0, %1\n\t"
+		"cmp.c\t%1, %0\n\t"
+		"lw\t%1, [%3, 4]\n\t"
+		"bleu 1f\n\t"
+		"addi\t%0, 0x1\n\t"
+		"1:add\t%0, %0, %1\n\t"
+		"cmp.c\t%1, %0\n\t"
+		"lw\t%1, [%3, 8]\n\t"
+		"bleu 1f\n\t"
+		"addi\t%0, 0x1\n\t"
+		"1:add\t%0, %0, %1\n\t"
+		"cmp.c\t%1, %0\n\t"
+		"lw\t%1, [%3, 12]\n\t"
+		"bleu 1f\n\t"
+		"addi\t%0, 0x1\n\t"
+		"1:add\t%0, %0, %1\n\t"
+		"cmp.c\t%1, %0\n\t"
+		"bleu 1f\n\t"
+		"addi\t%0, 0x1\n\t"
+		"1:\n\t"
+		".set\toptimize"
 		: "=r" (sum), "=r" (proto)
 		: "r" (saddr), "r" (daddr),
 		  "0" (htonl(len)), "1" (htonl(proto)), "r" (sum));
diff --git a/arch/score/include/asm/io.h b/arch/score/include/asm/io.h
index fbbfd7132e3b..574c8827abe2 100644
--- a/arch/score/include/asm/io.h
+++ b/arch/score/include/asm/io.h
@@ -5,5 +5,4 @@
 
 #define virt_to_bus	virt_to_phys
 #define bus_to_virt	phys_to_virt
-
 #endif /* _ASM_SCORE_IO_H */
diff --git a/arch/score/include/asm/pgalloc.h b/arch/score/include/asm/pgalloc.h
index 059a61b7071b..716b3fd1d863 100644
--- a/arch/score/include/asm/pgalloc.h
+++ b/arch/score/include/asm/pgalloc.h
@@ -2,7 +2,7 @@
 #define _ASM_SCORE_PGALLOC_H
 
 #include <linux/mm.h>
-
+#include <linux/highmem.h>
 static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd,
 	pte_t *pte)
 {
diff --git a/arch/score/kernel/entry.S b/arch/score/kernel/entry.S
index 7234ed09b7b7..befb87d30a89 100644
--- a/arch/score/kernel/entry.S
+++ b/arch/score/kernel/entry.S
@@ -264,7 +264,7 @@ resume_kernel:
 	disable_irq
 	lw	r8, [r28, TI_PRE_COUNT]
 	cmpz.c	r8
-	bne	r8, restore_all
+	bne	restore_all
 need_resched:
 	lw	r8, [r28, TI_FLAGS]
 	andri.c	r9, r8, _TIF_NEED_RESCHED
@@ -415,7 +415,7 @@ ENTRY(handle_sys)
 	sw	r9, [r0, PT_EPC]
 
 	cmpi.c	r27, __NR_syscalls 	# check syscall number
-	bgeu	illegal_syscall
+	bcs	illegal_syscall
 
 	slli	r8, r27, 2		# get syscall routine
 	la	r11, sys_call_table
diff --git a/arch/score/kernel/process.c b/arch/score/kernel/process.c
index f4c6d02421d3..a1519ad3d49d 100644
--- a/arch/score/kernel/process.c
+++ b/arch/score/kernel/process.c
@@ -78,8 +78,8 @@ int copy_thread(unsigned long clone_flags, unsigned long usp,
 	p->thread.reg0 = (unsigned long) childregs;
 	if (unlikely(p->flags & PF_KTHREAD)) {
 		memset(childregs, 0, sizeof(struct pt_regs));
-		p->thread->reg12 = usp;
-		p->thread->reg13 = arg;
+		p->thread.reg12 = usp;
+		p->thread.reg13 = arg;
 		p->thread.reg3 = (unsigned long) ret_from_kernel_thread;
 	} else {
 		*childregs = *current_pt_regs();
diff --git a/arch/score/mm/fault.c b/arch/score/mm/fault.c
index 6b18fb0189ae..52238983527d 100644
--- a/arch/score/mm/fault.c
+++ b/arch/score/mm/fault.c
@@ -47,6 +47,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long write,
 	struct task_struct *tsk = current;
 	struct mm_struct *mm = tsk->mm;
 	const int field = sizeof(unsigned long) * 2;
+	unsigned long flags = 0;
 	siginfo_t info;
 	int fault;
 
@@ -75,6 +76,9 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long write,
 	if (in_atomic() || !mm)
 		goto bad_area_nosemaphore;
 
+	if (user_mode(regs))
+		flags |= FAULT_FLAG_USER;
+
 	down_read(&mm->mmap_sem);
 	vma = find_vma(mm, address);
 	if (!vma)
@@ -95,18 +99,18 @@ good_area:
 	if (write) {
 		if (!(vma->vm_flags & VM_WRITE))
 			goto bad_area;
+		flags |= FAULT_FLAG_WRITE;
 	} else {
 		if (!(vma->vm_flags & (VM_READ | VM_WRITE | VM_EXEC)))
 			goto bad_area;
 	}
 
-survive:
 	/*
 	* If for any reason at all we couldn't handle the fault,
 	* make sure we exit gracefully rather than endlessly redo
 	* the fault.
 	*/
-	fault = handle_mm_fault(mm, vma, address, write);
+	fault = handle_mm_fault(mm, vma, address, flags);
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
@@ -167,11 +171,6 @@ no_context:
 	*/
 out_of_memory:
 	up_read(&mm->mmap_sem);
-	if (is_global_init(tsk)) {
-		yield();
-		down_read(&mm->mmap_sem);
-		goto survive;
-	}
 	if (!user_mode(regs))
 		goto no_context;
 	pagefault_out_of_memory();
diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig
index 1020dd85431a..224f4bc9925e 100644
--- a/arch/sh/Kconfig
+++ b/arch/sh/Kconfig
@@ -26,7 +26,6 @@ config SUPERH
 	select ARCH_WANT_IPC_PARSE_VERSION
 	select HAVE_SYSCALL_TRACEPOINTS
 	select HAVE_REGS_AND_STACK_ACCESS_API
-	select HAVE_GENERIC_HARDIRQS
 	select MAY_HAVE_SPARSE_IRQ
 	select IRQ_FORCED_THREADING
 	select RTC_LIB
@@ -643,9 +642,9 @@ config KEXEC
 
 	  It is an ongoing process to be certain the hardware in a machine
 	  is properly shutdown, so do not be surprised if this code does not
-	  initially work for you.  It may help to enable device hotplugging
-	  support.  As of this writing the exact hardware interface is
-	  strongly in flux, so no good recommendation can be made.
+	  initially work for you.  As of this writing the exact hardware
+	  interface is strongly in flux, so no good recommendation can be
+	  made.
 
 config CRASH_DUMP
 	bool "kernel crash dumps (EXPERIMENTAL)"
diff --git a/arch/sh/boards/board-espt.c b/arch/sh/boards/board-espt.c
index 4d94dff9015c..7291e2f11a47 100644
--- a/arch/sh/boards/board-espt.c
+++ b/arch/sh/boards/board-espt.c
@@ -80,7 +80,6 @@ static struct resource sh_eth_resources[] = {
 static struct sh_eth_plat_data sh7763_eth_pdata = {
 	.phy = 0,
 	.edmac_endian = EDMAC_LITTLE_ENDIAN,
-	.register_type = SH_ETH_REG_GIGABIT,
 	.phy_interface = PHY_INTERFACE_MODE_MII,
 };
 
diff --git a/arch/sh/boards/board-sh7757lcr.c b/arch/sh/boards/board-sh7757lcr.c
index 4f114d1cd019..25c5a932f9fe 100644
--- a/arch/sh/boards/board-sh7757lcr.c
+++ b/arch/sh/boards/board-sh7757lcr.c
@@ -77,7 +77,6 @@ static struct resource sh_eth0_resources[] = {
 static struct sh_eth_plat_data sh7757_eth0_pdata = {
 	.phy = 1,
 	.edmac_endian = EDMAC_LITTLE_ENDIAN,
-	.register_type = SH_ETH_REG_FAST_SH4,
 	.set_mdio_gate = sh7757_eth_set_mdio_gate,
 };
 
@@ -106,7 +105,6 @@ static struct resource sh_eth1_resources[] = {
 static struct sh_eth_plat_data sh7757_eth1_pdata = {
 	.phy = 1,
 	.edmac_endian = EDMAC_LITTLE_ENDIAN,
-	.register_type = SH_ETH_REG_FAST_SH4,
 	.set_mdio_gate = sh7757_eth_set_mdio_gate,
 };
 
@@ -151,7 +149,6 @@ static struct resource sh_eth_giga0_resources[] = {
 static struct sh_eth_plat_data sh7757_eth_giga0_pdata = {
 	.phy = 18,
 	.edmac_endian = EDMAC_LITTLE_ENDIAN,
-	.register_type = SH_ETH_REG_GIGABIT,
 	.set_mdio_gate = sh7757_eth_giga_set_mdio_gate,
 	.phy_interface = PHY_INTERFACE_MODE_RGMII_ID,
 };
@@ -186,7 +183,6 @@ static struct resource sh_eth_giga1_resources[] = {
 static struct sh_eth_plat_data sh7757_eth_giga1_pdata = {
 	.phy = 19,
 	.edmac_endian = EDMAC_LITTLE_ENDIAN,
-	.register_type = SH_ETH_REG_GIGABIT,
 	.set_mdio_gate = sh7757_eth_giga_set_mdio_gate,
 	.phy_interface = PHY_INTERFACE_MODE_RGMII_ID,
 };
diff --git a/arch/sh/boards/mach-ecovec24/setup.c b/arch/sh/boards/mach-ecovec24/setup.c
index 61fade0ffa96..1fa8be409771 100644
--- a/arch/sh/boards/mach-ecovec24/setup.c
+++ b/arch/sh/boards/mach-ecovec24/setup.c
@@ -30,6 +30,7 @@
 #include <linux/spi/mmc_spi.h>
 #include <linux/input.h>
 #include <linux/input/sh_keysc.h>
+#include <linux/platform_data/gpio_backlight.h>
 #include <linux/sh_eth.h>
 #include <linux/sh_intc.h>
 #include <linux/videodev2.h>
@@ -159,7 +160,6 @@ static struct resource sh_eth_resources[] = {
 static struct sh_eth_plat_data sh_eth_plat = {
 	.phy = 0x1f, /* SMSC LAN8700 */
 	.edmac_endian = EDMAC_LITTLE_ENDIAN,
-	.register_type = SH_ETH_REG_FAST_SH4,
 	.phy_interface = PHY_INTERFACE_MODE_MII,
 	.ether_link_active_low = 1
 };
@@ -303,7 +303,7 @@ static struct platform_device usbhs_device = {
 	.resource	= usbhs_resources,
 };
 
-/* LCDC */
+/* LCDC and backlight */
 static const struct fb_videomode ecovec_lcd_modes[] = {
 	{
 		.name		= "Panel",
@@ -334,13 +334,6 @@ static const struct fb_videomode ecovec_dvi_modes[] = {
 	},
 };
 
-static int ecovec24_set_brightness(int brightness)
-{
-	gpio_set_value(GPIO_PTR1, brightness);
-
-	return 0;
-}
-
 static struct sh_mobile_lcdc_info lcdc_info = {
 	.ch[0] = {
 		.interface_type = RGB18,
@@ -350,11 +343,6 @@ static struct sh_mobile_lcdc_info lcdc_info = {
 			.width = 152,
 			.height = 91,
 		},
-		.bl_info = {
-			.name = "sh_mobile_lcdc_bl",
-			.max_brightness = 1,
-			.set_brightness = ecovec24_set_brightness,
-		},
 	}
 };
 
@@ -380,6 +368,20 @@ static struct platform_device lcdc_device = {
 	},
 };
 
+static struct gpio_backlight_platform_data gpio_backlight_data = {
+	.fbdev = &lcdc_device.dev,
+	.gpio = GPIO_PTR1,
+	.def_value = 1,
+	.name = "backlight",
+};
+
+static struct platform_device gpio_backlight_device = {
+	.name = "gpio-backlight",
+	.dev = {
+		.platform_data = &gpio_backlight_data,
+	},
+};
+
 /* CEU0 */
 static struct sh_mobile_ceu_info sh_mobile_ceu0_info = {
 	.flags = SH_CEU_FLAG_USE_8BIT_BUS,
@@ -598,37 +600,13 @@ static struct platform_device sdhi0_power = {
 	},
 };
 
-static void sdhi0_set_pwr(struct platform_device *pdev, int state)
-{
-	static int power_gpio = -EINVAL;
-
-	if (power_gpio < 0) {
-		int ret = gpio_request(GPIO_PTB6, NULL);
-		if (!ret) {
-			power_gpio = GPIO_PTB6;
-			gpio_direction_output(power_gpio, 0);
-		}
-	}
-
-	/*
-	 * Toggle the GPIO regardless, whether we managed to grab it above or
-	 * the fixed regulator driver did.
-	 */
-	gpio_set_value(GPIO_PTB6, state);
-}
-
-static int sdhi0_get_cd(struct platform_device *pdev)
-{
-	return !gpio_get_value(GPIO_PTY7);
-}
-
 static struct sh_mobile_sdhi_info sdhi0_info = {
 	.dma_slave_tx	= SHDMA_SLAVE_SDHI0_TX,
 	.dma_slave_rx	= SHDMA_SLAVE_SDHI0_RX,
-	.set_pwr	= sdhi0_set_pwr,
 	.tmio_caps      = MMC_CAP_SDIO_IRQ | MMC_CAP_POWER_OFF_CARD |
 			  MMC_CAP_NEEDS_POLL,
-	.get_cd		= sdhi0_get_cd,
+	.tmio_flags	= TMIO_MMC_USE_GPIO_CD,
+	.cd_gpio	= GPIO_PTY7,
 };
 
 static struct resource sdhi0_resources[] = {
@@ -654,39 +632,15 @@ static struct platform_device sdhi0_device = {
 	},
 };
 
-static void cn12_set_pwr(struct platform_device *pdev, int state)
-{
-	static int power_gpio = -EINVAL;
-
-	if (power_gpio < 0) {
-		int ret = gpio_request(GPIO_PTB7, NULL);
-		if (!ret) {
-			power_gpio = GPIO_PTB7;
-			gpio_direction_output(power_gpio, 0);
-		}
-	}
-
-	/*
-	 * Toggle the GPIO regardless, whether we managed to grab it above or
-	 * the fixed regulator driver did.
-	 */
-	gpio_set_value(GPIO_PTB7, state);
-}
-
 #if !defined(CONFIG_MMC_SH_MMCIF) && !defined(CONFIG_MMC_SH_MMCIF_MODULE)
 /* SDHI1 */
-static int sdhi1_get_cd(struct platform_device *pdev)
-{
-	return !gpio_get_value(GPIO_PTW7);
-}
-
 static struct sh_mobile_sdhi_info sdhi1_info = {
 	.dma_slave_tx	= SHDMA_SLAVE_SDHI1_TX,
 	.dma_slave_rx	= SHDMA_SLAVE_SDHI1_RX,
 	.tmio_caps      = MMC_CAP_SDIO_IRQ | MMC_CAP_POWER_OFF_CARD |
 			  MMC_CAP_NEEDS_POLL,
-	.set_pwr	= cn12_set_pwr,
-	.get_cd		= sdhi1_get_cd,
+	.tmio_flags	= TMIO_MMC_USE_GPIO_CD,
+	.cd_gpio	= GPIO_PTW7,
 };
 
 static struct resource sdhi1_resources[] = {
@@ -716,27 +670,19 @@ static struct platform_device sdhi1_device = {
 #else
 
 /* MMC SPI */
-static int mmc_spi_get_ro(struct device *dev)
-{
-	return gpio_get_value(GPIO_PTY6);
-}
-
-static int mmc_spi_get_cd(struct device *dev)
-{
-	return !gpio_get_value(GPIO_PTY7);
-}
-
 static void mmc_spi_setpower(struct device *dev, unsigned int maskval)
 {
 	gpio_set_value(GPIO_PTB6, maskval ? 1 : 0);
 }
 
 static struct mmc_spi_platform_data mmc_spi_info = {
-	.get_ro = mmc_spi_get_ro,
-	.get_cd = mmc_spi_get_cd,
 	.caps = MMC_CAP_NEEDS_POLL,
+	.caps2 = MMC_CAP2_RO_ACTIVE_HIGH,
 	.ocr_mask = MMC_VDD_32_33 | MMC_VDD_33_34, /* 3.3V only */
 	.setpower = mmc_spi_setpower,
+	.flags = MMC_SPI_USE_CD_GPIO | MMC_SPI_USE_RO_GPIO,
+	.cd_gpio = GPIO_PTY7,
+	.ro_gpio = GPIO_PTY6,
 };
 
 static struct spi_board_info spi_bus[] = {
@@ -996,11 +942,6 @@ static struct platform_device vou_device = {
 
 #if defined(CONFIG_MMC_SH_MMCIF) || defined(CONFIG_MMC_SH_MMCIF_MODULE)
 /* SH_MMCIF */
-static void mmcif_down_pwr(struct platform_device *pdev)
-{
-	cn12_set_pwr(pdev, 0);
-}
-
 static struct resource sh_mmcif_resources[] = {
 	[0] = {
 		.name	= "SH_MMCIF",
@@ -1021,8 +962,6 @@ static struct resource sh_mmcif_resources[] = {
 };
 
 static struct sh_mmcif_plat_data sh_mmcif_plat = {
-	.set_pwr	= cn12_set_pwr,
-	.down_pwr	= mmcif_down_pwr,
 	.sup_pclk	= 0, /* SH7724: Max Pclk/2 */
 	.caps		= MMC_CAP_4_BIT_DATA |
 			  MMC_CAP_8_BIT_DATA |
@@ -1049,6 +988,7 @@ static struct platform_device *ecovec_devices[] __initdata = {
 	&usb1_common_device,
 	&usbhs_device,
 	&lcdc_device,
+	&gpio_backlight_device,
 	&ceu0_device,
 	&ceu1_device,
 	&keysc_device,
@@ -1239,11 +1179,9 @@ static int __init arch_setup(void)
 
 	gpio_request(GPIO_PTE6, NULL);
 	gpio_request(GPIO_PTU1, NULL);
-	gpio_request(GPIO_PTR1, NULL);
 	gpio_request(GPIO_PTA2, NULL);
 	gpio_direction_input(GPIO_PTE6);
 	gpio_direction_output(GPIO_PTU1, 0);
-	gpio_direction_output(GPIO_PTR1, 0);
 	gpio_direction_output(GPIO_PTA2, 0);
 
 	/* I/O buffer drive ability is high */
@@ -1256,6 +1194,9 @@ static int __init arch_setup(void)
 		lcdc_info.ch[0].lcd_modes		= ecovec_dvi_modes;
 		lcdc_info.ch[0].num_modes		= ARRAY_SIZE(ecovec_dvi_modes);
 
+		/* No backlight */
+		gpio_backlight_data.fbdev = NULL;
+
 		gpio_set_value(GPIO_PTA2, 1);
 		gpio_set_value(GPIO_PTU1, 1);
 	} else {
@@ -1265,8 +1206,6 @@ static int __init arch_setup(void)
 		lcdc_info.ch[0].lcd_modes		= ecovec_lcd_modes;
 		lcdc_info.ch[0].num_modes		= ARRAY_SIZE(ecovec_lcd_modes);
 
-		gpio_set_value(GPIO_PTR1, 1);
-
 		/* FIXME
 		 *
 		 * LCDDON control is needed for Panel,
@@ -1339,10 +1278,6 @@ static int __init arch_setup(void)
 	gpio_direction_input(GPIO_PTR6);
 
 	/* SD-card slot CN11 */
-	/* Card-detect, used on CN11, either with SDHI0 or with SPI */
-	gpio_request(GPIO_PTY7, NULL);
-	gpio_direction_input(GPIO_PTY7);
-
 #if defined(CONFIG_MMC_SDHI) || defined(CONFIG_MMC_SDHI_MODULE)
 	/* enable SDHI0 on CN11 (needs DS2.4 set to ON) */
 	gpio_request(GPIO_FN_SDHI0WP,  NULL);
@@ -1361,8 +1296,6 @@ static int __init arch_setup(void)
 	gpio_direction_output(GPIO_PTM4, 1); /* active low CS */
 	gpio_request(GPIO_PTB6, NULL); /* 3.3V power control */
 	gpio_direction_output(GPIO_PTB6, 0); /* disable power by default */
-	gpio_request(GPIO_PTY6, NULL); /* write protect */
-	gpio_direction_input(GPIO_PTY6);
 
 	spi_register_board_info(spi_bus, ARRAY_SIZE(spi_bus));
 #endif
@@ -1392,10 +1325,6 @@ static int __init arch_setup(void)
 	gpio_request(GPIO_FN_SDHI1D1,  NULL);
 	gpio_request(GPIO_FN_SDHI1D0,  NULL);
 
-	/* Card-detect, used on CN12 with SDHI1 */
-	gpio_request(GPIO_PTW7, NULL);
-	gpio_direction_input(GPIO_PTW7);
-
 	cn12_enabled = true;
 #endif
 
diff --git a/arch/sh/boards/mach-kfr2r09/lcd_wqvga.c b/arch/sh/boards/mach-kfr2r09/lcd_wqvga.c
index c62050332629..355a78a3b313 100644
--- a/arch/sh/boards/mach-kfr2r09/lcd_wqvga.c
+++ b/arch/sh/boards/mach-kfr2r09/lcd_wqvga.c
@@ -276,51 +276,3 @@ void kfr2r09_lcd_start(void *sohandle, struct sh_mobile_lcdc_sys_bus_ops *so)
 {
 	write_memory_start(sohandle, so);
 }
-
-#define CTRL_CKSW       0x10
-#define CTRL_C10        0x20
-#define CTRL_CPSW       0x80
-#define MAIN_MLED4      0x40
-#define MAIN_MSW        0x80
-
-int kfr2r09_lcd_set_brightness(int brightness)
-{
-	struct i2c_adapter *a;
-	struct i2c_msg msg;
-	unsigned char buf[2];
-	int ret;
-
-	a = i2c_get_adapter(0);
-	if (!a)
-		return -ENODEV;
-
-	buf[0] = 0x00;
-	if (brightness)
-		buf[1] = CTRL_CPSW | CTRL_C10 | CTRL_CKSW;
-	else
-		buf[1] = 0;
-
-	msg.addr = 0x75;
-	msg.buf = buf;
-	msg.len = 2;
-	msg.flags = 0;
-	ret = i2c_transfer(a, &msg, 1);
-	if (ret != 1)
-		return -ENODEV;
-
-	buf[0] = 0x01;
-	if (brightness)
-		buf[1] = MAIN_MSW | MAIN_MLED4 | 0x0c;
-	else
-		buf[1] = 0;
-
-	msg.addr = 0x75;
-	msg.buf = buf;
-	msg.len = 2;
-	msg.flags = 0;
-	ret = i2c_transfer(a, &msg, 1);
-	if (ret != 1)
-		return -ENODEV;
-
-	return 0;
-}
diff --git a/arch/sh/boards/mach-kfr2r09/setup.c b/arch/sh/boards/mach-kfr2r09/setup.c
index ab502f12ef57..1df4398f8375 100644
--- a/arch/sh/boards/mach-kfr2r09/setup.c
+++ b/arch/sh/boards/mach-kfr2r09/setup.c
@@ -21,6 +21,7 @@
 #include <linux/input.h>
 #include <linux/input/sh_keysc.h>
 #include <linux/i2c.h>
+#include <linux/platform_data/lv5207lp.h>
 #include <linux/regulator/fixed.h>
 #include <linux/regulator/machine.h>
 #include <linux/usb/r8a66597.h>
@@ -159,11 +160,6 @@ static struct sh_mobile_lcdc_info kfr2r09_sh_lcdc_info = {
 			.setup_sys = kfr2r09_lcd_setup,
 			.start_transfer = kfr2r09_lcd_start,
 		},
-		.bl_info = {
-			.name = "sh_mobile_lcdc_bl",
-			.max_brightness = 1,
-			.set_brightness = kfr2r09_lcd_set_brightness,
-		},
 		.sys_bus_cfg = {
 			.ldmt2r = 0x07010904,
 			.ldmt3r = 0x14012914,
@@ -195,6 +191,17 @@ static struct platform_device kfr2r09_sh_lcdc_device = {
 	},
 };
 
+static struct lv5207lp_platform_data kfr2r09_backlight_data = {
+	.fbdev = &kfr2r09_sh_lcdc_device.dev,
+	.def_value = 13,
+	.max_value = 13,
+};
+
+static struct i2c_board_info kfr2r09_backlight_board_info = {
+	I2C_BOARD_INFO("lv5207lp", 0x75),
+	.platform_data = &kfr2r09_backlight_data,
+};
+
 static struct r8a66597_platdata kfr2r09_usb0_gadget_data = {
 	.on_chip = 1,
 };
@@ -627,6 +634,8 @@ static int __init kfr2r09_devices_setup(void)
 	gpio_request(GPIO_FN_SDHI0CMD, NULL);
 	gpio_request(GPIO_FN_SDHI0CLK, NULL);
 
+	i2c_register_board_info(0, &kfr2r09_backlight_board_info, 1);
+
 	return platform_add_devices(kfr2r09_devices,
 				    ARRAY_SIZE(kfr2r09_devices));
 }
diff --git a/arch/sh/boards/mach-se/7724/setup.c b/arch/sh/boards/mach-se/7724/setup.c
index b70180ef3e29..21e4230659a5 100644
--- a/arch/sh/boards/mach-se/7724/setup.c
+++ b/arch/sh/boards/mach-se/7724/setup.c
@@ -365,7 +365,7 @@ static struct platform_device keysc_device = {
 static struct resource sh_eth_resources[] = {
 	[0] = {
 		.start = SH_ETH_ADDR,
-		.end   = SH_ETH_ADDR + 0x1FC,
+		.end   = SH_ETH_ADDR + 0x1FC - 1,
 		.flags = IORESOURCE_MEM,
 	},
 	[1] = {
@@ -377,6 +377,7 @@ static struct resource sh_eth_resources[] = {
 static struct sh_eth_plat_data sh_eth_plat = {
 	.phy = 0x1f, /* SMSC LAN8187 */
 	.edmac_endian = EDMAC_LITTLE_ENDIAN,
+	.phy_interface = PHY_INTERFACE_MODE_MII,
 };
 
 static struct platform_device sh_eth_device = {
diff --git a/arch/sh/boards/mach-sh7763rdp/setup.c b/arch/sh/boards/mach-sh7763rdp/setup.c
index 50ba481fa240..2c8fb04685d4 100644
--- a/arch/sh/boards/mach-sh7763rdp/setup.c
+++ b/arch/sh/boards/mach-sh7763rdp/setup.c
@@ -88,7 +88,6 @@ static struct resource sh_eth_resources[] = {
 static struct sh_eth_plat_data sh7763_eth_pdata = {
 	.phy = 1,
 	.edmac_endian = EDMAC_LITTLE_ENDIAN,
-	.register_type = SH_ETH_REG_GIGABIT,
 	.phy_interface = PHY_INTERFACE_MODE_MII,
 };
 
diff --git a/arch/sh/drivers/pci/pci.c b/arch/sh/drivers/pci/pci.c
index 102f5d58b037..60ed3e1c4b75 100644
--- a/arch/sh/drivers/pci/pci.c
+++ b/arch/sh/drivers/pci/pci.c
@@ -69,7 +69,6 @@ static void pcibios_scanbus(struct pci_channel *hose)
 
 		pci_bus_size_bridges(bus);
 		pci_bus_assign_resources(bus);
-		pci_enable_bridges(bus);
 	} else {
 		pci_free_resource_list(&resources);
 	}
diff --git a/arch/sh/include/mach-kfr2r09/mach/kfr2r09.h b/arch/sh/include/mach-kfr2r09/mach/kfr2r09.h
index c20c9e5f5eab..79f154e5cb9c 100644
--- a/arch/sh/include/mach-kfr2r09/mach/kfr2r09.h
+++ b/arch/sh/include/mach-kfr2r09/mach/kfr2r09.h
@@ -4,13 +4,11 @@
 #include <video/sh_mobile_lcdc.h>
 
 #if defined(CONFIG_FB_SH_MOBILE_LCDC) || defined(CONFIG_FB_SH_MOBILE_LCDC_MODULE)
-int kfr2r09_lcd_set_brightness(int brightness);
 int kfr2r09_lcd_setup(void *sys_ops_handle,
 		      struct sh_mobile_lcdc_sys_bus_ops *sys_ops);
 void kfr2r09_lcd_start(void *sys_ops_handle,
 		       struct sh_mobile_lcdc_sys_bus_ops *sys_ops);
 #else
-static int kfr2r09_lcd_set_brightness(int brightness) {}
 static int kfr2r09_lcd_setup(void *sys_ops_handle,
 				struct sh_mobile_lcdc_sys_bus_ops *sys_ops)
 {
diff --git a/arch/sh/kernel/cpu/sh2/setup-sh7619.c b/arch/sh/kernel/cpu/sh2/setup-sh7619.c
index bb11e1925178..4df4d4ffe39b 100644
--- a/arch/sh/kernel/cpu/sh2/setup-sh7619.c
+++ b/arch/sh/kernel/cpu/sh2/setup-sh7619.c
@@ -12,6 +12,7 @@
 #include <linux/init.h>
 #include <linux/serial.h>
 #include <linux/serial_sci.h>
+#include <linux/sh_eth.h>
 #include <linux/sh_timer.h>
 #include <linux/io.h>
 
@@ -110,10 +111,16 @@ static struct platform_device scif2_device = {
 	},
 };
 
+static struct sh_eth_plat_data eth_platform_data = {
+	.phy		= 1,
+	.edmac_endian	= EDMAC_LITTLE_ENDIAN,
+	.phy_interface	= PHY_INTERFACE_MODE_MII,
+};
+
 static struct resource eth_resources[] = {
 	[0] = {
 		.start = 0xfb000000,
-		.end =   0xfb0001c8,
+		.end = 0xfb0001c7,
 		.flags = IORESOURCE_MEM,
 	},
 	[1] = {
@@ -127,7 +134,7 @@ static struct platform_device eth_device = {
 	.name = "sh7619-ether",
 	.id = -1,
 	.dev = {
-		.platform_data = (void *)1,
+		.platform_data = &eth_platform_data,
 	},
 	.num_resources = ARRAY_SIZE(eth_resources),
 	.resource = eth_resources,
diff --git a/arch/sh/kernel/cpu/shmobile/cpuidle.c b/arch/sh/kernel/cpu/shmobile/cpuidle.c
index d30622592116..e3abfd4277e2 100644
--- a/arch/sh/kernel/cpu/shmobile/cpuidle.c
+++ b/arch/sh/kernel/cpu/shmobile/cpuidle.c
@@ -91,13 +91,11 @@ static struct cpuidle_driver cpuidle_driver = {
 
 int __init sh_mobile_setup_cpuidle(void)
 {
-	int ret;
-
 	if (sh_mobile_sleep_supported & SUSP_SH_SF)
 		cpuidle_driver.states[1].disabled = false;
 
 	if (sh_mobile_sleep_supported & SUSP_SH_STANDBY)
 		cpuidle_driver.states[2].disabled = false;
 
-	return cpuidle_register(&cpuidle_driver);
+	return cpuidle_register(&cpuidle_driver, NULL);
 }
diff --git a/arch/sh/mm/fault.c b/arch/sh/mm/fault.c
index 1f49c28affa9..541dc6101508 100644
--- a/arch/sh/mm/fault.c
+++ b/arch/sh/mm/fault.c
@@ -400,9 +400,7 @@ asmlinkage void __kprobes do_page_fault(struct pt_regs *regs,
 	struct mm_struct *mm;
 	struct vm_area_struct * vma;
 	int fault;
-	int write = error_code & FAULT_CODE_WRITE;
-	unsigned int flags = (FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
-			      (write ? FAULT_FLAG_WRITE : 0));
+	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
 
 	tsk = current;
 	mm = tsk->mm;
@@ -476,6 +474,11 @@ good_area:
 
 	set_thread_fault_code(error_code);
 
+	if (user_mode(regs))
+		flags |= FAULT_FLAG_USER;
+	if (error_code & FAULT_CODE_WRITE)
+		flags |= FAULT_FLAG_WRITE;
+
 	/*
 	 * If for any reason at all we couldn't handle the fault,
 	 * make sure we exit gracefully rather than endlessly redo
diff --git a/arch/sh/mm/hugetlbpage.c b/arch/sh/mm/hugetlbpage.c
index d7762349ea48..0d676a41081e 100644
--- a/arch/sh/mm/hugetlbpage.c
+++ b/arch/sh/mm/hugetlbpage.c
@@ -83,6 +83,11 @@ int pud_huge(pud_t pud)
 	return 0;
 }
 
+int pmd_huge_support(void)
+{
+	return 0;
+}
+
 struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address,
 			     pmd_t *pmd, int write)
 {
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index a00cbd356db5..78c4fdb91bc5 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -26,7 +26,6 @@ config SPARC
 	select HAVE_DMA_ATTRS
 	select HAVE_DMA_API_DEBUG
 	select HAVE_ARCH_JUMP_LABEL
-	select HAVE_GENERIC_HARDIRQS
 	select GENERIC_IRQ_SHOW
 	select ARCH_WANT_IPC_PARSE_VERSION
 	select USE_GENERIC_SMP_HELPERS if SMP
@@ -52,7 +51,6 @@ config SPARC32
 
 config SPARC64
 	def_bool 64BIT
-	select ARCH_SUPPORTS_MSI
 	select HAVE_FUNCTION_TRACER
 	select HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_FUNCTION_GRAPH_FP_TEST
@@ -508,12 +506,17 @@ config SUN_OPENPROMFS
 	  Only choose N if you know in advance that you will not need to modify
 	  OpenPROM settings on the running system.
 
-# Makefile helper
+# Makefile helpers
 config SPARC64_PCI
 	bool
 	default y
 	depends on SPARC64 && PCI
 
+config SPARC64_PCI_MSI
+	bool
+	default y
+	depends on SPARC64_PCI && PCI_MSI
+
 endmenu
 
 menu "Executable file formats"
diff --git a/arch/sparc/include/asm/floppy_64.h b/arch/sparc/include/asm/floppy_64.h
index e204f902e6c9..7c90c50c200d 100644
--- a/arch/sparc/include/asm/floppy_64.h
+++ b/arch/sparc/include/asm/floppy_64.h
@@ -254,7 +254,7 @@ static int sun_fd_request_irq(void)
 		once = 1;
 
 		error = request_irq(FLOPPY_IRQ, sparc_floppy_irq,
-				    IRQF_DISABLED, "floppy", NULL);
+				    0, "floppy", NULL);
 
 		return ((error == 0) ? 0 : -1);
 	}
diff --git a/arch/sparc/include/asm/jump_label.h b/arch/sparc/include/asm/jump_label.h
index 5080d16a832f..ec2e2e2aba7d 100644
--- a/arch/sparc/include/asm/jump_label.h
+++ b/arch/sparc/include/asm/jump_label.h
@@ -9,7 +9,7 @@
 
 static __always_inline bool arch_static_branch(struct static_key *key)
 {
-		asm goto("1:\n\t"
+		asm_volatile_goto("1:\n\t"
 			 "nop\n\t"
 			 "nop\n\t"
 			 ".pushsection __jump_table,  \"aw\"\n\t"
diff --git a/arch/sparc/include/asm/switch_to_64.h b/arch/sparc/include/asm/switch_to_64.h
index c7de3323819c..8d284801f232 100644
--- a/arch/sparc/include/asm/switch_to_64.h
+++ b/arch/sparc/include/asm/switch_to_64.h
@@ -48,8 +48,8 @@ do {	save_and_clear_fpu();						\
 	"wrpr	%%g0, 14, %%pil\n\t"					\
 	"brz,pt %%o7, switch_to_pc\n\t"					\
 	" mov	%%g7, %0\n\t"						\
-	"sethi	%%hi(ret_from_syscall), %%g1\n\t"			\
-	"jmpl	%%g1 + %%lo(ret_from_syscall), %%g0\n\t"		\
+	"sethi	%%hi(ret_from_fork), %%g1\n\t"				\
+	"jmpl	%%g1 + %%lo(ret_from_fork), %%g0\n\t"			\
 	" nop\n\t"							\
 	".globl switch_to_pc\n\t"					\
 	"switch_to_pc:\n\t"						\
diff --git a/arch/sparc/kernel/Makefile b/arch/sparc/kernel/Makefile
index d432fb20358e..d15cc1794b0e 100644
--- a/arch/sparc/kernel/Makefile
+++ b/arch/sparc/kernel/Makefile
@@ -1,3 +1,4 @@
+
 #
 # Makefile for the linux kernel.
 #
@@ -99,7 +100,7 @@ obj-$(CONFIG_STACKTRACE)     += stacktrace.o
 obj-$(CONFIG_SPARC64_PCI)    += pci.o pci_common.o psycho_common.o
 obj-$(CONFIG_SPARC64_PCI)    += pci_psycho.o pci_sabre.o pci_schizo.o
 obj-$(CONFIG_SPARC64_PCI)    += pci_sun4v.o pci_sun4v_asm.o pci_fire.o
-obj-$(CONFIG_PCI_MSI)        += pci_msi.o
+obj-$(CONFIG_SPARC64_PCI_MSI) += pci_msi.o
 
 obj-$(CONFIG_COMPAT)         += sys32.o sys_sparc32.o signal32.o
 
diff --git a/arch/sparc/kernel/cpumap.c b/arch/sparc/kernel/cpumap.c
index e4de74c2c9b0..cb5d272d658a 100644
--- a/arch/sparc/kernel/cpumap.c
+++ b/arch/sparc/kernel/cpumap.c
@@ -327,6 +327,7 @@ static int iterate_cpu(struct cpuinfo_tree *t, unsigned int root_index)
 	case SUN4V_CHIP_NIAGARA3:
 	case SUN4V_CHIP_NIAGARA4:
 	case SUN4V_CHIP_NIAGARA5:
+	case SUN4V_CHIP_SPARC64X:
 		rover_inc_table = niagara_iterate_method;
 		break;
 	default:
diff --git a/arch/sparc/kernel/ds.c b/arch/sparc/kernel/ds.c
index 62d6b153ffa2..dff60abbea01 100644
--- a/arch/sparc/kernel/ds.c
+++ b/arch/sparc/kernel/ds.c
@@ -849,9 +849,8 @@ void ldom_reboot(const char *boot_command)
 	if (boot_command && strlen(boot_command)) {
 		unsigned long len;
 
-		strcpy(full_boot_str, "boot ");
-		strlcpy(full_boot_str + strlen("boot "), boot_command,
-			sizeof(full_boot_str + strlen("boot ")));
+		snprintf(full_boot_str, sizeof(full_boot_str), "boot %s",
+			 boot_command);
 		len = strlen(full_boot_str);
 
 		if (reboot_data_supported) {
diff --git a/arch/sparc/kernel/entry.S b/arch/sparc/kernel/entry.S
index e2a030045089..33c02b15f478 100644
--- a/arch/sparc/kernel/entry.S
+++ b/arch/sparc/kernel/entry.S
@@ -839,7 +839,7 @@ sys_sigreturn:
 	 nop
 
 	call	syscall_trace
-	 nop
+	 mov	1, %o1
 
 1:
 	/* We don't want to muck with user registers like a
diff --git a/arch/sparc/kernel/kgdb_64.c b/arch/sparc/kernel/kgdb_64.c
index c8759550799f..53c0a82e6030 100644
--- a/arch/sparc/kernel/kgdb_64.c
+++ b/arch/sparc/kernel/kgdb_64.c
@@ -42,7 +42,7 @@ void sleeping_thread_to_gdb_regs(unsigned long *gdb_regs, struct task_struct *p)
 {
 	struct thread_info *t = task_thread_info(p);
 	extern unsigned int switch_to_pc;
-	extern unsigned int ret_from_syscall;
+	extern unsigned int ret_from_fork;
 	struct reg_window *win;
 	unsigned long pc, cwp;
 	int i;
@@ -66,7 +66,7 @@ void sleeping_thread_to_gdb_regs(unsigned long *gdb_regs, struct task_struct *p)
 		gdb_regs[i] = 0;
 
 	if (t->new_child)
-		pc = (unsigned long) &ret_from_syscall;
+		pc = (unsigned long) &ret_from_fork;
 	else
 		pc = (unsigned long) &switch_to_pc;
 
diff --git a/arch/sparc/kernel/ktlb.S b/arch/sparc/kernel/ktlb.S
index 0746e5e32b37..fde5a419cf27 100644
--- a/arch/sparc/kernel/ktlb.S
+++ b/arch/sparc/kernel/ktlb.S
@@ -25,11 +25,10 @@ kvmap_itlb:
 	 */
 kvmap_itlb_4v:
 
-kvmap_itlb_nonlinear:
 	/* Catch kernel NULL pointer calls.  */
 	sethi		%hi(PAGE_SIZE), %g5
 	cmp		%g4, %g5
-	bleu,pn		%xcc, kvmap_dtlb_longpath
+	blu,pn		%xcc, kvmap_itlb_longpath
 	 nop
 
 	KERN_TSB_LOOKUP_TL1(%g4, %g6, %g5, %g1, %g2, %g3, kvmap_itlb_load)
diff --git a/arch/sparc/kernel/ldc.c b/arch/sparc/kernel/ldc.c
index 54df554b82d9..e01d75d40329 100644
--- a/arch/sparc/kernel/ldc.c
+++ b/arch/sparc/kernel/ldc.c
@@ -1249,12 +1249,12 @@ int ldc_bind(struct ldc_channel *lp, const char *name)
 	snprintf(lp->rx_irq_name, LDC_IRQ_NAME_MAX, "%s RX", name);
 	snprintf(lp->tx_irq_name, LDC_IRQ_NAME_MAX, "%s TX", name);
 
-	err = request_irq(lp->cfg.rx_irq, ldc_rx, IRQF_DISABLED,
+	err = request_irq(lp->cfg.rx_irq, ldc_rx, 0,
 			  lp->rx_irq_name, lp);
 	if (err)
 		return err;
 
-	err = request_irq(lp->cfg.tx_irq, ldc_tx, IRQF_DISABLED,
+	err = request_irq(lp->cfg.tx_irq, ldc_tx, 0,
 			  lp->tx_irq_name, lp);
 	if (err) {
 		free_irq(lp->cfg.rx_irq, lp);
diff --git a/arch/sparc/kernel/ptrace_64.c b/arch/sparc/kernel/ptrace_64.c
index 7ff45e4ba681..773c1f2983ce 100644
--- a/arch/sparc/kernel/ptrace_64.c
+++ b/arch/sparc/kernel/ptrace_64.c
@@ -14,6 +14,7 @@
 #include <linux/sched.h>
 #include <linux/mm.h>
 #include <linux/errno.h>
+#include <linux/export.h>
 #include <linux/ptrace.h>
 #include <linux/user.h>
 #include <linux/smp.h>
@@ -116,6 +117,7 @@ void flush_ptrace_access(struct vm_area_struct *vma, struct page *page,
 
 	preempt_enable();
 }
+EXPORT_SYMBOL_GPL(flush_ptrace_access);
 
 static int get_from_target(struct task_struct *target, unsigned long uaddr,
 			   void *kbuf, int len)
@@ -1087,7 +1089,7 @@ asmlinkage void syscall_trace_leave(struct pt_regs *regs)
 	audit_syscall_exit(regs);
 
 	if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
-		trace_sys_exit(regs, regs->u_regs[UREG_G1]);
+		trace_sys_exit(regs, regs->u_regs[UREG_I0]);
 
 	if (test_thread_flag(TIF_SYSCALL_TRACE))
 		tracehook_report_syscall_exit(regs, 0);
diff --git a/arch/sparc/kernel/setup_64.c b/arch/sparc/kernel/setup_64.c
index 13785547e435..3fdb455e3318 100644
--- a/arch/sparc/kernel/setup_64.c
+++ b/arch/sparc/kernel/setup_64.c
@@ -499,12 +499,14 @@ static void __init init_sparc64_elf_hwcap(void)
 		    sun4v_chip_type == SUN4V_CHIP_NIAGARA2 ||
 		    sun4v_chip_type == SUN4V_CHIP_NIAGARA3 ||
 		    sun4v_chip_type == SUN4V_CHIP_NIAGARA4 ||
-		    sun4v_chip_type == SUN4V_CHIP_NIAGARA5)
+		    sun4v_chip_type == SUN4V_CHIP_NIAGARA5 ||
+		    sun4v_chip_type == SUN4V_CHIP_SPARC64X)
 			cap |= HWCAP_SPARC_BLKINIT;
 		if (sun4v_chip_type == SUN4V_CHIP_NIAGARA2 ||
 		    sun4v_chip_type == SUN4V_CHIP_NIAGARA3 ||
 		    sun4v_chip_type == SUN4V_CHIP_NIAGARA4 ||
-		    sun4v_chip_type == SUN4V_CHIP_NIAGARA5)
+		    sun4v_chip_type == SUN4V_CHIP_NIAGARA5 ||
+		    sun4v_chip_type == SUN4V_CHIP_SPARC64X)
 			cap |= HWCAP_SPARC_N2;
 	}
 
@@ -530,13 +532,15 @@ static void __init init_sparc64_elf_hwcap(void)
 			if (sun4v_chip_type == SUN4V_CHIP_NIAGARA2 ||
 			    sun4v_chip_type == SUN4V_CHIP_NIAGARA3 ||
 			    sun4v_chip_type == SUN4V_CHIP_NIAGARA4 ||
-			    sun4v_chip_type == SUN4V_CHIP_NIAGARA5)
+			    sun4v_chip_type == SUN4V_CHIP_NIAGARA5 ||
+			    sun4v_chip_type == SUN4V_CHIP_SPARC64X)
 				cap |= (AV_SPARC_VIS | AV_SPARC_VIS2 |
 					AV_SPARC_ASI_BLK_INIT |
 					AV_SPARC_POPC);
 			if (sun4v_chip_type == SUN4V_CHIP_NIAGARA3 ||
 			    sun4v_chip_type == SUN4V_CHIP_NIAGARA4 ||
-			    sun4v_chip_type == SUN4V_CHIP_NIAGARA5)
+			    sun4v_chip_type == SUN4V_CHIP_NIAGARA5 ||
+			    sun4v_chip_type == SUN4V_CHIP_SPARC64X)
 				cap |= (AV_SPARC_VIS3 | AV_SPARC_HPC |
 					AV_SPARC_FMAF);
 		}
diff --git a/arch/sparc/kernel/sys_sparc32.c b/arch/sparc/kernel/sys_sparc32.c
index 3d0ddbc005fe..71368850dfc0 100644
--- a/arch/sparc/kernel/sys_sparc32.c
+++ b/arch/sparc/kernel/sys_sparc32.c
@@ -169,10 +169,10 @@ COMPAT_SYSCALL_DEFINE5(rt_sigaction, int, sig,
 		new_ka.ka_restorer = restorer;
 		ret = get_user(u_handler, &act->sa_handler);
 		new_ka.sa.sa_handler =  compat_ptr(u_handler);
-		ret |= __copy_from_user(&set32, &act->sa_mask, sizeof(compat_sigset_t));
+		ret |= copy_from_user(&set32, &act->sa_mask, sizeof(compat_sigset_t));
 		sigset_from_compat(&new_ka.sa.sa_mask, &set32);
-		ret |= __get_user(new_ka.sa.sa_flags, &act->sa_flags);
-		ret |= __get_user(u_restorer, &act->sa_restorer);
+		ret |= get_user(new_ka.sa.sa_flags, &act->sa_flags);
+		ret |= get_user(u_restorer, &act->sa_restorer);
 		new_ka.sa.sa_restorer = compat_ptr(u_restorer);
                 if (ret)
                 	return -EFAULT;
@@ -183,9 +183,9 @@ COMPAT_SYSCALL_DEFINE5(rt_sigaction, int, sig,
 	if (!ret && oact) {
 		sigset_to_compat(&set32, &old_ka.sa.sa_mask);
 		ret = put_user(ptr_to_compat(old_ka.sa.sa_handler), &oact->sa_handler);
-		ret |= __copy_to_user(&oact->sa_mask, &set32, sizeof(compat_sigset_t));
-		ret |= __put_user(old_ka.sa.sa_flags, &oact->sa_flags);
-		ret |= __put_user(ptr_to_compat(old_ka.sa.sa_restorer), &oact->sa_restorer);
+		ret |= copy_to_user(&oact->sa_mask, &set32, sizeof(compat_sigset_t));
+		ret |= put_user(old_ka.sa.sa_flags, &oact->sa_flags);
+		ret |= put_user(ptr_to_compat(old_ka.sa.sa_restorer), &oact->sa_restorer);
 		if (ret)
 			ret = -EFAULT;
         }
diff --git a/arch/sparc/kernel/syscalls.S b/arch/sparc/kernel/syscalls.S
index 22a1098961f5..d950197a17e1 100644
--- a/arch/sparc/kernel/syscalls.S
+++ b/arch/sparc/kernel/syscalls.S
@@ -98,8 +98,8 @@ sys_clone:
 	ba,pt	%xcc, sparc_do_fork
 	 add	%sp, PTREGS_OFF, %o2
 
-	.globl	ret_from_syscall
-ret_from_syscall:
+	.globl	ret_from_fork
+ret_from_fork:
 	/* Clear current_thread_info()->new_child. */
 	stb	%g0, [%g6 + TI_NEW_CHILD]
 	call	schedule_tail
@@ -152,7 +152,7 @@ linux_syscall_trace32:
 	srl	%i4, 0, %o4
 	srl	%i1, 0, %o1
 	srl	%i2, 0, %o2
-	ba,pt	%xcc, 2f
+	ba,pt	%xcc, 5f
 	 srl	%i3, 0, %o3
 
 linux_syscall_trace:
@@ -182,13 +182,13 @@ linux_sparc_syscall32:
 	srl	%i1, 0, %o1				! IEU0	Group
 	ldx	[%g6 + TI_FLAGS], %l0		! Load
 
-	srl	%i5, 0, %o5				! IEU1
+	srl	%i3, 0, %o3				! IEU0
 	srl	%i2, 0, %o2				! IEU0	Group
 	andcc	%l0, (_TIF_SYSCALL_TRACE|_TIF_SECCOMP|_TIF_SYSCALL_AUDIT|_TIF_SYSCALL_TRACEPOINT), %g0
 	bne,pn	%icc, linux_syscall_trace32		! CTI
 	 mov	%i0, %l5				! IEU1
-	call	%l7					! CTI	Group brk forced
-	 srl	%i3, 0, %o3				! IEU0
+5:	call	%l7					! CTI	Group brk forced
+	 srl	%i5, 0, %o5				! IEU1
 	ba,a,pt	%xcc, 3f
 
 	/* Linux native system calls enter here... */
diff --git a/arch/sparc/kernel/trampoline_64.S b/arch/sparc/kernel/trampoline_64.S
index e0b1e13a0736..ad4bde3bb61e 100644
--- a/arch/sparc/kernel/trampoline_64.S
+++ b/arch/sparc/kernel/trampoline_64.S
@@ -129,7 +129,6 @@ startup_continue:
 	clr		%l5
 	sethi		%hi(num_kernel_image_mappings), %l6
 	lduw		[%l6 + %lo(num_kernel_image_mappings)], %l6
-	add		%l6, 1, %l6
 
 	mov		15, %l7
 	BRANCH_IF_ANY_CHEETAH(g1,g5,2f)
@@ -222,7 +221,6 @@ niagara_lock_tlb:
 	clr		%l5
 	sethi		%hi(num_kernel_image_mappings), %l6
 	lduw		[%l6 + %lo(num_kernel_image_mappings)], %l6
-	add		%l6, 1, %l6
 
 1:
 	mov		HV_FAST_MMU_MAP_PERM_ADDR, %o5
diff --git a/arch/sparc/lib/ksyms.c b/arch/sparc/lib/ksyms.c
index 0c4e35e522fa..323335b9cd2b 100644
--- a/arch/sparc/lib/ksyms.c
+++ b/arch/sparc/lib/ksyms.c
@@ -98,15 +98,6 @@ EXPORT_SYMBOL(___copy_from_user);
 EXPORT_SYMBOL(___copy_in_user);
 EXPORT_SYMBOL(__clear_user);
 
-/* RW semaphores */
-EXPORT_SYMBOL(__down_read);
-EXPORT_SYMBOL(__down_read_trylock);
-EXPORT_SYMBOL(__down_write);
-EXPORT_SYMBOL(__down_write_trylock);
-EXPORT_SYMBOL(__up_read);
-EXPORT_SYMBOL(__up_write);
-EXPORT_SYMBOL(__downgrade_write);
-
 /* Atomic counter implementation. */
 EXPORT_SYMBOL(atomic_add);
 EXPORT_SYMBOL(atomic_add_ret);
diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c
index e98bfda205a2..59dbd4645725 100644
--- a/arch/sparc/mm/fault_32.c
+++ b/arch/sparc/mm/fault_32.c
@@ -177,8 +177,7 @@ asmlinkage void do_sparc_fault(struct pt_regs *regs, int text_fault, int write,
 	unsigned long g2;
 	int from_user = !(regs->psr & PSR_PS);
 	int fault, code;
-	unsigned int flags = (FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
-			      (write ? FAULT_FLAG_WRITE : 0));
+	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
 
 	if (text_fault)
 		address = regs->pc;
@@ -235,6 +234,11 @@ good_area:
 			goto bad_area;
 	}
 
+	if (from_user)
+		flags |= FAULT_FLAG_USER;
+	if (write)
+		flags |= FAULT_FLAG_WRITE;
+
 	/*
 	 * If for any reason at all we couldn't handle the fault,
 	 * make sure we exit gracefully rather than endlessly redo
@@ -383,6 +387,7 @@ static void force_user_fault(unsigned long address, int write)
 	struct vm_area_struct *vma;
 	struct task_struct *tsk = current;
 	struct mm_struct *mm = tsk->mm;
+	unsigned int flags = FAULT_FLAG_USER;
 	int code;
 
 	code = SEGV_MAPERR;
@@ -402,11 +407,12 @@ good_area:
 	if (write) {
 		if (!(vma->vm_flags & VM_WRITE))
 			goto bad_area;
+		flags |= FAULT_FLAG_WRITE;
 	} else {
 		if (!(vma->vm_flags & (VM_READ | VM_EXEC)))
 			goto bad_area;
 	}
-	switch (handle_mm_fault(mm, vma, address, write ? FAULT_FLAG_WRITE : 0)) {
+	switch (handle_mm_fault(mm, vma, address, flags)) {
 	case VM_FAULT_SIGBUS:
 	case VM_FAULT_OOM:
 		goto do_sigbus;
diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c
index 5062ff389e83..2ebec263d685 100644
--- a/arch/sparc/mm/fault_64.c
+++ b/arch/sparc/mm/fault_64.c
@@ -315,7 +315,8 @@ asmlinkage void __kprobes do_sparc64_fault(struct pt_regs *regs)
 			bad_kernel_pc(regs, address);
 			return;
 		}
-	}
+	} else
+		flags |= FAULT_FLAG_USER;
 
 	/*
 	 * If we're in an interrupt or have no user
@@ -418,13 +419,14 @@ good_area:
 		    vma->vm_file != NULL)
 			set_thread_fault_code(fault_code |
 					      FAULT_CODE_BLKCOMMIT);
+
+		flags |= FAULT_FLAG_WRITE;
 	} else {
 		/* Allow reads even for write-only mappings */
 		if (!(vma->vm_flags & (VM_READ | VM_EXEC)))
 			goto bad_area;
 	}
 
-	flags |= ((fault_code & FAULT_CODE_WRITE) ? FAULT_FLAG_WRITE : 0);
 	fault = handle_mm_fault(mm, vma, address, flags);
 
 	if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
diff --git a/arch/sparc/mm/hugetlbpage.c b/arch/sparc/mm/hugetlbpage.c
index d2b59441ebdd..96399646570a 100644
--- a/arch/sparc/mm/hugetlbpage.c
+++ b/arch/sparc/mm/hugetlbpage.c
@@ -234,6 +234,11 @@ int pud_huge(pud_t pud)
 	return 0;
 }
 
+int pmd_huge_support(void)
+{
+	return 0;
+}
+
 struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address,
 			     pmd_t *pmd, int write)
 {
diff --git a/arch/tile/Kconfig b/arch/tile/Kconfig
index 24565a7ffe6d..d45a2c48f185 100644
--- a/arch/tile/Kconfig
+++ b/arch/tile/Kconfig
@@ -11,7 +11,6 @@ config TILE
 	select USE_GENERIC_SMP_HELPERS
 	select CC_OPTIMIZE_FOR_SIZE
 	select HAVE_DEBUG_KMEMLEAK
-	select HAVE_GENERIC_HARDIRQS
 	select GENERIC_IRQ_PROBE
 	select GENERIC_PENDING_IRQ if SMP
 	select GENERIC_IRQ_SHOW
@@ -26,6 +25,7 @@ config TILE
 	select HAVE_SYSCALL_TRACEPOINTS
 	select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
 	select HAVE_DEBUG_STACKOVERFLOW
+	select ARCH_WANT_FRAME_POINTERS
 
 # FIXME: investigate whether we need/want these options.
 #	select HAVE_IOREMAP_PROT
@@ -64,6 +64,9 @@ config HUGETLB_SUPER_PAGES
 	depends on HUGETLB_PAGE && TILEGX
 	def_bool y
 
+config GENERIC_TIME_VSYSCALL
+	def_bool y
+
 # FIXME: tilegx can implement a more efficient rwsem.
 config RWSEM_GENERIC_SPINLOCK
 	def_bool y
@@ -112,10 +115,19 @@ config SMP
 config HVC_TILE
 	depends on TTY
 	select HVC_DRIVER
+	select HVC_IRQ if TILEGX
 	def_bool y
 
 config TILEGX
-	bool "Building with TILE-Gx (64-bit) compiler and toolchain"
+	bool "Building for TILE-Gx (64-bit) processor"
+	select HAVE_FUNCTION_TRACER
+	select HAVE_FUNCTION_TRACE_MCOUNT_TEST
+	select HAVE_FUNCTION_GRAPH_TRACER
+	select HAVE_DYNAMIC_FTRACE
+	select HAVE_FTRACE_MCOUNT_RECORD
+	select HAVE_KPROBES
+	select HAVE_KRETPROBES
+	select HAVE_ARCH_KGDB
 
 config TILEPRO
 	def_bool !TILEGX
@@ -194,7 +206,7 @@ config SYSVIPC_COMPAT
 	def_bool y
 	depends on COMPAT && SYSVIPC
 
-# We do not currently support disabling HIGHMEM on tile64 and tilepro.
+# We do not currently support disabling HIGHMEM on tilepro.
 config HIGHMEM
 	bool # "Support for more than 512 MB of RAM"
 	default !TILEGX
@@ -300,6 +312,8 @@ config PAGE_OFFSET
 
 source "mm/Kconfig"
 
+source "kernel/Kconfig.preempt"
+
 config CMDLINE_BOOL
 	bool "Built-in kernel command line"
 	default n
@@ -347,7 +361,7 @@ config CMDLINE_OVERRIDE
 
 config VMALLOC_RESERVE
 	hex
-	default 0x1000000
+	default 0x2000000
 
 config HARDWALL
 	bool "Hardwall support to allow access to user dynamic network"
@@ -380,7 +394,6 @@ config PCI
 	select PCI_DOMAINS
 	select GENERIC_PCI_IOMAP
 	select TILE_GXIO_TRIO if TILEGX
-	select ARCH_SUPPORTS_MSI if TILEGX
 	select PCI_MSI if TILEGX
 	---help---
 	  Enable PCI root complex support, so PCIe endpoint devices can
@@ -396,8 +409,20 @@ config NO_IOMEM
 config NO_IOPORT
 	def_bool !PCI
 
+config TILE_PCI_IO
+	bool "PCI I/O space support"
+	default n
+	depends on PCI
+	depends on TILEGX
+	---help---
+	  Enable PCI I/O space support on TILEGx. Since the PCI I/O space
+	  is used by few modern PCIe endpoint devices, its support is disabled
+	  by default to save the TRIO PIO Region resource for other purposes.
+
 source "drivers/pci/Kconfig"
 
+source "drivers/pci/pcie/Kconfig"
+
 config TILE_USB
 	tristate "Tilera USB host adapter support"
 	default y
diff --git a/arch/tile/Kconfig.debug b/arch/tile/Kconfig.debug
index 9165ea979e85..19734d3ab1e8 100644
--- a/arch/tile/Kconfig.debug
+++ b/arch/tile/Kconfig.debug
@@ -14,14 +14,12 @@ config EARLY_PRINTK
 	  with klogd/syslogd. You should normally N here,
 	  unless you want to debug such a crash.
 
-config DEBUG_EXTRA_FLAGS
-	string "Additional compiler arguments when building with '-g'"
-	depends on DEBUG_INFO
-	default ""
+config TILE_HVGLUE_TRACE
+	bool "Provide wrapper functions for hypervisor ABI calls"
+	default n
 	help
-	  Debug info can be large, and flags like
-	  `-femit-struct-debug-baseonly' can reduce the kernel file
-	  size and build time noticeably.  Such flags are often
-	  helpful if the main use of debug info is line number info.
+	  Provide wrapper functions for the hypervisor ABI calls
+	  defined in arch/tile/kernel/hvglue.S.  This allows tracing
+	  mechanisms, etc., to have visibility into those calls.
 
 endmenu
diff --git a/arch/tile/Makefile b/arch/tile/Makefile
index 3d15364c6071..4dc380a519d4 100644
--- a/arch/tile/Makefile
+++ b/arch/tile/Makefile
@@ -30,10 +30,6 @@ endif
 # In kernel modules, this causes load failures due to unsupported relocations.
 KBUILD_CFLAGS   += -fno-asynchronous-unwind-tables
 
-ifneq ($(CONFIG_DEBUG_EXTRA_FLAGS),"")
-KBUILD_CFLAGS   += $(CONFIG_DEBUG_EXTRA_FLAGS)
-endif
-
 LIBGCC_PATH     := \
   $(shell $(CC) $(KBUILD_CFLAGS) $(KCFLAGS) -print-libgcc-file-name)
 
diff --git a/arch/tile/configs/tilegx_defconfig b/arch/tile/configs/tilegx_defconfig
index 47684815e5c8..730e40d9cf62 100644
--- a/arch/tile/configs/tilegx_defconfig
+++ b/arch/tile/configs/tilegx_defconfig
@@ -1,16 +1,15 @@
 CONFIG_TILEGX=y
-CONFIG_EXPERIMENTAL=y
-# CONFIG_LOCALVERSION_AUTO is not set
 CONFIG_SYSVIPC=y
 CONFIG_POSIX_MQUEUE=y
+CONFIG_FHANDLE=y
+CONFIG_AUDIT=y
+CONFIG_NO_HZ=y
 CONFIG_BSD_PROCESS_ACCT=y
 CONFIG_BSD_PROCESS_ACCT_V3=y
-CONFIG_FHANDLE=y
 CONFIG_TASKSTATS=y
 CONFIG_TASK_DELAY_ACCT=y
 CONFIG_TASK_XACCT=y
 CONFIG_TASK_IO_ACCOUNTING=y
-CONFIG_AUDIT=y
 CONFIG_LOG_BUF_SHIFT=19
 CONFIG_CGROUPS=y
 CONFIG_CGROUP_DEBUG=y
@@ -18,18 +17,18 @@ CONFIG_CGROUP_DEVICE=y
 CONFIG_CPUSETS=y
 CONFIG_CGROUP_CPUACCT=y
 CONFIG_RESOURCE_COUNTERS=y
-CONFIG_CGROUP_MEMCG=y
-CONFIG_CGROUP_MEMCG_SWAP=y
 CONFIG_CGROUP_SCHED=y
 CONFIG_RT_GROUP_SCHED=y
 CONFIG_BLK_CGROUP=y
 CONFIG_NAMESPACES=y
 CONFIG_RELAY=y
 CONFIG_BLK_DEV_INITRD=y
+CONFIG_RD_XZ=y
 CONFIG_SYSCTL_SYSCALL=y
 CONFIG_EMBEDDED=y
 # CONFIG_COMPAT_BRK is not set
 CONFIG_PROFILING=y
+CONFIG_KPROBES=y
 CONFIG_MODULES=y
 CONFIG_MODULE_FORCE_LOAD=y
 CONFIG_MODULE_UNLOAD=y
@@ -45,12 +44,12 @@ CONFIG_UNIXWARE_DISKLABEL=y
 CONFIG_SGI_PARTITION=y
 CONFIG_SUN_PARTITION=y
 CONFIG_KARMA_PARTITION=y
-CONFIG_EFI_PARTITION=y
 CONFIG_CFQ_GROUP_IOSCHED=y
 CONFIG_NR_CPUS=100
-CONFIG_NO_HZ=y
-CONFIG_HIGH_RES_TIMERS=y
 CONFIG_HZ_100=y
+# CONFIG_COMPACTION is not set
+CONFIG_PREEMPT_VOLUNTARY=y
+CONFIG_TILE_PCI_IO=y
 CONFIG_PCI_DEBUG=y
 # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
 CONFIG_BINFMT_MISC=y
@@ -108,150 +107,9 @@ CONFIG_IPV6_MULTIPLE_TABLES=y
 CONFIG_IPV6_MROUTE=y
 CONFIG_IPV6_PIMSM_V2=y
 CONFIG_NETLABEL=y
-CONFIG_NETFILTER=y
-CONFIG_NF_CONNTRACK=m
-CONFIG_NF_CONNTRACK_SECMARK=y
-CONFIG_NF_CONNTRACK_ZONES=y
-CONFIG_NF_CONNTRACK_EVENTS=y
-CONFIG_NF_CT_PROTO_DCCP=m
-CONFIG_NF_CT_PROTO_UDPLITE=m
-CONFIG_NF_CONNTRACK_AMANDA=m
-CONFIG_NF_CONNTRACK_FTP=m
-CONFIG_NF_CONNTRACK_H323=m
-CONFIG_NF_CONNTRACK_IRC=m
-CONFIG_NF_CONNTRACK_NETBIOS_NS=m
-CONFIG_NF_CONNTRACK_PPTP=m
-CONFIG_NF_CONNTRACK_SANE=m
-CONFIG_NF_CONNTRACK_SIP=m
-CONFIG_NF_CONNTRACK_TFTP=m
-CONFIG_NETFILTER_TPROXY=m
-CONFIG_NETFILTER_XT_TARGET_CLASSIFY=m
-CONFIG_NETFILTER_XT_TARGET_CONNMARK=m
-CONFIG_NETFILTER_XT_TARGET_CONNSECMARK=m
-CONFIG_NETFILTER_XT_TARGET_CT=m
-CONFIG_NETFILTER_XT_TARGET_DSCP=m
-CONFIG_NETFILTER_XT_TARGET_IDLETIMER=m
-CONFIG_NETFILTER_XT_TARGET_MARK=m
-CONFIG_NETFILTER_XT_TARGET_NFLOG=m
-CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m
-CONFIG_NETFILTER_XT_TARGET_TEE=m
-CONFIG_NETFILTER_XT_TARGET_TPROXY=m
-CONFIG_NETFILTER_XT_TARGET_TRACE=m
-CONFIG_NETFILTER_XT_TARGET_SECMARK=m
-CONFIG_NETFILTER_XT_TARGET_TCPMSS=m
-CONFIG_NETFILTER_XT_TARGET_TCPOPTSTRIP=m
-CONFIG_NETFILTER_XT_MATCH_CLUSTER=m
-CONFIG_NETFILTER_XT_MATCH_COMMENT=m
-CONFIG_NETFILTER_XT_MATCH_CONNBYTES=m
-CONFIG_NETFILTER_XT_MATCH_CONNLIMIT=m
-CONFIG_NETFILTER_XT_MATCH_CONNMARK=m
-CONFIG_NETFILTER_XT_MATCH_CONNTRACK=m
-CONFIG_NETFILTER_XT_MATCH_DCCP=m
-CONFIG_NETFILTER_XT_MATCH_DSCP=m
-CONFIG_NETFILTER_XT_MATCH_ESP=m
-CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=m
-CONFIG_NETFILTER_XT_MATCH_HELPER=m
-CONFIG_NETFILTER_XT_MATCH_IPRANGE=m
-CONFIG_NETFILTER_XT_MATCH_IPVS=m
-CONFIG_NETFILTER_XT_MATCH_LENGTH=m
-CONFIG_NETFILTER_XT_MATCH_LIMIT=m
-CONFIG_NETFILTER_XT_MATCH_MAC=m
-CONFIG_NETFILTER_XT_MATCH_MARK=m
-CONFIG_NETFILTER_XT_MATCH_MULTIPORT=m
-CONFIG_NETFILTER_XT_MATCH_OSF=m
-CONFIG_NETFILTER_XT_MATCH_OWNER=m
-CONFIG_NETFILTER_XT_MATCH_POLICY=m
-CONFIG_NETFILTER_XT_MATCH_PHYSDEV=m
-CONFIG_NETFILTER_XT_MATCH_PKTTYPE=m
-CONFIG_NETFILTER_XT_MATCH_QUOTA=m
-CONFIG_NETFILTER_XT_MATCH_RATEEST=m
-CONFIG_NETFILTER_XT_MATCH_REALM=m
-CONFIG_NETFILTER_XT_MATCH_RECENT=m
-CONFIG_NETFILTER_XT_MATCH_SOCKET=m
-CONFIG_NETFILTER_XT_MATCH_STATE=m
-CONFIG_NETFILTER_XT_MATCH_STATISTIC=m
-CONFIG_NETFILTER_XT_MATCH_STRING=m
-CONFIG_NETFILTER_XT_MATCH_TCPMSS=m
-CONFIG_NETFILTER_XT_MATCH_TIME=m
-CONFIG_NETFILTER_XT_MATCH_U32=m
-CONFIG_IP_VS=m
-CONFIG_IP_VS_IPV6=y
-CONFIG_IP_VS_PROTO_TCP=y
-CONFIG_IP_VS_PROTO_UDP=y
-CONFIG_IP_VS_PROTO_ESP=y
-CONFIG_IP_VS_PROTO_AH=y
-CONFIG_IP_VS_PROTO_SCTP=y
-CONFIG_IP_VS_RR=m
-CONFIG_IP_VS_WRR=m
-CONFIG_IP_VS_LC=m
-CONFIG_IP_VS_WLC=m
-CONFIG_IP_VS_LBLC=m
-CONFIG_IP_VS_LBLCR=m
-CONFIG_IP_VS_SED=m
-CONFIG_IP_VS_NQ=m
-CONFIG_NF_CONNTRACK_IPV4=m
-# CONFIG_NF_CONNTRACK_PROC_COMPAT is not set
-CONFIG_IP_NF_QUEUE=m
-CONFIG_IP_NF_IPTABLES=y
-CONFIG_IP_NF_MATCH_AH=m
-CONFIG_IP_NF_MATCH_ECN=m
-CONFIG_IP_NF_MATCH_TTL=m
-CONFIG_IP_NF_FILTER=y
-CONFIG_IP_NF_TARGET_REJECT=y
-CONFIG_IP_NF_TARGET_LOG=m
-CONFIG_IP_NF_TARGET_ULOG=m
-CONFIG_IP_NF_MANGLE=m
-CONFIG_IP_NF_TARGET_ECN=m
-CONFIG_IP_NF_TARGET_TTL=m
-CONFIG_IP_NF_RAW=m
-CONFIG_IP_NF_SECURITY=m
-CONFIG_IP_NF_ARPTABLES=m
-CONFIG_IP_NF_ARPFILTER=m
-CONFIG_IP_NF_ARP_MANGLE=m
-CONFIG_NF_CONNTRACK_IPV6=m
-CONFIG_IP6_NF_QUEUE=m
-CONFIG_IP6_NF_IPTABLES=m
-CONFIG_IP6_NF_MATCH_AH=m
-CONFIG_IP6_NF_MATCH_EUI64=m
-CONFIG_IP6_NF_MATCH_FRAG=m
-CONFIG_IP6_NF_MATCH_OPTS=m
-CONFIG_IP6_NF_MATCH_HL=m
-CONFIG_IP6_NF_MATCH_IPV6HEADER=m
-CONFIG_IP6_NF_MATCH_MH=m
-CONFIG_IP6_NF_MATCH_RT=m
-CONFIG_IP6_NF_TARGET_HL=m
-CONFIG_IP6_NF_TARGET_LOG=m
-CONFIG_IP6_NF_FILTER=m
-CONFIG_IP6_NF_TARGET_REJECT=m
-CONFIG_IP6_NF_MANGLE=m
-CONFIG_IP6_NF_RAW=m
-CONFIG_IP6_NF_SECURITY=m
-CONFIG_BRIDGE_NF_EBTABLES=m
-CONFIG_BRIDGE_EBT_BROUTE=m
-CONFIG_BRIDGE_EBT_T_FILTER=m
-CONFIG_BRIDGE_EBT_T_NAT=m
-CONFIG_BRIDGE_EBT_802_3=m
-CONFIG_BRIDGE_EBT_AMONG=m
-CONFIG_BRIDGE_EBT_ARP=m
-CONFIG_BRIDGE_EBT_IP=m
-CONFIG_BRIDGE_EBT_IP6=m
-CONFIG_BRIDGE_EBT_LIMIT=m
-CONFIG_BRIDGE_EBT_MARK=m
-CONFIG_BRIDGE_EBT_PKTTYPE=m
-CONFIG_BRIDGE_EBT_STP=m
-CONFIG_BRIDGE_EBT_VLAN=m
-CONFIG_BRIDGE_EBT_ARPREPLY=m
-CONFIG_BRIDGE_EBT_DNAT=m
-CONFIG_BRIDGE_EBT_MARK_T=m
-CONFIG_BRIDGE_EBT_REDIRECT=m
-CONFIG_BRIDGE_EBT_SNAT=m
-CONFIG_BRIDGE_EBT_LOG=m
-CONFIG_BRIDGE_EBT_ULOG=m
-CONFIG_BRIDGE_EBT_NFLOG=m
 CONFIG_RDS=m
 CONFIG_RDS_TCP=m
 CONFIG_BRIDGE=m
-CONFIG_NET_DSA=y
 CONFIG_VLAN_8021Q=m
 CONFIG_VLAN_8021Q_GVRP=y
 CONFIG_PHONET=m
@@ -292,13 +150,13 @@ CONFIG_NET_ACT_POLICE=m
 CONFIG_NET_ACT_GACT=m
 CONFIG_GACT_PROB=y
 CONFIG_NET_ACT_MIRRED=m
-CONFIG_NET_ACT_IPT=m
 CONFIG_NET_ACT_NAT=m
 CONFIG_NET_ACT_PEDIT=m
 CONFIG_NET_ACT_SIMP=m
 CONFIG_NET_ACT_SKBEDIT=m
 CONFIG_NET_CLS_IND=y
 CONFIG_DCB=y
+CONFIG_DNS_RESOLVER=y
 # CONFIG_WIRELESS is not set
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_DEVTMPFS=y
@@ -317,10 +175,12 @@ CONFIG_BLK_DEV_SD=y
 CONFIG_SCSI_CONSTANTS=y
 CONFIG_SCSI_LOGGING=y
 CONFIG_SCSI_SAS_ATA=y
+CONFIG_ISCSI_TCP=m
 CONFIG_SCSI_MVSAS=y
 # CONFIG_SCSI_MVSAS_DEBUG is not set
 CONFIG_SCSI_MVSAS_TASKLET=y
 CONFIG_ATA=y
+CONFIG_SATA_AHCI=y
 CONFIG_SATA_SIL24=y
 # CONFIG_ATA_SFF is not set
 CONFIG_MD=y
@@ -343,6 +203,12 @@ CONFIG_DM_MULTIPATH_QL=m
 CONFIG_DM_MULTIPATH_ST=m
 CONFIG_DM_DELAY=m
 CONFIG_DM_UEVENT=y
+CONFIG_TARGET_CORE=m
+CONFIG_TCM_IBLOCK=m
+CONFIG_TCM_FILEIO=m
+CONFIG_TCM_PSCSI=m
+CONFIG_LOOPBACK_TARGET=m
+CONFIG_ISCSI_TARGET=m
 CONFIG_FUSION=y
 CONFIG_FUSION_SAS=y
 CONFIG_NETDEVICES=y
@@ -359,42 +225,8 @@ CONFIG_VETH=m
 CONFIG_NET_DSA_MV88E6060=y
 CONFIG_NET_DSA_MV88E6131=y
 CONFIG_NET_DSA_MV88E6123_61_65=y
-# CONFIG_NET_VENDOR_3COM is not set
-# CONFIG_NET_VENDOR_ADAPTEC is not set
-# CONFIG_NET_VENDOR_ALTEON is not set
-# CONFIG_NET_VENDOR_AMD is not set
-# CONFIG_NET_VENDOR_ATHEROS is not set
-# CONFIG_NET_VENDOR_BROADCOM is not set
-# CONFIG_NET_VENDOR_BROCADE is not set
-# CONFIG_NET_VENDOR_CHELSIO is not set
-# CONFIG_NET_VENDOR_CISCO is not set
-# CONFIG_NET_VENDOR_DEC is not set
-# CONFIG_NET_VENDOR_DLINK is not set
-# CONFIG_NET_VENDOR_EMULEX is not set
-# CONFIG_NET_VENDOR_EXAR is not set
-# CONFIG_NET_VENDOR_HP is not set
-# CONFIG_NET_VENDOR_INTEL is not set
-# CONFIG_NET_VENDOR_MARVELL is not set
-# CONFIG_NET_VENDOR_MELLANOX is not set
-# CONFIG_NET_VENDOR_MICREL is not set
-# CONFIG_NET_VENDOR_MYRI is not set
-# CONFIG_NET_VENDOR_NATSEMI is not set
-# CONFIG_NET_VENDOR_NVIDIA is not set
-# CONFIG_NET_VENDOR_OKI is not set
-# CONFIG_NET_PACKET_ENGINE is not set
-# CONFIG_NET_VENDOR_QLOGIC is not set
-# CONFIG_NET_VENDOR_REALTEK is not set
-# CONFIG_NET_VENDOR_RDC is not set
-# CONFIG_NET_VENDOR_SEEQ is not set
-# CONFIG_NET_VENDOR_SILAN is not set
-# CONFIG_NET_VENDOR_SIS is not set
-# CONFIG_NET_VENDOR_SMSC is not set
-# CONFIG_NET_VENDOR_STMICRO is not set
-# CONFIG_NET_VENDOR_SUN is not set
-# CONFIG_NET_VENDOR_TEHUTI is not set
-# CONFIG_NET_VENDOR_TI is not set
-# CONFIG_TILE_NET is not set
-# CONFIG_NET_VENDOR_VIA is not set
+CONFIG_SKY2=y
+CONFIG_PTP_1588_CLOCK_TILEGX=y
 # CONFIG_WLAN is not set
 # CONFIG_INPUT_MOUSEDEV is not set
 # CONFIG_INPUT_KEYBOARD is not set
@@ -402,6 +234,7 @@ CONFIG_NET_DSA_MV88E6123_61_65=y
 # CONFIG_SERIO is not set
 # CONFIG_VT is not set
 # CONFIG_LEGACY_PTYS is not set
+CONFIG_SERIAL_TILEGX=y
 CONFIG_HW_RANDOM=y
 CONFIG_HW_RANDOM_TIMERIOMEM=m
 CONFIG_I2C=y
@@ -410,13 +243,16 @@ CONFIG_I2C_CHARDEV=y
 CONFIG_WATCHDOG=y
 CONFIG_WATCHDOG_NOWAYOUT=y
 # CONFIG_VGA_ARB is not set
-# CONFIG_HID_SUPPORT is not set
+CONFIG_DRM=m
+CONFIG_DRM_TDFX=m
+CONFIG_DRM_R128=m
+CONFIG_DRM_MGA=m
+CONFIG_DRM_VIA=m
+CONFIG_DRM_SAVAGE=m
 CONFIG_USB=y
-# CONFIG_USB_DEVICE_CLASS is not set
 CONFIG_USB_EHCI_HCD=y
 CONFIG_USB_OHCI_HCD=y
 CONFIG_USB_STORAGE=y
-CONFIG_USB_LIBUSUAL=y
 CONFIG_EDAC=y
 CONFIG_EDAC_MM_EDAC=y
 CONFIG_RTC_CLASS=y
@@ -464,9 +300,8 @@ CONFIG_ECRYPT_FS=m
 CONFIG_CRAMFS=m
 CONFIG_SQUASHFS=m
 CONFIG_NFS_FS=m
-CONFIG_NFS_V3=y
 CONFIG_NFS_V3_ACL=y
-CONFIG_NFS_V4=y
+CONFIG_NFS_V4=m
 CONFIG_NFS_V4_1=y
 CONFIG_NFS_FSCACHE=y
 CONFIG_NFSD=m
@@ -519,25 +354,28 @@ CONFIG_NLS_ISO8859_15=m
 CONFIG_NLS_KOI8_R=m
 CONFIG_NLS_KOI8_U=m
 CONFIG_NLS_UTF8=m
+CONFIG_DLM=m
 CONFIG_DLM_DEBUG=y
+CONFIG_DYNAMIC_DEBUG=y
+CONFIG_DEBUG_INFO=y
+CONFIG_DEBUG_INFO_REDUCED=y
 # CONFIG_ENABLE_WARN_DEPRECATED is not set
-CONFIG_MAGIC_SYSRQ=y
 CONFIG_STRIP_ASM_SYMS=y
 CONFIG_DEBUG_FS=y
 CONFIG_HEADERS_CHECK=y
+# CONFIG_FRAME_POINTER is not set
+CONFIG_DEBUG_FORCE_WEAK_PER_CPU=y
+CONFIG_DEBUG_VM=y
+CONFIG_DEBUG_MEMORY_INIT=y
+CONFIG_DEBUG_STACKOVERFLOW=y
 CONFIG_LOCKUP_DETECTOR=y
 CONFIG_SCHEDSTATS=y
 CONFIG_TIMER_STATS=y
-CONFIG_DEBUG_INFO=y
-CONFIG_DEBUG_INFO_REDUCED=y
-CONFIG_DEBUG_VM=y
-CONFIG_DEBUG_MEMORY_INIT=y
 CONFIG_DEBUG_LIST=y
 CONFIG_DEBUG_CREDENTIALS=y
-CONFIG_DEBUG_FORCE_WEAK_PER_CPU=y
-CONFIG_DYNAMIC_DEBUG=y
+CONFIG_RCU_CPU_STALL_TIMEOUT=60
 CONFIG_ASYNC_RAID6_TEST=m
-CONFIG_DEBUG_STACKOVERFLOW=y
+CONFIG_KGDB=y
 CONFIG_KEYS_DEBUG_PROC_KEYS=y
 CONFIG_SECURITY=y
 CONFIG_SECURITYFS=y
@@ -546,7 +384,6 @@ CONFIG_SECURITY_NETWORK_XFRM=y
 CONFIG_SECURITY_SELINUX=y
 CONFIG_SECURITY_SELINUX_BOOTPARAM=y
 CONFIG_SECURITY_SELINUX_DISABLE=y
-CONFIG_CRYPTO_NULL=m
 CONFIG_CRYPTO_PCRYPT=m
 CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_TEST=m
@@ -559,14 +396,12 @@ CONFIG_CRYPTO_XTS=m
 CONFIG_CRYPTO_HMAC=y
 CONFIG_CRYPTO_XCBC=m
 CONFIG_CRYPTO_VMAC=m
-CONFIG_CRYPTO_CRC32C=y
 CONFIG_CRYPTO_MICHAEL_MIC=m
 CONFIG_CRYPTO_RMD128=m
 CONFIG_CRYPTO_RMD160=m
 CONFIG_CRYPTO_RMD256=m
 CONFIG_CRYPTO_RMD320=m
 CONFIG_CRYPTO_SHA1=y
-CONFIG_CRYPTO_SHA256=m
 CONFIG_CRYPTO_SHA512=m
 CONFIG_CRYPTO_TGR192=m
 CONFIG_CRYPTO_WP512=m
diff --git a/arch/tile/configs/tilepro_defconfig b/arch/tile/configs/tilepro_defconfig
index dd2b8f0c631f..80fc32ed0491 100644
--- a/arch/tile/configs/tilepro_defconfig
+++ b/arch/tile/configs/tilepro_defconfig
@@ -1,15 +1,14 @@
-CONFIG_EXPERIMENTAL=y
-# CONFIG_LOCALVERSION_AUTO is not set
 CONFIG_SYSVIPC=y
 CONFIG_POSIX_MQUEUE=y
+CONFIG_AUDIT=y
+CONFIG_NO_HZ=y
+CONFIG_HIGH_RES_TIMERS=y
 CONFIG_BSD_PROCESS_ACCT=y
 CONFIG_BSD_PROCESS_ACCT_V3=y
-CONFIG_FHANDLE=y
 CONFIG_TASKSTATS=y
 CONFIG_TASK_DELAY_ACCT=y
 CONFIG_TASK_XACCT=y
 CONFIG_TASK_IO_ACCOUNTING=y
-CONFIG_AUDIT=y
 CONFIG_LOG_BUF_SHIFT=19
 CONFIG_CGROUPS=y
 CONFIG_CGROUP_DEBUG=y
@@ -17,14 +16,13 @@ CONFIG_CGROUP_DEVICE=y
 CONFIG_CPUSETS=y
 CONFIG_CGROUP_CPUACCT=y
 CONFIG_RESOURCE_COUNTERS=y
-CONFIG_CGROUP_MEMCG=y
-CONFIG_CGROUP_MEMCG_SWAP=y
 CONFIG_CGROUP_SCHED=y
 CONFIG_RT_GROUP_SCHED=y
 CONFIG_BLK_CGROUP=y
 CONFIG_NAMESPACES=y
 CONFIG_RELAY=y
 CONFIG_BLK_DEV_INITRD=y
+CONFIG_RD_XZ=y
 CONFIG_SYSCTL_SYSCALL=y
 CONFIG_EMBEDDED=y
 # CONFIG_COMPAT_BRK is not set
@@ -44,11 +42,10 @@ CONFIG_UNIXWARE_DISKLABEL=y
 CONFIG_SGI_PARTITION=y
 CONFIG_SUN_PARTITION=y
 CONFIG_KARMA_PARTITION=y
-CONFIG_EFI_PARTITION=y
 CONFIG_CFQ_GROUP_IOSCHED=y
-CONFIG_NO_HZ=y
-CONFIG_HIGH_RES_TIMERS=y
 CONFIG_HZ_100=y
+# CONFIG_COMPACTION is not set
+CONFIG_PREEMPT_VOLUNTARY=y
 CONFIG_PCI_DEBUG=y
 # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
 CONFIG_BINFMT_MISC=y
@@ -122,16 +119,15 @@ CONFIG_NF_CONNTRACK_PPTP=m
 CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
-CONFIG_NETFILTER_TPROXY=m
 CONFIG_NETFILTER_XT_TARGET_CLASSIFY=m
 CONFIG_NETFILTER_XT_TARGET_CONNMARK=m
 CONFIG_NETFILTER_XT_TARGET_CONNSECMARK=m
-CONFIG_NETFILTER_XT_TARGET_CT=m
 CONFIG_NETFILTER_XT_TARGET_DSCP=m
 CONFIG_NETFILTER_XT_TARGET_IDLETIMER=m
 CONFIG_NETFILTER_XT_TARGET_MARK=m
 CONFIG_NETFILTER_XT_TARGET_NFLOG=m
 CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m
+CONFIG_NETFILTER_XT_TARGET_NOTRACK=m
 CONFIG_NETFILTER_XT_TARGET_TEE=m
 CONFIG_NETFILTER_XT_TARGET_TPROXY=m
 CONFIG_NETFILTER_XT_TARGET_TRACE=m
@@ -189,14 +185,12 @@ CONFIG_IP_VS_SED=m
 CONFIG_IP_VS_NQ=m
 CONFIG_NF_CONNTRACK_IPV4=m
 # CONFIG_NF_CONNTRACK_PROC_COMPAT is not set
-CONFIG_IP_NF_QUEUE=m
 CONFIG_IP_NF_IPTABLES=y
 CONFIG_IP_NF_MATCH_AH=m
 CONFIG_IP_NF_MATCH_ECN=m
 CONFIG_IP_NF_MATCH_TTL=m
 CONFIG_IP_NF_FILTER=y
 CONFIG_IP_NF_TARGET_REJECT=y
-CONFIG_IP_NF_TARGET_LOG=m
 CONFIG_IP_NF_TARGET_ULOG=m
 CONFIG_IP_NF_MANGLE=m
 CONFIG_IP_NF_TARGET_ECN=m
@@ -207,8 +201,6 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
-CONFIG_IP6_NF_QUEUE=m
-CONFIG_IP6_NF_IPTABLES=m
 CONFIG_IP6_NF_MATCH_AH=m
 CONFIG_IP6_NF_MATCH_EUI64=m
 CONFIG_IP6_NF_MATCH_FRAG=m
@@ -218,7 +210,6 @@ CONFIG_IP6_NF_MATCH_IPV6HEADER=m
 CONFIG_IP6_NF_MATCH_MH=m
 CONFIG_IP6_NF_MATCH_RT=m
 CONFIG_IP6_NF_TARGET_HL=m
-CONFIG_IP6_NF_TARGET_LOG=m
 CONFIG_IP6_NF_FILTER=m
 CONFIG_IP6_NF_TARGET_REJECT=m
 CONFIG_IP6_NF_MANGLE=m
@@ -249,7 +240,6 @@ CONFIG_BRIDGE_EBT_NFLOG=m
 CONFIG_RDS=m
 CONFIG_RDS_TCP=m
 CONFIG_BRIDGE=m
-CONFIG_NET_DSA=y
 CONFIG_VLAN_8021Q=m
 CONFIG_VLAN_8021Q_GVRP=y
 CONFIG_PHONET=m
@@ -297,6 +287,7 @@ CONFIG_NET_ACT_SIMP=m
 CONFIG_NET_ACT_SKBEDIT=m
 CONFIG_NET_CLS_IND=y
 CONFIG_DCB=y
+CONFIG_DNS_RESOLVER=y
 # CONFIG_WIRELESS is not set
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_DEVTMPFS=y
@@ -354,40 +345,7 @@ CONFIG_NET_DSA_MV88E6060=y
 CONFIG_NET_DSA_MV88E6131=y
 CONFIG_NET_DSA_MV88E6123_61_65=y
 # CONFIG_NET_VENDOR_3COM is not set
-# CONFIG_NET_VENDOR_ADAPTEC is not set
-# CONFIG_NET_VENDOR_ALTEON is not set
-# CONFIG_NET_VENDOR_AMD is not set
-# CONFIG_NET_VENDOR_ATHEROS is not set
-# CONFIG_NET_VENDOR_BROADCOM is not set
-# CONFIG_NET_VENDOR_BROCADE is not set
-# CONFIG_NET_VENDOR_CHELSIO is not set
-# CONFIG_NET_VENDOR_CISCO is not set
-# CONFIG_NET_VENDOR_DEC is not set
-# CONFIG_NET_VENDOR_DLINK is not set
-# CONFIG_NET_VENDOR_EMULEX is not set
-# CONFIG_NET_VENDOR_EXAR is not set
-# CONFIG_NET_VENDOR_HP is not set
-# CONFIG_NET_VENDOR_INTEL is not set
-# CONFIG_NET_VENDOR_MARVELL is not set
-# CONFIG_NET_VENDOR_MELLANOX is not set
-# CONFIG_NET_VENDOR_MICREL is not set
-# CONFIG_NET_VENDOR_MYRI is not set
-# CONFIG_NET_VENDOR_NATSEMI is not set
-# CONFIG_NET_VENDOR_NVIDIA is not set
-# CONFIG_NET_VENDOR_OKI is not set
-# CONFIG_NET_PACKET_ENGINE is not set
-# CONFIG_NET_VENDOR_QLOGIC is not set
-# CONFIG_NET_VENDOR_REALTEK is not set
-# CONFIG_NET_VENDOR_RDC is not set
-# CONFIG_NET_VENDOR_SEEQ is not set
-# CONFIG_NET_VENDOR_SILAN is not set
-# CONFIG_NET_VENDOR_SIS is not set
-# CONFIG_NET_VENDOR_SMSC is not set
-# CONFIG_NET_VENDOR_STMICRO is not set
-# CONFIG_NET_VENDOR_SUN is not set
-# CONFIG_NET_VENDOR_TEHUTI is not set
-# CONFIG_NET_VENDOR_TI is not set
-# CONFIG_NET_VENDOR_VIA is not set
+CONFIG_E1000E=y
 # CONFIG_WLAN is not set
 # CONFIG_INPUT_MOUSEDEV is not set
 # CONFIG_INPUT_KEYBOARD is not set
@@ -403,7 +361,6 @@ CONFIG_I2C_CHARDEV=y
 CONFIG_WATCHDOG=y
 CONFIG_WATCHDOG_NOWAYOUT=y
 # CONFIG_VGA_ARB is not set
-# CONFIG_HID_SUPPORT is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_EDAC=y
 CONFIG_EDAC_MM_EDAC=y
@@ -448,13 +405,13 @@ CONFIG_PROC_KCORE=y
 CONFIG_TMPFS=y
 CONFIG_TMPFS_POSIX_ACL=y
 CONFIG_HUGETLBFS=y
+CONFIG_CONFIGFS_FS=m
 CONFIG_ECRYPT_FS=m
 CONFIG_CRAMFS=m
 CONFIG_SQUASHFS=m
 CONFIG_NFS_FS=m
-CONFIG_NFS_V3=y
 CONFIG_NFS_V3_ACL=y
-CONFIG_NFS_V4=y
+CONFIG_NFS_V4=m
 CONFIG_NFS_V4_1=y
 CONFIG_NFS_FSCACHE=y
 CONFIG_NFSD=m
@@ -508,26 +465,29 @@ CONFIG_NLS_ISO8859_15=m
 CONFIG_NLS_KOI8_R=m
 CONFIG_NLS_KOI8_U=m
 CONFIG_NLS_UTF8=m
+CONFIG_DLM=m
 CONFIG_DLM_DEBUG=y
+CONFIG_DYNAMIC_DEBUG=y
+CONFIG_DEBUG_INFO=y
+CONFIG_DEBUG_INFO_REDUCED=y
 # CONFIG_ENABLE_WARN_DEPRECATED is not set
 CONFIG_FRAME_WARN=2048
-CONFIG_MAGIC_SYSRQ=y
 CONFIG_STRIP_ASM_SYMS=y
 CONFIG_DEBUG_FS=y
 CONFIG_HEADERS_CHECK=y
+# CONFIG_FRAME_POINTER is not set
+CONFIG_DEBUG_FORCE_WEAK_PER_CPU=y
+CONFIG_MAGIC_SYSRQ=y
+CONFIG_DEBUG_VM=y
+CONFIG_DEBUG_MEMORY_INIT=y
+CONFIG_DEBUG_STACKOVERFLOW=y
 CONFIG_LOCKUP_DETECTOR=y
 CONFIG_SCHEDSTATS=y
 CONFIG_TIMER_STATS=y
-CONFIG_DEBUG_INFO=y
-CONFIG_DEBUG_INFO_REDUCED=y
-CONFIG_DEBUG_VM=y
-CONFIG_DEBUG_MEMORY_INIT=y
 CONFIG_DEBUG_LIST=y
 CONFIG_DEBUG_CREDENTIALS=y
-CONFIG_DEBUG_FORCE_WEAK_PER_CPU=y
-CONFIG_DYNAMIC_DEBUG=y
+CONFIG_RCU_CPU_STALL_TIMEOUT=60
 CONFIG_ASYNC_RAID6_TEST=m
-CONFIG_DEBUG_STACKOVERFLOW=y
 CONFIG_KEYS_DEBUG_PROC_KEYS=y
 CONFIG_SECURITY=y
 CONFIG_SECURITYFS=y
@@ -536,7 +496,6 @@ CONFIG_SECURITY_NETWORK_XFRM=y
 CONFIG_SECURITY_SELINUX=y
 CONFIG_SECURITY_SELINUX_BOOTPARAM=y
 CONFIG_SECURITY_SELINUX_DISABLE=y
-CONFIG_CRYPTO_NULL=m
 CONFIG_CRYPTO_PCRYPT=m
 CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_TEST=m
@@ -549,14 +508,12 @@ CONFIG_CRYPTO_XTS=m
 CONFIG_CRYPTO_HMAC=y
 CONFIG_CRYPTO_XCBC=m
 CONFIG_CRYPTO_VMAC=m
-CONFIG_CRYPTO_CRC32C=y
 CONFIG_CRYPTO_MICHAEL_MIC=m
 CONFIG_CRYPTO_RMD128=m
 CONFIG_CRYPTO_RMD160=m
 CONFIG_CRYPTO_RMD256=m
 CONFIG_CRYPTO_RMD320=m
 CONFIG_CRYPTO_SHA1=y
-CONFIG_CRYPTO_SHA256=m
 CONFIG_CRYPTO_SHA512=m
 CONFIG_CRYPTO_TGR192=m
 CONFIG_CRYPTO_WP512=m
diff --git a/arch/tile/gxio/Kconfig b/arch/tile/gxio/Kconfig
index d221f8d6de8b..d4e10d58071b 100644
--- a/arch/tile/gxio/Kconfig
+++ b/arch/tile/gxio/Kconfig
@@ -26,3 +26,8 @@ config TILE_GXIO_TRIO
 config TILE_GXIO_USB_HOST
 	bool
 	select TILE_GXIO
+
+# Support direct access to the TILE-Gx UART hardware from kernel space.
+config TILE_GXIO_UART
+	bool
+	select TILE_GXIO
diff --git a/arch/tile/gxio/Makefile b/arch/tile/gxio/Makefile
index 8684bcaa74ea..26ae2c727467 100644
--- a/arch/tile/gxio/Makefile
+++ b/arch/tile/gxio/Makefile
@@ -6,4 +6,5 @@ obj-$(CONFIG_TILE_GXIO) += iorpc_globals.o kiorpc.o
 obj-$(CONFIG_TILE_GXIO_DMA) += dma_queue.o
 obj-$(CONFIG_TILE_GXIO_MPIPE) += mpipe.o iorpc_mpipe.o iorpc_mpipe_info.o
 obj-$(CONFIG_TILE_GXIO_TRIO) += trio.o iorpc_trio.o
+obj-$(CONFIG_TILE_GXIO_UART) += uart.o iorpc_uart.o
 obj-$(CONFIG_TILE_GXIO_USB_HOST) += usb_host.o iorpc_usb_host.o
diff --git a/arch/tile/gxio/iorpc_mpipe.c b/arch/tile/gxio/iorpc_mpipe.c
index 31b87bf8c027..e19325c4c431 100644
--- a/arch/tile/gxio/iorpc_mpipe.c
+++ b/arch/tile/gxio/iorpc_mpipe.c
@@ -21,7 +21,7 @@ struct alloc_buffer_stacks_param {
 	unsigned int flags;
 };
 
-int gxio_mpipe_alloc_buffer_stacks(gxio_mpipe_context_t * context,
+int gxio_mpipe_alloc_buffer_stacks(gxio_mpipe_context_t *context,
 				   unsigned int count, unsigned int first,
 				   unsigned int flags)
 {
@@ -45,7 +45,7 @@ struct init_buffer_stack_aux_param {
 	unsigned int buffer_size_enum;
 };
 
-int gxio_mpipe_init_buffer_stack_aux(gxio_mpipe_context_t * context,
+int gxio_mpipe_init_buffer_stack_aux(gxio_mpipe_context_t *context,
 				     void *mem_va, size_t mem_size,
 				     unsigned int mem_flags, unsigned int stack,
 				     unsigned int buffer_size_enum)
@@ -80,7 +80,7 @@ struct alloc_notif_rings_param {
 	unsigned int flags;
 };
 
-int gxio_mpipe_alloc_notif_rings(gxio_mpipe_context_t * context,
+int gxio_mpipe_alloc_notif_rings(gxio_mpipe_context_t *context,
 				 unsigned int count, unsigned int first,
 				 unsigned int flags)
 {
@@ -102,7 +102,7 @@ struct init_notif_ring_aux_param {
 	unsigned int ring;
 };
 
-int gxio_mpipe_init_notif_ring_aux(gxio_mpipe_context_t * context, void *mem_va,
+int gxio_mpipe_init_notif_ring_aux(gxio_mpipe_context_t *context, void *mem_va,
 				   size_t mem_size, unsigned int mem_flags,
 				   unsigned int ring)
 {
@@ -133,7 +133,7 @@ struct request_notif_ring_interrupt_param {
 	unsigned int ring;
 };
 
-int gxio_mpipe_request_notif_ring_interrupt(gxio_mpipe_context_t * context,
+int gxio_mpipe_request_notif_ring_interrupt(gxio_mpipe_context_t *context,
 					    int inter_x, int inter_y,
 					    int inter_ipi, int inter_event,
 					    unsigned int ring)
@@ -158,7 +158,7 @@ struct enable_notif_ring_interrupt_param {
 	unsigned int ring;
 };
 
-int gxio_mpipe_enable_notif_ring_interrupt(gxio_mpipe_context_t * context,
+int gxio_mpipe_enable_notif_ring_interrupt(gxio_mpipe_context_t *context,
 					   unsigned int ring)
 {
 	struct enable_notif_ring_interrupt_param temp;
@@ -179,7 +179,7 @@ struct alloc_notif_groups_param {
 	unsigned int flags;
 };
 
-int gxio_mpipe_alloc_notif_groups(gxio_mpipe_context_t * context,
+int gxio_mpipe_alloc_notif_groups(gxio_mpipe_context_t *context,
 				  unsigned int count, unsigned int first,
 				  unsigned int flags)
 {
@@ -201,7 +201,7 @@ struct init_notif_group_param {
 	gxio_mpipe_notif_group_bits_t bits;
 };
 
-int gxio_mpipe_init_notif_group(gxio_mpipe_context_t * context,
+int gxio_mpipe_init_notif_group(gxio_mpipe_context_t *context,
 				unsigned int group,
 				gxio_mpipe_notif_group_bits_t bits)
 {
@@ -223,7 +223,7 @@ struct alloc_buckets_param {
 	unsigned int flags;
 };
 
-int gxio_mpipe_alloc_buckets(gxio_mpipe_context_t * context, unsigned int count,
+int gxio_mpipe_alloc_buckets(gxio_mpipe_context_t *context, unsigned int count,
 			     unsigned int first, unsigned int flags)
 {
 	struct alloc_buckets_param temp;
@@ -244,7 +244,7 @@ struct init_bucket_param {
 	MPIPE_LBL_INIT_DAT_BSTS_TBL_t bucket_info;
 };
 
-int gxio_mpipe_init_bucket(gxio_mpipe_context_t * context, unsigned int bucket,
+int gxio_mpipe_init_bucket(gxio_mpipe_context_t *context, unsigned int bucket,
 			   MPIPE_LBL_INIT_DAT_BSTS_TBL_t bucket_info)
 {
 	struct init_bucket_param temp;
@@ -265,7 +265,7 @@ struct alloc_edma_rings_param {
 	unsigned int flags;
 };
 
-int gxio_mpipe_alloc_edma_rings(gxio_mpipe_context_t * context,
+int gxio_mpipe_alloc_edma_rings(gxio_mpipe_context_t *context,
 				unsigned int count, unsigned int first,
 				unsigned int flags)
 {
@@ -288,7 +288,7 @@ struct init_edma_ring_aux_param {
 	unsigned int channel;
 };
 
-int gxio_mpipe_init_edma_ring_aux(gxio_mpipe_context_t * context, void *mem_va,
+int gxio_mpipe_init_edma_ring_aux(gxio_mpipe_context_t *context, void *mem_va,
 				  size_t mem_size, unsigned int mem_flags,
 				  unsigned int ring, unsigned int channel)
 {
@@ -315,7 +315,7 @@ int gxio_mpipe_init_edma_ring_aux(gxio_mpipe_context_t * context, void *mem_va,
 EXPORT_SYMBOL(gxio_mpipe_init_edma_ring_aux);
 
 
-int gxio_mpipe_commit_rules(gxio_mpipe_context_t * context, const void *blob,
+int gxio_mpipe_commit_rules(gxio_mpipe_context_t *context, const void *blob,
 			    size_t blob_size)
 {
 	const void *params = blob;
@@ -332,7 +332,7 @@ struct register_client_memory_param {
 	unsigned int flags;
 };
 
-int gxio_mpipe_register_client_memory(gxio_mpipe_context_t * context,
+int gxio_mpipe_register_client_memory(gxio_mpipe_context_t *context,
 				      unsigned int iotlb, HV_PTE pte,
 				      unsigned int flags)
 {
@@ -355,7 +355,7 @@ struct link_open_aux_param {
 	unsigned int flags;
 };
 
-int gxio_mpipe_link_open_aux(gxio_mpipe_context_t * context,
+int gxio_mpipe_link_open_aux(gxio_mpipe_context_t *context,
 			     _gxio_mpipe_link_name_t name, unsigned int flags)
 {
 	struct link_open_aux_param temp;
@@ -374,7 +374,7 @@ struct link_close_aux_param {
 	int mac;
 };
 
-int gxio_mpipe_link_close_aux(gxio_mpipe_context_t * context, int mac)
+int gxio_mpipe_link_close_aux(gxio_mpipe_context_t *context, int mac)
 {
 	struct link_close_aux_param temp;
 	struct link_close_aux_param *params = &temp;
@@ -387,6 +387,27 @@ int gxio_mpipe_link_close_aux(gxio_mpipe_context_t * context, int mac)
 
 EXPORT_SYMBOL(gxio_mpipe_link_close_aux);
 
+struct link_set_attr_aux_param {
+	int mac;
+	uint32_t attr;
+	int64_t val;
+};
+
+int gxio_mpipe_link_set_attr_aux(gxio_mpipe_context_t *context, int mac,
+				 uint32_t attr, int64_t val)
+{
+	struct link_set_attr_aux_param temp;
+	struct link_set_attr_aux_param *params = &temp;
+
+	params->mac = mac;
+	params->attr = attr;
+	params->val = val;
+
+	return hv_dev_pwrite(context->fd, 0, (HV_VirtAddr) params,
+			     sizeof(*params), GXIO_MPIPE_OP_LINK_SET_ATTR_AUX);
+}
+
+EXPORT_SYMBOL(gxio_mpipe_link_set_attr_aux);
 
 struct get_timestamp_aux_param {
 	uint64_t sec;
@@ -394,8 +415,8 @@ struct get_timestamp_aux_param {
 	uint64_t cycles;
 };
 
-int gxio_mpipe_get_timestamp_aux(gxio_mpipe_context_t * context, uint64_t * sec,
-				 uint64_t * nsec, uint64_t * cycles)
+int gxio_mpipe_get_timestamp_aux(gxio_mpipe_context_t *context, uint64_t *sec,
+				 uint64_t *nsec, uint64_t *cycles)
 {
 	int __result;
 	struct get_timestamp_aux_param temp;
@@ -419,7 +440,7 @@ struct set_timestamp_aux_param {
 	uint64_t cycles;
 };
 
-int gxio_mpipe_set_timestamp_aux(gxio_mpipe_context_t * context, uint64_t sec,
+int gxio_mpipe_set_timestamp_aux(gxio_mpipe_context_t *context, uint64_t sec,
 				 uint64_t nsec, uint64_t cycles)
 {
 	struct set_timestamp_aux_param temp;
@@ -439,8 +460,7 @@ struct adjust_timestamp_aux_param {
 	int64_t nsec;
 };
 
-int gxio_mpipe_adjust_timestamp_aux(gxio_mpipe_context_t * context,
-				    int64_t nsec)
+int gxio_mpipe_adjust_timestamp_aux(gxio_mpipe_context_t *context, int64_t nsec)
 {
 	struct adjust_timestamp_aux_param temp;
 	struct adjust_timestamp_aux_param *params = &temp;
@@ -454,11 +474,55 @@ int gxio_mpipe_adjust_timestamp_aux(gxio_mpipe_context_t * context,
 
 EXPORT_SYMBOL(gxio_mpipe_adjust_timestamp_aux);
 
+struct config_edma_ring_blks_param {
+	unsigned int ering;
+	unsigned int max_blks;
+	unsigned int min_snf_blks;
+	unsigned int db;
+};
+
+int gxio_mpipe_config_edma_ring_blks(gxio_mpipe_context_t *context,
+				     unsigned int ering, unsigned int max_blks,
+				     unsigned int min_snf_blks, unsigned int db)
+{
+	struct config_edma_ring_blks_param temp;
+	struct config_edma_ring_blks_param *params = &temp;
+
+	params->ering = ering;
+	params->max_blks = max_blks;
+	params->min_snf_blks = min_snf_blks;
+	params->db = db;
+
+	return hv_dev_pwrite(context->fd, 0, (HV_VirtAddr) params,
+			     sizeof(*params),
+			     GXIO_MPIPE_OP_CONFIG_EDMA_RING_BLKS);
+}
+
+EXPORT_SYMBOL(gxio_mpipe_config_edma_ring_blks);
+
+struct adjust_timestamp_freq_param {
+	int32_t ppb;
+};
+
+int gxio_mpipe_adjust_timestamp_freq(gxio_mpipe_context_t *context, int32_t ppb)
+{
+	struct adjust_timestamp_freq_param temp;
+	struct adjust_timestamp_freq_param *params = &temp;
+
+	params->ppb = ppb;
+
+	return hv_dev_pwrite(context->fd, 0, (HV_VirtAddr) params,
+			     sizeof(*params),
+			     GXIO_MPIPE_OP_ADJUST_TIMESTAMP_FREQ);
+}
+
+EXPORT_SYMBOL(gxio_mpipe_adjust_timestamp_freq);
+
 struct arm_pollfd_param {
 	union iorpc_pollfd pollfd;
 };
 
-int gxio_mpipe_arm_pollfd(gxio_mpipe_context_t * context, int pollfd_cookie)
+int gxio_mpipe_arm_pollfd(gxio_mpipe_context_t *context, int pollfd_cookie)
 {
 	struct arm_pollfd_param temp;
 	struct arm_pollfd_param *params = &temp;
@@ -475,7 +539,7 @@ struct close_pollfd_param {
 	union iorpc_pollfd pollfd;
 };
 
-int gxio_mpipe_close_pollfd(gxio_mpipe_context_t * context, int pollfd_cookie)
+int gxio_mpipe_close_pollfd(gxio_mpipe_context_t *context, int pollfd_cookie)
 {
 	struct close_pollfd_param temp;
 	struct close_pollfd_param *params = &temp;
@@ -492,7 +556,7 @@ struct get_mmio_base_param {
 	HV_PTE base;
 };
 
-int gxio_mpipe_get_mmio_base(gxio_mpipe_context_t * context, HV_PTE *base)
+int gxio_mpipe_get_mmio_base(gxio_mpipe_context_t *context, HV_PTE *base)
 {
 	int __result;
 	struct get_mmio_base_param temp;
@@ -513,7 +577,7 @@ struct check_mmio_offset_param {
 	unsigned long size;
 };
 
-int gxio_mpipe_check_mmio_offset(gxio_mpipe_context_t * context,
+int gxio_mpipe_check_mmio_offset(gxio_mpipe_context_t *context,
 				 unsigned long offset, unsigned long size)
 {
 	struct check_mmio_offset_param temp;
diff --git a/arch/tile/gxio/iorpc_mpipe_info.c b/arch/tile/gxio/iorpc_mpipe_info.c
index d0254aa60cba..77019c6e9b4a 100644
--- a/arch/tile/gxio/iorpc_mpipe_info.c
+++ b/arch/tile/gxio/iorpc_mpipe_info.c
@@ -15,16 +15,33 @@
 /* This file is machine-generated; DO NOT EDIT! */
 #include "gxio/iorpc_mpipe_info.h"
 
+struct instance_aux_param {
+	_gxio_mpipe_link_name_t name;
+};
+
+int gxio_mpipe_info_instance_aux(gxio_mpipe_info_context_t *context,
+				 _gxio_mpipe_link_name_t name)
+{
+	struct instance_aux_param temp;
+	struct instance_aux_param *params = &temp;
+
+	params->name = name;
+
+	return hv_dev_pwrite(context->fd, 0, (HV_VirtAddr) params,
+			     sizeof(*params), GXIO_MPIPE_INFO_OP_INSTANCE_AUX);
+}
+
+EXPORT_SYMBOL(gxio_mpipe_info_instance_aux);
 
 struct enumerate_aux_param {
 	_gxio_mpipe_link_name_t name;
 	_gxio_mpipe_link_mac_t mac;
 };
 
-int gxio_mpipe_info_enumerate_aux(gxio_mpipe_info_context_t * context,
+int gxio_mpipe_info_enumerate_aux(gxio_mpipe_info_context_t *context,
 				  unsigned int idx,
-				  _gxio_mpipe_link_name_t * name,
-				  _gxio_mpipe_link_mac_t * mac)
+				  _gxio_mpipe_link_name_t *name,
+				  _gxio_mpipe_link_mac_t *mac)
 {
 	int __result;
 	struct enumerate_aux_param temp;
@@ -32,7 +49,7 @@ int gxio_mpipe_info_enumerate_aux(gxio_mpipe_info_context_t * context,
 
 	__result =
 	    hv_dev_pread(context->fd, 0, (HV_VirtAddr) params, sizeof(*params),
-			 (((uint64_t) idx << 32) |
+			 (((uint64_t)idx << 32) |
 			  GXIO_MPIPE_INFO_OP_ENUMERATE_AUX));
 	*name = params->name;
 	*mac = params->mac;
@@ -46,7 +63,7 @@ struct get_mmio_base_param {
 	HV_PTE base;
 };
 
-int gxio_mpipe_info_get_mmio_base(gxio_mpipe_info_context_t * context,
+int gxio_mpipe_info_get_mmio_base(gxio_mpipe_info_context_t *context,
 				  HV_PTE *base)
 {
 	int __result;
@@ -68,7 +85,7 @@ struct check_mmio_offset_param {
 	unsigned long size;
 };
 
-int gxio_mpipe_info_check_mmio_offset(gxio_mpipe_info_context_t * context,
+int gxio_mpipe_info_check_mmio_offset(gxio_mpipe_info_context_t *context,
 				      unsigned long offset, unsigned long size)
 {
 	struct check_mmio_offset_param temp;
diff --git a/arch/tile/gxio/iorpc_trio.c b/arch/tile/gxio/iorpc_trio.c
index cef4b2209cda..1d3cedb9aeb4 100644
--- a/arch/tile/gxio/iorpc_trio.c
+++ b/arch/tile/gxio/iorpc_trio.c
@@ -21,7 +21,7 @@ struct alloc_asids_param {
 	unsigned int flags;
 };
 
-int gxio_trio_alloc_asids(gxio_trio_context_t * context, unsigned int count,
+int gxio_trio_alloc_asids(gxio_trio_context_t *context, unsigned int count,
 			  unsigned int first, unsigned int flags)
 {
 	struct alloc_asids_param temp;
@@ -44,7 +44,7 @@ struct alloc_memory_maps_param {
 	unsigned int flags;
 };
 
-int gxio_trio_alloc_memory_maps(gxio_trio_context_t * context,
+int gxio_trio_alloc_memory_maps(gxio_trio_context_t *context,
 				unsigned int count, unsigned int first,
 				unsigned int flags)
 {
@@ -61,6 +61,29 @@ int gxio_trio_alloc_memory_maps(gxio_trio_context_t * context,
 
 EXPORT_SYMBOL(gxio_trio_alloc_memory_maps);
 
+struct alloc_scatter_queues_param {
+	unsigned int count;
+	unsigned int first;
+	unsigned int flags;
+};
+
+int gxio_trio_alloc_scatter_queues(gxio_trio_context_t *context,
+				   unsigned int count, unsigned int first,
+				   unsigned int flags)
+{
+	struct alloc_scatter_queues_param temp;
+	struct alloc_scatter_queues_param *params = &temp;
+
+	params->count = count;
+	params->first = first;
+	params->flags = flags;
+
+	return hv_dev_pwrite(context->fd, 0, (HV_VirtAddr) params,
+			     sizeof(*params),
+			     GXIO_TRIO_OP_ALLOC_SCATTER_QUEUES);
+}
+
+EXPORT_SYMBOL(gxio_trio_alloc_scatter_queues);
 
 struct alloc_pio_regions_param {
 	unsigned int count;
@@ -68,7 +91,7 @@ struct alloc_pio_regions_param {
 	unsigned int flags;
 };
 
-int gxio_trio_alloc_pio_regions(gxio_trio_context_t * context,
+int gxio_trio_alloc_pio_regions(gxio_trio_context_t *context,
 				unsigned int count, unsigned int first,
 				unsigned int flags)
 {
@@ -92,7 +115,7 @@ struct init_pio_region_aux_param {
 	unsigned int flags;
 };
 
-int gxio_trio_init_pio_region_aux(gxio_trio_context_t * context,
+int gxio_trio_init_pio_region_aux(gxio_trio_context_t *context,
 				  unsigned int pio_region, unsigned int mac,
 				  uint32_t bus_address_hi, unsigned int flags)
 {
@@ -122,7 +145,7 @@ struct init_memory_map_mmu_aux_param {
 	unsigned int order_mode;
 };
 
-int gxio_trio_init_memory_map_mmu_aux(gxio_trio_context_t * context,
+int gxio_trio_init_memory_map_mmu_aux(gxio_trio_context_t *context,
 				      unsigned int map, unsigned long va,
 				      uint64_t size, unsigned int asid,
 				      unsigned int mac, uint64_t bus_address,
@@ -152,7 +175,7 @@ struct get_port_property_param {
 	struct pcie_trio_ports_property trio_ports;
 };
 
-int gxio_trio_get_port_property(gxio_trio_context_t * context,
+int gxio_trio_get_port_property(gxio_trio_context_t *context,
 				struct pcie_trio_ports_property *trio_ports)
 {
 	int __result;
@@ -175,7 +198,7 @@ struct config_legacy_intr_param {
 	unsigned int intx;
 };
 
-int gxio_trio_config_legacy_intr(gxio_trio_context_t * context, int inter_x,
+int gxio_trio_config_legacy_intr(gxio_trio_context_t *context, int inter_x,
 				 int inter_y, int inter_ipi, int inter_event,
 				 unsigned int mac, unsigned int intx)
 {
@@ -204,7 +227,7 @@ struct config_msi_intr_param {
 	unsigned int asid;
 };
 
-int gxio_trio_config_msi_intr(gxio_trio_context_t * context, int inter_x,
+int gxio_trio_config_msi_intr(gxio_trio_context_t *context, int inter_x,
 			      int inter_y, int inter_ipi, int inter_event,
 			      unsigned int mac, unsigned int mem_map,
 			      uint64_t mem_map_base, uint64_t mem_map_limit,
@@ -236,7 +259,7 @@ struct set_mps_mrs_param {
 	unsigned int mac;
 };
 
-int gxio_trio_set_mps_mrs(gxio_trio_context_t * context, uint16_t mps,
+int gxio_trio_set_mps_mrs(gxio_trio_context_t *context, uint16_t mps,
 			  uint16_t mrs, unsigned int mac)
 {
 	struct set_mps_mrs_param temp;
@@ -256,7 +279,7 @@ struct force_rc_link_up_param {
 	unsigned int mac;
 };
 
-int gxio_trio_force_rc_link_up(gxio_trio_context_t * context, unsigned int mac)
+int gxio_trio_force_rc_link_up(gxio_trio_context_t *context, unsigned int mac)
 {
 	struct force_rc_link_up_param temp;
 	struct force_rc_link_up_param *params = &temp;
@@ -273,7 +296,7 @@ struct force_ep_link_up_param {
 	unsigned int mac;
 };
 
-int gxio_trio_force_ep_link_up(gxio_trio_context_t * context, unsigned int mac)
+int gxio_trio_force_ep_link_up(gxio_trio_context_t *context, unsigned int mac)
 {
 	struct force_ep_link_up_param temp;
 	struct force_ep_link_up_param *params = &temp;
@@ -290,7 +313,7 @@ struct get_mmio_base_param {
 	HV_PTE base;
 };
 
-int gxio_trio_get_mmio_base(gxio_trio_context_t * context, HV_PTE *base)
+int gxio_trio_get_mmio_base(gxio_trio_context_t *context, HV_PTE *base)
 {
 	int __result;
 	struct get_mmio_base_param temp;
@@ -311,7 +334,7 @@ struct check_mmio_offset_param {
 	unsigned long size;
 };
 
-int gxio_trio_check_mmio_offset(gxio_trio_context_t * context,
+int gxio_trio_check_mmio_offset(gxio_trio_context_t *context,
 				unsigned long offset, unsigned long size)
 {
 	struct check_mmio_offset_param temp;
diff --git a/arch/tile/gxio/iorpc_uart.c b/arch/tile/gxio/iorpc_uart.c
new file mode 100644
index 000000000000..b9a6d6193d73
--- /dev/null
+++ b/arch/tile/gxio/iorpc_uart.c
@@ -0,0 +1,77 @@
+/*
+ * Copyright 2013 Tilera Corporation. All Rights Reserved.
+ *
+ *   This program is free software; you can redistribute it and/or
+ *   modify it under the terms of the GNU General Public License
+ *   as published by the Free Software Foundation, version 2.
+ *
+ *   This program is distributed in the hope that it will be useful, but
+ *   WITHOUT ANY WARRANTY; without even the implied warranty of
+ *   MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ *   NON INFRINGEMENT.  See the GNU General Public License for
+ *   more details.
+ */
+
+/* This file is machine-generated; DO NOT EDIT! */
+#include "gxio/iorpc_uart.h"
+
+struct cfg_interrupt_param {
+	union iorpc_interrupt interrupt;
+};
+
+int gxio_uart_cfg_interrupt(gxio_uart_context_t *context, int inter_x,
+			    int inter_y, int inter_ipi, int inter_event)
+{
+	struct cfg_interrupt_param temp;
+	struct cfg_interrupt_param *params = &temp;
+
+	params->interrupt.kernel.x = inter_x;
+	params->interrupt.kernel.y = inter_y;
+	params->interrupt.kernel.ipi = inter_ipi;
+	params->interrupt.kernel.event = inter_event;
+
+	return hv_dev_pwrite(context->fd, 0, (HV_VirtAddr) params,
+			     sizeof(*params), GXIO_UART_OP_CFG_INTERRUPT);
+}
+
+EXPORT_SYMBOL(gxio_uart_cfg_interrupt);
+
+struct get_mmio_base_param {
+	HV_PTE base;
+};
+
+int gxio_uart_get_mmio_base(gxio_uart_context_t *context, HV_PTE *base)
+{
+	int __result;
+	struct get_mmio_base_param temp;
+	struct get_mmio_base_param *params = &temp;
+
+	__result =
+	    hv_dev_pread(context->fd, 0, (HV_VirtAddr) params, sizeof(*params),
+			 GXIO_UART_OP_GET_MMIO_BASE);
+	*base = params->base;
+
+	return __result;
+}
+
+EXPORT_SYMBOL(gxio_uart_get_mmio_base);
+
+struct check_mmio_offset_param {
+	unsigned long offset;
+	unsigned long size;
+};
+
+int gxio_uart_check_mmio_offset(gxio_uart_context_t *context,
+				unsigned long offset, unsigned long size)
+{
+	struct check_mmio_offset_param temp;
+	struct check_mmio_offset_param *params = &temp;
+
+	params->offset = offset;
+	params->size = size;
+
+	return hv_dev_pwrite(context->fd, 0, (HV_VirtAddr) params,
+			     sizeof(*params), GXIO_UART_OP_CHECK_MMIO_OFFSET);
+}
+
+EXPORT_SYMBOL(gxio_uart_check_mmio_offset);
diff --git a/arch/tile/gxio/iorpc_usb_host.c b/arch/tile/gxio/iorpc_usb_host.c
index cf3c3cc12204..9c820073bfc0 100644
--- a/arch/tile/gxio/iorpc_usb_host.c
+++ b/arch/tile/gxio/iorpc_usb_host.c
@@ -19,7 +19,7 @@ struct cfg_interrupt_param {
 	union iorpc_interrupt interrupt;
 };
 
-int gxio_usb_host_cfg_interrupt(gxio_usb_host_context_t * context, int inter_x,
+int gxio_usb_host_cfg_interrupt(gxio_usb_host_context_t *context, int inter_x,
 				int inter_y, int inter_ipi, int inter_event)
 {
 	struct cfg_interrupt_param temp;
@@ -41,7 +41,7 @@ struct register_client_memory_param {
 	unsigned int flags;
 };
 
-int gxio_usb_host_register_client_memory(gxio_usb_host_context_t * context,
+int gxio_usb_host_register_client_memory(gxio_usb_host_context_t *context,
 					 HV_PTE pte, unsigned int flags)
 {
 	struct register_client_memory_param temp;
@@ -61,7 +61,7 @@ struct get_mmio_base_param {
 	HV_PTE base;
 };
 
-int gxio_usb_host_get_mmio_base(gxio_usb_host_context_t * context, HV_PTE *base)
+int gxio_usb_host_get_mmio_base(gxio_usb_host_context_t *context, HV_PTE *base)
 {
 	int __result;
 	struct get_mmio_base_param temp;
@@ -82,7 +82,7 @@ struct check_mmio_offset_param {
 	unsigned long size;
 };
 
-int gxio_usb_host_check_mmio_offset(gxio_usb_host_context_t * context,
+int gxio_usb_host_check_mmio_offset(gxio_usb_host_context_t *context,
 				    unsigned long offset, unsigned long size)
 {
 	struct check_mmio_offset_param temp;
diff --git a/arch/tile/gxio/mpipe.c b/arch/tile/gxio/mpipe.c
index e71c63390acc..5301a9ffbae1 100644
--- a/arch/tile/gxio/mpipe.c
+++ b/arch/tile/gxio/mpipe.c
@@ -36,8 +36,14 @@ int gxio_mpipe_init(gxio_mpipe_context_t *context, unsigned int mpipe_index)
 	int fd;
 	int i;
 
+	if (mpipe_index >= GXIO_MPIPE_INSTANCE_MAX)
+		return -EINVAL;
+
 	snprintf(file, sizeof(file), "mpipe/%d/iorpc", mpipe_index);
 	fd = hv_dev_open((HV_VirtAddr) file, 0);
+
+	context->fd = fd;
+
 	if (fd < 0) {
 		if (fd >= GXIO_ERR_MIN && fd <= GXIO_ERR_MAX)
 			return fd;
@@ -45,8 +51,6 @@ int gxio_mpipe_init(gxio_mpipe_context_t *context, unsigned int mpipe_index)
 			return -ENODEV;
 	}
 
-	context->fd = fd;
-
 	/* Map in the MMIO space. */
 	context->mmio_cfg_base = (void __force *)
 		iorpc_ioremap(fd, HV_MPIPE_CONFIG_MMIO_OFFSET,
@@ -64,12 +68,15 @@ int gxio_mpipe_init(gxio_mpipe_context_t *context, unsigned int mpipe_index)
 	for (i = 0; i < 8; i++)
 		context->__stacks.stacks[i] = 255;
 
+	context->instance = mpipe_index;
+
 	return 0;
 
       fast_failed:
 	iounmap((void __force __iomem *)(context->mmio_cfg_base));
       cfg_failed:
 	hv_dev_close(context->fd);
+	context->fd = -1;
 	return -ENODEV;
 }
 
@@ -383,7 +390,7 @@ EXPORT_SYMBOL_GPL(gxio_mpipe_iqueue_init);
 
 int gxio_mpipe_equeue_init(gxio_mpipe_equeue_t *equeue,
 			   gxio_mpipe_context_t *context,
-			   unsigned int edma_ring_id,
+			   unsigned int ering,
 			   unsigned int channel,
 			   void *mem, unsigned int mem_size,
 			   unsigned int mem_flags)
@@ -394,7 +401,7 @@ int gxio_mpipe_equeue_init(gxio_mpipe_equeue_t *equeue,
 	/* Offset used to read number of completed commands. */
 	MPIPE_EDMA_POST_REGION_ADDR_t offset;
 
-	int result = gxio_mpipe_init_edma_ring(context, edma_ring_id, channel,
+	int result = gxio_mpipe_init_edma_ring(context, ering, channel,
 					       mem, mem_size, mem_flags);
 	if (result < 0)
 		return result;
@@ -405,7 +412,7 @@ int gxio_mpipe_equeue_init(gxio_mpipe_equeue_t *equeue,
 	offset.region =
 		MPIPE_MMIO_ADDR__REGION_VAL_EDMA -
 		MPIPE_MMIO_ADDR__REGION_VAL_IDMA;
-	offset.ring = edma_ring_id;
+	offset.ring = ering;
 
 	__gxio_dma_queue_init(&equeue->dma_queue,
 			      context->mmio_fast_base + offset.word,
@@ -413,6 +420,9 @@ int gxio_mpipe_equeue_init(gxio_mpipe_equeue_t *equeue,
 	equeue->edescs = mem;
 	equeue->mask_num_entries = num_entries - 1;
 	equeue->log2_num_entries = __builtin_ctz(num_entries);
+	equeue->context = context;
+	equeue->ering = ering;
+	equeue->channel = channel;
 
 	return 0;
 }
@@ -493,6 +503,20 @@ static gxio_mpipe_context_t *_gxio_get_link_context(void)
 	return contextp;
 }
 
+int gxio_mpipe_link_instance(const char *link_name)
+{
+	_gxio_mpipe_link_name_t name;
+	gxio_mpipe_context_t *context = _gxio_get_link_context();
+
+	if (!context)
+		return GXIO_ERR_NO_DEVICE;
+
+	strncpy(name.name, link_name, sizeof(name.name));
+	name.name[GXIO_MPIPE_LINK_NAME_LEN - 1] = '\0';
+
+	return gxio_mpipe_info_instance_aux(context, name);
+}
+
 int gxio_mpipe_link_enumerate_mac(int idx, char *link_name, uint8_t *link_mac)
 {
 	int rv;
@@ -543,3 +567,12 @@ int gxio_mpipe_link_close(gxio_mpipe_link_t *link)
 }
 
 EXPORT_SYMBOL_GPL(gxio_mpipe_link_close);
+
+int gxio_mpipe_link_set_attr(gxio_mpipe_link_t *link, uint32_t attr,
+			     int64_t val)
+{
+	return gxio_mpipe_link_set_attr_aux(link->context, link->mac, attr,
+					    val);
+}
+
+EXPORT_SYMBOL_GPL(gxio_mpipe_link_set_attr);
diff --git a/arch/tile/gxio/uart.c b/arch/tile/gxio/uart.c
new file mode 100644
index 000000000000..ba585175ef88
--- /dev/null
+++ b/arch/tile/gxio/uart.c
@@ -0,0 +1,87 @@
+/*
+ * Copyright 2013 Tilera Corporation. All Rights Reserved.
+ *
+ *   This program is free software; you can redistribute it and/or
+ *   modify it under the terms of the GNU General Public License
+ *   as published by the Free Software Foundation, version 2.
+ *
+ *   This program is distributed in the hope that it will be useful, but
+ *   WITHOUT ANY WARRANTY; without even the implied warranty of
+ *   MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ *   NON INFRINGEMENT.  See the GNU General Public License for
+ *   more details.
+ */
+
+/*
+ * Implementation of UART gxio calls.
+ */
+
+#include <linux/io.h>
+#include <linux/errno.h>
+#include <linux/module.h>
+
+#include <gxio/uart.h>
+#include <gxio/iorpc_globals.h>
+#include <gxio/iorpc_uart.h>
+#include <gxio/kiorpc.h>
+
+int gxio_uart_init(gxio_uart_context_t *context, int uart_index)
+{
+	char file[32];
+	int fd;
+
+	snprintf(file, sizeof(file), "uart/%d/iorpc", uart_index);
+	fd = hv_dev_open((HV_VirtAddr) file, 0);
+	if (fd < 0) {
+		if (fd >= GXIO_ERR_MIN && fd <= GXIO_ERR_MAX)
+			return fd;
+		else
+			return -ENODEV;
+	}
+
+	context->fd = fd;
+
+	/* Map in the MMIO space. */
+	context->mmio_base = (void __force *)
+		iorpc_ioremap(fd, HV_UART_MMIO_OFFSET, HV_UART_MMIO_SIZE);
+
+	if (context->mmio_base == NULL) {
+		hv_dev_close(context->fd);
+		context->fd = -1;
+		return -ENODEV;
+	}
+
+	return 0;
+}
+
+EXPORT_SYMBOL_GPL(gxio_uart_init);
+
+int gxio_uart_destroy(gxio_uart_context_t *context)
+{
+	iounmap((void __force __iomem *)(context->mmio_base));
+	hv_dev_close(context->fd);
+
+	context->mmio_base = NULL;
+	context->fd = -1;
+
+	return 0;
+}
+
+EXPORT_SYMBOL_GPL(gxio_uart_destroy);
+
+/* UART register write wrapper. */
+void gxio_uart_write(gxio_uart_context_t *context, uint64_t offset,
+		     uint64_t word)
+{
+	__gxio_mmio_write(context->mmio_base + offset, word);
+}
+
+EXPORT_SYMBOL_GPL(gxio_uart_write);
+
+/* UART register read wrapper. */
+uint64_t gxio_uart_read(gxio_uart_context_t *context, uint64_t offset)
+{
+	return __gxio_mmio_read(context->mmio_base + offset);
+}
+
+EXPORT_SYMBOL_GPL(gxio_uart_read);
diff --git a/arch/tile/gxio/usb_host.c b/arch/tile/gxio/usb_host.c
index 66b002f54ecc..785afad7922e 100644
--- a/arch/tile/gxio/usb_host.c
+++ b/arch/tile/gxio/usb_host.c
@@ -26,7 +26,7 @@
 #include <gxio/kiorpc.h>
 #include <gxio/usb_host.h>
 
-int gxio_usb_host_init(gxio_usb_host_context_t * context, int usb_index,
+int gxio_usb_host_init(gxio_usb_host_context_t *context, int usb_index,
 		       int is_ehci)
 {
 	char file[32];
@@ -63,7 +63,7 @@ int gxio_usb_host_init(gxio_usb_host_context_t * context, int usb_index,
 
 EXPORT_SYMBOL_GPL(gxio_usb_host_init);
 
-int gxio_usb_host_destroy(gxio_usb_host_context_t * context)
+int gxio_usb_host_destroy(gxio_usb_host_context_t *context)
 {
 	iounmap((void __force __iomem *)(context->mmio_base));
 	hv_dev_close(context->fd);
@@ -76,14 +76,14 @@ int gxio_usb_host_destroy(gxio_usb_host_context_t * context)
 
 EXPORT_SYMBOL_GPL(gxio_usb_host_destroy);
 
-void *gxio_usb_host_get_reg_start(gxio_usb_host_context_t * context)
+void *gxio_usb_host_get_reg_start(gxio_usb_host_context_t *context)
 {
 	return context->mmio_base;
 }
 
 EXPORT_SYMBOL_GPL(gxio_usb_host_get_reg_start);
 
-size_t gxio_usb_host_get_reg_len(gxio_usb_host_context_t * context)
+size_t gxio_usb_host_get_reg_len(gxio_usb_host_context_t *context)
 {
 	return HV_USB_HOST_MMIO_SIZE;
 }
diff --git a/arch/tile/include/arch/mpipe.h b/arch/tile/include/arch/mpipe.h
index 8a33912fd6cc..904538e754d8 100644
--- a/arch/tile/include/arch/mpipe.h
+++ b/arch/tile/include/arch/mpipe.h
@@ -176,7 +176,18 @@ typedef union
      */
     uint_reg_t stack_idx    : 5;
     /* Reserved. */
-    uint_reg_t __reserved_2 : 5;
+    uint_reg_t __reserved_2 : 3;
+    /*
+     * Instance ID.  For devices that support automatic buffer return between
+     * mPIPE instances, this field indicates the buffer owner.  If the INST
+     * field does not match the mPIPE's instance number when a packet is
+     * egressed, buffers with HWB set will be returned to the other mPIPE
+     * instance.  Note that not all devices support multi-mPIPE buffer
+     * return.  The MPIPE_EDMA_INFO.REMOTE_BUFF_RTN_SUPPORT bit indicates
+     * whether the INST field in the buffer descriptor is populated by iDMA
+     * hardware. This field is ignored on writes.
+     */
+    uint_reg_t inst         : 2;
     /*
      * Reads as one to indicate that this is a hardware managed buffer.
      * Ignored on writes since all buffers on a given stack are the same size.
@@ -205,7 +216,8 @@ typedef union
     uint_reg_t c            : 2;
     uint_reg_t size         : 3;
     uint_reg_t hwb          : 1;
-    uint_reg_t __reserved_2 : 5;
+    uint_reg_t inst         : 2;
+    uint_reg_t __reserved_2 : 3;
     uint_reg_t stack_idx    : 5;
     uint_reg_t __reserved_1 : 6;
     int_reg_t va           : 35;
@@ -231,9 +243,9 @@ typedef union
     /* Reserved. */
     uint_reg_t __reserved_0 : 3;
     /* eDMA ring being accessed */
-    uint_reg_t ring         : 5;
+    uint_reg_t ring         : 6;
     /* Reserved. */
-    uint_reg_t __reserved_1 : 18;
+    uint_reg_t __reserved_1 : 17;
     /*
      * This field of the address selects the region (address space) to be
      * accessed.  For the egress DMA post region, this field must be 5.
@@ -250,8 +262,8 @@ typedef union
     uint_reg_t svc_dom      : 5;
     uint_reg_t __reserved_2 : 6;
     uint_reg_t region       : 3;
-    uint_reg_t __reserved_1 : 18;
-    uint_reg_t ring         : 5;
+    uint_reg_t __reserved_1 : 17;
+    uint_reg_t ring         : 6;
     uint_reg_t __reserved_0 : 3;
 #endif
   };
diff --git a/arch/tile/include/arch/mpipe_constants.h b/arch/tile/include/arch/mpipe_constants.h
index 410a0400e055..84022ac5fe82 100644
--- a/arch/tile/include/arch/mpipe_constants.h
+++ b/arch/tile/include/arch/mpipe_constants.h
@@ -16,13 +16,13 @@
 #ifndef __ARCH_MPIPE_CONSTANTS_H__
 #define __ARCH_MPIPE_CONSTANTS_H__
 
-#define MPIPE_NUM_CLASSIFIERS 10
+#define MPIPE_NUM_CLASSIFIERS 16
 #define MPIPE_CLS_MHZ 1200
 
-#define MPIPE_NUM_EDMA_RINGS 32
+#define MPIPE_NUM_EDMA_RINGS 64
 
 #define MPIPE_NUM_SGMII_MACS 16
-#define MPIPE_NUM_XAUI_MACS 4
+#define MPIPE_NUM_XAUI_MACS 16
 #define MPIPE_NUM_LOOPBACK_CHANNELS 4
 #define MPIPE_NUM_NON_LB_CHANNELS 28
 
diff --git a/arch/tile/include/arch/mpipe_shm.h b/arch/tile/include/arch/mpipe_shm.h
index f2e9e122818d..13b3c4300e50 100644
--- a/arch/tile/include/arch/mpipe_shm.h
+++ b/arch/tile/include/arch/mpipe_shm.h
@@ -44,8 +44,14 @@ typedef union
      * descriptors toggles each time the ring tail pointer wraps.
      */
     uint_reg_t gen        : 1;
+    /**
+     * For devices with EDMA reorder support, this field allows the
+     * descriptor to select the egress FIFO.  The associated DMA ring must
+     * have ALLOW_EFIFO_SEL enabled.
+     */
+    uint_reg_t efifo_sel  : 6;
     /** Reserved.  Must be zero. */
-    uint_reg_t r0         : 7;
+    uint_reg_t r0         : 1;
     /** Checksum generation enabled for this transfer. */
     uint_reg_t csum       : 1;
     /**
@@ -110,7 +116,8 @@ typedef union
     uint_reg_t notif      : 1;
     uint_reg_t ns         : 1;
     uint_reg_t csum       : 1;
-    uint_reg_t r0         : 7;
+    uint_reg_t r0         : 1;
+    uint_reg_t efifo_sel  : 6;
     uint_reg_t gen        : 1;
 #endif
 
@@ -126,14 +133,16 @@ typedef union
     /** Reserved. */
     uint_reg_t __reserved_1 : 3;
     /**
-     * Instance ID.  For devices that support more than one mPIPE instance,
-     * this field indicates the buffer owner.  If the INST field does not
-     * match the mPIPE's instance number when a packet is egressed, buffers
-     * with HWB set will be returned to the other mPIPE instance.
+     * Instance ID.  For devices that support automatic buffer return between
+     * mPIPE instances, this field indicates the buffer owner.  If the INST
+     * field does not match the mPIPE's instance number when a packet is
+     * egressed, buffers with HWB set will be returned to the other mPIPE
+     * instance.  Note that not all devices support multi-mPIPE buffer
+     * return.  The MPIPE_EDMA_INFO.REMOTE_BUFF_RTN_SUPPORT bit indicates
+     * whether the INST field in the buffer descriptor is populated by iDMA
+     * hardware.
      */
-    uint_reg_t inst         : 1;
-    /** Reserved. */
-    uint_reg_t __reserved_2 : 1;
+    uint_reg_t inst         : 2;
     /**
      * Always set to one by hardware in iDMA packet descriptors.  For eDMA,
      * indicates whether the buffer will be released to the buffer stack
@@ -166,8 +175,7 @@ typedef union
     uint_reg_t c            : 2;
     uint_reg_t size         : 3;
     uint_reg_t hwb          : 1;
-    uint_reg_t __reserved_2 : 1;
-    uint_reg_t inst         : 1;
+    uint_reg_t inst         : 2;
     uint_reg_t __reserved_1 : 3;
     uint_reg_t stack_idx    : 5;
     uint_reg_t __reserved_0 : 6;
@@ -408,7 +416,10 @@ typedef union
     /**
      * Sequence number applied when packet is distributed.   Classifier
      * selects which sequence number is to be applied by writing the 13-bit
-     * SQN-selector into this field.
+     * SQN-selector into this field.  For devices that support EXT_SQN (as
+     * indicated in IDMA_INFO.EXT_SQN_SUPPORT), the GP_SQN can be extended to
+     * 32-bits via the IDMA_CTL.EXT_SQN register.  In this case the
+     * PACKET_SQN will be reduced to 32 bits.
      */
     uint_reg_t gp_sqn     : 16;
     /**
@@ -451,14 +462,16 @@ typedef union
     /** Reserved. */
     uint_reg_t __reserved_5 : 3;
     /**
-     * Instance ID.  For devices that support more than one mPIPE instance,
-     * this field indicates the buffer owner.  If the INST field does not
-     * match the mPIPE's instance number when a packet is egressed, buffers
-     * with HWB set will be returned to the other mPIPE instance.
+     * Instance ID.  For devices that support automatic buffer return between
+     * mPIPE instances, this field indicates the buffer owner.  If the INST
+     * field does not match the mPIPE's instance number when a packet is
+     * egressed, buffers with HWB set will be returned to the other mPIPE
+     * instance.  Note that not all devices support multi-mPIPE buffer
+     * return.  The MPIPE_EDMA_INFO.REMOTE_BUFF_RTN_SUPPORT bit indicates
+     * whether the INST field in the buffer descriptor is populated by iDMA
+     * hardware.
      */
-    uint_reg_t inst         : 1;
-    /** Reserved. */
-    uint_reg_t __reserved_6 : 1;
+    uint_reg_t inst         : 2;
     /**
      * Always set to one by hardware in iDMA packet descriptors.  For eDMA,
      * indicates whether the buffer will be released to the buffer stack
@@ -491,8 +504,7 @@ typedef union
     uint_reg_t c            : 2;
     uint_reg_t size         : 3;
     uint_reg_t hwb          : 1;
-    uint_reg_t __reserved_6 : 1;
-    uint_reg_t inst         : 1;
+    uint_reg_t inst         : 2;
     uint_reg_t __reserved_5 : 3;
     uint_reg_t stack_idx    : 5;
     uint_reg_t __reserved_4 : 6;
diff --git a/arch/tile/include/arch/trio.h b/arch/tile/include/arch/trio.h
index d3000a871a21..c0ddedcae085 100644
--- a/arch/tile/include/arch/trio.h
+++ b/arch/tile/include/arch/trio.h
@@ -23,6 +23,45 @@
 #ifndef __ASSEMBLER__
 
 /*
+ * Map SQ Doorbell Format.
+ * This describes the format of the write-only doorbell register that exists
+ * in the last 8-bytes of the MAP_SQ_BASE/LIM range.  This register is only
+ * writable from PCIe space.  Writes to this register will not be written to
+ * Tile memory space and thus no IO VA translation is required if the last
+ * page of the BASE/LIM range is not otherwise written.
+ */
+
+__extension__
+typedef union
+{
+  struct
+  {
+#ifndef __BIG_ENDIAN__
+    /*
+     * When written with a 1, the associated MAP_SQ region's doorbell
+     * interrupt will be triggered once all previous writes are visible to
+     * Tile software.
+     */
+    uint_reg_t doorbell   : 1;
+    /*
+     * When written with a 1, the descriptor at the head of the associated
+     * MAP_SQ's FIFO will be dequeued.
+     */
+    uint_reg_t pop        : 1;
+    /* Reserved. */
+    uint_reg_t __reserved : 62;
+#else   /* __BIG_ENDIAN__ */
+    uint_reg_t __reserved : 62;
+    uint_reg_t pop        : 1;
+    uint_reg_t doorbell   : 1;
+#endif
+  };
+
+  uint_reg_t word;
+} TRIO_MAP_SQ_DOORBELL_FMT_t;
+
+
+/*
  * Tile PIO Region Configuration - CFG Address Format.
  * This register describes the address format for PIO accesses when the
  * associated region is setup with TYPE=CFG.
diff --git a/arch/tile/include/arch/trio_constants.h b/arch/tile/include/arch/trio_constants.h
index 628b045436b8..85647e91a458 100644
--- a/arch/tile/include/arch/trio_constants.h
+++ b/arch/tile/include/arch/trio_constants.h
@@ -16,21 +16,21 @@
 #ifndef __ARCH_TRIO_CONSTANTS_H__
 #define __ARCH_TRIO_CONSTANTS_H__
 
-#define TRIO_NUM_ASIDS 16
+#define TRIO_NUM_ASIDS 32
 #define TRIO_NUM_TLBS_PER_ASID 16
 
 #define TRIO_NUM_TPIO_REGIONS 8
 #define TRIO_LOG2_NUM_TPIO_REGIONS 3
 
-#define TRIO_NUM_MAP_MEM_REGIONS 16
-#define TRIO_LOG2_NUM_MAP_MEM_REGIONS 4
+#define TRIO_NUM_MAP_MEM_REGIONS 32
+#define TRIO_LOG2_NUM_MAP_MEM_REGIONS 5
 #define TRIO_NUM_MAP_SQ_REGIONS 8
 #define TRIO_LOG2_NUM_MAP_SQ_REGIONS 3
 
 #define TRIO_LOG2_NUM_SQ_FIFO_ENTRIES 6
 
-#define TRIO_NUM_PUSH_DMA_RINGS 32
+#define TRIO_NUM_PUSH_DMA_RINGS 64
 
-#define TRIO_NUM_PULL_DMA_RINGS 32
+#define TRIO_NUM_PULL_DMA_RINGS 64
 
 #endif /* __ARCH_TRIO_CONSTANTS_H__ */
diff --git a/arch/tile/include/arch/uart.h b/arch/tile/include/arch/uart.h
new file mode 100644
index 000000000000..07966970adad
--- /dev/null
+++ b/arch/tile/include/arch/uart.h
@@ -0,0 +1,300 @@
+/*
+ * Copyright 2013 Tilera Corporation. All Rights Reserved.
+ *
+ *   This program is free software; you can redistribute it and/or
+ *   modify it under the terms of the GNU General Public License
+ *   as published by the Free Software Foundation, version 2.
+ *
+ *   This program is distributed in the hope that it will be useful, but
+ *   WITHOUT ANY WARRANTY; without even the implied warranty of
+ *   MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ *   NON INFRINGEMENT.  See the GNU General Public License for
+ *   more details.
+ */
+
+/* Machine-generated file; do not edit. */
+
+#ifndef __ARCH_UART_H__
+#define __ARCH_UART_H__
+
+#include <arch/abi.h>
+#include <arch/uart_def.h>
+
+#ifndef __ASSEMBLER__
+
+/* Divisor. */
+
+__extension__
+typedef union
+{
+  struct
+  {
+#ifndef __BIG_ENDIAN__
+    /*
+     * Baud Rate Divisor.  Desired_baud_rate = REF_CLK frequency / (baud *
+     * 16).
+     *                       Note: REF_CLK is always 125 MHz, the default
+     * divisor = 68, baud rate = 125M/(68*16) = 115200 baud.
+     */
+    uint_reg_t divisor    : 12;
+    /* Reserved. */
+    uint_reg_t __reserved : 52;
+#else   /* __BIG_ENDIAN__ */
+    uint_reg_t __reserved : 52;
+    uint_reg_t divisor    : 12;
+#endif
+  };
+
+  uint_reg_t word;
+} UART_DIVISOR_t;
+
+/* FIFO Count. */
+
+__extension__
+typedef union
+{
+  struct
+  {
+#ifndef __BIG_ENDIAN__
+    /*
+     * n: n active entries in the receive FIFO (max is 2**8). Each entry has
+     * 8 bits.
+     * 0: no active entry in the receive FIFO (that is empty).
+     */
+    uint_reg_t rfifo_count  : 9;
+    /* Reserved. */
+    uint_reg_t __reserved_0 : 7;
+    /*
+     * n: n active entries in the transmit FIFO (max is 2**8). Each entry has
+     * 8 bits.
+     * 0: no active entry in the transmit FIFO (that is empty).
+     */
+    uint_reg_t tfifo_count  : 9;
+    /* Reserved. */
+    uint_reg_t __reserved_1 : 7;
+    /*
+     * n: n active entries in the write FIFO (max is 2**2). Each entry has 8
+     * bits.
+     * 0: no active entry in the write FIFO (that is empty).
+     */
+    uint_reg_t wfifo_count  : 3;
+    /* Reserved. */
+    uint_reg_t __reserved_2 : 29;
+#else   /* __BIG_ENDIAN__ */
+    uint_reg_t __reserved_2 : 29;
+    uint_reg_t wfifo_count  : 3;
+    uint_reg_t __reserved_1 : 7;
+    uint_reg_t tfifo_count  : 9;
+    uint_reg_t __reserved_0 : 7;
+    uint_reg_t rfifo_count  : 9;
+#endif
+  };
+
+  uint_reg_t word;
+} UART_FIFO_COUNT_t;
+
+/* FLAG. */
+
+__extension__
+typedef union
+{
+  struct
+  {
+#ifndef __BIG_ENDIAN__
+    /* Reserved. */
+    uint_reg_t __reserved_0 : 1;
+    /* 1: receive FIFO is empty */
+    uint_reg_t rfifo_empty  : 1;
+    /* 1: write FIFO is empty. */
+    uint_reg_t wfifo_empty  : 1;
+    /* 1: transmit FIFO is empty. */
+    uint_reg_t tfifo_empty  : 1;
+    /* 1: receive FIFO is full. */
+    uint_reg_t rfifo_full   : 1;
+    /* 1: write FIFO is full. */
+    uint_reg_t wfifo_full   : 1;
+    /* 1: transmit FIFO is full. */
+    uint_reg_t tfifo_full   : 1;
+    /* Reserved. */
+    uint_reg_t __reserved_1 : 57;
+#else   /* __BIG_ENDIAN__ */
+    uint_reg_t __reserved_1 : 57;
+    uint_reg_t tfifo_full   : 1;
+    uint_reg_t wfifo_full   : 1;
+    uint_reg_t rfifo_full   : 1;
+    uint_reg_t tfifo_empty  : 1;
+    uint_reg_t wfifo_empty  : 1;
+    uint_reg_t rfifo_empty  : 1;
+    uint_reg_t __reserved_0 : 1;
+#endif
+  };
+
+  uint_reg_t word;
+} UART_FLAG_t;
+
+/*
+ * Interrupt Vector Mask.
+ * Each bit in this register corresponds to a specific interrupt. When set,
+ * the associated interrupt will not be dispatched.
+ */
+
+__extension__
+typedef union
+{
+  struct
+  {
+#ifndef __BIG_ENDIAN__
+    /* Read data FIFO read and no data available */
+    uint_reg_t rdat_err       : 1;
+    /* Write FIFO was written but it was full */
+    uint_reg_t wdat_err       : 1;
+    /* Stop bit not found when current data was received */
+    uint_reg_t frame_err      : 1;
+    /* Parity error was detected when current data was received */
+    uint_reg_t parity_err     : 1;
+    /* Data was received but the receive FIFO was full */
+    uint_reg_t rfifo_overflow : 1;
+    /*
+     * An almost full event is reached when data is to be written to the
+     * receive FIFO, and the receive FIFO has more than or equal to
+     * BUFFER_THRESHOLD.RFIFO_AFULL bytes.
+     */
+    uint_reg_t rfifo_afull    : 1;
+    /* Reserved. */
+    uint_reg_t __reserved_0   : 1;
+    /* An entry in the transmit FIFO was popped */
+    uint_reg_t tfifo_re       : 1;
+    /* An entry has been pushed into the receive FIFO */
+    uint_reg_t rfifo_we       : 1;
+    /* An entry of the write FIFO has been popped */
+    uint_reg_t wfifo_re       : 1;
+    /* Rshim read receive FIFO in protocol mode */
+    uint_reg_t rfifo_err      : 1;
+    /*
+     * An almost empty event is reached when data is to be read from the
+     * transmit FIFO, and the transmit FIFO has less than or equal to
+     * BUFFER_THRESHOLD.TFIFO_AEMPTY bytes.
+     */
+    uint_reg_t tfifo_aempty   : 1;
+    /* Reserved. */
+    uint_reg_t __reserved_1   : 52;
+#else   /* __BIG_ENDIAN__ */
+    uint_reg_t __reserved_1   : 52;
+    uint_reg_t tfifo_aempty   : 1;
+    uint_reg_t rfifo_err      : 1;
+    uint_reg_t wfifo_re       : 1;
+    uint_reg_t rfifo_we       : 1;
+    uint_reg_t tfifo_re       : 1;
+    uint_reg_t __reserved_0   : 1;
+    uint_reg_t rfifo_afull    : 1;
+    uint_reg_t rfifo_overflow : 1;
+    uint_reg_t parity_err     : 1;
+    uint_reg_t frame_err      : 1;
+    uint_reg_t wdat_err       : 1;
+    uint_reg_t rdat_err       : 1;
+#endif
+  };
+
+  uint_reg_t word;
+} UART_INTERRUPT_MASK_t;
+
+/*
+ * Interrupt vector, write-one-to-clear.
+ * Each bit in this register corresponds to a specific interrupt. Hardware
+ * sets the bit when the associated condition has occurred. Writing a 1
+ * clears the status bit.
+ */
+
+__extension__
+typedef union
+{
+  struct
+  {
+#ifndef __BIG_ENDIAN__
+    /* Read data FIFO read and no data available */
+    uint_reg_t rdat_err       : 1;
+    /* Write FIFO was written but it was full */
+    uint_reg_t wdat_err       : 1;
+    /* Stop bit not found when current data was received */
+    uint_reg_t frame_err      : 1;
+    /* Parity error was detected when current data was received */
+    uint_reg_t parity_err     : 1;
+    /* Data was received but the receive FIFO was full */
+    uint_reg_t rfifo_overflow : 1;
+    /*
+     * Data was received and the receive FIFO is now almost full (more than
+     * BUFFER_THRESHOLD.RFIFO_AFULL bytes in it)
+     */
+    uint_reg_t rfifo_afull    : 1;
+    /* Reserved. */
+    uint_reg_t __reserved_0   : 1;
+    /* An entry in the transmit FIFO was popped */
+    uint_reg_t tfifo_re       : 1;
+    /* An entry has been pushed into the receive FIFO */
+    uint_reg_t rfifo_we       : 1;
+    /* An entry of the write FIFO has been popped */
+    uint_reg_t wfifo_re       : 1;
+    /* Rshim read receive FIFO in protocol mode */
+    uint_reg_t rfifo_err      : 1;
+    /*
+     * Data was read from the transmit FIFO and now it is almost empty (less
+     * than or equal to BUFFER_THRESHOLD.TFIFO_AEMPTY bytes in it).
+     */
+    uint_reg_t tfifo_aempty   : 1;
+    /* Reserved. */
+    uint_reg_t __reserved_1   : 52;
+#else   /* __BIG_ENDIAN__ */
+    uint_reg_t __reserved_1   : 52;
+    uint_reg_t tfifo_aempty   : 1;
+    uint_reg_t rfifo_err      : 1;
+    uint_reg_t wfifo_re       : 1;
+    uint_reg_t rfifo_we       : 1;
+    uint_reg_t tfifo_re       : 1;
+    uint_reg_t __reserved_0   : 1;
+    uint_reg_t rfifo_afull    : 1;
+    uint_reg_t rfifo_overflow : 1;
+    uint_reg_t parity_err     : 1;
+    uint_reg_t frame_err      : 1;
+    uint_reg_t wdat_err       : 1;
+    uint_reg_t rdat_err       : 1;
+#endif
+  };
+
+  uint_reg_t word;
+} UART_INTERRUPT_STATUS_t;
+
+/* Type. */
+
+__extension__
+typedef union
+{
+  struct
+  {
+#ifndef __BIG_ENDIAN__
+    /* Number of stop bits, rx and tx */
+    uint_reg_t sbits        : 1;
+    /* Reserved. */
+    uint_reg_t __reserved_0 : 1;
+    /* Data word size, rx and tx */
+    uint_reg_t dbits        : 1;
+    /* Reserved. */
+    uint_reg_t __reserved_1 : 1;
+    /* Parity selection, rx and tx */
+    uint_reg_t ptype        : 3;
+    /* Reserved. */
+    uint_reg_t __reserved_2 : 57;
+#else   /* __BIG_ENDIAN__ */
+    uint_reg_t __reserved_2 : 57;
+    uint_reg_t ptype        : 3;
+    uint_reg_t __reserved_1 : 1;
+    uint_reg_t dbits        : 1;
+    uint_reg_t __reserved_0 : 1;
+    uint_reg_t sbits        : 1;
+#endif
+  };
+
+  uint_reg_t word;
+} UART_TYPE_t;
+#endif /* !defined(__ASSEMBLER__) */
+
+#endif /* !defined(__ARCH_UART_H__) */
diff --git a/arch/tile/include/arch/uart_def.h b/arch/tile/include/arch/uart_def.h
new file mode 100644
index 000000000000..42bcaf535379
--- /dev/null
+++ b/arch/tile/include/arch/uart_def.h
@@ -0,0 +1,120 @@
+/*
+ * Copyright 2013 Tilera Corporation. All Rights Reserved.
+ *
+ *   This program is free software; you can redistribute it and/or
+ *   modify it under the terms of the GNU General Public License
+ *   as published by the Free Software Foundation, version 2.
+ *
+ *   This program is distributed in the hope that it will be useful, but
+ *   WITHOUT ANY WARRANTY; without even the implied warranty of
+ *   MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ *   NON INFRINGEMENT.  See the GNU General Public License for
+ *   more details.
+ */
+
+/* Machine-generated file; do not edit. */
+
+#ifndef __ARCH_UART_DEF_H__
+#define __ARCH_UART_DEF_H__
+#define UART_DIVISOR 0x0158
+#define UART_FIFO_COUNT 0x0110
+#define UART_FLAG 0x0108
+#define UART_INTERRUPT_MASK 0x0208
+#define UART_INTERRUPT_MASK__RDAT_ERR_SHIFT 0
+#define UART_INTERRUPT_MASK__RDAT_ERR_WIDTH 1
+#define UART_INTERRUPT_MASK__RDAT_ERR_RESET_VAL 1
+#define UART_INTERRUPT_MASK__RDAT_ERR_RMASK 0x1
+#define UART_INTERRUPT_MASK__RDAT_ERR_MASK  0x1
+#define UART_INTERRUPT_MASK__RDAT_ERR_FIELD 0,0
+#define UART_INTERRUPT_MASK__WDAT_ERR_SHIFT 1
+#define UART_INTERRUPT_MASK__WDAT_ERR_WIDTH 1
+#define UART_INTERRUPT_MASK__WDAT_ERR_RESET_VAL 1
+#define UART_INTERRUPT_MASK__WDAT_ERR_RMASK 0x1
+#define UART_INTERRUPT_MASK__WDAT_ERR_MASK  0x2
+#define UART_INTERRUPT_MASK__WDAT_ERR_FIELD 1,1
+#define UART_INTERRUPT_MASK__FRAME_ERR_SHIFT 2
+#define UART_INTERRUPT_MASK__FRAME_ERR_WIDTH 1
+#define UART_INTERRUPT_MASK__FRAME_ERR_RESET_VAL 1
+#define UART_INTERRUPT_MASK__FRAME_ERR_RMASK 0x1
+#define UART_INTERRUPT_MASK__FRAME_ERR_MASK  0x4
+#define UART_INTERRUPT_MASK__FRAME_ERR_FIELD 2,2
+#define UART_INTERRUPT_MASK__PARITY_ERR_SHIFT 3
+#define UART_INTERRUPT_MASK__PARITY_ERR_WIDTH 1
+#define UART_INTERRUPT_MASK__PARITY_ERR_RESET_VAL 1
+#define UART_INTERRUPT_MASK__PARITY_ERR_RMASK 0x1
+#define UART_INTERRUPT_MASK__PARITY_ERR_MASK  0x8
+#define UART_INTERRUPT_MASK__PARITY_ERR_FIELD 3,3
+#define UART_INTERRUPT_MASK__RFIFO_OVERFLOW_SHIFT 4
+#define UART_INTERRUPT_MASK__RFIFO_OVERFLOW_WIDTH 1
+#define UART_INTERRUPT_MASK__RFIFO_OVERFLOW_RESET_VAL 1
+#define UART_INTERRUPT_MASK__RFIFO_OVERFLOW_RMASK 0x1
+#define UART_INTERRUPT_MASK__RFIFO_OVERFLOW_MASK  0x10
+#define UART_INTERRUPT_MASK__RFIFO_OVERFLOW_FIELD 4,4
+#define UART_INTERRUPT_MASK__RFIFO_AFULL_SHIFT 5
+#define UART_INTERRUPT_MASK__RFIFO_AFULL_WIDTH 1
+#define UART_INTERRUPT_MASK__RFIFO_AFULL_RESET_VAL 1
+#define UART_INTERRUPT_MASK__RFIFO_AFULL_RMASK 0x1
+#define UART_INTERRUPT_MASK__RFIFO_AFULL_MASK  0x20
+#define UART_INTERRUPT_MASK__RFIFO_AFULL_FIELD 5,5
+#define UART_INTERRUPT_MASK__TFIFO_RE_SHIFT 7
+#define UART_INTERRUPT_MASK__TFIFO_RE_WIDTH 1
+#define UART_INTERRUPT_MASK__TFIFO_RE_RESET_VAL 1
+#define UART_INTERRUPT_MASK__TFIFO_RE_RMASK 0x1
+#define UART_INTERRUPT_MASK__TFIFO_RE_MASK  0x80
+#define UART_INTERRUPT_MASK__TFIFO_RE_FIELD 7,7
+#define UART_INTERRUPT_MASK__RFIFO_WE_SHIFT 8
+#define UART_INTERRUPT_MASK__RFIFO_WE_WIDTH 1
+#define UART_INTERRUPT_MASK__RFIFO_WE_RESET_VAL 1
+#define UART_INTERRUPT_MASK__RFIFO_WE_RMASK 0x1
+#define UART_INTERRUPT_MASK__RFIFO_WE_MASK  0x100
+#define UART_INTERRUPT_MASK__RFIFO_WE_FIELD 8,8
+#define UART_INTERRUPT_MASK__WFIFO_RE_SHIFT 9
+#define UART_INTERRUPT_MASK__WFIFO_RE_WIDTH 1
+#define UART_INTERRUPT_MASK__WFIFO_RE_RESET_VAL 1
+#define UART_INTERRUPT_MASK__WFIFO_RE_RMASK 0x1
+#define UART_INTERRUPT_MASK__WFIFO_RE_MASK  0x200
+#define UART_INTERRUPT_MASK__WFIFO_RE_FIELD 9,9
+#define UART_INTERRUPT_MASK__RFIFO_ERR_SHIFT 10
+#define UART_INTERRUPT_MASK__RFIFO_ERR_WIDTH 1
+#define UART_INTERRUPT_MASK__RFIFO_ERR_RESET_VAL 1
+#define UART_INTERRUPT_MASK__RFIFO_ERR_RMASK 0x1
+#define UART_INTERRUPT_MASK__RFIFO_ERR_MASK  0x400
+#define UART_INTERRUPT_MASK__RFIFO_ERR_FIELD 10,10
+#define UART_INTERRUPT_MASK__TFIFO_AEMPTY_SHIFT 11
+#define UART_INTERRUPT_MASK__TFIFO_AEMPTY_WIDTH 1
+#define UART_INTERRUPT_MASK__TFIFO_AEMPTY_RESET_VAL 1
+#define UART_INTERRUPT_MASK__TFIFO_AEMPTY_RMASK 0x1
+#define UART_INTERRUPT_MASK__TFIFO_AEMPTY_MASK  0x800
+#define UART_INTERRUPT_MASK__TFIFO_AEMPTY_FIELD 11,11
+#define UART_INTERRUPT_STATUS 0x0200
+#define UART_RECEIVE_DATA 0x0148
+#define UART_TRANSMIT_DATA 0x0140
+#define UART_TYPE 0x0160
+#define UART_TYPE__SBITS_SHIFT 0
+#define UART_TYPE__SBITS_WIDTH 1
+#define UART_TYPE__SBITS_RESET_VAL 1
+#define UART_TYPE__SBITS_RMASK 0x1
+#define UART_TYPE__SBITS_MASK  0x1
+#define UART_TYPE__SBITS_FIELD 0,0
+#define UART_TYPE__SBITS_VAL_ONE_SBITS 0x0
+#define UART_TYPE__SBITS_VAL_TWO_SBITS 0x1
+#define UART_TYPE__DBITS_SHIFT 2
+#define UART_TYPE__DBITS_WIDTH 1
+#define UART_TYPE__DBITS_RESET_VAL 0
+#define UART_TYPE__DBITS_RMASK 0x1
+#define UART_TYPE__DBITS_MASK  0x4
+#define UART_TYPE__DBITS_FIELD 2,2
+#define UART_TYPE__DBITS_VAL_EIGHT_DBITS 0x0
+#define UART_TYPE__DBITS_VAL_SEVEN_DBITS 0x1
+#define UART_TYPE__PTYPE_SHIFT 4
+#define UART_TYPE__PTYPE_WIDTH 3
+#define UART_TYPE__PTYPE_RESET_VAL 3
+#define UART_TYPE__PTYPE_RMASK 0x7
+#define UART_TYPE__PTYPE_MASK  0x70
+#define UART_TYPE__PTYPE_FIELD 4,6
+#define UART_TYPE__PTYPE_VAL_NONE 0x0
+#define UART_TYPE__PTYPE_VAL_MARK 0x1
+#define UART_TYPE__PTYPE_VAL_SPACE 0x2
+#define UART_TYPE__PTYPE_VAL_EVEN 0x3
+#define UART_TYPE__PTYPE_VAL_ODD 0x4
+#endif /* !defined(__ARCH_UART_DEF_H__) */
diff --git a/arch/tile/include/asm/Kbuild b/arch/tile/include/asm/Kbuild
index b17b9b8e53cd..664d6ad23f80 100644
--- a/arch/tile/include/asm/Kbuild
+++ b/arch/tile/include/asm/Kbuild
@@ -11,12 +11,13 @@ generic-y += errno.h
 generic-y += exec.h
 generic-y += fb.h
 generic-y += fcntl.h
+generic-y += hw_irq.h
 generic-y += ioctl.h
 generic-y += ioctls.h
 generic-y += ipcbuf.h
 generic-y += irq_regs.h
-generic-y += kdebug.h
 generic-y += local.h
+generic-y += local64.h
 generic-y += msgbuf.h
 generic-y += mutex.h
 generic-y += param.h
diff --git a/arch/tile/include/asm/atomic.h b/arch/tile/include/asm/atomic.h
index e71387ab20ca..709798460763 100644
--- a/arch/tile/include/asm/atomic.h
+++ b/arch/tile/include/asm/atomic.h
@@ -114,6 +114,32 @@ static inline int atomic_read(const atomic_t *v)
 #define atomic_inc_and_test(v)		(atomic_inc_return(v) == 0)
 
 /**
+ * atomic_xchg - atomically exchange contents of memory with a new value
+ * @v: pointer of type atomic_t
+ * @i: integer value to store in memory
+ *
+ * Atomically sets @v to @i and returns old @v
+ */
+static inline int atomic_xchg(atomic_t *v, int n)
+{
+	return xchg(&v->counter, n);
+}
+
+/**
+ * atomic_cmpxchg - atomically exchange contents of memory if it matches
+ * @v: pointer of type atomic_t
+ * @o: old value that memory should have
+ * @n: new value to write to memory if it matches
+ *
+ * Atomically checks if @v holds @o and replaces it with @n if so.
+ * Returns the old value at @v.
+ */
+static inline int atomic_cmpxchg(atomic_t *v, int o, int n)
+{
+	return cmpxchg(&v->counter, o, n);
+}
+
+/**
  * atomic_add_negative - add and test if negative
  * @v: pointer of type atomic_t
  * @i: integer value to add
@@ -133,6 +159,33 @@ static inline int atomic_read(const atomic_t *v)
 
 #ifndef __ASSEMBLY__
 
+/**
+ * atomic64_xchg - atomically exchange contents of memory with a new value
+ * @v: pointer of type atomic64_t
+ * @i: integer value to store in memory
+ *
+ * Atomically sets @v to @i and returns old @v
+ */
+static inline long long atomic64_xchg(atomic64_t *v, long long n)
+{
+	return xchg64(&v->counter, n);
+}
+
+/**
+ * atomic64_cmpxchg - atomically exchange contents of memory if it matches
+ * @v: pointer of type atomic64_t
+ * @o: old value that memory should have
+ * @n: new value to write to memory if it matches
+ *
+ * Atomically checks if @v holds @o and replaces it with @n if so.
+ * Returns the old value at @v.
+ */
+static inline long long atomic64_cmpxchg(atomic64_t *v, long long o,
+					long long n)
+{
+	return cmpxchg64(&v->counter, o, n);
+}
+
 static inline long long atomic64_dec_if_positive(atomic64_t *v)
 {
 	long long c, old, dec;
diff --git a/arch/tile/include/asm/atomic_32.h b/arch/tile/include/asm/atomic_32.h
index e7fb5cfb9597..1ad4a1f7d42b 100644
--- a/arch/tile/include/asm/atomic_32.h
+++ b/arch/tile/include/asm/atomic_32.h
@@ -22,40 +22,6 @@
 
 #ifndef __ASSEMBLY__
 
-/* Tile-specific routines to support <linux/atomic.h>. */
-int _atomic_xchg(atomic_t *v, int n);
-int _atomic_xchg_add(atomic_t *v, int i);
-int _atomic_xchg_add_unless(atomic_t *v, int a, int u);
-int _atomic_cmpxchg(atomic_t *v, int o, int n);
-
-/**
- * atomic_xchg - atomically exchange contents of memory with a new value
- * @v: pointer of type atomic_t
- * @i: integer value to store in memory
- *
- * Atomically sets @v to @i and returns old @v
- */
-static inline int atomic_xchg(atomic_t *v, int n)
-{
-	smp_mb();  /* barrier for proper semantics */
-	return _atomic_xchg(v, n);
-}
-
-/**
- * atomic_cmpxchg - atomically exchange contents of memory if it matches
- * @v: pointer of type atomic_t
- * @o: old value that memory should have
- * @n: new value to write to memory if it matches
- *
- * Atomically checks if @v holds @o and replaces it with @n if so.
- * Returns the old value at @v.
- */
-static inline int atomic_cmpxchg(atomic_t *v, int o, int n)
-{
-	smp_mb();  /* barrier for proper semantics */
-	return _atomic_cmpxchg(v, o, n);
-}
-
 /**
  * atomic_add - add integer to atomic variable
  * @i: integer value to add
@@ -65,7 +31,7 @@ static inline int atomic_cmpxchg(atomic_t *v, int o, int n)
  */
 static inline void atomic_add(int i, atomic_t *v)
 {
-	_atomic_xchg_add(v, i);
+	_atomic_xchg_add(&v->counter, i);
 }
 
 /**
@@ -78,7 +44,7 @@ static inline void atomic_add(int i, atomic_t *v)
 static inline int atomic_add_return(int i, atomic_t *v)
 {
 	smp_mb();  /* barrier for proper semantics */
-	return _atomic_xchg_add(v, i) + i;
+	return _atomic_xchg_add(&v->counter, i) + i;
 }
 
 /**
@@ -93,7 +59,7 @@ static inline int atomic_add_return(int i, atomic_t *v)
 static inline int __atomic_add_unless(atomic_t *v, int a, int u)
 {
 	smp_mb();  /* barrier for proper semantics */
-	return _atomic_xchg_add_unless(v, a, u);
+	return _atomic_xchg_add_unless(&v->counter, a, u);
 }
 
 /**
@@ -108,64 +74,31 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u)
  */
 static inline void atomic_set(atomic_t *v, int n)
 {
-	_atomic_xchg(v, n);
+	_atomic_xchg(&v->counter, n);
 }
 
 /* A 64bit atomic type */
 
 typedef struct {
-	u64 __aligned(8) counter;
+	long long counter;
 } atomic64_t;
 
 #define ATOMIC64_INIT(val) { (val) }
 
-u64 _atomic64_xchg(atomic64_t *v, u64 n);
-u64 _atomic64_xchg_add(atomic64_t *v, u64 i);
-u64 _atomic64_xchg_add_unless(atomic64_t *v, u64 a, u64 u);
-u64 _atomic64_cmpxchg(atomic64_t *v, u64 o, u64 n);
-
 /**
  * atomic64_read - read atomic variable
  * @v: pointer of type atomic64_t
  *
  * Atomically reads the value of @v.
  */
-static inline u64 atomic64_read(const atomic64_t *v)
+static inline long long atomic64_read(const atomic64_t *v)
 {
 	/*
 	 * Requires an atomic op to read both 32-bit parts consistently.
 	 * Casting away const is safe since the atomic support routines
 	 * do not write to memory if the value has not been modified.
 	 */
-	return _atomic64_xchg_add((atomic64_t *)v, 0);
-}
-
-/**
- * atomic64_xchg - atomically exchange contents of memory with a new value
- * @v: pointer of type atomic64_t
- * @i: integer value to store in memory
- *
- * Atomically sets @v to @i and returns old @v
- */
-static inline u64 atomic64_xchg(atomic64_t *v, u64 n)
-{
-	smp_mb();  /* barrier for proper semantics */
-	return _atomic64_xchg(v, n);
-}
-
-/**
- * atomic64_cmpxchg - atomically exchange contents of memory if it matches
- * @v: pointer of type atomic64_t
- * @o: old value that memory should have
- * @n: new value to write to memory if it matches
- *
- * Atomically checks if @v holds @o and replaces it with @n if so.
- * Returns the old value at @v.
- */
-static inline u64 atomic64_cmpxchg(atomic64_t *v, u64 o, u64 n)
-{
-	smp_mb();  /* barrier for proper semantics */
-	return _atomic64_cmpxchg(v, o, n);
+	return _atomic64_xchg_add((long long *)&v->counter, 0);
 }
 
 /**
@@ -175,9 +108,9 @@ static inline u64 atomic64_cmpxchg(atomic64_t *v, u64 o, u64 n)
  *
  * Atomically adds @i to @v.
  */
-static inline void atomic64_add(u64 i, atomic64_t *v)
+static inline void atomic64_add(long long i, atomic64_t *v)
 {
-	_atomic64_xchg_add(v, i);
+	_atomic64_xchg_add(&v->counter, i);
 }
 
 /**
@@ -187,10 +120,10 @@ static inline void atomic64_add(u64 i, atomic64_t *v)
  *
  * Atomically adds @i to @v and returns @i + @v
  */
-static inline u64 atomic64_add_return(u64 i, atomic64_t *v)
+static inline long long atomic64_add_return(long long i, atomic64_t *v)
 {
 	smp_mb();  /* barrier for proper semantics */
-	return _atomic64_xchg_add(v, i) + i;
+	return _atomic64_xchg_add(&v->counter, i) + i;
 }
 
 /**
@@ -202,10 +135,11 @@ static inline u64 atomic64_add_return(u64 i, atomic64_t *v)
  * Atomically adds @a to @v, so long as @v was not already @u.
  * Returns non-zero if @v was not @u, and zero otherwise.
  */
-static inline u64 atomic64_add_unless(atomic64_t *v, u64 a, u64 u)
+static inline long long atomic64_add_unless(atomic64_t *v, long long a,
+					long long u)
 {
 	smp_mb();  /* barrier for proper semantics */
-	return _atomic64_xchg_add_unless(v, a, u) != u;
+	return _atomic64_xchg_add_unless(&v->counter, a, u) != u;
 }
 
 /**
@@ -218,9 +152,9 @@ static inline u64 atomic64_add_unless(atomic64_t *v, u64 a, u64 u)
  * atomic64_set() can't be just a raw store, since it would be lost if it
  * fell between the load and store of one of the other atomic ops.
  */
-static inline void atomic64_set(atomic64_t *v, u64 n)
+static inline void atomic64_set(atomic64_t *v, long long n)
 {
-	_atomic64_xchg(v, n);
+	_atomic64_xchg(&v->counter, n);
 }
 
 #define atomic64_add_negative(a, v)	(atomic64_add_return((a), (v)) < 0)
@@ -252,21 +186,6 @@ static inline void atomic64_set(atomic64_t *v, u64 n)
  * Internal definitions only beyond this point.
  */
 
-#define ATOMIC_LOCKS_FOUND_VIA_TABLE() \
-  (!CHIP_HAS_CBOX_HOME_MAP() && defined(CONFIG_SMP))
-
-#if ATOMIC_LOCKS_FOUND_VIA_TABLE()
-
-/* Number of entries in atomic_lock_ptr[]. */
-#define ATOMIC_HASH_L1_SHIFT 6
-#define ATOMIC_HASH_L1_SIZE (1 << ATOMIC_HASH_L1_SHIFT)
-
-/* Number of locks in each struct pointed to by atomic_lock_ptr[]. */
-#define ATOMIC_HASH_L2_SHIFT (CHIP_L2_LOG_LINE_SIZE() - 2)
-#define ATOMIC_HASH_L2_SIZE (1 << ATOMIC_HASH_L2_SHIFT)
-
-#else /* ATOMIC_LOCKS_FOUND_VIA_TABLE() */
-
 /*
  * Number of atomic locks in atomic_locks[]. Must be a power of two.
  * There is no reason for more than PAGE_SIZE / 8 entries, since that
@@ -281,8 +200,6 @@ static inline void atomic64_set(atomic64_t *v, u64 n)
 extern int atomic_locks[];
 #endif
 
-#endif /* ATOMIC_LOCKS_FOUND_VIA_TABLE() */
-
 /*
  * All the code that may fault while holding an atomic lock must
  * place the pointer to the lock in ATOMIC_LOCK_REG so the fault code
@@ -320,11 +237,13 @@ extern struct __get_user __atomic_xchg_add_unless(volatile int *p,
 extern struct __get_user __atomic_or(volatile int *p, int *lock, int n);
 extern struct __get_user __atomic_andn(volatile int *p, int *lock, int n);
 extern struct __get_user __atomic_xor(volatile int *p, int *lock, int n);
-extern u64 __atomic64_cmpxchg(volatile u64 *p, int *lock, u64 o, u64 n);
-extern u64 __atomic64_xchg(volatile u64 *p, int *lock, u64 n);
-extern u64 __atomic64_xchg_add(volatile u64 *p, int *lock, u64 n);
-extern u64 __atomic64_xchg_add_unless(volatile u64 *p,
-				      int *lock, u64 o, u64 n);
+extern long long __atomic64_cmpxchg(volatile long long *p, int *lock,
+					long long o, long long n);
+extern long long __atomic64_xchg(volatile long long *p, int *lock, long long n);
+extern long long __atomic64_xchg_add(volatile long long *p, int *lock,
+					long long n);
+extern long long __atomic64_xchg_add_unless(volatile long long *p,
+					int *lock, long long o, long long n);
 
 /* Return failure from the atomic wrappers. */
 struct __get_user __atomic_bad_address(int __user *addr);
diff --git a/arch/tile/include/asm/atomic_64.h b/arch/tile/include/asm/atomic_64.h
index f4500c688ffa..ad220eed05fc 100644
--- a/arch/tile/include/asm/atomic_64.h
+++ b/arch/tile/include/asm/atomic_64.h
@@ -32,25 +32,6 @@
  * on any routine which updates memory and returns a value.
  */
 
-static inline int atomic_cmpxchg(atomic_t *v, int o, int n)
-{
-	int val;
-	__insn_mtspr(SPR_CMPEXCH_VALUE, o);
-	smp_mb();  /* barrier for proper semantics */
-	val = __insn_cmpexch4((void *)&v->counter, n);
-	smp_mb();  /* barrier for proper semantics */
-	return val;
-}
-
-static inline int atomic_xchg(atomic_t *v, int n)
-{
-	int val;
-	smp_mb();  /* barrier for proper semantics */
-	val = __insn_exch4((void *)&v->counter, n);
-	smp_mb();  /* barrier for proper semantics */
-	return val;
-}
-
 static inline void atomic_add(int i, atomic_t *v)
 {
 	__insn_fetchadd4((void *)&v->counter, i);
@@ -72,7 +53,7 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u)
 		if (oldval == u)
 			break;
 		guess = oldval;
-		oldval = atomic_cmpxchg(v, guess, guess + a);
+		oldval = cmpxchg(&v->counter, guess, guess + a);
 	} while (guess != oldval);
 	return oldval;
 }
@@ -84,25 +65,6 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u)
 #define atomic64_read(v)		((v)->counter)
 #define atomic64_set(v, i) ((v)->counter = (i))
 
-static inline long atomic64_cmpxchg(atomic64_t *v, long o, long n)
-{
-	long val;
-	smp_mb();  /* barrier for proper semantics */
-	__insn_mtspr(SPR_CMPEXCH_VALUE, o);
-	val = __insn_cmpexch((void *)&v->counter, n);
-	smp_mb();  /* barrier for proper semantics */
-	return val;
-}
-
-static inline long atomic64_xchg(atomic64_t *v, long n)
-{
-	long val;
-	smp_mb();  /* barrier for proper semantics */
-	val = __insn_exch((void *)&v->counter, n);
-	smp_mb();  /* barrier for proper semantics */
-	return val;
-}
-
 static inline void atomic64_add(long i, atomic64_t *v)
 {
 	__insn_fetchadd((void *)&v->counter, i);
@@ -124,7 +86,7 @@ static inline long atomic64_add_unless(atomic64_t *v, long a, long u)
 		if (oldval == u)
 			break;
 		guess = oldval;
-		oldval = atomic64_cmpxchg(v, guess, guess + a);
+		oldval = cmpxchg(&v->counter, guess, guess + a);
 	} while (guess != oldval);
 	return oldval != u;
 }
diff --git a/arch/tile/include/asm/barrier.h b/arch/tile/include/asm/barrier.h
index 990a217a0b72..a9a73da5865d 100644
--- a/arch/tile/include/asm/barrier.h
+++ b/arch/tile/include/asm/barrier.h
@@ -77,7 +77,6 @@
 
 #define __sync()	__insn_mf()
 
-#if !CHIP_HAS_MF_WAITS_FOR_VICTIMS()
 #include <hv/syscall_public.h>
 /*
  * Issue an uncacheable load to each memory controller, then
@@ -96,7 +95,6 @@ static inline void __mb_incoherent(void)
 		       "r20", "r21", "r22", "r23", "r24",
 		       "r25", "r26", "r27", "r28", "r29");
 }
-#endif
 
 /* Fence to guarantee visibility of stores to incoherent memory. */
 static inline void
@@ -104,7 +102,6 @@ mb_incoherent(void)
 {
 	__insn_mf();
 
-#if !CHIP_HAS_MF_WAITS_FOR_VICTIMS()
 	{
 #if CHIP_HAS_TILE_WRITE_PENDING()
 		const unsigned long WRITE_TIMEOUT_CYCLES = 400;
@@ -116,7 +113,6 @@ mb_incoherent(void)
 #endif /* CHIP_HAS_TILE_WRITE_PENDING() */
 		(void) __mb_incoherent();
 	}
-#endif /* CHIP_HAS_MF_WAITS_FOR_VICTIMS() */
 }
 
 #define fast_wmb()	__sync()
diff --git a/arch/tile/include/asm/bitops.h b/arch/tile/include/asm/bitops.h
index bd186c4eaa50..d5a206865036 100644
--- a/arch/tile/include/asm/bitops.h
+++ b/arch/tile/include/asm/bitops.h
@@ -29,17 +29,6 @@
 #endif
 
 /**
- * __ffs - find first set bit in word
- * @word: The word to search
- *
- * Undefined if no set bit exists, so code should check against 0 first.
- */
-static inline unsigned long __ffs(unsigned long word)
-{
-	return __builtin_ctzl(word);
-}
-
-/**
  * ffz - find first zero bit in word
  * @word: The word to search
  *
@@ -50,33 +39,6 @@ static inline unsigned long ffz(unsigned long word)
 	return __builtin_ctzl(~word);
 }
 
-/**
- * __fls - find last set bit in word
- * @word: The word to search
- *
- * Undefined if no set bit exists, so code should check against 0 first.
- */
-static inline unsigned long __fls(unsigned long word)
-{
-	return (sizeof(word) * 8) - 1 - __builtin_clzl(word);
-}
-
-/**
- * ffs - find first set bit in word
- * @x: the word to search
- *
- * This is defined the same way as the libc and compiler builtin ffs
- * routines, therefore differs in spirit from the other bitops.
- *
- * ffs(value) returns 0 if value is 0 or the position of the first
- * set bit if value is nonzero. The first (least significant) bit
- * is at position 1.
- */
-static inline int ffs(int x)
-{
-	return __builtin_ffs(x);
-}
-
 static inline int fls64(__u64 w)
 {
 	return (sizeof(__u64) * 8) - __builtin_clzll(w);
@@ -118,6 +80,9 @@ static inline unsigned long __arch_hweight64(__u64 w)
 	return __builtin_popcountll(w);
 }
 
+#include <asm-generic/bitops/builtin-__ffs.h>
+#include <asm-generic/bitops/builtin-__fls.h>
+#include <asm-generic/bitops/builtin-ffs.h>
 #include <asm-generic/bitops/const_hweight.h>
 #include <asm-generic/bitops/lock.h>
 #include <asm-generic/bitops/find.h>
diff --git a/arch/tile/include/asm/bitops_32.h b/arch/tile/include/asm/bitops_32.h
index ddc4c1efde43..386865ad2f55 100644
--- a/arch/tile/include/asm/bitops_32.h
+++ b/arch/tile/include/asm/bitops_32.h
@@ -16,7 +16,7 @@
 #define _ASM_TILE_BITOPS_32_H
 
 #include <linux/compiler.h>
-#include <linux/atomic.h>
+#include <asm/barrier.h>
 
 /* Tile-specific routines to support <asm/bitops.h>. */
 unsigned long _atomic_or(volatile unsigned long *p, unsigned long mask);
diff --git a/arch/tile/include/asm/bitops_64.h b/arch/tile/include/asm/bitops_64.h
index 60b87ee54fb8..ad34cd056085 100644
--- a/arch/tile/include/asm/bitops_64.h
+++ b/arch/tile/include/asm/bitops_64.h
@@ -16,7 +16,7 @@
 #define _ASM_TILE_BITOPS_64_H
 
 #include <linux/compiler.h>
-#include <linux/atomic.h>
+#include <asm/cmpxchg.h>
 
 /* See <asm/bitops.h> for API comments. */
 
@@ -44,8 +44,7 @@ static inline void change_bit(unsigned nr, volatile unsigned long *addr)
 	oldval = *addr;
 	do {
 		guess = oldval;
-		oldval = atomic64_cmpxchg((atomic64_t *)addr,
-					  guess, guess ^ mask);
+		oldval = cmpxchg(addr, guess, guess ^ mask);
 	} while (guess != oldval);
 }
 
@@ -90,8 +89,7 @@ static inline int test_and_change_bit(unsigned nr,
 	oldval = *addr;
 	do {
 		guess = oldval;
-		oldval = atomic64_cmpxchg((atomic64_t *)addr,
-					  guess, guess ^ mask);
+		oldval = cmpxchg(addr, guess, guess ^ mask);
 	} while (guess != oldval);
 	return (oldval & mask) != 0;
 }
diff --git a/arch/tile/include/asm/cache.h b/arch/tile/include/asm/cache.h
index a9a529964e07..6160761d5f61 100644
--- a/arch/tile/include/asm/cache.h
+++ b/arch/tile/include/asm/cache.h
@@ -49,9 +49,16 @@
 #define __read_mostly __attribute__((__section__(".data..read_mostly")))
 
 /*
- * Attribute for data that is kept read/write coherent until the end of
- * initialization, then bumped to read/only incoherent for performance.
+ * Originally we used small TLB pages for kernel data and grouped some
+ * things together as "write once", enforcing the property at the end
+ * of initialization by making those pages read-only and non-coherent.
+ * This allowed better cache utilization since cache inclusion did not
+ * need to be maintained.  However, to do this requires an extra TLB
+ * entry, which on balance is more of a performance hit than the
+ * non-coherence is a performance gain, so we now just make "read
+ * mostly" and "write once" be synonyms.  We keep the attribute
+ * separate in case we change our minds at a future date.
  */
-#define __write_once __attribute__((__section__(".w1data")))
+#define __write_once __read_mostly
 
 #endif /* _ASM_TILE_CACHE_H */
diff --git a/arch/tile/include/asm/cacheflush.h b/arch/tile/include/asm/cacheflush.h
index 0fc63c488edf..92ee4c8a4f76 100644
--- a/arch/tile/include/asm/cacheflush.h
+++ b/arch/tile/include/asm/cacheflush.h
@@ -75,23 +75,6 @@ static inline void copy_to_user_page(struct vm_area_struct *vma,
 #define copy_from_user_page(vma, page, vaddr, dst, src, len) \
 	memcpy((dst), (src), (len))
 
-/*
- * Invalidate a VA range; pads to L2 cacheline boundaries.
- *
- * Note that on TILE64, __inv_buffer() actually flushes modified
- * cache lines in addition to invalidating them, i.e., it's the
- * same as __finv_buffer().
- */
-static inline void __inv_buffer(void *buffer, size_t size)
-{
-	char *next = (char *)((long)buffer & -L2_CACHE_BYTES);
-	char *finish = (char *)L2_CACHE_ALIGN((long)buffer + size);
-	while (next < finish) {
-		__insn_inv(next);
-		next += CHIP_INV_STRIDE();
-	}
-}
-
 /* Flush a VA range; pads to L2 cacheline boundaries. */
 static inline void __flush_buffer(void *buffer, size_t size)
 {
@@ -115,13 +98,6 @@ static inline void __finv_buffer(void *buffer, size_t size)
 }
 
 
-/* Invalidate a VA range and wait for it to be complete. */
-static inline void inv_buffer(void *buffer, size_t size)
-{
-	__inv_buffer(buffer, size);
-	mb();
-}
-
 /*
  * Flush a locally-homecached VA range and wait for the evicted
  * cachelines to hit memory.
@@ -142,6 +118,26 @@ static inline void finv_buffer_local(void *buffer, size_t size)
 	mb_incoherent();
 }
 
+#ifdef __tilepro__
+/* Invalidate a VA range; pads to L2 cacheline boundaries. */
+static inline void __inv_buffer(void *buffer, size_t size)
+{
+	char *next = (char *)((long)buffer & -L2_CACHE_BYTES);
+	char *finish = (char *)L2_CACHE_ALIGN((long)buffer + size);
+	while (next < finish) {
+		__insn_inv(next);
+		next += CHIP_INV_STRIDE();
+	}
+}
+
+/* Invalidate a VA range and wait for it to be complete. */
+static inline void inv_buffer(void *buffer, size_t size)
+{
+	__inv_buffer(buffer, size);
+	mb();
+}
+#endif
+
 /*
  * Flush and invalidate a VA range that is homed remotely, waiting
  * until the memory controller holds the flushed values.  If "hfh" is
diff --git a/arch/tile/include/asm/cmpxchg.h b/arch/tile/include/asm/cmpxchg.h
index 276f067e3640..0ccda3c425be 100644
--- a/arch/tile/include/asm/cmpxchg.h
+++ b/arch/tile/include/asm/cmpxchg.h
@@ -20,53 +20,114 @@
 
 #ifndef __ASSEMBLY__
 
-/* Nonexistent functions intended to cause link errors. */
-extern unsigned long __xchg_called_with_bad_pointer(void);
-extern unsigned long __cmpxchg_called_with_bad_pointer(void);
+#include <asm/barrier.h>
 
-#define xchg(ptr, x)							\
+/* Nonexistent functions intended to cause compile errors. */
+extern void __xchg_called_with_bad_pointer(void)
+	__compiletime_error("Bad argument size for xchg");
+extern void __cmpxchg_called_with_bad_pointer(void)
+	__compiletime_error("Bad argument size for cmpxchg");
+
+#ifndef __tilegx__
+
+/* Note the _atomic_xxx() routines include a final mb(). */
+int _atomic_xchg(int *ptr, int n);
+int _atomic_xchg_add(int *v, int i);
+int _atomic_xchg_add_unless(int *v, int a, int u);
+int _atomic_cmpxchg(int *ptr, int o, int n);
+long long _atomic64_xchg(long long *v, long long n);
+long long _atomic64_xchg_add(long long *v, long long i);
+long long _atomic64_xchg_add_unless(long long *v, long long a, long long u);
+long long _atomic64_cmpxchg(long long *v, long long o, long long n);
+
+#define xchg(ptr, n)							\
+	({								\
+		if (sizeof(*(ptr)) != 4)				\
+			__xchg_called_with_bad_pointer();		\
+		smp_mb();						\
+		(typeof(*(ptr)))_atomic_xchg((int *)(ptr), (int)(n));	\
+	})
+
+#define cmpxchg(ptr, o, n)						\
+	({								\
+		if (sizeof(*(ptr)) != 4)				\
+			__cmpxchg_called_with_bad_pointer();		\
+		smp_mb();						\
+		(typeof(*(ptr)))_atomic_cmpxchg((int *)ptr, (int)o,	\
+						(int)n);		\
+	})
+
+#define xchg64(ptr, n)							\
+	({								\
+		if (sizeof(*(ptr)) != 8)				\
+			__xchg_called_with_bad_pointer();		\
+		smp_mb();						\
+		(typeof(*(ptr)))_atomic64_xchg((long long *)(ptr),	\
+						(long long)(n));	\
+	})
+
+#define cmpxchg64(ptr, o, n)						\
+	({								\
+		if (sizeof(*(ptr)) != 8)				\
+			__cmpxchg_called_with_bad_pointer();		\
+		smp_mb();						\
+		(typeof(*(ptr)))_atomic64_cmpxchg((long long *)ptr,	\
+					(long long)o, (long long)n);	\
+	})
+
+#else
+
+#define xchg(ptr, n)							\
 	({								\
 		typeof(*(ptr)) __x;					\
+		smp_mb();						\
 		switch (sizeof(*(ptr))) {				\
 		case 4:							\
-			__x = (typeof(__x))(typeof(__x-__x))atomic_xchg( \
-				(atomic_t *)(ptr),			\
-				(u32)(typeof((x)-(x)))(x));		\
+			__x = (typeof(__x))(unsigned long)		\
+				__insn_exch4((ptr),			\
+					(u32)(unsigned long)(n));	\
 			break;						\
 		case 8:							\
-			__x = (typeof(__x))(typeof(__x-__x))atomic64_xchg( \
-				(atomic64_t *)(ptr),			\
-				(u64)(typeof((x)-(x)))(x));		\
+			__x = (typeof(__x))				\
+				__insn_exch((ptr), (unsigned long)(n));	\
 			break;						\
 		default:						\
 			__xchg_called_with_bad_pointer();		\
+			break;						\
 		}							\
+		smp_mb();						\
 		__x;							\
 	})
 
 #define cmpxchg(ptr, o, n)						\
 	({								\
 		typeof(*(ptr)) __x;					\
+		__insn_mtspr(SPR_CMPEXCH_VALUE, (unsigned long)(o));	\
+		smp_mb();						\
 		switch (sizeof(*(ptr))) {				\
 		case 4:							\
-			__x = (typeof(__x))(typeof(__x-__x))atomic_cmpxchg( \
-				(atomic_t *)(ptr),			\
-				(u32)(typeof((o)-(o)))(o),		\
-				(u32)(typeof((n)-(n)))(n));		\
+			__x = (typeof(__x))(unsigned long)		\
+				__insn_cmpexch4((ptr),			\
+					(u32)(unsigned long)(n));	\
 			break;						\
 		case 8:							\
-			__x = (typeof(__x))(typeof(__x-__x))atomic64_cmpxchg( \
-				(atomic64_t *)(ptr),			\
-				(u64)(typeof((o)-(o)))(o),		\
-				(u64)(typeof((n)-(n)))(n));		\
+			__x = (typeof(__x))__insn_cmpexch((ptr),	\
+						(long long)(n));	\
 			break;						\
 		default:						\
 			__cmpxchg_called_with_bad_pointer();		\
+			break;						\
 		}							\
+		smp_mb();						\
 		__x;							\
 	})
 
-#define tas(ptr) (xchg((ptr), 1))
+#define xchg64 xchg
+#define cmpxchg64 cmpxchg
+
+#endif
+
+#define tas(ptr) xchg((ptr), 1)
 
 #endif /* __ASSEMBLY__ */
 
diff --git a/arch/tile/include/asm/device.h b/arch/tile/include/asm/device.h
index 5182705bd056..6ab8bf146d4c 100644
--- a/arch/tile/include/asm/device.h
+++ b/arch/tile/include/asm/device.h
@@ -23,7 +23,10 @@ struct dev_archdata {
 	/* Offset of the DMA address from the PA. */
 	dma_addr_t		dma_offset;
 
-	/* Highest DMA address that can be generated by this device. */
+	/*
+	 * Highest DMA address that can be generated by devices that
+	 * have limited DMA capability, i.e. non 64-bit capable.
+	 */
 	dma_addr_t		max_direct_dma_addr;
 };
 
diff --git a/arch/tile/include/asm/dma-mapping.h b/arch/tile/include/asm/dma-mapping.h
index f2ff191376b4..1eae359d8315 100644
--- a/arch/tile/include/asm/dma-mapping.h
+++ b/arch/tile/include/asm/dma-mapping.h
@@ -20,9 +20,14 @@
 #include <linux/cache.h>
 #include <linux/io.h>
 
+#ifdef __tilegx__
+#define ARCH_HAS_DMA_GET_REQUIRED_MASK
+#endif
+
 extern struct dma_map_ops *tile_dma_map_ops;
 extern struct dma_map_ops *gx_pci_dma_map_ops;
 extern struct dma_map_ops *gx_legacy_pci_dma_map_ops;
+extern struct dma_map_ops *gx_hybrid_pci_dma_map_ops;
 
 static inline struct dma_map_ops *get_dma_ops(struct device *dev)
 {
@@ -44,12 +49,12 @@ static inline void set_dma_offset(struct device *dev, dma_addr_t off)
 
 static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
 {
-	return paddr + get_dma_offset(dev);
+	return paddr;
 }
 
 static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr)
 {
-	return daddr - get_dma_offset(dev);
+	return daddr;
 }
 
 static inline void dma_mark_clean(void *addr, size_t size) {}
@@ -87,11 +92,19 @@ dma_set_mask(struct device *dev, u64 mask)
 {
 	struct dma_map_ops *dma_ops = get_dma_ops(dev);
 
-	/* Handle legacy PCI devices with limited memory addressability. */
-	if ((dma_ops == gx_pci_dma_map_ops) && (mask <= DMA_BIT_MASK(32))) {
-		set_dma_ops(dev, gx_legacy_pci_dma_map_ops);
-		set_dma_offset(dev, 0);
-		if (mask > dev->archdata.max_direct_dma_addr)
+	/*
+	 * For PCI devices with 64-bit DMA addressing capability, promote
+	 * the dma_ops to hybrid, with the consistent memory DMA space limited
+	 * to 32-bit. For 32-bit capable devices, limit the streaming DMA
+	 * address range to max_direct_dma_addr.
+	 */
+	if (dma_ops == gx_pci_dma_map_ops ||
+	    dma_ops == gx_hybrid_pci_dma_map_ops ||
+	    dma_ops == gx_legacy_pci_dma_map_ops) {
+		if (mask == DMA_BIT_MASK(64) &&
+		    dma_ops == gx_legacy_pci_dma_map_ops)
+			set_dma_ops(dev, gx_hybrid_pci_dma_map_ops);
+		else if (mask > dev->archdata.max_direct_dma_addr)
 			mask = dev->archdata.max_direct_dma_addr;
 	}
 
diff --git a/arch/tile/include/asm/elf.h b/arch/tile/include/asm/elf.h
index ff8a93408823..41d9878a9686 100644
--- a/arch/tile/include/asm/elf.h
+++ b/arch/tile/include/asm/elf.h
@@ -30,7 +30,6 @@ typedef unsigned long elf_greg_t;
 #define ELF_NGREG (sizeof(struct pt_regs) / sizeof(elf_greg_t))
 typedef elf_greg_t elf_gregset_t[ELF_NGREG];
 
-#define EM_TILE64  187
 #define EM_TILEPRO 188
 #define EM_TILEGX  191
 
@@ -132,6 +131,15 @@ extern int dump_task_regs(struct task_struct *, elf_gregset_t *);
 struct linux_binprm;
 extern int arch_setup_additional_pages(struct linux_binprm *bprm,
 				       int executable_stack);
+#define ARCH_DLINFO \
+do { \
+	NEW_AUX_ENT(AT_SYSINFO_EHDR, VDSO_BASE); \
+} while (0)
+
+struct mm_struct;
+extern unsigned long arch_randomize_brk(struct mm_struct *mm);
+#define arch_randomize_brk arch_randomize_brk
+
 #ifdef CONFIG_COMPAT
 
 #define COMPAT_ELF_PLATFORM "tilegx-m32"
diff --git a/arch/tile/include/asm/fixmap.h b/arch/tile/include/asm/fixmap.h
index e16dbf929cb5..c6b9c1b38fd1 100644
--- a/arch/tile/include/asm/fixmap.h
+++ b/arch/tile/include/asm/fixmap.h
@@ -78,14 +78,6 @@ enum fixed_addresses {
 #endif
 };
 
-extern void __set_fixmap(enum fixed_addresses idx,
-			 unsigned long phys, pgprot_t flags);
-
-#define set_fixmap(idx, phys) \
-		__set_fixmap(idx, phys, PAGE_KERNEL)
-#define clear_fixmap(idx) \
-		__set_fixmap(idx, 0, __pgprot(0))
-
 #define __FIXADDR_SIZE	(__end_of_permanent_fixed_addresses << PAGE_SHIFT)
 #define __FIXADDR_BOOT_SIZE	(__end_of_fixed_addresses << PAGE_SHIFT)
 #define FIXADDR_START		(FIXADDR_TOP + PAGE_SIZE - __FIXADDR_SIZE)
diff --git a/arch/tile/include/asm/ftrace.h b/arch/tile/include/asm/ftrace.h
index 461459b06d98..13a9bb81a8ab 100644
--- a/arch/tile/include/asm/ftrace.h
+++ b/arch/tile/include/asm/ftrace.h
@@ -15,6 +15,26 @@
 #ifndef _ASM_TILE_FTRACE_H
 #define _ASM_TILE_FTRACE_H
 
-/* empty */
+#ifdef CONFIG_FUNCTION_TRACER
+
+#define MCOUNT_ADDR ((unsigned long)(__mcount))
+#define MCOUNT_INSN_SIZE 8		/* sizeof mcount call */
+
+#ifndef __ASSEMBLY__
+extern void __mcount(void);
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+static inline unsigned long ftrace_call_adjust(unsigned long addr)
+{
+	return addr;
+}
+
+struct dyn_arch_ftrace {
+};
+#endif /*  CONFIG_DYNAMIC_FTRACE */
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* CONFIG_FUNCTION_TRACER */
 
 #endif /* _ASM_TILE_FTRACE_H */
diff --git a/arch/tile/include/asm/futex.h b/arch/tile/include/asm/futex.h
index 5909ac3d7218..1a6ef1b69cb1 100644
--- a/arch/tile/include/asm/futex.h
+++ b/arch/tile/include/asm/futex.h
@@ -43,6 +43,7 @@
 	    ".pushsection .fixup,\"ax\"\n"			\
 	    "0: { movei %0, %5; j 9f }\n"			\
 	    ".section __ex_table,\"a\"\n"			\
+	    ".align 8\n"					\
 	    ".quad 1b, 0b\n"					\
 	    ".popsection\n"					\
 	    "9:"						\
diff --git a/arch/tile/include/asm/homecache.h b/arch/tile/include/asm/homecache.h
index 7b7771328642..7ddd1b8d6910 100644
--- a/arch/tile/include/asm/homecache.h
+++ b/arch/tile/include/asm/homecache.h
@@ -33,8 +33,7 @@ struct zone;
 
 /*
  * Is this page immutable (unwritable) and thus able to be cached more
- * widely than would otherwise be possible?  On tile64 this means we
- * mark the PTE to cache locally; on tilepro it means we have "nc" set.
+ * widely than would otherwise be possible?  This means we have "nc" set.
  */
 #define PAGE_HOME_IMMUTABLE -2
 
@@ -44,16 +43,8 @@ struct zone;
  */
 #define PAGE_HOME_INCOHERENT -3
 
-#if CHIP_HAS_CBOX_HOME_MAP()
 /* Home for the page is distributed via hash-for-home. */
 #define PAGE_HOME_HASH -4
-#endif
-
-/* Homing is unknown or unspecified.  Not valid for page_home(). */
-#define PAGE_HOME_UNKNOWN -5
-
-/* Home on the current cpu.  Not valid for page_home(). */
-#define PAGE_HOME_HERE -6
 
 /* Support wrapper to use instead of explicit hv_flush_remote(). */
 extern void flush_remote(unsigned long cache_pfn, unsigned long cache_length,
diff --git a/arch/tile/include/asm/io.h b/arch/tile/include/asm/io.h
index 31672918064c..9fe434969fab 100644
--- a/arch/tile/include/asm/io.h
+++ b/arch/tile/include/asm/io.h
@@ -19,7 +19,8 @@
 #include <linux/bug.h>
 #include <asm/page.h>
 
-#define IO_SPACE_LIMIT 0xfffffffful
+/* Maximum PCI I/O space address supported. */
+#define IO_SPACE_LIMIT 0xffffffff
 
 /*
  * Convert a physical pointer to a virtual kernel pointer for /dev/mem
@@ -254,7 +255,7 @@ static inline void writeq(u64 val, unsigned long addr)
 
 static inline void memset_io(volatile void *dst, int val, size_t len)
 {
-	int x;
+	size_t x;
 	BUG_ON((unsigned long)dst & 0x3);
 	val = (val & 0xff) * 0x01010101;
 	for (x = 0; x < len; x += 4)
@@ -264,7 +265,7 @@ static inline void memset_io(volatile void *dst, int val, size_t len)
 static inline void memcpy_fromio(void *dst, const volatile void __iomem *src,
 				 size_t len)
 {
-	int x;
+	size_t x;
 	BUG_ON((unsigned long)src & 0x3);
 	for (x = 0; x < len; x += 4)
 		*(u32 *)(dst + x) = readl(src + x);
@@ -273,7 +274,7 @@ static inline void memcpy_fromio(void *dst, const volatile void __iomem *src,
 static inline void memcpy_toio(volatile void __iomem *dst, const void *src,
 				size_t len)
 {
-	int x;
+	size_t x;
 	BUG_ON((unsigned long)dst & 0x3);
 	for (x = 0; x < len; x += 4)
 		writel(*(u32 *)(src + x), dst + x);
@@ -281,8 +282,108 @@ static inline void memcpy_toio(volatile void __iomem *dst, const void *src,
 
 #endif
 
+#if CHIP_HAS_MMIO() && defined(CONFIG_TILE_PCI_IO)
+
+static inline u8 inb(unsigned long addr)
+{
+	return readb((volatile void __iomem *) addr);
+}
+
+static inline u16 inw(unsigned long addr)
+{
+	return readw((volatile void __iomem *) addr);
+}
+
+static inline u32 inl(unsigned long addr)
+{
+	return readl((volatile void __iomem *) addr);
+}
+
+static inline void outb(u8 b, unsigned long addr)
+{
+	writeb(b, (volatile void __iomem *) addr);
+}
+
+static inline void outw(u16 b, unsigned long addr)
+{
+	writew(b, (volatile void __iomem *) addr);
+}
+
+static inline void outl(u32 b, unsigned long addr)
+{
+	writel(b, (volatile void __iomem *) addr);
+}
+
+static inline void insb(unsigned long addr, void *buffer, int count)
+{
+	if (count) {
+		u8 *buf = buffer;
+		do {
+			u8 x = inb(addr);
+			*buf++ = x;
+		} while (--count);
+	}
+}
+
+static inline void insw(unsigned long addr, void *buffer, int count)
+{
+	if (count) {
+		u16 *buf = buffer;
+		do {
+			u16 x = inw(addr);
+			*buf++ = x;
+		} while (--count);
+	}
+}
+
+static inline void insl(unsigned long addr, void *buffer, int count)
+{
+	if (count) {
+		u32 *buf = buffer;
+		do {
+			u32 x = inl(addr);
+			*buf++ = x;
+		} while (--count);
+	}
+}
+
+static inline void outsb(unsigned long addr, const void *buffer, int count)
+{
+	if (count) {
+		const u8 *buf = buffer;
+		do {
+			outb(*buf++, addr);
+		} while (--count);
+	}
+}
+
+static inline void outsw(unsigned long addr, const void *buffer, int count)
+{
+	if (count) {
+		const u16 *buf = buffer;
+		do {
+			outw(*buf++, addr);
+		} while (--count);
+	}
+}
+
+static inline void outsl(unsigned long addr, const void *buffer, int count)
+{
+	if (count) {
+		const u32 *buf = buffer;
+		do {
+			outl(*buf++, addr);
+		} while (--count);
+	}
+}
+
+extern void __iomem *ioport_map(unsigned long port, unsigned int len);
+extern void ioport_unmap(void __iomem *addr);
+
+#else
+
 /*
- * The Tile architecture does not support IOPORT, even with PCI.
+ * The TilePro architecture does not support IOPORT, even with PCI.
  * Unfortunately we can't yet simply not declare these methods,
  * since some generic code that compiles into the kernel, but
  * we never run, uses them unconditionally.
@@ -290,7 +391,12 @@ static inline void memcpy_toio(volatile void __iomem *dst, const void *src,
 
 static inline long ioport_panic(void)
 {
+#ifdef __tilegx__
+	panic("PCI IO space support is disabled. Configure the kernel with"
+	      " CONFIG_TILE_PCI_IO to enable it");
+#else
 	panic("inb/outb and friends do not exist on tile");
+#endif
 	return 0;
 }
 
@@ -335,13 +441,6 @@ static inline void outl(u32 b, unsigned long addr)
 	ioport_panic();
 }
 
-#define inb_p(addr)	inb(addr)
-#define inw_p(addr)	inw(addr)
-#define inl_p(addr)	inl(addr)
-#define outb_p(x, addr)	outb((x), (addr))
-#define outw_p(x, addr)	outw((x), (addr))
-#define outl_p(x, addr)	outl((x), (addr))
-
 static inline void insb(unsigned long addr, void *buffer, int count)
 {
 	ioport_panic();
@@ -372,6 +471,15 @@ static inline void outsl(unsigned long addr, const void *buffer, int count)
 	ioport_panic();
 }
 
+#endif /* CHIP_HAS_MMIO() && defined(CONFIG_TILE_PCI_IO) */
+
+#define inb_p(addr)	inb(addr)
+#define inw_p(addr)	inw(addr)
+#define inl_p(addr)	inl(addr)
+#define outb_p(x, addr)	outb((x), (addr))
+#define outw_p(x, addr)	outw((x), (addr))
+#define outl_p(x, addr)	outl((x), (addr))
+
 #define ioread16be(addr)	be16_to_cpu(ioread16(addr))
 #define ioread32be(addr)	be32_to_cpu(ioread32(addr))
 #define iowrite16be(v, addr)	iowrite16(be16_to_cpu(v), (addr))
diff --git a/arch/tile/include/asm/irqflags.h b/arch/tile/include/asm/irqflags.h
index c96f9bbb760d..71af5747874d 100644
--- a/arch/tile/include/asm/irqflags.h
+++ b/arch/tile/include/asm/irqflags.h
@@ -124,6 +124,12 @@
 DECLARE_PER_CPU(unsigned long long, interrupts_enabled_mask);
 #define INITIAL_INTERRUPTS_ENABLED (1ULL << INT_MEM_ERROR)
 
+#ifdef CONFIG_DEBUG_PREEMPT
+/* Due to inclusion issues, we can't rely on <linux/smp.h> here. */
+extern unsigned int debug_smp_processor_id(void);
+# define smp_processor_id() debug_smp_processor_id()
+#endif
+
 /* Disable interrupts. */
 #define arch_local_irq_disable() \
 	interrupt_mask_set_mask(LINUX_MASKABLE_INTERRUPTS)
@@ -132,9 +138,18 @@ DECLARE_PER_CPU(unsigned long long, interrupts_enabled_mask);
 #define arch_local_irq_disable_all() \
 	interrupt_mask_set_mask(-1ULL)
 
+/*
+ * Read the set of maskable interrupts.
+ * We avoid the preemption warning here via __this_cpu_ptr since even
+ * if irqs are already enabled, it's harmless to read the wrong cpu's
+ * enabled mask.
+ */
+#define arch_local_irqs_enabled() \
+	(*__this_cpu_ptr(&interrupts_enabled_mask))
+
 /* Re-enable all maskable interrupts. */
 #define arch_local_irq_enable() \
-	interrupt_mask_reset_mask(__get_cpu_var(interrupts_enabled_mask))
+	interrupt_mask_reset_mask(arch_local_irqs_enabled())
 
 /* Disable or enable interrupts based on flag argument. */
 #define arch_local_irq_restore(disabled) do { \
@@ -161,7 +176,7 @@ DECLARE_PER_CPU(unsigned long long, interrupts_enabled_mask);
 
 /* Prevent the given interrupt from being enabled next time we enable irqs. */
 #define arch_local_irq_mask(interrupt) \
-	(__get_cpu_var(interrupts_enabled_mask) &= ~(1ULL << (interrupt)))
+	this_cpu_and(interrupts_enabled_mask, ~(1ULL << (interrupt)))
 
 /* Prevent the given interrupt from being enabled immediately. */
 #define arch_local_irq_mask_now(interrupt) do { \
@@ -171,7 +186,7 @@ DECLARE_PER_CPU(unsigned long long, interrupts_enabled_mask);
 
 /* Allow the given interrupt to be enabled next time we enable irqs. */
 #define arch_local_irq_unmask(interrupt) \
-	(__get_cpu_var(interrupts_enabled_mask) |= (1ULL << (interrupt)))
+	this_cpu_or(interrupts_enabled_mask, (1ULL << (interrupt)))
 
 /* Allow the given interrupt to be enabled immediately, if !irqs_disabled. */
 #define arch_local_irq_unmask_now(interrupt) do { \
diff --git a/arch/tile/include/asm/hw_irq.h b/arch/tile/include/asm/kdebug.h
index 4fac5fbf333e..5bbbfa904c2d 100644
--- a/arch/tile/include/asm/hw_irq.h
+++ b/arch/tile/include/asm/kdebug.h
@@ -1,5 +1,5 @@
 /*
- * Copyright 2010 Tilera Corporation. All Rights Reserved.
+ * Copyright 2012 Tilera Corporation. All Rights Reserved.
  *
  *   This program is free software; you can redistribute it and/or
  *   modify it under the terms of the GNU General Public License
@@ -12,7 +12,17 @@
  *   more details.
  */
 
-#ifndef _ASM_TILE_HW_IRQ_H
-#define _ASM_TILE_HW_IRQ_H
+#ifndef _ASM_TILE_KDEBUG_H
+#define _ASM_TILE_KDEBUG_H
 
-#endif /* _ASM_TILE_HW_IRQ_H */
+#include <linux/notifier.h>
+
+enum die_val {
+	DIE_OOPS = 1,
+	DIE_BREAK,
+	DIE_SSTEPBP,
+	DIE_PAGE_FAULT,
+	DIE_COMPILED_BPT
+};
+
+#endif /* _ASM_TILE_KDEBUG_H */
diff --git a/arch/tile/include/asm/kgdb.h b/arch/tile/include/asm/kgdb.h
new file mode 100644
index 000000000000..280c181cf0db
--- /dev/null
+++ b/arch/tile/include/asm/kgdb.h
@@ -0,0 +1,71 @@
+/*
+ * Copyright 2013 Tilera Corporation. All Rights Reserved.
+ *
+ *   This program is free software; you can redistribute it and/or
+ *   modify it under the terms of the GNU General Public License
+ *   as published by the Free Software Foundation, version 2.
+ *
+ *   This program is distributed in the hope that it will be useful, but
+ *   WITHOUT ANY WARRANTY; without even the implied warranty of
+ *   MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ *   NON INFRINGEMENT.  See the GNU General Public License for
+ *   more details.
+ *
+ * TILE-Gx KGDB support.
+ */
+
+#ifndef __TILE_KGDB_H__
+#define __TILE_KGDB_H__
+
+#include <linux/kdebug.h>
+#include <arch/opcode.h>
+
+#define GDB_SIZEOF_REG		sizeof(unsigned long)
+
+/*
+ * TILE-Gx gdb is expecting the following register layout:
+ * 56 GPRs(R0 - R52, TP, SP, LR), 8 special GPRs(networks and ZERO),
+ * plus the PC and the faultnum.
+ *
+ * Even though kernel not use the 8 special GPRs, they need to be present
+ * in the registers sent for correct processing in the host-side gdb.
+ *
+ */
+#define DBG_MAX_REG_NUM		(56+8+2)
+#define NUMREGBYTES		(DBG_MAX_REG_NUM * GDB_SIZEOF_REG)
+
+/*
+ * BUFMAX defines the maximum number of characters in inbound/outbound
+ * buffers at least NUMREGBYTES*2 are needed for register packets,
+ * Longer buffer is needed to list all threads.
+ */
+#define BUFMAX			2048
+
+#define BREAK_INSTR_SIZE	TILEGX_BUNDLE_SIZE_IN_BYTES
+
+/*
+ * Require cache flush for set/clear a software breakpoint or write memory.
+ */
+#define CACHE_FLUSH_IS_SAFE	1
+
+/*
+ * The compiled-in breakpoint instruction can be used to "break" into
+ * the debugger via magic system request key (sysrq-G).
+ */
+static tile_bundle_bits compiled_bpt = TILEGX_BPT_BUNDLE | DIE_COMPILED_BPT;
+
+enum tilegx_regnum {
+	TILEGX_PC_REGNUM = TREG_LAST_GPR + 9,
+	TILEGX_FAULTNUM_REGNUM,
+};
+
+/*
+ * Generate a breakpoint exception to "break" into the debugger.
+ */
+static inline void arch_kgdb_breakpoint(void)
+{
+	asm volatile (".quad %0\n\t"
+		      ::""(compiled_bpt));
+}
+
+#endif /* __TILE_KGDB_H__ */
diff --git a/arch/tile/include/asm/kprobes.h b/arch/tile/include/asm/kprobes.h
new file mode 100644
index 000000000000..d8f9a83943b1
--- /dev/null
+++ b/arch/tile/include/asm/kprobes.h
@@ -0,0 +1,79 @@
+/*
+ * arch/tile/include/asm/kprobes.h
+ *
+ * Copyright 2012 Tilera Corporation. All Rights Reserved.
+ *
+ *   This program is free software; you can redistribute it and/or
+ *   modify it under the terms of the GNU General Public License
+ *   as published by the Free Software Foundation, version 2.
+ *
+ *   This program is distributed in the hope that it will be useful, but
+ *   WITHOUT ANY WARRANTY; without even the implied warranty of
+ *   MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ *   NON INFRINGEMENT.  See the GNU General Public License for
+ *   more details.
+ */
+
+#ifndef _ASM_TILE_KPROBES_H
+#define _ASM_TILE_KPROBES_H
+
+#include <linux/types.h>
+#include <linux/ptrace.h>
+#include <linux/percpu.h>
+
+#include <arch/opcode.h>
+
+#define __ARCH_WANT_KPROBES_INSN_SLOT
+#define MAX_INSN_SIZE			2
+
+#define kretprobe_blacklist_size 0
+
+typedef tile_bundle_bits kprobe_opcode_t;
+
+#define flush_insn_slot(p)						\
+	flush_icache_range((unsigned long)p->addr,			\
+			   (unsigned long)p->addr +			\
+			   (MAX_INSN_SIZE * sizeof(kprobe_opcode_t)))
+
+struct kprobe;
+
+/* Architecture specific copy of original instruction. */
+struct arch_specific_insn {
+	kprobe_opcode_t *insn;
+};
+
+struct prev_kprobe {
+	struct kprobe *kp;
+	unsigned long status;
+	unsigned long saved_pc;
+};
+
+#define MAX_JPROBES_STACK_SIZE 128
+#define MAX_JPROBES_STACK_ADDR \
+	(((unsigned long)current_thread_info()) + THREAD_SIZE - 32 \
+		- sizeof(struct pt_regs))
+
+#define MIN_JPROBES_STACK_SIZE(ADDR)					\
+	((((ADDR) + MAX_JPROBES_STACK_SIZE) > MAX_JPROBES_STACK_ADDR)	\
+		? MAX_JPROBES_STACK_ADDR - (ADDR)			\
+		: MAX_JPROBES_STACK_SIZE)
+
+/* per-cpu kprobe control block. */
+struct kprobe_ctlblk {
+	unsigned long kprobe_status;
+	unsigned long kprobe_saved_pc;
+	unsigned long jprobe_saved_sp;
+	struct prev_kprobe prev_kprobe;
+	struct pt_regs jprobe_saved_regs;
+	char jprobes_stack[MAX_JPROBES_STACK_SIZE];
+};
+
+extern tile_bundle_bits breakpoint2_insn;
+extern tile_bundle_bits breakpoint_insn;
+
+void arch_remove_kprobe(struct kprobe *);
+
+extern int kprobe_exceptions_notify(struct notifier_block *self,
+			     unsigned long val, void *data);
+
+#endif /* _ASM_TILE_KPROBES_H */
diff --git a/arch/tile/include/asm/mmu.h b/arch/tile/include/asm/mmu.h
index e2c789096795..0cab1182bde1 100644
--- a/arch/tile/include/asm/mmu.h
+++ b/arch/tile/include/asm/mmu.h
@@ -22,6 +22,7 @@ struct mm_context {
 	 * semaphore but atomically, but it is conservatively set.
 	 */
 	unsigned long priority_cached;
+	unsigned long vdso_base;
 };
 
 typedef struct mm_context mm_context_t;
diff --git a/arch/tile/include/asm/mmu_context.h b/arch/tile/include/asm/mmu_context.h
index 37f0b741dee7..4734215e2ad4 100644
--- a/arch/tile/include/asm/mmu_context.h
+++ b/arch/tile/include/asm/mmu_context.h
@@ -45,7 +45,7 @@ static inline void __install_page_table(pgd_t *pgdir, int asid, pgprot_t prot)
 
 static inline void install_page_table(pgd_t *pgdir, int asid)
 {
-	pte_t *ptep = virt_to_pte(NULL, (unsigned long)pgdir);
+	pte_t *ptep = virt_to_kpte((unsigned long)pgdir);
 	__install_page_table(pgdir, asid, *ptep);
 }
 
diff --git a/arch/tile/include/asm/mmzone.h b/arch/tile/include/asm/mmzone.h
index 9d3dbce8f953..804f1098b6cd 100644
--- a/arch/tile/include/asm/mmzone.h
+++ b/arch/tile/include/asm/mmzone.h
@@ -42,7 +42,7 @@ static inline int pfn_to_nid(unsigned long pfn)
 
 #define kern_addr_valid(kaddr)	virt_addr_valid((void *)kaddr)
 
-static inline int pfn_valid(int pfn)
+static inline int pfn_valid(unsigned long pfn)
 {
 	int nid = pfn_to_nid(pfn);
 
diff --git a/arch/tile/include/asm/page.h b/arch/tile/include/asm/page.h
index dd033a4fd627..672768008618 100644
--- a/arch/tile/include/asm/page.h
+++ b/arch/tile/include/asm/page.h
@@ -39,6 +39,12 @@
 #define HPAGE_MASK	(~(HPAGE_SIZE - 1))
 
 /*
+ * We do define AT_SYSINFO_EHDR to support vDSO,
+ * but don't use the gate mechanism.
+ */
+#define __HAVE_ARCH_GATE_AREA		1
+
+/*
  * If the Kconfig doesn't specify, set a maximum zone order that
  * is enough so that we can create huge pages from small pages given
  * the respective sizes of the two page types.  See <linux/mmzone.h>.
@@ -142,8 +148,12 @@ static inline __attribute_const__ int get_order(unsigned long size)
 #define HAVE_ARCH_HUGETLB_UNMAPPED_AREA
 #endif
 
+/* Allow overriding how much VA or PA the kernel will use. */
+#define MAX_PA_WIDTH CHIP_PA_WIDTH()
+#define MAX_VA_WIDTH CHIP_VA_WIDTH()
+
 /* Each memory controller has PAs distinct in their high bits. */
-#define NR_PA_HIGHBIT_SHIFT (CHIP_PA_WIDTH() - CHIP_LOG_NUM_MSHIMS())
+#define NR_PA_HIGHBIT_SHIFT (MAX_PA_WIDTH - CHIP_LOG_NUM_MSHIMS())
 #define NR_PA_HIGHBIT_VALUES (1 << CHIP_LOG_NUM_MSHIMS())
 #define __pa_to_highbits(pa) ((phys_addr_t)(pa) >> NR_PA_HIGHBIT_SHIFT)
 #define __pfn_to_highbits(pfn) ((pfn) >> (NR_PA_HIGHBIT_SHIFT - PAGE_SHIFT))
@@ -154,7 +164,7 @@ static inline __attribute_const__ int get_order(unsigned long size)
  * We reserve the lower half of memory for user-space programs, and the
  * upper half for system code.  We re-map all of physical memory in the
  * upper half, which takes a quarter of our VA space.  Then we have
- * the vmalloc regions.  The supervisor code lives at 0xfffffff700000000,
+ * the vmalloc regions.  The supervisor code lives at the highest address,
  * with the hypervisor above that.
  *
  * Loadable kernel modules are placed immediately after the static
@@ -166,26 +176,18 @@ static inline __attribute_const__ int get_order(unsigned long size)
  * Similarly, for now we don't play any struct page mapping games.
  */
 
-#if CHIP_PA_WIDTH() + 2 > CHIP_VA_WIDTH()
+#if MAX_PA_WIDTH + 2 > MAX_VA_WIDTH
 # error Too much PA to map with the VA available!
 #endif
-#define HALF_VA_SPACE           (_AC(1, UL) << (CHIP_VA_WIDTH() - 1))
 
-#define MEM_LOW_END		(HALF_VA_SPACE - 1)         /* low half */
-#define MEM_HIGH_START		(-HALF_VA_SPACE)            /* high half */
-#define PAGE_OFFSET		MEM_HIGH_START
-#define FIXADDR_BASE		_AC(0xfffffff400000000, UL) /* 4 GB */
-#define FIXADDR_TOP		_AC(0xfffffff500000000, UL) /* 4 GB */
+#define PAGE_OFFSET		(-(_AC(1, UL) << (MAX_VA_WIDTH - 1)))
+#define KERNEL_HIGH_VADDR	_AC(0xfffffff800000000, UL)  /* high 32GB */
+#define FIXADDR_BASE		(KERNEL_HIGH_VADDR - 0x300000000) /* 4 GB */
+#define FIXADDR_TOP		(KERNEL_HIGH_VADDR - 0x200000000) /* 4 GB */
 #define _VMALLOC_START		FIXADDR_TOP
-#define HUGE_VMAP_BASE		_AC(0xfffffff600000000, UL) /* 4 GB */
-#define MEM_SV_START		_AC(0xfffffff700000000, UL) /* 256 MB */
-#define MEM_SV_INTRPT		MEM_SV_START
-#define MEM_MODULE_START	_AC(0xfffffff710000000, UL) /* 256 MB */
+#define MEM_SV_START		(KERNEL_HIGH_VADDR - 0x100000000) /* 256 MB */
+#define MEM_MODULE_START	(MEM_SV_START + (256*1024*1024)) /* 256 MB */
 #define MEM_MODULE_END		(MEM_MODULE_START + (256*1024*1024))
-#define MEM_HV_START		_AC(0xfffffff800000000, UL) /* 32 GB */
-
-/* Highest DTLB address we will use */
-#define KERNEL_HIGH_VADDR	MEM_SV_START
 
 #else /* !__tilegx__ */
 
@@ -207,25 +209,18 @@ static inline __attribute_const__ int get_order(unsigned long size)
  * values, and after that, we show "typical" values, since the actual
  * addresses depend on kernel #defines.
  *
- * MEM_HV_INTRPT                   0xfe000000
- * MEM_SV_INTRPT (kernel code)     0xfd000000
+ * MEM_HV_START                    0xfe000000
+ * MEM_SV_START  (kernel code)     0xfd000000
  * MEM_USER_INTRPT (user vector)   0xfc000000
- * FIX_KMAP_xxx                    0xf8000000 (via NR_CPUS * KM_TYPE_NR)
- * PKMAP_BASE                      0xf7000000 (via LAST_PKMAP)
- * HUGE_VMAP                       0xf3000000 (via CONFIG_NR_HUGE_VMAPS)
- * VMALLOC_START                   0xf0000000 (via __VMALLOC_RESERVE)
+ * FIX_KMAP_xxx                    0xfa000000 (via NR_CPUS * KM_TYPE_NR)
+ * PKMAP_BASE                      0xf9000000 (via LAST_PKMAP)
+ * VMALLOC_START                   0xf7000000 (via VMALLOC_RESERVE)
  * mapped LOWMEM                   0xc0000000
  */
 
 #define MEM_USER_INTRPT		_AC(0xfc000000, UL)
-#if CONFIG_KERNEL_PL == 1
-#define MEM_SV_INTRPT		_AC(0xfd000000, UL)
-#define MEM_HV_INTRPT		_AC(0xfe000000, UL)
-#else
-#define MEM_GUEST_INTRPT	_AC(0xfd000000, UL)
-#define MEM_SV_INTRPT		_AC(0xfe000000, UL)
-#define MEM_HV_INTRPT		_AC(0xff000000, UL)
-#endif
+#define MEM_SV_START		_AC(0xfd000000, UL)
+#define MEM_HV_START		_AC(0xfe000000, UL)
 
 #define INTRPT_SIZE		0x4000
 
@@ -246,7 +241,7 @@ static inline __attribute_const__ int get_order(unsigned long size)
 
 #endif /* __tilegx__ */
 
-#ifndef __ASSEMBLY__
+#if !defined(__ASSEMBLY__) && !defined(VDSO_BUILD)
 
 #ifdef CONFIG_HIGHMEM
 
@@ -332,6 +327,7 @@ static inline int pfn_valid(unsigned long pfn)
 
 struct mm_struct;
 extern pte_t *virt_to_pte(struct mm_struct *mm, unsigned long addr);
+extern pte_t *virt_to_kpte(unsigned long kaddr);
 
 #endif /* !__ASSEMBLY__ */
 
diff --git a/arch/tile/include/asm/pci.h b/arch/tile/include/asm/pci.h
index 54a924208d3c..dfedd7ac7298 100644
--- a/arch/tile/include/asm/pci.h
+++ b/arch/tile/include/asm/pci.h
@@ -17,7 +17,6 @@
 
 #include <linux/dma-mapping.h>
 #include <linux/pci.h>
-#include <linux/numa.h>
 #include <asm-generic/pci_iomap.h>
 
 #ifndef __tilegx__
@@ -29,7 +28,6 @@ struct pci_controller {
 	int index;		/* PCI domain number */
 	struct pci_bus *root_bus;
 
-	int first_busno;
 	int last_busno;
 
 	int hv_cfg_fd[2];	/* config{0,1} fds for this PCIe controller */
@@ -124,6 +122,11 @@ static inline void pci_iounmap(struct pci_dev *dev, void __iomem *addr) {}
  * the CPA plus TILE_PCI_MEM_MAP_BASE_OFFSET. To support 32-bit
  * devices, we create a separate map region that handles the low
  * 4GB.
+ *
+ * This design lets us avoid the "PCI hole" problem where the host bridge
+ * won't pass DMA traffic with target addresses that happen to fall within the
+ * BAR space. This enables us to use all the physical memory for DMA, instead
+ * of wasting the same amount of physical memory as the BAR window size.
  */
 #define	TILE_PCI_MEM_MAP_BASE_OFFSET	(1ULL << CHIP_PA_WIDTH())
 
@@ -145,6 +148,10 @@ struct pci_controller {
 
 	int pio_mem_index;	/* PIO region index for memory access */
 
+#ifdef CONFIG_TILE_PCI_IO
+	int pio_io_index;	/* PIO region index for I/O space access */
+#endif
+
 	/*
 	 * Mem-Map regions for all the memory controllers so that Linux can
 	 * map all of its physical memory space to the PCI bus.
@@ -154,6 +161,10 @@ struct pci_controller {
 	int index;		/* PCI domain number */
 	struct pci_bus *root_bus;
 
+	/* PCI I/O space resource for this controller. */
+	struct resource io_space;
+	char io_space_name[32];
+
 	/* PCI memory space resource for this controller. */
 	struct resource mem_space;
 	char mem_space_name[32];
@@ -166,13 +177,11 @@ struct pci_controller {
 
 	/* Table that maps the INTx numbers to Linux irq numbers. */
 	int irq_intx_table[4];
-
-	/* Address ranges that are routed to this controller/bridge. */
-	struct resource mem_resources[3];
 };
 
 extern struct pci_controller pci_controllers[TILEGX_NUM_TRIO * TILEGX_TRIO_PCIES];
 extern gxio_trio_context_t trio_contexts[TILEGX_NUM_TRIO];
+extern int num_trio_shims;
 
 extern void pci_iounmap(struct pci_dev *dev, void __iomem *);
 
@@ -211,7 +220,8 @@ static inline int pcibios_assign_all_busses(void)
 }
 
 #define PCIBIOS_MIN_MEM		0
-#define PCIBIOS_MIN_IO		0
+/* Minimum PCI I/O address, starting at the page boundary. */
+#define PCIBIOS_MIN_IO		PAGE_SIZE
 
 /* Use any cpu for PCI. */
 #define cpumask_of_pcibus(bus) cpu_online_mask
diff --git a/arch/tile/include/asm/percpu.h b/arch/tile/include/asm/percpu.h
index 63294f5a8efb..4f7ae39fa202 100644
--- a/arch/tile/include/asm/percpu.h
+++ b/arch/tile/include/asm/percpu.h
@@ -15,9 +15,37 @@
 #ifndef _ASM_TILE_PERCPU_H
 #define _ASM_TILE_PERCPU_H
 
-register unsigned long __my_cpu_offset __asm__("tp");
-#define __my_cpu_offset __my_cpu_offset
-#define set_my_cpu_offset(tp) (__my_cpu_offset = (tp))
+register unsigned long my_cpu_offset_reg asm("tp");
+
+#ifdef CONFIG_PREEMPT
+/*
+ * For full preemption, we can't just use the register variable
+ * directly, since we need barrier() to hazard against it, causing the
+ * compiler to reload anything computed from a previous "tp" value.
+ * But we also don't want to use volatile asm, since we'd like the
+ * compiler to be able to cache the value across multiple percpu reads.
+ * So we use a fake stack read as a hazard against barrier().
+ * The 'U' constraint is like 'm' but disallows postincrement.
+ */
+static inline unsigned long __my_cpu_offset(void)
+{
+	unsigned long tp;
+	register unsigned long *sp asm("sp");
+	asm("move %0, tp" : "=r" (tp) : "U" (*sp));
+	return tp;
+}
+#define __my_cpu_offset __my_cpu_offset()
+#else
+/*
+ * We don't need to hazard against barrier() since "tp" doesn't ever
+ * change with PREEMPT_NONE, and with PREEMPT_VOLUNTARY it only
+ * changes at function call points, at which we are already re-reading
+ * the value of "tp" due to "my_cpu_offset_reg" being a global variable.
+ */
+#define __my_cpu_offset my_cpu_offset_reg
+#endif
+
+#define set_my_cpu_offset(tp) (my_cpu_offset_reg = (tp))
 
 #include <asm-generic/percpu.h>
 
diff --git a/arch/tile/include/asm/pgtable_32.h b/arch/tile/include/asm/pgtable_32.h
index 4ce4a7a99c24..d26a42279036 100644
--- a/arch/tile/include/asm/pgtable_32.h
+++ b/arch/tile/include/asm/pgtable_32.h
@@ -55,17 +55,9 @@
 #define PKMAP_BASE   ((FIXADDR_BOOT_START - PAGE_SIZE*LAST_PKMAP) & PGDIR_MASK)
 
 #ifdef CONFIG_HIGHMEM
-# define __VMAPPING_END	(PKMAP_BASE & ~(HPAGE_SIZE-1))
+# define _VMALLOC_END	(PKMAP_BASE & ~(HPAGE_SIZE-1))
 #else
-# define __VMAPPING_END	(FIXADDR_START & ~(HPAGE_SIZE-1))
-#endif
-
-#ifdef CONFIG_HUGEVMAP
-#define HUGE_VMAP_END	__VMAPPING_END
-#define HUGE_VMAP_BASE	(HUGE_VMAP_END - CONFIG_NR_HUGE_VMAPS * HPAGE_SIZE)
-#define _VMALLOC_END	HUGE_VMAP_BASE
-#else
-#define _VMALLOC_END	__VMAPPING_END
+# define _VMALLOC_END	(FIXADDR_START & ~(HPAGE_SIZE-1))
 #endif
 
 /*
@@ -84,10 +76,12 @@ extern unsigned long VMALLOC_RESERVE /* = CONFIG_VMALLOC_RESERVE */;
 /* We have no pmd or pud since we are strictly a two-level page table */
 #include <asm-generic/pgtable-nopmd.h>
 
+static inline int pud_huge_page(pud_t pud)	{ return 0; }
+
 /* We don't define any pgds for these addresses. */
 static inline int pgd_addr_invalid(unsigned long addr)
 {
-	return addr >= MEM_HV_INTRPT;
+	return addr >= MEM_HV_START;
 }
 
 /*
diff --git a/arch/tile/include/asm/pgtable_64.h b/arch/tile/include/asm/pgtable_64.h
index 2492fa5478e7..2c8a9cd102d3 100644
--- a/arch/tile/include/asm/pgtable_64.h
+++ b/arch/tile/include/asm/pgtable_64.h
@@ -52,17 +52,24 @@
  * memory allocation code).  The vmalloc code puts in an internal
  * guard page between each allocation.
  */
-#define _VMALLOC_END	HUGE_VMAP_BASE
+#define _VMALLOC_END	MEM_SV_START
 #define VMALLOC_END	_VMALLOC_END
 #define VMALLOC_START	_VMALLOC_START
 
-#define HUGE_VMAP_END	(HUGE_VMAP_BASE + PGDIR_SIZE)
-
 #ifndef __ASSEMBLY__
 
 /* We have no pud since we are a three-level page table. */
 #include <asm-generic/pgtable-nopud.h>
 
+/*
+ * pmds are the same as pgds and ptes, so converting is a no-op.
+ */
+#define pmd_pte(pmd) (pmd)
+#define pmdp_ptep(pmdp) (pmdp)
+#define pte_pmd(pte) (pte)
+
+#define pud_pte(pud) ((pud).pgd)
+
 static inline int pud_none(pud_t pud)
 {
 	return pud_val(pud) == 0;
@@ -73,6 +80,11 @@ static inline int pud_present(pud_t pud)
 	return pud_val(pud) & _PAGE_PRESENT;
 }
 
+static inline int pud_huge_page(pud_t pud)
+{
+	return pud_val(pud) & _PAGE_HUGE_PAGE;
+}
+
 #define pmd_ERROR(e) \
 	pr_err("%s:%d: bad pmd 0x%016llx.\n", __FILE__, __LINE__, pmd_val(e))
 
@@ -89,6 +101,9 @@ static inline int pud_bad(pud_t pud)
 /* Return the page-table frame number (ptfn) that a pud_t points at. */
 #define pud_ptfn(pud) hv_pte_get_ptfn((pud).pgd)
 
+/* Return the page frame number (pfn) that a pud_t points at. */
+#define pud_pfn(pud) pte_pfn(pud_pte(pud))
+
 /*
  * A given kernel pud_t maps to a kernel pmd_t table at a specific
  * virtual address.  Since kernel pmd_t tables can be aligned at
@@ -123,8 +138,7 @@ static inline unsigned long pgd_addr_normalize(unsigned long addr)
 /* We don't define any pgds for these addresses. */
 static inline int pgd_addr_invalid(unsigned long addr)
 {
-	return addr >= MEM_HV_START ||
-		(addr > MEM_LOW_END && addr < MEM_HIGH_START);
+	return addr >= KERNEL_HIGH_VADDR || addr != pgd_addr_normalize(addr);
 }
 
 /*
@@ -152,13 +166,6 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
 	return hv_pte(__insn_exch(&ptep->val, 0UL));
 }
 
-/*
- * pmds are the same as pgds and ptes, so converting is a no-op.
- */
-#define pmd_pte(pmd) (pmd)
-#define pmdp_ptep(pmdp) (pmdp)
-#define pte_pmd(pte) (pte)
-
 #endif /* __ASSEMBLY__ */
 
 #endif /* _ASM_TILE_PGTABLE_64_H */
diff --git a/arch/tile/include/asm/processor.h b/arch/tile/include/asm/processor.h
index b3f104953da2..42323636c459 100644
--- a/arch/tile/include/asm/processor.h
+++ b/arch/tile/include/asm/processor.h
@@ -15,6 +15,8 @@
 #ifndef _ASM_TILE_PROCESSOR_H
 #define _ASM_TILE_PROCESSOR_H
 
+#include <arch/chip.h>
+
 #ifndef __ASSEMBLY__
 
 /*
@@ -25,7 +27,6 @@
 #include <asm/ptrace.h>
 #include <asm/percpu.h>
 
-#include <arch/chip.h>
 #include <arch/spr_def.h>
 
 struct task_struct;
@@ -110,18 +111,16 @@ struct thread_struct {
 	unsigned long long interrupt_mask;
 	/* User interrupt-control 0 state */
 	unsigned long intctrl_0;
-#if CHIP_HAS_PROC_STATUS_SPR()
+	/* Is this task currently doing a backtrace? */
+	bool in_backtrace;
 	/* Any other miscellaneous processor state bits */
 	unsigned long proc_status;
-#endif
 #if !CHIP_HAS_FIXED_INTVEC_BASE()
 	/* Interrupt base for PL0 interrupts */
 	unsigned long interrupt_vector_base;
 #endif
-#if CHIP_HAS_TILE_RTF_HWM()
 	/* Tile cache retry fifo high-water mark */
 	unsigned long tile_rtf_hwm;
-#endif
 #if CHIP_HAS_DSTREAM_PF()
 	/* Data stream prefetch control */
 	unsigned long dstream_pf;
@@ -134,21 +133,16 @@ struct thread_struct {
 	/* Async DMA TLB fault information */
 	struct async_tlb dma_async_tlb;
 #endif
-#if CHIP_HAS_SN_PROC()
-	/* Was static network processor when we were switched out? */
-	int sn_proc_running;
-	/* Async SNI TLB fault information */
-	struct async_tlb sn_async_tlb;
-#endif
 };
 
 #endif /* !__ASSEMBLY__ */
 
 /*
  * Start with "sp" this many bytes below the top of the kernel stack.
- * This preserves the invariant that a called function may write to *sp.
+ * This allows us to be cache-aware when handling the initial save
+ * of the pt_regs value to the stack.
  */
-#define STACK_TOP_DELTA 8
+#define STACK_TOP_DELTA 64
 
 /*
  * When entering the kernel via a fault, start with the top of the
@@ -164,7 +158,7 @@ struct thread_struct {
 #ifndef __ASSEMBLY__
 
 #ifdef __tilegx__
-#define TASK_SIZE_MAX		(MEM_LOW_END + 1)
+#define TASK_SIZE_MAX		(_AC(1, UL) << (MAX_VA_WIDTH - 1))
 #else
 #define TASK_SIZE_MAX		PAGE_OFFSET
 #endif
@@ -178,10 +172,10 @@ struct thread_struct {
 #define TASK_SIZE		TASK_SIZE_MAX
 #endif
 
-/* We provide a minimal "vdso" a la x86; just the sigreturn code for now. */
-#define VDSO_BASE		(TASK_SIZE - PAGE_SIZE)
+#define VDSO_BASE	((unsigned long)current->active_mm->context.vdso_base)
+#define VDSO_SYM(x)	(VDSO_BASE + (unsigned long)(x))
 
-#define STACK_TOP		VDSO_BASE
+#define STACK_TOP		TASK_SIZE
 
 /* STACK_TOP_MAX is used temporarily in execve and should not check COMPAT. */
 #define STACK_TOP_MAX		TASK_SIZE_MAX
@@ -232,21 +226,28 @@ extern int do_work_pending(struct pt_regs *regs, u32 flags);
 unsigned long get_wchan(struct task_struct *p);
 
 /* Return initial ksp value for given task. */
-#define task_ksp0(task) ((unsigned long)(task)->stack + THREAD_SIZE)
+#define task_ksp0(task) \
+	((unsigned long)(task)->stack + THREAD_SIZE - STACK_TOP_DELTA)
 
 /* Return some info about the user process TASK. */
-#define KSTK_TOP(task)	(task_ksp0(task) - STACK_TOP_DELTA)
 #define task_pt_regs(task) \
-  ((struct pt_regs *)(task_ksp0(task) - KSTK_PTREGS_GAP) - 1)
+	((struct pt_regs *)(task_ksp0(task) - KSTK_PTREGS_GAP) - 1)
 #define current_pt_regs()                                   \
-  ((struct pt_regs *)((stack_pointer | (THREAD_SIZE - 1)) - \
-                      (KSTK_PTREGS_GAP - 1)) - 1)
+	((struct pt_regs *)((stack_pointer | (THREAD_SIZE - 1)) - \
+			    STACK_TOP_DELTA - (KSTK_PTREGS_GAP - 1)) - 1)
 #define task_sp(task)	(task_pt_regs(task)->sp)
 #define task_pc(task)	(task_pt_regs(task)->pc)
 /* Aliases for pc and sp (used in fs/proc/array.c) */
 #define KSTK_EIP(task)	task_pc(task)
 #define KSTK_ESP(task)	task_sp(task)
 
+/* Fine-grained unaligned JIT support */
+#define GET_UNALIGN_CTL(tsk, adr)	get_unalign_ctl((tsk), (adr))
+#define SET_UNALIGN_CTL(tsk, val)	set_unalign_ctl((tsk), (val))
+
+extern int get_unalign_ctl(struct task_struct *tsk, unsigned long adr);
+extern int set_unalign_ctl(struct task_struct *tsk, unsigned int val);
+
 /* Standard format for printing registers and other word-size data. */
 #ifdef __tilegx__
 # define REGFMT "0x%016lx"
@@ -275,7 +276,6 @@ extern char chip_model[64];
 /* Data on which physical memory controller corresponds to which NUMA node. */
 extern int node_controller[];
 
-#if CHIP_HAS_CBOX_HOME_MAP()
 /* Does the heap allocator return hash-for-home pages by default? */
 extern int hash_default;
 
@@ -285,11 +285,6 @@ extern int kstack_hash;
 /* Does MAP_ANONYMOUS return hash-for-home pages by default? */
 #define uheap_hash hash_default
 
-#else
-#define hash_default 0
-#define kstack_hash 0
-#define uheap_hash 0
-#endif
 
 /* Are we using huge pages in the TLB for kernel data? */
 extern int kdata_huge;
@@ -337,7 +332,6 @@ extern int kdata_huge;
 
 /*
  * Provide symbolic constants for PLs.
- * Note that assembly code assumes that USER_PL is zero.
  */
 #define USER_PL 0
 #if CONFIG_KERNEL_PL == 2
@@ -346,20 +340,38 @@ extern int kdata_huge;
 #define KERNEL_PL CONFIG_KERNEL_PL
 
 /* SYSTEM_SAVE_K_0 holds the current cpu number ORed with ksp0. */
-#define CPU_LOG_MASK_VALUE 12
-#define CPU_MASK_VALUE ((1 << CPU_LOG_MASK_VALUE) - 1)
-#if CONFIG_NR_CPUS > CPU_MASK_VALUE
-# error Too many cpus!
+#ifdef __tilegx__
+#define CPU_SHIFT 48
+#if CHIP_VA_WIDTH() > CPU_SHIFT
+# error Too many VA bits!
 #endif
+#define MAX_CPU_ID ((1 << (64 - CPU_SHIFT)) - 1)
+#define raw_smp_processor_id() \
+	((int)(__insn_mfspr(SPR_SYSTEM_SAVE_K_0) >> CPU_SHIFT))
+#define get_current_ksp0() \
+	((unsigned long)(((long)__insn_mfspr(SPR_SYSTEM_SAVE_K_0) << \
+			  (64 - CPU_SHIFT)) >> (64 - CPU_SHIFT)))
+#define next_current_ksp0(task) ({ \
+	unsigned long __ksp0 = task_ksp0(task) & ((1UL << CPU_SHIFT) - 1); \
+	unsigned long __cpu = (long)raw_smp_processor_id() << CPU_SHIFT; \
+	__ksp0 | __cpu; \
+})
+#else
+#define LOG2_NR_CPU_IDS 6
+#define MAX_CPU_ID ((1 << LOG2_NR_CPU_IDS) - 1)
 #define raw_smp_processor_id() \
-	((int)__insn_mfspr(SPR_SYSTEM_SAVE_K_0) & CPU_MASK_VALUE)
+	((int)__insn_mfspr(SPR_SYSTEM_SAVE_K_0) & MAX_CPU_ID)
 #define get_current_ksp0() \
-	(__insn_mfspr(SPR_SYSTEM_SAVE_K_0) & ~CPU_MASK_VALUE)
+	(__insn_mfspr(SPR_SYSTEM_SAVE_K_0) & ~MAX_CPU_ID)
 #define next_current_ksp0(task) ({ \
 	unsigned long __ksp0 = task_ksp0(task); \
 	int __cpu = raw_smp_processor_id(); \
-	BUG_ON(__ksp0 & CPU_MASK_VALUE); \
+	BUG_ON(__ksp0 & MAX_CPU_ID); \
 	__ksp0 | __cpu; \
 })
+#endif
+#if CONFIG_NR_CPUS > (MAX_CPU_ID + 1)
+# error Too many cpus!
+#endif
 
 #endif /* _ASM_TILE_PROCESSOR_H */
diff --git a/arch/tile/include/asm/ptrace.h b/arch/tile/include/asm/ptrace.h
index fd412260aff7..b9620c077abc 100644
--- a/arch/tile/include/asm/ptrace.h
+++ b/arch/tile/include/asm/ptrace.h
@@ -33,12 +33,13 @@ typedef unsigned long pt_reg_t;
 
 #ifndef __ASSEMBLY__
 
+#define regs_return_value(regs) ((regs)->regs[0])
 #define instruction_pointer(regs) ((regs)->pc)
 #define profile_pc(regs) instruction_pointer(regs)
 #define user_stack_pointer(regs) ((regs)->sp)
 
 /* Does the process account for user or for system time? */
-#define user_mode(regs) (EX1_PL((regs)->ex1) == USER_PL)
+#define user_mode(regs) (EX1_PL((regs)->ex1) < KERNEL_PL)
 
 /* Fill in a struct pt_regs with the current kernel registers. */
 struct pt_regs *get_pt_regs(struct pt_regs *);
@@ -79,8 +80,7 @@ extern void single_step_execve(void);
 
 struct task_struct;
 
-extern void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs,
-			 int error_code);
+extern void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs);
 
 #ifdef __tilegx__
 /* We need this since sigval_t has a user pointer in it, for GETSIGINFO etc. */
diff --git a/arch/tile/include/asm/sections.h b/arch/tile/include/asm/sections.h
index 7d8a935a9238..5d5d3b739a6b 100644
--- a/arch/tile/include/asm/sections.h
+++ b/arch/tile/include/asm/sections.h
@@ -25,10 +25,16 @@ extern char _sinitdata[], _einitdata[];
 /* Write-once data is writable only till the end of initialization. */
 extern char __w1data_begin[], __w1data_end[];
 
+extern char vdso_start[], vdso_end[];
+#ifdef CONFIG_COMPAT
+extern char vdso32_start[], vdso32_end[];
+#endif
 
 /* Not exactly sections, but PC comparison points in the code. */
 extern char __rt_sigreturn[], __rt_sigreturn_end[];
-#ifndef __tilegx__
+#ifdef __tilegx__
+extern char __start_unalign_asm_code[], __end_unalign_asm_code[];
+#else
 extern char sys_cmpxchg[], __sys_cmpxchg_end[];
 extern char __sys_cmpxchg_grab_lock[];
 extern char __start_atomic_asm_code[], __end_atomic_asm_code[];
diff --git a/arch/tile/include/asm/setup.h b/arch/tile/include/asm/setup.h
index d048888c5d9a..e98909033e5b 100644
--- a/arch/tile/include/asm/setup.h
+++ b/arch/tile/include/asm/setup.h
@@ -24,9 +24,8 @@
  */
 #define MAXMEM_PFN	PFN_DOWN(MAXMEM)
 
+int tile_console_write(const char *buf, int count);
 void early_panic(const char *fmt, ...);
-void warn_early_printk(void);
-void __init disable_early_printk(void);
 
 /* Init-time routine to do tile-specific per-cpu setup. */
 void setup_cpu(int boot);
diff --git a/arch/tile/include/asm/smp.h b/arch/tile/include/asm/smp.h
index 1aa759aeb5b3..9a326b64f7ae 100644
--- a/arch/tile/include/asm/smp.h
+++ b/arch/tile/include/asm/smp.h
@@ -101,10 +101,8 @@ void print_disabled_cpus(void);
 extern struct cpumask cpu_lotar_map;
 #define cpu_is_valid_lotar(cpu) cpumask_test_cpu((cpu), &cpu_lotar_map)
 
-#if CHIP_HAS_CBOX_HOME_MAP()
 /* Which processors are used for hash-for-home mapping */
 extern struct cpumask hash_for_home_map;
-#endif
 
 /* Which cpus can have their cache flushed by hv_flush_remote(). */
 extern struct cpumask cpu_cacheable_map;
diff --git a/arch/tile/include/asm/spinlock_64.h b/arch/tile/include/asm/spinlock_64.h
index 5f8b6a095fd8..9a12b9c7e5d3 100644
--- a/arch/tile/include/asm/spinlock_64.h
+++ b/arch/tile/include/asm/spinlock_64.h
@@ -27,7 +27,7 @@
  * Return the "current" portion of a ticket lock value,
  * i.e. the number that currently owns the lock.
  */
-static inline int arch_spin_current(u32 val)
+static inline u32 arch_spin_current(u32 val)
 {
 	return val >> __ARCH_SPIN_CURRENT_SHIFT;
 }
@@ -36,7 +36,7 @@ static inline int arch_spin_current(u32 val)
  * Return the "next" portion of a ticket lock value,
  * i.e. the number that the next task to try to acquire the lock will get.
  */
-static inline int arch_spin_next(u32 val)
+static inline u32 arch_spin_next(u32 val)
 {
 	return val & __ARCH_SPIN_NEXT_MASK;
 }
diff --git a/arch/tile/include/asm/string.h b/arch/tile/include/asm/string.h
index 7535cf1a30e4..92b271bd9ebd 100644
--- a/arch/tile/include/asm/string.h
+++ b/arch/tile/include/asm/string.h
@@ -21,8 +21,10 @@
 #define __HAVE_ARCH_MEMMOVE
 #define __HAVE_ARCH_STRCHR
 #define __HAVE_ARCH_STRLEN
+#define __HAVE_ARCH_STRNLEN
 
 extern __kernel_size_t strlen(const char *);
+extern __kernel_size_t strnlen(const char *, __kernel_size_t);
 extern char *strchr(const char *s, int c);
 extern void *memchr(const void *s, int c, size_t n);
 extern void *memset(void *, int, __kernel_size_t);
diff --git a/arch/tile/include/asm/thread_info.h b/arch/tile/include/asm/thread_info.h
index d1733dee98a2..b8aa6df3e102 100644
--- a/arch/tile/include/asm/thread_info.h
+++ b/arch/tile/include/asm/thread_info.h
@@ -39,6 +39,11 @@ struct thread_info {
 	struct restart_block	restart_block;
 	struct single_step_state *step_state;	/* single step state
 						   (if non-zero) */
+	int			align_ctl;	/* controls unaligned access */
+#ifdef __tilegx__
+	unsigned long		unalign_jit_tmp[4]; /* temp r0..r3 storage */
+	void __user		*unalign_jit_base; /* unalign fixup JIT base */
+#endif
 };
 
 /*
@@ -56,6 +61,7 @@ struct thread_info {
 		.fn = do_no_restart_syscall,	\
 	},					\
 	.step_state	= NULL,			\
+	.align_ctl	= 0,			\
 }
 
 #define init_thread_info	(init_thread_union.thread_info)
diff --git a/arch/tile/include/asm/topology.h b/arch/tile/include/asm/topology.h
index d5e86c9f74fd..d15c0d8d550f 100644
--- a/arch/tile/include/asm/topology.h
+++ b/arch/tile/include/asm/topology.h
@@ -89,9 +89,6 @@ static inline const struct cpumask *cpumask_of_node(int node)
 #define topology_core_id(cpu)                   (cpu)
 #define topology_core_cpumask(cpu)              ((void)(cpu), cpu_online_mask)
 #define topology_thread_cpumask(cpu)            cpumask_of(cpu)
-
-/* indicates that pointers to the topology struct cpumask maps are valid */
-#define arch_provides_topology_pointers         yes
 #endif
 
 #endif /* _ASM_TILE_TOPOLOGY_H */
diff --git a/arch/tile/include/asm/traps.h b/arch/tile/include/asm/traps.h
index e28c3df4176a..4b99a1c3aab2 100644
--- a/arch/tile/include/asm/traps.h
+++ b/arch/tile/include/asm/traps.h
@@ -15,12 +15,13 @@
 #ifndef _ASM_TILE_TRAPS_H
 #define _ASM_TILE_TRAPS_H
 
+#ifndef __ASSEMBLY__
 #include <arch/chip.h>
 
 /* mm/fault.c */
 void do_page_fault(struct pt_regs *, int fault_num,
 		   unsigned long address, unsigned long write);
-#if CHIP_HAS_TILE_DMA() || CHIP_HAS_SN_PROC()
+#if CHIP_HAS_TILE_DMA()
 void do_async_page_fault(struct pt_regs *);
 #endif
 
@@ -69,6 +70,16 @@ void gx_singlestep_handle(struct pt_regs *, int fault_num);
 
 /* kernel/intvec_64.S */
 void fill_ra_stack(void);
+
+/* Handle unalign data fixup. */
+extern void do_unaligned(struct pt_regs *regs, int vecnum);
+#endif
+
+#endif /* __ASSEMBLY__ */
+
+#ifdef __tilegx__
+/* 128 byte JIT per unalign fixup. */
+#define UNALIGN_JIT_SHIFT    7
 #endif
 
 #endif /* _ASM_TILE_TRAPS_H */
diff --git a/arch/tile/include/asm/uaccess.h b/arch/tile/include/asm/uaccess.h
index e4d44bd7df27..b6cde3209b96 100644
--- a/arch/tile/include/asm/uaccess.h
+++ b/arch/tile/include/asm/uaccess.h
@@ -127,8 +127,10 @@ extern int fixup_exception(struct pt_regs *regs);
 
 #ifdef __LP64__
 #define _ASM_PTR	".quad"
+#define _ASM_ALIGN	".align 8"
 #else
 #define _ASM_PTR	".long"
+#define _ASM_ALIGN	".align 4"
 #endif
 
 #define __get_user_asm(OP, x, ptr, ret)					\
@@ -137,6 +139,7 @@ extern int fixup_exception(struct pt_regs *regs);
 		     "0: { movei %1, 0; movei %0, %3 }\n"		\
 		     "j 9f\n"						\
 		     ".section __ex_table,\"a\"\n"			\
+		     _ASM_ALIGN "\n"					\
 		     _ASM_PTR " 1b, 0b\n"				\
 		     ".popsection\n"					\
 		     "9:"						\
@@ -168,6 +171,7 @@ extern int fixup_exception(struct pt_regs *regs);
 			     "0: { movei %1, 0; movei %2, 0 }\n"	\
 			     "{ movei %0, %4; j 9f }\n"			\
 			     ".section __ex_table,\"a\"\n"		\
+			     ".align 4\n"				\
 			     ".word 1b, 0b\n"				\
 			     ".word 2b, 0b\n"				\
 			     ".popsection\n"				\
@@ -224,6 +228,7 @@ extern int __get_user_bad(void)
 		     ".pushsection .fixup,\"ax\"\n"			\
 		     "0: { movei %0, %3; j 9f }\n"			\
 		     ".section __ex_table,\"a\"\n"			\
+		     _ASM_ALIGN "\n"					\
 		     _ASM_PTR " 1b, 0b\n"				\
 		     ".popsection\n"					\
 		     "9:"						\
@@ -248,6 +253,7 @@ extern int __get_user_bad(void)
 			     ".pushsection .fixup,\"ax\"\n"		\
 			     "0: { movei %0, %4; j 9f }\n"		\
 			     ".section __ex_table,\"a\"\n"		\
+			     ".align 4\n"				\
 			     ".word 1b, 0b\n"				\
 			     ".word 2b, 0b\n"				\
 			     ".popsection\n"				\
@@ -567,37 +573,6 @@ static inline unsigned long __must_check flush_user(
 }
 
 /**
- * inv_user: - Invalidate a block of memory in user space from cache.
- * @mem:   Destination address, in user space.
- * @len:   Number of bytes to invalidate.
- *
- * Returns number of bytes that could not be invalidated.
- * On success, this will be zero.
- *
- * Note that on Tile64, the "inv" operation is in fact a
- * "flush and invalidate", so cache write-backs will occur prior
- * to the cache being marked invalid.
- */
-extern unsigned long inv_user_asm(void __user *mem, unsigned long len);
-static inline unsigned long __must_check __inv_user(
-	void __user *mem, unsigned long len)
-{
-	int retval;
-
-	might_fault();
-	retval = inv_user_asm(mem, len);
-	mb_incoherent();
-	return retval;
-}
-static inline unsigned long __must_check inv_user(
-	void __user *mem, unsigned long len)
-{
-	if (access_ok(VERIFY_WRITE, mem, len))
-		return __inv_user(mem, len);
-	return len;
-}
-
-/**
  * finv_user: - Flush-inval a block of memory in user space from cache.
  * @mem:   Destination address, in user space.
  * @len:   Number of bytes to invalidate.
diff --git a/arch/tile/include/asm/unaligned.h b/arch/tile/include/asm/unaligned.h
index 37dfbe598872..5a58a0d11449 100644
--- a/arch/tile/include/asm/unaligned.h
+++ b/arch/tile/include/asm/unaligned.h
@@ -15,11 +15,15 @@
 #ifndef _ASM_TILE_UNALIGNED_H
 #define _ASM_TILE_UNALIGNED_H
 
-#include <linux/unaligned/le_struct.h>
-#include <linux/unaligned/be_byteshift.h>
-#include <linux/unaligned/generic.h>
-#define get_unaligned	__get_unaligned_le
-#define put_unaligned	__put_unaligned_le
+/*
+ * We could implement faster get_unaligned_[be/le]64 using the ldna
+ * instruction on tilegx; however, we need to either copy all of the
+ * other generic functions to here (which is pretty ugly) or else
+ * modify both the generic code and other arch code to allow arch
+ * specific unaligned data access functions.  Given these functions
+ * are not often called, we'll stick with the generic version.
+ */
+#include <asm-generic/unaligned.h>
 
 /*
  * Is the kernel doing fixups of unaligned accesses?  If <0, no kernel
diff --git a/arch/tile/include/asm/vdso.h b/arch/tile/include/asm/vdso.h
new file mode 100644
index 000000000000..9f6a78d665fa
--- /dev/null
+++ b/arch/tile/include/asm/vdso.h
@@ -0,0 +1,49 @@
+/*
+ * Copyright 2012 Tilera Corporation. All Rights Reserved.
+ *
+ *   This program is free software; you can redistribute it and/or
+ *   modify it under the terms of the GNU General Public License
+ *   as published by the Free Software Foundation, version 2.
+ *
+ *   This program is distributed in the hope that it will be useful, but
+ *   WITHOUT ANY WARRANTY; without even the implied warranty of
+ *   MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ *   NON INFRINGEMENT.  See the GNU General Public License for
+ *   more details.
+ */
+
+#ifndef __TILE_VDSO_H__
+#define __TILE_VDSO_H__
+
+#include <linux/types.h>
+
+/*
+ * Note about the vdso_data structure:
+ *
+ * NEVER USE THEM IN USERSPACE CODE DIRECTLY. The layout of the
+ * structure is supposed to be known only to the function in the vdso
+ * itself and may change without notice.
+ */
+
+struct vdso_data {
+	__u64 tz_update_count;  /* Timezone atomicity ctr             */
+	__u64 tb_update_count;  /* Timebase atomicity ctr             */
+	__u64 xtime_tod_stamp;  /* TOD clock for xtime                */
+	__u64 xtime_clock_sec;  /* Kernel time second                 */
+	__u64 xtime_clock_nsec; /* Kernel time nanosecond             */
+	__u64 wtom_clock_sec;   /* Wall to monotonic clock second     */
+	__u64 wtom_clock_nsec;  /* Wall to monotonic clock nanosecond */
+	__u32 mult;             /* Cycle to nanosecond multiplier     */
+	__u32 shift;            /* Cycle to nanosecond divisor (power of two) */
+	__u32 tz_minuteswest;   /* Minutes west of Greenwich          */
+	__u32 tz_dsttime;       /* Type of dst correction             */
+};
+
+extern struct vdso_data *vdso_data;
+
+/* __vdso_rt_sigreturn is defined with the addresses in the vdso page. */
+extern void __vdso_rt_sigreturn(void);
+
+extern int setup_vdso_pages(void);
+
+#endif /* __TILE_VDSO_H__ */
diff --git a/arch/tile/include/gxio/iorpc_mpipe.h b/arch/tile/include/gxio/iorpc_mpipe.h
index 9d50fce1b1a7..4cda03de734f 100644
--- a/arch/tile/include/gxio/iorpc_mpipe.h
+++ b/arch/tile/include/gxio/iorpc_mpipe.h
@@ -44,93 +44,101 @@
 #define GXIO_MPIPE_OP_REGISTER_CLIENT_MEMORY IORPC_OPCODE(IORPC_FORMAT_NONE_NOUSER, 0x1210)
 #define GXIO_MPIPE_OP_LINK_OPEN_AUX    IORPC_OPCODE(IORPC_FORMAT_NONE, 0x1211)
 #define GXIO_MPIPE_OP_LINK_CLOSE_AUX   IORPC_OPCODE(IORPC_FORMAT_NONE, 0x1212)
+#define GXIO_MPIPE_OP_LINK_SET_ATTR_AUX IORPC_OPCODE(IORPC_FORMAT_NONE, 0x1213)
 
-#define GXIO_MPIPE_OP_GET_TIMESTAMP_AUX IORPC_OPCODE(IORPC_FORMAT_NONE_NOUSER, 0x121e)
-#define GXIO_MPIPE_OP_SET_TIMESTAMP_AUX IORPC_OPCODE(IORPC_FORMAT_NONE_NOUSER, 0x121f)
-#define GXIO_MPIPE_OP_ADJUST_TIMESTAMP_AUX IORPC_OPCODE(IORPC_FORMAT_NONE_NOUSER, 0x1220)
+#define GXIO_MPIPE_OP_GET_TIMESTAMP_AUX IORPC_OPCODE(IORPC_FORMAT_NONE, 0x121e)
+#define GXIO_MPIPE_OP_SET_TIMESTAMP_AUX IORPC_OPCODE(IORPC_FORMAT_NONE, 0x121f)
+#define GXIO_MPIPE_OP_ADJUST_TIMESTAMP_AUX IORPC_OPCODE(IORPC_FORMAT_NONE, 0x1220)
+#define GXIO_MPIPE_OP_CONFIG_EDMA_RING_BLKS IORPC_OPCODE(IORPC_FORMAT_NONE, 0x1221)
+#define GXIO_MPIPE_OP_ADJUST_TIMESTAMP_FREQ IORPC_OPCODE(IORPC_FORMAT_NONE, 0x1222)
 #define GXIO_MPIPE_OP_ARM_POLLFD       IORPC_OPCODE(IORPC_FORMAT_KERNEL_POLLFD, 0x9000)
 #define GXIO_MPIPE_OP_CLOSE_POLLFD     IORPC_OPCODE(IORPC_FORMAT_KERNEL_POLLFD, 0x9001)
 #define GXIO_MPIPE_OP_GET_MMIO_BASE    IORPC_OPCODE(IORPC_FORMAT_NONE_NOUSER, 0x8000)
 #define GXIO_MPIPE_OP_CHECK_MMIO_OFFSET IORPC_OPCODE(IORPC_FORMAT_NONE_NOUSER, 0x8001)
 
-int gxio_mpipe_alloc_buffer_stacks(gxio_mpipe_context_t * context,
+int gxio_mpipe_alloc_buffer_stacks(gxio_mpipe_context_t *context,
 				   unsigned int count, unsigned int first,
 				   unsigned int flags);
 
-int gxio_mpipe_init_buffer_stack_aux(gxio_mpipe_context_t * context,
+int gxio_mpipe_init_buffer_stack_aux(gxio_mpipe_context_t *context,
 				     void *mem_va, size_t mem_size,
 				     unsigned int mem_flags, unsigned int stack,
 				     unsigned int buffer_size_enum);
 
 
-int gxio_mpipe_alloc_notif_rings(gxio_mpipe_context_t * context,
+int gxio_mpipe_alloc_notif_rings(gxio_mpipe_context_t *context,
 				 unsigned int count, unsigned int first,
 				 unsigned int flags);
 
-int gxio_mpipe_init_notif_ring_aux(gxio_mpipe_context_t * context, void *mem_va,
+int gxio_mpipe_init_notif_ring_aux(gxio_mpipe_context_t *context, void *mem_va,
 				   size_t mem_size, unsigned int mem_flags,
 				   unsigned int ring);
 
-int gxio_mpipe_request_notif_ring_interrupt(gxio_mpipe_context_t * context,
+int gxio_mpipe_request_notif_ring_interrupt(gxio_mpipe_context_t *context,
 					    int inter_x, int inter_y,
 					    int inter_ipi, int inter_event,
 					    unsigned int ring);
 
-int gxio_mpipe_enable_notif_ring_interrupt(gxio_mpipe_context_t * context,
+int gxio_mpipe_enable_notif_ring_interrupt(gxio_mpipe_context_t *context,
 					   unsigned int ring);
 
-int gxio_mpipe_alloc_notif_groups(gxio_mpipe_context_t * context,
+int gxio_mpipe_alloc_notif_groups(gxio_mpipe_context_t *context,
 				  unsigned int count, unsigned int first,
 				  unsigned int flags);
 
-int gxio_mpipe_init_notif_group(gxio_mpipe_context_t * context,
+int gxio_mpipe_init_notif_group(gxio_mpipe_context_t *context,
 				unsigned int group,
 				gxio_mpipe_notif_group_bits_t bits);
 
-int gxio_mpipe_alloc_buckets(gxio_mpipe_context_t * context, unsigned int count,
+int gxio_mpipe_alloc_buckets(gxio_mpipe_context_t *context, unsigned int count,
 			     unsigned int first, unsigned int flags);
 
-int gxio_mpipe_init_bucket(gxio_mpipe_context_t * context, unsigned int bucket,
+int gxio_mpipe_init_bucket(gxio_mpipe_context_t *context, unsigned int bucket,
 			   MPIPE_LBL_INIT_DAT_BSTS_TBL_t bucket_info);
 
-int gxio_mpipe_alloc_edma_rings(gxio_mpipe_context_t * context,
+int gxio_mpipe_alloc_edma_rings(gxio_mpipe_context_t *context,
 				unsigned int count, unsigned int first,
 				unsigned int flags);
 
-int gxio_mpipe_init_edma_ring_aux(gxio_mpipe_context_t * context, void *mem_va,
+int gxio_mpipe_init_edma_ring_aux(gxio_mpipe_context_t *context, void *mem_va,
 				  size_t mem_size, unsigned int mem_flags,
 				  unsigned int ring, unsigned int channel);
 
 
-int gxio_mpipe_commit_rules(gxio_mpipe_context_t * context, const void *blob,
+int gxio_mpipe_commit_rules(gxio_mpipe_context_t *context, const void *blob,
 			    size_t blob_size);
 
-int gxio_mpipe_register_client_memory(gxio_mpipe_context_t * context,
+int gxio_mpipe_register_client_memory(gxio_mpipe_context_t *context,
 				      unsigned int iotlb, HV_PTE pte,
 				      unsigned int flags);
 
-int gxio_mpipe_link_open_aux(gxio_mpipe_context_t * context,
+int gxio_mpipe_link_open_aux(gxio_mpipe_context_t *context,
 			     _gxio_mpipe_link_name_t name, unsigned int flags);
 
-int gxio_mpipe_link_close_aux(gxio_mpipe_context_t * context, int mac);
+int gxio_mpipe_link_close_aux(gxio_mpipe_context_t *context, int mac);
 
+int gxio_mpipe_link_set_attr_aux(gxio_mpipe_context_t *context, int mac,
+				 uint32_t attr, int64_t val);
 
-int gxio_mpipe_get_timestamp_aux(gxio_mpipe_context_t * context, uint64_t * sec,
-				 uint64_t * nsec, uint64_t * cycles);
+int gxio_mpipe_get_timestamp_aux(gxio_mpipe_context_t *context, uint64_t *sec,
+				 uint64_t *nsec, uint64_t *cycles);
 
-int gxio_mpipe_set_timestamp_aux(gxio_mpipe_context_t * context, uint64_t sec,
+int gxio_mpipe_set_timestamp_aux(gxio_mpipe_context_t *context, uint64_t sec,
 				 uint64_t nsec, uint64_t cycles);
 
-int gxio_mpipe_adjust_timestamp_aux(gxio_mpipe_context_t * context,
+int gxio_mpipe_adjust_timestamp_aux(gxio_mpipe_context_t *context,
 				    int64_t nsec);
 
-int gxio_mpipe_arm_pollfd(gxio_mpipe_context_t * context, int pollfd_cookie);
+int gxio_mpipe_adjust_timestamp_freq(gxio_mpipe_context_t *context,
+				     int32_t ppb);
 
-int gxio_mpipe_close_pollfd(gxio_mpipe_context_t * context, int pollfd_cookie);
+int gxio_mpipe_arm_pollfd(gxio_mpipe_context_t *context, int pollfd_cookie);
 
-int gxio_mpipe_get_mmio_base(gxio_mpipe_context_t * context, HV_PTE *base);
+int gxio_mpipe_close_pollfd(gxio_mpipe_context_t *context, int pollfd_cookie);
 
-int gxio_mpipe_check_mmio_offset(gxio_mpipe_context_t * context,
+int gxio_mpipe_get_mmio_base(gxio_mpipe_context_t *context, HV_PTE *base);
+
+int gxio_mpipe_check_mmio_offset(gxio_mpipe_context_t *context,
 				 unsigned long offset, unsigned long size);
 
 #endif /* !__GXIO_MPIPE_LINUX_RPC_H__ */
diff --git a/arch/tile/include/gxio/iorpc_mpipe_info.h b/arch/tile/include/gxio/iorpc_mpipe_info.h
index 0bcf3f71ce8b..f0b04284468b 100644
--- a/arch/tile/include/gxio/iorpc_mpipe_info.h
+++ b/arch/tile/include/gxio/iorpc_mpipe_info.h
@@ -27,20 +27,24 @@
 #include <asm/pgtable.h>
 
 
+#define GXIO_MPIPE_INFO_OP_INSTANCE_AUX IORPC_OPCODE(IORPC_FORMAT_NONE, 0x1250)
 #define GXIO_MPIPE_INFO_OP_ENUMERATE_AUX IORPC_OPCODE(IORPC_FORMAT_NONE, 0x1251)
 #define GXIO_MPIPE_INFO_OP_GET_MMIO_BASE IORPC_OPCODE(IORPC_FORMAT_NONE_NOUSER, 0x8000)
 #define GXIO_MPIPE_INFO_OP_CHECK_MMIO_OFFSET IORPC_OPCODE(IORPC_FORMAT_NONE_NOUSER, 0x8001)
 
 
-int gxio_mpipe_info_enumerate_aux(gxio_mpipe_info_context_t * context,
+int gxio_mpipe_info_instance_aux(gxio_mpipe_info_context_t *context,
+				 _gxio_mpipe_link_name_t name);
+
+int gxio_mpipe_info_enumerate_aux(gxio_mpipe_info_context_t *context,
 				  unsigned int idx,
-				  _gxio_mpipe_link_name_t * name,
-				  _gxio_mpipe_link_mac_t * mac);
+				  _gxio_mpipe_link_name_t *name,
+				  _gxio_mpipe_link_mac_t *mac);
 
-int gxio_mpipe_info_get_mmio_base(gxio_mpipe_info_context_t * context,
+int gxio_mpipe_info_get_mmio_base(gxio_mpipe_info_context_t *context,
 				  HV_PTE *base);
 
-int gxio_mpipe_info_check_mmio_offset(gxio_mpipe_info_context_t * context,
+int gxio_mpipe_info_check_mmio_offset(gxio_mpipe_info_context_t *context,
 				      unsigned long offset, unsigned long size);
 
 #endif /* !__GXIO_MPIPE_INFO_LINUX_RPC_H__ */
diff --git a/arch/tile/include/gxio/iorpc_trio.h b/arch/tile/include/gxio/iorpc_trio.h
index 58105c31228b..376a4f771167 100644
--- a/arch/tile/include/gxio/iorpc_trio.h
+++ b/arch/tile/include/gxio/iorpc_trio.h
@@ -30,6 +30,7 @@
 
 #define GXIO_TRIO_OP_ALLOC_MEMORY_MAPS IORPC_OPCODE(IORPC_FORMAT_NONE, 0x1404)
 
+#define GXIO_TRIO_OP_ALLOC_SCATTER_QUEUES IORPC_OPCODE(IORPC_FORMAT_NONE, 0x140e)
 #define GXIO_TRIO_OP_ALLOC_PIO_REGIONS IORPC_OPCODE(IORPC_FORMAT_NONE, 0x1412)
 
 #define GXIO_TRIO_OP_INIT_PIO_REGION_AUX IORPC_OPCODE(IORPC_FORMAT_NONE, 0x1414)
@@ -45,55 +46,59 @@
 #define GXIO_TRIO_OP_GET_MMIO_BASE     IORPC_OPCODE(IORPC_FORMAT_NONE_NOUSER, 0x8000)
 #define GXIO_TRIO_OP_CHECK_MMIO_OFFSET IORPC_OPCODE(IORPC_FORMAT_NONE_NOUSER, 0x8001)
 
-int gxio_trio_alloc_asids(gxio_trio_context_t * context, unsigned int count,
+int gxio_trio_alloc_asids(gxio_trio_context_t *context, unsigned int count,
 			  unsigned int first, unsigned int flags);
 
 
-int gxio_trio_alloc_memory_maps(gxio_trio_context_t * context,
+int gxio_trio_alloc_memory_maps(gxio_trio_context_t *context,
 				unsigned int count, unsigned int first,
 				unsigned int flags);
 
 
-int gxio_trio_alloc_pio_regions(gxio_trio_context_t * context,
+int gxio_trio_alloc_scatter_queues(gxio_trio_context_t *context,
+				   unsigned int count, unsigned int first,
+				   unsigned int flags);
+
+int gxio_trio_alloc_pio_regions(gxio_trio_context_t *context,
 				unsigned int count, unsigned int first,
 				unsigned int flags);
 
-int gxio_trio_init_pio_region_aux(gxio_trio_context_t * context,
+int gxio_trio_init_pio_region_aux(gxio_trio_context_t *context,
 				  unsigned int pio_region, unsigned int mac,
 				  uint32_t bus_address_hi, unsigned int flags);
 
 
-int gxio_trio_init_memory_map_mmu_aux(gxio_trio_context_t * context,
+int gxio_trio_init_memory_map_mmu_aux(gxio_trio_context_t *context,
 				      unsigned int map, unsigned long va,
 				      uint64_t size, unsigned int asid,
 				      unsigned int mac, uint64_t bus_address,
 				      unsigned int node,
 				      unsigned int order_mode);
 
-int gxio_trio_get_port_property(gxio_trio_context_t * context,
+int gxio_trio_get_port_property(gxio_trio_context_t *context,
 				struct pcie_trio_ports_property *trio_ports);
 
-int gxio_trio_config_legacy_intr(gxio_trio_context_t * context, int inter_x,
+int gxio_trio_config_legacy_intr(gxio_trio_context_t *context, int inter_x,
 				 int inter_y, int inter_ipi, int inter_event,
 				 unsigned int mac, unsigned int intx);
 
-int gxio_trio_config_msi_intr(gxio_trio_context_t * context, int inter_x,
+int gxio_trio_config_msi_intr(gxio_trio_context_t *context, int inter_x,
 			      int inter_y, int inter_ipi, int inter_event,
 			      unsigned int mac, unsigned int mem_map,
 			      uint64_t mem_map_base, uint64_t mem_map_limit,
 			      unsigned int asid);
 
 
-int gxio_trio_set_mps_mrs(gxio_trio_context_t * context, uint16_t mps,
+int gxio_trio_set_mps_mrs(gxio_trio_context_t *context, uint16_t mps,
 			  uint16_t mrs, unsigned int mac);
 
-int gxio_trio_force_rc_link_up(gxio_trio_context_t * context, unsigned int mac);
+int gxio_trio_force_rc_link_up(gxio_trio_context_t *context, unsigned int mac);
 
-int gxio_trio_force_ep_link_up(gxio_trio_context_t * context, unsigned int mac);
+int gxio_trio_force_ep_link_up(gxio_trio_context_t *context, unsigned int mac);
 
-int gxio_trio_get_mmio_base(gxio_trio_context_t * context, HV_PTE *base);
+int gxio_trio_get_mmio_base(gxio_trio_context_t *context, HV_PTE *base);
 
-int gxio_trio_check_mmio_offset(gxio_trio_context_t * context,
+int gxio_trio_check_mmio_offset(gxio_trio_context_t *context,
 				unsigned long offset, unsigned long size);
 
 #endif /* !__GXIO_TRIO_LINUX_RPC_H__ */
diff --git a/arch/tile/include/gxio/iorpc_uart.h b/arch/tile/include/gxio/iorpc_uart.h
new file mode 100644
index 000000000000..55429d48ea56
--- /dev/null
+++ b/arch/tile/include/gxio/iorpc_uart.h
@@ -0,0 +1,40 @@
+/*
+ * Copyright 2013 Tilera Corporation. All Rights Reserved.
+ *
+ *   This program is free software; you can redistribute it and/or
+ *   modify it under the terms of the GNU General Public License
+ *   as published by the Free Software Foundation, version 2.
+ *
+ *   This program is distributed in the hope that it will be useful, but
+ *   WITHOUT ANY WARRANTY; without even the implied warranty of
+ *   MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ *   NON INFRINGEMENT.  See the GNU General Public License for
+ *   more details.
+ */
+
+/* This file is machine-generated; DO NOT EDIT! */
+#ifndef __GXIO_UART_LINUX_RPC_H__
+#define __GXIO_UART_LINUX_RPC_H__
+
+#include <hv/iorpc.h>
+
+#include <hv/drv_uart_intf.h>
+#include <gxio/uart.h>
+#include <gxio/kiorpc.h>
+#include <linux/string.h>
+#include <linux/module.h>
+#include <asm/pgtable.h>
+
+#define GXIO_UART_OP_CFG_INTERRUPT     IORPC_OPCODE(IORPC_FORMAT_KERNEL_INTERRUPT, 0x1900)
+#define GXIO_UART_OP_GET_MMIO_BASE     IORPC_OPCODE(IORPC_FORMAT_NONE_NOUSER, 0x8000)
+#define GXIO_UART_OP_CHECK_MMIO_OFFSET IORPC_OPCODE(IORPC_FORMAT_NONE_NOUSER, 0x8001)
+
+int gxio_uart_cfg_interrupt(gxio_uart_context_t *context, int inter_x,
+			    int inter_y, int inter_ipi, int inter_event);
+
+int gxio_uart_get_mmio_base(gxio_uart_context_t *context, HV_PTE *base);
+
+int gxio_uart_check_mmio_offset(gxio_uart_context_t *context,
+				unsigned long offset, unsigned long size);
+
+#endif /* !__GXIO_UART_LINUX_RPC_H__ */
diff --git a/arch/tile/include/gxio/iorpc_usb_host.h b/arch/tile/include/gxio/iorpc_usb_host.h
index 8622e7d126ad..79962a97de8e 100644
--- a/arch/tile/include/gxio/iorpc_usb_host.h
+++ b/arch/tile/include/gxio/iorpc_usb_host.h
@@ -31,16 +31,16 @@
 #define GXIO_USB_HOST_OP_GET_MMIO_BASE IORPC_OPCODE(IORPC_FORMAT_NONE_NOUSER, 0x8000)
 #define GXIO_USB_HOST_OP_CHECK_MMIO_OFFSET IORPC_OPCODE(IORPC_FORMAT_NONE_NOUSER, 0x8001)
 
-int gxio_usb_host_cfg_interrupt(gxio_usb_host_context_t * context, int inter_x,
+int gxio_usb_host_cfg_interrupt(gxio_usb_host_context_t *context, int inter_x,
 				int inter_y, int inter_ipi, int inter_event);
 
-int gxio_usb_host_register_client_memory(gxio_usb_host_context_t * context,
+int gxio_usb_host_register_client_memory(gxio_usb_host_context_t *context,
 					 HV_PTE pte, unsigned int flags);
 
-int gxio_usb_host_get_mmio_base(gxio_usb_host_context_t * context,
+int gxio_usb_host_get_mmio_base(gxio_usb_host_context_t *context,
 				HV_PTE *base);
 
-int gxio_usb_host_check_mmio_offset(gxio_usb_host_context_t * context,
+int gxio_usb_host_check_mmio_offset(gxio_usb_host_context_t *context,
 				    unsigned long offset, unsigned long size);
 
 #endif /* !__GXIO_USB_HOST_LINUX_RPC_H__ */
diff --git a/arch/tile/include/gxio/mpipe.h b/arch/tile/include/gxio/mpipe.h
index b74f470ed11e..e37cf4f0cffd 100644
--- a/arch/tile/include/gxio/mpipe.h
+++ b/arch/tile/include/gxio/mpipe.h
@@ -220,6 +220,13 @@ typedef MPIPE_PDESC_t gxio_mpipe_idesc_t;
  */
 typedef MPIPE_EDMA_DESC_t gxio_mpipe_edesc_t;
 
+/*
+ * Max # of mpipe instances. 2 currently.
+ */
+#define GXIO_MPIPE_INSTANCE_MAX  HV_MPIPE_INSTANCE_MAX
+
+#define NR_MPIPE_MAX   GXIO_MPIPE_INSTANCE_MAX
+
 /* Get the "va" field from an "idesc".
  *
  * This is the address at which the ingress hardware copied the first
@@ -311,6 +318,9 @@ typedef struct {
 	/* File descriptor for calling up to Linux (and thus the HV). */
 	int fd;
 
+	/* Corresponding mpipe instance #. */
+	int instance;
+
 	/* The VA at which configuration registers are mapped. */
 	char *mmio_cfg_base;
 
@@ -810,7 +820,7 @@ extern int gxio_mpipe_alloc_edma_rings(gxio_mpipe_context_t *context,
 /* Initialize an eDMA ring, using the given memory and size.
  *
  * @param context An initialized mPIPE context.
- * @param ring The eDMA ring index.
+ * @param ering The eDMA ring index.
  * @param channel The channel to use.  This must be one of the channels
  * associated with the context's set of open links.
  * @param mem A physically contiguous region of memory to be filled
@@ -823,10 +833,37 @@ extern int gxio_mpipe_alloc_edma_rings(gxio_mpipe_context_t *context,
  * ::GXIO_ERR_INVAL_MEMORY_SIZE on failure.
  */
 extern int gxio_mpipe_init_edma_ring(gxio_mpipe_context_t *context,
-				     unsigned int ring, unsigned int channel,
+				     unsigned int ering, unsigned int channel,
 				     void *mem, size_t mem_size,
 				     unsigned int mem_flags);
 
+/* Set the "max_blks", "min_snf_blks", and "db" fields of
+ * ::MPIPE_EDMA_RG_INIT_DAT_THRESH_t for a given edma ring.
+ *
+ * The global pool of dynamic blocks will be automatically adjusted.
+ *
+ * This function should not be called after any egress has been done
+ * on the edma ring.
+ *
+ * Most applications should just use gxio_mpipe_equeue_set_snf_size().
+ *
+ * @param context An initialized mPIPE context.
+ * @param ering The eDMA ring index.
+ * @param max_blks The number of blocks to dedicate to the ring
+ * (normally min_snf_blks + 1).  Must be greater than min_snf_blocks.
+ * @param min_snf_blks The number of blocks which must be stored
+ * prior to starting to send the packet (normally 12).
+ * @param db Whether to allow use of dynamic blocks by the ring
+ * (normally 1).
+ *
+ * @return 0 on success, negative on error.
+ */
+extern int gxio_mpipe_config_edma_ring_blks(gxio_mpipe_context_t *context,
+					    unsigned int ering,
+					    unsigned int max_blks,
+					    unsigned int min_snf_blks,
+					    unsigned int db);
+
 /*****************************************************************
  *                      Classifier Program                        *
  ******************************************************************/
@@ -1288,15 +1325,39 @@ typedef struct {
 	/* The log2() of the number of entries. */
 	unsigned long log2_num_entries;
 
+	/* The context. */
+	gxio_mpipe_context_t *context;
+
+	/* The ering. */
+	unsigned int ering;
+
+	/* The channel. */
+	unsigned int channel;
+
 } gxio_mpipe_equeue_t;
 
 /* Initialize an "equeue".
  *
- * Takes the equeue plus the same args as gxio_mpipe_init_edma_ring().
+ * This function uses gxio_mpipe_init_edma_ring() to initialize the
+ * underlying edma_ring using the provided arguments.
+ *
+ * @param equeue An egress queue to be initialized.
+ * @param context An initialized mPIPE context.
+ * @param ering The eDMA ring index.
+ * @param channel The channel to use.  This must be one of the channels
+ * associated with the context's set of open links.
+ * @param mem A physically contiguous region of memory to be filled
+ * with a ring of ::gxio_mpipe_edesc_t structures.
+ * @param mem_size Number of bytes in the ring.  Must be 512, 2048,
+ * 8192 or 65536, times 16 (i.e. sizeof(gxio_mpipe_edesc_t)).
+ * @param mem_flags ::gxio_mpipe_mem_flags_e memory flags.
+ *
+ * @return 0 on success, ::GXIO_MPIPE_ERR_BAD_EDMA_RING or
+ * ::GXIO_ERR_INVAL_MEMORY_SIZE on failure.
  */
 extern int gxio_mpipe_equeue_init(gxio_mpipe_equeue_t *equeue,
 				  gxio_mpipe_context_t *context,
-				  unsigned int edma_ring_id,
+				  unsigned int ering,
 				  unsigned int channel,
 				  void *mem, unsigned int mem_size,
 				  unsigned int mem_flags);
@@ -1494,6 +1555,37 @@ static inline int gxio_mpipe_equeue_is_complete(gxio_mpipe_equeue_t *equeue,
 					    completion_slot, update);
 }
 
+/* Set the snf (store and forward) size for an equeue.
+ *
+ * The snf size for an equeue defaults to 1536, and encodes the size
+ * of the largest packet for which egress is guaranteed to avoid
+ * transmission underruns and/or corrupt checksums under heavy load.
+ *
+ * The snf size affects a global resource pool which cannot support,
+ * for example, all 24 equeues each requesting an snf size of 8K.
+ *
+ * To ensure that jumbo packets can be egressed properly, the snf size
+ * should be set to the size of the largest possible packet, which
+ * will usually be limited by the size of the app's largest buffer.
+ *
+ * This is a convenience wrapper around
+ * gxio_mpipe_config_edma_ring_blks().
+ *
+ * This function should not be called after any egress has been done
+ * on the equeue.
+ *
+ * @param equeue An egress queue initialized via gxio_mpipe_equeue_init().
+ * @param size The snf size, in bytes.
+ * @return Zero on success, negative error otherwise.
+ */
+static inline int gxio_mpipe_equeue_set_snf_size(gxio_mpipe_equeue_t *equeue,
+						 size_t size)
+{
+	int blks = (size + 127) / 128;
+	return gxio_mpipe_config_edma_ring_blks(equeue->context, equeue->ering,
+						blks + 1, blks, 1);
+}
+
 /*****************************************************************
  *                        Link Management                         *
  ******************************************************************/
@@ -1634,6 +1726,24 @@ typedef struct {
 	uint8_t mac;
 } gxio_mpipe_link_t;
 
+/* Translate a link name to the instance number of the mPIPE shim which is
+ *  connected to that link.  This call does not verify whether the link is
+ *  currently available, and does not reserve any link resources;
+ *  gxio_mpipe_link_open() must be called to perform those functions.
+ *
+ *  Typically applications will call this function to translate a link name
+ *  to an mPIPE instance number; call gxio_mpipe_init(), passing it that
+ *  instance number, to initialize the mPIPE shim; and then call
+ *  gxio_mpipe_link_open(), passing it the same link name plus the mPIPE
+ *  context, to configure the link.
+ *
+ * @param link_name Name of the link; see @ref gxio_mpipe_link_names.
+ * @return The mPIPE instance number which is associated with the named
+ *  link, or a negative error code (::GXIO_ERR_NO_DEVICE) if the link does
+ *  not exist.
+ */
+extern int gxio_mpipe_link_instance(const char *link_name);
+
 /* Retrieve one of this system's legal link names, and its MAC address.
  *
  * @param index Link name index.  If a system supports N legal link names,
@@ -1697,6 +1807,17 @@ static inline int gxio_mpipe_link_channel(gxio_mpipe_link_t *link)
 	return link->channel;
 }
 
+/* Set a link attribute.
+ *
+ * @param link A properly initialized link state object.
+ * @param attr An attribute from the set of @ref gxio_mpipe_link_attrs.
+ * @param val New value of the attribute.
+ * @return 0 if the attribute was successfully set, or a negative error
+ *  code.
+ */
+extern int gxio_mpipe_link_set_attr(gxio_mpipe_link_t *link, uint32_t attr,
+				    int64_t val);
+
 ///////////////////////////////////////////////////////////////////
 //                             Timestamp                         //
 ///////////////////////////////////////////////////////////////////
@@ -1733,4 +1854,18 @@ extern int gxio_mpipe_set_timestamp(gxio_mpipe_context_t *context,
 extern int gxio_mpipe_adjust_timestamp(gxio_mpipe_context_t *context,
 				       int64_t delta);
 
+/** Adjust the mPIPE timestamp clock frequency.
+ *
+ * @param context An initialized mPIPE context.
+ * @param ppb A 32-bit signed PPB (Parts Per Billion) value to adjust.
+ * The absolute value of ppb must be less than or equal to 1000000000.
+ * Values less than about 30000 will generally cause a GXIO_ERR_INVAL
+ * return due to the granularity of the hardware that converts reference
+ * clock cycles into seconds and nanoseconds.
+ * @return If the call was successful, zero; otherwise, a negative error
+ *  code.
+ */
+extern int gxio_mpipe_adjust_timestamp_freq(gxio_mpipe_context_t* context,
+                                            int32_t ppb);
+
 #endif /* !_GXIO_MPIPE_H_ */
diff --git a/arch/tile/include/gxio/uart.h b/arch/tile/include/gxio/uart.h
new file mode 100644
index 000000000000..438ee7e46c7b
--- /dev/null
+++ b/arch/tile/include/gxio/uart.h
@@ -0,0 +1,105 @@
+/*
+ * Copyright 2013 Tilera Corporation. All Rights Reserved.
+ *
+ *   This program is free software; you can redistribute it and/or
+ *   modify it under the terms of the GNU General Public License
+ *   as published by the Free Software Foundation, version 2.
+ *
+ *   This program is distributed in the hope that it will be useful, but
+ *   WITHOUT ANY WARRANTY; without even the implied warranty of
+ *   MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ *   NON INFRINGEMENT.  See the GNU General Public License for
+ *   more details.
+ */
+
+#ifndef _GXIO_UART_H_
+#define _GXIO_UART_H_
+
+#include "common.h"
+
+#include <hv/drv_uart_intf.h>
+#include <hv/iorpc.h>
+
+/*
+ *
+ * An API for manipulating UART interface.
+ */
+
+/*
+ *
+ * The Rshim allows access to the processor's UART interface.
+ */
+
+/* A context object used to manage UART resources. */
+typedef struct {
+
+	/* File descriptor for calling up to the hypervisor. */
+	int fd;
+
+	/* The VA at which our MMIO registers are mapped. */
+	char *mmio_base;
+
+} gxio_uart_context_t;
+
+/* Request UART interrupts.
+ *
+ *  Request that interrupts be delivered to a tile when the UART's
+ *  Receive FIFO is written, or the Write FIFO is read.
+ *
+ * @param context Pointer to a properly initialized gxio_uart_context_t.
+ * @param bind_cpu_x X coordinate of CPU to which interrupt will be delivered.
+ * @param bind_cpu_y Y coordinate of CPU to which interrupt will be delivered.
+ * @param bind_interrupt IPI interrupt number.
+ * @param bind_event Sub-interrupt event bit number; a negative value can
+ *  disable the interrupt.
+ * @return Zero if all of the requested UART events were successfully
+ *  configured to interrupt.
+ */
+extern int gxio_uart_cfg_interrupt(gxio_uart_context_t *context,
+				   int bind_cpu_x,
+				   int bind_cpu_y,
+				   int bind_interrupt, int bind_event);
+
+/* Initialize a UART context.
+ *
+ *  A properly initialized context must be obtained before any of the other
+ *  gxio_uart routines may be used.
+ *
+ * @param context Pointer to a gxio_uart_context_t, which will be initialized
+ *  by this routine, if it succeeds.
+ * @param uart_index Index of the UART to use.
+ * @return Zero if the context was successfully initialized, else a
+ *  GXIO_ERR_xxx error code.
+ */
+extern int gxio_uart_init(gxio_uart_context_t *context, int uart_index);
+
+/* Destroy a UART context.
+ *
+ *  Once destroyed, a context may not be used with any gxio_uart routines
+ *  other than gxio_uart_init().  After this routine returns, no further
+ *  interrupts requested on this context will be delivered.  The state and
+ *  configuration of the pins which had been attached to this context are
+ *  unchanged by this operation.
+ *
+ * @param context Pointer to a gxio_uart_context_t.
+ * @return Zero if the context was successfully destroyed, else a
+ *  GXIO_ERR_xxx error code.
+ */
+extern int gxio_uart_destroy(gxio_uart_context_t *context);
+
+/* Write UART register.
+ * @param context Pointer to a gxio_uart_context_t.
+ * @param offset UART register offset.
+ * @param word Data will be wrote to UART reigister.
+ */
+extern void gxio_uart_write(gxio_uart_context_t *context, uint64_t offset,
+			    uint64_t word);
+
+/* Read UART register.
+ * @param context Pointer to a gxio_uart_context_t.
+ * @param offset UART register offset.
+ * @return Data read from UART register.
+ */
+extern uint64_t gxio_uart_read(gxio_uart_context_t *context, uint64_t offset);
+
+#endif /* _GXIO_UART_H_ */
diff --git a/arch/tile/include/gxio/usb_host.h b/arch/tile/include/gxio/usb_host.h
index 5eedec0e988e..93c9636d2dd7 100644
--- a/arch/tile/include/gxio/usb_host.h
+++ b/arch/tile/include/gxio/usb_host.h
@@ -53,7 +53,7 @@ typedef struct {
  * @return Zero if the context was successfully initialized, else a
  *  GXIO_ERR_xxx error code.
  */
-extern int gxio_usb_host_init(gxio_usb_host_context_t * context, int usb_index,
+extern int gxio_usb_host_init(gxio_usb_host_context_t *context, int usb_index,
 			      int is_ehci);
 
 /* Destroy a USB context.
@@ -68,20 +68,20 @@ extern int gxio_usb_host_init(gxio_usb_host_context_t * context, int usb_index,
  * @return Zero if the context was successfully destroyed, else a
  *  GXIO_ERR_xxx error code.
  */
-extern int gxio_usb_host_destroy(gxio_usb_host_context_t * context);
+extern int gxio_usb_host_destroy(gxio_usb_host_context_t *context);
 
 /* Retrieve the address of the shim's MMIO registers.
  *
  * @param context Pointer to a properly initialized gxio_usb_host_context_t.
  * @return The address of the shim's MMIO registers.
  */
-extern void *gxio_usb_host_get_reg_start(gxio_usb_host_context_t * context);
+extern void *gxio_usb_host_get_reg_start(gxio_usb_host_context_t *context);
 
 /* Retrieve the length of the shim's MMIO registers.
  *
  * @param context Pointer to a properly initialized gxio_usb_host_context_t.
  * @return The length of the shim's MMIO registers.
  */
-extern size_t gxio_usb_host_get_reg_len(gxio_usb_host_context_t * context);
+extern size_t gxio_usb_host_get_reg_len(gxio_usb_host_context_t *context);
 
 #endif /* _GXIO_USB_H_ */
diff --git a/arch/tile/include/hv/drv_mpipe_intf.h b/arch/tile/include/hv/drv_mpipe_intf.h
index 6cdae3bf046e..c97e416dd963 100644
--- a/arch/tile/include/hv/drv_mpipe_intf.h
+++ b/arch/tile/include/hv/drv_mpipe_intf.h
@@ -23,6 +23,9 @@
 #include <arch/mpipe_constants.h>
 
 
+/** Number of mPIPE instances supported */
+#define HV_MPIPE_INSTANCE_MAX   (2)
+
 /** Number of buffer stacks (32). */
 #define HV_MPIPE_NUM_BUFFER_STACKS \
   (MPIPE_MMIO_INIT_DAT_GX36_1__BUFFER_STACK_MASK_WIDTH)
diff --git a/arch/tile/include/hv/drv_trio_intf.h b/arch/tile/include/hv/drv_trio_intf.h
index ef9f3f52ee27..237e04dee66c 100644
--- a/arch/tile/include/hv/drv_trio_intf.h
+++ b/arch/tile/include/hv/drv_trio_intf.h
@@ -64,8 +64,9 @@ struct pcie_port_property
    *  will not consider it an error if the link comes up as a x8 link. */
   uint8_t allow_x8: 1;
 
-  /** Reserved. */
-  uint8_t reserved: 1;
+  /** If true, this link is connected to a device which may or may not
+   *  be present. */
+  uint8_t removable: 1;
 
 };
 
@@ -167,6 +168,9 @@ pcie_stream_intr_config_sel_t;
 struct pcie_trio_ports_property
 {
   struct pcie_port_property ports[TILEGX_TRIO_PCIES];
+
+  /** Set if this TRIO belongs to a Gx72 device. */
+  uint8_t is_gx72;
 };
 
 /* Flags indicating traffic class. */
diff --git a/arch/tile/include/hv/drv_uart_intf.h b/arch/tile/include/hv/drv_uart_intf.h
new file mode 100644
index 000000000000..f5379e2404fd
--- /dev/null
+++ b/arch/tile/include/hv/drv_uart_intf.h
@@ -0,0 +1,33 @@
+/*
+ * Copyright 2013 Tilera Corporation. All Rights Reserved.
+ *
+ *   This program is free software; you can redistribute it and/or
+ *   modify it under the terms of the GNU General Public License
+ *   as published by the Free Software Foundation, version 2.
+ *
+ *   This program is distributed in the hope that it will be useful, but
+ *   WITHOUT ANY WARRANTY; without even the implied warranty of
+ *   MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ *   NON INFRINGEMENT.  See the GNU General Public License for
+ *   more details.
+ */
+
+/**
+ * Interface definitions for the UART driver.
+ */
+
+#ifndef _SYS_HV_DRV_UART_INTF_H
+#define _SYS_HV_DRV_UART_INTF_H
+
+#include <arch/uart.h>
+
+/** Number of UART ports supported. */
+#define TILEGX_UART_NR        2
+
+/** The mmap file offset (PA) of the UART MMIO region. */
+#define HV_UART_MMIO_OFFSET   0
+
+/** The maximum size of the UARTs MMIO region (64K Bytes). */
+#define HV_UART_MMIO_SIZE     (1UL << 16)
+
+#endif /* _SYS_HV_DRV_UART_INTF_H */
diff --git a/arch/tile/include/hv/hypervisor.h b/arch/tile/include/hv/hypervisor.h
index 837dca5328c2..dfcdeb61ba34 100644
--- a/arch/tile/include/hv/hypervisor.h
+++ b/arch/tile/include/hv/hypervisor.h
@@ -318,8 +318,11 @@
 /** hv_set_pte_super_shift */
 #define HV_DISPATCH_SET_PTE_SUPER_SHIFT           57
 
+/** hv_console_set_ipi */
+#define HV_DISPATCH_CONSOLE_SET_IPI               63
+
 /** One more than the largest dispatch value */
-#define _HV_DISPATCH_END                          58
+#define _HV_DISPATCH_END                          64
 
 
 #ifndef __ASSEMBLER__
@@ -541,14 +544,24 @@ typedef enum {
   HV_CONFSTR_CPUMOD_REV      = 18,
 
   /** Human-readable CPU module description. */
-  HV_CONFSTR_CPUMOD_DESC     = 19
+  HV_CONFSTR_CPUMOD_DESC     = 19,
+
+  /** Per-tile hypervisor statistics.  When this identifier is specified,
+   *  the hv_confstr call takes two extra arguments.  The first is the
+   *  HV_XY_TO_LOTAR of the target tile's coordinates.  The second is
+   *  a flag word.  The only current flag is the lowest bit, which means
+   *  "zero out the stats instead of retrieving them"; in this case the
+   *  buffer and buffer length are ignored. */
+  HV_CONFSTR_HV_STATS        = 20
 
 } HV_ConfstrQuery;
 
 /** Query a configuration string from the hypervisor.
  *
  * @param query Identifier for the specific string to be retrieved
- *        (HV_CONFSTR_xxx).
+ *        (HV_CONFSTR_xxx).  Some strings may require or permit extra
+ *        arguments to be appended which select specific objects to be
+ *        described; see the string descriptions above.
  * @param buf Buffer in which to place the string.
  * @param len Length of the buffer.
  * @return If query is valid, then the length of the corresponding string,
@@ -556,21 +569,16 @@ typedef enum {
  *        was truncated.  If query is invalid, HV_EINVAL.  If the specified
  *        buffer is not writable by the client, HV_EFAULT.
  */
-int hv_confstr(HV_ConfstrQuery query, HV_VirtAddr buf, int len);
+int hv_confstr(HV_ConfstrQuery query, HV_VirtAddr buf, int len, ...);
 
 /** Tile coordinate */
 typedef struct
 {
-#ifndef __BIG_ENDIAN__
   /** X coordinate, relative to supervisor's top-left coordinate */
   int x;
 
   /** Y coordinate, relative to supervisor's top-left coordinate */
   int y;
-#else
-  int y;
-  int x;
-#endif
 } HV_Coord;
 
 
@@ -585,6 +593,30 @@ typedef struct
  */
 int hv_get_ipi_pte(HV_Coord tile, int pl, HV_PTE* pte);
 
+/** Configure the console interrupt.
+ *
+ * When the console client interrupt is enabled, the hypervisor will
+ * deliver the specified IPI to the client in the following situations:
+ *
+ * - The console has at least one character available for input.
+ *
+ * - The console can accept new characters for output, and the last call
+ *   to hv_console_write() did not write all of the characters requested
+ *   by the client.
+ *
+ * Note that in some system configurations, console interrupt will not
+ * be available; clients should be prepared for this routine to fail and
+ * to fall back to periodic console polling in that case.
+ *
+ * @param ipi Index of the IPI register which will receive the interrupt.
+ * @param event IPI event number for console interrupt. If less than 0,
+ *        disable the console IPI interrupt.
+ * @param coord Tile to be targeted for console interrupt.
+ * @return 0 on success, otherwise, HV_EINVAL if illegal parameter,
+ *         HV_ENOTSUP if console interrupt are not available.
+ */
+int hv_console_set_ipi(int ipi, int event, HV_Coord coord);
+
 #else /* !CHIP_HAS_IPI() */
 
 /** A set of interrupts. */
@@ -1092,13 +1124,8 @@ HV_VirtAddrRange hv_inquire_virtual(int idx);
 /** A range of ASID values. */
 typedef struct
 {
-#ifndef __BIG_ENDIAN__
   HV_ASID start;        /**< First ASID in the range. */
   unsigned int size;    /**< Number of ASIDs. Zero for an invalid range. */
-#else
-  unsigned int size;    /**< Number of ASIDs. Zero for an invalid range. */
-  HV_ASID start;        /**< First ASID in the range. */
-#endif
 } HV_ASIDRange;
 
 /** Returns information about a range of ASIDs.
@@ -1422,7 +1449,6 @@ typedef enum
 /** Message recipient. */
 typedef struct
 {
-#ifndef __BIG_ENDIAN__
   /** X coordinate, relative to supervisor's top-left coordinate */
   unsigned int x:11;
 
@@ -1431,11 +1457,6 @@ typedef struct
 
   /** Status of this recipient */
   HV_Recip_State state:10;
-#else //__BIG_ENDIAN__
-  HV_Recip_State state:10;
-  unsigned int y:11;
-  unsigned int x:11;
-#endif
 } HV_Recipient;
 
 /** Send a message to a set of recipients.
diff --git a/arch/tile/include/uapi/arch/Kbuild b/arch/tile/include/uapi/arch/Kbuild
index 4ebc34f4768d..97dfbecec6b6 100644
--- a/arch/tile/include/uapi/arch/Kbuild
+++ b/arch/tile/include/uapi/arch/Kbuild
@@ -1,7 +1,6 @@
 # UAPI Header export list
 header-y += abi.h
 header-y += chip.h
-header-y += chip_tile64.h
 header-y += chip_tilegx.h
 header-y += chip_tilepro.h
 header-y += icache.h
diff --git a/arch/tile/include/uapi/arch/chip.h b/arch/tile/include/uapi/arch/chip.h
index 926d3db0e91e..4c91f90b9369 100644
--- a/arch/tile/include/uapi/arch/chip.h
+++ b/arch/tile/include/uapi/arch/chip.h
@@ -12,9 +12,7 @@
  *   more details.
  */
 
-#if __tile_chip__ == 0
-#include <arch/chip_tile64.h>
-#elif __tile_chip__ == 1
+#if __tile_chip__ == 1
 #include <arch/chip_tilepro.h>
 #elif defined(__tilegx__)
 #include <arch/chip_tilegx.h>
diff --git a/arch/tile/include/uapi/arch/chip_tile64.h b/arch/tile/include/uapi/arch/chip_tile64.h
deleted file mode 100644
index 261aaba092d4..000000000000
--- a/arch/tile/include/uapi/arch/chip_tile64.h
+++ /dev/null
@@ -1,258 +0,0 @@
-/*
- * Copyright 2010 Tilera Corporation. All Rights Reserved.
- *
- *   This program is free software; you can redistribute it and/or
- *   modify it under the terms of the GNU General Public License
- *   as published by the Free Software Foundation, version 2.
- *
- *   This program is distributed in the hope that it will be useful, but
- *   WITHOUT ANY WARRANTY; without even the implied warranty of
- *   MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
- *   NON INFRINGEMENT.  See the GNU General Public License for
- *   more details.
- */
-
-/*
- * @file
- * Global header file.
- * This header file specifies defines for TILE64.
- */
-
-#ifndef __ARCH_CHIP_H__
-#define __ARCH_CHIP_H__
-
-/** Specify chip version.
- * When possible, prefer the CHIP_xxx symbols below for future-proofing.
- * This is intended for cross-compiling; native compilation should
- * use the predefined __tile_chip__ symbol.
- */
-#define TILE_CHIP 0
-
-/** Specify chip revision.
- * This provides for the case of a respin of a particular chip type;
- * the normal value for this symbol is "0".
- * This is intended for cross-compiling; native compilation should
- * use the predefined __tile_chip_rev__ symbol.
- */
-#define TILE_CHIP_REV 0
-
-/** The name of this architecture. */
-#define CHIP_ARCH_NAME "tile64"
-
-/** The ELF e_machine type for binaries for this chip. */
-#define CHIP_ELF_TYPE() EM_TILE64
-
-/** The alternate ELF e_machine type for binaries for this chip. */
-#define CHIP_COMPAT_ELF_TYPE() 0x2506
-
-/** What is the native word size of the machine? */
-#define CHIP_WORD_SIZE() 32
-
-/** How many bits of a virtual address are used. Extra bits must be
- * the sign extension of the low bits.
- */
-#define CHIP_VA_WIDTH() 32
-
-/** How many bits are in a physical address? */
-#define CHIP_PA_WIDTH() 36
-
-/** Size of the L2 cache, in bytes. */
-#define CHIP_L2_CACHE_SIZE() 65536
-
-/** Log size of an L2 cache line in bytes. */
-#define CHIP_L2_LOG_LINE_SIZE() 6
-
-/** Size of an L2 cache line, in bytes. */
-#define CHIP_L2_LINE_SIZE() (1 << CHIP_L2_LOG_LINE_SIZE())
-
-/** Associativity of the L2 cache. */
-#define CHIP_L2_ASSOC() 2
-
-/** Size of the L1 data cache, in bytes. */
-#define CHIP_L1D_CACHE_SIZE() 8192
-
-/** Log size of an L1 data cache line in bytes. */
-#define CHIP_L1D_LOG_LINE_SIZE() 4
-
-/** Size of an L1 data cache line, in bytes. */
-#define CHIP_L1D_LINE_SIZE() (1 << CHIP_L1D_LOG_LINE_SIZE())
-
-/** Associativity of the L1 data cache. */
-#define CHIP_L1D_ASSOC() 2
-
-/** Size of the L1 instruction cache, in bytes. */
-#define CHIP_L1I_CACHE_SIZE() 8192
-
-/** Log size of an L1 instruction cache line in bytes. */
-#define CHIP_L1I_LOG_LINE_SIZE() 6
-
-/** Size of an L1 instruction cache line, in bytes. */
-#define CHIP_L1I_LINE_SIZE() (1 << CHIP_L1I_LOG_LINE_SIZE())
-
-/** Associativity of the L1 instruction cache. */
-#define CHIP_L1I_ASSOC() 1
-
-/** Stride with which flush instructions must be issued. */
-#define CHIP_FLUSH_STRIDE() CHIP_L2_LINE_SIZE()
-
-/** Stride with which inv instructions must be issued. */
-#define CHIP_INV_STRIDE() CHIP_L1D_LINE_SIZE()
-
-/** Stride with which finv instructions must be issued. */
-#define CHIP_FINV_STRIDE() CHIP_L1D_LINE_SIZE()
-
-/** Can the local cache coherently cache data that is homed elsewhere? */
-#define CHIP_HAS_COHERENT_LOCAL_CACHE() 0
-
-/** How many simultaneous outstanding victims can the L2 cache have? */
-#define CHIP_MAX_OUTSTANDING_VICTIMS() 2
-
-/** Does the TLB support the NC and NOALLOC bits? */
-#define CHIP_HAS_NC_AND_NOALLOC_BITS() 0
-
-/** Does the chip support hash-for-home caching? */
-#define CHIP_HAS_CBOX_HOME_MAP() 0
-
-/** Number of entries in the chip's home map tables. */
-/* #define CHIP_CBOX_HOME_MAP_SIZE() -- does not apply to chip 0 */
-
-/** Do uncacheable requests miss in the cache regardless of whether
- * there is matching data? */
-#define CHIP_HAS_ENFORCED_UNCACHEABLE_REQUESTS() 0
-
-/** Does the mf instruction wait for victims? */
-#define CHIP_HAS_MF_WAITS_FOR_VICTIMS() 1
-
-/** Does the chip have an "inv" instruction that doesn't also flush? */
-#define CHIP_HAS_INV() 0
-
-/** Does the chip have a "wh64" instruction? */
-#define CHIP_HAS_WH64() 0
-
-/** Does this chip have a 'dword_align' instruction? */
-#define CHIP_HAS_DWORD_ALIGN() 0
-
-/** Number of performance counters. */
-#define CHIP_PERFORMANCE_COUNTERS() 2
-
-/** Does this chip have auxiliary performance counters? */
-#define CHIP_HAS_AUX_PERF_COUNTERS() 0
-
-/** Is the CBOX_MSR1 SPR supported? */
-#define CHIP_HAS_CBOX_MSR1() 0
-
-/** Is the TILE_RTF_HWM SPR supported? */
-#define CHIP_HAS_TILE_RTF_HWM() 0
-
-/** Is the TILE_WRITE_PENDING SPR supported? */
-#define CHIP_HAS_TILE_WRITE_PENDING() 0
-
-/** Is the PROC_STATUS SPR supported? */
-#define CHIP_HAS_PROC_STATUS_SPR() 0
-
-/** Is the DSTREAM_PF SPR supported? */
-#define CHIP_HAS_DSTREAM_PF() 0
-
-/** Log of the number of mshims we have. */
-#define CHIP_LOG_NUM_MSHIMS() 2
-
-/** Are the bases of the interrupt vector areas fixed? */
-#define CHIP_HAS_FIXED_INTVEC_BASE() 1
-
-/** Are the interrupt masks split up into 2 SPRs? */
-#define CHIP_HAS_SPLIT_INTR_MASK() 1
-
-/** Is the cycle count split up into 2 SPRs? */
-#define CHIP_HAS_SPLIT_CYCLE() 1
-
-/** Does the chip have a static network? */
-#define CHIP_HAS_SN() 1
-
-/** Does the chip have a static network processor? */
-#define CHIP_HAS_SN_PROC() 1
-
-/** Size of the L1 static network processor instruction cache, in bytes. */
-#define CHIP_L1SNI_CACHE_SIZE() 2048
-
-/** Does the chip have DMA support in each tile? */
-#define CHIP_HAS_TILE_DMA() 1
-
-/** Does the chip have the second revision of the directly accessible
- *  dynamic networks?  This encapsulates a number of characteristics,
- *  including the absence of the catch-all, the absence of inline message
- *  tags, the absence of support for network context-switching, and so on.
- */
-#define CHIP_HAS_REV1_XDN() 0
-
-/** Does the chip have cmpexch and similar (fetchadd, exch, etc.)? */
-#define CHIP_HAS_CMPEXCH() 0
-
-/** Does the chip have memory-mapped I/O support? */
-#define CHIP_HAS_MMIO() 0
-
-/** Does the chip have post-completion interrupts? */
-#define CHIP_HAS_POST_COMPLETION_INTERRUPTS() 0
-
-/** Does the chip have native single step support? */
-#define CHIP_HAS_SINGLE_STEP() 0
-
-#ifndef __OPEN_SOURCE__  /* features only relevant to hypervisor-level code */
-
-/** How many entries are present in the instruction TLB? */
-#define CHIP_ITLB_ENTRIES() 8
-
-/** How many entries are present in the data TLB? */
-#define CHIP_DTLB_ENTRIES() 16
-
-/** How many MAF entries does the XAUI shim have? */
-#define CHIP_XAUI_MAF_ENTRIES() 16
-
-/** Does the memory shim have a source-id table? */
-#define CHIP_HAS_MSHIM_SRCID_TABLE() 1
-
-/** Does the L1 instruction cache clear on reset? */
-#define CHIP_HAS_L1I_CLEAR_ON_RESET() 0
-
-/** Does the chip come out of reset with valid coordinates on all tiles?
- * Note that if defined, this also implies that the upper left is 1,1.
- */
-#define CHIP_HAS_VALID_TILE_COORD_RESET() 0
-
-/** Does the chip have unified packet formats? */
-#define CHIP_HAS_UNIFIED_PACKET_FORMATS() 0
-
-/** Does the chip support write reordering? */
-#define CHIP_HAS_WRITE_REORDERING() 0
-
-/** Does the chip support Y-X routing as well as X-Y? */
-#define CHIP_HAS_Y_X_ROUTING() 0
-
-/** Is INTCTRL_3 managed with the correct MPL? */
-#define CHIP_HAS_INTCTRL_3_STATUS_FIX() 0
-
-/** Is it possible to configure the chip to be big-endian? */
-#define CHIP_HAS_BIG_ENDIAN_CONFIG() 0
-
-/** Is the CACHE_RED_WAY_OVERRIDDEN SPR supported? */
-#define CHIP_HAS_CACHE_RED_WAY_OVERRIDDEN() 0
-
-/** Is the DIAG_TRACE_WAY SPR supported? */
-#define CHIP_HAS_DIAG_TRACE_WAY() 0
-
-/** Is the MEM_STRIPE_CONFIG SPR supported? */
-#define CHIP_HAS_MEM_STRIPE_CONFIG() 0
-
-/** Are the TLB_PERF SPRs supported? */
-#define CHIP_HAS_TLB_PERF() 0
-
-/** Is the VDN_SNOOP_SHIM_CTL SPR supported? */
-#define CHIP_HAS_VDN_SNOOP_SHIM_CTL() 0
-
-/** Does the chip support rev1 DMA packets? */
-#define CHIP_HAS_REV1_DMA_PACKETS() 0
-
-/** Does the chip have an IPI shim? */
-#define CHIP_HAS_IPI() 0
-
-#endif /* !__OPEN_SOURCE__ */
-#endif /* __ARCH_CHIP_H__ */
diff --git a/arch/tile/include/uapi/arch/opcode_tilegx.h b/arch/tile/include/uapi/arch/opcode_tilegx.h
index c14d02c81600..d76ff2db745e 100644
--- a/arch/tile/include/uapi/arch/opcode_tilegx.h
+++ b/arch/tile/include/uapi/arch/opcode_tilegx.h
@@ -61,6 +61,7 @@ typedef tilegx_bundle_bits tile_bundle_bits;
 #define TILE_BUNDLE_ALIGNMENT_IN_BYTES TILEGX_BUNDLE_ALIGNMENT_IN_BYTES
 #define TILE_LOG2_BUNDLE_ALIGNMENT_IN_BYTES \
   TILEGX_LOG2_BUNDLE_ALIGNMENT_IN_BYTES
+#define TILE_BPT_BUNDLE TILEGX_BPT_BUNDLE
 
 /* 64-bit pattern for a { bpt ; nop } bundle. */
 #define TILEGX_BPT_BUNDLE 0x286a44ae51485000ULL
diff --git a/arch/tile/include/uapi/arch/opcode_tilepro.h b/arch/tile/include/uapi/arch/opcode_tilepro.h
index 71b763b8ce83..4451cff1a861 100644
--- a/arch/tile/include/uapi/arch/opcode_tilepro.h
+++ b/arch/tile/include/uapi/arch/opcode_tilepro.h
@@ -71,6 +71,7 @@ typedef tilepro_bundle_bits tile_bundle_bits;
 #define TILE_BUNDLE_ALIGNMENT_IN_BYTES TILEPRO_BUNDLE_ALIGNMENT_IN_BYTES
 #define TILE_LOG2_BUNDLE_ALIGNMENT_IN_BYTES \
   TILEPRO_LOG2_BUNDLE_ALIGNMENT_IN_BYTES
+#define TILE_BPT_BUNDLE TILEPRO_BPT_BUNDLE
 
 /* 64-bit pattern for a { bpt ; nop } bundle. */
 #define TILEPRO_BPT_BUNDLE 0x400b3cae70166000ULL
diff --git a/arch/tile/include/uapi/arch/spr_def_32.h b/arch/tile/include/uapi/arch/spr_def_32.h
index c689446e6284..78daa3146d25 100644
--- a/arch/tile/include/uapi/arch/spr_def_32.h
+++ b/arch/tile/include/uapi/arch/spr_def_32.h
@@ -200,8 +200,6 @@
 #define SPR_SIM_CONTROL 0x4e0c
 #define SPR_SNCTL 0x0805
 #define SPR_SNCTL__FRZFABRIC_MASK  0x1
-#define SPR_SNCTL__FRZPROC_MASK  0x2
-#define SPR_SNPC 0x080b
 #define SPR_SNSTATIC 0x080c
 #define SPR_SYSTEM_SAVE_0_0 0x4b00
 #define SPR_SYSTEM_SAVE_0_1 0x4b01
diff --git a/arch/tile/include/uapi/asm/auxvec.h b/arch/tile/include/uapi/asm/auxvec.h
index 1d393edb0641..c93e92709f14 100644
--- a/arch/tile/include/uapi/asm/auxvec.h
+++ b/arch/tile/include/uapi/asm/auxvec.h
@@ -15,6 +15,7 @@
 #ifndef _ASM_TILE_AUXVEC_H
 #define _ASM_TILE_AUXVEC_H
 
-/* No extensions to auxvec */
+/* The vDSO location. */
+#define AT_SYSINFO_EHDR         33
 
 #endif /* _ASM_TILE_AUXVEC_H */
diff --git a/arch/tile/include/uapi/asm/cachectl.h b/arch/tile/include/uapi/asm/cachectl.h
index af4c9f9154d1..572ddcad2090 100644
--- a/arch/tile/include/uapi/asm/cachectl.h
+++ b/arch/tile/include/uapi/asm/cachectl.h
@@ -29,8 +29,8 @@
  * to honor the arguments at some point.)
  *
  * Flush and invalidation of memory can normally be performed with the
- * __insn_flush(), __insn_inv(), and __insn_finv() instructions from
- * userspace.  The DCACHE option to the system call allows userspace
+ * __insn_flush() and __insn_finv() instructions from userspace.
+ * The DCACHE option to the system call allows userspace
  * to flush the entire L1+L2 data cache from the core.  In this case,
  * the address and length arguments are not used.  The DCACHE flush is
  * restricted to the current core, not all cores in the address space.
diff --git a/arch/tile/kernel/Makefile b/arch/tile/kernel/Makefile
index 5334be8e2538..27a2bf39dae8 100644
--- a/arch/tile/kernel/Makefile
+++ b/arch/tile/kernel/Makefile
@@ -3,11 +3,17 @@
 #
 
 extra-y := vmlinux.lds head_$(BITS).o
-obj-y := backtrace.o entry.o irq.o messaging.o \
+obj-y := backtrace.o entry.o hvglue.o irq.o messaging.o \
 	pci-dma.o proc.o process.o ptrace.o reboot.o \
-	setup.o signal.o single_step.o stack.o sys.o sysfs.o time.o traps.o \
+	setup.o signal.o single_step.o stack.o sys.o \
+	sysfs.o time.o traps.o unaligned.o vdso.o \
 	intvec_$(BITS).o regs_$(BITS).o tile-desc_$(BITS).o
 
+ifdef CONFIG_FUNCTION_TRACER
+CFLAGS_REMOVE_ftrace.o = -pg
+CFLAGS_REMOVE_early_printk.o = -pg
+endif
+
 obj-$(CONFIG_HARDWALL)		+= hardwall.o
 obj-$(CONFIG_COMPAT)		+= compat.o compat_signal.o
 obj-$(CONFIG_SMP)		+= smpboot.o smp.o tlb.o
@@ -20,3 +26,9 @@ else
 obj-$(CONFIG_PCI)		+= pci.o
 endif
 obj-$(CONFIG_TILE_USB)		+= usb.o
+obj-$(CONFIG_TILE_HVGLUE_TRACE)	+= hvglue_trace.o
+obj-$(CONFIG_FUNCTION_TRACER)	+= ftrace.o mcount_64.o
+obj-$(CONFIG_KPROBES)		+= kprobes.o
+obj-$(CONFIG_KGDB)		+= kgdb.o
+
+obj-y				+= vdso/
diff --git a/arch/tile/kernel/asm-offsets.c b/arch/tile/kernel/asm-offsets.c
index 01ddf19cc36d..375e7c321eef 100644
--- a/arch/tile/kernel/asm-offsets.c
+++ b/arch/tile/kernel/asm-offsets.c
@@ -14,13 +14,6 @@
  * Generates definitions from c-type structures used by assembly sources.
  */
 
-#include <linux/kbuild.h>
-#include <linux/thread_info.h>
-#include <linux/sched.h>
-#include <linux/hardirq.h>
-#include <linux/ptrace.h>
-#include <hv/hypervisor.h>
-
 /* Check for compatible compiler early in the build. */
 #ifdef CONFIG_TILEGX
 # ifndef __tilegx__
@@ -31,46 +24,61 @@
 # endif
 #else
 # ifdef __tilegx__
-#  error Can not build TILEPro/TILE64 configurations with tilegx compiler
+#  error Can not build TILEPro configurations with tilegx compiler
 # endif
 #endif
 
+#include <linux/kbuild.h>
+#include <linux/thread_info.h>
+#include <linux/sched.h>
+#include <linux/hardirq.h>
+#include <linux/ptrace.h>
+#include <hv/hypervisor.h>
+
 void foo(void)
 {
-	DEFINE(SINGLESTEP_STATE_BUFFER_OFFSET, \
+	DEFINE(SINGLESTEP_STATE_BUFFER_OFFSET,
 	       offsetof(struct single_step_state, buffer));
-	DEFINE(SINGLESTEP_STATE_FLAGS_OFFSET, \
+	DEFINE(SINGLESTEP_STATE_FLAGS_OFFSET,
 	       offsetof(struct single_step_state, flags));
-	DEFINE(SINGLESTEP_STATE_ORIG_PC_OFFSET, \
+	DEFINE(SINGLESTEP_STATE_ORIG_PC_OFFSET,
 	       offsetof(struct single_step_state, orig_pc));
-	DEFINE(SINGLESTEP_STATE_NEXT_PC_OFFSET, \
+	DEFINE(SINGLESTEP_STATE_NEXT_PC_OFFSET,
 	       offsetof(struct single_step_state, next_pc));
-	DEFINE(SINGLESTEP_STATE_BRANCH_NEXT_PC_OFFSET, \
+	DEFINE(SINGLESTEP_STATE_BRANCH_NEXT_PC_OFFSET,
 	       offsetof(struct single_step_state, branch_next_pc));
-	DEFINE(SINGLESTEP_STATE_UPDATE_VALUE_OFFSET, \
+	DEFINE(SINGLESTEP_STATE_UPDATE_VALUE_OFFSET,
 	       offsetof(struct single_step_state, update_value));
 
-	DEFINE(THREAD_INFO_TASK_OFFSET, \
+	DEFINE(THREAD_INFO_TASK_OFFSET,
 	       offsetof(struct thread_info, task));
-	DEFINE(THREAD_INFO_FLAGS_OFFSET, \
+	DEFINE(THREAD_INFO_FLAGS_OFFSET,
 	       offsetof(struct thread_info, flags));
-	DEFINE(THREAD_INFO_STATUS_OFFSET, \
+	DEFINE(THREAD_INFO_STATUS_OFFSET,
 	       offsetof(struct thread_info, status));
-	DEFINE(THREAD_INFO_HOMECACHE_CPU_OFFSET, \
+	DEFINE(THREAD_INFO_HOMECACHE_CPU_OFFSET,
 	       offsetof(struct thread_info, homecache_cpu));
-	DEFINE(THREAD_INFO_STEP_STATE_OFFSET, \
+	DEFINE(THREAD_INFO_PREEMPT_COUNT_OFFSET,
+	       offsetof(struct thread_info, preempt_count));
+	DEFINE(THREAD_INFO_STEP_STATE_OFFSET,
 	       offsetof(struct thread_info, step_state));
+#ifdef __tilegx__
+	DEFINE(THREAD_INFO_UNALIGN_JIT_BASE_OFFSET,
+	       offsetof(struct thread_info, unalign_jit_base));
+	DEFINE(THREAD_INFO_UNALIGN_JIT_TMP_OFFSET,
+	       offsetof(struct thread_info, unalign_jit_tmp));
+#endif
 
 	DEFINE(TASK_STRUCT_THREAD_KSP_OFFSET,
 	       offsetof(struct task_struct, thread.ksp));
 	DEFINE(TASK_STRUCT_THREAD_PC_OFFSET,
 	       offsetof(struct task_struct, thread.pc));
 
-	DEFINE(HV_TOPOLOGY_WIDTH_OFFSET, \
+	DEFINE(HV_TOPOLOGY_WIDTH_OFFSET,
 	       offsetof(HV_Topology, width));
-	DEFINE(HV_TOPOLOGY_HEIGHT_OFFSET, \
+	DEFINE(HV_TOPOLOGY_HEIGHT_OFFSET,
 	       offsetof(HV_Topology, height));
 
-	DEFINE(IRQ_CPUSTAT_SYSCALL_COUNT_OFFSET, \
+	DEFINE(IRQ_CPUSTAT_SYSCALL_COUNT_OFFSET,
 	       offsetof(irq_cpustat_t, irq_syscall_count));
 }
diff --git a/arch/tile/kernel/compat.c b/arch/tile/kernel/compat.c
index ed378416b86a..49120843ff96 100644
--- a/arch/tile/kernel/compat.c
+++ b/arch/tile/kernel/compat.c
@@ -84,7 +84,7 @@ COMPAT_SYSCALL_DEFINE5(llseek, unsigned int, fd, unsigned int, offset_high,
 {
 	return sys_llseek(fd, offset_high, offset_low, result, origin);
 }
- 
+
 /* Provide the compat syscall number to call mapping. */
 #undef __SYSCALL
 #define __SYSCALL(nr, call) [nr] = (call),
diff --git a/arch/tile/kernel/compat_signal.c b/arch/tile/kernel/compat_signal.c
index d0a052e725be..85e00b2f39bf 100644
--- a/arch/tile/kernel/compat_signal.c
+++ b/arch/tile/kernel/compat_signal.c
@@ -32,6 +32,7 @@
 #include <asm/ucontext.h>
 #include <asm/sigframe.h>
 #include <asm/syscalls.h>
+#include <asm/vdso.h>
 #include <arch/interrupts.h>
 
 struct compat_ucontext {
@@ -227,7 +228,7 @@ int compat_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
 	if (err)
 		goto give_sigsegv;
 
-	restorer = VDSO_BASE;
+	restorer = VDSO_SYM(&__vdso_rt_sigreturn);
 	if (ka->sa.sa_flags & SA_RESTORER)
 		restorer = ptr_to_compat_reg(ka->sa.sa_restorer);
 
diff --git a/arch/tile/kernel/early_printk.c b/arch/tile/kernel/early_printk.c
index 34d72a151bf3..b608e00e7f6d 100644
--- a/arch/tile/kernel/early_printk.c
+++ b/arch/tile/kernel/early_printk.c
@@ -23,19 +23,24 @@
 
 static void early_hv_write(struct console *con, const char *s, unsigned n)
 {
-	hv_console_write((HV_VirtAddr) s, n);
+	tile_console_write(s, n);
+
+	/*
+	 * Convert NL to NLCR (close enough to CRNL) during early boot.
+	 * We assume newlines are at the ends of strings, which turns out
+	 * to be good enough for early boot console output.
+	 */
+	if (n && s[n-1] == '\n')
+		tile_console_write("\r", 1);
 }
 
 static struct console early_hv_console = {
 	.name =		"earlyhv",
 	.write =	early_hv_write,
-	.flags =	CON_PRINTBUFFER,
+	.flags =	CON_PRINTBUFFER | CON_BOOT,
 	.index =	-1,
 };
 
-/* Direct interface for emergencies */
-static int early_console_complete;
-
 void early_panic(const char *fmt, ...)
 {
 	va_list ap;
@@ -43,51 +48,21 @@ void early_panic(const char *fmt, ...)
 	va_start(ap, fmt);
 	early_printk("Kernel panic - not syncing: ");
 	early_vprintk(fmt, ap);
-	early_console->write(early_console, "\n", 1);
+	early_printk("\n");
 	va_end(ap);
 	dump_stack();
 	hv_halt();
 }
 
-static int __initdata keep_early;
-
 static int __init setup_early_printk(char *str)
 {
 	if (early_console)
 		return 1;
 
-	if (str != NULL && strncmp(str, "keep", 4) == 0)
-		keep_early = 1;
-
 	early_console = &early_hv_console;
 	register_console(early_console);
 
 	return 0;
 }
 
-void __init disable_early_printk(void)
-{
-	early_console_complete = 1;
-	if (!early_console)
-		return;
-	if (!keep_early) {
-		early_printk("disabling early console\n");
-		unregister_console(early_console);
-		early_console = NULL;
-	} else {
-		early_printk("keeping early console\n");
-	}
-}
-
-void warn_early_printk(void)
-{
-	if (early_console_complete || early_console)
-		return;
-	early_printk("\
-Machine shutting down before console output is fully initialized.\n\
-You may wish to reboot and add the option 'earlyprintk' to your\n\
-boot command line to see any diagnostic early console output.\n\
-");
-}
-
 early_param("earlyprintk", setup_early_printk);
diff --git a/arch/tile/kernel/entry.S b/arch/tile/kernel/entry.S
index f116cb0bce20..3d9175992a20 100644
--- a/arch/tile/kernel/entry.S
+++ b/arch/tile/kernel/entry.S
@@ -27,22 +27,6 @@ STD_ENTRY(current_text_addr)
 	{ move r0, lr; jrp lr }
 	STD_ENDPROC(current_text_addr)
 
-/*
- * We don't run this function directly, but instead copy it to a page
- * we map into every user process.  See vdso_setup().
- *
- * Note that libc has a copy of this function that it uses to compare
- * against the PC when a stack backtrace ends, so if this code is
- * changed, the libc implementation(s) should also be updated.
- */
-	.pushsection .data
-ENTRY(__rt_sigreturn)
-	moveli TREG_SYSCALL_NR_NAME,__NR_rt_sigreturn
-	swint1
-	ENDPROC(__rt_sigreturn)
-	ENTRY(__rt_sigreturn_end)
-	.popsection
-
 STD_ENTRY(dump_stack)
 	{ move r2, lr; lnk r1 }
 	{ move r4, r52; addli r1, r1, dump_stack - . }
diff --git a/arch/tile/kernel/ftrace.c b/arch/tile/kernel/ftrace.c
new file mode 100644
index 000000000000..f1c452092eeb
--- /dev/null
+++ b/arch/tile/kernel/ftrace.c
@@ -0,0 +1,246 @@
+/*
+ * Copyright 2012 Tilera Corporation. All Rights Reserved.
+ *
+ *   This program is free software; you can redistribute it and/or
+ *   modify it under the terms of the GNU General Public License
+ *   as published by the Free Software Foundation, version 2.
+ *
+ *   This program is distributed in the hope that it will be useful, but
+ *   WITHOUT ANY WARRANTY; without even the implied warranty of
+ *   MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ *   NON INFRINGEMENT.  See the GNU General Public License for
+ *   more details.
+ *
+ * TILE-Gx specific ftrace support
+ */
+
+#include <linux/ftrace.h>
+#include <linux/uaccess.h>
+
+#include <asm/cacheflush.h>
+#include <asm/ftrace.h>
+#include <asm/sections.h>
+
+#include <arch/opcode.h>
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+
+static inline tilegx_bundle_bits NOP(void)
+{
+	return create_UnaryOpcodeExtension_X0(FNOP_UNARY_OPCODE_X0) |
+		create_RRROpcodeExtension_X0(UNARY_RRR_0_OPCODE_X0) |
+		create_Opcode_X0(RRR_0_OPCODE_X0) |
+		create_UnaryOpcodeExtension_X1(NOP_UNARY_OPCODE_X1) |
+		create_RRROpcodeExtension_X1(UNARY_RRR_0_OPCODE_X1) |
+		create_Opcode_X1(RRR_0_OPCODE_X1);
+}
+
+static int machine_stopped __read_mostly;
+
+int ftrace_arch_code_modify_prepare(void)
+{
+	machine_stopped = 1;
+	return 0;
+}
+
+int ftrace_arch_code_modify_post_process(void)
+{
+	flush_icache_range(0, CHIP_L1I_CACHE_SIZE());
+	machine_stopped = 0;
+	return 0;
+}
+
+/*
+ * Put { move r10, lr; jal ftrace_caller } in a bundle, this lets dynamic
+ * tracer just add one cycle overhead to every kernel function when disabled.
+ */
+static unsigned long ftrace_gen_branch(unsigned long pc, unsigned long addr,
+				       bool link)
+{
+	tilegx_bundle_bits opcode_x0, opcode_x1;
+	long pcrel_by_instr = (addr - pc) >> TILEGX_LOG2_BUNDLE_SIZE_IN_BYTES;
+
+	if (link) {
+		/* opcode: jal addr */
+		opcode_x1 =
+			create_Opcode_X1(JUMP_OPCODE_X1) |
+			create_JumpOpcodeExtension_X1(JAL_JUMP_OPCODE_X1) |
+			create_JumpOff_X1(pcrel_by_instr);
+	} else {
+		/* opcode: j addr */
+		opcode_x1 =
+			create_Opcode_X1(JUMP_OPCODE_X1) |
+			create_JumpOpcodeExtension_X1(J_JUMP_OPCODE_X1) |
+			create_JumpOff_X1(pcrel_by_instr);
+	}
+
+	if (addr == FTRACE_ADDR) {
+		/* opcode: or r10, lr, zero */
+		opcode_x0 =
+			create_Dest_X0(10) |
+			create_SrcA_X0(TREG_LR) |
+			create_SrcB_X0(TREG_ZERO) |
+			create_RRROpcodeExtension_X0(OR_RRR_0_OPCODE_X0) |
+			create_Opcode_X0(RRR_0_OPCODE_X0);
+	} else {
+		/* opcode: fnop */
+		opcode_x0 =
+			create_UnaryOpcodeExtension_X0(FNOP_UNARY_OPCODE_X0) |
+			create_RRROpcodeExtension_X0(UNARY_RRR_0_OPCODE_X0) |
+			create_Opcode_X0(RRR_0_OPCODE_X0);
+	}
+
+	return opcode_x1 | opcode_x0;
+}
+
+static unsigned long ftrace_nop_replace(struct dyn_ftrace *rec)
+{
+	return NOP();
+}
+
+static unsigned long ftrace_call_replace(unsigned long pc, unsigned long addr)
+{
+	return ftrace_gen_branch(pc, addr, true);
+}
+
+static int ftrace_modify_code(unsigned long pc, unsigned long old,
+			      unsigned long new)
+{
+	unsigned long pc_wr;
+
+	/* Check if the address is in kernel text space and module space. */
+	if (!kernel_text_address(pc))
+		return -EINVAL;
+
+	/* Operate on writable kernel text mapping. */
+	pc_wr = pc - MEM_SV_START + PAGE_OFFSET;
+
+	if (probe_kernel_write((void *)pc_wr, &new, MCOUNT_INSN_SIZE))
+		return -EPERM;
+
+	smp_wmb();
+
+	if (!machine_stopped && num_online_cpus() > 1)
+		flush_icache_range(pc, pc + MCOUNT_INSN_SIZE);
+
+	return 0;
+}
+
+int ftrace_update_ftrace_func(ftrace_func_t func)
+{
+	unsigned long pc, old;
+	unsigned long new;
+	int ret;
+
+	pc = (unsigned long)&ftrace_call;
+	memcpy(&old, &ftrace_call, MCOUNT_INSN_SIZE);
+	new = ftrace_call_replace(pc, (unsigned long)func);
+
+	ret = ftrace_modify_code(pc, old, new);
+
+	return ret;
+}
+
+int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
+{
+	unsigned long new, old;
+	unsigned long ip = rec->ip;
+
+	old = ftrace_nop_replace(rec);
+	new = ftrace_call_replace(ip, addr);
+
+	return ftrace_modify_code(rec->ip, old, new);
+}
+
+int ftrace_make_nop(struct module *mod,
+		    struct dyn_ftrace *rec, unsigned long addr)
+{
+	unsigned long ip = rec->ip;
+	unsigned long old;
+	unsigned long new;
+	int ret;
+
+	old = ftrace_call_replace(ip, addr);
+	new = ftrace_nop_replace(rec);
+	ret = ftrace_modify_code(ip, old, new);
+
+	return ret;
+}
+
+int __init ftrace_dyn_arch_init(void *data)
+{
+	*(unsigned long *)data = 0;
+
+	return 0;
+}
+#endif /* CONFIG_DYNAMIC_FTRACE */
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
+			   unsigned long frame_pointer)
+{
+	unsigned long return_hooker = (unsigned long) &return_to_handler;
+	struct ftrace_graph_ent trace;
+	unsigned long old;
+	int err;
+
+	if (unlikely(atomic_read(&current->tracing_graph_pause)))
+		return;
+
+	old = *parent;
+	*parent = return_hooker;
+
+	err = ftrace_push_return_trace(old, self_addr, &trace.depth,
+				       frame_pointer);
+	if (err == -EBUSY) {
+		*parent = old;
+		return;
+	}
+
+	trace.func = self_addr;
+
+	/* Only trace if the calling function expects to */
+	if (!ftrace_graph_entry(&trace)) {
+		current->curr_ret_stack--;
+		*parent = old;
+	}
+}
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+extern unsigned long ftrace_graph_call;
+
+static int __ftrace_modify_caller(unsigned long *callsite,
+				  void (*func) (void), bool enable)
+{
+	unsigned long caller_fn = (unsigned long) func;
+	unsigned long pc = (unsigned long) callsite;
+	unsigned long branch = ftrace_gen_branch(pc, caller_fn, false);
+	unsigned long nop = NOP();
+	unsigned long old = enable ? nop : branch;
+	unsigned long new = enable ? branch : nop;
+
+	return ftrace_modify_code(pc, old, new);
+}
+
+static int ftrace_modify_graph_caller(bool enable)
+{
+	int ret;
+
+	ret = __ftrace_modify_caller(&ftrace_graph_call,
+				     ftrace_graph_caller,
+				     enable);
+
+	return ret;
+}
+
+int ftrace_enable_ftrace_graph_caller(void)
+{
+	return ftrace_modify_graph_caller(true);
+}
+
+int ftrace_disable_ftrace_graph_caller(void)
+{
+	return ftrace_modify_graph_caller(false);
+}
+#endif /* CONFIG_DYNAMIC_FTRACE */
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
diff --git a/arch/tile/kernel/futex_64.S b/arch/tile/kernel/futex_64.S
deleted file mode 100644
index f465d1eda20f..000000000000
--- a/arch/tile/kernel/futex_64.S
+++ /dev/null
@@ -1,55 +0,0 @@
-/*
- * Copyright 2011 Tilera Corporation. All Rights Reserved.
- *
- *   This program is free software; you can redistribute it and/or
- *   modify it under the terms of the GNU General Public License
- *   as published by the Free Software Foundation, version 2.
- *
- *   This program is distributed in the hope that it will be useful, but
- *   WITHOUT ANY WARRANTY; without even the implied warranty of
- *   MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
- *   NON INFRINGEMENT.  See the GNU General Public License for
- *   more details.
- *
- * Atomically access user memory, but use MMU to avoid propagating
- * kernel exceptions.
- */
-
-#include <linux/linkage.h>
-#include <asm/errno.h>
-#include <asm/futex.h>
-#include <asm/page.h>
-#include <asm/processor.h>
-
-/*
- * Provide a set of atomic memory operations supporting <asm/futex.h>.
- *
- * r0: user address to manipulate
- * r1: new value to write, or for cmpxchg, old value to compare against
- * r2: (cmpxchg only) new value to write
- *
- * Return __get_user struct, r0 with value, r1 with error.
- */
-#define FUTEX_OP(name, ...) \
-STD_ENTRY(futex_##name)			\
-	__VA_ARGS__;			\
-	{				\
-	 move   r1, zero;		\
-	 jrp    lr			\
-	};				\
-	STD_ENDPROC(futex_##name);	\
-	.pushsection __ex_table,"a";	\
-	.quad 1b, get_user_fault;	\
-	.popsection
-
-	.pushsection .fixup,"ax"
-get_user_fault:
-	{ movei r1, -EFAULT; jrp lr }
-	ENDPROC(get_user_fault)
-	.popsection
-
-FUTEX_OP(cmpxchg, mtspr CMPEXCH_VALUE, r1; 1: cmpexch4 r0, r0, r2)
-FUTEX_OP(set, 1: exch4 r0, r0, r1)
-FUTEX_OP(add, 1: fetchadd4 r0, r0, r1)
-FUTEX_OP(or, 1: fetchor4 r0, r0, r1)
-FUTEX_OP(andn, nor r1, r1, zero; 1: fetchand4 r0, r0, r1)
diff --git a/arch/tile/kernel/hardwall.c b/arch/tile/kernel/hardwall.c
index 38ac189d9575..531f4c365351 100644
--- a/arch/tile/kernel/hardwall.c
+++ b/arch/tile/kernel/hardwall.c
@@ -66,7 +66,7 @@ static struct hardwall_type hardwall_types[] = {
 		0,
 		"udn",
 		LIST_HEAD_INIT(hardwall_types[HARDWALL_UDN].list),
-		__SPIN_LOCK_INITIALIZER(hardwall_types[HARDWALL_UDN].lock),
+		__SPIN_LOCK_UNLOCKED(hardwall_types[HARDWALL_UDN].lock),
 		NULL
 	},
 #ifndef __tilepro__
@@ -77,7 +77,7 @@ static struct hardwall_type hardwall_types[] = {
 		1,  /* disabled pending hypervisor support */
 		"idn",
 		LIST_HEAD_INIT(hardwall_types[HARDWALL_IDN].list),
-		__SPIN_LOCK_INITIALIZER(hardwall_types[HARDWALL_IDN].lock),
+		__SPIN_LOCK_UNLOCKED(hardwall_types[HARDWALL_IDN].lock),
 		NULL
 	},
 	{  /* access to user-space IPI */
@@ -87,7 +87,7 @@ static struct hardwall_type hardwall_types[] = {
 		0,
 		"ipi",
 		LIST_HEAD_INIT(hardwall_types[HARDWALL_IPI].list),
-		__SPIN_LOCK_INITIALIZER(hardwall_types[HARDWALL_IPI].lock),
+		__SPIN_LOCK_UNLOCKED(hardwall_types[HARDWALL_IPI].lock),
 		NULL
 	},
 #endif
@@ -272,9 +272,9 @@ static void hardwall_setup_func(void *info)
 	struct hardwall_info *r = info;
 	struct hardwall_type *hwt = r->type;
 
-	int cpu = smp_processor_id();
-	int x = cpu % smp_width;
-	int y = cpu / smp_width;
+	int cpu = smp_processor_id();  /* on_each_cpu disables preemption */
+	int x = cpu_x(cpu);
+	int y = cpu_y(cpu);
 	int bits = 0;
 	if (x == r->ulhc_x)
 		bits |= W_PROTECT;
@@ -317,6 +317,7 @@ static void hardwall_protect_rectangle(struct hardwall_info *r)
 	on_each_cpu_mask(&rect_cpus, hardwall_setup_func, r, 1);
 }
 
+/* Entered from INT_xDN_FIREWALL interrupt vector with irqs disabled. */
 void __kprobes do_hardwall_trap(struct pt_regs* regs, int fault_num)
 {
 	struct hardwall_info *rect;
@@ -325,7 +326,6 @@ void __kprobes do_hardwall_trap(struct pt_regs* regs, int fault_num)
 	struct siginfo info;
 	int cpu = smp_processor_id();
 	int found_processes;
-	unsigned long flags;
 	struct pt_regs *old_regs = set_irq_regs(regs);
 
 	irq_enter();
@@ -346,7 +346,7 @@ void __kprobes do_hardwall_trap(struct pt_regs* regs, int fault_num)
 	BUG_ON(hwt->disabled);
 
 	/* This tile trapped a network access; find the rectangle. */
-	spin_lock_irqsave(&hwt->lock, flags);
+	spin_lock(&hwt->lock);
 	list_for_each_entry(rect, &hwt->list, list) {
 		if (cpumask_test_cpu(cpu, &rect->cpumask))
 			break;
@@ -401,7 +401,7 @@ void __kprobes do_hardwall_trap(struct pt_regs* regs, int fault_num)
 		pr_notice("hardwall: no associated processes!\n");
 
  done:
-	spin_unlock_irqrestore(&hwt->lock, flags);
+	spin_unlock(&hwt->lock);
 
 	/*
 	 * We have to disable firewall interrupts now, or else when we
@@ -540,6 +540,14 @@ static struct hardwall_info *hardwall_create(struct hardwall_type *hwt,
 		}
 	}
 
+	/*
+	 * Eliminate cpus that are not part of this Linux client.
+	 * Note that this allows for configurations that we might not want to
+	 * support, such as one client on every even cpu, another client on
+	 * every odd cpu.
+	 */
+	cpumask_and(&info->cpumask, &info->cpumask, cpu_online_mask);
+
 	/* Confirm it doesn't overlap and add it to the list. */
 	spin_lock_irqsave(&hwt->lock, flags);
 	list_for_each_entry(iter, &hwt->list, list) {
@@ -612,7 +620,7 @@ static int hardwall_activate(struct hardwall_info *info)
 
 /*
  * Deactivate a task's hardwall.  Must hold lock for hardwall_type.
- * This method may be called from free_task(), so we don't want to
+ * This method may be called from exit_thread(), so we don't want to
  * rely on too many fields of struct task_struct still being valid.
  * We assume the cpus_allowed, pid, and comm fields are still valid.
  */
@@ -653,7 +661,7 @@ static int hardwall_deactivate(struct hardwall_type *hwt,
 		return -EINVAL;
 
 	printk(KERN_DEBUG "Pid %d (%s) deactivated for %s hardwall: cpu %d\n",
-	       task->pid, task->comm, hwt->name, smp_processor_id());
+	       task->pid, task->comm, hwt->name, raw_smp_processor_id());
 	return 0;
 }
 
@@ -795,8 +803,8 @@ static void reset_xdn_network_state(struct hardwall_type *hwt)
 	/* Reset UDN coordinates to their standard value */
 	{
 		unsigned int cpu = smp_processor_id();
-		unsigned int x = cpu % smp_width;
-		unsigned int y = cpu / smp_width;
+		unsigned int x = cpu_x(cpu);
+		unsigned int y = cpu_y(cpu);
 		__insn_mtspr(SPR_UDN_TILE_COORD, (x << 18) | (y << 7));
 	}
 
diff --git a/arch/tile/kernel/head_32.S b/arch/tile/kernel/head_32.S
index ac115307e5e4..8d5b40ff2922 100644
--- a/arch/tile/kernel/head_32.S
+++ b/arch/tile/kernel/head_32.S
@@ -39,12 +39,12 @@ ENTRY(_start)
 	}
 	{
 	  moveli r0, _HV_VERSION_OLD_HV_INIT
-	  jal hv_init
+	  jal _hv_init
 	}
 	/* Get a reasonable default ASID in r0 */
 	{
 	  move r0, zero
-	  jal hv_inquire_asid
+	  jal _hv_inquire_asid
 	}
 	/* Install the default page table */
 	{
@@ -64,7 +64,7 @@ ENTRY(_start)
 	  auli r0, r0, ha16(swapper_pg_dir - PAGE_OFFSET)
 	}
 	{
-	  inv r6
+	  finv r6
 	  move r1, zero   /* high 32 bits of CPA is zero */
 	}
 	{
@@ -73,12 +73,12 @@ ENTRY(_start)
 	}
 	{
 	  auli lr, lr, ha16(1f)
-	  j hv_install_context
+	  j _hv_install_context
 	}
 1:
 
 	/* Get our processor number and save it away in SAVE_K_0. */
-	jal hv_inquire_topology
+	jal _hv_inquire_topology
 	mulll_uu r4, r1, r2        /* r1 == y, r2 == width */
 	add r4, r4, r0             /* r0 == x, so r4 == cpu == y*width + x */
 
@@ -86,7 +86,7 @@ ENTRY(_start)
 	/*
 	 * Load up our per-cpu offset.  When the first (master) tile
 	 * boots, this value is still zero, so we will load boot_pc
-	 * with start_kernel, and boot_sp with init_stack + THREAD_SIZE.
+	 * with start_kernel, and boot_sp at the top of init_stack.
 	 * The master tile initializes the per-cpu offset array, so that
 	 * when subsequent (secondary) tiles boot, they will instead load
 	 * from their per-cpu versions of boot_sp and boot_pc.
@@ -126,7 +126,6 @@ ENTRY(_start)
 	lw sp, r1
 	or r4, sp, r4
 	mtspr SPR_SYSTEM_SAVE_K_0, r4  /* save ksp0 + cpu */
-	addi sp, sp, -STACK_TOP_DELTA
 	{
 	  move lr, zero   /* stop backtraces in the called function */
 	  jr r0
@@ -163,8 +162,8 @@ ENTRY(swapper_pg_dir)
 	.set addr, addr + PGDIR_SIZE
 	.endr
 
-	/* The true text VAs are mapped as VA = PA + MEM_SV_INTRPT */
-	PTE MEM_SV_INTRPT, 0, (1 << (HV_PTE_INDEX_READABLE - 32)) | \
+	/* The true text VAs are mapped as VA = PA + MEM_SV_START */
+	PTE MEM_SV_START, 0, (1 << (HV_PTE_INDEX_READABLE - 32)) | \
 			      (1 << (HV_PTE_INDEX_EXECUTABLE - 32))
 	.org swapper_pg_dir + PGDIR_SIZE
 	END(swapper_pg_dir)
diff --git a/arch/tile/kernel/head_64.S b/arch/tile/kernel/head_64.S
index 6093964fa5c7..bd0e12f283f3 100644
--- a/arch/tile/kernel/head_64.S
+++ b/arch/tile/kernel/head_64.S
@@ -25,6 +25,15 @@
 #include <arch/chip.h>
 #include <arch/spr_def.h>
 
+/* Extract two 32-bit bit values that were read into one register. */
+#ifdef __BIG_ENDIAN__
+#define GET_FIRST_INT(rd, rs) shrsi rd, rs, 32
+#define GET_SECOND_INT(rd, rs) addxi rd, rs, 0
+#else
+#define GET_FIRST_INT(rd, rs) addxi rd, rs, 0
+#define GET_SECOND_INT(rd, rs) shrsi rd, rs, 32
+#endif
+
 /*
  * This module contains the entry code for kernel images. It performs the
  * minimal setup needed to call the generic C routines.
@@ -46,11 +55,11 @@ ENTRY(_start)
 	  movei r2, TILE_CHIP_REV
 	  movei r3, KERNEL_PL
 	}
-	jal hv_init
+	jal _hv_init
 	/* Get a reasonable default ASID in r0 */
 	{
 	  move r0, zero
-	  jal hv_inquire_asid
+	  jal _hv_inquire_asid
 	}
 
 	/*
@@ -61,7 +70,7 @@ ENTRY(_start)
 	 * other CPUs should see a properly-constructed page table.
 	 */
 	{
-	  v4int_l r2, zero, r0    /* ASID for hv_install_context */
+	  GET_FIRST_INT(r2, r0)    /* ASID for hv_install_context */
 	  moveli r4, hw1_last(swapper_pgprot - PAGE_OFFSET)
 	}
 	{
@@ -77,7 +86,7 @@ ENTRY(_start)
 	{
 	  /* After initializing swapper_pgprot, HV_PTE_GLOBAL is set. */
 	  bfextu r7, r1, HV_PTE_INDEX_GLOBAL, HV_PTE_INDEX_GLOBAL
-	  inv r4
+	  finv r4
 	}
 	bnez r7, .Lno_write
 	{
@@ -121,29 +130,24 @@ ENTRY(_start)
 	}
 	{
 	  moveli r3, CTX_PAGE_FLAG
-	  j hv_install_context
+	  j _hv_install_context
 	}
 1:
 
 	/* Install the interrupt base. */
-	moveli r0, hw2_last(MEM_SV_START)
-	shl16insli r0, r0, hw1(MEM_SV_START)
-	shl16insli r0, r0, hw0(MEM_SV_START)
+	moveli r0, hw2_last(intrpt_start)
+	shl16insli r0, r0, hw1(intrpt_start)
+	shl16insli r0, r0, hw0(intrpt_start)
 	mtspr SPR_INTERRUPT_VECTOR_BASE_K, r0
 
-	/*
-	 * Get our processor number and save it away in SAVE_K_0.
-	 * Extract stuff from the topology structure: r4 = y, r6 = x,
-	 * r5 = width.  FIXME: consider whether we want to just make these
-	 * 64-bit values (and if so fix smp_topology write below, too).
-	 */
-	jal hv_inquire_topology
+	/* Get our processor number and save it away in SAVE_K_0. */
+	jal _hv_inquire_topology
 	{
-	  v4int_l r5, zero, r1    /* r5 = width */
-	  shrui r4, r0, 32        /* r4 = y */
+	  GET_FIRST_INT(r5, r1)   /* r5 = width */
+	  GET_SECOND_INT(r4, r0)  /* r4 = y */
 	}
 	{
-	  v4int_l r6, zero, r0    /* r6 = x */
+	  GET_FIRST_INT(r6, r0)   /* r6 = x */
 	  mul_lu_lu r4, r4, r5
 	}
 	{
@@ -154,7 +158,7 @@ ENTRY(_start)
 	/*
 	 * Load up our per-cpu offset.  When the first (master) tile
 	 * boots, this value is still zero, so we will load boot_pc
-	 * with start_kernel, and boot_sp with init_stack + THREAD_SIZE.
+	 * with start_kernel, and boot_sp with at the top of init_stack.
 	 * The master tile initializes the per-cpu offset array, so that
 	 * when subsequent (secondary) tiles boot, they will instead load
 	 * from their per-cpu versions of boot_sp and boot_pc.
@@ -198,9 +202,9 @@ ENTRY(_start)
 	}
 	ld r0, r0
 	ld sp, r1
-	or r4, sp, r4
+	shli r4, r4, CPU_SHIFT
+	bfins r4, sp, 0, CPU_SHIFT-1
 	mtspr SPR_SYSTEM_SAVE_K_0, r4  /* save ksp0 + cpu */
-	addi sp, sp, -STACK_TOP_DELTA
 	{
 	  move lr, zero   /* stop backtraces in the called function */
 	  jr r0
diff --git a/arch/tile/kernel/hvglue.S b/arch/tile/kernel/hvglue.S
new file mode 100644
index 000000000000..2ab456622391
--- /dev/null
+++ b/arch/tile/kernel/hvglue.S
@@ -0,0 +1,74 @@
+/* Hypervisor call vector addresses; see <hv/hypervisor.h> */
+.macro gensym sym, val, size
+.org \val
+.global _\sym
+.type _\sym,function
+_\sym:
+.size _\sym,\size
+#ifndef CONFIG_TILE_HVGLUE_TRACE
+.globl \sym
+.set \sym,_\sym
+#endif
+.endm
+
+.section .hvglue,"x",@nobits
+.align 8
+gensym hv_init, 0x20, 32
+gensym hv_install_context, 0x40, 32
+gensym hv_sysconf, 0x60, 32
+gensym hv_get_rtc, 0x80, 32
+gensym hv_set_rtc, 0xa0, 32
+gensym hv_flush_asid, 0xc0, 32
+gensym hv_flush_page, 0xe0, 32
+gensym hv_flush_pages, 0x100, 32
+gensym hv_restart, 0x120, 32
+gensym hv_halt, 0x140, 32
+gensym hv_power_off, 0x160, 32
+gensym hv_inquire_physical, 0x180, 32
+gensym hv_inquire_memory_controller, 0x1a0, 32
+gensym hv_inquire_virtual, 0x1c0, 32
+gensym hv_inquire_asid, 0x1e0, 32
+gensym hv_nanosleep, 0x200, 32
+gensym hv_console_read_if_ready, 0x220, 32
+gensym hv_console_write, 0x240, 32
+gensym hv_downcall_dispatch, 0x260, 32
+gensym hv_inquire_topology, 0x280, 32
+gensym hv_fs_findfile, 0x2a0, 32
+gensym hv_fs_fstat, 0x2c0, 32
+gensym hv_fs_pread, 0x2e0, 32
+gensym hv_physaddr_read64, 0x300, 32
+gensym hv_physaddr_write64, 0x320, 32
+gensym hv_get_command_line, 0x340, 32
+gensym hv_set_caching, 0x360, 32
+gensym hv_bzero_page, 0x380, 32
+gensym hv_register_message_state, 0x3a0, 32
+gensym hv_send_message, 0x3c0, 32
+gensym hv_receive_message, 0x3e0, 32
+gensym hv_inquire_context, 0x400, 32
+gensym hv_start_all_tiles, 0x420, 32
+gensym hv_dev_open, 0x440, 32
+gensym hv_dev_close, 0x460, 32
+gensym hv_dev_pread, 0x480, 32
+gensym hv_dev_pwrite, 0x4a0, 32
+gensym hv_dev_poll, 0x4c0, 32
+gensym hv_dev_poll_cancel, 0x4e0, 32
+gensym hv_dev_preada, 0x500, 32
+gensym hv_dev_pwritea, 0x520, 32
+gensym hv_flush_remote, 0x540, 32
+gensym hv_console_putc, 0x560, 32
+gensym hv_inquire_tiles, 0x580, 32
+gensym hv_confstr, 0x5a0, 32
+gensym hv_reexec, 0x5c0, 32
+gensym hv_set_command_line, 0x5e0, 32
+gensym hv_clear_intr, 0x600, 32
+gensym hv_enable_intr, 0x620, 32
+gensym hv_disable_intr, 0x640, 32
+gensym hv_raise_intr, 0x660, 32
+gensym hv_trigger_ipi, 0x680, 32
+gensym hv_store_mapping, 0x6a0, 32
+gensym hv_inquire_realpa, 0x6c0, 32
+gensym hv_flush_all, 0x6e0, 32
+gensym hv_get_ipi_pte, 0x700, 32
+gensym hv_set_pte_super_shift, 0x720, 32
+gensym hv_console_set_ipi, 0x7e0, 32
+gensym hv_glue_internals, 0x800, 30720
diff --git a/arch/tile/kernel/hvglue.lds b/arch/tile/kernel/hvglue.lds
deleted file mode 100644
index d44c5a67a1ed..000000000000
--- a/arch/tile/kernel/hvglue.lds
+++ /dev/null
@@ -1,59 +0,0 @@
-/* Hypervisor call vector addresses; see <hv/hypervisor.h> */
-hv_init = TEXT_OFFSET + 0x10020;
-hv_install_context = TEXT_OFFSET + 0x10040;
-hv_sysconf = TEXT_OFFSET + 0x10060;
-hv_get_rtc = TEXT_OFFSET + 0x10080;
-hv_set_rtc = TEXT_OFFSET + 0x100a0;
-hv_flush_asid = TEXT_OFFSET + 0x100c0;
-hv_flush_page = TEXT_OFFSET + 0x100e0;
-hv_flush_pages = TEXT_OFFSET + 0x10100;
-hv_restart = TEXT_OFFSET + 0x10120;
-hv_halt = TEXT_OFFSET + 0x10140;
-hv_power_off = TEXT_OFFSET + 0x10160;
-hv_inquire_physical = TEXT_OFFSET + 0x10180;
-hv_inquire_memory_controller = TEXT_OFFSET + 0x101a0;
-hv_inquire_virtual = TEXT_OFFSET + 0x101c0;
-hv_inquire_asid = TEXT_OFFSET + 0x101e0;
-hv_nanosleep = TEXT_OFFSET + 0x10200;
-hv_console_read_if_ready = TEXT_OFFSET + 0x10220;
-hv_console_write = TEXT_OFFSET + 0x10240;
-hv_downcall_dispatch = TEXT_OFFSET + 0x10260;
-hv_inquire_topology = TEXT_OFFSET + 0x10280;
-hv_fs_findfile = TEXT_OFFSET + 0x102a0;
-hv_fs_fstat = TEXT_OFFSET + 0x102c0;
-hv_fs_pread = TEXT_OFFSET + 0x102e0;
-hv_physaddr_read64 = TEXT_OFFSET + 0x10300;
-hv_physaddr_write64 = TEXT_OFFSET + 0x10320;
-hv_get_command_line = TEXT_OFFSET + 0x10340;
-hv_set_caching = TEXT_OFFSET + 0x10360;
-hv_bzero_page = TEXT_OFFSET + 0x10380;
-hv_register_message_state = TEXT_OFFSET + 0x103a0;
-hv_send_message = TEXT_OFFSET + 0x103c0;
-hv_receive_message = TEXT_OFFSET + 0x103e0;
-hv_inquire_context = TEXT_OFFSET + 0x10400;
-hv_start_all_tiles = TEXT_OFFSET + 0x10420;
-hv_dev_open = TEXT_OFFSET + 0x10440;
-hv_dev_close = TEXT_OFFSET + 0x10460;
-hv_dev_pread = TEXT_OFFSET + 0x10480;
-hv_dev_pwrite = TEXT_OFFSET + 0x104a0;
-hv_dev_poll = TEXT_OFFSET + 0x104c0;
-hv_dev_poll_cancel = TEXT_OFFSET + 0x104e0;
-hv_dev_preada = TEXT_OFFSET + 0x10500;
-hv_dev_pwritea = TEXT_OFFSET + 0x10520;
-hv_flush_remote = TEXT_OFFSET + 0x10540;
-hv_console_putc = TEXT_OFFSET + 0x10560;
-hv_inquire_tiles = TEXT_OFFSET + 0x10580;
-hv_confstr = TEXT_OFFSET + 0x105a0;
-hv_reexec = TEXT_OFFSET + 0x105c0;
-hv_set_command_line = TEXT_OFFSET + 0x105e0;
-hv_clear_intr = TEXT_OFFSET + 0x10600;
-hv_enable_intr = TEXT_OFFSET + 0x10620;
-hv_disable_intr = TEXT_OFFSET + 0x10640;
-hv_raise_intr = TEXT_OFFSET + 0x10660;
-hv_trigger_ipi = TEXT_OFFSET + 0x10680;
-hv_store_mapping = TEXT_OFFSET + 0x106a0;
-hv_inquire_realpa = TEXT_OFFSET + 0x106c0;
-hv_flush_all = TEXT_OFFSET + 0x106e0;
-hv_get_ipi_pte = TEXT_OFFSET + 0x10700;
-hv_set_pte_super_shift = TEXT_OFFSET + 0x10720;
-hv_glue_internals = TEXT_OFFSET + 0x10740;
diff --git a/arch/tile/kernel/hvglue_trace.c b/arch/tile/kernel/hvglue_trace.c
new file mode 100644
index 000000000000..85c74ad29312
--- /dev/null
+++ b/arch/tile/kernel/hvglue_trace.c
@@ -0,0 +1,266 @@
+/*
+ * Copyright 2013 Tilera Corporation. All Rights Reserved.
+ *
+ *   This program is free software; you can redistribute it and/or
+ *   modify it under the terms of the GNU General Public License
+ *   as published by the Free Software Foundation, version 2.
+ *
+ *   This program is distributed in the hope that it will be useful, but
+ *   WITHOUT ANY WARRANTY; without even the implied warranty of
+ *   MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ *   NON INFRINGEMENT.  See the GNU General Public License for
+ *   more details.
+ */
+
+/*
+ * Pull in the hypervisor header so we declare all the ABI functions
+ * with the underscore versions, then undef the names so that we can
+ * provide our own wrapper versions.
+ */
+#define hv_init _hv_init
+#define hv_install_context _hv_install_context
+#define hv_sysconf _hv_sysconf
+#define hv_get_rtc _hv_get_rtc
+#define hv_set_rtc _hv_set_rtc
+#define hv_flush_asid _hv_flush_asid
+#define hv_flush_page _hv_flush_page
+#define hv_flush_pages _hv_flush_pages
+#define hv_restart _hv_restart
+#define hv_halt _hv_halt
+#define hv_power_off _hv_power_off
+#define hv_inquire_physical _hv_inquire_physical
+#define hv_inquire_memory_controller _hv_inquire_memory_controller
+#define hv_inquire_virtual _hv_inquire_virtual
+#define hv_inquire_asid _hv_inquire_asid
+#define hv_nanosleep _hv_nanosleep
+#define hv_console_read_if_ready _hv_console_read_if_ready
+#define hv_console_write _hv_console_write
+#define hv_downcall_dispatch _hv_downcall_dispatch
+#define hv_inquire_topology _hv_inquire_topology
+#define hv_fs_findfile _hv_fs_findfile
+#define hv_fs_fstat _hv_fs_fstat
+#define hv_fs_pread _hv_fs_pread
+#define hv_physaddr_read64 _hv_physaddr_read64
+#define hv_physaddr_write64 _hv_physaddr_write64
+#define hv_get_command_line _hv_get_command_line
+#define hv_set_caching _hv_set_caching
+#define hv_bzero_page _hv_bzero_page
+#define hv_register_message_state _hv_register_message_state
+#define hv_send_message _hv_send_message
+#define hv_receive_message _hv_receive_message
+#define hv_inquire_context _hv_inquire_context
+#define hv_start_all_tiles _hv_start_all_tiles
+#define hv_dev_open _hv_dev_open
+#define hv_dev_close _hv_dev_close
+#define hv_dev_pread _hv_dev_pread
+#define hv_dev_pwrite _hv_dev_pwrite
+#define hv_dev_poll _hv_dev_poll
+#define hv_dev_poll_cancel _hv_dev_poll_cancel
+#define hv_dev_preada _hv_dev_preada
+#define hv_dev_pwritea _hv_dev_pwritea
+#define hv_flush_remote _hv_flush_remote
+#define hv_console_putc _hv_console_putc
+#define hv_inquire_tiles _hv_inquire_tiles
+#define hv_confstr _hv_confstr
+#define hv_reexec _hv_reexec
+#define hv_set_command_line _hv_set_command_line
+#define hv_clear_intr _hv_clear_intr
+#define hv_enable_intr _hv_enable_intr
+#define hv_disable_intr _hv_disable_intr
+#define hv_raise_intr _hv_raise_intr
+#define hv_trigger_ipi _hv_trigger_ipi
+#define hv_store_mapping _hv_store_mapping
+#define hv_inquire_realpa _hv_inquire_realpa
+#define hv_flush_all _hv_flush_all
+#define hv_get_ipi_pte _hv_get_ipi_pte
+#define hv_set_pte_super_shift _hv_set_pte_super_shift
+#define hv_console_set_ipi _hv_console_set_ipi
+#include <hv/hypervisor.h>
+#undef hv_init
+#undef hv_install_context
+#undef hv_sysconf
+#undef hv_get_rtc
+#undef hv_set_rtc
+#undef hv_flush_asid
+#undef hv_flush_page
+#undef hv_flush_pages
+#undef hv_restart
+#undef hv_halt
+#undef hv_power_off
+#undef hv_inquire_physical
+#undef hv_inquire_memory_controller
+#undef hv_inquire_virtual
+#undef hv_inquire_asid
+#undef hv_nanosleep
+#undef hv_console_read_if_ready
+#undef hv_console_write
+#undef hv_downcall_dispatch
+#undef hv_inquire_topology
+#undef hv_fs_findfile
+#undef hv_fs_fstat
+#undef hv_fs_pread
+#undef hv_physaddr_read64
+#undef hv_physaddr_write64
+#undef hv_get_command_line
+#undef hv_set_caching
+#undef hv_bzero_page
+#undef hv_register_message_state
+#undef hv_send_message
+#undef hv_receive_message
+#undef hv_inquire_context
+#undef hv_start_all_tiles
+#undef hv_dev_open
+#undef hv_dev_close
+#undef hv_dev_pread
+#undef hv_dev_pwrite
+#undef hv_dev_poll
+#undef hv_dev_poll_cancel
+#undef hv_dev_preada
+#undef hv_dev_pwritea
+#undef hv_flush_remote
+#undef hv_console_putc
+#undef hv_inquire_tiles
+#undef hv_confstr
+#undef hv_reexec
+#undef hv_set_command_line
+#undef hv_clear_intr
+#undef hv_enable_intr
+#undef hv_disable_intr
+#undef hv_raise_intr
+#undef hv_trigger_ipi
+#undef hv_store_mapping
+#undef hv_inquire_realpa
+#undef hv_flush_all
+#undef hv_get_ipi_pte
+#undef hv_set_pte_super_shift
+#undef hv_console_set_ipi
+
+/*
+ * Provide macros based on <linux/syscalls.h> to provide a wrapper
+ * function that invokes the same function with an underscore prefix.
+ * We can't use the existing __SC_xxx macros because we need to
+ * support up to nine arguments rather than up to six, and also this
+ * way the file stands alone from possible changes in the
+ * implementation of <linux/syscalls.h>.
+ */
+#define HV_WRAP0(type, name)					\
+	type name(void);					\
+	type name(void)						\
+	{							\
+		return _##name();				\
+	}
+#define __HV_DECL1(t1, a1)	t1 a1
+#define __HV_DECL2(t2, a2, ...) t2 a2, __HV_DECL1(__VA_ARGS__)
+#define __HV_DECL3(t3, a3, ...) t3 a3, __HV_DECL2(__VA_ARGS__)
+#define __HV_DECL4(t4, a4, ...) t4 a4, __HV_DECL3(__VA_ARGS__)
+#define __HV_DECL5(t5, a5, ...) t5 a5, __HV_DECL4(__VA_ARGS__)
+#define __HV_DECL6(t6, a6, ...) t6 a6, __HV_DECL5(__VA_ARGS__)
+#define __HV_DECL7(t7, a7, ...) t7 a7, __HV_DECL6(__VA_ARGS__)
+#define __HV_DECL8(t8, a8, ...) t8 a8, __HV_DECL7(__VA_ARGS__)
+#define __HV_DECL9(t9, a9, ...) t9 a9, __HV_DECL8(__VA_ARGS__)
+#define __HV_PASS1(t1, a1)	a1
+#define __HV_PASS2(t2, a2, ...) a2, __HV_PASS1(__VA_ARGS__)
+#define __HV_PASS3(t3, a3, ...) a3, __HV_PASS2(__VA_ARGS__)
+#define __HV_PASS4(t4, a4, ...) a4, __HV_PASS3(__VA_ARGS__)
+#define __HV_PASS5(t5, a5, ...) a5, __HV_PASS4(__VA_ARGS__)
+#define __HV_PASS6(t6, a6, ...) a6, __HV_PASS5(__VA_ARGS__)
+#define __HV_PASS7(t7, a7, ...) a7, __HV_PASS6(__VA_ARGS__)
+#define __HV_PASS8(t8, a8, ...) a8, __HV_PASS7(__VA_ARGS__)
+#define __HV_PASS9(t9, a9, ...) a9, __HV_PASS8(__VA_ARGS__)
+#define HV_WRAPx(x, type, name, ...)				\
+	type name(__HV_DECL##x(__VA_ARGS__));			\
+	type name(__HV_DECL##x(__VA_ARGS__))			\
+	{							\
+		return _##name(__HV_PASS##x(__VA_ARGS__));	\
+	}
+#define HV_WRAP1(type, name, ...) HV_WRAPx(1, type, name, __VA_ARGS__)
+#define HV_WRAP2(type, name, ...) HV_WRAPx(2, type, name, __VA_ARGS__)
+#define HV_WRAP3(type, name, ...) HV_WRAPx(3, type, name, __VA_ARGS__)
+#define HV_WRAP4(type, name, ...) HV_WRAPx(4, type, name, __VA_ARGS__)
+#define HV_WRAP5(type, name, ...) HV_WRAPx(5, type, name, __VA_ARGS__)
+#define HV_WRAP6(type, name, ...) HV_WRAPx(6, type, name, __VA_ARGS__)
+#define HV_WRAP7(type, name, ...) HV_WRAPx(7, type, name, __VA_ARGS__)
+#define HV_WRAP8(type, name, ...) HV_WRAPx(8, type, name, __VA_ARGS__)
+#define HV_WRAP9(type, name, ...) HV_WRAPx(9, type, name, __VA_ARGS__)
+
+/* List all the hypervisor API functions. */
+HV_WRAP4(void, hv_init, HV_VersionNumber, interface_version_number,
+	 int, chip_num, int, chip_rev_num, int, client_pl)
+HV_WRAP1(long, hv_sysconf, HV_SysconfQuery, query)
+HV_WRAP3(int, hv_confstr, HV_ConfstrQuery, query, HV_VirtAddr, buf, int, len)
+#if CHIP_HAS_IPI()
+HV_WRAP3(int, hv_get_ipi_pte, HV_Coord, tile, int, pl, HV_PTE*, pte)
+HV_WRAP3(int, hv_console_set_ipi, int, ipi, int, event, HV_Coord, coord);
+#else
+HV_WRAP1(void, hv_enable_intr, HV_IntrMask, enab_mask)
+HV_WRAP1(void, hv_disable_intr, HV_IntrMask, disab_mask)
+HV_WRAP1(void, hv_clear_intr, HV_IntrMask, clear_mask)
+HV_WRAP1(void, hv_raise_intr, HV_IntrMask, raise_mask)
+HV_WRAP2(HV_Errno, hv_trigger_ipi, HV_Coord, tile, int, interrupt)
+#endif /* !CHIP_HAS_IPI() */
+HV_WRAP3(int, hv_store_mapping, HV_VirtAddr, va, unsigned int, len,
+	 HV_PhysAddr, pa)
+HV_WRAP2(HV_PhysAddr, hv_inquire_realpa, HV_PhysAddr, cpa, unsigned int, len)
+HV_WRAP0(HV_RTCTime, hv_get_rtc)
+HV_WRAP1(void, hv_set_rtc, HV_RTCTime, time)
+HV_WRAP4(int, hv_install_context, HV_PhysAddr, page_table, HV_PTE, access,
+	 HV_ASID, asid, __hv32, flags)
+HV_WRAP2(int, hv_set_pte_super_shift, int, level, int, log2_count)
+HV_WRAP0(HV_Context, hv_inquire_context)
+HV_WRAP1(int, hv_flush_asid, HV_ASID, asid)
+HV_WRAP2(int, hv_flush_page, HV_VirtAddr, address, HV_PageSize, page_size)
+HV_WRAP3(int, hv_flush_pages, HV_VirtAddr, start, HV_PageSize, page_size,
+	 unsigned long, size)
+HV_WRAP1(int, hv_flush_all, int, preserve_global)
+HV_WRAP2(void, hv_restart, HV_VirtAddr, cmd, HV_VirtAddr, args)
+HV_WRAP0(void, hv_halt)
+HV_WRAP0(void, hv_power_off)
+HV_WRAP1(int, hv_reexec, HV_PhysAddr, entry)
+HV_WRAP0(HV_Topology, hv_inquire_topology)
+HV_WRAP3(HV_Errno, hv_inquire_tiles, HV_InqTileSet, set, HV_VirtAddr, cpumask,
+	 int, length)
+HV_WRAP1(HV_PhysAddrRange, hv_inquire_physical, int, idx)
+HV_WRAP2(HV_MemoryControllerInfo, hv_inquire_memory_controller, HV_Coord, coord,
+	 int, controller)
+HV_WRAP1(HV_VirtAddrRange, hv_inquire_virtual, int, idx)
+HV_WRAP1(HV_ASIDRange, hv_inquire_asid, int, idx)
+HV_WRAP1(void, hv_nanosleep, int, nanosecs)
+HV_WRAP0(int, hv_console_read_if_ready)
+HV_WRAP1(void, hv_console_putc, int, byte)
+HV_WRAP2(int, hv_console_write, HV_VirtAddr, bytes, int, len)
+HV_WRAP0(void, hv_downcall_dispatch)
+HV_WRAP1(int, hv_fs_findfile, HV_VirtAddr, filename)
+HV_WRAP1(HV_FS_StatInfo, hv_fs_fstat, int, inode)
+HV_WRAP4(int, hv_fs_pread, int, inode, HV_VirtAddr, buf,
+	 int, length, int, offset)
+HV_WRAP2(unsigned long long, hv_physaddr_read64, HV_PhysAddr, addr,
+	 HV_PTE, access)
+HV_WRAP3(void, hv_physaddr_write64, HV_PhysAddr, addr, HV_PTE, access,
+	 unsigned long long, val)
+HV_WRAP2(int, hv_get_command_line, HV_VirtAddr, buf, int, length)
+HV_WRAP2(HV_Errno, hv_set_command_line, HV_VirtAddr, buf, int, length)
+HV_WRAP1(void, hv_set_caching, unsigned long, bitmask)
+HV_WRAP2(void, hv_bzero_page, HV_VirtAddr, va, unsigned int, size)
+HV_WRAP1(HV_Errno, hv_register_message_state, HV_MsgState*, msgstate)
+HV_WRAP4(int, hv_send_message, HV_Recipient *, recips, int, nrecip,
+	 HV_VirtAddr, buf, int, buflen)
+HV_WRAP3(HV_RcvMsgInfo, hv_receive_message, HV_MsgState, msgstate,
+	 HV_VirtAddr, buf, int, buflen)
+HV_WRAP0(void, hv_start_all_tiles)
+HV_WRAP2(int, hv_dev_open, HV_VirtAddr, name, __hv32, flags)
+HV_WRAP1(int, hv_dev_close, int, devhdl)
+HV_WRAP5(int, hv_dev_pread, int, devhdl, __hv32, flags, HV_VirtAddr, va,
+	 __hv32, len, __hv64, offset)
+HV_WRAP5(int, hv_dev_pwrite, int, devhdl, __hv32, flags, HV_VirtAddr, va,
+	 __hv32, len, __hv64, offset)
+HV_WRAP3(int, hv_dev_poll, int, devhdl, __hv32, events, HV_IntArg, intarg)
+HV_WRAP1(int, hv_dev_poll_cancel, int, devhdl)
+HV_WRAP6(int, hv_dev_preada, int, devhdl, __hv32, flags, __hv32, sgl_len,
+	 HV_SGL *, sglp, __hv64, offset, HV_IntArg, intarg)
+HV_WRAP6(int, hv_dev_pwritea, int, devhdl, __hv32, flags, __hv32, sgl_len,
+	 HV_SGL *, sglp, __hv64, offset, HV_IntArg, intarg)
+HV_WRAP9(int, hv_flush_remote, HV_PhysAddr, cache_pa,
+	 unsigned long, cache_control, unsigned long*, cache_cpumask,
+	 HV_VirtAddr, tlb_va, unsigned long, tlb_length,
+	 unsigned long, tlb_pgsize, unsigned long*, tlb_cpumask,
+	 HV_Remote_ASID*, asids, int, asidcount)
diff --git a/arch/tile/kernel/intvec_32.S b/arch/tile/kernel/intvec_32.S
index cb52d66343ed..2cbe6d5dd6b0 100644
--- a/arch/tile/kernel/intvec_32.S
+++ b/arch/tile/kernel/intvec_32.S
@@ -28,20 +28,10 @@
 #include <arch/interrupts.h>
 #include <arch/spr_def.h>
 
-#ifdef CONFIG_PREEMPT
-# error "No support for kernel preemption currently"
-#endif
-
 #define PTREGS_PTR(reg, ptreg) addli reg, sp, C_ABI_SAVE_AREA_SIZE + (ptreg)
 
 #define PTREGS_OFFSET_SYSCALL PTREGS_OFFSET_REG(TREG_SYSCALL_NR)
 
-#if !CHIP_HAS_WH64()
-	/* By making this an empty macro, we can use wh64 in the code. */
-	.macro  wh64 reg
-	.endm
-#endif
-
 	.macro  push_reg reg, ptr=sp, delta=-4
 	{
 	 sw     \ptr, \reg
@@ -189,7 +179,7 @@ intvec_\vecname:
 	 * point sp at the top aligned address on the actual stack page.
 	 */
 	mfspr   r0, SPR_SYSTEM_SAVE_K_0
-	mm      r0, r0, zero, LOG2_THREAD_SIZE, 31
+	mm      r0, r0, zero, LOG2_NR_CPU_IDS, 31
 
 0:
 	/*
@@ -207,6 +197,9 @@ intvec_\vecname:
 	 *    cache line 1: r14...r29
 	 *    cache line 0: 2 x frame, r0..r13
 	 */
+#if STACK_TOP_DELTA != 64
+#error STACK_TOP_DELTA must be 64 for assumptions here and in task_pt_regs()
+#endif
 	andi    r0, r0, -64
 
 	/*
@@ -326,18 +319,14 @@ intvec_\vecname:
 	 movei  r3, -1   /* not used, but set for consistency */
 	}
 	.else
-#if CHIP_HAS_AUX_PERF_COUNTERS()
 	.ifc \c_routine, op_handle_aux_perf_interrupt
 	{
 	 mfspr  r2, AUX_PERF_COUNT_STS
 	 movei  r3, -1   /* not used, but set for consistency */
 	}
 	.else
-#endif
 	movei   r3, 0
-#if CHIP_HAS_AUX_PERF_COUNTERS()
 	.endif
-#endif
 	.endif
 	.endif
 	.endif
@@ -354,7 +343,7 @@ intvec_\vecname:
 #ifdef __COLLECT_LINKER_FEEDBACK__
 	.pushsection .text.intvec_feedback,"ax"
 	.org    (\vecnum << 5)
-	FEEDBACK_ENTER_EXPLICIT(intvec_\vecname, .intrpt1, 1 << 8)
+	FEEDBACK_ENTER_EXPLICIT(intvec_\vecname, .intrpt, 1 << 8)
 	jrp     lr
 	.popsection
 #endif
@@ -468,7 +457,7 @@ intvec_\vecname:
 	}
 	{
 	 auli   r21, r21, ha16(__per_cpu_offset)
-	 mm     r20, r20, zero, 0, LOG2_THREAD_SIZE-1
+	 mm     r20, r20, zero, 0, LOG2_NR_CPU_IDS-1
 	}
 	s2a     r20, r20, r21
 	lw      tp, r20
@@ -562,7 +551,6 @@ intvec_\vecname:
 	.endif
 	mtspr   INTERRUPT_CRITICAL_SECTION, zero
 
-#if CHIP_HAS_WH64()
 	/*
 	 * Prepare the first 256 stack bytes to be rapidly accessible
 	 * without having to fetch the background data.  We don't really
@@ -583,7 +571,6 @@ intvec_\vecname:
 	 addi   r52, r52, -64
 	}
 	wh64    r52
-#endif
 
 #ifdef CONFIG_TRACE_IRQFLAGS
 	.ifnc \function,handle_nmi
@@ -762,7 +749,7 @@ intvec_\vecname:
 	.macro  dc_dispatch vecnum, vecname
 	.org    (\vecnum << 8)
 intvec_\vecname:
-	j       hv_downcall_dispatch
+	j       _hv_downcall_dispatch
 	ENDPROC(intvec_\vecname)
 	.endm
 
@@ -812,17 +799,37 @@ STD_ENTRY(interrupt_return)
 	}
 	lw      r29, r29
 	andi    r29, r29, SPR_EX_CONTEXT_1_1__PL_MASK  /* mask off ICS */
+	bzt     r29, .Lresume_userspace
+
+#ifdef CONFIG_PREEMPT
+	/* Returning to kernel space. Check if we need preemption. */
+	GET_THREAD_INFO(r29)
+	addli   r28, r29, THREAD_INFO_FLAGS_OFFSET
 	{
-	 bzt    r29, .Lresume_userspace
-	 PTREGS_PTR(r29, PTREGS_OFFSET_PC)
+	 lw     r28, r28
+	 addli  r29, r29, THREAD_INFO_PREEMPT_COUNT_OFFSET
 	}
+	{
+	 andi   r28, r28, _TIF_NEED_RESCHED
+	 lw     r29, r29
+	}
+	bzt     r28, 1f
+	bnz     r29, 1f
+	/* Disable interrupts explicitly for preemption. */
+	IRQ_DISABLE(r20,r21)
+	TRACE_IRQS_OFF
+	jal     preempt_schedule_irq
+	FEEDBACK_REENTER(interrupt_return)
+1:
+#endif
 
 	/* If we're resuming to _cpu_idle_nap, bump PC forward by 8. */
 	{
-	 lw     r28, r29
+	 PTREGS_PTR(r29, PTREGS_OFFSET_PC)
 	 moveli r27, lo16(_cpu_idle_nap)
 	}
 	{
+	 lw     r28, r29
 	 auli   r27, r27, ha16(_cpu_idle_nap)
 	}
 	{
@@ -1420,7 +1427,6 @@ handle_ill:
 	{
 	 lw     r0, r0          /* indirect thru thread_info to get task_info*/
 	 addi   r1, sp, C_ABI_SAVE_AREA_SIZE  /* put ptregs pointer into r1 */
-	 move   r2, zero        /* load error code into r2 */
 	}
 
 	jal     send_sigtrap    /* issue a SIGTRAP */
@@ -1518,12 +1524,10 @@ STD_ENTRY(_sys_clone)
 	__HEAD
 	.align 64
 	/* Align much later jump on the start of a cache line. */
-#if !ATOMIC_LOCKS_FOUND_VIA_TABLE()
 	nop
 #if PAGE_SIZE >= 0x10000
 	nop
 #endif
-#endif
 ENTRY(sys_cmpxchg)
 
 	/*
@@ -1557,45 +1561,6 @@ ENTRY(sys_cmpxchg)
 # error Code here assumes PAGE_OFFSET can be loaded with just hi16()
 #endif
 
-#if ATOMIC_LOCKS_FOUND_VIA_TABLE()
-	{
-	 /* Check for unaligned input. */
-	 bnz    sp, .Lcmpxchg_badaddr
-	 mm     r25, r0, zero, 3, PAGE_SHIFT-1
-	}
-	{
-	 crc32_32 r25, zero, r25
-	 moveli r21, lo16(atomic_lock_ptr)
-	}
-	{
-	 auli   r21, r21, ha16(atomic_lock_ptr)
-	 auli   r23, zero, hi16(PAGE_OFFSET)  /* hugepage-aligned */
-	}
-	{
-	 shri	r20, r25, 32 - ATOMIC_HASH_L1_SHIFT
-	 slt_u  r23, r0, r23
-	 lw	r26, r0  /* see comment in the "#else" for the "lw r26". */
-	}
-	{
-	 s2a    r21, r20, r21
-	 bbns   r23, .Lcmpxchg_badaddr
-	}
-	{
-	 lw     r21, r21
-	 seqi	r23, TREG_SYSCALL_NR_NAME, __NR_FAST_cmpxchg64
-	 andi	r25, r25, ATOMIC_HASH_L2_SIZE - 1
-	}
-	{
-	 /* Branch away at this point if we're doing a 64-bit cmpxchg. */
-	 bbs    r23, .Lcmpxchg64
-	 andi   r23, r0, 7       /* Precompute alignment for cmpxchg64. */
-	}
-	{
-	 s2a	ATOMIC_LOCK_REG_NAME, r25, r21
-	 j      .Lcmpxchg32_tns   /* see comment in the #else for the jump. */
-	}
-
-#else /* ATOMIC_LOCKS_FOUND_VIA_TABLE() */
 	{
 	 /* Check for unaligned input. */
 	 bnz    sp, .Lcmpxchg_badaddr
@@ -1609,7 +1574,7 @@ ENTRY(sys_cmpxchg)
 	  * Because of C pointer arithmetic, we want to compute this:
 	  *
 	  * ((char*)atomic_locks +
-	  *  (((r0 >> 3) & (1 << (ATOMIC_HASH_SIZE - 1))) << 2))
+	  *  (((r0 >> 3) & ((1 << ATOMIC_HASH_SHIFT) - 1)) << 2))
 	  *
 	  * Instead of two shifts we just ">> 1", and use 'mm'
 	  * to ignore the low and high bits we don't want.
@@ -1620,12 +1585,9 @@ ENTRY(sys_cmpxchg)
 
 	 /*
 	  * Ensure that the TLB is loaded before we take out the lock.
-	  * On tilepro, this will start fetching the value all the way
-	  * into our L1 as well (and if it gets modified before we
-	  * grab the lock, it will be invalidated from our cache
-	  * before we reload it).  On tile64, we'll start fetching it
-	  * into our L1 if we're the home, and if we're not, we'll
-	  * still at least start fetching it into the home's L2.
+	  * This will start fetching the value all the way into our L1
+	  * as well (and if it gets modified before we grab the lock,
+	  * it will be invalidated from our cache before we reload it).
 	  */
 	 lw	r26, r0
 	}
@@ -1668,8 +1630,6 @@ ENTRY(sys_cmpxchg)
 	 j      .Lcmpxchg32_tns
 	}
 
-#endif /* ATOMIC_LOCKS_FOUND_VIA_TABLE() */
-
 /* Symbol for do_page_fault_ics() to use to compare against the PC. */
 .global __sys_cmpxchg_grab_lock
 __sys_cmpxchg_grab_lock:
@@ -1807,9 +1767,6 @@ __sys_cmpxchg_grab_lock:
 	.align 64
 .Lcmpxchg64:
 	{
-#if ATOMIC_LOCKS_FOUND_VIA_TABLE()
-	 s2a	ATOMIC_LOCK_REG_NAME, r25, r21
-#endif
 	 bzt     r23, .Lcmpxchg64_tns
 	}
 	j       .Lcmpxchg_badaddr
@@ -1875,8 +1832,8 @@ int_unalign:
 	push_extra_callee_saves r0
 	j       do_trap
 
-/* Include .intrpt1 array of interrupt vectors */
-	.section ".intrpt1", "ax"
+/* Include .intrpt array of interrupt vectors */
+	.section ".intrpt", "ax"
 
 #define op_handle_perf_interrupt bad_intr
 #define op_handle_aux_perf_interrupt bad_intr
@@ -1944,10 +1901,8 @@ int_unalign:
 		     do_page_fault
 	int_hand     INT_SN_CPL, SN_CPL, bad_intr
 	int_hand     INT_DOUBLE_FAULT, DOUBLE_FAULT, do_trap
-#if CHIP_HAS_AUX_PERF_COUNTERS()
 	int_hand     INT_AUX_PERF_COUNT, AUX_PERF_COUNT, \
 		     op_handle_aux_perf_interrupt, handle_nmi
-#endif
 
 	/* Synthetic interrupt delivered only by the simulator */
 	int_hand     INT_BREAKPOINT, BREAKPOINT, do_breakpoint
diff --git a/arch/tile/kernel/intvec_64.S b/arch/tile/kernel/intvec_64.S
index 85d483957027..b8fc497f2437 100644
--- a/arch/tile/kernel/intvec_64.S
+++ b/arch/tile/kernel/intvec_64.S
@@ -17,25 +17,33 @@
 #include <linux/linkage.h>
 #include <linux/errno.h>
 #include <linux/unistd.h>
+#include <linux/init.h>
 #include <asm/ptrace.h>
 #include <asm/thread_info.h>
 #include <asm/irqflags.h>
 #include <asm/asm-offsets.h>
 #include <asm/types.h>
+#include <asm/traps.h>
 #include <asm/signal.h>
 #include <hv/hypervisor.h>
 #include <arch/abi.h>
 #include <arch/interrupts.h>
 #include <arch/spr_def.h>
 
-#ifdef CONFIG_PREEMPT
-# error "No support for kernel preemption currently"
-#endif
-
 #define PTREGS_PTR(reg, ptreg) addli reg, sp, C_ABI_SAVE_AREA_SIZE + (ptreg)
 
 #define PTREGS_OFFSET_SYSCALL PTREGS_OFFSET_REG(TREG_SYSCALL_NR)
 
+#if CONFIG_KERNEL_PL == 1 || CONFIG_KERNEL_PL == 2
+/*
+ * Set "result" non-zero if ex1 holds the PL of the kernel
+ * (with or without ICS being set).  Note this works only
+ * because we never find the PL at level 3.
+ */
+# define IS_KERNEL_EX1(result, ex1) andi result, ex1, CONFIG_KERNEL_PL
+#else
+# error Recode IS_KERNEL_EX1 for CONFIG_KERNEL_PL
+#endif
 
 	.macro  push_reg reg, ptr=sp, delta=-8
 	{
@@ -98,6 +106,185 @@
 	}
 	.endm
 
+	/*
+	 * Unalign data exception fast handling: In order to handle
+	 * unaligned data access, a fast JIT version is generated and stored
+	 * in a specific area in user space. We first need to do a quick poke
+	 * to see if the JIT is available. We use certain bits in the fault
+	 * PC (3 to 9 is used for 16KB page size) as index to address the JIT
+	 * code area. The first 64bit word is the fault PC, and the 2nd one is
+	 * the fault bundle itself. If these 2 words both match, then we
+	 * directly "iret" to JIT code. If not, a slow path is invoked to
+	 * generate new JIT code. Note: the current JIT code WILL be
+	 * overwritten if it existed. So, ideally we can handle 128 unalign
+	 * fixups via JIT. For lookup efficiency and to effectively support
+	 * tight loops with multiple unaligned reference, a simple
+	 * direct-mapped cache is used.
+	 *
+	 * SPR_EX_CONTEXT_K_0 is modified to return to JIT code.
+	 * SPR_EX_CONTEXT_K_1 has ICS set.
+	 * SPR_EX_CONTEXT_0_0 is setup to user program's next PC.
+	 * SPR_EX_CONTEXT_0_1 = 0.
+	 */
+	.macro int_hand_unalign_fast  vecnum, vecname
+	.org  (\vecnum << 8)
+intvec_\vecname:
+	/* Put r3 in SPR_SYSTEM_SAVE_K_1.  */
+	mtspr   SPR_SYSTEM_SAVE_K_1, r3
+
+	mfspr   r3, SPR_EX_CONTEXT_K_1
+	/*
+	 * Examine if exception comes from user without ICS set.
+	 * If not, just go directly to the slow path.
+	 */
+	bnez    r3, hand_unalign_slow_nonuser
+
+	mfspr   r3, SPR_SYSTEM_SAVE_K_0
+
+	/* Get &thread_info->unalign_jit_tmp[0] in r3. */
+	bfexts  r3, r3, 0, CPU_SHIFT-1
+	mm      r3, zero, LOG2_THREAD_SIZE, 63
+	addli   r3, r3, THREAD_INFO_UNALIGN_JIT_TMP_OFFSET
+
+	/*
+	 * Save r0, r1, r2 into thread_info array r3 points to
+	 * from low to high memory in order.
+	 */
+	st_add  r3, r0, 8
+	st_add  r3, r1, 8
+	{
+	 st_add r3, r2, 8
+	 andi   r2, sp, 7
+	}
+
+	/* Save stored r3 value so we can revert it on a page fault. */
+	mfspr   r1, SPR_SYSTEM_SAVE_K_1
+	st      r3, r1
+
+	{
+	 /* Generate a SIGBUS if sp is not 8-byte aligned. */
+	 bnez   r2, hand_unalign_slow_badsp
+	}
+
+	/*
+	 * Get the thread_info in r0; load r1 with pc. Set the low bit of sp
+	 * as an indicator to the page fault code in case we fault.
+	 */
+	{
+	 ori    sp, sp, 1
+	 mfspr  r1, SPR_EX_CONTEXT_K_0
+	}
+
+	/* Add the jit_info offset in thread_info; extract r1 [3:9] into r2. */
+	{
+	 addli  r0, r3, THREAD_INFO_UNALIGN_JIT_BASE_OFFSET - \
+	  (THREAD_INFO_UNALIGN_JIT_TMP_OFFSET + (3 * 8))
+	 bfextu r2, r1, 3, (2 + PAGE_SHIFT - UNALIGN_JIT_SHIFT)
+	}
+
+	/* Load the jit_info; multiply r2 by 128. */
+	{
+	 ld     r0, r0
+	 shli   r2, r2, UNALIGN_JIT_SHIFT
+	}
+
+	/*
+	 * If r0 is NULL, the JIT page is not mapped, so go to slow path;
+	 * add offset r2 to r0 at the same time.
+	 */
+	{
+	 beqz   r0, hand_unalign_slow
+	 add    r2, r0, r2
+	}
+
+        /*
+	 * We are loading from userspace (both the JIT info PC and
+	 * instruction word, and the instruction word we executed)
+	 * and since either could fault while holding the interrupt
+	 * critical section, we must tag this region and check it in
+	 * do_page_fault() to handle it properly.
+	 */
+ENTRY(__start_unalign_asm_code)
+
+	/* Load first word of JIT in r0 and increment r2 by 8. */
+	ld_add  r0, r2, 8
+
+	/*
+	 * Compare the PC with the 1st word in JIT; load the fault bundle
+	 * into r1.
+	 */
+	{
+	 cmpeq  r0, r0, r1
+	 ld     r1, r1
+	}
+
+	/* Go to slow path if PC doesn't match. */
+	beqz    r0, hand_unalign_slow
+
+	/*
+	 * Load the 2nd word of JIT, which is supposed to be the fault
+	 * bundle for a cache hit. Increment r2; after this bundle r2 will
+	 * point to the potential start of the JIT code we want to run.
+	 */
+	ld_add  r0, r2, 8
+
+	/* No further accesses to userspace are done after this point. */
+ENTRY(__end_unalign_asm_code)
+
+	/* Compare the real bundle with what is saved in the JIT area. */
+	{
+	 cmpeq  r0, r1, r0
+	 mtspr  SPR_EX_CONTEXT_0_1, zero
+	}
+
+	/* Go to slow path if the fault bundle does not match. */
+	beqz    r0, hand_unalign_slow
+
+	/*
+	 * A cache hit is found.
+	 * r2 points to start of JIT code (3rd word).
+	 * r0 is the fault pc.
+	 * r1 is the fault bundle.
+	 * Reset the low bit of sp.
+	 */
+	{
+	 mfspr  r0, SPR_EX_CONTEXT_K_0
+	 andi   sp, sp, ~1
+	}
+
+	/* Write r2 into EX_CONTEXT_K_0 and increment PC. */
+	{
+	 mtspr  SPR_EX_CONTEXT_K_0, r2
+	 addi   r0, r0, 8
+	}
+
+	/*
+	 * Set ICS on kernel EX_CONTEXT_K_1 in order to "iret" to
+	 * user with ICS set. This way, if the JIT fixup causes another
+	 * unalign exception (which shouldn't be possible) the user
+	 * process will be terminated with SIGBUS. Also, our fixup will
+	 * run without interleaving with external interrupts.
+	 * Each fixup is at most 14 bundles, so it won't hold ICS for long.
+	 */
+	{
+	 movei  r1, PL_ICS_EX1(USER_PL, 1)
+	 mtspr  SPR_EX_CONTEXT_0_0, r0
+	}
+
+	{
+	 mtspr  SPR_EX_CONTEXT_K_1, r1
+	 addi   r3, r3, -(3 * 8)
+	}
+
+	/* Restore r0..r3. */
+	ld_add  r0, r3, 8
+	ld_add  r1, r3, 8
+	ld_add  r2, r3, 8
+	ld      r3, r3
+
+	iret
+	ENDPROC(intvec_\vecname)
+	.endm
 
 #ifdef __COLLECT_LINKER_FEEDBACK__
 	.pushsection .text.intvec_feedback,"ax"
@@ -118,15 +305,21 @@ intvec_feedback:
 	 * The "processing" argument specifies the code for processing
 	 * the interrupt. Defaults to "handle_interrupt".
 	 */
-	.macro  int_hand vecnum, vecname, c_routine, processing=handle_interrupt
-	.org    (\vecnum << 8)
+	.macro __int_hand vecnum, vecname, c_routine,processing=handle_interrupt
 intvec_\vecname:
 	/* Temporarily save a register so we have somewhere to work. */
 
 	mtspr   SPR_SYSTEM_SAVE_K_1, r0
 	mfspr   r0, SPR_EX_CONTEXT_K_1
 
-	andi    r0, r0, SPR_EX_CONTEXT_1_1__PL_MASK  /* mask off ICS */
+	/*
+	 * The unalign data fastpath code sets the low bit in sp to
+	 * force us to reset it here on fault.
+	 */
+	{
+	 blbs   sp, 2f
+	 IS_KERNEL_EX1(r0, r0)
+	}
 
 	.ifc    \vecnum, INT_DOUBLE_FAULT
 	/*
@@ -176,15 +369,15 @@ intvec_\vecname:
 	}
 	.endif
 
-
+2:
 	/*
-	 * SYSTEM_SAVE_K_0 holds the cpu number in the low bits, and
-	 * the current stack top in the higher bits.  So we recover
-	 * our stack top by just masking off the low bits, then
+	 * SYSTEM_SAVE_K_0 holds the cpu number in the high bits, and
+	 * the current stack top in the lower bits.  So we recover
+	 * our starting stack value by sign-extending the low bits, then
 	 * point sp at the top aligned address on the actual stack page.
 	 */
 	mfspr   r0, SPR_SYSTEM_SAVE_K_0
-	mm      r0, zero, LOG2_THREAD_SIZE, 63
+	bfexts  r0, r0, 0, CPU_SHIFT-1
 
 0:
 	/*
@@ -206,6 +399,9 @@ intvec_\vecname:
 	 *    cache line 1: r6...r13
 	 *    cache line 0: 2 x frame, r0..r5
 	 */
+#if STACK_TOP_DELTA != 64
+#error STACK_TOP_DELTA must be 64 for assumptions here and in task_pt_regs()
+#endif
 	andi    r0, r0, -64
 
 	/*
@@ -305,7 +501,7 @@ intvec_\vecname:
 	mfspr   r3, SPR_SYSTEM_SAVE_K_2   /* info about page fault */
 	.else
 	.ifc \vecnum, INT_ILL_TRANS
-	mfspr   r2, ILL_TRANS_REASON
+	mfspr   r2, ILL_VA_PC
 	.else
 	.ifc \vecnum, INT_DOUBLE_FAULT
 	mfspr   r2, SPR_SYSTEM_SAVE_K_2   /* double fault info from HV */
@@ -315,12 +511,10 @@ intvec_\vecname:
 	.else
 	.ifc \c_routine, op_handle_perf_interrupt
 	mfspr   r2, PERF_COUNT_STS
-#if CHIP_HAS_AUX_PERF_COUNTERS()
 	.else
 	.ifc \c_routine, op_handle_aux_perf_interrupt
 	mfspr   r2, AUX_PERF_COUNT_STS
 	.endif
-#endif
 	.endif
 	.endif
 	.endif
@@ -339,7 +533,7 @@ intvec_\vecname:
 #ifdef __COLLECT_LINKER_FEEDBACK__
 	.pushsection .text.intvec_feedback,"ax"
 	.org    (\vecnum << 5)
-	FEEDBACK_ENTER_EXPLICIT(intvec_\vecname, .intrpt1, 1 << 8)
+	FEEDBACK_ENTER_EXPLICIT(intvec_\vecname, .intrpt, 1 << 8)
 	jrp     lr
 	.popsection
 #endif
@@ -455,11 +649,12 @@ intvec_\vecname:
 	/*
 	 * If we will be returning to the kernel, we will need to
 	 * reset the interrupt masks to the state they had before.
-	 * Set DISABLE_IRQ in flags iff we came from PL1 with irqs disabled.
+	 * Set DISABLE_IRQ in flags iff we came from kernel pl with
+	 * irqs disabled.
 	 */
 	mfspr   r32, SPR_EX_CONTEXT_K_1
 	{
-	 andi   r32, r32, SPR_EX_CONTEXT_1_1__PL_MASK  /* mask off ICS */
+	 IS_KERNEL_EX1(r22, r22)
 	 PTREGS_PTR(r21, PTREGS_OFFSET_FLAGS)
 	}
 	beqzt   r32, 1f       /* zero if from user space */
@@ -503,7 +698,7 @@ intvec_\vecname:
 	}
 	{
 	 shl16insli r21, r21, hw1(__per_cpu_offset)
-	 bfextu r20, r20, 0, LOG2_THREAD_SIZE-1
+	 bfextu r20, r20, CPU_SHIFT, 63
 	}
 	shl16insli r21, r21, hw0(__per_cpu_offset)
 	shl3add r20, r20, r21
@@ -585,7 +780,7 @@ intvec_\vecname:
 	.macro  dc_dispatch vecnum, vecname
 	.org    (\vecnum << 8)
 intvec_\vecname:
-	j       hv_downcall_dispatch
+	j       _hv_downcall_dispatch
 	ENDPROC(intvec_\vecname)
 	.endm
 
@@ -626,14 +821,39 @@ STD_ENTRY(interrupt_return)
 	 PTREGS_PTR(r29, PTREGS_OFFSET_EX1)
 	}
 	ld      r29, r29
-	andi    r29, r29, SPR_EX_CONTEXT_1_1__PL_MASK  /* mask off ICS */
+	IS_KERNEL_EX1(r29, r29)
 	{
 	 beqzt  r29, .Lresume_userspace
-	 PTREGS_PTR(r29, PTREGS_OFFSET_PC)
+	 move   r29, sp
+	}
+
+#ifdef CONFIG_PREEMPT
+	/* Returning to kernel space. Check if we need preemption. */
+	EXTRACT_THREAD_INFO(r29)
+	addli   r28, r29, THREAD_INFO_FLAGS_OFFSET
+	{
+	 ld     r28, r28
+	 addli  r29, r29, THREAD_INFO_PREEMPT_COUNT_OFFSET
+	}
+	{
+	 andi   r28, r28, _TIF_NEED_RESCHED
+	 ld4s   r29, r29
 	}
+	beqzt   r28, 1f
+	bnez    r29, 1f
+	/* Disable interrupts explicitly for preemption. */
+	IRQ_DISABLE(r20,r21)
+	TRACE_IRQS_OFF
+	jal     preempt_schedule_irq
+	FEEDBACK_REENTER(interrupt_return)
+1:
+#endif
 
 	/* If we're resuming to _cpu_idle_nap, bump PC forward by 8. */
-	moveli  r27, hw2_last(_cpu_idle_nap)
+	{
+	 moveli r27, hw2_last(_cpu_idle_nap)
+	 PTREGS_PTR(r29, PTREGS_OFFSET_PC)
+	}
 	{
 	 ld     r28, r29
 	 shl16insli r27, r27, hw1(_cpu_idle_nap)
@@ -728,7 +948,7 @@ STD_ENTRY(interrupt_return)
 	 PTREGS_PTR(r32, PTREGS_OFFSET_FLAGS)
 	}
 	{
-	 andi   r0, r0, SPR_EX_CONTEXT_1_1__PL_MASK
+	 IS_KERNEL_EX1(r0, r0)
 	 ld     r32, r32
 	}
 	bnez    r0, 1f
@@ -799,7 +1019,7 @@ STD_ENTRY(interrupt_return)
 	pop_reg r21, sp, PTREGS_OFFSET_REG(31) - PTREGS_OFFSET_PC
 	{
 	 mtspr  SPR_EX_CONTEXT_K_1, lr
-	 andi   lr, lr, SPR_EX_CONTEXT_1_1__PL_MASK  /* mask off ICS */
+	 IS_KERNEL_EX1(lr, lr)
 	}
 	{
 	 mtspr  SPR_EX_CONTEXT_K_0, r21
@@ -1223,10 +1443,31 @@ STD_ENTRY(_sys_clone)
 	j       sys_clone
 	STD_ENDPROC(_sys_clone)
 
-/* The single-step support may need to read all the registers. */
+	/*
+	 * Recover r3, r2, r1 and r0 here saved by unalign fast vector.
+	 * The vector area limit is 32 bundles, so we handle the reload here.
+	 * r0, r1, r2 are in thread_info from low to high memory in order.
+	 * r3 points to location the original r3 was saved.
+	 * We put this code in the __HEAD section so it can be reached
+	 * via a conditional branch from the fast path.
+	 */
+	__HEAD
+hand_unalign_slow:
+	andi    sp, sp, ~1
+hand_unalign_slow_badsp:
+	addi    r3, r3, -(3 * 8)
+	ld_add  r0, r3, 8
+	ld_add  r1, r3, 8
+	ld      r2, r3
+hand_unalign_slow_nonuser:
+	mfspr   r3, SPR_SYSTEM_SAVE_K_1
+	__int_hand     INT_UNALIGN_DATA, UNALIGN_DATA_SLOW, int_unalign
+
+/* The unaligned data support needs to read all the registers. */
 int_unalign:
 	push_extra_callee_saves r0
-	j       do_trap
+	j       do_unaligned
+ENDPROC(hand_unalign_slow)
 
 /* Fill the return address stack with nonzero entries. */
 STD_ENTRY(fill_ra_stack)
@@ -1240,8 +1481,15 @@ STD_ENTRY(fill_ra_stack)
 4:	jrp	r0
 	STD_ENDPROC(fill_ra_stack)
 
-/* Include .intrpt1 array of interrupt vectors */
-	.section ".intrpt1", "ax"
+	.macro int_hand  vecnum, vecname, c_routine, processing=handle_interrupt
+	.org   (\vecnum << 8)
+		__int_hand   \vecnum, \vecname, \c_routine, \processing
+	.endm
+
+/* Include .intrpt array of interrupt vectors */
+	.section ".intrpt", "ax"
+	.global intrpt_start
+intrpt_start:
 
 #define op_handle_perf_interrupt bad_intr
 #define op_handle_aux_perf_interrupt bad_intr
@@ -1272,7 +1520,7 @@ STD_ENTRY(fill_ra_stack)
 	int_hand     INT_SWINT_1, SWINT_1, SYSCALL, handle_syscall
 	int_hand     INT_SWINT_0, SWINT_0, do_trap
 	int_hand     INT_ILL_TRANS, ILL_TRANS, do_trap
-	int_hand     INT_UNALIGN_DATA, UNALIGN_DATA, int_unalign
+	int_hand_unalign_fast INT_UNALIGN_DATA, UNALIGN_DATA
 	int_hand     INT_DTLB_MISS, DTLB_MISS, do_page_fault
 	int_hand     INT_DTLB_ACCESS, DTLB_ACCESS, do_page_fault
 	int_hand     INT_IDN_FIREWALL, IDN_FIREWALL, do_hardwall_trap
diff --git a/arch/tile/kernel/irq.c b/arch/tile/kernel/irq.c
index 3ccf2cd7182e..0586fdb9352d 100644
--- a/arch/tile/kernel/irq.c
+++ b/arch/tile/kernel/irq.c
@@ -55,7 +55,8 @@ static DEFINE_PER_CPU(int, irq_depth);
 
 /* State for allocating IRQs on Gx. */
 #if CHIP_HAS_IPI()
-static unsigned long available_irqs = ~(1UL << IRQ_RESCHEDULE);
+static unsigned long available_irqs = ((1UL << NR_IRQS) - 1) &
+				      (~(1UL << IRQ_RESCHEDULE));
 static DEFINE_SPINLOCK(available_irqs_lock);
 #endif
 
@@ -73,7 +74,8 @@ static DEFINE_SPINLOCK(available_irqs_lock);
 
 /*
  * The interrupt handling path, implemented in terms of HV interrupt
- * emulation on TILE64 and TILEPro, and IPI hardware on TILE-Gx.
+ * emulation on TILEPro, and IPI hardware on TILE-Gx.
+ * Entered with interrupts disabled.
  */
 void tile_dev_intr(struct pt_regs *regs, int intnum)
 {
@@ -233,7 +235,7 @@ void tile_irq_activate(unsigned int irq, int tile_irq_type)
 {
 	/*
 	 * We use handle_level_irq() by default because the pending
-	 * interrupt vector (whether modeled by the HV on TILE64 and
+	 * interrupt vector (whether modeled by the HV on
 	 * TILEPro or implemented in hardware on TILE-Gx) has
 	 * level-style semantics for each bit.  An interrupt fires
 	 * whenever a bit is high, not just at edges.
diff --git a/arch/tile/kernel/kgdb.c b/arch/tile/kernel/kgdb.c
new file mode 100644
index 000000000000..4cd88381a83e
--- /dev/null
+++ b/arch/tile/kernel/kgdb.c
@@ -0,0 +1,499 @@
+/*
+ * Copyright 2013 Tilera Corporation. All Rights Reserved.
+ *
+ *   This program is free software; you can redistribute it and/or
+ *   modify it under the terms of the GNU General Public License
+ *   as published by the Free Software Foundation, version 2.
+ *
+ *   This program is distributed in the hope that it will be useful, but
+ *   WITHOUT ANY WARRANTY; without even the implied warranty of
+ *   MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ *   NON INFRINGEMENT.  See the GNU General Public License for
+ *   more details.
+ *
+ * TILE-Gx KGDB support.
+ */
+
+#include <linux/ptrace.h>
+#include <linux/kgdb.h>
+#include <linux/kdebug.h>
+#include <linux/uaccess.h>
+#include <linux/module.h>
+#include <asm/cacheflush.h>
+
+static tile_bundle_bits singlestep_insn = TILEGX_BPT_BUNDLE | DIE_SSTEPBP;
+static unsigned long stepped_addr;
+static tile_bundle_bits stepped_instr;
+
+struct dbg_reg_def_t dbg_reg_def[DBG_MAX_REG_NUM] = {
+	{ "r0", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[0])},
+	{ "r1", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[1])},
+	{ "r2", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[2])},
+	{ "r3", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[3])},
+	{ "r4", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[4])},
+	{ "r5", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[5])},
+	{ "r6", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[6])},
+	{ "r7", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[7])},
+	{ "r8", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[8])},
+	{ "r9", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[9])},
+	{ "r10", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[10])},
+	{ "r11", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[11])},
+	{ "r12", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[12])},
+	{ "r13", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[13])},
+	{ "r14", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[14])},
+	{ "r15", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[15])},
+	{ "r16", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[16])},
+	{ "r17", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[17])},
+	{ "r18", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[18])},
+	{ "r19", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[19])},
+	{ "r20", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[20])},
+	{ "r21", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[21])},
+	{ "r22", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[22])},
+	{ "r23", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[23])},
+	{ "r24", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[24])},
+	{ "r25", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[25])},
+	{ "r26", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[26])},
+	{ "r27", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[27])},
+	{ "r28", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[28])},
+	{ "r29", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[29])},
+	{ "r30", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[30])},
+	{ "r31", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[31])},
+	{ "r32", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[32])},
+	{ "r33", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[33])},
+	{ "r34", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[34])},
+	{ "r35", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[35])},
+	{ "r36", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[36])},
+	{ "r37", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[37])},
+	{ "r38", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[38])},
+	{ "r39", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[39])},
+	{ "r40", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[40])},
+	{ "r41", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[41])},
+	{ "r42", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[42])},
+	{ "r43", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[43])},
+	{ "r44", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[44])},
+	{ "r45", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[45])},
+	{ "r46", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[46])},
+	{ "r47", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[47])},
+	{ "r48", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[48])},
+	{ "r49", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[49])},
+	{ "r50", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[50])},
+	{ "r51", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[51])},
+	{ "r52", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[52])},
+	{ "tp", GDB_SIZEOF_REG, offsetof(struct pt_regs, tp)},
+	{ "sp", GDB_SIZEOF_REG, offsetof(struct pt_regs, sp)},
+	{ "lr", GDB_SIZEOF_REG, offsetof(struct pt_regs, lr)},
+	{ "sn", GDB_SIZEOF_REG, -1},
+	{ "idn0", GDB_SIZEOF_REG, -1},
+	{ "idn1", GDB_SIZEOF_REG, -1},
+	{ "udn0", GDB_SIZEOF_REG, -1},
+	{ "udn1", GDB_SIZEOF_REG, -1},
+	{ "udn2", GDB_SIZEOF_REG, -1},
+	{ "udn3", GDB_SIZEOF_REG, -1},
+	{ "zero", GDB_SIZEOF_REG, -1},
+	{ "pc", GDB_SIZEOF_REG, offsetof(struct pt_regs, pc)},
+	{ "faultnum", GDB_SIZEOF_REG, offsetof(struct pt_regs, faultnum)},
+};
+
+char *dbg_get_reg(int regno, void *mem, struct pt_regs *regs)
+{
+	if (regno >= DBG_MAX_REG_NUM || regno < 0)
+		return NULL;
+
+	if (dbg_reg_def[regno].offset != -1)
+		memcpy(mem, (void *)regs + dbg_reg_def[regno].offset,
+		       dbg_reg_def[regno].size);
+	else
+		memset(mem, 0, dbg_reg_def[regno].size);
+	return dbg_reg_def[regno].name;
+}
+
+int dbg_set_reg(int regno, void *mem, struct pt_regs *regs)
+{
+	if (regno >= DBG_MAX_REG_NUM || regno < 0)
+		return -EINVAL;
+
+	if (dbg_reg_def[regno].offset != -1)
+		memcpy((void *)regs + dbg_reg_def[regno].offset, mem,
+		       dbg_reg_def[regno].size);
+	return 0;
+}
+
+/*
+ * Similar to pt_regs_to_gdb_regs() except that process is sleeping and so
+ * we may not be able to get all the info.
+ */
+void
+sleeping_thread_to_gdb_regs(unsigned long *gdb_regs, struct task_struct *task)
+{
+	int reg;
+	struct pt_regs *thread_regs;
+	unsigned long *ptr = gdb_regs;
+
+	if (task == NULL)
+		return;
+
+	/* Initialize to zero. */
+	memset(gdb_regs, 0, NUMREGBYTES);
+
+	thread_regs = task_pt_regs(task);
+	for (reg = 0; reg <= TREG_LAST_GPR; reg++)
+		*(ptr++) = thread_regs->regs[reg];
+
+	gdb_regs[TILEGX_PC_REGNUM] = thread_regs->pc;
+	gdb_regs[TILEGX_FAULTNUM_REGNUM] = thread_regs->faultnum;
+}
+
+void kgdb_arch_set_pc(struct pt_regs *regs, unsigned long pc)
+{
+	regs->pc = pc;
+}
+
+static void kgdb_call_nmi_hook(void *ignored)
+{
+	kgdb_nmicallback(raw_smp_processor_id(), NULL);
+}
+
+void kgdb_roundup_cpus(unsigned long flags)
+{
+	local_irq_enable();
+	smp_call_function(kgdb_call_nmi_hook, NULL, 0);
+	local_irq_disable();
+}
+
+/*
+ * Convert a kernel address to the writable kernel text mapping.
+ */
+static unsigned long writable_address(unsigned long addr)
+{
+	unsigned long ret = 0;
+
+	if (core_kernel_text(addr))
+		ret = addr - MEM_SV_START + PAGE_OFFSET;
+	else if (is_module_text_address(addr))
+		ret = addr;
+	else
+		pr_err("Unknown virtual address 0x%lx\n", addr);
+
+	return ret;
+}
+
+/*
+ * Calculate the new address for after a step.
+ */
+static unsigned long get_step_address(struct pt_regs *regs)
+{
+	int src_reg;
+	int jump_off;
+	int br_off;
+	unsigned long addr;
+	unsigned int opcode;
+	tile_bundle_bits bundle;
+
+	/* Move to the next instruction by default. */
+	addr = regs->pc + TILEGX_BUNDLE_SIZE_IN_BYTES;
+	bundle = *(unsigned long *)instruction_pointer(regs);
+
+	/* 0: X mode, Otherwise: Y mode. */
+	if (bundle & TILEGX_BUNDLE_MODE_MASK) {
+		if (get_Opcode_Y1(bundle) == RRR_1_OPCODE_Y1 &&
+		    get_RRROpcodeExtension_Y1(bundle) ==
+		    UNARY_RRR_1_OPCODE_Y1) {
+			opcode = get_UnaryOpcodeExtension_Y1(bundle);
+
+			switch (opcode) {
+			case JALR_UNARY_OPCODE_Y1:
+			case JALRP_UNARY_OPCODE_Y1:
+			case JR_UNARY_OPCODE_Y1:
+			case JRP_UNARY_OPCODE_Y1:
+				src_reg = get_SrcA_Y1(bundle);
+				dbg_get_reg(src_reg, &addr, regs);
+				break;
+			}
+		}
+	} else if (get_Opcode_X1(bundle) == RRR_0_OPCODE_X1) {
+		if (get_RRROpcodeExtension_X1(bundle) ==
+		    UNARY_RRR_0_OPCODE_X1) {
+			opcode = get_UnaryOpcodeExtension_X1(bundle);
+
+			switch (opcode) {
+			case JALR_UNARY_OPCODE_X1:
+			case JALRP_UNARY_OPCODE_X1:
+			case JR_UNARY_OPCODE_X1:
+			case JRP_UNARY_OPCODE_X1:
+				src_reg = get_SrcA_X1(bundle);
+				dbg_get_reg(src_reg, &addr, regs);
+				break;
+			}
+		}
+	} else if (get_Opcode_X1(bundle) == JUMP_OPCODE_X1) {
+		opcode = get_JumpOpcodeExtension_X1(bundle);
+
+		switch (opcode) {
+		case JAL_JUMP_OPCODE_X1:
+		case J_JUMP_OPCODE_X1:
+			jump_off = sign_extend(get_JumpOff_X1(bundle), 27);
+			addr = regs->pc +
+				(jump_off << TILEGX_LOG2_BUNDLE_SIZE_IN_BYTES);
+			break;
+		}
+	} else if (get_Opcode_X1(bundle) == BRANCH_OPCODE_X1) {
+		br_off = 0;
+		opcode = get_BrType_X1(bundle);
+
+		switch (opcode) {
+		case BEQZT_BRANCH_OPCODE_X1:
+		case BEQZ_BRANCH_OPCODE_X1:
+			if (get_SrcA_X1(bundle) == 0)
+				br_off = get_BrOff_X1(bundle);
+			break;
+		case BGEZT_BRANCH_OPCODE_X1:
+		case BGEZ_BRANCH_OPCODE_X1:
+			if (get_SrcA_X1(bundle) >= 0)
+				br_off = get_BrOff_X1(bundle);
+			break;
+		case BGTZT_BRANCH_OPCODE_X1:
+		case BGTZ_BRANCH_OPCODE_X1:
+			if (get_SrcA_X1(bundle) > 0)
+				br_off = get_BrOff_X1(bundle);
+			break;
+		case BLBCT_BRANCH_OPCODE_X1:
+		case BLBC_BRANCH_OPCODE_X1:
+			if (!(get_SrcA_X1(bundle) & 1))
+				br_off = get_BrOff_X1(bundle);
+			break;
+		case BLBST_BRANCH_OPCODE_X1:
+		case BLBS_BRANCH_OPCODE_X1:
+			if (get_SrcA_X1(bundle) & 1)
+				br_off = get_BrOff_X1(bundle);
+			break;
+		case BLEZT_BRANCH_OPCODE_X1:
+		case BLEZ_BRANCH_OPCODE_X1:
+			if (get_SrcA_X1(bundle) <= 0)
+				br_off = get_BrOff_X1(bundle);
+			break;
+		case BLTZT_BRANCH_OPCODE_X1:
+		case BLTZ_BRANCH_OPCODE_X1:
+			if (get_SrcA_X1(bundle) < 0)
+				br_off = get_BrOff_X1(bundle);
+			break;
+		case BNEZT_BRANCH_OPCODE_X1:
+		case BNEZ_BRANCH_OPCODE_X1:
+			if (get_SrcA_X1(bundle) != 0)
+				br_off = get_BrOff_X1(bundle);
+			break;
+		}
+
+		if (br_off != 0) {
+			br_off = sign_extend(br_off, 17);
+			addr = regs->pc +
+				(br_off << TILEGX_LOG2_BUNDLE_SIZE_IN_BYTES);
+		}
+	}
+
+	return addr;
+}
+
+/*
+ * Replace the next instruction after the current instruction with a
+ * breakpoint instruction.
+ */
+static void do_single_step(struct pt_regs *regs)
+{
+	unsigned long addr_wr;
+
+	/* Determine where the target instruction will send us to. */
+	stepped_addr = get_step_address(regs);
+	probe_kernel_read((char *)&stepped_instr, (char *)stepped_addr,
+			  BREAK_INSTR_SIZE);
+
+	addr_wr = writable_address(stepped_addr);
+	probe_kernel_write((char *)addr_wr, (char *)&singlestep_insn,
+			   BREAK_INSTR_SIZE);
+	smp_wmb();
+	flush_icache_range(stepped_addr, stepped_addr + BREAK_INSTR_SIZE);
+}
+
+static void undo_single_step(struct pt_regs *regs)
+{
+	unsigned long addr_wr;
+
+	if (stepped_instr == 0)
+		return;
+
+	addr_wr = writable_address(stepped_addr);
+	probe_kernel_write((char *)addr_wr, (char *)&stepped_instr,
+			   BREAK_INSTR_SIZE);
+	stepped_instr = 0;
+	smp_wmb();
+	flush_icache_range(stepped_addr, stepped_addr + BREAK_INSTR_SIZE);
+}
+
+/*
+ * Calls linux_debug_hook before the kernel dies. If KGDB is enabled,
+ * then try to fall into the debugger.
+ */
+static int
+kgdb_notify(struct notifier_block *self, unsigned long cmd, void *ptr)
+{
+	int ret;
+	unsigned long flags;
+	struct die_args *args = (struct die_args *)ptr;
+	struct pt_regs *regs = args->regs;
+
+#ifdef CONFIG_KPROBES
+	/*
+	 * Return immediately if the kprobes fault notifier has set
+	 * DIE_PAGE_FAULT.
+	 */
+	if (cmd == DIE_PAGE_FAULT)
+		return NOTIFY_DONE;
+#endif /* CONFIG_KPROBES */
+
+	switch (cmd) {
+	case DIE_BREAK:
+	case DIE_COMPILED_BPT:
+		break;
+	case DIE_SSTEPBP:
+		local_irq_save(flags);
+		kgdb_handle_exception(0, SIGTRAP, 0, regs);
+		local_irq_restore(flags);
+		return NOTIFY_STOP;
+	default:
+		/* Userspace events, ignore. */
+		if (user_mode(regs))
+			return NOTIFY_DONE;
+	}
+
+	local_irq_save(flags);
+	ret = kgdb_handle_exception(args->trapnr, args->signr, args->err, regs);
+	local_irq_restore(flags);
+	if (ret)
+		return NOTIFY_DONE;
+
+	return NOTIFY_STOP;
+}
+
+static struct notifier_block kgdb_notifier = {
+	.notifier_call = kgdb_notify,
+};
+
+/*
+ * kgdb_arch_handle_exception - Handle architecture specific GDB packets.
+ * @vector: The error vector of the exception that happened.
+ * @signo: The signal number of the exception that happened.
+ * @err_code: The error code of the exception that happened.
+ * @remcom_in_buffer: The buffer of the packet we have read.
+ * @remcom_out_buffer: The buffer of %BUFMAX bytes to write a packet into.
+ * @regs: The &struct pt_regs of the current process.
+ *
+ * This function MUST handle the 'c' and 's' command packets,
+ * as well packets to set / remove a hardware breakpoint, if used.
+ * If there are additional packets which the hardware needs to handle,
+ * they are handled here. The code should return -1 if it wants to
+ * process more packets, and a %0 or %1 if it wants to exit from the
+ * kgdb callback.
+ */
+int kgdb_arch_handle_exception(int vector, int signo, int err_code,
+			       char *remcom_in_buffer, char *remcom_out_buffer,
+			       struct pt_regs *regs)
+{
+	char *ptr;
+	unsigned long address;
+
+	/* Undo any stepping we may have done. */
+	undo_single_step(regs);
+
+	switch (remcom_in_buffer[0]) {
+	case 'c':
+	case 's':
+	case 'D':
+	case 'k':
+		/*
+		 * Try to read optional parameter, pc unchanged if no parm.
+		 * If this was a compiled-in breakpoint, we need to move
+		 * to the next instruction or we will just breakpoint
+		 * over and over again.
+		 */
+		ptr = &remcom_in_buffer[1];
+		if (kgdb_hex2long(&ptr, &address))
+			regs->pc = address;
+		else if (*(unsigned long *)regs->pc == compiled_bpt)
+			regs->pc += BREAK_INSTR_SIZE;
+
+		if (remcom_in_buffer[0] == 's') {
+			do_single_step(regs);
+			kgdb_single_step = 1;
+			atomic_set(&kgdb_cpu_doing_single_step,
+				   raw_smp_processor_id());
+		} else
+			atomic_set(&kgdb_cpu_doing_single_step, -1);
+
+		return 0;
+	}
+
+	return -1; /* this means that we do not want to exit from the handler */
+}
+
+struct kgdb_arch arch_kgdb_ops;
+
+/*
+ * kgdb_arch_init - Perform any architecture specific initalization.
+ *
+ * This function will handle the initalization of any architecture
+ * specific callbacks.
+ */
+int kgdb_arch_init(void)
+{
+	tile_bundle_bits bundle = TILEGX_BPT_BUNDLE;
+
+	memcpy(arch_kgdb_ops.gdb_bpt_instr, &bundle, BREAK_INSTR_SIZE);
+	return register_die_notifier(&kgdb_notifier);
+}
+
+/*
+ * kgdb_arch_exit - Perform any architecture specific uninitalization.
+ *
+ * This function will handle the uninitalization of any architecture
+ * specific callbacks, for dynamic registration and unregistration.
+ */
+void kgdb_arch_exit(void)
+{
+	unregister_die_notifier(&kgdb_notifier);
+}
+
+int kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt)
+{
+	int err;
+	unsigned long addr_wr = writable_address(bpt->bpt_addr);
+
+	if (addr_wr == 0)
+		return -1;
+
+	err = probe_kernel_read(bpt->saved_instr, (char *)bpt->bpt_addr,
+				BREAK_INSTR_SIZE);
+	if (err)
+		return err;
+
+	err = probe_kernel_write((char *)addr_wr, arch_kgdb_ops.gdb_bpt_instr,
+				 BREAK_INSTR_SIZE);
+	smp_wmb();
+	flush_icache_range((unsigned long)bpt->bpt_addr,
+			   (unsigned long)bpt->bpt_addr + BREAK_INSTR_SIZE);
+	return err;
+}
+
+int kgdb_arch_remove_breakpoint(struct kgdb_bkpt *bpt)
+{
+	int err;
+	unsigned long addr_wr = writable_address(bpt->bpt_addr);
+
+	if (addr_wr == 0)
+		return -1;
+
+	err = probe_kernel_write((char *)addr_wr, (char *)bpt->saved_instr,
+				 BREAK_INSTR_SIZE);
+	smp_wmb();
+	flush_icache_range((unsigned long)bpt->bpt_addr,
+			   (unsigned long)bpt->bpt_addr + BREAK_INSTR_SIZE);
+	return err;
+}
diff --git a/arch/tile/kernel/kprobes.c b/arch/tile/kernel/kprobes.c
new file mode 100644
index 000000000000..27cdcacbe81d
--- /dev/null
+++ b/arch/tile/kernel/kprobes.c
@@ -0,0 +1,528 @@
+/*
+ * arch/tile/kernel/kprobes.c
+ * Kprobes on TILE-Gx
+ *
+ * Some portions copied from the MIPS version.
+ *
+ * Copyright (C) IBM Corporation, 2002, 2004
+ * Copyright 2006 Sony Corp.
+ * Copyright 2010 Cavium Networks
+ *
+ * Copyright 2012 Tilera Corporation. All Rights Reserved.
+ *
+ *   This program is free software; you can redistribute it and/or
+ *   modify it under the terms of the GNU General Public License
+ *   as published by the Free Software Foundation, version 2.
+ *
+ *   This program is distributed in the hope that it will be useful, but
+ *   WITHOUT ANY WARRANTY; without even the implied warranty of
+ *   MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ *   NON INFRINGEMENT.  See the GNU General Public License for
+ *   more details.
+ */
+
+#include <linux/kprobes.h>
+#include <linux/kdebug.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/uaccess.h>
+#include <asm/cacheflush.h>
+
+#include <arch/opcode.h>
+
+DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL;
+DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);
+
+tile_bundle_bits breakpoint_insn = TILEGX_BPT_BUNDLE;
+tile_bundle_bits breakpoint2_insn = TILEGX_BPT_BUNDLE | DIE_SSTEPBP;
+
+/*
+ * Check whether instruction is branch or jump, or if executing it
+ * has different results depending on where it is executed (e.g. lnk).
+ */
+static int __kprobes insn_has_control(kprobe_opcode_t insn)
+{
+	if (get_Mode(insn) != 0) {   /* Y-format bundle */
+		if (get_Opcode_Y1(insn) != RRR_1_OPCODE_Y1 ||
+		    get_RRROpcodeExtension_Y1(insn) != UNARY_RRR_1_OPCODE_Y1)
+			return 0;
+
+		switch (get_UnaryOpcodeExtension_Y1(insn)) {
+		case JALRP_UNARY_OPCODE_Y1:
+		case JALR_UNARY_OPCODE_Y1:
+		case JRP_UNARY_OPCODE_Y1:
+		case JR_UNARY_OPCODE_Y1:
+		case LNK_UNARY_OPCODE_Y1:
+			return 1;
+		default:
+			return 0;
+		}
+	}
+
+	switch (get_Opcode_X1(insn)) {
+	case BRANCH_OPCODE_X1:	/* branch instructions */
+	case JUMP_OPCODE_X1:	/* jump instructions: j and jal */
+		return 1;
+
+	case RRR_0_OPCODE_X1:   /* other jump instructions */
+		if (get_RRROpcodeExtension_X1(insn) != UNARY_RRR_0_OPCODE_X1)
+			return 0;
+		switch (get_UnaryOpcodeExtension_X1(insn)) {
+		case JALRP_UNARY_OPCODE_X1:
+		case JALR_UNARY_OPCODE_X1:
+		case JRP_UNARY_OPCODE_X1:
+		case JR_UNARY_OPCODE_X1:
+		case LNK_UNARY_OPCODE_X1:
+			return 1;
+		default:
+			return 0;
+		}
+	default:
+		return 0;
+	}
+}
+
+int __kprobes arch_prepare_kprobe(struct kprobe *p)
+{
+	unsigned long addr = (unsigned long)p->addr;
+
+	if (addr & (sizeof(kprobe_opcode_t) - 1))
+		return -EINVAL;
+
+	if (insn_has_control(*p->addr)) {
+		pr_notice("Kprobes for control instructions are not "
+			  "supported\n");
+		return -EINVAL;
+	}
+
+	/* insn: must be on special executable page on tile. */
+	p->ainsn.insn = get_insn_slot();
+	if (!p->ainsn.insn)
+		return -ENOMEM;
+
+	/*
+	 * In the kprobe->ainsn.insn[] array we store the original
+	 * instruction at index zero and a break trap instruction at
+	 * index one.
+	 */
+	memcpy(&p->ainsn.insn[0], p->addr, sizeof(kprobe_opcode_t));
+	p->ainsn.insn[1] = breakpoint2_insn;
+	p->opcode = *p->addr;
+
+	return 0;
+}
+
+void __kprobes arch_arm_kprobe(struct kprobe *p)
+{
+	unsigned long addr_wr;
+
+	/* Operate on writable kernel text mapping. */
+	addr_wr = (unsigned long)p->addr - MEM_SV_START + PAGE_OFFSET;
+
+	if (probe_kernel_write((void *)addr_wr, &breakpoint_insn,
+		sizeof(breakpoint_insn)))
+		pr_err("%s: failed to enable kprobe\n", __func__);
+
+	smp_wmb();
+	flush_insn_slot(p);
+}
+
+void __kprobes arch_disarm_kprobe(struct kprobe *kp)
+{
+	unsigned long addr_wr;
+
+	/* Operate on writable kernel text mapping. */
+	addr_wr = (unsigned long)kp->addr - MEM_SV_START + PAGE_OFFSET;
+
+	if (probe_kernel_write((void *)addr_wr, &kp->opcode,
+		sizeof(kp->opcode)))
+		pr_err("%s: failed to enable kprobe\n", __func__);
+
+	smp_wmb();
+	flush_insn_slot(kp);
+}
+
+void __kprobes arch_remove_kprobe(struct kprobe *p)
+{
+	if (p->ainsn.insn) {
+		free_insn_slot(p->ainsn.insn, 0);
+		p->ainsn.insn = NULL;
+	}
+}
+
+static void __kprobes save_previous_kprobe(struct kprobe_ctlblk *kcb)
+{
+	kcb->prev_kprobe.kp = kprobe_running();
+	kcb->prev_kprobe.status = kcb->kprobe_status;
+	kcb->prev_kprobe.saved_pc = kcb->kprobe_saved_pc;
+}
+
+static void __kprobes restore_previous_kprobe(struct kprobe_ctlblk *kcb)
+{
+	__this_cpu_write(current_kprobe, kcb->prev_kprobe.kp);
+	kcb->kprobe_status = kcb->prev_kprobe.status;
+	kcb->kprobe_saved_pc = kcb->prev_kprobe.saved_pc;
+}
+
+static void __kprobes set_current_kprobe(struct kprobe *p, struct pt_regs *regs,
+			struct kprobe_ctlblk *kcb)
+{
+	__this_cpu_write(current_kprobe, p);
+	kcb->kprobe_saved_pc = regs->pc;
+}
+
+static void __kprobes prepare_singlestep(struct kprobe *p, struct pt_regs *regs)
+{
+	/* Single step inline if the instruction is a break. */
+	if (p->opcode == breakpoint_insn ||
+	    p->opcode == breakpoint2_insn)
+		regs->pc = (unsigned long)p->addr;
+	else
+		regs->pc = (unsigned long)&p->ainsn.insn[0];
+}
+
+static int __kprobes kprobe_handler(struct pt_regs *regs)
+{
+	struct kprobe *p;
+	int ret = 0;
+	kprobe_opcode_t *addr;
+	struct kprobe_ctlblk *kcb;
+
+	addr = (kprobe_opcode_t *)regs->pc;
+
+	/*
+	 * We don't want to be preempted for the entire
+	 * duration of kprobe processing.
+	 */
+	preempt_disable();
+	kcb = get_kprobe_ctlblk();
+
+	/* Check we're not actually recursing. */
+	if (kprobe_running()) {
+		p = get_kprobe(addr);
+		if (p) {
+			if (kcb->kprobe_status == KPROBE_HIT_SS &&
+			    p->ainsn.insn[0] == breakpoint_insn) {
+				goto no_kprobe;
+			}
+			/*
+			 * We have reentered the kprobe_handler(), since
+			 * another probe was hit while within the handler.
+			 * We here save the original kprobes variables and
+			 * just single step on the instruction of the new probe
+			 * without calling any user handlers.
+			 */
+			save_previous_kprobe(kcb);
+			set_current_kprobe(p, regs, kcb);
+			kprobes_inc_nmissed_count(p);
+			prepare_singlestep(p, regs);
+			kcb->kprobe_status = KPROBE_REENTER;
+			return 1;
+		} else {
+			if (*addr != breakpoint_insn) {
+				/*
+				 * The breakpoint instruction was removed by
+				 * another cpu right after we hit, no further
+				 * handling of this interrupt is appropriate.
+				 */
+				ret = 1;
+				goto no_kprobe;
+			}
+			p = __this_cpu_read(current_kprobe);
+			if (p->break_handler && p->break_handler(p, regs))
+				goto ss_probe;
+		}
+		goto no_kprobe;
+	}
+
+	p = get_kprobe(addr);
+	if (!p) {
+		if (*addr != breakpoint_insn) {
+			/*
+			 * The breakpoint instruction was removed right
+			 * after we hit it.  Another cpu has removed
+			 * either a probepoint or a debugger breakpoint
+			 * at this address.  In either case, no further
+			 * handling of this interrupt is appropriate.
+			 */
+			ret = 1;
+		}
+		/* Not one of ours: let kernel handle it. */
+		goto no_kprobe;
+	}
+
+	set_current_kprobe(p, regs, kcb);
+	kcb->kprobe_status = KPROBE_HIT_ACTIVE;
+
+	if (p->pre_handler && p->pre_handler(p, regs)) {
+		/* Handler has already set things up, so skip ss setup. */
+		return 1;
+	}
+
+ss_probe:
+	prepare_singlestep(p, regs);
+	kcb->kprobe_status = KPROBE_HIT_SS;
+	return 1;
+
+no_kprobe:
+	preempt_enable_no_resched();
+	return ret;
+}
+
+/*
+ * Called after single-stepping.  p->addr is the address of the
+ * instruction that has been replaced by the breakpoint. To avoid the
+ * SMP problems that can occur when we temporarily put back the
+ * original opcode to single-step, we single-stepped a copy of the
+ * instruction.  The address of this copy is p->ainsn.insn.
+ *
+ * This function prepares to return from the post-single-step
+ * breakpoint trap.
+ */
+static void __kprobes resume_execution(struct kprobe *p,
+				       struct pt_regs *regs,
+				       struct kprobe_ctlblk *kcb)
+{
+	unsigned long orig_pc = kcb->kprobe_saved_pc;
+	regs->pc = orig_pc + 8;
+}
+
+static inline int post_kprobe_handler(struct pt_regs *regs)
+{
+	struct kprobe *cur = kprobe_running();
+	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
+
+	if (!cur)
+		return 0;
+
+	if ((kcb->kprobe_status != KPROBE_REENTER) && cur->post_handler) {
+		kcb->kprobe_status = KPROBE_HIT_SSDONE;
+		cur->post_handler(cur, regs, 0);
+	}
+
+	resume_execution(cur, regs, kcb);
+
+	/* Restore back the original saved kprobes variables and continue. */
+	if (kcb->kprobe_status == KPROBE_REENTER) {
+		restore_previous_kprobe(kcb);
+		goto out;
+	}
+	reset_current_kprobe();
+out:
+	preempt_enable_no_resched();
+
+	return 1;
+}
+
+static inline int kprobe_fault_handler(struct pt_regs *regs, int trapnr)
+{
+	struct kprobe *cur = kprobe_running();
+	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
+
+	if (cur->fault_handler && cur->fault_handler(cur, regs, trapnr))
+		return 1;
+
+	if (kcb->kprobe_status & KPROBE_HIT_SS) {
+		/*
+		 * We are here because the instruction being single
+		 * stepped caused a page fault. We reset the current
+		 * kprobe and the ip points back to the probe address
+		 * and allow the page fault handler to continue as a
+		 * normal page fault.
+		 */
+		resume_execution(cur, regs, kcb);
+		reset_current_kprobe();
+		preempt_enable_no_resched();
+	}
+	return 0;
+}
+
+/*
+ * Wrapper routine for handling exceptions.
+ */
+int __kprobes kprobe_exceptions_notify(struct notifier_block *self,
+				       unsigned long val, void *data)
+{
+	struct die_args *args = (struct die_args *)data;
+	int ret = NOTIFY_DONE;
+
+	switch (val) {
+	case DIE_BREAK:
+		if (kprobe_handler(args->regs))
+			ret = NOTIFY_STOP;
+		break;
+	case DIE_SSTEPBP:
+		if (post_kprobe_handler(args->regs))
+			ret = NOTIFY_STOP;
+		break;
+	case DIE_PAGE_FAULT:
+		/* kprobe_running() needs smp_processor_id(). */
+		preempt_disable();
+
+		if (kprobe_running()
+		    && kprobe_fault_handler(args->regs, args->trapnr))
+			ret = NOTIFY_STOP;
+		preempt_enable();
+		break;
+	default:
+		break;
+	}
+	return ret;
+}
+
+int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
+{
+	struct jprobe *jp = container_of(p, struct jprobe, kp);
+	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
+
+	kcb->jprobe_saved_regs = *regs;
+	kcb->jprobe_saved_sp = regs->sp;
+
+	memcpy(kcb->jprobes_stack, (void *)kcb->jprobe_saved_sp,
+	       MIN_JPROBES_STACK_SIZE(kcb->jprobe_saved_sp));
+
+	regs->pc = (unsigned long)(jp->entry);
+
+	return 1;
+}
+
+/* Defined in the inline asm below. */
+void jprobe_return_end(void);
+
+void __kprobes jprobe_return(void)
+{
+	asm volatile(
+		"bpt\n\t"
+		".globl jprobe_return_end\n"
+		"jprobe_return_end:\n");
+}
+
+int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
+{
+	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
+
+	if (regs->pc >= (unsigned long)jprobe_return &&
+	    regs->pc <= (unsigned long)jprobe_return_end) {
+		*regs = kcb->jprobe_saved_regs;
+		memcpy((void *)kcb->jprobe_saved_sp, kcb->jprobes_stack,
+		       MIN_JPROBES_STACK_SIZE(kcb->jprobe_saved_sp));
+		preempt_enable_no_resched();
+
+		return 1;
+	}
+	return 0;
+}
+
+/*
+ * Function return probe trampoline:
+ * - init_kprobes() establishes a probepoint here
+ * - When the probed function returns, this probe causes the
+ *   handlers to fire
+ */
+static void __used kretprobe_trampoline_holder(void)
+{
+	asm volatile(
+		"nop\n\t"
+		".global kretprobe_trampoline\n"
+		"kretprobe_trampoline:\n\t"
+		"nop\n\t"
+		: : : "memory");
+}
+
+void kretprobe_trampoline(void);
+
+void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri,
+				      struct pt_regs *regs)
+{
+	ri->ret_addr = (kprobe_opcode_t *) regs->lr;
+
+	/* Replace the return addr with trampoline addr */
+	regs->lr = (unsigned long)kretprobe_trampoline;
+}
+
+/*
+ * Called when the probe at kretprobe trampoline is hit.
+ */
+static int __kprobes trampoline_probe_handler(struct kprobe *p,
+						struct pt_regs *regs)
+{
+	struct kretprobe_instance *ri = NULL;
+	struct hlist_head *head, empty_rp;
+	struct hlist_node *tmp;
+	unsigned long flags, orig_ret_address = 0;
+	unsigned long trampoline_address = (unsigned long)kretprobe_trampoline;
+
+	INIT_HLIST_HEAD(&empty_rp);
+	kretprobe_hash_lock(current, &head, &flags);
+
+	/*
+	 * It is possible to have multiple instances associated with a given
+	 * task either because multiple functions in the call path have
+	 * a return probe installed on them, and/or more than one return
+	 * return probe was registered for a target function.
+	 *
+	 * We can handle this because:
+	 *     - instances are always inserted at the head of the list
+	 *     - when multiple return probes are registered for the same
+	 *       function, the first instance's ret_addr will point to the
+	 *       real return address, and all the rest will point to
+	 *       kretprobe_trampoline
+	 */
+	hlist_for_each_entry_safe(ri, tmp, head, hlist) {
+		if (ri->task != current)
+			/* another task is sharing our hash bucket */
+			continue;
+
+		if (ri->rp && ri->rp->handler)
+			ri->rp->handler(ri, regs);
+
+		orig_ret_address = (unsigned long)ri->ret_addr;
+		recycle_rp_inst(ri, &empty_rp);
+
+		if (orig_ret_address != trampoline_address) {
+			/*
+			 * This is the real return address. Any other
+			 * instances associated with this task are for
+			 * other calls deeper on the call stack
+			 */
+			break;
+		}
+	}
+
+	kretprobe_assert(ri, orig_ret_address, trampoline_address);
+	instruction_pointer(regs) = orig_ret_address;
+
+	reset_current_kprobe();
+	kretprobe_hash_unlock(current, &flags);
+	preempt_enable_no_resched();
+
+	hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
+		hlist_del(&ri->hlist);
+		kfree(ri);
+	}
+	/*
+	 * By returning a non-zero value, we are telling
+	 * kprobe_handler() that we don't want the post_handler
+	 * to run (and have re-enabled preemption)
+	 */
+	return 1;
+}
+
+int __kprobes arch_trampoline_kprobe(struct kprobe *p)
+{
+	if (p->addr == (kprobe_opcode_t *)kretprobe_trampoline)
+		return 1;
+
+	return 0;
+}
+
+static struct kprobe trampoline_p = {
+	.addr = (kprobe_opcode_t *)kretprobe_trampoline,
+	.pre_handler = trampoline_probe_handler
+};
+
+int __init arch_init_kprobes(void)
+{
+	register_kprobe(&trampoline_p);
+	return 0;
+}
diff --git a/arch/tile/kernel/mcount_64.S b/arch/tile/kernel/mcount_64.S
new file mode 100644
index 000000000000..70d7bb0c4d8f
--- /dev/null
+++ b/arch/tile/kernel/mcount_64.S
@@ -0,0 +1,224 @@
+/*
+ * Copyright 2012 Tilera Corporation. All Rights Reserved.
+ *
+ *   This program is free software; you can redistribute it and/or
+ *   modify it under the terms of the GNU General Public License
+ *   as published by the Free Software Foundation, version 2.
+ *
+ *   This program is distributed in the hope that it will be useful, but
+ *   WITHOUT ANY WARRANTY; without even the implied warranty of
+ *   MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ *   NON INFRINGEMENT.  See the GNU General Public License for
+ *   more details.
+ *
+ * TILE-Gx specific __mcount support
+ */
+
+#include <linux/linkage.h>
+#include <asm/ftrace.h>
+
+#define REGSIZE 8
+
+	.text
+	.global __mcount
+
+	.macro	MCOUNT_SAVE_REGS
+	addli	sp, sp, -REGSIZE
+	{
+	 st     sp, lr
+	 addli	r29, sp, - (12 * REGSIZE)
+	}
+	{
+	 addli	sp, sp, - (13 * REGSIZE)
+	 st     r29, sp
+	}
+	addli	r29, r29, REGSIZE
+	{ st	r29, r0; addli	r29, r29, REGSIZE }
+	{ st	r29, r1; addli	r29, r29, REGSIZE }
+	{ st	r29, r2; addli	r29, r29, REGSIZE }
+	{ st	r29, r3; addli	r29, r29, REGSIZE }
+	{ st	r29, r4; addli	r29, r29, REGSIZE }
+	{ st	r29, r5; addli	r29, r29, REGSIZE }
+	{ st	r29, r6; addli	r29, r29, REGSIZE }
+	{ st	r29, r7; addli	r29, r29, REGSIZE }
+	{ st	r29, r8; addli	r29, r29, REGSIZE }
+	{ st	r29, r9; addli	r29, r29, REGSIZE }
+	{ st	r29, r10; addli	r29, r29, REGSIZE }
+	.endm
+
+	.macro	MCOUNT_RESTORE_REGS
+	addli	r29, sp, (2 * REGSIZE)
+	{ ld	r0, r29; addli	r29, r29, REGSIZE }
+	{ ld	r1, r29; addli	r29, r29, REGSIZE }
+	{ ld	r2, r29; addli	r29, r29, REGSIZE }
+	{ ld	r3, r29; addli	r29, r29, REGSIZE }
+	{ ld	r4, r29; addli	r29, r29, REGSIZE }
+	{ ld	r5, r29; addli	r29, r29, REGSIZE }
+	{ ld	r6, r29; addli	r29, r29, REGSIZE }
+	{ ld	r7, r29; addli	r29, r29, REGSIZE }
+	{ ld	r8, r29; addli	r29, r29, REGSIZE }
+	{ ld	r9, r29; addli	r29, r29, REGSIZE }
+	{ ld	r10, r29; addli	lr, sp, (13 * REGSIZE) }
+	{ ld	lr, lr;  addli	sp, sp, (14 * REGSIZE) }
+	.endm
+
+	.macro  RETURN_BACK
+	{ move	r12, lr; move	lr, r10 }
+	jrp	r12
+	.endm
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+
+	.align	64
+STD_ENTRY(__mcount)
+__mcount:
+	j	ftrace_stub
+STD_ENDPROC(__mcount)
+
+	.align	64
+STD_ENTRY(ftrace_caller)
+	moveli	r11, hw2_last(function_trace_stop)
+	{ shl16insli	r11, r11, hw1(function_trace_stop); move r12, lr }
+	{ shl16insli	r11, r11, hw0(function_trace_stop); move lr, r10 }
+	ld	r11, r11
+	beqz	r11, 1f
+	jrp	r12
+
+1:
+	{ move	r10, lr; move	lr, r12 }
+	MCOUNT_SAVE_REGS
+
+	/* arg1: self return address */
+	/* arg2: parent's return address */
+	{ move	r0, lr; move	r1, r10 }
+
+	.global	ftrace_call
+ftrace_call:
+	/*
+	 * a placeholder for the call to a real tracing function, i.e.
+	 * ftrace_trace_function()
+	 */
+	nop
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	.global	ftrace_graph_call
+ftrace_graph_call:
+	/*
+	 * a placeholder for the call to a real tracing function, i.e.
+	 * ftrace_graph_caller()
+	 */
+	nop
+#endif
+	MCOUNT_RESTORE_REGS
+	.global	ftrace_stub
+ftrace_stub:
+	RETURN_BACK
+STD_ENDPROC(ftrace_caller)
+
+#else /* ! CONFIG_DYNAMIC_FTRACE */
+
+	.align	64
+STD_ENTRY(__mcount)
+	moveli	r11, hw2_last(function_trace_stop)
+	{ shl16insli	r11, r11, hw1(function_trace_stop); move r12, lr }
+	{ shl16insli	r11, r11, hw0(function_trace_stop); move lr, r10 }
+	ld	r11, r11
+	beqz	r11, 1f
+	jrp	r12
+
+1:
+	{ move	r10, lr; move	lr, r12 }
+	{
+	 moveli	r11, hw2_last(ftrace_trace_function)
+	 moveli	r13, hw2_last(ftrace_stub)
+	}
+	{
+	 shl16insli	r11, r11, hw1(ftrace_trace_function)
+	 shl16insli	r13, r13, hw1(ftrace_stub)
+	}
+	{
+	 shl16insli	r11, r11, hw0(ftrace_trace_function)
+	 shl16insli	r13, r13, hw0(ftrace_stub)
+	}
+
+	ld	r11, r11
+	sub	r14, r13, r11
+	bnez	r14, static_trace
+
+#ifdef	CONFIG_FUNCTION_GRAPH_TRACER
+	moveli	r15, hw2_last(ftrace_graph_return)
+	shl16insli	r15, r15, hw1(ftrace_graph_return)
+	shl16insli	r15, r15, hw0(ftrace_graph_return)
+	ld	r15, r15
+	sub	r15, r15, r13
+	bnez	r15, ftrace_graph_caller
+
+	{
+	 moveli	r16, hw2_last(ftrace_graph_entry)
+	 moveli	r17, hw2_last(ftrace_graph_entry_stub)
+	}
+	{
+	 shl16insli	r16, r16, hw1(ftrace_graph_entry)
+	 shl16insli	r17, r17, hw1(ftrace_graph_entry_stub)
+	}
+	{
+	 shl16insli	r16, r16, hw0(ftrace_graph_entry)
+	 shl16insli	r17, r17, hw0(ftrace_graph_entry_stub)
+	}
+	ld	r16, r16
+	sub	r17, r16, r17
+	bnez	r17, ftrace_graph_caller
+
+#endif
+	RETURN_BACK
+
+static_trace:
+	MCOUNT_SAVE_REGS
+
+	/* arg1: self return address */
+	/* arg2: parent's return address */
+	{ move	r0, lr; move	r1, r10 }
+
+	/* call ftrace_trace_function() */
+	jalr	r11
+
+	MCOUNT_RESTORE_REGS
+
+	.global ftrace_stub
+ftrace_stub:
+	RETURN_BACK
+STD_ENDPROC(__mcount)
+
+#endif	/* ! CONFIG_DYNAMIC_FTRACE */
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+
+STD_ENTRY(ftrace_graph_caller)
+ftrace_graph_caller:
+#ifndef CONFIG_DYNAMIC_FTRACE
+	MCOUNT_SAVE_REGS
+#endif
+
+	/* arg1: Get the location of the parent's return address */
+	addi	r0, sp, 12 * REGSIZE
+	/* arg2: Get self return address */
+	move	r1, lr
+
+	jal prepare_ftrace_return
+
+	MCOUNT_RESTORE_REGS
+	RETURN_BACK
+STD_ENDPROC(ftrace_graph_caller)
+
+	.global return_to_handler
+return_to_handler:
+	MCOUNT_SAVE_REGS
+
+	jal	ftrace_return_to_handler
+	/* restore the real parent address */
+	move	r11, r0
+
+	MCOUNT_RESTORE_REGS
+	jr	r11
+
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
diff --git a/arch/tile/kernel/pci-dma.c b/arch/tile/kernel/pci-dma.c
index b9fe80ec1089..09b58703ac26 100644
--- a/arch/tile/kernel/pci-dma.c
+++ b/arch/tile/kernel/pci-dma.c
@@ -36,8 +36,9 @@ static void *tile_dma_alloc_coherent(struct device *dev, size_t size,
 				     dma_addr_t *dma_handle, gfp_t gfp,
 				     struct dma_attrs *attrs)
 {
-	u64 dma_mask = dev->coherent_dma_mask ?: DMA_BIT_MASK(32);
-	int node = dev_to_node(dev);
+	u64 dma_mask = (dev && dev->coherent_dma_mask) ?
+		dev->coherent_dma_mask : DMA_BIT_MASK(32);
+	int node = dev ? dev_to_node(dev) : 0;
 	int order = get_order(size);
 	struct page *pg;
 	dma_addr_t addr;
@@ -256,7 +257,7 @@ static void tile_dma_unmap_page(struct device *dev, dma_addr_t dma_address,
 	BUG_ON(!valid_dma_direction(direction));
 
 	__dma_complete_page(pfn_to_page(PFN_DOWN(dma_address)),
-			    dma_address & PAGE_OFFSET, size, direction);
+			    dma_address & (PAGE_SIZE - 1), size, direction);
 }
 
 static void tile_dma_sync_single_for_cpu(struct device *dev,
@@ -357,7 +358,7 @@ static void *tile_pci_dma_alloc_coherent(struct device *dev, size_t size,
 
 	addr = page_to_phys(pg);
 
-	*dma_handle = phys_to_dma(dev, addr);
+	*dma_handle = addr + get_dma_offset(dev);
 
 	return page_address(pg);
 }
@@ -387,7 +388,7 @@ static int tile_pci_dma_map_sg(struct device *dev, struct scatterlist *sglist,
 		sg->dma_address = sg_phys(sg);
 		__dma_prep_pa_range(sg->dma_address, sg->length, direction);
 
-		sg->dma_address = phys_to_dma(dev, sg->dma_address);
+		sg->dma_address = sg->dma_address + get_dma_offset(dev);
 #ifdef CONFIG_NEED_SG_DMA_LENGTH
 		sg->dma_length = sg->length;
 #endif
@@ -422,7 +423,7 @@ static dma_addr_t tile_pci_dma_map_page(struct device *dev, struct page *page,
 	BUG_ON(offset + size > PAGE_SIZE);
 	__dma_prep_page(page, offset, size, direction);
 
-	return phys_to_dma(dev, page_to_pa(page) + offset);
+	return page_to_pa(page) + offset + get_dma_offset(dev);
 }
 
 static void tile_pci_dma_unmap_page(struct device *dev, dma_addr_t dma_address,
@@ -432,10 +433,10 @@ static void tile_pci_dma_unmap_page(struct device *dev, dma_addr_t dma_address,
 {
 	BUG_ON(!valid_dma_direction(direction));
 
-	dma_address = dma_to_phys(dev, dma_address);
+	dma_address -= get_dma_offset(dev);
 
 	__dma_complete_page(pfn_to_page(PFN_DOWN(dma_address)),
-			    dma_address & PAGE_OFFSET, size, direction);
+			    dma_address & (PAGE_SIZE - 1), size, direction);
 }
 
 static void tile_pci_dma_sync_single_for_cpu(struct device *dev,
@@ -445,7 +446,7 @@ static void tile_pci_dma_sync_single_for_cpu(struct device *dev,
 {
 	BUG_ON(!valid_dma_direction(direction));
 
-	dma_handle = dma_to_phys(dev, dma_handle);
+	dma_handle -= get_dma_offset(dev);
 
 	__dma_complete_pa_range(dma_handle, size, direction);
 }
@@ -456,7 +457,7 @@ static void tile_pci_dma_sync_single_for_device(struct device *dev,
 						enum dma_data_direction
 						direction)
 {
-	dma_handle = dma_to_phys(dev, dma_handle);
+	dma_handle -= get_dma_offset(dev);
 
 	__dma_prep_pa_range(dma_handle, size, direction);
 }
@@ -558,22 +559,47 @@ static struct dma_map_ops pci_swiotlb_dma_ops = {
 	.mapping_error = swiotlb_dma_mapping_error,
 };
 
+static struct dma_map_ops pci_hybrid_dma_ops = {
+	.alloc = tile_swiotlb_alloc_coherent,
+	.free = tile_swiotlb_free_coherent,
+	.map_page = tile_pci_dma_map_page,
+	.unmap_page = tile_pci_dma_unmap_page,
+	.map_sg = tile_pci_dma_map_sg,
+	.unmap_sg = tile_pci_dma_unmap_sg,
+	.sync_single_for_cpu = tile_pci_dma_sync_single_for_cpu,
+	.sync_single_for_device = tile_pci_dma_sync_single_for_device,
+	.sync_sg_for_cpu = tile_pci_dma_sync_sg_for_cpu,
+	.sync_sg_for_device = tile_pci_dma_sync_sg_for_device,
+	.mapping_error = tile_pci_dma_mapping_error,
+	.dma_supported = tile_pci_dma_supported
+};
+
 struct dma_map_ops *gx_legacy_pci_dma_map_ops = &pci_swiotlb_dma_ops;
+struct dma_map_ops *gx_hybrid_pci_dma_map_ops = &pci_hybrid_dma_ops;
 #else
 struct dma_map_ops *gx_legacy_pci_dma_map_ops;
+struct dma_map_ops *gx_hybrid_pci_dma_map_ops;
 #endif
 EXPORT_SYMBOL(gx_legacy_pci_dma_map_ops);
+EXPORT_SYMBOL(gx_hybrid_pci_dma_map_ops);
 
 #ifdef CONFIG_ARCH_HAS_DMA_SET_COHERENT_MASK
 int dma_set_coherent_mask(struct device *dev, u64 mask)
 {
 	struct dma_map_ops *dma_ops = get_dma_ops(dev);
 
-	/* Handle legacy PCI devices with limited memory addressability. */
-	if (((dma_ops == gx_pci_dma_map_ops) ||
-	    (dma_ops == gx_legacy_pci_dma_map_ops)) &&
-	    (mask <= DMA_BIT_MASK(32))) {
-		if (mask > dev->archdata.max_direct_dma_addr)
+	/*
+	 * For PCI devices with 64-bit DMA addressing capability, promote
+	 * the dma_ops to full capability for both streams and consistent
+	 * memory access. For 32-bit capable devices, limit the consistent 
+	 * memory DMA range to max_direct_dma_addr.
+	 */
+	if (dma_ops == gx_pci_dma_map_ops ||
+	    dma_ops == gx_hybrid_pci_dma_map_ops ||
+	    dma_ops == gx_legacy_pci_dma_map_ops) {
+		if (mask == DMA_BIT_MASK(64))
+			set_dma_ops(dev, gx_pci_dma_map_ops);
+		else if (mask > dev->archdata.max_direct_dma_addr)
 			mask = dev->archdata.max_direct_dma_addr;
 	}
 
@@ -584,3 +610,21 @@ int dma_set_coherent_mask(struct device *dev, u64 mask)
 }
 EXPORT_SYMBOL(dma_set_coherent_mask);
 #endif
+
+#ifdef ARCH_HAS_DMA_GET_REQUIRED_MASK
+/*
+ * The generic dma_get_required_mask() uses the highest physical address
+ * (max_pfn) to provide the hint to the PCI drivers regarding 32-bit or
+ * 64-bit DMA configuration. Since TILEGx has I/O TLB/MMU, allowing the
+ * DMAs to use the full 64-bit PCI address space and not limited by
+ * the physical memory space, we always let the PCI devices use
+ * 64-bit DMA if they have that capability, by returning the 64-bit
+ * DMA mask here. The device driver has the option to use 32-bit DMA if
+ * the device is not capable of 64-bit DMA.
+ */
+u64 dma_get_required_mask(struct device *dev)
+{
+	return DMA_BIT_MASK(64);
+}
+EXPORT_SYMBOL_GPL(dma_get_required_mask);
+#endif
diff --git a/arch/tile/kernel/pci.c b/arch/tile/kernel/pci.c
index 67237d34c2e2..b7180e6e900d 100644
--- a/arch/tile/kernel/pci.c
+++ b/arch/tile/kernel/pci.c
@@ -20,7 +20,6 @@
 #include <linux/capability.h>
 #include <linux/sched.h>
 #include <linux/errno.h>
-#include <linux/bootmem.h>
 #include <linux/irq.h>
 #include <linux/io.h>
 #include <linux/uaccess.h>
@@ -52,6 +51,8 @@
  *
  */
 
+static int pci_probe = 1;
+
 /*
  * This flag tells if the platform is TILEmpower that needs
  * special configuration for the PLX switch chip.
@@ -144,6 +145,11 @@ int __init tile_pci_init(void)
 {
 	int i;
 
+	if (!pci_probe) {
+		pr_info("PCI: disabled by boot argument\n");
+		return 0;
+	}
+
 	pr_info("PCI: Searching for controllers...\n");
 
 	/* Re-init number of PCIe controllers to support hot-plug feature. */
@@ -192,7 +198,6 @@ int __init tile_pci_init(void)
 			controller->hv_cfg_fd[0] = hv_cfg_fd0;
 			controller->hv_cfg_fd[1] = hv_cfg_fd1;
 			controller->hv_mem_fd = hv_mem_fd;
-			controller->first_busno = 0;
 			controller->last_busno = 0xff;
 			controller->ops = &tile_cfg_ops;
 
@@ -283,7 +288,7 @@ int __init pcibios_init(void)
 	 * known to require at least 20ms here, but we use a more
 	 * conservative value.
 	 */
-	mdelay(250);
+	msleep(250);
 
 	/* Scan all of the recorded PCI controllers.  */
 	for (i = 0; i < TILE_NUM_PCIE; i++) {
@@ -304,18 +309,10 @@ int __init pcibios_init(void)
 
 			pr_info("PCI: initializing controller #%d\n", i);
 
-			/*
-			 * This comes from the generic Linux PCI driver.
-			 *
-			 * It reads the PCI tree for this bus into the Linux
-			 * data structures.
-			 *
-			 * This is inlined in linux/pci.h and calls into
-			 * pci_scan_bus_parented() in probe.c.
-			 */
 			pci_add_resource(&resources, &ioport_resource);
 			pci_add_resource(&resources, &iomem_resource);
-			bus = pci_scan_root_bus(NULL, 0, controller->ops, controller, &resources);
+			bus = pci_scan_root_bus(NULL, 0, controller->ops,
+						controller, &resources);
 			controller->root_bus = bus;
 			controller->last_busno = bus->busn_res.end;
 		}
@@ -388,6 +385,16 @@ void pcibios_set_master(struct pci_dev *dev)
 	/* No special bus mastering setup handling. */
 }
 
+/* Process any "pci=" kernel boot arguments. */
+char *__init pcibios_setup(char *str)
+{
+	if (!strcmp(str, "off")) {
+		pci_probe = 0;
+		return NULL;
+	}
+	return str;
+}
+
 /*
  * Enable memory and/or address decoding, as appropriate, for the
  * device described by the 'dev' struct.
diff --git a/arch/tile/kernel/pci_gx.c b/arch/tile/kernel/pci_gx.c
index 11425633b2d7..a97a6452b812 100644
--- a/arch/tile/kernel/pci_gx.c
+++ b/arch/tile/kernel/pci_gx.c
@@ -69,19 +69,32 @@ static int pcie_rc[TILEGX_NUM_TRIO][TILEGX_TRIO_PCIES];
  * a HW PCIe link-training bug. The exact delay is specified with
  * a kernel boot argument in the form of "pcie_rc_delay=T,P,S",
  * where T is the TRIO instance number, P is the port number and S is
- * the delay in seconds. If the delay is not provided, the value
- * will be DEFAULT_RC_DELAY.
+ * the delay in seconds. If the argument is specified, but the delay is
+ * not provided, the value will be DEFAULT_RC_DELAY.
  */
 static int rc_delay[TILEGX_NUM_TRIO][TILEGX_TRIO_PCIES];
 
 /* Default number of seconds that the PCIe RC port probe can be delayed. */
 #define DEFAULT_RC_DELAY	10
 
-/* Max number of seconds that the PCIe RC port probe can be delayed. */
-#define MAX_RC_DELAY		20
+/* The PCI I/O space size in each PCI domain. */
+#define IO_SPACE_SIZE		0x10000
+
+/* Provide shorter versions of some very long constant names. */
+#define AUTO_CONFIG_RC	\
+	TRIO_PCIE_INTFC_PORT_CONFIG__STRAP_STATE_VAL_AUTO_CONFIG_RC
+#define AUTO_CONFIG_RC_G1	\
+	TRIO_PCIE_INTFC_PORT_CONFIG__STRAP_STATE_VAL_AUTO_CONFIG_RC_G1
+#define AUTO_CONFIG_EP	\
+	TRIO_PCIE_INTFC_PORT_CONFIG__STRAP_STATE_VAL_AUTO_CONFIG_ENDPOINT
+#define AUTO_CONFIG_EP_G1	\
+	TRIO_PCIE_INTFC_PORT_CONFIG__STRAP_STATE_VAL_AUTO_CONFIG_ENDPOINT_G1
 
 /* Array of the PCIe ports configuration info obtained from the BIB. */
-struct pcie_port_property pcie_ports[TILEGX_NUM_TRIO][TILEGX_TRIO_PCIES];
+struct pcie_trio_ports_property pcie_ports[TILEGX_NUM_TRIO];
+
+/* Number of configured TRIO instances. */
+int num_trio_shims;
 
 /* All drivers share the TRIO contexts defined here. */
 gxio_trio_context_t trio_contexts[TILEGX_NUM_TRIO];
@@ -89,24 +102,21 @@ gxio_trio_context_t trio_contexts[TILEGX_NUM_TRIO];
 /* Pointer to an array of PCIe RC controllers. */
 struct pci_controller pci_controllers[TILEGX_NUM_TRIO * TILEGX_TRIO_PCIES];
 int num_rc_controllers;
-static int num_ep_controllers;
 
 static struct pci_ops tile_cfg_ops;
 
 /* Mask of CPUs that should receive PCIe interrupts. */
 static struct cpumask intr_cpus_map;
 
-/*
- * We don't need to worry about the alignment of resources.
- */
+/* We don't need to worry about the alignment of resources. */
 resource_size_t pcibios_align_resource(void *data, const struct resource *res,
-				resource_size_t size, resource_size_t align)
+				       resource_size_t size,
+				       resource_size_t align)
 {
 	return res->start;
 }
 EXPORT_SYMBOL(pcibios_align_resource);
 
-
 /*
  * Pick a CPU to receive and handle the PCIe interrupts, based on the IRQ #.
  * For now, we simply send interrupts to non-dataplane CPUs.
@@ -134,24 +144,19 @@ static int tile_irq_cpu(int irq)
 	return cpu;
 }
 
-/*
- * Open a file descriptor to the TRIO shim.
- */
+/* Open a file descriptor to the TRIO shim. */
 static int tile_pcie_open(int trio_index)
 {
 	gxio_trio_context_t *context = &trio_contexts[trio_index];
 	int ret;
+	int mac;
 
-	/*
-	 * This opens a file descriptor to the TRIO shim.
-	 */
+	/* This opens a file descriptor to the TRIO shim. */
 	ret = gxio_trio_init(context, trio_index);
 	if (ret < 0)
-		return ret;
+		goto gxio_trio_init_failure;
 
-	/*
-	 * Allocate an ASID for the kernel.
-	 */
+	/* Allocate an ASID for the kernel. */
 	ret = gxio_trio_alloc_asids(context, 1, 0, 0);
 	if (ret < 0) {
 		pr_err("PCI: ASID alloc failure on TRIO %d, give up\n",
@@ -189,31 +194,97 @@ static int tile_pcie_open(int trio_index)
 	}
 #endif
 
+	/* Get the properties of the PCIe ports on this TRIO instance. */
+	ret = gxio_trio_get_port_property(context, &pcie_ports[trio_index]);
+	if (ret < 0) {
+		pr_err("PCI: PCIE_GET_PORT_PROPERTY failure, error %d,"
+		       " on TRIO %d\n", ret, trio_index);
+		goto get_port_property_failure;
+	}
+
+	context->mmio_base_mac =
+		iorpc_ioremap(context->fd, 0, HV_TRIO_CONFIG_IOREMAP_SIZE);
+	if (context->mmio_base_mac == NULL) {
+		pr_err("PCI: TRIO config space mapping failure, error %d,"
+		       " on TRIO %d\n", ret, trio_index);
+		ret = -ENOMEM;
+
+		goto trio_mmio_mapping_failure;
+	}
+
+	/* Check the port strap state which will override the BIB setting. */
+	for (mac = 0; mac < TILEGX_TRIO_PCIES; mac++) {
+		TRIO_PCIE_INTFC_PORT_CONFIG_t port_config;
+		unsigned int reg_offset;
+
+		/* Ignore ports that are not specified in the BIB. */
+		if (!pcie_ports[trio_index].ports[mac].allow_rc &&
+		    !pcie_ports[trio_index].ports[mac].allow_ep)
+			continue;
+
+		reg_offset =
+			(TRIO_PCIE_INTFC_PORT_CONFIG <<
+				TRIO_CFG_REGION_ADDR__REG_SHIFT) |
+			(TRIO_CFG_REGION_ADDR__INTFC_VAL_MAC_INTERFACE <<
+				TRIO_CFG_REGION_ADDR__INTFC_SHIFT) |
+			(mac << TRIO_CFG_REGION_ADDR__MAC_SEL_SHIFT);
+
+		port_config.word =
+			__gxio_mmio_read(context->mmio_base_mac + reg_offset);
+
+		if (port_config.strap_state != AUTO_CONFIG_RC &&
+		    port_config.strap_state != AUTO_CONFIG_RC_G1) {
+			/*
+			 * If this is really intended to be an EP port, record
+			 * it so that the endpoint driver will know about it.
+			 */
+			if (port_config.strap_state == AUTO_CONFIG_EP ||
+			    port_config.strap_state == AUTO_CONFIG_EP_G1)
+				pcie_ports[trio_index].ports[mac].allow_ep = 1;
+		}
+	}
+
 	return ret;
 
+trio_mmio_mapping_failure:
+get_port_property_failure:
 asid_alloc_failure:
 #ifdef USE_SHARED_PCIE_CONFIG_REGION
 pio_alloc_failure:
 #endif
 	hv_dev_close(context->fd);
+gxio_trio_init_failure:
+	context->fd = -1;
 
 	return ret;
 }
 
-static void
-tilegx_legacy_irq_ack(struct irq_data *d)
+static int __init tile_trio_init(void)
+{
+	int i;
+
+	/* We loop over all the TRIO shims. */
+	for (i = 0; i < TILEGX_NUM_TRIO; i++) {
+		if (tile_pcie_open(i) < 0)
+			continue;
+		num_trio_shims++;
+	}
+
+	return 0;
+}
+postcore_initcall(tile_trio_init);
+
+static void tilegx_legacy_irq_ack(struct irq_data *d)
 {
 	__insn_mtspr(SPR_IPI_EVENT_RESET_K, 1UL << d->irq);
 }
 
-static void
-tilegx_legacy_irq_mask(struct irq_data *d)
+static void tilegx_legacy_irq_mask(struct irq_data *d)
 {
 	__insn_mtspr(SPR_IPI_MASK_SET_K, 1UL << d->irq);
 }
 
-static void
-tilegx_legacy_irq_unmask(struct irq_data *d)
+static void tilegx_legacy_irq_unmask(struct irq_data *d)
 {
 	__insn_mtspr(SPR_IPI_MASK_RESET_K, 1UL << d->irq);
 }
@@ -234,8 +305,7 @@ static struct irq_chip tilegx_legacy_irq_chip = {
  * to Linux which just calls handle_level_irq() after clearing the
  * MAC INTx Assert status bit associated with this interrupt.
  */
-static void
-trio_handle_level_irq(unsigned int irq, struct irq_desc *desc)
+static void trio_handle_level_irq(unsigned int irq, struct irq_desc *desc)
 {
 	struct pci_controller *controller = irq_desc_get_handler_data(desc);
 	gxio_trio_context_t *trio_context = controller->trio;
@@ -301,9 +371,7 @@ static int tile_init_irqs(struct pci_controller *controller)
 			goto free_irqs;
 		}
 
-		/*
-		 * Register the IRQ handler with the kernel.
-		 */
+		/* Register the IRQ handler with the kernel. */
 		irq_set_chip_and_handler(irq, &tilegx_legacy_irq_chip,
 					trio_handle_level_irq);
 		irq_set_chip_data(irq, (void *)(uint64_t)i);
@@ -320,14 +388,39 @@ free_irqs:
 }
 
 /*
+ * Return 1 if the port is strapped to operate in RC mode.
+ */
+static int
+strapped_for_rc(gxio_trio_context_t *trio_context, int mac)
+{
+	TRIO_PCIE_INTFC_PORT_CONFIG_t port_config;
+	unsigned int reg_offset;
+
+	/* Check the port configuration. */
+	reg_offset =
+		(TRIO_PCIE_INTFC_PORT_CONFIG <<
+			TRIO_CFG_REGION_ADDR__REG_SHIFT) |
+		(TRIO_CFG_REGION_ADDR__INTFC_VAL_MAC_INTERFACE <<
+			TRIO_CFG_REGION_ADDR__INTFC_SHIFT) |
+		(mac << TRIO_CFG_REGION_ADDR__MAC_SEL_SHIFT);
+	port_config.word =
+		__gxio_mmio_read(trio_context->mmio_base_mac + reg_offset);
+
+	if (port_config.strap_state == AUTO_CONFIG_RC ||
+	    port_config.strap_state == AUTO_CONFIG_RC_G1)
+		return 1;
+	else
+		return 0;
+}
+
+/*
  * Find valid controllers and fill in pci_controller structs for each
  * of them.
  *
- * Returns the number of controllers discovered.
+ * Return the number of controllers discovered.
  */
 int __init tile_pci_init(void)
 {
-	int num_trio_shims = 0;
 	int ctl_index = 0;
 	int i, j;
 
@@ -338,64 +431,62 @@ int __init tile_pci_init(void)
 
 	pr_info("PCI: Searching for controllers...\n");
 
-	/*
-	 * We loop over all the TRIO shims.
-	 */
-	for (i = 0; i < TILEGX_NUM_TRIO; i++) {
-		int ret;
-
-		ret = tile_pcie_open(i);
-		if (ret < 0)
-			continue;
-
-		num_trio_shims++;
-	}
-
 	if (num_trio_shims == 0 || sim_is_simulator())
 		return 0;
 
 	/*
-	 * Now determine which PCIe ports are configured to operate in RC mode.
-	 * We look at the Board Information Block first and then see if there
-	 * are any overriding configuration by the HW strapping pin.
+	 * Now determine which PCIe ports are configured to operate in RC
+	 * mode. There is a differece in the port configuration capability
+	 * between the Gx36 and Gx72 devices.
+	 *
+	 * The Gx36 has configuration capability for each of the 3 PCIe
+	 * interfaces (disable, auto endpoint, auto RC, etc.).
+	 * On the Gx72, you can only select one of the 3 PCIe interfaces per
+	 * TRIO to train automatically. Further, the allowable training modes
+	 * are reduced to four options (auto endpoint, auto RC, stream x1,
+	 * stream x4).
+	 *
+	 * For Gx36 ports, it must be allowed to be in RC mode by the
+	 * Board Information Block, and the hardware strapping pins must be
+	 * set to RC mode.
+	 *
+	 * For Gx72 ports, the port will operate in RC mode if either of the
+	 * following is true:
+	 * 1. It is allowed to be in RC mode by the Board Information Block,
+	 *    and the BIB doesn't allow the EP mode.
+	 * 2. It is allowed to be in either the RC or the EP mode by the BIB,
+	 *    and the hardware strapping pin is set to RC mode.
 	 */
 	for (i = 0; i < TILEGX_NUM_TRIO; i++) {
 		gxio_trio_context_t *context = &trio_contexts[i];
-		int ret;
 
 		if (context->fd < 0)
 			continue;
 
-		ret = hv_dev_pread(context->fd, 0,
-			(HV_VirtAddr)&pcie_ports[i][0],
-			sizeof(struct pcie_port_property) * TILEGX_TRIO_PCIES,
-			GXIO_TRIO_OP_GET_PORT_PROPERTY);
-		if (ret < 0) {
-			pr_err("PCI: PCIE_GET_PORT_PROPERTY failure, error %d,"
-				" on TRIO %d\n", ret, i);
-			continue;
-		}
-
 		for (j = 0; j < TILEGX_TRIO_PCIES; j++) {
-			if (pcie_ports[i][j].allow_rc) {
+			int is_rc = 0;
+
+			if (pcie_ports[i].is_gx72 &&
+			    pcie_ports[i].ports[j].allow_rc) {
+				if (!pcie_ports[i].ports[j].allow_ep ||
+				    strapped_for_rc(context, j))
+					is_rc = 1;
+			} else if (pcie_ports[i].ports[j].allow_rc &&
+				   strapped_for_rc(context, j)) {
+				is_rc = 1;
+			}
+			if (is_rc) {
 				pcie_rc[i][j] = 1;
 				num_rc_controllers++;
 			}
-			else if (pcie_ports[i][j].allow_ep) {
-				num_ep_controllers++;
-			}
 		}
 	}
 
-	/*
-	 * Return if no PCIe ports are configured to operate in RC mode.
-	 */
+	/* Return if no PCIe ports are configured to operate in RC mode. */
 	if (num_rc_controllers == 0)
 		return 0;
 
-	/*
-	 * Set the TRIO pointer and MAC index for each PCIe RC port.
-	 */
+	/* Set the TRIO pointer and MAC index for each PCIe RC port. */
 	for (i = 0; i < TILEGX_NUM_TRIO; i++) {
 		for (j = 0; j < TILEGX_TRIO_PCIES; j++) {
 			if (pcie_rc[i][j]) {
@@ -411,26 +502,32 @@ int __init tile_pci_init(void)
 	}
 
 out:
-	/*
-	 * Configure each PCIe RC port.
-	 */
+	/* Configure each PCIe RC port. */
 	for (i = 0; i < num_rc_controllers; i++) {
-		/*
-		 * Configure the PCIe MAC to run in RC mode.
-		 */
 
+		/* Configure the PCIe MAC to run in RC mode. */
 		struct pci_controller *controller = &pci_controllers[i];
 
 		controller->index = i;
 		controller->ops = &tile_cfg_ops;
 
+		controller->io_space.start = PCIBIOS_MIN_IO +
+			(i * IO_SPACE_SIZE);
+		controller->io_space.end = controller->io_space.start +
+			IO_SPACE_SIZE - 1;
+		BUG_ON(controller->io_space.end > IO_SPACE_LIMIT);
+		controller->io_space.flags = IORESOURCE_IO;
+		snprintf(controller->io_space_name,
+			 sizeof(controller->io_space_name),
+			 "PCI I/O domain %d", i);
+		controller->io_space.name = controller->io_space_name;
+
 		/*
 		 * The PCI memory resource is located above the PA space.
 		 * For every host bridge, the BAR window or the MMIO aperture
 		 * is in range [3GB, 4GB - 1] of a 4GB space beyond the
 		 * PA space.
 		 */
-
 		controller->mem_offset = TILE_PCI_MEM_START +
 			(i * TILE_PCI_BAR_WINDOW_TOP);
 		controller->mem_space.start = controller->mem_offset +
@@ -458,7 +555,6 @@ static int tile_map_irq(const struct pci_dev *dev, u8 device, u8 pin)
 	return controller->irq_intx_table[pin - 1];
 }
 
-
 static void fixup_read_and_payload_sizes(struct pci_controller *controller)
 {
 	gxio_trio_context_t *trio_context = controller->trio;
@@ -472,9 +568,7 @@ static void fixup_read_and_payload_sizes(struct pci_controller *controller)
 
 	mac = controller->mac;
 
-	/*
-	 * Set our max read request size to be 4KB.
-	 */
+	/* Set our max read request size to be 4KB. */
 	reg_offset =
 		(TRIO_PCIE_RC_DEVICE_CONTROL <<
 			TRIO_CFG_REGION_ADDR__REG_SHIFT) |
@@ -483,10 +577,10 @@ static void fixup_read_and_payload_sizes(struct pci_controller *controller)
 		(mac << TRIO_CFG_REGION_ADDR__MAC_SEL_SHIFT);
 
 	dev_control.word = __gxio_mmio_read32(trio_context->mmio_base_mac +
-						reg_offset);
+					      reg_offset);
 	dev_control.max_read_req_sz = 5;
 	__gxio_mmio_write32(trio_context->mmio_base_mac + reg_offset,
-						dev_control.word);
+			    dev_control.word);
 
 	/*
 	 * Set the max payload size supported by this Gx PCIe MAC.
@@ -502,19 +596,14 @@ static void fixup_read_and_payload_sizes(struct pci_controller *controller)
 		(mac << TRIO_CFG_REGION_ADDR__MAC_SEL_SHIFT);
 
 	rc_dev_cap.word = __gxio_mmio_read32(trio_context->mmio_base_mac +
-						reg_offset);
+					     reg_offset);
 	rc_dev_cap.mps_sup = 1;
 	__gxio_mmio_write32(trio_context->mmio_base_mac + reg_offset,
-						rc_dev_cap.word);
+			    rc_dev_cap.word);
 
 	/* Configure PCI Express MPS setting. */
-	list_for_each_entry(child, &root_bus->children, node) {
-		struct pci_dev *self = child->self;
-		if (!self)
-			continue;
-
-		pcie_bus_configure_settings(child, self->pcie_mpss);
-	}
+	list_for_each_entry(child, &root_bus->children, node)
+		pcie_bus_configure_settings(child);
 
 	/*
 	 * Set the mac_config register in trio based on the MPS/MRS of the link.
@@ -533,7 +622,7 @@ static void fixup_read_and_payload_sizes(struct pci_controller *controller)
 				    dev_control.max_payload_size,
 				    dev_control.max_read_req_sz,
 				    mac);
-        if (err < 0) {
+	if (err < 0) {
 		pr_err("PCI: PCIE_CONFIGURE_MAC_MPS_MRS failure, "
 			"MAC %d on TRIO %d\n",
 			mac, controller->trio_index);
@@ -570,21 +659,14 @@ static int setup_pcie_rc_delay(char *str)
 		if (!isdigit(*str))
 			return -EINVAL;
 		delay = simple_strtoul(str, (char **)&str, 10);
-		if (delay > MAX_RC_DELAY)
-			return -EINVAL;
 	}
 
 	rc_delay[trio_index][mac] = delay ? : DEFAULT_RC_DELAY;
-	pr_info("Delaying PCIe RC link training for %u sec"
-		" on MAC %lu on TRIO %lu\n", rc_delay[trio_index][mac],
-		mac, trio_index);
 	return 0;
 }
 early_param("pcie_rc_delay", setup_pcie_rc_delay);
 
-/*
- * PCI initialization entry point, called by subsys_initcall.
- */
+/* PCI initialization entry point, called by subsys_initcall. */
 int __init pcibios_init(void)
 {
 	resource_size_t offset;
@@ -594,35 +676,10 @@ int __init pcibios_init(void)
 
 	tile_pci_init();
 
-	if (num_rc_controllers == 0 && num_ep_controllers == 0)
+	if (num_rc_controllers == 0)
 		return 0;
 
 	/*
-	 * We loop over all the TRIO shims and set up the MMIO mappings.
-	 */
-	for (i = 0; i < TILEGX_NUM_TRIO; i++) {
-		gxio_trio_context_t *context = &trio_contexts[i];
-
-		if (context->fd < 0)
-			continue;
-
-		/*
-		 * Map in the MMIO space for the MAC.
-		 */
-		offset = 0;
-		context->mmio_base_mac =
-			iorpc_ioremap(context->fd, offset,
-				      HV_TRIO_CONFIG_IOREMAP_SIZE);
-		if (context->mmio_base_mac == NULL) {
-			pr_err("PCI: MAC map failure on TRIO %d\n", i);
-
-			hv_dev_close(context->fd);
-			context->fd = -1;
-			continue;
-		}
-	}
-
-	/*
 	 * Delay a bit in case devices aren't ready.  Some devices are
 	 * known to require at least 20ms here, but we use a more
 	 * conservative value.
@@ -633,7 +690,6 @@ int __init pcibios_init(void)
 	for (next_busno = 0, i = 0; i < num_rc_controllers; i++) {
 		struct pci_controller *controller = &pci_controllers[i];
 		gxio_trio_context_t *trio_context = controller->trio;
-		TRIO_PCIE_INTFC_PORT_CONFIG_t port_config;
 		TRIO_PCIE_INTFC_PORT_STATUS_t port_status;
 		TRIO_PCIE_INTFC_TX_FIFO_CTL_t tx_fifo_ctl;
 		struct pci_bus *bus;
@@ -650,75 +706,64 @@ int __init pcibios_init(void)
 		mac = controller->mac;
 
 		/*
-		 * Check the port strap state which will override the BIB
-		 * setting.
+		 * Check for PCIe link-up status to decide if we need
+		 * to force the link to come up.
 		 */
-
 		reg_offset =
-			(TRIO_PCIE_INTFC_PORT_CONFIG <<
+			(TRIO_PCIE_INTFC_PORT_STATUS <<
 				TRIO_CFG_REGION_ADDR__REG_SHIFT) |
 			(TRIO_CFG_REGION_ADDR__INTFC_VAL_MAC_INTERFACE <<
-				TRIO_CFG_REGION_ADDR__INTFC_SHIFT ) |
+				TRIO_CFG_REGION_ADDR__INTFC_SHIFT) |
 			(mac << TRIO_CFG_REGION_ADDR__MAC_SEL_SHIFT);
 
-		port_config.word =
+		port_status.word =
 			__gxio_mmio_read(trio_context->mmio_base_mac +
 					 reg_offset);
-
-		if ((port_config.strap_state !=
-			TRIO_PCIE_INTFC_PORT_CONFIG__STRAP_STATE_VAL_AUTO_CONFIG_RC) &&
-			(port_config.strap_state !=
-			TRIO_PCIE_INTFC_PORT_CONFIG__STRAP_STATE_VAL_AUTO_CONFIG_RC_G1)) {
-			/*
-			 * If this is really intended to be an EP port,
-			 * record it so that the endpoint driver will know about it.
-			 */
-			if (port_config.strap_state ==
-			TRIO_PCIE_INTFC_PORT_CONFIG__STRAP_STATE_VAL_AUTO_CONFIG_ENDPOINT ||
-			port_config.strap_state ==
-			TRIO_PCIE_INTFC_PORT_CONFIG__STRAP_STATE_VAL_AUTO_CONFIG_ENDPOINT_G1)
-				pcie_ports[trio_index][mac].allow_ep = 1;
-
-			continue;
+		if (!port_status.dl_up) {
+			if (rc_delay[trio_index][mac]) {
+				pr_info("Delaying PCIe RC TRIO init %d sec"
+					" on MAC %d on TRIO %d\n",
+					rc_delay[trio_index][mac], mac,
+					trio_index);
+				msleep(rc_delay[trio_index][mac] * 1000);
+			}
+			ret = gxio_trio_force_rc_link_up(trio_context, mac);
+			if (ret < 0)
+				pr_err("PCI: PCIE_FORCE_LINK_UP failure, "
+					"MAC %d on TRIO %d\n", mac, trio_index);
 		}
 
-		/*
-		 * Delay the RC link training if needed.
-		 */
-		if (rc_delay[trio_index][mac])
-			msleep(rc_delay[trio_index][mac] * 1000);
-
-		ret = gxio_trio_force_rc_link_up(trio_context, mac);
-		if (ret < 0)
-			pr_err("PCI: PCIE_FORCE_LINK_UP failure, "
-				"MAC %d on TRIO %d\n", mac, trio_index);
-
 		pr_info("PCI: Found PCI controller #%d on TRIO %d MAC %d\n", i,
 			trio_index, controller->mac);
 
-		/*
-		 * Wait a bit here because some EP devices take longer
-		 * to come up.
-		 */
-		msleep(1000);
-
-		/*
-		 * Check for PCIe link-up status.
-		 */
-
-		reg_offset =
-			(TRIO_PCIE_INTFC_PORT_STATUS <<
-				TRIO_CFG_REGION_ADDR__REG_SHIFT) |
-			(TRIO_CFG_REGION_ADDR__INTFC_VAL_MAC_INTERFACE <<
-				TRIO_CFG_REGION_ADDR__INTFC_SHIFT ) |
-			(mac << TRIO_CFG_REGION_ADDR__MAC_SEL_SHIFT);
+		/* Delay the bus probe if needed. */
+		if (rc_delay[trio_index][mac]) {
+			pr_info("Delaying PCIe RC bus enumerating %d sec"
+				" on MAC %d on TRIO %d\n",
+				rc_delay[trio_index][mac], mac,
+				trio_index);
+			msleep(rc_delay[trio_index][mac] * 1000);
+		} else {
+			/*
+			 * Wait a bit here because some EP devices
+			 * take longer to come up.
+			 */
+			msleep(1000);
+		}
 
+		/* Check for PCIe link-up status again. */
 		port_status.word =
 			__gxio_mmio_read(trio_context->mmio_base_mac +
 					 reg_offset);
 		if (!port_status.dl_up) {
-			pr_err("PCI: link is down, MAC %d on TRIO %d\n",
-				mac, trio_index);
+			if (pcie_ports[trio_index].ports[mac].removable) {
+				pr_info("PCI: link is down, MAC %d on TRIO %d\n",
+					mac, trio_index);
+				pr_info("This is expected if no PCIe card"
+					" is connected to this link\n");
+			} else
+				pr_err("PCI: link is down, MAC %d on TRIO %d\n",
+					mac, trio_index);
 			continue;
 		}
 
@@ -744,7 +789,6 @@ int __init pcibios_init(void)
 		 * Change the device ID so that Linux bus crawl doesn't confuse
 		 * the internal bridge with any Tilera endpoints.
 		 */
-
 		reg_offset =
 			(TRIO_PCIE_RC_DEVICE_ID_VEN_ID <<
 				TRIO_CFG_REGION_ADDR__REG_SHIFT) |
@@ -757,10 +801,7 @@ int __init pcibios_init(void)
 				    TRIO_PCIE_RC_DEVICE_ID_VEN_ID__DEV_ID_SHIFT) |
 				    TILERA_VENDOR_ID);
 
-		/*
-		 * Set the internal P2P bridge class code.
-		 */
-
+		/* Set the internal P2P bridge class code. */
 		reg_offset =
 			(TRIO_PCIE_RC_REVISION_ID <<
 				TRIO_CFG_REGION_ADDR__REG_SHIFT) |
@@ -771,26 +812,22 @@ int __init pcibios_init(void)
 		class_code_revision =
 			__gxio_mmio_read32(trio_context->mmio_base_mac +
 					   reg_offset);
-		class_code_revision = (class_code_revision & 0xff ) |
-					(PCI_CLASS_BRIDGE_PCI << 16);
+		class_code_revision = (class_code_revision & 0xff) |
+			(PCI_CLASS_BRIDGE_PCI << 16);
 
 		__gxio_mmio_write32(trio_context->mmio_base_mac +
 				    reg_offset, class_code_revision);
 
 #ifdef USE_SHARED_PCIE_CONFIG_REGION
 
-		/*
-		 * Map in the MMIO space for the PIO region.
-		 */
+		/* Map in the MMIO space for the PIO region. */
 		offset = HV_TRIO_PIO_OFFSET(trio_context->pio_cfg_index) |
 			(((unsigned long long)mac) <<
 			TRIO_TILE_PIO_REGION_SETUP_CFG_ADDR__MAC_SHIFT);
 
 #else
 
-		/*
-		 * Alloc a PIO region for PCI config access per MAC.
-		 */
+		/* Alloc a PIO region for PCI config access per MAC. */
 		ret = gxio_trio_alloc_pio_regions(trio_context, 1, 0, 0);
 		if (ret < 0) {
 			pr_err("PCI: PCI CFG PIO alloc failure for mac %d "
@@ -801,9 +838,7 @@ int __init pcibios_init(void)
 
 		trio_context->pio_cfg_index[mac] = ret;
 
-		/*
-		 * For PIO CFG, the bus_address_hi parameter is 0.
-		 */
+		/* For PIO CFG, the bus_address_hi parameter is 0. */
 		ret = gxio_trio_init_pio_region_aux(trio_context,
 			trio_context->pio_cfg_index[mac],
 			mac, 0, HV_TRIO_PIO_FLAG_CONFIG_SPACE);
@@ -820,9 +855,15 @@ int __init pcibios_init(void)
 
 #endif
 
+		/*
+		 * To save VMALLOC space, we take advantage of the fact that
+		 * bit 29 in the PIO CFG address format is reserved 0. With
+		 * TRIO_TILE_PIO_REGION_SETUP_CFG_ADDR__MAC_SHIFT being 30,
+		 * this cuts VMALLOC space usage from 1GB to 512MB per mac.
+		 */
 		trio_context->mmio_base_pio_cfg[mac] =
-			iorpc_ioremap(trio_context->fd, offset,
-			(1 << TRIO_TILE_PIO_REGION_SETUP_CFG_ADDR__MAC_SHIFT));
+			iorpc_ioremap(trio_context->fd, offset, (1UL <<
+			(TRIO_TILE_PIO_REGION_SETUP_CFG_ADDR__MAC_SHIFT - 1)));
 		if (trio_context->mmio_base_pio_cfg[mac] == NULL) {
 			pr_err("PCI: PIO map failure for mac %d on TRIO %d\n",
 				mac, trio_index);
@@ -830,9 +871,7 @@ int __init pcibios_init(void)
 			continue;
 		}
 
-		/*
-		 * Initialize the PCIe interrupts.
-		 */
+		/* Initialize the PCIe interrupts. */
 		if (tile_init_irqs(controller)) {
 			pr_err("PCI: IRQs init failure for mac %d on TRIO %d\n",
 				mac, trio_index);
@@ -843,17 +882,16 @@ int __init pcibios_init(void)
 		/*
 		 * The PCI memory resource is located above the PA space.
 		 * The memory range for the PCI root bus should not overlap
-		 * with the physical RAM
+		 * with the physical RAM.
 		 */
 		pci_add_resource_offset(&resources, &controller->mem_space,
 					controller->mem_offset);
-
+		pci_add_resource(&resources, &controller->io_space);
 		controller->first_busno = next_busno;
 		bus = pci_scan_root_bus(NULL, next_busno, controller->ops,
 					controller, &resources);
 		controller->root_bus = bus;
 		next_busno = bus->busn_res.end + 1;
-
 	}
 
 	/* Do machine dependent PCI interrupt routing */
@@ -865,7 +903,6 @@ int __init pcibios_init(void)
 	 * It allocates all of the resources (I/O memory, etc)
 	 * associated with the devices read in above.
 	 */
-
 	pci_assign_unassigned_resources();
 
 	/* Record the I/O resources in the PCI controller structure. */
@@ -873,9 +910,6 @@ int __init pcibios_init(void)
 		struct pci_controller *controller = &pci_controllers[i];
 		gxio_trio_context_t *trio_context = controller->trio;
 		struct pci_bus *root_bus = pci_controllers[i].root_bus;
-		struct pci_bus *next_bus;
-		uint32_t bus_address_hi;
-		struct pci_dev *dev;
 		int ret;
 		int j;
 
@@ -889,43 +923,12 @@ int __init pcibios_init(void)
 		/* Configure the max_payload_size values for this domain. */
 		fixup_read_and_payload_sizes(controller);
 
-		list_for_each_entry(dev, &root_bus->devices, bus_list) {
-			/* Find the PCI host controller, ie. the 1st bridge. */
-			if ((dev->class >> 8) == PCI_CLASS_BRIDGE_PCI &&
-				(PCI_SLOT(dev->devfn) == 0)) {
-				next_bus = dev->subordinate;
-				pci_controllers[i].mem_resources[0] =
-					*next_bus->resource[0];
-				pci_controllers[i].mem_resources[1] =
-					 *next_bus->resource[1];
-				pci_controllers[i].mem_resources[2] =
-					 *next_bus->resource[2];
-
-				break;
-			}
-		}
-
-		if (pci_controllers[i].mem_resources[1].flags & IORESOURCE_MEM)
-			bus_address_hi =
-				pci_controllers[i].mem_resources[1].start >> 32;
-		else if (pci_controllers[i].mem_resources[2].flags & IORESOURCE_PREFETCH)
-			bus_address_hi =
-				pci_controllers[i].mem_resources[2].start >> 32;
-		else {
-			/* This is unlikely. */
-			pr_err("PCI: no memory resources on TRIO %d mac %d\n",
-				controller->trio_index, controller->mac);
-			continue;
-		}
-
-		/*
-		 * Alloc a PIO region for PCI memory access for each RC port.
-		 */
+		/* Alloc a PIO region for PCI memory access for each RC port. */
 		ret = gxio_trio_alloc_pio_regions(trio_context, 1, 0, 0);
 		if (ret < 0) {
 			pr_err("PCI: MEM PIO alloc failure on TRIO %d mac %d, "
-				"give up\n", controller->trio_index,
-				controller->mac);
+			       "give up\n", controller->trio_index,
+			       controller->mac);
 
 			continue;
 		}
@@ -943,12 +946,45 @@ int __init pcibios_init(void)
 						    0);
 		if (ret < 0) {
 			pr_err("PCI: MEM PIO init failure on TRIO %d mac %d, "
-				"give up\n", controller->trio_index,
-				controller->mac);
+			       "give up\n", controller->trio_index,
+			       controller->mac);
+
+			continue;
+		}
+
+#ifdef CONFIG_TILE_PCI_IO
+		/*
+		 * Alloc a PIO region for PCI I/O space access for each RC port.
+		 */
+		ret = gxio_trio_alloc_pio_regions(trio_context, 1, 0, 0);
+		if (ret < 0) {
+			pr_err("PCI: I/O PIO alloc failure on TRIO %d mac %d, "
+			       "give up\n", controller->trio_index,
+			       controller->mac);
 
 			continue;
 		}
 
+		controller->pio_io_index = ret;
+
+		/*
+		 * For PIO IO, the bus_address_hi parameter is hard-coded 0
+		 * because PCI I/O address space is 32-bit.
+		 */
+		ret = gxio_trio_init_pio_region_aux(trio_context,
+						    controller->pio_io_index,
+						    controller->mac,
+						    0,
+						    HV_TRIO_PIO_FLAG_IO_SPACE);
+		if (ret < 0) {
+			pr_err("PCI: I/O PIO init failure on TRIO %d mac %d, "
+			       "give up\n", controller->trio_index,
+			       controller->mac);
+
+			continue;
+		}
+#endif
+
 		/*
 		 * Configure a Mem-Map region for each memory controller so
 		 * that Linux can map all of its PA space to the PCI bus.
@@ -963,9 +999,9 @@ int __init pcibios_init(void)
 							  0);
 			if (ret < 0) {
 				pr_err("PCI: Mem-Map alloc failure on TRIO %d "
-					"mac %d for MC %d, give up\n",
-					controller->trio_index,
-					controller->mac, j);
+				       "mac %d for MC %d, give up\n",
+				       controller->trio_index,
+				       controller->mac, j);
 
 				goto alloc_mem_map_failed;
 			}
@@ -996,9 +1032,9 @@ int __init pcibios_init(void)
 				GXIO_TRIO_ORDER_MODE_UNORDERED);
 			if (ret < 0) {
 				pr_err("PCI: Mem-Map init failure on TRIO %d "
-					"mac %d for MC %d, give up\n",
-					controller->trio_index,
-					controller->mac, j);
+				       "mac %d for MC %d, give up\n",
+				       controller->trio_index,
+				       controller->mac, j);
 
 				goto alloc_mem_map_failed;
 			}
@@ -1007,23 +1043,19 @@ int __init pcibios_init(void)
 alloc_mem_map_failed:
 			break;
 		}
-
 	}
 
 	return 0;
 }
 subsys_initcall(pcibios_init);
 
-/* Note: to be deleted after Linux 3.6 merge. */
+/* No bus fixups needed. */
 void pcibios_fixup_bus(struct pci_bus *bus)
 {
 }
 
-/*
- * This can be called from the generic PCI layer, but doesn't need to
- * do anything.
- */
-char *pcibios_setup(char *str)
+/* Process any "pci=" kernel boot arguments. */
+char *__init pcibios_setup(char *str)
 {
 	if (!strcmp(str, "off")) {
 		pci_probe = 0;
@@ -1034,8 +1066,7 @@ char *pcibios_setup(char *str)
 
 /*
  * Enable memory address decoding, as appropriate, for the
- * device described by the 'dev' struct. The I/O decoding
- * is disabled, though the TILE-Gx supports I/O addressing.
+ * device described by the 'dev' struct.
  *
  * This is called from the generic PCI layer, and can be called
  * for bridges or endpoints.
@@ -1045,13 +1076,24 @@ int pcibios_enable_device(struct pci_dev *dev, int mask)
 	return pci_enable_resources(dev, mask);
 }
 
-/* Called for each device after PCI setup is done. */
+/*
+ * Called for each device after PCI setup is done.
+ * We initialize the PCI device capabilities conservatively, assuming that
+ * all devices can only address the 32-bit DMA space. The exception here is
+ * that the device dma_offset is set to the value that matches the 64-bit
+ * capable devices. This is OK because dma_offset is not used by legacy
+ * dma_ops, nor by the hybrid dma_ops's streaming DMAs, which are 64-bit ops.
+ * This implementation matches the kernel design of setting PCI devices'
+ * coherent_dma_mask to 0xffffffffull by default, allowing the device drivers
+ * to skip calling pci_set_consistent_dma_mask(DMA_BIT_MASK(32)).
+ */
 static void pcibios_fixup_final(struct pci_dev *pdev)
 {
-	set_dma_ops(&pdev->dev, gx_pci_dma_map_ops);
+	set_dma_ops(&pdev->dev, gx_legacy_pci_dma_map_ops);
 	set_dma_offset(&pdev->dev, TILE_PCI_MEM_MAP_BASE_OFFSET);
 	pdev->dev.archdata.max_direct_dma_addr =
 		TILE_PCI_MAX_DIRECT_DMA_ADDRESS;
+	pdev->dev.coherent_dma_mask = TILE_PCI_MAX_DIRECT_DMA_ADDRESS;
 }
 DECLARE_PCI_FIXUP_FINAL(PCI_ANY_ID, PCI_ANY_ID, pcibios_fixup_final);
 
@@ -1065,19 +1107,15 @@ void __iomem *ioremap(resource_size_t phys_addr, unsigned long size)
 	resource_size_t start;
 	resource_size_t end;
 	int trio_fd;
-	int i, j;
+	int i;
 
 	start = phys_addr;
 	end = phys_addr + size - 1;
 
 	/*
-	 * In the following, each PCI controller's mem_resources[1]
-	 * represents its (non-prefetchable) PCI memory resource and
-	 * mem_resources[2] refers to its prefetchable PCI memory resource.
-	 * By searching phys_addr in each controller's mem_resources[], we can
+	 * By searching phys_addr in each controller's mem_space, we can
 	 * determine the controller that should accept the PCI memory access.
 	 */
-
 	for (i = 0; i < num_rc_controllers; i++) {
 		/*
 		 * Skip controllers that are not properly initialized or
@@ -1086,25 +1124,18 @@ void __iomem *ioremap(resource_size_t phys_addr, unsigned long size)
 		if (pci_controllers[i].root_bus == NULL)
 			continue;
 
-		for (j = 1; j < 3; j++) {
-			bar_start =
-				pci_controllers[i].mem_resources[j].start;
-			bar_end =
-				pci_controllers[i].mem_resources[j].end;
+		bar_start = pci_controllers[i].mem_space.start;
+		bar_end = pci_controllers[i].mem_space.end;
 
-			if ((start >= bar_start) && (end <= bar_end)) {
-
-				controller = &pci_controllers[i];
-
-				goto got_it;
-			}
+		if ((start >= bar_start) && (end <= bar_end)) {
+			controller = &pci_controllers[i];
+			break;
 		}
 	}
 
 	if (controller == NULL)
 		return NULL;
 
-got_it:
 	trio_fd = controller->trio->fd;
 
 	/* Convert the resource start to the bus address offset. */
@@ -1112,14 +1143,71 @@ got_it:
 
 	offset = HV_TRIO_PIO_OFFSET(controller->pio_mem_index) + start;
 
-	/*
-	 * We need to keep the PCI bus address's in-page offset in the VA.
-	 */
+	/* We need to keep the PCI bus address's in-page offset in the VA. */
 	return iorpc_ioremap(trio_fd, offset, size) +
-		(phys_addr & (PAGE_SIZE - 1));
+		(start & (PAGE_SIZE - 1));
 }
 EXPORT_SYMBOL(ioremap);
 
+#ifdef CONFIG_TILE_PCI_IO
+/* Map a PCI I/O address into VA space. */
+void __iomem *ioport_map(unsigned long port, unsigned int size)
+{
+	struct pci_controller *controller = NULL;
+	resource_size_t bar_start;
+	resource_size_t bar_end;
+	resource_size_t offset;
+	resource_size_t start;
+	resource_size_t end;
+	int trio_fd;
+	int i;
+
+	start = port;
+	end = port + size - 1;
+
+	/*
+	 * By searching the port in each controller's io_space, we can
+	 * determine the controller that should accept the PCI I/O access.
+	 */
+	for (i = 0; i < num_rc_controllers; i++) {
+		/*
+		 * Skip controllers that are not properly initialized or
+		 * have down links.
+		 */
+		if (pci_controllers[i].root_bus == NULL)
+			continue;
+
+		bar_start = pci_controllers[i].io_space.start;
+		bar_end = pci_controllers[i].io_space.end;
+
+		if ((start >= bar_start) && (end <= bar_end)) {
+			controller = &pci_controllers[i];
+			break;
+		}
+	}
+
+	if (controller == NULL)
+		return NULL;
+
+	trio_fd = controller->trio->fd;
+
+	/* Convert the resource start to the bus address offset. */
+	port -= controller->io_space.start;
+
+	offset = HV_TRIO_PIO_OFFSET(controller->pio_io_index) + port;
+
+	/* We need to keep the PCI bus address's in-page offset in the VA. */
+	return iorpc_ioremap(trio_fd, offset, size) + (port & (PAGE_SIZE - 1));
+}
+EXPORT_SYMBOL(ioport_map);
+
+void ioport_unmap(void __iomem *addr)
+{
+	iounmap(addr);
+}
+EXPORT_SYMBOL(ioport_unmap);
+#endif
+
 void pci_iounmap(struct pci_dev *dev, void __iomem *addr)
 {
 	iounmap(addr);
@@ -1141,7 +1229,6 @@ EXPORT_SYMBOL(pci_iounmap);
  * offset is in bytes, from the start of config space for the
  * specified bus & device.
  */
-
 static int tile_cfg_read(struct pci_bus *bus, unsigned int devfn, int offset,
 			 int size, u32 *val)
 {
@@ -1191,7 +1278,6 @@ static int tile_cfg_read(struct pci_bus *bus, unsigned int devfn, int offset,
 	 * Accesses to the directly attached device have to be
 	 * sent as type-0 configs.
 	 */
-
 	if (busnum == (controller->first_busno + 1)) {
 		/*
 		 * There is only one device off of our built-in P2P bridge.
@@ -1213,9 +1299,8 @@ static int tile_cfg_read(struct pci_bus *bus, unsigned int devfn, int offset,
 	 * Note that we don't set the mac field in cfg_addr because the
 	 * mapping is per port.
 	 */
-
 	mmio_addr = trio_context->mmio_base_pio_cfg[controller->mac] +
-			cfg_addr.word;
+		cfg_addr.word;
 
 valid_device:
 
@@ -1319,7 +1404,6 @@ static int tile_cfg_write(struct pci_bus *bus, unsigned int devfn, int offset,
 	 * Accesses to the directly attached device have to be
 	 * sent as type-0 configs.
 	 */
-
 	if (busnum == (controller->first_busno + 1)) {
 		/*
 		 * There is only one device off of our built-in P2P bridge.
@@ -1341,7 +1425,6 @@ static int tile_cfg_write(struct pci_bus *bus, unsigned int devfn, int offset,
 	 * Note that we don't set the mac field in cfg_addr because the
 	 * mapping is per port.
 	 */
-
 	mmio_addr = trio_context->mmio_base_pio_cfg[controller->mac] +
 			cfg_addr.word;
 
@@ -1379,11 +1462,8 @@ static struct pci_ops tile_cfg_ops = {
 };
 
 
-/*
- * MSI support starts here.
- */
-static unsigned int
-tilegx_msi_startup(struct irq_data *d)
+/* MSI support starts here. */
+static unsigned int tilegx_msi_startup(struct irq_data *d)
 {
 	if (d->msi_desc)
 		unmask_msi_irq(d);
@@ -1391,21 +1471,18 @@ tilegx_msi_startup(struct irq_data *d)
 	return 0;
 }
 
-static void
-tilegx_msi_ack(struct irq_data *d)
+static void tilegx_msi_ack(struct irq_data *d)
 {
 	__insn_mtspr(SPR_IPI_EVENT_RESET_K, 1UL << d->irq);
 }
 
-static void
-tilegx_msi_mask(struct irq_data *d)
+static void tilegx_msi_mask(struct irq_data *d)
 {
 	mask_msi_irq(d);
 	__insn_mtspr(SPR_IPI_MASK_SET_K, 1UL << d->irq);
 }
 
-static void
-tilegx_msi_unmask(struct irq_data *d)
+static void tilegx_msi_unmask(struct irq_data *d)
 {
 	__insn_mtspr(SPR_IPI_MASK_RESET_K, 1UL << d->irq);
 	unmask_msi_irq(d);
@@ -1462,32 +1539,55 @@ int arch_setup_msi_irq(struct pci_dev *pdev, struct msi_desc *desc)
 	trio_context = controller->trio;
 
 	/*
-	 * Allocate the Mem-Map that will accept the MSI write and
-	 * trigger the TILE-side interrupts.
+	 * Allocate a scatter-queue that will accept the MSI write and
+	 * trigger the TILE-side interrupts. We use the scatter-queue regions
+	 * before the mem map regions, because the latter are needed by more
+	 * applications.
 	 */
-	mem_map = gxio_trio_alloc_memory_maps(trio_context, 1, 0, 0);
-	if (mem_map < 0) {
-		dev_printk(KERN_INFO, &pdev->dev,
-			"%s Mem-Map alloc failure. "
-			"Failed to initialize MSI interrupts. "
-			"Falling back to legacy interrupts.\n",
-			desc->msi_attrib.is_msix ? "MSI-X" : "MSI");
+	mem_map = gxio_trio_alloc_scatter_queues(trio_context, 1, 0, 0);
+	if (mem_map >= 0) {
+		TRIO_MAP_SQ_DOORBELL_FMT_t doorbell_template = {{
+			.pop = 0,
+			.doorbell = 1,
+		}};
+
+		mem_map += TRIO_NUM_MAP_MEM_REGIONS;
+		mem_map_base = MEM_MAP_INTR_REGIONS_BASE +
+			mem_map * MEM_MAP_INTR_REGION_SIZE;
+		mem_map_limit = mem_map_base + MEM_MAP_INTR_REGION_SIZE - 1;
+
+		msi_addr = mem_map_base + MEM_MAP_INTR_REGION_SIZE - 8;
+		msg.data = (unsigned int)doorbell_template.word;
+	} else {
+		/* SQ regions are out, allocate from map mem regions. */
+		mem_map = gxio_trio_alloc_memory_maps(trio_context, 1, 0, 0);
+		if (mem_map < 0) {
+			dev_printk(KERN_INFO, &pdev->dev,
+				"%s Mem-Map alloc failure. "
+				"Failed to initialize MSI interrupts. "
+				"Falling back to legacy interrupts.\n",
+				desc->msi_attrib.is_msix ? "MSI-X" : "MSI");
+			ret = -ENOMEM;
+			goto msi_mem_map_alloc_failure;
+		}
 
-		ret = -ENOMEM;
-		goto msi_mem_map_alloc_failure;
+		mem_map_base = MEM_MAP_INTR_REGIONS_BASE +
+			mem_map * MEM_MAP_INTR_REGION_SIZE;
+		mem_map_limit = mem_map_base + MEM_MAP_INTR_REGION_SIZE - 1;
+
+		msi_addr = mem_map_base + TRIO_MAP_MEM_REG_INT3 -
+			TRIO_MAP_MEM_REG_INT0;
+
+		msg.data = mem_map;
 	}
 
 	/* We try to distribute different IRQs to different tiles. */
 	cpu = tile_irq_cpu(irq);
 
 	/*
-	 * Now call up to the HV to configure the Mem-Map interrupt and
+	 * Now call up to the HV to configure the MSI interrupt and
 	 * set up the IPI binding.
 	 */
-	mem_map_base = MEM_MAP_INTR_REGIONS_BASE +
-		mem_map * MEM_MAP_INTR_REGION_SIZE;
-	mem_map_limit = mem_map_base + MEM_MAP_INTR_REGION_SIZE - 1;
-
 	ret = gxio_trio_config_msi_intr(trio_context, cpu_x(cpu), cpu_y(cpu),
 					KERNEL_PL, irq, controller->mac,
 					mem_map, mem_map_base, mem_map_limit,
@@ -1500,13 +1600,9 @@ int arch_setup_msi_irq(struct pci_dev *pdev, struct msi_desc *desc)
 
 	irq_set_msi_desc(irq, desc);
 
-	msi_addr = mem_map_base + TRIO_MAP_MEM_REG_INT3 - TRIO_MAP_MEM_REG_INT0;
-
 	msg.address_hi = msi_addr >> 32;
 	msg.address_lo = msi_addr & 0xffffffff;
 
-	msg.data = mem_map;
-
 	write_msi_msg(irq, &msg);
 	irq_set_chip_and_handler(irq, &tilegx_msi_chip, handle_level_irq);
 	irq_set_handler_data(irq, controller);
diff --git a/arch/tile/kernel/proc.c b/arch/tile/kernel/proc.c
index dafc447b5125..681100c59fda 100644
--- a/arch/tile/kernel/proc.c
+++ b/arch/tile/kernel/proc.c
@@ -113,7 +113,6 @@ arch_initcall(proc_tile_init);
  * Support /proc/sys/tile directory
  */
 
-#ifndef __tilegx__  /* FIXME: GX: no support for unaligned access yet */
 static ctl_table unaligned_subtable[] = {
 	{
 		.procname	= "enabled",
@@ -160,4 +159,3 @@ static int __init proc_sys_tile_init(void)
 }
 
 arch_initcall(proc_sys_tile_init);
-#endif
diff --git a/arch/tile/kernel/process.c b/arch/tile/kernel/process.c
index 8ac304484f98..16ed58948757 100644
--- a/arch/tile/kernel/process.c
+++ b/arch/tile/kernel/process.c
@@ -33,6 +33,7 @@
 #include <asm/syscalls.h>
 #include <asm/traps.h>
 #include <asm/setup.h>
+#include <asm/uaccess.h>
 #ifdef CONFIG_HARDWALL
 #include <asm/hardwall.h>
 #endif
@@ -74,19 +75,6 @@ void arch_release_thread_info(struct thread_info *info)
 {
 	struct single_step_state *step_state = info->step_state;
 
-#ifdef CONFIG_HARDWALL
-	/*
-	 * We free a thread_info from the context of the task that has
-	 * been scheduled next, so the original task is already dead.
-	 * Calling deactivate here just frees up the data structures.
-	 * If the task we're freeing held the last reference to a
-	 * hardwall fd, it would have been released prior to this point
-	 * anyway via exit_files(), and the hardwall_task.info pointers
-	 * would be NULL by now.
-	 */
-	hardwall_deactivate_all(info->task);
-#endif
-
 	if (step_state) {
 
 		/*
@@ -160,6 +148,14 @@ int copy_thread(unsigned long clone_flags, unsigned long sp,
 	 */
 	task_thread_info(p)->step_state = NULL;
 
+#ifdef __tilegx__
+	/*
+	 * Do not clone unalign jit fixup from the parent; each thread
+	 * must allocate its own on demand.
+	 */
+	task_thread_info(p)->unalign_jit_base = NULL;
+#endif
+
 	/*
 	 * Copy the registers onto the kernel stack so the
 	 * return-from-interrupt code will reload it into registers.
@@ -191,16 +187,8 @@ int copy_thread(unsigned long clone_flags, unsigned long sp,
 	memset(&p->thread.dma_async_tlb, 0, sizeof(struct async_tlb));
 #endif
 
-#if CHIP_HAS_SN_PROC()
-	/* Likewise, the new thread is not running static processor code. */
-	p->thread.sn_proc_running = 0;
-	memset(&p->thread.sn_async_tlb, 0, sizeof(struct async_tlb));
-#endif
-
-#if CHIP_HAS_PROC_STATUS_SPR()
 	/* New thread has its miscellaneous processor state bits clear. */
 	p->thread.proc_status = 0;
-#endif
 
 #ifdef CONFIG_HARDWALL
 	/* New thread does not own any networks. */
@@ -218,19 +206,32 @@ int copy_thread(unsigned long clone_flags, unsigned long sp,
 	return 0;
 }
 
+int set_unalign_ctl(struct task_struct *tsk, unsigned int val)
+{
+	task_thread_info(tsk)->align_ctl = val;
+	return 0;
+}
+
+int get_unalign_ctl(struct task_struct *tsk, unsigned long adr)
+{
+	return put_user(task_thread_info(tsk)->align_ctl,
+			(unsigned int __user *)adr);
+}
+
+static struct task_struct corrupt_current = { .comm = "<corrupt>" };
+
 /*
  * Return "current" if it looks plausible, or else a pointer to a dummy.
  * This can be helpful if we are just trying to emit a clean panic.
  */
 struct task_struct *validate_current(void)
 {
-	static struct task_struct corrupt = { .comm = "<corrupt>" };
 	struct task_struct *tsk = current;
 	if (unlikely((unsigned long)tsk < PAGE_OFFSET ||
 		     (high_memory && (void *)tsk > high_memory) ||
 		     ((unsigned long)tsk & (__alignof__(*tsk) - 1)) != 0)) {
 		pr_err("Corrupt 'current' %p (sp %#lx)\n", tsk, stack_pointer);
-		tsk = &corrupt;
+		tsk = &corrupt_current;
 	}
 	return tsk;
 }
@@ -369,15 +370,11 @@ static void save_arch_state(struct thread_struct *t)
 	t->system_save[2] = __insn_mfspr(SPR_SYSTEM_SAVE_0_2);
 	t->system_save[3] = __insn_mfspr(SPR_SYSTEM_SAVE_0_3);
 	t->intctrl_0 = __insn_mfspr(SPR_INTCTRL_0_STATUS);
-#if CHIP_HAS_PROC_STATUS_SPR()
 	t->proc_status = __insn_mfspr(SPR_PROC_STATUS);
-#endif
 #if !CHIP_HAS_FIXED_INTVEC_BASE()
 	t->interrupt_vector_base = __insn_mfspr(SPR_INTERRUPT_VECTOR_BASE_0);
 #endif
-#if CHIP_HAS_TILE_RTF_HWM()
 	t->tile_rtf_hwm = __insn_mfspr(SPR_TILE_RTF_HWM);
-#endif
 #if CHIP_HAS_DSTREAM_PF()
 	t->dstream_pf = __insn_mfspr(SPR_DSTREAM_PF);
 #endif
@@ -398,15 +395,11 @@ static void restore_arch_state(const struct thread_struct *t)
 	__insn_mtspr(SPR_SYSTEM_SAVE_0_2, t->system_save[2]);
 	__insn_mtspr(SPR_SYSTEM_SAVE_0_3, t->system_save[3]);
 	__insn_mtspr(SPR_INTCTRL_0_STATUS, t->intctrl_0);
-#if CHIP_HAS_PROC_STATUS_SPR()
 	__insn_mtspr(SPR_PROC_STATUS, t->proc_status);
-#endif
 #if !CHIP_HAS_FIXED_INTVEC_BASE()
 	__insn_mtspr(SPR_INTERRUPT_VECTOR_BASE_0, t->interrupt_vector_base);
 #endif
-#if CHIP_HAS_TILE_RTF_HWM()
 	__insn_mtspr(SPR_TILE_RTF_HWM, t->tile_rtf_hwm);
-#endif
 #if CHIP_HAS_DSTREAM_PF()
 	__insn_mtspr(SPR_DSTREAM_PF, t->dstream_pf);
 #endif
@@ -415,26 +408,11 @@ static void restore_arch_state(const struct thread_struct *t)
 
 void _prepare_arch_switch(struct task_struct *next)
 {
-#if CHIP_HAS_SN_PROC()
-	int snctl;
-#endif
 #if CHIP_HAS_TILE_DMA()
 	struct tile_dma_state *dma = &current->thread.tile_dma_state;
 	if (dma->enabled)
 		save_tile_dma_state(dma);
 #endif
-#if CHIP_HAS_SN_PROC()
-	/*
-	 * Suspend the static network processor if it was running.
-	 * We do not suspend the fabric itself, just like we don't
-	 * try to suspend the UDN.
-	 */
-	snctl = __insn_mfspr(SPR_SNCTL);
-	current->thread.sn_proc_running =
-		(snctl & SPR_SNCTL__FRZPROC_MASK) == 0;
-	if (current->thread.sn_proc_running)
-		__insn_mtspr(SPR_SNCTL, snctl | SPR_SNCTL__FRZPROC_MASK);
-#endif
 }
 
 
@@ -462,17 +440,6 @@ struct task_struct *__sched _switch_to(struct task_struct *prev,
 	/* Restore other arch state. */
 	restore_arch_state(&next->thread);
 
-#if CHIP_HAS_SN_PROC()
-	/*
-	 * Restart static network processor in the new process
-	 * if it was running before.
-	 */
-	if (next->thread.sn_proc_running) {
-		int snctl = __insn_mfspr(SPR_SNCTL);
-		__insn_mtspr(SPR_SNCTL, snctl & ~SPR_SNCTL__FRZPROC_MASK);
-	}
-#endif
-
 #ifdef CONFIG_HARDWALL
 	/* Enable or disable access to the network registers appropriately. */
 	hardwall_switch_tasks(prev, next);
@@ -514,7 +481,7 @@ int do_work_pending(struct pt_regs *regs, u32 thread_info_flags)
 		schedule();
 		return 1;
 	}
-#if CHIP_HAS_TILE_DMA() || CHIP_HAS_SN_PROC()
+#if CHIP_HAS_TILE_DMA()
 	if (thread_info_flags & _TIF_ASYNC_TLB) {
 		do_async_page_fault(regs);
 		return 1;
@@ -564,7 +531,15 @@ void flush_thread(void)
  */
 void exit_thread(void)
 {
-	/* Nothing */
+#ifdef CONFIG_HARDWALL
+	/*
+	 * Remove the task from the list of tasks that are associated
+	 * with any live hardwalls.  (If the task that is exiting held
+	 * the last reference to a hardwall fd, it would already have
+	 * been released and deactivated at this point.)
+	 */
+	hardwall_deactivate_all(current);
+#endif
 }
 
 void show_regs(struct pt_regs *regs)
@@ -573,23 +548,24 @@ void show_regs(struct pt_regs *regs)
 	int i;
 
 	pr_err("\n");
-	show_regs_print_info(KERN_ERR);
+	if (tsk != &corrupt_current)
+		show_regs_print_info(KERN_ERR);
 #ifdef __tilegx__
-	for (i = 0; i < 51; i += 3)
+	for (i = 0; i < 17; i++)
 		pr_err(" r%-2d: "REGFMT" r%-2d: "REGFMT" r%-2d: "REGFMT"\n",
-		       i, regs->regs[i], i+1, regs->regs[i+1],
-		       i+2, regs->regs[i+2]);
-	pr_err(" r51: "REGFMT" r52: "REGFMT" tp : "REGFMT"\n",
-	       regs->regs[51], regs->regs[52], regs->tp);
+		       i, regs->regs[i], i+18, regs->regs[i+18],
+		       i+36, regs->regs[i+36]);
+	pr_err(" r17: "REGFMT" r35: "REGFMT" tp : "REGFMT"\n",
+	       regs->regs[17], regs->regs[35], regs->tp);
 	pr_err(" sp : "REGFMT" lr : "REGFMT"\n", regs->sp, regs->lr);
 #else
-	for (i = 0; i < 52; i += 4)
+	for (i = 0; i < 13; i++)
 		pr_err(" r%-2d: "REGFMT" r%-2d: "REGFMT
 		       " r%-2d: "REGFMT" r%-2d: "REGFMT"\n",
-		       i, regs->regs[i], i+1, regs->regs[i+1],
-		       i+2, regs->regs[i+2], i+3, regs->regs[i+3]);
-	pr_err(" r52: "REGFMT" tp : "REGFMT" sp : "REGFMT" lr : "REGFMT"\n",
-	       regs->regs[52], regs->tp, regs->sp, regs->lr);
+		       i, regs->regs[i], i+14, regs->regs[i+14],
+		       i+27, regs->regs[i+27], i+40, regs->regs[i+40]);
+	pr_err(" r13: "REGFMT" tp : "REGFMT" sp : "REGFMT" lr : "REGFMT"\n",
+	       regs->regs[13], regs->tp, regs->sp, regs->lr);
 #endif
 	pr_err(" pc : "REGFMT" ex1: %ld     faultnum: %ld\n",
 	       regs->pc, regs->ex1, regs->faultnum);
diff --git a/arch/tile/kernel/ptrace.c b/arch/tile/kernel/ptrace.c
index 0f83ed4602b2..de98c6ddf136 100644
--- a/arch/tile/kernel/ptrace.c
+++ b/arch/tile/kernel/ptrace.c
@@ -265,6 +265,21 @@ int do_syscall_trace_enter(struct pt_regs *regs)
 
 void do_syscall_trace_exit(struct pt_regs *regs)
 {
+	long errno;
+
+	/*
+	 * The standard tile calling convention returns the value (or negative
+	 * errno) in r0, and zero (or positive errno) in r1.
+	 * It saves a couple of cycles on the hot path to do this work in
+	 * registers only as we return, rather than updating the in-memory
+	 * struct ptregs.
+	 */
+	errno = (long) regs->regs[0];
+	if (errno < 0 && errno > -4096)
+		regs->regs[1] = -errno;
+	else
+		regs->regs[1] = 0;
+
 	if (test_thread_flag(TIF_SYSCALL_TRACE))
 		tracehook_report_syscall_exit(regs, 0);
 
@@ -272,7 +287,7 @@ void do_syscall_trace_exit(struct pt_regs *regs)
 		trace_sys_exit(regs, regs->regs[0]);
 }
 
-void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs, int error_code)
+void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs)
 {
 	struct siginfo info;
 
@@ -288,5 +303,5 @@ void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs, int error_code)
 /* Handle synthetic interrupt delivered only by the simulator. */
 void __kprobes do_breakpoint(struct pt_regs* regs, int fault_num)
 {
-	send_sigtrap(current, regs, fault_num);
+	send_sigtrap(current, regs);
 }
diff --git a/arch/tile/kernel/reboot.c b/arch/tile/kernel/reboot.c
index d1b5c913ae72..6c5d2c070a12 100644
--- a/arch/tile/kernel/reboot.c
+++ b/arch/tile/kernel/reboot.c
@@ -27,7 +27,6 @@
 
 void machine_halt(void)
 {
-	warn_early_printk();
 	arch_local_irq_disable_all();
 	smp_send_stop();
 	hv_halt();
@@ -35,7 +34,6 @@ void machine_halt(void)
 
 void machine_power_off(void)
 {
-	warn_early_printk();
 	arch_local_irq_disable_all();
 	smp_send_stop();
 	hv_power_off();
diff --git a/arch/tile/kernel/regs_32.S b/arch/tile/kernel/regs_32.S
index c12280c2d904..542cae17a93a 100644
--- a/arch/tile/kernel/regs_32.S
+++ b/arch/tile/kernel/regs_32.S
@@ -20,7 +20,7 @@
 #include <asm/switch_to.h>
 
 /*
- * See <asm/system.h>; called with prev and next task_struct pointers.
+ * See <asm/switch_to.h>; called with prev and next task_struct pointers.
  * "prev" is returned in r0 for _switch_to and also for ret_from_fork.
  *
  * We want to save pc/sp in "prev", and get the new pc/sp from "next".
@@ -39,7 +39,7 @@
  */
 
 #if CALLEE_SAVED_REGS_COUNT != 24
-# error Mismatch between <asm/system.h> and kernel/entry.S
+# error Mismatch between <asm/switch_to.h> and kernel/entry.S
 #endif
 #define FRAME_SIZE ((2 + CALLEE_SAVED_REGS_COUNT) * 4)
 
diff --git a/arch/tile/kernel/regs_64.S b/arch/tile/kernel/regs_64.S
index 0829fd01fa30..bbffcc6f340f 100644
--- a/arch/tile/kernel/regs_64.S
+++ b/arch/tile/kernel/regs_64.S
@@ -20,7 +20,7 @@
 #include <asm/switch_to.h>
 
 /*
- * See <asm/system.h>; called with prev and next task_struct pointers.
+ * See <asm/switch_to.h>; called with prev and next task_struct pointers.
  * "prev" is returned in r0 for _switch_to and also for ret_from_fork.
  *
  * We want to save pc/sp in "prev", and get the new pc/sp from "next".
@@ -39,7 +39,7 @@
  */
 
 #if CALLEE_SAVED_REGS_COUNT != 24
-# error Mismatch between <asm/system.h> and kernel/entry.S
+# error Mismatch between <asm/switch_to.h> and kernel/entry.S
 #endif
 #define FRAME_SIZE ((2 + CALLEE_SAVED_REGS_COUNT) * 8)
 
diff --git a/arch/tile/kernel/relocate_kernel_32.S b/arch/tile/kernel/relocate_kernel_32.S
index 010b418515f8..e44fbcf8cbd5 100644
--- a/arch/tile/kernel/relocate_kernel_32.S
+++ b/arch/tile/kernel/relocate_kernel_32.S
@@ -20,15 +20,6 @@
 #include <asm/page.h>
 #include <hv/hypervisor.h>
 
-#define ___hvb	MEM_SV_INTRPT + HV_GLUE_START_CPA
-
-#define ___hv_dispatch(f) (___hvb + (HV_DISPATCH_ENTRY_SIZE * f))
-
-#define ___hv_console_putc ___hv_dispatch(HV_DISPATCH_CONSOLE_PUTC)
-#define ___hv_halt         ___hv_dispatch(HV_DISPATCH_HALT)
-#define ___hv_reexec       ___hv_dispatch(HV_DISPATCH_REEXEC)
-#define ___hv_flush_remote ___hv_dispatch(HV_DISPATCH_FLUSH_REMOTE)
-
 #undef RELOCATE_NEW_KERNEL_VERBOSE
 
 STD_ENTRY(relocate_new_kernel)
@@ -43,8 +34,8 @@ STD_ENTRY(relocate_new_kernel)
 	addi	sp, sp, -8
 	/* we now have a stack (whether we need one or not) */
 
-	moveli	r40, lo16(___hv_console_putc)
-	auli	r40, r40, ha16(___hv_console_putc)
+	moveli	r40, lo16(hv_console_putc)
+	auli	r40, r40, ha16(hv_console_putc)
 
 #ifdef RELOCATE_NEW_KERNEL_VERBOSE
 	moveli	r0, 'r'
@@ -86,7 +77,6 @@ STD_ENTRY(relocate_new_kernel)
 	move	r30, sp
 	addi	sp, sp, -8
 
-#if CHIP_HAS_CBOX_HOME_MAP()
 	/*
 	 * On TILEPro, we need to flush all tiles' caches, since we may
 	 * have been doing hash-for-home caching there.  Note that we
@@ -114,15 +104,14 @@ STD_ENTRY(relocate_new_kernel)
 	}
 	{
 	 move	r8, zero	 /* asids */
-	 moveli	r20, lo16(___hv_flush_remote)
+	 moveli	r20, lo16(hv_flush_remote)
 	}
 	{
 	 move	r9, zero	 /* asidcount */
-	 auli	r20, r20, ha16(___hv_flush_remote)
+	 auli	r20, r20, ha16(hv_flush_remote)
 	}
 
 	jalr	r20
-#endif
 
 	/* r33 is destination pointer, default to zero */
 
@@ -175,8 +164,8 @@ STD_ENTRY(relocate_new_kernel)
 	move	r0, r32
 	moveli	r1, 0		/* arg to hv_reexec is 64 bits */
 
-	moveli	r41, lo16(___hv_reexec)
-	auli	r41, r41, ha16(___hv_reexec)
+	moveli	r41, lo16(hv_reexec)
+	auli	r41, r41, ha16(hv_reexec)
 
 	jalr	r41
 
@@ -267,8 +256,8 @@ STD_ENTRY(relocate_new_kernel)
 	moveli	r0, '\n'
 	jalr	r40
 .Lhalt:
-	moveli	r41, lo16(___hv_halt)
-	auli	r41, r41, ha16(___hv_halt)
+	moveli	r41, lo16(hv_halt)
+	auli	r41, r41, ha16(hv_halt)
 
 	jalr	r41
 	STD_ENDPROC(relocate_new_kernel)
diff --git a/arch/tile/kernel/relocate_kernel_64.S b/arch/tile/kernel/relocate_kernel_64.S
index 1c09a4f5a4ea..d9d8cf6176e8 100644
--- a/arch/tile/kernel/relocate_kernel_64.S
+++ b/arch/tile/kernel/relocate_kernel_64.S
@@ -34,11 +34,11 @@ STD_ENTRY(relocate_new_kernel)
 	addi	sp, sp, -8
 	/* we now have a stack (whether we need one or not) */
 
+#ifdef RELOCATE_NEW_KERNEL_VERBOSE
 	moveli	r40, hw2_last(hv_console_putc)
 	shl16insli r40, r40, hw1(hv_console_putc)
 	shl16insli r40, r40, hw0(hv_console_putc)
 
-#ifdef RELOCATE_NEW_KERNEL_VERBOSE
 	moveli	r0, 'r'
 	jalr	r40
 
@@ -78,7 +78,6 @@ STD_ENTRY(relocate_new_kernel)
 	move	r30, sp
 	addi	sp, sp, -16
 
-#if CHIP_HAS_CBOX_HOME_MAP()
 	/*
 	 * On TILE-GX, we need to flush all tiles' caches, since we may
 	 * have been doing hash-for-home caching there.  Note that we
@@ -116,7 +115,6 @@ STD_ENTRY(relocate_new_kernel)
 	shl16insli	r20, r20, hw0(hv_flush_remote)
 
 	jalr	r20
-#endif
 
 	/* r33 is destination pointer, default to zero */
 
@@ -176,10 +174,12 @@ STD_ENTRY(relocate_new_kernel)
 
 	/* we should not get here */
 
+#ifdef RELOCATE_NEW_KERNEL_VERBOSE
 	moveli	r0, '?'
 	jalr	r40
 	moveli	r0, '\n'
 	jalr	r40
+#endif
 
 	j	.Lhalt
 
@@ -237,7 +237,9 @@ STD_ENTRY(relocate_new_kernel)
 	j	.Lloop
 
 
-.Lerr:	moveli	r0, 'e'
+.Lerr:
+#ifdef RELOCATE_NEW_KERNEL_VERBOSE
+	moveli	r0, 'e'
 	jalr	r40
 	moveli	r0, 'r'
 	jalr	r40
@@ -245,6 +247,7 @@ STD_ENTRY(relocate_new_kernel)
 	jalr	r40
 	moveli	r0, '\n'
 	jalr	r40
+#endif
 .Lhalt:
 	moveli r41, hw2_last(hv_halt)
 	shl16insli r41, r41, hw1(hv_halt)
diff --git a/arch/tile/kernel/setup.c b/arch/tile/kernel/setup.c
index eceb8344280f..74c91729a62a 100644
--- a/arch/tile/kernel/setup.c
+++ b/arch/tile/kernel/setup.c
@@ -154,6 +154,65 @@ static int __init setup_maxnodemem(char *str)
 }
 early_param("maxnodemem", setup_maxnodemem);
 
+struct memmap_entry {
+	u64 addr;	/* start of memory segment */
+	u64 size;	/* size of memory segment */
+};
+static struct memmap_entry memmap_map[64];
+static int memmap_nr;
+
+static void add_memmap_region(u64 addr, u64 size)
+{
+	if (memmap_nr >= ARRAY_SIZE(memmap_map)) {
+		pr_err("Ooops! Too many entries in the memory map!\n");
+		return;
+	}
+	memmap_map[memmap_nr].addr = addr;
+	memmap_map[memmap_nr].size = size;
+	memmap_nr++;
+}
+
+static int __init setup_memmap(char *p)
+{
+	char *oldp;
+	u64 start_at, mem_size;
+
+	if (!p)
+		return -EINVAL;
+
+	if (!strncmp(p, "exactmap", 8)) {
+		pr_err("\"memmap=exactmap\" not valid on tile\n");
+		return 0;
+	}
+
+	oldp = p;
+	mem_size = memparse(p, &p);
+	if (p == oldp)
+		return -EINVAL;
+
+	if (*p == '@') {
+		pr_err("\"memmap=nn@ss\" (force RAM) invalid on tile\n");
+	} else if (*p == '#') {
+		pr_err("\"memmap=nn#ss\" (force ACPI data) invalid on tile\n");
+	} else if (*p == '$') {
+		start_at = memparse(p+1, &p);
+		add_memmap_region(start_at, mem_size);
+	} else {
+		if (mem_size == 0)
+			return -EINVAL;
+		maxmem_pfn = (mem_size >> HPAGE_SHIFT) <<
+			(HPAGE_SHIFT - PAGE_SHIFT);
+	}
+	return *p == '\0' ? 0 : -EINVAL;
+}
+early_param("memmap", setup_memmap);
+
+static int __init setup_mem(char *str)
+{
+	return setup_maxmem(str);
+}
+early_param("mem", setup_mem);  /* compatibility with x86 */
+
 static int __init setup_isolnodes(char *str)
 {
 	char buf[MAX_NUMNODES * 5];
@@ -209,7 +268,7 @@ early_param("vmalloc", parse_vmalloc);
 /*
  * Determine for each controller where its lowmem is mapped and how much of
  * it is mapped there.  On controller zero, the first few megabytes are
- * already mapped in as code at MEM_SV_INTRPT, so in principle we could
+ * already mapped in as code at MEM_SV_START, so in principle we could
  * start our data mappings higher up, but for now we don't bother, to avoid
  * additional confusion.
  *
@@ -614,11 +673,12 @@ static void __init setup_bootmem_allocator_node(int i)
 	/*
 	 * Throw away any memory aliased by the PCI region.
 	 */
-	if (pci_reserve_start_pfn < end && pci_reserve_end_pfn > start)
-		reserve_bootmem(PFN_PHYS(pci_reserve_start_pfn),
-				PFN_PHYS(pci_reserve_end_pfn -
-					 pci_reserve_start_pfn),
+	if (pci_reserve_start_pfn < end && pci_reserve_end_pfn > start) {
+		start = max(pci_reserve_start_pfn, start);
+		end = min(pci_reserve_end_pfn, end);
+		reserve_bootmem(PFN_PHYS(start), PFN_PHYS(end - start),
 				BOOTMEM_EXCLUSIVE);
+	}
 #endif
 }
 
@@ -628,6 +688,31 @@ static void __init setup_bootmem_allocator(void)
 	for (i = 0; i < MAX_NUMNODES; ++i)
 		setup_bootmem_allocator_node(i);
 
+	/* Reserve any memory excluded by "memmap" arguments. */
+	for (i = 0; i < memmap_nr; ++i) {
+		struct memmap_entry *m = &memmap_map[i];
+		reserve_bootmem(m->addr, m->size, 0);
+	}
+
+#ifdef CONFIG_BLK_DEV_INITRD
+	if (initrd_start) {
+		/* Make sure the initrd memory region is not modified. */
+		if (reserve_bootmem(initrd_start, initrd_end - initrd_start,
+				    BOOTMEM_EXCLUSIVE)) {
+			pr_crit("The initrd memory region has been polluted. Disabling it.\n");
+			initrd_start = 0;
+			initrd_end = 0;
+		} else {
+			/*
+			 * Translate initrd_start & initrd_end from PA to VA for
+			 * future access.
+			 */
+			initrd_start += PAGE_OFFSET;
+			initrd_end += PAGE_OFFSET;
+		}
+	}
+#endif
+
 #ifdef CONFIG_KEXEC
 	if (crashk_res.start != crashk_res.end)
 		reserve_bootmem(crashk_res.start, resource_size(&crashk_res), 0);
@@ -961,9 +1046,6 @@ void setup_cpu(int boot)
 	arch_local_irq_unmask(INT_DMATLB_MISS);
 	arch_local_irq_unmask(INT_DMATLB_ACCESS);
 #endif
-#if CHIP_HAS_SN_PROC()
-	arch_local_irq_unmask(INT_SNITLB_MISS);
-#endif
 #ifdef __tilegx__
 	arch_local_irq_unmask(INT_SINGLE_STEP_K);
 #endif
@@ -978,10 +1060,6 @@ void setup_cpu(int boot)
 	/* Static network is not restricted. */
 	__insn_mtspr(SPR_MPL_SN_ACCESS_SET_0, 1);
 #endif
-#if CHIP_HAS_SN_PROC()
-	__insn_mtspr(SPR_MPL_SN_NOTIFY_SET_0, 1);
-	__insn_mtspr(SPR_MPL_SN_CPL_SET_0, 1);
-#endif
 
 	/*
 	 * Set the MPL for interrupt control 0 & 1 to the corresponding
@@ -1029,6 +1107,10 @@ static void __init load_hv_initrd(void)
 	int fd, rc;
 	void *initrd;
 
+	/* If initrd has already been set, skip initramfs file in hvfs. */
+	if (initrd_start)
+		return;
+
 	fd = hv_fs_findfile((HV_VirtAddr) initramfs_file);
 	if (fd == HV_ENOENT) {
 		if (set_initramfs_file) {
@@ -1067,6 +1149,25 @@ void __init free_initrd_mem(unsigned long begin, unsigned long end)
 	free_bootmem(__pa(begin), end - begin);
 }
 
+static int __init setup_initrd(char *str)
+{
+	char *endp;
+	unsigned long initrd_size;
+
+	initrd_size = str ? simple_strtoul(str, &endp, 0) : 0;
+	if (initrd_size == 0 || *endp != '@')
+		return -EINVAL;
+
+	initrd_start = simple_strtoul(endp+1, &endp, 0);
+	if (initrd_start == 0)
+		return -EINVAL;
+
+	initrd_end = initrd_start + initrd_size;
+
+	return 0;
+}
+early_param("initrd", setup_initrd);
+
 #else
 static inline void load_hv_initrd(void) {}
 #endif /* CONFIG_BLK_DEV_INITRD */
@@ -1134,7 +1235,7 @@ static void __init validate_va(void)
 #ifndef __tilegx__   /* FIXME: GX: probably some validation relevant here */
 	/*
 	 * Similarly, make sure we're only using allowed VAs.
-	 * We assume we can contiguously use MEM_USER_INTRPT .. MEM_HV_INTRPT,
+	 * We assume we can contiguously use MEM_USER_INTRPT .. MEM_HV_START,
 	 * and 0 .. KERNEL_HIGH_VADDR.
 	 * In addition, make sure we CAN'T use the end of memory, since
 	 * we use the last chunk of each pgd for the pgd_list.
@@ -1149,7 +1250,7 @@ static void __init validate_va(void)
 		if (range.size == 0)
 			break;
 		if (range.start <= MEM_USER_INTRPT &&
-		    range.start + range.size >= MEM_HV_INTRPT)
+		    range.start + range.size >= MEM_HV_START)
 			user_kernel_ok = 1;
 		if (range.start == 0)
 			max_va = range.size;
@@ -1167,8 +1268,7 @@ static void __init validate_va(void)
 	if ((long)VMALLOC_START >= 0)
 		early_panic(
 			"Linux VMALLOC region below the 2GB line (%#lx)!\n"
-			"Reconfigure the kernel with fewer NR_HUGE_VMAPS\n"
-			"or smaller VMALLOC_RESERVE.\n",
+			"Reconfigure the kernel with smaller VMALLOC_RESERVE.\n",
 			VMALLOC_START);
 #endif
 }
@@ -1183,7 +1283,6 @@ static void __init validate_va(void)
 struct cpumask __write_once cpu_lotar_map;
 EXPORT_SYMBOL(cpu_lotar_map);
 
-#if CHIP_HAS_CBOX_HOME_MAP()
 /*
  * hash_for_home_map lists all the tiles that hash-for-home data
  * will be cached on.  Note that this may includes tiles that are not
@@ -1193,7 +1292,6 @@ EXPORT_SYMBOL(cpu_lotar_map);
  */
 struct cpumask hash_for_home_map;
 EXPORT_SYMBOL(hash_for_home_map);
-#endif
 
 /*
  * cpu_cacheable_map lists all the cpus whose caches the hypervisor can
@@ -1286,7 +1384,6 @@ static void __init setup_cpu_maps(void)
 		cpu_lotar_map = *cpu_possible_mask;
 	}
 
-#if CHIP_HAS_CBOX_HOME_MAP()
 	/* Retrieve set of CPUs used for hash-for-home caching */
 	rc = hv_inquire_tiles(HV_INQ_TILES_HFH_CACHE,
 			      (HV_VirtAddr) hash_for_home_map.bits,
@@ -1294,9 +1391,6 @@ static void __init setup_cpu_maps(void)
 	if (rc < 0)
 		early_panic("hv_inquire_tiles(HFH_CACHE) failed: rc %d\n", rc);
 	cpumask_or(&cpu_cacheable_map, cpu_possible_mask, &hash_for_home_map);
-#else
-	cpu_cacheable_map = *cpu_possible_mask;
-#endif
 }
 
 
@@ -1492,7 +1586,7 @@ void __init setup_per_cpu_areas(void)
 
 			/* Update the vmalloc mapping and page home. */
 			unsigned long addr = (unsigned long)ptr + i;
-			pte_t *ptep = virt_to_pte(NULL, addr);
+			pte_t *ptep = virt_to_kpte(addr);
 			pte_t pte = *ptep;
 			BUG_ON(pfn != pte_pfn(pte));
 			pte = hv_pte_set_mode(pte, HV_PTE_MODE_CACHE_TILE_L3);
@@ -1501,12 +1595,12 @@ void __init setup_per_cpu_areas(void)
 
 			/* Update the lowmem mapping for consistency. */
 			lowmem_va = (unsigned long)pfn_to_kaddr(pfn);
-			ptep = virt_to_pte(NULL, lowmem_va);
+			ptep = virt_to_kpte(lowmem_va);
 			if (pte_huge(*ptep)) {
 				printk(KERN_DEBUG "early shatter of huge page"
 				       " at %#lx\n", lowmem_va);
 				shatter_pmd((pmd_t *)ptep);
-				ptep = virt_to_pte(NULL, lowmem_va);
+				ptep = virt_to_kpte(lowmem_va);
 				BUG_ON(pte_huge(*ptep));
 			}
 			BUG_ON(pfn != pte_pfn(*ptep));
@@ -1548,6 +1642,8 @@ insert_non_bus_resource(void)
 {
 	struct resource *res =
 		kzalloc(sizeof(struct resource), GFP_ATOMIC);
+	if (!res)
+		return NULL;
 	res->name = "Non-Bus Physical Address Space";
 	res->start = (1ULL << 32);
 	res->end = -1LL;
@@ -1561,11 +1657,13 @@ insert_non_bus_resource(void)
 #endif
 
 static struct resource* __init
-insert_ram_resource(u64 start_pfn, u64 end_pfn)
+insert_ram_resource(u64 start_pfn, u64 end_pfn, bool reserved)
 {
 	struct resource *res =
 		kzalloc(sizeof(struct resource), GFP_ATOMIC);
-	res->name = "System RAM";
+	if (!res)
+		return NULL;
+	res->name = reserved ? "Reserved" : "System RAM";
 	res->start = start_pfn << PAGE_SHIFT;
 	res->end = (end_pfn << PAGE_SHIFT) - 1;
 	res->flags = IORESOURCE_BUSY | IORESOURCE_MEM;
@@ -1585,7 +1683,7 @@ insert_ram_resource(u64 start_pfn, u64 end_pfn)
 static int __init request_standard_resources(void)
 {
 	int i;
-	enum { CODE_DELTA = MEM_SV_INTRPT - PAGE_OFFSET };
+	enum { CODE_DELTA = MEM_SV_START - PAGE_OFFSET };
 
 #if defined(CONFIG_PCI) && !defined(__tilegx__)
 	insert_non_bus_resource();
@@ -1600,11 +1698,11 @@ static int __init request_standard_resources(void)
 		    end_pfn > pci_reserve_start_pfn) {
 			if (end_pfn > pci_reserve_end_pfn)
 				insert_ram_resource(pci_reserve_end_pfn,
-						     end_pfn);
+						    end_pfn, 0);
 			end_pfn = pci_reserve_start_pfn;
 		}
 #endif
-		insert_ram_resource(start_pfn, end_pfn);
+		insert_ram_resource(start_pfn, end_pfn, 0);
 	}
 
 	code_resource.start = __pa(_text - CODE_DELTA);
@@ -1615,6 +1713,13 @@ static int __init request_standard_resources(void)
 	insert_resource(&iomem_resource, &code_resource);
 	insert_resource(&iomem_resource, &data_resource);
 
+	/* Mark any "memmap" regions busy for the resource manager. */
+	for (i = 0; i < memmap_nr; ++i) {
+		struct memmap_entry *m = &memmap_map[i];
+		insert_ram_resource(PFN_DOWN(m->addr),
+				    PFN_UP(m->addr + m->size - 1), 1);
+	}
+
 #ifdef CONFIG_KEXEC
 	insert_resource(&iomem_resource, &crashk_res);
 #endif
diff --git a/arch/tile/kernel/signal.c b/arch/tile/kernel/signal.c
index 9531845bf661..2d1dbf38a9ab 100644
--- a/arch/tile/kernel/signal.c
+++ b/arch/tile/kernel/signal.c
@@ -33,6 +33,7 @@
 #include <asm/ucontext.h>
 #include <asm/sigframe.h>
 #include <asm/syscalls.h>
+#include <asm/vdso.h>
 #include <arch/interrupts.h>
 
 #define DEBUG_SIG 0
@@ -190,7 +191,7 @@ static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
 	if (err)
 		goto give_sigsegv;
 
-	restorer = VDSO_BASE;
+	restorer = VDSO_SYM(&__vdso_rt_sigreturn);
 	if (ka->sa.sa_flags & SA_RESTORER)
 		restorer = (unsigned long) ka->sa.sa_restorer;
 
diff --git a/arch/tile/kernel/single_step.c b/arch/tile/kernel/single_step.c
index 27742e87e255..de07fa7d1315 100644
--- a/arch/tile/kernel/single_step.c
+++ b/arch/tile/kernel/single_step.c
@@ -12,41 +12,30 @@
  *   more details.
  *
  * A code-rewriter that enables instruction single-stepping.
- * Derived from iLib's single-stepping code.
  */
 
-#ifndef __tilegx__   /* Hardware support for single step unavailable. */
-
-/* These functions are only used on the TILE platform */
+#include <linux/smp.h>
+#include <linux/ptrace.h>
 #include <linux/slab.h>
 #include <linux/thread_info.h>
 #include <linux/uaccess.h>
 #include <linux/mman.h>
 #include <linux/types.h>
 #include <linux/err.h>
+#include <linux/prctl.h>
 #include <asm/cacheflush.h>
+#include <asm/traps.h>
+#include <asm/uaccess.h>
 #include <asm/unaligned.h>
 #include <arch/abi.h>
+#include <arch/spr_def.h>
 #include <arch/opcode.h>
 
-#define signExtend17(val) sign_extend((val), 17)
-#define TILE_X1_MASK (0xffffffffULL << 31)
-
-int unaligned_printk;
 
-static int __init setup_unaligned_printk(char *str)
-{
-	long val;
-	if (strict_strtol(str, 0, &val) != 0)
-		return 0;
-	unaligned_printk = val;
-	pr_info("Printk for each unaligned data accesses is %s\n",
-		unaligned_printk ? "enabled" : "disabled");
-	return 1;
-}
-__setup("unaligned_printk=", setup_unaligned_printk);
+#ifndef __tilegx__   /* Hardware support for single step unavailable. */
 
-unsigned int unaligned_fixup_count;
+#define signExtend17(val) sign_extend((val), 17)
+#define TILE_X1_MASK (0xffffffffULL << 31)
 
 enum mem_op {
 	MEMOP_NONE,
@@ -56,12 +45,13 @@ enum mem_op {
 	MEMOP_STORE_POSTINCR
 };
 
-static inline tile_bundle_bits set_BrOff_X1(tile_bundle_bits n, s32 offset)
+static inline tilepro_bundle_bits set_BrOff_X1(tilepro_bundle_bits n,
+	s32 offset)
 {
-	tile_bundle_bits result;
+	tilepro_bundle_bits result;
 
 	/* mask out the old offset */
-	tile_bundle_bits mask = create_BrOff_X1(-1);
+	tilepro_bundle_bits mask = create_BrOff_X1(-1);
 	result = n & (~mask);
 
 	/* or in the new offset */
@@ -70,10 +60,11 @@ static inline tile_bundle_bits set_BrOff_X1(tile_bundle_bits n, s32 offset)
 	return result;
 }
 
-static inline tile_bundle_bits move_X1(tile_bundle_bits n, int dest, int src)
+static inline tilepro_bundle_bits move_X1(tilepro_bundle_bits n, int dest,
+	int src)
 {
-	tile_bundle_bits result;
-	tile_bundle_bits op;
+	tilepro_bundle_bits result;
+	tilepro_bundle_bits op;
 
 	result = n & (~TILE_X1_MASK);
 
@@ -87,13 +78,13 @@ static inline tile_bundle_bits move_X1(tile_bundle_bits n, int dest, int src)
 	return result;
 }
 
-static inline tile_bundle_bits nop_X1(tile_bundle_bits n)
+static inline tilepro_bundle_bits nop_X1(tilepro_bundle_bits n)
 {
 	return move_X1(n, TREG_ZERO, TREG_ZERO);
 }
 
-static inline tile_bundle_bits addi_X1(
-	tile_bundle_bits n, int dest, int src, int imm)
+static inline tilepro_bundle_bits addi_X1(
+	tilepro_bundle_bits n, int dest, int src, int imm)
 {
 	n &= ~TILE_X1_MASK;
 
@@ -107,15 +98,26 @@ static inline tile_bundle_bits addi_X1(
 	return n;
 }
 
-static tile_bundle_bits rewrite_load_store_unaligned(
+static tilepro_bundle_bits rewrite_load_store_unaligned(
 	struct single_step_state *state,
-	tile_bundle_bits bundle,
+	tilepro_bundle_bits bundle,
 	struct pt_regs *regs,
 	enum mem_op mem_op,
 	int size, int sign_ext)
 {
 	unsigned char __user *addr;
 	int val_reg, addr_reg, err, val;
+	int align_ctl;
+
+	align_ctl = unaligned_fixup;
+	switch (task_thread_info(current)->align_ctl) {
+	case PR_UNALIGN_NOPRINT:
+		align_ctl = 1;
+		break;
+	case PR_UNALIGN_SIGBUS:
+		align_ctl = 0;
+		break;
+	}
 
 	/* Get address and value registers */
 	if (bundle & TILEPRO_BUNDLE_Y_ENCODING_MASK) {
@@ -160,7 +162,7 @@ static tile_bundle_bits rewrite_load_store_unaligned(
 	 * tilepro hardware would be doing, if it could provide us with the
 	 * actual bad address in an SPR, which it doesn't.
 	 */
-	if (unaligned_fixup == 0) {
+	if (align_ctl == 0) {
 		siginfo_t info = {
 			.si_signo = SIGBUS,
 			.si_code = BUS_ADRALN,
@@ -209,14 +211,14 @@ static tile_bundle_bits rewrite_load_store_unaligned(
 
 	if (err) {
 		siginfo_t info = {
-			.si_signo = SIGSEGV,
-			.si_code = SEGV_MAPERR,
+			.si_signo = SIGBUS,
+			.si_code = BUS_ADRALN,
 			.si_addr = addr
 		};
-		trace_unhandled_signal("segfault", regs,
-				       (unsigned long)addr, SIGSEGV);
+		trace_unhandled_signal("bad address for unaligned fixup", regs,
+				       (unsigned long)addr, SIGBUS);
 		force_sig_info(info.si_signo, &info, current);
-		return (tile_bundle_bits) 0;
+		return (tilepro_bundle_bits) 0;
 	}
 
 	if (unaligned_printk || unaligned_fixup_count == 0) {
@@ -285,7 +287,7 @@ void single_step_execve(void)
 	ti->step_state = NULL;
 }
 
-/**
+/*
  * single_step_once() - entry point when single stepping has been triggered.
  * @regs: The machine register state
  *
@@ -304,20 +306,31 @@ void single_step_execve(void)
  */
 void single_step_once(struct pt_regs *regs)
 {
-	extern tile_bundle_bits __single_step_ill_insn;
-	extern tile_bundle_bits __single_step_j_insn;
-	extern tile_bundle_bits __single_step_addli_insn;
-	extern tile_bundle_bits __single_step_auli_insn;
+	extern tilepro_bundle_bits __single_step_ill_insn;
+	extern tilepro_bundle_bits __single_step_j_insn;
+	extern tilepro_bundle_bits __single_step_addli_insn;
+	extern tilepro_bundle_bits __single_step_auli_insn;
 	struct thread_info *info = (void *)current_thread_info();
 	struct single_step_state *state = info->step_state;
 	int is_single_step = test_ti_thread_flag(info, TIF_SINGLESTEP);
-	tile_bundle_bits __user *buffer, *pc;
-	tile_bundle_bits bundle;
+	tilepro_bundle_bits __user *buffer, *pc;
+	tilepro_bundle_bits bundle;
 	int temp_reg;
 	int target_reg = TREG_LR;
 	int err;
 	enum mem_op mem_op = MEMOP_NONE;
 	int size = 0, sign_ext = 0;  /* happy compiler */
+	int align_ctl;
+
+	align_ctl = unaligned_fixup;
+	switch (task_thread_info(current)->align_ctl) {
+	case PR_UNALIGN_NOPRINT:
+		align_ctl = 1;
+		break;
+	case PR_UNALIGN_SIGBUS:
+		align_ctl = 0;
+		break;
+	}
 
 	asm(
 "    .pushsection .rodata.single_step\n"
@@ -390,7 +403,7 @@ void single_step_once(struct pt_regs *regs)
 	if (regs->faultnum == INT_SWINT_1)
 		regs->pc -= 8;
 
-	pc = (tile_bundle_bits __user *)(regs->pc);
+	pc = (tilepro_bundle_bits __user *)(regs->pc);
 	if (get_user(bundle, pc) != 0) {
 		pr_err("Couldn't read instruction at %p trying to step\n", pc);
 		return;
@@ -533,7 +546,6 @@ void single_step_once(struct pt_regs *regs)
 			}
 			break;
 
-#if CHIP_HAS_WH64()
 		/* postincrement operations */
 		case IMM_0_OPCODE_X1:
 			switch (get_ImmOpcodeExtension_X1(bundle)) {
@@ -568,7 +580,6 @@ void single_step_once(struct pt_regs *regs)
 				break;
 			}
 			break;
-#endif /* CHIP_HAS_WH64() */
 		}
 
 		if (state->update) {
@@ -627,9 +638,9 @@ void single_step_once(struct pt_regs *regs)
 
 	/*
 	 * Check if we need to rewrite an unaligned load/store.
-	 * Returning zero is a special value meaning we need to SIGSEGV.
+	 * Returning zero is a special value meaning we generated a signal.
 	 */
-	if (mem_op != MEMOP_NONE && unaligned_fixup >= 0) {
+	if (mem_op != MEMOP_NONE && align_ctl >= 0) {
 		bundle = rewrite_load_store_unaligned(state, bundle, regs,
 						      mem_op, size, sign_ext);
 		if (bundle == 0)
@@ -668,9 +679,9 @@ void single_step_once(struct pt_regs *regs)
 		}
 
 		/* End with a jump back to the next instruction */
-		delta = ((regs->pc + TILE_BUNDLE_SIZE_IN_BYTES) -
+		delta = ((regs->pc + TILEPRO_BUNDLE_SIZE_IN_BYTES) -
 			(unsigned long)buffer) >>
-			TILE_LOG2_BUNDLE_ALIGNMENT_IN_BYTES;
+			TILEPRO_LOG2_BUNDLE_ALIGNMENT_IN_BYTES;
 		bundle = __single_step_j_insn;
 		bundle |= create_JOffLong_X1(delta);
 		err |= __put_user(bundle, buffer++);
@@ -698,9 +709,6 @@ void single_step_once(struct pt_regs *regs)
 }
 
 #else
-#include <linux/smp.h>
-#include <linux/ptrace.h>
-#include <arch/spr_def.h>
 
 static DEFINE_PER_CPU(unsigned long, ss_saved_pc);
 
@@ -743,10 +751,10 @@ void gx_singlestep_handle(struct pt_regs *regs, int fault_num)
 	} else if ((*ss_pc != regs->pc) ||
 		   (!(control & SPR_SINGLE_STEP_CONTROL_1__CANCELED_MASK))) {
 
-		ptrace_notify(SIGTRAP);
 		control |= SPR_SINGLE_STEP_CONTROL_1__CANCELED_MASK;
 		control |= SPR_SINGLE_STEP_CONTROL_1__INHIBIT_MASK;
 		__insn_mtspr(SPR_SINGLE_STEP_CONTROL_K, control);
+		send_sigtrap(current, regs);
 	}
 }
 
diff --git a/arch/tile/kernel/smp.c b/arch/tile/kernel/smp.c
index cbc73a8b8fe1..01e8ab29f43a 100644
--- a/arch/tile/kernel/smp.c
+++ b/arch/tile/kernel/smp.c
@@ -20,8 +20,13 @@
 #include <linux/irq.h>
 #include <linux/module.h>
 #include <asm/cacheflush.h>
+#include <asm/homecache.h>
 
-HV_Topology smp_topology __write_once;
+/*
+ * We write to width and height with a single store in head_NN.S,
+ * so make the variable aligned to "long".
+ */
+HV_Topology smp_topology __write_once __aligned(sizeof(long));
 EXPORT_SYMBOL(smp_topology);
 
 #if CHIP_HAS_IPI()
@@ -100,8 +105,8 @@ static void smp_start_cpu_interrupt(void)
 /* Handler to stop the current cpu. */
 static void smp_stop_cpu_interrupt(void)
 {
-	set_cpu_online(smp_processor_id(), 0);
 	arch_local_irq_disable_all();
+	set_cpu_online(smp_processor_id(), 0);
 	for (;;)
 		asm("nap; nop");
 }
@@ -167,9 +172,16 @@ static void ipi_flush_icache_range(void *info)
 void flush_icache_range(unsigned long start, unsigned long end)
 {
 	struct ipi_flush flush = { start, end };
-	preempt_disable();
-	on_each_cpu(ipi_flush_icache_range, &flush, 1);
-	preempt_enable();
+
+	/* If invoked with irqs disabled, we can not issue IPIs. */
+	if (irqs_disabled())
+		flush_remote(0, HV_FLUSH_EVICT_L1I, NULL, 0, 0, 0,
+			NULL, NULL, 0);
+	else {
+		preempt_disable();
+		on_each_cpu(ipi_flush_icache_range, &flush, 1);
+		preempt_enable();
+	}
 }
 
 
diff --git a/arch/tile/kernel/smpboot.c b/arch/tile/kernel/smpboot.c
index a535655b7089..732e9d138661 100644
--- a/arch/tile/kernel/smpboot.c
+++ b/arch/tile/kernel/smpboot.c
@@ -142,13 +142,15 @@ static struct cpumask cpu_started;
  */
 static void start_secondary(void)
 {
-	int cpuid = smp_processor_id();
+	int cpuid;
+
+	preempt_disable();
+
+	cpuid = smp_processor_id();
 
 	/* Set our thread pointer appropriately. */
 	set_my_cpu_offset(__per_cpu_offset[cpuid]);
 
-	preempt_disable();
-
 	/*
 	 * In large machines even this will slow us down, since we
 	 * will be contending for for the printk spinlock.
diff --git a/arch/tile/kernel/stack.c b/arch/tile/kernel/stack.c
index af8dfc9665f6..c93977a62116 100644
--- a/arch/tile/kernel/stack.c
+++ b/arch/tile/kernel/stack.c
@@ -23,12 +23,14 @@
 #include <linux/mmzone.h>
 #include <linux/dcache.h>
 #include <linux/fs.h>
+#include <linux/string.h>
 #include <asm/backtrace.h>
 #include <asm/page.h>
 #include <asm/ucontext.h>
 #include <asm/switch_to.h>
 #include <asm/sigframe.h>
 #include <asm/stack.h>
+#include <asm/vdso.h>
 #include <arch/abi.h>
 #include <arch/interrupts.h>
 
@@ -102,9 +104,8 @@ static struct pt_regs *valid_fault_handler(struct KBacktraceIterator* kbt)
 	    p->sp >= sp) {
 		if (kbt->verbose)
 			pr_err("  <%s while in kernel mode>\n", fault);
-	} else if (EX1_PL(p->ex1) == USER_PL &&
-	    p->pc < PAGE_OFFSET &&
-	    p->sp < PAGE_OFFSET) {
+	} else if (user_mode(p) &&
+		   p->sp < PAGE_OFFSET && p->sp != 0) {
 		if (kbt->verbose)
 			pr_err("  <%s while in user mode>\n", fault);
 	} else if (kbt->verbose) {
@@ -120,7 +121,7 @@ static struct pt_regs *valid_fault_handler(struct KBacktraceIterator* kbt)
 /* Is the pc pointing to a sigreturn trampoline? */
 static int is_sigreturn(unsigned long pc)
 {
-	return (pc == VDSO_BASE);
+	return current->mm && (pc == VDSO_SYM(&__vdso_rt_sigreturn));
 }
 
 /* Return a pt_regs pointer for a valid signal handler frame */
@@ -129,7 +130,7 @@ static struct pt_regs *valid_sigframe(struct KBacktraceIterator* kbt,
 {
 	BacktraceIterator *b = &kbt->it;
 
-	if (b->pc == VDSO_BASE && b->sp < PAGE_OFFSET &&
+	if (is_sigreturn(b->pc) && b->sp < PAGE_OFFSET &&
 	    b->sp % sizeof(long) == 0) {
 		int retval;
 		pagefault_disable();
@@ -195,21 +196,21 @@ static int KBacktraceIterator_next_item_inclusive(
  */
 static void validate_stack(struct pt_regs *regs)
 {
-	int cpu = smp_processor_id();
+	int cpu = raw_smp_processor_id();
 	unsigned long ksp0 = get_current_ksp0();
-	unsigned long ksp0_base = ksp0 - THREAD_SIZE;
+	unsigned long ksp0_base = ksp0 & -THREAD_SIZE;
 	unsigned long sp = stack_pointer;
 
 	if (EX1_PL(regs->ex1) == KERNEL_PL && regs->sp >= ksp0) {
-		pr_err("WARNING: cpu %d: kernel stack page %#lx underrun!\n"
+		pr_err("WARNING: cpu %d: kernel stack %#lx..%#lx underrun!\n"
 		       "  sp %#lx (%#lx in caller), caller pc %#lx, lr %#lx\n",
-		       cpu, ksp0_base, sp, regs->sp, regs->pc, regs->lr);
+		       cpu, ksp0_base, ksp0, sp, regs->sp, regs->pc, regs->lr);
 	}
 
 	else if (sp < ksp0_base + sizeof(struct thread_info)) {
-		pr_err("WARNING: cpu %d: kernel stack page %#lx overrun!\n"
+		pr_err("WARNING: cpu %d: kernel stack %#lx..%#lx overrun!\n"
 		       "  sp %#lx (%#lx in caller), caller pc %#lx, lr %#lx\n",
-		       cpu, ksp0_base, sp, regs->sp, regs->pc, regs->lr);
+		       cpu, ksp0_base, ksp0, sp, regs->sp, regs->pc, regs->lr);
 	}
 }
 
@@ -332,26 +333,43 @@ static void describe_addr(struct KBacktraceIterator *kbt,
 	}
 
 	if (vma->vm_file) {
-		char *s;
 		p = d_path(&vma->vm_file->f_path, buf, bufsize);
 		if (IS_ERR(p))
 			p = "?";
-		s = strrchr(p, '/');
-		if (s)
-			p = s+1;
+		name = kbasename(p);
 	} else {
-		p = "anon";
+		name = "anon";
 	}
 
 	/* Generate a string description of the vma info. */
-	namelen = strlen(p);
+	namelen = strlen(name);
 	remaining = (bufsize - 1) - namelen;
-	memmove(buf, p, namelen);
+	memmove(buf, name, namelen);
 	snprintf(buf + namelen, remaining, "[%lx+%lx] ",
 		 vma->vm_start, vma->vm_end - vma->vm_start);
 }
 
 /*
+ * Avoid possible crash recursion during backtrace.  If it happens, it
+ * makes it easy to lose the actual root cause of the failure, so we
+ * put a simple guard on all the backtrace loops.
+ */
+static bool start_backtrace(void)
+{
+	if (current->thread.in_backtrace) {
+		pr_err("Backtrace requested while in backtrace!\n");
+		return false;
+	}
+	current->thread.in_backtrace = true;
+	return true;
+}
+
+static void end_backtrace(void)
+{
+	current->thread.in_backtrace = false;
+}
+
+/*
  * This method wraps the backtracer's more generic support.
  * It is only invoked from the architecture-specific code; show_stack()
  * and dump_stack() (in entry.S) are architecture-independent entry points.
@@ -361,6 +379,8 @@ void tile_show_stack(struct KBacktraceIterator *kbt, int headers)
 	int i;
 	int have_mmap_sem = 0;
 
+	if (!start_backtrace())
+		return;
 	if (headers) {
 		/*
 		 * Add a blank line since if we are called from panic(),
@@ -371,7 +391,7 @@ void tile_show_stack(struct KBacktraceIterator *kbt, int headers)
 		pr_err("Starting stack dump of tid %d, pid %d (%s)"
 		       " on cpu %d at cycle %lld\n",
 		       kbt->task->pid, kbt->task->tgid, kbt->task->comm,
-		       smp_processor_id(), get_cycles());
+		       raw_smp_processor_id(), get_cycles());
 	}
 	kbt->verbose = 1;
 	i = 0;
@@ -402,6 +422,7 @@ void tile_show_stack(struct KBacktraceIterator *kbt, int headers)
 		pr_err("Stack dump complete\n");
 	if (have_mmap_sem)
 		up_read(&kbt->task->mm->mmap_sem);
+	end_backtrace();
 }
 EXPORT_SYMBOL(tile_show_stack);
 
@@ -463,6 +484,8 @@ void save_stack_trace_tsk(struct task_struct *task, struct stack_trace *trace)
 	int skip = trace->skip;
 	int i = 0;
 
+	if (!start_backtrace())
+		goto done;
 	if (task == NULL || task == current)
 		KBacktraceIterator_init_current(&kbt);
 	else
@@ -476,6 +499,8 @@ void save_stack_trace_tsk(struct task_struct *task, struct stack_trace *trace)
 			break;
 		trace->entries[i++] = kbt.it.pc;
 	}
+	end_backtrace();
+done:
 	trace->nr_entries = i;
 }
 EXPORT_SYMBOL(save_stack_trace_tsk);
diff --git a/arch/tile/kernel/sys.c b/arch/tile/kernel/sys.c
index b881a7be24bd..38debe706061 100644
--- a/arch/tile/kernel/sys.c
+++ b/arch/tile/kernel/sys.c
@@ -38,8 +38,10 @@
 SYSCALL_DEFINE3(cacheflush, unsigned long, addr, unsigned long, len,
 		unsigned long, flags)
 {
+	/* DCACHE is not particularly effective if not bound to one cpu. */
 	if (flags & DCACHE)
-		homecache_evict(cpumask_of(smp_processor_id()));
+		homecache_evict(cpumask_of(raw_smp_processor_id()));
+
 	if (flags & ICACHE)
 		flush_remote(0, HV_FLUSH_EVICT_L1I, mm_cpumask(current->mm),
 			     0, 0, 0, NULL, NULL, 0);
diff --git a/arch/tile/kernel/sysfs.c b/arch/tile/kernel/sysfs.c
index e25b0a89c18f..a3ed12f8f83b 100644
--- a/arch/tile/kernel/sysfs.c
+++ b/arch/tile/kernel/sysfs.c
@@ -157,6 +157,67 @@ hvconfig_bin_read(struct file *filp, struct kobject *kobj,
 	return count;
 }
 
+static ssize_t hv_stats_show(struct device *dev,
+			     struct device_attribute *attr,
+			     char *page)
+{
+	int cpu = dev->id;
+	long lotar = HV_XY_TO_LOTAR(cpu_x(cpu), cpu_y(cpu));
+
+	ssize_t n = hv_confstr(HV_CONFSTR_HV_STATS,
+			       (unsigned long)page, PAGE_SIZE - 1,
+			       lotar, 0);
+	n = n < 0 ? 0 : min(n, (ssize_t)PAGE_SIZE - 1);
+	page[n] = '\0';
+	return n;
+}
+
+static ssize_t hv_stats_store(struct device *dev,
+			      struct device_attribute *attr,
+			      const char *page,
+			      size_t count)
+{
+	int cpu = dev->id;
+	long lotar = HV_XY_TO_LOTAR(cpu_x(cpu), cpu_y(cpu));
+
+	ssize_t n = hv_confstr(HV_CONFSTR_HV_STATS, 0, 0, lotar, 1);
+	return n < 0 ? n : count;
+}
+
+static DEVICE_ATTR(hv_stats, 0644, hv_stats_show, hv_stats_store);
+
+static int hv_stats_device_add(struct device *dev, struct subsys_interface *sif)
+{
+	int err, cpu = dev->id;
+
+	if (!cpu_online(cpu))
+		return 0;
+
+	err = sysfs_create_file(&dev->kobj, &dev_attr_hv_stats.attr);
+
+	return err;
+}
+
+static int hv_stats_device_remove(struct device *dev,
+				  struct subsys_interface *sif)
+{
+	int cpu = dev->id;
+
+	if (!cpu_online(cpu))
+		return 0;
+
+	sysfs_remove_file(&dev->kobj, &dev_attr_hv_stats.attr);
+	return 0;
+}
+
+
+static struct subsys_interface hv_stats_interface = {
+	.name			= "hv_stats",
+	.subsys			= &cpu_subsys,
+	.add_dev		= hv_stats_device_add,
+	.remove_dev		= hv_stats_device_remove,
+};
+
 static int __init create_sysfs_entries(void)
 {
 	int err = 0;
@@ -188,6 +249,21 @@ static int __init create_sysfs_entries(void)
 		err = sysfs_create_bin_file(hypervisor_kobj, &hvconfig_bin);
 	}
 
+	if (!err) {
+		/*
+		 * Don't bother adding the hv_stats files on each CPU if
+		 * our hypervisor doesn't supply statistics.
+		 */
+		int cpu = raw_smp_processor_id();
+		long lotar = HV_XY_TO_LOTAR(cpu_x(cpu), cpu_y(cpu));
+		char dummy;
+		ssize_t n = hv_confstr(HV_CONFSTR_HV_STATS,
+				       (unsigned long) &dummy, 1,
+				       lotar, 0);
+		if (n >= 0)
+			err = subsys_interface_register(&hv_stats_interface);
+	}
+
 	return err;
 }
 subsys_initcall(create_sysfs_entries);
diff --git a/arch/tile/kernel/time.c b/arch/tile/kernel/time.c
index 7c353d8c2da9..5d10642db63e 100644
--- a/arch/tile/kernel/time.c
+++ b/arch/tile/kernel/time.c
@@ -23,8 +23,10 @@
 #include <linux/smp.h>
 #include <linux/delay.h>
 #include <linux/module.h>
+#include <linux/timekeeper_internal.h>
 #include <asm/irq_regs.h>
 #include <asm/traps.h>
+#include <asm/vdso.h>
 #include <hv/hypervisor.h>
 #include <arch/interrupts.h>
 #include <arch/spr_def.h>
@@ -110,7 +112,6 @@ void __init time_init(void)
 	setup_tile_timer();
 }
 
-
 /*
  * Define the tile timer clock event device.  The timer is driven by
  * the TILE_TIMER_CONTROL register, which consists of a 31-bit down
@@ -237,3 +238,37 @@ cycles_t ns2cycles(unsigned long nsecs)
 	struct clock_event_device *dev = &__raw_get_cpu_var(tile_timer);
 	return ((u64)nsecs * dev->mult) >> dev->shift;
 }
+
+void update_vsyscall_tz(void)
+{
+	/* Userspace gettimeofday will spin while this value is odd. */
+	++vdso_data->tz_update_count;
+	smp_wmb();
+	vdso_data->tz_minuteswest = sys_tz.tz_minuteswest;
+	vdso_data->tz_dsttime = sys_tz.tz_dsttime;
+	smp_wmb();
+	++vdso_data->tz_update_count;
+}
+
+void update_vsyscall(struct timekeeper *tk)
+{
+	struct timespec wall_time = tk_xtime(tk);
+	struct timespec *wtm = &tk->wall_to_monotonic;
+	struct clocksource *clock = tk->clock;
+
+	if (clock != &cycle_counter_cs)
+		return;
+
+	/* Userspace gettimeofday will spin while this value is odd. */
+	++vdso_data->tb_update_count;
+	smp_wmb();
+	vdso_data->xtime_tod_stamp = clock->cycle_last;
+	vdso_data->xtime_clock_sec = wall_time.tv_sec;
+	vdso_data->xtime_clock_nsec = wall_time.tv_nsec;
+	vdso_data->wtom_clock_sec = wtm->tv_sec;
+	vdso_data->wtom_clock_nsec = wtm->tv_nsec;
+	vdso_data->mult = clock->mult;
+	vdso_data->shift = clock->shift;
+	smp_wmb();
+	++vdso_data->tb_update_count;
+}
diff --git a/arch/tile/kernel/tlb.c b/arch/tile/kernel/tlb.c
index 3fd54d5bbd4c..f23b53515671 100644
--- a/arch/tile/kernel/tlb.c
+++ b/arch/tile/kernel/tlb.c
@@ -91,8 +91,14 @@ void flush_tlb_all(void)
 	}
 }
 
+/*
+ * Callers need to flush the L1I themselves if necessary, e.g. for
+ * kernel module unload.  Otherwise we assume callers are not using
+ * executable pgprot_t's.  Using EVICT_L1I means that dataplane cpus
+ * will get an unnecessary interrupt otherwise.
+ */
 void flush_tlb_kernel_range(unsigned long start, unsigned long end)
 {
-	flush_remote(0, HV_FLUSH_EVICT_L1I, cpu_online_mask,
+	flush_remote(0, 0, NULL,
 		     start, end - start, PAGE_SIZE, cpu_online_mask, NULL, 0);
 }
diff --git a/arch/tile/kernel/traps.c b/arch/tile/kernel/traps.c
index 5b19a23c8908..6b603d556ca6 100644
--- a/arch/tile/kernel/traps.c
+++ b/arch/tile/kernel/traps.c
@@ -15,6 +15,7 @@
 #include <linux/sched.h>
 #include <linux/kernel.h>
 #include <linux/kprobes.h>
+#include <linux/kdebug.h>
 #include <linux/module.h>
 #include <linux/reboot.h>
 #include <linux/uaccess.h>
@@ -29,7 +30,7 @@
 
 void __init trap_init(void)
 {
-	/* Nothing needed here since we link code at .intrpt1 */
+	/* Nothing needed here since we link code at .intrpt */
 }
 
 int unaligned_fixup = 1;
@@ -100,13 +101,7 @@ static int retry_gpv(unsigned int gpv_reason)
 
 #endif /* CHIP_HAS_TILE_DMA() */
 
-#ifdef __tilegx__
-#define bundle_bits tilegx_bundle_bits
-#else
-#define bundle_bits tile_bundle_bits
-#endif
-
-extern bundle_bits bpt_code;
+extern tile_bundle_bits bpt_code;
 
 asm(".pushsection .rodata.bpt_code,\"a\";"
     ".align 8;"
@@ -114,7 +109,7 @@ asm(".pushsection .rodata.bpt_code,\"a\";"
     ".size bpt_code,.-bpt_code;"
     ".popsection");
 
-static int special_ill(bundle_bits bundle, int *sigp, int *codep)
+static int special_ill(tile_bundle_bits bundle, int *sigp, int *codep)
 {
 	int sig, code, maxcode;
 
@@ -214,24 +209,73 @@ static const char *const int_name[] = {
 #endif
 };
 
+static int do_bpt(struct pt_regs *regs)
+{
+	unsigned long bundle, bcode, bpt;
+
+	bundle = *(unsigned long *)instruction_pointer(regs);
+
+	/*
+	 * bpt shoule be { bpt; nop }, which is 0x286a44ae51485000ULL.
+	 * we encode the unused least significant bits for other purpose.
+	 */
+	bpt = bundle & ~((1ULL << 12) - 1);
+	if (bpt != TILE_BPT_BUNDLE)
+		return 0;
+
+	bcode = bundle & ((1ULL << 12) - 1);
+	/*
+	 * notify the kprobe handlers, if instruction is likely to
+	 * pertain to them.
+	 */
+	switch (bcode) {
+	/* breakpoint_insn */
+	case 0:
+		notify_die(DIE_BREAK, "debug", regs, bundle,
+			INT_ILL, SIGTRAP);
+		break;
+	/* compiled_bpt */
+	case DIE_COMPILED_BPT:
+		notify_die(DIE_COMPILED_BPT, "debug", regs, bundle,
+			INT_ILL, SIGTRAP);
+		break;
+	/* breakpoint2_insn */
+	case DIE_SSTEPBP:
+		notify_die(DIE_SSTEPBP, "single_step", regs, bundle,
+			INT_ILL, SIGTRAP);
+		break;
+	default:
+		return 0;
+	}
+
+	return 1;
+}
+
 void __kprobes do_trap(struct pt_regs *regs, int fault_num,
 		       unsigned long reason)
 {
 	siginfo_t info = { 0 };
 	int signo, code;
 	unsigned long address = 0;
-	bundle_bits instr;
+	tile_bundle_bits instr;
+	int is_kernel = !user_mode(regs);
+
+	/* Handle breakpoints, etc. */
+	if (is_kernel && fault_num == INT_ILL && do_bpt(regs))
+		return;
 
-	/* Re-enable interrupts. */
-	local_irq_enable();
+	/* Re-enable interrupts, if they were previously enabled. */
+	if (!(regs->flags & PT_FLAGS_DISABLE_IRQ))
+		local_irq_enable();
 
 	/*
 	 * If it hits in kernel mode and we can't fix it up, just exit the
 	 * current process and hope for the best.
 	 */
-	if (!user_mode(regs)) {
+	if (is_kernel) {
 		const char *name;
-		if (fixup_exception(regs))  /* only UNALIGN_DATA in practice */
+		char buf[100];
+		if (fixup_exception(regs))  /* ILL_TRANS or UNALIGN_DATA */
 			return;
 		if (fault_num >= 0 &&
 		    fault_num < sizeof(int_name)/sizeof(int_name[0]) &&
@@ -239,10 +283,16 @@ void __kprobes do_trap(struct pt_regs *regs, int fault_num,
 			name = int_name[fault_num];
 		else
 			name = "Unknown interrupt";
-		pr_alert("Kernel took bad trap %d (%s) at PC %#lx\n",
-			 fault_num, name, regs->pc);
 		if (fault_num == INT_GPV)
-			pr_alert("GPV_REASON is %#lx\n", reason);
+			snprintf(buf, sizeof(buf), "; GPV_REASON %#lx", reason);
+#ifdef __tilegx__
+		else if (fault_num == INT_ILL_TRANS)
+			snprintf(buf, sizeof(buf), "; address %#lx", reason);
+#endif
+		else
+			buf[0] = '\0';
+		pr_alert("Kernel took bad trap %d (%s) at PC %#lx%s\n",
+			 fault_num, name, regs->pc, buf);
 		show_regs(regs);
 		do_exit(SIGKILL);  /* FIXME: implement i386 die() */
 		return;
@@ -324,11 +374,8 @@ void __kprobes do_trap(struct pt_regs *regs, int fault_num,
 		fill_ra_stack();
 
 		signo = SIGSEGV;
+		address = reason;
 		code = SEGV_MAPERR;
-		if (reason & SPR_ILL_TRANS_REASON__I_STREAM_VA_RMASK)
-			address = regs->pc;
-		else
-			address = 0;  /* FIXME: GX: single-step for address */
 		break;
 	}
 #endif
diff --git a/arch/tile/kernel/unaligned.c b/arch/tile/kernel/unaligned.c
new file mode 100644
index 000000000000..b030b4e78845
--- /dev/null
+++ b/arch/tile/kernel/unaligned.c
@@ -0,0 +1,1609 @@
+/*
+ * Copyright 2013 Tilera Corporation. All Rights Reserved.
+ *
+ *   This program is free software; you can redistribute it and/or
+ *   modify it under the terms of the GNU General Public License
+ *   as published by the Free Software Foundation, version 2.
+ *
+ *   This program is distributed in the hope that it will be useful, but
+ *   WITHOUT ANY WARRANTY; without even the implied warranty of
+ *   MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ *   NON INFRINGEMENT.  See the GNU General Public License for
+ *   more details.
+ *
+ * A code-rewriter that handles unaligned exception.
+ */
+
+#include <linux/smp.h>
+#include <linux/ptrace.h>
+#include <linux/slab.h>
+#include <linux/thread_info.h>
+#include <linux/uaccess.h>
+#include <linux/mman.h>
+#include <linux/types.h>
+#include <linux/err.h>
+#include <linux/module.h>
+#include <linux/compat.h>
+#include <linux/prctl.h>
+#include <asm/cacheflush.h>
+#include <asm/traps.h>
+#include <asm/uaccess.h>
+#include <asm/unaligned.h>
+#include <arch/abi.h>
+#include <arch/spr_def.h>
+#include <arch/opcode.h>
+
+
+/*
+ * This file handles unaligned exception for tile-Gx. The tilepro's unaligned
+ * exception is supported out of single_step.c
+ */
+
+int unaligned_printk;
+
+static int __init setup_unaligned_printk(char *str)
+{
+	long val;
+	if (kstrtol(str, 0, &val) != 0)
+		return 0;
+	unaligned_printk = val;
+	pr_info("Printk for each unaligned data accesses is %s\n",
+		unaligned_printk ? "enabled" : "disabled");
+	return 1;
+}
+__setup("unaligned_printk=", setup_unaligned_printk);
+
+unsigned int unaligned_fixup_count;
+
+#ifdef __tilegx__
+
+/*
+ * Unalign data jit fixup code fragement. Reserved space is 128 bytes.
+ * The 1st 64-bit word saves fault PC address, 2nd word is the fault
+ * instruction bundle followed by 14 JIT bundles.
+ */
+
+struct unaligned_jit_fragment {
+	unsigned long       pc;
+	tilegx_bundle_bits  bundle;
+	tilegx_bundle_bits  insn[14];
+};
+
+/*
+ * Check if a nop or fnop at bundle's pipeline X0.
+ */
+
+static bool is_bundle_x0_nop(tilegx_bundle_bits bundle)
+{
+	return (((get_UnaryOpcodeExtension_X0(bundle) ==
+		  NOP_UNARY_OPCODE_X0) &&
+		 (get_RRROpcodeExtension_X0(bundle) ==
+		  UNARY_RRR_0_OPCODE_X0) &&
+		 (get_Opcode_X0(bundle) ==
+		  RRR_0_OPCODE_X0)) ||
+		((get_UnaryOpcodeExtension_X0(bundle) ==
+		  FNOP_UNARY_OPCODE_X0) &&
+		 (get_RRROpcodeExtension_X0(bundle) ==
+		  UNARY_RRR_0_OPCODE_X0) &&
+		 (get_Opcode_X0(bundle) ==
+		  RRR_0_OPCODE_X0)));
+}
+
+/*
+ * Check if nop or fnop at bundle's pipeline X1.
+ */
+
+static bool is_bundle_x1_nop(tilegx_bundle_bits bundle)
+{
+	return (((get_UnaryOpcodeExtension_X1(bundle) ==
+		  NOP_UNARY_OPCODE_X1) &&
+		 (get_RRROpcodeExtension_X1(bundle) ==
+		  UNARY_RRR_0_OPCODE_X1) &&
+		 (get_Opcode_X1(bundle) ==
+		  RRR_0_OPCODE_X1)) ||
+		((get_UnaryOpcodeExtension_X1(bundle) ==
+		  FNOP_UNARY_OPCODE_X1) &&
+		 (get_RRROpcodeExtension_X1(bundle) ==
+		  UNARY_RRR_0_OPCODE_X1) &&
+		 (get_Opcode_X1(bundle) ==
+		  RRR_0_OPCODE_X1)));
+}
+
+/*
+ * Check if nop or fnop at bundle's Y0 pipeline.
+ */
+
+static bool is_bundle_y0_nop(tilegx_bundle_bits bundle)
+{
+	return (((get_UnaryOpcodeExtension_Y0(bundle) ==
+		  NOP_UNARY_OPCODE_Y0) &&
+		 (get_RRROpcodeExtension_Y0(bundle) ==
+		  UNARY_RRR_1_OPCODE_Y0) &&
+		 (get_Opcode_Y0(bundle) ==
+		  RRR_1_OPCODE_Y0)) ||
+		((get_UnaryOpcodeExtension_Y0(bundle) ==
+		  FNOP_UNARY_OPCODE_Y0) &&
+		 (get_RRROpcodeExtension_Y0(bundle) ==
+		  UNARY_RRR_1_OPCODE_Y0) &&
+		 (get_Opcode_Y0(bundle) ==
+		  RRR_1_OPCODE_Y0)));
+}
+
+/*
+ * Check if nop or fnop at bundle's pipeline Y1.
+ */
+
+static bool is_bundle_y1_nop(tilegx_bundle_bits bundle)
+{
+	return (((get_UnaryOpcodeExtension_Y1(bundle) ==
+		  NOP_UNARY_OPCODE_Y1) &&
+		 (get_RRROpcodeExtension_Y1(bundle) ==
+		  UNARY_RRR_1_OPCODE_Y1) &&
+		 (get_Opcode_Y1(bundle) ==
+		  RRR_1_OPCODE_Y1)) ||
+		((get_UnaryOpcodeExtension_Y1(bundle) ==
+		  FNOP_UNARY_OPCODE_Y1) &&
+		 (get_RRROpcodeExtension_Y1(bundle) ==
+		  UNARY_RRR_1_OPCODE_Y1) &&
+		 (get_Opcode_Y1(bundle) ==
+		  RRR_1_OPCODE_Y1)));
+}
+
+/*
+ * Test if a bundle's y0 and y1 pipelines are both nop or fnop.
+ */
+
+static bool is_y0_y1_nop(tilegx_bundle_bits bundle)
+{
+	return is_bundle_y0_nop(bundle) && is_bundle_y1_nop(bundle);
+}
+
+/*
+ * Test if a bundle's x0 and x1 pipelines are both nop or fnop.
+ */
+
+static bool is_x0_x1_nop(tilegx_bundle_bits bundle)
+{
+	return is_bundle_x0_nop(bundle) && is_bundle_x1_nop(bundle);
+}
+
+/*
+ * Find the destination, source registers of fault unalign access instruction
+ * at X1 or Y2. Also, allocate up to 3 scratch registers clob1, clob2 and
+ * clob3, which are guaranteed different from any register used in the fault
+ * bundle. r_alias is used to return if the other instructions other than the
+ * unalign load/store shares same register with ra, rb and rd.
+ */
+
+static void find_regs(tilegx_bundle_bits bundle, uint64_t *rd, uint64_t *ra,
+		      uint64_t *rb, uint64_t *clob1, uint64_t *clob2,
+		      uint64_t *clob3, bool *r_alias)
+{
+	int i;
+	uint64_t reg;
+	uint64_t reg_map = 0, alias_reg_map = 0, map;
+	bool alias;
+
+	*ra = -1;
+	*rb = -1;
+
+	if (rd)
+		*rd = -1;
+
+	*clob1 = -1;
+	*clob2 = -1;
+	*clob3 = -1;
+	alias = false;
+
+	/*
+	 * Parse fault bundle, find potential used registers and mark
+	 * corresponding bits in reg_map and alias_map. These 2 bit maps
+	 * are used to find the scratch registers and determine if there
+	 * is register alais.
+	 */
+	if (bundle & TILEGX_BUNDLE_MODE_MASK) {  /* Y Mode Bundle. */
+
+		reg = get_SrcA_Y2(bundle);
+		reg_map |= 1ULL << reg;
+		*ra = reg;
+		reg = get_SrcBDest_Y2(bundle);
+		reg_map |= 1ULL << reg;
+
+		if (rd) {
+			/* Load. */
+			*rd = reg;
+			alias_reg_map = (1ULL << *rd) | (1ULL << *ra);
+		} else {
+			/* Store. */
+			*rb = reg;
+			alias_reg_map = (1ULL << *ra) | (1ULL << *rb);
+		}
+
+		if (!is_bundle_y1_nop(bundle)) {
+			reg = get_SrcA_Y1(bundle);
+			reg_map |= (1ULL << reg);
+			map = (1ULL << reg);
+
+			reg = get_SrcB_Y1(bundle);
+			reg_map |= (1ULL << reg);
+			map |= (1ULL << reg);
+
+			reg = get_Dest_Y1(bundle);
+			reg_map |= (1ULL << reg);
+			map |= (1ULL << reg);
+
+			if (map & alias_reg_map)
+				alias = true;
+		}
+
+		if (!is_bundle_y0_nop(bundle)) {
+			reg = get_SrcA_Y0(bundle);
+			reg_map |= (1ULL << reg);
+			map = (1ULL << reg);
+
+			reg = get_SrcB_Y0(bundle);
+			reg_map |= (1ULL << reg);
+			map |= (1ULL << reg);
+
+			reg = get_Dest_Y0(bundle);
+			reg_map |= (1ULL << reg);
+			map |= (1ULL << reg);
+
+			if (map & alias_reg_map)
+				alias = true;
+		}
+	} else	{ /* X Mode Bundle. */
+
+		reg = get_SrcA_X1(bundle);
+		reg_map |= (1ULL << reg);
+		*ra = reg;
+		if (rd)	{
+			/* Load. */
+			reg = get_Dest_X1(bundle);
+			reg_map |= (1ULL << reg);
+			*rd = reg;
+			alias_reg_map = (1ULL << *rd) | (1ULL << *ra);
+		} else {
+			/* Store. */
+			reg = get_SrcB_X1(bundle);
+			reg_map |= (1ULL << reg);
+			*rb = reg;
+			alias_reg_map = (1ULL << *ra) | (1ULL << *rb);
+		}
+
+		if (!is_bundle_x0_nop(bundle)) {
+			reg = get_SrcA_X0(bundle);
+			reg_map |= (1ULL << reg);
+			map = (1ULL << reg);
+
+			reg = get_SrcB_X0(bundle);
+			reg_map |= (1ULL << reg);
+			map |= (1ULL << reg);
+
+			reg = get_Dest_X0(bundle);
+			reg_map |= (1ULL << reg);
+			map |= (1ULL << reg);
+
+			if (map & alias_reg_map)
+				alias = true;
+		}
+	}
+
+	/*
+	 * "alias" indicates if the unalign access registers have collision
+	 * with others in the same bundle. We jsut simply test all register
+	 * operands case (RRR), ignored the case with immidate. If a bundle
+	 * has no register alias, we may do fixup in a simple or fast manner.
+	 * So if an immidata field happens to hit with a register, we may end
+	 * up fall back to the generic handling.
+	 */
+
+	*r_alias = alias;
+
+	/* Flip bits on reg_map. */
+	reg_map ^= -1ULL;
+
+	/* Scan reg_map lower 54(TREG_SP) bits to find 3 set bits. */
+	for (i = 0; i < TREG_SP; i++) {
+		if (reg_map & (0x1ULL << i)) {
+			if (*clob1 == -1) {
+				*clob1 = i;
+			} else if (*clob2 == -1) {
+				*clob2 = i;
+			} else if (*clob3 == -1) {
+				*clob3 = i;
+				return;
+			}
+		}
+	}
+}
+
+/*
+ * Sanity check for register ra, rb, rd, clob1/2/3. Return true if any of them
+ * is unexpected.
+ */
+
+static bool check_regs(uint64_t rd, uint64_t ra, uint64_t rb,
+		       uint64_t clob1, uint64_t clob2,  uint64_t clob3)
+{
+	bool unexpected = false;
+	if ((ra >= 56) && (ra != TREG_ZERO))
+		unexpected = true;
+
+	if ((clob1 >= 56) || (clob2 >= 56) || (clob3 >= 56))
+		unexpected = true;
+
+	if (rd != -1) {
+		if ((rd >= 56) && (rd != TREG_ZERO))
+			unexpected = true;
+	} else {
+		if ((rb >= 56) && (rb != TREG_ZERO))
+			unexpected = true;
+	}
+	return unexpected;
+}
+
+
+#define  GX_INSN_X0_MASK   ((1ULL << 31) - 1)
+#define  GX_INSN_X1_MASK   (((1ULL << 31) - 1) << 31)
+#define  GX_INSN_Y0_MASK   ((0xFULL << 27) | (0xFFFFFULL))
+#define  GX_INSN_Y1_MASK   (GX_INSN_Y0_MASK << 31)
+#define  GX_INSN_Y2_MASK   ((0x7FULL << 51) | (0x7FULL << 20))
+
+#ifdef __LITTLE_ENDIAN
+#define  GX_INSN_BSWAP(_bundle_)    (_bundle_)
+#else
+#define  GX_INSN_BSWAP(_bundle_)    swab64(_bundle_)
+#endif /* __LITTLE_ENDIAN */
+
+/*
+ * __JIT_CODE(.) creates template bundles in .rodata.unalign_data section.
+ * The corresponding static function jix_x#_###(.) generates partial or
+ * whole bundle based on the template and given arguments.
+ */
+
+#define __JIT_CODE(_X_)						\
+	asm (".pushsection .rodata.unalign_data, \"a\"\n"	\
+	     _X_"\n"						\
+	     ".popsection\n")
+
+__JIT_CODE("__unalign_jit_x1_mtspr:   {mtspr 0,  r0}");
+static tilegx_bundle_bits jit_x1_mtspr(int spr, int reg)
+{
+	extern  tilegx_bundle_bits __unalign_jit_x1_mtspr;
+	return (GX_INSN_BSWAP(__unalign_jit_x1_mtspr) & GX_INSN_X1_MASK) |
+		create_MT_Imm14_X1(spr) | create_SrcA_X1(reg);
+}
+
+__JIT_CODE("__unalign_jit_x1_mfspr:   {mfspr r0, 0}");
+static tilegx_bundle_bits  jit_x1_mfspr(int reg, int spr)
+{
+	extern  tilegx_bundle_bits __unalign_jit_x1_mfspr;
+	return (GX_INSN_BSWAP(__unalign_jit_x1_mfspr) & GX_INSN_X1_MASK) |
+		create_MF_Imm14_X1(spr) | create_Dest_X1(reg);
+}
+
+__JIT_CODE("__unalign_jit_x0_addi:   {addi  r0, r0, 0; iret}");
+static tilegx_bundle_bits  jit_x0_addi(int rd, int ra, int imm8)
+{
+	extern  tilegx_bundle_bits __unalign_jit_x0_addi;
+	return (GX_INSN_BSWAP(__unalign_jit_x0_addi) & GX_INSN_X0_MASK) |
+		create_Dest_X0(rd) | create_SrcA_X0(ra) |
+		create_Imm8_X0(imm8);
+}
+
+__JIT_CODE("__unalign_jit_x1_ldna:   {ldna  r0, r0}");
+static tilegx_bundle_bits  jit_x1_ldna(int rd, int ra)
+{
+	extern  tilegx_bundle_bits __unalign_jit_x1_ldna;
+	return (GX_INSN_BSWAP(__unalign_jit_x1_ldna) &  GX_INSN_X1_MASK) |
+		create_Dest_X1(rd) | create_SrcA_X1(ra);
+}
+
+__JIT_CODE("__unalign_jit_x0_dblalign:   {dblalign r0, r0 ,r0}");
+static tilegx_bundle_bits  jit_x0_dblalign(int rd, int ra, int rb)
+{
+	extern  tilegx_bundle_bits __unalign_jit_x0_dblalign;
+	return (GX_INSN_BSWAP(__unalign_jit_x0_dblalign) & GX_INSN_X0_MASK) |
+		create_Dest_X0(rd) | create_SrcA_X0(ra) |
+		create_SrcB_X0(rb);
+}
+
+__JIT_CODE("__unalign_jit_x1_iret:   {iret}");
+static tilegx_bundle_bits  jit_x1_iret(void)
+{
+	extern  tilegx_bundle_bits __unalign_jit_x1_iret;
+	return GX_INSN_BSWAP(__unalign_jit_x1_iret) & GX_INSN_X1_MASK;
+}
+
+__JIT_CODE("__unalign_jit_x01_fnop:   {fnop;fnop}");
+static tilegx_bundle_bits  jit_x0_fnop(void)
+{
+	extern  tilegx_bundle_bits __unalign_jit_x01_fnop;
+	return GX_INSN_BSWAP(__unalign_jit_x01_fnop) & GX_INSN_X0_MASK;
+}
+
+static tilegx_bundle_bits  jit_x1_fnop(void)
+{
+	extern  tilegx_bundle_bits __unalign_jit_x01_fnop;
+	return GX_INSN_BSWAP(__unalign_jit_x01_fnop) & GX_INSN_X1_MASK;
+}
+
+__JIT_CODE("__unalign_jit_y2_dummy:   {fnop; fnop; ld zero, sp}");
+static tilegx_bundle_bits  jit_y2_dummy(void)
+{
+	extern  tilegx_bundle_bits __unalign_jit_y2_dummy;
+	return GX_INSN_BSWAP(__unalign_jit_y2_dummy) & GX_INSN_Y2_MASK;
+}
+
+static tilegx_bundle_bits  jit_y1_fnop(void)
+{
+	extern  tilegx_bundle_bits __unalign_jit_y2_dummy;
+	return GX_INSN_BSWAP(__unalign_jit_y2_dummy) & GX_INSN_Y1_MASK;
+}
+
+__JIT_CODE("__unalign_jit_x1_st1_add:  {st1_add r1, r0, 0}");
+static tilegx_bundle_bits  jit_x1_st1_add(int ra, int rb, int imm8)
+{
+	extern  tilegx_bundle_bits __unalign_jit_x1_st1_add;
+	return (GX_INSN_BSWAP(__unalign_jit_x1_st1_add) &
+		(~create_SrcA_X1(-1)) &
+		GX_INSN_X1_MASK) | create_SrcA_X1(ra) |
+		create_SrcB_X1(rb) | create_Dest_Imm8_X1(imm8);
+}
+
+__JIT_CODE("__unalign_jit_x1_st:  {crc32_8 r1, r0, r0; st  r0, r0}");
+static tilegx_bundle_bits  jit_x1_st(int ra, int rb)
+{
+	extern  tilegx_bundle_bits __unalign_jit_x1_st;
+	return (GX_INSN_BSWAP(__unalign_jit_x1_st) & GX_INSN_X1_MASK) |
+		create_SrcA_X1(ra) | create_SrcB_X1(rb);
+}
+
+__JIT_CODE("__unalign_jit_x1_st_add:  {st_add  r1, r0, 0}");
+static tilegx_bundle_bits  jit_x1_st_add(int ra, int rb, int imm8)
+{
+	extern  tilegx_bundle_bits __unalign_jit_x1_st_add;
+	return (GX_INSN_BSWAP(__unalign_jit_x1_st_add) &
+		(~create_SrcA_X1(-1)) &
+		GX_INSN_X1_MASK) | create_SrcA_X1(ra) |
+		create_SrcB_X1(rb) | create_Dest_Imm8_X1(imm8);
+}
+
+__JIT_CODE("__unalign_jit_x1_ld:  {crc32_8 r1, r0, r0; ld  r0, r0}");
+static tilegx_bundle_bits  jit_x1_ld(int rd, int ra)
+{
+	extern  tilegx_bundle_bits __unalign_jit_x1_ld;
+	return (GX_INSN_BSWAP(__unalign_jit_x1_ld) & GX_INSN_X1_MASK) |
+		create_Dest_X1(rd) | create_SrcA_X1(ra);
+}
+
+__JIT_CODE("__unalign_jit_x1_ld_add:  {ld_add  r1, r0, 0}");
+static tilegx_bundle_bits  jit_x1_ld_add(int rd, int ra, int imm8)
+{
+	extern  tilegx_bundle_bits __unalign_jit_x1_ld_add;
+	return (GX_INSN_BSWAP(__unalign_jit_x1_ld_add) &
+		(~create_Dest_X1(-1)) &
+		GX_INSN_X1_MASK) | create_Dest_X1(rd) |
+		create_SrcA_X1(ra) | create_Imm8_X1(imm8);
+}
+
+__JIT_CODE("__unalign_jit_x0_bfexts:  {bfexts r0, r0, 0, 0}");
+static tilegx_bundle_bits  jit_x0_bfexts(int rd, int ra, int bfs, int bfe)
+{
+	extern  tilegx_bundle_bits __unalign_jit_x0_bfexts;
+	return (GX_INSN_BSWAP(__unalign_jit_x0_bfexts) &
+		GX_INSN_X0_MASK) |
+		create_Dest_X0(rd) | create_SrcA_X0(ra) |
+		create_BFStart_X0(bfs) | create_BFEnd_X0(bfe);
+}
+
+__JIT_CODE("__unalign_jit_x0_bfextu:  {bfextu r0, r0, 0, 0}");
+static tilegx_bundle_bits  jit_x0_bfextu(int rd, int ra, int bfs, int bfe)
+{
+	extern  tilegx_bundle_bits __unalign_jit_x0_bfextu;
+	return (GX_INSN_BSWAP(__unalign_jit_x0_bfextu) &
+		GX_INSN_X0_MASK) |
+		create_Dest_X0(rd) | create_SrcA_X0(ra) |
+		create_BFStart_X0(bfs) | create_BFEnd_X0(bfe);
+}
+
+__JIT_CODE("__unalign_jit_x1_addi:  {bfextu r1, r1, 0, 0; addi r0, r0, 0}");
+static tilegx_bundle_bits  jit_x1_addi(int rd, int ra, int imm8)
+{
+	extern  tilegx_bundle_bits __unalign_jit_x1_addi;
+	return (GX_INSN_BSWAP(__unalign_jit_x1_addi) & GX_INSN_X1_MASK) |
+		create_Dest_X1(rd) | create_SrcA_X1(ra) |
+		create_Imm8_X1(imm8);
+}
+
+__JIT_CODE("__unalign_jit_x0_shrui:  {shrui r0, r0, 0; iret}");
+static tilegx_bundle_bits  jit_x0_shrui(int rd, int ra, int imm6)
+{
+	extern  tilegx_bundle_bits __unalign_jit_x0_shrui;
+	return (GX_INSN_BSWAP(__unalign_jit_x0_shrui) &
+		GX_INSN_X0_MASK) |
+		create_Dest_X0(rd) | create_SrcA_X0(ra) |
+		create_ShAmt_X0(imm6);
+}
+
+__JIT_CODE("__unalign_jit_x0_rotli:  {rotli r0, r0, 0; iret}");
+static tilegx_bundle_bits  jit_x0_rotli(int rd, int ra, int imm6)
+{
+	extern  tilegx_bundle_bits __unalign_jit_x0_rotli;
+	return (GX_INSN_BSWAP(__unalign_jit_x0_rotli) &
+		GX_INSN_X0_MASK) |
+		create_Dest_X0(rd) | create_SrcA_X0(ra) |
+		create_ShAmt_X0(imm6);
+}
+
+__JIT_CODE("__unalign_jit_x1_bnezt:  {bnezt r0, __unalign_jit_x1_bnezt}");
+static tilegx_bundle_bits  jit_x1_bnezt(int ra, int broff)
+{
+	extern  tilegx_bundle_bits __unalign_jit_x1_bnezt;
+	return (GX_INSN_BSWAP(__unalign_jit_x1_bnezt) &
+		GX_INSN_X1_MASK) |
+		create_SrcA_X1(ra) | create_BrOff_X1(broff);
+}
+
+#undef __JIT_CODE
+
+/*
+ * This function generates unalign fixup JIT.
+ *
+ * We first find unalign load/store instruction's destination, source
+ * registers: ra, rb and rd. and 3 scratch registers by calling
+ * find_regs(...). 3 scratch clobbers should not alias with any register
+ * used in the fault bundle. Then analyze the fault bundle to determine
+ * if it's a load or store, operand width, branch or address increment etc.
+ * At last generated JIT is copied into JIT code area in user space.
+ */
+
+static
+void jit_bundle_gen(struct pt_regs *regs, tilegx_bundle_bits bundle,
+		    int align_ctl)
+{
+	struct thread_info *info = current_thread_info();
+	struct unaligned_jit_fragment frag;
+	struct unaligned_jit_fragment *jit_code_area;
+	tilegx_bundle_bits bundle_2 = 0;
+	/* If bundle_2_enable = false, bundle_2 is fnop/nop operation. */
+	bool     bundle_2_enable = true;
+	uint64_t ra, rb, rd = -1, clob1, clob2, clob3;
+	/*
+	 * Indicate if the unalign access
+	 * instruction's registers hit with
+	 * others in the same bundle.
+	 */
+	bool     alias = false;
+	bool     load_n_store = true;
+	bool     load_store_signed = false;
+	unsigned int  load_store_size = 8;
+	bool     y1_br = false;  /* True, for a branch in same bundle at Y1.*/
+	int      y1_br_reg = 0;
+	/* True for link operation. i.e. jalr or lnk at Y1 */
+	bool     y1_lr = false;
+	int      y1_lr_reg = 0;
+	bool     x1_add = false;/* True, for load/store ADD instruction at X1*/
+	int      x1_add_imm8 = 0;
+	bool     unexpected = false;
+	int      n = 0, k;
+
+	jit_code_area =
+		(struct unaligned_jit_fragment *)(info->unalign_jit_base);
+
+	memset((void *)&frag, 0, sizeof(frag));
+
+	/* 0: X mode, Otherwise: Y mode. */
+	if (bundle & TILEGX_BUNDLE_MODE_MASK) {
+		unsigned int mod, opcode;
+
+		if (get_Opcode_Y1(bundle) == RRR_1_OPCODE_Y1 &&
+		    get_RRROpcodeExtension_Y1(bundle) ==
+		    UNARY_RRR_1_OPCODE_Y1) {
+
+			opcode = get_UnaryOpcodeExtension_Y1(bundle);
+
+			/*
+			 * Test "jalr", "jalrp", "jr", "jrp" instruction at Y1
+			 * pipeline.
+			 */
+			switch (opcode) {
+			case JALR_UNARY_OPCODE_Y1:
+			case JALRP_UNARY_OPCODE_Y1:
+				y1_lr = true;
+				y1_lr_reg = 55; /* Link register. */
+				/* FALLTHROUGH */
+			case JR_UNARY_OPCODE_Y1:
+			case JRP_UNARY_OPCODE_Y1:
+				y1_br = true;
+				y1_br_reg = get_SrcA_Y1(bundle);
+				break;
+			case LNK_UNARY_OPCODE_Y1:
+				/* "lnk" at Y1 pipeline. */
+				y1_lr = true;
+				y1_lr_reg = get_Dest_Y1(bundle);
+				break;
+			}
+		}
+
+		opcode = get_Opcode_Y2(bundle);
+		mod = get_Mode(bundle);
+
+		/*
+		 *  bundle_2 is bundle after making Y2 as a dummy operation
+		 *  - ld zero, sp
+		 */
+		bundle_2 = (bundle & (~GX_INSN_Y2_MASK)) | jit_y2_dummy();
+
+		/* Make Y1 as fnop if Y1 is a branch or lnk operation. */
+		if (y1_br || y1_lr) {
+			bundle_2 &= ~(GX_INSN_Y1_MASK);
+			bundle_2 |= jit_y1_fnop();
+		}
+
+		if (is_y0_y1_nop(bundle_2))
+			bundle_2_enable = false;
+
+		if (mod == MODE_OPCODE_YC2) {
+			/* Store. */
+			load_n_store = false;
+			load_store_size = 1 << opcode;
+			load_store_signed = false;
+			find_regs(bundle, 0, &ra, &rb, &clob1, &clob2,
+				  &clob3, &alias);
+			if (load_store_size > 8)
+				unexpected = true;
+		} else {
+			/* Load. */
+			load_n_store = true;
+			if (mod == MODE_OPCODE_YB2) {
+				switch (opcode) {
+				case LD_OPCODE_Y2:
+					load_store_signed = false;
+					load_store_size = 8;
+					break;
+				case LD4S_OPCODE_Y2:
+					load_store_signed = true;
+					load_store_size = 4;
+					break;
+				case LD4U_OPCODE_Y2:
+					load_store_signed = false;
+					load_store_size = 4;
+					break;
+				default:
+					unexpected = true;
+				}
+			} else if (mod == MODE_OPCODE_YA2) {
+				if (opcode == LD2S_OPCODE_Y2) {
+					load_store_signed = true;
+					load_store_size = 2;
+				} else if (opcode == LD2U_OPCODE_Y2) {
+					load_store_signed = false;
+					load_store_size = 2;
+				} else
+					unexpected = true;
+			} else
+				unexpected = true;
+			find_regs(bundle, &rd, &ra, &rb, &clob1, &clob2,
+				  &clob3, &alias);
+		}
+	} else {
+		unsigned int opcode;
+
+		/* bundle_2 is bundle after making X1 as "fnop". */
+		bundle_2 = (bundle & (~GX_INSN_X1_MASK)) | jit_x1_fnop();
+
+		if (is_x0_x1_nop(bundle_2))
+			bundle_2_enable = false;
+
+		if (get_Opcode_X1(bundle) == RRR_0_OPCODE_X1) {
+			opcode = get_UnaryOpcodeExtension_X1(bundle);
+
+			if (get_RRROpcodeExtension_X1(bundle) ==
+			    UNARY_RRR_0_OPCODE_X1) {
+				load_n_store = true;
+				find_regs(bundle, &rd, &ra, &rb, &clob1,
+					  &clob2, &clob3, &alias);
+
+				switch (opcode) {
+				case LD_UNARY_OPCODE_X1:
+					load_store_signed = false;
+					load_store_size = 8;
+					break;
+				case LD4S_UNARY_OPCODE_X1:
+					load_store_signed = true;
+					/* FALLTHROUGH */
+				case LD4U_UNARY_OPCODE_X1:
+					load_store_size = 4;
+					break;
+
+				case LD2S_UNARY_OPCODE_X1:
+					load_store_signed = true;
+					/* FALLTHROUGH */
+				case LD2U_UNARY_OPCODE_X1:
+					load_store_size = 2;
+					break;
+				default:
+					unexpected = true;
+				}
+			} else {
+				load_n_store = false;
+				load_store_signed = false;
+				find_regs(bundle, 0, &ra, &rb,
+					  &clob1, &clob2, &clob3,
+					  &alias);
+
+				opcode = get_RRROpcodeExtension_X1(bundle);
+				switch (opcode)	{
+				case ST_RRR_0_OPCODE_X1:
+					load_store_size = 8;
+					break;
+				case ST4_RRR_0_OPCODE_X1:
+					load_store_size = 4;
+					break;
+				case ST2_RRR_0_OPCODE_X1:
+					load_store_size = 2;
+					break;
+				default:
+					unexpected = true;
+				}
+			}
+		} else if (get_Opcode_X1(bundle) == IMM8_OPCODE_X1) {
+			load_n_store = true;
+			opcode = get_Imm8OpcodeExtension_X1(bundle);
+			switch (opcode)	{
+			case LD_ADD_IMM8_OPCODE_X1:
+				load_store_size = 8;
+				break;
+
+			case LD4S_ADD_IMM8_OPCODE_X1:
+				load_store_signed = true;
+				/* FALLTHROUGH */
+			case LD4U_ADD_IMM8_OPCODE_X1:
+				load_store_size = 4;
+				break;
+
+			case LD2S_ADD_IMM8_OPCODE_X1:
+				load_store_signed = true;
+				/* FALLTHROUGH */
+			case LD2U_ADD_IMM8_OPCODE_X1:
+				load_store_size = 2;
+				break;
+
+			case ST_ADD_IMM8_OPCODE_X1:
+				load_n_store = false;
+				load_store_size = 8;
+				break;
+			case ST4_ADD_IMM8_OPCODE_X1:
+				load_n_store = false;
+				load_store_size = 4;
+				break;
+			case ST2_ADD_IMM8_OPCODE_X1:
+				load_n_store = false;
+				load_store_size = 2;
+				break;
+			default:
+				unexpected = true;
+			}
+
+			if (!unexpected) {
+				x1_add = true;
+				if (load_n_store)
+					x1_add_imm8 = get_Imm8_X1(bundle);
+				else
+					x1_add_imm8 = get_Dest_Imm8_X1(bundle);
+			}
+
+			find_regs(bundle, load_n_store ? (&rd) : NULL,
+				  &ra, &rb, &clob1, &clob2, &clob3, &alias);
+		} else
+			unexpected = true;
+	}
+
+	/*
+	 * Some sanity check for register numbers extracted from fault bundle.
+	 */
+	if (check_regs(rd, ra, rb, clob1, clob2, clob3) == true)
+		unexpected = true;
+
+	/* Give warning if register ra has an aligned address. */
+	if (!unexpected)
+		WARN_ON(!((load_store_size - 1) & (regs->regs[ra])));
+
+
+	/*
+	 * Fault came from kernel space, here we only need take care of
+	 * unaligned "get_user/put_user" macros defined in "uaccess.h".
+	 * Basically, we will handle bundle like this:
+	 * {ld/2u/4s rd, ra; movei rx, 0} or {st/2/4 ra, rb; movei rx, 0}
+	 * (Refer to file "arch/tile/include/asm/uaccess.h" for details).
+	 * For either load or store, byte-wise operation is performed by calling
+	 * get_user() or put_user(). If the macro returns non-zero value,
+	 * set the value to rx, otherwise set zero to rx. Finally make pc point
+	 * to next bundle and return.
+	 */
+
+	if (EX1_PL(regs->ex1) != USER_PL) {
+
+		unsigned long rx = 0;
+		unsigned long x = 0, ret = 0;
+
+		if (y1_br || y1_lr || x1_add ||
+		    (load_store_signed !=
+		     (load_n_store && load_store_size == 4))) {
+			/* No branch, link, wrong sign-ext or load/store add. */
+			unexpected = true;
+		} else if (!unexpected) {
+			if (bundle & TILEGX_BUNDLE_MODE_MASK) {
+				/*
+				 * Fault bundle is Y mode.
+				 * Check if the Y1 and Y0 is the form of
+				 * { movei rx, 0; nop/fnop }, if yes,
+				 * find the rx.
+				 */
+
+				if ((get_Opcode_Y1(bundle) == ADDI_OPCODE_Y1)
+				    && (get_SrcA_Y1(bundle) == TREG_ZERO) &&
+				    (get_Imm8_Y1(bundle) == 0) &&
+				    is_bundle_y0_nop(bundle)) {
+					rx = get_Dest_Y1(bundle);
+				} else if ((get_Opcode_Y0(bundle) ==
+					    ADDI_OPCODE_Y0) &&
+					   (get_SrcA_Y0(bundle) == TREG_ZERO) &&
+					   (get_Imm8_Y0(bundle) == 0) &&
+					   is_bundle_y1_nop(bundle)) {
+					rx = get_Dest_Y0(bundle);
+				} else {
+					unexpected = true;
+				}
+			} else {
+				/*
+				 * Fault bundle is X mode.
+				 * Check if the X0 is 'movei rx, 0',
+				 * if yes, find the rx.
+				 */
+
+				if ((get_Opcode_X0(bundle) == IMM8_OPCODE_X0)
+				    && (get_Imm8OpcodeExtension_X0(bundle) ==
+					ADDI_IMM8_OPCODE_X0) &&
+				    (get_SrcA_X0(bundle) == TREG_ZERO) &&
+				    (get_Imm8_X0(bundle) == 0)) {
+					rx = get_Dest_X0(bundle);
+				} else {
+					unexpected = true;
+				}
+			}
+
+			/* rx should be less than 56. */
+			if (!unexpected && (rx >= 56))
+				unexpected = true;
+		}
+
+		if (!search_exception_tables(regs->pc)) {
+			/* No fixup in the exception tables for the pc. */
+			unexpected = true;
+		}
+
+		if (unexpected) {
+			/* Unexpected unalign kernel fault. */
+			struct task_struct *tsk = validate_current();
+
+			bust_spinlocks(1);
+
+			show_regs(regs);
+
+			if (unlikely(tsk->pid < 2)) {
+				panic("Kernel unalign fault running %s!",
+				      tsk->pid ? "init" : "the idle task");
+			}
+#ifdef SUPPORT_DIE
+			die("Oops", regs);
+#endif
+			bust_spinlocks(1);
+
+			do_group_exit(SIGKILL);
+
+		} else {
+			unsigned long i, b = 0;
+			unsigned char *ptr =
+				(unsigned char *)regs->regs[ra];
+			if (load_n_store) {
+				/* handle get_user(x, ptr) */
+				for (i = 0; i < load_store_size; i++) {
+					ret = get_user(b, ptr++);
+					if (!ret) {
+						/* Success! update x. */
+#ifdef __LITTLE_ENDIAN
+						x |= (b << (8 * i));
+#else
+						x <<= 8;
+						x |= b;
+#endif /* __LITTLE_ENDIAN */
+					} else {
+						x = 0;
+						break;
+					}
+				}
+
+				/* Sign-extend 4-byte loads. */
+				if (load_store_size == 4)
+					x = (long)(int)x;
+
+				/* Set register rd. */
+				regs->regs[rd] = x;
+
+				/* Set register rx. */
+				regs->regs[rx] = ret;
+
+				/* Bump pc. */
+				regs->pc += 8;
+
+			} else {
+				/* Handle put_user(x, ptr) */
+				x = regs->regs[rb];
+#ifdef __LITTLE_ENDIAN
+				b = x;
+#else
+				/*
+				 * Swap x in order to store x from low
+				 * to high memory same as the
+				 * little-endian case.
+				 */
+				switch (load_store_size) {
+				case 8:
+					b = swab64(x);
+					break;
+				case 4:
+					b = swab32(x);
+					break;
+				case 2:
+					b = swab16(x);
+					break;
+				}
+#endif /* __LITTLE_ENDIAN */
+				for (i = 0; i < load_store_size; i++) {
+					ret = put_user(b, ptr++);
+					if (ret)
+						break;
+					/* Success! shift 1 byte. */
+					b >>= 8;
+				}
+				/* Set register rx. */
+				regs->regs[rx] = ret;
+
+				/* Bump pc. */
+				regs->pc += 8;
+			}
+		}
+
+		unaligned_fixup_count++;
+
+		if (unaligned_printk) {
+			pr_info("%s/%d. Unalign fixup for kernel access "
+				"to userspace %lx.",
+				current->comm, current->pid, regs->regs[ra]);
+		}
+
+		/* Done! Return to the exception handler. */
+		return;
+	}
+
+	if ((align_ctl == 0) || unexpected) {
+		siginfo_t info = {
+			.si_signo = SIGBUS,
+			.si_code = BUS_ADRALN,
+			.si_addr = (unsigned char __user *)0
+		};
+		if (unaligned_printk)
+			pr_info("Unalign bundle: unexp @%llx, %llx",
+				(unsigned long long)regs->pc,
+				(unsigned long long)bundle);
+
+		if (ra < 56) {
+			unsigned long uaa = (unsigned long)regs->regs[ra];
+			/* Set bus Address. */
+			info.si_addr = (unsigned char __user *)uaa;
+		}
+
+		unaligned_fixup_count++;
+
+		trace_unhandled_signal("unaligned fixup trap", regs,
+				       (unsigned long)info.si_addr, SIGBUS);
+		force_sig_info(info.si_signo, &info, current);
+		return;
+	}
+
+#ifdef __LITTLE_ENDIAN
+#define UA_FIXUP_ADDR_DELTA          1
+#define UA_FIXUP_BFEXT_START(_B_)    0
+#define UA_FIXUP_BFEXT_END(_B_)     (8 * (_B_) - 1)
+#else /* __BIG_ENDIAN */
+#define UA_FIXUP_ADDR_DELTA          -1
+#define UA_FIXUP_BFEXT_START(_B_)   (64 - 8 * (_B_))
+#define UA_FIXUP_BFEXT_END(_B_)      63
+#endif /* __LITTLE_ENDIAN */
+
+
+
+	if ((ra != rb) && (rd != TREG_SP) && !alias &&
+	    !y1_br && !y1_lr && !x1_add) {
+		/*
+		 * Simple case: ra != rb and no register alias found,
+		 * and no branch or link. This will be the majority.
+		 * We can do a little better for simplae case than the
+		 * generic scheme below.
+		 */
+		if (!load_n_store) {
+			/*
+			 * Simple store: ra != rb, no need for scratch register.
+			 * Just store and rotate to right bytewise.
+			 */
+#ifdef __BIG_ENDIAN
+			frag.insn[n++] =
+				jit_x0_addi(ra, ra, load_store_size - 1) |
+				jit_x1_fnop();
+#endif /* __BIG_ENDIAN */
+			for (k = 0; k < load_store_size; k++) {
+				/* Store a byte. */
+				frag.insn[n++] =
+					jit_x0_rotli(rb, rb, 56) |
+					jit_x1_st1_add(ra, rb,
+						       UA_FIXUP_ADDR_DELTA);
+			}
+#ifdef __BIG_ENDIAN
+			frag.insn[n] = jit_x1_addi(ra, ra, 1);
+#else
+			frag.insn[n] = jit_x1_addi(ra, ra,
+						   -1 * load_store_size);
+#endif /* __LITTLE_ENDIAN */
+
+			if (load_store_size == 8) {
+				frag.insn[n] |= jit_x0_fnop();
+			} else if (load_store_size == 4) {
+				frag.insn[n] |= jit_x0_rotli(rb, rb, 32);
+			} else { /* = 2 */
+				frag.insn[n] |= jit_x0_rotli(rb, rb, 16);
+			}
+			n++;
+			if (bundle_2_enable)
+				frag.insn[n++] = bundle_2;
+			frag.insn[n++] = jit_x0_fnop() | jit_x1_iret();
+		} else {
+			if (rd == ra) {
+				/* Use two clobber registers: clob1/2. */
+				frag.insn[n++] =
+					jit_x0_addi(TREG_SP, TREG_SP, -16) |
+					jit_x1_fnop();
+				frag.insn[n++] =
+					jit_x0_addi(clob1, ra, 7) |
+					jit_x1_st_add(TREG_SP, clob1, -8);
+				frag.insn[n++] =
+					jit_x0_addi(clob2, ra, 0) |
+					jit_x1_st(TREG_SP, clob2);
+				frag.insn[n++] =
+					jit_x0_fnop() |
+					jit_x1_ldna(rd, ra);
+				frag.insn[n++] =
+					jit_x0_fnop() |
+					jit_x1_ldna(clob1, clob1);
+				/*
+				 * Note: we must make sure that rd must not
+				 * be sp. Recover clob1/2 from stack.
+				 */
+				frag.insn[n++] =
+					jit_x0_dblalign(rd, clob1, clob2) |
+					jit_x1_ld_add(clob2, TREG_SP, 8);
+				frag.insn[n++] =
+					jit_x0_fnop() |
+					jit_x1_ld_add(clob1, TREG_SP, 16);
+			} else {
+				/* Use one clobber register: clob1 only. */
+				frag.insn[n++] =
+					jit_x0_addi(TREG_SP, TREG_SP, -16) |
+					jit_x1_fnop();
+				frag.insn[n++] =
+					jit_x0_addi(clob1, ra, 7) |
+					jit_x1_st(TREG_SP, clob1);
+				frag.insn[n++] =
+					jit_x0_fnop() |
+					jit_x1_ldna(rd, ra);
+				frag.insn[n++] =
+					jit_x0_fnop() |
+					jit_x1_ldna(clob1, clob1);
+				/*
+				 * Note: we must make sure that rd must not
+				 * be sp. Recover clob1 from stack.
+				 */
+				frag.insn[n++] =
+					jit_x0_dblalign(rd, clob1, ra) |
+					jit_x1_ld_add(clob1, TREG_SP, 16);
+			}
+
+			if (bundle_2_enable)
+				frag.insn[n++] = bundle_2;
+			/*
+			 * For non 8-byte load, extract corresponding bytes and
+			 * signed extension.
+			 */
+			if (load_store_size == 4) {
+				if (load_store_signed)
+					frag.insn[n++] =
+						jit_x0_bfexts(
+							rd, rd,
+							UA_FIXUP_BFEXT_START(4),
+							UA_FIXUP_BFEXT_END(4)) |
+						jit_x1_fnop();
+				else
+					frag.insn[n++] =
+						jit_x0_bfextu(
+							rd, rd,
+							UA_FIXUP_BFEXT_START(4),
+							UA_FIXUP_BFEXT_END(4)) |
+						jit_x1_fnop();
+			} else if (load_store_size == 2) {
+				if (load_store_signed)
+					frag.insn[n++] =
+						jit_x0_bfexts(
+							rd, rd,
+							UA_FIXUP_BFEXT_START(2),
+							UA_FIXUP_BFEXT_END(2)) |
+						jit_x1_fnop();
+				else
+					frag.insn[n++] =
+						jit_x0_bfextu(
+							rd, rd,
+							UA_FIXUP_BFEXT_START(2),
+							UA_FIXUP_BFEXT_END(2)) |
+						jit_x1_fnop();
+			}
+
+			frag.insn[n++] =
+				jit_x0_fnop()  |
+				jit_x1_iret();
+		}
+	} else if (!load_n_store) {
+
+		/*
+		 * Generic memory store cases: use 3 clobber registers.
+		 *
+		 * Alloc space for saveing clob2,1,3 on user's stack.
+		 * register clob3 points to where clob2 saved, followed by
+		 * clob1 and 3 from high to low memory.
+		 */
+		frag.insn[n++] =
+			jit_x0_addi(TREG_SP, TREG_SP, -32)    |
+			jit_x1_fnop();
+		frag.insn[n++] =
+			jit_x0_addi(clob3, TREG_SP, 16)  |
+			jit_x1_st_add(TREG_SP, clob3, 8);
+#ifdef __LITTLE_ENDIAN
+		frag.insn[n++] =
+			jit_x0_addi(clob1, ra, 0)   |
+			jit_x1_st_add(TREG_SP, clob1, 8);
+#else
+		frag.insn[n++] =
+			jit_x0_addi(clob1, ra, load_store_size - 1)   |
+			jit_x1_st_add(TREG_SP, clob1, 8);
+#endif
+		if (load_store_size == 8) {
+			/*
+			 * We save one byte a time, not for fast, but compact
+			 * code. After each store, data source register shift
+			 * right one byte. unchanged after 8 stores.
+			 */
+			frag.insn[n++] =
+				jit_x0_addi(clob2, TREG_ZERO, 7)     |
+				jit_x1_st_add(TREG_SP, clob2, 16);
+			frag.insn[n++] =
+				jit_x0_rotli(rb, rb, 56)      |
+				jit_x1_st1_add(clob1, rb, UA_FIXUP_ADDR_DELTA);
+			frag.insn[n++] =
+				jit_x0_addi(clob2, clob2, -1) |
+				jit_x1_bnezt(clob2, -1);
+			frag.insn[n++] =
+				jit_x0_fnop()                 |
+				jit_x1_addi(clob2, y1_br_reg, 0);
+		} else if (load_store_size == 4) {
+			frag.insn[n++] =
+				jit_x0_addi(clob2, TREG_ZERO, 3)     |
+				jit_x1_st_add(TREG_SP, clob2, 16);
+			frag.insn[n++] =
+				jit_x0_rotli(rb, rb, 56)      |
+				jit_x1_st1_add(clob1, rb, UA_FIXUP_ADDR_DELTA);
+			frag.insn[n++] =
+				jit_x0_addi(clob2, clob2, -1) |
+				jit_x1_bnezt(clob2, -1);
+			/*
+			 * same as 8-byte case, but need shift another 4
+			 * byte to recover rb for 4-byte store.
+			 */
+			frag.insn[n++] = jit_x0_rotli(rb, rb, 32)      |
+				jit_x1_addi(clob2, y1_br_reg, 0);
+		} else { /* =2 */
+			frag.insn[n++] =
+				jit_x0_addi(clob2, rb, 0)     |
+				jit_x1_st_add(TREG_SP, clob2, 16);
+			for (k = 0; k < 2; k++) {
+				frag.insn[n++] =
+					jit_x0_shrui(rb, rb, 8)  |
+					jit_x1_st1_add(clob1, rb,
+						       UA_FIXUP_ADDR_DELTA);
+			}
+			frag.insn[n++] =
+				jit_x0_addi(rb, clob2, 0)       |
+				jit_x1_addi(clob2, y1_br_reg, 0);
+		}
+
+		if (bundle_2_enable)
+			frag.insn[n++] = bundle_2;
+
+		if (y1_lr) {
+			frag.insn[n++] =
+				jit_x0_fnop()                    |
+				jit_x1_mfspr(y1_lr_reg,
+					     SPR_EX_CONTEXT_0_0);
+		}
+		if (y1_br) {
+			frag.insn[n++] =
+				jit_x0_fnop()                    |
+				jit_x1_mtspr(SPR_EX_CONTEXT_0_0,
+					     clob2);
+		}
+		if (x1_add) {
+			frag.insn[n++] =
+				jit_x0_addi(ra, ra, x1_add_imm8) |
+				jit_x1_ld_add(clob2, clob3, -8);
+		} else {
+			frag.insn[n++] =
+				jit_x0_fnop()                    |
+				jit_x1_ld_add(clob2, clob3, -8);
+		}
+		frag.insn[n++] =
+			jit_x0_fnop()   |
+			jit_x1_ld_add(clob1, clob3, -8);
+		frag.insn[n++] = jit_x0_fnop()   | jit_x1_ld(clob3, clob3);
+		frag.insn[n++] = jit_x0_fnop()   | jit_x1_iret();
+
+	} else {
+		/*
+		 * Generic memory load cases.
+		 *
+		 * Alloc space for saveing clob1,2,3 on user's stack.
+		 * register clob3 points to where clob1 saved, followed
+		 * by clob2 and 3 from high to low memory.
+		 */
+
+		frag.insn[n++] =
+			jit_x0_addi(TREG_SP, TREG_SP, -32) |
+			jit_x1_fnop();
+		frag.insn[n++] =
+			jit_x0_addi(clob3, TREG_SP, 16) |
+			jit_x1_st_add(TREG_SP, clob3, 8);
+		frag.insn[n++] =
+			jit_x0_addi(clob2, ra, 0) |
+			jit_x1_st_add(TREG_SP, clob2, 8);
+
+		if (y1_br) {
+			frag.insn[n++] =
+				jit_x0_addi(clob1, y1_br_reg, 0) |
+				jit_x1_st_add(TREG_SP, clob1, 16);
+		} else {
+			frag.insn[n++] =
+				jit_x0_fnop() |
+				jit_x1_st_add(TREG_SP, clob1, 16);
+		}
+
+		if (bundle_2_enable)
+			frag.insn[n++] = bundle_2;
+
+		if (y1_lr) {
+			frag.insn[n++] =
+				jit_x0_fnop()  |
+				jit_x1_mfspr(y1_lr_reg,
+					     SPR_EX_CONTEXT_0_0);
+		}
+
+		if (y1_br) {
+			frag.insn[n++] =
+				jit_x0_fnop() |
+				jit_x1_mtspr(SPR_EX_CONTEXT_0_0,
+					     clob1);
+		}
+
+		frag.insn[n++] =
+			jit_x0_addi(clob1, clob2, 7)      |
+			jit_x1_ldna(rd, clob2);
+		frag.insn[n++] =
+			jit_x0_fnop()                     |
+			jit_x1_ldna(clob1, clob1);
+		frag.insn[n++] =
+			jit_x0_dblalign(rd, clob1, clob2) |
+			jit_x1_ld_add(clob1, clob3, -8);
+		if (x1_add) {
+			frag.insn[n++] =
+				jit_x0_addi(ra, ra, x1_add_imm8) |
+				jit_x1_ld_add(clob2, clob3, -8);
+		} else {
+			frag.insn[n++] =
+				jit_x0_fnop()  |
+				jit_x1_ld_add(clob2, clob3, -8);
+		}
+
+		frag.insn[n++] =
+			jit_x0_fnop() |
+			jit_x1_ld(clob3, clob3);
+
+		if (load_store_size == 4) {
+			if (load_store_signed)
+				frag.insn[n++] =
+					jit_x0_bfexts(
+						rd, rd,
+						UA_FIXUP_BFEXT_START(4),
+						UA_FIXUP_BFEXT_END(4)) |
+					jit_x1_fnop();
+			else
+				frag.insn[n++] =
+					jit_x0_bfextu(
+						rd, rd,
+						UA_FIXUP_BFEXT_START(4),
+						UA_FIXUP_BFEXT_END(4)) |
+					jit_x1_fnop();
+		} else if (load_store_size == 2) {
+			if (load_store_signed)
+				frag.insn[n++] =
+					jit_x0_bfexts(
+						rd, rd,
+						UA_FIXUP_BFEXT_START(2),
+						UA_FIXUP_BFEXT_END(2)) |
+					jit_x1_fnop();
+			else
+				frag.insn[n++] =
+					jit_x0_bfextu(
+						rd, rd,
+						UA_FIXUP_BFEXT_START(2),
+						UA_FIXUP_BFEXT_END(2)) |
+					jit_x1_fnop();
+		}
+
+		frag.insn[n++] = jit_x0_fnop() | jit_x1_iret();
+	}
+
+	/* Max JIT bundle count is 14. */
+	WARN_ON(n > 14);
+
+	if (!unexpected) {
+		int status = 0;
+		int idx = (regs->pc >> 3) &
+			((1ULL << (PAGE_SHIFT - UNALIGN_JIT_SHIFT)) - 1);
+
+		frag.pc = regs->pc;
+		frag.bundle = bundle;
+
+		if (unaligned_printk) {
+			pr_info("%s/%d, Unalign fixup: pc=%lx "
+				"bundle=%lx %d %d %d %d %d %d %d %d.",
+				current->comm, current->pid,
+				(unsigned long)frag.pc,
+				(unsigned long)frag.bundle,
+				(int)alias, (int)rd, (int)ra,
+				(int)rb, (int)bundle_2_enable,
+				(int)y1_lr, (int)y1_br, (int)x1_add);
+
+			for (k = 0; k < n; k += 2)
+				pr_info("[%d] %016llx %016llx", k,
+					(unsigned long long)frag.insn[k],
+					(unsigned long long)frag.insn[k+1]);
+		}
+
+		/* Swap bundle byte order for big endian sys. */
+#ifdef __BIG_ENDIAN
+		frag.bundle = GX_INSN_BSWAP(frag.bundle);
+		for (k = 0; k < n; k++)
+			frag.insn[k] = GX_INSN_BSWAP(frag.insn[k]);
+#endif /* __BIG_ENDIAN */
+
+		status = copy_to_user((void __user *)&jit_code_area[idx],
+				      &frag, sizeof(frag));
+		if (status) {
+			/* Fail to copy JIT into user land. send SIGSEGV. */
+			siginfo_t info = {
+				.si_signo = SIGSEGV,
+				.si_code = SEGV_MAPERR,
+				.si_addr = (void __user *)&jit_code_area[idx]
+			};
+
+			pr_warn("Unalign fixup: pid=%d %s jit_code_area=%llx",
+				current->pid, current->comm,
+				(unsigned long long)&jit_code_area[idx]);
+
+			trace_unhandled_signal("segfault in unalign fixup",
+					       regs,
+					       (unsigned long)info.si_addr,
+					       SIGSEGV);
+			force_sig_info(info.si_signo, &info, current);
+			return;
+		}
+
+
+		/* Do a cheaper increment, not accurate. */
+		unaligned_fixup_count++;
+		__flush_icache_range((unsigned long)&jit_code_area[idx],
+				     (unsigned long)&jit_code_area[idx] +
+				     sizeof(frag));
+
+		/* Setup SPR_EX_CONTEXT_0_0/1 for returning to user program.*/
+		__insn_mtspr(SPR_EX_CONTEXT_0_0, regs->pc + 8);
+		__insn_mtspr(SPR_EX_CONTEXT_0_1, PL_ICS_EX1(USER_PL, 0));
+
+		/* Modify pc at the start of new JIT. */
+		regs->pc = (unsigned long)&jit_code_area[idx].insn[0];
+		/* Set ICS in SPR_EX_CONTEXT_K_1. */
+		regs->ex1 = PL_ICS_EX1(USER_PL, 1);
+	}
+}
+
+
+/*
+ * C function to generate unalign data JIT. Called from unalign data
+ * interrupt handler.
+ *
+ * First check if unalign fix is disabled or exception did not not come from
+ * user space or sp register points to unalign address, if true, generate a
+ * SIGBUS. Then map a page into user space as JIT area if it is not mapped
+ * yet. Genenerate JIT code by calling jit_bundle_gen(). After that return
+ * back to exception handler.
+ *
+ * The exception handler will "iret" to new generated JIT code after
+ * restoring caller saved registers. In theory, the JIT code will perform
+ * another "iret" to resume user's program.
+ */
+
+void do_unaligned(struct pt_regs *regs, int vecnum)
+{
+	tilegx_bundle_bits __user  *pc;
+	tilegx_bundle_bits bundle;
+	struct thread_info *info = current_thread_info();
+	int align_ctl;
+
+	/* Checks the per-process unaligned JIT flags */
+	align_ctl = unaligned_fixup;
+	switch (task_thread_info(current)->align_ctl) {
+	case PR_UNALIGN_NOPRINT:
+		align_ctl = 1;
+		break;
+	case PR_UNALIGN_SIGBUS:
+		align_ctl = 0;
+		break;
+	}
+
+	/* Enable iterrupt in order to access user land. */
+	local_irq_enable();
+
+	/*
+	 * The fault came from kernel space. Two choices:
+	 * (a) unaligned_fixup < 1, we will first call get/put_user fixup
+	 *     to return -EFAULT. If no fixup, simply panic the kernel.
+	 * (b) unaligned_fixup >=1, we will try to fix the unaligned access
+	 *     if it was triggered by get_user/put_user() macros. Panic the
+	 *     kernel if it is not fixable.
+	 */
+
+	if (EX1_PL(regs->ex1) != USER_PL) {
+
+		if (align_ctl < 1) {
+			unaligned_fixup_count++;
+			/* If exception came from kernel, try fix it up. */
+			if (fixup_exception(regs)) {
+				if (unaligned_printk)
+					pr_info("Unalign fixup: %d %llx @%llx",
+						(int)unaligned_fixup,
+						(unsigned long long)regs->ex1,
+						(unsigned long long)regs->pc);
+				return;
+			}
+			/* Not fixable. Go panic. */
+			panic("Unalign exception in Kernel. pc=%lx",
+			      regs->pc);
+			return;
+		} else {
+			/*
+			 * Try to fix the exception. If we can't, panic the
+			 * kernel.
+			 */
+			bundle = GX_INSN_BSWAP(
+				*((tilegx_bundle_bits *)(regs->pc)));
+			jit_bundle_gen(regs, bundle, align_ctl);
+			return;
+		}
+	}
+
+	/*
+	 * Fault came from user with ICS or stack is not aligned.
+	 * If so, we will trigger SIGBUS.
+	 */
+	if ((regs->sp & 0x7) || (regs->ex1) || (align_ctl < 0)) {
+		siginfo_t info = {
+			.si_signo = SIGBUS,
+			.si_code = BUS_ADRALN,
+			.si_addr = (unsigned char __user *)0
+		};
+
+		if (unaligned_printk)
+			pr_info("Unalign fixup: %d %llx @%llx",
+				(int)unaligned_fixup,
+				(unsigned long long)regs->ex1,
+				(unsigned long long)regs->pc);
+
+		unaligned_fixup_count++;
+
+		trace_unhandled_signal("unaligned fixup trap", regs, 0, SIGBUS);
+		force_sig_info(info.si_signo, &info, current);
+		return;
+	}
+
+
+	/* Read the bundle casued the exception! */
+	pc = (tilegx_bundle_bits __user *)(regs->pc);
+	if (get_user(bundle, pc) != 0) {
+		/* Probably never be here since pc is valid user address.*/
+		siginfo_t info = {
+			.si_signo = SIGSEGV,
+			.si_code = SEGV_MAPERR,
+			.si_addr = (void __user *)pc
+		};
+		pr_err("Couldn't read instruction at %p trying to step\n", pc);
+		trace_unhandled_signal("segfault in unalign fixup", regs,
+				       (unsigned long)info.si_addr, SIGSEGV);
+		force_sig_info(info.si_signo, &info, current);
+		return;
+	}
+
+	if (!info->unalign_jit_base) {
+		void __user *user_page;
+
+		/*
+		 * Allocate a page in userland.
+		 * For 64-bit processes we try to place the mapping far
+		 * from anything else that might be going on (specifically
+		 * 64 GB below the top of the user address space).  If it
+		 * happens not to be possible to put it there, it's OK;
+		 * the kernel will choose another location and we'll
+		 * remember it for later.
+		 */
+		if (is_compat_task())
+			user_page = NULL;
+		else
+			user_page = (void __user *)(TASK_SIZE - (1UL << 36)) +
+				(current->pid << PAGE_SHIFT);
+
+		user_page = (void __user *) vm_mmap(NULL,
+						    (unsigned long)user_page,
+						    PAGE_SIZE,
+						    PROT_EXEC | PROT_READ |
+						    PROT_WRITE,
+#ifdef CONFIG_HOMECACHE
+						    MAP_CACHE_HOME_TASK |
+#endif
+						    MAP_PRIVATE |
+						    MAP_ANONYMOUS,
+						    0);
+
+		if (IS_ERR((void __force *)user_page)) {
+			pr_err("Out of kernel pages trying do_mmap.\n");
+			return;
+		}
+
+		/* Save the address in the thread_info struct */
+		info->unalign_jit_base = user_page;
+		if (unaligned_printk)
+			pr_info("Unalign bundle: %d:%d, allocate page @%llx",
+				raw_smp_processor_id(), current->pid,
+				(unsigned long long)user_page);
+	}
+
+	/* Generate unalign JIT */
+	jit_bundle_gen(regs, GX_INSN_BSWAP(bundle), align_ctl);
+}
+
+#endif /* __tilegx__ */
diff --git a/arch/tile/kernel/vdso.c b/arch/tile/kernel/vdso.c
new file mode 100644
index 000000000000..1533af24106e
--- /dev/null
+++ b/arch/tile/kernel/vdso.c
@@ -0,0 +1,212 @@
+/*
+ * Copyright 2012 Tilera Corporation. All Rights Reserved.
+ *
+ *   This program is free software; you can redistribute it and/or
+ *   modify it under the terms of the GNU General Public License
+ *   as published by the Free Software Foundation, version 2.
+ *
+ *   This program is distributed in the hope that it will be useful, but
+ *   WITHOUT ANY WARRANTY; without even the implied warranty of
+ *   MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ *   NON INFRINGEMENT.  See the GNU General Public License for
+ *   more details.
+ */
+
+#include <linux/binfmts.h>
+#include <linux/compat.h>
+#include <linux/elf.h>
+#include <linux/mm.h>
+#include <linux/pagemap.h>
+
+#include <asm/vdso.h>
+#include <asm/mman.h>
+#include <asm/sections.h>
+
+#include <arch/sim.h>
+
+/* The alignment of the vDSO. */
+#define VDSO_ALIGNMENT  PAGE_SIZE
+
+
+static unsigned int vdso_pages;
+static struct page **vdso_pagelist;
+
+#ifdef CONFIG_COMPAT
+static unsigned int vdso32_pages;
+static struct page **vdso32_pagelist;
+#endif
+static int vdso_ready;
+
+/*
+ * The vdso data page.
+ */
+static union {
+	struct vdso_data	data;
+	u8			page[PAGE_SIZE];
+} vdso_data_store __page_aligned_data;
+
+struct vdso_data *vdso_data = &vdso_data_store.data;
+
+static unsigned int __read_mostly vdso_enabled = 1;
+
+static struct page **vdso_setup(void *vdso_kbase, unsigned int pages)
+{
+	int i;
+	struct page **pagelist;
+
+	pagelist = kzalloc(sizeof(struct page *) * (pages + 1), GFP_KERNEL);
+	BUG_ON(pagelist == NULL);
+	for (i = 0; i < pages - 1; i++) {
+		struct page *pg = virt_to_page(vdso_kbase + i*PAGE_SIZE);
+		ClearPageReserved(pg);
+		pagelist[i] = pg;
+	}
+	pagelist[pages - 1] = virt_to_page(vdso_data);
+	pagelist[pages] = NULL;
+
+	return pagelist;
+}
+
+static int __init vdso_init(void)
+{
+	int data_pages = sizeof(vdso_data_store) >> PAGE_SHIFT;
+
+	/*
+	 * We can disable vDSO support generally, but we need to retain
+	 * one page to support the two-bundle (16-byte) rt_sigreturn path.
+	 */
+	if (!vdso_enabled) {
+		size_t offset = (unsigned long)&__vdso_rt_sigreturn;
+		static struct page *sigret_page;
+		sigret_page = alloc_page(GFP_KERNEL | __GFP_ZERO);
+		BUG_ON(sigret_page == NULL);
+		vdso_pagelist = &sigret_page;
+		vdso_pages = 1;
+		BUG_ON(offset >= PAGE_SIZE);
+		memcpy(page_address(sigret_page) + offset,
+		       vdso_start + offset, 16);
+#ifdef CONFIG_COMPAT
+		vdso32_pages = vdso_pages;
+		vdso32_pagelist = vdso_pagelist;
+#endif
+		vdso_ready = 1;
+		return 0;
+	}
+
+	vdso_pages = (vdso_end - vdso_start) >> PAGE_SHIFT;
+	vdso_pages += data_pages;
+	vdso_pagelist = vdso_setup(vdso_start, vdso_pages);
+
+#ifdef CONFIG_COMPAT
+	vdso32_pages = (vdso32_end - vdso32_start) >> PAGE_SHIFT;
+	vdso32_pages += data_pages;
+	vdso32_pagelist = vdso_setup(vdso32_start, vdso32_pages);
+#endif
+
+	smp_wmb();
+	vdso_ready = 1;
+
+	return 0;
+}
+arch_initcall(vdso_init);
+
+const char *arch_vma_name(struct vm_area_struct *vma)
+{
+	if (vma->vm_mm && vma->vm_start == VDSO_BASE)
+		return "[vdso]";
+#ifndef __tilegx__
+	if (vma->vm_start == MEM_USER_INTRPT)
+		return "[intrpt]";
+#endif
+	return NULL;
+}
+
+struct vm_area_struct *get_gate_vma(struct mm_struct *mm)
+{
+	return NULL;
+}
+
+int in_gate_area(struct mm_struct *mm, unsigned long address)
+{
+	return 0;
+}
+
+int in_gate_area_no_mm(unsigned long address)
+{
+	return 0;
+}
+
+int setup_vdso_pages(void)
+{
+	struct page **pagelist;
+	unsigned long pages;
+	struct mm_struct *mm = current->mm;
+	unsigned long vdso_base = 0;
+	int retval = 0;
+
+	if (!vdso_ready)
+		return 0;
+
+	mm->context.vdso_base = 0;
+
+	pagelist = vdso_pagelist;
+	pages = vdso_pages;
+#ifdef CONFIG_COMPAT
+	if (is_compat_task()) {
+		pagelist = vdso32_pagelist;
+		pages = vdso32_pages;
+	}
+#endif
+
+	/*
+	 * vDSO has a problem and was disabled, just don't "enable" it for the
+	 * process.
+	 */
+	if (pages == 0)
+		return 0;
+
+	vdso_base = get_unmapped_area(NULL, vdso_base,
+				      (pages << PAGE_SHIFT) +
+				      ((VDSO_ALIGNMENT - 1) & PAGE_MASK),
+				      0, 0);
+	if (IS_ERR_VALUE(vdso_base)) {
+		retval = vdso_base;
+		return retval;
+	}
+
+	/* Add required alignment. */
+	vdso_base = ALIGN(vdso_base, VDSO_ALIGNMENT);
+
+	/*
+	 * Put vDSO base into mm struct. We need to do this before calling
+	 * install_special_mapping or the perf counter mmap tracking code
+	 * will fail to recognise it as a vDSO (since arch_vma_name fails).
+	 */
+	mm->context.vdso_base = vdso_base;
+
+	/*
+	 * our vma flags don't have VM_WRITE so by default, the process isn't
+	 * allowed to write those pages.
+	 * gdb can break that with ptrace interface, and thus trigger COW on
+	 * those pages but it's then your responsibility to never do that on
+	 * the "data" page of the vDSO or you'll stop getting kernel updates
+	 * and your nice userland gettimeofday will be totally dead.
+	 * It's fine to use that for setting breakpoints in the vDSO code
+	 * pages though
+	 */
+	retval = install_special_mapping(mm, vdso_base,
+					 pages << PAGE_SHIFT,
+					 VM_READ|VM_EXEC |
+					 VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC,
+					 pagelist);
+	if (retval)
+		mm->context.vdso_base = 0;
+
+	return retval;
+}
+
+static __init int vdso_func(char *s)
+{
+	return kstrtouint(s, 0, &vdso_enabled);
+}
+__setup("vdso=", vdso_func);
diff --git a/arch/tile/kernel/vdso/Makefile b/arch/tile/kernel/vdso/Makefile
new file mode 100644
index 000000000000..e2b7a2f4ee41
--- /dev/null
+++ b/arch/tile/kernel/vdso/Makefile
@@ -0,0 +1,118 @@
+# Symbols present in the vdso
+vdso-syms = rt_sigreturn gettimeofday
+
+# Files to link into the vdso
+obj-vdso = $(patsubst %, v%.o, $(vdso-syms))
+
+# Build rules
+targets := $(obj-vdso) vdso.so vdso.so.dbg vdso.lds
+obj-vdso := $(addprefix $(obj)/, $(obj-vdso))
+
+# vdso32 is only for tilegx -m32 compat task.
+VDSO32-$(CONFIG_COMPAT) := y
+
+obj-y += vdso.o
+obj-$(VDSO32-y) += vdso32.o
+extra-y += vdso.lds
+CPPFLAGS_vdso.lds += -P -C -U$(ARCH)
+
+# vDSO code runs in userspace and -pg doesn't help with profiling anyway.
+CFLAGS_REMOVE_vdso.o = -pg
+CFLAGS_REMOVE_vdso32.o = -pg
+CFLAGS_REMOVE_vrt_sigreturn.o = -pg
+CFLAGS_REMOVE_vrt_sigreturn32.o = -pg
+CFLAGS_REMOVE_vgettimeofday.o = -pg
+CFLAGS_REMOVE_vgettimeofday32.o = -pg
+
+ifdef CONFIG_FEEDBACK_COLLECT
+# vDSO code runs in userspace, not collecting feedback data.
+CFLAGS_REMOVE_vdso.o = -ffeedback-generate
+CFLAGS_REMOVE_vdso32.o = -ffeedback-generate
+CFLAGS_REMOVE_vrt_sigreturn.o = -ffeedback-generate
+CFLAGS_REMOVE_vrt_sigreturn32.o = -ffeedback-generate
+CFLAGS_REMOVE_vgettimeofday.o = -ffeedback-generate
+CFLAGS_REMOVE_vgettimeofday32.o = -ffeedback-generate
+endif
+
+# Disable gcov profiling for VDSO code
+GCOV_PROFILE := n
+
+# Force dependency
+$(obj)/vdso.o: $(obj)/vdso.so
+
+# link rule for the .so file, .lds has to be first
+SYSCFLAGS_vdso.so.dbg = $(c_flags)
+$(obj)/vdso.so.dbg: $(src)/vdso.lds $(obj-vdso)
+	$(call if_changed,vdsold)
+
+
+# We also create a special relocatable object that should mirror the symbol
+# table and layout of the linked DSO.  With ld -R we can then refer to
+# these symbols in the kernel code rather than hand-coded addresses.
+extra-y += vdso-syms.o
+$(obj)/built-in.o: $(obj)/vdso-syms.o
+$(obj)/built-in.o: ld_flags += -R $(obj)/vdso-syms.o
+
+SYSCFLAGS_vdso.so.dbg = -shared -s -Wl,-soname=linux-vdso.so.1 \
+                            $(call cc-ldoption, -Wl$(comma)--hash-style=sysv)
+SYSCFLAGS_vdso_syms.o = -r
+$(obj)/vdso-syms.o: $(src)/vdso.lds $(obj)/vrt_sigreturn.o FORCE
+	$(call if_changed,vdsold)
+
+
+# strip rule for the .so file
+$(obj)/%.so: OBJCOPYFLAGS := -S
+$(obj)/%.so: $(obj)/%.so.dbg FORCE
+	$(call if_changed,objcopy)
+
+# actual build commands
+# The DSO images are built using a special linker script
+# Add -lgcc so tilepro gets static muldi3 and lshrdi3 definitions.
+# Make sure only to export the intended __vdso_xxx symbol offsets.
+quiet_cmd_vdsold = VDSOLD  $@
+      cmd_vdsold = $(CC) $(KCFLAGS) -nostdlib $(SYSCFLAGS_$(@F)) \
+                           -Wl,-T,$(filter-out FORCE,$^) -o $@.tmp -lgcc && \
+                   $(CROSS_COMPILE)objcopy \
+                           $(patsubst %, -G __vdso_%, $(vdso-syms)) $@.tmp $@
+
+# install commands for the unstripped file
+quiet_cmd_vdso_install = INSTALL $@
+      cmd_vdso_install = cp $(obj)/$@.dbg $(MODLIB)/vdso/$@
+
+vdso.so: $(obj)/vdso.so.dbg
+	@mkdir -p $(MODLIB)/vdso
+	$(call cmd,vdso_install)
+
+vdso32.so: $(obj)/vdso32.so.dbg
+	$(call cmd,vdso_install)
+
+vdso_install: vdso.so
+vdso32_install: vdso32.so
+
+
+KBUILD_AFLAGS_32 := $(filter-out -m64,$(KBUILD_AFLAGS))
+KBUILD_AFLAGS_32 += -m32 -s
+KBUILD_CFLAGS_32 := $(filter-out -m64,$(KBUILD_CFLAGS))
+KBUILD_CFLAGS_32 += -m32 -fPIC -shared
+
+obj-vdso32 = $(patsubst %, v%32.o, $(vdso-syms))
+obj-vdso32 := $(addprefix $(obj)/, $(obj-vdso32))
+
+targets += $(obj-vdso32) vdso32.so vdso32.so.dbg
+
+$(obj-vdso32:%=%): KBUILD_AFLAGS = $(KBUILD_AFLAGS_32)
+$(obj-vdso32:%=%): KBUILD_CFLAGS = $(KBUILD_CFLAGS_32)
+
+$(obj)/vgettimeofday32.o: $(obj)/vgettimeofday.c
+	$(call if_changed,cc_o_c)
+
+$(obj)/vrt_sigreturn32.o: $(obj)/vrt_sigreturn.S
+	$(call if_changed,as_o_S)
+
+# Force dependency
+$(obj)/vdso32.o: $(obj)/vdso32.so
+
+SYSCFLAGS_vdso32.so.dbg = -m32 -shared -s -Wl,-soname=linux-vdso32.so.1 \
+			    $(call cc-ldoption, -Wl$(comma)--hash-style=sysv)
+$(obj)/vdso32.so.dbg: $(src)/vdso.lds $(obj-vdso32)
+	$(call if_changed,vdsold)
diff --git a/arch/tile/kernel/vdso/vdso.S b/arch/tile/kernel/vdso/vdso.S
new file mode 100644
index 000000000000..3467adb41630
--- /dev/null
+++ b/arch/tile/kernel/vdso/vdso.S
@@ -0,0 +1,28 @@
+/*
+ * Copyright 2012 Tilera Corporation. All Rights Reserved.
+ *
+ *   This program is free software; you can redistribute it and/or
+ *   modify it under the terms of the GNU General Public License
+ *   as published by the Free Software Foundation, version 2.
+ *
+ *   This program is distributed in the hope that it will be useful, but
+ *   WITHOUT ANY WARRANTY; without even the implied warranty of
+ *   MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ *   NON INFRINGEMENT.  See the GNU General Public License for
+ *   more details.
+ */
+
+#include <linux/init.h>
+#include <linux/linkage.h>
+#include <asm/page.h>
+
+	__PAGE_ALIGNED_DATA
+
+	.global vdso_start, vdso_end
+	.align PAGE_SIZE
+vdso_start:
+	.incbin "arch/tile/kernel/vdso/vdso.so"
+	.align PAGE_SIZE
+vdso_end:
+
+	.previous
diff --git a/arch/tile/kernel/vdso/vdso.lds.S b/arch/tile/kernel/vdso/vdso.lds.S
new file mode 100644
index 000000000000..041cd6c39c83
--- /dev/null
+++ b/arch/tile/kernel/vdso/vdso.lds.S
@@ -0,0 +1,87 @@
+/*
+ * Copyright 2012 Tilera Corporation. All Rights Reserved.
+ *
+ *   This program is free software; you can redistribute it and/or
+ *   modify it under the terms of the GNU General Public License
+ *   as published by the Free Software Foundation, version 2.
+ *
+ *   This program is distributed in the hope that it will be useful, but
+ *   WITHOUT ANY WARRANTY; without even the implied warranty of
+ *   MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ *   NON INFRINGEMENT.  See the GNU General Public License for
+ *   more details.
+ */
+
+#define VDSO_VERSION_STRING	LINUX_2.6
+
+
+OUTPUT_ARCH(tile)
+
+/* The ELF entry point can be used to set the AT_SYSINFO value. */
+ENTRY(__vdso_rt_sigreturn);
+
+
+SECTIONS
+{
+	. = SIZEOF_HEADERS;
+
+	.hash		: { *(.hash) }			:text
+	.gnu.hash	: { *(.gnu.hash) }
+	.dynsym		: { *(.dynsym) }
+	.dynstr		: { *(.dynstr) }
+	.gnu.version	: { *(.gnu.version) }
+	.gnu.version_d	: { *(.gnu.version_d) }
+	.gnu.version_r	: { *(.gnu.version_r) }
+
+	.note		: { *(.note.*) }		:text	:note
+	.dynamic	: { *(.dynamic) }		:text	:dynamic
+
+	.eh_frame_hdr	: { *(.eh_frame_hdr) }		:text	:eh_frame_hdr
+	.eh_frame	: { KEEP (*(.eh_frame)) }	:text
+
+	.rodata	 : { *(.rodata .rodata.* .gnu.linkonce.r.*) }
+
+	/*
+	 * This linker script is used both with -r and with -shared.
+	 * For the layouts to match, we need to skip more than enough
+	 * space for the dynamic symbol table et al. If this amount
+	 * is insufficient, ld -shared will barf. Just increase it here.
+	 */
+	. = 0x1000;
+	.text		: { *(.text .text.*) }		:text
+
+	.data		: {
+		*(.got.plt) *(.got)
+		*(.data .data.* .gnu.linkonce.d.*)
+		*(.dynbss)
+		*(.bss .bss.* .gnu.linkonce.b.*)
+	}
+}
+
+
+/*
+ * We must supply the ELF program headers explicitly to get just one
+ * PT_LOAD segment, and set the flags explicitly to make segments read-only.
+ */
+PHDRS
+{
+	text		PT_LOAD		FLAGS(5) FILEHDR PHDRS;	/* PF_R|PF_X */
+	dynamic		PT_DYNAMIC	FLAGS(4);		/* PF_R */
+	note		PT_NOTE		FLAGS(4);		/* PF_R */
+	eh_frame_hdr	PT_GNU_EH_FRAME;
+}
+
+
+/*
+ * This controls what userland symbols we export from the vDSO.
+ */
+VERSION
+{
+	VDSO_VERSION_STRING {
+	global:
+		__vdso_rt_sigreturn;
+		__vdso_gettimeofday;
+		gettimeofday;
+	local:*;
+	};
+}
diff --git a/arch/tile/kernel/vdso/vdso32.S b/arch/tile/kernel/vdso/vdso32.S
new file mode 100644
index 000000000000..1d1ac3257e11
--- /dev/null
+++ b/arch/tile/kernel/vdso/vdso32.S
@@ -0,0 +1,28 @@
+/*
+ * Copyright 2013 Tilera Corporation. All Rights Reserved.
+ *
+ *   This program is free software; you can redistribute it and/or
+ *   modify it under the terms of the GNU General Public License
+ *   as published by the Free Software Foundation, version 2.
+ *
+ *   This program is distributed in the hope that it will be useful, but
+ *   WITHOUT ANY WARRANTY; without even the implied warranty of
+ *   MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ *   NON INFRINGEMENT.  See the GNU General Public License for
+ *   more details.
+ */
+
+#include <linux/init.h>
+#include <linux/linkage.h>
+#include <asm/page.h>
+
+	__PAGE_ALIGNED_DATA
+
+	.global vdso32_start, vdso32_end
+	.align PAGE_SIZE
+vdso32_start:
+	.incbin "arch/tile/kernel/vdso/vdso32.so"
+	.align PAGE_SIZE
+vdso32_end:
+
+	.previous
diff --git a/arch/tile/kernel/vdso/vgettimeofday.c b/arch/tile/kernel/vdso/vgettimeofday.c
new file mode 100644
index 000000000000..51ec8e46f5f9
--- /dev/null
+++ b/arch/tile/kernel/vdso/vgettimeofday.c
@@ -0,0 +1,107 @@
+/*
+ * Copyright 2012 Tilera Corporation. All Rights Reserved.
+ *
+ *   This program is free software; you can redistribute it and/or
+ *   modify it under the terms of the GNU General Public License
+ *   as published by the Free Software Foundation, version 2.
+ *
+ *   This program is distributed in the hope that it will be useful, but
+ *   WITHOUT ANY WARRANTY; without even the implied warranty of
+ *   MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ *   NON INFRINGEMENT.  See the GNU General Public License for
+ *   more details.
+ */
+
+#define VDSO_BUILD  /* avoid some shift warnings for -m32 in <asm/page.h> */
+#include <linux/time.h>
+#include <asm/timex.h>
+#include <asm/vdso.h>
+
+#if CHIP_HAS_SPLIT_CYCLE()
+static inline cycles_t get_cycles_inline(void)
+{
+	unsigned int high = __insn_mfspr(SPR_CYCLE_HIGH);
+	unsigned int low = __insn_mfspr(SPR_CYCLE_LOW);
+	unsigned int high2 = __insn_mfspr(SPR_CYCLE_HIGH);
+
+	while (unlikely(high != high2)) {
+		low = __insn_mfspr(SPR_CYCLE_LOW);
+		high = high2;
+		high2 = __insn_mfspr(SPR_CYCLE_HIGH);
+	}
+
+	return (((cycles_t)high) << 32) | low;
+}
+#define get_cycles get_cycles_inline
+#endif
+
+/*
+ * Find out the vDSO data page address in the process address space.
+ */
+inline unsigned long get_datapage(void)
+{
+	unsigned long ret;
+
+	/* vdso data page located in the 2nd vDSO page. */
+	asm volatile ("lnk %0" : "=r"(ret));
+	ret &= ~(PAGE_SIZE - 1);
+	ret += PAGE_SIZE;
+
+	return ret;
+}
+
+int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz)
+{
+	cycles_t cycles;
+	unsigned long count, sec, ns;
+	volatile struct vdso_data *vdso_data;
+
+	vdso_data = (struct vdso_data *)get_datapage();
+	/* The use of the timezone is obsolete, normally tz is NULL. */
+	if (unlikely(tz != NULL)) {
+		while (1) {
+			/* Spin until the update finish. */
+			count = vdso_data->tz_update_count;
+			if (count & 1)
+				continue;
+
+			tz->tz_minuteswest = vdso_data->tz_minuteswest;
+			tz->tz_dsttime = vdso_data->tz_dsttime;
+
+			/* Check whether updated, read again if so. */
+			if (count == vdso_data->tz_update_count)
+				break;
+		}
+	}
+
+	if (unlikely(tv == NULL))
+		return 0;
+
+	while (1) {
+		/* Spin until the update finish. */
+		count = vdso_data->tb_update_count;
+		if (count & 1)
+			continue;
+
+		cycles = (get_cycles() - vdso_data->xtime_tod_stamp);
+		ns = (cycles * vdso_data->mult) >> vdso_data->shift;
+		sec = vdso_data->xtime_clock_sec;
+		ns += vdso_data->xtime_clock_nsec;
+		if (ns >= NSEC_PER_SEC) {
+			ns -= NSEC_PER_SEC;
+			sec += 1;
+		}
+
+		/* Check whether updated, read again if so. */
+		if (count == vdso_data->tb_update_count)
+			break;
+	}
+
+	tv->tv_sec = sec;
+	tv->tv_usec = ns / 1000;
+
+	return 0;
+}
+
+int gettimeofday(struct timeval *tv, struct timezone *tz)
+	__attribute__((weak, alias("__vdso_gettimeofday")));
diff --git a/arch/tile/kernel/vdso/vrt_sigreturn.S b/arch/tile/kernel/vdso/vrt_sigreturn.S
new file mode 100644
index 000000000000..6326caf4a039
--- /dev/null
+++ b/arch/tile/kernel/vdso/vrt_sigreturn.S
@@ -0,0 +1,30 @@
+/*
+ * Copyright 2012 Tilera Corporation. All Rights Reserved.
+ *
+ *   This program is free software; you can redistribute it and/or
+ *   modify it under the terms of the GNU General Public License
+ *   as published by the Free Software Foundation, version 2.
+ *
+ *   This program is distributed in the hope that it will be useful, but
+ *   WITHOUT ANY WARRANTY; without even the implied warranty of
+ *   MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ *   NON INFRINGEMENT.  See the GNU General Public License for
+ *   more details.
+ */
+
+#include <linux/linkage.h>
+#include <arch/abi.h>
+#include <asm/unistd.h>
+
+/*
+ * Note that libc has a copy of this function that it uses to compare
+ * against the PC when a stack backtrace ends, so if this code is
+ * changed, the libc implementation(s) should also be updated.
+ */
+ENTRY(__vdso_rt_sigreturn)
+	moveli TREG_SYSCALL_NR_NAME, __NR_rt_sigreturn
+	swint1
+	/* We don't use ENDPROC to avoid tagging this symbol as FUNC,
+	 * which confuses the perf tool.
+	 */
+	END(__vdso_rt_sigreturn)
diff --git a/arch/tile/kernel/vmlinux.lds.S b/arch/tile/kernel/vmlinux.lds.S
index a13ed902afbb..f1819423ffc9 100644
--- a/arch/tile/kernel/vmlinux.lds.S
+++ b/arch/tile/kernel/vmlinux.lds.S
@@ -5,7 +5,7 @@
 #include <hv/hypervisor.h>
 
 /* Text loads starting from the supervisor interrupt vector address. */
-#define TEXT_OFFSET MEM_SV_INTRPT
+#define TEXT_OFFSET MEM_SV_START
 
 OUTPUT_ARCH(tile)
 ENTRY(_start)
@@ -13,7 +13,7 @@ jiffies = jiffies_64;
 
 PHDRS
 {
-  intrpt1 PT_LOAD ;
+  intrpt PT_LOAD ;
   text PT_LOAD ;
   data PT_LOAD ;
 }
@@ -24,14 +24,17 @@ SECTIONS
   #define LOAD_OFFSET TEXT_OFFSET
 
   /* Interrupt vectors */
-  .intrpt1 (LOAD_OFFSET) : AT ( 0 )   /* put at the start of physical memory */
+  .intrpt (LOAD_OFFSET) : AT ( 0 )   /* put at the start of physical memory */
   {
     _text = .;
-    *(.intrpt1)
-  } :intrpt1 =0
+    *(.intrpt)
+  } :intrpt =0
 
   /* Hypervisor call vectors */
-  #include "hvglue.lds"
+  . = ALIGN(0x10000);
+  .hvglue : AT (ADDR(.hvglue) - LOAD_OFFSET) {
+    *(.hvglue)
+  } :NONE
 
   /* Now the real code */
   . = ALIGN(0x20000);
@@ -40,7 +43,11 @@ SECTIONS
     HEAD_TEXT
     SCHED_TEXT
     LOCK_TEXT
+    KPROBES_TEXT
+    IRQENTRY_TEXT
     __fix_text_end = .;   /* tile-cpack won't rearrange before this */
+    ALIGN_FUNCTION();
+    *(.hottext*)
     TEXT_TEXT
     *(.text.*)
     *(.coldtext*)
@@ -67,20 +74,8 @@ SECTIONS
   __init_end = .;
 
   _sdata = .;                   /* Start of data section */
-
   RO_DATA_SECTION(PAGE_SIZE)
-
-  /* initially writeable, then read-only */
-  . = ALIGN(PAGE_SIZE);
-  __w1data_begin = .;
-  .w1data : AT(ADDR(.w1data) - LOAD_OFFSET) {
-    VMLINUX_SYMBOL(__w1data_begin) = .;
-    *(.w1data)
-    VMLINUX_SYMBOL(__w1data_end) = .;
-  }
-
   RW_DATA_SECTION(L2_CACHE_BYTES, PAGE_SIZE, THREAD_SIZE)
-
   _edata = .;
 
   EXCEPTION_TABLE(L2_CACHE_BYTES)
diff --git a/arch/tile/lib/Makefile b/arch/tile/lib/Makefile
index 985f59858234..c4211cbb2021 100644
--- a/arch/tile/lib/Makefile
+++ b/arch/tile/lib/Makefile
@@ -4,15 +4,15 @@
 
 lib-y = cacheflush.o checksum.o cpumask.o delay.o uaccess.o \
 	memmove.o memcpy_$(BITS).o memchr_$(BITS).o memset_$(BITS).o \
-	strchr_$(BITS).o strlen_$(BITS).o
-
-ifeq ($(CONFIG_TILEGX),y)
-CFLAGS_REMOVE_memcpy_user_64.o = -fno-omit-frame-pointer
-lib-y += memcpy_user_64.o
-else
-lib-y += atomic_32.o atomic_asm_32.o memcpy_tile64.o
-endif
+	strchr_$(BITS).o strlen_$(BITS).o strnlen_$(BITS).o
 
+lib-$(CONFIG_TILEGX) += memcpy_user_64.o
+lib-$(CONFIG_TILEPRO) += atomic_32.o atomic_asm_32.o
 lib-$(CONFIG_SMP) += spinlock_$(BITS).o usercopy_$(BITS).o
 
 obj-$(CONFIG_MODULES) += exports.o
+
+# The finv_buffer_remote() and copy_{to,from}_user() routines can't
+# have -pg added, since they both rely on being leaf functions.
+CFLAGS_REMOVE_cacheflush.o = -pg
+CFLAGS_REMOVE_memcpy_user_64.o = -pg
diff --git a/arch/tile/lib/atomic_32.c b/arch/tile/lib/atomic_32.c
index f5cada70c3c8..c89b211fd9e7 100644
--- a/arch/tile/lib/atomic_32.c
+++ b/arch/tile/lib/atomic_32.c
@@ -20,50 +20,12 @@
 #include <linux/atomic.h>
 #include <arch/chip.h>
 
-/* See <asm/atomic_32.h> */
-#if ATOMIC_LOCKS_FOUND_VIA_TABLE()
-
-/*
- * A block of memory containing locks for atomic ops. Each instance of this
- * struct will be homed on a different CPU.
- */
-struct atomic_locks_on_cpu {
-	int lock[ATOMIC_HASH_L2_SIZE];
-} __attribute__((aligned(ATOMIC_HASH_L2_SIZE * 4)));
-
-static DEFINE_PER_CPU(struct atomic_locks_on_cpu, atomic_lock_pool);
-
-/* The locks we'll use until __init_atomic_per_cpu is called. */
-static struct atomic_locks_on_cpu __initdata initial_atomic_locks;
-
-/* Hash into this vector to get a pointer to lock for the given atomic. */
-struct atomic_locks_on_cpu *atomic_lock_ptr[ATOMIC_HASH_L1_SIZE]
-	__write_once = {
-	[0 ... ATOMIC_HASH_L1_SIZE-1] (&initial_atomic_locks)
-};
-
-#else /* ATOMIC_LOCKS_FOUND_VIA_TABLE() */
-
 /* This page is remapped on startup to be hash-for-home. */
 int atomic_locks[PAGE_SIZE / sizeof(int)] __page_aligned_bss;
 
-#endif /* ATOMIC_LOCKS_FOUND_VIA_TABLE() */
-
 int *__atomic_hashed_lock(volatile void *v)
 {
 	/* NOTE: this code must match "sys_cmpxchg" in kernel/intvec_32.S */
-#if ATOMIC_LOCKS_FOUND_VIA_TABLE()
-	unsigned long i =
-		(unsigned long) v & ((PAGE_SIZE-1) & -sizeof(long long));
-	unsigned long n = __insn_crc32_32(0, i);
-
-	/* Grab high bits for L1 index. */
-	unsigned long l1_index = n >> ((sizeof(n) * 8) - ATOMIC_HASH_L1_SHIFT);
-	/* Grab low bits for L2 index. */
-	unsigned long l2_index = n & (ATOMIC_HASH_L2_SIZE - 1);
-
-	return &atomic_lock_ptr[l1_index]->lock[l2_index];
-#else
 	/*
 	 * Use bits [3, 3 + ATOMIC_HASH_SHIFT) as the lock index.
 	 * Using mm works here because atomic_locks is page aligned.
@@ -72,26 +34,13 @@ int *__atomic_hashed_lock(volatile void *v)
 				      (unsigned long)atomic_locks,
 				      2, (ATOMIC_HASH_SHIFT + 2) - 1);
 	return (int *)ptr;
-#endif
 }
 
 #ifdef CONFIG_SMP
 /* Return whether the passed pointer is a valid atomic lock pointer. */
 static int is_atomic_lock(int *p)
 {
-#if ATOMIC_LOCKS_FOUND_VIA_TABLE()
-	int i;
-	for (i = 0; i < ATOMIC_HASH_L1_SIZE; ++i) {
-
-		if (p >= &atomic_lock_ptr[i]->lock[0] &&
-		    p < &atomic_lock_ptr[i]->lock[ATOMIC_HASH_L2_SIZE]) {
-			return 1;
-		}
-	}
-	return 0;
-#else
 	return p >= &atomic_locks[0] && p < &atomic_locks[ATOMIC_HASH_SIZE];
-#endif
 }
 
 void __atomic_fault_unlock(int *irqlock_word)
@@ -110,33 +59,32 @@ static inline int *__atomic_setup(volatile void *v)
 	return __atomic_hashed_lock(v);
 }
 
-int _atomic_xchg(atomic_t *v, int n)
+int _atomic_xchg(int *v, int n)
 {
-	return __atomic_xchg(&v->counter, __atomic_setup(v), n).val;
+	return __atomic_xchg(v, __atomic_setup(v), n).val;
 }
 EXPORT_SYMBOL(_atomic_xchg);
 
-int _atomic_xchg_add(atomic_t *v, int i)
+int _atomic_xchg_add(int *v, int i)
 {
-	return __atomic_xchg_add(&v->counter, __atomic_setup(v), i).val;
+	return __atomic_xchg_add(v, __atomic_setup(v), i).val;
 }
 EXPORT_SYMBOL(_atomic_xchg_add);
 
-int _atomic_xchg_add_unless(atomic_t *v, int a, int u)
+int _atomic_xchg_add_unless(int *v, int a, int u)
 {
 	/*
 	 * Note: argument order is switched here since it is easier
 	 * to use the first argument consistently as the "old value"
 	 * in the assembly, as is done for _atomic_cmpxchg().
 	 */
-	return __atomic_xchg_add_unless(&v->counter, __atomic_setup(v), u, a)
-		.val;
+	return __atomic_xchg_add_unless(v, __atomic_setup(v), u, a).val;
 }
 EXPORT_SYMBOL(_atomic_xchg_add_unless);
 
-int _atomic_cmpxchg(atomic_t *v, int o, int n)
+int _atomic_cmpxchg(int *v, int o, int n)
 {
-	return __atomic_cmpxchg(&v->counter, __atomic_setup(v), o, n).val;
+	return __atomic_cmpxchg(v, __atomic_setup(v), o, n).val;
 }
 EXPORT_SYMBOL(_atomic_cmpxchg);
 
@@ -159,33 +107,32 @@ unsigned long _atomic_xor(volatile unsigned long *p, unsigned long mask)
 EXPORT_SYMBOL(_atomic_xor);
 
 
-u64 _atomic64_xchg(atomic64_t *v, u64 n)
+long long _atomic64_xchg(long long *v, long long n)
 {
-	return __atomic64_xchg(&v->counter, __atomic_setup(v), n);
+	return __atomic64_xchg(v, __atomic_setup(v), n);
 }
 EXPORT_SYMBOL(_atomic64_xchg);
 
-u64 _atomic64_xchg_add(atomic64_t *v, u64 i)
+long long _atomic64_xchg_add(long long *v, long long i)
 {
-	return __atomic64_xchg_add(&v->counter, __atomic_setup(v), i);
+	return __atomic64_xchg_add(v, __atomic_setup(v), i);
 }
 EXPORT_SYMBOL(_atomic64_xchg_add);
 
-u64 _atomic64_xchg_add_unless(atomic64_t *v, u64 a, u64 u)
+long long _atomic64_xchg_add_unless(long long *v, long long a, long long u)
 {
 	/*
 	 * Note: argument order is switched here since it is easier
 	 * to use the first argument consistently as the "old value"
 	 * in the assembly, as is done for _atomic_cmpxchg().
 	 */
-	return __atomic64_xchg_add_unless(&v->counter, __atomic_setup(v),
-					  u, a);
+	return __atomic64_xchg_add_unless(v, __atomic_setup(v), u, a);
 }
 EXPORT_SYMBOL(_atomic64_xchg_add_unless);
 
-u64 _atomic64_cmpxchg(atomic64_t *v, u64 o, u64 n)
+long long _atomic64_cmpxchg(long long *v, long long o, long long n)
 {
-	return __atomic64_cmpxchg(&v->counter, __atomic_setup(v), o, n);
+	return __atomic64_cmpxchg(v, __atomic_setup(v), o, n);
 }
 EXPORT_SYMBOL(_atomic64_cmpxchg);
 
@@ -208,54 +155,8 @@ struct __get_user __atomic_bad_address(int __user *addr)
 }
 
 
-#if CHIP_HAS_CBOX_HOME_MAP()
-static int __init noatomichash(char *str)
-{
-	pr_warning("noatomichash is deprecated.\n");
-	return 1;
-}
-__setup("noatomichash", noatomichash);
-#endif
-
 void __init __init_atomic_per_cpu(void)
 {
-#if ATOMIC_LOCKS_FOUND_VIA_TABLE()
-
-	unsigned int i;
-	int actual_cpu;
-
-	/*
-	 * Before this is called from setup, we just have one lock for
-	 * all atomic objects/operations.  Here we replace the
-	 * elements of atomic_lock_ptr so that they point at per_cpu
-	 * integers.  This seemingly over-complex approach stems from
-	 * the fact that DEFINE_PER_CPU defines an entry for each cpu
-	 * in the grid, not each cpu from 0..ATOMIC_HASH_SIZE-1.  But
-	 * for efficient hashing of atomics to their locks we want a
-	 * compile time constant power of 2 for the size of this
-	 * table, so we use ATOMIC_HASH_SIZE.
-	 *
-	 * Here we populate atomic_lock_ptr from the per cpu
-	 * atomic_lock_pool, interspersing by actual cpu so that
-	 * subsequent elements are homed on consecutive cpus.
-	 */
-
-	actual_cpu = cpumask_first(cpu_possible_mask);
-
-	for (i = 0; i < ATOMIC_HASH_L1_SIZE; ++i) {
-		/*
-		 * Preincrement to slightly bias against using cpu 0,
-		 * which has plenty of stuff homed on it already.
-		 */
-		actual_cpu = cpumask_next(actual_cpu, cpu_possible_mask);
-		if (actual_cpu >= nr_cpu_ids)
-			actual_cpu = cpumask_first(cpu_possible_mask);
-
-		atomic_lock_ptr[i] = &per_cpu(atomic_lock_pool, actual_cpu);
-	}
-
-#else /* ATOMIC_LOCKS_FOUND_VIA_TABLE() */
-
 	/* Validate power-of-two and "bigger than cpus" assumption */
 	BUILD_BUG_ON(ATOMIC_HASH_SIZE & (ATOMIC_HASH_SIZE-1));
 	BUG_ON(ATOMIC_HASH_SIZE < nr_cpu_ids);
@@ -279,6 +180,4 @@ void __init __init_atomic_per_cpu(void)
 	 * That should not produce more indices than ATOMIC_HASH_SIZE.
 	 */
 	BUILD_BUG_ON((PAGE_SIZE >> 3) > ATOMIC_HASH_SIZE);
-
-#endif /* ATOMIC_LOCKS_FOUND_VIA_TABLE() */
 }
diff --git a/arch/tile/lib/atomic_asm_32.S b/arch/tile/lib/atomic_asm_32.S
index 30638042691d..6bda3132cd61 100644
--- a/arch/tile/lib/atomic_asm_32.S
+++ b/arch/tile/lib/atomic_asm_32.S
@@ -164,6 +164,7 @@ STD_ENTRY_SECTION(__atomic\name, .text.atomic)
 	STD_ENDPROC(__atomic\name)
 	.ifc \bitwidth,32
 	.pushsection __ex_table,"a"
+	.align  4
 	.word   1b, __atomic\name
 	.word   2b, __atomic\name
 	.word   __atomic\name, __atomic_bad_address
diff --git a/arch/tile/lib/cacheflush.c b/arch/tile/lib/cacheflush.c
index 8f8ad814b139..9c0ec22009a5 100644
--- a/arch/tile/lib/cacheflush.c
+++ b/arch/tile/lib/cacheflush.c
@@ -36,7 +36,8 @@ static inline void force_load(char *p)
  * core (if "!hfh") or homed via hash-for-home (if "hfh"), waiting
  * until the memory controller holds the flushed values.
  */
-void finv_buffer_remote(void *buffer, size_t size, int hfh)
+void __attribute__((optimize("omit-frame-pointer")))
+finv_buffer_remote(void *buffer, size_t size, int hfh)
 {
 	char *p, *base;
 	size_t step_size, load_count;
@@ -147,18 +148,21 @@ void finv_buffer_remote(void *buffer, size_t size, int hfh)
 		force_load(p);
 
 	/*
-	 * Repeat, but with inv's instead of loads, to get rid of the
+	 * Repeat, but with finv's instead of loads, to get rid of the
 	 * data we just loaded into our own cache and the old home L3.
-	 * No need to unroll since inv's don't target a register.
+	 * No need to unroll since finv's don't target a register.
+	 * The finv's are guaranteed not to actually flush the data in
+	 * the buffer back to their home, since we just read it, so the
+	 * lines are clean in cache; we will only invalidate those lines.
 	 */
 	p = (char *)buffer + size - 1;
-	__insn_inv(p);
+	__insn_finv(p);
 	p -= step_size;
 	p = (char *)((unsigned long)p | (step_size - 1));
 	for (; p >= base; p -= step_size)
-		__insn_inv(p);
+		__insn_finv(p);
 
-	/* Wait for the load+inv's (and thus finvs) to have completed. */
+	/* Wait for these finv's (and thus the first finvs) to be done. */
 	__insn_mf();
 
 #ifdef __tilegx__
diff --git a/arch/tile/lib/exports.c b/arch/tile/lib/exports.c
index a93b02a25222..82733c87d67e 100644
--- a/arch/tile/lib/exports.c
+++ b/arch/tile/lib/exports.c
@@ -22,7 +22,6 @@ EXPORT_SYMBOL(strnlen_user_asm);
 EXPORT_SYMBOL(strncpy_from_user_asm);
 EXPORT_SYMBOL(clear_user_asm);
 EXPORT_SYMBOL(flush_user_asm);
-EXPORT_SYMBOL(inv_user_asm);
 EXPORT_SYMBOL(finv_user_asm);
 
 /* arch/tile/kernel/entry.S */
@@ -34,6 +33,12 @@ EXPORT_SYMBOL(dump_stack);
 /* arch/tile/kernel/head.S */
 EXPORT_SYMBOL(empty_zero_page);
 
+#ifdef CONFIG_FUNCTION_TRACER
+/* arch/tile/kernel/mcount_64.S */
+#include <asm/ftrace.h>
+EXPORT_SYMBOL(__mcount);
+#endif /* CONFIG_FUNCTION_TRACER */
+
 /* arch/tile/lib/, various memcpy files */
 EXPORT_SYMBOL(memcpy);
 EXPORT_SYMBOL(__copy_to_user_inatomic);
diff --git a/arch/tile/lib/memchr_64.c b/arch/tile/lib/memchr_64.c
index 6f867dbf7c56..f8196b3a950e 100644
--- a/arch/tile/lib/memchr_64.c
+++ b/arch/tile/lib/memchr_64.c
@@ -36,7 +36,7 @@ void *memchr(const void *s, int c, size_t n)
 	p = (const uint64_t *)(s_int & -8);
 
 	/* Create eight copies of the byte for which we are looking. */
-	goal = 0x0101010101010101ULL * (uint8_t) c;
+	goal = copy_byte(c);
 
 	/* Read the first word, but munge it so that bytes before the array
 	 * will not match goal.
diff --git a/arch/tile/lib/memcpy_32.S b/arch/tile/lib/memcpy_32.S
index 2a419a6122db..a2771ae5da53 100644
--- a/arch/tile/lib/memcpy_32.S
+++ b/arch/tile/lib/memcpy_32.S
@@ -22,14 +22,6 @@
 
 #include <linux/linkage.h>
 
-/* On TILE64, we wrap these functions via arch/tile/lib/memcpy_tile64.c */
-#if !CHIP_HAS_COHERENT_LOCAL_CACHE()
-#define memcpy __memcpy_asm
-#define __copy_to_user_inatomic __copy_to_user_inatomic_asm
-#define __copy_from_user_inatomic __copy_from_user_inatomic_asm
-#define __copy_from_user_zeroing __copy_from_user_zeroing_asm
-#endif
-
 #define IS_MEMCPY	  0
 #define IS_COPY_FROM_USER  1
 #define IS_COPY_FROM_USER_ZEROING  2
@@ -44,6 +36,7 @@
  */
 #define EX \
 	.pushsection __ex_table, "a"; \
+	.align 4; \
 	.word 9f, memcpy_common_fixup; \
 	.popsection; \
 	9
@@ -158,12 +151,9 @@ EX:	{ sw r0, r3; addi r0, r0, 4; addi r2, r2, -4 }
 
 	{ addi r3, r1, 60; andi r9, r9, -64 }
 
-#if CHIP_HAS_WH64()
 	/* No need to prefetch dst, we'll just do the wh64
 	 * right before we copy a line.
 	 */
-#endif
-
 EX:	{ lw r5, r3; addi r3, r3, 64; movei r4, 1 }
 	/* Intentionally stall for a few cycles to leave L2 cache alone. */
 	{ bnzt zero, .; move r27, lr }
@@ -171,21 +161,6 @@ EX:	{ lw r6, r3; addi r3, r3, 64 }
 	/* Intentionally stall for a few cycles to leave L2 cache alone. */
 	{ bnzt zero, . }
 EX:	{ lw r7, r3; addi r3, r3, 64 }
-#if !CHIP_HAS_WH64()
-	/* Prefetch the dest */
-	/* Intentionally stall for a few cycles to leave L2 cache alone. */
-	{ bnzt zero, . }
-	/* Use a real load to cause a TLB miss if necessary.  We aren't using
-	 * r28, so this should be fine.
-	 */
-EX:	{ lw r28, r9; addi r9, r9, 64 }
-	/* Intentionally stall for a few cycles to leave L2 cache alone. */
-	{ bnzt zero, . }
-	{ prefetch r9; addi r9, r9, 64 }
-	/* Intentionally stall for a few cycles to leave L2 cache alone. */
-	{ bnzt zero, . }
-	{ prefetch r9; addi r9, r9, 64 }
-#endif
 	/* Intentionally stall for a few cycles to leave L2 cache alone. */
 	{ bz zero, .Lbig_loop2 }
 
@@ -286,13 +261,8 @@ EX:	{ lw r7, r3; addi r3, r3, 64 }
 	/* Fill second L1D line. */
 EX:	{ lw r17, r17; addi r1, r1, 48; mvz r3, r13, r1 } /* r17 = WORD_4 */
 
-#if CHIP_HAS_WH64()
 	/* Prepare destination line for writing. */
 EX:	{ wh64 r9; addi r9, r9, 64 }
-#else
-	/* Prefetch dest line */
-	{ prefetch r9; addi r9, r9, 64 }
-#endif
 	/* Load seven words that are L1D hits to cover wh64 L2 usage. */
 
 	/* Load the three remaining words from the last L1D line, which
@@ -330,16 +300,7 @@ EX:	{ lw r18, r1; addi r1, r1, 4 }                  /* r18 = WORD_8 */
 EX:	{ sw r0, r16; addi r0, r0, 4; add r16, r0, r2 } /* store(WORD_0) */
 EX:	{ sw r0, r13; addi r0, r0, 4; andi r16, r16, -64 } /* store(WORD_1) */
 EX:	{ sw r0, r14; addi r0, r0, 4; slt_u r16, r9, r16 } /* store(WORD_2) */
-#if CHIP_HAS_WH64()
 EX:	{ sw r0, r15; addi r0, r0, 4; addi r13, sp, -64 } /* store(WORD_3) */
-#else
-	/* Back up the r9 to a cache line we are already storing to
-	 * if it gets past the end of the dest vector.  Strictly speaking,
-	 * we don't need to back up to the start of a cache line, but it's free
-	 * and tidy, so why not?
-	 */
-EX:	{ sw r0, r15; addi r0, r0, 4; andi r13, r0, -64 } /* store(WORD_3) */
-#endif
 	/* Store second L1D line. */
 EX:	{ sw r0, r17; addi r0, r0, 4; mvz r9, r16, r13 }/* store(WORD_4) */
 EX:	{ sw r0, r19; addi r0, r0, 4 }                  /* store(WORD_5) */
@@ -403,7 +364,6 @@ EX:	{ sb r0, r3;   addi r0, r0, 1; addi r2, r2, -1 }
 
 .Ldest_is_word_aligned:
 
-#if CHIP_HAS_DWORD_ALIGN()
 EX:	{ andi r8, r0, 63; lwadd_na r6, r1, 4}
 	{ slti_u r9, r2, 64; bz r8, .Ldest_is_L2_line_aligned }
 
@@ -511,26 +471,6 @@ EX:	{ swadd r0, r13, 4; addi r2, r2, -32 }
 	/* Move r1 back to the point where it corresponds to r0. */
 	{ addi r1, r1, -4 }
 
-#else /* !CHIP_HAS_DWORD_ALIGN() */
-
-	/* Compute right/left shift counts and load initial source words. */
-	{ andi r5, r1, -4; andi r3, r1, 3 }
-EX:	{ lw r6, r5; addi r5, r5, 4; shli r3, r3, 3 }
-EX:	{ lw r7, r5; addi r5, r5, 4; sub r4, zero, r3 }
-
-	/* Load and store one word at a time, using shifts and ORs
-	 * to correct for the misaligned src.
-	 */
-.Lcopy_unaligned_src_loop:
-	{ shr r6, r6, r3; shl r8, r7, r4 }
-EX:	{ lw r7, r5; or r8, r8, r6; move r6, r7 }
-EX:	{ sw r0, r8; addi r0, r0, 4; addi r2, r2, -4 }
-	{ addi r5, r5, 4; slti_u r8, r2, 8 }
-	{ bzt r8, .Lcopy_unaligned_src_loop; addi r1, r1, 4 }
-
-	{ bz r2, .Lcopy_unaligned_done }
-#endif /* !CHIP_HAS_DWORD_ALIGN() */
-
 	/* Fall through */
 
 /*
@@ -614,5 +554,6 @@ memcpy_fixup_loop:
 	.size memcpy_common_fixup, . - memcpy_common_fixup
 
 	.section __ex_table,"a"
+	.align 4
 	.word .Lcfu, .Lcopy_from_user_fixup_zero_remainder
 	.word .Lctu, .Lcopy_to_user_fixup_done
diff --git a/arch/tile/lib/memcpy_64.c b/arch/tile/lib/memcpy_64.c
index c79b8e7c6828..4815354b8cd2 100644
--- a/arch/tile/lib/memcpy_64.c
+++ b/arch/tile/lib/memcpy_64.c
@@ -18,14 +18,17 @@
 /* EXPORT_SYMBOL() is in arch/tile/lib/exports.c since this should be asm. */
 
 /* Must be 8 bytes in size. */
-#define word_t uint64_t
+#define op_t uint64_t
 
-#if CHIP_L2_LINE_SIZE() != 64 && CHIP_L2_LINE_SIZE() != 128
-#error "Assumes 64 or 128 byte line size"
+/* Threshold value for when to enter the unrolled loops. */
+#define	OP_T_THRES	16
+
+#if CHIP_L2_LINE_SIZE() != 64
+#error "Assumes 64 byte line size"
 #endif
 
 /* How many cache lines ahead should we prefetch? */
-#define PREFETCH_LINES_AHEAD 3
+#define PREFETCH_LINES_AHEAD 4
 
 /*
  * Provide "base versions" of load and store for the normal code path.
@@ -51,15 +54,16 @@ void *memcpy(void *__restrict dstv, const void *__restrict srcv, size_t n)
  * macros to return a count of uncopied bytes due to mm fault.
  */
 #define RETVAL 0
-int USERCOPY_FUNC(void *__restrict dstv, const void *__restrict srcv, size_t n)
+int __attribute__((optimize("omit-frame-pointer")))
+USERCOPY_FUNC(void *__restrict dstv, const void *__restrict srcv, size_t n)
 #endif
 {
 	char *__restrict dst1 = (char *)dstv;
 	const char *__restrict src1 = (const char *)srcv;
 	const char *__restrict src1_end;
 	const char *__restrict prefetch;
-	word_t *__restrict dst8;    /* 8-byte pointer to destination memory. */
-	word_t final; /* Final bytes to write to trailing word, if any */
+	op_t *__restrict dst8;    /* 8-byte pointer to destination memory. */
+	op_t final; /* Final bytes to write to trailing word, if any */
 	long i;
 
 	if (n < 16) {
@@ -79,104 +83,228 @@ int USERCOPY_FUNC(void *__restrict dstv, const void *__restrict srcv, size_t n)
 	for (i = 0; i < PREFETCH_LINES_AHEAD; i++) {
 		__insn_prefetch(prefetch);
 		prefetch += CHIP_L2_LINE_SIZE();
-		prefetch = (prefetch > src1_end) ? prefetch : src1;
+		prefetch = (prefetch < src1_end) ? prefetch : src1;
 	}
 
 	/* Copy bytes until dst is word-aligned. */
-	for (; (uintptr_t)dst1 & (sizeof(word_t) - 1); n--)
+	for (; (uintptr_t)dst1 & (sizeof(op_t) - 1); n--)
 		ST1(dst1++, LD1(src1++));
 
 	/* 8-byte pointer to destination memory. */
-	dst8 = (word_t *)dst1;
-
-	if (__builtin_expect((uintptr_t)src1 & (sizeof(word_t) - 1), 0)) {
-		/*
-		 * Misaligned copy.  Copy 8 bytes at a time, but don't
-		 * bother with other fanciness.
-		 *
-		 * TODO: Consider prefetching and using wh64 as well.
-		 */
-
-		/* Create an aligned src8. */
-		const word_t *__restrict src8 =
-			(const word_t *)((uintptr_t)src1 & -sizeof(word_t));
-		word_t b;
-
-		word_t a = LD8(src8++);
-		for (; n >= sizeof(word_t); n -= sizeof(word_t)) {
-			b = LD8(src8++);
-			a = __insn_dblalign(a, b, src1);
-			ST8(dst8++, a);
-			a = b;
+	dst8 = (op_t *)dst1;
+
+	if (__builtin_expect((uintptr_t)src1 & (sizeof(op_t) - 1), 0)) {
+		/* Unaligned copy. */
+
+		op_t  tmp0 = 0, tmp1 = 0, tmp2, tmp3;
+		const op_t *src8 = (const op_t *) ((uintptr_t)src1 &
+						   -sizeof(op_t));
+		const void *srci = (void *)src1;
+		int m;
+
+		m = (CHIP_L2_LINE_SIZE() << 2) -
+			(((uintptr_t)dst8) & ((CHIP_L2_LINE_SIZE() << 2) - 1));
+		m = (n < m) ? n : m;
+		m /= sizeof(op_t);
+
+		/* Copy until 'dst' is cache-line-aligned. */
+		n -= (sizeof(op_t) * m);
+
+		switch (m % 4) {
+		case 0:
+			if (__builtin_expect(!m, 0))
+				goto _M0;
+			tmp1 = LD8(src8++);
+			tmp2 = LD8(src8++);
+			goto _8B3;
+		case 2:
+			m += 2;
+			tmp3 = LD8(src8++);
+			tmp0 = LD8(src8++);
+			goto _8B1;
+		case 3:
+			m += 1;
+			tmp2 = LD8(src8++);
+			tmp3 = LD8(src8++);
+			goto _8B2;
+		case 1:
+			m--;
+			tmp0 = LD8(src8++);
+			tmp1 = LD8(src8++);
+			if (__builtin_expect(!m, 0))
+				goto _8B0;
+		}
+
+		do {
+			tmp2 = LD8(src8++);
+			tmp0 =  __insn_dblalign(tmp0, tmp1, srci);
+			ST8(dst8++, tmp0);
+_8B3:
+			tmp3 = LD8(src8++);
+			tmp1 = __insn_dblalign(tmp1, tmp2, srci);
+			ST8(dst8++, tmp1);
+_8B2:
+			tmp0 = LD8(src8++);
+			tmp2 = __insn_dblalign(tmp2, tmp3, srci);
+			ST8(dst8++, tmp2);
+_8B1:
+			tmp1 = LD8(src8++);
+			tmp3 = __insn_dblalign(tmp3, tmp0, srci);
+			ST8(dst8++, tmp3);
+			m -= 4;
+		} while (m);
+
+_8B0:
+		tmp0 = __insn_dblalign(tmp0, tmp1, srci);
+		ST8(dst8++, tmp0);
+		src8--;
+
+_M0:
+		if (__builtin_expect(n >= CHIP_L2_LINE_SIZE(), 0)) {
+			op_t tmp4, tmp5, tmp6, tmp7, tmp8;
+
+			prefetch = ((const char *)src8) +
+				CHIP_L2_LINE_SIZE() * PREFETCH_LINES_AHEAD;
+
+			for (tmp0 = LD8(src8++); n >= CHIP_L2_LINE_SIZE();
+			     n -= CHIP_L2_LINE_SIZE()) {
+				/* Prefetch and advance to next line to
+				   prefetch, but don't go past the end.  */
+				__insn_prefetch(prefetch);
+
+				/* Make sure prefetch got scheduled
+				   earlier.  */
+				__asm__ ("" : : : "memory");
+
+				prefetch += CHIP_L2_LINE_SIZE();
+				prefetch = (prefetch < src1_end) ? prefetch :
+					(const char *) src8;
+
+				tmp1 = LD8(src8++);
+				tmp2 = LD8(src8++);
+				tmp3 = LD8(src8++);
+				tmp4 = LD8(src8++);
+				tmp5 = LD8(src8++);
+				tmp6 = LD8(src8++);
+				tmp7 = LD8(src8++);
+				tmp8 = LD8(src8++);
+
+				tmp0 = __insn_dblalign(tmp0, tmp1, srci);
+				tmp1 = __insn_dblalign(tmp1, tmp2, srci);
+				tmp2 = __insn_dblalign(tmp2, tmp3, srci);
+				tmp3 = __insn_dblalign(tmp3, tmp4, srci);
+				tmp4 = __insn_dblalign(tmp4, tmp5, srci);
+				tmp5 = __insn_dblalign(tmp5, tmp6, srci);
+				tmp6 = __insn_dblalign(tmp6, tmp7, srci);
+				tmp7 = __insn_dblalign(tmp7, tmp8, srci);
+
+				__insn_wh64(dst8);
+
+				ST8(dst8++, tmp0);
+				ST8(dst8++, tmp1);
+				ST8(dst8++, tmp2);
+				ST8(dst8++, tmp3);
+				ST8(dst8++, tmp4);
+				ST8(dst8++, tmp5);
+				ST8(dst8++, tmp6);
+				ST8(dst8++, tmp7);
+
+				tmp0 = tmp8;
+			}
+			src8--;
+		}
+
+		/* Copy the rest 8-byte chunks. */
+		if (n >= sizeof(op_t)) {
+			tmp0 = LD8(src8++);
+			for (; n >= sizeof(op_t); n -= sizeof(op_t)) {
+				tmp1 = LD8(src8++);
+				tmp0 = __insn_dblalign(tmp0, tmp1, srci);
+				ST8(dst8++, tmp0);
+				tmp0 = tmp1;
+			}
+			src8--;
 		}
 
 		if (n == 0)
 			return RETVAL;
 
-		b = ((const char *)src8 <= src1_end) ? *src8 : 0;
+		tmp0 = LD8(src8++);
+		tmp1 = ((const char *)src8 <= src1_end)
+			? LD8((op_t *)src8) : 0;
+		final = __insn_dblalign(tmp0, tmp1, srci);
 
-		/*
-		 * Final source bytes to write to trailing partial
-		 * word, if any.
-		 */
-		final = __insn_dblalign(a, b, src1);
 	} else {
 		/* Aligned copy. */
 
-		const word_t* __restrict src8 = (const word_t *)src1;
+		const op_t *__restrict src8 = (const op_t *)src1;
 
 		/* src8 and dst8 are both word-aligned. */
 		if (n >= CHIP_L2_LINE_SIZE()) {
 			/* Copy until 'dst' is cache-line-aligned. */
 			for (; (uintptr_t)dst8 & (CHIP_L2_LINE_SIZE() - 1);
-			     n -= sizeof(word_t))
+			     n -= sizeof(op_t))
 				ST8(dst8++, LD8(src8++));
 
 			for (; n >= CHIP_L2_LINE_SIZE(); ) {
-				__insn_wh64(dst8);
+				op_t tmp0, tmp1, tmp2, tmp3;
+				op_t tmp4, tmp5, tmp6, tmp7;
 
 				/*
 				 * Prefetch and advance to next line
-				 * to prefetch, but don't go past the end
+				 * to prefetch, but don't go past the
+				 * end.
 				 */
 				__insn_prefetch(prefetch);
+
+				/* Make sure prefetch got scheduled
+				   earlier.  */
+				__asm__ ("" : : : "memory");
+
 				prefetch += CHIP_L2_LINE_SIZE();
-				prefetch = (prefetch > src1_end) ? prefetch :
+				prefetch = (prefetch < src1_end) ? prefetch :
 					(const char *)src8;
 
 				/*
-				 * Copy an entire cache line.  Manually
-				 * unrolled to avoid idiosyncracies of
-				 * compiler unrolling.
+				 * Do all the loads before wh64.  This
+				 * is necessary if [src8, src8+7] and
+				 * [dst8, dst8+7] share the same cache
+				 * line and dst8 <= src8, as can be
+				 * the case when called from memmove,
+				 * or with code tested on x86 whose
+				 * memcpy always works with forward
+				 * copies.
 				 */
-#define COPY_WORD(offset) ({ ST8(dst8+offset, LD8(src8+offset)); n -= 8; })
-				COPY_WORD(0);
-				COPY_WORD(1);
-				COPY_WORD(2);
-				COPY_WORD(3);
-				COPY_WORD(4);
-				COPY_WORD(5);
-				COPY_WORD(6);
-				COPY_WORD(7);
-#if CHIP_L2_LINE_SIZE() == 128
-				COPY_WORD(8);
-				COPY_WORD(9);
-				COPY_WORD(10);
-				COPY_WORD(11);
-				COPY_WORD(12);
-				COPY_WORD(13);
-				COPY_WORD(14);
-				COPY_WORD(15);
-#elif CHIP_L2_LINE_SIZE() != 64
-# error Fix code that assumes particular L2 cache line sizes
-#endif
+				tmp0 = LD8(src8++);
+				tmp1 = LD8(src8++);
+				tmp2 = LD8(src8++);
+				tmp3 = LD8(src8++);
+				tmp4 = LD8(src8++);
+				tmp5 = LD8(src8++);
+				tmp6 = LD8(src8++);
+				tmp7 = LD8(src8++);
+
+				/* wh64 and wait for tmp7 load completion. */
+				__asm__ ("move %0, %0; wh64 %1\n"
+					 : : "r"(tmp7), "r"(dst8));
 
-				dst8 += CHIP_L2_LINE_SIZE() / sizeof(word_t);
-				src8 += CHIP_L2_LINE_SIZE() / sizeof(word_t);
+				ST8(dst8++, tmp0);
+				ST8(dst8++, tmp1);
+				ST8(dst8++, tmp2);
+				ST8(dst8++, tmp3);
+				ST8(dst8++, tmp4);
+				ST8(dst8++, tmp5);
+				ST8(dst8++, tmp6);
+				ST8(dst8++, tmp7);
+
+				n -= CHIP_L2_LINE_SIZE();
 			}
+#if CHIP_L2_LINE_SIZE() != 64
+# error "Fix code that assumes particular L2 cache line size."
+#endif
 		}
 
-		for (; n >= sizeof(word_t); n -= sizeof(word_t))
+		for (; n >= sizeof(op_t); n -= sizeof(op_t))
 			ST8(dst8++, LD8(src8++));
 
 		if (__builtin_expect(n == 0, 1))
diff --git a/arch/tile/lib/memcpy_tile64.c b/arch/tile/lib/memcpy_tile64.c
deleted file mode 100644
index 3bc4b4e40d93..000000000000
--- a/arch/tile/lib/memcpy_tile64.c
+++ /dev/null
@@ -1,276 +0,0 @@
-/*
- * Copyright 2010 Tilera Corporation. All Rights Reserved.
- *
- *   This program is free software; you can redistribute it and/or
- *   modify it under the terms of the GNU General Public License
- *   as published by the Free Software Foundation, version 2.
- *
- *   This program is distributed in the hope that it will be useful, but
- *   WITHOUT ANY WARRANTY; without even the implied warranty of
- *   MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
- *   NON INFRINGEMENT.  See the GNU General Public License for
- *   more details.
- */
-
-#include <linux/string.h>
-#include <linux/smp.h>
-#include <linux/module.h>
-#include <linux/uaccess.h>
-#include <asm/fixmap.h>
-#include <asm/kmap_types.h>
-#include <asm/tlbflush.h>
-#include <hv/hypervisor.h>
-#include <arch/chip.h>
-
-
-#if !CHIP_HAS_COHERENT_LOCAL_CACHE()
-
-/* Defined in memcpy.S */
-extern unsigned long __memcpy_asm(void *to, const void *from, unsigned long n);
-extern unsigned long __copy_to_user_inatomic_asm(
-	void __user *to, const void *from, unsigned long n);
-extern unsigned long __copy_from_user_inatomic_asm(
-	void *to, const void __user *from, unsigned long n);
-extern unsigned long __copy_from_user_zeroing_asm(
-	void *to, const void __user *from, unsigned long n);
-
-typedef unsigned long (*memcpy_t)(void *, const void *, unsigned long);
-
-/* Size above which to consider TLB games for performance */
-#define LARGE_COPY_CUTOFF 2048
-
-/* Communicate to the simulator what we are trying to do. */
-#define sim_allow_multiple_caching(b) \
-  __insn_mtspr(SPR_SIM_CONTROL, \
-   SIM_CONTROL_ALLOW_MULTIPLE_CACHING | ((b) << _SIM_CONTROL_OPERATOR_BITS))
-
-/*
- * Copy memory by briefly enabling incoherent cacheline-at-a-time mode.
- *
- * We set up our own source and destination PTEs that we fully control.
- * This is the only way to guarantee that we don't race with another
- * thread that is modifying the PTE; we can't afford to try the
- * copy_{to,from}_user() technique of catching the interrupt, since
- * we must run with interrupts disabled to avoid the risk of some
- * other code seeing the incoherent data in our cache.  (Recall that
- * our cache is indexed by PA, so even if the other code doesn't use
- * our kmap_atomic virtual addresses, they'll still hit in cache using
- * the normal VAs that aren't supposed to hit in cache.)
- */
-static void memcpy_multicache(void *dest, const void *source,
-			      pte_t dst_pte, pte_t src_pte, int len)
-{
-	int idx;
-	unsigned long flags, newsrc, newdst;
-	pmd_t *pmdp;
-	pte_t *ptep;
-	int type0, type1;
-	int cpu = get_cpu();
-
-	/*
-	 * Disable interrupts so that we don't recurse into memcpy()
-	 * in an interrupt handler, nor accidentally reference
-	 * the PA of the source from an interrupt routine.  Also
-	 * notify the simulator that we're playing games so we don't
-	 * generate spurious coherency warnings.
-	 */
-	local_irq_save(flags);
-	sim_allow_multiple_caching(1);
-
-	/* Set up the new dest mapping */
-	type0 = kmap_atomic_idx_push();
-	idx = FIX_KMAP_BEGIN + (KM_TYPE_NR * cpu) + type0;
-	newdst = __fix_to_virt(idx) + ((unsigned long)dest & (PAGE_SIZE-1));
-	pmdp = pmd_offset(pud_offset(pgd_offset_k(newdst), newdst), newdst);
-	ptep = pte_offset_kernel(pmdp, newdst);
-	if (pte_val(*ptep) != pte_val(dst_pte)) {
-		set_pte(ptep, dst_pte);
-		local_flush_tlb_page(NULL, newdst, PAGE_SIZE);
-	}
-
-	/* Set up the new source mapping */
-	type1 = kmap_atomic_idx_push();
-	idx += (type0 - type1);
-	src_pte = hv_pte_set_nc(src_pte);
-	src_pte = hv_pte_clear_writable(src_pte);  /* be paranoid */
-	newsrc = __fix_to_virt(idx) + ((unsigned long)source & (PAGE_SIZE-1));
-	pmdp = pmd_offset(pud_offset(pgd_offset_k(newsrc), newsrc), newsrc);
-	ptep = pte_offset_kernel(pmdp, newsrc);
-	__set_pte(ptep, src_pte);   /* set_pte() would be confused by this */
-	local_flush_tlb_page(NULL, newsrc, PAGE_SIZE);
-
-	/* Actually move the data. */
-	__memcpy_asm((void *)newdst, (const void *)newsrc, len);
-
-	/*
-	 * Remap the source as locally-cached and not OLOC'ed so that
-	 * we can inval without also invaling the remote cpu's cache.
-	 * This also avoids known errata with inv'ing cacheable oloc data.
-	 */
-	src_pte = hv_pte_set_mode(src_pte, HV_PTE_MODE_CACHE_NO_L3);
-	src_pte = hv_pte_set_writable(src_pte); /* need write access for inv */
-	__set_pte(ptep, src_pte);   /* set_pte() would be confused by this */
-	local_flush_tlb_page(NULL, newsrc, PAGE_SIZE);
-
-	/*
-	 * Do the actual invalidation, covering the full L2 cache line
-	 * at the end since __memcpy_asm() is somewhat aggressive.
-	 */
-	__inv_buffer((void *)newsrc, len);
-
-	/*
-	 * We're done: notify the simulator that all is back to normal,
-	 * and re-enable interrupts and pre-emption.
-	 */
-	kmap_atomic_idx_pop();
-	kmap_atomic_idx_pop();
-	sim_allow_multiple_caching(0);
-	local_irq_restore(flags);
-	put_cpu();
-}
-
-/*
- * Identify large copies from remotely-cached memory, and copy them
- * via memcpy_multicache() if they look good, otherwise fall back
- * to the particular kind of copying passed as the memcpy_t function.
- */
-static unsigned long fast_copy(void *dest, const void *source, int len,
-			       memcpy_t func)
-{
-	/*
-	 * Check if it's big enough to bother with.  We may end up doing a
-	 * small copy via TLB manipulation if we're near a page boundary,
-	 * but presumably we'll make it up when we hit the second page.
-	 */
-	while (len >= LARGE_COPY_CUTOFF) {
-		int copy_size, bytes_left_on_page;
-		pte_t *src_ptep, *dst_ptep;
-		pte_t src_pte, dst_pte;
-		struct page *src_page, *dst_page;
-
-		/* Is the source page oloc'ed to a remote cpu? */
-retry_source:
-		src_ptep = virt_to_pte(current->mm, (unsigned long)source);
-		if (src_ptep == NULL)
-			break;
-		src_pte = *src_ptep;
-		if (!hv_pte_get_present(src_pte) ||
-		    !hv_pte_get_readable(src_pte) ||
-		    hv_pte_get_mode(src_pte) != HV_PTE_MODE_CACHE_TILE_L3)
-			break;
-		if (get_remote_cache_cpu(src_pte) == smp_processor_id())
-			break;
-		src_page = pfn_to_page(pte_pfn(src_pte));
-		get_page(src_page);
-		if (pte_val(src_pte) != pte_val(*src_ptep)) {
-			put_page(src_page);
-			goto retry_source;
-		}
-		if (pte_huge(src_pte)) {
-			/* Adjust the PTE to correspond to a small page */
-			int pfn = pte_pfn(src_pte);
-			pfn += (((unsigned long)source & (HPAGE_SIZE-1))
-				>> PAGE_SHIFT);
-			src_pte = pfn_pte(pfn, src_pte);
-			src_pte = pte_mksmall(src_pte);
-		}
-
-		/* Is the destination page writable? */
-retry_dest:
-		dst_ptep = virt_to_pte(current->mm, (unsigned long)dest);
-		if (dst_ptep == NULL) {
-			put_page(src_page);
-			break;
-		}
-		dst_pte = *dst_ptep;
-		if (!hv_pte_get_present(dst_pte) ||
-		    !hv_pte_get_writable(dst_pte)) {
-			put_page(src_page);
-			break;
-		}
-		dst_page = pfn_to_page(pte_pfn(dst_pte));
-		if (dst_page == src_page) {
-			/*
-			 * Source and dest are on the same page; this
-			 * potentially exposes us to incoherence if any
-			 * part of src and dest overlap on a cache line.
-			 * Just give up rather than trying to be precise.
-			 */
-			put_page(src_page);
-			break;
-		}
-		get_page(dst_page);
-		if (pte_val(dst_pte) != pte_val(*dst_ptep)) {
-			put_page(dst_page);
-			goto retry_dest;
-		}
-		if (pte_huge(dst_pte)) {
-			/* Adjust the PTE to correspond to a small page */
-			int pfn = pte_pfn(dst_pte);
-			pfn += (((unsigned long)dest & (HPAGE_SIZE-1))
-				>> PAGE_SHIFT);
-			dst_pte = pfn_pte(pfn, dst_pte);
-			dst_pte = pte_mksmall(dst_pte);
-		}
-
-		/* All looks good: create a cachable PTE and copy from it */
-		copy_size = len;
-		bytes_left_on_page =
-			PAGE_SIZE - (((int)source) & (PAGE_SIZE-1));
-		if (copy_size > bytes_left_on_page)
-			copy_size = bytes_left_on_page;
-		bytes_left_on_page =
-			PAGE_SIZE - (((int)dest) & (PAGE_SIZE-1));
-		if (copy_size > bytes_left_on_page)
-			copy_size = bytes_left_on_page;
-		memcpy_multicache(dest, source, dst_pte, src_pte, copy_size);
-
-		/* Release the pages */
-		put_page(dst_page);
-		put_page(src_page);
-
-		/* Continue on the next page */
-		dest += copy_size;
-		source += copy_size;
-		len -= copy_size;
-	}
-
-	return func(dest, source, len);
-}
-
-void *memcpy(void *to, const void *from, __kernel_size_t n)
-{
-	if (n < LARGE_COPY_CUTOFF)
-		return (void *)__memcpy_asm(to, from, n);
-	else
-		return (void *)fast_copy(to, from, n, __memcpy_asm);
-}
-
-unsigned long __copy_to_user_inatomic(void __user *to, const void *from,
-				      unsigned long n)
-{
-	if (n < LARGE_COPY_CUTOFF)
-		return __copy_to_user_inatomic_asm(to, from, n);
-	else
-		return fast_copy(to, from, n, __copy_to_user_inatomic_asm);
-}
-
-unsigned long __copy_from_user_inatomic(void *to, const void __user *from,
-					unsigned long n)
-{
-	if (n < LARGE_COPY_CUTOFF)
-		return __copy_from_user_inatomic_asm(to, from, n);
-	else
-		return fast_copy(to, from, n, __copy_from_user_inatomic_asm);
-}
-
-unsigned long __copy_from_user_zeroing(void *to, const void __user *from,
-				       unsigned long n)
-{
-	if (n < LARGE_COPY_CUTOFF)
-		return __copy_from_user_zeroing_asm(to, from, n);
-	else
-		return fast_copy(to, from, n, __copy_from_user_zeroing_asm);
-}
-
-#endif /* !CHIP_HAS_COHERENT_LOCAL_CACHE() */
diff --git a/arch/tile/lib/memcpy_user_64.c b/arch/tile/lib/memcpy_user_64.c
index 37440caa7370..88c7016492c4 100644
--- a/arch/tile/lib/memcpy_user_64.c
+++ b/arch/tile/lib/memcpy_user_64.c
@@ -31,6 +31,7 @@
 		    ".pushsection .coldtext.memcpy,\"ax\";"	\
 		    "2: { move r0, %2; jrp lr };"		\
 		    ".section __ex_table,\"a\";"		\
+		    ".align 8;"					\
 		    ".quad 1b, 2b;"				\
 		    ".popsection"				\
 		    : "=m" (*(p)) : "r" (v), "r" (n));		\
@@ -43,6 +44,7 @@
 		    ".pushsection .coldtext.memcpy,\"ax\";"	\
 		    "2: { move r0, %2; jrp lr };"		\
 		    ".section __ex_table,\"a\";"		\
+		    ".align 8;"					\
 		    ".quad 1b, 2b;"				\
 		    ".popsection"				\
 		    : "=r" (__v) : "m" (*(p)), "r" (n));	\
diff --git a/arch/tile/lib/memset_32.c b/arch/tile/lib/memset_32.c
index 57dbb3a5bff8..2042bfe6595f 100644
--- a/arch/tile/lib/memset_32.c
+++ b/arch/tile/lib/memset_32.c
@@ -12,13 +12,10 @@
  *   more details.
  */
 
-#include <arch/chip.h>
-
 #include <linux/types.h>
 #include <linux/string.h>
 #include <linux/module.h>
-
-#undef memset
+#include <arch/chip.h>
 
 void *memset(void *s, int c, size_t n)
 {
@@ -26,11 +23,7 @@ void *memset(void *s, int c, size_t n)
 	int n32;
 	uint32_t v16, v32;
 	uint8_t *out8 = s;
-#if !CHIP_HAS_WH64()
-	int ahead32;
-#else
 	int to_align32;
-#endif
 
 	/* Experimentation shows that a trivial tight loop is a win up until
 	 * around a size of 20, where writing a word at a time starts to win.
@@ -61,21 +54,6 @@ void *memset(void *s, int c, size_t n)
 		return s;
 	}
 
-#if !CHIP_HAS_WH64()
-	/* Use a spare issue slot to start prefetching the first cache
-	 * line early. This instruction is free as the store can be buried
-	 * in otherwise idle issue slots doing ALU ops.
-	 */
-	__insn_prefetch(out8);
-
-	/* We prefetch the end so that a short memset that spans two cache
-	 * lines gets some prefetching benefit. Again we believe this is free
-	 * to issue.
-	 */
-	__insn_prefetch(&out8[n - 1]);
-#endif /* !CHIP_HAS_WH64() */
-
-
 	/* Align 'out8'. We know n >= 3 so this won't write past the end. */
 	while (((uintptr_t) out8 & 3) != 0) {
 		*out8++ = c;
@@ -96,90 +74,6 @@ void *memset(void *s, int c, size_t n)
 	/* This must be at least 8 or the following loop doesn't work. */
 #define CACHE_LINE_SIZE_IN_WORDS (CHIP_L2_LINE_SIZE() / 4)
 
-#if !CHIP_HAS_WH64()
-
-	ahead32 = CACHE_LINE_SIZE_IN_WORDS;
-
-	/* We already prefetched the first and last cache lines, so
-	 * we only need to do more prefetching if we are storing
-	 * to more than two cache lines.
-	 */
-	if (n32 > CACHE_LINE_SIZE_IN_WORDS * 2) {
-		int i;
-
-		/* Prefetch the next several cache lines.
-		 * This is the setup code for the software-pipelined
-		 * loop below.
-		 */
-#define MAX_PREFETCH 5
-		ahead32 = n32 & -CACHE_LINE_SIZE_IN_WORDS;
-		if (ahead32 > MAX_PREFETCH * CACHE_LINE_SIZE_IN_WORDS)
-			ahead32 = MAX_PREFETCH * CACHE_LINE_SIZE_IN_WORDS;
-
-		for (i = CACHE_LINE_SIZE_IN_WORDS;
-		     i < ahead32; i += CACHE_LINE_SIZE_IN_WORDS)
-			__insn_prefetch(&out32[i]);
-	}
-
-	if (n32 > ahead32) {
-		while (1) {
-			int j;
-
-			/* Prefetch by reading one word several cache lines
-			 * ahead.  Since loads are non-blocking this will
-			 * cause the full cache line to be read while we are
-			 * finishing earlier cache lines.  Using a store
-			 * here causes microarchitectural performance
-			 * problems where a victimizing store miss goes to
-			 * the head of the retry FIFO and locks the pipe for
-			 * a few cycles.  So a few subsequent stores in this
-			 * loop go into the retry FIFO, and then later
-			 * stores see other stores to the same cache line
-			 * are already in the retry FIFO and themselves go
-			 * into the retry FIFO, filling it up and grinding
-			 * to a halt waiting for the original miss to be
-			 * satisfied.
-			 */
-			__insn_prefetch(&out32[ahead32]);
-
-#if CACHE_LINE_SIZE_IN_WORDS % 4 != 0
-#error "Unhandled CACHE_LINE_SIZE_IN_WORDS"
-#endif
-
-			n32 -= CACHE_LINE_SIZE_IN_WORDS;
-
-			/* Save icache space by only partially unrolling
-			 * this loop.
-			 */
-			for (j = CACHE_LINE_SIZE_IN_WORDS / 4; j > 0; j--) {
-				*out32++ = v32;
-				*out32++ = v32;
-				*out32++ = v32;
-				*out32++ = v32;
-			}
-
-			/* To save compiled code size, reuse this loop even
-			 * when we run out of prefetching to do by dropping
-			 * ahead32 down.
-			 */
-			if (n32 <= ahead32) {
-				/* Not even a full cache line left,
-				 * so stop now.
-				 */
-				if (n32 < CACHE_LINE_SIZE_IN_WORDS)
-					break;
-
-				/* Choose a small enough value that we don't
-				 * prefetch past the end.  There's no sense
-				 * in touching cache lines we don't have to.
-				 */
-				ahead32 = CACHE_LINE_SIZE_IN_WORDS - 1;
-			}
-		}
-	}
-
-#else /* CHIP_HAS_WH64() */
-
 	/* Determine how many words we need to emit before the 'out32'
 	 * pointer becomes aligned modulo the cache line size.
 	 */
@@ -236,8 +130,6 @@ void *memset(void *s, int c, size_t n)
 		n32 &= CACHE_LINE_SIZE_IN_WORDS - 1;
 	}
 
-#endif /* CHIP_HAS_WH64() */
-
 	/* Now handle any leftover values. */
 	if (n32 != 0) {
 		do {
diff --git a/arch/tile/lib/memset_64.c b/arch/tile/lib/memset_64.c
index 3873085711d5..03ef69cd73de 100644
--- a/arch/tile/lib/memset_64.c
+++ b/arch/tile/lib/memset_64.c
@@ -12,13 +12,11 @@
  *   more details.
  */
 
-#include <arch/chip.h>
-
 #include <linux/types.h>
 #include <linux/string.h>
 #include <linux/module.h>
-
-#undef memset
+#include <arch/chip.h>
+#include "string-endian.h"
 
 void *memset(void *s, int c, size_t n)
 {
@@ -70,8 +68,7 @@ void *memset(void *s, int c, size_t n)
 	n64 = n >> 3;
 
 	/* Tile input byte out to 64 bits. */
-	/* KLUDGE */
-	v64 = 0x0101010101010101ULL * (uint8_t)c;
+	v64 = copy_byte(c);
 
 	/* This must be at least 8 or the following loop doesn't work. */
 #define CACHE_LINE_SIZE_IN_DOUBLEWORDS (CHIP_L2_LINE_SIZE() / 8)
diff --git a/arch/tile/lib/strchr_32.c b/arch/tile/lib/strchr_32.c
index c94e6f7ae7b5..841fe6963019 100644
--- a/arch/tile/lib/strchr_32.c
+++ b/arch/tile/lib/strchr_32.c
@@ -16,8 +16,6 @@
 #include <linux/string.h>
 #include <linux/module.h>
 
-#undef strchr
-
 char *strchr(const char *s, int c)
 {
 	int z, g;
diff --git a/arch/tile/lib/strchr_64.c b/arch/tile/lib/strchr_64.c
index f39f9dc422b0..fe6e31c06f8d 100644
--- a/arch/tile/lib/strchr_64.c
+++ b/arch/tile/lib/strchr_64.c
@@ -26,7 +26,7 @@ char *strchr(const char *s, int c)
 	const uint64_t *p = (const uint64_t *)(s_int & -8);
 
 	/* Create eight copies of the byte for which we are looking. */
-	const uint64_t goal = 0x0101010101010101ULL * (uint8_t) c;
+	const uint64_t goal = copy_byte(c);
 
 	/* Read the first aligned word, but force bytes before the string to
 	 * match neither zero nor goal (we make sure the high bit of each
diff --git a/arch/tile/lib/string-endian.h b/arch/tile/lib/string-endian.h
index c0eed7ce69c3..2e49cbfe9371 100644
--- a/arch/tile/lib/string-endian.h
+++ b/arch/tile/lib/string-endian.h
@@ -1,5 +1,5 @@
 /*
- * Copyright 2011 Tilera Corporation. All Rights Reserved.
+ * Copyright 2013 Tilera Corporation. All Rights Reserved.
  *
  *   This program is free software; you can redistribute it and/or
  *   modify it under the terms of the GNU General Public License
@@ -31,3 +31,14 @@
 #define CFZ(x) __insn_clz(x)
 #define REVCZ(x) __insn_ctz(x)
 #endif
+
+/*
+ * Create eight copies of the byte in a uint64_t.  Byte Shuffle uses
+ * the bytes of srcB as the index into the dest vector to select a
+ * byte.  With all indices of zero, the first byte is copied into all
+ * the other bytes.
+ */
+static inline uint64_t copy_byte(uint8_t byte)
+{
+	return __insn_shufflebytes(byte, 0, 0);
+}
diff --git a/arch/tile/lib/strlen_32.c b/arch/tile/lib/strlen_32.c
index 4974292a5534..f26f88e11e4a 100644
--- a/arch/tile/lib/strlen_32.c
+++ b/arch/tile/lib/strlen_32.c
@@ -16,8 +16,6 @@
 #include <linux/string.h>
 #include <linux/module.h>
 
-#undef strlen
-
 size_t strlen(const char *s)
 {
 	/* Get an aligned pointer. */
diff --git a/arch/tile/lib/strnlen_32.c b/arch/tile/lib/strnlen_32.c
new file mode 100644
index 000000000000..1434141d9e01
--- /dev/null
+++ b/arch/tile/lib/strnlen_32.c
@@ -0,0 +1,47 @@
+/*
+ * Copyright 2013 Tilera Corporation. All Rights Reserved.
+ *
+ *   This program is free software; you can redistribute it and/or
+ *   modify it under the terms of the GNU General Public License
+ *   as published by the Free Software Foundation, version 2.
+ *
+ *   This program is distributed in the hope that it will be useful, but
+ *   WITHOUT ANY WARRANTY; without even the implied warranty of
+ *   MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ *   NON INFRINGEMENT.  See the GNU General Public License for
+ *   more details.
+ */
+
+#include <linux/types.h>
+#include <linux/string.h>
+#include <linux/module.h>
+
+size_t strnlen(const char *s, size_t count)
+{
+	/* Get an aligned pointer. */
+	const uintptr_t s_int = (uintptr_t) s;
+	const uint32_t *p = (const uint32_t *)(s_int & -4);
+	size_t bytes_read = sizeof(*p) - (s_int & (sizeof(*p) - 1));
+	size_t len;
+	uint32_t v, bits;
+
+	/* Avoid page fault risk by not reading any bytes when count is 0. */
+	if (count == 0)
+		return 0;
+
+	/* Read first word, but force bytes before the string to be nonzero. */
+	v = *p | ((1 << ((s_int << 3) & 31)) - 1);
+
+	while ((bits = __insn_seqb(v, 0)) == 0) {
+		if (bytes_read >= count) {
+			/* Read COUNT bytes and didn't find the terminator. */
+			return count;
+		}
+		v = *++p;
+		bytes_read += sizeof(v);
+	}
+
+	len = ((const char *) p) + (__insn_ctz(bits) >> 3) - s;
+	return (len < count ? len : count);
+}
+EXPORT_SYMBOL(strnlen);
diff --git a/arch/tile/lib/strnlen_64.c b/arch/tile/lib/strnlen_64.c
new file mode 100644
index 000000000000..2e8de6a5136f
--- /dev/null
+++ b/arch/tile/lib/strnlen_64.c
@@ -0,0 +1,48 @@
+/*
+ * Copyright 2013 Tilera Corporation. All Rights Reserved.
+ *
+ *   This program is free software; you can redistribute it and/or
+ *   modify it under the terms of the GNU General Public License
+ *   as published by the Free Software Foundation, version 2.
+ *
+ *   This program is distributed in the hope that it will be useful, but
+ *   WITHOUT ANY WARRANTY; without even the implied warranty of
+ *   MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ *   NON INFRINGEMENT.  See the GNU General Public License for
+ *   more details.
+ */
+
+#include <linux/types.h>
+#include <linux/string.h>
+#include <linux/module.h>
+#include "string-endian.h"
+
+size_t strnlen(const char *s, size_t count)
+{
+	/* Get an aligned pointer. */
+	const uintptr_t s_int = (uintptr_t) s;
+	const uint64_t *p = (const uint64_t *)(s_int & -8);
+	size_t bytes_read = sizeof(*p) - (s_int & (sizeof(*p) - 1));
+	size_t len;
+	uint64_t v, bits;
+
+	/* Avoid page fault risk by not reading any bytes when count is 0. */
+	if (count == 0)
+		return 0;
+
+	/* Read and MASK the first word. */
+	v = *p | MASK(s_int);
+
+	while ((bits = __insn_v1cmpeqi(v, 0)) == 0) {
+		if (bytes_read >= count) {
+			/* Read COUNT bytes and didn't find the terminator. */
+			return count;
+		}
+		v = *++p;
+		bytes_read += sizeof(v);
+	}
+
+	len = ((const char *) p) + (CFZ(bits) >> 3) - s;
+	return (len < count ? len : count);
+}
+EXPORT_SYMBOL(strnlen);
diff --git a/arch/tile/lib/usercopy_32.S b/arch/tile/lib/usercopy_32.S
index b62d002af009..1bc162224638 100644
--- a/arch/tile/lib/usercopy_32.S
+++ b/arch/tile/lib/usercopy_32.S
@@ -36,6 +36,7 @@ strnlen_user_fault:
 	{ move r0, zero; jrp lr }
 	ENDPROC(strnlen_user_fault)
 	.section __ex_table,"a"
+	.align 4
 	.word 1b, strnlen_user_fault
 	.popsection
 
@@ -47,18 +48,20 @@ strnlen_user_fault:
  */
 STD_ENTRY(strncpy_from_user_asm)
 	{ bz r2, 2f; move r3, r0 }
-1:      { lb_u r4, r1; addi r1, r1, 1; addi r2, r2, -1 }
+1:	{ lb_u r4, r1; addi r1, r1, 1; addi r2, r2, -1 }
 	{ sb r0, r4; addi r0, r0, 1 }
-	bz r2, 2f
-	bnzt r4, 1b
-	addi r0, r0, -1   /* don't count the trailing NUL */
-2:      { sub r0, r0, r3; jrp lr }
+	bz r4, 2f
+	bnzt r2, 1b
+	{ sub r0, r0, r3; jrp lr }
+2:	addi r0, r0, -1   /* don't count the trailing NUL */
+	{ sub r0, r0, r3; jrp lr }
 	STD_ENDPROC(strncpy_from_user_asm)
 	.pushsection .fixup,"ax"
 strncpy_from_user_fault:
 	{ movei r0, -EFAULT; jrp lr }
 	ENDPROC(strncpy_from_user_fault)
 	.section __ex_table,"a"
+	.align 4
 	.word 1b, strncpy_from_user_fault
 	.popsection
 
@@ -77,6 +80,7 @@ STD_ENTRY(clear_user_asm)
 	bnzt r1, 1b
 2:      { move r0, r1; jrp lr }
 	.pushsection __ex_table,"a"
+	.align 4
 	.word 1b, 2b
 	.popsection
 
@@ -86,6 +90,7 @@ STD_ENTRY(clear_user_asm)
 2:      { move r0, r1; jrp lr }
 	STD_ENDPROC(clear_user_asm)
 	.pushsection __ex_table,"a"
+	.align 4
 	.word 1b, 2b
 	.popsection
 
@@ -105,25 +110,7 @@ STD_ENTRY(flush_user_asm)
 2:      { move r0, r1; jrp lr }
 	STD_ENDPROC(flush_user_asm)
 	.pushsection __ex_table,"a"
-	.word 1b, 2b
-	.popsection
-
-/*
- * inv_user_asm takes the user target address in r0 and the
- * number of bytes to invalidate in r1.
- * It returns the number of not inv'able bytes (hopefully zero) in r0.
- */
-STD_ENTRY(inv_user_asm)
-	bz r1, 2f
-	{ movei r2, L2_CACHE_BYTES; add r1, r0, r1 }
-	{ sub r2, zero, r2; addi r1, r1, L2_CACHE_BYTES-1 }
-	{ and r0, r0, r2; and r1, r1, r2 }
-	{ sub r1, r1, r0 }
-1:      { inv r0; addi r1, r1, -CHIP_INV_STRIDE() }
-	{ addi r0, r0, CHIP_INV_STRIDE(); bnzt r1, 1b }
-2:      { move r0, r1; jrp lr }
-	STD_ENDPROC(inv_user_asm)
-	.pushsection __ex_table,"a"
+	.align 4
 	.word 1b, 2b
 	.popsection
 
@@ -143,5 +130,6 @@ STD_ENTRY(finv_user_asm)
 2:      { move r0, r1; jrp lr }
 	STD_ENDPROC(finv_user_asm)
 	.pushsection __ex_table,"a"
+	.align 4
 	.word 1b, 2b
 	.popsection
diff --git a/arch/tile/lib/usercopy_64.S b/arch/tile/lib/usercopy_64.S
index adb2dbbc70cd..b3b31a3306f8 100644
--- a/arch/tile/lib/usercopy_64.S
+++ b/arch/tile/lib/usercopy_64.S
@@ -36,6 +36,7 @@ strnlen_user_fault:
 	{ move r0, zero; jrp lr }
 	ENDPROC(strnlen_user_fault)
 	.section __ex_table,"a"
+	.align 8
 	.quad 1b, strnlen_user_fault
 	.popsection
 
@@ -47,18 +48,20 @@ strnlen_user_fault:
  */
 STD_ENTRY(strncpy_from_user_asm)
 	{ beqz r2, 2f; move r3, r0 }
-1:      { ld1u r4, r1; addi r1, r1, 1; addi r2, r2, -1 }
+1:	{ ld1u r4, r1; addi r1, r1, 1; addi r2, r2, -1 }
 	{ st1 r0, r4; addi r0, r0, 1 }
-	beqz r2, 2f
-	bnezt r4, 1b
-	addi r0, r0, -1   /* don't count the trailing NUL */
-2:      { sub r0, r0, r3; jrp lr }
+	beqz r4, 2f
+	bnezt r2, 1b
+	{ sub r0, r0, r3; jrp lr }
+2:	addi r0, r0, -1   /* don't count the trailing NUL */
+	{ sub r0, r0, r3; jrp lr }
 	STD_ENDPROC(strncpy_from_user_asm)
 	.pushsection .fixup,"ax"
 strncpy_from_user_fault:
 	{ movei r0, -EFAULT; jrp lr }
 	ENDPROC(strncpy_from_user_fault)
 	.section __ex_table,"a"
+	.align 8
 	.quad 1b, strncpy_from_user_fault
 	.popsection
 
@@ -77,6 +80,7 @@ STD_ENTRY(clear_user_asm)
 	bnezt r1, 1b
 2:      { move r0, r1; jrp lr }
 	.pushsection __ex_table,"a"
+	.align 8
 	.quad 1b, 2b
 	.popsection
 
@@ -86,6 +90,7 @@ STD_ENTRY(clear_user_asm)
 2:      { move r0, r1; jrp lr }
 	STD_ENDPROC(clear_user_asm)
 	.pushsection __ex_table,"a"
+	.align 8
 	.quad 1b, 2b
 	.popsection
 
@@ -105,25 +110,7 @@ STD_ENTRY(flush_user_asm)
 2:      { move r0, r1; jrp lr }
 	STD_ENDPROC(flush_user_asm)
 	.pushsection __ex_table,"a"
-	.quad 1b, 2b
-	.popsection
-
-/*
- * inv_user_asm takes the user target address in r0 and the
- * number of bytes to invalidate in r1.
- * It returns the number of not inv'able bytes (hopefully zero) in r0.
- */
-STD_ENTRY(inv_user_asm)
-	beqz r1, 2f
-	{ movei r2, L2_CACHE_BYTES; add r1, r0, r1 }
-	{ sub r2, zero, r2; addi r1, r1, L2_CACHE_BYTES-1 }
-	{ and r0, r0, r2; and r1, r1, r2 }
-	{ sub r1, r1, r0 }
-1:      { inv r0; addi r1, r1, -CHIP_INV_STRIDE() }
-	{ addi r0, r0, CHIP_INV_STRIDE(); bnezt r1, 1b }
-2:      { move r0, r1; jrp lr }
-	STD_ENDPROC(inv_user_asm)
-	.pushsection __ex_table,"a"
+	.align 8
 	.quad 1b, 2b
 	.popsection
 
@@ -143,5 +130,6 @@ STD_ENTRY(finv_user_asm)
 2:      { move r0, r1; jrp lr }
 	STD_ENDPROC(finv_user_asm)
 	.pushsection __ex_table,"a"
+	.align 8
 	.quad 1b, 2b
 	.popsection
diff --git a/arch/tile/mm/elf.c b/arch/tile/mm/elf.c
index 743c951c61b0..23f044e8a7ab 100644
--- a/arch/tile/mm/elf.c
+++ b/arch/tile/mm/elf.c
@@ -21,7 +21,8 @@
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
 #include <asm/sections.h>
-#include <arch/sim_def.h>
+#include <asm/vdso.h>
+#include <arch/sim.h>
 
 /* Notify a running simulator, if any, that an exec just occurred. */
 static void sim_notify_exec(const char *binary_name)
@@ -38,21 +39,55 @@ static void sim_notify_exec(const char *binary_name)
 
 static int notify_exec(struct mm_struct *mm)
 {
-	int retval = 0;  /* failure */
-
-	if (mm->exe_file) {
-		char *buf = (char *) __get_free_page(GFP_KERNEL);
-		if (buf) {
-			char *path = d_path(&mm->exe_file->f_path,
-					    buf, PAGE_SIZE);
-			if (!IS_ERR(path)) {
-				sim_notify_exec(path);
-				retval = 1;
-			}
-			free_page((unsigned long)buf);
+	char *buf, *path;
+	struct vm_area_struct *vma;
+
+	if (!sim_is_simulator())
+		return 1;
+
+	if (mm->exe_file == NULL)
+		return 0;
+
+	for (vma = current->mm->mmap; ; vma = vma->vm_next) {
+		if (vma == NULL)
+			return 0;
+		if (vma->vm_file == mm->exe_file)
+			break;
+	}
+
+	buf = (char *) __get_free_page(GFP_KERNEL);
+	if (buf == NULL)
+		return 0;
+
+	path = d_path(&mm->exe_file->f_path, buf, PAGE_SIZE);
+	if (IS_ERR(path)) {
+		free_page((unsigned long)buf);
+		return 0;
+	}
+
+	/*
+	 * Notify simulator of an ET_DYN object so we know the load address.
+	 * The somewhat cryptic overuse of SIM_CONTROL_DLOPEN allows us
+	 * to be backward-compatible with older simulator releases.
+	 */
+	if (vma->vm_start == (ELF_ET_DYN_BASE & PAGE_MASK)) {
+		char buf[64];
+		int i;
+
+		snprintf(buf, sizeof(buf), "0x%lx:@", vma->vm_start);
+		for (i = 0; ; ++i) {
+			char c = buf[i];
+			__insn_mtspr(SPR_SIM_CONTROL,
+				     (SIM_CONTROL_DLOPEN
+				      | (c << _SIM_CONTROL_OPERATOR_BITS)));
+			if (c == '\0')
+				break;
 		}
 	}
-	return retval;
+
+	sim_notify_exec(path);
+	free_page((unsigned long)buf);
+	return 1;
 }
 
 /* Notify a running simulator, if any, that we loaded an interpreter. */
@@ -68,37 +103,10 @@ static void sim_notify_interp(unsigned long load_addr)
 }
 
 
-/* Kernel address of page used to map read-only kernel data into userspace. */
-static void *vdso_page;
-
-/* One-entry array used for install_special_mapping. */
-static struct page *vdso_pages[1];
-
-static int __init vdso_setup(void)
-{
-	vdso_page = (void *)get_zeroed_page(GFP_ATOMIC);
-	memcpy(vdso_page, __rt_sigreturn, __rt_sigreturn_end - __rt_sigreturn);
-	vdso_pages[0] = virt_to_page(vdso_page);
-	return 0;
-}
-device_initcall(vdso_setup);
-
-const char *arch_vma_name(struct vm_area_struct *vma)
-{
-	if (vma->vm_private_data == vdso_pages)
-		return "[vdso]";
-#ifndef __tilegx__
-	if (vma->vm_start == MEM_USER_INTRPT)
-		return "[intrpt]";
-#endif
-	return NULL;
-}
-
 int arch_setup_additional_pages(struct linux_binprm *bprm,
 				int executable_stack)
 {
 	struct mm_struct *mm = current->mm;
-	unsigned long vdso_base;
 	int retval = 0;
 
 	down_write(&mm->mmap_sem);
@@ -111,14 +119,7 @@ int arch_setup_additional_pages(struct linux_binprm *bprm,
 	if (!notify_exec(mm))
 		sim_notify_exec(bprm->filename);
 
-	/*
-	 * MAYWRITE to allow gdb to COW and set breakpoints
-	 */
-	vdso_base = VDSO_BASE;
-	retval = install_special_mapping(mm, vdso_base, PAGE_SIZE,
-					 VM_READ|VM_EXEC|
-					 VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
-					 vdso_pages);
+	retval = setup_vdso_pages();
 
 #ifndef __tilegx__
 	/*
diff --git a/arch/tile/mm/fault.c b/arch/tile/mm/fault.c
index f7f99f90cbe0..6c0571216a9d 100644
--- a/arch/tile/mm/fault.c
+++ b/arch/tile/mm/fault.c
@@ -34,6 +34,7 @@
 #include <linux/hugetlb.h>
 #include <linux/syscalls.h>
 #include <linux/uaccess.h>
+#include <linux/kdebug.h>
 
 #include <asm/pgalloc.h>
 #include <asm/sections.h>
@@ -122,10 +123,9 @@ static inline pmd_t *vmalloc_sync_one(pgd_t *pgd, unsigned long address)
 	pmd_k = pmd_offset(pud_k, address);
 	if (!pmd_present(*pmd_k))
 		return NULL;
-	if (!pmd_present(*pmd)) {
+	if (!pmd_present(*pmd))
 		set_pmd(pmd, *pmd_k);
-		arch_flush_lazy_mmu_mode();
-	} else
+	else
 		BUG_ON(pmd_ptfn(*pmd) != pmd_ptfn(*pmd_k));
 	return pmd_k;
 }
@@ -149,8 +149,6 @@ static inline int vmalloc_fault(pgd_t *pgd, unsigned long address)
 	pmd_k = vmalloc_sync_one(pgd, address);
 	if (!pmd_k)
 		return -1;
-	if (pmd_huge(*pmd_k))
-		return 0;   /* support TILE huge_vmap() API */
 	pte_k = pte_offset_kernel(pmd_k, address);
 	if (!pte_present(*pte_k))
 		return -1;
@@ -280,10 +278,9 @@ static int handle_page_fault(struct pt_regs *regs,
 	if (!is_page_fault)
 		write = 1;
 
-	flags = (FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
-		 (write ? FAULT_FLAG_WRITE : 0));
+	flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
 
-	is_kernel_mode = (EX1_PL(regs->ex1) != USER_PL);
+	is_kernel_mode = !user_mode(regs);
 
 	tsk = validate_current();
 
@@ -365,6 +362,9 @@ static int handle_page_fault(struct pt_regs *regs,
 		goto bad_area_nosemaphore;
 	}
 
+	if (!is_kernel_mode)
+		flags |= FAULT_FLAG_USER;
+
 	/*
 	 * When running in the kernel we expect faults to occur only to
 	 * addresses in user space.  All other faults represent errors in the
@@ -425,12 +425,12 @@ good_area:
 #endif
 		if (!(vma->vm_flags & VM_WRITE))
 			goto bad_area;
+		flags |= FAULT_FLAG_WRITE;
 	} else {
 		if (!is_page_fault || !(vma->vm_flags & VM_READ))
 			goto bad_area;
 	}
 
- survive:
 	/*
 	 * If for any reason at all we couldn't handle the fault,
 	 * make sure we exit gracefully rather than endlessly redo
@@ -466,28 +466,15 @@ good_area:
 		}
 	}
 
-#if CHIP_HAS_TILE_DMA() || CHIP_HAS_SN_PROC()
-	/*
-	 * If this was an asynchronous fault,
-	 * restart the appropriate engine.
-	 */
-	switch (fault_num) {
 #if CHIP_HAS_TILE_DMA()
+	/* If this was a DMA TLB fault, restart the DMA engine. */
+	switch (fault_num) {
 	case INT_DMATLB_MISS:
 	case INT_DMATLB_MISS_DWNCL:
 	case INT_DMATLB_ACCESS:
 	case INT_DMATLB_ACCESS_DWNCL:
 		__insn_mtspr(SPR_DMA_CTR, SPR_DMA_CTR__REQUEST_MASK);
 		break;
-#endif
-#if CHIP_HAS_SN_PROC()
-	case INT_SNITLB_MISS:
-	case INT_SNITLB_MISS_DWNCL:
-		__insn_mtspr(SPR_SNCTL,
-			     __insn_mfspr(SPR_SNCTL) &
-			     ~SPR_SNCTL__FRZPROC_MASK);
-		break;
-#endif
 	}
 #endif
 
@@ -568,11 +555,6 @@ no_context:
  */
 out_of_memory:
 	up_read(&mm->mmap_sem);
-	if (is_global_init(tsk)) {
-		yield();
-		down_read(&mm->mmap_sem);
-		goto survive;
-	}
 	if (is_kernel_mode)
 		goto no_context;
 	pagefault_out_of_memory();
@@ -722,8 +704,60 @@ void do_page_fault(struct pt_regs *regs, int fault_num,
 {
 	int is_page_fault;
 
+#ifdef CONFIG_KPROBES
+	/*
+	 * This is to notify the fault handler of the kprobes.  The
+	 * exception code is redundant as it is also carried in REGS,
+	 * but we pass it anyhow.
+	 */
+	if (notify_die(DIE_PAGE_FAULT, "page fault", regs, -1,
+		       regs->faultnum, SIGSEGV) == NOTIFY_STOP)
+		return;
+#endif
+
+#ifdef __tilegx__
+	/*
+	 * We don't need early do_page_fault_ics() support, since unlike
+	 * Pro we don't need to worry about unlocking the atomic locks.
+	 * There is only one current case in GX where we touch any memory
+	 * under ICS other than our own kernel stack, and we handle that
+	 * here.  (If we crash due to trying to touch our own stack,
+	 * we're in too much trouble for C code to help out anyway.)
+	 */
+	if (write & ~1) {
+		unsigned long pc = write & ~1;
+		if (pc >= (unsigned long) __start_unalign_asm_code &&
+		    pc < (unsigned long) __end_unalign_asm_code) {
+			struct thread_info *ti = current_thread_info();
+			/*
+			 * Our EX_CONTEXT is still what it was from the
+			 * initial unalign exception, but now we've faulted
+			 * on the JIT page.  We would like to complete the
+			 * page fault however is appropriate, and then retry
+			 * the instruction that caused the unalign exception.
+			 * Our state has been "corrupted" by setting the low
+			 * bit in "sp", and stashing r0..r3 in the
+			 * thread_info area, so we revert all of that, then
+			 * continue as if this were a normal page fault.
+			 */
+			regs->sp &= ~1UL;
+			regs->regs[0] = ti->unalign_jit_tmp[0];
+			regs->regs[1] = ti->unalign_jit_tmp[1];
+			regs->regs[2] = ti->unalign_jit_tmp[2];
+			regs->regs[3] = ti->unalign_jit_tmp[3];
+			write &= 1;
+		} else {
+			pr_alert("%s/%d: ICS set at page fault at %#lx: %#lx\n",
+				 current->comm, current->pid, pc, address);
+			show_regs(regs);
+			do_group_exit(SIGKILL);
+			return;
+		}
+	}
+#else
 	/* This case should have been handled by do_page_fault_ics(). */
 	BUG_ON(write & ~1);
+#endif
 
 #if CHIP_HAS_TILE_DMA()
 	/*
@@ -752,10 +786,6 @@ void do_page_fault(struct pt_regs *regs, int fault_num,
 	case INT_DMATLB_MISS:
 	case INT_DMATLB_MISS_DWNCL:
 #endif
-#if CHIP_HAS_SN_PROC()
-	case INT_SNITLB_MISS:
-	case INT_SNITLB_MISS_DWNCL:
-#endif
 		is_page_fault = 1;
 		break;
 
@@ -771,8 +801,8 @@ void do_page_fault(struct pt_regs *regs, int fault_num,
 		panic("Bad fault number %d in do_page_fault", fault_num);
 	}
 
-#if CHIP_HAS_TILE_DMA() || CHIP_HAS_SN_PROC()
-	if (EX1_PL(regs->ex1) != USER_PL) {
+#if CHIP_HAS_TILE_DMA()
+	if (!user_mode(regs)) {
 		struct async_tlb *async;
 		switch (fault_num) {
 #if CHIP_HAS_TILE_DMA()
@@ -783,12 +813,6 @@ void do_page_fault(struct pt_regs *regs, int fault_num,
 			async = &current->thread.dma_async_tlb;
 			break;
 #endif
-#if CHIP_HAS_SN_PROC()
-		case INT_SNITLB_MISS:
-		case INT_SNITLB_MISS_DWNCL:
-			async = &current->thread.sn_async_tlb;
-			break;
-#endif
 		default:
 			async = NULL;
 		}
@@ -821,14 +845,22 @@ void do_page_fault(struct pt_regs *regs, int fault_num,
 }
 
 
-#if CHIP_HAS_TILE_DMA() || CHIP_HAS_SN_PROC()
+#if CHIP_HAS_TILE_DMA()
 /*
- * Check an async_tlb structure to see if a deferred fault is waiting,
- * and if so pass it to the page-fault code.
+ * This routine effectively re-issues asynchronous page faults
+ * when we are returning to user space.
  */
-static void handle_async_page_fault(struct pt_regs *regs,
-				    struct async_tlb *async)
+void do_async_page_fault(struct pt_regs *regs)
 {
+	struct async_tlb *async = &current->thread.dma_async_tlb;
+
+	/*
+	 * Clear thread flag early.  If we re-interrupt while processing
+	 * code here, we will reset it and recall this routine before
+	 * returning to user space.
+	 */
+	clear_thread_flag(TIF_ASYNC_TLB);
+
 	if (async->fault_num) {
 		/*
 		 * Clear async->fault_num before calling the page-fault
@@ -842,35 +874,15 @@ static void handle_async_page_fault(struct pt_regs *regs,
 				  async->address, async->is_write);
 	}
 }
-
-/*
- * This routine effectively re-issues asynchronous page faults
- * when we are returning to user space.
- */
-void do_async_page_fault(struct pt_regs *regs)
-{
-	/*
-	 * Clear thread flag early.  If we re-interrupt while processing
-	 * code here, we will reset it and recall this routine before
-	 * returning to user space.
-	 */
-	clear_thread_flag(TIF_ASYNC_TLB);
-
-#if CHIP_HAS_TILE_DMA()
-	handle_async_page_fault(regs, &current->thread.dma_async_tlb);
-#endif
-#if CHIP_HAS_SN_PROC()
-	handle_async_page_fault(regs, &current->thread.sn_async_tlb);
-#endif
-}
-#endif /* CHIP_HAS_TILE_DMA() || CHIP_HAS_SN_PROC() */
+#endif /* CHIP_HAS_TILE_DMA() */
 
 
 void vmalloc_sync_all(void)
 {
 #ifdef __tilegx__
 	/* Currently all L1 kernel pmd's are static and shared. */
-	BUG_ON(pgd_index(VMALLOC_END) != pgd_index(VMALLOC_START));
+	BUILD_BUG_ON(pgd_index(VMALLOC_END - PAGE_SIZE) !=
+		     pgd_index(VMALLOC_START));
 #else
 	/*
 	 * Note that races in the updates of insync and start aren't
diff --git a/arch/tile/mm/highmem.c b/arch/tile/mm/highmem.c
index 347d123b14be..0dc218294770 100644
--- a/arch/tile/mm/highmem.c
+++ b/arch/tile/mm/highmem.c
@@ -114,7 +114,6 @@ static void kmap_atomic_register(struct page *page, int type,
 
 	list_add(&amp->list, &amp_list);
 	set_pte(ptep, pteval);
-	arch_flush_lazy_mmu_mode();
 
 	spin_unlock(&amp_lock);
 	homecache_kpte_unlock(flags);
@@ -259,7 +258,6 @@ void __kunmap_atomic(void *kvaddr)
 		BUG_ON(vaddr >= (unsigned long)high_memory);
 	}
 
-	arch_flush_lazy_mmu_mode();
 	pagefault_enable();
 }
 EXPORT_SYMBOL(__kunmap_atomic);
diff --git a/arch/tile/mm/homecache.c b/arch/tile/mm/homecache.c
index 1ae911939a18..004ba568d93f 100644
--- a/arch/tile/mm/homecache.c
+++ b/arch/tile/mm/homecache.c
@@ -43,12 +43,9 @@
 #include "migrate.h"
 
 
-#if CHIP_HAS_COHERENT_LOCAL_CACHE()
-
 /*
  * The noallocl2 option suppresses all use of the L2 cache to cache
- * locally from a remote home.  There's no point in using it if we
- * don't have coherent local caching, though.
+ * locally from a remote home.
  */
 static int __write_once noallocl2;
 static int __init set_noallocl2(char *str)
@@ -58,12 +55,6 @@ static int __init set_noallocl2(char *str)
 }
 early_param("noallocl2", set_noallocl2);
 
-#else
-
-#define noallocl2 0
-
-#endif
-
 
 /*
  * Update the irq_stat for cpus that we are going to interrupt
@@ -172,7 +163,8 @@ void flush_remote(unsigned long cache_pfn, unsigned long cache_control,
 
 static void homecache_finv_page_va(void* va, int home)
 {
-	if (home == smp_processor_id()) {
+	int cpu = get_cpu();
+	if (home == cpu) {
 		finv_buffer_local(va, PAGE_SIZE);
 	} else if (home == PAGE_HOME_HASH) {
 		finv_buffer_remote(va, PAGE_SIZE, 1);
@@ -180,6 +172,7 @@ static void homecache_finv_page_va(void* va, int home)
 		BUG_ON(home < 0 || home >= NR_CPUS);
 		finv_buffer_remote(va, PAGE_SIZE, 0);
 	}
+	put_cpu();
 }
 
 void homecache_finv_map_page(struct page *page, int home)
@@ -198,7 +191,7 @@ void homecache_finv_map_page(struct page *page, int home)
 #else
 	va = __fix_to_virt(FIX_HOMECACHE_BEGIN + smp_processor_id());
 #endif
-	ptep = virt_to_pte(NULL, (unsigned long)va);
+	ptep = virt_to_kpte(va);
 	pte = pfn_pte(page_to_pfn(page), PAGE_KERNEL);
 	__set_pte(ptep, pte_set_home(pte, home));
 	homecache_finv_page_va((void *)va, home);
@@ -263,10 +256,8 @@ static int pte_to_home(pte_t pte)
 		return PAGE_HOME_INCOHERENT;
 	case HV_PTE_MODE_UNCACHED:
 		return PAGE_HOME_UNCACHED;
-#if CHIP_HAS_CBOX_HOME_MAP()
 	case HV_PTE_MODE_CACHE_HASH_L3:
 		return PAGE_HOME_HASH;
-#endif
 	}
 	panic("Bad PTE %#llx\n", pte.val);
 }
@@ -323,20 +314,16 @@ pte_t pte_set_home(pte_t pte, int home)
 						      HV_PTE_MODE_CACHE_NO_L3);
 			}
 		} else
-#if CHIP_HAS_CBOX_HOME_MAP()
 		if (hash_default)
 			pte = hv_pte_set_mode(pte, HV_PTE_MODE_CACHE_HASH_L3);
 		else
-#endif
 			pte = hv_pte_set_mode(pte, HV_PTE_MODE_CACHE_NO_L3);
 		pte = hv_pte_set_nc(pte);
 		break;
 
-#if CHIP_HAS_CBOX_HOME_MAP()
 	case PAGE_HOME_HASH:
 		pte = hv_pte_set_mode(pte, HV_PTE_MODE_CACHE_HASH_L3);
 		break;
-#endif
 
 	default:
 		BUG_ON(home < 0 || home >= NR_CPUS ||
@@ -346,7 +333,6 @@ pte_t pte_set_home(pte_t pte, int home)
 		break;
 	}
 
-#if CHIP_HAS_NC_AND_NOALLOC_BITS()
 	if (noallocl2)
 		pte = hv_pte_set_no_alloc_l2(pte);
 
@@ -355,7 +341,6 @@ pte_t pte_set_home(pte_t pte, int home)
 	    hv_pte_get_mode(pte) == HV_PTE_MODE_CACHE_NO_L3) {
 		pte = hv_pte_set_mode(pte, HV_PTE_MODE_UNCACHED);
 	}
-#endif
 
 	/* Checking this case here gives a better panic than from the hv. */
 	BUG_ON(hv_pte_get_mode(pte) == 0);
@@ -371,19 +356,13 @@ EXPORT_SYMBOL(pte_set_home);
  * so they're not suitable for anything but infrequent use.
  */
 
-#if CHIP_HAS_CBOX_HOME_MAP()
-static inline int initial_page_home(void) { return PAGE_HOME_HASH; }
-#else
-static inline int initial_page_home(void) { return 0; }
-#endif
-
 int page_home(struct page *page)
 {
 	if (PageHighMem(page)) {
-		return initial_page_home();
+		return PAGE_HOME_HASH;
 	} else {
 		unsigned long kva = (unsigned long)page_address(page);
-		return pte_to_home(*virt_to_pte(NULL, kva));
+		return pte_to_home(*virt_to_kpte(kva));
 	}
 }
 EXPORT_SYMBOL(page_home);
@@ -402,7 +381,7 @@ void homecache_change_page_home(struct page *page, int order, int home)
 		     NULL, 0);
 
 	for (i = 0; i < pages; ++i, kva += PAGE_SIZE) {
-		pte_t *ptep = virt_to_pte(NULL, kva);
+		pte_t *ptep = virt_to_kpte(kva);
 		pte_t pteval = *ptep;
 		BUG_ON(!pte_present(pteval) || pte_huge(pteval));
 		__set_pte(ptep, pte_set_home(pteval, home));
@@ -436,7 +415,7 @@ struct page *homecache_alloc_pages_node(int nid, gfp_t gfp_mask,
 void __homecache_free_pages(struct page *page, unsigned int order)
 {
 	if (put_page_testzero(page)) {
-		homecache_change_page_home(page, order, initial_page_home());
+		homecache_change_page_home(page, order, PAGE_HOME_HASH);
 		if (order == 0) {
 			free_hot_cold_page(page, 0);
 		} else {
diff --git a/arch/tile/mm/hugetlbpage.c b/arch/tile/mm/hugetlbpage.c
index 650ccff8378c..0cb3bbaa580c 100644
--- a/arch/tile/mm/hugetlbpage.c
+++ b/arch/tile/mm/hugetlbpage.c
@@ -49,38 +49,6 @@ int huge_shift[HUGE_SHIFT_ENTRIES] = {
 #endif
 };
 
-/*
- * This routine is a hybrid of pte_alloc_map() and pte_alloc_kernel().
- * It assumes that L2 PTEs are never in HIGHMEM (we don't support that).
- * It locks the user pagetable, and bumps up the mm->nr_ptes field,
- * but otherwise allocate the page table using the kernel versions.
- */
-static pte_t *pte_alloc_hugetlb(struct mm_struct *mm, pmd_t *pmd,
-				unsigned long address)
-{
-	pte_t *new;
-
-	if (pmd_none(*pmd)) {
-		new = pte_alloc_one_kernel(mm, address);
-		if (!new)
-			return NULL;
-
-		smp_wmb(); /* See comment in __pte_alloc */
-
-		spin_lock(&mm->page_table_lock);
-		if (likely(pmd_none(*pmd))) {  /* Has another populated it ? */
-			mm->nr_ptes++;
-			pmd_populate_kernel(mm, pmd, new);
-			new = NULL;
-		} else
-			VM_BUG_ON(pmd_trans_splitting(*pmd));
-		spin_unlock(&mm->page_table_lock);
-		if (new)
-			pte_free_kernel(mm, new);
-	}
-
-	return pte_offset_kernel(pmd, address);
-}
 #endif
 
 pte_t *huge_pte_alloc(struct mm_struct *mm,
@@ -109,7 +77,7 @@ pte_t *huge_pte_alloc(struct mm_struct *mm,
 		else {
 			if (sz != PAGE_SIZE << huge_shift[HUGE_SHIFT_PAGE])
 				panic("Unexpected page size %#lx\n", sz);
-			return pte_alloc_hugetlb(mm, pmd, addr);
+			return pte_alloc_map(mm, NULL, pmd, addr);
 		}
 	}
 #else
@@ -144,14 +112,14 @@ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
 
 	/* Get the top-level page table entry. */
 	pgd = (pgd_t *)get_pte((pte_t *)mm->pgd, pgd_index(addr), 0);
-	if (!pgd_present(*pgd))
-		return NULL;
 
 	/* We don't have four levels. */
 	pud = pud_offset(pgd, addr);
 #ifndef __PAGETABLE_PUD_FOLDED
 # error support fourth page table level
 #endif
+	if (!pud_present(*pud))
+		return NULL;
 
 	/* Check for an L0 huge PTE, if we have three levels. */
 #ifndef __PAGETABLE_PMD_FOLDED
@@ -198,6 +166,11 @@ int pud_huge(pud_t pud)
 	return !!(pud_val(pud) & _PAGE_HUGE_PAGE);
 }
 
+int pmd_huge_support(void)
+{
+	return 1;
+}
+
 struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address,
 			     pmd_t *pmd, int write)
 {
diff --git a/arch/tile/mm/init.c b/arch/tile/mm/init.c
index e182958c707d..0fa1acfac79a 100644
--- a/arch/tile/mm/init.c
+++ b/arch/tile/mm/init.c
@@ -106,10 +106,8 @@ pte_t *get_prealloc_pte(unsigned long pfn)
  */
 static int initial_heap_home(void)
 {
-#if CHIP_HAS_CBOX_HOME_MAP()
 	if (hash_default)
 		return PAGE_HOME_HASH;
-#endif
 	return smp_processor_id();
 }
 
@@ -190,14 +188,11 @@ static void __init page_table_range_init(unsigned long start,
 }
 
 
-#if CHIP_HAS_CBOX_HOME_MAP()
-
 static int __initdata ktext_hash = 1;  /* .text pages */
 static int __initdata kdata_hash = 1;  /* .data and .bss pages */
 int __write_once hash_default = 1;     /* kernel allocator pages */
 EXPORT_SYMBOL(hash_default);
 int __write_once kstack_hash = 1;      /* if no homecaching, use h4h */
-#endif /* CHIP_HAS_CBOX_HOME_MAP */
 
 /*
  * CPUs to use to for striping the pages of kernel data.  If hash-for-home
@@ -215,14 +210,12 @@ int __write_once kdata_huge;       /* if no homecaching, small pages */
 static pgprot_t __init construct_pgprot(pgprot_t prot, int home)
 {
 	prot = pte_set_home(prot, home);
-#if CHIP_HAS_CBOX_HOME_MAP()
 	if (home == PAGE_HOME_IMMUTABLE) {
 		if (ktext_hash)
 			prot = hv_pte_set_mode(prot, HV_PTE_MODE_CACHE_HASH_L3);
 		else
 			prot = hv_pte_set_mode(prot, HV_PTE_MODE_CACHE_NO_L3);
 	}
-#endif
 	return prot;
 }
 
@@ -234,22 +227,17 @@ static pgprot_t __init init_pgprot(ulong address)
 {
 	int cpu;
 	unsigned long page;
-	enum { CODE_DELTA = MEM_SV_INTRPT - PAGE_OFFSET };
+	enum { CODE_DELTA = MEM_SV_START - PAGE_OFFSET };
 
-#if CHIP_HAS_CBOX_HOME_MAP()
 	/* For kdata=huge, everything is just hash-for-home. */
 	if (kdata_huge)
 		return construct_pgprot(PAGE_KERNEL, PAGE_HOME_HASH);
-#endif
 
 	/* We map the aliased pages of permanent text inaccessible. */
 	if (address < (ulong) _sinittext - CODE_DELTA)
 		return PAGE_NONE;
 
-	/*
-	 * We map read-only data non-coherent for performance.  We could
-	 * use neighborhood caching on TILE64, but it's not clear it's a win.
-	 */
+	/* We map read-only data non-coherent for performance. */
 	if ((address >= (ulong) __start_rodata &&
 	     address < (ulong) __end_rodata) ||
 	    address == (ulong) empty_zero_page) {
@@ -257,12 +245,10 @@ static pgprot_t __init init_pgprot(ulong address)
 	}
 
 #ifndef __tilegx__
-#if !ATOMIC_LOCKS_FOUND_VIA_TABLE()
 	/* Force the atomic_locks[] array page to be hash-for-home. */
 	if (address == (ulong) atomic_locks)
 		return construct_pgprot(PAGE_KERNEL, PAGE_HOME_HASH);
 #endif
-#endif
 
 	/*
 	 * Everything else that isn't data or bss is heap, so mark it
@@ -280,19 +266,9 @@ static pgprot_t __init init_pgprot(ulong address)
 	if (address >= (ulong) _end || address < (ulong) _einitdata)
 		return construct_pgprot(PAGE_KERNEL, initial_heap_home());
 
-#if CHIP_HAS_CBOX_HOME_MAP()
 	/* Use hash-for-home if requested for data/bss. */
 	if (kdata_hash)
 		return construct_pgprot(PAGE_KERNEL, PAGE_HOME_HASH);
-#endif
-
-	/*
-	 * Make the w1data homed like heap to start with, to avoid
-	 * making it part of the page-striped data area when we're just
-	 * going to convert it to read-only soon anyway.
-	 */
-	if (address >= (ulong)__w1data_begin && address < (ulong)__w1data_end)
-		return construct_pgprot(PAGE_KERNEL, initial_heap_home());
 
 	/*
 	 * Otherwise we just hand out consecutive cpus.  To avoid
@@ -301,7 +277,7 @@ static pgprot_t __init init_pgprot(ulong address)
 	 * the requested address, while walking cpu home around kdata_mask.
 	 * This is typically no more than a dozen or so iterations.
 	 */
-	page = (((ulong)__w1data_end) + PAGE_SIZE - 1) & PAGE_MASK;
+	page = (((ulong)__end_rodata) + PAGE_SIZE - 1) & PAGE_MASK;
 	BUG_ON(address < page || address >= (ulong)_end);
 	cpu = cpumask_first(&kdata_mask);
 	for (; page < address; page += PAGE_SIZE) {
@@ -311,11 +287,9 @@ static pgprot_t __init init_pgprot(ulong address)
 		if (page == (ulong)empty_zero_page)
 			continue;
 #ifndef __tilegx__
-#if !ATOMIC_LOCKS_FOUND_VIA_TABLE()
 		if (page == (ulong)atomic_locks)
 			continue;
 #endif
-#endif
 		cpu = cpumask_next(cpu, &kdata_mask);
 		if (cpu == NR_CPUS)
 			cpu = cpumask_first(&kdata_mask);
@@ -358,7 +332,7 @@ static int __init setup_ktext(char *str)
 
 	ktext_arg_seen = 1;
 
-	/* Default setting on Tile64: use a huge page */
+	/* Default setting: use a huge page */
 	if (strcmp(str, "huge") == 0)
 		pr_info("ktext: using one huge locally cached page\n");
 
@@ -404,10 +378,8 @@ static inline pgprot_t ktext_set_nocache(pgprot_t prot)
 {
 	if (!ktext_nocache)
 		prot = hv_pte_set_nc(prot);
-#if CHIP_HAS_NC_AND_NOALLOC_BITS()
 	else
 		prot = hv_pte_set_no_alloc_l2(prot);
-#endif
 	return prot;
 }
 
@@ -440,7 +412,6 @@ static void __init kernel_physical_mapping_init(pgd_t *pgd_base)
 	struct cpumask kstripe_mask;
 	int rc, i;
 
-#if CHIP_HAS_CBOX_HOME_MAP()
 	if (ktext_arg_seen && ktext_hash) {
 		pr_warning("warning: \"ktext\" boot argument ignored"
 			   " if \"kcache_hash\" sets up text hash-for-home\n");
@@ -457,7 +428,6 @@ static void __init kernel_physical_mapping_init(pgd_t *pgd_base)
 			  " kcache_hash=all or =allbutstack\n");
 		kdata_huge = 0;
 	}
-#endif
 
 	/*
 	 * Set up a mask for cpus to use for kernel striping.
@@ -538,7 +508,7 @@ static void __init kernel_physical_mapping_init(pgd_t *pgd_base)
 		}
 	}
 
-	address = MEM_SV_INTRPT;
+	address = MEM_SV_START;
 	pmd = get_pmd(pgtables, address);
 	pfn = 0;  /* code starts at PA 0 */
 	if (ktext_small) {
@@ -585,13 +555,11 @@ static void __init kernel_physical_mapping_init(pgd_t *pgd_base)
 	} else {
 		pte_t pteval = pfn_pte(0, PAGE_KERNEL_EXEC);
 		pteval = pte_mkhuge(pteval);
-#if CHIP_HAS_CBOX_HOME_MAP()
 		if (ktext_hash) {
 			pteval = hv_pte_set_mode(pteval,
 						 HV_PTE_MODE_CACHE_HASH_L3);
 			pteval = ktext_set_nocache(pteval);
 		} else
-#endif /* CHIP_HAS_CBOX_HOME_MAP() */
 		if (cpumask_weight(&ktext_mask) == 1) {
 			pteval = set_remote_cache_cpu(pteval,
 					      cpumask_first(&ktext_mask));
@@ -777,10 +745,7 @@ void __init paging_init(void)
 
 	kernel_physical_mapping_init(pgd_base);
 
-	/*
-	 * Fixed mappings, only the page table structure has to be
-	 * created - mappings will be set by set_fixmap():
-	 */
+	/* Fixed mappings, only the page table structure has to be created. */
 	page_table_range_init(fix_to_virt(__end_of_fixed_addresses - 1),
 			      FIXADDR_TOP, pgd_base);
 
@@ -863,10 +828,6 @@ void __init mem_init(void)
 	printk(KERN_DEBUG "  PKMAP   %#lx - %#lx\n",
 	       PKMAP_BASE, PKMAP_ADDR(LAST_PKMAP) - 1);
 #endif
-#ifdef CONFIG_HUGEVMAP
-	printk(KERN_DEBUG "  HUGEMAP %#lx - %#lx\n",
-	       HUGE_VMAP_BASE, HUGE_VMAP_END - 1);
-#endif
 	printk(KERN_DEBUG "  VMALLOC %#lx - %#lx\n",
 	       _VMALLOC_START, _VMALLOC_END - 1);
 #ifdef __tilegx__
@@ -941,26 +902,6 @@ void __init pgtable_cache_init(void)
 		panic("pgtable_cache_init(): Cannot create pgd cache");
 }
 
-#if !CHIP_HAS_COHERENT_LOCAL_CACHE()
-/*
- * The __w1data area holds data that is only written during initialization,
- * and is read-only and thus freely cacheable thereafter.  Fix the page
- * table entries that cover that region accordingly.
- */
-static void mark_w1data_ro(void)
-{
-	/* Loop over page table entries */
-	unsigned long addr = (unsigned long)__w1data_begin;
-	BUG_ON((addr & (PAGE_SIZE-1)) != 0);
-	for (; addr <= (unsigned long)__w1data_end - 1; addr += PAGE_SIZE) {
-		unsigned long pfn = kaddr_to_pfn((void *)addr);
-		pte_t *ptep = virt_to_pte(NULL, addr);
-		BUG_ON(pte_huge(*ptep));   /* not relevant for kdata_huge */
-		set_pte_at(&init_mm, addr, ptep, pfn_pte(pfn, PAGE_KERNEL_RO));
-	}
-}
-#endif
-
 #ifdef CONFIG_DEBUG_PAGEALLOC
 static long __write_once initfree;
 #else
@@ -1000,7 +941,7 @@ static void free_init_pages(char *what, unsigned long begin, unsigned long end)
 		 */
 		int pfn = kaddr_to_pfn((void *)addr);
 		struct page *page = pfn_to_page(pfn);
-		pte_t *ptep = virt_to_pte(NULL, addr);
+		pte_t *ptep = virt_to_kpte(addr);
 		if (!initfree) {
 			/*
 			 * If debugging page accesses then do not free
@@ -1024,15 +965,11 @@ static void free_init_pages(char *what, unsigned long begin, unsigned long end)
 
 void free_initmem(void)
 {
-	const unsigned long text_delta = MEM_SV_INTRPT - PAGE_OFFSET;
+	const unsigned long text_delta = MEM_SV_START - PAGE_OFFSET;
 
 	/*
-	 * Evict the dirty initdata on the boot cpu, evict the w1data
-	 * wherever it's homed, and evict all the init code everywhere.
-	 * We are guaranteed that no one will touch the init pages any
-	 * more, and although other cpus may be touching the w1data,
-	 * we only actually change the caching on tile64, which won't
-	 * be keeping local copies in the other tiles' caches anyway.
+	 * Evict the cache on all cores to avoid incoherence.
+	 * We are guaranteed that no one will touch the init pages any more.
 	 */
 	homecache_evict(&cpu_cacheable_map);
 
@@ -1043,26 +980,11 @@ void free_initmem(void)
 
 	/*
 	 * Free the pages mapped from 0xc0000000 that correspond to code
-	 * pages from MEM_SV_INTRPT that we won't use again after init.
+	 * pages from MEM_SV_START that we won't use again after init.
 	 */
 	free_init_pages("unused kernel text",
 			(unsigned long)_sinittext - text_delta,
 			(unsigned long)_einittext - text_delta);
-
-#if !CHIP_HAS_COHERENT_LOCAL_CACHE()
-	/*
-	 * Upgrade the .w1data section to globally cached.
-	 * We don't do this on tilepro, since the cache architecture
-	 * pretty much makes it irrelevant, and in any case we end
-	 * up having racing issues with other tiles that may touch
-	 * the data after we flush the cache but before we update
-	 * the PTEs and flush the TLBs, causing sharer shootdowns
-	 * later.  Even though this is to clean data, it seems like
-	 * an unnecessary complication.
-	 */
-	mark_w1data_ro();
-#endif
-
 	/* Do a global TLB flush so everyone sees the changes. */
 	flush_tlb_all();
 }
diff --git a/arch/tile/mm/migrate_32.S b/arch/tile/mm/migrate_32.S
index 5305814bf187..772085491bf9 100644
--- a/arch/tile/mm/migrate_32.S
+++ b/arch/tile/mm/migrate_32.S
@@ -136,7 +136,7 @@ STD_ENTRY(flush_and_install_context)
 	 move r8, zero  /* asids */
 	 move r9, zero  /* asidcount */
 	}
-	jal hv_flush_remote
+	jal _hv_flush_remote
 	bnz r0, .Ldone
 
 	/* Now install the new page table. */
@@ -152,7 +152,7 @@ STD_ENTRY(flush_and_install_context)
 	 move r4, r_asid
 	 moveli r5, HV_CTX_DIRECTIO | CTX_PAGE_FLAG
 	}
-	jal hv_install_context
+	jal _hv_install_context
 	bnz r0, .Ldone
 
 	/* Finally, flush the TLB. */
diff --git a/arch/tile/mm/migrate_64.S b/arch/tile/mm/migrate_64.S
index 1d15b10833d1..a49eee38f872 100644
--- a/arch/tile/mm/migrate_64.S
+++ b/arch/tile/mm/migrate_64.S
@@ -123,7 +123,7 @@ STD_ENTRY(flush_and_install_context)
 	}
 	{
 	 move r8, zero  /* asidcount */
-	 jal hv_flush_remote
+	 jal _hv_flush_remote
 	}
 	bnez r0, 1f
 
@@ -136,7 +136,7 @@ STD_ENTRY(flush_and_install_context)
 	 move r2, r_asid
 	 moveli r3, HV_CTX_DIRECTIO | CTX_PAGE_FLAG
 	}
-	jal hv_install_context
+	jal _hv_install_context
 	bnez r0, 1f
 
 	/* Finally, flush the TLB. */
diff --git a/arch/tile/mm/mmap.c b/arch/tile/mm/mmap.c
index d67d91ebf63e..851a94e6ae58 100644
--- a/arch/tile/mm/mmap.c
+++ b/arch/tile/mm/mmap.c
@@ -58,16 +58,36 @@ void arch_pick_mmap_layout(struct mm_struct *mm)
 #else
 	int is_32bit = 0;
 #endif
+	unsigned long random_factor = 0UL;
+
+	/*
+	 *  8 bits of randomness in 32bit mmaps, 24 address space bits
+	 * 12 bits of randomness in 64bit mmaps, 28 address space bits
+	 */
+	if (current->flags & PF_RANDOMIZE) {
+		if (is_32bit)
+			random_factor = get_random_int() % (1<<8);
+		else
+			random_factor = get_random_int() % (1<<12);
+
+		random_factor <<= PAGE_SHIFT;
+	}
 
 	/*
 	 * Use standard layout if the expected stack growth is unlimited
 	 * or we are running native 64 bits.
 	 */
-	if (!is_32bit || rlimit(RLIMIT_STACK) == RLIM_INFINITY) {
-		mm->mmap_base = TASK_UNMAPPED_BASE;
+	if (rlimit(RLIMIT_STACK) == RLIM_INFINITY) {
+		mm->mmap_base = TASK_UNMAPPED_BASE + random_factor;
 		mm->get_unmapped_area = arch_get_unmapped_area;
 	} else {
 		mm->mmap_base = mmap_base(mm);
 		mm->get_unmapped_area = arch_get_unmapped_area_topdown;
 	}
 }
+
+unsigned long arch_randomize_brk(struct mm_struct *mm)
+{
+	unsigned long range_end = mm->brk + 0x02000000;
+	return randomize_range(mm->brk, range_end, 0) ? : mm->brk;
+}
diff --git a/arch/tile/mm/pgtable.c b/arch/tile/mm/pgtable.c
index dfd63ce87327..4fd9ec0b58ed 100644
--- a/arch/tile/mm/pgtable.c
+++ b/arch/tile/mm/pgtable.c
@@ -83,55 +83,6 @@ void show_mem(unsigned int filter)
 	}
 }
 
-/*
- * Associate a virtual page frame with a given physical page frame
- * and protection flags for that frame.
- */
-static void set_pte_pfn(unsigned long vaddr, unsigned long pfn, pgprot_t flags)
-{
-	pgd_t *pgd;
-	pud_t *pud;
-	pmd_t *pmd;
-	pte_t *pte;
-
-	pgd = swapper_pg_dir + pgd_index(vaddr);
-	if (pgd_none(*pgd)) {
-		BUG();
-		return;
-	}
-	pud = pud_offset(pgd, vaddr);
-	if (pud_none(*pud)) {
-		BUG();
-		return;
-	}
-	pmd = pmd_offset(pud, vaddr);
-	if (pmd_none(*pmd)) {
-		BUG();
-		return;
-	}
-	pte = pte_offset_kernel(pmd, vaddr);
-	/* <pfn,flags> stored as-is, to permit clearing entries */
-	set_pte(pte, pfn_pte(pfn, flags));
-
-	/*
-	 * It's enough to flush this one mapping.
-	 * This appears conservative since it is only called
-	 * from __set_fixmap.
-	 */
-	local_flush_tlb_page(NULL, vaddr, PAGE_SIZE);
-}
-
-void __set_fixmap(enum fixed_addresses idx, unsigned long phys, pgprot_t flags)
-{
-	unsigned long address = __fix_to_virt(idx);
-
-	if (idx >= __end_of_fixed_addresses) {
-		BUG();
-		return;
-	}
-	set_pte_pfn(address, phys >> PAGE_SHIFT, flags);
-}
-
 /**
  * shatter_huge_page() - ensure a given address is mapped by a small page.
  *
@@ -176,8 +127,7 @@ void shatter_huge_page(unsigned long addr)
 	}
 
 	/* Shatter the huge page into the preallocated L2 page table. */
-	pmd_populate_kernel(&init_mm, pmd,
-			    get_prealloc_pte(pte_pfn(*(pte_t *)pmd)));
+	pmd_populate_kernel(&init_mm, pmd, get_prealloc_pte(pmd_pfn(*pmd)));
 
 #ifdef __PAGETABLE_PMD_FOLDED
 	/* Walk every pgd on the system and update the pmd there. */
@@ -374,6 +324,17 @@ void ptep_set_wrprotect(struct mm_struct *mm,
 
 #endif
 
+/*
+ * Return a pointer to the PTE that corresponds to the given
+ * address in the given page table.  A NULL page table just uses
+ * the standard kernel page table; the preferred API in this case
+ * is virt_to_kpte().
+ *
+ * The returned pointer can point to a huge page in other levels
+ * of the page table than the bottom, if the huge page is present
+ * in the page table.  For bottom-level PTEs, the returned pointer
+ * can point to a PTE that is either present or not.
+ */
 pte_t *virt_to_pte(struct mm_struct* mm, unsigned long addr)
 {
 	pgd_t *pgd;
@@ -387,13 +348,23 @@ pte_t *virt_to_pte(struct mm_struct* mm, unsigned long addr)
 	pud = pud_offset(pgd, addr);
 	if (!pud_present(*pud))
 		return NULL;
+	if (pud_huge_page(*pud))
+		return (pte_t *)pud;
 	pmd = pmd_offset(pud, addr);
-	if (pmd_huge_page(*pmd))
-		return (pte_t *)pmd;
 	if (!pmd_present(*pmd))
 		return NULL;
+	if (pmd_huge_page(*pmd))
+		return (pte_t *)pmd;
 	return pte_offset_kernel(pmd, addr);
 }
+EXPORT_SYMBOL(virt_to_pte);
+
+pte_t *virt_to_kpte(unsigned long kaddr)
+{
+	BUG_ON(kaddr < PAGE_OFFSET);
+	return virt_to_pte(NULL, kaddr);
+}
+EXPORT_SYMBOL(virt_to_kpte);
 
 pgprot_t set_remote_cache_cpu(pgprot_t prot, int cpu)
 {
@@ -568,7 +539,7 @@ void __iomem *ioremap_prot(resource_size_t phys_addr, unsigned long size,
 	addr = area->addr;
 	if (ioremap_page_range((unsigned long)addr, (unsigned long)addr + size,
 			       phys_addr, pgprot)) {
-		remove_vm_area((void *)(PAGE_MASK & (unsigned long) addr));
+		free_vm_area(area);
 		return NULL;
 	}
 	return (__force void __iomem *) (offset + (char *)addr);
diff --git a/arch/um/Kconfig.common b/arch/um/Kconfig.common
index bceee6623b00..8ddea1f8006a 100644
--- a/arch/um/Kconfig.common
+++ b/arch/um/Kconfig.common
@@ -6,7 +6,6 @@ config DEFCONFIG_LIST
 config UML
 	bool
 	default y
-	select HAVE_GENERIC_HARDIRQS
 	select HAVE_UID16
 	select GENERIC_IRQ_SHOW
 	select GENERIC_CPU_DEVICES
diff --git a/arch/um/defconfig b/arch/um/defconfig
index 08107a795062..2665e6b683f5 100644
--- a/arch/um/defconfig
+++ b/arch/um/defconfig
@@ -129,12 +129,10 @@ CONFIG_BSD_PROCESS_ACCT=y
 # CONFIG_FHANDLE is not set
 # CONFIG_TASKSTATS is not set
 # CONFIG_AUDIT is not set
-CONFIG_HAVE_GENERIC_HARDIRQS=y
 
 #
 # IRQ subsystem
 #
-CONFIG_GENERIC_HARDIRQS=y
 CONFIG_GENERIC_IRQ_SHOW=y
 
 #
diff --git a/arch/um/drivers/ubd.h b/arch/um/drivers/ubd.h
index 3845051f1b10..3b48cd2081ee 100644
--- a/arch/um/drivers/ubd.h
+++ b/arch/um/drivers/ubd.h
@@ -7,7 +7,6 @@
 #ifndef __UM_UBD_USER_H
 #define __UM_UBD_USER_H
 
-extern void ignore_sigwinch_sig(void);
 extern int start_io_thread(unsigned long sp, int *fds_out);
 extern int io_thread(void *arg);
 extern int kernel_fd;
diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c
index 879990cb66c6..3716e6952554 100644
--- a/arch/um/drivers/ubd_kern.c
+++ b/arch/um/drivers/ubd_kern.c
@@ -41,7 +41,7 @@
 #include <os.h>
 #include "cow.h"
 
-enum ubd_req { UBD_READ, UBD_WRITE };
+enum ubd_req { UBD_READ, UBD_WRITE, UBD_FLUSH };
 
 struct io_thread_req {
 	struct request *req;
@@ -866,6 +866,7 @@ static int ubd_add(int n, char **error_out)
 		goto out;
 	}
 	ubd_dev->queue->queuedata = ubd_dev;
+	blk_queue_flush(ubd_dev->queue, REQ_FLUSH);
 
 	blk_queue_max_segments(ubd_dev->queue, MAX_SG);
 	err = ubd_disk_register(UBD_MAJOR, ubd_dev->size, n, &ubd_gendisk[n]);
@@ -1239,11 +1240,40 @@ static void prepare_request(struct request *req, struct io_thread_req *io_req,
 }
 
 /* Called with dev->lock held */
+static void prepare_flush_request(struct request *req,
+				  struct io_thread_req *io_req)
+{
+	struct gendisk *disk = req->rq_disk;
+	struct ubd *ubd_dev = disk->private_data;
+
+	io_req->req = req;
+	io_req->fds[0] = (ubd_dev->cow.file != NULL) ? ubd_dev->cow.fd :
+		ubd_dev->fd;
+	io_req->op = UBD_FLUSH;
+}
+
+static bool submit_request(struct io_thread_req *io_req, struct ubd *dev)
+{
+	int n = os_write_file(thread_fd, &io_req,
+			     sizeof(io_req));
+	if (n != sizeof(io_req)) {
+		if (n != -EAGAIN)
+			printk("write to io thread failed, "
+			       "errno = %d\n", -n);
+		else if (list_empty(&dev->restart))
+			list_add(&dev->restart, &restart);
+
+		kfree(io_req);
+		return false;
+	}
+	return true;
+}
+
+/* Called with dev->lock held */
 static void do_ubd_request(struct request_queue *q)
 {
 	struct io_thread_req *io_req;
 	struct request *req;
-	int n;
 
 	while(1){
 		struct ubd *dev = q->queuedata;
@@ -1259,6 +1289,19 @@ static void do_ubd_request(struct request_queue *q)
 		}
 
 		req = dev->request;
+
+		if (req->cmd_flags & REQ_FLUSH) {
+			io_req = kmalloc(sizeof(struct io_thread_req),
+					 GFP_ATOMIC);
+			if (io_req == NULL) {
+				if (list_empty(&dev->restart))
+					list_add(&dev->restart, &restart);
+				return;
+			}
+			prepare_flush_request(req, io_req);
+			submit_request(io_req, dev);
+		}
+
 		while(dev->start_sg < dev->end_sg){
 			struct scatterlist *sg = &dev->sg[dev->start_sg];
 
@@ -1273,17 +1316,8 @@ static void do_ubd_request(struct request_queue *q)
 					(unsigned long long)dev->rq_pos << 9,
 					sg->offset, sg->length, sg_page(sg));
 
-			n = os_write_file(thread_fd, &io_req,
-					  sizeof(struct io_thread_req *));
-			if(n != sizeof(struct io_thread_req *)){
-				if(n != -EAGAIN)
-					printk("write to io thread failed, "
-					       "errno = %d\n", -n);
-				else if(list_empty(&dev->restart))
-					list_add(&dev->restart, &restart);
-				kfree(io_req);
+			if (submit_request(io_req, dev) == false)
 				return;
-			}
 
 			dev->rq_pos += sg->length >> 9;
 			dev->start_sg++;
@@ -1367,6 +1401,17 @@ static void do_io(struct io_thread_req *req)
 	int err;
 	__u64 off;
 
+	if (req->op == UBD_FLUSH) {
+		/* fds[0] is always either the rw image or our cow file */
+		n = os_sync_file(req->fds[0]);
+		if (n != 0) {
+			printk("do_io - sync failed err = %d "
+			       "fd = %d\n", -n, req->fds[0]);
+			req->error = 1;
+		}
+		return;
+	}
+
 	nsectors = req->length / req->sectorsize;
 	start = 0;
 	do {
@@ -1431,7 +1476,8 @@ int io_thread(void *arg)
 	struct io_thread_req *req;
 	int n;
 
-	ignore_sigwinch_sig();
+	os_fix_helper_signals();
+
 	while(1){
 		n = os_read_file(kernel_fd, &req,
 				 sizeof(struct io_thread_req *));
diff --git a/arch/um/drivers/ubd_user.c b/arch/um/drivers/ubd_user.c
index a703e45d8aac..e376f9b9c68d 100644
--- a/arch/um/drivers/ubd_user.c
+++ b/arch/um/drivers/ubd_user.c
@@ -21,11 +21,6 @@
 #include "ubd.h"
 #include <os.h>
 
-void ignore_sigwinch_sig(void)
-{
-	signal(SIGWINCH, SIG_IGN);
-}
-
 int start_io_thread(unsigned long sp, int *fd_out)
 {
 	int pid, fds[2], err;
diff --git a/arch/um/include/shared/os.h b/arch/um/include/shared/os.h
index 95feaa47a2fb..021104d98cb3 100644
--- a/arch/um/include/shared/os.h
+++ b/arch/um/include/shared/os.h
@@ -141,6 +141,7 @@ extern int os_seek_file(int fd, unsigned long long offset);
 extern int os_open_file(const char *file, struct openflags flags, int mode);
 extern int os_read_file(int fd, void *buf, int len);
 extern int os_write_file(int fd, const void *buf, int count);
+extern int os_sync_file(int fd);
 extern int os_file_size(const char *file, unsigned long long *size_out);
 extern int os_file_modtime(const char *file, unsigned long *modtime);
 extern int os_pipe(int *fd, int stream, int close_on_exec);
@@ -200,6 +201,7 @@ extern int os_unmap_memory(void *addr, int len);
 extern int os_drop_memory(void *addr, int length);
 extern int can_drop_memory(void);
 extern void os_flush_stdout(void);
+extern int os_mincore(void *addr, unsigned long len);
 
 /* execvp.c */
 extern int execvp_noalloc(char *buf, const char *file, char *const argv[]);
@@ -233,6 +235,7 @@ extern void setup_machinename(char *machine_out);
 extern void setup_hostinfo(char *buf, int len);
 extern void os_dump_core(void) __attribute__ ((noreturn));
 extern void um_early_printk(const char *s, unsigned int n);
+extern void os_fix_helper_signals(void);
 
 /* time.c */
 extern void idle_sleep(unsigned long long nsecs);
diff --git a/arch/um/kernel/Makefile b/arch/um/kernel/Makefile
index babe21826e3e..d8b78a03855c 100644
--- a/arch/um/kernel/Makefile
+++ b/arch/um/kernel/Makefile
@@ -13,7 +13,7 @@ clean-files :=
 obj-y = config.o exec.o exitcode.o irq.o ksyms.o mem.o \
 	physmem.o process.o ptrace.o reboot.o sigio.o \
 	signal.o smp.o syscall.o sysrq.o time.o tlb.o trap.o \
-	um_arch.o umid.o skas/
+	um_arch.o umid.o maccess.o skas/
 
 obj-$(CONFIG_BLK_DEV_INITRD) += initrd.o
 obj-$(CONFIG_GPROF)	+= gprof_syms.o
diff --git a/arch/um/kernel/irq.c b/arch/um/kernel/irq.c
index 36e12f0cefd5..1d8505b1e290 100644
--- a/arch/um/kernel/irq.c
+++ b/arch/um/kernel/irq.c
@@ -337,6 +337,8 @@ static struct irq_chip normal_irq_type = {
 	.irq_disable = dummy,
 	.irq_enable = dummy,
 	.irq_ack = dummy,
+	.irq_mask = dummy,
+	.irq_unmask = dummy,
 };
 
 static struct irq_chip SIGVTALRM_irq_type = {
@@ -344,6 +346,8 @@ static struct irq_chip SIGVTALRM_irq_type = {
 	.irq_disable = dummy,
 	.irq_enable = dummy,
 	.irq_ack = dummy,
+	.irq_mask = dummy,
+	.irq_unmask = dummy,
 };
 
 void __init init_IRQ(void)
diff --git a/arch/um/kernel/maccess.c b/arch/um/kernel/maccess.c
new file mode 100644
index 000000000000..1f3d5c4910d1
--- /dev/null
+++ b/arch/um/kernel/maccess.c
@@ -0,0 +1,24 @@
+/*
+ * Copyright (C) 2013 Richard Weinberger <richrd@nod.at>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/uaccess.h>
+#include <linux/kernel.h>
+#include <os.h>
+
+long probe_kernel_read(void *dst, const void *src, size_t size)
+{
+	void *psrc = (void *)rounddown((unsigned long)src, PAGE_SIZE);
+
+	if ((unsigned long)src < PAGE_SIZE || size <= 0)
+		return -EFAULT;
+
+	if (os_mincore(psrc, size + src - psrc) <= 0)
+		return -EFAULT;
+
+	return __probe_kernel_read(dst, src, size);
+}
diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c
index 089f3987e273..5c3aef74237f 100644
--- a/arch/um/kernel/trap.c
+++ b/arch/um/kernel/trap.c
@@ -30,8 +30,7 @@ int handle_page_fault(unsigned long address, unsigned long ip,
 	pmd_t *pmd;
 	pte_t *pte;
 	int err = -EFAULT;
-	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
-				 (is_write ? FAULT_FLAG_WRITE : 0);
+	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
 
 	*code_out = SEGV_MAPERR;
 
@@ -42,6 +41,8 @@ int handle_page_fault(unsigned long address, unsigned long ip,
 	if (in_atomic())
 		goto out_nosemaphore;
 
+	if (is_user)
+		flags |= FAULT_FLAG_USER;
 retry:
 	down_read(&mm->mmap_sem);
 	vma = find_vma(mm, address);
@@ -58,12 +59,15 @@ retry:
 
 good_area:
 	*code_out = SEGV_ACCERR;
-	if (is_write && !(vma->vm_flags & VM_WRITE))
-		goto out;
-
-	/* Don't require VM_READ|VM_EXEC for write faults! */
-	if (!is_write && !(vma->vm_flags & (VM_READ | VM_EXEC)))
-		goto out;
+	if (is_write) {
+		if (!(vma->vm_flags & VM_WRITE))
+			goto out;
+		flags |= FAULT_FLAG_WRITE;
+	} else {
+		/* Don't require VM_READ|VM_EXEC for write faults! */
+		if (!(vma->vm_flags & (VM_READ | VM_EXEC)))
+			goto out;
+	}
 
 	do {
 		int fault;
@@ -124,6 +128,8 @@ out_of_memory:
 	 * (which will retry the fault, or kill us if we got oom-killed).
 	 */
 	up_read(&mm->mmap_sem);
+	if (!is_user)
+		goto out_nosemaphore;
 	pagefault_out_of_memory();
 	return 0;
 }
diff --git a/arch/um/os-Linux/aio.c b/arch/um/os-Linux/aio.c
index 3a6bc2af0961..014eb35fd13b 100644
--- a/arch/um/os-Linux/aio.c
+++ b/arch/um/os-Linux/aio.c
@@ -104,8 +104,7 @@ static int aio_thread(void *arg)
 	struct io_event event;
 	int err, n, reply_fd;
 
-	signal(SIGWINCH, SIG_IGN);
-
+	os_fix_helper_signals();
 	while (1) {
 		n = io_getevents(ctx, 1, 1, &event, NULL);
 		if (n < 0) {
@@ -173,7 +172,7 @@ static int not_aio_thread(void *arg)
 	struct aio_thread_reply reply;
 	int err;
 
-	signal(SIGWINCH, SIG_IGN);
+	os_fix_helper_signals();
 	while (1) {
 		err = read(aio_req_fd_r, &req, sizeof(req));
 		if (err != sizeof(req)) {
diff --git a/arch/um/os-Linux/file.c b/arch/um/os-Linux/file.c
index c17bd6f7d674..07a750197bb0 100644
--- a/arch/um/os-Linux/file.c
+++ b/arch/um/os-Linux/file.c
@@ -266,6 +266,15 @@ int os_write_file(int fd, const void *buf, int len)
 	return n;
 }
 
+int os_sync_file(int fd)
+{
+	int n = fsync(fd);
+
+	if (n < 0)
+		return -errno;
+	return n;
+}
+
 int os_file_size(const char *file, unsigned long long *size_out)
 {
 	struct uml_stat buf;
diff --git a/arch/um/os-Linux/main.c b/arch/um/os-Linux/main.c
index 749c96da7b99..e1704ff600ff 100644
--- a/arch/um/os-Linux/main.c
+++ b/arch/um/os-Linux/main.c
@@ -123,6 +123,8 @@ int __init main(int argc, char **argv, char **envp)
 
 	setup_env_path();
 
+	setsid();
+
 	new_argv = malloc((argc + 1) * sizeof(char *));
 	if (new_argv == NULL) {
 		perror("Mallocing argv");
diff --git a/arch/um/os-Linux/process.c b/arch/um/os-Linux/process.c
index b8f34c9e53ae..33496fe2bb52 100644
--- a/arch/um/os-Linux/process.c
+++ b/arch/um/os-Linux/process.c
@@ -4,6 +4,7 @@
  */
 
 #include <stdio.h>
+#include <stdlib.h>
 #include <unistd.h>
 #include <errno.h>
 #include <signal.h>
@@ -232,6 +233,57 @@ out:
 	return ok;
 }
 
+static int os_page_mincore(void *addr)
+{
+	char vec[2];
+	int ret;
+
+	ret = mincore(addr, UM_KERN_PAGE_SIZE, vec);
+	if (ret < 0) {
+		if (errno == ENOMEM || errno == EINVAL)
+			return 0;
+		else
+			return -errno;
+	}
+
+	return vec[0] & 1;
+}
+
+int os_mincore(void *addr, unsigned long len)
+{
+	char *vec;
+	int ret, i;
+
+	if (len <= UM_KERN_PAGE_SIZE)
+		return os_page_mincore(addr);
+
+	vec = calloc(1, (len + UM_KERN_PAGE_SIZE - 1) / UM_KERN_PAGE_SIZE);
+	if (!vec)
+		return -ENOMEM;
+
+	ret = mincore(addr, UM_KERN_PAGE_SIZE, vec);
+	if (ret < 0) {
+		if (errno == ENOMEM || errno == EINVAL)
+			ret = 0;
+		else
+			ret = -errno;
+
+		goto out;
+	}
+
+	for (i = 0; i < ((len + UM_KERN_PAGE_SIZE - 1) / UM_KERN_PAGE_SIZE); i++) {
+		if (!(vec[i] & 1)) {
+			ret = 0;
+			goto out;
+		}
+	}
+
+	ret = 1;
+out:
+	free(vec);
+	return ret;
+}
+
 void init_new_thread_signals(void)
 {
 	set_handler(SIGSEGV);
@@ -242,5 +294,4 @@ void init_new_thread_signals(void)
 	signal(SIGHUP, SIG_IGN);
 	set_handler(SIGIO);
 	signal(SIGWINCH, SIG_IGN);
-	signal(SIGTERM, SIG_DFL);
 }
diff --git a/arch/um/os-Linux/sigio.c b/arch/um/os-Linux/sigio.c
index 8b61cc0e82c8..46e762f926eb 100644
--- a/arch/um/os-Linux/sigio.c
+++ b/arch/um/os-Linux/sigio.c
@@ -55,7 +55,7 @@ static int write_sigio_thread(void *unused)
 	int i, n, respond_fd;
 	char c;
 
-	signal(SIGWINCH, SIG_IGN);
+	os_fix_helper_signals();
 	fds = &current_poll;
 	while (1) {
 		n = poll(fds->poll, fds->used, -1);
diff --git a/arch/um/os-Linux/util.c b/arch/um/os-Linux/util.c
index 492ef5e6e166..faee55ef6d2f 100644
--- a/arch/um/os-Linux/util.c
+++ b/arch/um/os-Linux/util.c
@@ -94,6 +94,16 @@ static inline void __attribute__ ((noreturn)) uml_abort(void)
 			exit(127);
 }
 
+/*
+ * UML helper threads must not handle SIGWINCH/INT/TERM
+ */
+void os_fix_helper_signals(void)
+{
+	signal(SIGWINCH, SIG_IGN);
+	signal(SIGINT, SIG_DFL);
+	signal(SIGTERM, SIG_DFL);
+}
+
 void os_dump_core(void)
 {
 	int pid;
diff --git a/arch/unicore32/Kconfig b/arch/unicore32/Kconfig
index 41bcc0013442..82cdd8906f3d 100644
--- a/arch/unicore32/Kconfig
+++ b/arch/unicore32/Kconfig
@@ -2,7 +2,6 @@ config UNICORE32
 	def_bool y
 	select HAVE_MEMBLOCK
 	select HAVE_GENERIC_DMA_COHERENT
-	select HAVE_GENERIC_HARDIRQS
 	select HAVE_DMA_ATTRS
 	select HAVE_KERNEL_GZIP
 	select HAVE_KERNEL_BZIP2
diff --git a/arch/unicore32/mm/fault.c b/arch/unicore32/mm/fault.c
index f9b5c10bccee..0dc922dba915 100644
--- a/arch/unicore32/mm/fault.c
+++ b/arch/unicore32/mm/fault.c
@@ -209,8 +209,7 @@ static int do_pf(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 	struct task_struct *tsk;
 	struct mm_struct *mm;
 	int fault, sig, code;
-	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
-				 ((!(fsr ^ 0x12)) ? FAULT_FLAG_WRITE : 0);
+	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
 
 	tsk = current;
 	mm = tsk->mm;
@@ -222,6 +221,11 @@ static int do_pf(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 	if (in_atomic() || !mm)
 		goto no_context;
 
+	if (user_mode(regs))
+		flags |= FAULT_FLAG_USER;
+	if (!(fsr ^ 0x12))
+		flags |= FAULT_FLAG_WRITE;
+
 	/*
 	 * As per x86, we may deadlock here.  However, since the kernel only
 	 * validly references user space from well defined areas of the code,
@@ -278,6 +282,13 @@ retry:
 	       (VM_FAULT_ERROR | VM_FAULT_BADMAP | VM_FAULT_BADACCESS))))
 		return 0;
 
+	/*
+	 * If we are in kernel mode at this point, we
+	 * have no context to handle this fault with.
+	 */
+	if (!user_mode(regs))
+		goto no_context;
+
 	if (fault & VM_FAULT_OOM) {
 		/*
 		 * We ran out of memory, call the OOM killer, and return to
@@ -288,13 +299,6 @@ retry:
 		return 0;
 	}
 
-	/*
-	 * If we are in kernel mode at this point, we
-	 * have no context to handle this fault with.
-	 */
-	if (!user_mode(regs))
-		goto no_context;
-
 	if (fault & VM_FAULT_SIGBUS) {
 		/*
 		 * We had some memory, but were unable to
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index b32ebf92b0ce..f67e839f06c8 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -16,6 +16,7 @@ config X86_64
 	def_bool y
 	depends on 64BIT
 	select X86_DEV_DMA_OPS
+	select ARCH_USE_CMPXCHG_LOCKREF
 
 ### Arch settings
 config X86
@@ -81,8 +82,6 @@ config X86
 	select HAVE_USER_RETURN_NOTIFIER
 	select ARCH_BINFMT_ELF_RANDOMIZE_PIE
 	select HAVE_ARCH_JUMP_LABEL
-	select HAVE_TEXT_POKE_SMP
-	select HAVE_GENERIC_HARDIRQS
 	select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
 	select SPARSE_IRQ
 	select GENERIC_FIND_FIRST_BIT
@@ -482,11 +481,12 @@ config X86_INTEL_LPSS
 	bool "Intel Low Power Subsystem Support"
 	depends on ACPI
 	select COMMON_CLK
+	select PINCTRL
 	---help---
 	  Select to build support for Intel Low Power Subsystem such as
 	  found on Intel Lynxpoint PCH. Selecting this option enables
-	  things like clock tree (common clock framework) which are needed
-	  by the LPSS peripheral drivers.
+	  things like clock tree (common clock framework) and pincontrol
+	  which are needed by the LPSS peripheral drivers.
 
 config X86_RDC321X
 	bool "RDC R-321x SoC"
@@ -632,6 +632,7 @@ config PARAVIRT_DEBUG
 config PARAVIRT_SPINLOCKS
 	bool "Paravirtualization layer for spinlocks"
 	depends on PARAVIRT && SMP
+	select UNINLINE_SPIN_UNLOCK
 	---help---
 	  Paravirtualized spinlocks allow a pvops backend to replace the
 	  spinlock implementation with something virtualization-friendly
@@ -656,6 +657,15 @@ config KVM_GUEST
 	  underlying device model, the host provides the guest with
 	  timing infrastructure such as time of day, and system time
 
+config KVM_DEBUG_FS
+	bool "Enable debug information for KVM Guests in debugfs"
+	depends on KVM_GUEST && DEBUG_FS
+	default n
+	---help---
+	  This option enables collection of various statistics for KVM guest.
+	  Statistics are displayed in debugfs filesystem. Enabling this option
+	  may incur significant overhead.
+
 source "arch/x86/lguest/Kconfig"
 
 config PARAVIRT_TIME_ACCOUNTING
@@ -850,7 +860,7 @@ source "kernel/Kconfig.preempt"
 
 config X86_UP_APIC
 	bool "Local APIC support on uniprocessors"
-	depends on X86_32 && !SMP && !X86_32_NON_STANDARD
+	depends on X86_32 && !SMP && !X86_32_NON_STANDARD && !PCI_MSI
 	---help---
 	  A local APIC (Advanced Programmable Interrupt Controller) is an
 	  integrated interrupt controller in the CPU. If you have a single-CPU
@@ -875,11 +885,11 @@ config X86_UP_IOAPIC
 
 config X86_LOCAL_APIC
 	def_bool y
-	depends on X86_64 || SMP || X86_32_NON_STANDARD || X86_UP_APIC
+	depends on X86_64 || SMP || X86_32_NON_STANDARD || X86_UP_APIC || PCI_MSI
 
 config X86_IO_APIC
 	def_bool y
-	depends on X86_64 || SMP || X86_32_NON_STANDARD || X86_UP_IOAPIC
+	depends on X86_64 || SMP || X86_32_NON_STANDARD || X86_UP_IOAPIC || PCI_MSI
 
 config X86_VISWS_APIC
 	def_bool y
@@ -1023,6 +1033,7 @@ config X86_REBOOTFIXUPS
 
 config MICROCODE
 	tristate "CPU microcode loading support"
+	depends on CPU_SUP_AMD || CPU_SUP_INTEL
 	select FW_LOADER
 	---help---
 
@@ -1344,8 +1355,12 @@ config ARCH_SELECT_MEMORY_MODEL
 	depends on ARCH_SPARSEMEM_ENABLE
 
 config ARCH_MEMORY_PROBE
-	def_bool y
+	bool "Enable sysfs memory/probe interface"
 	depends on X86_64 && MEMORY_HOTPLUG
+	help
+	  This option enables a sysfs memory/probe interface for testing.
+	  See Documentation/memory-hotplug.txt for more information.
+	  If you are unsure how to answer this question, answer N.
 
 config ARCH_PROC_KCORE_TEXT
 	def_bool y
@@ -1627,9 +1642,9 @@ config KEXEC
 
 	  It is an ongoing process to be certain the hardware in a machine
 	  is properly shutdown, so do not be surprised if this code does not
-	  initially work for you.  It may help to enable device hotplugging
-	  support.  As of this writing the exact hardware interface is
-	  strongly in flux, so no good recommendation can be made.
+	  initially work for you.  As of this writing the exact hardware
+	  interface is strongly in flux, so no good recommendation can be
+	  made.
 
 config CRASH_DUMP
 	bool "kernel crash dumps"
@@ -1716,9 +1731,10 @@ config X86_NEED_RELOCS
 	depends on X86_32 && RELOCATABLE
 
 config PHYSICAL_ALIGN
-	hex "Alignment value to which kernel should be aligned" if X86_32
+	hex "Alignment value to which kernel should be aligned"
 	default "0x1000000"
-	range 0x2000 0x1000000
+	range 0x2000 0x1000000 if X86_32
+	range 0x200000 0x1000000 if X86_64
 	---help---
 	  This value puts the alignment restrictions on physical address
 	  where kernel is loaded and run from. Kernel is compiled for an
@@ -1736,6 +1752,9 @@ config PHYSICAL_ALIGN
 	  end result is that kernel runs from a physical address meeting
 	  above alignment restrictions.
 
+	  On 32-bit this value must be a multiple of 0x2000. On 64-bit
+	  this value must be a multiple of 0x200000.
+
 	  Don't change this unless you know what you are doing.
 
 config HOTPLUG_CPU
@@ -2014,7 +2033,6 @@ menu "Bus options (PCI etc.)"
 config PCI
 	bool "PCI support"
 	default y
-	select ARCH_SUPPORTS_MSI if (X86_LOCAL_APIC && X86_IO_APIC)
 	---help---
 	  Find out whether you have a PCI motherboard. PCI is the name of a
 	  bus system, i.e. the way the CPU talks to the other stuff inside
@@ -2270,6 +2288,32 @@ config RAPIDIO
 
 source "drivers/rapidio/Kconfig"
 
+config X86_SYSFB
+	bool "Mark VGA/VBE/EFI FB as generic system framebuffer"
+	help
+	  Firmwares often provide initial graphics framebuffers so the BIOS,
+	  bootloader or kernel can show basic video-output during boot for
+	  user-guidance and debugging. Historically, x86 used the VESA BIOS
+	  Extensions and EFI-framebuffers for this, which are mostly limited
+	  to x86.
+	  This option, if enabled, marks VGA/VBE/EFI framebuffers as generic
+	  framebuffers so the new generic system-framebuffer drivers can be
+	  used on x86. If the framebuffer is not compatible with the generic
+	  modes, it is adverticed as fallback platform framebuffer so legacy
+	  drivers like efifb, vesafb and uvesafb can pick it up.
+	  If this option is not selected, all system framebuffers are always
+	  marked as fallback platform framebuffers as usual.
+
+	  Note: Legacy fbdev drivers, including vesafb, efifb, uvesafb, will
+	  not be able to pick up generic system framebuffers if this option
+	  is selected. You are highly encouraged to enable simplefb as
+	  replacement if you select this option. simplefb can correctly deal
+	  with generic system framebuffers. But you should still keep vesafb
+	  and others enabled as fallback if a system framebuffer is
+	  incompatible with simplefb.
+
+	  If unsure, say Y.
+
 endmenu
 
 
@@ -2332,10 +2376,6 @@ config HAVE_ATOMIC_IOMAP
 	def_bool y
 	depends on X86_32
 
-config HAVE_TEXT_POKE_SMP
-	bool
-	select STOP_MACHINE if SMP
-
 config X86_DEV_DMA_OPS
 	bool
 	depends on X86_64 || STA2X11
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 07639c656fcd..41250fb33985 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -16,6 +16,10 @@ endif
 # e.g.: obj-y += foo_$(BITS).o
 export BITS
 
+ifdef CONFIG_X86_NEED_RELOCS
+        LDFLAGS_vmlinux := --emit-relocs
+endif
+
 ifeq ($(CONFIG_X86_32),y)
         BITS := 32
         UTS_MACHINE := i386
@@ -25,10 +29,6 @@ ifeq ($(CONFIG_X86_32),y)
         KBUILD_AFLAGS += $(biarch)
         KBUILD_CFLAGS += $(biarch)
 
-        ifdef CONFIG_RELOCATABLE
-                LDFLAGS_vmlinux := --emit-relocs
-        endif
-
         KBUILD_CFLAGS += -msoft-float -mregparm=3 -freg-struct-return
 
         # Never want PIC in a 32-bit kernel, prevent breakage with GCC built
diff --git a/arch/x86/boot/boot.h b/arch/x86/boot/boot.h
index 5b7531966b84..ef72baeff484 100644
--- a/arch/x86/boot/boot.h
+++ b/arch/x86/boot/boot.h
@@ -355,6 +355,7 @@ int strncmp(const char *cs, const char *ct, size_t count);
 size_t strnlen(const char *s, size_t maxlen);
 unsigned int atou(const char *s);
 unsigned long long simple_strtoull(const char *cp, char **endp, unsigned int base);
+size_t strlen(const char *s);
 
 /* tty.c */
 void puts(const char *);
diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S
index 1e3184f6072f..5d6f6891b188 100644
--- a/arch/x86/boot/compressed/head_32.S
+++ b/arch/x86/boot/compressed/head_32.S
@@ -181,8 +181,9 @@ relocated:
 /*
  * Do the decompression, and jump to the new kernel..
  */
-	leal	z_extract_offset_negative(%ebx), %ebp
 				/* push arguments for decompress_kernel: */
+	pushl	$z_output_len	/* decompressed length */
+	leal	z_extract_offset_negative(%ebx), %ebp
 	pushl	%ebp		/* output address */
 	pushl	$z_input_len	/* input_len */
 	leal	input_data(%ebx), %eax
@@ -191,33 +192,7 @@ relocated:
 	pushl	%eax		/* heap area */
 	pushl	%esi		/* real mode pointer */
 	call	decompress_kernel
-	addl	$20, %esp
-
-#if CONFIG_RELOCATABLE
-/*
- * Find the address of the relocations.
- */
-	leal	z_output_len(%ebp), %edi
-
-/*
- * Calculate the delta between where vmlinux was compiled to run
- * and where it was actually loaded.
- */
-	movl	%ebp, %ebx
-	subl	$LOAD_PHYSICAL_ADDR, %ebx
-	jz	2f	/* Nothing to be done if loaded at compiled addr. */
-/*
- * Process relocations.
- */
-
-1:	subl	$4, %edi
-	movl	(%edi), %ecx
-	testl	%ecx, %ecx
-	jz	2f
-	addl	%ebx, -__PAGE_OFFSET(%ebx, %ecx)
-	jmp	1b
-2:
-#endif
+	addl	$24, %esp
 
 /*
  * Jump to the decompressed kernel.
diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S
index 06e71c2c16bf..c337422b575d 100644
--- a/arch/x86/boot/compressed/head_64.S
+++ b/arch/x86/boot/compressed/head_64.S
@@ -338,6 +338,7 @@ relocated:
 	leaq	input_data(%rip), %rdx  /* input_data */
 	movl	$z_input_len, %ecx	/* input_len */
 	movq	%rbp, %r8		/* output target address */
+	movq	$z_output_len, %r9	/* decompressed length */
 	call	decompress_kernel
 	popq	%rsi
 
diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c
index 0319c88290a5..434f077d2c4d 100644
--- a/arch/x86/boot/compressed/misc.c
+++ b/arch/x86/boot/compressed/misc.c
@@ -271,6 +271,79 @@ static void error(char *x)
 		asm("hlt");
 }
 
+#if CONFIG_X86_NEED_RELOCS
+static void handle_relocations(void *output, unsigned long output_len)
+{
+	int *reloc;
+	unsigned long delta, map, ptr;
+	unsigned long min_addr = (unsigned long)output;
+	unsigned long max_addr = min_addr + output_len;
+
+	/*
+	 * Calculate the delta between where vmlinux was linked to load
+	 * and where it was actually loaded.
+	 */
+	delta = min_addr - LOAD_PHYSICAL_ADDR;
+	if (!delta) {
+		debug_putstr("No relocation needed... ");
+		return;
+	}
+	debug_putstr("Performing relocations... ");
+
+	/*
+	 * The kernel contains a table of relocation addresses. Those
+	 * addresses have the final load address of the kernel in virtual
+	 * memory. We are currently working in the self map. So we need to
+	 * create an adjustment for kernel memory addresses to the self map.
+	 * This will involve subtracting out the base address of the kernel.
+	 */
+	map = delta - __START_KERNEL_map;
+
+	/*
+	 * Process relocations: 32 bit relocations first then 64 bit after.
+	 * Two sets of binary relocations are added to the end of the kernel
+	 * before compression. Each relocation table entry is the kernel
+	 * address of the location which needs to be updated stored as a
+	 * 32-bit value which is sign extended to 64 bits.
+	 *
+	 * Format is:
+	 *
+	 * kernel bits...
+	 * 0 - zero terminator for 64 bit relocations
+	 * 64 bit relocation repeated
+	 * 0 - zero terminator for 32 bit relocations
+	 * 32 bit relocation repeated
+	 *
+	 * So we work backwards from the end of the decompressed image.
+	 */
+	for (reloc = output + output_len - sizeof(*reloc); *reloc; reloc--) {
+		int extended = *reloc;
+		extended += map;
+
+		ptr = (unsigned long)extended;
+		if (ptr < min_addr || ptr > max_addr)
+			error("32-bit relocation outside of kernel!\n");
+
+		*(uint32_t *)ptr += delta;
+	}
+#ifdef CONFIG_X86_64
+	for (reloc--; *reloc; reloc--) {
+		long extended = *reloc;
+		extended += map;
+
+		ptr = (unsigned long)extended;
+		if (ptr < min_addr || ptr > max_addr)
+			error("64-bit relocation outside of kernel!\n");
+
+		*(uint64_t *)ptr += delta;
+	}
+#endif
+}
+#else
+static inline void handle_relocations(void *output, unsigned long output_len)
+{ }
+#endif
+
 static void parse_elf(void *output)
 {
 #ifdef CONFIG_X86_64
@@ -325,7 +398,8 @@ static void parse_elf(void *output)
 asmlinkage void decompress_kernel(void *rmode, memptr heap,
 				  unsigned char *input_data,
 				  unsigned long input_len,
-				  unsigned char *output)
+				  unsigned char *output,
+				  unsigned long output_len)
 {
 	real_mode = rmode;
 
@@ -365,6 +439,7 @@ asmlinkage void decompress_kernel(void *rmode, memptr heap,
 	debug_putstr("\nDecompressing Linux... ");
 	decompress(input_data, input_len, NULL, NULL, output, NULL, error);
 	parse_elf(output);
+	handle_relocations(output, output_len);
 	debug_putstr("done.\nBooting the kernel.\n");
 	return;
 }
diff --git a/arch/x86/boot/printf.c b/arch/x86/boot/printf.c
index cdac91ca55d3..565083c16e5c 100644
--- a/arch/x86/boot/printf.c
+++ b/arch/x86/boot/printf.c
@@ -55,7 +55,7 @@ static char *number(char *str, long num, int base, int size, int precision,
 	locase = (type & SMALL);
 	if (type & LEFT)
 		type &= ~ZEROPAD;
-	if (base < 2 || base > 36)
+	if (base < 2 || base > 16)
 		return NULL;
 	c = (type & ZEROPAD) ? '0' : ' ';
 	sign = 0;
diff --git a/arch/x86/crypto/Makefile b/arch/x86/crypto/Makefile
index 6c63c358a7e6..7d6ba9db1be9 100644
--- a/arch/x86/crypto/Makefile
+++ b/arch/x86/crypto/Makefile
@@ -27,6 +27,7 @@ obj-$(CONFIG_CRYPTO_SHA1_SSSE3) += sha1-ssse3.o
 obj-$(CONFIG_CRYPTO_CRC32_PCLMUL) += crc32-pclmul.o
 obj-$(CONFIG_CRYPTO_SHA256_SSSE3) += sha256-ssse3.o
 obj-$(CONFIG_CRYPTO_SHA512_SSSE3) += sha512-ssse3.o
+obj-$(CONFIG_CRYPTO_CRCT10DIF_PCLMUL) += crct10dif-pclmul.o
 
 # These modules require assembler to support AVX.
 ifeq ($(avx_supported),yes)
@@ -81,3 +82,4 @@ crc32c-intel-$(CONFIG_64BIT) += crc32c-pcl-intel-asm_64.o
 crc32-pclmul-y := crc32-pclmul_asm.o crc32-pclmul_glue.o
 sha256-ssse3-y := sha256-ssse3-asm.o sha256-avx-asm.o sha256-avx2-asm.o sha256_ssse3_glue.o
 sha512-ssse3-y := sha512-ssse3-asm.o sha512-avx-asm.o sha512-avx2-asm.o sha512_ssse3_glue.o
+crct10dif-pclmul-y := crct10dif-pcl-asm_64.o crct10dif-pclmul_glue.o
diff --git a/arch/x86/crypto/camellia_glue.c b/arch/x86/crypto/camellia_glue.c
index 5cb86ccd4acb..c171dcbf192d 100644
--- a/arch/x86/crypto/camellia_glue.c
+++ b/arch/x86/crypto/camellia_glue.c
@@ -62,7 +62,7 @@ static void camellia_decrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src)
 }
 
 /* camellia sboxes */
-const u64 camellia_sp10011110[256] = {
+__visible const u64 camellia_sp10011110[256] = {
 	0x7000007070707000ULL, 0x8200008282828200ULL, 0x2c00002c2c2c2c00ULL,
 	0xec0000ecececec00ULL, 0xb30000b3b3b3b300ULL, 0x2700002727272700ULL,
 	0xc00000c0c0c0c000ULL, 0xe50000e5e5e5e500ULL, 0xe40000e4e4e4e400ULL,
@@ -151,7 +151,7 @@ const u64 camellia_sp10011110[256] = {
 	0x9e00009e9e9e9e00ULL,
 };
 
-const u64 camellia_sp22000222[256] = {
+__visible const u64 camellia_sp22000222[256] = {
 	0xe0e0000000e0e0e0ULL, 0x0505000000050505ULL, 0x5858000000585858ULL,
 	0xd9d9000000d9d9d9ULL, 0x6767000000676767ULL, 0x4e4e0000004e4e4eULL,
 	0x8181000000818181ULL, 0xcbcb000000cbcbcbULL, 0xc9c9000000c9c9c9ULL,
@@ -240,7 +240,7 @@ const u64 camellia_sp22000222[256] = {
 	0x3d3d0000003d3d3dULL,
 };
 
-const u64 camellia_sp03303033[256] = {
+__visible const u64 camellia_sp03303033[256] = {
 	0x0038380038003838ULL, 0x0041410041004141ULL, 0x0016160016001616ULL,
 	0x0076760076007676ULL, 0x00d9d900d900d9d9ULL, 0x0093930093009393ULL,
 	0x0060600060006060ULL, 0x00f2f200f200f2f2ULL, 0x0072720072007272ULL,
@@ -329,7 +329,7 @@ const u64 camellia_sp03303033[256] = {
 	0x004f4f004f004f4fULL,
 };
 
-const u64 camellia_sp00444404[256] = {
+__visible const u64 camellia_sp00444404[256] = {
 	0x0000707070700070ULL, 0x00002c2c2c2c002cULL, 0x0000b3b3b3b300b3ULL,
 	0x0000c0c0c0c000c0ULL, 0x0000e4e4e4e400e4ULL, 0x0000575757570057ULL,
 	0x0000eaeaeaea00eaULL, 0x0000aeaeaeae00aeULL, 0x0000232323230023ULL,
@@ -418,7 +418,7 @@ const u64 camellia_sp00444404[256] = {
 	0x00009e9e9e9e009eULL,
 };
 
-const u64 camellia_sp02220222[256] = {
+__visible const u64 camellia_sp02220222[256] = {
 	0x00e0e0e000e0e0e0ULL, 0x0005050500050505ULL, 0x0058585800585858ULL,
 	0x00d9d9d900d9d9d9ULL, 0x0067676700676767ULL, 0x004e4e4e004e4e4eULL,
 	0x0081818100818181ULL, 0x00cbcbcb00cbcbcbULL, 0x00c9c9c900c9c9c9ULL,
@@ -507,7 +507,7 @@ const u64 camellia_sp02220222[256] = {
 	0x003d3d3d003d3d3dULL,
 };
 
-const u64 camellia_sp30333033[256] = {
+__visible const u64 camellia_sp30333033[256] = {
 	0x3800383838003838ULL, 0x4100414141004141ULL, 0x1600161616001616ULL,
 	0x7600767676007676ULL, 0xd900d9d9d900d9d9ULL, 0x9300939393009393ULL,
 	0x6000606060006060ULL, 0xf200f2f2f200f2f2ULL, 0x7200727272007272ULL,
@@ -596,7 +596,7 @@ const u64 camellia_sp30333033[256] = {
 	0x4f004f4f4f004f4fULL,
 };
 
-const u64 camellia_sp44044404[256] = {
+__visible const u64 camellia_sp44044404[256] = {
 	0x7070007070700070ULL, 0x2c2c002c2c2c002cULL, 0xb3b300b3b3b300b3ULL,
 	0xc0c000c0c0c000c0ULL, 0xe4e400e4e4e400e4ULL, 0x5757005757570057ULL,
 	0xeaea00eaeaea00eaULL, 0xaeae00aeaeae00aeULL, 0x2323002323230023ULL,
@@ -685,7 +685,7 @@ const u64 camellia_sp44044404[256] = {
 	0x9e9e009e9e9e009eULL,
 };
 
-const u64 camellia_sp11101110[256] = {
+__visible const u64 camellia_sp11101110[256] = {
 	0x7070700070707000ULL, 0x8282820082828200ULL, 0x2c2c2c002c2c2c00ULL,
 	0xececec00ececec00ULL, 0xb3b3b300b3b3b300ULL, 0x2727270027272700ULL,
 	0xc0c0c000c0c0c000ULL, 0xe5e5e500e5e5e500ULL, 0xe4e4e400e4e4e400ULL,
@@ -828,8 +828,8 @@ static void camellia_setup_tail(u64 *subkey, u64 *subRL, int max)
 
 	subRL[1] ^= (subRL[1] & ~subRL[9]) << 32;
 	/* modified for FLinv(kl2) */
-	dw = (subRL[1] & subRL[9]) >> 32,
-		subRL[1] ^= rol32(dw, 1);
+	dw = (subRL[1] & subRL[9]) >> 32;
+	subRL[1] ^= rol32(dw, 1);
 
 	/* round 8 */
 	subRL[11] ^= subRL[1];
@@ -840,8 +840,8 @@ static void camellia_setup_tail(u64 *subkey, u64 *subRL, int max)
 
 	subRL[1] ^= (subRL[1] & ~subRL[17]) << 32;
 	/* modified for FLinv(kl4) */
-	dw = (subRL[1] & subRL[17]) >> 32,
-		subRL[1] ^= rol32(dw, 1);
+	dw = (subRL[1] & subRL[17]) >> 32;
+	subRL[1] ^= rol32(dw, 1);
 
 	/* round 14 */
 	subRL[19] ^= subRL[1];
@@ -859,8 +859,8 @@ static void camellia_setup_tail(u64 *subkey, u64 *subRL, int max)
 	} else {
 		subRL[1] ^= (subRL[1] & ~subRL[25]) << 32;
 		/* modified for FLinv(kl6) */
-		dw = (subRL[1] & subRL[25]) >> 32,
-			subRL[1] ^= rol32(dw, 1);
+		dw = (subRL[1] & subRL[25]) >> 32;
+		subRL[1] ^= rol32(dw, 1);
 
 		/* round 20 */
 		subRL[27] ^= subRL[1];
@@ -882,8 +882,8 @@ static void camellia_setup_tail(u64 *subkey, u64 *subRL, int max)
 
 		kw4 ^= (kw4 & ~subRL[24]) << 32;
 		/* modified for FL(kl5) */
-		dw = (kw4 & subRL[24]) >> 32,
-			kw4 ^= rol32(dw, 1);
+		dw = (kw4 & subRL[24]) >> 32;
+		kw4 ^= rol32(dw, 1);
 	}
 
 	/* round 17 */
@@ -895,8 +895,8 @@ static void camellia_setup_tail(u64 *subkey, u64 *subRL, int max)
 
 	kw4 ^= (kw4 & ~subRL[16]) << 32;
 	/* modified for FL(kl3) */
-	dw = (kw4 & subRL[16]) >> 32,
-		kw4 ^= rol32(dw, 1);
+	dw = (kw4 & subRL[16]) >> 32;
+	kw4 ^= rol32(dw, 1);
 
 	/* round 11 */
 	subRL[14] ^= kw4;
@@ -907,8 +907,8 @@ static void camellia_setup_tail(u64 *subkey, u64 *subRL, int max)
 
 	kw4 ^= (kw4 & ~subRL[8]) << 32;
 	/* modified for FL(kl1) */
-	dw = (kw4 & subRL[8]) >> 32,
-		kw4 ^= rol32(dw, 1);
+	dw = (kw4 & subRL[8]) >> 32;
+	kw4 ^= rol32(dw, 1);
 
 	/* round 5 */
 	subRL[6] ^= kw4;
@@ -928,8 +928,8 @@ static void camellia_setup_tail(u64 *subkey, u64 *subRL, int max)
 	SET_SUBKEY_LR(6, subRL[5] ^ subRL[7]);			/* round 5 */
 
 	tl = (subRL[10] >> 32) ^ (subRL[10] & ~subRL[8]);
-	dw = tl & (subRL[8] >> 32),				/* FL(kl1) */
-		tr = subRL[10] ^ rol32(dw, 1);
+	dw = tl & (subRL[8] >> 32);				/* FL(kl1) */
+	tr = subRL[10] ^ rol32(dw, 1);
 	tt = (tr | ((u64)tl << 32));
 
 	SET_SUBKEY_LR(7, subRL[6] ^ tt);			/* round 6 */
@@ -937,8 +937,8 @@ static void camellia_setup_tail(u64 *subkey, u64 *subRL, int max)
 	SET_SUBKEY_LR(9, subRL[9]);				/* FLinv(kl2) */
 
 	tl = (subRL[7] >> 32) ^ (subRL[7] & ~subRL[9]);
-	dw = tl & (subRL[9] >> 32),				/* FLinv(kl2) */
-		tr = subRL[7] ^ rol32(dw, 1);
+	dw = tl & (subRL[9] >> 32);				/* FLinv(kl2) */
+	tr = subRL[7] ^ rol32(dw, 1);
 	tt = (tr | ((u64)tl << 32));
 
 	SET_SUBKEY_LR(10, subRL[11] ^ tt);			/* round 7 */
@@ -948,8 +948,8 @@ static void camellia_setup_tail(u64 *subkey, u64 *subRL, int max)
 	SET_SUBKEY_LR(14, subRL[13] ^ subRL[15]);		/* round 11 */
 
 	tl = (subRL[18] >> 32) ^ (subRL[18] & ~subRL[16]);
-	dw = tl & (subRL[16] >> 32),				/* FL(kl3) */
-		tr = subRL[18] ^ rol32(dw, 1);
+	dw = tl & (subRL[16] >> 32);				/* FL(kl3) */
+	tr = subRL[18] ^ rol32(dw, 1);
 	tt = (tr | ((u64)tl << 32));
 
 	SET_SUBKEY_LR(15, subRL[14] ^ tt);			/* round 12 */
@@ -957,8 +957,8 @@ static void camellia_setup_tail(u64 *subkey, u64 *subRL, int max)
 	SET_SUBKEY_LR(17, subRL[17]);				/* FLinv(kl4) */
 
 	tl = (subRL[15] >> 32) ^ (subRL[15] & ~subRL[17]);
-	dw = tl & (subRL[17] >> 32),				/* FLinv(kl4) */
-		tr = subRL[15] ^ rol32(dw, 1);
+	dw = tl & (subRL[17] >> 32);				/* FLinv(kl4) */
+	tr = subRL[15] ^ rol32(dw, 1);
 	tt = (tr | ((u64)tl << 32));
 
 	SET_SUBKEY_LR(18, subRL[19] ^ tt);			/* round 13 */
@@ -972,8 +972,8 @@ static void camellia_setup_tail(u64 *subkey, u64 *subRL, int max)
 		SET_SUBKEY_LR(24, subRL[24] ^ subRL[23]);	/* kw3 */
 	} else {
 		tl = (subRL[26] >> 32) ^ (subRL[26] & ~subRL[24]);
-		dw = tl & (subRL[24] >> 32),			/* FL(kl5) */
-			tr = subRL[26] ^ rol32(dw, 1);
+		dw = tl & (subRL[24] >> 32);			/* FL(kl5) */
+		tr = subRL[26] ^ rol32(dw, 1);
 		tt = (tr | ((u64)tl << 32));
 
 		SET_SUBKEY_LR(23, subRL[22] ^ tt);		/* round 18 */
@@ -981,8 +981,8 @@ static void camellia_setup_tail(u64 *subkey, u64 *subRL, int max)
 		SET_SUBKEY_LR(25, subRL[25]);			/* FLinv(kl6) */
 
 		tl = (subRL[23] >> 32) ^ (subRL[23] & ~subRL[25]);
-		dw = tl & (subRL[25] >> 32),			/* FLinv(kl6) */
-			tr = subRL[23] ^ rol32(dw, 1);
+		dw = tl & (subRL[25] >> 32);			/* FLinv(kl6) */
+		tr = subRL[23] ^ rol32(dw, 1);
 		tt = (tr | ((u64)tl << 32));
 
 		SET_SUBKEY_LR(26, subRL[27] ^ tt);		/* round 19 */
diff --git a/arch/x86/crypto/crct10dif-pcl-asm_64.S b/arch/x86/crypto/crct10dif-pcl-asm_64.S
new file mode 100644
index 000000000000..35e97569d05f
--- /dev/null
+++ b/arch/x86/crypto/crct10dif-pcl-asm_64.S
@@ -0,0 +1,643 @@
+########################################################################
+# Implement fast CRC-T10DIF computation with SSE and PCLMULQDQ instructions
+#
+# Copyright (c) 2013, Intel Corporation
+#
+# Authors:
+#     Erdinc Ozturk <erdinc.ozturk@intel.com>
+#     Vinodh Gopal <vinodh.gopal@intel.com>
+#     James Guilford <james.guilford@intel.com>
+#     Tim Chen <tim.c.chen@linux.intel.com>
+#
+# This software is available to you under a choice of one of two
+# licenses.  You may choose to be licensed under the terms of the GNU
+# General Public License (GPL) Version 2, available from the file
+# COPYING in the main directory of this source tree, or the
+# OpenIB.org BSD license below:
+#
+# Redistribution and use in source and binary forms, with or without
+# modification, are permitted provided that the following conditions are
+# met:
+#
+# * Redistributions of source code must retain the above copyright
+#   notice, this list of conditions and the following disclaimer.
+#
+# * Redistributions in binary form must reproduce the above copyright
+#   notice, this list of conditions and the following disclaimer in the
+#   documentation and/or other materials provided with the
+#   distribution.
+#
+# * Neither the name of the Intel Corporation nor the names of its
+#   contributors may be used to endorse or promote products derived from
+#   this software without specific prior written permission.
+#
+#
+# THIS SOFTWARE IS PROVIDED BY INTEL CORPORATION ""AS IS"" AND ANY
+# EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
+# PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL INTEL CORPORATION OR
+# CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
+# EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
+# PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
+# PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
+# LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
+# NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+# SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+########################################################################
+#       Function API:
+#       UINT16 crc_t10dif_pcl(
+#               UINT16 init_crc, //initial CRC value, 16 bits
+#               const unsigned char *buf, //buffer pointer to calculate CRC on
+#               UINT64 len //buffer length in bytes (64-bit data)
+#       );
+#
+#       Reference paper titled "Fast CRC Computation for Generic
+#	Polynomials Using PCLMULQDQ Instruction"
+#       URL: http://www.intel.com/content/dam/www/public/us/en/documents
+#  /white-papers/fast-crc-computation-generic-polynomials-pclmulqdq-paper.pdf
+#
+#
+
+#include <linux/linkage.h>
+
+.text
+
+#define        arg1 %rdi
+#define        arg2 %rsi
+#define        arg3 %rdx
+
+#define        arg1_low32 %edi
+
+ENTRY(crc_t10dif_pcl)
+.align 16
+
+	# adjust the 16-bit initial_crc value, scale it to 32 bits
+	shl	$16, arg1_low32
+
+	# Allocate Stack Space
+	mov     %rsp, %rcx
+	sub	$16*2, %rsp
+	# align stack to 16 byte boundary
+	and     $~(0x10 - 1), %rsp
+
+	# check if smaller than 256
+	cmp	$256, arg3
+
+	# for sizes less than 128, we can't fold 64B at a time...
+	jl	_less_than_128
+
+
+	# load the initial crc value
+	movd	arg1_low32, %xmm10	# initial crc
+
+	# crc value does not need to be byte-reflected, but it needs
+	# to be moved to the high part of the register.
+	# because data will be byte-reflected and will align with
+	# initial crc at correct place.
+	pslldq	$12, %xmm10
+
+	movdqa  SHUF_MASK(%rip), %xmm11
+	# receive the initial 64B data, xor the initial crc value
+	movdqu	16*0(arg2), %xmm0
+	movdqu	16*1(arg2), %xmm1
+	movdqu	16*2(arg2), %xmm2
+	movdqu	16*3(arg2), %xmm3
+	movdqu	16*4(arg2), %xmm4
+	movdqu	16*5(arg2), %xmm5
+	movdqu	16*6(arg2), %xmm6
+	movdqu	16*7(arg2), %xmm7
+
+	pshufb	%xmm11, %xmm0
+	# XOR the initial_crc value
+	pxor	%xmm10, %xmm0
+	pshufb	%xmm11, %xmm1
+	pshufb	%xmm11, %xmm2
+	pshufb	%xmm11, %xmm3
+	pshufb	%xmm11, %xmm4
+	pshufb	%xmm11, %xmm5
+	pshufb	%xmm11, %xmm6
+	pshufb	%xmm11, %xmm7
+
+	movdqa	rk3(%rip), %xmm10	#xmm10 has rk3 and rk4
+					#imm value of pclmulqdq instruction
+					#will determine which constant to use
+
+	#################################################################
+	# we subtract 256 instead of 128 to save one instruction from the loop
+	sub	$256, arg3
+
+	# at this section of the code, there is 64*x+y (0<=y<64) bytes of
+	# buffer. The _fold_64_B_loop will fold 64B at a time
+	# until we have 64+y Bytes of buffer
+
+
+	# fold 64B at a time. This section of the code folds 4 xmm
+	# registers in parallel
+_fold_64_B_loop:
+
+	# update the buffer pointer
+	add	$128, arg2		#    buf += 64#
+
+	movdqu	16*0(arg2), %xmm9
+	movdqu	16*1(arg2), %xmm12
+	pshufb	%xmm11, %xmm9
+	pshufb	%xmm11, %xmm12
+	movdqa	%xmm0, %xmm8
+	movdqa	%xmm1, %xmm13
+	pclmulqdq	$0x0 , %xmm10, %xmm0
+	pclmulqdq	$0x11, %xmm10, %xmm8
+	pclmulqdq	$0x0 , %xmm10, %xmm1
+	pclmulqdq	$0x11, %xmm10, %xmm13
+	pxor	%xmm9 , %xmm0
+	xorps	%xmm8 , %xmm0
+	pxor	%xmm12, %xmm1
+	xorps	%xmm13, %xmm1
+
+	movdqu	16*2(arg2), %xmm9
+	movdqu	16*3(arg2), %xmm12
+	pshufb	%xmm11, %xmm9
+	pshufb	%xmm11, %xmm12
+	movdqa	%xmm2, %xmm8
+	movdqa	%xmm3, %xmm13
+	pclmulqdq	$0x0, %xmm10, %xmm2
+	pclmulqdq	$0x11, %xmm10, %xmm8
+	pclmulqdq	$0x0, %xmm10, %xmm3
+	pclmulqdq	$0x11, %xmm10, %xmm13
+	pxor	%xmm9 , %xmm2
+	xorps	%xmm8 , %xmm2
+	pxor	%xmm12, %xmm3
+	xorps	%xmm13, %xmm3
+
+	movdqu	16*4(arg2), %xmm9
+	movdqu	16*5(arg2), %xmm12
+	pshufb	%xmm11, %xmm9
+	pshufb	%xmm11, %xmm12
+	movdqa	%xmm4, %xmm8
+	movdqa	%xmm5, %xmm13
+	pclmulqdq	$0x0,  %xmm10, %xmm4
+	pclmulqdq	$0x11, %xmm10, %xmm8
+	pclmulqdq	$0x0,  %xmm10, %xmm5
+	pclmulqdq	$0x11, %xmm10, %xmm13
+	pxor	%xmm9 ,  %xmm4
+	xorps	%xmm8 ,  %xmm4
+	pxor	%xmm12,  %xmm5
+	xorps	%xmm13,  %xmm5
+
+	movdqu	16*6(arg2), %xmm9
+	movdqu	16*7(arg2), %xmm12
+	pshufb	%xmm11, %xmm9
+	pshufb	%xmm11, %xmm12
+	movdqa	%xmm6 , %xmm8
+	movdqa	%xmm7 , %xmm13
+	pclmulqdq	$0x0 , %xmm10, %xmm6
+	pclmulqdq	$0x11, %xmm10, %xmm8
+	pclmulqdq	$0x0 , %xmm10, %xmm7
+	pclmulqdq	$0x11, %xmm10, %xmm13
+	pxor	%xmm9 , %xmm6
+	xorps	%xmm8 , %xmm6
+	pxor	%xmm12, %xmm7
+	xorps	%xmm13, %xmm7
+
+	sub	$128, arg3
+
+	# check if there is another 64B in the buffer to be able to fold
+	jge	_fold_64_B_loop
+	##################################################################
+
+
+	add	$128, arg2
+	# at this point, the buffer pointer is pointing at the last y Bytes
+	# of the buffer the 64B of folded data is in 4 of the xmm
+	# registers: xmm0, xmm1, xmm2, xmm3
+
+
+	# fold the 8 xmm registers to 1 xmm register with different constants
+
+	movdqa	rk9(%rip), %xmm10
+	movdqa	%xmm0, %xmm8
+	pclmulqdq	$0x11, %xmm10, %xmm0
+	pclmulqdq	$0x0 , %xmm10, %xmm8
+	pxor	%xmm8, %xmm7
+	xorps	%xmm0, %xmm7
+
+	movdqa	rk11(%rip), %xmm10
+	movdqa	%xmm1, %xmm8
+	pclmulqdq	 $0x11, %xmm10, %xmm1
+	pclmulqdq	 $0x0 , %xmm10, %xmm8
+	pxor	%xmm8, %xmm7
+	xorps	%xmm1, %xmm7
+
+	movdqa	rk13(%rip), %xmm10
+	movdqa	%xmm2, %xmm8
+	pclmulqdq	 $0x11, %xmm10, %xmm2
+	pclmulqdq	 $0x0 , %xmm10, %xmm8
+	pxor	%xmm8, %xmm7
+	pxor	%xmm2, %xmm7
+
+	movdqa	rk15(%rip), %xmm10
+	movdqa	%xmm3, %xmm8
+	pclmulqdq	$0x11, %xmm10, %xmm3
+	pclmulqdq	$0x0 , %xmm10, %xmm8
+	pxor	%xmm8, %xmm7
+	xorps	%xmm3, %xmm7
+
+	movdqa	rk17(%rip), %xmm10
+	movdqa	%xmm4, %xmm8
+	pclmulqdq	$0x11, %xmm10, %xmm4
+	pclmulqdq	$0x0 , %xmm10, %xmm8
+	pxor	%xmm8, %xmm7
+	pxor	%xmm4, %xmm7
+
+	movdqa	rk19(%rip), %xmm10
+	movdqa	%xmm5, %xmm8
+	pclmulqdq	$0x11, %xmm10, %xmm5
+	pclmulqdq	$0x0 , %xmm10, %xmm8
+	pxor	%xmm8, %xmm7
+	xorps	%xmm5, %xmm7
+
+	movdqa	rk1(%rip), %xmm10	#xmm10 has rk1 and rk2
+					#imm value of pclmulqdq instruction
+					#will determine which constant to use
+	movdqa	%xmm6, %xmm8
+	pclmulqdq	$0x11, %xmm10, %xmm6
+	pclmulqdq	$0x0 , %xmm10, %xmm8
+	pxor	%xmm8, %xmm7
+	pxor	%xmm6, %xmm7
+
+
+	# instead of 64, we add 48 to the loop counter to save 1 instruction
+	# from the loop instead of a cmp instruction, we use the negative
+	# flag with the jl instruction
+	add	$128-16, arg3
+	jl	_final_reduction_for_128
+
+	# now we have 16+y bytes left to reduce. 16 Bytes is in register xmm7
+	# and the rest is in memory. We can fold 16 bytes at a time if y>=16
+	# continue folding 16B at a time
+
+_16B_reduction_loop:
+	movdqa	%xmm7, %xmm8
+	pclmulqdq	$0x11, %xmm10, %xmm7
+	pclmulqdq	$0x0 , %xmm10, %xmm8
+	pxor	%xmm8, %xmm7
+	movdqu	(arg2), %xmm0
+	pshufb	%xmm11, %xmm0
+	pxor	%xmm0 , %xmm7
+	add	$16, arg2
+	sub	$16, arg3
+	# instead of a cmp instruction, we utilize the flags with the
+	# jge instruction equivalent of: cmp arg3, 16-16
+	# check if there is any more 16B in the buffer to be able to fold
+	jge	_16B_reduction_loop
+
+	#now we have 16+z bytes left to reduce, where 0<= z < 16.
+	#first, we reduce the data in the xmm7 register
+
+
+_final_reduction_for_128:
+	# check if any more data to fold. If not, compute the CRC of
+	# the final 128 bits
+	add	$16, arg3
+	je	_128_done
+
+	# here we are getting data that is less than 16 bytes.
+	# since we know that there was data before the pointer, we can
+	# offset the input pointer before the actual point, to receive
+	# exactly 16 bytes. after that the registers need to be adjusted.
+_get_last_two_xmms:
+	movdqa	%xmm7, %xmm2
+
+	movdqu	-16(arg2, arg3), %xmm1
+	pshufb	%xmm11, %xmm1
+
+	# get rid of the extra data that was loaded before
+	# load the shift constant
+	lea	pshufb_shf_table+16(%rip), %rax
+	sub	arg3, %rax
+	movdqu	(%rax), %xmm0
+
+	# shift xmm2 to the left by arg3 bytes
+	pshufb	%xmm0, %xmm2
+
+	# shift xmm7 to the right by 16-arg3 bytes
+	pxor	mask1(%rip), %xmm0
+	pshufb	%xmm0, %xmm7
+	pblendvb	%xmm2, %xmm1	#xmm0 is implicit
+
+	# fold 16 Bytes
+	movdqa	%xmm1, %xmm2
+	movdqa	%xmm7, %xmm8
+	pclmulqdq	$0x11, %xmm10, %xmm7
+	pclmulqdq	$0x0 , %xmm10, %xmm8
+	pxor	%xmm8, %xmm7
+	pxor	%xmm2, %xmm7
+
+_128_done:
+	# compute crc of a 128-bit value
+	movdqa	rk5(%rip), %xmm10	# rk5 and rk6 in xmm10
+	movdqa	%xmm7, %xmm0
+
+	#64b fold
+	pclmulqdq	$0x1, %xmm10, %xmm7
+	pslldq	$8   ,  %xmm0
+	pxor	%xmm0,  %xmm7
+
+	#32b fold
+	movdqa	%xmm7, %xmm0
+
+	pand	mask2(%rip), %xmm0
+
+	psrldq	$12, %xmm7
+	pclmulqdq	$0x10, %xmm10, %xmm7
+	pxor	%xmm0, %xmm7
+
+	#barrett reduction
+_barrett:
+	movdqa	rk7(%rip), %xmm10	# rk7 and rk8 in xmm10
+	movdqa	%xmm7, %xmm0
+	pclmulqdq	$0x01, %xmm10, %xmm7
+	pslldq	$4, %xmm7
+	pclmulqdq	$0x11, %xmm10, %xmm7
+
+	pslldq	$4, %xmm7
+	pxor	%xmm0, %xmm7
+	pextrd	$1, %xmm7, %eax
+
+_cleanup:
+	# scale the result back to 16 bits
+	shr	$16, %eax
+	mov     %rcx, %rsp
+	ret
+
+########################################################################
+
+.align 16
+_less_than_128:
+
+	# check if there is enough buffer to be able to fold 16B at a time
+	cmp	$32, arg3
+	jl	_less_than_32
+	movdqa  SHUF_MASK(%rip), %xmm11
+
+	# now if there is, load the constants
+	movdqa	rk1(%rip), %xmm10	# rk1 and rk2 in xmm10
+
+	movd	arg1_low32, %xmm0	# get the initial crc value
+	pslldq	$12, %xmm0	# align it to its correct place
+	movdqu	(arg2), %xmm7	# load the plaintext
+	pshufb	%xmm11, %xmm7	# byte-reflect the plaintext
+	pxor	%xmm0, %xmm7
+
+
+	# update the buffer pointer
+	add	$16, arg2
+
+	# update the counter. subtract 32 instead of 16 to save one
+	# instruction from the loop
+	sub	$32, arg3
+
+	jmp	_16B_reduction_loop
+
+
+.align 16
+_less_than_32:
+	# mov initial crc to the return value. this is necessary for
+	# zero-length buffers.
+	mov	arg1_low32, %eax
+	test	arg3, arg3
+	je	_cleanup
+
+	movdqa  SHUF_MASK(%rip), %xmm11
+
+	movd	arg1_low32, %xmm0	# get the initial crc value
+	pslldq	$12, %xmm0	# align it to its correct place
+
+	cmp	$16, arg3
+	je	_exact_16_left
+	jl	_less_than_16_left
+
+	movdqu	(arg2), %xmm7	# load the plaintext
+	pshufb	%xmm11, %xmm7	# byte-reflect the plaintext
+	pxor	%xmm0 , %xmm7	# xor the initial crc value
+	add	$16, arg2
+	sub	$16, arg3
+	movdqa	rk1(%rip), %xmm10	# rk1 and rk2 in xmm10
+	jmp	_get_last_two_xmms
+
+
+.align 16
+_less_than_16_left:
+	# use stack space to load data less than 16 bytes, zero-out
+	# the 16B in memory first.
+
+	pxor	%xmm1, %xmm1
+	mov	%rsp, %r11
+	movdqa	%xmm1, (%r11)
+
+	cmp	$4, arg3
+	jl	_only_less_than_4
+
+	# backup the counter value
+	mov	arg3, %r9
+	cmp	$8, arg3
+	jl	_less_than_8_left
+
+	# load 8 Bytes
+	mov	(arg2), %rax
+	mov	%rax, (%r11)
+	add	$8, %r11
+	sub	$8, arg3
+	add	$8, arg2
+_less_than_8_left:
+
+	cmp	$4, arg3
+	jl	_less_than_4_left
+
+	# load 4 Bytes
+	mov	(arg2), %eax
+	mov	%eax, (%r11)
+	add	$4, %r11
+	sub	$4, arg3
+	add	$4, arg2
+_less_than_4_left:
+
+	cmp	$2, arg3
+	jl	_less_than_2_left
+
+	# load 2 Bytes
+	mov	(arg2), %ax
+	mov	%ax, (%r11)
+	add	$2, %r11
+	sub	$2, arg3
+	add	$2, arg2
+_less_than_2_left:
+	cmp     $1, arg3
+        jl      _zero_left
+
+	# load 1 Byte
+	mov	(arg2), %al
+	mov	%al, (%r11)
+_zero_left:
+	movdqa	(%rsp), %xmm7
+	pshufb	%xmm11, %xmm7
+	pxor	%xmm0 , %xmm7	# xor the initial crc value
+
+	# shl r9, 4
+	lea	pshufb_shf_table+16(%rip), %rax
+	sub	%r9, %rax
+	movdqu	(%rax), %xmm0
+	pxor	mask1(%rip), %xmm0
+
+	pshufb	%xmm0, %xmm7
+	jmp	_128_done
+
+.align 16
+_exact_16_left:
+	movdqu	(arg2), %xmm7
+	pshufb	%xmm11, %xmm7
+	pxor	%xmm0 , %xmm7   # xor the initial crc value
+
+	jmp	_128_done
+
+_only_less_than_4:
+	cmp	$3, arg3
+	jl	_only_less_than_3
+
+	# load 3 Bytes
+	mov	(arg2), %al
+	mov	%al, (%r11)
+
+	mov	1(arg2), %al
+	mov	%al, 1(%r11)
+
+	mov	2(arg2), %al
+	mov	%al, 2(%r11)
+
+	movdqa	 (%rsp), %xmm7
+	pshufb	 %xmm11, %xmm7
+	pxor	 %xmm0 , %xmm7  # xor the initial crc value
+
+	psrldq	$5, %xmm7
+
+	jmp	_barrett
+_only_less_than_3:
+	cmp	$2, arg3
+	jl	_only_less_than_2
+
+	# load 2 Bytes
+	mov	(arg2), %al
+	mov	%al, (%r11)
+
+	mov	1(arg2), %al
+	mov	%al, 1(%r11)
+
+	movdqa	(%rsp), %xmm7
+	pshufb	%xmm11, %xmm7
+	pxor	%xmm0 , %xmm7   # xor the initial crc value
+
+	psrldq	$6, %xmm7
+
+	jmp	_barrett
+_only_less_than_2:
+
+	# load 1 Byte
+	mov	(arg2), %al
+	mov	%al, (%r11)
+
+	movdqa	(%rsp), %xmm7
+	pshufb	%xmm11, %xmm7
+	pxor	%xmm0 , %xmm7   # xor the initial crc value
+
+	psrldq	$7, %xmm7
+
+	jmp	_barrett
+
+ENDPROC(crc_t10dif_pcl)
+
+.data
+
+# precomputed constants
+# these constants are precomputed from the poly:
+# 0x8bb70000 (0x8bb7 scaled to 32 bits)
+.align 16
+# Q = 0x18BB70000
+# rk1 = 2^(32*3) mod Q << 32
+# rk2 = 2^(32*5) mod Q << 32
+# rk3 = 2^(32*15) mod Q << 32
+# rk4 = 2^(32*17) mod Q << 32
+# rk5 = 2^(32*3) mod Q << 32
+# rk6 = 2^(32*2) mod Q << 32
+# rk7 = floor(2^64/Q)
+# rk8 = Q
+rk1:
+.quad 0x2d56000000000000
+rk2:
+.quad 0x06df000000000000
+rk3:
+.quad 0x9d9d000000000000
+rk4:
+.quad 0x7cf5000000000000
+rk5:
+.quad 0x2d56000000000000
+rk6:
+.quad 0x1368000000000000
+rk7:
+.quad 0x00000001f65a57f8
+rk8:
+.quad 0x000000018bb70000
+
+rk9:
+.quad 0xceae000000000000
+rk10:
+.quad 0xbfd6000000000000
+rk11:
+.quad 0x1e16000000000000
+rk12:
+.quad 0x713c000000000000
+rk13:
+.quad 0xf7f9000000000000
+rk14:
+.quad 0x80a6000000000000
+rk15:
+.quad 0x044c000000000000
+rk16:
+.quad 0xe658000000000000
+rk17:
+.quad 0xad18000000000000
+rk18:
+.quad 0xa497000000000000
+rk19:
+.quad 0x6ee3000000000000
+rk20:
+.quad 0xe7b5000000000000
+
+
+
+mask1:
+.octa 0x80808080808080808080808080808080
+mask2:
+.octa 0x00000000FFFFFFFFFFFFFFFFFFFFFFFF
+
+SHUF_MASK:
+.octa 0x000102030405060708090A0B0C0D0E0F
+
+pshufb_shf_table:
+# use these values for shift constants for the pshufb instruction
+# different alignments result in values as shown:
+#	DDQ 0x008f8e8d8c8b8a898887868584838281 # shl 15 (16-1) / shr1
+#	DDQ 0x01008f8e8d8c8b8a8988878685848382 # shl 14 (16-3) / shr2
+#	DDQ 0x0201008f8e8d8c8b8a89888786858483 # shl 13 (16-4) / shr3
+#	DDQ 0x030201008f8e8d8c8b8a898887868584 # shl 12 (16-4) / shr4
+#	DDQ 0x04030201008f8e8d8c8b8a8988878685 # shl 11 (16-5) / shr5
+#	DDQ 0x0504030201008f8e8d8c8b8a89888786 # shl 10 (16-6) / shr6
+#	DDQ 0x060504030201008f8e8d8c8b8a898887 # shl 9  (16-7) / shr7
+#	DDQ 0x07060504030201008f8e8d8c8b8a8988 # shl 8  (16-8) / shr8
+#	DDQ 0x0807060504030201008f8e8d8c8b8a89 # shl 7  (16-9) / shr9
+#	DDQ 0x090807060504030201008f8e8d8c8b8a # shl 6  (16-10) / shr10
+#	DDQ 0x0a090807060504030201008f8e8d8c8b # shl 5  (16-11) / shr11
+#	DDQ 0x0b0a090807060504030201008f8e8d8c # shl 4  (16-12) / shr12
+#	DDQ 0x0c0b0a090807060504030201008f8e8d # shl 3  (16-13) / shr13
+#	DDQ 0x0d0c0b0a090807060504030201008f8e # shl 2  (16-14) / shr14
+#	DDQ 0x0e0d0c0b0a090807060504030201008f # shl 1  (16-15) / shr15
+.octa 0x8f8e8d8c8b8a89888786858483828100
+.octa 0x000e0d0c0b0a09080706050403020100
diff --git a/arch/x86/crypto/crct10dif-pclmul_glue.c b/arch/x86/crypto/crct10dif-pclmul_glue.c
new file mode 100644
index 000000000000..7845d7fd54c0
--- /dev/null
+++ b/arch/x86/crypto/crct10dif-pclmul_glue.c
@@ -0,0 +1,151 @@
+/*
+ * Cryptographic API.
+ *
+ * T10 Data Integrity Field CRC16 Crypto Transform using PCLMULQDQ Instructions
+ *
+ * Copyright (C) 2013 Intel Corporation
+ * Author: Tim Chen <tim.c.chen@linux.intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ *
+ */
+
+#include <linux/types.h>
+#include <linux/module.h>
+#include <linux/crc-t10dif.h>
+#include <crypto/internal/hash.h>
+#include <linux/init.h>
+#include <linux/string.h>
+#include <linux/kernel.h>
+#include <asm/i387.h>
+#include <asm/cpufeature.h>
+#include <asm/cpu_device_id.h>
+
+asmlinkage __u16 crc_t10dif_pcl(__u16 crc, const unsigned char *buf,
+				size_t len);
+
+struct chksum_desc_ctx {
+	__u16 crc;
+};
+
+/*
+ * Steps through buffer one byte at at time, calculates reflected
+ * crc using table.
+ */
+
+static int chksum_init(struct shash_desc *desc)
+{
+	struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
+
+	ctx->crc = 0;
+
+	return 0;
+}
+
+static int chksum_update(struct shash_desc *desc, const u8 *data,
+			 unsigned int length)
+{
+	struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
+
+	if (irq_fpu_usable()) {
+		kernel_fpu_begin();
+		ctx->crc = crc_t10dif_pcl(ctx->crc, data, length);
+		kernel_fpu_end();
+	} else
+		ctx->crc = crc_t10dif_generic(ctx->crc, data, length);
+	return 0;
+}
+
+static int chksum_final(struct shash_desc *desc, u8 *out)
+{
+	struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
+
+	*(__u16 *)out = ctx->crc;
+	return 0;
+}
+
+static int __chksum_finup(__u16 *crcp, const u8 *data, unsigned int len,
+			u8 *out)
+{
+	if (irq_fpu_usable()) {
+		kernel_fpu_begin();
+		*(__u16 *)out = crc_t10dif_pcl(*crcp, data, len);
+		kernel_fpu_end();
+	} else
+		*(__u16 *)out = crc_t10dif_generic(*crcp, data, len);
+	return 0;
+}
+
+static int chksum_finup(struct shash_desc *desc, const u8 *data,
+			unsigned int len, u8 *out)
+{
+	struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
+
+	return __chksum_finup(&ctx->crc, data, len, out);
+}
+
+static int chksum_digest(struct shash_desc *desc, const u8 *data,
+			 unsigned int length, u8 *out)
+{
+	struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
+
+	return __chksum_finup(&ctx->crc, data, length, out);
+}
+
+static struct shash_alg alg = {
+	.digestsize		=	CRC_T10DIF_DIGEST_SIZE,
+	.init		=	chksum_init,
+	.update		=	chksum_update,
+	.final		=	chksum_final,
+	.finup		=	chksum_finup,
+	.digest		=	chksum_digest,
+	.descsize		=	sizeof(struct chksum_desc_ctx),
+	.base			=	{
+		.cra_name		=	"crct10dif",
+		.cra_driver_name	=	"crct10dif-pclmul",
+		.cra_priority		=	200,
+		.cra_blocksize		=	CRC_T10DIF_BLOCK_SIZE,
+		.cra_module		=	THIS_MODULE,
+	}
+};
+
+static const struct x86_cpu_id crct10dif_cpu_id[] = {
+	X86_FEATURE_MATCH(X86_FEATURE_PCLMULQDQ),
+	{}
+};
+MODULE_DEVICE_TABLE(x86cpu, crct10dif_cpu_id);
+
+static int __init crct10dif_intel_mod_init(void)
+{
+	if (!x86_match_cpu(crct10dif_cpu_id))
+		return -ENODEV;
+
+	return crypto_register_shash(&alg);
+}
+
+static void __exit crct10dif_intel_mod_fini(void)
+{
+	crypto_unregister_shash(&alg);
+}
+
+module_init(crct10dif_intel_mod_init);
+module_exit(crct10dif_intel_mod_fini);
+
+MODULE_AUTHOR("Tim Chen <tim.c.chen@linux.intel.com>");
+MODULE_DESCRIPTION("T10 DIF CRC calculation accelerated with PCLMULQDQ.");
+MODULE_LICENSE("GPL");
+
+MODULE_ALIAS("crct10dif");
+MODULE_ALIAS("crct10dif-pclmul");
diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c
index bccfca68430e..665a730307f2 100644
--- a/arch/x86/ia32/ia32_signal.c
+++ b/arch/x86/ia32/ia32_signal.c
@@ -457,7 +457,7 @@ int ia32_setup_rt_frame(int sig, struct ksignal *ksig,
 		else
 			put_user_ex(0, &frame->uc.uc_flags);
 		put_user_ex(0, &frame->uc.uc_link);
-		err |= __compat_save_altstack(&frame->uc.uc_stack, regs->sp);
+		compat_save_altstack_ex(&frame->uc.uc_stack, regs->sp);
 
 		if (ksig->ka.sa.sa_flags & SA_RESTORER)
 			restorer = ksig->ka.sa.sa_restorer;
diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S
index 474dc1b59f72..4299eb05023c 100644
--- a/arch/x86/ia32/ia32entry.S
+++ b/arch/x86/ia32/ia32entry.S
@@ -452,7 +452,7 @@ ia32_badsys:
 
 	CFI_ENDPROC
 	
-	.macro PTREGSCALL label, func, arg
+	.macro PTREGSCALL label, func
 	ALIGN
 GLOBAL(\label)
 	leaq \func(%rip),%rax
diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h
index 2dfac58f3b11..b1977bad5435 100644
--- a/arch/x86/include/asm/acpi.h
+++ b/arch/x86/include/asm/acpi.h
@@ -86,6 +86,7 @@ extern int acpi_pci_disabled;
 extern int acpi_skip_timer_override;
 extern int acpi_use_timer_override;
 extern int acpi_fix_pin2_polarity;
+extern int acpi_disable_cmcff;
 
 extern u8 acpi_sci_flags;
 extern int acpi_sci_override_gsi;
@@ -168,6 +169,7 @@ static inline void arch_acpi_set_pdc_bits(u32 *buf)
 
 #define acpi_lapic 0
 #define acpi_ioapic 0
+#define acpi_disable_cmcff 0
 static inline void acpi_noirq_set(void) { }
 static inline void acpi_disable_pci(void) { }
 static inline void disable_acpi(void) { }
diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index 58ed6d96a6ac..0a3f9c9f98d5 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -5,6 +5,7 @@
 #include <linux/stddef.h>
 #include <linux/stringify.h>
 #include <asm/asm.h>
+#include <asm/ptrace.h>
 
 /*
  * Alternative inline assembly for SMP.
@@ -220,20 +221,11 @@ extern void *text_poke_early(void *addr, const void *opcode, size_t len);
  * no thread can be preempted in the instructions being modified (no iret to an
  * invalid instruction possible) or if the instructions are changed from a
  * consistent state to another consistent state atomically.
- * More care must be taken when modifying code in the SMP case because of
- * Intel's errata. text_poke_smp() takes care that errata, but still
- * doesn't support NMI/MCE handler code modifying.
  * On the local CPU you need to be protected again NMI or MCE handlers seeing an
  * inconsistent instruction while you patch.
  */
-struct text_poke_param {
-	void *addr;
-	const void *opcode;
-	size_t len;
-};
-
 extern void *text_poke(void *addr, const void *opcode, size_t len);
-extern void *text_poke_smp(void *addr, const void *opcode, size_t len);
-extern void text_poke_smp_batch(struct text_poke_param *params, int n);
+extern int poke_int3_handler(struct pt_regs *regs);
+extern void *text_poke_bp(void *addr, const void *opcode, size_t len, void *handler);
 
 #endif /* _ASM_X86_ALTERNATIVE_H */
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index f8119b582c3c..1d2091a226bc 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -715,4 +715,6 @@ static inline void exiting_ack_irq(void)
 	ack_APIC_irq();
 }
 
+extern void ioapic_zap_locks(void);
+
 #endif /* _ASM_X86_APIC_H */
diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h
index 1c2d247f65ce..4582e8e1cd1a 100644
--- a/arch/x86/include/asm/asm.h
+++ b/arch/x86/include/asm/asm.h
@@ -3,21 +3,25 @@
 
 #ifdef __ASSEMBLY__
 # define __ASM_FORM(x)	x
+# define __ASM_FORM_RAW(x)     x
 # define __ASM_FORM_COMMA(x) x,
 #else
 # define __ASM_FORM(x)	" " #x " "
+# define __ASM_FORM_RAW(x)     #x
 # define __ASM_FORM_COMMA(x) " " #x ","
 #endif
 
 #ifdef CONFIG_X86_32
 # define __ASM_SEL(a,b) __ASM_FORM(a)
+# define __ASM_SEL_RAW(a,b) __ASM_FORM_RAW(a)
 #else
 # define __ASM_SEL(a,b) __ASM_FORM(b)
+# define __ASM_SEL_RAW(a,b) __ASM_FORM_RAW(b)
 #endif
 
 #define __ASM_SIZE(inst, ...)	__ASM_SEL(inst##l##__VA_ARGS__, \
 					  inst##q##__VA_ARGS__)
-#define __ASM_REG(reg)		__ASM_SEL(e##reg, r##reg)
+#define __ASM_REG(reg)         __ASM_SEL_RAW(e##reg, r##reg)
 
 #define _ASM_PTR	__ASM_SEL(.long, .quad)
 #define _ASM_ALIGN	__ASM_SEL(.balign 4, .balign 8)
diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
index 6dfd0195bb55..41639ce8fd63 100644
--- a/arch/x86/include/asm/bitops.h
+++ b/arch/x86/include/asm/bitops.h
@@ -15,6 +15,14 @@
 #include <linux/compiler.h>
 #include <asm/alternative.h>
 
+#if BITS_PER_LONG == 32
+# define _BITOPS_LONG_SHIFT 5
+#elif BITS_PER_LONG == 64
+# define _BITOPS_LONG_SHIFT 6
+#else
+# error "Unexpected BITS_PER_LONG"
+#endif
+
 #define BIT_64(n)			(U64_C(1) << (n))
 
 /*
@@ -59,7 +67,7 @@
  * restricted to acting on a single-word quantity.
  */
 static __always_inline void
-set_bit(unsigned int nr, volatile unsigned long *addr)
+set_bit(long nr, volatile unsigned long *addr)
 {
 	if (IS_IMMEDIATE(nr)) {
 		asm volatile(LOCK_PREFIX "orb %1,%0"
@@ -81,7 +89,7 @@ set_bit(unsigned int nr, volatile unsigned long *addr)
  * If it's called on the same region of memory simultaneously, the effect
  * may be that only one operation succeeds.
  */
-static inline void __set_bit(int nr, volatile unsigned long *addr)
+static inline void __set_bit(long nr, volatile unsigned long *addr)
 {
 	asm volatile("bts %1,%0" : ADDR : "Ir" (nr) : "memory");
 }
@@ -97,7 +105,7 @@ static inline void __set_bit(int nr, volatile unsigned long *addr)
  * in order to ensure changes are visible on other processors.
  */
 static __always_inline void
-clear_bit(int nr, volatile unsigned long *addr)
+clear_bit(long nr, volatile unsigned long *addr)
 {
 	if (IS_IMMEDIATE(nr)) {
 		asm volatile(LOCK_PREFIX "andb %1,%0"
@@ -118,13 +126,13 @@ clear_bit(int nr, volatile unsigned long *addr)
  * clear_bit() is atomic and implies release semantics before the memory
  * operation. It can be used for an unlock.
  */
-static inline void clear_bit_unlock(unsigned nr, volatile unsigned long *addr)
+static inline void clear_bit_unlock(long nr, volatile unsigned long *addr)
 {
 	barrier();
 	clear_bit(nr, addr);
 }
 
-static inline void __clear_bit(int nr, volatile unsigned long *addr)
+static inline void __clear_bit(long nr, volatile unsigned long *addr)
 {
 	asm volatile("btr %1,%0" : ADDR : "Ir" (nr));
 }
@@ -141,7 +149,7 @@ static inline void __clear_bit(int nr, volatile unsigned long *addr)
  * No memory barrier is required here, because x86 cannot reorder stores past
  * older loads. Same principle as spin_unlock.
  */
-static inline void __clear_bit_unlock(unsigned nr, volatile unsigned long *addr)
+static inline void __clear_bit_unlock(long nr, volatile unsigned long *addr)
 {
 	barrier();
 	__clear_bit(nr, addr);
@@ -159,7 +167,7 @@ static inline void __clear_bit_unlock(unsigned nr, volatile unsigned long *addr)
  * If it's called on the same region of memory simultaneously, the effect
  * may be that only one operation succeeds.
  */
-static inline void __change_bit(int nr, volatile unsigned long *addr)
+static inline void __change_bit(long nr, volatile unsigned long *addr)
 {
 	asm volatile("btc %1,%0" : ADDR : "Ir" (nr));
 }
@@ -173,7 +181,7 @@ static inline void __change_bit(int nr, volatile unsigned long *addr)
  * Note that @nr may be almost arbitrarily large; this function is not
  * restricted to acting on a single-word quantity.
  */
-static inline void change_bit(int nr, volatile unsigned long *addr)
+static inline void change_bit(long nr, volatile unsigned long *addr)
 {
 	if (IS_IMMEDIATE(nr)) {
 		asm volatile(LOCK_PREFIX "xorb %1,%0"
@@ -194,7 +202,7 @@ static inline void change_bit(int nr, volatile unsigned long *addr)
  * This operation is atomic and cannot be reordered.
  * It also implies a memory barrier.
  */
-static inline int test_and_set_bit(int nr, volatile unsigned long *addr)
+static inline int test_and_set_bit(long nr, volatile unsigned long *addr)
 {
 	int oldbit;
 
@@ -212,7 +220,7 @@ static inline int test_and_set_bit(int nr, volatile unsigned long *addr)
  * This is the same as test_and_set_bit on x86.
  */
 static __always_inline int
-test_and_set_bit_lock(int nr, volatile unsigned long *addr)
+test_and_set_bit_lock(long nr, volatile unsigned long *addr)
 {
 	return test_and_set_bit(nr, addr);
 }
@@ -226,7 +234,7 @@ test_and_set_bit_lock(int nr, volatile unsigned long *addr)
  * If two examples of this operation race, one can appear to succeed
  * but actually fail.  You must protect multiple accesses with a lock.
  */
-static inline int __test_and_set_bit(int nr, volatile unsigned long *addr)
+static inline int __test_and_set_bit(long nr, volatile unsigned long *addr)
 {
 	int oldbit;
 
@@ -245,7 +253,7 @@ static inline int __test_and_set_bit(int nr, volatile unsigned long *addr)
  * This operation is atomic and cannot be reordered.
  * It also implies a memory barrier.
  */
-static inline int test_and_clear_bit(int nr, volatile unsigned long *addr)
+static inline int test_and_clear_bit(long nr, volatile unsigned long *addr)
 {
 	int oldbit;
 
@@ -272,7 +280,7 @@ static inline int test_and_clear_bit(int nr, volatile unsigned long *addr)
  * accessed from a hypervisor on the same CPU if running in a VM: don't change
  * this without also updating arch/x86/kernel/kvm.c
  */
-static inline int __test_and_clear_bit(int nr, volatile unsigned long *addr)
+static inline int __test_and_clear_bit(long nr, volatile unsigned long *addr)
 {
 	int oldbit;
 
@@ -284,7 +292,7 @@ static inline int __test_and_clear_bit(int nr, volatile unsigned long *addr)
 }
 
 /* WARNING: non atomic and it can be reordered! */
-static inline int __test_and_change_bit(int nr, volatile unsigned long *addr)
+static inline int __test_and_change_bit(long nr, volatile unsigned long *addr)
 {
 	int oldbit;
 
@@ -304,7 +312,7 @@ static inline int __test_and_change_bit(int nr, volatile unsigned long *addr)
  * This operation is atomic and cannot be reordered.
  * It also implies a memory barrier.
  */
-static inline int test_and_change_bit(int nr, volatile unsigned long *addr)
+static inline int test_and_change_bit(long nr, volatile unsigned long *addr)
 {
 	int oldbit;
 
@@ -315,13 +323,13 @@ static inline int test_and_change_bit(int nr, volatile unsigned long *addr)
 	return oldbit;
 }
 
-static __always_inline int constant_test_bit(unsigned int nr, const volatile unsigned long *addr)
+static __always_inline int constant_test_bit(long nr, const volatile unsigned long *addr)
 {
-	return ((1UL << (nr % BITS_PER_LONG)) &
-		(addr[nr / BITS_PER_LONG])) != 0;
+	return ((1UL << (nr & (BITS_PER_LONG-1))) &
+		(addr[nr >> _BITOPS_LONG_SHIFT])) != 0;
 }
 
-static inline int variable_test_bit(int nr, volatile const unsigned long *addr)
+static inline int variable_test_bit(long nr, volatile const unsigned long *addr)
 {
 	int oldbit;
 
diff --git a/arch/x86/include/asm/checksum_32.h b/arch/x86/include/asm/checksum_32.h
index 46fc474fd819..f50de6951738 100644
--- a/arch/x86/include/asm/checksum_32.h
+++ b/arch/x86/include/asm/checksum_32.h
@@ -49,9 +49,15 @@ static inline __wsum csum_partial_copy_from_user(const void __user *src,
 						 int len, __wsum sum,
 						 int *err_ptr)
 {
+	__wsum ret;
+
 	might_sleep();
-	return csum_partial_copy_generic((__force void *)src, dst,
-					 len, sum, err_ptr, NULL);
+	stac();
+	ret = csum_partial_copy_generic((__force void *)src, dst,
+					len, sum, err_ptr, NULL);
+	clac();
+
+	return ret;
 }
 
 /*
@@ -176,10 +182,16 @@ static inline __wsum csum_and_copy_to_user(const void *src,
 					   int len, __wsum sum,
 					   int *err_ptr)
 {
+	__wsum ret;
+
 	might_sleep();
-	if (access_ok(VERIFY_WRITE, dst, len))
-		return csum_partial_copy_generic(src, (__force void *)dst,
-						 len, sum, NULL, err_ptr);
+	if (access_ok(VERIFY_WRITE, dst, len)) {
+		stac();
+		ret = csum_partial_copy_generic(src, (__force void *)dst,
+						len, sum, NULL, err_ptr);
+		clac();
+		return ret;
+	}
 
 	if (len)
 		*err_ptr = -EFAULT;
diff --git a/arch/x86/include/asm/checksum_64.h b/arch/x86/include/asm/checksum_64.h
index 9bfdc41629ec..e6fd8a026c7b 100644
--- a/arch/x86/include/asm/checksum_64.h
+++ b/arch/x86/include/asm/checksum_64.h
@@ -133,7 +133,7 @@ extern __wsum csum_partial(const void *buff, int len, __wsum sum);
 
 
 /* Do not call this directly. Use the wrappers below */
-extern __wsum csum_partial_copy_generic(const void *src, const void *dst,
+extern __visible __wsum csum_partial_copy_generic(const void *src, const void *dst,
 					int len, __wsum sum,
 					int *src_err_ptr, int *dst_err_ptr);
 
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 47538a61c91b..89270b4318db 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -366,14 +366,15 @@ extern bool __static_cpu_has_safe(u16 bit);
  */
 static __always_inline __pure bool __static_cpu_has(u16 bit)
 {
-#if __GNUC__ > 4 || __GNUC_MINOR__ >= 5
+#ifdef CC_HAVE_ASM_GOTO
 
 #ifdef CONFIG_X86_DEBUG_STATIC_CPU_HAS
+
 		/*
 		 * Catch too early usage of this before alternatives
 		 * have run.
 		 */
-		asm goto("1: jmp %l[t_warn]\n"
+		asm_volatile_goto("1: jmp %l[t_warn]\n"
 			 "2:\n"
 			 ".section .altinstructions,\"a\"\n"
 			 " .long 1b - .\n"
@@ -384,9 +385,10 @@ static __always_inline __pure bool __static_cpu_has(u16 bit)
 			 ".previous\n"
 			 /* skipping size check since replacement size = 0 */
 			 : : "i" (X86_FEATURE_ALWAYS) : : t_warn);
+
 #endif
 
-		asm goto("1: jmp %l[t_no]\n"
+		asm_volatile_goto("1: jmp %l[t_no]\n"
 			 "2:\n"
 			 ".section .altinstructions,\"a\"\n"
 			 " .long 1b - .\n"
@@ -406,7 +408,9 @@ static __always_inline __pure bool __static_cpu_has(u16 bit)
 		warn_pre_alternatives();
 		return false;
 #endif
-#else /* GCC_VERSION >= 40500 */
+
+#else /* CC_HAVE_ASM_GOTO */
+
 		u8 flag;
 		/* Open-coded due to __stringify() in ALTERNATIVE() */
 		asm volatile("1: movb $0,%0\n"
@@ -427,7 +431,8 @@ static __always_inline __pure bool __static_cpu_has(u16 bit)
 			     ".previous\n"
 			     : "=qm" (flag) : "i" (bit));
 		return flag;
-#endif
+
+#endif /* CC_HAVE_ASM_GOTO */
 }
 
 #define static_cpu_has(bit)					\
@@ -441,14 +446,14 @@ static __always_inline __pure bool __static_cpu_has(u16 bit)
 
 static __always_inline __pure bool _static_cpu_has_safe(u16 bit)
 {
-#if __GNUC__ > 4 || __GNUC_MINOR__ >= 5
+#ifdef CC_HAVE_ASM_GOTO
 /*
  * We need to spell the jumps to the compiler because, depending on the offset,
  * the replacement jump can be bigger than the original jump, and this we cannot
  * have. Thus, we force the jump to the widest, 4-byte, signed relative
  * offset even though the last would often fit in less bytes.
  */
-		asm goto("1: .byte 0xe9\n .long %l[t_dynamic] - 2f\n"
+		asm_volatile_goto("1: .byte 0xe9\n .long %l[t_dynamic] - 2f\n"
 			 "2:\n"
 			 ".section .altinstructions,\"a\"\n"
 			 " .long 1b - .\n"		/* src offset */
@@ -475,7 +480,7 @@ static __always_inline __pure bool _static_cpu_has_safe(u16 bit)
 		return false;
 	t_dynamic:
 		return __static_cpu_has_safe(bit);
-#else /* GCC_VERSION >= 40500 */
+#else
 		u8 flag;
 		/* Open-coded due to __stringify() in ALTERNATIVE() */
 		asm volatile("1: movb $2,%0\n"
@@ -511,7 +516,7 @@ static __always_inline __pure bool _static_cpu_has_safe(u16 bit)
 			     : "=qm" (flag)
 			     : "i" (bit), "i" (X86_FEATURE_ALWAYS));
 		return (flag == 2 ? __static_cpu_has_safe(bit) : flag);
-#endif
+#endif /* CC_HAVE_ASM_GOTO */
 }
 
 #define static_cpu_has_safe(bit)				\
diff --git a/arch/x86/include/asm/dma-contiguous.h b/arch/x86/include/asm/dma-contiguous.h
index c09241659971..b4b38bacb404 100644
--- a/arch/x86/include/asm/dma-contiguous.h
+++ b/arch/x86/include/asm/dma-contiguous.h
@@ -4,7 +4,6 @@
 #ifdef __KERNEL__
 
 #include <linux/types.h>
-#include <asm-generic/dma-contiguous.h>
 
 static inline void
 dma_contiguous_early_fixup(phys_addr_t base, unsigned long size) { }
diff --git a/arch/x86/include/asm/e820.h b/arch/x86/include/asm/e820.h
index cccd07fa5e3a..779c2efe2e97 100644
--- a/arch/x86/include/asm/e820.h
+++ b/arch/x86/include/asm/e820.h
@@ -29,7 +29,7 @@ extern void e820_setup_gap(void);
 extern int e820_search_gap(unsigned long *gapstart, unsigned long *gapsize,
 			unsigned long start_addr, unsigned long long end_addr);
 struct setup_data;
-extern void parse_e820_ext(struct setup_data *data);
+extern void parse_e820_ext(u64 phys_addr, u32 data_len);
 
 #if defined(CONFIG_X86_64) || \
 	(defined(CONFIG_X86_32) && defined(CONFIG_HIBERNATION))
diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h
index e4ac559c4a24..92b3bae08b74 100644
--- a/arch/x86/include/asm/hw_irq.h
+++ b/arch/x86/include/asm/hw_irq.h
@@ -26,56 +26,56 @@
 #include <asm/sections.h>
 
 /* Interrupt handlers registered during init_IRQ */
-extern void apic_timer_interrupt(void);
-extern void x86_platform_ipi(void);
-extern void kvm_posted_intr_ipi(void);
-extern void error_interrupt(void);
-extern void irq_work_interrupt(void);
-
-extern void spurious_interrupt(void);
-extern void thermal_interrupt(void);
-extern void reschedule_interrupt(void);
-
-extern void invalidate_interrupt(void);
-extern void invalidate_interrupt0(void);
-extern void invalidate_interrupt1(void);
-extern void invalidate_interrupt2(void);
-extern void invalidate_interrupt3(void);
-extern void invalidate_interrupt4(void);
-extern void invalidate_interrupt5(void);
-extern void invalidate_interrupt6(void);
-extern void invalidate_interrupt7(void);
-extern void invalidate_interrupt8(void);
-extern void invalidate_interrupt9(void);
-extern void invalidate_interrupt10(void);
-extern void invalidate_interrupt11(void);
-extern void invalidate_interrupt12(void);
-extern void invalidate_interrupt13(void);
-extern void invalidate_interrupt14(void);
-extern void invalidate_interrupt15(void);
-extern void invalidate_interrupt16(void);
-extern void invalidate_interrupt17(void);
-extern void invalidate_interrupt18(void);
-extern void invalidate_interrupt19(void);
-extern void invalidate_interrupt20(void);
-extern void invalidate_interrupt21(void);
-extern void invalidate_interrupt22(void);
-extern void invalidate_interrupt23(void);
-extern void invalidate_interrupt24(void);
-extern void invalidate_interrupt25(void);
-extern void invalidate_interrupt26(void);
-extern void invalidate_interrupt27(void);
-extern void invalidate_interrupt28(void);
-extern void invalidate_interrupt29(void);
-extern void invalidate_interrupt30(void);
-extern void invalidate_interrupt31(void);
-
-extern void irq_move_cleanup_interrupt(void);
-extern void reboot_interrupt(void);
-extern void threshold_interrupt(void);
-
-extern void call_function_interrupt(void);
-extern void call_function_single_interrupt(void);
+extern asmlinkage void apic_timer_interrupt(void);
+extern asmlinkage void x86_platform_ipi(void);
+extern asmlinkage void kvm_posted_intr_ipi(void);
+extern asmlinkage void error_interrupt(void);
+extern asmlinkage void irq_work_interrupt(void);
+
+extern asmlinkage void spurious_interrupt(void);
+extern asmlinkage void thermal_interrupt(void);
+extern asmlinkage void reschedule_interrupt(void);
+
+extern asmlinkage void invalidate_interrupt(void);
+extern asmlinkage void invalidate_interrupt0(void);
+extern asmlinkage void invalidate_interrupt1(void);
+extern asmlinkage void invalidate_interrupt2(void);
+extern asmlinkage void invalidate_interrupt3(void);
+extern asmlinkage void invalidate_interrupt4(void);
+extern asmlinkage void invalidate_interrupt5(void);
+extern asmlinkage void invalidate_interrupt6(void);
+extern asmlinkage void invalidate_interrupt7(void);
+extern asmlinkage void invalidate_interrupt8(void);
+extern asmlinkage void invalidate_interrupt9(void);
+extern asmlinkage void invalidate_interrupt10(void);
+extern asmlinkage void invalidate_interrupt11(void);
+extern asmlinkage void invalidate_interrupt12(void);
+extern asmlinkage void invalidate_interrupt13(void);
+extern asmlinkage void invalidate_interrupt14(void);
+extern asmlinkage void invalidate_interrupt15(void);
+extern asmlinkage void invalidate_interrupt16(void);
+extern asmlinkage void invalidate_interrupt17(void);
+extern asmlinkage void invalidate_interrupt18(void);
+extern asmlinkage void invalidate_interrupt19(void);
+extern asmlinkage void invalidate_interrupt20(void);
+extern asmlinkage void invalidate_interrupt21(void);
+extern asmlinkage void invalidate_interrupt22(void);
+extern asmlinkage void invalidate_interrupt23(void);
+extern asmlinkage void invalidate_interrupt24(void);
+extern asmlinkage void invalidate_interrupt25(void);
+extern asmlinkage void invalidate_interrupt26(void);
+extern asmlinkage void invalidate_interrupt27(void);
+extern asmlinkage void invalidate_interrupt28(void);
+extern asmlinkage void invalidate_interrupt29(void);
+extern asmlinkage void invalidate_interrupt30(void);
+extern asmlinkage void invalidate_interrupt31(void);
+
+extern asmlinkage void irq_move_cleanup_interrupt(void);
+extern asmlinkage void reboot_interrupt(void);
+extern asmlinkage void threshold_interrupt(void);
+
+extern asmlinkage void call_function_interrupt(void);
+extern asmlinkage void call_function_single_interrupt(void);
 
 #ifdef CONFIG_TRACING
 /* Interrupt handlers registered during init_IRQ */
@@ -172,22 +172,18 @@ extern atomic_t irq_mis_count;
 extern void eisa_set_level_irq(unsigned int irq);
 
 /* SMP */
-extern void smp_apic_timer_interrupt(struct pt_regs *);
-extern void smp_spurious_interrupt(struct pt_regs *);
-extern void smp_x86_platform_ipi(struct pt_regs *);
-extern void smp_error_interrupt(struct pt_regs *);
+extern __visible void smp_apic_timer_interrupt(struct pt_regs *);
+extern __visible void smp_spurious_interrupt(struct pt_regs *);
+extern __visible void smp_x86_platform_ipi(struct pt_regs *);
+extern __visible void smp_error_interrupt(struct pt_regs *);
 #ifdef CONFIG_X86_IO_APIC
 extern asmlinkage void smp_irq_move_cleanup_interrupt(void);
 #endif
 #ifdef CONFIG_SMP
-extern void smp_reschedule_interrupt(struct pt_regs *);
-extern void smp_call_function_interrupt(struct pt_regs *);
-extern void smp_call_function_single_interrupt(struct pt_regs *);
-#ifdef CONFIG_X86_32
-extern void smp_invalidate_interrupt(struct pt_regs *);
-#else
-extern asmlinkage void smp_invalidate_interrupt(struct pt_regs *);
-#endif
+extern __visible void smp_reschedule_interrupt(struct pt_regs *);
+extern __visible void smp_call_function_interrupt(struct pt_regs *);
+extern __visible void smp_call_function_single_interrupt(struct pt_regs *);
+extern __visible void smp_invalidate_interrupt(struct pt_regs *);
 #endif
 
 extern void (*__initconst interrupt[NR_VECTORS-FIRST_EXTERNAL_VECTOR])(void);
diff --git a/arch/x86/include/asm/hypervisor.h b/arch/x86/include/asm/hypervisor.h
index 2d4b5e6107cd..e42f758a0fbd 100644
--- a/arch/x86/include/asm/hypervisor.h
+++ b/arch/x86/include/asm/hypervisor.h
@@ -33,7 +33,7 @@ struct hypervisor_x86 {
 	const char	*name;
 
 	/* Detection routine */
-	bool		(*detect)(void);
+	uint32_t	(*detect)(void);
 
 	/* Adjust CPU feature bits (run once per CPU) */
 	void		(*set_cpu_features)(struct cpuinfo_x86 *);
diff --git a/arch/x86/include/asm/irq.h b/arch/x86/include/asm/irq.h
index 57873beb3292..0ea10f27d613 100644
--- a/arch/x86/include/asm/irq.h
+++ b/arch/x86/include/asm/irq.h
@@ -33,7 +33,7 @@ extern void (*x86_platform_ipi_callback)(void);
 extern void native_init_IRQ(void);
 extern bool handle_irq(unsigned irq, struct pt_regs *regs);
 
-extern unsigned int do_IRQ(struct pt_regs *regs);
+extern __visible unsigned int do_IRQ(struct pt_regs *regs);
 
 /* Interrupt vector management */
 extern DECLARE_BITMAP(used_vectors, NR_VECTORS);
diff --git a/arch/x86/include/asm/jump_label.h b/arch/x86/include/asm/jump_label.h
index 3a16c1483b45..6a2cefb4395a 100644
--- a/arch/x86/include/asm/jump_label.h
+++ b/arch/x86/include/asm/jump_label.h
@@ -3,18 +3,23 @@
 
 #ifdef __KERNEL__
 
+#include <linux/stringify.h>
 #include <linux/types.h>
 #include <asm/nops.h>
 #include <asm/asm.h>
 
 #define JUMP_LABEL_NOP_SIZE 5
 
-#define STATIC_KEY_INITIAL_NOP ".byte 0xe9 \n\t .long 0\n\t"
+#ifdef CONFIG_X86_64
+# define STATIC_KEY_INIT_NOP P6_NOP5_ATOMIC
+#else
+# define STATIC_KEY_INIT_NOP GENERIC_NOP5_ATOMIC
+#endif
 
 static __always_inline bool arch_static_branch(struct static_key *key)
 {
-	asm goto("1:"
-		STATIC_KEY_INITIAL_NOP
+	asm_volatile_goto("1:"
+		".byte " __stringify(STATIC_KEY_INIT_NOP) "\n\t"
 		".pushsection __jump_table,  \"aw\" \n\t"
 		_ASM_ALIGN "\n\t"
 		_ASM_PTR "1b, %l[l_yes], %c0 \n\t"
diff --git a/arch/x86/include/asm/kprobes.h b/arch/x86/include/asm/kprobes.h
index 5a6d2873f80e..9454c167629f 100644
--- a/arch/x86/include/asm/kprobes.h
+++ b/arch/x86/include/asm/kprobes.h
@@ -49,10 +49,10 @@ typedef u8 kprobe_opcode_t;
 #define flush_insn_slot(p)	do { } while (0)
 
 /* optinsn template addresses */
-extern kprobe_opcode_t optprobe_template_entry;
-extern kprobe_opcode_t optprobe_template_val;
-extern kprobe_opcode_t optprobe_template_call;
-extern kprobe_opcode_t optprobe_template_end;
+extern __visible kprobe_opcode_t optprobe_template_entry;
+extern __visible kprobe_opcode_t optprobe_template_val;
+extern __visible kprobe_opcode_t optprobe_template_call;
+extern __visible kprobe_opcode_t optprobe_template_end;
 #define MAX_OPTIMIZED_LENGTH (MAX_INSN_SIZE + RELATIVE_ADDR_SIZE)
 #define MAX_OPTINSN_SIZE 				\
 	(((unsigned long)&optprobe_template_end -	\
@@ -62,7 +62,7 @@ extern kprobe_opcode_t optprobe_template_end;
 extern const int kretprobe_blacklist_size;
 
 void arch_remove_kprobe(struct kprobe *p);
-void kretprobe_trampoline(void);
+asmlinkage void kretprobe_trampoline(void);
 
 /* Architecture specific copy of original instruction*/
 struct arch_specific_insn {
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index f87f7fcefa0a..c76ff74a98f2 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -286,6 +286,7 @@ struct kvm_mmu {
 	u64 *pae_root;
 	u64 *lm_root;
 	u64 rsvd_bits_mask[2][4];
+	u64 bad_mt_xwr;
 
 	/*
 	 * Bitmap: bit set = last pte in walk
@@ -323,6 +324,7 @@ struct kvm_pmu {
 	u64 global_ovf_ctrl;
 	u64 counter_bitmask[2];
 	u64 global_ctrl_mask;
+	u64 reserved_bits;
 	u8 version;
 	struct kvm_pmc gp_counters[INTEL_PMC_MAX_GENERIC];
 	struct kvm_pmc fixed_counters[INTEL_PMC_MAX_FIXED];
@@ -511,6 +513,14 @@ struct kvm_vcpu_arch {
 	 * instruction.
 	 */
 	bool write_fault_to_shadow_pgtable;
+
+	/* set at EPT violation at this point */
+	unsigned long exit_qualification;
+
+	/* pv related host specific info */
+	struct {
+		bool pv_unhalted;
+	} pv;
 };
 
 struct kvm_lpage_info {
@@ -802,8 +812,8 @@ extern u32  kvm_min_guest_tsc_khz;
 extern u32  kvm_max_guest_tsc_khz;
 
 enum emulation_result {
-	EMULATE_DONE,       /* no further processing */
-	EMULATE_DO_MMIO,      /* kvm_run filled with mmio request */
+	EMULATE_DONE,         /* no further processing */
+	EMULATE_USER_EXIT,    /* kvm_run ready for userspace exit */
 	EMULATE_FAIL,         /* can't emulate this instruction */
 };
 
diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h
index 695399f2d5eb..1df115909758 100644
--- a/arch/x86/include/asm/kvm_para.h
+++ b/arch/x86/include/asm/kvm_para.h
@@ -85,26 +85,20 @@ static inline long kvm_hypercall4(unsigned int nr, unsigned long p1,
 	return ret;
 }
 
-static inline bool kvm_para_available(void)
+static inline uint32_t kvm_cpuid_base(void)
 {
-	unsigned int eax, ebx, ecx, edx;
-	char signature[13];
-
 	if (boot_cpu_data.cpuid_level < 0)
-		return false;	/* So we don't blow up on old processors */
+		return 0;	/* So we don't blow up on old processors */
 
-	if (cpu_has_hypervisor) {
-		cpuid(KVM_CPUID_SIGNATURE, &eax, &ebx, &ecx, &edx);
-		memcpy(signature + 0, &ebx, 4);
-		memcpy(signature + 4, &ecx, 4);
-		memcpy(signature + 8, &edx, 4);
-		signature[12] = 0;
+	if (cpu_has_hypervisor)
+		return hypervisor_cpuid_base("KVMKVMKVM\0\0\0", 0);
 
-		if (strcmp(signature, "KVMKVMKVM") == 0)
-			return true;
-	}
+	return 0;
+}
 
-	return false;
+static inline bool kvm_para_available(void)
+{
+	return kvm_cpuid_base() != 0;
 }
 
 static inline unsigned int kvm_arch_para_features(void)
@@ -118,10 +112,20 @@ void kvm_async_pf_task_wait(u32 token);
 void kvm_async_pf_task_wake(u32 token);
 u32 kvm_read_and_reset_pf_reason(void);
 extern void kvm_disable_steal_time(void);
-#else
-#define kvm_guest_init() do { } while (0)
+
+#ifdef CONFIG_PARAVIRT_SPINLOCKS
+void __init kvm_spinlock_init(void);
+#else /* !CONFIG_PARAVIRT_SPINLOCKS */
+static inline void kvm_spinlock_init(void)
+{
+}
+#endif /* CONFIG_PARAVIRT_SPINLOCKS */
+
+#else /* CONFIG_KVM_GUEST */
+#define kvm_guest_init() do {} while (0)
 #define kvm_async_pf_task_wait(T) do {} while(0)
 #define kvm_async_pf_task_wake(T) do {} while(0)
+
 static inline u32 kvm_read_and_reset_pf_reason(void)
 {
 	return 0;
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index 29e3093bbd21..cbe6b9e404ce 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -32,11 +32,20 @@
 #define MCI_STATUS_PCC   (1ULL<<57)  /* processor context corrupt */
 #define MCI_STATUS_S	 (1ULL<<56)  /* Signaled machine check */
 #define MCI_STATUS_AR	 (1ULL<<55)  /* Action required */
-#define MCACOD		  0xffff     /* MCA Error Code */
+
+/*
+ * Note that the full MCACOD field of IA32_MCi_STATUS MSR is
+ * bits 15:0.  But bit 12 is the 'F' bit, defined for corrected
+ * errors to indicate that errors are being filtered by hardware.
+ * We should mask out bit 12 when looking for specific signatures
+ * of uncorrected errors - so the F bit is deliberately skipped
+ * in this #define.
+ */
+#define MCACOD		  0xefff     /* MCA Error Code */
 
 /* Architecturally defined codes from SDM Vol. 3B Chapter 15 */
 #define MCACOD_SCRUB	0x00C0	/* 0xC0-0xCF Memory Scrubbing */
-#define MCACOD_SCRUBMSK	0xfff0
+#define MCACOD_SCRUBMSK	0xeff0	/* Skip bit 12 ('F' bit) */
 #define MCACOD_L3WB	0x017A	/* L3 Explicit Writeback */
 #define MCACOD_DATA	0x0134	/* Data Load */
 #define MCACOD_INSTR	0x0150	/* Instruction Fetch */
@@ -188,6 +197,9 @@ extern void register_mce_write_callback(ssize_t (*)(struct file *filp,
 				    const char __user *ubuf,
 				    size_t usize, loff_t *off));
 
+/* Disable CMCI/polling for MCA bank claimed by firmware */
+extern void mce_disable_bank(int bank);
+
 /*
  * Exception handler
  */
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index cdbf36776106..be12c534fd59 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -45,22 +45,28 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 		/* Re-load page tables */
 		load_cr3(next->pgd);
 
-		/* stop flush ipis for the previous mm */
+		/* Stop flush ipis for the previous mm */
 		cpumask_clear_cpu(cpu, mm_cpumask(prev));
 
-		/*
-		 * load the LDT, if the LDT is different:
-		 */
+		/* Load the LDT, if the LDT is different: */
 		if (unlikely(prev->context.ldt != next->context.ldt))
 			load_LDT_nolock(&next->context);
 	}
 #ifdef CONFIG_SMP
-	else {
+	  else {
 		this_cpu_write(cpu_tlbstate.state, TLBSTATE_OK);
 		BUG_ON(this_cpu_read(cpu_tlbstate.active_mm) != next);
 
-		if (!cpumask_test_and_set_cpu(cpu, mm_cpumask(next))) {
-			/* We were in lazy tlb mode and leave_mm disabled
+		if (!cpumask_test_cpu(cpu, mm_cpumask(next))) {
+			/*
+			 * On established mms, the mm_cpumask is only changed
+			 * from irq context, from ptep_clear_flush() while in
+			 * lazy tlb mode, and here. Irqs are blocked during
+			 * schedule, protecting us from simultaneous changes.
+			 */
+			cpumask_set_cpu(cpu, mm_cpumask(next));
+			/*
+			 * We were in lazy tlb mode and leave_mm disabled
 			 * tlb flush IPI delivery. We must reload CR3
 			 * to make sure to use no freed page tables.
 			 */
diff --git a/arch/x86/include/asm/mutex_64.h b/arch/x86/include/asm/mutex_64.h
index 2c543fff241b..07537a44216e 100644
--- a/arch/x86/include/asm/mutex_64.h
+++ b/arch/x86/include/asm/mutex_64.h
@@ -16,6 +16,20 @@
  *
  * Atomically decrements @v and calls <fail_fn> if the result is negative.
  */
+#ifdef CC_HAVE_ASM_GOTO
+static inline void __mutex_fastpath_lock(atomic_t *v,
+					 void (*fail_fn)(atomic_t *))
+{
+	asm_volatile_goto(LOCK_PREFIX "   decl %0\n"
+			  "   jns %l[exit]\n"
+			  : : "m" (v->counter)
+			  : "memory", "cc"
+			  : exit);
+	fail_fn(v);
+exit:
+	return;
+}
+#else
 #define __mutex_fastpath_lock(v, fail_fn)			\
 do {								\
 	unsigned long dummy;					\
@@ -32,6 +46,7 @@ do {								\
 		     : "rax", "rsi", "rdx", "rcx",		\
 		       "r8", "r9", "r10", "r11", "memory");	\
 } while (0)
+#endif
 
 /**
  *  __mutex_fastpath_lock_retval - try to take the lock by moving the count
@@ -56,6 +71,20 @@ static inline int __mutex_fastpath_lock_retval(atomic_t *count)
  *
  * Atomically increments @v and calls <fail_fn> if the result is nonpositive.
  */
+#ifdef CC_HAVE_ASM_GOTO
+static inline void __mutex_fastpath_unlock(atomic_t *v,
+					   void (*fail_fn)(atomic_t *))
+{
+	asm_volatile_goto(LOCK_PREFIX "   incl %0\n"
+			  "   jg %l[exit]\n"
+			  : : "m" (v->counter)
+			  : "memory", "cc"
+			  : exit);
+	fail_fn(v);
+exit:
+	return;
+}
+#else
 #define __mutex_fastpath_unlock(v, fail_fn)			\
 do {								\
 	unsigned long dummy;					\
@@ -72,6 +101,7 @@ do {								\
 		     : "rax", "rsi", "rdx", "rcx",		\
 		       "r8", "r9", "r10", "r11", "memory");	\
 } while (0)
+#endif
 
 #define __mutex_slowpath_needs_to_unlock()	1
 
diff --git a/arch/x86/include/asm/page_32_types.h b/arch/x86/include/asm/page_32_types.h
index ef17af013475..f48b17df4224 100644
--- a/arch/x86/include/asm/page_32_types.h
+++ b/arch/x86/include/asm/page_32_types.h
@@ -15,6 +15,8 @@
  */
 #define __PAGE_OFFSET		_AC(CONFIG_PAGE_OFFSET, UL)
 
+#define __START_KERNEL_map	__PAGE_OFFSET
+
 #define THREAD_SIZE_ORDER	1
 #define THREAD_SIZE		(PAGE_SIZE << THREAD_SIZE_ORDER)
 
diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h
index 6c896fbe21db..43dcd804ebd5 100644
--- a/arch/x86/include/asm/page_64_types.h
+++ b/arch/x86/include/asm/page_64_types.h
@@ -32,11 +32,6 @@
  */
 #define __PAGE_OFFSET           _AC(0xffff880000000000, UL)
 
-#define __PHYSICAL_START	((CONFIG_PHYSICAL_START +	 	\
-				  (CONFIG_PHYSICAL_ALIGN - 1)) &	\
-				 ~(CONFIG_PHYSICAL_ALIGN - 1))
-
-#define __START_KERNEL		(__START_KERNEL_map + __PHYSICAL_START)
 #define __START_KERNEL_map	_AC(0xffffffff80000000, UL)
 
 /* See Documentation/x86/x86_64/mm.txt for a description of the memory map. */
diff --git a/arch/x86/include/asm/page_types.h b/arch/x86/include/asm/page_types.h
index 54c97879195e..f97fbe3abb67 100644
--- a/arch/x86/include/asm/page_types.h
+++ b/arch/x86/include/asm/page_types.h
@@ -33,6 +33,11 @@
 	(((current->personality & READ_IMPLIES_EXEC) ? VM_EXEC : 0 ) | \
 	 VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
 
+#define __PHYSICAL_START	ALIGN(CONFIG_PHYSICAL_START, \
+				      CONFIG_PHYSICAL_ALIGN)
+
+#define __START_KERNEL		(__START_KERNEL_map + __PHYSICAL_START)
+
 #ifdef CONFIG_X86_64
 #include <asm/page_64_types.h>
 #else
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index cfdc9ee4c900..401f350ef71b 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -712,36 +712,16 @@ static inline void __set_fixmap(unsigned /* enum fixed_addresses */ idx,
 
 #if defined(CONFIG_SMP) && defined(CONFIG_PARAVIRT_SPINLOCKS)
 
-static inline int arch_spin_is_locked(struct arch_spinlock *lock)
+static __always_inline void __ticket_lock_spinning(struct arch_spinlock *lock,
+							__ticket_t ticket)
 {
-	return PVOP_CALL1(int, pv_lock_ops.spin_is_locked, lock);
+	PVOP_VCALLEE2(pv_lock_ops.lock_spinning, lock, ticket);
 }
 
-static inline int arch_spin_is_contended(struct arch_spinlock *lock)
+static __always_inline void __ticket_unlock_kick(struct arch_spinlock *lock,
+							__ticket_t ticket)
 {
-	return PVOP_CALL1(int, pv_lock_ops.spin_is_contended, lock);
-}
-#define arch_spin_is_contended	arch_spin_is_contended
-
-static __always_inline void arch_spin_lock(struct arch_spinlock *lock)
-{
-	PVOP_VCALL1(pv_lock_ops.spin_lock, lock);
-}
-
-static __always_inline void arch_spin_lock_flags(struct arch_spinlock *lock,
-						  unsigned long flags)
-{
-	PVOP_VCALL2(pv_lock_ops.spin_lock_flags, lock, flags);
-}
-
-static __always_inline int arch_spin_trylock(struct arch_spinlock *lock)
-{
-	return PVOP_CALL1(int, pv_lock_ops.spin_trylock, lock);
-}
-
-static __always_inline void arch_spin_unlock(struct arch_spinlock *lock)
-{
-	PVOP_VCALL1(pv_lock_ops.spin_unlock, lock);
+	PVOP_VCALL2(pv_lock_ops.unlock_kick, lock, ticket);
 }
 
 #endif
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 0db1fcac668c..aab8f671b523 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -327,13 +327,15 @@ struct pv_mmu_ops {
 };
 
 struct arch_spinlock;
+#ifdef CONFIG_SMP
+#include <asm/spinlock_types.h>
+#else
+typedef u16 __ticket_t;
+#endif
+
 struct pv_lock_ops {
-	int (*spin_is_locked)(struct arch_spinlock *lock);
-	int (*spin_is_contended)(struct arch_spinlock *lock);
-	void (*spin_lock)(struct arch_spinlock *lock);
-	void (*spin_lock_flags)(struct arch_spinlock *lock, unsigned long flags);
-	int (*spin_trylock)(struct arch_spinlock *lock);
-	void (*spin_unlock)(struct arch_spinlock *lock);
+	struct paravirt_callee_save lock_spinning;
+	void (*unlock_kick)(struct arch_spinlock *lock, __ticket_t ticket);
 };
 
 /* This contains all the paravirt structures: we get a convenient
@@ -387,7 +389,8 @@ extern struct pv_lock_ops pv_lock_ops;
 
 /* Simple instruction patching code. */
 #define DEF_NATIVE(ops, name, code) 					\
-	extern const char start_##ops##_##name[], end_##ops##_##name[];	\
+	extern const char start_##ops##_##name[] __visible,		\
+			  end_##ops##_##name[] __visible;		\
 	asm("start_" #ops "_" #name ": " code "; end_" #ops "_" #name ":")
 
 unsigned paravirt_patch_nop(void);
diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h
index d9e9e6c7ed32..7d7443283a9d 100644
--- a/arch/x86/include/asm/pci.h
+++ b/arch/x86/include/asm/pci.h
@@ -100,29 +100,6 @@ static inline void early_quirks(void) { }
 extern void pci_iommu_alloc(void);
 
 #ifdef CONFIG_PCI_MSI
-/* MSI arch specific hooks */
-static inline int x86_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
-{
-	return x86_msi.setup_msi_irqs(dev, nvec, type);
-}
-
-static inline void x86_teardown_msi_irqs(struct pci_dev *dev)
-{
-	x86_msi.teardown_msi_irqs(dev);
-}
-
-static inline void x86_teardown_msi_irq(unsigned int irq)
-{
-	x86_msi.teardown_msi_irq(irq);
-}
-static inline void x86_restore_msi_irqs(struct pci_dev *dev, int irq)
-{
-	x86_msi.restore_msi_irqs(dev, irq);
-}
-#define arch_setup_msi_irqs x86_setup_msi_irqs
-#define arch_teardown_msi_irqs x86_teardown_msi_irqs
-#define arch_teardown_msi_irq x86_teardown_msi_irq
-#define arch_restore_msi_irqs x86_restore_msi_irqs
 /* implemented in arch/x86/kernel/apic/io_apic. */
 struct msi_desc;
 int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type);
@@ -130,16 +107,9 @@ void native_teardown_msi_irq(unsigned int irq);
 void native_restore_msi_irqs(struct pci_dev *dev, int irq);
 int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc,
 		  unsigned int irq_base, unsigned int irq_offset);
-/* default to the implementation in drivers/lib/msi.c */
-#define HAVE_DEFAULT_MSI_TEARDOWN_IRQS
-#define HAVE_DEFAULT_MSI_RESTORE_IRQS
-void default_teardown_msi_irqs(struct pci_dev *dev);
-void default_restore_msi_irqs(struct pci_dev *dev, int irq);
 #else
 #define native_setup_msi_irqs		NULL
 #define native_teardown_msi_irq		NULL
-#define default_teardown_msi_irqs	NULL
-#define default_restore_msi_irqs	NULL
 #endif
 
 #define PCI_DMA_BUS_IS_PHYS (dma_ops->is_phys)
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 1c00631164c2..3d1999458709 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -22,7 +22,8 @@
  * ZERO_PAGE is a global shared page that is always zero: used
  * for zero-mapped memory areas etc..
  */
-extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
+extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]
+	__visible;
 #define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page))
 
 extern spinlock_t pgd_lock;
@@ -314,21 +315,6 @@ static inline pmd_t pmd_mksoft_dirty(pmd_t pmd)
 	return pmd_set_flags(pmd, _PAGE_SOFT_DIRTY);
 }
 
-static inline pte_t pte_swp_mksoft_dirty(pte_t pte)
-{
-	return pte_set_flags(pte, _PAGE_SWP_SOFT_DIRTY);
-}
-
-static inline int pte_swp_soft_dirty(pte_t pte)
-{
-	return pte_flags(pte) & _PAGE_SWP_SOFT_DIRTY;
-}
-
-static inline pte_t pte_swp_clear_soft_dirty(pte_t pte)
-{
-	return pte_clear_flags(pte, _PAGE_SWP_SOFT_DIRTY);
-}
-
 static inline pte_t pte_file_clear_soft_dirty(pte_t pte)
 {
 	return pte_clear_flags(pte, _PAGE_SOFT_DIRTY);
@@ -445,6 +431,7 @@ pte_t *populate_extra_pte(unsigned long vaddr);
 
 #ifndef __ASSEMBLY__
 #include <linux/mm_types.h>
+#include <linux/mmdebug.h>
 #include <linux/log2.h>
 
 static inline int pte_none(pte_t pte)
@@ -863,6 +850,24 @@ static inline void update_mmu_cache_pmd(struct vm_area_struct *vma,
 {
 }
 
+static inline pte_t pte_swp_mksoft_dirty(pte_t pte)
+{
+	VM_BUG_ON(pte_present(pte));
+	return pte_set_flags(pte, _PAGE_SWP_SOFT_DIRTY);
+}
+
+static inline int pte_swp_soft_dirty(pte_t pte)
+{
+	VM_BUG_ON(pte_present(pte));
+	return pte_flags(pte) & _PAGE_SWP_SOFT_DIRTY;
+}
+
+static inline pte_t pte_swp_clear_soft_dirty(pte_t pte)
+{
+	VM_BUG_ON(pte_present(pte));
+	return pte_clear_flags(pte, _PAGE_SWP_SOFT_DIRTY);
+}
+
 #include <asm-generic/pgtable.h>
 #endif	/* __ASSEMBLY__ */
 
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index f4843e031131..0ecac257fb26 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -75,6 +75,9 @@
  * with swap entry format. On x86 bits 6 and 7 are *not* involved
  * into swap entry computation, but bit 6 is used for nonlinear
  * file mapping, so we borrow bit 7 for soft dirty tracking.
+ *
+ * Please note that this bit must be treated as swap dirty page
+ * mark if and only if the PTE has present bit clear!
  */
 #ifdef CONFIG_MEM_SOFT_DIRTY
 #define _PAGE_SWP_SOFT_DIRTY	_PAGE_PSE
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 24cf5aefb704..987c75ecc334 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -412,7 +412,7 @@ union irq_stack_union {
 	};
 };
 
-DECLARE_PER_CPU_FIRST(union irq_stack_union, irq_stack_union);
+DECLARE_PER_CPU_FIRST(union irq_stack_union, irq_stack_union) __visible;
 DECLARE_INIT_PER_CPU(irq_stack_union);
 
 DECLARE_PER_CPU(char *, irq_stack_ptr);
@@ -942,33 +942,19 @@ extern int set_tsc_mode(unsigned int val);
 
 extern u16 amd_get_nb_id(int cpu);
 
-struct aperfmperf {
-	u64 aperf, mperf;
-};
-
-static inline void get_aperfmperf(struct aperfmperf *am)
+static inline uint32_t hypervisor_cpuid_base(const char *sig, uint32_t leaves)
 {
-	WARN_ON_ONCE(!boot_cpu_has(X86_FEATURE_APERFMPERF));
-
-	rdmsrl(MSR_IA32_APERF, am->aperf);
-	rdmsrl(MSR_IA32_MPERF, am->mperf);
-}
+	uint32_t base, eax, signature[3];
 
-#define APERFMPERF_SHIFT 10
+	for (base = 0x40000000; base < 0x40010000; base += 0x100) {
+		cpuid(base, &eax, &signature[0], &signature[1], &signature[2]);
 
-static inline
-unsigned long calc_aperfmperf_ratio(struct aperfmperf *old,
-				    struct aperfmperf *new)
-{
-	u64 aperf = new->aperf - old->aperf;
-	u64 mperf = new->mperf - old->mperf;
-	unsigned long ratio = aperf;
-
-	mperf >>= APERFMPERF_SHIFT;
-	if (mperf)
-		ratio = div64_u64(aperf, mperf);
+		if (!memcmp(sig, signature, 12) &&
+		    (leaves == 0 || ((eax - base) >= leaves)))
+			return base;
+	}
 
-	return ratio;
+	return 0;
 }
 
 extern unsigned long arch_align_stack(unsigned long sp);
diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h
index 109a9dd5d454..be8269b00e2a 100644
--- a/arch/x86/include/asm/pvclock.h
+++ b/arch/x86/include/asm/pvclock.h
@@ -93,7 +93,6 @@ unsigned __pvclock_read_cycles(const struct pvclock_vcpu_time_info *src,
 
 struct pvclock_vsyscall_time_info {
 	struct pvclock_vcpu_time_info pvti;
-	u32 migrate_count;
 } __attribute__((__aligned__(SMP_CACHE_BYTES)));
 
 #define PVTI_SIZE sizeof(struct pvclock_vsyscall_time_info)
diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h
index b7bf3505e1ec..347555492dad 100644
--- a/arch/x86/include/asm/setup.h
+++ b/arch/x86/include/asm/setup.h
@@ -6,6 +6,8 @@
 
 #define COMMAND_LINE_SIZE 2048
 
+#include <linux/linkage.h>
+
 #ifdef __i386__
 
 #include <linux/pfn.h>
@@ -108,11 +110,11 @@ void *extend_brk(size_t size, size_t align);
 extern void probe_roms(void);
 #ifdef __i386__
 
-void __init i386_start_kernel(void);
+asmlinkage void __init i386_start_kernel(void);
 
 #else
-void __init x86_64_start_kernel(char *real_mode);
-void __init x86_64_start_reservations(char *real_mode_data);
+asmlinkage void __init x86_64_start_kernel(char *real_mode);
+asmlinkage void __init x86_64_start_reservations(char *real_mode_data);
 
 #endif /* __i386__ */
 #endif /* _SETUP */
diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h
index 2f4d924fe6c9..645cad2c95ff 100644
--- a/arch/x86/include/asm/special_insns.h
+++ b/arch/x86/include/asm/special_insns.h
@@ -101,7 +101,7 @@ static inline void native_wbinvd(void)
 	asm volatile("wbinvd": : :"memory");
 }
 
-extern void native_load_gs_index(unsigned);
+extern asmlinkage void native_load_gs_index(unsigned);
 
 #ifdef CONFIG_PARAVIRT
 #include <asm/paravirt.h>
diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h
index e3ddd7db723f..bf156ded74b5 100644
--- a/arch/x86/include/asm/spinlock.h
+++ b/arch/x86/include/asm/spinlock.h
@@ -1,11 +1,14 @@
 #ifndef _ASM_X86_SPINLOCK_H
 #define _ASM_X86_SPINLOCK_H
 
+#include <linux/jump_label.h>
 #include <linux/atomic.h>
 #include <asm/page.h>
 #include <asm/processor.h>
 #include <linux/compiler.h>
 #include <asm/paravirt.h>
+#include <asm/bitops.h>
+
 /*
  * Your basic SMP spinlocks, allowing only a single CPU anywhere
  *
@@ -34,6 +37,36 @@
 # define UNLOCK_LOCK_PREFIX
 #endif
 
+/* How long a lock should spin before we consider blocking */
+#define SPIN_THRESHOLD	(1 << 15)
+
+extern struct static_key paravirt_ticketlocks_enabled;
+static __always_inline bool static_key_false(struct static_key *key);
+
+#ifdef CONFIG_PARAVIRT_SPINLOCKS
+
+static inline void __ticket_enter_slowpath(arch_spinlock_t *lock)
+{
+	set_bit(0, (volatile unsigned long *)&lock->tickets.tail);
+}
+
+#else  /* !CONFIG_PARAVIRT_SPINLOCKS */
+static __always_inline void __ticket_lock_spinning(arch_spinlock_t *lock,
+							__ticket_t ticket)
+{
+}
+static inline void __ticket_unlock_kick(arch_spinlock_t *lock,
+							__ticket_t ticket)
+{
+}
+
+#endif /* CONFIG_PARAVIRT_SPINLOCKS */
+
+static __always_inline int arch_spin_value_unlocked(arch_spinlock_t lock)
+{
+	return lock.tickets.head == lock.tickets.tail;
+}
+
 /*
  * Ticket locks are conceptually two parts, one indicating the current head of
  * the queue, and the other indicating the current tail. The lock is acquired
@@ -47,81 +80,101 @@
  * in the high part, because a wide xadd increment of the low part would carry
  * up and contaminate the high part.
  */
-static __always_inline void __ticket_spin_lock(arch_spinlock_t *lock)
+static __always_inline void arch_spin_lock(arch_spinlock_t *lock)
 {
-	register struct __raw_tickets inc = { .tail = 1 };
+	register struct __raw_tickets inc = { .tail = TICKET_LOCK_INC };
 
 	inc = xadd(&lock->tickets, inc);
+	if (likely(inc.head == inc.tail))
+		goto out;
 
+	inc.tail &= ~TICKET_SLOWPATH_FLAG;
 	for (;;) {
-		if (inc.head == inc.tail)
-			break;
-		cpu_relax();
-		inc.head = ACCESS_ONCE(lock->tickets.head);
+		unsigned count = SPIN_THRESHOLD;
+
+		do {
+			if (ACCESS_ONCE(lock->tickets.head) == inc.tail)
+				goto out;
+			cpu_relax();
+		} while (--count);
+		__ticket_lock_spinning(lock, inc.tail);
 	}
-	barrier();		/* make sure nothing creeps before the lock is taken */
+out:	barrier();	/* make sure nothing creeps before the lock is taken */
 }
 
-static __always_inline int __ticket_spin_trylock(arch_spinlock_t *lock)
+static __always_inline int arch_spin_trylock(arch_spinlock_t *lock)
 {
 	arch_spinlock_t old, new;
 
 	old.tickets = ACCESS_ONCE(lock->tickets);
-	if (old.tickets.head != old.tickets.tail)
+	if (old.tickets.head != (old.tickets.tail & ~TICKET_SLOWPATH_FLAG))
 		return 0;
 
-	new.head_tail = old.head_tail + (1 << TICKET_SHIFT);
+	new.head_tail = old.head_tail + (TICKET_LOCK_INC << TICKET_SHIFT);
 
 	/* cmpxchg is a full barrier, so nothing can move before it */
 	return cmpxchg(&lock->head_tail, old.head_tail, new.head_tail) == old.head_tail;
 }
 
-static __always_inline void __ticket_spin_unlock(arch_spinlock_t *lock)
+static inline void __ticket_unlock_slowpath(arch_spinlock_t *lock,
+					    arch_spinlock_t old)
 {
-	__add(&lock->tickets.head, 1, UNLOCK_LOCK_PREFIX);
+	arch_spinlock_t new;
+
+	BUILD_BUG_ON(((__ticket_t)NR_CPUS) != NR_CPUS);
+
+	/* Perform the unlock on the "before" copy */
+	old.tickets.head += TICKET_LOCK_INC;
+
+	/* Clear the slowpath flag */
+	new.head_tail = old.head_tail & ~(TICKET_SLOWPATH_FLAG << TICKET_SHIFT);
+
+	/*
+	 * If the lock is uncontended, clear the flag - use cmpxchg in
+	 * case it changes behind our back though.
+	 */
+	if (new.tickets.head != new.tickets.tail ||
+	    cmpxchg(&lock->head_tail, old.head_tail,
+					new.head_tail) != old.head_tail) {
+		/*
+		 * Lock still has someone queued for it, so wake up an
+		 * appropriate waiter.
+		 */
+		__ticket_unlock_kick(lock, old.tickets.head);
+	}
 }
 
-static inline int __ticket_spin_is_locked(arch_spinlock_t *lock)
+static __always_inline void arch_spin_unlock(arch_spinlock_t *lock)
 {
-	struct __raw_tickets tmp = ACCESS_ONCE(lock->tickets);
+	if (TICKET_SLOWPATH_FLAG &&
+	    static_key_false(&paravirt_ticketlocks_enabled)) {
+		arch_spinlock_t prev;
 
-	return tmp.tail != tmp.head;
-}
+		prev = *lock;
+		add_smp(&lock->tickets.head, TICKET_LOCK_INC);
 
-static inline int __ticket_spin_is_contended(arch_spinlock_t *lock)
-{
-	struct __raw_tickets tmp = ACCESS_ONCE(lock->tickets);
+		/* add_smp() is a full mb() */
 
-	return (__ticket_t)(tmp.tail - tmp.head) > 1;
+		if (unlikely(lock->tickets.tail & TICKET_SLOWPATH_FLAG))
+			__ticket_unlock_slowpath(lock, prev);
+	} else
+		__add(&lock->tickets.head, TICKET_LOCK_INC, UNLOCK_LOCK_PREFIX);
 }
 
-#ifndef CONFIG_PARAVIRT_SPINLOCKS
-
 static inline int arch_spin_is_locked(arch_spinlock_t *lock)
 {
-	return __ticket_spin_is_locked(lock);
-}
-
-static inline int arch_spin_is_contended(arch_spinlock_t *lock)
-{
-	return __ticket_spin_is_contended(lock);
-}
-#define arch_spin_is_contended	arch_spin_is_contended
+	struct __raw_tickets tmp = ACCESS_ONCE(lock->tickets);
 
-static __always_inline void arch_spin_lock(arch_spinlock_t *lock)
-{
-	__ticket_spin_lock(lock);
+	return tmp.tail != tmp.head;
 }
 
-static __always_inline int arch_spin_trylock(arch_spinlock_t *lock)
+static inline int arch_spin_is_contended(arch_spinlock_t *lock)
 {
-	return __ticket_spin_trylock(lock);
-}
+	struct __raw_tickets tmp = ACCESS_ONCE(lock->tickets);
 
-static __always_inline void arch_spin_unlock(arch_spinlock_t *lock)
-{
-	__ticket_spin_unlock(lock);
+	return (__ticket_t)(tmp.tail - tmp.head) > TICKET_LOCK_INC;
 }
+#define arch_spin_is_contended	arch_spin_is_contended
 
 static __always_inline void arch_spin_lock_flags(arch_spinlock_t *lock,
 						  unsigned long flags)
@@ -129,8 +182,6 @@ static __always_inline void arch_spin_lock_flags(arch_spinlock_t *lock,
 	arch_spin_lock(lock);
 }
 
-#endif	/* CONFIG_PARAVIRT_SPINLOCKS */
-
 static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
 {
 	while (arch_spin_is_locked(lock))
diff --git a/arch/x86/include/asm/spinlock_types.h b/arch/x86/include/asm/spinlock_types.h
index ad0ad07fc006..4f1bea19945b 100644
--- a/arch/x86/include/asm/spinlock_types.h
+++ b/arch/x86/include/asm/spinlock_types.h
@@ -1,13 +1,17 @@
 #ifndef _ASM_X86_SPINLOCK_TYPES_H
 #define _ASM_X86_SPINLOCK_TYPES_H
 
-#ifndef __LINUX_SPINLOCK_TYPES_H
-# error "please don't include this file directly"
-#endif
-
 #include <linux/types.h>
 
-#if (CONFIG_NR_CPUS < 256)
+#ifdef CONFIG_PARAVIRT_SPINLOCKS
+#define __TICKET_LOCK_INC	2
+#define TICKET_SLOWPATH_FLAG	((__ticket_t)1)
+#else
+#define __TICKET_LOCK_INC	1
+#define TICKET_SLOWPATH_FLAG	((__ticket_t)0)
+#endif
+
+#if (CONFIG_NR_CPUS < (256 / __TICKET_LOCK_INC))
 typedef u8  __ticket_t;
 typedef u16 __ticketpair_t;
 #else
@@ -15,6 +19,8 @@ typedef u16 __ticket_t;
 typedef u32 __ticketpair_t;
 #endif
 
+#define TICKET_LOCK_INC	((__ticket_t)__TICKET_LOCK_INC)
+
 #define TICKET_SHIFT	(sizeof(__ticket_t) * 8)
 
 typedef struct arch_spinlock {
diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h
index 4ec45b3abba1..d7f3b3b78ac3 100644
--- a/arch/x86/include/asm/switch_to.h
+++ b/arch/x86/include/asm/switch_to.h
@@ -2,8 +2,8 @@
 #define _ASM_X86_SWITCH_TO_H
 
 struct task_struct; /* one of the stranger aspects of C forward declarations */
-struct task_struct *__switch_to(struct task_struct *prev,
-				struct task_struct *next);
+__visible struct task_struct *__switch_to(struct task_struct *prev,
+					   struct task_struct *next);
 struct tss_struct;
 void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p,
 		      struct tss_struct *tss);
diff --git a/arch/x86/include/asm/sync_bitops.h b/arch/x86/include/asm/sync_bitops.h
index 9d09b4073b60..05af3b31d522 100644
--- a/arch/x86/include/asm/sync_bitops.h
+++ b/arch/x86/include/asm/sync_bitops.h
@@ -26,9 +26,9 @@
  * Note that @nr may be almost arbitrarily large; this function is not
  * restricted to acting on a single-word quantity.
  */
-static inline void sync_set_bit(int nr, volatile unsigned long *addr)
+static inline void sync_set_bit(long nr, volatile unsigned long *addr)
 {
-	asm volatile("lock; btsl %1,%0"
+	asm volatile("lock; bts %1,%0"
 		     : "+m" (ADDR)
 		     : "Ir" (nr)
 		     : "memory");
@@ -44,9 +44,9 @@ static inline void sync_set_bit(int nr, volatile unsigned long *addr)
  * you should call smp_mb__before_clear_bit() and/or smp_mb__after_clear_bit()
  * in order to ensure changes are visible on other processors.
  */
-static inline void sync_clear_bit(int nr, volatile unsigned long *addr)
+static inline void sync_clear_bit(long nr, volatile unsigned long *addr)
 {
-	asm volatile("lock; btrl %1,%0"
+	asm volatile("lock; btr %1,%0"
 		     : "+m" (ADDR)
 		     : "Ir" (nr)
 		     : "memory");
@@ -61,9 +61,9 @@ static inline void sync_clear_bit(int nr, volatile unsigned long *addr)
  * Note that @nr may be almost arbitrarily large; this function is not
  * restricted to acting on a single-word quantity.
  */
-static inline void sync_change_bit(int nr, volatile unsigned long *addr)
+static inline void sync_change_bit(long nr, volatile unsigned long *addr)
 {
-	asm volatile("lock; btcl %1,%0"
+	asm volatile("lock; btc %1,%0"
 		     : "+m" (ADDR)
 		     : "Ir" (nr)
 		     : "memory");
@@ -77,11 +77,11 @@ static inline void sync_change_bit(int nr, volatile unsigned long *addr)
  * This operation is atomic and cannot be reordered.
  * It also implies a memory barrier.
  */
-static inline int sync_test_and_set_bit(int nr, volatile unsigned long *addr)
+static inline int sync_test_and_set_bit(long nr, volatile unsigned long *addr)
 {
 	int oldbit;
 
-	asm volatile("lock; btsl %2,%1\n\tsbbl %0,%0"
+	asm volatile("lock; bts %2,%1\n\tsbbl %0,%0"
 		     : "=r" (oldbit), "+m" (ADDR)
 		     : "Ir" (nr) : "memory");
 	return oldbit;
@@ -95,11 +95,11 @@ static inline int sync_test_and_set_bit(int nr, volatile unsigned long *addr)
  * This operation is atomic and cannot be reordered.
  * It also implies a memory barrier.
  */
-static inline int sync_test_and_clear_bit(int nr, volatile unsigned long *addr)
+static inline int sync_test_and_clear_bit(long nr, volatile unsigned long *addr)
 {
 	int oldbit;
 
-	asm volatile("lock; btrl %2,%1\n\tsbbl %0,%0"
+	asm volatile("lock; btr %2,%1\n\tsbbl %0,%0"
 		     : "=r" (oldbit), "+m" (ADDR)
 		     : "Ir" (nr) : "memory");
 	return oldbit;
@@ -113,11 +113,11 @@ static inline int sync_test_and_clear_bit(int nr, volatile unsigned long *addr)
  * This operation is atomic and cannot be reordered.
  * It also implies a memory barrier.
  */
-static inline int sync_test_and_change_bit(int nr, volatile unsigned long *addr)
+static inline int sync_test_and_change_bit(long nr, volatile unsigned long *addr)
 {
 	int oldbit;
 
-	asm volatile("lock; btcl %2,%1\n\tsbbl %0,%0"
+	asm volatile("lock; btc %2,%1\n\tsbbl %0,%0"
 		     : "=r" (oldbit), "+m" (ADDR)
 		     : "Ir" (nr) : "memory");
 	return oldbit;
diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h
index 2e188d68397c..aea284b41312 100644
--- a/arch/x86/include/asm/syscall.h
+++ b/arch/x86/include/asm/syscall.h
@@ -20,7 +20,8 @@
 #include <asm/thread_info.h>	/* for TS_COMPAT */
 #include <asm/unistd.h>
 
-extern const unsigned long sys_call_table[];
+typedef void (*sys_call_ptr_t)(void);
+extern const sys_call_ptr_t sys_call_table[];
 
 /*
  * Only the low 32 bits of orig_ax are meaningful, so we return int.
diff --git a/arch/x86/include/asm/syscalls.h b/arch/x86/include/asm/syscalls.h
index 2917a6452c49..592a6a672e07 100644
--- a/arch/x86/include/asm/syscalls.h
+++ b/arch/x86/include/asm/syscalls.h
@@ -24,7 +24,7 @@ asmlinkage long sys_iopl(unsigned int);
 asmlinkage int sys_modify_ldt(int, void __user *, unsigned long);
 
 /* kernel/signal.c */
-long sys_rt_sigreturn(void);
+asmlinkage long sys_rt_sigreturn(void);
 
 /* kernel/tls.c */
 asmlinkage long sys_set_thread_area(struct user_desc __user *);
@@ -34,7 +34,7 @@ asmlinkage long sys_get_thread_area(struct user_desc __user *);
 #ifdef CONFIG_X86_32
 
 /* kernel/signal.c */
-unsigned long sys_sigreturn(void);
+asmlinkage unsigned long sys_sigreturn(void);
 
 /* kernel/vm86_32.c */
 asmlinkage long sys_vm86old(struct vm86_struct __user *);
@@ -44,7 +44,7 @@ asmlinkage long sys_vm86(unsigned long, unsigned long);
 
 /* X86_64 only */
 /* kernel/process_64.c */
-long sys_arch_prctl(int, unsigned long);
+asmlinkage long sys_arch_prctl(int, unsigned long);
 
 /* kernel/sys_x86_64.c */
 asmlinkage long sys_mmap(unsigned long, unsigned long, unsigned long,
diff --git a/arch/x86/include/asm/sysfb.h b/arch/x86/include/asm/sysfb.h
new file mode 100644
index 000000000000..2aeb3e25579c
--- /dev/null
+++ b/arch/x86/include/asm/sysfb.h
@@ -0,0 +1,98 @@
+#ifndef _ARCH_X86_KERNEL_SYSFB_H
+#define _ARCH_X86_KERNEL_SYSFB_H
+
+/*
+ * Generic System Framebuffers on x86
+ * Copyright (c) 2012-2013 David Herrmann <dh.herrmann@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/platform_data/simplefb.h>
+#include <linux/screen_info.h>
+
+enum {
+	M_I17,		/* 17-Inch iMac */
+	M_I20,		/* 20-Inch iMac */
+	M_I20_SR,	/* 20-Inch iMac (Santa Rosa) */
+	M_I24,		/* 24-Inch iMac */
+	M_I24_8_1,	/* 24-Inch iMac, 8,1th gen */
+	M_I24_10_1,	/* 24-Inch iMac, 10,1th gen */
+	M_I27_11_1,	/* 27-Inch iMac, 11,1th gen */
+	M_MINI,		/* Mac Mini */
+	M_MINI_3_1,	/* Mac Mini, 3,1th gen */
+	M_MINI_4_1,	/* Mac Mini, 4,1th gen */
+	M_MB,		/* MacBook */
+	M_MB_2,		/* MacBook, 2nd rev. */
+	M_MB_3,		/* MacBook, 3rd rev. */
+	M_MB_5_1,	/* MacBook, 5th rev. */
+	M_MB_6_1,	/* MacBook, 6th rev. */
+	M_MB_7_1,	/* MacBook, 7th rev. */
+	M_MB_SR,	/* MacBook, 2nd gen, (Santa Rosa) */
+	M_MBA,		/* MacBook Air */
+	M_MBA_3,	/* Macbook Air, 3rd rev */
+	M_MBP,		/* MacBook Pro */
+	M_MBP_2,	/* MacBook Pro 2nd gen */
+	M_MBP_2_2,	/* MacBook Pro 2,2nd gen */
+	M_MBP_SR,	/* MacBook Pro (Santa Rosa) */
+	M_MBP_4,	/* MacBook Pro, 4th gen */
+	M_MBP_5_1,	/* MacBook Pro, 5,1th gen */
+	M_MBP_5_2,	/* MacBook Pro, 5,2th gen */
+	M_MBP_5_3,	/* MacBook Pro, 5,3rd gen */
+	M_MBP_6_1,	/* MacBook Pro, 6,1th gen */
+	M_MBP_6_2,	/* MacBook Pro, 6,2th gen */
+	M_MBP_7_1,	/* MacBook Pro, 7,1th gen */
+	M_MBP_8_2,	/* MacBook Pro, 8,2nd gen */
+	M_UNKNOWN	/* placeholder */
+};
+
+struct efifb_dmi_info {
+	char *optname;
+	unsigned long base;
+	int stride;
+	int width;
+	int height;
+	int flags;
+};
+
+#ifdef CONFIG_EFI
+
+extern struct efifb_dmi_info efifb_dmi_list[];
+void sysfb_apply_efi_quirks(void);
+
+#else /* CONFIG_EFI */
+
+static inline void sysfb_apply_efi_quirks(void)
+{
+}
+
+#endif /* CONFIG_EFI */
+
+#ifdef CONFIG_X86_SYSFB
+
+bool parse_mode(const struct screen_info *si,
+		struct simplefb_platform_data *mode);
+int create_simplefb(const struct screen_info *si,
+		    const struct simplefb_platform_data *mode);
+
+#else /* CONFIG_X86_SYSFB */
+
+static inline bool parse_mode(const struct screen_info *si,
+			      struct simplefb_platform_data *mode)
+{
+	return false;
+}
+
+static inline int create_simplefb(const struct screen_info *si,
+				  const struct simplefb_platform_data *mode)
+{
+	return -EINVAL;
+}
+
+#endif /* CONFIG_X86_SYSFB */
+
+#endif /* _ARCH_X86_KERNEL_SYSFB_H */
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index cf512003e663..e6d90babc245 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -62,6 +62,7 @@ static inline void __flush_tlb_all(void)
 
 static inline void __flush_tlb_one(unsigned long addr)
 {
+	count_vm_event(NR_TLB_LOCAL_FLUSH_ONE);
 	__flush_tlb_single(addr);
 }
 
@@ -84,14 +85,38 @@ static inline void __flush_tlb_one(unsigned long addr)
 
 #ifndef CONFIG_SMP
 
-#define flush_tlb() __flush_tlb()
-#define flush_tlb_all() __flush_tlb_all()
-#define local_flush_tlb() __flush_tlb()
+/* "_up" is for UniProcessor.
+ *
+ * This is a helper for other header functions.  *Not* intended to be called
+ * directly.  All global TLB flushes need to either call this, or to bump the
+ * vm statistics themselves.
+ */
+static inline void __flush_tlb_up(void)
+{
+	count_vm_event(NR_TLB_LOCAL_FLUSH_ALL);
+	__flush_tlb();
+}
+
+static inline void flush_tlb_all(void)
+{
+	count_vm_event(NR_TLB_LOCAL_FLUSH_ALL);
+	__flush_tlb_all();
+}
+
+static inline void flush_tlb(void)
+{
+	__flush_tlb_up();
+}
+
+static inline void local_flush_tlb(void)
+{
+	__flush_tlb_up();
+}
 
 static inline void flush_tlb_mm(struct mm_struct *mm)
 {
 	if (mm == current->active_mm)
-		__flush_tlb();
+		__flush_tlb_up();
 }
 
 static inline void flush_tlb_page(struct vm_area_struct *vma,
@@ -105,14 +130,14 @@ static inline void flush_tlb_range(struct vm_area_struct *vma,
 				   unsigned long start, unsigned long end)
 {
 	if (vma->vm_mm == current->active_mm)
-		__flush_tlb();
+		__flush_tlb_up();
 }
 
 static inline void flush_tlb_mm_range(struct mm_struct *mm,
 	   unsigned long start, unsigned long end, unsigned long vmflag)
 {
 	if (mm == current->active_mm)
-		__flush_tlb();
+		__flush_tlb_up();
 }
 
 static inline void native_flush_tlb_others(const struct cpumask *cpumask,
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index 095b21507b6a..d35f24e231cd 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -124,9 +124,6 @@ extern const struct cpumask *cpu_coregroup_mask(int cpu);
 #define topology_core_id(cpu)			(cpu_data(cpu).cpu_core_id)
 #define topology_core_cpumask(cpu)		(per_cpu(cpu_core_map, cpu))
 #define topology_thread_cpumask(cpu)		(per_cpu(cpu_sibling_map, cpu))
-
-/* indicates that pointers to the topology cpumask_t maps are valid */
-#define arch_provides_topology_pointers		yes
 #endif
 
 static inline void arch_fix_phys_package_id(int num, u32 slot)
diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h
index 88eae2aec619..7036cb60cd87 100644
--- a/arch/x86/include/asm/traps.h
+++ b/arch/x86/include/asm/traps.h
@@ -6,11 +6,7 @@
 #include <asm/debugreg.h>
 #include <asm/siginfo.h>			/* TRAP_TRACE, ... */
 
-#ifdef CONFIG_X86_32
-#define dotraplinkage
-#else
-#define dotraplinkage asmlinkage
-#endif
+#define dotraplinkage __visible
 
 asmlinkage void divide_error(void);
 asmlinkage void debug(void);
diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h
index c91e8b9d588b..235be70d5bb4 100644
--- a/arch/x86/include/asm/tsc.h
+++ b/arch/x86/include/asm/tsc.h
@@ -49,6 +49,7 @@ extern void tsc_init(void);
 extern void mark_tsc_unstable(char *reason);
 extern int unsynchronized_tsc(void);
 extern int check_tsc_unstable(void);
+extern int check_tsc_disabled(void);
 extern unsigned long native_calibrate_tsc(void);
 
 extern int tsc_clocksource_reliable;
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 5ee26875baea..5838fa911aa0 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -153,16 +153,19 @@ __typeof__(__builtin_choose_expr(sizeof(x) > sizeof(0UL), 0ULL, 0UL))
  * Careful: we have to cast the result to the type of the pointer
  * for sign reasons.
  *
- * The use of %edx as the register specifier is a bit of a
+ * The use of _ASM_DX as the register specifier is a bit of a
  * simplification, as gcc only cares about it as the starting point
  * and not size: for a 64-bit value it will use %ecx:%edx on 32 bits
  * (%ecx being the next register in gcc's x86 register sequence), and
  * %rdx on 64 bits.
+ *
+ * Clang/LLVM cares about the size of the register, but still wants
+ * the base register for something that ends up being a pair.
  */
 #define get_user(x, ptr)						\
 ({									\
 	int __ret_gu;							\
-	register __inttype(*(ptr)) __val_gu asm("%edx");		\
+	register __inttype(*(ptr)) __val_gu asm("%"_ASM_DX);		\
 	__chk_user_ptr(ptr);						\
 	might_fault();							\
 	asm volatile("call __get_user_%P3"				\
diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index f3e01a2cbaa1..966502d4682e 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -387,6 +387,7 @@ enum vmcs_field {
 #define VMX_EPT_EXTENT_INDIVIDUAL_ADDR		0
 #define VMX_EPT_EXTENT_CONTEXT			1
 #define VMX_EPT_EXTENT_GLOBAL			2
+#define VMX_EPT_EXTENT_SHIFT			24
 
 #define VMX_EPT_EXECUTE_ONLY_BIT		(1ull)
 #define VMX_EPT_PAGE_WALK_4_BIT			(1ull << 6)
@@ -394,6 +395,7 @@ enum vmcs_field {
 #define VMX_EPTP_WB_BIT				(1ull << 14)
 #define VMX_EPT_2MB_PAGE_BIT			(1ull << 16)
 #define VMX_EPT_1GB_PAGE_BIT			(1ull << 17)
+#define VMX_EPT_INVEPT_BIT			(1ull << 20)
 #define VMX_EPT_AD_BIT				    (1ull << 21)
 #define VMX_EPT_EXTENT_CONTEXT_BIT		(1ull << 25)
 #define VMX_EPT_EXTENT_GLOBAL_BIT		(1ull << 26)
diff --git a/arch/x86/include/asm/vvar.h b/arch/x86/include/asm/vvar.h
index de656ac2af41..d76ac40da206 100644
--- a/arch/x86/include/asm/vvar.h
+++ b/arch/x86/include/asm/vvar.h
@@ -35,7 +35,7 @@
 
 #define DEFINE_VVAR(type, name)						\
 	type name							\
-	__attribute__((section(".vvar_" #name), aligned(16)))
+	__attribute__((section(".vvar_" #name), aligned(16))) __visible
 
 #define VVAR(name) (*vvaraddr_ ## name)
 
diff --git a/arch/x86/include/asm/xen/events.h b/arch/x86/include/asm/xen/events.h
index ca842f2769ef..608a79d5a466 100644
--- a/arch/x86/include/asm/xen/events.h
+++ b/arch/x86/include/asm/xen/events.h
@@ -7,6 +7,7 @@ enum ipi_vector {
 	XEN_CALL_FUNCTION_SINGLE_VECTOR,
 	XEN_SPIN_UNLOCK_VECTOR,
 	XEN_IRQ_WORK_VECTOR,
+	XEN_NMI_VECTOR,
 
 	XEN_NR_IPIS,
 };
diff --git a/arch/x86/include/asm/xen/hypervisor.h b/arch/x86/include/asm/xen/hypervisor.h
index 125f344f06a9..d866959e5685 100644
--- a/arch/x86/include/asm/xen/hypervisor.h
+++ b/arch/x86/include/asm/xen/hypervisor.h
@@ -40,21 +40,7 @@ extern struct start_info *xen_start_info;
 
 static inline uint32_t xen_cpuid_base(void)
 {
-	uint32_t base, eax, ebx, ecx, edx;
-	char signature[13];
-
-	for (base = 0x40000000; base < 0x40010000; base += 0x100) {
-		cpuid(base, &eax, &ebx, &ecx, &edx);
-		*(uint32_t *)(signature + 0) = ebx;
-		*(uint32_t *)(signature + 4) = ecx;
-		*(uint32_t *)(signature + 8) = edx;
-		signature[12] = 0;
-
-		if (!strcmp("XenVMMXenVMM", signature) && ((eax - base) >= 2))
-			return base;
-	}
-
-	return 0;
+	return hypervisor_cpuid_base("XenVMMXenVMM", 2);
 }
 
 #ifdef CONFIG_XEN
diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h
index 6aef9fbc09b7..b913915e8e63 100644
--- a/arch/x86/include/asm/xen/page.h
+++ b/arch/x86/include/asm/xen/page.h
@@ -79,30 +79,38 @@ static inline int phys_to_machine_mapping_valid(unsigned long pfn)
 	return get_phys_to_machine(pfn) != INVALID_P2M_ENTRY;
 }
 
-static inline unsigned long mfn_to_pfn(unsigned long mfn)
+static inline unsigned long mfn_to_pfn_no_overrides(unsigned long mfn)
 {
 	unsigned long pfn;
-	int ret = 0;
+	int ret;
 
 	if (xen_feature(XENFEAT_auto_translated_physmap))
 		return mfn;
 
-	if (unlikely(mfn >= machine_to_phys_nr)) {
-		pfn = ~0;
-		goto try_override;
-	}
-	pfn = 0;
+	if (unlikely(mfn >= machine_to_phys_nr))
+		return ~0;
+
 	/*
 	 * The array access can fail (e.g., device space beyond end of RAM).
 	 * In such cases it doesn't matter what we return (we return garbage),
 	 * but we must handle the fault without crashing!
 	 */
 	ret = __get_user(pfn, &machine_to_phys_mapping[mfn]);
-try_override:
-	/* ret might be < 0 if there are no entries in the m2p for mfn */
 	if (ret < 0)
-		pfn = ~0;
-	else if (get_phys_to_machine(pfn) != mfn)
+		return ~0;
+
+	return pfn;
+}
+
+static inline unsigned long mfn_to_pfn(unsigned long mfn)
+{
+	unsigned long pfn;
+
+	if (xen_feature(XENFEAT_auto_translated_physmap))
+		return mfn;
+
+	pfn = mfn_to_pfn_no_overrides(mfn);
+	if (get_phys_to_machine(pfn) != mfn) {
 		/*
 		 * If this appears to be a foreign mfn (because the pfn
 		 * doesn't map back to the mfn), then check the local override
@@ -111,6 +119,7 @@ try_override:
 		 * m2p_find_override_pfn returns ~0 if it doesn't find anything.
 		 */
 		pfn = m2p_find_override_pfn(mfn, ~0);
+	}
 
 	/* 
 	 * pfn is ~0 if there are no entries in the m2p for mfn or if the
diff --git a/arch/x86/include/asm/xor_avx.h b/arch/x86/include/asm/xor_avx.h
index 7ea79c5fa1f2..492b29802f57 100644
--- a/arch/x86/include/asm/xor_avx.h
+++ b/arch/x86/include/asm/xor_avx.h
@@ -167,12 +167,12 @@ static struct xor_block_template xor_block_avx = {
 
 #define AVX_XOR_SPEED \
 do { \
-	if (cpu_has_avx) \
+	if (cpu_has_avx && cpu_has_osxsave) \
 		xor_speed(&xor_block_avx); \
 } while (0)
 
 #define AVX_SELECT(FASTEST) \
-	(cpu_has_avx ? &xor_block_avx : FASTEST)
+	(cpu_has_avx && cpu_has_osxsave ? &xor_block_avx : FASTEST)
 
 #else
 
diff --git a/arch/x86/include/uapi/asm/kvm_para.h b/arch/x86/include/uapi/asm/kvm_para.h
index 06fdbd987e97..94dc8ca434e0 100644
--- a/arch/x86/include/uapi/asm/kvm_para.h
+++ b/arch/x86/include/uapi/asm/kvm_para.h
@@ -23,6 +23,7 @@
 #define KVM_FEATURE_ASYNC_PF		4
 #define KVM_FEATURE_STEAL_TIME		5
 #define KVM_FEATURE_PV_EOI		6
+#define KVM_FEATURE_PV_UNHALT		7
 
 /* The last 8 bits are used to indicate how to interpret the flags field
  * in pvclock structure. If no bits are set, all flags are ignored.
diff --git a/arch/x86/include/uapi/asm/vmx.h b/arch/x86/include/uapi/asm/vmx.h
index d651082c7cf7..0e79420376eb 100644
--- a/arch/x86/include/uapi/asm/vmx.h
+++ b/arch/x86/include/uapi/asm/vmx.h
@@ -65,6 +65,7 @@
 #define EXIT_REASON_EOI_INDUCED         45
 #define EXIT_REASON_EPT_VIOLATION       48
 #define EXIT_REASON_EPT_MISCONFIG       49
+#define EXIT_REASON_INVEPT              50
 #define EXIT_REASON_PREEMPTION_TIMER    52
 #define EXIT_REASON_WBINVD              54
 #define EXIT_REASON_XSETBV              55
@@ -106,12 +107,13 @@
 	{ EXIT_REASON_APIC_ACCESS,           "APIC_ACCESS" }, \
 	{ EXIT_REASON_EPT_VIOLATION,         "EPT_VIOLATION" }, \
 	{ EXIT_REASON_EPT_MISCONFIG,         "EPT_MISCONFIG" }, \
+	{ EXIT_REASON_INVEPT,                "INVEPT" }, \
+	{ EXIT_REASON_PREEMPTION_TIMER,      "PREEMPTION_TIMER" }, \
 	{ EXIT_REASON_WBINVD,                "WBINVD" }, \
 	{ EXIT_REASON_APIC_WRITE,            "APIC_WRITE" }, \
 	{ EXIT_REASON_EOI_INDUCED,           "EOI_INDUCED" }, \
 	{ EXIT_REASON_INVALID_STATE,         "INVALID_STATE" }, \
 	{ EXIT_REASON_INVD,                  "INVD" }, \
-	{ EXIT_REASON_INVPCID,               "INVPCID" }, \
-	{ EXIT_REASON_PREEMPTION_TIMER,      "PREEMPTION_TIMER" }
+	{ EXIT_REASON_INVPCID,               "INVPCID" }
 
 #endif /* _UAPIVMX_H */
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 88d99ea77723..a5408b965c9d 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -103,6 +103,9 @@ obj-$(CONFIG_X86_CHECK_BIOS_CORRUPTION) += check.o
 obj-$(CONFIG_SWIOTLB)			+= pci-swiotlb.o
 obj-$(CONFIG_OF)			+= devicetree.o
 obj-$(CONFIG_UPROBES)			+= uprobes.o
+obj-y					+= sysfb.o
+obj-$(CONFIG_X86_SYSFB)			+= sysfb_simplefb.o
+obj-$(CONFIG_EFI)			+= sysfb_efi.o
 
 obj-$(CONFIG_PERF_EVENTS)		+= perf_regs.o
 obj-$(CONFIG_TRACING)			+= tracepoint.o
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 2627a81253ee..40c76604199f 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -67,6 +67,7 @@ EXPORT_SYMBOL(acpi_pci_disabled);
 int acpi_lapic;
 int acpi_ioapic;
 int acpi_strict;
+int acpi_disable_cmcff;
 
 u8 acpi_sci_flags __initdata;
 int acpi_sci_override_gsi __initdata;
@@ -141,16 +142,8 @@ static u32 irq_to_gsi(int irq)
 }
 
 /*
- * Temporarily use the virtual area starting from FIX_IO_APIC_BASE_END,
- * to map the target physical address. The problem is that set_fixmap()
- * provides a single page, and it is possible that the page is not
- * sufficient.
- * By using this area, we can map up to MAX_IO_APICS pages temporarily,
- * i.e. until the next __va_range() call.
- *
- * Important Safety Note:  The fixed I/O APIC page numbers are *subtracted*
- * from the fixed base.  That's why we start at FIX_IO_APIC_BASE_END and
- * count idx down while incrementing the phys address.
+ * This is just a simple wrapper around early_ioremap(),
+ * with sanity checks for phys == 0 and size == 0.
  */
 char *__init __acpi_map_table(unsigned long phys, unsigned long size)
 {
@@ -160,6 +153,7 @@ char *__init __acpi_map_table(unsigned long phys, unsigned long size)
 
 	return early_ioremap(phys, size);
 }
+
 void __init __acpi_unmap_table(char *map, unsigned long size)
 {
 	if (!map || !size)
@@ -199,7 +193,7 @@ static void acpi_register_lapic(int id, u8 enabled)
 {
 	unsigned int ver = 0;
 
-	if (id >= (MAX_LOCAL_APIC-1)) {
+	if (id >= MAX_LOCAL_APIC) {
 		printk(KERN_INFO PREFIX "skipped apicid that is too big\n");
 		return;
 	}
@@ -1120,6 +1114,7 @@ int mp_register_gsi(struct device *dev, u32 gsi, int trigger, int polarity)
 	int ioapic;
 	int ioapic_pin;
 	struct io_apic_irq_attr irq_attr;
+	int ret;
 
 	if (acpi_irq_model != ACPI_IRQ_MODEL_IOAPIC)
 		return gsi;
@@ -1149,7 +1144,9 @@ int mp_register_gsi(struct device *dev, u32 gsi, int trigger, int polarity)
 	set_io_apic_irq_attr(&irq_attr, ioapic, ioapic_pin,
 			     trigger == ACPI_EDGE_SENSITIVE ? 0 : 1,
 			     polarity == ACPI_ACTIVE_HIGH ? 0 : 1);
-	io_apic_set_pci_routing(dev, gsi_to_irq(gsi), &irq_attr);
+	ret = io_apic_set_pci_routing(dev, gsi_to_irq(gsi), &irq_attr);
+	if (ret < 0)
+		gsi = INT_MIN;
 
 	return gsi;
 }
@@ -1626,6 +1623,10 @@ static int __init parse_acpi(char *arg)
 	/* "acpi=copy_dsdt" copys DSDT */
 	else if (strcmp(arg, "copy_dsdt") == 0) {
 		acpi_gbl_copy_dsdt_locally = 1;
+	}
+	/* "acpi=nocmcff" disables FF mode for corrected errors */
+	else if (strcmp(arg, "nocmcff") == 0) {
+		acpi_disable_cmcff = 1;
 	} else {
 		/* Core will printk when we return error. */
 		return -EINVAL;
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index c15cf9a25e27..15e8563e5c24 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -11,6 +11,7 @@
 #include <linux/memory.h>
 #include <linux/stop_machine.h>
 #include <linux/slab.h>
+#include <linux/kdebug.h>
 #include <asm/alternative.h>
 #include <asm/sections.h>
 #include <asm/pgtable.h>
@@ -596,97 +597,93 @@ void *__kprobes text_poke(void *addr, const void *opcode, size_t len)
 	return addr;
 }
 
-/*
- * Cross-modifying kernel text with stop_machine().
- * This code originally comes from immediate value.
- */
-static atomic_t stop_machine_first;
-static int wrote_text;
+static void do_sync_core(void *info)
+{
+	sync_core();
+}
 
-struct text_poke_params {
-	struct text_poke_param *params;
-	int nparams;
-};
+static bool bp_patching_in_progress;
+static void *bp_int3_handler, *bp_int3_addr;
 
-static int __kprobes stop_machine_text_poke(void *data)
+int poke_int3_handler(struct pt_regs *regs)
 {
-	struct text_poke_params *tpp = data;
-	struct text_poke_param *p;
-	int i;
+	/* bp_patching_in_progress */
+	smp_rmb();
 
-	if (atomic_xchg(&stop_machine_first, 0)) {
-		for (i = 0; i < tpp->nparams; i++) {
-			p = &tpp->params[i];
-			text_poke(p->addr, p->opcode, p->len);
-		}
-		smp_wmb();	/* Make sure other cpus see that this has run */
-		wrote_text = 1;
-	} else {
-		while (!wrote_text)
-			cpu_relax();
-		smp_mb();	/* Load wrote_text before following execution */
-	}
+	if (likely(!bp_patching_in_progress))
+		return 0;
 
-	for (i = 0; i < tpp->nparams; i++) {
-		p = &tpp->params[i];
-		flush_icache_range((unsigned long)p->addr,
-				   (unsigned long)p->addr + p->len);
-	}
-	/*
-	 * Intel Archiecture Software Developer's Manual section 7.1.3 specifies
-	 * that a core serializing instruction such as "cpuid" should be
-	 * executed on _each_ core before the new instruction is made visible.
-	 */
-	sync_core();
-	return 0;
-}
+	if (user_mode_vm(regs) || regs->ip != (unsigned long)bp_int3_addr)
+		return 0;
+
+	/* set up the specified breakpoint handler */
+	regs->ip = (unsigned long) bp_int3_handler;
+
+	return 1;
 
-/**
- * text_poke_smp - Update instructions on a live kernel on SMP
- * @addr: address to modify
- * @opcode: source of the copy
- * @len: length to copy
- *
- * Modify multi-byte instruction by using stop_machine() on SMP. This allows
- * user to poke/set multi-byte text on SMP. Only non-NMI/MCE code modifying
- * should be allowed, since stop_machine() does _not_ protect code against
- * NMI and MCE.
- *
- * Note: Must be called under get_online_cpus() and text_mutex.
- */
-void *__kprobes text_poke_smp(void *addr, const void *opcode, size_t len)
-{
-	struct text_poke_params tpp;
-	struct text_poke_param p;
-
-	p.addr = addr;
-	p.opcode = opcode;
-	p.len = len;
-	tpp.params = &p;
-	tpp.nparams = 1;
-	atomic_set(&stop_machine_first, 1);
-	wrote_text = 0;
-	/* Use __stop_machine() because the caller already got online_cpus. */
-	__stop_machine(stop_machine_text_poke, (void *)&tpp, cpu_online_mask);
-	return addr;
 }
 
 /**
- * text_poke_smp_batch - Update instructions on a live kernel on SMP
- * @params: an array of text_poke parameters
- * @n: the number of elements in params.
+ * text_poke_bp() -- update instructions on live kernel on SMP
+ * @addr:	address to patch
+ * @opcode:	opcode of new instruction
+ * @len:	length to copy
+ * @handler:	address to jump to when the temporary breakpoint is hit
  *
- * Modify multi-byte instruction by using stop_machine() on SMP. Since the
- * stop_machine() is heavy task, it is better to aggregate text_poke requests
- * and do it once if possible.
+ * Modify multi-byte instruction by using int3 breakpoint on SMP.
+ * We completely avoid stop_machine() here, and achieve the
+ * synchronization using int3 breakpoint.
  *
- * Note: Must be called under get_online_cpus() and text_mutex.
+ * The way it is done:
+ *	- add a int3 trap to the address that will be patched
+ *	- sync cores
+ *	- update all but the first byte of the patched range
+ *	- sync cores
+ *	- replace the first byte (int3) by the first byte of
+ *	  replacing opcode
+ *	- sync cores
+ *
+ * Note: must be called under text_mutex.
  */
-void __kprobes text_poke_smp_batch(struct text_poke_param *params, int n)
+void *text_poke_bp(void *addr, const void *opcode, size_t len, void *handler)
 {
-	struct text_poke_params tpp = {.params = params, .nparams = n};
+	unsigned char int3 = 0xcc;
+
+	bp_int3_handler = handler;
+	bp_int3_addr = (u8 *)addr + sizeof(int3);
+	bp_patching_in_progress = true;
+	/*
+	 * Corresponding read barrier in int3 notifier for
+	 * making sure the in_progress flags is correctly ordered wrt.
+	 * patching
+	 */
+	smp_wmb();
+
+	text_poke(addr, &int3, sizeof(int3));
 
-	atomic_set(&stop_machine_first, 1);
-	wrote_text = 0;
-	__stop_machine(stop_machine_text_poke, (void *)&tpp, cpu_online_mask);
+	on_each_cpu(do_sync_core, NULL, 1);
+
+	if (len - sizeof(int3) > 0) {
+		/* patch all but the first byte */
+		text_poke((char *)addr + sizeof(int3),
+			  (const char *) opcode + sizeof(int3),
+			  len - sizeof(int3));
+		/*
+		 * According to Intel, this core syncing is very likely
+		 * not necessary and we'd be safe even without it. But
+		 * better safe than sorry (plus there's not only Intel).
+		 */
+		on_each_cpu(do_sync_core, NULL, 1);
+	}
+
+	/* patch the first byte */
+	text_poke(addr, opcode, sizeof(int3));
+
+	on_each_cpu(do_sync_core, NULL, 1);
+
+	bp_patching_in_progress = false;
+	smp_wmb();
+
+	return addr;
 }
+
diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c
index 3048ded1b598..59554dca96ec 100644
--- a/arch/x86/kernel/amd_nb.c
+++ b/arch/x86/kernel/amd_nb.c
@@ -20,6 +20,7 @@ const struct pci_device_id amd_nb_misc_ids[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_10H_NB_MISC) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_F3) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_M10H_F3) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_M30H_NB_F3) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F3) },
 	{}
 };
@@ -27,6 +28,7 @@ EXPORT_SYMBOL(amd_nb_misc_ids);
 
 static const struct pci_device_id amd_nb_link_ids[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_F4) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_M30H_NB_F4) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F4) },
 	{}
 };
@@ -81,13 +83,20 @@ int amd_cache_northbridges(void)
 			next_northbridge(misc, amd_nb_misc_ids);
 		node_to_amd_nb(i)->link = link =
 			next_northbridge(link, amd_nb_link_ids);
-        }
+	}
 
+	/* GART present only on Fam15h upto model 0fh */
 	if (boot_cpu_data.x86 == 0xf || boot_cpu_data.x86 == 0x10 ||
-	    boot_cpu_data.x86 == 0x15)
+	    (boot_cpu_data.x86 == 0x15 && boot_cpu_data.x86_model < 0x10))
 		amd_northbridges.flags |= AMD_NB_GART;
 
 	/*
+	 * Check for L3 cache presence.
+	 */
+	if (!cpuid_edx(0x80000006))
+		return 0;
+
+	/*
 	 * Some CPU families support L3 Cache Index Disable. There are some
 	 * limitations because of E382 and E388 on family 0x10.
 	 */
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index eca89c53a7f5..a7eb82d9b012 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -913,7 +913,7 @@ static void local_apic_timer_interrupt(void)
  * [ if a single-CPU system runs an SMP kernel then we call the local
  *   interrupt as well. Thus we cannot inline the local irq ... ]
  */
-void __irq_entry smp_apic_timer_interrupt(struct pt_regs *regs)
+__visible void __irq_entry smp_apic_timer_interrupt(struct pt_regs *regs)
 {
 	struct pt_regs *old_regs = set_irq_regs(regs);
 
@@ -932,7 +932,7 @@ void __irq_entry smp_apic_timer_interrupt(struct pt_regs *regs)
 	set_irq_regs(old_regs);
 }
 
-void __irq_entry smp_trace_apic_timer_interrupt(struct pt_regs *regs)
+__visible void __irq_entry smp_trace_apic_timer_interrupt(struct pt_regs *regs)
 {
 	struct pt_regs *old_regs = set_irq_regs(regs);
 
@@ -1946,14 +1946,14 @@ static inline void __smp_spurious_interrupt(void)
 		"should never happen.\n", smp_processor_id());
 }
 
-void smp_spurious_interrupt(struct pt_regs *regs)
+__visible void smp_spurious_interrupt(struct pt_regs *regs)
 {
 	entering_irq();
 	__smp_spurious_interrupt();
 	exiting_irq();
 }
 
-void smp_trace_spurious_interrupt(struct pt_regs *regs)
+__visible void smp_trace_spurious_interrupt(struct pt_regs *regs)
 {
 	entering_irq();
 	trace_spurious_apic_entry(SPURIOUS_APIC_VECTOR);
@@ -2002,14 +2002,14 @@ static inline void __smp_error_interrupt(struct pt_regs *regs)
 
 }
 
-void smp_error_interrupt(struct pt_regs *regs)
+__visible void smp_error_interrupt(struct pt_regs *regs)
 {
 	entering_irq();
 	__smp_error_interrupt(regs);
 	exiting_irq();
 }
 
-void smp_trace_error_interrupt(struct pt_regs *regs)
+__visible void smp_trace_error_interrupt(struct pt_regs *regs)
 {
 	entering_irq();
 	trace_error_apic_entry(ERROR_APIC_VECTOR);
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 9ed796ccc32c..e63a5bd2a78f 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -1534,6 +1534,11 @@ void intel_ir_io_apic_print_entries(unsigned int apic,
 	}
 }
 
+void ioapic_zap_locks(void)
+{
+	raw_spin_lock_init(&ioapic_lock);
+}
+
 __apicdebuginit(void) print_IO_APIC(int ioapic_idx)
 {
 	union IO_APIC_reg_00 reg_00;
@@ -3375,12 +3380,15 @@ int io_apic_setup_irq_pin_once(unsigned int irq, int node,
 {
 	unsigned int ioapic_idx = attr->ioapic, pin = attr->ioapic_pin;
 	int ret;
+	struct IO_APIC_route_entry orig_entry;
 
 	/* Avoid redundant programming */
 	if (test_bit(pin, ioapics[ioapic_idx].pin_programmed)) {
-		pr_debug("Pin %d-%d already programmed\n",
-			 mpc_ioapic_id(ioapic_idx), pin);
-		return 0;
+		pr_debug("Pin %d-%d already programmed\n", mpc_ioapic_id(ioapic_idx), pin);
+		orig_entry = ioapic_read_entry(attr->ioapic, pin);
+		if (attr->trigger == orig_entry.trigger && attr->polarity == orig_entry.polarity)
+			return 0;
+		return -EBUSY;
 	}
 	ret = io_apic_setup_irq_pin(irq, node, attr);
 	if (!ret)
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index 1191ac1c9d25..a419814cea57 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -113,7 +113,7 @@ static int __init early_get_pnodeid(void)
 		break;
 	case UV3_HUB_PART_NUMBER:
 	case UV3_HUB_PART_NUMBER_X:
-		uv_min_hub_revision_id += UV3_HUB_REVISION_BASE - 1;
+		uv_min_hub_revision_id += UV3_HUB_REVISION_BASE;
 		break;
 	}
 
diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index 53a4e2744846..3ab03430211d 100644
--- a/arch/x86/kernel/apm_32.c
+++ b/arch/x86/kernel/apm_32.c
@@ -392,7 +392,7 @@ static struct cpuidle_device apm_cpuidle_device;
 /*
  * Local variables
  */
-static struct {
+__visible struct {
 	unsigned long	offset;
 	unsigned short	segment;
 } apm_bios_entry;
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 08a089043ccf..903a264af981 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -66,8 +66,8 @@ static inline int wrmsrl_amd_safe(unsigned msr, unsigned long long val)
  *	performance at the same time..
  */
 
-extern void vide(void);
-__asm__(".align 4\nvide: ret");
+extern __visible void vide(void);
+__asm__(".globl vide\n\t.align 4\nvide: ret");
 
 static void init_amd_k5(struct cpuinfo_x86 *c)
 {
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 25eb2747b063..2793d1f095a2 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1076,7 +1076,7 @@ struct desc_ptr debug_idt_descr = { NR_VECTORS * 16 - 1,
 				    (unsigned long) debug_idt_table };
 
 DEFINE_PER_CPU_FIRST(union irq_stack_union,
-		     irq_stack_union) __aligned(PAGE_SIZE);
+		     irq_stack_union) __aligned(PAGE_SIZE) __visible;
 
 /*
  * The following four percpu variables are hot.  Align current_task to
@@ -1093,7 +1093,7 @@ EXPORT_PER_CPU_SYMBOL(kernel_stack);
 DEFINE_PER_CPU(char *, irq_stack_ptr) =
 	init_per_cpu_var(irq_stack_union.irq_stack) + IRQ_STACK_SIZE - 64;
 
-DEFINE_PER_CPU(unsigned int, irq_count) = -1;
+DEFINE_PER_CPU(unsigned int, irq_count) __visible = -1;
 
 DEFINE_PER_CPU(struct task_struct *, fpu_owner_task);
 
diff --git a/arch/x86/kernel/cpu/hypervisor.c b/arch/x86/kernel/cpu/hypervisor.c
index 87279212d318..36ce402a3fa5 100644
--- a/arch/x86/kernel/cpu/hypervisor.c
+++ b/arch/x86/kernel/cpu/hypervisor.c
@@ -25,11 +25,6 @@
 #include <asm/processor.h>
 #include <asm/hypervisor.h>
 
-/*
- * Hypervisor detect order.  This is specified explicitly here because
- * some hypervisors might implement compatibility modes for other
- * hypervisors and therefore need to be detected in specific sequence.
- */
 static const __initconst struct hypervisor_x86 * const hypervisors[] =
 {
 #ifdef CONFIG_XEN_PVHVM
@@ -49,15 +44,19 @@ static inline void __init
 detect_hypervisor_vendor(void)
 {
 	const struct hypervisor_x86 *h, * const *p;
+	uint32_t pri, max_pri = 0;
 
 	for (p = hypervisors; p < hypervisors + ARRAY_SIZE(hypervisors); p++) {
 		h = *p;
-		if (h->detect()) {
+		pri = h->detect();
+		if (pri != 0 && pri > max_pri) {
+			max_pri = pri;
 			x86_hyper = h;
-			printk(KERN_INFO "Hypervisor detected: %s\n", h->name);
-			break;
 		}
 	}
+
+	if (max_pri)
+		printk(KERN_INFO "Hypervisor detected: %s\n", x86_hyper->name);
 }
 
 void init_hypervisor(struct cpuinfo_x86 *c)
diff --git a/arch/x86/kernel/cpu/mcheck/mce-internal.h b/arch/x86/kernel/cpu/mcheck/mce-internal.h
index 5b7d4fa5d3b7..09edd0b65fef 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-internal.h
+++ b/arch/x86/kernel/cpu/mcheck/mce-internal.h
@@ -25,15 +25,18 @@ int mce_severity(struct mce *a, int tolerant, char **msg);
 struct dentry *mce_get_debugfs_dir(void);
 
 extern struct mce_bank *mce_banks;
+extern mce_banks_t mce_banks_ce_disabled;
 
 #ifdef CONFIG_X86_MCE_INTEL
 unsigned long mce_intel_adjust_timer(unsigned long interval);
 void mce_intel_cmci_poll(void);
 void mce_intel_hcpu_update(unsigned long cpu);
+void cmci_disable_bank(int bank);
 #else
 # define mce_intel_adjust_timer mce_adjust_timer_default
 static inline void mce_intel_cmci_poll(void) { }
 static inline void mce_intel_hcpu_update(unsigned long cpu) { }
+static inline void cmci_disable_bank(int bank) { }
 #endif
 
 void mce_timer_kick(unsigned long interval);
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 87a65c939bcd..b3218cdee95f 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -97,6 +97,15 @@ DEFINE_PER_CPU(mce_banks_t, mce_poll_banks) = {
 	[0 ... BITS_TO_LONGS(MAX_NR_BANKS)-1] = ~0UL
 };
 
+/*
+ * MCA banks controlled through firmware first for corrected errors.
+ * This is a global list of banks for which we won't enable CMCI and we
+ * won't poll. Firmware controls these banks and is responsible for
+ * reporting corrected errors through GHES. Uncorrected/recoverable
+ * errors are still notified through a machine check.
+ */
+mce_banks_t mce_banks_ce_disabled;
+
 static DEFINE_PER_CPU(struct work_struct, mce_work);
 
 static void (*quirk_no_way_out)(int bank, struct mce *m, struct pt_regs *regs);
@@ -1935,6 +1944,25 @@ static struct miscdevice mce_chrdev_device = {
 	&mce_chrdev_ops,
 };
 
+static void __mce_disable_bank(void *arg)
+{
+	int bank = *((int *)arg);
+	__clear_bit(bank, __get_cpu_var(mce_poll_banks));
+	cmci_disable_bank(bank);
+}
+
+void mce_disable_bank(int bank)
+{
+	if (bank >= mca_cfg.banks) {
+		pr_warn(FW_BUG
+			"Ignoring request to disable invalid MCA bank %d.\n",
+			bank);
+		return;
+	}
+	set_bit(bank, mce_banks_ce_disabled);
+	on_each_cpu(__mce_disable_bank, &bank, 1);
+}
+
 /*
  * mce=off Disables machine check
  * mce=no_cmci Disables CMCI
diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c
index d56405309dc1..4cfe0458ca66 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_intel.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c
@@ -203,6 +203,10 @@ static void cmci_discover(int banks)
 		if (test_bit(i, owned))
 			continue;
 
+		/* Skip banks in firmware first mode */
+		if (test_bit(i, mce_banks_ce_disabled))
+			continue;
+
 		rdmsrl(MSR_IA32_MCx_CTL2(i), val);
 
 		/* Already owned by someone else? */
@@ -271,6 +275,19 @@ void cmci_recheck(void)
 	local_irq_restore(flags);
 }
 
+/* Caller must hold the lock on cmci_discover_lock */
+static void __cmci_disable_bank(int bank)
+{
+	u64 val;
+
+	if (!test_bit(bank, __get_cpu_var(mce_banks_owned)))
+		return;
+	rdmsrl(MSR_IA32_MCx_CTL2(bank), val);
+	val &= ~MCI_CTL2_CMCI_EN;
+	wrmsrl(MSR_IA32_MCx_CTL2(bank), val);
+	__clear_bit(bank, __get_cpu_var(mce_banks_owned));
+}
+
 /*
  * Disable CMCI on this CPU for all banks it owns when it goes down.
  * This allows other CPUs to claim the banks on rediscovery.
@@ -280,20 +297,12 @@ void cmci_clear(void)
 	unsigned long flags;
 	int i;
 	int banks;
-	u64 val;
 
 	if (!cmci_supported(&banks))
 		return;
 	raw_spin_lock_irqsave(&cmci_discover_lock, flags);
-	for (i = 0; i < banks; i++) {
-		if (!test_bit(i, __get_cpu_var(mce_banks_owned)))
-			continue;
-		/* Disable CMCI */
-		rdmsrl(MSR_IA32_MCx_CTL2(i), val);
-		val &= ~MCI_CTL2_CMCI_EN;
-		wrmsrl(MSR_IA32_MCx_CTL2(i), val);
-		__clear_bit(i, __get_cpu_var(mce_banks_owned));
-	}
+	for (i = 0; i < banks; i++)
+		__cmci_disable_bank(i);
 	raw_spin_unlock_irqrestore(&cmci_discover_lock, flags);
 }
 
@@ -327,6 +336,19 @@ void cmci_reenable(void)
 		cmci_discover(banks);
 }
 
+void cmci_disable_bank(int bank)
+{
+	int banks;
+	unsigned long flags;
+
+	if (!cmci_supported(&banks))
+		return;
+
+	raw_spin_lock_irqsave(&cmci_discover_lock, flags);
+	__cmci_disable_bank(bank);
+	raw_spin_unlock_irqrestore(&cmci_discover_lock, flags);
+}
+
 static void intel_init_cmci(void)
 {
 	int banks;
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index 8f4be53ea04b..71a39f3621ba 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -27,20 +27,23 @@
 struct ms_hyperv_info ms_hyperv;
 EXPORT_SYMBOL_GPL(ms_hyperv);
 
-static bool __init ms_hyperv_platform(void)
+static uint32_t  __init ms_hyperv_platform(void)
 {
 	u32 eax;
 	u32 hyp_signature[3];
 
 	if (!boot_cpu_has(X86_FEATURE_HYPERVISOR))
-		return false;
+		return 0;
 
 	cpuid(HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS,
 	      &eax, &hyp_signature[0], &hyp_signature[1], &hyp_signature[2]);
 
-	return eax >= HYPERV_CPUID_MIN &&
-		eax <= HYPERV_CPUID_MAX &&
-		!memcmp("Microsoft Hv", hyp_signature, 12);
+	if (eax >= HYPERV_CPUID_MIN &&
+	    eax <= HYPERV_CPUID_MAX &&
+	    !memcmp("Microsoft Hv", hyp_signature, 12))
+		return HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS;
+
+	return 0;
 }
 
 static cycle_t read_hv_clock(struct clocksource *arg)
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index d4cdfa67509e..ce2d0a2c3e4f 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -683,6 +683,7 @@ static void prepare_set(void) __acquires(set_atomicity_lock)
 	}
 
 	/* Flush all TLBs via a mov %cr3, %reg; mov %reg, %cr3 */
+	count_vm_event(NR_TLB_LOCAL_FLUSH_ALL);
 	__flush_tlb();
 
 	/* Save MTRR state */
@@ -696,6 +697,7 @@ static void prepare_set(void) __acquires(set_atomicity_lock)
 static void post_set(void) __releases(set_atomicity_lock)
 {
 	/* Flush TLBs (no need to flush caches - they are disabled) */
+	count_vm_event(NR_TLB_LOCAL_FLUSH_ALL);
 	__flush_tlb();
 
 	/* Intel (P6) standard MTRRs */
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index a7c7305030cc..9d8449158cf9 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1506,7 +1506,7 @@ static int __init init_hw_perf_events(void)
 		err = amd_pmu_init();
 		break;
 	default:
-		return 0;
+		err = -ENOTSUPP;
 	}
 	if (err != 0) {
 		pr_cont("no PMU driver, software events only.\n");
@@ -1883,20 +1883,21 @@ static struct pmu pmu = {
 
 void arch_perf_update_userpage(struct perf_event_mmap_page *userpg, u64 now)
 {
-	userpg->cap_usr_time = 0;
-	userpg->cap_usr_rdpmc = x86_pmu.attr_rdpmc;
+	userpg->cap_user_time = 0;
+	userpg->cap_user_time_zero = 0;
+	userpg->cap_user_rdpmc = x86_pmu.attr_rdpmc;
 	userpg->pmc_width = x86_pmu.cntval_bits;
 
-	if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC))
-		return;
-
-	if (!boot_cpu_has(X86_FEATURE_NONSTOP_TSC))
+	if (!sched_clock_stable)
 		return;
 
-	userpg->cap_usr_time = 1;
+	userpg->cap_user_time = 1;
 	userpg->time_mult = this_cpu_read(cyc2ns);
 	userpg->time_shift = CYC2NS_SCALE_FACTOR;
 	userpg->time_offset = this_cpu_read(cyc2ns_offset) - now;
+
+	userpg->cap_user_time_zero = 1;
+	userpg->time_zero = this_cpu_read(cyc2ns_offset);
 }
 
 /*
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 97e557bc4c91..cc16faae0538 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -641,6 +641,8 @@ extern struct event_constraint intel_core2_pebs_event_constraints[];
 
 extern struct event_constraint intel_atom_pebs_event_constraints[];
 
+extern struct event_constraint intel_slm_pebs_event_constraints[];
+
 extern struct event_constraint intel_nehalem_pebs_event_constraints[];
 
 extern struct event_constraint intel_westmere_pebs_event_constraints[];
diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c
index 4cbe03287b08..beeb7cc07044 100644
--- a/arch/x86/kernel/cpu/perf_event_amd.c
+++ b/arch/x86/kernel/cpu/perf_event_amd.c
@@ -347,8 +347,7 @@ static struct amd_nb *amd_alloc_nb(int cpu)
 	struct amd_nb *nb;
 	int i;
 
-	nb = kmalloc_node(sizeof(struct amd_nb), GFP_KERNEL | __GFP_ZERO,
-			  cpu_to_node(cpu));
+	nb = kzalloc_node(sizeof(struct amd_nb), GFP_KERNEL, cpu_to_node(cpu));
 	if (!nb)
 		return NULL;
 
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index a45d8d4ace10..f31a1655d1ff 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -81,7 +81,8 @@ static struct event_constraint intel_nehalem_event_constraints[] __read_mostly =
 
 static struct extra_reg intel_nehalem_extra_regs[] __read_mostly =
 {
-	INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0xffff, RSP_0),
+	/* must define OFFCORE_RSP_X first, see intel_fixup_er() */
+	INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0xffff, RSP_0),
 	INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x100b),
 	EVENT_EXTRA_END
 };
@@ -123,6 +124,7 @@ static struct event_constraint intel_ivb_event_constraints[] __read_mostly =
 	INTEL_UEVENT_CONSTRAINT(0x0148, 0x4), /* L1D_PEND_MISS.PENDING */
 	INTEL_UEVENT_CONSTRAINT(0x0279, 0xf), /* IDQ.EMTPY */
 	INTEL_UEVENT_CONSTRAINT(0x019c, 0xf), /* IDQ_UOPS_NOT_DELIVERED.CORE */
+	INTEL_UEVENT_CONSTRAINT(0x02a3, 0xf), /* CYCLE_ACTIVITY.CYCLES_LDM_PENDING */
 	INTEL_UEVENT_CONSTRAINT(0x04a3, 0xf), /* CYCLE_ACTIVITY.CYCLES_NO_EXECUTE */
 	INTEL_UEVENT_CONSTRAINT(0x05a3, 0xf), /* CYCLE_ACTIVITY.STALLS_L2_PENDING */
 	INTEL_UEVENT_CONSTRAINT(0x06a3, 0xf), /* CYCLE_ACTIVITY.STALLS_LDM_PENDING */
@@ -143,8 +145,9 @@ static struct event_constraint intel_ivb_event_constraints[] __read_mostly =
 
 static struct extra_reg intel_westmere_extra_regs[] __read_mostly =
 {
-	INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0xffff, RSP_0),
-	INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0xffff, RSP_1),
+	/* must define OFFCORE_RSP_X first, see intel_fixup_er() */
+	INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0xffff, RSP_0),
+	INTEL_UEVENT_EXTRA_REG(0x01bb, MSR_OFFCORE_RSP_1, 0xffff, RSP_1),
 	INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x100b),
 	EVENT_EXTRA_END
 };
@@ -162,16 +165,27 @@ static struct event_constraint intel_gen_event_constraints[] __read_mostly =
 	EVENT_CONSTRAINT_END
 };
 
+static struct event_constraint intel_slm_event_constraints[] __read_mostly =
+{
+	FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
+	FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
+	FIXED_EVENT_CONSTRAINT(0x013c, 2), /* CPU_CLK_UNHALTED.REF */
+	FIXED_EVENT_CONSTRAINT(0x0300, 2), /* pseudo CPU_CLK_UNHALTED.REF */
+	EVENT_CONSTRAINT_END
+};
+
 static struct extra_reg intel_snb_extra_regs[] __read_mostly = {
-	INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0x3f807f8fffull, RSP_0),
-	INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0x3f807f8fffull, RSP_1),
+	/* must define OFFCORE_RSP_X first, see intel_fixup_er() */
+	INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x3f807f8fffull, RSP_0),
+	INTEL_UEVENT_EXTRA_REG(0x01bb, MSR_OFFCORE_RSP_1, 0x3f807f8fffull, RSP_1),
 	INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd),
 	EVENT_EXTRA_END
 };
 
 static struct extra_reg intel_snbep_extra_regs[] __read_mostly = {
-	INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0x3fffff8fffull, RSP_0),
-	INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0x3fffff8fffull, RSP_1),
+	/* must define OFFCORE_RSP_X first, see intel_fixup_er() */
+	INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x3fffff8fffull, RSP_0),
+	INTEL_UEVENT_EXTRA_REG(0x01bb, MSR_OFFCORE_RSP_1, 0x3fffff8fffull, RSP_1),
 	INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd),
 	EVENT_EXTRA_END
 };
@@ -882,6 +896,140 @@ static __initconst const u64 atom_hw_cache_event_ids
  },
 };
 
+static struct extra_reg intel_slm_extra_regs[] __read_mostly =
+{
+	/* must define OFFCORE_RSP_X first, see intel_fixup_er() */
+	INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x768005ffffull, RSP_0),
+	INTEL_UEVENT_EXTRA_REG(0x02b7, MSR_OFFCORE_RSP_1, 0x768005ffffull, RSP_1),
+	EVENT_EXTRA_END
+};
+
+#define SLM_DMND_READ		SNB_DMND_DATA_RD
+#define SLM_DMND_WRITE		SNB_DMND_RFO
+#define SLM_DMND_PREFETCH	(SNB_PF_DATA_RD|SNB_PF_RFO)
+
+#define SLM_SNP_ANY		(SNB_SNP_NONE|SNB_SNP_MISS|SNB_NO_FWD|SNB_HITM)
+#define SLM_LLC_ACCESS		SNB_RESP_ANY
+#define SLM_LLC_MISS		(SLM_SNP_ANY|SNB_NON_DRAM)
+
+static __initconst const u64 slm_hw_cache_extra_regs
+				[PERF_COUNT_HW_CACHE_MAX]
+				[PERF_COUNT_HW_CACHE_OP_MAX]
+				[PERF_COUNT_HW_CACHE_RESULT_MAX] =
+{
+ [ C(LL  ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = SLM_DMND_READ|SLM_LLC_ACCESS,
+		[ C(RESULT_MISS)   ] = SLM_DMND_READ|SLM_LLC_MISS,
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = SLM_DMND_WRITE|SLM_LLC_ACCESS,
+		[ C(RESULT_MISS)   ] = SLM_DMND_WRITE|SLM_LLC_MISS,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = SLM_DMND_PREFETCH|SLM_LLC_ACCESS,
+		[ C(RESULT_MISS)   ] = SLM_DMND_PREFETCH|SLM_LLC_MISS,
+	},
+ },
+};
+
+static __initconst const u64 slm_hw_cache_event_ids
+				[PERF_COUNT_HW_CACHE_MAX]
+				[PERF_COUNT_HW_CACHE_OP_MAX]
+				[PERF_COUNT_HW_CACHE_RESULT_MAX] =
+{
+ [ C(L1D) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0,
+		[ C(RESULT_MISS)   ] = 0x0104, /* LD_DCU_MISS */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0,
+		[ C(RESULT_MISS)   ] = 0,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0,
+		[ C(RESULT_MISS)   ] = 0,
+	},
+ },
+ [ C(L1I ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0380, /* ICACHE.ACCESSES */
+		[ C(RESULT_MISS)   ] = 0x0280, /* ICACGE.MISSES */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0,
+		[ C(RESULT_MISS)   ] = 0,
+	},
+ },
+ [ C(LL  ) ] = {
+	[ C(OP_READ) ] = {
+		/* OFFCORE_RESPONSE.ANY_DATA.LOCAL_CACHE */
+		[ C(RESULT_ACCESS) ] = 0x01b7,
+		/* OFFCORE_RESPONSE.ANY_DATA.ANY_LLC_MISS */
+		[ C(RESULT_MISS)   ] = 0x01b7,
+	},
+	[ C(OP_WRITE) ] = {
+		/* OFFCORE_RESPONSE.ANY_RFO.LOCAL_CACHE */
+		[ C(RESULT_ACCESS) ] = 0x01b7,
+		/* OFFCORE_RESPONSE.ANY_RFO.ANY_LLC_MISS */
+		[ C(RESULT_MISS)   ] = 0x01b7,
+	},
+	[ C(OP_PREFETCH) ] = {
+		/* OFFCORE_RESPONSE.PREFETCH.LOCAL_CACHE */
+		[ C(RESULT_ACCESS) ] = 0x01b7,
+		/* OFFCORE_RESPONSE.PREFETCH.ANY_LLC_MISS */
+		[ C(RESULT_MISS)   ] = 0x01b7,
+	},
+ },
+ [ C(DTLB) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0,
+		[ C(RESULT_MISS)   ] = 0x0804, /* LD_DTLB_MISS */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0,
+		[ C(RESULT_MISS)   ] = 0,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0,
+		[ C(RESULT_MISS)   ] = 0,
+	},
+ },
+ [ C(ITLB) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x00c0, /* INST_RETIRED.ANY_P */
+		[ C(RESULT_MISS)   ] = 0x0282, /* ITLB.MISSES */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+ },
+ [ C(BPU ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x00c4, /* BR_INST_RETIRED.ANY */
+		[ C(RESULT_MISS)   ] = 0x00c5, /* BP_INST_RETIRED.MISPRED */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+ },
+};
+
 static inline bool intel_pmu_needs_lbr_smpl(struct perf_event *event)
 {
 	/* user explicitly requested branch sampling */
@@ -1301,11 +1449,11 @@ static void intel_fixup_er(struct perf_event *event, int idx)
 
 	if (idx == EXTRA_REG_RSP_0) {
 		event->hw.config &= ~INTEL_ARCH_EVENT_MASK;
-		event->hw.config |= 0x01b7;
+		event->hw.config |= x86_pmu.extra_regs[EXTRA_REG_RSP_0].event;
 		event->hw.extra_reg.reg = MSR_OFFCORE_RSP_0;
 	} else if (idx == EXTRA_REG_RSP_1) {
 		event->hw.config &= ~INTEL_ARCH_EVENT_MASK;
-		event->hw.config |= 0x01bb;
+		event->hw.config |= x86_pmu.extra_regs[EXTRA_REG_RSP_1].event;
 		event->hw.extra_reg.reg = MSR_OFFCORE_RSP_1;
 	}
 }
@@ -2176,6 +2324,22 @@ __init int intel_pmu_init(void)
 		pr_cont("Atom events, ");
 		break;
 
+	case 55: /* Atom 22nm "Silvermont" */
+	case 77: /* Avoton "Silvermont" */
+		memcpy(hw_cache_event_ids, slm_hw_cache_event_ids,
+			sizeof(hw_cache_event_ids));
+		memcpy(hw_cache_extra_regs, slm_hw_cache_extra_regs,
+		       sizeof(hw_cache_extra_regs));
+
+		intel_pmu_lbr_init_atom();
+
+		x86_pmu.event_constraints = intel_slm_event_constraints;
+		x86_pmu.pebs_constraints = intel_slm_pebs_event_constraints;
+		x86_pmu.extra_regs = intel_slm_extra_regs;
+		x86_pmu.er_flags |= ERF_HAS_RSP_1;
+		pr_cont("Silvermont events, ");
+		break;
+
 	case 37: /* 32 nm nehalem, "Clarkdale" */
 	case 44: /* 32 nm nehalem, "Gulftown" */
 	case 47: /* 32 nm Xeon E7 */
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index 3065c57a63c1..ab3ba1c1b7dd 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -224,7 +224,7 @@ static int alloc_pebs_buffer(int cpu)
 	if (!x86_pmu.pebs)
 		return 0;
 
-	buffer = kmalloc_node(PEBS_BUFFER_SIZE, GFP_KERNEL | __GFP_ZERO, node);
+	buffer = kzalloc_node(PEBS_BUFFER_SIZE, GFP_KERNEL, node);
 	if (unlikely(!buffer))
 		return -ENOMEM;
 
@@ -262,7 +262,7 @@ static int alloc_bts_buffer(int cpu)
 	if (!x86_pmu.bts)
 		return 0;
 
-	buffer = kmalloc_node(BTS_BUFFER_SIZE, GFP_KERNEL | __GFP_ZERO, node);
+	buffer = kzalloc_node(BTS_BUFFER_SIZE, GFP_KERNEL, node);
 	if (unlikely(!buffer))
 		return -ENOMEM;
 
@@ -295,7 +295,7 @@ static int alloc_ds_buffer(int cpu)
 	int node = cpu_to_node(cpu);
 	struct debug_store *ds;
 
-	ds = kmalloc_node(sizeof(*ds), GFP_KERNEL | __GFP_ZERO, node);
+	ds = kzalloc_node(sizeof(*ds), GFP_KERNEL, node);
 	if (unlikely(!ds))
 		return -ENOMEM;
 
@@ -517,6 +517,32 @@ struct event_constraint intel_atom_pebs_event_constraints[] = {
 	EVENT_CONSTRAINT_END
 };
 
+struct event_constraint intel_slm_pebs_event_constraints[] = {
+	INTEL_UEVENT_CONSTRAINT(0x0103, 0x1), /* REHABQ.LD_BLOCK_ST_FORWARD_PS */
+	INTEL_UEVENT_CONSTRAINT(0x0803, 0x1), /* REHABQ.LD_SPLITS_PS */
+	INTEL_UEVENT_CONSTRAINT(0x0204, 0x1), /* MEM_UOPS_RETIRED.L2_HIT_LOADS_PS */
+	INTEL_UEVENT_CONSTRAINT(0x0404, 0x1), /* MEM_UOPS_RETIRED.L2_MISS_LOADS_PS */
+	INTEL_UEVENT_CONSTRAINT(0x0804, 0x1), /* MEM_UOPS_RETIRED.DTLB_MISS_LOADS_PS */
+	INTEL_UEVENT_CONSTRAINT(0x2004, 0x1), /* MEM_UOPS_RETIRED.HITM_PS */
+	INTEL_UEVENT_CONSTRAINT(0x00c0, 0x1), /* INST_RETIRED.ANY_PS */
+	INTEL_UEVENT_CONSTRAINT(0x00c4, 0x1), /* BR_INST_RETIRED.ALL_BRANCHES_PS */
+	INTEL_UEVENT_CONSTRAINT(0x7ec4, 0x1), /* BR_INST_RETIRED.JCC_PS */
+	INTEL_UEVENT_CONSTRAINT(0xbfc4, 0x1), /* BR_INST_RETIRED.FAR_BRANCH_PS */
+	INTEL_UEVENT_CONSTRAINT(0xebc4, 0x1), /* BR_INST_RETIRED.NON_RETURN_IND_PS */
+	INTEL_UEVENT_CONSTRAINT(0xf7c4, 0x1), /* BR_INST_RETIRED.RETURN_PS */
+	INTEL_UEVENT_CONSTRAINT(0xf9c4, 0x1), /* BR_INST_RETIRED.CALL_PS */
+	INTEL_UEVENT_CONSTRAINT(0xfbc4, 0x1), /* BR_INST_RETIRED.IND_CALL_PS */
+	INTEL_UEVENT_CONSTRAINT(0xfdc4, 0x1), /* BR_INST_RETIRED.REL_CALL_PS */
+	INTEL_UEVENT_CONSTRAINT(0xfec4, 0x1), /* BR_INST_RETIRED.TAKEN_JCC_PS */
+	INTEL_UEVENT_CONSTRAINT(0x00c5, 0x1), /* BR_INST_MISP_RETIRED.ALL_BRANCHES_PS */
+	INTEL_UEVENT_CONSTRAINT(0x7ec5, 0x1), /* BR_INST_MISP_RETIRED.JCC_PS */
+	INTEL_UEVENT_CONSTRAINT(0xebc5, 0x1), /* BR_INST_MISP_RETIRED.NON_RETURN_IND_PS */
+	INTEL_UEVENT_CONSTRAINT(0xf7c5, 0x1), /* BR_INST_MISP_RETIRED.RETURN_PS */
+	INTEL_UEVENT_CONSTRAINT(0xfbc5, 0x1), /* BR_INST_MISP_RETIRED.IND_CALL_PS */
+	INTEL_UEVENT_CONSTRAINT(0xfec5, 0x1), /* BR_INST_MISP_RETIRED.TAKEN_JCC_PS */
+	EVENT_CONSTRAINT_END
+};
+
 struct event_constraint intel_nehalem_pebs_event_constraints[] = {
 	INTEL_PLD_CONSTRAINT(0x100b, 0xf),      /* MEM_INST_RETIRED.* */
 	INTEL_EVENT_CONSTRAINT(0x0f, 0xf),    /* MEM_UNCORE_RETIRED.* */
@@ -558,6 +584,7 @@ struct event_constraint intel_snb_pebs_event_constraints[] = {
 	INTEL_EVENT_CONSTRAINT(0xd0, 0xf),    /* MEM_UOP_RETIRED.* */
 	INTEL_EVENT_CONSTRAINT(0xd1, 0xf),    /* MEM_LOAD_UOPS_RETIRED.* */
 	INTEL_EVENT_CONSTRAINT(0xd2, 0xf),    /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */
+	INTEL_EVENT_CONSTRAINT(0xd3, 0xf),    /* MEM_LOAD_UOPS_LLC_MISS_RETIRED.* */
 	INTEL_UEVENT_CONSTRAINT(0x02d4, 0xf), /* MEM_LOAD_UOPS_MISC_RETIRED.LLC_MISS */
 	EVENT_CONSTRAINT_END
 };
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
index 1fb6c72717bd..4118f9f68315 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -6,6 +6,8 @@ static struct intel_uncore_type **pci_uncores = empty_uncore;
 /* pci bus to socket mapping */
 static int pcibus_to_physid[256] = { [0 ... 255] = -1, };
 
+static struct pci_dev *extra_pci_dev[UNCORE_SOCKET_MAX][UNCORE_EXTRA_PCI_DEV_MAX];
+
 static DEFINE_RAW_SPINLOCK(uncore_box_lock);
 
 /* mask of cpus that collect uncore events */
@@ -45,6 +47,24 @@ DEFINE_UNCORE_FORMAT_ATTR(filter_band0, filter_band0, "config1:0-7");
 DEFINE_UNCORE_FORMAT_ATTR(filter_band1, filter_band1, "config1:8-15");
 DEFINE_UNCORE_FORMAT_ATTR(filter_band2, filter_band2, "config1:16-23");
 DEFINE_UNCORE_FORMAT_ATTR(filter_band3, filter_band3, "config1:24-31");
+DEFINE_UNCORE_FORMAT_ATTR(match_rds, match_rds, "config1:48-51");
+DEFINE_UNCORE_FORMAT_ATTR(match_rnid30, match_rnid30, "config1:32-35");
+DEFINE_UNCORE_FORMAT_ATTR(match_rnid4, match_rnid4, "config1:31");
+DEFINE_UNCORE_FORMAT_ATTR(match_dnid, match_dnid, "config1:13-17");
+DEFINE_UNCORE_FORMAT_ATTR(match_mc, match_mc, "config1:9-12");
+DEFINE_UNCORE_FORMAT_ATTR(match_opc, match_opc, "config1:5-8");
+DEFINE_UNCORE_FORMAT_ATTR(match_vnw, match_vnw, "config1:3-4");
+DEFINE_UNCORE_FORMAT_ATTR(match0, match0, "config1:0-31");
+DEFINE_UNCORE_FORMAT_ATTR(match1, match1, "config1:32-63");
+DEFINE_UNCORE_FORMAT_ATTR(mask_rds, mask_rds, "config2:48-51");
+DEFINE_UNCORE_FORMAT_ATTR(mask_rnid30, mask_rnid30, "config2:32-35");
+DEFINE_UNCORE_FORMAT_ATTR(mask_rnid4, mask_rnid4, "config2:31");
+DEFINE_UNCORE_FORMAT_ATTR(mask_dnid, mask_dnid, "config2:13-17");
+DEFINE_UNCORE_FORMAT_ATTR(mask_mc, mask_mc, "config2:9-12");
+DEFINE_UNCORE_FORMAT_ATTR(mask_opc, mask_opc, "config2:5-8");
+DEFINE_UNCORE_FORMAT_ATTR(mask_vnw, mask_vnw, "config2:3-4");
+DEFINE_UNCORE_FORMAT_ATTR(mask0, mask0, "config2:0-31");
+DEFINE_UNCORE_FORMAT_ATTR(mask1, mask1, "config2:32-63");
 
 static u64 uncore_msr_read_counter(struct intel_uncore_box *box, struct perf_event *event)
 {
@@ -281,7 +301,7 @@ static struct attribute *snbep_uncore_cbox_formats_attr[] = {
 };
 
 static struct attribute *snbep_uncore_pcu_formats_attr[] = {
-	&format_attr_event.attr,
+	&format_attr_event_ext.attr,
 	&format_attr_occ_sel.attr,
 	&format_attr_edge.attr,
 	&format_attr_inv.attr,
@@ -301,6 +321,24 @@ static struct attribute *snbep_uncore_qpi_formats_attr[] = {
 	&format_attr_edge.attr,
 	&format_attr_inv.attr,
 	&format_attr_thresh8.attr,
+	&format_attr_match_rds.attr,
+	&format_attr_match_rnid30.attr,
+	&format_attr_match_rnid4.attr,
+	&format_attr_match_dnid.attr,
+	&format_attr_match_mc.attr,
+	&format_attr_match_opc.attr,
+	&format_attr_match_vnw.attr,
+	&format_attr_match0.attr,
+	&format_attr_match1.attr,
+	&format_attr_mask_rds.attr,
+	&format_attr_mask_rnid30.attr,
+	&format_attr_mask_rnid4.attr,
+	&format_attr_mask_dnid.attr,
+	&format_attr_mask_mc.attr,
+	&format_attr_mask_opc.attr,
+	&format_attr_mask_vnw.attr,
+	&format_attr_mask0.attr,
+	&format_attr_mask1.attr,
 	NULL,
 };
 
@@ -356,13 +394,16 @@ static struct intel_uncore_ops snbep_uncore_msr_ops = {
 	SNBEP_UNCORE_MSR_OPS_COMMON_INIT(),
 };
 
+#define SNBEP_UNCORE_PCI_OPS_COMMON_INIT()			\
+	.init_box	= snbep_uncore_pci_init_box,		\
+	.disable_box	= snbep_uncore_pci_disable_box,		\
+	.enable_box	= snbep_uncore_pci_enable_box,		\
+	.disable_event	= snbep_uncore_pci_disable_event,	\
+	.read_counter	= snbep_uncore_pci_read_counter
+
 static struct intel_uncore_ops snbep_uncore_pci_ops = {
-	.init_box	= snbep_uncore_pci_init_box,
-	.disable_box	= snbep_uncore_pci_disable_box,
-	.enable_box	= snbep_uncore_pci_enable_box,
-	.disable_event	= snbep_uncore_pci_disable_event,
-	.enable_event	= snbep_uncore_pci_enable_event,
-	.read_counter	= snbep_uncore_pci_read_counter,
+	SNBEP_UNCORE_PCI_OPS_COMMON_INIT(),
+	.enable_event	= snbep_uncore_pci_enable_event,	\
 };
 
 static struct event_constraint snbep_uncore_cbox_constraints[] = {
@@ -726,6 +767,61 @@ static struct intel_uncore_type *snbep_msr_uncores[] = {
 	NULL,
 };
 
+enum {
+	SNBEP_PCI_QPI_PORT0_FILTER,
+	SNBEP_PCI_QPI_PORT1_FILTER,
+};
+
+static int snbep_qpi_hw_config(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+	struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
+
+	if ((hwc->config & SNBEP_PMON_CTL_EV_SEL_MASK) == 0x38) {
+		reg1->idx = 0;
+		reg1->reg = SNBEP_Q_Py_PCI_PMON_PKT_MATCH0;
+		reg1->config = event->attr.config1;
+		reg2->reg = SNBEP_Q_Py_PCI_PMON_PKT_MASK0;
+		reg2->config = event->attr.config2;
+	}
+	return 0;
+}
+
+static void snbep_qpi_enable_event(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct pci_dev *pdev = box->pci_dev;
+	struct hw_perf_event *hwc = &event->hw;
+	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+	struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
+
+	if (reg1->idx != EXTRA_REG_NONE) {
+		int idx = box->pmu->pmu_idx + SNBEP_PCI_QPI_PORT0_FILTER;
+		struct pci_dev *filter_pdev = extra_pci_dev[box->phys_id][idx];
+		WARN_ON_ONCE(!filter_pdev);
+		if (filter_pdev) {
+			pci_write_config_dword(filter_pdev, reg1->reg,
+						(u32)reg1->config);
+			pci_write_config_dword(filter_pdev, reg1->reg + 4,
+						(u32)(reg1->config >> 32));
+			pci_write_config_dword(filter_pdev, reg2->reg,
+						(u32)reg2->config);
+			pci_write_config_dword(filter_pdev, reg2->reg + 4,
+						(u32)(reg2->config >> 32));
+		}
+	}
+
+	pci_write_config_dword(pdev, hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN);
+}
+
+static struct intel_uncore_ops snbep_uncore_qpi_ops = {
+	SNBEP_UNCORE_PCI_OPS_COMMON_INIT(),
+	.enable_event		= snbep_qpi_enable_event,
+	.hw_config		= snbep_qpi_hw_config,
+	.get_constraint		= uncore_get_constraint,
+	.put_constraint		= uncore_put_constraint,
+};
+
 #define SNBEP_UNCORE_PCI_COMMON_INIT()				\
 	.perf_ctr	= SNBEP_PCI_PMON_CTR0,			\
 	.event_ctl	= SNBEP_PCI_PMON_CTL0,			\
@@ -755,17 +851,18 @@ static struct intel_uncore_type snbep_uncore_imc = {
 };
 
 static struct intel_uncore_type snbep_uncore_qpi = {
-	.name		= "qpi",
-	.num_counters   = 4,
-	.num_boxes	= 2,
-	.perf_ctr_bits	= 48,
-	.perf_ctr	= SNBEP_PCI_PMON_CTR0,
-	.event_ctl	= SNBEP_PCI_PMON_CTL0,
-	.event_mask	= SNBEP_QPI_PCI_PMON_RAW_EVENT_MASK,
-	.box_ctl	= SNBEP_PCI_PMON_BOX_CTL,
-	.ops		= &snbep_uncore_pci_ops,
-	.event_descs	= snbep_uncore_qpi_events,
-	.format_group	= &snbep_uncore_qpi_format_group,
+	.name			= "qpi",
+	.num_counters		= 4,
+	.num_boxes		= 2,
+	.perf_ctr_bits		= 48,
+	.perf_ctr		= SNBEP_PCI_PMON_CTR0,
+	.event_ctl		= SNBEP_PCI_PMON_CTL0,
+	.event_mask		= SNBEP_QPI_PCI_PMON_RAW_EVENT_MASK,
+	.box_ctl		= SNBEP_PCI_PMON_BOX_CTL,
+	.num_shared_regs	= 1,
+	.ops			= &snbep_uncore_qpi_ops,
+	.event_descs		= snbep_uncore_qpi_events,
+	.format_group		= &snbep_uncore_qpi_format_group,
 };
 
 
@@ -807,43 +904,53 @@ static struct intel_uncore_type *snbep_pci_uncores[] = {
 static DEFINE_PCI_DEVICE_TABLE(snbep_uncore_pci_ids) = {
 	{ /* Home Agent */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_HA),
-		.driver_data = SNBEP_PCI_UNCORE_HA,
+		.driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_HA, 0),
 	},
 	{ /* MC Channel 0 */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC0),
-		.driver_data = SNBEP_PCI_UNCORE_IMC,
+		.driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_IMC, 0),
 	},
 	{ /* MC Channel 1 */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC1),
-		.driver_data = SNBEP_PCI_UNCORE_IMC,
+		.driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_IMC, 1),
 	},
 	{ /* MC Channel 2 */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC2),
-		.driver_data = SNBEP_PCI_UNCORE_IMC,
+		.driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_IMC, 2),
 	},
 	{ /* MC Channel 3 */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC3),
-		.driver_data = SNBEP_PCI_UNCORE_IMC,
+		.driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_IMC, 3),
 	},
 	{ /* QPI Port 0 */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_QPI0),
-		.driver_data = SNBEP_PCI_UNCORE_QPI,
+		.driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_QPI, 0),
 	},
 	{ /* QPI Port 1 */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_QPI1),
-		.driver_data = SNBEP_PCI_UNCORE_QPI,
+		.driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_QPI, 1),
 	},
 	{ /* R2PCIe */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_R2PCIE),
-		.driver_data = SNBEP_PCI_UNCORE_R2PCIE,
+		.driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_R2PCIE, 0),
 	},
 	{ /* R3QPI Link 0 */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_R3QPI0),
-		.driver_data = SNBEP_PCI_UNCORE_R3QPI,
+		.driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_R3QPI, 0),
 	},
 	{ /* R3QPI Link 1 */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_R3QPI1),
-		.driver_data = SNBEP_PCI_UNCORE_R3QPI,
+		.driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_R3QPI, 1),
+	},
+	{ /* QPI Port 0 filter  */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x3c86),
+		.driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
+						   SNBEP_PCI_QPI_PORT0_FILTER),
+	},
+	{ /* QPI Port 0 filter  */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x3c96),
+		.driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
+						   SNBEP_PCI_QPI_PORT1_FILTER),
 	},
 	{ /* end: all zeroes */ }
 };
@@ -1256,71 +1363,71 @@ static struct intel_uncore_type *ivt_pci_uncores[] = {
 static DEFINE_PCI_DEVICE_TABLE(ivt_uncore_pci_ids) = {
 	{ /* Home Agent 0 */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe30),
-		.driver_data = IVT_PCI_UNCORE_HA,
+		.driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_HA, 0),
 	},
 	{ /* Home Agent 1 */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe38),
-		.driver_data = IVT_PCI_UNCORE_HA,
+		.driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_HA, 1),
 	},
 	{ /* MC0 Channel 0 */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb4),
-		.driver_data = IVT_PCI_UNCORE_IMC,
+		.driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 0),
 	},
 	{ /* MC0 Channel 1 */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb5),
-		.driver_data = IVT_PCI_UNCORE_IMC,
+		.driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 1),
 	},
 	{ /* MC0 Channel 3 */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb0),
-		.driver_data = IVT_PCI_UNCORE_IMC,
+		.driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 2),
 	},
 	{ /* MC0 Channel 4 */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb1),
-		.driver_data = IVT_PCI_UNCORE_IMC,
+		.driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 3),
 	},
 	{ /* MC1 Channel 0 */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef4),
-		.driver_data = IVT_PCI_UNCORE_IMC,
+		.driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 4),
 	},
 	{ /* MC1 Channel 1 */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef5),
-		.driver_data = IVT_PCI_UNCORE_IMC,
+		.driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 5),
 	},
 	{ /* MC1 Channel 3 */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef0),
-		.driver_data = IVT_PCI_UNCORE_IMC,
+		.driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 6),
 	},
 	{ /* MC1 Channel 4 */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef1),
-		.driver_data = IVT_PCI_UNCORE_IMC,
+		.driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 7),
 	},
 	{ /* QPI0 Port 0 */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe32),
-		.driver_data = IVT_PCI_UNCORE_QPI,
+		.driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_QPI, 0),
 	},
 	{ /* QPI0 Port 1 */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe33),
-		.driver_data = IVT_PCI_UNCORE_QPI,
+		.driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_QPI, 1),
 	},
 	{ /* QPI1 Port 2 */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe3a),
-		.driver_data = IVT_PCI_UNCORE_QPI,
+		.driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_QPI, 2),
 	},
 	{ /* R2PCIe */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe34),
-		.driver_data = IVT_PCI_UNCORE_R2PCIE,
+		.driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_R2PCIE, 0),
 	},
 	{ /* R3QPI0 Link 0 */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe36),
-		.driver_data = IVT_PCI_UNCORE_R3QPI,
+		.driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_R3QPI, 0),
 	},
 	{ /* R3QPI0 Link 1 */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe37),
-		.driver_data = IVT_PCI_UNCORE_R3QPI,
+		.driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_R3QPI, 1),
 	},
 	{ /* R3QPI1 Link 2 */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe3e),
-		.driver_data = IVT_PCI_UNCORE_R3QPI,
+		.driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_R3QPI, 2),
 	},
 	{ /* end: all zeroes */ }
 };
@@ -2599,14 +2706,14 @@ static void uncore_pmu_init_hrtimer(struct intel_uncore_box *box)
 	box->hrtimer.function = uncore_pmu_hrtimer;
 }
 
-struct intel_uncore_box *uncore_alloc_box(struct intel_uncore_type *type, int cpu)
+static struct intel_uncore_box *uncore_alloc_box(struct intel_uncore_type *type, int node)
 {
 	struct intel_uncore_box *box;
 	int i, size;
 
 	size = sizeof(*box) + type->num_shared_regs * sizeof(struct intel_uncore_extra_reg);
 
-	box = kmalloc_node(size, GFP_KERNEL | __GFP_ZERO, cpu_to_node(cpu));
+	box = kzalloc_node(size, GFP_KERNEL, node);
 	if (!box)
 		return NULL;
 
@@ -2701,7 +2808,7 @@ uncore_get_event_constraint(struct intel_uncore_box *box, struct perf_event *eve
 			return c;
 	}
 
-	if (event->hw.config == ~0ULL)
+	if (event->attr.config == UNCORE_FIXED_EVENT)
 		return &constraint_fixed;
 
 	if (type->constraints) {
@@ -2924,7 +3031,7 @@ static int uncore_validate_group(struct intel_uncore_pmu *pmu,
 	struct intel_uncore_box *fake_box;
 	int ret = -EINVAL, n;
 
-	fake_box = uncore_alloc_box(pmu->type, smp_processor_id());
+	fake_box = uncore_alloc_box(pmu->type, NUMA_NO_NODE);
 	if (!fake_box)
 		return -ENOMEM;
 
@@ -3005,7 +3112,9 @@ static int uncore_pmu_event_init(struct perf_event *event)
 		 */
 		if (pmu->type->single_fixed && pmu->pmu_idx > 0)
 			return -EINVAL;
-		hwc->config = ~0ULL;
+
+		/* fixed counters have event field hardcoded to zero */
+		hwc->config = 0ULL;
 	} else {
 		hwc->config = event->attr.config & pmu->type->event_mask;
 		if (pmu->type->ops->hw_config) {
@@ -3167,17 +3276,25 @@ static bool pcidrv_registered;
 /*
  * add a pci uncore device
  */
-static int uncore_pci_add(struct intel_uncore_type *type, struct pci_dev *pdev)
+static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 {
 	struct intel_uncore_pmu *pmu;
 	struct intel_uncore_box *box;
-	int i, phys_id;
+	struct intel_uncore_type *type;
+	int phys_id;
 
 	phys_id = pcibus_to_physid[pdev->bus->number];
 	if (phys_id < 0)
 		return -ENODEV;
 
-	box = uncore_alloc_box(type, 0);
+	if (UNCORE_PCI_DEV_TYPE(id->driver_data) == UNCORE_EXTRA_PCI_DEV) {
+		extra_pci_dev[phys_id][UNCORE_PCI_DEV_IDX(id->driver_data)] = pdev;
+		pci_set_drvdata(pdev, NULL);
+		return 0;
+	}
+
+	type = pci_uncores[UNCORE_PCI_DEV_TYPE(id->driver_data)];
+	box = uncore_alloc_box(type, NUMA_NO_NODE);
 	if (!box)
 		return -ENOMEM;
 
@@ -3185,21 +3302,11 @@ static int uncore_pci_add(struct intel_uncore_type *type, struct pci_dev *pdev)
 	 * for performance monitoring unit with multiple boxes,
 	 * each box has a different function id.
 	 */
-	for (i = 0; i < type->num_boxes; i++) {
-		pmu = &type->pmus[i];
-		if (pmu->func_id == pdev->devfn)
-			break;
-		if (pmu->func_id < 0) {
-			pmu->func_id = pdev->devfn;
-			break;
-		}
-		pmu = NULL;
-	}
-
-	if (!pmu) {
-		kfree(box);
-		return -EINVAL;
-	}
+	pmu = &type->pmus[UNCORE_PCI_DEV_IDX(id->driver_data)];
+	if (pmu->func_id < 0)
+		pmu->func_id = pdev->devfn;
+	else
+		WARN_ON_ONCE(pmu->func_id != pdev->devfn);
 
 	box->phys_id = phys_id;
 	box->pci_dev = pdev;
@@ -3217,9 +3324,22 @@ static int uncore_pci_add(struct intel_uncore_type *type, struct pci_dev *pdev)
 static void uncore_pci_remove(struct pci_dev *pdev)
 {
 	struct intel_uncore_box *box = pci_get_drvdata(pdev);
-	struct intel_uncore_pmu *pmu = box->pmu;
-	int cpu, phys_id = pcibus_to_physid[pdev->bus->number];
+	struct intel_uncore_pmu *pmu;
+	int i, cpu, phys_id = pcibus_to_physid[pdev->bus->number];
+
+	box = pci_get_drvdata(pdev);
+	if (!box) {
+		for (i = 0; i < UNCORE_EXTRA_PCI_DEV_MAX; i++) {
+			if (extra_pci_dev[phys_id][i] == pdev) {
+				extra_pci_dev[phys_id][i] = NULL;
+				break;
+			}
+		}
+		WARN_ON_ONCE(i >= UNCORE_EXTRA_PCI_DEV_MAX);
+		return;
+	}
 
+	pmu = box->pmu;
 	if (WARN_ON_ONCE(phys_id != box->phys_id))
 		return;
 
@@ -3240,12 +3360,6 @@ static void uncore_pci_remove(struct pci_dev *pdev)
 	kfree(box);
 }
 
-static int uncore_pci_probe(struct pci_dev *pdev,
-			    const struct pci_device_id *id)
-{
-	return uncore_pci_add(pci_uncores[id->driver_data], pdev);
-}
-
 static int __init uncore_pci_init(void)
 {
 	int ret;
@@ -3385,7 +3499,7 @@ static int uncore_cpu_prepare(int cpu, int phys_id)
 			if (pmu->func_id < 0)
 				pmu->func_id = j;
 
-			box = uncore_alloc_box(type, cpu);
+			box = uncore_alloc_box(type, cpu_to_node(cpu));
 			if (!box)
 				return -ENOMEM;
 
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
index 47b3d00c9d89..a80ab71a883d 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
@@ -12,6 +12,15 @@
 #define UNCORE_PMC_IDX_FIXED		UNCORE_PMC_IDX_MAX_GENERIC
 #define UNCORE_PMC_IDX_MAX		(UNCORE_PMC_IDX_FIXED + 1)
 
+#define UNCORE_PCI_DEV_DATA(type, idx)	((type << 8) | idx)
+#define UNCORE_PCI_DEV_TYPE(data)	((data >> 8) & 0xff)
+#define UNCORE_PCI_DEV_IDX(data)	(data & 0xff)
+#define UNCORE_EXTRA_PCI_DEV		0xff
+#define UNCORE_EXTRA_PCI_DEV_MAX	2
+
+/* support up to 8 sockets */
+#define UNCORE_SOCKET_MAX		8
+
 #define UNCORE_EVENT_CONSTRAINT(c, n) EVENT_CONSTRAINT(c, n, 0xff)
 
 /* SNB event control */
@@ -108,6 +117,7 @@
 				(SNBEP_PMON_CTL_EV_SEL_MASK | \
 				 SNBEP_PCU_MSR_PMON_CTL_OCC_SEL_MASK | \
 				 SNBEP_PMON_CTL_EDGE_DET | \
+				 SNBEP_PMON_CTL_EV_SEL_EXT | \
 				 SNBEP_PMON_CTL_INVERT | \
 				 SNBEP_PCU_MSR_PMON_CTL_TRESH_MASK | \
 				 SNBEP_PCU_MSR_PMON_CTL_OCC_INVERT | \
diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c
index 7076878404ec..628a059a9a06 100644
--- a/arch/x86/kernel/cpu/vmware.c
+++ b/arch/x86/kernel/cpu/vmware.c
@@ -93,7 +93,7 @@ static void __init vmware_platform_setup(void)
  * serial key should be enough, as this will always have a VMware
  * specific string when running under VMware hypervisor.
  */
-static bool __init vmware_platform(void)
+static uint32_t __init vmware_platform(void)
 {
 	if (cpu_has_hypervisor) {
 		unsigned int eax;
@@ -102,12 +102,12 @@ static bool __init vmware_platform(void)
 		cpuid(CPUID_VMWARE_INFO_LEAF, &eax, &hyper_vendor_id[0],
 		      &hyper_vendor_id[1], &hyper_vendor_id[2]);
 		if (!memcmp(hyper_vendor_id, "VMwareVMware", 12))
-			return true;
+			return CPUID_VMWARE_INFO_LEAF;
 	} else if (dmi_available && dmi_name_in_serial("VMware") &&
 		   __vmware_platform())
-		return true;
+		return 1;
 
-	return false;
+	return 0;
 }
 
 /*
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index 74467feb4dc5..e0e0841eef45 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -128,7 +128,9 @@ void native_machine_crash_shutdown(struct pt_regs *regs)
 	cpu_emergency_svm_disable();
 
 	lapic_shutdown();
-#if defined(CONFIG_X86_IO_APIC)
+#ifdef CONFIG_X86_IO_APIC
+	/* Prevent crash_kexec() from deadlocking on ioapic_lock. */
+	ioapic_zap_locks();
 	disable_IO_APIC();
 #endif
 #ifdef CONFIG_HPET_TIMER
diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c
index 69eb2fa25494..376dc7873447 100644
--- a/arch/x86/kernel/devicetree.c
+++ b/arch/x86/kernel/devicetree.c
@@ -52,8 +52,7 @@ void * __init early_init_dt_alloc_memory_arch(u64 size, u64 align)
 }
 
 #ifdef CONFIG_BLK_DEV_INITRD
-void __init early_init_dt_setup_initrd_arch(unsigned long start,
-					    unsigned long end)
+void __init early_init_dt_setup_initrd_arch(u64 start, u64 end)
 {
 	initrd_start = (unsigned long)__va(start);
 	initrd_end = (unsigned long)__va(end);
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index d32abeabbda5..174da5fc5a7b 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -658,15 +658,18 @@ __init void e820_setup_gap(void)
  * boot_params.e820_map, others are passed via SETUP_E820_EXT node of
  * linked list of struct setup_data, which is parsed here.
  */
-void __init parse_e820_ext(struct setup_data *sdata)
+void __init parse_e820_ext(u64 phys_addr, u32 data_len)
 {
 	int entries;
 	struct e820entry *extmap;
+	struct setup_data *sdata;
 
+	sdata = early_memremap(phys_addr, data_len);
 	entries = sdata->len / sizeof(struct e820entry);
 	extmap = (struct e820entry *)(sdata->data);
 	__append_e820_map(extmap, entries);
 	sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
+	early_iounmap(sdata, data_len);
 	printk(KERN_INFO "e820: extended physical RAM map:\n");
 	e820_print_map("extended");
 }
diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c
index 63bdb29b2549..b3cd3ebae077 100644
--- a/arch/x86/kernel/early-quirks.c
+++ b/arch/x86/kernel/early-quirks.c
@@ -12,6 +12,7 @@
 #include <linux/pci.h>
 #include <linux/acpi.h>
 #include <linux/pci_ids.h>
+#include <drm/i915_drm.h>
 #include <asm/pci-direct.h>
 #include <asm/dma.h>
 #include <asm/io_apic.h>
@@ -216,6 +217,157 @@ static void __init intel_remapping_check(int num, int slot, int func)
 
 }
 
+/*
+ * Systems with Intel graphics controllers set aside memory exclusively
+ * for gfx driver use.  This memory is not marked in the E820 as reserved
+ * or as RAM, and so is subject to overlap from E820 manipulation later
+ * in the boot process.  On some systems, MMIO space is allocated on top,
+ * despite the efforts of the "RAM buffer" approach, which simply rounds
+ * memory boundaries up to 64M to try to catch space that may decode
+ * as RAM and so is not suitable for MMIO.
+ *
+ * And yes, so far on current devices the base addr is always under 4G.
+ */
+static u32 __init intel_stolen_base(int num, int slot, int func)
+{
+	u32 base;
+
+	/*
+	 * For the PCI IDs in this quirk, the stolen base is always
+	 * in 0x5c, aka the BDSM register (yes that's really what
+	 * it's called).
+	 */
+	base = read_pci_config(num, slot, func, 0x5c);
+	base &= ~((1<<20) - 1);
+
+	return base;
+}
+
+#define KB(x)	((x) * 1024)
+#define MB(x)	(KB (KB (x)))
+#define GB(x)	(MB (KB (x)))
+
+static size_t __init gen3_stolen_size(int num, int slot, int func)
+{
+	size_t stolen_size;
+	u16 gmch_ctrl;
+
+	gmch_ctrl = read_pci_config_16(0, 0, 0, I830_GMCH_CTRL);
+
+	switch (gmch_ctrl & I855_GMCH_GMS_MASK) {
+	case I855_GMCH_GMS_STOLEN_1M:
+		stolen_size = MB(1);
+		break;
+	case I855_GMCH_GMS_STOLEN_4M:
+		stolen_size = MB(4);
+		break;
+	case I855_GMCH_GMS_STOLEN_8M:
+		stolen_size = MB(8);
+		break;
+	case I855_GMCH_GMS_STOLEN_16M:
+		stolen_size = MB(16);
+		break;
+	case I855_GMCH_GMS_STOLEN_32M:
+		stolen_size = MB(32);
+		break;
+	case I915_GMCH_GMS_STOLEN_48M:
+		stolen_size = MB(48);
+		break;
+	case I915_GMCH_GMS_STOLEN_64M:
+		stolen_size = MB(64);
+		break;
+	case G33_GMCH_GMS_STOLEN_128M:
+		stolen_size = MB(128);
+		break;
+	case G33_GMCH_GMS_STOLEN_256M:
+		stolen_size = MB(256);
+		break;
+	case INTEL_GMCH_GMS_STOLEN_96M:
+		stolen_size = MB(96);
+		break;
+	case INTEL_GMCH_GMS_STOLEN_160M:
+		stolen_size = MB(160);
+		break;
+	case INTEL_GMCH_GMS_STOLEN_224M:
+		stolen_size = MB(224);
+		break;
+	case INTEL_GMCH_GMS_STOLEN_352M:
+		stolen_size = MB(352);
+		break;
+	default:
+		stolen_size = 0;
+		break;
+	}
+
+	return stolen_size;
+}
+
+static size_t __init gen6_stolen_size(int num, int slot, int func)
+{
+	u16 gmch_ctrl;
+
+	gmch_ctrl = read_pci_config_16(num, slot, func, SNB_GMCH_CTRL);
+	gmch_ctrl >>= SNB_GMCH_GMS_SHIFT;
+	gmch_ctrl &= SNB_GMCH_GMS_MASK;
+
+	return gmch_ctrl << 25; /* 32 MB units */
+}
+
+typedef size_t (*stolen_size_fn)(int num, int slot, int func);
+
+static struct pci_device_id intel_stolen_ids[] __initdata = {
+	INTEL_I915G_IDS(gen3_stolen_size),
+	INTEL_I915GM_IDS(gen3_stolen_size),
+	INTEL_I945G_IDS(gen3_stolen_size),
+	INTEL_I945GM_IDS(gen3_stolen_size),
+	INTEL_VLV_M_IDS(gen3_stolen_size),
+	INTEL_VLV_D_IDS(gen3_stolen_size),
+	INTEL_PINEVIEW_IDS(gen3_stolen_size),
+	INTEL_I965G_IDS(gen3_stolen_size),
+	INTEL_G33_IDS(gen3_stolen_size),
+	INTEL_I965GM_IDS(gen3_stolen_size),
+	INTEL_GM45_IDS(gen3_stolen_size),
+	INTEL_G45_IDS(gen3_stolen_size),
+	INTEL_IRONLAKE_D_IDS(gen3_stolen_size),
+	INTEL_IRONLAKE_M_IDS(gen3_stolen_size),
+	INTEL_SNB_D_IDS(gen6_stolen_size),
+	INTEL_SNB_M_IDS(gen6_stolen_size),
+	INTEL_IVB_M_IDS(gen6_stolen_size),
+	INTEL_IVB_D_IDS(gen6_stolen_size),
+	INTEL_HSW_D_IDS(gen6_stolen_size),
+	INTEL_HSW_M_IDS(gen6_stolen_size),
+};
+
+static void __init intel_graphics_stolen(int num, int slot, int func)
+{
+	size_t size;
+	int i;
+	u32 start;
+	u16 device, subvendor, subdevice;
+
+	device = read_pci_config_16(num, slot, func, PCI_DEVICE_ID);
+	subvendor = read_pci_config_16(num, slot, func,
+				       PCI_SUBSYSTEM_VENDOR_ID);
+	subdevice = read_pci_config_16(num, slot, func, PCI_SUBSYSTEM_ID);
+
+	for (i = 0; i < ARRAY_SIZE(intel_stolen_ids); i++) {
+		if (intel_stolen_ids[i].device == device) {
+			stolen_size_fn stolen_size =
+				(stolen_size_fn)intel_stolen_ids[i].driver_data;
+			size = stolen_size(num, slot, func);
+			start = intel_stolen_base(num, slot, func);
+			if (size && start) {
+				/* Mark this space as reserved */
+				e820_add_region(start, size, E820_RESERVED);
+				sanitize_e820_map(e820.map,
+						  ARRAY_SIZE(e820.map),
+						  &e820.nr_map);
+			}
+			return;
+		}
+	}
+}
+
 #define QFLAG_APPLY_ONCE 	0x1
 #define QFLAG_APPLIED		0x2
 #define QFLAG_DONE		(QFLAG_APPLY_ONCE|QFLAG_APPLIED)
@@ -251,6 +403,8 @@ static struct chipset early_qrk[] __initdata = {
 	  PCI_BASE_CLASS_BRIDGE, 0, intel_remapping_check },
 	{ PCI_VENDOR_ID_INTEL, 0x3406, PCI_CLASS_BRIDGE_HOST,
 	  PCI_BASE_CLASS_BRIDGE, 0, intel_remapping_check },
+	{ PCI_VENDOR_ID_INTEL, PCI_ANY_ID, PCI_CLASS_DISPLAY_VGA, PCI_ANY_ID,
+	  QFLAG_APPLY_ONCE, intel_graphics_stolen },
 	{}
 };
 
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index 2cfbc3a3a2dd..f0dcb0ceb6a2 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -1176,6 +1176,9 @@ ftrace_restore_flags:
 #else /* ! CONFIG_DYNAMIC_FTRACE */
 
 ENTRY(mcount)
+	cmpl $__PAGE_OFFSET, %esp
+	jb ftrace_stub		/* Paging not enabled yet? */
+
 	cmpl $0, function_trace_stop
 	jne  ftrace_stub
 
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 1b69951a81e2..b077f4cc225a 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -487,21 +487,6 @@ ENDPROC(native_usergs_sysret64)
 	TRACE_IRQS_OFF
 	.endm
 
-ENTRY(save_rest)
-	PARTIAL_FRAME 1 (REST_SKIP+8)
-	movq 5*8+16(%rsp), %r11	/* save return address */
-	movq_cfi rbx, RBX+16
-	movq_cfi rbp, RBP+16
-	movq_cfi r12, R12+16
-	movq_cfi r13, R13+16
-	movq_cfi r14, R14+16
-	movq_cfi r15, R15+16
-	movq %r11, 8(%rsp)	/* return address */
-	FIXUP_TOP_OF_STACK %r11, 16
-	ret
-	CFI_ENDPROC
-END(save_rest)
-
 /* save complete stack frame */
 	.pushsection .kprobes.text, "ax"
 ENTRY(save_paranoid)
diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c
index 138463a24877..06f87bece92a 100644
--- a/arch/x86/kernel/head32.c
+++ b/arch/x86/kernel/head32.c
@@ -29,7 +29,7 @@ static void __init i386_default_early_setup(void)
 	reserve_ebda_region();
 }
 
-void __init i386_start_kernel(void)
+asmlinkage void __init i386_start_kernel(void)
 {
 	sanitize_boot_params(&boot_params);
 
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 55b67614ed94..1be8e43b669e 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -137,7 +137,7 @@ static void __init copy_bootdata(char *real_mode_data)
 	}
 }
 
-void __init x86_64_start_kernel(char * real_mode_data)
+asmlinkage void __init x86_64_start_kernel(char * real_mode_data)
 {
 	int i;
 
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index 5dd87a89f011..81ba27679f18 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -409,6 +409,7 @@ enable_paging:
 /*
  * Check if it is 486
  */
+	movb $4,X86			# at least 486
 	cmpl $-1,X86_CPUID
 	je is486
 
@@ -436,7 +437,6 @@ enable_paging:
 	movl %edx,X86_CAPABILITY
 
 is486:
-	movb $4,X86
 	movl $0x50022,%ecx	# set AM, WP, NE and MP
 	movl %cr0,%eax
 	andl $0x80000011,%eax	# Save PG,PE,ET
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 3a8185c042a2..22d0687e7fda 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -177,7 +177,7 @@ u64 arch_irq_stat(void)
  * SMP cross-CPU interrupts have their own specific
  * handlers).
  */
-unsigned int __irq_entry do_IRQ(struct pt_regs *regs)
+__visible unsigned int __irq_entry do_IRQ(struct pt_regs *regs)
 {
 	struct pt_regs *old_regs = set_irq_regs(regs);
 
@@ -215,7 +215,7 @@ void __smp_x86_platform_ipi(void)
 		x86_platform_ipi_callback();
 }
 
-void smp_x86_platform_ipi(struct pt_regs *regs)
+__visible void smp_x86_platform_ipi(struct pt_regs *regs)
 {
 	struct pt_regs *old_regs = set_irq_regs(regs);
 
@@ -229,7 +229,7 @@ void smp_x86_platform_ipi(struct pt_regs *regs)
 /*
  * Handler for POSTED_INTERRUPT_VECTOR.
  */
-void smp_kvm_posted_intr_ipi(struct pt_regs *regs)
+__visible void smp_kvm_posted_intr_ipi(struct pt_regs *regs)
 {
 	struct pt_regs *old_regs = set_irq_regs(regs);
 
@@ -247,7 +247,7 @@ void smp_kvm_posted_intr_ipi(struct pt_regs *regs)
 }
 #endif
 
-void smp_trace_x86_platform_ipi(struct pt_regs *regs)
+__visible void smp_trace_x86_platform_ipi(struct pt_regs *regs)
 {
 	struct pt_regs *old_regs = set_irq_regs(regs);
 
diff --git a/arch/x86/kernel/irq_work.c b/arch/x86/kernel/irq_work.c
index 636a55e4a13c..1de84e3ab4e0 100644
--- a/arch/x86/kernel/irq_work.c
+++ b/arch/x86/kernel/irq_work.c
@@ -22,14 +22,14 @@ static inline void __smp_irq_work_interrupt(void)
 	irq_work_run();
 }
 
-void smp_irq_work_interrupt(struct pt_regs *regs)
+__visible void smp_irq_work_interrupt(struct pt_regs *regs)
 {
 	irq_work_entering_irq();
 	__smp_irq_work_interrupt();
 	exiting_irq();
 }
 
-void smp_trace_irq_work_interrupt(struct pt_regs *regs)
+__visible void smp_trace_irq_work_interrupt(struct pt_regs *regs)
 {
 	irq_work_entering_irq();
 	trace_irq_work_entry(IRQ_WORK_VECTOR);
diff --git a/arch/x86/kernel/jump_label.c b/arch/x86/kernel/jump_label.c
index 2889b3d43882..ee11b7dfbfbb 100644
--- a/arch/x86/kernel/jump_label.c
+++ b/arch/x86/kernel/jump_label.c
@@ -24,20 +24,71 @@ union jump_code_union {
 	} __attribute__((packed));
 };
 
+static void bug_at(unsigned char *ip, int line)
+{
+	/*
+	 * The location is not an op that we were expecting.
+	 * Something went wrong. Crash the box, as something could be
+	 * corrupting the kernel.
+	 */
+	pr_warning("Unexpected op at %pS [%p] (%02x %02x %02x %02x %02x) %s:%d\n",
+	       ip, ip, ip[0], ip[1], ip[2], ip[3], ip[4], __FILE__, line);
+	BUG();
+}
+
 static void __jump_label_transform(struct jump_entry *entry,
 				   enum jump_label_type type,
-				   void *(*poker)(void *, const void *, size_t))
+				   void *(*poker)(void *, const void *, size_t),
+				   int init)
 {
 	union jump_code_union code;
+	const unsigned char *ideal_nop = ideal_nops[NOP_ATOMIC5];
 
 	if (type == JUMP_LABEL_ENABLE) {
+		/*
+		 * We are enabling this jump label. If it is not a nop
+		 * then something must have gone wrong.
+		 */
+		if (unlikely(memcmp((void *)entry->code, ideal_nop, 5) != 0))
+			bug_at((void *)entry->code, __LINE__);
+
 		code.jump = 0xe9;
 		code.offset = entry->target -
 				(entry->code + JUMP_LABEL_NOP_SIZE);
-	} else
+	} else {
+		/*
+		 * We are disabling this jump label. If it is not what
+		 * we think it is, then something must have gone wrong.
+		 * If this is the first initialization call, then we
+		 * are converting the default nop to the ideal nop.
+		 */
+		if (init) {
+			const unsigned char default_nop[] = { STATIC_KEY_INIT_NOP };
+			if (unlikely(memcmp((void *)entry->code, default_nop, 5) != 0))
+				bug_at((void *)entry->code, __LINE__);
+		} else {
+			code.jump = 0xe9;
+			code.offset = entry->target -
+				(entry->code + JUMP_LABEL_NOP_SIZE);
+			if (unlikely(memcmp((void *)entry->code, &code, 5) != 0))
+				bug_at((void *)entry->code, __LINE__);
+		}
 		memcpy(&code, ideal_nops[NOP_ATOMIC5], JUMP_LABEL_NOP_SIZE);
+	}
 
-	(*poker)((void *)entry->code, &code, JUMP_LABEL_NOP_SIZE);
+	/*
+	 * Make text_poke_bp() a default fallback poker.
+	 *
+	 * At the time the change is being done, just ignore whether we
+	 * are doing nop -> jump or jump -> nop transition, and assume
+	 * always nop being the 'currently valid' instruction
+	 *
+	 */
+	if (poker)
+		(*poker)((void *)entry->code, &code, JUMP_LABEL_NOP_SIZE);
+	else
+		text_poke_bp((void *)entry->code, &code, JUMP_LABEL_NOP_SIZE,
+			     (void *)entry->code + JUMP_LABEL_NOP_SIZE);
 }
 
 void arch_jump_label_transform(struct jump_entry *entry,
@@ -45,15 +96,38 @@ void arch_jump_label_transform(struct jump_entry *entry,
 {
 	get_online_cpus();
 	mutex_lock(&text_mutex);
-	__jump_label_transform(entry, type, text_poke_smp);
+	__jump_label_transform(entry, type, NULL, 0);
 	mutex_unlock(&text_mutex);
 	put_online_cpus();
 }
 
+static enum {
+	JL_STATE_START,
+	JL_STATE_NO_UPDATE,
+	JL_STATE_UPDATE,
+} jlstate __initdata_or_module = JL_STATE_START;
+
 __init_or_module void arch_jump_label_transform_static(struct jump_entry *entry,
 				      enum jump_label_type type)
 {
-	__jump_label_transform(entry, type, text_poke_early);
+	/*
+	 * This function is called at boot up and when modules are
+	 * first loaded. Check if the default nop, the one that is
+	 * inserted at compile time, is the ideal nop. If it is, then
+	 * we do not need to update the nop, and we can leave it as is.
+	 * If it is not, then we need to update the nop to the ideal nop.
+	 */
+	if (jlstate == JL_STATE_START) {
+		const unsigned char default_nop[] = { STATIC_KEY_INIT_NOP };
+		const unsigned char *ideal_nop = ideal_nops[NOP_ATOMIC5];
+
+		if (memcmp(ideal_nop, default_nop, 5) != 0)
+			jlstate = JL_STATE_UPDATE;
+		else
+			jlstate = JL_STATE_NO_UPDATE;
+	}
+	if (jlstate == JL_STATE_UPDATE)
+		__jump_label_transform(entry, type, text_poke_early, 1);
 }
 
 #endif
diff --git a/arch/x86/kernel/kprobes/common.h b/arch/x86/kernel/kprobes/common.h
index 2e9d4b5af036..c6ee63f927ab 100644
--- a/arch/x86/kernel/kprobes/common.h
+++ b/arch/x86/kernel/kprobes/common.h
@@ -82,14 +82,9 @@ extern void synthesize_reljump(void *from, void *to);
 extern void synthesize_relcall(void *from, void *to);
 
 #ifdef	CONFIG_OPTPROBES
-extern int arch_init_optprobes(void);
 extern int setup_detour_execution(struct kprobe *p, struct pt_regs *regs, int reenter);
 extern unsigned long __recover_optprobed_insn(kprobe_opcode_t *buf, unsigned long addr);
 #else	/* !CONFIG_OPTPROBES */
-static inline int arch_init_optprobes(void)
-{
-	return 0;
-}
 static inline int setup_detour_execution(struct kprobe *p, struct pt_regs *regs, int reenter)
 {
 	return 0;
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 211bce445522..79a3f9682871 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -661,7 +661,7 @@ static void __used __kprobes kretprobe_trampoline_holder(void)
 /*
  * Called from kretprobe_trampoline
  */
-static __used __kprobes void *trampoline_handler(struct pt_regs *regs)
+__visible __used __kprobes void *trampoline_handler(struct pt_regs *regs)
 {
 	struct kretprobe_instance *ri = NULL;
 	struct hlist_head *head, empty_rp;
@@ -1068,7 +1068,7 @@ int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
 
 int __init arch_init_kprobes(void)
 {
-	return arch_init_optprobes();
+	return 0;
 }
 
 int __kprobes arch_trampoline_kprobe(struct kprobe *p)
diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c
index 76dc6f095724..898160b42e43 100644
--- a/arch/x86/kernel/kprobes/opt.c
+++ b/arch/x86/kernel/kprobes/opt.c
@@ -88,9 +88,7 @@ static void __kprobes synthesize_set_arg1(kprobe_opcode_t *addr, unsigned long v
 	*(unsigned long *)addr = val;
 }
 
-static void __used __kprobes kprobes_optinsn_template_holder(void)
-{
-	asm volatile (
+asm (
 			".global optprobe_template_entry\n"
 			"optprobe_template_entry:\n"
 #ifdef CONFIG_X86_64
@@ -129,7 +127,6 @@ static void __used __kprobes kprobes_optinsn_template_holder(void)
 #endif
 			".global optprobe_template_end\n"
 			"optprobe_template_end:\n");
-}
 
 #define TMPL_MOVE_IDX \
 	((long)&optprobe_template_val - (long)&optprobe_template_entry)
@@ -371,31 +368,6 @@ int __kprobes arch_prepare_optimized_kprobe(struct optimized_kprobe *op)
 	return 0;
 }
 
-#define MAX_OPTIMIZE_PROBES 256
-static struct text_poke_param *jump_poke_params;
-static struct jump_poke_buffer {
-	u8 buf[RELATIVEJUMP_SIZE];
-} *jump_poke_bufs;
-
-static void __kprobes setup_optimize_kprobe(struct text_poke_param *tprm,
-					    u8 *insn_buf,
-					    struct optimized_kprobe *op)
-{
-	s32 rel = (s32)((long)op->optinsn.insn -
-			((long)op->kp.addr + RELATIVEJUMP_SIZE));
-
-	/* Backup instructions which will be replaced by jump address */
-	memcpy(op->optinsn.copied_insn, op->kp.addr + INT3_SIZE,
-	       RELATIVE_ADDR_SIZE);
-
-	insn_buf[0] = RELATIVEJUMP_OPCODE;
-	*(s32 *)(&insn_buf[1]) = rel;
-
-	tprm->addr = op->kp.addr;
-	tprm->opcode = insn_buf;
-	tprm->len = RELATIVEJUMP_SIZE;
-}
-
 /*
  * Replace breakpoints (int3) with relative jumps.
  * Caller must call with locking kprobe_mutex and text_mutex.
@@ -403,37 +375,38 @@ static void __kprobes setup_optimize_kprobe(struct text_poke_param *tprm,
 void __kprobes arch_optimize_kprobes(struct list_head *oplist)
 {
 	struct optimized_kprobe *op, *tmp;
-	int c = 0;
+	u8 insn_buf[RELATIVEJUMP_SIZE];
 
 	list_for_each_entry_safe(op, tmp, oplist, list) {
+		s32 rel = (s32)((long)op->optinsn.insn -
+			((long)op->kp.addr + RELATIVEJUMP_SIZE));
+
 		WARN_ON(kprobe_disabled(&op->kp));
-		/* Setup param */
-		setup_optimize_kprobe(&jump_poke_params[c],
-				      jump_poke_bufs[c].buf, op);
+
+		/* Backup instructions which will be replaced by jump address */
+		memcpy(op->optinsn.copied_insn, op->kp.addr + INT3_SIZE,
+		       RELATIVE_ADDR_SIZE);
+
+		insn_buf[0] = RELATIVEJUMP_OPCODE;
+		*(s32 *)(&insn_buf[1]) = rel;
+
+		text_poke_bp(op->kp.addr, insn_buf, RELATIVEJUMP_SIZE,
+			     op->optinsn.insn);
+
 		list_del_init(&op->list);
-		if (++c >= MAX_OPTIMIZE_PROBES)
-			break;
 	}
-
-	/*
-	 * text_poke_smp doesn't support NMI/MCE code modifying.
-	 * However, since kprobes itself also doesn't support NMI/MCE
-	 * code probing, it's not a problem.
-	 */
-	text_poke_smp_batch(jump_poke_params, c);
 }
 
-static void __kprobes setup_unoptimize_kprobe(struct text_poke_param *tprm,
-					      u8 *insn_buf,
-					      struct optimized_kprobe *op)
+/* Replace a relative jump with a breakpoint (int3).  */
+void __kprobes arch_unoptimize_kprobe(struct optimized_kprobe *op)
 {
+	u8 insn_buf[RELATIVEJUMP_SIZE];
+
 	/* Set int3 to first byte for kprobes */
 	insn_buf[0] = BREAKPOINT_INSTRUCTION;
 	memcpy(insn_buf + 1, op->optinsn.copied_insn, RELATIVE_ADDR_SIZE);
-
-	tprm->addr = op->kp.addr;
-	tprm->opcode = insn_buf;
-	tprm->len = RELATIVEJUMP_SIZE;
+	text_poke_bp(op->kp.addr, insn_buf, RELATIVEJUMP_SIZE,
+		     op->optinsn.insn);
 }
 
 /*
@@ -444,34 +417,11 @@ extern void arch_unoptimize_kprobes(struct list_head *oplist,
 				    struct list_head *done_list)
 {
 	struct optimized_kprobe *op, *tmp;
-	int c = 0;
 
 	list_for_each_entry_safe(op, tmp, oplist, list) {
-		/* Setup param */
-		setup_unoptimize_kprobe(&jump_poke_params[c],
-					jump_poke_bufs[c].buf, op);
+		arch_unoptimize_kprobe(op);
 		list_move(&op->list, done_list);
-		if (++c >= MAX_OPTIMIZE_PROBES)
-			break;
 	}
-
-	/*
-	 * text_poke_smp doesn't support NMI/MCE code modifying.
-	 * However, since kprobes itself also doesn't support NMI/MCE
-	 * code probing, it's not a problem.
-	 */
-	text_poke_smp_batch(jump_poke_params, c);
-}
-
-/* Replace a relative jump with a breakpoint (int3).  */
-void __kprobes arch_unoptimize_kprobe(struct optimized_kprobe *op)
-{
-	u8 buf[RELATIVEJUMP_SIZE];
-
-	/* Set int3 to first byte for kprobes */
-	buf[0] = BREAKPOINT_INSTRUCTION;
-	memcpy(buf + 1, op->optinsn.copied_insn, RELATIVE_ADDR_SIZE);
-	text_poke_smp(op->kp.addr, buf, RELATIVEJUMP_SIZE);
 }
 
 int  __kprobes
@@ -491,22 +441,3 @@ setup_detour_execution(struct kprobe *p, struct pt_regs *regs, int reenter)
 	}
 	return 0;
 }
-
-int __kprobes arch_init_optprobes(void)
-{
-	/* Allocate code buffer and parameter array */
-	jump_poke_bufs = kmalloc(sizeof(struct jump_poke_buffer) *
-				 MAX_OPTIMIZE_PROBES, GFP_KERNEL);
-	if (!jump_poke_bufs)
-		return -ENOMEM;
-
-	jump_poke_params = kmalloc(sizeof(struct text_poke_param) *
-				   MAX_OPTIMIZE_PROBES, GFP_KERNEL);
-	if (!jump_poke_params) {
-		kfree(jump_poke_bufs);
-		jump_poke_bufs = NULL;
-		return -ENOMEM;
-	}
-
-	return 0;
-}
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index a96d32cc55b8..a0e2a8a80c94 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -34,6 +34,7 @@
 #include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/kprobes.h>
+#include <linux/debugfs.h>
 #include <asm/timer.h>
 #include <asm/cpu.h>
 #include <asm/traps.h>
@@ -419,6 +420,7 @@ static void __init kvm_smp_prepare_boot_cpu(void)
 	WARN_ON(kvm_register_clock("primary cpu clock"));
 	kvm_guest_cpu_init();
 	native_smp_prepare_boot_cpu();
+	kvm_spinlock_init();
 }
 
 static void kvm_guest_cpu_online(void *dummy)
@@ -498,11 +500,9 @@ void __init kvm_guest_init(void)
 #endif
 }
 
-static bool __init kvm_detect(void)
+static uint32_t __init kvm_detect(void)
 {
-	if (!kvm_para_available())
-		return false;
-	return true;
+	return kvm_cpuid_base();
 }
 
 const struct hypervisor_x86 x86_hyper_kvm __refconst = {
@@ -523,3 +523,274 @@ static __init int activate_jump_labels(void)
 	return 0;
 }
 arch_initcall(activate_jump_labels);
+
+#ifdef CONFIG_PARAVIRT_SPINLOCKS
+
+/* Kick a cpu by its apicid. Used to wake up a halted vcpu */
+static void kvm_kick_cpu(int cpu)
+{
+	int apicid;
+	unsigned long flags = 0;
+
+	apicid = per_cpu(x86_cpu_to_apicid, cpu);
+	kvm_hypercall2(KVM_HC_KICK_CPU, flags, apicid);
+}
+
+enum kvm_contention_stat {
+	TAKEN_SLOW,
+	TAKEN_SLOW_PICKUP,
+	RELEASED_SLOW,
+	RELEASED_SLOW_KICKED,
+	NR_CONTENTION_STATS
+};
+
+#ifdef CONFIG_KVM_DEBUG_FS
+#define HISTO_BUCKETS	30
+
+static struct kvm_spinlock_stats
+{
+	u32 contention_stats[NR_CONTENTION_STATS];
+	u32 histo_spin_blocked[HISTO_BUCKETS+1];
+	u64 time_blocked;
+} spinlock_stats;
+
+static u8 zero_stats;
+
+static inline void check_zero(void)
+{
+	u8 ret;
+	u8 old;
+
+	old = ACCESS_ONCE(zero_stats);
+	if (unlikely(old)) {
+		ret = cmpxchg(&zero_stats, old, 0);
+		/* This ensures only one fellow resets the stat */
+		if (ret == old)
+			memset(&spinlock_stats, 0, sizeof(spinlock_stats));
+	}
+}
+
+static inline void add_stats(enum kvm_contention_stat var, u32 val)
+{
+	check_zero();
+	spinlock_stats.contention_stats[var] += val;
+}
+
+
+static inline u64 spin_time_start(void)
+{
+	return sched_clock();
+}
+
+static void __spin_time_accum(u64 delta, u32 *array)
+{
+	unsigned index;
+
+	index = ilog2(delta);
+	check_zero();
+
+	if (index < HISTO_BUCKETS)
+		array[index]++;
+	else
+		array[HISTO_BUCKETS]++;
+}
+
+static inline void spin_time_accum_blocked(u64 start)
+{
+	u32 delta;
+
+	delta = sched_clock() - start;
+	__spin_time_accum(delta, spinlock_stats.histo_spin_blocked);
+	spinlock_stats.time_blocked += delta;
+}
+
+static struct dentry *d_spin_debug;
+static struct dentry *d_kvm_debug;
+
+struct dentry *kvm_init_debugfs(void)
+{
+	d_kvm_debug = debugfs_create_dir("kvm", NULL);
+	if (!d_kvm_debug)
+		printk(KERN_WARNING "Could not create 'kvm' debugfs directory\n");
+
+	return d_kvm_debug;
+}
+
+static int __init kvm_spinlock_debugfs(void)
+{
+	struct dentry *d_kvm;
+
+	d_kvm = kvm_init_debugfs();
+	if (d_kvm == NULL)
+		return -ENOMEM;
+
+	d_spin_debug = debugfs_create_dir("spinlocks", d_kvm);
+
+	debugfs_create_u8("zero_stats", 0644, d_spin_debug, &zero_stats);
+
+	debugfs_create_u32("taken_slow", 0444, d_spin_debug,
+		   &spinlock_stats.contention_stats[TAKEN_SLOW]);
+	debugfs_create_u32("taken_slow_pickup", 0444, d_spin_debug,
+		   &spinlock_stats.contention_stats[TAKEN_SLOW_PICKUP]);
+
+	debugfs_create_u32("released_slow", 0444, d_spin_debug,
+		   &spinlock_stats.contention_stats[RELEASED_SLOW]);
+	debugfs_create_u32("released_slow_kicked", 0444, d_spin_debug,
+		   &spinlock_stats.contention_stats[RELEASED_SLOW_KICKED]);
+
+	debugfs_create_u64("time_blocked", 0444, d_spin_debug,
+			   &spinlock_stats.time_blocked);
+
+	debugfs_create_u32_array("histo_blocked", 0444, d_spin_debug,
+		     spinlock_stats.histo_spin_blocked, HISTO_BUCKETS + 1);
+
+	return 0;
+}
+fs_initcall(kvm_spinlock_debugfs);
+#else  /* !CONFIG_KVM_DEBUG_FS */
+static inline void add_stats(enum kvm_contention_stat var, u32 val)
+{
+}
+
+static inline u64 spin_time_start(void)
+{
+	return 0;
+}
+
+static inline void spin_time_accum_blocked(u64 start)
+{
+}
+#endif  /* CONFIG_KVM_DEBUG_FS */
+
+struct kvm_lock_waiting {
+	struct arch_spinlock *lock;
+	__ticket_t want;
+};
+
+/* cpus 'waiting' on a spinlock to become available */
+static cpumask_t waiting_cpus;
+
+/* Track spinlock on which a cpu is waiting */
+static DEFINE_PER_CPU(struct kvm_lock_waiting, klock_waiting);
+
+static void kvm_lock_spinning(struct arch_spinlock *lock, __ticket_t want)
+{
+	struct kvm_lock_waiting *w;
+	int cpu;
+	u64 start;
+	unsigned long flags;
+
+	if (in_nmi())
+		return;
+
+	w = &__get_cpu_var(klock_waiting);
+	cpu = smp_processor_id();
+	start = spin_time_start();
+
+	/*
+	 * Make sure an interrupt handler can't upset things in a
+	 * partially setup state.
+	 */
+	local_irq_save(flags);
+
+	/*
+	 * The ordering protocol on this is that the "lock" pointer
+	 * may only be set non-NULL if the "want" ticket is correct.
+	 * If we're updating "want", we must first clear "lock".
+	 */
+	w->lock = NULL;
+	smp_wmb();
+	w->want = want;
+	smp_wmb();
+	w->lock = lock;
+
+	add_stats(TAKEN_SLOW, 1);
+
+	/*
+	 * This uses set_bit, which is atomic but we should not rely on its
+	 * reordering gurantees. So barrier is needed after this call.
+	 */
+	cpumask_set_cpu(cpu, &waiting_cpus);
+
+	barrier();
+
+	/*
+	 * Mark entry to slowpath before doing the pickup test to make
+	 * sure we don't deadlock with an unlocker.
+	 */
+	__ticket_enter_slowpath(lock);
+
+	/*
+	 * check again make sure it didn't become free while
+	 * we weren't looking.
+	 */
+	if (ACCESS_ONCE(lock->tickets.head) == want) {
+		add_stats(TAKEN_SLOW_PICKUP, 1);
+		goto out;
+	}
+
+	/*
+	 * halt until it's our turn and kicked. Note that we do safe halt
+	 * for irq enabled case to avoid hang when lock info is overwritten
+	 * in irq spinlock slowpath and no spurious interrupt occur to save us.
+	 */
+	if (arch_irqs_disabled_flags(flags))
+		halt();
+	else
+		safe_halt();
+
+out:
+	cpumask_clear_cpu(cpu, &waiting_cpus);
+	w->lock = NULL;
+	local_irq_restore(flags);
+	spin_time_accum_blocked(start);
+}
+PV_CALLEE_SAVE_REGS_THUNK(kvm_lock_spinning);
+
+/* Kick vcpu waiting on @lock->head to reach value @ticket */
+static void kvm_unlock_kick(struct arch_spinlock *lock, __ticket_t ticket)
+{
+	int cpu;
+
+	add_stats(RELEASED_SLOW, 1);
+	for_each_cpu(cpu, &waiting_cpus) {
+		const struct kvm_lock_waiting *w = &per_cpu(klock_waiting, cpu);
+		if (ACCESS_ONCE(w->lock) == lock &&
+		    ACCESS_ONCE(w->want) == ticket) {
+			add_stats(RELEASED_SLOW_KICKED, 1);
+			kvm_kick_cpu(cpu);
+			break;
+		}
+	}
+}
+
+/*
+ * Setup pv_lock_ops to exploit KVM_FEATURE_PV_UNHALT if present.
+ */
+void __init kvm_spinlock_init(void)
+{
+	if (!kvm_para_available())
+		return;
+	/* Does host kernel support KVM_FEATURE_PV_UNHALT? */
+	if (!kvm_para_has_feature(KVM_FEATURE_PV_UNHALT))
+		return;
+
+	pv_lock_ops.lock_spinning = PV_CALLEE_SAVE(kvm_lock_spinning);
+	pv_lock_ops.unlock_kick = kvm_unlock_kick;
+}
+
+static __init int kvm_spinlock_init_jump(void)
+{
+	if (!kvm_para_available())
+		return 0;
+	if (!kvm_para_has_feature(KVM_FEATURE_PV_UNHALT))
+		return 0;
+
+	static_key_slow_inc(&paravirt_ticketlocks_enabled);
+	printk(KERN_INFO "KVM setup paravirtual spinlock\n");
+
+	return 0;
+}
+early_initcall(kvm_spinlock_init_jump);
+
+#endif	/* CONFIG_PARAVIRT_SPINLOCKS */
diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c
index 7123b5df479d..af99f71aeb7f 100644
--- a/arch/x86/kernel/microcode_amd.c
+++ b/arch/x86/kernel/microcode_amd.c
@@ -216,6 +216,7 @@ int apply_microcode_amd(int cpu)
 	/* need to apply patch? */
 	if (rev >= mc_amd->hdr.patch_id) {
 		c->microcode = rev;
+		uci->cpu_sig.rev = rev;
 		return 0;
 	}
 
diff --git a/arch/x86/kernel/paravirt-spinlocks.c b/arch/x86/kernel/paravirt-spinlocks.c
index 676b8c77a976..bbb6c7316341 100644
--- a/arch/x86/kernel/paravirt-spinlocks.c
+++ b/arch/x86/kernel/paravirt-spinlocks.c
@@ -4,25 +4,17 @@
  */
 #include <linux/spinlock.h>
 #include <linux/module.h>
+#include <linux/jump_label.h>
 
 #include <asm/paravirt.h>
 
-static inline void
-default_spin_lock_flags(arch_spinlock_t *lock, unsigned long flags)
-{
-	arch_spin_lock(lock);
-}
-
 struct pv_lock_ops pv_lock_ops = {
 #ifdef CONFIG_SMP
-	.spin_is_locked = __ticket_spin_is_locked,
-	.spin_is_contended = __ticket_spin_is_contended,
-
-	.spin_lock = __ticket_spin_lock,
-	.spin_lock_flags = default_spin_lock_flags,
-	.spin_trylock = __ticket_spin_trylock,
-	.spin_unlock = __ticket_spin_unlock,
+	.lock_spinning = __PV_IS_CALLEE_SAVE(paravirt_nop),
+	.unlock_kick = paravirt_nop,
 #endif
 };
 EXPORT_SYMBOL(pv_lock_ops);
 
+struct static_key paravirt_ticketlocks_enabled = STATIC_KEY_INIT_FALSE;
+EXPORT_SYMBOL(paravirt_ticketlocks_enabled);
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index cd6de64cc480..1b10af835c31 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -62,11 +62,6 @@ void __init default_banner(void)
 	       pv_info.name);
 }
 
-/* Simple instruction patching code. */
-#define DEF_NATIVE(ops, name, code)					\
-	extern const char start_##ops##_##name[], end_##ops##_##name[];	\
-	asm("start_" #ops "_" #name ": " code "; end_" #ops "_" #name ":")
-
 /* Undefined instruction for dealing with missing ops pointers. */
 static const unsigned char ud2a[] = { 0x0f, 0x0b };
 
@@ -324,7 +319,7 @@ struct pv_time_ops pv_time_ops = {
 	.steal_clock = native_steal_clock,
 };
 
-struct pv_irq_ops pv_irq_ops = {
+__visible struct pv_irq_ops pv_irq_ops = {
 	.save_fl = __PV_IS_CALLEE_SAVE(native_save_fl),
 	.restore_fl = __PV_IS_CALLEE_SAVE(native_restore_fl),
 	.irq_disable = __PV_IS_CALLEE_SAVE(native_irq_disable),
@@ -336,7 +331,7 @@ struct pv_irq_ops pv_irq_ops = {
 #endif
 };
 
-struct pv_cpu_ops pv_cpu_ops = {
+__visible struct pv_cpu_ops pv_cpu_ops = {
 	.cpuid = native_cpuid,
 	.get_debugreg = native_get_debugreg,
 	.set_debugreg = native_set_debugreg,
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 83369e5a1d27..c83516be1052 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -36,7 +36,7 @@
  * section. Since TSS's are completely CPU-local, we want them
  * on exact cacheline boundaries, to eliminate cacheline ping-pong.
  */
-DEFINE_PER_CPU_SHARED_ALIGNED(struct tss_struct, init_tss) = INIT_TSS;
+__visible DEFINE_PER_CPU_SHARED_ALIGNED(struct tss_struct, init_tss) = INIT_TSS;
 
 #ifdef CONFIG_X86_64
 static DEFINE_PER_CPU(unsigned char, is_idle);
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index f8adefca71dc..884f98f69354 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -247,7 +247,7 @@ EXPORT_SYMBOL_GPL(start_thread);
  * the task-switch, and shows up in ret_from_fork in entry.S,
  * for example.
  */
-__notrace_funcgraph struct task_struct *
+__visible __notrace_funcgraph struct task_struct *
 __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 {
 	struct thread_struct *prev = &prev_p->thread,
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 05646bab4ca6..bb1dc51bab05 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -52,7 +52,7 @@
 
 asmlinkage extern void ret_from_fork(void);
 
-DEFINE_PER_CPU(unsigned long, old_rsp);
+asmlinkage DEFINE_PER_CPU(unsigned long, old_rsp);
 
 /* Prints also some state that isn't saved in the pt_regs */
 void __show_regs(struct pt_regs *regs, int all)
@@ -274,7 +274,7 @@ void start_thread_ia32(struct pt_regs *regs, u32 new_ip, u32 new_sp)
  * Kprobes not supported here. Set the probe on schedule instead.
  * Function graph tracer not supported too.
  */
-__notrace_funcgraph struct task_struct *
+__visible __notrace_funcgraph struct task_struct *
 __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 {
 	struct thread_struct *prev = &prev_p->thread;
diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c
index 2cb9470ea85b..a16bae3f83b3 100644
--- a/arch/x86/kernel/pvclock.c
+++ b/arch/x86/kernel/pvclock.c
@@ -128,46 +128,7 @@ void pvclock_read_wallclock(struct pvclock_wall_clock *wall_clock,
 	set_normalized_timespec(ts, now.tv_sec, now.tv_nsec);
 }
 
-static struct pvclock_vsyscall_time_info *pvclock_vdso_info;
-
-static struct pvclock_vsyscall_time_info *
-pvclock_get_vsyscall_user_time_info(int cpu)
-{
-	if (!pvclock_vdso_info) {
-		BUG();
-		return NULL;
-	}
-
-	return &pvclock_vdso_info[cpu];
-}
-
-struct pvclock_vcpu_time_info *pvclock_get_vsyscall_time_info(int cpu)
-{
-	return &pvclock_get_vsyscall_user_time_info(cpu)->pvti;
-}
-
 #ifdef CONFIG_X86_64
-static int pvclock_task_migrate(struct notifier_block *nb, unsigned long l,
-			        void *v)
-{
-	struct task_migration_notifier *mn = v;
-	struct pvclock_vsyscall_time_info *pvti;
-
-	pvti = pvclock_get_vsyscall_user_time_info(mn->from_cpu);
-
-	/* this is NULL when pvclock vsyscall is not initialized */
-	if (unlikely(pvti == NULL))
-		return NOTIFY_DONE;
-
-	pvti->migrate_count++;
-
-	return NOTIFY_DONE;
-}
-
-static struct notifier_block pvclock_migrate = {
-	.notifier_call = pvclock_task_migrate,
-};
-
 /*
  * Initialize the generic pvclock vsyscall state.  This will allocate
  * a/some page(s) for the per-vcpu pvclock information, set up a
@@ -181,17 +142,12 @@ int __init pvclock_init_vsyscall(struct pvclock_vsyscall_time_info *i,
 
 	WARN_ON (size != PVCLOCK_VSYSCALL_NR_PAGES*PAGE_SIZE);
 
-	pvclock_vdso_info = i;
-
 	for (idx = 0; idx <= (PVCLOCK_FIXMAP_END-PVCLOCK_FIXMAP_BEGIN); idx++) {
 		__set_fixmap(PVCLOCK_FIXMAP_BEGIN + idx,
 			     __pa(i) + (idx*PAGE_SIZE),
 			     PAGE_KERNEL_VVAR);
 	}
 
-
-	register_task_migration_notifier(&pvclock_migrate);
-
 	return 0;
 }
 #endif
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 563ed91e6faa..7e920bff99a3 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -326,6 +326,14 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "Latitude E6320"),
 		},
 	},
+	{	/* Handle problems with rebooting on the Latitude E5410. */
+		.callback = set_pci_reboot,
+		.ident = "Dell Latitude E5410",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Latitude E5410"),
+		},
+	},
 	{	/* Handle problems with rebooting on the Latitude E5420. */
 		.callback = set_pci_reboot,
 		.ident = "Dell Latitude E5420",
@@ -352,12 +360,28 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = {
 	},
 	{	/* Handle problems with rebooting on the Precision M6600. */
 		.callback = set_pci_reboot,
-		.ident = "Dell OptiPlex 990",
+		.ident = "Dell Precision M6600",
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
 			DMI_MATCH(DMI_PRODUCT_NAME, "Precision M6600"),
 		},
 	},
+	{	/* Handle problems with rebooting on the Dell PowerEdge C6100. */
+		.callback = set_pci_reboot,
+		.ident = "Dell PowerEdge C6100",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "C6100"),
+		},
+	},
+	{	/* Some C6100 machines were shipped with vendor being 'Dell'. */
+		.callback = set_pci_reboot,
+		.ident = "Dell PowerEdge C6100",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "C6100"),
+		},
+	},
 	{ }
 };
 
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index f8ec57815c05..f0de6294b955 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -206,9 +206,9 @@ EXPORT_SYMBOL(boot_cpu_data);
 
 
 #if !defined(CONFIG_X86_PAE) || defined(CONFIG_X86_64)
-unsigned long mmu_cr4_features;
+__visible unsigned long mmu_cr4_features;
 #else
-unsigned long mmu_cr4_features = X86_CR4_PAE;
+__visible unsigned long mmu_cr4_features = X86_CR4_PAE;
 #endif
 
 /* Boot loader ID and version as integers, for the benefit of proc_dointvec */
@@ -426,25 +426,23 @@ static void __init reserve_initrd(void)
 static void __init parse_setup_data(void)
 {
 	struct setup_data *data;
-	u64 pa_data;
+	u64 pa_data, pa_next;
 
 	pa_data = boot_params.hdr.setup_data;
 	while (pa_data) {
-		u32 data_len, map_len;
+		u32 data_len, map_len, data_type;
 
 		map_len = max(PAGE_SIZE - (pa_data & ~PAGE_MASK),
 			      (u64)sizeof(struct setup_data));
 		data = early_memremap(pa_data, map_len);
 		data_len = data->len + sizeof(struct setup_data);
-		if (data_len > map_len) {
-			early_iounmap(data, map_len);
-			data = early_memremap(pa_data, data_len);
-			map_len = data_len;
-		}
+		data_type = data->type;
+		pa_next = data->next;
+		early_iounmap(data, map_len);
 
-		switch (data->type) {
+		switch (data_type) {
 		case SETUP_E820_EXT:
-			parse_e820_ext(data);
+			parse_e820_ext(pa_data, data_len);
 			break;
 		case SETUP_DTB:
 			add_dtb(pa_data);
@@ -452,8 +450,7 @@ static void __init parse_setup_data(void)
 		default:
 			break;
 		}
-		pa_data = data->next;
-		early_iounmap(data, map_len);
+		pa_data = pa_next;
 	}
 }
 
@@ -1070,7 +1067,7 @@ void __init setup_arch(char **cmdline_p)
 
 	cleanup_highmap();
 
-	memblock.current_limit = ISA_END_ADDRESS;
+	memblock_set_current_limit(ISA_END_ADDRESS);
 	memblock_x86_fill();
 
 	/*
@@ -1103,7 +1100,7 @@ void __init setup_arch(char **cmdline_p)
 
 	setup_real_mode();
 
-	memblock.current_limit = get_max_mapped();
+	memblock_set_current_limit(get_max_mapped());
 	dma_contiguous_reserve(0);
 
 	/*
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index cf913587d4dd..9e5de6813e1f 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -358,7 +358,7 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig,
 		else
 			put_user_ex(0, &frame->uc.uc_flags);
 		put_user_ex(0, &frame->uc.uc_link);
-		err |= __save_altstack(&frame->uc.uc_stack, regs->sp);
+		save_altstack_ex(&frame->uc.uc_stack, regs->sp);
 
 		/* Set up to return from userspace.  */
 		restorer = VDSO32_SYMBOL(current->mm->context.vdso, rt_sigreturn);
@@ -423,7 +423,7 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig,
 		else
 			put_user_ex(0, &frame->uc.uc_flags);
 		put_user_ex(0, &frame->uc.uc_link);
-		err |= __save_altstack(&frame->uc.uc_stack, regs->sp);
+		save_altstack_ex(&frame->uc.uc_stack, regs->sp);
 
 		/* Set up to return from userspace.  If provided, use a stub
 		   already in userspace.  */
@@ -490,7 +490,7 @@ static int x32_setup_rt_frame(struct ksignal *ksig,
 		else
 			put_user_ex(0, &frame->uc.uc_flags);
 		put_user_ex(0, &frame->uc.uc_link);
-		err |= __compat_save_altstack(&frame->uc.uc_stack, regs->sp);
+		compat_save_altstack_ex(&frame->uc.uc_stack, regs->sp);
 		put_user_ex(0, &frame->uc.uc__pad0);
 
 		if (ksig->ka.sa.sa_flags & SA_RESTORER) {
@@ -533,7 +533,7 @@ static int x32_setup_rt_frame(struct ksignal *ksig,
  * Do a signal return; undo the signal stack.
  */
 #ifdef CONFIG_X86_32
-unsigned long sys_sigreturn(void)
+asmlinkage unsigned long sys_sigreturn(void)
 {
 	struct pt_regs *regs = current_pt_regs();
 	struct sigframe __user *frame;
@@ -562,7 +562,7 @@ badframe:
 }
 #endif /* CONFIG_X86_32 */
 
-long sys_rt_sigreturn(void)
+asmlinkage long sys_rt_sigreturn(void)
 {
 	struct pt_regs *regs = current_pt_regs();
 	struct rt_sigframe __user *frame;
@@ -728,7 +728,7 @@ static void do_signal(struct pt_regs *regs)
  * notification of userspace execution resumption
  * - triggered by the TIF_WORK_MASK flags
  */
-void
+__visible void
 do_notify_resume(struct pt_regs *regs, void *unused, __u32 thread_info_flags)
 {
 	user_exit();
diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c
index cdaa347dfcad..7c3a5a61f2e4 100644
--- a/arch/x86/kernel/smp.c
+++ b/arch/x86/kernel/smp.c
@@ -256,7 +256,7 @@ static inline void __smp_reschedule_interrupt(void)
 	scheduler_ipi();
 }
 
-void smp_reschedule_interrupt(struct pt_regs *regs)
+__visible void smp_reschedule_interrupt(struct pt_regs *regs)
 {
 	ack_APIC_irq();
 	__smp_reschedule_interrupt();
@@ -271,7 +271,7 @@ static inline void smp_entering_irq(void)
 	irq_enter();
 }
 
-void smp_trace_reschedule_interrupt(struct pt_regs *regs)
+__visible void smp_trace_reschedule_interrupt(struct pt_regs *regs)
 {
 	/*
 	 * Need to call irq_enter() before calling the trace point.
@@ -295,14 +295,14 @@ static inline void __smp_call_function_interrupt(void)
 	inc_irq_stat(irq_call_count);
 }
 
-void smp_call_function_interrupt(struct pt_regs *regs)
+__visible void smp_call_function_interrupt(struct pt_regs *regs)
 {
 	smp_entering_irq();
 	__smp_call_function_interrupt();
 	exiting_irq();
 }
 
-void smp_trace_call_function_interrupt(struct pt_regs *regs)
+__visible void smp_trace_call_function_interrupt(struct pt_regs *regs)
 {
 	smp_entering_irq();
 	trace_call_function_entry(CALL_FUNCTION_VECTOR);
@@ -317,14 +317,14 @@ static inline void __smp_call_function_single_interrupt(void)
 	inc_irq_stat(irq_call_count);
 }
 
-void smp_call_function_single_interrupt(struct pt_regs *regs)
+__visible void smp_call_function_single_interrupt(struct pt_regs *regs)
 {
 	smp_entering_irq();
 	__smp_call_function_single_interrupt();
 	exiting_irq();
 }
 
-void smp_trace_call_function_single_interrupt(struct pt_regs *regs)
+__visible void smp_trace_call_function_single_interrupt(struct pt_regs *regs)
 {
 	smp_entering_irq();
 	trace_call_function_single_entry(CALL_FUNCTION_SINGLE_VECTOR);
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index aecc98a93d1b..6cacab671f9b 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -653,6 +653,7 @@ static void announce_cpu(int cpu, int apicid)
 {
 	static int current_node = -1;
 	int node = early_cpu_to_node(cpu);
+	int max_cpu_present = find_last_bit(cpumask_bits(cpu_present_mask), NR_CPUS);
 
 	if (system_state == SYSTEM_BOOTING) {
 		if (node != current_node) {
@@ -661,7 +662,7 @@ static void announce_cpu(int cpu, int apicid)
 			current_node = node;
 			pr_info("Booting Node %3d, Processors ", node);
 		}
-		pr_cont(" #%d%s", cpu, cpu == (nr_cpu_ids - 1) ? " OK\n" : "");
+		pr_cont(" #%4d%s", cpu, cpu == max_cpu_present ? " OK\n" : "");
 		return;
 	} else
 		pr_info("Booting Node %d Processor %d APIC 0x%x\n",
diff --git a/arch/x86/kernel/syscall_32.c b/arch/x86/kernel/syscall_32.c
index 147fcd4941c4..e9bcd57d8a9e 100644
--- a/arch/x86/kernel/syscall_32.c
+++ b/arch/x86/kernel/syscall_32.c
@@ -15,7 +15,7 @@ typedef asmlinkage void (*sys_call_ptr_t)(void);
 
 extern asmlinkage void sys_ni_syscall(void);
 
-const sys_call_ptr_t sys_call_table[__NR_syscall_max+1] = {
+__visible const sys_call_ptr_t sys_call_table[__NR_syscall_max+1] = {
 	/*
 	 * Smells like a compiler bug -- it doesn't work
 	 * when the & below is removed.
diff --git a/arch/x86/kernel/syscall_64.c b/arch/x86/kernel/syscall_64.c
index 5c7f8c20da74..4ac730b37f0b 100644
--- a/arch/x86/kernel/syscall_64.c
+++ b/arch/x86/kernel/syscall_64.c
@@ -4,6 +4,7 @@
 #include <linux/sys.h>
 #include <linux/cache.h>
 #include <asm/asm-offsets.h>
+#include <asm/syscall.h>
 
 #define __SYSCALL_COMMON(nr, sym, compat) __SYSCALL_64(nr, sym, compat)
 
@@ -19,11 +20,9 @@
 
 #define __SYSCALL_64(nr, sym, compat) [nr] = sym,
 
-typedef void (*sys_call_ptr_t)(void);
-
 extern void sys_ni_syscall(void);
 
-const sys_call_ptr_t sys_call_table[__NR_syscall_max+1] = {
+asmlinkage const sys_call_ptr_t sys_call_table[__NR_syscall_max+1] = {
 	/*
 	 * Smells like a compiler bug -- it doesn't work
 	 * when the & below is removed.
diff --git a/arch/x86/kernel/sysfb.c b/arch/x86/kernel/sysfb.c
new file mode 100644
index 000000000000..193ec2ce46c7
--- /dev/null
+++ b/arch/x86/kernel/sysfb.c
@@ -0,0 +1,74 @@
+/*
+ * Generic System Framebuffers on x86
+ * Copyright (c) 2012-2013 David Herrmann <dh.herrmann@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ */
+
+/*
+ * Simple-Framebuffer support for x86 systems
+ * Create a platform-device for any available boot framebuffer. The
+ * simple-framebuffer platform device is already available on DT systems, so
+ * this module parses the global "screen_info" object and creates a suitable
+ * platform device compatible with the "simple-framebuffer" DT object. If
+ * the framebuffer is incompatible, we instead create a legacy
+ * "vesa-framebuffer", "efi-framebuffer" or "platform-framebuffer" device and
+ * pass the screen_info as platform_data. This allows legacy drivers
+ * to pick these devices up without messing with simple-framebuffer drivers.
+ * The global "screen_info" is still valid at all times.
+ *
+ * If CONFIG_X86_SYSFB is not selected, we never register "simple-framebuffer"
+ * platform devices, but only use legacy framebuffer devices for
+ * backwards compatibility.
+ *
+ * TODO: We set the dev_id field of all platform-devices to 0. This allows
+ * other x86 OF/DT parsers to create such devices, too. However, they must
+ * start at offset 1 for this to work.
+ */
+
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/platform_data/simplefb.h>
+#include <linux/platform_device.h>
+#include <linux/screen_info.h>
+#include <asm/sysfb.h>
+
+static __init int sysfb_init(void)
+{
+	struct screen_info *si = &screen_info;
+	struct simplefb_platform_data mode;
+	struct platform_device *pd;
+	const char *name;
+	bool compatible;
+	int ret;
+
+	sysfb_apply_efi_quirks();
+
+	/* try to create a simple-framebuffer device */
+	compatible = parse_mode(si, &mode);
+	if (compatible) {
+		ret = create_simplefb(si, &mode);
+		if (!ret)
+			return 0;
+	}
+
+	/* if the FB is incompatible, create a legacy framebuffer device */
+	if (si->orig_video_isVGA == VIDEO_TYPE_EFI)
+		name = "efi-framebuffer";
+	else if (si->orig_video_isVGA == VIDEO_TYPE_VLFB)
+		name = "vesa-framebuffer";
+	else
+		name = "platform-framebuffer";
+
+	pd = platform_device_register_resndata(NULL, name, 0,
+					       NULL, 0, si, sizeof(*si));
+	return IS_ERR(pd) ? PTR_ERR(pd) : 0;
+}
+
+/* must execute after PCI subsystem for EFI quirks */
+device_initcall(sysfb_init);
diff --git a/arch/x86/kernel/sysfb_efi.c b/arch/x86/kernel/sysfb_efi.c
new file mode 100644
index 000000000000..b285d4e8c68e
--- /dev/null
+++ b/arch/x86/kernel/sysfb_efi.c
@@ -0,0 +1,214 @@
+/*
+ * Generic System Framebuffers on x86
+ * Copyright (c) 2012-2013 David Herrmann <dh.herrmann@gmail.com>
+ *
+ * EFI Quirks Copyright (c) 2006 Edgar Hucek <gimli@dark-green.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ */
+
+/*
+ * EFI Quirks
+ * Several EFI systems do not correctly advertise their boot framebuffers.
+ * Hence, we use this static table of known broken machines and fix up the
+ * information so framebuffer drivers can load corectly.
+ */
+
+#include <linux/dmi.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/pci.h>
+#include <linux/screen_info.h>
+#include <video/vga.h>
+#include <asm/sysfb.h>
+
+enum {
+	OVERRIDE_NONE = 0x0,
+	OVERRIDE_BASE = 0x1,
+	OVERRIDE_STRIDE = 0x2,
+	OVERRIDE_HEIGHT = 0x4,
+	OVERRIDE_WIDTH = 0x8,
+};
+
+struct efifb_dmi_info efifb_dmi_list[] = {
+	[M_I17] = { "i17", 0x80010000, 1472 * 4, 1440, 900, OVERRIDE_NONE },
+	[M_I20] = { "i20", 0x80010000, 1728 * 4, 1680, 1050, OVERRIDE_NONE }, /* guess */
+	[M_I20_SR] = { "imac7", 0x40010000, 1728 * 4, 1680, 1050, OVERRIDE_NONE },
+	[M_I24] = { "i24", 0x80010000, 2048 * 4, 1920, 1200, OVERRIDE_NONE }, /* guess */
+	[M_I24_8_1] = { "imac8", 0xc0060000, 2048 * 4, 1920, 1200, OVERRIDE_NONE },
+	[M_I24_10_1] = { "imac10", 0xc0010000, 2048 * 4, 1920, 1080, OVERRIDE_NONE },
+	[M_I27_11_1] = { "imac11", 0xc0010000, 2560 * 4, 2560, 1440, OVERRIDE_NONE },
+	[M_MINI]= { "mini", 0x80000000, 2048 * 4, 1024, 768, OVERRIDE_NONE },
+	[M_MINI_3_1] = { "mini31", 0x40010000, 1024 * 4, 1024, 768, OVERRIDE_NONE },
+	[M_MINI_4_1] = { "mini41", 0xc0010000, 2048 * 4, 1920, 1200, OVERRIDE_NONE },
+	[M_MB] = { "macbook", 0x80000000, 2048 * 4, 1280, 800, OVERRIDE_NONE },
+	[M_MB_5_1] = { "macbook51", 0x80010000, 2048 * 4, 1280, 800, OVERRIDE_NONE },
+	[M_MB_6_1] = { "macbook61", 0x80010000, 2048 * 4, 1280, 800, OVERRIDE_NONE },
+	[M_MB_7_1] = { "macbook71", 0x80010000, 2048 * 4, 1280, 800, OVERRIDE_NONE },
+	[M_MBA] = { "mba", 0x80000000, 2048 * 4, 1280, 800, OVERRIDE_NONE },
+	/* 11" Macbook Air 3,1 passes the wrong stride */
+	[M_MBA_3] = { "mba3", 0, 2048 * 4, 0, 0, OVERRIDE_STRIDE },
+	[M_MBP] = { "mbp", 0x80010000, 1472 * 4, 1440, 900, OVERRIDE_NONE },
+	[M_MBP_2] = { "mbp2", 0, 0, 0, 0, OVERRIDE_NONE }, /* placeholder */
+	[M_MBP_2_2] = { "mbp22", 0x80010000, 1472 * 4, 1440, 900, OVERRIDE_NONE },
+	[M_MBP_SR] = { "mbp3", 0x80030000, 2048 * 4, 1440, 900, OVERRIDE_NONE },
+	[M_MBP_4] = { "mbp4", 0xc0060000, 2048 * 4, 1920, 1200, OVERRIDE_NONE },
+	[M_MBP_5_1] = { "mbp51", 0xc0010000, 2048 * 4, 1440, 900, OVERRIDE_NONE },
+	[M_MBP_5_2] = { "mbp52", 0xc0010000, 2048 * 4, 1920, 1200, OVERRIDE_NONE },
+	[M_MBP_5_3] = { "mbp53", 0xd0010000, 2048 * 4, 1440, 900, OVERRIDE_NONE },
+	[M_MBP_6_1] = { "mbp61", 0x90030000, 2048 * 4, 1920, 1200, OVERRIDE_NONE },
+	[M_MBP_6_2] = { "mbp62", 0x90030000, 2048 * 4, 1680, 1050, OVERRIDE_NONE },
+	[M_MBP_7_1] = { "mbp71", 0xc0010000, 2048 * 4, 1280, 800, OVERRIDE_NONE },
+	[M_MBP_8_2] = { "mbp82", 0x90010000, 1472 * 4, 1440, 900, OVERRIDE_NONE },
+	[M_UNKNOWN] = { NULL, 0, 0, 0, 0, OVERRIDE_NONE }
+};
+
+#define choose_value(dmivalue, fwvalue, field, flags) ({	\
+		typeof(fwvalue) _ret_ = fwvalue;		\
+		if ((flags) & (field))				\
+			_ret_ = dmivalue;			\
+		else if ((fwvalue) == 0)			\
+			_ret_ = dmivalue;			\
+		_ret_;						\
+	})
+
+static int __init efifb_set_system(const struct dmi_system_id *id)
+{
+	struct efifb_dmi_info *info = id->driver_data;
+
+	if (info->base == 0 && info->height == 0 && info->width == 0 &&
+	    info->stride == 0)
+		return 0;
+
+	/* Trust the bootloader over the DMI tables */
+	if (screen_info.lfb_base == 0) {
+#if defined(CONFIG_PCI)
+		struct pci_dev *dev = NULL;
+		int found_bar = 0;
+#endif
+		if (info->base) {
+			screen_info.lfb_base = choose_value(info->base,
+				screen_info.lfb_base, OVERRIDE_BASE,
+				info->flags);
+
+#if defined(CONFIG_PCI)
+			/* make sure that the address in the table is actually
+			 * on a VGA device's PCI BAR */
+
+			for_each_pci_dev(dev) {
+				int i;
+				if ((dev->class >> 8) != PCI_CLASS_DISPLAY_VGA)
+					continue;
+				for (i = 0; i < DEVICE_COUNT_RESOURCE; i++) {
+					resource_size_t start, end;
+
+					start = pci_resource_start(dev, i);
+					if (start == 0)
+						break;
+					end = pci_resource_end(dev, i);
+					if (screen_info.lfb_base >= start &&
+					    screen_info.lfb_base < end) {
+						found_bar = 1;
+					}
+				}
+			}
+			if (!found_bar)
+				screen_info.lfb_base = 0;
+#endif
+		}
+	}
+	if (screen_info.lfb_base) {
+		screen_info.lfb_linelength = choose_value(info->stride,
+			screen_info.lfb_linelength, OVERRIDE_STRIDE,
+			info->flags);
+		screen_info.lfb_width = choose_value(info->width,
+			screen_info.lfb_width, OVERRIDE_WIDTH,
+			info->flags);
+		screen_info.lfb_height = choose_value(info->height,
+			screen_info.lfb_height, OVERRIDE_HEIGHT,
+			info->flags);
+		if (screen_info.orig_video_isVGA == 0)
+			screen_info.orig_video_isVGA = VIDEO_TYPE_EFI;
+	} else {
+		screen_info.lfb_linelength = 0;
+		screen_info.lfb_width = 0;
+		screen_info.lfb_height = 0;
+		screen_info.orig_video_isVGA = 0;
+		return 0;
+	}
+
+	printk(KERN_INFO "efifb: dmi detected %s - framebuffer at 0x%08x "
+			 "(%dx%d, stride %d)\n", id->ident,
+			 screen_info.lfb_base, screen_info.lfb_width,
+			 screen_info.lfb_height, screen_info.lfb_linelength);
+
+	return 1;
+}
+
+#define EFIFB_DMI_SYSTEM_ID(vendor, name, enumid)		\
+	{							\
+		efifb_set_system,				\
+		name,						\
+		{						\
+			DMI_MATCH(DMI_BIOS_VENDOR, vendor),	\
+			DMI_MATCH(DMI_PRODUCT_NAME, name)	\
+		},						\
+		&efifb_dmi_list[enumid]				\
+	}
+
+static const struct dmi_system_id efifb_dmi_system_table[] __initconst = {
+	EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "iMac4,1", M_I17),
+	/* At least one of these two will be right; maybe both? */
+	EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "iMac5,1", M_I20),
+	EFIFB_DMI_SYSTEM_ID("Apple Inc.", "iMac5,1", M_I20),
+	/* At least one of these two will be right; maybe both? */
+	EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "iMac6,1", M_I24),
+	EFIFB_DMI_SYSTEM_ID("Apple Inc.", "iMac6,1", M_I24),
+	EFIFB_DMI_SYSTEM_ID("Apple Inc.", "iMac7,1", M_I20_SR),
+	EFIFB_DMI_SYSTEM_ID("Apple Inc.", "iMac8,1", M_I24_8_1),
+	EFIFB_DMI_SYSTEM_ID("Apple Inc.", "iMac10,1", M_I24_10_1),
+	EFIFB_DMI_SYSTEM_ID("Apple Inc.", "iMac11,1", M_I27_11_1),
+	EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "Macmini1,1", M_MINI),
+	EFIFB_DMI_SYSTEM_ID("Apple Inc.", "Macmini3,1", M_MINI_3_1),
+	EFIFB_DMI_SYSTEM_ID("Apple Inc.", "Macmini4,1", M_MINI_4_1),
+	EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "MacBook1,1", M_MB),
+	/* At least one of these two will be right; maybe both? */
+	EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "MacBook2,1", M_MB),
+	EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBook2,1", M_MB),
+	/* At least one of these two will be right; maybe both? */
+	EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "MacBook3,1", M_MB),
+	EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBook3,1", M_MB),
+	EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBook4,1", M_MB),
+	EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBook5,1", M_MB_5_1),
+	EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBook6,1", M_MB_6_1),
+	EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBook7,1", M_MB_7_1),
+	EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookAir1,1", M_MBA),
+	EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookAir3,1", M_MBA_3),
+	EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "MacBookPro1,1", M_MBP),
+	EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "MacBookPro2,1", M_MBP_2),
+	EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "MacBookPro2,2", M_MBP_2_2),
+	EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookPro2,1", M_MBP_2),
+	EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "MacBookPro3,1", M_MBP_SR),
+	EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookPro3,1", M_MBP_SR),
+	EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookPro4,1", M_MBP_4),
+	EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookPro5,1", M_MBP_5_1),
+	EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookPro5,2", M_MBP_5_2),
+	EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookPro5,3", M_MBP_5_3),
+	EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookPro6,1", M_MBP_6_1),
+	EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookPro6,2", M_MBP_6_2),
+	EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookPro7,1", M_MBP_7_1),
+	EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookPro8,2", M_MBP_8_2),
+	{},
+};
+
+__init void sysfb_apply_efi_quirks(void)
+{
+	if (screen_info.orig_video_isVGA != VIDEO_TYPE_EFI ||
+	    !(screen_info.capabilities & VIDEO_CAPABILITY_SKIP_QUIRKS))
+		dmi_check_system(efifb_dmi_system_table);
+}
diff --git a/arch/x86/kernel/sysfb_simplefb.c b/arch/x86/kernel/sysfb_simplefb.c
new file mode 100644
index 000000000000..86179d409893
--- /dev/null
+++ b/arch/x86/kernel/sysfb_simplefb.c
@@ -0,0 +1,95 @@
+/*
+ * Generic System Framebuffers on x86
+ * Copyright (c) 2012-2013 David Herrmann <dh.herrmann@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ */
+
+/*
+ * simple-framebuffer probing
+ * Try to convert "screen_info" into a "simple-framebuffer" compatible mode.
+ * If the mode is incompatible, we return "false" and let the caller create
+ * legacy nodes instead.
+ */
+
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/platform_data/simplefb.h>
+#include <linux/platform_device.h>
+#include <linux/screen_info.h>
+#include <asm/sysfb.h>
+
+static const char simplefb_resname[] = "BOOTFB";
+static const struct simplefb_format formats[] = SIMPLEFB_FORMATS;
+
+/* try parsing x86 screen_info into a simple-framebuffer mode struct */
+__init bool parse_mode(const struct screen_info *si,
+		       struct simplefb_platform_data *mode)
+{
+	const struct simplefb_format *f;
+	__u8 type;
+	unsigned int i;
+
+	type = si->orig_video_isVGA;
+	if (type != VIDEO_TYPE_VLFB && type != VIDEO_TYPE_EFI)
+		return false;
+
+	for (i = 0; i < ARRAY_SIZE(formats); ++i) {
+		f = &formats[i];
+		if (si->lfb_depth == f->bits_per_pixel &&
+		    si->red_size == f->red.length &&
+		    si->red_pos == f->red.offset &&
+		    si->green_size == f->green.length &&
+		    si->green_pos == f->green.offset &&
+		    si->blue_size == f->blue.length &&
+		    si->blue_pos == f->blue.offset &&
+		    si->rsvd_size == f->transp.length &&
+		    si->rsvd_pos == f->transp.offset) {
+			mode->format = f->name;
+			mode->width = si->lfb_width;
+			mode->height = si->lfb_height;
+			mode->stride = si->lfb_linelength;
+			return true;
+		}
+	}
+
+	return false;
+}
+
+__init int create_simplefb(const struct screen_info *si,
+			   const struct simplefb_platform_data *mode)
+{
+	struct platform_device *pd;
+	struct resource res;
+	unsigned long len;
+
+	/* don't use lfb_size as it may contain the whole VMEM instead of only
+	 * the part that is occupied by the framebuffer */
+	len = mode->height * mode->stride;
+	len = PAGE_ALIGN(len);
+	if (len > (u64)si->lfb_size << 16) {
+		printk(KERN_WARNING "sysfb: VRAM smaller than advertised\n");
+		return -EINVAL;
+	}
+
+	/* setup IORESOURCE_MEM as framebuffer memory */
+	memset(&res, 0, sizeof(res));
+	res.flags = IORESOURCE_MEM | IORESOURCE_BUSY;
+	res.name = simplefb_resname;
+	res.start = si->lfb_base;
+	res.end = si->lfb_base + len - 1;
+	if (res.end <= res.start)
+		return -EINVAL;
+
+	pd = platform_device_register_resndata(NULL, "simple-framebuffer", 0,
+					       &res, 1, mode, sizeof(*mode));
+	if (IS_ERR(pd))
+		return PTR_ERR(pd);
+
+	return 0;
+}
diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c
index addf7b58f4e8..91a4496db434 100644
--- a/arch/x86/kernel/tboot.c
+++ b/arch/x86/kernel/tboot.c
@@ -301,6 +301,15 @@ static int tboot_sleep(u8 sleep_state, u32 pm1a_control, u32 pm1b_control)
 	return 0;
 }
 
+static int tboot_extended_sleep(u8 sleep_state, u32 val_a, u32 val_b)
+{
+	if (!tboot_enabled())
+		return 0;
+
+	pr_warning("tboot is not able to suspend on platforms with reduced hardware sleep (ACPIv5)");
+	return -ENODEV;
+}
+
 static atomic_t ap_wfs_count;
 
 static int tboot_wait_for_aps(int num_aps)
@@ -422,6 +431,7 @@ static __init int tboot_late_init(void)
 #endif
 
 	acpi_os_set_prepare_sleep(&tboot_sleep);
+	acpi_os_set_prepare_extended_sleep(&tboot_extended_sleep);
 	return 0;
 }
 
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 1b23a1c92746..8c8093b146ca 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -58,6 +58,7 @@
 #include <asm/mce.h>
 #include <asm/fixmap.h>
 #include <asm/mach_traps.h>
+#include <asm/alternative.h>
 
 #ifdef CONFIG_X86_64
 #include <asm/x86_init.h>
@@ -327,6 +328,9 @@ dotraplinkage void __kprobes notrace do_int3(struct pt_regs *regs, long error_co
 	    ftrace_int3_handler(regs))
 		return;
 #endif
+	if (poke_int3_handler(regs))
+		return;
+
 	prev_state = exception_enter();
 #ifdef CONFIG_KGDB_LOW_LEVEL_TRAP
 	if (kgdb_ll_trap(DIE_INT3, "int3", regs, error_code, X86_TRAP_BP,
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 6ff49247edf8..930e5d48f560 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -89,6 +89,12 @@ int check_tsc_unstable(void)
 }
 EXPORT_SYMBOL_GPL(check_tsc_unstable);
 
+int check_tsc_disabled(void)
+{
+	return tsc_disabled;
+}
+EXPORT_SYMBOL_GPL(check_tsc_disabled);
+
 #ifdef CONFIG_X86_TSC
 int __init notsc_setup(char *str)
 {
diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c
index 5f24c71accaa..8ce0072cd700 100644
--- a/arch/x86/kernel/x86_init.c
+++ b/arch/x86/kernel/x86_init.c
@@ -107,6 +107,8 @@ struct x86_platform_ops x86_platform = {
 };
 
 EXPORT_SYMBOL_GPL(x86_platform);
+
+#if defined(CONFIG_PCI_MSI)
 struct x86_msi_ops x86_msi = {
 	.setup_msi_irqs		= native_setup_msi_irqs,
 	.compose_msi_msg	= native_compose_msi_msg,
@@ -116,6 +118,28 @@ struct x86_msi_ops x86_msi = {
 	.setup_hpet_msi		= default_setup_hpet_msi,
 };
 
+/* MSI arch specific hooks */
+int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
+{
+	return x86_msi.setup_msi_irqs(dev, nvec, type);
+}
+
+void arch_teardown_msi_irqs(struct pci_dev *dev)
+{
+	x86_msi.teardown_msi_irqs(dev);
+}
+
+void arch_teardown_msi_irq(unsigned int irq)
+{
+	x86_msi.teardown_msi_irq(irq);
+}
+
+void arch_restore_msi_irqs(struct pci_dev *dev, int irq)
+{
+	x86_msi.restore_msi_irqs(dev, irq);
+}
+#endif
+
 struct x86_io_apic_ops x86_io_apic_ops = {
 	.init			= native_io_apic_init_mappings,
 	.read			= native_io_apic_read,
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index a20ecb5b6cbf..b110fe6c03d4 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -413,7 +413,8 @@ static int do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 			     (1 << KVM_FEATURE_CLOCKSOURCE2) |
 			     (1 << KVM_FEATURE_ASYNC_PF) |
 			     (1 << KVM_FEATURE_PV_EOI) |
-			     (1 << KVM_FEATURE_CLOCKSOURCE_STABLE_BIT);
+			     (1 << KVM_FEATURE_CLOCKSOURCE_STABLE_BIT) |
+			     (1 << KVM_FEATURE_PV_UNHALT);
 
 		if (sched_info_on())
 			entry->eax |= (1 << KVM_FEATURE_STEAL_TIME);
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 2bc1e81045b0..ddc3f3d2afdb 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -2025,6 +2025,17 @@ static int em_ret_far(struct x86_emulate_ctxt *ctxt)
 	return rc;
 }
 
+static int em_ret_far_imm(struct x86_emulate_ctxt *ctxt)
+{
+        int rc;
+
+        rc = em_ret_far(ctxt);
+        if (rc != X86EMUL_CONTINUE)
+                return rc;
+        rsp_increment(ctxt, ctxt->src.val);
+        return X86EMUL_CONTINUE;
+}
+
 static int em_cmpxchg(struct x86_emulate_ctxt *ctxt)
 {
 	/* Save real source value, then compare EAX against destination. */
@@ -3763,7 +3774,8 @@ static const struct opcode opcode_table[256] = {
 	G(ByteOp, group11), G(0, group11),
 	/* 0xC8 - 0xCF */
 	I(Stack | SrcImmU16 | Src2ImmByte, em_enter), I(Stack, em_leave),
-	N, I(ImplicitOps | Stack, em_ret_far),
+	I(ImplicitOps | Stack | SrcImmU16, em_ret_far_imm),
+	I(ImplicitOps | Stack, em_ret_far),
 	D(ImplicitOps), DI(SrcImmByte, intn),
 	D(ImplicitOps | No64), II(ImplicitOps, em_iret, iret),
 	/* 0xD0 - 0xD7 */
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index afc11245827c..5439117d5c4c 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -79,16 +79,6 @@ static inline void apic_set_reg(struct kvm_lapic *apic, int reg_off, u32 val)
 	*((u32 *) (apic->regs + reg_off)) = val;
 }
 
-static inline int apic_test_and_set_vector(int vec, void *bitmap)
-{
-	return test_and_set_bit(VEC_POS(vec), (bitmap) + REG_POS(vec));
-}
-
-static inline int apic_test_and_clear_vector(int vec, void *bitmap)
-{
-	return test_and_clear_bit(VEC_POS(vec), (bitmap) + REG_POS(vec));
-}
-
 static inline int apic_test_vector(int vec, void *bitmap)
 {
 	return test_bit(VEC_POS(vec), (bitmap) + REG_POS(vec));
@@ -331,10 +321,10 @@ void kvm_apic_update_irr(struct kvm_vcpu *vcpu, u32 *pir)
 }
 EXPORT_SYMBOL_GPL(kvm_apic_update_irr);
 
-static inline int apic_test_and_set_irr(int vec, struct kvm_lapic *apic)
+static inline void apic_set_irr(int vec, struct kvm_lapic *apic)
 {
 	apic->irr_pending = true;
-	return apic_test_and_set_vector(vec, apic->regs + APIC_IRR);
+	apic_set_vector(vec, apic->regs + APIC_IRR);
 }
 
 static inline int apic_search_irr(struct kvm_lapic *apic)
@@ -681,32 +671,28 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode,
 		if (unlikely(!apic_enabled(apic)))
 			break;
 
+		result = 1;
+
 		if (dest_map)
 			__set_bit(vcpu->vcpu_id, dest_map);
 
-		if (kvm_x86_ops->deliver_posted_interrupt) {
-			result = 1;
+		if (kvm_x86_ops->deliver_posted_interrupt)
 			kvm_x86_ops->deliver_posted_interrupt(vcpu, vector);
-		} else {
-			result = !apic_test_and_set_irr(vector, apic);
-
-			if (!result) {
-				if (trig_mode)
-					apic_debug("level trig mode repeatedly "
-						"for vector %d", vector);
-				goto out;
-			}
+		else {
+			apic_set_irr(vector, apic);
 
 			kvm_make_request(KVM_REQ_EVENT, vcpu);
 			kvm_vcpu_kick(vcpu);
 		}
-out:
 		trace_kvm_apic_accept_irq(vcpu->vcpu_id, delivery_mode,
-				trig_mode, vector, !result);
+					  trig_mode, vector, false);
 		break;
 
 	case APIC_DM_REMRD:
-		apic_debug("Ignoring delivery mode 3\n");
+		result = 1;
+		vcpu->arch.pv.pv_unhalted = 1;
+		kvm_make_request(KVM_REQ_EVENT, vcpu);
+		kvm_vcpu_kick(vcpu);
 		break;
 
 	case APIC_DM_SMI:
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 9e9285ae9b94..dce0df8150df 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -132,8 +132,8 @@ module_param(dbg, bool, 0644);
 	(PAGE_MASK & ~((1ULL << (PAGE_SHIFT + (((level) - 1) \
 					    * PT32_LEVEL_BITS))) - 1))
 
-#define PT64_PERM_MASK (PT_PRESENT_MASK | PT_WRITABLE_MASK | PT_USER_MASK \
-			| PT64_NX_MASK)
+#define PT64_PERM_MASK (PT_PRESENT_MASK | PT_WRITABLE_MASK | shadow_user_mask \
+			| shadow_x_mask | shadow_nx_mask)
 
 #define ACC_EXEC_MASK    1
 #define ACC_WRITE_MASK   PT_WRITABLE_MASK
@@ -331,11 +331,6 @@ static int is_large_pte(u64 pte)
 	return pte & PT_PAGE_SIZE_MASK;
 }
 
-static int is_dirty_gpte(unsigned long pte)
-{
-	return pte & PT_DIRTY_MASK;
-}
-
 static int is_rmap_spte(u64 pte)
 {
 	return is_shadow_present_pte(pte);
@@ -2052,12 +2047,18 @@ static void shadow_walk_next(struct kvm_shadow_walk_iterator *iterator)
 	return __shadow_walk_next(iterator, *iterator->sptep);
 }
 
-static void link_shadow_page(u64 *sptep, struct kvm_mmu_page *sp)
+static void link_shadow_page(u64 *sptep, struct kvm_mmu_page *sp, bool accessed)
 {
 	u64 spte;
 
+	BUILD_BUG_ON(VMX_EPT_READABLE_MASK != PT_PRESENT_MASK ||
+			VMX_EPT_WRITABLE_MASK != PT_WRITABLE_MASK);
+
 	spte = __pa(sp->spt) | PT_PRESENT_MASK | PT_WRITABLE_MASK |
-	       shadow_user_mask | shadow_x_mask | shadow_accessed_mask;
+	       shadow_user_mask | shadow_x_mask;
+
+	if (accessed)
+		spte |= shadow_accessed_mask;
 
 	mmu_spte_set(sptep, spte);
 }
@@ -2574,14 +2575,6 @@ static void nonpaging_new_cr3(struct kvm_vcpu *vcpu)
 	mmu_free_roots(vcpu);
 }
 
-static bool is_rsvd_bits_set(struct kvm_mmu *mmu, u64 gpte, int level)
-{
-	int bit7;
-
-	bit7 = (gpte >> 7) & 1;
-	return (gpte & mmu->rsvd_bits_mask[bit7][level-1]) != 0;
-}
-
 static pfn_t pte_prefetch_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn,
 				     bool no_dirty_log)
 {
@@ -2594,26 +2587,6 @@ static pfn_t pte_prefetch_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn,
 	return gfn_to_pfn_memslot_atomic(slot, gfn);
 }
 
-static bool prefetch_invalid_gpte(struct kvm_vcpu *vcpu,
-				  struct kvm_mmu_page *sp, u64 *spte,
-				  u64 gpte)
-{
-	if (is_rsvd_bits_set(&vcpu->arch.mmu, gpte, PT_PAGE_TABLE_LEVEL))
-		goto no_present;
-
-	if (!is_present_gpte(gpte))
-		goto no_present;
-
-	if (!(gpte & PT_ACCESSED_MASK))
-		goto no_present;
-
-	return false;
-
-no_present:
-	drop_spte(vcpu->kvm, spte);
-	return true;
-}
-
 static int direct_pte_prefetch_many(struct kvm_vcpu *vcpu,
 				    struct kvm_mmu_page *sp,
 				    u64 *start, u64 *end)
@@ -2710,7 +2683,7 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write,
 					      iterator.level - 1,
 					      1, ACC_ALL, iterator.sptep);
 
-			link_shadow_page(iterator.sptep, sp);
+			link_shadow_page(iterator.sptep, sp, true);
 		}
 	}
 	return emulate;
@@ -2808,7 +2781,7 @@ exit:
 	return ret;
 }
 
-static bool page_fault_can_be_fast(struct kvm_vcpu *vcpu, u32 error_code)
+static bool page_fault_can_be_fast(u32 error_code)
 {
 	/*
 	 * Do not fix the mmio spte with invalid generation number which
@@ -2861,7 +2834,7 @@ static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level,
 	bool ret = false;
 	u64 spte = 0ull;
 
-	if (!page_fault_can_be_fast(vcpu, error_code))
+	if (!page_fault_can_be_fast(error_code))
 		return false;
 
 	walk_shadow_page_lockless_begin(vcpu);
@@ -3209,6 +3182,7 @@ void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu)
 	mmu_sync_roots(vcpu);
 	spin_unlock(&vcpu->kvm->mmu_lock);
 }
+EXPORT_SYMBOL_GPL(kvm_mmu_sync_roots);
 
 static gpa_t nonpaging_gva_to_gpa(struct kvm_vcpu *vcpu, gva_t vaddr,
 				  u32 access, struct x86_exception *exception)
@@ -3478,6 +3452,7 @@ void kvm_mmu_flush_tlb(struct kvm_vcpu *vcpu)
 	++vcpu->stat.tlb_flush;
 	kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
 }
+EXPORT_SYMBOL_GPL(kvm_mmu_flush_tlb);
 
 static void paging_new_cr3(struct kvm_vcpu *vcpu)
 {
@@ -3501,18 +3476,6 @@ static void paging_free(struct kvm_vcpu *vcpu)
 	nonpaging_free(vcpu);
 }
 
-static inline void protect_clean_gpte(unsigned *access, unsigned gpte)
-{
-	unsigned mask;
-
-	BUILD_BUG_ON(PT_WRITABLE_MASK != ACC_WRITE_MASK);
-
-	mask = (unsigned)~ACC_WRITE_MASK;
-	/* Allow write access to dirty gptes */
-	mask |= (gpte >> (PT_DIRTY_SHIFT - PT_WRITABLE_SHIFT)) & PT_WRITABLE_MASK;
-	*access &= mask;
-}
-
 static bool sync_mmio_spte(struct kvm *kvm, u64 *sptep, gfn_t gfn,
 			   unsigned access, int *nr_present)
 {
@@ -3530,16 +3493,6 @@ static bool sync_mmio_spte(struct kvm *kvm, u64 *sptep, gfn_t gfn,
 	return false;
 }
 
-static inline unsigned gpte_access(struct kvm_vcpu *vcpu, u64 gpte)
-{
-	unsigned access;
-
-	access = (gpte & (PT_WRITABLE_MASK | PT_USER_MASK)) | ACC_EXEC_MASK;
-	access &= ~(gpte >> PT64_NX_SHIFT);
-
-	return access;
-}
-
 static inline bool is_last_gpte(struct kvm_mmu *mmu, unsigned level, unsigned gpte)
 {
 	unsigned index;
@@ -3549,6 +3502,11 @@ static inline bool is_last_gpte(struct kvm_mmu *mmu, unsigned level, unsigned gp
 	return mmu->last_pte_bitmap & (1 << index);
 }
 
+#define PTTYPE_EPT 18 /* arbitrary */
+#define PTTYPE PTTYPE_EPT
+#include "paging_tmpl.h"
+#undef PTTYPE
+
 #define PTTYPE 64
 #include "paging_tmpl.h"
 #undef PTTYPE
@@ -3563,6 +3521,8 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu,
 	int maxphyaddr = cpuid_maxphyaddr(vcpu);
 	u64 exb_bit_rsvd = 0;
 
+	context->bad_mt_xwr = 0;
+
 	if (!context->nx)
 		exb_bit_rsvd = rsvd_bits(63, 63);
 	switch (context->root_level) {
@@ -3618,7 +3578,40 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu,
 	}
 }
 
-static void update_permission_bitmask(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu)
+static void reset_rsvds_bits_mask_ept(struct kvm_vcpu *vcpu,
+		struct kvm_mmu *context, bool execonly)
+{
+	int maxphyaddr = cpuid_maxphyaddr(vcpu);
+	int pte;
+
+	context->rsvd_bits_mask[0][3] =
+		rsvd_bits(maxphyaddr, 51) | rsvd_bits(3, 7);
+	context->rsvd_bits_mask[0][2] =
+		rsvd_bits(maxphyaddr, 51) | rsvd_bits(3, 6);
+	context->rsvd_bits_mask[0][1] =
+		rsvd_bits(maxphyaddr, 51) | rsvd_bits(3, 6);
+	context->rsvd_bits_mask[0][0] = rsvd_bits(maxphyaddr, 51);
+
+	/* large page */
+	context->rsvd_bits_mask[1][3] = context->rsvd_bits_mask[0][3];
+	context->rsvd_bits_mask[1][2] =
+		rsvd_bits(maxphyaddr, 51) | rsvd_bits(12, 29);
+	context->rsvd_bits_mask[1][1] =
+		rsvd_bits(maxphyaddr, 51) | rsvd_bits(12, 20);
+	context->rsvd_bits_mask[1][0] = context->rsvd_bits_mask[0][0];
+
+	for (pte = 0; pte < 64; pte++) {
+		int rwx_bits = pte & 7;
+		int mt = pte >> 3;
+		if (mt == 0x2 || mt == 0x3 || mt == 0x7 ||
+				rwx_bits == 0x2 || rwx_bits == 0x6 ||
+				(rwx_bits == 0x4 && !execonly))
+			context->bad_mt_xwr |= (1ull << pte);
+	}
+}
+
+static void update_permission_bitmask(struct kvm_vcpu *vcpu,
+		struct kvm_mmu *mmu, bool ept)
 {
 	unsigned bit, byte, pfec;
 	u8 map;
@@ -3636,12 +3629,16 @@ static void update_permission_bitmask(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu
 			w = bit & ACC_WRITE_MASK;
 			u = bit & ACC_USER_MASK;
 
-			/* Not really needed: !nx will cause pte.nx to fault */
-			x |= !mmu->nx;
-			/* Allow supervisor writes if !cr0.wp */
-			w |= !is_write_protection(vcpu) && !uf;
-			/* Disallow supervisor fetches of user code if cr4.smep */
-			x &= !(smep && u && !uf);
+			if (!ept) {
+				/* Not really needed: !nx will cause pte.nx to fault */
+				x |= !mmu->nx;
+				/* Allow supervisor writes if !cr0.wp */
+				w |= !is_write_protection(vcpu) && !uf;
+				/* Disallow supervisor fetches of user code if cr4.smep */
+				x &= !(smep && u && !uf);
+			} else
+				/* Not really needed: no U/S accesses on ept  */
+				u = 1;
 
 			fault = (ff && !x) || (uf && !u) || (wf && !w);
 			map |= fault << bit;
@@ -3676,7 +3673,7 @@ static int paging64_init_context_common(struct kvm_vcpu *vcpu,
 	context->root_level = level;
 
 	reset_rsvds_bits_mask(vcpu, context);
-	update_permission_bitmask(vcpu, context);
+	update_permission_bitmask(vcpu, context, false);
 	update_last_pte_bitmap(vcpu, context);
 
 	ASSERT(is_pae(vcpu));
@@ -3706,7 +3703,7 @@ static int paging32_init_context(struct kvm_vcpu *vcpu,
 	context->root_level = PT32_ROOT_LEVEL;
 
 	reset_rsvds_bits_mask(vcpu, context);
-	update_permission_bitmask(vcpu, context);
+	update_permission_bitmask(vcpu, context, false);
 	update_last_pte_bitmap(vcpu, context);
 
 	context->new_cr3 = paging_new_cr3;
@@ -3768,7 +3765,7 @@ static int init_kvm_tdp_mmu(struct kvm_vcpu *vcpu)
 		context->gva_to_gpa = paging32_gva_to_gpa;
 	}
 
-	update_permission_bitmask(vcpu, context);
+	update_permission_bitmask(vcpu, context, false);
 	update_last_pte_bitmap(vcpu, context);
 
 	return 0;
@@ -3800,6 +3797,33 @@ int kvm_init_shadow_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *context)
 }
 EXPORT_SYMBOL_GPL(kvm_init_shadow_mmu);
 
+int kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *context,
+		bool execonly)
+{
+	ASSERT(vcpu);
+	ASSERT(!VALID_PAGE(vcpu->arch.mmu.root_hpa));
+
+	context->shadow_root_level = kvm_x86_ops->get_tdp_level();
+
+	context->nx = true;
+	context->new_cr3 = paging_new_cr3;
+	context->page_fault = ept_page_fault;
+	context->gva_to_gpa = ept_gva_to_gpa;
+	context->sync_page = ept_sync_page;
+	context->invlpg = ept_invlpg;
+	context->update_pte = ept_update_pte;
+	context->free = paging_free;
+	context->root_level = context->shadow_root_level;
+	context->root_hpa = INVALID_PAGE;
+	context->direct_map = false;
+
+	update_permission_bitmask(vcpu, context, true);
+	reset_rsvds_bits_mask_ept(vcpu, context, execonly);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(kvm_init_shadow_ept_mmu);
+
 static int init_kvm_softmmu(struct kvm_vcpu *vcpu)
 {
 	int r = kvm_init_shadow_mmu(vcpu, vcpu->arch.walk_mmu);
@@ -3847,7 +3871,7 @@ static int init_kvm_nested_mmu(struct kvm_vcpu *vcpu)
 		g_context->gva_to_gpa = paging32_gva_to_gpa_nested;
 	}
 
-	update_permission_bitmask(vcpu, g_context);
+	update_permission_bitmask(vcpu, g_context, false);
 	update_last_pte_bitmap(vcpu, g_context);
 
 	return 0;
@@ -3923,8 +3947,8 @@ static bool need_remote_flush(u64 old, u64 new)
 		return true;
 	if ((old ^ new) & PT64_BASE_ADDR_MASK)
 		return true;
-	old ^= PT64_NX_MASK;
-	new ^= PT64_NX_MASK;
+	old ^= shadow_nx_mask;
+	new ^= shadow_nx_mask;
 	return (old & ~new & PT64_PERM_MASK) != 0;
 }
 
@@ -4182,7 +4206,7 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u32 error_code,
 	switch (er) {
 	case EMULATE_DONE:
 		return 1;
-	case EMULATE_DO_MMIO:
+	case EMULATE_USER_EXIT:
 		++vcpu->stat.mmio_exits;
 		/* fall through */
 	case EMULATE_FAIL:
@@ -4390,23 +4414,19 @@ void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm)
 	/*
 	 * The very rare case: if the generation-number is round,
 	 * zap all shadow pages.
-	 *
-	 * The max value is MMIO_MAX_GEN - 1 since it is not called
-	 * when mark memslot invalid.
 	 */
-	if (unlikely(kvm_current_mmio_generation(kvm) >= (MMIO_MAX_GEN - 1))) {
+	if (unlikely(kvm_current_mmio_generation(kvm) >= MMIO_MAX_GEN)) {
 		printk_ratelimited(KERN_INFO "kvm: zapping shadow pages for mmio generation wraparound\n");
 		kvm_mmu_invalidate_zap_all_pages(kvm);
 	}
 }
 
-static int mmu_shrink(struct shrinker *shrink, struct shrink_control *sc)
+static unsigned long
+mmu_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
 {
 	struct kvm *kvm;
 	int nr_to_scan = sc->nr_to_scan;
-
-	if (nr_to_scan == 0)
-		goto out;
+	unsigned long freed = 0;
 
 	raw_spin_lock(&kvm_lock);
 
@@ -4441,25 +4461,37 @@ static int mmu_shrink(struct shrinker *shrink, struct shrink_control *sc)
 			goto unlock;
 		}
 
-		prepare_zap_oldest_mmu_page(kvm, &invalid_list);
+		if (prepare_zap_oldest_mmu_page(kvm, &invalid_list))
+			freed++;
 		kvm_mmu_commit_zap_page(kvm, &invalid_list);
 
 unlock:
 		spin_unlock(&kvm->mmu_lock);
 		srcu_read_unlock(&kvm->srcu, idx);
 
+		/*
+		 * unfair on small ones
+		 * per-vm shrinkers cry out
+		 * sadness comes quickly
+		 */
 		list_move_tail(&kvm->vm_list, &vm_list);
 		break;
 	}
 
 	raw_spin_unlock(&kvm_lock);
+	return freed;
 
-out:
+}
+
+static unsigned long
+mmu_shrink_count(struct shrinker *shrink, struct shrink_control *sc)
+{
 	return percpu_counter_read_positive(&kvm_total_used_mmu_pages);
 }
 
 static struct shrinker mmu_shrinker = {
-	.shrink = mmu_shrink,
+	.count_objects = mmu_shrink_count,
+	.scan_objects = mmu_shrink_scan,
 	.seeks = DEFAULT_SEEKS * 10,
 };
 
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index 5b59c573aba7..77e044a0f5f7 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -71,6 +71,8 @@ enum {
 
 int handle_mmio_page_fault_common(struct kvm_vcpu *vcpu, u64 addr, bool direct);
 int kvm_init_shadow_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *context);
+int kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *context,
+		bool execonly);
 
 static inline unsigned int kvm_mmu_available_pages(struct kvm *kvm)
 {
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index 7769699d48a8..ad75d77999d0 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -23,6 +23,13 @@
  * so the code in this file is compiled twice, once per pte size.
  */
 
+/*
+ * This is used to catch non optimized PT_GUEST_(DIRTY|ACCESS)_SHIFT macro
+ * uses for EPT without A/D paging type.
+ */
+extern u64 __pure __using_nonexistent_pte_bit(void)
+	       __compiletime_error("wrong use of PT_GUEST_(DIRTY|ACCESS)_SHIFT");
+
 #if PTTYPE == 64
 	#define pt_element_t u64
 	#define guest_walker guest_walker64
@@ -32,6 +39,10 @@
 	#define PT_LVL_OFFSET_MASK(lvl) PT64_LVL_OFFSET_MASK(lvl)
 	#define PT_INDEX(addr, level) PT64_INDEX(addr, level)
 	#define PT_LEVEL_BITS PT64_LEVEL_BITS
+	#define PT_GUEST_ACCESSED_MASK PT_ACCESSED_MASK
+	#define PT_GUEST_DIRTY_MASK PT_DIRTY_MASK
+	#define PT_GUEST_DIRTY_SHIFT PT_DIRTY_SHIFT
+	#define PT_GUEST_ACCESSED_SHIFT PT_ACCESSED_SHIFT
 	#ifdef CONFIG_X86_64
 	#define PT_MAX_FULL_LEVELS 4
 	#define CMPXCHG cmpxchg
@@ -49,7 +60,26 @@
 	#define PT_INDEX(addr, level) PT32_INDEX(addr, level)
 	#define PT_LEVEL_BITS PT32_LEVEL_BITS
 	#define PT_MAX_FULL_LEVELS 2
+	#define PT_GUEST_ACCESSED_MASK PT_ACCESSED_MASK
+	#define PT_GUEST_DIRTY_MASK PT_DIRTY_MASK
+	#define PT_GUEST_DIRTY_SHIFT PT_DIRTY_SHIFT
+	#define PT_GUEST_ACCESSED_SHIFT PT_ACCESSED_SHIFT
 	#define CMPXCHG cmpxchg
+#elif PTTYPE == PTTYPE_EPT
+	#define pt_element_t u64
+	#define guest_walker guest_walkerEPT
+	#define FNAME(name) ept_##name
+	#define PT_BASE_ADDR_MASK PT64_BASE_ADDR_MASK
+	#define PT_LVL_ADDR_MASK(lvl) PT64_LVL_ADDR_MASK(lvl)
+	#define PT_LVL_OFFSET_MASK(lvl) PT64_LVL_OFFSET_MASK(lvl)
+	#define PT_INDEX(addr, level) PT64_INDEX(addr, level)
+	#define PT_LEVEL_BITS PT64_LEVEL_BITS
+	#define PT_GUEST_ACCESSED_MASK 0
+	#define PT_GUEST_DIRTY_MASK 0
+	#define PT_GUEST_DIRTY_SHIFT __using_nonexistent_pte_bit()
+	#define PT_GUEST_ACCESSED_SHIFT __using_nonexistent_pte_bit()
+	#define CMPXCHG cmpxchg64
+	#define PT_MAX_FULL_LEVELS 4
 #else
 	#error Invalid PTTYPE value
 #endif
@@ -69,6 +99,7 @@ struct guest_walker {
 	pt_element_t prefetch_ptes[PTE_PREFETCH_NUM];
 	gpa_t pte_gpa[PT_MAX_FULL_LEVELS];
 	pt_element_t __user *ptep_user[PT_MAX_FULL_LEVELS];
+	bool pte_writable[PT_MAX_FULL_LEVELS];
 	unsigned pt_access;
 	unsigned pte_access;
 	gfn_t gfn;
@@ -80,6 +111,40 @@ static gfn_t gpte_to_gfn_lvl(pt_element_t gpte, int lvl)
 	return (gpte & PT_LVL_ADDR_MASK(lvl)) >> PAGE_SHIFT;
 }
 
+static inline void FNAME(protect_clean_gpte)(unsigned *access, unsigned gpte)
+{
+	unsigned mask;
+
+	/* dirty bit is not supported, so no need to track it */
+	if (!PT_GUEST_DIRTY_MASK)
+		return;
+
+	BUILD_BUG_ON(PT_WRITABLE_MASK != ACC_WRITE_MASK);
+
+	mask = (unsigned)~ACC_WRITE_MASK;
+	/* Allow write access to dirty gptes */
+	mask |= (gpte >> (PT_GUEST_DIRTY_SHIFT - PT_WRITABLE_SHIFT)) &
+		PT_WRITABLE_MASK;
+	*access &= mask;
+}
+
+static bool FNAME(is_rsvd_bits_set)(struct kvm_mmu *mmu, u64 gpte, int level)
+{
+	int bit7 = (gpte >> 7) & 1, low6 = gpte & 0x3f;
+
+	return (gpte & mmu->rsvd_bits_mask[bit7][level-1]) |
+		((mmu->bad_mt_xwr & (1ull << low6)) != 0);
+}
+
+static inline int FNAME(is_present_gpte)(unsigned long pte)
+{
+#if PTTYPE != PTTYPE_EPT
+	return is_present_gpte(pte);
+#else
+	return pte & 7;
+#endif
+}
+
 static int FNAME(cmpxchg_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
 			       pt_element_t __user *ptep_user, unsigned index,
 			       pt_element_t orig_pte, pt_element_t new_pte)
@@ -103,6 +168,42 @@ static int FNAME(cmpxchg_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
 	return (ret != orig_pte);
 }
 
+static bool FNAME(prefetch_invalid_gpte)(struct kvm_vcpu *vcpu,
+				  struct kvm_mmu_page *sp, u64 *spte,
+				  u64 gpte)
+{
+	if (FNAME(is_rsvd_bits_set)(&vcpu->arch.mmu, gpte, PT_PAGE_TABLE_LEVEL))
+		goto no_present;
+
+	if (!FNAME(is_present_gpte)(gpte))
+		goto no_present;
+
+	/* if accessed bit is not supported prefetch non accessed gpte */
+	if (PT_GUEST_ACCESSED_MASK && !(gpte & PT_GUEST_ACCESSED_MASK))
+		goto no_present;
+
+	return false;
+
+no_present:
+	drop_spte(vcpu->kvm, spte);
+	return true;
+}
+
+static inline unsigned FNAME(gpte_access)(struct kvm_vcpu *vcpu, u64 gpte)
+{
+	unsigned access;
+#if PTTYPE == PTTYPE_EPT
+	access = ((gpte & VMX_EPT_WRITABLE_MASK) ? ACC_WRITE_MASK : 0) |
+		((gpte & VMX_EPT_EXECUTABLE_MASK) ? ACC_EXEC_MASK : 0) |
+		ACC_USER_MASK;
+#else
+	access = (gpte & (PT_WRITABLE_MASK | PT_USER_MASK)) | ACC_EXEC_MASK;
+	access &= ~(gpte >> PT64_NX_SHIFT);
+#endif
+
+	return access;
+}
+
 static int FNAME(update_accessed_dirty_bits)(struct kvm_vcpu *vcpu,
 					     struct kvm_mmu *mmu,
 					     struct guest_walker *walker,
@@ -114,22 +215,43 @@ static int FNAME(update_accessed_dirty_bits)(struct kvm_vcpu *vcpu,
 	gfn_t table_gfn;
 	int ret;
 
+	/* dirty/accessed bits are not supported, so no need to update them */
+	if (!PT_GUEST_DIRTY_MASK)
+		return 0;
+
 	for (level = walker->max_level; level >= walker->level; --level) {
 		pte = orig_pte = walker->ptes[level - 1];
 		table_gfn = walker->table_gfn[level - 1];
 		ptep_user = walker->ptep_user[level - 1];
 		index = offset_in_page(ptep_user) / sizeof(pt_element_t);
-		if (!(pte & PT_ACCESSED_MASK)) {
+		if (!(pte & PT_GUEST_ACCESSED_MASK)) {
 			trace_kvm_mmu_set_accessed_bit(table_gfn, index, sizeof(pte));
-			pte |= PT_ACCESSED_MASK;
+			pte |= PT_GUEST_ACCESSED_MASK;
 		}
-		if (level == walker->level && write_fault && !is_dirty_gpte(pte)) {
+		if (level == walker->level && write_fault &&
+				!(pte & PT_GUEST_DIRTY_MASK)) {
 			trace_kvm_mmu_set_dirty_bit(table_gfn, index, sizeof(pte));
-			pte |= PT_DIRTY_MASK;
+			pte |= PT_GUEST_DIRTY_MASK;
 		}
 		if (pte == orig_pte)
 			continue;
 
+		/*
+		 * If the slot is read-only, simply do not process the accessed
+		 * and dirty bits.  This is the correct thing to do if the slot
+		 * is ROM, and page tables in read-as-ROM/write-as-MMIO slots
+		 * are only supported if the accessed and dirty bits are already
+		 * set in the ROM (so that MMIO writes are never needed).
+		 *
+		 * Note that NPT does not allow this at all and faults, since
+		 * it always wants nested page table entries for the guest
+		 * page tables to be writable.  And EPT works but will simply
+		 * overwrite the read-only memory to set the accessed and dirty
+		 * bits.
+		 */
+		if (unlikely(!walker->pte_writable[level - 1]))
+			continue;
+
 		ret = FNAME(cmpxchg_gpte)(vcpu, mmu, ptep_user, index, orig_pte, pte);
 		if (ret)
 			return ret;
@@ -170,7 +292,7 @@ retry_walk:
 	if (walker->level == PT32E_ROOT_LEVEL) {
 		pte = mmu->get_pdptr(vcpu, (addr >> 30) & 3);
 		trace_kvm_mmu_paging_element(pte, walker->level);
-		if (!is_present_gpte(pte))
+		if (!FNAME(is_present_gpte)(pte))
 			goto error;
 		--walker->level;
 	}
@@ -179,7 +301,7 @@ retry_walk:
 	ASSERT((!is_long_mode(vcpu) && is_pae(vcpu)) ||
 	       (mmu->get_cr3(vcpu) & CR3_NONPAE_RESERVED_BITS) == 0);
 
-	accessed_dirty = PT_ACCESSED_MASK;
+	accessed_dirty = PT_GUEST_ACCESSED_MASK;
 	pt_access = pte_access = ACC_ALL;
 	++walker->level;
 
@@ -204,7 +326,8 @@ retry_walk:
 			goto error;
 		real_gfn = gpa_to_gfn(real_gfn);
 
-		host_addr = gfn_to_hva(vcpu->kvm, real_gfn);
+		host_addr = gfn_to_hva_prot(vcpu->kvm, real_gfn,
+					    &walker->pte_writable[walker->level - 1]);
 		if (unlikely(kvm_is_error_hva(host_addr)))
 			goto error;
 
@@ -215,17 +338,17 @@ retry_walk:
 
 		trace_kvm_mmu_paging_element(pte, walker->level);
 
-		if (unlikely(!is_present_gpte(pte)))
+		if (unlikely(!FNAME(is_present_gpte)(pte)))
 			goto error;
 
-		if (unlikely(is_rsvd_bits_set(&vcpu->arch.mmu, pte,
-					      walker->level))) {
+		if (unlikely(FNAME(is_rsvd_bits_set)(mmu, pte,
+					             walker->level))) {
 			errcode |= PFERR_RSVD_MASK | PFERR_PRESENT_MASK;
 			goto error;
 		}
 
 		accessed_dirty &= pte;
-		pte_access = pt_access & gpte_access(vcpu, pte);
+		pte_access = pt_access & FNAME(gpte_access)(vcpu, pte);
 
 		walker->ptes[walker->level - 1] = pte;
 	} while (!is_last_gpte(mmu, walker->level, pte));
@@ -248,13 +371,15 @@ retry_walk:
 	walker->gfn = real_gpa >> PAGE_SHIFT;
 
 	if (!write_fault)
-		protect_clean_gpte(&pte_access, pte);
+		FNAME(protect_clean_gpte)(&pte_access, pte);
 	else
 		/*
-		 * On a write fault, fold the dirty bit into accessed_dirty by
-		 * shifting it one place right.
+		 * On a write fault, fold the dirty bit into accessed_dirty.
+		 * For modes without A/D bits support accessed_dirty will be
+		 * always clear.
 		 */
-		accessed_dirty &= pte >> (PT_DIRTY_SHIFT - PT_ACCESSED_SHIFT);
+		accessed_dirty &= pte >>
+			(PT_GUEST_DIRTY_SHIFT - PT_GUEST_ACCESSED_SHIFT);
 
 	if (unlikely(!accessed_dirty)) {
 		ret = FNAME(update_accessed_dirty_bits)(vcpu, mmu, walker, write_fault);
@@ -279,6 +404,25 @@ error:
 	walker->fault.vector = PF_VECTOR;
 	walker->fault.error_code_valid = true;
 	walker->fault.error_code = errcode;
+
+#if PTTYPE == PTTYPE_EPT
+	/*
+	 * Use PFERR_RSVD_MASK in error_code to to tell if EPT
+	 * misconfiguration requires to be injected. The detection is
+	 * done by is_rsvd_bits_set() above.
+	 *
+	 * We set up the value of exit_qualification to inject:
+	 * [2:0] - Derive from [2:0] of real exit_qualification at EPT violation
+	 * [5:3] - Calculated by the page walk of the guest EPT page tables
+	 * [7:8] - Derived from [7:8] of real exit_qualification
+	 *
+	 * The other bits are set to 0.
+	 */
+	if (!(errcode & PFERR_RSVD_MASK)) {
+		vcpu->arch.exit_qualification &= 0x187;
+		vcpu->arch.exit_qualification |= ((pt_access & pte) & 0x7) << 3;
+	}
+#endif
 	walker->fault.address = addr;
 	walker->fault.nested_page_fault = mmu != vcpu->arch.walk_mmu;
 
@@ -293,6 +437,7 @@ static int FNAME(walk_addr)(struct guest_walker *walker,
 					access);
 }
 
+#if PTTYPE != PTTYPE_EPT
 static int FNAME(walk_addr_nested)(struct guest_walker *walker,
 				   struct kvm_vcpu *vcpu, gva_t addr,
 				   u32 access)
@@ -300,6 +445,7 @@ static int FNAME(walk_addr_nested)(struct guest_walker *walker,
 	return FNAME(walk_addr_generic)(walker, vcpu, &vcpu->arch.nested_mmu,
 					addr, access);
 }
+#endif
 
 static bool
 FNAME(prefetch_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
@@ -309,14 +455,14 @@ FNAME(prefetch_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
 	gfn_t gfn;
 	pfn_t pfn;
 
-	if (prefetch_invalid_gpte(vcpu, sp, spte, gpte))
+	if (FNAME(prefetch_invalid_gpte)(vcpu, sp, spte, gpte))
 		return false;
 
 	pgprintk("%s: gpte %llx spte %p\n", __func__, (u64)gpte, spte);
 
 	gfn = gpte_to_gfn(gpte);
-	pte_access = sp->role.access & gpte_access(vcpu, gpte);
-	protect_clean_gpte(&pte_access, gpte);
+	pte_access = sp->role.access & FNAME(gpte_access)(vcpu, gpte);
+	FNAME(protect_clean_gpte)(&pte_access, gpte);
 	pfn = pte_prefetch_gfn_to_pfn(vcpu, gfn,
 			no_dirty_log && (pte_access & ACC_WRITE_MASK));
 	if (is_error_pfn(pfn))
@@ -446,7 +592,7 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
 			goto out_gpte_changed;
 
 		if (sp)
-			link_shadow_page(it.sptep, sp);
+			link_shadow_page(it.sptep, sp, PT_GUEST_ACCESSED_MASK);
 	}
 
 	for (;
@@ -466,7 +612,7 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
 
 		sp = kvm_mmu_get_page(vcpu, direct_gfn, addr, it.level-1,
 				      true, direct_access, it.sptep);
-		link_shadow_page(it.sptep, sp);
+		link_shadow_page(it.sptep, sp, PT_GUEST_ACCESSED_MASK);
 	}
 
 	clear_sp_write_flooding_count(it.sptep);
@@ -727,6 +873,7 @@ static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t vaddr, u32 access,
 	return gpa;
 }
 
+#if PTTYPE != PTTYPE_EPT
 static gpa_t FNAME(gva_to_gpa_nested)(struct kvm_vcpu *vcpu, gva_t vaddr,
 				      u32 access,
 				      struct x86_exception *exception)
@@ -745,6 +892,7 @@ static gpa_t FNAME(gva_to_gpa_nested)(struct kvm_vcpu *vcpu, gva_t vaddr,
 
 	return gpa;
 }
+#endif
 
 /*
  * Using the cached information from sp->gfns is safe because:
@@ -785,15 +933,15 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
 					  sizeof(pt_element_t)))
 			return -EINVAL;
 
-		if (prefetch_invalid_gpte(vcpu, sp, &sp->spt[i], gpte)) {
+		if (FNAME(prefetch_invalid_gpte)(vcpu, sp, &sp->spt[i], gpte)) {
 			vcpu->kvm->tlbs_dirty++;
 			continue;
 		}
 
 		gfn = gpte_to_gfn(gpte);
 		pte_access = sp->role.access;
-		pte_access &= gpte_access(vcpu, gpte);
-		protect_clean_gpte(&pte_access, gpte);
+		pte_access &= FNAME(gpte_access)(vcpu, gpte);
+		FNAME(protect_clean_gpte)(&pte_access, gpte);
 
 		if (sync_mmio_spte(vcpu->kvm, &sp->spt[i], gfn, pte_access,
 		      &nr_present))
@@ -830,3 +978,7 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
 #undef gpte_to_gfn
 #undef gpte_to_gfn_lvl
 #undef CMPXCHG
+#undef PT_GUEST_ACCESSED_MASK
+#undef PT_GUEST_DIRTY_MASK
+#undef PT_GUEST_DIRTY_SHIFT
+#undef PT_GUEST_ACCESSED_SHIFT
diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index c53e797e7369..5c4f63151b4d 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -160,7 +160,7 @@ static void stop_counter(struct kvm_pmc *pmc)
 
 static void reprogram_counter(struct kvm_pmc *pmc, u32 type,
 		unsigned config, bool exclude_user, bool exclude_kernel,
-		bool intr)
+		bool intr, bool in_tx, bool in_tx_cp)
 {
 	struct perf_event *event;
 	struct perf_event_attr attr = {
@@ -173,6 +173,10 @@ static void reprogram_counter(struct kvm_pmc *pmc, u32 type,
 		.exclude_kernel = exclude_kernel,
 		.config = config,
 	};
+	if (in_tx)
+		attr.config |= HSW_IN_TX;
+	if (in_tx_cp)
+		attr.config |= HSW_IN_TX_CHECKPOINTED;
 
 	attr.sample_period = (-pmc->counter) & pmc_bitmask(pmc);
 
@@ -226,7 +230,9 @@ static void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel)
 
 	if (!(eventsel & (ARCH_PERFMON_EVENTSEL_EDGE |
 				ARCH_PERFMON_EVENTSEL_INV |
-				ARCH_PERFMON_EVENTSEL_CMASK))) {
+				ARCH_PERFMON_EVENTSEL_CMASK |
+				HSW_IN_TX |
+				HSW_IN_TX_CHECKPOINTED))) {
 		config = find_arch_event(&pmc->vcpu->arch.pmu, event_select,
 				unit_mask);
 		if (config != PERF_COUNT_HW_MAX)
@@ -239,7 +245,9 @@ static void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel)
 	reprogram_counter(pmc, type, config,
 			!(eventsel & ARCH_PERFMON_EVENTSEL_USR),
 			!(eventsel & ARCH_PERFMON_EVENTSEL_OS),
-			eventsel & ARCH_PERFMON_EVENTSEL_INT);
+			eventsel & ARCH_PERFMON_EVENTSEL_INT,
+			(eventsel & HSW_IN_TX),
+			(eventsel & HSW_IN_TX_CHECKPOINTED));
 }
 
 static void reprogram_fixed_counter(struct kvm_pmc *pmc, u8 en_pmi, int idx)
@@ -256,7 +264,7 @@ static void reprogram_fixed_counter(struct kvm_pmc *pmc, u8 en_pmi, int idx)
 			arch_events[fixed_pmc_events[idx]].event_type,
 			!(en & 0x2), /* exclude user */
 			!(en & 0x1), /* exclude kernel */
-			pmi);
+			pmi, false, false);
 }
 
 static inline u8 fixed_en_pmi(u64 ctrl, int idx)
@@ -408,7 +416,7 @@ int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		} else if ((pmc = get_gp_pmc(pmu, index, MSR_P6_EVNTSEL0))) {
 			if (data == pmc->eventsel)
 				return 0;
-			if (!(data & 0xffffffff00200000ull)) {
+			if (!(data & pmu->reserved_bits)) {
 				reprogram_gp_counter(pmc, data);
 				return 0;
 			}
@@ -450,6 +458,7 @@ void kvm_pmu_cpuid_update(struct kvm_vcpu *vcpu)
 	pmu->counter_bitmask[KVM_PMC_GP] = 0;
 	pmu->counter_bitmask[KVM_PMC_FIXED] = 0;
 	pmu->version = 0;
+	pmu->reserved_bits = 0xffffffff00200000ull;
 
 	entry = kvm_find_cpuid_entry(vcpu, 0xa, 0);
 	if (!entry)
@@ -478,6 +487,12 @@ void kvm_pmu_cpuid_update(struct kvm_vcpu *vcpu)
 	pmu->global_ctrl = ((1 << pmu->nr_arch_gp_counters) - 1) |
 		(((1ull << pmu->nr_arch_fixed_counters) - 1) << INTEL_PMC_IDX_FIXED);
 	pmu->global_ctrl_mask = ~pmu->global_ctrl;
+
+	entry = kvm_find_cpuid_entry(vcpu, 7, 0);
+	if (entry &&
+	    (boot_cpu_has(X86_FEATURE_HLE) || boot_cpu_has(X86_FEATURE_RTM)) &&
+	    (entry->ebx & (X86_FEATURE_HLE|X86_FEATURE_RTM)))
+		pmu->reserved_bits ^= HSW_IN_TX|HSW_IN_TX_CHECKPOINTED;
 }
 
 void kvm_pmu_init(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 064d0be67ecc..2b2fce1b2009 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -373,6 +373,7 @@ struct nested_vmx {
 	 * we must keep them pinned while L2 runs.
 	 */
 	struct page *apic_access_page;
+	u64 msr_ia32_feature_control;
 };
 
 #define POSTED_INTR_ON  0
@@ -711,10 +712,10 @@ static void nested_release_page_clean(struct page *page)
 	kvm_release_page_clean(page);
 }
 
+static unsigned long nested_ept_get_cr3(struct kvm_vcpu *vcpu);
 static u64 construct_eptp(unsigned long root_hpa);
 static void kvm_cpu_vmxon(u64 addr);
 static void kvm_cpu_vmxoff(void);
-static void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3);
 static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr);
 static void vmx_set_segment(struct kvm_vcpu *vcpu,
 			    struct kvm_segment *var, int seg);
@@ -1039,12 +1040,16 @@ static inline bool nested_cpu_has2(struct vmcs12 *vmcs12, u32 bit)
 		(vmcs12->secondary_vm_exec_control & bit);
 }
 
-static inline bool nested_cpu_has_virtual_nmis(struct vmcs12 *vmcs12,
-	struct kvm_vcpu *vcpu)
+static inline bool nested_cpu_has_virtual_nmis(struct vmcs12 *vmcs12)
 {
 	return vmcs12->pin_based_vm_exec_control & PIN_BASED_VIRTUAL_NMIS;
 }
 
+static inline int nested_cpu_has_ept(struct vmcs12 *vmcs12)
+{
+	return nested_cpu_has2(vmcs12, SECONDARY_EXEC_ENABLE_EPT);
+}
+
 static inline bool is_exception(u32 intr_info)
 {
 	return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VALID_MASK))
@@ -2155,6 +2160,7 @@ static u32 nested_vmx_pinbased_ctls_low, nested_vmx_pinbased_ctls_high;
 static u32 nested_vmx_exit_ctls_low, nested_vmx_exit_ctls_high;
 static u32 nested_vmx_entry_ctls_low, nested_vmx_entry_ctls_high;
 static u32 nested_vmx_misc_low, nested_vmx_misc_high;
+static u32 nested_vmx_ept_caps;
 static __init void nested_vmx_setup_ctls_msrs(void)
 {
 	/*
@@ -2190,14 +2196,17 @@ static __init void nested_vmx_setup_ctls_msrs(void)
 	 * If bit 55 of VMX_BASIC is off, bits 0-8 and 10, 11, 13, 14, 16 and
 	 * 17 must be 1.
 	 */
+	rdmsr(MSR_IA32_VMX_EXIT_CTLS,
+		nested_vmx_exit_ctls_low, nested_vmx_exit_ctls_high);
 	nested_vmx_exit_ctls_low = VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR;
 	/* Note that guest use of VM_EXIT_ACK_INTR_ON_EXIT is not supported. */
+	nested_vmx_exit_ctls_high &=
 #ifdef CONFIG_X86_64
-	nested_vmx_exit_ctls_high = VM_EXIT_HOST_ADDR_SPACE_SIZE;
-#else
-	nested_vmx_exit_ctls_high = 0;
+		VM_EXIT_HOST_ADDR_SPACE_SIZE |
 #endif
-	nested_vmx_exit_ctls_high |= VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR;
+		VM_EXIT_LOAD_IA32_PAT | VM_EXIT_SAVE_IA32_PAT;
+	nested_vmx_exit_ctls_high |= (VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR |
+				      VM_EXIT_LOAD_IA32_EFER);
 
 	/* entry controls */
 	rdmsr(MSR_IA32_VMX_ENTRY_CTLS,
@@ -2205,8 +2214,12 @@ static __init void nested_vmx_setup_ctls_msrs(void)
 	/* If bit 55 of VMX_BASIC is off, bits 0-8 and 12 must be 1. */
 	nested_vmx_entry_ctls_low = VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR;
 	nested_vmx_entry_ctls_high &=
-		VM_ENTRY_LOAD_IA32_PAT | VM_ENTRY_IA32E_MODE;
-	nested_vmx_entry_ctls_high |= VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR;
+#ifdef CONFIG_X86_64
+		VM_ENTRY_IA32E_MODE |
+#endif
+		VM_ENTRY_LOAD_IA32_PAT;
+	nested_vmx_entry_ctls_high |= (VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR |
+				       VM_ENTRY_LOAD_IA32_EFER);
 
 	/* cpu-based controls */
 	rdmsr(MSR_IA32_VMX_PROCBASED_CTLS,
@@ -2241,6 +2254,22 @@ static __init void nested_vmx_setup_ctls_msrs(void)
 		SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES |
 		SECONDARY_EXEC_WBINVD_EXITING;
 
+	if (enable_ept) {
+		/* nested EPT: emulate EPT also to L1 */
+		nested_vmx_secondary_ctls_high |= SECONDARY_EXEC_ENABLE_EPT;
+		nested_vmx_ept_caps = VMX_EPT_PAGE_WALK_4_BIT |
+			 VMX_EPTP_WB_BIT | VMX_EPT_INVEPT_BIT;
+		nested_vmx_ept_caps &= vmx_capability.ept;
+		/*
+		 * Since invept is completely emulated we support both global
+		 * and context invalidation independent of what host cpu
+		 * supports
+		 */
+		nested_vmx_ept_caps |= VMX_EPT_EXTENT_GLOBAL_BIT |
+			VMX_EPT_EXTENT_CONTEXT_BIT;
+	} else
+		nested_vmx_ept_caps = 0;
+
 	/* miscellaneous data */
 	rdmsr(MSR_IA32_VMX_MISC, nested_vmx_misc_low, nested_vmx_misc_high);
 	nested_vmx_misc_low &= VMX_MISC_PREEMPTION_TIMER_RATE_MASK |
@@ -2282,8 +2311,11 @@ static int vmx_get_vmx_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata)
 
 	switch (msr_index) {
 	case MSR_IA32_FEATURE_CONTROL:
-		*pdata = 0;
-		break;
+		if (nested_vmx_allowed(vcpu)) {
+			*pdata = to_vmx(vcpu)->nested.msr_ia32_feature_control;
+			break;
+		}
+		return 0;
 	case MSR_IA32_VMX_BASIC:
 		/*
 		 * This MSR reports some information about VMX support. We
@@ -2346,8 +2378,8 @@ static int vmx_get_vmx_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata)
 					nested_vmx_secondary_ctls_high);
 		break;
 	case MSR_IA32_VMX_EPT_VPID_CAP:
-		/* Currently, no nested ept or nested vpid */
-		*pdata = 0;
+		/* Currently, no nested vpid support */
+		*pdata = nested_vmx_ept_caps;
 		break;
 	default:
 		return 0;
@@ -2356,14 +2388,24 @@ static int vmx_get_vmx_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata)
 	return 1;
 }
 
-static int vmx_set_vmx_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data)
+static int vmx_set_vmx_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 {
+	u32 msr_index = msr_info->index;
+	u64 data = msr_info->data;
+	bool host_initialized = msr_info->host_initiated;
+
 	if (!nested_vmx_allowed(vcpu))
 		return 0;
 
-	if (msr_index == MSR_IA32_FEATURE_CONTROL)
-		/* TODO: the right thing. */
+	if (msr_index == MSR_IA32_FEATURE_CONTROL) {
+		if (!host_initialized &&
+				to_vmx(vcpu)->nested.msr_ia32_feature_control
+				& FEATURE_CONTROL_LOCKED)
+			return 0;
+		to_vmx(vcpu)->nested.msr_ia32_feature_control = data;
 		return 1;
+	}
+
 	/*
 	 * No need to treat VMX capability MSRs specially: If we don't handle
 	 * them, handle_wrmsr will #GP(0), which is correct (they are readonly)
@@ -2494,7 +2536,7 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 			return 1;
 		/* Otherwise falls through */
 	default:
-		if (vmx_set_vmx_msr(vcpu, msr_index, data))
+		if (vmx_set_vmx_msr(vcpu, msr_info))
 			break;
 		msr = find_msr_entry(vmx, msr_index);
 		if (msr) {
@@ -3213,25 +3255,29 @@ static void vmx_decache_cr4_guest_bits(struct kvm_vcpu *vcpu)
 
 static void ept_load_pdptrs(struct kvm_vcpu *vcpu)
 {
+	struct kvm_mmu *mmu = vcpu->arch.walk_mmu;
+
 	if (!test_bit(VCPU_EXREG_PDPTR,
 		      (unsigned long *)&vcpu->arch.regs_dirty))
 		return;
 
 	if (is_paging(vcpu) && is_pae(vcpu) && !is_long_mode(vcpu)) {
-		vmcs_write64(GUEST_PDPTR0, vcpu->arch.mmu.pdptrs[0]);
-		vmcs_write64(GUEST_PDPTR1, vcpu->arch.mmu.pdptrs[1]);
-		vmcs_write64(GUEST_PDPTR2, vcpu->arch.mmu.pdptrs[2]);
-		vmcs_write64(GUEST_PDPTR3, vcpu->arch.mmu.pdptrs[3]);
+		vmcs_write64(GUEST_PDPTR0, mmu->pdptrs[0]);
+		vmcs_write64(GUEST_PDPTR1, mmu->pdptrs[1]);
+		vmcs_write64(GUEST_PDPTR2, mmu->pdptrs[2]);
+		vmcs_write64(GUEST_PDPTR3, mmu->pdptrs[3]);
 	}
 }
 
 static void ept_save_pdptrs(struct kvm_vcpu *vcpu)
 {
+	struct kvm_mmu *mmu = vcpu->arch.walk_mmu;
+
 	if (is_paging(vcpu) && is_pae(vcpu) && !is_long_mode(vcpu)) {
-		vcpu->arch.mmu.pdptrs[0] = vmcs_read64(GUEST_PDPTR0);
-		vcpu->arch.mmu.pdptrs[1] = vmcs_read64(GUEST_PDPTR1);
-		vcpu->arch.mmu.pdptrs[2] = vmcs_read64(GUEST_PDPTR2);
-		vcpu->arch.mmu.pdptrs[3] = vmcs_read64(GUEST_PDPTR3);
+		mmu->pdptrs[0] = vmcs_read64(GUEST_PDPTR0);
+		mmu->pdptrs[1] = vmcs_read64(GUEST_PDPTR1);
+		mmu->pdptrs[2] = vmcs_read64(GUEST_PDPTR2);
+		mmu->pdptrs[3] = vmcs_read64(GUEST_PDPTR3);
 	}
 
 	__set_bit(VCPU_EXREG_PDPTR,
@@ -5297,14 +5343,29 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu)
 		return 0;
 	}
 
+	/*
+	 * EPT violation happened while executing iret from NMI,
+	 * "blocked by NMI" bit has to be set before next VM entry.
+	 * There are errata that may cause this bit to not be set:
+	 * AAK134, BY25.
+	 */
+	if (!(to_vmx(vcpu)->idt_vectoring_info & VECTORING_INFO_VALID_MASK) &&
+			cpu_has_virtual_nmis() &&
+			(exit_qualification & INTR_INFO_UNBLOCK_NMI))
+		vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO, GUEST_INTR_STATE_NMI);
+
 	gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS);
 	trace_kvm_page_fault(gpa, exit_qualification);
 
 	/* It is a write fault? */
 	error_code = exit_qualification & (1U << 1);
+	/* It is a fetch fault? */
+	error_code |= (exit_qualification & (1U << 2)) << 2;
 	/* ept page table is present? */
 	error_code |= (exit_qualification >> 3) & 0x1;
 
+	vcpu->arch.exit_qualification = exit_qualification;
+
 	return kvm_mmu_page_fault(vcpu, gpa, error_code, NULL, 0);
 }
 
@@ -5438,7 +5499,8 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu)
 
 		err = emulate_instruction(vcpu, EMULTYPE_NO_REEXECUTE);
 
-		if (err == EMULATE_DO_MMIO) {
+		if (err == EMULATE_USER_EXIT) {
+			++vcpu->stat.mmio_exits;
 			ret = 0;
 			goto out;
 		}
@@ -5567,8 +5629,47 @@ static void nested_free_all_saved_vmcss(struct vcpu_vmx *vmx)
 		free_loaded_vmcs(&vmx->vmcs01);
 }
 
+/*
+ * The following 3 functions, nested_vmx_succeed()/failValid()/failInvalid(),
+ * set the success or error code of an emulated VMX instruction, as specified
+ * by Vol 2B, VMX Instruction Reference, "Conventions".
+ */
+static void nested_vmx_succeed(struct kvm_vcpu *vcpu)
+{
+	vmx_set_rflags(vcpu, vmx_get_rflags(vcpu)
+			& ~(X86_EFLAGS_CF | X86_EFLAGS_PF | X86_EFLAGS_AF |
+			    X86_EFLAGS_ZF | X86_EFLAGS_SF | X86_EFLAGS_OF));
+}
+
+static void nested_vmx_failInvalid(struct kvm_vcpu *vcpu)
+{
+	vmx_set_rflags(vcpu, (vmx_get_rflags(vcpu)
+			& ~(X86_EFLAGS_PF | X86_EFLAGS_AF | X86_EFLAGS_ZF |
+			    X86_EFLAGS_SF | X86_EFLAGS_OF))
+			| X86_EFLAGS_CF);
+}
+
 static void nested_vmx_failValid(struct kvm_vcpu *vcpu,
-				 u32 vm_instruction_error);
+					u32 vm_instruction_error)
+{
+	if (to_vmx(vcpu)->nested.current_vmptr == -1ull) {
+		/*
+		 * failValid writes the error number to the current VMCS, which
+		 * can't be done there isn't a current VMCS.
+		 */
+		nested_vmx_failInvalid(vcpu);
+		return;
+	}
+	vmx_set_rflags(vcpu, (vmx_get_rflags(vcpu)
+			& ~(X86_EFLAGS_CF | X86_EFLAGS_PF | X86_EFLAGS_AF |
+			    X86_EFLAGS_SF | X86_EFLAGS_OF))
+			| X86_EFLAGS_ZF);
+	get_vmcs12(vcpu)->vm_instruction_error = vm_instruction_error;
+	/*
+	 * We don't need to force a shadow sync because
+	 * VM_INSTRUCTION_ERROR is not shadowed
+	 */
+}
 
 /*
  * Emulate the VMXON instruction.
@@ -5583,6 +5684,8 @@ static int handle_vmon(struct kvm_vcpu *vcpu)
 	struct kvm_segment cs;
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	struct vmcs *shadow_vmcs;
+	const u64 VMXON_NEEDED_FEATURES = FEATURE_CONTROL_LOCKED
+		| FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX;
 
 	/* The Intel VMX Instruction Reference lists a bunch of bits that
 	 * are prerequisite to running VMXON, most notably cr4.VMXE must be
@@ -5611,6 +5714,13 @@ static int handle_vmon(struct kvm_vcpu *vcpu)
 		skip_emulated_instruction(vcpu);
 		return 1;
 	}
+
+	if ((vmx->nested.msr_ia32_feature_control & VMXON_NEEDED_FEATURES)
+			!= VMXON_NEEDED_FEATURES) {
+		kvm_inject_gp(vcpu, 0);
+		return 1;
+	}
+
 	if (enable_shadow_vmcs) {
 		shadow_vmcs = alloc_vmcs();
 		if (!shadow_vmcs)
@@ -5628,6 +5738,7 @@ static int handle_vmon(struct kvm_vcpu *vcpu)
 	vmx->nested.vmxon = true;
 
 	skip_emulated_instruction(vcpu);
+	nested_vmx_succeed(vcpu);
 	return 1;
 }
 
@@ -5712,6 +5823,7 @@ static int handle_vmoff(struct kvm_vcpu *vcpu)
 		return 1;
 	free_nested(to_vmx(vcpu));
 	skip_emulated_instruction(vcpu);
+	nested_vmx_succeed(vcpu);
 	return 1;
 }
 
@@ -5768,48 +5880,6 @@ static int get_vmx_mem_address(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
-/*
- * The following 3 functions, nested_vmx_succeed()/failValid()/failInvalid(),
- * set the success or error code of an emulated VMX instruction, as specified
- * by Vol 2B, VMX Instruction Reference, "Conventions".
- */
-static void nested_vmx_succeed(struct kvm_vcpu *vcpu)
-{
-	vmx_set_rflags(vcpu, vmx_get_rflags(vcpu)
-			& ~(X86_EFLAGS_CF | X86_EFLAGS_PF | X86_EFLAGS_AF |
-			    X86_EFLAGS_ZF | X86_EFLAGS_SF | X86_EFLAGS_OF));
-}
-
-static void nested_vmx_failInvalid(struct kvm_vcpu *vcpu)
-{
-	vmx_set_rflags(vcpu, (vmx_get_rflags(vcpu)
-			& ~(X86_EFLAGS_PF | X86_EFLAGS_AF | X86_EFLAGS_ZF |
-			    X86_EFLAGS_SF | X86_EFLAGS_OF))
-			| X86_EFLAGS_CF);
-}
-
-static void nested_vmx_failValid(struct kvm_vcpu *vcpu,
-					u32 vm_instruction_error)
-{
-	if (to_vmx(vcpu)->nested.current_vmptr == -1ull) {
-		/*
-		 * failValid writes the error number to the current VMCS, which
-		 * can't be done there isn't a current VMCS.
-		 */
-		nested_vmx_failInvalid(vcpu);
-		return;
-	}
-	vmx_set_rflags(vcpu, (vmx_get_rflags(vcpu)
-			& ~(X86_EFLAGS_CF | X86_EFLAGS_PF | X86_EFLAGS_AF |
-			    X86_EFLAGS_SF | X86_EFLAGS_OF))
-			| X86_EFLAGS_ZF);
-	get_vmcs12(vcpu)->vm_instruction_error = vm_instruction_error;
-	/*
-	 * We don't need to force a shadow sync because
-	 * VM_INSTRUCTION_ERROR is not shadowed
-	 */
-}
-
 /* Emulate the VMCLEAR instruction */
 static int handle_vmclear(struct kvm_vcpu *vcpu)
 {
@@ -5972,8 +6042,8 @@ static void copy_shadow_to_vmcs12(struct vcpu_vmx *vmx)
 	unsigned long field;
 	u64 field_value;
 	struct vmcs *shadow_vmcs = vmx->nested.current_shadow_vmcs;
-	unsigned long *fields = (unsigned long *)shadow_read_write_fields;
-	int num_fields = max_shadow_read_write_fields;
+	const unsigned long *fields = shadow_read_write_fields;
+	const int num_fields = max_shadow_read_write_fields;
 
 	vmcs_load(shadow_vmcs);
 
@@ -6002,12 +6072,11 @@ static void copy_shadow_to_vmcs12(struct vcpu_vmx *vmx)
 
 static void copy_vmcs12_to_shadow(struct vcpu_vmx *vmx)
 {
-	unsigned long *fields[] = {
-		(unsigned long *)shadow_read_write_fields,
-		(unsigned long *)shadow_read_only_fields
+	const unsigned long *fields[] = {
+		shadow_read_write_fields,
+		shadow_read_only_fields
 	};
-	int num_lists =  ARRAY_SIZE(fields);
-	int max_fields[] = {
+	const int max_fields[] = {
 		max_shadow_read_write_fields,
 		max_shadow_read_only_fields
 	};
@@ -6018,7 +6087,7 @@ static void copy_vmcs12_to_shadow(struct vcpu_vmx *vmx)
 
 	vmcs_load(shadow_vmcs);
 
-	for (q = 0; q < num_lists; q++) {
+	for (q = 0; q < ARRAY_SIZE(fields); q++) {
 		for (i = 0; i < max_fields[q]; i++) {
 			field = fields[q][i];
 			vmcs12_read_any(&vmx->vcpu, field, &field_value);
@@ -6248,6 +6317,74 @@ static int handle_vmptrst(struct kvm_vcpu *vcpu)
 	return 1;
 }
 
+/* Emulate the INVEPT instruction */
+static int handle_invept(struct kvm_vcpu *vcpu)
+{
+	u32 vmx_instruction_info, types;
+	unsigned long type;
+	gva_t gva;
+	struct x86_exception e;
+	struct {
+		u64 eptp, gpa;
+	} operand;
+	u64 eptp_mask = ((1ull << 51) - 1) & PAGE_MASK;
+
+	if (!(nested_vmx_secondary_ctls_high & SECONDARY_EXEC_ENABLE_EPT) ||
+	    !(nested_vmx_ept_caps & VMX_EPT_INVEPT_BIT)) {
+		kvm_queue_exception(vcpu, UD_VECTOR);
+		return 1;
+	}
+
+	if (!nested_vmx_check_permission(vcpu))
+		return 1;
+
+	if (!kvm_read_cr0_bits(vcpu, X86_CR0_PE)) {
+		kvm_queue_exception(vcpu, UD_VECTOR);
+		return 1;
+	}
+
+	vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO);
+	type = kvm_register_read(vcpu, (vmx_instruction_info >> 28) & 0xf);
+
+	types = (nested_vmx_ept_caps >> VMX_EPT_EXTENT_SHIFT) & 6;
+
+	if (!(types & (1UL << type))) {
+		nested_vmx_failValid(vcpu,
+				VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
+		return 1;
+	}
+
+	/* According to the Intel VMX instruction reference, the memory
+	 * operand is read even if it isn't needed (e.g., for type==global)
+	 */
+	if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION),
+			vmx_instruction_info, &gva))
+		return 1;
+	if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, &operand,
+				sizeof(operand), &e)) {
+		kvm_inject_page_fault(vcpu, &e);
+		return 1;
+	}
+
+	switch (type) {
+	case VMX_EPT_EXTENT_CONTEXT:
+		if ((operand.eptp & eptp_mask) !=
+				(nested_ept_get_cr3(vcpu) & eptp_mask))
+			break;
+	case VMX_EPT_EXTENT_GLOBAL:
+		kvm_mmu_sync_roots(vcpu);
+		kvm_mmu_flush_tlb(vcpu);
+		nested_vmx_succeed(vcpu);
+		break;
+	default:
+		BUG_ON(1);
+		break;
+	}
+
+	skip_emulated_instruction(vcpu);
+	return 1;
+}
+
 /*
  * The exit handlers return 1 if the exit was handled fully and guest execution
  * may resume.  Otherwise they set the kvm_run parameter to indicate what needs
@@ -6292,6 +6429,7 @@ static int (*const kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = {
 	[EXIT_REASON_PAUSE_INSTRUCTION]       = handle_pause,
 	[EXIT_REASON_MWAIT_INSTRUCTION]	      = handle_invalid_op,
 	[EXIT_REASON_MONITOR_INSTRUCTION]     = handle_invalid_op,
+	[EXIT_REASON_INVEPT]                  = handle_invept,
 };
 
 static const int kvm_vmx_max_exit_handlers =
@@ -6518,6 +6656,7 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu)
 	case EXIT_REASON_VMPTRST: case EXIT_REASON_VMREAD:
 	case EXIT_REASON_VMRESUME: case EXIT_REASON_VMWRITE:
 	case EXIT_REASON_VMOFF: case EXIT_REASON_VMON:
+	case EXIT_REASON_INVEPT:
 		/*
 		 * VMX instructions trap unconditionally. This allows L1 to
 		 * emulate them for its L2 guest, i.e., allows 3-level nesting!
@@ -6550,7 +6689,20 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu)
 		return nested_cpu_has2(vmcs12,
 			SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES);
 	case EXIT_REASON_EPT_VIOLATION:
+		/*
+		 * L0 always deals with the EPT violation. If nested EPT is
+		 * used, and the nested mmu code discovers that the address is
+		 * missing in the guest EPT table (EPT12), the EPT violation
+		 * will be injected with nested_ept_inject_page_fault()
+		 */
+		return 0;
 	case EXIT_REASON_EPT_MISCONFIG:
+		/*
+		 * L2 never uses directly L1's EPT, but rather L0's own EPT
+		 * table (shadow on EPT) or a merged EPT table that L0 built
+		 * (EPT on EPT). So any problems with the structure of the
+		 * table is L0's fault.
+		 */
 		return 0;
 	case EXIT_REASON_PREEMPTION_TIMER:
 		return vmcs12->pin_based_vm_exec_control &
@@ -6638,7 +6790,7 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu)
 
 	if (unlikely(!cpu_has_virtual_nmis() && vmx->soft_vnmi_blocked &&
 	    !(is_guest_mode(vcpu) && nested_cpu_has_virtual_nmis(
-	                                get_vmcs12(vcpu), vcpu)))) {
+					get_vmcs12(vcpu))))) {
 		if (vmx_interrupt_allowed(vcpu)) {
 			vmx->soft_vnmi_blocked = 0;
 		} else if (vmx->vnmi_blocked_time > 1000000000LL &&
@@ -7326,6 +7478,48 @@ static void vmx_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry)
 		entry->ecx |= bit(X86_FEATURE_VMX);
 }
 
+static void nested_ept_inject_page_fault(struct kvm_vcpu *vcpu,
+		struct x86_exception *fault)
+{
+	struct vmcs12 *vmcs12;
+	nested_vmx_vmexit(vcpu);
+	vmcs12 = get_vmcs12(vcpu);
+
+	if (fault->error_code & PFERR_RSVD_MASK)
+		vmcs12->vm_exit_reason = EXIT_REASON_EPT_MISCONFIG;
+	else
+		vmcs12->vm_exit_reason = EXIT_REASON_EPT_VIOLATION;
+	vmcs12->exit_qualification = vcpu->arch.exit_qualification;
+	vmcs12->guest_physical_address = fault->address;
+}
+
+/* Callbacks for nested_ept_init_mmu_context: */
+
+static unsigned long nested_ept_get_cr3(struct kvm_vcpu *vcpu)
+{
+	/* return the page table to be shadowed - in our case, EPT12 */
+	return get_vmcs12(vcpu)->ept_pointer;
+}
+
+static int nested_ept_init_mmu_context(struct kvm_vcpu *vcpu)
+{
+	int r = kvm_init_shadow_ept_mmu(vcpu, &vcpu->arch.mmu,
+			nested_vmx_ept_caps & VMX_EPT_EXECUTE_ONLY_BIT);
+
+	vcpu->arch.mmu.set_cr3           = vmx_set_cr3;
+	vcpu->arch.mmu.get_cr3           = nested_ept_get_cr3;
+	vcpu->arch.mmu.inject_page_fault = nested_ept_inject_page_fault;
+
+	vcpu->arch.walk_mmu              = &vcpu->arch.nested_mmu;
+
+	return r;
+}
+
+static void nested_ept_uninit_mmu_context(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.walk_mmu = &vcpu->arch.mmu;
+}
+
 /*
  * prepare_vmcs02 is called when the L1 guest hypervisor runs its nested
  * L2 guest. L1 has a vmcs for L2 (vmcs12), and this function "merges" it
@@ -7388,7 +7582,7 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 		vmcs12->guest_interruptibility_info);
 	vmcs_write32(GUEST_SYSENTER_CS, vmcs12->guest_sysenter_cs);
 	kvm_set_dr(vcpu, 7, vmcs12->guest_dr7);
-	vmcs_writel(GUEST_RFLAGS, vmcs12->guest_rflags);
+	vmx_set_rflags(vcpu, vmcs12->guest_rflags);
 	vmcs_writel(GUEST_PENDING_DBG_EXCEPTIONS,
 		vmcs12->guest_pending_dbg_exceptions);
 	vmcs_writel(GUEST_SYSENTER_ESP, vmcs12->guest_sysenter_esp);
@@ -7508,15 +7702,24 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 	vcpu->arch.cr0_guest_owned_bits &= ~vmcs12->cr0_guest_host_mask;
 	vmcs_writel(CR0_GUEST_HOST_MASK, ~vcpu->arch.cr0_guest_owned_bits);
 
-	/* Note: IA32_MODE, LOAD_IA32_EFER are modified by vmx_set_efer below */
-	vmcs_write32(VM_EXIT_CONTROLS,
-		vmcs12->vm_exit_controls | vmcs_config.vmexit_ctrl);
-	vmcs_write32(VM_ENTRY_CONTROLS, vmcs12->vm_entry_controls |
+	/* L2->L1 exit controls are emulated - the hardware exit is to L0 so
+	 * we should use its exit controls. Note that VM_EXIT_LOAD_IA32_EFER
+	 * bits are further modified by vmx_set_efer() below.
+	 */
+	vmcs_write32(VM_EXIT_CONTROLS, vmcs_config.vmexit_ctrl);
+
+	/* vmcs12's VM_ENTRY_LOAD_IA32_EFER and VM_ENTRY_IA32E_MODE are
+	 * emulated by vmx_set_efer(), below.
+	 */
+	vmcs_write32(VM_ENTRY_CONTROLS,
+		(vmcs12->vm_entry_controls & ~VM_ENTRY_LOAD_IA32_EFER &
+			~VM_ENTRY_IA32E_MODE) |
 		(vmcs_config.vmentry_ctrl & ~VM_ENTRY_IA32E_MODE));
 
-	if (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PAT)
+	if (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PAT) {
 		vmcs_write64(GUEST_IA32_PAT, vmcs12->guest_ia32_pat);
-	else if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT)
+		vcpu->arch.pat = vmcs12->guest_ia32_pat;
+	} else if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT)
 		vmcs_write64(GUEST_IA32_PAT, vmx->vcpu.arch.pat);
 
 
@@ -7538,6 +7741,11 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 		vmx_flush_tlb(vcpu);
 	}
 
+	if (nested_cpu_has_ept(vmcs12)) {
+		kvm_mmu_unload(vcpu);
+		nested_ept_init_mmu_context(vcpu);
+	}
+
 	if (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_EFER)
 		vcpu->arch.efer = vmcs12->guest_ia32_efer;
 	else if (vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE)
@@ -7565,6 +7773,16 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 	kvm_set_cr3(vcpu, vmcs12->guest_cr3);
 	kvm_mmu_reset_context(vcpu);
 
+	/*
+	 * L1 may access the L2's PDPTR, so save them to construct vmcs12
+	 */
+	if (enable_ept) {
+		vmcs_write64(GUEST_PDPTR0, vmcs12->guest_pdptr0);
+		vmcs_write64(GUEST_PDPTR1, vmcs12->guest_pdptr1);
+		vmcs_write64(GUEST_PDPTR2, vmcs12->guest_pdptr2);
+		vmcs_write64(GUEST_PDPTR3, vmcs12->guest_pdptr3);
+	}
+
 	kvm_register_write(vcpu, VCPU_REGS_RSP, vmcs12->guest_rsp);
 	kvm_register_write(vcpu, VCPU_REGS_RIP, vmcs12->guest_rip);
 }
@@ -7887,6 +8105,22 @@ static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 	vmcs12->guest_pending_dbg_exceptions =
 		vmcs_readl(GUEST_PENDING_DBG_EXCEPTIONS);
 
+	/*
+	 * In some cases (usually, nested EPT), L2 is allowed to change its
+	 * own CR3 without exiting. If it has changed it, we must keep it.
+	 * Of course, if L0 is using shadow page tables, GUEST_CR3 was defined
+	 * by L0, not L1 or L2, so we mustn't unconditionally copy it to vmcs12.
+	 *
+	 * Additionally, restore L2's PDPTR to vmcs12.
+	 */
+	if (enable_ept) {
+		vmcs12->guest_cr3 = vmcs_read64(GUEST_CR3);
+		vmcs12->guest_pdptr0 = vmcs_read64(GUEST_PDPTR0);
+		vmcs12->guest_pdptr1 = vmcs_read64(GUEST_PDPTR1);
+		vmcs12->guest_pdptr2 = vmcs_read64(GUEST_PDPTR2);
+		vmcs12->guest_pdptr3 = vmcs_read64(GUEST_PDPTR3);
+	}
+
 	vmcs12->vm_entry_controls =
 		(vmcs12->vm_entry_controls & ~VM_ENTRY_IA32E_MODE) |
 		(vmcs_read32(VM_ENTRY_CONTROLS) & VM_ENTRY_IA32E_MODE);
@@ -7948,6 +8182,8 @@ static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
 				   struct vmcs12 *vmcs12)
 {
+	struct kvm_segment seg;
+
 	if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_EFER)
 		vcpu->arch.efer = vmcs12->host_ia32_efer;
 	else if (vmcs12->vm_exit_controls & VM_EXIT_HOST_ADDR_SPACE_SIZE)
@@ -7982,7 +8218,9 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
 	vcpu->arch.cr4_guest_owned_bits = ~vmcs_readl(CR4_GUEST_HOST_MASK);
 	kvm_set_cr4(vcpu, vmcs12->host_cr4);
 
-	/* shadow page tables on either EPT or shadow page tables */
+	if (nested_cpu_has_ept(vmcs12))
+		nested_ept_uninit_mmu_context(vcpu);
+
 	kvm_set_cr3(vcpu, vmcs12->host_cr3);
 	kvm_mmu_reset_context(vcpu);
 
@@ -8001,23 +8239,61 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
 	vmcs_writel(GUEST_SYSENTER_EIP, vmcs12->host_ia32_sysenter_eip);
 	vmcs_writel(GUEST_IDTR_BASE, vmcs12->host_idtr_base);
 	vmcs_writel(GUEST_GDTR_BASE, vmcs12->host_gdtr_base);
-	vmcs_writel(GUEST_TR_BASE, vmcs12->host_tr_base);
-	vmcs_writel(GUEST_GS_BASE, vmcs12->host_gs_base);
-	vmcs_writel(GUEST_FS_BASE, vmcs12->host_fs_base);
-	vmcs_write16(GUEST_ES_SELECTOR, vmcs12->host_es_selector);
-	vmcs_write16(GUEST_CS_SELECTOR, vmcs12->host_cs_selector);
-	vmcs_write16(GUEST_SS_SELECTOR, vmcs12->host_ss_selector);
-	vmcs_write16(GUEST_DS_SELECTOR, vmcs12->host_ds_selector);
-	vmcs_write16(GUEST_FS_SELECTOR, vmcs12->host_fs_selector);
-	vmcs_write16(GUEST_GS_SELECTOR, vmcs12->host_gs_selector);
-	vmcs_write16(GUEST_TR_SELECTOR, vmcs12->host_tr_selector);
-
-	if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_PAT)
+
+	if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_PAT) {
 		vmcs_write64(GUEST_IA32_PAT, vmcs12->host_ia32_pat);
+		vcpu->arch.pat = vmcs12->host_ia32_pat;
+	}
 	if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL)
 		vmcs_write64(GUEST_IA32_PERF_GLOBAL_CTRL,
 			vmcs12->host_ia32_perf_global_ctrl);
 
+	/* Set L1 segment info according to Intel SDM
+	    27.5.2 Loading Host Segment and Descriptor-Table Registers */
+	seg = (struct kvm_segment) {
+		.base = 0,
+		.limit = 0xFFFFFFFF,
+		.selector = vmcs12->host_cs_selector,
+		.type = 11,
+		.present = 1,
+		.s = 1,
+		.g = 1
+	};
+	if (vmcs12->vm_exit_controls & VM_EXIT_HOST_ADDR_SPACE_SIZE)
+		seg.l = 1;
+	else
+		seg.db = 1;
+	vmx_set_segment(vcpu, &seg, VCPU_SREG_CS);
+	seg = (struct kvm_segment) {
+		.base = 0,
+		.limit = 0xFFFFFFFF,
+		.type = 3,
+		.present = 1,
+		.s = 1,
+		.db = 1,
+		.g = 1
+	};
+	seg.selector = vmcs12->host_ds_selector;
+	vmx_set_segment(vcpu, &seg, VCPU_SREG_DS);
+	seg.selector = vmcs12->host_es_selector;
+	vmx_set_segment(vcpu, &seg, VCPU_SREG_ES);
+	seg.selector = vmcs12->host_ss_selector;
+	vmx_set_segment(vcpu, &seg, VCPU_SREG_SS);
+	seg.selector = vmcs12->host_fs_selector;
+	seg.base = vmcs12->host_fs_base;
+	vmx_set_segment(vcpu, &seg, VCPU_SREG_FS);
+	seg.selector = vmcs12->host_gs_selector;
+	seg.base = vmcs12->host_gs_base;
+	vmx_set_segment(vcpu, &seg, VCPU_SREG_GS);
+	seg = (struct kvm_segment) {
+		.base = vmcs12->host_tr_base,
+		.limit = 0x67,
+		.selector = vmcs12->host_tr_selector,
+		.type = 11,
+		.present = 1
+	};
+	vmx_set_segment(vcpu, &seg, VCPU_SREG_TR);
+
 	kvm_set_dr(vcpu, 7, 0x400);
 	vmcs_write64(GUEST_IA32_DEBUGCTL, 0);
 }
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index d21bce505315..e5ca72a5cdb6 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -682,17 +682,6 @@ int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
 		 */
 	}
 
-	/*
-	 * Does the new cr3 value map to physical memory? (Note, we
-	 * catch an invalid cr3 even in real-mode, because it would
-	 * cause trouble later on when we turn on paging anyway.)
-	 *
-	 * A real CPU would silently accept an invalid cr3 and would
-	 * attempt to use it - with largely undefined (and often hard
-	 * to debug) behavior on the guest side.
-	 */
-	if (unlikely(!gfn_to_memslot(vcpu->kvm, cr3 >> PAGE_SHIFT)))
-		return 1;
 	vcpu->arch.cr3 = cr3;
 	__set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail);
 	vcpu->arch.mmu.new_cr3(vcpu);
@@ -850,7 +839,8 @@ static u32 msrs_to_save[] = {
 #ifdef CONFIG_X86_64
 	MSR_CSTAR, MSR_KERNEL_GS_BASE, MSR_SYSCALL_MASK, MSR_LSTAR,
 #endif
-	MSR_IA32_TSC, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA
+	MSR_IA32_TSC, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA,
+	MSR_IA32_FEATURE_CONTROL
 };
 
 static unsigned num_msrs_to_save;
@@ -1457,6 +1447,29 @@ static void pvclock_update_vm_gtod_copy(struct kvm *kvm)
 #endif
 }
 
+static void kvm_gen_update_masterclock(struct kvm *kvm)
+{
+#ifdef CONFIG_X86_64
+	int i;
+	struct kvm_vcpu *vcpu;
+	struct kvm_arch *ka = &kvm->arch;
+
+	spin_lock(&ka->pvclock_gtod_sync_lock);
+	kvm_make_mclock_inprogress_request(kvm);
+	/* no guest entries from this point */
+	pvclock_update_vm_gtod_copy(kvm);
+
+	kvm_for_each_vcpu(i, vcpu, kvm)
+		set_bit(KVM_REQ_CLOCK_UPDATE, &vcpu->requests);
+
+	/* guest entries allowed */
+	kvm_for_each_vcpu(i, vcpu, kvm)
+		clear_bit(KVM_REQ_MCLOCK_INPROGRESS, &vcpu->requests);
+
+	spin_unlock(&ka->pvclock_gtod_sync_lock);
+#endif
+}
+
 static int kvm_guest_time_update(struct kvm_vcpu *v)
 {
 	unsigned long flags, this_tsc_khz;
@@ -3806,6 +3819,7 @@ long kvm_arch_vm_ioctl(struct file *filp,
 		delta = user_ns.clock - now_ns;
 		local_irq_enable();
 		kvm->arch.kvmclock_offset = delta;
+		kvm_gen_update_masterclock(kvm);
 		break;
 	}
 	case KVM_GET_CLOCK: {
@@ -4955,6 +4969,97 @@ static bool retry_instruction(struct x86_emulate_ctxt *ctxt,
 static int complete_emulated_mmio(struct kvm_vcpu *vcpu);
 static int complete_emulated_pio(struct kvm_vcpu *vcpu);
 
+static int kvm_vcpu_check_hw_bp(unsigned long addr, u32 type, u32 dr7,
+				unsigned long *db)
+{
+	u32 dr6 = 0;
+	int i;
+	u32 enable, rwlen;
+
+	enable = dr7;
+	rwlen = dr7 >> 16;
+	for (i = 0; i < 4; i++, enable >>= 2, rwlen >>= 4)
+		if ((enable & 3) && (rwlen & 15) == type && db[i] == addr)
+			dr6 |= (1 << i);
+	return dr6;
+}
+
+static void kvm_vcpu_check_singlestep(struct kvm_vcpu *vcpu, int *r)
+{
+	struct kvm_run *kvm_run = vcpu->run;
+
+	/*
+	 * Use the "raw" value to see if TF was passed to the processor.
+	 * Note that the new value of the flags has not been saved yet.
+	 *
+	 * This is correct even for TF set by the guest, because "the
+	 * processor will not generate this exception after the instruction
+	 * that sets the TF flag".
+	 */
+	unsigned long rflags = kvm_x86_ops->get_rflags(vcpu);
+
+	if (unlikely(rflags & X86_EFLAGS_TF)) {
+		if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) {
+			kvm_run->debug.arch.dr6 = DR6_BS | DR6_FIXED_1;
+			kvm_run->debug.arch.pc = vcpu->arch.singlestep_rip;
+			kvm_run->debug.arch.exception = DB_VECTOR;
+			kvm_run->exit_reason = KVM_EXIT_DEBUG;
+			*r = EMULATE_USER_EXIT;
+		} else {
+			vcpu->arch.emulate_ctxt.eflags &= ~X86_EFLAGS_TF;
+			/*
+			 * "Certain debug exceptions may clear bit 0-3.  The
+			 * remaining contents of the DR6 register are never
+			 * cleared by the processor".
+			 */
+			vcpu->arch.dr6 &= ~15;
+			vcpu->arch.dr6 |= DR6_BS;
+			kvm_queue_exception(vcpu, DB_VECTOR);
+		}
+	}
+}
+
+static bool kvm_vcpu_check_breakpoint(struct kvm_vcpu *vcpu, int *r)
+{
+	struct kvm_run *kvm_run = vcpu->run;
+	unsigned long eip = vcpu->arch.emulate_ctxt.eip;
+	u32 dr6 = 0;
+
+	if (unlikely(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) &&
+	    (vcpu->arch.guest_debug_dr7 & DR7_BP_EN_MASK)) {
+		dr6 = kvm_vcpu_check_hw_bp(eip, 0,
+					   vcpu->arch.guest_debug_dr7,
+					   vcpu->arch.eff_db);
+
+		if (dr6 != 0) {
+			kvm_run->debug.arch.dr6 = dr6 | DR6_FIXED_1;
+			kvm_run->debug.arch.pc = kvm_rip_read(vcpu) +
+				get_segment_base(vcpu, VCPU_SREG_CS);
+
+			kvm_run->debug.arch.exception = DB_VECTOR;
+			kvm_run->exit_reason = KVM_EXIT_DEBUG;
+			*r = EMULATE_USER_EXIT;
+			return true;
+		}
+	}
+
+	if (unlikely(vcpu->arch.dr7 & DR7_BP_EN_MASK)) {
+		dr6 = kvm_vcpu_check_hw_bp(eip, 0,
+					   vcpu->arch.dr7,
+					   vcpu->arch.db);
+
+		if (dr6 != 0) {
+			vcpu->arch.dr6 &= ~15;
+			vcpu->arch.dr6 |= dr6;
+			kvm_queue_exception(vcpu, DB_VECTOR);
+			*r = EMULATE_DONE;
+			return true;
+		}
+	}
+
+	return false;
+}
+
 int x86_emulate_instruction(struct kvm_vcpu *vcpu,
 			    unsigned long cr2,
 			    int emulation_type,
@@ -4975,6 +5080,16 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu,
 
 	if (!(emulation_type & EMULTYPE_NO_DECODE)) {
 		init_emulate_ctxt(vcpu);
+
+		/*
+		 * We will reenter on the same instruction since
+		 * we do not set complete_userspace_io.  This does not
+		 * handle watchpoints yet, those would be handled in
+		 * the emulate_ops.
+		 */
+		if (kvm_vcpu_check_breakpoint(vcpu, &r))
+			return r;
+
 		ctxt->interruptibility = 0;
 		ctxt->have_exception = false;
 		ctxt->perm_ok = false;
@@ -5031,17 +5146,18 @@ restart:
 		inject_emulated_exception(vcpu);
 		r = EMULATE_DONE;
 	} else if (vcpu->arch.pio.count) {
-		if (!vcpu->arch.pio.in)
+		if (!vcpu->arch.pio.in) {
+			/* FIXME: return into emulator if single-stepping.  */
 			vcpu->arch.pio.count = 0;
-		else {
+		} else {
 			writeback = false;
 			vcpu->arch.complete_userspace_io = complete_emulated_pio;
 		}
-		r = EMULATE_DO_MMIO;
+		r = EMULATE_USER_EXIT;
 	} else if (vcpu->mmio_needed) {
 		if (!vcpu->mmio_is_write)
 			writeback = false;
-		r = EMULATE_DO_MMIO;
+		r = EMULATE_USER_EXIT;
 		vcpu->arch.complete_userspace_io = complete_emulated_mmio;
 	} else if (r == EMULATION_RESTART)
 		goto restart;
@@ -5050,10 +5166,12 @@ restart:
 
 	if (writeback) {
 		toggle_interruptibility(vcpu, ctxt->interruptibility);
-		kvm_set_rflags(vcpu, ctxt->eflags);
 		kvm_make_request(KVM_REQ_EVENT, vcpu);
 		vcpu->arch.emulate_regs_need_sync_to_vcpu = false;
 		kvm_rip_write(vcpu, ctxt->eip);
+		if (r == EMULATE_DONE)
+			kvm_vcpu_check_singlestep(vcpu, &r);
+		kvm_set_rflags(vcpu, ctxt->eflags);
 	} else
 		vcpu->arch.emulate_regs_need_sync_to_vcpu = true;
 
@@ -5347,7 +5465,7 @@ static struct notifier_block pvclock_gtod_notifier = {
 int kvm_arch_init(void *opaque)
 {
 	int r;
-	struct kvm_x86_ops *ops = (struct kvm_x86_ops *)opaque;
+	struct kvm_x86_ops *ops = opaque;
 
 	if (kvm_x86_ops) {
 		printk(KERN_ERR "kvm: already loaded the other module\n");
@@ -5495,6 +5613,23 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
 	return 1;
 }
 
+/*
+ * kvm_pv_kick_cpu_op:  Kick a vcpu.
+ *
+ * @apicid - apicid of vcpu to be kicked.
+ */
+static void kvm_pv_kick_cpu_op(struct kvm *kvm, unsigned long flags, int apicid)
+{
+	struct kvm_lapic_irq lapic_irq;
+
+	lapic_irq.shorthand = 0;
+	lapic_irq.dest_mode = 0;
+	lapic_irq.dest_id = apicid;
+
+	lapic_irq.delivery_mode = APIC_DM_REMRD;
+	kvm_irq_delivery_to_apic(kvm, 0, &lapic_irq, NULL);
+}
+
 int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
 {
 	unsigned long nr, a0, a1, a2, a3, ret;
@@ -5528,6 +5663,10 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
 	case KVM_HC_VAPIC_POLL_IRQ:
 		ret = 0;
 		break;
+	case KVM_HC_KICK_CPU:
+		kvm_pv_kick_cpu_op(vcpu->kvm, a0, a1);
+		ret = 0;
+		break;
 	default:
 		ret = -KVM_ENOSYS;
 		break;
@@ -5689,29 +5828,6 @@ static void process_nmi(struct kvm_vcpu *vcpu)
 	kvm_make_request(KVM_REQ_EVENT, vcpu);
 }
 
-static void kvm_gen_update_masterclock(struct kvm *kvm)
-{
-#ifdef CONFIG_X86_64
-	int i;
-	struct kvm_vcpu *vcpu;
-	struct kvm_arch *ka = &kvm->arch;
-
-	spin_lock(&ka->pvclock_gtod_sync_lock);
-	kvm_make_mclock_inprogress_request(kvm);
-	/* no guest entries from this point */
-	pvclock_update_vm_gtod_copy(kvm);
-
-	kvm_for_each_vcpu(i, vcpu, kvm)
-		set_bit(KVM_REQ_CLOCK_UPDATE, &vcpu->requests);
-
-	/* guest entries allowed */
-	kvm_for_each_vcpu(i, vcpu, kvm)
-		clear_bit(KVM_REQ_MCLOCK_INPROGRESS, &vcpu->requests);
-
-	spin_unlock(&ka->pvclock_gtod_sync_lock);
-#endif
-}
-
 static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu)
 {
 	u64 eoi_exit_bitmap[4];
@@ -5950,6 +6066,7 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
 				kvm_apic_accept_events(vcpu);
 				switch(vcpu->arch.mp_state) {
 				case KVM_MP_STATE_HALTED:
+					vcpu->arch.pv.pv_unhalted = false;
 					vcpu->arch.mp_state =
 						KVM_MP_STATE_RUNNABLE;
 				case KVM_MP_STATE_RUNNABLE:
@@ -6061,6 +6178,8 @@ static int complete_emulated_mmio(struct kvm_vcpu *vcpu)
 
 	if (vcpu->mmio_cur_fragment == vcpu->mmio_nr_fragments) {
 		vcpu->mmio_needed = 0;
+
+		/* FIXME: return into emulator if single-stepping.  */
 		if (vcpu->mmio_is_write)
 			return 1;
 		vcpu->mmio_read_completed = 1;
@@ -6249,7 +6368,12 @@ int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
 				    struct kvm_mp_state *mp_state)
 {
 	kvm_apic_accept_events(vcpu);
-	mp_state->mp_state = vcpu->arch.mp_state;
+	if (vcpu->arch.mp_state == KVM_MP_STATE_HALTED &&
+					vcpu->arch.pv.pv_unhalted)
+		mp_state->mp_state = KVM_MP_STATE_RUNNABLE;
+	else
+		mp_state->mp_state = vcpu->arch.mp_state;
+
 	return 0;
 }
 
@@ -6770,6 +6894,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 	BUG_ON(vcpu->kvm == NULL);
 	kvm = vcpu->kvm;
 
+	vcpu->arch.pv.pv_unhalted = false;
 	vcpu->arch.emulate_ctxt.ops = &emulate_ops;
 	if (!irqchip_in_kernel(kvm) || kvm_vcpu_is_bsp(vcpu))
 		vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
@@ -7019,6 +7144,15 @@ out_free:
 	return -ENOMEM;
 }
 
+void kvm_arch_memslots_updated(struct kvm *kvm)
+{
+	/*
+	 * memslots->generation has been incremented.
+	 * mmio generation may have reached its maximum value.
+	 */
+	kvm_mmu_invalidate_mmio_sptes(kvm);
+}
+
 int kvm_arch_prepare_memory_region(struct kvm *kvm,
 				struct kvm_memory_slot *memslot,
 				struct kvm_userspace_memory_region *mem,
@@ -7079,11 +7213,6 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
 	 */
 	if ((change != KVM_MR_DELETE) && (mem->flags & KVM_MEM_LOG_DIRTY_PAGES))
 		kvm_mmu_slot_remove_write_access(kvm, mem->slot);
-	/*
-	 * If memory slot is created, or moved, we need to clear all
-	 * mmio sptes.
-	 */
-	kvm_mmu_invalidate_mmio_sptes(kvm);
 }
 
 void kvm_arch_flush_shadow_all(struct kvm *kvm)
@@ -7103,6 +7232,7 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
 		!vcpu->arch.apf.halted)
 		|| !list_empty_careful(&vcpu->async_pf.done)
 		|| kvm_apic_has_events(vcpu)
+		|| vcpu->arch.pv.pv_unhalted
 		|| atomic_read(&vcpu->arch.nmi_queued) ||
 		(kvm_arch_interrupt_allowed(vcpu) &&
 		 kvm_cpu_has_interrupt(vcpu));
diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c
index 6a22c19da663..bdf8532494fe 100644
--- a/arch/x86/lguest/boot.c
+++ b/arch/x86/lguest/boot.c
@@ -7,8 +7,7 @@
  * kernel and insert a module (lg.ko) which allows us to run other Linux
  * kernels the same way we'd run processes.  We call the first kernel the Host,
  * and the others the Guests.  The program which sets up and configures Guests
- * (such as the example in Documentation/virtual/lguest/lguest.c) is called the
- * Launcher.
+ * (such as the example in tools/lguest/lguest.c) is called the Launcher.
  *
  * Secondly, we only run specially modified Guests, not normal kernels: setting
  * CONFIG_LGUEST_GUEST to "y" compiles this file into the kernel so it knows
@@ -1057,6 +1056,12 @@ static void lguest_load_sp0(struct tss_struct *tss,
 }
 
 /* Let's just say, I wouldn't do debugging under a Guest. */
+static unsigned long lguest_get_debugreg(int regno)
+{
+	/* FIXME: Implement */
+	return 0;
+}
+
 static void lguest_set_debugreg(int regno, unsigned long value)
 {
 	/* FIXME: Implement */
@@ -1304,6 +1309,7 @@ __init void lguest_init(void)
 	pv_cpu_ops.load_tr_desc = lguest_load_tr_desc;
 	pv_cpu_ops.set_ldt = lguest_set_ldt;
 	pv_cpu_ops.load_tls = lguest_load_tls;
+	pv_cpu_ops.get_debugreg = lguest_get_debugreg;
 	pv_cpu_ops.set_debugreg = lguest_set_debugreg;
 	pv_cpu_ops.clts = lguest_clts;
 	pv_cpu_ops.read_cr0 = lguest_read_cr0;
diff --git a/arch/x86/lib/csum-wrappers_64.c b/arch/x86/lib/csum-wrappers_64.c
index 25b7ae8d058a..7609e0e421ec 100644
--- a/arch/x86/lib/csum-wrappers_64.c
+++ b/arch/x86/lib/csum-wrappers_64.c
@@ -6,6 +6,7 @@
  */
 #include <asm/checksum.h>
 #include <linux/module.h>
+#include <asm/smap.h>
 
 /**
  * csum_partial_copy_from_user - Copy and checksum from user space.
@@ -52,8 +53,10 @@ csum_partial_copy_from_user(const void __user *src, void *dst,
 			len -= 2;
 		}
 	}
+	stac();
 	isum = csum_partial_copy_generic((__force const void *)src,
 				dst, len, isum, errp, NULL);
+	clac();
 	if (unlikely(*errp))
 		goto out_err;
 
@@ -82,6 +85,8 @@ __wsum
 csum_partial_copy_to_user(const void *src, void __user *dst,
 			  int len, __wsum isum, int *errp)
 {
+	__wsum ret;
+
 	might_sleep();
 
 	if (unlikely(!access_ok(VERIFY_WRITE, dst, len))) {
@@ -105,8 +110,11 @@ csum_partial_copy_to_user(const void *src, void __user *dst,
 	}
 
 	*errp = 0;
-	return csum_partial_copy_generic(src, (void __force *)dst,
-					 len, isum, NULL, errp);
+	stac();
+	ret = csum_partial_copy_generic(src, (void __force *)dst,
+					len, isum, NULL, errp);
+	clac();
+	return ret;
 }
 EXPORT_SYMBOL(csum_partial_copy_to_user);
 
diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c
index 906fea315791..c905e89e19fe 100644
--- a/arch/x86/lib/usercopy_64.c
+++ b/arch/x86/lib/usercopy_64.c
@@ -68,7 +68,7 @@ EXPORT_SYMBOL(copy_in_user);
  * Since protection fault in copy_from/to_user is not a normal situation,
  * it is not necessary to optimize tail handling.
  */
-unsigned long
+__visible unsigned long
 copy_user_handle_tail(char *to, char *from, unsigned len, unsigned zerorest)
 {
 	char c;
diff --git a/arch/x86/lib/x86-opcode-map.txt b/arch/x86/lib/x86-opcode-map.txt
index 5d7e51f3fd28..533a85e3a07e 100644
--- a/arch/x86/lib/x86-opcode-map.txt
+++ b/arch/x86/lib/x86-opcode-map.txt
@@ -1,10 +1,8 @@
 # x86 Opcode Maps
 #
 # This is (mostly) based on following documentations.
-# - Intel(R) 64 and IA-32 Architectures Software Developer's Manual Vol.2
-#   (#325383-040US, October 2011)
-# - Intel(R) Advanced Vector Extensions Programming Reference
-#   (#319433-011,JUNE 2011).
+# - Intel(R) 64 and IA-32 Architectures Software Developer's Manual Vol.2C
+#   (#326018-047US, June 2013)
 #
 #<Opcode maps>
 # Table: table-name
@@ -29,6 +27,7 @@
 #  - (F3): the last prefix is 0xF3
 #  - (F2): the last prefix is 0xF2
 #  - (!F3) : the last prefix is not 0xF3 (including non-last prefix case)
+#  - (66&F2): Both 0x66 and 0xF2 prefixes are specified.
 
 Table: one byte opcode
 Referrer:
@@ -246,8 +245,8 @@ c2: RETN Iw (f64)
 c3: RETN
 c4: LES Gz,Mp (i64) | VEX+2byte (Prefix)
 c5: LDS Gz,Mp (i64) | VEX+1byte (Prefix)
-c6: Grp11 Eb,Ib (1A)
-c7: Grp11 Ev,Iz (1A)
+c6: Grp11A Eb,Ib (1A)
+c7: Grp11B Ev,Iz (1A)
 c8: ENTER Iw,Ib
 c9: LEAVE (d64)
 ca: RETF Iw
@@ -293,8 +292,8 @@ ef: OUT DX,eAX
 # 0xf0 - 0xff
 f0: LOCK (Prefix)
 f1:
-f2: REPNE (Prefix)
-f3: REP/REPE (Prefix)
+f2: REPNE (Prefix) | XACQUIRE (Prefix)
+f3: REP/REPE (Prefix) | XRELEASE (Prefix)
 f4: HLT
 f5: CMC
 f6: Grp3_1 Eb (1A)
@@ -326,7 +325,8 @@ AVXcode: 1
 0a:
 0b: UD2 (1B)
 0c:
-0d: NOP Ev | GrpP
+# AMD's prefetch group. Intel supports prefetchw(/1) only.
+0d: GrpP
 0e: FEMMS
 # 3DNow! uses the last imm byte as opcode extension.
 0f: 3DNow! Pq,Qq,Ib
@@ -729,12 +729,12 @@ dc: VAESENC Vdq,Hdq,Wdq (66),(v1)
 dd: VAESENCLAST Vdq,Hdq,Wdq (66),(v1)
 de: VAESDEC Vdq,Hdq,Wdq (66),(v1)
 df: VAESDECLAST Vdq,Hdq,Wdq (66),(v1)
-f0: MOVBE Gy,My | MOVBE Gw,Mw (66) | CRC32 Gd,Eb (F2)
-f1: MOVBE My,Gy | MOVBE Mw,Gw (66) | CRC32 Gd,Ey (F2)
+f0: MOVBE Gy,My | MOVBE Gw,Mw (66) | CRC32 Gd,Eb (F2) | CRC32 Gd,Eb (66&F2)
+f1: MOVBE My,Gy | MOVBE Mw,Gw (66) | CRC32 Gd,Ey (F2) | CRC32 Gd,Ew (66&F2)
 f2: ANDN Gy,By,Ey (v)
 f3: Grp17 (1A)
 f5: BZHI Gy,Ey,By (v) | PEXT Gy,By,Ey (F3),(v) | PDEP Gy,By,Ey (F2),(v)
-f6: MULX By,Gy,rDX,Ey (F2),(v)
+f6: ADCX Gy,Ey (66) | ADOX Gy,Ey (F3) | MULX By,Gy,rDX,Ey (F2),(v)
 f7: BEXTR Gy,Ey,By (v) | SHLX Gy,Ey,By (66),(v) | SARX Gy,Ey,By (F3),(v) | SHRX Gy,Ey,By (F2),(v)
 EndTable
 
@@ -861,8 +861,8 @@ EndTable
 
 GrpTable: Grp7
 0: SGDT Ms | VMCALL (001),(11B) | VMLAUNCH (010),(11B) | VMRESUME (011),(11B) | VMXOFF (100),(11B)
-1: SIDT Ms | MONITOR (000),(11B) | MWAIT (001)
-2: LGDT Ms | XGETBV (000),(11B) | XSETBV (001),(11B) | VMFUNC (100),(11B)
+1: SIDT Ms | MONITOR (000),(11B) | MWAIT (001),(11B) | CLAC (010),(11B) | STAC (011),(11B)
+2: LGDT Ms | XGETBV (000),(11B) | XSETBV (001),(11B) | VMFUNC (100),(11B) | XEND (101)(11B) | XTEST (110)(11B)
 3: LIDT Ms
 4: SMSW Mw/Rv
 5:
@@ -880,15 +880,21 @@ EndTable
 GrpTable: Grp9
 1: CMPXCHG8B/16B Mq/Mdq
 6: VMPTRLD Mq | VMCLEAR Mq (66) | VMXON Mq (F3) | RDRAND Rv (11B)
-7: VMPTRST Mq | VMPTRST Mq (F3)
+7: VMPTRST Mq | VMPTRST Mq (F3) | RDSEED Rv (11B)
 EndTable
 
 GrpTable: Grp10
 EndTable
 
-GrpTable: Grp11
-# Note: the operands are given by group opcode
-0: MOV
+# Grp11A and Grp11B are expressed as Grp11 in Intel SDM
+GrpTable: Grp11A
+0: MOV Eb,Ib
+7: XABORT Ib (000),(11B)
+EndTable
+
+GrpTable: Grp11B
+0: MOV Eb,Iz
+7: XBEGIN Jz (000),(11B)
 EndTable
 
 GrpTable: Grp12
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 654be4ae3047..3aaeffcfd67a 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -842,23 +842,15 @@ do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address,
 	force_sig_info_fault(SIGBUS, code, address, tsk, fault);
 }
 
-static noinline int
+static noinline void
 mm_fault_error(struct pt_regs *regs, unsigned long error_code,
 	       unsigned long address, unsigned int fault)
 {
-	/*
-	 * Pagefault was interrupted by SIGKILL. We have no reason to
-	 * continue pagefault.
-	 */
-	if (fatal_signal_pending(current)) {
-		if (!(fault & VM_FAULT_RETRY))
-			up_read(&current->mm->mmap_sem);
-		if (!(error_code & PF_USER))
-			no_context(regs, error_code, address, 0, 0);
-		return 1;
+	if (fatal_signal_pending(current) && !(error_code & PF_USER)) {
+		up_read(&current->mm->mmap_sem);
+		no_context(regs, error_code, address, 0, 0);
+		return;
 	}
-	if (!(fault & VM_FAULT_ERROR))
-		return 0;
 
 	if (fault & VM_FAULT_OOM) {
 		/* Kernel mode? Handle exceptions or die: */
@@ -866,7 +858,7 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code,
 			up_read(&current->mm->mmap_sem);
 			no_context(regs, error_code, address,
 				   SIGSEGV, SEGV_MAPERR);
-			return 1;
+			return;
 		}
 
 		up_read(&current->mm->mmap_sem);
@@ -884,7 +876,6 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code,
 		else
 			BUG();
 	}
-	return 1;
 }
 
 static int spurious_fault_check(unsigned long error_code, pte_t *pte)
@@ -1011,9 +1002,7 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code)
 	unsigned long address;
 	struct mm_struct *mm;
 	int fault;
-	int write = error_code & PF_WRITE;
-	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
-					(write ? FAULT_FLAG_WRITE : 0);
+	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
 
 	tsk = current;
 	mm = tsk->mm;
@@ -1083,6 +1072,7 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code)
 	if (user_mode_vm(regs)) {
 		local_irq_enable();
 		error_code |= PF_USER;
+		flags |= FAULT_FLAG_USER;
 	} else {
 		if (regs->flags & X86_EFLAGS_IF)
 			local_irq_enable();
@@ -1109,6 +1099,9 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code)
 		return;
 	}
 
+	if (error_code & PF_WRITE)
+		flags |= FAULT_FLAG_WRITE;
+
 	/*
 	 * When running in the kernel we expect faults to occur only to
 	 * addresses in user space.  All other faults represent errors in
@@ -1187,9 +1180,17 @@ good_area:
 	 */
 	fault = handle_mm_fault(mm, vma, address, flags);
 
-	if (unlikely(fault & (VM_FAULT_RETRY|VM_FAULT_ERROR))) {
-		if (mm_fault_error(regs, error_code, address, fault))
-			return;
+	/*
+	 * If we need to retry but a fatal signal is pending, handle the
+	 * signal first. We do not need to release the mmap_sem because it
+	 * would already be released in __lock_page_or_retry in mm/filemap.c.
+	 */
+	if (unlikely((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)))
+		return;
+
+	if (unlikely(fault & VM_FAULT_ERROR)) {
+		mm_fault_error(regs, error_code, address, fault);
+		return;
 	}
 
 	/*
diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c
index 7e73e8c69096..9d980d88b747 100644
--- a/arch/x86/mm/hugetlbpage.c
+++ b/arch/x86/mm/hugetlbpage.c
@@ -59,6 +59,10 @@ follow_huge_pmd(struct mm_struct *mm, unsigned long address,
 	return NULL;
 }
 
+int pmd_huge_support(void)
+{
+	return 0;
+}
 #else
 
 struct page *
@@ -77,6 +81,10 @@ int pud_huge(pud_t pud)
 	return !!(pud_val(pud) & _PAGE_PSE);
 }
 
+int pmd_huge_support(void)
+{
+	return 1;
+}
 #endif
 
 /* x86_64 also uses this file */
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index 0215e2c563ef..799580cabc78 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -487,7 +487,7 @@ __early_ioremap(resource_size_t phys_addr, unsigned long size, pgprot_t prot)
 	unsigned long offset;
 	resource_size_t last_addr;
 	unsigned int nrpages;
-	enum fixed_addresses idx0, idx;
+	enum fixed_addresses idx;
 	int i, slot;
 
 	WARN_ON(system_state != SYSTEM_BOOTING);
@@ -540,8 +540,7 @@ __early_ioremap(resource_size_t phys_addr, unsigned long size, pgprot_t prot)
 	/*
 	 * Ok, go for it..
 	 */
-	idx0 = FIX_BTMAP_BEGIN - NR_FIX_BTMAPS*slot;
-	idx = idx0;
+	idx = FIX_BTMAP_BEGIN - NR_FIX_BTMAPS*slot;
 	while (nrpages > 0) {
 		early_set_fixmap(idx, phys_addr, prot);
 		phys_addr += PAGE_SIZE;
diff --git a/arch/x86/mm/srat.c b/arch/x86/mm/srat.c
index cdd0da9dd530..266ca912f62e 100644
--- a/arch/x86/mm/srat.c
+++ b/arch/x86/mm/srat.c
@@ -146,6 +146,7 @@ int __init
 acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma)
 {
 	u64 start, end;
+	u32 hotpluggable;
 	int node, pxm;
 
 	if (srat_disabled())
@@ -154,7 +155,8 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma)
 		goto out_err_bad_srat;
 	if ((ma->flags & ACPI_SRAT_MEM_ENABLED) == 0)
 		goto out_err;
-	if ((ma->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE) && !save_add_info())
+	hotpluggable = ma->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE;
+	if (hotpluggable && !save_add_info())
 		goto out_err;
 
 	start = ma->base_address;
@@ -174,9 +176,10 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma)
 
 	node_set(node, numa_nodes_parsed);
 
-	printk(KERN_INFO "SRAT: Node %u PXM %u [mem %#010Lx-%#010Lx]\n",
-	       node, pxm,
-	       (unsigned long long) start, (unsigned long long) end - 1);
+	pr_info("SRAT: Node %u PXM %u [mem %#010Lx-%#010Lx]%s\n",
+		node, pxm,
+		(unsigned long long) start, (unsigned long long) end - 1,
+		hotpluggable ? " hotplug" : "");
 
 	return 0;
 out_err_bad_srat:
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 282375f13c7e..ae699b3bbac8 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -103,6 +103,7 @@ static void flush_tlb_func(void *info)
 	if (f->flush_mm != this_cpu_read(cpu_tlbstate.active_mm))
 		return;
 
+	count_vm_event(NR_TLB_REMOTE_FLUSH_RECEIVED);
 	if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_OK) {
 		if (f->flush_end == TLB_FLUSH_ALL)
 			local_flush_tlb();
@@ -130,6 +131,7 @@ void native_flush_tlb_others(const struct cpumask *cpumask,
 	info.flush_start = start;
 	info.flush_end = end;
 
+	count_vm_event(NR_TLB_REMOTE_FLUSH);
 	if (is_uv_system()) {
 		unsigned int cpu;
 
@@ -149,6 +151,7 @@ void flush_tlb_current_task(void)
 
 	preempt_disable();
 
+	count_vm_event(NR_TLB_LOCAL_FLUSH_ALL);
 	local_flush_tlb();
 	if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids)
 		flush_tlb_others(mm_cpumask(mm), mm, 0UL, TLB_FLUSH_ALL);
@@ -211,16 +214,19 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
 	act_entries = mm->total_vm > tlb_entries ? tlb_entries : mm->total_vm;
 
 	/* tlb_flushall_shift is on balance point, details in commit log */
-	if ((end - start) >> PAGE_SHIFT > act_entries >> tlb_flushall_shift)
+	if ((end - start) >> PAGE_SHIFT > act_entries >> tlb_flushall_shift) {
+		count_vm_event(NR_TLB_LOCAL_FLUSH_ALL);
 		local_flush_tlb();
-	else {
+	} else {
 		if (has_large_page(mm, start, end)) {
 			local_flush_tlb();
 			goto flush_all;
 		}
 		/* flush range by one by one 'invlpg' */
-		for (addr = start; addr < end;	addr += PAGE_SIZE)
+		for (addr = start; addr < end;	addr += PAGE_SIZE) {
+			count_vm_event(NR_TLB_LOCAL_FLUSH_ONE);
 			__flush_tlb_single(addr);
+		}
 
 		if (cpumask_any_but(mm_cpumask(mm),
 				smp_processor_id()) < nr_cpu_ids)
@@ -256,6 +262,7 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long start)
 
 static void do_flush_tlb_all(void *info)
 {
+	count_vm_event(NR_TLB_REMOTE_FLUSH_RECEIVED);
 	__flush_tlb_all();
 	if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_LAZY)
 		leave_mm(smp_processor_id());
@@ -263,6 +270,7 @@ static void do_flush_tlb_all(void *info)
 
 void flush_tlb_all(void)
 {
+	count_vm_event(NR_TLB_REMOTE_FLUSH);
 	on_each_cpu(do_flush_tlb_all, NULL, 1);
 }
 
diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c
index 48768df2471a..6890d8498e0b 100644
--- a/arch/x86/oprofile/nmi_int.c
+++ b/arch/x86/oprofile/nmi_int.c
@@ -403,7 +403,7 @@ static void nmi_cpu_down(void *dummy)
 		nmi_cpu_shutdown(dummy);
 }
 
-static int nmi_create_files(struct super_block *sb, struct dentry *root)
+static int nmi_create_files(struct dentry *root)
 {
 	unsigned int i;
 
@@ -420,14 +420,14 @@ static int nmi_create_files(struct super_block *sb, struct dentry *root)
 			continue;
 
 		snprintf(buf,  sizeof(buf), "%d", i);
-		dir = oprofilefs_mkdir(sb, root, buf);
-		oprofilefs_create_ulong(sb, dir, "enabled", &counter_config[i].enabled);
-		oprofilefs_create_ulong(sb, dir, "event", &counter_config[i].event);
-		oprofilefs_create_ulong(sb, dir, "count", &counter_config[i].count);
-		oprofilefs_create_ulong(sb, dir, "unit_mask", &counter_config[i].unit_mask);
-		oprofilefs_create_ulong(sb, dir, "kernel", &counter_config[i].kernel);
-		oprofilefs_create_ulong(sb, dir, "user", &counter_config[i].user);
-		oprofilefs_create_ulong(sb, dir, "extra", &counter_config[i].extra);
+		dir = oprofilefs_mkdir(root, buf);
+		oprofilefs_create_ulong(dir, "enabled", &counter_config[i].enabled);
+		oprofilefs_create_ulong(dir, "event", &counter_config[i].event);
+		oprofilefs_create_ulong(dir, "count", &counter_config[i].count);
+		oprofilefs_create_ulong(dir, "unit_mask", &counter_config[i].unit_mask);
+		oprofilefs_create_ulong(dir, "kernel", &counter_config[i].kernel);
+		oprofilefs_create_ulong(dir, "user", &counter_config[i].user);
+		oprofilefs_create_ulong(dir, "extra", &counter_config[i].extra);
 	}
 
 	return 0;
diff --git a/arch/x86/oprofile/op_model_amd.c b/arch/x86/oprofile/op_model_amd.c
index b2b94438ff05..50d86c0e9ba4 100644
--- a/arch/x86/oprofile/op_model_amd.c
+++ b/arch/x86/oprofile/op_model_amd.c
@@ -454,16 +454,16 @@ static void init_ibs(void)
 	printk(KERN_INFO "oprofile: AMD IBS detected (0x%08x)\n", ibs_caps);
 }
 
-static int (*create_arch_files)(struct super_block *sb, struct dentry *root);
+static int (*create_arch_files)(struct dentry *root);
 
-static int setup_ibs_files(struct super_block *sb, struct dentry *root)
+static int setup_ibs_files(struct dentry *root)
 {
 	struct dentry *dir;
 	int ret = 0;
 
 	/* architecture specific files */
 	if (create_arch_files)
-		ret = create_arch_files(sb, root);
+		ret = create_arch_files(root);
 
 	if (ret)
 		return ret;
@@ -479,26 +479,26 @@ static int setup_ibs_files(struct super_block *sb, struct dentry *root)
 	ibs_config.max_cnt_op = 250000;
 
 	if (ibs_caps & IBS_CAPS_FETCHSAM) {
-		dir = oprofilefs_mkdir(sb, root, "ibs_fetch");
-		oprofilefs_create_ulong(sb, dir, "enable",
+		dir = oprofilefs_mkdir(root, "ibs_fetch");
+		oprofilefs_create_ulong(dir, "enable",
 					&ibs_config.fetch_enabled);
-		oprofilefs_create_ulong(sb, dir, "max_count",
+		oprofilefs_create_ulong(dir, "max_count",
 					&ibs_config.max_cnt_fetch);
-		oprofilefs_create_ulong(sb, dir, "rand_enable",
+		oprofilefs_create_ulong(dir, "rand_enable",
 					&ibs_config.rand_en);
 	}
 
 	if (ibs_caps & IBS_CAPS_OPSAM) {
-		dir = oprofilefs_mkdir(sb, root, "ibs_op");
-		oprofilefs_create_ulong(sb, dir, "enable",
+		dir = oprofilefs_mkdir(root, "ibs_op");
+		oprofilefs_create_ulong(dir, "enable",
 					&ibs_config.op_enabled);
-		oprofilefs_create_ulong(sb, dir, "max_count",
+		oprofilefs_create_ulong(dir, "max_count",
 					&ibs_config.max_cnt_op);
 		if (ibs_caps & IBS_CAPS_OPCNT)
-			oprofilefs_create_ulong(sb, dir, "dispatched_ops",
+			oprofilefs_create_ulong(dir, "dispatched_ops",
 						&ibs_config.dispatched_ops);
 		if (ibs_caps & IBS_CAPS_BRNTRGT)
-			oprofilefs_create_ulong(sb, dir, "branch_target",
+			oprofilefs_create_ulong(dir, "branch_target",
 						&ibs_config.branch_target);
 	}
 
diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c
index d641897a1f4e..b30e937689d6 100644
--- a/arch/x86/pci/acpi.c
+++ b/arch/x86/pci/acpi.c
@@ -568,13 +568,8 @@ struct pci_bus *pci_acpi_scan_root(struct acpi_pci_root *root)
 	 */
 	if (bus) {
 		struct pci_bus *child;
-		list_for_each_entry(child, &bus->children, node) {
-			struct pci_dev *self = child->self;
-			if (!self)
-				continue;
-
-			pcie_bus_configure_settings(child, self->pcie_mpss);
-		}
+		list_for_each_entry(child, &bus->children, node)
+			pcie_bus_configure_settings(child);
 	}
 
 	if (bus && node != -1) {
diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c
index 94919e307f8e..db6b1ab43255 100644
--- a/arch/x86/pci/i386.c
+++ b/arch/x86/pci/i386.c
@@ -210,6 +210,8 @@ static void pcibios_allocate_bridge_resources(struct pci_dev *dev)
 		r = &dev->resource[idx];
 		if (!r->flags)
 			continue;
+		if (r->parent)	/* Already allocated */
+			continue;
 		if (!r->start || pci_claim_resource(dev, idx) < 0) {
 			/*
 			 * Something is wrong with the region.
@@ -318,6 +320,8 @@ static void pcibios_allocate_dev_rom_resource(struct pci_dev *dev)
 	r = &dev->resource[PCI_ROM_RESOURCE];
 	if (!r->flags || !r->start)
 		return;
+	if (r->parent) /* Already allocated */
+		return;
 
 	if (pci_claim_resource(dev, PCI_ROM_RESOURCE) < 0) {
 		r->end -= r->start;
diff --git a/arch/x86/pci/mrst.c b/arch/x86/pci/mrst.c
index 6eb18c42a28a..903fded50786 100644
--- a/arch/x86/pci/mrst.c
+++ b/arch/x86/pci/mrst.c
@@ -23,11 +23,11 @@
 #include <linux/ioport.h>
 #include <linux/init.h>
 #include <linux/dmi.h>
+#include <linux/acpi.h>
+#include <linux/io.h>
+#include <linux/smp.h>
 
-#include <asm/acpi.h>
 #include <asm/segment.h>
-#include <asm/io.h>
-#include <asm/smp.h>
 #include <asm/pci_x86.h>
 #include <asm/hw_irq.h>
 #include <asm/io_apic.h>
@@ -43,7 +43,7 @@
 #define PCI_FIXED_BAR_4_SIZE	0x14
 #define PCI_FIXED_BAR_5_SIZE	0x1c
 
-static int pci_soc_mode = 0;
+static int pci_soc_mode;
 
 /**
  * fixed_bar_cap - return the offset of the fixed BAR cap if found
@@ -141,7 +141,8 @@ static int pci_device_update_fixed(struct pci_bus *bus, unsigned int devfn,
  */
 static bool type1_access_ok(unsigned int bus, unsigned int devfn, int reg)
 {
-	/* This is a workaround for A0 LNC bug where PCI status register does
+	/*
+	 * This is a workaround for A0 LNC bug where PCI status register does
 	 * not have new CAP bit set. can not be written by SW either.
 	 *
 	 * PCI header type in real LNC indicates a single function device, this
@@ -154,7 +155,7 @@ static bool type1_access_ok(unsigned int bus, unsigned int devfn, int reg)
 				|| devfn == PCI_DEVFN(0, 0)
 				|| devfn == PCI_DEVFN(3, 0)))
 		return 1;
-	return 0; /* langwell on others */
+	return 0; /* Langwell on others */
 }
 
 static int pci_read(struct pci_bus *bus, unsigned int devfn, int where,
@@ -172,7 +173,8 @@ static int pci_write(struct pci_bus *bus, unsigned int devfn, int where,
 {
 	int offset;
 
-	/* On MRST, there is no PCI ROM BAR, this will cause a subsequent read
+	/*
+	 * On MRST, there is no PCI ROM BAR, this will cause a subsequent read
 	 * to ROM BAR return 0 then being ignored.
 	 */
 	if (where == PCI_ROM_ADDRESS)
@@ -210,7 +212,8 @@ static int mrst_pci_irq_enable(struct pci_dev *dev)
 
 	pci_read_config_byte(dev, PCI_INTERRUPT_PIN, &pin);
 
-	/* MRST only have IOAPIC, the PCI irq lines are 1:1 mapped to
+	/*
+	 * MRST only have IOAPIC, the PCI irq lines are 1:1 mapped to
 	 * IOAPIC RTE entries, so we just enable RTE for the device.
 	 */
 	irq_attr.ioapic = mp_find_ioapic(dev->irq);
@@ -235,7 +238,7 @@ struct pci_ops pci_mrst_ops = {
  */
 int __init pci_mrst_init(void)
 {
-	printk(KERN_INFO "Intel MID platform detected, using MID PCI ops\n");
+	pr_info("Intel MID platform detected, using MID PCI ops\n");
 	pci_mmcfg_late_init();
 	pcibios_enable_irq = mrst_pci_irq_enable;
 	pci_root_ops = pci_mrst_ops;
@@ -244,17 +247,21 @@ int __init pci_mrst_init(void)
 	return 1;
 }
 
-/* Langwell devices are not true pci devices, they are not subject to 10 ms
- * d3 to d0 delay required by pci spec.
+/*
+ * Langwell devices are not true PCI devices; they are not subject to 10 ms
+ * d3 to d0 delay required by PCI spec.
  */
 static void pci_d3delay_fixup(struct pci_dev *dev)
 {
-	/* PCI fixups are effectively decided compile time. If we have a dual
-	   SoC/non-SoC kernel we don't want to mangle d3 on non SoC devices */
-        if (!pci_soc_mode)
-            return;
-	/* true pci devices in lincroft should allow type 1 access, the rest
-	 * are langwell fake pci devices.
+	/*
+	 * PCI fixups are effectively decided compile time. If we have a dual
+	 * SoC/non-SoC kernel we don't want to mangle d3 on non-SoC devices.
+	 */
+	if (!pci_soc_mode)
+		return;
+	/*
+	 * True PCI devices in Lincroft should allow type 1 access, the rest
+	 * are Langwell fake PCI devices.
 	 */
 	if (type1_access_ok(dev->bus->number, dev->devfn, PCI_DEVICE_ID))
 		return;
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index 90f6ed127096..c7e22ab29a5a 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -912,10 +912,13 @@ void __init efi_enter_virtual_mode(void)
 
 	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
 		md = p;
-		if (!(md->attribute & EFI_MEMORY_RUNTIME) &&
-		    md->type != EFI_BOOT_SERVICES_CODE &&
-		    md->type != EFI_BOOT_SERVICES_DATA)
-			continue;
+		if (!(md->attribute & EFI_MEMORY_RUNTIME)) {
+#ifdef CONFIG_X86_64
+			if (md->type != EFI_BOOT_SERVICES_CODE &&
+			    md->type != EFI_BOOT_SERVICES_DATA)
+#endif
+				continue;
+		}
 
 		size = md->num_pages << EFI_PAGE_SHIFT;
 		end = md->phys_addr + size;
diff --git a/arch/x86/platform/mrst/mrst.c b/arch/x86/platform/mrst/mrst.c
index 47fe66fe61f1..3ca5957b7a34 100644
--- a/arch/x86/platform/mrst/mrst.c
+++ b/arch/x86/platform/mrst/mrst.c
@@ -20,7 +20,7 @@
 #include <linux/intel_pmic_gpio.h>
 #include <linux/spi/spi.h>
 #include <linux/i2c.h>
-#include <linux/i2c/pca953x.h>
+#include <linux/platform_data/pca953x.h>
 #include <linux/gpio_keys.h>
 #include <linux/input.h>
 #include <linux/platform_device.h>
diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c
index 1cf5b300305e..424f4c97a44d 100644
--- a/arch/x86/power/cpu.c
+++ b/arch/x86/power/cpu.c
@@ -25,10 +25,10 @@
 #include <asm/cpu.h>
 
 #ifdef CONFIG_X86_32
-unsigned long saved_context_ebx;
-unsigned long saved_context_esp, saved_context_ebp;
-unsigned long saved_context_esi, saved_context_edi;
-unsigned long saved_context_eflags;
+__visible unsigned long saved_context_ebx;
+__visible unsigned long saved_context_esp, saved_context_ebp;
+__visible unsigned long saved_context_esi, saved_context_edi;
+__visible unsigned long saved_context_eflags;
 #endif
 struct saved_context saved_context;
 
diff --git a/arch/x86/power/hibernate_64.c b/arch/x86/power/hibernate_64.c
index a0fde91c16cf..304fca20d96e 100644
--- a/arch/x86/power/hibernate_64.c
+++ b/arch/x86/power/hibernate_64.c
@@ -20,26 +20,26 @@
 #include <asm/suspend.h>
 
 /* References to section boundaries */
-extern const void __nosave_begin, __nosave_end;
+extern __visible const void __nosave_begin, __nosave_end;
 
 /* Defined in hibernate_asm_64.S */
-extern int restore_image(void);
+extern asmlinkage int restore_image(void);
 
 /*
  * Address to jump to in the last phase of restore in order to get to the image
  * kernel's text (this value is passed in the image header).
  */
-unsigned long restore_jump_address;
+unsigned long restore_jump_address __visible;
 
 /*
  * Value of the cr3 register from before the hibernation (this value is passed
  * in the image header).
  */
-unsigned long restore_cr3;
+unsigned long restore_cr3 __visible;
 
-pgd_t *temp_level4_pgt;
+pgd_t *temp_level4_pgt __visible;
 
-void *relocated_restore_code;
+void *relocated_restore_code __visible;
 
 static void *alloc_pgt_page(void *context)
 {
diff --git a/arch/x86/tools/gen-insn-attr-x86.awk b/arch/x86/tools/gen-insn-attr-x86.awk
index e6773dc8ac41..093a892026f9 100644
--- a/arch/x86/tools/gen-insn-attr-x86.awk
+++ b/arch/x86/tools/gen-insn-attr-x86.awk
@@ -68,7 +68,7 @@ BEGIN {
 
 	lprefix1_expr = "\\((66|!F3)\\)"
 	lprefix2_expr = "\\(F3\\)"
-	lprefix3_expr = "\\((F2|!F3)\\)"
+	lprefix3_expr = "\\((F2|!F3|66\\&F2)\\)"
 	lprefix_expr = "\\((66|F2|F3)\\)"
 	max_lprefix = 4
 
@@ -83,6 +83,8 @@ BEGIN {
 	prefix_num["Operand-Size"] = "INAT_PFX_OPNDSZ"
 	prefix_num["REPNE"] = "INAT_PFX_REPNE"
 	prefix_num["REP/REPE"] = "INAT_PFX_REPE"
+	prefix_num["XACQUIRE"] = "INAT_PFX_REPNE"
+	prefix_num["XRELEASE"] = "INAT_PFX_REPE"
 	prefix_num["LOCK"] = "INAT_PFX_LOCK"
 	prefix_num["SEG=CS"] = "INAT_PFX_CS"
 	prefix_num["SEG=DS"] = "INAT_PFX_DS"
diff --git a/arch/x86/um/os-Linux/prctl.c b/arch/x86/um/os-Linux/prctl.c
index 9d34eddb517f..96eb2bd28832 100644
--- a/arch/x86/um/os-Linux/prctl.c
+++ b/arch/x86/um/os-Linux/prctl.c
@@ -4,7 +4,7 @@
  */
 
 #include <sys/ptrace.h>
-#include <linux/ptrace.h>
+#include <asm/ptrace.h>
 
 int os_arch_prctl(int pid, int code, unsigned long *addr)
 {
diff --git a/arch/x86/vdso/vclock_gettime.c b/arch/x86/vdso/vclock_gettime.c
index c74436e687bf..72074d528400 100644
--- a/arch/x86/vdso/vclock_gettime.c
+++ b/arch/x86/vdso/vclock_gettime.c
@@ -85,15 +85,18 @@ static notrace cycle_t vread_pvclock(int *mode)
 	cycle_t ret;
 	u64 last;
 	u32 version;
-	u32 migrate_count;
 	u8 flags;
 	unsigned cpu, cpu1;
 
 
 	/*
-	 * When looping to get a consistent (time-info, tsc) pair, we
-	 * also need to deal with the possibility we can switch vcpus,
-	 * so make sure we always re-fetch time-info for the current vcpu.
+	 * Note: hypervisor must guarantee that:
+	 * 1. cpu ID number maps 1:1 to per-CPU pvclock time info.
+	 * 2. that per-CPU pvclock time info is updated if the
+	 *    underlying CPU changes.
+	 * 3. that version is increased whenever underlying CPU
+	 *    changes.
+	 *
 	 */
 	do {
 		cpu = __getcpu() & VGETCPU_CPU_MASK;
@@ -104,8 +107,6 @@ static notrace cycle_t vread_pvclock(int *mode)
 
 		pvti = get_pvti(cpu);
 
-		migrate_count = pvti->migrate_count;
-
 		version = __pvclock_read_cycles(&pvti->pvti, &ret, &flags);
 
 		/*
@@ -117,8 +118,7 @@ static notrace cycle_t vread_pvclock(int *mode)
 		cpu1 = __getcpu() & VGETCPU_CPU_MASK;
 	} while (unlikely(cpu != cpu1 ||
 			  (pvti->pvti.version & 1) ||
-			  pvti->pvti.version != version ||
-			  pvti->migrate_count != migrate_count));
+			  pvti->pvti.version != version));
 
 	if (unlikely(!(flags & PVCLOCK_TSC_STABLE_BIT)))
 		*mode = VCLOCK_NONE;
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 193097ef3d7d..fa6ade76ef3f 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -427,8 +427,7 @@ static void __init xen_init_cpuid_mask(void)
 
 	if (!xen_initial_domain())
 		cpuid_leaf1_edx_mask &=
-			~((1 << X86_FEATURE_APIC) |  /* disable local APIC */
-			  (1 << X86_FEATURE_ACPI));  /* disable ACPI */
+			~((1 << X86_FEATURE_ACPI));  /* disable ACPI */
 
 	cpuid_leaf1_ecx_mask &= ~(1 << (X86_FEATURE_X2APIC % 32));
 
@@ -735,8 +734,7 @@ static int cvt_gate_to_trap(int vector, const gate_desc *val,
 		addr = (unsigned long)xen_int3;
 	else if (addr == (unsigned long)stack_segment)
 		addr = (unsigned long)xen_stack_segment;
-	else if (addr == (unsigned long)double_fault ||
-		 addr == (unsigned long)nmi) {
+	else if (addr == (unsigned long)double_fault) {
 		/* Don't need to handle these */
 		return 0;
 #ifdef CONFIG_X86_MCE
@@ -747,7 +745,12 @@ static int cvt_gate_to_trap(int vector, const gate_desc *val,
 		 */
 		;
 #endif
-	} else {
+	} else if (addr == (unsigned long)nmi)
+		/*
+		 * Use the native version as well.
+		 */
+		;
+	else {
 		/* Some other trap using IST? */
 		if (WARN_ON(val->ist != 0))
 			return 0;
@@ -1689,7 +1692,6 @@ static int xen_hvm_cpu_notify(struct notifier_block *self, unsigned long action,
 	case CPU_UP_PREPARE:
 		xen_vcpu_setup(cpu);
 		if (xen_have_vector_callback) {
-			xen_init_lock_cpu(cpu);
 			if (xen_feature(XENFEAT_hvm_safe_pvclock))
 				xen_setup_timer(cpu);
 		}
@@ -1710,6 +1712,8 @@ static void __init xen_hvm_guest_init(void)
 
 	xen_hvm_init_shared_info();
 
+	xen_panic_handler_init();
+
 	if (xen_feature(XENFEAT_hvm_callback_vector))
 		xen_have_vector_callback = 1;
 	xen_hvm_smp_init();
@@ -1720,15 +1724,12 @@ static void __init xen_hvm_guest_init(void)
 	xen_hvm_init_mmu_ops();
 }
 
-static bool __init xen_hvm_platform(void)
+static uint32_t __init xen_hvm_platform(void)
 {
 	if (xen_pv_domain())
-		return false;
-
-	if (!xen_cpuid_base())
-		return false;
+		return 0;
 
-	return true;
+	return xen_cpuid_base();
 }
 
 bool xen_hvm_need_lapic(void)
diff --git a/arch/x86/xen/irq.c b/arch/x86/xen/irq.c
index 01a4dc015ae1..0da7f863056f 100644
--- a/arch/x86/xen/irq.c
+++ b/arch/x86/xen/irq.c
@@ -47,23 +47,18 @@ static void xen_restore_fl(unsigned long flags)
 	/* convert from IF type flag */
 	flags = !(flags & X86_EFLAGS_IF);
 
-	/* There's a one instruction preempt window here.  We need to
-	   make sure we're don't switch CPUs between getting the vcpu
-	   pointer and updating the mask. */
+	/* See xen_irq_enable() for why preemption must be disabled. */
 	preempt_disable();
 	vcpu = this_cpu_read(xen_vcpu);
 	vcpu->evtchn_upcall_mask = flags;
-	preempt_enable_no_resched();
-
-	/* Doesn't matter if we get preempted here, because any
-	   pending event will get dealt with anyway. */
 
 	if (flags == 0) {
-		preempt_check_resched();
 		barrier(); /* unmask then check (avoid races) */
 		if (unlikely(vcpu->evtchn_upcall_pending))
 			xen_force_evtchn_callback();
-	}
+		preempt_enable();
+	} else
+		preempt_enable_no_resched();
 }
 PV_CALLEE_SAVE_REGS_THUNK(xen_restore_fl);
 
@@ -82,10 +77,12 @@ static void xen_irq_enable(void)
 {
 	struct vcpu_info *vcpu;
 
-	/* We don't need to worry about being preempted here, since
-	   either a) interrupts are disabled, so no preemption, or b)
-	   the caller is confused and is trying to re-enable interrupts
-	   on an indeterminate processor. */
+	/*
+	 * We may be preempted as soon as vcpu->evtchn_upcall_mask is
+	 * cleared, so disable preemption to ensure we check for
+	 * events on the VCPU we are still running on.
+	 */
+	preempt_disable();
 
 	vcpu = this_cpu_read(xen_vcpu);
 	vcpu->evtchn_upcall_mask = 0;
@@ -96,6 +93,8 @@ static void xen_irq_enable(void)
 	barrier(); /* unmask then check (avoid races) */
 	if (unlikely(vcpu->evtchn_upcall_pending))
 		xen_force_evtchn_callback();
+
+	preempt_enable();
 }
 PV_CALLEE_SAVE_REGS_THUNK(xen_irq_enable);
 
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index 95fb2aa5927e..a61c7d5811be 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -161,6 +161,7 @@
 #include <asm/xen/page.h>
 #include <asm/xen/hypercall.h>
 #include <asm/xen/hypervisor.h>
+#include <xen/balloon.h>
 #include <xen/grant_table.h>
 
 #include "multicalls.h"
@@ -878,7 +879,6 @@ int m2p_add_override(unsigned long mfn, struct page *page,
 	unsigned long uninitialized_var(address);
 	unsigned level;
 	pte_t *ptep = NULL;
-	int ret = 0;
 
 	pfn = page_to_pfn(page);
 	if (!PageHighMem(page)) {
@@ -925,8 +925,8 @@ int m2p_add_override(unsigned long mfn, struct page *page,
 	 * frontend pages while they are being shared with the backend,
 	 * because mfn_to_pfn (that ends up being called by GUPF) will
 	 * return the backend pfn rather than the frontend pfn. */
-	ret = __get_user(pfn, &machine_to_phys_mapping[mfn]);
-	if (ret == 0 && get_phys_to_machine(pfn) == mfn)
+	pfn = mfn_to_pfn_no_overrides(mfn);
+	if (get_phys_to_machine(pfn) == mfn)
 		set_phys_to_machine(pfn, FOREIGN_FRAME(mfn));
 
 	return 0;
@@ -941,7 +941,6 @@ int m2p_remove_override(struct page *page,
 	unsigned long uninitialized_var(address);
 	unsigned level;
 	pte_t *ptep = NULL;
-	int ret = 0;
 
 	pfn = page_to_pfn(page);
 	mfn = get_phys_to_machine(pfn);
@@ -967,7 +966,10 @@ int m2p_remove_override(struct page *page,
 	if (kmap_op != NULL) {
 		if (!PageHighMem(page)) {
 			struct multicall_space mcs;
-			struct gnttab_unmap_grant_ref *unmap_op;
+			struct gnttab_unmap_and_replace *unmap_op;
+			struct page *scratch_page = get_balloon_scratch_page();
+			unsigned long scratch_page_address = (unsigned long)
+				__va(page_to_pfn(scratch_page) << PAGE_SHIFT);
 
 			/*
 			 * It might be that we queued all the m2p grant table
@@ -986,25 +988,31 @@ int m2p_remove_override(struct page *page,
 				printk(KERN_WARNING "m2p_remove_override: "
 						"pfn %lx mfn %lx, failed to modify kernel mappings",
 						pfn, mfn);
+				put_balloon_scratch_page();
 				return -1;
 			}
 
-			mcs = xen_mc_entry(
-					sizeof(struct gnttab_unmap_grant_ref));
+			xen_mc_batch();
+
+			mcs = __xen_mc_entry(
+					sizeof(struct gnttab_unmap_and_replace));
 			unmap_op = mcs.args;
 			unmap_op->host_addr = kmap_op->host_addr;
+			unmap_op->new_addr = scratch_page_address;
 			unmap_op->handle = kmap_op->handle;
-			unmap_op->dev_bus_addr = 0;
 
 			MULTI_grant_table_op(mcs.mc,
-					GNTTABOP_unmap_grant_ref, unmap_op, 1);
+					GNTTABOP_unmap_and_replace, unmap_op, 1);
+
+			mcs = __xen_mc_entry(0);
+			MULTI_update_va_mapping(mcs.mc, scratch_page_address,
+					pfn_pte(page_to_pfn(scratch_page),
+					PAGE_KERNEL_RO), 0);
 
 			xen_mc_issue(PARAVIRT_LAZY_MMU);
 
-			set_pte_at(&init_mm, address, ptep,
-					pfn_pte(pfn, PAGE_KERNEL));
-			__flush_tlb_single(address);
 			kmap_op->host_addr = 0;
+			put_balloon_scratch_page();
 		}
 	}
 
@@ -1019,8 +1027,8 @@ int m2p_remove_override(struct page *page,
 	 * the original pfn causes mfn_to_pfn(mfn) to return the frontend
 	 * pfn again. */
 	mfn &= ~FOREIGN_FRAME_BIT;
-	ret = __get_user(pfn, &machine_to_phys_mapping[mfn]);
-	if (ret == 0 && get_phys_to_machine(pfn) == FOREIGN_FRAME(mfn) &&
+	pfn = mfn_to_pfn_no_overrides(mfn);
+	if (get_phys_to_machine(pfn) == FOREIGN_FRAME(mfn) &&
 			m2p_find_override(mfn) == NULL)
 		set_phys_to_machine(pfn, mfn);
 
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index 8f3eea6b80c5..09f3059cb00b 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -33,6 +33,9 @@
 /* These are code, but not functions.  Defined in entry.S */
 extern const char xen_hypervisor_callback[];
 extern const char xen_failsafe_callback[];
+#ifdef CONFIG_X86_64
+extern const char nmi[];
+#endif
 extern void xen_sysenter_target(void);
 extern void xen_syscall_target(void);
 extern void xen_syscall32_target(void);
@@ -215,13 +218,19 @@ static void __init xen_set_identity_and_release_chunk(
 	unsigned long pfn;
 
 	/*
-	 * If the PFNs are currently mapped, the VA mapping also needs
-	 * to be updated to be 1:1.
+	 * If the PFNs are currently mapped, clear the mappings
+	 * (except for the ISA region which must be 1:1 mapped) to
+	 * release the refcounts (in Xen) on the original frames.
 	 */
-	for (pfn = start_pfn; pfn <= max_pfn_mapped && pfn < end_pfn; pfn++)
+	for (pfn = start_pfn; pfn <= max_pfn_mapped && pfn < end_pfn; pfn++) {
+		pte_t pte = __pte_ma(0);
+
+		if (pfn < PFN_UP(ISA_END_ADDRESS))
+			pte = mfn_pte(pfn, PAGE_KERNEL_IO);
+
 		(void)HYPERVISOR_update_va_mapping(
-			(unsigned long)__va(pfn << PAGE_SHIFT),
-			mfn_pte(pfn, PAGE_KERNEL_IO), 0);
+			(unsigned long)__va(pfn << PAGE_SHIFT), pte, 0);
+	}
 
 	if (start_pfn < nr_pages)
 		*released += xen_release_chunk(
@@ -547,7 +556,13 @@ void xen_enable_syscall(void)
 	}
 #endif /* CONFIG_X86_64 */
 }
-
+void __cpuinit xen_enable_nmi(void)
+{
+#ifdef CONFIG_X86_64
+	if (register_callback(CALLBACKTYPE_nmi, nmi))
+		BUG();
+#endif
+}
 void __init xen_arch_setup(void)
 {
 	xen_panic_handler_init();
@@ -565,7 +580,7 @@ void __init xen_arch_setup(void)
 
 	xen_enable_sysenter();
 	xen_enable_syscall();
-
+	xen_enable_nmi();
 #ifdef CONFIG_ACPI
 	if (!(xen_start_info->flags & SIF_INITDOMAIN)) {
 		printk(KERN_INFO "ACPI in unprivileged domain disabled\n");
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index b81c88e51daa..31d04758b76f 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -273,12 +273,30 @@ static void __init xen_smp_prepare_boot_cpu(void)
 	BUG_ON(smp_processor_id() != 0);
 	native_smp_prepare_boot_cpu();
 
-	/* We've switched to the "real" per-cpu gdt, so make sure the
-	   old memory can be recycled */
-	make_lowmem_page_readwrite(xen_initial_gdt);
+	if (xen_pv_domain()) {
+		/* We've switched to the "real" per-cpu gdt, so make sure the
+		   old memory can be recycled */
+		make_lowmem_page_readwrite(xen_initial_gdt);
 
-	xen_filter_cpu_maps();
-	xen_setup_vcpu_info_placement();
+#ifdef CONFIG_X86_32
+		/*
+		 * Xen starts us with XEN_FLAT_RING1_DS, but linux code
+		 * expects __USER_DS
+		 */
+		loadsegment(ds, __USER_DS);
+		loadsegment(es, __USER_DS);
+#endif
+
+		xen_filter_cpu_maps();
+		xen_setup_vcpu_info_placement();
+	}
+	/*
+	 * The alternative logic (which patches the unlock/lock) runs before
+	 * the smp bootup up code is activated. Hence we need to set this up
+	 * the core kernel is being patched. Otherwise we will have only
+	 * modules patched but not core code.
+	 */
+	xen_init_spinlocks();
 }
 
 static void __init xen_smp_prepare_cpus(unsigned int max_cpus)
@@ -572,6 +590,12 @@ static inline int xen_map_vector(int vector)
 	case IRQ_WORK_VECTOR:
 		xen_vector = XEN_IRQ_WORK_VECTOR;
 		break;
+#ifdef CONFIG_X86_64
+	case NMI_VECTOR:
+	case APIC_DM_NMI: /* Some use that instead of NMI_VECTOR */
+		xen_vector = XEN_NMI_VECTOR;
+		break;
+#endif
 	default:
 		xen_vector = -1;
 		printk(KERN_ERR "xen: vector 0x%x is not implemented\n",
@@ -680,7 +704,6 @@ void __init xen_smp_init(void)
 {
 	smp_ops = xen_smp_ops;
 	xen_fill_possible_map();
-	xen_init_spinlocks();
 }
 
 static void __init xen_hvm_smp_prepare_cpus(unsigned int max_cpus)
@@ -703,6 +726,15 @@ static int xen_hvm_cpu_up(unsigned int cpu, struct task_struct *tidle)
 	WARN_ON(rc);
 	if (!rc)
 		rc =  native_cpu_up(cpu, tidle);
+
+	/*
+	 * We must initialize the slowpath CPU kicker _after_ the native
+	 * path has executed. If we initialized it before none of the
+	 * unlocker IPI kicks would reach the booting CPU as the booting
+	 * CPU had not set itself 'online' in cpu_online_mask. That mask
+	 * is checked when IPIs are sent (on HVM at least).
+	 */
+	xen_init_lock_cpu(cpu);
 	return rc;
 }
 
@@ -722,4 +754,5 @@ void __init xen_hvm_smp_init(void)
 	smp_ops.cpu_die = xen_hvm_cpu_die;
 	smp_ops.send_call_func_ipi = xen_smp_send_call_function_ipi;
 	smp_ops.send_call_func_single_ipi = xen_smp_send_call_function_single_ipi;
+	smp_ops.smp_prepare_boot_cpu = xen_smp_prepare_boot_cpu;
 }
diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c
index cf3caee356b3..be6b86078957 100644
--- a/arch/x86/xen/spinlock.c
+++ b/arch/x86/xen/spinlock.c
@@ -17,45 +17,44 @@
 #include "xen-ops.h"
 #include "debugfs.h"
 
-#ifdef CONFIG_XEN_DEBUG_FS
-static struct xen_spinlock_stats
-{
-	u64 taken;
-	u32 taken_slow;
-	u32 taken_slow_nested;
-	u32 taken_slow_pickup;
-	u32 taken_slow_spurious;
-	u32 taken_slow_irqenable;
+enum xen_contention_stat {
+	TAKEN_SLOW,
+	TAKEN_SLOW_PICKUP,
+	TAKEN_SLOW_SPURIOUS,
+	RELEASED_SLOW,
+	RELEASED_SLOW_KICKED,
+	NR_CONTENTION_STATS
+};
 
-	u64 released;
-	u32 released_slow;
-	u32 released_slow_kicked;
 
+#ifdef CONFIG_XEN_DEBUG_FS
 #define HISTO_BUCKETS	30
-	u32 histo_spin_total[HISTO_BUCKETS+1];
-	u32 histo_spin_spinning[HISTO_BUCKETS+1];
+static struct xen_spinlock_stats
+{
+	u32 contention_stats[NR_CONTENTION_STATS];
 	u32 histo_spin_blocked[HISTO_BUCKETS+1];
-
-	u64 time_total;
-	u64 time_spinning;
 	u64 time_blocked;
 } spinlock_stats;
 
 static u8 zero_stats;
 
-static unsigned lock_timeout = 1 << 10;
-#define TIMEOUT lock_timeout
-
 static inline void check_zero(void)
 {
-	if (unlikely(zero_stats)) {
-		memset(&spinlock_stats, 0, sizeof(spinlock_stats));
-		zero_stats = 0;
+	u8 ret;
+	u8 old = ACCESS_ONCE(zero_stats);
+	if (unlikely(old)) {
+		ret = cmpxchg(&zero_stats, old, 0);
+		/* This ensures only one fellow resets the stat */
+		if (ret == old)
+			memset(&spinlock_stats, 0, sizeof(spinlock_stats));
 	}
 }
 
-#define ADD_STATS(elem, val)			\
-	do { check_zero(); spinlock_stats.elem += (val); } while(0)
+static inline void add_stats(enum xen_contention_stat var, u32 val)
+{
+	check_zero();
+	spinlock_stats.contention_stats[var] += val;
+}
 
 static inline u64 spin_time_start(void)
 {
@@ -74,22 +73,6 @@ static void __spin_time_accum(u64 delta, u32 *array)
 		array[HISTO_BUCKETS]++;
 }
 
-static inline void spin_time_accum_spinning(u64 start)
-{
-	u32 delta = xen_clocksource_read() - start;
-
-	__spin_time_accum(delta, spinlock_stats.histo_spin_spinning);
-	spinlock_stats.time_spinning += delta;
-}
-
-static inline void spin_time_accum_total(u64 start)
-{
-	u32 delta = xen_clocksource_read() - start;
-
-	__spin_time_accum(delta, spinlock_stats.histo_spin_total);
-	spinlock_stats.time_total += delta;
-}
-
 static inline void spin_time_accum_blocked(u64 start)
 {
 	u32 delta = xen_clocksource_read() - start;
@@ -98,263 +81,138 @@ static inline void spin_time_accum_blocked(u64 start)
 	spinlock_stats.time_blocked += delta;
 }
 #else  /* !CONFIG_XEN_DEBUG_FS */
-#define TIMEOUT			(1 << 10)
-#define ADD_STATS(elem, val)	do { (void)(val); } while(0)
+static inline void add_stats(enum xen_contention_stat var, u32 val)
+{
+}
 
 static inline u64 spin_time_start(void)
 {
 	return 0;
 }
 
-static inline void spin_time_accum_total(u64 start)
-{
-}
-static inline void spin_time_accum_spinning(u64 start)
-{
-}
 static inline void spin_time_accum_blocked(u64 start)
 {
 }
 #endif  /* CONFIG_XEN_DEBUG_FS */
 
-/*
- * Size struct xen_spinlock so it's the same as arch_spinlock_t.
- */
-#if NR_CPUS < 256
-typedef u8 xen_spinners_t;
-# define inc_spinners(xl) \
-	asm(LOCK_PREFIX " incb %0" : "+m" ((xl)->spinners) : : "memory");
-# define dec_spinners(xl) \
-	asm(LOCK_PREFIX " decb %0" : "+m" ((xl)->spinners) : : "memory");
-#else
-typedef u16 xen_spinners_t;
-# define inc_spinners(xl) \
-	asm(LOCK_PREFIX " incw %0" : "+m" ((xl)->spinners) : : "memory");
-# define dec_spinners(xl) \
-	asm(LOCK_PREFIX " decw %0" : "+m" ((xl)->spinners) : : "memory");
-#endif
-
-struct xen_spinlock {
-	unsigned char lock;		/* 0 -> free; 1 -> locked */
-	xen_spinners_t spinners;	/* count of waiting cpus */
+struct xen_lock_waiting {
+	struct arch_spinlock *lock;
+	__ticket_t want;
 };
 
-static int xen_spin_is_locked(struct arch_spinlock *lock)
-{
-	struct xen_spinlock *xl = (struct xen_spinlock *)lock;
-
-	return xl->lock != 0;
-}
-
-static int xen_spin_is_contended(struct arch_spinlock *lock)
-{
-	struct xen_spinlock *xl = (struct xen_spinlock *)lock;
-
-	/* Not strictly true; this is only the count of contended
-	   lock-takers entering the slow path. */
-	return xl->spinners != 0;
-}
-
-static int xen_spin_trylock(struct arch_spinlock *lock)
-{
-	struct xen_spinlock *xl = (struct xen_spinlock *)lock;
-	u8 old = 1;
-
-	asm("xchgb %b0,%1"
-	    : "+q" (old), "+m" (xl->lock) : : "memory");
-
-	return old == 0;
-}
-
-static DEFINE_PER_CPU(char *, irq_name);
 static DEFINE_PER_CPU(int, lock_kicker_irq) = -1;
-static DEFINE_PER_CPU(struct xen_spinlock *, lock_spinners);
-
-/*
- * Mark a cpu as interested in a lock.  Returns the CPU's previous
- * lock of interest, in case we got preempted by an interrupt.
- */
-static inline struct xen_spinlock *spinning_lock(struct xen_spinlock *xl)
-{
-	struct xen_spinlock *prev;
-
-	prev = __this_cpu_read(lock_spinners);
-	__this_cpu_write(lock_spinners, xl);
-
-	wmb();			/* set lock of interest before count */
-
-	inc_spinners(xl);
-
-	return prev;
-}
-
-/*
- * Mark a cpu as no longer interested in a lock.  Restores previous
- * lock of interest (NULL for none).
- */
-static inline void unspinning_lock(struct xen_spinlock *xl, struct xen_spinlock *prev)
-{
-	dec_spinners(xl);
-	wmb();			/* decrement count before restoring lock */
-	__this_cpu_write(lock_spinners, prev);
-}
+static DEFINE_PER_CPU(char *, irq_name);
+static DEFINE_PER_CPU(struct xen_lock_waiting, lock_waiting);
+static cpumask_t waiting_cpus;
 
-static noinline int xen_spin_lock_slow(struct arch_spinlock *lock, bool irq_enable)
+static bool xen_pvspin = true;
+static void xen_lock_spinning(struct arch_spinlock *lock, __ticket_t want)
 {
-	struct xen_spinlock *xl = (struct xen_spinlock *)lock;
-	struct xen_spinlock *prev;
 	int irq = __this_cpu_read(lock_kicker_irq);
-	int ret;
+	struct xen_lock_waiting *w = &__get_cpu_var(lock_waiting);
+	int cpu = smp_processor_id();
 	u64 start;
+	unsigned long flags;
 
 	/* If kicker interrupts not initialized yet, just spin */
 	if (irq == -1)
-		return 0;
+		return;
 
 	start = spin_time_start();
 
-	/* announce we're spinning */
-	prev = spinning_lock(xl);
+	/*
+	 * Make sure an interrupt handler can't upset things in a
+	 * partially setup state.
+	 */
+	local_irq_save(flags);
+	/*
+	 * We don't really care if we're overwriting some other
+	 * (lock,want) pair, as that would mean that we're currently
+	 * in an interrupt context, and the outer context had
+	 * interrupts enabled.  That has already kicked the VCPU out
+	 * of xen_poll_irq(), so it will just return spuriously and
+	 * retry with newly setup (lock,want).
+	 *
+	 * The ordering protocol on this is that the "lock" pointer
+	 * may only be set non-NULL if the "want" ticket is correct.
+	 * If we're updating "want", we must first clear "lock".
+	 */
+	w->lock = NULL;
+	smp_wmb();
+	w->want = want;
+	smp_wmb();
+	w->lock = lock;
 
-	ADD_STATS(taken_slow, 1);
-	ADD_STATS(taken_slow_nested, prev != NULL);
+	/* This uses set_bit, which atomic and therefore a barrier */
+	cpumask_set_cpu(cpu, &waiting_cpus);
+	add_stats(TAKEN_SLOW, 1);
 
-	do {
-		unsigned long flags;
+	/* clear pending */
+	xen_clear_irq_pending(irq);
 
-		/* clear pending */
-		xen_clear_irq_pending(irq);
+	/* Only check lock once pending cleared */
+	barrier();
 
-		/* check again make sure it didn't become free while
-		   we weren't looking  */
-		ret = xen_spin_trylock(lock);
-		if (ret) {
-			ADD_STATS(taken_slow_pickup, 1);
+	/*
+	 * Mark entry to slowpath before doing the pickup test to make
+	 * sure we don't deadlock with an unlocker.
+	 */
+	__ticket_enter_slowpath(lock);
 
-			/*
-			 * If we interrupted another spinlock while it
-			 * was blocking, make sure it doesn't block
-			 * without rechecking the lock.
-			 */
-			if (prev != NULL)
-				xen_set_irq_pending(irq);
-			goto out;
-		}
+	/*
+	 * check again make sure it didn't become free while
+	 * we weren't looking
+	 */
+	if (ACCESS_ONCE(lock->tickets.head) == want) {
+		add_stats(TAKEN_SLOW_PICKUP, 1);
+		goto out;
+	}
 
-		flags = arch_local_save_flags();
-		if (irq_enable) {
-			ADD_STATS(taken_slow_irqenable, 1);
-			raw_local_irq_enable();
-		}
+	/* Allow interrupts while blocked */
+	local_irq_restore(flags);
 
-		/*
-		 * Block until irq becomes pending.  If we're
-		 * interrupted at this point (after the trylock but
-		 * before entering the block), then the nested lock
-		 * handler guarantees that the irq will be left
-		 * pending if there's any chance the lock became free;
-		 * xen_poll_irq() returns immediately if the irq is
-		 * pending.
-		 */
-		xen_poll_irq(irq);
+	/*
+	 * If an interrupt happens here, it will leave the wakeup irq
+	 * pending, which will cause xen_poll_irq() to return
+	 * immediately.
+	 */
 
-		raw_local_irq_restore(flags);
+	/* Block until irq becomes pending (or perhaps a spurious wakeup) */
+	xen_poll_irq(irq);
+	add_stats(TAKEN_SLOW_SPURIOUS, !xen_test_irq_pending(irq));
 
-		ADD_STATS(taken_slow_spurious, !xen_test_irq_pending(irq));
-	} while (!xen_test_irq_pending(irq)); /* check for spurious wakeups */
+	local_irq_save(flags);
 
 	kstat_incr_irqs_this_cpu(irq, irq_to_desc(irq));
-
 out:
-	unspinning_lock(xl, prev);
-	spin_time_accum_blocked(start);
-
-	return ret;
-}
-
-static inline void __xen_spin_lock(struct arch_spinlock *lock, bool irq_enable)
-{
-	struct xen_spinlock *xl = (struct xen_spinlock *)lock;
-	unsigned timeout;
-	u8 oldval;
-	u64 start_spin;
-
-	ADD_STATS(taken, 1);
-
-	start_spin = spin_time_start();
-
-	do {
-		u64 start_spin_fast = spin_time_start();
+	cpumask_clear_cpu(cpu, &waiting_cpus);
+	w->lock = NULL;
 
-		timeout = TIMEOUT;
+	local_irq_restore(flags);
 
-		asm("1: xchgb %1,%0\n"
-		    "   testb %1,%1\n"
-		    "   jz 3f\n"
-		    "2: rep;nop\n"
-		    "   cmpb $0,%0\n"
-		    "   je 1b\n"
-		    "   dec %2\n"
-		    "   jnz 2b\n"
-		    "3:\n"
-		    : "+m" (xl->lock), "=q" (oldval), "+r" (timeout)
-		    : "1" (1)
-		    : "memory");
-
-		spin_time_accum_spinning(start_spin_fast);
-
-	} while (unlikely(oldval != 0 &&
-			  (TIMEOUT == ~0 || !xen_spin_lock_slow(lock, irq_enable))));
-
-	spin_time_accum_total(start_spin);
-}
-
-static void xen_spin_lock(struct arch_spinlock *lock)
-{
-	__xen_spin_lock(lock, false);
-}
-
-static void xen_spin_lock_flags(struct arch_spinlock *lock, unsigned long flags)
-{
-	__xen_spin_lock(lock, !raw_irqs_disabled_flags(flags));
+	spin_time_accum_blocked(start);
 }
+PV_CALLEE_SAVE_REGS_THUNK(xen_lock_spinning);
 
-static noinline void xen_spin_unlock_slow(struct xen_spinlock *xl)
+static void xen_unlock_kick(struct arch_spinlock *lock, __ticket_t next)
 {
 	int cpu;
 
-	ADD_STATS(released_slow, 1);
+	add_stats(RELEASED_SLOW, 1);
 
-	for_each_online_cpu(cpu) {
-		/* XXX should mix up next cpu selection */
-		if (per_cpu(lock_spinners, cpu) == xl) {
-			ADD_STATS(released_slow_kicked, 1);
+	for_each_cpu(cpu, &waiting_cpus) {
+		const struct xen_lock_waiting *w = &per_cpu(lock_waiting, cpu);
+
+		/* Make sure we read lock before want */
+		if (ACCESS_ONCE(w->lock) == lock &&
+		    ACCESS_ONCE(w->want) == next) {
+			add_stats(RELEASED_SLOW_KICKED, 1);
 			xen_send_IPI_one(cpu, XEN_SPIN_UNLOCK_VECTOR);
+			break;
 		}
 	}
 }
 
-static void xen_spin_unlock(struct arch_spinlock *lock)
-{
-	struct xen_spinlock *xl = (struct xen_spinlock *)lock;
-
-	ADD_STATS(released, 1);
-
-	smp_wmb();		/* make sure no writes get moved after unlock */
-	xl->lock = 0;		/* release lock */
-
-	/*
-	 * Make sure unlock happens before checking for waiting
-	 * spinners.  We need a strong barrier to enforce the
-	 * write-read ordering to different memory locations, as the
-	 * CPU makes no implied guarantees about their ordering.
-	 */
-	mb();
-
-	if (unlikely(xl->spinners))
-		xen_spin_unlock_slow(xl);
-}
-
 static irqreturn_t dummy_handler(int irq, void *dev_id)
 {
 	BUG();
@@ -366,16 +224,12 @@ void xen_init_lock_cpu(int cpu)
 	int irq;
 	char *name;
 
+	if (!xen_pvspin)
+		return;
+
 	WARN(per_cpu(lock_kicker_irq, cpu) >= 0, "spinlock on CPU%d exists on IRQ%d!\n",
 	     cpu, per_cpu(lock_kicker_irq, cpu));
 
-	/*
-	 * See git commit f10cd522c5fbfec9ae3cc01967868c9c2401ed23
-	 * (xen: disable PV spinlocks on HVM)
-	 */
-	if (xen_hvm_domain())
-		return;
-
 	name = kasprintf(GFP_KERNEL, "spinlock%d", cpu);
 	irq = bind_ipi_to_irqhandler(XEN_SPIN_UNLOCK_VECTOR,
 				     cpu,
@@ -395,11 +249,7 @@ void xen_init_lock_cpu(int cpu)
 
 void xen_uninit_lock_cpu(int cpu)
 {
-	/*
-	 * See git commit f10cd522c5fbfec9ae3cc01967868c9c2401ed23
-	 * (xen: disable PV spinlocks on HVM)
-	 */
-	if (xen_hvm_domain())
+	if (!xen_pvspin)
 		return;
 
 	unbind_from_irqhandler(per_cpu(lock_kicker_irq, cpu), NULL);
@@ -408,24 +258,49 @@ void xen_uninit_lock_cpu(int cpu)
 	per_cpu(irq_name, cpu) = NULL;
 }
 
+
+/*
+ * Our init of PV spinlocks is split in two init functions due to us
+ * using paravirt patching and jump labels patching and having to do
+ * all of this before SMP code is invoked.
+ *
+ * The paravirt patching needs to be done _before_ the alternative asm code
+ * is started, otherwise we would not patch the core kernel code.
+ */
 void __init xen_init_spinlocks(void)
 {
-	/*
-	 * See git commit f10cd522c5fbfec9ae3cc01967868c9c2401ed23
-	 * (xen: disable PV spinlocks on HVM)
-	 */
-	if (xen_hvm_domain())
+
+	if (!xen_pvspin) {
+		printk(KERN_DEBUG "xen: PV spinlocks disabled\n");
 		return;
+	}
+
+	pv_lock_ops.lock_spinning = PV_CALLEE_SAVE(xen_lock_spinning);
+	pv_lock_ops.unlock_kick = xen_unlock_kick;
+}
+
+/*
+ * While the jump_label init code needs to happend _after_ the jump labels are
+ * enabled and before SMP is started. Hence we use pre-SMP initcall level
+ * init. We cannot do it in xen_init_spinlocks as that is done before
+ * jump labels are activated.
+ */
+static __init int xen_init_spinlocks_jump(void)
+{
+	if (!xen_pvspin)
+		return 0;
 
-	BUILD_BUG_ON(sizeof(struct xen_spinlock) > sizeof(arch_spinlock_t));
+	static_key_slow_inc(&paravirt_ticketlocks_enabled);
+	return 0;
+}
+early_initcall(xen_init_spinlocks_jump);
 
-	pv_lock_ops.spin_is_locked = xen_spin_is_locked;
-	pv_lock_ops.spin_is_contended = xen_spin_is_contended;
-	pv_lock_ops.spin_lock = xen_spin_lock;
-	pv_lock_ops.spin_lock_flags = xen_spin_lock_flags;
-	pv_lock_ops.spin_trylock = xen_spin_trylock;
-	pv_lock_ops.spin_unlock = xen_spin_unlock;
+static __init int xen_parse_nopvspin(char *arg)
+{
+	xen_pvspin = false;
+	return 0;
 }
+early_param("xen_nopvspin", xen_parse_nopvspin);
 
 #ifdef CONFIG_XEN_DEBUG_FS
 
@@ -438,41 +313,28 @@ static int __init xen_spinlock_debugfs(void)
 	if (d_xen == NULL)
 		return -ENOMEM;
 
+	if (!xen_pvspin)
+		return 0;
+
 	d_spin_debug = debugfs_create_dir("spinlocks", d_xen);
 
 	debugfs_create_u8("zero_stats", 0644, d_spin_debug, &zero_stats);
 
-	debugfs_create_u32("timeout", 0644, d_spin_debug, &lock_timeout);
-
-	debugfs_create_u64("taken", 0444, d_spin_debug, &spinlock_stats.taken);
 	debugfs_create_u32("taken_slow", 0444, d_spin_debug,
-			   &spinlock_stats.taken_slow);
-	debugfs_create_u32("taken_slow_nested", 0444, d_spin_debug,
-			   &spinlock_stats.taken_slow_nested);
+			   &spinlock_stats.contention_stats[TAKEN_SLOW]);
 	debugfs_create_u32("taken_slow_pickup", 0444, d_spin_debug,
-			   &spinlock_stats.taken_slow_pickup);
+			   &spinlock_stats.contention_stats[TAKEN_SLOW_PICKUP]);
 	debugfs_create_u32("taken_slow_spurious", 0444, d_spin_debug,
-			   &spinlock_stats.taken_slow_spurious);
-	debugfs_create_u32("taken_slow_irqenable", 0444, d_spin_debug,
-			   &spinlock_stats.taken_slow_irqenable);
+			   &spinlock_stats.contention_stats[TAKEN_SLOW_SPURIOUS]);
 
-	debugfs_create_u64("released", 0444, d_spin_debug, &spinlock_stats.released);
 	debugfs_create_u32("released_slow", 0444, d_spin_debug,
-			   &spinlock_stats.released_slow);
+			   &spinlock_stats.contention_stats[RELEASED_SLOW]);
 	debugfs_create_u32("released_slow_kicked", 0444, d_spin_debug,
-			   &spinlock_stats.released_slow_kicked);
+			   &spinlock_stats.contention_stats[RELEASED_SLOW_KICKED]);
 
-	debugfs_create_u64("time_spinning", 0444, d_spin_debug,
-			   &spinlock_stats.time_spinning);
 	debugfs_create_u64("time_blocked", 0444, d_spin_debug,
 			   &spinlock_stats.time_blocked);
-	debugfs_create_u64("time_total", 0444, d_spin_debug,
-			   &spinlock_stats.time_total);
 
-	debugfs_create_u32_array("histo_total", 0444, d_spin_debug,
-				spinlock_stats.histo_spin_total, HISTO_BUCKETS + 1);
-	debugfs_create_u32_array("histo_spinning", 0444, d_spin_debug,
-				spinlock_stats.histo_spin_spinning, HISTO_BUCKETS + 1);
 	debugfs_create_u32_array("histo_blocked", 0444, d_spin_debug,
 				spinlock_stats.histo_spin_blocked, HISTO_BUCKETS + 1);
 
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index 86782c5d7e2a..95f8c6142328 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -105,9 +105,9 @@ static inline void __init xen_init_apic(void)
 /* Declare an asm function, along with symbols needed to make it
    inlineable */
 #define DECL_ASM(ret, name, ...)		\
-	ret name(__VA_ARGS__);			\
-	extern char name##_end[];		\
-	extern char name##_reloc[]		\
+	__visible ret name(__VA_ARGS__);	\
+	extern char name##_end[] __visible;	\
+	extern char name##_reloc[] __visible
 
 DECL_ASM(void, xen_irq_enable_direct, void);
 DECL_ASM(void, xen_irq_disable_direct, void);
@@ -115,11 +115,11 @@ DECL_ASM(unsigned long, xen_save_fl_direct, void);
 DECL_ASM(void, xen_restore_fl_direct, unsigned long);
 
 /* These are not functions, and cannot be called normally */
-void xen_iret(void);
-void xen_sysexit(void);
-void xen_sysret32(void);
-void xen_sysret64(void);
-void xen_adjust_exception_frame(void);
+__visible void xen_iret(void);
+__visible void xen_sysexit(void);
+__visible void xen_sysret32(void);
+__visible void xen_sysret64(void);
+__visible void xen_adjust_exception_frame(void);
 
 extern int xen_panic_handler_init(void);
 
diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig
index 7ea6451a3a33..8d24dcb7cdac 100644
--- a/arch/xtensa/Kconfig
+++ b/arch/xtensa/Kconfig
@@ -7,7 +7,6 @@ config XTENSA
 	select HAVE_IDE
 	select GENERIC_ATOMIC64
 	select GENERIC_CLOCKEVENTS
-	select HAVE_GENERIC_HARDIRQS
 	select VIRT_TO_BUS
 	select GENERIC_IRQ_SHOW
 	select GENERIC_CPU_DEVICES
diff --git a/arch/xtensa/Makefile b/arch/xtensa/Makefile
index 136224b74d4f..81250ece3062 100644
--- a/arch/xtensa/Makefile
+++ b/arch/xtensa/Makefile
@@ -55,10 +55,10 @@ ifneq ($(CONFIG_LD_NO_RELAX),)
 LDFLAGS := --no-relax
 endif
 
-ifeq ($(shell echo -e __XTENSA_EB__ | $(CC) -E - | grep -v "\#"),1)
+ifeq ($(shell echo __XTENSA_EB__ | $(CC) -E - | grep -v "\#"),1)
 CHECKFLAGS += -D__XTENSA_EB__
 endif
-ifeq ($(shell echo -e __XTENSA_EL__ | $(CC) -E - | grep -v "\#"),1)
+ifeq ($(shell echo __XTENSA_EL__ | $(CC) -E - | grep -v "\#"),1)
 CHECKFLAGS += -D__XTENSA_EL__
 endif
 
diff --git a/arch/xtensa/boot/Makefile b/arch/xtensa/boot/Makefile
index 64ffc4b53df6..ca20a892021b 100644
--- a/arch/xtensa/boot/Makefile
+++ b/arch/xtensa/boot/Makefile
@@ -12,7 +12,7 @@
 KBUILD_CFLAGS	+= -fno-builtin -Iarch/$(ARCH)/boot/include
 HOSTFLAGS	+= -Iarch/$(ARCH)/boot/include
 
-BIG_ENDIAN	:= $(shell echo -e __XTENSA_EB__ | $(CC) -E - | grep -v "\#")
+BIG_ENDIAN	:= $(shell echo __XTENSA_EB__ | $(CC) -E - | grep -v "\#")
 
 export ccflags-y
 export BIG_ENDIAN
diff --git a/arch/xtensa/configs/common_defconfig b/arch/xtensa/configs/common_defconfig
index a182a4e6d688..f6000fe05119 100644
--- a/arch/xtensa/configs/common_defconfig
+++ b/arch/xtensa/configs/common_defconfig
@@ -8,7 +8,6 @@ CONFIG_XTENSA=y
 # CONFIG_UID16 is not set
 CONFIG_RWSEM_XCHGADD_ALGORITHM=y
 CONFIG_HAVE_DEC_LOCK=y
-CONFIG_GENERIC_HARDIRQS=y
 
 #
 # Code maturity level options
diff --git a/arch/xtensa/configs/iss_defconfig b/arch/xtensa/configs/iss_defconfig
index 77c52f80187a..4f233204faf9 100644
--- a/arch/xtensa/configs/iss_defconfig
+++ b/arch/xtensa/configs/iss_defconfig
@@ -9,7 +9,6 @@ CONFIG_XTENSA=y
 CONFIG_RWSEM_XCHGADD_ALGORITHM=y
 CONFIG_GENERIC_FIND_NEXT_BIT=y
 CONFIG_GENERIC_HWEIGHT=y
-CONFIG_GENERIC_HARDIRQS=y
 # CONFIG_ARCH_HAS_ILOG2_U32 is not set
 # CONFIG_ARCH_HAS_ILOG2_U64 is not set
 CONFIG_NO_IOPORT=y
diff --git a/arch/xtensa/configs/s6105_defconfig b/arch/xtensa/configs/s6105_defconfig
index 4799c6a526b5..d929f77a0360 100644
--- a/arch/xtensa/configs/s6105_defconfig
+++ b/arch/xtensa/configs/s6105_defconfig
@@ -9,7 +9,6 @@ CONFIG_XTENSA=y
 CONFIG_RWSEM_XCHGADD_ALGORITHM=y
 CONFIG_GENERIC_FIND_NEXT_BIT=y
 CONFIG_GENERIC_HWEIGHT=y
-CONFIG_GENERIC_HARDIRQS=y
 # CONFIG_ARCH_HAS_ILOG2_U32 is not set
 # CONFIG_ARCH_HAS_ILOG2_U64 is not set
 CONFIG_NO_IOPORT=y
diff --git a/arch/xtensa/include/asm/regs.h b/arch/xtensa/include/asm/regs.h
index b24de6717020..4ba9f516b0e2 100644
--- a/arch/xtensa/include/asm/regs.h
+++ b/arch/xtensa/include/asm/regs.h
@@ -82,6 +82,7 @@
 #define PS_CALLINC_SHIFT	16
 #define PS_CALLINC_MASK		0x00030000
 #define PS_OWB_SHIFT		8
+#define PS_OWB_WIDTH		4
 #define PS_OWB_MASK		0x00000F00
 #define PS_RING_SHIFT		6
 #define PS_RING_MASK		0x000000C0
diff --git a/arch/xtensa/include/asm/timex.h b/arch/xtensa/include/asm/timex.h
index 69f901713fb6..27fa3c170662 100644
--- a/arch/xtensa/include/asm/timex.h
+++ b/arch/xtensa/include/asm/timex.h
@@ -35,13 +35,7 @@
 # error "Bad timer number for Linux configurations!"
 #endif
 
-#ifdef CONFIG_XTENSA_CALIBRATE_CCOUNT
 extern unsigned long ccount_freq;
-#define CCOUNT_PER_JIFFY (ccount_freq / HZ)
-#else
-#define CCOUNT_PER_JIFFY (CONFIG_XTENSA_CPU_CLOCK*(1000000UL/HZ))
-#endif
-
 
 typedef unsigned long long cycles_t;
 
diff --git a/arch/xtensa/kernel/align.S b/arch/xtensa/kernel/align.S
index aa2e87b8566a..d4cef6039a5c 100644
--- a/arch/xtensa/kernel/align.S
+++ b/arch/xtensa/kernel/align.S
@@ -146,9 +146,9 @@
  *   a0:	trashed, original value saved on stack (PT_AREG0)
  *   a1:	a1
  *   a2:	new stack pointer, original in DEPC
- *   a3:	dispatch table
+ *   a3:	a3
  *   depc:	a2, original value saved on stack (PT_DEPC)
- *   excsave_1:	a3
+ *   excsave_1:	dispatch table
  *
  *   PT_DEPC >= VALID_DOUBLE_EXCEPTION_ADDRESS: double exception, DEPC
  *	     <  VALID_DOUBLE_EXCEPTION_ADDRESS: regular exception
@@ -171,7 +171,6 @@ ENTRY(fast_unaligned)
 	s32i	a8, a2, PT_AREG8
 
 	rsr	a0, depc
-	xsr	a3, excsave1
 	s32i	a0, a2, PT_AREG2
 	s32i	a3, a2, PT_AREG3
 
diff --git a/arch/xtensa/kernel/coprocessor.S b/arch/xtensa/kernel/coprocessor.S
index 647657484866..a482df5df2b2 100644
--- a/arch/xtensa/kernel/coprocessor.S
+++ b/arch/xtensa/kernel/coprocessor.S
@@ -32,9 +32,9 @@
  *   a0:	trashed, original value saved on stack (PT_AREG0)
  *   a1:	a1
  *   a2:	new stack pointer, original in DEPC
- *   a3:	dispatch table
+ *   a3:	a3
  *   depc:	a2, original value saved on stack (PT_DEPC)
- *   excsave_1:	a3
+ *   excsave_1:	dispatch table
  *
  *   PT_DEPC >= VALID_DOUBLE_EXCEPTION_ADDRESS: double exception, DEPC
  *	     <  VALID_DOUBLE_EXCEPTION_ADDRESS: regular exception
@@ -225,9 +225,9 @@ ENDPROC(coprocessor_restore)
  *   a0:	trashed, original value saved on stack (PT_AREG0)
  *   a1:	a1
  *   a2:	new stack pointer, original in DEPC
- *   a3:	dispatch table
+ *   a3:	a3
  *   depc:	a2, original value saved on stack (PT_DEPC)
- *   excsave_1:	a3
+ *   excsave_1:	dispatch table
  *
  *   PT_DEPC >= VALID_DOUBLE_EXCEPTION_ADDRESS: double exception, DEPC
  *	     <  VALID_DOUBLE_EXCEPTION_ADDRESS: regular exception
@@ -245,7 +245,6 @@ ENTRY(fast_coprocessor)
 
 	/* Save remaining registers a1-a3 and SAR */
 
-	xsr	a3, excsave1
 	s32i	a3, a2, PT_AREG3
 	rsr	a3, sar
 	s32i	a1, a2, PT_AREG1
diff --git a/arch/xtensa/kernel/entry.S b/arch/xtensa/kernel/entry.S
index 9298742f0fd0..de1dfa18d0a1 100644
--- a/arch/xtensa/kernel/entry.S
+++ b/arch/xtensa/kernel/entry.S
@@ -31,8 +31,6 @@
 /* Unimplemented features. */
 
 #undef KERNEL_STACK_OVERFLOW_CHECK
-#undef PREEMPTIBLE_KERNEL
-#undef ALLOCA_EXCEPTION_IN_IRAM
 
 /* Not well tested.
  *
@@ -92,9 +90,9 @@
  *   a0:	trashed, original value saved on stack (PT_AREG0)
  *   a1:	a1
  *   a2:	new stack pointer, original value in depc
- *   a3:	dispatch table
+ *   a3:	a3
  *   depc:	a2, original value saved on stack (PT_DEPC)
- *   excsave1:	a3
+ *   excsave1:	dispatch table
  *
  *   PT_DEPC >= VALID_DOUBLE_EXCEPTION_ADDRESS: double exception, DEPC
  *	     <  VALID_DOUBLE_EXCEPTION_ADDRESS: regular exception
@@ -110,9 +108,8 @@
 
 ENTRY(user_exception)
 
-	/* Save a2, a3, and depc, restore excsave_1 and set SP. */
+	/* Save a1, a2, a3, and set SP. */
 
-	xsr	a3, excsave1
 	rsr	a0, depc
 	s32i	a1, a2, PT_AREG1
 	s32i	a0, a2, PT_AREG2
@@ -238,9 +235,9 @@ ENDPROC(user_exception)
  *   a0:	trashed, original value saved on stack (PT_AREG0)
  *   a1:	a1
  *   a2:	new stack pointer, original in DEPC
- *   a3:	dispatch table
+ *   a3:	a3
  *   depc:	a2, original value saved on stack (PT_DEPC)
- *   excsave_1:	a3
+ *   excsave_1:	dispatch table
  *
  *   PT_DEPC >= VALID_DOUBLE_EXCEPTION_ADDRESS: double exception, DEPC
  *	     <  VALID_DOUBLE_EXCEPTION_ADDRESS: regular exception
@@ -256,9 +253,8 @@ ENDPROC(user_exception)
 
 ENTRY(kernel_exception)
 
-	/* Save a0, a2, a3, DEPC and set SP. */
+	/* Save a1, a2, a3, and set SP. */
 
-	xsr	a3, excsave1		# restore a3, excsave_1
 	rsr	a0, depc		# get a2
 	s32i	a1, a2, PT_AREG1
 	s32i	a0, a2, PT_AREG2
@@ -409,7 +405,7 @@ common_exception:
 	 * exception handler and call the exception handler.
 	 */
 
-	movi	a4, exc_table
+	rsr	a4, excsave1
 	mov	a6, a1			# pass stack frame
 	mov	a7, a0			# pass EXCCAUSE
 	addx4	a4, a0, a4
@@ -423,28 +419,15 @@ common_exception:
 	.global common_exception_return
 common_exception_return:
 
-#ifdef CONFIG_TRACE_IRQFLAGS
-	l32i	a4, a1, PT_DEPC
-	/* Double exception means we came here with an exception
-	 * while PS.EXCM was set, i.e. interrupts disabled.
-	 */
-	bgeui	a4, VALID_DOUBLE_EXCEPTION_ADDRESS, 1f
-	l32i	a4, a1, PT_EXCCAUSE
-	bnei	a4, EXCCAUSE_LEVEL1_INTERRUPT, 1f
-	/* We came here with an interrupt means interrupts were enabled
-	 * and we'll reenable them on return.
-	 */
-	movi	a4, trace_hardirqs_on
-	callx4	a4
 1:
-#endif
+	rsil	a2, LOCKLEVEL
 
 	/* Jump if we are returning from kernel exceptions. */
 
-1:	l32i	a3, a1, PT_PS
-	_bbci.l	a3, PS_UM_BIT, 4f
-
-	rsil	a2, 0
+	l32i	a3, a1, PT_PS
+	GET_THREAD_INFO(a2, a1)
+	l32i	a4, a2, TI_FLAGS
+	_bbci.l	a3, PS_UM_BIT, 6f
 
 	/* Specific to a user exception exit:
 	 * We need to check some flags for signal handling and rescheduling,
@@ -453,9 +436,6 @@ common_exception_return:
 	 * Note that we don't disable interrupts here. 
 	 */
 
-	GET_THREAD_INFO(a2,a1)
-	l32i	a4, a2, TI_FLAGS
-
 	_bbsi.l	a4, TIF_NEED_RESCHED, 3f
 	_bbsi.l	a4, TIF_NOTIFY_RESUME, 2f
 	_bbci.l	a4, TIF_SIGPENDING, 5f
@@ -465,6 +445,7 @@ common_exception_return:
 
 	/* Call do_signal() */
 
+	rsil	a2, 0
 	movi	a4, do_notify_resume	# int do_notify_resume(struct pt_regs*)
 	mov	a6, a1
 	callx4	a4
@@ -472,10 +453,24 @@ common_exception_return:
 
 3:	/* Reschedule */
 
+	rsil	a2, 0
 	movi	a4, schedule	# void schedule (void)
 	callx4	a4
 	j	1b
 
+#ifdef CONFIG_PREEMPT
+6:
+	_bbci.l	a4, TIF_NEED_RESCHED, 4f
+
+	/* Check current_thread_info->preempt_count */
+
+	l32i	a4, a2, TI_PRE_COUNT
+	bnez	a4, 4f
+	movi	a4, preempt_schedule_irq
+	callx4	a4
+	j	1b
+#endif
+
 5:
 #ifdef CONFIG_DEBUG_TLB_SANITY
 	l32i	a4, a1, PT_DEPC
@@ -483,7 +478,24 @@ common_exception_return:
 	movi	a4, check_tlb_sanity
 	callx4	a4
 #endif
-4:	/* Restore optional registers. */
+6:
+4:
+#ifdef CONFIG_TRACE_IRQFLAGS
+	l32i	a4, a1, PT_DEPC
+	/* Double exception means we came here with an exception
+	 * while PS.EXCM was set, i.e. interrupts disabled.
+	 */
+	bgeui	a4, VALID_DOUBLE_EXCEPTION_ADDRESS, 1f
+	l32i	a4, a1, PT_EXCCAUSE
+	bnei	a4, EXCCAUSE_LEVEL1_INTERRUPT, 1f
+	/* We came here with an interrupt means interrupts were enabled
+	 * and we'll reenable them on return.
+	 */
+	movi	a4, trace_hardirqs_on
+	callx4	a4
+1:
+#endif
+	/* Restore optional registers. */
 
 	load_xtregs_opt a1 a2 a4 a5 a6 a7 PT_XTREGS_OPT
 
@@ -570,29 +582,6 @@ user_exception_exit:
 
 kernel_exception_exit:
 
-#ifdef PREEMPTIBLE_KERNEL
-
-#ifdef CONFIG_PREEMPT
-
-	/*
-	 * Note: We've just returned from a call4, so we have
-	 * at least 4 addt'l regs.
-	 */
-
-	/* Check current_thread_info->preempt_count */
-
-	GET_THREAD_INFO(a2)
-	l32i	a3, a2, TI_PREEMPT
-	bnez	a3, 1f
-
-	l32i	a2, a2, TI_FLAGS
-
-1:
-
-#endif
-
-#endif
-
 	/* Check if we have to do a movsp.
 	 *
 	 * We only have to do a movsp if the previous window-frame has
@@ -829,176 +818,63 @@ ENDPROC(unrecoverable_exception)
  *
  *  The ALLOCA handler is entered when user code executes the MOVSP
  *  instruction and the caller's frame is not in the register file.
- *  In this case, the caller frame's a0..a3 are on the stack just
- *  below sp (a1), and this handler moves them.
  *
- *  For "MOVSP <ar>,<as>" without destination register a1, this routine
- *  simply moves the value from <as> to <ar> without moving the save area.
+ * This algorithm was taken from the Ross Morley's RTOS Porting Layer:
+ *
+ *    /home/ross/rtos/porting/XtensaRTOS-PortingLayer-20090507/xtensa_vectors.S
+ *
+ * It leverages the existing window spill/fill routines and their support for
+ * double exceptions. The 'movsp' instruction will only cause an exception if
+ * the next window needs to be loaded. In fact this ALLOCA exception may be
+ * replaced at some point by changing the hardware to do a underflow exception
+ * of the proper size instead.
+ *
+ * This algorithm simply backs out the register changes started by the user
+ * excpetion handler, makes it appear that we have started a window underflow
+ * by rotating the window back and then setting the old window base (OWB) in
+ * the 'ps' register with the rolled back window base. The 'movsp' instruction
+ * will be re-executed and this time since the next window frames is in the
+ * active AR registers it won't cause an exception.
+ *
+ * If the WindowUnderflow code gets a TLB miss the page will get mapped
+ * the the partial windeowUnderflow will be handeled in the double exception
+ * handler.
  *
  * Entry condition:
  *
  *   a0:	trashed, original value saved on stack (PT_AREG0)
  *   a1:	a1
  *   a2:	new stack pointer, original in DEPC
- *   a3:	dispatch table
+ *   a3:	a3
  *   depc:	a2, original value saved on stack (PT_DEPC)
- *   excsave_1:	a3
+ *   excsave_1:	dispatch table
  *
  *   PT_DEPC >= VALID_DOUBLE_EXCEPTION_ADDRESS: double exception, DEPC
  *	     <  VALID_DOUBLE_EXCEPTION_ADDRESS: regular exception
  */
 
-#if XCHAL_HAVE_BE
-#define _EXTUI_MOVSP_SRC(ar)	extui ar, ar, 4, 4
-#define _EXTUI_MOVSP_DST(ar)	extui ar, ar, 0, 4
-#else
-#define _EXTUI_MOVSP_SRC(ar)	extui ar, ar, 0, 4
-#define _EXTUI_MOVSP_DST(ar)	extui ar, ar, 4, 4
-#endif
-
 ENTRY(fast_alloca)
+	rsr	a0, windowbase
+	rotw	-1
+	rsr	a2, ps
+	extui	a3, a2, PS_OWB_SHIFT, PS_OWB_WIDTH
+	xor	a3, a3, a4
+	l32i	a4, a6, PT_AREG0
+	l32i	a1, a6, PT_DEPC
+	rsr	a6, depc
+	wsr	a1, depc
+	slli	a3, a3, PS_OWB_SHIFT
+	xor	a2, a2, a3
+	wsr	a2, ps
+	rsync
 
-	/* We shouldn't be in a double exception. */
-
-	l32i	a0, a2, PT_DEPC
-	_bgeui	a0, VALID_DOUBLE_EXCEPTION_ADDRESS, .Lunhandled_double
-
-	rsr	a0, depc		# get a2
-	s32i	a4, a2, PT_AREG4	# save a4 and
-	s32i	a0, a2, PT_AREG2	# a2 to stack
-
-	/* Exit critical section. */
-
-	movi	a0, 0
-	s32i	a0, a3, EXC_TABLE_FIXUP
-
-	/* Restore a3, excsave_1 */
-
-	xsr	a3, excsave1		# make sure excsave_1 is valid for dbl.
-	rsr	a4, epc1		# get exception address
-	s32i	a3, a2, PT_AREG3	# save a3 to stack
-
-#ifdef ALLOCA_EXCEPTION_IN_IRAM
-#error	iram not supported
-#else
-	/* Note: l8ui not allowed in IRAM/IROM!! */
-	l8ui	a0, a4, 1		# read as(src) from MOVSP instruction
-#endif
-	movi	a3, .Lmovsp_src
-	_EXTUI_MOVSP_SRC(a0)		# extract source register number
-	addx8	a3, a0, a3
-	jx	a3
-
-.Lunhandled_double:
-	wsr	a0, excsave1
-	movi	a0, unrecoverable_exception
-	callx0	a0
-
-	.align 8
-.Lmovsp_src:
-	l32i	a3, a2, PT_AREG0;	_j 1f;	.align 8
-	mov	a3, a1;			_j 1f;	.align 8
-	l32i	a3, a2, PT_AREG2;	_j 1f;	.align 8
-	l32i	a3, a2, PT_AREG3;	_j 1f;	.align 8
-	l32i	a3, a2, PT_AREG4;	_j 1f;	.align 8
-	mov	a3, a5;			_j 1f;	.align 8
-	mov	a3, a6;			_j 1f;	.align 8
-	mov	a3, a7;			_j 1f;	.align 8
-	mov	a3, a8;			_j 1f;	.align 8
-	mov	a3, a9;			_j 1f;	.align 8
-	mov	a3, a10;		_j 1f;	.align 8
-	mov	a3, a11;		_j 1f;	.align 8
-	mov	a3, a12;		_j 1f;	.align 8
-	mov	a3, a13;		_j 1f;	.align 8
-	mov	a3, a14;		_j 1f;	.align 8
-	mov	a3, a15;		_j 1f;	.align 8
-
-1:
-
-#ifdef ALLOCA_EXCEPTION_IN_IRAM
-#error	iram not supported
-#else
-	l8ui	a0, a4, 0		# read ar(dst) from MOVSP instruction
-#endif
-	addi	a4, a4, 3		# step over movsp
-	_EXTUI_MOVSP_DST(a0)		# extract destination register
-	wsr	a4, epc1		# save new epc_1
-
-	_bnei	a0, 1, 1f		# no 'movsp a1, ax': jump
-
-	/* Move the save area. This implies the use of the L32E
-	 * and S32E instructions, because this move must be done with
-	 * the user's PS.RING privilege levels, not with ring 0
-	 * (kernel's) privileges currently active with PS.EXCM
-	 * set. Note that we have stil registered a fixup routine with the
-	 * double exception vector in case a double exception occurs.
-	 */
-
-	/* a0,a4:avail a1:old user stack a2:exc. stack a3:new user stack. */
-
-	l32e	a0, a1, -16
-	l32e	a4, a1, -12
-	s32e	a0, a3, -16
-	s32e	a4, a3, -12
-	l32e	a0, a1, -8
-	l32e	a4, a1, -4
-	s32e	a0, a3, -8
-	s32e	a4, a3, -4
-
-	/* Restore stack-pointer and all the other saved registers. */
-
-	mov	a1, a3
-
-	l32i	a4, a2, PT_AREG4
-	l32i	a3, a2, PT_AREG3
-	l32i	a0, a2, PT_AREG0
-	l32i	a2, a2, PT_AREG2
-	rfe
-
-	/*  MOVSP <at>,<as>  was invoked with <at> != a1.
-	 *  Because the stack pointer is not being modified,
-	 *  we should be able to just modify the pointer
-	 *  without moving any save area.
-	 *  The processor only traps these occurrences if the
-	 *  caller window isn't live, so unfortunately we can't
-	 *  use this as an alternate trap mechanism.
-	 *  So we just do the move.  This requires that we
-	 *  resolve the destination register, not just the source,
-	 *  so there's some extra work.
-	 *  (PERHAPS NOT REALLY NEEDED, BUT CLEANER...)
-	 */
-
-	/* a0 dst-reg, a1 user-stack, a2 stack, a3 value of src reg. */
-
-1:	movi	a4, .Lmovsp_dst
-	addx8	a4, a0, a4
-	jx	a4
-
-	.align 8
-.Lmovsp_dst:
-	s32i	a3, a2, PT_AREG0;	_j 1f;	.align 8
-	mov	a1, a3;			_j 1f;	.align 8
-	s32i	a3, a2, PT_AREG2;	_j 1f;	.align 8
-	s32i	a3, a2, PT_AREG3;	_j 1f;	.align 8
-	s32i	a3, a2, PT_AREG4;	_j 1f;	.align 8
-	mov	a5, a3;			_j 1f;	.align 8
-	mov	a6, a3;			_j 1f;	.align 8
-	mov	a7, a3;			_j 1f;	.align 8
-	mov	a8, a3;			_j 1f;	.align 8
-	mov	a9, a3;			_j 1f;	.align 8
-	mov	a10, a3;		_j 1f;	.align 8
-	mov	a11, a3;		_j 1f;	.align 8
-	mov	a12, a3;		_j 1f;	.align 8
-	mov	a13, a3;		_j 1f;	.align 8
-	mov	a14, a3;		_j 1f;	.align 8
-	mov	a15, a3;		_j 1f;	.align 8
-
-1:	l32i	a4, a2, PT_AREG4
-	l32i	a3, a2, PT_AREG3
-	l32i	a0, a2, PT_AREG0
-	l32i	a2, a2, PT_AREG2
-	rfe
-
+	_bbci.l	a4, 31, 4f
+	rotw	-1
+	_bbci.l	a8, 30, 8f
+	rotw	-1
+	j	_WindowUnderflow12
+8:	j	_WindowUnderflow8
+4:	j	_WindowUnderflow4
 ENDPROC(fast_alloca)
 
 /*
@@ -1015,9 +891,9 @@ ENDPROC(fast_alloca)
  *   a0:	trashed, original value saved on stack (PT_AREG0)
  *   a1:	a1
  *   a2:	new stack pointer, original in DEPC
- *   a3:	dispatch table
+ *   a3:	a3
  *   depc:	a2, original value saved on stack (PT_DEPC)
- *   excsave_1:	a3
+ *   excsave_1:	dispatch table
  */
 
 ENTRY(fast_syscall_kernel)
@@ -1064,7 +940,6 @@ ENTRY(fast_syscall_unrecoverable)
 
 	l32i    a0, a2, PT_AREG0        # restore a0
 	xsr     a2, depc                # restore a2, depc
-	rsr     a3, excsave1
 
 	wsr     a0, excsave1
 	movi    a0, unrecoverable_exception
@@ -1086,10 +961,10 @@ ENDPROC(fast_syscall_unrecoverable)
  *   a0:	a2 (syscall-nr), original value saved on stack (PT_AREG0)
  *   a1:	a1
  *   a2:	new stack pointer, original in a0 and DEPC
- *   a3:	dispatch table, original in excsave_1
+ *   a3:	a3
  *   a4..a15:	unchanged
  *   depc:	a2, original value saved on stack (PT_DEPC)
- *   excsave_1:	a3
+ *   excsave_1:	dispatch table
  *
  *   PT_DEPC >= VALID_DOUBLE_EXCEPTION_ADDRESS: double exception, DEPC
  *	     <  VALID_DOUBLE_EXCEPTION_ADDRESS: regular exception
@@ -1122,8 +997,6 @@ ENDPROC(fast_syscall_unrecoverable)
 
 ENTRY(fast_syscall_xtensa)
 
-	xsr	a3, excsave1		# restore a3, excsave1
-
 	s32i	a7, a2, PT_AREG7	# we need an additional register
 	movi	a7, 4			# sizeof(unsigned int)
 	access_ok a3, a7, a0, a2, .Leac	# a0: scratch reg, a2: sp
@@ -1186,9 +1059,9 @@ ENDPROC(fast_syscall_xtensa)
  *   a0:	trashed, original value saved on stack (PT_AREG0)
  *   a1:	a1
  *   a2:	new stack pointer, original in DEPC
- *   a3:	dispatch table
+ *   a3:	a3
  *   depc:	a2, original value saved on stack (PT_DEPC)
- *   excsave_1:	a3
+ *   excsave_1:	dispatch table
  *
  * Note: We assume the stack pointer is EXC_TABLE_KSTK in the fixup handler.
  */
@@ -1197,15 +1070,16 @@ ENTRY(fast_syscall_spill_registers)
 
 	/* Register a FIXUP handler (pass current wb as a parameter) */
 
+	xsr	a3, excsave1
 	movi	a0, fast_syscall_spill_registers_fixup
 	s32i	a0, a3, EXC_TABLE_FIXUP
 	rsr	a0, windowbase
 	s32i	a0, a3, EXC_TABLE_PARAM
+	xsr	a3, excsave1		# restore a3 and excsave_1
 
-	/* Save a3 and SAR on stack. */
+	/* Save a3, a4 and SAR on stack. */
 
 	rsr	a0, sar
-	xsr	a3, excsave1		# restore a3 and excsave_1
 	s32i	a3, a2, PT_AREG3
 	s32i	a4, a2, PT_AREG4
 	s32i	a0, a2, PT_AREG5	# store SAR to PT_AREG5
@@ -1259,14 +1133,14 @@ fast_syscall_spill_registers_fixup:
 	 * in WS, so that the exception handlers save them to the task stack.
 	 */
 
-	rsr	a3, excsave1	# get spill-mask
+	xsr	a3, excsave1	# get spill-mask
 	slli	a2, a3, 1	# shift left by one
 
 	slli	a3, a2, 32-WSBITS
 	src	a2, a2, a3	# a1 = xxwww1yyxxxwww1yy......
 	wsr	a2, windowstart	# set corrected windowstart
 
-	movi	a3, exc_table
+	rsr	a3, excsave1
 	l32i	a2, a3, EXC_TABLE_DOUBLE_SAVE	# restore a2
 	l32i	a3, a3, EXC_TABLE_PARAM	# original WB (in user task)
 
@@ -1303,7 +1177,7 @@ fast_syscall_spill_registers_fixup:
 
 	/* Jump to the exception handler. */
 
-	movi	a3, exc_table
+	rsr	a3, excsave1
 	rsr	a0, exccause
 	addx4	a0, a0, a3              	# find entry in table
 	l32i	a0, a0, EXC_TABLE_FAST_USER     # load handler
@@ -1320,6 +1194,7 @@ fast_syscall_spill_registers_fixup_return:
 	xsr	a3, excsave1
 	movi	a2, fast_syscall_spill_registers_fixup
 	s32i	a2, a3, EXC_TABLE_FIXUP
+	s32i	a0, a3, EXC_TABLE_DOUBLE_SAVE
 	rsr	a2, windowbase
 	s32i	a2, a3, EXC_TABLE_PARAM
 	l32i	a2, a3, EXC_TABLE_KSTK
@@ -1331,11 +1206,6 @@ fast_syscall_spill_registers_fixup_return:
 	wsr	a3, windowbase
 	rsync
 
-	/* Restore a3 and return. */
-
-	movi	a3, exc_table
-	xsr	a3, excsave1
-
 	rfde
 
 
@@ -1522,9 +1392,8 @@ ENTRY(_spill_registers)
 
 	movi	a0, 0
 
-	movi	a3, exc_table
+	rsr	a3, excsave1
 	l32i	a1, a3, EXC_TABLE_KSTK
-	wsr	a3, excsave1
 
 	movi	a4, (1 << PS_WOE_BIT) | LOCKLEVEL
 	wsr	a4, ps
@@ -1568,9 +1437,9 @@ ENDPROC(fast_second_level_miss_double_kernel)
  *   a0:	trashed, original value saved on stack (PT_AREG0)
  *   a1:	a1
  *   a2:	new stack pointer, original in DEPC
- *   a3:	dispatch table
+ *   a3:	a3
  *   depc:	a2, original value saved on stack (PT_DEPC)
- *   excsave_1:	a3
+ *   excsave_1:	dispatch table
  *
  *   PT_DEPC >= VALID_DOUBLE_EXCEPTION_ADDRESS: double exception, DEPC
  *	     <  VALID_DOUBLE_EXCEPTION_ADDRESS: regular exception
@@ -1578,9 +1447,10 @@ ENDPROC(fast_second_level_miss_double_kernel)
 
 ENTRY(fast_second_level_miss)
 
-	/* Save a1. Note: we don't expect a double exception. */
+	/* Save a1 and a3. Note: we don't expect a double exception. */
 
 	s32i	a1, a2, PT_AREG1
+	s32i	a3, a2, PT_AREG3
 
 	/* We need to map the page of PTEs for the user task.  Find
 	 * the pointer to that page.  Also, it's possible for tsk->mm
@@ -1602,9 +1472,6 @@ ENTRY(fast_second_level_miss)
 	l32i	a0, a1, TASK_MM		# tsk->mm
 	beqz	a0, 9f
 
-
-	/* We deliberately destroy a3 that holds the exception table. */
-
 8:	rsr	a3, excvaddr		# fault address
 	_PGD_OFFSET(a0, a3, a1)
 	l32i	a0, a0, 0		# read pmdval
@@ -1655,7 +1522,7 @@ ENTRY(fast_second_level_miss)
 
 	/* Exit critical section. */
 
-4:	movi	a3, exc_table		# restore a3
+4:	rsr	a3, excsave1
 	movi	a0, 0
 	s32i	a0, a3, EXC_TABLE_FIXUP
 
@@ -1663,8 +1530,8 @@ ENTRY(fast_second_level_miss)
 
 	l32i	a0, a2, PT_AREG0
 	l32i	a1, a2, PT_AREG1
+	l32i	a3, a2, PT_AREG3
 	l32i	a2, a2, PT_DEPC
-	xsr	a3, excsave1
 
 	bgeui	a2, VALID_DOUBLE_EXCEPTION_ADDRESS, 1f
 
@@ -1751,11 +1618,8 @@ ENTRY(fast_second_level_miss)
 
 2:	/* Invalid PGD, default exception handling */
 
-	movi	a3, exc_table
 	rsr	a1, depc
-	xsr	a3, excsave1
 	s32i	a1, a2, PT_AREG2
-	s32i	a3, a2, PT_AREG3
 	mov	a1, a2
 
 	rsr	a2, ps
@@ -1775,9 +1639,9 @@ ENDPROC(fast_second_level_miss)
  *   a0:	trashed, original value saved on stack (PT_AREG0)
  *   a1:	a1
  *   a2:	new stack pointer, original in DEPC
- *   a3:	dispatch table
+ *   a3:	a3
  *   depc:	a2, original value saved on stack (PT_DEPC)
- *   excsave_1:	a3
+ *   excsave_1:	dispatch table
  *
  *   PT_DEPC >= VALID_DOUBLE_EXCEPTION_ADDRESS: double exception, DEPC
  *	     <  VALID_DOUBLE_EXCEPTION_ADDRESS: regular exception
@@ -1785,17 +1649,17 @@ ENDPROC(fast_second_level_miss)
 
 ENTRY(fast_store_prohibited)
 
-	/* Save a1 and a4. */
+	/* Save a1 and a3. */
 
 	s32i	a1, a2, PT_AREG1
-	s32i	a4, a2, PT_AREG4
+	s32i	a3, a2, PT_AREG3
 
 	GET_CURRENT(a1,a2)
 	l32i	a0, a1, TASK_MM		# tsk->mm
 	beqz	a0, 9f
 
 8:	rsr	a1, excvaddr		# fault address
-	_PGD_OFFSET(a0, a1, a4)
+	_PGD_OFFSET(a0, a1, a3)
 	l32i	a0, a0, 0
 	beqz	a0, 2f
 
@@ -1804,39 +1668,37 @@ ENTRY(fast_store_prohibited)
 	 * and is not PAGE_NONE. See pgtable.h for possible PTE layouts.
 	 */
 
-	_PTE_OFFSET(a0, a1, a4)
-	l32i	a4, a0, 0		# read pteval
+	_PTE_OFFSET(a0, a1, a3)
+	l32i	a3, a0, 0		# read pteval
 	movi	a1, _PAGE_CA_INVALID
-	ball	a4, a1, 2f
-	bbci.l	a4, _PAGE_WRITABLE_BIT, 2f
+	ball	a3, a1, 2f
+	bbci.l	a3, _PAGE_WRITABLE_BIT, 2f
 
 	movi	a1, _PAGE_ACCESSED | _PAGE_DIRTY | _PAGE_HW_WRITE
-	or	a4, a4, a1
+	or	a3, a3, a1
 	rsr	a1, excvaddr
-	s32i	a4, a0, 0
+	s32i	a3, a0, 0
 
 	/* We need to flush the cache if we have page coloring. */
 #if (DCACHE_WAY_SIZE > PAGE_SIZE) && XCHAL_DCACHE_IS_WRITEBACK
 	dhwb	a0, 0
 #endif
 	pdtlb	a0, a1
-	wdtlb	a4, a0
+	wdtlb	a3, a0
 
 	/* Exit critical section. */
 
 	movi	a0, 0
+	rsr	a3, excsave1
 	s32i	a0, a3, EXC_TABLE_FIXUP
 
 	/* Restore the working registers, and return. */
 
-	l32i	a4, a2, PT_AREG4
+	l32i	a3, a2, PT_AREG3
 	l32i	a1, a2, PT_AREG1
 	l32i	a0, a2, PT_AREG0
 	l32i	a2, a2, PT_DEPC
 
-	/* Restore excsave1 and a3. */
-
-	xsr	a3, excsave1
 	bgeui	a2, VALID_DOUBLE_EXCEPTION_ADDRESS, 1f
 
 	rsr	a2, depc
@@ -1853,11 +1715,8 @@ ENTRY(fast_store_prohibited)
 
 2:	/* If there was a problem, handle fault in C */
 
-	rsr	a4, depc	# still holds a2
-	xsr	a3, excsave1
-	s32i	a4, a2, PT_AREG2
-	s32i	a3, a2, PT_AREG3
-	l32i	a4, a2, PT_AREG4
+	rsr	a3, depc	# still holds a2
+	s32i	a3, a2, PT_AREG2
 	mov	a1, a2
 
 	rsr	a2, ps
diff --git a/arch/xtensa/kernel/setup.c b/arch/xtensa/kernel/setup.c
index 42a8bba0b0ea..946fb8d06c8b 100644
--- a/arch/xtensa/kernel/setup.c
+++ b/arch/xtensa/kernel/setup.c
@@ -170,8 +170,7 @@ static int __init parse_tag_fdt(const bp_tag_t *tag)
 
 __tagtable(BP_TAG_FDT, parse_tag_fdt);
 
-void __init early_init_dt_setup_initrd_arch(unsigned long start,
-		unsigned long end)
+void __init early_init_dt_setup_initrd_arch(u64 start, u64 end)
 {
 	initrd_start = (void *)__va(start);
 	initrd_end = (void *)__va(end);
@@ -585,8 +584,8 @@ c_show(struct seq_file *f, void *slot)
 		     "bogomips\t: %lu.%02lu\n",
 		     XCHAL_BUILD_UNIQUE_ID,
 		     XCHAL_HAVE_BE ?  "big" : "little",
-		     CCOUNT_PER_JIFFY/(1000000/HZ),
-		     (CCOUNT_PER_JIFFY/(10000/HZ)) % 100,
+		     ccount_freq/1000000,
+		     (ccount_freq/10000) % 100,
 		     loops_per_jiffy/(500000/HZ),
 		     (loops_per_jiffy/(5000/HZ)) % 100);
 
diff --git a/arch/xtensa/kernel/time.c b/arch/xtensa/kernel/time.c
index 24bb0c1776ba..9af3dd88ad7e 100644
--- a/arch/xtensa/kernel/time.c
+++ b/arch/xtensa/kernel/time.c
@@ -29,9 +29,7 @@
 #include <asm/timex.h>
 #include <asm/platform.h>
 
-#ifdef CONFIG_XTENSA_CALIBRATE_CCOUNT
 unsigned long ccount_freq;		/* ccount Hz */
-#endif
 
 static cycle_t ccount_read(struct clocksource *cs)
 {
@@ -129,8 +127,10 @@ void __init time_init(void)
 	platform_calibrate_ccount();
 	printk("%d.%02d MHz\n", (int)ccount_freq/1000000,
 			(int)(ccount_freq/10000)%100);
+#else
+	ccount_freq = CONFIG_XTENSA_CPU_CLOCK*1000000UL;
 #endif
-	clocksource_register_hz(&ccount_clocksource, CCOUNT_PER_JIFFY * HZ);
+	clocksource_register_hz(&ccount_clocksource, ccount_freq);
 
 	ccount_timer.evt.cpumask = cpumask_of(0);
 	ccount_timer.evt.irq = irq_create_mapping(NULL, LINUX_TIMER_INT);
@@ -164,7 +164,7 @@ irqreturn_t timer_interrupt (int irq, void *dev_id)
 #ifndef CONFIG_GENERIC_CALIBRATE_DELAY
 void calibrate_delay(void)
 {
-	loops_per_jiffy = CCOUNT_PER_JIFFY;
+	loops_per_jiffy = ccount_freq / HZ;
 	printk("Calibrating delay loop (skipped)... "
 	       "%lu.%02lu BogoMIPS preset\n",
 	       loops_per_jiffy/(1000000/HZ),
diff --git a/arch/xtensa/kernel/vectors.S b/arch/xtensa/kernel/vectors.S
index f9e175382aa9..cb8fd44caabc 100644
--- a/arch/xtensa/kernel/vectors.S
+++ b/arch/xtensa/kernel/vectors.S
@@ -78,6 +78,7 @@ ENTRY(_UserExceptionVector)
 	s32i	a0, a2, PT_DEPC		# mark it as a regular exception
 	addx4	a0, a0, a3		# find entry in table
 	l32i	a0, a0, EXC_TABLE_FAST_USER	# load handler
+	xsr	a3, excsave1		# restore a3 and dispatch table
 	jx	a0
 
 ENDPROC(_UserExceptionVector)
@@ -104,6 +105,7 @@ ENTRY(_KernelExceptionVector)
 	s32i	a0, a2, PT_DEPC		# mark it as a regular exception
 	addx4	a0, a0, a3		# find entry in table
 	l32i	a0, a0, EXC_TABLE_FAST_KERNEL	# load handler address
+	xsr	a3, excsave1		# restore a3 and dispatch table
 	jx	a0
 
 ENDPROC(_KernelExceptionVector)
@@ -168,7 +170,7 @@ ENDPROC(_KernelExceptionVector)
  *
  *	a0:	   DEPC
  *	a1: 	   a1
- *	a2:	   trashed, original value in EXC_TABLE_DOUBLE_A2
+ *	a2:	   trashed, original value in EXC_TABLE_DOUBLE_SAVE
  *	a3:	   exctable
  *	depc:	   a0
  *	excsave_1: a3
@@ -204,47 +206,46 @@ ENDPROC(_KernelExceptionVector)
 
 	.section .DoubleExceptionVector.text, "ax"
 	.begin literal_prefix .DoubleExceptionVector
+	.globl _DoubleExceptionVector_WindowUnderflow
+	.globl _DoubleExceptionVector_WindowOverflow
 
 ENTRY(_DoubleExceptionVector)
 
-	/* Deliberately destroy excsave (don't assume it's value was valid). */
-
-	wsr	a3, excsave1		# save a3
+	xsr	a3, excsave1
+	s32i	a2, a3, EXC_TABLE_DOUBLE_SAVE
 
 	/* Check for kernel double exception (usually fatal). */
 
-	rsr	a3, ps
-	_bbci.l	a3, PS_UM_BIT, .Lksp
+	rsr	a2, ps
+	_bbci.l	a2, PS_UM_BIT, .Lksp
 
 	/* Check if we are currently handling a window exception. */
 	/* Note: We don't need to indicate that we enter a critical section. */
 
 	xsr	a0, depc		# get DEPC, save a0
 
-	movi	a3, WINDOW_VECTORS_VADDR
-	_bltu	a0, a3, .Lfixup
-	addi	a3, a3, WINDOW_VECTORS_SIZE
-	_bgeu	a0, a3, .Lfixup
+	movi	a2, WINDOW_VECTORS_VADDR
+	_bltu	a0, a2, .Lfixup
+	addi	a2, a2, WINDOW_VECTORS_SIZE
+	_bgeu	a0, a2, .Lfixup
 
 	/* Window overflow/underflow exception. Get stack pointer. */
 
-	mov	a3, a2
-	/* This explicit literal and the following references to it are made
-	 * in order to fit DoubleExceptionVector.literals into the available
-	 * 16-byte gap before DoubleExceptionVector.text in the absence of
-	 * link time relaxation. See kernel/vmlinux.lds.S
-	 */
-	.literal .Lexc_table, exc_table
-	l32r	a2, .Lexc_table
-	l32i	a2, a2, EXC_TABLE_KSTK
+	l32i	a2, a3, EXC_TABLE_KSTK
 
 	/* Check for overflow/underflow exception, jump if overflow. */
 
-	_bbci.l	a0, 6, .Lovfl
-
-	/* a0: depc, a1: a1, a2: kstk, a3: a2, depc: a0, excsave: a3  */
+	_bbci.l	a0, 6, _DoubleExceptionVector_WindowOverflow
 
-	/* Restart window underflow exception.
+	/*
+	 * Restart window underflow exception.
+	 * Currently:
+	 *	depc = orig a0,
+	 *	a0 = orig DEPC,
+	 *	a2 = new sp based on KSTK from exc_table
+	 *	a3 = excsave_1
+	 *	excsave_1 = orig a3
+	 *
 	 * We return to the instruction in user space that caused the window
 	 * underflow exception. Therefore, we change window base to the value
 	 * before we entered the window underflow exception and prepare the
@@ -252,10 +253,11 @@ ENTRY(_DoubleExceptionVector)
 	 * by changing depc (in a0).
 	 * Note: We can trash the current window frame (a0...a3) and depc!
 	 */
-
+_DoubleExceptionVector_WindowUnderflow:
+	xsr	a3, excsave1
 	wsr	a2, depc		# save stack pointer temporarily
 	rsr	a0, ps
-	extui	a0, a0, PS_OWB_SHIFT, 4
+	extui	a0, a0, PS_OWB_SHIFT, PS_OWB_WIDTH
 	wsr	a0, windowbase
 	rsync
 
@@ -263,28 +265,57 @@ ENTRY(_DoubleExceptionVector)
 
 	xsr	a2, depc		# save a2 and get stack pointer
 	s32i	a0, a2, PT_AREG0
-
-	wsr	a3, excsave1		# save a3
-	l32r	a3, .Lexc_table
-
+	xsr	a3, excsave1
 	rsr	a0, exccause
 	s32i	a0, a2, PT_DEPC		# mark it as a regular exception
 	addx4	a0, a0, a3
+	xsr	a3, excsave1
 	l32i	a0, a0, EXC_TABLE_FAST_USER
 	jx	a0
 
-.Lfixup:/* Check for a fixup handler or if we were in a critical section. */
+	/*
+	 * We only allow the ITLB miss exception if we are in kernel space.
+	 * All other exceptions are unexpected and thus unrecoverable!
+	 */
+
+#ifdef CONFIG_MMU
+	.extern fast_second_level_miss_double_kernel
+
+.Lksp:	/* a0: a0, a1: a1, a2: a2, a3: trashed, depc: depc, excsave: a3 */
+
+	rsr	a3, exccause
+	beqi	a3, EXCCAUSE_ITLB_MISS, 1f
+	addi	a3, a3, -EXCCAUSE_DTLB_MISS
+	bnez	a3, .Lunrecoverable
+1:	movi	a3, fast_second_level_miss_double_kernel
+	jx	a3
+#else
+.equ	.Lksp,	.Lunrecoverable
+#endif
+
+	/* Critical! We can't handle this situation. PANIC! */
 
-	/* a0: depc, a1: a1, a2: a2, a3: trashed, depc: a0, excsave1: a3 */
+	.extern unrecoverable_exception
 
-	l32r	a3, .Lexc_table
-	s32i	a2, a3, EXC_TABLE_DOUBLE_SAVE	# temporary variable
+.Lunrecoverable_fixup:
+	l32i	a2, a3, EXC_TABLE_DOUBLE_SAVE
+	xsr	a0, depc
+
+.Lunrecoverable:
+	rsr	a3, excsave1
+	wsr	a0, excsave1
+	movi	a0, unrecoverable_exception
+	callx0	a0
+
+.Lfixup:/* Check for a fixup handler or if we were in a critical section. */
+
+	/* a0: depc, a1: a1, a2: trash, a3: exctable, depc: a0, excsave1: a3 */
 
 	/* Enter critical section. */
 
 	l32i	a2, a3, EXC_TABLE_FIXUP
 	s32i	a3, a3, EXC_TABLE_FIXUP
-	beq	a2, a3, .Lunrecoverable_fixup	# critical!
+	beq	a2, a3, .Lunrecoverable_fixup	# critical section
 	beqz	a2, .Ldflt			# no handler was registered
 
 	/* a0: depc, a1: a1, a2: trash, a3: exctable, depc: a0, excsave: a3 */
@@ -293,58 +324,145 @@ ENTRY(_DoubleExceptionVector)
 
 .Ldflt:	/* Get stack pointer. */
 
-	l32i	a3, a3, EXC_TABLE_DOUBLE_SAVE
-	addi	a2, a3, -PT_USER_SIZE
-
-.Lovfl:	/* Jump to default handlers. */
+	l32i	a2, a3, EXC_TABLE_DOUBLE_SAVE
+	addi	a2, a2, -PT_USER_SIZE
 
-	/* a0: depc, a1: a1, a2: kstk, a3: a2, depc: a0, excsave: a3 */
+	/* a0: depc, a1: a1, a2: kstk, a3: exctable, depc: a0, excsave: a3 */
 
-	xsr	a3, depc
 	s32i	a0, a2, PT_DEPC
-	s32i	a3, a2, PT_AREG0
+	l32i	a0, a3, EXC_TABLE_DOUBLE_SAVE
+	xsr	a0, depc
+	s32i	a0, a2, PT_AREG0
 
-	/* a0: avail, a1: a1, a2: kstk, a3: avail, depc: a2, excsave: a3 */
+	/* a0: avail, a1: a1, a2: kstk, a3: exctable, depc: a2, excsave: a3 */
 
-	l32r	a3, .Lexc_table
 	rsr	a0, exccause
 	addx4	a0, a0, a3
+	xsr	a3, excsave1
 	l32i	a0, a0, EXC_TABLE_FAST_USER
 	jx	a0
 
 	/*
-	 * We only allow the ITLB miss exception if we are in kernel space.
-	 * All other exceptions are unexpected and thus unrecoverable!
+	 * Restart window OVERFLOW exception.
+	 * Currently:
+	 *	depc = orig a0,
+	 *	a0 = orig DEPC,
+	 *	a2 = new sp based on KSTK from exc_table
+	 *	a3 = EXCSAVE_1
+	 *	excsave_1 = orig a3
+	 *
+	 * We return to the instruction in user space that caused the window
+	 * overflow exception. Therefore, we change window base to the value
+	 * before we entered the window overflow exception and prepare the
+	 * registers to return as if we were coming from a regular exception
+	 * by changing DEPC (in a0).
+	 *
+	 * NOTE: We CANNOT trash the current window frame (a0...a3), but we
+	 * can clobber depc.
+	 *
+	 * The tricky part here is that overflow8 and overflow12 handlers
+	 * save a0, then clobber a0.  To restart the handler, we have to restore
+	 * a0 if the double exception was past the point where a0 was clobbered.
+	 *
+	 * To keep things simple, we take advantage of the fact all overflow
+	 * handlers save a0 in their very first instruction.  If DEPC was past
+	 * that instruction, we can safely restore a0 from where it was saved
+	 * on the stack.
+	 *
+	 * a0: depc, a1: a1, a2: kstk, a3: exc_table, depc: a0, excsave1: a3
 	 */
+_DoubleExceptionVector_WindowOverflow:
+	extui	a2, a0, 0, 6	# get offset into 64-byte vector handler
+	beqz	a2, 1f		# if at start of vector, don't restore
 
-#ifdef CONFIG_MMU
-	.extern fast_second_level_miss_double_kernel
+	addi	a0, a0, -128
+	bbsi	a0, 8, 1f	# don't restore except for overflow 8 and 12
+	bbsi	a0, 7, 2f
 
-.Lksp:	/* a0: a0, a1: a1, a2: a2, a3: trashed, depc: depc, excsave: a3 */
+	/*
+	 * Restore a0 as saved by _WindowOverflow8().
+	 *
+	 * FIXME:  we really need a fixup handler for this L32E,
+	 * for the extremely unlikely case where the overflow handler's
+	 * reference thru a0 gets a hardware TLB refill that bumps out
+	 * the (distinct, aliasing) TLB entry that mapped its prior
+	 * references thru a9, and where our reference now thru a9
+	 * gets a 2nd-level miss exception (not hardware TLB refill).
+	 */
 
-	rsr	a3, exccause
-	beqi	a3, EXCCAUSE_ITLB_MISS, 1f
-	addi	a3, a3, -EXCCAUSE_DTLB_MISS
-	bnez	a3, .Lunrecoverable
-1:	movi	a3, fast_second_level_miss_double_kernel
-	jx	a3
-#else
-.equ	.Lksp,	.Lunrecoverable
-#endif
+	l32e	a2, a9, -16
+	wsr	a2, depc	# replace the saved a0
+	j	1f
 
-	/* Critical! We can't handle this situation. PANIC! */
+2:
+	/*
+	 * Restore a0 as saved by _WindowOverflow12().
+	 *
+	 * FIXME:  we really need a fixup handler for this L32E,
+	 * for the extremely unlikely case where the overflow handler's
+	 * reference thru a0 gets a hardware TLB refill that bumps out
+	 * the (distinct, aliasing) TLB entry that mapped its prior
+	 * references thru a13, and where our reference now thru a13
+	 * gets a 2nd-level miss exception (not hardware TLB refill).
+	 */
 
-	.extern unrecoverable_exception
+	l32e	a2, a13, -16
+	wsr	a2, depc	# replace the saved a0
+1:
+	/*
+	 * Restore WindowBase while leaving all address registers restored.
+	 * We have to use ROTW for this, because WSR.WINDOWBASE requires
+	 * an address register (which would prevent restore).
+	 *
+	 * Window Base goes from 0 ... 7 (Module 8)
+	 * Window Start is 8 bits; Ex: (0b1010 1010):0x55 from series of call4s
+	 */
+
+	rsr	a0, ps
+	extui	a0, a0, PS_OWB_SHIFT, PS_OWB_WIDTH
+	rsr	a2, windowbase
+	sub	a0, a2, a0
+	extui	a0, a0, 0, 3
 
-.Lunrecoverable_fixup:
 	l32i	a2, a3, EXC_TABLE_DOUBLE_SAVE
-	xsr	a0, depc
+	xsr	a3, excsave1
+	beqi	a0, 1, .L1pane
+	beqi	a0, 3, .L3pane
 
-.Lunrecoverable:
-	rsr	a3, excsave1
-	wsr	a0, excsave1
-	movi	a0, unrecoverable_exception
-	callx0	a0
+	rsr	a0, depc
+	rotw	-2
+
+	/*
+	 * We are now in the user code's original window frame.
+	 * Process the exception as a user exception as if it was
+	 * taken by the user code.
+	 *
+	 * This is similar to the user exception vector,
+	 * except that PT_DEPC isn't set to EXCCAUSE.
+	 */
+1:
+	xsr	a3, excsave1
+	wsr	a2, depc
+	l32i	a2, a3, EXC_TABLE_KSTK
+	s32i	a0, a2, PT_AREG0
+	rsr	a0, exccause
+
+	s32i	a0, a2, PT_DEPC
+
+	addx4	a0, a0, a3
+	l32i	a0, a0, EXC_TABLE_FAST_USER
+	xsr	a3, excsave1
+	jx	a0
+
+.L1pane:
+	rsr	a0, depc
+	rotw	-1
+	j	1b
+
+.L3pane:
+	rsr	a0, depc
+	rotw	-3
+	j	1b
 
 	.end literal_prefix
 
diff --git a/arch/xtensa/kernel/xtensa_ksyms.c b/arch/xtensa/kernel/xtensa_ksyms.c
index d8507f812f46..74a60c7e085e 100644
--- a/arch/xtensa/kernel/xtensa_ksyms.c
+++ b/arch/xtensa/kernel/xtensa_ksyms.c
@@ -25,6 +25,7 @@
 #include <asm/io.h>
 #include <asm/page.h>
 #include <asm/pgalloc.h>
+#include <asm/ftrace.h>
 #ifdef CONFIG_BLK_DEV_FD
 #include <asm/floppy.h>
 #endif
diff --git a/arch/xtensa/mm/fault.c b/arch/xtensa/mm/fault.c
index 4b7bc8db170f..70fa7bc42b4a 100644
--- a/arch/xtensa/mm/fault.c
+++ b/arch/xtensa/mm/fault.c
@@ -72,6 +72,8 @@ void do_page_fault(struct pt_regs *regs)
 	       address, exccause, regs->pc, is_write? "w":"", is_exec? "x":"");
 #endif
 
+	if (user_mode(regs))
+		flags |= FAULT_FLAG_USER;
 retry:
 	down_read(&mm->mmap_sem);
 	vma = find_vma(mm, address);
diff --git a/block/Kconfig b/block/Kconfig
index a7e40a7c8214..2429515c05c2 100644
--- a/block/Kconfig
+++ b/block/Kconfig
@@ -99,6 +99,17 @@ config BLK_DEV_THROTTLING
 
 	See Documentation/cgroups/blkio-controller.txt for more information.
 
+config BLK_CMDLINE_PARSER
+	bool "Block device command line partition parser"
+	default n
+	---help---
+	Enabling this option allows you to specify the partition layout from
+	the kernel boot args.  This is typically of use for embedded devices
+	which don't otherwise have any standardized method for listing the
+	partitions on a block device.
+
+	See Documentation/block/cmdline-partition.txt for more information.
+
 menu "Partition Types"
 
 source "block/partitions/Kconfig"
diff --git a/block/Makefile b/block/Makefile
index 39b76ba66ffd..671a83d063a5 100644
--- a/block/Makefile
+++ b/block/Makefile
@@ -18,3 +18,4 @@ obj-$(CONFIG_IOSCHED_CFQ)	+= cfq-iosched.o
 
 obj-$(CONFIG_BLOCK_COMPAT)	+= compat_ioctl.o
 obj-$(CONFIG_BLK_DEV_INTEGRITY)	+= blk-integrity.o
+obj-$(CONFIG_BLK_CMDLINE_PARSER)	+= cmdline-parser.o
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 290792a13e3c..4e491d9b5292 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -235,8 +235,13 @@ static struct blkcg_gq *blkg_create(struct blkcg *blkcg,
 	blkg->online = true;
 	spin_unlock(&blkcg->lock);
 
-	if (!ret)
+	if (!ret) {
+		if (blkcg == &blkcg_root) {
+			q->root_blkg = blkg;
+			q->root_rl.blkg = blkg;
+		}
 		return blkg;
+	}
 
 	/* @blkg failed fully initialized, use the usual release path */
 	blkg_put(blkg);
@@ -335,6 +340,15 @@ static void blkg_destroy(struct blkcg_gq *blkg)
 		rcu_assign_pointer(blkcg->blkg_hint, NULL);
 
 	/*
+	 * If root blkg is destroyed.  Just clear the pointer since root_rl
+	 * does not take reference on root blkg.
+	 */
+	if (blkcg == &blkcg_root) {
+		blkg->q->root_blkg = NULL;
+		blkg->q->root_rl.blkg = NULL;
+	}
+
+	/*
 	 * Put the reference taken at the time of creation so that when all
 	 * queues are gone, group can be destroyed.
 	 */
@@ -360,13 +374,6 @@ static void blkg_destroy_all(struct request_queue *q)
 		blkg_destroy(blkg);
 		spin_unlock(&blkcg->lock);
 	}
-
-	/*
-	 * root blkg is destroyed.  Just clear the pointer since
-	 * root_rl does not take reference on root blkg.
-	 */
-	q->root_blkg = NULL;
-	q->root_rl.blkg = NULL;
 }
 
 /*
@@ -437,10 +444,10 @@ struct request_list *__blk_queue_next_rl(struct request_list *rl,
 	return &blkg->rl;
 }
 
-static int blkcg_reset_stats(struct cgroup *cgroup, struct cftype *cftype,
-			     u64 val)
+static int blkcg_reset_stats(struct cgroup_subsys_state *css,
+			     struct cftype *cftype, u64 val)
 {
-	struct blkcg *blkcg = cgroup_to_blkcg(cgroup);
+	struct blkcg *blkcg = css_to_blkcg(css);
 	struct blkcg_gq *blkg;
 	int i;
 
@@ -614,15 +621,13 @@ u64 blkg_stat_recursive_sum(struct blkg_policy_data *pd, int off)
 {
 	struct blkcg_policy *pol = blkcg_policy[pd->plid];
 	struct blkcg_gq *pos_blkg;
-	struct cgroup *pos_cgrp;
-	u64 sum;
+	struct cgroup_subsys_state *pos_css;
+	u64 sum = 0;
 
 	lockdep_assert_held(pd->blkg->q->queue_lock);
 
-	sum = blkg_stat_read((void *)pd + off);
-
 	rcu_read_lock();
-	blkg_for_each_descendant_pre(pos_blkg, pos_cgrp, pd_to_blkg(pd)) {
+	blkg_for_each_descendant_pre(pos_blkg, pos_css, pd_to_blkg(pd)) {
 		struct blkg_policy_data *pos_pd = blkg_to_pd(pos_blkg, pol);
 		struct blkg_stat *stat = (void *)pos_pd + off;
 
@@ -649,16 +654,14 @@ struct blkg_rwstat blkg_rwstat_recursive_sum(struct blkg_policy_data *pd,
 {
 	struct blkcg_policy *pol = blkcg_policy[pd->plid];
 	struct blkcg_gq *pos_blkg;
-	struct cgroup *pos_cgrp;
-	struct blkg_rwstat sum;
+	struct cgroup_subsys_state *pos_css;
+	struct blkg_rwstat sum = { };
 	int i;
 
 	lockdep_assert_held(pd->blkg->q->queue_lock);
 
-	sum = blkg_rwstat_read((void *)pd + off);
-
 	rcu_read_lock();
-	blkg_for_each_descendant_pre(pos_blkg, pos_cgrp, pd_to_blkg(pd)) {
+	blkg_for_each_descendant_pre(pos_blkg, pos_css, pd_to_blkg(pd)) {
 		struct blkg_policy_data *pos_pd = blkg_to_pd(pos_blkg, pol);
 		struct blkg_rwstat *rwstat = (void *)pos_pd + off;
 		struct blkg_rwstat tmp;
@@ -765,18 +768,18 @@ struct cftype blkcg_files[] = {
 
 /**
  * blkcg_css_offline - cgroup css_offline callback
- * @cgroup: cgroup of interest
+ * @css: css of interest
  *
- * This function is called when @cgroup is about to go away and responsible
- * for shooting down all blkgs associated with @cgroup.  blkgs should be
+ * This function is called when @css is about to go away and responsible
+ * for shooting down all blkgs associated with @css.  blkgs should be
  * removed while holding both q and blkcg locks.  As blkcg lock is nested
  * inside q lock, this function performs reverse double lock dancing.
  *
  * This is the blkcg counterpart of ioc_release_fn().
  */
-static void blkcg_css_offline(struct cgroup *cgroup)
+static void blkcg_css_offline(struct cgroup_subsys_state *css)
 {
-	struct blkcg *blkcg = cgroup_to_blkcg(cgroup);
+	struct blkcg *blkcg = css_to_blkcg(css);
 
 	spin_lock_irq(&blkcg->lock);
 
@@ -798,21 +801,21 @@ static void blkcg_css_offline(struct cgroup *cgroup)
 	spin_unlock_irq(&blkcg->lock);
 }
 
-static void blkcg_css_free(struct cgroup *cgroup)
+static void blkcg_css_free(struct cgroup_subsys_state *css)
 {
-	struct blkcg *blkcg = cgroup_to_blkcg(cgroup);
+	struct blkcg *blkcg = css_to_blkcg(css);
 
 	if (blkcg != &blkcg_root)
 		kfree(blkcg);
 }
 
-static struct cgroup_subsys_state *blkcg_css_alloc(struct cgroup *cgroup)
+static struct cgroup_subsys_state *
+blkcg_css_alloc(struct cgroup_subsys_state *parent_css)
 {
 	static atomic64_t id_seq = ATOMIC64_INIT(0);
 	struct blkcg *blkcg;
-	struct cgroup *parent = cgroup->parent;
 
-	if (!parent) {
+	if (!parent_css) {
 		blkcg = &blkcg_root;
 		goto done;
 	}
@@ -883,14 +886,15 @@ void blkcg_exit_queue(struct request_queue *q)
  * of the main cic data structures.  For now we allow a task to change
  * its cgroup only if it's the only owner of its ioc.
  */
-static int blkcg_can_attach(struct cgroup *cgrp, struct cgroup_taskset *tset)
+static int blkcg_can_attach(struct cgroup_subsys_state *css,
+			    struct cgroup_taskset *tset)
 {
 	struct task_struct *task;
 	struct io_context *ioc;
 	int ret = 0;
 
 	/* task_lock() is needed to avoid races with exit_io_context() */
-	cgroup_taskset_for_each(task, cgrp, tset) {
+	cgroup_taskset_for_each(task, css, tset) {
 		task_lock(task);
 		ioc = task->io_context;
 		if (ioc && atomic_read(&ioc->nr_tasks) > 1)
@@ -973,8 +977,6 @@ int blkcg_activate_policy(struct request_queue *q,
 		ret = PTR_ERR(blkg);
 		goto out_unlock;
 	}
-	q->root_blkg = blkg;
-	q->root_rl.blkg = blkg;
 
 	list_for_each_entry(blkg, &q->blkg_list, q_node)
 		cnt++;
@@ -1127,7 +1129,7 @@ void blkcg_policy_unregister(struct blkcg_policy *pol)
 
 	/* kill the intf files first */
 	if (pol->cftypes)
-		cgroup_rm_cftypes(&blkio_subsys, pol->cftypes);
+		cgroup_rm_cftypes(pol->cftypes);
 
 	/* unregister and update blkgs */
 	blkcg_policy[pol->plid] = NULL;
diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h
index 8056c03a3382..ae6969a7ffd4 100644
--- a/block/blk-cgroup.h
+++ b/block/blk-cgroup.h
@@ -179,22 +179,20 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
 void blkg_conf_finish(struct blkg_conf_ctx *ctx);
 
 
-static inline struct blkcg *cgroup_to_blkcg(struct cgroup *cgroup)
+static inline struct blkcg *css_to_blkcg(struct cgroup_subsys_state *css)
 {
-	return container_of(cgroup_subsys_state(cgroup, blkio_subsys_id),
-			    struct blkcg, css);
+	return css ? container_of(css, struct blkcg, css) : NULL;
 }
 
 static inline struct blkcg *task_blkcg(struct task_struct *tsk)
 {
-	return container_of(task_subsys_state(tsk, blkio_subsys_id),
-			    struct blkcg, css);
+	return css_to_blkcg(task_css(tsk, blkio_subsys_id));
 }
 
 static inline struct blkcg *bio_blkcg(struct bio *bio)
 {
 	if (bio && bio->bi_css)
-		return container_of(bio->bi_css, struct blkcg, css);
+		return css_to_blkcg(bio->bi_css);
 	return task_blkcg(current);
 }
 
@@ -206,9 +204,7 @@ static inline struct blkcg *bio_blkcg(struct bio *bio)
  */
 static inline struct blkcg *blkcg_parent(struct blkcg *blkcg)
 {
-	struct cgroup *pcg = blkcg->css.cgroup->parent;
-
-	return pcg ? cgroup_to_blkcg(pcg) : NULL;
+	return css_to_blkcg(css_parent(&blkcg->css));
 }
 
 /**
@@ -288,32 +284,33 @@ struct blkcg_gq *__blkg_lookup(struct blkcg *blkcg, struct request_queue *q,
 /**
  * blkg_for_each_descendant_pre - pre-order walk of a blkg's descendants
  * @d_blkg: loop cursor pointing to the current descendant
- * @pos_cgrp: used for iteration
+ * @pos_css: used for iteration
  * @p_blkg: target blkg to walk descendants of
  *
  * Walk @c_blkg through the descendants of @p_blkg.  Must be used with RCU
  * read locked.  If called under either blkcg or queue lock, the iteration
  * is guaranteed to include all and only online blkgs.  The caller may
- * update @pos_cgrp by calling cgroup_rightmost_descendant() to skip
- * subtree.
+ * update @pos_css by calling css_rightmost_descendant() to skip subtree.
+ * @p_blkg is included in the iteration and the first node to be visited.
  */
-#define blkg_for_each_descendant_pre(d_blkg, pos_cgrp, p_blkg)		\
-	cgroup_for_each_descendant_pre((pos_cgrp), (p_blkg)->blkcg->css.cgroup) \
-		if (((d_blkg) = __blkg_lookup(cgroup_to_blkcg(pos_cgrp), \
+#define blkg_for_each_descendant_pre(d_blkg, pos_css, p_blkg)		\
+	css_for_each_descendant_pre((pos_css), &(p_blkg)->blkcg->css)	\
+		if (((d_blkg) = __blkg_lookup(css_to_blkcg(pos_css),	\
 					      (p_blkg)->q, false)))
 
 /**
  * blkg_for_each_descendant_post - post-order walk of a blkg's descendants
  * @d_blkg: loop cursor pointing to the current descendant
- * @pos_cgrp: used for iteration
+ * @pos_css: used for iteration
  * @p_blkg: target blkg to walk descendants of
  *
  * Similar to blkg_for_each_descendant_pre() but performs post-order
- * traversal instead.  Synchronization rules are the same.
+ * traversal instead.  Synchronization rules are the same.  @p_blkg is
+ * included in the iteration and the last node to be visited.
  */
-#define blkg_for_each_descendant_post(d_blkg, pos_cgrp, p_blkg)		\
-	cgroup_for_each_descendant_post((pos_cgrp), (p_blkg)->blkcg->css.cgroup) \
-		if (((d_blkg) = __blkg_lookup(cgroup_to_blkcg(pos_cgrp), \
+#define blkg_for_each_descendant_post(d_blkg, pos_css, p_blkg)		\
+	css_for_each_descendant_post((pos_css), &(p_blkg)->blkcg->css)	\
+		if (((d_blkg) = __blkg_lookup(css_to_blkcg(pos_css),	\
 					      (p_blkg)->q, false)))
 
 /**
@@ -576,7 +573,6 @@ static inline int blkcg_activate_policy(struct request_queue *q,
 static inline void blkcg_deactivate_policy(struct request_queue *q,
 					   const struct blkcg_policy *pol) { }
 
-static inline struct blkcg *cgroup_to_blkcg(struct cgroup *cgroup) { return NULL; }
 static inline struct blkcg *bio_blkcg(struct bio *bio) { return NULL; }
 
 static inline struct blkg_policy_data *blkg_to_pd(struct blkcg_gq *blkg,
diff --git a/block/blk-core.c b/block/blk-core.c
index 93a18d1d3da8..0a00e4ecf87c 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1549,11 +1549,9 @@ get_rq:
 	if (plug) {
 		/*
 		 * If this is the first request added after a plug, fire
-		 * of a plug trace. If others have been added before, check
-		 * if we have multiple devices in this plug. If so, make a
-		 * note to sort the list before dispatch.
+		 * of a plug trace.
 		 */
-		if (list_empty(&plug->list))
+		if (!request_count)
 			trace_block_plug(q);
 		else {
 			if (request_count >= BLK_MAX_REQUEST_COUNT) {
@@ -2318,6 +2316,12 @@ bool blk_update_request(struct request *req, int error, unsigned int nr_bytes)
 		case -ETIMEDOUT:
 			error_type = "timeout";
 			break;
+		case -ENOSPC:
+			error_type = "critical space allocation";
+			break;
+		case -ENODATA:
+			error_type = "critical medium";
+			break;
 		case -EIO:
 		default:
 			error_type = "I/O";
diff --git a/block/blk-exec.c b/block/blk-exec.c
index e70621396129..ae4f27d7944e 100644
--- a/block/blk-exec.c
+++ b/block/blk-exec.c
@@ -68,9 +68,9 @@ void blk_execute_rq_nowait(struct request_queue *q, struct gendisk *bd_disk,
 	spin_lock_irq(q->queue_lock);
 
 	if (unlikely(blk_queue_dying(q))) {
+		rq->cmd_flags |= REQ_QUIET; 
 		rq->errors = -ENXIO;
-		if (rq->end_io)
-			rq->end_io(rq, rq->errors);
+		__blk_end_request_all(rq, rq->errors);
 		spin_unlock_irq(q->queue_lock);
 		return;
 	}
diff --git a/block/blk-ioc.c b/block/blk-ioc.c
index 4464c823cff2..46cd7bd18b34 100644
--- a/block/blk-ioc.c
+++ b/block/blk-ioc.c
@@ -367,7 +367,7 @@ struct io_cq *ioc_create_icq(struct io_context *ioc, struct request_queue *q,
 	if (!icq)
 		return NULL;
 
-	if (radix_tree_preload(gfp_mask) < 0) {
+	if (radix_tree_maybe_preload(gfp_mask) < 0) {
 		kmem_cache_free(et->icq_cache, icq);
 		return NULL;
 	}
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 5efc5a647183..3aa5b195f4dd 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -29,7 +29,7 @@ queue_var_store(unsigned long *var, const char *page, size_t count)
 	int err;
 	unsigned long v;
 
-	err = strict_strtoul(page, 10, &v);
+	err = kstrtoul(page, 10, &v);
 	if (err || v > UINT_MAX)
 		return -EINVAL;
 
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index 08a32dfd3844..8331aba9426f 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -1293,10 +1293,10 @@ static u64 tg_prfill_cpu_rwstat(struct seq_file *sf,
 	return __blkg_prfill_rwstat(sf, pd, &rwstat);
 }
 
-static int tg_print_cpu_rwstat(struct cgroup *cgrp, struct cftype *cft,
-			       struct seq_file *sf)
+static int tg_print_cpu_rwstat(struct cgroup_subsys_state *css,
+			       struct cftype *cft, struct seq_file *sf)
 {
-	struct blkcg *blkcg = cgroup_to_blkcg(cgrp);
+	struct blkcg *blkcg = css_to_blkcg(css);
 
 	blkcg_print_blkgs(sf, blkcg, tg_prfill_cpu_rwstat, &blkcg_policy_throtl,
 			  cft->private, true);
@@ -1325,31 +1325,31 @@ static u64 tg_prfill_conf_uint(struct seq_file *sf, struct blkg_policy_data *pd,
 	return __blkg_prfill_u64(sf, pd, v);
 }
 
-static int tg_print_conf_u64(struct cgroup *cgrp, struct cftype *cft,
-			     struct seq_file *sf)
+static int tg_print_conf_u64(struct cgroup_subsys_state *css,
+			     struct cftype *cft, struct seq_file *sf)
 {
-	blkcg_print_blkgs(sf, cgroup_to_blkcg(cgrp), tg_prfill_conf_u64,
+	blkcg_print_blkgs(sf, css_to_blkcg(css), tg_prfill_conf_u64,
 			  &blkcg_policy_throtl, cft->private, false);
 	return 0;
 }
 
-static int tg_print_conf_uint(struct cgroup *cgrp, struct cftype *cft,
-			      struct seq_file *sf)
+static int tg_print_conf_uint(struct cgroup_subsys_state *css,
+			      struct cftype *cft, struct seq_file *sf)
 {
-	blkcg_print_blkgs(sf, cgroup_to_blkcg(cgrp), tg_prfill_conf_uint,
+	blkcg_print_blkgs(sf, css_to_blkcg(css), tg_prfill_conf_uint,
 			  &blkcg_policy_throtl, cft->private, false);
 	return 0;
 }
 
-static int tg_set_conf(struct cgroup *cgrp, struct cftype *cft, const char *buf,
-		       bool is_u64)
+static int tg_set_conf(struct cgroup_subsys_state *css, struct cftype *cft,
+		       const char *buf, bool is_u64)
 {
-	struct blkcg *blkcg = cgroup_to_blkcg(cgrp);
+	struct blkcg *blkcg = css_to_blkcg(css);
 	struct blkg_conf_ctx ctx;
 	struct throtl_grp *tg;
 	struct throtl_service_queue *sq;
 	struct blkcg_gq *blkg;
-	struct cgroup *pos_cgrp;
+	struct cgroup_subsys_state *pos_css;
 	int ret;
 
 	ret = blkg_conf_prep(blkcg, &blkcg_policy_throtl, buf, &ctx);
@@ -1379,8 +1379,7 @@ static int tg_set_conf(struct cgroup *cgrp, struct cftype *cft, const char *buf,
 	 * restrictions in the whole hierarchy and allows them to bypass
 	 * blk-throttle.
 	 */
-	tg_update_has_rules(tg);
-	blkg_for_each_descendant_pre(blkg, pos_cgrp, ctx.blkg)
+	blkg_for_each_descendant_pre(blkg, pos_css, ctx.blkg)
 		tg_update_has_rules(blkg_to_tg(blkg));
 
 	/*
@@ -1403,16 +1402,16 @@ static int tg_set_conf(struct cgroup *cgrp, struct cftype *cft, const char *buf,
 	return 0;
 }
 
-static int tg_set_conf_u64(struct cgroup *cgrp, struct cftype *cft,
+static int tg_set_conf_u64(struct cgroup_subsys_state *css, struct cftype *cft,
 			   const char *buf)
 {
-	return tg_set_conf(cgrp, cft, buf, true);
+	return tg_set_conf(css, cft, buf, true);
 }
 
-static int tg_set_conf_uint(struct cgroup *cgrp, struct cftype *cft,
+static int tg_set_conf_uint(struct cgroup_subsys_state *css, struct cftype *cft,
 			    const char *buf)
 {
-	return tg_set_conf(cgrp, cft, buf, false);
+	return tg_set_conf(css, cft, buf, false);
 }
 
 static struct cftype throtl_files[] = {
@@ -1623,7 +1622,7 @@ void blk_throtl_drain(struct request_queue *q)
 {
 	struct throtl_data *td = q->td;
 	struct blkcg_gq *blkg;
-	struct cgroup *pos_cgrp;
+	struct cgroup_subsys_state *pos_css;
 	struct bio *bio;
 	int rw;
 
@@ -1636,11 +1635,9 @@ void blk_throtl_drain(struct request_queue *q)
 	 * better to walk service_queue tree directly but blkg walk is
 	 * easier.
 	 */
-	blkg_for_each_descendant_post(blkg, pos_cgrp, td->queue->root_blkg)
+	blkg_for_each_descendant_post(blkg, pos_css, td->queue->root_blkg)
 		tg_drain_bios(&blkg_to_tg(blkg)->service_queue);
 
-	tg_drain_bios(&td_root_tg(td)->service_queue);
-
 	/* finally, transfer bios from top-level tg's into the td */
 	tg_drain_bios(&td->service_queue);
 
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index d5bbdcfd0dab..434944cbd761 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -1607,12 +1607,11 @@ static u64 cfqg_prfill_weight_device(struct seq_file *sf,
 	return __blkg_prfill_u64(sf, pd, cfqg->dev_weight);
 }
 
-static int cfqg_print_weight_device(struct cgroup *cgrp, struct cftype *cft,
-				    struct seq_file *sf)
+static int cfqg_print_weight_device(struct cgroup_subsys_state *css,
+				    struct cftype *cft, struct seq_file *sf)
 {
-	blkcg_print_blkgs(sf, cgroup_to_blkcg(cgrp),
-			  cfqg_prfill_weight_device, &blkcg_policy_cfq, 0,
-			  false);
+	blkcg_print_blkgs(sf, css_to_blkcg(css), cfqg_prfill_weight_device,
+			  &blkcg_policy_cfq, 0, false);
 	return 0;
 }
 
@@ -1626,35 +1625,34 @@ static u64 cfqg_prfill_leaf_weight_device(struct seq_file *sf,
 	return __blkg_prfill_u64(sf, pd, cfqg->dev_leaf_weight);
 }
 
-static int cfqg_print_leaf_weight_device(struct cgroup *cgrp,
+static int cfqg_print_leaf_weight_device(struct cgroup_subsys_state *css,
 					 struct cftype *cft,
 					 struct seq_file *sf)
 {
-	blkcg_print_blkgs(sf, cgroup_to_blkcg(cgrp),
-			  cfqg_prfill_leaf_weight_device, &blkcg_policy_cfq, 0,
-			  false);
+	blkcg_print_blkgs(sf, css_to_blkcg(css), cfqg_prfill_leaf_weight_device,
+			  &blkcg_policy_cfq, 0, false);
 	return 0;
 }
 
-static int cfq_print_weight(struct cgroup *cgrp, struct cftype *cft,
+static int cfq_print_weight(struct cgroup_subsys_state *css, struct cftype *cft,
 			    struct seq_file *sf)
 {
-	seq_printf(sf, "%u\n", cgroup_to_blkcg(cgrp)->cfq_weight);
+	seq_printf(sf, "%u\n", css_to_blkcg(css)->cfq_weight);
 	return 0;
 }
 
-static int cfq_print_leaf_weight(struct cgroup *cgrp, struct cftype *cft,
-				 struct seq_file *sf)
+static int cfq_print_leaf_weight(struct cgroup_subsys_state *css,
+				 struct cftype *cft, struct seq_file *sf)
 {
-	seq_printf(sf, "%u\n",
-		   cgroup_to_blkcg(cgrp)->cfq_leaf_weight);
+	seq_printf(sf, "%u\n", css_to_blkcg(css)->cfq_leaf_weight);
 	return 0;
 }
 
-static int __cfqg_set_weight_device(struct cgroup *cgrp, struct cftype *cft,
-				    const char *buf, bool is_leaf_weight)
+static int __cfqg_set_weight_device(struct cgroup_subsys_state *css,
+				    struct cftype *cft, const char *buf,
+				    bool is_leaf_weight)
 {
-	struct blkcg *blkcg = cgroup_to_blkcg(cgrp);
+	struct blkcg *blkcg = css_to_blkcg(css);
 	struct blkg_conf_ctx ctx;
 	struct cfq_group *cfqg;
 	int ret;
@@ -1680,22 +1678,22 @@ static int __cfqg_set_weight_device(struct cgroup *cgrp, struct cftype *cft,
 	return ret;
 }
 
-static int cfqg_set_weight_device(struct cgroup *cgrp, struct cftype *cft,
-				  const char *buf)
+static int cfqg_set_weight_device(struct cgroup_subsys_state *css,
+				  struct cftype *cft, const char *buf)
 {
-	return __cfqg_set_weight_device(cgrp, cft, buf, false);
+	return __cfqg_set_weight_device(css, cft, buf, false);
 }
 
-static int cfqg_set_leaf_weight_device(struct cgroup *cgrp, struct cftype *cft,
-				       const char *buf)
+static int cfqg_set_leaf_weight_device(struct cgroup_subsys_state *css,
+				       struct cftype *cft, const char *buf)
 {
-	return __cfqg_set_weight_device(cgrp, cft, buf, true);
+	return __cfqg_set_weight_device(css, cft, buf, true);
 }
 
-static int __cfq_set_weight(struct cgroup *cgrp, struct cftype *cft, u64 val,
-			    bool is_leaf_weight)
+static int __cfq_set_weight(struct cgroup_subsys_state *css, struct cftype *cft,
+			    u64 val, bool is_leaf_weight)
 {
-	struct blkcg *blkcg = cgroup_to_blkcg(cgrp);
+	struct blkcg *blkcg = css_to_blkcg(css);
 	struct blkcg_gq *blkg;
 
 	if (val < CFQ_WEIGHT_MIN || val > CFQ_WEIGHT_MAX)
@@ -1727,30 +1725,32 @@ static int __cfq_set_weight(struct cgroup *cgrp, struct cftype *cft, u64 val,
 	return 0;
 }
 
-static int cfq_set_weight(struct cgroup *cgrp, struct cftype *cft, u64 val)
+static int cfq_set_weight(struct cgroup_subsys_state *css, struct cftype *cft,
+			  u64 val)
 {
-	return __cfq_set_weight(cgrp, cft, val, false);
+	return __cfq_set_weight(css, cft, val, false);
 }
 
-static int cfq_set_leaf_weight(struct cgroup *cgrp, struct cftype *cft, u64 val)
+static int cfq_set_leaf_weight(struct cgroup_subsys_state *css,
+			       struct cftype *cft, u64 val)
 {
-	return __cfq_set_weight(cgrp, cft, val, true);
+	return __cfq_set_weight(css, cft, val, true);
 }
 
-static int cfqg_print_stat(struct cgroup *cgrp, struct cftype *cft,
+static int cfqg_print_stat(struct cgroup_subsys_state *css, struct cftype *cft,
 			   struct seq_file *sf)
 {
-	struct blkcg *blkcg = cgroup_to_blkcg(cgrp);
+	struct blkcg *blkcg = css_to_blkcg(css);
 
 	blkcg_print_blkgs(sf, blkcg, blkg_prfill_stat, &blkcg_policy_cfq,
 			  cft->private, false);
 	return 0;
 }
 
-static int cfqg_print_rwstat(struct cgroup *cgrp, struct cftype *cft,
-			     struct seq_file *sf)
+static int cfqg_print_rwstat(struct cgroup_subsys_state *css,
+			     struct cftype *cft, struct seq_file *sf)
 {
-	struct blkcg *blkcg = cgroup_to_blkcg(cgrp);
+	struct blkcg *blkcg = css_to_blkcg(css);
 
 	blkcg_print_blkgs(sf, blkcg, blkg_prfill_rwstat, &blkcg_policy_cfq,
 			  cft->private, true);
@@ -1773,20 +1773,20 @@ static u64 cfqg_prfill_rwstat_recursive(struct seq_file *sf,
 	return __blkg_prfill_rwstat(sf, pd, &sum);
 }
 
-static int cfqg_print_stat_recursive(struct cgroup *cgrp, struct cftype *cft,
-				     struct seq_file *sf)
+static int cfqg_print_stat_recursive(struct cgroup_subsys_state *css,
+				     struct cftype *cft, struct seq_file *sf)
 {
-	struct blkcg *blkcg = cgroup_to_blkcg(cgrp);
+	struct blkcg *blkcg = css_to_blkcg(css);
 
 	blkcg_print_blkgs(sf, blkcg, cfqg_prfill_stat_recursive,
 			  &blkcg_policy_cfq, cft->private, false);
 	return 0;
 }
 
-static int cfqg_print_rwstat_recursive(struct cgroup *cgrp, struct cftype *cft,
-				       struct seq_file *sf)
+static int cfqg_print_rwstat_recursive(struct cgroup_subsys_state *css,
+				       struct cftype *cft, struct seq_file *sf)
 {
-	struct blkcg *blkcg = cgroup_to_blkcg(cgrp);
+	struct blkcg *blkcg = css_to_blkcg(css);
 
 	blkcg_print_blkgs(sf, blkcg, cfqg_prfill_rwstat_recursive,
 			  &blkcg_policy_cfq, cft->private, true);
@@ -1803,17 +1803,17 @@ static u64 cfqg_prfill_avg_queue_size(struct seq_file *sf,
 
 	if (samples) {
 		v = blkg_stat_read(&cfqg->stats.avg_queue_size_sum);
-		do_div(v, samples);
+		v = div64_u64(v, samples);
 	}
 	__blkg_prfill_u64(sf, pd, v);
 	return 0;
 }
 
 /* print avg_queue_size */
-static int cfqg_print_avg_queue_size(struct cgroup *cgrp, struct cftype *cft,
-				     struct seq_file *sf)
+static int cfqg_print_avg_queue_size(struct cgroup_subsys_state *css,
+				     struct cftype *cft, struct seq_file *sf)
 {
-	struct blkcg *blkcg = cgroup_to_blkcg(cgrp);
+	struct blkcg *blkcg = css_to_blkcg(css);
 
 	blkcg_print_blkgs(sf, blkcg, cfqg_prfill_avg_queue_size,
 			  &blkcg_policy_cfq, 0, false);
@@ -4358,7 +4358,7 @@ static int cfq_init_queue(struct request_queue *q, struct elevator_type *e)
 	if (!eq)
 		return -ENOMEM;
 
-	cfqd = kmalloc_node(sizeof(*cfqd), GFP_KERNEL | __GFP_ZERO, q->node);
+	cfqd = kzalloc_node(sizeof(*cfqd), GFP_KERNEL, q->node);
 	if (!cfqd) {
 		kobject_put(&eq->kobj);
 		return -ENOMEM;
diff --git a/block/cmdline-parser.c b/block/cmdline-parser.c
new file mode 100644
index 000000000000..cc2637f8674e
--- /dev/null
+++ b/block/cmdline-parser.c
@@ -0,0 +1,250 @@
+/*
+ * Parse command line, get partition information
+ *
+ * Written by Cai Zhiyong <caizhiyong@huawei.com>
+ *
+ */
+#include <linux/buffer_head.h>
+#include <linux/module.h>
+#include <linux/cmdline-parser.h>
+
+static int parse_subpart(struct cmdline_subpart **subpart, char *partdef)
+{
+	int ret = 0;
+	struct cmdline_subpart *new_subpart;
+
+	*subpart = NULL;
+
+	new_subpart = kzalloc(sizeof(struct cmdline_subpart), GFP_KERNEL);
+	if (!new_subpart)
+		return -ENOMEM;
+
+	if (*partdef == '-') {
+		new_subpart->size = (sector_t)(~0ULL);
+		partdef++;
+	} else {
+		new_subpart->size = (sector_t)memparse(partdef, &partdef);
+		if (new_subpart->size < (sector_t)PAGE_SIZE) {
+			pr_warn("cmdline partition size is invalid.");
+			ret = -EINVAL;
+			goto fail;
+		}
+	}
+
+	if (*partdef == '@') {
+		partdef++;
+		new_subpart->from = (sector_t)memparse(partdef, &partdef);
+	} else {
+		new_subpart->from = (sector_t)(~0ULL);
+	}
+
+	if (*partdef == '(') {
+		int length;
+		char *next = strchr(++partdef, ')');
+
+		if (!next) {
+			pr_warn("cmdline partition format is invalid.");
+			ret = -EINVAL;
+			goto fail;
+		}
+
+		length = min_t(int, next - partdef,
+			       sizeof(new_subpart->name) - 1);
+		strncpy(new_subpart->name, partdef, length);
+		new_subpart->name[length] = '\0';
+
+		partdef = ++next;
+	} else
+		new_subpart->name[0] = '\0';
+
+	new_subpart->flags = 0;
+
+	if (!strncmp(partdef, "ro", 2)) {
+		new_subpart->flags |= PF_RDONLY;
+		partdef += 2;
+	}
+
+	if (!strncmp(partdef, "lk", 2)) {
+		new_subpart->flags |= PF_POWERUP_LOCK;
+		partdef += 2;
+	}
+
+	*subpart = new_subpart;
+	return 0;
+fail:
+	kfree(new_subpart);
+	return ret;
+}
+
+static void free_subpart(struct cmdline_parts *parts)
+{
+	struct cmdline_subpart *subpart;
+
+	while (parts->subpart) {
+		subpart = parts->subpart;
+		parts->subpart = subpart->next_subpart;
+		kfree(subpart);
+	}
+}
+
+static int parse_parts(struct cmdline_parts **parts, const char *bdevdef)
+{
+	int ret = -EINVAL;
+	char *next;
+	int length;
+	struct cmdline_subpart **next_subpart;
+	struct cmdline_parts *newparts;
+	char buf[BDEVNAME_SIZE + 32 + 4];
+
+	*parts = NULL;
+
+	newparts = kzalloc(sizeof(struct cmdline_parts), GFP_KERNEL);
+	if (!newparts)
+		return -ENOMEM;
+
+	next = strchr(bdevdef, ':');
+	if (!next) {
+		pr_warn("cmdline partition has no block device.");
+		goto fail;
+	}
+
+	length = min_t(int, next - bdevdef, sizeof(newparts->name) - 1);
+	strncpy(newparts->name, bdevdef, length);
+	newparts->name[length] = '\0';
+	newparts->nr_subparts = 0;
+
+	next_subpart = &newparts->subpart;
+
+	while (next && *(++next)) {
+		bdevdef = next;
+		next = strchr(bdevdef, ',');
+
+		length = (!next) ? (sizeof(buf) - 1) :
+			min_t(int, next - bdevdef, sizeof(buf) - 1);
+
+		strncpy(buf, bdevdef, length);
+		buf[length] = '\0';
+
+		ret = parse_subpart(next_subpart, buf);
+		if (ret)
+			goto fail;
+
+		newparts->nr_subparts++;
+		next_subpart = &(*next_subpart)->next_subpart;
+	}
+
+	if (!newparts->subpart) {
+		pr_warn("cmdline partition has no valid partition.");
+		ret = -EINVAL;
+		goto fail;
+	}
+
+	*parts = newparts;
+
+	return 0;
+fail:
+	free_subpart(newparts);
+	kfree(newparts);
+	return ret;
+}
+
+void cmdline_parts_free(struct cmdline_parts **parts)
+{
+	struct cmdline_parts *next_parts;
+
+	while (*parts) {
+		next_parts = (*parts)->next_parts;
+		free_subpart(*parts);
+		kfree(*parts);
+		*parts = next_parts;
+	}
+}
+
+int cmdline_parts_parse(struct cmdline_parts **parts, const char *cmdline)
+{
+	int ret;
+	char *buf;
+	char *pbuf;
+	char *next;
+	struct cmdline_parts **next_parts;
+
+	*parts = NULL;
+
+	next = pbuf = buf = kstrdup(cmdline, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	next_parts = parts;
+
+	while (next && *pbuf) {
+		next = strchr(pbuf, ';');
+		if (next)
+			*next = '\0';
+
+		ret = parse_parts(next_parts, pbuf);
+		if (ret)
+			goto fail;
+
+		if (next)
+			pbuf = ++next;
+
+		next_parts = &(*next_parts)->next_parts;
+	}
+
+	if (!*parts) {
+		pr_warn("cmdline partition has no valid partition.");
+		ret = -EINVAL;
+		goto fail;
+	}
+
+	ret = 0;
+done:
+	kfree(buf);
+	return ret;
+
+fail:
+	cmdline_parts_free(parts);
+	goto done;
+}
+
+struct cmdline_parts *cmdline_parts_find(struct cmdline_parts *parts,
+					 const char *bdev)
+{
+	while (parts && strncmp(bdev, parts->name, sizeof(parts->name)))
+		parts = parts->next_parts;
+	return parts;
+}
+
+/*
+ *  add_part()
+ *    0 success.
+ *    1 can not add so many partitions.
+ */
+void cmdline_parts_set(struct cmdline_parts *parts, sector_t disk_size,
+		       int slot,
+		       int (*add_part)(int, struct cmdline_subpart *, void *),
+		       void *param)
+
+{
+	sector_t from = 0;
+	struct cmdline_subpart *subpart;
+
+	for (subpart = parts->subpart; subpart;
+	     subpart = subpart->next_subpart, slot++) {
+		if (subpart->from == (sector_t)(~0ULL))
+			subpart->from = from;
+		else
+			from = subpart->from;
+
+		if (from >= disk_size)
+			break;
+
+		if (subpart->size > (disk_size - from))
+			subpart->size = disk_size - from;
+
+		from += subpart->size;
+
+		if (add_part(slot, subpart, param))
+			break;
+	}
+}
diff --git a/block/compat_ioctl.c b/block/compat_ioctl.c
index 7e5d474dc6ba..fbd5a67cb773 100644
--- a/block/compat_ioctl.c
+++ b/block/compat_ioctl.c
@@ -70,7 +70,7 @@ static int compat_hdio_getgeo(struct gendisk *disk, struct block_device *bdev,
 		return ret;
 
 	ret = copy_to_user(ugeo, &geo, 4);
-	ret |= __put_user(geo.start, &ugeo->start);
+	ret |= put_user(geo.start, &ugeo->start);
 	if (ret)
 		ret = -EFAULT;
 
diff --git a/block/deadline-iosched.c b/block/deadline-iosched.c
index 20614a332362..9ef66406c625 100644
--- a/block/deadline-iosched.c
+++ b/block/deadline-iosched.c
@@ -346,7 +346,7 @@ static int deadline_init_queue(struct request_queue *q, struct elevator_type *e)
 	if (!eq)
 		return -ENOMEM;
 
-	dd = kmalloc_node(sizeof(*dd), GFP_KERNEL | __GFP_ZERO, q->node);
+	dd = kzalloc_node(sizeof(*dd), GFP_KERNEL, q->node);
 	if (!dd) {
 		kobject_put(&eq->kobj);
 		return -ENOMEM;
diff --git a/block/elevator.c b/block/elevator.c
index 668394d18588..2bcbd8cc14d4 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -155,7 +155,7 @@ struct elevator_queue *elevator_alloc(struct request_queue *q,
 {
 	struct elevator_queue *eq;
 
-	eq = kmalloc_node(sizeof(*eq), GFP_KERNEL | __GFP_ZERO, q->node);
+	eq = kzalloc_node(sizeof(*eq), GFP_KERNEL, q->node);
 	if (unlikely(!eq))
 		goto err;
 
diff --git a/block/genhd.c b/block/genhd.c
index dadf42b454a3..791f41943132 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -1252,8 +1252,7 @@ struct gendisk *alloc_disk_node(int minors, int node_id)
 {
 	struct gendisk *disk;
 
-	disk = kmalloc_node(sizeof(struct gendisk),
-				GFP_KERNEL | __GFP_ZERO, node_id);
+	disk = kzalloc_node(sizeof(struct gendisk), GFP_KERNEL, node_id);
 	if (disk) {
 		if (!init_part_stats(&disk->part0)) {
 			kfree(disk);
diff --git a/block/partitions/Kconfig b/block/partitions/Kconfig
index 4cebb2f0d2f4..9b29a996c311 100644
--- a/block/partitions/Kconfig
+++ b/block/partitions/Kconfig
@@ -260,3 +260,10 @@ config SYSV68_PARTITION
 	  partition table format used by Motorola Delta machines (using
 	  sysv68).
 	  Otherwise, say N.
+
+config CMDLINE_PARTITION
+	bool "Command line partition support" if PARTITION_ADVANCED
+	select BLK_CMDLINE_PARSER
+	help
+	  Say Y here if you want to read the partition table from bootargs.
+	  The format for the command line is just like mtdparts.
diff --git a/block/partitions/Makefile b/block/partitions/Makefile
index 2be4d7ba4e3a..37a95270503c 100644
--- a/block/partitions/Makefile
+++ b/block/partitions/Makefile
@@ -8,6 +8,7 @@ obj-$(CONFIG_ACORN_PARTITION) += acorn.o
 obj-$(CONFIG_AMIGA_PARTITION) += amiga.o
 obj-$(CONFIG_ATARI_PARTITION) += atari.o
 obj-$(CONFIG_AIX_PARTITION) += aix.o
+obj-$(CONFIG_CMDLINE_PARTITION) += cmdline.o
 obj-$(CONFIG_MAC_PARTITION) += mac.o
 obj-$(CONFIG_LDM_PARTITION) += ldm.o
 obj-$(CONFIG_MSDOS_PARTITION) += msdos.o
diff --git a/block/partitions/check.c b/block/partitions/check.c
index 19ba207ea7d1..9ac1df74f699 100644
--- a/block/partitions/check.c
+++ b/block/partitions/check.c
@@ -34,6 +34,7 @@
 #include "efi.h"
 #include "karma.h"
 #include "sysv68.h"
+#include "cmdline.h"
 
 int warn_no_part = 1; /*This is ugly: should make genhd removable media aware*/
 
@@ -65,6 +66,9 @@ static int (*check_part[])(struct parsed_partitions *) = {
 	adfspart_check_ADFS,
 #endif
 
+#ifdef CONFIG_CMDLINE_PARTITION
+	cmdline_partition,
+#endif
 #ifdef CONFIG_EFI_PARTITION
 	efi_partition,		/* this must come before msdos */
 #endif
diff --git a/block/partitions/cmdline.c b/block/partitions/cmdline.c
new file mode 100644
index 000000000000..5141b563adf1
--- /dev/null
+++ b/block/partitions/cmdline.c
@@ -0,0 +1,99 @@
+/*
+ * Copyright (C) 2013 HUAWEI
+ * Author: Cai Zhiyong <caizhiyong@huawei.com>
+ *
+ * Read block device partition table from the command line.
+ * Typically used for fixed block (eMMC) embedded devices.
+ * It has no MBR, so saves storage space. Bootloader can be easily accessed
+ * by absolute address of data on the block device.
+ * Users can easily change the partition.
+ *
+ * The format for the command line is just like mtdparts.
+ *
+ * For further information, see "Documentation/block/cmdline-partition.txt"
+ *
+ */
+
+#include <linux/cmdline-parser.h>
+
+#include "check.h"
+#include "cmdline.h"
+
+static char *cmdline;
+static struct cmdline_parts *bdev_parts;
+
+static int add_part(int slot, struct cmdline_subpart *subpart, void *param)
+{
+	int label_min;
+	struct partition_meta_info *info;
+	char tmp[sizeof(info->volname) + 4];
+	struct parsed_partitions *state = (struct parsed_partitions *)param;
+
+	if (slot >= state->limit)
+		return 1;
+
+	put_partition(state, slot, subpart->from >> 9,
+		      subpart->size >> 9);
+
+	info = &state->parts[slot].info;
+
+	label_min = min_t(int, sizeof(info->volname) - 1,
+			  sizeof(subpart->name));
+	strncpy(info->volname, subpart->name, label_min);
+	info->volname[label_min] = '\0';
+
+	snprintf(tmp, sizeof(tmp), "(%s)", info->volname);
+	strlcat(state->pp_buf, tmp, PAGE_SIZE);
+
+	state->parts[slot].has_info = true;
+
+	return 0;
+}
+
+static int __init cmdline_parts_setup(char *s)
+{
+	cmdline = s;
+	return 1;
+}
+__setup("blkdevparts=", cmdline_parts_setup);
+
+/*
+ * Purpose: allocate cmdline partitions.
+ * Returns:
+ * -1 if unable to read the partition table
+ *  0 if this isn't our partition table
+ *  1 if successful
+ */
+int cmdline_partition(struct parsed_partitions *state)
+{
+	sector_t disk_size;
+	char bdev[BDEVNAME_SIZE];
+	struct cmdline_parts *parts;
+
+	if (cmdline) {
+		if (bdev_parts)
+			cmdline_parts_free(&bdev_parts);
+
+		if (cmdline_parts_parse(&bdev_parts, cmdline)) {
+			cmdline = NULL;
+			return -1;
+		}
+		cmdline = NULL;
+	}
+
+	if (!bdev_parts)
+		return 0;
+
+	bdevname(state->bdev, bdev);
+	parts = cmdline_parts_find(bdev_parts, bdev);
+	if (!parts)
+		return 0;
+
+	disk_size = get_capacity(state->bdev->bd_disk) << 9;
+
+	cmdline_parts_set(parts, disk_size, 1, add_part, (void *)state);
+
+	strlcat(state->pp_buf, "\n", PAGE_SIZE);
+
+	return 1;
+}
diff --git a/block/partitions/cmdline.h b/block/partitions/cmdline.h
new file mode 100644
index 000000000000..26e0f8da1414
--- /dev/null
+++ b/block/partitions/cmdline.h
@@ -0,0 +1,2 @@
+
+int cmdline_partition(struct parsed_partitions *state);
diff --git a/block/partitions/efi.c b/block/partitions/efi.c
index c85fc895ecdb..a8287b49d062 100644
--- a/block/partitions/efi.c
+++ b/block/partitions/efi.c
@@ -25,6 +25,9 @@
  * TODO:
  *
  * Changelog:
+ * Mon August 5th, 2013 Davidlohr Bueso <davidlohr@hp.com>
+ * - detect hybrid MBRs, tighter pMBR checking & cleanups.
+ *
  * Mon Nov 09 2004 Matt Domsch <Matt_Domsch@dell.com>
  * - test for valid PMBR and valid PGPT before ever reading
  *   AGPT, allow override with 'gpt' kernel command line option.
@@ -149,34 +152,89 @@ static u64 last_lba(struct block_device *bdev)
 		       bdev_logical_block_size(bdev)) - 1ULL;
 }
 
-static inline int
-pmbr_part_valid(struct partition *part)
+static inline int pmbr_part_valid(gpt_mbr_record *part)
 {
-        if (part->sys_ind == EFI_PMBR_OSTYPE_EFI_GPT &&
-            le32_to_cpu(part->start_sect) == 1UL)
-                return 1;
-        return 0;
+	if (part->os_type != EFI_PMBR_OSTYPE_EFI_GPT)
+		goto invalid;
+
+	/* set to 0x00000001 (i.e., the LBA of the GPT Partition Header) */
+	if (le32_to_cpu(part->starting_lba) != GPT_PRIMARY_PARTITION_TABLE_LBA)
+		goto invalid;
+
+	return GPT_MBR_PROTECTIVE;
+invalid:
+	return 0;
 }
 
 /**
  * is_pmbr_valid(): test Protective MBR for validity
  * @mbr: pointer to a legacy mbr structure
+ * @total_sectors: amount of sectors in the device
  *
- * Description: Returns 1 if PMBR is valid, 0 otherwise.
- * Validity depends on two things:
+ * Description: Checks for a valid protective or hybrid
+ * master boot record (MBR). The validity of a pMBR depends
+ * on all of the following properties:
  *  1) MSDOS signature is in the last two bytes of the MBR
  *  2) One partition of type 0xEE is found
+ *
+ * In addition, a hybrid MBR will have up to three additional
+ * primary partitions, which point to the same space that's
+ * marked out by up to three GPT partitions.
+ *
+ * Returns 0 upon invalid MBR, or GPT_MBR_PROTECTIVE or
+ * GPT_MBR_HYBRID depending on the device layout.
  */
-static int
-is_pmbr_valid(legacy_mbr *mbr)
+static int is_pmbr_valid(legacy_mbr *mbr, sector_t total_sectors)
 {
-	int i;
+	uint32_t sz = 0;
+	int i, part = 0, ret = 0; /* invalid by default */
+
 	if (!mbr || le16_to_cpu(mbr->signature) != MSDOS_MBR_SIGNATURE)
-                return 0;
+		goto done;
+
+	for (i = 0; i < 4; i++) {
+		ret = pmbr_part_valid(&mbr->partition_record[i]);
+		if (ret == GPT_MBR_PROTECTIVE) {
+			part = i;
+			/*
+			 * Ok, we at least know that there's a protective MBR,
+			 * now check if there are other partition types for
+			 * hybrid MBR.
+			 */
+			goto check_hybrid;
+		}
+	}
+
+	if (ret != GPT_MBR_PROTECTIVE)
+		goto done;
+check_hybrid:
 	for (i = 0; i < 4; i++)
-		if (pmbr_part_valid(&mbr->partition_record[i]))
-                        return 1;
-	return 0;
+		if ((mbr->partition_record[i].os_type !=
+			EFI_PMBR_OSTYPE_EFI_GPT) &&
+		    (mbr->partition_record[i].os_type != 0x00))
+			ret = GPT_MBR_HYBRID;
+
+	/*
+	 * Protective MBRs take up the lesser of the whole disk
+	 * or 2 TiB (32bit LBA), ignoring the rest of the disk.
+	 * Some partitioning programs, nonetheless, choose to set
+	 * the size to the maximum 32-bit limitation, disregarding
+	 * the disk size.
+	 *
+	 * Hybrid MBRs do not necessarily comply with this.
+	 *
+	 * Consider a bad value here to be a warning to support dd'ing
+	 * an image from a smaller disk to a larger disk.
+	 */
+	if (ret == GPT_MBR_PROTECTIVE) {
+		sz = le32_to_cpu(mbr->partition_record[part].size_in_lba);
+		if (sz != (uint32_t) total_sectors - 1 && sz != 0xFFFFFFFF)
+			pr_debug("GPT: mbr size in lba (%u) different than whole disk (%u).\n",
+				 sz, min_t(uint32_t,
+					   total_sectors - 1, 0xFFFFFFFF));
+	}
+done:
+	return ret;
 }
 
 /**
@@ -243,8 +301,7 @@ static gpt_entry *alloc_read_gpt_entries(struct parsed_partitions *state,
 		return NULL;
 
 	if (read_lba(state, le64_to_cpu(gpt->partition_entry_lba),
-                     (u8 *) pte,
-		     count) < count) {
+			(u8 *) pte, count) < count) {
 		kfree(pte);
                 pte=NULL;
 		return NULL;
@@ -364,7 +421,12 @@ static int is_gpt_valid(struct parsed_partitions *state, u64 lba,
 			 (unsigned long long)lastlba);
 		goto fail;
 	}
-
+	if (le64_to_cpu((*gpt)->last_usable_lba) < le64_to_cpu((*gpt)->first_usable_lba)) {
+		pr_debug("GPT: last_usable_lba incorrect: %lld > %lld\n",
+			 (unsigned long long)le64_to_cpu((*gpt)->last_usable_lba),
+			 (unsigned long long)le64_to_cpu((*gpt)->first_usable_lba));
+		goto fail;
+	}
 	/* Check that sizeof_partition_entry has the correct value */
 	if (le32_to_cpu((*gpt)->sizeof_partition_entry) != sizeof(gpt_entry)) {
 		pr_debug("GUID Partitition Entry Size check failed.\n");
@@ -429,44 +491,42 @@ compare_gpts(gpt_header *pgpt, gpt_header *agpt, u64 lastlba)
 	if (!pgpt || !agpt)
 		return;
 	if (le64_to_cpu(pgpt->my_lba) != le64_to_cpu(agpt->alternate_lba)) {
-		printk(KERN_WARNING
-		       "GPT:Primary header LBA != Alt. header alternate_lba\n");
-		printk(KERN_WARNING "GPT:%lld != %lld\n",
+		pr_warn("GPT:Primary header LBA != Alt. header alternate_lba\n");
+		pr_warn("GPT:%lld != %lld\n",
 		       (unsigned long long)le64_to_cpu(pgpt->my_lba),
                        (unsigned long long)le64_to_cpu(agpt->alternate_lba));
 		error_found++;
 	}
 	if (le64_to_cpu(pgpt->alternate_lba) != le64_to_cpu(agpt->my_lba)) {
-		printk(KERN_WARNING
-		       "GPT:Primary header alternate_lba != Alt. header my_lba\n");
-		printk(KERN_WARNING "GPT:%lld != %lld\n",
+		pr_warn("GPT:Primary header alternate_lba != Alt. header my_lba\n");
+		pr_warn("GPT:%lld != %lld\n",
 		       (unsigned long long)le64_to_cpu(pgpt->alternate_lba),
                        (unsigned long long)le64_to_cpu(agpt->my_lba));
 		error_found++;
 	}
 	if (le64_to_cpu(pgpt->first_usable_lba) !=
             le64_to_cpu(agpt->first_usable_lba)) {
-		printk(KERN_WARNING "GPT:first_usable_lbas don't match.\n");
-		printk(KERN_WARNING "GPT:%lld != %lld\n",
+		pr_warn("GPT:first_usable_lbas don't match.\n");
+		pr_warn("GPT:%lld != %lld\n",
 		       (unsigned long long)le64_to_cpu(pgpt->first_usable_lba),
                        (unsigned long long)le64_to_cpu(agpt->first_usable_lba));
 		error_found++;
 	}
 	if (le64_to_cpu(pgpt->last_usable_lba) !=
             le64_to_cpu(agpt->last_usable_lba)) {
-		printk(KERN_WARNING "GPT:last_usable_lbas don't match.\n");
-		printk(KERN_WARNING "GPT:%lld != %lld\n",
+		pr_warn("GPT:last_usable_lbas don't match.\n");
+		pr_warn("GPT:%lld != %lld\n",
 		       (unsigned long long)le64_to_cpu(pgpt->last_usable_lba),
                        (unsigned long long)le64_to_cpu(agpt->last_usable_lba));
 		error_found++;
 	}
 	if (efi_guidcmp(pgpt->disk_guid, agpt->disk_guid)) {
-		printk(KERN_WARNING "GPT:disk_guids don't match.\n");
+		pr_warn("GPT:disk_guids don't match.\n");
 		error_found++;
 	}
 	if (le32_to_cpu(pgpt->num_partition_entries) !=
             le32_to_cpu(agpt->num_partition_entries)) {
-		printk(KERN_WARNING "GPT:num_partition_entries don't match: "
+		pr_warn("GPT:num_partition_entries don't match: "
 		       "0x%x != 0x%x\n",
 		       le32_to_cpu(pgpt->num_partition_entries),
 		       le32_to_cpu(agpt->num_partition_entries));
@@ -474,8 +534,7 @@ compare_gpts(gpt_header *pgpt, gpt_header *agpt, u64 lastlba)
 	}
 	if (le32_to_cpu(pgpt->sizeof_partition_entry) !=
             le32_to_cpu(agpt->sizeof_partition_entry)) {
-		printk(KERN_WARNING
-		       "GPT:sizeof_partition_entry values don't match: "
+		pr_warn("GPT:sizeof_partition_entry values don't match: "
 		       "0x%x != 0x%x\n",
                        le32_to_cpu(pgpt->sizeof_partition_entry),
 		       le32_to_cpu(agpt->sizeof_partition_entry));
@@ -483,34 +542,30 @@ compare_gpts(gpt_header *pgpt, gpt_header *agpt, u64 lastlba)
 	}
 	if (le32_to_cpu(pgpt->partition_entry_array_crc32) !=
             le32_to_cpu(agpt->partition_entry_array_crc32)) {
-		printk(KERN_WARNING
-		       "GPT:partition_entry_array_crc32 values don't match: "
+		pr_warn("GPT:partition_entry_array_crc32 values don't match: "
 		       "0x%x != 0x%x\n",
                        le32_to_cpu(pgpt->partition_entry_array_crc32),
 		       le32_to_cpu(agpt->partition_entry_array_crc32));
 		error_found++;
 	}
 	if (le64_to_cpu(pgpt->alternate_lba) != lastlba) {
-		printk(KERN_WARNING
-		       "GPT:Primary header thinks Alt. header is not at the end of the disk.\n");
-		printk(KERN_WARNING "GPT:%lld != %lld\n",
+		pr_warn("GPT:Primary header thinks Alt. header is not at the end of the disk.\n");
+		pr_warn("GPT:%lld != %lld\n",
 			(unsigned long long)le64_to_cpu(pgpt->alternate_lba),
 			(unsigned long long)lastlba);
 		error_found++;
 	}
 
 	if (le64_to_cpu(agpt->my_lba) != lastlba) {
-		printk(KERN_WARNING
-		       "GPT:Alternate GPT header not at the end of the disk.\n");
-		printk(KERN_WARNING "GPT:%lld != %lld\n",
+		pr_warn("GPT:Alternate GPT header not at the end of the disk.\n");
+		pr_warn("GPT:%lld != %lld\n",
 			(unsigned long long)le64_to_cpu(agpt->my_lba),
 			(unsigned long long)lastlba);
 		error_found++;
 	}
 
 	if (error_found)
-		printk(KERN_WARNING
-		       "GPT: Use GNU Parted to correct GPT errors.\n");
+		pr_warn("GPT: Use GNU Parted to correct GPT errors.\n");
 	return;
 }
 
@@ -536,6 +591,7 @@ static int find_valid_gpt(struct parsed_partitions *state, gpt_header **gpt,
 	gpt_header *pgpt = NULL, *agpt = NULL;
 	gpt_entry *pptes = NULL, *aptes = NULL;
 	legacy_mbr *legacymbr;
+	sector_t total_sectors = i_size_read(state->bdev->bd_inode) >> 9;
 	u64 lastlba;
 
 	if (!ptes)
@@ -543,17 +599,22 @@ static int find_valid_gpt(struct parsed_partitions *state, gpt_header **gpt,
 
 	lastlba = last_lba(state->bdev);
         if (!force_gpt) {
-                /* This will be added to the EFI Spec. per Intel after v1.02. */
-                legacymbr = kzalloc(sizeof (*legacymbr), GFP_KERNEL);
-                if (legacymbr) {
-                        read_lba(state, 0, (u8 *) legacymbr,
-				 sizeof (*legacymbr));
-                        good_pmbr = is_pmbr_valid(legacymbr);
-                        kfree(legacymbr);
-                }
-                if (!good_pmbr)
-                        goto fail;
-        }
+		/* This will be added to the EFI Spec. per Intel after v1.02. */
+		legacymbr = kzalloc(sizeof(*legacymbr), GFP_KERNEL);
+		if (!legacymbr)
+			goto fail;
+
+		read_lba(state, 0, (u8 *)legacymbr, sizeof(*legacymbr));
+		good_pmbr = is_pmbr_valid(legacymbr, total_sectors);
+		kfree(legacymbr);
+
+		if (!good_pmbr)
+			goto fail;
+
+		pr_debug("Device has a %s MBR\n",
+			 good_pmbr == GPT_MBR_PROTECTIVE ?
+						"protective" : "hybrid");
+	}
 
 	good_pgpt = is_gpt_valid(state, GPT_PRIMARY_PARTITION_TABLE_LBA,
 				 &pgpt, &pptes);
@@ -576,11 +637,8 @@ static int find_valid_gpt(struct parsed_partitions *state, gpt_header **gpt,
                 *ptes = pptes;
                 kfree(agpt);
                 kfree(aptes);
-                if (!good_agpt) {
-                        printk(KERN_WARNING 
-			       "Alternate GPT is invalid, "
-                               "using primary GPT.\n");
-                }
+		if (!good_agpt)
+                        pr_warn("Alternate GPT is invalid, using primary GPT.\n");
                 return 1;
         }
         else if (good_agpt) {
@@ -588,8 +646,7 @@ static int find_valid_gpt(struct parsed_partitions *state, gpt_header **gpt,
                 *ptes = aptes;
                 kfree(pgpt);
                 kfree(pptes);
-                printk(KERN_WARNING 
-                       "Primary GPT is invalid, using alternate GPT.\n");
+		pr_warn("Primary GPT is invalid, using alternate GPT.\n");
                 return 1;
         }
 
@@ -651,8 +708,7 @@ int efi_partition(struct parsed_partitions *state)
 		put_partition(state, i+1, start * ssz, size * ssz);
 
 		/* If this is a RAID volume, tell md */
-		if (!efi_guidcmp(ptes[i].partition_type_guid,
-				 PARTITION_LINUX_RAID_GUID))
+		if (!efi_guidcmp(ptes[i].partition_type_guid, PARTITION_LINUX_RAID_GUID))
 			state->parts[i + 1].flags = ADDPART_FLAG_RAID;
 
 		info = &state->parts[i + 1].info;
diff --git a/block/partitions/efi.h b/block/partitions/efi.h
index b69ab729558f..4efcafba7e64 100644
--- a/block/partitions/efi.h
+++ b/block/partitions/efi.h
@@ -37,6 +37,9 @@
 #define EFI_PMBR_OSTYPE_EFI 0xEF
 #define EFI_PMBR_OSTYPE_EFI_GPT 0xEE
 
+#define GPT_MBR_PROTECTIVE  1
+#define GPT_MBR_HYBRID      2
+
 #define GPT_HEADER_SIGNATURE 0x5452415020494645ULL
 #define GPT_HEADER_REVISION_V1 0x00010000
 #define GPT_PRIMARY_PARTITION_TABLE_LBA 1
@@ -101,11 +104,25 @@ typedef struct _gpt_entry {
 	efi_char16_t partition_name[72 / sizeof (efi_char16_t)];
 } __attribute__ ((packed)) gpt_entry;
 
+typedef struct _gpt_mbr_record {
+	u8	boot_indicator; /* unused by EFI, set to 0x80 for bootable */
+	u8	start_head;     /* unused by EFI, pt start in CHS */
+	u8	start_sector;   /* unused by EFI, pt start in CHS */
+	u8	start_track;
+	u8	os_type;        /* EFI and legacy non-EFI OS types */
+	u8	end_head;       /* unused by EFI, pt end in CHS */
+	u8	end_sector;     /* unused by EFI, pt end in CHS */
+	u8	end_track;      /* unused by EFI, pt end in CHS */
+	__le32	starting_lba;   /* used by EFI - start addr of the on disk pt */
+	__le32	size_in_lba;    /* used by EFI - size of pt in LBA */
+} __packed gpt_mbr_record;
+
+
 typedef struct _legacy_mbr {
 	u8 boot_code[440];
 	__le32 unique_mbr_signature;
 	__le16 unknown;
-	struct partition partition_record[4];
+	gpt_mbr_record partition_record[4];
 	__le16 signature;
 } __attribute__ ((packed)) legacy_mbr;
 
@@ -113,22 +130,3 @@ typedef struct _legacy_mbr {
 extern int efi_partition(struct parsed_partitions *state);
 
 #endif
-
-/*
- * Overrides for Emacs so that we follow Linus's tabbing style.
- * Emacs will notice this stuff at the end of the file and automatically
- * adjust the settings for this buffer only.  This must remain at the end
- * of the file.
- * --------------------------------------------------------------------------
- * Local variables:
- * c-indent-level: 4 
- * c-brace-imaginary-offset: 0
- * c-brace-offset: -4
- * c-argdecl-indent: 4
- * c-label-offset: -4
- * c-continued-statement-offset: 4
- * c-continued-brace-offset: 0
- * indent-tabs-mode: nil
- * tab-width: 8
- * End:
- */
diff --git a/crypto/Kconfig b/crypto/Kconfig
index aca01164f002..69ce573f1224 100644
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
@@ -376,6 +376,25 @@ config CRYPTO_CRC32_PCLMUL
 	  which will enable any routine to use the CRC-32-IEEE 802.3 checksum
 	  and gain better performance as compared with the table implementation.
 
+config CRYPTO_CRCT10DIF
+	tristate "CRCT10DIF algorithm"
+	select CRYPTO_HASH
+	help
+	  CRC T10 Data Integrity Field computation is being cast as
+	  a crypto transform.  This allows for faster crc t10 diff
+	  transforms to be used if they are available.
+
+config CRYPTO_CRCT10DIF_PCLMUL
+	tristate "CRCT10DIF PCLMULQDQ hardware acceleration"
+	depends on X86 && 64BIT && CRC_T10DIF
+	select CRYPTO_HASH
+	help
+	  For x86_64 processors with SSE4.2 and PCLMULQDQ supported,
+	  CRC T10 DIF PCLMULQDQ computation can be hardware
+	  accelerated PCLMULQDQ instruction. This option will create
+	  'crct10dif-plcmul' module, which is faster when computing the
+	  crct10dif checksum as compared with the generic table implementation.
+
 config CRYPTO_GHASH
 	tristate "GHASH digest algorithm"
 	select CRYPTO_GF128MUL
diff --git a/crypto/Makefile b/crypto/Makefile
index 2ba0df2f908f..80019ba8da3a 100644
--- a/crypto/Makefile
+++ b/crypto/Makefile
@@ -83,6 +83,7 @@ obj-$(CONFIG_CRYPTO_ZLIB) += zlib.o
 obj-$(CONFIG_CRYPTO_MICHAEL_MIC) += michael_mic.o
 obj-$(CONFIG_CRYPTO_CRC32C) += crc32c.o
 obj-$(CONFIG_CRYPTO_CRC32) += crc32.o
+obj-$(CONFIG_CRYPTO_CRCT10DIF) += crct10dif_common.o crct10dif_generic.o
 obj-$(CONFIG_CRYPTO_AUTHENC) += authenc.o authencesn.o
 obj-$(CONFIG_CRYPTO_LZO) += lzo.o
 obj-$(CONFIG_CRYPTO_LZ4) += lz4.o
diff --git a/crypto/aes_generic.c b/crypto/aes_generic.c
index 47f2e5c71759..fd0d6b454975 100644
--- a/crypto/aes_generic.c
+++ b/crypto/aes_generic.c
@@ -62,7 +62,7 @@ static inline u8 byte(const u32 x, const unsigned n)
 
 static const u32 rco_tab[10] = { 1, 2, 4, 8, 16, 32, 64, 128, 27, 54 };
 
-const u32 crypto_ft_tab[4][256] = {
+__visible const u32 crypto_ft_tab[4][256] = {
 	{
 		0xa56363c6, 0x847c7cf8, 0x997777ee, 0x8d7b7bf6,
 		0x0df2f2ff, 0xbd6b6bd6, 0xb16f6fde, 0x54c5c591,
@@ -326,7 +326,7 @@ const u32 crypto_ft_tab[4][256] = {
 	}
 };
 
-const u32 crypto_fl_tab[4][256] = {
+__visible const u32 crypto_fl_tab[4][256] = {
 	{
 		0x00000063, 0x0000007c, 0x00000077, 0x0000007b,
 		0x000000f2, 0x0000006b, 0x0000006f, 0x000000c5,
@@ -590,7 +590,7 @@ const u32 crypto_fl_tab[4][256] = {
 	}
 };
 
-const u32 crypto_it_tab[4][256] = {
+__visible const u32 crypto_it_tab[4][256] = {
 	{
 		0x50a7f451, 0x5365417e, 0xc3a4171a, 0x965e273a,
 		0xcb6bab3b, 0xf1459d1f, 0xab58faac, 0x9303e34b,
@@ -854,7 +854,7 @@ const u32 crypto_it_tab[4][256] = {
 	}
 };
 
-const u32 crypto_il_tab[4][256] = {
+__visible const u32 crypto_il_tab[4][256] = {
 	{
 		0x00000052, 0x00000009, 0x0000006a, 0x000000d5,
 		0x00000030, 0x00000036, 0x000000a5, 0x00000038,
diff --git a/crypto/api.c b/crypto/api.c
index 3b6180336d3d..a2b39c5f3649 100644
--- a/crypto/api.c
+++ b/crypto/api.c
@@ -34,6 +34,8 @@ EXPORT_SYMBOL_GPL(crypto_alg_sem);
 BLOCKING_NOTIFIER_HEAD(crypto_chain);
 EXPORT_SYMBOL_GPL(crypto_chain);
 
+static struct crypto_alg *crypto_larval_wait(struct crypto_alg *alg);
+
 struct crypto_alg *crypto_mod_get(struct crypto_alg *alg)
 {
 	return try_module_get(alg->cra_module) ? crypto_alg_get(alg) : NULL;
@@ -144,8 +146,11 @@ static struct crypto_alg *crypto_larval_add(const char *name, u32 type,
 	}
 	up_write(&crypto_alg_sem);
 
-	if (alg != &larval->alg)
+	if (alg != &larval->alg) {
 		kfree(larval);
+		if (crypto_is_larval(alg))
+			alg = crypto_larval_wait(alg);
+	}
 
 	return alg;
 }
@@ -391,7 +396,7 @@ EXPORT_SYMBOL_GPL(__crypto_alloc_tfm);
  *	@mask: Mask for type comparison
  *
  *	This function should not be used by new algorithm types.
- *	Plesae use crypto_alloc_tfm instead.
+ *	Please use crypto_alloc_tfm instead.
  *
  *	crypto_alloc_base() will first attempt to locate an already loaded
  *	algorithm.  If that fails and the kernel supports dynamically loadable
diff --git a/crypto/camellia_generic.c b/crypto/camellia_generic.c
index 75efa2052305..26bcd7a2d6b4 100644
--- a/crypto/camellia_generic.c
+++ b/crypto/camellia_generic.c
@@ -388,8 +388,8 @@ static void camellia_setup_tail(u32 *subkey, u32 *subL, u32 *subR, int max)
 	/* round 6 */
 	subL[7] ^= subL[1]; subR[7] ^= subR[1];
 	subL[1] ^= subR[1] & ~subR[9];
-	dw = subL[1] & subL[9],
-		subR[1] ^= rol32(dw, 1); /* modified for FLinv(kl2) */
+	dw = subL[1] & subL[9];
+	subR[1] ^= rol32(dw, 1); /* modified for FLinv(kl2) */
 	/* round 8 */
 	subL[11] ^= subL[1]; subR[11] ^= subR[1];
 	/* round 10 */
@@ -397,8 +397,8 @@ static void camellia_setup_tail(u32 *subkey, u32 *subL, u32 *subR, int max)
 	/* round 12 */
 	subL[15] ^= subL[1]; subR[15] ^= subR[1];
 	subL[1] ^= subR[1] & ~subR[17];
-	dw = subL[1] & subL[17],
-		subR[1] ^= rol32(dw, 1); /* modified for FLinv(kl4) */
+	dw = subL[1] & subL[17];
+	subR[1] ^= rol32(dw, 1); /* modified for FLinv(kl4) */
 	/* round 14 */
 	subL[19] ^= subL[1]; subR[19] ^= subR[1];
 	/* round 16 */
@@ -413,8 +413,8 @@ static void camellia_setup_tail(u32 *subkey, u32 *subL, u32 *subR, int max)
 		kw4l = subL[25]; kw4r = subR[25];
 	} else {
 		subL[1] ^= subR[1] & ~subR[25];
-		dw = subL[1] & subL[25],
-			subR[1] ^= rol32(dw, 1); /* modified for FLinv(kl6) */
+		dw = subL[1] & subL[25];
+		subR[1] ^= rol32(dw, 1); /* modified for FLinv(kl6) */
 		/* round 20 */
 		subL[27] ^= subL[1]; subR[27] ^= subR[1];
 		/* round 22 */
@@ -433,8 +433,8 @@ static void camellia_setup_tail(u32 *subkey, u32 *subL, u32 *subR, int max)
 		/* round 19 */
 		subL[26] ^= kw4l; subR[26] ^= kw4r;
 		kw4l ^= kw4r & ~subR[24];
-		dw = kw4l & subL[24],
-			kw4r ^= rol32(dw, 1); /* modified for FL(kl5) */
+		dw = kw4l & subL[24];
+		kw4r ^= rol32(dw, 1); /* modified for FL(kl5) */
 	}
 	/* round 17 */
 	subL[22] ^= kw4l; subR[22] ^= kw4r;
@@ -443,8 +443,8 @@ static void camellia_setup_tail(u32 *subkey, u32 *subL, u32 *subR, int max)
 	/* round 13 */
 	subL[18] ^= kw4l; subR[18] ^= kw4r;
 	kw4l ^= kw4r & ~subR[16];
-	dw = kw4l & subL[16],
-		kw4r ^= rol32(dw, 1); /* modified for FL(kl3) */
+	dw = kw4l & subL[16];
+	kw4r ^= rol32(dw, 1); /* modified for FL(kl3) */
 	/* round 11 */
 	subL[14] ^= kw4l; subR[14] ^= kw4r;
 	/* round 9 */
@@ -452,8 +452,8 @@ static void camellia_setup_tail(u32 *subkey, u32 *subL, u32 *subR, int max)
 	/* round 7 */
 	subL[10] ^= kw4l; subR[10] ^= kw4r;
 	kw4l ^= kw4r & ~subR[8];
-	dw = kw4l & subL[8],
-		kw4r ^= rol32(dw, 1); /* modified for FL(kl1) */
+	dw = kw4l & subL[8];
+	kw4r ^= rol32(dw, 1); /* modified for FL(kl1) */
 	/* round 5 */
 	subL[6] ^= kw4l; subR[6] ^= kw4r;
 	/* round 3 */
@@ -477,8 +477,8 @@ static void camellia_setup_tail(u32 *subkey, u32 *subL, u32 *subR, int max)
 	SUBKEY_L(6) = subL[5] ^ subL[7]; /* round 5 */
 	SUBKEY_R(6) = subR[5] ^ subR[7];
 	tl = subL[10] ^ (subR[10] & ~subR[8]);
-	dw = tl & subL[8],  /* FL(kl1) */
-		tr = subR[10] ^ rol32(dw, 1);
+	dw = tl & subL[8];  /* FL(kl1) */
+	tr = subR[10] ^ rol32(dw, 1);
 	SUBKEY_L(7) = subL[6] ^ tl; /* round 6 */
 	SUBKEY_R(7) = subR[6] ^ tr;
 	SUBKEY_L(8) = subL[8];       /* FL(kl1) */
@@ -486,8 +486,8 @@ static void camellia_setup_tail(u32 *subkey, u32 *subL, u32 *subR, int max)
 	SUBKEY_L(9) = subL[9];       /* FLinv(kl2) */
 	SUBKEY_R(9) = subR[9];
 	tl = subL[7] ^ (subR[7] & ~subR[9]);
-	dw = tl & subL[9],  /* FLinv(kl2) */
-		tr = subR[7] ^ rol32(dw, 1);
+	dw = tl & subL[9];  /* FLinv(kl2) */
+	tr = subR[7] ^ rol32(dw, 1);
 	SUBKEY_L(10) = tl ^ subL[11]; /* round 7 */
 	SUBKEY_R(10) = tr ^ subR[11];
 	SUBKEY_L(11) = subL[10] ^ subL[12]; /* round 8 */
@@ -499,8 +499,8 @@ static void camellia_setup_tail(u32 *subkey, u32 *subL, u32 *subR, int max)
 	SUBKEY_L(14) = subL[13] ^ subL[15]; /* round 11 */
 	SUBKEY_R(14) = subR[13] ^ subR[15];
 	tl = subL[18] ^ (subR[18] & ~subR[16]);
-	dw = tl & subL[16], /* FL(kl3) */
-		tr = subR[18] ^ rol32(dw, 1);
+	dw = tl & subL[16]; /* FL(kl3) */
+	tr = subR[18] ^ rol32(dw, 1);
 	SUBKEY_L(15) = subL[14] ^ tl; /* round 12 */
 	SUBKEY_R(15) = subR[14] ^ tr;
 	SUBKEY_L(16) = subL[16];     /* FL(kl3) */
@@ -508,8 +508,8 @@ static void camellia_setup_tail(u32 *subkey, u32 *subL, u32 *subR, int max)
 	SUBKEY_L(17) = subL[17];     /* FLinv(kl4) */
 	SUBKEY_R(17) = subR[17];
 	tl = subL[15] ^ (subR[15] & ~subR[17]);
-	dw = tl & subL[17], /* FLinv(kl4) */
-		tr = subR[15] ^ rol32(dw, 1);
+	dw = tl & subL[17]; /* FLinv(kl4) */
+	tr = subR[15] ^ rol32(dw, 1);
 	SUBKEY_L(18) = tl ^ subL[19]; /* round 13 */
 	SUBKEY_R(18) = tr ^ subR[19];
 	SUBKEY_L(19) = subL[18] ^ subL[20]; /* round 14 */
@@ -527,8 +527,8 @@ static void camellia_setup_tail(u32 *subkey, u32 *subL, u32 *subR, int max)
 		SUBKEY_R(24) = subR[24] ^ subR[23];
 	} else {
 		tl = subL[26] ^ (subR[26] & ~subR[24]);
-		dw = tl & subL[24], /* FL(kl5) */
-			tr = subR[26] ^ rol32(dw, 1);
+		dw = tl & subL[24]; /* FL(kl5) */
+		tr = subR[26] ^ rol32(dw, 1);
 		SUBKEY_L(23) = subL[22] ^ tl; /* round 18 */
 		SUBKEY_R(23) = subR[22] ^ tr;
 		SUBKEY_L(24) = subL[24];     /* FL(kl5) */
@@ -536,8 +536,8 @@ static void camellia_setup_tail(u32 *subkey, u32 *subL, u32 *subR, int max)
 		SUBKEY_L(25) = subL[25];     /* FLinv(kl6) */
 		SUBKEY_R(25) = subR[25];
 		tl = subL[23] ^ (subR[23] & ~subR[25]);
-		dw = tl & subL[25], /* FLinv(kl6) */
-			tr = subR[23] ^ rol32(dw, 1);
+		dw = tl & subL[25]; /* FLinv(kl6) */
+		tr = subR[23] ^ rol32(dw, 1);
 		SUBKEY_L(26) = tl ^ subL[27]; /* round 19 */
 		SUBKEY_R(26) = tr ^ subR[27];
 		SUBKEY_L(27) = subL[26] ^ subL[28]; /* round 20 */
diff --git a/crypto/cast_common.c b/crypto/cast_common.c
index a15f523d5f56..117dd8250f27 100644
--- a/crypto/cast_common.c
+++ b/crypto/cast_common.c
@@ -15,7 +15,7 @@
 #include <linux/module.h>
 #include <crypto/cast_common.h>
 
-const u32 cast_s1[256] = {
+__visible const u32 cast_s1[256] = {
 	0x30fb40d4, 0x9fa0ff0b, 0x6beccd2f, 0x3f258c7a, 0x1e213f2f,
 	0x9c004dd3, 0x6003e540, 0xcf9fc949,
 	0xbfd4af27, 0x88bbbdb5, 0xe2034090, 0x98d09675, 0x6e63a0e0,
@@ -83,7 +83,7 @@ const u32 cast_s1[256] = {
 };
 EXPORT_SYMBOL_GPL(cast_s1);
 
-const u32 cast_s2[256] = {
+__visible const u32 cast_s2[256] = {
 	0x1f201094, 0xef0ba75b, 0x69e3cf7e, 0x393f4380, 0xfe61cf7a,
 	0xeec5207a, 0x55889c94, 0x72fc0651,
 	0xada7ef79, 0x4e1d7235, 0xd55a63ce, 0xde0436ba, 0x99c430ef,
@@ -151,7 +151,7 @@ const u32 cast_s2[256] = {
 };
 EXPORT_SYMBOL_GPL(cast_s2);
 
-const u32 cast_s3[256] = {
+__visible const u32 cast_s3[256] = {
 	0x8defc240, 0x25fa5d9f, 0xeb903dbf, 0xe810c907, 0x47607fff,
 	0x369fe44b, 0x8c1fc644, 0xaececa90,
 	0xbeb1f9bf, 0xeefbcaea, 0xe8cf1950, 0x51df07ae, 0x920e8806,
@@ -219,7 +219,7 @@ const u32 cast_s3[256] = {
 };
 EXPORT_SYMBOL_GPL(cast_s3);
 
-const u32 cast_s4[256] = {
+__visible const u32 cast_s4[256] = {
 	0x9db30420, 0x1fb6e9de, 0xa7be7bef, 0xd273a298, 0x4a4f7bdb,
 	0x64ad8c57, 0x85510443, 0xfa020ed1,
 	0x7e287aff, 0xe60fb663, 0x095f35a1, 0x79ebf120, 0xfd059d43,
diff --git a/crypto/crct10dif_common.c b/crypto/crct10dif_common.c
new file mode 100644
index 000000000000..b2fab366f518
--- /dev/null
+++ b/crypto/crct10dif_common.c
@@ -0,0 +1,82 @@
+/*
+ * Cryptographic API.
+ *
+ * T10 Data Integrity Field CRC16 Crypto Transform
+ *
+ * Copyright (c) 2007 Oracle Corporation.  All rights reserved.
+ * Written by Martin K. Petersen <martin.petersen@oracle.com>
+ * Copyright (C) 2013 Intel Corporation
+ * Author: Tim Chen <tim.c.chen@linux.intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ *
+ */
+
+#include <linux/crc-t10dif.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+
+/* Table generated using the following polynomium:
+ * x^16 + x^15 + x^11 + x^9 + x^8 + x^7 + x^5 + x^4 + x^2 + x + 1
+ * gt: 0x8bb7
+ */
+static const __u16 t10_dif_crc_table[256] = {
+	0x0000, 0x8BB7, 0x9CD9, 0x176E, 0xB205, 0x39B2, 0x2EDC, 0xA56B,
+	0xEFBD, 0x640A, 0x7364, 0xF8D3, 0x5DB8, 0xD60F, 0xC161, 0x4AD6,
+	0x54CD, 0xDF7A, 0xC814, 0x43A3, 0xE6C8, 0x6D7F, 0x7A11, 0xF1A6,
+	0xBB70, 0x30C7, 0x27A9, 0xAC1E, 0x0975, 0x82C2, 0x95AC, 0x1E1B,
+	0xA99A, 0x222D, 0x3543, 0xBEF4, 0x1B9F, 0x9028, 0x8746, 0x0CF1,
+	0x4627, 0xCD90, 0xDAFE, 0x5149, 0xF422, 0x7F95, 0x68FB, 0xE34C,
+	0xFD57, 0x76E0, 0x618E, 0xEA39, 0x4F52, 0xC4E5, 0xD38B, 0x583C,
+	0x12EA, 0x995D, 0x8E33, 0x0584, 0xA0EF, 0x2B58, 0x3C36, 0xB781,
+	0xD883, 0x5334, 0x445A, 0xCFED, 0x6A86, 0xE131, 0xF65F, 0x7DE8,
+	0x373E, 0xBC89, 0xABE7, 0x2050, 0x853B, 0x0E8C, 0x19E2, 0x9255,
+	0x8C4E, 0x07F9, 0x1097, 0x9B20, 0x3E4B, 0xB5FC, 0xA292, 0x2925,
+	0x63F3, 0xE844, 0xFF2A, 0x749D, 0xD1F6, 0x5A41, 0x4D2F, 0xC698,
+	0x7119, 0xFAAE, 0xEDC0, 0x6677, 0xC31C, 0x48AB, 0x5FC5, 0xD472,
+	0x9EA4, 0x1513, 0x027D, 0x89CA, 0x2CA1, 0xA716, 0xB078, 0x3BCF,
+	0x25D4, 0xAE63, 0xB90D, 0x32BA, 0x97D1, 0x1C66, 0x0B08, 0x80BF,
+	0xCA69, 0x41DE, 0x56B0, 0xDD07, 0x786C, 0xF3DB, 0xE4B5, 0x6F02,
+	0x3AB1, 0xB106, 0xA668, 0x2DDF, 0x88B4, 0x0303, 0x146D, 0x9FDA,
+	0xD50C, 0x5EBB, 0x49D5, 0xC262, 0x6709, 0xECBE, 0xFBD0, 0x7067,
+	0x6E7C, 0xE5CB, 0xF2A5, 0x7912, 0xDC79, 0x57CE, 0x40A0, 0xCB17,
+	0x81C1, 0x0A76, 0x1D18, 0x96AF, 0x33C4, 0xB873, 0xAF1D, 0x24AA,
+	0x932B, 0x189C, 0x0FF2, 0x8445, 0x212E, 0xAA99, 0xBDF7, 0x3640,
+	0x7C96, 0xF721, 0xE04F, 0x6BF8, 0xCE93, 0x4524, 0x524A, 0xD9FD,
+	0xC7E6, 0x4C51, 0x5B3F, 0xD088, 0x75E3, 0xFE54, 0xE93A, 0x628D,
+	0x285B, 0xA3EC, 0xB482, 0x3F35, 0x9A5E, 0x11E9, 0x0687, 0x8D30,
+	0xE232, 0x6985, 0x7EEB, 0xF55C, 0x5037, 0xDB80, 0xCCEE, 0x4759,
+	0x0D8F, 0x8638, 0x9156, 0x1AE1, 0xBF8A, 0x343D, 0x2353, 0xA8E4,
+	0xB6FF, 0x3D48, 0x2A26, 0xA191, 0x04FA, 0x8F4D, 0x9823, 0x1394,
+	0x5942, 0xD2F5, 0xC59B, 0x4E2C, 0xEB47, 0x60F0, 0x779E, 0xFC29,
+	0x4BA8, 0xC01F, 0xD771, 0x5CC6, 0xF9AD, 0x721A, 0x6574, 0xEEC3,
+	0xA415, 0x2FA2, 0x38CC, 0xB37B, 0x1610, 0x9DA7, 0x8AC9, 0x017E,
+	0x1F65, 0x94D2, 0x83BC, 0x080B, 0xAD60, 0x26D7, 0x31B9, 0xBA0E,
+	0xF0D8, 0x7B6F, 0x6C01, 0xE7B6, 0x42DD, 0xC96A, 0xDE04, 0x55B3
+};
+
+__u16 crc_t10dif_generic(__u16 crc, const unsigned char *buffer, size_t len)
+{
+	unsigned int i;
+
+	for (i = 0 ; i < len ; i++)
+		crc = (crc << 8) ^ t10_dif_crc_table[((crc >> 8) ^ buffer[i]) & 0xff];
+
+	return crc;
+}
+EXPORT_SYMBOL(crc_t10dif_generic);
+
+MODULE_DESCRIPTION("T10 DIF CRC calculation common code");
+MODULE_LICENSE("GPL");
diff --git a/crypto/crct10dif_generic.c b/crypto/crct10dif_generic.c
new file mode 100644
index 000000000000..877e7114ec5c
--- /dev/null
+++ b/crypto/crct10dif_generic.c
@@ -0,0 +1,127 @@
+/*
+ * Cryptographic API.
+ *
+ * T10 Data Integrity Field CRC16 Crypto Transform
+ *
+ * Copyright (c) 2007 Oracle Corporation.  All rights reserved.
+ * Written by Martin K. Petersen <martin.petersen@oracle.com>
+ * Copyright (C) 2013 Intel Corporation
+ * Author: Tim Chen <tim.c.chen@linux.intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/crc-t10dif.h>
+#include <crypto/internal/hash.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+
+struct chksum_desc_ctx {
+	__u16 crc;
+};
+
+/*
+ * Steps through buffer one byte at at time, calculates reflected
+ * crc using table.
+ */
+
+static int chksum_init(struct shash_desc *desc)
+{
+	struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
+
+	ctx->crc = 0;
+
+	return 0;
+}
+
+static int chksum_update(struct shash_desc *desc, const u8 *data,
+			 unsigned int length)
+{
+	struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
+
+	ctx->crc = crc_t10dif_generic(ctx->crc, data, length);
+	return 0;
+}
+
+static int chksum_final(struct shash_desc *desc, u8 *out)
+{
+	struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
+
+	*(__u16 *)out = ctx->crc;
+	return 0;
+}
+
+static int __chksum_finup(__u16 *crcp, const u8 *data, unsigned int len,
+			u8 *out)
+{
+	*(__u16 *)out = crc_t10dif_generic(*crcp, data, len);
+	return 0;
+}
+
+static int chksum_finup(struct shash_desc *desc, const u8 *data,
+			unsigned int len, u8 *out)
+{
+	struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
+
+	return __chksum_finup(&ctx->crc, data, len, out);
+}
+
+static int chksum_digest(struct shash_desc *desc, const u8 *data,
+			 unsigned int length, u8 *out)
+{
+	struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
+
+	return __chksum_finup(&ctx->crc, data, length, out);
+}
+
+static struct shash_alg alg = {
+	.digestsize		=	CRC_T10DIF_DIGEST_SIZE,
+	.init		=	chksum_init,
+	.update		=	chksum_update,
+	.final		=	chksum_final,
+	.finup		=	chksum_finup,
+	.digest		=	chksum_digest,
+	.descsize		=	sizeof(struct chksum_desc_ctx),
+	.base			=	{
+		.cra_name		=	"crct10dif",
+		.cra_driver_name	=	"crct10dif-generic",
+		.cra_priority		=	100,
+		.cra_blocksize		=	CRC_T10DIF_BLOCK_SIZE,
+		.cra_module		=	THIS_MODULE,
+	}
+};
+
+static int __init crct10dif_mod_init(void)
+{
+	int ret;
+
+	ret = crypto_register_shash(&alg);
+	return ret;
+}
+
+static void __exit crct10dif_mod_fini(void)
+{
+	crypto_unregister_shash(&alg);
+}
+
+module_init(crct10dif_mod_init);
+module_exit(crct10dif_mod_fini);
+
+MODULE_AUTHOR("Tim Chen <tim.c.chen@linux.intel.com>");
+MODULE_DESCRIPTION("T10 DIF CRC calculation.");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("crct10dif");
diff --git a/crypto/fcrypt.c b/crypto/fcrypt.c
index 3b2cf569c684..021d7fec6bc8 100644
--- a/crypto/fcrypt.c
+++ b/crypto/fcrypt.c
@@ -110,7 +110,7 @@ static const __be32 sbox0[256] = {
 };
 
 #undef Z
-#define Z(x) cpu_to_be32((x << 27) | (x >> 5))
+#define Z(x) cpu_to_be32(((x & 0x1f) << 27) | (x >> 5))
 static const __be32 sbox1[256] = {
 	Z(0x77), Z(0x14), Z(0xa6), Z(0xfe), Z(0xb2), Z(0x5e), Z(0x8c), Z(0x3e),
 	Z(0x67), Z(0x6c), Z(0xa1), Z(0x0d), Z(0xc2), Z(0xa2), Z(0xc1), Z(0x85),
diff --git a/crypto/scatterwalk.c b/crypto/scatterwalk.c
index 7281b8a93ad3..79ca2278c2a3 100644
--- a/crypto/scatterwalk.c
+++ b/crypto/scatterwalk.c
@@ -124,3 +124,25 @@ void scatterwalk_map_and_copy(void *buf, struct scatterlist *sg,
 	scatterwalk_done(&walk, out, 0);
 }
 EXPORT_SYMBOL_GPL(scatterwalk_map_and_copy);
+
+int scatterwalk_bytes_sglen(struct scatterlist *sg, int num_bytes)
+{
+	int offset = 0, n = 0;
+
+	/* num_bytes is too small */
+	if (num_bytes < sg->length)
+		return -1;
+
+	do {
+		offset += sg->length;
+		n++;
+		sg = scatterwalk_sg_next(sg);
+
+		/* num_bytes is too large */
+		if (unlikely(!sg && (num_bytes < offset)))
+			return -1;
+	} while (sg && (num_bytes > offset));
+
+	return n;
+}
+EXPORT_SYMBOL_GPL(scatterwalk_bytes_sglen);
diff --git a/crypto/tcrypt.c b/crypto/tcrypt.c
index 66d254ce0d11..25a5934f0e50 100644
--- a/crypto/tcrypt.c
+++ b/crypto/tcrypt.c
@@ -1174,6 +1174,10 @@ static int do_test(int m)
 		ret += tcrypt_test("ghash");
 		break;
 
+	case 47:
+		ret += tcrypt_test("crct10dif");
+		break;
+
 	case 100:
 		ret += tcrypt_test("hmac(md5)");
 		break;
@@ -1498,6 +1502,10 @@ static int do_test(int m)
 		test_hash_speed("crc32c", sec, generic_hash_speed_template);
 		if (mode > 300 && mode < 400) break;
 
+	case 320:
+		test_hash_speed("crct10dif", sec, generic_hash_speed_template);
+		if (mode > 300 && mode < 400) break;
+
 	case 399:
 		break;
 
diff --git a/crypto/testmgr.c b/crypto/testmgr.c
index ecddf921a9db..e091ef6e1791 100644
--- a/crypto/testmgr.c
+++ b/crypto/testmgr.c
@@ -2046,6 +2046,16 @@ static const struct alg_test_desc alg_test_descs[] = {
 			}
 		}
 	}, {
+		.alg = "crct10dif",
+		.test = alg_test_hash,
+		.fips_allowed = 1,
+		.suite = {
+			.hash = {
+				.vecs = crct10dif_tv_template,
+				.count = CRCT10DIF_TEST_VECTORS
+			}
+		}
+	}, {
 		.alg = "cryptd(__driver-cbc-aes-aesni)",
 		.test = alg_test_null,
 		.fips_allowed = 1,
@@ -3224,7 +3234,7 @@ int alg_test(const char *driver, const char *alg, u32 type, u32 mask)
 	if (i >= 0)
 		rc |= alg_test_descs[i].test(alg_test_descs + i, driver,
 					     type, mask);
-	if (j >= 0)
+	if (j >= 0 && j != i)
 		rc |= alg_test_descs[j].test(alg_test_descs + j, driver,
 					     type, mask);
 
diff --git a/crypto/testmgr.h b/crypto/testmgr.h
index 1e701bc075b9..7d44aa3d6b44 100644
--- a/crypto/testmgr.h
+++ b/crypto/testmgr.h
@@ -450,6 +450,39 @@ static struct hash_testvec rmd320_tv_template[] = {
 	}
 };
 
+#define CRCT10DIF_TEST_VECTORS	3
+static struct hash_testvec crct10dif_tv_template[] = {
+	{
+		.plaintext = "abc",
+		.psize  = 3,
+#ifdef __LITTLE_ENDIAN
+		.digest = "\x3b\x44",
+#else
+		.digest = "\x44\x3b",
+#endif
+	}, {
+		.plaintext = "1234567890123456789012345678901234567890"
+			     "123456789012345678901234567890123456789",
+		.psize	= 79,
+#ifdef __LITTLE_ENDIAN
+		.digest	= "\x70\x4b",
+#else
+		.digest	= "\x4b\x70",
+#endif
+	}, {
+		.plaintext =
+		"abcddddddddddddddddddddddddddddddddddddddddddddddddddddd",
+		.psize  = 56,
+#ifdef __LITTLE_ENDIAN
+		.digest = "\xe3\x9c",
+#else
+		.digest = "\x9c\xe3",
+#endif
+		.np     = 2,
+		.tap    = { 28, 28 }
+	}
+};
+
 /*
  * SHA1 test vectors  from from FIPS PUB 180-1
  * Long vector from CAVS 5.0
diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig
index 100bd724f648..6efe2ac6902f 100644
--- a/drivers/acpi/Kconfig
+++ b/drivers/acpi/Kconfig
@@ -24,7 +24,7 @@ menuconfig ACPI
 	  are configured, ACPI is used.
 
 	  The project home page for the Linux ACPI subsystem is here:
-	  <http://www.lesswatts.org/projects/acpi/>
+	  <https://01.org/linux-acpi>
 
 	  Linux support for ACPI is based on Intel Corporation's ACPI
 	  Component Architecture (ACPI CA).  For more information on the
@@ -91,24 +91,6 @@ config ACPI_EC_DEBUGFS
 	  Thus this option is a debug option that helps to write ACPI drivers
 	  and can be used to identify ACPI code or EC firmware bugs.
 
-config ACPI_PROC_EVENT
-	bool "Deprecated /proc/acpi/event support"
-	depends on PROC_FS
-	default y
-	help
-	  A user-space daemon, acpid, typically reads /proc/acpi/event
-	  and handles all ACPI-generated events.
-
-	  These events are now delivered to user-space either
-	  via the input layer or as netlink events.
-
-	  This build option enables the old code for legacy
-	  user-space implementation.  After some time, this will
-	  be moved under CONFIG_ACPI_PROCFS, and then deleted.
-
-	  Say Y here to retain the old behaviour.  Say N if your
-	  user-space is newer than kernel 2.6.23 (September 2007).
-
 config ACPI_AC
 	tristate "AC Adapter"
 	depends on X86
@@ -141,9 +123,9 @@ config ACPI_BUTTON
 	default y
 	help
 	  This driver handles events on the power, sleep, and lid buttons.
-	  A daemon reads /proc/acpi/event and perform user-defined actions
-	  such as shutting down the system.  This is necessary for
-	  software-controlled poweroff.
+	  A daemon reads events from input devices or via netlink and
+	  performs user-defined actions such as shutting down the system.
+	  This is necessary for software-controlled poweroff.
 
 	  To compile this driver as a module, choose M here:
 	  the module will be called button.
@@ -180,12 +162,6 @@ config ACPI_DOCK
 	  This driver supports ACPI-controlled docking stations and removable
 	  drive bays such as the IBM Ultrabay and the Dell Module Bay.
 
-config ACPI_I2C
-	def_tristate I2C
-	depends on I2C
-	help
-	  ACPI I2C enumeration support.
-
 config ACPI_PROCESSOR
 	tristate "Processor"
 	select THERMAL
diff --git a/drivers/acpi/Makefile b/drivers/acpi/Makefile
index 81dbeb83bb45..cdaf68b58b00 100644
--- a/drivers/acpi/Makefile
+++ b/drivers/acpi/Makefile
@@ -73,7 +73,6 @@ obj-$(CONFIG_ACPI_HED)		+= hed.o
 obj-$(CONFIG_ACPI_EC_DEBUGFS)	+= ec_sys.o
 obj-$(CONFIG_ACPI_CUSTOM_METHOD)+= custom_method.o
 obj-$(CONFIG_ACPI_BGRT)		+= bgrt.o
-obj-$(CONFIG_ACPI_I2C)		+= acpi_i2c.o
 
 # processor has its own "processor." module_param namespace
 processor-y			:= processor_driver.o processor_throttling.o
diff --git a/drivers/acpi/ac.c b/drivers/acpi/ac.c
index 4f4e741d34b2..f37beaa32750 100644
--- a/drivers/acpi/ac.c
+++ b/drivers/acpi/ac.c
@@ -267,7 +267,6 @@ static void acpi_ac_notify(struct acpi_device *device, u32 event)
 			msleep(ac_sleep_before_get_state_ms);
 
 		acpi_ac_get_state(ac);
-		acpi_bus_generate_proc_event(device, event, (u32) ac->state);
 		acpi_bus_generate_netlink_event(device->pnp.device_class,
 						  dev_name(&device->dev), event,
 						  (u32) ac->state);
diff --git a/drivers/acpi/acpi_i2c.c b/drivers/acpi/acpi_i2c.c
deleted file mode 100644
index a82c7626aa9b..000000000000
--- a/drivers/acpi/acpi_i2c.c
+++ /dev/null
@@ -1,103 +0,0 @@
-/*
- * ACPI I2C enumeration support
- *
- * Copyright (C) 2012, Intel Corporation
- * Author: Mika Westerberg <mika.westerberg@linux.intel.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/acpi.h>
-#include <linux/device.h>
-#include <linux/export.h>
-#include <linux/i2c.h>
-#include <linux/ioport.h>
-
-ACPI_MODULE_NAME("i2c");
-
-static int acpi_i2c_add_resource(struct acpi_resource *ares, void *data)
-{
-	struct i2c_board_info *info = data;
-
-	if (ares->type == ACPI_RESOURCE_TYPE_SERIAL_BUS) {
-		struct acpi_resource_i2c_serialbus *sb;
-
-		sb = &ares->data.i2c_serial_bus;
-		if (sb->type == ACPI_RESOURCE_SERIAL_TYPE_I2C) {
-			info->addr = sb->slave_address;
-			if (sb->access_mode == ACPI_I2C_10BIT_MODE)
-				info->flags |= I2C_CLIENT_TEN;
-		}
-	} else if (info->irq < 0) {
-		struct resource r;
-
-		if (acpi_dev_resource_interrupt(ares, 0, &r))
-			info->irq = r.start;
-	}
-
-	/* Tell the ACPI core to skip this resource */
-	return 1;
-}
-
-static acpi_status acpi_i2c_add_device(acpi_handle handle, u32 level,
-				       void *data, void **return_value)
-{
-	struct i2c_adapter *adapter = data;
-	struct list_head resource_list;
-	struct i2c_board_info info;
-	struct acpi_device *adev;
-	int ret;
-
-	if (acpi_bus_get_device(handle, &adev))
-		return AE_OK;
-	if (acpi_bus_get_status(adev) || !adev->status.present)
-		return AE_OK;
-
-	memset(&info, 0, sizeof(info));
-	info.acpi_node.handle = handle;
-	info.irq = -1;
-
-	INIT_LIST_HEAD(&resource_list);
-	ret = acpi_dev_get_resources(adev, &resource_list,
-				     acpi_i2c_add_resource, &info);
-	acpi_dev_free_resource_list(&resource_list);
-
-	if (ret < 0 || !info.addr)
-		return AE_OK;
-
-	strlcpy(info.type, dev_name(&adev->dev), sizeof(info.type));
-	if (!i2c_new_device(adapter, &info)) {
-		dev_err(&adapter->dev,
-			"failed to add I2C device %s from ACPI\n",
-			dev_name(&adev->dev));
-	}
-
-	return AE_OK;
-}
-
-/**
- * acpi_i2c_register_devices - enumerate I2C slave devices behind adapter
- * @adapter: pointer to adapter
- *
- * Enumerate all I2C slave devices behind this adapter by walking the ACPI
- * namespace. When a device is found it will be added to the Linux device
- * model and bound to the corresponding ACPI handle.
- */
-void acpi_i2c_register_devices(struct i2c_adapter *adapter)
-{
-	acpi_handle handle;
-	acpi_status status;
-
-	handle = ACPI_HANDLE(adapter->dev.parent);
-	if (!handle)
-		return;
-
-	status = acpi_walk_namespace(ACPI_TYPE_DEVICE, handle, 1,
-				     acpi_i2c_add_device, NULL,
-				     adapter, NULL);
-	if (ACPI_FAILURE(status))
-		dev_warn(&adapter->dev, "failed to enumerate I2C slaves\n");
-}
-EXPORT_SYMBOL_GPL(acpi_i2c_register_devices);
diff --git a/drivers/acpi/acpi_ipmi.c b/drivers/acpi/acpi_ipmi.c
index f40acef80269..a6977e12d574 100644
--- a/drivers/acpi/acpi_ipmi.c
+++ b/drivers/acpi/acpi_ipmi.c
@@ -39,6 +39,7 @@
 #include <linux/ipmi.h>
 #include <linux/device.h>
 #include <linux/pnp.h>
+#include <linux/spinlock.h>
 
 MODULE_AUTHOR("Zhao Yakui");
 MODULE_DESCRIPTION("ACPI IPMI Opregion driver");
@@ -57,7 +58,7 @@ struct acpi_ipmi_device {
 	struct list_head head;
 	/* the IPMI request message list */
 	struct list_head tx_msg_list;
-	struct mutex	tx_msg_lock;
+	spinlock_t	tx_msg_lock;
 	acpi_handle handle;
 	struct pnp_dev *pnp_dev;
 	ipmi_user_t	user_interface;
@@ -147,6 +148,7 @@ static void acpi_format_ipmi_msg(struct acpi_ipmi_msg *tx_msg,
 	struct kernel_ipmi_msg *msg;
 	struct acpi_ipmi_buffer *buffer;
 	struct acpi_ipmi_device *device;
+	unsigned long flags;
 
 	msg = &tx_msg->tx_message;
 	/*
@@ -177,10 +179,10 @@ static void acpi_format_ipmi_msg(struct acpi_ipmi_msg *tx_msg,
 
 	/* Get the msgid */
 	device = tx_msg->device;
-	mutex_lock(&device->tx_msg_lock);
+	spin_lock_irqsave(&device->tx_msg_lock, flags);
 	device->curr_msgid++;
 	tx_msg->tx_msgid = device->curr_msgid;
-	mutex_unlock(&device->tx_msg_lock);
+	spin_unlock_irqrestore(&device->tx_msg_lock, flags);
 }
 
 static void acpi_format_ipmi_response(struct acpi_ipmi_msg *msg,
@@ -242,6 +244,7 @@ static void ipmi_msg_handler(struct ipmi_recv_msg *msg, void *user_msg_data)
 	int msg_found = 0;
 	struct acpi_ipmi_msg *tx_msg;
 	struct pnp_dev *pnp_dev = ipmi_device->pnp_dev;
+	unsigned long flags;
 
 	if (msg->user != ipmi_device->user_interface) {
 		dev_warn(&pnp_dev->dev, "Unexpected response is returned. "
@@ -250,7 +253,7 @@ static void ipmi_msg_handler(struct ipmi_recv_msg *msg, void *user_msg_data)
 		ipmi_free_recv_msg(msg);
 		return;
 	}
-	mutex_lock(&ipmi_device->tx_msg_lock);
+	spin_lock_irqsave(&ipmi_device->tx_msg_lock, flags);
 	list_for_each_entry(tx_msg, &ipmi_device->tx_msg_list, head) {
 		if (msg->msgid == tx_msg->tx_msgid) {
 			msg_found = 1;
@@ -258,7 +261,7 @@ static void ipmi_msg_handler(struct ipmi_recv_msg *msg, void *user_msg_data)
 		}
 	}
 
-	mutex_unlock(&ipmi_device->tx_msg_lock);
+	spin_unlock_irqrestore(&ipmi_device->tx_msg_lock, flags);
 	if (!msg_found) {
 		dev_warn(&pnp_dev->dev, "Unexpected response (msg id %ld) is "
 			"returned.\n", msg->msgid);
@@ -378,6 +381,7 @@ acpi_ipmi_space_handler(u32 function, acpi_physical_address address,
 	struct acpi_ipmi_device *ipmi_device = handler_context;
 	int err, rem_time;
 	acpi_status status;
+	unsigned long flags;
 	/*
 	 * IPMI opregion message.
 	 * IPMI message is firstly written to the BMC and system software
@@ -395,9 +399,9 @@ acpi_ipmi_space_handler(u32 function, acpi_physical_address address,
 		return AE_NO_MEMORY;
 
 	acpi_format_ipmi_msg(tx_msg, address, value);
-	mutex_lock(&ipmi_device->tx_msg_lock);
+	spin_lock_irqsave(&ipmi_device->tx_msg_lock, flags);
 	list_add_tail(&tx_msg->head, &ipmi_device->tx_msg_list);
-	mutex_unlock(&ipmi_device->tx_msg_lock);
+	spin_unlock_irqrestore(&ipmi_device->tx_msg_lock, flags);
 	err = ipmi_request_settime(ipmi_device->user_interface,
 					&tx_msg->addr,
 					tx_msg->tx_msgid,
@@ -413,9 +417,9 @@ acpi_ipmi_space_handler(u32 function, acpi_physical_address address,
 	status = AE_OK;
 
 end_label:
-	mutex_lock(&ipmi_device->tx_msg_lock);
+	spin_lock_irqsave(&ipmi_device->tx_msg_lock, flags);
 	list_del(&tx_msg->head);
-	mutex_unlock(&ipmi_device->tx_msg_lock);
+	spin_unlock_irqrestore(&ipmi_device->tx_msg_lock, flags);
 	kfree(tx_msg);
 	return status;
 }
@@ -457,7 +461,7 @@ static void acpi_add_ipmi_device(struct acpi_ipmi_device *ipmi_device)
 
 	INIT_LIST_HEAD(&ipmi_device->head);
 
-	mutex_init(&ipmi_device->tx_msg_lock);
+	spin_lock_init(&ipmi_device->tx_msg_lock);
 	INIT_LIST_HEAD(&ipmi_device->tx_msg_list);
 	ipmi_install_space_handler(ipmi_device);
 
diff --git a/drivers/acpi/acpi_lpss.c b/drivers/acpi/acpi_lpss.c
index 6a382188fa20..fb78bb9ad8f6 100644
--- a/drivers/acpi/acpi_lpss.c
+++ b/drivers/acpi/acpi_lpss.c
@@ -257,12 +257,13 @@ static int acpi_lpss_create_device(struct acpi_device *adev,
 				pdata->mmio_size = resource_size(&rentry->res);
 			pdata->mmio_base = ioremap(rentry->res.start,
 						   pdata->mmio_size);
-			pdata->dev_desc = dev_desc;
 			break;
 		}
 
 	acpi_dev_free_resource_list(&resource_list);
 
+	pdata->dev_desc = dev_desc;
+
 	if (dev_desc->clk_required) {
 		ret = register_device_clock(adev, pdata);
 		if (ret) {
diff --git a/drivers/acpi/acpi_pad.c b/drivers/acpi/acpi_pad.c
index 27bb6a91de5f..fc6008fbce35 100644
--- a/drivers/acpi/acpi_pad.c
+++ b/drivers/acpi/acpi_pad.c
@@ -231,16 +231,19 @@ static struct task_struct *ps_tsks[NR_CPUS];
 static unsigned int ps_tsk_num;
 static int create_power_saving_task(void)
 {
-	int rc = -ENOMEM;
+	int rc;
 
 	ps_tsks[ps_tsk_num] = kthread_run(power_saving_thread,
 		(void *)(unsigned long)ps_tsk_num,
 		"acpi_pad/%d", ps_tsk_num);
-	rc = PTR_RET(ps_tsks[ps_tsk_num]);
-	if (!rc)
-		ps_tsk_num++;
-	else
+
+	if (IS_ERR(ps_tsks[ps_tsk_num])) {
+		rc = PTR_ERR(ps_tsks[ps_tsk_num]);
 		ps_tsks[ps_tsk_num] = NULL;
+	} else {
+		rc = 0;
+		ps_tsk_num++;
+	}
 
 	return rc;
 }
@@ -452,7 +455,6 @@ static void acpi_pad_notify(acpi_handle handle, u32 event,
 	switch (event) {
 	case ACPI_PROCESSOR_AGGREGATOR_NOTIFY:
 		acpi_pad_handle_notify(handle);
-		acpi_bus_generate_proc_event(device, event, 0);
 		acpi_bus_generate_netlink_event(device->pnp.device_class,
 			dev_name(&device->dev), event, 0);
 		break;
diff --git a/drivers/acpi/acpi_platform.c b/drivers/acpi/acpi_platform.c
index fafec5ddf17f..1bde12708f9e 100644
--- a/drivers/acpi/acpi_platform.c
+++ b/drivers/acpi/acpi_platform.c
@@ -52,7 +52,7 @@ int acpi_create_platform_device(struct acpi_device *adev,
 	struct platform_device_info pdevinfo;
 	struct resource_list_entry *rentry;
 	struct list_head resource_list;
-	struct resource *resources;
+	struct resource *resources = NULL;
 	int count;
 
 	/* If the ACPI node already has a physical device attached, skip it. */
@@ -61,20 +61,22 @@ int acpi_create_platform_device(struct acpi_device *adev,
 
 	INIT_LIST_HEAD(&resource_list);
 	count = acpi_dev_get_resources(adev, &resource_list, NULL, NULL);
-	if (count <= 0)
+	if (count < 0) {
 		return 0;
+	} else if (count > 0) {
+		resources = kmalloc(count * sizeof(struct resource),
+				    GFP_KERNEL);
+		if (!resources) {
+			dev_err(&adev->dev, "No memory for resources\n");
+			acpi_dev_free_resource_list(&resource_list);
+			return -ENOMEM;
+		}
+		count = 0;
+		list_for_each_entry(rentry, &resource_list, node)
+			resources[count++] = rentry->res;
 
-	resources = kmalloc(count * sizeof(struct resource), GFP_KERNEL);
-	if (!resources) {
-		dev_err(&adev->dev, "No memory for resources\n");
 		acpi_dev_free_resource_list(&resource_list);
-		return -ENOMEM;
 	}
-	count = 0;
-	list_for_each_entry(rentry, &resource_list, node)
-		resources[count++] = rentry->res;
-
-	acpi_dev_free_resource_list(&resource_list);
 
 	memset(&pdevinfo, 0, sizeof(pdevinfo));
 	/*
diff --git a/drivers/acpi/acpi_processor.c b/drivers/acpi/acpi_processor.c
index 5a74a9c1e42c..f29e06efa479 100644
--- a/drivers/acpi/acpi_processor.c
+++ b/drivers/acpi/acpi_processor.c
@@ -178,14 +178,17 @@ static int acpi_processor_hotadd_init(struct acpi_processor *pr)
 	if (ACPI_FAILURE(status) || !(sta & ACPI_STA_DEVICE_PRESENT))
 		return -ENODEV;
 
+	cpu_maps_update_begin();
+	cpu_hotplug_begin();
+
 	ret = acpi_map_lsapic(pr->handle, &pr->id);
 	if (ret)
-		return ret;
+		goto out;
 
 	ret = arch_register_cpu(pr->id);
 	if (ret) {
 		acpi_unmap_lsapic(pr->id);
-		return ret;
+		goto out;
 	}
 
 	/*
@@ -195,7 +198,11 @@ static int acpi_processor_hotadd_init(struct acpi_processor *pr)
 	 */
 	pr_info("CPU%d has been hot-added\n", pr->id);
 	pr->flags.need_hotplug_init = 1;
-	return 0;
+
+out:
+	cpu_hotplug_done();
+	cpu_maps_update_done();
+	return ret;
 }
 #else
 static inline int acpi_processor_hotadd_init(struct acpi_processor *pr)
@@ -452,11 +459,15 @@ static void acpi_processor_remove(struct acpi_device *device)
 	per_cpu(processor_device_array, pr->id) = NULL;
 	per_cpu(processors, pr->id) = NULL;
 
+	cpu_maps_update_begin();
+	cpu_hotplug_begin();
+
 	/* Remove the CPU. */
-	get_online_cpus();
 	arch_unregister_cpu(pr->id);
 	acpi_unmap_lsapic(pr->id);
-	put_online_cpus();
+
+	cpu_hotplug_done();
+	cpu_maps_update_done();
 
 	try_offline_node(cpu_to_node(pr->id));
 
diff --git a/drivers/acpi/acpica/acglobal.h b/drivers/acpi/acpica/acglobal.h
index b8d38117a20c..90e846f985fa 100644
--- a/drivers/acpi/acpica/acglobal.h
+++ b/drivers/acpi/acpica/acglobal.h
@@ -138,6 +138,12 @@ u8 ACPI_INIT_GLOBAL(acpi_gbl_disable_auto_repair, FALSE);
  */
 u8 ACPI_INIT_GLOBAL(acpi_gbl_disable_ssdt_table_load, FALSE);
 
+/*
+ * We keep track of the latest version of Windows that has been requested by
+ * the BIOS.
+ */
+u8 ACPI_INIT_GLOBAL(acpi_gbl_osi_data, 0);
+
 /* acpi_gbl_FADT is a local copy of the FADT, converted to a common format. */
 
 struct acpi_table_fadt acpi_gbl_FADT;
@@ -285,7 +291,6 @@ ACPI_EXTERN u8 acpi_gbl_debugger_configuration;
 ACPI_EXTERN u8 acpi_gbl_step_to_next_call;
 ACPI_EXTERN u8 acpi_gbl_acpi_hardware_present;
 ACPI_EXTERN u8 acpi_gbl_events_initialized;
-ACPI_EXTERN u8 acpi_gbl_osi_data;
 ACPI_EXTERN struct acpi_interface_info *acpi_gbl_supported_interfaces;
 ACPI_EXTERN struct acpi_address_range
     *acpi_gbl_address_range_list[ACPI_ADDRESS_RANGE_MAX];
diff --git a/drivers/acpi/acpica/aclocal.h b/drivers/acpi/acpica/aclocal.h
index d4a4901637cd..0ed00669cd21 100644
--- a/drivers/acpi/acpica/aclocal.h
+++ b/drivers/acpi/acpica/aclocal.h
@@ -942,6 +942,9 @@ struct acpi_interface_info {
 
 #define ACPI_OSI_INVALID                0x01
 #define ACPI_OSI_DYNAMIC                0x02
+#define ACPI_OSI_FEATURE                0x04
+#define ACPI_OSI_DEFAULT_INVALID        0x08
+#define ACPI_OSI_OPTIONAL_FEATURE       (ACPI_OSI_FEATURE | ACPI_OSI_DEFAULT_INVALID | ACPI_OSI_INVALID)
 
 struct acpi_port_info {
 	char *name;
@@ -1030,6 +1033,7 @@ struct acpi_external_list {
 	u8 type;
 	u8 flags;
 	u8 resolved;
+	u8 emitted;
 };
 
 /* Values for Flags field above */
diff --git a/drivers/acpi/acpica/acnamesp.h b/drivers/acpi/acpica/acnamesp.h
index b83dc32a5ae0..40b04bd5579e 100644
--- a/drivers/acpi/acpica/acnamesp.h
+++ b/drivers/acpi/acpica/acnamesp.h
@@ -104,8 +104,8 @@ acpi_ns_walk_namespace(acpi_object_type type,
 		       acpi_handle start_object,
 		       u32 max_depth,
 		       u32 flags,
-		       acpi_walk_callback pre_order_visit,
-		       acpi_walk_callback post_order_visit,
+		       acpi_walk_callback descending_callback,
+		       acpi_walk_callback ascending_callback,
 		       void *context, void **return_value);
 
 struct acpi_namespace_node *acpi_ns_get_next_node(struct acpi_namespace_node
diff --git a/drivers/acpi/acpica/actables.h b/drivers/acpi/acpica/actables.h
index 7755e915a007..c54f42c64fe2 100644
--- a/drivers/acpi/acpica/actables.h
+++ b/drivers/acpi/acpica/actables.h
@@ -47,6 +47,13 @@
 acpi_status acpi_allocate_root_table(u32 initial_table_count);
 
 /*
+ * tbxfroot - Root pointer utilities
+ */
+acpi_status acpi_tb_validate_rsdp(struct acpi_table_rsdp *rsdp);
+
+u8 *acpi_tb_scan_memory_for_rsdp(u8 *start_address, u32 length);
+
+/*
  * tbfadt - FADT parse/convert/validate
  */
 void acpi_tb_parse_fadt(u32 table_index);
diff --git a/drivers/acpi/acpica/acutils.h b/drivers/acpi/acpica/acutils.h
index 3c76edea6803..d5a62a6182bb 100644
--- a/drivers/acpi/acpica/acutils.h
+++ b/drivers/acpi/acpica/acutils.h
@@ -470,6 +470,8 @@ acpi_status acpi_ut_install_interface(acpi_string interface_name);
 
 acpi_status acpi_ut_remove_interface(acpi_string interface_name);
 
+acpi_status acpi_ut_update_interfaces(u8 action);
+
 struct acpi_interface_info *acpi_ut_get_interface(acpi_string interface_name);
 
 acpi_status acpi_ut_osi_implementation(struct acpi_walk_state *walk_state);
@@ -616,7 +618,7 @@ int acpi_ut_stricmp(char *string1, char *string2);
 
 acpi_status acpi_ut_strtoul64(char *string, u32 base, u64 *ret_integer);
 
-void acpi_ut_print_string(char *string, u8 max_length);
+void acpi_ut_print_string(char *string, u16 max_length);
 
 void ut_convert_backslashes(char *pathname);
 
diff --git a/drivers/acpi/acpica/evgpeinit.c b/drivers/acpi/acpica/evgpeinit.c
index 9037f17c9608..7842700346a4 100644
--- a/drivers/acpi/acpica/evgpeinit.c
+++ b/drivers/acpi/acpica/evgpeinit.c
@@ -125,7 +125,6 @@ acpi_status acpi_ev_gpe_initialize(void)
 		/* GPE block 0 exists (has both length and address > 0) */
 
 		register_count0 = (u16)(acpi_gbl_FADT.gpe0_block_length / 2);
-
 		gpe_number_max =
 		    (register_count0 * ACPI_GPE_REGISTER_WIDTH) - 1;
 
@@ -204,16 +203,6 @@ acpi_status acpi_ev_gpe_initialize(void)
 		goto cleanup;
 	}
 
-	/* Check for Max GPE number out-of-range */
-
-	if (gpe_number_max > ACPI_GPE_MAX) {
-		ACPI_ERROR((AE_INFO,
-			    "Maximum GPE number from FADT is too large: 0x%X",
-			    gpe_number_max));
-		status = AE_BAD_VALUE;
-		goto cleanup;
-	}
-
       cleanup:
 	(void)acpi_ut_release_mutex(ACPI_MTX_NAMESPACE);
 	return_ACPI_STATUS(AE_OK);
diff --git a/drivers/acpi/acpica/exdump.c b/drivers/acpi/acpica/exdump.c
index c740f24e3101..4d046faac48c 100644
--- a/drivers/acpi/acpica/exdump.c
+++ b/drivers/acpi/acpica/exdump.c
@@ -338,6 +338,7 @@ acpi_ex_dump_object(union acpi_operand_object *obj_desc,
 {
 	u8 *target;
 	char *name;
+	const char *reference_name;
 	u8 count;
 
 	if (!info) {
@@ -426,10 +427,9 @@ acpi_ex_dump_object(union acpi_operand_object *obj_desc,
 
 		case ACPI_EXD_REFERENCE:
 
+			reference_name = acpi_ut_get_reference_name(obj_desc);
 			acpi_ex_out_string("Class Name",
-					   ACPI_CAST_PTR(char,
-							 acpi_ut_get_reference_name
-							 (obj_desc)));
+					   ACPI_CAST_PTR(char, reference_name));
 			acpi_ex_dump_reference_obj(obj_desc);
 			break;
 
diff --git a/drivers/acpi/acpica/exoparg1.c b/drivers/acpi/acpica/exoparg1.c
index 814b4a3d656a..2cdd41d8ade6 100644
--- a/drivers/acpi/acpica/exoparg1.c
+++ b/drivers/acpi/acpica/exoparg1.c
@@ -962,10 +962,17 @@ acpi_status acpi_ex_opcode_1A_0T_1R(struct acpi_walk_state *walk_state)
 					 */
 					return_desc =
 					    *(operand[0]->reference.where);
-					if (return_desc) {
-						acpi_ut_add_reference
-						    (return_desc);
+					if (!return_desc) {
+						/*
+						 * Element is NULL, do not allow the dereference.
+						 * This provides compatibility with other ACPI
+						 * implementations.
+						 */
+						return_ACPI_STATUS
+						    (AE_AML_UNINITIALIZED_ELEMENT);
 					}
+
+					acpi_ut_add_reference(return_desc);
 					break;
 
 				default:
@@ -990,11 +997,40 @@ acpi_status acpi_ex_opcode_1A_0T_1R(struct acpi_walk_state *walk_state)
 									 acpi_namespace_node
 									 *)
 									return_desc);
-				}
+					if (!return_desc) {
+						break;
+					}
 
-				/* Add another reference to the object! */
+					/*
+					 * June 2013:
+					 * buffer_fields/field_units require additional resolution
+					 */
+					switch (return_desc->common.type) {
+					case ACPI_TYPE_BUFFER_FIELD:
+					case ACPI_TYPE_LOCAL_REGION_FIELD:
+					case ACPI_TYPE_LOCAL_BANK_FIELD:
+					case ACPI_TYPE_LOCAL_INDEX_FIELD:
 
-				acpi_ut_add_reference(return_desc);
+						status =
+						    acpi_ex_read_data_from_field
+						    (walk_state, return_desc,
+						     &temp_desc);
+						if (ACPI_FAILURE(status)) {
+							goto cleanup;
+						}
+
+						return_desc = temp_desc;
+						break;
+
+					default:
+
+						/* Add another reference to the object */
+
+						acpi_ut_add_reference
+						    (return_desc);
+						break;
+					}
+				}
 				break;
 
 			default:
diff --git a/drivers/acpi/acpica/exstore.c b/drivers/acpi/acpica/exstore.c
index 2bdba6f7d762..f0b09bf9887d 100644
--- a/drivers/acpi/acpica/exstore.c
+++ b/drivers/acpi/acpica/exstore.c
@@ -57,6 +57,11 @@ acpi_ex_store_object_to_index(union acpi_operand_object *val_desc,
 			      union acpi_operand_object *dest_desc,
 			      struct acpi_walk_state *walk_state);
 
+static acpi_status
+acpi_ex_store_direct_to_node(union acpi_operand_object *source_desc,
+			     struct acpi_namespace_node *node,
+			     struct acpi_walk_state *walk_state);
+
 /*******************************************************************************
  *
  * FUNCTION:    acpi_ex_store
@@ -375,7 +380,11 @@ acpi_ex_store_object_to_index(union acpi_operand_object *source_desc,
  *              When storing into an object the data is converted to the
  *              target object type then stored in the object. This means
  *              that the target object type (for an initialized target) will
- *              not be changed by a store operation.
+ *              not be changed by a store operation. A copy_object can change
+ *              the target type, however.
+ *
+ *              The implicit_conversion flag is set to NO/FALSE only when
+ *              storing to an arg_x -- as per the rules of the ACPI spec.
  *
  *              Assumes parameters are already validated.
  *
@@ -399,7 +408,7 @@ acpi_ex_store_object_to_node(union acpi_operand_object *source_desc,
 	target_type = acpi_ns_get_type(node);
 	target_desc = acpi_ns_get_attached_object(node);
 
-	ACPI_DEBUG_PRINT((ACPI_DB_EXEC, "Storing %p(%s) into node %p(%s)\n",
+	ACPI_DEBUG_PRINT((ACPI_DB_EXEC, "Storing %p (%s) to node %p (%s)\n",
 			  source_desc,
 			  acpi_ut_get_object_type_name(source_desc), node,
 			  acpi_ut_get_type_name(target_type)));
@@ -413,45 +422,30 @@ acpi_ex_store_object_to_node(union acpi_operand_object *source_desc,
 		return_ACPI_STATUS(status);
 	}
 
-	/* If no implicit conversion, drop into the default case below */
-
-	if ((!implicit_conversion) ||
-	    ((walk_state->opcode == AML_COPY_OP) &&
-	     (target_type != ACPI_TYPE_LOCAL_REGION_FIELD) &&
-	     (target_type != ACPI_TYPE_LOCAL_BANK_FIELD) &&
-	     (target_type != ACPI_TYPE_LOCAL_INDEX_FIELD))) {
-		/*
-		 * Force execution of default (no implicit conversion). Note:
-		 * copy_object does not perform an implicit conversion, as per the ACPI
-		 * spec -- except in case of region/bank/index fields -- because these
-		 * objects must retain their original type permanently.
-		 */
-		target_type = ACPI_TYPE_ANY;
-	}
-
 	/* Do the actual store operation */
 
 	switch (target_type) {
-	case ACPI_TYPE_BUFFER_FIELD:
-	case ACPI_TYPE_LOCAL_REGION_FIELD:
-	case ACPI_TYPE_LOCAL_BANK_FIELD:
-	case ACPI_TYPE_LOCAL_INDEX_FIELD:
-
-		/* For fields, copy the source data to the target field. */
-
-		status = acpi_ex_write_data_to_field(source_desc, target_desc,
-						     &walk_state->result_obj);
-		break;
-
 	case ACPI_TYPE_INTEGER:
 	case ACPI_TYPE_STRING:
 	case ACPI_TYPE_BUFFER:
 		/*
-		 * These target types are all of type Integer/String/Buffer, and
-		 * therefore support implicit conversion before the store.
-		 *
-		 * Copy and/or convert the source object to a new target object
+		 * The simple data types all support implicit source operand
+		 * conversion before the store.
 		 */
+
+		if ((walk_state->opcode == AML_COPY_OP) || !implicit_conversion) {
+			/*
+			 * However, copy_object and Stores to arg_x do not perform
+			 * an implicit conversion, as per the ACPI specification.
+			 * A direct store is performed instead.
+			 */
+			status = acpi_ex_store_direct_to_node(source_desc, node,
+							      walk_state);
+			break;
+		}
+
+		/* Store with implicit source operand conversion support */
+
 		status =
 		    acpi_ex_store_object_to_object(source_desc, target_desc,
 						   &new_desc, walk_state);
@@ -465,13 +459,12 @@ acpi_ex_store_object_to_node(union acpi_operand_object *source_desc,
 			 * the Name's type to that of the value being stored in it.
 			 * source_desc reference count is incremented by attach_object.
 			 *
-			 * Note: This may change the type of the node if an explicit store
-			 * has been performed such that the node/object type has been
-			 * changed.
+			 * Note: This may change the type of the node if an explicit
+			 * store has been performed such that the node/object type
+			 * has been changed.
 			 */
-			status =
-			    acpi_ns_attach_object(node, new_desc,
-						  new_desc->common.type);
+			status = acpi_ns_attach_object(node, new_desc,
+						       new_desc->common.type);
 
 			ACPI_DEBUG_PRINT((ACPI_DB_EXEC,
 					  "Store %s into %s via Convert/Attach\n",
@@ -482,38 +475,83 @@ acpi_ex_store_object_to_node(union acpi_operand_object *source_desc,
 		}
 		break;
 
-	default:
-
-		ACPI_DEBUG_PRINT((ACPI_DB_EXEC,
-				  "Storing [%s] (%p) directly into node [%s] (%p)"
-				  " with no implicit conversion\n",
-				  acpi_ut_get_object_type_name(source_desc),
-				  source_desc,
-				  acpi_ut_get_object_type_name(target_desc),
-				  node));
+	case ACPI_TYPE_BUFFER_FIELD:
+	case ACPI_TYPE_LOCAL_REGION_FIELD:
+	case ACPI_TYPE_LOCAL_BANK_FIELD:
+	case ACPI_TYPE_LOCAL_INDEX_FIELD:
+		/*
+		 * For all fields, always write the source data to the target
+		 * field. Any required implicit source operand conversion is
+		 * performed in the function below as necessary. Note, field
+		 * objects must retain their original type permanently.
+		 */
+		status = acpi_ex_write_data_to_field(source_desc, target_desc,
+						     &walk_state->result_obj);
+		break;
 
+	default:
 		/*
 		 * No conversions for all other types. Directly store a copy of
-		 * the source object. NOTE: This is a departure from the ACPI
-		 * spec, which states "If conversion is impossible, abort the
-		 * running control method".
+		 * the source object. This is the ACPI spec-defined behavior for
+		 * the copy_object operator.
 		 *
-		 * This code implements "If conversion is impossible, treat the
-		 * Store operation as a CopyObject".
+		 * NOTE: For the Store operator, this is a departure from the
+		 * ACPI spec, which states "If conversion is impossible, abort
+		 * the running control method". Instead, this code implements
+		 * "If conversion is impossible, treat the Store operation as
+		 * a CopyObject".
 		 */
-		status =
-		    acpi_ut_copy_iobject_to_iobject(source_desc, &new_desc,
-						    walk_state);
-		if (ACPI_FAILURE(status)) {
-			return_ACPI_STATUS(status);
-		}
-
-		status =
-		    acpi_ns_attach_object(node, new_desc,
-					  new_desc->common.type);
-		acpi_ut_remove_reference(new_desc);
+		status = acpi_ex_store_direct_to_node(source_desc, node,
+						      walk_state);
 		break;
 	}
 
 	return_ACPI_STATUS(status);
 }
+
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_ex_store_direct_to_node
+ *
+ * PARAMETERS:  source_desc             - Value to be stored
+ *              node                    - Named object to receive the value
+ *              walk_state              - Current walk state
+ *
+ * RETURN:      Status
+ *
+ * DESCRIPTION: "Store" an object directly to a node. This involves a copy
+ *              and an attach.
+ *
+ ******************************************************************************/
+
+static acpi_status
+acpi_ex_store_direct_to_node(union acpi_operand_object *source_desc,
+			     struct acpi_namespace_node *node,
+			     struct acpi_walk_state *walk_state)
+{
+	acpi_status status;
+	union acpi_operand_object *new_desc;
+
+	ACPI_FUNCTION_TRACE(ex_store_direct_to_node);
+
+	ACPI_DEBUG_PRINT((ACPI_DB_EXEC,
+			  "Storing [%s] (%p) directly into node [%s] (%p)"
+			  " with no implicit conversion\n",
+			  acpi_ut_get_object_type_name(source_desc),
+			  source_desc, acpi_ut_get_type_name(node->type),
+			  node));
+
+	/* Copy the source object to a new object */
+
+	status =
+	    acpi_ut_copy_iobject_to_iobject(source_desc, &new_desc, walk_state);
+	if (ACPI_FAILURE(status)) {
+		return_ACPI_STATUS(status);
+	}
+
+	/* Attach the new object to the node */
+
+	status = acpi_ns_attach_object(node, new_desc, new_desc->common.type);
+	acpi_ut_remove_reference(new_desc);
+	return_ACPI_STATUS(status);
+}
diff --git a/drivers/acpi/acpica/hwesleep.c b/drivers/acpi/acpica/hwesleep.c
index 5e5f76230f5e..414076818d40 100644
--- a/drivers/acpi/acpica/hwesleep.c
+++ b/drivers/acpi/acpica/hwesleep.c
@@ -43,6 +43,7 @@
  */
 
 #include <acpi/acpi.h>
+#include <linux/acpi.h>
 #include "accommon.h"
 
 #define _COMPONENT          ACPI_HARDWARE
@@ -128,6 +129,14 @@ acpi_status acpi_hw_extended_sleep(u8 sleep_state)
 
 	ACPI_FLUSH_CPU_CACHE();
 
+	status = acpi_os_prepare_extended_sleep(sleep_state,
+						acpi_gbl_sleep_type_a,
+						acpi_gbl_sleep_type_b);
+	if (ACPI_SKIP(status))
+		return_ACPI_STATUS(AE_OK);
+	if (ACPI_FAILURE(status))
+		return_ACPI_STATUS(status);
+
 	/*
 	 * Set the SLP_TYP and SLP_EN bits.
 	 *
diff --git a/drivers/acpi/acpica/hwtimer.c b/drivers/acpi/acpica/hwtimer.c
index 0c1a8bbd05d6..2d7d22ebc782 100644
--- a/drivers/acpi/acpica/hwtimer.c
+++ b/drivers/acpi/acpica/hwtimer.c
@@ -100,8 +100,13 @@ acpi_status acpi_get_timer(u32 * ticks)
 		return_ACPI_STATUS(AE_BAD_PARAMETER);
 	}
 
-	status = acpi_hw_read(ticks, &acpi_gbl_FADT.xpm_timer_block);
+	/* ACPI 5.0A: PM Timer is optional */
+
+	if (!acpi_gbl_FADT.xpm_timer_block.address) {
+		return_ACPI_STATUS(AE_SUPPORT);
+	}
 
+	status = acpi_hw_read(ticks, &acpi_gbl_FADT.xpm_timer_block);
 	return_ACPI_STATUS(status);
 }
 
@@ -148,6 +153,12 @@ acpi_get_timer_duration(u32 start_ticks, u32 end_ticks, u32 * time_elapsed)
 		return_ACPI_STATUS(AE_BAD_PARAMETER);
 	}
 
+	/* ACPI 5.0A: PM Timer is optional */
+
+	if (!acpi_gbl_FADT.xpm_timer_block.address) {
+		return_ACPI_STATUS(AE_SUPPORT);
+	}
+
 	/*
 	 * Compute Tick Delta:
 	 * Handle (max one) timer rollovers on 24-bit versus 32-bit timers.
diff --git a/drivers/acpi/acpica/nspredef.c b/drivers/acpi/acpica/nspredef.c
index 24b71a01bf93..098e7666cbc9 100644
--- a/drivers/acpi/acpica/nspredef.c
+++ b/drivers/acpi/acpica/nspredef.c
@@ -151,6 +151,15 @@ acpi_ns_check_return_value(struct acpi_namespace_node *node,
 	}
 
 	/*
+	 *
+	 * 4) If there is no return value and it is optional, just return
+	 * AE_OK (_WAK).
+	 */
+	if (!(*return_object_ptr)) {
+		goto exit;
+	}
+
+	/*
 	 * For returned Package objects, check the type of all sub-objects.
 	 * Note: Package may have been newly created by call above.
 	 */
@@ -268,7 +277,12 @@ acpi_ns_check_object_type(struct acpi_evaluate_info *info,
 
 	acpi_ut_get_expected_return_types(type_buffer, expected_btypes);
 
-	if (package_index == ACPI_NOT_PACKAGE_ELEMENT) {
+	if (!return_object) {
+		ACPI_WARN_PREDEFINED((AE_INFO, info->full_pathname,
+				      info->node_flags,
+				      "Expected return object of type %s",
+				      type_buffer));
+	} else if (package_index == ACPI_NOT_PACKAGE_ELEMENT) {
 		ACPI_WARN_PREDEFINED((AE_INFO, info->full_pathname,
 				      info->node_flags,
 				      "Return type mismatch - found %s, expected %s",
diff --git a/drivers/acpi/acpica/nswalk.c b/drivers/acpi/acpica/nswalk.c
index e70911a9e441..e81f15ef659a 100644
--- a/drivers/acpi/acpica/nswalk.c
+++ b/drivers/acpi/acpica/nswalk.c
@@ -156,9 +156,9 @@ struct acpi_namespace_node *acpi_ns_get_next_node_typed(acpi_object_type type,
  *              max_depth           - Depth to which search is to reach
  *              flags               - Whether to unlock the NS before invoking
  *                                    the callback routine
- *              pre_order_visit     - Called during tree pre-order visit
+ *              descending_callback - Called during tree descent
  *                                    when an object of "Type" is found
- *              post_order_visit    - Called during tree post-order visit
+ *              ascending_callback  - Called during tree ascent
  *                                    when an object of "Type" is found
  *              context             - Passed to user function(s) above
  *              return_value        - from the user_function if terminated
@@ -185,8 +185,8 @@ acpi_ns_walk_namespace(acpi_object_type type,
 		       acpi_handle start_node,
 		       u32 max_depth,
 		       u32 flags,
-		       acpi_walk_callback pre_order_visit,
-		       acpi_walk_callback post_order_visit,
+		       acpi_walk_callback descending_callback,
+		       acpi_walk_callback ascending_callback,
 		       void *context, void **return_value)
 {
 	acpi_status status;
@@ -255,22 +255,22 @@ acpi_ns_walk_namespace(acpi_object_type type,
 			}
 
 			/*
-			 * Invoke the user function, either pre-order or post-order
+			 * Invoke the user function, either descending, ascending,
 			 * or both.
 			 */
 			if (!node_previously_visited) {
-				if (pre_order_visit) {
+				if (descending_callback) {
 					status =
-					    pre_order_visit(child_node, level,
-							    context,
-							    return_value);
+					    descending_callback(child_node,
+								level, context,
+								return_value);
 				}
 			} else {
-				if (post_order_visit) {
+				if (ascending_callback) {
 					status =
-					    post_order_visit(child_node, level,
-							     context,
-							     return_value);
+					    ascending_callback(child_node,
+							       level, context,
+							       return_value);
 				}
 			}
 
diff --git a/drivers/acpi/acpica/nsxfeval.c b/drivers/acpi/acpica/nsxfeval.c
index f553cfdb71dd..b38b4b07f86e 100644
--- a/drivers/acpi/acpica/nsxfeval.c
+++ b/drivers/acpi/acpica/nsxfeval.c
@@ -533,9 +533,9 @@ static void acpi_ns_resolve_references(struct acpi_evaluate_info *info)
  * PARAMETERS:  type                - acpi_object_type to search for
  *              start_object        - Handle in namespace where search begins
  *              max_depth           - Depth to which search is to reach
- *              pre_order_visit     - Called during tree pre-order visit
+ *              descending_callback - Called during tree descent
  *                                    when an object of "Type" is found
- *              post_order_visit    - Called during tree post-order visit
+ *              ascending_callback  - Called during tree ascent
  *                                    when an object of "Type" is found
  *              context             - Passed to user function(s) above
  *              return_value        - Location where return value of
@@ -563,8 +563,8 @@ acpi_status
 acpi_walk_namespace(acpi_object_type type,
 		    acpi_handle start_object,
 		    u32 max_depth,
-		    acpi_walk_callback pre_order_visit,
-		    acpi_walk_callback post_order_visit,
+		    acpi_walk_callback descending_callback,
+		    acpi_walk_callback ascending_callback,
 		    void *context, void **return_value)
 {
 	acpi_status status;
@@ -574,7 +574,7 @@ acpi_walk_namespace(acpi_object_type type,
 	/* Parameter validation */
 
 	if ((type > ACPI_TYPE_LOCAL_MAX) ||
-	    (!max_depth) || (!pre_order_visit && !post_order_visit)) {
+	    (!max_depth) || (!descending_callback && !ascending_callback)) {
 		return_ACPI_STATUS(AE_BAD_PARAMETER);
 	}
 
@@ -606,9 +606,9 @@ acpi_walk_namespace(acpi_object_type type,
 	}
 
 	status = acpi_ns_walk_namespace(type, start_object, max_depth,
-					ACPI_NS_WALK_UNLOCK, pre_order_visit,
-					post_order_visit, context,
-					return_value);
+					ACPI_NS_WALK_UNLOCK,
+					descending_callback, ascending_callback,
+					context, return_value);
 
 	(void)acpi_ut_release_mutex(ACPI_MTX_NAMESPACE);
 
diff --git a/drivers/acpi/acpica/nsxfname.c b/drivers/acpi/acpica/nsxfname.c
index f3a4d95899f7..83c164434580 100644
--- a/drivers/acpi/acpica/nsxfname.c
+++ b/drivers/acpi/acpica/nsxfname.c
@@ -158,6 +158,7 @@ acpi_get_name(acpi_handle handle, u32 name_type, struct acpi_buffer * buffer)
 {
 	acpi_status status;
 	struct acpi_namespace_node *node;
+	char *node_name;
 
 	/* Parameter validation */
 
@@ -202,7 +203,8 @@ acpi_get_name(acpi_handle handle, u32 name_type, struct acpi_buffer * buffer)
 
 	/* Just copy the ACPI name from the Node and zero terminate it */
 
-	ACPI_MOVE_NAME(buffer->pointer, acpi_ut_get_node_name(node));
+	node_name = acpi_ut_get_node_name(node);
+	ACPI_MOVE_NAME(buffer->pointer, node_name);
 	((char *)buffer->pointer)[ACPI_NAME_SIZE] = 0;
 	status = AE_OK;
 
@@ -379,9 +381,14 @@ acpi_get_object_info(acpi_handle handle,
 		 * Get extra info for ACPI Device/Processor objects only:
 		 * Run the _STA, _ADR and, sx_w, and _sx_d methods.
 		 *
-		 * Note: none of these methods are required, so they may or may
+		 * Notes: none of these methods are required, so they may or may
 		 * not be present for this device. The Info->Valid bitfield is used
 		 * to indicate which methods were found and run successfully.
+		 *
+		 * For _STA, if the method does not exist, then (as per the ACPI
+		 * specification), the returned current_status flags will indicate
+		 * that the device is present/functional/enabled. Otherwise, the
+		 * current_status flags reflect the value returned from _STA.
 		 */
 
 		/* Execute the Device._STA method */
diff --git a/drivers/acpi/acpica/tbfadt.c b/drivers/acpi/acpica/tbfadt.c
index 33b00d22300a..9d99f2189693 100644
--- a/drivers/acpi/acpica/tbfadt.c
+++ b/drivers/acpi/acpica/tbfadt.c
@@ -117,7 +117,7 @@ static struct acpi_fadt_info fadt_info_table[] = {
 	 ACPI_FADT_OFFSET(pm_timer_block),
 	 ACPI_FADT_OFFSET(pm_timer_length),
 	 ACPI_PM_TIMER_WIDTH,
-	 ACPI_FADT_REQUIRED},
+	 ACPI_FADT_SEPARATE_LENGTH},	/* ACPI 5.0A: Timer is optional */
 
 	{"Gpe0Block",
 	 ACPI_FADT_OFFSET(xgpe0_block),
@@ -574,7 +574,7 @@ static void acpi_tb_validate_fadt(void)
 
 		if (fadt_info_table[i].type & ACPI_FADT_REQUIRED) {
 			/*
-			 * Field is required (Pm1a_event, Pm1a_control, pm_timer).
+			 * Field is required (Pm1a_event, Pm1a_control).
 			 * Both the address and length must be non-zero.
 			 */
 			if (!address64->address || !length) {
diff --git a/drivers/acpi/acpica/tbxfroot.c b/drivers/acpi/acpica/tbxfroot.c
index 7c2ecfb7c2c3..948c95e80d44 100644
--- a/drivers/acpi/acpica/tbxfroot.c
+++ b/drivers/acpi/acpica/tbxfroot.c
@@ -48,11 +48,6 @@
 #define _COMPONENT          ACPI_TABLES
 ACPI_MODULE_NAME("tbxfroot")
 
-/* Local prototypes */
-static u8 *acpi_tb_scan_memory_for_rsdp(u8 * start_address, u32 length);
-
-static acpi_status acpi_tb_validate_rsdp(struct acpi_table_rsdp *rsdp);
-
 /*******************************************************************************
  *
  * FUNCTION:    acpi_tb_validate_rsdp
@@ -64,8 +59,7 @@ static acpi_status acpi_tb_validate_rsdp(struct acpi_table_rsdp *rsdp);
  * DESCRIPTION: Validate the RSDP (ptr)
  *
  ******************************************************************************/
-
-static acpi_status acpi_tb_validate_rsdp(struct acpi_table_rsdp *rsdp)
+acpi_status acpi_tb_validate_rsdp(struct acpi_table_rsdp *rsdp)
 {
 
 	/*
@@ -74,7 +68,7 @@ static acpi_status acpi_tb_validate_rsdp(struct acpi_table_rsdp *rsdp)
 	 * Note: Sometimes there exists more than one RSDP in memory; the valid
 	 * RSDP has a valid checksum, all others have an invalid checksum.
 	 */
-	if (ACPI_STRNCMP((char *)rsdp, ACPI_SIG_RSDP,
+	if (ACPI_STRNCMP((char *)rsdp->signature, ACPI_SIG_RSDP,
 			 sizeof(ACPI_SIG_RSDP) - 1) != 0) {
 
 		/* Nope, BAD Signature */
@@ -231,7 +225,7 @@ acpi_status acpi_find_root_pointer(acpi_size *table_address)
  * DESCRIPTION: Search a block of memory for the RSDP signature
  *
  ******************************************************************************/
-static u8 *acpi_tb_scan_memory_for_rsdp(u8 * start_address, u32 length)
+u8 *acpi_tb_scan_memory_for_rsdp(u8 *start_address, u32 length)
 {
 	acpi_status status;
 	u8 *mem_rover;
diff --git a/drivers/acpi/acpica/uteval.c b/drivers/acpi/acpica/uteval.c
index ee83adb97b1e..4fd68971019b 100644
--- a/drivers/acpi/acpica/uteval.c
+++ b/drivers/acpi/acpica/uteval.c
@@ -239,7 +239,8 @@ acpi_ut_evaluate_numeric_object(char *object_name,
  * RETURN:      Status
  *
  * DESCRIPTION: Executes _STA for selected device and stores results in
- *              *Flags.
+ *              *Flags. If _STA does not exist, then the device is assumed
+ *              to be present/functional/enabled (as per the ACPI spec).
  *
  *              NOTE: Internal function, no parameter validation
  *
@@ -257,6 +258,11 @@ acpi_ut_execute_STA(struct acpi_namespace_node *device_node, u32 * flags)
 					 ACPI_BTYPE_INTEGER, &obj_desc);
 	if (ACPI_FAILURE(status)) {
 		if (AE_NOT_FOUND == status) {
+			/*
+			 * if _STA does not exist, then (as per the ACPI specification),
+			 * the returned flags will indicate that the device is present,
+			 * functional, and enabled.
+			 */
 			ACPI_DEBUG_PRINT((ACPI_DB_EXEC,
 					  "_STA on %4.4s was not found, assuming device is present\n",
 					  acpi_ut_get_node_name(device_node)));
diff --git a/drivers/acpi/acpica/utglobal.c b/drivers/acpi/acpica/utglobal.c
index f736448a8606..d6f26bf8a062 100644
--- a/drivers/acpi/acpica/utglobal.c
+++ b/drivers/acpi/acpica/utglobal.c
@@ -336,7 +336,6 @@ acpi_status acpi_ut_init_globals(void)
 	acpi_gbl_trace_dbg_layer = 0;
 	acpi_gbl_debugger_configuration = DEBUGGER_THREADING;
 	acpi_gbl_db_output_flags = ACPI_DB_CONSOLE_OUTPUT;
-	acpi_gbl_osi_data = 0;
 	acpi_gbl_osi_mutex = NULL;
 	acpi_gbl_reg_methods_executed = FALSE;
 
diff --git a/drivers/acpi/acpica/utosi.c b/drivers/acpi/acpica/utosi.c
index 7e807725c636..8856bd37bc76 100644
--- a/drivers/acpi/acpica/utosi.c
+++ b/drivers/acpi/acpica/utosi.c
@@ -77,21 +77,20 @@ static struct acpi_interface_info acpi_default_supported_interfaces[] = {
 
 	/* Feature Group Strings */
 
-	{"Extended Address Space Descriptor", NULL, 0, 0}
+	{"Extended Address Space Descriptor", NULL, ACPI_OSI_FEATURE, 0},
 
 	/*
 	 * All "optional" feature group strings (features that are implemented
-	 * by the host) should be dynamically added by the host via
-	 * acpi_install_interface and should not be manually added here.
-	 *
-	 * Examples of optional feature group strings:
-	 *
-	 * "Module Device"
-	 * "Processor Device"
-	 * "3.0 Thermal Model"
-	 * "3.0 _SCP Extensions"
-	 * "Processor Aggregator Device"
+	 * by the host) should be dynamically modified to VALID by the host via
+	 * acpi_install_interface or acpi_update_interfaces. Such optional feature
+	 * group strings are set as INVALID by default here.
 	 */
+
+	{"Module Device", NULL, ACPI_OSI_OPTIONAL_FEATURE, 0},
+	{"Processor Device", NULL, ACPI_OSI_OPTIONAL_FEATURE, 0},
+	{"3.0 Thermal Model", NULL, ACPI_OSI_OPTIONAL_FEATURE, 0},
+	{"3.0 _SCP Extensions", NULL, ACPI_OSI_OPTIONAL_FEATURE, 0},
+	{"Processor Aggregator Device", NULL, ACPI_OSI_OPTIONAL_FEATURE, 0}
 };
 
 /*******************************************************************************
@@ -158,11 +157,20 @@ acpi_status acpi_ut_interface_terminate(void)
 	while (next_interface) {
 		acpi_gbl_supported_interfaces = next_interface->next;
 
-		/* Only interfaces added at runtime can be freed */
-
 		if (next_interface->flags & ACPI_OSI_DYNAMIC) {
+
+			/* Only interfaces added at runtime can be freed */
+
 			ACPI_FREE(next_interface->name);
 			ACPI_FREE(next_interface);
+		} else {
+			/* Interface is in static list. Reset it to invalid or valid. */
+
+			if (next_interface->flags & ACPI_OSI_DEFAULT_INVALID) {
+				next_interface->flags |= ACPI_OSI_INVALID;
+			} else {
+				next_interface->flags &= ~ACPI_OSI_INVALID;
+			}
 		}
 
 		next_interface = acpi_gbl_supported_interfaces;
@@ -278,6 +286,49 @@ acpi_status acpi_ut_remove_interface(acpi_string interface_name)
 
 /*******************************************************************************
  *
+ * FUNCTION:    acpi_ut_update_interfaces
+ *
+ * PARAMETERS:  action              - Actions to be performed during the
+ *                                    update
+ *
+ * RETURN:      Status
+ *
+ * DESCRIPTION: Update _OSI interface strings, disabling or enabling OS vendor
+ *              strings or/and feature group strings.
+ *              Caller MUST hold acpi_gbl_osi_mutex
+ *
+ ******************************************************************************/
+
+acpi_status acpi_ut_update_interfaces(u8 action)
+{
+	struct acpi_interface_info *next_interface;
+
+	next_interface = acpi_gbl_supported_interfaces;
+	while (next_interface) {
+		if (((next_interface->flags & ACPI_OSI_FEATURE) &&
+		     (action & ACPI_FEATURE_STRINGS)) ||
+		    (!(next_interface->flags & ACPI_OSI_FEATURE) &&
+		     (action & ACPI_VENDOR_STRINGS))) {
+			if (action & ACPI_DISABLE_INTERFACES) {
+
+				/* Mark the interfaces as invalid */
+
+				next_interface->flags |= ACPI_OSI_INVALID;
+			} else {
+				/* Mark the interfaces as valid */
+
+				next_interface->flags &= ~ACPI_OSI_INVALID;
+			}
+		}
+
+		next_interface = next_interface->next;
+	}
+
+	return (AE_OK);
+}
+
+/*******************************************************************************
+ *
  * FUNCTION:    acpi_ut_get_interface
  *
  * PARAMETERS:  interface_name      - The interface to find
diff --git a/drivers/acpi/acpica/utstring.c b/drivers/acpi/acpica/utstring.c
index c53759b76a3f..cb1e9cc32d5f 100644
--- a/drivers/acpi/acpica/utstring.c
+++ b/drivers/acpi/acpica/utstring.c
@@ -333,7 +333,8 @@ acpi_status acpi_ut_strtoul64(char *string, u32 base, u64 *ret_integer)
  * FUNCTION:    acpi_ut_print_string
  *
  * PARAMETERS:  string          - Null terminated ASCII string
- *              max_length      - Maximum output length
+ *              max_length      - Maximum output length. Used to constrain the
+ *                                length of strings during debug output only.
  *
  * RETURN:      None
  *
@@ -342,7 +343,7 @@ acpi_status acpi_ut_strtoul64(char *string, u32 base, u64 *ret_integer)
  *
  ******************************************************************************/
 
-void acpi_ut_print_string(char *string, u8 max_length)
+void acpi_ut_print_string(char *string, u16 max_length)
 {
 	u32 i;
 
diff --git a/drivers/acpi/acpica/utxface.c b/drivers/acpi/acpica/utxface.c
index 6505774f223e..03a211e6e26a 100644
--- a/drivers/acpi/acpica/utxface.c
+++ b/drivers/acpi/acpica/utxface.c
@@ -389,6 +389,34 @@ ACPI_EXPORT_SYMBOL(acpi_install_interface_handler)
 
 /*****************************************************************************
  *
+ * FUNCTION:    acpi_update_interfaces
+ *
+ * PARAMETERS:  action              - Actions to be performed during the
+ *                                    update
+ *
+ * RETURN:      Status
+ *
+ * DESCRIPTION: Update _OSI interface strings, disabling or enabling OS vendor
+ *              string or/and feature group strings.
+ *
+ ****************************************************************************/
+acpi_status acpi_update_interfaces(u8 action)
+{
+	acpi_status status;
+
+	status = acpi_os_acquire_mutex(acpi_gbl_osi_mutex, ACPI_WAIT_FOREVER);
+	if (ACPI_FAILURE(status)) {
+		return (status);
+	}
+
+	status = acpi_ut_update_interfaces(action);
+
+	acpi_os_release_mutex(acpi_gbl_osi_mutex);
+	return (status);
+}
+
+/*****************************************************************************
+ *
  * FUNCTION:    acpi_check_address_range
  *
  * PARAMETERS:  space_id            - Address space ID
@@ -402,6 +430,7 @@ ACPI_EXPORT_SYMBOL(acpi_install_interface_handler)
  *              ASL operation region address ranges.
  *
  ****************************************************************************/
+
 u32
 acpi_check_address_range(acpi_adr_space_type space_id,
 			 acpi_physical_address address,
diff --git a/drivers/acpi/apei/erst.c b/drivers/acpi/apei/erst.c
index 88d0b0f9f92b..26311f23c824 100644
--- a/drivers/acpi/apei/erst.c
+++ b/drivers/acpi/apei/erst.c
@@ -39,7 +39,8 @@
 
 #include "apei-internal.h"
 
-#define ERST_PFX "ERST: "
+#undef pr_fmt
+#define pr_fmt(fmt) "ERST: " fmt
 
 /* ERST command status */
 #define ERST_STATUS_SUCCESS			0x0
@@ -109,8 +110,7 @@ static inline int erst_errno(int command_status)
 static int erst_timedout(u64 *t, u64 spin_unit)
 {
 	if ((s64)*t < spin_unit) {
-		pr_warning(FW_WARN ERST_PFX
-			   "Firmware does not respond in time\n");
+		pr_warn(FW_WARN "Firmware does not respond in time.\n");
 		return 1;
 	}
 	*t -= spin_unit;
@@ -186,8 +186,8 @@ static int erst_exec_stall(struct apei_exec_context *ctx,
 
 	if (ctx->value > FIRMWARE_MAX_STALL) {
 		if (!in_nmi())
-			pr_warning(FW_WARN ERST_PFX
-			"Too long stall time for stall instruction: %llx.\n",
+			pr_warn(FW_WARN
+			"Too long stall time for stall instruction: 0x%llx.\n",
 				   ctx->value);
 		stall_time = FIRMWARE_MAX_STALL;
 	} else
@@ -206,8 +206,8 @@ static int erst_exec_stall_while_true(struct apei_exec_context *ctx,
 
 	if (ctx->var1 > FIRMWARE_MAX_STALL) {
 		if (!in_nmi())
-			pr_warning(FW_WARN ERST_PFX
-		"Too long stall time for stall while true instruction: %llx.\n",
+			pr_warn(FW_WARN
+		"Too long stall time for stall while true instruction: 0x%llx.\n",
 				   ctx->var1);
 		stall_time = FIRMWARE_MAX_STALL;
 	} else
@@ -271,8 +271,7 @@ static int erst_exec_move_data(struct apei_exec_context *ctx,
 
 	/* ioremap does not work in interrupt context */
 	if (in_interrupt()) {
-		pr_warning(ERST_PFX
-			   "MOVE_DATA can not be used in interrupt context");
+		pr_warn("MOVE_DATA can not be used in interrupt context.\n");
 		return -EBUSY;
 	}
 
@@ -284,8 +283,10 @@ static int erst_exec_move_data(struct apei_exec_context *ctx,
 	if (!src)
 		return -ENOMEM;
 	dst = ioremap(ctx->dst_base + offset, ctx->var2);
-	if (!dst)
+	if (!dst) {
+		iounmap(src);
 		return -ENOMEM;
+	}
 
 	memmove(dst, src, ctx->var2);
 
@@ -522,8 +523,7 @@ retry:
 				     ERST_RECORD_ID_CACHE_SIZE_MAX);
 		if (new_size <= erst_record_id_cache.size) {
 			if (printk_ratelimit())
-				pr_warning(FW_WARN ERST_PFX
-					   "too many record ID!\n");
+				pr_warn(FW_WARN "too many record IDs!\n");
 			return 0;
 		}
 		alloc_size = new_size * sizeof(entries[0]);
@@ -759,8 +759,7 @@ static int __erst_clear_from_storage(u64 record_id)
 static void pr_unimpl_nvram(void)
 {
 	if (printk_ratelimit())
-		pr_warning(ERST_PFX
-		"NVRAM ERST Log Address Range is not implemented yet\n");
+		pr_warn("NVRAM ERST Log Address Range not implemented yet.\n");
 }
 
 static int __erst_write_to_nvram(const struct cper_record_header *record)
@@ -933,9 +932,9 @@ static int erst_open_pstore(struct pstore_info *psi);
 static int erst_close_pstore(struct pstore_info *psi);
 static ssize_t erst_reader(u64 *id, enum pstore_type_id *type, int *count,
 			   struct timespec *time, char **buf,
-			   struct pstore_info *psi);
+			   bool *compressed, struct pstore_info *psi);
 static int erst_writer(enum pstore_type_id type, enum kmsg_dump_reason reason,
-		       u64 *id, unsigned int part, int count, size_t hsize,
+		       u64 *id, unsigned int part, int count, bool compressed,
 		       size_t size, struct pstore_info *psi);
 static int erst_clearer(enum pstore_type_id type, u64 id, int count,
 			struct timespec time, struct pstore_info *psi);
@@ -956,6 +955,9 @@ static struct pstore_info erst_info = {
 #define CPER_SECTION_TYPE_DMESG						\
 	UUID_LE(0xc197e04e, 0xd545, 0x4a70, 0x9c, 0x17, 0xa5, 0x54,	\
 		0x94, 0x19, 0xeb, 0x12)
+#define CPER_SECTION_TYPE_DMESG_Z					\
+	UUID_LE(0x4f118707, 0x04dd, 0x4055, 0xb5, 0xdd, 0x95, 0x6d,	\
+		0x34, 0xdd, 0xfa, 0xc6)
 #define CPER_SECTION_TYPE_MCE						\
 	UUID_LE(0xfe08ffbe, 0x95e4, 0x4be7, 0xbc, 0x73, 0x40, 0x96,	\
 		0x04, 0x4a, 0x38, 0xfc)
@@ -989,7 +991,7 @@ static int erst_close_pstore(struct pstore_info *psi)
 
 static ssize_t erst_reader(u64 *id, enum pstore_type_id *type, int *count,
 			   struct timespec *time, char **buf,
-			   struct pstore_info *psi)
+			   bool *compressed, struct pstore_info *psi)
 {
 	int rc;
 	ssize_t len = 0;
@@ -1034,7 +1036,12 @@ skip:
 	}
 	memcpy(*buf, rcd->data, len - sizeof(*rcd));
 	*id = record_id;
+	*compressed = false;
 	if (uuid_le_cmp(rcd->sec_hdr.section_type,
+			CPER_SECTION_TYPE_DMESG_Z) == 0) {
+		*type = PSTORE_TYPE_DMESG;
+		*compressed = true;
+	} else if (uuid_le_cmp(rcd->sec_hdr.section_type,
 			CPER_SECTION_TYPE_DMESG) == 0)
 		*type = PSTORE_TYPE_DMESG;
 	else if (uuid_le_cmp(rcd->sec_hdr.section_type,
@@ -1055,7 +1062,7 @@ out:
 }
 
 static int erst_writer(enum pstore_type_id type, enum kmsg_dump_reason reason,
-		       u64 *id, unsigned int part, int count, size_t hsize,
+		       u64 *id, unsigned int part, int count, bool compressed,
 		       size_t size, struct pstore_info *psi)
 {
 	struct cper_pstore_record *rcd = (struct cper_pstore_record *)
@@ -1085,7 +1092,10 @@ static int erst_writer(enum pstore_type_id type, enum kmsg_dump_reason reason,
 	rcd->sec_hdr.flags = CPER_SEC_PRIMARY;
 	switch (type) {
 	case PSTORE_TYPE_DMESG:
-		rcd->sec_hdr.section_type = CPER_SECTION_TYPE_DMESG;
+		if (compressed)
+			rcd->sec_hdr.section_type = CPER_SECTION_TYPE_DMESG_Z;
+		else
+			rcd->sec_hdr.section_type = CPER_SECTION_TYPE_DMESG;
 		break;
 	case PSTORE_TYPE_MCE:
 		rcd->sec_hdr.section_type = CPER_SECTION_TYPE_MCE;
@@ -1120,7 +1130,7 @@ static int __init erst_init(void)
 		goto err;
 
 	if (erst_disable) {
-		pr_info(ERST_PFX
+		pr_info(
 	"Error Record Serialization Table (ERST) support is disabled.\n");
 		goto err;
 	}
@@ -1131,14 +1141,14 @@ static int __init erst_init(void)
 		goto err;
 	else if (ACPI_FAILURE(status)) {
 		const char *msg = acpi_format_exception(status);
-		pr_err(ERST_PFX "Failed to get table, %s\n", msg);
+		pr_err("Failed to get table, %s\n", msg);
 		rc = -EINVAL;
 		goto err;
 	}
 
 	rc = erst_check_table(erst_tab);
 	if (rc) {
-		pr_err(FW_BUG ERST_PFX "ERST table is invalid\n");
+		pr_err(FW_BUG "ERST table is invalid.\n");
 		goto err;
 	}
 
@@ -1156,21 +1166,19 @@ static int __init erst_init(void)
 	rc = erst_get_erange(&erst_erange);
 	if (rc) {
 		if (rc == -ENODEV)
-			pr_info(ERST_PFX
+			pr_info(
 	"The corresponding hardware device or firmware implementation "
 	"is not available.\n");
 		else
-			pr_err(ERST_PFX
-			       "Failed to get Error Log Address Range.\n");
+			pr_err("Failed to get Error Log Address Range.\n");
 		goto err_unmap_reg;
 	}
 
 	r = request_mem_region(erst_erange.base, erst_erange.size, "APEI ERST");
 	if (!r) {
-		pr_err(ERST_PFX
-		"Can not request iomem region <0x%16llx-0x%16llx> for ERST.\n",
-		(unsigned long long)erst_erange.base,
-		(unsigned long long)erst_erange.base + erst_erange.size);
+		pr_err("Can not request [mem %#010llx-%#010llx] for ERST.\n",
+		       (unsigned long long)erst_erange.base,
+		       (unsigned long long)erst_erange.base + erst_erange.size - 1);
 		rc = -EIO;
 		goto err_unmap_reg;
 	}
@@ -1180,7 +1188,7 @@ static int __init erst_init(void)
 	if (!erst_erange.vaddr)
 		goto err_release_erange;
 
-	pr_info(ERST_PFX
+	pr_info(
 	"Error Record Serialization Table (ERST) support is initialized.\n");
 
 	buf = kmalloc(erst_erange.size, GFP_KERNEL);
@@ -1192,15 +1200,15 @@ static int __init erst_init(void)
 		rc = pstore_register(&erst_info);
 		if (rc) {
 			if (rc != -EPERM)
-				pr_info(ERST_PFX
-				"Could not register with persistent store\n");
+				pr_info(
+				"Could not register with persistent store.\n");
 			erst_info.buf = NULL;
 			erst_info.bufsize = 0;
 			kfree(buf);
 		}
 	} else
-		pr_err(ERST_PFX
-		"Failed to allocate %lld bytes for persistent store error log\n",
+		pr_err(
+		"Failed to allocate %lld bytes for persistent store error log.\n",
 		erst_erange.size);
 
 	return 0;
diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index ec9b57d428a1..8ec37bbdd699 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -409,6 +409,34 @@ static void ghes_clear_estatus(struct ghes *ghes)
 	ghes->flags &= ~GHES_TO_CLEAR;
 }
 
+static void ghes_handle_memory_failure(struct acpi_hest_generic_data *gdata, int sev)
+{
+#ifdef CONFIG_ACPI_APEI_MEMORY_FAILURE
+	unsigned long pfn;
+	int sec_sev = ghes_severity(gdata->error_severity);
+	struct cper_sec_mem_err *mem_err;
+	mem_err = (struct cper_sec_mem_err *)(gdata + 1);
+
+	if (sec_sev == GHES_SEV_CORRECTED &&
+	    (gdata->flags & CPER_SEC_ERROR_THRESHOLD_EXCEEDED) &&
+	    (mem_err->validation_bits & CPER_MEM_VALID_PHYSICAL_ADDRESS)) {
+		pfn = mem_err->physical_addr >> PAGE_SHIFT;
+		if (pfn_valid(pfn))
+			memory_failure_queue(pfn, 0, MF_SOFT_OFFLINE);
+		else if (printk_ratelimit())
+			pr_warn(FW_WARN GHES_PFX
+			"Invalid address in generic error data: %#llx\n",
+			mem_err->physical_addr);
+	}
+	if (sev == GHES_SEV_RECOVERABLE &&
+	    sec_sev == GHES_SEV_RECOVERABLE &&
+	    mem_err->validation_bits & CPER_MEM_VALID_PHYSICAL_ADDRESS) {
+		pfn = mem_err->physical_addr >> PAGE_SHIFT;
+		memory_failure_queue(pfn, 0, 0);
+	}
+#endif
+}
+
 static void ghes_do_proc(struct ghes *ghes,
 			 const struct acpi_hest_generic_status *estatus)
 {
@@ -428,15 +456,7 @@ static void ghes_do_proc(struct ghes *ghes,
 			apei_mce_report_mem_error(sev == GHES_SEV_CORRECTED,
 						  mem_err);
 #endif
-#ifdef CONFIG_ACPI_APEI_MEMORY_FAILURE
-			if (sev == GHES_SEV_RECOVERABLE &&
-			    sec_sev == GHES_SEV_RECOVERABLE &&
-			    mem_err->validation_bits & CPER_MEM_VALID_PHYSICAL_ADDRESS) {
-				unsigned long pfn;
-				pfn = mem_err->physical_addr >> PAGE_SHIFT;
-				memory_failure_queue(pfn, 0, 0);
-			}
-#endif
+			ghes_handle_memory_failure(gdata, sev);
 		}
 #ifdef CONFIG_ACPI_APEI_PCIEAER
 		else if (!uuid_le_cmp(*(uuid_le *)gdata->section_type,
diff --git a/drivers/acpi/apei/hest.c b/drivers/acpi/apei/hest.c
index f5ef5d54e4ac..f5e37f32c71f 100644
--- a/drivers/acpi/apei/hest.c
+++ b/drivers/acpi/apei/hest.c
@@ -36,6 +36,7 @@
 #include <linux/io.h>
 #include <linux/platform_device.h>
 #include <acpi/apei.h>
+#include <asm/mce.h>
 
 #include "apei-internal.h"
 
@@ -121,6 +122,41 @@ int apei_hest_parse(apei_hest_func_t func, void *data)
 }
 EXPORT_SYMBOL_GPL(apei_hest_parse);
 
+/*
+ * Check if firmware advertises firmware first mode. We need FF bit to be set
+ * along with a set of MC banks which work in FF mode.
+ */
+static int __init hest_parse_cmc(struct acpi_hest_header *hest_hdr, void *data)
+{
+#ifdef CONFIG_X86_MCE
+	int i;
+	struct acpi_hest_ia_corrected *cmc;
+	struct acpi_hest_ia_error_bank *mc_bank;
+
+	if (hest_hdr->type != ACPI_HEST_TYPE_IA32_CORRECTED_CHECK)
+		return 0;
+
+	cmc = (struct acpi_hest_ia_corrected *)hest_hdr;
+	if (!cmc->enabled)
+		return 0;
+
+	/*
+	 * We expect HEST to provide a list of MC banks that report errors
+	 * in firmware first mode. Otherwise, return non-zero value to
+	 * indicate that we are done parsing HEST.
+	 */
+	if (!(cmc->flags & ACPI_HEST_FIRMWARE_FIRST) || !cmc->num_hardware_banks)
+		return 1;
+
+	pr_info(HEST_PFX "Enabling Firmware First mode for corrected errors.\n");
+
+	mc_bank = (struct acpi_hest_ia_error_bank *)(cmc + 1);
+	for (i = 0; i < cmc->num_hardware_banks; i++, mc_bank++)
+		mce_disable_bank(mc_bank->bank_number);
+#endif
+	return 1;
+}
+
 struct ghes_arr {
 	struct platform_device **ghes_devs;
 	unsigned int count;
@@ -227,6 +263,9 @@ void __init acpi_hest_init(void)
 		goto err;
 	}
 
+	if (!acpi_disable_cmcff)
+		apei_hest_parse(hest_parse_cmc, NULL);
+
 	if (!ghes_disable) {
 		rc = apei_hest_parse(hest_parse_ghes_count, &ghes_count);
 		if (rc)
diff --git a/drivers/acpi/battery.c b/drivers/acpi/battery.c
index d405fbad406a..2c9958cd7a43 100644
--- a/drivers/acpi/battery.c
+++ b/drivers/acpi/battery.c
@@ -527,18 +527,14 @@ static int acpi_battery_get_state(struct acpi_battery *battery)
 static int acpi_battery_set_alarm(struct acpi_battery *battery)
 {
 	acpi_status status = 0;
-	union acpi_object arg0 = { .type = ACPI_TYPE_INTEGER };
-	struct acpi_object_list arg_list = { 1, &arg0 };
 
 	if (!acpi_battery_present(battery) ||
 	    !test_bit(ACPI_BATTERY_ALARM_PRESENT, &battery->flags))
 		return -ENODEV;
 
-	arg0.integer.value = battery->alarm;
-
 	mutex_lock(&battery->lock);
-	status = acpi_evaluate_object(battery->device->handle, "_BTP",
-				 &arg_list, NULL);
+	status = acpi_execute_simple_method(battery->device->handle, "_BTP",
+					    battery->alarm);
 	mutex_unlock(&battery->lock);
 
 	if (ACPI_FAILURE(status))
@@ -550,12 +546,8 @@ static int acpi_battery_set_alarm(struct acpi_battery *battery)
 
 static int acpi_battery_init_alarm(struct acpi_battery *battery)
 {
-	acpi_status status = AE_OK;
-	acpi_handle handle = NULL;
-
 	/* See if alarms are supported, and if so, set default */
-	status = acpi_get_handle(battery->device->handle, "_BTP", &handle);
-	if (ACPI_FAILURE(status)) {
+	if (!acpi_has_method(battery->device->handle, "_BTP")) {
 		clear_bit(ACPI_BATTERY_ALARM_PRESENT, &battery->flags);
 		return 0;
 	}
@@ -1036,8 +1028,6 @@ static void acpi_battery_notify(struct acpi_device *device, u32 event)
 	if (event == ACPI_BATTERY_NOTIFY_INFO)
 		acpi_battery_refresh(battery);
 	acpi_battery_update(battery);
-	acpi_bus_generate_proc_event(device, event,
-				     acpi_battery_present(battery));
 	acpi_bus_generate_netlink_event(device->pnp.device_class,
 					dev_name(&device->dev), event,
 					acpi_battery_present(battery));
@@ -1068,7 +1058,7 @@ static int acpi_battery_add(struct acpi_device *device)
 {
 	int result = 0;
 	struct acpi_battery *battery = NULL;
-	acpi_handle handle;
+
 	if (!device)
 		return -EINVAL;
 	battery = kzalloc(sizeof(struct acpi_battery), GFP_KERNEL);
@@ -1080,8 +1070,7 @@ static int acpi_battery_add(struct acpi_device *device)
 	device->driver_data = battery;
 	mutex_init(&battery->lock);
 	mutex_init(&battery->sysfs_lock);
-	if (ACPI_SUCCESS(acpi_get_handle(battery->device->handle,
-			"_BIX", &handle)))
+	if (acpi_has_method(battery->device->handle, "_BIX"))
 		set_bit(ACPI_BATTERY_XINFO_PRESENT, &battery->flags);
 	result = acpi_battery_update(battery);
 	if (result)
diff --git a/drivers/acpi/bgrt.c b/drivers/acpi/bgrt.c
index be6039958545..a83e3c62c5a9 100644
--- a/drivers/acpi/bgrt.c
+++ b/drivers/acpi/bgrt.c
@@ -51,20 +51,14 @@ static ssize_t show_yoffset(struct device *dev,
 }
 static DEVICE_ATTR(yoffset, S_IRUGO, show_yoffset, NULL);
 
-static ssize_t show_image(struct file *file, struct kobject *kobj,
+static ssize_t image_read(struct file *file, struct kobject *kobj,
 	       struct bin_attribute *attr, char *buf, loff_t off, size_t count)
 {
 	memcpy(buf, attr->private + off, count);
 	return count;
 }
 
-static struct bin_attribute image_attr = {
-	.attr = {
-		.name = "image",
-		.mode = S_IRUGO,
-	},
-	.read = show_image,
-};
+static BIN_ATTR_RO(image, 0);	/* size gets filled in later */
 
 static struct attribute *bgrt_attributes[] = {
 	&dev_attr_version.attr,
@@ -75,8 +69,14 @@ static struct attribute *bgrt_attributes[] = {
 	NULL,
 };
 
+static struct bin_attribute *bgrt_bin_attributes[] = {
+	&bin_attr_image,
+	NULL,
+};
+
 static struct attribute_group bgrt_attribute_group = {
 	.attrs = bgrt_attributes,
+	.bin_attrs = bgrt_bin_attributes,
 };
 
 static int __init bgrt_init(void)
@@ -86,9 +86,8 @@ static int __init bgrt_init(void)
 	if (!bgrt_image)
 		return -ENODEV;
 
-	sysfs_bin_attr_init(&image_attr);
-	image_attr.private = bgrt_image;
-	image_attr.size = bgrt_image_size;
+	bin_attr_image.private = bgrt_image;
+	bin_attr_image.size = bgrt_image_size;
 
 	bgrt_kobj = kobject_create_and_add("bgrt", acpi_kobj);
 	if (!bgrt_kobj)
@@ -98,14 +97,8 @@ static int __init bgrt_init(void)
 	if (ret)
 		goto out_kobject;
 
-	ret = sysfs_create_bin_file(bgrt_kobj, &image_attr);
-	if (ret)
-		goto out_group;
-
 	return 0;
 
-out_group:
-	sysfs_remove_group(bgrt_kobj, &bgrt_attribute_group);
 out_kobject:
 	kobject_put(bgrt_kobj);
 	return ret;
diff --git a/drivers/acpi/blacklist.c b/drivers/acpi/blacklist.c
index cb9629638def..9515f18898b2 100644
--- a/drivers/acpi/blacklist.c
+++ b/drivers/acpi/blacklist.c
@@ -192,6 +192,12 @@ static int __init dmi_disable_osi_win7(const struct dmi_system_id *d)
 	acpi_osi_setup("!Windows 2009");
 	return 0;
 }
+static int __init dmi_disable_osi_win8(const struct dmi_system_id *d)
+{
+	printk(KERN_NOTICE PREFIX "DMI detected: %s\n", d->ident);
+	acpi_osi_setup("!Windows 2012");
+	return 0;
+}
 
 static struct dmi_system_id acpi_osi_dmi_table[] __initdata = {
 	{
@@ -267,6 +273,30 @@ static struct dmi_system_id acpi_osi_dmi_table[] __initdata = {
 		     DMI_MATCH(DMI_PRODUCT_NAME, "Satellite P305D"),
 		},
 	},
+	{
+	.callback = dmi_disable_osi_win8,
+	.ident = "ASUS Zenbook Prime UX31A",
+	.matches = {
+		     DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+		     DMI_MATCH(DMI_PRODUCT_NAME, "UX31A"),
+		},
+	},
+	{
+	.callback = dmi_disable_osi_win8,
+	.ident = "Dell Inspiron 15R SE",
+	.matches = {
+		     DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+		     DMI_MATCH(DMI_PRODUCT_NAME, "Inspiron 7520"),
+		},
+	},
+	{
+	.callback = dmi_disable_osi_win8,
+	.ident = "Lenovo ThinkPad Edge E530",
+	.matches = {
+		     DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+		     DMI_MATCH(DMI_PRODUCT_VERSION, "3259A2G"),
+		},
+	},
 
 	/*
 	 * BIOS invocation of _OSI(Linux) is almost always a BIOS bug.
diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c
index a5bb33bab448..b587ec8257b2 100644
--- a/drivers/acpi/bus.c
+++ b/drivers/acpi/bus.c
@@ -89,27 +89,6 @@ static struct dmi_system_id dsdt_dmi_table[] __initdata = {
                                 Device Management
    -------------------------------------------------------------------------- */
 
-int acpi_bus_get_device(acpi_handle handle, struct acpi_device **device)
-{
-	acpi_status status;
-
-	if (!device)
-		return -EINVAL;
-
-	/* TBD: Support fixed-feature devices */
-
-	status = acpi_get_data(handle, acpi_bus_data_handler, (void **)device);
-	if (ACPI_FAILURE(status) || !*device) {
-		ACPI_DEBUG_PRINT((ACPI_DB_INFO, "No context for object [%p]\n",
-				  handle));
-		return -ENODEV;
-	}
-
-	return 0;
-}
-
-EXPORT_SYMBOL(acpi_bus_get_device);
-
 acpi_status acpi_bus_get_status_handle(acpi_handle handle,
 				       unsigned long long *sta)
 {
@@ -346,104 +325,6 @@ static void acpi_bus_osc_support(void)
 }
 
 /* --------------------------------------------------------------------------
-                                Event Management
-   -------------------------------------------------------------------------- */
-
-#ifdef CONFIG_ACPI_PROC_EVENT
-static DEFINE_SPINLOCK(acpi_bus_event_lock);
-
-LIST_HEAD(acpi_bus_event_list);
-DECLARE_WAIT_QUEUE_HEAD(acpi_bus_event_queue);
-
-extern int event_is_open;
-
-int acpi_bus_generate_proc_event4(const char *device_class, const char *bus_id, u8 type, int data)
-{
-	struct acpi_bus_event *event;
-	unsigned long flags;
-
-	/* drop event on the floor if no one's listening */
-	if (!event_is_open)
-		return 0;
-
-	event = kzalloc(sizeof(struct acpi_bus_event), GFP_ATOMIC);
-	if (!event)
-		return -ENOMEM;
-
-	strcpy(event->device_class, device_class);
-	strcpy(event->bus_id, bus_id);
-	event->type = type;
-	event->data = data;
-
-	spin_lock_irqsave(&acpi_bus_event_lock, flags);
-	list_add_tail(&event->node, &acpi_bus_event_list);
-	spin_unlock_irqrestore(&acpi_bus_event_lock, flags);
-
-	wake_up_interruptible(&acpi_bus_event_queue);
-
-	return 0;
-
-}
-
-EXPORT_SYMBOL_GPL(acpi_bus_generate_proc_event4);
-
-int acpi_bus_generate_proc_event(struct acpi_device *device, u8 type, int data)
-{
-	if (!device)
-		return -EINVAL;
-	return acpi_bus_generate_proc_event4(device->pnp.device_class,
-					     device->pnp.bus_id, type, data);
-}
-
-EXPORT_SYMBOL(acpi_bus_generate_proc_event);
-
-int acpi_bus_receive_event(struct acpi_bus_event *event)
-{
-	unsigned long flags;
-	struct acpi_bus_event *entry = NULL;
-
-	DECLARE_WAITQUEUE(wait, current);
-
-
-	if (!event)
-		return -EINVAL;
-
-	if (list_empty(&acpi_bus_event_list)) {
-
-		set_current_state(TASK_INTERRUPTIBLE);
-		add_wait_queue(&acpi_bus_event_queue, &wait);
-
-		if (list_empty(&acpi_bus_event_list))
-			schedule();
-
-		remove_wait_queue(&acpi_bus_event_queue, &wait);
-		set_current_state(TASK_RUNNING);
-
-		if (signal_pending(current))
-			return -ERESTARTSYS;
-	}
-
-	spin_lock_irqsave(&acpi_bus_event_lock, flags);
-	if (!list_empty(&acpi_bus_event_list)) {
-		entry = list_entry(acpi_bus_event_list.next,
-				   struct acpi_bus_event, node);
-		list_del(&entry->node);
-	}
-	spin_unlock_irqrestore(&acpi_bus_event_lock, flags);
-
-	if (!entry)
-		return -ENODEV;
-
-	memcpy(event, entry, sizeof(struct acpi_bus_event));
-
-	kfree(entry);
-
-	return 0;
-}
-
-#endif	/* CONFIG_ACPI_PROC_EVENT */
-
-/* --------------------------------------------------------------------------
                              Notification Handling
    -------------------------------------------------------------------------- */
 
@@ -499,19 +380,6 @@ static void acpi_bus_check_scope(acpi_handle handle)
 	 */
 }
 
-static BLOCKING_NOTIFIER_HEAD(acpi_bus_notify_list);
-int register_acpi_bus_notifier(struct notifier_block *nb)
-{
-	return blocking_notifier_chain_register(&acpi_bus_notify_list, nb);
-}
-EXPORT_SYMBOL_GPL(register_acpi_bus_notifier);
-
-void unregister_acpi_bus_notifier(struct notifier_block *nb)
-{
-	blocking_notifier_chain_unregister(&acpi_bus_notify_list, nb);
-}
-EXPORT_SYMBOL_GPL(unregister_acpi_bus_notifier);
-
 /**
  * acpi_bus_notify
  * ---------------
@@ -525,9 +393,6 @@ static void acpi_bus_notify(acpi_handle handle, u32 type, void *data)
 	ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Notification %#02x to handle %p\n",
 			  type, handle));
 
-	blocking_notifier_call_chain(&acpi_bus_notify_list,
-		type, (void *)handle);
-
 	switch (type) {
 
 	case ACPI_NOTIFY_BUS_CHECK:
@@ -593,8 +458,6 @@ static void acpi_bus_notify(acpi_handle handle, u32 type, void *data)
 static int __init acpi_bus_init_irq(void)
 {
 	acpi_status status;
-	union acpi_object arg = { ACPI_TYPE_INTEGER };
-	struct acpi_object_list arg_list = { 1, &arg };
 	char *message = NULL;
 
 
@@ -623,9 +486,7 @@ static int __init acpi_bus_init_irq(void)
 
 	printk(KERN_INFO PREFIX "Using %s for interrupt routing\n", message);
 
-	arg.integer.value = acpi_irq_model;
-
-	status = acpi_evaluate_object(NULL, "\\_PIC", &arg_list, NULL);
+	status = acpi_execute_simple_method(NULL, "\\_PIC", acpi_irq_model);
 	if (ACPI_FAILURE(status) && (status != AE_NOT_FOUND)) {
 		ACPI_EXCEPTION((AE_INFO, status, "Evaluating _PIC"));
 		return -ENODEV;
@@ -715,7 +576,6 @@ static int __init acpi_bus_init(void)
 {
 	int result;
 	acpi_status status;
-	extern acpi_status acpi_os_initialize1(void);
 
 	acpi_os_initialize1();
 
diff --git a/drivers/acpi/button.c b/drivers/acpi/button.c
index d2e617b5b3f6..a55773801c5f 100644
--- a/drivers/acpi/button.c
+++ b/drivers/acpi/button.c
@@ -303,8 +303,6 @@ static void acpi_button_notify(struct acpi_device *device, u32 event)
 
 			pm_wakeup_event(&device->dev, 0);
 		}
-
-		acpi_bus_generate_proc_event(device, event, ++button->pushed);
 		break;
 	default:
 		ACPI_DEBUG_PRINT((ACPI_DB_INFO,
diff --git a/drivers/acpi/device_pm.c b/drivers/acpi/device_pm.c
index 4ab807dc8518..a94383d1f350 100644
--- a/drivers/acpi/device_pm.c
+++ b/drivers/acpi/device_pm.c
@@ -159,26 +159,29 @@ int acpi_device_set_power(struct acpi_device *device, int state)
 	int result = 0;
 	bool cut_power = false;
 
-	if (!device || (state < ACPI_STATE_D0) || (state > ACPI_STATE_D3_COLD))
+	if (!device || !device->flags.power_manageable
+	    || (state < ACPI_STATE_D0) || (state > ACPI_STATE_D3_COLD))
 		return -EINVAL;
 
 	/* Make sure this is a valid target state */
 
 	if (state == device->power.state) {
-		ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Device is already at %s\n",
+		ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Device [%s] already in %s\n",
+				  device->pnp.bus_id,
 				  acpi_power_state_string(state)));
 		return 0;
 	}
 
 	if (!device->power.states[state].flags.valid) {
-		printk(KERN_WARNING PREFIX "Device does not support %s\n",
-		       acpi_power_state_string(state));
+		dev_warn(&device->dev, "Power state %s not supported\n",
+			 acpi_power_state_string(state));
 		return -ENODEV;
 	}
 	if (device->parent && (state < device->parent->power.state)) {
-		printk(KERN_WARNING PREFIX
-			      "Cannot set device to a higher-powered"
-			      " state than parent\n");
+		dev_warn(&device->dev,
+			 "Cannot transition to power state %s for parent in %s\n",
+			 acpi_power_state_string(state),
+			 acpi_power_state_string(device->parent->power.state));
 		return -ENODEV;
 	}
 
@@ -191,8 +194,8 @@ int acpi_device_set_power(struct acpi_device *device, int state)
 
 	if (state < device->power.state && state != ACPI_STATE_D0
 	    && device->power.state >= ACPI_STATE_D3_HOT) {
-		printk(KERN_WARNING PREFIX
-			"Cannot transition to non-D0 state from D3\n");
+		dev_warn(&device->dev,
+			 "Cannot transition to non-D0 state from D3\n");
 		return -ENODEV;
 	}
 
@@ -219,10 +222,8 @@ int acpi_device_set_power(struct acpi_device *device, int state)
 
  end:
 	if (result) {
-		printk(KERN_WARNING PREFIX
-			      "Device [%s] failed to transition to %s\n",
-			      device->pnp.bus_id,
-			      acpi_power_state_string(state));
+		dev_warn(&device->dev, "Failed to change power state to %s\n",
+			 acpi_power_state_string(state));
 	} else {
 		device->power.state = state;
 		ACPI_DEBUG_PRINT((ACPI_DB_INFO,
@@ -244,13 +245,6 @@ int acpi_bus_set_power(acpi_handle handle, int state)
 	if (result)
 		return result;
 
-	if (!device->flags.power_manageable) {
-		ACPI_DEBUG_PRINT((ACPI_DB_INFO,
-				"Device [%s] is not power manageable\n",
-				dev_name(&device->dev)));
-		return -ENODEV;
-	}
-
 	return acpi_device_set_power(device, state);
 }
 EXPORT_SYMBOL(acpi_bus_set_power);
@@ -1031,60 +1025,4 @@ void acpi_dev_pm_detach(struct device *dev, bool power_off)
 	}
 }
 EXPORT_SYMBOL_GPL(acpi_dev_pm_detach);
-
-/**
- * acpi_dev_pm_add_dependent - Add physical device depending for PM.
- * @handle: Handle of ACPI device node.
- * @depdev: Device depending on that node for PM.
- */
-void acpi_dev_pm_add_dependent(acpi_handle handle, struct device *depdev)
-{
-	struct acpi_device_physical_node *dep;
-	struct acpi_device *adev;
-
-	if (!depdev || acpi_bus_get_device(handle, &adev))
-		return;
-
-	mutex_lock(&adev->physical_node_lock);
-
-	list_for_each_entry(dep, &adev->power_dependent, node)
-		if (dep->dev == depdev)
-			goto out;
-
-	dep = kzalloc(sizeof(*dep), GFP_KERNEL);
-	if (dep) {
-		dep->dev = depdev;
-		list_add_tail(&dep->node, &adev->power_dependent);
-	}
-
- out:
-	mutex_unlock(&adev->physical_node_lock);
-}
-EXPORT_SYMBOL_GPL(acpi_dev_pm_add_dependent);
-
-/**
- * acpi_dev_pm_remove_dependent - Remove physical device depending for PM.
- * @handle: Handle of ACPI device node.
- * @depdev: Device depending on that node for PM.
- */
-void acpi_dev_pm_remove_dependent(acpi_handle handle, struct device *depdev)
-{
-	struct acpi_device_physical_node *dep;
-	struct acpi_device *adev;
-
-	if (!depdev || acpi_bus_get_device(handle, &adev))
-		return;
-
-	mutex_lock(&adev->physical_node_lock);
-
-	list_for_each_entry(dep, &adev->power_dependent, node)
-		if (dep->dev == depdev) {
-			list_del(&dep->node);
-			kfree(dep);
-			break;
-		}
-
-	mutex_unlock(&adev->physical_node_lock);
-}
-EXPORT_SYMBOL_GPL(acpi_dev_pm_remove_dependent);
 #endif /* CONFIG_PM */
diff --git a/drivers/acpi/dock.c b/drivers/acpi/dock.c
index 826560753389..05ea4be01a83 100644
--- a/drivers/acpi/dock.c
+++ b/drivers/acpi/dock.c
@@ -51,8 +51,6 @@ MODULE_PARM_DESC(immediate_undock, "1 (default) will cause the driver to "
 	" the driver to wait for userspace to write the undock sysfs file "
 	" before undocking");
 
-static struct atomic_notifier_head dock_notifier_list;
-
 static const struct acpi_device_id dock_device_ids[] = {
 	{"LNXDOCK", 0},
 	{"", 0},
@@ -63,8 +61,6 @@ struct dock_station {
 	acpi_handle handle;
 	unsigned long last_dock_time;
 	u32 flags;
-	spinlock_t dd_lock;
-	struct mutex hp_lock;
 	struct list_head dependent_devices;
 
 	struct list_head sibling;
@@ -91,6 +87,12 @@ struct dock_dependent_device {
 #define DOCK_EVENT	3
 #define UNDOCK_EVENT	2
 
+enum dock_callback_type {
+	DOCK_CALL_HANDLER,
+	DOCK_CALL_FIXUP,
+	DOCK_CALL_UEVENT,
+};
+
 /*****************************************************************************
  *                         Dock Dependent device functions                   *
  *****************************************************************************/
@@ -101,7 +103,7 @@ struct dock_dependent_device {
  *
  * Add the dependent device to the dock's dependent device list.
  */
-static int
+static int __init
 add_dock_dependent_device(struct dock_station *ds, acpi_handle handle)
 {
 	struct dock_dependent_device *dd;
@@ -112,14 +114,21 @@ add_dock_dependent_device(struct dock_station *ds, acpi_handle handle)
 
 	dd->handle = handle;
 	INIT_LIST_HEAD(&dd->list);
-
-	spin_lock(&ds->dd_lock);
 	list_add_tail(&dd->list, &ds->dependent_devices);
-	spin_unlock(&ds->dd_lock);
 
 	return 0;
 }
 
+static void remove_dock_dependent_devices(struct dock_station *ds)
+{
+	struct dock_dependent_device *dd, *aux;
+
+	list_for_each_entry_safe(dd, aux, &ds->dependent_devices, list) {
+		list_del(&dd->list);
+		kfree(dd);
+	}
+}
+
 /**
  * dock_init_hotplug - Initialize a hotplug device on a docking station.
  * @dd: Dock-dependent device.
@@ -135,19 +144,16 @@ static int dock_init_hotplug(struct dock_dependent_device *dd,
 	int ret = 0;
 
 	mutex_lock(&hotplug_lock);
-
-	if (dd->hp_context) {
+	if (WARN_ON(dd->hp_context)) {
 		ret = -EEXIST;
 	} else {
 		dd->hp_refcount = 1;
 		dd->hp_ops = ops;
 		dd->hp_context = context;
 		dd->hp_release = release;
+		if (init)
+			init(context);
 	}
-
-	if (!WARN_ON(ret) && init)
-		init(context);
-
 	mutex_unlock(&hotplug_lock);
 	return ret;
 }
@@ -162,27 +168,22 @@ static int dock_init_hotplug(struct dock_dependent_device *dd,
  */
 static void dock_release_hotplug(struct dock_dependent_device *dd)
 {
-	void (*release)(void *) = NULL;
-	void *context = NULL;
-
 	mutex_lock(&hotplug_lock);
-
 	if (dd->hp_context && !--dd->hp_refcount) {
+		void (*release)(void *) = dd->hp_release;
+		void *context = dd->hp_context;
+
 		dd->hp_ops = NULL;
-		context = dd->hp_context;
 		dd->hp_context = NULL;
-		release = dd->hp_release;
 		dd->hp_release = NULL;
+		if (release)
+			release(context);
 	}
-
-	if (release && context)
-		release(context);
-
 	mutex_unlock(&hotplug_lock);
 }
 
 static void dock_hotplug_event(struct dock_dependent_device *dd, u32 event,
-			       bool uevent)
+			       enum dock_callback_type cb_type)
 {
 	acpi_notify_handler cb = NULL;
 	bool run = false;
@@ -192,8 +193,18 @@ static void dock_hotplug_event(struct dock_dependent_device *dd, u32 event,
 	if (dd->hp_context) {
 		run = true;
 		dd->hp_refcount++;
-		if (dd->hp_ops)
-			cb = uevent ? dd->hp_ops->uevent : dd->hp_ops->handler;
+		if (dd->hp_ops) {
+			switch (cb_type) {
+			case DOCK_CALL_FIXUP:
+				cb = dd->hp_ops->fixup;
+				break;
+			case DOCK_CALL_UEVENT:
+				cb = dd->hp_ops->uevent;
+				break;
+			default:
+				cb = dd->hp_ops->handler;
+			}
+		}
 	}
 
 	mutex_unlock(&hotplug_lock);
@@ -220,63 +231,17 @@ find_dock_dependent_device(struct dock_station *ds, acpi_handle handle)
 {
 	struct dock_dependent_device *dd;
 
-	spin_lock(&ds->dd_lock);
-	list_for_each_entry(dd, &ds->dependent_devices, list) {
-		if (handle == dd->handle) {
-			spin_unlock(&ds->dd_lock);
+	list_for_each_entry(dd, &ds->dependent_devices, list)
+		if (handle == dd->handle)
 			return dd;
-		}
-	}
-	spin_unlock(&ds->dd_lock);
+
 	return NULL;
 }
 
 /*****************************************************************************
  *                         Dock functions                                    *
  *****************************************************************************/
-/**
- * is_dock - see if a device is a dock station
- * @handle: acpi handle of the device
- *
- * If an acpi object has a _DCK method, then it is by definition a dock
- * station, so return true.
- */
-static int is_dock(acpi_handle handle)
-{
-	acpi_status status;
-	acpi_handle tmp;
-
-	status = acpi_get_handle(handle, "_DCK", &tmp);
-	if (ACPI_FAILURE(status))
-		return 0;
-	return 1;
-}
-
-static int is_ejectable(acpi_handle handle)
-{
-	acpi_status status;
-	acpi_handle tmp;
-
-	status = acpi_get_handle(handle, "_EJ0", &tmp);
-	if (ACPI_FAILURE(status))
-		return 0;
-	return 1;
-}
-
-static int is_ata(acpi_handle handle)
-{
-	acpi_handle tmp;
-
-	if ((ACPI_SUCCESS(acpi_get_handle(handle, "_GTF", &tmp))) ||
-	   (ACPI_SUCCESS(acpi_get_handle(handle, "_GTM", &tmp))) ||
-	   (ACPI_SUCCESS(acpi_get_handle(handle, "_STM", &tmp))) ||
-	   (ACPI_SUCCESS(acpi_get_handle(handle, "_SDD", &tmp))))
-		return 1;
-
-	return 0;
-}
-
-static int is_battery(acpi_handle handle)
+static int __init is_battery(acpi_handle handle)
 {
 	struct acpi_device_info *info;
 	int ret = 1;
@@ -292,17 +257,13 @@ static int is_battery(acpi_handle handle)
 	return ret;
 }
 
-static int is_ejectable_bay(acpi_handle handle)
+/* Check whether ACPI object is an ejectable battery or disk bay */
+static bool __init is_ejectable_bay(acpi_handle handle)
 {
-	acpi_handle phandle;
+	if (acpi_has_method(handle, "_EJ0") && is_battery(handle))
+		return true;
 
-	if (!is_ejectable(handle))
-		return 0;
-	if (is_battery(handle) || is_ata(handle))
-		return 1;
-	if (!acpi_get_parent(handle, &phandle) && is_ata(phandle))
-		return 1;
-	return 0;
+	return acpi_bay_match(handle);
 }
 
 /**
@@ -320,7 +281,7 @@ int is_dock_device(acpi_handle handle)
 	if (!dock_station_count)
 		return 0;
 
-	if (is_dock(handle))
+	if (acpi_dock_match(handle))
 		return 1;
 
 	list_for_each_entry(dock_station, &dock_stations, sibling)
@@ -359,10 +320,8 @@ static int dock_present(struct dock_station *ds)
  *  handle if one does not exist already.  This should cause
  *  acpi to scan for drivers for the given devices, and call
  *  matching driver's add routine.
- *
- *  Returns a pointer to the acpi_device corresponding to the handle.
  */
-static struct acpi_device * dock_create_acpi_device(acpi_handle handle)
+static void dock_create_acpi_device(acpi_handle handle)
 {
 	struct acpi_device *device;
 	int ret;
@@ -375,10 +334,7 @@ static struct acpi_device * dock_create_acpi_device(acpi_handle handle)
 		ret = acpi_bus_scan(handle);
 		if (ret)
 			pr_debug("error adding bus, %x\n", -ret);
-
-		acpi_bus_get_device(handle, &device);
 	}
-	return device;
 }
 
 /**
@@ -397,9 +353,29 @@ static void dock_remove_acpi_device(acpi_handle handle)
 }
 
 /**
- * hotplug_dock_devices - insert or remove devices on the dock station
+ * hot_remove_dock_devices - Remove dock station devices.
+ * @ds: Dock station.
+ */
+static void hot_remove_dock_devices(struct dock_station *ds)
+{
+	struct dock_dependent_device *dd;
+
+	/*
+	 * Walk the list in reverse order so that devices that have been added
+	 * last are removed first (in case there are some indirect dependencies
+	 * between them).
+	 */
+	list_for_each_entry_reverse(dd, &ds->dependent_devices, list)
+		dock_hotplug_event(dd, ACPI_NOTIFY_EJECT_REQUEST, false);
+
+	list_for_each_entry_reverse(dd, &ds->dependent_devices, list)
+		dock_remove_acpi_device(dd->handle);
+}
+
+/**
+ * hotplug_dock_devices - Insert devices on a dock station.
  * @ds: the dock station
- * @event: either bus check or eject request
+ * @event: either bus check or device check request
  *
  * Some devices on the dock station need to have drivers called
  * to perform hotplug operations after a dock event has occurred.
@@ -410,27 +386,21 @@ static void hotplug_dock_devices(struct dock_station *ds, u32 event)
 {
 	struct dock_dependent_device *dd;
 
-	mutex_lock(&ds->hp_lock);
+	/* Call driver specific post-dock fixups. */
+	list_for_each_entry(dd, &ds->dependent_devices, list)
+		dock_hotplug_event(dd, event, DOCK_CALL_FIXUP);
 
-	/*
-	 * First call driver specific hotplug functions
-	 */
+	/* Call driver specific hotplug functions. */
 	list_for_each_entry(dd, &ds->dependent_devices, list)
-		dock_hotplug_event(dd, event, false);
+		dock_hotplug_event(dd, event, DOCK_CALL_HANDLER);
 
 	/*
-	 * Now make sure that an acpi_device is created for each
-	 * dependent device, or removed if this is an eject request.
-	 * This will cause acpi_drivers to be stopped/started if they
-	 * exist
+	 * Now make sure that an acpi_device is created for each dependent
+	 * device.  That will cause scan handlers to be attached to device
+	 * objects or acpi_drivers to be stopped/started if they are present.
 	 */
-	list_for_each_entry(dd, &ds->dependent_devices, list) {
-		if (event == ACPI_NOTIFY_EJECT_REQUEST)
-			dock_remove_acpi_device(dd->handle);
-		else
-			dock_create_acpi_device(dd->handle);
-	}
-	mutex_unlock(&ds->hp_lock);
+	list_for_each_entry(dd, &ds->dependent_devices, list)
+		dock_create_acpi_device(dd->handle);
 }
 
 static void dock_event(struct dock_station *ds, u32 event, int num)
@@ -453,44 +423,13 @@ static void dock_event(struct dock_station *ds, u32 event, int num)
 		kobject_uevent_env(&dev->kobj, KOBJ_CHANGE, envp);
 
 	list_for_each_entry(dd, &ds->dependent_devices, list)
-		dock_hotplug_event(dd, event, true);
+		dock_hotplug_event(dd, event, DOCK_CALL_UEVENT);
 
 	if (num != DOCK_EVENT)
 		kobject_uevent_env(&dev->kobj, KOBJ_CHANGE, envp);
 }
 
 /**
- * eject_dock - respond to a dock eject request
- * @ds: the dock station
- *
- * This is called after _DCK is called, to execute the dock station's
- * _EJ0 method.
- */
-static void eject_dock(struct dock_station *ds)
-{
-	struct acpi_object_list arg_list;
-	union acpi_object arg;
-	acpi_status status;
-	acpi_handle tmp;
-
-	/* all dock devices should have _EJ0, but check anyway */
-	status = acpi_get_handle(ds->handle, "_EJ0", &tmp);
-	if (ACPI_FAILURE(status)) {
-		pr_debug("No _EJ0 support for dock device\n");
-		return;
-	}
-
-	arg_list.count = 1;
-	arg_list.pointer = &arg;
-	arg.type = ACPI_TYPE_INTEGER;
-	arg.integer.value = 1;
-
-	status = acpi_evaluate_object(ds->handle, "_EJ0", &arg_list, NULL);
-	if (ACPI_FAILURE(status))
-		pr_debug("Failed to evaluate _EJ0!\n");
-}
-
-/**
  * handle_dock - handle a dock event
  * @ds: the dock station
  * @dock: to dock, or undock - that is the question
@@ -550,27 +489,6 @@ static inline void complete_undock(struct dock_station *ds)
 	ds->flags &= ~(DOCK_UNDOCKING);
 }
 
-static void dock_lock(struct dock_station *ds, int lock)
-{
-	struct acpi_object_list arg_list;
-	union acpi_object arg;
-	acpi_status status;
-
-	arg_list.count = 1;
-	arg_list.pointer = &arg;
-	arg.type = ACPI_TYPE_INTEGER;
-	arg.integer.value = !!lock;
-	status = acpi_evaluate_object(ds->handle, "_LCK", &arg_list, NULL);
-	if (ACPI_FAILURE(status) && status != AE_NOT_FOUND) {
-		if (lock)
-			acpi_handle_warn(ds->handle,
-				"Locking device failed (0x%x)\n", status);
-		else
-			acpi_handle_warn(ds->handle,
-				"Unlocking device failed (0x%x)\n", status);
-	}
-}
-
 /**
  * dock_in_progress - see if we are in the middle of handling a dock event
  * @ds: the dock station
@@ -588,37 +506,6 @@ static int dock_in_progress(struct dock_station *ds)
 }
 
 /**
- * register_dock_notifier - add yourself to the dock notifier list
- * @nb: the callers notifier block
- *
- * If a driver wishes to be notified about dock events, they can
- * use this function to put a notifier block on the dock notifier list.
- * this notifier call chain will be called after a dock event, but
- * before hotplugging any new devices.
- */
-int register_dock_notifier(struct notifier_block *nb)
-{
-	if (!dock_station_count)
-		return -ENODEV;
-
-	return atomic_notifier_chain_register(&dock_notifier_list, nb);
-}
-EXPORT_SYMBOL_GPL(register_dock_notifier);
-
-/**
- * unregister_dock_notifier - remove yourself from the dock notifier list
- * @nb: the callers notifier block
- */
-void unregister_dock_notifier(struct notifier_block *nb)
-{
-	if (!dock_station_count)
-		return;
-
-	atomic_notifier_chain_unregister(&dock_notifier_list, nb);
-}
-EXPORT_SYMBOL_GPL(unregister_dock_notifier);
-
-/**
  * register_hotplug_dock_device - register a hotplug function
  * @handle: the handle of the device
  * @ops: handlers to call after docking
@@ -703,10 +590,10 @@ static int handle_eject_request(struct dock_station *ds, u32 event)
 	 */
 	dock_event(ds, event, UNDOCK_EVENT);
 
-	hotplug_dock_devices(ds, ACPI_NOTIFY_EJECT_REQUEST);
+	hot_remove_dock_devices(ds);
 	undock(ds);
-	dock_lock(ds, 0);
-	eject_dock(ds);
+	acpi_evaluate_lck(ds->handle, 0);
+	acpi_evaluate_ej0(ds->handle);
 	if (dock_present(ds)) {
 		acpi_handle_err(ds->handle, "Unable to undock!\n");
 		return -EBUSY;
@@ -717,18 +604,17 @@ static int handle_eject_request(struct dock_station *ds, u32 event)
 
 /**
  * dock_notify - act upon an acpi dock notification
- * @handle: the dock station handle
+ * @ds: dock station
  * @event: the acpi event
- * @data: our driver data struct
  *
  * If we are notified to dock, then check to see if the dock is
  * present and then dock.  Notify all drivers of the dock event,
  * and then hotplug and devices that may need hotplugging.
  */
-static void dock_notify(acpi_handle handle, u32 event, void *data)
+static void dock_notify(struct dock_station *ds, u32 event)
 {
-	struct dock_station *ds = data;
-	struct acpi_device *tmp;
+	acpi_handle handle = ds->handle;
+	struct acpi_device *ad;
 	int surprise_removal = 0;
 
 	/*
@@ -751,8 +637,7 @@ static void dock_notify(acpi_handle handle, u32 event, void *data)
 	switch (event) {
 	case ACPI_NOTIFY_BUS_CHECK:
 	case ACPI_NOTIFY_DEVICE_CHECK:
-		if (!dock_in_progress(ds) && acpi_bus_get_device(ds->handle,
-		   &tmp)) {
+		if (!dock_in_progress(ds) && acpi_bus_get_device(handle, &ad)) {
 			begin_dock(ds);
 			dock(ds);
 			if (!dock_present(ds)) {
@@ -760,12 +645,10 @@ static void dock_notify(acpi_handle handle, u32 event, void *data)
 				complete_dock(ds);
 				break;
 			}
-			atomic_notifier_call_chain(&dock_notifier_list,
-						   event, NULL);
 			hotplug_dock_devices(ds, event);
 			complete_dock(ds);
 			dock_event(ds, event, DOCK_EVENT);
-			dock_lock(ds, 1);
+			acpi_evaluate_lck(ds->handle, 1);
 			acpi_update_all_gpes();
 			break;
 		}
@@ -789,9 +672,8 @@ static void dock_notify(acpi_handle handle, u32 event, void *data)
 }
 
 struct dock_data {
-	acpi_handle handle;
-	unsigned long event;
 	struct dock_station *ds;
+	u32 event;
 };
 
 static void acpi_dock_deferred_cb(void *context)
@@ -799,52 +681,31 @@ static void acpi_dock_deferred_cb(void *context)
 	struct dock_data *data = context;
 
 	acpi_scan_lock_acquire();
-	dock_notify(data->handle, data->event, data->ds);
+	dock_notify(data->ds, data->event);
 	acpi_scan_lock_release();
 	kfree(data);
 }
 
-static int acpi_dock_notifier_call(struct notifier_block *this,
-	unsigned long event, void *data)
+static void dock_notify_handler(acpi_handle handle, u32 event, void *data)
 {
-	struct dock_station *dock_station;
-	acpi_handle handle = data;
+	struct dock_data *dd;
 
 	if (event != ACPI_NOTIFY_BUS_CHECK && event != ACPI_NOTIFY_DEVICE_CHECK
 	   && event != ACPI_NOTIFY_EJECT_REQUEST)
-		return 0;
-
-	acpi_scan_lock_acquire();
-
-	list_for_each_entry(dock_station, &dock_stations, sibling) {
-		if (dock_station->handle == handle) {
-			struct dock_data *dd;
-			acpi_status status;
-
-			dd = kmalloc(sizeof(*dd), GFP_KERNEL);
-			if (!dd)
-				break;
+		return;
 
-			dd->handle = handle;
-			dd->event = event;
-			dd->ds = dock_station;
-			status = acpi_os_hotplug_execute(acpi_dock_deferred_cb,
-							 dd);
-			if (ACPI_FAILURE(status))
-				kfree(dd);
+	dd = kmalloc(sizeof(*dd), GFP_KERNEL);
+	if (dd) {
+		acpi_status status;
 
-			break;
-		}
+		dd->ds = data;
+		dd->event = event;
+		status = acpi_os_hotplug_execute(acpi_dock_deferred_cb, dd);
+		if (ACPI_FAILURE(status))
+			kfree(dd);
 	}
-
-	acpi_scan_lock_release();
-	return 0;
 }
 
-static struct notifier_block dock_acpi_notifier = {
-	.notifier_call = acpi_dock_notifier_call,
-};
-
 /**
  * find_dock_devices - find devices on the dock station
  * @handle: the handle of the device we are examining
@@ -856,29 +717,16 @@ static struct notifier_block dock_acpi_notifier = {
  * check to see if an object has an _EJD method.  If it does, then it
  * will see if it is dependent on the dock station.
  */
-static acpi_status
-find_dock_devices(acpi_handle handle, u32 lvl, void *context, void **rv)
+static acpi_status __init find_dock_devices(acpi_handle handle, u32 lvl,
+					    void *context, void **rv)
 {
-	acpi_status status;
-	acpi_handle tmp, parent;
 	struct dock_station *ds = context;
+	acpi_handle ejd = NULL;
 
-	status = acpi_bus_get_ejd(handle, &tmp);
-	if (ACPI_FAILURE(status)) {
-		/* try the parent device as well */
-		status = acpi_get_parent(handle, &parent);
-		if (ACPI_FAILURE(status))
-			goto fdd_out;
-		/* see if parent is dependent on dock */
-		status = acpi_bus_get_ejd(parent, &tmp);
-		if (ACPI_FAILURE(status))
-			goto fdd_out;
-	}
-
-	if (tmp == ds->handle)
+	acpi_bus_get_ejd(handle, &ejd);
+	if (ejd == ds->handle)
 		add_dock_dependent_device(ds, handle);
 
-fdd_out:
 	return AE_OK;
 }
 
@@ -988,13 +836,13 @@ static struct attribute_group dock_attribute_group = {
  */
 static int __init dock_add(acpi_handle handle)
 {
-	int ret, id;
-	struct dock_station ds, *dock_station;
+	struct dock_station *dock_station, ds = { NULL, };
 	struct platform_device *dd;
+	acpi_status status;
+	int ret;
 
-	id = dock_station_count;
-	memset(&ds, 0, sizeof(ds));
-	dd = platform_device_register_data(NULL, "dock", id, &ds, sizeof(ds));
+	dd = platform_device_register_data(NULL, "dock", dock_station_count,
+					   &ds, sizeof(ds));
 	if (IS_ERR(dd))
 		return PTR_ERR(dd);
 
@@ -1004,18 +852,15 @@ static int __init dock_add(acpi_handle handle)
 	dock_station->dock_device = dd;
 	dock_station->last_dock_time = jiffies - HZ;
 
-	mutex_init(&dock_station->hp_lock);
-	spin_lock_init(&dock_station->dd_lock);
 	INIT_LIST_HEAD(&dock_station->sibling);
-	ATOMIC_INIT_NOTIFIER_HEAD(&dock_notifier_list);
 	INIT_LIST_HEAD(&dock_station->dependent_devices);
 
 	/* we want the dock device to send uevents */
 	dev_set_uevent_suppress(&dd->dev, 0);
 
-	if (is_dock(handle))
+	if (acpi_dock_match(handle))
 		dock_station->flags |= DOCK_IS_DOCK;
-	if (is_ata(handle))
+	if (acpi_ata_match(handle))
 		dock_station->flags |= DOCK_IS_ATA;
 	if (is_battery(handle))
 		dock_station->flags |= DOCK_IS_BAT;
@@ -1034,11 +879,19 @@ static int __init dock_add(acpi_handle handle)
 	if (ret)
 		goto err_rmgroup;
 
+	status = acpi_install_notify_handler(handle, ACPI_SYSTEM_NOTIFY,
+					     dock_notify_handler, dock_station);
+	if (ACPI_FAILURE(status)) {
+		ret = -ENODEV;
+		goto err_rmgroup;
+	}
+
 	dock_station_count++;
 	list_add(&dock_station->sibling, &dock_stations);
 	return 0;
 
 err_rmgroup:
+	remove_dock_dependent_devices(dock_station);
 	sysfs_remove_group(&dd->dev.kobj, &dock_attribute_group);
 err_unregister:
 	platform_device_unregister(dd);
@@ -1055,10 +908,10 @@ err_unregister:
  *
  * This is called by acpi_walk_namespace to look for dock stations and bays.
  */
-static __init acpi_status
+static acpi_status __init
 find_dock_and_bay(acpi_handle handle, u32 lvl, void *context, void **rv)
 {
-	if (is_dock(handle) || is_ejectable_bay(handle))
+	if (acpi_dock_match(handle) || is_ejectable_bay(handle))
 		dock_add(handle);
 
 	return AE_OK;
@@ -1078,7 +931,6 @@ void __init acpi_dock_init(void)
 		return;
 	}
 
-	register_acpi_bus_notifier(&dock_acpi_notifier);
 	pr_info(PREFIX "%s: %d docks/bays found\n",
 		ACPI_DOCK_DRIVER_DESCRIPTION, dock_station_count);
 }
diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c
index 80403c1a89f8..a06d98374705 100644
--- a/drivers/acpi/ec.c
+++ b/drivers/acpi/ec.c
@@ -948,7 +948,7 @@ static int ec_enlarge_storm_threshold(const struct dmi_system_id *id)
 	return 0;
 }
 
-static struct dmi_system_id __initdata ec_dmi_table[] = {
+static struct dmi_system_id ec_dmi_table[] __initdata = {
 	{
 	ec_skip_dsdt_scan, "Compal JFL92", {
 	DMI_MATCH(DMI_BIOS_VENDOR, "COMPAL"),
@@ -987,6 +987,10 @@ static struct dmi_system_id __initdata ec_dmi_table[] = {
 	ec_skip_dsdt_scan, "HP Folio 13", {
 	DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
 	DMI_MATCH(DMI_PRODUCT_NAME, "HP Folio 13"),}, NULL},
+	{
+	ec_validate_ecdt, "ASUS hardware", {
+	DMI_MATCH(DMI_SYS_VENDOR, "ASUSTek Computer Inc."),
+	DMI_MATCH(DMI_PRODUCT_NAME, "L4R"),}, NULL},
 	{},
 };
 
@@ -1049,10 +1053,8 @@ int __init acpi_ec_ecdt_probe(void)
 		* which needs it, has fake EC._INI method, so use it as flag.
 		* Keep boot_ec struct as it will be needed soon.
 		*/
-		acpi_handle dummy;
 		if (!dmi_name_in_vendors("ASUS") ||
-		    ACPI_FAILURE(acpi_get_handle(boot_ec->handle, "_INI",
-							&dummy)))
+		    !acpi_has_method(boot_ec->handle, "_INI"))
 			return -ENODEV;
 	}
 install:
diff --git a/drivers/acpi/event.c b/drivers/acpi/event.c
index 1442737cedec..8247fcdde079 100644
--- a/drivers/acpi/event.c
+++ b/drivers/acpi/event.c
@@ -21,100 +21,6 @@
 #define _COMPONENT		ACPI_SYSTEM_COMPONENT
 ACPI_MODULE_NAME("event");
 
-#ifdef CONFIG_ACPI_PROC_EVENT
-/* Global vars for handling event proc entry */
-static DEFINE_SPINLOCK(acpi_system_event_lock);
-int event_is_open = 0;
-extern struct list_head acpi_bus_event_list;
-extern wait_queue_head_t acpi_bus_event_queue;
-
-static int acpi_system_open_event(struct inode *inode, struct file *file)
-{
-	spin_lock_irq(&acpi_system_event_lock);
-
-	if (event_is_open)
-		goto out_busy;
-
-	event_is_open = 1;
-
-	spin_unlock_irq(&acpi_system_event_lock);
-	return 0;
-
-      out_busy:
-	spin_unlock_irq(&acpi_system_event_lock);
-	return -EBUSY;
-}
-
-static ssize_t
-acpi_system_read_event(struct file *file, char __user * buffer, size_t count,
-		       loff_t * ppos)
-{
-	int result = 0;
-	struct acpi_bus_event event;
-	static char str[ACPI_MAX_STRING];
-	static int chars_remaining = 0;
-	static char *ptr;
-
-	if (!chars_remaining) {
-		memset(&event, 0, sizeof(struct acpi_bus_event));
-
-		if ((file->f_flags & O_NONBLOCK)
-		    && (list_empty(&acpi_bus_event_list)))
-			return -EAGAIN;
-
-		result = acpi_bus_receive_event(&event);
-		if (result)
-			return result;
-
-		chars_remaining = sprintf(str, "%s %s %08x %08x\n",
-					  event.device_class ? event.
-					  device_class : "<unknown>",
-					  event.bus_id ? event.
-					  bus_id : "<unknown>", event.type,
-					  event.data);
-		ptr = str;
-	}
-
-	if (chars_remaining < count) {
-		count = chars_remaining;
-	}
-
-	if (copy_to_user(buffer, ptr, count))
-		return -EFAULT;
-
-	*ppos += count;
-	chars_remaining -= count;
-	ptr += count;
-
-	return count;
-}
-
-static int acpi_system_close_event(struct inode *inode, struct file *file)
-{
-	spin_lock_irq(&acpi_system_event_lock);
-	event_is_open = 0;
-	spin_unlock_irq(&acpi_system_event_lock);
-	return 0;
-}
-
-static unsigned int acpi_system_poll_event(struct file *file, poll_table * wait)
-{
-	poll_wait(file, &acpi_bus_event_queue, wait);
-	if (!list_empty(&acpi_bus_event_list))
-		return POLLIN | POLLRDNORM;
-	return 0;
-}
-
-static const struct file_operations acpi_system_event_ops = {
-	.owner = THIS_MODULE,
-	.open = acpi_system_open_event,
-	.read = acpi_system_read_event,
-	.release = acpi_system_close_event,
-	.poll = acpi_system_poll_event,
-	.llseek = default_llseek,
-};
-#endif	/* CONFIG_ACPI_PROC_EVENT */
-
 /* ACPI notifier chain */
 static BLOCKING_NOTIFIER_HEAD(acpi_chain_head);
 
@@ -280,9 +186,6 @@ static int acpi_event_genetlink_init(void)
 
 static int __init acpi_event_init(void)
 {
-#ifdef CONFIG_ACPI_PROC_EVENT
-	struct proc_dir_entry *entry;
-#endif
 	int error = 0;
 
 	if (acpi_disabled)
@@ -293,15 +196,6 @@ static int __init acpi_event_init(void)
 	if (error)
 		printk(KERN_WARNING PREFIX
 		       "Failed to create genetlink family for ACPI event\n");
-
-#ifdef CONFIG_ACPI_PROC_EVENT
-	/* 'event' [R] */
-	entry = proc_create("event", S_IRUSR, acpi_root_dir,
-			    &acpi_system_event_ops);
-	if (!entry)
-		return -ENODEV;
-#endif
-
 	return 0;
 }
 
diff --git a/drivers/acpi/fan.c b/drivers/acpi/fan.c
index 5b02a0aa540c..41ade6570bc0 100644
--- a/drivers/acpi/fan.c
+++ b/drivers/acpi/fan.c
@@ -93,7 +93,7 @@ static int fan_get_cur_state(struct thermal_cooling_device *cdev, unsigned long
 	if (result)
 		return result;
 
-	*state = (acpi_state == ACPI_STATE_D3 ? 0 :
+	*state = (acpi_state == ACPI_STATE_D3_COLD ? 0 :
 		 (acpi_state == ACPI_STATE_D0 ? 1 : -1));
 	return 0;
 }
@@ -108,7 +108,7 @@ fan_set_cur_state(struct thermal_cooling_device *cdev, unsigned long state)
 		return -EINVAL;
 
 	result = acpi_bus_set_power(device->handle,
-				state ? ACPI_STATE_D0 : ACPI_STATE_D3);
+				state ? ACPI_STATE_D0 : ACPI_STATE_D3_COLD);
 
 	return result;
 }
diff --git a/drivers/acpi/glue.c b/drivers/acpi/glue.c
index 408f6b2a5fa8..10f0f40587bb 100644
--- a/drivers/acpi/glue.c
+++ b/drivers/acpi/glue.c
@@ -79,6 +79,9 @@ static struct acpi_bus_type *acpi_get_bus_type(struct device *dev)
 	return ret;
 }
 
+#define FIND_CHILD_MIN_SCORE	1
+#define FIND_CHILD_MAX_SCORE	2
+
 static acpi_status acpi_dev_present(acpi_handle handle, u32 lvl_not_used,
 				  void *not_used, void **ret_p)
 {
@@ -92,14 +95,17 @@ static acpi_status acpi_dev_present(acpi_handle handle, u32 lvl_not_used,
 	return AE_OK;
 }
 
-static bool acpi_extra_checks_passed(acpi_handle handle, bool is_bridge)
+static int do_find_child_checks(acpi_handle handle, bool is_bridge)
 {
+	bool sta_present = true;
 	unsigned long long sta;
 	acpi_status status;
 
-	status = acpi_bus_get_status_handle(handle, &sta);
-	if (ACPI_FAILURE(status) || !(sta & ACPI_STA_DEVICE_ENABLED))
-		return false;
+	status = acpi_evaluate_integer(handle, "_STA", NULL, &sta);
+	if (status == AE_NOT_FOUND)
+		sta_present = false;
+	else if (ACPI_FAILURE(status) || !(sta & ACPI_STA_DEVICE_ENABLED))
+		return -ENODEV;
 
 	if (is_bridge) {
 		void *test = NULL;
@@ -107,16 +113,17 @@ static bool acpi_extra_checks_passed(acpi_handle handle, bool is_bridge)
 		/* Check if this object has at least one child device. */
 		acpi_walk_namespace(ACPI_TYPE_DEVICE, handle, 1,
 				    acpi_dev_present, NULL, NULL, &test);
-		return !!test;
+		if (!test)
+			return -ENODEV;
 	}
-	return true;
+	return sta_present ? FIND_CHILD_MAX_SCORE : FIND_CHILD_MIN_SCORE;
 }
 
 struct find_child_context {
 	u64 addr;
 	bool is_bridge;
 	acpi_handle ret;
-	bool ret_checked;
+	int ret_score;
 };
 
 static acpi_status do_find_child(acpi_handle handle, u32 lvl_not_used,
@@ -125,6 +132,7 @@ static acpi_status do_find_child(acpi_handle handle, u32 lvl_not_used,
 	struct find_child_context *context = data;
 	unsigned long long addr;
 	acpi_status status;
+	int score;
 
 	status = acpi_evaluate_integer(handle, METHOD_NAME__ADR, NULL, &addr);
 	if (ACPI_FAILURE(status) || addr != context->addr)
@@ -144,15 +152,20 @@ static acpi_status do_find_child(acpi_handle handle, u32 lvl_not_used,
 	 * its handle if so.  Second, check the same for the object that we've
 	 * just found.
 	 */
-	if (!context->ret_checked) {
-		if (acpi_extra_checks_passed(context->ret, context->is_bridge))
+	if (!context->ret_score) {
+		score = do_find_child_checks(context->ret, context->is_bridge);
+		if (score == FIND_CHILD_MAX_SCORE)
 			return AE_CTRL_TERMINATE;
 		else
-			context->ret_checked = true;
+			context->ret_score = score;
 	}
-	if (acpi_extra_checks_passed(handle, context->is_bridge)) {
+	score = do_find_child_checks(handle, context->is_bridge);
+	if (score == FIND_CHILD_MAX_SCORE) {
 		context->ret = handle;
 		return AE_CTRL_TERMINATE;
+	} else if (score > context->ret_score) {
+		context->ret = handle;
+		context->ret_score = score;
 	}
 	return AE_OK;
 }
@@ -173,6 +186,15 @@ acpi_handle acpi_find_child(acpi_handle parent, u64 addr, bool is_bridge)
 }
 EXPORT_SYMBOL_GPL(acpi_find_child);
 
+static void acpi_physnode_link_name(char *buf, unsigned int node_id)
+{
+	if (node_id > 0)
+		snprintf(buf, PHYSICAL_NODE_NAME_SIZE,
+			 PHYSICAL_NODE_STRING "%u", node_id);
+	else
+		strcpy(buf, PHYSICAL_NODE_STRING);
+}
+
 int acpi_bind_one(struct device *dev, acpi_handle handle)
 {
 	struct acpi_device *acpi_dev;
@@ -216,8 +238,15 @@ int acpi_bind_one(struct device *dev, acpi_handle handle)
 	list_for_each_entry(pn, &acpi_dev->physical_node_list, node) {
 		/* Sanity check. */
 		if (pn->dev == dev) {
+			mutex_unlock(&acpi_dev->physical_node_lock);
+
 			dev_warn(dev, "Already associated with ACPI node\n");
-			goto err_free;
+			kfree(physical_node);
+			if (ACPI_HANDLE(dev) != handle)
+				goto err;
+
+			put_device(dev);
+			return 0;
 		}
 		if (pn->node_id == node_id) {
 			physnode_list = &pn->node;
@@ -230,20 +259,23 @@ int acpi_bind_one(struct device *dev, acpi_handle handle)
 	list_add(&physical_node->node, physnode_list);
 	acpi_dev->physical_node_count++;
 
-	mutex_unlock(&acpi_dev->physical_node_lock);
-
 	if (!ACPI_HANDLE(dev))
 		ACPI_HANDLE_SET(dev, acpi_dev->handle);
 
-	if (!physical_node->node_id)
-		strcpy(physical_node_name, PHYSICAL_NODE_STRING);
-	else
-		sprintf(physical_node_name,
-			"physical_node%d", physical_node->node_id);
+	acpi_physnode_link_name(physical_node_name, node_id);
 	retval = sysfs_create_link(&acpi_dev->dev.kobj, &dev->kobj,
-			physical_node_name);
+				   physical_node_name);
+	if (retval)
+		dev_err(&acpi_dev->dev, "Failed to create link %s (%d)\n",
+			physical_node_name, retval);
+
 	retval = sysfs_create_link(&dev->kobj, &acpi_dev->dev.kobj,
-		"firmware_node");
+				   "firmware_node");
+	if (retval)
+		dev_err(dev, "Failed to create link firmware_node (%d)\n",
+			retval);
+
+	mutex_unlock(&acpi_dev->physical_node_lock);
 
 	if (acpi_dev->wakeup.flags.valid)
 		device_set_wakeup_capable(dev, true);
@@ -254,11 +286,6 @@ int acpi_bind_one(struct device *dev, acpi_handle handle)
 	ACPI_HANDLE_SET(dev, NULL);
 	put_device(dev);
 	return retval;
-
- err_free:
-	mutex_unlock(&acpi_dev->physical_node_lock);
-	kfree(physical_node);
-	goto err;
 }
 EXPORT_SYMBOL_GPL(acpi_bind_one);
 
@@ -267,48 +294,37 @@ int acpi_unbind_one(struct device *dev)
 	struct acpi_device_physical_node *entry;
 	struct acpi_device *acpi_dev;
 	acpi_status status;
-	struct list_head *node, *next;
 
 	if (!ACPI_HANDLE(dev))
 		return 0;
 
 	status = acpi_bus_get_device(ACPI_HANDLE(dev), &acpi_dev);
-	if (ACPI_FAILURE(status))
-		goto err;
+	if (ACPI_FAILURE(status)) {
+		dev_err(dev, "Oops, ACPI handle corrupt in %s()\n", __func__);
+		return -EINVAL;
+	}
 
 	mutex_lock(&acpi_dev->physical_node_lock);
-	list_for_each_safe(node, next, &acpi_dev->physical_node_list) {
-		char physical_node_name[PHYSICAL_NODE_NAME_SIZE];
 
-		entry = list_entry(node, struct acpi_device_physical_node,
-			node);
-		if (entry->dev != dev)
-			continue;
+	list_for_each_entry(entry, &acpi_dev->physical_node_list, node)
+		if (entry->dev == dev) {
+			char physnode_name[PHYSICAL_NODE_NAME_SIZE];
 
-		list_del(node);
+			list_del(&entry->node);
+			acpi_dev->physical_node_count--;
 
-		acpi_dev->physical_node_count--;
+			acpi_physnode_link_name(physnode_name, entry->node_id);
+			sysfs_remove_link(&acpi_dev->dev.kobj, physnode_name);
+			sysfs_remove_link(&dev->kobj, "firmware_node");
+			ACPI_HANDLE_SET(dev, NULL);
+			/* acpi_bind_one() increase refcnt by one. */
+			put_device(dev);
+			kfree(entry);
+			break;
+		}
 
-		if (!entry->node_id)
-			strcpy(physical_node_name, PHYSICAL_NODE_STRING);
-		else
-			sprintf(physical_node_name,
-				"physical_node%d", entry->node_id);
-
-		sysfs_remove_link(&acpi_dev->dev.kobj, physical_node_name);
-		sysfs_remove_link(&dev->kobj, "firmware_node");
-		ACPI_HANDLE_SET(dev, NULL);
-		/* acpi_bind_one increase refcnt by one */
-		put_device(dev);
-		kfree(entry);
-	}
 	mutex_unlock(&acpi_dev->physical_node_lock);
-
 	return 0;
-
-err:
-	dev_err(dev, "Oops, 'acpi_handle' corrupt\n");
-	return -EINVAL;
 }
 EXPORT_SYMBOL_GPL(acpi_unbind_one);
 
diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h
index 5da44e81dd4d..20f423337e1f 100644
--- a/drivers/acpi/internal.h
+++ b/drivers/acpi/internal.h
@@ -23,6 +23,7 @@
 
 #define PREFIX "ACPI: "
 
+acpi_status acpi_os_initialize1(void);
 int init_acpi_device_notify(void);
 int acpi_scan_init(void);
 #ifdef	CONFIG_ACPI_PCI_SLOT
diff --git a/drivers/acpi/numa.c b/drivers/acpi/numa.c
index 33e609f63585..2e82e5d76930 100644
--- a/drivers/acpi/numa.c
+++ b/drivers/acpi/numa.c
@@ -159,7 +159,7 @@ acpi_table_print_srat_entry(struct acpi_subtable_header *header)
  * distance than the others.
  * Do some quick checks here and only use the SLIT if it passes.
  */
-static __init int slit_valid(struct acpi_table_slit *slit)
+static int __init slit_valid(struct acpi_table_slit *slit)
 {
 	int i, j;
 	int d = slit->locality_count;
diff --git a/drivers/acpi/osl.c b/drivers/acpi/osl.c
index 6ab2c3505520..e5f416c7f66e 100644
--- a/drivers/acpi/osl.c
+++ b/drivers/acpi/osl.c
@@ -52,6 +52,7 @@
 #include <acpi/acpi.h>
 #include <acpi/acpi_bus.h>
 #include <acpi/processor.h>
+#include "internal.h"
 
 #define _COMPONENT		ACPI_OS_SERVICES
 ACPI_MODULE_NAME("osl");
@@ -79,6 +80,8 @@ extern char line_buf[80];
 
 static int (*__acpi_os_prepare_sleep)(u8 sleep_state, u32 pm1a_ctrl,
 				      u32 pm1b_ctrl);
+static int (*__acpi_os_prepare_extended_sleep)(u8 sleep_state, u32 val_a,
+				      u32 val_b);
 
 static acpi_osd_handler acpi_irq_handler;
 static void *acpi_irq_context;
@@ -140,7 +143,8 @@ static struct osi_linux {
 	unsigned int	enable:1;
 	unsigned int	dmi:1;
 	unsigned int	cmdline:1;
-} osi_linux = {0, 0, 0};
+	unsigned int	default_disabling:1;
+} osi_linux = {0, 0, 0, 0};
 
 static u32 acpi_osi_handler(acpi_string interface, u32 supported)
 {
@@ -563,10 +567,6 @@ static const char * const table_sigs[] = {
 	ACPI_SIG_WDRT, ACPI_SIG_DSDT, ACPI_SIG_FADT, ACPI_SIG_PSDT,
 	ACPI_SIG_RSDT, ACPI_SIG_XSDT, ACPI_SIG_SSDT, NULL };
 
-/* Non-fatal errors: Affected tables/files are ignored */
-#define INVALID_TABLE(x, path, name)					\
-	{ pr_err("ACPI OVERRIDE: " x " [%s%s]\n", path, name); continue; }
-
 #define ACPI_HEADER_SIZE sizeof(struct acpi_table_header)
 
 /* Must not increase 10 or needs code modification below */
@@ -593,9 +593,11 @@ void __init acpi_initrd_override(void *data, size_t size)
 		data += offset;
 		size -= offset;
 
-		if (file.size < sizeof(struct acpi_table_header))
-			INVALID_TABLE("Table smaller than ACPI header",
-				      cpio_path, file.name);
+		if (file.size < sizeof(struct acpi_table_header)) {
+			pr_err("ACPI OVERRIDE: Table smaller than ACPI header [%s%s]\n",
+				cpio_path, file.name);
+			continue;
+		}
 
 		table = file.data;
 
@@ -603,15 +605,21 @@ void __init acpi_initrd_override(void *data, size_t size)
 			if (!memcmp(table->signature, table_sigs[sig], 4))
 				break;
 
-		if (!table_sigs[sig])
-			INVALID_TABLE("Unknown signature",
-				      cpio_path, file.name);
-		if (file.size != table->length)
-			INVALID_TABLE("File length does not match table length",
-				      cpio_path, file.name);
-		if (acpi_table_checksum(file.data, table->length))
-			INVALID_TABLE("Bad table checksum",
-				      cpio_path, file.name);
+		if (!table_sigs[sig]) {
+			pr_err("ACPI OVERRIDE: Unknown signature [%s%s]\n",
+				cpio_path, file.name);
+			continue;
+		}
+		if (file.size != table->length) {
+			pr_err("ACPI OVERRIDE: File length does not match table length [%s%s]\n",
+				cpio_path, file.name);
+			continue;
+		}
+		if (acpi_table_checksum(file.data, table->length)) {
+			pr_err("ACPI OVERRIDE: Bad table checksum [%s%s]\n",
+				cpio_path, file.name);
+			continue;
+		}
 
 		pr_info("%4.4s ACPI table found in initrd [%s%s][0x%x]\n",
 			table->signature, cpio_path, file.name, table->length);
@@ -1351,8 +1359,8 @@ struct osi_setup_entry {
 	bool enable;
 };
 
-static struct osi_setup_entry __initdata
-		osi_setup_entries[OSI_STRING_ENTRIES_MAX] = {
+static struct osi_setup_entry
+		osi_setup_entries[OSI_STRING_ENTRIES_MAX] __initdata = {
 	{"Module Device", true},
 	{"Processor Device", true},
 	{"3.0 _SCP Extensions", true},
@@ -1376,6 +1384,17 @@ void __init acpi_osi_setup(char *str)
 
 	if (*str == '!') {
 		str++;
+		if (*str == '\0') {
+			osi_linux.default_disabling = 1;
+			return;
+		} else if (*str == '*') {
+			acpi_update_interfaces(ACPI_DISABLE_ALL_STRINGS);
+			for (i = 0; i < OSI_STRING_ENTRIES_MAX; i++) {
+				osi = &osi_setup_entries[i];
+				osi->enable = false;
+			}
+			return;
+		}
 		enable = false;
 	}
 
@@ -1441,6 +1460,13 @@ static void __init acpi_osi_setup_late(void)
 	int i;
 	acpi_status status;
 
+	if (osi_linux.default_disabling) {
+		status = acpi_update_interfaces(ACPI_DISABLE_ALL_VENDOR_STRINGS);
+
+		if (ACPI_SUCCESS(status))
+			printk(KERN_INFO PREFIX "Disabled all _OSI OS vendors\n");
+	}
+
 	for (i = 0; i < OSI_STRING_ENTRIES_MAX; i++) {
 		osi = &osi_setup_entries[i];
 		str = osi->string;
@@ -1779,6 +1805,28 @@ void acpi_os_set_prepare_sleep(int (*func)(u8 sleep_state,
 	__acpi_os_prepare_sleep = func;
 }
 
+acpi_status acpi_os_prepare_extended_sleep(u8 sleep_state, u32 val_a,
+				  u32 val_b)
+{
+	int rc = 0;
+	if (__acpi_os_prepare_extended_sleep)
+		rc = __acpi_os_prepare_extended_sleep(sleep_state,
+					     val_a, val_b);
+	if (rc < 0)
+		return AE_ERROR;
+	else if (rc > 0)
+		return AE_CTRL_SKIP;
+
+	return AE_OK;
+}
+
+void acpi_os_set_prepare_extended_sleep(int (*func)(u8 sleep_state,
+			       u32 val_a, u32 val_b))
+{
+	__acpi_os_prepare_extended_sleep = func;
+}
+
+
 void alloc_acpi_hp_work(acpi_handle handle, u32 type, void *context,
 			void (*func)(struct work_struct *work))
 {
diff --git a/drivers/acpi/pci_root.c b/drivers/acpi/pci_root.c
index 5917839321b8..d3874f425653 100644
--- a/drivers/acpi/pci_root.c
+++ b/drivers/acpi/pci_root.c
@@ -378,6 +378,7 @@ static int acpi_pci_root_add(struct acpi_device *device,
 	struct acpi_pci_root *root;
 	u32 flags, base_flags;
 	acpi_handle handle = device->handle;
+	bool no_aspm = false, clear_aspm = false;
 
 	root = kzalloc(sizeof(struct acpi_pci_root), GFP_KERNEL);
 	if (!root)
@@ -437,27 +438,6 @@ static int acpi_pci_root_add(struct acpi_device *device,
 	flags = base_flags = OSC_PCI_SEGMENT_GROUPS_SUPPORT;
 	acpi_pci_osc_support(root, flags);
 
-	/*
-	 * TBD: Need PCI interface for enumeration/configuration of roots.
-	 */
-
-	/*
-	 * Scan the Root Bridge
-	 * --------------------
-	 * Must do this prior to any attempt to bind the root device, as the
-	 * PCI namespace does not get created until this call is made (and
-	 * thus the root bridge's pci_dev does not exist).
-	 */
-	root->bus = pci_acpi_scan_root(root);
-	if (!root->bus) {
-		dev_err(&device->dev,
-			"Bus %04x:%02x not present in PCI namespace\n",
-			root->segment, (unsigned int)root->secondary.start);
-		result = -ENODEV;
-		goto end;
-	}
-
-	/* Indicate support for various _OSC capabilities. */
 	if (pci_ext_cfg_avail())
 		flags |= OSC_EXT_PCI_CONFIG_SUPPORT;
 	if (pcie_aspm_support_enabled()) {
@@ -471,7 +451,7 @@ static int acpi_pci_root_add(struct acpi_device *device,
 		if (ACPI_FAILURE(status)) {
 			dev_info(&device->dev, "ACPI _OSC support "
 				"notification failed, disabling PCIe ASPM\n");
-			pcie_no_aspm();
+			no_aspm = true;
 			flags = base_flags;
 		}
 	}
@@ -503,7 +483,7 @@ static int acpi_pci_root_add(struct acpi_device *device,
 				 * We have ASPM control, but the FADT indicates
 				 * that it's unsupported. Clear it.
 				 */
-				pcie_clear_aspm(root->bus);
+				clear_aspm = true;
 			}
 		} else {
 			dev_info(&device->dev,
@@ -512,7 +492,14 @@ static int acpi_pci_root_add(struct acpi_device *device,
 				acpi_format_exception(status), flags);
 			dev_info(&device->dev,
 				 "ACPI _OSC control for PCIe not granted, disabling ASPM\n");
-			pcie_no_aspm();
+			/*
+			 * We want to disable ASPM here, but aspm_disabled
+			 * needs to remain in its state from boot so that we
+			 * properly handle PCIe 1.1 devices.  So we set this
+			 * flag here, to defer the action until after the ACPI
+			 * root scan.
+			 */
+			no_aspm = true;
 		}
 	} else {
 		dev_info(&device->dev,
@@ -520,16 +507,40 @@ static int acpi_pci_root_add(struct acpi_device *device,
 			 "(_OSC support mask: 0x%02x)\n", flags);
 	}
 
+	/*
+	 * TBD: Need PCI interface for enumeration/configuration of roots.
+	 */
+
+	/*
+	 * Scan the Root Bridge
+	 * --------------------
+	 * Must do this prior to any attempt to bind the root device, as the
+	 * PCI namespace does not get created until this call is made (and
+	 * thus the root bridge's pci_dev does not exist).
+	 */
+	root->bus = pci_acpi_scan_root(root);
+	if (!root->bus) {
+		dev_err(&device->dev,
+			"Bus %04x:%02x not present in PCI namespace\n",
+			root->segment, (unsigned int)root->secondary.start);
+		result = -ENODEV;
+		goto end;
+	}
+
+	if (clear_aspm) {
+		dev_info(&device->dev, "Disabling ASPM (FADT indicates it is unsupported)\n");
+		pcie_clear_aspm(root->bus);
+	}
+	if (no_aspm)
+		pcie_no_aspm();
+
 	pci_acpi_add_bus_pm_notifier(device, root->bus);
 	if (device->wakeup.flags.run_wake)
 		device_set_run_wake(root->bus->bridge, true);
 
 	if (system_state != SYSTEM_BOOTING) {
 		pcibios_resource_survey_bus(root->bus);
-		pci_assign_unassigned_bus_resources(root->bus);
-
-		/* need to after hot-added ioapic is registered */
-		pci_enable_bridges(root->bus);
+		pci_assign_unassigned_root_bus_resources(root->bus);
 	}
 
 	pci_bus_add_devices(root->bus);
diff --git a/drivers/acpi/pci_slot.c b/drivers/acpi/pci_slot.c
index 033d1179bdb5..d678a180ca2a 100644
--- a/drivers/acpi/pci_slot.c
+++ b/drivers/acpi/pci_slot.c
@@ -159,12 +159,16 @@ register_slot(acpi_handle handle, u32 lvl, void *context, void **rv)
 	return AE_OK;
 }
 
-void acpi_pci_slot_enumerate(struct pci_bus *bus, acpi_handle handle)
+void acpi_pci_slot_enumerate(struct pci_bus *bus)
 {
-	mutex_lock(&slot_list_lock);
-	acpi_walk_namespace(ACPI_TYPE_DEVICE, handle, 1,
-			    register_slot, NULL, bus, NULL);
-	mutex_unlock(&slot_list_lock);
+	acpi_handle handle = ACPI_HANDLE(bus->bridge);
+
+	if (handle) {
+		mutex_lock(&slot_list_lock);
+		acpi_walk_namespace(ACPI_TYPE_DEVICE, handle, 1,
+				    register_slot, NULL, bus, NULL);
+		mutex_unlock(&slot_list_lock);
+	}
 }
 
 void acpi_pci_slot_remove(struct pci_bus *bus)
diff --git a/drivers/acpi/power.c b/drivers/acpi/power.c
index 5c28c894c0fc..c2ad391d8041 100644
--- a/drivers/acpi/power.c
+++ b/drivers/acpi/power.c
@@ -59,16 +59,9 @@ ACPI_MODULE_NAME("power");
 #define ACPI_POWER_RESOURCE_STATE_ON	0x01
 #define ACPI_POWER_RESOURCE_STATE_UNKNOWN 0xFF
 
-struct acpi_power_dependent_device {
-	struct list_head node;
-	struct acpi_device *adev;
-	struct work_struct work;
-};
-
 struct acpi_power_resource {
 	struct acpi_device device;
 	struct list_head list_node;
-	struct list_head dependent;
 	char *name;
 	u32 system_level;
 	u32 order;
@@ -233,32 +226,6 @@ static int acpi_power_get_list_state(struct list_head *list, int *state)
 	return 0;
 }
 
-static void acpi_power_resume_dependent(struct work_struct *work)
-{
-	struct acpi_power_dependent_device *dep;
-	struct acpi_device_physical_node *pn;
-	struct acpi_device *adev;
-	int state;
-
-	dep = container_of(work, struct acpi_power_dependent_device, work);
-	adev = dep->adev;
-	if (acpi_power_get_inferred_state(adev, &state))
-		return;
-
-	if (state > ACPI_STATE_D0)
-		return;
-
-	mutex_lock(&adev->physical_node_lock);
-
-	list_for_each_entry(pn, &adev->physical_node_list, node)
-		pm_request_resume(pn->dev);
-
-	list_for_each_entry(pn, &adev->power_dependent, node)
-		pm_request_resume(pn->dev);
-
-	mutex_unlock(&adev->physical_node_lock);
-}
-
 static int __acpi_power_on(struct acpi_power_resource *resource)
 {
 	acpi_status status = AE_OK;
@@ -283,14 +250,8 @@ static int acpi_power_on_unlocked(struct acpi_power_resource *resource)
 				  resource->name));
 	} else {
 		result = __acpi_power_on(resource);
-		if (result) {
+		if (result)
 			resource->ref_count--;
-		} else {
-			struct acpi_power_dependent_device *dep;
-
-			list_for_each_entry(dep, &resource->dependent, node)
-				schedule_work(&dep->work);
-		}
 	}
 	return result;
 }
@@ -390,52 +351,6 @@ static int acpi_power_on_list(struct list_head *list)
 	return result;
 }
 
-static void acpi_power_add_dependent(struct acpi_power_resource *resource,
-				     struct acpi_device *adev)
-{
-	struct acpi_power_dependent_device *dep;
-
-	mutex_lock(&resource->resource_lock);
-
-	list_for_each_entry(dep, &resource->dependent, node)
-		if (dep->adev == adev)
-			goto out;
-
-	dep = kzalloc(sizeof(*dep), GFP_KERNEL);
-	if (!dep)
-		goto out;
-
-	dep->adev = adev;
-	INIT_WORK(&dep->work, acpi_power_resume_dependent);
-	list_add_tail(&dep->node, &resource->dependent);
-
- out:
-	mutex_unlock(&resource->resource_lock);
-}
-
-static void acpi_power_remove_dependent(struct acpi_power_resource *resource,
-					struct acpi_device *adev)
-{
-	struct acpi_power_dependent_device *dep;
-	struct work_struct *work = NULL;
-
-	mutex_lock(&resource->resource_lock);
-
-	list_for_each_entry(dep, &resource->dependent, node)
-		if (dep->adev == adev) {
-			list_del(&dep->node);
-			work = &dep->work;
-			break;
-		}
-
-	mutex_unlock(&resource->resource_lock);
-
-	if (work) {
-		cancel_work_sync(work);
-		kfree(dep);
-	}
-}
-
 static struct attribute *attrs[] = {
 	NULL,
 };
@@ -524,8 +439,6 @@ static void acpi_power_expose_hide(struct acpi_device *adev,
 
 void acpi_power_add_remove_device(struct acpi_device *adev, bool add)
 {
-	struct acpi_device_power_state *ps;
-	struct acpi_power_resource_entry *entry;
 	int state;
 
 	if (adev->wakeup.flags.valid)
@@ -535,16 +448,6 @@ void acpi_power_add_remove_device(struct acpi_device *adev, bool add)
 	if (!adev->power.flags.power_resources)
 		return;
 
-	ps = &adev->power.states[ACPI_STATE_D0];
-	list_for_each_entry(entry, &ps->resources, node) {
-		struct acpi_power_resource *resource = entry->resource;
-
-		if (add)
-			acpi_power_add_dependent(resource, adev);
-		else
-			acpi_power_remove_dependent(resource, adev);
-	}
-
 	for (state = ACPI_STATE_D0; state <= ACPI_STATE_D3_HOT; state++)
 		acpi_power_expose_hide(adev,
 				       &adev->power.states[state].resources,
@@ -637,9 +540,7 @@ int acpi_device_sleep_wake(struct acpi_device *dev,
 	}
 
 	/* Execute _PSW */
-	arg_list.count = 1;
-	in_arg[0].integer.value = enable;
-	status = acpi_evaluate_object(dev->handle, "_PSW", &arg_list, NULL);
+	status = acpi_execute_simple_method(dev->handle, "_PSW", enable);
 	if (ACPI_FAILURE(status) && (status != AE_NOT_FOUND)) {
 		printk(KERN_ERR PREFIX "_PSW execution failed\n");
 		dev->wakeup.flags.valid = 0;
@@ -786,7 +687,7 @@ int acpi_power_get_inferred_state(struct acpi_device *device, int *state)
 		}
 	}
 
-	*state = ACPI_STATE_D3;
+	*state = ACPI_STATE_D3_COLD;
 	return 0;
 }
 
@@ -884,7 +785,6 @@ int acpi_add_power_resource(acpi_handle handle)
 	acpi_init_device_object(device, handle, ACPI_BUS_TYPE_POWER,
 				ACPI_STA_DEFAULT);
 	mutex_init(&resource->resource_lock);
-	INIT_LIST_HEAD(&resource->dependent);
 	INIT_LIST_HEAD(&resource->list_node);
 	resource->name = device->pnp.bus_id;
 	strcpy(acpi_device_name(device), ACPI_POWER_DEVICE_NAME);
@@ -938,8 +838,10 @@ void acpi_resume_power_resources(void)
 		mutex_lock(&resource->resource_lock);
 
 		result = acpi_power_get_state(resource->device.handle, &state);
-		if (result)
+		if (result) {
+			mutex_unlock(&resource->resource_lock);
 			continue;
+		}
 
 		if (state == ACPI_POWER_RESOURCE_STATE_OFF
 		    && resource->ref_count) {
diff --git a/drivers/acpi/processor_core.c b/drivers/acpi/processor_core.c
index a5e9f4a5b281..cf34d903f4fb 100644
--- a/drivers/acpi/processor_core.c
+++ b/drivers/acpi/processor_core.c
@@ -28,7 +28,7 @@ static int __init set_no_mwait(const struct dmi_system_id *id)
 	return 0;
 }
 
-static struct dmi_system_id __initdata processor_idle_dmi_table[] = {
+static struct dmi_system_id processor_idle_dmi_table[] __initdata = {
 	{
 	set_no_mwait, "Extensa 5220", {
 	DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix Technologies LTD"),
diff --git a/drivers/acpi/processor_driver.c b/drivers/acpi/processor_driver.c
index 870eaf5fa547..e534ba66d5b8 100644
--- a/drivers/acpi/processor_driver.c
+++ b/drivers/acpi/processor_driver.c
@@ -91,21 +91,17 @@ static void acpi_processor_notify(acpi_handle handle, u32 event, void *data)
 		acpi_processor_ppc_has_changed(pr, 1);
 		if (saved == pr->performance_platform_limit)
 			break;
-		acpi_bus_generate_proc_event(device, event,
-					pr->performance_platform_limit);
 		acpi_bus_generate_netlink_event(device->pnp.device_class,
 						  dev_name(&device->dev), event,
 						  pr->performance_platform_limit);
 		break;
 	case ACPI_PROCESSOR_NOTIFY_POWER:
 		acpi_processor_cst_has_changed(pr);
-		acpi_bus_generate_proc_event(device, event, 0);
 		acpi_bus_generate_netlink_event(device->pnp.device_class,
 						  dev_name(&device->dev), event, 0);
 		break;
 	case ACPI_PROCESSOR_NOTIFY_THROTTLING:
 		acpi_processor_tstate_has_changed(pr);
-		acpi_bus_generate_proc_event(device, event, 0);
 		acpi_bus_generate_netlink_event(device->pnp.device_class,
 						  dev_name(&device->dev), event, 0);
 		break;
@@ -179,7 +175,9 @@ static int __acpi_processor_start(struct acpi_device *device)
 	acpi_processor_load_module(pr);
 #endif
 	acpi_processor_get_throttling_info(pr);
-	acpi_processor_get_limit_info(pr);
+
+	if (pr->flags.throttling)
+		pr->flags.limit = 1;
 
 	if (!cpuidle_get_driver() || cpuidle_get_driver() == &acpi_idle_driver)
 		acpi_processor_power_init(pr);
diff --git a/drivers/acpi/processor_perflib.c b/drivers/acpi/processor_perflib.c
index 1e9732d809bf..51d7948611da 100644
--- a/drivers/acpi/processor_perflib.c
+++ b/drivers/acpi/processor_perflib.c
@@ -164,17 +164,12 @@ static void acpi_processor_ppc_ost(acpi_handle handle, int status)
 		{.type = ACPI_TYPE_INTEGER,},
 	};
 	struct acpi_object_list arg_list = {2, params};
-	acpi_handle temp;
 
-	params[0].integer.value = ACPI_PROCESSOR_NOTIFY_PERFORMANCE;
-	params[1].integer.value =  status;
-
-	/* when there is no _OST , skip it */
-	if (ACPI_FAILURE(acpi_get_handle(handle, "_OST", &temp)))
-		return;
-
-	acpi_evaluate_object(handle, "_OST", &arg_list, NULL);
-	return;
+	if (acpi_has_method(handle, "_OST")) {
+		params[0].integer.value = ACPI_PROCESSOR_NOTIFY_PERFORMANCE;
+		params[1].integer.value =  status;
+		acpi_evaluate_object(handle, "_OST", &arg_list, NULL);
+	}
 }
 
 int acpi_processor_ppc_has_changed(struct acpi_processor *pr, int event_flag)
@@ -468,14 +463,11 @@ static int acpi_processor_get_performance_states(struct acpi_processor *pr)
 int acpi_processor_get_performance_info(struct acpi_processor *pr)
 {
 	int result = 0;
-	acpi_status status = AE_OK;
-	acpi_handle handle = NULL;
 
 	if (!pr || !pr->performance || !pr->handle)
 		return -EINVAL;
 
-	status = acpi_get_handle(pr->handle, "_PCT", &handle);
-	if (ACPI_FAILURE(status)) {
+	if (!acpi_has_method(pr->handle, "_PCT")) {
 		ACPI_DEBUG_PRINT((ACPI_DB_INFO,
 				  "ACPI-based processor performance control unavailable\n"));
 		return -ENODEV;
@@ -501,7 +493,7 @@ int acpi_processor_get_performance_info(struct acpi_processor *pr)
 	 */
  update_bios:
 #ifdef CONFIG_X86
-	if (ACPI_SUCCESS(acpi_get_handle(pr->handle, "_PPC", &handle))){
+	if (acpi_has_method(pr->handle, "_PPC")) {
 		if(boot_cpu_has(X86_FEATURE_EST))
 			printk(KERN_WARNING FW_BUG "BIOS needs update for CPU "
 			       "frequency support\n");
diff --git a/drivers/acpi/processor_thermal.c b/drivers/acpi/processor_thermal.c
index e8e652710e65..d1d2e7fb5b30 100644
--- a/drivers/acpi/processor_thermal.c
+++ b/drivers/acpi/processor_thermal.c
@@ -186,18 +186,6 @@ static int cpufreq_set_cur_state(unsigned int cpu, int state)
 
 #endif
 
-int acpi_processor_get_limit_info(struct acpi_processor *pr)
-{
-
-	if (!pr)
-		return -EINVAL;
-
-	if (pr->flags.throttling)
-		pr->flags.limit = 1;
-
-	return 0;
-}
-
 /* thermal coolign device callbacks */
 static int acpi_processor_max_state(struct acpi_processor *pr)
 {
diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c
index 3322b47ab7ca..b7201fc6f1e1 100644
--- a/drivers/acpi/resource.c
+++ b/drivers/acpi/resource.c
@@ -505,14 +505,12 @@ int acpi_dev_get_resources(struct acpi_device *adev, struct list_head *list,
 			   void *preproc_data)
 {
 	struct res_proc_context c;
-	acpi_handle not_used;
 	acpi_status status;
 
 	if (!adev || !adev->handle || !list_empty(list))
 		return -EINVAL;
 
-	status = acpi_get_handle(adev->handle, METHOD_NAME__CRS, &not_used);
-	if (ACPI_FAILURE(status))
+	if (!acpi_has_method(adev->handle, METHOD_NAME__CRS))
 		return 0;
 
 	c.list = list;
diff --git a/drivers/acpi/sbs.c b/drivers/acpi/sbs.c
index b6241eeb1132..aef7e1cd1e5d 100644
--- a/drivers/acpi/sbs.c
+++ b/drivers/acpi/sbs.c
@@ -873,14 +873,9 @@ static void acpi_sbs_callback(void *context)
 	u8 saved_charger_state = sbs->charger_present;
 	u8 saved_battery_state;
 	acpi_ac_get_present(sbs);
-	if (sbs->charger_present != saved_charger_state) {
-#ifdef CONFIG_ACPI_PROC_EVENT
-		acpi_bus_generate_proc_event4(ACPI_AC_CLASS, ACPI_AC_DIR_NAME,
-					      ACPI_SBS_NOTIFY_STATUS,
-					      sbs->charger_present);
-#endif
+	if (sbs->charger_present != saved_charger_state)
 		kobject_uevent(&sbs->charger.dev->kobj, KOBJ_CHANGE);
-	}
+
 	if (sbs->manager_present) {
 		for (id = 0; id < MAX_SBS_BAT; ++id) {
 			if (!(sbs->batteries_supported & (1 << id)))
@@ -890,12 +885,6 @@ static void acpi_sbs_callback(void *context)
 			acpi_battery_read(bat);
 			if (saved_battery_state == bat->present)
 				continue;
-#ifdef CONFIG_ACPI_PROC_EVENT
-			acpi_bus_generate_proc_event4(ACPI_BATTERY_CLASS,
-						      bat->name,
-						      ACPI_SBS_NOTIFY_STATUS,
-						      bat->present);
-#endif
 			kobject_uevent(&bat->bat.dev->kobj, KOBJ_CHANGE);
 		}
 	}
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index 8a46c924effd..fee8a297c7d9 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -193,9 +193,6 @@ static acpi_status acpi_bus_online_companions(acpi_handle handle, u32 lvl,
 static int acpi_scan_hot_remove(struct acpi_device *device)
 {
 	acpi_handle handle = device->handle;
-	acpi_handle not_used;
-	struct acpi_object_list arg_list;
-	union acpi_object arg;
 	struct device *errdev;
 	acpi_status status;
 	unsigned long long sta;
@@ -207,8 +204,6 @@ static int acpi_scan_hot_remove(struct acpi_device *device)
 		return -EINVAL;
 	}
 
-	lock_device_hotplug();
-
 	/*
 	 * Carry out two passes here and ignore errors in the first pass,
 	 * because if the devices in question are memory blocks and
@@ -239,9 +234,6 @@ static int acpi_scan_hot_remove(struct acpi_device *device)
 					    ACPI_UINT32_MAX,
 					    acpi_bus_online_companions, NULL,
 					    NULL, NULL);
-
-			unlock_device_hotplug();
-
 			put_device(&device->dev);
 			return -EBUSY;
 		}
@@ -252,38 +244,19 @@ static int acpi_scan_hot_remove(struct acpi_device *device)
 
 	acpi_bus_trim(device);
 
-	unlock_device_hotplug();
-
 	/* Device node has been unregistered. */
 	put_device(&device->dev);
 	device = NULL;
 
-	if (ACPI_SUCCESS(acpi_get_handle(handle, "_LCK", &not_used))) {
-		arg_list.count = 1;
-		arg_list.pointer = &arg;
-		arg.type = ACPI_TYPE_INTEGER;
-		arg.integer.value = 0;
-		acpi_evaluate_object(handle, "_LCK", &arg_list, NULL);
-	}
-
-	arg_list.count = 1;
-	arg_list.pointer = &arg;
-	arg.type = ACPI_TYPE_INTEGER;
-	arg.integer.value = 1;
-
+	acpi_evaluate_lck(handle, 0);
 	/*
 	 * TBD: _EJD support.
 	 */
-	status = acpi_evaluate_object(handle, "_EJ0", &arg_list, NULL);
-	if (ACPI_FAILURE(status)) {
-		if (status == AE_NOT_FOUND) {
-			return -ENODEV;
-		} else {
-			acpi_handle_warn(handle, "Eject failed (0x%x)\n",
-								status);
-			return -EIO;
-		}
-	}
+	status = acpi_evaluate_ej0(handle);
+	if (status == AE_NOT_FOUND)
+		return -ENODEV;
+	else if (ACPI_FAILURE(status))
+		return -EIO;
 
 	/*
 	 * Verify if eject was indeed successful.  If not, log an error
@@ -307,7 +280,9 @@ static void acpi_bus_device_eject(void *context)
 	struct acpi_device *device = NULL;
 	struct acpi_scan_handler *handler;
 	u32 ost_code = ACPI_OST_SC_NON_SPECIFIC_FAILURE;
+	int error;
 
+	lock_device_hotplug();
 	mutex_lock(&acpi_scan_lock);
 
 	acpi_bus_get_device(handle, &device);
@@ -321,20 +296,17 @@ static void acpi_bus_device_eject(void *context)
 	}
 	acpi_evaluate_hotplug_ost(handle, ACPI_NOTIFY_EJECT_REQUEST,
 				  ACPI_OST_SC_EJECT_IN_PROGRESS, NULL);
-	if (handler->hotplug.mode == AHM_CONTAINER) {
-		device->flags.eject_pending = true;
+	if (handler->hotplug.mode == AHM_CONTAINER)
 		kobject_uevent(&device->dev.kobj, KOBJ_OFFLINE);
-	} else {
-		int error;
 
-		get_device(&device->dev);
-		error = acpi_scan_hot_remove(device);
-		if (error)
-			goto err_out;
-	}
+	get_device(&device->dev);
+	error = acpi_scan_hot_remove(device);
+	if (error)
+		goto err_out;
 
  out:
 	mutex_unlock(&acpi_scan_lock);
+	unlock_device_hotplug();
 	return;
 
  err_out:
@@ -349,8 +321,8 @@ static void acpi_scan_bus_device_check(acpi_handle handle, u32 ost_source)
 	u32 ost_code = ACPI_OST_SC_NON_SPECIFIC_FAILURE;
 	int error;
 
-	mutex_lock(&acpi_scan_lock);
 	lock_device_hotplug();
+	mutex_lock(&acpi_scan_lock);
 
 	if (ost_source != ACPI_NOTIFY_BUS_CHECK) {
 		acpi_bus_get_device(handle, &device);
@@ -376,9 +348,9 @@ static void acpi_scan_bus_device_check(acpi_handle handle, u32 ost_source)
 		kobject_uevent(&device->dev.kobj, KOBJ_ONLINE);
 
  out:
-	unlock_device_hotplug();
 	acpi_evaluate_hotplug_ost(handle, ost_source, ost_code, NULL);
 	mutex_unlock(&acpi_scan_lock);
+	unlock_device_hotplug();
 }
 
 static void acpi_scan_bus_check(void *context)
@@ -469,6 +441,7 @@ void acpi_bus_hot_remove_device(void *context)
 	acpi_handle handle = device->handle;
 	int error;
 
+	lock_device_hotplug();
 	mutex_lock(&acpi_scan_lock);
 
 	error = acpi_scan_hot_remove(device);
@@ -478,6 +451,7 @@ void acpi_bus_hot_remove_device(void *context)
 					  NULL);
 
 	mutex_unlock(&acpi_scan_lock);
+	unlock_device_hotplug();
 	kfree(context);
 }
 EXPORT_SYMBOL(acpi_bus_hot_remove_device);
@@ -516,7 +490,6 @@ acpi_eject_store(struct device *d, struct device_attribute *attr,
 	struct acpi_eject_event *ej_event;
 	acpi_object_type not_used;
 	acpi_status status;
-	u32 ost_source;
 	int ret;
 
 	if (!count || buf[0] != '1')
@@ -530,43 +503,28 @@ acpi_eject_store(struct device *d, struct device_attribute *attr,
 	if (ACPI_FAILURE(status) || !acpi_device->flags.ejectable)
 		return -ENODEV;
 
-	mutex_lock(&acpi_scan_lock);
-
-	if (acpi_device->flags.eject_pending) {
-		/* ACPI eject notification event. */
-		ost_source = ACPI_NOTIFY_EJECT_REQUEST;
-		acpi_device->flags.eject_pending = 0;
-	} else {
-		/* Eject initiated by user space. */
-		ost_source = ACPI_OST_EC_OSPM_EJECT;
-	}
 	ej_event = kmalloc(sizeof(*ej_event), GFP_KERNEL);
 	if (!ej_event) {
 		ret = -ENOMEM;
 		goto err_out;
 	}
-	acpi_evaluate_hotplug_ost(acpi_device->handle, ost_source,
+	acpi_evaluate_hotplug_ost(acpi_device->handle, ACPI_OST_EC_OSPM_EJECT,
 				  ACPI_OST_SC_EJECT_IN_PROGRESS, NULL);
 	ej_event->device = acpi_device;
-	ej_event->event = ost_source;
+	ej_event->event = ACPI_OST_EC_OSPM_EJECT;
 	get_device(&acpi_device->dev);
 	status = acpi_os_hotplug_execute(acpi_bus_hot_remove_device, ej_event);
-	if (ACPI_FAILURE(status)) {
-		put_device(&acpi_device->dev);
-		kfree(ej_event);
-		ret = status == AE_NO_MEMORY ? -ENOMEM : -EAGAIN;
-		goto err_out;
-	}
-	ret = count;
+	if (ACPI_SUCCESS(status))
+		return count;
 
- out:
-	mutex_unlock(&acpi_scan_lock);
-	return ret;
+	put_device(&acpi_device->dev);
+	kfree(ej_event);
+	ret = status == AE_NO_MEMORY ? -ENOMEM : -EAGAIN;
 
  err_out:
-	acpi_evaluate_hotplug_ost(acpi_device->handle, ost_source,
+	acpi_evaluate_hotplug_ost(acpi_device->handle, ACPI_OST_EC_OSPM_EJECT,
 				  ACPI_OST_SC_NON_SPECIFIC_FAILURE, NULL);
-	goto out;
+	return ret;
 }
 
 static DEVICE_ATTR(eject, 0200, NULL, acpi_eject_store);
@@ -654,7 +612,6 @@ static int acpi_device_setup_files(struct acpi_device *dev)
 {
 	struct acpi_buffer buffer = {ACPI_ALLOCATE_BUFFER, NULL};
 	acpi_status status;
-	acpi_handle temp;
 	unsigned long long sun;
 	int result = 0;
 
@@ -680,8 +637,7 @@ static int acpi_device_setup_files(struct acpi_device *dev)
 	/*
 	 * If device has _STR, 'description' file is created
 	 */
-	status = acpi_get_handle(dev->handle, "_STR", &temp);
-	if (ACPI_SUCCESS(status)) {
+	if (acpi_has_method(dev->handle, "_STR")) {
 		status = acpi_evaluate_object(dev->handle, "_STR",
 					NULL, &buffer);
 		if (ACPI_FAILURE(status))
@@ -711,8 +667,7 @@ static int acpi_device_setup_files(struct acpi_device *dev)
          * If device has _EJ0, 'eject' file is created that is used to trigger
          * hot-removal function from userland.
          */
-	status = acpi_get_handle(dev->handle, "_EJ0", &temp);
-	if (ACPI_SUCCESS(status)) {
+	if (acpi_has_method(dev->handle, "_EJ0")) {
 		result = device_create_file(&dev->dev, &dev_attr_eject);
 		if (result)
 			return result;
@@ -734,9 +689,6 @@ end:
 
 static void acpi_device_remove_files(struct acpi_device *dev)
 {
-	acpi_status status;
-	acpi_handle temp;
-
 	if (dev->flags.power_manageable) {
 		device_remove_file(&dev->dev, &dev_attr_power_state);
 		if (dev->power.flags.power_resources)
@@ -747,20 +699,17 @@ static void acpi_device_remove_files(struct acpi_device *dev)
 	/*
 	 * If device has _STR, remove 'description' file
 	 */
-	status = acpi_get_handle(dev->handle, "_STR", &temp);
-	if (ACPI_SUCCESS(status)) {
+	if (acpi_has_method(dev->handle, "_STR")) {
 		kfree(dev->pnp.str_obj);
 		device_remove_file(&dev->dev, &dev_attr_description);
 	}
 	/*
 	 * If device has _EJ0, remove 'eject' file.
 	 */
-	status = acpi_get_handle(dev->handle, "_EJ0", &temp);
-	if (ACPI_SUCCESS(status))
+	if (acpi_has_method(dev->handle, "_EJ0"))
 		device_remove_file(&dev->dev, &dev_attr_eject);
 
-	status = acpi_get_handle(dev->handle, "_SUN", &temp);
-	if (ACPI_SUCCESS(status))
+	if (acpi_has_method(dev->handle, "_SUN"))
 		device_remove_file(&dev->dev, &dev_attr_sun);
 
 	if (dev->pnp.unique_id)
@@ -999,6 +948,28 @@ struct bus_type acpi_bus_type = {
 	.uevent		= acpi_device_uevent,
 };
 
+static void acpi_bus_data_handler(acpi_handle handle, void *context)
+{
+	/* Intentionally empty. */
+}
+
+int acpi_bus_get_device(acpi_handle handle, struct acpi_device **device)
+{
+	acpi_status status;
+
+	if (!device)
+		return -EINVAL;
+
+	status = acpi_get_data(handle, acpi_bus_data_handler, (void **)device);
+	if (ACPI_FAILURE(status) || !*device) {
+		ACPI_DEBUG_PRINT((ACPI_DB_INFO, "No context for object [%p]\n",
+				  handle));
+		return -ENODEV;
+	}
+	return 0;
+}
+EXPORT_SYMBOL(acpi_bus_get_device);
+
 int acpi_device_add(struct acpi_device *device,
 		    void (*release)(struct device *))
 {
@@ -1028,7 +999,6 @@ int acpi_device_add(struct acpi_device *device,
 	INIT_LIST_HEAD(&device->wakeup_list);
 	INIT_LIST_HEAD(&device->physical_node_list);
 	mutex_init(&device->physical_node_lock);
-	INIT_LIST_HEAD(&device->power_dependent);
 
 	new_bus_id = kzalloc(sizeof(struct acpi_device_bus_id), GFP_KERNEL);
 	if (!new_bus_id) {
@@ -1150,7 +1120,7 @@ int acpi_bus_register_driver(struct acpi_driver *driver)
 EXPORT_SYMBOL(acpi_bus_register_driver);
 
 /**
- * acpi_bus_unregister_driver - unregisters a driver with the APIC bus
+ * acpi_bus_unregister_driver - unregisters a driver with the ACPI bus
  * @driver: driver to unregister
  *
  * Unregisters a driver with the ACPI bus.  Searches the namespace for all
@@ -1210,14 +1180,6 @@ acpi_bus_get_ejd(acpi_handle handle, acpi_handle *ejd)
 }
 EXPORT_SYMBOL_GPL(acpi_bus_get_ejd);
 
-void acpi_bus_data_handler(acpi_handle handle, void *context)
-{
-
-	/* TBD */
-
-	return;
-}
-
 static int acpi_bus_extract_wakeup_device_power_package(acpi_handle handle,
 					struct acpi_device_wakeup *wakeup)
 {
@@ -1336,13 +1298,10 @@ static void acpi_bus_set_run_wake_flags(struct acpi_device *device)
 
 static void acpi_bus_get_wakeup_device_flags(struct acpi_device *device)
 {
-	acpi_handle temp;
-	acpi_status status = 0;
 	int err;
 
 	/* Presence of _PRW indicates wake capable */
-	status = acpi_get_handle(device->handle, "_PRW", &temp);
-	if (ACPI_FAILURE(status))
+	if (!acpi_has_method(device->handle, "_PRW"))
 		return;
 
 	err = acpi_bus_extract_wakeup_device_power_package(device->handle,
@@ -1372,7 +1331,6 @@ static void acpi_bus_init_power_state(struct acpi_device *device, int state)
 	struct acpi_device_power_state *ps = &device->power.states[state];
 	char pathname[5] = { '_', 'P', 'R', '0' + state, '\0' };
 	struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
-	acpi_handle handle;
 	acpi_status status;
 
 	INIT_LIST_HEAD(&ps->resources);
@@ -1395,8 +1353,7 @@ static void acpi_bus_init_power_state(struct acpi_device *device, int state)
 
 	/* Evaluate "_PSx" to see if we can do explicit sets */
 	pathname[2] = 'S';
-	status = acpi_get_handle(device->handle, pathname, &handle);
-	if (ACPI_SUCCESS(status))
+	if (acpi_has_method(device->handle, pathname))
 		ps->flags.explicit_set = 1;
 
 	/*
@@ -1415,28 +1372,21 @@ static void acpi_bus_init_power_state(struct acpi_device *device, int state)
 
 static void acpi_bus_get_power_flags(struct acpi_device *device)
 {
-	acpi_status status;
-	acpi_handle handle;
 	u32 i;
 
 	/* Presence of _PS0|_PR0 indicates 'power manageable' */
-	status = acpi_get_handle(device->handle, "_PS0", &handle);
-	if (ACPI_FAILURE(status)) {
-		status = acpi_get_handle(device->handle, "_PR0", &handle);
-		if (ACPI_FAILURE(status))
-			return;
-	}
+	if (!acpi_has_method(device->handle, "_PS0") &&
+	    !acpi_has_method(device->handle, "_PR0"))
+		return;
 
 	device->flags.power_manageable = 1;
 
 	/*
 	 * Power Management Flags
 	 */
-	status = acpi_get_handle(device->handle, "_PSC", &handle);
-	if (ACPI_SUCCESS(status))
+	if (acpi_has_method(device->handle, "_PSC"))
 		device->power.flags.explicit_get = 1;
-	status = acpi_get_handle(device->handle, "_IRC", &handle);
-	if (ACPI_SUCCESS(status))
+	if (acpi_has_method(device->handle, "_IRC"))
 		device->power.flags.inrush_current = 1;
 
 	/*
@@ -1450,8 +1400,8 @@ static void acpi_bus_get_power_flags(struct acpi_device *device)
 	/* Set defaults for D0 and D3 states (always valid) */
 	device->power.states[ACPI_STATE_D0].flags.valid = 1;
 	device->power.states[ACPI_STATE_D0].power = 100;
-	device->power.states[ACPI_STATE_D3].flags.valid = 1;
-	device->power.states[ACPI_STATE_D3].power = 0;
+	device->power.states[ACPI_STATE_D3_COLD].flags.valid = 1;
+	device->power.states[ACPI_STATE_D3_COLD].power = 0;
 
 	/* Set D3cold's explicit_set flag if _PS3 exists. */
 	if (device->power.states[ACPI_STATE_D3_HOT].flags.explicit_set)
@@ -1470,28 +1420,18 @@ static void acpi_bus_get_power_flags(struct acpi_device *device)
 
 static void acpi_bus_get_flags(struct acpi_device *device)
 {
-	acpi_status status = AE_OK;
-	acpi_handle temp = NULL;
-
 	/* Presence of _STA indicates 'dynamic_status' */
-	status = acpi_get_handle(device->handle, "_STA", &temp);
-	if (ACPI_SUCCESS(status))
+	if (acpi_has_method(device->handle, "_STA"))
 		device->flags.dynamic_status = 1;
 
 	/* Presence of _RMV indicates 'removable' */
-	status = acpi_get_handle(device->handle, "_RMV", &temp);
-	if (ACPI_SUCCESS(status))
+	if (acpi_has_method(device->handle, "_RMV"))
 		device->flags.removable = 1;
 
 	/* Presence of _EJD|_EJ0 indicates 'ejectable' */
-	status = acpi_get_handle(device->handle, "_EJD", &temp);
-	if (ACPI_SUCCESS(status))
+	if (acpi_has_method(device->handle, "_EJD") ||
+	    acpi_has_method(device->handle, "_EJ0"))
 		device->flags.ejectable = 1;
-	else {
-		status = acpi_get_handle(device->handle, "_EJ0", &temp);
-		if (ACPI_SUCCESS(status))
-			device->flags.ejectable = 1;
-	}
 }
 
 static void acpi_device_get_busid(struct acpi_device *device)
@@ -1533,46 +1473,45 @@ static void acpi_device_get_busid(struct acpi_device *device)
 }
 
 /*
+ * acpi_ata_match - see if an acpi object is an ATA device
+ *
+ * If an acpi object has one of the ACPI ATA methods defined,
+ * then we can safely call it an ATA device.
+ */
+bool acpi_ata_match(acpi_handle handle)
+{
+	return acpi_has_method(handle, "_GTF") ||
+	       acpi_has_method(handle, "_GTM") ||
+	       acpi_has_method(handle, "_STM") ||
+	       acpi_has_method(handle, "_SDD");
+}
+
+/*
  * acpi_bay_match - see if an acpi object is an ejectable driver bay
  *
  * If an acpi object is ejectable and has one of the ACPI ATA methods defined,
  * then we can safely call it an ejectable drive bay
  */
-static int acpi_bay_match(acpi_handle handle)
+bool acpi_bay_match(acpi_handle handle)
 {
-	acpi_status status;
-	acpi_handle tmp;
 	acpi_handle phandle;
 
-	status = acpi_get_handle(handle, "_EJ0", &tmp);
-	if (ACPI_FAILURE(status))
-		return -ENODEV;
-
-	if ((ACPI_SUCCESS(acpi_get_handle(handle, "_GTF", &tmp))) ||
-		(ACPI_SUCCESS(acpi_get_handle(handle, "_GTM", &tmp))) ||
-		(ACPI_SUCCESS(acpi_get_handle(handle, "_STM", &tmp))) ||
-		(ACPI_SUCCESS(acpi_get_handle(handle, "_SDD", &tmp))))
-		return 0;
+	if (!acpi_has_method(handle, "_EJ0"))
+		return false;
+	if (acpi_ata_match(handle))
+		return true;
+	if (ACPI_FAILURE(acpi_get_parent(handle, &phandle)))
+		return false;
 
-	if (acpi_get_parent(handle, &phandle))
-		return -ENODEV;
-
-        if ((ACPI_SUCCESS(acpi_get_handle(phandle, "_GTF", &tmp))) ||
-                (ACPI_SUCCESS(acpi_get_handle(phandle, "_GTM", &tmp))) ||
-                (ACPI_SUCCESS(acpi_get_handle(phandle, "_STM", &tmp))) ||
-                (ACPI_SUCCESS(acpi_get_handle(phandle, "_SDD", &tmp))))
-                return 0;
-
-	return -ENODEV;
+	return acpi_ata_match(phandle);
 }
 
 /*
  * acpi_dock_match - see if an acpi object has a _DCK method
  */
-static int acpi_dock_match(acpi_handle handle)
+bool acpi_dock_match(acpi_handle handle)
 {
-	acpi_handle tmp;
-	return acpi_get_handle(handle, "_DCK", &tmp);
+	return acpi_has_method(handle, "_DCK");
 }
 
 const char *acpi_device_hid(struct acpi_device *device)
@@ -1610,34 +1549,26 @@ static void acpi_add_id(struct acpi_device_pnp *pnp, const char *dev_id)
  * lacks the SMBUS01 HID and the methods do not have the necessary "_"
  * prefix.  Work around this.
  */
-static int acpi_ibm_smbus_match(acpi_handle handle)
+static bool acpi_ibm_smbus_match(acpi_handle handle)
 {
-	acpi_handle h_dummy;
-	struct acpi_buffer path = {ACPI_ALLOCATE_BUFFER, NULL};
-	int result;
+	char node_name[ACPI_PATH_SEGMENT_LENGTH];
+	struct acpi_buffer path = { sizeof(node_name), node_name };
 
 	if (!dmi_name_in_vendors("IBM"))
-		return -ENODEV;
+		return false;
 
 	/* Look for SMBS object */
-	result = acpi_get_name(handle, ACPI_SINGLE_NAME, &path);
-	if (result)
-		return result;
-
-	if (strcmp("SMBS", path.pointer)) {
-		result = -ENODEV;
-		goto out;
-	}
+	if (ACPI_FAILURE(acpi_get_name(handle, ACPI_SINGLE_NAME, &path)) ||
+	    strcmp("SMBS", path.pointer))
+		return false;
 
 	/* Does it have the necessary (but misnamed) methods? */
-	result = -ENODEV;
-	if (ACPI_SUCCESS(acpi_get_handle(handle, "SBI", &h_dummy)) &&
-	    ACPI_SUCCESS(acpi_get_handle(handle, "SBR", &h_dummy)) &&
-	    ACPI_SUCCESS(acpi_get_handle(handle, "SBW", &h_dummy)))
-		result = 0;
-out:
-	kfree(path.pointer);
-	return result;
+	if (acpi_has_method(handle, "SBI") &&
+	    acpi_has_method(handle, "SBR") &&
+	    acpi_has_method(handle, "SBW"))
+		return true;
+
+	return false;
 }
 
 static void acpi_set_pnp_ids(acpi_handle handle, struct acpi_device_pnp *pnp,
@@ -1685,11 +1616,11 @@ static void acpi_set_pnp_ids(acpi_handle handle, struct acpi_device_pnp *pnp,
 		 */
 		if (acpi_is_video_device(handle))
 			acpi_add_id(pnp, ACPI_VIDEO_HID);
-		else if (ACPI_SUCCESS(acpi_bay_match(handle)))
+		else if (acpi_bay_match(handle))
 			acpi_add_id(pnp, ACPI_BAY_HID);
-		else if (ACPI_SUCCESS(acpi_dock_match(handle)))
+		else if (acpi_dock_match(handle))
 			acpi_add_id(pnp, ACPI_DOCK_HID);
-		else if (!acpi_ibm_smbus_match(handle))
+		else if (acpi_ibm_smbus_match(handle))
 			acpi_add_id(pnp, ACPI_SMBUS_IBM_HID);
 		else if (list_empty(&pnp->ids) && handle == ACPI_ROOT_OBJECT) {
 			acpi_add_id(pnp, ACPI_BUS_HID); /* \_SB, LNXSYBUS */
@@ -1900,7 +1831,6 @@ static acpi_status acpi_bus_check_add(acpi_handle handle, u32 lvl_not_used,
 	struct acpi_device *device = NULL;
 	int type;
 	unsigned long long sta;
-	acpi_status status;
 	int result;
 
 	acpi_bus_get_device(handle, &device);
@@ -1921,10 +1851,8 @@ static acpi_status acpi_bus_check_add(acpi_handle handle, u32 lvl_not_used,
 	if (!(sta & ACPI_STA_DEVICE_PRESENT) &&
 	    !(sta & ACPI_STA_DEVICE_FUNCTIONING)) {
 		struct acpi_device_wakeup wakeup;
-		acpi_handle temp;
 
-		status = acpi_get_handle(handle, "_PRW", &temp);
-		if (ACPI_SUCCESS(status)) {
+		if (acpi_has_method(handle, "_PRW")) {
 			acpi_bus_extract_wakeup_device_power_package(handle,
 								     &wakeup);
 			acpi_power_resources_list_free(&wakeup.resources);
diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c
index 187ab61889e6..14df30580e15 100644
--- a/drivers/acpi/sleep.c
+++ b/drivers/acpi/sleep.c
@@ -31,12 +31,9 @@ static u8 sleep_states[ACPI_S_STATE_COUNT];
 
 static void acpi_sleep_tts_switch(u32 acpi_state)
 {
-	union acpi_object in_arg = { ACPI_TYPE_INTEGER };
-	struct acpi_object_list arg_list = { 1, &in_arg };
-	acpi_status status = AE_OK;
+	acpi_status status;
 
-	in_arg.integer.value = acpi_state;
-	status = acpi_evaluate_object(NULL, "\\_TTS", &arg_list, NULL);
+	status = acpi_execute_simple_method(NULL, "\\_TTS", acpi_state);
 	if (ACPI_FAILURE(status) && status != AE_NOT_FOUND) {
 		/*
 		 * OS can't evaluate the _TTS object correctly. Some warning
@@ -141,7 +138,7 @@ static int __init init_nvs_nosave(const struct dmi_system_id *d)
 	return 0;
 }
 
-static struct dmi_system_id __initdata acpisleep_dmi_table[] = {
+static struct dmi_system_id acpisleep_dmi_table[] __initdata = {
 	{
 	.callback = init_old_suspend_ordering,
 	.ident = "Abit KN9 (nForce4 variant)",
@@ -423,10 +420,21 @@ static void acpi_pm_finish(void)
 }
 
 /**
- *	acpi_pm_end - Finish up suspend sequence.
+ * acpi_pm_start - Start system PM transition.
+ */
+static void acpi_pm_start(u32 acpi_state)
+{
+	acpi_target_sleep_state = acpi_state;
+	acpi_sleep_tts_switch(acpi_target_sleep_state);
+	acpi_scan_lock_acquire();
+}
+
+/**
+ * acpi_pm_end - Finish up system PM transition.
  */
 static void acpi_pm_end(void)
 {
+	acpi_scan_lock_release();
 	/*
 	 * This is necessary in case acpi_pm_finish() is not called during a
 	 * failing transition to a sleep state.
@@ -454,21 +462,19 @@ static u32 acpi_suspend_states[] = {
 static int acpi_suspend_begin(suspend_state_t pm_state)
 {
 	u32 acpi_state = acpi_suspend_states[pm_state];
-	int error = 0;
+	int error;
 
 	error = (nvs_nosave || nvs_nosave_s3) ? 0 : suspend_nvs_alloc();
 	if (error)
 		return error;
 
-	if (sleep_states[acpi_state]) {
-		acpi_target_sleep_state = acpi_state;
-		acpi_sleep_tts_switch(acpi_target_sleep_state);
-	} else {
-		printk(KERN_ERR "ACPI does not support this state: %d\n",
-			pm_state);
-		error = -ENOSYS;
+	if (!sleep_states[acpi_state]) {
+		pr_err("ACPI does not support sleep state S%u\n", acpi_state);
+		return -ENOSYS;
 	}
-	return error;
+
+	acpi_pm_start(acpi_state);
+	return 0;
 }
 
 /**
@@ -634,10 +640,8 @@ static int acpi_hibernation_begin(void)
 	int error;
 
 	error = nvs_nosave ? 0 : suspend_nvs_alloc();
-	if (!error) {
-		acpi_target_sleep_state = ACPI_STATE_S4;
-		acpi_sleep_tts_switch(acpi_target_sleep_state);
-	}
+	if (!error)
+		acpi_pm_start(ACPI_STATE_S4);
 
 	return error;
 }
@@ -716,8 +720,10 @@ static int acpi_hibernation_begin_old(void)
 	if (!error) {
 		if (!nvs_nosave)
 			error = suspend_nvs_alloc();
-		if (!error)
+		if (!error) {
 			acpi_target_sleep_state = ACPI_STATE_S4;
+			acpi_scan_lock_acquire();
+		}
 	}
 	return error;
 }
diff --git a/drivers/acpi/thermal.c b/drivers/acpi/thermal.c
index a33821ca3895..6a0329340b42 100644
--- a/drivers/acpi/thermal.c
+++ b/drivers/acpi/thermal.c
@@ -50,11 +50,6 @@
 
 #define ACPI_THERMAL_CLASS		"thermal_zone"
 #define ACPI_THERMAL_DEVICE_NAME	"Thermal Zone"
-#define ACPI_THERMAL_FILE_STATE		"state"
-#define ACPI_THERMAL_FILE_TEMPERATURE	"temperature"
-#define ACPI_THERMAL_FILE_TRIP_POINTS	"trip_points"
-#define ACPI_THERMAL_FILE_COOLING_MODE	"cooling_mode"
-#define ACPI_THERMAL_FILE_POLLING_FREQ	"polling_frequency"
 #define ACPI_THERMAL_NOTIFY_TEMPERATURE	0x80
 #define ACPI_THERMAL_NOTIFY_THRESHOLDS	0x81
 #define ACPI_THERMAL_NOTIFY_DEVICES	0x82
@@ -190,7 +185,6 @@ struct acpi_thermal {
 	struct thermal_zone_device *thermal_zone;
 	int tz_enabled;
 	int kelvin_offset;
-	struct mutex lock;
 };
 
 /* --------------------------------------------------------------------------
@@ -239,26 +233,16 @@ static int acpi_thermal_get_polling_frequency(struct acpi_thermal *tz)
 
 static int acpi_thermal_set_cooling_mode(struct acpi_thermal *tz, int mode)
 {
-	acpi_status status = AE_OK;
-	union acpi_object arg0 = { ACPI_TYPE_INTEGER };
-	struct acpi_object_list arg_list = { 1, &arg0 };
-	acpi_handle handle = NULL;
-
-
 	if (!tz)
 		return -EINVAL;
 
-	status = acpi_get_handle(tz->device->handle, "_SCP", &handle);
-	if (ACPI_FAILURE(status)) {
+	if (!acpi_has_method(tz->device->handle, "_SCP")) {
 		ACPI_DEBUG_PRINT((ACPI_DB_INFO, "_SCP not present\n"));
 		return -ENODEV;
-	}
-
-	arg0.integer.value = mode;
-
-	status = acpi_evaluate_object(handle, NULL, &arg_list, NULL);
-	if (ACPI_FAILURE(status))
+	} else if (ACPI_FAILURE(acpi_execute_simple_method(tz->device->handle,
+							   "_SCP", mode))) {
 		return -ENODEV;
+	}
 
 	return 0;
 }
@@ -491,14 +475,14 @@ static int acpi_thermal_trips_update(struct acpi_thermal *tz, int flag)
 			break;
 	}
 
-	if (flag & ACPI_TRIPS_DEVICES) {
-		memset(&devices, 0, sizeof(struct acpi_handle_list));
+	if ((flag & ACPI_TRIPS_DEVICES)
+	    && acpi_has_method(tz->device->handle, "_TZD")) {
+		memset(&devices, 0, sizeof(devices));
 		status = acpi_evaluate_reference(tz->device->handle, "_TZD",
 						NULL, &devices);
-		if (memcmp(&tz->devices, &devices,
-				sizeof(struct acpi_handle_list))) {
-			memcpy(&tz->devices, &devices,
-				sizeof(struct acpi_handle_list));
+		if (ACPI_SUCCESS(status)
+		    && memcmp(&tz->devices, &devices, sizeof(devices))) {
+			tz->devices = devices;
 			ACPI_THERMAL_TRIPS_EXCEPTION(flag, "device");
 		}
 	}
@@ -769,7 +753,6 @@ static int thermal_notify(struct thermal_zone_device *thermal, int trip,
 	else
 		return 0;
 
-	acpi_bus_generate_proc_event(tz->device, type, 1);
 	acpi_bus_generate_netlink_event(tz->device->pnp.device_class,
 					dev_name(&tz->device->dev), type, 1);
 
@@ -850,12 +833,13 @@ static int acpi_thermal_cooling_device_cb(struct thermal_zone_device *thermal,
 		if (ACPI_SUCCESS(status) && (dev == device)) {
 			if (bind)
 				result = thermal_zone_bind_cooling_device
-						(thermal, -1, cdev,
-						 THERMAL_NO_LIMIT,
+						(thermal, THERMAL_TRIPS_NONE,
+						 cdev, THERMAL_NO_LIMIT,
 						 THERMAL_NO_LIMIT);
 			else
 				result = thermal_zone_unbind_cooling_device
-						(thermal, -1, cdev);
+						(thermal, THERMAL_TRIPS_NONE,
+						 cdev);
 			if (result)
 				goto failed;
 		}
@@ -980,14 +964,12 @@ static void acpi_thermal_notify(struct acpi_device *device, u32 event)
 	case ACPI_THERMAL_NOTIFY_THRESHOLDS:
 		acpi_thermal_trips_update(tz, ACPI_TRIPS_REFRESH_THRESHOLDS);
 		acpi_thermal_check(tz);
-		acpi_bus_generate_proc_event(device, event, 0);
 		acpi_bus_generate_netlink_event(device->pnp.device_class,
 						  dev_name(&device->dev), event, 0);
 		break;
 	case ACPI_THERMAL_NOTIFY_DEVICES:
 		acpi_thermal_trips_update(tz, ACPI_TRIPS_REFRESH_DEVICES);
 		acpi_thermal_check(tz);
-		acpi_bus_generate_proc_event(device, event, 0);
 		acpi_bus_generate_netlink_event(device->pnp.device_class,
 						  dev_name(&device->dev), event, 0);
 		break;
@@ -1101,8 +1083,6 @@ static int acpi_thermal_add(struct acpi_device *device)
 	strcpy(acpi_device_name(device), ACPI_THERMAL_DEVICE_NAME);
 	strcpy(acpi_device_class(device), ACPI_THERMAL_CLASS);
 	device->driver_data = tz;
-	mutex_init(&tz->lock);
-
 
 	result = acpi_thermal_get_info(tz);
 	if (result)
@@ -1135,7 +1115,6 @@ static int acpi_thermal_remove(struct acpi_device *device)
 	tz = acpi_driver_data(device);
 
 	acpi_thermal_unregister_thermal_zone(tz);
-	mutex_destroy(&tz->lock);
 	kfree(tz);
 	return 0;
 }
diff --git a/drivers/acpi/utils.c b/drivers/acpi/utils.c
index 744371304313..552248b0005b 100644
--- a/drivers/acpi/utils.c
+++ b/drivers/acpi/utils.c
@@ -495,3 +495,73 @@ acpi_handle_printk(const char *level, acpi_handle handle, const char *fmt, ...)
 	kfree(buffer.pointer);
 }
 EXPORT_SYMBOL(acpi_handle_printk);
+
+/**
+ * acpi_has_method: Check whether @handle has a method named @name
+ * @handle: ACPI device handle
+ * @name: name of object or method
+ *
+ * Check whether @handle has a method named @name.
+ */
+bool acpi_has_method(acpi_handle handle, char *name)
+{
+	acpi_handle tmp;
+
+	return ACPI_SUCCESS(acpi_get_handle(handle, name, &tmp));
+}
+EXPORT_SYMBOL(acpi_has_method);
+
+acpi_status acpi_execute_simple_method(acpi_handle handle, char *method,
+				       u64 arg)
+{
+	union acpi_object obj = { .type = ACPI_TYPE_INTEGER };
+	struct acpi_object_list arg_list = { .count = 1, .pointer = &obj, };
+
+	obj.integer.value = arg;
+
+	return acpi_evaluate_object(handle, method, &arg_list, NULL);
+}
+EXPORT_SYMBOL(acpi_execute_simple_method);
+
+/**
+ * acpi_evaluate_ej0: Evaluate _EJ0 method for hotplug operations
+ * @handle: ACPI device handle
+ *
+ * Evaluate device's _EJ0 method for hotplug operations.
+ */
+acpi_status acpi_evaluate_ej0(acpi_handle handle)
+{
+	acpi_status status;
+
+	status = acpi_execute_simple_method(handle, "_EJ0", 1);
+	if (status == AE_NOT_FOUND)
+		acpi_handle_warn(handle, "No _EJ0 support for device\n");
+	else if (ACPI_FAILURE(status))
+		acpi_handle_warn(handle, "Eject failed (0x%x)\n", status);
+
+	return status;
+}
+
+/**
+ * acpi_evaluate_lck: Evaluate _LCK method to lock/unlock device
+ * @handle: ACPI device handle
+ * @lock: lock device if non-zero, otherwise unlock device
+ *
+ * Evaluate device's _LCK method if present to lock/unlock device
+ */
+acpi_status acpi_evaluate_lck(acpi_handle handle, int lock)
+{
+	acpi_status status;
+
+	status = acpi_execute_simple_method(handle, "_LCK", !!lock);
+	if (ACPI_FAILURE(status) && status != AE_NOT_FOUND) {
+		if (lock)
+			acpi_handle_warn(handle,
+				"Locking device failed (0x%x)\n", status);
+		else
+			acpi_handle_warn(handle,
+				"Unlocking device failed (0x%x)\n", status);
+	}
+
+	return status;
+}
diff --git a/drivers/acpi/video.c b/drivers/acpi/video.c
index 3270d3c8ba4e..aebcf6355df4 100644
--- a/drivers/acpi/video.c
+++ b/drivers/acpi/video.c
@@ -1,5 +1,5 @@
 /*
- *  video.c - ACPI Video Driver ($Revision:$)
+ *  video.c - ACPI Video Driver
  *
  *  Copyright (C) 2004 Luming Yu <luming.yu@intel.com>
  *  Copyright (C) 2004 Bruno Ducrot <ducrot@poupinou.org>
@@ -88,7 +88,7 @@ module_param(allow_duplicates, bool, 0644);
 static bool use_bios_initial_backlight = 1;
 module_param(use_bios_initial_backlight, bool, 0644);
 
-static int register_count = 0;
+static int register_count;
 static int acpi_video_bus_add(struct acpi_device *device);
 static int acpi_video_bus_remove(struct acpi_device *device);
 static void acpi_video_bus_notify(struct acpi_device *device, u32 event);
@@ -118,26 +118,26 @@ struct acpi_video_bus_flags {
 };
 
 struct acpi_video_bus_cap {
-	u8 _DOS:1;		/*Enable/Disable output switching */
-	u8 _DOD:1;		/*Enumerate all devices attached to display adapter */
-	u8 _ROM:1;		/*Get ROM Data */
-	u8 _GPD:1;		/*Get POST Device */
-	u8 _SPD:1;		/*Set POST Device */
-	u8 _VPO:1;		/*Video POST Options */
+	u8 _DOS:1;		/* Enable/Disable output switching */
+	u8 _DOD:1;		/* Enumerate all devices attached to display adapter */
+	u8 _ROM:1;		/* Get ROM Data */
+	u8 _GPD:1;		/* Get POST Device */
+	u8 _SPD:1;		/* Set POST Device */
+	u8 _VPO:1;		/* Video POST Options */
 	u8 reserved:2;
 };
 
 struct acpi_video_device_attrib {
 	u32 display_index:4;	/* A zero-based instance of the Display */
-	u32 display_port_attachment:4;	/*This field differentiates the display type */
-	u32 display_type:4;	/*Describe the specific type in use */
-	u32 vendor_specific:4;	/*Chipset Vendor Specific */
-	u32 bios_can_detect:1;	/*BIOS can detect the device */
-	u32 depend_on_vga:1;	/*Non-VGA output device whose power is related to 
+	u32 display_port_attachment:4;	/* This field differentiates the display type */
+	u32 display_type:4;	/* Describe the specific type in use */
+	u32 vendor_specific:4;	/* Chipset Vendor Specific */
+	u32 bios_can_detect:1;	/* BIOS can detect the device */
+	u32 depend_on_vga:1;	/* Non-VGA output device whose power is related to
 				   the VGA device. */
-	u32 pipe_id:3;		/*For VGA multiple-head devices. */
-	u32 reserved:10;	/*Must be 0 */
-	u32 device_id_scheme:1;	/*Device ID Scheme */
+	u32 pipe_id:3;		/* For VGA multiple-head devices. */
+	u32 reserved:10;	/* Must be 0 */
+	u32 device_id_scheme:1;	/* Device ID Scheme */
 };
 
 struct acpi_video_enumerated_device {
@@ -174,19 +174,17 @@ struct acpi_video_device_flags {
 };
 
 struct acpi_video_device_cap {
-	u8 _ADR:1;		/*Return the unique ID */
-	u8 _BCL:1;		/*Query list of brightness control levels supported */
-	u8 _BCM:1;		/*Set the brightness level */
+	u8 _ADR:1;		/* Return the unique ID */
+	u8 _BCL:1;		/* Query list of brightness control levels supported */
+	u8 _BCM:1;		/* Set the brightness level */
 	u8 _BQC:1;		/* Get current brightness level */
 	u8 _BCQ:1;		/* Some buggy BIOS uses _BCQ instead of _BQC */
-	u8 _DDC:1;		/*Return the EDID for this device */
+	u8 _DDC:1;		/* Return the EDID for this device */
 };
 
 struct acpi_video_brightness_flags {
 	u8 _BCL_no_ac_battery_levels:1;	/* no AC/Battery levels in _BCL */
-	u8 _BCL_reversed:1;		/* _BCL package is in a reversed order*/
-	u8 _BCL_use_index:1;		/* levels in _BCL are index values */
-	u8 _BCM_use_index:1;		/* input of _BCM is an index value */
+	u8 _BCL_reversed:1;		/* _BCL package is in a reversed order */
 	u8 _BQC_use_index:1;		/* _BQC returns an index value */
 };
 
@@ -231,21 +229,22 @@ static int acpi_video_get_next_level(struct acpi_video_device *device,
 static int acpi_video_switch_brightness(struct acpi_video_device *device,
 					 int event);
 
-/*backlight device sysfs support*/
+/* backlight device sysfs support */
 static int acpi_video_get_brightness(struct backlight_device *bd)
 {
 	unsigned long long cur_level;
 	int i;
-	struct acpi_video_device *vd =
-		(struct acpi_video_device *)bl_get_data(bd);
+	struct acpi_video_device *vd = bl_get_data(bd);
 
 	if (acpi_video_device_lcd_get_level_current(vd, &cur_level, false))
 		return -EINVAL;
 	for (i = 2; i < vd->brightness->count; i++) {
 		if (vd->brightness->levels[i] == cur_level)
-			/* The first two entries are special - see page 575
-			   of the ACPI spec 3.0 */
-			return i-2;
+			/*
+			 * The first two entries are special - see page 575
+			 * of the ACPI spec 3.0
+			 */
+			return i - 2;
 	}
 	return 0;
 }
@@ -253,8 +252,7 @@ static int acpi_video_get_brightness(struct backlight_device *bd)
 static int acpi_video_set_brightness(struct backlight_device *bd)
 {
 	int request_level = bd->props.brightness + 2;
-	struct acpi_video_device *vd =
-		(struct acpi_video_device *)bl_get_data(bd);
+	struct acpi_video_device *vd = bl_get_data(bd);
 
 	return acpi_video_device_lcd_set_level(vd,
 				vd->brightness->levels[request_level]);
@@ -302,11 +300,11 @@ video_set_cur_state(struct thermal_cooling_device *cooling_dev, unsigned long st
 	struct acpi_video_device *video = acpi_driver_data(device);
 	int level;
 
-	if ( state >= video->brightness->count - 2)
+	if (state >= video->brightness->count - 2)
 		return -EINVAL;
 
 	state = video->brightness->count - state;
-	level = video->brightness->levels[state -1];
+	level = video->brightness->levels[state - 1];
 	return acpi_video_device_lcd_set_level(video, level);
 }
 
@@ -316,9 +314,11 @@ static const struct thermal_cooling_device_ops video_cooling_ops = {
 	.set_cur_state = video_set_cur_state,
 };
 
-/* --------------------------------------------------------------------------
-                               Video Management
-   -------------------------------------------------------------------------- */
+/*
+ * --------------------------------------------------------------------------
+ *                             Video Management
+ * --------------------------------------------------------------------------
+ */
 
 static int
 acpi_video_device_lcd_query_levels(struct acpi_video_device *device,
@@ -345,7 +345,7 @@ acpi_video_device_lcd_query_levels(struct acpi_video_device *device,
 
 	return 0;
 
-      err:
+err:
 	kfree(buffer.pointer);
 
 	return status;
@@ -355,14 +355,10 @@ static int
 acpi_video_device_lcd_set_level(struct acpi_video_device *device, int level)
 {
 	int status;
-	union acpi_object arg0 = { ACPI_TYPE_INTEGER };
-	struct acpi_object_list args = { 1, &arg0 };
 	int state;
 
-	arg0.integer.value = level;
-
-	status = acpi_evaluate_object(device->dev->handle, "_BCM",
-				      &args, NULL);
+	status = acpi_execute_simple_method(device->dev->handle,
+					    "_BCM", level);
 	if (ACPI_FAILURE(status)) {
 		ACPI_ERROR((AE_INFO, "Evaluating _BCM failed"));
 		return -EIO;
@@ -546,7 +542,7 @@ acpi_video_device_lcd_get_level_current(struct acpi_video_device *device,
 				if (device->brightness->levels[i] == *level) {
 					device->brightness->curr = *level;
 					return 0;
-			}
+				}
 			/*
 			 * BQC returned an invalid level.
 			 * Stop using it.
@@ -556,7 +552,8 @@ acpi_video_device_lcd_get_level_current(struct acpi_video_device *device,
 				      buf));
 			device->cap._BQC = device->cap._BCQ = 0;
 		} else {
-			/* Fixme:
+			/*
+			 * Fixme:
 			 * should we return an error or ignore this failure?
 			 * dev->brightness->curr is a cached value which stores
 			 * the correct current backlight level in most cases.
@@ -615,8 +612,8 @@ acpi_video_device_EDID(struct acpi_video_device *device,
 
 /*
  *  Arg:
- *  	video		: video bus device pointer
- *	bios_flag	: 
+ *	video		: video bus device pointer
+ *	bios_flag	:
  *		0.	The system BIOS should NOT automatically switch(toggle)
  *			the active display output.
  *		1.	The system BIOS should automatically switch (toggle) the
@@ -628,9 +625,9 @@ acpi_video_device_EDID(struct acpi_video_device *device,
  *	lcd_flag	:
  *		0.	The system BIOS should automatically control the brightness level
  *			of the LCD when the power changes from AC to DC
- *		1. 	The system BIOS should NOT automatically control the brightness 
+ *		1.	The system BIOS should NOT automatically control the brightness
  *			level of the LCD when the power changes from AC to DC.
- * Return Value:
+ *  Return Value:
  *		-EINVAL	wrong arg.
  */
 
@@ -638,18 +635,15 @@ static int
 acpi_video_bus_DOS(struct acpi_video_bus *video, int bios_flag, int lcd_flag)
 {
 	acpi_status status;
-	union acpi_object arg0 = { ACPI_TYPE_INTEGER };
-	struct acpi_object_list args = { 1, &arg0 };
 
 	if (!video->cap._DOS)
 		return 0;
 
 	if (bios_flag < 0 || bios_flag > 3 || lcd_flag < 0 || lcd_flag > 1)
 		return -EINVAL;
-	arg0.integer.value = (lcd_flag << 2) | bios_flag;
-	video->dos_setting = arg0.integer.value;
-	status = acpi_evaluate_object(video->device->handle, "_DOS",
-		&args, NULL);
+	video->dos_setting = (lcd_flag << 2) | bios_flag;
+	status = acpi_execute_simple_method(video->device->handle, "_DOS",
+					    (lcd_flag << 2) | bios_flag);
 	if (ACPI_FAILURE(status))
 		return -EIO;
 
@@ -717,8 +711,8 @@ static int acpi_video_bqc_quirk(struct acpi_video_device *device,
 
 
 /*
- *  Arg:	
- *  	device	: video output device (LCD, CRT, ..)
+ *  Arg:
+ *	device	: video output device (LCD, CRT, ..)
  *
  *  Return Value:
  *	Maximum brightness level
@@ -806,16 +800,6 @@ acpi_video_init_brightness(struct acpi_video_device *device)
 	br->count = count;
 	device->brightness = br;
 
-	/* Check the input/output of _BQC/_BCL/_BCM */
-	if ((max_level < 100) && (max_level <= (count - 2)))
-		br->flags._BCL_use_index = 1;
-
-	/*
-	 * _BCM is always consistent with _BCL,
-	 * at least for all the laptops we have ever seen.
-	 */
-	br->flags._BCM_use_index = br->flags._BCL_use_index;
-
 	/* _BQC uses INDEX while _BCL uses VALUE in some laptops */
 	br->curr = level = max_level;
 
@@ -877,7 +861,7 @@ out:
  *	device	: video output device (LCD, CRT, ..)
  *
  *  Return Value:
- *  	None
+ *	None
  *
  *  Find out all required AML methods defined under the output
  *  device.
@@ -885,28 +869,21 @@ out:
 
 static void acpi_video_device_find_cap(struct acpi_video_device *device)
 {
-	acpi_handle h_dummy1;
-
-	if (ACPI_SUCCESS(acpi_get_handle(device->dev->handle, "_ADR", &h_dummy1))) {
+	if (acpi_has_method(device->dev->handle, "_ADR"))
 		device->cap._ADR = 1;
-	}
-	if (ACPI_SUCCESS(acpi_get_handle(device->dev->handle, "_BCL", &h_dummy1))) {
+	if (acpi_has_method(device->dev->handle, "_BCL"))
 		device->cap._BCL = 1;
-	}
-	if (ACPI_SUCCESS(acpi_get_handle(device->dev->handle, "_BCM", &h_dummy1))) {
+	if (acpi_has_method(device->dev->handle, "_BCM"))
 		device->cap._BCM = 1;
-	}
-	if (ACPI_SUCCESS(acpi_get_handle(device->dev->handle,"_BQC",&h_dummy1)))
+	if (acpi_has_method(device->dev->handle, "_BQC")) {
 		device->cap._BQC = 1;
-	else if (ACPI_SUCCESS(acpi_get_handle(device->dev->handle, "_BCQ",
-				&h_dummy1))) {
+	} else if (acpi_has_method(device->dev->handle, "_BCQ")) {
 		printk(KERN_WARNING FW_BUG "_BCQ is used instead of _BQC\n");
 		device->cap._BCQ = 1;
 	}
 
-	if (ACPI_SUCCESS(acpi_get_handle(device->dev->handle, "_DDC", &h_dummy1))) {
+	if (acpi_has_method(device->dev->handle, "_DDC"))
 		device->cap._DDC = 1;
-	}
 
 	if (acpi_video_backlight_support()) {
 		struct backlight_properties props;
@@ -914,7 +891,7 @@ static void acpi_video_device_find_cap(struct acpi_video_device *device)
 		acpi_handle acpi_parent;
 		struct device *parent = NULL;
 		int result;
-		static int count = 0;
+		static int count;
 		char *name;
 
 		result = acpi_video_init_brightness(device);
@@ -983,37 +960,29 @@ static void acpi_video_device_find_cap(struct acpi_video_device *device)
 }
 
 /*
- *  Arg:	
- *  	device	: video output device (VGA)
+ *  Arg:
+ *	device	: video output device (VGA)
  *
  *  Return Value:
- *  	None
+ *	None
  *
  *  Find out all required AML methods defined under the video bus device.
  */
 
 static void acpi_video_bus_find_cap(struct acpi_video_bus *video)
 {
-	acpi_handle h_dummy1;
-
-	if (ACPI_SUCCESS(acpi_get_handle(video->device->handle, "_DOS", &h_dummy1))) {
+	if (acpi_has_method(video->device->handle, "_DOS"))
 		video->cap._DOS = 1;
-	}
-	if (ACPI_SUCCESS(acpi_get_handle(video->device->handle, "_DOD", &h_dummy1))) {
+	if (acpi_has_method(video->device->handle, "_DOD"))
 		video->cap._DOD = 1;
-	}
-	if (ACPI_SUCCESS(acpi_get_handle(video->device->handle, "_ROM", &h_dummy1))) {
+	if (acpi_has_method(video->device->handle, "_ROM"))
 		video->cap._ROM = 1;
-	}
-	if (ACPI_SUCCESS(acpi_get_handle(video->device->handle, "_GPD", &h_dummy1))) {
+	if (acpi_has_method(video->device->handle, "_GPD"))
 		video->cap._GPD = 1;
-	}
-	if (ACPI_SUCCESS(acpi_get_handle(video->device->handle, "_SPD", &h_dummy1))) {
+	if (acpi_has_method(video->device->handle, "_SPD"))
 		video->cap._SPD = 1;
-	}
-	if (ACPI_SUCCESS(acpi_get_handle(video->device->handle, "_VPO", &h_dummy1))) {
+	if (acpi_has_method(video->device->handle, "_VPO"))
 		video->cap._VPO = 1;
-	}
 }
 
 /*
@@ -1034,7 +1003,8 @@ static int acpi_video_bus_check(struct acpi_video_bus *video)
 		return -ENODEV;
 	pci_dev_put(dev);
 
-	/* Since there is no HID, CID and so on for VGA driver, we have
+	/*
+	 * Since there is no HID, CID and so on for VGA driver, we have
 	 * to check well known required nodes.
 	 */
 
@@ -1064,12 +1034,14 @@ static int acpi_video_bus_check(struct acpi_video_bus *video)
 	return status;
 }
 
-/* --------------------------------------------------------------------------
-                                 Driver Interface
-   -------------------------------------------------------------------------- */
+/*
+ * --------------------------------------------------------------------------
+ *                               Driver Interface
+ * --------------------------------------------------------------------------
+ */
 
 /* device interface */
-static struct acpi_video_device_attrib*
+static struct acpi_video_device_attrib *
 acpi_video_get_device_attr(struct acpi_video_bus *video, unsigned long device_id)
 {
 	struct acpi_video_enumerated_device *ids;
@@ -1107,7 +1079,7 @@ acpi_video_bus_get_one_device(struct acpi_device *device,
 	unsigned long long device_id;
 	int status, device_type;
 	struct acpi_video_device *data;
-	struct acpi_video_device_attrib* attribute;
+	struct acpi_video_device_attrib *attribute;
 
 	status =
 	    acpi_evaluate_integer(device->handle, "_ADR", NULL, &device_id);
@@ -1129,7 +1101,7 @@ acpi_video_bus_get_one_device(struct acpi_device *device,
 
 	attribute = acpi_video_get_device_attr(video, device_id);
 
-	if((attribute != NULL) && attribute->device_id_scheme) {
+	if (attribute && attribute->device_id_scheme) {
 		switch (attribute->display_type) {
 		case ACPI_VIDEO_DISPLAY_CRT:
 			data->flags.crt = 1;
@@ -1147,24 +1119,24 @@ acpi_video_bus_get_one_device(struct acpi_device *device,
 			data->flags.unknown = 1;
 			break;
 		}
-		if(attribute->bios_can_detect)
+		if (attribute->bios_can_detect)
 			data->flags.bios = 1;
 	} else {
 		/* Check for legacy IDs */
 		device_type = acpi_video_get_device_type(video, device_id);
 		/* Ignore bits 16 and 18-20 */
 		switch (device_type & 0xffe2ffff) {
-			case ACPI_VIDEO_DISPLAY_LEGACY_MONITOR:
-				data->flags.crt = 1;
-				break;
-			case ACPI_VIDEO_DISPLAY_LEGACY_PANEL:
-				data->flags.lcd = 1;
-				break;
-			case ACPI_VIDEO_DISPLAY_LEGACY_TV:
-				data->flags.tvout = 1;
-				break;
-			default:
-				data->flags.unknown = 1;
+		case ACPI_VIDEO_DISPLAY_LEGACY_MONITOR:
+			data->flags.crt = 1;
+			break;
+		case ACPI_VIDEO_DISPLAY_LEGACY_PANEL:
+			data->flags.lcd = 1;
+			break;
+		case ACPI_VIDEO_DISPLAY_LEGACY_TV:
+			data->flags.tvout = 1;
+			break;
+		default:
+			data->flags.unknown = 1;
 		}
 	}
 
@@ -1187,12 +1159,12 @@ acpi_video_bus_get_one_device(struct acpi_device *device,
 
 /*
  *  Arg:
- *  	video	: video bus device 
+ *	video	: video bus device
  *
  *  Return:
- *  	none
- *  
- *  Enumerate the video device list of the video bus, 
+ *	none
+ *
+ *  Enumerate the video device list of the video bus,
  *  bind the ids with the corresponding video devices
  *  under the video bus.
  */
@@ -1211,13 +1183,13 @@ static void acpi_video_device_rebind(struct acpi_video_bus *video)
 
 /*
  *  Arg:
- *  	video	: video bus device 
- *  	device	: video output device under the video 
- *  		bus
+ *	video	: video bus device
+ *	device	: video output device under the video
+ *		bus
  *
  *  Return:
- *  	none
- *  
+ *	none
+ *
  *  Bind the ids with the corresponding video devices
  *  under the video bus.
  */
@@ -1240,11 +1212,11 @@ acpi_video_device_bind(struct acpi_video_bus *video,
 
 /*
  *  Arg:
- *  	video	: video bus device 
+ *	video	: video bus device
  *
  *  Return:
- *  	< 0	: error
- *  
+ *	< 0	: error
+ *
  *  Call _DOD to enumerate all devices attached to display adapter
  *
  */
@@ -1305,7 +1277,7 @@ static int acpi_video_device_enumerate(struct acpi_video_bus *video)
 	video->attached_array = active_list;
 	video->attached_count = count;
 
- out:
+out:
 	kfree(buffer.pointer);
 	return status;
 }
@@ -1572,7 +1544,6 @@ static void acpi_video_bus_notify(struct acpi_device *device, u32 event)
 	switch (event) {
 	case ACPI_VIDEO_NOTIFY_SWITCH:	/* User requested a switch,
 					 * most likely via hotkey. */
-		acpi_bus_generate_proc_event(device, event, 0);
 		keycode = KEY_SWITCHVIDEOMODE;
 		break;
 
@@ -1580,20 +1551,16 @@ static void acpi_video_bus_notify(struct acpi_device *device, u32 event)
 					 * connector. */
 		acpi_video_device_enumerate(video);
 		acpi_video_device_rebind(video);
-		acpi_bus_generate_proc_event(device, event, 0);
 		keycode = KEY_SWITCHVIDEOMODE;
 		break;
 
 	case ACPI_VIDEO_NOTIFY_CYCLE:	/* Cycle Display output hotkey pressed. */
-		acpi_bus_generate_proc_event(device, event, 0);
 		keycode = KEY_SWITCHVIDEOMODE;
 		break;
 	case ACPI_VIDEO_NOTIFY_NEXT_OUTPUT:	/* Next Display output hotkey pressed. */
-		acpi_bus_generate_proc_event(device, event, 0);
 		keycode = KEY_VIDEO_NEXT;
 		break;
 	case ACPI_VIDEO_NOTIFY_PREV_OUTPUT:	/* previous Display output hotkey pressed. */
-		acpi_bus_generate_proc_event(device, event, 0);
 		keycode = KEY_VIDEO_PREV;
 		break;
 
@@ -1636,31 +1603,26 @@ static void acpi_video_device_notify(acpi_handle handle, u32 event, void *data)
 	case ACPI_VIDEO_NOTIFY_CYCLE_BRIGHTNESS:	/* Cycle brightness */
 		if (brightness_switch_enabled)
 			acpi_video_switch_brightness(video_device, event);
-		acpi_bus_generate_proc_event(device, event, 0);
 		keycode = KEY_BRIGHTNESS_CYCLE;
 		break;
 	case ACPI_VIDEO_NOTIFY_INC_BRIGHTNESS:	/* Increase brightness */
 		if (brightness_switch_enabled)
 			acpi_video_switch_brightness(video_device, event);
-		acpi_bus_generate_proc_event(device, event, 0);
 		keycode = KEY_BRIGHTNESSUP;
 		break;
 	case ACPI_VIDEO_NOTIFY_DEC_BRIGHTNESS:	/* Decrease brightness */
 		if (brightness_switch_enabled)
 			acpi_video_switch_brightness(video_device, event);
-		acpi_bus_generate_proc_event(device, event, 0);
 		keycode = KEY_BRIGHTNESSDOWN;
 		break;
 	case ACPI_VIDEO_NOTIFY_ZERO_BRIGHTNESS:	/* zero brightness */
 		if (brightness_switch_enabled)
 			acpi_video_switch_brightness(video_device, event);
-		acpi_bus_generate_proc_event(device, event, 0);
 		keycode = KEY_BRIGHTNESS_ZERO;
 		break;
 	case ACPI_VIDEO_NOTIFY_DISPLAY_OFF:	/* display device off */
 		if (brightness_switch_enabled)
 			acpi_video_switch_brightness(video_device, event);
-		acpi_bus_generate_proc_event(device, event, 0);
 		keycode = KEY_DISPLAY_OFF;
 		break;
 	default:
@@ -1760,7 +1722,7 @@ static int acpi_video_bus_add(struct acpi_device *device)
 	if (!strcmp(device->pnp.bus_id, "VID")) {
 		if (instance)
 			device->pnp.bus_id[3] = '0' + instance;
-		instance ++;
+		instance++;
 	}
 	/* a hack to fix the duplicate name "VGA" problem on Pa 3553 */
 	if (!strcmp(device->pnp.bus_id, "VGA")) {
diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c
index c3397748ba46..940edbf2fe8f 100644
--- a/drivers/acpi/video_detect.c
+++ b/drivers/acpi/video_detect.c
@@ -53,14 +53,13 @@ acpi_backlight_cap_match(acpi_handle handle, u32 level, void *context,
 			  void **retyurn_value)
 {
 	long *cap = context;
-	acpi_handle h_dummy;
 
-	if (ACPI_SUCCESS(acpi_get_handle(handle, "_BCM", &h_dummy)) &&
-	    ACPI_SUCCESS(acpi_get_handle(handle, "_BCL", &h_dummy))) {
+	if (acpi_has_method(handle, "_BCM") &&
+	    acpi_has_method(handle, "_BCL")) {
 		ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Found generic backlight "
 				  "support\n"));
 		*cap |= ACPI_VIDEO_BACKLIGHT;
-		if (ACPI_FAILURE(acpi_get_handle(handle, "_BQC", &h_dummy)))
+		if (!acpi_has_method(handle, "_BQC"))
 			printk(KERN_WARNING FW_BUG PREFIX "No _BQC method, "
 				"cannot determine initial brightness\n");
 		/* We have backlight support, no need to scan further */
@@ -79,22 +78,20 @@ acpi_backlight_cap_match(acpi_handle handle, u32 level, void *context,
  */
 long acpi_is_video_device(acpi_handle handle)
 {
-	acpi_handle h_dummy;
 	long video_caps = 0;
 
 	/* Is this device able to support video switching ? */
-	if (ACPI_SUCCESS(acpi_get_handle(handle, "_DOD", &h_dummy)) ||
-	    ACPI_SUCCESS(acpi_get_handle(handle, "_DOS", &h_dummy)))
+	if (acpi_has_method(handle, "_DOD") || acpi_has_method(handle, "_DOS"))
 		video_caps |= ACPI_VIDEO_OUTPUT_SWITCHING;
 
 	/* Is this device able to retrieve a video ROM ? */
-	if (ACPI_SUCCESS(acpi_get_handle(handle, "_ROM", &h_dummy)))
+	if (acpi_has_method(handle, "_ROM"))
 		video_caps |= ACPI_VIDEO_ROM_AVAILABLE;
 
 	/* Is this device able to configure which video head to be POSTed ? */
-	if (ACPI_SUCCESS(acpi_get_handle(handle, "_VPO", &h_dummy)) &&
-	    ACPI_SUCCESS(acpi_get_handle(handle, "_GPD", &h_dummy)) &&
-	    ACPI_SUCCESS(acpi_get_handle(handle, "_SPD", &h_dummy)))
+	if (acpi_has_method(handle, "_VPO") &&
+	    acpi_has_method(handle, "_GPD") &&
+	    acpi_has_method(handle, "_SPD"))
 		video_caps |= ACPI_VIDEO_DEVICE_POSTING;
 
 	/* Only check for backlight functionality if one of the above hit. */
diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index db4380d70031..9d715ae5ff6b 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -1295,6 +1295,14 @@ static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 		 */
 		if (!(hpriv->flags & AHCI_HFLAG_NO_FPDMA_AA))
 			pi.flags |= ATA_FLAG_FPDMA_AA;
+
+		/*
+		 * All AHCI controllers should be forward-compatible
+		 * with the new auxiliary field. This code should be
+		 * conditionalized if any buggy AHCI controllers are
+		 * encountered.
+		 */
+		pi.flags |= ATA_FLAG_FPDMA_AUX;
 	}
 
 	if (hpriv->cap & HOST_CAP_PMP)
diff --git a/drivers/ata/libata-acpi.c b/drivers/ata/libata-acpi.c
index cf4e7020adac..ab714d2ad978 100644
--- a/drivers/ata/libata-acpi.c
+++ b/drivers/ata/libata-acpi.c
@@ -34,14 +34,6 @@ struct ata_acpi_gtf {
 	u8	tf[REGS_PER_GTF];	/* regs. 0x1f1 - 0x1f7 */
 } __packed;
 
-/*
- *	Helper - belongs in the PCI layer somewhere eventually
- */
-static int is_pci_dev(struct device *dev)
-{
-	return (dev->bus == &pci_bus_type);
-}
-
 static void ata_acpi_clear_gtf(struct ata_device *dev)
 {
 	kfree(dev->gtf_cache);
@@ -49,47 +41,18 @@ static void ata_acpi_clear_gtf(struct ata_device *dev)
 }
 
 /**
- * ata_ap_acpi_handle - provide the acpi_handle for an ata_port
- * @ap: the acpi_handle returned will correspond to this port
- *
- * Returns the acpi_handle for the ACPI namespace object corresponding to
- * the ata_port passed into the function, or NULL if no such object exists
- */
-acpi_handle ata_ap_acpi_handle(struct ata_port *ap)
-{
-	if (ap->flags & ATA_FLAG_ACPI_SATA)
-		return NULL;
-
-	return ap->scsi_host ?
-		DEVICE_ACPI_HANDLE(&ap->scsi_host->shost_gendev) : NULL;
-}
-EXPORT_SYMBOL(ata_ap_acpi_handle);
-
-/**
  * ata_dev_acpi_handle - provide the acpi_handle for an ata_device
- * @dev: the acpi_device returned will correspond to this port
+ * @dev: the acpi_handle returned will correspond to this device
  *
  * Returns the acpi_handle for the ACPI namespace object corresponding to
  * the ata_device passed into the function, or NULL if no such object exists
+ * or ACPI is disabled for this device due to consecutive errors.
  */
 acpi_handle ata_dev_acpi_handle(struct ata_device *dev)
 {
-	acpi_integer adr;
-	struct ata_port *ap = dev->link->ap;
-
-	if (libata_noacpi || dev->flags & ATA_DFLAG_ACPI_DISABLED)
-		return NULL;
-
-	if (ap->flags & ATA_FLAG_ACPI_SATA) {
-		if (!sata_pmp_attached(ap))
-			adr = SATA_ADR(ap->port_no, NO_PORT_MULT);
-		else
-			adr = SATA_ADR(ap->port_no, dev->link->pmp);
-		return acpi_get_child(DEVICE_ACPI_HANDLE(ap->host->dev), adr);
-	} else
-		return acpi_get_child(ata_ap_acpi_handle(ap), dev->devno);
+	return dev->flags & ATA_DFLAG_ACPI_DISABLED ?
+			NULL : ACPI_HANDLE(&dev->tdev);
 }
-EXPORT_SYMBOL(ata_dev_acpi_handle);
 
 /* @ap and @dev are the same as ata_acpi_handle_hotplug() */
 static void ata_acpi_detach_device(struct ata_port *ap, struct ata_device *dev)
@@ -156,10 +119,8 @@ static void ata_acpi_handle_hotplug(struct ata_port *ap, struct ata_device *dev,
 
 	spin_unlock_irqrestore(ap->lock, flags);
 
-	if (wait) {
+	if (wait)
 		ata_port_wait_eh(ap);
-		flush_work(&ap->hotplug_task.work);
-	}
 }
 
 static void ata_acpi_dev_notify_dock(acpi_handle handle, u32 event, void *data)
@@ -216,37 +177,55 @@ static const struct acpi_dock_ops ata_acpi_ap_dock_ops = {
 	.uevent = ata_acpi_ap_uevent,
 };
 
-void ata_acpi_hotplug_init(struct ata_host *host)
+/* bind acpi handle to pata port */
+void ata_acpi_bind_port(struct ata_port *ap)
 {
-	int i;
+	acpi_handle host_handle = ACPI_HANDLE(ap->host->dev);
 
-	for (i = 0; i < host->n_ports; i++) {
-		struct ata_port *ap = host->ports[i];
-		acpi_handle handle;
-		struct ata_device *dev;
+	if (libata_noacpi || ap->flags & ATA_FLAG_ACPI_SATA || !host_handle)
+		return;
 
-		if (!ap)
-			continue;
+	ACPI_HANDLE_SET(&ap->tdev, acpi_get_child(host_handle, ap->port_no));
 
-		handle = ata_ap_acpi_handle(ap);
-		if (handle) {
-			/* we might be on a docking station */
-			register_hotplug_dock_device(handle,
-						     &ata_acpi_ap_dock_ops, ap,
-						     NULL, NULL);
-		}
+	if (ata_acpi_gtm(ap, &ap->__acpi_init_gtm) == 0)
+		ap->pflags |= ATA_PFLAG_INIT_GTM_VALID;
 
-		ata_for_each_dev(dev, &ap->link, ALL) {
-			handle = ata_dev_acpi_handle(dev);
-			if (!handle)
-				continue;
+	/* we might be on a docking station */
+	register_hotplug_dock_device(ACPI_HANDLE(&ap->tdev),
+				     &ata_acpi_ap_dock_ops, ap, NULL, NULL);
+}
 
-			/* we might be on a docking station */
-			register_hotplug_dock_device(handle,
-						     &ata_acpi_dev_dock_ops,
-						     dev, NULL, NULL);
-		}
+void ata_acpi_bind_dev(struct ata_device *dev)
+{
+	struct ata_port *ap = dev->link->ap;
+	acpi_handle port_handle = ACPI_HANDLE(&ap->tdev);
+	acpi_handle host_handle = ACPI_HANDLE(ap->host->dev);
+	acpi_handle parent_handle;
+	u64 adr;
+
+	/*
+	 * For both sata/pata devices, host handle is required.
+	 * For pata device, port handle is also required.
+	 */
+	if (libata_noacpi || !host_handle ||
+			(!(ap->flags & ATA_FLAG_ACPI_SATA) && !port_handle))
+		return;
+
+	if (ap->flags & ATA_FLAG_ACPI_SATA) {
+		if (!sata_pmp_attached(ap))
+			adr = SATA_ADR(ap->port_no, NO_PORT_MULT);
+		else
+			adr = SATA_ADR(ap->port_no, dev->link->pmp);
+		parent_handle = host_handle;
+	} else {
+		adr = dev->devno;
+		parent_handle = port_handle;
 	}
+
+	ACPI_HANDLE_SET(&dev->tdev, acpi_get_child(parent_handle, adr));
+
+	register_hotplug_dock_device(ata_dev_acpi_handle(dev),
+				     &ata_acpi_dev_dock_ops, dev, NULL, NULL);
 }
 
 /**
@@ -270,18 +249,34 @@ void ata_acpi_dissociate(struct ata_host *host)
 		struct ata_port *ap = host->ports[i];
 		const struct ata_acpi_gtm *gtm = ata_acpi_init_gtm(ap);
 
-		if (ata_ap_acpi_handle(ap) && gtm)
+		if (ACPI_HANDLE(&ap->tdev) && gtm)
 			ata_acpi_stm(ap, gtm);
 	}
 }
 
-static int __ata_acpi_gtm(struct ata_port *ap, acpi_handle handle,
-			  struct ata_acpi_gtm *gtm)
+/**
+ * ata_acpi_gtm - execute _GTM
+ * @ap: target ATA port
+ * @gtm: out parameter for _GTM result
+ *
+ * Evaluate _GTM and store the result in @gtm.
+ *
+ * LOCKING:
+ * EH context.
+ *
+ * RETURNS:
+ * 0 on success, -ENOENT if _GTM doesn't exist, -errno on failure.
+ */
+int ata_acpi_gtm(struct ata_port *ap, struct ata_acpi_gtm *gtm)
 {
 	struct acpi_buffer output = { .length = ACPI_ALLOCATE_BUFFER };
 	union acpi_object *out_obj;
 	acpi_status status;
 	int rc = 0;
+	acpi_handle handle = ACPI_HANDLE(&ap->tdev);
+
+	if (!handle)
+		return -EINVAL;
 
 	status = acpi_evaluate_object(handle, "_GTM", NULL, &output);
 
@@ -317,27 +312,6 @@ static int __ata_acpi_gtm(struct ata_port *ap, acpi_handle handle,
 	return rc;
 }
 
-/**
- * ata_acpi_gtm - execute _GTM
- * @ap: target ATA port
- * @gtm: out parameter for _GTM result
- *
- * Evaluate _GTM and store the result in @gtm.
- *
- * LOCKING:
- * EH context.
- *
- * RETURNS:
- * 0 on success, -ENOENT if _GTM doesn't exist, -errno on failure.
- */
-int ata_acpi_gtm(struct ata_port *ap, struct ata_acpi_gtm *gtm)
-{
-	if (ata_ap_acpi_handle(ap))
-		return __ata_acpi_gtm(ap, ata_ap_acpi_handle(ap), gtm);
-	else
-		return -EINVAL;
-}
-
 EXPORT_SYMBOL_GPL(ata_acpi_gtm);
 
 /**
@@ -374,8 +348,8 @@ int ata_acpi_stm(struct ata_port *ap, const struct ata_acpi_gtm *stm)
 	input.count = 3;
 	input.pointer = in_params;
 
-	status = acpi_evaluate_object(ata_ap_acpi_handle(ap), "_STM", &input,
-				      NULL);
+	status = acpi_evaluate_object(ACPI_HANDLE(&ap->tdev), "_STM",
+				      &input, NULL);
 
 	if (status == AE_NOT_FOUND)
 		return -ENOENT;
@@ -850,7 +824,7 @@ void ata_acpi_on_resume(struct ata_port *ap)
 	const struct ata_acpi_gtm *gtm = ata_acpi_init_gtm(ap);
 	struct ata_device *dev;
 
-	if (ata_ap_acpi_handle(ap) && gtm) {
+	if (ACPI_HANDLE(&ap->tdev) && gtm) {
 		/* _GTM valid */
 
 		/* restore timing parameters */
@@ -894,8 +868,7 @@ static int ata_acpi_choose_suspend_state(struct ata_device *dev, bool runtime)
 		d_max_in = ACPI_STATE_D3_HOT;
 
 out:
-	return acpi_pm_device_sleep_state(&dev->sdev->sdev_gendev,
-					  NULL, d_max_in);
+	return acpi_pm_device_sleep_state(&dev->tdev, NULL, d_max_in);
 }
 
 static void sata_acpi_set_state(struct ata_port *ap, pm_message_t state)
@@ -932,7 +905,7 @@ static void pata_acpi_set_state(struct ata_port *ap, pm_message_t state)
 	struct ata_device *dev;
 	acpi_handle port_handle;
 
-	port_handle = ata_ap_acpi_handle(ap);
+	port_handle = ACPI_HANDLE(&ap->tdev);
 	if (!port_handle)
 		return;
 
@@ -947,11 +920,11 @@ static void pata_acpi_set_state(struct ata_port *ap, pm_message_t state)
 			continue;
 
 		acpi_bus_set_power(dev_handle, state.event & PM_EVENT_RESUME ?
-						ACPI_STATE_D0 : ACPI_STATE_D3);
+					ACPI_STATE_D0 : ACPI_STATE_D3_COLD);
 	}
 
 	if (!(state.event & PM_EVENT_RESUME))
-		acpi_bus_set_power(port_handle, ACPI_STATE_D3);
+		acpi_bus_set_power(port_handle, ACPI_STATE_D3_COLD);
 }
 
 /**
@@ -1062,110 +1035,3 @@ void ata_acpi_on_disable(struct ata_device *dev)
 {
 	ata_acpi_clear_gtf(dev);
 }
-
-static int compat_pci_ata(struct ata_port *ap)
-{
-	struct device *dev = ap->tdev.parent;
-	struct pci_dev *pdev;
-
-	if (!is_pci_dev(dev))
-		return 0;
-
-	pdev = to_pci_dev(dev);
-
-	if ((pdev->class >> 8) != PCI_CLASS_STORAGE_SATA &&
-	    (pdev->class >> 8) != PCI_CLASS_STORAGE_IDE)
-		return 0;
-
-	return 1;
-}
-
-static int ata_acpi_bind_host(struct ata_port *ap, acpi_handle *handle)
-{
-	if (libata_noacpi || ap->flags & ATA_FLAG_ACPI_SATA)
-		return -ENODEV;
-
-	*handle = acpi_get_child(DEVICE_ACPI_HANDLE(ap->tdev.parent),
-			ap->port_no);
-
-	if (!*handle)
-		return -ENODEV;
-
-	if (__ata_acpi_gtm(ap, *handle, &ap->__acpi_init_gtm) == 0)
-		ap->pflags |= ATA_PFLAG_INIT_GTM_VALID;
-
-	return 0;
-}
-
-static int ata_acpi_bind_device(struct ata_port *ap, struct scsi_device *sdev,
-				acpi_handle *handle)
-{
-	struct ata_device *ata_dev;
-
-	if (ap->flags & ATA_FLAG_ACPI_SATA) {
-		if (!sata_pmp_attached(ap))
-			ata_dev = &ap->link.device[sdev->id];
-		else
-			ata_dev = &ap->pmp_link[sdev->channel].device[sdev->id];
-	}
-	else {
-		ata_dev = &ap->link.device[sdev->id];
-	}
-
-	*handle = ata_dev_acpi_handle(ata_dev);
-
-	if (!*handle)
-		return -ENODEV;
-
-	return 0;
-}
-
-static int is_ata_port(const struct device *dev)
-{
-	return dev->type == &ata_port_type;
-}
-
-static struct ata_port *dev_to_ata_port(struct device *dev)
-{
-	while (!is_ata_port(dev)) {
-		if (!dev->parent)
-			return NULL;
-		dev = dev->parent;
-	}
-	return to_ata_port(dev);
-}
-
-static int ata_acpi_find_device(struct device *dev, acpi_handle *handle)
-{
-	struct ata_port *ap = dev_to_ata_port(dev);
-
-	if (!ap)
-		return -ENODEV;
-
-	if (!compat_pci_ata(ap))
-		return -ENODEV;
-
-	if (scsi_is_host_device(dev))
-		return ata_acpi_bind_host(ap, handle);
-	else if (scsi_is_sdev_device(dev)) {
-		struct scsi_device *sdev = to_scsi_device(dev);
-
-		return ata_acpi_bind_device(ap, sdev, handle);
-	} else
-		return -ENODEV;
-}
-
-static struct acpi_bus_type ata_acpi_bus = {
-	.name = "ATA",
-	.find_device = ata_acpi_find_device,
-};
-
-int ata_acpi_register(void)
-{
-	return scsi_register_acpi_bus_type(&ata_acpi_bus);
-}
-
-void ata_acpi_unregister(void)
-{
-	scsi_unregister_acpi_bus_type(&ata_acpi_bus);
-}
diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index c24354d44f3d..83b1a9fb2d44 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -569,10 +569,10 @@ void ata_tf_to_fis(const struct ata_taskfile *tf, u8 pmp, int is_cmd, u8 *fis)
 	fis[14] = 0;
 	fis[15] = tf->ctl;
 
-	fis[16] = 0;
-	fis[17] = 0;
-	fis[18] = 0;
-	fis[19] = 0;
+	fis[16] = tf->auxiliary & 0xff;
+	fis[17] = (tf->auxiliary >> 8) & 0xff;
+	fis[18] = (tf->auxiliary >> 16) & 0xff;
+	fis[19] = (tf->auxiliary >> 24) & 0xff;
 }
 
 /**
@@ -2139,6 +2139,22 @@ static int ata_dev_config_ncq(struct ata_device *dev,
 	else
 		snprintf(desc, desc_sz, "NCQ (depth %d/%d)%s", hdepth,
 			ddepth, aa_desc);
+
+	if ((ap->flags & ATA_FLAG_FPDMA_AUX) &&
+	    ata_id_has_ncq_send_and_recv(dev->id)) {
+		err_mask = ata_read_log_page(dev, ATA_LOG_NCQ_SEND_RECV,
+					     0, ap->sector_buf, 1);
+		if (err_mask) {
+			ata_dev_dbg(dev,
+				    "failed to get NCQ Send/Recv Log Emask 0x%x\n",
+				    err_mask);
+		} else {
+			dev->flags |= ATA_DFLAG_NCQ_SEND_RECV;
+			memcpy(dev->ncq_send_recv_cmds, ap->sector_buf,
+				ATA_LOG_NCQ_SEND_RECV_SIZE);
+		}
+	}
+
 	return 0;
 }
 
@@ -6150,8 +6166,6 @@ int ata_host_register(struct ata_host *host, struct scsi_host_template *sht)
 	if (rc)
 		goto err_tadd;
 
-	ata_acpi_hotplug_init(host);
-
 	/* set cable, sata_spd_limit and report */
 	for (i = 0; i < host->n_ports; i++) {
 		struct ata_port *ap = host->ports[i];
@@ -6632,8 +6646,6 @@ static int __init ata_init(void)
 
 	ata_parse_force_param();
 
-	ata_acpi_register();
-
 	rc = ata_sff_init();
 	if (rc) {
 		kfree(ata_force_tbl);
@@ -6660,7 +6672,6 @@ static void __exit ata_exit(void)
 	ata_release_transport(ata_scsi_transport_template);
 	libata_transport_exit();
 	ata_sff_exit();
-	ata_acpi_unregister();
 	kfree(ata_force_tbl);
 }
 
diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index b1e880a3c3da..db6dfcfa3e2e 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -49,7 +49,6 @@
 #include <linux/hdreg.h>
 #include <linux/uaccess.h>
 #include <linux/suspend.h>
-#include <linux/pm_qos.h>
 #include <asm/unaligned.h>
 
 #include "libata.h"
@@ -3100,12 +3099,25 @@ static unsigned int ata_scsi_write_same_xlat(struct ata_queued_cmd *qc)
 	buf = page_address(sg_page(scsi_sglist(scmd)));
 	size = ata_set_lba_range_entries(buf, 512, block, n_block);
 
-	tf->protocol = ATA_PROT_DMA;
-	tf->hob_feature = 0;
-	tf->feature = ATA_DSM_TRIM;
-	tf->hob_nsect = (size / 512) >> 8;
-	tf->nsect = size / 512;
-	tf->command = ATA_CMD_DSM;
+	if (ata_ncq_enabled(dev) && ata_fpdma_dsm_supported(dev)) {
+		/* Newer devices support queued TRIM commands */
+		tf->protocol = ATA_PROT_NCQ;
+		tf->command = ATA_CMD_FPDMA_SEND;
+		tf->hob_nsect = ATA_SUBCMD_FPDMA_SEND_DSM & 0x1f;
+		tf->nsect = qc->tag << 3;
+		tf->hob_feature = (size / 512) >> 8;
+		tf->feature = size / 512;
+
+		tf->auxiliary = 1;
+	} else {
+		tf->protocol = ATA_PROT_DMA;
+		tf->hob_feature = 0;
+		tf->feature = ATA_DSM_TRIM;
+		tf->hob_nsect = (size / 512) >> 8;
+		tf->nsect = size / 512;
+		tf->command = ATA_CMD_DSM;
+	}
+
 	tf->flags |= ATA_TFLAG_ISADDR | ATA_TFLAG_DEVICE | ATA_TFLAG_LBA48 |
 		     ATA_TFLAG_WRITE;
 
@@ -3667,9 +3679,6 @@ void ata_scsi_scan_host(struct ata_port *ap, int sync)
 			if (!IS_ERR(sdev)) {
 				dev->sdev = sdev;
 				scsi_device_put(sdev);
-				if (zpodd_dev_enabled(dev))
-					dev_pm_qos_expose_flags(
-							&sdev->sdev_gendev, 0);
 			} else {
 				dev->sdev = NULL;
 			}
@@ -3766,9 +3775,6 @@ static void ata_scsi_remove_dev(struct ata_device *dev)
 	mutex_lock(&ap->scsi_host->scan_mutex);
 	spin_lock_irqsave(ap->lock, flags);
 
-	if (zpodd_dev_enabled(dev))
-		zpodd_exit(dev);
-
 	/* clearing dev->sdev is protected by host lock */
 	sdev = dev->sdev;
 	dev->sdev = NULL;
@@ -3818,6 +3824,9 @@ static void ata_scsi_handle_link_detach(struct ata_link *link)
 		dev->flags &= ~ATA_DFLAG_DETACHED;
 		spin_unlock_irqrestore(ap->lock, flags);
 
+		if (zpodd_dev_enabled(dev))
+			zpodd_exit(dev);
+
 		ata_scsi_remove_dev(dev);
 	}
 }
diff --git a/drivers/ata/libata-transport.c b/drivers/ata/libata-transport.c
index 077a856f5fd0..150a917f0c3c 100644
--- a/drivers/ata/libata-transport.c
+++ b/drivers/ata/libata-transport.c
@@ -287,6 +287,7 @@ int ata_tport_add(struct device *parent,
 	dev->release = ata_tport_release;
 	dev_set_name(dev, "ata%d", ap->print_id);
 	transport_setup_device(dev);
+	ata_acpi_bind_port(ap);
 	error = device_add(dev);
 	if (error) {
 		goto tport_err;
@@ -644,6 +645,7 @@ static int ata_tdev_add(struct ata_device *ata_dev)
 		dev_set_name(dev, "dev%d.%d.0", ap->print_id, link->pmp);
 
 	transport_setup_device(dev);
+	ata_acpi_bind_dev(ata_dev);
 	error = device_add(dev);
 	if (error) {
 		ata_tdev_free(ata_dev);
diff --git a/drivers/ata/libata-zpodd.c b/drivers/ata/libata-zpodd.c
index cd8daf47188b..68f9e3293e9c 100644
--- a/drivers/ata/libata-zpodd.c
+++ b/drivers/ata/libata-zpodd.c
@@ -2,6 +2,7 @@
 #include <linux/cdrom.h>
 #include <linux/pm_runtime.h>
 #include <linux/module.h>
+#include <linux/pm_qos.h>
 #include <scsi/scsi_device.h>
 
 #include "libata.h"
@@ -190,8 +191,8 @@ void zpodd_enable_run_wake(struct ata_device *dev)
 	sdev_disable_disk_events(dev->sdev);
 
 	zpodd->powered_off = true;
-	device_set_run_wake(&dev->sdev->sdev_gendev, true);
-	acpi_pm_device_run_wake(&dev->sdev->sdev_gendev, true);
+	device_set_run_wake(&dev->tdev, true);
+	acpi_pm_device_run_wake(&dev->tdev, true);
 }
 
 /* Disable runtime wake capability if it is enabled */
@@ -200,8 +201,8 @@ void zpodd_disable_run_wake(struct ata_device *dev)
 	struct zpodd *zpodd = dev->zpodd;
 
 	if (zpodd->powered_off) {
-		acpi_pm_device_run_wake(&dev->sdev->sdev_gendev, false);
-		device_set_run_wake(&dev->sdev->sdev_gendev, false);
+		acpi_pm_device_run_wake(&dev->tdev, false);
+		device_set_run_wake(&dev->tdev, false);
 	}
 }
 
@@ -262,7 +263,7 @@ static void ata_acpi_add_pm_notifier(struct ata_device *dev)
 
 static void ata_acpi_remove_pm_notifier(struct ata_device *dev)
 {
-	acpi_handle handle = DEVICE_ACPI_HANDLE(&dev->sdev->sdev_gendev);
+	acpi_handle handle = ata_dev_acpi_handle(dev);
 	acpi_remove_notify_handler(handle, ACPI_SYSTEM_NOTIFY, zpodd_wake_dev);
 }
 
@@ -290,6 +291,7 @@ void zpodd_init(struct ata_device *dev)
 	ata_acpi_add_pm_notifier(dev);
 	zpodd->dev = dev;
 	dev->zpodd = zpodd;
+	dev_pm_qos_expose_flags(&dev->tdev, 0);
 }
 
 void zpodd_exit(struct ata_device *dev)
diff --git a/drivers/ata/libata.h b/drivers/ata/libata.h
index 577d902bc4de..45b5ab3a95d5 100644
--- a/drivers/ata/libata.h
+++ b/drivers/ata/libata.h
@@ -118,11 +118,9 @@ extern void ata_acpi_on_resume(struct ata_port *ap);
 extern int ata_acpi_on_devcfg(struct ata_device *dev);
 extern void ata_acpi_on_disable(struct ata_device *dev);
 extern void ata_acpi_set_state(struct ata_port *ap, pm_message_t state);
-extern int ata_acpi_register(void);
-extern void ata_acpi_unregister(void);
-extern void ata_acpi_bind(struct ata_device *dev);
-extern void ata_acpi_unbind(struct ata_device *dev);
-extern void ata_acpi_hotplug_init(struct ata_host *host);
+extern void ata_acpi_bind_port(struct ata_port *ap);
+extern void ata_acpi_bind_dev(struct ata_device *dev);
+extern acpi_handle ata_dev_acpi_handle(struct ata_device *dev);
 #else
 static inline void ata_acpi_dissociate(struct ata_host *host) { }
 static inline int ata_acpi_on_suspend(struct ata_port *ap) { return 0; }
@@ -131,11 +129,8 @@ static inline int ata_acpi_on_devcfg(struct ata_device *dev) { return 0; }
 static inline void ata_acpi_on_disable(struct ata_device *dev) { }
 static inline void ata_acpi_set_state(struct ata_port *ap,
 				      pm_message_t state) { }
-static inline int ata_acpi_register(void) { return 0; }
-static inline void ata_acpi_unregister(void) { }
-static inline void ata_acpi_bind(struct ata_device *dev) { }
-static inline void ata_acpi_unbind(struct ata_device *dev) { }
-static inline void ata_acpi_hotplug_init(struct ata_host *host) {}
+static inline void ata_acpi_bind_port(struct ata_port *ap) {}
+static inline void ata_acpi_bind_dev(struct ata_device *dev) {}
 #endif
 
 /* libata-scsi.c */
diff --git a/drivers/ata/pata_acpi.c b/drivers/ata/pata_acpi.c
index 09723b76beac..73212c9c6d5b 100644
--- a/drivers/ata/pata_acpi.c
+++ b/drivers/ata/pata_acpi.c
@@ -39,7 +39,7 @@ static int pacpi_pre_reset(struct ata_link *link, unsigned long deadline)
 {
 	struct ata_port *ap = link->ap;
 	struct pata_acpi *acpi = ap->private_data;
-	if (ata_ap_acpi_handle(ap) == NULL || ata_acpi_gtm(ap, &acpi->gtm) < 0)
+	if (ACPI_HANDLE(&ap->tdev) == NULL || ata_acpi_gtm(ap, &acpi->gtm) < 0)
 		return -ENODEV;
 
 	return ata_sff_prereset(link, deadline);
@@ -195,7 +195,7 @@ static int pacpi_port_start(struct ata_port *ap)
 	struct pci_dev *pdev = to_pci_dev(ap->host->dev);
 	struct pata_acpi *acpi;
 
-	if (ata_ap_acpi_handle(ap) == NULL)
+	if (ACPI_HANDLE(&ap->tdev) == NULL)
 		return -ENODEV;
 
 	acpi = ap->private_data = devm_kzalloc(&pdev->dev, sizeof(struct pata_acpi), GFP_KERNEL);
diff --git a/drivers/ata/pata_arasan_cf.c b/drivers/ata/pata_arasan_cf.c
index 848ed3254ddd..853f610af28f 100644
--- a/drivers/ata/pata_arasan_cf.c
+++ b/drivers/ata/pata_arasan_cf.c
@@ -654,7 +654,7 @@ static void arasan_cf_freeze(struct ata_port *ap)
 	ata_sff_freeze(ap);
 }
 
-void arasan_cf_error_handler(struct ata_port *ap)
+static void arasan_cf_error_handler(struct ata_port *ap)
 {
 	struct arasan_cf_dev *acdev = ap->host->private_data;
 
@@ -683,7 +683,7 @@ static void arasan_cf_dma_start(struct arasan_cf_dev *acdev)
 	ata_sff_queue_work(&acdev->work);
 }
 
-unsigned int arasan_cf_qc_issue(struct ata_queued_cmd *qc)
+static unsigned int arasan_cf_qc_issue(struct ata_queued_cmd *qc)
 {
 	struct ata_port *ap = qc->ap;
 	struct arasan_cf_dev *acdev = ap->host->private_data;
diff --git a/drivers/ata/pata_at32.c b/drivers/ata/pata_at32.c
index 8d493b4a0961..d59d5239405f 100644
--- a/drivers/ata/pata_at32.c
+++ b/drivers/ata/pata_at32.c
@@ -271,7 +271,7 @@ static int __init pata_at32_probe(struct platform_device *pdev)
 
 	struct device		 *dev = &pdev->dev;
 	struct at32_ide_info	 *info;
-	struct ide_platform_data *board = pdev->dev.platform_data;
+	struct ide_platform_data *board = dev_get_platdata(&pdev->dev);
 	struct resource		 *res;
 
 	int irq;
diff --git a/drivers/ata/pata_at91.c b/drivers/ata/pata_at91.c
index 5364f97b42c6..d63ee8f41a4f 100644
--- a/drivers/ata/pata_at91.c
+++ b/drivers/ata/pata_at91.c
@@ -315,7 +315,7 @@ static struct ata_port_operations pata_at91_port_ops = {
 
 static int pata_at91_probe(struct platform_device *pdev)
 {
-	struct at91_cf_data *board = pdev->dev.platform_data;
+	struct at91_cf_data *board = dev_get_platdata(&pdev->dev);
 	struct device *dev = &pdev->dev;
 	struct at91_ide_info *info;
 	struct resource *mem_res;
diff --git a/drivers/ata/pata_ixp4xx_cf.c b/drivers/ata/pata_ixp4xx_cf.c
index dcc6b243e525..1ec53f8ca96f 100644
--- a/drivers/ata/pata_ixp4xx_cf.c
+++ b/drivers/ata/pata_ixp4xx_cf.c
@@ -48,7 +48,7 @@ static unsigned int ixp4xx_mmio_data_xfer(struct ata_device *dev,
 	u16 *buf16 = (u16 *) buf;
 	struct ata_port *ap = dev->link->ap;
 	void __iomem *mmio = ap->ioaddr.data_addr;
-	struct ixp4xx_pata_data *data = ap->host->dev->platform_data;
+	struct ixp4xx_pata_data *data = dev_get_platdata(ap->host->dev);
 
 	/* set the expansion bus in 16bit mode and restore
 	 * 8 bit mode after the transaction.
@@ -143,7 +143,7 @@ static int ixp4xx_pata_probe(struct platform_device *pdev)
 	struct resource *cs0, *cs1;
 	struct ata_host *host;
 	struct ata_port *ap;
-	struct ixp4xx_pata_data *data = pdev->dev.platform_data;
+	struct ixp4xx_pata_data *data = dev_get_platdata(&pdev->dev);
 
 	cs0 = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	cs1 = platform_get_resource(pdev, IORESOURCE_MEM, 1);
diff --git a/drivers/ata/pata_octeon_cf.c b/drivers/ata/pata_octeon_cf.c
index e73bef3093d2..c51bbb9ea8e8 100644
--- a/drivers/ata/pata_octeon_cf.c
+++ b/drivers/ata/pata_octeon_cf.c
@@ -1037,7 +1037,7 @@ static void octeon_cf_shutdown(struct device *dev)
 	union cvmx_mio_boot_dma_cfgx dma_cfg;
 	union cvmx_mio_boot_dma_intx dma_int;
 
-	struct octeon_cf_port *cf_port = dev->platform_data;
+	struct octeon_cf_port *cf_port = dev_get_platdata(dev);
 
 	if (cf_port->dma_base) {
 		/* Stop and clear the dma engine.  */
diff --git a/drivers/ata/pata_platform.c b/drivers/ata/pata_platform.c
index 71e093767f4e..02794885de10 100644
--- a/drivers/ata/pata_platform.c
+++ b/drivers/ata/pata_platform.c
@@ -180,7 +180,7 @@ static int pata_platform_probe(struct platform_device *pdev)
 	struct resource *io_res;
 	struct resource *ctl_res;
 	struct resource *irq_res;
-	struct pata_platform_info *pp_info = pdev->dev.platform_data;
+	struct pata_platform_info *pp_info = dev_get_platdata(&pdev->dev);
 
 	/*
 	 * Simple resource validation ..
diff --git a/drivers/ata/pata_pxa.c b/drivers/ata/pata_pxa.c
index 942ef94b29e6..a6f05acad61e 100644
--- a/drivers/ata/pata_pxa.c
+++ b/drivers/ata/pata_pxa.c
@@ -238,7 +238,7 @@ static int pxa_ata_probe(struct platform_device *pdev)
 	struct resource *ctl_res;
 	struct resource *dma_res;
 	struct resource *irq_res;
-	struct pata_pxa_pdata *pdata = pdev->dev.platform_data;
+	struct pata_pxa_pdata *pdata = dev_get_platdata(&pdev->dev);
 	int ret = 0;
 
 	/*
diff --git a/drivers/ata/pata_samsung_cf.c b/drivers/ata/pata_samsung_cf.c
index 6ef27e98c508..898e544a7ae8 100644
--- a/drivers/ata/pata_samsung_cf.c
+++ b/drivers/ata/pata_samsung_cf.c
@@ -241,8 +241,8 @@ static u8 pata_s3c_check_altstatus(struct ata_port *ap)
 /*
  * pata_s3c_data_xfer - Transfer data by PIO
  */
-unsigned int pata_s3c_data_xfer(struct ata_device *dev, unsigned char *buf,
-				unsigned int buflen, int rw)
+static unsigned int pata_s3c_data_xfer(struct ata_device *dev,
+				unsigned char *buf, unsigned int buflen, int rw)
 {
 	struct ata_port *ap = dev->link->ap;
 	struct s3c_ide_info *info = ap->host->private_data;
@@ -418,7 +418,7 @@ static struct ata_port_operations pata_s5p_port_ops = {
 	.set_piomode		= pata_s3c_set_piomode,
 };
 
-static void pata_s3c_enable(void *s3c_ide_regbase, bool state)
+static void pata_s3c_enable(void __iomem *s3c_ide_regbase, bool state)
 {
 	u32 temp = readl(s3c_ide_regbase + S3C_ATA_CTRL);
 	temp = state ? (temp | 1) : (temp & ~1);
@@ -475,7 +475,7 @@ static void pata_s3c_hwinit(struct s3c_ide_info *info,
 
 static int __init pata_s3c_probe(struct platform_device *pdev)
 {
-	struct s3c_ide_platdata *pdata = pdev->dev.platform_data;
+	struct s3c_ide_platdata *pdata = dev_get_platdata(&pdev->dev);
 	struct device *dev = &pdev->dev;
 	struct s3c_ide_info *info;
 	struct resource *res;
@@ -617,7 +617,7 @@ static int pata_s3c_resume(struct device *dev)
 {
 	struct platform_device *pdev = to_platform_device(dev);
 	struct ata_host *host = platform_get_drvdata(pdev);
-	struct s3c_ide_platdata *pdata = pdev->dev.platform_data;
+	struct s3c_ide_platdata *pdata = dev_get_platdata(&pdev->dev);
 	struct s3c_ide_info *info = host->private_data;
 
 	pata_s3c_hwinit(info, pdata);
diff --git a/drivers/ata/sata_highbank.c b/drivers/ata/sata_highbank.c
index e9a4f46d962e..7f5e5d96327f 100644
--- a/drivers/ata/sata_highbank.c
+++ b/drivers/ata/sata_highbank.c
@@ -46,14 +46,19 @@
 #define CR_BUSY				0x0001
 #define CR_START			0x0001
 #define CR_WR_RDN			0x0002
+#define CPHY_TX_INPUT_STS		0x2001
 #define CPHY_RX_INPUT_STS		0x2002
-#define CPHY_SATA_OVERRIDE	 	0x4000
-#define CPHY_OVERRIDE			0x2005
+#define CPHY_SATA_TX_OVERRIDE		0x8000
+#define CPHY_SATA_RX_OVERRIDE	 	0x4000
+#define CPHY_TX_OVERRIDE		0x2004
+#define CPHY_RX_OVERRIDE		0x2005
 #define SPHY_LANE			0x100
 #define SPHY_HALF_RATE			0x0001
 #define CPHY_SATA_DPLL_MODE		0x0700
 #define CPHY_SATA_DPLL_SHIFT		8
 #define CPHY_SATA_DPLL_RESET		(1 << 11)
+#define CPHY_SATA_TX_ATTEN		0x1c00
+#define CPHY_SATA_TX_ATTEN_SHIFT	10
 #define CPHY_PHY_COUNT			6
 #define CPHY_LANE_COUNT			4
 #define CPHY_PORT_COUNT			(CPHY_PHY_COUNT * CPHY_LANE_COUNT)
@@ -66,6 +71,7 @@ struct phy_lane_info {
 	void __iomem *phy_base;
 	u8 lane_mapping;
 	u8 phy_devs;
+	u8 tx_atten;
 };
 static struct phy_lane_info port_data[CPHY_PORT_COUNT];
 
@@ -76,9 +82,11 @@ static DEFINE_SPINLOCK(sgpio_lock);
 #define SGPIO_PINS			3
 #define SGPIO_PORTS			8
 
-/* can be cast as an ahci_host_priv for compatibility with most functions */
 struct ecx_plat_data {
 	u32		n_ports;
+	/* number of extra clocks that the SGPIO PIC controller expects */
+	u32		pre_clocks;
+	u32		post_clocks;
 	unsigned	sgpio_gpio[SGPIO_PINS];
 	u32		sgpio_pattern;
 	u32		port_to_sgpio[SGPIO_PORTS];
@@ -155,6 +163,9 @@ static ssize_t ecx_transmit_led_message(struct ata_port *ap, u32 state,
 	spin_lock_irqsave(&sgpio_lock, flags);
 	ecx_parse_sgpio(pdata, ap->port_no, state);
 	sgpio_out = pdata->sgpio_pattern;
+	for (i = 0; i < pdata->pre_clocks; i++)
+		ecx_led_cycle_clock(pdata);
+
 	gpio_set_value(pdata->sgpio_gpio[SLOAD], 1);
 	ecx_led_cycle_clock(pdata);
 	gpio_set_value(pdata->sgpio_gpio[SLOAD], 0);
@@ -167,6 +178,8 @@ static ssize_t ecx_transmit_led_message(struct ata_port *ap, u32 state,
 		sgpio_out >>= 1;
 		ecx_led_cycle_clock(pdata);
 	}
+	for (i = 0; i < pdata->post_clocks; i++)
+		ecx_led_cycle_clock(pdata);
 
 	/* save off new led state for port/slot */
 	emp->led_state = state;
@@ -201,6 +214,11 @@ static void highbank_set_em_messages(struct device *dev,
 	of_property_read_u32_array(np, "calxeda,led-order",
 						pdata->port_to_sgpio,
 						pdata->n_ports);
+	if (of_property_read_u32(np, "calxeda,pre-clocks", &pdata->pre_clocks))
+		pdata->pre_clocks = 0;
+	if (of_property_read_u32(np, "calxeda,post-clocks",
+				&pdata->post_clocks))
+		pdata->post_clocks = 0;
 
 	/* store em_loc */
 	hpriv->em_loc = 0;
@@ -259,8 +277,27 @@ static void highbank_cphy_disable_overrides(u8 sata_port)
 	if (unlikely(port_data[sata_port].phy_base == NULL))
 		return;
 	tmp = combo_phy_read(sata_port, CPHY_RX_INPUT_STS + lane * SPHY_LANE);
-	tmp &= ~CPHY_SATA_OVERRIDE;
-	combo_phy_write(sata_port, CPHY_OVERRIDE + lane * SPHY_LANE, tmp);
+	tmp &= ~CPHY_SATA_RX_OVERRIDE;
+	combo_phy_write(sata_port, CPHY_RX_OVERRIDE + lane * SPHY_LANE, tmp);
+}
+
+static void cphy_override_tx_attenuation(u8 sata_port, u32 val)
+{
+	u8 lane = port_data[sata_port].lane_mapping;
+	u32 tmp;
+
+	if (val & 0x8)
+		return;
+
+	tmp = combo_phy_read(sata_port, CPHY_TX_INPUT_STS + lane * SPHY_LANE);
+	tmp &= ~CPHY_SATA_TX_OVERRIDE;
+	combo_phy_write(sata_port, CPHY_TX_OVERRIDE + lane * SPHY_LANE, tmp);
+
+	tmp |= CPHY_SATA_TX_OVERRIDE;
+	combo_phy_write(sata_port, CPHY_TX_OVERRIDE + lane * SPHY_LANE, tmp);
+
+	tmp |= (val << CPHY_SATA_TX_ATTEN_SHIFT) & CPHY_SATA_TX_ATTEN;
+	combo_phy_write(sata_port, CPHY_TX_OVERRIDE + lane * SPHY_LANE, tmp);
 }
 
 static void cphy_override_rx_mode(u8 sata_port, u32 val)
@@ -268,21 +305,21 @@ static void cphy_override_rx_mode(u8 sata_port, u32 val)
 	u8 lane = port_data[sata_port].lane_mapping;
 	u32 tmp;
 	tmp = combo_phy_read(sata_port, CPHY_RX_INPUT_STS + lane * SPHY_LANE);
-	tmp &= ~CPHY_SATA_OVERRIDE;
-	combo_phy_write(sata_port, CPHY_OVERRIDE + lane * SPHY_LANE, tmp);
+	tmp &= ~CPHY_SATA_RX_OVERRIDE;
+	combo_phy_write(sata_port, CPHY_RX_OVERRIDE + lane * SPHY_LANE, tmp);
 
-	tmp |= CPHY_SATA_OVERRIDE;
-	combo_phy_write(sata_port, CPHY_OVERRIDE + lane * SPHY_LANE, tmp);
+	tmp |= CPHY_SATA_RX_OVERRIDE;
+	combo_phy_write(sata_port, CPHY_RX_OVERRIDE + lane * SPHY_LANE, tmp);
 
 	tmp &= ~CPHY_SATA_DPLL_MODE;
 	tmp |= val << CPHY_SATA_DPLL_SHIFT;
-	combo_phy_write(sata_port, CPHY_OVERRIDE + lane * SPHY_LANE, tmp);
+	combo_phy_write(sata_port, CPHY_RX_OVERRIDE + lane * SPHY_LANE, tmp);
 
 	tmp |= CPHY_SATA_DPLL_RESET;
-	combo_phy_write(sata_port, CPHY_OVERRIDE + lane * SPHY_LANE, tmp);
+	combo_phy_write(sata_port, CPHY_RX_OVERRIDE + lane * SPHY_LANE, tmp);
 
 	tmp &= ~CPHY_SATA_DPLL_RESET;
-	combo_phy_write(sata_port, CPHY_OVERRIDE + lane * SPHY_LANE, tmp);
+	combo_phy_write(sata_port, CPHY_RX_OVERRIDE + lane * SPHY_LANE, tmp);
 
 	msleep(15);
 }
@@ -299,16 +336,20 @@ static void highbank_cphy_override_lane(u8 sata_port)
 						lane * SPHY_LANE);
 	} while ((tmp & SPHY_HALF_RATE) && (k++ < 1000));
 	cphy_override_rx_mode(sata_port, 3);
+	cphy_override_tx_attenuation(sata_port, port_data[sata_port].tx_atten);
 }
 
 static int highbank_initialize_phys(struct device *dev, void __iomem *addr)
 {
 	struct device_node *sata_node = dev->of_node;
-	int phy_count = 0, phy, port = 0;
+	int phy_count = 0, phy, port = 0, i;
 	void __iomem *cphy_base[CPHY_PHY_COUNT];
 	struct device_node *phy_nodes[CPHY_PHY_COUNT];
+	u32 tx_atten[CPHY_PORT_COUNT];
+
 	memset(port_data, 0, sizeof(struct phy_lane_info) * CPHY_PORT_COUNT);
 	memset(phy_nodes, 0, sizeof(struct device_node*) * CPHY_PHY_COUNT);
+	memset(tx_atten, 0xff, CPHY_PORT_COUNT);
 
 	do {
 		u32 tmp;
@@ -336,6 +377,10 @@ static int highbank_initialize_phys(struct device *dev, void __iomem *addr)
 		of_node_put(phy_data.np);
 		port += 1;
 	} while (port < CPHY_PORT_COUNT);
+	of_property_read_u32_array(sata_node, "calxeda,tx-atten",
+				tx_atten, port);
+	for (i = 0; i < port; i++)
+		port_data[i].tx_atten = (u8) tx_atten[i];
 	return 0;
 }
 
@@ -479,6 +524,9 @@ static int ahci_highbank_probe(struct platform_device *pdev)
 	if (hpriv->cap & HOST_CAP_PMP)
 		pi.flags |= ATA_FLAG_PMP;
 
+	if (hpriv->cap & HOST_CAP_64)
+		dma_set_coherent_mask(dev, DMA_BIT_MASK(64));
+
 	/* CAP.NP sometimes indicate the index of the last enabled
 	 * port, at other times, that of the last possible port, so
 	 * determining the maximum port number requires looking at
diff --git a/drivers/ata/sata_mv.c b/drivers/ata/sata_mv.c
index 35c6b6d09c27..56be31819897 100644
--- a/drivers/ata/sata_mv.c
+++ b/drivers/ata/sata_mv.c
@@ -553,10 +553,15 @@ struct mv_host_priv {
 	u32			irq_mask_offset;
 	u32			unmask_all_irqs;
 
-#if defined(CONFIG_HAVE_CLK)
+	/*
+	 * Needed on some devices that require their clocks to be enabled.
+	 * These are optional: if the platform device does not have any
+	 * clocks, they won't be used.  Also, if the underlying hardware
+	 * does not support the common clock framework (CONFIG_HAVE_CLK=n),
+	 * all the clock operations become no-ops (see clk.h).
+	 */
 	struct clk		*clk;
 	struct clk              **port_clks;
-#endif
 	/*
 	 * These consistent DMA memory pools give us guaranteed
 	 * alignment for hardware-accessed data structures,
@@ -4032,9 +4037,7 @@ static int mv_platform_probe(struct platform_device *pdev)
 	struct resource *res;
 	int n_ports = 0, irq = 0;
 	int rc;
-#if defined(CONFIG_HAVE_CLK)
 	int port;
-#endif
 
 	ata_print_version_once(&pdev->dev, DRV_VERSION);
 
@@ -4058,7 +4061,7 @@ static int mv_platform_probe(struct platform_device *pdev)
 		of_property_read_u32(pdev->dev.of_node, "nr-ports", &n_ports);
 		irq = irq_of_parse_and_map(pdev->dev.of_node, 0);
 	} else {
-		mv_platform_data = pdev->dev.platform_data;
+		mv_platform_data = dev_get_platdata(&pdev->dev);
 		n_ports = mv_platform_data->n_ports;
 		irq = platform_get_irq(pdev, 0);
 	}
@@ -4068,13 +4071,11 @@ static int mv_platform_probe(struct platform_device *pdev)
 
 	if (!host || !hpriv)
 		return -ENOMEM;
-#if defined(CONFIG_HAVE_CLK)
 	hpriv->port_clks = devm_kzalloc(&pdev->dev,
 					sizeof(struct clk *) * n_ports,
 					GFP_KERNEL);
 	if (!hpriv->port_clks)
 		return -ENOMEM;
-#endif
 	host->private_data = hpriv;
 	hpriv->n_ports = n_ports;
 	hpriv->board_idx = chip_soc;
@@ -4084,7 +4085,6 @@ static int mv_platform_probe(struct platform_device *pdev)
 				   resource_size(res));
 	hpriv->base -= SATAHC0_REG_BASE;
 
-#if defined(CONFIG_HAVE_CLK)
 	hpriv->clk = clk_get(&pdev->dev, NULL);
 	if (IS_ERR(hpriv->clk))
 		dev_notice(&pdev->dev, "cannot get optional clkdev\n");
@@ -4098,7 +4098,6 @@ static int mv_platform_probe(struct platform_device *pdev)
 		if (!IS_ERR(hpriv->port_clks[port]))
 			clk_prepare_enable(hpriv->port_clks[port]);
 	}
-#endif
 
 	/*
 	 * (Re-)program MBUS remapping windows if we are asked to.
@@ -4124,7 +4123,6 @@ static int mv_platform_probe(struct platform_device *pdev)
 		return 0;
 
 err:
-#if defined(CONFIG_HAVE_CLK)
 	if (!IS_ERR(hpriv->clk)) {
 		clk_disable_unprepare(hpriv->clk);
 		clk_put(hpriv->clk);
@@ -4135,7 +4133,6 @@ err:
 			clk_put(hpriv->port_clks[port]);
 		}
 	}
-#endif
 
 	return rc;
 }
@@ -4151,13 +4148,10 @@ err:
 static int mv_platform_remove(struct platform_device *pdev)
 {
 	struct ata_host *host = platform_get_drvdata(pdev);
-#if defined(CONFIG_HAVE_CLK)
 	struct mv_host_priv *hpriv = host->private_data;
 	int port;
-#endif
 	ata_host_detach(host);
 
-#if defined(CONFIG_HAVE_CLK)
 	if (!IS_ERR(hpriv->clk)) {
 		clk_disable_unprepare(hpriv->clk);
 		clk_put(hpriv->clk);
@@ -4168,7 +4162,6 @@ static int mv_platform_remove(struct platform_device *pdev)
 			clk_put(hpriv->port_clks[port]);
 		}
 	}
-#endif
 	return 0;
 }
 
@@ -4428,9 +4421,6 @@ static int mv_pci_device_resume(struct pci_dev *pdev)
 #endif
 #endif
 
-static int mv_platform_probe(struct platform_device *pdev);
-static int mv_platform_remove(struct platform_device *pdev);
-
 static int __init mv_init(void)
 {
 	int rc = -ENODEV;
diff --git a/drivers/ata/sata_promise.c b/drivers/ata/sata_promise.c
index 958ba2a420c3..97f4acb54ad6 100644
--- a/drivers/ata/sata_promise.c
+++ b/drivers/ata/sata_promise.c
@@ -2,7 +2,7 @@
  *  sata_promise.c - Promise SATA
  *
  *  Maintained by:  Tejun Heo <tj@kernel.org>
- *		    Mikael Pettersson <mikpe@it.uu.se>
+ *		    Mikael Pettersson
  *  		    Please ALWAYS copy linux-ide@vger.kernel.org
  *		    on emails.
  *
diff --git a/drivers/ata/sata_rcar.c b/drivers/ata/sata_rcar.c
index 8108eb065444..c2d95e9fb971 100644
--- a/drivers/ata/sata_rcar.c
+++ b/drivers/ata/sata_rcar.c
@@ -778,10 +778,6 @@ static int sata_rcar_probe(struct platform_device *pdev)
 	int irq;
 	int ret = 0;
 
-	mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (mem == NULL)
-		return -EINVAL;
-
 	irq = platform_get_irq(pdev, 0);
 	if (irq <= 0)
 		return -EINVAL;
@@ -807,6 +803,7 @@ static int sata_rcar_probe(struct platform_device *pdev)
 
 	host->private_data = priv;
 
+	mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	priv->base = devm_ioremap_resource(&pdev->dev, mem);
 	if (IS_ERR(priv->base)) {
 		ret = PTR_ERR(priv->base);
diff --git a/drivers/atm/he.c b/drivers/atm/he.c
index 507362a76a73..8557adcd34ee 100644
--- a/drivers/atm/he.c
+++ b/drivers/atm/he.c
@@ -1088,15 +1088,8 @@ static int he_start(struct atm_dev *dev)
 	for (i = 0; i < 6; ++i)
 		dev->esi[i] = read_prom_byte(he_dev, MAC_ADDR + i);
 
-	hprintk("%s%s, %x:%x:%x:%x:%x:%x\n",
-				he_dev->prod_id,
-					he_dev->media & 0x40 ? "SM" : "MM",
-						dev->esi[0],
-						dev->esi[1],
-						dev->esi[2],
-						dev->esi[3],
-						dev->esi[4],
-						dev->esi[5]);
+	hprintk("%s%s, %pM\n", he_dev->prod_id,
+		he_dev->media & 0x40 ? "SM" : "MM", dev->esi);
 	he_dev->atm_dev->link_rate = he_is622(he_dev) ?
 						ATM_OC12_PCR : ATM_OC3_PCR;
 
@@ -2872,15 +2865,4 @@ static struct pci_driver he_driver = {
 	.id_table =	he_pci_tbl,
 };
 
-static int __init he_init(void)
-{
-	return pci_register_driver(&he_driver);
-}
-
-static void __exit he_cleanup(void)
-{
-	pci_unregister_driver(&he_driver);
-}
-
-module_init(he_init);
-module_exit(he_cleanup);
+module_pci_driver(he_driver);
diff --git a/drivers/atm/nicstar.c b/drivers/atm/nicstar.c
index 6587dc295eb0..5aca5f4c5458 100644
--- a/drivers/atm/nicstar.c
+++ b/drivers/atm/nicstar.c
@@ -153,7 +153,6 @@ static int ns_ioctl(struct atm_dev *dev, unsigned int cmd, void __user * arg);
 static void which_list(ns_dev * card, struct sk_buff *skb);
 #endif
 static void ns_poll(unsigned long arg);
-static int ns_parse_mac(char *mac, unsigned char *esi);
 static void ns_phy_put(struct atm_dev *dev, unsigned char value,
 		       unsigned long addr);
 static unsigned char ns_phy_get(struct atm_dev *dev, unsigned long addr);
@@ -779,7 +778,7 @@ static int ns_init_card(int i, struct pci_dev *pcidev)
 		return error;
 	}
 
-	if (ns_parse_mac(mac[i], card->atmdev->esi)) {
+	if (mac[i] == NULL || !mac_pton(mac[i], card->atmdev->esi)) {
 		nicstar_read_eprom(card->membase, NICSTAR_EPROM_MAC_ADDR_OFFSET,
 				   card->atmdev->esi, 6);
 		if (memcmp(card->atmdev->esi, "\x00\x00\x00\x00\x00\x00", 6) ==
@@ -2802,29 +2801,6 @@ static void ns_poll(unsigned long arg)
 	PRINTK("nicstar: Leaving ns_poll().\n");
 }
 
-static int ns_parse_mac(char *mac, unsigned char *esi)
-{
-	int i, j;
-	short byte1, byte0;
-
-	if (mac == NULL || esi == NULL)
-		return -1;
-	j = 0;
-	for (i = 0; i < 6; i++) {
-		if ((byte1 = hex_to_bin(mac[j++])) < 0)
-			return -1;
-		if ((byte0 = hex_to_bin(mac[j++])) < 0)
-			return -1;
-		esi[i] = (unsigned char)(byte1 * 16 + byte0);
-		if (i < 5) {
-			if (mac[j++] != ':')
-				return -1;
-		}
-	}
-	return 0;
-}
-
-
 static void ns_phy_put(struct atm_dev *dev, unsigned char value,
 		       unsigned long addr)
 {
diff --git a/drivers/base/Kconfig b/drivers/base/Kconfig
index 5daa2599ed48..e373671652b0 100644
--- a/drivers/base/Kconfig
+++ b/drivers/base/Kconfig
@@ -200,11 +200,9 @@ config DMA_SHARED_BUFFER
 	  APIs extension; the file's descriptor can then be passed on to other
 	  driver.
 
-config CMA
-	bool "Contiguous Memory Allocator"
-	depends on HAVE_DMA_CONTIGUOUS && HAVE_MEMBLOCK
-	select MIGRATION
-	select MEMORY_ISOLATION
+config DMA_CMA
+	bool "DMA Contiguous Memory Allocator"
+	depends on HAVE_DMA_CONTIGUOUS && CMA
 	help
 	  This enables the Contiguous Memory Allocator which allows drivers
 	  to allocate big physically-contiguous blocks of memory for use with
@@ -213,17 +211,7 @@ config CMA
 	  For more information see <include/linux/dma-contiguous.h>.
 	  If unsure, say "n".
 
-if CMA
-
-config CMA_DEBUG
-	bool "CMA debug messages (DEVELOPMENT)"
-	depends on DEBUG_KERNEL
-	help
-	  Turns on debug messages in CMA.  This produces KERN_DEBUG
-	  messages for every CMA call as well as various messages while
-	  processing calls such as dma_alloc_from_contiguous().
-	  This option does not affect warning and error messages.
-
+if  DMA_CMA
 comment "Default contiguous memory area size:"
 
 config CMA_SIZE_MBYTES
diff --git a/drivers/base/Makefile b/drivers/base/Makefile
index 48029aa477d9..94e8a80e87f8 100644
--- a/drivers/base/Makefile
+++ b/drivers/base/Makefile
@@ -6,7 +6,7 @@ obj-y			:= core.o bus.o dd.o syscore.o \
 			   attribute_container.o transport_class.o \
 			   topology.o
 obj-$(CONFIG_DEVTMPFS)	+= devtmpfs.o
-obj-$(CONFIG_CMA) += dma-contiguous.o
+obj-$(CONFIG_DMA_CMA) += dma-contiguous.o
 obj-y			+= power/
 obj-$(CONFIG_HAS_DMA)	+= dma-mapping.o
 obj-$(CONFIG_HAVE_GENERIC_DMA_COHERENT) += dma-coherent.o
diff --git a/drivers/base/base.h b/drivers/base/base.h
index b8bdfe61daa6..2cbc6774f4cd 100644
--- a/drivers/base/base.h
+++ b/drivers/base/base.h
@@ -119,6 +119,16 @@ static inline int driver_match_device(struct device_driver *drv,
 	return drv->bus->match ? drv->bus->match(dev, drv) : 1;
 }
 
+extern int driver_add_groups(struct device_driver *drv,
+			     const struct attribute_group **groups);
+extern void driver_remove_groups(struct device_driver *drv,
+				 const struct attribute_group **groups);
+
+extern int device_add_groups(struct device *dev,
+			     const struct attribute_group **groups);
+extern void device_remove_groups(struct device *dev,
+				 const struct attribute_group **groups);
+
 extern char *make_class_name(const char *name, struct kobject *kobj);
 
 extern int devres_release_all(struct device *dev);
diff --git a/drivers/base/bus.c b/drivers/base/bus.c
index d414331b480e..4c289ab91357 100644
--- a/drivers/base/bus.c
+++ b/drivers/base/bus.c
@@ -17,6 +17,7 @@
 #include <linux/init.h>
 #include <linux/string.h>
 #include <linux/mutex.h>
+#include <linux/sysfs.h>
 #include "base.h"
 #include "power/power.h"
 
@@ -165,8 +166,8 @@ static const struct kset_uevent_ops bus_uevent_ops = {
 static struct kset *bus_kset;
 
 /* Manually detach a device from its associated driver. */
-static ssize_t driver_unbind(struct device_driver *drv,
-			     const char *buf, size_t count)
+static ssize_t unbind_store(struct device_driver *drv, const char *buf,
+			    size_t count)
 {
 	struct bus_type *bus = bus_get(drv->bus);
 	struct device *dev;
@@ -185,15 +186,15 @@ static ssize_t driver_unbind(struct device_driver *drv,
 	bus_put(bus);
 	return err;
 }
-static DRIVER_ATTR(unbind, S_IWUSR, NULL, driver_unbind);
+static DRIVER_ATTR_WO(unbind);
 
 /*
  * Manually attach a device to a driver.
  * Note: the driver must want to bind to the device,
  * it is not possible to override the driver's id table.
  */
-static ssize_t driver_bind(struct device_driver *drv,
-			   const char *buf, size_t count)
+static ssize_t bind_store(struct device_driver *drv, const char *buf,
+			  size_t count)
 {
 	struct bus_type *bus = bus_get(drv->bus);
 	struct device *dev;
@@ -221,7 +222,7 @@ static ssize_t driver_bind(struct device_driver *drv,
 	bus_put(bus);
 	return err;
 }
-static DRIVER_ATTR(bind, S_IWUSR, NULL, driver_bind);
+static DRIVER_ATTR_WO(bind);
 
 static ssize_t show_drivers_autoprobe(struct bus_type *bus, char *buf)
 {
@@ -460,7 +461,7 @@ static int device_add_attrs(struct bus_type *bus, struct device *dev)
 	if (!bus->dev_attrs)
 		return 0;
 
-	for (i = 0; attr_name(bus->dev_attrs[i]); i++) {
+	for (i = 0; bus->dev_attrs[i].attr.name; i++) {
 		error = device_create_file(dev, &bus->dev_attrs[i]);
 		if (error) {
 			while (--i >= 0)
@@ -476,7 +477,7 @@ static void device_remove_attrs(struct bus_type *bus, struct device *dev)
 	int i;
 
 	if (bus->dev_attrs) {
-		for (i = 0; attr_name(bus->dev_attrs[i]); i++)
+		for (i = 0; bus->dev_attrs[i].attr.name; i++)
 			device_remove_file(dev, &bus->dev_attrs[i]);
 	}
 }
@@ -499,6 +500,9 @@ int bus_add_device(struct device *dev)
 		error = device_add_attrs(bus, dev);
 		if (error)
 			goto out_put;
+		error = device_add_groups(dev, bus->dev_groups);
+		if (error)
+			goto out_groups;
 		error = sysfs_create_link(&bus->p->devices_kset->kobj,
 						&dev->kobj, dev_name(dev));
 		if (error)
@@ -513,6 +517,8 @@ int bus_add_device(struct device *dev)
 
 out_subsys:
 	sysfs_remove_link(&bus->p->devices_kset->kobj, dev_name(dev));
+out_groups:
+	device_remove_groups(dev, bus->dev_groups);
 out_id:
 	device_remove_attrs(bus, dev);
 out_put:
@@ -575,6 +581,7 @@ void bus_remove_device(struct device *dev)
 	sysfs_remove_link(&dev->bus->p->devices_kset->kobj,
 			  dev_name(dev));
 	device_remove_attrs(dev->bus, dev);
+	device_remove_groups(dev, dev->bus->dev_groups);
 	if (klist_node_attached(&dev->p->knode_bus))
 		klist_del(&dev->p->knode_bus);
 
@@ -590,7 +597,7 @@ static int driver_add_attrs(struct bus_type *bus, struct device_driver *drv)
 	int i;
 
 	if (bus->drv_attrs) {
-		for (i = 0; attr_name(bus->drv_attrs[i]); i++) {
+		for (i = 0; bus->drv_attrs[i].attr.name; i++) {
 			error = driver_create_file(drv, &bus->drv_attrs[i]);
 			if (error)
 				goto err;
@@ -610,7 +617,7 @@ static void driver_remove_attrs(struct bus_type *bus,
 	int i;
 
 	if (bus->drv_attrs) {
-		for (i = 0; attr_name(bus->drv_attrs[i]); i++)
+		for (i = 0; bus->drv_attrs[i].attr.name; i++)
 			driver_remove_file(drv, &bus->drv_attrs[i]);
 	}
 }
@@ -659,8 +666,8 @@ static void remove_probe_files(struct bus_type *bus)
 	bus_remove_file(bus, &bus_attr_drivers_probe);
 }
 
-static ssize_t driver_uevent_store(struct device_driver *drv,
-				   const char *buf, size_t count)
+static ssize_t uevent_store(struct device_driver *drv, const char *buf,
+			    size_t count)
 {
 	enum kobject_action action;
 
@@ -668,7 +675,7 @@ static ssize_t driver_uevent_store(struct device_driver *drv,
 		kobject_uevent(&drv->p->kobj, action);
 	return count;
 }
-static DRIVER_ATTR(uevent, S_IWUSR, NULL, driver_uevent_store);
+static DRIVER_ATTR_WO(uevent);
 
 /**
  * bus_add_driver - Add a driver to the bus.
@@ -719,6 +726,10 @@ int bus_add_driver(struct device_driver *drv)
 		printk(KERN_ERR "%s: driver_add_attrs(%s) failed\n",
 			__func__, drv->name);
 	}
+	error = driver_add_groups(drv, bus->drv_groups);
+	if (error)
+		printk(KERN_ERR "%s: driver_create_groups(%s) failed\n",
+			__func__, drv->name);
 
 	if (!drv->suppress_bind_attrs) {
 		error = add_bind_files(drv);
@@ -756,6 +767,7 @@ void bus_remove_driver(struct device_driver *drv)
 	if (!drv->suppress_bind_attrs)
 		remove_bind_files(drv);
 	driver_remove_attrs(drv->bus, drv);
+	driver_remove_groups(drv, drv->bus->drv_groups);
 	driver_remove_file(drv, &driver_attr_uevent);
 	klist_remove(&drv->p->knode_bus);
 	pr_debug("bus: '%s': remove driver %s\n", drv->bus->name, drv->name);
@@ -846,7 +858,7 @@ static int bus_add_attrs(struct bus_type *bus)
 	int i;
 
 	if (bus->bus_attrs) {
-		for (i = 0; attr_name(bus->bus_attrs[i]); i++) {
+		for (i = 0; bus->bus_attrs[i].attr.name; i++) {
 			error = bus_create_file(bus, &bus->bus_attrs[i]);
 			if (error)
 				goto err;
@@ -865,11 +877,23 @@ static void bus_remove_attrs(struct bus_type *bus)
 	int i;
 
 	if (bus->bus_attrs) {
-		for (i = 0; attr_name(bus->bus_attrs[i]); i++)
+		for (i = 0; bus->bus_attrs[i].attr.name; i++)
 			bus_remove_file(bus, &bus->bus_attrs[i]);
 	}
 }
 
+static int bus_add_groups(struct bus_type *bus,
+			  const struct attribute_group **groups)
+{
+	return sysfs_create_groups(&bus->p->subsys.kobj, groups);
+}
+
+static void bus_remove_groups(struct bus_type *bus,
+			      const struct attribute_group **groups)
+{
+	sysfs_remove_groups(&bus->p->subsys.kobj, groups);
+}
+
 static void klist_devices_get(struct klist_node *n)
 {
 	struct device_private *dev_prv = to_device_private_bus(n);
@@ -962,10 +986,15 @@ int bus_register(struct bus_type *bus)
 	retval = bus_add_attrs(bus);
 	if (retval)
 		goto bus_attrs_fail;
+	retval = bus_add_groups(bus, bus->bus_groups);
+	if (retval)
+		goto bus_groups_fail;
 
 	pr_debug("bus: '%s': registered\n", bus->name);
 	return 0;
 
+bus_groups_fail:
+	bus_remove_attrs(bus);
 bus_attrs_fail:
 	remove_probe_files(bus);
 bus_probe_files_fail:
@@ -996,6 +1025,7 @@ void bus_unregister(struct bus_type *bus)
 	if (bus->dev_root)
 		device_unregister(bus->dev_root);
 	bus_remove_attrs(bus);
+	bus_remove_groups(bus, bus->bus_groups);
 	remove_probe_files(bus);
 	kset_unregister(bus->p->drivers_kset);
 	kset_unregister(bus->p->devices_kset);
diff --git a/drivers/base/class.c b/drivers/base/class.c
index 3ce845471327..8b7818b80056 100644
--- a/drivers/base/class.c
+++ b/drivers/base/class.c
@@ -135,7 +135,7 @@ static int add_class_attrs(struct class *cls)
 	int error = 0;
 
 	if (cls->class_attrs) {
-		for (i = 0; attr_name(cls->class_attrs[i]); i++) {
+		for (i = 0; cls->class_attrs[i].attr.name; i++) {
 			error = class_create_file(cls, &cls->class_attrs[i]);
 			if (error)
 				goto error;
@@ -154,7 +154,7 @@ static void remove_class_attrs(struct class *cls)
 	int i;
 
 	if (cls->class_attrs) {
-		for (i = 0; attr_name(cls->class_attrs[i]); i++)
+		for (i = 0; cls->class_attrs[i].attr.name; i++)
 			class_remove_file(cls, &cls->class_attrs[i]);
 	}
 }
diff --git a/drivers/base/core.c b/drivers/base/core.c
index 8856d74545d9..34abf4d8a45f 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -26,6 +26,7 @@
 #include <linux/async.h>
 #include <linux/pm_runtime.h>
 #include <linux/netdevice.h>
+#include <linux/sysfs.h>
 
 #include "base.h"
 #include "power/power.h"
@@ -36,9 +37,9 @@ long sysfs_deprecated = 1;
 #else
 long sysfs_deprecated = 0;
 #endif
-static __init int sysfs_deprecated_setup(char *arg)
+static int __init sysfs_deprecated_setup(char *arg)
 {
-	return strict_strtol(arg, 10, &sysfs_deprecated);
+	return kstrtol(arg, 10, &sysfs_deprecated);
 }
 early_param("sysfs.deprecated", sysfs_deprecated_setup);
 #endif
@@ -49,6 +50,28 @@ static struct kobject *dev_kobj;
 struct kobject *sysfs_dev_char_kobj;
 struct kobject *sysfs_dev_block_kobj;
 
+static DEFINE_MUTEX(device_hotplug_lock);
+
+void lock_device_hotplug(void)
+{
+	mutex_lock(&device_hotplug_lock);
+}
+
+void unlock_device_hotplug(void)
+{
+	mutex_unlock(&device_hotplug_lock);
+}
+
+int lock_device_hotplug_sysfs(void)
+{
+	if (mutex_trylock(&device_hotplug_lock))
+		return 0;
+
+	/* Avoid busy looping (5 ms of sleep should do). */
+	msleep(5);
+	return restart_syscall();
+}
+
 #ifdef CONFIG_BLOCK
 static inline int device_is_not_partition(struct device *dev)
 {
@@ -345,7 +368,7 @@ static const struct kset_uevent_ops device_uevent_ops = {
 	.uevent =	dev_uevent,
 };
 
-static ssize_t show_uevent(struct device *dev, struct device_attribute *attr,
+static ssize_t uevent_show(struct device *dev, struct device_attribute *attr,
 			   char *buf)
 {
 	struct kobject *top_kobj;
@@ -388,7 +411,7 @@ out:
 	return count;
 }
 
-static ssize_t store_uevent(struct device *dev, struct device_attribute *attr,
+static ssize_t uevent_store(struct device *dev, struct device_attribute *attr,
 			    const char *buf, size_t count)
 {
 	enum kobject_action action;
@@ -399,22 +422,20 @@ static ssize_t store_uevent(struct device *dev, struct device_attribute *attr,
 		dev_err(dev, "uevent: unknown action-string\n");
 	return count;
 }
+static DEVICE_ATTR_RW(uevent);
 
-static struct device_attribute uevent_attr =
-	__ATTR(uevent, S_IRUGO | S_IWUSR, show_uevent, store_uevent);
-
-static ssize_t show_online(struct device *dev, struct device_attribute *attr,
+static ssize_t online_show(struct device *dev, struct device_attribute *attr,
 			   char *buf)
 {
 	bool val;
 
-	lock_device_hotplug();
+	device_lock(dev);
 	val = !dev->offline;
-	unlock_device_hotplug();
+	device_unlock(dev);
 	return sprintf(buf, "%u\n", val);
 }
 
-static ssize_t store_online(struct device *dev, struct device_attribute *attr,
+static ssize_t online_store(struct device *dev, struct device_attribute *attr,
 			    const char *buf, size_t count)
 {
 	bool val;
@@ -424,14 +445,15 @@ static ssize_t store_online(struct device *dev, struct device_attribute *attr,
 	if (ret < 0)
 		return ret;
 
-	lock_device_hotplug();
+	ret = lock_device_hotplug_sysfs();
+	if (ret)
+		return ret;
+
 	ret = val ? device_online(dev) : device_offline(dev);
 	unlock_device_hotplug();
 	return ret < 0 ? ret : count;
 }
-
-static struct device_attribute online_attr =
-	__ATTR(online, S_IRUGO | S_IWUSR, show_online, store_online);
+static DEVICE_ATTR_RW(online);
 
 static int device_add_attributes(struct device *dev,
 				 struct device_attribute *attrs)
@@ -440,7 +462,7 @@ static int device_add_attributes(struct device *dev,
 	int i;
 
 	if (attrs) {
-		for (i = 0; attr_name(attrs[i]); i++) {
+		for (i = 0; attrs[i].attr.name; i++) {
 			error = device_create_file(dev, &attrs[i]);
 			if (error)
 				break;
@@ -458,7 +480,7 @@ static void device_remove_attributes(struct device *dev,
 	int i;
 
 	if (attrs)
-		for (i = 0; attr_name(attrs[i]); i++)
+		for (i = 0; attrs[i].attr.name; i++)
 			device_remove_file(dev, &attrs[i]);
 }
 
@@ -469,7 +491,7 @@ static int device_add_bin_attributes(struct device *dev,
 	int i;
 
 	if (attrs) {
-		for (i = 0; attr_name(attrs[i]); i++) {
+		for (i = 0; attrs[i].attr.name; i++) {
 			error = device_create_bin_file(dev, &attrs[i]);
 			if (error)
 				break;
@@ -487,38 +509,19 @@ static void device_remove_bin_attributes(struct device *dev,
 	int i;
 
 	if (attrs)
-		for (i = 0; attr_name(attrs[i]); i++)
+		for (i = 0; attrs[i].attr.name; i++)
 			device_remove_bin_file(dev, &attrs[i]);
 }
 
-static int device_add_groups(struct device *dev,
-			     const struct attribute_group **groups)
+int device_add_groups(struct device *dev, const struct attribute_group **groups)
 {
-	int error = 0;
-	int i;
-
-	if (groups) {
-		for (i = 0; groups[i]; i++) {
-			error = sysfs_create_group(&dev->kobj, groups[i]);
-			if (error) {
-				while (--i >= 0)
-					sysfs_remove_group(&dev->kobj,
-							   groups[i]);
-				break;
-			}
-		}
-	}
-	return error;
+	return sysfs_create_groups(&dev->kobj, groups);
 }
 
-static void device_remove_groups(struct device *dev,
-				 const struct attribute_group **groups)
+void device_remove_groups(struct device *dev,
+			  const struct attribute_group **groups)
 {
-	int i;
-
-	if (groups)
-		for (i = 0; groups[i]; i++)
-			sysfs_remove_group(&dev->kobj, groups[i]);
+	sysfs_remove_groups(&dev->kobj, groups);
 }
 
 static int device_add_attrs(struct device *dev)
@@ -550,7 +553,7 @@ static int device_add_attrs(struct device *dev)
 		goto err_remove_type_groups;
 
 	if (device_supports_offline(dev) && !dev->offline_disabled) {
-		error = device_create_file(dev, &online_attr);
+		error = device_create_file(dev, &dev_attr_online);
 		if (error)
 			goto err_remove_type_groups;
 	}
@@ -578,7 +581,7 @@ static void device_remove_attrs(struct device *dev)
 	struct class *class = dev->class;
 	const struct device_type *type = dev->type;
 
-	device_remove_file(dev, &online_attr);
+	device_remove_file(dev, &dev_attr_online);
 	device_remove_groups(dev, dev->groups);
 
 	if (type)
@@ -591,15 +594,12 @@ static void device_remove_attrs(struct device *dev)
 	}
 }
 
-
-static ssize_t show_dev(struct device *dev, struct device_attribute *attr,
+static ssize_t dev_show(struct device *dev, struct device_attribute *attr,
 			char *buf)
 {
 	return print_dev_t(buf, dev->devt);
 }
-
-static struct device_attribute devt_attr =
-	__ATTR(dev, S_IRUGO, show_dev, NULL);
+static DEVICE_ATTR_RO(dev);
 
 /* /sys/devices/ */
 struct kset *devices_kset;
@@ -626,6 +626,7 @@ int device_create_file(struct device *dev,
 
 	return error;
 }
+EXPORT_SYMBOL_GPL(device_create_file);
 
 /**
  * device_remove_file - remove sysfs attribute file.
@@ -638,6 +639,7 @@ void device_remove_file(struct device *dev,
 	if (dev)
 		sysfs_remove_file(&dev->kobj, &attr->attr);
 }
+EXPORT_SYMBOL_GPL(device_remove_file);
 
 /**
  * device_create_bin_file - create sysfs binary attribute file for device.
@@ -748,6 +750,7 @@ void device_initialize(struct device *dev)
 	device_pm_init(dev);
 	set_dev_node(dev, -1);
 }
+EXPORT_SYMBOL_GPL(device_initialize);
 
 struct kobject *virtual_device_parent(struct device *dev)
 {
@@ -1100,12 +1103,12 @@ int device_add(struct device *dev)
 	if (platform_notify)
 		platform_notify(dev);
 
-	error = device_create_file(dev, &uevent_attr);
+	error = device_create_file(dev, &dev_attr_uevent);
 	if (error)
 		goto attrError;
 
 	if (MAJOR(dev->devt)) {
-		error = device_create_file(dev, &devt_attr);
+		error = device_create_file(dev, &dev_attr_dev);
 		if (error)
 			goto ueventattrError;
 
@@ -1172,9 +1175,9 @@ done:
 		device_remove_sys_dev_entry(dev);
  devtattrError:
 	if (MAJOR(dev->devt))
-		device_remove_file(dev, &devt_attr);
+		device_remove_file(dev, &dev_attr_dev);
  ueventattrError:
-	device_remove_file(dev, &uevent_attr);
+	device_remove_file(dev, &dev_attr_uevent);
  attrError:
 	kobject_uevent(&dev->kobj, KOBJ_REMOVE);
 	kobject_del(&dev->kobj);
@@ -1187,6 +1190,7 @@ name_error:
 	dev->p = NULL;
 	goto done;
 }
+EXPORT_SYMBOL_GPL(device_add);
 
 /**
  * device_register - register a device with the system.
@@ -1211,6 +1215,7 @@ int device_register(struct device *dev)
 	device_initialize(dev);
 	return device_add(dev);
 }
+EXPORT_SYMBOL_GPL(device_register);
 
 /**
  * get_device - increment reference count for device.
@@ -1224,6 +1229,7 @@ struct device *get_device(struct device *dev)
 {
 	return dev ? kobj_to_dev(kobject_get(&dev->kobj)) : NULL;
 }
+EXPORT_SYMBOL_GPL(get_device);
 
 /**
  * put_device - decrement reference count.
@@ -1235,6 +1241,7 @@ void put_device(struct device *dev)
 	if (dev)
 		kobject_put(&dev->kobj);
 }
+EXPORT_SYMBOL_GPL(put_device);
 
 /**
  * device_del - delete device from system.
@@ -1266,7 +1273,7 @@ void device_del(struct device *dev)
 	if (MAJOR(dev->devt)) {
 		devtmpfs_delete_node(dev);
 		device_remove_sys_dev_entry(dev);
-		device_remove_file(dev, &devt_attr);
+		device_remove_file(dev, &dev_attr_dev);
 	}
 	if (dev->class) {
 		device_remove_class_symlinks(dev);
@@ -1281,7 +1288,7 @@ void device_del(struct device *dev)
 		klist_del(&dev->knode_class);
 		mutex_unlock(&dev->class->p->mutex);
 	}
-	device_remove_file(dev, &uevent_attr);
+	device_remove_file(dev, &dev_attr_uevent);
 	device_remove_attrs(dev);
 	bus_remove_device(dev);
 	device_pm_remove(dev);
@@ -1297,6 +1304,7 @@ void device_del(struct device *dev)
 	kobject_del(&dev->kobj);
 	put_device(parent);
 }
+EXPORT_SYMBOL_GPL(device_del);
 
 /**
  * device_unregister - unregister device from system.
@@ -1315,6 +1323,7 @@ void device_unregister(struct device *dev)
 	device_del(dev);
 	put_device(dev);
 }
+EXPORT_SYMBOL_GPL(device_unregister);
 
 static struct device *next_device(struct klist_iter *i)
 {
@@ -1403,6 +1412,7 @@ int device_for_each_child(struct device *parent, void *data,
 	klist_iter_exit(&i);
 	return error;
 }
+EXPORT_SYMBOL_GPL(device_for_each_child);
 
 /**
  * device_find_child - device iterator for locating a particular device.
@@ -1437,6 +1447,7 @@ struct device *device_find_child(struct device *parent, void *data,
 	klist_iter_exit(&i);
 	return child;
 }
+EXPORT_SYMBOL_GPL(device_find_child);
 
 int __init devices_init(void)
 {
@@ -1464,33 +1475,6 @@ int __init devices_init(void)
 	return -ENOMEM;
 }
 
-EXPORT_SYMBOL_GPL(device_for_each_child);
-EXPORT_SYMBOL_GPL(device_find_child);
-
-EXPORT_SYMBOL_GPL(device_initialize);
-EXPORT_SYMBOL_GPL(device_add);
-EXPORT_SYMBOL_GPL(device_register);
-
-EXPORT_SYMBOL_GPL(device_del);
-EXPORT_SYMBOL_GPL(device_unregister);
-EXPORT_SYMBOL_GPL(get_device);
-EXPORT_SYMBOL_GPL(put_device);
-
-EXPORT_SYMBOL_GPL(device_create_file);
-EXPORT_SYMBOL_GPL(device_remove_file);
-
-static DEFINE_MUTEX(device_hotplug_lock);
-
-void lock_device_hotplug(void)
-{
-	mutex_lock(&device_hotplug_lock);
-}
-
-void unlock_device_hotplug(void)
-{
-	mutex_unlock(&device_hotplug_lock);
-}
-
 static int device_check_offline(struct device *dev, void *not_used)
 {
 	int ret;
@@ -2033,7 +2017,7 @@ EXPORT_SYMBOL_GPL(device_move);
  */
 void device_shutdown(void)
 {
-	struct device *dev;
+	struct device *dev, *parent;
 
 	spin_lock(&devices_kset->list_lock);
 	/*
@@ -2050,7 +2034,7 @@ void device_shutdown(void)
 		 * prevent it from being freed because parent's
 		 * lock is to be held
 		 */
-		get_device(dev->parent);
+		parent = get_device(dev->parent);
 		get_device(dev);
 		/*
 		 * Make sure the device is off the kset list, in the
@@ -2060,8 +2044,8 @@ void device_shutdown(void)
 		spin_unlock(&devices_kset->list_lock);
 
 		/* hold lock to avoid race with probe/release */
-		if (dev->parent)
-			device_lock(dev->parent);
+		if (parent)
+			device_lock(parent);
 		device_lock(dev);
 
 		/* Don't allow any more runtime suspends */
@@ -2079,11 +2063,11 @@ void device_shutdown(void)
 		}
 
 		device_unlock(dev);
-		if (dev->parent)
-			device_unlock(dev->parent);
+		if (parent)
+			device_unlock(parent);
 
 		put_device(dev);
-		put_device(dev->parent);
+		put_device(parent);
 
 		spin_lock(&devices_kset->list_lock);
 	}
diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c
index 4c358bc44c72..848ebbd25717 100644
--- a/drivers/base/cpu.c
+++ b/drivers/base/cpu.c
@@ -14,6 +14,7 @@
 #include <linux/slab.h>
 #include <linux/percpu.h>
 #include <linux/acpi.h>
+#include <linux/of.h>
 
 #include "base.h"
 
@@ -43,11 +44,14 @@ static int __ref cpu_subsys_online(struct device *dev)
 	struct cpu *cpu = container_of(dev, struct cpu, dev);
 	int cpuid = dev->id;
 	int from_nid, to_nid;
-	int ret;
+	int ret = -ENODEV;
 
 	cpu_hotplug_driver_lock();
 
 	from_nid = cpu_to_node(cpuid);
+	if (from_nid == NUMA_NO_NODE)
+		goto out;
+
 	ret = cpu_up(cpuid);
 	/*
 	 * When hot adding memory to memoryless node and enabling a cpu
@@ -57,6 +61,7 @@ static int __ref cpu_subsys_online(struct device *dev)
 	if (from_nid != to_nid)
 		change_cpu_under_node(cpu, from_nid, to_nid);
 
+ out:
 	cpu_hotplug_driver_unlock();
 	return ret;
 }
@@ -289,6 +294,7 @@ int register_cpu(struct cpu *cpu, int num)
 	cpu->dev.release = cpu_device_release;
 	cpu->dev.offline_disabled = !cpu->hotpluggable;
 	cpu->dev.offline = !cpu_online(num);
+	cpu->dev.of_node = of_get_cpu_node(num, NULL);
 #ifdef CONFIG_ARCH_HAS_CPU_AUTOPROBE
 	cpu->dev.bus->uevent = arch_cpu_uevent;
 #endif
diff --git a/drivers/base/dma-buf.c b/drivers/base/dma-buf.c
index 6687ba741879..1e16cbd61da2 100644
--- a/drivers/base/dma-buf.c
+++ b/drivers/base/dma-buf.c
@@ -77,9 +77,36 @@ static int dma_buf_mmap_internal(struct file *file, struct vm_area_struct *vma)
 	return dmabuf->ops->mmap(dmabuf, vma);
 }
 
+static loff_t dma_buf_llseek(struct file *file, loff_t offset, int whence)
+{
+	struct dma_buf *dmabuf;
+	loff_t base;
+
+	if (!is_dma_buf_file(file))
+		return -EBADF;
+
+	dmabuf = file->private_data;
+
+	/* only support discovering the end of the buffer,
+	   but also allow SEEK_SET to maintain the idiomatic
+	   SEEK_END(0), SEEK_CUR(0) pattern */
+	if (whence == SEEK_END)
+		base = dmabuf->size;
+	else if (whence == SEEK_SET)
+		base = 0;
+	else
+		return -EINVAL;
+
+	if (offset != 0)
+		return -EINVAL;
+
+	return base + offset;
+}
+
 static const struct file_operations dma_buf_fops = {
 	.release	= dma_buf_release,
 	.mmap		= dma_buf_mmap_internal,
+	.llseek		= dma_buf_llseek,
 };
 
 /*
@@ -133,7 +160,12 @@ struct dma_buf *dma_buf_export_named(void *priv, const struct dma_buf_ops *ops,
 	dmabuf->exp_name = exp_name;
 
 	file = anon_inode_getfile("dmabuf", &dma_buf_fops, dmabuf, flags);
+	if (IS_ERR(file)) {
+		kfree(dmabuf);
+		return ERR_CAST(file);
+	}
 
+	file->f_mode |= FMODE_LSEEK;
 	dmabuf->file = file;
 
 	mutex_init(&dmabuf->lock);
@@ -680,7 +712,7 @@ int dma_buf_debugfs_create_file(const char *name,
 	d = debugfs_create_file(name, S_IRUGO, dma_buf_debugfs_dir,
 			write, &dma_buf_debug_fops);
 
-	return PTR_RET(d);
+	return PTR_ERR_OR_ZERO(d);
 }
 #else
 static inline int dma_buf_init_debugfs(void)
diff --git a/drivers/base/dma-contiguous.c b/drivers/base/dma-contiguous.c
index 0ca54421ce97..99802d6f3c60 100644
--- a/drivers/base/dma-contiguous.c
+++ b/drivers/base/dma-contiguous.c
@@ -96,7 +96,7 @@ static inline __maybe_unused phys_addr_t cma_early_percent_memory(void)
 #endif
 
 /**
- * dma_contiguous_reserve() - reserve area for contiguous memory handling
+ * dma_contiguous_reserve() - reserve area(s) for contiguous memory handling
  * @limit: End address of the reserved memory (optional, 0 for any).
  *
  * This function reserves memory from early allocator. It should be
@@ -124,22 +124,29 @@ void __init dma_contiguous_reserve(phys_addr_t limit)
 #endif
 	}
 
-	if (selected_size) {
+	if (selected_size && !dma_contiguous_default_area) {
 		pr_debug("%s: reserving %ld MiB for global area\n", __func__,
 			 (unsigned long)selected_size / SZ_1M);
 
-		dma_declare_contiguous(NULL, selected_size, 0, limit);
+		dma_contiguous_reserve_area(selected_size, 0, limit,
+					    &dma_contiguous_default_area);
 	}
 };
 
 static DEFINE_MUTEX(cma_mutex);
 
-static __init int cma_activate_area(unsigned long base_pfn, unsigned long count)
+static int __init cma_activate_area(struct cma *cma)
 {
-	unsigned long pfn = base_pfn;
-	unsigned i = count >> pageblock_order;
+	int bitmap_size = BITS_TO_LONGS(cma->count) * sizeof(long);
+	unsigned long base_pfn = cma->base_pfn, pfn = base_pfn;
+	unsigned i = cma->count >> pageblock_order;
 	struct zone *zone;
 
+	cma->bitmap = kzalloc(bitmap_size, GFP_KERNEL);
+
+	if (!cma->bitmap)
+		return -ENOMEM;
+
 	WARN_ON_ONCE(!pfn_valid(pfn));
 	zone = page_zone(pfn_to_page(pfn));
 
@@ -153,92 +160,53 @@ static __init int cma_activate_area(unsigned long base_pfn, unsigned long count)
 		}
 		init_cma_reserved_pageblock(pfn_to_page(base_pfn));
 	} while (--i);
-	return 0;
-}
-
-static __init struct cma *cma_create_area(unsigned long base_pfn,
-				     unsigned long count)
-{
-	int bitmap_size = BITS_TO_LONGS(count) * sizeof(long);
-	struct cma *cma;
-	int ret = -ENOMEM;
-
-	pr_debug("%s(base %08lx, count %lx)\n", __func__, base_pfn, count);
-
-	cma = kmalloc(sizeof *cma, GFP_KERNEL);
-	if (!cma)
-		return ERR_PTR(-ENOMEM);
-
-	cma->base_pfn = base_pfn;
-	cma->count = count;
-	cma->bitmap = kzalloc(bitmap_size, GFP_KERNEL);
 
-	if (!cma->bitmap)
-		goto no_mem;
-
-	ret = cma_activate_area(base_pfn, count);
-	if (ret)
-		goto error;
-
-	pr_debug("%s: returned %p\n", __func__, (void *)cma);
-	return cma;
-
-error:
-	kfree(cma->bitmap);
-no_mem:
-	kfree(cma);
-	return ERR_PTR(ret);
+	return 0;
 }
 
-static struct cma_reserved {
-	phys_addr_t start;
-	unsigned long size;
-	struct device *dev;
-} cma_reserved[MAX_CMA_AREAS] __initdata;
-static unsigned cma_reserved_count __initdata;
+static struct cma cma_areas[MAX_CMA_AREAS];
+static unsigned cma_area_count;
 
 static int __init cma_init_reserved_areas(void)
 {
-	struct cma_reserved *r = cma_reserved;
-	unsigned i = cma_reserved_count;
-
-	pr_debug("%s()\n", __func__);
+	int i;
 
-	for (; i; --i, ++r) {
-		struct cma *cma;
-		cma = cma_create_area(PFN_DOWN(r->start),
-				      r->size >> PAGE_SHIFT);
-		if (!IS_ERR(cma))
-			dev_set_cma_area(r->dev, cma);
+	for (i = 0; i < cma_area_count; i++) {
+		int ret = cma_activate_area(&cma_areas[i]);
+		if (ret)
+			return ret;
 	}
+
 	return 0;
 }
 core_initcall(cma_init_reserved_areas);
 
 /**
- * dma_declare_contiguous() - reserve area for contiguous memory handling
- *			      for particular device
- * @dev:   Pointer to device structure.
- * @size:  Size of the reserved memory.
- * @base:  Start address of the reserved memory (optional, 0 for any).
+ * dma_contiguous_reserve_area() - reserve custom contiguous area
+ * @size: Size of the reserved area (in bytes),
+ * @base: Base address of the reserved area optional, use 0 for any
  * @limit: End address of the reserved memory (optional, 0 for any).
+ * @res_cma: Pointer to store the created cma region.
  *
- * This function reserves memory for specified device. It should be
- * called by board specific code when early allocator (memblock or bootmem)
- * is still activate.
+ * This function reserves memory from early allocator. It should be
+ * called by arch specific code once the early allocator (memblock or bootmem)
+ * has been activated and all other subsystems have already allocated/reserved
+ * memory. This function allows to create custom reserved areas for specific
+ * devices.
  */
-int __init dma_declare_contiguous(struct device *dev, phys_addr_t size,
-				  phys_addr_t base, phys_addr_t limit)
+int __init dma_contiguous_reserve_area(phys_addr_t size, phys_addr_t base,
+				       phys_addr_t limit, struct cma **res_cma)
 {
-	struct cma_reserved *r = &cma_reserved[cma_reserved_count];
+	struct cma *cma = &cma_areas[cma_area_count];
 	phys_addr_t alignment;
+	int ret = 0;
 
 	pr_debug("%s(size %lx, base %08lx, limit %08lx)\n", __func__,
 		 (unsigned long)size, (unsigned long)base,
 		 (unsigned long)limit);
 
 	/* Sanity checks */
-	if (cma_reserved_count == ARRAY_SIZE(cma_reserved)) {
+	if (cma_area_count == ARRAY_SIZE(cma_areas)) {
 		pr_err("Not enough slots for CMA reserved regions!\n");
 		return -ENOSPC;
 	}
@@ -256,7 +224,7 @@ int __init dma_declare_contiguous(struct device *dev, phys_addr_t size,
 	if (base) {
 		if (memblock_is_region_reserved(base, size) ||
 		    memblock_reserve(base, size) < 0) {
-			base = -EBUSY;
+			ret = -EBUSY;
 			goto err;
 		}
 	} else {
@@ -266,7 +234,7 @@ int __init dma_declare_contiguous(struct device *dev, phys_addr_t size,
 		 */
 		phys_addr_t addr = __memblock_alloc_base(size, alignment, limit);
 		if (!addr) {
-			base = -ENOMEM;
+			ret = -ENOMEM;
 			goto err;
 		} else {
 			base = addr;
@@ -277,10 +245,11 @@ int __init dma_declare_contiguous(struct device *dev, phys_addr_t size,
 	 * Each reserved area must be initialised later, when more kernel
 	 * subsystems (like slab allocator) are available.
 	 */
-	r->start = base;
-	r->size = size;
-	r->dev = dev;
-	cma_reserved_count++;
+	cma->base_pfn = PFN_DOWN(base);
+	cma->count = size >> PAGE_SHIFT;
+	*res_cma = cma;
+	cma_area_count++;
+
 	pr_info("CMA: reserved %ld MiB at %08lx\n", (unsigned long)size / SZ_1M,
 		(unsigned long)base);
 
@@ -289,7 +258,7 @@ int __init dma_declare_contiguous(struct device *dev, phys_addr_t size,
 	return 0;
 err:
 	pr_err("CMA: failed to reserve %ld MiB\n", (unsigned long)size / SZ_1M);
-	return base;
+	return ret;
 }
 
 /**
diff --git a/drivers/base/driver.c b/drivers/base/driver.c
index 974e301a1ef0..9e29943e56ca 100644
--- a/drivers/base/driver.c
+++ b/drivers/base/driver.c
@@ -15,6 +15,7 @@
 #include <linux/errno.h>
 #include <linux/slab.h>
 #include <linux/string.h>
+#include <linux/sysfs.h>
 #include "base.h"
 
 static struct device *next_device(struct klist_iter *i)
@@ -123,34 +124,16 @@ void driver_remove_file(struct device_driver *drv,
 }
 EXPORT_SYMBOL_GPL(driver_remove_file);
 
-static int driver_add_groups(struct device_driver *drv,
-			     const struct attribute_group **groups)
+int driver_add_groups(struct device_driver *drv,
+		      const struct attribute_group **groups)
 {
-	int error = 0;
-	int i;
-
-	if (groups) {
-		for (i = 0; groups[i]; i++) {
-			error = sysfs_create_group(&drv->p->kobj, groups[i]);
-			if (error) {
-				while (--i >= 0)
-					sysfs_remove_group(&drv->p->kobj,
-							   groups[i]);
-				break;
-			}
-		}
-	}
-	return error;
+	return sysfs_create_groups(&drv->p->kobj, groups);
 }
 
-static void driver_remove_groups(struct device_driver *drv,
-				 const struct attribute_group **groups)
+void driver_remove_groups(struct device_driver *drv,
+			  const struct attribute_group **groups)
 {
-	int i;
-
-	if (groups)
-		for (i = 0; groups[i]; i++)
-			sysfs_remove_group(&drv->p->kobj, groups[i]);
+	sysfs_remove_groups(&drv->p->kobj, groups);
 }
 
 /**
diff --git a/drivers/base/firmware_class.c b/drivers/base/firmware_class.c
index a439602ea919..10a4467c63f1 100644
--- a/drivers/base/firmware_class.c
+++ b/drivers/base/firmware_class.c
@@ -486,9 +486,8 @@ static struct notifier_block fw_shutdown_nb = {
 	.notifier_call = fw_shutdown_notify,
 };
 
-static ssize_t firmware_timeout_show(struct class *class,
-				     struct class_attribute *attr,
-				     char *buf)
+static ssize_t timeout_show(struct class *class, struct class_attribute *attr,
+			    char *buf)
 {
 	return sprintf(buf, "%d\n", loading_timeout);
 }
@@ -506,9 +505,8 @@ static ssize_t firmware_timeout_show(struct class *class,
  *
  *	Note: zero means 'wait forever'.
  **/
-static ssize_t firmware_timeout_store(struct class *class,
-				      struct class_attribute *attr,
-				      const char *buf, size_t count)
+static ssize_t timeout_store(struct class *class, struct class_attribute *attr,
+			     const char *buf, size_t count)
 {
 	loading_timeout = simple_strtol(buf, NULL, 10);
 	if (loading_timeout < 0)
@@ -518,8 +516,7 @@ static ssize_t firmware_timeout_store(struct class *class,
 }
 
 static struct class_attribute firmware_class_attrs[] = {
-	__ATTR(timeout, S_IWUSR | S_IRUGO,
-		firmware_timeout_show, firmware_timeout_store),
+	__ATTR_RW(timeout),
 	__ATTR_NULL
 };
 
@@ -868,8 +865,15 @@ static int _request_firmware_load(struct firmware_priv *fw_priv, bool uevent,
 		goto err_del_dev;
 	}
 
+	mutex_lock(&fw_lock);
+	list_add(&buf->pending_list, &pending_fw_head);
+	mutex_unlock(&fw_lock);
+
 	retval = device_create_file(f_dev, &dev_attr_loading);
 	if (retval) {
+		mutex_lock(&fw_lock);
+		list_del_init(&buf->pending_list);
+		mutex_unlock(&fw_lock);
 		dev_err(f_dev, "%s: device_create_file failed\n", __func__);
 		goto err_del_bin_attr;
 	}
@@ -884,10 +888,6 @@ static int _request_firmware_load(struct firmware_priv *fw_priv, bool uevent,
 		kobject_uevent(&fw_priv->dev.kobj, KOBJ_ADD);
 	}
 
-	mutex_lock(&fw_lock);
-	list_add(&buf->pending_list, &pending_fw_head);
-	mutex_unlock(&fw_lock);
-
 	wait_for_completion(&buf->completion);
 
 	cancel_delayed_work_sync(&fw_priv->timeout_work);
diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index ec386ee9cb22..bece691cb5d9 100644
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -16,7 +16,6 @@
 #include <linux/capability.h>
 #include <linux/device.h>
 #include <linux/memory.h>
-#include <linux/kobject.h>
 #include <linux/memory_hotplug.h>
 #include <linux/mm.h>
 #include <linux/mutex.h>
@@ -30,6 +29,8 @@ static DEFINE_MUTEX(mem_sysfs_mutex);
 
 #define MEMORY_CLASS_NAME	"memory"
 
+#define to_memory_block(dev) container_of(dev, struct memory_block, dev)
+
 static int sections_per_block;
 
 static inline int base_memory_block_id(int section_nr)
@@ -77,7 +78,7 @@ EXPORT_SYMBOL(unregister_memory_isolate_notifier);
 
 static void memory_block_release(struct device *dev)
 {
-	struct memory_block *mem = container_of(dev, struct memory_block, dev);
+	struct memory_block *mem = to_memory_block(dev);
 
 	kfree(mem);
 }
@@ -110,8 +111,7 @@ static unsigned long get_memory_block_size(void)
 static ssize_t show_mem_start_phys_index(struct device *dev,
 			struct device_attribute *attr, char *buf)
 {
-	struct memory_block *mem =
-		container_of(dev, struct memory_block, dev);
+	struct memory_block *mem = to_memory_block(dev);
 	unsigned long phys_index;
 
 	phys_index = mem->start_section_nr / sections_per_block;
@@ -121,8 +121,7 @@ static ssize_t show_mem_start_phys_index(struct device *dev,
 static ssize_t show_mem_end_phys_index(struct device *dev,
 			struct device_attribute *attr, char *buf)
 {
-	struct memory_block *mem =
-		container_of(dev, struct memory_block, dev);
+	struct memory_block *mem = to_memory_block(dev);
 	unsigned long phys_index;
 
 	phys_index = mem->end_section_nr / sections_per_block;
@@ -137,8 +136,7 @@ static ssize_t show_mem_removable(struct device *dev,
 {
 	unsigned long i, pfn;
 	int ret = 1;
-	struct memory_block *mem =
-		container_of(dev, struct memory_block, dev);
+	struct memory_block *mem = to_memory_block(dev);
 
 	for (i = 0; i < sections_per_block; i++) {
 		if (!present_section_nr(mem->start_section_nr + i))
@@ -156,8 +154,7 @@ static ssize_t show_mem_removable(struct device *dev,
 static ssize_t show_mem_state(struct device *dev,
 			struct device_attribute *attr, char *buf)
 {
-	struct memory_block *mem =
-		container_of(dev, struct memory_block, dev);
+	struct memory_block *mem = to_memory_block(dev);
 	ssize_t len = 0;
 
 	/*
@@ -263,9 +260,8 @@ memory_block_action(unsigned long phys_index, unsigned long action, int online_t
 	return ret;
 }
 
-static int __memory_block_change_state(struct memory_block *mem,
-		unsigned long to_state, unsigned long from_state_req,
-		int online_type)
+static int memory_block_change_state(struct memory_block *mem,
+		unsigned long to_state, unsigned long from_state_req)
 {
 	int ret = 0;
 
@@ -275,106 +271,95 @@ static int __memory_block_change_state(struct memory_block *mem,
 	if (to_state == MEM_OFFLINE)
 		mem->state = MEM_GOING_OFFLINE;
 
-	ret = memory_block_action(mem->start_section_nr, to_state, online_type);
+	ret = memory_block_action(mem->start_section_nr, to_state,
+				mem->online_type);
+
 	mem->state = ret ? from_state_req : to_state;
+
 	return ret;
 }
 
+/* The device lock serializes operations on memory_subsys_[online|offline] */
 static int memory_subsys_online(struct device *dev)
 {
-	struct memory_block *mem = container_of(dev, struct memory_block, dev);
+	struct memory_block *mem = to_memory_block(dev);
 	int ret;
 
-	mutex_lock(&mem->state_mutex);
-
-	ret = mem->state == MEM_ONLINE ? 0 :
-		__memory_block_change_state(mem, MEM_ONLINE, MEM_OFFLINE,
-					    ONLINE_KEEP);
+	if (mem->state == MEM_ONLINE)
+		return 0;
 
-	mutex_unlock(&mem->state_mutex);
-	return ret;
-}
-
-static int memory_subsys_offline(struct device *dev)
-{
-	struct memory_block *mem = container_of(dev, struct memory_block, dev);
-	int ret;
+	/*
+	 * If we are called from store_mem_state(), online_type will be
+	 * set >= 0 Otherwise we were called from the device online
+	 * attribute and need to set the online_type.
+	 */
+	if (mem->online_type < 0)
+		mem->online_type = ONLINE_KEEP;
 
-	mutex_lock(&mem->state_mutex);
+	ret = memory_block_change_state(mem, MEM_ONLINE, MEM_OFFLINE);
 
-	ret = mem->state == MEM_OFFLINE ? 0 :
-		__memory_block_change_state(mem, MEM_OFFLINE, MEM_ONLINE, -1);
+	/* clear online_type */
+	mem->online_type = -1;
 
-	mutex_unlock(&mem->state_mutex);
-	return ret;
-}
-
-static int __memory_block_change_state_uevent(struct memory_block *mem,
-		unsigned long to_state, unsigned long from_state_req,
-		int online_type)
-{
-	int ret = __memory_block_change_state(mem, to_state, from_state_req,
-					      online_type);
-	if (!ret) {
-		switch (mem->state) {
-		case MEM_OFFLINE:
-			kobject_uevent(&mem->dev.kobj, KOBJ_OFFLINE);
-			break;
-		case MEM_ONLINE:
-			kobject_uevent(&mem->dev.kobj, KOBJ_ONLINE);
-			break;
-		default:
-			break;
-		}
-	}
 	return ret;
 }
 
-static int memory_block_change_state(struct memory_block *mem,
-		unsigned long to_state, unsigned long from_state_req,
-		int online_type)
+static int memory_subsys_offline(struct device *dev)
 {
-	int ret;
+	struct memory_block *mem = to_memory_block(dev);
 
-	mutex_lock(&mem->state_mutex);
-	ret = __memory_block_change_state_uevent(mem, to_state, from_state_req,
-						 online_type);
-	mutex_unlock(&mem->state_mutex);
+	if (mem->state == MEM_OFFLINE)
+		return 0;
 
-	return ret;
+	return memory_block_change_state(mem, MEM_OFFLINE, MEM_ONLINE);
 }
+
 static ssize_t
 store_mem_state(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t count)
 {
-	struct memory_block *mem;
-	bool offline;
-	int ret = -EINVAL;
-
-	mem = container_of(dev, struct memory_block, dev);
-
-	lock_device_hotplug();
-
-	if (!strncmp(buf, "online_kernel", min_t(int, count, 13))) {
-		offline = false;
-		ret = memory_block_change_state(mem, MEM_ONLINE,
-						MEM_OFFLINE, ONLINE_KERNEL);
-	} else if (!strncmp(buf, "online_movable", min_t(int, count, 14))) {
-		offline = false;
-		ret = memory_block_change_state(mem, MEM_ONLINE,
-						MEM_OFFLINE, ONLINE_MOVABLE);
-	} else if (!strncmp(buf, "online", min_t(int, count, 6))) {
-		offline = false;
-		ret = memory_block_change_state(mem, MEM_ONLINE,
-						MEM_OFFLINE, ONLINE_KEEP);
-	} else if(!strncmp(buf, "offline", min_t(int, count, 7))) {
-		offline = true;
-		ret = memory_block_change_state(mem, MEM_OFFLINE,
-						MEM_ONLINE, -1);
+	struct memory_block *mem = to_memory_block(dev);
+	int ret, online_type;
+
+	ret = lock_device_hotplug_sysfs();
+	if (ret)
+		return ret;
+
+	if (!strncmp(buf, "online_kernel", min_t(int, count, 13)))
+		online_type = ONLINE_KERNEL;
+	else if (!strncmp(buf, "online_movable", min_t(int, count, 14)))
+		online_type = ONLINE_MOVABLE;
+	else if (!strncmp(buf, "online", min_t(int, count, 6)))
+		online_type = ONLINE_KEEP;
+	else if (!strncmp(buf, "offline", min_t(int, count, 7)))
+		online_type = -1;
+	else {
+		ret = -EINVAL;
+		goto err;
+	}
+
+	switch (online_type) {
+	case ONLINE_KERNEL:
+	case ONLINE_MOVABLE:
+	case ONLINE_KEEP:
+		/*
+		 * mem->online_type is not protected so there can be a
+		 * race here.  However, when racing online, the first
+		 * will succeed and the second will just return as the
+		 * block will already be online.  The online type
+		 * could be either one, but that is expected.
+		 */
+		mem->online_type = online_type;
+		ret = device_online(&mem->dev);
+		break;
+	case -1:
+		ret = device_offline(&mem->dev);
+		break;
+	default:
+		ret = -EINVAL; /* should never happen */
 	}
-	if (!ret)
-		dev->offline = offline;
 
+err:
 	unlock_device_hotplug();
 
 	if (ret)
@@ -394,8 +379,7 @@ store_mem_state(struct device *dev,
 static ssize_t show_phys_device(struct device *dev,
 				struct device_attribute *attr, char *buf)
 {
-	struct memory_block *mem =
-		container_of(dev, struct memory_block, dev);
+	struct memory_block *mem = to_memory_block(dev);
 	return sprintf(buf, "%d\n", mem->phys_device);
 }
 
@@ -471,7 +455,7 @@ store_soft_offline_page(struct device *dev,
 	u64 pfn;
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
-	if (strict_strtoull(buf, 0, &pfn) < 0)
+	if (kstrtoull(buf, 0, &pfn) < 0)
 		return -EINVAL;
 	pfn >>= PAGE_SHIFT;
 	if (!pfn_valid(pfn))
@@ -490,7 +474,7 @@ store_hard_offline_page(struct device *dev,
 	u64 pfn;
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
-	if (strict_strtoull(buf, 0, &pfn) < 0)
+	if (kstrtoull(buf, 0, &pfn) < 0)
 		return -EINVAL;
 	pfn >>= PAGE_SHIFT;
 	ret = memory_failure(pfn, 0, 0);
@@ -527,7 +511,7 @@ struct memory_block *find_memory_block_hinted(struct mem_section *section,
 		put_device(&hint->dev);
 	if (!dev)
 		return NULL;
-	return container_of(dev, struct memory_block, dev);
+	return to_memory_block(dev);
 }
 
 /*
@@ -567,16 +551,13 @@ static const struct attribute_group *memory_memblk_attr_groups[] = {
 static
 int register_memory(struct memory_block *memory)
 {
-	int error;
-
 	memory->dev.bus = &memory_subsys;
 	memory->dev.id = memory->start_section_nr / sections_per_block;
 	memory->dev.release = memory_block_release;
 	memory->dev.groups = memory_memblk_attr_groups;
 	memory->dev.offline = memory->state == MEM_OFFLINE;
 
-	error = device_register(&memory->dev);
-	return error;
+	return device_register(&memory->dev);
 }
 
 static int init_memory_block(struct memory_block **memory,
@@ -597,7 +578,6 @@ static int init_memory_block(struct memory_block **memory,
 	mem->end_section_nr = mem->start_section_nr + sections_per_block - 1;
 	mem->state = state;
 	mem->section_count++;
-	mutex_init(&mem->state_mutex);
 	start_pfn = section_nr_to_pfn(mem->start_section_nr);
 	mem->phys_device = arch_get_memory_phys_device(start_pfn);
 
@@ -607,55 +587,57 @@ static int init_memory_block(struct memory_block **memory,
 	return ret;
 }
 
-static int add_memory_section(int nid, struct mem_section *section,
-			struct memory_block **mem_p,
-			unsigned long state, enum mem_add_context context)
+static int add_memory_block(int base_section_nr)
 {
-	struct memory_block *mem = NULL;
-	int scn_nr = __section_nr(section);
-	int ret = 0;
-
-	mutex_lock(&mem_sysfs_mutex);
-
-	if (context == BOOT) {
-		/* same memory block ? */
-		if (mem_p && *mem_p)
-			if (scn_nr >= (*mem_p)->start_section_nr &&
-			    scn_nr <= (*mem_p)->end_section_nr) {
-				mem = *mem_p;
-				kobject_get(&mem->dev.kobj);
-			}
-	} else
-		mem = find_memory_block(section);
-
-	if (mem) {
-		mem->section_count++;
-		kobject_put(&mem->dev.kobj);
-	} else {
-		ret = init_memory_block(&mem, section, state);
-		/* store memory_block pointer for next loop */
-		if (!ret && context == BOOT)
-			if (mem_p)
-				*mem_p = mem;
-	}
+	struct memory_block *mem;
+	int i, ret, section_count = 0, section_nr;
 
-	if (!ret) {
-		if (context == HOTPLUG &&
-		    mem->section_count == sections_per_block)
-			ret = register_mem_sect_under_node(mem, nid);
+	for (i = base_section_nr;
+	     (i < base_section_nr + sections_per_block) && i < NR_MEM_SECTIONS;
+	     i++) {
+		if (!present_section_nr(i))
+			continue;
+		if (section_count == 0)
+			section_nr = i;
+		section_count++;
 	}
 
-	mutex_unlock(&mem_sysfs_mutex);
-	return ret;
+	if (section_count == 0)
+		return 0;
+	ret = init_memory_block(&mem, __nr_to_section(section_nr), MEM_ONLINE);
+	if (ret)
+		return ret;
+	mem->section_count = section_count;
+	return 0;
 }
 
+
 /*
  * need an interface for the VM to add new memory regions,
  * but without onlining it.
  */
 int register_new_memory(int nid, struct mem_section *section)
 {
-	return add_memory_section(nid, section, NULL, MEM_OFFLINE, HOTPLUG);
+	int ret = 0;
+	struct memory_block *mem;
+
+	mutex_lock(&mem_sysfs_mutex);
+
+	mem = find_memory_block(section);
+	if (mem) {
+		mem->section_count++;
+		put_device(&mem->dev);
+	} else {
+		ret = init_memory_block(&mem, section, MEM_OFFLINE);
+		if (ret)
+			goto out;
+	}
+
+	if (mem->section_count == sections_per_block)
+		ret = register_mem_sect_under_node(mem, nid);
+out:
+	mutex_unlock(&mem_sysfs_mutex);
+	return ret;
 }
 
 #ifdef CONFIG_MEMORY_HOTREMOVE
@@ -665,7 +647,7 @@ unregister_memory(struct memory_block *memory)
 	BUG_ON(memory->dev.bus != &memory_subsys);
 
 	/* drop the ref. we got in remove_memory_block() */
-	kobject_put(&memory->dev.kobj);
+	put_device(&memory->dev);
 	device_unregister(&memory->dev);
 }
 
@@ -682,7 +664,7 @@ static int remove_memory_block(unsigned long node_id,
 	if (mem->section_count == 0)
 		unregister_memory(mem);
 	else
-		kobject_put(&mem->dev.kobj);
+		put_device(&mem->dev);
 
 	mutex_unlock(&mem_sysfs_mutex);
 	return 0;
@@ -735,7 +717,6 @@ int __init memory_dev_init(void)
 	int ret;
 	int err;
 	unsigned long block_sz;
-	struct memory_block *mem = NULL;
 
 	ret = subsys_system_register(&memory_subsys, memory_root_attr_groups);
 	if (ret)
@@ -748,17 +729,13 @@ int __init memory_dev_init(void)
 	 * Create entries for memory sections that were found
 	 * during boot and have been initialized
 	 */
-	for (i = 0; i < NR_MEM_SECTIONS; i++) {
-		if (!present_section_nr(i))
-			continue;
-		/* don't need to reuse memory_block if only one per block */
-		err = add_memory_section(0, __nr_to_section(i),
-				 (sections_per_block == 1) ? NULL : &mem,
-					 MEM_ONLINE,
-					 BOOT);
+	mutex_lock(&mem_sysfs_mutex);
+	for (i = 0; i < NR_MEM_SECTIONS; i += sections_per_block) {
+		err = add_memory_block(i);
 		if (!ret)
 			ret = err;
 	}
+	mutex_unlock(&mem_sysfs_mutex);
 
 out:
 	if (ret)
diff --git a/drivers/base/node.c b/drivers/base/node.c
index 7616a77ca322..bc9f43bf7e29 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -125,13 +125,7 @@ static ssize_t node_read_meminfo(struct device *dev,
 		       nid, K(node_page_state(nid, NR_WRITEBACK)),
 		       nid, K(node_page_state(nid, NR_FILE_PAGES)),
 		       nid, K(node_page_state(nid, NR_FILE_MAPPED)),
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-		       nid, K(node_page_state(nid, NR_ANON_PAGES)
-			+ node_page_state(nid, NR_ANON_TRANSPARENT_HUGEPAGES) *
-			HPAGE_PMD_NR),
-#else
 		       nid, K(node_page_state(nid, NR_ANON_PAGES)),
-#endif
 		       nid, K(node_page_state(nid, NR_SHMEM)),
 		       nid, node_page_state(nid, NR_KERNEL_STACK) *
 				THREAD_SIZE / 1024,
diff --git a/drivers/base/platform.c b/drivers/base/platform.c
index 3c3197a8de41..4f8bef3eb5a8 100644
--- a/drivers/base/platform.c
+++ b/drivers/base/platform.c
@@ -672,11 +672,13 @@ static ssize_t modalias_show(struct device *dev, struct device_attribute *a,
 
 	return (len >= PAGE_SIZE) ? (PAGE_SIZE - 1) : len;
 }
+static DEVICE_ATTR_RO(modalias);
 
-static struct device_attribute platform_dev_attrs[] = {
-	__ATTR_RO(modalias),
-	__ATTR_NULL,
+static struct attribute *platform_dev_attrs[] = {
+	&dev_attr_modalias.attr,
+	NULL,
 };
+ATTRIBUTE_GROUPS(platform_dev);
 
 static int platform_uevent(struct device *dev, struct kobj_uevent_env *env)
 {
@@ -893,7 +895,7 @@ static const struct dev_pm_ops platform_dev_pm_ops = {
 
 struct bus_type platform_bus_type = {
 	.name		= "platform",
-	.dev_attrs	= platform_dev_attrs,
+	.dev_groups	= platform_dev_groups,
 	.match		= platform_match,
 	.uevent		= platform_uevent,
 	.pm		= &platform_dev_pm_ops,
@@ -1054,7 +1056,7 @@ void __init early_platform_driver_register_all(char *class_str)
  * @epdrv: early platform driver structure
  * @id: id to match against
  */
-static  __init struct platform_device *
+static struct platform_device * __init
 early_platform_match(struct early_platform_driver *epdrv, int id)
 {
 	struct platform_device *pd;
@@ -1072,7 +1074,7 @@ early_platform_match(struct early_platform_driver *epdrv, int id)
  * @epdrv: early platform driver structure
  * @id: return true if id or above exists
  */
-static  __init int early_platform_left(struct early_platform_driver *epdrv,
+static int __init early_platform_left(struct early_platform_driver *epdrv,
 				       int id)
 {
 	struct platform_device *pd;
diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index 5a9b6569dd74..9f098a82cf04 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -28,6 +28,7 @@
 #include <linux/sched.h>
 #include <linux/async.h>
 #include <linux/suspend.h>
+#include <trace/events/power.h>
 #include <linux/cpuidle.h>
 #include "../base.h"
 #include "power.h"
@@ -56,6 +57,30 @@ static pm_message_t pm_transition;
 
 static int async_error;
 
+static char *pm_verb(int event)
+{
+	switch (event) {
+	case PM_EVENT_SUSPEND:
+		return "suspend";
+	case PM_EVENT_RESUME:
+		return "resume";
+	case PM_EVENT_FREEZE:
+		return "freeze";
+	case PM_EVENT_QUIESCE:
+		return "quiesce";
+	case PM_EVENT_HIBERNATE:
+		return "hibernate";
+	case PM_EVENT_THAW:
+		return "thaw";
+	case PM_EVENT_RESTORE:
+		return "restore";
+	case PM_EVENT_RECOVER:
+		return "recover";
+	default:
+		return "(unknown PM event)";
+	}
+}
+
 /**
  * device_pm_sleep_init - Initialize system suspend-related device fields.
  * @dev: Device object being initialized.
@@ -172,16 +197,21 @@ static ktime_t initcall_debug_start(struct device *dev)
 }
 
 static void initcall_debug_report(struct device *dev, ktime_t calltime,
-				  int error)
+				  int error, pm_message_t state, char *info)
 {
-	ktime_t delta, rettime;
+	ktime_t rettime;
+	s64 nsecs;
+
+	rettime = ktime_get();
+	nsecs = (s64) ktime_to_ns(ktime_sub(rettime, calltime));
 
 	if (pm_print_times_enabled) {
-		rettime = ktime_get();
-		delta = ktime_sub(rettime, calltime);
 		pr_info("call %s+ returned %d after %Ld usecs\n", dev_name(dev),
-			error, (unsigned long long)ktime_to_ns(delta) >> 10);
+			error, (unsigned long long)nsecs >> 10);
 	}
+
+	trace_device_pm_report_time(dev, info, nsecs, pm_verb(state.event),
+				    error);
 }
 
 /**
@@ -309,30 +339,6 @@ static pm_callback_t pm_noirq_op(const struct dev_pm_ops *ops, pm_message_t stat
 	return NULL;
 }
 
-static char *pm_verb(int event)
-{
-	switch (event) {
-	case PM_EVENT_SUSPEND:
-		return "suspend";
-	case PM_EVENT_RESUME:
-		return "resume";
-	case PM_EVENT_FREEZE:
-		return "freeze";
-	case PM_EVENT_QUIESCE:
-		return "quiesce";
-	case PM_EVENT_HIBERNATE:
-		return "hibernate";
-	case PM_EVENT_THAW:
-		return "thaw";
-	case PM_EVENT_RESTORE:
-		return "restore";
-	case PM_EVENT_RECOVER:
-		return "recover";
-	default:
-		return "(unknown PM event)";
-	}
-}
-
 static void pm_dev_dbg(struct device *dev, pm_message_t state, char *info)
 {
 	dev_dbg(dev, "%s%s%s\n", info, pm_verb(state.event),
@@ -379,7 +385,7 @@ static int dpm_run_callback(pm_callback_t cb, struct device *dev,
 	error = cb(dev);
 	suspend_report_result(cb, error);
 
-	initcall_debug_report(dev, calltime, error);
+	initcall_debug_report(dev, calltime, error, state, info);
 
 	return error;
 }
@@ -1027,7 +1033,8 @@ EXPORT_SYMBOL_GPL(dpm_suspend_end);
  * @cb: Suspend callback to execute.
  */
 static int legacy_suspend(struct device *dev, pm_message_t state,
-			  int (*cb)(struct device *dev, pm_message_t state))
+			  int (*cb)(struct device *dev, pm_message_t state),
+			  char *info)
 {
 	int error;
 	ktime_t calltime;
@@ -1037,7 +1044,7 @@ static int legacy_suspend(struct device *dev, pm_message_t state,
 	error = cb(dev, state);
 	suspend_report_result(cb, error);
 
-	initcall_debug_report(dev, calltime, error);
+	initcall_debug_report(dev, calltime, error, state, info);
 
 	return error;
 }
@@ -1097,7 +1104,8 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async)
 			goto Run;
 		} else if (dev->class->suspend) {
 			pm_dev_dbg(dev, state, "legacy class ");
-			error = legacy_suspend(dev, state, dev->class->suspend);
+			error = legacy_suspend(dev, state, dev->class->suspend,
+						"legacy class ");
 			goto End;
 		}
 	}
@@ -1108,7 +1116,8 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async)
 			callback = pm_op(dev->bus->pm, state);
 		} else if (dev->bus->suspend) {
 			pm_dev_dbg(dev, state, "legacy bus ");
-			error = legacy_suspend(dev, state, dev->bus->suspend);
+			error = legacy_suspend(dev, state, dev->bus->suspend,
+						"legacy bus ");
 			goto End;
 		}
 	}
diff --git a/drivers/base/power/opp.c b/drivers/base/power/opp.c
index c8ec186303db..ef89897c6043 100644
--- a/drivers/base/power/opp.c
+++ b/drivers/base/power/opp.c
@@ -460,6 +460,7 @@ int opp_add(struct device *dev, unsigned long freq, unsigned long u_volt)
 	srcu_notifier_call_chain(&dev_opp->head, OPP_EVENT_ADD, new_opp);
 	return 0;
 }
+EXPORT_SYMBOL_GPL(opp_add);
 
 /**
  * opp_set_availability() - helper to set the availability of an opp
diff --git a/drivers/base/power/sysfs.c b/drivers/base/power/sysfs.c
index a53ebd265701..03e089ade5ce 100644
--- a/drivers/base/power/sysfs.c
+++ b/drivers/base/power/sysfs.c
@@ -206,7 +206,7 @@ static ssize_t autosuspend_delay_ms_store(struct device *dev,
 	if (!dev->power.use_autosuspend)
 		return -EIO;
 
-	if (strict_strtol(buf, 10, &delay) != 0 || delay != (int) delay)
+	if (kstrtol(buf, 10, &delay) != 0 || delay != (int) delay)
 		return -EINVAL;
 
 	device_lock(dev);
diff --git a/drivers/base/regmap/internal.h b/drivers/base/regmap/internal.h
index 29c83160ca29..57f777835d97 100644
--- a/drivers/base/regmap/internal.h
+++ b/drivers/base/regmap/internal.h
@@ -128,9 +128,6 @@ struct regmap {
 	void *cache;
 	u32 cache_dirty;
 
-	unsigned long *cache_present;
-	unsigned int cache_present_nbits;
-
 	struct reg_default *patch;
 	int patch_regs;
 
@@ -203,6 +200,7 @@ int regcache_write(struct regmap *map,
 			unsigned int reg, unsigned int value);
 int regcache_sync(struct regmap *map);
 int regcache_sync_block(struct regmap *map, void *block,
+			unsigned long *cache_present,
 			unsigned int block_base, unsigned int start,
 			unsigned int end);
 
@@ -218,16 +216,6 @@ unsigned int regcache_get_val(struct regmap *map, const void *base,
 bool regcache_set_val(struct regmap *map, void *base, unsigned int idx,
 		      unsigned int val);
 int regcache_lookup_reg(struct regmap *map, unsigned int reg);
-int regcache_set_reg_present(struct regmap *map, unsigned int reg);
-
-static inline bool regcache_reg_present(struct regmap *map, unsigned int reg)
-{
-	if (!map->cache_present)
-		return true;
-	if (reg > map->cache_present_nbits)
-		return false;
-	return map->cache_present[BIT_WORD(reg)] & BIT_MASK(reg);
-}
 
 int _regmap_raw_write(struct regmap *map, unsigned int reg,
 		      const void *val, size_t val_len, bool async);
diff --git a/drivers/base/regmap/regcache-rbtree.c b/drivers/base/regmap/regcache-rbtree.c
index 0fccc99881fd..930cad4e5df8 100644
--- a/drivers/base/regmap/regcache-rbtree.c
+++ b/drivers/base/regmap/regcache-rbtree.c
@@ -29,6 +29,8 @@ struct regcache_rbtree_node {
 	unsigned int base_reg;
 	/* block of adjacent registers */
 	void *block;
+	/* Which registers are present */
+	long *cache_present;
 	/* number of registers available in the block */
 	unsigned int blklen;
 } __attribute__ ((packed));
@@ -57,6 +59,7 @@ static void regcache_rbtree_set_register(struct regmap *map,
 					 struct regcache_rbtree_node *rbnode,
 					 unsigned int idx, unsigned int val)
 {
+	set_bit(idx, rbnode->cache_present);
 	regcache_set_val(map, rbnode->block, idx, val);
 }
 
@@ -146,13 +149,13 @@ static int rbtree_show(struct seq_file *s, void *ignored)
 	map->lock(map->lock_arg);
 
 	mem_size = sizeof(*rbtree_ctx);
-	mem_size += BITS_TO_LONGS(map->cache_present_nbits) * sizeof(long);
 
 	for (node = rb_first(&rbtree_ctx->root); node != NULL;
 	     node = rb_next(node)) {
 		n = container_of(node, struct regcache_rbtree_node, node);
 		mem_size += sizeof(*n);
 		mem_size += (n->blklen * map->cache_word_size);
+		mem_size += BITS_TO_LONGS(n->blklen) * sizeof(long);
 
 		regcache_rbtree_get_base_top_reg(map, n, &base, &top);
 		this_registers = ((top - base) / map->reg_stride) + 1;
@@ -245,6 +248,7 @@ static int regcache_rbtree_exit(struct regmap *map)
 		rbtree_node = rb_entry(next, struct regcache_rbtree_node, node);
 		next = rb_next(&rbtree_node->node);
 		rb_erase(&rbtree_node->node, &rbtree_ctx->root);
+		kfree(rbtree_node->cache_present);
 		kfree(rbtree_node->block);
 		kfree(rbtree_node);
 	}
@@ -265,7 +269,7 @@ static int regcache_rbtree_read(struct regmap *map,
 	rbnode = regcache_rbtree_lookup(map, reg);
 	if (rbnode) {
 		reg_tmp = (reg - rbnode->base_reg) / map->reg_stride;
-		if (!regcache_reg_present(map, reg))
+		if (!test_bit(reg_tmp, rbnode->cache_present))
 			return -ENOENT;
 		*value = regcache_rbtree_get_register(map, rbnode, reg_tmp);
 	} else {
@@ -278,27 +282,45 @@ static int regcache_rbtree_read(struct regmap *map,
 
 static int regcache_rbtree_insert_to_block(struct regmap *map,
 					   struct regcache_rbtree_node *rbnode,
-					   unsigned int pos, unsigned int reg,
+					   unsigned int base_reg,
+					   unsigned int top_reg,
+					   unsigned int reg,
 					   unsigned int value)
 {
+	unsigned int blklen;
+	unsigned int pos, offset;
+	unsigned long *present;
 	u8 *blk;
 
+	blklen = (top_reg - base_reg) / map->reg_stride + 1;
+	pos = (reg - base_reg) / map->reg_stride;
+	offset = (rbnode->base_reg - base_reg) / map->reg_stride;
+
 	blk = krealloc(rbnode->block,
-		       (rbnode->blklen + 1) * map->cache_word_size,
+		       blklen * map->cache_word_size,
 		       GFP_KERNEL);
 	if (!blk)
 		return -ENOMEM;
 
+	present = krealloc(rbnode->cache_present,
+		    BITS_TO_LONGS(blklen) * sizeof(*present), GFP_KERNEL);
+	if (!present) {
+		kfree(blk);
+		return -ENOMEM;
+	}
+
 	/* insert the register value in the correct place in the rbnode block */
-	memmove(blk + (pos + 1) * map->cache_word_size,
-		blk + pos * map->cache_word_size,
-		(rbnode->blklen - pos) * map->cache_word_size);
+	if (pos == 0) {
+		memmove(blk + offset * map->cache_word_size,
+			blk, rbnode->blklen * map->cache_word_size);
+		bitmap_shift_right(present, present, offset, blklen);
+	}
 
 	/* update the rbnode block, its size and the base register */
 	rbnode->block = blk;
-	rbnode->blklen++;
-	if (!pos)
-		rbnode->base_reg = reg;
+	rbnode->blklen = blklen;
+	rbnode->base_reg = base_reg;
+	rbnode->cache_present = present;
 
 	regcache_rbtree_set_register(map, rbnode, pos, value);
 	return 0;
@@ -325,8 +347,8 @@ regcache_rbtree_node_alloc(struct regmap *map, unsigned int reg)
 
 		if (i != map->rd_table->n_yes_ranges) {
 			range = &map->rd_table->yes_ranges[i];
-			rbnode->blklen = range->range_max - range->range_min
-				+ 1;
+			rbnode->blklen = (range->range_max - range->range_min) /
+				map->reg_stride	+ 1;
 			rbnode->base_reg = range->range_min;
 		}
 	}
@@ -338,12 +360,21 @@ regcache_rbtree_node_alloc(struct regmap *map, unsigned int reg)
 
 	rbnode->block = kmalloc(rbnode->blklen * map->cache_word_size,
 				GFP_KERNEL);
-	if (!rbnode->block) {
-		kfree(rbnode);
-		return NULL;
-	}
+	if (!rbnode->block)
+		goto err_free;
+
+	rbnode->cache_present = kzalloc(BITS_TO_LONGS(rbnode->blklen) *
+		sizeof(*rbnode->cache_present), GFP_KERNEL);
+	if (!rbnode->cache_present)
+		goto err_free_block;
 
 	return rbnode;
+
+err_free_block:
+	kfree(rbnode->block);
+err_free:
+	kfree(rbnode);
+	return NULL;
 }
 
 static int regcache_rbtree_write(struct regmap *map, unsigned int reg,
@@ -353,15 +384,9 @@ static int regcache_rbtree_write(struct regmap *map, unsigned int reg,
 	struct regcache_rbtree_node *rbnode, *rbnode_tmp;
 	struct rb_node *node;
 	unsigned int reg_tmp;
-	unsigned int pos;
-	int i;
 	int ret;
 
 	rbtree_ctx = map->cache;
-	/* update the reg_present bitmap, make space if necessary */
-	ret = regcache_set_reg_present(map, reg);
-	if (ret < 0)
-		return ret;
 
 	/* if we can't locate it in the cached rbnode we'll have
 	 * to traverse the rbtree looking for it.
@@ -371,30 +396,43 @@ static int regcache_rbtree_write(struct regmap *map, unsigned int reg,
 		reg_tmp = (reg - rbnode->base_reg) / map->reg_stride;
 		regcache_rbtree_set_register(map, rbnode, reg_tmp, value);
 	} else {
+		unsigned int base_reg, top_reg;
+		unsigned int new_base_reg, new_top_reg;
+		unsigned int min, max;
+		unsigned int max_dist;
+
+		max_dist = map->reg_stride * sizeof(*rbnode_tmp) /
+			map->cache_word_size;
+		if (reg < max_dist)
+			min = 0;
+		else
+			min = reg - max_dist;
+		max = reg + max_dist;
+
 		/* look for an adjacent register to the one we are about to add */
 		for (node = rb_first(&rbtree_ctx->root); node;
 		     node = rb_next(node)) {
 			rbnode_tmp = rb_entry(node, struct regcache_rbtree_node,
 					      node);
-			for (i = 0; i < rbnode_tmp->blklen; i++) {
-				reg_tmp = rbnode_tmp->base_reg +
-						(i * map->reg_stride);
-				if (abs(reg_tmp - reg) != map->reg_stride)
-					continue;
-				/* decide where in the block to place our register */
-				if (reg_tmp + map->reg_stride == reg)
-					pos = i + 1;
-				else
-					pos = i;
-				ret = regcache_rbtree_insert_to_block(map,
-								      rbnode_tmp,
-								      pos, reg,
-								      value);
-				if (ret)
-					return ret;
-				rbtree_ctx->cached_rbnode = rbnode_tmp;
-				return 0;
+
+			regcache_rbtree_get_base_top_reg(map, rbnode_tmp,
+				&base_reg, &top_reg);
+
+			if (base_reg <= max && top_reg >= min) {
+				new_base_reg = min(reg, base_reg);
+				new_top_reg = max(reg, top_reg);
+			} else {
+				continue;
 			}
+
+			ret = regcache_rbtree_insert_to_block(map, rbnode_tmp,
+							      new_base_reg,
+							      new_top_reg, reg,
+							      value);
+			if (ret)
+				return ret;
+			rbtree_ctx->cached_rbnode = rbnode_tmp;
+			return 0;
 		}
 
 		/* We did not manage to find a place to insert it in
@@ -418,30 +456,34 @@ static int regcache_rbtree_sync(struct regmap *map, unsigned int min,
 	struct regcache_rbtree_ctx *rbtree_ctx;
 	struct rb_node *node;
 	struct regcache_rbtree_node *rbnode;
+	unsigned int base_reg, top_reg;
+	unsigned int start, end;
 	int ret;
-	int base, end;
 
 	rbtree_ctx = map->cache;
 	for (node = rb_first(&rbtree_ctx->root); node; node = rb_next(node)) {
 		rbnode = rb_entry(node, struct regcache_rbtree_node, node);
 
-		if (rbnode->base_reg > max)
+		regcache_rbtree_get_base_top_reg(map, rbnode, &base_reg,
+			&top_reg);
+		if (base_reg > max)
 			break;
-		if (rbnode->base_reg + rbnode->blklen < min)
+		if (top_reg < min)
 			continue;
 
-		if (min > rbnode->base_reg)
-			base = min - rbnode->base_reg;
+		if (min > base_reg)
+			start = (min - base_reg) / map->reg_stride;
 		else
-			base = 0;
+			start = 0;
 
-		if (max < rbnode->base_reg + rbnode->blklen)
-			end = max - rbnode->base_reg + 1;
+		if (max < top_reg)
+			end = (max - base_reg) / map->reg_stride + 1;
 		else
 			end = rbnode->blklen;
 
-		ret = regcache_sync_block(map, rbnode->block, rbnode->base_reg,
-					  base, end);
+		ret = regcache_sync_block(map, rbnode->block,
+					  rbnode->cache_present,
+					  rbnode->base_reg, start, end);
 		if (ret != 0)
 			return ret;
 	}
@@ -449,6 +491,42 @@ static int regcache_rbtree_sync(struct regmap *map, unsigned int min,
 	return regmap_async_complete(map);
 }
 
+static int regcache_rbtree_drop(struct regmap *map, unsigned int min,
+				unsigned int max)
+{
+	struct regcache_rbtree_ctx *rbtree_ctx;
+	struct regcache_rbtree_node *rbnode;
+	struct rb_node *node;
+	unsigned int base_reg, top_reg;
+	unsigned int start, end;
+
+	rbtree_ctx = map->cache;
+	for (node = rb_first(&rbtree_ctx->root); node; node = rb_next(node)) {
+		rbnode = rb_entry(node, struct regcache_rbtree_node, node);
+
+		regcache_rbtree_get_base_top_reg(map, rbnode, &base_reg,
+			&top_reg);
+		if (base_reg > max)
+			break;
+		if (top_reg < min)
+			continue;
+
+		if (min > base_reg)
+			start = (min - base_reg) / map->reg_stride;
+		else
+			start = 0;
+
+		if (max < top_reg)
+			end = (max - base_reg) / map->reg_stride + 1;
+		else
+			end = rbnode->blklen;
+
+		bitmap_clear(rbnode->cache_present, start, end - start);
+	}
+
+	return 0;
+}
+
 struct regcache_ops regcache_rbtree_ops = {
 	.type = REGCACHE_RBTREE,
 	.name = "rbtree",
@@ -456,5 +534,6 @@ struct regcache_ops regcache_rbtree_ops = {
 	.exit = regcache_rbtree_exit,
 	.read = regcache_rbtree_read,
 	.write = regcache_rbtree_write,
-	.sync = regcache_rbtree_sync
+	.sync = regcache_rbtree_sync,
+	.drop = regcache_rbtree_drop,
 };
diff --git a/drivers/base/regmap/regcache.c b/drivers/base/regmap/regcache.c
index 3455f833e473..d6c2d691b6e8 100644
--- a/drivers/base/regmap/regcache.c
+++ b/drivers/base/regmap/regcache.c
@@ -121,8 +121,6 @@ int regcache_init(struct regmap *map, const struct regmap_config *config)
 	map->reg_defaults_raw = config->reg_defaults_raw;
 	map->cache_word_size = DIV_ROUND_UP(config->val_bits, 8);
 	map->cache_size_raw = map->cache_word_size * config->num_reg_defaults_raw;
-	map->cache_present = NULL;
-	map->cache_present_nbits = 0;
 
 	map->cache = NULL;
 	map->cache_ops = cache_types[i];
@@ -181,7 +179,6 @@ void regcache_exit(struct regmap *map)
 
 	BUG_ON(!map->cache_ops);
 
-	kfree(map->cache_present);
 	kfree(map->reg_defaults);
 	if (map->cache_free)
 		kfree(map->reg_defaults_raw);
@@ -241,9 +238,6 @@ int regcache_write(struct regmap *map,
 
 	BUG_ON(!map->cache_ops);
 
-	if (!regmap_writeable(map, reg))
-		return -EIO;
-
 	if (!regmap_volatile(map, reg))
 		return map->cache_ops->write(map, reg, value);
 
@@ -410,22 +404,16 @@ EXPORT_SYMBOL_GPL(regcache_sync_region);
 int regcache_drop_region(struct regmap *map, unsigned int min,
 			 unsigned int max)
 {
-	unsigned int reg;
 	int ret = 0;
 
-	if (!map->cache_present && !(map->cache_ops && map->cache_ops->drop))
+	if (!map->cache_ops || !map->cache_ops->drop)
 		return -EINVAL;
 
 	map->lock(map->lock_arg);
 
 	trace_regcache_drop_region(map->dev, min, max);
 
-	if (map->cache_present)
-		for (reg = min; reg < max + 1; reg++)
-			clear_bit(reg, map->cache_present);
-
-	if (map->cache_ops && map->cache_ops->drop)
-		ret = map->cache_ops->drop(map, min, max);
+	ret = map->cache_ops->drop(map, min, max);
 
 	map->unlock(map->lock_arg);
 
@@ -493,42 +481,6 @@ void regcache_cache_bypass(struct regmap *map, bool enable)
 }
 EXPORT_SYMBOL_GPL(regcache_cache_bypass);
 
-int regcache_set_reg_present(struct regmap *map, unsigned int reg)
-{
-	unsigned long *cache_present;
-	unsigned int cache_present_size;
-	unsigned int nregs;
-	int i;
-
-	nregs = reg + 1;
-	cache_present_size = BITS_TO_LONGS(nregs);
-	cache_present_size *= sizeof(long);
-
-	if (!map->cache_present) {
-		cache_present = kmalloc(cache_present_size, GFP_KERNEL);
-		if (!cache_present)
-			return -ENOMEM;
-		bitmap_zero(cache_present, nregs);
-		map->cache_present = cache_present;
-		map->cache_present_nbits = nregs;
-	}
-
-	if (nregs > map->cache_present_nbits) {
-		cache_present = krealloc(map->cache_present,
-					 cache_present_size, GFP_KERNEL);
-		if (!cache_present)
-			return -ENOMEM;
-		for (i = 0; i < nregs; i++)
-			if (i >= map->cache_present_nbits)
-				clear_bit(i, cache_present);
-		map->cache_present = cache_present;
-		map->cache_present_nbits = nregs;
-	}
-
-	set_bit(reg, map->cache_present);
-	return 0;
-}
-
 bool regcache_set_val(struct regmap *map, void *base, unsigned int idx,
 		      unsigned int val)
 {
@@ -620,7 +572,16 @@ int regcache_lookup_reg(struct regmap *map, unsigned int reg)
 		return -ENOENT;
 }
 
+static bool regcache_reg_present(unsigned long *cache_present, unsigned int idx)
+{
+	if (!cache_present)
+		return true;
+
+	return test_bit(idx, cache_present);
+}
+
 static int regcache_sync_block_single(struct regmap *map, void *block,
+				      unsigned long *cache_present,
 				      unsigned int block_base,
 				      unsigned int start, unsigned int end)
 {
@@ -630,7 +591,7 @@ static int regcache_sync_block_single(struct regmap *map, void *block,
 	for (i = start; i < end; i++) {
 		regtmp = block_base + (i * map->reg_stride);
 
-		if (!regcache_reg_present(map, regtmp))
+		if (!regcache_reg_present(cache_present, i))
 			continue;
 
 		val = regcache_get_val(map, block, i);
@@ -681,6 +642,7 @@ static int regcache_sync_block_raw_flush(struct regmap *map, const void **data,
 }
 
 static int regcache_sync_block_raw(struct regmap *map, void *block,
+			    unsigned long *cache_present,
 			    unsigned int block_base, unsigned int start,
 			    unsigned int end)
 {
@@ -693,7 +655,7 @@ static int regcache_sync_block_raw(struct regmap *map, void *block,
 	for (i = start; i < end; i++) {
 		regtmp = block_base + (i * map->reg_stride);
 
-		if (!regcache_reg_present(map, regtmp)) {
+		if (!regcache_reg_present(cache_present, i)) {
 			ret = regcache_sync_block_raw_flush(map, &data,
 							    base, regtmp);
 			if (ret != 0)
@@ -724,13 +686,14 @@ static int regcache_sync_block_raw(struct regmap *map, void *block,
 }
 
 int regcache_sync_block(struct regmap *map, void *block,
+			unsigned long *cache_present,
 			unsigned int block_base, unsigned int start,
 			unsigned int end)
 {
 	if (regmap_can_raw_write(map))
-		return regcache_sync_block_raw(map, block, block_base,
-					       start, end);
+		return regcache_sync_block_raw(map, block, cache_present,
+					       block_base, start, end);
 	else
-		return regcache_sync_block_single(map, block, block_base,
-						  start, end);
+		return regcache_sync_block_single(map, block, cache_present,
+						  block_base, start, end);
 }
diff --git a/drivers/base/regmap/regmap-debugfs.c b/drivers/base/regmap/regmap-debugfs.c
index 53495753fbdb..de11ecaf3833 100644
--- a/drivers/base/regmap/regmap-debugfs.c
+++ b/drivers/base/regmap/regmap-debugfs.c
@@ -85,8 +85,8 @@ static unsigned int regmap_debugfs_get_dump_start(struct regmap *map,
 	unsigned int reg_offset;
 
 	/* Suppress the cache if we're using a subrange */
-	if (from)
-		return from;
+	if (base)
+		return base;
 
 	/*
 	 * If we don't have a cache build one so we don't have to do a
@@ -281,7 +281,7 @@ static ssize_t regmap_map_write_file(struct file *file,
 	reg = simple_strtoul(start, &start, 16);
 	while (*start == ' ')
 		start++;
-	if (strict_strtoul(start, 16, &value))
+	if (kstrtoul(start, 16, &value))
 		return -EINVAL;
 
 	/* Userspace has been fiddling around behind the kernel's back */
diff --git a/drivers/base/regmap/regmap-irq.c b/drivers/base/regmap/regmap-irq.c
index 1643e889bafc..d10456ffd811 100644
--- a/drivers/base/regmap/regmap-irq.c
+++ b/drivers/base/regmap/regmap-irq.c
@@ -418,6 +418,31 @@ int regmap_add_irq_chip(struct regmap *map, int irq, int irq_flags,
 				reg, ret);
 			goto err_alloc;
 		}
+
+		if (!chip->init_ack_masked)
+			continue;
+
+		/* Ack masked but set interrupts */
+		reg = chip->status_base +
+			(i * map->reg_stride * d->irq_reg_stride);
+		ret = regmap_read(map, reg, &d->status_buf[i]);
+		if (ret != 0) {
+			dev_err(map->dev, "Failed to read IRQ status: %d\n",
+				ret);
+			goto err_alloc;
+		}
+
+		if (d->status_buf[i] && chip->ack_base) {
+			reg = chip->ack_base +
+				(i * map->reg_stride * d->irq_reg_stride);
+			ret = regmap_write(map, reg,
+					d->status_buf[i] & d->mask_buf[i]);
+			if (ret != 0) {
+				dev_err(map->dev, "Failed to ack 0x%x: %d\n",
+					reg, ret);
+				goto err_alloc;
+			}
+		}
 	}
 
 	/* Wake is disabled by default */
diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c
index e0d0c7d8a5c5..7d689a15c500 100644
--- a/drivers/base/regmap/regmap.c
+++ b/drivers/base/regmap/regmap.c
@@ -303,6 +303,7 @@ static void regmap_unlock_mutex(void *__map)
 }
 
 static void regmap_lock_spinlock(void *__map)
+__acquires(&map->spinlock)
 {
 	struct regmap *map = __map;
 	unsigned long flags;
@@ -312,6 +313,7 @@ static void regmap_lock_spinlock(void *__map)
 }
 
 static void regmap_unlock_spinlock(void *__map)
+__releases(&map->spinlock)
 {
 	struct regmap *map = __map;
 	spin_unlock_irqrestore(&map->spinlock, map->spinlock_flags);
@@ -687,6 +689,10 @@ skip_format_initialization:
 			unsigned win_max = win_min +
 					   config->ranges[j].window_len - 1;
 
+			/* Allow data window inside its own virtual range */
+			if (j == i)
+				continue;
+
 			if (range_cfg->range_min <= sel_reg &&
 			    sel_reg <= range_cfg->range_max) {
 				dev_err(map->dev,
@@ -1261,6 +1267,9 @@ int _regmap_write(struct regmap *map, unsigned int reg,
 	int ret;
 	void *context = _regmap_map_get_context(map);
 
+	if (!regmap_writeable(map, reg))
+		return -EIO;
+
 	if (!map->cache_bypass && !map->defer_caching) {
 		ret = regcache_write(map, reg, val);
 		if (ret != 0)
@@ -1888,13 +1897,10 @@ EXPORT_SYMBOL_GPL(regmap_async_complete);
 int regmap_register_patch(struct regmap *map, const struct reg_default *regs,
 			  int num_regs)
 {
+	struct reg_default *p;
 	int i, ret;
 	bool bypass;
 
-	/* If needed the implementation can be extended to support this */
-	if (map->patch)
-		return -EBUSY;
-
 	map->lock(map->lock_arg);
 
 	bypass = map->cache_bypass;
@@ -1911,11 +1917,13 @@ int regmap_register_patch(struct regmap *map, const struct reg_default *regs,
 		}
 	}
 
-	map->patch = kcalloc(num_regs, sizeof(struct reg_default), GFP_KERNEL);
-	if (map->patch != NULL) {
-		memcpy(map->patch, regs,
-		       num_regs * sizeof(struct reg_default));
-		map->patch_regs = num_regs;
+	p = krealloc(map->patch,
+		     sizeof(struct reg_default) * (map->patch_regs + num_regs),
+		     GFP_KERNEL);
+	if (p) {
+		memcpy(p + map->patch_regs, regs, num_regs * sizeof(*regs));
+		map->patch = p;
+		map->patch_regs += num_regs;
 	} else {
 		ret = -ENOMEM;
 	}
diff --git a/drivers/base/topology.c b/drivers/base/topology.c
index 2f5919ed91ab..94ffee378f10 100644
--- a/drivers/base/topology.c
+++ b/drivers/base/topology.c
@@ -62,25 +62,6 @@ static ssize_t show_cpumap(int type, const struct cpumask *mask, char *buf)
 }
 #endif
 
-#ifdef arch_provides_topology_pointers
-#define define_siblings_show_map(name)					\
-static ssize_t show_##name(struct device *dev,				\
-			   struct device_attribute *attr, char *buf)	\
-{									\
-	unsigned int cpu = dev->id;					\
-	return show_cpumap(0, topology_##name(cpu), buf);		\
-}
-
-#define define_siblings_show_list(name)					\
-static ssize_t show_##name##_list(struct device *dev,			\
-				  struct device_attribute *attr,	\
-				  char *buf)				\
-{									\
-	unsigned int cpu = dev->id;					\
-	return show_cpumap(1, topology_##name(cpu), buf);		\
-}
-
-#else
 #define define_siblings_show_map(name)					\
 static ssize_t show_##name(struct device *dev,				\
 			   struct device_attribute *attr, char *buf)	\
@@ -95,7 +76,6 @@ static ssize_t show_##name##_list(struct device *dev,			\
 {									\
 	return show_cpumap(1, topology_##name(dev->id), buf);		\
 }
-#endif
 
 #define define_siblings_show_func(name)		\
 	define_siblings_show_map(name); define_siblings_show_list(name)
diff --git a/drivers/bcma/Kconfig b/drivers/bcma/Kconfig
index 380a2003231e..7c081b38ef3e 100644
--- a/drivers/bcma/Kconfig
+++ b/drivers/bcma/Kconfig
@@ -35,8 +35,14 @@ config BCMA_DRIVER_PCI_HOSTMODE
 	  PCI core hostmode operation (external PCI bus).
 
 config BCMA_HOST_SOC
-	bool
-	depends on BCMA_DRIVER_MIPS
+	bool "Support for BCMA in a SoC"
+	depends on BCMA
+	help
+	  Host interface for a Broadcom AIX bus directly mapped into
+	  the memory. This only works with the Broadcom SoCs from the
+	  BCM47XX line.
+
+	  If unsure, say N
 
 config BCMA_DRIVER_MIPS
 	bool "BCMA Broadcom MIPS core driver"
diff --git a/drivers/bcma/driver_pci.c b/drivers/bcma/driver_pci.c
index cf7a476a519f..50329d1057ed 100644
--- a/drivers/bcma/driver_pci.c
+++ b/drivers/bcma/driver_pci.c
@@ -31,7 +31,7 @@ static void bcma_pcie_write(struct bcma_drv_pci *pc, u32 address, u32 data)
 	pcicore_write32(pc, BCMA_CORE_PCI_PCIEIND_DATA, data);
 }
 
-static void bcma_pcie_mdio_set_phy(struct bcma_drv_pci *pc, u8 phy)
+static void bcma_pcie_mdio_set_phy(struct bcma_drv_pci *pc, u16 phy)
 {
 	u32 v;
 	int i;
@@ -55,7 +55,7 @@ static void bcma_pcie_mdio_set_phy(struct bcma_drv_pci *pc, u8 phy)
 	}
 }
 
-static u16 bcma_pcie_mdio_read(struct bcma_drv_pci *pc, u8 device, u8 address)
+static u16 bcma_pcie_mdio_read(struct bcma_drv_pci *pc, u16 device, u8 address)
 {
 	int max_retries = 10;
 	u16 ret = 0;
@@ -98,7 +98,7 @@ static u16 bcma_pcie_mdio_read(struct bcma_drv_pci *pc, u8 device, u8 address)
 	return ret;
 }
 
-static void bcma_pcie_mdio_write(struct bcma_drv_pci *pc, u8 device,
+static void bcma_pcie_mdio_write(struct bcma_drv_pci *pc, u16 device,
 				u8 address, u16 data)
 {
 	int max_retries = 10;
@@ -137,6 +137,13 @@ static void bcma_pcie_mdio_write(struct bcma_drv_pci *pc, u8 device,
 	pcicore_write32(pc, BCMA_CORE_PCI_MDIO_CONTROL, 0);
 }
 
+static u16 bcma_pcie_mdio_writeread(struct bcma_drv_pci *pc, u16 device,
+				    u8 address, u16 data)
+{
+	bcma_pcie_mdio_write(pc, device, address, data);
+	return bcma_pcie_mdio_read(pc, device, address);
+}
+
 /**************************************************
  * Workarounds.
  **************************************************/
@@ -229,6 +236,32 @@ void bcma_core_pci_init(struct bcma_drv_pci *pc)
 		bcma_core_pci_clientmode_init(pc);
 }
 
+void bcma_core_pci_power_save(struct bcma_bus *bus, bool up)
+{
+	struct bcma_drv_pci *pc;
+	u16 data;
+
+	if (bus->hosttype != BCMA_HOSTTYPE_PCI)
+		return;
+
+	pc = &bus->drv_pci[0];
+
+	if (pc->core->id.rev >= 15 && pc->core->id.rev <= 20) {
+		data = up ? 0x74 : 0x7C;
+		bcma_pcie_mdio_writeread(pc, BCMA_CORE_PCI_MDIO_BLK1,
+					 BCMA_CORE_PCI_MDIO_BLK1_MGMT1, 0x7F64);
+		bcma_pcie_mdio_writeread(pc, BCMA_CORE_PCI_MDIO_BLK1,
+					 BCMA_CORE_PCI_MDIO_BLK1_MGMT3, data);
+	} else if (pc->core->id.rev >= 21 && pc->core->id.rev <= 22) {
+		data = up ? 0x75 : 0x7D;
+		bcma_pcie_mdio_writeread(pc, BCMA_CORE_PCI_MDIO_BLK1,
+					 BCMA_CORE_PCI_MDIO_BLK1_MGMT1, 0x7E65);
+		bcma_pcie_mdio_writeread(pc, BCMA_CORE_PCI_MDIO_BLK1,
+					 BCMA_CORE_PCI_MDIO_BLK1_MGMT3, data);
+	}
+}
+EXPORT_SYMBOL_GPL(bcma_core_pci_power_save);
+
 int bcma_core_pci_irq_ctl(struct bcma_drv_pci *pc, struct bcma_device *core,
 			  bool enable)
 {
@@ -262,7 +295,7 @@ out:
 }
 EXPORT_SYMBOL_GPL(bcma_core_pci_irq_ctl);
 
-void bcma_core_pci_extend_L1timer(struct bcma_drv_pci *pc, bool extend)
+static void bcma_core_pci_extend_L1timer(struct bcma_drv_pci *pc, bool extend)
 {
 	u32 w;
 
@@ -274,4 +307,29 @@ void bcma_core_pci_extend_L1timer(struct bcma_drv_pci *pc, bool extend)
 	bcma_pcie_write(pc, BCMA_CORE_PCI_DLLP_PMTHRESHREG, w);
 	bcma_pcie_read(pc, BCMA_CORE_PCI_DLLP_PMTHRESHREG);
 }
-EXPORT_SYMBOL_GPL(bcma_core_pci_extend_L1timer);
+
+void bcma_core_pci_up(struct bcma_bus *bus)
+{
+	struct bcma_drv_pci *pc;
+
+	if (bus->hosttype != BCMA_HOSTTYPE_PCI)
+		return;
+
+	pc = &bus->drv_pci[0];
+
+	bcma_core_pci_extend_L1timer(pc, true);
+}
+EXPORT_SYMBOL_GPL(bcma_core_pci_up);
+
+void bcma_core_pci_down(struct bcma_bus *bus)
+{
+	struct bcma_drv_pci *pc;
+
+	if (bus->hosttype != BCMA_HOSTTYPE_PCI)
+		return;
+
+	pc = &bus->drv_pci[0];
+
+	bcma_core_pci_extend_L1timer(pc, false);
+}
+EXPORT_SYMBOL_GPL(bcma_core_pci_down);
diff --git a/drivers/bcma/driver_pci_host.c b/drivers/bcma/driver_pci_host.c
index 30629a3d44cc..c3d7b03c2fdc 100644
--- a/drivers/bcma/driver_pci_host.c
+++ b/drivers/bcma/driver_pci_host.c
@@ -581,6 +581,7 @@ DECLARE_PCI_FIXUP_HEADER(PCI_ANY_ID, PCI_ANY_ID, bcma_core_pci_fixup_addresses);
 int bcma_core_pci_plat_dev_init(struct pci_dev *dev)
 {
 	struct bcma_drv_pci_host *pc_host;
+	int readrq;
 
 	if (dev->bus->ops->read != bcma_core_pci_hostmode_read_config) {
 		/* This is not a device on the PCI-core bridge. */
@@ -595,6 +596,11 @@ int bcma_core_pci_plat_dev_init(struct pci_dev *dev)
 	dev->irq = bcma_core_irq(pc_host->pdev->core);
 	pci_write_config_byte(dev, PCI_INTERRUPT_LINE, dev->irq);
 
+	readrq = pcie_get_readrq(dev);
+	if (readrq > 128) {
+		pr_info("change PCIe max read request size from %i to 128\n", readrq);
+		pcie_set_readrq(dev, 128);
+	}
 	return 0;
 }
 EXPORT_SYMBOL(bcma_core_pci_plat_dev_init);
diff --git a/drivers/bcma/main.c b/drivers/bcma/main.c
index 0067422ec17d..90ee350442a9 100644
--- a/drivers/bcma/main.c
+++ b/drivers/bcma/main.c
@@ -237,7 +237,7 @@ int bcma_bus_register(struct bcma_bus *bus)
 	err = bcma_bus_scan(bus);
 	if (err) {
 		bcma_err(bus, "Failed to scan: %d\n", err);
-		return -1;
+		return err;
 	}
 
 	/* Early init CC core */
diff --git a/drivers/bcma/scan.c b/drivers/bcma/scan.c
index 8bffa5c9818c..37768401d113 100644
--- a/drivers/bcma/scan.c
+++ b/drivers/bcma/scan.c
@@ -32,6 +32,18 @@ static const struct bcma_device_id_name bcma_bcm_device_names[] = {
 	{ BCMA_CORE_4706_CHIPCOMMON, "BCM4706 ChipCommon" },
 	{ BCMA_CORE_4706_SOC_RAM, "BCM4706 SOC RAM" },
 	{ BCMA_CORE_4706_MAC_GBIT, "BCM4706 GBit MAC" },
+	{ BCMA_CORE_PCIEG2, "PCIe Gen 2" },
+	{ BCMA_CORE_DMA, "DMA" },
+	{ BCMA_CORE_SDIO3, "SDIO3" },
+	{ BCMA_CORE_USB20, "USB 2.0" },
+	{ BCMA_CORE_USB30, "USB 3.0" },
+	{ BCMA_CORE_A9JTAG, "ARM Cortex A9 JTAG" },
+	{ BCMA_CORE_DDR23, "Denali DDR2/DDR3 memory controller" },
+	{ BCMA_CORE_ROM, "ROM" },
+	{ BCMA_CORE_NAND, "NAND flash controller" },
+	{ BCMA_CORE_QSPI, "SPI flash controller" },
+	{ BCMA_CORE_CHIPCOMMON_B, "Chipcommon B" },
+	{ BCMA_CORE_ARMCA9, "ARM Cortex A9 core (ihost)" },
 	{ BCMA_CORE_AMEMC, "AMEMC (DDR)" },
 	{ BCMA_CORE_ALTA, "ALTA (I2S)" },
 	{ BCMA_CORE_INVALID, "Invalid" },
@@ -201,7 +213,7 @@ static s32 bcma_erom_get_mst_port(struct bcma_bus *bus, u32 __iomem **eromptr)
 	return ent;
 }
 
-static s32 bcma_erom_get_addr_desc(struct bcma_bus *bus, u32 __iomem **eromptr,
+static u32 bcma_erom_get_addr_desc(struct bcma_bus *bus, u32 __iomem **eromptr,
 				  u32 type, u8 port)
 {
 	u32 addrl, addrh, sizel, sizeh = 0;
@@ -213,7 +225,7 @@ static s32 bcma_erom_get_addr_desc(struct bcma_bus *bus, u32 __iomem **eromptr,
 	    ((ent & SCAN_ADDR_TYPE) != type) ||
 	    (((ent & SCAN_ADDR_PORT) >> SCAN_ADDR_PORT_SHIFT) != port)) {
 		bcma_erom_push_ent(eromptr);
-		return -EINVAL;
+		return (u32)-EINVAL;
 	}
 
 	addrl = ent & SCAN_ADDR_ADDR;
@@ -257,11 +269,13 @@ static struct bcma_device *bcma_find_core_reverse(struct bcma_bus *bus, u16 core
 	return NULL;
 }
 
+#define IS_ERR_VALUE_U32(x) ((x) >= (u32)-MAX_ERRNO)
+
 static int bcma_get_next_core(struct bcma_bus *bus, u32 __iomem **eromptr,
 			      struct bcma_device_id *match, int core_num,
 			      struct bcma_device *core)
 {
-	s32 tmp;
+	u32 tmp;
 	u8 i, j;
 	s32 cia, cib;
 	u8 ports[2], wrappers[2];
@@ -339,11 +353,11 @@ static int bcma_get_next_core(struct bcma_bus *bus, u32 __iomem **eromptr,
 	 * the main register space for the core
 	 */
 	tmp = bcma_erom_get_addr_desc(bus, eromptr, SCAN_ADDR_TYPE_SLAVE, 0);
-	if (tmp <= 0) {
+	if (tmp == 0 || IS_ERR_VALUE_U32(tmp)) {
 		/* Try again to see if it is a bridge */
 		tmp = bcma_erom_get_addr_desc(bus, eromptr,
 					      SCAN_ADDR_TYPE_BRIDGE, 0);
-		if (tmp <= 0) {
+		if (tmp == 0 || IS_ERR_VALUE_U32(tmp)) {
 			return -EILSEQ;
 		} else {
 			bcma_info(bus, "Bridge found\n");
@@ -357,7 +371,7 @@ static int bcma_get_next_core(struct bcma_bus *bus, u32 __iomem **eromptr,
 		for (j = 0; ; j++) {
 			tmp = bcma_erom_get_addr_desc(bus, eromptr,
 				SCAN_ADDR_TYPE_SLAVE, i);
-			if (tmp < 0) {
+			if (IS_ERR_VALUE_U32(tmp)) {
 				/* no more entries for port _i_ */
 				/* pr_debug("erom: slave port %d "
 				 * "has %d descriptors\n", i, j); */
@@ -374,7 +388,7 @@ static int bcma_get_next_core(struct bcma_bus *bus, u32 __iomem **eromptr,
 		for (j = 0; ; j++) {
 			tmp = bcma_erom_get_addr_desc(bus, eromptr,
 				SCAN_ADDR_TYPE_MWRAP, i);
-			if (tmp < 0) {
+			if (IS_ERR_VALUE_U32(tmp)) {
 				/* no more entries for port _i_ */
 				/* pr_debug("erom: master wrapper %d "
 				 * "has %d descriptors\n", i, j); */
@@ -392,7 +406,7 @@ static int bcma_get_next_core(struct bcma_bus *bus, u32 __iomem **eromptr,
 		for (j = 0; ; j++) {
 			tmp = bcma_erom_get_addr_desc(bus, eromptr,
 				SCAN_ADDR_TYPE_SWRAP, i + hack);
-			if (tmp < 0) {
+			if (IS_ERR_VALUE_U32(tmp)) {
 				/* no more entries for port _i_ */
 				/* pr_debug("erom: master wrapper %d "
 				 * has %d descriptors\n", i, j); */
diff --git a/drivers/block/aoe/aoe.h b/drivers/block/aoe/aoe.h
index 025c41d3cb33..14a9d1912318 100644
--- a/drivers/block/aoe/aoe.h
+++ b/drivers/block/aoe/aoe.h
@@ -1,5 +1,5 @@
 /* Copyright (c) 2013 Coraid, Inc.  See COPYING for GPL terms. */
-#define VERSION "83"
+#define VERSION "85"
 #define AOE_MAJOR 152
 #define DEVICE_NAME "aoe"
 
@@ -169,6 +169,7 @@ struct aoedev {
 	ulong ref;
 	struct work_struct work;/* disk create work struct */
 	struct gendisk *gd;
+	struct dentry *debugfs;
 	struct request_queue *blkq;
 	struct hd_geometry geo;
 	sector_t ssize;
@@ -206,6 +207,7 @@ struct ktstate {
 int aoeblk_init(void);
 void aoeblk_exit(void);
 void aoeblk_gdalloc(void *);
+void aoedisk_rm_debugfs(struct aoedev *d);
 void aoedisk_rm_sysfs(struct aoedev *d);
 
 int aoechr_init(void);
diff --git a/drivers/block/aoe/aoeblk.c b/drivers/block/aoe/aoeblk.c
index 916d9ed5c8aa..dd73e1ff1759 100644
--- a/drivers/block/aoe/aoeblk.c
+++ b/drivers/block/aoe/aoeblk.c
@@ -1,4 +1,4 @@
-/* Copyright (c) 2012 Coraid, Inc.  See COPYING for GPL terms. */
+/* Copyright (c) 2013 Coraid, Inc.  See COPYING for GPL terms. */
 /*
  * aoeblk.c
  * block device routines
@@ -17,11 +17,13 @@
 #include <linux/mutex.h>
 #include <linux/export.h>
 #include <linux/moduleparam.h>
+#include <linux/debugfs.h>
 #include <scsi/sg.h>
 #include "aoe.h"
 
 static DEFINE_MUTEX(aoeblk_mutex);
 static struct kmem_cache *buf_pool_cache;
+static struct dentry *aoe_debugfs_dir;
 
 /* GPFS needs a larger value than the default. */
 static int aoe_maxsectors;
@@ -108,6 +110,55 @@ static ssize_t aoedisk_show_payload(struct device *dev,
 	return snprintf(page, PAGE_SIZE, "%lu\n", d->maxbcnt);
 }
 
+static int aoedisk_debugfs_show(struct seq_file *s, void *ignored)
+{
+	struct aoedev *d;
+	struct aoetgt **t, **te;
+	struct aoeif *ifp, *ife;
+	unsigned long flags;
+	char c;
+
+	d = s->private;
+	seq_printf(s, "rttavg: %d rttdev: %d\n",
+		d->rttavg >> RTTSCALE,
+		d->rttdev >> RTTDSCALE);
+	seq_printf(s, "nskbpool: %d\n", skb_queue_len(&d->skbpool));
+	seq_printf(s, "kicked: %ld\n", d->kicked);
+	seq_printf(s, "maxbcnt: %ld\n", d->maxbcnt);
+	seq_printf(s, "ref: %ld\n", d->ref);
+
+	spin_lock_irqsave(&d->lock, flags);
+	t = d->targets;
+	te = t + d->ntargets;
+	for (; t < te && *t; t++) {
+		c = '\t';
+		seq_printf(s, "falloc: %ld\n", (*t)->falloc);
+		seq_printf(s, "ffree: %p\n",
+			list_empty(&(*t)->ffree) ? NULL : (*t)->ffree.next);
+		seq_printf(s, "%pm:%d:%d:%d\n", (*t)->addr, (*t)->nout,
+			(*t)->maxout, (*t)->nframes);
+		seq_printf(s, "\tssthresh:%d\n", (*t)->ssthresh);
+		seq_printf(s, "\ttaint:%d\n", (*t)->taint);
+		seq_printf(s, "\tr:%d\n", (*t)->rpkts);
+		seq_printf(s, "\tw:%d\n", (*t)->wpkts);
+		ifp = (*t)->ifs;
+		ife = ifp + ARRAY_SIZE((*t)->ifs);
+		for (; ifp->nd && ifp < ife; ifp++) {
+			seq_printf(s, "%c%s", c, ifp->nd->name);
+			c = ',';
+		}
+		seq_puts(s, "\n");
+	}
+	spin_unlock_irqrestore(&d->lock, flags);
+
+	return 0;
+}
+
+static int aoe_debugfs_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, aoedisk_debugfs_show, inode->i_private);
+}
+
 static DEVICE_ATTR(state, S_IRUGO, aoedisk_show_state, NULL);
 static DEVICE_ATTR(mac, S_IRUGO, aoedisk_show_mac, NULL);
 static DEVICE_ATTR(netif, S_IRUGO, aoedisk_show_netif, NULL);
@@ -130,6 +181,44 @@ static const struct attribute_group attr_group = {
 	.attrs = aoe_attrs,
 };
 
+static const struct file_operations aoe_debugfs_fops = {
+	.open = aoe_debugfs_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+
+static void
+aoedisk_add_debugfs(struct aoedev *d)
+{
+	struct dentry *entry;
+	char *p;
+
+	if (aoe_debugfs_dir == NULL)
+		return;
+	p = strchr(d->gd->disk_name, '/');
+	if (p == NULL)
+		p = d->gd->disk_name;
+	else
+		p++;
+	BUG_ON(*p == '\0');
+	entry = debugfs_create_file(p, 0444, aoe_debugfs_dir, d,
+				    &aoe_debugfs_fops);
+	if (IS_ERR_OR_NULL(entry)) {
+		pr_info("aoe: cannot create debugfs file for %s\n",
+			d->gd->disk_name);
+		return;
+	}
+	BUG_ON(d->debugfs);
+	d->debugfs = entry;
+}
+void
+aoedisk_rm_debugfs(struct aoedev *d)
+{
+	debugfs_remove(d->debugfs);
+	d->debugfs = NULL;
+}
+
 static int
 aoedisk_add_sysfs(struct aoedev *d)
 {
@@ -330,6 +419,7 @@ aoeblk_gdalloc(void *vp)
 
 	add_disk(gd);
 	aoedisk_add_sysfs(d);
+	aoedisk_add_debugfs(d);
 
 	spin_lock_irqsave(&d->lock, flags);
 	WARN_ON(!(d->flags & DEVFL_GD_NOW));
@@ -351,6 +441,8 @@ err:
 void
 aoeblk_exit(void)
 {
+	debugfs_remove_recursive(aoe_debugfs_dir);
+	aoe_debugfs_dir = NULL;
 	kmem_cache_destroy(buf_pool_cache);
 }
 
@@ -362,7 +454,11 @@ aoeblk_init(void)
 					   0, 0, NULL);
 	if (buf_pool_cache == NULL)
 		return -ENOMEM;
-
+	aoe_debugfs_dir = debugfs_create_dir("aoe", NULL);
+	if (IS_ERR_OR_NULL(aoe_debugfs_dir)) {
+		pr_info("aoe: cannot create debugfs directory\n");
+		aoe_debugfs_dir = NULL;
+	}
 	return 0;
 }
 
diff --git a/drivers/block/aoe/aoecmd.c b/drivers/block/aoe/aoecmd.c
index 4d45dba7fb8f..d2515435e23f 100644
--- a/drivers/block/aoe/aoecmd.c
+++ b/drivers/block/aoe/aoecmd.c
@@ -380,7 +380,6 @@ aoecmd_ata_rw(struct aoedev *d)
 {
 	struct frame *f;
 	struct buf *buf;
-	struct aoetgt *t;
 	struct sk_buff *skb;
 	struct sk_buff_head queue;
 	ulong bcnt, fbcnt;
@@ -391,7 +390,6 @@ aoecmd_ata_rw(struct aoedev *d)
 	f = newframe(d);
 	if (f == NULL)
 		return 0;
-	t = *d->tgt;
 	bcnt = d->maxbcnt;
 	if (bcnt == 0)
 		bcnt = DEFAULTBCNT;
@@ -485,7 +483,6 @@ resend(struct aoedev *d, struct frame *f)
 	struct sk_buff *skb;
 	struct sk_buff_head queue;
 	struct aoe_hdr *h;
-	struct aoe_atahdr *ah;
 	struct aoetgt *t;
 	char buf[128];
 	u32 n;
@@ -500,7 +497,6 @@ resend(struct aoedev *d, struct frame *f)
 		return;
 	}
 	h = (struct aoe_hdr *) skb_mac_header(skb);
-	ah = (struct aoe_atahdr *) (h+1);
 
 	if (!(f->flags & FFL_PROBE)) {
 		snprintf(buf, sizeof(buf),
diff --git a/drivers/block/aoe/aoedev.c b/drivers/block/aoe/aoedev.c
index 784c92e038d1..e774c50b6842 100644
--- a/drivers/block/aoe/aoedev.c
+++ b/drivers/block/aoe/aoedev.c
@@ -12,6 +12,7 @@
 #include <linux/bitmap.h>
 #include <linux/kdev_t.h>
 #include <linux/moduleparam.h>
+#include <linux/string.h>
 #include "aoe.h"
 
 static void dummy_timer(ulong);
@@ -241,16 +242,12 @@ aoedev_downdev(struct aoedev *d)
 static int
 user_req(char *s, size_t slen, struct aoedev *d)
 {
-	char *p;
+	const char *p;
 	size_t lim;
 
 	if (!d->gd)
 		return 0;
-	p = strrchr(d->gd->disk_name, '/');
-	if (!p)
-		p = d->gd->disk_name;
-	else
-		p += 1;
+	p = kbasename(d->gd->disk_name);
 	lim = sizeof(d->gd->disk_name);
 	lim -= p - d->gd->disk_name;
 	if (slen < lim)
@@ -278,6 +275,7 @@ freedev(struct aoedev *d)
 
 	del_timer_sync(&d->timer);
 	if (d->gd) {
+		aoedisk_rm_debugfs(d);
 		aoedisk_rm_sysfs(d);
 		del_gendisk(d->gd);
 		put_disk(d->gd);
diff --git a/drivers/block/cciss.c b/drivers/block/cciss.c
index 62b6c2cc80b5..edfa2515bc86 100644
--- a/drivers/block/cciss.c
+++ b/drivers/block/cciss.c
@@ -1189,6 +1189,7 @@ static int cciss_ioctl32_passthru(struct block_device *bdev, fmode_t mode,
 	int err;
 	u32 cp;
 
+	memset(&arg64, 0, sizeof(arg64));
 	err = 0;
 	err |=
 	    copy_from_user(&arg64.LUN_info, &arg32->LUN_info,
@@ -4258,6 +4259,13 @@ static void cciss_find_board_params(ctlr_info_t *h)
 	h->nr_cmds = h->max_commands - 4 - cciss_tape_cmds;
 	h->maxsgentries = readl(&(h->cfgtable->MaxSGElements));
 	/*
+	 * The P600 may exhibit poor performnace under some workloads
+	 * if we use the value in the configuration table. Limit this
+	 * controller to MAXSGENTRIES (32) instead.
+	 */
+	if (h->board_id == 0x3225103C)
+		h->maxsgentries = MAXSGENTRIES;
+	/*
 	 * Limit in-command s/g elements to 32 save dma'able memory.
 	 * Howvever spec says if 0, use 31
 	 */
diff --git a/drivers/block/cpqarray.c b/drivers/block/cpqarray.c
index 639d26b90b91..2b9440384536 100644
--- a/drivers/block/cpqarray.c
+++ b/drivers/block/cpqarray.c
@@ -1193,6 +1193,7 @@ out_passthru:
 		ida_pci_info_struct pciinfo;
 
 		if (!arg) return -EINVAL;
+		memset(&pciinfo, 0, sizeof(pciinfo));
 		pciinfo.bus = host->pci_dev->bus->number;
 		pciinfo.dev_fn = host->pci_dev->devfn;
 		pciinfo.board_id = host->board_id;
diff --git a/drivers/block/drbd/drbd_bitmap.c b/drivers/block/drbd/drbd_bitmap.c
index 64fbb8385cdc..b12c11ec4bd2 100644
--- a/drivers/block/drbd/drbd_bitmap.c
+++ b/drivers/block/drbd/drbd_bitmap.c
@@ -393,7 +393,7 @@ static struct page **bm_realloc_pages(struct drbd_bitmap *b, unsigned long want)
 	 * we must not block on IO to ourselves.
 	 * Context is receiver thread or dmsetup. */
 	bytes = sizeof(struct page *)*want;
-	new_pages = kzalloc(bytes, GFP_NOIO);
+	new_pages = kzalloc(bytes, GFP_NOIO | __GFP_NOWARN);
 	if (!new_pages) {
 		new_pages = __vmalloc(bytes,
 				GFP_NOIO | __GFP_HIGHMEM | __GFP_ZERO,
diff --git a/drivers/block/mg_disk.c b/drivers/block/mg_disk.c
index a56cfcd5d648..77a60bedd7a3 100644
--- a/drivers/block/mg_disk.c
+++ b/drivers/block/mg_disk.c
@@ -636,7 +636,7 @@ ok_to_write:
 		mg_request(host->breq);
 }
 
-void mg_times_out(unsigned long data)
+static void mg_times_out(unsigned long data)
 {
 	struct mg_host *host = (struct mg_host *)data;
 	char *name;
diff --git a/drivers/block/mtip32xx/Kconfig b/drivers/block/mtip32xx/Kconfig
index 1fca1f996b45..0ba837fc62a8 100644
--- a/drivers/block/mtip32xx/Kconfig
+++ b/drivers/block/mtip32xx/Kconfig
@@ -4,6 +4,6 @@
 
 config BLK_DEV_PCIESSD_MTIP32XX
 	tristate "Block Device Driver for Micron PCIe SSDs"
-	depends on PCI && GENERIC_HARDIRQS
+	depends on PCI
 	help
           This enables the block driver for Micron PCIe SSDs.
diff --git a/drivers/block/nvme-core.c b/drivers/block/nvme-core.c
index ce79a590b45b..da52092980e2 100644
--- a/drivers/block/nvme-core.c
+++ b/drivers/block/nvme-core.c
@@ -36,6 +36,7 @@
 #include <linux/moduleparam.h>
 #include <linux/pci.h>
 #include <linux/poison.h>
+#include <linux/ptrace.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/types.h>
@@ -79,7 +80,9 @@ struct nvme_queue {
 	u16 sq_head;
 	u16 sq_tail;
 	u16 cq_head;
-	u16 cq_phase;
+	u8 cq_phase;
+	u8 cqe_seen;
+	u8 q_suspended;
 	unsigned long cmdid_data[];
 };
 
@@ -115,6 +118,11 @@ static struct nvme_cmd_info *nvme_cmd_info(struct nvme_queue *nvmeq)
 	return (void *)&nvmeq->cmdid_data[BITS_TO_LONGS(nvmeq->q_depth)];
 }
 
+static unsigned nvme_queue_extra(int depth)
+{
+	return DIV_ROUND_UP(depth, 8) + (depth * sizeof(struct nvme_cmd_info));
+}
+
 /**
  * alloc_cmdid() - Allocate a Command ID
  * @nvmeq: The queue that will be used for this command
@@ -285,6 +293,7 @@ nvme_alloc_iod(unsigned nseg, unsigned nbytes, gfp_t gfp)
 		iod->npages = -1;
 		iod->length = nbytes;
 		iod->nents = 0;
+		iod->start_time = jiffies;
 	}
 
 	return iod;
@@ -308,6 +317,30 @@ void nvme_free_iod(struct nvme_dev *dev, struct nvme_iod *iod)
 	kfree(iod);
 }
 
+static void nvme_start_io_acct(struct bio *bio)
+{
+	struct gendisk *disk = bio->bi_bdev->bd_disk;
+	const int rw = bio_data_dir(bio);
+	int cpu = part_stat_lock();
+	part_round_stats(cpu, &disk->part0);
+	part_stat_inc(cpu, &disk->part0, ios[rw]);
+	part_stat_add(cpu, &disk->part0, sectors[rw], bio_sectors(bio));
+	part_inc_in_flight(&disk->part0, rw);
+	part_stat_unlock();
+}
+
+static void nvme_end_io_acct(struct bio *bio, unsigned long start_time)
+{
+	struct gendisk *disk = bio->bi_bdev->bd_disk;
+	const int rw = bio_data_dir(bio);
+	unsigned long duration = jiffies - start_time;
+	int cpu = part_stat_lock();
+	part_stat_add(cpu, &disk->part0, ticks[rw], duration);
+	part_round_stats(cpu, &disk->part0);
+	part_dec_in_flight(&disk->part0, rw);
+	part_stat_unlock();
+}
+
 static void bio_completion(struct nvme_dev *dev, void *ctx,
 						struct nvme_completion *cqe)
 {
@@ -315,9 +348,11 @@ static void bio_completion(struct nvme_dev *dev, void *ctx,
 	struct bio *bio = iod->private;
 	u16 status = le16_to_cpup(&cqe->status) >> 1;
 
-	if (iod->nents)
+	if (iod->nents) {
 		dma_unmap_sg(&dev->pci_dev->dev, iod->sg, iod->nents,
 			bio_data_dir(bio) ? DMA_TO_DEVICE : DMA_FROM_DEVICE);
+		nvme_end_io_acct(bio, iod->start_time);
+	}
 	nvme_free_iod(dev, iod);
 	if (status)
 		bio_endio(bio, -EIO);
@@ -422,10 +457,8 @@ static void nvme_bio_pair_endio(struct bio *bio, int err)
 
 	if (atomic_dec_and_test(&bp->cnt)) {
 		bio_endio(bp->parent, bp->err);
-		if (bp->bv1)
-			kfree(bp->bv1);
-		if (bp->bv2)
-			kfree(bp->bv2);
+		kfree(bp->bv1);
+		kfree(bp->bv2);
 		kfree(bp);
 	}
 }
@@ -695,6 +728,7 @@ static int nvme_submit_bio_queue(struct nvme_queue *nvmeq, struct nvme_ns *ns,
 	cmnd->rw.control = cpu_to_le16(control);
 	cmnd->rw.dsmgmt = cpu_to_le32(dsmgmt);
 
+	nvme_start_io_acct(bio);
 	if (++nvmeq->sq_tail == nvmeq->q_depth)
 		nvmeq->sq_tail = 0;
 	writel(nvmeq->sq_tail, nvmeq->q_db);
@@ -709,26 +743,7 @@ static int nvme_submit_bio_queue(struct nvme_queue *nvmeq, struct nvme_ns *ns,
 	return result;
 }
 
-static void nvme_make_request(struct request_queue *q, struct bio *bio)
-{
-	struct nvme_ns *ns = q->queuedata;
-	struct nvme_queue *nvmeq = get_nvmeq(ns->dev);
-	int result = -EBUSY;
-
-	spin_lock_irq(&nvmeq->q_lock);
-	if (bio_list_empty(&nvmeq->sq_cong))
-		result = nvme_submit_bio_queue(nvmeq, ns, bio);
-	if (unlikely(result)) {
-		if (bio_list_empty(&nvmeq->sq_cong))
-			add_wait_queue(&nvmeq->sq_full, &nvmeq->sq_cong_wait);
-		bio_list_add(&nvmeq->sq_cong, bio);
-	}
-
-	spin_unlock_irq(&nvmeq->q_lock);
-	put_nvmeq(nvmeq);
-}
-
-static irqreturn_t nvme_process_cq(struct nvme_queue *nvmeq)
+static int nvme_process_cq(struct nvme_queue *nvmeq)
 {
 	u16 head, phase;
 
@@ -758,13 +773,40 @@ static irqreturn_t nvme_process_cq(struct nvme_queue *nvmeq)
 	 * a big problem.
 	 */
 	if (head == nvmeq->cq_head && phase == nvmeq->cq_phase)
-		return IRQ_NONE;
+		return 0;
 
 	writel(head, nvmeq->q_db + (1 << nvmeq->dev->db_stride));
 	nvmeq->cq_head = head;
 	nvmeq->cq_phase = phase;
 
-	return IRQ_HANDLED;
+	nvmeq->cqe_seen = 1;
+	return 1;
+}
+
+static void nvme_make_request(struct request_queue *q, struct bio *bio)
+{
+	struct nvme_ns *ns = q->queuedata;
+	struct nvme_queue *nvmeq = get_nvmeq(ns->dev);
+	int result = -EBUSY;
+
+	if (!nvmeq) {
+		put_nvmeq(NULL);
+		bio_endio(bio, -EIO);
+		return;
+	}
+
+	spin_lock_irq(&nvmeq->q_lock);
+	if (!nvmeq->q_suspended && bio_list_empty(&nvmeq->sq_cong))
+		result = nvme_submit_bio_queue(nvmeq, ns, bio);
+	if (unlikely(result)) {
+		if (bio_list_empty(&nvmeq->sq_cong))
+			add_wait_queue(&nvmeq->sq_full, &nvmeq->sq_cong_wait);
+		bio_list_add(&nvmeq->sq_cong, bio);
+	}
+
+	nvme_process_cq(nvmeq);
+	spin_unlock_irq(&nvmeq->q_lock);
+	put_nvmeq(nvmeq);
 }
 
 static irqreturn_t nvme_irq(int irq, void *data)
@@ -772,7 +814,9 @@ static irqreturn_t nvme_irq(int irq, void *data)
 	irqreturn_t result;
 	struct nvme_queue *nvmeq = data;
 	spin_lock(&nvmeq->q_lock);
-	result = nvme_process_cq(nvmeq);
+	nvme_process_cq(nvmeq);
+	result = nvmeq->cqe_seen ? IRQ_HANDLED : IRQ_NONE;
+	nvmeq->cqe_seen = 0;
 	spin_unlock(&nvmeq->q_lock);
 	return result;
 }
@@ -986,8 +1030,15 @@ static void nvme_cancel_ios(struct nvme_queue *nvmeq, bool timeout)
 	}
 }
 
-static void nvme_free_queue_mem(struct nvme_queue *nvmeq)
+static void nvme_free_queue(struct nvme_queue *nvmeq)
 {
+	spin_lock_irq(&nvmeq->q_lock);
+	while (bio_list_peek(&nvmeq->sq_cong)) {
+		struct bio *bio = bio_list_pop(&nvmeq->sq_cong);
+		bio_endio(bio, -EIO);
+	}
+	spin_unlock_irq(&nvmeq->q_lock);
+
 	dma_free_coherent(nvmeq->q_dmadev, CQ_SIZE(nvmeq->q_depth),
 				(void *)nvmeq->cqes, nvmeq->cq_dma_addr);
 	dma_free_coherent(nvmeq->q_dmadev, SQ_SIZE(nvmeq->q_depth),
@@ -995,17 +1046,28 @@ static void nvme_free_queue_mem(struct nvme_queue *nvmeq)
 	kfree(nvmeq);
 }
 
-static void nvme_free_queue(struct nvme_dev *dev, int qid)
+static void nvme_free_queues(struct nvme_dev *dev)
+{
+	int i;
+
+	for (i = dev->queue_count - 1; i >= 0; i--) {
+		nvme_free_queue(dev->queues[i]);
+		dev->queue_count--;
+		dev->queues[i] = NULL;
+	}
+}
+
+static void nvme_disable_queue(struct nvme_dev *dev, int qid)
 {
 	struct nvme_queue *nvmeq = dev->queues[qid];
 	int vector = dev->entry[nvmeq->cq_vector].vector;
 
 	spin_lock_irq(&nvmeq->q_lock);
-	nvme_cancel_ios(nvmeq, false);
-	while (bio_list_peek(&nvmeq->sq_cong)) {
-		struct bio *bio = bio_list_pop(&nvmeq->sq_cong);
-		bio_endio(bio, -EIO);
+	if (nvmeq->q_suspended) {
+		spin_unlock_irq(&nvmeq->q_lock);
+		return;
 	}
+	nvmeq->q_suspended = 1;
 	spin_unlock_irq(&nvmeq->q_lock);
 
 	irq_set_affinity_hint(vector, NULL);
@@ -1017,15 +1079,17 @@ static void nvme_free_queue(struct nvme_dev *dev, int qid)
 		adapter_delete_cq(dev, qid);
 	}
 
-	nvme_free_queue_mem(nvmeq);
+	spin_lock_irq(&nvmeq->q_lock);
+	nvme_process_cq(nvmeq);
+	nvme_cancel_ios(nvmeq, false);
+	spin_unlock_irq(&nvmeq->q_lock);
 }
 
 static struct nvme_queue *nvme_alloc_queue(struct nvme_dev *dev, int qid,
 							int depth, int vector)
 {
 	struct device *dmadev = &dev->pci_dev->dev;
-	unsigned extra = DIV_ROUND_UP(depth, 8) + (depth *
-						sizeof(struct nvme_cmd_info));
+	unsigned extra = nvme_queue_extra(depth);
 	struct nvme_queue *nvmeq = kzalloc(sizeof(*nvmeq) + extra, GFP_KERNEL);
 	if (!nvmeq)
 		return NULL;
@@ -1052,6 +1116,8 @@ static struct nvme_queue *nvme_alloc_queue(struct nvme_dev *dev, int qid,
 	nvmeq->q_db = &dev->dbs[qid << (dev->db_stride + 1)];
 	nvmeq->q_depth = depth;
 	nvmeq->cq_vector = vector;
+	nvmeq->q_suspended = 1;
+	dev->queue_count++;
 
 	return nvmeq;
 
@@ -1075,18 +1141,29 @@ static int queue_request_irq(struct nvme_dev *dev, struct nvme_queue *nvmeq,
 				IRQF_DISABLED | IRQF_SHARED, name, nvmeq);
 }
 
-static struct nvme_queue *nvme_create_queue(struct nvme_dev *dev, int qid,
-					    int cq_size, int vector)
+static void nvme_init_queue(struct nvme_queue *nvmeq, u16 qid)
 {
-	int result;
-	struct nvme_queue *nvmeq = nvme_alloc_queue(dev, qid, cq_size, vector);
+	struct nvme_dev *dev = nvmeq->dev;
+	unsigned extra = nvme_queue_extra(nvmeq->q_depth);
 
-	if (!nvmeq)
-		return ERR_PTR(-ENOMEM);
+	nvmeq->sq_tail = 0;
+	nvmeq->cq_head = 0;
+	nvmeq->cq_phase = 1;
+	nvmeq->q_db = &dev->dbs[qid << (dev->db_stride + 1)];
+	memset(nvmeq->cmdid_data, 0, extra);
+	memset((void *)nvmeq->cqes, 0, CQ_SIZE(nvmeq->q_depth));
+	nvme_cancel_ios(nvmeq, false);
+	nvmeq->q_suspended = 0;
+}
+
+static int nvme_create_queue(struct nvme_queue *nvmeq, int qid)
+{
+	struct nvme_dev *dev = nvmeq->dev;
+	int result;
 
 	result = adapter_alloc_cq(dev, qid, nvmeq);
 	if (result < 0)
-		goto free_nvmeq;
+		return result;
 
 	result = adapter_alloc_sq(dev, qid, nvmeq);
 	if (result < 0)
@@ -1096,19 +1173,17 @@ static struct nvme_queue *nvme_create_queue(struct nvme_dev *dev, int qid,
 	if (result < 0)
 		goto release_sq;
 
-	return nvmeq;
+	spin_lock(&nvmeq->q_lock);
+	nvme_init_queue(nvmeq, qid);
+	spin_unlock(&nvmeq->q_lock);
+
+	return result;
 
  release_sq:
 	adapter_delete_sq(dev, qid);
  release_cq:
 	adapter_delete_cq(dev, qid);
- free_nvmeq:
-	dma_free_coherent(nvmeq->q_dmadev, CQ_SIZE(nvmeq->q_depth),
-				(void *)nvmeq->cqes, nvmeq->cq_dma_addr);
-	dma_free_coherent(nvmeq->q_dmadev, SQ_SIZE(nvmeq->q_depth),
-					nvmeq->sq_cmds, nvmeq->sq_dma_addr);
-	kfree(nvmeq);
-	return ERR_PTR(result);
+	return result;
 }
 
 static int nvme_wait_ready(struct nvme_dev *dev, u64 cap, bool enabled)
@@ -1152,6 +1227,30 @@ static int nvme_enable_ctrl(struct nvme_dev *dev, u64 cap)
 	return nvme_wait_ready(dev, cap, true);
 }
 
+static int nvme_shutdown_ctrl(struct nvme_dev *dev)
+{
+	unsigned long timeout;
+	u32 cc;
+
+	cc = (readl(&dev->bar->cc) & ~NVME_CC_SHN_MASK) | NVME_CC_SHN_NORMAL;
+	writel(cc, &dev->bar->cc);
+
+	timeout = 2 * HZ + jiffies;
+	while ((readl(&dev->bar->csts) & NVME_CSTS_SHST_MASK) !=
+							NVME_CSTS_SHST_CMPLT) {
+		msleep(100);
+		if (fatal_signal_pending(current))
+			return -EINTR;
+		if (time_after(jiffies, timeout)) {
+			dev_err(&dev->pci_dev->dev,
+				"Device shutdown incomplete; abort shutdown\n");
+			return -ENODEV;
+		}
+	}
+
+	return 0;
+}
+
 static int nvme_configure_admin_queue(struct nvme_dev *dev)
 {
 	int result;
@@ -1159,16 +1258,17 @@ static int nvme_configure_admin_queue(struct nvme_dev *dev)
 	u64 cap = readq(&dev->bar->cap);
 	struct nvme_queue *nvmeq;
 
-	dev->dbs = ((void __iomem *)dev->bar) + 4096;
-	dev->db_stride = NVME_CAP_STRIDE(cap);
-
 	result = nvme_disable_ctrl(dev, cap);
 	if (result < 0)
 		return result;
 
-	nvmeq = nvme_alloc_queue(dev, 0, 64, 0);
-	if (!nvmeq)
-		return -ENOMEM;
+	nvmeq = dev->queues[0];
+	if (!nvmeq) {
+		nvmeq = nvme_alloc_queue(dev, 0, 64, 0);
+		if (!nvmeq)
+			return -ENOMEM;
+		dev->queues[0] = nvmeq;
+	}
 
 	aqa = nvmeq->q_depth - 1;
 	aqa |= aqa << 16;
@@ -1185,17 +1285,15 @@ static int nvme_configure_admin_queue(struct nvme_dev *dev)
 
 	result = nvme_enable_ctrl(dev, cap);
 	if (result)
-		goto free_q;
+		return result;
 
 	result = queue_request_irq(dev, nvmeq, "nvme admin");
 	if (result)
-		goto free_q;
-
-	dev->queues[0] = nvmeq;
-	return result;
+		return result;
 
- free_q:
-	nvme_free_queue_mem(nvmeq);
+	spin_lock(&nvmeq->q_lock);
+	nvme_init_queue(nvmeq, 0);
+	spin_unlock(&nvmeq->q_lock);
 	return result;
 }
 
@@ -1314,7 +1412,8 @@ static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio)
 	c.rw.appmask = cpu_to_le16(io.appmask);
 
 	if (meta_len) {
-		meta_iod = nvme_map_user_pages(dev, io.opcode & 1, io.metadata, meta_len);
+		meta_iod = nvme_map_user_pages(dev, io.opcode & 1, io.metadata,
+								meta_len);
 		if (IS_ERR(meta_iod)) {
 			status = PTR_ERR(meta_iod);
 			meta_iod = NULL;
@@ -1356,6 +1455,8 @@ static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio)
 	put_nvmeq(nvmeq);
 	if (length != (io.nblocks + 1) << ns->lba_shift)
 		status = -ENOMEM;
+	else if (!nvmeq || nvmeq->q_suspended)
+		status = -EBUSY;
 	else
 		status = nvme_submit_sync_cmd(nvmeq, &c, NULL, NVME_IO_TIMEOUT);
 
@@ -1453,6 +1554,7 @@ static int nvme_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd,
 
 	switch (cmd) {
 	case NVME_IOCTL_ID:
+		force_successful_syscall_return();
 		return ns->ns_id;
 	case NVME_IOCTL_ADMIN_CMD:
 		return nvme_user_admin_cmd(ns->dev, (void __user *)arg);
@@ -1506,10 +1608,12 @@ static int nvme_kthread(void *data)
 				if (!nvmeq)
 					continue;
 				spin_lock_irq(&nvmeq->q_lock);
-				if (nvme_process_cq(nvmeq))
-					printk("process_cq did something\n");
+				if (nvmeq->q_suspended)
+					goto unlock;
+				nvme_process_cq(nvmeq);
 				nvme_cancel_ios(nvmeq, true);
 				nvme_resubmit_bios(nvmeq);
+ unlock:
 				spin_unlock_irq(&nvmeq->q_lock);
 			}
 		}
@@ -1556,7 +1660,7 @@ static void nvme_config_discard(struct nvme_ns *ns)
 	queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, ns->queue);
 }
 
-static struct nvme_ns *nvme_alloc_ns(struct nvme_dev *dev, int nsid,
+static struct nvme_ns *nvme_alloc_ns(struct nvme_dev *dev, unsigned nsid,
 			struct nvme_id_ns *id, struct nvme_lba_range_type *rt)
 {
 	struct nvme_ns *ns;
@@ -1631,14 +1735,19 @@ static int set_queue_count(struct nvme_dev *dev, int count)
 	status = nvme_set_features(dev, NVME_FEAT_NUM_QUEUES, q_count, 0,
 								&result);
 	if (status)
-		return -EIO;
+		return status < 0 ? -EIO : -EBUSY;
 	return min(result & 0xffff, result >> 16) + 1;
 }
 
+static size_t db_bar_size(struct nvme_dev *dev, unsigned nr_io_queues)
+{
+	return 4096 + ((nr_io_queues + 1) << (dev->db_stride + 3));
+}
+
 static int nvme_setup_io_queues(struct nvme_dev *dev)
 {
 	struct pci_dev *pdev = dev->pci_dev;
-	int result, cpu, i, nr_io_queues, db_bar_size, q_depth, q_count;
+	int result, cpu, i, vecs, nr_io_queues, size, q_depth;
 
 	nr_io_queues = num_online_cpus();
 	result = set_queue_count(dev, nr_io_queues);
@@ -1647,53 +1756,80 @@ static int nvme_setup_io_queues(struct nvme_dev *dev)
 	if (result < nr_io_queues)
 		nr_io_queues = result;
 
-	q_count = nr_io_queues;
-	/* Deregister the admin queue's interrupt */
-	free_irq(dev->entry[0].vector, dev->queues[0]);
-
-	db_bar_size = 4096 + ((nr_io_queues + 1) << (dev->db_stride + 3));
-	if (db_bar_size > 8192) {
+	size = db_bar_size(dev, nr_io_queues);
+	if (size > 8192) {
 		iounmap(dev->bar);
-		dev->bar = ioremap(pci_resource_start(pdev, 0), db_bar_size);
+		do {
+			dev->bar = ioremap(pci_resource_start(pdev, 0), size);
+			if (dev->bar)
+				break;
+			if (!--nr_io_queues)
+				return -ENOMEM;
+			size = db_bar_size(dev, nr_io_queues);
+		} while (1);
 		dev->dbs = ((void __iomem *)dev->bar) + 4096;
 		dev->queues[0]->q_db = dev->dbs;
 	}
 
-	for (i = 0; i < nr_io_queues; i++)
+	/* Deregister the admin queue's interrupt */
+	free_irq(dev->entry[0].vector, dev->queues[0]);
+
+	vecs = nr_io_queues;
+	for (i = 0; i < vecs; i++)
 		dev->entry[i].entry = i;
 	for (;;) {
-		result = pci_enable_msix(pdev, dev->entry, nr_io_queues);
-		if (result == 0) {
-			break;
-		} else if (result > 0) {
-			nr_io_queues = result;
-			continue;
-		} else {
-			nr_io_queues = 0;
+		result = pci_enable_msix(pdev, dev->entry, vecs);
+		if (result <= 0)
 			break;
-		}
+		vecs = result;
 	}
 
-	if (nr_io_queues == 0) {
-		nr_io_queues = q_count;
+	if (result < 0) {
+		vecs = nr_io_queues;
+		if (vecs > 32)
+			vecs = 32;
 		for (;;) {
-			result = pci_enable_msi_block(pdev, nr_io_queues);
+			result = pci_enable_msi_block(pdev, vecs);
 			if (result == 0) {
-				for (i = 0; i < nr_io_queues; i++)
+				for (i = 0; i < vecs; i++)
 					dev->entry[i].vector = i + pdev->irq;
 				break;
-			} else if (result > 0) {
-				nr_io_queues = result;
-				continue;
-			} else {
-				nr_io_queues = 1;
+			} else if (result < 0) {
+				vecs = 1;
 				break;
 			}
+			vecs = result;
 		}
 	}
 
+	/*
+	 * Should investigate if there's a performance win from allocating
+	 * more queues than interrupt vectors; it might allow the submission
+	 * path to scale better, even if the receive path is limited by the
+	 * number of interrupts.
+	 */
+	nr_io_queues = vecs;
+
 	result = queue_request_irq(dev, dev->queues[0], "nvme admin");
-	/* XXX: handle failure here */
+	if (result) {
+		dev->queues[0]->q_suspended = 1;
+		goto free_queues;
+	}
+
+	/* Free previously allocated queues that are no longer usable */
+	spin_lock(&dev_list_lock);
+	for (i = dev->queue_count - 1; i > nr_io_queues; i--) {
+		struct nvme_queue *nvmeq = dev->queues[i];
+
+		spin_lock(&nvmeq->q_lock);
+		nvme_cancel_ios(nvmeq, false);
+		spin_unlock(&nvmeq->q_lock);
+
+		nvme_free_queue(nvmeq);
+		dev->queue_count--;
+		dev->queues[i] = NULL;
+	}
+	spin_unlock(&dev_list_lock);
 
 	cpu = cpumask_first(cpu_online_mask);
 	for (i = 0; i < nr_io_queues; i++) {
@@ -1703,11 +1839,12 @@ static int nvme_setup_io_queues(struct nvme_dev *dev)
 
 	q_depth = min_t(int, NVME_CAP_MQES(readq(&dev->bar->cap)) + 1,
 								NVME_Q_DEPTH);
-	for (i = 0; i < nr_io_queues; i++) {
-		dev->queues[i + 1] = nvme_create_queue(dev, i + 1, q_depth, i);
-		if (IS_ERR(dev->queues[i + 1]))
-			return PTR_ERR(dev->queues[i + 1]);
-		dev->queue_count++;
+	for (i = dev->queue_count - 1; i < nr_io_queues; i++) {
+		dev->queues[i + 1] = nvme_alloc_queue(dev, i + 1, q_depth, i);
+		if (!dev->queues[i + 1]) {
+			result = -ENOMEM;
+			goto free_queues;
+		}
 	}
 
 	for (; i < num_possible_cpus(); i++) {
@@ -1715,15 +1852,20 @@ static int nvme_setup_io_queues(struct nvme_dev *dev)
 		dev->queues[i + 1] = dev->queues[target + 1];
 	}
 
-	return 0;
-}
+	for (i = 1; i < dev->queue_count; i++) {
+		result = nvme_create_queue(dev->queues[i], i);
+		if (result) {
+			for (--i; i > 0; i--)
+				nvme_disable_queue(dev, i);
+			goto free_queues;
+		}
+	}
 
-static void nvme_free_queues(struct nvme_dev *dev)
-{
-	int i;
+	return 0;
 
-	for (i = dev->queue_count - 1; i >= 0; i--)
-		nvme_free_queue(dev, i);
+ free_queues:
+	nvme_free_queues(dev);
+	return result;
 }
 
 /*
@@ -1734,7 +1876,8 @@ static void nvme_free_queues(struct nvme_dev *dev)
  */
 static int nvme_dev_add(struct nvme_dev *dev)
 {
-	int res, nn, i;
+	int res;
+	unsigned nn, i;
 	struct nvme_ns *ns;
 	struct nvme_id_ctrl *ctrl;
 	struct nvme_id_ns *id_ns;
@@ -1742,10 +1885,6 @@ static int nvme_dev_add(struct nvme_dev *dev)
 	dma_addr_t dma_addr;
 	int shift = NVME_CAP_MPSMIN(readq(&dev->bar->cap)) + 12;
 
-	res = nvme_setup_io_queues(dev);
-	if (res)
-		return res;
-
 	mem = dma_alloc_coherent(&dev->pci_dev->dev, 8192, &dma_addr,
 								GFP_KERNEL);
 	if (!mem)
@@ -1796,23 +1935,86 @@ static int nvme_dev_add(struct nvme_dev *dev)
 	return res;
 }
 
-static int nvme_dev_remove(struct nvme_dev *dev)
+static int nvme_dev_map(struct nvme_dev *dev)
 {
-	struct nvme_ns *ns, *next;
+	int bars, result = -ENOMEM;
+	struct pci_dev *pdev = dev->pci_dev;
+
+	if (pci_enable_device_mem(pdev))
+		return result;
+
+	dev->entry[0].vector = pdev->irq;
+	pci_set_master(pdev);
+	bars = pci_select_bars(pdev, IORESOURCE_MEM);
+	if (pci_request_selected_regions(pdev, bars, "nvme"))
+		goto disable_pci;
+
+	if (!dma_set_mask(&pdev->dev, DMA_BIT_MASK(64)))
+		dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(64));
+	else if (!dma_set_mask(&pdev->dev, DMA_BIT_MASK(32)))
+		dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(32));
+	else
+		goto disable_pci;
+
+	pci_set_drvdata(pdev, dev);
+	dev->bar = ioremap(pci_resource_start(pdev, 0), 8192);
+	if (!dev->bar)
+		goto disable;
+
+	dev->db_stride = NVME_CAP_STRIDE(readq(&dev->bar->cap));
+	dev->dbs = ((void __iomem *)dev->bar) + 4096;
+
+	return 0;
+
+ disable:
+	pci_release_regions(pdev);
+ disable_pci:
+	pci_disable_device(pdev);
+	return result;
+}
+
+static void nvme_dev_unmap(struct nvme_dev *dev)
+{
+	if (dev->pci_dev->msi_enabled)
+		pci_disable_msi(dev->pci_dev);
+	else if (dev->pci_dev->msix_enabled)
+		pci_disable_msix(dev->pci_dev);
+
+	if (dev->bar) {
+		iounmap(dev->bar);
+		dev->bar = NULL;
+	}
+
+	pci_release_regions(dev->pci_dev);
+	if (pci_is_enabled(dev->pci_dev))
+		pci_disable_device(dev->pci_dev);
+}
+
+static void nvme_dev_shutdown(struct nvme_dev *dev)
+{
+	int i;
+
+	for (i = dev->queue_count - 1; i >= 0; i--)
+		nvme_disable_queue(dev, i);
 
 	spin_lock(&dev_list_lock);
-	list_del(&dev->node);
+	list_del_init(&dev->node);
 	spin_unlock(&dev_list_lock);
 
+	if (dev->bar)
+		nvme_shutdown_ctrl(dev);
+	nvme_dev_unmap(dev);
+}
+
+static void nvme_dev_remove(struct nvme_dev *dev)
+{
+	struct nvme_ns *ns, *next;
+
 	list_for_each_entry_safe(ns, next, &dev->namespaces, list) {
 		list_del(&ns->list);
 		del_gendisk(ns->disk);
 		nvme_ns_free(ns);
 	}
-
-	nvme_free_queues(dev);
-
-	return 0;
 }
 
 static int nvme_setup_prp_pools(struct nvme_dev *dev)
@@ -1872,15 +2074,10 @@ static void nvme_free_dev(struct kref *kref)
 {
 	struct nvme_dev *dev = container_of(kref, struct nvme_dev, kref);
 	nvme_dev_remove(dev);
-	if (dev->pci_dev->msi_enabled)
-		pci_disable_msi(dev->pci_dev);
-	else if (dev->pci_dev->msix_enabled)
-		pci_disable_msix(dev->pci_dev);
-	iounmap(dev->bar);
+	nvme_dev_shutdown(dev);
+	nvme_free_queues(dev);
 	nvme_release_instance(dev);
 	nvme_release_prp_pools(dev);
-	pci_disable_device(dev->pci_dev);
-	pci_release_regions(dev->pci_dev);
 	kfree(dev->queues);
 	kfree(dev->entry);
 	kfree(dev);
@@ -1921,9 +2118,40 @@ static const struct file_operations nvme_dev_fops = {
 	.compat_ioctl	= nvme_dev_ioctl,
 };
 
+static int nvme_dev_start(struct nvme_dev *dev)
+{
+	int result;
+
+	result = nvme_dev_map(dev);
+	if (result)
+		return result;
+
+	result = nvme_configure_admin_queue(dev);
+	if (result)
+		goto unmap;
+
+	spin_lock(&dev_list_lock);
+	list_add(&dev->node, &dev_list);
+	spin_unlock(&dev_list_lock);
+
+	result = nvme_setup_io_queues(dev);
+	if (result && result != -EBUSY)
+		goto disable;
+
+	return result;
+
+ disable:
+	spin_lock(&dev_list_lock);
+	list_del_init(&dev->node);
+	spin_unlock(&dev_list_lock);
+ unmap:
+	nvme_dev_unmap(dev);
+	return result;
+}
+
 static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 {
-	int bars, result = -ENOMEM;
+	int result = -ENOMEM;
 	struct nvme_dev *dev;
 
 	dev = kzalloc(sizeof(*dev), GFP_KERNEL);
@@ -1938,53 +2166,28 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (!dev->queues)
 		goto free;
 
-	if (pci_enable_device_mem(pdev))
-		goto free;
-	pci_set_master(pdev);
-	bars = pci_select_bars(pdev, IORESOURCE_MEM);
-	if (pci_request_selected_regions(pdev, bars, "nvme"))
-		goto disable;
-
 	INIT_LIST_HEAD(&dev->namespaces);
 	dev->pci_dev = pdev;
-	pci_set_drvdata(pdev, dev);
-
-	if (!dma_set_mask(&pdev->dev, DMA_BIT_MASK(64)))
-		dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(64));
-	else if (!dma_set_mask(&pdev->dev, DMA_BIT_MASK(32)))
-		dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(32));
-	else
-		goto disable;
-
 	result = nvme_set_instance(dev);
 	if (result)
-		goto disable;
-
-	dev->entry[0].vector = pdev->irq;
+		goto free;
 
 	result = nvme_setup_prp_pools(dev);
 	if (result)
-		goto disable_msix;
+		goto release;
 
-	dev->bar = ioremap(pci_resource_start(pdev, 0), 8192);
-	if (!dev->bar) {
-		result = -ENOMEM;
-		goto disable_msix;
+	result = nvme_dev_start(dev);
+	if (result) {
+		if (result == -EBUSY)
+			goto create_cdev;
+		goto release_pools;
 	}
 
-	result = nvme_configure_admin_queue(dev);
-	if (result)
-		goto unmap;
-	dev->queue_count++;
-
-	spin_lock(&dev_list_lock);
-	list_add(&dev->node, &dev_list);
-	spin_unlock(&dev_list_lock);
-
 	result = nvme_dev_add(dev);
 	if (result)
-		goto delete;
+		goto shutdown;
 
+ create_cdev:
 	scnprintf(dev->name, sizeof(dev->name), "nvme%d", dev->instance);
 	dev->miscdev.minor = MISC_DYNAMIC_MINOR;
 	dev->miscdev.parent = &pdev->dev;
@@ -1999,24 +2202,13 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 
  remove:
 	nvme_dev_remove(dev);
- delete:
-	spin_lock(&dev_list_lock);
-	list_del(&dev->node);
-	spin_unlock(&dev_list_lock);
-
+ shutdown:
+	nvme_dev_shutdown(dev);
+ release_pools:
 	nvme_free_queues(dev);
- unmap:
-	iounmap(dev->bar);
- disable_msix:
-	if (dev->pci_dev->msi_enabled)
-		pci_disable_msi(dev->pci_dev);
-	else if (dev->pci_dev->msix_enabled)
-		pci_disable_msix(dev->pci_dev);
-	nvme_release_instance(dev);
 	nvme_release_prp_pools(dev);
- disable:
-	pci_disable_device(pdev);
-	pci_release_regions(pdev);
+ release:
+	nvme_release_instance(dev);
  free:
 	kfree(dev->queues);
 	kfree(dev->entry);
@@ -2037,8 +2229,30 @@ static void nvme_remove(struct pci_dev *pdev)
 #define nvme_link_reset NULL
 #define nvme_slot_reset NULL
 #define nvme_error_resume NULL
-#define nvme_suspend NULL
-#define nvme_resume NULL
+
+static int nvme_suspend(struct device *dev)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct nvme_dev *ndev = pci_get_drvdata(pdev);
+
+	nvme_dev_shutdown(ndev);
+	return 0;
+}
+
+static int nvme_resume(struct device *dev)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct nvme_dev *ndev = pci_get_drvdata(pdev);
+	int ret;
+
+	ret = nvme_dev_start(ndev);
+	/* XXX: should remove gendisks if resume fails */
+	if (ret)
+		nvme_free_queues(ndev);
+	return ret;
+}
+
+static SIMPLE_DEV_PM_OPS(nvme_dev_pm_ops, nvme_suspend, nvme_resume);
 
 static const struct pci_error_handlers nvme_err_handler = {
 	.error_detected	= nvme_error_detected,
@@ -2062,8 +2276,9 @@ static struct pci_driver nvme_driver = {
 	.id_table	= nvme_id_table,
 	.probe		= nvme_probe,
 	.remove		= nvme_remove,
-	.suspend	= nvme_suspend,
-	.resume		= nvme_resume,
+	.driver		= {
+		.pm	= &nvme_dev_pm_ops,
+	},
 	.err_handler	= &nvme_err_handler,
 };
 
diff --git a/drivers/block/nvme-scsi.c b/drivers/block/nvme-scsi.c
index 102de2f52b5c..4a4ff4eb8e23 100644
--- a/drivers/block/nvme-scsi.c
+++ b/drivers/block/nvme-scsi.c
@@ -933,13 +933,12 @@ static int nvme_trans_bdev_char_page(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 	int res = SNTI_TRANSLATION_SUCCESS;
 	int xfer_len;
 
-	inq_response = kmalloc(EXTENDED_INQUIRY_DATA_PAGE_LENGTH, GFP_KERNEL);
+	inq_response = kzalloc(EXTENDED_INQUIRY_DATA_PAGE_LENGTH, GFP_KERNEL);
 	if (inq_response == NULL) {
 		res = -ENOMEM;
 		goto out_mem;
 	}
 
-	memset(inq_response, 0, EXTENDED_INQUIRY_DATA_PAGE_LENGTH);
 	inq_response[1] = INQ_BDEV_CHARACTERISTICS_PAGE;    /* Page Code */
 	inq_response[2] = 0x00;    /* Page Length MSB */
 	inq_response[3] = 0x3C;    /* Page Length LSB */
@@ -964,12 +963,11 @@ static int nvme_trans_log_supp_pages(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 	int xfer_len;
 	u8 *log_response;
 
-	log_response = kmalloc(LOG_PAGE_SUPPORTED_LOG_PAGES_LENGTH, GFP_KERNEL);
+	log_response = kzalloc(LOG_PAGE_SUPPORTED_LOG_PAGES_LENGTH, GFP_KERNEL);
 	if (log_response == NULL) {
 		res = -ENOMEM;
 		goto out_mem;
 	}
-	memset(log_response, 0, LOG_PAGE_SUPPORTED_LOG_PAGES_LENGTH);
 
 	log_response[0] = LOG_PAGE_SUPPORTED_LOG_PAGES_PAGE;
 	/* Subpage=0x00, Page Length MSB=0 */
@@ -1000,12 +998,11 @@ static int nvme_trans_log_info_exceptions(struct nvme_ns *ns,
 	u8 temp_c;
 	u16 temp_k;
 
-	log_response = kmalloc(LOG_INFO_EXCP_PAGE_LENGTH, GFP_KERNEL);
+	log_response = kzalloc(LOG_INFO_EXCP_PAGE_LENGTH, GFP_KERNEL);
 	if (log_response == NULL) {
 		res = -ENOMEM;
 		goto out_mem;
 	}
-	memset(log_response, 0, LOG_INFO_EXCP_PAGE_LENGTH);
 
 	mem = dma_alloc_coherent(&dev->pci_dev->dev,
 					sizeof(struct nvme_smart_log),
@@ -1069,12 +1066,11 @@ static int nvme_trans_log_temperature(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 	u8 temp_c_cur, temp_c_thresh;
 	u16 temp_k;
 
-	log_response = kmalloc(LOG_TEMP_PAGE_LENGTH, GFP_KERNEL);
+	log_response = kzalloc(LOG_TEMP_PAGE_LENGTH, GFP_KERNEL);
 	if (log_response == NULL) {
 		res = -ENOMEM;
 		goto out_mem;
 	}
-	memset(log_response, 0, LOG_TEMP_PAGE_LENGTH);
 
 	mem = dma_alloc_coherent(&dev->pci_dev->dev,
 					sizeof(struct nvme_smart_log),
@@ -1380,12 +1376,11 @@ static int nvme_trans_mode_page_create(struct nvme_ns *ns,
 	blk_desc_offset = mph_size;
 	mode_pages_offset_1 = blk_desc_offset + blk_desc_len;
 
-	response = kmalloc(resp_size, GFP_KERNEL);
+	response = kzalloc(resp_size, GFP_KERNEL);
 	if (response == NULL) {
 		res = -ENOMEM;
 		goto out_mem;
 	}
-	memset(response, 0, resp_size);
 
 	res = nvme_trans_fill_mode_parm_hdr(&response[0], mph_size, cdb10,
 					llbaa, mode_data_length, blk_desc_len);
@@ -2480,12 +2475,11 @@ static int nvme_trans_read_capacity(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 	}
 	id_ns = mem;
 
-	response = kmalloc(resp_size, GFP_KERNEL);
+	response = kzalloc(resp_size, GFP_KERNEL);
 	if (response == NULL) {
 		res = -ENOMEM;
 		goto out_dma;
 	}
-	memset(response, 0, resp_size);
 	nvme_trans_fill_read_cap(response, id_ns, cdb16);
 
 	xfer_len = min(alloc_len, resp_size);
@@ -2554,12 +2548,11 @@ static int nvme_trans_report_luns(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 			goto out_dma;
 		}
 
-		response = kmalloc(resp_size, GFP_KERNEL);
+		response = kzalloc(resp_size, GFP_KERNEL);
 		if (response == NULL) {
 			res = -ENOMEM;
 			goto out_dma;
 		}
-		memset(response, 0, resp_size);
 
 		/* The first LUN ID will always be 0 per the SAM spec */
 		for (lun_id = 0; lun_id < le32_to_cpu(id_ctrl->nn); lun_id++) {
@@ -2600,12 +2593,11 @@ static int nvme_trans_request_sense(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 
 	resp_size = ((desc_format) ? (DESC_FMT_SENSE_DATA_SIZE) :
 					(FIXED_FMT_SENSE_DATA_SIZE));
-	response = kmalloc(resp_size, GFP_KERNEL);
+	response = kzalloc(resp_size, GFP_KERNEL);
 	if (response == NULL) {
 		res = -ENOMEM;
 		goto out;
 	}
-	memset(response, 0, resp_size);
 
 	if (desc_format == DESCRIPTOR_FORMAT_SENSE_DATA_TYPE) {
 		/* Descriptor Format Sense Data */
diff --git a/drivers/block/osdblk.c b/drivers/block/osdblk.c
index 1bbc681688e4..79aa179305b5 100644
--- a/drivers/block/osdblk.c
+++ b/drivers/block/osdblk.c
@@ -598,7 +598,7 @@ static ssize_t class_osdblk_remove(struct class *c,
 	unsigned long ul;
 	struct list_head *tmp;
 
-	rc = strict_strtoul(buf, 10, &ul);
+	rc = kstrtoul(buf, 10, &ul);
 	if (rc)
 		return rc;
 
diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c
index f5d0ea11d9fd..56188475cfd3 100644
--- a/drivers/block/pktcdvd.c
+++ b/drivers/block/pktcdvd.c
@@ -44,6 +44,8 @@
  *
  *************************************************************************/
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/pktcdvd.h>
 #include <linux/module.h>
 #include <linux/types.h>
@@ -69,23 +71,24 @@
 
 #define DRIVER_NAME	"pktcdvd"
 
-#if PACKET_DEBUG
-#define DPRINTK(fmt, args...) printk(KERN_NOTICE fmt, ##args)
-#else
-#define DPRINTK(fmt, args...)
-#endif
-
-#if PACKET_DEBUG > 1
-#define VPRINTK(fmt, args...) printk(KERN_NOTICE fmt, ##args)
-#else
-#define VPRINTK(fmt, args...)
-#endif
+#define pkt_err(pd, fmt, ...)						\
+	pr_err("%s: " fmt, pd->name, ##__VA_ARGS__)
+#define pkt_notice(pd, fmt, ...)					\
+	pr_notice("%s: " fmt, pd->name, ##__VA_ARGS__)
+#define pkt_info(pd, fmt, ...)						\
+	pr_info("%s: " fmt, pd->name, ##__VA_ARGS__)
+
+#define pkt_dbg(level, pd, fmt, ...)					\
+do {									\
+	if (level == 2 && PACKET_DEBUG >= 2)				\
+		pr_notice("%s: %s():" fmt,				\
+			  pd->name, __func__, ##__VA_ARGS__);		\
+	else if (level == 1 && PACKET_DEBUG >= 1)			\
+		pr_notice("%s: " fmt, pd->name, ##__VA_ARGS__);		\
+} while (0)
 
 #define MAX_SPEED 0xffff
 
-#define ZONE(sector, pd) (((sector) + (pd)->offset) & \
-			~(sector_t)((pd)->settings.size - 1))
-
 static DEFINE_MUTEX(pktcdvd_mutex);
 static struct pktcdvd_device *pkt_devs[MAX_WRITERS];
 static struct proc_dir_entry *pkt_proc;
@@ -103,7 +106,10 @@ static int pkt_setup_dev(dev_t dev, dev_t* pkt_dev);
 static int pkt_remove_dev(dev_t pkt_dev);
 static int pkt_seq_show(struct seq_file *m, void *p);
 
-
+static sector_t get_zone(sector_t sector, struct pktcdvd_device *pd)
+{
+	return (sector + pd->offset) & ~(sector_t)(pd->settings.size - 1);
+}
 
 /*
  * create and register a pktcdvd kernel object.
@@ -424,7 +430,7 @@ static int pkt_sysfs_init(void)
 	if (ret) {
 		kfree(class_pktcdvd);
 		class_pktcdvd = NULL;
-		printk(DRIVER_NAME": failed to create class pktcdvd\n");
+		pr_err("failed to create class pktcdvd\n");
 		return ret;
 	}
 	return 0;
@@ -517,7 +523,7 @@ static void pkt_bio_finished(struct pktcdvd_device *pd)
 {
 	BUG_ON(atomic_read(&pd->cdrw.pending_bios) <= 0);
 	if (atomic_dec_and_test(&pd->cdrw.pending_bios)) {
-		VPRINTK(DRIVER_NAME": queue empty\n");
+		pkt_dbg(2, pd, "queue empty\n");
 		atomic_set(&pd->iosched.attention, 1);
 		wake_up(&pd->wqueue);
 	}
@@ -734,36 +740,33 @@ out:
 	return ret;
 }
 
+static const char *sense_key_string(__u8 index)
+{
+	static const char * const info[] = {
+		"No sense", "Recovered error", "Not ready",
+		"Medium error", "Hardware error", "Illegal request",
+		"Unit attention", "Data protect", "Blank check",
+	};
+
+	return index < ARRAY_SIZE(info) ? info[index] : "INVALID";
+}
+
 /*
  * A generic sense dump / resolve mechanism should be implemented across
  * all ATAPI + SCSI devices.
  */
-static void pkt_dump_sense(struct packet_command *cgc)
+static void pkt_dump_sense(struct pktcdvd_device *pd,
+			   struct packet_command *cgc)
 {
-	static char *info[9] = { "No sense", "Recovered error", "Not ready",
-				 "Medium error", "Hardware error", "Illegal request",
-				 "Unit attention", "Data protect", "Blank check" };
-	int i;
 	struct request_sense *sense = cgc->sense;
 
-	printk(DRIVER_NAME":");
-	for (i = 0; i < CDROM_PACKET_SIZE; i++)
-		printk(" %02x", cgc->cmd[i]);
-	printk(" - ");
-
-	if (sense == NULL) {
-		printk("no sense\n");
-		return;
-	}
-
-	printk("sense %02x.%02x.%02x", sense->sense_key, sense->asc, sense->ascq);
-
-	if (sense->sense_key > 8) {
-		printk(" (INVALID)\n");
-		return;
-	}
-
-	printk(" (%s)\n", info[sense->sense_key]);
+	if (sense)
+		pkt_err(pd, "%*ph - sense %02x.%02x.%02x (%s)\n",
+			CDROM_PACKET_SIZE, cgc->cmd,
+			sense->sense_key, sense->asc, sense->ascq,
+			sense_key_string(sense->sense_key));
+	else
+		pkt_err(pd, "%*ph - no sense\n", CDROM_PACKET_SIZE, cgc->cmd);
 }
 
 /*
@@ -806,7 +809,7 @@ static noinline_for_stack int pkt_set_speed(struct pktcdvd_device *pd,
 	cgc.cmd[5] = write_speed & 0xff;
 
 	if ((ret = pkt_generic_packet(pd, &cgc)))
-		pkt_dump_sense(&cgc);
+		pkt_dump_sense(pd, &cgc);
 
 	return ret;
 }
@@ -872,7 +875,7 @@ static void pkt_iosched_process_queue(struct pktcdvd_device *pd)
 				need_write_seek = 0;
 			if (need_write_seek && reads_queued) {
 				if (atomic_read(&pd->cdrw.pending_bios) > 0) {
-					VPRINTK(DRIVER_NAME": write, waiting\n");
+					pkt_dbg(2, pd, "write, waiting\n");
 					break;
 				}
 				pkt_flush_cache(pd);
@@ -881,7 +884,7 @@ static void pkt_iosched_process_queue(struct pktcdvd_device *pd)
 		} else {
 			if (!reads_queued && writes_queued) {
 				if (atomic_read(&pd->cdrw.pending_bios) > 0) {
-					VPRINTK(DRIVER_NAME": read, waiting\n");
+					pkt_dbg(2, pd, "read, waiting\n");
 					break;
 				}
 				pd->iosched.writing = 1;
@@ -943,7 +946,7 @@ static int pkt_set_segment_merging(struct pktcdvd_device *pd, struct request_que
 		set_bit(PACKET_MERGE_SEGS, &pd->flags);
 		return 0;
 	} else {
-		printk(DRIVER_NAME": cdrom max_phys_segments too small\n");
+		pkt_err(pd, "cdrom max_phys_segments too small\n");
 		return -EIO;
 	}
 }
@@ -987,8 +990,9 @@ static void pkt_end_io_read(struct bio *bio, int err)
 	struct pktcdvd_device *pd = pkt->pd;
 	BUG_ON(!pd);
 
-	VPRINTK("pkt_end_io_read: bio=%p sec0=%llx sec=%llx err=%d\n", bio,
-		(unsigned long long)pkt->sector, (unsigned long long)bio->bi_sector, err);
+	pkt_dbg(2, pd, "bio=%p sec0=%llx sec=%llx err=%d\n",
+		bio, (unsigned long long)pkt->sector,
+		(unsigned long long)bio->bi_sector, err);
 
 	if (err)
 		atomic_inc(&pkt->io_errors);
@@ -1005,7 +1009,7 @@ static void pkt_end_io_packet_write(struct bio *bio, int err)
 	struct pktcdvd_device *pd = pkt->pd;
 	BUG_ON(!pd);
 
-	VPRINTK("pkt_end_io_packet_write: id=%d, err=%d\n", pkt->id, err);
+	pkt_dbg(2, pd, "id=%d, err=%d\n", pkt->id, err);
 
 	pd->stats.pkt_ended++;
 
@@ -1047,7 +1051,7 @@ static void pkt_gather_data(struct pktcdvd_device *pd, struct packet_data *pkt)
 	spin_unlock(&pkt->lock);
 
 	if (pkt->cache_valid) {
-		VPRINTK("pkt_gather_data: zone %llx cached\n",
+		pkt_dbg(2, pd, "zone %llx cached\n",
 			(unsigned long long)pkt->sector);
 		goto out_account;
 	}
@@ -1070,7 +1074,7 @@ static void pkt_gather_data(struct pktcdvd_device *pd, struct packet_data *pkt)
 
 		p = (f * CD_FRAMESIZE) / PAGE_SIZE;
 		offset = (f * CD_FRAMESIZE) % PAGE_SIZE;
-		VPRINTK("pkt_gather_data: Adding frame %d, page:%p offs:%d\n",
+		pkt_dbg(2, pd, "Adding frame %d, page:%p offs:%d\n",
 			f, pkt->pages[p], offset);
 		if (!bio_add_page(bio, pkt->pages[p], CD_FRAMESIZE, offset))
 			BUG();
@@ -1082,7 +1086,7 @@ static void pkt_gather_data(struct pktcdvd_device *pd, struct packet_data *pkt)
 	}
 
 out_account:
-	VPRINTK("pkt_gather_data: need %d frames for zone %llx\n",
+	pkt_dbg(2, pd, "need %d frames for zone %llx\n",
 		frames_read, (unsigned long long)pkt->sector);
 	pd->stats.pkt_started++;
 	pd->stats.secs_rg += frames_read * (CD_FRAMESIZE >> 9);
@@ -1183,7 +1187,8 @@ static inline void pkt_set_state(struct packet_data *pkt, enum packet_data_state
 		"IDLE", "WAITING", "READ_WAIT", "WRITE_WAIT", "RECOVERY", "FINISHED"
 	};
 	enum packet_data_state old_state = pkt->state;
-	VPRINTK("pkt %2d : s=%6llx %s -> %s\n", pkt->id, (unsigned long long)pkt->sector,
+	pkt_dbg(2, pd, "pkt %2d : s=%6llx %s -> %s\n",
+		pkt->id, (unsigned long long)pkt->sector,
 		state_name[old_state], state_name[state]);
 #endif
 	pkt->state = state;
@@ -1202,12 +1207,10 @@ static int pkt_handle_queue(struct pktcdvd_device *pd)
 	struct rb_node *n;
 	int wakeup;
 
-	VPRINTK("handle_queue\n");
-
 	atomic_set(&pd->scan_queue, 0);
 
 	if (list_empty(&pd->cdrw.pkt_free_list)) {
-		VPRINTK("handle_queue: no pkt\n");
+		pkt_dbg(2, pd, "no pkt\n");
 		return 0;
 	}
 
@@ -1224,7 +1227,7 @@ static int pkt_handle_queue(struct pktcdvd_device *pd)
 	node = first_node;
 	while (node) {
 		bio = node->bio;
-		zone = ZONE(bio->bi_sector, pd);
+		zone = get_zone(bio->bi_sector, pd);
 		list_for_each_entry(p, &pd->cdrw.pkt_active_list, list) {
 			if (p->sector == zone) {
 				bio = NULL;
@@ -1244,7 +1247,7 @@ try_next_bio:
 	}
 	spin_unlock(&pd->lock);
 	if (!bio) {
-		VPRINTK("handle_queue: no bio\n");
+		pkt_dbg(2, pd, "no bio\n");
 		return 0;
 	}
 
@@ -1260,12 +1263,12 @@ try_next_bio:
 	 * to this packet.
 	 */
 	spin_lock(&pd->lock);
-	VPRINTK("pkt_handle_queue: looking for zone %llx\n", (unsigned long long)zone);
+	pkt_dbg(2, pd, "looking for zone %llx\n", (unsigned long long)zone);
 	while ((node = pkt_rbtree_find(pd, zone)) != NULL) {
 		bio = node->bio;
-		VPRINTK("pkt_handle_queue: found zone=%llx\n",
-			(unsigned long long)ZONE(bio->bi_sector, pd));
-		if (ZONE(bio->bi_sector, pd) != zone)
+		pkt_dbg(2, pd, "found zone=%llx\n",
+			(unsigned long long)get_zone(bio->bi_sector, pd));
+		if (get_zone(bio->bi_sector, pd) != zone)
 			break;
 		pkt_rbtree_erase(pd, node);
 		spin_lock(&pkt->lock);
@@ -1316,7 +1319,7 @@ static void pkt_start_write(struct pktcdvd_device *pd, struct packet_data *pkt)
 		if (!bio_add_page(pkt->w_bio, bvec[f].bv_page, CD_FRAMESIZE, bvec[f].bv_offset))
 			BUG();
 	}
-	VPRINTK(DRIVER_NAME": vcnt=%d\n", pkt->w_bio->bi_vcnt);
+	pkt_dbg(2, pd, "vcnt=%d\n", pkt->w_bio->bi_vcnt);
 
 	/*
 	 * Fill-in bvec with data from orig_bios.
@@ -1327,7 +1330,7 @@ static void pkt_start_write(struct pktcdvd_device *pd, struct packet_data *pkt)
 	pkt_set_state(pkt, PACKET_WRITE_WAIT_STATE);
 	spin_unlock(&pkt->lock);
 
-	VPRINTK("pkt_start_write: Writing %d frames for zone %llx\n",
+	pkt_dbg(2, pd, "Writing %d frames for zone %llx\n",
 		pkt->write_size, (unsigned long long)pkt->sector);
 
 	if (test_bit(PACKET_MERGE_SEGS, &pd->flags) || (pkt->write_size < pkt->frames)) {
@@ -1359,7 +1362,7 @@ static void pkt_run_state_machine(struct pktcdvd_device *pd, struct packet_data
 {
 	int uptodate;
 
-	VPRINTK("run_state_machine: pkt %d\n", pkt->id);
+	pkt_dbg(2, pd, "pkt %d\n", pkt->id);
 
 	for (;;) {
 		switch (pkt->state) {
@@ -1398,7 +1401,7 @@ static void pkt_run_state_machine(struct pktcdvd_device *pd, struct packet_data
 			if (pkt_start_recovery(pkt)) {
 				pkt_start_write(pd, pkt);
 			} else {
-				VPRINTK("No recovery possible\n");
+				pkt_dbg(2, pd, "No recovery possible\n");
 				pkt_set_state(pkt, PACKET_FINISHED_STATE);
 			}
 			break;
@@ -1419,8 +1422,6 @@ static void pkt_handle_packets(struct pktcdvd_device *pd)
 {
 	struct packet_data *pkt, *next;
 
-	VPRINTK("pkt_handle_packets\n");
-
 	/*
 	 * Run state machine for active packets
 	 */
@@ -1502,9 +1503,9 @@ static int kcdrwd(void *foobar)
 			if (PACKET_DEBUG > 1) {
 				int states[PACKET_NUM_STATES];
 				pkt_count_states(pd, states);
-				VPRINTK("kcdrwd: i:%d ow:%d rw:%d ww:%d rec:%d fin:%d\n",
-					states[0], states[1], states[2], states[3],
-					states[4], states[5]);
+				pkt_dbg(2, pd, "i:%d ow:%d rw:%d ww:%d rec:%d fin:%d\n",
+					states[0], states[1], states[2],
+					states[3], states[4], states[5]);
 			}
 
 			min_sleep_time = MAX_SCHEDULE_TIMEOUT;
@@ -1513,9 +1514,9 @@ static int kcdrwd(void *foobar)
 					min_sleep_time = pkt->sleep_time;
 			}
 
-			VPRINTK("kcdrwd: sleeping\n");
+			pkt_dbg(2, pd, "sleeping\n");
 			residue = schedule_timeout(min_sleep_time);
-			VPRINTK("kcdrwd: wake up\n");
+			pkt_dbg(2, pd, "wake up\n");
 
 			/* make swsusp happy with our thread */
 			try_to_freeze();
@@ -1563,9 +1564,10 @@ work_to_do:
 
 static void pkt_print_settings(struct pktcdvd_device *pd)
 {
-	printk(DRIVER_NAME": %s packets, ", pd->settings.fp ? "Fixed" : "Variable");
-	printk("%u blocks, ", pd->settings.size >> 2);
-	printk("Mode-%c disc\n", pd->settings.block_mode == 8 ? '1' : '2');
+	pkt_info(pd, "%s packets, %u blocks, Mode-%c disc\n",
+		 pd->settings.fp ? "Fixed" : "Variable",
+		 pd->settings.size >> 2,
+		 pd->settings.block_mode == 8 ? '1' : '2');
 }
 
 static int pkt_mode_sense(struct pktcdvd_device *pd, struct packet_command *cgc, int page_code, int page_control)
@@ -1699,7 +1701,7 @@ static noinline_for_stack int pkt_set_write_settings(struct pktcdvd_device *pd)
 	init_cdrom_command(&cgc, buffer, sizeof(*wp), CGC_DATA_READ);
 	cgc.sense = &sense;
 	if ((ret = pkt_mode_sense(pd, &cgc, GPMODE_WRITE_PARMS_PAGE, 0))) {
-		pkt_dump_sense(&cgc);
+		pkt_dump_sense(pd, &cgc);
 		return ret;
 	}
 
@@ -1714,7 +1716,7 @@ static noinline_for_stack int pkt_set_write_settings(struct pktcdvd_device *pd)
 	init_cdrom_command(&cgc, buffer, size, CGC_DATA_READ);
 	cgc.sense = &sense;
 	if ((ret = pkt_mode_sense(pd, &cgc, GPMODE_WRITE_PARMS_PAGE, 0))) {
-		pkt_dump_sense(&cgc);
+		pkt_dump_sense(pd, &cgc);
 		return ret;
 	}
 
@@ -1749,14 +1751,14 @@ static noinline_for_stack int pkt_set_write_settings(struct pktcdvd_device *pd)
 		/*
 		 * paranoia
 		 */
-		printk(DRIVER_NAME": write mode wrong %d\n", wp->data_block_type);
+		pkt_err(pd, "write mode wrong %d\n", wp->data_block_type);
 		return 1;
 	}
 	wp->packet_size = cpu_to_be32(pd->settings.size >> 2);
 
 	cgc.buflen = cgc.cmd[8] = size;
 	if ((ret = pkt_mode_select(pd, &cgc))) {
-		pkt_dump_sense(&cgc);
+		pkt_dump_sense(pd, &cgc);
 		return ret;
 	}
 
@@ -1793,7 +1795,7 @@ static int pkt_writable_track(struct pktcdvd_device *pd, track_information *ti)
 	if (ti->rt == 1 && ti->blank == 0)
 		return 1;
 
-	printk(DRIVER_NAME": bad state %d-%d-%d\n", ti->rt, ti->blank, ti->packet);
+	pkt_err(pd, "bad state %d-%d-%d\n", ti->rt, ti->blank, ti->packet);
 	return 0;
 }
 
@@ -1811,7 +1813,8 @@ static int pkt_writable_disc(struct pktcdvd_device *pd, disc_information *di)
 		case 0x12: /* DVD-RAM */
 			return 1;
 		default:
-			VPRINTK(DRIVER_NAME": Wrong disc profile (%x)\n", pd->mmc3_profile);
+			pkt_dbg(2, pd, "Wrong disc profile (%x)\n",
+				pd->mmc3_profile);
 			return 0;
 	}
 
@@ -1820,22 +1823,22 @@ static int pkt_writable_disc(struct pktcdvd_device *pd, disc_information *di)
 	 * but i'm not sure, should we leave this to user apps? probably.
 	 */
 	if (di->disc_type == 0xff) {
-		printk(DRIVER_NAME": Unknown disc. No track?\n");
+		pkt_notice(pd, "unknown disc - no track?\n");
 		return 0;
 	}
 
 	if (di->disc_type != 0x20 && di->disc_type != 0) {
-		printk(DRIVER_NAME": Wrong disc type (%x)\n", di->disc_type);
+		pkt_err(pd, "wrong disc type (%x)\n", di->disc_type);
 		return 0;
 	}
 
 	if (di->erasable == 0) {
-		printk(DRIVER_NAME": Disc not erasable\n");
+		pkt_notice(pd, "disc not erasable\n");
 		return 0;
 	}
 
 	if (di->border_status == PACKET_SESSION_RESERVED) {
-		printk(DRIVER_NAME": Can't write to last track (reserved)\n");
+		pkt_err(pd, "can't write to last track (reserved)\n");
 		return 0;
 	}
 
@@ -1860,7 +1863,7 @@ static noinline_for_stack int pkt_probe_settings(struct pktcdvd_device *pd)
 	memset(&ti, 0, sizeof(track_information));
 
 	if ((ret = pkt_get_disc_info(pd, &di))) {
-		printk("failed get_disc\n");
+		pkt_err(pd, "failed get_disc\n");
 		return ret;
 	}
 
@@ -1871,12 +1874,12 @@ static noinline_for_stack int pkt_probe_settings(struct pktcdvd_device *pd)
 
 	track = 1; /* (di.last_track_msb << 8) | di.last_track_lsb; */
 	if ((ret = pkt_get_track_info(pd, track, 1, &ti))) {
-		printk(DRIVER_NAME": failed get_track\n");
+		pkt_err(pd, "failed get_track\n");
 		return ret;
 	}
 
 	if (!pkt_writable_track(pd, &ti)) {
-		printk(DRIVER_NAME": can't write to this track\n");
+		pkt_err(pd, "can't write to this track\n");
 		return -EROFS;
 	}
 
@@ -1886,11 +1889,11 @@ static noinline_for_stack int pkt_probe_settings(struct pktcdvd_device *pd)
 	 */
 	pd->settings.size = be32_to_cpu(ti.fixed_packet_size) << 2;
 	if (pd->settings.size == 0) {
-		printk(DRIVER_NAME": detected zero packet size!\n");
+		pkt_notice(pd, "detected zero packet size!\n");
 		return -ENXIO;
 	}
 	if (pd->settings.size > PACKET_MAX_SECTORS) {
-		printk(DRIVER_NAME": packet size is too big\n");
+		pkt_err(pd, "packet size is too big\n");
 		return -EROFS;
 	}
 	pd->settings.fp = ti.fp;
@@ -1932,7 +1935,7 @@ static noinline_for_stack int pkt_probe_settings(struct pktcdvd_device *pd)
 			pd->settings.block_mode = PACKET_BLOCK_MODE2;
 			break;
 		default:
-			printk(DRIVER_NAME": unknown data mode\n");
+			pkt_err(pd, "unknown data mode\n");
 			return -EROFS;
 	}
 	return 0;
@@ -1966,10 +1969,10 @@ static noinline_for_stack int pkt_write_caching(struct pktcdvd_device *pd,
 	cgc.buflen = cgc.cmd[8] = 2 + ((buf[0] << 8) | (buf[1] & 0xff));
 	ret = pkt_mode_select(pd, &cgc);
 	if (ret) {
-		printk(DRIVER_NAME": write caching control failed\n");
-		pkt_dump_sense(&cgc);
+		pkt_err(pd, "write caching control failed\n");
+		pkt_dump_sense(pd, &cgc);
 	} else if (!ret && set)
-		printk(DRIVER_NAME": enabled write caching on %s\n", pd->name);
+		pkt_notice(pd, "enabled write caching\n");
 	return ret;
 }
 
@@ -2005,7 +2008,7 @@ static noinline_for_stack int pkt_get_max_speed(struct pktcdvd_device *pd,
 			     sizeof(struct mode_page_header);
 		ret = pkt_mode_sense(pd, &cgc, GPMODE_CAPABILITIES_PAGE, 0);
 		if (ret) {
-			pkt_dump_sense(&cgc);
+			pkt_dump_sense(pd, &cgc);
 			return ret;
 		}
 	}
@@ -2064,7 +2067,7 @@ static noinline_for_stack int pkt_media_speed(struct pktcdvd_device *pd,
 	cgc.cmd[8] = 2;
 	ret = pkt_generic_packet(pd, &cgc);
 	if (ret) {
-		pkt_dump_sense(&cgc);
+		pkt_dump_sense(pd, &cgc);
 		return ret;
 	}
 	size = ((unsigned int) buf[0]<<8) + buf[1] + 2;
@@ -2079,16 +2082,16 @@ static noinline_for_stack int pkt_media_speed(struct pktcdvd_device *pd,
 	cgc.cmd[8] = size;
 	ret = pkt_generic_packet(pd, &cgc);
 	if (ret) {
-		pkt_dump_sense(&cgc);
+		pkt_dump_sense(pd, &cgc);
 		return ret;
 	}
 
 	if (!(buf[6] & 0x40)) {
-		printk(DRIVER_NAME": Disc type is not CD-RW\n");
+		pkt_notice(pd, "disc type is not CD-RW\n");
 		return 1;
 	}
 	if (!(buf[6] & 0x4)) {
-		printk(DRIVER_NAME": A1 values on media are not valid, maybe not CDRW?\n");
+		pkt_notice(pd, "A1 values on media are not valid, maybe not CDRW?\n");
 		return 1;
 	}
 
@@ -2108,14 +2111,14 @@ static noinline_for_stack int pkt_media_speed(struct pktcdvd_device *pd,
 			*speed = us_clv_to_speed[sp];
 			break;
 		default:
-			printk(DRIVER_NAME": Unknown disc sub-type %d\n",st);
+			pkt_notice(pd, "unknown disc sub-type %d\n", st);
 			return 1;
 	}
 	if (*speed) {
-		printk(DRIVER_NAME": Max. media speed: %d\n",*speed);
+		pkt_info(pd, "maximum media speed: %d\n", *speed);
 		return 0;
 	} else {
-		printk(DRIVER_NAME": Unknown speed %d for sub-type %d\n",sp,st);
+		pkt_notice(pd, "unknown speed %d for sub-type %d\n", sp, st);
 		return 1;
 	}
 }
@@ -2126,7 +2129,7 @@ static noinline_for_stack int pkt_perform_opc(struct pktcdvd_device *pd)
 	struct request_sense sense;
 	int ret;
 
-	VPRINTK(DRIVER_NAME": Performing OPC\n");
+	pkt_dbg(2, pd, "Performing OPC\n");
 
 	init_cdrom_command(&cgc, NULL, 0, CGC_DATA_NONE);
 	cgc.sense = &sense;
@@ -2134,7 +2137,7 @@ static noinline_for_stack int pkt_perform_opc(struct pktcdvd_device *pd)
 	cgc.cmd[0] = GPCMD_SEND_OPC;
 	cgc.cmd[1] = 1;
 	if ((ret = pkt_generic_packet(pd, &cgc)))
-		pkt_dump_sense(&cgc);
+		pkt_dump_sense(pd, &cgc);
 	return ret;
 }
 
@@ -2144,12 +2147,12 @@ static int pkt_open_write(struct pktcdvd_device *pd)
 	unsigned int write_speed, media_write_speed, read_speed;
 
 	if ((ret = pkt_probe_settings(pd))) {
-		VPRINTK(DRIVER_NAME": %s failed probe\n", pd->name);
+		pkt_dbg(2, pd, "failed probe\n");
 		return ret;
 	}
 
 	if ((ret = pkt_set_write_settings(pd))) {
-		DPRINTK(DRIVER_NAME": %s failed saving write settings\n", pd->name);
+		pkt_dbg(1, pd, "failed saving write settings\n");
 		return -EIO;
 	}
 
@@ -2161,26 +2164,26 @@ static int pkt_open_write(struct pktcdvd_device *pd)
 		case 0x13: /* DVD-RW */
 		case 0x1a: /* DVD+RW */
 		case 0x12: /* DVD-RAM */
-			DPRINTK(DRIVER_NAME": write speed %ukB/s\n", write_speed);
+			pkt_dbg(1, pd, "write speed %ukB/s\n", write_speed);
 			break;
 		default:
 			if ((ret = pkt_media_speed(pd, &media_write_speed)))
 				media_write_speed = 16;
 			write_speed = min(write_speed, media_write_speed * 177);
-			DPRINTK(DRIVER_NAME": write speed %ux\n", write_speed / 176);
+			pkt_dbg(1, pd, "write speed %ux\n", write_speed / 176);
 			break;
 	}
 	read_speed = write_speed;
 
 	if ((ret = pkt_set_speed(pd, write_speed, read_speed))) {
-		DPRINTK(DRIVER_NAME": %s couldn't set write speed\n", pd->name);
+		pkt_dbg(1, pd, "couldn't set write speed\n");
 		return -EIO;
 	}
 	pd->write_speed = write_speed;
 	pd->read_speed = read_speed;
 
 	if ((ret = pkt_perform_opc(pd))) {
-		DPRINTK(DRIVER_NAME": %s Optimum Power Calibration failed\n", pd->name);
+		pkt_dbg(1, pd, "Optimum Power Calibration failed\n");
 	}
 
 	return 0;
@@ -2205,7 +2208,7 @@ static int pkt_open_dev(struct pktcdvd_device *pd, fmode_t write)
 		goto out;
 
 	if ((ret = pkt_get_last_written(pd, &lba))) {
-		printk(DRIVER_NAME": pkt_get_last_written failed\n");
+		pkt_err(pd, "pkt_get_last_written failed\n");
 		goto out_putdev;
 	}
 
@@ -2235,11 +2238,11 @@ static int pkt_open_dev(struct pktcdvd_device *pd, fmode_t write)
 
 	if (write) {
 		if (!pkt_grow_pktlist(pd, CONFIG_CDROM_PKTCDVD_BUFFERS)) {
-			printk(DRIVER_NAME": not enough memory for buffers\n");
+			pkt_err(pd, "not enough memory for buffers\n");
 			ret = -ENOMEM;
 			goto out_putdev;
 		}
-		printk(DRIVER_NAME": %lukB available on disc\n", lba << 1);
+		pkt_info(pd, "%lukB available on disc\n", lba << 1);
 	}
 
 	return 0;
@@ -2257,7 +2260,7 @@ out:
 static void pkt_release_dev(struct pktcdvd_device *pd, int flush)
 {
 	if (flush && pkt_flush_cache(pd))
-		DPRINTK(DRIVER_NAME": %s not flushing cache\n", pd->name);
+		pkt_dbg(1, pd, "not flushing cache\n");
 
 	pkt_lock_door(pd, 0);
 
@@ -2279,8 +2282,6 @@ static int pkt_open(struct block_device *bdev, fmode_t mode)
 	struct pktcdvd_device *pd = NULL;
 	int ret;
 
-	VPRINTK(DRIVER_NAME": entering open\n");
-
 	mutex_lock(&pktcdvd_mutex);
 	mutex_lock(&ctl_mutex);
 	pd = pkt_find_dev_from_minor(MINOR(bdev->bd_dev));
@@ -2315,7 +2316,6 @@ static int pkt_open(struct block_device *bdev, fmode_t mode)
 out_dec:
 	pd->refcnt--;
 out:
-	VPRINTK(DRIVER_NAME": failed open (%d)\n", ret);
 	mutex_unlock(&ctl_mutex);
 	mutex_unlock(&pktcdvd_mutex);
 	return ret;
@@ -2360,7 +2360,8 @@ static void pkt_make_request(struct request_queue *q, struct bio *bio)
 
 	pd = q->queuedata;
 	if (!pd) {
-		printk(DRIVER_NAME": %s incorrect request queue\n", bdevname(bio->bi_bdev, b));
+		pr_err("%s incorrect request queue\n",
+		       bdevname(bio->bi_bdev, b));
 		goto end_io;
 	}
 
@@ -2382,20 +2383,20 @@ static void pkt_make_request(struct request_queue *q, struct bio *bio)
 	}
 
 	if (!test_bit(PACKET_WRITABLE, &pd->flags)) {
-		printk(DRIVER_NAME": WRITE for ro device %s (%llu)\n",
-			pd->name, (unsigned long long)bio->bi_sector);
+		pkt_notice(pd, "WRITE for ro device (%llu)\n",
+			   (unsigned long long)bio->bi_sector);
 		goto end_io;
 	}
 
 	if (!bio->bi_size || (bio->bi_size % CD_FRAMESIZE)) {
-		printk(DRIVER_NAME": wrong bio size\n");
+		pkt_err(pd, "wrong bio size\n");
 		goto end_io;
 	}
 
 	blk_queue_bounce(q, &bio);
 
-	zone = ZONE(bio->bi_sector, pd);
-	VPRINTK("pkt_make_request: start = %6llx stop = %6llx\n",
+	zone = get_zone(bio->bi_sector, pd);
+	pkt_dbg(2, pd, "start = %6llx stop = %6llx\n",
 		(unsigned long long)bio->bi_sector,
 		(unsigned long long)bio_end_sector(bio));
 
@@ -2405,7 +2406,7 @@ static void pkt_make_request(struct request_queue *q, struct bio *bio)
 		sector_t last_zone;
 		int first_sectors;
 
-		last_zone = ZONE(bio_end_sector(bio) - 1, pd);
+		last_zone = get_zone(bio_end_sector(bio) - 1, pd);
 		if (last_zone != zone) {
 			BUG_ON(last_zone != zone + pd->settings.size);
 			first_sectors = last_zone - bio->bi_sector;
@@ -2500,7 +2501,7 @@ static int pkt_merge_bvec(struct request_queue *q, struct bvec_merge_data *bmd,
 			  struct bio_vec *bvec)
 {
 	struct pktcdvd_device *pd = q->queuedata;
-	sector_t zone = ZONE(bmd->bi_sector, pd);
+	sector_t zone = get_zone(bmd->bi_sector, pd);
 	int used = ((bmd->bi_sector - zone) << 9) + bmd->bi_size;
 	int remaining = (pd->settings.size << 9) - used;
 	int remaining2;
@@ -2609,7 +2610,7 @@ static int pkt_new_dev(struct pktcdvd_device *pd, dev_t dev)
 	struct block_device *bdev;
 
 	if (pd->pkt_dev == dev) {
-		printk(DRIVER_NAME": Recursive setup not allowed\n");
+		pkt_err(pd, "recursive setup not allowed\n");
 		return -EBUSY;
 	}
 	for (i = 0; i < MAX_WRITERS; i++) {
@@ -2617,11 +2618,12 @@ static int pkt_new_dev(struct pktcdvd_device *pd, dev_t dev)
 		if (!pd2)
 			continue;
 		if (pd2->bdev->bd_dev == dev) {
-			printk(DRIVER_NAME": %s already setup\n", bdevname(pd2->bdev, b));
+			pkt_err(pd, "%s already setup\n",
+				bdevname(pd2->bdev, b));
 			return -EBUSY;
 		}
 		if (pd2->pkt_dev == dev) {
-			printk(DRIVER_NAME": Can't chain pktcdvd devices\n");
+			pkt_err(pd, "can't chain pktcdvd devices\n");
 			return -EBUSY;
 		}
 	}
@@ -2644,13 +2646,13 @@ static int pkt_new_dev(struct pktcdvd_device *pd, dev_t dev)
 	atomic_set(&pd->cdrw.pending_bios, 0);
 	pd->cdrw.thread = kthread_run(kcdrwd, pd, "%s", pd->name);
 	if (IS_ERR(pd->cdrw.thread)) {
-		printk(DRIVER_NAME": can't start kernel thread\n");
+		pkt_err(pd, "can't start kernel thread\n");
 		ret = -ENOMEM;
 		goto out_mem;
 	}
 
 	proc_create_data(pd->name, 0, pkt_proc, &pkt_proc_fops, pd);
-	DPRINTK(DRIVER_NAME": writer %s mapped to %s\n", pd->name, bdevname(bdev, b));
+	pkt_dbg(1, pd, "writer mapped to %s\n", bdevname(bdev, b));
 	return 0;
 
 out_mem:
@@ -2665,8 +2667,8 @@ static int pkt_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd,
 	struct pktcdvd_device *pd = bdev->bd_disk->private_data;
 	int ret;
 
-	VPRINTK("pkt_ioctl: cmd %x, dev %d:%d\n", cmd,
-		MAJOR(bdev->bd_dev), MINOR(bdev->bd_dev));
+	pkt_dbg(2, pd, "cmd %x, dev %d:%d\n",
+		cmd, MAJOR(bdev->bd_dev), MINOR(bdev->bd_dev));
 
 	mutex_lock(&pktcdvd_mutex);
 	switch (cmd) {
@@ -2690,7 +2692,7 @@ static int pkt_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd,
 		break;
 
 	default:
-		VPRINTK(DRIVER_NAME": Unknown ioctl for %s (%x)\n", pd->name, cmd);
+		pkt_dbg(2, pd, "Unknown ioctl (%x)\n", cmd);
 		ret = -ENOTTY;
 	}
 	mutex_unlock(&pktcdvd_mutex);
@@ -2743,7 +2745,7 @@ static int pkt_setup_dev(dev_t dev, dev_t* pkt_dev)
 		if (!pkt_devs[idx])
 			break;
 	if (idx == MAX_WRITERS) {
-		printk(DRIVER_NAME": max %d writers supported\n", MAX_WRITERS);
+		pr_err("max %d writers supported\n", MAX_WRITERS);
 		ret = -EBUSY;
 		goto out_mutex;
 	}
@@ -2818,7 +2820,7 @@ out_mem:
 	kfree(pd);
 out_mutex:
 	mutex_unlock(&ctl_mutex);
-	printk(DRIVER_NAME": setup of pktcdvd device failed\n");
+	pr_err("setup of pktcdvd device failed\n");
 	return ret;
 }
 
@@ -2839,7 +2841,7 @@ static int pkt_remove_dev(dev_t pkt_dev)
 			break;
 	}
 	if (idx == MAX_WRITERS) {
-		DPRINTK(DRIVER_NAME": dev not setup\n");
+		pr_debug("dev not setup\n");
 		ret = -ENXIO;
 		goto out;
 	}
@@ -2859,7 +2861,7 @@ static int pkt_remove_dev(dev_t pkt_dev)
 	blkdev_put(pd->bdev, FMODE_READ | FMODE_NDELAY);
 
 	remove_proc_entry(pd->name, pkt_proc);
-	DPRINTK(DRIVER_NAME": writer %s unmapped\n", pd->name);
+	pkt_dbg(1, pd, "writer unmapped\n");
 
 	del_gendisk(pd->disk);
 	blk_cleanup_queue(pd->disk->queue);
@@ -2969,7 +2971,7 @@ static int __init pkt_init(void)
 
 	ret = register_blkdev(pktdev_major, DRIVER_NAME);
 	if (ret < 0) {
-		printk(DRIVER_NAME": Unable to register block device\n");
+		pr_err("unable to register block device\n");
 		goto out2;
 	}
 	if (!pktdev_major)
@@ -2983,7 +2985,7 @@ static int __init pkt_init(void)
 
 	ret = misc_register(&pkt_misc);
 	if (ret) {
-		printk(DRIVER_NAME": Unable to register misc device\n");
+		pr_err("unable to register misc device\n");
 		goto out_misc;
 	}
 
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index 4ad2ad9a5bb0..cb1db2979d3d 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -397,15 +397,19 @@ static ssize_t rbd_remove(struct bus_type *bus, const char *buf,
 static int rbd_dev_image_probe(struct rbd_device *rbd_dev, bool mapping);
 static void rbd_spec_put(struct rbd_spec *spec);
 
-static struct bus_attribute rbd_bus_attrs[] = {
-	__ATTR(add, S_IWUSR, NULL, rbd_add),
-	__ATTR(remove, S_IWUSR, NULL, rbd_remove),
-	__ATTR_NULL
+static BUS_ATTR(add, S_IWUSR, NULL, rbd_add);
+static BUS_ATTR(remove, S_IWUSR, NULL, rbd_remove);
+
+static struct attribute *rbd_bus_attrs[] = {
+	&bus_attr_add.attr,
+	&bus_attr_remove.attr,
+	NULL,
 };
+ATTRIBUTE_GROUPS(rbd_bus);
 
 static struct bus_type rbd_bus_type = {
 	.name		= "rbd",
-	.bus_attrs	= rbd_bus_attrs,
+	.bus_groups	= rbd_bus_groups,
 };
 
 static void rbd_root_dev_release(struct device *dev)
@@ -927,12 +931,14 @@ static const char *rbd_dev_v1_snap_name(struct rbd_device *rbd_dev,
 					u64 snap_id)
 {
 	u32 which;
+	const char *snap_name;
 
 	which = rbd_dev_snap_index(rbd_dev, snap_id);
 	if (which == BAD_SNAP_INDEX)
-		return NULL;
+		return ERR_PTR(-ENOENT);
 
-	return _rbd_dev_v1_snap_name(rbd_dev, which);
+	snap_name = _rbd_dev_v1_snap_name(rbd_dev, which);
+	return snap_name ? snap_name : ERR_PTR(-ENOMEM);
 }
 
 static const char *rbd_snap_name(struct rbd_device *rbd_dev, u64 snap_id)
@@ -1557,11 +1563,12 @@ rbd_img_obj_request_read_callback(struct rbd_obj_request *obj_request)
 		obj_request, obj_request->img_request, obj_request->result,
 		xferred, length);
 	/*
-	 * ENOENT means a hole in the image.  We zero-fill the
-	 * entire length of the request.  A short read also implies
-	 * zero-fill to the end of the request.  Either way we
-	 * update the xferred count to indicate the whole request
-	 * was satisfied.
+	 * ENOENT means a hole in the image.  We zero-fill the entire
+	 * length of the request.  A short read also implies zero-fill
+	 * to the end of the request.  An error requires the whole
+	 * length of the request to be reported finished with an error
+	 * to the block layer.  In each case we update the xferred
+	 * count to indicate the whole request was satisfied.
 	 */
 	rbd_assert(obj_request->type != OBJ_REQUEST_NODATA);
 	if (obj_request->result == -ENOENT) {
@@ -1570,14 +1577,13 @@ rbd_img_obj_request_read_callback(struct rbd_obj_request *obj_request)
 		else
 			zero_pages(obj_request->pages, 0, length);
 		obj_request->result = 0;
-		obj_request->xferred = length;
 	} else if (xferred < length && !obj_request->result) {
 		if (obj_request->type == OBJ_REQUEST_BIO)
 			zero_bio_chain(obj_request->bio_list, xferred);
 		else
 			zero_pages(obj_request->pages, xferred, length);
-		obj_request->xferred = length;
 	}
+	obj_request->xferred = length;
 	obj_request_done_set(obj_request);
 }
 
@@ -2163,9 +2169,9 @@ static int rbd_img_request_fill(struct rbd_img_request *img_request,
 	struct rbd_obj_request *obj_request = NULL;
 	struct rbd_obj_request *next_obj_request;
 	bool write_request = img_request_write_test(img_request);
-	struct bio *bio_list = 0;
+	struct bio *bio_list = NULL;
 	unsigned int bio_offset = 0;
-	struct page **pages = 0;
+	struct page **pages = NULL;
 	u64 img_offset;
 	u64 resid;
 	u16 opcode;
@@ -2203,6 +2209,11 @@ static int rbd_img_request_fill(struct rbd_img_request *img_request,
 		rbd_segment_name_free(object_name);
 		if (!obj_request)
 			goto out_unwind;
+		/*
+		 * set obj_request->img_request before creating the
+		 * osd_request so that it gets the right snapc
+		 */
+		rbd_img_obj_request_add(img_request, obj_request);
 
 		if (type == OBJ_REQUEST_BIO) {
 			unsigned int clone_size;
@@ -2244,11 +2255,6 @@ static int rbd_img_request_fill(struct rbd_img_request *img_request,
 					obj_request->pages, length,
 					offset & ~PAGE_MASK, false, false);
 
-		/*
-		 * set obj_request->img_request before formatting
-		 * the osd_request so that it gets the right snapc
-		 */
-		rbd_img_obj_request_add(img_request, obj_request);
 		if (write_request)
 			rbd_osd_req_format_write(obj_request);
 		else
@@ -2808,7 +2814,7 @@ out_err:
 	obj_request_done_set(obj_request);
 }
 
-static int rbd_obj_notify_ack(struct rbd_device *rbd_dev, u64 notify_id)
+static int rbd_obj_notify_ack_sync(struct rbd_device *rbd_dev, u64 notify_id)
 {
 	struct rbd_obj_request *obj_request;
 	struct ceph_osd_client *osdc = &rbd_dev->rbd_client->client->osdc;
@@ -2823,16 +2829,17 @@ static int rbd_obj_notify_ack(struct rbd_device *rbd_dev, u64 notify_id)
 	obj_request->osd_req = rbd_osd_req_create(rbd_dev, false, obj_request);
 	if (!obj_request->osd_req)
 		goto out;
-	obj_request->callback = rbd_obj_request_put;
 
 	osd_req_op_watch_init(obj_request->osd_req, 0, CEPH_OSD_OP_NOTIFY_ACK,
 					notify_id, 0, 0);
 	rbd_osd_req_format_read(obj_request);
 
 	ret = rbd_obj_request_submit(osdc, obj_request);
-out:
 	if (ret)
-		rbd_obj_request_put(obj_request);
+		goto out;
+	ret = rbd_obj_request_wait(obj_request);
+out:
+	rbd_obj_request_put(obj_request);
 
 	return ret;
 }
@@ -2852,7 +2859,7 @@ static void rbd_watch_cb(u64 ver, u64 notify_id, u8 opcode, void *data)
 	if (ret)
 		rbd_warn(rbd_dev, "header refresh error (%d)\n", ret);
 
-	rbd_obj_notify_ack(rbd_dev, notify_id);
+	rbd_obj_notify_ack_sync(rbd_dev, notify_id);
 }
 
 /*
@@ -3324,6 +3331,31 @@ static void rbd_exists_validate(struct rbd_device *rbd_dev)
 		clear_bit(RBD_DEV_FLAG_EXISTS, &rbd_dev->flags);
 }
 
+static void rbd_dev_update_size(struct rbd_device *rbd_dev)
+{
+	sector_t size;
+	bool removing;
+
+	/*
+	 * Don't hold the lock while doing disk operations,
+	 * or lock ordering will conflict with the bdev mutex via:
+	 * rbd_add() -> blkdev_get() -> rbd_open()
+	 */
+	spin_lock_irq(&rbd_dev->lock);
+	removing = test_bit(RBD_DEV_FLAG_REMOVING, &rbd_dev->flags);
+	spin_unlock_irq(&rbd_dev->lock);
+	/*
+	 * If the device is being removed, rbd_dev->disk has
+	 * been destroyed, so don't try to update its size
+	 */
+	if (!removing) {
+		size = (sector_t)rbd_dev->mapping.size / SECTOR_SIZE;
+		dout("setting size to %llu sectors", (unsigned long long)size);
+		set_capacity(rbd_dev->disk, size);
+		revalidate_disk(rbd_dev->disk);
+	}
+}
+
 static int rbd_dev_refresh(struct rbd_device *rbd_dev)
 {
 	u64 mapping_size;
@@ -3343,12 +3375,7 @@ static int rbd_dev_refresh(struct rbd_device *rbd_dev)
 	up_write(&rbd_dev->header_rwsem);
 
 	if (mapping_size != rbd_dev->mapping.size) {
-		sector_t size;
-
-		size = (sector_t)rbd_dev->mapping.size / SECTOR_SIZE;
-		dout("setting size to %llu sectors", (unsigned long long)size);
-		set_capacity(rbd_dev->disk, size);
-		revalidate_disk(rbd_dev->disk);
+		rbd_dev_update_size(rbd_dev);
 	}
 
 	return ret;
@@ -3702,12 +3729,14 @@ static int _rbd_dev_v2_snap_size(struct rbd_device *rbd_dev, u64 snap_id,
 	if (ret < sizeof (size_buf))
 		return -ERANGE;
 
-	if (order)
+	if (order) {
 		*order = size_buf.order;
+		dout("  order %u", (unsigned int)*order);
+	}
 	*snap_size = le64_to_cpu(size_buf.size);
 
-	dout("  snap_id 0x%016llx order = %u, snap_size = %llu\n",
-		(unsigned long long)snap_id, (unsigned int)*order,
+	dout("  snap_id 0x%016llx snap_size = %llu\n",
+		(unsigned long long)snap_id,
 		(unsigned long long)*snap_size);
 
 	return 0;
@@ -4055,8 +4084,13 @@ static u64 rbd_v2_snap_id_by_name(struct rbd_device *rbd_dev, const char *name)
 
 		snap_id = snapc->snaps[which];
 		snap_name = rbd_dev_v2_snap_name(rbd_dev, snap_id);
-		if (IS_ERR(snap_name))
-			break;
+		if (IS_ERR(snap_name)) {
+			/* ignore no-longer existing snapshots */
+			if (PTR_ERR(snap_name) == -ENOENT)
+				continue;
+			else
+				break;
+		}
 		found = !strcmp(name, snap_name);
 		kfree(snap_name);
 	}
@@ -4135,8 +4169,8 @@ static int rbd_dev_spec_update(struct rbd_device *rbd_dev)
 	/* Look up the snapshot name, and make a copy */
 
 	snap_name = rbd_snap_name(rbd_dev, spec->snap_id);
-	if (!snap_name) {
-		ret = -ENOMEM;
+	if (IS_ERR(snap_name)) {
+		ret = PTR_ERR(snap_name);
 		goto out_err;
 	}
 
@@ -5126,7 +5160,7 @@ static ssize_t rbd_remove(struct bus_type *bus,
 	bool already = false;
 	int ret;
 
-	ret = strict_strtoul(buf, 10, &ul);
+	ret = kstrtoul(buf, 10, &ul);
 	if (ret)
 		return ret;
 
@@ -5157,10 +5191,23 @@ static ssize_t rbd_remove(struct bus_type *bus,
 	if (ret < 0 || already)
 		return ret;
 
-	rbd_bus_del_dev(rbd_dev);
 	ret = rbd_dev_header_watch_sync(rbd_dev, false);
 	if (ret)
 		rbd_warn(rbd_dev, "failed to cancel watch event (%d)\n", ret);
+
+	/*
+	 * flush remaining watch callbacks - these must be complete
+	 * before the osd_client is shutdown
+	 */
+	dout("%s: flushing notifies", __func__);
+	ceph_osdc_flush_notifies(&rbd_dev->rbd_client->client->osdc);
+	/*
+	 * Don't free anything from rbd_dev->disk until after all
+	 * notifies are completely processed. Otherwise
+	 * rbd_bus_del_dev() will race with rbd_watch_cb(), resulting
+	 * in a potential use after free of rbd_dev->disk or rbd_dev.
+	 */
+	rbd_bus_del_dev(rbd_dev);
 	rbd_dev_image_release(rbd_dev);
 	module_put(THIS_MODULE);
 
diff --git a/drivers/block/swim.c b/drivers/block/swim.c
index 8ed6ccb748cf..b02d53a399f3 100644
--- a/drivers/block/swim.c
+++ b/drivers/block/swim.c
@@ -924,7 +924,6 @@ static int swim_probe(struct platform_device *dev)
 	return 0;
 
 out_kfree:
-	platform_set_drvdata(dev, NULL);
 	kfree(swd);
 out_iounmap:
 	iounmap(swim_base);
@@ -962,7 +961,6 @@ static int swim_remove(struct platform_device *dev)
 	if (res)
 		release_mem_region(res->start, resource_size(res));
 
-	platform_set_drvdata(dev, NULL);
 	kfree(swd);
 
 	return 0;
diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c
index fe5c3cd10c34..c2014a0aa206 100644
--- a/drivers/block/xen-blkback/xenbus.c
+++ b/drivers/block/xen-blkback/xenbus.c
@@ -620,7 +620,7 @@ static void backend_changed(struct xenbus_watch *watch,
 	}
 
 	/* Front end dir is a number, which is used as the handle. */
-	err = strict_strtoul(strrchr(dev->otherend, '/') + 1, 0, &handle);
+	err = kstrtoul(strrchr(dev->otherend, '/') + 1, 0, &handle);
 	if (err)
 		return;
 
diff --git a/drivers/bluetooth/ath3k.c b/drivers/bluetooth/ath3k.c
index a12b923bbaca..0a327f4154a2 100644
--- a/drivers/bluetooth/ath3k.c
+++ b/drivers/bluetooth/ath3k.c
@@ -85,6 +85,7 @@ static struct usb_device_id ath3k_table[] = {
 	{ USB_DEVICE(0x04CA, 0x3008) },
 	{ USB_DEVICE(0x13d3, 0x3362) },
 	{ USB_DEVICE(0x0CF3, 0xE004) },
+	{ USB_DEVICE(0x0CF3, 0xE005) },
 	{ USB_DEVICE(0x0930, 0x0219) },
 	{ USB_DEVICE(0x0489, 0xe057) },
 	{ USB_DEVICE(0x13d3, 0x3393) },
@@ -126,6 +127,7 @@ static struct usb_device_id ath3k_blist_tbl[] = {
 	{ USB_DEVICE(0x04ca, 0x3008), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x13d3, 0x3362), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0cf3, 0xe004), .driver_info = BTUSB_ATH3012 },
+	{ USB_DEVICE(0x0cf3, 0xe005), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0930, 0x0219), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0489, 0xe057), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x13d3, 0x3393), .driver_info = BTUSB_ATH3012 },
diff --git a/drivers/bluetooth/btmrvl_debugfs.c b/drivers/bluetooth/btmrvl_debugfs.c
index db2c3c305df8..023d35e3c7a7 100644
--- a/drivers/bluetooth/btmrvl_debugfs.c
+++ b/drivers/bluetooth/btmrvl_debugfs.c
@@ -43,7 +43,7 @@ static ssize_t btmrvl_hscfgcmd_write(struct file *file,
 	if (copy_from_user(&buf, ubuf, min_t(size_t, sizeof(buf) - 1, count)))
 		return -EFAULT;
 
-	ret = strict_strtol(buf, 10, &result);
+	ret = kstrtol(buf, 10, &result);
 	if (ret)
 		return ret;
 
@@ -89,7 +89,7 @@ static ssize_t btmrvl_pscmd_write(struct file *file, const char __user *ubuf,
 	if (copy_from_user(&buf, ubuf, min_t(size_t, sizeof(buf) - 1, count)))
 		return -EFAULT;
 
-	ret = strict_strtol(buf, 10, &result);
+	ret = kstrtol(buf, 10, &result);
 	if (ret)
 		return ret;
 
@@ -135,7 +135,7 @@ static ssize_t btmrvl_hscmd_write(struct file *file, const char __user *ubuf,
 	if (copy_from_user(&buf, ubuf, min_t(size_t, sizeof(buf) - 1, count)))
 		return -EFAULT;
 
-	ret = strict_strtol(buf, 10, &result);
+	ret = kstrtol(buf, 10, &result);
 	if (ret)
 		return ret;
 
diff --git a/drivers/bluetooth/btmrvl_sdio.c b/drivers/bluetooth/btmrvl_sdio.c
index 75c262694632..00da6df9f71e 100644
--- a/drivers/bluetooth/btmrvl_sdio.c
+++ b/drivers/bluetooth/btmrvl_sdio.c
@@ -486,7 +486,7 @@ static int btmrvl_sdio_download_fw_w_helper(struct btmrvl_sdio_card *card)
 			if (firmwarelen - offset < txlen)
 				txlen = firmwarelen - offset;
 
-			tx_blocks = (txlen + blksz_dl - 1) / blksz_dl;
+			tx_blocks = DIV_ROUND_UP(txlen, blksz_dl);
 
 			memcpy(fwbuf, &firmware[offset], txlen);
 		}
@@ -873,7 +873,7 @@ static int btmrvl_sdio_host_to_card(struct btmrvl_private *priv,
 	}
 
 	blksz = SDIO_BLOCK_SIZE;
-	buf_block_len = (nb + blksz - 1) / blksz;
+	buf_block_len = DIV_ROUND_UP(nb, blksz);
 
 	sdio_claim_host(card->func);
 
diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index 8e16f0af6358..f3dfc0a88fdc 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -102,6 +102,7 @@ static struct usb_device_id btusb_table[] = {
 
 	/* Broadcom BCM20702A0 */
 	{ USB_DEVICE(0x0b05, 0x17b5) },
+	{ USB_DEVICE(0x0b05, 0x17cb) },
 	{ USB_DEVICE(0x04ca, 0x2003) },
 	{ USB_DEVICE(0x0489, 0xe042) },
 	{ USB_DEVICE(0x413c, 0x8197) },
@@ -112,6 +113,9 @@ static struct usb_device_id btusb_table[] = {
 	/*Broadcom devices with vendor specific id */
 	{ USB_VENDOR_AND_INTERFACE_INFO(0x0a5c, 0xff, 0x01, 0x01) },
 
+	/* Belkin F8065bf - Broadcom based */
+	{ USB_VENDOR_AND_INTERFACE_INFO(0x050d, 0xff, 0x01, 0x01) },
+
 	{ }	/* Terminating entry */
 };
 
@@ -148,6 +152,7 @@ static struct usb_device_id blacklist_table[] = {
 	{ USB_DEVICE(0x04ca, 0x3008), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x13d3, 0x3362), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0cf3, 0xe004), .driver_info = BTUSB_ATH3012 },
+	{ USB_DEVICE(0x0cf3, 0xe005), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0930, 0x0219), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0489, 0xe057), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x13d3, 0x3393), .driver_info = BTUSB_ATH3012 },
diff --git a/drivers/bus/Kconfig b/drivers/bus/Kconfig
index 1f70e84b442c..552373c4e362 100644
--- a/drivers/bus/Kconfig
+++ b/drivers/bus/Kconfig
@@ -8,10 +8,9 @@ config IMX_WEIM
 	bool "Freescale EIM DRIVER"
 	depends on ARCH_MXC
 	help
-	  Driver for i.MX6 WEIM controller.
+	  Driver for i.MX WEIM controller.
 	  The WEIM(Wireless External Interface Module) works like a bus.
 	  You can attach many different devices on it, such as NOR, onenand.
-	  But now, we only support the Parallel NOR.
 
 config MVEBU_MBUS
 	bool
diff --git a/drivers/bus/arm-cci.c b/drivers/bus/arm-cci.c
index 733288967d4d..200926699778 100644
--- a/drivers/bus/arm-cci.c
+++ b/drivers/bus/arm-cci.c
@@ -122,17 +122,8 @@ EXPORT_SYMBOL_GPL(cci_ace_get_port);
 
 static void __init cci_ace_init_ports(void)
 {
-	int port, ac, cpu;
-	u64 hwid;
-	const u32 *cell;
-	struct device_node *cpun, *cpus;
-
-	cpus = of_find_node_by_path("/cpus");
-	if (WARN(!cpus, "Missing cpus node, bailing out\n"))
-		return;
-
-	if (WARN_ON(of_property_read_u32(cpus, "#address-cells", &ac)))
-		ac = of_n_addr_cells(cpus);
+	int port, cpu;
+	struct device_node *cpun;
 
 	/*
 	 * Port index look-up speeds up the function disabling ports by CPU,
@@ -141,18 +132,13 @@ static void __init cci_ace_init_ports(void)
 	 * The stashed index array is initialized for all possible CPUs
 	 * at probe time.
 	 */
-	for_each_child_of_node(cpus, cpun) {
-		if (of_node_cmp(cpun->type, "cpu"))
-			continue;
-		cell = of_get_property(cpun, "reg", NULL);
-		if (WARN(!cell, "%s: missing reg property\n", cpun->full_name))
-			continue;
-
-		hwid = of_read_number(cell, ac);
-		cpu = get_logical_index(hwid & MPIDR_HWID_BITMASK);
+	for_each_possible_cpu(cpu) {
+		/* too early to use cpu->of_node */
+		cpun = of_get_cpu_node(cpu, NULL);
 
-		if (cpu < 0 || !cpu_possible(cpu))
+		if (WARN(!cpun, "Missing cpu device node\n"))
 			continue;
+
 		port = __cci_ace_get_port(cpun, ACE_PORT);
 		if (port < 0)
 			continue;
diff --git a/drivers/bus/imx-weim.c b/drivers/bus/imx-weim.c
index 349f14e886b7..3ef58c8dbf11 100644
--- a/drivers/bus/imx-weim.c
+++ b/drivers/bus/imx-weim.c
@@ -12,52 +12,83 @@
 #include <linux/io.h>
 #include <linux/of_device.h>
 
-struct imx_weim {
-	void __iomem *base;
-	struct clk *clk;
+struct imx_weim_devtype {
+	unsigned int	cs_count;
+	unsigned int	cs_regs_count;
+	unsigned int	cs_stride;
+};
+
+static const struct imx_weim_devtype imx1_weim_devtype = {
+	.cs_count	= 6,
+	.cs_regs_count	= 2,
+	.cs_stride	= 0x08,
+};
+
+static const struct imx_weim_devtype imx27_weim_devtype = {
+	.cs_count	= 6,
+	.cs_regs_count	= 3,
+	.cs_stride	= 0x10,
+};
+
+static const struct imx_weim_devtype imx50_weim_devtype = {
+	.cs_count	= 4,
+	.cs_regs_count	= 6,
+	.cs_stride	= 0x18,
+};
+
+static const struct imx_weim_devtype imx51_weim_devtype = {
+	.cs_count	= 6,
+	.cs_regs_count	= 6,
+	.cs_stride	= 0x18,
 };
 
 static const struct of_device_id weim_id_table[] = {
-	{ .compatible = "fsl,imx6q-weim", },
-	{}
+	/* i.MX1/21 */
+	{ .compatible = "fsl,imx1-weim", .data = &imx1_weim_devtype, },
+	/* i.MX25/27/31/35 */
+	{ .compatible = "fsl,imx27-weim", .data = &imx27_weim_devtype, },
+	/* i.MX50/53/6Q */
+	{ .compatible = "fsl,imx50-weim", .data = &imx50_weim_devtype, },
+	{ .compatible = "fsl,imx6q-weim", .data = &imx50_weim_devtype, },
+	/* i.MX51 */
+	{ .compatible = "fsl,imx51-weim", .data = &imx51_weim_devtype, },
+	{ }
 };
 MODULE_DEVICE_TABLE(of, weim_id_table);
 
-#define CS_TIMING_LEN 6
-#define CS_REG_RANGE  0x18
-
 /* Parse and set the timing for this device. */
-static int
-weim_timing_setup(struct platform_device *pdev, struct device_node *np)
+static int __init weim_timing_setup(struct device_node *np, void __iomem *base,
+				    const struct imx_weim_devtype *devtype)
 {
-	struct imx_weim *weim = platform_get_drvdata(pdev);
-	u32 value[CS_TIMING_LEN];
-	u32 cs_idx;
-	int ret;
-	int i;
+	u32 cs_idx, value[devtype->cs_regs_count];
+	int i, ret;
 
 	/* get the CS index from this child node's "reg" property. */
 	ret = of_property_read_u32(np, "reg", &cs_idx);
 	if (ret)
 		return ret;
 
-	/* The weim has four chip selects. */
-	if (cs_idx > 3)
+	if (cs_idx >= devtype->cs_count)
 		return -EINVAL;
 
 	ret = of_property_read_u32_array(np, "fsl,weim-cs-timing",
-					value, CS_TIMING_LEN);
+					 value, devtype->cs_regs_count);
 	if (ret)
 		return ret;
 
 	/* set the timing for WEIM */
-	for (i = 0; i < CS_TIMING_LEN; i++)
-		writel(value[i], weim->base + cs_idx * CS_REG_RANGE + i * 4);
+	for (i = 0; i < devtype->cs_regs_count; i++)
+		writel(value[i], base + cs_idx * devtype->cs_stride + i * 4);
+
 	return 0;
 }
 
-static int weim_parse_dt(struct platform_device *pdev)
+static int __init weim_parse_dt(struct platform_device *pdev,
+				void __iomem *base)
 {
+	const struct of_device_id *of_id = of_match_device(weim_id_table,
+							   &pdev->dev);
+	const struct imx_weim_devtype *devtype = of_id->data;
 	struct device_node *child;
 	int ret;
 
@@ -65,7 +96,7 @@ static int weim_parse_dt(struct platform_device *pdev)
 		if (!child->name)
 			continue;
 
-		ret = weim_timing_setup(pdev, child);
+		ret = weim_timing_setup(child, base, devtype);
 		if (ret) {
 			dev_err(&pdev->dev, "%s set timing failed.\n",
 				child->full_name);
@@ -80,59 +111,47 @@ static int weim_parse_dt(struct platform_device *pdev)
 	return ret;
 }
 
-static int weim_probe(struct platform_device *pdev)
+static int __init weim_probe(struct platform_device *pdev)
 {
-	struct imx_weim *weim;
 	struct resource *res;
-	int ret = -EINVAL;
-
-	weim = devm_kzalloc(&pdev->dev, sizeof(*weim), GFP_KERNEL);
-	if (!weim) {
-		ret = -ENOMEM;
-		goto weim_err;
-	}
-	platform_set_drvdata(pdev, weim);
+	struct clk *clk;
+	void __iomem *base;
+	int ret;
 
 	/* get the resource */
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	weim->base = devm_ioremap_resource(&pdev->dev, res);
-	if (IS_ERR(weim->base)) {
-		ret = PTR_ERR(weim->base);
-		goto weim_err;
-	}
+	base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
 
 	/* get the clock */
-	weim->clk = devm_clk_get(&pdev->dev, NULL);
-	if (IS_ERR(weim->clk))
-		goto weim_err;
+	clk = devm_clk_get(&pdev->dev, NULL);
+	if (IS_ERR(clk))
+		return PTR_ERR(clk);
 
-	ret = clk_prepare_enable(weim->clk);
+	ret = clk_prepare_enable(clk);
 	if (ret)
-		goto weim_err;
+		return ret;
 
 	/* parse the device node */
-	ret = weim_parse_dt(pdev);
-	if (ret) {
-		clk_disable_unprepare(weim->clk);
-		goto weim_err;
-	}
-
-	dev_info(&pdev->dev, "WEIM driver registered.\n");
-	return 0;
+	ret = weim_parse_dt(pdev, base);
+	if (ret)
+		clk_disable_unprepare(clk);
+	else
+		dev_info(&pdev->dev, "Driver registered.\n");
 
-weim_err:
 	return ret;
 }
 
 static struct platform_driver weim_driver = {
 	.driver = {
-		.name = "imx-weim",
-		.of_match_table = weim_id_table,
+		.name		= "imx-weim",
+		.owner		= THIS_MODULE,
+		.of_match_table	= weim_id_table,
 	},
-	.probe   = weim_probe,
 };
+module_platform_driver_probe(weim_driver, weim_probe);
 
-module_platform_driver(weim_driver);
 MODULE_AUTHOR("Freescale Semiconductor Inc.");
 MODULE_DESCRIPTION("i.MX EIM Controller Driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/bus/mvebu-mbus.c b/drivers/bus/mvebu-mbus.c
index 33c6947eebec..2394e9753ef5 100644
--- a/drivers/bus/mvebu-mbus.c
+++ b/drivers/bus/mvebu-mbus.c
@@ -35,13 +35,9 @@
  *
  * - Provides an API for platform code or device drivers to
  *   dynamically add or remove address decoding windows for the CPU ->
- *   device accesses. This API is mvebu_mbus_add_window(),
- *   mvebu_mbus_add_window_remap_flags() and
- *   mvebu_mbus_del_window(). Since the (target, attribute) values
- *   differ from one SoC family to another, the API uses a 'const char
- *   *' string to identify devices, and this driver is responsible for
- *   knowing the mapping between the name of a device and its
- *   corresponding (target, attribute) in the current SoC family.
+ *   device accesses. This API is mvebu_mbus_add_window_by_id(),
+ *   mvebu_mbus_add_window_remap_by_id() and
+ *   mvebu_mbus_del_window().
  *
  * - Provides a debugfs interface in /sys/kernel/debug/mvebu-mbus/ to
  *   see the list of CPU -> SDRAM windows and their configuration
@@ -97,33 +93,6 @@
 
 #define DOVE_DDR_BASE_CS_OFF(n) ((n) << 4)
 
-struct mvebu_mbus_mapping {
-	const char *name;
-	u8 target;
-	u8 attr;
-	u8 attrmask;
-};
-
-/*
- * Masks used for the 'attrmask' field of mvebu_mbus_mapping. They
- * allow to get the real attribute value, discarding the special bits
- * used to select a PCI MEM region or a PCI WA region. This allows the
- * debugfs code to reverse-match the name of a device from its
- * target/attr values.
- *
- * For all devices except PCI, all bits of 'attr' must be
- * considered. For most SoCs, only bit 3 should be ignored (it allows
- * to select between PCI MEM and PCI I/O). On Orion5x however, there
- * is the special bit 5 to select a PCI WA region.
- */
-#define MAPDEF_NOMASK       0xff
-#define MAPDEF_PCIMASK      0xf7
-#define MAPDEF_ORIONPCIMASK 0xd7
-
-/* Macro used to define one mvebu_mbus_mapping entry */
-#define MAPDEF(__n, __t, __a, __m) \
-	{ .name = __n, .target = __t, .attr = __a, .attrmask = __m }
-
 struct mvebu_mbus_state;
 
 struct mvebu_mbus_soc_data {
@@ -133,7 +102,6 @@ struct mvebu_mbus_soc_data {
 	void (*setup_cpu_target)(struct mvebu_mbus_state *s);
 	int (*show_cpu_target)(struct mvebu_mbus_state *s,
 			       struct seq_file *seq, void *v);
-	const struct mvebu_mbus_mapping *map;
 };
 
 struct mvebu_mbus_state {
@@ -142,6 +110,8 @@ struct mvebu_mbus_state {
 	struct dentry *debugfs_root;
 	struct dentry *debugfs_sdram;
 	struct dentry *debugfs_devs;
+	struct resource pcie_mem_aperture;
+	struct resource pcie_io_aperture;
 	const struct mvebu_mbus_soc_data *soc;
 	int hw_io_coherency;
 };
@@ -428,8 +398,7 @@ static int mvebu_devs_debug_show(struct seq_file *seq, void *v)
 		u64 wbase, wremap;
 		u32 wsize;
 		u8 wtarget, wattr;
-		int enabled, i;
-		const char *name;
+		int enabled;
 
 		mvebu_mbus_read_window(mbus, win,
 				       &enabled, &wbase, &wsize,
@@ -440,18 +409,9 @@ static int mvebu_devs_debug_show(struct seq_file *seq, void *v)
 			continue;
 		}
 
-
-		for (i = 0; mbus->soc->map[i].name; i++)
-			if (mbus->soc->map[i].target == wtarget &&
-			    mbus->soc->map[i].attr ==
-			    (wattr & mbus->soc->map[i].attrmask))
-				break;
-
-		name = mbus->soc->map[i].name ?: "unknown";
-
-		seq_printf(seq, "[%02d] %016llx - %016llx : %s",
+		seq_printf(seq, "[%02d] %016llx - %016llx : %04x:%04x",
 			   win, (unsigned long long)wbase,
-			   (unsigned long long)(wbase + wsize), name);
+			   (unsigned long long)(wbase + wsize), wtarget, wattr);
 
 		if (win < mbus->soc->num_remappable_wins) {
 			seq_printf(seq, " (remap %016llx)\n",
@@ -576,62 +536,12 @@ mvebu_mbus_dove_setup_cpu_target(struct mvebu_mbus_state *mbus)
 	mvebu_mbus_dram_info.num_cs = cs;
 }
 
-static const struct mvebu_mbus_mapping armada_370_map[] = {
-	MAPDEF("bootrom",     1, 0xe0, MAPDEF_NOMASK),
-	MAPDEF("devbus-boot", 1, 0x2f, MAPDEF_NOMASK),
-	MAPDEF("devbus-cs0",  1, 0x3e, MAPDEF_NOMASK),
-	MAPDEF("devbus-cs1",  1, 0x3d, MAPDEF_NOMASK),
-	MAPDEF("devbus-cs2",  1, 0x3b, MAPDEF_NOMASK),
-	MAPDEF("devbus-cs3",  1, 0x37, MAPDEF_NOMASK),
-	MAPDEF("pcie0.0",     4, 0xe0, MAPDEF_PCIMASK),
-	MAPDEF("pcie1.0",     8, 0xe0, MAPDEF_PCIMASK),
-	{},
-};
-
-static const struct mvebu_mbus_soc_data armada_370_mbus_data = {
+static const struct mvebu_mbus_soc_data armada_370_xp_mbus_data = {
 	.num_wins            = 20,
 	.num_remappable_wins = 8,
 	.win_cfg_offset      = armada_370_xp_mbus_win_offset,
 	.setup_cpu_target    = mvebu_mbus_default_setup_cpu_target,
 	.show_cpu_target     = mvebu_sdram_debug_show_orion,
-	.map                 = armada_370_map,
-};
-
-static const struct mvebu_mbus_mapping armada_xp_map[] = {
-	MAPDEF("bootrom",     1, 0x1d, MAPDEF_NOMASK),
-	MAPDEF("devbus-boot", 1, 0x2f, MAPDEF_NOMASK),
-	MAPDEF("devbus-cs0",  1, 0x3e, MAPDEF_NOMASK),
-	MAPDEF("devbus-cs1",  1, 0x3d, MAPDEF_NOMASK),
-	MAPDEF("devbus-cs2",  1, 0x3b, MAPDEF_NOMASK),
-	MAPDEF("devbus-cs3",  1, 0x37, MAPDEF_NOMASK),
-	MAPDEF("pcie0.0",     4, 0xe0, MAPDEF_PCIMASK),
-	MAPDEF("pcie0.1",     4, 0xd0, MAPDEF_PCIMASK),
-	MAPDEF("pcie0.2",     4, 0xb0, MAPDEF_PCIMASK),
-	MAPDEF("pcie0.3",     4, 0x70, MAPDEF_PCIMASK),
-	MAPDEF("pcie1.0",     8, 0xe0, MAPDEF_PCIMASK),
-	MAPDEF("pcie1.1",     8, 0xd0, MAPDEF_PCIMASK),
-	MAPDEF("pcie1.2",     8, 0xb0, MAPDEF_PCIMASK),
-	MAPDEF("pcie1.3",     8, 0x70, MAPDEF_PCIMASK),
-	MAPDEF("pcie2.0",     4, 0xf0, MAPDEF_PCIMASK),
-	MAPDEF("pcie3.0",     8, 0xf0, MAPDEF_PCIMASK),
-	{},
-};
-
-static const struct mvebu_mbus_soc_data armada_xp_mbus_data = {
-	.num_wins            = 20,
-	.num_remappable_wins = 8,
-	.win_cfg_offset      = armada_370_xp_mbus_win_offset,
-	.setup_cpu_target    = mvebu_mbus_default_setup_cpu_target,
-	.show_cpu_target     = mvebu_sdram_debug_show_orion,
-	.map                 = armada_xp_map,
-};
-
-static const struct mvebu_mbus_mapping kirkwood_map[] = {
-	MAPDEF("pcie0.0", 4, 0xe0, MAPDEF_PCIMASK),
-	MAPDEF("pcie1.0", 4, 0xd0, MAPDEF_PCIMASK),
-	MAPDEF("sram",    3, 0x01, MAPDEF_NOMASK),
-	MAPDEF("nand",    1, 0x2f, MAPDEF_NOMASK),
-	{},
 };
 
 static const struct mvebu_mbus_soc_data kirkwood_mbus_data = {
@@ -640,16 +550,6 @@ static const struct mvebu_mbus_soc_data kirkwood_mbus_data = {
 	.win_cfg_offset      = orion_mbus_win_offset,
 	.setup_cpu_target    = mvebu_mbus_default_setup_cpu_target,
 	.show_cpu_target     = mvebu_sdram_debug_show_orion,
-	.map                 = kirkwood_map,
-};
-
-static const struct mvebu_mbus_mapping dove_map[] = {
-	MAPDEF("pcie0.0",    0x4, 0xe0, MAPDEF_PCIMASK),
-	MAPDEF("pcie1.0",    0x8, 0xe0, MAPDEF_PCIMASK),
-	MAPDEF("cesa",       0x3, 0x01, MAPDEF_NOMASK),
-	MAPDEF("bootrom",    0x1, 0xfd, MAPDEF_NOMASK),
-	MAPDEF("scratchpad", 0xd, 0x0, MAPDEF_NOMASK),
-	{},
 };
 
 static const struct mvebu_mbus_soc_data dove_mbus_data = {
@@ -658,18 +558,6 @@ static const struct mvebu_mbus_soc_data dove_mbus_data = {
 	.win_cfg_offset      = orion_mbus_win_offset,
 	.setup_cpu_target    = mvebu_mbus_dove_setup_cpu_target,
 	.show_cpu_target     = mvebu_sdram_debug_show_dove,
-	.map                 = dove_map,
-};
-
-static const struct mvebu_mbus_mapping orion5x_map[] = {
-	MAPDEF("pcie0.0",     4, 0x51, MAPDEF_ORIONPCIMASK),
-	MAPDEF("pci0.0",      3, 0x51, MAPDEF_ORIONPCIMASK),
-	MAPDEF("devbus-boot", 1, 0x0f, MAPDEF_NOMASK),
-	MAPDEF("devbus-cs0",  1, 0x1e, MAPDEF_NOMASK),
-	MAPDEF("devbus-cs1",  1, 0x1d, MAPDEF_NOMASK),
-	MAPDEF("devbus-cs2",  1, 0x1b, MAPDEF_NOMASK),
-	MAPDEF("sram",        0, 0x00, MAPDEF_NOMASK),
-	{},
 };
 
 /*
@@ -682,7 +570,6 @@ static const struct mvebu_mbus_soc_data orion5x_4win_mbus_data = {
 	.win_cfg_offset      = orion_mbus_win_offset,
 	.setup_cpu_target    = mvebu_mbus_default_setup_cpu_target,
 	.show_cpu_target     = mvebu_sdram_debug_show_orion,
-	.map                 = orion5x_map,
 };
 
 static const struct mvebu_mbus_soc_data orion5x_2win_mbus_data = {
@@ -691,21 +578,6 @@ static const struct mvebu_mbus_soc_data orion5x_2win_mbus_data = {
 	.win_cfg_offset      = orion_mbus_win_offset,
 	.setup_cpu_target    = mvebu_mbus_default_setup_cpu_target,
 	.show_cpu_target     = mvebu_sdram_debug_show_orion,
-	.map                 = orion5x_map,
-};
-
-static const struct mvebu_mbus_mapping mv78xx0_map[] = {
-	MAPDEF("pcie0.0", 4, 0xe0, MAPDEF_PCIMASK),
-	MAPDEF("pcie0.1", 4, 0xd0, MAPDEF_PCIMASK),
-	MAPDEF("pcie0.2", 4, 0xb0, MAPDEF_PCIMASK),
-	MAPDEF("pcie0.3", 4, 0x70, MAPDEF_PCIMASK),
-	MAPDEF("pcie1.0", 8, 0xe0, MAPDEF_PCIMASK),
-	MAPDEF("pcie1.1", 8, 0xd0, MAPDEF_PCIMASK),
-	MAPDEF("pcie1.2", 8, 0xb0, MAPDEF_PCIMASK),
-	MAPDEF("pcie1.3", 8, 0x70, MAPDEF_PCIMASK),
-	MAPDEF("pcie2.0", 4, 0xf0, MAPDEF_PCIMASK),
-	MAPDEF("pcie3.0", 8, 0xf0, MAPDEF_PCIMASK),
-	{},
 };
 
 static const struct mvebu_mbus_soc_data mv78xx0_mbus_data = {
@@ -714,7 +586,6 @@ static const struct mvebu_mbus_soc_data mv78xx0_mbus_data = {
 	.win_cfg_offset      = mv78xx0_mbus_win_offset,
 	.setup_cpu_target    = mvebu_mbus_default_setup_cpu_target,
 	.show_cpu_target     = mvebu_sdram_debug_show_orion,
-	.map                 = mv78xx0_map,
 };
 
 /*
@@ -725,9 +596,9 @@ static const struct mvebu_mbus_soc_data mv78xx0_mbus_data = {
  */
 static const struct of_device_id of_mvebu_mbus_ids[] = {
 	{ .compatible = "marvell,armada370-mbus",
-	  .data = &armada_370_mbus_data, },
+	  .data = &armada_370_xp_mbus_data, },
 	{ .compatible = "marvell,armadaxp-mbus",
-	  .data = &armada_xp_mbus_data, },
+	  .data = &armada_370_xp_mbus_data, },
 	{ .compatible = "marvell,kirkwood-mbus",
 	  .data = &kirkwood_mbus_data, },
 	{ .compatible = "marvell,dove-mbus",
@@ -748,48 +619,27 @@ static const struct of_device_id of_mvebu_mbus_ids[] = {
 /*
  * Public API of the driver
  */
-int mvebu_mbus_add_window_remap_flags(const char *devname, phys_addr_t base,
-				      size_t size, phys_addr_t remap,
-				      unsigned int flags)
+int mvebu_mbus_add_window_remap_by_id(unsigned int target,
+				      unsigned int attribute,
+				      phys_addr_t base, size_t size,
+				      phys_addr_t remap)
 {
 	struct mvebu_mbus_state *s = &mbus_state;
-	u8 target, attr;
-	int i;
-
-	if (!s->soc->map)
-		return -ENODEV;
-
-	for (i = 0; s->soc->map[i].name; i++)
-		if (!strcmp(s->soc->map[i].name, devname))
-			break;
-
-	if (!s->soc->map[i].name) {
-		pr_err("unknown device '%s'\n", devname);
-		return -ENODEV;
-	}
-
-	target = s->soc->map[i].target;
-	attr   = s->soc->map[i].attr;
-
-	if (flags == MVEBU_MBUS_PCI_MEM)
-		attr |= 0x8;
-	else if (flags == MVEBU_MBUS_PCI_WA)
-		attr |= 0x28;
 
-	if (!mvebu_mbus_window_conflicts(s, base, size, target, attr)) {
-		pr_err("cannot add window '%s', conflicts with another window\n",
-		       devname);
+	if (!mvebu_mbus_window_conflicts(s, base, size, target, attribute)) {
+		pr_err("cannot add window '%x:%x', conflicts with another window\n",
+		       target, attribute);
 		return -EINVAL;
 	}
 
-	return mvebu_mbus_alloc_window(s, base, size, remap, target, attr);
-
+	return mvebu_mbus_alloc_window(s, base, size, remap, target, attribute);
 }
 
-int mvebu_mbus_add_window(const char *devname, phys_addr_t base, size_t size)
+int mvebu_mbus_add_window_by_id(unsigned int target, unsigned int attribute,
+				phys_addr_t base, size_t size)
 {
-	return mvebu_mbus_add_window_remap_flags(devname, base, size,
-						 MVEBU_MBUS_NO_REMAP, 0);
+	return mvebu_mbus_add_window_remap_by_id(target, attribute, base,
+						 size, MVEBU_MBUS_NO_REMAP);
 }
 
 int mvebu_mbus_del_window(phys_addr_t base, size_t size)
@@ -804,6 +654,20 @@ int mvebu_mbus_del_window(phys_addr_t base, size_t size)
 	return 0;
 }
 
+void mvebu_mbus_get_pcie_mem_aperture(struct resource *res)
+{
+	if (!res)
+		return;
+	*res = mbus_state.pcie_mem_aperture;
+}
+
+void mvebu_mbus_get_pcie_io_aperture(struct resource *res)
+{
+	if (!res)
+		return;
+	*res = mbus_state.pcie_io_aperture;
+}
+
 static __init int mvebu_mbus_debugfs_init(void)
 {
 	struct mvebu_mbus_state *s = &mbus_state;
@@ -830,14 +694,45 @@ static __init int mvebu_mbus_debugfs_init(void)
 }
 fs_initcall(mvebu_mbus_debugfs_init);
 
+static int __init mvebu_mbus_common_init(struct mvebu_mbus_state *mbus,
+					 phys_addr_t mbuswins_phys_base,
+					 size_t mbuswins_size,
+					 phys_addr_t sdramwins_phys_base,
+					 size_t sdramwins_size)
+{
+	struct device_node *np;
+	int win;
+
+	mbus->mbuswins_base = ioremap(mbuswins_phys_base, mbuswins_size);
+	if (!mbus->mbuswins_base)
+		return -ENOMEM;
+
+	mbus->sdramwins_base = ioremap(sdramwins_phys_base, sdramwins_size);
+	if (!mbus->sdramwins_base) {
+		iounmap(mbus_state.mbuswins_base);
+		return -ENOMEM;
+	}
+
+	np = of_find_compatible_node(NULL, NULL, "marvell,coherency-fabric");
+	if (np) {
+		mbus->hw_io_coherency = 1;
+		of_node_put(np);
+	}
+
+	for (win = 0; win < mbus->soc->num_wins; win++)
+		mvebu_mbus_disable_window(mbus, win);
+
+	mbus->soc->setup_cpu_target(mbus);
+
+	return 0;
+}
+
 int __init mvebu_mbus_init(const char *soc, phys_addr_t mbuswins_phys_base,
 			   size_t mbuswins_size,
 			   phys_addr_t sdramwins_phys_base,
 			   size_t sdramwins_size)
 {
-	struct mvebu_mbus_state *mbus = &mbus_state;
 	const struct of_device_id *of_id;
-	int win;
 
 	for (of_id = of_mvebu_mbus_ids; of_id->compatible; of_id++)
 		if (!strcmp(of_id->compatible, soc))
@@ -848,25 +743,203 @@ int __init mvebu_mbus_init(const char *soc, phys_addr_t mbuswins_phys_base,
 		return -ENODEV;
 	}
 
-	mbus->soc = of_id->data;
+	mbus_state.soc = of_id->data;
 
-	mbus->mbuswins_base = ioremap(mbuswins_phys_base, mbuswins_size);
-	if (!mbus->mbuswins_base)
-		return -ENOMEM;
+	return mvebu_mbus_common_init(&mbus_state,
+			mbuswins_phys_base,
+			mbuswins_size,
+			sdramwins_phys_base,
+			sdramwins_size);
+}
 
-	mbus->sdramwins_base = ioremap(sdramwins_phys_base, sdramwins_size);
-	if (!mbus->sdramwins_base) {
-		iounmap(mbus_state.mbuswins_base);
+#ifdef CONFIG_OF
+/*
+ * The window IDs in the ranges DT property have the following format:
+ *  - bits 28 to 31: MBus custom field
+ *  - bits 24 to 27: window target ID
+ *  - bits 16 to 23: window attribute ID
+ *  - bits  0 to 15: unused
+ */
+#define CUSTOM(id) (((id) & 0xF0000000) >> 24)
+#define TARGET(id) (((id) & 0x0F000000) >> 24)
+#define ATTR(id)   (((id) & 0x00FF0000) >> 16)
+
+static int __init mbus_dt_setup_win(struct mvebu_mbus_state *mbus,
+				    u32 base, u32 size,
+				    u8 target, u8 attr)
+{
+	if (!mvebu_mbus_window_conflicts(mbus, base, size, target, attr)) {
+		pr_err("cannot add window '%04x:%04x', conflicts with another window\n",
+		       target, attr);
+		return -EBUSY;
+	}
+
+	if (mvebu_mbus_alloc_window(mbus, base, size, MVEBU_MBUS_NO_REMAP,
+				    target, attr)) {
+		pr_err("cannot add window '%04x:%04x', too many windows\n",
+		       target, attr);
 		return -ENOMEM;
 	}
+	return 0;
+}
 
-	if (of_find_compatible_node(NULL, NULL, "marvell,coherency-fabric"))
-		mbus->hw_io_coherency = 1;
+static int __init
+mbus_parse_ranges(struct device_node *node,
+		  int *addr_cells, int *c_addr_cells, int *c_size_cells,
+		  int *cell_count, const __be32 **ranges_start,
+		  const __be32 **ranges_end)
+{
+	const __be32 *prop;
+	int ranges_len, tuple_len;
+
+	/* Allow a node with no 'ranges' property */
+	*ranges_start = of_get_property(node, "ranges", &ranges_len);
+	if (*ranges_start == NULL) {
+		*addr_cells = *c_addr_cells = *c_size_cells = *cell_count = 0;
+		*ranges_start = *ranges_end = NULL;
+		return 0;
+	}
+	*ranges_end = *ranges_start + ranges_len / sizeof(__be32);
 
-	for (win = 0; win < mbus->soc->num_wins; win++)
-		mvebu_mbus_disable_window(mbus, win);
+	*addr_cells = of_n_addr_cells(node);
 
-	mbus->soc->setup_cpu_target(mbus);
+	prop = of_get_property(node, "#address-cells", NULL);
+	*c_addr_cells = be32_to_cpup(prop);
+
+	prop = of_get_property(node, "#size-cells", NULL);
+	*c_size_cells = be32_to_cpup(prop);
 
+	*cell_count = *addr_cells + *c_addr_cells + *c_size_cells;
+	tuple_len = (*cell_count) * sizeof(__be32);
+
+	if (ranges_len % tuple_len) {
+		pr_warn("malformed ranges entry '%s'\n", node->name);
+		return -EINVAL;
+	}
 	return 0;
 }
+
+static int __init mbus_dt_setup(struct mvebu_mbus_state *mbus,
+				struct device_node *np)
+{
+	int addr_cells, c_addr_cells, c_size_cells;
+	int i, ret, cell_count;
+	const __be32 *r, *ranges_start, *ranges_end;
+
+	ret = mbus_parse_ranges(np, &addr_cells, &c_addr_cells,
+				&c_size_cells, &cell_count,
+				&ranges_start, &ranges_end);
+	if (ret < 0)
+		return ret;
+
+	for (i = 0, r = ranges_start; r < ranges_end; r += cell_count, i++) {
+		u32 windowid, base, size;
+		u8 target, attr;
+
+		/*
+		 * An entry with a non-zero custom field do not
+		 * correspond to a static window, so skip it.
+		 */
+		windowid = of_read_number(r, 1);
+		if (CUSTOM(windowid))
+			continue;
+
+		target = TARGET(windowid);
+		attr = ATTR(windowid);
+
+		base = of_read_number(r + c_addr_cells, addr_cells);
+		size = of_read_number(r + c_addr_cells + addr_cells,
+				      c_size_cells);
+		ret = mbus_dt_setup_win(mbus, base, size, target, attr);
+		if (ret < 0)
+			return ret;
+	}
+	return 0;
+}
+
+static void __init mvebu_mbus_get_pcie_resources(struct device_node *np,
+						 struct resource *mem,
+						 struct resource *io)
+{
+	u32 reg[2];
+	int ret;
+
+	/*
+	 * These are optional, so we make sure that resource_size(x) will
+	 * return 0.
+	 */
+	memset(mem, 0, sizeof(struct resource));
+	mem->end = -1;
+	memset(io, 0, sizeof(struct resource));
+	io->end = -1;
+
+	ret = of_property_read_u32_array(np, "pcie-mem-aperture", reg, ARRAY_SIZE(reg));
+	if (!ret) {
+		mem->start = reg[0];
+		mem->end = mem->start + reg[1];
+		mem->flags = IORESOURCE_MEM;
+	}
+
+	ret = of_property_read_u32_array(np, "pcie-io-aperture", reg, ARRAY_SIZE(reg));
+	if (!ret) {
+		io->start = reg[0];
+		io->end = io->start + reg[1];
+		io->flags = IORESOURCE_IO;
+	}
+}
+
+int __init mvebu_mbus_dt_init(void)
+{
+	struct resource mbuswins_res, sdramwins_res;
+	struct device_node *np, *controller;
+	const struct of_device_id *of_id;
+	const __be32 *prop;
+	int ret;
+
+	np = of_find_matching_node(NULL, of_mvebu_mbus_ids);
+	if (!np) {
+		pr_err("could not find a matching SoC family\n");
+		return -ENODEV;
+	}
+
+	of_id = of_match_node(of_mvebu_mbus_ids, np);
+	mbus_state.soc = of_id->data;
+
+	prop = of_get_property(np, "controller", NULL);
+	if (!prop) {
+		pr_err("required 'controller' property missing\n");
+		return -EINVAL;
+	}
+
+	controller = of_find_node_by_phandle(be32_to_cpup(prop));
+	if (!controller) {
+		pr_err("could not find an 'mbus-controller' node\n");
+		return -ENODEV;
+	}
+
+	if (of_address_to_resource(controller, 0, &mbuswins_res)) {
+		pr_err("cannot get MBUS register address\n");
+		return -EINVAL;
+	}
+
+	if (of_address_to_resource(controller, 1, &sdramwins_res)) {
+		pr_err("cannot get SDRAM register address\n");
+		return -EINVAL;
+	}
+
+	/* Get optional pcie-{mem,io}-aperture properties */
+	mvebu_mbus_get_pcie_resources(np, &mbus_state.pcie_mem_aperture,
+					  &mbus_state.pcie_io_aperture);
+
+	ret = mvebu_mbus_common_init(&mbus_state,
+				     mbuswins_res.start,
+				     resource_size(&mbuswins_res),
+				     sdramwins_res.start,
+				     resource_size(&sdramwins_res));
+	if (ret)
+		return ret;
+
+	/* Setup statically declared windows in the DT */
+	return mbus_dt_setup(&mbus_state, np);
+}
+#endif
diff --git a/drivers/char/bsr.c b/drivers/char/bsr.c
index 97467053a01b..0671e45daa57 100644
--- a/drivers/char/bsr.c
+++ b/drivers/char/bsr.c
@@ -95,6 +95,7 @@ bsr_size_show(struct device *dev, struct device_attribute *attr, char *buf)
 	struct bsr_dev *bsr_dev = dev_get_drvdata(dev);
 	return sprintf(buf, "%u\n", bsr_dev->bsr_bytes);
 }
+static DEVICE_ATTR_RO(bsr_size);
 
 static ssize_t
 bsr_stride_show(struct device *dev, struct device_attribute *attr, char *buf)
@@ -102,20 +103,23 @@ bsr_stride_show(struct device *dev, struct device_attribute *attr, char *buf)
 	struct bsr_dev *bsr_dev = dev_get_drvdata(dev);
 	return sprintf(buf, "%u\n", bsr_dev->bsr_stride);
 }
+static DEVICE_ATTR_RO(bsr_stride);
 
 static ssize_t
-bsr_len_show(struct device *dev, struct device_attribute *attr, char *buf)
+bsr_length_show(struct device *dev, struct device_attribute *attr, char *buf)
 {
 	struct bsr_dev *bsr_dev = dev_get_drvdata(dev);
 	return sprintf(buf, "%llu\n", bsr_dev->bsr_len);
 }
+static DEVICE_ATTR_RO(bsr_length);
 
-static struct device_attribute bsr_dev_attrs[] = {
-	__ATTR(bsr_size, S_IRUGO, bsr_size_show, NULL),
-	__ATTR(bsr_stride, S_IRUGO, bsr_stride_show, NULL),
-	__ATTR(bsr_length, S_IRUGO, bsr_len_show, NULL),
-	__ATTR_NULL
+static struct attribute *bsr_dev_attrs[] = {
+	&dev_attr_bsr_size.attr,
+	&dev_attr_bsr_stride.attr,
+	&dev_attr_bsr_length.attr,
+	NULL,
 };
+ATTRIBUTE_GROUPS(bsr_dev);
 
 static int bsr_mmap(struct file *filp, struct vm_area_struct *vma)
 {
@@ -308,7 +312,7 @@ static int __init bsr_init(void)
 		ret = PTR_ERR(bsr_class);
 		goto out_err_1;
 	}
-	bsr_class->dev_attrs = bsr_dev_attrs;
+	bsr_class->dev_groups = bsr_dev_groups;
 
 	ret = alloc_chrdev_region(&bsr_dev, 0, BSR_MAX_DEVS, "bsr");
 	bsr_major = MAJOR(bsr_dev);
diff --git a/drivers/char/hw_random/Kconfig b/drivers/char/hw_random/Kconfig
index 40a865449f35..0aa9d91daef5 100644
--- a/drivers/char/hw_random/Kconfig
+++ b/drivers/char/hw_random/Kconfig
@@ -153,12 +153,12 @@ config HW_RANDOM_IXP4XX
 
 config HW_RANDOM_OMAP
 	tristate "OMAP Random Number Generator support"
-	depends on HW_RANDOM && (ARCH_OMAP16XX || ARCH_OMAP2)
+	depends on HW_RANDOM && (ARCH_OMAP16XX || ARCH_OMAP2PLUS)
 	default HW_RANDOM
  	---help---
  	  This driver provides kernel-side support for the Random Number
-	  Generator hardware found on OMAP16xx and OMAP24xx multimedia
-	  processors.
+	  Generator hardware found on OMAP16xx, OMAP2/3/4/5 and AM33xx/AM43xx
+	  multimedia processors.
 
 	  To compile this driver as a module, choose M here: the
 	  module will be called omap-rng.
diff --git a/drivers/char/hw_random/mxc-rnga.c b/drivers/char/hw_random/mxc-rnga.c
index 19a12ac64a9e..6a86b6f56af2 100644
--- a/drivers/char/hw_random/mxc-rnga.c
+++ b/drivers/char/hw_random/mxc-rnga.c
@@ -164,7 +164,9 @@ static int __init mxc_rnga_probe(struct platform_device *pdev)
 		goto out;
 	}
 
-	clk_prepare_enable(mxc_rng->clk);
+	err = clk_prepare_enable(mxc_rng->clk);
+	if (err)
+		goto out;
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	mxc_rng->mem = devm_ioremap_resource(&pdev->dev, res);
diff --git a/drivers/char/hw_random/omap-rng.c b/drivers/char/hw_random/omap-rng.c
index 6843ec87b98b..9b89ff4881de 100644
--- a/drivers/char/hw_random/omap-rng.c
+++ b/drivers/char/hw_random/omap-rng.c
@@ -24,57 +24,131 @@
 #include <linux/delay.h>
 #include <linux/slab.h>
 #include <linux/pm_runtime.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/of_address.h>
+#include <linux/interrupt.h>
 
 #include <asm/io.h>
 
-#define RNG_OUT_REG		0x00		/* Output register */
-#define RNG_STAT_REG		0x04		/* Status register
-							[0] = STAT_BUSY */
-#define RNG_ALARM_REG		0x24		/* Alarm register
-							[7:0] = ALARM_COUNTER */
-#define RNG_CONFIG_REG		0x28		/* Configuration register
-							[11:6] = RESET_COUNT
-							[5:3]  = RING2_DELAY
-							[2:0]  = RING1_DELAY */
-#define RNG_REV_REG		0x3c		/* Revision register
-							[7:0] = REV_NB */
-#define RNG_MASK_REG		0x40		/* Mask and reset register
-							[2] = IT_EN
-							[1] = SOFTRESET
-							[0] = AUTOIDLE */
-#define RNG_SYSSTATUS		0x44		/* System status
-							[0] = RESETDONE */
+#define RNG_REG_STATUS_RDY			(1 << 0)
+
+#define RNG_REG_INTACK_RDY_MASK			(1 << 0)
+#define RNG_REG_INTACK_SHUTDOWN_OFLO_MASK	(1 << 1)
+#define RNG_SHUTDOWN_OFLO_MASK			(1 << 1)
+
+#define RNG_CONTROL_STARTUP_CYCLES_SHIFT	16
+#define RNG_CONTROL_STARTUP_CYCLES_MASK		(0xffff << 16)
+#define RNG_CONTROL_ENABLE_TRNG_SHIFT		10
+#define RNG_CONTROL_ENABLE_TRNG_MASK		(1 << 10)
+
+#define RNG_CONFIG_MAX_REFIL_CYCLES_SHIFT	16
+#define RNG_CONFIG_MAX_REFIL_CYCLES_MASK	(0xffff << 16)
+#define RNG_CONFIG_MIN_REFIL_CYCLES_SHIFT	0
+#define RNG_CONFIG_MIN_REFIL_CYCLES_MASK	(0xff << 0)
+
+#define RNG_CONTROL_STARTUP_CYCLES		0xff
+#define RNG_CONFIG_MIN_REFIL_CYCLES		0x21
+#define RNG_CONFIG_MAX_REFIL_CYCLES		0x22
+
+#define RNG_ALARMCNT_ALARM_TH_SHIFT		0x0
+#define RNG_ALARMCNT_ALARM_TH_MASK		(0xff << 0)
+#define RNG_ALARMCNT_SHUTDOWN_TH_SHIFT		16
+#define RNG_ALARMCNT_SHUTDOWN_TH_MASK		(0x1f << 16)
+#define RNG_ALARM_THRESHOLD			0xff
+#define RNG_SHUTDOWN_THRESHOLD			0x4
+
+#define RNG_REG_FROENABLE_MASK			0xffffff
+#define RNG_REG_FRODETUNE_MASK			0xffffff
+
+#define OMAP2_RNG_OUTPUT_SIZE			0x4
+#define OMAP4_RNG_OUTPUT_SIZE			0x8
+
+enum {
+	RNG_OUTPUT_L_REG = 0,
+	RNG_OUTPUT_H_REG,
+	RNG_STATUS_REG,
+	RNG_INTMASK_REG,
+	RNG_INTACK_REG,
+	RNG_CONTROL_REG,
+	RNG_CONFIG_REG,
+	RNG_ALARMCNT_REG,
+	RNG_FROENABLE_REG,
+	RNG_FRODETUNE_REG,
+	RNG_ALARMMASK_REG,
+	RNG_ALARMSTOP_REG,
+	RNG_REV_REG,
+	RNG_SYSCONFIG_REG,
+};
+
+static const u16 reg_map_omap2[] = {
+	[RNG_OUTPUT_L_REG]	= 0x0,
+	[RNG_STATUS_REG]	= 0x4,
+	[RNG_CONFIG_REG]	= 0x28,
+	[RNG_REV_REG]		= 0x3c,
+	[RNG_SYSCONFIG_REG]	= 0x40,
+};
 
+static const u16 reg_map_omap4[] = {
+	[RNG_OUTPUT_L_REG]	= 0x0,
+	[RNG_OUTPUT_H_REG]	= 0x4,
+	[RNG_STATUS_REG]	= 0x8,
+	[RNG_INTMASK_REG]	= 0xc,
+	[RNG_INTACK_REG]	= 0x10,
+	[RNG_CONTROL_REG]	= 0x14,
+	[RNG_CONFIG_REG]	= 0x18,
+	[RNG_ALARMCNT_REG]	= 0x1c,
+	[RNG_FROENABLE_REG]	= 0x20,
+	[RNG_FRODETUNE_REG]	= 0x24,
+	[RNG_ALARMMASK_REG]	= 0x28,
+	[RNG_ALARMSTOP_REG]	= 0x2c,
+	[RNG_REV_REG]		= 0x1FE0,
+	[RNG_SYSCONFIG_REG]	= 0x1FE4,
+};
+
+struct omap_rng_dev;
 /**
- * struct omap_rng_private_data - RNG IP block-specific data
- * @base: virtual address of the beginning of the RNG IP block registers
- * @mem_res: struct resource * for the IP block registers physical memory
+ * struct omap_rng_pdata - RNG IP block-specific data
+ * @regs: Pointer to the register offsets structure.
+ * @data_size: No. of bytes in RNG output.
+ * @data_present: Callback to determine if data is available.
+ * @init: Callback for IP specific initialization sequence.
+ * @cleanup: Callback for IP specific cleanup sequence.
  */
-struct omap_rng_private_data {
-	void __iomem *base;
-	struct resource *mem_res;
+struct omap_rng_pdata {
+	u16	*regs;
+	u32	data_size;
+	u32	(*data_present)(struct omap_rng_dev *priv);
+	int	(*init)(struct omap_rng_dev *priv);
+	void	(*cleanup)(struct omap_rng_dev *priv);
 };
 
-static inline u32 omap_rng_read_reg(struct omap_rng_private_data *priv, int reg)
+struct omap_rng_dev {
+	void __iomem			*base;
+	struct device			*dev;
+	const struct omap_rng_pdata	*pdata;
+};
+
+static inline u32 omap_rng_read(struct omap_rng_dev *priv, u16 reg)
 {
-	return __raw_readl(priv->base + reg);
+	return __raw_readl(priv->base + priv->pdata->regs[reg]);
 }
 
-static inline void omap_rng_write_reg(struct omap_rng_private_data *priv,
-				      int reg, u32 val)
+static inline void omap_rng_write(struct omap_rng_dev *priv, u16 reg,
+				      u32 val)
 {
-	__raw_writel(val, priv->base + reg);
+	__raw_writel(val, priv->base + priv->pdata->regs[reg]);
 }
 
 static int omap_rng_data_present(struct hwrng *rng, int wait)
 {
-	struct omap_rng_private_data *priv;
+	struct omap_rng_dev *priv;
 	int data, i;
 
-	priv = (struct omap_rng_private_data *)rng->priv;
+	priv = (struct omap_rng_dev *)rng->priv;
 
 	for (i = 0; i < 20; i++) {
-		data = omap_rng_read_reg(priv, RNG_STAT_REG) ? 0 : 1;
+		data = priv->pdata->data_present(priv);
 		if (data || !wait)
 			break;
 		/* RNG produces data fast enough (2+ MBit/sec, even
@@ -89,27 +163,212 @@ static int omap_rng_data_present(struct hwrng *rng, int wait)
 
 static int omap_rng_data_read(struct hwrng *rng, u32 *data)
 {
-	struct omap_rng_private_data *priv;
+	struct omap_rng_dev *priv;
+	u32 data_size, i;
+
+	priv = (struct omap_rng_dev *)rng->priv;
+	data_size = priv->pdata->data_size;
+
+	for (i = 0; i < data_size / sizeof(u32); i++)
+		data[i] = omap_rng_read(priv, RNG_OUTPUT_L_REG + i);
+
+	if (priv->pdata->regs[RNG_INTACK_REG])
+		omap_rng_write(priv, RNG_INTACK_REG, RNG_REG_INTACK_RDY_MASK);
+	return data_size;
+}
+
+static int omap_rng_init(struct hwrng *rng)
+{
+	struct omap_rng_dev *priv;
 
-	priv = (struct omap_rng_private_data *)rng->priv;
+	priv = (struct omap_rng_dev *)rng->priv;
+	return priv->pdata->init(priv);
+}
 
-	*data = omap_rng_read_reg(priv, RNG_OUT_REG);
+static void omap_rng_cleanup(struct hwrng *rng)
+{
+	struct omap_rng_dev *priv;
 
-	return sizeof(u32);
+	priv = (struct omap_rng_dev *)rng->priv;
+	priv->pdata->cleanup(priv);
 }
 
 static struct hwrng omap_rng_ops = {
 	.name		= "omap",
 	.data_present	= omap_rng_data_present,
 	.data_read	= omap_rng_data_read,
+	.init		= omap_rng_init,
+	.cleanup	= omap_rng_cleanup,
+};
+
+static inline u32 omap2_rng_data_present(struct omap_rng_dev *priv)
+{
+	return omap_rng_read(priv, RNG_STATUS_REG) ? 0 : 1;
+}
+
+static int omap2_rng_init(struct omap_rng_dev *priv)
+{
+	omap_rng_write(priv, RNG_SYSCONFIG_REG, 0x1);
+	return 0;
+}
+
+static void omap2_rng_cleanup(struct omap_rng_dev *priv)
+{
+	omap_rng_write(priv, RNG_SYSCONFIG_REG, 0x0);
+}
+
+static struct omap_rng_pdata omap2_rng_pdata = {
+	.regs		= (u16 *)reg_map_omap2,
+	.data_size	= OMAP2_RNG_OUTPUT_SIZE,
+	.data_present	= omap2_rng_data_present,
+	.init		= omap2_rng_init,
+	.cleanup	= omap2_rng_cleanup,
 };
 
+#if defined(CONFIG_OF)
+static inline u32 omap4_rng_data_present(struct omap_rng_dev *priv)
+{
+	return omap_rng_read(priv, RNG_STATUS_REG) & RNG_REG_STATUS_RDY;
+}
+
+static int omap4_rng_init(struct omap_rng_dev *priv)
+{
+	u32 val;
+
+	/* Return if RNG is already running. */
+	if (omap_rng_read(priv, RNG_CONFIG_REG) & RNG_CONTROL_ENABLE_TRNG_MASK)
+		return 0;
+
+	val = RNG_CONFIG_MIN_REFIL_CYCLES << RNG_CONFIG_MIN_REFIL_CYCLES_SHIFT;
+	val |= RNG_CONFIG_MAX_REFIL_CYCLES << RNG_CONFIG_MAX_REFIL_CYCLES_SHIFT;
+	omap_rng_write(priv, RNG_CONFIG_REG, val);
+
+	omap_rng_write(priv, RNG_FRODETUNE_REG, 0x0);
+	omap_rng_write(priv, RNG_FROENABLE_REG, RNG_REG_FROENABLE_MASK);
+	val = RNG_ALARM_THRESHOLD << RNG_ALARMCNT_ALARM_TH_SHIFT;
+	val |= RNG_SHUTDOWN_THRESHOLD << RNG_ALARMCNT_SHUTDOWN_TH_SHIFT;
+	omap_rng_write(priv, RNG_ALARMCNT_REG, val);
+
+	val = RNG_CONTROL_STARTUP_CYCLES << RNG_CONTROL_STARTUP_CYCLES_SHIFT;
+	val |= RNG_CONTROL_ENABLE_TRNG_MASK;
+	omap_rng_write(priv, RNG_CONTROL_REG, val);
+
+	return 0;
+}
+
+static void omap4_rng_cleanup(struct omap_rng_dev *priv)
+{
+	int val;
+
+	val = omap_rng_read(priv, RNG_CONTROL_REG);
+	val &= ~RNG_CONTROL_ENABLE_TRNG_MASK;
+	omap_rng_write(priv, RNG_CONFIG_REG, val);
+}
+
+static irqreturn_t omap4_rng_irq(int irq, void *dev_id)
+{
+	struct omap_rng_dev *priv = dev_id;
+	u32 fro_detune, fro_enable;
+
+	/*
+	 * Interrupt raised by a fro shutdown threshold, do the following:
+	 * 1. Clear the alarm events.
+	 * 2. De tune the FROs which are shutdown.
+	 * 3. Re enable the shutdown FROs.
+	 */
+	omap_rng_write(priv, RNG_ALARMMASK_REG, 0x0);
+	omap_rng_write(priv, RNG_ALARMSTOP_REG, 0x0);
+
+	fro_enable = omap_rng_read(priv, RNG_FROENABLE_REG);
+	fro_detune = ~fro_enable & RNG_REG_FRODETUNE_MASK;
+	fro_detune = fro_detune | omap_rng_read(priv, RNG_FRODETUNE_REG);
+	fro_enable = RNG_REG_FROENABLE_MASK;
+
+	omap_rng_write(priv, RNG_FRODETUNE_REG, fro_detune);
+	omap_rng_write(priv, RNG_FROENABLE_REG, fro_enable);
+
+	omap_rng_write(priv, RNG_INTACK_REG, RNG_REG_INTACK_SHUTDOWN_OFLO_MASK);
+
+	return IRQ_HANDLED;
+}
+
+static struct omap_rng_pdata omap4_rng_pdata = {
+	.regs		= (u16 *)reg_map_omap4,
+	.data_size	= OMAP4_RNG_OUTPUT_SIZE,
+	.data_present	= omap4_rng_data_present,
+	.init		= omap4_rng_init,
+	.cleanup	= omap4_rng_cleanup,
+};
+
+static const struct of_device_id omap_rng_of_match[] = {
+		{
+			.compatible	= "ti,omap2-rng",
+			.data		= &omap2_rng_pdata,
+		},
+		{
+			.compatible	= "ti,omap4-rng",
+			.data		= &omap4_rng_pdata,
+		},
+		{},
+};
+MODULE_DEVICE_TABLE(of, omap_rng_of_match);
+
+static int of_get_omap_rng_device_details(struct omap_rng_dev *priv,
+					  struct platform_device *pdev)
+{
+	const struct of_device_id *match;
+	struct device *dev = &pdev->dev;
+	int irq, err;
+
+	match = of_match_device(of_match_ptr(omap_rng_of_match), dev);
+	if (!match) {
+		dev_err(dev, "no compatible OF match\n");
+		return -EINVAL;
+	}
+	priv->pdata = match->data;
+
+	if (of_device_is_compatible(dev->of_node, "ti,omap4-rng")) {
+		irq = platform_get_irq(pdev, 0);
+		if (irq < 0) {
+			dev_err(dev, "%s: error getting IRQ resource - %d\n",
+				__func__, irq);
+			return irq;
+		}
+
+		err = devm_request_irq(dev, irq, omap4_rng_irq,
+				       IRQF_TRIGGER_NONE, dev_name(dev), priv);
+		if (err) {
+			dev_err(dev, "unable to request irq %d, err = %d\n",
+				irq, err);
+			return err;
+		}
+		omap_rng_write(priv, RNG_INTMASK_REG, RNG_SHUTDOWN_OFLO_MASK);
+	}
+	return 0;
+}
+#else
+static int of_get_omap_rng_device_details(struct omap_rng_dev *omap_rng,
+					  struct platform_device *pdev)
+{
+	return -EINVAL;
+}
+#endif
+
+static int get_omap_rng_device_details(struct omap_rng_dev *omap_rng)
+{
+	/* Only OMAP2/3 can be non-DT */
+	omap_rng->pdata = &omap2_rng_pdata;
+	return 0;
+}
+
 static int omap_rng_probe(struct platform_device *pdev)
 {
-	struct omap_rng_private_data *priv;
+	struct omap_rng_dev *priv;
+	struct resource *res;
+	struct device *dev = &pdev->dev;
 	int ret;
 
-	priv = kzalloc(sizeof(struct omap_rng_private_data), GFP_KERNEL);
+	priv = devm_kzalloc(dev, sizeof(struct omap_rng_dev), GFP_KERNEL);
 	if (!priv) {
 		dev_err(&pdev->dev, "could not allocate memory\n");
 		return -ENOMEM;
@@ -117,26 +376,29 @@ static int omap_rng_probe(struct platform_device *pdev)
 
 	omap_rng_ops.priv = (unsigned long)priv;
 	platform_set_drvdata(pdev, priv);
+	priv->dev = dev;
 
-	priv->mem_res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	priv->base = devm_ioremap_resource(&pdev->dev, priv->mem_res);
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	priv->base = devm_ioremap_resource(dev, res);
 	if (IS_ERR(priv->base)) {
 		ret = PTR_ERR(priv->base);
 		goto err_ioremap;
 	}
-	platform_set_drvdata(pdev, priv);
 
 	pm_runtime_enable(&pdev->dev);
 	pm_runtime_get_sync(&pdev->dev);
 
+	ret = (dev->of_node) ? of_get_omap_rng_device_details(priv, pdev) :
+				get_omap_rng_device_details(priv);
+	if (ret)
+		goto err_ioremap;
+
 	ret = hwrng_register(&omap_rng_ops);
 	if (ret)
 		goto err_register;
 
 	dev_info(&pdev->dev, "OMAP Random Number Generator ver. %02x\n",
-		 omap_rng_read_reg(priv, RNG_REV_REG));
-
-	omap_rng_write_reg(priv, RNG_MASK_REG, 0x1);
+		 omap_rng_read(priv, RNG_REV_REG));
 
 	return 0;
 
@@ -144,26 +406,21 @@ err_register:
 	priv->base = NULL;
 	pm_runtime_disable(&pdev->dev);
 err_ioremap:
-	kfree(priv);
-
+	dev_err(dev, "initialization failed.\n");
 	return ret;
 }
 
 static int __exit omap_rng_remove(struct platform_device *pdev)
 {
-	struct omap_rng_private_data *priv = platform_get_drvdata(pdev);
+	struct omap_rng_dev *priv = platform_get_drvdata(pdev);
 
 	hwrng_unregister(&omap_rng_ops);
 
-	omap_rng_write_reg(priv, RNG_MASK_REG, 0x0);
+	priv->pdata->cleanup(priv);
 
 	pm_runtime_put_sync(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
 
-	release_mem_region(priv->mem_res->start, resource_size(priv->mem_res));
-
-	kfree(priv);
-
 	return 0;
 }
 
@@ -171,9 +428,9 @@ static int __exit omap_rng_remove(struct platform_device *pdev)
 
 static int omap_rng_suspend(struct device *dev)
 {
-	struct omap_rng_private_data *priv = dev_get_drvdata(dev);
+	struct omap_rng_dev *priv = dev_get_drvdata(dev);
 
-	omap_rng_write_reg(priv, RNG_MASK_REG, 0x0);
+	priv->pdata->cleanup(priv);
 	pm_runtime_put_sync(dev);
 
 	return 0;
@@ -181,10 +438,10 @@ static int omap_rng_suspend(struct device *dev)
 
 static int omap_rng_resume(struct device *dev)
 {
-	struct omap_rng_private_data *priv = dev_get_drvdata(dev);
+	struct omap_rng_dev *priv = dev_get_drvdata(dev);
 
 	pm_runtime_get_sync(dev);
-	omap_rng_write_reg(priv, RNG_MASK_REG, 0x1);
+	priv->pdata->init(priv);
 
 	return 0;
 }
@@ -198,31 +455,18 @@ static SIMPLE_DEV_PM_OPS(omap_rng_pm, omap_rng_suspend, omap_rng_resume);
 
 #endif
 
-/* work with hotplug and coldplug */
-MODULE_ALIAS("platform:omap_rng");
-
 static struct platform_driver omap_rng_driver = {
 	.driver = {
 		.name		= "omap_rng",
 		.owner		= THIS_MODULE,
 		.pm		= OMAP_RNG_PM,
+		.of_match_table = of_match_ptr(omap_rng_of_match),
 	},
 	.probe		= omap_rng_probe,
 	.remove		= __exit_p(omap_rng_remove),
 };
 
-static int __init omap_rng_init(void)
-{
-	return platform_driver_register(&omap_rng_driver);
-}
-
-static void __exit omap_rng_exit(void)
-{
-	platform_driver_unregister(&omap_rng_driver);
-}
-
-module_init(omap_rng_init);
-module_exit(omap_rng_exit);
-
+module_platform_driver(omap_rng_driver);
+MODULE_ALIAS("platform:omap_rng");
 MODULE_AUTHOR("Deepak Saxena (and others)");
 MODULE_LICENSE("GPL");
diff --git a/drivers/char/hw_random/picoxcell-rng.c b/drivers/char/hw_random/picoxcell-rng.c
index 973b95113edf..3d4c2293c6f5 100644
--- a/drivers/char/hw_random/picoxcell-rng.c
+++ b/drivers/char/hw_random/picoxcell-rng.c
@@ -33,7 +33,7 @@
 
 static void __iomem *rng_base;
 static struct clk *rng_clk;
-struct device *rng_dev;
+static struct device *rng_dev;
 
 static inline u32 picoxcell_trng_read_csr(void)
 {
diff --git a/drivers/char/hw_random/tx4939-rng.c b/drivers/char/hw_random/tx4939-rng.c
index 00593c847cf0..09c5fbea2b93 100644
--- a/drivers/char/hw_random/tx4939-rng.c
+++ b/drivers/char/hw_random/tx4939-rng.c
@@ -110,12 +110,10 @@ static int __init tx4939_rng_probe(struct platform_device *dev)
 	struct resource *r;
 	int i;
 
-	r = platform_get_resource(dev, IORESOURCE_MEM, 0);
-	if (!r)
-		return -EBUSY;
 	rngdev = devm_kzalloc(&dev->dev, sizeof(*rngdev), GFP_KERNEL);
 	if (!rngdev)
 		return -ENOMEM;
+	r = platform_get_resource(dev, IORESOURCE_MEM, 0);
 	rngdev->base = devm_ioremap_resource(&dev->dev, r);
 	if (IS_ERR(rngdev->base))
 		return PTR_ERR(rngdev->base);
diff --git a/drivers/char/hw_random/via-rng.c b/drivers/char/hw_random/via-rng.c
index d0387a84eec1..e737772ad69a 100644
--- a/drivers/char/hw_random/via-rng.c
+++ b/drivers/char/hw_random/via-rng.c
@@ -29,6 +29,7 @@
 #include <linux/kernel.h>
 #include <linux/hw_random.h>
 #include <linux/delay.h>
+#include <asm/cpu_device_id.h>
 #include <asm/io.h>
 #include <asm/msr.h>
 #include <asm/cpufeature.h>
@@ -220,5 +221,11 @@ static void __exit mod_exit(void)
 module_init(mod_init);
 module_exit(mod_exit);
 
+static struct x86_cpu_id via_rng_cpu_id[] = {
+	X86_FEATURE_MATCH(X86_FEATURE_XSTORE),
+	{}
+};
+
 MODULE_DESCRIPTION("H/W RNG driver for VIA CPU with PadLock");
 MODULE_LICENSE("GPL");
+MODULE_DEVICE_TABLE(x86cpu, via_rng_cpu_id);
diff --git a/drivers/char/ipmi/ipmi_devintf.c b/drivers/char/ipmi/ipmi_devintf.c
index d5a5f020810a..ec318bf434a6 100644
--- a/drivers/char/ipmi/ipmi_devintf.c
+++ b/drivers/char/ipmi/ipmi_devintf.c
@@ -810,6 +810,7 @@ static long compat_ipmi_ioctl(struct file *filep, unsigned int cmd,
 		struct ipmi_recv   __user *precv64;
 		struct ipmi_recv   recv64;
 
+		memset(&recv64, 0, sizeof(recv64));
 		if (get_compat_ipmi_recv(&recv64, compat_ptr(arg)))
 			return -EFAULT;
 
diff --git a/drivers/char/ipmi/ipmi_msghandler.c b/drivers/char/ipmi/ipmi_msghandler.c
index 4445fa164a2d..ec4e10fcf1a5 100644
--- a/drivers/char/ipmi/ipmi_msghandler.c
+++ b/drivers/char/ipmi/ipmi_msghandler.c
@@ -1848,7 +1848,7 @@ int ipmi_request_settime(ipmi_user_t      user,
 			 int              retries,
 			 unsigned int     retry_time_ms)
 {
-	unsigned char saddr, lun;
+	unsigned char saddr = 0, lun = 0;
 	int           rv;
 
 	if (!user)
diff --git a/drivers/char/ipmi/ipmi_si_intf.c b/drivers/char/ipmi/ipmi_si_intf.c
index af4b23ffc5a6..15e4a6031934 100644
--- a/drivers/char/ipmi/ipmi_si_intf.c
+++ b/drivers/char/ipmi/ipmi_si_intf.c
@@ -71,6 +71,11 @@
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
 
+#ifdef CONFIG_PARISC
+#include <asm/hardware.h>	/* for register_parisc_driver() stuff */
+#include <asm/parisc-device.h>
+#endif
+
 #define PFX "ipmi_si: "
 
 /* Measure times between events in the driver. */
@@ -298,6 +303,9 @@ static int pci_registered;
 #ifdef CONFIG_ACPI
 static int pnp_registered;
 #endif
+#ifdef CONFIG_PARISC
+static int parisc_registered;
+#endif
 
 static unsigned int kipmid_max_busy_us[SI_MAX_PARMS];
 static int num_max_busy_us;
@@ -2279,6 +2287,8 @@ static struct pnp_driver ipmi_pnp_driver = {
 	.remove		= ipmi_pnp_remove,
 	.id_table	= pnp_dev_table,
 };
+
+MODULE_DEVICE_TABLE(pnp, pnp_dev_table);
 #endif
 
 #ifdef CONFIG_DMI
@@ -2697,6 +2707,62 @@ static struct platform_driver ipmi_driver = {
 	.remove		= ipmi_remove,
 };
 
+#ifdef CONFIG_PARISC
+static int ipmi_parisc_probe(struct parisc_device *dev)
+{
+	struct smi_info *info;
+
+	info = smi_info_alloc();
+
+	if (!info) {
+		dev_err(&dev->dev,
+			"could not allocate memory for PARISC probe\n");
+		return -ENOMEM;
+	}
+
+	info->si_type		= SI_KCS;
+	info->addr_source	= SI_DEVICETREE;
+	info->io_setup		= mem_setup;
+	info->io.addr_type	= IPMI_MEM_ADDR_SPACE;
+	info->io.addr_data	= dev->hpa.start;
+	info->io.regsize	= 1;
+	info->io.regspacing	= 1;
+	info->io.regshift	= 0;
+	info->irq		= 0; /* no interrupt */
+	info->irq_setup		= NULL;
+	info->dev		= &dev->dev;
+
+	dev_dbg(&dev->dev, "addr 0x%lx\n", info->io.addr_data);
+
+	dev_set_drvdata(&dev->dev, info);
+
+	if (add_smi(info)) {
+		kfree(info);
+		return -EBUSY;
+	}
+
+	return 0;
+}
+
+static int ipmi_parisc_remove(struct parisc_device *dev)
+{
+	cleanup_one_si(dev_get_drvdata(&dev->dev));
+	return 0;
+}
+
+static struct parisc_device_id ipmi_parisc_tbl[] = {
+	{ HPHW_MC, HVERSION_REV_ANY_ID, 0x004, 0xC0 },
+	{ 0, }
+};
+
+static struct parisc_driver ipmi_parisc_driver = {
+	.name =		"ipmi",
+	.id_table =	ipmi_parisc_tbl,
+	.probe =	ipmi_parisc_probe,
+	.remove =	ipmi_parisc_remove,
+};
+#endif /* CONFIG_PARISC */
+
 static int wait_for_msg_done(struct smi_info *smi_info)
 {
 	enum si_sm_result     smi_result;
@@ -3462,6 +3528,13 @@ static int init_ipmi_si(void)
 		spmi_find_bmc();
 #endif
 
+#ifdef CONFIG_PARISC
+	register_parisc_driver(&ipmi_parisc_driver);
+	parisc_registered = 1;
+	/* poking PC IO addresses will crash machine, don't do it */
+	si_trydefaults = 0;
+#endif
+
 	/* We prefer devices with interrupts, but in the case of a machine
 	   with multiple BMCs we assume that there will be several instances
 	   of a given type so if we succeed in registering a type then also
@@ -3608,6 +3681,10 @@ static void cleanup_ipmi_si(void)
 	if (pnp_registered)
 		pnp_unregister_driver(&ipmi_pnp_driver);
 #endif
+#ifdef CONFIG_PARISC
+	if (parisc_registered)
+		unregister_parisc_driver(&ipmi_parisc_driver);
+#endif
 
 	platform_driver_unregister(&ipmi_driver);
 
diff --git a/drivers/char/pcmcia/synclink_cs.c b/drivers/char/pcmcia/synclink_cs.c
index 5c5cc00ebb07..d39cca659a3f 100644
--- a/drivers/char/pcmcia/synclink_cs.c
+++ b/drivers/char/pcmcia/synclink_cs.c
@@ -1182,14 +1182,14 @@ static irqreturn_t mgslpc_isr(int dummy, void *dev_id)
 		}
 		count++;
 
-		if (gis & (BIT1 + BIT0)) {
+		if (gis & (BIT1 | BIT0)) {
 			isr = read_reg16(info, CHB + ISR);
 			if (isr & IRQ_DCD)
 				dcd_change(info, tty);
 			if (isr & IRQ_CTS)
 				cts_change(info, tty);
 		}
-		if (gis & (BIT3 + BIT2))
+		if (gis & (BIT3 | BIT2))
 		{
 			isr = read_reg16(info, CHA + ISR);
 			if (isr & IRQ_TIMER) {
@@ -1210,7 +1210,7 @@ static irqreturn_t mgslpc_isr(int dummy, void *dev_id)
 			if (isr & IRQ_RXTIME) {
 				issue_command(info, CHA, CMD_RXFIFO_READ);
 			}
-			if (isr & (IRQ_RXEOM + IRQ_RXFIFO)) {
+			if (isr & (IRQ_RXEOM | IRQ_RXFIFO)) {
 				if (info->params.mode == MGSL_MODE_HDLC)
 					rx_ready_hdlc(info, isr & IRQ_RXEOM);
 				else
@@ -3031,11 +3031,11 @@ static void loopback_enable(MGSLPC_INFO *info)
 	unsigned char val;
 
 	/* CCR1:02..00  CM[2..0] Clock Mode = 111 (clock mode 7) */
-	val = read_reg(info, CHA + CCR1) | (BIT2 + BIT1 + BIT0);
+	val = read_reg(info, CHA + CCR1) | (BIT2 | BIT1 | BIT0);
 	write_reg(info, CHA + CCR1, val);
 
 	/* CCR2:04 SSEL Clock source select, 1=submode b */
-	val = read_reg(info, CHA + CCR2) | (BIT4 + BIT5);
+	val = read_reg(info, CHA + CCR2) | (BIT4 | BIT5);
 	write_reg(info, CHA + CCR2, val);
 
 	/* set LinkSpeed if available, otherwise default to 2Mbps */
@@ -3125,10 +3125,10 @@ static void hdlc_mode(MGSLPC_INFO *info)
 		val |= BIT4;
 		break;		// FM0
 	case HDLC_ENCODING_BIPHASE_MARK:
-		val |= BIT4 + BIT2;
+		val |= BIT4 | BIT2;
 		break;		// FM1
 	case HDLC_ENCODING_BIPHASE_LEVEL:
-		val |= BIT4 + BIT3;
+		val |= BIT4 | BIT3;
 		break;		// Manchester
 	}
 	write_reg(info, CHA + CCR0, val);
@@ -3185,7 +3185,7 @@ static void hdlc_mode(MGSLPC_INFO *info)
 	 */
 	val = 0x00;
 	if (info->params.crc_type == HDLC_CRC_NONE)
-		val |= BIT2 + BIT1;
+		val |= BIT2 | BIT1;
 	if (info->params.preamble != HDLC_PREAMBLE_PATTERN_NONE)
 		val |= BIT5;
 	switch (info->params.preamble_length)
@@ -3197,7 +3197,7 @@ static void hdlc_mode(MGSLPC_INFO *info)
 		val |= BIT6;
 		break;
 	case HDLC_PREAMBLE_LENGTH_64BITS:
-		val |= BIT7 + BIT6;
+		val |= BIT7 | BIT6;
 		break;
 	}
 	write_reg(info, CHA + CCR3, val);
@@ -3264,8 +3264,8 @@ static void hdlc_mode(MGSLPC_INFO *info)
 		clear_reg_bits(info, CHA + PVR, BIT3);
 
 	irq_enable(info, CHA,
-			 IRQ_RXEOM + IRQ_RXFIFO + IRQ_ALLSENT +
-			 IRQ_UNDERRUN + IRQ_TXFIFO);
+			 IRQ_RXEOM | IRQ_RXFIFO | IRQ_ALLSENT |
+			 IRQ_UNDERRUN | IRQ_TXFIFO);
 	issue_command(info, CHA, CMD_TXRESET + CMD_RXRESET);
 	wait_command_complete(info, CHA);
 	read_reg16(info, CHA + ISR);	/* clear pending IRQs */
@@ -3582,8 +3582,8 @@ static void async_mode(MGSLPC_INFO *info)
 	} else
 		clear_reg_bits(info, CHA + PVR, BIT3);
 	irq_enable(info, CHA,
-			  IRQ_RXEOM + IRQ_RXFIFO + IRQ_BREAK_ON + IRQ_RXTIME +
-			  IRQ_ALLSENT + IRQ_TXFIFO);
+			  IRQ_RXEOM | IRQ_RXFIFO | IRQ_BREAK_ON | IRQ_RXTIME |
+			  IRQ_ALLSENT | IRQ_TXFIFO);
 	issue_command(info, CHA, CMD_TXRESET + CMD_RXRESET);
 	wait_command_complete(info, CHA);
 	read_reg16(info, CHA + ISR);	/* clear pending IRQs */
diff --git a/drivers/char/random.c b/drivers/char/random.c
index 0d91fe52f3f5..7a744d391756 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -255,10 +255,7 @@
 #include <linux/fips.h>
 #include <linux/ptrace.h>
 #include <linux/kmemcheck.h>
-
-#ifdef CONFIG_GENERIC_HARDIRQS
-# include <linux/irq.h>
-#endif
+#include <linux/irq.h>
 
 #include <asm/processor.h>
 #include <asm/uaccess.h>
@@ -643,7 +640,7 @@ struct timer_rand_state {
  */
 void add_device_randomness(const void *buf, unsigned int size)
 {
-	unsigned long time = get_cycles() ^ jiffies;
+	unsigned long time = random_get_entropy() ^ jiffies;
 
 	mix_pool_bytes(&input_pool, buf, size, NULL);
 	mix_pool_bytes(&input_pool, &time, sizeof(time), NULL);
@@ -680,7 +677,7 @@ static void add_timer_randomness(struct timer_rand_state *state, unsigned num)
 		goto out;
 
 	sample.jiffies = jiffies;
-	sample.cycles = get_cycles();
+	sample.cycles = random_get_entropy();
 	sample.num = num;
 	mix_pool_bytes(&input_pool, &sample, sizeof(sample), NULL);
 
@@ -747,7 +744,7 @@ void add_interrupt_randomness(int irq, int irq_flags)
 	struct fast_pool	*fast_pool = &__get_cpu_var(irq_randomness);
 	struct pt_regs		*regs = get_irq_regs();
 	unsigned long		now = jiffies;
-	__u32			input[4], cycles = get_cycles();
+	__u32			input[4], cycles = random_get_entropy();
 
 	input[0] = cycles ^ jiffies;
 	input[1] = irq;
@@ -1462,12 +1459,11 @@ struct ctl_table random_table[] = {
 
 static u32 random_int_secret[MD5_MESSAGE_BYTES / 4] ____cacheline_aligned;
 
-static int __init random_int_secret_init(void)
+int random_int_secret_init(void)
 {
 	get_random_bytes(random_int_secret, sizeof(random_int_secret));
 	return 0;
 }
-late_initcall(random_int_secret_init);
 
 /*
  * Get a random word for internal kernel use only. Similar to urandom but
@@ -1486,7 +1482,7 @@ unsigned int get_random_int(void)
 
 	hash = get_cpu_var(get_random_int_hash);
 
-	hash[0] += current->pid + jiffies + get_cycles();
+	hash[0] += current->pid + jiffies + random_get_entropy();
 	md5_transform(hash, random_int_secret);
 	ret = hash[0];
 	put_cpu_var(get_random_int_hash);
diff --git a/drivers/char/sonypi.c b/drivers/char/sonypi.c
index bf2349dbbf7f..7cc1fe2241fd 100644
--- a/drivers/char/sonypi.c
+++ b/drivers/char/sonypi.c
@@ -876,11 +876,6 @@ found:
 	if (useinput)
 		sonypi_report_input_event(event);
 
-#ifdef CONFIG_ACPI
-	if (sonypi_acpi_device)
-		acpi_bus_generate_proc_event(sonypi_acpi_device, 1, event);
-#endif
-
 	kfifo_in_locked(&sonypi_device.fifo, (unsigned char *)&event,
 			sizeof(event), &sonypi_device.fifo_lock);
 	kill_fasync(&sonypi_device.fifo_async, SIGIO, POLL_IN);
diff --git a/drivers/char/tile-srom.c b/drivers/char/tile-srom.c
index 7faeb1cde97d..0e506bad1986 100644
--- a/drivers/char/tile-srom.c
+++ b/drivers/char/tile-srom.c
@@ -279,33 +279,37 @@ loff_t srom_llseek(struct file *file, loff_t offset, int origin)
 	return fixed_size_llseek(file, offset, origin, srom->total_size);
 }
 
-static ssize_t total_show(struct device *dev,
-			  struct device_attribute *attr, char *buf)
+static ssize_t total_size_show(struct device *dev,
+			       struct device_attribute *attr, char *buf)
 {
 	struct srom_dev *srom = dev_get_drvdata(dev);
 	return sprintf(buf, "%u\n", srom->total_size);
 }
+static DEVICE_ATTR_RO(total_size);
 
-static ssize_t sector_show(struct device *dev,
-			   struct device_attribute *attr, char *buf)
+static ssize_t sector_size_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
 {
 	struct srom_dev *srom = dev_get_drvdata(dev);
 	return sprintf(buf, "%u\n", srom->sector_size);
 }
+static DEVICE_ATTR_RO(sector_size);
 
-static ssize_t page_show(struct device *dev,
-			 struct device_attribute *attr, char *buf)
+static ssize_t page_size_show(struct device *dev,
+			      struct device_attribute *attr, char *buf)
 {
 	struct srom_dev *srom = dev_get_drvdata(dev);
 	return sprintf(buf, "%u\n", srom->page_size);
 }
+static DEVICE_ATTR_RO(page_size);
 
-static struct device_attribute srom_dev_attrs[] = {
-	__ATTR(total_size, S_IRUGO, total_show, NULL),
-	__ATTR(sector_size, S_IRUGO, sector_show, NULL),
-	__ATTR(page_size, S_IRUGO, page_show, NULL),
-	__ATTR_NULL
+static struct attribute *srom_dev_attrs[] = {
+	&dev_attr_total_size.attr,
+	&dev_attr_sector_size.attr,
+	&dev_attr_page_size.attr,
+	NULL,
 };
+ATTRIBUTE_GROUPS(srom_dev);
 
 static char *srom_devnode(struct device *dev, umode_t *mode)
 {
@@ -349,7 +353,7 @@ static int srom_setup_minor(struct srom_dev *srom, int index)
 
 	dev = device_create(srom_class, &platform_bus,
 			    MKDEV(srom_major, index), srom, "%d", index);
-	return PTR_RET(dev);
+	return PTR_ERR_OR_ZERO(dev);
 }
 
 /** srom_init() - Initialize the driver's module. */
@@ -418,7 +422,7 @@ static int srom_init(void)
 		result = PTR_ERR(srom_class);
 		goto fail_cdev;
 	}
-	srom_class->dev_attrs = srom_dev_attrs;
+	srom_class->dev_groups = srom_dev_groups;
 	srom_class->devnode = srom_devnode;
 
 	/* Do per-partition initialization */
diff --git a/drivers/char/tpm/Kconfig b/drivers/char/tpm/Kconfig
index dbfd56446c31..94c0c74434ea 100644
--- a/drivers/char/tpm/Kconfig
+++ b/drivers/char/tpm/Kconfig
@@ -91,4 +91,16 @@ config TCG_ST33_I2C
         To compile this driver as a module, choose M here; the module will be
         called tpm_stm_st33_i2c.
 
+config TCG_XEN
+	tristate "XEN TPM Interface"
+	depends on TCG_TPM && XEN
+	select XEN_XENBUS_FRONTEND
+	---help---
+	  If you want to make TPM support available to a Xen user domain,
+	  say Yes and it will be accessible from within Linux. See
+	  the manpages for xl, xl.conf, and docs/misc/vtpm.txt in
+	  the Xen source repository for more details.
+	  To compile this driver as a module, choose M here; the module
+	  will be called xen-tpmfront.
+
 endif # TCG_TPM
diff --git a/drivers/char/tpm/Makefile b/drivers/char/tpm/Makefile
index a3736c97c65a..eb41ff97d0ad 100644
--- a/drivers/char/tpm/Makefile
+++ b/drivers/char/tpm/Makefile
@@ -18,3 +18,4 @@ obj-$(CONFIG_TCG_ATMEL) += tpm_atmel.o
 obj-$(CONFIG_TCG_INFINEON) += tpm_infineon.o
 obj-$(CONFIG_TCG_IBMVTPM) += tpm_ibmvtpm.o
 obj-$(CONFIG_TCG_ST33_I2C) += tpm_i2c_stm_st33.o
+obj-$(CONFIG_TCG_XEN) += xen-tpmfront.o
diff --git a/drivers/char/tpm/tpm_tis.c b/drivers/char/tpm/tpm_tis.c
index 4519cb332987..5796d0157ce0 100644
--- a/drivers/char/tpm/tpm_tis.c
+++ b/drivers/char/tpm/tpm_tis.c
@@ -766,6 +766,25 @@ static void tpm_tis_reenable_interrupts(struct tpm_chip *chip)
 }
 #endif
 
+#ifdef CONFIG_PM_SLEEP
+static int tpm_tis_resume(struct device *dev)
+{
+	struct tpm_chip *chip = dev_get_drvdata(dev);
+	int ret;
+
+	if (chip->vendor.irq)
+		tpm_tis_reenable_interrupts(chip);
+
+	ret = tpm_pm_resume(dev);
+	if (!ret)
+		tpm_do_selftest(chip);
+
+	return ret;
+}
+#endif
+
+static SIMPLE_DEV_PM_OPS(tpm_tis_pm, tpm_pm_suspend, tpm_tis_resume);
+
 #ifdef CONFIG_PNP
 static int tpm_tis_pnp_init(struct pnp_dev *pnp_dev,
 				      const struct pnp_device_id *pnp_id)
@@ -787,26 +806,6 @@ static int tpm_tis_pnp_init(struct pnp_dev *pnp_dev,
 	return tpm_tis_init(&pnp_dev->dev, start, len, irq);
 }
 
-static int tpm_tis_pnp_suspend(struct pnp_dev *dev, pm_message_t msg)
-{
-	return tpm_pm_suspend(&dev->dev);
-}
-
-static int tpm_tis_pnp_resume(struct pnp_dev *dev)
-{
-	struct tpm_chip *chip = pnp_get_drvdata(dev);
-	int ret;
-
-	if (chip->vendor.irq)
-		tpm_tis_reenable_interrupts(chip);
-
-	ret = tpm_pm_resume(&dev->dev);
-	if (!ret)
-		tpm_do_selftest(chip);
-
-	return ret;
-}
-
 static struct pnp_device_id tpm_pnp_tbl[] = {
 	{"PNP0C31", 0},		/* TPM */
 	{"ATM1200", 0},		/* Atmel */
@@ -835,9 +834,12 @@ static struct pnp_driver tis_pnp_driver = {
 	.name = "tpm_tis",
 	.id_table = tpm_pnp_tbl,
 	.probe = tpm_tis_pnp_init,
-	.suspend = tpm_tis_pnp_suspend,
-	.resume = tpm_tis_pnp_resume,
 	.remove = tpm_tis_pnp_remove,
+#ifdef CONFIG_PM_SLEEP
+	.driver	= {
+		.pm = &tpm_tis_pm,
+	},
+#endif
 };
 
 #define TIS_HID_USR_IDX sizeof(tpm_pnp_tbl)/sizeof(struct pnp_device_id) -2
@@ -846,20 +848,6 @@ module_param_string(hid, tpm_pnp_tbl[TIS_HID_USR_IDX].id,
 MODULE_PARM_DESC(hid, "Set additional specific HID for this driver to probe");
 #endif
 
-#ifdef CONFIG_PM_SLEEP
-static int tpm_tis_resume(struct device *dev)
-{
-	struct tpm_chip *chip = dev_get_drvdata(dev);
-
-	if (chip->vendor.irq)
-		tpm_tis_reenable_interrupts(chip);
-
-	return tpm_pm_resume(dev);
-}
-#endif
-
-static SIMPLE_DEV_PM_OPS(tpm_tis_pm, tpm_pm_suspend, tpm_tis_resume);
-
 static struct platform_driver tis_drv = {
 	.driver = {
 		.name = "tpm_tis",
diff --git a/drivers/char/tpm/xen-tpmfront.c b/drivers/char/tpm/xen-tpmfront.c
new file mode 100644
index 000000000000..94c280d36e8b
--- /dev/null
+++ b/drivers/char/tpm/xen-tpmfront.c
@@ -0,0 +1,438 @@
+/*
+ * Implementation of the Xen vTPM device frontend
+ *
+ * Author:  Daniel De Graaf <dgdegra@tycho.nsa.gov>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2,
+ * as published by the Free Software Foundation.
+ */
+#include <linux/errno.h>
+#include <linux/err.h>
+#include <linux/interrupt.h>
+#include <xen/xen.h>
+#include <xen/events.h>
+#include <xen/interface/io/tpmif.h>
+#include <xen/grant_table.h>
+#include <xen/xenbus.h>
+#include <xen/page.h>
+#include "tpm.h"
+
+struct tpm_private {
+	struct tpm_chip *chip;
+	struct xenbus_device *dev;
+
+	struct vtpm_shared_page *shr;
+
+	unsigned int evtchn;
+	int ring_ref;
+	domid_t backend_id;
+};
+
+enum status_bits {
+	VTPM_STATUS_RUNNING  = 0x1,
+	VTPM_STATUS_IDLE     = 0x2,
+	VTPM_STATUS_RESULT   = 0x4,
+	VTPM_STATUS_CANCELED = 0x8,
+};
+
+static u8 vtpm_status(struct tpm_chip *chip)
+{
+	struct tpm_private *priv = TPM_VPRIV(chip);
+	switch (priv->shr->state) {
+	case VTPM_STATE_IDLE:
+		return VTPM_STATUS_IDLE | VTPM_STATUS_CANCELED;
+	case VTPM_STATE_FINISH:
+		return VTPM_STATUS_IDLE | VTPM_STATUS_RESULT;
+	case VTPM_STATE_SUBMIT:
+	case VTPM_STATE_CANCEL: /* cancel requested, not yet canceled */
+		return VTPM_STATUS_RUNNING;
+	default:
+		return 0;
+	}
+}
+
+static bool vtpm_req_canceled(struct tpm_chip *chip, u8 status)
+{
+	return status & VTPM_STATUS_CANCELED;
+}
+
+static void vtpm_cancel(struct tpm_chip *chip)
+{
+	struct tpm_private *priv = TPM_VPRIV(chip);
+	priv->shr->state = VTPM_STATE_CANCEL;
+	wmb();
+	notify_remote_via_evtchn(priv->evtchn);
+}
+
+static unsigned int shr_data_offset(struct vtpm_shared_page *shr)
+{
+	return sizeof(*shr) + sizeof(u32) * shr->nr_extra_pages;
+}
+
+static int vtpm_send(struct tpm_chip *chip, u8 *buf, size_t count)
+{
+	struct tpm_private *priv = TPM_VPRIV(chip);
+	struct vtpm_shared_page *shr = priv->shr;
+	unsigned int offset = shr_data_offset(shr);
+
+	u32 ordinal;
+	unsigned long duration;
+
+	if (offset > PAGE_SIZE)
+		return -EINVAL;
+
+	if (offset + count > PAGE_SIZE)
+		return -EINVAL;
+
+	/* Wait for completion of any existing command or cancellation */
+	if (wait_for_tpm_stat(chip, VTPM_STATUS_IDLE, chip->vendor.timeout_c,
+			&chip->vendor.read_queue, true) < 0) {
+		vtpm_cancel(chip);
+		return -ETIME;
+	}
+
+	memcpy(offset + (u8 *)shr, buf, count);
+	shr->length = count;
+	barrier();
+	shr->state = VTPM_STATE_SUBMIT;
+	wmb();
+	notify_remote_via_evtchn(priv->evtchn);
+
+	ordinal = be32_to_cpu(((struct tpm_input_header*)buf)->ordinal);
+	duration = tpm_calc_ordinal_duration(chip, ordinal);
+
+	if (wait_for_tpm_stat(chip, VTPM_STATUS_IDLE, duration,
+			&chip->vendor.read_queue, true) < 0) {
+		/* got a signal or timeout, try to cancel */
+		vtpm_cancel(chip);
+		return -ETIME;
+	}
+
+	return count;
+}
+
+static int vtpm_recv(struct tpm_chip *chip, u8 *buf, size_t count)
+{
+	struct tpm_private *priv = TPM_VPRIV(chip);
+	struct vtpm_shared_page *shr = priv->shr;
+	unsigned int offset = shr_data_offset(shr);
+	size_t length = shr->length;
+
+	if (shr->state == VTPM_STATE_IDLE)
+		return -ECANCELED;
+
+	/* In theory the wait at the end of _send makes this one unnecessary */
+	if (wait_for_tpm_stat(chip, VTPM_STATUS_RESULT, chip->vendor.timeout_c,
+			&chip->vendor.read_queue, true) < 0) {
+		vtpm_cancel(chip);
+		return -ETIME;
+	}
+
+	if (offset > PAGE_SIZE)
+		return -EIO;
+
+	if (offset + length > PAGE_SIZE)
+		length = PAGE_SIZE - offset;
+
+	if (length > count)
+		length = count;
+
+	memcpy(buf, offset + (u8 *)shr, length);
+
+	return length;
+}
+
+static const struct file_operations vtpm_ops = {
+	.owner = THIS_MODULE,
+	.llseek = no_llseek,
+	.open = tpm_open,
+	.read = tpm_read,
+	.write = tpm_write,
+	.release = tpm_release,
+};
+
+static DEVICE_ATTR(pubek, S_IRUGO, tpm_show_pubek, NULL);
+static DEVICE_ATTR(pcrs, S_IRUGO, tpm_show_pcrs, NULL);
+static DEVICE_ATTR(enabled, S_IRUGO, tpm_show_enabled, NULL);
+static DEVICE_ATTR(active, S_IRUGO, tpm_show_active, NULL);
+static DEVICE_ATTR(owned, S_IRUGO, tpm_show_owned, NULL);
+static DEVICE_ATTR(temp_deactivated, S_IRUGO, tpm_show_temp_deactivated,
+		NULL);
+static DEVICE_ATTR(caps, S_IRUGO, tpm_show_caps, NULL);
+static DEVICE_ATTR(cancel, S_IWUSR | S_IWGRP, NULL, tpm_store_cancel);
+static DEVICE_ATTR(durations, S_IRUGO, tpm_show_durations, NULL);
+static DEVICE_ATTR(timeouts, S_IRUGO, tpm_show_timeouts, NULL);
+
+static struct attribute *vtpm_attrs[] = {
+	&dev_attr_pubek.attr,
+	&dev_attr_pcrs.attr,
+	&dev_attr_enabled.attr,
+	&dev_attr_active.attr,
+	&dev_attr_owned.attr,
+	&dev_attr_temp_deactivated.attr,
+	&dev_attr_caps.attr,
+	&dev_attr_cancel.attr,
+	&dev_attr_durations.attr,
+	&dev_attr_timeouts.attr,
+	NULL,
+};
+
+static struct attribute_group vtpm_attr_grp = {
+	.attrs = vtpm_attrs,
+};
+
+static const struct tpm_vendor_specific tpm_vtpm = {
+	.status = vtpm_status,
+	.recv = vtpm_recv,
+	.send = vtpm_send,
+	.cancel = vtpm_cancel,
+	.req_complete_mask = VTPM_STATUS_IDLE | VTPM_STATUS_RESULT,
+	.req_complete_val  = VTPM_STATUS_IDLE | VTPM_STATUS_RESULT,
+	.req_canceled      = vtpm_req_canceled,
+	.attr_group = &vtpm_attr_grp,
+	.miscdev = {
+		.fops = &vtpm_ops,
+	},
+};
+
+static irqreturn_t tpmif_interrupt(int dummy, void *dev_id)
+{
+	struct tpm_private *priv = dev_id;
+
+	switch (priv->shr->state) {
+	case VTPM_STATE_IDLE:
+	case VTPM_STATE_FINISH:
+		wake_up_interruptible(&priv->chip->vendor.read_queue);
+		break;
+	case VTPM_STATE_SUBMIT:
+	case VTPM_STATE_CANCEL:
+	default:
+		break;
+	}
+	return IRQ_HANDLED;
+}
+
+static int setup_chip(struct device *dev, struct tpm_private *priv)
+{
+	struct tpm_chip *chip;
+
+	chip = tpm_register_hardware(dev, &tpm_vtpm);
+	if (!chip)
+		return -ENODEV;
+
+	init_waitqueue_head(&chip->vendor.read_queue);
+
+	priv->chip = chip;
+	TPM_VPRIV(chip) = priv;
+
+	return 0;
+}
+
+/* caller must clean up in case of errors */
+static int setup_ring(struct xenbus_device *dev, struct tpm_private *priv)
+{
+	struct xenbus_transaction xbt;
+	const char *message = NULL;
+	int rv;
+
+	priv->shr = (void *)__get_free_page(GFP_KERNEL|__GFP_ZERO);
+	if (!priv->shr) {
+		xenbus_dev_fatal(dev, -ENOMEM, "allocating shared ring");
+		return -ENOMEM;
+	}
+
+	rv = xenbus_grant_ring(dev, virt_to_mfn(priv->shr));
+	if (rv < 0)
+		return rv;
+
+	priv->ring_ref = rv;
+
+	rv = xenbus_alloc_evtchn(dev, &priv->evtchn);
+	if (rv)
+		return rv;
+
+	rv = bind_evtchn_to_irqhandler(priv->evtchn, tpmif_interrupt, 0,
+				       "tpmif", priv);
+	if (rv <= 0) {
+		xenbus_dev_fatal(dev, rv, "allocating TPM irq");
+		return rv;
+	}
+	priv->chip->vendor.irq = rv;
+
+ again:
+	rv = xenbus_transaction_start(&xbt);
+	if (rv) {
+		xenbus_dev_fatal(dev, rv, "starting transaction");
+		return rv;
+	}
+
+	rv = xenbus_printf(xbt, dev->nodename,
+			"ring-ref", "%u", priv->ring_ref);
+	if (rv) {
+		message = "writing ring-ref";
+		goto abort_transaction;
+	}
+
+	rv = xenbus_printf(xbt, dev->nodename, "event-channel", "%u",
+			priv->evtchn);
+	if (rv) {
+		message = "writing event-channel";
+		goto abort_transaction;
+	}
+
+	rv = xenbus_printf(xbt, dev->nodename, "feature-protocol-v2", "1");
+	if (rv) {
+		message = "writing feature-protocol-v2";
+		goto abort_transaction;
+	}
+
+	rv = xenbus_transaction_end(xbt, 0);
+	if (rv == -EAGAIN)
+		goto again;
+	if (rv) {
+		xenbus_dev_fatal(dev, rv, "completing transaction");
+		return rv;
+	}
+
+	xenbus_switch_state(dev, XenbusStateInitialised);
+
+	return 0;
+
+ abort_transaction:
+	xenbus_transaction_end(xbt, 1);
+	if (message)
+		xenbus_dev_error(dev, rv, "%s", message);
+
+	return rv;
+}
+
+static void ring_free(struct tpm_private *priv)
+{
+	if (!priv)
+		return;
+
+	if (priv->ring_ref)
+		gnttab_end_foreign_access(priv->ring_ref, 0,
+				(unsigned long)priv->shr);
+	else
+		free_page((unsigned long)priv->shr);
+
+	if (priv->chip && priv->chip->vendor.irq)
+		unbind_from_irqhandler(priv->chip->vendor.irq, priv);
+
+	kfree(priv);
+}
+
+static int tpmfront_probe(struct xenbus_device *dev,
+		const struct xenbus_device_id *id)
+{
+	struct tpm_private *priv;
+	int rv;
+
+	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
+	if (!priv) {
+		xenbus_dev_fatal(dev, -ENOMEM, "allocating priv structure");
+		return -ENOMEM;
+	}
+
+	rv = setup_chip(&dev->dev, priv);
+	if (rv) {
+		kfree(priv);
+		return rv;
+	}
+
+	rv = setup_ring(dev, priv);
+	if (rv) {
+		tpm_remove_hardware(&dev->dev);
+		ring_free(priv);
+		return rv;
+	}
+
+	tpm_get_timeouts(priv->chip);
+
+	dev_set_drvdata(&dev->dev, priv->chip);
+
+	return rv;
+}
+
+static int tpmfront_remove(struct xenbus_device *dev)
+{
+	struct tpm_chip *chip = dev_get_drvdata(&dev->dev);
+	struct tpm_private *priv = TPM_VPRIV(chip);
+	tpm_remove_hardware(&dev->dev);
+	ring_free(priv);
+	TPM_VPRIV(chip) = NULL;
+	return 0;
+}
+
+static int tpmfront_resume(struct xenbus_device *dev)
+{
+	/* A suspend/resume/migrate will interrupt a vTPM anyway */
+	tpmfront_remove(dev);
+	return tpmfront_probe(dev, NULL);
+}
+
+static void backend_changed(struct xenbus_device *dev,
+		enum xenbus_state backend_state)
+{
+	int val;
+
+	switch (backend_state) {
+	case XenbusStateInitialised:
+	case XenbusStateConnected:
+		if (dev->state == XenbusStateConnected)
+			break;
+
+		if (xenbus_scanf(XBT_NIL, dev->otherend,
+				"feature-protocol-v2", "%d", &val) < 0)
+			val = 0;
+		if (!val) {
+			xenbus_dev_fatal(dev, -EINVAL,
+					"vTPM protocol 2 required");
+			return;
+		}
+		xenbus_switch_state(dev, XenbusStateConnected);
+		break;
+
+	case XenbusStateClosing:
+	case XenbusStateClosed:
+		device_unregister(&dev->dev);
+		xenbus_frontend_closed(dev);
+		break;
+	default:
+		break;
+	}
+}
+
+static const struct xenbus_device_id tpmfront_ids[] = {
+	{ "vtpm" },
+	{ "" }
+};
+MODULE_ALIAS("xen:vtpm");
+
+static DEFINE_XENBUS_DRIVER(tpmfront, ,
+		.probe = tpmfront_probe,
+		.remove = tpmfront_remove,
+		.resume = tpmfront_resume,
+		.otherend_changed = backend_changed,
+	);
+
+static int __init xen_tpmfront_init(void)
+{
+	if (!xen_domain())
+		return -ENODEV;
+
+	return xenbus_register_frontend(&tpmfront_driver);
+}
+module_init(xen_tpmfront_init);
+
+static void __exit xen_tpmfront_exit(void)
+{
+	xenbus_unregister_driver(&tpmfront_driver);
+}
+module_exit(xen_tpmfront_exit);
+
+MODULE_AUTHOR("Daniel De Graaf <dgdegra@tycho.nsa.gov>");
+MODULE_DESCRIPTION("Xen vTPM Driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c
index fc45567ad3ac..b79cf3e1b793 100644
--- a/drivers/char/virtio_console.c
+++ b/drivers/char/virtio_console.c
@@ -1529,18 +1529,22 @@ static void remove_port_data(struct port *port)
 {
 	struct port_buffer *buf;
 
+	spin_lock_irq(&port->inbuf_lock);
 	/* Remove unused data this port might have received. */
 	discard_port_data(port);
 
-	reclaim_consumed_buffers(port);
-
 	/* Remove buffers we queued up for the Host to send us data in. */
 	while ((buf = virtqueue_detach_unused_buf(port->in_vq)))
 		free_buf(buf, true);
+	spin_unlock_irq(&port->inbuf_lock);
+
+	spin_lock_irq(&port->outvq_lock);
+	reclaim_consumed_buffers(port);
 
 	/* Free pending buffers from the out-queue. */
 	while ((buf = virtqueue_detach_unused_buf(port->out_vq)))
 		free_buf(buf, true);
+	spin_unlock_irq(&port->outvq_lock);
 }
 
 /*
@@ -1554,6 +1558,7 @@ static void unplug_port(struct port *port)
 	list_del(&port->list);
 	spin_unlock_irq(&port->portdev->ports_lock);
 
+	spin_lock_irq(&port->inbuf_lock);
 	if (port->guest_connected) {
 		/* Let the app know the port is going down. */
 		send_sigio_to_port(port);
@@ -1564,6 +1569,7 @@ static void unplug_port(struct port *port)
 
 		wake_up_interruptible(&port->waitqueue);
 	}
+	spin_unlock_irq(&port->inbuf_lock);
 
 	if (is_console_port(port)) {
 		spin_lock_irq(&pdrvdata_lock);
@@ -1585,9 +1591,8 @@ static void unplug_port(struct port *port)
 	device_destroy(pdrvdata.class, port->dev->devt);
 	cdev_del(port->cdev);
 
-	kfree(port->name);
-
 	debugfs_remove(port->debugfs_file);
+	kfree(port->name);
 
 	/*
 	 * Locks around here are not necessary - a port can't be
@@ -1681,7 +1686,9 @@ static void handle_control_message(struct ports_device *portdev,
 		 * If the guest is connected, it'll be interested in
 		 * knowing the host connection state changed.
 		 */
+		spin_lock_irq(&port->inbuf_lock);
 		send_sigio_to_port(port);
+		spin_unlock_irq(&port->inbuf_lock);
 		break;
 	case VIRTIO_CONSOLE_PORT_NAME:
 		/*
@@ -1801,13 +1808,13 @@ static void in_intr(struct virtqueue *vq)
 	if (!port->guest_connected && !is_rproc_serial(port->portdev->vdev))
 		discard_port_data(port);
 
+	/* Send a SIGIO indicating new data in case the process asked for it */
+	send_sigio_to_port(port);
+
 	spin_unlock_irqrestore(&port->inbuf_lock, flags);
 
 	wake_up_interruptible(&port->waitqueue);
 
-	/* Send a SIGIO indicating new data in case the process asked for it */
-	send_sigio_to_port(port);
-
 	if (is_console_port(port) && hvc_poll(port->cons.hvc))
 		hvc_kick();
 }
@@ -2241,10 +2248,8 @@ static int __init init(void)
 	}
 
 	pdrvdata.debugfs_dir = debugfs_create_dir("virtio-ports", NULL);
-	if (!pdrvdata.debugfs_dir) {
-		pr_warning("Error %ld creating debugfs dir for virtio-ports\n",
-			   PTR_ERR(pdrvdata.debugfs_dir));
-	}
+	if (!pdrvdata.debugfs_dir)
+		pr_warning("Error creating debugfs dir for virtio-ports\n");
 	INIT_LIST_HEAD(&pdrvdata.consoles);
 	INIT_LIST_HEAD(&pdrvdata.portdevs);
 
diff --git a/drivers/clk/Kconfig b/drivers/clk/Kconfig
index 51380d655d1a..279407a36391 100644
--- a/drivers/clk/Kconfig
+++ b/drivers/clk/Kconfig
@@ -27,7 +27,7 @@ config COMMON_CLK_DEBUG
 	bool "DebugFS representation of clock tree"
 	select DEBUG_FS
 	---help---
-	  Creates a directory hierchy in debugfs for visualizing the clk
+	  Creates a directory hierarchy in debugfs for visualizing the clk
 	  tree structure.  Each directory contains read-only members
 	  that export information specific to that clk node: clk_rate,
 	  clk_flags, clk_prepare_count, clk_enable_count &
@@ -64,6 +64,12 @@ config COMMON_CLK_SI5351
 	  This driver supports Silicon Labs 5351A/B/C programmable clock
 	  generators.
 
+config COMMON_CLK_S2MPS11
+	tristate "Clock driver for S2MPS11 MFD"
+	depends on MFD_SEC_CORE
+	---help---
+	  This driver supports S2MPS11 crystal oscillator clock.
+
 config CLK_TWL6040
 	tristate "External McPDM functional clock from twl6040"
 	depends on TWL6040_CORE
diff --git a/drivers/clk/Makefile b/drivers/clk/Makefile
index 4038c2bdf334..7b111062ccba 100644
--- a/drivers/clk/Makefile
+++ b/drivers/clk/Makefile
@@ -40,5 +40,6 @@ obj-$(CONFIG_COMMON_CLK_AXI_CLKGEN) += clk-axi-clkgen.o
 obj-$(CONFIG_COMMON_CLK_WM831X) += clk-wm831x.o
 obj-$(CONFIG_COMMON_CLK_MAX77686) += clk-max77686.o
 obj-$(CONFIG_COMMON_CLK_SI5351) += clk-si5351.o
+obj-$(CONFIG_COMMON_CLK_S2MPS11) += clk-s2mps11.o
 obj-$(CONFIG_CLK_TWL6040)	+= clk-twl6040.o
 obj-$(CONFIG_CLK_PPC_CORENET)	+= clk-ppc-corenet.o
diff --git a/drivers/clk/clk-bcm2835.c b/drivers/clk/clk-bcm2835.c
index 792bc57a9db7..5fb4ff53d088 100644
--- a/drivers/clk/clk-bcm2835.c
+++ b/drivers/clk/clk-bcm2835.c
@@ -23,7 +23,7 @@
 #include <linux/clk-provider.h>
 #include <linux/of.h>
 
-static const __initconst struct of_device_id clk_match[] = {
+static const struct of_device_id clk_match[] __initconst = {
 	{ .compatible = "fixed-clock", .data = of_fixed_clk_setup, },
 	{ }
 };
diff --git a/drivers/clk/clk-divider.c b/drivers/clk/clk-divider.c
index 6d55eb2cb959..8d3009e44fba 100644
--- a/drivers/clk/clk-divider.c
+++ b/drivers/clk/clk-divider.c
@@ -104,7 +104,7 @@ static unsigned long clk_divider_recalc_rate(struct clk_hw *hw,
 	struct clk_divider *divider = to_clk_divider(hw);
 	unsigned int div, val;
 
-	val = readl(divider->reg) >> divider->shift;
+	val = clk_readl(divider->reg) >> divider->shift;
 	val &= div_mask(divider);
 
 	div = _get_div(divider, val);
@@ -230,11 +230,11 @@ static int clk_divider_set_rate(struct clk_hw *hw, unsigned long rate,
 	if (divider->flags & CLK_DIVIDER_HIWORD_MASK) {
 		val = div_mask(divider) << (divider->shift + 16);
 	} else {
-		val = readl(divider->reg);
+		val = clk_readl(divider->reg);
 		val &= ~(div_mask(divider) << divider->shift);
 	}
 	val |= value << divider->shift;
-	writel(val, divider->reg);
+	clk_writel(val, divider->reg);
 
 	if (divider->lock)
 		spin_unlock_irqrestore(divider->lock, flags);
@@ -317,6 +317,7 @@ struct clk *clk_register_divider(struct device *dev, const char *name,
 	return _register_divider(dev, name, parent_name, flags, reg, shift,
 			width, clk_divider_flags, NULL, lock);
 }
+EXPORT_SYMBOL_GPL(clk_register_divider);
 
 /**
  * clk_register_divider_table - register a table based divider clock with
@@ -341,3 +342,4 @@ struct clk *clk_register_divider_table(struct device *dev, const char *name,
 	return _register_divider(dev, name, parent_name, flags, reg, shift,
 			width, clk_divider_flags, table, lock);
 }
+EXPORT_SYMBOL_GPL(clk_register_divider_table);
diff --git a/drivers/clk/clk-fixed-factor.c b/drivers/clk/clk-fixed-factor.c
index 9ff7d510faa3..0e1d89b4321b 100644
--- a/drivers/clk/clk-fixed-factor.c
+++ b/drivers/clk/clk-fixed-factor.c
@@ -97,6 +97,8 @@ struct clk *clk_register_fixed_factor(struct device *dev, const char *name,
 
 	return clk;
 }
+EXPORT_SYMBOL_GPL(clk_register_fixed_factor);
+
 #ifdef CONFIG_OF
 /**
  * of_fixed_factor_clk_setup() - Setup function for simple fixed factor clock
diff --git a/drivers/clk/clk-fixed-rate.c b/drivers/clk/clk-fixed-rate.c
index dc58fbd8516f..1ed591ab8b1d 100644
--- a/drivers/clk/clk-fixed-rate.c
+++ b/drivers/clk/clk-fixed-rate.c
@@ -80,6 +80,7 @@ struct clk *clk_register_fixed_rate(struct device *dev, const char *name,
 
 	return clk;
 }
+EXPORT_SYMBOL_GPL(clk_register_fixed_rate);
 
 #ifdef CONFIG_OF
 /**
diff --git a/drivers/clk/clk-gate.c b/drivers/clk/clk-gate.c
index 790306e921c8..4a58c55255bd 100644
--- a/drivers/clk/clk-gate.c
+++ b/drivers/clk/clk-gate.c
@@ -58,7 +58,7 @@ static void clk_gate_endisable(struct clk_hw *hw, int enable)
 		if (set)
 			reg |= BIT(gate->bit_idx);
 	} else {
-		reg = readl(gate->reg);
+		reg = clk_readl(gate->reg);
 
 		if (set)
 			reg |= BIT(gate->bit_idx);
@@ -66,7 +66,7 @@ static void clk_gate_endisable(struct clk_hw *hw, int enable)
 			reg &= ~BIT(gate->bit_idx);
 	}
 
-	writel(reg, gate->reg);
+	clk_writel(reg, gate->reg);
 
 	if (gate->lock)
 		spin_unlock_irqrestore(gate->lock, flags);
@@ -89,7 +89,7 @@ static int clk_gate_is_enabled(struct clk_hw *hw)
 	u32 reg;
 	struct clk_gate *gate = to_clk_gate(hw);
 
-	reg = readl(gate->reg);
+	reg = clk_readl(gate->reg);
 
 	/* if a set bit disables this clk, flip it before masking */
 	if (gate->flags & CLK_GATE_SET_TO_DISABLE)
@@ -161,3 +161,4 @@ struct clk *clk_register_gate(struct device *dev, const char *name,
 
 	return clk;
 }
+EXPORT_SYMBOL_GPL(clk_register_gate);
diff --git a/drivers/clk/clk-mux.c b/drivers/clk/clk-mux.c
index 614444ca40cd..4f96ff3ba728 100644
--- a/drivers/clk/clk-mux.c
+++ b/drivers/clk/clk-mux.c
@@ -42,7 +42,7 @@ static u8 clk_mux_get_parent(struct clk_hw *hw)
 	 * OTOH, pmd_trace_clk_mux_ck uses a separate bit for each clock, so
 	 * val = 0x4 really means "bit 2, index starts at bit 0"
 	 */
-	val = readl(mux->reg) >> mux->shift;
+	val = clk_readl(mux->reg) >> mux->shift;
 	val &= mux->mask;
 
 	if (mux->table) {
@@ -89,11 +89,11 @@ static int clk_mux_set_parent(struct clk_hw *hw, u8 index)
 	if (mux->flags & CLK_MUX_HIWORD_MASK) {
 		val = mux->mask << (mux->shift + 16);
 	} else {
-		val = readl(mux->reg);
+		val = clk_readl(mux->reg);
 		val &= ~(mux->mask << mux->shift);
 	}
 	val |= index << mux->shift;
-	writel(val, mux->reg);
+	clk_writel(val, mux->reg);
 
 	if (mux->lock)
 		spin_unlock_irqrestore(mux->lock, flags);
@@ -104,9 +104,15 @@ static int clk_mux_set_parent(struct clk_hw *hw, u8 index)
 const struct clk_ops clk_mux_ops = {
 	.get_parent = clk_mux_get_parent,
 	.set_parent = clk_mux_set_parent,
+	.determine_rate = __clk_mux_determine_rate,
 };
 EXPORT_SYMBOL_GPL(clk_mux_ops);
 
+const struct clk_ops clk_mux_ro_ops = {
+	.get_parent = clk_mux_get_parent,
+};
+EXPORT_SYMBOL_GPL(clk_mux_ro_ops);
+
 struct clk *clk_register_mux_table(struct device *dev, const char *name,
 		const char **parent_names, u8 num_parents, unsigned long flags,
 		void __iomem *reg, u8 shift, u32 mask,
@@ -133,7 +139,10 @@ struct clk *clk_register_mux_table(struct device *dev, const char *name,
 	}
 
 	init.name = name;
-	init.ops = &clk_mux_ops;
+	if (clk_mux_flags & CLK_MUX_READ_ONLY)
+		init.ops = &clk_mux_ro_ops;
+	else
+		init.ops = &clk_mux_ops;
 	init.flags = flags | CLK_IS_BASIC;
 	init.parent_names = parent_names;
 	init.num_parents = num_parents;
@@ -154,6 +163,7 @@ struct clk *clk_register_mux_table(struct device *dev, const char *name,
 
 	return clk;
 }
+EXPORT_SYMBOL_GPL(clk_register_mux_table);
 
 struct clk *clk_register_mux(struct device *dev, const char *name,
 		const char **parent_names, u8 num_parents, unsigned long flags,
@@ -166,3 +176,4 @@ struct clk *clk_register_mux(struct device *dev, const char *name,
 				      flags, reg, shift, mask, clk_mux_flags,
 				      NULL, lock);
 }
+EXPORT_SYMBOL_GPL(clk_register_mux);
diff --git a/drivers/clk/clk-nomadik.c b/drivers/clk/clk-nomadik.c
index 6d819a37f647..51410c2ac2cb 100644
--- a/drivers/clk/clk-nomadik.c
+++ b/drivers/clk/clk-nomadik.c
@@ -479,12 +479,12 @@ static void __init of_nomadik_src_clk_setup(struct device_node *np)
 		of_clk_add_provider(np, of_clk_src_simple_get, clk);
 }
 
-static const __initconst struct of_device_id nomadik_src_match[] = {
+static const struct of_device_id nomadik_src_match[] __initconst = {
 	{ .compatible = "stericsson,nomadik-src" },
 	{ /* sentinel */ }
 };
 
-static const __initconst struct of_device_id nomadik_src_clk_match[] = {
+static const struct of_device_id nomadik_src_clk_match[] __initconst = {
 	{
 		.compatible = "fixed-clock",
 		.data = of_fixed_clk_setup,
diff --git a/drivers/clk/clk-prima2.c b/drivers/clk/clk-prima2.c
index 643ca653fef0..5ab95f1ad579 100644
--- a/drivers/clk/clk-prima2.c
+++ b/drivers/clk/clk-prima2.c
@@ -1034,7 +1034,7 @@ enum prima2_clk_index {
 	usb0,  usb1,  maxclk,
 };
 
-static __initdata struct clk_hw* prima2_clk_hw_array[maxclk] = {
+static struct clk_hw *prima2_clk_hw_array[maxclk] __initdata = {
 	NULL, /* dummy */
 	NULL,
 	&clk_pll1.hw,
diff --git a/drivers/clk/clk-s2mps11.c b/drivers/clk/clk-s2mps11.c
new file mode 100644
index 000000000000..7be41e676a64
--- /dev/null
+++ b/drivers/clk/clk-s2mps11.c
@@ -0,0 +1,273 @@
+/*
+ * clk-s2mps11.c - Clock driver for S2MPS11.
+ *
+ * Copyright (C) 2013 Samsung Electornics
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/err.h>
+#include <linux/of.h>
+#include <linux/clkdev.h>
+#include <linux/regmap.h>
+#include <linux/clk-provider.h>
+#include <linux/platform_device.h>
+#include <linux/mfd/samsung/s2mps11.h>
+#include <linux/mfd/samsung/core.h>
+
+#define s2mps11_name(a) (a->hw.init->name)
+
+static struct clk **clk_table;
+static struct clk_onecell_data clk_data;
+
+enum {
+	S2MPS11_CLK_AP = 0,
+	S2MPS11_CLK_CP,
+	S2MPS11_CLK_BT,
+	S2MPS11_CLKS_NUM,
+};
+
+struct s2mps11_clk {
+	struct sec_pmic_dev *iodev;
+	struct clk_hw hw;
+	struct clk *clk;
+	struct clk_lookup *lookup;
+	u32 mask;
+	bool enabled;
+};
+
+static struct s2mps11_clk *to_s2mps11_clk(struct clk_hw *hw)
+{
+	return container_of(hw, struct s2mps11_clk, hw);
+}
+
+static int s2mps11_clk_prepare(struct clk_hw *hw)
+{
+	struct s2mps11_clk *s2mps11 = to_s2mps11_clk(hw);
+	int ret;
+
+	ret = regmap_update_bits(s2mps11->iodev->regmap,
+				S2MPS11_REG_RTC_CTRL,
+				 s2mps11->mask, s2mps11->mask);
+	if (!ret)
+		s2mps11->enabled = true;
+
+	return ret;
+}
+
+static void s2mps11_clk_unprepare(struct clk_hw *hw)
+{
+	struct s2mps11_clk *s2mps11 = to_s2mps11_clk(hw);
+	int ret;
+
+	ret = regmap_update_bits(s2mps11->iodev->regmap, S2MPS11_REG_RTC_CTRL,
+			   s2mps11->mask, ~s2mps11->mask);
+
+	if (!ret)
+		s2mps11->enabled = false;
+}
+
+static int s2mps11_clk_is_enabled(struct clk_hw *hw)
+{
+	struct s2mps11_clk *s2mps11 = to_s2mps11_clk(hw);
+
+	return s2mps11->enabled;
+}
+
+static unsigned long s2mps11_clk_recalc_rate(struct clk_hw *hw,
+					     unsigned long parent_rate)
+{
+	struct s2mps11_clk *s2mps11 = to_s2mps11_clk(hw);
+	if (s2mps11->enabled)
+		return 32768;
+	else
+		return 0;
+}
+
+static struct clk_ops s2mps11_clk_ops = {
+	.prepare	= s2mps11_clk_prepare,
+	.unprepare	= s2mps11_clk_unprepare,
+	.is_enabled	= s2mps11_clk_is_enabled,
+	.recalc_rate	= s2mps11_clk_recalc_rate,
+};
+
+static struct clk_init_data s2mps11_clks_init[S2MPS11_CLKS_NUM] = {
+	[S2MPS11_CLK_AP] = {
+		.name = "s2mps11_ap",
+		.ops = &s2mps11_clk_ops,
+		.flags = CLK_IS_ROOT,
+	},
+	[S2MPS11_CLK_CP] = {
+		.name = "s2mps11_cp",
+		.ops = &s2mps11_clk_ops,
+		.flags = CLK_IS_ROOT,
+	},
+	[S2MPS11_CLK_BT] = {
+		.name = "s2mps11_bt",
+		.ops = &s2mps11_clk_ops,
+		.flags = CLK_IS_ROOT,
+	},
+};
+
+static struct device_node *s2mps11_clk_parse_dt(struct platform_device *pdev)
+{
+	struct sec_pmic_dev *iodev = dev_get_drvdata(pdev->dev.parent);
+	struct device_node *clk_np;
+	int i;
+
+	if (!iodev->dev->of_node)
+		return NULL;
+
+	clk_np = of_find_node_by_name(iodev->dev->of_node, "clocks");
+	if (!clk_np) {
+		dev_err(&pdev->dev, "could not find clock sub-node\n");
+		return ERR_PTR(-EINVAL);
+	}
+
+	clk_table = devm_kzalloc(&pdev->dev, sizeof(struct clk *) *
+				 S2MPS11_CLKS_NUM, GFP_KERNEL);
+	if (!clk_table)
+		return ERR_PTR(-ENOMEM);
+
+	for (i = 0; i < S2MPS11_CLKS_NUM; i++)
+		of_property_read_string_index(clk_np, "clock-output-names", i,
+				&s2mps11_clks_init[i].name);
+
+	return clk_np;
+}
+
+static int s2mps11_clk_probe(struct platform_device *pdev)
+{
+	struct sec_pmic_dev *iodev = dev_get_drvdata(pdev->dev.parent);
+	struct s2mps11_clk *s2mps11_clks, *s2mps11_clk;
+	struct device_node *clk_np = NULL;
+	int i, ret = 0;
+	u32 val;
+
+	s2mps11_clks = devm_kzalloc(&pdev->dev, sizeof(*s2mps11_clk) *
+					S2MPS11_CLKS_NUM, GFP_KERNEL);
+	if (!s2mps11_clks)
+		return -ENOMEM;
+
+	s2mps11_clk = s2mps11_clks;
+
+	clk_np = s2mps11_clk_parse_dt(pdev);
+	if (IS_ERR(clk_np))
+		return PTR_ERR(clk_np);
+
+	for (i = 0; i < S2MPS11_CLKS_NUM; i++, s2mps11_clk++) {
+		s2mps11_clk->iodev = iodev;
+		s2mps11_clk->hw.init = &s2mps11_clks_init[i];
+		s2mps11_clk->mask = 1 << i;
+
+		ret = regmap_read(s2mps11_clk->iodev->regmap,
+				  S2MPS11_REG_RTC_CTRL, &val);
+		if (ret < 0)
+			goto err_reg;
+
+		s2mps11_clk->enabled = val & s2mps11_clk->mask;
+
+		s2mps11_clk->clk = devm_clk_register(&pdev->dev,
+							&s2mps11_clk->hw);
+		if (IS_ERR(s2mps11_clk->clk)) {
+			dev_err(&pdev->dev, "Fail to register : %s\n",
+						s2mps11_name(s2mps11_clk));
+			ret = PTR_ERR(s2mps11_clk->clk);
+			goto err_reg;
+		}
+
+		s2mps11_clk->lookup = devm_kzalloc(&pdev->dev,
+					sizeof(struct clk_lookup), GFP_KERNEL);
+		if (!s2mps11_clk->lookup) {
+			ret = -ENOMEM;
+			goto err_lup;
+		}
+
+		s2mps11_clk->lookup->con_id = s2mps11_name(s2mps11_clk);
+		s2mps11_clk->lookup->clk = s2mps11_clk->clk;
+
+		clkdev_add(s2mps11_clk->lookup);
+	}
+
+	if (clk_table) {
+		for (i = 0; i < S2MPS11_CLKS_NUM; i++)
+			clk_table[i] = s2mps11_clks[i].clk;
+
+		clk_data.clks = clk_table;
+		clk_data.clk_num = S2MPS11_CLKS_NUM;
+		of_clk_add_provider(clk_np, of_clk_src_onecell_get, &clk_data);
+	}
+
+	platform_set_drvdata(pdev, s2mps11_clks);
+
+	return ret;
+err_lup:
+	devm_clk_unregister(&pdev->dev, s2mps11_clk->clk);
+err_reg:
+	while (s2mps11_clk > s2mps11_clks) {
+		if (s2mps11_clk->lookup) {
+			clkdev_drop(s2mps11_clk->lookup);
+			devm_clk_unregister(&pdev->dev, s2mps11_clk->clk);
+		}
+		s2mps11_clk--;
+	}
+
+	return ret;
+}
+
+static int s2mps11_clk_remove(struct platform_device *pdev)
+{
+	struct s2mps11_clk *s2mps11_clks = platform_get_drvdata(pdev);
+	int i;
+
+	for (i = 0; i < S2MPS11_CLKS_NUM; i++)
+		clkdev_drop(s2mps11_clks[i].lookup);
+
+	return 0;
+}
+
+static const struct platform_device_id s2mps11_clk_id[] = {
+	{ "s2mps11-clk", 0},
+	{ },
+};
+MODULE_DEVICE_TABLE(platform, s2mps11_clk_id);
+
+static struct platform_driver s2mps11_clk_driver = {
+	.driver = {
+		.name  = "s2mps11-clk",
+		.owner = THIS_MODULE,
+	},
+	.probe = s2mps11_clk_probe,
+	.remove = s2mps11_clk_remove,
+	.id_table = s2mps11_clk_id,
+};
+
+static int __init s2mps11_clk_init(void)
+{
+	return platform_driver_register(&s2mps11_clk_driver);
+}
+subsys_initcall(s2mps11_clk_init);
+
+static void __init s2mps11_clk_cleanup(void)
+{
+	platform_driver_unregister(&s2mps11_clk_driver);
+}
+module_exit(s2mps11_clk_cleanup);
+
+MODULE_DESCRIPTION("S2MPS11 Clock Driver");
+MODULE_AUTHOR("Yadwinder Singh Brar <yadi.brar@samsung.com>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/clk/clk-u300.c b/drivers/clk/clk-u300.c
index 8774e058cb6c..3efbdd078d14 100644
--- a/drivers/clk/clk-u300.c
+++ b/drivers/clk/clk-u300.c
@@ -746,7 +746,7 @@ struct u300_clock {
 	u16 clk_val;
 };
 
-struct u300_clock const __initconst u300_clk_lookup[] = {
+static struct u300_clock const u300_clk_lookup[] __initconst = {
 	{
 		.type = U300_CLK_TYPE_REST,
 		.id = 3,
@@ -1151,7 +1151,7 @@ static void __init of_u300_syscon_mclk_init(struct device_node *np)
 		of_clk_add_provider(np, of_clk_src_simple_get, clk);
 }
 
-static const __initconst struct of_device_id u300_clk_match[] = {
+static const struct of_device_id u300_clk_match[] __initconst = {
 	{
 		.compatible = "fixed-clock",
 		.data = of_fixed_clk_setup,
diff --git a/drivers/clk/clk-wm831x.c b/drivers/clk/clk-wm831x.c
index 1b3f8c9b98cc..805b4c344006 100644
--- a/drivers/clk/clk-wm831x.c
+++ b/drivers/clk/clk-wm831x.c
@@ -31,7 +31,7 @@ struct wm831x_clk {
 	bool xtal_ena;
 };
 
-static int wm831x_xtal_is_enabled(struct clk_hw *hw)
+static int wm831x_xtal_is_prepared(struct clk_hw *hw)
 {
 	struct wm831x_clk *clkdata = container_of(hw, struct wm831x_clk,
 						  xtal_hw);
@@ -52,7 +52,7 @@ static unsigned long wm831x_xtal_recalc_rate(struct clk_hw *hw,
 }
 
 static const struct clk_ops wm831x_xtal_ops = {
-	.is_enabled = wm831x_xtal_is_enabled,
+	.is_prepared = wm831x_xtal_is_prepared,
 	.recalc_rate = wm831x_xtal_recalc_rate,
 };
 
@@ -73,7 +73,7 @@ static const unsigned long wm831x_fll_auto_rates[] = {
 	24576000,
 };
 
-static int wm831x_fll_is_enabled(struct clk_hw *hw)
+static int wm831x_fll_is_prepared(struct clk_hw *hw)
 {
 	struct wm831x_clk *clkdata = container_of(hw, struct wm831x_clk,
 						  fll_hw);
@@ -170,7 +170,7 @@ static int wm831x_fll_set_rate(struct clk_hw *hw, unsigned long rate,
 	if (i == ARRAY_SIZE(wm831x_fll_auto_rates))
 		return -EINVAL;
 
-	if (wm831x_fll_is_enabled(hw))
+	if (wm831x_fll_is_prepared(hw))
 		return -EPERM;
 
 	return wm831x_set_bits(wm831x, WM831X_CLOCK_CONTROL_2,
@@ -220,7 +220,7 @@ static u8 wm831x_fll_get_parent(struct clk_hw *hw)
 }
 
 static const struct clk_ops wm831x_fll_ops = {
-	.is_enabled = wm831x_fll_is_enabled,
+	.is_prepared = wm831x_fll_is_prepared,
 	.prepare = wm831x_fll_prepare,
 	.unprepare = wm831x_fll_unprepare,
 	.round_rate = wm831x_fll_round_rate,
@@ -237,7 +237,7 @@ static struct clk_init_data wm831x_fll_init = {
 	.flags = CLK_SET_RATE_GATE,
 };
 
-static int wm831x_clkout_is_enabled(struct clk_hw *hw)
+static int wm831x_clkout_is_prepared(struct clk_hw *hw)
 {
 	struct wm831x_clk *clkdata = container_of(hw, struct wm831x_clk,
 						  clkout_hw);
@@ -335,7 +335,7 @@ static int wm831x_clkout_set_parent(struct clk_hw *hw, u8 parent)
 }
 
 static const struct clk_ops wm831x_clkout_ops = {
-	.is_enabled = wm831x_clkout_is_enabled,
+	.is_prepared = wm831x_clkout_is_prepared,
 	.prepare = wm831x_clkout_prepare,
 	.unprepare = wm831x_clkout_unprepare,
 	.get_parent = wm831x_clkout_get_parent,
@@ -360,6 +360,8 @@ static int wm831x_clk_probe(struct platform_device *pdev)
 	if (!clkdata)
 		return -ENOMEM;
 
+	clkdata->wm831x = wm831x;
+
 	/* XTAL_ENA can only be set via OTP/InstantConfig so just read once */
 	ret = wm831x_reg_read(wm831x, WM831X_CLOCK_CONTROL_2);
 	if (ret < 0) {
diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c
index 54a191c5bbf0..a004769528e6 100644
--- a/drivers/clk/clk.c
+++ b/drivers/clk/clk.c
@@ -458,7 +458,6 @@ static void clk_unprepare_unused_subtree(struct clk *clk)
 			clk->ops->unprepare(clk->hw);
 	}
 }
-EXPORT_SYMBOL_GPL(__clk_get_flags);
 
 /* caller must hold prepare_lock */
 static void clk_disable_unused_subtree(struct clk *clk)
@@ -559,6 +558,19 @@ struct clk *__clk_get_parent(struct clk *clk)
 	return !clk ? NULL : clk->parent;
 }
 
+struct clk *clk_get_parent_by_index(struct clk *clk, u8 index)
+{
+	if (!clk || index >= clk->num_parents)
+		return NULL;
+	else if (!clk->parents)
+		return __clk_lookup(clk->parent_names[index]);
+	else if (!clk->parents[index])
+		return clk->parents[index] =
+			__clk_lookup(clk->parent_names[index]);
+	else
+		return clk->parents[index];
+}
+
 unsigned int __clk_get_enable_count(struct clk *clk)
 {
 	return !clk ? 0 : clk->enable_count;
@@ -594,6 +606,7 @@ unsigned long __clk_get_flags(struct clk *clk)
 {
 	return !clk ? 0 : clk->flags;
 }
+EXPORT_SYMBOL_GPL(__clk_get_flags);
 
 bool __clk_is_prepared(struct clk *clk)
 {
@@ -679,6 +692,55 @@ struct clk *__clk_lookup(const char *name)
 	return NULL;
 }
 
+/*
+ * Helper for finding best parent to provide a given frequency. This can be used
+ * directly as a determine_rate callback (e.g. for a mux), or from a more
+ * complex clock that may combine a mux with other operations.
+ */
+long __clk_mux_determine_rate(struct clk_hw *hw, unsigned long rate,
+			      unsigned long *best_parent_rate,
+			      struct clk **best_parent_p)
+{
+	struct clk *clk = hw->clk, *parent, *best_parent = NULL;
+	int i, num_parents;
+	unsigned long parent_rate, best = 0;
+
+	/* if NO_REPARENT flag set, pass through to current parent */
+	if (clk->flags & CLK_SET_RATE_NO_REPARENT) {
+		parent = clk->parent;
+		if (clk->flags & CLK_SET_RATE_PARENT)
+			best = __clk_round_rate(parent, rate);
+		else if (parent)
+			best = __clk_get_rate(parent);
+		else
+			best = __clk_get_rate(clk);
+		goto out;
+	}
+
+	/* find the parent that can provide the fastest rate <= rate */
+	num_parents = clk->num_parents;
+	for (i = 0; i < num_parents; i++) {
+		parent = clk_get_parent_by_index(clk, i);
+		if (!parent)
+			continue;
+		if (clk->flags & CLK_SET_RATE_PARENT)
+			parent_rate = __clk_round_rate(parent, rate);
+		else
+			parent_rate = __clk_get_rate(parent);
+		if (parent_rate <= rate && parent_rate > best) {
+			best_parent = parent;
+			best = parent_rate;
+		}
+	}
+
+out:
+	if (best_parent)
+		*best_parent_p = best_parent;
+	*best_parent_rate = best;
+
+	return best;
+}
+
 /***        clk api        ***/
 
 void __clk_unprepare(struct clk *clk)
@@ -702,7 +764,7 @@ void __clk_unprepare(struct clk *clk)
 
 /**
  * clk_unprepare - undo preparation of a clock source
- * @clk: the clk being unprepare
+ * @clk: the clk being unprepared
  *
  * clk_unprepare may sleep, which differentiates it from clk_disable.  In a
  * simple case, clk_unprepare can be used instead of clk_disable to gate a clk
@@ -869,27 +931,31 @@ EXPORT_SYMBOL_GPL(clk_enable);
 /**
  * __clk_round_rate - round the given rate for a clk
  * @clk: round the rate of this clock
+ * @rate: the rate which is to be rounded
  *
  * Caller must hold prepare_lock.  Useful for clk_ops such as .set_rate
  */
 unsigned long __clk_round_rate(struct clk *clk, unsigned long rate)
 {
 	unsigned long parent_rate = 0;
+	struct clk *parent;
 
 	if (!clk)
 		return 0;
 
-	if (!clk->ops->round_rate) {
-		if (clk->flags & CLK_SET_RATE_PARENT)
-			return __clk_round_rate(clk->parent, rate);
-		else
-			return clk->rate;
-	}
-
-	if (clk->parent)
-		parent_rate = clk->parent->rate;
-
-	return clk->ops->round_rate(clk->hw, rate, &parent_rate);
+	parent = clk->parent;
+	if (parent)
+		parent_rate = parent->rate;
+
+	if (clk->ops->determine_rate)
+		return clk->ops->determine_rate(clk->hw, rate, &parent_rate,
+						&parent);
+	else if (clk->ops->round_rate)
+		return clk->ops->round_rate(clk->hw, rate, &parent_rate);
+	else if (clk->flags & CLK_SET_RATE_PARENT)
+		return __clk_round_rate(clk->parent, rate);
+	else
+		return clk->rate;
 }
 
 /**
@@ -956,7 +1022,7 @@ static int __clk_notify(struct clk *clk, unsigned long msg,
  *
  * Walks the subtree of clks starting with clk and recalculates rates as it
  * goes.  Note that if a clk does not implement the .recalc_rate callback then
- * it is assumed that the clock will take on the rate of it's parent.
+ * it is assumed that the clock will take on the rate of its parent.
  *
  * clk_recalc_rates also propagates the POST_RATE_CHANGE notification,
  * if necessary.
@@ -1014,6 +1080,115 @@ unsigned long clk_get_rate(struct clk *clk)
 }
 EXPORT_SYMBOL_GPL(clk_get_rate);
 
+static u8 clk_fetch_parent_index(struct clk *clk, struct clk *parent)
+{
+	u8 i;
+
+	if (!clk->parents)
+		clk->parents = kzalloc((sizeof(struct clk*) * clk->num_parents),
+								GFP_KERNEL);
+
+	/*
+	 * find index of new parent clock using cached parent ptrs,
+	 * or if not yet cached, use string name comparison and cache
+	 * them now to avoid future calls to __clk_lookup.
+	 */
+	for (i = 0; i < clk->num_parents; i++) {
+		if (clk->parents && clk->parents[i] == parent)
+			break;
+		else if (!strcmp(clk->parent_names[i], parent->name)) {
+			if (clk->parents)
+				clk->parents[i] = __clk_lookup(parent->name);
+			break;
+		}
+	}
+
+	return i;
+}
+
+static void clk_reparent(struct clk *clk, struct clk *new_parent)
+{
+	hlist_del(&clk->child_node);
+
+	if (new_parent) {
+		/* avoid duplicate POST_RATE_CHANGE notifications */
+		if (new_parent->new_child == clk)
+			new_parent->new_child = NULL;
+
+		hlist_add_head(&clk->child_node, &new_parent->children);
+	} else {
+		hlist_add_head(&clk->child_node, &clk_orphan_list);
+	}
+
+	clk->parent = new_parent;
+}
+
+static int __clk_set_parent(struct clk *clk, struct clk *parent, u8 p_index)
+{
+	unsigned long flags;
+	int ret = 0;
+	struct clk *old_parent = clk->parent;
+
+	/*
+	 * Migrate prepare state between parents and prevent race with
+	 * clk_enable().
+	 *
+	 * If the clock is not prepared, then a race with
+	 * clk_enable/disable() is impossible since we already have the
+	 * prepare lock (future calls to clk_enable() need to be preceded by
+	 * a clk_prepare()).
+	 *
+	 * If the clock is prepared, migrate the prepared state to the new
+	 * parent and also protect against a race with clk_enable() by
+	 * forcing the clock and the new parent on.  This ensures that all
+	 * future calls to clk_enable() are practically NOPs with respect to
+	 * hardware and software states.
+	 *
+	 * See also: Comment for clk_set_parent() below.
+	 */
+	if (clk->prepare_count) {
+		__clk_prepare(parent);
+		clk_enable(parent);
+		clk_enable(clk);
+	}
+
+	/* update the clk tree topology */
+	flags = clk_enable_lock();
+	clk_reparent(clk, parent);
+	clk_enable_unlock(flags);
+
+	/* change clock input source */
+	if (parent && clk->ops->set_parent)
+		ret = clk->ops->set_parent(clk->hw, p_index);
+
+	if (ret) {
+		flags = clk_enable_lock();
+		clk_reparent(clk, old_parent);
+		clk_enable_unlock(flags);
+
+		if (clk->prepare_count) {
+			clk_disable(clk);
+			clk_disable(parent);
+			__clk_unprepare(parent);
+		}
+		return ret;
+	}
+
+	/*
+	 * Finish the migration of prepare state and undo the changes done
+	 * for preventing a race with clk_enable().
+	 */
+	if (clk->prepare_count) {
+		clk_disable(clk);
+		clk_disable(old_parent);
+		__clk_unprepare(old_parent);
+	}
+
+	/* update debugfs with new clk tree topology */
+	clk_debug_reparent(clk, parent);
+	return 0;
+}
+
 /**
  * __clk_speculate_rates
  * @clk: first clk in the subtree
@@ -1026,7 +1201,7 @@ EXPORT_SYMBOL_GPL(clk_get_rate);
  * pre-rate change notifications and returns early if no clks in the
  * subtree have subscribed to the notifications.  Note that if a clk does not
  * implement the .recalc_rate callback then it is assumed that the clock will
- * take on the rate of it's parent.
+ * take on the rate of its parent.
  *
  * Caller must hold prepare_lock.
  */
@@ -1058,18 +1233,25 @@ out:
 	return ret;
 }
 
-static void clk_calc_subtree(struct clk *clk, unsigned long new_rate)
+static void clk_calc_subtree(struct clk *clk, unsigned long new_rate,
+			     struct clk *new_parent, u8 p_index)
 {
 	struct clk *child;
 
 	clk->new_rate = new_rate;
+	clk->new_parent = new_parent;
+	clk->new_parent_index = p_index;
+	/* include clk in new parent's PRE_RATE_CHANGE notifications */
+	clk->new_child = NULL;
+	if (new_parent && new_parent != clk->parent)
+		new_parent->new_child = clk;
 
 	hlist_for_each_entry(child, &clk->children, child_node) {
 		if (child->ops->recalc_rate)
 			child->new_rate = child->ops->recalc_rate(child->hw, new_rate);
 		else
 			child->new_rate = new_rate;
-		clk_calc_subtree(child, child->new_rate);
+		clk_calc_subtree(child, child->new_rate, NULL, 0);
 	}
 }
 
@@ -1080,50 +1262,63 @@ static void clk_calc_subtree(struct clk *clk, unsigned long new_rate)
 static struct clk *clk_calc_new_rates(struct clk *clk, unsigned long rate)
 {
 	struct clk *top = clk;
+	struct clk *old_parent, *parent;
 	unsigned long best_parent_rate = 0;
 	unsigned long new_rate;
+	u8 p_index = 0;
 
 	/* sanity */
 	if (IS_ERR_OR_NULL(clk))
 		return NULL;
 
 	/* save parent rate, if it exists */
-	if (clk->parent)
-		best_parent_rate = clk->parent->rate;
-
-	/* never propagate up to the parent */
-	if (!(clk->flags & CLK_SET_RATE_PARENT)) {
-		if (!clk->ops->round_rate) {
-			clk->new_rate = clk->rate;
-			return NULL;
-		}
-		new_rate = clk->ops->round_rate(clk->hw, rate, &best_parent_rate);
+	parent = old_parent = clk->parent;
+	if (parent)
+		best_parent_rate = parent->rate;
+
+	/* find the closest rate and parent clk/rate */
+	if (clk->ops->determine_rate) {
+		new_rate = clk->ops->determine_rate(clk->hw, rate,
+						    &best_parent_rate,
+						    &parent);
+	} else if (clk->ops->round_rate) {
+		new_rate = clk->ops->round_rate(clk->hw, rate,
+						&best_parent_rate);
+	} else if (!parent || !(clk->flags & CLK_SET_RATE_PARENT)) {
+		/* pass-through clock without adjustable parent */
+		clk->new_rate = clk->rate;
+		return NULL;
+	} else {
+		/* pass-through clock with adjustable parent */
+		top = clk_calc_new_rates(parent, rate);
+		new_rate = parent->new_rate;
 		goto out;
 	}
 
-	/* need clk->parent from here on out */
-	if (!clk->parent) {
-		pr_debug("%s: %s has NULL parent\n", __func__, clk->name);
+	/* some clocks must be gated to change parent */
+	if (parent != old_parent &&
+	    (clk->flags & CLK_SET_PARENT_GATE) && clk->prepare_count) {
+		pr_debug("%s: %s not gated but wants to reparent\n",
+			 __func__, clk->name);
 		return NULL;
 	}
 
-	if (!clk->ops->round_rate) {
-		top = clk_calc_new_rates(clk->parent, rate);
-		new_rate = clk->parent->new_rate;
-
-		goto out;
+	/* try finding the new parent index */
+	if (parent) {
+		p_index = clk_fetch_parent_index(clk, parent);
+		if (p_index == clk->num_parents) {
+			pr_debug("%s: clk %s can not be parent of clk %s\n",
+				 __func__, parent->name, clk->name);
+			return NULL;
+		}
 	}
 
-	new_rate = clk->ops->round_rate(clk->hw, rate, &best_parent_rate);
-
-	if (best_parent_rate != clk->parent->rate) {
-		top = clk_calc_new_rates(clk->parent, best_parent_rate);
-
-		goto out;
-	}
+	if ((clk->flags & CLK_SET_RATE_PARENT) && parent &&
+	    best_parent_rate != parent->rate)
+		top = clk_calc_new_rates(parent, best_parent_rate);
 
 out:
-	clk_calc_subtree(clk, new_rate);
+	clk_calc_subtree(clk, new_rate, parent, p_index);
 
 	return top;
 }
@@ -1135,7 +1330,7 @@ out:
  */
 static struct clk *clk_propagate_rate_change(struct clk *clk, unsigned long event)
 {
-	struct clk *child, *fail_clk = NULL;
+	struct clk *child, *tmp_clk, *fail_clk = NULL;
 	int ret = NOTIFY_DONE;
 
 	if (clk->rate == clk->new_rate)
@@ -1148,9 +1343,19 @@ static struct clk *clk_propagate_rate_change(struct clk *clk, unsigned long even
 	}
 
 	hlist_for_each_entry(child, &clk->children, child_node) {
-		clk = clk_propagate_rate_change(child, event);
-		if (clk)
-			fail_clk = clk;
+		/* Skip children who will be reparented to another clock */
+		if (child->new_parent && child->new_parent != clk)
+			continue;
+		tmp_clk = clk_propagate_rate_change(child, event);
+		if (tmp_clk)
+			fail_clk = tmp_clk;
+	}
+
+	/* handle the new child who might not be in clk->children yet */
+	if (clk->new_child) {
+		tmp_clk = clk_propagate_rate_change(clk->new_child, event);
+		if (tmp_clk)
+			fail_clk = tmp_clk;
 	}
 
 	return fail_clk;
@@ -1168,6 +1373,10 @@ static void clk_change_rate(struct clk *clk)
 
 	old_rate = clk->rate;
 
+	/* set parent */
+	if (clk->new_parent && clk->new_parent != clk->parent)
+		__clk_set_parent(clk, clk->new_parent, clk->new_parent_index);
+
 	if (clk->parent)
 		best_parent_rate = clk->parent->rate;
 
@@ -1182,8 +1391,16 @@ static void clk_change_rate(struct clk *clk)
 	if (clk->notifier_count && old_rate != clk->rate)
 		__clk_notify(clk, POST_RATE_CHANGE, old_rate, clk->rate);
 
-	hlist_for_each_entry(child, &clk->children, child_node)
+	hlist_for_each_entry(child, &clk->children, child_node) {
+		/* Skip children who will be reparented to another clock */
+		if (child->new_parent && child->new_parent != clk)
+			continue;
 		clk_change_rate(child);
+	}
+
+	/* handle the new child who might not be in clk->children yet */
+	if (clk->new_child)
+		clk_change_rate(clk->new_child);
 }
 
 /**
@@ -1198,7 +1415,7 @@ static void clk_change_rate(struct clk *clk)
  * outcome of clk's .round_rate implementation.  If *parent_rate is unchanged
  * after calling .round_rate then upstream parent propagation is ignored.  If
  * *parent_rate comes back with a new rate for clk's parent then we propagate
- * up to clk's parent and set it's rate.  Upward propagation will continue
+ * up to clk's parent and set its rate.  Upward propagation will continue
  * until either a clk does not support the CLK_SET_RATE_PARENT flag or
  * .round_rate stops requesting changes to clk's parent_rate.
  *
@@ -1212,6 +1429,9 @@ int clk_set_rate(struct clk *clk, unsigned long rate)
 	struct clk *top, *fail_clk;
 	int ret = 0;
 
+	if (!clk)
+		return 0;
+
 	/* prevent racing with updates to the clock topology */
 	clk_prepare_lock();
 
@@ -1315,30 +1535,12 @@ static struct clk *__clk_init_parent(struct clk *clk)
 			kzalloc((sizeof(struct clk*) * clk->num_parents),
 					GFP_KERNEL);
 
-	if (!clk->parents)
-		ret = __clk_lookup(clk->parent_names[index]);
-	else if (!clk->parents[index])
-		ret = clk->parents[index] =
-			__clk_lookup(clk->parent_names[index]);
-	else
-		ret = clk->parents[index];
+	ret = clk_get_parent_by_index(clk, index);
 
 out:
 	return ret;
 }
 
-static void clk_reparent(struct clk *clk, struct clk *new_parent)
-{
-	hlist_del(&clk->child_node);
-
-	if (new_parent)
-		hlist_add_head(&clk->child_node, &new_parent->children);
-	else
-		hlist_add_head(&clk->child_node, &clk_orphan_list);
-
-	clk->parent = new_parent;
-}
-
 void __clk_reparent(struct clk *clk, struct clk *new_parent)
 {
 	clk_reparent(clk, new_parent);
@@ -1346,98 +1548,6 @@ void __clk_reparent(struct clk *clk, struct clk *new_parent)
 	__clk_recalc_rates(clk, POST_RATE_CHANGE);
 }
 
-static u8 clk_fetch_parent_index(struct clk *clk, struct clk *parent)
-{
-	u8 i;
-
-	if (!clk->parents)
-		clk->parents = kzalloc((sizeof(struct clk*) * clk->num_parents),
-								GFP_KERNEL);
-
-	/*
-	 * find index of new parent clock using cached parent ptrs,
-	 * or if not yet cached, use string name comparison and cache
-	 * them now to avoid future calls to __clk_lookup.
-	 */
-	for (i = 0; i < clk->num_parents; i++) {
-		if (clk->parents && clk->parents[i] == parent)
-			break;
-		else if (!strcmp(clk->parent_names[i], parent->name)) {
-			if (clk->parents)
-				clk->parents[i] = __clk_lookup(parent->name);
-			break;
-		}
-	}
-
-	return i;
-}
-
-static int __clk_set_parent(struct clk *clk, struct clk *parent, u8 p_index)
-{
-	unsigned long flags;
-	int ret = 0;
-	struct clk *old_parent = clk->parent;
-
-	/*
-	 * Migrate prepare state between parents and prevent race with
-	 * clk_enable().
-	 *
-	 * If the clock is not prepared, then a race with
-	 * clk_enable/disable() is impossible since we already have the
-	 * prepare lock (future calls to clk_enable() need to be preceded by
-	 * a clk_prepare()).
-	 *
-	 * If the clock is prepared, migrate the prepared state to the new
-	 * parent and also protect against a race with clk_enable() by
-	 * forcing the clock and the new parent on.  This ensures that all
-	 * future calls to clk_enable() are practically NOPs with respect to
-	 * hardware and software states.
-	 *
-	 * See also: Comment for clk_set_parent() below.
-	 */
-	if (clk->prepare_count) {
-		__clk_prepare(parent);
-		clk_enable(parent);
-		clk_enable(clk);
-	}
-
-	/* update the clk tree topology */
-	flags = clk_enable_lock();
-	clk_reparent(clk, parent);
-	clk_enable_unlock(flags);
-
-	/* change clock input source */
-	if (parent && clk->ops->set_parent)
-		ret = clk->ops->set_parent(clk->hw, p_index);
-
-	if (ret) {
-		flags = clk_enable_lock();
-		clk_reparent(clk, old_parent);
-		clk_enable_unlock(flags);
-
-		if (clk->prepare_count) {
-			clk_disable(clk);
-			clk_disable(parent);
-			__clk_unprepare(parent);
-		}
-		return ret;
-	}
-
-	/*
-	 * Finish the migration of prepare state and undo the changes done
-	 * for preventing a race with clk_enable().
-	 */
-	if (clk->prepare_count) {
-		clk_disable(clk);
-		clk_disable(old_parent);
-		__clk_unprepare(old_parent);
-	}
-
-	/* update debugfs with new clk tree topology */
-	clk_debug_reparent(clk, parent);
-	return 0;
-}
-
 /**
  * clk_set_parent - switch the parent of a mux clk
  * @clk: the mux clk whose input we are switching
@@ -1461,7 +1571,10 @@ int clk_set_parent(struct clk *clk, struct clk *parent)
 	u8 p_index = 0;
 	unsigned long p_rate = 0;
 
-	if (!clk || !clk->ops)
+	if (!clk)
+		return 0;
+
+	if (!clk->ops)
 		return -EINVAL;
 
 	/* verify ops for for multi-parent clks */
@@ -1544,8 +1657,9 @@ int __clk_init(struct device *dev, struct clk *clk)
 
 	/* check that clk_ops are sane.  See Documentation/clk.txt */
 	if (clk->ops->set_rate &&
-			!(clk->ops->round_rate && clk->ops->recalc_rate)) {
-		pr_warning("%s: %s must implement .round_rate & .recalc_rate\n",
+	    !((clk->ops->round_rate || clk->ops->determine_rate) &&
+	      clk->ops->recalc_rate)) {
+		pr_warning("%s: %s must implement .round_rate or .determine_rate in addition to .recalc_rate\n",
 				__func__, clk->name);
 		ret = -EINVAL;
 		goto out;
@@ -1628,7 +1742,7 @@ int __clk_init(struct device *dev, struct clk *clk)
 	 * this clock
 	 */
 	hlist_for_each_entry_safe(orphan, tmp2, &clk_orphan_list, child_node) {
-		if (orphan->ops->get_parent) {
+		if (orphan->num_parents && orphan->ops->get_parent) {
 			i = orphan->ops->get_parent(orphan->hw);
 			if (!strcmp(clk->name, orphan->parent_names[i]))
 				__clk_reparent(orphan, clk);
@@ -1648,7 +1762,7 @@ int __clk_init(struct device *dev, struct clk *clk)
 	 * The .init callback is not used by any of the basic clock types, but
 	 * exists for weird hardware that must perform initialization magic.
 	 * Please consider other ways of solving initialization problems before
-	 * using this callback, as it's use is discouraged.
+	 * using this callback, as its use is discouraged.
 	 */
 	if (clk->ops->init)
 		clk->ops->init(clk->hw);
@@ -1675,7 +1789,7 @@ out:
  * very large numbers of clocks that need to be statically initialized.  It is
  * a layering violation to include clk-private.h from any code which implements
  * a clock's .ops; as such any statically initialized clock data MUST be in a
- * separate C file from the logic that implements it's operations.  Returns 0
+ * separate C file from the logic that implements its operations.  Returns 0
  * on success, otherwise an error code.
  */
 struct clk *__clk_register(struct device *dev, struct clk_hw *hw)
@@ -2115,13 +2229,13 @@ EXPORT_SYMBOL_GPL(of_clk_get_parent_name);
  */
 void __init of_clk_init(const struct of_device_id *matches)
 {
+	const struct of_device_id *match;
 	struct device_node *np;
 
 	if (!matches)
 		matches = __clk_of_table;
 
-	for_each_matching_node(np, matches) {
-		const struct of_device_id *match = of_match_node(matches, np);
+	for_each_matching_node_and_match(np, matches, &match) {
 		of_clk_init_cb_t clk_init_cb = match->data;
 		clk_init_cb(np);
 	}
diff --git a/drivers/clk/mmp/clk-mmp2.c b/drivers/clk/mmp/clk-mmp2.c
index d1f1a19d4351..b2721cae257a 100644
--- a/drivers/clk/mmp/clk-mmp2.c
+++ b/drivers/clk/mmp/clk-mmp2.c
@@ -248,7 +248,8 @@ void __init mmp2_clk_init(void)
 	clk_register_clkdev(clk, NULL, "mmp2-pwm.3");
 
 	clk = clk_register_mux(NULL, "uart0_mux", uart_parent,
-				ARRAY_SIZE(uart_parent), CLK_SET_RATE_PARENT,
+				ARRAY_SIZE(uart_parent),
+				CLK_SET_RATE_PARENT | CLK_SET_RATE_NO_REPARENT,
 				apbc_base + APBC_UART0, 4, 3, 0, &clk_lock);
 	clk_set_parent(clk, vctcxo);
 	clk_register_clkdev(clk, "uart_mux.0", NULL);
@@ -258,7 +259,8 @@ void __init mmp2_clk_init(void)
 	clk_register_clkdev(clk, NULL, "pxa2xx-uart.0");
 
 	clk = clk_register_mux(NULL, "uart1_mux", uart_parent,
-				ARRAY_SIZE(uart_parent), CLK_SET_RATE_PARENT,
+				ARRAY_SIZE(uart_parent),
+				CLK_SET_RATE_PARENT | CLK_SET_RATE_NO_REPARENT,
 				apbc_base + APBC_UART1, 4, 3, 0, &clk_lock);
 	clk_set_parent(clk, vctcxo);
 	clk_register_clkdev(clk, "uart_mux.1", NULL);
@@ -268,7 +270,8 @@ void __init mmp2_clk_init(void)
 	clk_register_clkdev(clk, NULL, "pxa2xx-uart.1");
 
 	clk = clk_register_mux(NULL, "uart2_mux", uart_parent,
-				ARRAY_SIZE(uart_parent), CLK_SET_RATE_PARENT,
+				ARRAY_SIZE(uart_parent),
+				CLK_SET_RATE_PARENT | CLK_SET_RATE_NO_REPARENT,
 				apbc_base + APBC_UART2, 4, 3, 0, &clk_lock);
 	clk_set_parent(clk, vctcxo);
 	clk_register_clkdev(clk, "uart_mux.2", NULL);
@@ -278,7 +281,8 @@ void __init mmp2_clk_init(void)
 	clk_register_clkdev(clk, NULL, "pxa2xx-uart.2");
 
 	clk = clk_register_mux(NULL, "uart3_mux", uart_parent,
-				ARRAY_SIZE(uart_parent), CLK_SET_RATE_PARENT,
+				ARRAY_SIZE(uart_parent),
+				CLK_SET_RATE_PARENT | CLK_SET_RATE_NO_REPARENT,
 				apbc_base + APBC_UART3, 4, 3, 0, &clk_lock);
 	clk_set_parent(clk, vctcxo);
 	clk_register_clkdev(clk, "uart_mux.3", NULL);
@@ -288,7 +292,8 @@ void __init mmp2_clk_init(void)
 	clk_register_clkdev(clk, NULL, "pxa2xx-uart.3");
 
 	clk = clk_register_mux(NULL, "ssp0_mux", ssp_parent,
-				ARRAY_SIZE(ssp_parent), CLK_SET_RATE_PARENT,
+				ARRAY_SIZE(ssp_parent),
+				CLK_SET_RATE_PARENT | CLK_SET_RATE_NO_REPARENT,
 				apbc_base + APBC_SSP0, 4, 3, 0, &clk_lock);
 	clk_register_clkdev(clk, "uart_mux.0", NULL);
 
@@ -297,7 +302,8 @@ void __init mmp2_clk_init(void)
 	clk_register_clkdev(clk, NULL, "mmp-ssp.0");
 
 	clk = clk_register_mux(NULL, "ssp1_mux", ssp_parent,
-				ARRAY_SIZE(ssp_parent), CLK_SET_RATE_PARENT,
+				ARRAY_SIZE(ssp_parent),
+				CLK_SET_RATE_PARENT | CLK_SET_RATE_NO_REPARENT,
 				apbc_base + APBC_SSP1, 4, 3, 0, &clk_lock);
 	clk_register_clkdev(clk, "ssp_mux.1", NULL);
 
@@ -306,7 +312,8 @@ void __init mmp2_clk_init(void)
 	clk_register_clkdev(clk, NULL, "mmp-ssp.1");
 
 	clk = clk_register_mux(NULL, "ssp2_mux", ssp_parent,
-				ARRAY_SIZE(ssp_parent), CLK_SET_RATE_PARENT,
+				ARRAY_SIZE(ssp_parent),
+				CLK_SET_RATE_PARENT | CLK_SET_RATE_NO_REPARENT,
 				apbc_base + APBC_SSP2, 4, 3, 0, &clk_lock);
 	clk_register_clkdev(clk, "ssp_mux.2", NULL);
 
@@ -315,7 +322,8 @@ void __init mmp2_clk_init(void)
 	clk_register_clkdev(clk, NULL, "mmp-ssp.2");
 
 	clk = clk_register_mux(NULL, "ssp3_mux", ssp_parent,
-				ARRAY_SIZE(ssp_parent), CLK_SET_RATE_PARENT,
+				ARRAY_SIZE(ssp_parent),
+				CLK_SET_RATE_PARENT | CLK_SET_RATE_NO_REPARENT,
 				apbc_base + APBC_SSP3, 4, 3, 0, &clk_lock);
 	clk_register_clkdev(clk, "ssp_mux.3", NULL);
 
@@ -324,7 +332,8 @@ void __init mmp2_clk_init(void)
 	clk_register_clkdev(clk, NULL, "mmp-ssp.3");
 
 	clk = clk_register_mux(NULL, "sdh_mux", sdh_parent,
-				ARRAY_SIZE(sdh_parent), CLK_SET_RATE_PARENT,
+				ARRAY_SIZE(sdh_parent),
+				CLK_SET_RATE_PARENT | CLK_SET_RATE_NO_REPARENT,
 				apmu_base + APMU_SDH0, 8, 2, 0, &clk_lock);
 	clk_register_clkdev(clk, "sdh_mux", NULL);
 
@@ -354,7 +363,8 @@ void __init mmp2_clk_init(void)
 	clk_register_clkdev(clk, "usb_clk", NULL);
 
 	clk = clk_register_mux(NULL, "disp0_mux", disp_parent,
-				ARRAY_SIZE(disp_parent), CLK_SET_RATE_PARENT,
+				ARRAY_SIZE(disp_parent),
+				CLK_SET_RATE_PARENT | CLK_SET_RATE_NO_REPARENT,
 				apmu_base + APMU_DISP0, 6, 2, 0, &clk_lock);
 	clk_register_clkdev(clk, "disp_mux.0", NULL);
 
@@ -376,7 +386,8 @@ void __init mmp2_clk_init(void)
 	clk_register_clkdev(clk, "disp_sphy.0", NULL);
 
 	clk = clk_register_mux(NULL, "disp1_mux", disp_parent,
-				ARRAY_SIZE(disp_parent), CLK_SET_RATE_PARENT,
+				ARRAY_SIZE(disp_parent),
+				CLK_SET_RATE_PARENT | CLK_SET_RATE_NO_REPARENT,
 				apmu_base + APMU_DISP1, 6, 2, 0, &clk_lock);
 	clk_register_clkdev(clk, "disp_mux.1", NULL);
 
@@ -394,7 +405,8 @@ void __init mmp2_clk_init(void)
 	clk_register_clkdev(clk, "ccic_arbiter", NULL);
 
 	clk = clk_register_mux(NULL, "ccic0_mux", ccic_parent,
-				ARRAY_SIZE(ccic_parent), CLK_SET_RATE_PARENT,
+				ARRAY_SIZE(ccic_parent),
+				CLK_SET_RATE_PARENT | CLK_SET_RATE_NO_REPARENT,
 				apmu_base + APMU_CCIC0, 6, 2, 0, &clk_lock);
 	clk_register_clkdev(clk, "ccic_mux.0", NULL);
 
@@ -421,7 +433,8 @@ void __init mmp2_clk_init(void)
 	clk_register_clkdev(clk, "sphyclk", "mmp-ccic.0");
 
 	clk = clk_register_mux(NULL, "ccic1_mux", ccic_parent,
-				ARRAY_SIZE(ccic_parent), CLK_SET_RATE_PARENT,
+				ARRAY_SIZE(ccic_parent),
+				CLK_SET_RATE_PARENT | CLK_SET_RATE_NO_REPARENT,
 				apmu_base + APMU_CCIC1, 6, 2, 0, &clk_lock);
 	clk_register_clkdev(clk, "ccic_mux.1", NULL);
 
diff --git a/drivers/clk/mmp/clk-pxa168.c b/drivers/clk/mmp/clk-pxa168.c
index 28b3b51c794b..014396b028a2 100644
--- a/drivers/clk/mmp/clk-pxa168.c
+++ b/drivers/clk/mmp/clk-pxa168.c
@@ -199,7 +199,8 @@ void __init pxa168_clk_init(void)
 	clk_register_clkdev(clk, NULL, "pxa168-pwm.3");
 
 	clk = clk_register_mux(NULL, "uart0_mux", uart_parent,
-				ARRAY_SIZE(uart_parent), CLK_SET_RATE_PARENT,
+				ARRAY_SIZE(uart_parent),
+				CLK_SET_RATE_PARENT | CLK_SET_RATE_NO_REPARENT,
 				apbc_base + APBC_UART0, 4, 3, 0, &clk_lock);
 	clk_set_parent(clk, uart_pll);
 	clk_register_clkdev(clk, "uart_mux.0", NULL);
@@ -209,7 +210,8 @@ void __init pxa168_clk_init(void)
 	clk_register_clkdev(clk, NULL, "pxa2xx-uart.0");
 
 	clk = clk_register_mux(NULL, "uart1_mux", uart_parent,
-				ARRAY_SIZE(uart_parent), CLK_SET_RATE_PARENT,
+				ARRAY_SIZE(uart_parent),
+				CLK_SET_RATE_PARENT | CLK_SET_RATE_NO_REPARENT,
 				apbc_base + APBC_UART1, 4, 3, 0, &clk_lock);
 	clk_set_parent(clk, uart_pll);
 	clk_register_clkdev(clk, "uart_mux.1", NULL);
@@ -219,7 +221,8 @@ void __init pxa168_clk_init(void)
 	clk_register_clkdev(clk, NULL, "pxa2xx-uart.1");
 
 	clk = clk_register_mux(NULL, "uart2_mux", uart_parent,
-				ARRAY_SIZE(uart_parent), CLK_SET_RATE_PARENT,
+				ARRAY_SIZE(uart_parent),
+				CLK_SET_RATE_PARENT | CLK_SET_RATE_NO_REPARENT,
 				apbc_base + APBC_UART2, 4, 3, 0, &clk_lock);
 	clk_set_parent(clk, uart_pll);
 	clk_register_clkdev(clk, "uart_mux.2", NULL);
@@ -229,7 +232,8 @@ void __init pxa168_clk_init(void)
 	clk_register_clkdev(clk, NULL, "pxa2xx-uart.2");
 
 	clk = clk_register_mux(NULL, "ssp0_mux", ssp_parent,
-				ARRAY_SIZE(ssp_parent), CLK_SET_RATE_PARENT,
+				ARRAY_SIZE(ssp_parent),
+				CLK_SET_RATE_PARENT | CLK_SET_RATE_NO_REPARENT,
 				apbc_base + APBC_SSP0, 4, 3, 0, &clk_lock);
 	clk_register_clkdev(clk, "uart_mux.0", NULL);
 
@@ -238,7 +242,8 @@ void __init pxa168_clk_init(void)
 	clk_register_clkdev(clk, NULL, "mmp-ssp.0");
 
 	clk = clk_register_mux(NULL, "ssp1_mux", ssp_parent,
-				ARRAY_SIZE(ssp_parent), CLK_SET_RATE_PARENT,
+				ARRAY_SIZE(ssp_parent),
+				CLK_SET_RATE_PARENT | CLK_SET_RATE_NO_REPARENT,
 				apbc_base + APBC_SSP1, 4, 3, 0, &clk_lock);
 	clk_register_clkdev(clk, "ssp_mux.1", NULL);
 
@@ -247,7 +252,8 @@ void __init pxa168_clk_init(void)
 	clk_register_clkdev(clk, NULL, "mmp-ssp.1");
 
 	clk = clk_register_mux(NULL, "ssp2_mux", ssp_parent,
-				ARRAY_SIZE(ssp_parent), CLK_SET_RATE_PARENT,
+				ARRAY_SIZE(ssp_parent),
+				CLK_SET_RATE_PARENT | CLK_SET_RATE_NO_REPARENT,
 				apbc_base + APBC_SSP2, 4, 3, 0, &clk_lock);
 	clk_register_clkdev(clk, "ssp_mux.2", NULL);
 
@@ -256,7 +262,8 @@ void __init pxa168_clk_init(void)
 	clk_register_clkdev(clk, NULL, "mmp-ssp.2");
 
 	clk = clk_register_mux(NULL, "ssp3_mux", ssp_parent,
-				ARRAY_SIZE(ssp_parent), CLK_SET_RATE_PARENT,
+				ARRAY_SIZE(ssp_parent),
+				CLK_SET_RATE_PARENT | CLK_SET_RATE_NO_REPARENT,
 				apbc_base + APBC_SSP3, 4, 3, 0, &clk_lock);
 	clk_register_clkdev(clk, "ssp_mux.3", NULL);
 
@@ -265,7 +272,8 @@ void __init pxa168_clk_init(void)
 	clk_register_clkdev(clk, NULL, "mmp-ssp.3");
 
 	clk = clk_register_mux(NULL, "ssp4_mux", ssp_parent,
-				ARRAY_SIZE(ssp_parent), CLK_SET_RATE_PARENT,
+				ARRAY_SIZE(ssp_parent),
+				CLK_SET_RATE_PARENT | CLK_SET_RATE_NO_REPARENT,
 				apbc_base + APBC_SSP4, 4, 3, 0, &clk_lock);
 	clk_register_clkdev(clk, "ssp_mux.4", NULL);
 
@@ -278,7 +286,8 @@ void __init pxa168_clk_init(void)
 	clk_register_clkdev(clk, NULL, "pxa3xx-nand.0");
 
 	clk = clk_register_mux(NULL, "sdh0_mux", sdh_parent,
-				ARRAY_SIZE(sdh_parent), CLK_SET_RATE_PARENT,
+				ARRAY_SIZE(sdh_parent),
+				CLK_SET_RATE_PARENT | CLK_SET_RATE_NO_REPARENT,
 				apmu_base + APMU_SDH0, 6, 1, 0, &clk_lock);
 	clk_register_clkdev(clk, "sdh0_mux", NULL);
 
@@ -287,7 +296,8 @@ void __init pxa168_clk_init(void)
 	clk_register_clkdev(clk, NULL, "sdhci-pxa.0");
 
 	clk = clk_register_mux(NULL, "sdh1_mux", sdh_parent,
-				ARRAY_SIZE(sdh_parent), CLK_SET_RATE_PARENT,
+				ARRAY_SIZE(sdh_parent),
+				CLK_SET_RATE_PARENT | CLK_SET_RATE_NO_REPARENT,
 				apmu_base + APMU_SDH1, 6, 1, 0, &clk_lock);
 	clk_register_clkdev(clk, "sdh1_mux", NULL);
 
@@ -304,7 +314,8 @@ void __init pxa168_clk_init(void)
 	clk_register_clkdev(clk, "sph_clk", NULL);
 
 	clk = clk_register_mux(NULL, "disp0_mux", disp_parent,
-				ARRAY_SIZE(disp_parent), CLK_SET_RATE_PARENT,
+				ARRAY_SIZE(disp_parent),
+				CLK_SET_RATE_PARENT | CLK_SET_RATE_NO_REPARENT,
 				apmu_base + APMU_DISP0, 6, 1, 0, &clk_lock);
 	clk_register_clkdev(clk, "disp_mux.0", NULL);
 
@@ -317,7 +328,8 @@ void __init pxa168_clk_init(void)
 	clk_register_clkdev(clk, "hclk", "mmp-disp.0");
 
 	clk = clk_register_mux(NULL, "ccic0_mux", ccic_parent,
-				ARRAY_SIZE(ccic_parent), CLK_SET_RATE_PARENT,
+				ARRAY_SIZE(ccic_parent),
+				CLK_SET_RATE_PARENT | CLK_SET_RATE_NO_REPARENT,
 				apmu_base + APMU_CCIC0, 6, 1, 0, &clk_lock);
 	clk_register_clkdev(clk, "ccic_mux.0", NULL);
 
@@ -327,8 +339,8 @@ void __init pxa168_clk_init(void)
 
 	clk = clk_register_mux(NULL, "ccic0_phy_mux", ccic_phy_parent,
 				ARRAY_SIZE(ccic_phy_parent),
-				CLK_SET_RATE_PARENT, apmu_base + APMU_CCIC0,
-				7, 1, 0, &clk_lock);
+				CLK_SET_RATE_PARENT | CLK_SET_RATE_NO_REPARENT,
+				apmu_base + APMU_CCIC0, 7, 1, 0, &clk_lock);
 	clk_register_clkdev(clk, "ccic_phy_mux.0", NULL);
 
 	clk = mmp_clk_register_apmu("ccic0_phy", "ccic0_phy_mux",
diff --git a/drivers/clk/mmp/clk-pxa910.c b/drivers/clk/mmp/clk-pxa910.c
index 6ec05698ed38..9efc6a47535d 100644
--- a/drivers/clk/mmp/clk-pxa910.c
+++ b/drivers/clk/mmp/clk-pxa910.c
@@ -204,7 +204,8 @@ void __init pxa910_clk_init(void)
 	clk_register_clkdev(clk, NULL, "pxa910-pwm.3");
 
 	clk = clk_register_mux(NULL, "uart0_mux", uart_parent,
-				ARRAY_SIZE(uart_parent), CLK_SET_RATE_PARENT,
+				ARRAY_SIZE(uart_parent),
+				CLK_SET_RATE_PARENT | CLK_SET_RATE_NO_REPARENT,
 				apbc_base + APBC_UART0, 4, 3, 0, &clk_lock);
 	clk_set_parent(clk, uart_pll);
 	clk_register_clkdev(clk, "uart_mux.0", NULL);
@@ -214,7 +215,8 @@ void __init pxa910_clk_init(void)
 	clk_register_clkdev(clk, NULL, "pxa2xx-uart.0");
 
 	clk = clk_register_mux(NULL, "uart1_mux", uart_parent,
-				ARRAY_SIZE(uart_parent), CLK_SET_RATE_PARENT,
+				ARRAY_SIZE(uart_parent),
+				CLK_SET_RATE_PARENT | CLK_SET_RATE_NO_REPARENT,
 				apbc_base + APBC_UART1, 4, 3, 0, &clk_lock);
 	clk_set_parent(clk, uart_pll);
 	clk_register_clkdev(clk, "uart_mux.1", NULL);
@@ -224,7 +226,8 @@ void __init pxa910_clk_init(void)
 	clk_register_clkdev(clk, NULL, "pxa2xx-uart.1");
 
 	clk = clk_register_mux(NULL, "uart2_mux", uart_parent,
-				ARRAY_SIZE(uart_parent), CLK_SET_RATE_PARENT,
+				ARRAY_SIZE(uart_parent),
+				CLK_SET_RATE_PARENT | CLK_SET_RATE_NO_REPARENT,
 				apbcp_base + APBCP_UART2, 4, 3, 0, &clk_lock);
 	clk_set_parent(clk, uart_pll);
 	clk_register_clkdev(clk, "uart_mux.2", NULL);
@@ -234,7 +237,8 @@ void __init pxa910_clk_init(void)
 	clk_register_clkdev(clk, NULL, "pxa2xx-uart.2");
 
 	clk = clk_register_mux(NULL, "ssp0_mux", ssp_parent,
-				ARRAY_SIZE(ssp_parent), CLK_SET_RATE_PARENT,
+				ARRAY_SIZE(ssp_parent),
+				CLK_SET_RATE_PARENT | CLK_SET_RATE_NO_REPARENT,
 				apbc_base + APBC_SSP0, 4, 3, 0, &clk_lock);
 	clk_register_clkdev(clk, "uart_mux.0", NULL);
 
@@ -243,7 +247,8 @@ void __init pxa910_clk_init(void)
 	clk_register_clkdev(clk, NULL, "mmp-ssp.0");
 
 	clk = clk_register_mux(NULL, "ssp1_mux", ssp_parent,
-				ARRAY_SIZE(ssp_parent), CLK_SET_RATE_PARENT,
+				ARRAY_SIZE(ssp_parent),
+				CLK_SET_RATE_PARENT | CLK_SET_RATE_NO_REPARENT,
 				apbc_base + APBC_SSP1, 4, 3, 0, &clk_lock);
 	clk_register_clkdev(clk, "ssp_mux.1", NULL);
 
@@ -256,7 +261,8 @@ void __init pxa910_clk_init(void)
 	clk_register_clkdev(clk, NULL, "pxa3xx-nand.0");
 
 	clk = clk_register_mux(NULL, "sdh0_mux", sdh_parent,
-				ARRAY_SIZE(sdh_parent), CLK_SET_RATE_PARENT,
+				ARRAY_SIZE(sdh_parent),
+				CLK_SET_RATE_PARENT | CLK_SET_RATE_NO_REPARENT,
 				apmu_base + APMU_SDH0, 6, 1, 0, &clk_lock);
 	clk_register_clkdev(clk, "sdh0_mux", NULL);
 
@@ -265,7 +271,8 @@ void __init pxa910_clk_init(void)
 	clk_register_clkdev(clk, NULL, "sdhci-pxa.0");
 
 	clk = clk_register_mux(NULL, "sdh1_mux", sdh_parent,
-				ARRAY_SIZE(sdh_parent), CLK_SET_RATE_PARENT,
+				ARRAY_SIZE(sdh_parent),
+				CLK_SET_RATE_PARENT | CLK_SET_RATE_NO_REPARENT,
 				apmu_base + APMU_SDH1, 6, 1, 0, &clk_lock);
 	clk_register_clkdev(clk, "sdh1_mux", NULL);
 
@@ -282,7 +289,8 @@ void __init pxa910_clk_init(void)
 	clk_register_clkdev(clk, "sph_clk", NULL);
 
 	clk = clk_register_mux(NULL, "disp0_mux", disp_parent,
-				ARRAY_SIZE(disp_parent), CLK_SET_RATE_PARENT,
+				ARRAY_SIZE(disp_parent),
+				CLK_SET_RATE_PARENT | CLK_SET_RATE_NO_REPARENT,
 				apmu_base + APMU_DISP0, 6, 1, 0, &clk_lock);
 	clk_register_clkdev(clk, "disp_mux.0", NULL);
 
@@ -291,7 +299,8 @@ void __init pxa910_clk_init(void)
 	clk_register_clkdev(clk, NULL, "mmp-disp.0");
 
 	clk = clk_register_mux(NULL, "ccic0_mux", ccic_parent,
-				ARRAY_SIZE(ccic_parent), CLK_SET_RATE_PARENT,
+				ARRAY_SIZE(ccic_parent),
+				CLK_SET_RATE_PARENT | CLK_SET_RATE_NO_REPARENT,
 				apmu_base + APMU_CCIC0, 6, 1, 0, &clk_lock);
 	clk_register_clkdev(clk, "ccic_mux.0", NULL);
 
@@ -301,8 +310,8 @@ void __init pxa910_clk_init(void)
 
 	clk = clk_register_mux(NULL, "ccic0_phy_mux", ccic_phy_parent,
 				ARRAY_SIZE(ccic_phy_parent),
-				CLK_SET_RATE_PARENT, apmu_base + APMU_CCIC0,
-				7, 1, 0, &clk_lock);
+				CLK_SET_RATE_PARENT | CLK_SET_RATE_NO_REPARENT,
+				apmu_base + APMU_CCIC0, 7, 1, 0, &clk_lock);
 	clk_register_clkdev(clk, "ccic_phy_mux.0", NULL);
 
 	clk = mmp_clk_register_apmu("ccic0_phy", "ccic0_phy_mux",
diff --git a/drivers/clk/mvebu/armada-370.c b/drivers/clk/mvebu/armada-370.c
index 079960e7c304..fc777bdc1886 100644
--- a/drivers/clk/mvebu/armada-370.c
+++ b/drivers/clk/mvebu/armada-370.c
@@ -32,13 +32,13 @@
 
 enum { A370_CPU_TO_NBCLK, A370_CPU_TO_HCLK, A370_CPU_TO_DRAMCLK };
 
-static const struct coreclk_ratio __initconst a370_coreclk_ratios[] = {
+static const struct coreclk_ratio a370_coreclk_ratios[] __initconst = {
 	{ .id = A370_CPU_TO_NBCLK, .name = "nbclk" },
 	{ .id = A370_CPU_TO_HCLK, .name = "hclk" },
 	{ .id = A370_CPU_TO_DRAMCLK, .name = "dramclk" },
 };
 
-static const u32 __initconst a370_tclk_freqs[] = {
+static const u32 a370_tclk_freqs[] __initconst = {
 	16600000,
 	20000000,
 };
@@ -52,7 +52,7 @@ static u32 __init a370_get_tclk_freq(void __iomem *sar)
 	return a370_tclk_freqs[tclk_freq_select];
 }
 
-static const u32 __initconst a370_cpu_freqs[] = {
+static const u32 a370_cpu_freqs[] __initconst = {
 	400000000,
 	533000000,
 	667000000,
@@ -78,7 +78,7 @@ static u32 __init a370_get_cpu_freq(void __iomem *sar)
 	return cpu_freq;
 }
 
-static const int __initconst a370_nbclk_ratios[32][2] = {
+static const int a370_nbclk_ratios[32][2] __initconst = {
 	{0, 1}, {1, 2}, {2, 2}, {2, 2},
 	{1, 2}, {1, 2}, {1, 1}, {2, 3},
 	{0, 1}, {1, 2}, {2, 4}, {0, 1},
@@ -89,7 +89,7 @@ static const int __initconst a370_nbclk_ratios[32][2] = {
 	{0, 1}, {0, 1}, {0, 1}, {0, 1},
 };
 
-static const int __initconst a370_hclk_ratios[32][2] = {
+static const int a370_hclk_ratios[32][2] __initconst = {
 	{0, 1}, {1, 2}, {2, 6}, {2, 3},
 	{1, 3}, {1, 4}, {1, 2}, {2, 6},
 	{0, 1}, {1, 6}, {2, 10}, {0, 1},
@@ -100,7 +100,7 @@ static const int __initconst a370_hclk_ratios[32][2] = {
 	{0, 1}, {0, 1}, {0, 1}, {0, 1},
 };
 
-static const int __initconst a370_dramclk_ratios[32][2] = {
+static const int a370_dramclk_ratios[32][2] __initconst = {
 	{0, 1}, {1, 2}, {2, 3}, {2, 3},
 	{1, 3}, {1, 2}, {1, 2}, {2, 6},
 	{0, 1}, {1, 3}, {2, 5}, {0, 1},
@@ -152,7 +152,7 @@ CLK_OF_DECLARE(a370_core_clk, "marvell,armada-370-core-clock",
  * Clock Gating Control
  */
 
-static const struct clk_gating_soc_desc __initconst a370_gating_desc[] = {
+static const struct clk_gating_soc_desc a370_gating_desc[] __initconst = {
 	{ "audio", NULL, 0, 0 },
 	{ "pex0_en", NULL, 1, 0 },
 	{ "pex1_en", NULL,  2, 0 },
diff --git a/drivers/clk/mvebu/armada-xp.c b/drivers/clk/mvebu/armada-xp.c
index 13b62ceb3407..9922c4475aa8 100644
--- a/drivers/clk/mvebu/armada-xp.c
+++ b/drivers/clk/mvebu/armada-xp.c
@@ -40,7 +40,7 @@
 
 enum { AXP_CPU_TO_NBCLK, AXP_CPU_TO_HCLK, AXP_CPU_TO_DRAMCLK };
 
-static const struct coreclk_ratio __initconst axp_coreclk_ratios[] = {
+static const struct coreclk_ratio axp_coreclk_ratios[] __initconst = {
 	{ .id = AXP_CPU_TO_NBCLK, .name = "nbclk" },
 	{ .id = AXP_CPU_TO_HCLK, .name = "hclk" },
 	{ .id = AXP_CPU_TO_DRAMCLK, .name = "dramclk" },
@@ -52,7 +52,7 @@ static u32 __init axp_get_tclk_freq(void __iomem *sar)
 	return 250000000;
 }
 
-static const u32 __initconst axp_cpu_freqs[] = {
+static const u32 axp_cpu_freqs[] __initconst = {
 	1000000000,
 	1066000000,
 	1200000000,
@@ -89,7 +89,7 @@ static u32 __init axp_get_cpu_freq(void __iomem *sar)
 	return cpu_freq;
 }
 
-static const int __initconst axp_nbclk_ratios[32][2] = {
+static const int axp_nbclk_ratios[32][2] __initconst = {
 	{0, 1}, {1, 2}, {2, 2}, {2, 2},
 	{1, 2}, {1, 2}, {1, 1}, {2, 3},
 	{0, 1}, {1, 2}, {2, 4}, {0, 1},
@@ -100,7 +100,7 @@ static const int __initconst axp_nbclk_ratios[32][2] = {
 	{0, 1}, {0, 1}, {0, 1}, {0, 1},
 };
 
-static const int __initconst axp_hclk_ratios[32][2] = {
+static const int axp_hclk_ratios[32][2] __initconst = {
 	{0, 1}, {1, 2}, {2, 6}, {2, 3},
 	{1, 3}, {1, 4}, {1, 2}, {2, 6},
 	{0, 1}, {1, 6}, {2, 10}, {0, 1},
@@ -111,7 +111,7 @@ static const int __initconst axp_hclk_ratios[32][2] = {
 	{0, 1}, {0, 1}, {0, 1}, {0, 1},
 };
 
-static const int __initconst axp_dramclk_ratios[32][2] = {
+static const int axp_dramclk_ratios[32][2] __initconst = {
 	{0, 1}, {1, 2}, {2, 3}, {2, 3},
 	{1, 3}, {1, 2}, {1, 2}, {2, 6},
 	{0, 1}, {1, 3}, {2, 5}, {0, 1},
@@ -169,7 +169,7 @@ CLK_OF_DECLARE(axp_core_clk, "marvell,armada-xp-core-clock",
  * Clock Gating Control
  */
 
-static const struct clk_gating_soc_desc __initconst axp_gating_desc[] = {
+static const struct clk_gating_soc_desc axp_gating_desc[] __initconst = {
 	{ "audio", NULL, 0, 0 },
 	{ "ge3", NULL, 1, 0 },
 	{ "ge2", NULL,  2, 0 },
diff --git a/drivers/clk/mvebu/clk-cpu.c b/drivers/clk/mvebu/clk-cpu.c
index b0fbc0715491..1466865b0743 100644
--- a/drivers/clk/mvebu/clk-cpu.c
+++ b/drivers/clk/mvebu/clk-cpu.c
@@ -119,7 +119,7 @@ void __init of_cpu_clk_setup(struct device_node *node)
 
 	cpuclk = kzalloc(ncpus * sizeof(*cpuclk), GFP_KERNEL);
 	if (WARN_ON(!cpuclk))
-		return;
+		goto cpuclk_out;
 
 	clks = kzalloc(ncpus * sizeof(*clks), GFP_KERNEL);
 	if (WARN_ON(!clks))
@@ -170,6 +170,8 @@ bail_out:
 		kfree(cpuclk[ncpus].clk_name);
 clks_out:
 	kfree(cpuclk);
+cpuclk_out:
+	iounmap(clock_complex_base);
 }
 
 CLK_OF_DECLARE(armada_xp_cpu_clock, "marvell,armada-xp-cpu-clock",
diff --git a/drivers/clk/mvebu/common.c b/drivers/clk/mvebu/common.c
index adaa4a1821b8..25ceccf939ad 100644
--- a/drivers/clk/mvebu/common.c
+++ b/drivers/clk/mvebu/common.c
@@ -45,8 +45,10 @@ void __init mvebu_coreclk_setup(struct device_node *np,
 	clk_data.clk_num = 2 + desc->num_ratios;
 	clk_data.clks = kzalloc(clk_data.clk_num * sizeof(struct clk *),
 				GFP_KERNEL);
-	if (WARN_ON(!clk_data.clks))
+	if (WARN_ON(!clk_data.clks)) {
+		iounmap(base);
 		return;
+	}
 
 	/* Register TCLK */
 	of_property_read_string_index(np, "clock-output-names", 0,
@@ -134,7 +136,7 @@ void __init mvebu_clk_gating_setup(struct device_node *np,
 
 	ctrl = kzalloc(sizeof(*ctrl), GFP_KERNEL);
 	if (WARN_ON(!ctrl))
-		return;
+		goto ctrl_out;
 
 	spin_lock_init(&ctrl->lock);
 
@@ -145,10 +147,8 @@ void __init mvebu_clk_gating_setup(struct device_node *np,
 	ctrl->num_gates = n;
 	ctrl->gates = kzalloc(ctrl->num_gates * sizeof(struct clk *),
 			      GFP_KERNEL);
-	if (WARN_ON(!ctrl->gates)) {
-		kfree(ctrl);
-		return;
-	}
+	if (WARN_ON(!ctrl->gates))
+		goto gates_out;
 
 	for (n = 0; n < ctrl->num_gates; n++) {
 		const char *parent =
@@ -160,4 +160,10 @@ void __init mvebu_clk_gating_setup(struct device_node *np,
 	}
 
 	of_clk_add_provider(np, clk_gating_get_src, ctrl);
+
+	return;
+gates_out:
+	kfree(ctrl);
+ctrl_out:
+	iounmap(base);
 }
diff --git a/drivers/clk/mvebu/dove.c b/drivers/clk/mvebu/dove.c
index 79d7aedf03fb..38aee1e3f242 100644
--- a/drivers/clk/mvebu/dove.c
+++ b/drivers/clk/mvebu/dove.c
@@ -74,12 +74,12 @@
 
 enum { DOVE_CPU_TO_L2, DOVE_CPU_TO_DDR };
 
-static const struct coreclk_ratio __initconst dove_coreclk_ratios[] = {
+static const struct coreclk_ratio dove_coreclk_ratios[] __initconst = {
 	{ .id = DOVE_CPU_TO_L2, .name = "l2clk", },
 	{ .id = DOVE_CPU_TO_DDR, .name = "ddrclk", }
 };
 
-static const u32 __initconst dove_tclk_freqs[] = {
+static const u32 dove_tclk_freqs[] __initconst = {
 	166666667,
 	125000000,
 	0, 0
@@ -92,7 +92,7 @@ static u32 __init dove_get_tclk_freq(void __iomem *sar)
 	return dove_tclk_freqs[opt];
 }
 
-static const u32 __initconst dove_cpu_freqs[] = {
+static const u32 dove_cpu_freqs[] __initconst = {
 	0, 0, 0, 0, 0,
 	1000000000,
 	933333333, 933333333,
@@ -111,12 +111,12 @@ static u32 __init dove_get_cpu_freq(void __iomem *sar)
 	return dove_cpu_freqs[opt];
 }
 
-static const int __initconst dove_cpu_l2_ratios[8][2] = {
+static const int dove_cpu_l2_ratios[8][2] __initconst = {
 	{ 1, 1 }, { 0, 1 }, { 1, 2 }, { 0, 1 },
 	{ 1, 3 }, { 0, 1 }, { 1, 4 }, { 0, 1 }
 };
 
-static const int __initconst dove_cpu_ddr_ratios[16][2] = {
+static const int dove_cpu_ddr_ratios[16][2] __initconst = {
 	{ 1, 1 }, { 0, 1 }, { 1, 2 }, { 2, 5 },
 	{ 1, 3 }, { 0, 1 }, { 1, 4 }, { 0, 1 },
 	{ 1, 5 }, { 0, 1 }, { 1, 6 }, { 0, 1 },
@@ -164,7 +164,7 @@ CLK_OF_DECLARE(dove_core_clk, "marvell,dove-core-clock", dove_coreclk_init);
  * Clock Gating Control
  */
 
-static const struct clk_gating_soc_desc __initconst dove_gating_desc[] = {
+static const struct clk_gating_soc_desc dove_gating_desc[] __initconst = {
 	{ "usb0", NULL, 0, 0 },
 	{ "usb1", NULL, 1, 0 },
 	{ "ge",	"gephy", 2, 0 },
diff --git a/drivers/clk/mvebu/kirkwood.c b/drivers/clk/mvebu/kirkwood.c
index 71d24619ccdb..2636a55f29f9 100644
--- a/drivers/clk/mvebu/kirkwood.c
+++ b/drivers/clk/mvebu/kirkwood.c
@@ -78,7 +78,7 @@
 
 enum { KIRKWOOD_CPU_TO_L2, KIRKWOOD_CPU_TO_DDR };
 
-static const struct coreclk_ratio __initconst kirkwood_coreclk_ratios[] = {
+static const struct coreclk_ratio kirkwood_coreclk_ratios[] __initconst = {
 	{ .id = KIRKWOOD_CPU_TO_L2, .name = "l2clk", },
 	{ .id = KIRKWOOD_CPU_TO_DDR, .name = "ddrclk", }
 };
@@ -90,7 +90,7 @@ static u32 __init kirkwood_get_tclk_freq(void __iomem *sar)
 	return (opt) ? 166666667 : 200000000;
 }
 
-static const u32 __initconst kirkwood_cpu_freqs[] = {
+static const u32 kirkwood_cpu_freqs[] __initconst = {
 	0, 0, 0, 0,
 	600000000,
 	0,
@@ -111,12 +111,12 @@ static u32 __init kirkwood_get_cpu_freq(void __iomem *sar)
 	return kirkwood_cpu_freqs[opt];
 }
 
-static const int __initconst kirkwood_cpu_l2_ratios[8][2] = {
+static const int kirkwood_cpu_l2_ratios[8][2] __initconst = {
 	{ 0, 1 }, { 1, 2 }, { 0, 1 }, { 1, 3 },
 	{ 0, 1 }, { 1, 4 }, { 0, 1 }, { 0, 1 }
 };
 
-static const int __initconst kirkwood_cpu_ddr_ratios[16][2] = {
+static const int kirkwood_cpu_ddr_ratios[16][2] __initconst = {
 	{ 0, 1 }, { 0, 1 }, { 1, 2 }, { 0, 1 },
 	{ 1, 3 }, { 0, 1 }, { 1, 4 }, { 2, 9 },
 	{ 1, 5 }, { 1, 6 }, { 0, 1 }, { 0, 1 },
@@ -145,7 +145,7 @@ static void __init kirkwood_get_clk_ratio(
 	}
 }
 
-static const u32 __initconst mv88f6180_cpu_freqs[] = {
+static const u32 mv88f6180_cpu_freqs[] __initconst = {
 	0, 0, 0, 0, 0,
 	600000000,
 	800000000,
@@ -158,7 +158,7 @@ static u32 __init mv88f6180_get_cpu_freq(void __iomem *sar)
 	return mv88f6180_cpu_freqs[opt];
 }
 
-static const int __initconst mv88f6180_cpu_ddr_ratios[8][2] = {
+static const int mv88f6180_cpu_ddr_ratios[8][2] __initconst = {
 	{ 0, 1 }, { 0, 1 }, { 0, 1 }, { 0, 1 },
 	{ 0, 1 }, { 1, 3 }, { 1, 4 }, { 1, 5 }
 };
@@ -219,7 +219,7 @@ CLK_OF_DECLARE(mv88f6180_core_clk, "marvell,mv88f6180-core-clock",
  * Clock Gating Control
  */
 
-static const struct clk_gating_soc_desc __initconst kirkwood_gating_desc[] = {
+static const struct clk_gating_soc_desc kirkwood_gating_desc[] __initconst = {
 	{ "ge0", NULL, 0, 0 },
 	{ "pex0", NULL, 2, 0 },
 	{ "usb0", NULL, 3, 0 },
diff --git a/drivers/clk/mxs/clk-imx23.c b/drivers/clk/mxs/clk-imx23.c
index f6a74872f14e..c396fe361589 100644
--- a/drivers/clk/mxs/clk-imx23.c
+++ b/drivers/clk/mxs/clk-imx23.c
@@ -10,6 +10,7 @@
  */
 
 #include <linux/clk.h>
+#include <linux/clk/mxs.h>
 #include <linux/clkdev.h>
 #include <linux/err.h>
 #include <linux/init.h>
diff --git a/drivers/clk/mxs/clk.h b/drivers/clk/mxs/clk.h
index 81421e28e69c..ef10ad9b5daa 100644
--- a/drivers/clk/mxs/clk.h
+++ b/drivers/clk/mxs/clk.h
@@ -52,8 +52,8 @@ static inline struct clk *mxs_clk_mux(const char *name, void __iomem *reg,
 		u8 shift, u8 width, const char **parent_names, int num_parents)
 {
 	return clk_register_mux(NULL, name, parent_names, num_parents,
-				CLK_SET_RATE_PARENT, reg, shift, width,
-				0, &mxs_lock);
+				CLK_SET_RATE_PARENT | CLK_SET_RATE_NO_REPARENT,
+				reg, shift, width, 0, &mxs_lock);
 }
 
 static inline struct clk *mxs_clk_fixed_factor(const char *name,
diff --git a/drivers/clk/samsung/Makefile b/drivers/clk/samsung/Makefile
index 5d4d432cc4ac..3413380086d5 100644
--- a/drivers/clk/samsung/Makefile
+++ b/drivers/clk/samsung/Makefile
@@ -8,3 +8,6 @@ obj-$(CONFIG_SOC_EXYNOS5250)	+= clk-exynos5250.o
 obj-$(CONFIG_SOC_EXYNOS5420)	+= clk-exynos5420.o
 obj-$(CONFIG_SOC_EXYNOS5440)	+= clk-exynos5440.o
 obj-$(CONFIG_ARCH_EXYNOS)	+= clk-exynos-audss.o
+ifdef CONFIG_COMMON_CLK
+obj-$(CONFIG_ARCH_S3C64XX)	+= clk-s3c64xx.o
+endif
diff --git a/drivers/clk/samsung/clk-exynos-audss.c b/drivers/clk/samsung/clk-exynos-audss.c
index 9b1bbd52fd1f..39b40aaede2b 100644
--- a/drivers/clk/samsung/clk-exynos-audss.c
+++ b/drivers/clk/samsung/clk-exynos-audss.c
@@ -62,7 +62,7 @@ static struct syscore_ops exynos_audss_clk_syscore_ops = {
 #endif /* CONFIG_PM_SLEEP */
 
 /* register exynos_audss clocks */
-void __init exynos_audss_clk_init(struct device_node *np)
+static void __init exynos_audss_clk_init(struct device_node *np)
 {
 	reg_base = of_iomap(np, 0);
 	if (!reg_base) {
@@ -82,11 +82,13 @@ void __init exynos_audss_clk_init(struct device_node *np)
 	of_clk_add_provider(np, of_clk_src_onecell_get, &clk_data);
 
 	clk_table[EXYNOS_MOUT_AUDSS] = clk_register_mux(NULL, "mout_audss",
-				mout_audss_p, ARRAY_SIZE(mout_audss_p), 0,
+				mout_audss_p, ARRAY_SIZE(mout_audss_p),
+				CLK_SET_RATE_NO_REPARENT,
 				reg_base + ASS_CLK_SRC, 0, 1, 0, &lock);
 
 	clk_table[EXYNOS_MOUT_I2S] = clk_register_mux(NULL, "mout_i2s",
-				mout_i2s_p, ARRAY_SIZE(mout_i2s_p), 0,
+				mout_i2s_p, ARRAY_SIZE(mout_i2s_p),
+				CLK_SET_RATE_NO_REPARENT,
 				reg_base + ASS_CLK_SRC, 2, 2, 0, &lock);
 
 	clk_table[EXYNOS_DOUT_SRP] = clk_register_divider(NULL, "dout_srp",
diff --git a/drivers/clk/samsung/clk-exynos4.c b/drivers/clk/samsung/clk-exynos4.c
index 4e5739773c33..ad5ff50c5f28 100644
--- a/drivers/clk/samsung/clk-exynos4.c
+++ b/drivers/clk/samsung/clk-exynos4.c
@@ -17,7 +17,6 @@
 #include <linux/of_address.h>
 
 #include "clk.h"
-#include "clk-pll.h"
 
 /* Exynos4 clock controller register offsets */
 #define SRC_LEFTBUS		0x4200
@@ -97,12 +96,15 @@
 #define GATE_IP_PERIL		0xc950
 #define E4210_GATE_IP_PERIR	0xc960
 #define GATE_BLOCK		0xc970
+#define E4X12_MPLL_LOCK		0x10008
 #define E4X12_MPLL_CON0		0x10108
 #define SRC_DMC			0x10200
 #define SRC_MASK_DMC		0x10300
 #define DIV_DMC0		0x10500
 #define DIV_DMC1		0x10504
 #define GATE_IP_DMC		0x10900
+#define APLL_LOCK		0x14000
+#define E4210_MPLL_LOCK		0x14008
 #define APLL_CON0		0x14100
 #define E4210_MPLL_CON0		0x14108
 #define SRC_CPU			0x14200
@@ -121,6 +123,12 @@ enum exynos4_soc {
 	EXYNOS4X12,
 };
 
+/* list of PLLs to be registered */
+enum exynos4_plls {
+	apll, mpll, epll, vpll,
+	nr_plls			/* number of PLLs */
+};
+
 /*
  * Let each supported clock get a unique id. This id is used to lookup the clock
  * for device tree based platforms. The clocks are categorized into three
@@ -169,7 +177,7 @@ enum exynos4_clks {
 	gicisp, smmu_isp, smmu_drc, smmu_fd, smmu_lite0, smmu_lite1, mcuctl_isp,
 	mpwm_isp, i2c0_isp, i2c1_isp, mtcadc_isp, pwm_isp, wdt_isp, uart_isp,
 	asyncaxim, smmu_ispcx, spi0_isp, spi1_isp, pwm_isp_sclk, spi0_isp_sclk,
-	spi1_isp_sclk, uart_isp_sclk,
+	spi1_isp_sclk, uart_isp_sclk, tmu_apbif,
 
 	/* mux clocks */
 	mout_fimc0 = 384, mout_fimc1, mout_fimc2, mout_fimc3, mout_cam0,
@@ -187,7 +195,7 @@ enum exynos4_clks {
  * list of controller registers to be saved and restored during a
  * suspend/resume cycle.
  */
-static __initdata unsigned long exynos4210_clk_save[] = {
+static unsigned long exynos4210_clk_save[] __initdata = {
 	E4210_SRC_IMAGE,
 	E4210_SRC_LCD1,
 	E4210_SRC_MASK_LCD1,
@@ -198,7 +206,7 @@ static __initdata unsigned long exynos4210_clk_save[] = {
 	E4210_MPLL_CON0,
 };
 
-static __initdata unsigned long exynos4x12_clk_save[] = {
+static unsigned long exynos4x12_clk_save[] __initdata = {
 	E4X12_GATE_IP_IMAGE,
 	E4X12_GATE_IP_PERIR,
 	E4X12_SRC_CAM1,
@@ -207,7 +215,7 @@ static __initdata unsigned long exynos4x12_clk_save[] = {
 	E4X12_MPLL_CON0,
 };
 
-static __initdata unsigned long exynos4_clk_regs[] = {
+static unsigned long exynos4_clk_regs[] __initdata = {
 	SRC_LEFTBUS,
 	DIV_LEFTBUS,
 	GATE_IP_LEFTBUS,
@@ -338,24 +346,24 @@ PNAME(mout_user_aclk200_p4x12) = {"fin_pll", "div_aclk200", };
 PNAME(mout_user_aclk266_gps_p4x12) = {"fin_pll", "div_aclk266_gps", };
 
 /* fixed rate clocks generated outside the soc */
-struct samsung_fixed_rate_clock exynos4_fixed_rate_ext_clks[] __initdata = {
+static struct samsung_fixed_rate_clock exynos4_fixed_rate_ext_clks[] __initdata = {
 	FRATE(xxti, "xxti", NULL, CLK_IS_ROOT, 0),
 	FRATE(xusbxti, "xusbxti", NULL, CLK_IS_ROOT, 0),
 };
 
 /* fixed rate clocks generated inside the soc */
-struct samsung_fixed_rate_clock exynos4_fixed_rate_clks[] __initdata = {
+static struct samsung_fixed_rate_clock exynos4_fixed_rate_clks[] __initdata = {
 	FRATE(none, "sclk_hdmi24m", NULL, CLK_IS_ROOT, 24000000),
 	FRATE(none, "sclk_hdmiphy", NULL, CLK_IS_ROOT, 27000000),
 	FRATE(none, "sclk_usbphy0", NULL, CLK_IS_ROOT, 48000000),
 };
 
-struct samsung_fixed_rate_clock exynos4210_fixed_rate_clks[] __initdata = {
+static struct samsung_fixed_rate_clock exynos4210_fixed_rate_clks[] __initdata = {
 	FRATE(none, "sclk_usbphy1", NULL, CLK_IS_ROOT, 48000000),
 };
 
 /* list of mux clocks supported in all exynos4 soc's */
-struct samsung_mux_clock exynos4_mux_clks[] __initdata = {
+static struct samsung_mux_clock exynos4_mux_clks[] __initdata = {
 	MUX_FA(mout_apll, "mout_apll", mout_apll_p, SRC_CPU, 0, 1,
 			CLK_SET_RATE_PARENT, 0, "mout_apll"),
 	MUX(none, "mout_hdmi", mout_hdmi_p, SRC_TV, 0, 1),
@@ -367,17 +375,20 @@ struct samsung_mux_clock exynos4_mux_clks[] __initdata = {
 			CLK_SET_RATE_PARENT, 0),
 	MUX(none, "mout_spdif", mout_spdif_p, SRC_PERIL1, 8, 2),
 	MUX(none, "mout_onenand1", mout_onenand1_p, SRC_TOP0, 0, 1),
-	MUX_A(sclk_epll, "sclk_epll", mout_epll_p, SRC_TOP0, 4, 1, "sclk_epll"),
+	MUX(sclk_epll, "sclk_epll", mout_epll_p, SRC_TOP0, 4, 1),
 	MUX(none, "mout_onenand", mout_onenand_p, SRC_TOP0, 28, 1),
 };
 
 /* list of mux clocks supported in exynos4210 soc */
-struct samsung_mux_clock exynos4210_mux_clks[] __initdata = {
+static struct samsung_mux_clock exynos4210_mux_early[] __initdata = {
+	MUX(none, "mout_vpllsrc", mout_vpllsrc_p, SRC_TOP1, 0, 1),
+};
+
+static struct samsung_mux_clock exynos4210_mux_clks[] __initdata = {
 	MUX(none, "mout_aclk200", sclk_ampll_p4210, SRC_TOP0, 12, 1),
 	MUX(none, "mout_aclk100", sclk_ampll_p4210, SRC_TOP0, 16, 1),
 	MUX(none, "mout_aclk160", sclk_ampll_p4210, SRC_TOP0, 20, 1),
 	MUX(none, "mout_aclk133", sclk_ampll_p4210, SRC_TOP0, 24, 1),
-	MUX(none, "mout_vpllsrc", mout_vpllsrc_p, SRC_TOP1, 0, 1),
 	MUX(none, "mout_mixer", mout_mixer_p4210, SRC_TV, 4, 1),
 	MUX(none, "mout_dac", mout_dac_p4210, SRC_TV, 8, 1),
 	MUX(none, "mout_g2d0", sclk_ampll_p4210, E4210_SRC_IMAGE, 0, 1),
@@ -385,11 +396,9 @@ struct samsung_mux_clock exynos4210_mux_clks[] __initdata = {
 	MUX(none, "mout_g2d", mout_g2d_p, E4210_SRC_IMAGE, 8, 1),
 	MUX(none, "mout_fimd1", group1_p4210, E4210_SRC_LCD1, 0, 4),
 	MUX(none, "mout_mipi1", group1_p4210, E4210_SRC_LCD1, 12, 4),
-	MUX_A(sclk_mpll, "sclk_mpll", mout_mpll_p, SRC_CPU, 8, 1, "mout_mpll"),
-	MUX_A(mout_core, "mout_core", mout_core_p4210,
-			SRC_CPU, 16, 1, "moutcore"),
-	MUX_A(sclk_vpll, "sclk_vpll", sclk_vpll_p4210,
-			SRC_TOP0, 8, 1, "sclk_vpll"),
+	MUX(sclk_mpll, "sclk_mpll", mout_mpll_p, SRC_CPU, 8, 1),
+	MUX(mout_core, "mout_core", mout_core_p4210, SRC_CPU, 16, 1),
+	MUX(sclk_vpll, "sclk_vpll", sclk_vpll_p4210, SRC_TOP0, 8, 1),
 	MUX(mout_fimc0, "mout_fimc0", group1_p4210, SRC_CAM, 0, 4),
 	MUX(mout_fimc1, "mout_fimc1", group1_p4210, SRC_CAM, 4, 4),
 	MUX(mout_fimc2, "mout_fimc2", group1_p4210, SRC_CAM, 8, 4),
@@ -423,9 +432,9 @@ struct samsung_mux_clock exynos4210_mux_clks[] __initdata = {
 };
 
 /* list of mux clocks supported in exynos4x12 soc */
-struct samsung_mux_clock exynos4x12_mux_clks[] __initdata = {
-	MUX_A(mout_mpll_user_c, "mout_mpll_user_c", mout_mpll_user_p4x12,
-			SRC_CPU, 24, 1, "mout_mpll"),
+static struct samsung_mux_clock exynos4x12_mux_clks[] __initdata = {
+	MUX(mout_mpll_user_c, "mout_mpll_user_c", mout_mpll_user_p4x12,
+			SRC_CPU, 24, 1),
 	MUX(none, "mout_aclk266_gps", aclk_p4412, SRC_TOP1, 4, 1),
 	MUX(none, "mout_aclk400_mcuisp", aclk_p4412, SRC_TOP1, 8, 1),
 	MUX(mout_mpll_user_t, "mout_mpll_user_t", mout_mpll_user_p4x12,
@@ -445,12 +454,9 @@ struct samsung_mux_clock exynos4x12_mux_clks[] __initdata = {
 	MUX(none, "mout_jpeg0", sclk_ampll_p4x12, E4X12_SRC_CAM1, 0, 1),
 	MUX(none, "mout_jpeg1", sclk_evpll_p, E4X12_SRC_CAM1, 4, 1),
 	MUX(none, "mout_jpeg", mout_jpeg_p, E4X12_SRC_CAM1, 8, 1),
-	MUX_A(sclk_mpll, "sclk_mpll", mout_mpll_p,
-			SRC_DMC, 12, 1, "sclk_mpll"),
-	MUX_A(sclk_vpll, "sclk_vpll", mout_vpll_p,
-			SRC_TOP0, 8, 1, "sclk_vpll"),
-	MUX_A(mout_core, "mout_core", mout_core_p4x12,
-			SRC_CPU, 16, 1, "moutcore"),
+	MUX(sclk_mpll, "sclk_mpll", mout_mpll_p, SRC_DMC, 12, 1),
+	MUX(sclk_vpll, "sclk_vpll", mout_vpll_p, SRC_TOP0, 8, 1),
+	MUX(mout_core, "mout_core", mout_core_p4x12, SRC_CPU, 16, 1),
 	MUX(mout_fimc0, "mout_fimc0", group1_p4x12, SRC_CAM, 0, 4),
 	MUX(mout_fimc1, "mout_fimc1", group1_p4x12, SRC_CAM, 4, 4),
 	MUX(mout_fimc2, "mout_fimc2", group1_p4x12, SRC_CAM, 8, 4),
@@ -491,7 +497,7 @@ struct samsung_mux_clock exynos4x12_mux_clks[] __initdata = {
 };
 
 /* list of divider clocks supported in all exynos4 soc's */
-struct samsung_div_clock exynos4_div_clks[] __initdata = {
+static struct samsung_div_clock exynos4_div_clks[] __initdata = {
 	DIV(none, "div_core", "mout_core", DIV_CPU0, 0, 3),
 	DIV(none, "div_core2", "div_core", DIV_CPU0, 28, 3),
 	DIV(none, "div_fimc0", "mout_fimc0", DIV_CAM, 0, 4),
@@ -538,9 +544,8 @@ struct samsung_div_clock exynos4_div_clks[] __initdata = {
 	DIV(none, "div_spi_pre2", "div_spi2", DIV_PERIL2, 8, 8),
 	DIV(none, "div_audio1", "mout_audio1", DIV_PERIL4, 0, 4),
 	DIV(none, "div_audio2", "mout_audio2", DIV_PERIL4, 16, 4),
-	DIV_A(arm_clk, "arm_clk", "div_core2", DIV_CPU0, 28, 3, "armclk"),
-	DIV_A(sclk_apll, "sclk_apll", "mout_apll",
-			DIV_CPU0, 24, 3, "sclk_apll"),
+	DIV(arm_clk, "arm_clk", "div_core2", DIV_CPU0, 28, 3),
+	DIV(sclk_apll, "sclk_apll", "mout_apll", DIV_CPU0, 24, 3),
 	DIV_F(none, "div_mipi_pre0", "div_mipi0", DIV_LCD0, 20, 4,
 			CLK_SET_RATE_PARENT, 0),
 	DIV_F(none, "div_mmc_pre0", "div_mmc0", DIV_FSYS1, 8, 8,
@@ -554,7 +559,7 @@ struct samsung_div_clock exynos4_div_clks[] __initdata = {
 };
 
 /* list of divider clocks supported in exynos4210 soc */
-struct samsung_div_clock exynos4210_div_clks[] __initdata = {
+static struct samsung_div_clock exynos4210_div_clks[] __initdata = {
 	DIV(aclk200, "aclk200", "mout_aclk200", DIV_TOP, 0, 3),
 	DIV(sclk_fimg2d, "sclk_fimg2d", "mout_g2d", DIV_IMAGE, 0, 4),
 	DIV(none, "div_fimd1", "mout_fimd1", E4210_DIV_LCD1, 0, 4),
@@ -565,7 +570,7 @@ struct samsung_div_clock exynos4210_div_clks[] __initdata = {
 };
 
 /* list of divider clocks supported in exynos4x12 soc */
-struct samsung_div_clock exynos4x12_div_clks[] __initdata = {
+static struct samsung_div_clock exynos4x12_div_clks[] __initdata = {
 	DIV(none, "div_mdnie0", "mout_mdnie0", DIV_LCD0, 4, 4),
 	DIV(none, "div_mdnie_pwm0", "mout_mdnie_pwm0", DIV_LCD0, 8, 4),
 	DIV(none, "div_mdnie_pwm_pre0", "div_mdnie_pwm0", DIV_LCD0, 12, 4),
@@ -594,7 +599,7 @@ struct samsung_div_clock exynos4x12_div_clks[] __initdata = {
 };
 
 /* list of gate clocks supported in all exynos4 soc's */
-struct samsung_gate_clock exynos4_gate_clks[] __initdata = {
+static struct samsung_gate_clock exynos4_gate_clks[] __initdata = {
 	/*
 	 * After all Exynos4 based platforms are migrated to use device tree,
 	 * the device name and clock alias names specified below for some
@@ -629,164 +634,151 @@ struct samsung_gate_clock exynos4_gate_clks[] __initdata = {
 			CLK_SET_RATE_PARENT, 0),
 	GATE(sclk_audio1, "sclk_audio1", "div_audio1", SRC_MASK_PERIL1, 0,
 			CLK_SET_RATE_PARENT, 0),
-	GATE_D(vp, "s5p-mixer", "vp", "aclk160", GATE_IP_TV, 0, 0, 0),
-	GATE_D(mixer, "s5p-mixer", "mixer", "aclk160", GATE_IP_TV, 1, 0, 0),
-	GATE_D(hdmi, "exynos4-hdmi", "hdmi", "aclk160", GATE_IP_TV, 3, 0, 0),
-	GATE_A(pwm, "pwm", "aclk100", GATE_IP_PERIL, 24, 0, 0, "timers"),
-	GATE_A(sdmmc4, "sdmmc4", "aclk133", GATE_IP_FSYS, 9, 0, 0, "biu"),
-	GATE_A(usb_host, "usb_host", "aclk133",
-			GATE_IP_FSYS, 12, 0, 0, "usbhost"),
-	GATE_DA(sclk_fimc0, "exynos4-fimc.0", "sclk_fimc0", "div_fimc0",
-			SRC_MASK_CAM, 0, CLK_SET_RATE_PARENT, 0, "sclk_fimc"),
-	GATE_DA(sclk_fimc1, "exynos4-fimc.1", "sclk_fimc1", "div_fimc1",
-			SRC_MASK_CAM, 4, CLK_SET_RATE_PARENT, 0, "sclk_fimc"),
-	GATE_DA(sclk_fimc2, "exynos4-fimc.2", "sclk_fimc2", "div_fimc2",
-			SRC_MASK_CAM, 8, CLK_SET_RATE_PARENT, 0, "sclk_fimc"),
-	GATE_DA(sclk_fimc3, "exynos4-fimc.3", "sclk_fimc3", "div_fimc3",
-			SRC_MASK_CAM, 12, CLK_SET_RATE_PARENT, 0, "sclk_fimc"),
-	GATE_DA(sclk_csis0, "s5p-mipi-csis.0", "sclk_csis0", "div_csis0",
-			SRC_MASK_CAM, 24, CLK_SET_RATE_PARENT, 0, "sclk_csis"),
-	GATE_DA(sclk_csis1, "s5p-mipi-csis.1", "sclk_csis1", "div_csis1",
-			SRC_MASK_CAM, 28, CLK_SET_RATE_PARENT, 0, "sclk_csis"),
-	GATE_DA(sclk_fimd0, "exynos4-fb.0", "sclk_fimd0", "div_fimd0",
-			SRC_MASK_LCD0, 0, CLK_SET_RATE_PARENT, 0, "sclk_fimd"),
-	GATE_DA(sclk_mmc0, "exynos4-sdhci.0", "sclk_mmc0", "div_mmc_pre0",
-			SRC_MASK_FSYS, 0, CLK_SET_RATE_PARENT, 0,
-			"mmc_busclk.2"),
-	GATE_DA(sclk_mmc1, "exynos4-sdhci.1", "sclk_mmc1", "div_mmc_pre1",
-			SRC_MASK_FSYS, 4, CLK_SET_RATE_PARENT, 0,
-			"mmc_busclk.2"),
-	GATE_DA(sclk_mmc2, "exynos4-sdhci.2", "sclk_mmc2", "div_mmc_pre2",
-			SRC_MASK_FSYS, 8, CLK_SET_RATE_PARENT, 0,
-			"mmc_busclk.2"),
-	GATE_DA(sclk_mmc3, "exynos4-sdhci.3", "sclk_mmc3", "div_mmc_pre3",
-			SRC_MASK_FSYS, 12, CLK_SET_RATE_PARENT, 0,
-			"mmc_busclk.2"),
-	GATE_DA(sclk_mmc4, NULL, "sclk_mmc4", "div_mmc_pre4",
-			SRC_MASK_FSYS, 16, CLK_SET_RATE_PARENT, 0, "ciu"),
-	GATE_DA(sclk_uart0, "exynos4210-uart.0", "uclk0", "div_uart0",
-			SRC_MASK_PERIL0, 0, CLK_SET_RATE_PARENT,
-			0, "clk_uart_baud0"),
-	GATE_DA(sclk_uart1, "exynos4210-uart.1", "uclk1", "div_uart1",
-			SRC_MASK_PERIL0, 4, CLK_SET_RATE_PARENT,
-			0, "clk_uart_baud0"),
-	GATE_DA(sclk_uart2, "exynos4210-uart.2", "uclk2", "div_uart2",
-			SRC_MASK_PERIL0, 8, CLK_SET_RATE_PARENT,
-			0, "clk_uart_baud0"),
-	GATE_DA(sclk_uart3, "exynos4210-uart.3", "uclk3", "div_uart3",
-			SRC_MASK_PERIL0, 12, CLK_SET_RATE_PARENT,
-			0, "clk_uart_baud0"),
-	GATE_DA(sclk_uart4, "exynos4210-uart.4", "uclk4", "div_uart4",
-			SRC_MASK_PERIL0, 16, CLK_SET_RATE_PARENT,
-			0, "clk_uart_baud0"),
+	GATE(vp, "vp", "aclk160", GATE_IP_TV, 0, 0, 0),
+	GATE(mixer, "mixer", "aclk160", GATE_IP_TV, 1, 0, 0),
+	GATE(hdmi, "hdmi", "aclk160", GATE_IP_TV, 3, 0, 0),
+	GATE(pwm, "pwm", "aclk100", GATE_IP_PERIL, 24, 0, 0),
+	GATE(sdmmc4, "sdmmc4", "aclk133", GATE_IP_FSYS, 9, 0, 0),
+	GATE(usb_host, "usb_host", "aclk133", GATE_IP_FSYS, 12, 0, 0),
+	GATE(sclk_fimc0, "sclk_fimc0", "div_fimc0", SRC_MASK_CAM, 0,
+			CLK_SET_RATE_PARENT, 0),
+	GATE(sclk_fimc1, "sclk_fimc1", "div_fimc1", SRC_MASK_CAM, 4,
+			CLK_SET_RATE_PARENT, 0),
+	GATE(sclk_fimc2, "sclk_fimc2", "div_fimc2", SRC_MASK_CAM, 8,
+			CLK_SET_RATE_PARENT, 0),
+	GATE(sclk_fimc3, "sclk_fimc3", "div_fimc3", SRC_MASK_CAM, 12,
+			CLK_SET_RATE_PARENT, 0),
+	GATE(sclk_csis0, "sclk_csis0", "div_csis0", SRC_MASK_CAM, 24,
+			CLK_SET_RATE_PARENT, 0),
+	GATE(sclk_csis1, "sclk_csis1", "div_csis1", SRC_MASK_CAM, 28,
+			CLK_SET_RATE_PARENT, 0),
+	GATE(sclk_fimd0, "sclk_fimd0", "div_fimd0", SRC_MASK_LCD0, 0,
+			CLK_SET_RATE_PARENT, 0),
+	GATE(sclk_mmc0, "sclk_mmc0", "div_mmc_pre0", SRC_MASK_FSYS, 0,
+			CLK_SET_RATE_PARENT, 0),
+	GATE(sclk_mmc1, "sclk_mmc1", "div_mmc_pre1", SRC_MASK_FSYS, 4,
+			CLK_SET_RATE_PARENT, 0),
+	GATE(sclk_mmc2, "sclk_mmc2", "div_mmc_pre2", SRC_MASK_FSYS, 8,
+			CLK_SET_RATE_PARENT, 0),
+	GATE(sclk_mmc3, "sclk_mmc3", "div_mmc_pre3", SRC_MASK_FSYS, 12,
+			CLK_SET_RATE_PARENT, 0),
+	GATE(sclk_mmc4, "sclk_mmc4", "div_mmc_pre4", SRC_MASK_FSYS, 16,
+			CLK_SET_RATE_PARENT, 0),
+	GATE(sclk_uart0, "uclk0", "div_uart0", SRC_MASK_PERIL0, 0,
+			CLK_SET_RATE_PARENT, 0),
+	GATE(sclk_uart1, "uclk1", "div_uart1", SRC_MASK_PERIL0, 4,
+			CLK_SET_RATE_PARENT, 0),
+	GATE(sclk_uart2, "uclk2", "div_uart2", SRC_MASK_PERIL0, 8,
+			CLK_SET_RATE_PARENT, 0),
+	GATE(sclk_uart3, "uclk3", "div_uart3", SRC_MASK_PERIL0, 12,
+			CLK_SET_RATE_PARENT, 0),
+	GATE(sclk_uart4, "uclk4", "div_uart4", SRC_MASK_PERIL0, 16,
+			CLK_SET_RATE_PARENT, 0),
 	GATE(sclk_audio2, "sclk_audio2", "div_audio2", SRC_MASK_PERIL1, 4,
 			CLK_SET_RATE_PARENT, 0),
-	GATE_DA(sclk_spi0, "exynos4210-spi.0", "sclk_spi0", "div_spi_pre0",
-			SRC_MASK_PERIL1, 16, CLK_SET_RATE_PARENT,
-			0, "spi_busclk0"),
-	GATE_DA(sclk_spi1, "exynos4210-spi.1", "sclk_spi1", "div_spi_pre1",
-			SRC_MASK_PERIL1, 20, CLK_SET_RATE_PARENT,
-			0, "spi_busclk0"),
-	GATE_DA(sclk_spi2, "exynos4210-spi.2", "sclk_spi2", "div_spi_pre2",
-			SRC_MASK_PERIL1, 24, CLK_SET_RATE_PARENT,
-			0, "spi_busclk0"),
-	GATE_DA(fimc0, "exynos4-fimc.0", "fimc0", "aclk160",
-			GATE_IP_CAM, 0, 0, 0, "fimc"),
-	GATE_DA(fimc1, "exynos4-fimc.1", "fimc1", "aclk160",
-			GATE_IP_CAM, 1, 0, 0, "fimc"),
-	GATE_DA(fimc2, "exynos4-fimc.2", "fimc2", "aclk160",
-			GATE_IP_CAM, 2, 0, 0, "fimc"),
-	GATE_DA(fimc3, "exynos4-fimc.3", "fimc3", "aclk160",
-			GATE_IP_CAM, 3, 0, 0, "fimc"),
-	GATE_DA(csis0, "s5p-mipi-csis.0", "csis0", "aclk160",
-			GATE_IP_CAM, 4, 0, 0, "fimc"),
-	GATE_DA(csis1, "s5p-mipi-csis.1", "csis1", "aclk160",
-			GATE_IP_CAM, 5, 0, 0, "fimc"),
-	GATE_DA(smmu_fimc0, "exynos-sysmmu.5", "smmu_fimc0", "aclk160",
-			GATE_IP_CAM, 7, 0, 0, "sysmmu"),
-	GATE_DA(smmu_fimc1, "exynos-sysmmu.6", "smmu_fimc1", "aclk160",
-			GATE_IP_CAM, 8, 0, 0, "sysmmu"),
-	GATE_DA(smmu_fimc2, "exynos-sysmmu.7", "smmu_fimc2", "aclk160",
-			GATE_IP_CAM, 9, 0, 0, "sysmmu"),
-	GATE_DA(smmu_fimc3, "exynos-sysmmu.8", "smmu_fimc3", "aclk160",
-			GATE_IP_CAM, 10, 0, 0, "sysmmu"),
-	GATE_DA(smmu_jpeg, "exynos-sysmmu.3", "smmu_jpeg", "aclk160",
-			GATE_IP_CAM, 11, 0, 0, "sysmmu"),
+	GATE(sclk_spi0, "sclk_spi0", "div_spi_pre0", SRC_MASK_PERIL1, 16,
+			CLK_SET_RATE_PARENT, 0),
+	GATE(sclk_spi1, "sclk_spi1", "div_spi_pre1", SRC_MASK_PERIL1, 20,
+			CLK_SET_RATE_PARENT, 0),
+	GATE(sclk_spi2, "sclk_spi2", "div_spi_pre2", SRC_MASK_PERIL1, 24,
+			CLK_SET_RATE_PARENT, 0),
+	GATE(fimc0, "fimc0", "aclk160", GATE_IP_CAM, 0,
+			0, 0),
+	GATE(fimc1, "fimc1", "aclk160", GATE_IP_CAM, 1,
+			0, 0),
+	GATE(fimc2, "fimc2", "aclk160", GATE_IP_CAM, 2,
+			0, 0),
+	GATE(fimc3, "fimc3", "aclk160", GATE_IP_CAM, 3,
+			0, 0),
+	GATE(csis0, "csis0", "aclk160", GATE_IP_CAM, 4,
+			0, 0),
+	GATE(csis1, "csis1", "aclk160", GATE_IP_CAM, 5,
+			0, 0),
+	GATE(smmu_fimc0, "smmu_fimc0", "aclk160", GATE_IP_CAM, 7,
+			0, 0),
+	GATE(smmu_fimc1, "smmu_fimc1", "aclk160", GATE_IP_CAM, 8,
+			0, 0),
+	GATE(smmu_fimc2, "smmu_fimc2", "aclk160", GATE_IP_CAM, 9,
+			0, 0),
+	GATE(smmu_fimc3, "smmu_fimc3", "aclk160", GATE_IP_CAM, 10,
+			0, 0),
+	GATE(smmu_jpeg, "smmu_jpeg", "aclk160", GATE_IP_CAM, 11,
+			0, 0),
 	GATE(pixelasyncm0, "pxl_async0", "aclk160", GATE_IP_CAM, 17, 0, 0),
 	GATE(pixelasyncm1, "pxl_async1", "aclk160", GATE_IP_CAM, 18, 0, 0),
-	GATE_DA(smmu_tv, "exynos-sysmmu.2", "smmu_tv", "aclk160",
-			GATE_IP_TV, 4, 0, 0, "sysmmu"),
-	GATE_DA(mfc, "s5p-mfc", "mfc", "aclk100", GATE_IP_MFC, 0, 0, 0, "mfc"),
-	GATE_DA(smmu_mfcl, "exynos-sysmmu.0", "smmu_mfcl", "aclk100",
-			GATE_IP_MFC, 1, 0, 0, "sysmmu"),
-	GATE_DA(smmu_mfcr, "exynos-sysmmu.1", "smmu_mfcr", "aclk100",
-			GATE_IP_MFC, 2, 0, 0, "sysmmu"),
-	GATE_DA(fimd0, "exynos4-fb.0", "fimd0", "aclk160",
-			GATE_IP_LCD0, 0, 0, 0, "fimd"),
-	GATE_DA(smmu_fimd0, "exynos-sysmmu.10", "smmu_fimd0", "aclk160",
-			GATE_IP_LCD0, 4, 0, 0, "sysmmu"),
-	GATE_DA(pdma0, "dma-pl330.0", "pdma0", "aclk133",
-			GATE_IP_FSYS, 0, 0, 0, "dma"),
-	GATE_DA(pdma1, "dma-pl330.1", "pdma1", "aclk133",
-			GATE_IP_FSYS, 1, 0, 0, "dma"),
-	GATE_DA(sdmmc0, "exynos4-sdhci.0", "sdmmc0", "aclk133",
-			GATE_IP_FSYS, 5, 0, 0, "hsmmc"),
-	GATE_DA(sdmmc1, "exynos4-sdhci.1", "sdmmc1", "aclk133",
-			GATE_IP_FSYS, 6, 0, 0, "hsmmc"),
-	GATE_DA(sdmmc2, "exynos4-sdhci.2", "sdmmc2", "aclk133",
-			GATE_IP_FSYS, 7, 0, 0, "hsmmc"),
-	GATE_DA(sdmmc3, "exynos4-sdhci.3", "sdmmc3", "aclk133",
-			GATE_IP_FSYS, 8, 0, 0, "hsmmc"),
-	GATE_DA(uart0, "exynos4210-uart.0", "uart0", "aclk100",
-			GATE_IP_PERIL, 0, 0, 0, "uart"),
-	GATE_DA(uart1, "exynos4210-uart.1", "uart1", "aclk100",
-			GATE_IP_PERIL, 1, 0, 0, "uart"),
-	GATE_DA(uart2, "exynos4210-uart.2", "uart2", "aclk100",
-			GATE_IP_PERIL, 2, 0, 0, "uart"),
-	GATE_DA(uart3, "exynos4210-uart.3", "uart3", "aclk100",
-			GATE_IP_PERIL, 3, 0, 0, "uart"),
-	GATE_DA(uart4, "exynos4210-uart.4", "uart4", "aclk100",
-			GATE_IP_PERIL, 4, 0, 0, "uart"),
-	GATE_DA(i2c0, "s3c2440-i2c.0", "i2c0", "aclk100",
-			GATE_IP_PERIL, 6, 0, 0, "i2c"),
-	GATE_DA(i2c1, "s3c2440-i2c.1", "i2c1", "aclk100",
-			GATE_IP_PERIL, 7, 0, 0, "i2c"),
-	GATE_DA(i2c2, "s3c2440-i2c.2", "i2c2", "aclk100",
-			GATE_IP_PERIL, 8, 0, 0, "i2c"),
-	GATE_DA(i2c3, "s3c2440-i2c.3", "i2c3", "aclk100",
-			GATE_IP_PERIL, 9, 0, 0, "i2c"),
-	GATE_DA(i2c4, "s3c2440-i2c.4", "i2c4", "aclk100",
-			GATE_IP_PERIL, 10, 0, 0, "i2c"),
-	GATE_DA(i2c5, "s3c2440-i2c.5", "i2c5", "aclk100",
-			GATE_IP_PERIL, 11, 0, 0, "i2c"),
-	GATE_DA(i2c6, "s3c2440-i2c.6", "i2c6", "aclk100",
-			GATE_IP_PERIL, 12, 0, 0, "i2c"),
-	GATE_DA(i2c7, "s3c2440-i2c.7", "i2c7", "aclk100",
-			GATE_IP_PERIL, 13, 0, 0, "i2c"),
-	GATE_DA(i2c_hdmi, "s3c2440-hdmiphy-i2c", "i2c-hdmi", "aclk100",
-			GATE_IP_PERIL, 14, 0, 0, "i2c"),
-	GATE_DA(spi0, "exynos4210-spi.0", "spi0", "aclk100",
-			GATE_IP_PERIL, 16, 0, 0, "spi"),
-	GATE_DA(spi1, "exynos4210-spi.1", "spi1", "aclk100",
-			GATE_IP_PERIL, 17, 0, 0, "spi"),
-	GATE_DA(spi2, "exynos4210-spi.2", "spi2", "aclk100",
-			GATE_IP_PERIL, 18, 0, 0, "spi"),
-	GATE_DA(i2s1, "samsung-i2s.1", "i2s1", "aclk100",
-			GATE_IP_PERIL, 20, 0, 0, "iis"),
-	GATE_DA(i2s2, "samsung-i2s.2", "i2s2", "aclk100",
-			GATE_IP_PERIL, 21, 0, 0, "iis"),
-	GATE_DA(pcm1, "samsung-pcm.1", "pcm1", "aclk100",
-			GATE_IP_PERIL, 22, 0, 0, "pcm"),
-	GATE_DA(pcm2, "samsung-pcm.2", "pcm2", "aclk100",
-			GATE_IP_PERIL, 23, 0, 0, "pcm"),
-	GATE_DA(spdif, "samsung-spdif", "spdif", "aclk100",
-			GATE_IP_PERIL, 26, 0, 0, "spdif"),
-	GATE_DA(ac97, "samsung-ac97", "ac97", "aclk100",
-			GATE_IP_PERIL, 27, 0, 0, "ac97"),
+	GATE(smmu_tv, "smmu_tv", "aclk160", GATE_IP_TV, 4,
+			0, 0),
+	GATE(mfc, "mfc", "aclk100", GATE_IP_MFC, 0, 0, 0),
+	GATE(smmu_mfcl, "smmu_mfcl", "aclk100", GATE_IP_MFC, 1,
+			0, 0),
+	GATE(smmu_mfcr, "smmu_mfcr", "aclk100", GATE_IP_MFC, 2,
+			0, 0),
+	GATE(fimd0, "fimd0", "aclk160", GATE_IP_LCD0, 0,
+			0, 0),
+	GATE(smmu_fimd0, "smmu_fimd0", "aclk160", GATE_IP_LCD0, 4,
+			0, 0),
+	GATE(pdma0, "pdma0", "aclk133", GATE_IP_FSYS, 0,
+			0, 0),
+	GATE(pdma1, "pdma1", "aclk133", GATE_IP_FSYS, 1,
+			0, 0),
+	GATE(sdmmc0, "sdmmc0", "aclk133", GATE_IP_FSYS, 5,
+			0, 0),
+	GATE(sdmmc1, "sdmmc1", "aclk133", GATE_IP_FSYS, 6,
+			0, 0),
+	GATE(sdmmc2, "sdmmc2", "aclk133", GATE_IP_FSYS, 7,
+			0, 0),
+	GATE(sdmmc3, "sdmmc3", "aclk133", GATE_IP_FSYS, 8,
+			0, 0),
+	GATE(uart0, "uart0", "aclk100", GATE_IP_PERIL, 0,
+			0, 0),
+	GATE(uart1, "uart1", "aclk100", GATE_IP_PERIL, 1,
+			0, 0),
+	GATE(uart2, "uart2", "aclk100", GATE_IP_PERIL, 2,
+			0, 0),
+	GATE(uart3, "uart3", "aclk100", GATE_IP_PERIL, 3,
+			0, 0),
+	GATE(uart4, "uart4", "aclk100", GATE_IP_PERIL, 4,
+			0, 0),
+	GATE(i2c0, "i2c0", "aclk100", GATE_IP_PERIL, 6,
+			0, 0),
+	GATE(i2c1, "i2c1", "aclk100", GATE_IP_PERIL, 7,
+			0, 0),
+	GATE(i2c2, "i2c2", "aclk100", GATE_IP_PERIL, 8,
+			0, 0),
+	GATE(i2c3, "i2c3", "aclk100", GATE_IP_PERIL, 9,
+			0, 0),
+	GATE(i2c4, "i2c4", "aclk100", GATE_IP_PERIL, 10,
+			0, 0),
+	GATE(i2c5, "i2c5", "aclk100", GATE_IP_PERIL, 11,
+			0, 0),
+	GATE(i2c6, "i2c6", "aclk100", GATE_IP_PERIL, 12,
+			0, 0),
+	GATE(i2c7, "i2c7", "aclk100", GATE_IP_PERIL, 13,
+			0, 0),
+	GATE(i2c_hdmi, "i2c-hdmi", "aclk100", GATE_IP_PERIL, 14,
+			0, 0),
+	GATE(spi0, "spi0", "aclk100", GATE_IP_PERIL, 16,
+			0, 0),
+	GATE(spi1, "spi1", "aclk100", GATE_IP_PERIL, 17,
+			0, 0),
+	GATE(spi2, "spi2", "aclk100", GATE_IP_PERIL, 18,
+			0, 0),
+	GATE(i2s1, "i2s1", "aclk100", GATE_IP_PERIL, 20,
+			0, 0),
+	GATE(i2s2, "i2s2", "aclk100", GATE_IP_PERIL, 21,
+			0, 0),
+	GATE(pcm1, "pcm1", "aclk100", GATE_IP_PERIL, 22,
+			0, 0),
+	GATE(pcm2, "pcm2", "aclk100", GATE_IP_PERIL, 23,
+			0, 0),
+	GATE(spdif, "spdif", "aclk100", GATE_IP_PERIL, 26,
+			0, 0),
+	GATE(ac97, "ac97", "aclk100", GATE_IP_PERIL, 27,
+			0, 0),
 };
 
 /* list of gate clocks supported in exynos4210 soc */
-struct samsung_gate_clock exynos4210_gate_clks[] __initdata = {
+static struct samsung_gate_clock exynos4210_gate_clks[] __initdata = {
 	GATE(tvenc, "tvenc", "aclk160", GATE_IP_TV, 2, 0, 0),
 	GATE(g2d, "g2d", "aclk200", E4210_GATE_IP_IMAGE, 0, 0, 0),
 	GATE(rotator, "rotator", "aclk200", E4210_GATE_IP_IMAGE, 1, 0, 0),
@@ -811,17 +803,23 @@ struct samsung_gate_clock exynos4210_gate_clks[] __initdata = {
 			SRC_MASK_FSYS, 24, CLK_SET_RATE_PARENT, 0),
 	GATE(sclk_mixer, "sclk_mixer", "mout_mixer", SRC_MASK_TV, 4, 0, 0),
 	GATE(sclk_dac, "sclk_dac", "mout_dac", SRC_MASK_TV, 8, 0, 0),
-	GATE_A(tsadc, "tsadc", "aclk100", GATE_IP_PERIL, 15, 0, 0, "adc"),
-	GATE_A(mct, "mct", "aclk100", E4210_GATE_IP_PERIR, 13, 0, 0, "mct"),
-	GATE_A(wdt, "watchdog", "aclk100", E4210_GATE_IP_PERIR, 14, 0, 0, "watchdog"),
-	GATE_A(rtc, "rtc", "aclk100", E4210_GATE_IP_PERIR, 15, 0, 0, "rtc"),
-	GATE_A(keyif, "keyif", "aclk100", E4210_GATE_IP_PERIR, 16, 0, 0, "keypad"),
-	GATE_DA(sclk_fimd1, "exynos4-fb.1", "sclk_fimd1", "div_fimd1",
-			E4210_SRC_MASK_LCD1, 0, CLK_SET_RATE_PARENT, 0, "sclk_fimd"),
+	GATE(tsadc, "tsadc", "aclk100", GATE_IP_PERIL, 15,
+			0, 0),
+	GATE(mct, "mct", "aclk100", E4210_GATE_IP_PERIR, 13,
+			0, 0),
+	GATE(wdt, "watchdog", "aclk100", E4210_GATE_IP_PERIR, 14,
+			0, 0),
+	GATE(rtc, "rtc", "aclk100", E4210_GATE_IP_PERIR, 15,
+			0, 0),
+	GATE(keyif, "keyif", "aclk100", E4210_GATE_IP_PERIR, 16,
+			0, 0),
+	GATE(sclk_fimd1, "sclk_fimd1", "div_fimd1", E4210_SRC_MASK_LCD1, 0,
+			CLK_SET_RATE_PARENT, 0),
+	GATE(tmu_apbif, "tmu_apbif", "aclk100", E4210_GATE_IP_PERIR, 17, 0, 0),
 };
 
 /* list of gate clocks supported in exynos4x12 soc */
-struct samsung_gate_clock exynos4x12_gate_clks[] __initdata = {
+static struct samsung_gate_clock exynos4x12_gate_clks[] __initdata = {
 	GATE(audss, "audss", "sclk_epll", E4X12_GATE_IP_MAUDIO, 0, 0, 0),
 	GATE(mdnie0, "mdnie0", "aclk160", GATE_IP_LCD0, 2, 0, 0),
 	GATE(rotator, "rotator", "aclk200", E4X12_GATE_IP_IMAGE, 1, 0, 0),
@@ -840,10 +838,11 @@ struct samsung_gate_clock exynos4x12_gate_clks[] __initdata = {
 			SRC_MASK_FSYS, 24, CLK_SET_RATE_PARENT, 0),
 	GATE(smmu_rotator, "smmu_rotator", "aclk200",
 			E4X12_GATE_IP_IMAGE, 4, 0, 0),
-	GATE_A(mct, "mct", "aclk100", E4X12_GATE_IP_PERIR, 13, 0, 0, "mct"),
-	GATE_A(rtc, "rtc", "aclk100", E4X12_GATE_IP_PERIR, 15, 0, 0, "rtc"),
-	GATE_A(keyif, "keyif", "aclk100",
-			E4X12_GATE_IP_PERIR, 16, 0, 0, "keypad"),
+	GATE(mct, "mct", "aclk100", E4X12_GATE_IP_PERIR, 13,
+			0, 0),
+	GATE(rtc, "rtc", "aclk100", E4X12_GATE_IP_PERIR, 15,
+			0, 0),
+	GATE(keyif, "keyif", "aclk100", E4X12_GATE_IP_PERIR, 16, 0, 0),
 	GATE(sclk_pwm_isp, "sclk_pwm_isp", "div_pwm_isp",
 			E4X12_SRC_MASK_ISP, 0, CLK_SET_RATE_PARENT, 0),
 	GATE(sclk_spi0_isp, "sclk_spi0_isp", "div_spi0_isp_pre",
@@ -860,12 +859,11 @@ struct samsung_gate_clock exynos4x12_gate_clks[] __initdata = {
 			E4X12_GATE_IP_ISP, 2, 0, 0),
 	GATE(uart_isp_sclk, "uart_isp_sclk", "sclk_uart_isp",
 			E4X12_GATE_IP_ISP, 3, 0, 0),
-	GATE_A(wdt, "watchdog", "aclk100",
-			E4X12_GATE_IP_PERIR, 14, 0, 0, "watchdog"),
-	GATE_DA(pcm0, "samsung-pcm.0", "pcm0", "aclk100",
-			E4X12_GATE_IP_MAUDIO, 2, 0, 0, "pcm"),
-	GATE_DA(i2s0, "samsung-i2s.0", "i2s0", "aclk100",
-			E4X12_GATE_IP_MAUDIO, 3, 0, 0, "iis"),
+	GATE(wdt, "watchdog", "aclk100", E4X12_GATE_IP_PERIR, 14, 0, 0),
+	GATE(pcm0, "pcm0", "aclk100", E4X12_GATE_IP_MAUDIO, 2,
+			0, 0),
+	GATE(i2s0, "i2s0", "aclk100", E4X12_GATE_IP_MAUDIO, 3,
+			0, 0),
 	GATE(fimc_isp, "isp", "aclk200", E4X12_GATE_ISP0, 0,
 			CLK_IGNORE_UNUSED | CLK_GET_RATE_NOCACHE, 0),
 	GATE(fimc_drc, "drc", "aclk200", E4X12_GATE_ISP0, 1,
@@ -919,6 +917,21 @@ struct samsung_gate_clock exynos4x12_gate_clks[] __initdata = {
 	GATE(spi1_isp, "spi1_isp", "aclk200", E4X12_GATE_ISP1, 13,
 			CLK_IGNORE_UNUSED | CLK_GET_RATE_NOCACHE, 0),
 	GATE(g2d, "g2d", "aclk200", GATE_IP_DMC, 23, 0, 0),
+	GATE(tmu_apbif, "tmu_apbif", "aclk100", E4X12_GATE_IP_PERIR, 17, 0, 0),
+};
+
+static struct samsung_clock_alias exynos4_aliases[] __initdata = {
+	ALIAS(mout_core, NULL, "moutcore"),
+	ALIAS(arm_clk, NULL, "armclk"),
+	ALIAS(sclk_apll, NULL, "mout_apll"),
+};
+
+static struct samsung_clock_alias exynos4210_aliases[] __initdata = {
+	ALIAS(sclk_mpll, NULL, "mout_mpll"),
+};
+
+static struct samsung_clock_alias exynos4x12_aliases[] __initdata = {
+	ALIAS(mout_mpll_user_c, NULL, "mout_mpll"),
 };
 
 /*
@@ -973,36 +986,116 @@ static void __init exynos4_clk_register_finpll(unsigned long xom)
 
 }
 
-/*
- * This function allows non-dt platforms to specify the clock speed of the
- * xxti and xusbxti clocks. These clocks are then registered with the specified
- * clock speed.
- */
-void __init exynos4_clk_register_fixed_ext(unsigned long xxti_f,
-						unsigned long xusbxti_f)
-{
-	exynos4_fixed_rate_ext_clks[0].fixed_rate = xxti_f;
-	exynos4_fixed_rate_ext_clks[1].fixed_rate = xusbxti_f;
-	samsung_clk_register_fixed_rate(exynos4_fixed_rate_ext_clks,
-			ARRAY_SIZE(exynos4_fixed_rate_ext_clks));
-}
-
-static __initdata struct of_device_id ext_clk_match[] = {
+static struct of_device_id ext_clk_match[] __initdata = {
 	{ .compatible = "samsung,clock-xxti", .data = (void *)0, },
 	{ .compatible = "samsung,clock-xusbxti", .data = (void *)1, },
 	{},
 };
 
+/* PLLs PMS values */
+static struct samsung_pll_rate_table exynos4210_apll_rates[] __initdata = {
+	PLL_45XX_RATE(1200000000, 150,  3, 1, 28),
+	PLL_45XX_RATE(1000000000, 250,  6, 1, 28),
+	PLL_45XX_RATE( 800000000, 200,  6, 1, 28),
+	PLL_45XX_RATE( 666857142, 389, 14, 1, 13),
+	PLL_45XX_RATE( 600000000, 100,  4, 1, 13),
+	PLL_45XX_RATE( 533000000, 533, 24, 1,  5),
+	PLL_45XX_RATE( 500000000, 250,  6, 2, 28),
+	PLL_45XX_RATE( 400000000, 200,  6, 2, 28),
+	PLL_45XX_RATE( 200000000, 200,  6, 3, 28),
+	{ /* sentinel */ }
+};
+
+static struct samsung_pll_rate_table exynos4210_epll_rates[] __initdata = {
+	PLL_4600_RATE(192000000, 48, 3, 1,     0, 0),
+	PLL_4600_RATE(180633605, 45, 3, 1, 10381, 0),
+	PLL_4600_RATE(180000000, 45, 3, 1,     0, 0),
+	PLL_4600_RATE( 73727996, 73, 3, 3, 47710, 1),
+	PLL_4600_RATE( 67737602, 90, 4, 3, 20762, 1),
+	PLL_4600_RATE( 49151992, 49, 3, 3,  9961, 0),
+	PLL_4600_RATE( 45158401, 45, 3, 3, 10381, 0),
+	{ /* sentinel */ }
+};
+
+static struct samsung_pll_rate_table exynos4210_vpll_rates[] __initdata = {
+	PLL_4650_RATE(360000000, 44, 3, 0, 1024, 0, 14, 0),
+	PLL_4650_RATE(324000000, 53, 2, 1, 1024, 1,  1, 1),
+	PLL_4650_RATE(259617187, 63, 3, 1, 1950, 0, 20, 1),
+	PLL_4650_RATE(110000000, 53, 3, 2, 2048, 0, 17, 0),
+	PLL_4650_RATE( 55360351, 53, 3, 3, 2417, 0, 17, 0),
+	{ /* sentinel */ }
+};
+
+static struct samsung_pll_rate_table exynos4x12_apll_rates[] __initdata = {
+	PLL_35XX_RATE(1500000000, 250, 4, 0),
+	PLL_35XX_RATE(1400000000, 175, 3, 0),
+	PLL_35XX_RATE(1300000000, 325, 6, 0),
+	PLL_35XX_RATE(1200000000, 200, 4, 0),
+	PLL_35XX_RATE(1100000000, 275, 6, 0),
+	PLL_35XX_RATE(1000000000, 125, 3, 0),
+	PLL_35XX_RATE( 900000000, 150, 4, 0),
+	PLL_35XX_RATE( 800000000, 100, 3, 0),
+	PLL_35XX_RATE( 700000000, 175, 3, 1),
+	PLL_35XX_RATE( 600000000, 200, 4, 1),
+	PLL_35XX_RATE( 500000000, 125, 3, 1),
+	PLL_35XX_RATE( 400000000, 100, 3, 1),
+	PLL_35XX_RATE( 300000000, 200, 4, 2),
+	PLL_35XX_RATE( 200000000, 100, 3, 2),
+	{ /* sentinel */ }
+};
+
+static struct samsung_pll_rate_table exynos4x12_epll_rates[] __initdata = {
+	PLL_36XX_RATE(192000000, 48, 3, 1,     0),
+	PLL_36XX_RATE(180633605, 45, 3, 1, 10381),
+	PLL_36XX_RATE(180000000, 45, 3, 1,     0),
+	PLL_36XX_RATE( 73727996, 73, 3, 3, 47710),
+	PLL_36XX_RATE( 67737602, 90, 4, 3, 20762),
+	PLL_36XX_RATE( 49151992, 49, 3, 3,  9961),
+	PLL_36XX_RATE( 45158401, 45, 3, 3, 10381),
+	{ /* sentinel */ }
+};
+
+static struct samsung_pll_rate_table exynos4x12_vpll_rates[] __initdata = {
+	PLL_36XX_RATE(533000000, 133, 3, 1, 16384),
+	PLL_36XX_RATE(440000000, 110, 3, 1,     0),
+	PLL_36XX_RATE(350000000, 175, 3, 2,     0),
+	PLL_36XX_RATE(266000000, 133, 3, 2,     0),
+	PLL_36XX_RATE(160000000, 160, 3, 3,     0),
+	PLL_36XX_RATE(106031250,  53, 3, 2,  1024),
+	PLL_36XX_RATE( 53015625,  53, 3, 3,  1024),
+	{ /* sentinel */ }
+};
+
+static struct samsung_pll_clock exynos4210_plls[nr_plls] __initdata = {
+	[apll] = PLL_A(pll_4508, fout_apll, "fout_apll", "fin_pll", APLL_LOCK,
+		APLL_CON0, "fout_apll", NULL),
+	[mpll] = PLL_A(pll_4508, fout_mpll, "fout_mpll", "fin_pll",
+		E4210_MPLL_LOCK, E4210_MPLL_CON0, "fout_mpll", NULL),
+	[epll] = PLL_A(pll_4600, fout_epll, "fout_epll", "fin_pll", EPLL_LOCK,
+		EPLL_CON0, "fout_epll", NULL),
+	[vpll] = PLL_A(pll_4650c, fout_vpll, "fout_vpll", "mout_vpllsrc",
+		VPLL_LOCK, VPLL_CON0, "fout_vpll", NULL),
+};
+
+static struct samsung_pll_clock exynos4x12_plls[nr_plls] __initdata = {
+	[apll] = PLL(pll_35xx, fout_apll, "fout_apll", "fin_pll",
+			APLL_LOCK, APLL_CON0, NULL),
+	[mpll] = PLL(pll_35xx, fout_mpll, "fout_mpll", "fin_pll",
+			E4X12_MPLL_LOCK, E4X12_MPLL_CON0, NULL),
+	[epll] = PLL(pll_36xx, fout_epll, "fout_epll", "fin_pll",
+			EPLL_LOCK, EPLL_CON0, NULL),
+	[vpll] = PLL(pll_36xx, fout_vpll, "fout_vpll", "fin_pll",
+			VPLL_LOCK, VPLL_CON0, NULL),
+};
+
 /* register exynos4 clocks */
-void __init exynos4_clk_init(struct device_node *np, enum exynos4_soc exynos4_soc, void __iomem *reg_base, unsigned long xom)
+static void __init exynos4_clk_init(struct device_node *np,
+				    enum exynos4_soc exynos4_soc,
+				    void __iomem *reg_base, unsigned long xom)
 {
-	struct clk *apll, *mpll, *epll, *vpll;
-
-	if (np) {
-		reg_base = of_iomap(np, 0);
-		if (!reg_base)
-			panic("%s: failed to map registers\n", __func__);
-	}
+	reg_base = of_iomap(np, 0);
+	if (!reg_base)
+		panic("%s: failed to map registers\n", __func__);
 
 	if (exynos4_soc == EXYNOS4210)
 		samsung_clk_init(np, reg_base, nr_clks,
@@ -1013,37 +1106,42 @@ void __init exynos4_clk_init(struct device_node *np, enum exynos4_soc exynos4_so
 			exynos4_clk_regs, ARRAY_SIZE(exynos4_clk_regs),
 			exynos4x12_clk_save, ARRAY_SIZE(exynos4x12_clk_save));
 
-	if (np)
-		samsung_clk_of_register_fixed_ext(exynos4_fixed_rate_ext_clks,
+	samsung_clk_of_register_fixed_ext(exynos4_fixed_rate_ext_clks,
 			ARRAY_SIZE(exynos4_fixed_rate_ext_clks),
 			ext_clk_match);
 
 	exynos4_clk_register_finpll(xom);
 
 	if (exynos4_soc == EXYNOS4210) {
-		apll = samsung_clk_register_pll45xx("fout_apll", "fin_pll",
-					reg_base + APLL_CON0, pll_4508);
-		mpll = samsung_clk_register_pll45xx("fout_mpll", "fin_pll",
-					reg_base + E4210_MPLL_CON0, pll_4508);
-		epll = samsung_clk_register_pll46xx("fout_epll", "fin_pll",
-					reg_base + EPLL_CON0, pll_4600);
-		vpll = samsung_clk_register_pll46xx("fout_vpll", "mout_vpllsrc",
-					reg_base + VPLL_CON0, pll_4650c);
+		samsung_clk_register_mux(exynos4210_mux_early,
+					ARRAY_SIZE(exynos4210_mux_early));
+
+		if (_get_rate("fin_pll") == 24000000) {
+			exynos4210_plls[apll].rate_table =
+							exynos4210_apll_rates;
+			exynos4210_plls[epll].rate_table =
+							exynos4210_epll_rates;
+		}
+
+		if (_get_rate("mout_vpllsrc") == 24000000)
+			exynos4210_plls[vpll].rate_table =
+							exynos4210_vpll_rates;
+
+		samsung_clk_register_pll(exynos4210_plls,
+					ARRAY_SIZE(exynos4210_plls), reg_base);
 	} else {
-		apll = samsung_clk_register_pll35xx("fout_apll", "fin_pll",
-					reg_base + APLL_CON0);
-		mpll = samsung_clk_register_pll35xx("fout_mpll", "fin_pll",
-					reg_base + E4X12_MPLL_CON0);
-		epll = samsung_clk_register_pll36xx("fout_epll", "fin_pll",
-					reg_base + EPLL_CON0);
-		vpll = samsung_clk_register_pll36xx("fout_vpll", "fin_pll",
-					reg_base + VPLL_CON0);
-	}
+		if (_get_rate("fin_pll") == 24000000) {
+			exynos4x12_plls[apll].rate_table =
+							exynos4x12_apll_rates;
+			exynos4x12_plls[epll].rate_table =
+							exynos4x12_epll_rates;
+			exynos4x12_plls[vpll].rate_table =
+							exynos4x12_vpll_rates;
+		}
 
-	samsung_clk_add_lookup(apll, fout_apll);
-	samsung_clk_add_lookup(mpll, fout_mpll);
-	samsung_clk_add_lookup(epll, fout_epll);
-	samsung_clk_add_lookup(vpll, fout_vpll);
+		samsung_clk_register_pll(exynos4x12_plls,
+					ARRAY_SIZE(exynos4x12_plls), reg_base);
+	}
 
 	samsung_clk_register_fixed_rate(exynos4_fixed_rate_clks,
 			ARRAY_SIZE(exynos4_fixed_rate_clks));
@@ -1063,6 +1161,8 @@ void __init exynos4_clk_init(struct device_node *np, enum exynos4_soc exynos4_so
 			ARRAY_SIZE(exynos4210_div_clks));
 		samsung_clk_register_gate(exynos4210_gate_clks,
 			ARRAY_SIZE(exynos4210_gate_clks));
+		samsung_clk_register_alias(exynos4210_aliases,
+			ARRAY_SIZE(exynos4210_aliases));
 	} else {
 		samsung_clk_register_mux(exynos4x12_mux_clks,
 			ARRAY_SIZE(exynos4x12_mux_clks));
@@ -1070,14 +1170,19 @@ void __init exynos4_clk_init(struct device_node *np, enum exynos4_soc exynos4_so
 			ARRAY_SIZE(exynos4x12_div_clks));
 		samsung_clk_register_gate(exynos4x12_gate_clks,
 			ARRAY_SIZE(exynos4x12_gate_clks));
+		samsung_clk_register_alias(exynos4x12_aliases,
+			ARRAY_SIZE(exynos4x12_aliases));
 	}
 
+	samsung_clk_register_alias(exynos4_aliases,
+			ARRAY_SIZE(exynos4_aliases));
+
 	pr_info("%s clocks: sclk_apll = %ld, sclk_mpll = %ld\n"
 		"\tsclk_epll = %ld, sclk_vpll = %ld, arm_clk = %ld\n",
 		exynos4_soc == EXYNOS4210 ? "Exynos4210" : "Exynos4x12",
-		_get_rate("sclk_apll"),	_get_rate("mout_mpll"),
+		_get_rate("sclk_apll"),	_get_rate("sclk_mpll"),
 		_get_rate("sclk_epll"), _get_rate("sclk_vpll"),
-		_get_rate("armclk"));
+		_get_rate("arm_clk"));
 }
 
 
diff --git a/drivers/clk/samsung/clk-exynos5250.c b/drivers/clk/samsung/clk-exynos5250.c
index 6f767c515ec7..adf32343c9f9 100644
--- a/drivers/clk/samsung/clk-exynos5250.c
+++ b/drivers/clk/samsung/clk-exynos5250.c
@@ -17,11 +17,22 @@
 #include <linux/of_address.h>
 
 #include "clk.h"
-#include "clk-pll.h"
 
+#define APLL_LOCK		0x0
+#define APLL_CON0		0x100
 #define SRC_CPU			0x200
 #define DIV_CPU0		0x500
+#define MPLL_LOCK		0x4000
+#define MPLL_CON0		0x4100
 #define SRC_CORE1		0x4204
+#define CPLL_LOCK		0x10020
+#define EPLL_LOCK		0x10030
+#define VPLL_LOCK		0x10040
+#define GPLL_LOCK		0x10050
+#define CPLL_CON0		0x10120
+#define EPLL_CON0		0x10130
+#define VPLL_CON0		0x10140
+#define GPLL_CON0		0x10150
 #define SRC_TOP0		0x10210
 #define SRC_TOP2		0x10218
 #define SRC_GSCL		0x10220
@@ -59,9 +70,18 @@
 #define GATE_IP_FSYS		0x10944
 #define GATE_IP_PERIC		0x10950
 #define GATE_IP_PERIS		0x10960
+#define BPLL_LOCK		0x20010
+#define BPLL_CON0		0x20110
 #define SRC_CDREX		0x20200
 #define PLL_DIV2_SEL		0x20a24
 #define GATE_IP_DISP1		0x10928
+#define GATE_IP_ACP		0x10000
+
+/* list of PLLs to be registered */
+enum exynos5250_plls {
+	apll, mpll, cpll, epll, vpll, gpll, bpll,
+	nr_plls			/* number of PLLs */
+};
 
 /*
  * Let each supported clock get a unique id. This id is used to lookup the clock
@@ -79,7 +99,8 @@ enum exynos5250_clks {
 	none,
 
 	/* core clocks */
-	fin_pll,
+	fin_pll, fout_apll, fout_mpll, fout_bpll, fout_gpll, fout_cpll,
+	fout_epll, fout_vpll,
 
 	/* gate for special clocks (sclk) */
 	sclk_cam_bayer = 128, sclk_cam0, sclk_cam1, sclk_gscl_wa, sclk_gscl_wb,
@@ -87,7 +108,7 @@ enum exynos5250_clks {
 	sclk_mmc0, sclk_mmc1, sclk_mmc2, sclk_mmc3, sclk_sata, sclk_usb3,
 	sclk_jpeg, sclk_uart0, sclk_uart1, sclk_uart2, sclk_uart3, sclk_pwm,
 	sclk_audio1, sclk_audio2, sclk_spdif, sclk_spi0, sclk_spi1, sclk_spi2,
-	div_i2s1, div_i2s2,
+	div_i2s1, div_i2s2, sclk_hdmiphy,
 
 	/* gate clocks */
 	gscl0 = 256, gscl1, gscl2, gscl3, gscl_wa, gscl_wb, smmu_gscl0,
@@ -99,7 +120,10 @@ enum exynos5250_clks {
 	spi2, i2s1, i2s2, pcm1, pcm2, pwm, spdif, ac97, hsi2c0, hsi2c1, hsi2c2,
 	hsi2c3, chipid, sysreg, pmu, cmu_top, cmu_core, cmu_mem, tzpc0, tzpc1,
 	tzpc2, tzpc3, tzpc4, tzpc5, tzpc6, tzpc7, tzpc8, tzpc9, hdmi_cec, mct,
-	wdt, rtc, tmu, fimd1, mie1, dsim0, dp, mixer, hdmi,
+	wdt, rtc, tmu, fimd1, mie1, dsim0, dp, mixer, hdmi, g2d,
+
+	/* mux clocks */
+	mout_hdmi = 1024,
 
 	nr_clks,
 };
@@ -108,7 +132,7 @@ enum exynos5250_clks {
  * list of controller registers to be saved and restored during a
  * suspend/resume cycle.
  */
-static __initdata unsigned long exynos5250_clk_regs[] = {
+static unsigned long exynos5250_clk_regs[] __initdata = {
 	SRC_CPU,
 	DIV_CPU0,
 	SRC_CORE1,
@@ -152,6 +176,7 @@ static __initdata unsigned long exynos5250_clk_regs[] = {
 	SRC_CDREX,
 	PLL_DIV2_SEL,
 	GATE_IP_DISP1,
+	GATE_IP_ACP,
 };
 
 /* list of all parent clock list */
@@ -191,31 +216,34 @@ PNAME(mout_spdif_p)	= { "sclk_audio0", "sclk_audio1", "sclk_audio2",
 				"spdif_extclk" };
 
 /* fixed rate clocks generated outside the soc */
-struct samsung_fixed_rate_clock exynos5250_fixed_rate_ext_clks[] __initdata = {
+static struct samsung_fixed_rate_clock exynos5250_fixed_rate_ext_clks[] __initdata = {
 	FRATE(fin_pll, "fin_pll", NULL, CLK_IS_ROOT, 0),
 };
 
 /* fixed rate clocks generated inside the soc */
-struct samsung_fixed_rate_clock exynos5250_fixed_rate_clks[] __initdata = {
-	FRATE(none, "sclk_hdmiphy", NULL, CLK_IS_ROOT, 24000000),
+static struct samsung_fixed_rate_clock exynos5250_fixed_rate_clks[] __initdata = {
+	FRATE(sclk_hdmiphy, "sclk_hdmiphy", NULL, CLK_IS_ROOT, 24000000),
 	FRATE(none, "sclk_hdmi27m", NULL, CLK_IS_ROOT, 27000000),
 	FRATE(none, "sclk_dptxphy", NULL, CLK_IS_ROOT, 24000000),
 	FRATE(none, "sclk_uhostphy", NULL, CLK_IS_ROOT, 48000000),
 };
 
-struct samsung_fixed_factor_clock exynos5250_fixed_factor_clks[] __initdata = {
+static struct samsung_fixed_factor_clock exynos5250_fixed_factor_clks[] __initdata = {
 	FFACTOR(none, "fout_mplldiv2", "fout_mpll", 1, 2, 0),
 	FFACTOR(none, "fout_bplldiv2", "fout_bpll", 1, 2, 0),
 };
 
-struct samsung_mux_clock exynos5250_mux_clks[] __initdata = {
+static struct samsung_mux_clock exynos5250_pll_pmux_clks[] __initdata = {
+	MUX(none, "mout_vpllsrc", mout_vpllsrc_p, SRC_TOP2, 0, 1),
+};
+
+static struct samsung_mux_clock exynos5250_mux_clks[] __initdata = {
 	MUX_A(none, "mout_apll", mout_apll_p, SRC_CPU, 0, 1, "mout_apll"),
 	MUX_A(none, "mout_cpu", mout_cpu_p, SRC_CPU, 16, 1, "mout_cpu"),
 	MUX(none, "mout_mpll_fout", mout_mpll_fout_p, PLL_DIV2_SEL, 4, 1),
 	MUX_A(none, "sclk_mpll", mout_mpll_p, SRC_CORE1, 8, 1, "mout_mpll"),
 	MUX(none, "mout_bpll_fout", mout_bpll_fout_p, PLL_DIV2_SEL, 0, 1),
 	MUX(none, "sclk_bpll", mout_bpll_p, SRC_CDREX, 0, 1),
-	MUX(none, "mout_vpllsrc", mout_vpllsrc_p, SRC_TOP2, 0, 1),
 	MUX(none, "sclk_vpll", mout_vpll_p, SRC_TOP2, 16, 1),
 	MUX(none, "sclk_epll", mout_epll_p, SRC_TOP2, 12, 1),
 	MUX(none, "sclk_cpll", mout_cpll_p, SRC_TOP2, 8, 1),
@@ -232,7 +260,7 @@ struct samsung_mux_clock exynos5250_mux_clks[] __initdata = {
 	MUX(none, "mout_fimd1", mout_group1_p, SRC_DISP1_0, 0, 4),
 	MUX(none, "mout_mipi1", mout_group1_p, SRC_DISP1_0, 12, 4),
 	MUX(none, "mout_dp", mout_group1_p, SRC_DISP1_0, 16, 4),
-	MUX(none, "mout_hdmi", mout_hdmi_p, SRC_DISP1_0, 20, 1),
+	MUX(mout_hdmi, "mout_hdmi", mout_hdmi_p, SRC_DISP1_0, 20, 1),
 	MUX(none, "mout_audio0", mout_audio0_p, SRC_MAU, 0, 4),
 	MUX(none, "mout_mmc0", mout_group1_p, SRC_FSYS, 0, 4),
 	MUX(none, "mout_mmc1", mout_group1_p, SRC_FSYS, 4, 4),
@@ -254,7 +282,7 @@ struct samsung_mux_clock exynos5250_mux_clks[] __initdata = {
 	MUX(none, "mout_spi2", mout_group1_p, SRC_PERIC1, 24, 4),
 };
 
-struct samsung_div_clock exynos5250_div_clks[] __initdata = {
+static struct samsung_div_clock exynos5250_div_clks[] __initdata = {
 	DIV(none, "div_arm", "mout_cpu", DIV_CPU0, 0, 3),
 	DIV(none, "sclk_apll", "mout_apll", DIV_CPU0, 24, 3),
 	DIV(none, "aclk66_pre", "sclk_mpll_user", DIV_TOP1, 24, 3),
@@ -314,7 +342,7 @@ struct samsung_div_clock exynos5250_div_clks[] __initdata = {
 			DIV_PERIC2, 8, 8, CLK_SET_RATE_PARENT, 0),
 };
 
-struct samsung_gate_clock exynos5250_gate_clks[] __initdata = {
+static struct samsung_gate_clock exynos5250_gate_clks[] __initdata = {
 	GATE(gscl0, "gscl0", "none", GATE_IP_GSCL, 0, 0, 0),
 	GATE(gscl1, "gscl1", "none", GATE_IP_GSCL, 1, 0, 0),
 	GATE(gscl2, "gscl2", "aclk266", GATE_IP_GSCL, 2, 0, 0),
@@ -461,20 +489,60 @@ struct samsung_gate_clock exynos5250_gate_clks[] __initdata = {
 	GATE(mie1, "mie1", "aclk200", GATE_IP_DISP1, 1, 0, 0),
 	GATE(dsim0, "dsim0", "aclk200", GATE_IP_DISP1, 3, 0, 0),
 	GATE(dp, "dp", "aclk200", GATE_IP_DISP1, 4, 0, 0),
-	GATE(mixer, "mixer", "aclk200", GATE_IP_DISP1, 5, 0, 0),
-	GATE(hdmi, "hdmi", "aclk200", GATE_IP_DISP1, 6, 0, 0),
+	GATE(mixer, "mixer", "mout_aclk200_disp1", GATE_IP_DISP1, 5, 0, 0),
+	GATE(hdmi, "hdmi", "mout_aclk200_disp1", GATE_IP_DISP1, 6, 0, 0),
+	GATE(g2d, "g2d", "aclk200", GATE_IP_ACP, 3, 0, 0),
+};
+
+static struct samsung_pll_rate_table vpll_24mhz_tbl[] __initdata = {
+	/* sorted in descending order */
+	/* PLL_36XX_RATE(rate, m, p, s, k) */
+	PLL_36XX_RATE(266000000, 266, 3, 3, 0),
+	/* Not in UM, but need for eDP on snow */
+	PLL_36XX_RATE(70500000, 94, 2, 4, 0),
+	{ },
+};
+
+static struct samsung_pll_rate_table epll_24mhz_tbl[] __initdata = {
+	/* sorted in descending order */
+	/* PLL_36XX_RATE(rate, m, p, s, k) */
+	PLL_36XX_RATE(192000000, 64, 2, 2, 0),
+	PLL_36XX_RATE(180633600, 90, 3, 2, 20762),
+	PLL_36XX_RATE(180000000, 90, 3, 2, 0),
+	PLL_36XX_RATE(73728000, 98, 2, 4, 19923),
+	PLL_36XX_RATE(67737600, 90, 2, 4, 20762),
+	PLL_36XX_RATE(49152000, 98, 3, 4, 19923),
+	PLL_36XX_RATE(45158400, 90, 3, 4, 20762),
+	PLL_36XX_RATE(32768000, 131, 3, 5, 4719),
+	{ },
+};
+
+static struct samsung_pll_clock exynos5250_plls[nr_plls] __initdata = {
+	[apll] = PLL_A(pll_35xx, fout_apll, "fout_apll", "fin_pll", APLL_LOCK,
+		APLL_CON0, "fout_apll", NULL),
+	[mpll] = PLL_A(pll_35xx, fout_mpll, "fout_mpll", "fin_pll", MPLL_LOCK,
+		MPLL_CON0, "fout_mpll", NULL),
+	[bpll] = PLL(pll_35xx, fout_bpll, "fout_bpll", "fin_pll", BPLL_LOCK,
+		BPLL_CON0, NULL),
+	[gpll] = PLL(pll_35xx, fout_gpll, "fout_gpll", "fin_pll", GPLL_LOCK,
+		GPLL_CON0, NULL),
+	[cpll] = PLL(pll_35xx, fout_cpll, "fout_cpll", "fin_pll", CPLL_LOCK,
+		CPLL_CON0, NULL),
+	[epll] = PLL(pll_36xx, fout_epll, "fout_epll", "fin_pll", EPLL_LOCK,
+		EPLL_CON0, NULL),
+	[vpll] = PLL(pll_36xx, fout_vpll, "fout_vpll", "mout_vpllsrc",
+		VPLL_LOCK, VPLL_CON0, NULL),
 };
 
-static __initdata struct of_device_id ext_clk_match[] = {
+static struct of_device_id ext_clk_match[] __initdata = {
 	{ .compatible = "samsung,clock-xxti", .data = (void *)0, },
 	{ },
 };
 
 /* register exynox5250 clocks */
-void __init exynos5250_clk_init(struct device_node *np)
+static void __init exynos5250_clk_init(struct device_node *np)
 {
 	void __iomem *reg_base;
-	struct clk *apll, *mpll, *epll, *vpll, *bpll, *gpll, *cpll;
 
 	if (np) {
 		reg_base = of_iomap(np, 0);
@@ -490,22 +558,17 @@ void __init exynos5250_clk_init(struct device_node *np)
 	samsung_clk_of_register_fixed_ext(exynos5250_fixed_rate_ext_clks,
 			ARRAY_SIZE(exynos5250_fixed_rate_ext_clks),
 			ext_clk_match);
+	samsung_clk_register_mux(exynos5250_pll_pmux_clks,
+				ARRAY_SIZE(exynos5250_pll_pmux_clks));
+
+	if (_get_rate("fin_pll") == 24 * MHZ)
+		exynos5250_plls[epll].rate_table = epll_24mhz_tbl;
 
-	apll = samsung_clk_register_pll35xx("fout_apll", "fin_pll",
-			reg_base + 0x100);
-	mpll = samsung_clk_register_pll35xx("fout_mpll", "fin_pll",
-			reg_base + 0x4100);
-	bpll = samsung_clk_register_pll35xx("fout_bpll", "fin_pll",
-			reg_base + 0x20110);
-	gpll = samsung_clk_register_pll35xx("fout_gpll", "fin_pll",
-			reg_base + 0x10150);
-	cpll = samsung_clk_register_pll35xx("fout_cpll", "fin_pll",
-			reg_base + 0x10120);
-	epll = samsung_clk_register_pll36xx("fout_epll", "fin_pll",
-			reg_base + 0x10130);
-	vpll = samsung_clk_register_pll36xx("fout_vpll", "mout_vpllsrc",
-			reg_base + 0x10140);
+	if (_get_rate("mout_vpllsrc") == 24 * MHZ)
+		exynos5250_plls[vpll].rate_table =  vpll_24mhz_tbl;
 
+	samsung_clk_register_pll(exynos5250_plls, ARRAY_SIZE(exynos5250_plls),
+					reg_base);
 	samsung_clk_register_fixed_rate(exynos5250_fixed_rate_clks,
 			ARRAY_SIZE(exynos5250_fixed_rate_clks));
 	samsung_clk_register_fixed_factor(exynos5250_fixed_factor_clks,
diff --git a/drivers/clk/samsung/clk-exynos5420.c b/drivers/clk/samsung/clk-exynos5420.c
index 68a96cbd4936..48c4a9350b91 100644
--- a/drivers/clk/samsung/clk-exynos5420.c
+++ b/drivers/clk/samsung/clk-exynos5420.c
@@ -17,13 +17,30 @@
 #include <linux/of_address.h>
 
 #include "clk.h"
-#include "clk-pll.h"
 
+#define APLL_LOCK		0x0
+#define APLL_CON0		0x100
 #define SRC_CPU			0x200
 #define DIV_CPU0		0x500
 #define DIV_CPU1		0x504
 #define GATE_BUS_CPU		0x700
 #define GATE_SCLK_CPU		0x800
+#define CPLL_LOCK		0x10020
+#define DPLL_LOCK		0x10030
+#define EPLL_LOCK		0x10040
+#define RPLL_LOCK		0x10050
+#define IPLL_LOCK		0x10060
+#define SPLL_LOCK		0x10070
+#define VPLL_LOCK		0x10070
+#define MPLL_LOCK		0x10090
+#define CPLL_CON0		0x10120
+#define DPLL_CON0		0x10128
+#define EPLL_CON0		0x10130
+#define RPLL_CON0		0x10140
+#define IPLL_CON0		0x10150
+#define SPLL_CON0		0x10160
+#define VPLL_CON0		0x10170
+#define MPLL_CON0		0x10180
 #define SRC_TOP0		0x10200
 #define SRC_TOP1		0x10204
 #define SRC_TOP2		0x10208
@@ -75,15 +92,27 @@
 #define GATE_TOP_SCLK_MAU	0x1083c
 #define GATE_TOP_SCLK_FSYS	0x10840
 #define GATE_TOP_SCLK_PERIC	0x10850
+#define BPLL_LOCK		0x20010
+#define BPLL_CON0		0x20110
 #define SRC_CDREX		0x20200
+#define KPLL_LOCK		0x28000
+#define KPLL_CON0		0x28100
 #define SRC_KFC			0x28200
 #define DIV_KFC0		0x28500
 
+/* list of PLLs */
+enum exynos5420_plls {
+	apll, cpll, dpll, epll, rpll, ipll, spll, vpll, mpll,
+	bpll, kpll,
+	nr_plls			/* number of PLLs */
+};
+
 enum exynos5420_clks {
 	none,
 
 	/* core clocks */
-	fin_pll,
+	fin_pll,  fout_apll, fout_cpll, fout_dpll, fout_epll, fout_rpll,
+	fout_ipll, fout_spll, fout_vpll, fout_mpll, fout_bpll, fout_kpll,
 
 	/* gate for special clocks (sclk) */
 	sclk_uart0 = 128, sclk_uart1, sclk_uart2, sclk_uart3, sclk_mmc0,
@@ -91,7 +120,7 @@ enum exynos5420_clks {
 	sclk_i2s2, sclk_pcm1, sclk_pcm2, sclk_spdif, sclk_hdmi, sclk_pixel,
 	sclk_dp1, sclk_mipi1, sclk_fimd1, sclk_maudio0, sclk_maupcm0,
 	sclk_usbd300, sclk_usbd301, sclk_usbphy300, sclk_usbphy301, sclk_unipro,
-	sclk_pwm, sclk_gscl_wa, sclk_gscl_wb,
+	sclk_pwm, sclk_gscl_wa, sclk_gscl_wb, sclk_hdmiphy,
 
 	/* gate clocks */
 	aclk66_peric = 256, uart0, uart1, uart2, uart3, i2c0, i2c1, i2c2, i2c3,
@@ -109,7 +138,13 @@ enum exynos5420_clks {
 	aclk300_gscl = 460, smmu_gscl0, smmu_gscl1, gscl_wa, gscl_wb, gscl0,
 	gscl1, clk_3aa, aclk266_g2d = 470, sss, slim_sss, mdma0,
 	aclk333_g2d = 480, g2d, aclk333_432_gscl = 490, smmu_3aa, smmu_fimcl0,
-	smmu_fimcl1, smmu_fimcl3, fimc_lite3, aclk_g3d = 500, g3d,
+	smmu_fimcl1, smmu_fimcl3, fimc_lite3, aclk_g3d = 500, g3d, smmu_mixer,
+
+	/* mux clocks */
+	mout_hdmi = 640,
+
+	/* divider clocks */
+	dout_pixel = 768,
 
 	nr_clks,
 };
@@ -118,7 +153,7 @@ enum exynos5420_clks {
  * list of controller registers to be saved and restored during a
  * suspend/resume cycle.
  */
-static __initdata unsigned long exynos5420_clk_regs[] = {
+static unsigned long exynos5420_clk_regs[] __initdata = {
 	SRC_CPU,
 	DIV_CPU0,
 	DIV_CPU1,
@@ -257,29 +292,29 @@ PNAME(audio2_p)	= { "fin_pll", "cdclk2", "sclk_dpll", "sclk_mpll",
 		  "sclk_spll", "sclk_ipll", "sclk_epll", "sclk_rpll" };
 PNAME(spdif_p)	= { "fin_pll", "dout_audio0", "dout_audio1", "dout_audio2",
 		  "spdif_extclk", "sclk_ipll", "sclk_epll", "sclk_rpll" };
-PNAME(hdmi_p)	= { "sclk_hdmiphy", "dout_hdmi_pixel" };
+PNAME(hdmi_p)	= { "dout_hdmi_pixel", "sclk_hdmiphy" };
 PNAME(maudio0_p)	= { "fin_pll", "maudio_clk", "sclk_dpll", "sclk_mpll",
 			  "sclk_spll", "sclk_ipll", "sclk_epll", "sclk_rpll" };
 
 /* fixed rate clocks generated outside the soc */
-struct samsung_fixed_rate_clock exynos5420_fixed_rate_ext_clks[] __initdata = {
+static struct samsung_fixed_rate_clock exynos5420_fixed_rate_ext_clks[] __initdata = {
 	FRATE(fin_pll, "fin_pll", NULL, CLK_IS_ROOT, 0),
 };
 
 /* fixed rate clocks generated inside the soc */
-struct samsung_fixed_rate_clock exynos5420_fixed_rate_clks[] __initdata = {
-	FRATE(none, "sclk_hdmiphy", NULL, CLK_IS_ROOT, 24000000),
+static struct samsung_fixed_rate_clock exynos5420_fixed_rate_clks[] __initdata = {
+	FRATE(sclk_hdmiphy, "sclk_hdmiphy", NULL, CLK_IS_ROOT, 24000000),
 	FRATE(none, "sclk_pwi", NULL, CLK_IS_ROOT, 24000000),
 	FRATE(none, "sclk_usbh20", NULL, CLK_IS_ROOT, 48000000),
 	FRATE(none, "mphy_refclk_ixtal24", NULL, CLK_IS_ROOT, 48000000),
 	FRATE(none, "sclk_usbh20_scan_clk", NULL, CLK_IS_ROOT, 480000000),
 };
 
-struct samsung_fixed_factor_clock exynos5420_fixed_factor_clks[] __initdata = {
+static struct samsung_fixed_factor_clock exynos5420_fixed_factor_clks[] __initdata = {
 	FFACTOR(none, "sclk_hsic_12m", "fin_pll", 1, 2, 0),
 };
 
-struct samsung_mux_clock exynos5420_mux_clks[] __initdata = {
+static struct samsung_mux_clock exynos5420_mux_clks[] __initdata = {
 	MUX(none, "mout_mspll_kfc", mspll_cpu_p, SRC_TOP7, 8, 2),
 	MUX(none, "mout_mspll_cpu", mspll_cpu_p, SRC_TOP7, 12, 2),
 	MUX(none, "mout_apll", apll_p, SRC_CPU, 0, 1),
@@ -371,7 +406,7 @@ struct samsung_mux_clock exynos5420_mux_clks[] __initdata = {
 	MUX(none, "mout_mipi1", group2_p, SRC_DISP10, 16, 3),
 	MUX(none, "mout_dp1", group2_p, SRC_DISP10, 20, 3),
 	MUX(none, "mout_pixel", group2_p, SRC_DISP10, 24, 3),
-	MUX(none, "mout_hdmi", hdmi_p, SRC_DISP10, 28, 1),
+	MUX(mout_hdmi, "mout_hdmi", hdmi_p, SRC_DISP10, 28, 1),
 
 	/* MAU Block */
 	MUX(none, "mout_maudio0", maudio0_p, SRC_MAU, 28, 3),
@@ -399,7 +434,7 @@ struct samsung_mux_clock exynos5420_mux_clks[] __initdata = {
 	MUX(none, "mout_spi2", group2_p, SRC_PERIC1, 28, 3),
 };
 
-struct samsung_div_clock exynos5420_div_clks[] __initdata = {
+static struct samsung_div_clock exynos5420_div_clks[] __initdata = {
 	DIV(none, "div_arm", "mout_cpu", DIV_CPU0, 0, 3),
 	DIV(none, "sclk_apll", "mout_apll", DIV_CPU0, 24, 3),
 	DIV(none, "armclk2", "div_arm", DIV_CPU0, 28, 3),
@@ -431,7 +466,7 @@ struct samsung_div_clock exynos5420_div_clks[] __initdata = {
 	DIV(none, "dout_fimd1", "mout_fimd1", DIV_DISP10, 0, 4),
 	DIV(none, "dout_mipi1", "mout_mipi1", DIV_DISP10, 16, 8),
 	DIV(none, "dout_dp1", "mout_dp1", DIV_DISP10, 24, 4),
-	DIV(none, "dout_hdmi_pixel", "mout_pixel", DIV_DISP10, 28, 4),
+	DIV(dout_pixel, "dout_hdmi_pixel", "mout_pixel", DIV_DISP10, 28, 4),
 
 	/* Audio Block */
 	DIV(none, "dout_maudio0", "mout_maudio0", DIV_MAU, 20, 4),
@@ -479,7 +514,7 @@ struct samsung_div_clock exynos5420_div_clks[] __initdata = {
 	DIV(none, "dout_pre_spi2", "dout_spi2", DIV_PERIC4, 24, 8),
 };
 
-struct samsung_gate_clock exynos5420_gate_clks[] __initdata = {
+static struct samsung_gate_clock exynos5420_gate_clks[] __initdata = {
 	/* TODO: Re-verify the CG bits for all the gate clocks */
 	GATE_A(mct, "pclk_st", "aclk66_psgen", GATE_BUS_PERIS1, 2, 0, 0, "mct"),
 
@@ -696,19 +731,43 @@ struct samsung_gate_clock exynos5420_gate_clks[] __initdata = {
 	GATE(smmu_mscl0, "smmu_mscl0", "aclk400_mscl", GATE_IP_MSCL, 8, 0, 0),
 	GATE(smmu_mscl1, "smmu_mscl1", "aclk400_mscl", GATE_IP_MSCL, 9, 0, 0),
 	GATE(smmu_mscl2, "smmu_mscl2", "aclk400_mscl", GATE_IP_MSCL, 10, 0, 0),
+	GATE(smmu_mixer, "smmu_mixer", "aclk200_disp1", GATE_IP_DISP1, 9, 0, 0),
 };
 
-static __initdata struct of_device_id ext_clk_match[] = {
+static struct samsung_pll_clock exynos5420_plls[nr_plls] __initdata = {
+	[apll] = PLL(pll_2550, fout_apll, "fout_apll", "fin_pll", APLL_LOCK,
+		APLL_CON0, NULL),
+	[cpll] = PLL(pll_2550, fout_mpll, "fout_mpll", "fin_pll", MPLL_LOCK,
+		MPLL_CON0, NULL),
+	[dpll] = PLL(pll_2550, fout_dpll, "fout_dpll", "fin_pll", DPLL_LOCK,
+		DPLL_CON0, NULL),
+	[epll] = PLL(pll_2650, fout_epll, "fout_epll", "fin_pll", EPLL_LOCK,
+		EPLL_CON0, NULL),
+	[rpll] = PLL(pll_2650, fout_rpll, "fout_rpll", "fin_pll", RPLL_LOCK,
+		RPLL_CON0, NULL),
+	[ipll] = PLL(pll_2550, fout_ipll, "fout_ipll", "fin_pll", IPLL_LOCK,
+		IPLL_CON0, NULL),
+	[spll] = PLL(pll_2550, fout_spll, "fout_spll", "fin_pll", SPLL_LOCK,
+		SPLL_CON0, NULL),
+	[vpll] = PLL(pll_2550, fout_vpll, "fout_vpll", "fin_pll", VPLL_LOCK,
+		VPLL_CON0, NULL),
+	[mpll] = PLL(pll_2550, fout_mpll, "fout_mpll", "fin_pll", MPLL_LOCK,
+		MPLL_CON0, NULL),
+	[bpll] = PLL(pll_2550, fout_bpll, "fout_bpll", "fin_pll", BPLL_LOCK,
+		BPLL_CON0, NULL),
+	[kpll] = PLL(pll_2550, fout_kpll, "fout_kpll", "fin_pll", KPLL_LOCK,
+		KPLL_CON0, NULL),
+};
+
+static struct of_device_id ext_clk_match[] __initdata = {
 	{ .compatible = "samsung,exynos5420-oscclk", .data = (void *)0, },
 	{ },
 };
 
 /* register exynos5420 clocks */
-void __init exynos5420_clk_init(struct device_node *np)
+static void __init exynos5420_clk_init(struct device_node *np)
 {
 	void __iomem *reg_base;
-	struct clk *apll, *bpll, *cpll, *dpll, *epll, *ipll, *kpll, *mpll;
-	struct clk *rpll, *spll, *vpll;
 
 	if (np) {
 		reg_base = of_iomap(np, 0);
@@ -724,30 +783,8 @@ void __init exynos5420_clk_init(struct device_node *np)
 	samsung_clk_of_register_fixed_ext(exynos5420_fixed_rate_ext_clks,
 			ARRAY_SIZE(exynos5420_fixed_rate_ext_clks),
 			ext_clk_match);
-
-	apll = samsung_clk_register_pll35xx("fout_apll", "fin_pll",
-			reg_base + 0x100);
-	bpll = samsung_clk_register_pll35xx("fout_bpll", "fin_pll",
-			reg_base + 0x20110);
-	cpll = samsung_clk_register_pll35xx("fout_cpll", "fin_pll",
-			reg_base + 0x10120);
-	dpll = samsung_clk_register_pll35xx("fout_dpll", "fin_pll",
-			reg_base + 0x10128);
-	epll = samsung_clk_register_pll36xx("fout_epll", "fin_pll",
-			reg_base + 0x10130);
-	ipll = samsung_clk_register_pll35xx("fout_ipll", "fin_pll",
-			reg_base + 0x10150);
-	kpll = samsung_clk_register_pll35xx("fout_kpll", "fin_pll",
-			reg_base + 0x28100);
-	mpll = samsung_clk_register_pll35xx("fout_mpll", "fin_pll",
-			reg_base + 0x10180);
-	rpll = samsung_clk_register_pll36xx("fout_rpll", "fin_pll",
-			reg_base + 0x10140);
-	spll = samsung_clk_register_pll35xx("fout_spll", "fin_pll",
-			reg_base + 0x10160);
-	vpll = samsung_clk_register_pll35xx("fout_vpll", "fin_pll",
-			reg_base + 0x10170);
-
+	samsung_clk_register_pll(exynos5420_plls, ARRAY_SIZE(exynos5420_plls),
+					reg_base);
 	samsung_clk_register_fixed_rate(exynos5420_fixed_rate_clks,
 			ARRAY_SIZE(exynos5420_fixed_rate_clks));
 	samsung_clk_register_fixed_factor(exynos5420_fixed_factor_clks,
diff --git a/drivers/clk/samsung/clk-exynos5440.c b/drivers/clk/samsung/clk-exynos5440.c
index 7d5434167a96..f8658945bfd2 100644
--- a/drivers/clk/samsung/clk-exynos5440.c
+++ b/drivers/clk/samsung/clk-exynos5440.c
@@ -41,12 +41,12 @@ PNAME(mout_armclk_p)	= { "cplla", "cpllb" };
 PNAME(mout_spi_p)	= { "div125", "div200" };
 
 /* fixed rate clocks generated outside the soc */
-struct samsung_fixed_rate_clock exynos5440_fixed_rate_ext_clks[] __initdata = {
+static struct samsung_fixed_rate_clock exynos5440_fixed_rate_ext_clks[] __initdata = {
 	FRATE(none, "xtal", NULL, CLK_IS_ROOT, 0),
 };
 
 /* fixed rate clocks */
-struct samsung_fixed_rate_clock exynos5440_fixed_rate_clks[] __initdata = {
+static struct samsung_fixed_rate_clock exynos5440_fixed_rate_clks[] __initdata = {
 	FRATE(none, "ppll", NULL, CLK_IS_ROOT, 1000000000),
 	FRATE(none, "usb_phy0", NULL, CLK_IS_ROOT, 60000000),
 	FRATE(none, "usb_phy1", NULL, CLK_IS_ROOT, 60000000),
@@ -55,26 +55,26 @@ struct samsung_fixed_rate_clock exynos5440_fixed_rate_clks[] __initdata = {
 };
 
 /* fixed factor clocks */
-struct samsung_fixed_factor_clock exynos5440_fixed_factor_clks[] __initdata = {
+static struct samsung_fixed_factor_clock exynos5440_fixed_factor_clks[] __initdata = {
 	FFACTOR(none, "div250", "ppll", 1, 4, 0),
 	FFACTOR(none, "div200", "ppll", 1, 5, 0),
 	FFACTOR(none, "div125", "div250", 1, 2, 0),
 };
 
 /* mux clocks */
-struct samsung_mux_clock exynos5440_mux_clks[] __initdata = {
+static struct samsung_mux_clock exynos5440_mux_clks[] __initdata = {
 	MUX(none, "mout_spi", mout_spi_p, MISC_DOUT1, 5, 1),
 	MUX_A(arm_clk, "arm_clk", mout_armclk_p,
 			CPU_CLK_STATUS, 0, 1, "armclk"),
 };
 
 /* divider clocks */
-struct samsung_div_clock exynos5440_div_clks[] __initdata = {
+static struct samsung_div_clock exynos5440_div_clks[] __initdata = {
 	DIV(spi_baud, "div_spi", "mout_spi", MISC_DOUT1, 3, 2),
 };
 
 /* gate clocks */
-struct samsung_gate_clock exynos5440_gate_clks[] __initdata = {
+static struct samsung_gate_clock exynos5440_gate_clks[] __initdata = {
 	GATE(pb0_250, "pb0_250", "div250", CLKEN_OV_VAL, 3, 0, 0),
 	GATE(pr0_250, "pr0_250", "div250", CLKEN_OV_VAL, 4, 0, 0),
 	GATE(pr1_250, "pr1_250", "div250", CLKEN_OV_VAL, 5, 0, 0),
@@ -97,13 +97,13 @@ struct samsung_gate_clock exynos5440_gate_clks[] __initdata = {
 	GATE(cs250_o, "cs250_o", "cs250", CLKEN_OV_VAL, 19, 0, 0),
 };
 
-static __initdata struct of_device_id ext_clk_match[] = {
+static struct of_device_id ext_clk_match[] __initdata = {
 	{ .compatible = "samsung,clock-xtal", .data = (void *)0, },
 	{},
 };
 
 /* register exynos5440 clocks */
-void __init exynos5440_clk_init(struct device_node *np)
+static void __init exynos5440_clk_init(struct device_node *np)
 {
 	void __iomem *reg_base;
 
@@ -132,7 +132,7 @@ void __init exynos5440_clk_init(struct device_node *np)
 	samsung_clk_register_gate(exynos5440_gate_clks,
 			ARRAY_SIZE(exynos5440_gate_clks));
 
-	pr_info("Exynos5440: arm_clk = %ldHz\n", _get_rate("armclk"));
+	pr_info("Exynos5440: arm_clk = %ldHz\n", _get_rate("arm_clk"));
 	pr_info("exynos5440 clock initialization complete\n");
 }
 CLK_OF_DECLARE(exynos5440_clk, "samsung,exynos5440-clock", exynos5440_clk_init);
diff --git a/drivers/clk/samsung/clk-pll.c b/drivers/clk/samsung/clk-pll.c
index 362f12dcd944..529e11dc2c6b 100644
--- a/drivers/clk/samsung/clk-pll.c
+++ b/drivers/clk/samsung/clk-pll.c
@@ -10,31 +10,73 @@
 */
 
 #include <linux/errno.h>
+#include <linux/hrtimer.h>
 #include "clk.h"
 #include "clk-pll.h"
 
+#define PLL_TIMEOUT_MS		10
+
+struct samsung_clk_pll {
+	struct clk_hw		hw;
+	void __iomem		*lock_reg;
+	void __iomem		*con_reg;
+	enum samsung_pll_type	type;
+	unsigned int		rate_count;
+	const struct samsung_pll_rate_table *rate_table;
+};
+
+#define to_clk_pll(_hw) container_of(_hw, struct samsung_clk_pll, hw)
+
+static const struct samsung_pll_rate_table *samsung_get_pll_settings(
+				struct samsung_clk_pll *pll, unsigned long rate)
+{
+	const struct samsung_pll_rate_table  *rate_table = pll->rate_table;
+	int i;
+
+	for (i = 0; i < pll->rate_count; i++) {
+		if (rate == rate_table[i].rate)
+			return &rate_table[i];
+	}
+
+	return NULL;
+}
+
+static long samsung_pll_round_rate(struct clk_hw *hw,
+			unsigned long drate, unsigned long *prate)
+{
+	struct samsung_clk_pll *pll = to_clk_pll(hw);
+	const struct samsung_pll_rate_table *rate_table = pll->rate_table;
+	int i;
+
+	/* Assumming rate_table is in descending order */
+	for (i = 0; i < pll->rate_count; i++) {
+		if (drate >= rate_table[i].rate)
+			return rate_table[i].rate;
+	}
+
+	/* return minimum supported value */
+	return rate_table[i - 1].rate;
+}
+
 /*
  * PLL35xx Clock Type
  */
+/* Maximum lock time can be 270 * PDIV cycles */
+#define PLL35XX_LOCK_FACTOR	(270)
 
 #define PLL35XX_MDIV_MASK       (0x3FF)
 #define PLL35XX_PDIV_MASK       (0x3F)
 #define PLL35XX_SDIV_MASK       (0x7)
+#define PLL35XX_LOCK_STAT_MASK	(0x1)
 #define PLL35XX_MDIV_SHIFT      (16)
 #define PLL35XX_PDIV_SHIFT      (8)
 #define PLL35XX_SDIV_SHIFT      (0)
-
-struct samsung_clk_pll35xx {
-	struct clk_hw		hw;
-	const void __iomem	*con_reg;
-};
-
-#define to_clk_pll35xx(_hw) container_of(_hw, struct samsung_clk_pll35xx, hw)
+#define PLL35XX_LOCK_STAT_SHIFT	(29)
 
 static unsigned long samsung_pll35xx_recalc_rate(struct clk_hw *hw,
 				unsigned long parent_rate)
 {
-	struct samsung_clk_pll35xx *pll = to_clk_pll35xx(hw);
+	struct samsung_clk_pll *pll = to_clk_pll(hw);
 	u32 mdiv, pdiv, sdiv, pll_con;
 	u64 fvco = parent_rate;
 
@@ -49,48 +91,80 @@ static unsigned long samsung_pll35xx_recalc_rate(struct clk_hw *hw,
 	return (unsigned long)fvco;
 }
 
-static const struct clk_ops samsung_pll35xx_clk_ops = {
-	.recalc_rate = samsung_pll35xx_recalc_rate,
-};
-
-struct clk * __init samsung_clk_register_pll35xx(const char *name,
-			const char *pname, const void __iomem *con_reg)
+static inline bool samsung_pll35xx_mp_change(
+		const struct samsung_pll_rate_table *rate, u32 pll_con)
 {
-	struct samsung_clk_pll35xx *pll;
-	struct clk *clk;
-	struct clk_init_data init;
+	u32 old_mdiv, old_pdiv;
 
-	pll = kzalloc(sizeof(*pll), GFP_KERNEL);
-	if (!pll) {
-		pr_err("%s: could not allocate pll clk %s\n", __func__, name);
-		return NULL;
+	old_mdiv = (pll_con >> PLL35XX_MDIV_SHIFT) & PLL35XX_MDIV_MASK;
+	old_pdiv = (pll_con >> PLL35XX_PDIV_SHIFT) & PLL35XX_PDIV_MASK;
+
+	return (rate->mdiv != old_mdiv || rate->pdiv != old_pdiv);
+}
+
+static int samsung_pll35xx_set_rate(struct clk_hw *hw, unsigned long drate,
+					unsigned long prate)
+{
+	struct samsung_clk_pll *pll = to_clk_pll(hw);
+	const struct samsung_pll_rate_table *rate;
+	u32 tmp;
+
+	/* Get required rate settings from table */
+	rate = samsung_get_pll_settings(pll, drate);
+	if (!rate) {
+		pr_err("%s: Invalid rate : %lu for pll clk %s\n", __func__,
+			drate, __clk_get_name(hw->clk));
+		return -EINVAL;
 	}
 
-	init.name = name;
-	init.ops = &samsung_pll35xx_clk_ops;
-	init.flags = CLK_GET_RATE_NOCACHE;
-	init.parent_names = &pname;
-	init.num_parents = 1;
+	tmp = __raw_readl(pll->con_reg);
 
-	pll->hw.init = &init;
-	pll->con_reg = con_reg;
+	if (!(samsung_pll35xx_mp_change(rate, tmp))) {
+		/* If only s change, change just s value only*/
+		tmp &= ~(PLL35XX_SDIV_MASK << PLL35XX_SDIV_SHIFT);
+		tmp |= rate->sdiv << PLL35XX_SDIV_SHIFT;
+		__raw_writel(tmp, pll->con_reg);
 
-	clk = clk_register(NULL, &pll->hw);
-	if (IS_ERR(clk)) {
-		pr_err("%s: failed to register pll clock %s\n", __func__,
-				name);
-		kfree(pll);
+		return 0;
 	}
 
-	if (clk_register_clkdev(clk, name, NULL))
-		pr_err("%s: failed to register lookup for %s", __func__, name);
-
-	return clk;
+	/* Set PLL lock time. */
+	__raw_writel(rate->pdiv * PLL35XX_LOCK_FACTOR,
+			pll->lock_reg);
+
+	/* Change PLL PMS values */
+	tmp &= ~((PLL35XX_MDIV_MASK << PLL35XX_MDIV_SHIFT) |
+			(PLL35XX_PDIV_MASK << PLL35XX_PDIV_SHIFT) |
+			(PLL35XX_SDIV_MASK << PLL35XX_SDIV_SHIFT));
+	tmp |= (rate->mdiv << PLL35XX_MDIV_SHIFT) |
+			(rate->pdiv << PLL35XX_PDIV_SHIFT) |
+			(rate->sdiv << PLL35XX_SDIV_SHIFT);
+	__raw_writel(tmp, pll->con_reg);
+
+	/* wait_lock_time */
+	do {
+		cpu_relax();
+		tmp = __raw_readl(pll->con_reg);
+	} while (!(tmp & (PLL35XX_LOCK_STAT_MASK
+				<< PLL35XX_LOCK_STAT_SHIFT)));
+	return 0;
 }
 
+static const struct clk_ops samsung_pll35xx_clk_ops = {
+	.recalc_rate = samsung_pll35xx_recalc_rate,
+	.round_rate = samsung_pll_round_rate,
+	.set_rate = samsung_pll35xx_set_rate,
+};
+
+static const struct clk_ops samsung_pll35xx_clk_min_ops = {
+	.recalc_rate = samsung_pll35xx_recalc_rate,
+};
+
 /*
  * PLL36xx Clock Type
  */
+/* Maximum lock time can be 3000 * PDIV cycles */
+#define PLL36XX_LOCK_FACTOR    (3000)
 
 #define PLL36XX_KDIV_MASK	(0xFFFF)
 #define PLL36XX_MDIV_MASK	(0x1FF)
@@ -99,18 +173,13 @@ struct clk * __init samsung_clk_register_pll35xx(const char *name,
 #define PLL36XX_MDIV_SHIFT	(16)
 #define PLL36XX_PDIV_SHIFT	(8)
 #define PLL36XX_SDIV_SHIFT	(0)
-
-struct samsung_clk_pll36xx {
-	struct clk_hw		hw;
-	const void __iomem	*con_reg;
-};
-
-#define to_clk_pll36xx(_hw) container_of(_hw, struct samsung_clk_pll36xx, hw)
+#define PLL36XX_KDIV_SHIFT	(0)
+#define PLL36XX_LOCK_STAT_SHIFT	(29)
 
 static unsigned long samsung_pll36xx_recalc_rate(struct clk_hw *hw,
 				unsigned long parent_rate)
 {
-	struct samsung_clk_pll36xx *pll = to_clk_pll36xx(hw);
+	struct samsung_clk_pll *pll = to_clk_pll(hw);
 	u32 mdiv, pdiv, sdiv, pll_con0, pll_con1;
 	s16 kdiv;
 	u64 fvco = parent_rate;
@@ -129,68 +198,102 @@ static unsigned long samsung_pll36xx_recalc_rate(struct clk_hw *hw,
 	return (unsigned long)fvco;
 }
 
-static const struct clk_ops samsung_pll36xx_clk_ops = {
-	.recalc_rate = samsung_pll36xx_recalc_rate,
-};
-
-struct clk * __init samsung_clk_register_pll36xx(const char *name,
-			const char *pname, const void __iomem *con_reg)
+static inline bool samsung_pll36xx_mpk_change(
+	const struct samsung_pll_rate_table *rate, u32 pll_con0, u32 pll_con1)
 {
-	struct samsung_clk_pll36xx *pll;
-	struct clk *clk;
-	struct clk_init_data init;
+	u32 old_mdiv, old_pdiv, old_kdiv;
 
-	pll = kzalloc(sizeof(*pll), GFP_KERNEL);
-	if (!pll) {
-		pr_err("%s: could not allocate pll clk %s\n", __func__, name);
-		return NULL;
+	old_mdiv = (pll_con0 >> PLL36XX_MDIV_SHIFT) & PLL36XX_MDIV_MASK;
+	old_pdiv = (pll_con0 >> PLL36XX_PDIV_SHIFT) & PLL36XX_PDIV_MASK;
+	old_kdiv = (pll_con1 >> PLL36XX_KDIV_SHIFT) & PLL36XX_KDIV_MASK;
+
+	return (rate->mdiv != old_mdiv || rate->pdiv != old_pdiv ||
+		rate->kdiv != old_kdiv);
+}
+
+static int samsung_pll36xx_set_rate(struct clk_hw *hw, unsigned long drate,
+					unsigned long parent_rate)
+{
+	struct samsung_clk_pll *pll = to_clk_pll(hw);
+	u32 tmp, pll_con0, pll_con1;
+	const struct samsung_pll_rate_table *rate;
+
+	rate = samsung_get_pll_settings(pll, drate);
+	if (!rate) {
+		pr_err("%s: Invalid rate : %lu for pll clk %s\n", __func__,
+			drate, __clk_get_name(hw->clk));
+		return -EINVAL;
 	}
 
-	init.name = name;
-	init.ops = &samsung_pll36xx_clk_ops;
-	init.flags = CLK_GET_RATE_NOCACHE;
-	init.parent_names = &pname;
-	init.num_parents = 1;
+	pll_con0 = __raw_readl(pll->con_reg);
+	pll_con1 = __raw_readl(pll->con_reg + 4);
 
-	pll->hw.init = &init;
-	pll->con_reg = con_reg;
+	if (!(samsung_pll36xx_mpk_change(rate, pll_con0, pll_con1))) {
+		/* If only s change, change just s value only*/
+		pll_con0 &= ~(PLL36XX_SDIV_MASK << PLL36XX_SDIV_SHIFT);
+		pll_con0 |= (rate->sdiv << PLL36XX_SDIV_SHIFT);
+		__raw_writel(pll_con0, pll->con_reg);
 
-	clk = clk_register(NULL, &pll->hw);
-	if (IS_ERR(clk)) {
-		pr_err("%s: failed to register pll clock %s\n", __func__,
-				name);
-		kfree(pll);
+		return 0;
 	}
 
-	if (clk_register_clkdev(clk, name, NULL))
-		pr_err("%s: failed to register lookup for %s", __func__, name);
-
-	return clk;
+	/* Set PLL lock time. */
+	__raw_writel(rate->pdiv * PLL36XX_LOCK_FACTOR, pll->lock_reg);
+
+	 /* Change PLL PMS values */
+	pll_con0 &= ~((PLL36XX_MDIV_MASK << PLL36XX_MDIV_SHIFT) |
+			(PLL36XX_PDIV_MASK << PLL36XX_PDIV_SHIFT) |
+			(PLL36XX_SDIV_MASK << PLL36XX_SDIV_SHIFT));
+	pll_con0 |= (rate->mdiv << PLL36XX_MDIV_SHIFT) |
+			(rate->pdiv << PLL36XX_PDIV_SHIFT) |
+			(rate->sdiv << PLL36XX_SDIV_SHIFT);
+	__raw_writel(pll_con0, pll->con_reg);
+
+	pll_con1 &= ~(PLL36XX_KDIV_MASK << PLL36XX_KDIV_SHIFT);
+	pll_con1 |= rate->kdiv << PLL36XX_KDIV_SHIFT;
+	__raw_writel(pll_con1, pll->con_reg + 4);
+
+	/* wait_lock_time */
+	do {
+		cpu_relax();
+		tmp = __raw_readl(pll->con_reg);
+	} while (!(tmp & (1 << PLL36XX_LOCK_STAT_SHIFT)));
+
+	return 0;
 }
 
+static const struct clk_ops samsung_pll36xx_clk_ops = {
+	.recalc_rate = samsung_pll36xx_recalc_rate,
+	.set_rate = samsung_pll36xx_set_rate,
+	.round_rate = samsung_pll_round_rate,
+};
+
+static const struct clk_ops samsung_pll36xx_clk_min_ops = {
+	.recalc_rate = samsung_pll36xx_recalc_rate,
+};
+
 /*
  * PLL45xx Clock Type
  */
+#define PLL4502_LOCK_FACTOR	400
+#define PLL4508_LOCK_FACTOR	240
 
 #define PLL45XX_MDIV_MASK	(0x3FF)
 #define PLL45XX_PDIV_MASK	(0x3F)
 #define PLL45XX_SDIV_MASK	(0x7)
+#define PLL45XX_AFC_MASK	(0x1F)
 #define PLL45XX_MDIV_SHIFT	(16)
 #define PLL45XX_PDIV_SHIFT	(8)
 #define PLL45XX_SDIV_SHIFT	(0)
+#define PLL45XX_AFC_SHIFT	(0)
 
-struct samsung_clk_pll45xx {
-	struct clk_hw		hw;
-	enum pll45xx_type	type;
-	const void __iomem	*con_reg;
-};
-
-#define to_clk_pll45xx(_hw) container_of(_hw, struct samsung_clk_pll45xx, hw)
+#define PLL45XX_ENABLE		BIT(31)
+#define PLL45XX_LOCKED		BIT(29)
 
 static unsigned long samsung_pll45xx_recalc_rate(struct clk_hw *hw,
 				unsigned long parent_rate)
 {
-	struct samsung_clk_pll45xx *pll = to_clk_pll45xx(hw);
+	struct samsung_clk_pll *pll = to_clk_pll(hw);
 	u32 mdiv, pdiv, sdiv, pll_con;
 	u64 fvco = parent_rate;
 
@@ -208,54 +311,113 @@ static unsigned long samsung_pll45xx_recalc_rate(struct clk_hw *hw,
 	return (unsigned long)fvco;
 }
 
-static const struct clk_ops samsung_pll45xx_clk_ops = {
-	.recalc_rate = samsung_pll45xx_recalc_rate,
-};
-
-struct clk * __init samsung_clk_register_pll45xx(const char *name,
-			const char *pname, const void __iomem *con_reg,
-			enum pll45xx_type type)
+static bool samsung_pll45xx_mp_change(u32 pll_con0, u32 pll_con1,
+				const struct samsung_pll_rate_table *rate)
 {
-	struct samsung_clk_pll45xx *pll;
-	struct clk *clk;
-	struct clk_init_data init;
+	u32 old_mdiv, old_pdiv, old_afc;
 
-	pll = kzalloc(sizeof(*pll), GFP_KERNEL);
-	if (!pll) {
-		pr_err("%s: could not allocate pll clk %s\n", __func__, name);
-		return NULL;
+	old_mdiv = (pll_con0 >> PLL45XX_MDIV_SHIFT) & PLL45XX_MDIV_MASK;
+	old_pdiv = (pll_con0 >> PLL45XX_PDIV_SHIFT) & PLL45XX_PDIV_MASK;
+	old_afc = (pll_con1 >> PLL45XX_AFC_SHIFT) & PLL45XX_AFC_MASK;
+
+	return (old_mdiv != rate->mdiv || old_pdiv != rate->pdiv
+		|| old_afc != rate->afc);
+}
+
+static int samsung_pll45xx_set_rate(struct clk_hw *hw, unsigned long drate,
+					unsigned long prate)
+{
+	struct samsung_clk_pll *pll = to_clk_pll(hw);
+	const struct samsung_pll_rate_table *rate;
+	u32 con0, con1;
+	ktime_t start;
+
+	/* Get required rate settings from table */
+	rate = samsung_get_pll_settings(pll, drate);
+	if (!rate) {
+		pr_err("%s: Invalid rate : %lu for pll clk %s\n", __func__,
+			drate, __clk_get_name(hw->clk));
+		return -EINVAL;
 	}
 
-	init.name = name;
-	init.ops = &samsung_pll45xx_clk_ops;
-	init.flags = CLK_GET_RATE_NOCACHE;
-	init.parent_names = &pname;
-	init.num_parents = 1;
+	con0 = __raw_readl(pll->con_reg);
+	con1 = __raw_readl(pll->con_reg + 0x4);
 
-	pll->hw.init = &init;
-	pll->con_reg = con_reg;
-	pll->type = type;
+	if (!(samsung_pll45xx_mp_change(con0, con1, rate))) {
+		/* If only s change, change just s value only*/
+		con0 &= ~(PLL45XX_SDIV_MASK << PLL45XX_SDIV_SHIFT);
+		con0 |= rate->sdiv << PLL45XX_SDIV_SHIFT;
+		__raw_writel(con0, pll->con_reg);
 
-	clk = clk_register(NULL, &pll->hw);
-	if (IS_ERR(clk)) {
-		pr_err("%s: failed to register pll clock %s\n", __func__,
-				name);
-		kfree(pll);
+		return 0;
 	}
 
-	if (clk_register_clkdev(clk, name, NULL))
-		pr_err("%s: failed to register lookup for %s", __func__, name);
+	/* Set PLL PMS values. */
+	con0 &= ~((PLL45XX_MDIV_MASK << PLL45XX_MDIV_SHIFT) |
+			(PLL45XX_PDIV_MASK << PLL45XX_PDIV_SHIFT) |
+			(PLL45XX_SDIV_MASK << PLL45XX_SDIV_SHIFT));
+	con0 |= (rate->mdiv << PLL45XX_MDIV_SHIFT) |
+			(rate->pdiv << PLL45XX_PDIV_SHIFT) |
+			(rate->sdiv << PLL45XX_SDIV_SHIFT);
+
+	/* Set PLL AFC value. */
+	con1 = __raw_readl(pll->con_reg + 0x4);
+	con1 &= ~(PLL45XX_AFC_MASK << PLL45XX_AFC_SHIFT);
+	con1 |= (rate->afc << PLL45XX_AFC_SHIFT);
+
+	/* Set PLL lock time. */
+	switch (pll->type) {
+	case pll_4502:
+		__raw_writel(rate->pdiv * PLL4502_LOCK_FACTOR, pll->lock_reg);
+		break;
+	case pll_4508:
+		__raw_writel(rate->pdiv * PLL4508_LOCK_FACTOR, pll->lock_reg);
+		break;
+	default:
+		break;
+	};
+
+	/* Set new configuration. */
+	__raw_writel(con1, pll->con_reg + 0x4);
+	__raw_writel(con0, pll->con_reg);
+
+	/* Wait for locking. */
+	start = ktime_get();
+	while (!(__raw_readl(pll->con_reg) & PLL45XX_LOCKED)) {
+		ktime_t delta = ktime_sub(ktime_get(), start);
+
+		if (ktime_to_ms(delta) > PLL_TIMEOUT_MS) {
+			pr_err("%s: could not lock PLL %s\n",
+					__func__, __clk_get_name(hw->clk));
+			return -EFAULT;
+		}
+
+		cpu_relax();
+	}
 
-	return clk;
+	return 0;
 }
 
+static const struct clk_ops samsung_pll45xx_clk_ops = {
+	.recalc_rate = samsung_pll45xx_recalc_rate,
+	.round_rate = samsung_pll_round_rate,
+	.set_rate = samsung_pll45xx_set_rate,
+};
+
+static const struct clk_ops samsung_pll45xx_clk_min_ops = {
+	.recalc_rate = samsung_pll45xx_recalc_rate,
+};
+
 /*
  * PLL46xx Clock Type
  */
+#define PLL46XX_LOCK_FACTOR	3000
 
+#define PLL46XX_VSEL_MASK	(1)
 #define PLL46XX_MDIV_MASK	(0x1FF)
 #define PLL46XX_PDIV_MASK	(0x3F)
 #define PLL46XX_SDIV_MASK	(0x7)
+#define PLL46XX_VSEL_SHIFT	(27)
 #define PLL46XX_MDIV_SHIFT	(16)
 #define PLL46XX_PDIV_SHIFT	(8)
 #define PLL46XX_SDIV_SHIFT	(0)
@@ -263,19 +425,20 @@ struct clk * __init samsung_clk_register_pll45xx(const char *name,
 #define PLL46XX_KDIV_MASK	(0xFFFF)
 #define PLL4650C_KDIV_MASK	(0xFFF)
 #define PLL46XX_KDIV_SHIFT	(0)
+#define PLL46XX_MFR_MASK	(0x3F)
+#define PLL46XX_MRR_MASK	(0x1F)
+#define PLL46XX_KDIV_SHIFT	(0)
+#define PLL46XX_MFR_SHIFT	(16)
+#define PLL46XX_MRR_SHIFT	(24)
 
-struct samsung_clk_pll46xx {
-	struct clk_hw		hw;
-	enum pll46xx_type	type;
-	const void __iomem	*con_reg;
-};
-
-#define to_clk_pll46xx(_hw) container_of(_hw, struct samsung_clk_pll46xx, hw)
+#define PLL46XX_ENABLE		BIT(31)
+#define PLL46XX_LOCKED		BIT(29)
+#define PLL46XX_VSEL		BIT(27)
 
 static unsigned long samsung_pll46xx_recalc_rate(struct clk_hw *hw,
 				unsigned long parent_rate)
 {
-	struct samsung_clk_pll46xx *pll = to_clk_pll46xx(hw);
+	struct samsung_clk_pll *pll = to_clk_pll(hw);
 	u32 mdiv, pdiv, sdiv, kdiv, pll_con0, pll_con1, shift;
 	u64 fvco = parent_rate;
 
@@ -295,47 +458,175 @@ static unsigned long samsung_pll46xx_recalc_rate(struct clk_hw *hw,
 	return (unsigned long)fvco;
 }
 
+static bool samsung_pll46xx_mpk_change(u32 pll_con0, u32 pll_con1,
+				const struct samsung_pll_rate_table *rate)
+{
+	u32 old_mdiv, old_pdiv, old_kdiv;
+
+	old_mdiv = (pll_con0 >> PLL46XX_MDIV_SHIFT) & PLL46XX_MDIV_MASK;
+	old_pdiv = (pll_con0 >> PLL46XX_PDIV_SHIFT) & PLL46XX_PDIV_MASK;
+	old_kdiv = (pll_con1 >> PLL46XX_KDIV_SHIFT) & PLL46XX_KDIV_MASK;
+
+	return (old_mdiv != rate->mdiv || old_pdiv != rate->pdiv
+		|| old_kdiv != rate->kdiv);
+}
+
+static int samsung_pll46xx_set_rate(struct clk_hw *hw, unsigned long drate,
+					unsigned long prate)
+{
+	struct samsung_clk_pll *pll = to_clk_pll(hw);
+	const struct samsung_pll_rate_table *rate;
+	u32 con0, con1, lock;
+	ktime_t start;
+
+	/* Get required rate settings from table */
+	rate = samsung_get_pll_settings(pll, drate);
+	if (!rate) {
+		pr_err("%s: Invalid rate : %lu for pll clk %s\n", __func__,
+			drate, __clk_get_name(hw->clk));
+		return -EINVAL;
+	}
+
+	con0 = __raw_readl(pll->con_reg);
+	con1 = __raw_readl(pll->con_reg + 0x4);
+
+	if (!(samsung_pll46xx_mpk_change(con0, con1, rate))) {
+		/* If only s change, change just s value only*/
+		con0 &= ~(PLL46XX_SDIV_MASK << PLL46XX_SDIV_SHIFT);
+		con0 |= rate->sdiv << PLL46XX_SDIV_SHIFT;
+		__raw_writel(con0, pll->con_reg);
+
+		return 0;
+	}
+
+	/* Set PLL lock time. */
+	lock = rate->pdiv * PLL46XX_LOCK_FACTOR;
+	if (lock > 0xffff)
+		/* Maximum lock time bitfield is 16-bit. */
+		lock = 0xffff;
+
+	/* Set PLL PMS and VSEL values. */
+	con0 &= ~((PLL46XX_MDIV_MASK << PLL46XX_MDIV_SHIFT) |
+			(PLL46XX_PDIV_MASK << PLL46XX_PDIV_SHIFT) |
+			(PLL46XX_SDIV_MASK << PLL46XX_SDIV_SHIFT) |
+			(PLL46XX_VSEL_MASK << PLL46XX_VSEL_SHIFT));
+	con0 |= (rate->mdiv << PLL46XX_MDIV_SHIFT) |
+			(rate->pdiv << PLL46XX_PDIV_SHIFT) |
+			(rate->sdiv << PLL46XX_SDIV_SHIFT) |
+			(rate->vsel << PLL46XX_VSEL_SHIFT);
+
+	/* Set PLL K, MFR and MRR values. */
+	con1 = __raw_readl(pll->con_reg + 0x4);
+	con1 &= ~((PLL46XX_KDIV_MASK << PLL46XX_KDIV_SHIFT) |
+			(PLL46XX_MFR_MASK << PLL46XX_MFR_SHIFT) |
+			(PLL46XX_MRR_MASK << PLL46XX_MRR_SHIFT));
+	con1 |= (rate->kdiv << PLL46XX_KDIV_SHIFT) |
+			(rate->mfr << PLL46XX_MFR_SHIFT) |
+			(rate->mrr << PLL46XX_MRR_SHIFT);
+
+	/* Write configuration to PLL */
+	__raw_writel(lock, pll->lock_reg);
+	__raw_writel(con0, pll->con_reg);
+	__raw_writel(con1, pll->con_reg + 0x4);
+
+	/* Wait for locking. */
+	start = ktime_get();
+	while (!(__raw_readl(pll->con_reg) & PLL46XX_LOCKED)) {
+		ktime_t delta = ktime_sub(ktime_get(), start);
+
+		if (ktime_to_ms(delta) > PLL_TIMEOUT_MS) {
+			pr_err("%s: could not lock PLL %s\n",
+					__func__, __clk_get_name(hw->clk));
+			return -EFAULT;
+		}
+
+		cpu_relax();
+	}
+
+	return 0;
+}
+
 static const struct clk_ops samsung_pll46xx_clk_ops = {
 	.recalc_rate = samsung_pll46xx_recalc_rate,
+	.round_rate = samsung_pll_round_rate,
+	.set_rate = samsung_pll46xx_set_rate,
+};
+
+static const struct clk_ops samsung_pll46xx_clk_min_ops = {
+	.recalc_rate = samsung_pll46xx_recalc_rate,
 };
 
-struct clk * __init samsung_clk_register_pll46xx(const char *name,
-			const char *pname, const void __iomem *con_reg,
-			enum pll46xx_type type)
+/*
+ * PLL6552 Clock Type
+ */
+
+#define PLL6552_MDIV_MASK	0x3ff
+#define PLL6552_PDIV_MASK	0x3f
+#define PLL6552_SDIV_MASK	0x7
+#define PLL6552_MDIV_SHIFT	16
+#define PLL6552_PDIV_SHIFT	8
+#define PLL6552_SDIV_SHIFT	0
+
+static unsigned long samsung_pll6552_recalc_rate(struct clk_hw *hw,
+						unsigned long parent_rate)
 {
-	struct samsung_clk_pll46xx *pll;
-	struct clk *clk;
-	struct clk_init_data init;
+	struct samsung_clk_pll *pll = to_clk_pll(hw);
+	u32 mdiv, pdiv, sdiv, pll_con;
+	u64 fvco = parent_rate;
 
-	pll = kzalloc(sizeof(*pll), GFP_KERNEL);
-	if (!pll) {
-		pr_err("%s: could not allocate pll clk %s\n", __func__, name);
-		return NULL;
-	}
+	pll_con = __raw_readl(pll->con_reg);
+	mdiv = (pll_con >> PLL6552_MDIV_SHIFT) & PLL6552_MDIV_MASK;
+	pdiv = (pll_con >> PLL6552_PDIV_SHIFT) & PLL6552_PDIV_MASK;
+	sdiv = (pll_con >> PLL6552_SDIV_SHIFT) & PLL6552_SDIV_MASK;
 
-	init.name = name;
-	init.ops = &samsung_pll46xx_clk_ops;
-	init.flags = CLK_GET_RATE_NOCACHE;
-	init.parent_names = &pname;
-	init.num_parents = 1;
+	fvco *= mdiv;
+	do_div(fvco, (pdiv << sdiv));
 
-	pll->hw.init = &init;
-	pll->con_reg = con_reg;
-	pll->type = type;
+	return (unsigned long)fvco;
+}
 
-	clk = clk_register(NULL, &pll->hw);
-	if (IS_ERR(clk)) {
-		pr_err("%s: failed to register pll clock %s\n", __func__,
-				name);
-		kfree(pll);
-	}
+static const struct clk_ops samsung_pll6552_clk_ops = {
+	.recalc_rate = samsung_pll6552_recalc_rate,
+};
 
-	if (clk_register_clkdev(clk, name, NULL))
-		pr_err("%s: failed to register lookup for %s", __func__, name);
+/*
+ * PLL6553 Clock Type
+ */
 
-	return clk;
+#define PLL6553_MDIV_MASK	0xff
+#define PLL6553_PDIV_MASK	0x3f
+#define PLL6553_SDIV_MASK	0x7
+#define PLL6553_KDIV_MASK	0xffff
+#define PLL6553_MDIV_SHIFT	16
+#define PLL6553_PDIV_SHIFT	8
+#define PLL6553_SDIV_SHIFT	0
+#define PLL6553_KDIV_SHIFT	0
+
+static unsigned long samsung_pll6553_recalc_rate(struct clk_hw *hw,
+						unsigned long parent_rate)
+{
+	struct samsung_clk_pll *pll = to_clk_pll(hw);
+	u32 mdiv, pdiv, sdiv, kdiv, pll_con0, pll_con1;
+	u64 fvco = parent_rate;
+
+	pll_con0 = __raw_readl(pll->con_reg);
+	pll_con1 = __raw_readl(pll->con_reg + 0x4);
+	mdiv = (pll_con0 >> PLL6553_MDIV_SHIFT) & PLL6553_MDIV_MASK;
+	pdiv = (pll_con0 >> PLL6553_PDIV_SHIFT) & PLL6553_PDIV_MASK;
+	sdiv = (pll_con0 >> PLL6553_SDIV_SHIFT) & PLL6553_SDIV_MASK;
+	kdiv = (pll_con1 >> PLL6553_KDIV_SHIFT) & PLL6553_KDIV_MASK;
+
+	fvco *= (mdiv << 16) + kdiv;
+	do_div(fvco, (pdiv << sdiv));
+	fvco >>= 16;
+
+	return (unsigned long)fvco;
 }
 
+static const struct clk_ops samsung_pll6553_clk_ops = {
+	.recalc_rate = samsung_pll6553_recalc_rate,
+};
+
 /*
  * PLL2550x Clock Type
  */
@@ -418,3 +709,117 @@ struct clk * __init samsung_clk_register_pll2550x(const char *name,
 
 	return clk;
 }
+
+static void __init _samsung_clk_register_pll(struct samsung_pll_clock *pll_clk,
+						void __iomem *base)
+{
+	struct samsung_clk_pll *pll;
+	struct clk *clk;
+	struct clk_init_data init;
+	int ret, len;
+
+	pll = kzalloc(sizeof(*pll), GFP_KERNEL);
+	if (!pll) {
+		pr_err("%s: could not allocate pll clk %s\n",
+			__func__, pll_clk->name);
+		return;
+	}
+
+	init.name = pll_clk->name;
+	init.flags = pll_clk->flags;
+	init.parent_names = &pll_clk->parent_name;
+	init.num_parents = 1;
+
+	if (pll_clk->rate_table) {
+		/* find count of rates in rate_table */
+		for (len = 0; pll_clk->rate_table[len].rate != 0; )
+			len++;
+
+		pll->rate_count = len;
+		pll->rate_table = kmemdup(pll_clk->rate_table,
+					pll->rate_count *
+					sizeof(struct samsung_pll_rate_table),
+					GFP_KERNEL);
+		WARN(!pll->rate_table,
+			"%s: could not allocate rate table for %s\n",
+			__func__, pll_clk->name);
+	}
+
+	switch (pll_clk->type) {
+	/* clk_ops for 35xx and 2550 are similar */
+	case pll_35xx:
+	case pll_2550:
+		if (!pll->rate_table)
+			init.ops = &samsung_pll35xx_clk_min_ops;
+		else
+			init.ops = &samsung_pll35xx_clk_ops;
+		break;
+	case pll_4500:
+		init.ops = &samsung_pll45xx_clk_min_ops;
+		break;
+	case pll_4502:
+	case pll_4508:
+		if (!pll->rate_table)
+			init.ops = &samsung_pll45xx_clk_min_ops;
+		else
+			init.ops = &samsung_pll45xx_clk_ops;
+		break;
+	/* clk_ops for 36xx and 2650 are similar */
+	case pll_36xx:
+	case pll_2650:
+		if (!pll->rate_table)
+			init.ops = &samsung_pll36xx_clk_min_ops;
+		else
+			init.ops = &samsung_pll36xx_clk_ops;
+		break;
+	case pll_6552:
+		init.ops = &samsung_pll6552_clk_ops;
+		break;
+	case pll_6553:
+		init.ops = &samsung_pll6553_clk_ops;
+		break;
+	case pll_4600:
+	case pll_4650:
+	case pll_4650c:
+		if (!pll->rate_table)
+			init.ops = &samsung_pll46xx_clk_min_ops;
+		else
+			init.ops = &samsung_pll46xx_clk_ops;
+		break;
+	default:
+		pr_warn("%s: Unknown pll type for pll clk %s\n",
+			__func__, pll_clk->name);
+	}
+
+	pll->hw.init = &init;
+	pll->type = pll_clk->type;
+	pll->lock_reg = base + pll_clk->lock_offset;
+	pll->con_reg = base + pll_clk->con_offset;
+
+	clk = clk_register(NULL, &pll->hw);
+	if (IS_ERR(clk)) {
+		pr_err("%s: failed to register pll clock %s : %ld\n",
+			__func__, pll_clk->name, PTR_ERR(clk));
+		kfree(pll);
+		return;
+	}
+
+	samsung_clk_add_lookup(clk, pll_clk->id);
+
+	if (!pll_clk->alias)
+		return;
+
+	ret = clk_register_clkdev(clk, pll_clk->alias, pll_clk->dev_name);
+	if (ret)
+		pr_err("%s: failed to register lookup for %s : %d",
+			__func__, pll_clk->name, ret);
+}
+
+void __init samsung_clk_register_pll(struct samsung_pll_clock *pll_list,
+				unsigned int nr_pll, void __iomem *base)
+{
+	int cnt;
+
+	for (cnt = 0; cnt < nr_pll; cnt++)
+		_samsung_clk_register_pll(&pll_list[cnt], base);
+}
diff --git a/drivers/clk/samsung/clk-pll.h b/drivers/clk/samsung/clk-pll.h
index f33786e9a78b..6c39030080fb 100644
--- a/drivers/clk/samsung/clk-pll.h
+++ b/drivers/clk/samsung/clk-pll.h
@@ -12,28 +12,83 @@
 #ifndef __SAMSUNG_CLK_PLL_H
 #define __SAMSUNG_CLK_PLL_H
 
-enum pll45xx_type {
+enum samsung_pll_type {
+	pll_35xx,
+	pll_36xx,
+	pll_2550,
+	pll_2650,
 	pll_4500,
 	pll_4502,
-	pll_4508
-};
-
-enum pll46xx_type {
+	pll_4508,
 	pll_4600,
 	pll_4650,
 	pll_4650c,
+	pll_6552,
+	pll_6553,
+};
+
+#define PLL_35XX_RATE(_rate, _m, _p, _s)			\
+	{							\
+		.rate	=	(_rate),				\
+		.mdiv	=	(_m),				\
+		.pdiv	=	(_p),				\
+		.sdiv	=	(_s),				\
+	}
+
+#define PLL_36XX_RATE(_rate, _m, _p, _s, _k)			\
+	{							\
+		.rate	=	(_rate),				\
+		.mdiv	=	(_m),				\
+		.pdiv	=	(_p),				\
+		.sdiv	=	(_s),				\
+		.kdiv	=	(_k),				\
+	}
+
+#define PLL_45XX_RATE(_rate, _m, _p, _s, _afc)			\
+	{							\
+		.rate	=	(_rate),			\
+		.mdiv	=	(_m),				\
+		.pdiv	=	(_p),				\
+		.sdiv	=	(_s),				\
+		.afc	=	(_afc),				\
+	}
+
+#define PLL_4600_RATE(_rate, _m, _p, _s, _k, _vsel)		\
+	{							\
+		.rate	=	(_rate),			\
+		.mdiv	=	(_m),				\
+		.pdiv	=	(_p),				\
+		.sdiv	=	(_s),				\
+		.kdiv	=	(_k),				\
+		.vsel	=	(_vsel),			\
+	}
+
+#define PLL_4650_RATE(_rate, _m, _p, _s, _k, _mfr, _mrr, _vsel)	\
+	{							\
+		.rate	=	(_rate),			\
+		.mdiv	=	(_m),				\
+		.pdiv	=	(_p),				\
+		.sdiv	=	(_s),				\
+		.kdiv	=	(_k),				\
+		.mfr	=	(_mfr),				\
+		.mrr	=	(_mrr),				\
+		.vsel	=	(_vsel),			\
+	}
+
+/* NOTE: Rate table should be kept sorted in descending order. */
+
+struct samsung_pll_rate_table {
+	unsigned int rate;
+	unsigned int pdiv;
+	unsigned int mdiv;
+	unsigned int sdiv;
+	unsigned int kdiv;
+	unsigned int afc;
+	unsigned int mfr;
+	unsigned int mrr;
+	unsigned int vsel;
 };
 
-extern struct clk * __init samsung_clk_register_pll35xx(const char *name,
-			const char *pname, const void __iomem *con_reg);
-extern struct clk * __init samsung_clk_register_pll36xx(const char *name,
-			const char *pname, const void __iomem *con_reg);
-extern struct clk * __init samsung_clk_register_pll45xx(const char *name,
-			const char *pname, const void __iomem *con_reg,
-			enum pll45xx_type type);
-extern struct clk * __init samsung_clk_register_pll46xx(const char *name,
-			const char *pname, const void __iomem *con_reg,
-			enum pll46xx_type type);
 extern struct clk * __init samsung_clk_register_pll2550x(const char *name,
 			const char *pname, const void __iomem *reg_base,
 			const unsigned long offset);
diff --git a/drivers/clk/samsung/clk-s3c64xx.c b/drivers/clk/samsung/clk-s3c64xx.c
new file mode 100644
index 000000000000..7d2c84265947
--- /dev/null
+++ b/drivers/clk/samsung/clk-s3c64xx.c
@@ -0,0 +1,473 @@
+/*
+ * Copyright (c) 2013 Tomasz Figa <tomasz.figa at gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Common Clock Framework support for all S3C64xx SoCs.
+*/
+
+#include <linux/clk.h>
+#include <linux/clkdev.h>
+#include <linux/clk-provider.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+
+#include <dt-bindings/clock/samsung,s3c64xx-clock.h>
+
+#include "clk.h"
+#include "clk-pll.h"
+
+/* S3C64xx clock controller register offsets. */
+#define APLL_LOCK		0x000
+#define MPLL_LOCK		0x004
+#define EPLL_LOCK		0x008
+#define APLL_CON		0x00c
+#define MPLL_CON		0x010
+#define EPLL_CON0		0x014
+#define EPLL_CON1		0x018
+#define CLK_SRC			0x01c
+#define CLK_DIV0		0x020
+#define CLK_DIV1		0x024
+#define CLK_DIV2		0x028
+#define HCLK_GATE		0x030
+#define PCLK_GATE		0x034
+#define SCLK_GATE		0x038
+#define MEM0_GATE		0x03c
+#define CLK_SRC2		0x10c
+#define OTHERS			0x900
+
+/* Helper macros to define clock arrays. */
+#define FIXED_RATE_CLOCKS(name)	\
+		static struct samsung_fixed_rate_clock name[]
+#define MUX_CLOCKS(name)	\
+		static struct samsung_mux_clock name[]
+#define DIV_CLOCKS(name)	\
+		static struct samsung_div_clock name[]
+#define GATE_CLOCKS(name)	\
+		static struct samsung_gate_clock name[]
+
+/* Helper macros for gate types present on S3C64xx. */
+#define GATE_BUS(_id, cname, pname, o, b) \
+		GATE(_id, cname, pname, o, b, 0, 0)
+#define GATE_SCLK(_id, cname, pname, o, b) \
+		GATE(_id, cname, pname, o, b, CLK_SET_RATE_PARENT, 0)
+#define GATE_ON(_id, cname, pname, o, b) \
+		GATE(_id, cname, pname, o, b, CLK_IGNORE_UNUSED, 0)
+
+/* list of PLLs to be registered */
+enum s3c64xx_plls {
+	apll, mpll, epll,
+};
+
+/*
+ * List of controller registers to be saved and restored during
+ * a suspend/resume cycle.
+ */
+static unsigned long s3c64xx_clk_regs[] __initdata = {
+	APLL_LOCK,
+	MPLL_LOCK,
+	EPLL_LOCK,
+	APLL_CON,
+	MPLL_CON,
+	EPLL_CON0,
+	EPLL_CON1,
+	CLK_SRC,
+	CLK_DIV0,
+	CLK_DIV1,
+	CLK_DIV2,
+	HCLK_GATE,
+	PCLK_GATE,
+	SCLK_GATE,
+};
+
+static unsigned long s3c6410_clk_regs[] __initdata = {
+	CLK_SRC2,
+	MEM0_GATE,
+};
+
+/* List of parent clocks common for all S3C64xx SoCs. */
+PNAME(spi_mmc_p)	= { "mout_epll", "dout_mpll", "fin_pll", "clk27m" };
+PNAME(uart_p)		= { "mout_epll", "dout_mpll" };
+PNAME(audio0_p)		= { "mout_epll", "dout_mpll", "fin_pll", "iiscdclk0",
+				"pcmcdclk0", "none", "none", "none" };
+PNAME(audio1_p)		= { "mout_epll", "dout_mpll", "fin_pll", "iiscdclk1",
+				"pcmcdclk0", "none", "none", "none" };
+PNAME(mfc_p)		= { "hclkx2", "mout_epll" };
+PNAME(apll_p)		= { "fin_pll", "fout_apll" };
+PNAME(mpll_p)		= { "fin_pll", "fout_mpll" };
+PNAME(epll_p)		= { "fin_pll", "fout_epll" };
+PNAME(hclkx2_p)		= { "mout_mpll", "mout_apll" };
+
+/* S3C6400-specific parent clocks. */
+PNAME(scaler_lcd_p6400)	= { "mout_epll", "dout_mpll", "none", "none" };
+PNAME(irda_p6400)	= { "mout_epll", "dout_mpll", "none", "clk48m" };
+PNAME(uhost_p6400)	= { "clk48m", "mout_epll", "dout_mpll", "none" };
+
+/* S3C6410-specific parent clocks. */
+PNAME(clk27_p6410)	= { "clk27m", "fin_pll" };
+PNAME(scaler_lcd_p6410)	= { "mout_epll", "dout_mpll", "fin_pll", "none" };
+PNAME(irda_p6410)	= { "mout_epll", "dout_mpll", "fin_pll", "clk48m" };
+PNAME(uhost_p6410)	= { "clk48m", "mout_epll", "dout_mpll", "fin_pll" };
+PNAME(audio2_p6410)	= { "mout_epll", "dout_mpll", "fin_pll", "iiscdclk2",
+				"pcmcdclk1", "none", "none", "none" };
+
+/* Fixed rate clocks generated outside the SoC. */
+FIXED_RATE_CLOCKS(s3c64xx_fixed_rate_ext_clks) __initdata = {
+	FRATE(0, "fin_pll", NULL, CLK_IS_ROOT, 0),
+	FRATE(0, "xusbxti", NULL, CLK_IS_ROOT, 0),
+};
+
+/* Fixed rate clocks generated inside the SoC. */
+FIXED_RATE_CLOCKS(s3c64xx_fixed_rate_clks) __initdata = {
+	FRATE(CLK27M, "clk27m", NULL, CLK_IS_ROOT, 27000000),
+	FRATE(CLK48M, "clk48m", NULL, CLK_IS_ROOT, 48000000),
+};
+
+/* List of clock muxes present on all S3C64xx SoCs. */
+MUX_CLOCKS(s3c64xx_mux_clks) __initdata = {
+	MUX_F(0, "mout_syncmux", hclkx2_p, OTHERS, 6, 1, 0, CLK_MUX_READ_ONLY),
+	MUX(MOUT_APLL, "mout_apll", apll_p, CLK_SRC, 0, 1),
+	MUX(MOUT_MPLL, "mout_mpll", mpll_p, CLK_SRC, 1, 1),
+	MUX(MOUT_EPLL, "mout_epll", epll_p, CLK_SRC, 2, 1),
+	MUX(MOUT_MFC, "mout_mfc", mfc_p, CLK_SRC, 4, 1),
+	MUX(MOUT_AUDIO0, "mout_audio0", audio0_p, CLK_SRC, 7, 3),
+	MUX(MOUT_AUDIO1, "mout_audio1", audio1_p, CLK_SRC, 10, 3),
+	MUX(MOUT_UART, "mout_uart", uart_p, CLK_SRC, 13, 1),
+	MUX(MOUT_SPI0, "mout_spi0", spi_mmc_p, CLK_SRC, 14, 2),
+	MUX(MOUT_SPI1, "mout_spi1", spi_mmc_p, CLK_SRC, 16, 2),
+	MUX(MOUT_MMC0, "mout_mmc0", spi_mmc_p, CLK_SRC, 18, 2),
+	MUX(MOUT_MMC1, "mout_mmc1", spi_mmc_p, CLK_SRC, 20, 2),
+	MUX(MOUT_MMC2, "mout_mmc2", spi_mmc_p, CLK_SRC, 22, 2),
+};
+
+/* List of clock muxes present on S3C6400. */
+MUX_CLOCKS(s3c6400_mux_clks) __initdata = {
+	MUX(MOUT_UHOST, "mout_uhost", uhost_p6400, CLK_SRC, 5, 2),
+	MUX(MOUT_IRDA, "mout_irda", irda_p6400, CLK_SRC, 24, 2),
+	MUX(MOUT_LCD, "mout_lcd", scaler_lcd_p6400, CLK_SRC, 26, 2),
+	MUX(MOUT_SCALER, "mout_scaler", scaler_lcd_p6400, CLK_SRC, 28, 2),
+};
+
+/* List of clock muxes present on S3C6410. */
+MUX_CLOCKS(s3c6410_mux_clks) __initdata = {
+	MUX(MOUT_UHOST, "mout_uhost", uhost_p6410, CLK_SRC, 5, 2),
+	MUX(MOUT_IRDA, "mout_irda", irda_p6410, CLK_SRC, 24, 2),
+	MUX(MOUT_LCD, "mout_lcd", scaler_lcd_p6410, CLK_SRC, 26, 2),
+	MUX(MOUT_SCALER, "mout_scaler", scaler_lcd_p6410, CLK_SRC, 28, 2),
+	MUX(MOUT_DAC27, "mout_dac27", clk27_p6410, CLK_SRC, 30, 1),
+	MUX(MOUT_TV27, "mout_tv27", clk27_p6410, CLK_SRC, 31, 1),
+	MUX(MOUT_AUDIO2, "mout_audio2", audio2_p6410, CLK_SRC2, 0, 3),
+};
+
+/* List of clock dividers present on all S3C64xx SoCs. */
+DIV_CLOCKS(s3c64xx_div_clks) __initdata = {
+	DIV(DOUT_MPLL, "dout_mpll", "mout_mpll", CLK_DIV0, 4, 1),
+	DIV(HCLKX2, "hclkx2", "mout_syncmux", CLK_DIV0, 9, 3),
+	DIV(HCLK, "hclk", "hclkx2", CLK_DIV0, 8, 1),
+	DIV(PCLK, "pclk", "hclkx2", CLK_DIV0, 12, 4),
+	DIV(DOUT_SECUR, "dout_secur", "hclkx2", CLK_DIV0, 18, 2),
+	DIV(DOUT_CAM, "dout_cam", "hclkx2", CLK_DIV0, 20, 4),
+	DIV(DOUT_JPEG, "dout_jpeg", "hclkx2", CLK_DIV0, 24, 4),
+	DIV(DOUT_MFC, "dout_mfc", "mout_mfc", CLK_DIV0, 28, 4),
+	DIV(DOUT_MMC0, "dout_mmc0", "mout_mmc0", CLK_DIV1, 0, 4),
+	DIV(DOUT_MMC1, "dout_mmc1", "mout_mmc1", CLK_DIV1, 4, 4),
+	DIV(DOUT_MMC2, "dout_mmc2", "mout_mmc2", CLK_DIV1, 8, 4),
+	DIV(DOUT_LCD, "dout_lcd", "mout_lcd", CLK_DIV1, 12, 4),
+	DIV(DOUT_SCALER, "dout_scaler", "mout_scaler", CLK_DIV1, 16, 4),
+	DIV(DOUT_UHOST, "dout_uhost", "mout_uhost", CLK_DIV1, 20, 4),
+	DIV(DOUT_SPI0, "dout_spi0", "mout_spi0", CLK_DIV2, 0, 4),
+	DIV(DOUT_SPI1, "dout_spi1", "mout_spi1", CLK_DIV2, 4, 4),
+	DIV(DOUT_AUDIO0, "dout_audio0", "mout_audio0", CLK_DIV2, 8, 4),
+	DIV(DOUT_AUDIO1, "dout_audio1", "mout_audio1", CLK_DIV2, 12, 4),
+	DIV(DOUT_UART, "dout_uart", "mout_uart", CLK_DIV2, 16, 4),
+	DIV(DOUT_IRDA, "dout_irda", "mout_irda", CLK_DIV2, 20, 4),
+};
+
+/* List of clock dividers present on S3C6400. */
+DIV_CLOCKS(s3c6400_div_clks) __initdata = {
+	DIV(ARMCLK, "armclk", "mout_apll", CLK_DIV0, 0, 3),
+};
+
+/* List of clock dividers present on S3C6410. */
+DIV_CLOCKS(s3c6410_div_clks) __initdata = {
+	DIV(ARMCLK, "armclk", "mout_apll", CLK_DIV0, 0, 4),
+	DIV(DOUT_FIMC, "dout_fimc", "hclk", CLK_DIV1, 24, 4),
+	DIV(DOUT_AUDIO2, "dout_audio2", "mout_audio2", CLK_DIV2, 24, 4),
+};
+
+/* List of clock gates present on all S3C64xx SoCs. */
+GATE_CLOCKS(s3c64xx_gate_clks) __initdata = {
+	GATE_BUS(HCLK_UHOST, "hclk_uhost", "hclk", HCLK_GATE, 29),
+	GATE_BUS(HCLK_SECUR, "hclk_secur", "hclk", HCLK_GATE, 28),
+	GATE_BUS(HCLK_SDMA1, "hclk_sdma1", "hclk", HCLK_GATE, 27),
+	GATE_BUS(HCLK_SDMA0, "hclk_sdma0", "hclk", HCLK_GATE, 26),
+	GATE_ON(HCLK_DDR1, "hclk_ddr1", "hclk", HCLK_GATE, 24),
+	GATE_BUS(HCLK_USB, "hclk_usb", "hclk", HCLK_GATE, 20),
+	GATE_BUS(HCLK_HSMMC2, "hclk_hsmmc2", "hclk", HCLK_GATE, 19),
+	GATE_BUS(HCLK_HSMMC1, "hclk_hsmmc1", "hclk", HCLK_GATE, 18),
+	GATE_BUS(HCLK_HSMMC0, "hclk_hsmmc0", "hclk", HCLK_GATE, 17),
+	GATE_BUS(HCLK_MDP, "hclk_mdp", "hclk", HCLK_GATE, 16),
+	GATE_BUS(HCLK_DHOST, "hclk_dhost", "hclk", HCLK_GATE, 15),
+	GATE_BUS(HCLK_IHOST, "hclk_ihost", "hclk", HCLK_GATE, 14),
+	GATE_BUS(HCLK_DMA1, "hclk_dma1", "hclk", HCLK_GATE, 13),
+	GATE_BUS(HCLK_DMA0, "hclk_dma0", "hclk", HCLK_GATE, 12),
+	GATE_BUS(HCLK_JPEG, "hclk_jpeg", "hclk", HCLK_GATE, 11),
+	GATE_BUS(HCLK_CAMIF, "hclk_camif", "hclk", HCLK_GATE, 10),
+	GATE_BUS(HCLK_SCALER, "hclk_scaler", "hclk", HCLK_GATE, 9),
+	GATE_BUS(HCLK_2D, "hclk_2d", "hclk", HCLK_GATE, 8),
+	GATE_BUS(HCLK_TV, "hclk_tv", "hclk", HCLK_GATE, 7),
+	GATE_BUS(HCLK_POST0, "hclk_post0", "hclk", HCLK_GATE, 5),
+	GATE_BUS(HCLK_ROT, "hclk_rot", "hclk", HCLK_GATE, 4),
+	GATE_BUS(HCLK_LCD, "hclk_lcd", "hclk", HCLK_GATE, 3),
+	GATE_BUS(HCLK_TZIC, "hclk_tzic", "hclk", HCLK_GATE, 2),
+	GATE_ON(HCLK_INTC, "hclk_intc", "hclk", HCLK_GATE, 1),
+	GATE_ON(PCLK_SKEY, "pclk_skey", "pclk", PCLK_GATE, 24),
+	GATE_ON(PCLK_CHIPID, "pclk_chipid", "pclk", PCLK_GATE, 23),
+	GATE_BUS(PCLK_SPI1, "pclk_spi1", "pclk", PCLK_GATE, 22),
+	GATE_BUS(PCLK_SPI0, "pclk_spi0", "pclk", PCLK_GATE, 21),
+	GATE_BUS(PCLK_HSIRX, "pclk_hsirx", "pclk", PCLK_GATE, 20),
+	GATE_BUS(PCLK_HSITX, "pclk_hsitx", "pclk", PCLK_GATE, 19),
+	GATE_ON(PCLK_GPIO, "pclk_gpio", "pclk", PCLK_GATE, 18),
+	GATE_BUS(PCLK_IIC0, "pclk_iic0", "pclk", PCLK_GATE, 17),
+	GATE_BUS(PCLK_IIS1, "pclk_iis1", "pclk", PCLK_GATE, 16),
+	GATE_BUS(PCLK_IIS0, "pclk_iis0", "pclk", PCLK_GATE, 15),
+	GATE_BUS(PCLK_AC97, "pclk_ac97", "pclk", PCLK_GATE, 14),
+	GATE_BUS(PCLK_TZPC, "pclk_tzpc", "pclk", PCLK_GATE, 13),
+	GATE_BUS(PCLK_TSADC, "pclk_tsadc", "pclk", PCLK_GATE, 12),
+	GATE_BUS(PCLK_KEYPAD, "pclk_keypad", "pclk", PCLK_GATE, 11),
+	GATE_BUS(PCLK_IRDA, "pclk_irda", "pclk", PCLK_GATE, 10),
+	GATE_BUS(PCLK_PCM1, "pclk_pcm1", "pclk", PCLK_GATE, 9),
+	GATE_BUS(PCLK_PCM0, "pclk_pcm0", "pclk", PCLK_GATE, 8),
+	GATE_BUS(PCLK_PWM, "pclk_pwm", "pclk", PCLK_GATE, 7),
+	GATE_BUS(PCLK_RTC, "pclk_rtc", "pclk", PCLK_GATE, 6),
+	GATE_BUS(PCLK_WDT, "pclk_wdt", "pclk", PCLK_GATE, 5),
+	GATE_BUS(PCLK_UART3, "pclk_uart3", "pclk", PCLK_GATE, 4),
+	GATE_BUS(PCLK_UART2, "pclk_uart2", "pclk", PCLK_GATE, 3),
+	GATE_BUS(PCLK_UART1, "pclk_uart1", "pclk", PCLK_GATE, 2),
+	GATE_BUS(PCLK_UART0, "pclk_uart0", "pclk", PCLK_GATE, 1),
+	GATE_BUS(PCLK_MFC, "pclk_mfc", "pclk", PCLK_GATE, 0),
+	GATE_SCLK(SCLK_UHOST, "sclk_uhost", "dout_uhost", SCLK_GATE, 30),
+	GATE_SCLK(SCLK_MMC2_48, "sclk_mmc2_48", "clk48m", SCLK_GATE, 29),
+	GATE_SCLK(SCLK_MMC1_48, "sclk_mmc1_48", "clk48m", SCLK_GATE, 28),
+	GATE_SCLK(SCLK_MMC0_48, "sclk_mmc0_48", "clk48m", SCLK_GATE, 27),
+	GATE_SCLK(SCLK_MMC2, "sclk_mmc2", "dout_mmc2", SCLK_GATE, 26),
+	GATE_SCLK(SCLK_MMC1, "sclk_mmc1", "dout_mmc1", SCLK_GATE, 25),
+	GATE_SCLK(SCLK_MMC0, "sclk_mmc0", "dout_mmc0", SCLK_GATE, 24),
+	GATE_SCLK(SCLK_SPI1_48, "sclk_spi1_48", "clk48m", SCLK_GATE, 23),
+	GATE_SCLK(SCLK_SPI0_48, "sclk_spi0_48", "clk48m", SCLK_GATE, 22),
+	GATE_SCLK(SCLK_SPI1, "sclk_spi1", "dout_spi1", SCLK_GATE, 21),
+	GATE_SCLK(SCLK_SPI0, "sclk_spi0", "dout_spi0", SCLK_GATE, 20),
+	GATE_SCLK(SCLK_DAC27, "sclk_dac27", "mout_dac27", SCLK_GATE, 19),
+	GATE_SCLK(SCLK_TV27, "sclk_tv27", "mout_tv27", SCLK_GATE, 18),
+	GATE_SCLK(SCLK_SCALER27, "sclk_scaler27", "clk27m", SCLK_GATE, 17),
+	GATE_SCLK(SCLK_SCALER, "sclk_scaler", "dout_scaler", SCLK_GATE, 16),
+	GATE_SCLK(SCLK_LCD27, "sclk_lcd27", "clk27m", SCLK_GATE, 15),
+	GATE_SCLK(SCLK_LCD, "sclk_lcd", "dout_lcd", SCLK_GATE, 14),
+	GATE_SCLK(SCLK_POST0_27, "sclk_post0_27", "clk27m", SCLK_GATE, 12),
+	GATE_SCLK(SCLK_POST0, "sclk_post0", "dout_lcd", SCLK_GATE, 10),
+	GATE_SCLK(SCLK_AUDIO1, "sclk_audio1", "dout_audio1", SCLK_GATE, 9),
+	GATE_SCLK(SCLK_AUDIO0, "sclk_audio0", "dout_audio0", SCLK_GATE, 8),
+	GATE_SCLK(SCLK_SECUR, "sclk_secur", "dout_secur", SCLK_GATE, 7),
+	GATE_SCLK(SCLK_IRDA, "sclk_irda", "dout_irda", SCLK_GATE, 6),
+	GATE_SCLK(SCLK_UART, "sclk_uart", "dout_uart", SCLK_GATE, 5),
+	GATE_SCLK(SCLK_MFC, "sclk_mfc", "dout_mfc", SCLK_GATE, 3),
+	GATE_SCLK(SCLK_CAM, "sclk_cam", "dout_cam", SCLK_GATE, 2),
+	GATE_SCLK(SCLK_JPEG, "sclk_jpeg", "dout_jpeg", SCLK_GATE, 1),
+};
+
+/* List of clock gates present on S3C6400. */
+GATE_CLOCKS(s3c6400_gate_clks) __initdata = {
+	GATE_ON(HCLK_DDR0, "hclk_ddr0", "hclk", HCLK_GATE, 23),
+	GATE_SCLK(SCLK_ONENAND, "sclk_onenand", "parent", SCLK_GATE, 4),
+};
+
+/* List of clock gates present on S3C6410. */
+GATE_CLOCKS(s3c6410_gate_clks) __initdata = {
+	GATE_BUS(HCLK_3DSE, "hclk_3dse", "hclk", HCLK_GATE, 31),
+	GATE_ON(HCLK_IROM, "hclk_irom", "hclk", HCLK_GATE, 25),
+	GATE_ON(HCLK_MEM1, "hclk_mem1", "hclk", HCLK_GATE, 22),
+	GATE_ON(HCLK_MEM0, "hclk_mem0", "hclk", HCLK_GATE, 21),
+	GATE_BUS(HCLK_MFC, "hclk_mfc", "hclk", HCLK_GATE, 0),
+	GATE_BUS(PCLK_IIC1, "pclk_iic1", "pclk", PCLK_GATE, 27),
+	GATE_BUS(PCLK_IIS2, "pclk_iis2", "pclk", PCLK_GATE, 26),
+	GATE_SCLK(SCLK_FIMC, "sclk_fimc", "dout_fimc", SCLK_GATE, 13),
+	GATE_SCLK(SCLK_AUDIO2, "sclk_audio2", "dout_audio2", SCLK_GATE, 11),
+	GATE_BUS(MEM0_CFCON, "mem0_cfcon", "hclk_mem0", MEM0_GATE, 5),
+	GATE_BUS(MEM0_ONENAND1, "mem0_onenand1", "hclk_mem0", MEM0_GATE, 4),
+	GATE_BUS(MEM0_ONENAND0, "mem0_onenand0", "hclk_mem0", MEM0_GATE, 3),
+	GATE_BUS(MEM0_NFCON, "mem0_nfcon", "hclk_mem0", MEM0_GATE, 2),
+	GATE_ON(MEM0_SROM, "mem0_srom", "hclk_mem0", MEM0_GATE, 1),
+};
+
+/* List of PLL clocks. */
+static struct samsung_pll_clock s3c64xx_pll_clks[] __initdata = {
+	[apll] = PLL(pll_6552, FOUT_APLL, "fout_apll", "fin_pll",
+						APLL_LOCK, APLL_CON, NULL),
+	[mpll] = PLL(pll_6552, FOUT_MPLL, "fout_mpll", "fin_pll",
+						MPLL_LOCK, MPLL_CON, NULL),
+	[epll] = PLL(pll_6553, FOUT_EPLL, "fout_epll", "fin_pll",
+						EPLL_LOCK, EPLL_CON0, NULL),
+};
+
+/* Aliases for common s3c64xx clocks. */
+static struct samsung_clock_alias s3c64xx_clock_aliases[] = {
+	ALIAS(FOUT_APLL, NULL, "fout_apll"),
+	ALIAS(FOUT_MPLL, NULL, "fout_mpll"),
+	ALIAS(FOUT_EPLL, NULL, "fout_epll"),
+	ALIAS(MOUT_EPLL, NULL, "mout_epll"),
+	ALIAS(DOUT_MPLL, NULL, "dout_mpll"),
+	ALIAS(HCLKX2, NULL, "hclk2"),
+	ALIAS(HCLK, NULL, "hclk"),
+	ALIAS(PCLK, NULL, "pclk"),
+	ALIAS(PCLK, NULL, "clk_uart_baud2"),
+	ALIAS(ARMCLK, NULL, "armclk"),
+	ALIAS(HCLK_UHOST, "s3c2410-ohci", "usb-host"),
+	ALIAS(HCLK_USB, "s3c-hsotg", "otg"),
+	ALIAS(HCLK_HSMMC2, "s3c-sdhci.2", "hsmmc"),
+	ALIAS(HCLK_HSMMC2, "s3c-sdhci.2", "mmc_busclk.0"),
+	ALIAS(HCLK_HSMMC1, "s3c-sdhci.1", "hsmmc"),
+	ALIAS(HCLK_HSMMC1, "s3c-sdhci.1", "mmc_busclk.0"),
+	ALIAS(HCLK_HSMMC0, "s3c-sdhci.0", "hsmmc"),
+	ALIAS(HCLK_HSMMC0, "s3c-sdhci.0", "mmc_busclk.0"),
+	ALIAS(HCLK_DMA1, NULL, "dma1"),
+	ALIAS(HCLK_DMA0, NULL, "dma0"),
+	ALIAS(HCLK_CAMIF, "s3c-camif", "camif"),
+	ALIAS(HCLK_LCD, "s3c-fb", "lcd"),
+	ALIAS(PCLK_SPI1, "s3c6410-spi.1", "spi"),
+	ALIAS(PCLK_SPI0, "s3c6410-spi.0", "spi"),
+	ALIAS(PCLK_IIC0, "s3c2440-i2c.0", "i2c"),
+	ALIAS(PCLK_IIS1, "samsung-i2s.1", "iis"),
+	ALIAS(PCLK_IIS0, "samsung-i2s.0", "iis"),
+	ALIAS(PCLK_AC97, "samsung-ac97", "ac97"),
+	ALIAS(PCLK_TSADC, "s3c64xx-adc", "adc"),
+	ALIAS(PCLK_KEYPAD, "samsung-keypad", "keypad"),
+	ALIAS(PCLK_PCM1, "samsung-pcm.1", "pcm"),
+	ALIAS(PCLK_PCM0, "samsung-pcm.0", "pcm"),
+	ALIAS(PCLK_PWM, NULL, "timers"),
+	ALIAS(PCLK_RTC, "s3c64xx-rtc", "rtc"),
+	ALIAS(PCLK_WDT, NULL, "watchdog"),
+	ALIAS(PCLK_UART3, "s3c6400-uart.3", "uart"),
+	ALIAS(PCLK_UART2, "s3c6400-uart.2", "uart"),
+	ALIAS(PCLK_UART1, "s3c6400-uart.1", "uart"),
+	ALIAS(PCLK_UART0, "s3c6400-uart.0", "uart"),
+	ALIAS(SCLK_UHOST, "s3c2410-ohci", "usb-bus-host"),
+	ALIAS(SCLK_MMC2, "s3c-sdhci.2", "mmc_busclk.2"),
+	ALIAS(SCLK_MMC1, "s3c-sdhci.1", "mmc_busclk.2"),
+	ALIAS(SCLK_MMC0, "s3c-sdhci.0", "mmc_busclk.2"),
+	ALIAS(SCLK_SPI1, "s3c6410-spi.1", "spi-bus"),
+	ALIAS(SCLK_SPI0, "s3c6410-spi.0", "spi-bus"),
+	ALIAS(SCLK_AUDIO1, "samsung-pcm.1", "audio-bus"),
+	ALIAS(SCLK_AUDIO1, "samsung-i2s.1", "audio-bus"),
+	ALIAS(SCLK_AUDIO0, "samsung-pcm.0", "audio-bus"),
+	ALIAS(SCLK_AUDIO0, "samsung-i2s.0", "audio-bus"),
+	ALIAS(SCLK_UART, NULL, "clk_uart_baud3"),
+	ALIAS(SCLK_CAM, "s3c-camif", "camera"),
+};
+
+/* Aliases for s3c6400-specific clocks. */
+static struct samsung_clock_alias s3c6400_clock_aliases[] = {
+	/* Nothing to place here yet. */
+};
+
+/* Aliases for s3c6410-specific clocks. */
+static struct samsung_clock_alias s3c6410_clock_aliases[] = {
+	ALIAS(PCLK_IIC1, "s3c2440-i2c.1", "i2c"),
+	ALIAS(PCLK_IIS2, "samsung-i2s.2", "iis"),
+	ALIAS(SCLK_FIMC, "s3c-camif", "fimc"),
+	ALIAS(SCLK_AUDIO2, "samsung-i2s.2", "audio-bus"),
+	ALIAS(MEM0_SROM, NULL, "srom"),
+};
+
+static void __init s3c64xx_clk_register_fixed_ext(unsigned long fin_pll_f,
+							unsigned long xusbxti_f)
+{
+	s3c64xx_fixed_rate_ext_clks[0].fixed_rate = fin_pll_f;
+	s3c64xx_fixed_rate_ext_clks[1].fixed_rate = xusbxti_f;
+	samsung_clk_register_fixed_rate(s3c64xx_fixed_rate_ext_clks,
+				ARRAY_SIZE(s3c64xx_fixed_rate_ext_clks));
+}
+
+/* Register s3c64xx clocks. */
+void __init s3c64xx_clk_init(struct device_node *np, unsigned long xtal_f,
+			     unsigned long xusbxti_f, bool is_s3c6400,
+			     void __iomem *reg_base)
+{
+	unsigned long *soc_regs = NULL;
+	unsigned long nr_soc_regs = 0;
+
+	if (np) {
+		reg_base = of_iomap(np, 0);
+		if (!reg_base)
+			panic("%s: failed to map registers\n", __func__);
+	}
+
+	if (!is_s3c6400) {
+		soc_regs = s3c6410_clk_regs;
+		nr_soc_regs = ARRAY_SIZE(s3c6410_clk_regs);
+	}
+
+	samsung_clk_init(np, reg_base, NR_CLKS, s3c64xx_clk_regs,
+			ARRAY_SIZE(s3c64xx_clk_regs), soc_regs, nr_soc_regs);
+
+	/* Register external clocks. */
+	if (!np)
+		s3c64xx_clk_register_fixed_ext(xtal_f, xusbxti_f);
+
+	/* Register PLLs. */
+	samsung_clk_register_pll(s3c64xx_pll_clks,
+				ARRAY_SIZE(s3c64xx_pll_clks), reg_base);
+
+	/* Register common internal clocks. */
+	samsung_clk_register_fixed_rate(s3c64xx_fixed_rate_clks,
+					ARRAY_SIZE(s3c64xx_fixed_rate_clks));
+	samsung_clk_register_mux(s3c64xx_mux_clks,
+					ARRAY_SIZE(s3c64xx_mux_clks));
+	samsung_clk_register_div(s3c64xx_div_clks,
+					ARRAY_SIZE(s3c64xx_div_clks));
+	samsung_clk_register_gate(s3c64xx_gate_clks,
+					ARRAY_SIZE(s3c64xx_gate_clks));
+
+	/* Register SoC-specific clocks. */
+	if (is_s3c6400) {
+		samsung_clk_register_mux(s3c6400_mux_clks,
+					ARRAY_SIZE(s3c6400_mux_clks));
+		samsung_clk_register_div(s3c6400_div_clks,
+					ARRAY_SIZE(s3c6400_div_clks));
+		samsung_clk_register_gate(s3c6400_gate_clks,
+					ARRAY_SIZE(s3c6400_gate_clks));
+		samsung_clk_register_alias(s3c6400_clock_aliases,
+					ARRAY_SIZE(s3c6400_clock_aliases));
+	} else {
+		samsung_clk_register_mux(s3c6410_mux_clks,
+					ARRAY_SIZE(s3c6410_mux_clks));
+		samsung_clk_register_div(s3c6410_div_clks,
+					ARRAY_SIZE(s3c6410_div_clks));
+		samsung_clk_register_gate(s3c6410_gate_clks,
+					ARRAY_SIZE(s3c6410_gate_clks));
+		samsung_clk_register_alias(s3c6410_clock_aliases,
+					ARRAY_SIZE(s3c6410_clock_aliases));
+	}
+
+	samsung_clk_register_alias(s3c64xx_clock_aliases,
+					ARRAY_SIZE(s3c64xx_clock_aliases));
+
+	pr_info("%s clocks: apll = %lu, mpll = %lu\n"
+		"\tepll = %lu, arm_clk = %lu\n",
+		is_s3c6400 ? "S3C6400" : "S3C6410",
+		_get_rate("fout_apll"),	_get_rate("fout_mpll"),
+		_get_rate("fout_epll"), _get_rate("armclk"));
+}
+
+static void __init s3c6400_clk_init(struct device_node *np)
+{
+	s3c64xx_clk_init(np, 0, 0, true, NULL);
+}
+CLK_OF_DECLARE(s3c6400_clk, "samsung,s3c6400-clock", s3c6400_clk_init);
+
+static void __init s3c6410_clk_init(struct device_node *np)
+{
+	s3c64xx_clk_init(np, 0, 0, false, NULL);
+}
+CLK_OF_DECLARE(s3c6410_clk, "samsung,s3c6410-clock", s3c6410_clk_init);
diff --git a/drivers/clk/samsung/clk.c b/drivers/clk/samsung/clk.c
index cd3c40ab50f3..f503f32e2f80 100644
--- a/drivers/clk/samsung/clk.c
+++ b/drivers/clk/samsung/clk.c
@@ -307,14 +307,12 @@ void __init samsung_clk_of_register_fixed_ext(
 unsigned long _get_rate(const char *clk_name)
 {
 	struct clk *clk;
-	unsigned long rate;
 
-	clk = clk_get(NULL, clk_name);
-	if (IS_ERR(clk)) {
+	clk = __clk_lookup(clk_name);
+	if (!clk) {
 		pr_err("%s: could not find clock %s\n", __func__, clk_name);
 		return 0;
 	}
-	rate = clk_get_rate(clk);
-	clk_put(clk);
-	return rate;
+
+	return clk_get_rate(clk);
 }
diff --git a/drivers/clk/samsung/clk.h b/drivers/clk/samsung/clk.h
index 2f7dba20ced8..31b4174e7a5b 100644
--- a/drivers/clk/samsung/clk.h
+++ b/drivers/clk/samsung/clk.h
@@ -19,6 +19,7 @@
 #include <linux/clk-provider.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
+#include "clk-pll.h"
 
 /**
  * struct samsung_clock_alias: information about mux clock
@@ -39,6 +40,8 @@ struct samsung_clock_alias {
 		.alias		= a,				\
 	}
 
+#define MHZ (1000 * 1000)
+
 /**
  * struct samsung_fixed_rate_clock: information about fixed-rate clock
  * @id: platform specific id of the clock.
@@ -127,7 +130,7 @@ struct samsung_mux_clock {
 		.name		= cname,			\
 		.parent_names	= pnames,			\
 		.num_parents	= ARRAY_SIZE(pnames),		\
-		.flags		= f,				\
+		.flags		= (f) | CLK_SET_RATE_NO_REPARENT, \
 		.offset		= o,				\
 		.shift		= s,				\
 		.width		= w,				\
@@ -261,6 +264,54 @@ struct samsung_clk_reg_dump {
 	u32	value;
 };
 
+/**
+ * struct samsung_pll_clock: information about pll clock
+ * @id: platform specific id of the clock.
+ * @dev_name: name of the device to which this clock belongs.
+ * @name: name of this pll clock.
+ * @parent_name: name of the parent clock.
+ * @flags: optional flags for basic clock.
+ * @con_offset: offset of the register for configuring the PLL.
+ * @lock_offset: offset of the register for locking the PLL.
+ * @type: Type of PLL to be registered.
+ * @alias: optional clock alias name to be assigned to this clock.
+ */
+struct samsung_pll_clock {
+	unsigned int		id;
+	const char		*dev_name;
+	const char		*name;
+	const char		*parent_name;
+	unsigned long		flags;
+	int			con_offset;
+	int			lock_offset;
+	enum samsung_pll_type	type;
+	const struct samsung_pll_rate_table *rate_table;
+	const char              *alias;
+};
+
+#define __PLL(_typ, _id, _dname, _name, _pname, _flags, _lock, _con,	\
+		_rtable, _alias)					\
+	{								\
+		.id		= _id,					\
+		.type		= _typ,					\
+		.dev_name	= _dname,				\
+		.name		= _name,				\
+		.parent_name	= _pname,				\
+		.flags		= CLK_GET_RATE_NOCACHE,			\
+		.con_offset	= _con,					\
+		.lock_offset	= _lock,				\
+		.rate_table	= _rtable,				\
+		.alias		= _alias,				\
+	}
+
+#define PLL(_typ, _id, _name, _pname, _lock, _con, _rtable)	\
+	__PLL(_typ, _id, NULL, _name, _pname, CLK_GET_RATE_NOCACHE,	\
+		_lock, _con, _rtable, _name)
+
+#define PLL_A(_typ, _id, _name, _pname, _lock, _con, _alias, _rtable) \
+	__PLL(_typ, _id, NULL, _name, _pname, CLK_GET_RATE_NOCACHE,	\
+		_lock, _con, _rtable, _alias)
+
 extern void __init samsung_clk_init(struct device_node *np, void __iomem *base,
 		unsigned long nr_clks, unsigned long *rdump,
 		unsigned long nr_rdump, unsigned long *soc_rdump,
@@ -284,6 +335,8 @@ extern void __init samsung_clk_register_div(struct samsung_div_clock *clk_list,
 		unsigned int nr_clk);
 extern void __init samsung_clk_register_gate(
 		struct samsung_gate_clock *clk_list, unsigned int nr_clk);
+extern void __init samsung_clk_register_pll(struct samsung_pll_clock *pll_list,
+		unsigned int nr_clk, void __iomem *base);
 
 extern unsigned long _get_rate(const char *clk_name);
 
diff --git a/drivers/clk/spear/spear1310_clock.c b/drivers/clk/spear/spear1310_clock.c
index aedbbe12f321..65894f7687ed 100644
--- a/drivers/clk/spear/spear1310_clock.c
+++ b/drivers/clk/spear/spear1310_clock.c
@@ -416,9 +416,9 @@ void __init spear1310_clk_init(void __iomem *misc_base, void __iomem *ras_base)
 	/* clock derived from 24 or 25 MHz osc clk */
 	/* vco-pll */
 	clk = clk_register_mux(NULL, "vco1_mclk", vco_parents,
-			ARRAY_SIZE(vco_parents), 0, SPEAR1310_PLL_CFG,
-			SPEAR1310_PLL1_CLK_SHIFT, SPEAR1310_PLL_CLK_MASK, 0,
-			&_lock);
+			ARRAY_SIZE(vco_parents), CLK_SET_RATE_NO_REPARENT,
+			SPEAR1310_PLL_CFG, SPEAR1310_PLL1_CLK_SHIFT,
+			SPEAR1310_PLL_CLK_MASK, 0, &_lock);
 	clk_register_clkdev(clk, "vco1_mclk", NULL);
 	clk = clk_register_vco_pll("vco1_clk", "pll1_clk", NULL, "vco1_mclk",
 			0, SPEAR1310_PLL1_CTR, SPEAR1310_PLL1_FRQ, pll_rtbl,
@@ -427,9 +427,9 @@ void __init spear1310_clk_init(void __iomem *misc_base, void __iomem *ras_base)
 	clk_register_clkdev(clk1, "pll1_clk", NULL);
 
 	clk = clk_register_mux(NULL, "vco2_mclk", vco_parents,
-			ARRAY_SIZE(vco_parents), 0, SPEAR1310_PLL_CFG,
-			SPEAR1310_PLL2_CLK_SHIFT, SPEAR1310_PLL_CLK_MASK, 0,
-			&_lock);
+			ARRAY_SIZE(vco_parents), CLK_SET_RATE_NO_REPARENT,
+			SPEAR1310_PLL_CFG, SPEAR1310_PLL2_CLK_SHIFT,
+			SPEAR1310_PLL_CLK_MASK, 0, &_lock);
 	clk_register_clkdev(clk, "vco2_mclk", NULL);
 	clk = clk_register_vco_pll("vco2_clk", "pll2_clk", NULL, "vco2_mclk",
 			0, SPEAR1310_PLL2_CTR, SPEAR1310_PLL2_FRQ, pll_rtbl,
@@ -438,9 +438,9 @@ void __init spear1310_clk_init(void __iomem *misc_base, void __iomem *ras_base)
 	clk_register_clkdev(clk1, "pll2_clk", NULL);
 
 	clk = clk_register_mux(NULL, "vco3_mclk", vco_parents,
-			ARRAY_SIZE(vco_parents), 0, SPEAR1310_PLL_CFG,
-			SPEAR1310_PLL3_CLK_SHIFT, SPEAR1310_PLL_CLK_MASK, 0,
-			&_lock);
+			ARRAY_SIZE(vco_parents), CLK_SET_RATE_NO_REPARENT,
+			SPEAR1310_PLL_CFG, SPEAR1310_PLL3_CLK_SHIFT,
+			SPEAR1310_PLL_CLK_MASK, 0, &_lock);
 	clk_register_clkdev(clk, "vco3_mclk", NULL);
 	clk = clk_register_vco_pll("vco3_clk", "pll3_clk", NULL, "vco3_mclk",
 			0, SPEAR1310_PLL3_CTR, SPEAR1310_PLL3_FRQ, pll_rtbl,
@@ -515,9 +515,9 @@ void __init spear1310_clk_init(void __iomem *misc_base, void __iomem *ras_base)
 
 	/* gpt clocks */
 	clk = clk_register_mux(NULL, "gpt0_mclk", gpt_parents,
-			ARRAY_SIZE(gpt_parents), 0, SPEAR1310_PERIP_CLK_CFG,
-			SPEAR1310_GPT0_CLK_SHIFT, SPEAR1310_GPT_CLK_MASK, 0,
-			&_lock);
+			ARRAY_SIZE(gpt_parents), CLK_SET_RATE_NO_REPARENT,
+			SPEAR1310_PERIP_CLK_CFG, SPEAR1310_GPT0_CLK_SHIFT,
+			SPEAR1310_GPT_CLK_MASK, 0, &_lock);
 	clk_register_clkdev(clk, "gpt0_mclk", NULL);
 	clk = clk_register_gate(NULL, "gpt0_clk", "gpt0_mclk", 0,
 			SPEAR1310_PERIP1_CLK_ENB, SPEAR1310_GPT0_CLK_ENB, 0,
@@ -525,9 +525,9 @@ void __init spear1310_clk_init(void __iomem *misc_base, void __iomem *ras_base)
 	clk_register_clkdev(clk, NULL, "gpt0");
 
 	clk = clk_register_mux(NULL, "gpt1_mclk", gpt_parents,
-			ARRAY_SIZE(gpt_parents), 0, SPEAR1310_PERIP_CLK_CFG,
-			SPEAR1310_GPT1_CLK_SHIFT, SPEAR1310_GPT_CLK_MASK, 0,
-			&_lock);
+			ARRAY_SIZE(gpt_parents), CLK_SET_RATE_NO_REPARENT,
+			SPEAR1310_PERIP_CLK_CFG, SPEAR1310_GPT1_CLK_SHIFT,
+			SPEAR1310_GPT_CLK_MASK, 0, &_lock);
 	clk_register_clkdev(clk, "gpt1_mclk", NULL);
 	clk = clk_register_gate(NULL, "gpt1_clk", "gpt1_mclk", 0,
 			SPEAR1310_PERIP1_CLK_ENB, SPEAR1310_GPT1_CLK_ENB, 0,
@@ -535,9 +535,9 @@ void __init spear1310_clk_init(void __iomem *misc_base, void __iomem *ras_base)
 	clk_register_clkdev(clk, NULL, "gpt1");
 
 	clk = clk_register_mux(NULL, "gpt2_mclk", gpt_parents,
-			ARRAY_SIZE(gpt_parents), 0, SPEAR1310_PERIP_CLK_CFG,
-			SPEAR1310_GPT2_CLK_SHIFT, SPEAR1310_GPT_CLK_MASK, 0,
-			&_lock);
+			ARRAY_SIZE(gpt_parents), CLK_SET_RATE_NO_REPARENT,
+			SPEAR1310_PERIP_CLK_CFG, SPEAR1310_GPT2_CLK_SHIFT,
+			SPEAR1310_GPT_CLK_MASK, 0, &_lock);
 	clk_register_clkdev(clk, "gpt2_mclk", NULL);
 	clk = clk_register_gate(NULL, "gpt2_clk", "gpt2_mclk", 0,
 			SPEAR1310_PERIP2_CLK_ENB, SPEAR1310_GPT2_CLK_ENB, 0,
@@ -545,9 +545,9 @@ void __init spear1310_clk_init(void __iomem *misc_base, void __iomem *ras_base)
 	clk_register_clkdev(clk, NULL, "gpt2");
 
 	clk = clk_register_mux(NULL, "gpt3_mclk", gpt_parents,
-			ARRAY_SIZE(gpt_parents), 0, SPEAR1310_PERIP_CLK_CFG,
-			SPEAR1310_GPT3_CLK_SHIFT, SPEAR1310_GPT_CLK_MASK, 0,
-			&_lock);
+			ARRAY_SIZE(gpt_parents), CLK_SET_RATE_NO_REPARENT,
+			SPEAR1310_PERIP_CLK_CFG, SPEAR1310_GPT3_CLK_SHIFT,
+			SPEAR1310_GPT_CLK_MASK, 0, &_lock);
 	clk_register_clkdev(clk, "gpt3_mclk", NULL);
 	clk = clk_register_gate(NULL, "gpt3_clk", "gpt3_mclk", 0,
 			SPEAR1310_PERIP2_CLK_ENB, SPEAR1310_GPT3_CLK_ENB, 0,
@@ -562,7 +562,8 @@ void __init spear1310_clk_init(void __iomem *misc_base, void __iomem *ras_base)
 	clk_register_clkdev(clk1, "uart_syn_gclk", NULL);
 
 	clk = clk_register_mux(NULL, "uart0_mclk", uart0_parents,
-			ARRAY_SIZE(uart0_parents), CLK_SET_RATE_PARENT,
+			ARRAY_SIZE(uart0_parents),
+			CLK_SET_RATE_PARENT | CLK_SET_RATE_NO_REPARENT,
 			SPEAR1310_PERIP_CLK_CFG, SPEAR1310_UART_CLK_SHIFT,
 			SPEAR1310_UART_CLK_MASK, 0, &_lock);
 	clk_register_clkdev(clk, "uart0_mclk", NULL);
@@ -602,7 +603,8 @@ void __init spear1310_clk_init(void __iomem *misc_base, void __iomem *ras_base)
 	clk_register_clkdev(clk1, "c3_syn_gclk", NULL);
 
 	clk = clk_register_mux(NULL, "c3_mclk", c3_parents,
-			ARRAY_SIZE(c3_parents), CLK_SET_RATE_PARENT,
+			ARRAY_SIZE(c3_parents),
+			CLK_SET_RATE_PARENT | CLK_SET_RATE_NO_REPARENT,
 			SPEAR1310_PERIP_CLK_CFG, SPEAR1310_C3_CLK_SHIFT,
 			SPEAR1310_C3_CLK_MASK, 0, &_lock);
 	clk_register_clkdev(clk, "c3_mclk", NULL);
@@ -614,8 +616,8 @@ void __init spear1310_clk_init(void __iomem *misc_base, void __iomem *ras_base)
 
 	/* gmac */
 	clk = clk_register_mux(NULL, "phy_input_mclk", gmac_phy_input_parents,
-			ARRAY_SIZE(gmac_phy_input_parents), 0,
-			SPEAR1310_GMAC_CLK_CFG,
+			ARRAY_SIZE(gmac_phy_input_parents),
+			CLK_SET_RATE_NO_REPARENT, SPEAR1310_GMAC_CLK_CFG,
 			SPEAR1310_GMAC_PHY_INPUT_CLK_SHIFT,
 			SPEAR1310_GMAC_PHY_INPUT_CLK_MASK, 0, &_lock);
 	clk_register_clkdev(clk, "phy_input_mclk", NULL);
@@ -627,15 +629,16 @@ void __init spear1310_clk_init(void __iomem *misc_base, void __iomem *ras_base)
 	clk_register_clkdev(clk1, "phy_syn_gclk", NULL);
 
 	clk = clk_register_mux(NULL, "phy_mclk", gmac_phy_parents,
-			ARRAY_SIZE(gmac_phy_parents), 0,
+			ARRAY_SIZE(gmac_phy_parents), CLK_SET_RATE_NO_REPARENT,
 			SPEAR1310_PERIP_CLK_CFG, SPEAR1310_GMAC_PHY_CLK_SHIFT,
 			SPEAR1310_GMAC_PHY_CLK_MASK, 0, &_lock);
 	clk_register_clkdev(clk, "stmmacphy.0", NULL);
 
 	/* clcd */
 	clk = clk_register_mux(NULL, "clcd_syn_mclk", clcd_synth_parents,
-			ARRAY_SIZE(clcd_synth_parents), 0,
-			SPEAR1310_CLCD_CLK_SYNT, SPEAR1310_CLCD_SYNT_CLK_SHIFT,
+			ARRAY_SIZE(clcd_synth_parents),
+			CLK_SET_RATE_NO_REPARENT, SPEAR1310_CLCD_CLK_SYNT,
+			SPEAR1310_CLCD_SYNT_CLK_SHIFT,
 			SPEAR1310_CLCD_SYNT_CLK_MASK, 0, &_lock);
 	clk_register_clkdev(clk, "clcd_syn_mclk", NULL);
 
@@ -645,7 +648,8 @@ void __init spear1310_clk_init(void __iomem *misc_base, void __iomem *ras_base)
 	clk_register_clkdev(clk, "clcd_syn_clk", NULL);
 
 	clk = clk_register_mux(NULL, "clcd_pixel_mclk", clcd_pixel_parents,
-			ARRAY_SIZE(clcd_pixel_parents), CLK_SET_RATE_PARENT,
+			ARRAY_SIZE(clcd_pixel_parents),
+			CLK_SET_RATE_PARENT | CLK_SET_RATE_NO_REPARENT,
 			SPEAR1310_PERIP_CLK_CFG, SPEAR1310_CLCD_CLK_SHIFT,
 			SPEAR1310_CLCD_CLK_MASK, 0, &_lock);
 	clk_register_clkdev(clk, "clcd_pixel_mclk", NULL);
@@ -657,9 +661,9 @@ void __init spear1310_clk_init(void __iomem *misc_base, void __iomem *ras_base)
 
 	/* i2s */
 	clk = clk_register_mux(NULL, "i2s_src_mclk", i2s_src_parents,
-			ARRAY_SIZE(i2s_src_parents), 0, SPEAR1310_I2S_CLK_CFG,
-			SPEAR1310_I2S_SRC_CLK_SHIFT, SPEAR1310_I2S_SRC_CLK_MASK,
-			0, &_lock);
+			ARRAY_SIZE(i2s_src_parents), CLK_SET_RATE_NO_REPARENT,
+			SPEAR1310_I2S_CLK_CFG, SPEAR1310_I2S_SRC_CLK_SHIFT,
+			SPEAR1310_I2S_SRC_CLK_MASK, 0, &_lock);
 	clk_register_clkdev(clk, "i2s_src_mclk", NULL);
 
 	clk = clk_register_aux("i2s_prs1_clk", NULL, "i2s_src_mclk", 0,
@@ -668,7 +672,8 @@ void __init spear1310_clk_init(void __iomem *misc_base, void __iomem *ras_base)
 	clk_register_clkdev(clk, "i2s_prs1_clk", NULL);
 
 	clk = clk_register_mux(NULL, "i2s_ref_mclk", i2s_ref_parents,
-			ARRAY_SIZE(i2s_ref_parents), CLK_SET_RATE_PARENT,
+			ARRAY_SIZE(i2s_ref_parents),
+			CLK_SET_RATE_PARENT | CLK_SET_RATE_NO_REPARENT,
 			SPEAR1310_I2S_CLK_CFG, SPEAR1310_I2S_REF_SHIFT,
 			SPEAR1310_I2S_REF_SEL_MASK, 0, &_lock);
 	clk_register_clkdev(clk, "i2s_ref_mclk", NULL);
@@ -806,13 +811,15 @@ void __init spear1310_clk_init(void __iomem *misc_base, void __iomem *ras_base)
 
 	/* RAS clks */
 	clk = clk_register_mux(NULL, "gen_syn0_1_mclk", gen_synth0_1_parents,
-			ARRAY_SIZE(gen_synth0_1_parents), 0, SPEAR1310_PLL_CFG,
+			ARRAY_SIZE(gen_synth0_1_parents),
+			CLK_SET_RATE_NO_REPARENT, SPEAR1310_PLL_CFG,
 			SPEAR1310_RAS_SYNT0_1_CLK_SHIFT,
 			SPEAR1310_RAS_SYNT_CLK_MASK, 0, &_lock);
 	clk_register_clkdev(clk, "gen_syn0_1_clk", NULL);
 
 	clk = clk_register_mux(NULL, "gen_syn2_3_mclk", gen_synth2_3_parents,
-			ARRAY_SIZE(gen_synth2_3_parents), 0, SPEAR1310_PLL_CFG,
+			ARRAY_SIZE(gen_synth2_3_parents),
+			CLK_SET_RATE_NO_REPARENT, SPEAR1310_PLL_CFG,
 			SPEAR1310_RAS_SYNT2_3_CLK_SHIFT,
 			SPEAR1310_RAS_SYNT_CLK_MASK, 0, &_lock);
 	clk_register_clkdev(clk, "gen_syn2_3_clk", NULL);
@@ -929,8 +936,8 @@ void __init spear1310_clk_init(void __iomem *misc_base, void __iomem *ras_base)
 
 	clk = clk_register_mux(NULL, "smii_rgmii_phy_mclk",
 			smii_rgmii_phy_parents,
-			ARRAY_SIZE(smii_rgmii_phy_parents), 0,
-			SPEAR1310_RAS_CTRL_REG1,
+			ARRAY_SIZE(smii_rgmii_phy_parents),
+			CLK_SET_RATE_NO_REPARENT, SPEAR1310_RAS_CTRL_REG1,
 			SPEAR1310_SMII_RGMII_PHY_CLK_SHIFT,
 			SPEAR1310_PHY_CLK_MASK, 0, &_lock);
 	clk_register_clkdev(clk, "stmmacphy.1", NULL);
@@ -938,15 +945,15 @@ void __init spear1310_clk_init(void __iomem *misc_base, void __iomem *ras_base)
 	clk_register_clkdev(clk, "stmmacphy.4", NULL);
 
 	clk = clk_register_mux(NULL, "rmii_phy_mclk", rmii_phy_parents,
-			ARRAY_SIZE(rmii_phy_parents), 0,
+			ARRAY_SIZE(rmii_phy_parents), CLK_SET_RATE_NO_REPARENT,
 			SPEAR1310_RAS_CTRL_REG1, SPEAR1310_RMII_PHY_CLK_SHIFT,
 			SPEAR1310_PHY_CLK_MASK, 0, &_lock);
 	clk_register_clkdev(clk, "stmmacphy.3", NULL);
 
 	clk = clk_register_mux(NULL, "uart1_mclk", uart_parents,
-			ARRAY_SIZE(uart_parents), 0, SPEAR1310_RAS_CTRL_REG0,
-			SPEAR1310_UART1_CLK_SHIFT, SPEAR1310_RAS_UART_CLK_MASK,
-			0, &_lock);
+			ARRAY_SIZE(uart_parents), CLK_SET_RATE_NO_REPARENT,
+			SPEAR1310_RAS_CTRL_REG0, SPEAR1310_UART1_CLK_SHIFT,
+			SPEAR1310_RAS_UART_CLK_MASK, 0, &_lock);
 	clk_register_clkdev(clk, "uart1_mclk", NULL);
 
 	clk = clk_register_gate(NULL, "uart1_clk", "uart1_mclk", 0,
@@ -955,9 +962,9 @@ void __init spear1310_clk_init(void __iomem *misc_base, void __iomem *ras_base)
 	clk_register_clkdev(clk, NULL, "5c800000.serial");
 
 	clk = clk_register_mux(NULL, "uart2_mclk", uart_parents,
-			ARRAY_SIZE(uart_parents), 0, SPEAR1310_RAS_CTRL_REG0,
-			SPEAR1310_UART2_CLK_SHIFT, SPEAR1310_RAS_UART_CLK_MASK,
-			0, &_lock);
+			ARRAY_SIZE(uart_parents), CLK_SET_RATE_NO_REPARENT,
+			SPEAR1310_RAS_CTRL_REG0, SPEAR1310_UART2_CLK_SHIFT,
+			SPEAR1310_RAS_UART_CLK_MASK, 0, &_lock);
 	clk_register_clkdev(clk, "uart2_mclk", NULL);
 
 	clk = clk_register_gate(NULL, "uart2_clk", "uart2_mclk", 0,
@@ -966,9 +973,9 @@ void __init spear1310_clk_init(void __iomem *misc_base, void __iomem *ras_base)
 	clk_register_clkdev(clk, NULL, "5c900000.serial");
 
 	clk = clk_register_mux(NULL, "uart3_mclk", uart_parents,
-			ARRAY_SIZE(uart_parents), 0, SPEAR1310_RAS_CTRL_REG0,
-			SPEAR1310_UART3_CLK_SHIFT, SPEAR1310_RAS_UART_CLK_MASK,
-			0, &_lock);
+			ARRAY_SIZE(uart_parents), CLK_SET_RATE_NO_REPARENT,
+			SPEAR1310_RAS_CTRL_REG0, SPEAR1310_UART3_CLK_SHIFT,
+			SPEAR1310_RAS_UART_CLK_MASK, 0, &_lock);
 	clk_register_clkdev(clk, "uart3_mclk", NULL);
 
 	clk = clk_register_gate(NULL, "uart3_clk", "uart3_mclk", 0,
@@ -977,9 +984,9 @@ void __init spear1310_clk_init(void __iomem *misc_base, void __iomem *ras_base)
 	clk_register_clkdev(clk, NULL, "5ca00000.serial");
 
 	clk = clk_register_mux(NULL, "uart4_mclk", uart_parents,
-			ARRAY_SIZE(uart_parents), 0, SPEAR1310_RAS_CTRL_REG0,
-			SPEAR1310_UART4_CLK_SHIFT, SPEAR1310_RAS_UART_CLK_MASK,
-			0, &_lock);
+			ARRAY_SIZE(uart_parents), CLK_SET_RATE_NO_REPARENT,
+			SPEAR1310_RAS_CTRL_REG0, SPEAR1310_UART4_CLK_SHIFT,
+			SPEAR1310_RAS_UART_CLK_MASK, 0, &_lock);
 	clk_register_clkdev(clk, "uart4_mclk", NULL);
 
 	clk = clk_register_gate(NULL, "uart4_clk", "uart4_mclk", 0,
@@ -988,9 +995,9 @@ void __init spear1310_clk_init(void __iomem *misc_base, void __iomem *ras_base)
 	clk_register_clkdev(clk, NULL, "5cb00000.serial");
 
 	clk = clk_register_mux(NULL, "uart5_mclk", uart_parents,
-			ARRAY_SIZE(uart_parents), 0, SPEAR1310_RAS_CTRL_REG0,
-			SPEAR1310_UART5_CLK_SHIFT, SPEAR1310_RAS_UART_CLK_MASK,
-			0, &_lock);
+			ARRAY_SIZE(uart_parents), CLK_SET_RATE_NO_REPARENT,
+			SPEAR1310_RAS_CTRL_REG0, SPEAR1310_UART5_CLK_SHIFT,
+			SPEAR1310_RAS_UART_CLK_MASK, 0, &_lock);
 	clk_register_clkdev(clk, "uart5_mclk", NULL);
 
 	clk = clk_register_gate(NULL, "uart5_clk", "uart5_mclk", 0,
@@ -999,9 +1006,9 @@ void __init spear1310_clk_init(void __iomem *misc_base, void __iomem *ras_base)
 	clk_register_clkdev(clk, NULL, "5cc00000.serial");
 
 	clk = clk_register_mux(NULL, "i2c1_mclk", i2c_parents,
-			ARRAY_SIZE(i2c_parents), 0, SPEAR1310_RAS_CTRL_REG0,
-			SPEAR1310_I2C1_CLK_SHIFT, SPEAR1310_I2C_CLK_MASK, 0,
-			&_lock);
+			ARRAY_SIZE(i2c_parents), CLK_SET_RATE_NO_REPARENT,
+			SPEAR1310_RAS_CTRL_REG0, SPEAR1310_I2C1_CLK_SHIFT,
+			SPEAR1310_I2C_CLK_MASK, 0, &_lock);
 	clk_register_clkdev(clk, "i2c1_mclk", NULL);
 
 	clk = clk_register_gate(NULL, "i2c1_clk", "i2c1_mclk", 0,
@@ -1010,9 +1017,9 @@ void __init spear1310_clk_init(void __iomem *misc_base, void __iomem *ras_base)
 	clk_register_clkdev(clk, NULL, "5cd00000.i2c");
 
 	clk = clk_register_mux(NULL, "i2c2_mclk", i2c_parents,
-			ARRAY_SIZE(i2c_parents), 0, SPEAR1310_RAS_CTRL_REG0,
-			SPEAR1310_I2C2_CLK_SHIFT, SPEAR1310_I2C_CLK_MASK, 0,
-			&_lock);
+			ARRAY_SIZE(i2c_parents), CLK_SET_RATE_NO_REPARENT,
+			SPEAR1310_RAS_CTRL_REG0, SPEAR1310_I2C2_CLK_SHIFT,
+			SPEAR1310_I2C_CLK_MASK, 0, &_lock);
 	clk_register_clkdev(clk, "i2c2_mclk", NULL);
 
 	clk = clk_register_gate(NULL, "i2c2_clk", "i2c2_mclk", 0,
@@ -1021,9 +1028,9 @@ void __init spear1310_clk_init(void __iomem *misc_base, void __iomem *ras_base)
 	clk_register_clkdev(clk, NULL, "5ce00000.i2c");
 
 	clk = clk_register_mux(NULL, "i2c3_mclk", i2c_parents,
-			ARRAY_SIZE(i2c_parents), 0, SPEAR1310_RAS_CTRL_REG0,
-			SPEAR1310_I2C3_CLK_SHIFT, SPEAR1310_I2C_CLK_MASK, 0,
-			&_lock);
+			ARRAY_SIZE(i2c_parents), CLK_SET_RATE_NO_REPARENT,
+			SPEAR1310_RAS_CTRL_REG0, SPEAR1310_I2C3_CLK_SHIFT,
+			SPEAR1310_I2C_CLK_MASK, 0, &_lock);
 	clk_register_clkdev(clk, "i2c3_mclk", NULL);
 
 	clk = clk_register_gate(NULL, "i2c3_clk", "i2c3_mclk", 0,
@@ -1032,9 +1039,9 @@ void __init spear1310_clk_init(void __iomem *misc_base, void __iomem *ras_base)
 	clk_register_clkdev(clk, NULL, "5cf00000.i2c");
 
 	clk = clk_register_mux(NULL, "i2c4_mclk", i2c_parents,
-			ARRAY_SIZE(i2c_parents), 0, SPEAR1310_RAS_CTRL_REG0,
-			SPEAR1310_I2C4_CLK_SHIFT, SPEAR1310_I2C_CLK_MASK, 0,
-			&_lock);
+			ARRAY_SIZE(i2c_parents), CLK_SET_RATE_NO_REPARENT,
+			SPEAR1310_RAS_CTRL_REG0, SPEAR1310_I2C4_CLK_SHIFT,
+			SPEAR1310_I2C_CLK_MASK, 0, &_lock);
 	clk_register_clkdev(clk, "i2c4_mclk", NULL);
 
 	clk = clk_register_gate(NULL, "i2c4_clk", "i2c4_mclk", 0,
@@ -1043,9 +1050,9 @@ void __init spear1310_clk_init(void __iomem *misc_base, void __iomem *ras_base)
 	clk_register_clkdev(clk, NULL, "5d000000.i2c");
 
 	clk = clk_register_mux(NULL, "i2c5_mclk", i2c_parents,
-			ARRAY_SIZE(i2c_parents), 0, SPEAR1310_RAS_CTRL_REG0,
-			SPEAR1310_I2C5_CLK_SHIFT, SPEAR1310_I2C_CLK_MASK, 0,
-			&_lock);
+			ARRAY_SIZE(i2c_parents), CLK_SET_RATE_NO_REPARENT,
+			SPEAR1310_RAS_CTRL_REG0, SPEAR1310_I2C5_CLK_SHIFT,
+			SPEAR1310_I2C_CLK_MASK, 0, &_lock);
 	clk_register_clkdev(clk, "i2c5_mclk", NULL);
 
 	clk = clk_register_gate(NULL, "i2c5_clk", "i2c5_mclk", 0,
@@ -1054,9 +1061,9 @@ void __init spear1310_clk_init(void __iomem *misc_base, void __iomem *ras_base)
 	clk_register_clkdev(clk, NULL, "5d100000.i2c");
 
 	clk = clk_register_mux(NULL, "i2c6_mclk", i2c_parents,
-			ARRAY_SIZE(i2c_parents), 0, SPEAR1310_RAS_CTRL_REG0,
-			SPEAR1310_I2C6_CLK_SHIFT, SPEAR1310_I2C_CLK_MASK, 0,
-			&_lock);
+			ARRAY_SIZE(i2c_parents), CLK_SET_RATE_NO_REPARENT,
+			SPEAR1310_RAS_CTRL_REG0, SPEAR1310_I2C6_CLK_SHIFT,
+			SPEAR1310_I2C_CLK_MASK, 0, &_lock);
 	clk_register_clkdev(clk, "i2c6_mclk", NULL);
 
 	clk = clk_register_gate(NULL, "i2c6_clk", "i2c6_mclk", 0,
@@ -1065,9 +1072,9 @@ void __init spear1310_clk_init(void __iomem *misc_base, void __iomem *ras_base)
 	clk_register_clkdev(clk, NULL, "5d200000.i2c");
 
 	clk = clk_register_mux(NULL, "i2c7_mclk", i2c_parents,
-			ARRAY_SIZE(i2c_parents), 0, SPEAR1310_RAS_CTRL_REG0,
-			SPEAR1310_I2C7_CLK_SHIFT, SPEAR1310_I2C_CLK_MASK, 0,
-			&_lock);
+			ARRAY_SIZE(i2c_parents), CLK_SET_RATE_NO_REPARENT,
+			SPEAR1310_RAS_CTRL_REG0, SPEAR1310_I2C7_CLK_SHIFT,
+			SPEAR1310_I2C_CLK_MASK, 0, &_lock);
 	clk_register_clkdev(clk, "i2c7_mclk", NULL);
 
 	clk = clk_register_gate(NULL, "i2c7_clk", "i2c7_mclk", 0,
@@ -1076,9 +1083,9 @@ void __init spear1310_clk_init(void __iomem *misc_base, void __iomem *ras_base)
 	clk_register_clkdev(clk, NULL, "5d300000.i2c");
 
 	clk = clk_register_mux(NULL, "ssp1_mclk", ssp1_parents,
-			ARRAY_SIZE(ssp1_parents), 0, SPEAR1310_RAS_CTRL_REG0,
-			SPEAR1310_SSP1_CLK_SHIFT, SPEAR1310_SSP1_CLK_MASK, 0,
-			&_lock);
+			ARRAY_SIZE(ssp1_parents), CLK_SET_RATE_NO_REPARENT,
+			SPEAR1310_RAS_CTRL_REG0, SPEAR1310_SSP1_CLK_SHIFT,
+			SPEAR1310_SSP1_CLK_MASK, 0, &_lock);
 	clk_register_clkdev(clk, "ssp1_mclk", NULL);
 
 	clk = clk_register_gate(NULL, "ssp1_clk", "ssp1_mclk", 0,
@@ -1087,9 +1094,9 @@ void __init spear1310_clk_init(void __iomem *misc_base, void __iomem *ras_base)
 	clk_register_clkdev(clk, NULL, "5d400000.spi");
 
 	clk = clk_register_mux(NULL, "pci_mclk", pci_parents,
-			ARRAY_SIZE(pci_parents), 0, SPEAR1310_RAS_CTRL_REG0,
-			SPEAR1310_PCI_CLK_SHIFT, SPEAR1310_PCI_CLK_MASK, 0,
-			&_lock);
+			ARRAY_SIZE(pci_parents), CLK_SET_RATE_NO_REPARENT,
+			SPEAR1310_RAS_CTRL_REG0, SPEAR1310_PCI_CLK_SHIFT,
+			SPEAR1310_PCI_CLK_MASK, 0, &_lock);
 	clk_register_clkdev(clk, "pci_mclk", NULL);
 
 	clk = clk_register_gate(NULL, "pci_clk", "pci_mclk", 0,
@@ -1098,9 +1105,9 @@ void __init spear1310_clk_init(void __iomem *misc_base, void __iomem *ras_base)
 	clk_register_clkdev(clk, NULL, "pci");
 
 	clk = clk_register_mux(NULL, "tdm1_mclk", tdm_parents,
-			ARRAY_SIZE(tdm_parents), 0, SPEAR1310_RAS_CTRL_REG0,
-			SPEAR1310_TDM1_CLK_SHIFT, SPEAR1310_TDM_CLK_MASK, 0,
-			&_lock);
+			ARRAY_SIZE(tdm_parents), CLK_SET_RATE_NO_REPARENT,
+			SPEAR1310_RAS_CTRL_REG0, SPEAR1310_TDM1_CLK_SHIFT,
+			SPEAR1310_TDM_CLK_MASK, 0, &_lock);
 	clk_register_clkdev(clk, "tdm1_mclk", NULL);
 
 	clk = clk_register_gate(NULL, "tdm1_clk", "tdm1_mclk", 0,
@@ -1109,9 +1116,9 @@ void __init spear1310_clk_init(void __iomem *misc_base, void __iomem *ras_base)
 	clk_register_clkdev(clk, NULL, "tdm_hdlc.0");
 
 	clk = clk_register_mux(NULL, "tdm2_mclk", tdm_parents,
-			ARRAY_SIZE(tdm_parents), 0, SPEAR1310_RAS_CTRL_REG0,
-			SPEAR1310_TDM2_CLK_SHIFT, SPEAR1310_TDM_CLK_MASK, 0,
-			&_lock);
+			ARRAY_SIZE(tdm_parents), CLK_SET_RATE_NO_REPARENT,
+			SPEAR1310_RAS_CTRL_REG0, SPEAR1310_TDM2_CLK_SHIFT,
+			SPEAR1310_TDM_CLK_MASK, 0, &_lock);
 	clk_register_clkdev(clk, "tdm2_mclk", NULL);
 
 	clk = clk_register_gate(NULL, "tdm2_clk", "tdm2_mclk", 0,
diff --git a/drivers/clk/spear/spear1340_clock.c b/drivers/clk/spear/spear1340_clock.c
index 9d0b3949db30..fe835c1845fe 100644
--- a/drivers/clk/spear/spear1340_clock.c
+++ b/drivers/clk/spear/spear1340_clock.c
@@ -473,9 +473,9 @@ void __init spear1340_clk_init(void __iomem *misc_base)
 	/* clock derived from 24 or 25 MHz osc clk */
 	/* vco-pll */
 	clk = clk_register_mux(NULL, "vco1_mclk", vco_parents,
-			ARRAY_SIZE(vco_parents), 0, SPEAR1340_PLL_CFG,
-			SPEAR1340_PLL1_CLK_SHIFT, SPEAR1340_PLL_CLK_MASK, 0,
-			&_lock);
+			ARRAY_SIZE(vco_parents), CLK_SET_RATE_NO_REPARENT,
+			SPEAR1340_PLL_CFG, SPEAR1340_PLL1_CLK_SHIFT,
+			SPEAR1340_PLL_CLK_MASK, 0, &_lock);
 	clk_register_clkdev(clk, "vco1_mclk", NULL);
 	clk = clk_register_vco_pll("vco1_clk", "pll1_clk", NULL, "vco1_mclk", 0,
 			SPEAR1340_PLL1_CTR, SPEAR1340_PLL1_FRQ, pll_rtbl,
@@ -484,9 +484,9 @@ void __init spear1340_clk_init(void __iomem *misc_base)
 	clk_register_clkdev(clk1, "pll1_clk", NULL);
 
 	clk = clk_register_mux(NULL, "vco2_mclk", vco_parents,
-			ARRAY_SIZE(vco_parents), 0, SPEAR1340_PLL_CFG,
-			SPEAR1340_PLL2_CLK_SHIFT, SPEAR1340_PLL_CLK_MASK, 0,
-			&_lock);
+			ARRAY_SIZE(vco_parents), CLK_SET_RATE_NO_REPARENT,
+			SPEAR1340_PLL_CFG, SPEAR1340_PLL2_CLK_SHIFT,
+			SPEAR1340_PLL_CLK_MASK, 0, &_lock);
 	clk_register_clkdev(clk, "vco2_mclk", NULL);
 	clk = clk_register_vco_pll("vco2_clk", "pll2_clk", NULL, "vco2_mclk", 0,
 			SPEAR1340_PLL2_CTR, SPEAR1340_PLL2_FRQ, pll_rtbl,
@@ -495,9 +495,9 @@ void __init spear1340_clk_init(void __iomem *misc_base)
 	clk_register_clkdev(clk1, "pll2_clk", NULL);
 
 	clk = clk_register_mux(NULL, "vco3_mclk", vco_parents,
-			ARRAY_SIZE(vco_parents), 0, SPEAR1340_PLL_CFG,
-			SPEAR1340_PLL3_CLK_SHIFT, SPEAR1340_PLL_CLK_MASK, 0,
-			&_lock);
+			ARRAY_SIZE(vco_parents), CLK_SET_RATE_NO_REPARENT,
+			SPEAR1340_PLL_CFG, SPEAR1340_PLL3_CLK_SHIFT,
+			SPEAR1340_PLL_CLK_MASK, 0, &_lock);
 	clk_register_clkdev(clk, "vco3_mclk", NULL);
 	clk = clk_register_vco_pll("vco3_clk", "pll3_clk", NULL, "vco3_mclk", 0,
 			SPEAR1340_PLL3_CTR, SPEAR1340_PLL3_FRQ, pll_rtbl,
@@ -561,8 +561,8 @@ void __init spear1340_clk_init(void __iomem *misc_base)
 	clk_register_clkdev(clk, "amba_syn_clk", NULL);
 
 	clk = clk_register_mux(NULL, "sys_mclk", sys_parents,
-			ARRAY_SIZE(sys_parents), 0, SPEAR1340_SYS_CLK_CTRL,
-			SPEAR1340_SCLK_SRC_SEL_SHIFT,
+			ARRAY_SIZE(sys_parents), CLK_SET_RATE_NO_REPARENT,
+			SPEAR1340_SYS_CLK_CTRL, SPEAR1340_SCLK_SRC_SEL_SHIFT,
 			SPEAR1340_SCLK_SRC_SEL_MASK, 0, &_lock);
 	clk_register_clkdev(clk, "sys_mclk", NULL);
 
@@ -583,8 +583,8 @@ void __init spear1340_clk_init(void __iomem *misc_base)
 	clk_register_clkdev(clk, NULL, "smp_twd");
 
 	clk = clk_register_mux(NULL, "ahb_clk", ahb_parents,
-			ARRAY_SIZE(ahb_parents), 0, SPEAR1340_SYS_CLK_CTRL,
-			SPEAR1340_HCLK_SRC_SEL_SHIFT,
+			ARRAY_SIZE(ahb_parents), CLK_SET_RATE_NO_REPARENT,
+			SPEAR1340_SYS_CLK_CTRL, SPEAR1340_HCLK_SRC_SEL_SHIFT,
 			SPEAR1340_HCLK_SRC_SEL_MASK, 0, &_lock);
 	clk_register_clkdev(clk, "ahb_clk", NULL);
 
@@ -594,9 +594,9 @@ void __init spear1340_clk_init(void __iomem *misc_base)
 
 	/* gpt clocks */
 	clk = clk_register_mux(NULL, "gpt0_mclk", gpt_parents,
-			ARRAY_SIZE(gpt_parents), 0, SPEAR1340_PERIP_CLK_CFG,
-			SPEAR1340_GPT0_CLK_SHIFT, SPEAR1340_GPT_CLK_MASK, 0,
-			&_lock);
+			ARRAY_SIZE(gpt_parents), CLK_SET_RATE_NO_REPARENT,
+			SPEAR1340_PERIP_CLK_CFG, SPEAR1340_GPT0_CLK_SHIFT,
+			SPEAR1340_GPT_CLK_MASK, 0, &_lock);
 	clk_register_clkdev(clk, "gpt0_mclk", NULL);
 	clk = clk_register_gate(NULL, "gpt0_clk", "gpt0_mclk", 0,
 			SPEAR1340_PERIP1_CLK_ENB, SPEAR1340_GPT0_CLK_ENB, 0,
@@ -604,9 +604,9 @@ void __init spear1340_clk_init(void __iomem *misc_base)
 	clk_register_clkdev(clk, NULL, "gpt0");
 
 	clk = clk_register_mux(NULL, "gpt1_mclk", gpt_parents,
-			ARRAY_SIZE(gpt_parents), 0, SPEAR1340_PERIP_CLK_CFG,
-			SPEAR1340_GPT1_CLK_SHIFT, SPEAR1340_GPT_CLK_MASK, 0,
-			&_lock);
+			ARRAY_SIZE(gpt_parents), CLK_SET_RATE_NO_REPARENT,
+			SPEAR1340_PERIP_CLK_CFG, SPEAR1340_GPT1_CLK_SHIFT,
+			SPEAR1340_GPT_CLK_MASK, 0, &_lock);
 	clk_register_clkdev(clk, "gpt1_mclk", NULL);
 	clk = clk_register_gate(NULL, "gpt1_clk", "gpt1_mclk", 0,
 			SPEAR1340_PERIP1_CLK_ENB, SPEAR1340_GPT1_CLK_ENB, 0,
@@ -614,9 +614,9 @@ void __init spear1340_clk_init(void __iomem *misc_base)
 	clk_register_clkdev(clk, NULL, "gpt1");
 
 	clk = clk_register_mux(NULL, "gpt2_mclk", gpt_parents,
-			ARRAY_SIZE(gpt_parents), 0, SPEAR1340_PERIP_CLK_CFG,
-			SPEAR1340_GPT2_CLK_SHIFT, SPEAR1340_GPT_CLK_MASK, 0,
-			&_lock);
+			ARRAY_SIZE(gpt_parents), CLK_SET_RATE_NO_REPARENT,
+			SPEAR1340_PERIP_CLK_CFG, SPEAR1340_GPT2_CLK_SHIFT,
+			SPEAR1340_GPT_CLK_MASK, 0, &_lock);
 	clk_register_clkdev(clk, "gpt2_mclk", NULL);
 	clk = clk_register_gate(NULL, "gpt2_clk", "gpt2_mclk", 0,
 			SPEAR1340_PERIP2_CLK_ENB, SPEAR1340_GPT2_CLK_ENB, 0,
@@ -624,9 +624,9 @@ void __init spear1340_clk_init(void __iomem *misc_base)
 	clk_register_clkdev(clk, NULL, "gpt2");
 
 	clk = clk_register_mux(NULL, "gpt3_mclk", gpt_parents,
-			ARRAY_SIZE(gpt_parents), 0, SPEAR1340_PERIP_CLK_CFG,
-			SPEAR1340_GPT3_CLK_SHIFT, SPEAR1340_GPT_CLK_MASK, 0,
-			&_lock);
+			ARRAY_SIZE(gpt_parents), CLK_SET_RATE_NO_REPARENT,
+			SPEAR1340_PERIP_CLK_CFG, SPEAR1340_GPT3_CLK_SHIFT,
+			SPEAR1340_GPT_CLK_MASK, 0, &_lock);
 	clk_register_clkdev(clk, "gpt3_mclk", NULL);
 	clk = clk_register_gate(NULL, "gpt3_clk", "gpt3_mclk", 0,
 			SPEAR1340_PERIP2_CLK_ENB, SPEAR1340_GPT3_CLK_ENB, 0,
@@ -641,7 +641,8 @@ void __init spear1340_clk_init(void __iomem *misc_base)
 	clk_register_clkdev(clk1, "uart0_syn_gclk", NULL);
 
 	clk = clk_register_mux(NULL, "uart0_mclk", uart0_parents,
-			ARRAY_SIZE(uart0_parents), CLK_SET_RATE_PARENT,
+			ARRAY_SIZE(uart0_parents),
+			CLK_SET_RATE_PARENT | CLK_SET_RATE_NO_REPARENT,
 			SPEAR1340_PERIP_CLK_CFG, SPEAR1340_UART0_CLK_SHIFT,
 			SPEAR1340_UART_CLK_MASK, 0, &_lock);
 	clk_register_clkdev(clk, "uart0_mclk", NULL);
@@ -658,9 +659,9 @@ void __init spear1340_clk_init(void __iomem *misc_base)
 	clk_register_clkdev(clk1, "uart1_syn_gclk", NULL);
 
 	clk = clk_register_mux(NULL, "uart1_mclk", uart1_parents,
-			ARRAY_SIZE(uart1_parents), 0, SPEAR1340_PERIP_CLK_CFG,
-			SPEAR1340_UART1_CLK_SHIFT, SPEAR1340_UART_CLK_MASK, 0,
-			&_lock);
+			ARRAY_SIZE(uart1_parents), CLK_SET_RATE_NO_REPARENT,
+			SPEAR1340_PERIP_CLK_CFG, SPEAR1340_UART1_CLK_SHIFT,
+			SPEAR1340_UART_CLK_MASK, 0, &_lock);
 	clk_register_clkdev(clk, "uart1_mclk", NULL);
 
 	clk = clk_register_gate(NULL, "uart1_clk", "uart1_mclk", 0,
@@ -698,7 +699,8 @@ void __init spear1340_clk_init(void __iomem *misc_base)
 	clk_register_clkdev(clk1, "c3_syn_gclk", NULL);
 
 	clk = clk_register_mux(NULL, "c3_mclk", c3_parents,
-			ARRAY_SIZE(c3_parents), CLK_SET_RATE_PARENT,
+			ARRAY_SIZE(c3_parents),
+			CLK_SET_RATE_PARENT | CLK_SET_RATE_NO_REPARENT,
 			SPEAR1340_PERIP_CLK_CFG, SPEAR1340_C3_CLK_SHIFT,
 			SPEAR1340_C3_CLK_MASK, 0, &_lock);
 	clk_register_clkdev(clk, "c3_mclk", NULL);
@@ -710,8 +712,8 @@ void __init spear1340_clk_init(void __iomem *misc_base)
 
 	/* gmac */
 	clk = clk_register_mux(NULL, "phy_input_mclk", gmac_phy_input_parents,
-			ARRAY_SIZE(gmac_phy_input_parents), 0,
-			SPEAR1340_GMAC_CLK_CFG,
+			ARRAY_SIZE(gmac_phy_input_parents),
+			CLK_SET_RATE_NO_REPARENT, SPEAR1340_GMAC_CLK_CFG,
 			SPEAR1340_GMAC_PHY_INPUT_CLK_SHIFT,
 			SPEAR1340_GMAC_PHY_INPUT_CLK_MASK, 0, &_lock);
 	clk_register_clkdev(clk, "phy_input_mclk", NULL);
@@ -723,15 +725,16 @@ void __init spear1340_clk_init(void __iomem *misc_base)
 	clk_register_clkdev(clk1, "phy_syn_gclk", NULL);
 
 	clk = clk_register_mux(NULL, "phy_mclk", gmac_phy_parents,
-			ARRAY_SIZE(gmac_phy_parents), 0,
+			ARRAY_SIZE(gmac_phy_parents), CLK_SET_RATE_NO_REPARENT,
 			SPEAR1340_PERIP_CLK_CFG, SPEAR1340_GMAC_PHY_CLK_SHIFT,
 			SPEAR1340_GMAC_PHY_CLK_MASK, 0, &_lock);
 	clk_register_clkdev(clk, "stmmacphy.0", NULL);
 
 	/* clcd */
 	clk = clk_register_mux(NULL, "clcd_syn_mclk", clcd_synth_parents,
-			ARRAY_SIZE(clcd_synth_parents), 0,
-			SPEAR1340_CLCD_CLK_SYNT, SPEAR1340_CLCD_SYNT_CLK_SHIFT,
+			ARRAY_SIZE(clcd_synth_parents),
+			CLK_SET_RATE_NO_REPARENT, SPEAR1340_CLCD_CLK_SYNT,
+			SPEAR1340_CLCD_SYNT_CLK_SHIFT,
 			SPEAR1340_CLCD_SYNT_CLK_MASK, 0, &_lock);
 	clk_register_clkdev(clk, "clcd_syn_mclk", NULL);
 
@@ -741,7 +744,8 @@ void __init spear1340_clk_init(void __iomem *misc_base)
 	clk_register_clkdev(clk, "clcd_syn_clk", NULL);
 
 	clk = clk_register_mux(NULL, "clcd_pixel_mclk", clcd_pixel_parents,
-			ARRAY_SIZE(clcd_pixel_parents), CLK_SET_RATE_PARENT,
+			ARRAY_SIZE(clcd_pixel_parents),
+			CLK_SET_RATE_PARENT | CLK_SET_RATE_NO_REPARENT,
 			SPEAR1340_PERIP_CLK_CFG, SPEAR1340_CLCD_CLK_SHIFT,
 			SPEAR1340_CLCD_CLK_MASK, 0, &_lock);
 	clk_register_clkdev(clk, "clcd_pixel_mclk", NULL);
@@ -753,9 +757,9 @@ void __init spear1340_clk_init(void __iomem *misc_base)
 
 	/* i2s */
 	clk = clk_register_mux(NULL, "i2s_src_mclk", i2s_src_parents,
-			ARRAY_SIZE(i2s_src_parents), 0, SPEAR1340_I2S_CLK_CFG,
-			SPEAR1340_I2S_SRC_CLK_SHIFT, SPEAR1340_I2S_SRC_CLK_MASK,
-			0, &_lock);
+			ARRAY_SIZE(i2s_src_parents), CLK_SET_RATE_NO_REPARENT,
+			SPEAR1340_I2S_CLK_CFG, SPEAR1340_I2S_SRC_CLK_SHIFT,
+			SPEAR1340_I2S_SRC_CLK_MASK, 0, &_lock);
 	clk_register_clkdev(clk, "i2s_src_mclk", NULL);
 
 	clk = clk_register_aux("i2s_prs1_clk", NULL, "i2s_src_mclk",
@@ -765,7 +769,8 @@ void __init spear1340_clk_init(void __iomem *misc_base)
 	clk_register_clkdev(clk, "i2s_prs1_clk", NULL);
 
 	clk = clk_register_mux(NULL, "i2s_ref_mclk", i2s_ref_parents,
-			ARRAY_SIZE(i2s_ref_parents), CLK_SET_RATE_PARENT,
+			ARRAY_SIZE(i2s_ref_parents),
+			CLK_SET_RATE_PARENT | CLK_SET_RATE_NO_REPARENT,
 			SPEAR1340_I2S_CLK_CFG, SPEAR1340_I2S_REF_SHIFT,
 			SPEAR1340_I2S_REF_SEL_MASK, 0, &_lock);
 	clk_register_clkdev(clk, "i2s_ref_mclk", NULL);
@@ -891,13 +896,15 @@ void __init spear1340_clk_init(void __iomem *misc_base)
 
 	/* RAS clks */
 	clk = clk_register_mux(NULL, "gen_syn0_1_mclk", gen_synth0_1_parents,
-			ARRAY_SIZE(gen_synth0_1_parents), 0, SPEAR1340_PLL_CFG,
+			ARRAY_SIZE(gen_synth0_1_parents),
+			CLK_SET_RATE_NO_REPARENT, SPEAR1340_PLL_CFG,
 			SPEAR1340_GEN_SYNT0_1_CLK_SHIFT,
 			SPEAR1340_GEN_SYNT_CLK_MASK, 0, &_lock);
 	clk_register_clkdev(clk, "gen_syn0_1_mclk", NULL);
 
 	clk = clk_register_mux(NULL, "gen_syn2_3_mclk", gen_synth2_3_parents,
-			ARRAY_SIZE(gen_synth2_3_parents), 0, SPEAR1340_PLL_CFG,
+			ARRAY_SIZE(gen_synth2_3_parents),
+			CLK_SET_RATE_NO_REPARENT, SPEAR1340_PLL_CFG,
 			SPEAR1340_GEN_SYNT2_3_CLK_SHIFT,
 			SPEAR1340_GEN_SYNT_CLK_MASK, 0, &_lock);
 	clk_register_clkdev(clk, "gen_syn2_3_mclk", NULL);
@@ -938,7 +945,8 @@ void __init spear1340_clk_init(void __iomem *misc_base)
 	clk_register_clkdev(clk, NULL, "spear_cec.1");
 
 	clk = clk_register_mux(NULL, "spdif_out_mclk", spdif_out_parents,
-			ARRAY_SIZE(spdif_out_parents), CLK_SET_RATE_PARENT,
+			ARRAY_SIZE(spdif_out_parents),
+			CLK_SET_RATE_PARENT | CLK_SET_RATE_NO_REPARENT,
 			SPEAR1340_PERIP_CLK_CFG, SPEAR1340_SPDIF_OUT_CLK_SHIFT,
 			SPEAR1340_SPDIF_CLK_MASK, 0, &_lock);
 	clk_register_clkdev(clk, "spdif_out_mclk", NULL);
@@ -949,7 +957,8 @@ void __init spear1340_clk_init(void __iomem *misc_base)
 	clk_register_clkdev(clk, NULL, "d0000000.spdif-out");
 
 	clk = clk_register_mux(NULL, "spdif_in_mclk", spdif_in_parents,
-			ARRAY_SIZE(spdif_in_parents), CLK_SET_RATE_PARENT,
+			ARRAY_SIZE(spdif_in_parents),
+			CLK_SET_RATE_PARENT | CLK_SET_RATE_NO_REPARENT,
 			SPEAR1340_PERIP_CLK_CFG, SPEAR1340_SPDIF_IN_CLK_SHIFT,
 			SPEAR1340_SPDIF_CLK_MASK, 0, &_lock);
 	clk_register_clkdev(clk, "spdif_in_mclk", NULL);
diff --git a/drivers/clk/spear/spear3xx_clock.c b/drivers/clk/spear/spear3xx_clock.c
index 080c3c5e33f6..c2d204315546 100644
--- a/drivers/clk/spear/spear3xx_clock.c
+++ b/drivers/clk/spear/spear3xx_clock.c
@@ -294,7 +294,8 @@ static void __init spear320_clk_init(void __iomem *soc_config_base)
 	clk_register_clkdev(clk, NULL, "a9400000.i2s");
 
 	clk = clk_register_mux(NULL, "i2s_ref_clk", i2s_ref_parents,
-			ARRAY_SIZE(i2s_ref_parents), CLK_SET_RATE_PARENT,
+			ARRAY_SIZE(i2s_ref_parents),
+			CLK_SET_RATE_PARENT | CLK_SET_RATE_NO_REPARENT,
 			SPEAR320_CONTROL_REG, I2S_REF_PCLK_SHIFT,
 			I2S_REF_PCLK_MASK, 0, &_lock);
 	clk_register_clkdev(clk, "i2s_ref_clk", NULL);
@@ -313,57 +314,66 @@ static void __init spear320_clk_init(void __iomem *soc_config_base)
 	clk_register_clkdev(clk, "hclk", "ab000000.eth");
 
 	clk = clk_register_mux(NULL, "rs485_clk", uartx_parents,
-			ARRAY_SIZE(uartx_parents), CLK_SET_RATE_PARENT,
+			ARRAY_SIZE(uartx_parents),
+			CLK_SET_RATE_PARENT | CLK_SET_RATE_NO_REPARENT,
 			SPEAR320_EXT_CTRL_REG, SPEAR320_RS485_PCLK_SHIFT,
 			SPEAR320_UARTX_PCLK_MASK, 0, &_lock);
 	clk_register_clkdev(clk, NULL, "a9300000.serial");
 
 	clk = clk_register_mux(NULL, "sdhci_clk", sdhci_parents,
-			ARRAY_SIZE(sdhci_parents), CLK_SET_RATE_PARENT,
+			ARRAY_SIZE(sdhci_parents),
+			CLK_SET_RATE_PARENT | CLK_SET_RATE_NO_REPARENT,
 			SPEAR320_CONTROL_REG, SDHCI_PCLK_SHIFT, SDHCI_PCLK_MASK,
 			0, &_lock);
 	clk_register_clkdev(clk, NULL, "70000000.sdhci");
 
 	clk = clk_register_mux(NULL, "smii_pclk", smii0_parents,
-			ARRAY_SIZE(smii0_parents), 0, SPEAR320_CONTROL_REG,
-			SMII_PCLK_SHIFT, SMII_PCLK_MASK, 0, &_lock);
+			ARRAY_SIZE(smii0_parents), CLK_SET_RATE_NO_REPARENT,
+			SPEAR320_CONTROL_REG, SMII_PCLK_SHIFT, SMII_PCLK_MASK,
+			0, &_lock);
 	clk_register_clkdev(clk, NULL, "smii_pclk");
 
 	clk = clk_register_fixed_factor(NULL, "smii_clk", "smii_pclk", 0, 1, 1);
 	clk_register_clkdev(clk, NULL, "smii");
 
 	clk = clk_register_mux(NULL, "uart1_clk", uartx_parents,
-			ARRAY_SIZE(uartx_parents), CLK_SET_RATE_PARENT,
+			ARRAY_SIZE(uartx_parents),
+			CLK_SET_RATE_PARENT | CLK_SET_RATE_NO_REPARENT,
 			SPEAR320_CONTROL_REG, UART1_PCLK_SHIFT, UART1_PCLK_MASK,
 			0, &_lock);
 	clk_register_clkdev(clk, NULL, "a3000000.serial");
 
 	clk = clk_register_mux(NULL, "uart2_clk", uartx_parents,
-			ARRAY_SIZE(uartx_parents), CLK_SET_RATE_PARENT,
+			ARRAY_SIZE(uartx_parents),
+			CLK_SET_RATE_PARENT | CLK_SET_RATE_NO_REPARENT,
 			SPEAR320_EXT_CTRL_REG, SPEAR320_UART2_PCLK_SHIFT,
 			SPEAR320_UARTX_PCLK_MASK, 0, &_lock);
 	clk_register_clkdev(clk, NULL, "a4000000.serial");
 
 	clk = clk_register_mux(NULL, "uart3_clk", uartx_parents,
-			ARRAY_SIZE(uartx_parents), CLK_SET_RATE_PARENT,
+			ARRAY_SIZE(uartx_parents),
+			CLK_SET_RATE_PARENT | CLK_SET_RATE_NO_REPARENT,
 			SPEAR320_EXT_CTRL_REG, SPEAR320_UART3_PCLK_SHIFT,
 			SPEAR320_UARTX_PCLK_MASK, 0, &_lock);
 	clk_register_clkdev(clk, NULL, "a9100000.serial");
 
 	clk = clk_register_mux(NULL, "uart4_clk", uartx_parents,
-			ARRAY_SIZE(uartx_parents), CLK_SET_RATE_PARENT,
+			ARRAY_SIZE(uartx_parents),
+			CLK_SET_RATE_PARENT | CLK_SET_RATE_NO_REPARENT,
 			SPEAR320_EXT_CTRL_REG, SPEAR320_UART4_PCLK_SHIFT,
 			SPEAR320_UARTX_PCLK_MASK, 0, &_lock);
 	clk_register_clkdev(clk, NULL, "a9200000.serial");
 
 	clk = clk_register_mux(NULL, "uart5_clk", uartx_parents,
-			ARRAY_SIZE(uartx_parents), CLK_SET_RATE_PARENT,
+			ARRAY_SIZE(uartx_parents),
+			CLK_SET_RATE_PARENT | CLK_SET_RATE_NO_REPARENT,
 			SPEAR320_EXT_CTRL_REG, SPEAR320_UART5_PCLK_SHIFT,
 			SPEAR320_UARTX_PCLK_MASK, 0, &_lock);
 	clk_register_clkdev(clk, NULL, "60000000.serial");
 
 	clk = clk_register_mux(NULL, "uart6_clk", uartx_parents,
-			ARRAY_SIZE(uartx_parents), CLK_SET_RATE_PARENT,
+			ARRAY_SIZE(uartx_parents),
+			CLK_SET_RATE_PARENT | CLK_SET_RATE_NO_REPARENT,
 			SPEAR320_EXT_CTRL_REG, SPEAR320_UART6_PCLK_SHIFT,
 			SPEAR320_UARTX_PCLK_MASK, 0, &_lock);
 	clk_register_clkdev(clk, NULL, "60100000.serial");
@@ -427,7 +437,8 @@ void __init spear3xx_clk_init(void __iomem *misc_base, void __iomem *soc_config_
 	clk_register_clkdev(clk1, "uart_syn_gclk", NULL);
 
 	clk = clk_register_mux(NULL, "uart0_mclk", uart0_parents,
-			ARRAY_SIZE(uart0_parents), CLK_SET_RATE_PARENT,
+			ARRAY_SIZE(uart0_parents),
+			CLK_SET_RATE_PARENT | CLK_SET_RATE_NO_REPARENT,
 			PERIP_CLK_CFG, UART_CLK_SHIFT, UART_CLK_MASK, 0,
 			&_lock);
 	clk_register_clkdev(clk, "uart0_mclk", NULL);
@@ -444,7 +455,8 @@ void __init spear3xx_clk_init(void __iomem *misc_base, void __iomem *soc_config_
 	clk_register_clkdev(clk1, "firda_syn_gclk", NULL);
 
 	clk = clk_register_mux(NULL, "firda_mclk", firda_parents,
-			ARRAY_SIZE(firda_parents), CLK_SET_RATE_PARENT,
+			ARRAY_SIZE(firda_parents),
+			CLK_SET_RATE_PARENT | CLK_SET_RATE_NO_REPARENT,
 			PERIP_CLK_CFG, FIRDA_CLK_SHIFT, FIRDA_CLK_MASK, 0,
 			&_lock);
 	clk_register_clkdev(clk, "firda_mclk", NULL);
@@ -458,14 +470,16 @@ void __init spear3xx_clk_init(void __iomem *misc_base, void __iomem *soc_config_
 	clk_register_gpt("gpt0_syn_clk", "pll1_clk", 0, PRSC0_CLK_CFG, gpt_rtbl,
 			ARRAY_SIZE(gpt_rtbl), &_lock);
 	clk = clk_register_mux(NULL, "gpt0_clk", gpt0_parents,
-			ARRAY_SIZE(gpt0_parents), CLK_SET_RATE_PARENT,
+			ARRAY_SIZE(gpt0_parents),
+			CLK_SET_RATE_PARENT | CLK_SET_RATE_NO_REPARENT,
 			PERIP_CLK_CFG, GPT0_CLK_SHIFT, GPT_CLK_MASK, 0, &_lock);
 	clk_register_clkdev(clk, NULL, "gpt0");
 
 	clk_register_gpt("gpt1_syn_clk", "pll1_clk", 0, PRSC1_CLK_CFG, gpt_rtbl,
 			ARRAY_SIZE(gpt_rtbl), &_lock);
 	clk = clk_register_mux(NULL, "gpt1_mclk", gpt1_parents,
-			ARRAY_SIZE(gpt1_parents), CLK_SET_RATE_PARENT,
+			ARRAY_SIZE(gpt1_parents),
+			CLK_SET_RATE_PARENT | CLK_SET_RATE_NO_REPARENT,
 			PERIP_CLK_CFG, GPT1_CLK_SHIFT, GPT_CLK_MASK, 0, &_lock);
 	clk_register_clkdev(clk, "gpt1_mclk", NULL);
 	clk = clk_register_gate(NULL, "gpt1_clk", "gpt1_mclk",
@@ -476,7 +490,8 @@ void __init spear3xx_clk_init(void __iomem *misc_base, void __iomem *soc_config_
 	clk_register_gpt("gpt2_syn_clk", "pll1_clk", 0, PRSC2_CLK_CFG, gpt_rtbl,
 			ARRAY_SIZE(gpt_rtbl), &_lock);
 	clk = clk_register_mux(NULL, "gpt2_mclk", gpt2_parents,
-			ARRAY_SIZE(gpt2_parents), CLK_SET_RATE_PARENT,
+			ARRAY_SIZE(gpt2_parents),
+			CLK_SET_RATE_PARENT | CLK_SET_RATE_NO_REPARENT,
 			PERIP_CLK_CFG, GPT2_CLK_SHIFT, GPT_CLK_MASK, 0, &_lock);
 	clk_register_clkdev(clk, "gpt2_mclk", NULL);
 	clk = clk_register_gate(NULL, "gpt2_clk", "gpt2_mclk",
@@ -498,9 +513,9 @@ void __init spear3xx_clk_init(void __iomem *misc_base, void __iomem *soc_config_
 	clk_register_clkdev(clk1, "gen1_syn_gclk", NULL);
 
 	clk = clk_register_mux(NULL, "gen2_3_par_clk", gen2_3_parents,
-			ARRAY_SIZE(gen2_3_parents), 0, CORE_CLK_CFG,
-			GEN_SYNTH2_3_CLK_SHIFT, GEN_SYNTH2_3_CLK_MASK, 0,
-			&_lock);
+			ARRAY_SIZE(gen2_3_parents), CLK_SET_RATE_NO_REPARENT,
+			CORE_CLK_CFG, GEN_SYNTH2_3_CLK_SHIFT,
+			GEN_SYNTH2_3_CLK_MASK, 0, &_lock);
 	clk_register_clkdev(clk, "gen2_3_par_clk", NULL);
 
 	clk = clk_register_aux("gen2_syn_clk", "gen2_syn_gclk",
@@ -540,8 +555,8 @@ void __init spear3xx_clk_init(void __iomem *misc_base, void __iomem *soc_config_
 	clk_register_clkdev(clk, "ahbmult2_clk", NULL);
 
 	clk = clk_register_mux(NULL, "ddr_clk", ddr_parents,
-			ARRAY_SIZE(ddr_parents), 0, PLL_CLK_CFG, MCTR_CLK_SHIFT,
-			MCTR_CLK_MASK, 0, &_lock);
+			ARRAY_SIZE(ddr_parents), CLK_SET_RATE_NO_REPARENT,
+			PLL_CLK_CFG, MCTR_CLK_SHIFT, MCTR_CLK_MASK, 0, &_lock);
 	clk_register_clkdev(clk, "ddr_clk", NULL);
 
 	clk = clk_register_divider(NULL, "apb_clk", "ahb_clk",
diff --git a/drivers/clk/spear/spear6xx_clock.c b/drivers/clk/spear/spear6xx_clock.c
index 9406f2426d64..4f649c9cb094 100644
--- a/drivers/clk/spear/spear6xx_clock.c
+++ b/drivers/clk/spear/spear6xx_clock.c
@@ -169,8 +169,9 @@ void __init spear6xx_clk_init(void __iomem *misc_base)
 	clk_register_clkdev(clk1, "uart_syn_gclk", NULL);
 
 	clk = clk_register_mux(NULL, "uart_mclk", uart_parents,
-			ARRAY_SIZE(uart_parents), 0, PERIP_CLK_CFG,
-			UART_CLK_SHIFT, UART_CLK_MASK, 0, &_lock);
+			ARRAY_SIZE(uart_parents), CLK_SET_RATE_NO_REPARENT,
+			PERIP_CLK_CFG, UART_CLK_SHIFT, UART_CLK_MASK, 0,
+			&_lock);
 	clk_register_clkdev(clk, "uart_mclk", NULL);
 
 	clk = clk_register_gate(NULL, "uart0", "uart_mclk", 0, PERIP1_CLK_ENB,
@@ -188,8 +189,9 @@ void __init spear6xx_clk_init(void __iomem *misc_base)
 	clk_register_clkdev(clk1, "firda_syn_gclk", NULL);
 
 	clk = clk_register_mux(NULL, "firda_mclk", firda_parents,
-			ARRAY_SIZE(firda_parents), 0, PERIP_CLK_CFG,
-			FIRDA_CLK_SHIFT, FIRDA_CLK_MASK, 0, &_lock);
+			ARRAY_SIZE(firda_parents), CLK_SET_RATE_NO_REPARENT,
+			PERIP_CLK_CFG, FIRDA_CLK_SHIFT, FIRDA_CLK_MASK, 0,
+			&_lock);
 	clk_register_clkdev(clk, "firda_mclk", NULL);
 
 	clk = clk_register_gate(NULL, "firda_clk", "firda_mclk", 0,
@@ -203,8 +205,9 @@ void __init spear6xx_clk_init(void __iomem *misc_base)
 	clk_register_clkdev(clk1, "clcd_syn_gclk", NULL);
 
 	clk = clk_register_mux(NULL, "clcd_mclk", clcd_parents,
-			ARRAY_SIZE(clcd_parents), 0, PERIP_CLK_CFG,
-			CLCD_CLK_SHIFT, CLCD_CLK_MASK, 0, &_lock);
+			ARRAY_SIZE(clcd_parents), CLK_SET_RATE_NO_REPARENT,
+			PERIP_CLK_CFG, CLCD_CLK_SHIFT, CLCD_CLK_MASK, 0,
+			&_lock);
 	clk_register_clkdev(clk, "clcd_mclk", NULL);
 
 	clk = clk_register_gate(NULL, "clcd_clk", "clcd_mclk", 0,
@@ -217,13 +220,13 @@ void __init spear6xx_clk_init(void __iomem *misc_base)
 	clk_register_clkdev(clk, "gpt0_1_syn_clk", NULL);
 
 	clk = clk_register_mux(NULL, "gpt0_mclk", gpt0_1_parents,
-			ARRAY_SIZE(gpt0_1_parents), 0, PERIP_CLK_CFG,
-			GPT0_CLK_SHIFT, GPT_CLK_MASK, 0, &_lock);
+			ARRAY_SIZE(gpt0_1_parents), CLK_SET_RATE_NO_REPARENT,
+			PERIP_CLK_CFG, GPT0_CLK_SHIFT, GPT_CLK_MASK, 0, &_lock);
 	clk_register_clkdev(clk, NULL, "gpt0");
 
 	clk = clk_register_mux(NULL, "gpt1_mclk", gpt0_1_parents,
-			ARRAY_SIZE(gpt0_1_parents), 0, PERIP_CLK_CFG,
-			GPT1_CLK_SHIFT, GPT_CLK_MASK, 0, &_lock);
+			ARRAY_SIZE(gpt0_1_parents), CLK_SET_RATE_NO_REPARENT,
+			PERIP_CLK_CFG, GPT1_CLK_SHIFT, GPT_CLK_MASK, 0, &_lock);
 	clk_register_clkdev(clk, "gpt1_mclk", NULL);
 
 	clk = clk_register_gate(NULL, "gpt1_clk", "gpt1_mclk", 0,
@@ -235,8 +238,8 @@ void __init spear6xx_clk_init(void __iomem *misc_base)
 	clk_register_clkdev(clk, "gpt2_syn_clk", NULL);
 
 	clk = clk_register_mux(NULL, "gpt2_mclk", gpt2_parents,
-			ARRAY_SIZE(gpt2_parents), 0, PERIP_CLK_CFG,
-			GPT2_CLK_SHIFT, GPT_CLK_MASK, 0, &_lock);
+			ARRAY_SIZE(gpt2_parents), CLK_SET_RATE_NO_REPARENT,
+			PERIP_CLK_CFG, GPT2_CLK_SHIFT, GPT_CLK_MASK, 0, &_lock);
 	clk_register_clkdev(clk, "gpt2_mclk", NULL);
 
 	clk = clk_register_gate(NULL, "gpt2_clk", "gpt2_mclk", 0,
@@ -248,8 +251,8 @@ void __init spear6xx_clk_init(void __iomem *misc_base)
 	clk_register_clkdev(clk, "gpt3_syn_clk", NULL);
 
 	clk = clk_register_mux(NULL, "gpt3_mclk", gpt3_parents,
-			ARRAY_SIZE(gpt3_parents), 0, PERIP_CLK_CFG,
-			GPT3_CLK_SHIFT, GPT_CLK_MASK, 0, &_lock);
+			ARRAY_SIZE(gpt3_parents), CLK_SET_RATE_NO_REPARENT,
+			PERIP_CLK_CFG, GPT3_CLK_SHIFT, GPT_CLK_MASK, 0, &_lock);
 	clk_register_clkdev(clk, "gpt3_mclk", NULL);
 
 	clk = clk_register_gate(NULL, "gpt3_clk", "gpt3_mclk", 0,
@@ -277,8 +280,8 @@ void __init spear6xx_clk_init(void __iomem *misc_base)
 	clk_register_clkdev(clk, "ahbmult2_clk", NULL);
 
 	clk = clk_register_mux(NULL, "ddr_clk", ddr_parents,
-			ARRAY_SIZE(ddr_parents), 0, PLL_CLK_CFG, MCTR_CLK_SHIFT,
-			MCTR_CLK_MASK, 0, &_lock);
+			ARRAY_SIZE(ddr_parents), CLK_SET_RATE_NO_REPARENT,
+			PLL_CLK_CFG, MCTR_CLK_SHIFT, MCTR_CLK_MASK, 0, &_lock);
 	clk_register_clkdev(clk, "ddr_clk", NULL);
 
 	clk = clk_register_divider(NULL, "apb_clk", "ahb_clk",
diff --git a/drivers/clk/sunxi/clk-sunxi.c b/drivers/clk/sunxi/clk-sunxi.c
index 412912bbba53..34ee69f4d50c 100644
--- a/drivers/clk/sunxi/clk-sunxi.c
+++ b/drivers/clk/sunxi/clk-sunxi.c
@@ -25,12 +25,12 @@
 static DEFINE_SPINLOCK(clk_lock);
 
 /**
- * sunxi_osc_clk_setup() - Setup function for gatable oscillator
+ * sun4i_osc_clk_setup() - Setup function for gatable oscillator
  */
 
 #define SUNXI_OSC24M_GATE	0
 
-static void __init sunxi_osc_clk_setup(struct device_node *node)
+static void __init sun4i_osc_clk_setup(struct device_node *node)
 {
 	struct clk *clk;
 	struct clk_fixed_rate *fixed;
@@ -64,22 +64,23 @@ static void __init sunxi_osc_clk_setup(struct device_node *node)
 			&gate->hw, &clk_gate_ops,
 			CLK_IS_ROOT);
 
-	if (clk) {
+	if (!IS_ERR(clk)) {
 		of_clk_add_provider(node, of_clk_src_simple_get, clk);
 		clk_register_clkdev(clk, clk_name, NULL);
 	}
 }
+CLK_OF_DECLARE(sun4i_osc, "allwinner,sun4i-osc-clk", sun4i_osc_clk_setup);
 
 
 
 /**
- * sunxi_get_pll1_factors() - calculates n, k, m, p factors for PLL1
+ * sun4i_get_pll1_factors() - calculates n, k, m, p factors for PLL1
  * PLL1 rate is calculated as follows
  * rate = (parent_rate * n * (k + 1) >> p) / (m + 1);
  * parent_rate is always 24Mhz
  */
 
-static void sunxi_get_pll1_factors(u32 *freq, u32 parent_rate,
+static void sun4i_get_pll1_factors(u32 *freq, u32 parent_rate,
 				   u8 *n, u8 *k, u8 *m, u8 *p)
 {
 	u8 div;
@@ -124,15 +125,97 @@ static void sunxi_get_pll1_factors(u32 *freq, u32 parent_rate,
 	*n = div / 4;
 }
 
+/**
+ * sun6i_a31_get_pll1_factors() - calculates n, k and m factors for PLL1
+ * PLL1 rate is calculated as follows
+ * rate = parent_rate * (n + 1) * (k + 1) / (m + 1);
+ * parent_rate should always be 24MHz
+ */
+static void sun6i_a31_get_pll1_factors(u32 *freq, u32 parent_rate,
+				       u8 *n, u8 *k, u8 *m, u8 *p)
+{
+	/*
+	 * We can operate only on MHz, this will make our life easier
+	 * later.
+	 */
+	u32 freq_mhz = *freq / 1000000;
+	u32 parent_freq_mhz = parent_rate / 1000000;
+
+	/*
+	 * Round down the frequency to the closest multiple of either
+	 * 6 or 16
+	 */
+	u32 round_freq_6 = round_down(freq_mhz, 6);
+	u32 round_freq_16 = round_down(freq_mhz, 16);
+
+	if (round_freq_6 > round_freq_16)
+		freq_mhz = round_freq_6;
+	else
+		freq_mhz = round_freq_16;
+
+	*freq = freq_mhz * 1000000;
 
+	/*
+	 * If the factors pointer are null, we were just called to
+	 * round down the frequency.
+	 * Exit.
+	 */
+	if (n == NULL)
+		return;
+
+	/* If the frequency is a multiple of 32 MHz, k is always 3 */
+	if (!(freq_mhz % 32))
+		*k = 3;
+	/* If the frequency is a multiple of 9 MHz, k is always 2 */
+	else if (!(freq_mhz % 9))
+		*k = 2;
+	/* If the frequency is a multiple of 8 MHz, k is always 1 */
+	else if (!(freq_mhz % 8))
+		*k = 1;
+	/* Otherwise, we don't use the k factor */
+	else
+		*k = 0;
+
+	/*
+	 * If the frequency is a multiple of 2 but not a multiple of
+	 * 3, m is 3. This is the first time we use 6 here, yet we
+	 * will use it on several other places.
+	 * We use this number because it's the lowest frequency we can
+	 * generate (with n = 0, k = 0, m = 3), so every other frequency
+	 * somehow relates to this frequency.
+	 */
+	if ((freq_mhz % 6) == 2 || (freq_mhz % 6) == 4)
+		*m = 2;
+	/*
+	 * If the frequency is a multiple of 6MHz, but the factor is
+	 * odd, m will be 3
+	 */
+	else if ((freq_mhz / 6) & 1)
+		*m = 3;
+	/* Otherwise, we end up with m = 1 */
+	else
+		*m = 1;
+
+	/* Calculate n thanks to the above factors we already got */
+	*n = freq_mhz * (*m + 1) / ((*k + 1) * parent_freq_mhz) - 1;
+
+	/*
+	 * If n end up being outbound, and that we can still decrease
+	 * m, do it.
+	 */
+	if ((*n + 1) > 31 && (*m + 1) > 1) {
+		*n = (*n + 1) / 2 - 1;
+		*m = (*m + 1) / 2 - 1;
+	}
+}
 
 /**
- * sunxi_get_apb1_factors() - calculates m, p factors for APB1
+ * sun4i_get_apb1_factors() - calculates m, p factors for APB1
  * APB1 rate is calculated as follows
  * rate = (parent_rate >> p) / (m + 1);
  */
 
-static void sunxi_get_apb1_factors(u32 *freq, u32 parent_rate,
+static void sun4i_get_apb1_factors(u32 *freq, u32 parent_rate,
 				   u8 *n, u8 *k, u8 *m, u8 *p)
 {
 	u8 calcm, calcp;
@@ -178,7 +261,7 @@ struct factors_data {
 	void (*getter) (u32 *rate, u32 parent_rate, u8 *n, u8 *k, u8 *m, u8 *p);
 };
 
-static struct clk_factors_config pll1_config = {
+static struct clk_factors_config sun4i_pll1_config = {
 	.nshift = 8,
 	.nwidth = 5,
 	.kshift = 4,
@@ -189,21 +272,35 @@ static struct clk_factors_config pll1_config = {
 	.pwidth = 2,
 };
 
-static struct clk_factors_config apb1_config = {
+static struct clk_factors_config sun6i_a31_pll1_config = {
+	.nshift	= 8,
+	.nwidth = 5,
+	.kshift = 4,
+	.kwidth = 2,
+	.mshift = 0,
+	.mwidth = 2,
+};
+
+static struct clk_factors_config sun4i_apb1_config = {
 	.mshift = 0,
 	.mwidth = 5,
 	.pshift = 16,
 	.pwidth = 2,
 };
 
-static const __initconst struct factors_data pll1_data = {
-	.table = &pll1_config,
-	.getter = sunxi_get_pll1_factors,
+static const struct factors_data sun4i_pll1_data __initconst = {
+	.table = &sun4i_pll1_config,
+	.getter = sun4i_get_pll1_factors,
 };
 
-static const __initconst struct factors_data apb1_data = {
-	.table = &apb1_config,
-	.getter = sunxi_get_apb1_factors,
+static const struct factors_data sun6i_a31_pll1_data __initconst = {
+	.table = &sun6i_a31_pll1_config,
+	.getter = sun6i_a31_get_pll1_factors,
+};
+
+static const struct factors_data sun4i_apb1_data __initconst = {
+	.table = &sun4i_apb1_config,
+	.getter = sun4i_get_apb1_factors,
 };
 
 static void __init sunxi_factors_clk_setup(struct device_node *node,
@@ -221,7 +318,7 @@ static void __init sunxi_factors_clk_setup(struct device_node *node,
 	clk = clk_register_factors(NULL, clk_name, parent, 0, reg,
 				   data->table, data->getter, &clk_lock);
 
-	if (clk) {
+	if (!IS_ERR(clk)) {
 		of_clk_add_provider(node, of_clk_src_simple_get, clk);
 		clk_register_clkdev(clk, clk_name, NULL);
 	}
@@ -239,11 +336,15 @@ struct mux_data {
 	u8 shift;
 };
 
-static const __initconst struct mux_data cpu_mux_data = {
+static const struct mux_data sun4i_cpu_mux_data __initconst = {
 	.shift = 16,
 };
 
-static const __initconst struct mux_data apb1_mux_data = {
+static const struct mux_data sun6i_a31_ahb1_mux_data __initconst = {
+	.shift = 12,
+};
+
+static const struct mux_data sun4i_apb1_mux_data __initconst = {
 	.shift = 24,
 };
 
@@ -261,7 +362,8 @@ static void __init sunxi_mux_clk_setup(struct device_node *node,
 	while (i < 5 && (parents[i] = of_clk_get_parent_name(node, i)) != NULL)
 		i++;
 
-	clk = clk_register_mux(NULL, clk_name, parents, i, 0, reg,
+	clk = clk_register_mux(NULL, clk_name, parents, i,
+			       CLK_SET_RATE_NO_REPARENT, reg,
 			       data->shift, SUNXI_MUX_GATE_WIDTH,
 			       0, &clk_lock);
 
@@ -277,26 +379,34 @@ static void __init sunxi_mux_clk_setup(struct device_node *node,
  * sunxi_divider_clk_setup() - Setup function for simple divider clocks
  */
 
-#define SUNXI_DIVISOR_WIDTH	2
-
 struct div_data {
-	u8 shift;
-	u8 pow;
+	u8	shift;
+	u8	pow;
+	u8	width;
 };
 
-static const __initconst struct div_data axi_data = {
-	.shift = 0,
-	.pow = 0,
+static const struct div_data sun4i_axi_data __initconst = {
+	.shift	= 0,
+	.pow	= 0,
+	.width	= 2,
 };
 
-static const __initconst struct div_data ahb_data = {
-	.shift = 4,
-	.pow = 1,
+static const struct div_data sun4i_ahb_data __initconst = {
+	.shift	= 4,
+	.pow	= 1,
+	.width	= 2,
 };
 
-static const __initconst struct div_data apb0_data = {
-	.shift = 8,
-	.pow = 1,
+static const struct div_data sun4i_apb0_data __initconst = {
+	.shift	= 8,
+	.pow	= 1,
+	.width	= 2,
+};
+
+static const struct div_data sun6i_a31_apb2_div_data __initconst = {
+	.shift	= 0,
+	.pow	= 0,
+	.width	= 4,
 };
 
 static void __init sunxi_divider_clk_setup(struct device_node *node,
@@ -312,7 +422,7 @@ static void __init sunxi_divider_clk_setup(struct device_node *node,
 	clk_parent = of_clk_get_parent_name(node, 0);
 
 	clk = clk_register_divider(NULL, clk_name, clk_parent, 0,
-				   reg, data->shift, SUNXI_DIVISOR_WIDTH,
+				   reg, data->shift, data->width,
 				   data->pow ? CLK_DIVIDER_POWER_OF_TWO : 0,
 				   &clk_lock);
 	if (clk) {
@@ -333,34 +443,70 @@ struct gates_data {
 	DECLARE_BITMAP(mask, SUNXI_GATES_MAX_SIZE);
 };
 
-static const __initconst struct gates_data sun4i_axi_gates_data = {
+static const struct gates_data sun4i_axi_gates_data __initconst = {
 	.mask = {1},
 };
 
-static const __initconst struct gates_data sun4i_ahb_gates_data = {
+static const struct gates_data sun4i_ahb_gates_data __initconst = {
 	.mask = {0x7F77FFF, 0x14FB3F},
 };
 
-static const __initconst struct gates_data sun5i_a13_ahb_gates_data = {
+static const struct gates_data sun5i_a10s_ahb_gates_data __initconst = {
+	.mask = {0x147667e7, 0x185915},
+};
+
+static const struct gates_data sun5i_a13_ahb_gates_data __initconst = {
 	.mask = {0x107067e7, 0x185111},
 };
 
-static const __initconst struct gates_data sun4i_apb0_gates_data = {
+static const struct gates_data sun6i_a31_ahb1_gates_data __initconst = {
+	.mask = {0xEDFE7F62, 0x794F931},
+};
+
+static const struct gates_data sun7i_a20_ahb_gates_data __initconst = {
+	.mask = { 0x12f77fff, 0x16ff3f },
+};
+
+static const struct gates_data sun4i_apb0_gates_data __initconst = {
 	.mask = {0x4EF},
 };
 
-static const __initconst struct gates_data sun5i_a13_apb0_gates_data = {
+static const struct gates_data sun5i_a10s_apb0_gates_data __initconst = {
+	.mask = {0x469},
+};
+
+static const struct gates_data sun5i_a13_apb0_gates_data __initconst = {
 	.mask = {0x61},
 };
 
-static const __initconst struct gates_data sun4i_apb1_gates_data = {
+static const struct gates_data sun7i_a20_apb0_gates_data __initconst = {
+	.mask = { 0x4ff },
+};
+
+static const struct gates_data sun4i_apb1_gates_data __initconst = {
 	.mask = {0xFF00F7},
 };
 
-static const __initconst struct gates_data sun5i_a13_apb1_gates_data = {
+static const struct gates_data sun5i_a10s_apb1_gates_data __initconst = {
+	.mask = {0xf0007},
+};
+
+static const struct gates_data sun5i_a13_apb1_gates_data __initconst = {
 	.mask = {0xa0007},
 };
 
+static const struct gates_data sun6i_a31_apb1_gates_data __initconst = {
+	.mask = {0x3031},
+};
+
+static const struct gates_data sun6i_a31_apb2_gates_data __initconst = {
+	.mask = {0x3F000F},
+};
+
+static const struct gates_data sun7i_a20_apb1_gates_data __initconst = {
+	.mask = { 0xff80ff },
+};
+
 static void __init sunxi_gates_clk_setup(struct device_node *node,
 					 struct gates_data *data)
 {
@@ -410,43 +556,49 @@ static void __init sunxi_gates_clk_setup(struct device_node *node,
 	of_clk_add_provider(node, of_clk_src_onecell_get, clk_data);
 }
 
-/* Matches for of_clk_init */
-static const __initconst struct of_device_id clk_match[] = {
-	{.compatible = "allwinner,sun4i-osc-clk", .data = sunxi_osc_clk_setup,},
-	{}
-};
-
 /* Matches for factors clocks */
-static const __initconst struct of_device_id clk_factors_match[] = {
-	{.compatible = "allwinner,sun4i-pll1-clk", .data = &pll1_data,},
-	{.compatible = "allwinner,sun4i-apb1-clk", .data = &apb1_data,},
+static const struct of_device_id clk_factors_match[] __initconst = {
+	{.compatible = "allwinner,sun4i-pll1-clk", .data = &sun4i_pll1_data,},
+	{.compatible = "allwinner,sun6i-a31-pll1-clk", .data = &sun6i_a31_pll1_data,},
+	{.compatible = "allwinner,sun4i-apb1-clk", .data = &sun4i_apb1_data,},
 	{}
 };
 
 /* Matches for divider clocks */
-static const __initconst struct of_device_id clk_div_match[] = {
-	{.compatible = "allwinner,sun4i-axi-clk", .data = &axi_data,},
-	{.compatible = "allwinner,sun4i-ahb-clk", .data = &ahb_data,},
-	{.compatible = "allwinner,sun4i-apb0-clk", .data = &apb0_data,},
+static const struct of_device_id clk_div_match[] __initconst = {
+	{.compatible = "allwinner,sun4i-axi-clk", .data = &sun4i_axi_data,},
+	{.compatible = "allwinner,sun4i-ahb-clk", .data = &sun4i_ahb_data,},
+	{.compatible = "allwinner,sun4i-apb0-clk", .data = &sun4i_apb0_data,},
+	{.compatible = "allwinner,sun6i-a31-apb2-div-clk", .data = &sun6i_a31_apb2_div_data,},
 	{}
 };
 
 /* Matches for mux clocks */
-static const __initconst struct of_device_id clk_mux_match[] = {
-	{.compatible = "allwinner,sun4i-cpu-clk", .data = &cpu_mux_data,},
-	{.compatible = "allwinner,sun4i-apb1-mux-clk", .data = &apb1_mux_data,},
+static const struct of_device_id clk_mux_match[] __initconst = {
+	{.compatible = "allwinner,sun4i-cpu-clk", .data = &sun4i_cpu_mux_data,},
+	{.compatible = "allwinner,sun4i-apb1-mux-clk", .data = &sun4i_apb1_mux_data,},
+	{.compatible = "allwinner,sun6i-a31-ahb1-mux-clk", .data = &sun6i_a31_ahb1_mux_data,},
 	{}
 };
 
 /* Matches for gate clocks */
-static const __initconst struct of_device_id clk_gates_match[] = {
+static const struct of_device_id clk_gates_match[] __initconst = {
 	{.compatible = "allwinner,sun4i-axi-gates-clk", .data = &sun4i_axi_gates_data,},
 	{.compatible = "allwinner,sun4i-ahb-gates-clk", .data = &sun4i_ahb_gates_data,},
+	{.compatible = "allwinner,sun5i-a10s-ahb-gates-clk", .data = &sun5i_a10s_ahb_gates_data,},
 	{.compatible = "allwinner,sun5i-a13-ahb-gates-clk", .data = &sun5i_a13_ahb_gates_data,},
+	{.compatible = "allwinner,sun6i-a31-ahb1-gates-clk", .data = &sun6i_a31_ahb1_gates_data,},
+	{.compatible = "allwinner,sun7i-a20-ahb-gates-clk", .data = &sun7i_a20_ahb_gates_data,},
 	{.compatible = "allwinner,sun4i-apb0-gates-clk", .data = &sun4i_apb0_gates_data,},
+	{.compatible = "allwinner,sun5i-a10s-apb0-gates-clk", .data = &sun5i_a10s_apb0_gates_data,},
 	{.compatible = "allwinner,sun5i-a13-apb0-gates-clk", .data = &sun5i_a13_apb0_gates_data,},
+	{.compatible = "allwinner,sun7i-a20-apb0-gates-clk", .data = &sun7i_a20_apb0_gates_data,},
 	{.compatible = "allwinner,sun4i-apb1-gates-clk", .data = &sun4i_apb1_gates_data,},
+	{.compatible = "allwinner,sun5i-a10s-apb1-gates-clk", .data = &sun5i_a10s_apb1_gates_data,},
 	{.compatible = "allwinner,sun5i-a13-apb1-gates-clk", .data = &sun5i_a13_apb1_gates_data,},
+	{.compatible = "allwinner,sun6i-a31-apb1-gates-clk", .data = &sun6i_a31_apb1_gates_data,},
+	{.compatible = "allwinner,sun7i-a20-apb1-gates-clk", .data = &sun7i_a20_apb1_gates_data,},
+	{.compatible = "allwinner,sun6i-a31-apb2-gates-clk", .data = &sun6i_a31_apb2_gates_data,},
 	{}
 };
 
@@ -467,8 +619,8 @@ static void __init of_sunxi_table_clock_setup(const struct of_device_id *clk_mat
 
 void __init sunxi_init_clocks(void)
 {
-	/* Register all the simple sunxi clocks on DT */
-	of_clk_init(clk_match);
+	/* Register all the simple and basic clocks on DT */
+	of_clk_init(NULL);
 
 	/* Register factor clocks */
 	of_sunxi_table_clock_setup(clk_factors_match, sunxi_factors_clk_setup);
diff --git a/drivers/clk/tegra/clk-tegra114.c b/drivers/clk/tegra/clk-tegra114.c
index b6015cb4fc01..9467da7dee49 100644
--- a/drivers/clk/tegra/clk-tegra114.c
+++ b/drivers/clk/tegra/clk-tegra114.c
@@ -290,6 +290,14 @@
 /* Tegra CPU clock and reset control regs */
 #define CLK_RST_CONTROLLER_CPU_CMPLX_STATUS	0x470
 
+#ifdef CONFIG_PM_SLEEP
+static struct cpu_clk_suspend_context {
+	u32 clk_csite_src;
+	u32 cclkg_burst;
+	u32 cclkg_divider;
+} tegra114_cpu_clk_sctx;
+#endif
+
 static int periph_clk_enb_refcnt[CLK_OUT_ENB_NUM * 32];
 
 static void __iomem *clk_base;
@@ -1558,7 +1566,8 @@ static void __init tegra114_audio_clk_init(void __iomem *clk_base)
 
 	/* audio0 */
 	clk = clk_register_mux(NULL, "audio0_mux", mux_audio_sync_clk,
-			       ARRAY_SIZE(mux_audio_sync_clk), 0,
+			       ARRAY_SIZE(mux_audio_sync_clk),
+			       CLK_SET_RATE_NO_REPARENT,
 			       clk_base + AUDIO_SYNC_CLK_I2S0, 0, 3, 0,
 			       NULL);
 	clks[audio0_mux] = clk;
@@ -1570,7 +1579,8 @@ static void __init tegra114_audio_clk_init(void __iomem *clk_base)
 
 	/* audio1 */
 	clk = clk_register_mux(NULL, "audio1_mux", mux_audio_sync_clk,
-			       ARRAY_SIZE(mux_audio_sync_clk), 0,
+			       ARRAY_SIZE(mux_audio_sync_clk),
+			       CLK_SET_RATE_NO_REPARENT,
 			       clk_base + AUDIO_SYNC_CLK_I2S1, 0, 3, 0,
 			       NULL);
 	clks[audio1_mux] = clk;
@@ -1582,7 +1592,8 @@ static void __init tegra114_audio_clk_init(void __iomem *clk_base)
 
 	/* audio2 */
 	clk = clk_register_mux(NULL, "audio2_mux", mux_audio_sync_clk,
-			       ARRAY_SIZE(mux_audio_sync_clk), 0,
+			       ARRAY_SIZE(mux_audio_sync_clk),
+			       CLK_SET_RATE_NO_REPARENT,
 			       clk_base + AUDIO_SYNC_CLK_I2S2, 0, 3, 0,
 			       NULL);
 	clks[audio2_mux] = clk;
@@ -1594,7 +1605,8 @@ static void __init tegra114_audio_clk_init(void __iomem *clk_base)
 
 	/* audio3 */
 	clk = clk_register_mux(NULL, "audio3_mux", mux_audio_sync_clk,
-			       ARRAY_SIZE(mux_audio_sync_clk), 0,
+			       ARRAY_SIZE(mux_audio_sync_clk),
+			       CLK_SET_RATE_NO_REPARENT,
 			       clk_base + AUDIO_SYNC_CLK_I2S3, 0, 3, 0,
 			       NULL);
 	clks[audio3_mux] = clk;
@@ -1606,7 +1618,8 @@ static void __init tegra114_audio_clk_init(void __iomem *clk_base)
 
 	/* audio4 */
 	clk = clk_register_mux(NULL, "audio4_mux", mux_audio_sync_clk,
-			       ARRAY_SIZE(mux_audio_sync_clk), 0,
+			       ARRAY_SIZE(mux_audio_sync_clk),
+			       CLK_SET_RATE_NO_REPARENT,
 			       clk_base + AUDIO_SYNC_CLK_I2S4, 0, 3, 0,
 			       NULL);
 	clks[audio4_mux] = clk;
@@ -1618,7 +1631,8 @@ static void __init tegra114_audio_clk_init(void __iomem *clk_base)
 
 	/* spdif */
 	clk = clk_register_mux(NULL, "spdif_mux", mux_audio_sync_clk,
-			       ARRAY_SIZE(mux_audio_sync_clk), 0,
+			       ARRAY_SIZE(mux_audio_sync_clk),
+			       CLK_SET_RATE_NO_REPARENT,
 			       clk_base + AUDIO_SYNC_CLK_SPDIF, 0, 3, 0,
 			       NULL);
 	clks[spdif_mux] = clk;
@@ -1713,7 +1727,8 @@ static void __init tegra114_pmc_clk_init(void __iomem *pmc_base)
 
 	/* clk_out_1 */
 	clk = clk_register_mux(NULL, "clk_out_1_mux", clk_out1_parents,
-			       ARRAY_SIZE(clk_out1_parents), 0,
+			       ARRAY_SIZE(clk_out1_parents),
+			       CLK_SET_RATE_NO_REPARENT,
 			       pmc_base + PMC_CLK_OUT_CNTRL, 6, 3, 0,
 			       &clk_out_lock);
 	clks[clk_out_1_mux] = clk;
@@ -1725,7 +1740,8 @@ static void __init tegra114_pmc_clk_init(void __iomem *pmc_base)
 
 	/* clk_out_2 */
 	clk = clk_register_mux(NULL, "clk_out_2_mux", clk_out2_parents,
-			       ARRAY_SIZE(clk_out2_parents), 0,
+			       ARRAY_SIZE(clk_out2_parents),
+			       CLK_SET_RATE_NO_REPARENT,
 			       pmc_base + PMC_CLK_OUT_CNTRL, 14, 3, 0,
 			       &clk_out_lock);
 	clks[clk_out_2_mux] = clk;
@@ -1737,7 +1753,8 @@ static void __init tegra114_pmc_clk_init(void __iomem *pmc_base)
 
 	/* clk_out_3 */
 	clk = clk_register_mux(NULL, "clk_out_3_mux", clk_out3_parents,
-			       ARRAY_SIZE(clk_out3_parents), 0,
+			       ARRAY_SIZE(clk_out3_parents),
+			       CLK_SET_RATE_NO_REPARENT,
 			       pmc_base + PMC_CLK_OUT_CNTRL, 22, 3, 0,
 			       &clk_out_lock);
 	clks[clk_out_3_mux] = clk;
@@ -2055,7 +2072,8 @@ static __init void tegra114_periph_clk_init(void __iomem *clk_base)
 
 	/* dsia */
 	clk = clk_register_mux(NULL, "dsia_mux", mux_plld_out0_plld2_out0,
-			       ARRAY_SIZE(mux_plld_out0_plld2_out0), 0,
+			       ARRAY_SIZE(mux_plld_out0_plld2_out0),
+			       CLK_SET_RATE_NO_REPARENT,
 			       clk_base + PLLD_BASE, 25, 1, 0, &pll_d_lock);
 	clks[dsia_mux] = clk;
 	clk = tegra_clk_register_periph_gate("dsia", "dsia_mux", 0, clk_base,
@@ -2065,7 +2083,8 @@ static __init void tegra114_periph_clk_init(void __iomem *clk_base)
 
 	/* dsib */
 	clk = clk_register_mux(NULL, "dsib_mux", mux_plld_out0_plld2_out0,
-			       ARRAY_SIZE(mux_plld_out0_plld2_out0), 0,
+			       ARRAY_SIZE(mux_plld_out0_plld2_out0),
+			       CLK_SET_RATE_NO_REPARENT,
 			       clk_base + PLLD2_BASE, 25, 1, 0, &pll_d2_lock);
 	clks[dsib_mux] = clk;
 	clk = tegra_clk_register_periph_gate("dsib", "dsib_mux", 0, clk_base,
@@ -2102,7 +2121,8 @@ static __init void tegra114_periph_clk_init(void __iomem *clk_base)
 
 	/* emc */
 	clk = clk_register_mux(NULL, "emc_mux", mux_pllmcp_clkm,
-			       ARRAY_SIZE(mux_pllmcp_clkm), 0,
+			       ARRAY_SIZE(mux_pllmcp_clkm),
+			       CLK_SET_RATE_NO_REPARENT,
 			       clk_base + CLK_SOURCE_EMC,
 			       29, 3, 0, NULL);
 	clk = tegra_clk_register_periph_gate("emc", "emc_mux", 0, clk_base,
@@ -2142,9 +2162,39 @@ static void tegra114_disable_cpu_clock(u32 cpu)
 	/* flow controller would take care in the power sequence. */
 }
 
+#ifdef CONFIG_PM_SLEEP
+static void tegra114_cpu_clock_suspend(void)
+{
+	/* switch coresite to clk_m, save off original source */
+	tegra114_cpu_clk_sctx.clk_csite_src =
+				readl(clk_base + CLK_SOURCE_CSITE);
+	writel(3 << 30, clk_base + CLK_SOURCE_CSITE);
+
+	tegra114_cpu_clk_sctx.cclkg_burst =
+				readl(clk_base + CCLKG_BURST_POLICY);
+	tegra114_cpu_clk_sctx.cclkg_divider =
+				readl(clk_base + CCLKG_BURST_POLICY + 4);
+}
+
+static void tegra114_cpu_clock_resume(void)
+{
+	writel(tegra114_cpu_clk_sctx.clk_csite_src,
+					clk_base + CLK_SOURCE_CSITE);
+
+	writel(tegra114_cpu_clk_sctx.cclkg_burst,
+					clk_base + CCLKG_BURST_POLICY);
+	writel(tegra114_cpu_clk_sctx.cclkg_divider,
+					clk_base + CCLKG_BURST_POLICY + 4);
+}
+#endif
+
 static struct tegra_cpu_car_ops tegra114_cpu_car_ops = {
 	.wait_for_reset	= tegra114_wait_cpu_in_reset,
 	.disable_clock	= tegra114_disable_cpu_clock,
+#ifdef CONFIG_PM_SLEEP
+	.suspend	= tegra114_cpu_clock_suspend,
+	.resume		= tegra114_cpu_clock_resume,
+#endif
 };
 
 static const struct of_device_id pmc_match[] __initconst = {
@@ -2156,7 +2206,7 @@ static const struct of_device_id pmc_match[] __initconst = {
  * dfll_soc/dfll_ref apparently must be kept enabled, otherwise I2C5
  * breaks
  */
-static __initdata struct tegra_clk_init_table init_table[] = {
+static struct tegra_clk_init_table init_table[] __initdata = {
 	{uarta, pll_p, 408000000, 0},
 	{uartb, pll_p, 408000000, 0},
 	{uartc, pll_p, 408000000, 0},
diff --git a/drivers/clk/tegra/clk-tegra20.c b/drivers/clk/tegra/clk-tegra20.c
index 759ca47be753..056f649d0d89 100644
--- a/drivers/clk/tegra/clk-tegra20.c
+++ b/drivers/clk/tegra/clk-tegra20.c
@@ -778,7 +778,8 @@ static void __init tegra20_audio_clk_init(void)
 
 	/* audio */
 	clk = clk_register_mux(NULL, "audio_mux", audio_parents,
-				ARRAY_SIZE(audio_parents), 0,
+				ARRAY_SIZE(audio_parents),
+				CLK_SET_RATE_NO_REPARENT,
 				clk_base + AUDIO_SYNC_CLK, 0, 3, 0, NULL);
 	clk = clk_register_gate(NULL, "audio", "audio_mux", 0,
 				clk_base + AUDIO_SYNC_CLK, 4,
@@ -941,7 +942,8 @@ static void __init tegra20_periph_clk_init(void)
 
 	/* emc */
 	clk = clk_register_mux(NULL, "emc_mux", mux_pllmcp_clkm,
-			       ARRAY_SIZE(mux_pllmcp_clkm), 0,
+			       ARRAY_SIZE(mux_pllmcp_clkm),
+			       CLK_SET_RATE_NO_REPARENT,
 			       clk_base + CLK_SOURCE_EMC,
 			       30, 2, 0, NULL);
 	clk = tegra_clk_register_periph_gate("emc", "emc_mux", 0, clk_base, 0,
@@ -1223,7 +1225,7 @@ static struct tegra_cpu_car_ops tegra20_cpu_car_ops = {
 #endif
 };
 
-static __initdata struct tegra_clk_init_table init_table[] = {
+static struct tegra_clk_init_table init_table[] __initdata = {
 	{pll_p, clk_max, 216000000, 1},
 	{pll_p_out1, clk_max, 28800000, 1},
 	{pll_p_out2, clk_max, 48000000, 1},
diff --git a/drivers/clk/tegra/clk-tegra30.c b/drivers/clk/tegra/clk-tegra30.c
index e2c6ca0431d6..dbe7c8003c5c 100644
--- a/drivers/clk/tegra/clk-tegra30.c
+++ b/drivers/clk/tegra/clk-tegra30.c
@@ -971,7 +971,7 @@ static void __init tegra30_pll_init(void)
 	/* PLLU */
 	clk = tegra_clk_register_pll("pll_u", "pll_ref", clk_base, pmc_base, 0,
 			    0, &pll_u_params, TEGRA_PLLU | TEGRA_PLL_HAS_CPCON |
-			    TEGRA_PLL_SET_LFCON | TEGRA_PLL_USE_LOCK,
+			    TEGRA_PLL_SET_LFCON,
 			    pll_u_freq_table,
 			    NULL);
 	clk_register_clkdev(clk, "pll_u", NULL);
@@ -1026,7 +1026,8 @@ static void __init tegra30_pll_init(void)
 
 	/* PLLE */
 	clk = clk_register_mux(NULL, "pll_e_mux", pll_e_parents,
-			       ARRAY_SIZE(pll_e_parents), 0,
+			       ARRAY_SIZE(pll_e_parents),
+			       CLK_SET_RATE_NO_REPARENT,
 			       clk_base + PLLE_AUX, 2, 1, 0, NULL);
 	clk = tegra_clk_register_plle("pll_e", "pll_e_mux", clk_base, pmc_base,
 			     CLK_GET_RATE_NOCACHE, 100000000, &pll_e_params,
@@ -1086,7 +1087,8 @@ static void __init tegra30_audio_clk_init(void)
 
 	/* audio0 */
 	clk = clk_register_mux(NULL, "audio0_mux", mux_audio_sync_clk,
-				ARRAY_SIZE(mux_audio_sync_clk), 0,
+				ARRAY_SIZE(mux_audio_sync_clk),
+				CLK_SET_RATE_NO_REPARENT,
 				clk_base + AUDIO_SYNC_CLK_I2S0, 0, 3, 0, NULL);
 	clk = clk_register_gate(NULL, "audio0", "audio0_mux", 0,
 				clk_base + AUDIO_SYNC_CLK_I2S0, 4,
@@ -1096,7 +1098,8 @@ static void __init tegra30_audio_clk_init(void)
 
 	/* audio1 */
 	clk = clk_register_mux(NULL, "audio1_mux", mux_audio_sync_clk,
-				ARRAY_SIZE(mux_audio_sync_clk), 0,
+				ARRAY_SIZE(mux_audio_sync_clk),
+				CLK_SET_RATE_NO_REPARENT,
 				clk_base + AUDIO_SYNC_CLK_I2S1, 0, 3, 0, NULL);
 	clk = clk_register_gate(NULL, "audio1", "audio1_mux", 0,
 				clk_base + AUDIO_SYNC_CLK_I2S1, 4,
@@ -1106,7 +1109,8 @@ static void __init tegra30_audio_clk_init(void)
 
 	/* audio2 */
 	clk = clk_register_mux(NULL, "audio2_mux", mux_audio_sync_clk,
-				ARRAY_SIZE(mux_audio_sync_clk), 0,
+				ARRAY_SIZE(mux_audio_sync_clk),
+				CLK_SET_RATE_NO_REPARENT,
 				clk_base + AUDIO_SYNC_CLK_I2S2, 0, 3, 0, NULL);
 	clk = clk_register_gate(NULL, "audio2", "audio2_mux", 0,
 				clk_base + AUDIO_SYNC_CLK_I2S2, 4,
@@ -1116,7 +1120,8 @@ static void __init tegra30_audio_clk_init(void)
 
 	/* audio3 */
 	clk = clk_register_mux(NULL, "audio3_mux", mux_audio_sync_clk,
-				ARRAY_SIZE(mux_audio_sync_clk), 0,
+				ARRAY_SIZE(mux_audio_sync_clk),
+				CLK_SET_RATE_NO_REPARENT,
 				clk_base + AUDIO_SYNC_CLK_I2S3, 0, 3, 0, NULL);
 	clk = clk_register_gate(NULL, "audio3", "audio3_mux", 0,
 				clk_base + AUDIO_SYNC_CLK_I2S3, 4,
@@ -1126,7 +1131,8 @@ static void __init tegra30_audio_clk_init(void)
 
 	/* audio4 */
 	clk = clk_register_mux(NULL, "audio4_mux", mux_audio_sync_clk,
-				ARRAY_SIZE(mux_audio_sync_clk), 0,
+				ARRAY_SIZE(mux_audio_sync_clk),
+				CLK_SET_RATE_NO_REPARENT,
 				clk_base + AUDIO_SYNC_CLK_I2S4, 0, 3, 0, NULL);
 	clk = clk_register_gate(NULL, "audio4", "audio4_mux", 0,
 				clk_base + AUDIO_SYNC_CLK_I2S4, 4,
@@ -1136,7 +1142,8 @@ static void __init tegra30_audio_clk_init(void)
 
 	/* spdif */
 	clk = clk_register_mux(NULL, "spdif_mux", mux_audio_sync_clk,
-				ARRAY_SIZE(mux_audio_sync_clk), 0,
+				ARRAY_SIZE(mux_audio_sync_clk),
+				CLK_SET_RATE_NO_REPARENT,
 				clk_base + AUDIO_SYNC_CLK_SPDIF, 0, 3, 0, NULL);
 	clk = clk_register_gate(NULL, "spdif", "spdif_mux", 0,
 				clk_base + AUDIO_SYNC_CLK_SPDIF, 4,
@@ -1229,7 +1236,8 @@ static void __init tegra30_pmc_clk_init(void)
 
 	/* clk_out_1 */
 	clk = clk_register_mux(NULL, "clk_out_1_mux", clk_out1_parents,
-			       ARRAY_SIZE(clk_out1_parents), 0,
+			       ARRAY_SIZE(clk_out1_parents),
+			       CLK_SET_RATE_NO_REPARENT,
 			       pmc_base + PMC_CLK_OUT_CNTRL, 6, 3, 0,
 			       &clk_out_lock);
 	clks[clk_out_1_mux] = clk;
@@ -1241,7 +1249,8 @@ static void __init tegra30_pmc_clk_init(void)
 
 	/* clk_out_2 */
 	clk = clk_register_mux(NULL, "clk_out_2_mux", clk_out2_parents,
-			       ARRAY_SIZE(clk_out2_parents), 0,
+			       ARRAY_SIZE(clk_out2_parents),
+			       CLK_SET_RATE_NO_REPARENT,
 			       pmc_base + PMC_CLK_OUT_CNTRL, 14, 3, 0,
 			       &clk_out_lock);
 	clk = clk_register_gate(NULL, "clk_out_2", "clk_out_2_mux", 0,
@@ -1252,7 +1261,8 @@ static void __init tegra30_pmc_clk_init(void)
 
 	/* clk_out_3 */
 	clk = clk_register_mux(NULL, "clk_out_3_mux", clk_out3_parents,
-			       ARRAY_SIZE(clk_out3_parents), 0,
+			       ARRAY_SIZE(clk_out3_parents),
+			       CLK_SET_RATE_NO_REPARENT,
 			       pmc_base + PMC_CLK_OUT_CNTRL, 22, 3, 0,
 			       &clk_out_lock);
 	clk = clk_register_gate(NULL, "clk_out_3", "clk_out_3_mux", 0,
@@ -1679,7 +1689,8 @@ static void __init tegra30_periph_clk_init(void)
 
 	/* emc */
 	clk = clk_register_mux(NULL, "emc_mux", mux_pllmcp_clkm,
-			       ARRAY_SIZE(mux_pllmcp_clkm), 0,
+			       ARRAY_SIZE(mux_pllmcp_clkm),
+			       CLK_SET_RATE_NO_REPARENT,
 			       clk_base + CLK_SOURCE_EMC,
 			       30, 2, 0, NULL);
 	clk = tegra_clk_register_periph_gate("emc", "emc_mux", 0, clk_base, 0,
@@ -1901,7 +1912,7 @@ static struct tegra_cpu_car_ops tegra30_cpu_car_ops = {
 #endif
 };
 
-static __initdata struct tegra_clk_init_table init_table[] = {
+static struct tegra_clk_init_table init_table[] __initdata = {
 	{uarta, pll_p, 408000000, 0},
 	{uartb, pll_p, 408000000, 0},
 	{uartc, pll_p, 408000000, 0},
diff --git a/drivers/clk/versatile/clk-vexpress.c b/drivers/clk/versatile/clk-vexpress.c
index a4a728d05092..2d5e1b4820e0 100644
--- a/drivers/clk/versatile/clk-vexpress.c
+++ b/drivers/clk/versatile/clk-vexpress.c
@@ -37,8 +37,8 @@ static void __init vexpress_sp810_init(void __iomem *base)
 		snprintf(name, ARRAY_SIZE(name), "timerclken%d", i);
 
 		vexpress_sp810_timerclken[i] = clk_register_mux(NULL, name,
-				parents, 2, 0, base + SCCTRL,
-				SCCTRL_TIMERENnSEL_SHIFT(i), 1,
+				parents, 2, CLK_SET_RATE_NO_REPARENT,
+				base + SCCTRL, SCCTRL_TIMERENnSEL_SHIFT(i), 1,
 				0, &vexpress_sp810_lock);
 
 		if (WARN_ON(IS_ERR(vexpress_sp810_timerclken[i])))
diff --git a/drivers/clk/zynq/clkc.c b/drivers/clk/zynq/clkc.c
index 089d3e30e221..cc40fe64f2dc 100644
--- a/drivers/clk/zynq/clkc.c
+++ b/drivers/clk/zynq/clkc.c
@@ -125,8 +125,9 @@ static void __init zynq_clk_register_fclk(enum zynq_clk fclk,
 	div0_name = kasprintf(GFP_KERNEL, "%s_div0", clk_name);
 	div1_name = kasprintf(GFP_KERNEL, "%s_div1", clk_name);
 
-	clk = clk_register_mux(NULL, mux_name, parents, 4, 0,
-			fclk_ctrl_reg, 4, 2, 0, fclk_lock);
+	clk = clk_register_mux(NULL, mux_name, parents, 4,
+			CLK_SET_RATE_NO_REPARENT, fclk_ctrl_reg, 4, 2, 0,
+			fclk_lock);
 
 	clk = clk_register_divider(NULL, div0_name, mux_name,
 			0, fclk_ctrl_reg, 8, 6, CLK_DIVIDER_ONE_BASED |
@@ -168,8 +169,8 @@ static void __init zynq_clk_register_periph_clk(enum zynq_clk clk0,
 	mux_name = kasprintf(GFP_KERNEL, "%s_mux", clk_name0);
 	div_name = kasprintf(GFP_KERNEL, "%s_div", clk_name0);
 
-	clk = clk_register_mux(NULL, mux_name, parents, 4, 0,
-			clk_ctrl, 4, 2, 0, lock);
+	clk = clk_register_mux(NULL, mux_name, parents, 4,
+			CLK_SET_RATE_NO_REPARENT, clk_ctrl, 4, 2, 0, lock);
 
 	clk = clk_register_divider(NULL, div_name, mux_name, 0, clk_ctrl, 8, 6,
 			CLK_DIVIDER_ONE_BASED | CLK_DIVIDER_ALLOW_ZERO, lock);
@@ -236,25 +237,26 @@ static void __init zynq_clk_setup(struct device_node *np)
 	clk = clk_register_zynq_pll("armpll_int", "ps_clk", SLCR_ARMPLL_CTRL,
 			SLCR_PLL_STATUS, 0, &armpll_lock);
 	clks[armpll] = clk_register_mux(NULL, clk_output_name[armpll],
-			armpll_parents, 2, 0, SLCR_ARMPLL_CTRL, 4, 1, 0,
-			&armpll_lock);
+			armpll_parents, 2, CLK_SET_RATE_NO_REPARENT,
+			SLCR_ARMPLL_CTRL, 4, 1, 0, &armpll_lock);
 
 	clk = clk_register_zynq_pll("ddrpll_int", "ps_clk", SLCR_DDRPLL_CTRL,
 			SLCR_PLL_STATUS, 1, &ddrpll_lock);
 	clks[ddrpll] = clk_register_mux(NULL, clk_output_name[ddrpll],
-			ddrpll_parents, 2, 0, SLCR_DDRPLL_CTRL, 4, 1, 0,
-			&ddrpll_lock);
+			ddrpll_parents, 2, CLK_SET_RATE_NO_REPARENT,
+			SLCR_DDRPLL_CTRL, 4, 1, 0, &ddrpll_lock);
 
 	clk = clk_register_zynq_pll("iopll_int", "ps_clk", SLCR_IOPLL_CTRL,
 			SLCR_PLL_STATUS, 2, &iopll_lock);
 	clks[iopll] = clk_register_mux(NULL, clk_output_name[iopll],
-			iopll_parents, 2, 0, SLCR_IOPLL_CTRL, 4, 1, 0,
-			&iopll_lock);
+			iopll_parents, 2, CLK_SET_RATE_NO_REPARENT,
+			SLCR_IOPLL_CTRL, 4, 1, 0, &iopll_lock);
 
 	/* CPU clocks */
 	tmp = readl(SLCR_621_TRUE) & 1;
-	clk = clk_register_mux(NULL, "cpu_mux", cpu_parents, 4, 0,
-			SLCR_ARM_CLK_CTRL, 4, 2, 0, &armclk_lock);
+	clk = clk_register_mux(NULL, "cpu_mux", cpu_parents, 4,
+			CLK_SET_RATE_NO_REPARENT, SLCR_ARM_CLK_CTRL, 4, 2, 0,
+			&armclk_lock);
 	clk = clk_register_divider(NULL, "cpu_div", "cpu_mux", 0,
 			SLCR_ARM_CLK_CTRL, 8, 6, CLK_DIVIDER_ONE_BASED |
 			CLK_DIVIDER_ALLOW_ZERO, &armclk_lock);
@@ -293,8 +295,9 @@ static void __init zynq_clk_setup(struct device_node *np)
 			swdt_ext_clk_mux_parents[i + 1] = dummy_nm;
 	}
 	clks[swdt] = clk_register_mux(NULL, clk_output_name[swdt],
-			swdt_ext_clk_mux_parents, 2, CLK_SET_RATE_PARENT,
-			SLCR_SWDT_CLK_SEL, 0, 1, 0, &swdtclk_lock);
+			swdt_ext_clk_mux_parents, 2, CLK_SET_RATE_PARENT |
+			CLK_SET_RATE_NO_REPARENT, SLCR_SWDT_CLK_SEL, 0, 1, 0,
+			&swdtclk_lock);
 
 	/* DDR clocks */
 	clk = clk_register_divider(NULL, "ddr2x_div", "ddrpll", 0,
@@ -356,8 +359,9 @@ static void __init zynq_clk_setup(struct device_node *np)
 			gem0_mux_parents[i + 1] = of_clk_get_parent_name(np,
 					idx);
 	}
-	clk = clk_register_mux(NULL, "gem0_mux", periph_parents, 4, 0,
-			SLCR_GEM0_CLK_CTRL, 4, 2, 0, &gem0clk_lock);
+	clk = clk_register_mux(NULL, "gem0_mux", periph_parents, 4,
+			CLK_SET_RATE_NO_REPARENT, SLCR_GEM0_CLK_CTRL, 4, 2, 0,
+			&gem0clk_lock);
 	clk = clk_register_divider(NULL, "gem0_div0", "gem0_mux", 0,
 			SLCR_GEM0_CLK_CTRL, 8, 6, CLK_DIVIDER_ONE_BASED |
 			CLK_DIVIDER_ALLOW_ZERO, &gem0clk_lock);
@@ -366,7 +370,8 @@ static void __init zynq_clk_setup(struct device_node *np)
 			CLK_DIVIDER_ONE_BASED | CLK_DIVIDER_ALLOW_ZERO,
 			&gem0clk_lock);
 	clk = clk_register_mux(NULL, "gem0_emio_mux", gem0_mux_parents, 2,
-			CLK_SET_RATE_PARENT, SLCR_GEM0_CLK_CTRL, 6, 1, 0,
+			CLK_SET_RATE_PARENT | CLK_SET_RATE_NO_REPARENT,
+			SLCR_GEM0_CLK_CTRL, 6, 1, 0,
 			&gem0clk_lock);
 	clks[gem0] = clk_register_gate(NULL, clk_output_name[gem0],
 			"gem0_emio_mux", CLK_SET_RATE_PARENT,
@@ -379,8 +384,9 @@ static void __init zynq_clk_setup(struct device_node *np)
 			gem1_mux_parents[i + 1] = of_clk_get_parent_name(np,
 					idx);
 	}
-	clk = clk_register_mux(NULL, "gem1_mux", periph_parents, 4, 0,
-			SLCR_GEM1_CLK_CTRL, 4, 2, 0, &gem1clk_lock);
+	clk = clk_register_mux(NULL, "gem1_mux", periph_parents, 4,
+			CLK_SET_RATE_NO_REPARENT, SLCR_GEM1_CLK_CTRL, 4, 2, 0,
+			&gem1clk_lock);
 	clk = clk_register_divider(NULL, "gem1_div0", "gem1_mux", 0,
 			SLCR_GEM1_CLK_CTRL, 8, 6, CLK_DIVIDER_ONE_BASED |
 			CLK_DIVIDER_ALLOW_ZERO, &gem1clk_lock);
@@ -389,7 +395,8 @@ static void __init zynq_clk_setup(struct device_node *np)
 			CLK_DIVIDER_ONE_BASED | CLK_DIVIDER_ALLOW_ZERO,
 			&gem1clk_lock);
 	clk = clk_register_mux(NULL, "gem1_emio_mux", gem1_mux_parents, 2,
-			CLK_SET_RATE_PARENT, SLCR_GEM1_CLK_CTRL, 6, 1, 0,
+			CLK_SET_RATE_PARENT | CLK_SET_RATE_NO_REPARENT,
+			SLCR_GEM1_CLK_CTRL, 6, 1, 0,
 			&gem1clk_lock);
 	clks[gem1] = clk_register_gate(NULL, clk_output_name[gem1],
 			"gem1_emio_mux", CLK_SET_RATE_PARENT,
@@ -409,8 +416,9 @@ static void __init zynq_clk_setup(struct device_node *np)
 			can_mio_mux_parents[i] = dummy_nm;
 	}
 	kfree(clk_name);
-	clk = clk_register_mux(NULL, "can_mux", periph_parents, 4, 0,
-			SLCR_CAN_CLK_CTRL, 4, 2, 0, &canclk_lock);
+	clk = clk_register_mux(NULL, "can_mux", periph_parents, 4,
+			CLK_SET_RATE_NO_REPARENT, SLCR_CAN_CLK_CTRL, 4, 2, 0,
+			&canclk_lock);
 	clk = clk_register_divider(NULL, "can_div0", "can_mux", 0,
 			SLCR_CAN_CLK_CTRL, 8, 6, CLK_DIVIDER_ONE_BASED |
 			CLK_DIVIDER_ALLOW_ZERO, &canclk_lock);
@@ -425,17 +433,21 @@ static void __init zynq_clk_setup(struct device_node *np)
 			CLK_SET_RATE_PARENT, SLCR_CAN_CLK_CTRL, 1, 0,
 			&canclk_lock);
 	clk = clk_register_mux(NULL, "can0_mio_mux",
-			can_mio_mux_parents, 54, CLK_SET_RATE_PARENT,
-			SLCR_CAN_MIOCLK_CTRL, 0, 6, 0, &canmioclk_lock);
+			can_mio_mux_parents, 54, CLK_SET_RATE_PARENT |
+			CLK_SET_RATE_NO_REPARENT, SLCR_CAN_MIOCLK_CTRL, 0, 6, 0,
+			&canmioclk_lock);
 	clk = clk_register_mux(NULL, "can1_mio_mux",
-			can_mio_mux_parents, 54, CLK_SET_RATE_PARENT,
-			SLCR_CAN_MIOCLK_CTRL, 16, 6, 0, &canmioclk_lock);
+			can_mio_mux_parents, 54, CLK_SET_RATE_PARENT |
+			CLK_SET_RATE_NO_REPARENT, SLCR_CAN_MIOCLK_CTRL, 16, 6,
+			0, &canmioclk_lock);
 	clks[can0] = clk_register_mux(NULL, clk_output_name[can0],
-			can0_mio_mux2_parents, 2, CLK_SET_RATE_PARENT,
-			SLCR_CAN_MIOCLK_CTRL, 6, 1, 0, &canmioclk_lock);
+			can0_mio_mux2_parents, 2, CLK_SET_RATE_PARENT |
+			CLK_SET_RATE_NO_REPARENT, SLCR_CAN_MIOCLK_CTRL, 6, 1, 0,
+			&canmioclk_lock);
 	clks[can1] = clk_register_mux(NULL, clk_output_name[can1],
-			can1_mio_mux2_parents, 2, CLK_SET_RATE_PARENT,
-			SLCR_CAN_MIOCLK_CTRL, 22, 1, 0, &canmioclk_lock);
+			can1_mio_mux2_parents, 2, CLK_SET_RATE_PARENT |
+			CLK_SET_RATE_NO_REPARENT, SLCR_CAN_MIOCLK_CTRL, 22, 1,
+			0, &canmioclk_lock);
 
 	for (i = 0; i < ARRAY_SIZE(dbgtrc_emio_input_names); i++) {
 		int idx = of_property_match_string(np, "clock-names",
@@ -444,13 +456,15 @@ static void __init zynq_clk_setup(struct device_node *np)
 			dbg_emio_mux_parents[i + 1] = of_clk_get_parent_name(np,
 					idx);
 	}
-	clk = clk_register_mux(NULL, "dbg_mux", periph_parents, 4, 0,
-			SLCR_DBG_CLK_CTRL, 4, 2, 0, &dbgclk_lock);
+	clk = clk_register_mux(NULL, "dbg_mux", periph_parents, 4,
+			CLK_SET_RATE_NO_REPARENT, SLCR_DBG_CLK_CTRL, 4, 2, 0,
+			&dbgclk_lock);
 	clk = clk_register_divider(NULL, "dbg_div", "dbg_mux", 0,
 			SLCR_DBG_CLK_CTRL, 8, 6, CLK_DIVIDER_ONE_BASED |
 			CLK_DIVIDER_ALLOW_ZERO, &dbgclk_lock);
-	clk = clk_register_mux(NULL, "dbg_emio_mux", dbg_emio_mux_parents, 2, 0,
-			SLCR_DBG_CLK_CTRL, 6, 1, 0, &dbgclk_lock);
+	clk = clk_register_mux(NULL, "dbg_emio_mux", dbg_emio_mux_parents, 2,
+			CLK_SET_RATE_NO_REPARENT, SLCR_DBG_CLK_CTRL, 6, 1, 0,
+			&dbgclk_lock);
 	clks[dbg_trc] = clk_register_gate(NULL, clk_output_name[dbg_trc],
 			"dbg_emio_mux", CLK_SET_RATE_PARENT, SLCR_DBG_CLK_CTRL,
 			0, 0, &dbgclk_lock);
diff --git a/drivers/clk/zynq/pll.c b/drivers/clk/zynq/pll.c
index 47e307c25a7b..3226f54fa595 100644
--- a/drivers/clk/zynq/pll.c
+++ b/drivers/clk/zynq/pll.c
@@ -50,6 +50,9 @@ struct zynq_pll {
 #define PLLCTRL_RESET_MASK	1
 #define PLLCTRL_RESET_SHIFT	0
 
+#define PLL_FBDIV_MIN	13
+#define PLL_FBDIV_MAX	66
+
 /**
  * zynq_pll_round_rate() - Round a clock frequency
  * @hw:		Handle between common and hardware-specific interfaces
@@ -63,10 +66,10 @@ static long zynq_pll_round_rate(struct clk_hw *hw, unsigned long rate,
 	u32 fbdiv;
 
 	fbdiv = DIV_ROUND_CLOSEST(rate, *prate);
-	if (fbdiv < 13)
-		fbdiv = 13;
-	else if (fbdiv > 66)
-		fbdiv = 66;
+	if (fbdiv < PLL_FBDIV_MIN)
+		fbdiv = PLL_FBDIV_MIN;
+	else if (fbdiv > PLL_FBDIV_MAX)
+		fbdiv = PLL_FBDIV_MAX;
 
 	return *prate * fbdiv;
 }
@@ -182,7 +185,13 @@ static const struct clk_ops zynq_pll_ops = {
 
 /**
  * clk_register_zynq_pll() - Register PLL with the clock framework
- * @np	Pointer to the DT device node
+ * @name	PLL name
+ * @parent	Parent clock name
+ * @pll_ctrl	Pointer to PLL control register
+ * @pll_status	Pointer to PLL status register
+ * @lock_index	Bit index to this PLL's lock status bit in @pll_status
+ * @lock	Register lock
+ * Returns handle to the registered clock.
  */
 struct clk *clk_register_zynq_pll(const char *name, const char *parent,
 		void __iomem *pll_ctrl, void __iomem *pll_status, u8 lock_index,
diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig
index b7b9b040a89b..971d796e071d 100644
--- a/drivers/clocksource/Kconfig
+++ b/drivers/clocksource/Kconfig
@@ -26,6 +26,7 @@ config DW_APB_TIMER_OF
 
 config ARMADA_370_XP_TIMER
 	bool
+	select CLKSRC_OF
 
 config ORION_TIMER
 	select CLKSRC_OF
@@ -99,7 +100,6 @@ config CLKSRC_EXYNOS_MCT
 
 config CLKSRC_SAMSUNG_PWM
 	bool
-	select CLKSRC_MMIO
 	help
 	  This is a new clocksource driver for the PWM timer found in
 	  Samsung S3C, S5P and Exynos SoCs, replacing an earlier driver
diff --git a/drivers/clocksource/Makefile b/drivers/clocksource/Makefile
index 8b00c5cebfa4..704d6d342adc 100644
--- a/drivers/clocksource/Makefile
+++ b/drivers/clocksource/Makefile
@@ -18,6 +18,7 @@ obj-$(CONFIG_ARMADA_370_XP_TIMER)	+= time-armada-370-xp.o
 obj-$(CONFIG_ORION_TIMER)	+= time-orion.o
 obj-$(CONFIG_ARCH_BCM2835)	+= bcm2835_timer.o
 obj-$(CONFIG_ARCH_MARCO)	+= timer-marco.o
+obj-$(CONFIG_ARCH_MOXART)	+= moxart_timer.o
 obj-$(CONFIG_ARCH_MXS)		+= mxs_timer.o
 obj-$(CONFIG_ARCH_PRIMA2)	+= timer-prima2.o
 obj-$(CONFIG_SUN4I_TIMER)	+= sun4i_timer.o
diff --git a/drivers/clocksource/acpi_pm.c b/drivers/clocksource/acpi_pm.c
index 6efe4d1ab3aa..6eab88985670 100644
--- a/drivers/clocksource/acpi_pm.c
+++ b/drivers/clocksource/acpi_pm.c
@@ -200,14 +200,14 @@ static int __init init_acpi_pm_clocksource(void)
 			if ((value2 < value1) && ((value2) < 0xFFF))
 				break;
 			printk(KERN_INFO "PM-Timer had inconsistent results:"
-			       " 0x%#llx, 0x%#llx - aborting.\n",
+			       " %#llx, %#llx - aborting.\n",
 			       value1, value2);
 			pmtmr_ioport = 0;
 			return -EINVAL;
 		}
 		if (i == ACPI_PM_READ_CHECKS) {
 			printk(KERN_INFO "PM-Timer failed consistency check "
-			       " (0x%#llx) - aborting.\n", value1);
+			       " (%#llx) - aborting.\n", value1);
 			pmtmr_ioport = 0;
 			return -ENODEV;
 		}
diff --git a/drivers/clocksource/arm_arch_timer.c b/drivers/clocksource/arm_arch_timer.c
index ffadd836e0b5..fbd9ccd5e114 100644
--- a/drivers/clocksource/arm_arch_timer.c
+++ b/drivers/clocksource/arm_arch_timer.c
@@ -16,13 +16,39 @@
 #include <linux/clockchips.h>
 #include <linux/interrupt.h>
 #include <linux/of_irq.h>
+#include <linux/of_address.h>
 #include <linux/io.h>
+#include <linux/slab.h>
 
 #include <asm/arch_timer.h>
 #include <asm/virt.h>
 
 #include <clocksource/arm_arch_timer.h>
 
+#define CNTTIDR		0x08
+#define CNTTIDR_VIRT(n)	(BIT(1) << ((n) * 4))
+
+#define CNTVCT_LO	0x08
+#define CNTVCT_HI	0x0c
+#define CNTFRQ		0x10
+#define CNTP_TVAL	0x28
+#define CNTP_CTL	0x2c
+#define CNTV_TVAL	0x38
+#define CNTV_CTL	0x3c
+
+#define ARCH_CP15_TIMER	BIT(0)
+#define ARCH_MEM_TIMER	BIT(1)
+static unsigned arch_timers_present __initdata;
+
+static void __iomem *arch_counter_base;
+
+struct arch_timer {
+	void __iomem *base;
+	struct clock_event_device evt;
+};
+
+#define to_arch_timer(e) container_of(e, struct arch_timer, evt)
+
 static u32 arch_timer_rate;
 
 enum ppi_nr {
@@ -38,19 +64,83 @@ static int arch_timer_ppi[MAX_TIMER_PPI];
 static struct clock_event_device __percpu *arch_timer_evt;
 
 static bool arch_timer_use_virtual = true;
+static bool arch_timer_mem_use_virtual;
 
 /*
  * Architected system timer support.
  */
 
-static inline irqreturn_t timer_handler(const int access,
+static __always_inline
+void arch_timer_reg_write(int access, enum arch_timer_reg reg, u32 val,
+			  struct clock_event_device *clk)
+{
+	if (access == ARCH_TIMER_MEM_PHYS_ACCESS) {
+		struct arch_timer *timer = to_arch_timer(clk);
+		switch (reg) {
+		case ARCH_TIMER_REG_CTRL:
+			writel_relaxed(val, timer->base + CNTP_CTL);
+			break;
+		case ARCH_TIMER_REG_TVAL:
+			writel_relaxed(val, timer->base + CNTP_TVAL);
+			break;
+		}
+	} else if (access == ARCH_TIMER_MEM_VIRT_ACCESS) {
+		struct arch_timer *timer = to_arch_timer(clk);
+		switch (reg) {
+		case ARCH_TIMER_REG_CTRL:
+			writel_relaxed(val, timer->base + CNTV_CTL);
+			break;
+		case ARCH_TIMER_REG_TVAL:
+			writel_relaxed(val, timer->base + CNTV_TVAL);
+			break;
+		}
+	} else {
+		arch_timer_reg_write_cp15(access, reg, val);
+	}
+}
+
+static __always_inline
+u32 arch_timer_reg_read(int access, enum arch_timer_reg reg,
+			struct clock_event_device *clk)
+{
+	u32 val;
+
+	if (access == ARCH_TIMER_MEM_PHYS_ACCESS) {
+		struct arch_timer *timer = to_arch_timer(clk);
+		switch (reg) {
+		case ARCH_TIMER_REG_CTRL:
+			val = readl_relaxed(timer->base + CNTP_CTL);
+			break;
+		case ARCH_TIMER_REG_TVAL:
+			val = readl_relaxed(timer->base + CNTP_TVAL);
+			break;
+		}
+	} else if (access == ARCH_TIMER_MEM_VIRT_ACCESS) {
+		struct arch_timer *timer = to_arch_timer(clk);
+		switch (reg) {
+		case ARCH_TIMER_REG_CTRL:
+			val = readl_relaxed(timer->base + CNTV_CTL);
+			break;
+		case ARCH_TIMER_REG_TVAL:
+			val = readl_relaxed(timer->base + CNTV_TVAL);
+			break;
+		}
+	} else {
+		val = arch_timer_reg_read_cp15(access, reg);
+	}
+
+	return val;
+}
+
+static __always_inline irqreturn_t timer_handler(const int access,
 					struct clock_event_device *evt)
 {
 	unsigned long ctrl;
-	ctrl = arch_timer_reg_read(access, ARCH_TIMER_REG_CTRL);
+
+	ctrl = arch_timer_reg_read(access, ARCH_TIMER_REG_CTRL, evt);
 	if (ctrl & ARCH_TIMER_CTRL_IT_STAT) {
 		ctrl |= ARCH_TIMER_CTRL_IT_MASK;
-		arch_timer_reg_write(access, ARCH_TIMER_REG_CTRL, ctrl);
+		arch_timer_reg_write(access, ARCH_TIMER_REG_CTRL, ctrl, evt);
 		evt->event_handler(evt);
 		return IRQ_HANDLED;
 	}
@@ -72,15 +162,30 @@ static irqreturn_t arch_timer_handler_phys(int irq, void *dev_id)
 	return timer_handler(ARCH_TIMER_PHYS_ACCESS, evt);
 }
 
-static inline void timer_set_mode(const int access, int mode)
+static irqreturn_t arch_timer_handler_phys_mem(int irq, void *dev_id)
+{
+	struct clock_event_device *evt = dev_id;
+
+	return timer_handler(ARCH_TIMER_MEM_PHYS_ACCESS, evt);
+}
+
+static irqreturn_t arch_timer_handler_virt_mem(int irq, void *dev_id)
+{
+	struct clock_event_device *evt = dev_id;
+
+	return timer_handler(ARCH_TIMER_MEM_VIRT_ACCESS, evt);
+}
+
+static __always_inline void timer_set_mode(const int access, int mode,
+				  struct clock_event_device *clk)
 {
 	unsigned long ctrl;
 	switch (mode) {
 	case CLOCK_EVT_MODE_UNUSED:
 	case CLOCK_EVT_MODE_SHUTDOWN:
-		ctrl = arch_timer_reg_read(access, ARCH_TIMER_REG_CTRL);
+		ctrl = arch_timer_reg_read(access, ARCH_TIMER_REG_CTRL, clk);
 		ctrl &= ~ARCH_TIMER_CTRL_ENABLE;
-		arch_timer_reg_write(access, ARCH_TIMER_REG_CTRL, ctrl);
+		arch_timer_reg_write(access, ARCH_TIMER_REG_CTRL, ctrl, clk);
 		break;
 	default:
 		break;
@@ -90,60 +195,108 @@ static inline void timer_set_mode(const int access, int mode)
 static void arch_timer_set_mode_virt(enum clock_event_mode mode,
 				     struct clock_event_device *clk)
 {
-	timer_set_mode(ARCH_TIMER_VIRT_ACCESS, mode);
+	timer_set_mode(ARCH_TIMER_VIRT_ACCESS, mode, clk);
 }
 
 static void arch_timer_set_mode_phys(enum clock_event_mode mode,
 				     struct clock_event_device *clk)
 {
-	timer_set_mode(ARCH_TIMER_PHYS_ACCESS, mode);
+	timer_set_mode(ARCH_TIMER_PHYS_ACCESS, mode, clk);
+}
+
+static void arch_timer_set_mode_virt_mem(enum clock_event_mode mode,
+					 struct clock_event_device *clk)
+{
+	timer_set_mode(ARCH_TIMER_MEM_VIRT_ACCESS, mode, clk);
 }
 
-static inline void set_next_event(const int access, unsigned long evt)
+static void arch_timer_set_mode_phys_mem(enum clock_event_mode mode,
+					 struct clock_event_device *clk)
+{
+	timer_set_mode(ARCH_TIMER_MEM_PHYS_ACCESS, mode, clk);
+}
+
+static __always_inline void set_next_event(const int access, unsigned long evt,
+					   struct clock_event_device *clk)
 {
 	unsigned long ctrl;
-	ctrl = arch_timer_reg_read(access, ARCH_TIMER_REG_CTRL);
+	ctrl = arch_timer_reg_read(access, ARCH_TIMER_REG_CTRL, clk);
 	ctrl |= ARCH_TIMER_CTRL_ENABLE;
 	ctrl &= ~ARCH_TIMER_CTRL_IT_MASK;
-	arch_timer_reg_write(access, ARCH_TIMER_REG_TVAL, evt);
-	arch_timer_reg_write(access, ARCH_TIMER_REG_CTRL, ctrl);
+	arch_timer_reg_write(access, ARCH_TIMER_REG_TVAL, evt, clk);
+	arch_timer_reg_write(access, ARCH_TIMER_REG_CTRL, ctrl, clk);
 }
 
 static int arch_timer_set_next_event_virt(unsigned long evt,
-					  struct clock_event_device *unused)
+					  struct clock_event_device *clk)
 {
-	set_next_event(ARCH_TIMER_VIRT_ACCESS, evt);
+	set_next_event(ARCH_TIMER_VIRT_ACCESS, evt, clk);
 	return 0;
 }
 
 static int arch_timer_set_next_event_phys(unsigned long evt,
-					  struct clock_event_device *unused)
+					  struct clock_event_device *clk)
 {
-	set_next_event(ARCH_TIMER_PHYS_ACCESS, evt);
+	set_next_event(ARCH_TIMER_PHYS_ACCESS, evt, clk);
 	return 0;
 }
 
-static int arch_timer_setup(struct clock_event_device *clk)
+static int arch_timer_set_next_event_virt_mem(unsigned long evt,
+					      struct clock_event_device *clk)
 {
-	clk->features = CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_FEAT_C3STOP;
-	clk->name = "arch_sys_timer";
-	clk->rating = 450;
-	if (arch_timer_use_virtual) {
-		clk->irq = arch_timer_ppi[VIRT_PPI];
-		clk->set_mode = arch_timer_set_mode_virt;
-		clk->set_next_event = arch_timer_set_next_event_virt;
+	set_next_event(ARCH_TIMER_MEM_VIRT_ACCESS, evt, clk);
+	return 0;
+}
+
+static int arch_timer_set_next_event_phys_mem(unsigned long evt,
+					      struct clock_event_device *clk)
+{
+	set_next_event(ARCH_TIMER_MEM_PHYS_ACCESS, evt, clk);
+	return 0;
+}
+
+static void __arch_timer_setup(unsigned type,
+			       struct clock_event_device *clk)
+{
+	clk->features = CLOCK_EVT_FEAT_ONESHOT;
+
+	if (type == ARCH_CP15_TIMER) {
+		clk->features |= CLOCK_EVT_FEAT_C3STOP;
+		clk->name = "arch_sys_timer";
+		clk->rating = 450;
+		clk->cpumask = cpumask_of(smp_processor_id());
+		if (arch_timer_use_virtual) {
+			clk->irq = arch_timer_ppi[VIRT_PPI];
+			clk->set_mode = arch_timer_set_mode_virt;
+			clk->set_next_event = arch_timer_set_next_event_virt;
+		} else {
+			clk->irq = arch_timer_ppi[PHYS_SECURE_PPI];
+			clk->set_mode = arch_timer_set_mode_phys;
+			clk->set_next_event = arch_timer_set_next_event_phys;
+		}
 	} else {
-		clk->irq = arch_timer_ppi[PHYS_SECURE_PPI];
-		clk->set_mode = arch_timer_set_mode_phys;
-		clk->set_next_event = arch_timer_set_next_event_phys;
+		clk->name = "arch_mem_timer";
+		clk->rating = 400;
+		clk->cpumask = cpu_all_mask;
+		if (arch_timer_mem_use_virtual) {
+			clk->set_mode = arch_timer_set_mode_virt_mem;
+			clk->set_next_event =
+				arch_timer_set_next_event_virt_mem;
+		} else {
+			clk->set_mode = arch_timer_set_mode_phys_mem;
+			clk->set_next_event =
+				arch_timer_set_next_event_phys_mem;
+		}
 	}
 
-	clk->cpumask = cpumask_of(smp_processor_id());
+	clk->set_mode(CLOCK_EVT_MODE_SHUTDOWN, clk);
 
-	clk->set_mode(CLOCK_EVT_MODE_SHUTDOWN, NULL);
+	clockevents_config_and_register(clk, arch_timer_rate, 0xf, 0x7fffffff);
+}
 
-	clockevents_config_and_register(clk, arch_timer_rate,
-					0xf, 0x7fffffff);
+static int arch_timer_setup(struct clock_event_device *clk)
+{
+	__arch_timer_setup(ARCH_CP15_TIMER, clk);
 
 	if (arch_timer_use_virtual)
 		enable_percpu_irq(arch_timer_ppi[VIRT_PPI], 0);
@@ -158,27 +311,41 @@ static int arch_timer_setup(struct clock_event_device *clk)
 	return 0;
 }
 
-static int arch_timer_available(void)
+static void
+arch_timer_detect_rate(void __iomem *cntbase, struct device_node *np)
 {
-	u32 freq;
-
-	if (arch_timer_rate == 0) {
-		freq = arch_timer_get_cntfrq();
-
-		/* Check the timer frequency. */
-		if (freq == 0) {
-			pr_warn("Architected timer frequency not available\n");
-			return -EINVAL;
-		}
+	/* Who has more than one independent system counter? */
+	if (arch_timer_rate)
+		return;
 
-		arch_timer_rate = freq;
+	/* Try to determine the frequency from the device tree or CNTFRQ */
+	if (of_property_read_u32(np, "clock-frequency", &arch_timer_rate)) {
+		if (cntbase)
+			arch_timer_rate = readl_relaxed(cntbase + CNTFRQ);
+		else
+			arch_timer_rate = arch_timer_get_cntfrq();
 	}
 
-	pr_info_once("Architected local timer running at %lu.%02luMHz (%s).\n",
+	/* Check the timer frequency. */
+	if (arch_timer_rate == 0)
+		pr_warn("Architected timer frequency not available\n");
+}
+
+static void arch_timer_banner(unsigned type)
+{
+	pr_info("Architected %s%s%s timer(s) running at %lu.%02luMHz (%s%s%s).\n",
+		     type & ARCH_CP15_TIMER ? "cp15" : "",
+		     type == (ARCH_CP15_TIMER | ARCH_MEM_TIMER) ?  " and " : "",
+		     type & ARCH_MEM_TIMER ? "mmio" : "",
 		     (unsigned long)arch_timer_rate / 1000000,
 		     (unsigned long)(arch_timer_rate / 10000) % 100,
-		     arch_timer_use_virtual ? "virt" : "phys");
-	return 0;
+		     type & ARCH_CP15_TIMER ?
+			arch_timer_use_virtual ? "virt" : "phys" :
+			"",
+		     type == (ARCH_CP15_TIMER | ARCH_MEM_TIMER) ?  "/" : "",
+		     type & ARCH_MEM_TIMER ?
+			arch_timer_mem_use_virtual ? "virt" : "phys" :
+			"");
 }
 
 u32 arch_timer_get_rate(void)
@@ -186,19 +353,35 @@ u32 arch_timer_get_rate(void)
 	return arch_timer_rate;
 }
 
-u64 arch_timer_read_counter(void)
+static u64 arch_counter_get_cntvct_mem(void)
 {
-	return arch_counter_get_cntvct();
+	u32 vct_lo, vct_hi, tmp_hi;
+
+	do {
+		vct_hi = readl_relaxed(arch_counter_base + CNTVCT_HI);
+		vct_lo = readl_relaxed(arch_counter_base + CNTVCT_LO);
+		tmp_hi = readl_relaxed(arch_counter_base + CNTVCT_HI);
+	} while (vct_hi != tmp_hi);
+
+	return ((u64) vct_hi << 32) | vct_lo;
 }
 
+/*
+ * Default to cp15 based access because arm64 uses this function for
+ * sched_clock() before DT is probed and the cp15 method is guaranteed
+ * to exist on arm64. arm doesn't use this before DT is probed so even
+ * if we don't have the cp15 accessors we won't have a problem.
+ */
+u64 (*arch_timer_read_counter)(void) = arch_counter_get_cntvct;
+
 static cycle_t arch_counter_read(struct clocksource *cs)
 {
-	return arch_counter_get_cntvct();
+	return arch_timer_read_counter();
 }
 
 static cycle_t arch_counter_read_cc(const struct cyclecounter *cc)
 {
-	return arch_counter_get_cntvct();
+	return arch_timer_read_counter();
 }
 
 static struct clocksource clocksource_counter = {
@@ -221,6 +404,23 @@ struct timecounter *arch_timer_get_timecounter(void)
 	return &timecounter;
 }
 
+static void __init arch_counter_register(unsigned type)
+{
+	u64 start_count;
+
+	/* Register the CP15 based counter if we have one */
+	if (type & ARCH_CP15_TIMER)
+		arch_timer_read_counter = arch_counter_get_cntvct;
+	else
+		arch_timer_read_counter = arch_counter_get_cntvct_mem;
+
+	start_count = arch_timer_read_counter();
+	clocksource_register_hz(&clocksource_counter, arch_timer_rate);
+	cyclecounter.mult = clocksource_counter.mult;
+	cyclecounter.shift = clocksource_counter.shift;
+	timecounter_init(&timecounter, &cyclecounter, start_count);
+}
+
 static void arch_timer_stop(struct clock_event_device *clk)
 {
 	pr_debug("arch_timer_teardown disable IRQ%d cpu #%d\n",
@@ -265,22 +465,12 @@ static int __init arch_timer_register(void)
 	int err;
 	int ppi;
 
-	err = arch_timer_available();
-	if (err)
-		goto out;
-
 	arch_timer_evt = alloc_percpu(struct clock_event_device);
 	if (!arch_timer_evt) {
 		err = -ENOMEM;
 		goto out;
 	}
 
-	clocksource_register_hz(&clocksource_counter, arch_timer_rate);
-	cyclecounter.mult = clocksource_counter.mult;
-	cyclecounter.shift = clocksource_counter.shift;
-	timecounter_init(&timecounter, &cyclecounter,
-			 arch_counter_get_cntvct());
-
 	if (arch_timer_use_virtual) {
 		ppi = arch_timer_ppi[VIRT_PPI];
 		err = request_percpu_irq(ppi, arch_timer_handler_virt,
@@ -331,24 +521,77 @@ out:
 	return err;
 }
 
+static int __init arch_timer_mem_register(void __iomem *base, unsigned int irq)
+{
+	int ret;
+	irq_handler_t func;
+	struct arch_timer *t;
+
+	t = kzalloc(sizeof(*t), GFP_KERNEL);
+	if (!t)
+		return -ENOMEM;
+
+	t->base = base;
+	t->evt.irq = irq;
+	__arch_timer_setup(ARCH_MEM_TIMER, &t->evt);
+
+	if (arch_timer_mem_use_virtual)
+		func = arch_timer_handler_virt_mem;
+	else
+		func = arch_timer_handler_phys_mem;
+
+	ret = request_irq(irq, func, IRQF_TIMER, "arch_mem_timer", &t->evt);
+	if (ret) {
+		pr_err("arch_timer: Failed to request mem timer irq\n");
+		kfree(t);
+	}
+
+	return ret;
+}
+
+static const struct of_device_id arch_timer_of_match[] __initconst = {
+	{ .compatible   = "arm,armv7-timer",    },
+	{ .compatible   = "arm,armv8-timer",    },
+	{},
+};
+
+static const struct of_device_id arch_timer_mem_of_match[] __initconst = {
+	{ .compatible   = "arm,armv7-timer-mem", },
+	{},
+};
+
+static void __init arch_timer_common_init(void)
+{
+	unsigned mask = ARCH_CP15_TIMER | ARCH_MEM_TIMER;
+
+	/* Wait until both nodes are probed if we have two timers */
+	if ((arch_timers_present & mask) != mask) {
+		if (of_find_matching_node(NULL, arch_timer_mem_of_match) &&
+				!(arch_timers_present & ARCH_MEM_TIMER))
+			return;
+		if (of_find_matching_node(NULL, arch_timer_of_match) &&
+				!(arch_timers_present & ARCH_CP15_TIMER))
+			return;
+	}
+
+	arch_timer_banner(arch_timers_present);
+	arch_counter_register(arch_timers_present);
+	arch_timer_arch_init();
+}
+
 static void __init arch_timer_init(struct device_node *np)
 {
-	u32 freq;
 	int i;
 
-	if (arch_timer_get_rate()) {
+	if (arch_timers_present & ARCH_CP15_TIMER) {
 		pr_warn("arch_timer: multiple nodes in dt, skipping\n");
 		return;
 	}
 
-	/* Try to determine the frequency from the device tree or CNTFRQ */
-	if (!of_property_read_u32(np, "clock-frequency", &freq))
-		arch_timer_rate = freq;
-
+	arch_timers_present |= ARCH_CP15_TIMER;
 	for (i = PHYS_SECURE_PPI; i < MAX_TIMER_PPI; i++)
 		arch_timer_ppi[i] = irq_of_parse_and_map(np, i);
-
-	of_node_put(np);
+	arch_timer_detect_rate(NULL, np);
 
 	/*
 	 * If HYP mode is available, we know that the physical timer
@@ -369,7 +612,73 @@ static void __init arch_timer_init(struct device_node *np)
 	}
 
 	arch_timer_register();
-	arch_timer_arch_init();
+	arch_timer_common_init();
 }
 CLOCKSOURCE_OF_DECLARE(armv7_arch_timer, "arm,armv7-timer", arch_timer_init);
 CLOCKSOURCE_OF_DECLARE(armv8_arch_timer, "arm,armv8-timer", arch_timer_init);
+
+static void __init arch_timer_mem_init(struct device_node *np)
+{
+	struct device_node *frame, *best_frame = NULL;
+	void __iomem *cntctlbase, *base;
+	unsigned int irq;
+	u32 cnttidr;
+
+	arch_timers_present |= ARCH_MEM_TIMER;
+	cntctlbase = of_iomap(np, 0);
+	if (!cntctlbase) {
+		pr_err("arch_timer: Can't find CNTCTLBase\n");
+		return;
+	}
+
+	cnttidr = readl_relaxed(cntctlbase + CNTTIDR);
+	iounmap(cntctlbase);
+
+	/*
+	 * Try to find a virtual capable frame. Otherwise fall back to a
+	 * physical capable frame.
+	 */
+	for_each_available_child_of_node(np, frame) {
+		int n;
+
+		if (of_property_read_u32(frame, "frame-number", &n)) {
+			pr_err("arch_timer: Missing frame-number\n");
+			of_node_put(best_frame);
+			of_node_put(frame);
+			return;
+		}
+
+		if (cnttidr & CNTTIDR_VIRT(n)) {
+			of_node_put(best_frame);
+			best_frame = frame;
+			arch_timer_mem_use_virtual = true;
+			break;
+		}
+		of_node_put(best_frame);
+		best_frame = of_node_get(frame);
+	}
+
+	base = arch_counter_base = of_iomap(best_frame, 0);
+	if (!base) {
+		pr_err("arch_timer: Can't map frame's registers\n");
+		of_node_put(best_frame);
+		return;
+	}
+
+	if (arch_timer_mem_use_virtual)
+		irq = irq_of_parse_and_map(best_frame, 1);
+	else
+		irq = irq_of_parse_and_map(best_frame, 0);
+	of_node_put(best_frame);
+	if (!irq) {
+		pr_err("arch_timer: Frame missing %s irq",
+		       arch_timer_mem_use_virtual ? "virt" : "phys");
+		return;
+	}
+
+	arch_timer_detect_rate(base, np);
+	arch_timer_mem_register(base, irq);
+	arch_timer_common_init();
+}
+CLOCKSOURCE_OF_DECLARE(armv7_arch_timer_mem, "arm,armv7-timer-mem",
+		       arch_timer_mem_init);
diff --git a/drivers/clocksource/bcm_kona_timer.c b/drivers/clocksource/bcm_kona_timer.c
index ba3d85904c9a..0d7d8c3ed6b2 100644
--- a/drivers/clocksource/bcm_kona_timer.c
+++ b/drivers/clocksource/bcm_kona_timer.c
@@ -99,7 +99,8 @@ kona_timer_get_counter(void *timer_base, uint32_t *msw, uint32_t *lsw)
 }
 
 static const struct of_device_id bcm_timer_ids[] __initconst = {
-	{.compatible = "bcm,kona-timer"},
+	{.compatible = "brcm,kona-timer"},
+	{.compatible = "bcm,kona-timer"}, /* deprecated name */
 	{},
 };
 
@@ -201,4 +202,9 @@ static void __init kona_timer_init(struct device_node *node)
 	kona_timer_set_next_event((arch_timer_rate / HZ), NULL);
 }
 
+CLOCKSOURCE_OF_DECLARE(brcm_kona, "brcm,kona-timer", kona_timer_init);
+/*
+ * bcm,kona-timer is deprecated by brcm,kona-timer
+ * being kept here for driver compatibility
+ */
 CLOCKSOURCE_OF_DECLARE(bcm_kona, "bcm,kona-timer", kona_timer_init);
diff --git a/drivers/clocksource/cadence_ttc_timer.c b/drivers/clocksource/cadence_ttc_timer.c
index 4cbe28c74631..b2bb3a4bc205 100644
--- a/drivers/clocksource/cadence_ttc_timer.c
+++ b/drivers/clocksource/cadence_ttc_timer.c
@@ -21,7 +21,7 @@
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
 #include <linux/slab.h>
-#include <linux/clk-provider.h>
+#include <linux/sched_clock.h>
 
 /*
  * This driver configures the 2 16-bit count-up timers as follows:
@@ -95,6 +95,8 @@ struct ttc_timer_clockevent {
 #define to_ttc_timer_clkevent(x) \
 		container_of(x, struct ttc_timer_clockevent, ce)
 
+static void __iomem *ttc_sched_clock_val_reg;
+
 /**
  * ttc_set_interval - Set the timer interval value
  *
@@ -156,6 +158,11 @@ static cycle_t __ttc_clocksource_read(struct clocksource *cs)
 				TTC_COUNT_VAL_OFFSET);
 }
 
+static u32 notrace ttc_sched_clock_read(void)
+{
+	return __raw_readl(ttc_sched_clock_val_reg);
+}
+
 /**
  * ttc_set_next_event - Sets the time interval for next event
  *
@@ -297,6 +304,10 @@ static void __init ttc_setup_clocksource(struct clk *clk, void __iomem *base)
 		kfree(ttccs);
 		return;
 	}
+
+	ttc_sched_clock_val_reg = base + TTC_COUNT_VAL_OFFSET;
+	setup_sched_clock(ttc_sched_clock_read, 16,
+			clk_get_rate(ttccs->ttc.clk) / PRESCALE);
 }
 
 static int ttc_rate_change_clockevent_cb(struct notifier_block *nb,
diff --git a/drivers/clocksource/clksrc-of.c b/drivers/clocksource/clksrc-of.c
index 37f5325bec95..b9ddd9e3a2f5 100644
--- a/drivers/clocksource/clksrc-of.c
+++ b/drivers/clocksource/clksrc-of.c
@@ -30,6 +30,9 @@ void __init clocksource_of_init(void)
 	clocksource_of_init_fn init_func;
 
 	for_each_matching_node_and_match(np, __clksrc_of_table, &match) {
+		if (!of_device_is_available(np))
+			continue;
+
 		init_func = match->data;
 		init_func(np);
 	}
diff --git a/drivers/clocksource/em_sti.c b/drivers/clocksource/em_sti.c
index 4329a29a5310..3a5909c12d42 100644
--- a/drivers/clocksource/em_sti.c
+++ b/drivers/clocksource/em_sti.c
@@ -301,7 +301,7 @@ static void em_sti_register_clockevent(struct em_sti_priv *p)
 	ced->name = dev_name(&p->pdev->dev);
 	ced->features = CLOCK_EVT_FEAT_ONESHOT;
 	ced->rating = 200;
-	ced->cpumask = cpumask_of(0);
+	ced->cpumask = cpu_possible_mask;
 	ced->set_next_event = em_sti_clock_event_next;
 	ced->set_mode = em_sti_clock_event_mode;
 
@@ -315,68 +315,47 @@ static int em_sti_probe(struct platform_device *pdev)
 {
 	struct em_sti_priv *p;
 	struct resource *res;
-	int irq, ret;
+	int irq;
 
-	p = kzalloc(sizeof(*p), GFP_KERNEL);
+	p = devm_kzalloc(&pdev->dev, sizeof(*p), GFP_KERNEL);
 	if (p == NULL) {
 		dev_err(&pdev->dev, "failed to allocate driver data\n");
-		ret = -ENOMEM;
-		goto err0;
+		return -ENOMEM;
 	}
 
 	p->pdev = pdev;
 	platform_set_drvdata(pdev, p);
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!res) {
-		dev_err(&pdev->dev, "failed to get I/O memory\n");
-		ret = -EINVAL;
-		goto err0;
-	}
-
 	irq = platform_get_irq(pdev, 0);
 	if (irq < 0) {
 		dev_err(&pdev->dev, "failed to get irq\n");
-		ret = -EINVAL;
-		goto err0;
+		return -EINVAL;
 	}
 
 	/* map memory, let base point to the STI instance */
-	p->base = ioremap_nocache(res->start, resource_size(res));
-	if (p->base == NULL) {
-		dev_err(&pdev->dev, "failed to remap I/O memory\n");
-		ret = -ENXIO;
-		goto err0;
-	}
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	p->base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(p->base))
+		return PTR_ERR(p->base);
 
 	/* get hold of clock */
-	p->clk = clk_get(&pdev->dev, "sclk");
+	p->clk = devm_clk_get(&pdev->dev, "sclk");
 	if (IS_ERR(p->clk)) {
 		dev_err(&pdev->dev, "cannot get clock\n");
-		ret = PTR_ERR(p->clk);
-		goto err1;
+		return PTR_ERR(p->clk);
 	}
 
-	if (request_irq(irq, em_sti_interrupt,
-			IRQF_TIMER | IRQF_IRQPOLL | IRQF_NOBALANCING,
-			dev_name(&pdev->dev), p)) {
+	if (devm_request_irq(&pdev->dev, irq, em_sti_interrupt,
+			     IRQF_TIMER | IRQF_IRQPOLL | IRQF_NOBALANCING,
+			     dev_name(&pdev->dev), p)) {
 		dev_err(&pdev->dev, "failed to request low IRQ\n");
-		ret = -ENOENT;
-		goto err2;
+		return -ENOENT;
 	}
 
 	raw_spin_lock_init(&p->lock);
 	em_sti_register_clockevent(p);
 	em_sti_register_clocksource(p);
 	return 0;
-
-err2:
-	clk_put(p->clk);
-err1:
-	iounmap(p->base);
-err0:
-	kfree(p);
-	return ret;
 }
 
 static int em_sti_remove(struct platform_device *pdev)
diff --git a/drivers/clocksource/exynos_mct.c b/drivers/clocksource/exynos_mct.c
index b2bbc415f120..62b0de6a1837 100644
--- a/drivers/clocksource/exynos_mct.c
+++ b/drivers/clocksource/exynos_mct.c
@@ -16,6 +16,7 @@
 #include <linux/err.h>
 #include <linux/clk.h>
 #include <linux/clockchips.h>
+#include <linux/cpu.h>
 #include <linux/platform_device.h>
 #include <linux/delay.h>
 #include <linux/percpu.h>
@@ -24,7 +25,6 @@
 #include <linux/of_address.h>
 #include <linux/clocksource.h>
 
-#include <asm/localtimer.h>
 #include <asm/mach/time.h>
 
 #define EXYNOS4_MCTREG(x)		(x)
@@ -80,7 +80,7 @@ static unsigned int mct_int_type;
 static int mct_irqs[MCT_NR_IRQS];
 
 struct mct_clock_event_device {
-	struct clock_event_device *evt;
+	struct clock_event_device evt;
 	unsigned long base;
 	char name[10];
 };
@@ -295,8 +295,6 @@ static void exynos4_clockevent_init(void)
 	setup_irq(mct_irqs[MCT_G0_IRQ], &mct_comp_event_irq);
 }
 
-#ifdef CONFIG_LOCAL_TIMERS
-
 static DEFINE_PER_CPU(struct mct_clock_event_device, percpu_mct_tick);
 
 /* Clock event handling */
@@ -369,7 +367,7 @@ static inline void exynos4_tick_set_mode(enum clock_event_mode mode,
 
 static int exynos4_mct_tick_clear(struct mct_clock_event_device *mevt)
 {
-	struct clock_event_device *evt = mevt->evt;
+	struct clock_event_device *evt = &mevt->evt;
 
 	/*
 	 * This is for supporting oneshot mode.
@@ -391,7 +389,7 @@ static int exynos4_mct_tick_clear(struct mct_clock_event_device *mevt)
 static irqreturn_t exynos4_mct_tick_isr(int irq, void *dev_id)
 {
 	struct mct_clock_event_device *mevt = dev_id;
-	struct clock_event_device *evt = mevt->evt;
+	struct clock_event_device *evt = &mevt->evt;
 
 	exynos4_mct_tick_clear(mevt);
 
@@ -405,8 +403,7 @@ static int exynos4_local_timer_setup(struct clock_event_device *evt)
 	struct mct_clock_event_device *mevt;
 	unsigned int cpu = smp_processor_id();
 
-	mevt = this_cpu_ptr(&percpu_mct_tick);
-	mevt->evt = evt;
+	mevt = container_of(evt, struct mct_clock_event_device, evt);
 
 	mevt->base = EXYNOS4_MCT_L_BASE(cpu);
 	sprintf(mevt->name, "mct_tick%d", cpu);
@@ -431,7 +428,6 @@ static int exynos4_local_timer_setup(struct clock_event_device *evt)
 				evt->irq);
 			return -EIO;
 		}
-		irq_set_affinity(evt->irq, cpumask_of(cpu));
 	} else {
 		enable_percpu_irq(mct_irqs[MCT_L0_IRQ], 0);
 	}
@@ -448,14 +444,44 @@ static void exynos4_local_timer_stop(struct clock_event_device *evt)
 		disable_percpu_irq(mct_irqs[MCT_L0_IRQ]);
 }
 
-static struct local_timer_ops exynos4_mct_tick_ops = {
-	.setup	= exynos4_local_timer_setup,
-	.stop	= exynos4_local_timer_stop,
+static int exynos4_mct_cpu_notify(struct notifier_block *self,
+					   unsigned long action, void *hcpu)
+{
+	struct mct_clock_event_device *mevt;
+	unsigned int cpu;
+
+	/*
+	 * Grab cpu pointer in each case to avoid spurious
+	 * preemptible warnings
+	 */
+	switch (action & ~CPU_TASKS_FROZEN) {
+	case CPU_STARTING:
+		mevt = this_cpu_ptr(&percpu_mct_tick);
+		exynos4_local_timer_setup(&mevt->evt);
+		break;
+	case CPU_ONLINE:
+		cpu = (unsigned long)hcpu;
+		if (mct_int_type == MCT_INT_SPI)
+			irq_set_affinity(mct_irqs[MCT_L0_IRQ + cpu],
+						cpumask_of(cpu));
+		break;
+	case CPU_DYING:
+		mevt = this_cpu_ptr(&percpu_mct_tick);
+		exynos4_local_timer_stop(&mevt->evt);
+		break;
+	}
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block exynos4_mct_cpu_nb = {
+	.notifier_call = exynos4_mct_cpu_notify,
 };
-#endif /* CONFIG_LOCAL_TIMERS */
 
 static void __init exynos4_timer_resources(struct device_node *np, void __iomem *base)
 {
+	int err;
+	struct mct_clock_event_device *mevt = this_cpu_ptr(&percpu_mct_tick);
 	struct clk *mct_clk, *tick_clk;
 
 	tick_clk = np ? of_clk_get_by_name(np, "fin_pll") :
@@ -473,19 +499,27 @@ static void __init exynos4_timer_resources(struct device_node *np, void __iomem
 	if (!reg_base)
 		panic("%s: unable to ioremap mct address space\n", __func__);
 
-#ifdef CONFIG_LOCAL_TIMERS
 	if (mct_int_type == MCT_INT_PPI) {
-		int err;
 
 		err = request_percpu_irq(mct_irqs[MCT_L0_IRQ],
 					 exynos4_mct_tick_isr, "MCT",
 					 &percpu_mct_tick);
 		WARN(err, "MCT: can't request IRQ %d (%d)\n",
 		     mct_irqs[MCT_L0_IRQ], err);
+	} else {
+		irq_set_affinity(mct_irqs[MCT_L0_IRQ], cpumask_of(0));
 	}
 
-	local_timer_register(&exynos4_mct_tick_ops);
-#endif /* CONFIG_LOCAL_TIMERS */
+	err = register_cpu_notifier(&exynos4_mct_cpu_nb);
+	if (err)
+		goto out_irq;
+
+	/* Immediately configure the timer on the boot CPU */
+	exynos4_local_timer_setup(&mevt->evt);
+	return;
+
+out_irq:
+	free_percpu_irq(mct_irqs[MCT_L0_IRQ], &percpu_mct_tick);
 }
 
 void __init mct_init(void __iomem *base, int irq_g0, int irq_l0, int irq_l1)
diff --git a/drivers/clocksource/moxart_timer.c b/drivers/clocksource/moxart_timer.c
new file mode 100644
index 000000000000..5eb2c35932b1
--- /dev/null
+++ b/drivers/clocksource/moxart_timer.c
@@ -0,0 +1,165 @@
+/*
+ * MOXA ART SoCs timer handling.
+ *
+ * Copyright (C) 2013 Jonas Jensen
+ *
+ * Jonas Jensen <jonas.jensen@gmail.com>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2.  This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+#include <linux/clk.h>
+#include <linux/clockchips.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/irqreturn.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/io.h>
+#include <linux/clocksource.h>
+#include <linux/bitops.h>
+
+#define TIMER1_BASE		0x00
+#define TIMER2_BASE		0x10
+#define TIMER3_BASE		0x20
+
+#define REG_COUNT		0x0 /* writable */
+#define REG_LOAD		0x4
+#define REG_MATCH1		0x8
+#define REG_MATCH2		0xC
+
+#define TIMER_CR		0x30
+#define TIMER_INTR_STATE	0x34
+#define TIMER_INTR_MASK		0x38
+
+/*
+ * TIMER_CR flags:
+ *
+ * TIMEREG_CR_*_CLOCK	0: PCLK, 1: EXT1CLK
+ * TIMEREG_CR_*_INT	overflow interrupt enable bit
+ */
+#define TIMEREG_CR_1_ENABLE	BIT(0)
+#define TIMEREG_CR_1_CLOCK	BIT(1)
+#define TIMEREG_CR_1_INT	BIT(2)
+#define TIMEREG_CR_2_ENABLE	BIT(3)
+#define TIMEREG_CR_2_CLOCK	BIT(4)
+#define TIMEREG_CR_2_INT	BIT(5)
+#define TIMEREG_CR_3_ENABLE	BIT(6)
+#define TIMEREG_CR_3_CLOCK	BIT(7)
+#define TIMEREG_CR_3_INT	BIT(8)
+#define TIMEREG_CR_COUNT_UP	BIT(9)
+
+#define TIMER1_ENABLE		(TIMEREG_CR_2_ENABLE | TIMEREG_CR_1_ENABLE)
+#define TIMER1_DISABLE		(TIMEREG_CR_2_ENABLE)
+
+static void __iomem *base;
+static unsigned int clock_count_per_tick;
+
+static void moxart_clkevt_mode(enum clock_event_mode mode,
+			       struct clock_event_device *clk)
+{
+	switch (mode) {
+	case CLOCK_EVT_MODE_RESUME:
+	case CLOCK_EVT_MODE_ONESHOT:
+		writel(TIMER1_DISABLE, base + TIMER_CR);
+		writel(~0, base + TIMER1_BASE + REG_LOAD);
+		break;
+	case CLOCK_EVT_MODE_PERIODIC:
+		writel(clock_count_per_tick, base + TIMER1_BASE + REG_LOAD);
+		writel(TIMER1_ENABLE, base + TIMER_CR);
+		break;
+	case CLOCK_EVT_MODE_UNUSED:
+	case CLOCK_EVT_MODE_SHUTDOWN:
+	default:
+		writel(TIMER1_DISABLE, base + TIMER_CR);
+		break;
+	}
+}
+
+static int moxart_clkevt_next_event(unsigned long cycles,
+				    struct clock_event_device *unused)
+{
+	u32 u;
+
+	writel(TIMER1_DISABLE, base + TIMER_CR);
+
+	u = readl(base + TIMER1_BASE + REG_COUNT) - cycles;
+	writel(u, base + TIMER1_BASE + REG_MATCH1);
+
+	writel(TIMER1_ENABLE, base + TIMER_CR);
+
+	return 0;
+}
+
+static struct clock_event_device moxart_clockevent = {
+	.name		= "moxart_timer",
+	.rating		= 200,
+	.features	= CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT,
+	.set_mode	= moxart_clkevt_mode,
+	.set_next_event	= moxart_clkevt_next_event,
+};
+
+static irqreturn_t moxart_timer_interrupt(int irq, void *dev_id)
+{
+	struct clock_event_device *evt = dev_id;
+	evt->event_handler(evt);
+	return IRQ_HANDLED;
+}
+
+static struct irqaction moxart_timer_irq = {
+	.name		= "moxart-timer",
+	.flags		= IRQF_TIMER,
+	.handler	= moxart_timer_interrupt,
+	.dev_id		= &moxart_clockevent,
+};
+
+static void __init moxart_timer_init(struct device_node *node)
+{
+	int ret, irq;
+	unsigned long pclk;
+	struct clk *clk;
+
+	base = of_iomap(node, 0);
+	if (!base)
+		panic("%s: of_iomap failed\n", node->full_name);
+
+	irq = irq_of_parse_and_map(node, 0);
+	if (irq <= 0)
+		panic("%s: irq_of_parse_and_map failed\n", node->full_name);
+
+	ret = setup_irq(irq, &moxart_timer_irq);
+	if (ret)
+		panic("%s: setup_irq failed\n", node->full_name);
+
+	clk = of_clk_get(node, 0);
+	if (IS_ERR(clk))
+		panic("%s: of_clk_get failed\n", node->full_name);
+
+	pclk = clk_get_rate(clk);
+
+	if (clocksource_mmio_init(base + TIMER2_BASE + REG_COUNT,
+				  "moxart_timer", pclk, 200, 32,
+				  clocksource_mmio_readl_down))
+		panic("%s: clocksource_mmio_init failed\n", node->full_name);
+
+	clock_count_per_tick = DIV_ROUND_CLOSEST(pclk, HZ);
+
+	writel(~0, base + TIMER2_BASE + REG_LOAD);
+	writel(TIMEREG_CR_2_ENABLE, base + TIMER_CR);
+
+	moxart_clockevent.cpumask = cpumask_of(0);
+	moxart_clockevent.irq = irq;
+
+	/*
+	 * documentation is not publicly available:
+	 * min_delta / max_delta obtained by trial-and-error,
+	 * max_delta 0xfffffffe should be ok because count
+	 * register size is u32
+	 */
+	clockevents_config_and_register(&moxart_clockevent, pclk,
+					0x4, 0xfffffffe);
+}
+CLOCKSOURCE_OF_DECLARE(moxart, "moxa,moxart-timer", moxart_timer_init);
diff --git a/drivers/clocksource/nomadik-mtu.c b/drivers/clocksource/nomadik-mtu.c
index 7d2c2c56f73c..1b74bea12385 100644
--- a/drivers/clocksource/nomadik-mtu.c
+++ b/drivers/clocksource/nomadik-mtu.c
@@ -165,7 +165,8 @@ static void nmdk_clkevt_resume(struct clock_event_device *cedev)
 
 static struct clock_event_device nmdk_clkevt = {
 	.name		= "mtu_1",
-	.features	= CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_FEAT_PERIODIC,
+	.features	= CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_FEAT_PERIODIC |
+	                  CLOCK_EVT_FEAT_DYNIRQ,
 	.rating		= 200,
 	.set_mode	= nmdk_clkevt_mode,
 	.set_next_event	= nmdk_clkevt_next,
diff --git a/drivers/clocksource/samsung_pwm_timer.c b/drivers/clocksource/samsung_pwm_timer.c
index 584b5472eea3..ab29476ee5f9 100644
--- a/drivers/clocksource/samsung_pwm_timer.c
+++ b/drivers/clocksource/samsung_pwm_timer.c
@@ -44,16 +44,28 @@
 #define TCFG1_SHIFT(x)	  		((x) * 4)
 #define TCFG1_MUX_MASK	  		0xf
 
+/*
+ * Each channel occupies 4 bits in TCON register, but there is a gap of 4
+ * bits (one channel) after channel 0, so channels have different numbering
+ * when accessing TCON register.
+ *
+ * In addition, the location of autoreload bit for channel 4 (TCON channel 5)
+ * in its set of bits is 2 as opposed to 3 for other channels.
+ */
 #define TCON_START(chan)		(1 << (4 * (chan) + 0))
 #define TCON_MANUALUPDATE(chan)		(1 << (4 * (chan) + 1))
 #define TCON_INVERT(chan)		(1 << (4 * (chan) + 2))
-#define TCON_AUTORELOAD(chan)		(1 << (4 * (chan) + 3))
+#define _TCON_AUTORELOAD(chan)		(1 << (4 * (chan) + 3))
+#define _TCON_AUTORELOAD4(chan)		(1 << (4 * (chan) + 2))
+#define TCON_AUTORELOAD(chan)		\
+	((chan < 5) ? _TCON_AUTORELOAD(chan) : _TCON_AUTORELOAD4(chan))
 
 DEFINE_SPINLOCK(samsung_pwm_lock);
 EXPORT_SYMBOL(samsung_pwm_lock);
 
 struct samsung_pwm_clocksource {
 	void __iomem *base;
+	void __iomem *source_reg;
 	unsigned int irq[SAMSUNG_PWM_NUM];
 	struct samsung_pwm_variant variant;
 
@@ -195,17 +207,6 @@ static int samsung_set_next_event(unsigned long cycles,
 	return 0;
 }
 
-static void samsung_timer_resume(void)
-{
-	/* event timer restart */
-	samsung_time_setup(pwm.event_id, pwm.clock_count_per_tick - 1);
-	samsung_time_start(pwm.event_id, true);
-
-	/* source timer restart */
-	samsung_time_setup(pwm.source_id, pwm.tcnt_max);
-	samsung_time_start(pwm.source_id, true);
-}
-
 static void samsung_set_mode(enum clock_event_mode mode,
 				struct clock_event_device *evt)
 {
@@ -222,20 +223,29 @@ static void samsung_set_mode(enum clock_event_mode mode,
 
 	case CLOCK_EVT_MODE_UNUSED:
 	case CLOCK_EVT_MODE_SHUTDOWN:
-		break;
-
 	case CLOCK_EVT_MODE_RESUME:
-		samsung_timer_resume();
 		break;
 	}
 }
 
+static void samsung_clockevent_resume(struct clock_event_device *cev)
+{
+	samsung_timer_set_prescale(pwm.event_id, pwm.tscaler_div);
+	samsung_timer_set_divisor(pwm.event_id, pwm.tdiv);
+
+	if (pwm.variant.has_tint_cstat) {
+		u32 mask = (1 << pwm.event_id);
+		writel(mask | (mask << 5), pwm.base + REG_TINT_CSTAT);
+	}
+}
+
 static struct clock_event_device time_event_device = {
 	.name		= "samsung_event_timer",
 	.features	= CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT,
 	.rating		= 200,
 	.set_next_event	= samsung_set_next_event,
 	.set_mode	= samsung_set_mode,
+	.resume		= samsung_clockevent_resume,
 };
 
 static irqreturn_t samsung_clock_event_isr(int irq, void *dev_id)
@@ -286,23 +296,34 @@ static void __init samsung_clockevent_init(void)
 	}
 }
 
-static void __iomem *samsung_timer_reg(void)
+static void samsung_clocksource_suspend(struct clocksource *cs)
 {
-	switch (pwm.source_id) {
-	case 0:
-	case 1:
-	case 2:
-	case 3:
-		return pwm.base + pwm.source_id * 0x0c + 0x14;
-
-	case 4:
-		return pwm.base + 0x40;
-
-	default:
-		BUG();
-	}
+	samsung_time_stop(pwm.source_id);
 }
 
+static void samsung_clocksource_resume(struct clocksource *cs)
+{
+	samsung_timer_set_prescale(pwm.source_id, pwm.tscaler_div);
+	samsung_timer_set_divisor(pwm.source_id, pwm.tdiv);
+
+	samsung_time_setup(pwm.source_id, pwm.tcnt_max);
+	samsung_time_start(pwm.source_id, true);
+}
+
+static cycle_t samsung_clocksource_read(struct clocksource *c)
+{
+	return ~readl_relaxed(pwm.source_reg);
+}
+
+static struct clocksource samsung_clocksource = {
+	.name		= "samsung_clocksource_timer",
+	.rating		= 250,
+	.read		= samsung_clocksource_read,
+	.suspend	= samsung_clocksource_suspend,
+	.resume		= samsung_clocksource_resume,
+	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
+};
+
 /*
  * Override the global weak sched_clock symbol with this
  * local implementation which uses the clocksource to get some
@@ -312,17 +333,11 @@ static void __iomem *samsung_timer_reg(void)
  */
 static u32 notrace samsung_read_sched_clock(void)
 {
-	void __iomem *reg = samsung_timer_reg();
-
-	if (!reg)
-		return 0;
-
-	return ~__raw_readl(reg);
+	return samsung_clocksource_read(NULL);
 }
 
 static void __init samsung_clocksource_init(void)
 {
-	void __iomem *reg = samsung_timer_reg();
 	unsigned long pclk;
 	unsigned long clock_rate;
 	int ret;
@@ -337,22 +352,22 @@ static void __init samsung_clocksource_init(void)
 	samsung_time_setup(pwm.source_id, pwm.tcnt_max);
 	samsung_time_start(pwm.source_id, true);
 
+	if (pwm.source_id == 4)
+		pwm.source_reg = pwm.base + 0x40;
+	else
+		pwm.source_reg = pwm.base + pwm.source_id * 0x0c + 0x14;
+
 	setup_sched_clock(samsung_read_sched_clock,
 						pwm.variant.bits, clock_rate);
 
-	ret = clocksource_mmio_init(reg, "samsung_clocksource_timer",
-					clock_rate, 250, pwm.variant.bits,
-					clocksource_mmio_readl_down);
+	samsung_clocksource.mask = CLOCKSOURCE_MASK(pwm.variant.bits);
+	ret = clocksource_register_hz(&samsung_clocksource, clock_rate);
 	if (ret)
 		panic("samsung_clocksource_timer: can't register clocksource\n");
 }
 
 static void __init samsung_timer_resources(void)
 {
-	pwm.timerclk = clk_get(NULL, "timers");
-	if (IS_ERR(pwm.timerclk))
-		panic("failed to get timers clock for timer");
-
 	clk_prepare_enable(pwm.timerclk);
 
 	pwm.tcnt_max = (1UL << pwm.variant.bits) - 1;
@@ -397,6 +412,10 @@ void __init samsung_pwm_clocksource_init(void __iomem *base,
 	memcpy(&pwm.variant, variant, sizeof(pwm.variant));
 	memcpy(pwm.irq, irqs, SAMSUNG_PWM_NUM * sizeof(*irqs));
 
+	pwm.timerclk = clk_get(NULL, "timers");
+	if (IS_ERR(pwm.timerclk))
+		panic("failed to get timers clock for timer");
+
 	_samsung_pwm_clocksource_init();
 }
 
@@ -404,7 +423,6 @@ void __init samsung_pwm_clocksource_init(void __iomem *base,
 static void __init samsung_pwm_alloc(struct device_node *np,
 				     const struct samsung_pwm_variant *variant)
 {
-	struct resource res;
 	struct property *prop;
 	const __be32 *cur;
 	u32 val;
@@ -423,20 +441,16 @@ static void __init samsung_pwm_alloc(struct device_node *np,
 		pwm.variant.output_mask |= 1 << val;
 	}
 
-	of_address_to_resource(np, 0, &res);
-	if (!request_mem_region(res.start,
-				resource_size(&res), "samsung-pwm")) {
-		pr_err("%s: failed to request IO mem region\n", __func__);
-		return;
-	}
-
-	pwm.base = ioremap(res.start, resource_size(&res));
+	pwm.base = of_iomap(np, 0);
 	if (!pwm.base) {
 		pr_err("%s: failed to map PWM registers\n", __func__);
-		release_mem_region(res.start, resource_size(&res));
 		return;
 	}
 
+	pwm.timerclk = of_clk_get_by_name(np, "timers");
+	if (IS_ERR(pwm.timerclk))
+		panic("failed to get timers clock for timer");
+
 	_samsung_pwm_clocksource_init();
 }
 
diff --git a/drivers/clocksource/sh_cmt.c b/drivers/clocksource/sh_cmt.c
index 08d0c418c94a..0965e9848b3d 100644
--- a/drivers/clocksource/sh_cmt.c
+++ b/drivers/clocksource/sh_cmt.c
@@ -37,6 +37,7 @@
 
 struct sh_cmt_priv {
 	void __iomem *mapbase;
+	void __iomem *mapbase_str;
 	struct clk *clk;
 	unsigned long width; /* 16 or 32 bit version of hardware block */
 	unsigned long overflow_bit;
@@ -79,6 +80,12 @@ struct sh_cmt_priv {
  * CMCSR 0xffca0060 16-bit
  * CMCNT 0xffca0064 32-bit
  * CMCOR 0xffca0068 32-bit
+ *
+ * "32-bit counter and 32-bit control" as found on r8a73a4 and r8a7790:
+ * CMSTR 0xffca0500 32-bit
+ * CMCSR 0xffca0510 32-bit
+ * CMCNT 0xffca0514 32-bit
+ * CMCOR 0xffca0518 32-bit
  */
 
 static unsigned long sh_cmt_read16(void __iomem *base, unsigned long offs)
@@ -109,9 +116,7 @@ static void sh_cmt_write32(void __iomem *base, unsigned long offs,
 
 static inline unsigned long sh_cmt_read_cmstr(struct sh_cmt_priv *p)
 {
-	struct sh_timer_config *cfg = p->pdev->dev.platform_data;
-
-	return p->read_control(p->mapbase - cfg->channel_offset, 0);
+	return p->read_control(p->mapbase_str, 0);
 }
 
 static inline unsigned long sh_cmt_read_cmcsr(struct sh_cmt_priv *p)
@@ -127,9 +132,7 @@ static inline unsigned long sh_cmt_read_cmcnt(struct sh_cmt_priv *p)
 static inline void sh_cmt_write_cmstr(struct sh_cmt_priv *p,
 				      unsigned long value)
 {
-	struct sh_timer_config *cfg = p->pdev->dev.platform_data;
-
-	p->write_control(p->mapbase - cfg->channel_offset, 0, value);
+	p->write_control(p->mapbase_str, 0, value);
 }
 
 static inline void sh_cmt_write_cmcsr(struct sh_cmt_priv *p,
@@ -676,7 +679,7 @@ static int sh_cmt_register(struct sh_cmt_priv *p, char *name,
 static int sh_cmt_setup(struct sh_cmt_priv *p, struct platform_device *pdev)
 {
 	struct sh_timer_config *cfg = pdev->dev.platform_data;
-	struct resource *res;
+	struct resource *res, *res2;
 	int irq, ret;
 	ret = -ENXIO;
 
@@ -694,6 +697,9 @@ static int sh_cmt_setup(struct sh_cmt_priv *p, struct platform_device *pdev)
 		goto err0;
 	}
 
+	/* optional resource for the shared timer start/stop register */
+	res2 = platform_get_resource(p->pdev, IORESOURCE_MEM, 1);
+
 	irq = platform_get_irq(p->pdev, 0);
 	if (irq < 0) {
 		dev_err(&p->pdev->dev, "failed to get irq\n");
@@ -707,6 +713,15 @@ static int sh_cmt_setup(struct sh_cmt_priv *p, struct platform_device *pdev)
 		goto err0;
 	}
 
+	/* map second resource for CMSTR */
+	p->mapbase_str = ioremap_nocache(res2 ? res2->start :
+					 res->start - cfg->channel_offset,
+					 res2 ? resource_size(res2) : 2);
+	if (p->mapbase_str == NULL) {
+		dev_err(&p->pdev->dev, "failed to remap I/O second memory\n");
+		goto err1;
+	}
+
 	/* request irq using setup_irq() (too early for request_irq()) */
 	p->irqaction.name = dev_name(&p->pdev->dev);
 	p->irqaction.handler = sh_cmt_interrupt;
@@ -719,11 +734,17 @@ static int sh_cmt_setup(struct sh_cmt_priv *p, struct platform_device *pdev)
 	if (IS_ERR(p->clk)) {
 		dev_err(&p->pdev->dev, "cannot get clock\n");
 		ret = PTR_ERR(p->clk);
-		goto err1;
+		goto err2;
 	}
 
-	p->read_control = sh_cmt_read16;
-	p->write_control = sh_cmt_write16;
+	if (res2 && (resource_size(res2) == 4)) {
+		/* assume both CMSTR and CMCSR to be 32-bit */
+		p->read_control = sh_cmt_read32;
+		p->write_control = sh_cmt_write32;
+	} else {
+		p->read_control = sh_cmt_read16;
+		p->write_control = sh_cmt_write16;
+	}
 
 	if (resource_size(res) == 6) {
 		p->width = 16;
@@ -752,22 +773,23 @@ static int sh_cmt_setup(struct sh_cmt_priv *p, struct platform_device *pdev)
 			      cfg->clocksource_rating);
 	if (ret) {
 		dev_err(&p->pdev->dev, "registration failed\n");
-		goto err2;
+		goto err3;
 	}
 	p->cs_enabled = false;
 
 	ret = setup_irq(irq, &p->irqaction);
 	if (ret) {
 		dev_err(&p->pdev->dev, "failed to request irq %d\n", irq);
-		goto err2;
+		goto err3;
 	}
 
 	platform_set_drvdata(pdev, p);
 
 	return 0;
-err2:
+err3:
 	clk_put(p->clk);
-
+err2:
+	iounmap(p->mapbase_str);
 err1:
 	iounmap(p->mapbase);
 err0:
diff --git a/drivers/clocksource/sun4i_timer.c b/drivers/clocksource/sun4i_timer.c
index d4674e78ef35..8ead0258740a 100644
--- a/drivers/clocksource/sun4i_timer.c
+++ b/drivers/clocksource/sun4i_timer.c
@@ -19,42 +19,83 @@
 #include <linux/interrupt.h>
 #include <linux/irq.h>
 #include <linux/irqreturn.h>
+#include <linux/sched_clock.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
 
 #define TIMER_IRQ_EN_REG	0x00
-#define TIMER_IRQ_EN(val)		(1 << val)
+#define TIMER_IRQ_EN(val)		BIT(val)
 #define TIMER_IRQ_ST_REG	0x04
 #define TIMER_CTL_REG(val)	(0x10 * val + 0x10)
-#define TIMER_CTL_ENABLE		(1 << 0)
-#define TIMER_CTL_AUTORELOAD		(1 << 1)
-#define TIMER_CTL_ONESHOT		(1 << 7)
-#define TIMER_INTVAL_REG(val)	(0x10 * val + 0x14)
-#define TIMER_CNTVAL_REG(val)	(0x10 * val + 0x18)
-
-#define TIMER_SCAL		16
+#define TIMER_CTL_ENABLE		BIT(0)
+#define TIMER_CTL_RELOAD		BIT(1)
+#define TIMER_CTL_CLK_SRC(val)		(((val) & 0x3) << 2)
+#define TIMER_CTL_CLK_SRC_OSC24M		(1)
+#define TIMER_CTL_CLK_PRES(val)		(((val) & 0x7) << 4)
+#define TIMER_CTL_ONESHOT		BIT(7)
+#define TIMER_INTVAL_REG(val)	(0x10 * (val) + 0x14)
+#define TIMER_CNTVAL_REG(val)	(0x10 * (val) + 0x18)
 
 static void __iomem *timer_base;
+static u32 ticks_per_jiffy;
+
+/*
+ * When we disable a timer, we need to wait at least for 2 cycles of
+ * the timer source clock. We will use for that the clocksource timer
+ * that is already setup and runs at the same frequency than the other
+ * timers, and we never will be disabled.
+ */
+static void sun4i_clkevt_sync(void)
+{
+	u32 old = readl(timer_base + TIMER_CNTVAL_REG(1));
+
+	while ((old - readl(timer_base + TIMER_CNTVAL_REG(1))) < 3)
+		cpu_relax();
+}
+
+static void sun4i_clkevt_time_stop(u8 timer)
+{
+	u32 val = readl(timer_base + TIMER_CTL_REG(timer));
+	writel(val & ~TIMER_CTL_ENABLE, timer_base + TIMER_CTL_REG(timer));
+	sun4i_clkevt_sync();
+}
+
+static void sun4i_clkevt_time_setup(u8 timer, unsigned long delay)
+{
+	writel(delay, timer_base + TIMER_INTVAL_REG(timer));
+}
+
+static void sun4i_clkevt_time_start(u8 timer, bool periodic)
+{
+	u32 val = readl(timer_base + TIMER_CTL_REG(timer));
+
+	if (periodic)
+		val &= ~TIMER_CTL_ONESHOT;
+	else
+		val |= TIMER_CTL_ONESHOT;
+
+	writel(val | TIMER_CTL_ENABLE | TIMER_CTL_RELOAD,
+	       timer_base + TIMER_CTL_REG(timer));
+}
 
 static void sun4i_clkevt_mode(enum clock_event_mode mode,
 			      struct clock_event_device *clk)
 {
-	u32 u = readl(timer_base + TIMER_CTL_REG(0));
-
 	switch (mode) {
 	case CLOCK_EVT_MODE_PERIODIC:
-		u &= ~(TIMER_CTL_ONESHOT);
-		writel(u | TIMER_CTL_ENABLE, timer_base + TIMER_CTL_REG(0));
+		sun4i_clkevt_time_stop(0);
+		sun4i_clkevt_time_setup(0, ticks_per_jiffy);
+		sun4i_clkevt_time_start(0, true);
 		break;
-
 	case CLOCK_EVT_MODE_ONESHOT:
-		writel(u | TIMER_CTL_ONESHOT, timer_base + TIMER_CTL_REG(0));
+		sun4i_clkevt_time_stop(0);
+		sun4i_clkevt_time_start(0, false);
 		break;
 	case CLOCK_EVT_MODE_UNUSED:
 	case CLOCK_EVT_MODE_SHUTDOWN:
 	default:
-		writel(u & ~(TIMER_CTL_ENABLE), timer_base + TIMER_CTL_REG(0));
+		sun4i_clkevt_time_stop(0);
 		break;
 	}
 }
@@ -62,10 +103,9 @@ static void sun4i_clkevt_mode(enum clock_event_mode mode,
 static int sun4i_clkevt_next_event(unsigned long evt,
 				   struct clock_event_device *unused)
 {
-	u32 u = readl(timer_base + TIMER_CTL_REG(0));
-	writel(evt, timer_base + TIMER_CNTVAL_REG(0));
-	writel(u | TIMER_CTL_ENABLE | TIMER_CTL_AUTORELOAD,
-	       timer_base + TIMER_CTL_REG(0));
+	sun4i_clkevt_time_stop(0);
+	sun4i_clkevt_time_setup(0, evt);
+	sun4i_clkevt_time_start(0, false);
 
 	return 0;
 }
@@ -96,6 +136,11 @@ static struct irqaction sun4i_timer_irq = {
 	.dev_id = &sun4i_clockevent,
 };
 
+static u32 sun4i_timer_sched_read(void)
+{
+	return ~readl(timer_base + TIMER_CNTVAL_REG(1));
+}
+
 static void __init sun4i_timer_init(struct device_node *node)
 {
 	unsigned long rate = 0;
@@ -114,22 +159,23 @@ static void __init sun4i_timer_init(struct device_node *node)
 	clk = of_clk_get(node, 0);
 	if (IS_ERR(clk))
 		panic("Can't get timer clock");
+	clk_prepare_enable(clk);
 
 	rate = clk_get_rate(clk);
 
-	writel(rate / (TIMER_SCAL * HZ),
-	       timer_base + TIMER_INTVAL_REG(0));
+	writel(~0, timer_base + TIMER_INTVAL_REG(1));
+	writel(TIMER_CTL_ENABLE | TIMER_CTL_RELOAD |
+	       TIMER_CTL_CLK_SRC(TIMER_CTL_CLK_SRC_OSC24M),
+	       timer_base + TIMER_CTL_REG(1));
+
+	setup_sched_clock(sun4i_timer_sched_read, 32, rate);
+	clocksource_mmio_init(timer_base + TIMER_CNTVAL_REG(1), node->name,
+			      rate, 300, 32, clocksource_mmio_readl_down);
 
-	/* set clock source to HOSC, 16 pre-division */
-	val = readl(timer_base + TIMER_CTL_REG(0));
-	val &= ~(0x07 << 4);
-	val &= ~(0x03 << 2);
-	val |= (4 << 4) | (1 << 2);
-	writel(val, timer_base + TIMER_CTL_REG(0));
+	ticks_per_jiffy = DIV_ROUND_UP(rate, HZ);
 
-	/* set mode to auto reload */
-	val = readl(timer_base + TIMER_CTL_REG(0));
-	writel(val | TIMER_CTL_AUTORELOAD, timer_base + TIMER_CTL_REG(0));
+	writel(TIMER_CTL_CLK_SRC(TIMER_CTL_CLK_SRC_OSC24M),
+	       timer_base + TIMER_CTL_REG(0));
 
 	ret = setup_irq(irq, &sun4i_timer_irq);
 	if (ret)
@@ -141,8 +187,8 @@ static void __init sun4i_timer_init(struct device_node *node)
 
 	sun4i_clockevent.cpumask = cpumask_of(0);
 
-	clockevents_config_and_register(&sun4i_clockevent, rate / TIMER_SCAL,
-					0x1, 0xff);
+	clockevents_config_and_register(&sun4i_clockevent, rate, 0x1,
+					0xffffffff);
 }
 CLOCKSOURCE_OF_DECLARE(sun4i, "allwinner,sun4i-timer",
 		       sun4i_timer_init);
diff --git a/drivers/clocksource/time-armada-370-xp.c b/drivers/clocksource/time-armada-370-xp.c
index 1b04b7e1d39b..0198504ef6b0 100644
--- a/drivers/clocksource/time-armada-370-xp.c
+++ b/drivers/clocksource/time-armada-370-xp.c
@@ -13,12 +13,26 @@
  *
  * Timer 0 is used as free-running clocksource, while timer 1 is
  * used as clock_event_device.
+ *
+ * ---
+ * Clocksource driver for Armada 370 and Armada XP SoC.
+ * This driver implements one compatible string for each SoC, given
+ * each has its own characteristics:
+ *
+ *   * Armada 370 has no 25 MHz fixed timer.
+ *
+ *   * Armada XP cannot work properly without such 25 MHz fixed timer as
+ *     doing otherwise leads to using a clocksource whose frequency varies
+ *     when doing cpufreq frequency changes.
+ *
+ * See Documentation/devicetree/bindings/timer/marvell,armada-370-xp-timer.txt
  */
 
 #include <linux/init.h>
 #include <linux/platform_device.h>
 #include <linux/kernel.h>
 #include <linux/clk.h>
+#include <linux/cpu.h>
 #include <linux/timer.h>
 #include <linux/clockchips.h>
 #include <linux/interrupt.h>
@@ -28,20 +42,19 @@
 #include <linux/irq.h>
 #include <linux/module.h>
 #include <linux/sched_clock.h>
-
-#include <asm/localtimer.h>
 #include <linux/percpu.h>
+
 /*
  * Timer block registers.
  */
 #define TIMER_CTRL_OFF		0x0000
-#define  TIMER0_EN		 0x0001
-#define  TIMER0_RELOAD_EN	 0x0002
-#define  TIMER0_25MHZ            0x0800
+#define  TIMER0_EN		 BIT(0)
+#define  TIMER0_RELOAD_EN	 BIT(1)
+#define  TIMER0_25MHZ            BIT(11)
 #define  TIMER0_DIV(div)         ((div) << 19)
-#define  TIMER1_EN		 0x0004
-#define  TIMER1_RELOAD_EN	 0x0008
-#define  TIMER1_25MHZ            0x1000
+#define  TIMER1_EN		 BIT(2)
+#define  TIMER1_RELOAD_EN	 BIT(3)
+#define  TIMER1_25MHZ            BIT(12)
 #define  TIMER1_DIV(div)         ((div) << 22)
 #define TIMER_EVENTS_STATUS	0x0004
 #define  TIMER0_CLR_MASK         (~0x1)
@@ -69,7 +82,19 @@ static bool timer25Mhz = true;
  */
 static u32 ticks_per_jiffy;
 
-static struct clock_event_device __percpu **percpu_armada_370_xp_evt;
+static struct clock_event_device __percpu *armada_370_xp_evt;
+
+static void timer_ctrl_clrset(u32 clr, u32 set)
+{
+	writel((readl(timer_base + TIMER_CTRL_OFF) & ~clr) | set,
+		timer_base + TIMER_CTRL_OFF);
+}
+
+static void local_timer_ctrl_clrset(u32 clr, u32 set)
+{
+	writel((readl(local_base + TIMER_CTRL_OFF) & ~clr) | set,
+		local_base + TIMER_CTRL_OFF);
+}
 
 static u32 notrace armada_370_xp_read_sched_clock(void)
 {
@@ -83,7 +108,6 @@ static int
 armada_370_xp_clkevt_next_event(unsigned long delta,
 				struct clock_event_device *dev)
 {
-	u32 u;
 	/*
 	 * Clear clockevent timer interrupt.
 	 */
@@ -97,11 +121,8 @@ armada_370_xp_clkevt_next_event(unsigned long delta,
 	/*
 	 * Enable the timer.
 	 */
-	u = readl(local_base + TIMER_CTRL_OFF);
-	u = ((u & ~TIMER0_RELOAD_EN) | TIMER0_EN |
-	     TIMER0_DIV(TIMER_DIVIDER_SHIFT));
-	writel(u, local_base + TIMER_CTRL_OFF);
-
+	local_timer_ctrl_clrset(TIMER0_RELOAD_EN,
+				TIMER0_EN | TIMER0_DIV(TIMER_DIVIDER_SHIFT));
 	return 0;
 }
 
@@ -109,8 +130,6 @@ static void
 armada_370_xp_clkevt_mode(enum clock_event_mode mode,
 			  struct clock_event_device *dev)
 {
-	u32 u;
-
 	if (mode == CLOCK_EVT_MODE_PERIODIC) {
 
 		/*
@@ -122,18 +141,14 @@ armada_370_xp_clkevt_mode(enum clock_event_mode mode,
 		/*
 		 * Enable timer.
 		 */
-
-		u = readl(local_base + TIMER_CTRL_OFF);
-
-		writel((u | TIMER0_EN | TIMER0_RELOAD_EN |
-			TIMER0_DIV(TIMER_DIVIDER_SHIFT)),
-			local_base + TIMER_CTRL_OFF);
+		local_timer_ctrl_clrset(0, TIMER0_RELOAD_EN |
+					   TIMER0_EN |
+					   TIMER0_DIV(TIMER_DIVIDER_SHIFT));
 	} else {
 		/*
 		 * Disable timer.
 		 */
-		u = readl(local_base + TIMER_CTRL_OFF);
-		writel(u & ~TIMER0_EN, local_base + TIMER_CTRL_OFF);
+		local_timer_ctrl_clrset(TIMER0_EN, 0);
 
 		/*
 		 * ACK pending timer interrupt.
@@ -142,21 +157,14 @@ armada_370_xp_clkevt_mode(enum clock_event_mode mode,
 	}
 }
 
-static struct clock_event_device armada_370_xp_clkevt = {
-	.name		= "armada_370_xp_per_cpu_tick",
-	.features	= CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_FEAT_PERIODIC,
-	.shift		= 32,
-	.rating		= 300,
-	.set_next_event	= armada_370_xp_clkevt_next_event,
-	.set_mode	= armada_370_xp_clkevt_mode,
-};
+static int armada_370_xp_clkevt_irq;
 
 static irqreturn_t armada_370_xp_timer_interrupt(int irq, void *dev_id)
 {
 	/*
 	 * ACK timer interrupt and call event handler.
 	 */
-	struct clock_event_device *evt = *(struct clock_event_device **)dev_id;
+	struct clock_event_device *evt = dev_id;
 
 	writel(TIMER0_CLR_MASK, local_base + LCL_TIMER_EVENTS_STATUS);
 	evt->event_handler(evt);
@@ -169,89 +177,81 @@ static irqreturn_t armada_370_xp_timer_interrupt(int irq, void *dev_id)
  */
 static int armada_370_xp_timer_setup(struct clock_event_device *evt)
 {
-	u32 u;
+	u32 clr = 0, set = 0;
 	int cpu = smp_processor_id();
 
-	/* Use existing clock_event for cpu 0 */
-	if (!smp_processor_id())
-		return 0;
-
-	u = readl(local_base + TIMER_CTRL_OFF);
 	if (timer25Mhz)
-		writel(u | TIMER0_25MHZ, local_base + TIMER_CTRL_OFF);
+		set = TIMER0_25MHZ;
 	else
-		writel(u & ~TIMER0_25MHZ, local_base + TIMER_CTRL_OFF);
-
-	evt->name		= armada_370_xp_clkevt.name;
-	evt->irq		= armada_370_xp_clkevt.irq;
-	evt->features		= armada_370_xp_clkevt.features;
-	evt->shift		= armada_370_xp_clkevt.shift;
-	evt->rating		= armada_370_xp_clkevt.rating,
+		clr = TIMER0_25MHZ;
+	local_timer_ctrl_clrset(clr, set);
+
+	evt->name		= "armada_370_xp_per_cpu_tick",
+	evt->features		= CLOCK_EVT_FEAT_ONESHOT |
+				  CLOCK_EVT_FEAT_PERIODIC;
+	evt->shift		= 32,
+	evt->rating		= 300,
 	evt->set_next_event	= armada_370_xp_clkevt_next_event,
 	evt->set_mode		= armada_370_xp_clkevt_mode,
+	evt->irq		= armada_370_xp_clkevt_irq;
 	evt->cpumask		= cpumask_of(cpu);
 
-	*__this_cpu_ptr(percpu_armada_370_xp_evt) = evt;
-
 	clockevents_config_and_register(evt, timer_clk, 1, 0xfffffffe);
 	enable_percpu_irq(evt->irq, 0);
 
 	return 0;
 }
 
-static void  armada_370_xp_timer_stop(struct clock_event_device *evt)
+static void armada_370_xp_timer_stop(struct clock_event_device *evt)
 {
 	evt->set_mode(CLOCK_EVT_MODE_UNUSED, evt);
 	disable_percpu_irq(evt->irq);
 }
 
-static struct local_timer_ops armada_370_xp_local_timer_ops = {
-	.setup	= armada_370_xp_timer_setup,
-	.stop	=  armada_370_xp_timer_stop,
+static int armada_370_xp_timer_cpu_notify(struct notifier_block *self,
+					   unsigned long action, void *hcpu)
+{
+	/*
+	 * Grab cpu pointer in each case to avoid spurious
+	 * preemptible warnings
+	 */
+	switch (action & ~CPU_TASKS_FROZEN) {
+	case CPU_STARTING:
+		armada_370_xp_timer_setup(this_cpu_ptr(armada_370_xp_evt));
+		break;
+	case CPU_DYING:
+		armada_370_xp_timer_stop(this_cpu_ptr(armada_370_xp_evt));
+		break;
+	}
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block armada_370_xp_timer_cpu_nb = {
+	.notifier_call = armada_370_xp_timer_cpu_notify,
 };
 
-void __init armada_370_xp_timer_init(void)
+static void __init armada_370_xp_timer_common_init(struct device_node *np)
 {
-	u32 u;
-	struct device_node *np;
+	u32 clr = 0, set = 0;
 	int res;
 
-	np = of_find_compatible_node(NULL, NULL, "marvell,armada-370-xp-timer");
 	timer_base = of_iomap(np, 0);
 	WARN_ON(!timer_base);
 	local_base = of_iomap(np, 1);
 
-	if (of_find_property(np, "marvell,timer-25Mhz", NULL)) {
-		/* The fixed 25MHz timer is available so let's use it */
-		u = readl(local_base + TIMER_CTRL_OFF);
-		writel(u | TIMER0_25MHZ,
-		       local_base + TIMER_CTRL_OFF);
-		u = readl(timer_base + TIMER_CTRL_OFF);
-		writel(u | TIMER0_25MHZ,
-		       timer_base + TIMER_CTRL_OFF);
-		timer_clk = 25000000;
-	} else {
-		unsigned long rate = 0;
-		struct clk *clk = of_clk_get(np, 0);
-		WARN_ON(IS_ERR(clk));
-		rate =  clk_get_rate(clk);
-		u = readl(local_base + TIMER_CTRL_OFF);
-		writel(u & ~(TIMER0_25MHZ),
-		       local_base + TIMER_CTRL_OFF);
-
-		u = readl(timer_base + TIMER_CTRL_OFF);
-		writel(u & ~(TIMER0_25MHZ),
-		       timer_base + TIMER_CTRL_OFF);
-
-		timer_clk = rate / TIMER_DIVIDER;
-		timer25Mhz = false;
-	}
+	if (timer25Mhz)
+		set = TIMER0_25MHZ;		
+	else
+		clr = TIMER0_25MHZ;
+	timer_ctrl_clrset(clr, set);
+	local_timer_ctrl_clrset(clr, set);
 
 	/*
 	 * We use timer 0 as clocksource, and private(local) timer 0
 	 * for clockevents
 	 */
-	armada_370_xp_clkevt.irq = irq_of_parse_and_map(np, 4);
+	armada_370_xp_clkevt_irq = irq_of_parse_and_map(np, 4);
 
 	ticks_per_jiffy = (timer_clk + HZ / 2) / HZ;
 
@@ -267,35 +267,52 @@ void __init armada_370_xp_timer_init(void)
 	writel(0xffffffff, timer_base + TIMER0_VAL_OFF);
 	writel(0xffffffff, timer_base + TIMER0_RELOAD_OFF);
 
-	u = readl(timer_base + TIMER_CTRL_OFF);
-
-	writel((u | TIMER0_EN | TIMER0_RELOAD_EN |
-		TIMER0_DIV(TIMER_DIVIDER_SHIFT)), timer_base + TIMER_CTRL_OFF);
+	timer_ctrl_clrset(0, TIMER0_EN | TIMER0_RELOAD_EN |
+			     TIMER0_DIV(TIMER_DIVIDER_SHIFT));
 
 	clocksource_mmio_init(timer_base + TIMER0_VAL_OFF,
 			      "armada_370_xp_clocksource",
 			      timer_clk, 300, 32, clocksource_mmio_readl_down);
 
-	/* Register the clockevent on the private timer of CPU 0 */
-	armada_370_xp_clkevt.cpumask = cpumask_of(0);
-	clockevents_config_and_register(&armada_370_xp_clkevt,
-					timer_clk, 1, 0xfffffffe);
+	register_cpu_notifier(&armada_370_xp_timer_cpu_nb);
 
-	percpu_armada_370_xp_evt = alloc_percpu(struct clock_event_device *);
+	armada_370_xp_evt = alloc_percpu(struct clock_event_device);
 
 
 	/*
 	 * Setup clockevent timer (interrupt-driven).
 	 */
-	*__this_cpu_ptr(percpu_armada_370_xp_evt) = &armada_370_xp_clkevt;
-	res = request_percpu_irq(armada_370_xp_clkevt.irq,
+	res = request_percpu_irq(armada_370_xp_clkevt_irq,
 				armada_370_xp_timer_interrupt,
-				armada_370_xp_clkevt.name,
-				percpu_armada_370_xp_evt);
-	if (!res) {
-		enable_percpu_irq(armada_370_xp_clkevt.irq, 0);
-#ifdef CONFIG_LOCAL_TIMERS
-		local_timer_register(&armada_370_xp_local_timer_ops);
-#endif
-	}
+				"armada_370_xp_per_cpu_tick",
+				armada_370_xp_evt);
+	/* Immediately configure the timer on the boot CPU */
+	if (!res)
+		armada_370_xp_timer_setup(this_cpu_ptr(armada_370_xp_evt));
+}
+
+static void __init armada_xp_timer_init(struct device_node *np)
+{
+	struct clk *clk = of_clk_get_by_name(np, "fixed");
+
+	/* The 25Mhz fixed clock is mandatory, and must always be available */
+	BUG_ON(IS_ERR(clk));
+	timer_clk = clk_get_rate(clk);
+
+	armada_370_xp_timer_common_init(np);
+}
+CLOCKSOURCE_OF_DECLARE(armada_xp, "marvell,armada-xp-timer",
+		       armada_xp_timer_init);
+
+static void __init armada_370_timer_init(struct device_node *np)
+{
+	struct clk *clk = of_clk_get(np, 0);
+
+	BUG_ON(IS_ERR(clk));
+	timer_clk = clk_get_rate(clk) / TIMER_DIVIDER;
+	timer25Mhz = false;
+
+	armada_370_xp_timer_common_init(np);
 }
+CLOCKSOURCE_OF_DECLARE(armada_370, "marvell,armada-370-timer",
+		       armada_370_timer_init);
diff --git a/drivers/clocksource/time-orion.c b/drivers/clocksource/time-orion.c
index ecbeb6810215..9c7f018a67ca 100644
--- a/drivers/clocksource/time-orion.c
+++ b/drivers/clocksource/time-orion.c
@@ -19,7 +19,7 @@
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
 #include <linux/spinlock.h>
-#include <asm/sched_clock.h>
+#include <linux/sched_clock.h>
 
 #define TIMER_CTRL		0x00
 #define  TIMER0_EN		BIT(0)
diff --git a/drivers/clocksource/timer-marco.c b/drivers/clocksource/timer-marco.c
index 62876baa3ab9..09a17d9a6594 100644
--- a/drivers/clocksource/timer-marco.c
+++ b/drivers/clocksource/timer-marco.c
@@ -10,6 +10,7 @@
 #include <linux/interrupt.h>
 #include <linux/clockchips.h>
 #include <linux/clocksource.h>
+#include <linux/cpu.h>
 #include <linux/bitops.h>
 #include <linux/irq.h>
 #include <linux/clk.h>
@@ -18,7 +19,6 @@
 #include <linux/of_irq.h>
 #include <linux/of_address.h>
 #include <linux/sched_clock.h>
-#include <asm/localtimer.h>
 #include <asm/mach/time.h>
 
 #define SIRFSOC_TIMER_32COUNTER_0_CTRL			0x0000
@@ -151,13 +151,7 @@ static void sirfsoc_clocksource_resume(struct clocksource *cs)
 		BIT(1) | BIT(0), sirfsoc_timer_base + SIRFSOC_TIMER_64COUNTER_CTRL);
 }
 
-static struct clock_event_device sirfsoc_clockevent = {
-	.name = "sirfsoc_clockevent",
-	.rating = 200,
-	.features = CLOCK_EVT_FEAT_ONESHOT,
-	.set_mode = sirfsoc_timer_set_mode,
-	.set_next_event = sirfsoc_timer_set_next_event,
-};
+static struct clock_event_device __percpu *sirfsoc_clockevent;
 
 static struct clocksource sirfsoc_clocksource = {
 	.name = "sirfsoc_clocksource",
@@ -173,11 +167,8 @@ static struct irqaction sirfsoc_timer_irq = {
 	.name = "sirfsoc_timer0",
 	.flags = IRQF_TIMER | IRQF_NOBALANCING,
 	.handler = sirfsoc_timer_interrupt,
-	.dev_id = &sirfsoc_clockevent,
 };
 
-#ifdef CONFIG_LOCAL_TIMERS
-
 static struct irqaction sirfsoc_timer1_irq = {
 	.name = "sirfsoc_timer1",
 	.flags = IRQF_TIMER | IRQF_NOBALANCING,
@@ -186,24 +177,28 @@ static struct irqaction sirfsoc_timer1_irq = {
 
 static int sirfsoc_local_timer_setup(struct clock_event_device *ce)
 {
-	/* Use existing clock_event for cpu 0 */
-	if (!smp_processor_id())
-		return 0;
+	int cpu = smp_processor_id();
+	struct irqaction *action;
+
+	if (cpu == 0)
+		action = &sirfsoc_timer_irq;
+	else
+		action = &sirfsoc_timer1_irq;
 
-	ce->irq = sirfsoc_timer1_irq.irq;
+	ce->irq = action->irq;
 	ce->name = "local_timer";
-	ce->features = sirfsoc_clockevent.features;
-	ce->rating = sirfsoc_clockevent.rating;
+	ce->features = CLOCK_EVT_FEAT_ONESHOT;
+	ce->rating = 200;
 	ce->set_mode = sirfsoc_timer_set_mode;
 	ce->set_next_event = sirfsoc_timer_set_next_event;
-	ce->shift = sirfsoc_clockevent.shift;
-	ce->mult = sirfsoc_clockevent.mult;
-	ce->max_delta_ns = sirfsoc_clockevent.max_delta_ns;
-	ce->min_delta_ns = sirfsoc_clockevent.min_delta_ns;
+	clockevents_calc_mult_shift(ce, CLOCK_TICK_RATE, 60);
+	ce->max_delta_ns = clockevent_delta2ns(-2, ce);
+	ce->min_delta_ns = clockevent_delta2ns(2, ce);
+	ce->cpumask = cpumask_of(cpu);
 
-	sirfsoc_timer1_irq.dev_id = ce;
-	BUG_ON(setup_irq(ce->irq, &sirfsoc_timer1_irq));
-	irq_set_affinity(sirfsoc_timer1_irq.irq, cpumask_of(1));
+	action->dev_id = ce;
+	BUG_ON(setup_irq(ce->irq, action));
+	irq_set_affinity(action->irq, cpumask_of(cpu));
 
 	clockevents_register_device(ce);
 	return 0;
@@ -211,31 +206,48 @@ static int sirfsoc_local_timer_setup(struct clock_event_device *ce)
 
 static void sirfsoc_local_timer_stop(struct clock_event_device *ce)
 {
+	int cpu = smp_processor_id();
+
 	sirfsoc_timer_count_disable(1);
 
-	remove_irq(sirfsoc_timer1_irq.irq, &sirfsoc_timer1_irq);
+	if (cpu == 0)
+		remove_irq(sirfsoc_timer_irq.irq, &sirfsoc_timer_irq);
+	else
+		remove_irq(sirfsoc_timer1_irq.irq, &sirfsoc_timer1_irq);
 }
 
-static struct local_timer_ops sirfsoc_local_timer_ops = {
-	.setup	= sirfsoc_local_timer_setup,
-	.stop	= sirfsoc_local_timer_stop,
+static int sirfsoc_cpu_notify(struct notifier_block *self,
+			      unsigned long action, void *hcpu)
+{
+	/*
+	 * Grab cpu pointer in each case to avoid spurious
+	 * preemptible warnings
+	 */
+	switch (action & ~CPU_TASKS_FROZEN) {
+	case CPU_STARTING:
+		sirfsoc_local_timer_setup(this_cpu_ptr(sirfsoc_clockevent));
+		break;
+	case CPU_DYING:
+		sirfsoc_local_timer_stop(this_cpu_ptr(sirfsoc_clockevent));
+		break;
+	}
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block sirfsoc_cpu_nb = {
+	.notifier_call = sirfsoc_cpu_notify,
 };
-#endif /* CONFIG_LOCAL_TIMERS */
 
 static void __init sirfsoc_clockevent_init(void)
 {
-	clockevents_calc_mult_shift(&sirfsoc_clockevent, CLOCK_TICK_RATE, 60);
-
-	sirfsoc_clockevent.max_delta_ns =
-		clockevent_delta2ns(-2, &sirfsoc_clockevent);
-	sirfsoc_clockevent.min_delta_ns =
-		clockevent_delta2ns(2, &sirfsoc_clockevent);
-
-	sirfsoc_clockevent.cpumask = cpumask_of(0);
-	clockevents_register_device(&sirfsoc_clockevent);
-#ifdef CONFIG_LOCAL_TIMERS
-	local_timer_register(&sirfsoc_local_timer_ops);
-#endif
+	sirfsoc_clockevent = alloc_percpu(struct clock_event_device);
+	BUG_ON(!sirfsoc_clockevent);
+
+	BUG_ON(register_cpu_notifier(&sirfsoc_cpu_nb));
+
+	/* Immediately configure the timer on the boot CPU */
+	sirfsoc_local_timer_setup(this_cpu_ptr(sirfsoc_clockevent));
 }
 
 /* initialize the kernel jiffy timer source */
@@ -273,8 +285,6 @@ static void __init sirfsoc_marco_timer_init(void)
 
 	BUG_ON(clocksource_register_hz(&sirfsoc_clocksource, CLOCK_TICK_RATE));
 
-	BUG_ON(setup_irq(sirfsoc_timer_irq.irq, &sirfsoc_timer_irq));
-
 	sirfsoc_clockevent_init();
 }
 
@@ -288,11 +298,9 @@ static void __init sirfsoc_of_timer_init(struct device_node *np)
 	if (!sirfsoc_timer_irq.irq)
 		panic("No irq passed for timer0 via DT\n");
 
-#ifdef CONFIG_LOCAL_TIMERS
 	sirfsoc_timer1_irq.irq = irq_of_parse_and_map(np, 1);
 	if (!sirfsoc_timer1_irq.irq)
 		panic("No irq passed for timer1 via DT\n");
-#endif
 
 	sirfsoc_marco_timer_init();
 }
diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm
index de4d5d93c3fd..0fa204b244bd 100644
--- a/drivers/cpufreq/Kconfig.arm
+++ b/drivers/cpufreq/Kconfig.arm
@@ -17,37 +17,47 @@ config ARM_DT_BL_CPUFREQ
 	  big.LITTLE platform. This gets frequency tables from DT.
 
 config ARM_EXYNOS_CPUFREQ
-	bool "SAMSUNG EXYNOS SoCs"
-	depends on ARCH_EXYNOS
+	bool
 	select CPU_FREQ_TABLE
-	default y
-	help
-	  This adds the CPUFreq driver common part for Samsung
-	  EXYNOS SoCs.
-
-	  If in doubt, say N.
 
 config ARM_EXYNOS4210_CPUFREQ
-	def_bool CPU_EXYNOS4210
+	bool "SAMSUNG EXYNOS4210"
+	depends on CPU_EXYNOS4210
+	default y
+	select ARM_EXYNOS_CPUFREQ
 	help
 	  This adds the CPUFreq driver for Samsung EXYNOS4210
 	  SoC (S5PV310 or S5PC210).
 
+	  If in doubt, say N.
+
 config ARM_EXYNOS4X12_CPUFREQ
-	def_bool (SOC_EXYNOS4212 || SOC_EXYNOS4412)
+	bool "SAMSUNG EXYNOS4x12"
+	depends on (SOC_EXYNOS4212 || SOC_EXYNOS4412)
+	default y
+	select ARM_EXYNOS_CPUFREQ
 	help
 	  This adds the CPUFreq driver for Samsung EXYNOS4X12
 	  SoC (EXYNOS4212 or EXYNOS4412).
 
+	  If in doubt, say N.
+
 config ARM_EXYNOS5250_CPUFREQ
-	def_bool SOC_EXYNOS5250
+	bool "SAMSUNG EXYNOS5250"
+	depends on SOC_EXYNOS5250
+	default y
+	select ARM_EXYNOS_CPUFREQ
 	help
 	  This adds the CPUFreq driver for Samsung EXYNOS5250
 	  SoC.
 
+	  If in doubt, say N.
+
 config ARM_EXYNOS5440_CPUFREQ
-	def_bool SOC_EXYNOS5440
+	bool "SAMSUNG EXYNOS5440"
+	depends on SOC_EXYNOS5440
 	depends on HAVE_CLK && PM_OPP && OF
+	default y
 	select CPU_FREQ_TABLE
 	help
 	  This adds the CPUFreq driver for Samsung EXYNOS5440
@@ -55,6 +65,8 @@ config ARM_EXYNOS5440_CPUFREQ
 	  different than previous exynos controllers so not using
 	  the common exynos framework.
 
+	  If in doubt, say N.
+
 config ARM_HIGHBANK_CPUFREQ
 	tristate "Calxeda Highbank-based"
 	depends on ARCH_HIGHBANK
diff --git a/drivers/cpufreq/Makefile b/drivers/cpufreq/Makefile
index d345b5a7aa71..ad5866c2ada0 100644
--- a/drivers/cpufreq/Makefile
+++ b/drivers/cpufreq/Makefile
@@ -23,7 +23,7 @@ obj-$(CONFIG_GENERIC_CPUFREQ_CPU0)	+= cpufreq-cpu0.o
 # powernow-k8 can load then. ACPI is preferred to all other hardware-specific drivers.
 # speedstep-* is preferred over p4-clockmod.
 
-obj-$(CONFIG_X86_ACPI_CPUFREQ)		+= acpi-cpufreq.o mperf.o
+obj-$(CONFIG_X86_ACPI_CPUFREQ)		+= acpi-cpufreq.o
 obj-$(CONFIG_X86_POWERNOW_K8)		+= powernow-k8.o
 obj-$(CONFIG_X86_PCC_CPUFREQ)		+= pcc-cpufreq.o
 obj-$(CONFIG_X86_POWERNOW_K6)		+= powernow-k6.o
diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c
index 39264020b88a..d2c3253e015e 100644
--- a/drivers/cpufreq/acpi-cpufreq.c
+++ b/drivers/cpufreq/acpi-cpufreq.c
@@ -45,7 +45,6 @@
 #include <asm/msr.h>
 #include <asm/processor.h>
 #include <asm/cpufeature.h>
-#include "mperf.h"
 
 MODULE_AUTHOR("Paul Diefenbaugh, Dominik Brodowski");
 MODULE_DESCRIPTION("ACPI Processor P-States Driver");
@@ -198,7 +197,7 @@ static ssize_t show_cpb(struct cpufreq_policy *policy, char *buf)
 	return sprintf(buf, "%u\n", boost_enabled);
 }
 
-static struct freq_attr cpb = __ATTR(cpb, 0644, show_cpb, store_cpb);
+cpufreq_freq_attr_rw(cpb);
 #endif
 
 static int check_est_cpu(unsigned int cpuid)
@@ -710,7 +709,7 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy)
 		return blacklisted;
 #endif
 
-	data = kzalloc(sizeof(struct acpi_cpufreq_data), GFP_KERNEL);
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
 	if (!data)
 		return -ENOMEM;
 
@@ -800,7 +799,7 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy)
 		goto err_unreg;
 	}
 
-	data->freq_table = kmalloc(sizeof(struct cpufreq_frequency_table) *
+	data->freq_table = kmalloc(sizeof(*data->freq_table) *
 		    (perf->state_count+1), GFP_KERNEL);
 	if (!data->freq_table) {
 		result = -ENOMEM;
@@ -861,10 +860,6 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	/* notify BIOS that we exist */
 	acpi_processor_notify_smm(THIS_MODULE);
 
-	/* Check for APERF/MPERF support in hardware */
-	if (boot_cpu_has(X86_FEATURE_APERFMPERF))
-		acpi_cpufreq_driver.getavg = cpufreq_get_measured_perf;
-
 	pr_debug("CPU%u - ACPI performance management activated.\n", cpu);
 	for (i = 0; i < perf->state_count; i++)
 		pr_debug("     %cP%d: %d MHz, %d mW, %d uS\n",
@@ -941,7 +936,6 @@ static struct cpufreq_driver acpi_cpufreq_driver = {
 	.exit		= acpi_cpufreq_cpu_exit,
 	.resume		= acpi_cpufreq_resume,
 	.name		= "acpi-cpufreq",
-	.owner		= THIS_MODULE,
 	.attr		= acpi_cpufreq_attr,
 };
 
@@ -992,6 +986,10 @@ static int __init acpi_cpufreq_init(void)
 {
 	int ret;
 
+	/* don't keep reloading if cpufreq_driver exists */
+	if (cpufreq_get_current_driver())
+		return 0;
+
 	if (acpi_disabled)
 		return 0;
 
diff --git a/drivers/cpufreq/arm_big_little_dt.c b/drivers/cpufreq/arm_big_little_dt.c
index fd9e3ea6a480..480c0bd0468d 100644
--- a/drivers/cpufreq/arm_big_little_dt.c
+++ b/drivers/cpufreq/arm_big_little_dt.c
@@ -19,12 +19,11 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
-#include <linux/cpu.h>
 #include <linux/cpufreq.h>
 #include <linux/device.h>
 #include <linux/export.h>
 #include <linux/module.h>
-#include <linux/of.h>
+#include <linux/of_device.h>
 #include <linux/opp.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
@@ -34,27 +33,13 @@
 /* get cpu node with valid operating-points */
 static struct device_node *get_cpu_node_with_valid_op(int cpu)
 {
-	struct device_node *np = NULL, *parent;
-	int count = 0;
+	struct device_node *np = of_cpu_device_node_get(cpu);
 
-	parent = of_find_node_by_path("/cpus");
-	if (!parent) {
-		pr_err("failed to find OF /cpus\n");
-		return NULL;
+	if (!of_get_property(np, "operating-points", NULL)) {
+		of_node_put(np);
+		np = NULL;
 	}
 
-	for_each_child_of_node(parent, np) {
-		if (count++ != cpu)
-			continue;
-		if (!of_get_property(np, "operating-points", NULL)) {
-			of_node_put(np);
-			np = NULL;
-		}
-
-		break;
-	}
-
-	of_node_put(parent);
 	return np;
 }
 
@@ -63,11 +48,12 @@ static int dt_init_opp_table(struct device *cpu_dev)
 	struct device_node *np;
 	int ret;
 
-	np = get_cpu_node_with_valid_op(cpu_dev->id);
-	if (!np)
-		return -ENODATA;
+	np = of_node_get(cpu_dev->of_node);
+	if (!np) {
+		pr_err("failed to find cpu%d node\n", cpu_dev->id);
+		return -ENOENT;
+	}
 
-	cpu_dev->of_node = np;
 	ret = of_init_opp_table(cpu_dev);
 	of_node_put(np);
 
@@ -79,9 +65,11 @@ static int dt_get_transition_latency(struct device *cpu_dev)
 	struct device_node *np;
 	u32 transition_latency = CPUFREQ_ETERNAL;
 
-	np = get_cpu_node_with_valid_op(cpu_dev->id);
-	if (!np)
+	np = of_node_get(cpu_dev->of_node);
+	if (!np) {
+		pr_info("Failed to find cpu node. Use CPUFREQ_ETERNAL transition latency\n");
 		return CPUFREQ_ETERNAL;
+	}
 
 	of_property_read_u32(np, "clock-latency", &transition_latency);
 	of_node_put(np);
diff --git a/drivers/cpufreq/at32ap-cpufreq.c b/drivers/cpufreq/at32ap-cpufreq.c
index 654488723cb5..e0c38d938997 100644
--- a/drivers/cpufreq/at32ap-cpufreq.c
+++ b/drivers/cpufreq/at32ap-cpufreq.c
@@ -108,7 +108,6 @@ static int __init at32_cpufreq_driver_init(struct cpufreq_policy *policy)
 
 static struct cpufreq_driver at32_driver = {
 	.name		= "at32ap",
-	.owner		= THIS_MODULE,
 	.init		= at32_cpufreq_driver_init,
 	.verify		= at32_verify_speed,
 	.target		= at32_set_target,
diff --git a/drivers/cpufreq/blackfin-cpufreq.c b/drivers/cpufreq/blackfin-cpufreq.c
index 9cdbbd278a80..ef05978a7237 100644
--- a/drivers/cpufreq/blackfin-cpufreq.c
+++ b/drivers/cpufreq/blackfin-cpufreq.c
@@ -225,7 +225,6 @@ static struct cpufreq_driver bfin_driver = {
 	.get = bfin_getfreq_khz,
 	.init = __bfin_cpu_init,
 	.name = "bfin cpufreq",
-	.owner = THIS_MODULE,
 	.attr = bfin_freq_attr,
 };
 
diff --git a/drivers/cpufreq/cpufreq-cpu0.c b/drivers/cpufreq/cpufreq-cpu0.c
index ad1fde277661..c522a95c0e16 100644
--- a/drivers/cpufreq/cpufreq-cpu0.c
+++ b/drivers/cpufreq/cpufreq-cpu0.c
@@ -12,6 +12,7 @@
 #define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
 
 #include <linux/clk.h>
+#include <linux/cpu.h>
 #include <linux/cpufreq.h>
 #include <linux/err.h>
 #include <linux/module.h>
@@ -69,7 +70,7 @@ static int cpu0_set_target(struct cpufreq_policy *policy,
 
 	cpufreq_notify_transition(policy, &freqs, CPUFREQ_PRECHANGE);
 
-	if (cpu_reg) {
+	if (!IS_ERR(cpu_reg)) {
 		rcu_read_lock();
 		opp = opp_find_freq_ceil(cpu_dev, &freq_Hz);
 		if (IS_ERR(opp)) {
@@ -90,7 +91,7 @@ static int cpu0_set_target(struct cpufreq_policy *policy,
 		 freqs.new / 1000, volt ? volt / 1000 : -1);
 
 	/* scaling up?  scale voltage before frequency */
-	if (cpu_reg && freqs.new > freqs.old) {
+	if (!IS_ERR(cpu_reg) && freqs.new > freqs.old) {
 		ret = regulator_set_voltage_tol(cpu_reg, volt, tol);
 		if (ret) {
 			pr_err("failed to scale voltage up: %d\n", ret);
@@ -102,14 +103,14 @@ static int cpu0_set_target(struct cpufreq_policy *policy,
 	ret = clk_set_rate(cpu_clk, freq_exact);
 	if (ret) {
 		pr_err("failed to set clock rate: %d\n", ret);
-		if (cpu_reg)
+		if (!IS_ERR(cpu_reg))
 			regulator_set_voltage_tol(cpu_reg, volt_old, tol);
 		freqs.new = freqs.old;
 		goto post_notify;
 	}
 
 	/* scaling down?  scale voltage after frequency */
-	if (cpu_reg && freqs.new < freqs.old) {
+	if (!IS_ERR(cpu_reg) && freqs.new < freqs.old) {
 		ret = regulator_set_voltage_tol(cpu_reg, volt, tol);
 		if (ret) {
 			pr_err("failed to scale voltage down: %d\n", ret);
@@ -174,30 +175,22 @@ static struct cpufreq_driver cpu0_cpufreq_driver = {
 
 static int cpu0_cpufreq_probe(struct platform_device *pdev)
 {
-	struct device_node *np, *parent;
+	struct device_node *np;
 	int ret;
 
-	parent = of_find_node_by_path("/cpus");
-	if (!parent) {
-		pr_err("failed to find OF /cpus\n");
-		return -ENOENT;
-	}
-
-	for_each_child_of_node(parent, np) {
-		if (of_get_property(np, "operating-points", NULL))
-			break;
+	cpu_dev = get_cpu_device(0);
+	if (!cpu_dev) {
+		pr_err("failed to get cpu0 device\n");
+		return -ENODEV;
 	}
 
+	np = of_node_get(cpu_dev->of_node);
 	if (!np) {
 		pr_err("failed to find cpu0 node\n");
-		ret = -ENOENT;
-		goto out_put_parent;
+		return -ENOENT;
 	}
 
-	cpu_dev = &pdev->dev;
-	cpu_dev->of_node = np;
-
-	cpu_reg = devm_regulator_get(cpu_dev, "cpu0");
+	cpu_reg = devm_regulator_get_optional(cpu_dev, "cpu0");
 	if (IS_ERR(cpu_reg)) {
 		/*
 		 * If cpu0 regulator supply node is present, but regulator is
@@ -210,7 +203,6 @@ static int cpu0_cpufreq_probe(struct platform_device *pdev)
 		}
 		pr_warn("failed to get cpu0 regulator: %ld\n",
 			PTR_ERR(cpu_reg));
-		cpu_reg = NULL;
 	}
 
 	cpu_clk = devm_clk_get(cpu_dev, NULL);
@@ -237,7 +229,7 @@ static int cpu0_cpufreq_probe(struct platform_device *pdev)
 	if (of_property_read_u32(np, "clock-latency", &transition_latency))
 		transition_latency = CPUFREQ_ETERNAL;
 
-	if (cpu_reg) {
+	if (!IS_ERR(cpu_reg)) {
 		struct opp *opp;
 		unsigned long min_uV, max_uV;
 		int i;
@@ -269,15 +261,12 @@ static int cpu0_cpufreq_probe(struct platform_device *pdev)
 	}
 
 	of_node_put(np);
-	of_node_put(parent);
 	return 0;
 
 out_free_table:
 	opp_free_cpufreq_table(cpu_dev, &freq_table);
 out_put_node:
 	of_node_put(np);
-out_put_parent:
-	of_node_put(parent);
 	return ret;
 }
 
diff --git a/drivers/cpufreq/cpufreq-nforce2.c b/drivers/cpufreq/cpufreq-nforce2.c
index af1542d41440..b83d45f68574 100644
--- a/drivers/cpufreq/cpufreq-nforce2.c
+++ b/drivers/cpufreq/cpufreq-nforce2.c
@@ -379,7 +379,6 @@ static struct cpufreq_driver nforce2_driver = {
 	.get = nforce2_get,
 	.init = nforce2_cpu_init,
 	.exit = nforce2_cpu_exit,
-	.owner = THIS_MODULE,
 };
 
 #ifdef MODULE
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index f0a5e2b0eb8a..04548f7023af 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -17,24 +17,17 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
-#include <asm/cputime.h>
-#include <linux/kernel.h>
-#include <linux/kernel_stat.h>
-#include <linux/module.h>
-#include <linux/init.h>
-#include <linux/notifier.h>
+#include <linux/cpu.h>
 #include <linux/cpufreq.h>
 #include <linux/delay.h>
-#include <linux/interrupt.h>
-#include <linux/spinlock.h>
-#include <linux/tick.h>
 #include <linux/device.h>
-#include <linux/slab.h>
-#include <linux/cpu.h>
-#include <linux/completion.h>
+#include <linux/init.h>
+#include <linux/kernel_stat.h>
+#include <linux/module.h>
 #include <linux/mutex.h>
+#include <linux/slab.h>
 #include <linux/syscore_ops.h>
-
+#include <linux/tick.h>
 #include <trace/events/power.h>
 
 /**
@@ -44,8 +37,10 @@
  */
 static struct cpufreq_driver *cpufreq_driver;
 static DEFINE_PER_CPU(struct cpufreq_policy *, cpufreq_cpu_data);
+static DEFINE_PER_CPU(struct cpufreq_policy *, cpufreq_cpu_data_fallback);
 static DEFINE_RWLOCK(cpufreq_driver_lock);
 static DEFINE_MUTEX(cpufreq_governor_lock);
+static LIST_HEAD(cpufreq_policy_list);
 
 #ifdef CONFIG_HOTPLUG_CPU
 /* This one keeps track of the previously set governor of a removed CPU */
@@ -69,15 +64,14 @@ static DEFINE_PER_CPU(char[CPUFREQ_NAME_LEN], cpufreq_cpu_governor);
  * - Lock should not be held across
  *     __cpufreq_governor(data, CPUFREQ_GOV_STOP);
  */
-static DEFINE_PER_CPU(int, cpufreq_policy_cpu);
 static DEFINE_PER_CPU(struct rw_semaphore, cpu_policy_rwsem);
 
 #define lock_policy_rwsem(mode, cpu)					\
 static int lock_policy_rwsem_##mode(int cpu)				\
 {									\
-	int policy_cpu = per_cpu(cpufreq_policy_cpu, cpu);		\
-	BUG_ON(policy_cpu == -1);					\
-	down_##mode(&per_cpu(cpu_policy_rwsem, policy_cpu));		\
+	struct cpufreq_policy *policy = per_cpu(cpufreq_cpu_data, cpu);	\
+	BUG_ON(!policy);						\
+	down_##mode(&per_cpu(cpu_policy_rwsem, policy->cpu));		\
 									\
 	return 0;							\
 }
@@ -88,14 +82,20 @@ lock_policy_rwsem(write, cpu);
 #define unlock_policy_rwsem(mode, cpu)					\
 static void unlock_policy_rwsem_##mode(int cpu)				\
 {									\
-	int policy_cpu = per_cpu(cpufreq_policy_cpu, cpu);		\
-	BUG_ON(policy_cpu == -1);					\
-	up_##mode(&per_cpu(cpu_policy_rwsem, policy_cpu));		\
+	struct cpufreq_policy *policy = per_cpu(cpufreq_cpu_data, cpu);	\
+	BUG_ON(!policy);						\
+	up_##mode(&per_cpu(cpu_policy_rwsem, policy->cpu));		\
 }
 
 unlock_policy_rwsem(read, cpu);
 unlock_policy_rwsem(write, cpu);
 
+/*
+ * rwsem to guarantee that cpufreq driver module doesn't unload during critical
+ * sections
+ */
+static DECLARE_RWSEM(cpufreq_rwsem);
+
 /* internal prototypes */
 static int __cpufreq_governor(struct cpufreq_policy *policy,
 		unsigned int event);
@@ -183,78 +183,46 @@ u64 get_cpu_idle_time(unsigned int cpu, u64 *wall, int io_busy)
 }
 EXPORT_SYMBOL_GPL(get_cpu_idle_time);
 
-static struct cpufreq_policy *__cpufreq_cpu_get(unsigned int cpu, bool sysfs)
+struct cpufreq_policy *cpufreq_cpu_get(unsigned int cpu)
 {
-	struct cpufreq_policy *data;
+	struct cpufreq_policy *policy = NULL;
 	unsigned long flags;
 
-	if (cpu >= nr_cpu_ids)
-		goto err_out;
+	if (cpufreq_disabled() || (cpu >= nr_cpu_ids))
+		return NULL;
+
+	if (!down_read_trylock(&cpufreq_rwsem))
+		return NULL;
 
 	/* get the cpufreq driver */
 	read_lock_irqsave(&cpufreq_driver_lock, flags);
 
-	if (!cpufreq_driver)
-		goto err_out_unlock;
-
-	if (!try_module_get(cpufreq_driver->owner))
-		goto err_out_unlock;
-
-	/* get the CPU */
-	data = per_cpu(cpufreq_cpu_data, cpu);
-
-	if (!data)
-		goto err_out_put_module;
-
-	if (!sysfs && !kobject_get(&data->kobj))
-		goto err_out_put_module;
-
-	read_unlock_irqrestore(&cpufreq_driver_lock, flags);
-	return data;
+	if (cpufreq_driver) {
+		/* get the CPU */
+		policy = per_cpu(cpufreq_cpu_data, cpu);
+		if (policy)
+			kobject_get(&policy->kobj);
+	}
 
-err_out_put_module:
-	module_put(cpufreq_driver->owner);
-err_out_unlock:
 	read_unlock_irqrestore(&cpufreq_driver_lock, flags);
-err_out:
-	return NULL;
-}
 
-struct cpufreq_policy *cpufreq_cpu_get(unsigned int cpu)
-{
-	if (cpufreq_disabled())
-		return NULL;
+	if (!policy)
+		up_read(&cpufreq_rwsem);
 
-	return __cpufreq_cpu_get(cpu, false);
+	return policy;
 }
 EXPORT_SYMBOL_GPL(cpufreq_cpu_get);
 
-static struct cpufreq_policy *cpufreq_cpu_get_sysfs(unsigned int cpu)
-{
-	return __cpufreq_cpu_get(cpu, true);
-}
-
-static void __cpufreq_cpu_put(struct cpufreq_policy *data, bool sysfs)
-{
-	if (!sysfs)
-		kobject_put(&data->kobj);
-	module_put(cpufreq_driver->owner);
-}
-
-void cpufreq_cpu_put(struct cpufreq_policy *data)
+void cpufreq_cpu_put(struct cpufreq_policy *policy)
 {
 	if (cpufreq_disabled())
 		return;
 
-	__cpufreq_cpu_put(data, false);
+	kobject_put(&policy->kobj);
+	up_read(&cpufreq_rwsem);
 }
 EXPORT_SYMBOL_GPL(cpufreq_cpu_put);
 
-static void cpufreq_cpu_put_sysfs(struct cpufreq_policy *data)
-{
-	__cpufreq_cpu_put(data, true);
-}
-
 /*********************************************************************
  *            EXTERNALLY AFFECTING FREQUENCY CHANGES                 *
  *********************************************************************/
@@ -312,13 +280,6 @@ static void __cpufreq_notify_transition(struct cpufreq_policy *policy,
 	switch (state) {
 
 	case CPUFREQ_PRECHANGE:
-		if (WARN(policy->transition_ongoing ==
-					cpumask_weight(policy->cpus),
-				"In middle of another frequency transition\n"))
-			return;
-
-		policy->transition_ongoing++;
-
 		/* detect if the driver reported a value as "old frequency"
 		 * which is not equal to what the cpufreq core thinks is
 		 * "old frequency".
@@ -338,12 +299,6 @@ static void __cpufreq_notify_transition(struct cpufreq_policy *policy,
 		break;
 
 	case CPUFREQ_POSTCHANGE:
-		if (WARN(!policy->transition_ongoing,
-				"No frequency transition in progress\n"))
-			return;
-
-		policy->transition_ongoing--;
-
 		adjust_jiffies(CPUFREQ_POSTCHANGE, freqs);
 		pr_debug("FREQ: %lu - CPU: %lu", (unsigned long)freqs->new,
 			(unsigned long)freqs->cpu);
@@ -459,8 +414,8 @@ show_one(scaling_min_freq, min);
 show_one(scaling_max_freq, max);
 show_one(scaling_cur_freq, cur);
 
-static int __cpufreq_set_policy(struct cpufreq_policy *data,
-				struct cpufreq_policy *policy);
+static int __cpufreq_set_policy(struct cpufreq_policy *policy,
+				struct cpufreq_policy *new_policy);
 
 /**
  * cpufreq_per_cpu_attr_write() / store_##file_name() - sysfs write access
@@ -469,7 +424,7 @@ static int __cpufreq_set_policy(struct cpufreq_policy *data,
 static ssize_t store_##file_name					\
 (struct cpufreq_policy *policy, const char *buf, size_t count)		\
 {									\
-	unsigned int ret;						\
+	int ret;							\
 	struct cpufreq_policy new_policy;				\
 									\
 	ret = cpufreq_get_policy(&new_policy, policy->cpu);		\
@@ -522,7 +477,7 @@ static ssize_t show_scaling_governor(struct cpufreq_policy *policy, char *buf)
 static ssize_t store_scaling_governor(struct cpufreq_policy *policy,
 					const char *buf, size_t count)
 {
-	unsigned int ret;
+	int ret;
 	char	str_governor[16];
 	struct cpufreq_policy new_policy;
 
@@ -699,12 +654,12 @@ static ssize_t show(struct kobject *kobj, struct attribute *attr, char *buf)
 	struct cpufreq_policy *policy = to_policy(kobj);
 	struct freq_attr *fattr = to_attr(attr);
 	ssize_t ret = -EINVAL;
-	policy = cpufreq_cpu_get_sysfs(policy->cpu);
-	if (!policy)
-		goto no_policy;
+
+	if (!down_read_trylock(&cpufreq_rwsem))
+		goto exit;
 
 	if (lock_policy_rwsem_read(policy->cpu) < 0)
-		goto fail;
+		goto up_read;
 
 	if (fattr->show)
 		ret = fattr->show(policy, buf);
@@ -712,9 +667,10 @@ static ssize_t show(struct kobject *kobj, struct attribute *attr, char *buf)
 		ret = -EIO;
 
 	unlock_policy_rwsem_read(policy->cpu);
-fail:
-	cpufreq_cpu_put_sysfs(policy);
-no_policy:
+
+up_read:
+	up_read(&cpufreq_rwsem);
+exit:
 	return ret;
 }
 
@@ -724,12 +680,17 @@ static ssize_t store(struct kobject *kobj, struct attribute *attr,
 	struct cpufreq_policy *policy = to_policy(kobj);
 	struct freq_attr *fattr = to_attr(attr);
 	ssize_t ret = -EINVAL;
-	policy = cpufreq_cpu_get_sysfs(policy->cpu);
-	if (!policy)
-		goto no_policy;
+
+	get_online_cpus();
+
+	if (!cpu_online(policy->cpu))
+		goto unlock;
+
+	if (!down_read_trylock(&cpufreq_rwsem))
+		goto unlock;
 
 	if (lock_policy_rwsem_write(policy->cpu) < 0)
-		goto fail;
+		goto up_read;
 
 	if (fattr->store)
 		ret = fattr->store(policy, buf, count);
@@ -737,9 +698,12 @@ static ssize_t store(struct kobject *kobj, struct attribute *attr,
 		ret = -EIO;
 
 	unlock_policy_rwsem_write(policy->cpu);
-fail:
-	cpufreq_cpu_put_sysfs(policy);
-no_policy:
+
+up_read:
+	up_read(&cpufreq_rwsem);
+unlock:
+	put_online_cpus();
+
 	return ret;
 }
 
@@ -805,41 +769,32 @@ void cpufreq_sysfs_remove_file(const struct attribute *attr)
 EXPORT_SYMBOL(cpufreq_sysfs_remove_file);
 
 /* symlink affected CPUs */
-static int cpufreq_add_dev_symlink(unsigned int cpu,
-				   struct cpufreq_policy *policy)
+static int cpufreq_add_dev_symlink(struct cpufreq_policy *policy)
 {
 	unsigned int j;
 	int ret = 0;
 
 	for_each_cpu(j, policy->cpus) {
-		struct cpufreq_policy *managed_policy;
 		struct device *cpu_dev;
 
-		if (j == cpu)
+		if (j == policy->cpu)
 			continue;
 
-		pr_debug("CPU %u already managed, adding link\n", j);
-		managed_policy = cpufreq_cpu_get(cpu);
+		pr_debug("Adding link for CPU: %u\n", j);
 		cpu_dev = get_cpu_device(j);
 		ret = sysfs_create_link(&cpu_dev->kobj, &policy->kobj,
 					"cpufreq");
-		if (ret) {
-			cpufreq_cpu_put(managed_policy);
-			return ret;
-		}
+		if (ret)
+			break;
 	}
 	return ret;
 }
 
-static int cpufreq_add_dev_interface(unsigned int cpu,
-				     struct cpufreq_policy *policy,
+static int cpufreq_add_dev_interface(struct cpufreq_policy *policy,
 				     struct device *dev)
 {
-	struct cpufreq_policy new_policy;
 	struct freq_attr **drv_attr;
-	unsigned long flags;
 	int ret = 0;
-	unsigned int j;
 
 	/* prepare interface data */
 	ret = kobject_init_and_add(&policy->kobj, &ktype_cpufreq,
@@ -871,18 +826,24 @@ static int cpufreq_add_dev_interface(unsigned int cpu,
 			goto err_out_kobj_put;
 	}
 
-	write_lock_irqsave(&cpufreq_driver_lock, flags);
-	for_each_cpu(j, policy->cpus) {
-		per_cpu(cpufreq_cpu_data, j) = policy;
-		per_cpu(cpufreq_policy_cpu, j) = policy->cpu;
-	}
-	write_unlock_irqrestore(&cpufreq_driver_lock, flags);
-
-	ret = cpufreq_add_dev_symlink(cpu, policy);
+	ret = cpufreq_add_dev_symlink(policy);
 	if (ret)
 		goto err_out_kobj_put;
 
-	memcpy(&new_policy, policy, sizeof(struct cpufreq_policy));
+	return ret;
+
+err_out_kobj_put:
+	kobject_put(&policy->kobj);
+	wait_for_completion(&policy->kobj_unregister);
+	return ret;
+}
+
+static void cpufreq_init_policy(struct cpufreq_policy *policy)
+{
+	struct cpufreq_policy new_policy;
+	int ret = 0;
+
+	memcpy(&new_policy, policy, sizeof(*policy));
 	/* assure that the starting sequence is run in __cpufreq_set_policy */
 	policy->governor = NULL;
 
@@ -896,72 +857,132 @@ static int cpufreq_add_dev_interface(unsigned int cpu,
 		if (cpufreq_driver->exit)
 			cpufreq_driver->exit(policy);
 	}
-	return ret;
-
-err_out_kobj_put:
-	kobject_put(&policy->kobj);
-	wait_for_completion(&policy->kobj_unregister);
-	return ret;
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
-static int cpufreq_add_policy_cpu(unsigned int cpu, unsigned int sibling,
-				  struct device *dev)
+static int cpufreq_add_policy_cpu(struct cpufreq_policy *policy,
+				  unsigned int cpu, struct device *dev,
+				  bool frozen)
 {
-	struct cpufreq_policy *policy;
 	int ret = 0, has_target = !!cpufreq_driver->target;
 	unsigned long flags;
 
-	policy = cpufreq_cpu_get(sibling);
-	WARN_ON(!policy);
-
-	if (has_target)
-		__cpufreq_governor(policy, CPUFREQ_GOV_STOP);
+	if (has_target) {
+		ret = __cpufreq_governor(policy, CPUFREQ_GOV_STOP);
+		if (ret) {
+			pr_err("%s: Failed to stop governor\n", __func__);
+			return ret;
+		}
+	}
 
-	lock_policy_rwsem_write(sibling);
+	lock_policy_rwsem_write(policy->cpu);
 
 	write_lock_irqsave(&cpufreq_driver_lock, flags);
 
 	cpumask_set_cpu(cpu, policy->cpus);
-	per_cpu(cpufreq_policy_cpu, cpu) = policy->cpu;
 	per_cpu(cpufreq_cpu_data, cpu) = policy;
 	write_unlock_irqrestore(&cpufreq_driver_lock, flags);
 
-	unlock_policy_rwsem_write(sibling);
+	unlock_policy_rwsem_write(policy->cpu);
 
 	if (has_target) {
-		__cpufreq_governor(policy, CPUFREQ_GOV_START);
-		__cpufreq_governor(policy, CPUFREQ_GOV_LIMITS);
+		if ((ret = __cpufreq_governor(policy, CPUFREQ_GOV_START)) ||
+			(ret = __cpufreq_governor(policy, CPUFREQ_GOV_LIMITS))) {
+			pr_err("%s: Failed to start governor\n", __func__);
+			return ret;
+		}
 	}
 
-	ret = sysfs_create_link(&dev->kobj, &policy->kobj, "cpufreq");
-	if (ret) {
-		cpufreq_cpu_put(policy);
-		return ret;
-	}
+	/* Don't touch sysfs links during light-weight init */
+	if (!frozen)
+		ret = sysfs_create_link(&dev->kobj, &policy->kobj, "cpufreq");
 
-	return 0;
+	return ret;
 }
 #endif
 
-/**
- * cpufreq_add_dev - add a CPU device
- *
- * Adds the cpufreq interface for a CPU device.
- *
- * The Oracle says: try running cpufreq registration/unregistration concurrently
- * with with cpu hotplugging and all hell will break loose. Tried to clean this
- * mess up, but more thorough testing is needed. - Mathieu
- */
-static int cpufreq_add_dev(struct device *dev, struct subsys_interface *sif)
+static struct cpufreq_policy *cpufreq_policy_restore(unsigned int cpu)
+{
+	struct cpufreq_policy *policy;
+	unsigned long flags;
+
+	read_lock_irqsave(&cpufreq_driver_lock, flags);
+
+	policy = per_cpu(cpufreq_cpu_data_fallback, cpu);
+
+	read_unlock_irqrestore(&cpufreq_driver_lock, flags);
+
+	return policy;
+}
+
+static struct cpufreq_policy *cpufreq_policy_alloc(void)
+{
+	struct cpufreq_policy *policy;
+
+	policy = kzalloc(sizeof(*policy), GFP_KERNEL);
+	if (!policy)
+		return NULL;
+
+	if (!alloc_cpumask_var(&policy->cpus, GFP_KERNEL))
+		goto err_free_policy;
+
+	if (!zalloc_cpumask_var(&policy->related_cpus, GFP_KERNEL))
+		goto err_free_cpumask;
+
+	INIT_LIST_HEAD(&policy->policy_list);
+	return policy;
+
+err_free_cpumask:
+	free_cpumask_var(policy->cpus);
+err_free_policy:
+	kfree(policy);
+
+	return NULL;
+}
+
+static void cpufreq_policy_free(struct cpufreq_policy *policy)
+{
+	free_cpumask_var(policy->related_cpus);
+	free_cpumask_var(policy->cpus);
+	kfree(policy);
+}
+
+static void update_policy_cpu(struct cpufreq_policy *policy, unsigned int cpu)
+{
+	if (cpu == policy->cpu)
+		return;
+
+	/*
+	 * Take direct locks as lock_policy_rwsem_write wouldn't work here.
+	 * Also lock for last cpu is enough here as contention will happen only
+	 * after policy->cpu is changed and after it is changed, other threads
+	 * will try to acquire lock for new cpu. And policy is already updated
+	 * by then.
+	 */
+	down_write(&per_cpu(cpu_policy_rwsem, policy->cpu));
+
+	policy->last_cpu = policy->cpu;
+	policy->cpu = cpu;
+
+	up_write(&per_cpu(cpu_policy_rwsem, policy->last_cpu));
+
+#ifdef CONFIG_CPU_FREQ_TABLE
+	cpufreq_frequency_table_update_policy_cpu(policy);
+#endif
+	blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
+			CPUFREQ_UPDATE_POLICY_CPU, policy);
+}
+
+static int __cpufreq_add_dev(struct device *dev, struct subsys_interface *sif,
+			     bool frozen)
 {
 	unsigned int j, cpu = dev->id;
 	int ret = -ENOMEM;
 	struct cpufreq_policy *policy;
 	unsigned long flags;
 #ifdef CONFIG_HOTPLUG_CPU
+	struct cpufreq_policy *tpolicy;
 	struct cpufreq_governor *gov;
-	int sibling;
 #endif
 
 	if (cpu_is_offline(cpu))
@@ -977,43 +998,49 @@ static int cpufreq_add_dev(struct device *dev, struct subsys_interface *sif)
 		cpufreq_cpu_put(policy);
 		return 0;
 	}
+#endif
+
+	if (!down_read_trylock(&cpufreq_rwsem))
+		return 0;
 
 #ifdef CONFIG_HOTPLUG_CPU
 	/* Check if this cpu was hot-unplugged earlier and has siblings */
 	read_lock_irqsave(&cpufreq_driver_lock, flags);
-	for_each_online_cpu(sibling) {
-		struct cpufreq_policy *cp = per_cpu(cpufreq_cpu_data, sibling);
-		if (cp && cpumask_test_cpu(cpu, cp->related_cpus)) {
+	list_for_each_entry(tpolicy, &cpufreq_policy_list, policy_list) {
+		if (cpumask_test_cpu(cpu, tpolicy->related_cpus)) {
 			read_unlock_irqrestore(&cpufreq_driver_lock, flags);
-			return cpufreq_add_policy_cpu(cpu, sibling, dev);
+			ret = cpufreq_add_policy_cpu(tpolicy, cpu, dev, frozen);
+			up_read(&cpufreq_rwsem);
+			return ret;
 		}
 	}
 	read_unlock_irqrestore(&cpufreq_driver_lock, flags);
 #endif
-#endif
 
-	if (!try_module_get(cpufreq_driver->owner)) {
-		ret = -EINVAL;
-		goto module_out;
-	}
+	if (frozen)
+		/* Restore the saved policy when doing light-weight init */
+		policy = cpufreq_policy_restore(cpu);
+	else
+		policy = cpufreq_policy_alloc();
 
-	policy = kzalloc(sizeof(struct cpufreq_policy), GFP_KERNEL);
 	if (!policy)
 		goto nomem_out;
 
-	if (!alloc_cpumask_var(&policy->cpus, GFP_KERNEL))
-		goto err_free_policy;
 
-	if (!zalloc_cpumask_var(&policy->related_cpus, GFP_KERNEL))
-		goto err_free_cpumask;
+	/*
+	 * In the resume path, since we restore a saved policy, the assignment
+	 * to policy->cpu is like an update of the existing policy, rather than
+	 * the creation of a brand new one. So we need to perform this update
+	 * by invoking update_policy_cpu().
+	 */
+	if (frozen && cpu != policy->cpu)
+		update_policy_cpu(policy, cpu);
+	else
+		policy->cpu = cpu;
 
-	policy->cpu = cpu;
 	policy->governor = CPUFREQ_DEFAULT_GOVERNOR;
 	cpumask_copy(policy->cpus, cpumask_of(cpu));
 
-	/* Initially set CPU itself as the policy_cpu */
-	per_cpu(cpufreq_policy_cpu, cpu) = cpu;
-
 	init_completion(&policy->kobj_unregister);
 	INIT_WORK(&policy->update, handle_update);
 
@@ -1050,12 +1077,26 @@ static int cpufreq_add_dev(struct device *dev, struct subsys_interface *sif)
 	}
 #endif
 
-	ret = cpufreq_add_dev_interface(cpu, policy, dev);
-	if (ret)
-		goto err_out_unregister;
+	write_lock_irqsave(&cpufreq_driver_lock, flags);
+	for_each_cpu(j, policy->cpus)
+		per_cpu(cpufreq_cpu_data, j) = policy;
+	write_unlock_irqrestore(&cpufreq_driver_lock, flags);
+
+	if (!frozen) {
+		ret = cpufreq_add_dev_interface(policy, dev);
+		if (ret)
+			goto err_out_unregister;
+	}
+
+	write_lock_irqsave(&cpufreq_driver_lock, flags);
+	list_add(&policy->policy_list, &cpufreq_policy_list);
+	write_unlock_irqrestore(&cpufreq_driver_lock, flags);
+
+	cpufreq_init_policy(policy);
 
 	kobject_uevent(&policy->kobj, KOBJ_ADD);
-	module_put(cpufreq_driver->owner);
+	up_read(&cpufreq_rwsem);
+
 	pr_debug("initialization complete\n");
 
 	return 0;
@@ -1066,155 +1107,229 @@ err_out_unregister:
 		per_cpu(cpufreq_cpu_data, j) = NULL;
 	write_unlock_irqrestore(&cpufreq_driver_lock, flags);
 
-	kobject_put(&policy->kobj);
-	wait_for_completion(&policy->kobj_unregister);
-
 err_set_policy_cpu:
-	per_cpu(cpufreq_policy_cpu, cpu) = -1;
-	free_cpumask_var(policy->related_cpus);
-err_free_cpumask:
-	free_cpumask_var(policy->cpus);
-err_free_policy:
-	kfree(policy);
+	cpufreq_policy_free(policy);
 nomem_out:
-	module_put(cpufreq_driver->owner);
-module_out:
+	up_read(&cpufreq_rwsem);
+
 	return ret;
 }
 
-static void update_policy_cpu(struct cpufreq_policy *policy, unsigned int cpu)
+/**
+ * cpufreq_add_dev - add a CPU device
+ *
+ * Adds the cpufreq interface for a CPU device.
+ *
+ * The Oracle says: try running cpufreq registration/unregistration concurrently
+ * with with cpu hotplugging and all hell will break loose. Tried to clean this
+ * mess up, but more thorough testing is needed. - Mathieu
+ */
+static int cpufreq_add_dev(struct device *dev, struct subsys_interface *sif)
 {
-	int j;
+	return __cpufreq_add_dev(dev, sif, false);
+}
 
-	policy->last_cpu = policy->cpu;
-	policy->cpu = cpu;
+static int cpufreq_nominate_new_policy_cpu(struct cpufreq_policy *policy,
+					   unsigned int old_cpu, bool frozen)
+{
+	struct device *cpu_dev;
+	int ret;
 
-	for_each_cpu(j, policy->cpus)
-		per_cpu(cpufreq_policy_cpu, j) = cpu;
+	/* first sibling now owns the new sysfs dir */
+	cpu_dev = get_cpu_device(cpumask_any_but(policy->cpus, old_cpu));
 
-#ifdef CONFIG_CPU_FREQ_TABLE
-	cpufreq_frequency_table_update_policy_cpu(policy);
-#endif
-	blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
-			CPUFREQ_UPDATE_POLICY_CPU, policy);
+	/* Don't touch sysfs files during light-weight tear-down */
+	if (frozen)
+		return cpu_dev->id;
+
+	sysfs_remove_link(&cpu_dev->kobj, "cpufreq");
+	ret = kobject_move(&policy->kobj, &cpu_dev->kobj);
+	if (ret) {
+		pr_err("%s: Failed to move kobj: %d", __func__, ret);
+
+		WARN_ON(lock_policy_rwsem_write(old_cpu));
+		cpumask_set_cpu(old_cpu, policy->cpus);
+		unlock_policy_rwsem_write(old_cpu);
+
+		ret = sysfs_create_link(&cpu_dev->kobj, &policy->kobj,
+					"cpufreq");
+
+		return -EINVAL;
+	}
+
+	return cpu_dev->id;
 }
 
-/**
- * __cpufreq_remove_dev - remove a CPU device
- *
- * Removes the cpufreq interface for a CPU device.
- * Caller should already have policy_rwsem in write mode for this CPU.
- * This routine frees the rwsem before returning.
- */
-static int __cpufreq_remove_dev(struct device *dev,
-		struct subsys_interface *sif)
+static int __cpufreq_remove_dev_prepare(struct device *dev,
+					struct subsys_interface *sif,
+					bool frozen)
 {
-	unsigned int cpu = dev->id, ret, cpus;
+	unsigned int cpu = dev->id, cpus;
+	int new_cpu, ret;
 	unsigned long flags;
-	struct cpufreq_policy *data;
-	struct kobject *kobj;
-	struct completion *cmp;
-	struct device *cpu_dev;
+	struct cpufreq_policy *policy;
 
 	pr_debug("%s: unregistering CPU %u\n", __func__, cpu);
 
 	write_lock_irqsave(&cpufreq_driver_lock, flags);
 
-	data = per_cpu(cpufreq_cpu_data, cpu);
-	per_cpu(cpufreq_cpu_data, cpu) = NULL;
+	policy = per_cpu(cpufreq_cpu_data, cpu);
+
+	/* Save the policy somewhere when doing a light-weight tear-down */
+	if (frozen)
+		per_cpu(cpufreq_cpu_data_fallback, cpu) = policy;
 
 	write_unlock_irqrestore(&cpufreq_driver_lock, flags);
 
-	if (!data) {
+	if (!policy) {
 		pr_debug("%s: No cpu_data found\n", __func__);
 		return -EINVAL;
 	}
 
-	if (cpufreq_driver->target)
-		__cpufreq_governor(data, CPUFREQ_GOV_STOP);
+	if (cpufreq_driver->target) {
+		ret = __cpufreq_governor(policy, CPUFREQ_GOV_STOP);
+		if (ret) {
+			pr_err("%s: Failed to stop governor\n", __func__);
+			return ret;
+		}
+	}
 
 #ifdef CONFIG_HOTPLUG_CPU
 	if (!cpufreq_driver->setpolicy)
 		strncpy(per_cpu(cpufreq_cpu_governor, cpu),
-			data->governor->name, CPUFREQ_NAME_LEN);
+			policy->governor->name, CPUFREQ_NAME_LEN);
 #endif
 
-	WARN_ON(lock_policy_rwsem_write(cpu));
-	cpus = cpumask_weight(data->cpus);
-
-	if (cpus > 1)
-		cpumask_clear_cpu(cpu, data->cpus);
-	unlock_policy_rwsem_write(cpu);
+	lock_policy_rwsem_read(cpu);
+	cpus = cpumask_weight(policy->cpus);
+	unlock_policy_rwsem_read(cpu);
 
-	if (cpu != data->cpu) {
-		sysfs_remove_link(&dev->kobj, "cpufreq");
+	if (cpu != policy->cpu) {
+		if (!frozen)
+			sysfs_remove_link(&dev->kobj, "cpufreq");
 	} else if (cpus > 1) {
-		/* first sibling now owns the new sysfs dir */
-		cpu_dev = get_cpu_device(cpumask_first(data->cpus));
-		sysfs_remove_link(&cpu_dev->kobj, "cpufreq");
-		ret = kobject_move(&data->kobj, &cpu_dev->kobj);
-		if (ret) {
-			pr_err("%s: Failed to move kobj: %d", __func__, ret);
 
-			WARN_ON(lock_policy_rwsem_write(cpu));
-			cpumask_set_cpu(cpu, data->cpus);
+		new_cpu = cpufreq_nominate_new_policy_cpu(policy, cpu, frozen);
+		if (new_cpu >= 0) {
+			update_policy_cpu(policy, new_cpu);
 
-			write_lock_irqsave(&cpufreq_driver_lock, flags);
-			per_cpu(cpufreq_cpu_data, cpu) = data;
-			write_unlock_irqrestore(&cpufreq_driver_lock, flags);
+			if (!frozen) {
+				pr_debug("%s: policy Kobject moved to cpu: %d "
+					 "from: %d\n",__func__, new_cpu, cpu);
+			}
+		}
+	}
 
-			unlock_policy_rwsem_write(cpu);
+	return 0;
+}
 
-			ret = sysfs_create_link(&cpu_dev->kobj, &data->kobj,
-					"cpufreq");
-			return -EINVAL;
-		}
+static int __cpufreq_remove_dev_finish(struct device *dev,
+				       struct subsys_interface *sif,
+				       bool frozen)
+{
+	unsigned int cpu = dev->id, cpus;
+	int ret;
+	unsigned long flags;
+	struct cpufreq_policy *policy;
+	struct kobject *kobj;
+	struct completion *cmp;
+
+	read_lock_irqsave(&cpufreq_driver_lock, flags);
+	policy = per_cpu(cpufreq_cpu_data, cpu);
+	read_unlock_irqrestore(&cpufreq_driver_lock, flags);
 
-		WARN_ON(lock_policy_rwsem_write(cpu));
-		update_policy_cpu(data, cpu_dev->id);
-		unlock_policy_rwsem_write(cpu);
-		pr_debug("%s: policy Kobject moved to cpu: %d from: %d\n",
-				__func__, cpu_dev->id, cpu);
+	if (!policy) {
+		pr_debug("%s: No cpu_data found\n", __func__);
+		return -EINVAL;
 	}
 
+	WARN_ON(lock_policy_rwsem_write(cpu));
+	cpus = cpumask_weight(policy->cpus);
+
+	if (cpus > 1)
+		cpumask_clear_cpu(cpu, policy->cpus);
+	unlock_policy_rwsem_write(cpu);
+
 	/* If cpu is last user of policy, free policy */
 	if (cpus == 1) {
-		if (cpufreq_driver->target)
-			__cpufreq_governor(data, CPUFREQ_GOV_POLICY_EXIT);
-
-		lock_policy_rwsem_read(cpu);
-		kobj = &data->kobj;
-		cmp = &data->kobj_unregister;
-		unlock_policy_rwsem_read(cpu);
-		kobject_put(kobj);
-
-		/* we need to make sure that the underlying kobj is actually
-		 * not referenced anymore by anybody before we proceed with
-		 * unloading.
-		 */
-		pr_debug("waiting for dropping of refcount\n");
-		wait_for_completion(cmp);
-		pr_debug("wait complete\n");
+		if (cpufreq_driver->target) {
+			ret = __cpufreq_governor(policy,
+					CPUFREQ_GOV_POLICY_EXIT);
+			if (ret) {
+				pr_err("%s: Failed to exit governor\n",
+						__func__);
+				return ret;
+			}
+		}
+
+		if (!frozen) {
+			lock_policy_rwsem_read(cpu);
+			kobj = &policy->kobj;
+			cmp = &policy->kobj_unregister;
+			unlock_policy_rwsem_read(cpu);
+			kobject_put(kobj);
+
+			/*
+			 * We need to make sure that the underlying kobj is
+			 * actually not referenced anymore by anybody before we
+			 * proceed with unloading.
+			 */
+			pr_debug("waiting for dropping of refcount\n");
+			wait_for_completion(cmp);
+			pr_debug("wait complete\n");
+		}
 
+		/*
+		 * Perform the ->exit() even during light-weight tear-down,
+		 * since this is a core component, and is essential for the
+		 * subsequent light-weight ->init() to succeed.
+		 */
 		if (cpufreq_driver->exit)
-			cpufreq_driver->exit(data);
+			cpufreq_driver->exit(policy);
+
+		/* Remove policy from list of active policies */
+		write_lock_irqsave(&cpufreq_driver_lock, flags);
+		list_del(&policy->policy_list);
+		write_unlock_irqrestore(&cpufreq_driver_lock, flags);
 
-		free_cpumask_var(data->related_cpus);
-		free_cpumask_var(data->cpus);
-		kfree(data);
+		if (!frozen)
+			cpufreq_policy_free(policy);
 	} else {
-		pr_debug("%s: removing link, cpu: %d\n", __func__, cpu);
-		cpufreq_cpu_put(data);
 		if (cpufreq_driver->target) {
-			__cpufreq_governor(data, CPUFREQ_GOV_START);
-			__cpufreq_governor(data, CPUFREQ_GOV_LIMITS);
+			if ((ret = __cpufreq_governor(policy, CPUFREQ_GOV_START)) ||
+					(ret = __cpufreq_governor(policy, CPUFREQ_GOV_LIMITS))) {
+				pr_err("%s: Failed to start governor\n",
+						__func__);
+				return ret;
+			}
 		}
 	}
 
-	per_cpu(cpufreq_policy_cpu, cpu) = -1;
+	per_cpu(cpufreq_cpu_data, cpu) = NULL;
 	return 0;
 }
 
+/**
+ * __cpufreq_remove_dev - remove a CPU device
+ *
+ * Removes the cpufreq interface for a CPU device.
+ * Caller should already have policy_rwsem in write mode for this CPU.
+ * This routine frees the rwsem before returning.
+ */
+static inline int __cpufreq_remove_dev(struct device *dev,
+				       struct subsys_interface *sif,
+				       bool frozen)
+{
+	int ret;
+
+	ret = __cpufreq_remove_dev_prepare(dev, sif, frozen);
+
+	if (!ret)
+		ret = __cpufreq_remove_dev_finish(dev, sif, frozen);
+
+	return ret;
+}
+
 static int cpufreq_remove_dev(struct device *dev, struct subsys_interface *sif)
 {
 	unsigned int cpu = dev->id;
@@ -1223,7 +1338,7 @@ static int cpufreq_remove_dev(struct device *dev, struct subsys_interface *sif)
 	if (cpu_is_offline(cpu))
 		return 0;
 
-	retval = __cpufreq_remove_dev(dev, sif);
+	retval = __cpufreq_remove_dev(dev, sif, false);
 	return retval;
 }
 
@@ -1344,10 +1459,12 @@ static unsigned int __cpufreq_get(unsigned int cpu)
 unsigned int cpufreq_get(unsigned int cpu)
 {
 	unsigned int ret_freq = 0;
-	struct cpufreq_policy *policy = cpufreq_cpu_get(cpu);
 
-	if (!policy)
-		goto out;
+	if (cpufreq_disabled() || !cpufreq_driver)
+		return -ENOENT;
+
+	if (!down_read_trylock(&cpufreq_rwsem))
+		return 0;
 
 	if (unlikely(lock_policy_rwsem_read(cpu)))
 		goto out_policy;
@@ -1357,8 +1474,8 @@ unsigned int cpufreq_get(unsigned int cpu)
 	unlock_policy_rwsem_read(cpu);
 
 out_policy:
-	cpufreq_cpu_put(policy);
-out:
+	up_read(&cpufreq_rwsem);
+
 	return ret_freq;
 }
 EXPORT_SYMBOL(cpufreq_get);
@@ -1381,23 +1498,23 @@ static int cpufreq_bp_suspend(void)
 	int ret = 0;
 
 	int cpu = smp_processor_id();
-	struct cpufreq_policy *cpu_policy;
+	struct cpufreq_policy *policy;
 
 	pr_debug("suspending cpu %u\n", cpu);
 
 	/* If there's no policy for the boot CPU, we have nothing to do. */
-	cpu_policy = cpufreq_cpu_get(cpu);
-	if (!cpu_policy)
+	policy = cpufreq_cpu_get(cpu);
+	if (!policy)
 		return 0;
 
 	if (cpufreq_driver->suspend) {
-		ret = cpufreq_driver->suspend(cpu_policy);
+		ret = cpufreq_driver->suspend(policy);
 		if (ret)
 			printk(KERN_ERR "cpufreq: suspend failed in ->suspend "
-					"step on CPU %u\n", cpu_policy->cpu);
+					"step on CPU %u\n", policy->cpu);
 	}
 
-	cpufreq_cpu_put(cpu_policy);
+	cpufreq_cpu_put(policy);
 	return ret;
 }
 
@@ -1419,28 +1536,28 @@ static void cpufreq_bp_resume(void)
 	int ret = 0;
 
 	int cpu = smp_processor_id();
-	struct cpufreq_policy *cpu_policy;
+	struct cpufreq_policy *policy;
 
 	pr_debug("resuming cpu %u\n", cpu);
 
 	/* If there's no policy for the boot CPU, we have nothing to do. */
-	cpu_policy = cpufreq_cpu_get(cpu);
-	if (!cpu_policy)
+	policy = cpufreq_cpu_get(cpu);
+	if (!policy)
 		return;
 
 	if (cpufreq_driver->resume) {
-		ret = cpufreq_driver->resume(cpu_policy);
+		ret = cpufreq_driver->resume(policy);
 		if (ret) {
 			printk(KERN_ERR "cpufreq: resume failed in ->resume "
-					"step on CPU %u\n", cpu_policy->cpu);
+					"step on CPU %u\n", policy->cpu);
 			goto fail;
 		}
 	}
 
-	schedule_work(&cpu_policy->update);
+	schedule_work(&policy->update);
 
 fail:
-	cpufreq_cpu_put(cpu_policy);
+	cpufreq_cpu_put(policy);
 }
 
 static struct syscore_ops cpufreq_syscore_ops = {
@@ -1554,8 +1671,6 @@ int __cpufreq_driver_target(struct cpufreq_policy *policy,
 
 	if (cpufreq_disabled())
 		return -ENODEV;
-	if (policy->transition_ongoing)
-		return -EBUSY;
 
 	/* Make sure that target_freq is within supported range */
 	if (target_freq > policy->max)
@@ -1594,18 +1709,6 @@ fail:
 }
 EXPORT_SYMBOL_GPL(cpufreq_driver_target);
 
-int __cpufreq_driver_getavg(struct cpufreq_policy *policy, unsigned int cpu)
-{
-	if (cpufreq_disabled())
-		return 0;
-
-	if (!cpufreq_driver->getavg)
-		return 0;
-
-	return cpufreq_driver->getavg(policy, cpu);
-}
-EXPORT_SYMBOL_GPL(__cpufreq_driver_getavg);
-
 /*
  * when "event" is CPUFREQ_GOV_LIMITS
  */
@@ -1640,15 +1743,17 @@ static int __cpufreq_governor(struct cpufreq_policy *policy,
 		}
 	}
 
-	if (!try_module_get(policy->governor->owner))
-		return -EINVAL;
+	if (event == CPUFREQ_GOV_POLICY_INIT)
+		if (!try_module_get(policy->governor->owner))
+			return -EINVAL;
 
 	pr_debug("__cpufreq_governor for CPU %u, event %u\n",
 						policy->cpu, event);
 
 	mutex_lock(&cpufreq_governor_lock);
-	if ((!policy->governor_enabled && (event == CPUFREQ_GOV_STOP)) ||
-	    (policy->governor_enabled && (event == CPUFREQ_GOV_START))) {
+	if ((policy->governor_enabled && event == CPUFREQ_GOV_START)
+	    || (!policy->governor_enabled
+	    && (event == CPUFREQ_GOV_LIMITS || event == CPUFREQ_GOV_STOP))) {
 		mutex_unlock(&cpufreq_governor_lock);
 		return -EBUSY;
 	}
@@ -1677,11 +1782,8 @@ static int __cpufreq_governor(struct cpufreq_policy *policy,
 		mutex_unlock(&cpufreq_governor_lock);
 	}
 
-	/* we keep one module reference alive for
-			each CPU governed by this CPU */
-	if ((event != CPUFREQ_GOV_START) || ret)
-		module_put(policy->governor->owner);
-	if ((event == CPUFREQ_GOV_STOP) && !ret)
+	if (((event == CPUFREQ_GOV_POLICY_INIT) && ret) ||
+			((event == CPUFREQ_GOV_POLICY_EXIT) && !ret))
 		module_put(policy->governor->owner);
 
 	return ret;
@@ -1761,7 +1863,7 @@ int cpufreq_get_policy(struct cpufreq_policy *policy, unsigned int cpu)
 	if (!cpu_policy)
 		return -EINVAL;
 
-	memcpy(policy, cpu_policy, sizeof(struct cpufreq_policy));
+	memcpy(policy, cpu_policy, sizeof(*policy));
 
 	cpufreq_cpu_put(cpu_policy);
 	return 0;
@@ -1772,95 +1874,94 @@ EXPORT_SYMBOL(cpufreq_get_policy);
  * data   : current policy.
  * policy : policy to be set.
  */
-static int __cpufreq_set_policy(struct cpufreq_policy *data,
-				struct cpufreq_policy *policy)
+static int __cpufreq_set_policy(struct cpufreq_policy *policy,
+				struct cpufreq_policy *new_policy)
 {
 	int ret = 0, failed = 1;
 
-	pr_debug("setting new policy for CPU %u: %u - %u kHz\n", policy->cpu,
-		policy->min, policy->max);
+	pr_debug("setting new policy for CPU %u: %u - %u kHz\n", new_policy->cpu,
+		new_policy->min, new_policy->max);
 
-	memcpy(&policy->cpuinfo, &data->cpuinfo,
-				sizeof(struct cpufreq_cpuinfo));
+	memcpy(&new_policy->cpuinfo, &policy->cpuinfo, sizeof(policy->cpuinfo));
 
-	if (policy->min > data->max || policy->max < data->min) {
+	if (new_policy->min > policy->max || new_policy->max < policy->min) {
 		ret = -EINVAL;
 		goto error_out;
 	}
 
 	/* verify the cpu speed can be set within this limit */
-	ret = cpufreq_driver->verify(policy);
+	ret = cpufreq_driver->verify(new_policy);
 	if (ret)
 		goto error_out;
 
 	/* adjust if necessary - all reasons */
 	blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
-			CPUFREQ_ADJUST, policy);
+			CPUFREQ_ADJUST, new_policy);
 
 	/* adjust if necessary - hardware incompatibility*/
 	blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
-			CPUFREQ_INCOMPATIBLE, policy);
+			CPUFREQ_INCOMPATIBLE, new_policy);
 
 	/*
 	 * verify the cpu speed can be set within this limit, which might be
 	 * different to the first one
 	 */
-	ret = cpufreq_driver->verify(policy);
+	ret = cpufreq_driver->verify(new_policy);
 	if (ret)
 		goto error_out;
 
 	/* notification of the new policy */
 	blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
-			CPUFREQ_NOTIFY, policy);
+			CPUFREQ_NOTIFY, new_policy);
 
-	data->min = policy->min;
-	data->max = policy->max;
+	policy->min = new_policy->min;
+	policy->max = new_policy->max;
 
 	pr_debug("new min and max freqs are %u - %u kHz\n",
-					data->min, data->max);
+					policy->min, policy->max);
 
 	if (cpufreq_driver->setpolicy) {
-		data->policy = policy->policy;
+		policy->policy = new_policy->policy;
 		pr_debug("setting range\n");
-		ret = cpufreq_driver->setpolicy(policy);
+		ret = cpufreq_driver->setpolicy(new_policy);
 	} else {
-		if (policy->governor != data->governor) {
+		if (new_policy->governor != policy->governor) {
 			/* save old, working values */
-			struct cpufreq_governor *old_gov = data->governor;
+			struct cpufreq_governor *old_gov = policy->governor;
 
 			pr_debug("governor switch\n");
 
 			/* end old governor */
-			if (data->governor) {
-				__cpufreq_governor(data, CPUFREQ_GOV_STOP);
-				unlock_policy_rwsem_write(policy->cpu);
-				__cpufreq_governor(data,
+			if (policy->governor) {
+				__cpufreq_governor(policy, CPUFREQ_GOV_STOP);
+				unlock_policy_rwsem_write(new_policy->cpu);
+				__cpufreq_governor(policy,
 						CPUFREQ_GOV_POLICY_EXIT);
-				lock_policy_rwsem_write(policy->cpu);
+				lock_policy_rwsem_write(new_policy->cpu);
 			}
 
 			/* start new governor */
-			data->governor = policy->governor;
-			if (!__cpufreq_governor(data, CPUFREQ_GOV_POLICY_INIT)) {
-				if (!__cpufreq_governor(data, CPUFREQ_GOV_START)) {
+			policy->governor = new_policy->governor;
+			if (!__cpufreq_governor(policy, CPUFREQ_GOV_POLICY_INIT)) {
+				if (!__cpufreq_governor(policy, CPUFREQ_GOV_START)) {
 					failed = 0;
 				} else {
-					unlock_policy_rwsem_write(policy->cpu);
-					__cpufreq_governor(data,
+					unlock_policy_rwsem_write(new_policy->cpu);
+					__cpufreq_governor(policy,
 							CPUFREQ_GOV_POLICY_EXIT);
-					lock_policy_rwsem_write(policy->cpu);
+					lock_policy_rwsem_write(new_policy->cpu);
 				}
 			}
 
 			if (failed) {
 				/* new governor failed, so re-start old one */
 				pr_debug("starting governor %s failed\n",
-							data->governor->name);
+							policy->governor->name);
 				if (old_gov) {
-					data->governor = old_gov;
-					__cpufreq_governor(data,
+					policy->governor = old_gov;
+					__cpufreq_governor(policy,
 							CPUFREQ_GOV_POLICY_INIT);
-					__cpufreq_governor(data,
+					__cpufreq_governor(policy,
 							   CPUFREQ_GOV_START);
 				}
 				ret = -EINVAL;
@@ -1869,7 +1970,7 @@ static int __cpufreq_set_policy(struct cpufreq_policy *data,
 			/* might be a policy change, too, so fall through */
 		}
 		pr_debug("governor: change or update limits\n");
-		__cpufreq_governor(data, CPUFREQ_GOV_LIMITS);
+		ret = __cpufreq_governor(policy, CPUFREQ_GOV_LIMITS);
 	}
 
 error_out:
@@ -1885,11 +1986,11 @@ error_out:
  */
 int cpufreq_update_policy(unsigned int cpu)
 {
-	struct cpufreq_policy *data = cpufreq_cpu_get(cpu);
-	struct cpufreq_policy policy;
+	struct cpufreq_policy *policy = cpufreq_cpu_get(cpu);
+	struct cpufreq_policy new_policy;
 	int ret;
 
-	if (!data) {
+	if (!policy) {
 		ret = -ENODEV;
 		goto no_policy;
 	}
@@ -1900,34 +2001,34 @@ int cpufreq_update_policy(unsigned int cpu)
 	}
 
 	pr_debug("updating policy for CPU %u\n", cpu);
-	memcpy(&policy, data, sizeof(struct cpufreq_policy));
-	policy.min = data->user_policy.min;
-	policy.max = data->user_policy.max;
-	policy.policy = data->user_policy.policy;
-	policy.governor = data->user_policy.governor;
+	memcpy(&new_policy, policy, sizeof(*policy));
+	new_policy.min = policy->user_policy.min;
+	new_policy.max = policy->user_policy.max;
+	new_policy.policy = policy->user_policy.policy;
+	new_policy.governor = policy->user_policy.governor;
 
 	/*
 	 * BIOS might change freq behind our back
 	 * -> ask driver for current freq and notify governors about a change
 	 */
 	if (cpufreq_driver->get) {
-		policy.cur = cpufreq_driver->get(cpu);
-		if (!data->cur) {
+		new_policy.cur = cpufreq_driver->get(cpu);
+		if (!policy->cur) {
 			pr_debug("Driver did not initialize current freq");
-			data->cur = policy.cur;
+			policy->cur = new_policy.cur;
 		} else {
-			if (data->cur != policy.cur && cpufreq_driver->target)
-				cpufreq_out_of_sync(cpu, data->cur,
-								policy.cur);
+			if (policy->cur != new_policy.cur && cpufreq_driver->target)
+				cpufreq_out_of_sync(cpu, policy->cur,
+								new_policy.cur);
 		}
 	}
 
-	ret = __cpufreq_set_policy(data, &policy);
+	ret = __cpufreq_set_policy(policy, &new_policy);
 
 	unlock_policy_rwsem_write(cpu);
 
 fail:
-	cpufreq_cpu_put(data);
+	cpufreq_cpu_put(policy);
 no_policy:
 	return ret;
 }
@@ -1938,21 +2039,30 @@ static int cpufreq_cpu_callback(struct notifier_block *nfb,
 {
 	unsigned int cpu = (unsigned long)hcpu;
 	struct device *dev;
+	bool frozen = false;
 
 	dev = get_cpu_device(cpu);
 	if (dev) {
-		switch (action) {
+
+		if (action & CPU_TASKS_FROZEN)
+			frozen = true;
+
+		switch (action & ~CPU_TASKS_FROZEN) {
 		case CPU_ONLINE:
-		case CPU_ONLINE_FROZEN:
-			cpufreq_add_dev(dev, NULL);
+			__cpufreq_add_dev(dev, NULL, frozen);
+			cpufreq_update_policy(cpu);
 			break;
+
 		case CPU_DOWN_PREPARE:
-		case CPU_DOWN_PREPARE_FROZEN:
-			__cpufreq_remove_dev(dev, NULL);
+			__cpufreq_remove_dev_prepare(dev, NULL, frozen);
+			break;
+
+		case CPU_POST_DEAD:
+			__cpufreq_remove_dev_finish(dev, NULL, frozen);
 			break;
+
 		case CPU_DOWN_FAILED:
-		case CPU_DOWN_FAILED_FROZEN:
-			cpufreq_add_dev(dev, NULL);
+			__cpufreq_add_dev(dev, NULL, frozen);
 			break;
 		}
 	}
@@ -1997,7 +2107,7 @@ int cpufreq_register_driver(struct cpufreq_driver *driver_data)
 	write_lock_irqsave(&cpufreq_driver_lock, flags);
 	if (cpufreq_driver) {
 		write_unlock_irqrestore(&cpufreq_driver_lock, flags);
-		return -EBUSY;
+		return -EEXIST;
 	}
 	cpufreq_driver = driver_data;
 	write_unlock_irqrestore(&cpufreq_driver_lock, flags);
@@ -2059,9 +2169,13 @@ int cpufreq_unregister_driver(struct cpufreq_driver *driver)
 	subsys_interface_unregister(&cpufreq_interface);
 	unregister_hotcpu_notifier(&cpufreq_cpu_notifier);
 
+	down_write(&cpufreq_rwsem);
 	write_lock_irqsave(&cpufreq_driver_lock, flags);
+
 	cpufreq_driver = NULL;
+
 	write_unlock_irqrestore(&cpufreq_driver_lock, flags);
+	up_write(&cpufreq_rwsem);
 
 	return 0;
 }
@@ -2074,10 +2188,8 @@ static int __init cpufreq_core_init(void)
 	if (cpufreq_disabled())
 		return -ENODEV;
 
-	for_each_possible_cpu(cpu) {
-		per_cpu(cpufreq_policy_cpu, cpu) = -1;
+	for_each_possible_cpu(cpu)
 		init_rwsem(&per_cpu(cpu_policy_rwsem, cpu));
-	}
 
 	cpufreq_global_kobject = kobject_create();
 	BUG_ON(!cpufreq_global_kobject);
diff --git a/drivers/cpufreq/cpufreq_conservative.c b/drivers/cpufreq/cpufreq_conservative.c
index f97cb3d8c5a2..f62d822048e6 100644
--- a/drivers/cpufreq/cpufreq_conservative.c
+++ b/drivers/cpufreq/cpufreq_conservative.c
@@ -11,19 +11,7 @@
  * published by the Free Software Foundation.
  */
 
-#include <linux/cpufreq.h>
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/kernel_stat.h>
-#include <linux/kobject.h>
-#include <linux/module.h>
-#include <linux/mutex.h>
-#include <linux/notifier.h>
-#include <linux/percpu-defs.h>
 #include <linux/slab.h>
-#include <linux/sysfs.h>
-#include <linux/types.h>
-
 #include "cpufreq_governor.h"
 
 /* Conservative governor macros */
@@ -79,8 +67,6 @@ static void cs_check_cpu(int cpu, unsigned int load)
 			return;
 
 		dbs_info->requested_freq += get_freq_target(cs_tuners, policy);
-		if (dbs_info->requested_freq > policy->max)
-			dbs_info->requested_freq = policy->max;
 
 		__cpufreq_driver_target(policy, dbs_info->requested_freq,
 			CPUFREQ_RELATION_H);
@@ -101,8 +87,6 @@ static void cs_check_cpu(int cpu, unsigned int load)
 			return;
 
 		dbs_info->requested_freq -= get_freq_target(cs_tuners, policy);
-		if (dbs_info->requested_freq < policy->min)
-			dbs_info->requested_freq = policy->min;
 
 		__cpufreq_driver_target(policy, dbs_info->requested_freq,
 				CPUFREQ_RELATION_L);
@@ -329,7 +313,7 @@ static int cs_init(struct dbs_data *dbs_data)
 {
 	struct cs_dbs_tuners *tuners;
 
-	tuners = kzalloc(sizeof(struct cs_dbs_tuners), GFP_KERNEL);
+	tuners = kzalloc(sizeof(*tuners), GFP_KERNEL);
 	if (!tuners) {
 		pr_err("%s: kzalloc failed\n", __func__);
 		return -ENOMEM;
diff --git a/drivers/cpufreq/cpufreq_governor.c b/drivers/cpufreq/cpufreq_governor.c
index e59afaa9da23..0806c31e5764 100644
--- a/drivers/cpufreq/cpufreq_governor.c
+++ b/drivers/cpufreq/cpufreq_governor.c
@@ -16,15 +16,9 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
-#include <asm/cputime.h>
-#include <linux/cpufreq.h>
-#include <linux/cpumask.h>
 #include <linux/export.h>
 #include <linux/kernel_stat.h>
-#include <linux/mutex.h>
 #include <linux/slab.h>
-#include <linux/types.h>
-#include <linux/workqueue.h>
 
 #include "cpufreq_governor.h"
 
@@ -53,7 +47,7 @@ void dbs_check_cpu(struct dbs_data *dbs_data, int cpu)
 
 	policy = cdbs->cur_policy;
 
-	/* Get Absolute Load (in terms of freq for ondemand gov) */
+	/* Get Absolute Load */
 	for_each_cpu(j, policy->cpus) {
 		struct cpu_dbs_common_info *j_cdbs;
 		u64 cur_wall_time, cur_idle_time;
@@ -104,14 +98,6 @@ void dbs_check_cpu(struct dbs_data *dbs_data, int cpu)
 
 		load = 100 * (wall_time - idle_time) / wall_time;
 
-		if (dbs_data->cdata->governor == GOV_ONDEMAND) {
-			int freq_avg = __cpufreq_driver_getavg(policy, j);
-			if (freq_avg <= 0)
-				freq_avg = policy->cur;
-
-			load *= freq_avg;
-		}
-
 		if (load > max_load)
 			max_load = load;
 	}
@@ -133,8 +119,18 @@ void gov_queue_work(struct dbs_data *dbs_data, struct cpufreq_policy *policy,
 {
 	int i;
 
+	if (!policy->governor_enabled)
+		return;
+
 	if (!all_cpus) {
-		__gov_queue_work(smp_processor_id(), dbs_data, delay);
+		/*
+		 * Use raw_smp_processor_id() to avoid preemptible warnings.
+		 * We know that this is only called with all_cpus == false from
+		 * works that have been queued with *_work_on() functions and
+		 * those works are canceled during CPU_DOWN_PREPARE so they
+		 * can't possibly run on any other CPU.
+		 */
+		__gov_queue_work(raw_smp_processor_id(), dbs_data, delay);
 	} else {
 		for_each_cpu(i, policy->cpus)
 			__gov_queue_work(i, dbs_data, delay);
@@ -244,7 +240,7 @@ int cpufreq_governor_dbs(struct cpufreq_policy *policy,
 
 		policy->governor_data = dbs_data;
 
-		/* policy latency is in nS. Convert it to uS first */
+		/* policy latency is in ns. Convert it to us first */
 		latency = policy->cpuinfo.transition_latency / 1000;
 		if (latency == 0)
 			latency = 1;
diff --git a/drivers/cpufreq/cpufreq_governor.h b/drivers/cpufreq/cpufreq_governor.h
index d5f12b4b11b8..88cd39f7b0e9 100644
--- a/drivers/cpufreq/cpufreq_governor.h
+++ b/drivers/cpufreq/cpufreq_governor.h
@@ -18,19 +18,18 @@
 #define _CPUFREQ_GOVERNOR_H
 
 #include <linux/cpufreq.h>
-#include <linux/kobject.h>
+#include <linux/kernel_stat.h>
+#include <linux/module.h>
 #include <linux/mutex.h>
-#include <linux/workqueue.h>
-#include <linux/sysfs.h>
 
 /*
  * The polling frequency depends on the capability of the processor. Default
  * polling frequency is 1000 times the transition latency of the processor. The
- * governor will work on any processor with transition latency <= 10mS, using
+ * governor will work on any processor with transition latency <= 10ms, using
  * appropriate sampling rate.
  *
- * For CPUs with transition latency > 10mS (mostly drivers with CPUFREQ_ETERNAL)
- * this governor will not work. All times here are in uS.
+ * For CPUs with transition latency > 10ms (mostly drivers with CPUFREQ_ETERNAL)
+ * this governor will not work. All times here are in us (micro seconds).
  */
 #define MIN_SAMPLING_RATE_RATIO			(2)
 #define LATENCY_MULTIPLIER			(1000)
@@ -163,13 +162,12 @@ struct cs_cpu_dbs_info_s {
 	unsigned int enable:1;
 };
 
-/* Per policy Governers sysfs tunables */
+/* Per policy Governors sysfs tunables */
 struct od_dbs_tuners {
 	unsigned int ignore_nice_load;
 	unsigned int sampling_rate;
 	unsigned int sampling_down_factor;
 	unsigned int up_threshold;
-	unsigned int adj_up_threshold;
 	unsigned int powersave_bias;
 	unsigned int io_is_busy;
 };
@@ -183,7 +181,7 @@ struct cs_dbs_tuners {
 	unsigned int freq_step;
 };
 
-/* Common Governer data across policies */
+/* Common Governor data across policies */
 struct dbs_data;
 struct common_dbs_data {
 	/* Common across governors */
@@ -207,7 +205,7 @@ struct common_dbs_data {
 	void *gov_ops;
 };
 
-/* Governer Per policy data */
+/* Governor Per policy data */
 struct dbs_data {
 	struct common_dbs_data *cdata;
 	unsigned int min_sampling_rate;
@@ -223,7 +221,7 @@ struct od_ops {
 	void (*powersave_bias_init_cpu)(int cpu);
 	unsigned int (*powersave_bias_target)(struct cpufreq_policy *policy,
 			unsigned int freq_next, unsigned int relation);
-	void (*freq_increase)(struct cpufreq_policy *p, unsigned int freq);
+	void (*freq_increase)(struct cpufreq_policy *policy, unsigned int freq);
 };
 
 struct cs_ops {
diff --git a/drivers/cpufreq/cpufreq_ondemand.c b/drivers/cpufreq/cpufreq_ondemand.c
index c087347d6688..32f26f6e17c5 100644
--- a/drivers/cpufreq/cpufreq_ondemand.c
+++ b/drivers/cpufreq/cpufreq_ondemand.c
@@ -12,28 +12,16 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
-#include <linux/cpufreq.h>
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/kernel_stat.h>
-#include <linux/kobject.h>
-#include <linux/module.h>
-#include <linux/mutex.h>
+#include <linux/cpu.h>
 #include <linux/percpu-defs.h>
 #include <linux/slab.h>
-#include <linux/sysfs.h>
 #include <linux/tick.h>
-#include <linux/types.h>
-#include <linux/cpu.h>
-
 #include "cpufreq_governor.h"
 
 /* On-demand governor macros */
-#define DEF_FREQUENCY_DOWN_DIFFERENTIAL		(10)
 #define DEF_FREQUENCY_UP_THRESHOLD		(80)
 #define DEF_SAMPLING_DOWN_FACTOR		(1)
 #define MAX_SAMPLING_DOWN_FACTOR		(100000)
-#define MICRO_FREQUENCY_DOWN_DIFFERENTIAL	(3)
 #define MICRO_FREQUENCY_UP_THRESHOLD		(95)
 #define MICRO_FREQUENCY_MIN_SAMPLE_RATE		(10000)
 #define MIN_FREQUENCY_UP_THRESHOLD		(11)
@@ -144,31 +132,27 @@ static void ondemand_powersave_bias_init(void)
 	}
 }
 
-static void dbs_freq_increase(struct cpufreq_policy *p, unsigned int freq)
+static void dbs_freq_increase(struct cpufreq_policy *policy, unsigned int freq)
 {
-	struct dbs_data *dbs_data = p->governor_data;
+	struct dbs_data *dbs_data = policy->governor_data;
 	struct od_dbs_tuners *od_tuners = dbs_data->tuners;
 
 	if (od_tuners->powersave_bias)
-		freq = od_ops.powersave_bias_target(p, freq,
+		freq = od_ops.powersave_bias_target(policy, freq,
 				CPUFREQ_RELATION_H);
-	else if (p->cur == p->max)
+	else if (policy->cur == policy->max)
 		return;
 
-	__cpufreq_driver_target(p, freq, od_tuners->powersave_bias ?
+	__cpufreq_driver_target(policy, freq, od_tuners->powersave_bias ?
 			CPUFREQ_RELATION_L : CPUFREQ_RELATION_H);
 }
 
 /*
  * Every sampling_rate, we check, if current idle time is less than 20%
- * (default), then we try to increase frequency. Every sampling_rate, we look
- * for the lowest frequency which can sustain the load while keeping idle time
- * over 30%. If such a frequency exist, we try to decrease to this frequency.
- *
- * Any frequency increase takes it to the maximum frequency. Frequency reduction
- * happens at minimum steps of 5% (default) of current frequency
+ * (default), then we try to increase frequency. Else, we adjust the frequency
+ * proportional to load.
  */
-static void od_check_cpu(int cpu, unsigned int load_freq)
+static void od_check_cpu(int cpu, unsigned int load)
 {
 	struct od_cpu_dbs_info_s *dbs_info = &per_cpu(od_cpu_dbs_info, cpu);
 	struct cpufreq_policy *policy = dbs_info->cdbs.cur_policy;
@@ -178,36 +162,21 @@ static void od_check_cpu(int cpu, unsigned int load_freq)
 	dbs_info->freq_lo = 0;
 
 	/* Check for frequency increase */
-	if (load_freq > od_tuners->up_threshold * policy->cur) {
+	if (load > od_tuners->up_threshold) {
 		/* If switching to max speed, apply sampling_down_factor */
 		if (policy->cur < policy->max)
 			dbs_info->rate_mult =
 				od_tuners->sampling_down_factor;
 		dbs_freq_increase(policy, policy->max);
 		return;
-	}
-
-	/* Check for frequency decrease */
-	/* if we cannot reduce the frequency anymore, break out early */
-	if (policy->cur == policy->min)
-		return;
-
-	/*
-	 * The optimal frequency is the frequency that is the lowest that can
-	 * support the current CPU usage without triggering the up policy. To be
-	 * safe, we focus 10 points under the threshold.
-	 */
-	if (load_freq < od_tuners->adj_up_threshold
-			* policy->cur) {
+	} else {
+		/* Calculate the next frequency proportional to load */
 		unsigned int freq_next;
-		freq_next = load_freq / od_tuners->adj_up_threshold;
+		freq_next = load * policy->cpuinfo.max_freq / 100;
 
 		/* No longer fully busy, reset rate_mult */
 		dbs_info->rate_mult = 1;
 
-		if (freq_next < policy->min)
-			freq_next = policy->min;
-
 		if (!od_tuners->powersave_bias) {
 			__cpufreq_driver_target(policy, freq_next,
 					CPUFREQ_RELATION_L);
@@ -374,9 +343,6 @@ static ssize_t store_up_threshold(struct dbs_data *dbs_data, const char *buf,
 			input < MIN_FREQUENCY_UP_THRESHOLD) {
 		return -EINVAL;
 	}
-	/* Calculate the new adj_up_threshold */
-	od_tuners->adj_up_threshold += input;
-	od_tuners->adj_up_threshold -= od_tuners->up_threshold;
 
 	od_tuners->up_threshold = input;
 	return count;
@@ -513,7 +479,7 @@ static int od_init(struct dbs_data *dbs_data)
 	u64 idle_time;
 	int cpu;
 
-	tuners = kzalloc(sizeof(struct od_dbs_tuners), GFP_KERNEL);
+	tuners = kzalloc(sizeof(*tuners), GFP_KERNEL);
 	if (!tuners) {
 		pr_err("%s: kzalloc failed\n", __func__);
 		return -ENOMEM;
@@ -525,8 +491,6 @@ static int od_init(struct dbs_data *dbs_data)
 	if (idle_time != -1ULL) {
 		/* Idle micro accounting is supported. Use finer thresholds */
 		tuners->up_threshold = MICRO_FREQUENCY_UP_THRESHOLD;
-		tuners->adj_up_threshold = MICRO_FREQUENCY_UP_THRESHOLD -
-			MICRO_FREQUENCY_DOWN_DIFFERENTIAL;
 		/*
 		 * In nohz/micro accounting case we set the minimum frequency
 		 * not depending on HZ, but fixed (very low). The deferred
@@ -535,8 +499,6 @@ static int od_init(struct dbs_data *dbs_data)
 		dbs_data->min_sampling_rate = MICRO_FREQUENCY_MIN_SAMPLE_RATE;
 	} else {
 		tuners->up_threshold = DEF_FREQUENCY_UP_THRESHOLD;
-		tuners->adj_up_threshold = DEF_FREQUENCY_UP_THRESHOLD -
-			DEF_FREQUENCY_DOWN_DIFFERENTIAL;
 
 		/* For correct statistics, we need 10 ticks for each measure */
 		dbs_data->min_sampling_rate = MIN_SAMPLING_RATE_RATIO *
diff --git a/drivers/cpufreq/cpufreq_performance.c b/drivers/cpufreq/cpufreq_performance.c
index 9fef7d6e4e6a..cf117deb39b1 100644
--- a/drivers/cpufreq/cpufreq_performance.c
+++ b/drivers/cpufreq/cpufreq_performance.c
@@ -12,10 +12,9 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
-#include <linux/kernel.h>
-#include <linux/module.h>
 #include <linux/cpufreq.h>
 #include <linux/init.h>
+#include <linux/module.h>
 
 static int cpufreq_governor_performance(struct cpufreq_policy *policy,
 					unsigned int event)
diff --git a/drivers/cpufreq/cpufreq_powersave.c b/drivers/cpufreq/cpufreq_powersave.c
index 32109a14f5dc..e3b874c235ea 100644
--- a/drivers/cpufreq/cpufreq_powersave.c
+++ b/drivers/cpufreq/cpufreq_powersave.c
@@ -12,10 +12,9 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
-#include <linux/kernel.h>
-#include <linux/module.h>
 #include <linux/cpufreq.h>
 #include <linux/init.h>
+#include <linux/module.h>
 
 static int cpufreq_governor_powersave(struct cpufreq_policy *policy,
 					unsigned int event)
diff --git a/drivers/cpufreq/cpufreq_stats.c b/drivers/cpufreq/cpufreq_stats.c
index d37568c5ca9c..4cf0d2805cb2 100644
--- a/drivers/cpufreq/cpufreq_stats.c
+++ b/drivers/cpufreq/cpufreq_stats.c
@@ -9,17 +9,10 @@
  * published by the Free Software Foundation.
  */
 
-#include <linux/kernel.h>
-#include <linux/slab.h>
 #include <linux/cpu.h>
-#include <linux/sysfs.h>
 #include <linux/cpufreq.h>
 #include <linux/module.h>
-#include <linux/jiffies.h>
-#include <linux/percpu.h>
-#include <linux/kobject.h>
-#include <linux/spinlock.h>
-#include <linux/notifier.h>
+#include <linux/slab.h>
 #include <asm/cputime.h>
 
 static spinlock_t cpufreq_stats_lock;
@@ -81,7 +74,7 @@ static ssize_t show_time_in_state(struct cpufreq_policy *policy, char *buf)
 	for (i = 0; i < stat->state_num; i++) {
 		len += sprintf(buf + len, "%u %llu\n", stat->freq_table[i],
 			(unsigned long long)
-			cputime64_to_clock_t(stat->time_in_state[i]));
+			jiffies_64_to_clock_t(stat->time_in_state[i]));
 	}
 	return len;
 }
@@ -200,22 +193,22 @@ static int cpufreq_stats_create_table(struct cpufreq_policy *policy,
 {
 	unsigned int i, j, count = 0, ret = 0;
 	struct cpufreq_stats *stat;
-	struct cpufreq_policy *data;
+	struct cpufreq_policy *current_policy;
 	unsigned int alloc_size;
 	unsigned int cpu = policy->cpu;
 	if (per_cpu(cpufreq_stats_table, cpu))
 		return -EBUSY;
-	stat = kzalloc(sizeof(struct cpufreq_stats), GFP_KERNEL);
+	stat = kzalloc(sizeof(*stat), GFP_KERNEL);
 	if ((stat) == NULL)
 		return -ENOMEM;
 
-	data = cpufreq_cpu_get(cpu);
-	if (data == NULL) {
+	current_policy = cpufreq_cpu_get(cpu);
+	if (current_policy == NULL) {
 		ret = -EINVAL;
 		goto error_get_fail;
 	}
 
-	ret = sysfs_create_group(&data->kobj, &stats_attr_group);
+	ret = sysfs_create_group(&current_policy->kobj, &stats_attr_group);
 	if (ret)
 		goto error_out;
 
@@ -258,10 +251,10 @@ static int cpufreq_stats_create_table(struct cpufreq_policy *policy,
 	stat->last_time = get_jiffies_64();
 	stat->last_index = freq_table_get_index(stat, policy->cur);
 	spin_unlock(&cpufreq_stats_lock);
-	cpufreq_cpu_put(data);
+	cpufreq_cpu_put(current_policy);
 	return 0;
 error_out:
-	cpufreq_cpu_put(data);
+	cpufreq_cpu_put(current_policy);
 error_get_fail:
 	kfree(stat);
 	per_cpu(cpufreq_stats_table, cpu) = NULL;
@@ -348,16 +341,10 @@ static int cpufreq_stat_cpu_callback(struct notifier_block *nfb,
 	unsigned int cpu = (unsigned long)hcpu;
 
 	switch (action) {
-	case CPU_ONLINE:
-	case CPU_ONLINE_FROZEN:
-		cpufreq_update_policy(cpu);
-		break;
 	case CPU_DOWN_PREPARE:
-	case CPU_DOWN_PREPARE_FROZEN:
 		cpufreq_stats_free_sysfs(cpu);
 		break;
 	case CPU_DEAD:
-	case CPU_DEAD_FROZEN:
 		cpufreq_stats_free_table(cpu);
 		break;
 	}
@@ -390,8 +377,6 @@ static int __init cpufreq_stats_init(void)
 		return ret;
 
 	register_hotcpu_notifier(&cpufreq_stat_cpu_notifier);
-	for_each_online_cpu(cpu)
-		cpufreq_update_policy(cpu);
 
 	ret = cpufreq_register_notifier(&notifier_trans_block,
 				CPUFREQ_TRANSITION_NOTIFIER);
diff --git a/drivers/cpufreq/cris-artpec3-cpufreq.c b/drivers/cpufreq/cris-artpec3-cpufreq.c
index ee142c490575..cb8276dd19ca 100644
--- a/drivers/cpufreq/cris-artpec3-cpufreq.c
+++ b/drivers/cpufreq/cris-artpec3-cpufreq.c
@@ -111,7 +111,6 @@ static struct cpufreq_driver cris_freq_driver = {
 	.init	= cris_freq_cpu_init,
 	.exit	= cris_freq_cpu_exit,
 	.name	= "cris_freq",
-	.owner	= THIS_MODULE,
 	.attr	= cris_freq_attr,
 };
 
diff --git a/drivers/cpufreq/cris-etraxfs-cpufreq.c b/drivers/cpufreq/cris-etraxfs-cpufreq.c
index 12952235d5db..72328f77dc53 100644
--- a/drivers/cpufreq/cris-etraxfs-cpufreq.c
+++ b/drivers/cpufreq/cris-etraxfs-cpufreq.c
@@ -108,7 +108,6 @@ static struct cpufreq_driver cris_freq_driver = {
 	.init = cris_freq_cpu_init,
 	.exit = cris_freq_cpu_exit,
 	.name = "cris_freq",
-	.owner = THIS_MODULE,
 	.attr = cris_freq_attr,
 };
 
diff --git a/drivers/cpufreq/e_powersaver.c b/drivers/cpufreq/e_powersaver.c
index a60efaeb4cf8..09f64cc83019 100644
--- a/drivers/cpufreq/e_powersaver.c
+++ b/drivers/cpufreq/e_powersaver.c
@@ -54,7 +54,7 @@ static struct acpi_processor_performance *eps_acpi_cpu_perf;
 /* Minimum necessary to get acpi_processor_get_bios_limit() working */
 static int eps_acpi_init(void)
 {
-	eps_acpi_cpu_perf = kzalloc(sizeof(struct acpi_processor_performance),
+	eps_acpi_cpu_perf = kzalloc(sizeof(*eps_acpi_cpu_perf),
 				      GFP_KERNEL);
 	if (!eps_acpi_cpu_perf)
 		return -ENOMEM;
@@ -366,7 +366,7 @@ static int eps_cpu_init(struct cpufreq_policy *policy)
 		states = 2;
 
 	/* Allocate private data and frequency table for current cpu */
-	centaur = kzalloc(sizeof(struct eps_cpu_data)
+	centaur = kzalloc(sizeof(*centaur)
 		    + (states + 1) * sizeof(struct cpufreq_frequency_table),
 		    GFP_KERNEL);
 	if (!centaur)
@@ -436,7 +436,6 @@ static struct cpufreq_driver eps_driver = {
 	.exit		= eps_cpu_exit,
 	.get		= eps_get,
 	.name		= "e_powersaver",
-	.owner		= THIS_MODULE,
 	.attr		= eps_attr,
 };
 
diff --git a/drivers/cpufreq/elanfreq.c b/drivers/cpufreq/elanfreq.c
index 658d860344b0..823a400d98fd 100644
--- a/drivers/cpufreq/elanfreq.c
+++ b/drivers/cpufreq/elanfreq.c
@@ -274,7 +274,6 @@ static struct cpufreq_driver elanfreq_driver = {
 	.init		= elanfreq_cpu_init,
 	.exit		= elanfreq_cpu_exit,
 	.name		= "elanfreq",
-	.owner		= THIS_MODULE,
 	.attr		= elanfreq_attr,
 };
 
diff --git a/drivers/cpufreq/exynos-cpufreq.c b/drivers/cpufreq/exynos-cpufreq.c
index 0d32f02ef4d6..0fac34439e31 100644
--- a/drivers/cpufreq/exynos-cpufreq.c
+++ b/drivers/cpufreq/exynos-cpufreq.c
@@ -289,7 +289,7 @@ static int __init exynos_cpufreq_init(void)
 {
 	int ret = -EINVAL;
 
-	exynos_info = kzalloc(sizeof(struct exynos_dvfs_info), GFP_KERNEL);
+	exynos_info = kzalloc(sizeof(*exynos_info), GFP_KERNEL);
 	if (!exynos_info)
 		return -ENOMEM;
 
@@ -332,7 +332,6 @@ err_cpufreq:
 	regulator_put(arm_regulator);
 err_vdd_arm:
 	kfree(exynos_info);
-	pr_debug("%s: failed initialization\n", __func__);
 	return -EINVAL;
 }
 late_initcall(exynos_cpufreq_init);
diff --git a/drivers/cpufreq/exynos-cpufreq.h b/drivers/cpufreq/exynos-cpufreq.h
index 92b852ee5ddc..7f25cee8cec2 100644
--- a/drivers/cpufreq/exynos-cpufreq.h
+++ b/drivers/cpufreq/exynos-cpufreq.h
@@ -43,6 +43,27 @@ struct exynos_dvfs_info {
 	bool (*need_apll_change)(unsigned int, unsigned int);
 };
 
+#ifdef CONFIG_ARM_EXYNOS4210_CPUFREQ
 extern int exynos4210_cpufreq_init(struct exynos_dvfs_info *);
+#else
+static inline int exynos4210_cpufreq_init(struct exynos_dvfs_info *info)
+{
+	return -EOPNOTSUPP;
+}
+#endif
+#ifdef CONFIG_ARM_EXYNOS4X12_CPUFREQ
 extern int exynos4x12_cpufreq_init(struct exynos_dvfs_info *);
+#else
+static inline int exynos4x12_cpufreq_init(struct exynos_dvfs_info *info)
+{
+	return -EOPNOTSUPP;
+}
+#endif
+#ifdef CONFIG_ARM_EXYNOS5250_CPUFREQ
 extern int exynos5250_cpufreq_init(struct exynos_dvfs_info *);
+#else
+static inline int exynos5250_cpufreq_init(struct exynos_dvfs_info *info)
+{
+	return -EOPNOTSUPP;
+}
+#endif
diff --git a/drivers/cpufreq/exynos5440-cpufreq.c b/drivers/cpufreq/exynos5440-cpufreq.c
index 0c74018eda47..be5380ecdcd4 100644
--- a/drivers/cpufreq/exynos5440-cpufreq.c
+++ b/drivers/cpufreq/exynos5440-cpufreq.c
@@ -238,6 +238,9 @@ static int exynos_target(struct cpufreq_policy *policy,
 	freqs.old = dvfs_info->cur_frequency;
 	freqs.new = freq_table[index].frequency;
 
+	if (freqs.old == freqs.new)
+		goto out;
+
 	cpufreq_notify_transition(policy, &freqs, CPUFREQ_PRECHANGE);
 
 	/* Set the target frequency in all C0_3_PSTATE register */
@@ -454,7 +457,7 @@ err_free_table:
 	opp_free_cpufreq_table(dvfs_info->dev, &dvfs_info->freq_table);
 err_put_node:
 	of_node_put(np);
-	dev_err(dvfs_info->dev, "%s: failed initialization\n", __func__);
+	dev_err(&pdev->dev, "%s: failed initialization\n", __func__);
 	return ret;
 }
 
diff --git a/drivers/cpufreq/freq_table.c b/drivers/cpufreq/freq_table.c
index f0d87412cc91..f111454a7aea 100644
--- a/drivers/cpufreq/freq_table.c
+++ b/drivers/cpufreq/freq_table.c
@@ -11,10 +11,8 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/init.h>
 #include <linux/cpufreq.h>
+#include <linux/module.h>
 
 /*********************************************************************
  *                     FREQUENCY TABLE HELPERS                       *
diff --git a/drivers/cpufreq/gx-suspmod.c b/drivers/cpufreq/gx-suspmod.c
index 3dfc99b9ca86..70442c7b5e71 100644
--- a/drivers/cpufreq/gx-suspmod.c
+++ b/drivers/cpufreq/gx-suspmod.c
@@ -183,7 +183,7 @@ static void gx_write_byte(int reg, int value)
  * gx_detect_chipset:
  *
  **/
-static __init struct pci_dev *gx_detect_chipset(void)
+static struct pci_dev * __init gx_detect_chipset(void)
 {
 	struct pci_dev *gx_pci = NULL;
 
@@ -446,7 +446,6 @@ static struct cpufreq_driver gx_suspmod_driver = {
 	.target		= cpufreq_gx_target,
 	.init		= cpufreq_gx_cpu_init,
 	.name		= "gx-suspmod",
-	.owner		= THIS_MODULE,
 };
 
 static int __init cpufreq_gx_init(void)
@@ -466,7 +465,7 @@ static int __init cpufreq_gx_init(void)
 
 	pr_debug("geode suspend modulation available.\n");
 
-	params = kzalloc(sizeof(struct gxfreq_params), GFP_KERNEL);
+	params = kzalloc(sizeof(*params), GFP_KERNEL);
 	if (params == NULL)
 		return -ENOMEM;
 
diff --git a/drivers/cpufreq/highbank-cpufreq.c b/drivers/cpufreq/highbank-cpufreq.c
index b61b5a3fad64..794123fcf3e3 100644
--- a/drivers/cpufreq/highbank-cpufreq.c
+++ b/drivers/cpufreq/highbank-cpufreq.c
@@ -69,23 +69,17 @@ static int hb_cpufreq_driver_init(void)
 	if (!of_machine_is_compatible("calxeda,highbank"))
 		return -ENODEV;
 
-	for_each_child_of_node(of_find_node_by_path("/cpus"), np)
-		if (of_get_property(np, "operating-points", NULL))
-			break;
-
-	if (!np) {
-		pr_err("failed to find highbank cpufreq node\n");
-		return -ENOENT;
-	}
-
 	cpu_dev = get_cpu_device(0);
 	if (!cpu_dev) {
 		pr_err("failed to get highbank cpufreq device\n");
-		ret = -ENODEV;
-		goto out_put_node;
+		return -ENODEV;
 	}
 
-	cpu_dev->of_node = np;
+	np = of_node_get(cpu_dev->of_node);
+	if (!np) {
+		pr_err("failed to find highbank cpufreq node\n");
+		return -ENOENT;
+	}
 
 	cpu_clk = clk_get(cpu_dev, NULL);
 	if (IS_ERR(cpu_clk)) {
diff --git a/drivers/cpufreq/ia64-acpi-cpufreq.c b/drivers/cpufreq/ia64-acpi-cpufreq.c
index 573c14ea802d..3e14f0317175 100644
--- a/drivers/cpufreq/ia64-acpi-cpufreq.c
+++ b/drivers/cpufreq/ia64-acpi-cpufreq.c
@@ -274,7 +274,7 @@ acpi_cpufreq_cpu_init (
 
 	pr_debug("acpi_cpufreq_cpu_init\n");
 
-	data = kzalloc(sizeof(struct cpufreq_acpi_io), GFP_KERNEL);
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
 	if (!data)
 		return (-ENOMEM);
 
@@ -304,7 +304,7 @@ acpi_cpufreq_cpu_init (
 	}
 
 	/* alloc freq_table */
-	data->freq_table = kmalloc(sizeof(struct cpufreq_frequency_table) *
+	data->freq_table = kmalloc(sizeof(*data->freq_table) *
 	                           (data->acpi_data.state_count + 1),
 	                           GFP_KERNEL);
 	if (!data->freq_table) {
@@ -409,7 +409,6 @@ static struct cpufreq_driver acpi_cpufreq_driver = {
 	.init		= acpi_cpufreq_cpu_init,
 	.exit		= acpi_cpufreq_cpu_exit,
 	.name		= "acpi-cpufreq",
-	.owner		= THIS_MODULE,
 	.attr           = acpi_cpufreq_attr,
 };
 
diff --git a/drivers/cpufreq/imx6q-cpufreq.c b/drivers/cpufreq/imx6q-cpufreq.c
index e37cdaedbb5b..c3fd2a101ca0 100644
--- a/drivers/cpufreq/imx6q-cpufreq.c
+++ b/drivers/cpufreq/imx6q-cpufreq.c
@@ -7,6 +7,7 @@
  */
 
 #include <linux/clk.h>
+#include <linux/cpu.h>
 #include <linux/cpufreq.h>
 #include <linux/delay.h>
 #include <linux/err.h>
@@ -117,28 +118,11 @@ static int imx6q_set_target(struct cpufreq_policy *policy,
 	 *  - Reprogram pll1_sys_clk and reparent pll1_sw_clk back to it
 	 *  - Disable pll2_pfd2_396m_clk
 	 */
-	clk_prepare_enable(pll2_pfd2_396m_clk);
 	clk_set_parent(step_clk, pll2_pfd2_396m_clk);
 	clk_set_parent(pll1_sw_clk, step_clk);
 	if (freq_hz > clk_get_rate(pll2_pfd2_396m_clk)) {
 		clk_set_rate(pll1_sys_clk, freqs.new * 1000);
-		/*
-		 * If we are leaving 396 MHz set-point, we need to enable
-		 * pll1_sys_clk and disable pll2_pfd2_396m_clk to keep
-		 * their use count correct.
-		 */
-		if (freqs.old * 1000 <= clk_get_rate(pll2_pfd2_396m_clk)) {
-			clk_prepare_enable(pll1_sys_clk);
-			clk_disable_unprepare(pll2_pfd2_396m_clk);
-		}
 		clk_set_parent(pll1_sw_clk, pll1_sys_clk);
-		clk_disable_unprepare(pll2_pfd2_396m_clk);
-	} else {
-		/*
-		 * Disable pll1_sys_clk if pll2_pfd2_396m_clk is sufficient
-		 * to provide the frequency.
-		 */
-		clk_disable_unprepare(pll1_sys_clk);
 	}
 
 	/* Ensure the arm clock divider is what we expect */
@@ -219,16 +203,18 @@ static int imx6q_cpufreq_probe(struct platform_device *pdev)
 	unsigned long min_volt, max_volt;
 	int num, ret;
 
-	cpu_dev = &pdev->dev;
+	cpu_dev = get_cpu_device(0);
+	if (!cpu_dev) {
+		pr_err("failed to get cpu0 device\n");
+		return -ENODEV;
+	}
 
-	np = of_find_node_by_path("/cpus/cpu@0");
+	np = of_node_get(cpu_dev->of_node);
 	if (!np) {
 		dev_err(cpu_dev, "failed to find cpu0 node\n");
 		return -ENOENT;
 	}
 
-	cpu_dev->of_node = np;
-
 	arm_clk = devm_clk_get(cpu_dev, "arm");
 	pll1_sys_clk = devm_clk_get(cpu_dev, "pll1_sys");
 	pll1_sw_clk = devm_clk_get(cpu_dev, "pll1_sw");
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 7cde885011ed..badf6206b2b2 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -383,6 +383,7 @@ static void intel_pstate_get_min_max(struct cpudata *cpu, int *min, int *max)
 static void intel_pstate_set_pstate(struct cpudata *cpu, int pstate)
 {
 	int max_perf, min_perf;
+	u64 val;
 
 	intel_pstate_get_min_max(cpu, &min_perf, &max_perf);
 
@@ -394,8 +395,11 @@ static void intel_pstate_set_pstate(struct cpudata *cpu, int pstate)
 	trace_cpu_frequency(pstate * 100000, cpu->cpu);
 
 	cpu->pstate.current_pstate = pstate;
-	wrmsrl(MSR_IA32_PERF_CTL, pstate << 8);
+	val = pstate << 8;
+	if (limits.no_turbo)
+		val |= (u64)1 << 32;
 
+	wrmsrl(MSR_IA32_PERF_CTL, val);
 }
 
 static inline void intel_pstate_pstate_increase(struct cpudata *cpu, int steps)
@@ -522,6 +526,11 @@ static const struct x86_cpu_id intel_pstate_cpu_ids[] = {
 	ICPU(0x2a, default_policy),
 	ICPU(0x2d, default_policy),
 	ICPU(0x3a, default_policy),
+	ICPU(0x3c, default_policy),
+	ICPU(0x3e, default_policy),
+	ICPU(0x3f, default_policy),
+	ICPU(0x45, default_policy),
+	ICPU(0x46, default_policy),
 	{}
 };
 MODULE_DEVICE_TABLE(x86cpu, intel_pstate_cpu_ids);
@@ -629,8 +638,8 @@ static int intel_pstate_cpu_exit(struct cpufreq_policy *policy)
 
 static int intel_pstate_cpu_init(struct cpufreq_policy *policy)
 {
-	int rc, min_pstate, max_pstate;
 	struct cpudata *cpu;
+	int rc;
 
 	rc = intel_pstate_init_cpu(policy->cpu);
 	if (rc)
@@ -644,9 +653,8 @@ static int intel_pstate_cpu_init(struct cpufreq_policy *policy)
 	else
 		policy->policy = CPUFREQ_POLICY_POWERSAVE;
 
-	intel_pstate_get_min_max(cpu, &min_pstate, &max_pstate);
-	policy->min = min_pstate * 100000;
-	policy->max = max_pstate * 100000;
+	policy->min = cpu->pstate.min_pstate * 100000;
+	policy->max = cpu->pstate.turbo_pstate * 100000;
 
 	/* cpuinfo and default policy values */
 	policy->cpuinfo.min_freq = cpu->pstate.min_pstate * 100000;
@@ -665,7 +673,6 @@ static struct cpufreq_driver intel_pstate_driver = {
 	.init		= intel_pstate_cpu_init,
 	.exit		= intel_pstate_cpu_exit,
 	.name		= "intel_pstate",
-	.owner		= THIS_MODULE,
 };
 
 static int __initdata no_load;
diff --git a/drivers/cpufreq/kirkwood-cpufreq.c b/drivers/cpufreq/kirkwood-cpufreq.c
index c233ea617366..ba10658a9394 100644
--- a/drivers/cpufreq/kirkwood-cpufreq.c
+++ b/drivers/cpufreq/kirkwood-cpufreq.c
@@ -14,7 +14,7 @@
 #include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/cpufreq.h>
-#include <linux/of.h>
+#include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/io.h>
 #include <asm/proc-fns.h>
@@ -158,7 +158,6 @@ static struct cpufreq_driver kirkwood_cpufreq_driver = {
 	.init	= kirkwood_cpufreq_cpu_init,
 	.exit	= kirkwood_cpufreq_cpu_exit,
 	.name	= "kirkwood-cpufreq",
-	.owner	= THIS_MODULE,
 	.attr	= kirkwood_cpufreq_attr,
 };
 
@@ -175,9 +174,11 @@ static int kirkwood_cpufreq_probe(struct platform_device *pdev)
 	if (IS_ERR(priv.base))
 		return PTR_ERR(priv.base);
 
-	np = of_find_node_by_path("/cpus/cpu@0");
-	if (!np)
+	np = of_cpu_device_node_get(0);
+	if (!np) {
+		dev_err(&pdev->dev, "failed to get cpu device node\n");
 		return -ENODEV;
+	}
 
 	priv.cpu_clk = of_clk_get_by_name(np, "cpu_clk");
 	if (IS_ERR(priv.cpu_clk)) {
diff --git a/drivers/cpufreq/longhaul.c b/drivers/cpufreq/longhaul.c
index 8c49261df57d..4ada1cccb052 100644
--- a/drivers/cpufreq/longhaul.c
+++ b/drivers/cpufreq/longhaul.c
@@ -948,7 +948,6 @@ static struct cpufreq_driver longhaul_driver = {
 	.init	= longhaul_cpu_init,
 	.exit	= longhaul_cpu_exit,
 	.name	= "longhaul",
-	.owner	= THIS_MODULE,
 	.attr	= longhaul_attr,
 };
 
diff --git a/drivers/cpufreq/longrun.c b/drivers/cpufreq/longrun.c
index 0fe041d1f77f..5aa031612d53 100644
--- a/drivers/cpufreq/longrun.c
+++ b/drivers/cpufreq/longrun.c
@@ -286,7 +286,6 @@ static struct cpufreq_driver longrun_driver = {
 	.get		= longrun_get,
 	.init		= longrun_cpu_init,
 	.name		= "longrun",
-	.owner		= THIS_MODULE,
 };
 
 static const struct x86_cpu_id longrun_ids[] = {
diff --git a/drivers/cpufreq/loongson2_cpufreq.c b/drivers/cpufreq/loongson2_cpufreq.c
index 9536852c504a..7bc3c44d34e2 100644
--- a/drivers/cpufreq/loongson2_cpufreq.c
+++ b/drivers/cpufreq/loongson2_cpufreq.c
@@ -158,7 +158,6 @@ static struct freq_attr *loongson2_table_attr[] = {
 };
 
 static struct cpufreq_driver loongson2_cpufreq_driver = {
-	.owner = THIS_MODULE,
 	.name = "loongson2",
 	.init = loongson2_cpufreq_cpu_init,
 	.verify = loongson2_cpufreq_verify,
diff --git a/drivers/cpufreq/maple-cpufreq.c b/drivers/cpufreq/maple-cpufreq.c
index cdd62915efaf..6168d77b296d 100644
--- a/drivers/cpufreq/maple-cpufreq.c
+++ b/drivers/cpufreq/maple-cpufreq.c
@@ -24,7 +24,7 @@
 #include <linux/completion.h>
 #include <linux/mutex.h>
 #include <linux/time.h>
-#include <linux/of.h>
+#include <linux/of_device.h>
 
 #define DBG(fmt...) pr_debug(fmt)
 
@@ -190,7 +190,6 @@ static int maple_cpufreq_cpu_init(struct cpufreq_policy *policy)
 
 static struct cpufreq_driver maple_cpufreq_driver = {
 	.name		= "maple",
-	.owner		= THIS_MODULE,
 	.flags		= CPUFREQ_CONST_LOOPS,
 	.init		= maple_cpufreq_cpu_init,
 	.verify		= maple_cpufreq_verify,
@@ -201,7 +200,6 @@ static struct cpufreq_driver maple_cpufreq_driver = {
 
 static int __init maple_cpufreq_init(void)
 {
-	struct device_node *cpus;
 	struct device_node *cpunode;
 	unsigned int psize;
 	unsigned long max_freq;
@@ -217,24 +215,11 @@ static int __init maple_cpufreq_init(void)
 	    !of_machine_is_compatible("Momentum,Apache"))
 		return 0;
 
-	cpus = of_find_node_by_path("/cpus");
-	if (cpus == NULL) {
-		DBG("No /cpus node !\n");
-		return -ENODEV;
-	}
-
 	/* Get first CPU node */
-	for (cpunode = NULL;
-	     (cpunode = of_get_next_child(cpus, cpunode)) != NULL;) {
-		const u32 *reg = of_get_property(cpunode, "reg", NULL);
-		if (reg == NULL || (*reg) != 0)
-			continue;
-		if (!strcmp(cpunode->type, "cpu"))
-			break;
-	}
+	cpunode = of_cpu_device_node_get(0);
 	if (cpunode == NULL) {
 		printk(KERN_ERR "cpufreq: Can't find any CPU 0 node\n");
-		goto bail_cpus;
+		goto bail_noprops;
 	}
 
 	/* Check 970FX for now */
@@ -290,14 +275,11 @@ static int __init maple_cpufreq_init(void)
 	rc = cpufreq_register_driver(&maple_cpufreq_driver);
 
 	of_node_put(cpunode);
-	of_node_put(cpus);
 
 	return rc;
 
 bail_noprops:
 	of_node_put(cpunode);
-bail_cpus:
-	of_node_put(cpus);
 
 	return rc;
 }
diff --git a/drivers/cpufreq/mperf.c b/drivers/cpufreq/mperf.c
deleted file mode 100644
index 911e193018ae..000000000000
--- a/drivers/cpufreq/mperf.c
+++ /dev/null
@@ -1,51 +0,0 @@
-#include <linux/kernel.h>
-#include <linux/smp.h>
-#include <linux/module.h>
-#include <linux/init.h>
-#include <linux/cpufreq.h>
-#include <linux/slab.h>
-
-#include "mperf.h"
-
-static DEFINE_PER_CPU(struct aperfmperf, acfreq_old_perf);
-
-/* Called via smp_call_function_single(), on the target CPU */
-static void read_measured_perf_ctrs(void *_cur)
-{
-	struct aperfmperf *am = _cur;
-
-	get_aperfmperf(am);
-}
-
-/*
- * Return the measured active (C0) frequency on this CPU since last call
- * to this function.
- * Input: cpu number
- * Return: Average CPU frequency in terms of max frequency (zero on error)
- *
- * We use IA32_MPERF and IA32_APERF MSRs to get the measured performance
- * over a period of time, while CPU is in C0 state.
- * IA32_MPERF counts at the rate of max advertised frequency
- * IA32_APERF counts at the rate of actual CPU frequency
- * Only IA32_APERF/IA32_MPERF ratio is architecturally defined and
- * no meaning should be associated with absolute values of these MSRs.
- */
-unsigned int cpufreq_get_measured_perf(struct cpufreq_policy *policy,
-					unsigned int cpu)
-{
-	struct aperfmperf perf;
-	unsigned long ratio;
-	unsigned int retval;
-
-	if (smp_call_function_single(cpu, read_measured_perf_ctrs, &perf, 1))
-		return 0;
-
-	ratio = calc_aperfmperf_ratio(&per_cpu(acfreq_old_perf, cpu), &perf);
-	per_cpu(acfreq_old_perf, cpu) = perf;
-
-	retval = (policy->cpuinfo.max_freq * ratio) >> APERFMPERF_SHIFT;
-
-	return retval;
-}
-EXPORT_SYMBOL_GPL(cpufreq_get_measured_perf);
-MODULE_LICENSE("GPL");
diff --git a/drivers/cpufreq/mperf.h b/drivers/cpufreq/mperf.h
deleted file mode 100644
index 5dbf2950dc22..000000000000
--- a/drivers/cpufreq/mperf.h
+++ /dev/null
@@ -1,9 +0,0 @@
-/*
- *  (c) 2010 Advanced Micro Devices, Inc.
- *  Your use of this code is subject to the terms and conditions of the
- *  GNU general public license version 2. See "COPYING" or
- *  http://www.gnu.org/licenses/gpl.html
- */
-
-unsigned int cpufreq_get_measured_perf(struct cpufreq_policy *policy,
-					unsigned int cpu);
diff --git a/drivers/cpufreq/p4-clockmod.c b/drivers/cpufreq/p4-clockmod.c
index 9ee78170ff86..2f0a2a65c37f 100644
--- a/drivers/cpufreq/p4-clockmod.c
+++ b/drivers/cpufreq/p4-clockmod.c
@@ -279,7 +279,6 @@ static struct cpufreq_driver p4clockmod_driver = {
 	.exit		= cpufreq_p4_cpu_exit,
 	.get		= cpufreq_p4_get,
 	.name		= "p4-clockmod",
-	.owner		= THIS_MODULE,
 	.attr		= p4clockmod_attr,
 };
 
diff --git a/drivers/cpufreq/pasemi-cpufreq.c b/drivers/cpufreq/pasemi-cpufreq.c
index b704da404067..534e43a60d1f 100644
--- a/drivers/cpufreq/pasemi-cpufreq.c
+++ b/drivers/cpufreq/pasemi-cpufreq.c
@@ -297,7 +297,6 @@ static int pas_cpufreq_target(struct cpufreq_policy *policy,
 
 static struct cpufreq_driver pas_cpufreq_driver = {
 	.name		= "pas-cpufreq",
-	.owner		= THIS_MODULE,
 	.flags		= CPUFREQ_CONST_LOOPS,
 	.init		= pas_cpufreq_cpu_init,
 	.exit		= pas_cpufreq_cpu_exit,
diff --git a/drivers/cpufreq/pcc-cpufreq.c b/drivers/cpufreq/pcc-cpufreq.c
index 1581fcc4cf4a..d81c4e5ea0ad 100644
--- a/drivers/cpufreq/pcc-cpufreq.c
+++ b/drivers/cpufreq/pcc-cpufreq.c
@@ -587,7 +587,6 @@ static struct cpufreq_driver pcc_cpufreq_driver = {
 	.init = pcc_cpufreq_cpu_init,
 	.exit = pcc_cpufreq_cpu_exit,
 	.name = "pcc-cpufreq",
-	.owner = THIS_MODULE,
 };
 
 static int __init pcc_cpufreq_init(void)
diff --git a/drivers/cpufreq/pmac32-cpufreq.c b/drivers/cpufreq/pmac32-cpufreq.c
index 3104fad82480..a096cd3fa23d 100644
--- a/drivers/cpufreq/pmac32-cpufreq.c
+++ b/drivers/cpufreq/pmac32-cpufreq.c
@@ -25,6 +25,7 @@
 #include <linux/init.h>
 #include <linux/device.h>
 #include <linux/hardirq.h>
+#include <linux/of_device.h>
 #include <asm/prom.h>
 #include <asm/machdep.h>
 #include <asm/irq.h>
@@ -477,7 +478,6 @@ static struct cpufreq_driver pmac_cpufreq_driver = {
 	.flags		= CPUFREQ_PM_NO_WARN,
 	.attr		= pmac_cpu_freqs_attr,
 	.name		= "powermac",
-	.owner		= THIS_MODULE,
 };
 
 
@@ -649,8 +649,8 @@ static int __init pmac_cpufreq_setup(void)
 	if (strstr(cmd_line, "nocpufreq"))
 		return 0;
 
-	/* Assume only one CPU */
-	cpunode = of_find_node_by_type(NULL, "cpu");
+	/* Get first CPU node */
+	cpunode = of_cpu_device_node_get(0);
 	if (!cpunode)
 		goto out;
 
diff --git a/drivers/cpufreq/pmac64-cpufreq.c b/drivers/cpufreq/pmac64-cpufreq.c
index 7ba423431cfe..3a51ad7e47c8 100644
--- a/drivers/cpufreq/pmac64-cpufreq.c
+++ b/drivers/cpufreq/pmac64-cpufreq.c
@@ -22,6 +22,7 @@
 #include <linux/init.h>
 #include <linux/completion.h>
 #include <linux/mutex.h>
+#include <linux/of_device.h>
 #include <asm/prom.h>
 #include <asm/machdep.h>
 #include <asm/irq.h>
@@ -371,7 +372,6 @@ static int g5_cpufreq_cpu_init(struct cpufreq_policy *policy)
 
 static struct cpufreq_driver g5_cpufreq_driver = {
 	.name		= "powermac",
-	.owner		= THIS_MODULE,
 	.flags		= CPUFREQ_CONST_LOOPS,
 	.init		= g5_cpufreq_cpu_init,
 	.verify		= g5_cpufreq_verify,
@@ -383,9 +383,8 @@ static struct cpufreq_driver g5_cpufreq_driver = {
 
 #ifdef CONFIG_PMAC_SMU
 
-static int __init g5_neo2_cpufreq_init(struct device_node *cpus)
+static int __init g5_neo2_cpufreq_init(struct device_node *cpunode)
 {
-	struct device_node *cpunode;
 	unsigned int psize, ssize;
 	unsigned long max_freq;
 	char *freq_method, *volt_method;
@@ -405,20 +404,6 @@ static int __init g5_neo2_cpufreq_init(struct device_node *cpus)
 	else
 		return -ENODEV;
 
-	/* Get first CPU node */
-	for (cpunode = NULL;
-	     (cpunode = of_get_next_child(cpus, cpunode)) != NULL;) {
-		const u32 *reg = of_get_property(cpunode, "reg", NULL);
-		if (reg == NULL || (*reg) != 0)
-			continue;
-		if (!strcmp(cpunode->type, "cpu"))
-			break;
-	}
-	if (cpunode == NULL) {
-		printk(KERN_ERR "cpufreq: Can't find any CPU 0 node\n");
-		return -ENODEV;
-	}
-
 	/* Check 970FX for now */
 	valp = of_get_property(cpunode, "cpu-version", NULL);
 	if (!valp) {
@@ -447,9 +432,8 @@ static int __init g5_neo2_cpufreq_init(struct device_node *cpus)
 		if (!shdr)
 			goto bail_noprops;
 		g5_fvt_table = (struct smu_sdbp_fvt *)&shdr[1];
-		ssize = (shdr->len * sizeof(u32)) -
-			sizeof(struct smu_sdbp_header);
-		g5_fvt_count = ssize / sizeof(struct smu_sdbp_fvt);
+		ssize = (shdr->len * sizeof(u32)) - sizeof(*shdr);
+		g5_fvt_count = ssize / sizeof(*g5_fvt_table);
 		g5_fvt_cur = 0;
 
 		/* Sanity checking */
@@ -537,9 +521,9 @@ static int __init g5_neo2_cpufreq_init(struct device_node *cpus)
 #endif /* CONFIG_PMAC_SMU */
 
 
-static int __init g5_pm72_cpufreq_init(struct device_node *cpus)
+static int __init g5_pm72_cpufreq_init(struct device_node *cpunode)
 {
-	struct device_node *cpuid = NULL, *hwclock = NULL, *cpunode = NULL;
+	struct device_node *cpuid = NULL, *hwclock = NULL;
 	const u8 *eeprom = NULL;
 	const u32 *valp;
 	u64 max_freq, min_freq, ih, il;
@@ -548,17 +532,6 @@ static int __init g5_pm72_cpufreq_init(struct device_node *cpus)
 	DBG("cpufreq: Initializing for PowerMac7,2, PowerMac7,3 and"
 	    " RackMac3,1...\n");
 
-	/* Get first CPU node */
-	for (cpunode = NULL;
-	     (cpunode = of_get_next_child(cpus, cpunode)) != NULL;) {
-		if (!strcmp(cpunode->type, "cpu"))
-			break;
-	}
-	if (cpunode == NULL) {
-		printk(KERN_ERR "cpufreq: Can't find any CPU node\n");
-		return -ENODEV;
-	}
-
 	/* Lookup the cpuid eeprom node */
         cpuid = of_find_node_by_path("/u3@0,f8000000/i2c@f8001000/cpuid@a0");
 	if (cpuid != NULL)
@@ -718,25 +691,25 @@ static int __init g5_pm72_cpufreq_init(struct device_node *cpus)
 
 static int __init g5_cpufreq_init(void)
 {
-	struct device_node *cpus;
+	struct device_node *cpunode;
 	int rc = 0;
 
-	cpus = of_find_node_by_path("/cpus");
-	if (cpus == NULL) {
-		DBG("No /cpus node !\n");
+	/* Get first CPU node */
+	cpunode = of_cpu_device_node_get(0);
+	if (cpunode == NULL) {
+		pr_err("cpufreq: Can't find any CPU node\n");
 		return -ENODEV;
 	}
 
 	if (of_machine_is_compatible("PowerMac7,2") ||
 	    of_machine_is_compatible("PowerMac7,3") ||
 	    of_machine_is_compatible("RackMac3,1"))
-		rc = g5_pm72_cpufreq_init(cpus);
+		rc = g5_pm72_cpufreq_init(cpunode);
 #ifdef CONFIG_PMAC_SMU
 	else
-		rc = g5_neo2_cpufreq_init(cpus);
+		rc = g5_neo2_cpufreq_init(cpunode);
 #endif /* CONFIG_PMAC_SMU */
 
-	of_node_put(cpus);
 	return rc;
 }
 
diff --git a/drivers/cpufreq/powernow-k6.c b/drivers/cpufreq/powernow-k6.c
index ea8e10382ec5..85f1c8c25ddc 100644
--- a/drivers/cpufreq/powernow-k6.c
+++ b/drivers/cpufreq/powernow-k6.c
@@ -207,7 +207,6 @@ static struct cpufreq_driver powernow_k6_driver = {
 	.exit		= powernow_k6_cpu_exit,
 	.get		= powernow_k6_get,
 	.name		= "powernow-k6",
-	.owner		= THIS_MODULE,
 	.attr		= powernow_k6_attr,
 };
 
diff --git a/drivers/cpufreq/powernow-k7.c b/drivers/cpufreq/powernow-k7.c
index 955870877935..14ce480be8ab 100644
--- a/drivers/cpufreq/powernow-k7.c
+++ b/drivers/cpufreq/powernow-k7.c
@@ -177,7 +177,7 @@ static int get_ranges(unsigned char *pst)
 	unsigned int speed;
 	u8 fid, vid;
 
-	powernow_table = kzalloc((sizeof(struct cpufreq_frequency_table) *
+	powernow_table = kzalloc((sizeof(*powernow_table) *
 				(number_scales + 1)), GFP_KERNEL);
 	if (!powernow_table)
 		return -ENOMEM;
@@ -309,8 +309,7 @@ static int powernow_acpi_init(void)
 		goto err0;
 	}
 
-	acpi_processor_perf = kzalloc(sizeof(struct acpi_processor_performance),
-				      GFP_KERNEL);
+	acpi_processor_perf = kzalloc(sizeof(*acpi_processor_perf), GFP_KERNEL);
 	if (!acpi_processor_perf) {
 		retval = -ENOMEM;
 		goto err0;
@@ -346,7 +345,7 @@ static int powernow_acpi_init(void)
 		goto err2;
 	}
 
-	powernow_table = kzalloc((sizeof(struct cpufreq_frequency_table) *
+	powernow_table = kzalloc((sizeof(*powernow_table) *
 				(number_scales + 1)), GFP_KERNEL);
 	if (!powernow_table) {
 		retval = -ENOMEM;
@@ -497,7 +496,7 @@ static int powernow_decode_bios(int maxfid, int startvid)
 					"relevant to this CPU).\n",
 					psb->numpst);
 
-			p += sizeof(struct psb_s);
+			p += sizeof(*psb);
 
 			pst = (struct pst_s *) p;
 
@@ -510,12 +509,12 @@ static int powernow_decode_bios(int maxfid, int startvid)
 				    (maxfid == pst->maxfid) &&
 				    (startvid == pst->startvid)) {
 					print_pst_entry(pst, j);
-					p = (char *)pst + sizeof(struct pst_s);
+					p = (char *)pst + sizeof(*pst);
 					ret = get_ranges(p);
 					return ret;
 				} else {
 					unsigned int k;
-					p = (char *)pst + sizeof(struct pst_s);
+					p = (char *)pst + sizeof(*pst);
 					for (k = 0; k < number_scales; k++)
 						p += 2;
 				}
@@ -717,7 +716,6 @@ static struct cpufreq_driver powernow_driver = {
 	.init		= powernow_cpu_init,
 	.exit		= powernow_cpu_exit,
 	.name		= "powernow-k7",
-	.owner		= THIS_MODULE,
 	.attr		= powernow_table_attr,
 };
 
diff --git a/drivers/cpufreq/powernow-k8.c b/drivers/cpufreq/powernow-k8.c
index c39d189217cb..2344a9ed17f3 100644
--- a/drivers/cpufreq/powernow-k8.c
+++ b/drivers/cpufreq/powernow-k8.c
@@ -623,7 +623,7 @@ static int fill_powernow_table(struct powernow_k8_data *data,
 	if (check_pst_table(data, pst, maxvid))
 		return -EINVAL;
 
-	powernow_table = kmalloc((sizeof(struct cpufreq_frequency_table)
+	powernow_table = kmalloc((sizeof(*powernow_table)
 		* (data->numps + 1)), GFP_KERNEL);
 	if (!powernow_table) {
 		printk(KERN_ERR PFX "powernow_table memory alloc failure\n");
@@ -793,7 +793,7 @@ static int powernow_k8_cpu_init_acpi(struct powernow_k8_data *data)
 	}
 
 	/* fill in data->powernow_table */
-	powernow_table = kmalloc((sizeof(struct cpufreq_frequency_table)
+	powernow_table = kmalloc((sizeof(*powernow_table)
 		* (data->acpi_data.state_count + 1)), GFP_KERNEL);
 	if (!powernow_table) {
 		pr_debug("powernow_table memory alloc failure\n");
@@ -1106,7 +1106,7 @@ static int powernowk8_cpu_init(struct cpufreq_policy *pol)
 	if (rc)
 		return -ENODEV;
 
-	data = kzalloc(sizeof(struct powernow_k8_data), GFP_KERNEL);
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
 	if (!data) {
 		printk(KERN_ERR PFX "unable to alloc powernow_k8_data");
 		return -ENOMEM;
@@ -1240,7 +1240,6 @@ static struct cpufreq_driver cpufreq_amd64_driver = {
 	.exit		= powernowk8_cpu_exit,
 	.get		= powernowk8_get,
 	.name		= "powernow-k8",
-	.owner		= THIS_MODULE,
 	.attr		= powernow_k8_attr,
 };
 
diff --git a/drivers/cpufreq/ppc-corenet-cpufreq.c b/drivers/cpufreq/ppc-corenet-cpufreq.c
index 3cae4529f959..60e81d524ea8 100644
--- a/drivers/cpufreq/ppc-corenet-cpufreq.c
+++ b/drivers/cpufreq/ppc-corenet-cpufreq.c
@@ -300,7 +300,6 @@ static struct freq_attr *corenet_cpufreq_attr[] = {
 
 static struct cpufreq_driver ppc_corenet_cpufreq_driver = {
 	.name		= "ppc_cpufreq",
-	.owner		= THIS_MODULE,
 	.flags		= CPUFREQ_CONST_LOOPS,
 	.init		= corenet_cpufreq_cpu_init,
 	.exit		= __exit_p(corenet_cpufreq_cpu_exit),
diff --git a/drivers/cpufreq/ppc_cbe_cpufreq.c b/drivers/cpufreq/ppc_cbe_cpufreq.c
index 5936f8d6f2cc..2e448f0bbdc5 100644
--- a/drivers/cpufreq/ppc_cbe_cpufreq.c
+++ b/drivers/cpufreq/ppc_cbe_cpufreq.c
@@ -181,7 +181,6 @@ static struct cpufreq_driver cbe_cpufreq_driver = {
 	.init		= cbe_cpufreq_cpu_init,
 	.exit		= cbe_cpufreq_cpu_exit,
 	.name		= "cbe-cpufreq",
-	.owner		= THIS_MODULE,
 	.flags		= CPUFREQ_CONST_LOOPS,
 };
 
diff --git a/drivers/cpufreq/pxa2xx-cpufreq.c b/drivers/cpufreq/pxa2xx-cpufreq.c
index fb3981ac829f..8749eaf18793 100644
--- a/drivers/cpufreq/pxa2xx-cpufreq.c
+++ b/drivers/cpufreq/pxa2xx-cpufreq.c
@@ -191,7 +191,7 @@ static int pxa_cpufreq_change_voltage(pxa_freqs_t *pxa_freq)
 	return ret;
 }
 
-static __init void pxa_cpufreq_init_voltages(void)
+static void __init pxa_cpufreq_init_voltages(void)
 {
 	vcc_core = regulator_get(NULL, "vcc_core");
 	if (IS_ERR(vcc_core)) {
@@ -207,7 +207,7 @@ static int pxa_cpufreq_change_voltage(pxa_freqs_t *pxa_freq)
 	return 0;
 }
 
-static __init void pxa_cpufreq_init_voltages(void) { }
+static void __init pxa_cpufreq_init_voltages(void) { }
 #endif
 
 static void find_freq_tables(struct cpufreq_frequency_table **freq_table,
diff --git a/drivers/cpufreq/pxa3xx-cpufreq.c b/drivers/cpufreq/pxa3xx-cpufreq.c
index 9c92ef032a9e..d26306fb00d2 100644
--- a/drivers/cpufreq/pxa3xx-cpufreq.c
+++ b/drivers/cpufreq/pxa3xx-cpufreq.c
@@ -213,10 +213,12 @@ static int pxa3xx_cpufreq_init(struct cpufreq_policy *policy)
 	policy->cur = policy->min = policy->max;
 
 	if (cpu_is_pxa300() || cpu_is_pxa310())
-		ret = setup_freqs_table(policy, ARRAY_AND_SIZE(pxa300_freqs));
+		ret = setup_freqs_table(policy, pxa300_freqs,
+					ARRAY_SIZE(pxa300_freqs));
 
 	if (cpu_is_pxa320())
-		ret = setup_freqs_table(policy, ARRAY_AND_SIZE(pxa320_freqs));
+		ret = setup_freqs_table(policy, pxa320_freqs,
+					ARRAY_SIZE(pxa320_freqs));
 
 	if (ret) {
 		pr_err("failed to setup frequency table\n");
diff --git a/drivers/cpufreq/s3c2416-cpufreq.c b/drivers/cpufreq/s3c2416-cpufreq.c
index ce5b9fca9c18..22dcb81ef9d0 100644
--- a/drivers/cpufreq/s3c2416-cpufreq.c
+++ b/drivers/cpufreq/s3c2416-cpufreq.c
@@ -524,7 +524,6 @@ static struct freq_attr *s3c2416_cpufreq_attr[] = {
 };
 
 static struct cpufreq_driver s3c2416_cpufreq_driver = {
-	.owner		= THIS_MODULE,
 	.flags          = 0,
 	.verify		= s3c2416_cpufreq_verify_speed,
 	.target		= s3c2416_cpufreq_set_target,
diff --git a/drivers/cpufreq/s3c24xx-cpufreq.c b/drivers/cpufreq/s3c24xx-cpufreq.c
index 87781eb20d6d..b0f343fcb7ee 100644
--- a/drivers/cpufreq/s3c24xx-cpufreq.c
+++ b/drivers/cpufreq/s3c24xx-cpufreq.c
@@ -392,7 +392,7 @@ static int s3c_cpufreq_init(struct cpufreq_policy *policy)
 	return 0;
 }
 
-static __init int s3c_cpufreq_initclks(void)
+static int __init s3c_cpufreq_initclks(void)
 {
 	_clk_mpll = s3c_cpufreq_clk_get(NULL, "mpll");
 	_clk_xtal = s3c_cpufreq_clk_get(NULL, "xtal");
@@ -522,7 +522,7 @@ int __init s3c_cpufreq_setboard(struct s3c_cpufreq_board *board)
 	/* Copy the board information so that each board can make this
 	 * initdata. */
 
-	ours = kzalloc(sizeof(struct s3c_cpufreq_board), GFP_KERNEL);
+	ours = kzalloc(sizeof(*ours), GFP_KERNEL);
 	if (ours == NULL) {
 		printk(KERN_ERR "%s: no memory\n", __func__);
 		return -ENOMEM;
@@ -615,7 +615,7 @@ static int s3c_cpufreq_build_freq(void)
 	size = cpu_cur.info->calc_freqtable(&cpu_cur, NULL, 0);
 	size++;
 
-	ftab = kmalloc(sizeof(struct cpufreq_frequency_table) * size, GFP_KERNEL);
+	ftab = kmalloc(sizeof(*ftab) * size, GFP_KERNEL);
 	if (!ftab) {
 		printk(KERN_ERR "%s: no memory for tables\n", __func__);
 		return -ENOMEM;
@@ -691,7 +691,7 @@ int __init s3c_plltab_register(struct cpufreq_frequency_table *plls,
 	struct cpufreq_frequency_table *vals;
 	unsigned int size;
 
-	size = sizeof(struct cpufreq_frequency_table) * (plls_no + 1);
+	size = sizeof(*vals) * (plls_no + 1);
 
 	vals = kmalloc(size, GFP_KERNEL);
 	if (vals) {
diff --git a/drivers/cpufreq/s3c64xx-cpufreq.c b/drivers/cpufreq/s3c64xx-cpufreq.c
index 13bb4bae64ee..15631f92ab7d 100644
--- a/drivers/cpufreq/s3c64xx-cpufreq.c
+++ b/drivers/cpufreq/s3c64xx-cpufreq.c
@@ -166,7 +166,7 @@ static void __init s3c64xx_cpufreq_config_regulator(void)
 		if (freq->frequency == CPUFREQ_ENTRY_INVALID)
 			continue;
 
-		dvfs = &s3c64xx_dvfs_table[freq->index];
+		dvfs = &s3c64xx_dvfs_table[freq->driver_data];
 		found = 0;
 
 		for (i = 0; i < count; i++) {
@@ -263,7 +263,6 @@ static int s3c64xx_cpufreq_driver_init(struct cpufreq_policy *policy)
 }
 
 static struct cpufreq_driver s3c64xx_cpufreq_driver = {
-	.owner		= THIS_MODULE,
 	.flags          = 0,
 	.verify		= s3c64xx_cpufreq_verify_speed,
 	.target		= s3c64xx_cpufreq_set_target,
diff --git a/drivers/cpufreq/sc520_freq.c b/drivers/cpufreq/sc520_freq.c
index 77a210975fc4..d6f6c6f4efa7 100644
--- a/drivers/cpufreq/sc520_freq.c
+++ b/drivers/cpufreq/sc520_freq.c
@@ -147,7 +147,6 @@ static struct cpufreq_driver sc520_freq_driver = {
 	.init	= sc520_freq_cpu_init,
 	.exit	= sc520_freq_cpu_exit,
 	.name	= "sc520_freq",
-	.owner	= THIS_MODULE,
 	.attr	= sc520_freq_attr,
 };
 
diff --git a/drivers/cpufreq/sh-cpufreq.c b/drivers/cpufreq/sh-cpufreq.c
index 73adb64651e8..ffc6d24b0cfb 100644
--- a/drivers/cpufreq/sh-cpufreq.c
+++ b/drivers/cpufreq/sh-cpufreq.c
@@ -160,7 +160,6 @@ static struct freq_attr *sh_freq_attr[] = {
 };
 
 static struct cpufreq_driver sh_cpufreq_driver = {
-	.owner		= THIS_MODULE,
 	.name		= "sh",
 	.get		= sh_cpufreq_get,
 	.target		= sh_cpufreq_target,
diff --git a/drivers/cpufreq/sparc-us2e-cpufreq.c b/drivers/cpufreq/sparc-us2e-cpufreq.c
index 93061a408773..cf5bc2ca16fa 100644
--- a/drivers/cpufreq/sparc-us2e-cpufreq.c
+++ b/drivers/cpufreq/sparc-us2e-cpufreq.c
@@ -351,12 +351,11 @@ static int __init us2e_freq_init(void)
 		struct cpufreq_driver *driver;
 
 		ret = -ENOMEM;
-		driver = kzalloc(sizeof(struct cpufreq_driver), GFP_KERNEL);
+		driver = kzalloc(sizeof(*driver), GFP_KERNEL);
 		if (!driver)
 			goto err_out;
 
-		us2e_freq_table = kzalloc(
-			(NR_CPUS * sizeof(struct us2e_freq_percpu_info)),
+		us2e_freq_table = kzalloc((NR_CPUS * sizeof(*us2e_freq_table)),
 			GFP_KERNEL);
 		if (!us2e_freq_table)
 			goto err_out;
@@ -366,7 +365,6 @@ static int __init us2e_freq_init(void)
 		driver->target = us2e_freq_target;
 		driver->get = us2e_freq_get;
 		driver->exit = us2e_freq_cpu_exit;
-		driver->owner = THIS_MODULE,
 		strcpy(driver->name, "UltraSPARC-IIe");
 
 		cpufreq_us2e_driver = driver;
diff --git a/drivers/cpufreq/sparc-us3-cpufreq.c b/drivers/cpufreq/sparc-us3-cpufreq.c
index 880ee293d61e..ac76b489979d 100644
--- a/drivers/cpufreq/sparc-us3-cpufreq.c
+++ b/drivers/cpufreq/sparc-us3-cpufreq.c
@@ -212,12 +212,11 @@ static int __init us3_freq_init(void)
 		struct cpufreq_driver *driver;
 
 		ret = -ENOMEM;
-		driver = kzalloc(sizeof(struct cpufreq_driver), GFP_KERNEL);
+		driver = kzalloc(sizeof(*driver), GFP_KERNEL);
 		if (!driver)
 			goto err_out;
 
-		us3_freq_table = kzalloc(
-			(NR_CPUS * sizeof(struct us3_freq_percpu_info)),
+		us3_freq_table = kzalloc((NR_CPUS * sizeof(*us3_freq_table)),
 			GFP_KERNEL);
 		if (!us3_freq_table)
 			goto err_out;
@@ -227,7 +226,6 @@ static int __init us3_freq_init(void)
 		driver->target = us3_freq_target;
 		driver->get = us3_freq_get;
 		driver->exit = us3_freq_cpu_exit;
-		driver->owner = THIS_MODULE,
 		strcpy(driver->name, "UltraSPARC-III");
 
 		cpufreq_us3_driver = driver;
diff --git a/drivers/cpufreq/spear-cpufreq.c b/drivers/cpufreq/spear-cpufreq.c
index c3efa7f2a908..3f418166ce02 100644
--- a/drivers/cpufreq/spear-cpufreq.c
+++ b/drivers/cpufreq/spear-cpufreq.c
@@ -18,7 +18,7 @@
 #include <linux/err.h>
 #include <linux/init.h>
 #include <linux/module.h>
-#include <linux/of.h>
+#include <linux/of_device.h>
 #include <linux/slab.h>
 #include <linux/types.h>
 
@@ -113,7 +113,7 @@ static int spear_cpufreq_target(struct cpufreq_policy *policy,
 		unsigned int target_freq, unsigned int relation)
 {
 	struct cpufreq_freqs freqs;
-	unsigned long newfreq;
+	long newfreq;
 	struct clk *srcclk;
 	int index, ret, mult = 1;
 
@@ -223,7 +223,7 @@ static int spear_cpufreq_driver_init(void)
 	const __be32 *val;
 	int cnt, i, ret;
 
-	np = of_find_node_by_path("/cpus/cpu@0");
+	np = of_cpu_device_node_get(0);
 	if (!np) {
 		pr_err("No cpu node found");
 		return -ENODEV;
diff --git a/drivers/cpufreq/speedstep-centrino.c b/drivers/cpufreq/speedstep-centrino.c
index 0915e712fbdc..f897d5105842 100644
--- a/drivers/cpufreq/speedstep-centrino.c
+++ b/drivers/cpufreq/speedstep-centrino.c
@@ -575,7 +575,6 @@ static struct cpufreq_driver centrino_driver = {
 	.target		= centrino_target,
 	.get		= get_cur_freq,
 	.attr           = centrino_attr,
-	.owner		= THIS_MODULE,
 };
 
 /*
diff --git a/drivers/cpufreq/speedstep-ich.c b/drivers/cpufreq/speedstep-ich.c
index e2e5aa971452..5355abb69afc 100644
--- a/drivers/cpufreq/speedstep-ich.c
+++ b/drivers/cpufreq/speedstep-ich.c
@@ -378,7 +378,6 @@ static struct cpufreq_driver speedstep_driver = {
 	.init	= speedstep_cpu_init,
 	.exit	= speedstep_cpu_exit,
 	.get	= speedstep_get,
-	.owner	= THIS_MODULE,
 	.attr	= speedstep_attr,
 };
 
diff --git a/drivers/cpufreq/speedstep-smi.c b/drivers/cpufreq/speedstep-smi.c
index f5a6b70ee6c0..abfba4f731eb 100644
--- a/drivers/cpufreq/speedstep-smi.c
+++ b/drivers/cpufreq/speedstep-smi.c
@@ -375,7 +375,6 @@ static struct cpufreq_driver speedstep_driver = {
 	.exit		= speedstep_cpu_exit,
 	.get		= speedstep_get,
 	.resume		= speedstep_resume,
-	.owner		= THIS_MODULE,
 	.attr		= speedstep_attr,
 };
 
diff --git a/drivers/cpufreq/tegra-cpufreq.c b/drivers/cpufreq/tegra-cpufreq.c
index cd66b85d927c..a7b876fdc1d8 100644
--- a/drivers/cpufreq/tegra-cpufreq.c
+++ b/drivers/cpufreq/tegra-cpufreq.c
@@ -255,7 +255,7 @@ static struct cpufreq_driver tegra_cpufreq_driver = {
 
 static int __init tegra_cpufreq_init(void)
 {
-	cpu_clk = clk_get_sys(NULL, "cpu");
+	cpu_clk = clk_get_sys(NULL, "cclk");
 	if (IS_ERR(cpu_clk))
 		return PTR_ERR(cpu_clk);
 
@@ -263,7 +263,7 @@ static int __init tegra_cpufreq_init(void)
 	if (IS_ERR(pll_x_clk))
 		return PTR_ERR(pll_x_clk);
 
-	pll_p_clk = clk_get_sys(NULL, "pll_p_cclk");
+	pll_p_clk = clk_get_sys(NULL, "pll_p");
 	if (IS_ERR(pll_p_clk))
 		return PTR_ERR(pll_p_clk);
 
diff --git a/drivers/cpufreq/unicore2-cpufreq.c b/drivers/cpufreq/unicore2-cpufreq.c
index 12fc904d7dab..b225f04d8ae5 100644
--- a/drivers/cpufreq/unicore2-cpufreq.c
+++ b/drivers/cpufreq/unicore2-cpufreq.c
@@ -24,7 +24,7 @@ static struct cpufreq_driver ucv2_driver;
 /* make sure that only the "userspace" governor is run
  * -- anything else wouldn't make sense on this platform, anyway.
  */
-int ucv2_verify_speed(struct cpufreq_policy *policy)
+static int ucv2_verify_speed(struct cpufreq_policy *policy)
 {
 	if (policy->cpu)
 		return -EINVAL;
diff --git a/drivers/cpuidle/Kconfig b/drivers/cpuidle/Kconfig
index 0e2cd5cab4d0..b3fb81d7cf04 100644
--- a/drivers/cpuidle/Kconfig
+++ b/drivers/cpuidle/Kconfig
@@ -1,5 +1,6 @@
+menu "CPU Idle"
 
-menuconfig CPU_IDLE
+config CPU_IDLE
 	bool "CPU idle PM support"
 	default y if ACPI || PPC_PSERIES
 	select CPU_IDLE_GOV_LADDER if (!NO_HZ && !NO_HZ_IDLE)
@@ -29,20 +30,13 @@ config CPU_IDLE_GOV_MENU
 	bool "Menu governor (for tickless system)"
 	default y
 
-config CPU_IDLE_CALXEDA
-	bool "CPU Idle Driver for Calxeda processors"
-	depends on ARCH_HIGHBANK
-	select ARM_CPU_SUSPEND
-	help
-	  Select this to enable cpuidle on Calxeda processors.
-
-config CPU_IDLE_ZYNQ
-	bool "CPU Idle Driver for Xilinx Zynq processors"
-	depends on ARCH_ZYNQ
-	help
-	  Select this to enable cpuidle on Xilinx Zynq processors.
+menu "ARM CPU Idle Drivers"
+depends on ARM
+source "drivers/cpuidle/Kconfig.arm"
+endmenu
 
 endif
 
 config ARCH_NEEDS_CPU_IDLE_COUPLED
 	def_bool n
+endmenu
diff --git a/drivers/cpuidle/Kconfig.arm b/drivers/cpuidle/Kconfig.arm
new file mode 100644
index 000000000000..8e3660322308
--- /dev/null
+++ b/drivers/cpuidle/Kconfig.arm
@@ -0,0 +1,39 @@
+#
+# ARM CPU Idle drivers
+#
+
+config ARM_HIGHBANK_CPUIDLE
+	bool "CPU Idle Driver for Calxeda processors"
+	depends on ARCH_HIGHBANK
+	select ARM_CPU_SUSPEND
+	help
+	  Select this to enable cpuidle on Calxeda processors.
+
+config ARM_KIRKWOOD_CPUIDLE
+	bool "CPU Idle Driver for Marvell Kirkwood SoCs"
+	depends on ARCH_KIRKWOOD
+	help
+	  This adds the CPU Idle driver for Marvell Kirkwood SoCs.
+
+config ARM_ZYNQ_CPUIDLE
+	bool "CPU Idle Driver for Xilinx Zynq processors"
+	depends on ARCH_ZYNQ
+	help
+	  Select this to enable cpuidle on Xilinx Zynq processors.
+
+config ARM_U8500_CPUIDLE
+	bool "Cpu Idle Driver for the ST-E u8500 processors"
+	depends on ARCH_U8500
+	help
+	  Select this to enable cpuidle for ST-E u8500 processors
+
+config CPU_IDLE_BIG_LITTLE
+	bool "Support for ARM big.LITTLE processors"
+	depends on ARCH_VEXPRESS_TC2_PM
+	select ARM_CPU_SUSPEND
+	select CPU_IDLE_MULTIPLE_DRIVERS
+	help
+	  Select this option to enable CPU idle driver for big.LITTLE based
+	  ARM systems. Driver manages CPUs coordination through MCPM and
+	  define different C-states for little and big cores through the
+	  multiple CPU idle drivers infrastructure.
diff --git a/drivers/cpuidle/Makefile b/drivers/cpuidle/Makefile
index 8767a7b3eb91..cea5ef58876d 100644
--- a/drivers/cpuidle/Makefile
+++ b/drivers/cpuidle/Makefile
@@ -5,6 +5,10 @@
 obj-y += cpuidle.o driver.o governor.o sysfs.o governors/
 obj-$(CONFIG_ARCH_NEEDS_CPU_IDLE_COUPLED) += coupled.o
 
-obj-$(CONFIG_CPU_IDLE_CALXEDA) += cpuidle-calxeda.o
-obj-$(CONFIG_ARCH_KIRKWOOD) += cpuidle-kirkwood.o
-obj-$(CONFIG_CPU_IDLE_ZYNQ) += cpuidle-zynq.o
+##################################################################################
+# ARM SoC drivers
+obj-$(CONFIG_ARM_HIGHBANK_CPUIDLE)	+= cpuidle-calxeda.o
+obj-$(CONFIG_ARM_KIRKWOOD_CPUIDLE)	+= cpuidle-kirkwood.o
+obj-$(CONFIG_ARM_ZYNQ_CPUIDLE)		+= cpuidle-zynq.o
+obj-$(CONFIG_ARM_U8500_CPUIDLE)         += cpuidle-ux500.o
+obj-$(CONFIG_CPU_IDLE_BIG_LITTLE)	+= cpuidle-big_little.o
diff --git a/drivers/cpuidle/coupled.c b/drivers/cpuidle/coupled.c
index 2a297f86dbad..f8a86364c6b6 100644
--- a/drivers/cpuidle/coupled.c
+++ b/drivers/cpuidle/coupled.c
@@ -106,6 +106,7 @@ struct cpuidle_coupled {
 	cpumask_t coupled_cpus;
 	int requested_state[NR_CPUS];
 	atomic_t ready_waiting_counts;
+	atomic_t abort_barrier;
 	int online_count;
 	int refcnt;
 	int prevent;
@@ -122,12 +123,19 @@ static DEFINE_MUTEX(cpuidle_coupled_lock);
 static DEFINE_PER_CPU(struct call_single_data, cpuidle_coupled_poke_cb);
 
 /*
- * The cpuidle_coupled_poked_mask mask is used to avoid calling
+ * The cpuidle_coupled_poke_pending mask is used to avoid calling
  * __smp_call_function_single with the per cpu call_single_data struct already
  * in use.  This prevents a deadlock where two cpus are waiting for each others
  * call_single_data struct to be available
  */
-static cpumask_t cpuidle_coupled_poked_mask;
+static cpumask_t cpuidle_coupled_poke_pending;
+
+/*
+ * The cpuidle_coupled_poked mask is used to ensure that each cpu has been poked
+ * once to minimize entering the ready loop with a poke pending, which would
+ * require aborting and retrying.
+ */
+static cpumask_t cpuidle_coupled_poked;
 
 /**
  * cpuidle_coupled_parallel_barrier - synchronize all online coupled cpus
@@ -291,10 +299,11 @@ static inline int cpuidle_coupled_get_state(struct cpuidle_device *dev,
 	return state;
 }
 
-static void cpuidle_coupled_poked(void *info)
+static void cpuidle_coupled_handle_poke(void *info)
 {
 	int cpu = (unsigned long)info;
-	cpumask_clear_cpu(cpu, &cpuidle_coupled_poked_mask);
+	cpumask_set_cpu(cpu, &cpuidle_coupled_poked);
+	cpumask_clear_cpu(cpu, &cpuidle_coupled_poke_pending);
 }
 
 /**
@@ -313,7 +322,7 @@ static void cpuidle_coupled_poke(int cpu)
 {
 	struct call_single_data *csd = &per_cpu(cpuidle_coupled_poke_cb, cpu);
 
-	if (!cpumask_test_and_set_cpu(cpu, &cpuidle_coupled_poked_mask))
+	if (!cpumask_test_and_set_cpu(cpu, &cpuidle_coupled_poke_pending))
 		__smp_call_function_single(cpu, csd, 0);
 }
 
@@ -340,30 +349,19 @@ static void cpuidle_coupled_poke_others(int this_cpu,
  * @coupled: the struct coupled that contains the current cpu
  * @next_state: the index in drv->states of the requested state for this cpu
  *
- * Updates the requested idle state for the specified cpuidle device,
- * poking all coupled cpus out of idle if necessary to let them see the new
- * state.
+ * Updates the requested idle state for the specified cpuidle device.
+ * Returns the number of waiting cpus.
  */
-static void cpuidle_coupled_set_waiting(int cpu,
+static int cpuidle_coupled_set_waiting(int cpu,
 		struct cpuidle_coupled *coupled, int next_state)
 {
-	int w;
-
 	coupled->requested_state[cpu] = next_state;
 
 	/*
-	 * If this is the last cpu to enter the waiting state, poke
-	 * all the other cpus out of their waiting state so they can
-	 * enter a deeper state.  This can race with one of the cpus
-	 * exiting the waiting state due to an interrupt and
-	 * decrementing waiting_count, see comment below.
-	 *
 	 * The atomic_inc_return provides a write barrier to order the write
 	 * to requested_state with the later write that increments ready_count.
 	 */
-	w = atomic_inc_return(&coupled->ready_waiting_counts) & WAITING_MASK;
-	if (w == coupled->online_count)
-		cpuidle_coupled_poke_others(cpu, coupled);
+	return atomic_inc_return(&coupled->ready_waiting_counts) & WAITING_MASK;
 }
 
 /**
@@ -410,19 +408,33 @@ static void cpuidle_coupled_set_done(int cpu, struct cpuidle_coupled *coupled)
  * been processed and the poke bit has been cleared.
  *
  * Other interrupts may also be processed while interrupts are enabled, so
- * need_resched() must be tested after turning interrupts off again to make sure
+ * need_resched() must be tested after this function returns to make sure
  * the interrupt didn't schedule work that should take the cpu out of idle.
  *
- * Returns 0 if need_resched was false, -EINTR if need_resched was true.
+ * Returns 0 if no poke was pending, 1 if a poke was cleared.
  */
 static int cpuidle_coupled_clear_pokes(int cpu)
 {
+	if (!cpumask_test_cpu(cpu, &cpuidle_coupled_poke_pending))
+		return 0;
+
 	local_irq_enable();
-	while (cpumask_test_cpu(cpu, &cpuidle_coupled_poked_mask))
+	while (cpumask_test_cpu(cpu, &cpuidle_coupled_poke_pending))
 		cpu_relax();
 	local_irq_disable();
 
-	return need_resched() ? -EINTR : 0;
+	return 1;
+}
+
+static bool cpuidle_coupled_any_pokes_pending(struct cpuidle_coupled *coupled)
+{
+	cpumask_t cpus;
+	int ret;
+
+	cpumask_and(&cpus, cpu_online_mask, &coupled->coupled_cpus);
+	ret = cpumask_and(&cpus, &cpuidle_coupled_poke_pending, &cpus);
+
+	return ret;
 }
 
 /**
@@ -449,31 +461,56 @@ int cpuidle_enter_state_coupled(struct cpuidle_device *dev,
 {
 	int entered_state = -1;
 	struct cpuidle_coupled *coupled = dev->coupled;
+	int w;
 
 	if (!coupled)
 		return -EINVAL;
 
 	while (coupled->prevent) {
-		if (cpuidle_coupled_clear_pokes(dev->cpu)) {
+		cpuidle_coupled_clear_pokes(dev->cpu);
+		if (need_resched()) {
 			local_irq_enable();
 			return entered_state;
 		}
 		entered_state = cpuidle_enter_state(dev, drv,
 			dev->safe_state_index);
+		local_irq_disable();
 	}
 
 	/* Read barrier ensures online_count is read after prevent is cleared */
 	smp_rmb();
 
-	cpuidle_coupled_set_waiting(dev->cpu, coupled, next_state);
+reset:
+	cpumask_clear_cpu(dev->cpu, &cpuidle_coupled_poked);
+
+	w = cpuidle_coupled_set_waiting(dev->cpu, coupled, next_state);
+	/*
+	 * If this is the last cpu to enter the waiting state, poke
+	 * all the other cpus out of their waiting state so they can
+	 * enter a deeper state.  This can race with one of the cpus
+	 * exiting the waiting state due to an interrupt and
+	 * decrementing waiting_count, see comment below.
+	 */
+	if (w == coupled->online_count) {
+		cpumask_set_cpu(dev->cpu, &cpuidle_coupled_poked);
+		cpuidle_coupled_poke_others(dev->cpu, coupled);
+	}
 
 retry:
 	/*
 	 * Wait for all coupled cpus to be idle, using the deepest state
-	 * allowed for a single cpu.
+	 * allowed for a single cpu.  If this was not the poking cpu, wait
+	 * for at least one poke before leaving to avoid a race where
+	 * two cpus could arrive at the waiting loop at the same time,
+	 * but the first of the two to arrive could skip the loop without
+	 * processing the pokes from the last to arrive.
 	 */
-	while (!cpuidle_coupled_cpus_waiting(coupled)) {
-		if (cpuidle_coupled_clear_pokes(dev->cpu)) {
+	while (!cpuidle_coupled_cpus_waiting(coupled) ||
+			!cpumask_test_cpu(dev->cpu, &cpuidle_coupled_poked)) {
+		if (cpuidle_coupled_clear_pokes(dev->cpu))
+			continue;
+
+		if (need_resched()) {
 			cpuidle_coupled_set_not_waiting(dev->cpu, coupled);
 			goto out;
 		}
@@ -485,14 +522,22 @@ retry:
 
 		entered_state = cpuidle_enter_state(dev, drv,
 			dev->safe_state_index);
+		local_irq_disable();
 	}
 
-	if (cpuidle_coupled_clear_pokes(dev->cpu)) {
+	cpuidle_coupled_clear_pokes(dev->cpu);
+	if (need_resched()) {
 		cpuidle_coupled_set_not_waiting(dev->cpu, coupled);
 		goto out;
 	}
 
 	/*
+	 * Make sure final poke status for this cpu is visible before setting
+	 * cpu as ready.
+	 */
+	smp_wmb();
+
+	/*
 	 * All coupled cpus are probably idle.  There is a small chance that
 	 * one of the other cpus just became active.  Increment the ready count,
 	 * and spin until all coupled cpus have incremented the counter. Once a
@@ -511,6 +556,28 @@ retry:
 		cpu_relax();
 	}
 
+	/*
+	 * Make sure read of all cpus ready is done before reading pending pokes
+	 */
+	smp_rmb();
+
+	/*
+	 * There is a small chance that a cpu left and reentered idle after this
+	 * cpu saw that all cpus were waiting.  The cpu that reentered idle will
+	 * have sent this cpu a poke, which will still be pending after the
+	 * ready loop.  The pending interrupt may be lost by the interrupt
+	 * controller when entering the deep idle state.  It's not possible to
+	 * clear a pending interrupt without turning interrupts on and handling
+	 * it, and it's too late to turn on interrupts here, so reset the
+	 * coupled idle state of all cpus and retry.
+	 */
+	if (cpuidle_coupled_any_pokes_pending(coupled)) {
+		cpuidle_coupled_set_done(dev->cpu, coupled);
+		/* Wait for all cpus to see the pending pokes */
+		cpuidle_coupled_parallel_barrier(dev, &coupled->abort_barrier);
+		goto reset;
+	}
+
 	/* all cpus have acked the coupled state */
 	next_state = cpuidle_coupled_get_state(dev, coupled);
 
@@ -596,7 +663,7 @@ have_coupled:
 	coupled->refcnt++;
 
 	csd = &per_cpu(cpuidle_coupled_poke_cb, dev->cpu);
-	csd->func = cpuidle_coupled_poked;
+	csd->func = cpuidle_coupled_handle_poke;
 	csd->info = (void *)(unsigned long)dev->cpu;
 
 	return 0;
diff --git a/drivers/cpuidle/cpuidle-big_little.c b/drivers/cpuidle/cpuidle-big_little.c
new file mode 100644
index 000000000000..b45fc6249041
--- /dev/null
+++ b/drivers/cpuidle/cpuidle-big_little.c
@@ -0,0 +1,209 @@
+/*
+ * Copyright (c) 2013 ARM/Linaro
+ *
+ * Authors: Daniel Lezcano <daniel.lezcano@linaro.org>
+ *          Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
+ *          Nicolas Pitre <nicolas.pitre@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Maintainer: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
+ * Maintainer: Daniel Lezcano <daniel.lezcano@linaro.org>
+ */
+#include <linux/cpuidle.h>
+#include <linux/cpu_pm.h>
+#include <linux/slab.h>
+#include <linux/of.h>
+
+#include <asm/cpu.h>
+#include <asm/cputype.h>
+#include <asm/cpuidle.h>
+#include <asm/mcpm.h>
+#include <asm/smp_plat.h>
+#include <asm/suspend.h>
+
+static int bl_enter_powerdown(struct cpuidle_device *dev,
+			      struct cpuidle_driver *drv, int idx);
+
+/*
+ * NB: Owing to current menu governor behaviour big and LITTLE
+ * index 1 states have to define exit_latency and target_residency for
+ * cluster state since, when all CPUs in a cluster hit it, the cluster
+ * can be shutdown. This means that when a single CPU enters this state
+ * the exit_latency and target_residency values are somewhat overkill.
+ * There is no notion of cluster states in the menu governor, so CPUs
+ * have to define CPU states where possibly the cluster will be shutdown
+ * depending on the state of other CPUs. idle states entry and exit happen
+ * at random times; however the cluster state provides target_residency
+ * values as if all CPUs in a cluster enter the state at once; this is
+ * somewhat optimistic and behaviour should be fixed either in the governor
+ * or in the MCPM back-ends.
+ * To make this driver 100% generic the number of states and the exit_latency
+ * target_residency values must be obtained from device tree bindings.
+ *
+ * exit_latency: refers to the TC2 vexpress test chip and depends on the
+ * current cluster operating point. It is the time it takes to get the CPU
+ * up and running when the CPU is powered up on cluster wake-up from shutdown.
+ * Current values for big and LITTLE clusters are provided for clusters
+ * running at default operating points.
+ *
+ * target_residency: it is the minimum amount of time the cluster has
+ * to be down to break even in terms of power consumption. cluster
+ * shutdown has inherent dynamic power costs (L2 writebacks to DRAM
+ * being the main factor) that depend on the current operating points.
+ * The current values for both clusters are provided for a CPU whose half
+ * of L2 lines are dirty and require cleaning to DRAM, and takes into
+ * account leakage static power values related to the vexpress TC2 testchip.
+ */
+static struct cpuidle_driver bl_idle_little_driver = {
+	.name = "little_idle",
+	.owner = THIS_MODULE,
+	.states[0] = ARM_CPUIDLE_WFI_STATE,
+	.states[1] = {
+		.enter			= bl_enter_powerdown,
+		.exit_latency		= 700,
+		.target_residency	= 2500,
+		.flags			= CPUIDLE_FLAG_TIME_VALID |
+					  CPUIDLE_FLAG_TIMER_STOP,
+		.name			= "C1",
+		.desc			= "ARM little-cluster power down",
+	},
+	.state_count = 2,
+};
+
+static struct cpuidle_driver bl_idle_big_driver = {
+	.name = "big_idle",
+	.owner = THIS_MODULE,
+	.states[0] = ARM_CPUIDLE_WFI_STATE,
+	.states[1] = {
+		.enter			= bl_enter_powerdown,
+		.exit_latency		= 500,
+		.target_residency	= 2000,
+		.flags			= CPUIDLE_FLAG_TIME_VALID |
+					  CPUIDLE_FLAG_TIMER_STOP,
+		.name			= "C1",
+		.desc			= "ARM big-cluster power down",
+	},
+	.state_count = 2,
+};
+
+/*
+ * notrace prevents trace shims from getting inserted where they
+ * should not. Global jumps and ldrex/strex must not be inserted
+ * in power down sequences where caches and MMU may be turned off.
+ */
+static int notrace bl_powerdown_finisher(unsigned long arg)
+{
+	/* MCPM works with HW CPU identifiers */
+	unsigned int mpidr = read_cpuid_mpidr();
+	unsigned int cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);
+	unsigned int cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
+
+	mcpm_set_entry_vector(cpu, cluster, cpu_resume);
+
+	/*
+	 * Residency value passed to mcpm_cpu_suspend back-end
+	 * has to be given clear semantics. Set to 0 as a
+	 * temporary value.
+	 */
+	mcpm_cpu_suspend(0);
+
+	/* return value != 0 means failure */
+	return 1;
+}
+
+/**
+ * bl_enter_powerdown - Programs CPU to enter the specified state
+ * @dev: cpuidle device
+ * @drv: The target state to be programmed
+ * @idx: state index
+ *
+ * Called from the CPUidle framework to program the device to the
+ * specified target state selected by the governor.
+ */
+static int bl_enter_powerdown(struct cpuidle_device *dev,
+				struct cpuidle_driver *drv, int idx)
+{
+	cpu_pm_enter();
+
+	cpu_suspend(0, bl_powerdown_finisher);
+
+	/* signals the MCPM core that CPU is out of low power state */
+	mcpm_cpu_powered_up();
+
+	cpu_pm_exit();
+
+	return idx;
+}
+
+static int __init bl_idle_driver_init(struct cpuidle_driver *drv, int cpu_id)
+{
+	struct cpuinfo_arm *cpu_info;
+	struct cpumask *cpumask;
+	unsigned long cpuid;
+	int cpu;
+
+	cpumask = kzalloc(cpumask_size(), GFP_KERNEL);
+	if (!cpumask)
+		return -ENOMEM;
+
+	for_each_possible_cpu(cpu) {
+		cpu_info = &per_cpu(cpu_data, cpu);
+		cpuid = is_smp() ? cpu_info->cpuid : read_cpuid_id();
+
+		/* read cpu id part number */
+		if ((cpuid & 0xFFF0) == cpu_id)
+			cpumask_set_cpu(cpu, cpumask);
+	}
+
+	drv->cpumask = cpumask;
+
+	return 0;
+}
+
+static int __init bl_idle_init(void)
+{
+	int ret;
+
+	/*
+	 * Initialize the driver just for a compliant set of machines
+	 */
+	if (!of_machine_is_compatible("arm,vexpress,v2p-ca15_a7"))
+		return -ENODEV;
+	/*
+	 * For now the differentiation between little and big cores
+	 * is based on the part number. A7 cores are considered little
+	 * cores, A15 are considered big cores. This distinction may
+	 * evolve in the future with a more generic matching approach.
+	 */
+	ret = bl_idle_driver_init(&bl_idle_little_driver,
+				  ARM_CPU_PART_CORTEX_A7);
+	if (ret)
+		return ret;
+
+	ret = bl_idle_driver_init(&bl_idle_big_driver, ARM_CPU_PART_CORTEX_A15);
+	if (ret)
+		goto out_uninit_little;
+
+	ret = cpuidle_register(&bl_idle_little_driver, NULL);
+	if (ret)
+		goto out_uninit_big;
+
+	ret = cpuidle_register(&bl_idle_big_driver, NULL);
+	if (ret)
+		goto out_unregister_little;
+
+	return 0;
+
+out_unregister_little:
+	cpuidle_unregister(&bl_idle_little_driver);
+out_uninit_big:
+	kfree(bl_idle_big_driver.cpumask);
+out_uninit_little:
+	kfree(bl_idle_little_driver.cpumask);
+
+	return ret;
+}
+device_initcall(bl_idle_init);
diff --git a/drivers/cpuidle/cpuidle-calxeda.c b/drivers/cpuidle/cpuidle-calxeda.c
index 0e6e408c0a63..346058479572 100644
--- a/drivers/cpuidle/cpuidle-calxeda.c
+++ b/drivers/cpuidle/cpuidle-calxeda.c
@@ -35,7 +35,7 @@
 #include <asm/cp15.h>
 
 extern void highbank_set_cpu_jump(int cpu, void *jump_addr);
-extern void *scu_base_addr;
+extern void __iomem *scu_base_addr;
 
 static noinline void calxeda_idle_restore(void)
 {
diff --git a/drivers/cpuidle/cpuidle-kirkwood.c b/drivers/cpuidle/cpuidle-kirkwood.c
index 521b0a7fdd89..41ba843251b8 100644
--- a/drivers/cpuidle/cpuidle-kirkwood.c
+++ b/drivers/cpuidle/cpuidle-kirkwood.c
@@ -60,9 +60,6 @@ static int kirkwood_cpuidle_probe(struct platform_device *pdev)
 	struct resource *res;
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (res == NULL)
-		return -EINVAL;
-
 	ddr_operation_base = devm_ioremap_resource(&pdev->dev, res);
 	if (IS_ERR(ddr_operation_base))
 		return PTR_ERR(ddr_operation_base);
@@ -70,7 +67,7 @@ static int kirkwood_cpuidle_probe(struct platform_device *pdev)
 	return cpuidle_register(&kirkwood_idle_driver, NULL);
 }
 
-int kirkwood_cpuidle_remove(struct platform_device *pdev)
+static int kirkwood_cpuidle_remove(struct platform_device *pdev)
 {
 	cpuidle_unregister(&kirkwood_idle_driver);
 	return 0;
diff --git a/arch/arm/mach-ux500/cpuidle.c b/drivers/cpuidle/cpuidle-ux500.c
index a45dd09daed9..e0564652af35 100644
--- a/arch/arm/mach-ux500/cpuidle.c
+++ b/drivers/cpuidle/cpuidle-ux500.c
@@ -16,13 +16,11 @@
 #include <linux/smp.h>
 #include <linux/mfd/dbx500-prcmu.h>
 #include <linux/platform_data/arm-ux500-pm.h>
+#include <linux/platform_device.h>
 
 #include <asm/cpuidle.h>
 #include <asm/proc-fns.h>
 
-#include "db8500-regs.h"
-#include "id.h"
-
 static atomic_t master = ATOMIC_INIT(0);
 static DEFINE_SPINLOCK(master_lock);
 
@@ -113,11 +111,8 @@ static struct cpuidle_driver ux500_idle_driver = {
 	.state_count = 2,
 };
 
-int __init ux500_idle_init(void)
+static int __init dbx500_cpuidle_probe(struct platform_device *pdev)
 {
-	if (!(cpu_is_u8500_family() || cpu_is_ux540_family()))
-		return -ENODEV;
-
 	/* Configure wake up reasons */
 	prcmu_enable_wakeups(PRCMU_WAKEUP(ARM) | PRCMU_WAKEUP(RTC) |
 			     PRCMU_WAKEUP(ABB));
@@ -125,4 +120,12 @@ int __init ux500_idle_init(void)
 	return cpuidle_register(&ux500_idle_driver, NULL);
 }
 
-device_initcall(ux500_idle_init);
+static struct platform_driver dbx500_cpuidle_plat_driver = {
+	.driver = {
+		.name = "cpuidle-dbx500",
+		.owner = THIS_MODULE,
+	},
+	.probe = dbx500_cpuidle_probe,
+};
+
+module_platform_driver(dbx500_cpuidle_plat_driver);
diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c
index fdc432f18022..d75040ddd2b3 100644
--- a/drivers/cpuidle/cpuidle.c
+++ b/drivers/cpuidle/cpuidle.c
@@ -42,8 +42,6 @@ void disable_cpuidle(void)
 	off = 1;
 }
 
-static int __cpuidle_register_device(struct cpuidle_device *dev);
-
 /**
  * cpuidle_play_dead - cpu off-lining
  *
@@ -278,7 +276,7 @@ static void poll_idle_init(struct cpuidle_driver *drv) {}
  */
 int cpuidle_enable_device(struct cpuidle_device *dev)
 {
-	int ret, i;
+	int ret;
 	struct cpuidle_driver *drv;
 
 	if (!dev)
@@ -292,15 +290,12 @@ int cpuidle_enable_device(struct cpuidle_device *dev)
 	if (!drv || !cpuidle_curr_governor)
 		return -EIO;
 
+	if (!dev->registered)
+		return -EINVAL;
+
 	if (!dev->state_count)
 		dev->state_count = drv->state_count;
 
-	if (dev->registered == 0) {
-		ret = __cpuidle_register_device(dev);
-		if (ret)
-			return ret;
-	}
-
 	poll_idle_init(drv);
 
 	ret = cpuidle_add_device_sysfs(dev);
@@ -311,12 +306,6 @@ int cpuidle_enable_device(struct cpuidle_device *dev)
 	    (ret = cpuidle_curr_governor->enable(drv, dev)))
 		goto fail_sysfs;
 
-	for (i = 0; i < dev->state_count; i++) {
-		dev->states_usage[i].usage = 0;
-		dev->states_usage[i].time = 0;
-	}
-	dev->last_residency = 0;
-
 	smp_wmb();
 
 	dev->enabled = 1;
@@ -360,6 +349,23 @@ void cpuidle_disable_device(struct cpuidle_device *dev)
 
 EXPORT_SYMBOL_GPL(cpuidle_disable_device);
 
+static void __cpuidle_unregister_device(struct cpuidle_device *dev)
+{
+	struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev);
+
+	list_del(&dev->device_list);
+	per_cpu(cpuidle_devices, dev->cpu) = NULL;
+	module_put(drv->owner);
+}
+
+static int __cpuidle_device_init(struct cpuidle_device *dev)
+{
+	memset(dev->states_usage, 0, sizeof(dev->states_usage));
+	dev->last_residency = 0;
+
+	return 0;
+}
+
 /**
  * __cpuidle_register_device - internal register function called before register
  * and enable routines
@@ -377,24 +383,15 @@ static int __cpuidle_register_device(struct cpuidle_device *dev)
 
 	per_cpu(cpuidle_devices, dev->cpu) = dev;
 	list_add(&dev->device_list, &cpuidle_detected_devices);
-	ret = cpuidle_add_sysfs(dev);
-	if (ret)
-		goto err_sysfs;
 
 	ret = cpuidle_coupled_register_device(dev);
-	if (ret)
-		goto err_coupled;
+	if (ret) {
+		__cpuidle_unregister_device(dev);
+		return ret;
+	}
 
 	dev->registered = 1;
 	return 0;
-
-err_coupled:
-	cpuidle_remove_sysfs(dev);
-err_sysfs:
-	list_del(&dev->device_list);
-	per_cpu(cpuidle_devices, dev->cpu) = NULL;
-	module_put(drv->owner);
-	return ret;
 }
 
 /**
@@ -403,25 +400,44 @@ err_sysfs:
  */
 int cpuidle_register_device(struct cpuidle_device *dev)
 {
-	int ret;
+	int ret = -EBUSY;
 
 	if (!dev)
 		return -EINVAL;
 
 	mutex_lock(&cpuidle_lock);
 
-	if ((ret = __cpuidle_register_device(dev))) {
-		mutex_unlock(&cpuidle_lock);
-		return ret;
-	}
+	if (dev->registered)
+		goto out_unlock;
+
+	ret = __cpuidle_device_init(dev);
+	if (ret)
+		goto out_unlock;
+
+	ret = __cpuidle_register_device(dev);
+	if (ret)
+		goto out_unlock;
+
+	ret = cpuidle_add_sysfs(dev);
+	if (ret)
+		goto out_unregister;
+
+	ret = cpuidle_enable_device(dev);
+	if (ret)
+		goto out_sysfs;
 
-	cpuidle_enable_device(dev);
 	cpuidle_install_idle_handler();
 
+out_unlock:
 	mutex_unlock(&cpuidle_lock);
 
-	return 0;
+	return ret;
 
+out_sysfs:
+	cpuidle_remove_sysfs(dev);
+out_unregister:
+	__cpuidle_unregister_device(dev);
+	goto out_unlock;
 }
 
 EXPORT_SYMBOL_GPL(cpuidle_register_device);
@@ -432,8 +448,6 @@ EXPORT_SYMBOL_GPL(cpuidle_register_device);
  */
 void cpuidle_unregister_device(struct cpuidle_device *dev)
 {
-	struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev);
-
 	if (dev->registered == 0)
 		return;
 
@@ -442,14 +456,12 @@ void cpuidle_unregister_device(struct cpuidle_device *dev)
 	cpuidle_disable_device(dev);
 
 	cpuidle_remove_sysfs(dev);
-	list_del(&dev->device_list);
-	per_cpu(cpuidle_devices, dev->cpu) = NULL;
+
+	__cpuidle_unregister_device(dev);
 
 	cpuidle_coupled_unregister_device(dev);
 
 	cpuidle_resume_and_unlock();
-
-	module_put(drv->owner);
 }
 
 EXPORT_SYMBOL_GPL(cpuidle_unregister_device);
diff --git a/drivers/cpuidle/driver.c b/drivers/cpuidle/driver.c
index 3ac499d5a207..6e11701f0fca 100644
--- a/drivers/cpuidle/driver.c
+++ b/drivers/cpuidle/driver.c
@@ -331,7 +331,8 @@ struct cpuidle_driver *cpuidle_driver_ref(void)
 	spin_lock(&cpuidle_driver_lock);
 
 	drv = cpuidle_get_driver();
-	drv->refcnt++;
+	if (drv)
+		drv->refcnt++;
 
 	spin_unlock(&cpuidle_driver_lock);
 	return drv;
diff --git a/drivers/cpuidle/governors/ladder.c b/drivers/cpuidle/governors/ladder.c
index 9b784051ec12..9f08e8cce1af 100644
--- a/drivers/cpuidle/governors/ladder.c
+++ b/drivers/cpuidle/governors/ladder.c
@@ -192,14 +192,4 @@ static int __init init_ladder(void)
 	return cpuidle_register_governor(&ladder_governor);
 }
 
-/**
- * exit_ladder - exits the governor
- */
-static void __exit exit_ladder(void)
-{
-	cpuidle_unregister_governor(&ladder_governor);
-}
-
-MODULE_LICENSE("GPL");
-module_init(init_ladder);
-module_exit(exit_ladder);
+postcore_initcall(init_ladder);
diff --git a/drivers/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c
index bc580b67a652..cf7f2f0e4ef5 100644
--- a/drivers/cpuidle/governors/menu.c
+++ b/drivers/cpuidle/governors/menu.c
@@ -21,6 +21,15 @@
 #include <linux/math64.h>
 #include <linux/module.h>
 
+/*
+ * Please note when changing the tuning values:
+ * If (MAX_INTERESTING-1) * RESOLUTION > UINT_MAX, the result of
+ * a scaling operation multiplication may overflow on 32 bit platforms.
+ * In that case, #define RESOLUTION as ULL to get 64 bit result:
+ * #define RESOLUTION 1024ULL
+ *
+ * The default values do not overflow.
+ */
 #define BUCKETS 12
 #define INTERVALS 8
 #define RESOLUTION 1024
@@ -114,11 +123,11 @@ struct menu_device {
 	int             needs_update;
 
 	unsigned int	expected_us;
-	u64		predicted_us;
+	unsigned int	predicted_us;
 	unsigned int	exit_us;
 	unsigned int	bucket;
-	u64		correction_factor[BUCKETS];
-	u32		intervals[INTERVALS];
+	unsigned int	correction_factor[BUCKETS];
+	unsigned int	intervals[INTERVALS];
 	int		interval_ptr;
 };
 
@@ -199,16 +208,20 @@ static u64 div_round64(u64 dividend, u32 divisor)
  */
 static void get_typical_interval(struct menu_device *data)
 {
-	int i = 0, divisor = 0;
-	uint64_t max = 0, avg = 0, stddev = 0;
-	int64_t thresh = LLONG_MAX; /* Discard outliers above this value. */
+	int i, divisor;
+	unsigned int max, thresh;
+	uint64_t avg, stddev;
+
+	thresh = UINT_MAX; /* Discard outliers above this value */
 
 again:
 
-	/* first calculate average and standard deviation of the past */
-	max = avg = divisor = stddev = 0;
+	/* First calculate the average of past intervals */
+	max = 0;
+	avg = 0;
+	divisor = 0;
 	for (i = 0; i < INTERVALS; i++) {
-		int64_t value = data->intervals[i];
+		unsigned int value = data->intervals[i];
 		if (value <= thresh) {
 			avg += value;
 			divisor++;
@@ -218,15 +231,38 @@ again:
 	}
 	do_div(avg, divisor);
 
+	/* Then try to determine standard deviation */
+	stddev = 0;
 	for (i = 0; i < INTERVALS; i++) {
-		int64_t value = data->intervals[i];
+		unsigned int value = data->intervals[i];
 		if (value <= thresh) {
 			int64_t diff = value - avg;
 			stddev += diff * diff;
 		}
 	}
 	do_div(stddev, divisor);
-	stddev = int_sqrt(stddev);
+	/*
+	 * The typical interval is obtained when standard deviation is small
+	 * or standard deviation is small compared to the average interval.
+	 *
+	 * int_sqrt() formal parameter type is unsigned long. When the
+	 * greatest difference to an outlier exceeds ~65 ms * sqrt(divisor)
+	 * the resulting squared standard deviation exceeds the input domain
+	 * of int_sqrt on platforms where unsigned long is 32 bits in size.
+	 * In such case reject the candidate average.
+	 *
+	 * Use this result only if there is no timer to wake us up sooner.
+	 */
+	if (likely(stddev <= ULONG_MAX)) {
+		stddev = int_sqrt(stddev);
+		if (((avg > stddev * 6) && (divisor * 4 >= INTERVALS * 3))
+							|| stddev <= 20) {
+			if (data->expected_us > avg)
+				data->predicted_us = avg;
+			return;
+		}
+	}
+
 	/*
 	 * If we have outliers to the upside in our distribution, discard
 	 * those by setting the threshold to exclude these outliers, then
@@ -235,20 +271,12 @@ again:
 	 *
 	 * This can deal with workloads that have long pauses interspersed
 	 * with sporadic activity with a bunch of short pauses.
-	 *
-	 * The typical interval is obtained when standard deviation is small
-	 * or standard deviation is small compared to the average interval.
 	 */
-	if (((avg > stddev * 6) && (divisor * 4 >= INTERVALS * 3))
-							|| stddev <= 20) {
-		data->predicted_us = avg;
+	if ((divisor * 4) <= INTERVALS * 3)
 		return;
 
-	} else if ((divisor * 4) > INTERVALS * 3) {
-		/* Exclude the max interval */
-		thresh = max - 1;
-		goto again;
-	}
+	thresh = max - 1;
+	goto again;
 }
 
 /**
@@ -293,8 +321,13 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 	if (data->correction_factor[data->bucket] == 0)
 		data->correction_factor[data->bucket] = RESOLUTION * DECAY;
 
-	/* Make sure to round up for half microseconds */
-	data->predicted_us = div_round64(data->expected_us * data->correction_factor[data->bucket],
+	/*
+	 * Force the result of multiplication to be 64 bits even if both
+	 * operands are 32 bits.
+	 * Make sure to round up for half microseconds.
+	 */
+	data->predicted_us = div_round64((uint64_t)data->expected_us *
+					 data->correction_factor[data->bucket],
 					 RESOLUTION * DECAY);
 
 	get_typical_interval(data);
@@ -360,7 +393,7 @@ static void menu_update(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 	unsigned int last_idle_us = cpuidle_get_last_residency(dev);
 	struct cpuidle_state *target = &drv->states[last_idx];
 	unsigned int measured_us;
-	u64 new_factor;
+	unsigned int new_factor;
 
 	/*
 	 * Ugh, this idle state doesn't support residency measurements, so we
@@ -381,10 +414,9 @@ static void menu_update(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 		measured_us -= data->exit_us;
 
 
-	/* update our correction ratio */
-
-	new_factor = data->correction_factor[data->bucket]
-			* (DECAY - 1) / DECAY;
+	/* Update our correction ratio */
+	new_factor = data->correction_factor[data->bucket];
+	new_factor -= new_factor / DECAY;
 
 	if (data->expected_us > 0 && measured_us < MAX_INTERESTING)
 		new_factor += RESOLUTION * measured_us / data->expected_us;
@@ -397,9 +429,11 @@ static void menu_update(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 
 	/*
 	 * We don't want 0 as factor; we always want at least
-	 * a tiny bit of estimated time.
+	 * a tiny bit of estimated time. Fortunately, due to rounding,
+	 * new_factor will stay nonzero regardless of measured_us values
+	 * and the compiler can eliminate this test as long as DECAY > 1.
 	 */
-	if (new_factor == 0)
+	if (DECAY == 1 && unlikely(new_factor == 0))
 		new_factor = 1;
 
 	data->correction_factor[data->bucket] = new_factor;
@@ -442,14 +476,4 @@ static int __init init_menu(void)
 	return cpuidle_register_governor(&menu_governor);
 }
 
-/**
- * exit_menu - exits the governor
- */
-static void __exit exit_menu(void)
-{
-	cpuidle_unregister_governor(&menu_governor);
-}
-
-MODULE_LICENSE("GPL");
-module_init(init_menu);
-module_exit(exit_menu);
+postcore_initcall(init_menu);
diff --git a/drivers/cpuidle/sysfs.c b/drivers/cpuidle/sysfs.c
index 428754af6236..8739cc05228c 100644
--- a/drivers/cpuidle/sysfs.c
+++ b/drivers/cpuidle/sysfs.c
@@ -11,8 +11,10 @@
 #include <linux/sysfs.h>
 #include <linux/slab.h>
 #include <linux/cpu.h>
+#include <linux/completion.h>
 #include <linux/capability.h>
 #include <linux/device.h>
+#include <linux/kobject.h>
 
 #include "cpuidle.h"
 
@@ -33,7 +35,8 @@ static ssize_t show_available_governors(struct device *dev,
 
 	mutex_lock(&cpuidle_lock);
 	list_for_each_entry(tmp, &cpuidle_governors, governor_list) {
-		if (i >= (ssize_t) ((PAGE_SIZE/sizeof(char)) - CPUIDLE_NAME_LEN - 2))
+		if (i >= (ssize_t) ((PAGE_SIZE/sizeof(char)) -
+				    CPUIDLE_NAME_LEN - 2))
 			goto out;
 		i += scnprintf(&buf[i], CPUIDLE_NAME_LEN, "%s ", tmp->name);
 	}
@@ -166,13 +169,28 @@ struct cpuidle_attr {
 #define define_one_rw(_name, show, store) \
 	static struct cpuidle_attr attr_##_name = __ATTR(_name, 0644, show, store)
 
-#define kobj_to_cpuidledev(k) container_of(k, struct cpuidle_device, kobj)
 #define attr_to_cpuidleattr(a) container_of(a, struct cpuidle_attr, attr)
-static ssize_t cpuidle_show(struct kobject * kobj, struct attribute * attr ,char * buf)
+
+struct cpuidle_device_kobj {
+	struct cpuidle_device *dev;
+	struct completion kobj_unregister;
+	struct kobject kobj;
+};
+
+static inline struct cpuidle_device *to_cpuidle_device(struct kobject *kobj)
+{
+	struct cpuidle_device_kobj *kdev =
+		container_of(kobj, struct cpuidle_device_kobj, kobj);
+
+	return kdev->dev;
+}
+
+static ssize_t cpuidle_show(struct kobject *kobj, struct attribute *attr,
+			    char *buf)
 {
 	int ret = -EIO;
-	struct cpuidle_device *dev = kobj_to_cpuidledev(kobj);
-	struct cpuidle_attr * cattr = attr_to_cpuidleattr(attr);
+	struct cpuidle_device *dev = to_cpuidle_device(kobj);
+	struct cpuidle_attr *cattr = attr_to_cpuidleattr(attr);
 
 	if (cattr->show) {
 		mutex_lock(&cpuidle_lock);
@@ -182,12 +200,12 @@ static ssize_t cpuidle_show(struct kobject * kobj, struct attribute * attr ,char
 	return ret;
 }
 
-static ssize_t cpuidle_store(struct kobject * kobj, struct attribute * attr,
-		     const char * buf, size_t count)
+static ssize_t cpuidle_store(struct kobject *kobj, struct attribute *attr,
+			     const char *buf, size_t count)
 {
 	int ret = -EIO;
-	struct cpuidle_device *dev = kobj_to_cpuidledev(kobj);
-	struct cpuidle_attr * cattr = attr_to_cpuidleattr(attr);
+	struct cpuidle_device *dev = to_cpuidle_device(kobj);
+	struct cpuidle_attr *cattr = attr_to_cpuidleattr(attr);
 
 	if (cattr->store) {
 		mutex_lock(&cpuidle_lock);
@@ -204,9 +222,10 @@ static const struct sysfs_ops cpuidle_sysfs_ops = {
 
 static void cpuidle_sysfs_release(struct kobject *kobj)
 {
-	struct cpuidle_device *dev = kobj_to_cpuidledev(kobj);
+	struct cpuidle_device_kobj *kdev =
+		container_of(kobj, struct cpuidle_device_kobj, kobj);
 
-	complete(&dev->kobj_unregister);
+	complete(&kdev->kobj_unregister);
 }
 
 static struct kobj_type ktype_cpuidle = {
@@ -237,8 +256,8 @@ static ssize_t show_state_##_name(struct cpuidle_state *state, \
 
 #define define_store_state_ull_function(_name) \
 static ssize_t store_state_##_name(struct cpuidle_state *state, \
-		struct cpuidle_state_usage *state_usage, \
-		const char *buf, size_t size) \
+				   struct cpuidle_state_usage *state_usage, \
+				   const char *buf, size_t size)	\
 { \
 	unsigned long long value; \
 	int err; \
@@ -256,14 +275,16 @@ static ssize_t store_state_##_name(struct cpuidle_state *state, \
 
 #define define_show_state_ull_function(_name) \
 static ssize_t show_state_##_name(struct cpuidle_state *state, \
-			struct cpuidle_state_usage *state_usage, char *buf) \
+				  struct cpuidle_state_usage *state_usage, \
+				  char *buf)				\
 { \
 	return sprintf(buf, "%llu\n", state_usage->_name);\
 }
 
 #define define_show_state_str_function(_name) \
 static ssize_t show_state_##_name(struct cpuidle_state *state, \
-			struct cpuidle_state_usage *state_usage, char *buf) \
+				  struct cpuidle_state_usage *state_usage, \
+				  char *buf)				\
 { \
 	if (state->_name[0] == '\0')\
 		return sprintf(buf, "<null>\n");\
@@ -309,8 +330,9 @@ struct cpuidle_state_kobj {
 #define kobj_to_state(k) (kobj_to_state_obj(k)->state)
 #define kobj_to_state_usage(k) (kobj_to_state_obj(k)->state_usage)
 #define attr_to_stateattr(a) container_of(a, struct cpuidle_state_attr, attr)
-static ssize_t cpuidle_state_show(struct kobject * kobj,
-	struct attribute * attr ,char * buf)
+
+static ssize_t cpuidle_state_show(struct kobject *kobj, struct attribute *attr,
+				  char * buf)
 {
 	int ret = -EIO;
 	struct cpuidle_state *state = kobj_to_state(kobj);
@@ -323,8 +345,8 @@ static ssize_t cpuidle_state_show(struct kobject * kobj,
 	return ret;
 }
 
-static ssize_t cpuidle_state_store(struct kobject *kobj,
-	struct attribute *attr, const char *buf, size_t size)
+static ssize_t cpuidle_state_store(struct kobject *kobj, struct attribute *attr,
+				   const char *buf, size_t size)
 {
 	int ret = -EIO;
 	struct cpuidle_state *state = kobj_to_state(kobj);
@@ -371,6 +393,7 @@ static int cpuidle_add_state_sysfs(struct cpuidle_device *device)
 {
 	int i, ret = -ENOMEM;
 	struct cpuidle_state_kobj *kobj;
+	struct cpuidle_device_kobj *kdev = device->kobj_dev;
 	struct cpuidle_driver *drv = cpuidle_get_cpu_driver(device);
 
 	/* state statistics */
@@ -383,7 +406,7 @@ static int cpuidle_add_state_sysfs(struct cpuidle_device *device)
 		init_completion(&kobj->kobj_unregister);
 
 		ret = kobject_init_and_add(&kobj->kobj, &ktype_state_cpuidle,
-					   &device->kobj, "state%d", i);
+					   &kdev->kobj, "state%d", i);
 		if (ret) {
 			kfree(kobj);
 			goto error_state;
@@ -449,8 +472,8 @@ static void cpuidle_driver_sysfs_release(struct kobject *kobj)
 	complete(&driver_kobj->kobj_unregister);
 }
 
-static ssize_t cpuidle_driver_show(struct kobject *kobj, struct attribute * attr,
-				   char * buf)
+static ssize_t cpuidle_driver_show(struct kobject *kobj, struct attribute *attr,
+				   char *buf)
 {
 	int ret = -EIO;
 	struct cpuidle_driver_kobj *driver_kobj = kobj_to_driver_kobj(kobj);
@@ -500,6 +523,7 @@ static struct kobj_type ktype_driver_cpuidle = {
 static int cpuidle_add_driver_sysfs(struct cpuidle_device *dev)
 {
 	struct cpuidle_driver_kobj *kdrv;
+	struct cpuidle_device_kobj *kdev = dev->kobj_dev;
 	struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev);
 	int ret;
 
@@ -511,7 +535,7 @@ static int cpuidle_add_driver_sysfs(struct cpuidle_device *dev)
 	init_completion(&kdrv->kobj_unregister);
 
 	ret = kobject_init_and_add(&kdrv->kobj, &ktype_driver_cpuidle,
-				   &dev->kobj, "driver");
+				   &kdev->kobj, "driver");
 	if (ret) {
 		kfree(kdrv);
 		return ret;
@@ -580,16 +604,28 @@ void cpuidle_remove_device_sysfs(struct cpuidle_device *device)
  */
 int cpuidle_add_sysfs(struct cpuidle_device *dev)
 {
+	struct cpuidle_device_kobj *kdev;
 	struct device *cpu_dev = get_cpu_device((unsigned long)dev->cpu);
 	int error;
 
-	init_completion(&dev->kobj_unregister);
+	kdev = kzalloc(sizeof(*kdev), GFP_KERNEL);
+	if (!kdev)
+		return -ENOMEM;
+	kdev->dev = dev;
+	dev->kobj_dev = kdev;
 
-	error = kobject_init_and_add(&dev->kobj, &ktype_cpuidle, &cpu_dev->kobj,
-				     "cpuidle");
-	if (!error)
-		kobject_uevent(&dev->kobj, KOBJ_ADD);
-	return error;
+	init_completion(&kdev->kobj_unregister);
+
+	error = kobject_init_and_add(&kdev->kobj, &ktype_cpuidle, &cpu_dev->kobj,
+				   "cpuidle");
+	if (error) {
+		kfree(kdev);
+		return error;
+	}
+
+	kobject_uevent(&kdev->kobj, KOBJ_ADD);
+
+	return 0;
 }
 
 /**
@@ -598,6 +634,9 @@ int cpuidle_add_sysfs(struct cpuidle_device *dev)
  */
 void cpuidle_remove_sysfs(struct cpuidle_device *dev)
 {
-	kobject_put(&dev->kobj);
-	wait_for_completion(&dev->kobj_unregister);
+	struct cpuidle_device_kobj *kdev = dev->kobj_dev;
+
+	kobject_put(&kdev->kobj);
+	wait_for_completion(&kdev->kobj_unregister);
+	kfree(kdev);
 }
diff --git a/drivers/crypto/Kconfig b/drivers/crypto/Kconfig
index 8ff7c230d82e..f4fd837bcb82 100644
--- a/drivers/crypto/Kconfig
+++ b/drivers/crypto/Kconfig
@@ -242,17 +242,20 @@ config CRYPTO_DEV_PPC4XX
 	  This option allows you to have support for AMCC crypto acceleration.
 
 config CRYPTO_DEV_OMAP_SHAM
-	tristate "Support for OMAP SHA1/MD5 hw accelerator"
-	depends on ARCH_OMAP2 || ARCH_OMAP3
+	tristate "Support for OMAP MD5/SHA1/SHA2 hw accelerator"
+	depends on ARCH_OMAP2PLUS
 	select CRYPTO_SHA1
 	select CRYPTO_MD5
+	select CRYPTO_SHA256
+	select CRYPTO_SHA512
+	select CRYPTO_HMAC
 	help
-	  OMAP processors have SHA1/MD5 hw accelerator. Select this if you
-	  want to use the OMAP module for SHA1/MD5 algorithms.
+	  OMAP processors have MD5/SHA1/SHA2 hw accelerator. Select this if you
+	  want to use the OMAP module for MD5/SHA1/SHA2 algorithms.
 
 config CRYPTO_DEV_OMAP_AES
 	tristate "Support for OMAP AES hw engine"
-	depends on ARCH_OMAP2 || ARCH_OMAP3
+	depends on ARCH_OMAP2 || ARCH_OMAP3 || ARCH_OMAP2PLUS
 	select CRYPTO_AES
 	select CRYPTO_BLKCIPHER2
 	help
diff --git a/drivers/crypto/amcc/crypto4xx_alg.c b/drivers/crypto/amcc/crypto4xx_alg.c
index a33243c17b00..4afca3968773 100644
--- a/drivers/crypto/amcc/crypto4xx_alg.c
+++ b/drivers/crypto/amcc/crypto4xx_alg.c
@@ -32,10 +32,10 @@
 #include "crypto4xx_sa.h"
 #include "crypto4xx_core.h"
 
-void set_dynamic_sa_command_0(struct dynamic_sa_ctl *sa, u32 save_h,
-			      u32 save_iv, u32 ld_h, u32 ld_iv, u32 hdr_proc,
-			      u32 h, u32 c, u32 pad_type, u32 op_grp, u32 op,
-			      u32 dir)
+static void set_dynamic_sa_command_0(struct dynamic_sa_ctl *sa, u32 save_h,
+				     u32 save_iv, u32 ld_h, u32 ld_iv,
+				     u32 hdr_proc, u32 h, u32 c, u32 pad_type,
+				     u32 op_grp, u32 op, u32 dir)
 {
 	sa->sa_command_0.w = 0;
 	sa->sa_command_0.bf.save_hash_state = save_h;
@@ -52,9 +52,10 @@ void set_dynamic_sa_command_0(struct dynamic_sa_ctl *sa, u32 save_h,
 	sa->sa_command_0.bf.dir = dir;
 }
 
-void set_dynamic_sa_command_1(struct dynamic_sa_ctl *sa, u32 cm, u32 hmac_mc,
-			      u32 cfb, u32 esn, u32 sn_mask, u32 mute,
-			      u32 cp_pad, u32 cp_pay, u32 cp_hdr)
+static void set_dynamic_sa_command_1(struct dynamic_sa_ctl *sa, u32 cm,
+				     u32 hmac_mc, u32 cfb, u32 esn,
+				     u32 sn_mask, u32 mute, u32 cp_pad,
+				     u32 cp_pay, u32 cp_hdr)
 {
 	sa->sa_command_1.w = 0;
 	sa->sa_command_1.bf.crypto_mode31 = (cm & 4) >> 2;
diff --git a/drivers/crypto/caam/Kconfig b/drivers/crypto/caam/Kconfig
index b44091c47f75..ca89f6b84b06 100644
--- a/drivers/crypto/caam/Kconfig
+++ b/drivers/crypto/caam/Kconfig
@@ -98,3 +98,11 @@ config CRYPTO_DEV_FSL_CAAM_RNG_API
 
 	  To compile this as a module, choose M here: the module
 	  will be called caamrng.
+
+config CRYPTO_DEV_FSL_CAAM_DEBUG
+	bool "Enable debug output in CAAM driver"
+	depends on CRYPTO_DEV_FSL_CAAM
+	default n
+	help
+	  Selecting this will enable printing of various debug
+	  information in the CAAM driver.
diff --git a/drivers/crypto/caam/Makefile b/drivers/crypto/caam/Makefile
index b1eb44838db5..d56bd0ec65d8 100644
--- a/drivers/crypto/caam/Makefile
+++ b/drivers/crypto/caam/Makefile
@@ -1,6 +1,9 @@
 #
 # Makefile for the CAAM backend and dependent components
 #
+ifeq ($(CONFIG_CRYPTO_DEV_FSL_CAAM_DEBUG), y)
+	EXTRA_CFLAGS := -DDEBUG
+endif
 
 obj-$(CONFIG_CRYPTO_DEV_FSL_CAAM) += caam.o
 obj-$(CONFIG_CRYPTO_DEV_FSL_CAAM_CRYPTO_API) += caamalg.o
diff --git a/drivers/crypto/caam/caamalg.c b/drivers/crypto/caam/caamalg.c
index bf416a8391a7..7c63b72ecd75 100644
--- a/drivers/crypto/caam/caamalg.c
+++ b/drivers/crypto/caam/caamalg.c
@@ -65,8 +65,6 @@
 #define CAAM_MAX_IV_LENGTH		16
 
 /* length of descriptors text */
-#define DESC_JOB_IO_LEN			(CAAM_CMD_SZ * 5 + CAAM_PTR_SZ * 3)
-
 #define DESC_AEAD_BASE			(4 * CAAM_CMD_SZ)
 #define DESC_AEAD_ENC_LEN		(DESC_AEAD_BASE + 16 * CAAM_CMD_SZ)
 #define DESC_AEAD_DEC_LEN		(DESC_AEAD_BASE + 21 * CAAM_CMD_SZ)
@@ -84,8 +82,6 @@
 
 #ifdef DEBUG
 /* for print_hex_dumps with line references */
-#define xstr(s) str(s)
-#define str(s) #s
 #define debug(format, arg...) printk(format, arg)
 #else
 #define debug(format, arg...)
@@ -285,7 +281,7 @@ static int aead_set_sh_desc(struct crypto_aead *aead)
 		return -ENOMEM;
 	}
 #ifdef DEBUG
-	print_hex_dump(KERN_ERR, "aead enc shdesc@"xstr(__LINE__)": ",
+	print_hex_dump(KERN_ERR, "aead enc shdesc@"__stringify(__LINE__)": ",
 		       DUMP_PREFIX_ADDRESS, 16, 4, desc,
 		       desc_bytes(desc), 1);
 #endif
@@ -353,7 +349,7 @@ static int aead_set_sh_desc(struct crypto_aead *aead)
 		return -ENOMEM;
 	}
 #ifdef DEBUG
-	print_hex_dump(KERN_ERR, "aead dec shdesc@"xstr(__LINE__)": ",
+	print_hex_dump(KERN_ERR, "aead dec shdesc@"__stringify(__LINE__)": ",
 		       DUMP_PREFIX_ADDRESS, 16, 4, desc,
 		       desc_bytes(desc), 1);
 #endif
@@ -436,7 +432,7 @@ static int aead_set_sh_desc(struct crypto_aead *aead)
 		return -ENOMEM;
 	}
 #ifdef DEBUG
-	print_hex_dump(KERN_ERR, "aead givenc shdesc@"xstr(__LINE__)": ",
+	print_hex_dump(KERN_ERR, "aead givenc shdesc@"__stringify(__LINE__)": ",
 		       DUMP_PREFIX_ADDRESS, 16, 4, desc,
 		       desc_bytes(desc), 1);
 #endif
@@ -500,7 +496,7 @@ static int aead_setkey(struct crypto_aead *aead,
 	       keylen, enckeylen, authkeylen);
 	printk(KERN_ERR "split_key_len %d split_key_pad_len %d\n",
 	       ctx->split_key_len, ctx->split_key_pad_len);
-	print_hex_dump(KERN_ERR, "key in @"xstr(__LINE__)": ",
+	print_hex_dump(KERN_ERR, "key in @"__stringify(__LINE__)": ",
 		       DUMP_PREFIX_ADDRESS, 16, 4, key, keylen, 1);
 #endif
 
@@ -519,7 +515,7 @@ static int aead_setkey(struct crypto_aead *aead,
 		return -ENOMEM;
 	}
 #ifdef DEBUG
-	print_hex_dump(KERN_ERR, "ctx.key@"xstr(__LINE__)": ",
+	print_hex_dump(KERN_ERR, "ctx.key@"__stringify(__LINE__)": ",
 		       DUMP_PREFIX_ADDRESS, 16, 4, ctx->key,
 		       ctx->split_key_pad_len + enckeylen, 1);
 #endif
@@ -549,7 +545,7 @@ static int ablkcipher_setkey(struct crypto_ablkcipher *ablkcipher,
 	u32 *desc;
 
 #ifdef DEBUG
-	print_hex_dump(KERN_ERR, "key in @"xstr(__LINE__)": ",
+	print_hex_dump(KERN_ERR, "key in @"__stringify(__LINE__)": ",
 		       DUMP_PREFIX_ADDRESS, 16, 4, key, keylen, 1);
 #endif
 
@@ -598,7 +594,8 @@ static int ablkcipher_setkey(struct crypto_ablkcipher *ablkcipher,
 		return -ENOMEM;
 	}
 #ifdef DEBUG
-	print_hex_dump(KERN_ERR, "ablkcipher enc shdesc@"xstr(__LINE__)": ",
+	print_hex_dump(KERN_ERR,
+		       "ablkcipher enc shdesc@"__stringify(__LINE__)": ",
 		       DUMP_PREFIX_ADDRESS, 16, 4, desc,
 		       desc_bytes(desc), 1);
 #endif
@@ -643,7 +640,8 @@ static int ablkcipher_setkey(struct crypto_ablkcipher *ablkcipher,
 	}
 
 #ifdef DEBUG
-	print_hex_dump(KERN_ERR, "ablkcipher dec shdesc@"xstr(__LINE__)": ",
+	print_hex_dump(KERN_ERR,
+		       "ablkcipher dec shdesc@"__stringify(__LINE__)": ",
 		       DUMP_PREFIX_ADDRESS, 16, 4, desc,
 		       desc_bytes(desc), 1);
 #endif
@@ -780,13 +778,13 @@ static void aead_encrypt_done(struct device *jrdev, u32 *desc, u32 err,
 	aead_unmap(jrdev, edesc, req);
 
 #ifdef DEBUG
-	print_hex_dump(KERN_ERR, "assoc  @"xstr(__LINE__)": ",
+	print_hex_dump(KERN_ERR, "assoc  @"__stringify(__LINE__)": ",
 		       DUMP_PREFIX_ADDRESS, 16, 4, sg_virt(req->assoc),
 		       req->assoclen , 1);
-	print_hex_dump(KERN_ERR, "dstiv  @"xstr(__LINE__)": ",
+	print_hex_dump(KERN_ERR, "dstiv  @"__stringify(__LINE__)": ",
 		       DUMP_PREFIX_ADDRESS, 16, 4, sg_virt(req->src) - ivsize,
 		       edesc->src_nents ? 100 : ivsize, 1);
-	print_hex_dump(KERN_ERR, "dst    @"xstr(__LINE__)": ",
+	print_hex_dump(KERN_ERR, "dst    @"__stringify(__LINE__)": ",
 		       DUMP_PREFIX_ADDRESS, 16, 4, sg_virt(req->src),
 		       edesc->src_nents ? 100 : req->cryptlen +
 		       ctx->authsize + 4, 1);
@@ -814,10 +812,10 @@ static void aead_decrypt_done(struct device *jrdev, u32 *desc, u32 err,
 		 offsetof(struct aead_edesc, hw_desc));
 
 #ifdef DEBUG
-	print_hex_dump(KERN_ERR, "dstiv  @"xstr(__LINE__)": ",
+	print_hex_dump(KERN_ERR, "dstiv  @"__stringify(__LINE__)": ",
 		       DUMP_PREFIX_ADDRESS, 16, 4, req->iv,
 		       ivsize, 1);
-	print_hex_dump(KERN_ERR, "dst    @"xstr(__LINE__)": ",
+	print_hex_dump(KERN_ERR, "dst    @"__stringify(__LINE__)": ",
 		       DUMP_PREFIX_ADDRESS, 16, 4, sg_virt(req->dst),
 		       req->cryptlen, 1);
 #endif
@@ -837,7 +835,7 @@ static void aead_decrypt_done(struct device *jrdev, u32 *desc, u32 err,
 		err = -EBADMSG;
 
 #ifdef DEBUG
-	print_hex_dump(KERN_ERR, "iphdrout@"xstr(__LINE__)": ",
+	print_hex_dump(KERN_ERR, "iphdrout@"__stringify(__LINE__)": ",
 		       DUMP_PREFIX_ADDRESS, 16, 4,
 		       ((char *)sg_virt(req->assoc) - sizeof(struct iphdr)),
 		       sizeof(struct iphdr) + req->assoclen +
@@ -845,7 +843,7 @@ static void aead_decrypt_done(struct device *jrdev, u32 *desc, u32 err,
 		       ctx->authsize + 36, 1);
 	if (!err && edesc->sec4_sg_bytes) {
 		struct scatterlist *sg = sg_last(req->src, edesc->src_nents);
-		print_hex_dump(KERN_ERR, "sglastout@"xstr(__LINE__)": ",
+		print_hex_dump(KERN_ERR, "sglastout@"__stringify(__LINE__)": ",
 			       DUMP_PREFIX_ADDRESS, 16, 4, sg_virt(sg),
 			sg->length + ctx->authsize + 16, 1);
 	}
@@ -878,10 +876,10 @@ static void ablkcipher_encrypt_done(struct device *jrdev, u32 *desc, u32 err,
 	}
 
 #ifdef DEBUG
-	print_hex_dump(KERN_ERR, "dstiv  @"xstr(__LINE__)": ",
+	print_hex_dump(KERN_ERR, "dstiv  @"__stringify(__LINE__)": ",
 		       DUMP_PREFIX_ADDRESS, 16, 4, req->info,
 		       edesc->src_nents > 1 ? 100 : ivsize, 1);
-	print_hex_dump(KERN_ERR, "dst    @"xstr(__LINE__)": ",
+	print_hex_dump(KERN_ERR, "dst    @"__stringify(__LINE__)": ",
 		       DUMP_PREFIX_ADDRESS, 16, 4, sg_virt(req->src),
 		       edesc->dst_nents > 1 ? 100 : req->nbytes, 1);
 #endif
@@ -913,10 +911,10 @@ static void ablkcipher_decrypt_done(struct device *jrdev, u32 *desc, u32 err,
 	}
 
 #ifdef DEBUG
-	print_hex_dump(KERN_ERR, "dstiv  @"xstr(__LINE__)": ",
+	print_hex_dump(KERN_ERR, "dstiv  @"__stringify(__LINE__)": ",
 		       DUMP_PREFIX_ADDRESS, 16, 4, req->info,
 		       ivsize, 1);
-	print_hex_dump(KERN_ERR, "dst    @"xstr(__LINE__)": ",
+	print_hex_dump(KERN_ERR, "dst    @"__stringify(__LINE__)": ",
 		       DUMP_PREFIX_ADDRESS, 16, 4, sg_virt(req->src),
 		       edesc->dst_nents > 1 ? 100 : req->nbytes, 1);
 #endif
@@ -947,16 +945,16 @@ static void init_aead_job(u32 *sh_desc, dma_addr_t ptr,
 #ifdef DEBUG
 	debug("assoclen %d cryptlen %d authsize %d\n",
 	      req->assoclen, req->cryptlen, authsize);
-	print_hex_dump(KERN_ERR, "assoc  @"xstr(__LINE__)": ",
+	print_hex_dump(KERN_ERR, "assoc  @"__stringify(__LINE__)": ",
 		       DUMP_PREFIX_ADDRESS, 16, 4, sg_virt(req->assoc),
 		       req->assoclen , 1);
-	print_hex_dump(KERN_ERR, "presciv@"xstr(__LINE__)": ",
+	print_hex_dump(KERN_ERR, "presciv@"__stringify(__LINE__)": ",
 		       DUMP_PREFIX_ADDRESS, 16, 4, req->iv,
 		       edesc->src_nents ? 100 : ivsize, 1);
-	print_hex_dump(KERN_ERR, "src    @"xstr(__LINE__)": ",
+	print_hex_dump(KERN_ERR, "src    @"__stringify(__LINE__)": ",
 		       DUMP_PREFIX_ADDRESS, 16, 4, sg_virt(req->src),
 			edesc->src_nents ? 100 : req->cryptlen, 1);
-	print_hex_dump(KERN_ERR, "shrdesc@"xstr(__LINE__)": ",
+	print_hex_dump(KERN_ERR, "shrdesc@"__stringify(__LINE__)": ",
 		       DUMP_PREFIX_ADDRESS, 16, 4, sh_desc,
 		       desc_bytes(sh_desc), 1);
 #endif
@@ -1025,15 +1023,15 @@ static void init_aead_giv_job(u32 *sh_desc, dma_addr_t ptr,
 #ifdef DEBUG
 	debug("assoclen %d cryptlen %d authsize %d\n",
 	      req->assoclen, req->cryptlen, authsize);
-	print_hex_dump(KERN_ERR, "assoc  @"xstr(__LINE__)": ",
+	print_hex_dump(KERN_ERR, "assoc  @"__stringify(__LINE__)": ",
 		       DUMP_PREFIX_ADDRESS, 16, 4, sg_virt(req->assoc),
 		       req->assoclen , 1);
-	print_hex_dump(KERN_ERR, "presciv@"xstr(__LINE__)": ",
+	print_hex_dump(KERN_ERR, "presciv@"__stringify(__LINE__)": ",
 		       DUMP_PREFIX_ADDRESS, 16, 4, req->iv, ivsize, 1);
-	print_hex_dump(KERN_ERR, "src    @"xstr(__LINE__)": ",
+	print_hex_dump(KERN_ERR, "src    @"__stringify(__LINE__)": ",
 		       DUMP_PREFIX_ADDRESS, 16, 4, sg_virt(req->src),
 			edesc->src_nents > 1 ? 100 : req->cryptlen, 1);
-	print_hex_dump(KERN_ERR, "shrdesc@"xstr(__LINE__)": ",
+	print_hex_dump(KERN_ERR, "shrdesc@"__stringify(__LINE__)": ",
 		       DUMP_PREFIX_ADDRESS, 16, 4, sh_desc,
 		       desc_bytes(sh_desc), 1);
 #endif
@@ -1086,10 +1084,10 @@ static void init_ablkcipher_job(u32 *sh_desc, dma_addr_t ptr,
 	int len, sec4_sg_index = 0;
 
 #ifdef DEBUG
-	print_hex_dump(KERN_ERR, "presciv@"xstr(__LINE__)": ",
+	print_hex_dump(KERN_ERR, "presciv@"__stringify(__LINE__)": ",
 		       DUMP_PREFIX_ADDRESS, 16, 4, req->info,
 		       ivsize, 1);
-	print_hex_dump(KERN_ERR, "src    @"xstr(__LINE__)": ",
+	print_hex_dump(KERN_ERR, "src    @"__stringify(__LINE__)": ",
 		       DUMP_PREFIX_ADDRESS, 16, 4, sg_virt(req->src),
 		       edesc->src_nents ? 100 : req->nbytes, 1);
 #endif
@@ -1247,7 +1245,7 @@ static int aead_encrypt(struct aead_request *req)
 	init_aead_job(ctx->sh_desc_enc, ctx->sh_desc_enc_dma, edesc, req,
 		      all_contig, true);
 #ifdef DEBUG
-	print_hex_dump(KERN_ERR, "aead jobdesc@"xstr(__LINE__)": ",
+	print_hex_dump(KERN_ERR, "aead jobdesc@"__stringify(__LINE__)": ",
 		       DUMP_PREFIX_ADDRESS, 16, 4, edesc->hw_desc,
 		       desc_bytes(edesc->hw_desc), 1);
 #endif
@@ -1281,7 +1279,7 @@ static int aead_decrypt(struct aead_request *req)
 		return PTR_ERR(edesc);
 
 #ifdef DEBUG
-	print_hex_dump(KERN_ERR, "dec src@"xstr(__LINE__)": ",
+	print_hex_dump(KERN_ERR, "dec src@"__stringify(__LINE__)": ",
 		       DUMP_PREFIX_ADDRESS, 16, 4, sg_virt(req->src),
 		       req->cryptlen, 1);
 #endif
@@ -1290,7 +1288,7 @@ static int aead_decrypt(struct aead_request *req)
 	init_aead_job(ctx->sh_desc_dec,
 		      ctx->sh_desc_dec_dma, edesc, req, all_contig, false);
 #ifdef DEBUG
-	print_hex_dump(KERN_ERR, "aead jobdesc@"xstr(__LINE__)": ",
+	print_hex_dump(KERN_ERR, "aead jobdesc@"__stringify(__LINE__)": ",
 		       DUMP_PREFIX_ADDRESS, 16, 4, edesc->hw_desc,
 		       desc_bytes(edesc->hw_desc), 1);
 #endif
@@ -1437,7 +1435,7 @@ static int aead_givencrypt(struct aead_givcrypt_request *areq)
 		return PTR_ERR(edesc);
 
 #ifdef DEBUG
-	print_hex_dump(KERN_ERR, "giv src@"xstr(__LINE__)": ",
+	print_hex_dump(KERN_ERR, "giv src@"__stringify(__LINE__)": ",
 		       DUMP_PREFIX_ADDRESS, 16, 4, sg_virt(req->src),
 		       req->cryptlen, 1);
 #endif
@@ -1446,7 +1444,7 @@ static int aead_givencrypt(struct aead_givcrypt_request *areq)
 	init_aead_giv_job(ctx->sh_desc_givenc,
 			  ctx->sh_desc_givenc_dma, edesc, req, contig);
 #ifdef DEBUG
-	print_hex_dump(KERN_ERR, "aead jobdesc@"xstr(__LINE__)": ",
+	print_hex_dump(KERN_ERR, "aead jobdesc@"__stringify(__LINE__)": ",
 		       DUMP_PREFIX_ADDRESS, 16, 4, edesc->hw_desc,
 		       desc_bytes(edesc->hw_desc), 1);
 #endif
@@ -1546,7 +1544,7 @@ static struct ablkcipher_edesc *ablkcipher_edesc_alloc(struct ablkcipher_request
 	edesc->iv_dma = iv_dma;
 
 #ifdef DEBUG
-	print_hex_dump(KERN_ERR, "ablkcipher sec4_sg@"xstr(__LINE__)": ",
+	print_hex_dump(KERN_ERR, "ablkcipher sec4_sg@"__stringify(__LINE__)": ",
 		       DUMP_PREFIX_ADDRESS, 16, 4, edesc->sec4_sg,
 		       sec4_sg_bytes, 1);
 #endif
@@ -1575,7 +1573,7 @@ static int ablkcipher_encrypt(struct ablkcipher_request *req)
 	init_ablkcipher_job(ctx->sh_desc_enc,
 		ctx->sh_desc_enc_dma, edesc, req, iv_contig);
 #ifdef DEBUG
-	print_hex_dump(KERN_ERR, "ablkcipher jobdesc@"xstr(__LINE__)": ",
+	print_hex_dump(KERN_ERR, "ablkcipher jobdesc@"__stringify(__LINE__)": ",
 		       DUMP_PREFIX_ADDRESS, 16, 4, edesc->hw_desc,
 		       desc_bytes(edesc->hw_desc), 1);
 #endif
@@ -1613,7 +1611,7 @@ static int ablkcipher_decrypt(struct ablkcipher_request *req)
 		ctx->sh_desc_dec_dma, edesc, req, iv_contig);
 	desc = edesc->hw_desc;
 #ifdef DEBUG
-	print_hex_dump(KERN_ERR, "ablkcipher jobdesc@"xstr(__LINE__)": ",
+	print_hex_dump(KERN_ERR, "ablkcipher jobdesc@"__stringify(__LINE__)": ",
 		       DUMP_PREFIX_ADDRESS, 16, 4, edesc->hw_desc,
 		       desc_bytes(edesc->hw_desc), 1);
 #endif
diff --git a/drivers/crypto/caam/caamhash.c b/drivers/crypto/caam/caamhash.c
index 84573b4d6f92..e732bd962e98 100644
--- a/drivers/crypto/caam/caamhash.c
+++ b/drivers/crypto/caam/caamhash.c
@@ -72,8 +72,6 @@
 #define CAAM_MAX_HASH_DIGEST_SIZE	SHA512_DIGEST_SIZE
 
 /* length of descriptors text */
-#define DESC_JOB_IO_LEN			(CAAM_CMD_SZ * 5 + CAAM_PTR_SZ * 3)
-
 #define DESC_AHASH_BASE			(4 * CAAM_CMD_SZ)
 #define DESC_AHASH_UPDATE_LEN		(6 * CAAM_CMD_SZ)
 #define DESC_AHASH_UPDATE_FIRST_LEN	(DESC_AHASH_BASE + 4 * CAAM_CMD_SZ)
@@ -91,8 +89,6 @@
 
 #ifdef DEBUG
 /* for print_hex_dumps with line references */
-#define xstr(s) str(s)
-#define str(s) #s
 #define debug(format, arg...) printk(format, arg)
 #else
 #define debug(format, arg...)
@@ -331,7 +327,8 @@ static int ahash_set_sh_desc(struct crypto_ahash *ahash)
 		return -ENOMEM;
 	}
 #ifdef DEBUG
-	print_hex_dump(KERN_ERR, "ahash update shdesc@"xstr(__LINE__)": ",
+	print_hex_dump(KERN_ERR,
+		       "ahash update shdesc@"__stringify(__LINE__)": ",
 		       DUMP_PREFIX_ADDRESS, 16, 4, desc, desc_bytes(desc), 1);
 #endif
 
@@ -349,7 +346,8 @@ static int ahash_set_sh_desc(struct crypto_ahash *ahash)
 		return -ENOMEM;
 	}
 #ifdef DEBUG
-	print_hex_dump(KERN_ERR, "ahash update first shdesc@"xstr(__LINE__)": ",
+	print_hex_dump(KERN_ERR,
+		       "ahash update first shdesc@"__stringify(__LINE__)": ",
 		       DUMP_PREFIX_ADDRESS, 16, 4, desc, desc_bytes(desc), 1);
 #endif
 
@@ -366,7 +364,7 @@ static int ahash_set_sh_desc(struct crypto_ahash *ahash)
 		return -ENOMEM;
 	}
 #ifdef DEBUG
-	print_hex_dump(KERN_ERR, "ahash final shdesc@"xstr(__LINE__)": ",
+	print_hex_dump(KERN_ERR, "ahash final shdesc@"__stringify(__LINE__)": ",
 		       DUMP_PREFIX_ADDRESS, 16, 4, desc,
 		       desc_bytes(desc), 1);
 #endif
@@ -384,7 +382,7 @@ static int ahash_set_sh_desc(struct crypto_ahash *ahash)
 		return -ENOMEM;
 	}
 #ifdef DEBUG
-	print_hex_dump(KERN_ERR, "ahash finup shdesc@"xstr(__LINE__)": ",
+	print_hex_dump(KERN_ERR, "ahash finup shdesc@"__stringify(__LINE__)": ",
 		       DUMP_PREFIX_ADDRESS, 16, 4, desc,
 		       desc_bytes(desc), 1);
 #endif
@@ -403,7 +401,8 @@ static int ahash_set_sh_desc(struct crypto_ahash *ahash)
 		return -ENOMEM;
 	}
 #ifdef DEBUG
-	print_hex_dump(KERN_ERR, "ahash digest shdesc@"xstr(__LINE__)": ",
+	print_hex_dump(KERN_ERR,
+		       "ahash digest shdesc@"__stringify(__LINE__)": ",
 		       DUMP_PREFIX_ADDRESS, 16, 4, desc,
 		       desc_bytes(desc), 1);
 #endif
@@ -464,9 +463,9 @@ static int hash_digest_key(struct caam_hash_ctx *ctx, const u8 *key_in,
 			 LDST_SRCDST_BYTE_CONTEXT);
 
 #ifdef DEBUG
-	print_hex_dump(KERN_ERR, "key_in@"xstr(__LINE__)": ",
+	print_hex_dump(KERN_ERR, "key_in@"__stringify(__LINE__)": ",
 		       DUMP_PREFIX_ADDRESS, 16, 4, key_in, *keylen, 1);
-	print_hex_dump(KERN_ERR, "jobdesc@"xstr(__LINE__)": ",
+	print_hex_dump(KERN_ERR, "jobdesc@"__stringify(__LINE__)": ",
 		       DUMP_PREFIX_ADDRESS, 16, 4, desc, desc_bytes(desc), 1);
 #endif
 
@@ -479,7 +478,8 @@ static int hash_digest_key(struct caam_hash_ctx *ctx, const u8 *key_in,
 		wait_for_completion_interruptible(&result.completion);
 		ret = result.err;
 #ifdef DEBUG
-		print_hex_dump(KERN_ERR, "digested key@"xstr(__LINE__)": ",
+		print_hex_dump(KERN_ERR,
+			       "digested key@"__stringify(__LINE__)": ",
 			       DUMP_PREFIX_ADDRESS, 16, 4, key_in,
 			       digestsize, 1);
 #endif
@@ -530,7 +530,7 @@ static int ahash_setkey(struct crypto_ahash *ahash,
 #ifdef DEBUG
 	printk(KERN_ERR "split_key_len %d split_key_pad_len %d\n",
 	       ctx->split_key_len, ctx->split_key_pad_len);
-	print_hex_dump(KERN_ERR, "key in @"xstr(__LINE__)": ",
+	print_hex_dump(KERN_ERR, "key in @"__stringify(__LINE__)": ",
 		       DUMP_PREFIX_ADDRESS, 16, 4, key, keylen, 1);
 #endif
 
@@ -545,7 +545,7 @@ static int ahash_setkey(struct crypto_ahash *ahash,
 		return -ENOMEM;
 	}
 #ifdef DEBUG
-	print_hex_dump(KERN_ERR, "ctx.key@"xstr(__LINE__)": ",
+	print_hex_dump(KERN_ERR, "ctx.key@"__stringify(__LINE__)": ",
 		       DUMP_PREFIX_ADDRESS, 16, 4, ctx->key,
 		       ctx->split_key_pad_len, 1);
 #endif
@@ -638,11 +638,11 @@ static void ahash_done(struct device *jrdev, u32 *desc, u32 err,
 	kfree(edesc);
 
 #ifdef DEBUG
-	print_hex_dump(KERN_ERR, "ctx@"xstr(__LINE__)": ",
+	print_hex_dump(KERN_ERR, "ctx@"__stringify(__LINE__)": ",
 		       DUMP_PREFIX_ADDRESS, 16, 4, state->caam_ctx,
 		       ctx->ctx_len, 1);
 	if (req->result)
-		print_hex_dump(KERN_ERR, "result@"xstr(__LINE__)": ",
+		print_hex_dump(KERN_ERR, "result@"__stringify(__LINE__)": ",
 			       DUMP_PREFIX_ADDRESS, 16, 4, req->result,
 			       digestsize, 1);
 #endif
@@ -676,11 +676,11 @@ static void ahash_done_bi(struct device *jrdev, u32 *desc, u32 err,
 	kfree(edesc);
 
 #ifdef DEBUG
-	print_hex_dump(KERN_ERR, "ctx@"xstr(__LINE__)": ",
+	print_hex_dump(KERN_ERR, "ctx@"__stringify(__LINE__)": ",
 		       DUMP_PREFIX_ADDRESS, 16, 4, state->caam_ctx,
 		       ctx->ctx_len, 1);
 	if (req->result)
-		print_hex_dump(KERN_ERR, "result@"xstr(__LINE__)": ",
+		print_hex_dump(KERN_ERR, "result@"__stringify(__LINE__)": ",
 			       DUMP_PREFIX_ADDRESS, 16, 4, req->result,
 			       digestsize, 1);
 #endif
@@ -714,11 +714,11 @@ static void ahash_done_ctx_src(struct device *jrdev, u32 *desc, u32 err,
 	kfree(edesc);
 
 #ifdef DEBUG
-	print_hex_dump(KERN_ERR, "ctx@"xstr(__LINE__)": ",
+	print_hex_dump(KERN_ERR, "ctx@"__stringify(__LINE__)": ",
 		       DUMP_PREFIX_ADDRESS, 16, 4, state->caam_ctx,
 		       ctx->ctx_len, 1);
 	if (req->result)
-		print_hex_dump(KERN_ERR, "result@"xstr(__LINE__)": ",
+		print_hex_dump(KERN_ERR, "result@"__stringify(__LINE__)": ",
 			       DUMP_PREFIX_ADDRESS, 16, 4, req->result,
 			       digestsize, 1);
 #endif
@@ -752,11 +752,11 @@ static void ahash_done_ctx_dst(struct device *jrdev, u32 *desc, u32 err,
 	kfree(edesc);
 
 #ifdef DEBUG
-	print_hex_dump(KERN_ERR, "ctx@"xstr(__LINE__)": ",
+	print_hex_dump(KERN_ERR, "ctx@"__stringify(__LINE__)": ",
 		       DUMP_PREFIX_ADDRESS, 16, 4, state->caam_ctx,
 		       ctx->ctx_len, 1);
 	if (req->result)
-		print_hex_dump(KERN_ERR, "result@"xstr(__LINE__)": ",
+		print_hex_dump(KERN_ERR, "result@"__stringify(__LINE__)": ",
 			       DUMP_PREFIX_ADDRESS, 16, 4, req->result,
 			       digestsize, 1);
 #endif
@@ -852,7 +852,7 @@ static int ahash_update_ctx(struct ahash_request *req)
 		append_seq_out_ptr(desc, state->ctx_dma, ctx->ctx_len, 0);
 
 #ifdef DEBUG
-		print_hex_dump(KERN_ERR, "jobdesc@"xstr(__LINE__)": ",
+		print_hex_dump(KERN_ERR, "jobdesc@"__stringify(__LINE__)": ",
 			       DUMP_PREFIX_ADDRESS, 16, 4, desc,
 			       desc_bytes(desc), 1);
 #endif
@@ -871,9 +871,9 @@ static int ahash_update_ctx(struct ahash_request *req)
 		*next_buflen = last_buflen;
 	}
 #ifdef DEBUG
-	print_hex_dump(KERN_ERR, "buf@"xstr(__LINE__)": ",
+	print_hex_dump(KERN_ERR, "buf@"__stringify(__LINE__)": ",
 		       DUMP_PREFIX_ADDRESS, 16, 4, buf, *buflen, 1);
-	print_hex_dump(KERN_ERR, "next buf@"xstr(__LINE__)": ",
+	print_hex_dump(KERN_ERR, "next buf@"__stringify(__LINE__)": ",
 		       DUMP_PREFIX_ADDRESS, 16, 4, next_buf,
 		       *next_buflen, 1);
 #endif
@@ -937,7 +937,7 @@ static int ahash_final_ctx(struct ahash_request *req)
 						digestsize);
 
 #ifdef DEBUG
-	print_hex_dump(KERN_ERR, "jobdesc@"xstr(__LINE__)": ",
+	print_hex_dump(KERN_ERR, "jobdesc@"__stringify(__LINE__)": ",
 		       DUMP_PREFIX_ADDRESS, 16, 4, desc, desc_bytes(desc), 1);
 #endif
 
@@ -1016,7 +1016,7 @@ static int ahash_finup_ctx(struct ahash_request *req)
 						digestsize);
 
 #ifdef DEBUG
-	print_hex_dump(KERN_ERR, "jobdesc@"xstr(__LINE__)": ",
+	print_hex_dump(KERN_ERR, "jobdesc@"__stringify(__LINE__)": ",
 		       DUMP_PREFIX_ADDRESS, 16, 4, desc, desc_bytes(desc), 1);
 #endif
 
@@ -1086,7 +1086,7 @@ static int ahash_digest(struct ahash_request *req)
 						digestsize);
 
 #ifdef DEBUG
-	print_hex_dump(KERN_ERR, "jobdesc@"xstr(__LINE__)": ",
+	print_hex_dump(KERN_ERR, "jobdesc@"__stringify(__LINE__)": ",
 		       DUMP_PREFIX_ADDRESS, 16, 4, desc, desc_bytes(desc), 1);
 #endif
 
@@ -1140,7 +1140,7 @@ static int ahash_final_no_ctx(struct ahash_request *req)
 	edesc->src_nents = 0;
 
 #ifdef DEBUG
-	print_hex_dump(KERN_ERR, "jobdesc@"xstr(__LINE__)": ",
+	print_hex_dump(KERN_ERR, "jobdesc@"__stringify(__LINE__)": ",
 		       DUMP_PREFIX_ADDRESS, 16, 4, desc, desc_bytes(desc), 1);
 #endif
 
@@ -1228,7 +1228,7 @@ static int ahash_update_no_ctx(struct ahash_request *req)
 		map_seq_out_ptr_ctx(desc, jrdev, state, ctx->ctx_len);
 
 #ifdef DEBUG
-		print_hex_dump(KERN_ERR, "jobdesc@"xstr(__LINE__)": ",
+		print_hex_dump(KERN_ERR, "jobdesc@"__stringify(__LINE__)": ",
 			       DUMP_PREFIX_ADDRESS, 16, 4, desc,
 			       desc_bytes(desc), 1);
 #endif
@@ -1250,9 +1250,9 @@ static int ahash_update_no_ctx(struct ahash_request *req)
 		*next_buflen = 0;
 	}
 #ifdef DEBUG
-	print_hex_dump(KERN_ERR, "buf@"xstr(__LINE__)": ",
+	print_hex_dump(KERN_ERR, "buf@"__stringify(__LINE__)": ",
 		       DUMP_PREFIX_ADDRESS, 16, 4, buf, *buflen, 1);
-	print_hex_dump(KERN_ERR, "next buf@"xstr(__LINE__)": ",
+	print_hex_dump(KERN_ERR, "next buf@"__stringify(__LINE__)": ",
 		       DUMP_PREFIX_ADDRESS, 16, 4, next_buf,
 		       *next_buflen, 1);
 #endif
@@ -1321,7 +1321,7 @@ static int ahash_finup_no_ctx(struct ahash_request *req)
 						digestsize);
 
 #ifdef DEBUG
-	print_hex_dump(KERN_ERR, "jobdesc@"xstr(__LINE__)": ",
+	print_hex_dump(KERN_ERR, "jobdesc@"__stringify(__LINE__)": ",
 		       DUMP_PREFIX_ADDRESS, 16, 4, desc, desc_bytes(desc), 1);
 #endif
 
@@ -1414,7 +1414,7 @@ static int ahash_update_first(struct ahash_request *req)
 		map_seq_out_ptr_ctx(desc, jrdev, state, ctx->ctx_len);
 
 #ifdef DEBUG
-		print_hex_dump(KERN_ERR, "jobdesc@"xstr(__LINE__)": ",
+		print_hex_dump(KERN_ERR, "jobdesc@"__stringify(__LINE__)": ",
 			       DUMP_PREFIX_ADDRESS, 16, 4, desc,
 			       desc_bytes(desc), 1);
 #endif
@@ -1438,7 +1438,7 @@ static int ahash_update_first(struct ahash_request *req)
 		sg_copy(next_buf, req->src, req->nbytes);
 	}
 #ifdef DEBUG
-	print_hex_dump(KERN_ERR, "next buf@"xstr(__LINE__)": ",
+	print_hex_dump(KERN_ERR, "next buf@"__stringify(__LINE__)": ",
 		       DUMP_PREFIX_ADDRESS, 16, 4, next_buf,
 		       *next_buflen, 1);
 #endif
diff --git a/drivers/crypto/caam/ctrl.c b/drivers/crypto/caam/ctrl.c
index f5d6deced1cb..b010d42a1803 100644
--- a/drivers/crypto/caam/ctrl.c
+++ b/drivers/crypto/caam/ctrl.c
@@ -75,55 +75,53 @@ static void build_instantiation_desc(u32 *desc)
 			 OP_ALG_RNG4_SK);
 }
 
-struct instantiate_result {
-	struct completion completion;
-	int err;
-};
-
-static void rng4_init_done(struct device *dev, u32 *desc, u32 err,
-			   void *context)
-{
-	struct instantiate_result *instantiation = context;
-
-	if (err) {
-		char tmp[CAAM_ERROR_STR_MAX];
-
-		dev_err(dev, "%08x: %s\n", err, caam_jr_strstatus(tmp, err));
-	}
-
-	instantiation->err = err;
-	complete(&instantiation->completion);
-}
-
-static int instantiate_rng(struct device *jrdev)
+static int instantiate_rng(struct device *ctrldev)
 {
-	struct instantiate_result instantiation;
-
-	dma_addr_t desc_dma;
+	struct caam_drv_private *ctrlpriv = dev_get_drvdata(ctrldev);
+	struct caam_full __iomem *topregs;
+	unsigned int timeout = 100000;
 	u32 *desc;
-	int ret;
+	int i, ret = 0;
 
 	desc = kmalloc(CAAM_CMD_SZ * 6, GFP_KERNEL | GFP_DMA);
 	if (!desc) {
-		dev_err(jrdev, "cannot allocate RNG init descriptor memory\n");
+		dev_err(ctrldev, "can't allocate RNG init descriptor memory\n");
 		return -ENOMEM;
 	}
-
 	build_instantiation_desc(desc);
-	desc_dma = dma_map_single(jrdev, desc, desc_bytes(desc), DMA_TO_DEVICE);
-	init_completion(&instantiation.completion);
-	ret = caam_jr_enqueue(jrdev, desc, rng4_init_done, &instantiation);
-	if (!ret) {
-		wait_for_completion_interruptible(&instantiation.completion);
-		ret = instantiation.err;
-		if (ret)
-			dev_err(jrdev, "unable to instantiate RNG\n");
+
+	/* Set the bit to request direct access to DECO0 */
+	topregs = (struct caam_full __iomem *)ctrlpriv->ctrl;
+	setbits32(&topregs->ctrl.deco_rq, DECORR_RQD0ENABLE);
+
+	while (!(rd_reg32(&topregs->ctrl.deco_rq) & DECORR_DEN0) &&
+								 --timeout)
+		cpu_relax();
+
+	if (!timeout) {
+		dev_err(ctrldev, "failed to acquire DECO 0\n");
+		ret = -EIO;
+		goto out;
 	}
 
-	dma_unmap_single(jrdev, desc_dma, desc_bytes(desc), DMA_TO_DEVICE);
+	for (i = 0; i < desc_len(desc); i++)
+		topregs->deco.descbuf[i] = *(desc + i);
 
-	kfree(desc);
+	wr_reg32(&topregs->deco.jr_ctl_hi, DECO_JQCR_WHL | DECO_JQCR_FOUR);
 
+	timeout = 10000000;
+	while ((rd_reg32(&topregs->deco.desc_dbg) & DECO_DBG_VALID) &&
+								 --timeout)
+		cpu_relax();
+
+	if (!timeout) {
+		dev_err(ctrldev, "failed to instantiate RNG\n");
+		ret = -EIO;
+	}
+
+	clrbits32(&topregs->ctrl.deco_rq, DECORR_RQD0ENABLE);
+out:
+	kfree(desc);
 	return ret;
 }
 
@@ -303,7 +301,7 @@ static int caam_probe(struct platform_device *pdev)
 	if ((cha_vid & CHA_ID_RNG_MASK) >> CHA_ID_RNG_SHIFT >= 4 &&
 	    !(rd_reg32(&topregs->ctrl.r4tst[0].rdsta) & RDSTA_IF0)) {
 		kick_trng(pdev);
-		ret = instantiate_rng(ctrlpriv->jrdev[0]);
+		ret = instantiate_rng(dev);
 		if (ret) {
 			caam_remove(pdev);
 			return ret;
@@ -315,9 +313,6 @@ static int caam_probe(struct platform_device *pdev)
 
 	/* NOTE: RTIC detection ought to go here, around Si time */
 
-	/* Initialize queue allocator lock */
-	spin_lock_init(&ctrlpriv->jr_alloc_lock);
-
 	caam_id = rd_reg64(&topregs->ctrl.perfmon.caam_id);
 
 	/* Report "alive" for developer to see */
diff --git a/drivers/crypto/caam/desc_constr.h b/drivers/crypto/caam/desc_constr.h
index fe3bfd1b08ca..cd5f678847ce 100644
--- a/drivers/crypto/caam/desc_constr.h
+++ b/drivers/crypto/caam/desc_constr.h
@@ -10,6 +10,7 @@
 #define CAAM_CMD_SZ sizeof(u32)
 #define CAAM_PTR_SZ sizeof(dma_addr_t)
 #define CAAM_DESC_BYTES_MAX (CAAM_CMD_SZ * MAX_CAAM_DESCSIZE)
+#define DESC_JOB_IO_LEN (CAAM_CMD_SZ * 5 + CAAM_PTR_SZ * 3)
 
 #ifdef DEBUG
 #define PRINT_POS do { printk(KERN_DEBUG "%02d: %s\n", desc_len(desc),\
diff --git a/drivers/crypto/caam/intern.h b/drivers/crypto/caam/intern.h
index e4a16b741371..34c4b9f7fbfa 100644
--- a/drivers/crypto/caam/intern.h
+++ b/drivers/crypto/caam/intern.h
@@ -9,9 +9,6 @@
 #ifndef INTERN_H
 #define INTERN_H
 
-#define JOBR_UNASSIGNED 0
-#define JOBR_ASSIGNED 1
-
 /* Currently comes from Kconfig param as a ^2 (driver-required) */
 #define JOBR_DEPTH (1 << CONFIG_CRYPTO_DEV_FSL_CAAM_RINGSIZE)
 
@@ -46,7 +43,6 @@ struct caam_drv_private_jr {
 	struct caam_job_ring __iomem *rregs;	/* JobR's register space */
 	struct tasklet_struct irqtask;
 	int irq;			/* One per queue */
-	int assign;			/* busy/free */
 
 	/* Job ring info */
 	int ringsize;	/* Size of rings (assume input = output) */
@@ -68,7 +64,6 @@ struct caam_drv_private {
 
 	struct device *dev;
 	struct device **jrdev; /* Alloc'ed array per sub-device */
-	spinlock_t jr_alloc_lock;
 	struct platform_device *pdev;
 
 	/* Physical-presence section */
diff --git a/drivers/crypto/caam/jr.c b/drivers/crypto/caam/jr.c
index b4aa773ecbc8..105ba4da6180 100644
--- a/drivers/crypto/caam/jr.c
+++ b/drivers/crypto/caam/jr.c
@@ -126,72 +126,6 @@ static void caam_jr_dequeue(unsigned long devarg)
 }
 
 /**
- * caam_jr_register() - Alloc a ring for someone to use as needed. Returns
- * an ordinal of the rings allocated, else returns -ENODEV if no rings
- * are available.
- * @ctrldev: points to the controller level dev (parent) that
- *           owns rings available for use.
- * @dev:     points to where a pointer to the newly allocated queue's
- *           dev can be written to if successful.
- **/
-int caam_jr_register(struct device *ctrldev, struct device **rdev)
-{
-	struct caam_drv_private *ctrlpriv = dev_get_drvdata(ctrldev);
-	struct caam_drv_private_jr *jrpriv = NULL;
-	int ring;
-
-	/* Lock, if free ring - assign, unlock */
-	spin_lock(&ctrlpriv->jr_alloc_lock);
-	for (ring = 0; ring < ctrlpriv->total_jobrs; ring++) {
-		jrpriv = dev_get_drvdata(ctrlpriv->jrdev[ring]);
-		if (jrpriv->assign == JOBR_UNASSIGNED) {
-			jrpriv->assign = JOBR_ASSIGNED;
-			*rdev = ctrlpriv->jrdev[ring];
-			spin_unlock(&ctrlpriv->jr_alloc_lock);
-			return ring;
-		}
-	}
-
-	/* If assigned, write dev where caller needs it */
-	spin_unlock(&ctrlpriv->jr_alloc_lock);
-	*rdev = NULL;
-
-	return -ENODEV;
-}
-EXPORT_SYMBOL(caam_jr_register);
-
-/**
- * caam_jr_deregister() - Deregister an API and release the queue.
- * Returns 0 if OK, -EBUSY if queue still contains pending entries
- * or unprocessed results at the time of the call
- * @dev     - points to the dev that identifies the queue to
- *            be released.
- **/
-int caam_jr_deregister(struct device *rdev)
-{
-	struct caam_drv_private_jr *jrpriv = dev_get_drvdata(rdev);
-	struct caam_drv_private *ctrlpriv;
-
-	/* Get the owning controller's private space */
-	ctrlpriv = dev_get_drvdata(jrpriv->parentdev);
-
-	/*
-	 * Make sure ring empty before release
-	 */
-	if (rd_reg32(&jrpriv->rregs->outring_used) ||
-	    (rd_reg32(&jrpriv->rregs->inpring_avail) != JOBR_DEPTH))
-		return -EBUSY;
-
-	/* Release ring */
-	spin_lock(&ctrlpriv->jr_alloc_lock);
-	jrpriv->assign = JOBR_UNASSIGNED;
-	spin_unlock(&ctrlpriv->jr_alloc_lock);
-
-	return 0;
-}
-EXPORT_SYMBOL(caam_jr_deregister);
-
-/**
  * caam_jr_enqueue() - Enqueue a job descriptor head. Returns 0 if OK,
  * -EBUSY if the queue is full, -EIO if it cannot map the caller's
  * descriptor.
@@ -379,7 +313,6 @@ static int caam_jr_init(struct device *dev)
 		  (JOBR_INTC_COUNT_THLD << JRCFG_ICDCT_SHIFT) |
 		  (JOBR_INTC_TIME_THLD << JRCFG_ICTT_SHIFT));
 
-	jrp->assign = JOBR_UNASSIGNED;
 	return 0;
 }
 
diff --git a/drivers/crypto/caam/jr.h b/drivers/crypto/caam/jr.h
index c23df395b622..9d8741a59037 100644
--- a/drivers/crypto/caam/jr.h
+++ b/drivers/crypto/caam/jr.h
@@ -8,8 +8,6 @@
 #define JR_H
 
 /* Prototypes for backend-level services exposed to APIs */
-int caam_jr_register(struct device *ctrldev, struct device **rdev);
-int caam_jr_deregister(struct device *rdev);
 int caam_jr_enqueue(struct device *dev, u32 *desc,
 		    void (*cbk)(struct device *dev, u32 *desc, u32 status,
 				void *areq),
diff --git a/drivers/crypto/caam/key_gen.c b/drivers/crypto/caam/key_gen.c
index 87138d2adb5f..ea2e406610eb 100644
--- a/drivers/crypto/caam/key_gen.c
+++ b/drivers/crypto/caam/key_gen.c
@@ -95,9 +95,9 @@ int gen_split_key(struct device *jrdev, u8 *key_out, int split_key_len,
 			  LDST_CLASS_2_CCB | FIFOST_TYPE_SPLIT_KEK);
 
 #ifdef DEBUG
-	print_hex_dump(KERN_ERR, "ctx.key@"xstr(__LINE__)": ",
+	print_hex_dump(KERN_ERR, "ctx.key@"__stringify(__LINE__)": ",
 		       DUMP_PREFIX_ADDRESS, 16, 4, key_in, keylen, 1);
-	print_hex_dump(KERN_ERR, "jobdesc@"xstr(__LINE__)": ",
+	print_hex_dump(KERN_ERR, "jobdesc@"__stringify(__LINE__)": ",
 		       DUMP_PREFIX_ADDRESS, 16, 4, desc, desc_bytes(desc), 1);
 #endif
 
@@ -110,7 +110,7 @@ int gen_split_key(struct device *jrdev, u8 *key_out, int split_key_len,
 		wait_for_completion_interruptible(&result.completion);
 		ret = result.err;
 #ifdef DEBUG
-		print_hex_dump(KERN_ERR, "ctx.key@"xstr(__LINE__)": ",
+		print_hex_dump(KERN_ERR, "ctx.key@"__stringify(__LINE__)": ",
 			       DUMP_PREFIX_ADDRESS, 16, 4, key_out,
 			       split_key_pad_len, 1);
 #endif
diff --git a/drivers/crypto/caam/regs.h b/drivers/crypto/caam/regs.h
index c09142fc13e3..4455396918de 100644
--- a/drivers/crypto/caam/regs.h
+++ b/drivers/crypto/caam/regs.h
@@ -341,6 +341,8 @@ struct caam_ctrl {
 #define MCFGR_DMA_RESET		0x10000000
 #define MCFGR_LONG_PTR		0x00010000 /* Use >32-bit desc addressing */
 #define SCFGR_RDBENABLE		0x00000400
+#define DECORR_RQD0ENABLE	0x00000001 /* Enable DECO0 for direct access */
+#define DECORR_DEN0		0x00010000 /* DECO0 available for access*/
 
 /* AXI read cache control */
 #define MCFGR_ARCACHE_SHIFT	12
@@ -703,9 +705,16 @@ struct caam_deco {
 	struct deco_sg_table sctr_tbl[4];	/* DxSTR - Scatter Tables */
 	u32 rsvd29[48];
 	u32 descbuf[64];	/* DxDESB - Descriptor buffer */
-	u32 rsvd30[320];
+	u32 rscvd30[193];
+	u32 desc_dbg;		/* DxDDR - DECO Debug Register */
+	u32 rsvd31[126];
 };
 
+/* DECO DBG Register Valid Bit*/
+#define DECO_DBG_VALID		0x80000000
+#define DECO_JQCR_WHL		0x20000000
+#define DECO_JQCR_FOUR		0x10000000
+
 /*
  * Current top-level view of memory map is:
  *
@@ -733,6 +742,7 @@ struct caam_full {
 	u64 rsvd[512];
 	struct caam_assurance assure;
 	struct caam_queue_if qi;
+	struct caam_deco deco;
 };
 
 #endif /* REGS_H */
diff --git a/drivers/crypto/nx/nx-aes-cbc.c b/drivers/crypto/nx/nx-aes-cbc.c
index 35d483f8db66..cc00b52306ba 100644
--- a/drivers/crypto/nx/nx-aes-cbc.c
+++ b/drivers/crypto/nx/nx-aes-cbc.c
@@ -70,35 +70,52 @@ static int cbc_aes_nx_crypt(struct blkcipher_desc *desc,
 {
 	struct nx_crypto_ctx *nx_ctx = crypto_blkcipher_ctx(desc->tfm);
 	struct nx_csbcpb *csbcpb = nx_ctx->csbcpb;
+	unsigned long irq_flags;
+	unsigned int processed = 0, to_process;
+	u32 max_sg_len;
 	int rc;
 
-	if (nbytes > nx_ctx->ap->databytelen)
-		return -EINVAL;
+	spin_lock_irqsave(&nx_ctx->lock, irq_flags);
+
+	max_sg_len = min_t(u32, nx_driver.of.max_sg_len/sizeof(struct nx_sg),
+			   nx_ctx->ap->sglen);
 
 	if (enc)
 		NX_CPB_FDM(csbcpb) |= NX_FDM_ENDE_ENCRYPT;
 	else
 		NX_CPB_FDM(csbcpb) &= ~NX_FDM_ENDE_ENCRYPT;
 
-	rc = nx_build_sg_lists(nx_ctx, desc, dst, src, nbytes,
-			       csbcpb->cpb.aes_cbc.iv);
-	if (rc)
-		goto out;
-
-	if (!nx_ctx->op.inlen || !nx_ctx->op.outlen) {
-		rc = -EINVAL;
-		goto out;
-	}
-
-	rc = nx_hcall_sync(nx_ctx, &nx_ctx->op,
-			   desc->flags & CRYPTO_TFM_REQ_MAY_SLEEP);
-	if (rc)
-		goto out;
-
-	atomic_inc(&(nx_ctx->stats->aes_ops));
-	atomic64_add(csbcpb->csb.processed_byte_count,
-		     &(nx_ctx->stats->aes_bytes));
+	do {
+		to_process = min_t(u64, nbytes - processed,
+				   nx_ctx->ap->databytelen);
+		to_process = min_t(u64, to_process,
+				   NX_PAGE_SIZE * (max_sg_len - 1));
+		to_process = to_process & ~(AES_BLOCK_SIZE - 1);
+
+		rc = nx_build_sg_lists(nx_ctx, desc, dst, src, to_process,
+				       processed, csbcpb->cpb.aes_cbc.iv);
+		if (rc)
+			goto out;
+
+		if (!nx_ctx->op.inlen || !nx_ctx->op.outlen) {
+			rc = -EINVAL;
+			goto out;
+		}
+
+		rc = nx_hcall_sync(nx_ctx, &nx_ctx->op,
+				   desc->flags & CRYPTO_TFM_REQ_MAY_SLEEP);
+		if (rc)
+			goto out;
+
+		memcpy(desc->info, csbcpb->cpb.aes_cbc.cv, AES_BLOCK_SIZE);
+		atomic_inc(&(nx_ctx->stats->aes_ops));
+		atomic64_add(csbcpb->csb.processed_byte_count,
+			     &(nx_ctx->stats->aes_bytes));
+
+		processed += to_process;
+	} while (processed < nbytes);
 out:
+	spin_unlock_irqrestore(&nx_ctx->lock, irq_flags);
 	return rc;
 }
 
diff --git a/drivers/crypto/nx/nx-aes-ccm.c b/drivers/crypto/nx/nx-aes-ccm.c
index ef5eae6d1400..5ecd4c2414aa 100644
--- a/drivers/crypto/nx/nx-aes-ccm.c
+++ b/drivers/crypto/nx/nx-aes-ccm.c
@@ -179,13 +179,26 @@ static int generate_pat(u8                   *iv,
 	struct nx_sg *nx_insg = nx_ctx->in_sg;
 	struct nx_sg *nx_outsg = nx_ctx->out_sg;
 	unsigned int iauth_len = 0;
-	struct vio_pfo_op *op = NULL;
 	u8 tmp[16], *b1 = NULL, *b0 = NULL, *result = NULL;
 	int rc;
 
 	/* zero the ctr value */
 	memset(iv + 15 - iv[0], 0, iv[0] + 1);
 
+	/* page 78 of nx_wb.pdf has,
+	 * Note: RFC3610 allows the AAD data to be up to 2^64 -1 bytes
+	 * in length. If a full message is used, the AES CCA implementation
+	 * restricts the maximum AAD length to 2^32 -1 bytes.
+	 * If partial messages are used, the implementation supports
+	 * 2^64 -1 bytes maximum AAD length.
+	 *
+	 * However, in the cryptoapi's aead_request structure,
+	 * assoclen is an unsigned int, thus it cannot hold a length
+	 * value greater than 2^32 - 1.
+	 * Thus the AAD is further constrained by this and is never
+	 * greater than 2^32.
+	 */
+
 	if (!req->assoclen) {
 		b0 = nx_ctx->csbcpb->cpb.aes_ccm.in_pat_or_b0;
 	} else if (req->assoclen <= 14) {
@@ -195,7 +208,46 @@ static int generate_pat(u8                   *iv,
 		b0 = nx_ctx->csbcpb->cpb.aes_ccm.in_pat_or_b0;
 		b1 = nx_ctx->priv.ccm.iauth_tag;
 		iauth_len = req->assoclen;
+	} else if (req->assoclen <= 65280) {
+		/* if associated data is less than (2^16 - 2^8), we construct
+		 * B1 differently and feed in the associated data to a CCA
+		 * operation */
+		b0 = nx_ctx->csbcpb_aead->cpb.aes_cca.b0;
+		b1 = nx_ctx->csbcpb_aead->cpb.aes_cca.b1;
+		iauth_len = 14;
+	} else {
+		b0 = nx_ctx->csbcpb_aead->cpb.aes_cca.b0;
+		b1 = nx_ctx->csbcpb_aead->cpb.aes_cca.b1;
+		iauth_len = 10;
+	}
+
+	/* generate B0 */
+	rc = generate_b0(iv, req->assoclen, authsize, nbytes, b0);
+	if (rc)
+		return rc;
+
+	/* generate B1:
+	 * add control info for associated data
+	 * RFC 3610 and NIST Special Publication 800-38C
+	 */
+	if (b1) {
+		memset(b1, 0, 16);
+		if (req->assoclen <= 65280) {
+			*(u16 *)b1 = (u16)req->assoclen;
+			scatterwalk_map_and_copy(b1 + 2, req->assoc, 0,
+					 iauth_len, SCATTERWALK_FROM_SG);
+		} else {
+			*(u16 *)b1 = (u16)(0xfffe);
+			*(u32 *)&b1[2] = (u32)req->assoclen;
+			scatterwalk_map_and_copy(b1 + 6, req->assoc, 0,
+					 iauth_len, SCATTERWALK_FROM_SG);
+		}
+	}
 
+	/* now copy any remaining AAD to scatterlist and call nx... */
+	if (!req->assoclen) {
+		return rc;
+	} else if (req->assoclen <= 14) {
 		nx_insg = nx_build_sg_list(nx_insg, b1, 16, nx_ctx->ap->sglen);
 		nx_outsg = nx_build_sg_list(nx_outsg, tmp, 16,
 					    nx_ctx->ap->sglen);
@@ -210,56 +262,74 @@ static int generate_pat(u8                   *iv,
 		NX_CPB_FDM(nx_ctx->csbcpb) |= NX_FDM_ENDE_ENCRYPT;
 		NX_CPB_FDM(nx_ctx->csbcpb) |= NX_FDM_INTERMEDIATE;
 
-		op = &nx_ctx->op;
 		result = nx_ctx->csbcpb->cpb.aes_ccm.out_pat_or_mac;
-	} else if (req->assoclen <= 65280) {
-		/* if associated data is less than (2^16 - 2^8), we construct
-		 * B1 differently and feed in the associated data to a CCA
-		 * operation */
-		b0 = nx_ctx->csbcpb_aead->cpb.aes_cca.b0;
-		b1 = nx_ctx->csbcpb_aead->cpb.aes_cca.b1;
-		iauth_len = 14;
 
-		/* remaining assoc data must have scatterlist built for it */
-		nx_insg = nx_walk_and_build(nx_insg, nx_ctx->ap->sglen,
-					    req->assoc, iauth_len,
-					    req->assoclen - iauth_len);
-		nx_ctx->op_aead.inlen = (nx_ctx->in_sg - nx_insg) *
-						sizeof(struct nx_sg);
+		rc = nx_hcall_sync(nx_ctx, &nx_ctx->op,
+				   req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP);
+		if (rc)
+			return rc;
+
+		atomic_inc(&(nx_ctx->stats->aes_ops));
+		atomic64_add(req->assoclen, &(nx_ctx->stats->aes_bytes));
 
-		op = &nx_ctx->op_aead;
-		result = nx_ctx->csbcpb_aead->cpb.aes_cca.out_pat_or_b0;
 	} else {
-		/* if associated data is less than (2^32), we construct B1
-		 * differently yet again and feed in the associated data to a
-		 * CCA operation */
-		pr_err("associated data len is %u bytes (returning -EINVAL)\n",
-		       req->assoclen);
-		rc = -EINVAL;
-	}
+		u32 max_sg_len;
+		unsigned int processed = 0, to_process;
+
+		/* page_limit: number of sg entries that fit on one page */
+		max_sg_len = min_t(u32,
+				   nx_driver.of.max_sg_len/sizeof(struct nx_sg),
+				   nx_ctx->ap->sglen);
+
+		processed += iauth_len;
+
+		do {
+			to_process = min_t(u32, req->assoclen - processed,
+					   nx_ctx->ap->databytelen);
+			to_process = min_t(u64, to_process,
+					   NX_PAGE_SIZE * (max_sg_len - 1));
+
+			if ((to_process + processed) < req->assoclen) {
+				NX_CPB_FDM(nx_ctx->csbcpb_aead) |=
+					NX_FDM_INTERMEDIATE;
+			} else {
+				NX_CPB_FDM(nx_ctx->csbcpb_aead) &=
+					~NX_FDM_INTERMEDIATE;
+			}
+
+			nx_insg = nx_walk_and_build(nx_ctx->in_sg,
+						    nx_ctx->ap->sglen,
+						    req->assoc, processed,
+						    to_process);
+
+			nx_ctx->op_aead.inlen = (nx_ctx->in_sg - nx_insg) *
+						sizeof(struct nx_sg);
 
-	rc = generate_b0(iv, req->assoclen, authsize, nbytes, b0);
-	if (rc)
-		goto done;
+			result = nx_ctx->csbcpb_aead->cpb.aes_cca.out_pat_or_b0;
 
-	if (b1) {
-		memset(b1, 0, 16);
-		*(u16 *)b1 = (u16)req->assoclen;
+			rc = nx_hcall_sync(nx_ctx, &nx_ctx->op_aead,
+				   req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP);
+			if (rc)
+				return rc;
 
-		scatterwalk_map_and_copy(b1 + 2, req->assoc, 0,
-					 iauth_len, SCATTERWALK_FROM_SG);
+			memcpy(nx_ctx->csbcpb_aead->cpb.aes_cca.b0,
+				nx_ctx->csbcpb_aead->cpb.aes_cca.out_pat_or_b0,
+				AES_BLOCK_SIZE);
 
-		rc = nx_hcall_sync(nx_ctx, op,
-				   req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP);
-		if (rc)
-			goto done;
+			NX_CPB_FDM(nx_ctx->csbcpb_aead) |= NX_FDM_CONTINUATION;
 
-		atomic_inc(&(nx_ctx->stats->aes_ops));
-		atomic64_add(req->assoclen, &(nx_ctx->stats->aes_bytes));
+			atomic_inc(&(nx_ctx->stats->aes_ops));
+			atomic64_add(req->assoclen,
+					&(nx_ctx->stats->aes_bytes));
 
-		memcpy(out, result, AES_BLOCK_SIZE);
+			processed += to_process;
+		} while (processed < req->assoclen);
+
+		result = nx_ctx->csbcpb_aead->cpb.aes_cca.out_pat_or_b0;
 	}
-done:
+
+	memcpy(out, result, AES_BLOCK_SIZE);
+
 	return rc;
 }
 
@@ -271,10 +341,12 @@ static int ccm_nx_decrypt(struct aead_request   *req,
 	unsigned int nbytes = req->cryptlen;
 	unsigned int authsize = crypto_aead_authsize(crypto_aead_reqtfm(req));
 	struct nx_ccm_priv *priv = &nx_ctx->priv.ccm;
+	unsigned long irq_flags;
+	unsigned int processed = 0, to_process;
+	u32 max_sg_len;
 	int rc = -1;
 
-	if (nbytes > nx_ctx->ap->databytelen)
-		return -EINVAL;
+	spin_lock_irqsave(&nx_ctx->lock, irq_flags);
 
 	nbytes -= authsize;
 
@@ -288,26 +360,61 @@ static int ccm_nx_decrypt(struct aead_request   *req,
 	if (rc)
 		goto out;
 
-	rc = nx_build_sg_lists(nx_ctx, desc, req->dst, req->src, nbytes,
-			       csbcpb->cpb.aes_ccm.iv_or_ctr);
-	if (rc)
-		goto out;
+	/* page_limit: number of sg entries that fit on one page */
+	max_sg_len = min_t(u32, nx_driver.of.max_sg_len/sizeof(struct nx_sg),
+			   nx_ctx->ap->sglen);
 
-	NX_CPB_FDM(nx_ctx->csbcpb) &= ~NX_FDM_ENDE_ENCRYPT;
-	NX_CPB_FDM(nx_ctx->csbcpb) &= ~NX_FDM_INTERMEDIATE;
+	do {
+
+		/* to_process: the AES_BLOCK_SIZE data chunk to process in this
+		 * update. This value is bound by sg list limits.
+		 */
+		to_process = min_t(u64, nbytes - processed,
+				   nx_ctx->ap->databytelen);
+		to_process = min_t(u64, to_process,
+				   NX_PAGE_SIZE * (max_sg_len - 1));
+
+		if ((to_process + processed) < nbytes)
+			NX_CPB_FDM(csbcpb) |= NX_FDM_INTERMEDIATE;
+		else
+			NX_CPB_FDM(csbcpb) &= ~NX_FDM_INTERMEDIATE;
+
+		NX_CPB_FDM(nx_ctx->csbcpb) &= ~NX_FDM_ENDE_ENCRYPT;
+
+		rc = nx_build_sg_lists(nx_ctx, desc, req->dst, req->src,
+					to_process, processed,
+					csbcpb->cpb.aes_ccm.iv_or_ctr);
+		if (rc)
+			goto out;
 
-	rc = nx_hcall_sync(nx_ctx, &nx_ctx->op,
+		rc = nx_hcall_sync(nx_ctx, &nx_ctx->op,
 			   req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP);
-	if (rc)
-		goto out;
+		if (rc)
+			goto out;
 
-	atomic_inc(&(nx_ctx->stats->aes_ops));
-	atomic64_add(csbcpb->csb.processed_byte_count,
-		     &(nx_ctx->stats->aes_bytes));
+		/* for partial completion, copy following for next
+		 * entry into loop...
+		 */
+		memcpy(desc->info, csbcpb->cpb.aes_ccm.out_ctr, AES_BLOCK_SIZE);
+		memcpy(csbcpb->cpb.aes_ccm.in_pat_or_b0,
+			csbcpb->cpb.aes_ccm.out_pat_or_mac, AES_BLOCK_SIZE);
+		memcpy(csbcpb->cpb.aes_ccm.in_s0,
+			csbcpb->cpb.aes_ccm.out_s0, AES_BLOCK_SIZE);
+
+		NX_CPB_FDM(csbcpb) |= NX_FDM_CONTINUATION;
+
+		/* update stats */
+		atomic_inc(&(nx_ctx->stats->aes_ops));
+		atomic64_add(csbcpb->csb.processed_byte_count,
+			     &(nx_ctx->stats->aes_bytes));
+
+		processed += to_process;
+	} while (processed < nbytes);
 
 	rc = memcmp(csbcpb->cpb.aes_ccm.out_pat_or_mac, priv->oauth_tag,
 		    authsize) ? -EBADMSG : 0;
 out:
+	spin_unlock_irqrestore(&nx_ctx->lock, irq_flags);
 	return rc;
 }
 
@@ -318,38 +425,76 @@ static int ccm_nx_encrypt(struct aead_request   *req,
 	struct nx_csbcpb *csbcpb = nx_ctx->csbcpb;
 	unsigned int nbytes = req->cryptlen;
 	unsigned int authsize = crypto_aead_authsize(crypto_aead_reqtfm(req));
+	unsigned long irq_flags;
+	unsigned int processed = 0, to_process;
+	u32 max_sg_len;
 	int rc = -1;
 
-	if (nbytes > nx_ctx->ap->databytelen)
-		return -EINVAL;
+	spin_lock_irqsave(&nx_ctx->lock, irq_flags);
 
 	rc = generate_pat(desc->info, req, nx_ctx, authsize, nbytes,
 			  csbcpb->cpb.aes_ccm.in_pat_or_b0);
 	if (rc)
 		goto out;
 
-	rc = nx_build_sg_lists(nx_ctx, desc, req->dst, req->src, nbytes,
-			       csbcpb->cpb.aes_ccm.iv_or_ctr);
-	if (rc)
-		goto out;
+	/* page_limit: number of sg entries that fit on one page */
+	max_sg_len = min_t(u32, nx_driver.of.max_sg_len/sizeof(struct nx_sg),
+			   nx_ctx->ap->sglen);
+
+	do {
+		/* to process: the AES_BLOCK_SIZE data chunk to process in this
+		 * update. This value is bound by sg list limits.
+		 */
+		to_process = min_t(u64, nbytes - processed,
+				   nx_ctx->ap->databytelen);
+		to_process = min_t(u64, to_process,
+				   NX_PAGE_SIZE * (max_sg_len - 1));
+
+		if ((to_process + processed) < nbytes)
+			NX_CPB_FDM(csbcpb) |= NX_FDM_INTERMEDIATE;
+		else
+			NX_CPB_FDM(csbcpb) &= ~NX_FDM_INTERMEDIATE;
+
+		NX_CPB_FDM(csbcpb) |= NX_FDM_ENDE_ENCRYPT;
+
+		rc = nx_build_sg_lists(nx_ctx, desc, req->dst, req->src,
+					to_process, processed,
+				       csbcpb->cpb.aes_ccm.iv_or_ctr);
+		if (rc)
+			goto out;
 
-	NX_CPB_FDM(csbcpb) |= NX_FDM_ENDE_ENCRYPT;
-	NX_CPB_FDM(csbcpb) &= ~NX_FDM_INTERMEDIATE;
+		rc = nx_hcall_sync(nx_ctx, &nx_ctx->op,
+				   req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP);
+		if (rc)
+			goto out;
 
-	rc = nx_hcall_sync(nx_ctx, &nx_ctx->op,
-			   req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP);
-	if (rc)
-		goto out;
+		/* for partial completion, copy following for next
+		 * entry into loop...
+		 */
+		memcpy(desc->info, csbcpb->cpb.aes_ccm.out_ctr, AES_BLOCK_SIZE);
+		memcpy(csbcpb->cpb.aes_ccm.in_pat_or_b0,
+			csbcpb->cpb.aes_ccm.out_pat_or_mac, AES_BLOCK_SIZE);
+		memcpy(csbcpb->cpb.aes_ccm.in_s0,
+			csbcpb->cpb.aes_ccm.out_s0, AES_BLOCK_SIZE);
 
-	atomic_inc(&(nx_ctx->stats->aes_ops));
-	atomic64_add(csbcpb->csb.processed_byte_count,
-		     &(nx_ctx->stats->aes_bytes));
+		NX_CPB_FDM(csbcpb) |= NX_FDM_CONTINUATION;
+
+		/* update stats */
+		atomic_inc(&(nx_ctx->stats->aes_ops));
+		atomic64_add(csbcpb->csb.processed_byte_count,
+			     &(nx_ctx->stats->aes_bytes));
+
+		processed += to_process;
+
+	} while (processed < nbytes);
 
 	/* copy out the auth tag */
 	scatterwalk_map_and_copy(csbcpb->cpb.aes_ccm.out_pat_or_mac,
 				 req->dst, nbytes, authsize,
 				 SCATTERWALK_TO_SG);
+
 out:
+	spin_unlock_irqrestore(&nx_ctx->lock, irq_flags);
 	return rc;
 }
 
diff --git a/drivers/crypto/nx/nx-aes-ctr.c b/drivers/crypto/nx/nx-aes-ctr.c
index b6286f14680b..a37d009dc75c 100644
--- a/drivers/crypto/nx/nx-aes-ctr.c
+++ b/drivers/crypto/nx/nx-aes-ctr.c
@@ -88,30 +88,48 @@ static int ctr_aes_nx_crypt(struct blkcipher_desc *desc,
 {
 	struct nx_crypto_ctx *nx_ctx = crypto_blkcipher_ctx(desc->tfm);
 	struct nx_csbcpb *csbcpb = nx_ctx->csbcpb;
+	unsigned long irq_flags;
+	unsigned int processed = 0, to_process;
+	u32 max_sg_len;
 	int rc;
 
-	if (nbytes > nx_ctx->ap->databytelen)
-		return -EINVAL;
+	spin_lock_irqsave(&nx_ctx->lock, irq_flags);
 
-	rc = nx_build_sg_lists(nx_ctx, desc, dst, src, nbytes,
-			       csbcpb->cpb.aes_ctr.iv);
-	if (rc)
-		goto out;
+	max_sg_len = min_t(u32, nx_driver.of.max_sg_len/sizeof(struct nx_sg),
+			   nx_ctx->ap->sglen);
 
-	if (!nx_ctx->op.inlen || !nx_ctx->op.outlen) {
-		rc = -EINVAL;
-		goto out;
-	}
+	do {
+		to_process = min_t(u64, nbytes - processed,
+				   nx_ctx->ap->databytelen);
+		to_process = min_t(u64, to_process,
+				   NX_PAGE_SIZE * (max_sg_len - 1));
+		to_process = to_process & ~(AES_BLOCK_SIZE - 1);
+
+		rc = nx_build_sg_lists(nx_ctx, desc, dst, src, to_process,
+				       processed, csbcpb->cpb.aes_ctr.iv);
+		if (rc)
+			goto out;
+
+		if (!nx_ctx->op.inlen || !nx_ctx->op.outlen) {
+			rc = -EINVAL;
+			goto out;
+		}
+
+		rc = nx_hcall_sync(nx_ctx, &nx_ctx->op,
+				   desc->flags & CRYPTO_TFM_REQ_MAY_SLEEP);
+		if (rc)
+			goto out;
+
+		memcpy(desc->info, csbcpb->cpb.aes_cbc.cv, AES_BLOCK_SIZE);
 
-	rc = nx_hcall_sync(nx_ctx, &nx_ctx->op,
-			   desc->flags & CRYPTO_TFM_REQ_MAY_SLEEP);
-	if (rc)
-		goto out;
+		atomic_inc(&(nx_ctx->stats->aes_ops));
+		atomic64_add(csbcpb->csb.processed_byte_count,
+			     &(nx_ctx->stats->aes_bytes));
 
-	atomic_inc(&(nx_ctx->stats->aes_ops));
-	atomic64_add(csbcpb->csb.processed_byte_count,
-		     &(nx_ctx->stats->aes_bytes));
+		processed += to_process;
+	} while (processed < nbytes);
 out:
+	spin_unlock_irqrestore(&nx_ctx->lock, irq_flags);
 	return rc;
 }
 
diff --git a/drivers/crypto/nx/nx-aes-ecb.c b/drivers/crypto/nx/nx-aes-ecb.c
index 7bbc9a81da21..85a8d23cf29d 100644
--- a/drivers/crypto/nx/nx-aes-ecb.c
+++ b/drivers/crypto/nx/nx-aes-ecb.c
@@ -70,34 +70,52 @@ static int ecb_aes_nx_crypt(struct blkcipher_desc *desc,
 {
 	struct nx_crypto_ctx *nx_ctx = crypto_blkcipher_ctx(desc->tfm);
 	struct nx_csbcpb *csbcpb = nx_ctx->csbcpb;
+	unsigned long irq_flags;
+	unsigned int processed = 0, to_process;
+	u32 max_sg_len;
 	int rc;
 
-	if (nbytes > nx_ctx->ap->databytelen)
-		return -EINVAL;
+	spin_lock_irqsave(&nx_ctx->lock, irq_flags);
+
+	max_sg_len = min_t(u32, nx_driver.of.max_sg_len/sizeof(struct nx_sg),
+			   nx_ctx->ap->sglen);
 
 	if (enc)
 		NX_CPB_FDM(csbcpb) |= NX_FDM_ENDE_ENCRYPT;
 	else
 		NX_CPB_FDM(csbcpb) &= ~NX_FDM_ENDE_ENCRYPT;
 
-	rc = nx_build_sg_lists(nx_ctx, desc, dst, src, nbytes, NULL);
-	if (rc)
-		goto out;
+	do {
+		to_process = min_t(u64, nbytes - processed,
+				   nx_ctx->ap->databytelen);
+		to_process = min_t(u64, to_process,
+				   NX_PAGE_SIZE * (max_sg_len - 1));
+		to_process = to_process & ~(AES_BLOCK_SIZE - 1);
 
-	if (!nx_ctx->op.inlen || !nx_ctx->op.outlen) {
-		rc = -EINVAL;
-		goto out;
-	}
+		rc = nx_build_sg_lists(nx_ctx, desc, dst, src, to_process,
+				processed, NULL);
+		if (rc)
+			goto out;
+
+		if (!nx_ctx->op.inlen || !nx_ctx->op.outlen) {
+			rc = -EINVAL;
+			goto out;
+		}
+
+		rc = nx_hcall_sync(nx_ctx, &nx_ctx->op,
+				   desc->flags & CRYPTO_TFM_REQ_MAY_SLEEP);
+		if (rc)
+			goto out;
+
+		atomic_inc(&(nx_ctx->stats->aes_ops));
+		atomic64_add(csbcpb->csb.processed_byte_count,
+			     &(nx_ctx->stats->aes_bytes));
 
-	rc = nx_hcall_sync(nx_ctx, &nx_ctx->op,
-			   desc->flags & CRYPTO_TFM_REQ_MAY_SLEEP);
-	if (rc)
-		goto out;
+		processed += to_process;
+	} while (processed < nbytes);
 
-	atomic_inc(&(nx_ctx->stats->aes_ops));
-	atomic64_add(csbcpb->csb.processed_byte_count,
-		     &(nx_ctx->stats->aes_bytes));
 out:
+	spin_unlock_irqrestore(&nx_ctx->lock, irq_flags);
 	return rc;
 }
 
diff --git a/drivers/crypto/nx/nx-aes-gcm.c b/drivers/crypto/nx/nx-aes-gcm.c
index 6cca6c392b00..025d9a8d5b19 100644
--- a/drivers/crypto/nx/nx-aes-gcm.c
+++ b/drivers/crypto/nx/nx-aes-gcm.c
@@ -125,38 +125,187 @@ static int nx_gca(struct nx_crypto_ctx  *nx_ctx,
 		  struct aead_request   *req,
 		  u8                    *out)
 {
+	int rc;
 	struct nx_csbcpb *csbcpb_aead = nx_ctx->csbcpb_aead;
-	int rc = -EINVAL;
 	struct scatter_walk walk;
 	struct nx_sg *nx_sg = nx_ctx->in_sg;
+	unsigned int nbytes = req->assoclen;
+	unsigned int processed = 0, to_process;
+	u32 max_sg_len;
 
-	if (req->assoclen > nx_ctx->ap->databytelen)
-		goto out;
-
-	if (req->assoclen <= AES_BLOCK_SIZE) {
+	if (nbytes <= AES_BLOCK_SIZE) {
 		scatterwalk_start(&walk, req->assoc);
-		scatterwalk_copychunks(out, &walk, req->assoclen,
-				       SCATTERWALK_FROM_SG);
+		scatterwalk_copychunks(out, &walk, nbytes, SCATTERWALK_FROM_SG);
 		scatterwalk_done(&walk, SCATTERWALK_FROM_SG, 0);
-
-		rc = 0;
-		goto out;
+		return 0;
 	}
 
-	nx_sg = nx_walk_and_build(nx_sg, nx_ctx->ap->sglen, req->assoc, 0,
-				  req->assoclen);
-	nx_ctx->op_aead.inlen = (nx_ctx->in_sg - nx_sg) * sizeof(struct nx_sg);
+	NX_CPB_FDM(csbcpb_aead) &= ~NX_FDM_CONTINUATION;
+
+	/* page_limit: number of sg entries that fit on one page */
+	max_sg_len = min_t(u32, nx_driver.of.max_sg_len/sizeof(struct nx_sg),
+			   nx_ctx->ap->sglen);
+
+	do {
+		/*
+		 * to_process: the data chunk to process in this update.
+		 * This value is bound by sg list limits.
+		 */
+		to_process = min_t(u64, nbytes - processed,
+				   nx_ctx->ap->databytelen);
+		to_process = min_t(u64, to_process,
+				   NX_PAGE_SIZE * (max_sg_len - 1));
+
+		if ((to_process + processed) < nbytes)
+			NX_CPB_FDM(csbcpb_aead) |= NX_FDM_INTERMEDIATE;
+		else
+			NX_CPB_FDM(csbcpb_aead) &= ~NX_FDM_INTERMEDIATE;
+
+		nx_sg = nx_walk_and_build(nx_ctx->in_sg, nx_ctx->ap->sglen,
+					  req->assoc, processed, to_process);
+		nx_ctx->op_aead.inlen = (nx_ctx->in_sg - nx_sg)
+					* sizeof(struct nx_sg);
+
+		rc = nx_hcall_sync(nx_ctx, &nx_ctx->op_aead,
+				req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP);
+		if (rc)
+			return rc;
+
+		memcpy(csbcpb_aead->cpb.aes_gca.in_pat,
+				csbcpb_aead->cpb.aes_gca.out_pat,
+				AES_BLOCK_SIZE);
+		NX_CPB_FDM(csbcpb_aead) |= NX_FDM_CONTINUATION;
+
+		atomic_inc(&(nx_ctx->stats->aes_ops));
+		atomic64_add(req->assoclen, &(nx_ctx->stats->aes_bytes));
+
+		processed += to_process;
+	} while (processed < nbytes);
+
+	memcpy(out, csbcpb_aead->cpb.aes_gca.out_pat, AES_BLOCK_SIZE);
+
+	return rc;
+}
+
+static int gmac(struct aead_request *req, struct blkcipher_desc *desc)
+{
+	int rc;
+	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(req->base.tfm);
+	struct nx_csbcpb *csbcpb = nx_ctx->csbcpb;
+	struct nx_sg *nx_sg;
+	unsigned int nbytes = req->assoclen;
+	unsigned int processed = 0, to_process;
+	u32 max_sg_len;
+
+	/* Set GMAC mode */
+	csbcpb->cpb.hdr.mode = NX_MODE_AES_GMAC;
+
+	NX_CPB_FDM(csbcpb) &= ~NX_FDM_CONTINUATION;
+
+	/* page_limit: number of sg entries that fit on one page */
+	max_sg_len = min_t(u32, nx_driver.of.max_sg_len/sizeof(struct nx_sg),
+			   nx_ctx->ap->sglen);
+
+	/* Copy IV */
+	memcpy(csbcpb->cpb.aes_gcm.iv_or_cnt, desc->info, AES_BLOCK_SIZE);
+
+	do {
+		/*
+		 * to_process: the data chunk to process in this update.
+		 * This value is bound by sg list limits.
+		 */
+		to_process = min_t(u64, nbytes - processed,
+				   nx_ctx->ap->databytelen);
+		to_process = min_t(u64, to_process,
+				   NX_PAGE_SIZE * (max_sg_len - 1));
+
+		if ((to_process + processed) < nbytes)
+			NX_CPB_FDM(csbcpb) |= NX_FDM_INTERMEDIATE;
+		else
+			NX_CPB_FDM(csbcpb) &= ~NX_FDM_INTERMEDIATE;
+
+		nx_sg = nx_walk_and_build(nx_ctx->in_sg, nx_ctx->ap->sglen,
+					  req->assoc, processed, to_process);
+		nx_ctx->op.inlen = (nx_ctx->in_sg - nx_sg)
+					* sizeof(struct nx_sg);
+
+		csbcpb->cpb.aes_gcm.bit_length_data = 0;
+		csbcpb->cpb.aes_gcm.bit_length_aad = 8 * nbytes;
+
+		rc = nx_hcall_sync(nx_ctx, &nx_ctx->op,
+				req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP);
+		if (rc)
+			goto out;
+
+		memcpy(csbcpb->cpb.aes_gcm.in_pat_or_aad,
+			csbcpb->cpb.aes_gcm.out_pat_or_mac, AES_BLOCK_SIZE);
+		memcpy(csbcpb->cpb.aes_gcm.in_s0,
+			csbcpb->cpb.aes_gcm.out_s0, AES_BLOCK_SIZE);
+
+		NX_CPB_FDM(csbcpb) |= NX_FDM_CONTINUATION;
+
+		atomic_inc(&(nx_ctx->stats->aes_ops));
+		atomic64_add(req->assoclen, &(nx_ctx->stats->aes_bytes));
+
+		processed += to_process;
+	} while (processed < nbytes);
+
+out:
+	/* Restore GCM mode */
+	csbcpb->cpb.hdr.mode = NX_MODE_AES_GCM;
+	return rc;
+}
+
+static int gcm_empty(struct aead_request *req, struct blkcipher_desc *desc,
+		     int enc)
+{
+	int rc;
+	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(req->base.tfm);
+	struct nx_csbcpb *csbcpb = nx_ctx->csbcpb;
+	char out[AES_BLOCK_SIZE];
+	struct nx_sg *in_sg, *out_sg;
+
+	/* For scenarios where the input message is zero length, AES CTR mode
+	 * may be used. Set the source data to be a single block (16B) of all
+	 * zeros, and set the input IV value to be the same as the GMAC IV
+	 * value. - nx_wb 4.8.1.3 */
+
+	/* Change to ECB mode */
+	csbcpb->cpb.hdr.mode = NX_MODE_AES_ECB;
+	memcpy(csbcpb->cpb.aes_ecb.key, csbcpb->cpb.aes_gcm.key,
+			sizeof(csbcpb->cpb.aes_ecb.key));
+	if (enc)
+		NX_CPB_FDM(csbcpb) |= NX_FDM_ENDE_ENCRYPT;
+	else
+		NX_CPB_FDM(csbcpb) &= ~NX_FDM_ENDE_ENCRYPT;
+
+	/* Encrypt the counter/IV */
+	in_sg = nx_build_sg_list(nx_ctx->in_sg, (u8 *) desc->info,
+				 AES_BLOCK_SIZE, nx_ctx->ap->sglen);
+	out_sg = nx_build_sg_list(nx_ctx->out_sg, (u8 *) out, sizeof(out),
+				  nx_ctx->ap->sglen);
+	nx_ctx->op.inlen = (nx_ctx->in_sg - in_sg) * sizeof(struct nx_sg);
+	nx_ctx->op.outlen = (nx_ctx->out_sg - out_sg) * sizeof(struct nx_sg);
 
-	rc = nx_hcall_sync(nx_ctx, &nx_ctx->op_aead,
-			   req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP);
+	rc = nx_hcall_sync(nx_ctx, &nx_ctx->op,
+			   desc->flags & CRYPTO_TFM_REQ_MAY_SLEEP);
 	if (rc)
 		goto out;
-
 	atomic_inc(&(nx_ctx->stats->aes_ops));
-	atomic64_add(req->assoclen, &(nx_ctx->stats->aes_bytes));
 
-	memcpy(out, csbcpb_aead->cpb.aes_gca.out_pat, AES_BLOCK_SIZE);
+	/* Copy out the auth tag */
+	memcpy(csbcpb->cpb.aes_gcm.out_pat_or_mac, out,
+			crypto_aead_authsize(crypto_aead_reqtfm(req)));
 out:
+	/* Restore XCBC mode */
+	csbcpb->cpb.hdr.mode = NX_MODE_AES_GCM;
+
+	/*
+	 * ECB key uses the same region that GCM AAD and counter, so it's safe
+	 * to just fill it with zeroes.
+	 */
+	memset(csbcpb->cpb.aes_ecb.key, 0, sizeof(csbcpb->cpb.aes_ecb.key));
+
 	return rc;
 }
 
@@ -166,88 +315,104 @@ static int gcm_aes_nx_crypt(struct aead_request *req, int enc)
 	struct nx_csbcpb *csbcpb = nx_ctx->csbcpb;
 	struct blkcipher_desc desc;
 	unsigned int nbytes = req->cryptlen;
+	unsigned int processed = 0, to_process;
+	unsigned long irq_flags;
+	u32 max_sg_len;
 	int rc = -EINVAL;
 
-	if (nbytes > nx_ctx->ap->databytelen)
-		goto out;
+	spin_lock_irqsave(&nx_ctx->lock, irq_flags);
 
 	desc.info = nx_ctx->priv.gcm.iv;
 	/* initialize the counter */
 	*(u32 *)(desc.info + NX_GCM_CTR_OFFSET) = 1;
 
-	/* For scenarios where the input message is zero length, AES CTR mode
-	 * may be used. Set the source data to be a single block (16B) of all
-	 * zeros, and set the input IV value to be the same as the GMAC IV
-	 * value. - nx_wb 4.8.1.3 */
 	if (nbytes == 0) {
-		char src[AES_BLOCK_SIZE] = {};
-		struct scatterlist sg;
-
-		desc.tfm = crypto_alloc_blkcipher("ctr(aes)", 0, 0);
-		if (IS_ERR(desc.tfm)) {
-			rc = -ENOMEM;
+		if (req->assoclen == 0)
+			rc = gcm_empty(req, &desc, enc);
+		else
+			rc = gmac(req, &desc);
+		if (rc)
 			goto out;
-		}
-
-		crypto_blkcipher_setkey(desc.tfm, csbcpb->cpb.aes_gcm.key,
-			NX_CPB_KEY_SIZE(csbcpb) == NX_KS_AES_128 ? 16 :
-			NX_CPB_KEY_SIZE(csbcpb) == NX_KS_AES_192 ? 24 : 32);
-
-		sg_init_one(&sg, src, AES_BLOCK_SIZE);
-		if (enc)
-			crypto_blkcipher_encrypt_iv(&desc, req->dst, &sg,
-						    AES_BLOCK_SIZE);
 		else
-			crypto_blkcipher_decrypt_iv(&desc, req->dst, &sg,
-						    AES_BLOCK_SIZE);
-		crypto_free_blkcipher(desc.tfm);
-
-		rc = 0;
-		goto out;
+			goto mac;
 	}
 
-	desc.tfm = (struct crypto_blkcipher *)req->base.tfm;
-
+	/* Process associated data */
 	csbcpb->cpb.aes_gcm.bit_length_aad = req->assoclen * 8;
-
 	if (req->assoclen) {
 		rc = nx_gca(nx_ctx, req, csbcpb->cpb.aes_gcm.in_pat_or_aad);
 		if (rc)
 			goto out;
 	}
 
-	if (enc)
+	/* Set flags for encryption */
+	NX_CPB_FDM(csbcpb) &= ~NX_FDM_CONTINUATION;
+	if (enc) {
 		NX_CPB_FDM(csbcpb) |= NX_FDM_ENDE_ENCRYPT;
-	else
+	} else {
+		NX_CPB_FDM(csbcpb) &= ~NX_FDM_ENDE_ENCRYPT;
 		nbytes -= crypto_aead_authsize(crypto_aead_reqtfm(req));
+	}
 
-	csbcpb->cpb.aes_gcm.bit_length_data = nbytes * 8;
+	/* page_limit: number of sg entries that fit on one page */
+	max_sg_len = min_t(u32, nx_driver.of.max_sg_len/sizeof(struct nx_sg),
+			   nx_ctx->ap->sglen);
+
+	do {
+		/*
+		 * to_process: the data chunk to process in this update.
+		 * This value is bound by sg list limits.
+		 */
+		to_process = min_t(u64, nbytes - processed,
+				   nx_ctx->ap->databytelen);
+		to_process = min_t(u64, to_process,
+				   NX_PAGE_SIZE * (max_sg_len - 1));
+
+		if ((to_process + processed) < nbytes)
+			NX_CPB_FDM(csbcpb) |= NX_FDM_INTERMEDIATE;
+		else
+			NX_CPB_FDM(csbcpb) &= ~NX_FDM_INTERMEDIATE;
 
-	rc = nx_build_sg_lists(nx_ctx, &desc, req->dst, req->src, nbytes,
-			       csbcpb->cpb.aes_gcm.iv_or_cnt);
-	if (rc)
-		goto out;
+		csbcpb->cpb.aes_gcm.bit_length_data = nbytes * 8;
+		desc.tfm = (struct crypto_blkcipher *) req->base.tfm;
+		rc = nx_build_sg_lists(nx_ctx, &desc, req->dst,
+				       req->src, to_process, processed,
+				       csbcpb->cpb.aes_gcm.iv_or_cnt);
+		if (rc)
+			goto out;
 
-	rc = nx_hcall_sync(nx_ctx, &nx_ctx->op,
-			   req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP);
-	if (rc)
-		goto out;
+		rc = nx_hcall_sync(nx_ctx, &nx_ctx->op,
+				   req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP);
+		if (rc)
+			goto out;
 
-	atomic_inc(&(nx_ctx->stats->aes_ops));
-	atomic64_add(csbcpb->csb.processed_byte_count,
-		     &(nx_ctx->stats->aes_bytes));
+		memcpy(desc.info, csbcpb->cpb.aes_gcm.out_cnt, AES_BLOCK_SIZE);
+		memcpy(csbcpb->cpb.aes_gcm.in_pat_or_aad,
+			csbcpb->cpb.aes_gcm.out_pat_or_mac, AES_BLOCK_SIZE);
+		memcpy(csbcpb->cpb.aes_gcm.in_s0,
+			csbcpb->cpb.aes_gcm.out_s0, AES_BLOCK_SIZE);
+
+		NX_CPB_FDM(csbcpb) |= NX_FDM_CONTINUATION;
+
+		atomic_inc(&(nx_ctx->stats->aes_ops));
+		atomic64_add(csbcpb->csb.processed_byte_count,
+			     &(nx_ctx->stats->aes_bytes));
+
+		processed += to_process;
+	} while (processed < nbytes);
 
+mac:
 	if (enc) {
 		/* copy out the auth tag */
 		scatterwalk_map_and_copy(csbcpb->cpb.aes_gcm.out_pat_or_mac,
 				 req->dst, nbytes,
 				 crypto_aead_authsize(crypto_aead_reqtfm(req)),
 				 SCATTERWALK_TO_SG);
-	} else if (req->assoclen) {
+	} else {
 		u8 *itag = nx_ctx->priv.gcm.iauth_tag;
 		u8 *otag = csbcpb->cpb.aes_gcm.out_pat_or_mac;
 
-		scatterwalk_map_and_copy(itag, req->dst, nbytes,
+		scatterwalk_map_and_copy(itag, req->src, nbytes,
 				 crypto_aead_authsize(crypto_aead_reqtfm(req)),
 				 SCATTERWALK_FROM_SG);
 		rc = memcmp(itag, otag,
@@ -255,6 +420,7 @@ static int gcm_aes_nx_crypt(struct aead_request *req, int enc)
 		     -EBADMSG : 0;
 	}
 out:
+	spin_unlock_irqrestore(&nx_ctx->lock, irq_flags);
 	return rc;
 }
 
diff --git a/drivers/crypto/nx/nx-aes-xcbc.c b/drivers/crypto/nx/nx-aes-xcbc.c
index 93923e4628c0..03c4bf57d066 100644
--- a/drivers/crypto/nx/nx-aes-xcbc.c
+++ b/drivers/crypto/nx/nx-aes-xcbc.c
@@ -56,6 +56,77 @@ static int nx_xcbc_set_key(struct crypto_shash *desc,
 	return 0;
 }
 
+/*
+ * Based on RFC 3566, for a zero-length message:
+ *
+ * n = 1
+ * K1 = E(K, 0x01010101010101010101010101010101)
+ * K3 = E(K, 0x03030303030303030303030303030303)
+ * E[0] = 0x00000000000000000000000000000000
+ * M[1] = 0x80000000000000000000000000000000 (0 length message with padding)
+ * E[1] = (K1, M[1] ^ E[0] ^ K3)
+ * Tag = M[1]
+ */
+static int nx_xcbc_empty(struct shash_desc *desc, u8 *out)
+{
+	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(&desc->tfm->base);
+	struct nx_csbcpb *csbcpb = nx_ctx->csbcpb;
+	struct nx_sg *in_sg, *out_sg;
+	u8 keys[2][AES_BLOCK_SIZE];
+	u8 key[32];
+	int rc = 0;
+
+	/* Change to ECB mode */
+	csbcpb->cpb.hdr.mode = NX_MODE_AES_ECB;
+	memcpy(key, csbcpb->cpb.aes_xcbc.key, AES_BLOCK_SIZE);
+	memcpy(csbcpb->cpb.aes_ecb.key, key, AES_BLOCK_SIZE);
+	NX_CPB_FDM(csbcpb) |= NX_FDM_ENDE_ENCRYPT;
+
+	/* K1 and K3 base patterns */
+	memset(keys[0], 0x01, sizeof(keys[0]));
+	memset(keys[1], 0x03, sizeof(keys[1]));
+
+	/* Generate K1 and K3 encrypting the patterns */
+	in_sg = nx_build_sg_list(nx_ctx->in_sg, (u8 *) keys, sizeof(keys),
+				 nx_ctx->ap->sglen);
+	out_sg = nx_build_sg_list(nx_ctx->out_sg, (u8 *) keys, sizeof(keys),
+				  nx_ctx->ap->sglen);
+	nx_ctx->op.inlen = (nx_ctx->in_sg - in_sg) * sizeof(struct nx_sg);
+	nx_ctx->op.outlen = (nx_ctx->out_sg - out_sg) * sizeof(struct nx_sg);
+
+	rc = nx_hcall_sync(nx_ctx, &nx_ctx->op,
+			   desc->flags & CRYPTO_TFM_REQ_MAY_SLEEP);
+	if (rc)
+		goto out;
+	atomic_inc(&(nx_ctx->stats->aes_ops));
+
+	/* XOr K3 with the padding for a 0 length message */
+	keys[1][0] ^= 0x80;
+
+	/* Encrypt the final result */
+	memcpy(csbcpb->cpb.aes_ecb.key, keys[0], AES_BLOCK_SIZE);
+	in_sg = nx_build_sg_list(nx_ctx->in_sg, (u8 *) keys[1], sizeof(keys[1]),
+				 nx_ctx->ap->sglen);
+	out_sg = nx_build_sg_list(nx_ctx->out_sg, out, AES_BLOCK_SIZE,
+				  nx_ctx->ap->sglen);
+	nx_ctx->op.inlen = (nx_ctx->in_sg - in_sg) * sizeof(struct nx_sg);
+	nx_ctx->op.outlen = (nx_ctx->out_sg - out_sg) * sizeof(struct nx_sg);
+
+	rc = nx_hcall_sync(nx_ctx, &nx_ctx->op,
+			   desc->flags & CRYPTO_TFM_REQ_MAY_SLEEP);
+	if (rc)
+		goto out;
+	atomic_inc(&(nx_ctx->stats->aes_ops));
+
+out:
+	/* Restore XCBC mode */
+	csbcpb->cpb.hdr.mode = NX_MODE_AES_XCBC_MAC;
+	memcpy(csbcpb->cpb.aes_xcbc.key, key, AES_BLOCK_SIZE);
+	NX_CPB_FDM(csbcpb) &= ~NX_FDM_ENDE_ENCRYPT;
+
+	return rc;
+}
+
 static int nx_xcbc_init(struct shash_desc *desc)
 {
 	struct xcbc_state *sctx = shash_desc_ctx(desc);
@@ -88,76 +159,99 @@ static int nx_xcbc_update(struct shash_desc *desc,
 	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(&desc->tfm->base);
 	struct nx_csbcpb *csbcpb = nx_ctx->csbcpb;
 	struct nx_sg *in_sg;
-	u32 to_process, leftover;
+	u32 to_process, leftover, total;
+	u32 max_sg_len;
+	unsigned long irq_flags;
 	int rc = 0;
 
-	if (NX_CPB_FDM(csbcpb) & NX_FDM_CONTINUATION) {
-		/* we've hit the nx chip previously and we're updating again,
-		 * so copy over the partial digest */
-		memcpy(csbcpb->cpb.aes_xcbc.cv,
-		       csbcpb->cpb.aes_xcbc.out_cv_mac, AES_BLOCK_SIZE);
-	}
+	spin_lock_irqsave(&nx_ctx->lock, irq_flags);
+
+
+	total = sctx->count + len;
 
 	/* 2 cases for total data len:
 	 *  1: <= AES_BLOCK_SIZE: copy into state, return 0
 	 *  2: > AES_BLOCK_SIZE: process X blocks, copy in leftover
 	 */
-	if (len + sctx->count <= AES_BLOCK_SIZE) {
+	if (total <= AES_BLOCK_SIZE) {
 		memcpy(sctx->buffer + sctx->count, data, len);
 		sctx->count += len;
 		goto out;
 	}
 
-	/* to_process: the AES_BLOCK_SIZE data chunk to process in this
-	 * update */
-	to_process = (sctx->count + len) & ~(AES_BLOCK_SIZE - 1);
-	leftover = (sctx->count + len) & (AES_BLOCK_SIZE - 1);
-
-	/* the hardware will not accept a 0 byte operation for this algorithm
-	 * and the operation MUST be finalized to be correct. So if we happen
-	 * to get an update that falls on a block sized boundary, we must
-	 * save off the last block to finalize with later. */
-	if (!leftover) {
-		to_process -= AES_BLOCK_SIZE;
-		leftover = AES_BLOCK_SIZE;
-	}
-
-	if (sctx->count) {
-		in_sg = nx_build_sg_list(nx_ctx->in_sg, sctx->buffer,
-					 sctx->count, nx_ctx->ap->sglen);
-		in_sg = nx_build_sg_list(in_sg, (u8 *)data,
-					 to_process - sctx->count,
-					 nx_ctx->ap->sglen);
+	in_sg = nx_ctx->in_sg;
+	max_sg_len = min_t(u32, nx_driver.of.max_sg_len/sizeof(struct nx_sg),
+				nx_ctx->ap->sglen);
+
+	do {
+
+		/* to_process: the AES_BLOCK_SIZE data chunk to process in this
+		 * update */
+		to_process = min_t(u64, total, nx_ctx->ap->databytelen);
+		to_process = min_t(u64, to_process,
+					NX_PAGE_SIZE * (max_sg_len - 1));
+		to_process = to_process & ~(AES_BLOCK_SIZE - 1);
+		leftover = total - to_process;
+
+		/* the hardware will not accept a 0 byte operation for this
+		 * algorithm and the operation MUST be finalized to be correct.
+		 * So if we happen to get an update that falls on a block sized
+		 * boundary, we must save off the last block to finalize with
+		 * later. */
+		if (!leftover) {
+			to_process -= AES_BLOCK_SIZE;
+			leftover = AES_BLOCK_SIZE;
+		}
+
+		if (sctx->count) {
+			in_sg = nx_build_sg_list(nx_ctx->in_sg,
+						(u8 *) sctx->buffer,
+						sctx->count,
+						max_sg_len);
+		}
+		in_sg = nx_build_sg_list(in_sg,
+					(u8 *) data,
+					to_process - sctx->count,
+					max_sg_len);
 		nx_ctx->op.inlen = (nx_ctx->in_sg - in_sg) *
 					sizeof(struct nx_sg);
-	} else {
-		in_sg = nx_build_sg_list(nx_ctx->in_sg, (u8 *)data, to_process,
-					 nx_ctx->ap->sglen);
-		nx_ctx->op.inlen = (nx_ctx->in_sg - in_sg) *
-					sizeof(struct nx_sg);
-	}
 
-	NX_CPB_FDM(csbcpb) |= NX_FDM_INTERMEDIATE;
+		/* we've hit the nx chip previously and we're updating again,
+		 * so copy over the partial digest */
+		if (NX_CPB_FDM(csbcpb) & NX_FDM_CONTINUATION) {
+			memcpy(csbcpb->cpb.aes_xcbc.cv,
+				csbcpb->cpb.aes_xcbc.out_cv_mac,
+				AES_BLOCK_SIZE);
+		}
+
+		NX_CPB_FDM(csbcpb) |= NX_FDM_INTERMEDIATE;
+		if (!nx_ctx->op.inlen || !nx_ctx->op.outlen) {
+			rc = -EINVAL;
+			goto out;
+		}
+
+		rc = nx_hcall_sync(nx_ctx, &nx_ctx->op,
+			   desc->flags & CRYPTO_TFM_REQ_MAY_SLEEP);
+		if (rc)
+			goto out;
 
-	if (!nx_ctx->op.inlen || !nx_ctx->op.outlen) {
-		rc = -EINVAL;
-		goto out;
-	}
+		atomic_inc(&(nx_ctx->stats->aes_ops));
 
-	rc = nx_hcall_sync(nx_ctx, &nx_ctx->op,
-			   desc->flags & CRYPTO_TFM_REQ_MAY_SLEEP);
-	if (rc)
-		goto out;
+		/* everything after the first update is continuation */
+		NX_CPB_FDM(csbcpb) |= NX_FDM_CONTINUATION;
 
-	atomic_inc(&(nx_ctx->stats->aes_ops));
+		total -= to_process;
+		data += to_process - sctx->count;
+		sctx->count = 0;
+		in_sg = nx_ctx->in_sg;
+	} while (leftover > AES_BLOCK_SIZE);
 
 	/* copy the leftover back into the state struct */
-	memcpy(sctx->buffer, data + len - leftover, leftover);
+	memcpy(sctx->buffer, data, leftover);
 	sctx->count = leftover;
 
-	/* everything after the first update is continuation */
-	NX_CPB_FDM(csbcpb) |= NX_FDM_CONTINUATION;
 out:
+	spin_unlock_irqrestore(&nx_ctx->lock, irq_flags);
 	return rc;
 }
 
@@ -167,21 +261,23 @@ static int nx_xcbc_final(struct shash_desc *desc, u8 *out)
 	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(&desc->tfm->base);
 	struct nx_csbcpb *csbcpb = nx_ctx->csbcpb;
 	struct nx_sg *in_sg, *out_sg;
+	unsigned long irq_flags;
 	int rc = 0;
 
+	spin_lock_irqsave(&nx_ctx->lock, irq_flags);
+
 	if (NX_CPB_FDM(csbcpb) & NX_FDM_CONTINUATION) {
 		/* we've hit the nx chip previously, now we're finalizing,
 		 * so copy over the partial digest */
 		memcpy(csbcpb->cpb.aes_xcbc.cv,
 		       csbcpb->cpb.aes_xcbc.out_cv_mac, AES_BLOCK_SIZE);
 	} else if (sctx->count == 0) {
-		/* we've never seen an update, so this is a 0 byte op. The
-		 * hardware cannot handle a 0 byte op, so just copy out the
-		 * known 0 byte result. This is cheaper than allocating a
-		 * software context to do a 0 byte op */
-		u8 data[] = { 0x75, 0xf0, 0x25, 0x1d, 0x52, 0x8a, 0xc0, 0x1c,
-			      0x45, 0x73, 0xdf, 0xd5, 0x84, 0xd7, 0x9f, 0x29 };
-		memcpy(out, data, sizeof(data));
+		/*
+		 * we've never seen an update, so this is a 0 byte op. The
+		 * hardware cannot handle a 0 byte op, so just ECB to
+		 * generate the hash.
+		 */
+		rc = nx_xcbc_empty(desc, out);
 		goto out;
 	}
 
@@ -211,6 +307,7 @@ static int nx_xcbc_final(struct shash_desc *desc, u8 *out)
 
 	memcpy(out, csbcpb->cpb.aes_xcbc.out_cv_mac, AES_BLOCK_SIZE);
 out:
+	spin_unlock_irqrestore(&nx_ctx->lock, irq_flags);
 	return rc;
 }
 
diff --git a/drivers/crypto/nx/nx-sha256.c b/drivers/crypto/nx/nx-sha256.c
index 67024f2f0b78..da0b24a7633f 100644
--- a/drivers/crypto/nx/nx-sha256.c
+++ b/drivers/crypto/nx/nx-sha256.c
@@ -55,71 +55,91 @@ static int nx_sha256_update(struct shash_desc *desc, const u8 *data,
 	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(&desc->tfm->base);
 	struct nx_csbcpb *csbcpb = (struct nx_csbcpb *)nx_ctx->csbcpb;
 	struct nx_sg *in_sg;
-	u64 to_process, leftover;
+	u64 to_process, leftover, total;
+	u32 max_sg_len;
+	unsigned long irq_flags;
 	int rc = 0;
 
-	if (NX_CPB_FDM(csbcpb) & NX_FDM_CONTINUATION) {
-		/* we've hit the nx chip previously and we're updating again,
-		 * so copy over the partial digest */
-		memcpy(csbcpb->cpb.sha256.input_partial_digest,
-		       csbcpb->cpb.sha256.message_digest, SHA256_DIGEST_SIZE);
-	}
+	spin_lock_irqsave(&nx_ctx->lock, irq_flags);
 
 	/* 2 cases for total data len:
-	 *  1: <= SHA256_BLOCK_SIZE: copy into state, return 0
-	 *  2: > SHA256_BLOCK_SIZE: process X blocks, copy in leftover
+	 *  1: < SHA256_BLOCK_SIZE: copy into state, return 0
+	 *  2: >= SHA256_BLOCK_SIZE: process X blocks, copy in leftover
 	 */
-	if (len + sctx->count < SHA256_BLOCK_SIZE) {
+	total = sctx->count + len;
+	if (total < SHA256_BLOCK_SIZE) {
 		memcpy(sctx->buf + sctx->count, data, len);
 		sctx->count += len;
 		goto out;
 	}
 
-	/* to_process: the SHA256_BLOCK_SIZE data chunk to process in this
-	 * update */
-	to_process = (sctx->count + len) & ~(SHA256_BLOCK_SIZE - 1);
-	leftover = (sctx->count + len) & (SHA256_BLOCK_SIZE - 1);
-
-	if (sctx->count) {
-		in_sg = nx_build_sg_list(nx_ctx->in_sg, (u8 *)sctx->buf,
-					 sctx->count, nx_ctx->ap->sglen);
-		in_sg = nx_build_sg_list(in_sg, (u8 *)data,
+	in_sg = nx_ctx->in_sg;
+	max_sg_len = min_t(u32, nx_driver.of.max_sg_len/sizeof(struct nx_sg),
+			   nx_ctx->ap->sglen);
+
+	do {
+		/*
+		 * to_process: the SHA256_BLOCK_SIZE data chunk to process in
+		 * this update. This value is also restricted by the sg list
+		 * limits.
+		 */
+		to_process = min_t(u64, total, nx_ctx->ap->databytelen);
+		to_process = min_t(u64, to_process,
+				   NX_PAGE_SIZE * (max_sg_len - 1));
+		to_process = to_process & ~(SHA256_BLOCK_SIZE - 1);
+		leftover = total - to_process;
+
+		if (sctx->count) {
+			in_sg = nx_build_sg_list(nx_ctx->in_sg,
+						 (u8 *) sctx->buf,
+						 sctx->count, max_sg_len);
+		}
+		in_sg = nx_build_sg_list(in_sg, (u8 *) data,
 					 to_process - sctx->count,
-					 nx_ctx->ap->sglen);
+					 max_sg_len);
 		nx_ctx->op.inlen = (nx_ctx->in_sg - in_sg) *
 					sizeof(struct nx_sg);
-	} else {
-		in_sg = nx_build_sg_list(nx_ctx->in_sg, (u8 *)data,
-					 to_process, nx_ctx->ap->sglen);
-		nx_ctx->op.inlen = (nx_ctx->in_sg - in_sg) *
-					sizeof(struct nx_sg);
-	}
 
-	NX_CPB_FDM(csbcpb) |= NX_FDM_INTERMEDIATE;
+		if (NX_CPB_FDM(csbcpb) & NX_FDM_CONTINUATION) {
+			/*
+			 * we've hit the nx chip previously and we're updating
+			 * again, so copy over the partial digest.
+			 */
+			memcpy(csbcpb->cpb.sha256.input_partial_digest,
+			       csbcpb->cpb.sha256.message_digest,
+			       SHA256_DIGEST_SIZE);
+		}
 
-	if (!nx_ctx->op.inlen || !nx_ctx->op.outlen) {
-		rc = -EINVAL;
-		goto out;
-	}
+		NX_CPB_FDM(csbcpb) |= NX_FDM_INTERMEDIATE;
+		if (!nx_ctx->op.inlen || !nx_ctx->op.outlen) {
+			rc = -EINVAL;
+			goto out;
+		}
 
-	rc = nx_hcall_sync(nx_ctx, &nx_ctx->op,
-			   desc->flags & CRYPTO_TFM_REQ_MAY_SLEEP);
-	if (rc)
-		goto out;
+		rc = nx_hcall_sync(nx_ctx, &nx_ctx->op,
+				   desc->flags & CRYPTO_TFM_REQ_MAY_SLEEP);
+		if (rc)
+			goto out;
 
-	atomic_inc(&(nx_ctx->stats->sha256_ops));
+		atomic_inc(&(nx_ctx->stats->sha256_ops));
+		csbcpb->cpb.sha256.message_bit_length += (u64)
+			(csbcpb->cpb.sha256.spbc * 8);
+
+		/* everything after the first update is continuation */
+		NX_CPB_FDM(csbcpb) |= NX_FDM_CONTINUATION;
+
+		total -= to_process;
+		data += to_process - sctx->count;
+		sctx->count = 0;
+		in_sg = nx_ctx->in_sg;
+	} while (leftover >= SHA256_BLOCK_SIZE);
 
 	/* copy the leftover back into the state struct */
 	if (leftover)
-		memcpy(sctx->buf, data + len - leftover, leftover);
+		memcpy(sctx->buf, data, leftover);
 	sctx->count = leftover;
-
-	csbcpb->cpb.sha256.message_bit_length += (u64)
-		(csbcpb->cpb.sha256.spbc * 8);
-
-	/* everything after the first update is continuation */
-	NX_CPB_FDM(csbcpb) |= NX_FDM_CONTINUATION;
 out:
+	spin_unlock_irqrestore(&nx_ctx->lock, irq_flags);
 	return rc;
 }
 
@@ -129,8 +149,13 @@ static int nx_sha256_final(struct shash_desc *desc, u8 *out)
 	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(&desc->tfm->base);
 	struct nx_csbcpb *csbcpb = (struct nx_csbcpb *)nx_ctx->csbcpb;
 	struct nx_sg *in_sg, *out_sg;
+	u32 max_sg_len;
+	unsigned long irq_flags;
 	int rc;
 
+	spin_lock_irqsave(&nx_ctx->lock, irq_flags);
+
+	max_sg_len = min_t(u32, nx_driver.of.max_sg_len, nx_ctx->ap->sglen);
 
 	if (NX_CPB_FDM(csbcpb) & NX_FDM_CONTINUATION) {
 		/* we've hit the nx chip previously, now we're finalizing,
@@ -146,9 +171,9 @@ static int nx_sha256_final(struct shash_desc *desc, u8 *out)
 	csbcpb->cpb.sha256.message_bit_length += (u64)(sctx->count * 8);
 
 	in_sg = nx_build_sg_list(nx_ctx->in_sg, (u8 *)sctx->buf,
-				 sctx->count, nx_ctx->ap->sglen);
+				 sctx->count, max_sg_len);
 	out_sg = nx_build_sg_list(nx_ctx->out_sg, out, SHA256_DIGEST_SIZE,
-				  nx_ctx->ap->sglen);
+				  max_sg_len);
 	nx_ctx->op.inlen = (nx_ctx->in_sg - in_sg) * sizeof(struct nx_sg);
 	nx_ctx->op.outlen = (nx_ctx->out_sg - out_sg) * sizeof(struct nx_sg);
 
@@ -168,6 +193,7 @@ static int nx_sha256_final(struct shash_desc *desc, u8 *out)
 		     &(nx_ctx->stats->sha256_bytes));
 	memcpy(out, csbcpb->cpb.sha256.message_digest, SHA256_DIGEST_SIZE);
 out:
+	spin_unlock_irqrestore(&nx_ctx->lock, irq_flags);
 	return rc;
 }
 
@@ -177,6 +203,9 @@ static int nx_sha256_export(struct shash_desc *desc, void *out)
 	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(&desc->tfm->base);
 	struct nx_csbcpb *csbcpb = (struct nx_csbcpb *)nx_ctx->csbcpb;
 	struct sha256_state *octx = out;
+	unsigned long irq_flags;
+
+	spin_lock_irqsave(&nx_ctx->lock, irq_flags);
 
 	octx->count = sctx->count +
 		      (csbcpb->cpb.sha256.message_bit_length / 8);
@@ -199,6 +228,7 @@ static int nx_sha256_export(struct shash_desc *desc, void *out)
 		octx->state[7] = SHA256_H7;
 	}
 
+	spin_unlock_irqrestore(&nx_ctx->lock, irq_flags);
 	return 0;
 }
 
@@ -208,6 +238,9 @@ static int nx_sha256_import(struct shash_desc *desc, const void *in)
 	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(&desc->tfm->base);
 	struct nx_csbcpb *csbcpb = (struct nx_csbcpb *)nx_ctx->csbcpb;
 	const struct sha256_state *ictx = in;
+	unsigned long irq_flags;
+
+	spin_lock_irqsave(&nx_ctx->lock, irq_flags);
 
 	memcpy(sctx->buf, ictx->buf, sizeof(ictx->buf));
 
@@ -222,6 +255,7 @@ static int nx_sha256_import(struct shash_desc *desc, const void *in)
 		NX_CPB_FDM(csbcpb) |= NX_FDM_INTERMEDIATE;
 	}
 
+	spin_unlock_irqrestore(&nx_ctx->lock, irq_flags);
 	return 0;
 }
 
diff --git a/drivers/crypto/nx/nx-sha512.c b/drivers/crypto/nx/nx-sha512.c
index 08eee1122349..4ae5b0f221d5 100644
--- a/drivers/crypto/nx/nx-sha512.c
+++ b/drivers/crypto/nx/nx-sha512.c
@@ -55,73 +55,93 @@ static int nx_sha512_update(struct shash_desc *desc, const u8 *data,
 	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(&desc->tfm->base);
 	struct nx_csbcpb *csbcpb = (struct nx_csbcpb *)nx_ctx->csbcpb;
 	struct nx_sg *in_sg;
-	u64 to_process, leftover, spbc_bits;
+	u64 to_process, leftover, total, spbc_bits;
+	u32 max_sg_len;
+	unsigned long irq_flags;
 	int rc = 0;
 
-	if (NX_CPB_FDM(csbcpb) & NX_FDM_CONTINUATION) {
-		/* we've hit the nx chip previously and we're updating again,
-		 * so copy over the partial digest */
-		memcpy(csbcpb->cpb.sha512.input_partial_digest,
-		       csbcpb->cpb.sha512.message_digest, SHA512_DIGEST_SIZE);
-	}
+	spin_lock_irqsave(&nx_ctx->lock, irq_flags);
 
 	/* 2 cases for total data len:
-	 *  1: <= SHA512_BLOCK_SIZE: copy into state, return 0
-	 *  2: > SHA512_BLOCK_SIZE: process X blocks, copy in leftover
+	 *  1: < SHA512_BLOCK_SIZE: copy into state, return 0
+	 *  2: >= SHA512_BLOCK_SIZE: process X blocks, copy in leftover
 	 */
-	if ((u64)len + sctx->count[0] < SHA512_BLOCK_SIZE) {
+	total = sctx->count[0] + len;
+	if (total < SHA512_BLOCK_SIZE) {
 		memcpy(sctx->buf + sctx->count[0], data, len);
 		sctx->count[0] += len;
 		goto out;
 	}
 
-	/* to_process: the SHA512_BLOCK_SIZE data chunk to process in this
-	 * update */
-	to_process = (sctx->count[0] + len) & ~(SHA512_BLOCK_SIZE - 1);
-	leftover = (sctx->count[0] + len) & (SHA512_BLOCK_SIZE - 1);
-
-	if (sctx->count[0]) {
-		in_sg = nx_build_sg_list(nx_ctx->in_sg, (u8 *)sctx->buf,
-					 sctx->count[0], nx_ctx->ap->sglen);
-		in_sg = nx_build_sg_list(in_sg, (u8 *)data,
+	in_sg = nx_ctx->in_sg;
+	max_sg_len = min_t(u32, nx_driver.of.max_sg_len/sizeof(struct nx_sg),
+			   nx_ctx->ap->sglen);
+
+	do {
+		/*
+		 * to_process: the SHA512_BLOCK_SIZE data chunk to process in
+		 * this update. This value is also restricted by the sg list
+		 * limits.
+		 */
+		to_process = min_t(u64, total, nx_ctx->ap->databytelen);
+		to_process = min_t(u64, to_process,
+				   NX_PAGE_SIZE * (max_sg_len - 1));
+		to_process = to_process & ~(SHA512_BLOCK_SIZE - 1);
+		leftover = total - to_process;
+
+		if (sctx->count[0]) {
+			in_sg = nx_build_sg_list(nx_ctx->in_sg,
+						 (u8 *) sctx->buf,
+						 sctx->count[0], max_sg_len);
+		}
+		in_sg = nx_build_sg_list(in_sg, (u8 *) data,
 					 to_process - sctx->count[0],
-					 nx_ctx->ap->sglen);
-		nx_ctx->op.inlen = (nx_ctx->in_sg - in_sg) *
-					sizeof(struct nx_sg);
-	} else {
-		in_sg = nx_build_sg_list(nx_ctx->in_sg, (u8 *)data,
-					 to_process, nx_ctx->ap->sglen);
+					 max_sg_len);
 		nx_ctx->op.inlen = (nx_ctx->in_sg - in_sg) *
 					sizeof(struct nx_sg);
-	}
 
-	NX_CPB_FDM(csbcpb) |= NX_FDM_INTERMEDIATE;
+		if (NX_CPB_FDM(csbcpb) & NX_FDM_CONTINUATION) {
+			/*
+			 * we've hit the nx chip previously and we're updating
+			 * again, so copy over the partial digest.
+			 */
+			memcpy(csbcpb->cpb.sha512.input_partial_digest,
+			       csbcpb->cpb.sha512.message_digest,
+			       SHA512_DIGEST_SIZE);
+		}
 
-	if (!nx_ctx->op.inlen || !nx_ctx->op.outlen) {
-		rc = -EINVAL;
-		goto out;
-	}
-
-	rc = nx_hcall_sync(nx_ctx, &nx_ctx->op,
-			   desc->flags & CRYPTO_TFM_REQ_MAY_SLEEP);
-	if (rc)
-		goto out;
+		NX_CPB_FDM(csbcpb) |= NX_FDM_INTERMEDIATE;
+		if (!nx_ctx->op.inlen || !nx_ctx->op.outlen) {
+			rc = -EINVAL;
+			goto out;
+		}
+
+		rc = nx_hcall_sync(nx_ctx, &nx_ctx->op,
+				   desc->flags & CRYPTO_TFM_REQ_MAY_SLEEP);
+		if (rc)
+			goto out;
+
+		atomic_inc(&(nx_ctx->stats->sha512_ops));
+		spbc_bits = csbcpb->cpb.sha512.spbc * 8;
+		csbcpb->cpb.sha512.message_bit_length_lo += spbc_bits;
+		if (csbcpb->cpb.sha512.message_bit_length_lo < spbc_bits)
+			csbcpb->cpb.sha512.message_bit_length_hi++;
+
+		/* everything after the first update is continuation */
+		NX_CPB_FDM(csbcpb) |= NX_FDM_CONTINUATION;
 
-	atomic_inc(&(nx_ctx->stats->sha512_ops));
+		total -= to_process;
+		data += to_process - sctx->count[0];
+		sctx->count[0] = 0;
+		in_sg = nx_ctx->in_sg;
+	} while (leftover >= SHA512_BLOCK_SIZE);
 
 	/* copy the leftover back into the state struct */
 	if (leftover)
-		memcpy(sctx->buf, data + len - leftover, leftover);
+		memcpy(sctx->buf, data, leftover);
 	sctx->count[0] = leftover;
-
-	spbc_bits = csbcpb->cpb.sha512.spbc * 8;
-	csbcpb->cpb.sha512.message_bit_length_lo += spbc_bits;
-	if (csbcpb->cpb.sha512.message_bit_length_lo < spbc_bits)
-		csbcpb->cpb.sha512.message_bit_length_hi++;
-
-	/* everything after the first update is continuation */
-	NX_CPB_FDM(csbcpb) |= NX_FDM_CONTINUATION;
 out:
+	spin_unlock_irqrestore(&nx_ctx->lock, irq_flags);
 	return rc;
 }
 
@@ -131,9 +151,15 @@ static int nx_sha512_final(struct shash_desc *desc, u8 *out)
 	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(&desc->tfm->base);
 	struct nx_csbcpb *csbcpb = (struct nx_csbcpb *)nx_ctx->csbcpb;
 	struct nx_sg *in_sg, *out_sg;
+	u32 max_sg_len;
 	u64 count0;
+	unsigned long irq_flags;
 	int rc;
 
+	spin_lock_irqsave(&nx_ctx->lock, irq_flags);
+
+	max_sg_len = min_t(u32, nx_driver.of.max_sg_len, nx_ctx->ap->sglen);
+
 	if (NX_CPB_FDM(csbcpb) & NX_FDM_CONTINUATION) {
 		/* we've hit the nx chip previously, now we're finalizing,
 		 * so copy over the partial digest */
@@ -152,9 +178,9 @@ static int nx_sha512_final(struct shash_desc *desc, u8 *out)
 		csbcpb->cpb.sha512.message_bit_length_hi++;
 
 	in_sg = nx_build_sg_list(nx_ctx->in_sg, sctx->buf, sctx->count[0],
-				 nx_ctx->ap->sglen);
+				 max_sg_len);
 	out_sg = nx_build_sg_list(nx_ctx->out_sg, out, SHA512_DIGEST_SIZE,
-				  nx_ctx->ap->sglen);
+				  max_sg_len);
 	nx_ctx->op.inlen = (nx_ctx->in_sg - in_sg) * sizeof(struct nx_sg);
 	nx_ctx->op.outlen = (nx_ctx->out_sg - out_sg) * sizeof(struct nx_sg);
 
@@ -174,6 +200,7 @@ static int nx_sha512_final(struct shash_desc *desc, u8 *out)
 
 	memcpy(out, csbcpb->cpb.sha512.message_digest, SHA512_DIGEST_SIZE);
 out:
+	spin_unlock_irqrestore(&nx_ctx->lock, irq_flags);
 	return rc;
 }
 
@@ -183,6 +210,9 @@ static int nx_sha512_export(struct shash_desc *desc, void *out)
 	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(&desc->tfm->base);
 	struct nx_csbcpb *csbcpb = (struct nx_csbcpb *)nx_ctx->csbcpb;
 	struct sha512_state *octx = out;
+	unsigned long irq_flags;
+
+	spin_lock_irqsave(&nx_ctx->lock, irq_flags);
 
 	/* move message_bit_length (128 bits) into count and convert its value
 	 * to bytes */
@@ -214,6 +244,7 @@ static int nx_sha512_export(struct shash_desc *desc, void *out)
 		octx->state[7] = SHA512_H7;
 	}
 
+	spin_unlock_irqrestore(&nx_ctx->lock, irq_flags);
 	return 0;
 }
 
@@ -223,6 +254,9 @@ static int nx_sha512_import(struct shash_desc *desc, const void *in)
 	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(&desc->tfm->base);
 	struct nx_csbcpb *csbcpb = (struct nx_csbcpb *)nx_ctx->csbcpb;
 	const struct sha512_state *ictx = in;
+	unsigned long irq_flags;
+
+	spin_lock_irqsave(&nx_ctx->lock, irq_flags);
 
 	memcpy(sctx->buf, ictx->buf, sizeof(ictx->buf));
 	sctx->count[0] = ictx->count[0] & 0x3f;
@@ -240,6 +274,7 @@ static int nx_sha512_import(struct shash_desc *desc, const void *in)
 		NX_CPB_FDM(csbcpb) |= NX_FDM_INTERMEDIATE;
 	}
 
+	spin_unlock_irqrestore(&nx_ctx->lock, irq_flags);
 	return 0;
 }
 
diff --git a/drivers/crypto/nx/nx.c b/drivers/crypto/nx/nx.c
index bbdab6e5ccf0..5533fe31c90d 100644
--- a/drivers/crypto/nx/nx.c
+++ b/drivers/crypto/nx/nx.c
@@ -61,8 +61,7 @@ int nx_hcall_sync(struct nx_crypto_ctx *nx_ctx,
 
 	do {
 		rc = vio_h_cop_sync(viodev, op);
-	} while ((rc == -EBUSY && !may_sleep && retries--) ||
-	         (rc == -EBUSY && may_sleep && cond_resched()));
+	} while (rc == -EBUSY && !may_sleep && retries--);
 
 	if (rc) {
 		dev_dbg(&viodev->dev, "vio_h_cop_sync failed: rc: %d "
@@ -114,13 +113,29 @@ struct nx_sg *nx_build_sg_list(struct nx_sg *sg_head,
 	 * have been described (or @sgmax elements have been written), the
 	 * loop ends. min_t is used to ensure @end_addr falls on the same page
 	 * as sg_addr, if not, we need to create another nx_sg element for the
-	 * data on the next page */
+	 * data on the next page.
+	 *
+	 * Also when using vmalloc'ed data, every time that a system page
+	 * boundary is crossed the physical address needs to be re-calculated.
+	 */
 	for (sg = sg_head; sg_len < len; sg++) {
+		u64 next_page;
+
 		sg->addr = sg_addr;
-		sg_addr = min_t(u64, NX_PAGE_NUM(sg_addr + NX_PAGE_SIZE), end_addr);
-		sg->len = sg_addr - sg->addr;
+		sg_addr = min_t(u64, NX_PAGE_NUM(sg_addr + NX_PAGE_SIZE),
+				end_addr);
+
+		next_page = (sg->addr & PAGE_MASK) + PAGE_SIZE;
+		sg->len = min_t(u64, sg_addr, next_page) - sg->addr;
 		sg_len += sg->len;
 
+		if (sg_addr >= next_page &&
+				is_vmalloc_addr(start_addr + sg_len)) {
+			sg_addr = page_to_phys(vmalloc_to_page(
+						start_addr + sg_len));
+			end_addr = sg_addr + len - sg_len;
+		}
+
 		if ((sg - sg_head) == sgmax) {
 			pr_err("nx: scatter/gather list overflow, pid: %d\n",
 			       current->pid);
@@ -196,6 +211,8 @@ struct nx_sg *nx_walk_and_build(struct nx_sg       *nx_dst,
  * @dst: destination scatterlist
  * @src: source scatterlist
  * @nbytes: length of data described in the scatterlists
+ * @offset: number of bytes to fast-forward past at the beginning of
+ *          scatterlists.
  * @iv: destination for the iv data, if the algorithm requires it
  *
  * This is common code shared by all the AES algorithms. It uses the block
@@ -207,6 +224,7 @@ int nx_build_sg_lists(struct nx_crypto_ctx  *nx_ctx,
 		      struct scatterlist    *dst,
 		      struct scatterlist    *src,
 		      unsigned int           nbytes,
+		      unsigned int           offset,
 		      u8                    *iv)
 {
 	struct nx_sg *nx_insg = nx_ctx->in_sg;
@@ -215,8 +233,10 @@ int nx_build_sg_lists(struct nx_crypto_ctx  *nx_ctx,
 	if (iv)
 		memcpy(iv, desc->info, AES_BLOCK_SIZE);
 
-	nx_insg = nx_walk_and_build(nx_insg, nx_ctx->ap->sglen, src, 0, nbytes);
-	nx_outsg = nx_walk_and_build(nx_outsg, nx_ctx->ap->sglen, dst, 0, nbytes);
+	nx_insg = nx_walk_and_build(nx_insg, nx_ctx->ap->sglen, src,
+				    offset, nbytes);
+	nx_outsg = nx_walk_and_build(nx_outsg, nx_ctx->ap->sglen, dst,
+				    offset, nbytes);
 
 	/* these lengths should be negative, which will indicate to phyp that
 	 * the input and output parameters are scatterlists, not linear
@@ -235,6 +255,7 @@ int nx_build_sg_lists(struct nx_crypto_ctx  *nx_ctx,
  */
 void nx_ctx_init(struct nx_crypto_ctx *nx_ctx, unsigned int function)
 {
+	spin_lock_init(&nx_ctx->lock);
 	memset(nx_ctx->kmem, 0, nx_ctx->kmem_len);
 	nx_ctx->csbcpb->csb.valid |= NX_CSB_VALID_BIT;
 
diff --git a/drivers/crypto/nx/nx.h b/drivers/crypto/nx/nx.h
index 3232b182dd28..befda07ca1da 100644
--- a/drivers/crypto/nx/nx.h
+++ b/drivers/crypto/nx/nx.h
@@ -117,6 +117,7 @@ struct nx_ctr_priv {
 };
 
 struct nx_crypto_ctx {
+	spinlock_t lock;	  /* synchronize access to the context */
 	void *kmem;		  /* unaligned, kmalloc'd buffer */
 	size_t kmem_len;	  /* length of kmem */
 	struct nx_csbcpb *csbcpb; /* aligned page given to phyp @ hcall time */
@@ -155,7 +156,7 @@ int nx_hcall_sync(struct nx_crypto_ctx *ctx, struct vio_pfo_op *op,
 struct nx_sg *nx_build_sg_list(struct nx_sg *, u8 *, unsigned int, u32);
 int nx_build_sg_lists(struct nx_crypto_ctx *, struct blkcipher_desc *,
 		      struct scatterlist *, struct scatterlist *, unsigned int,
-		      u8 *);
+		      unsigned int, u8 *);
 struct nx_sg *nx_walk_and_build(struct nx_sg *, unsigned int,
 				struct scatterlist *, unsigned int,
 				unsigned int);
diff --git a/drivers/crypto/omap-aes.c b/drivers/crypto/omap-aes.c
index 5f7980586850..ce791c2f81f7 100644
--- a/drivers/crypto/omap-aes.c
+++ b/drivers/crypto/omap-aes.c
@@ -13,7 +13,9 @@
  *
  */
 
-#define pr_fmt(fmt) "%s: " fmt, __func__
+#define pr_fmt(fmt) "%20s: " fmt, __func__
+#define prn(num) pr_debug(#num "=%d\n", num)
+#define prx(num) pr_debug(#num "=%x\n", num)
 
 #include <linux/err.h>
 #include <linux/module.h>
@@ -38,6 +40,8 @@
 #define DST_MAXBURST			4
 #define DMA_MIN				(DST_MAXBURST * sizeof(u32))
 
+#define _calc_walked(inout) (dd->inout##_walk.offset - dd->inout##_sg->offset)
+
 /* OMAP TRM gives bitfields as start:end, where start is the higher bit
    number. For example 7:0 */
 #define FLD_MASK(start, end)	(((1 << ((start) - (end) + 1)) - 1) << (end))
@@ -74,6 +78,10 @@
 
 #define AES_REG_LENGTH_N(x)		(0x54 + ((x) * 0x04))
 
+#define AES_REG_IRQ_STATUS(dd)         ((dd)->pdata->irq_status_ofs)
+#define AES_REG_IRQ_ENABLE(dd)         ((dd)->pdata->irq_enable_ofs)
+#define AES_REG_IRQ_DATA_IN            BIT(1)
+#define AES_REG_IRQ_DATA_OUT           BIT(2)
 #define DEFAULT_TIMEOUT		(5*HZ)
 
 #define FLAGS_MODE_MASK		0x000f
@@ -86,6 +94,8 @@
 #define FLAGS_FAST		BIT(5)
 #define FLAGS_BUSY		BIT(6)
 
+#define AES_BLOCK_WORDS		(AES_BLOCK_SIZE >> 2)
+
 struct omap_aes_ctx {
 	struct omap_aes_dev *dd;
 
@@ -119,6 +129,8 @@ struct omap_aes_pdata {
 	u32		data_ofs;
 	u32		rev_ofs;
 	u32		mask_ofs;
+	u32             irq_enable_ofs;
+	u32             irq_status_ofs;
 
 	u32		dma_enable_in;
 	u32		dma_enable_out;
@@ -146,25 +158,32 @@ struct omap_aes_dev {
 	struct tasklet_struct	queue_task;
 
 	struct ablkcipher_request	*req;
+
+	/*
+	 * total is used by PIO mode for book keeping so introduce
+	 * variable total_save as need it to calc page_order
+	 */
 	size_t				total;
+	size_t				total_save;
+
 	struct scatterlist		*in_sg;
-	struct scatterlist		in_sgl;
-	size_t				in_offset;
 	struct scatterlist		*out_sg;
+
+	/* Buffers for copying for unaligned cases */
+	struct scatterlist		in_sgl;
 	struct scatterlist		out_sgl;
-	size_t				out_offset;
+	struct scatterlist		*orig_out;
+	int				sgs_copied;
 
-	size_t			buflen;
-	void			*buf_in;
-	size_t			dma_size;
+	struct scatter_walk		in_walk;
+	struct scatter_walk		out_walk;
 	int			dma_in;
 	struct dma_chan		*dma_lch_in;
-	dma_addr_t		dma_addr_in;
-	void			*buf_out;
 	int			dma_out;
 	struct dma_chan		*dma_lch_out;
-	dma_addr_t		dma_addr_out;
-
+	int			in_sg_len;
+	int			out_sg_len;
+	int			pio_only;
 	const struct omap_aes_pdata	*pdata;
 };
 
@@ -172,16 +191,36 @@ struct omap_aes_dev {
 static LIST_HEAD(dev_list);
 static DEFINE_SPINLOCK(list_lock);
 
+#ifdef DEBUG
+#define omap_aes_read(dd, offset)				\
+({								\
+	int _read_ret;						\
+	_read_ret = __raw_readl(dd->io_base + offset);		\
+	pr_debug("omap_aes_read(" #offset "=%#x)= %#x\n",	\
+		 offset, _read_ret);				\
+	_read_ret;						\
+})
+#else
 static inline u32 omap_aes_read(struct omap_aes_dev *dd, u32 offset)
 {
 	return __raw_readl(dd->io_base + offset);
 }
+#endif
 
+#ifdef DEBUG
+#define omap_aes_write(dd, offset, value)				\
+	do {								\
+		pr_debug("omap_aes_write(" #offset "=%#x) value=%#x\n",	\
+			 offset, value);				\
+		__raw_writel(value, dd->io_base + offset);		\
+	} while (0)
+#else
 static inline void omap_aes_write(struct omap_aes_dev *dd, u32 offset,
 				  u32 value)
 {
 	__raw_writel(value, dd->io_base + offset);
 }
+#endif
 
 static inline void omap_aes_write_mask(struct omap_aes_dev *dd, u32 offset,
 					u32 value, u32 mask)
@@ -323,33 +362,6 @@ static int omap_aes_dma_init(struct omap_aes_dev *dd)
 	dd->dma_lch_out = NULL;
 	dd->dma_lch_in = NULL;
 
-	dd->buf_in = (void *)__get_free_pages(GFP_KERNEL, OMAP_AES_CACHE_SIZE);
-	dd->buf_out = (void *)__get_free_pages(GFP_KERNEL, OMAP_AES_CACHE_SIZE);
-	dd->buflen = PAGE_SIZE << OMAP_AES_CACHE_SIZE;
-	dd->buflen &= ~(AES_BLOCK_SIZE - 1);
-
-	if (!dd->buf_in || !dd->buf_out) {
-		dev_err(dd->dev, "unable to alloc pages.\n");
-		goto err_alloc;
-	}
-
-	/* MAP here */
-	dd->dma_addr_in = dma_map_single(dd->dev, dd->buf_in, dd->buflen,
-					 DMA_TO_DEVICE);
-	if (dma_mapping_error(dd->dev, dd->dma_addr_in)) {
-		dev_err(dd->dev, "dma %d bytes error\n", dd->buflen);
-		err = -EINVAL;
-		goto err_map_in;
-	}
-
-	dd->dma_addr_out = dma_map_single(dd->dev, dd->buf_out, dd->buflen,
-					  DMA_FROM_DEVICE);
-	if (dma_mapping_error(dd->dev, dd->dma_addr_out)) {
-		dev_err(dd->dev, "dma %d bytes error\n", dd->buflen);
-		err = -EINVAL;
-		goto err_map_out;
-	}
-
 	dma_cap_zero(mask);
 	dma_cap_set(DMA_SLAVE, mask);
 
@@ -376,14 +388,6 @@ static int omap_aes_dma_init(struct omap_aes_dev *dd)
 err_dma_out:
 	dma_release_channel(dd->dma_lch_in);
 err_dma_in:
-	dma_unmap_single(dd->dev, dd->dma_addr_out, dd->buflen,
-			 DMA_FROM_DEVICE);
-err_map_out:
-	dma_unmap_single(dd->dev, dd->dma_addr_in, dd->buflen, DMA_TO_DEVICE);
-err_map_in:
-	free_pages((unsigned long)dd->buf_out, OMAP_AES_CACHE_SIZE);
-	free_pages((unsigned long)dd->buf_in, OMAP_AES_CACHE_SIZE);
-err_alloc:
 	if (err)
 		pr_err("error: %d\n", err);
 	return err;
@@ -393,11 +397,6 @@ static void omap_aes_dma_cleanup(struct omap_aes_dev *dd)
 {
 	dma_release_channel(dd->dma_lch_out);
 	dma_release_channel(dd->dma_lch_in);
-	dma_unmap_single(dd->dev, dd->dma_addr_out, dd->buflen,
-			 DMA_FROM_DEVICE);
-	dma_unmap_single(dd->dev, dd->dma_addr_in, dd->buflen, DMA_TO_DEVICE);
-	free_pages((unsigned long)dd->buf_out, OMAP_AES_CACHE_SIZE);
-	free_pages((unsigned long)dd->buf_in, OMAP_AES_CACHE_SIZE);
 }
 
 static void sg_copy_buf(void *buf, struct scatterlist *sg,
@@ -414,59 +413,27 @@ static void sg_copy_buf(void *buf, struct scatterlist *sg,
 	scatterwalk_done(&walk, out, 0);
 }
 
-static int sg_copy(struct scatterlist **sg, size_t *offset, void *buf,
-		   size_t buflen, size_t total, int out)
-{
-	unsigned int count, off = 0;
-
-	while (buflen && total) {
-		count = min((*sg)->length - *offset, total);
-		count = min(count, buflen);
-
-		if (!count)
-			return off;
-
-		/*
-		 * buflen and total are AES_BLOCK_SIZE size aligned,
-		 * so count should be also aligned
-		 */
-
-		sg_copy_buf(buf + off, *sg, *offset, count, out);
-
-		off += count;
-		buflen -= count;
-		*offset += count;
-		total -= count;
-
-		if (*offset == (*sg)->length) {
-			*sg = sg_next(*sg);
-			if (*sg)
-				*offset = 0;
-			else
-				total = 0;
-		}
-	}
-
-	return off;
-}
-
 static int omap_aes_crypt_dma(struct crypto_tfm *tfm,
-		struct scatterlist *in_sg, struct scatterlist *out_sg)
+		struct scatterlist *in_sg, struct scatterlist *out_sg,
+		int in_sg_len, int out_sg_len)
 {
 	struct omap_aes_ctx *ctx = crypto_tfm_ctx(tfm);
 	struct omap_aes_dev *dd = ctx->dd;
 	struct dma_async_tx_descriptor *tx_in, *tx_out;
 	struct dma_slave_config cfg;
-	dma_addr_t dma_addr_in = sg_dma_address(in_sg);
-	int ret, length = sg_dma_len(in_sg);
+	int ret;
 
-	pr_debug("len: %d\n", length);
+	if (dd->pio_only) {
+		scatterwalk_start(&dd->in_walk, dd->in_sg);
+		scatterwalk_start(&dd->out_walk, dd->out_sg);
 
-	dd->dma_size = length;
+		/* Enable DATAIN interrupt and let it take
+		   care of the rest */
+		omap_aes_write(dd, AES_REG_IRQ_ENABLE(dd), 0x2);
+		return 0;
+	}
 
-	if (!(dd->flags & FLAGS_FAST))
-		dma_sync_single_for_device(dd->dev, dma_addr_in, length,
-					   DMA_TO_DEVICE);
+	dma_sync_sg_for_device(dd->dev, dd->in_sg, in_sg_len, DMA_TO_DEVICE);
 
 	memset(&cfg, 0, sizeof(cfg));
 
@@ -485,7 +452,7 @@ static int omap_aes_crypt_dma(struct crypto_tfm *tfm,
 		return ret;
 	}
 
-	tx_in = dmaengine_prep_slave_sg(dd->dma_lch_in, in_sg, 1,
+	tx_in = dmaengine_prep_slave_sg(dd->dma_lch_in, in_sg, in_sg_len,
 					DMA_MEM_TO_DEV,
 					DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
 	if (!tx_in) {
@@ -504,7 +471,7 @@ static int omap_aes_crypt_dma(struct crypto_tfm *tfm,
 		return ret;
 	}
 
-	tx_out = dmaengine_prep_slave_sg(dd->dma_lch_out, out_sg, 1,
+	tx_out = dmaengine_prep_slave_sg(dd->dma_lch_out, out_sg, out_sg_len,
 					DMA_DEV_TO_MEM,
 					DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
 	if (!tx_out) {
@@ -522,7 +489,7 @@ static int omap_aes_crypt_dma(struct crypto_tfm *tfm,
 	dma_async_issue_pending(dd->dma_lch_out);
 
 	/* start DMA */
-	dd->pdata->trigger(dd, length);
+	dd->pdata->trigger(dd, dd->total);
 
 	return 0;
 }
@@ -531,93 +498,32 @@ static int omap_aes_crypt_dma_start(struct omap_aes_dev *dd)
 {
 	struct crypto_tfm *tfm = crypto_ablkcipher_tfm(
 					crypto_ablkcipher_reqtfm(dd->req));
-	int err, fast = 0, in, out;
-	size_t count;
-	dma_addr_t addr_in, addr_out;
-	struct scatterlist *in_sg, *out_sg;
-	int len32;
+	int err;
 
 	pr_debug("total: %d\n", dd->total);
 
-	if (sg_is_last(dd->in_sg) && sg_is_last(dd->out_sg)) {
-		/* check for alignment */
-		in = IS_ALIGNED((u32)dd->in_sg->offset, sizeof(u32));
-		out = IS_ALIGNED((u32)dd->out_sg->offset, sizeof(u32));
-
-		fast = in && out;
-	}
-
-	if (fast)  {
-		count = min(dd->total, sg_dma_len(dd->in_sg));
-		count = min(count, sg_dma_len(dd->out_sg));
-
-		if (count != dd->total) {
-			pr_err("request length != buffer length\n");
-			return -EINVAL;
-		}
-
-		pr_debug("fast\n");
-
-		err = dma_map_sg(dd->dev, dd->in_sg, 1, DMA_TO_DEVICE);
+	if (!dd->pio_only) {
+		err = dma_map_sg(dd->dev, dd->in_sg, dd->in_sg_len,
+				 DMA_TO_DEVICE);
 		if (!err) {
 			dev_err(dd->dev, "dma_map_sg() error\n");
 			return -EINVAL;
 		}
 
-		err = dma_map_sg(dd->dev, dd->out_sg, 1, DMA_FROM_DEVICE);
+		err = dma_map_sg(dd->dev, dd->out_sg, dd->out_sg_len,
+				 DMA_FROM_DEVICE);
 		if (!err) {
 			dev_err(dd->dev, "dma_map_sg() error\n");
-			dma_unmap_sg(dd->dev, dd->in_sg, 1, DMA_TO_DEVICE);
 			return -EINVAL;
 		}
-
-		addr_in = sg_dma_address(dd->in_sg);
-		addr_out = sg_dma_address(dd->out_sg);
-
-		in_sg = dd->in_sg;
-		out_sg = dd->out_sg;
-
-		dd->flags |= FLAGS_FAST;
-
-	} else {
-		/* use cache buffers */
-		count = sg_copy(&dd->in_sg, &dd->in_offset, dd->buf_in,
-				 dd->buflen, dd->total, 0);
-
-		len32 = DIV_ROUND_UP(count, DMA_MIN) * DMA_MIN;
-
-		/*
-		 * The data going into the AES module has been copied
-		 * to a local buffer and the data coming out will go
-		 * into a local buffer so set up local SG entries for
-		 * both.
-		 */
-		sg_init_table(&dd->in_sgl, 1);
-		dd->in_sgl.offset = dd->in_offset;
-		sg_dma_len(&dd->in_sgl) = len32;
-		sg_dma_address(&dd->in_sgl) = dd->dma_addr_in;
-
-		sg_init_table(&dd->out_sgl, 1);
-		dd->out_sgl.offset = dd->out_offset;
-		sg_dma_len(&dd->out_sgl) = len32;
-		sg_dma_address(&dd->out_sgl) = dd->dma_addr_out;
-
-		in_sg = &dd->in_sgl;
-		out_sg = &dd->out_sgl;
-
-		addr_in = dd->dma_addr_in;
-		addr_out = dd->dma_addr_out;
-
-		dd->flags &= ~FLAGS_FAST;
-
 	}
 
-	dd->total -= count;
-
-	err = omap_aes_crypt_dma(tfm, in_sg, out_sg);
-	if (err) {
-		dma_unmap_sg(dd->dev, dd->in_sg, 1, DMA_TO_DEVICE);
-		dma_unmap_sg(dd->dev, dd->out_sg, 1, DMA_TO_DEVICE);
+	err = omap_aes_crypt_dma(tfm, dd->in_sg, dd->out_sg, dd->in_sg_len,
+				 dd->out_sg_len);
+	if (err && !dd->pio_only) {
+		dma_unmap_sg(dd->dev, dd->in_sg, dd->in_sg_len, DMA_TO_DEVICE);
+		dma_unmap_sg(dd->dev, dd->out_sg, dd->out_sg_len,
+			     DMA_FROM_DEVICE);
 	}
 
 	return err;
@@ -637,7 +543,6 @@ static void omap_aes_finish_req(struct omap_aes_dev *dd, int err)
 static int omap_aes_crypt_dma_stop(struct omap_aes_dev *dd)
 {
 	int err = 0;
-	size_t count;
 
 	pr_debug("total: %d\n", dd->total);
 
@@ -646,23 +551,49 @@ static int omap_aes_crypt_dma_stop(struct omap_aes_dev *dd)
 	dmaengine_terminate_all(dd->dma_lch_in);
 	dmaengine_terminate_all(dd->dma_lch_out);
 
-	if (dd->flags & FLAGS_FAST) {
-		dma_unmap_sg(dd->dev, dd->out_sg, 1, DMA_FROM_DEVICE);
-		dma_unmap_sg(dd->dev, dd->in_sg, 1, DMA_TO_DEVICE);
-	} else {
-		dma_sync_single_for_device(dd->dev, dd->dma_addr_out,
-					   dd->dma_size, DMA_FROM_DEVICE);
-
-		/* copy data */
-		count = sg_copy(&dd->out_sg, &dd->out_offset, dd->buf_out,
-				 dd->buflen, dd->dma_size, 1);
-		if (count != dd->dma_size) {
-			err = -EINVAL;
-			pr_err("not all data converted: %u\n", count);
-		}
+	return err;
+}
+
+int omap_aes_check_aligned(struct scatterlist *sg)
+{
+	while (sg) {
+		if (!IS_ALIGNED(sg->offset, 4))
+			return -1;
+		if (!IS_ALIGNED(sg->length, AES_BLOCK_SIZE))
+			return -1;
+		sg = sg_next(sg);
 	}
+	return 0;
+}
 
-	return err;
+int omap_aes_copy_sgs(struct omap_aes_dev *dd)
+{
+	void *buf_in, *buf_out;
+	int pages;
+
+	pages = get_order(dd->total);
+
+	buf_in = (void *)__get_free_pages(GFP_ATOMIC, pages);
+	buf_out = (void *)__get_free_pages(GFP_ATOMIC, pages);
+
+	if (!buf_in || !buf_out) {
+		pr_err("Couldn't allocated pages for unaligned cases.\n");
+		return -1;
+	}
+
+	dd->orig_out = dd->out_sg;
+
+	sg_copy_buf(buf_in, dd->in_sg, 0, dd->total, 0);
+
+	sg_init_table(&dd->in_sgl, 1);
+	sg_set_buf(&dd->in_sgl, buf_in, dd->total);
+	dd->in_sg = &dd->in_sgl;
+
+	sg_init_table(&dd->out_sgl, 1);
+	sg_set_buf(&dd->out_sgl, buf_out, dd->total);
+	dd->out_sg = &dd->out_sgl;
+
+	return 0;
 }
 
 static int omap_aes_handle_queue(struct omap_aes_dev *dd,
@@ -698,11 +629,23 @@ static int omap_aes_handle_queue(struct omap_aes_dev *dd,
 	/* assign new request to device */
 	dd->req = req;
 	dd->total = req->nbytes;
-	dd->in_offset = 0;
+	dd->total_save = req->nbytes;
 	dd->in_sg = req->src;
-	dd->out_offset = 0;
 	dd->out_sg = req->dst;
 
+	if (omap_aes_check_aligned(dd->in_sg) ||
+	    omap_aes_check_aligned(dd->out_sg)) {
+		if (omap_aes_copy_sgs(dd))
+			pr_err("Failed to copy SGs for unaligned cases\n");
+		dd->sgs_copied = 1;
+	} else {
+		dd->sgs_copied = 0;
+	}
+
+	dd->in_sg_len = scatterwalk_bytes_sglen(dd->in_sg, dd->total);
+	dd->out_sg_len = scatterwalk_bytes_sglen(dd->out_sg, dd->total);
+	BUG_ON(dd->in_sg_len < 0 || dd->out_sg_len < 0);
+
 	rctx = ablkcipher_request_ctx(req);
 	ctx = crypto_ablkcipher_ctx(crypto_ablkcipher_reqtfm(req));
 	rctx->mode &= FLAGS_MODE_MASK;
@@ -726,21 +669,32 @@ static int omap_aes_handle_queue(struct omap_aes_dev *dd,
 static void omap_aes_done_task(unsigned long data)
 {
 	struct omap_aes_dev *dd = (struct omap_aes_dev *)data;
-	int err;
-
-	pr_debug("enter\n");
+	void *buf_in, *buf_out;
+	int pages;
+
+	pr_debug("enter done_task\n");
+
+	if (!dd->pio_only) {
+		dma_sync_sg_for_device(dd->dev, dd->out_sg, dd->out_sg_len,
+				       DMA_FROM_DEVICE);
+		dma_unmap_sg(dd->dev, dd->in_sg, dd->in_sg_len, DMA_TO_DEVICE);
+		dma_unmap_sg(dd->dev, dd->out_sg, dd->out_sg_len,
+			     DMA_FROM_DEVICE);
+		omap_aes_crypt_dma_stop(dd);
+	}
 
-	err = omap_aes_crypt_dma_stop(dd);
+	if (dd->sgs_copied) {
+		buf_in = sg_virt(&dd->in_sgl);
+		buf_out = sg_virt(&dd->out_sgl);
 
-	err = dd->err ? : err;
+		sg_copy_buf(buf_out, dd->orig_out, 0, dd->total_save, 1);
 
-	if (dd->total && !err) {
-		err = omap_aes_crypt_dma_start(dd);
-		if (!err)
-			return; /* DMA started. Not fininishing. */
+		pages = get_order(dd->total_save);
+		free_pages((unsigned long)buf_in, pages);
+		free_pages((unsigned long)buf_out, pages);
 	}
 
-	omap_aes_finish_req(dd, err);
+	omap_aes_finish_req(dd, 0);
 	omap_aes_handle_queue(dd, NULL);
 
 	pr_debug("exit\n");
@@ -1002,6 +956,8 @@ static const struct omap_aes_pdata omap_aes_pdata_omap4 = {
 	.data_ofs	= 0x60,
 	.rev_ofs	= 0x80,
 	.mask_ofs	= 0x84,
+	.irq_status_ofs = 0x8c,
+	.irq_enable_ofs = 0x90,
 	.dma_enable_in	= BIT(5),
 	.dma_enable_out	= BIT(6),
 	.major_mask	= 0x0700,
@@ -1010,6 +966,90 @@ static const struct omap_aes_pdata omap_aes_pdata_omap4 = {
 	.minor_shift	= 0,
 };
 
+static irqreturn_t omap_aes_irq(int irq, void *dev_id)
+{
+	struct omap_aes_dev *dd = dev_id;
+	u32 status, i;
+	u32 *src, *dst;
+
+	status = omap_aes_read(dd, AES_REG_IRQ_STATUS(dd));
+	if (status & AES_REG_IRQ_DATA_IN) {
+		omap_aes_write(dd, AES_REG_IRQ_ENABLE(dd), 0x0);
+
+		BUG_ON(!dd->in_sg);
+
+		BUG_ON(_calc_walked(in) > dd->in_sg->length);
+
+		src = sg_virt(dd->in_sg) + _calc_walked(in);
+
+		for (i = 0; i < AES_BLOCK_WORDS; i++) {
+			omap_aes_write(dd, AES_REG_DATA_N(dd, i), *src);
+
+			scatterwalk_advance(&dd->in_walk, 4);
+			if (dd->in_sg->length == _calc_walked(in)) {
+				dd->in_sg = scatterwalk_sg_next(dd->in_sg);
+				if (dd->in_sg) {
+					scatterwalk_start(&dd->in_walk,
+							  dd->in_sg);
+					src = sg_virt(dd->in_sg) +
+					      _calc_walked(in);
+				}
+			} else {
+				src++;
+			}
+		}
+
+		/* Clear IRQ status */
+		status &= ~AES_REG_IRQ_DATA_IN;
+		omap_aes_write(dd, AES_REG_IRQ_STATUS(dd), status);
+
+		/* Enable DATA_OUT interrupt */
+		omap_aes_write(dd, AES_REG_IRQ_ENABLE(dd), 0x4);
+
+	} else if (status & AES_REG_IRQ_DATA_OUT) {
+		omap_aes_write(dd, AES_REG_IRQ_ENABLE(dd), 0x0);
+
+		BUG_ON(!dd->out_sg);
+
+		BUG_ON(_calc_walked(out) > dd->out_sg->length);
+
+		dst = sg_virt(dd->out_sg) + _calc_walked(out);
+
+		for (i = 0; i < AES_BLOCK_WORDS; i++) {
+			*dst = omap_aes_read(dd, AES_REG_DATA_N(dd, i));
+			scatterwalk_advance(&dd->out_walk, 4);
+			if (dd->out_sg->length == _calc_walked(out)) {
+				dd->out_sg = scatterwalk_sg_next(dd->out_sg);
+				if (dd->out_sg) {
+					scatterwalk_start(&dd->out_walk,
+							  dd->out_sg);
+					dst = sg_virt(dd->out_sg) +
+					      _calc_walked(out);
+				}
+			} else {
+				dst++;
+			}
+		}
+
+		dd->total -= AES_BLOCK_SIZE;
+
+		BUG_ON(dd->total < 0);
+
+		/* Clear IRQ status */
+		status &= ~AES_REG_IRQ_DATA_OUT;
+		omap_aes_write(dd, AES_REG_IRQ_STATUS(dd), status);
+
+		if (!dd->total)
+			/* All bytes read! */
+			tasklet_schedule(&dd->done_task);
+		else
+			/* Enable DATA_IN interrupt for next block */
+			omap_aes_write(dd, AES_REG_IRQ_ENABLE(dd), 0x2);
+	}
+
+	return IRQ_HANDLED;
+}
+
 static const struct of_device_id omap_aes_of_match[] = {
 	{
 		.compatible	= "ti,omap2-aes",
@@ -1115,10 +1155,10 @@ static int omap_aes_probe(struct platform_device *pdev)
 	struct omap_aes_dev *dd;
 	struct crypto_alg *algp;
 	struct resource res;
-	int err = -ENOMEM, i, j;
+	int err = -ENOMEM, i, j, irq = -1;
 	u32 reg;
 
-	dd = kzalloc(sizeof(struct omap_aes_dev), GFP_KERNEL);
+	dd = devm_kzalloc(dev, sizeof(struct omap_aes_dev), GFP_KERNEL);
 	if (dd == NULL) {
 		dev_err(dev, "unable to alloc data struct.\n");
 		goto err_data;
@@ -1158,8 +1198,23 @@ static int omap_aes_probe(struct platform_device *pdev)
 	tasklet_init(&dd->queue_task, omap_aes_queue_task, (unsigned long)dd);
 
 	err = omap_aes_dma_init(dd);
-	if (err)
-		goto err_dma;
+	if (err && AES_REG_IRQ_STATUS(dd) && AES_REG_IRQ_ENABLE(dd)) {
+		dd->pio_only = 1;
+
+		irq = platform_get_irq(pdev, 0);
+		if (irq < 0) {
+			dev_err(dev, "can't get IRQ resource\n");
+			goto err_irq;
+		}
+
+		err = devm_request_irq(dev, irq, omap_aes_irq, 0,
+				dev_name(dev), dd);
+		if (err) {
+			dev_err(dev, "Unable to grab omap-aes IRQ\n");
+			goto err_irq;
+		}
+	}
+
 
 	INIT_LIST_HEAD(&dd->list);
 	spin_lock(&list_lock);
@@ -1187,13 +1242,13 @@ err_algs:
 		for (j = dd->pdata->algs_info[i].registered - 1; j >= 0; j--)
 			crypto_unregister_alg(
 					&dd->pdata->algs_info[i].algs_list[j]);
-	omap_aes_dma_cleanup(dd);
-err_dma:
+	if (!dd->pio_only)
+		omap_aes_dma_cleanup(dd);
+err_irq:
 	tasklet_kill(&dd->done_task);
 	tasklet_kill(&dd->queue_task);
 	pm_runtime_disable(dev);
 err_res:
-	kfree(dd);
 	dd = NULL;
 err_data:
 	dev_err(dev, "initialization failed.\n");
@@ -1221,7 +1276,6 @@ static int omap_aes_remove(struct platform_device *pdev)
 	tasklet_kill(&dd->queue_task);
 	omap_aes_dma_cleanup(dd);
 	pm_runtime_disable(dd->dev);
-	kfree(dd);
 	dd = NULL;
 
 	return 0;
diff --git a/drivers/crypto/omap-sham.c b/drivers/crypto/omap-sham.c
index 4bb67652c200..8bdde57f6bb1 100644
--- a/drivers/crypto/omap-sham.c
+++ b/drivers/crypto/omap-sham.c
@@ -44,17 +44,13 @@
 #include <crypto/hash.h>
 #include <crypto/internal/hash.h>
 
-#define SHA1_MD5_BLOCK_SIZE		SHA1_BLOCK_SIZE
 #define MD5_DIGEST_SIZE			16
 
-#define DST_MAXBURST			16
-#define DMA_MIN				(DST_MAXBURST * sizeof(u32))
-
 #define SHA_REG_IDIGEST(dd, x)		((dd)->pdata->idigest_ofs + ((x)*0x04))
 #define SHA_REG_DIN(dd, x)		((dd)->pdata->din_ofs + ((x) * 0x04))
 #define SHA_REG_DIGCNT(dd)		((dd)->pdata->digcnt_ofs)
 
-#define SHA_REG_ODIGEST(x)		(0x00 + ((x) * 0x04))
+#define SHA_REG_ODIGEST(dd, x)		((dd)->pdata->odigest_ofs + (x * 0x04))
 
 #define SHA_REG_CTRL			0x18
 #define SHA_REG_CTRL_LENGTH		(0xFFFFFFFF << 5)
@@ -75,18 +71,21 @@
 #define SHA_REG_SYSSTATUS(dd)		((dd)->pdata->sysstatus_ofs)
 #define SHA_REG_SYSSTATUS_RESETDONE	(1 << 0)
 
-#define SHA_REG_MODE			0x44
+#define SHA_REG_MODE(dd)		((dd)->pdata->mode_ofs)
 #define SHA_REG_MODE_HMAC_OUTER_HASH	(1 << 7)
 #define SHA_REG_MODE_HMAC_KEY_PROC	(1 << 5)
 #define SHA_REG_MODE_CLOSE_HASH		(1 << 4)
 #define SHA_REG_MODE_ALGO_CONSTANT	(1 << 3)
-#define SHA_REG_MODE_ALGO_MASK		(3 << 1)
-#define		SHA_REG_MODE_ALGO_MD5_128	(0 << 1)
-#define		SHA_REG_MODE_ALGO_SHA1_160	(1 << 1)
-#define		SHA_REG_MODE_ALGO_SHA2_224	(2 << 1)
-#define		SHA_REG_MODE_ALGO_SHA2_256	(3 << 1)
 
-#define SHA_REG_LENGTH			0x48
+#define SHA_REG_MODE_ALGO_MASK		(7 << 0)
+#define SHA_REG_MODE_ALGO_MD5_128	(0 << 1)
+#define SHA_REG_MODE_ALGO_SHA1_160	(1 << 1)
+#define SHA_REG_MODE_ALGO_SHA2_224	(2 << 1)
+#define SHA_REG_MODE_ALGO_SHA2_256	(3 << 1)
+#define SHA_REG_MODE_ALGO_SHA2_384	(1 << 0)
+#define SHA_REG_MODE_ALGO_SHA2_512	(3 << 0)
+
+#define SHA_REG_LENGTH(dd)		((dd)->pdata->length_ofs)
 
 #define SHA_REG_IRQSTATUS		0x118
 #define SHA_REG_IRQSTATUS_CTX_RDY	(1 << 3)
@@ -117,18 +116,16 @@
 #define FLAGS_SG		17
 
 #define FLAGS_MODE_SHIFT	18
-#define FLAGS_MODE_MASK		(SHA_REG_MODE_ALGO_MASK			\
-					<< (FLAGS_MODE_SHIFT - 1))
-#define		FLAGS_MODE_MD5		(SHA_REG_MODE_ALGO_MD5_128	\
-						<< (FLAGS_MODE_SHIFT - 1))
-#define		FLAGS_MODE_SHA1		(SHA_REG_MODE_ALGO_SHA1_160	\
-						<< (FLAGS_MODE_SHIFT - 1))
-#define		FLAGS_MODE_SHA224	(SHA_REG_MODE_ALGO_SHA2_224	\
-						<< (FLAGS_MODE_SHIFT - 1))
-#define		FLAGS_MODE_SHA256	(SHA_REG_MODE_ALGO_SHA2_256	\
-						<< (FLAGS_MODE_SHIFT - 1))
-#define FLAGS_HMAC		20
-#define FLAGS_ERROR		21
+#define FLAGS_MODE_MASK		(SHA_REG_MODE_ALGO_MASK	<< FLAGS_MODE_SHIFT)
+#define FLAGS_MODE_MD5		(SHA_REG_MODE_ALGO_MD5_128 << FLAGS_MODE_SHIFT)
+#define FLAGS_MODE_SHA1		(SHA_REG_MODE_ALGO_SHA1_160 << FLAGS_MODE_SHIFT)
+#define FLAGS_MODE_SHA224	(SHA_REG_MODE_ALGO_SHA2_224 << FLAGS_MODE_SHIFT)
+#define FLAGS_MODE_SHA256	(SHA_REG_MODE_ALGO_SHA2_256 << FLAGS_MODE_SHIFT)
+#define FLAGS_MODE_SHA384	(SHA_REG_MODE_ALGO_SHA2_384 << FLAGS_MODE_SHIFT)
+#define FLAGS_MODE_SHA512	(SHA_REG_MODE_ALGO_SHA2_512 << FLAGS_MODE_SHIFT)
+
+#define FLAGS_HMAC		21
+#define FLAGS_ERROR		22
 
 #define OP_UPDATE		1
 #define OP_FINAL		2
@@ -145,7 +142,7 @@ struct omap_sham_reqctx {
 	unsigned long		flags;
 	unsigned long		op;
 
-	u8			digest[SHA256_DIGEST_SIZE] OMAP_ALIGNED;
+	u8			digest[SHA512_DIGEST_SIZE] OMAP_ALIGNED;
 	size_t			digcnt;
 	size_t			bufcnt;
 	size_t			buflen;
@@ -162,8 +159,8 @@ struct omap_sham_reqctx {
 
 struct omap_sham_hmac_ctx {
 	struct crypto_shash	*shash;
-	u8			ipad[SHA1_MD5_BLOCK_SIZE] OMAP_ALIGNED;
-	u8			opad[SHA1_MD5_BLOCK_SIZE] OMAP_ALIGNED;
+	u8			ipad[SHA512_BLOCK_SIZE] OMAP_ALIGNED;
+	u8			opad[SHA512_BLOCK_SIZE] OMAP_ALIGNED;
 };
 
 struct omap_sham_ctx {
@@ -205,6 +202,8 @@ struct omap_sham_pdata {
 	u32		rev_ofs;
 	u32		mask_ofs;
 	u32		sysstatus_ofs;
+	u32		mode_ofs;
+	u32		length_ofs;
 
 	u32		major_mask;
 	u32		major_shift;
@@ -223,6 +222,7 @@ struct omap_sham_dev {
 	unsigned int		dma;
 	struct dma_chan		*dma_lch;
 	struct tasklet_struct	done_task;
+	u8			polling_mode;
 
 	unsigned long		flags;
 	struct crypto_queue	queue;
@@ -306,9 +306,9 @@ static void omap_sham_copy_hash_omap4(struct ahash_request *req, int out)
 		for (i = 0; i < dd->pdata->digest_size / sizeof(u32); i++) {
 			if (out)
 				opad[i] = omap_sham_read(dd,
-						SHA_REG_ODIGEST(i));
+						SHA_REG_ODIGEST(dd, i));
 			else
-				omap_sham_write(dd, SHA_REG_ODIGEST(i),
+				omap_sham_write(dd, SHA_REG_ODIGEST(dd, i),
 						opad[i]);
 		}
 	}
@@ -342,6 +342,12 @@ static void omap_sham_copy_ready_hash(struct ahash_request *req)
 	case FLAGS_MODE_SHA256:
 		d = SHA256_DIGEST_SIZE / sizeof(u32);
 		break;
+	case FLAGS_MODE_SHA384:
+		d = SHA384_DIGEST_SIZE / sizeof(u32);
+		break;
+	case FLAGS_MODE_SHA512:
+		d = SHA512_DIGEST_SIZE / sizeof(u32);
+		break;
 	default:
 		d = 0;
 	}
@@ -404,6 +410,30 @@ static int omap_sham_poll_irq_omap2(struct omap_sham_dev *dd)
 	return omap_sham_wait(dd, SHA_REG_CTRL, SHA_REG_CTRL_INPUT_READY);
 }
 
+static int get_block_size(struct omap_sham_reqctx *ctx)
+{
+	int d;
+
+	switch (ctx->flags & FLAGS_MODE_MASK) {
+	case FLAGS_MODE_MD5:
+	case FLAGS_MODE_SHA1:
+		d = SHA1_BLOCK_SIZE;
+		break;
+	case FLAGS_MODE_SHA224:
+	case FLAGS_MODE_SHA256:
+		d = SHA256_BLOCK_SIZE;
+		break;
+	case FLAGS_MODE_SHA384:
+	case FLAGS_MODE_SHA512:
+		d = SHA512_BLOCK_SIZE;
+		break;
+	default:
+		d = 0;
+	}
+
+	return d;
+}
+
 static void omap_sham_write_n(struct omap_sham_dev *dd, u32 offset,
 				    u32 *value, int count)
 {
@@ -422,20 +452,24 @@ static void omap_sham_write_ctrl_omap4(struct omap_sham_dev *dd, size_t length,
 	 * CLOSE_HASH only for the last one. Note that flags mode bits
 	 * correspond to algorithm encoding in mode register.
 	 */
-	val = (ctx->flags & FLAGS_MODE_MASK) >> (FLAGS_MODE_SHIFT - 1);
+	val = (ctx->flags & FLAGS_MODE_MASK) >> (FLAGS_MODE_SHIFT);
 	if (!ctx->digcnt) {
 		struct crypto_ahash *tfm = crypto_ahash_reqtfm(dd->req);
 		struct omap_sham_ctx *tctx = crypto_ahash_ctx(tfm);
 		struct omap_sham_hmac_ctx *bctx = tctx->base;
+		int bs, nr_dr;
 
 		val |= SHA_REG_MODE_ALGO_CONSTANT;
 
 		if (ctx->flags & BIT(FLAGS_HMAC)) {
+			bs = get_block_size(ctx);
+			nr_dr = bs / (2 * sizeof(u32));
 			val |= SHA_REG_MODE_HMAC_KEY_PROC;
-			omap_sham_write_n(dd, SHA_REG_ODIGEST(0),
-					  (u32 *)bctx->ipad,
-					  SHA1_BLOCK_SIZE / sizeof(u32));
-			ctx->digcnt += SHA1_BLOCK_SIZE;
+			omap_sham_write_n(dd, SHA_REG_ODIGEST(dd, 0),
+					  (u32 *)bctx->ipad, nr_dr);
+			omap_sham_write_n(dd, SHA_REG_IDIGEST(dd, 0),
+					  (u32 *)bctx->ipad + nr_dr, nr_dr);
+			ctx->digcnt += bs;
 		}
 	}
 
@@ -451,7 +485,7 @@ static void omap_sham_write_ctrl_omap4(struct omap_sham_dev *dd, size_t length,
 	       SHA_REG_MODE_HMAC_KEY_PROC;
 
 	dev_dbg(dd->dev, "ctrl: %08x, flags: %08lx\n", val, ctx->flags);
-	omap_sham_write_mask(dd, SHA_REG_MODE, val, mask);
+	omap_sham_write_mask(dd, SHA_REG_MODE(dd), val, mask);
 	omap_sham_write(dd, SHA_REG_IRQENA, SHA_REG_IRQENA_OUTPUT_RDY);
 	omap_sham_write_mask(dd, SHA_REG_MASK(dd),
 			     SHA_REG_MASK_IT_EN |
@@ -461,7 +495,7 @@ static void omap_sham_write_ctrl_omap4(struct omap_sham_dev *dd, size_t length,
 
 static void omap_sham_trigger_omap4(struct omap_sham_dev *dd, size_t length)
 {
-	omap_sham_write(dd, SHA_REG_LENGTH, length);
+	omap_sham_write(dd, SHA_REG_LENGTH(dd), length);
 }
 
 static int omap_sham_poll_irq_omap4(struct omap_sham_dev *dd)
@@ -474,7 +508,7 @@ static int omap_sham_xmit_cpu(struct omap_sham_dev *dd, const u8 *buf,
 			      size_t length, int final)
 {
 	struct omap_sham_reqctx *ctx = ahash_request_ctx(dd->req);
-	int count, len32;
+	int count, len32, bs32, offset = 0;
 	const u32 *buffer = (const u32 *)buf;
 
 	dev_dbg(dd->dev, "xmit_cpu: digcnt: %d, length: %d, final: %d\n",
@@ -486,18 +520,23 @@ static int omap_sham_xmit_cpu(struct omap_sham_dev *dd, const u8 *buf,
 	/* should be non-zero before next lines to disable clocks later */
 	ctx->digcnt += length;
 
-	if (dd->pdata->poll_irq(dd))
-		return -ETIMEDOUT;
-
 	if (final)
 		set_bit(FLAGS_FINAL, &dd->flags); /* catch last interrupt */
 
 	set_bit(FLAGS_CPU, &dd->flags);
 
 	len32 = DIV_ROUND_UP(length, sizeof(u32));
+	bs32 = get_block_size(ctx) / sizeof(u32);
 
-	for (count = 0; count < len32; count++)
-		omap_sham_write(dd, SHA_REG_DIN(dd, count), buffer[count]);
+	while (len32) {
+		if (dd->pdata->poll_irq(dd))
+			return -ETIMEDOUT;
+
+		for (count = 0; count < min(len32, bs32); count++, offset++)
+			omap_sham_write(dd, SHA_REG_DIN(dd, count),
+					buffer[offset]);
+		len32 -= min(len32, bs32);
+	}
 
 	return -EINPROGRESS;
 }
@@ -516,7 +555,7 @@ static int omap_sham_xmit_dma(struct omap_sham_dev *dd, dma_addr_t dma_addr,
 	struct omap_sham_reqctx *ctx = ahash_request_ctx(dd->req);
 	struct dma_async_tx_descriptor *tx;
 	struct dma_slave_config cfg;
-	int len32, ret;
+	int len32, ret, dma_min = get_block_size(ctx);
 
 	dev_dbg(dd->dev, "xmit_dma: digcnt: %d, length: %d, final: %d\n",
 						ctx->digcnt, length, final);
@@ -525,7 +564,7 @@ static int omap_sham_xmit_dma(struct omap_sham_dev *dd, dma_addr_t dma_addr,
 
 	cfg.dst_addr = dd->phys_base + SHA_REG_DIN(dd, 0);
 	cfg.dst_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
-	cfg.dst_maxburst = DST_MAXBURST;
+	cfg.dst_maxburst = dma_min / DMA_SLAVE_BUSWIDTH_4_BYTES;
 
 	ret = dmaengine_slave_config(dd->dma_lch, &cfg);
 	if (ret) {
@@ -533,7 +572,7 @@ static int omap_sham_xmit_dma(struct omap_sham_dev *dd, dma_addr_t dma_addr,
 		return ret;
 	}
 
-	len32 = DIV_ROUND_UP(length, DMA_MIN) * DMA_MIN;
+	len32 = DIV_ROUND_UP(length, dma_min) * dma_min;
 
 	if (is_sg) {
 		/*
@@ -666,14 +705,14 @@ static int omap_sham_update_dma_slow(struct omap_sham_dev *dd)
 /* Start address alignment */
 #define SG_AA(sg)	(IS_ALIGNED(sg->offset, sizeof(u32)))
 /* SHA1 block size alignment */
-#define SG_SA(sg)	(IS_ALIGNED(sg->length, SHA1_MD5_BLOCK_SIZE))
+#define SG_SA(sg, bs)	(IS_ALIGNED(sg->length, bs))
 
 static int omap_sham_update_dma_start(struct omap_sham_dev *dd)
 {
 	struct omap_sham_reqctx *ctx = ahash_request_ctx(dd->req);
 	unsigned int length, final, tail;
 	struct scatterlist *sg;
-	int ret;
+	int ret, bs;
 
 	if (!ctx->total)
 		return 0;
@@ -687,30 +726,31 @@ static int omap_sham_update_dma_start(struct omap_sham_dev *dd)
 	 * the dmaengine infrastructure will calculate that it needs
 	 * to transfer 0 frames which ultimately fails.
 	 */
-	if (ctx->total < (DST_MAXBURST * sizeof(u32)))
+	if (ctx->total < get_block_size(ctx))
 		return omap_sham_update_dma_slow(dd);
 
 	dev_dbg(dd->dev, "fast: digcnt: %d, bufcnt: %u, total: %u\n",
 			ctx->digcnt, ctx->bufcnt, ctx->total);
 
 	sg = ctx->sg;
+	bs = get_block_size(ctx);
 
 	if (!SG_AA(sg))
 		return omap_sham_update_dma_slow(dd);
 
-	if (!sg_is_last(sg) && !SG_SA(sg))
-		/* size is not SHA1_BLOCK_SIZE aligned */
+	if (!sg_is_last(sg) && !SG_SA(sg, bs))
+		/* size is not BLOCK_SIZE aligned */
 		return omap_sham_update_dma_slow(dd);
 
 	length = min(ctx->total, sg->length);
 
 	if (sg_is_last(sg)) {
 		if (!(ctx->flags & BIT(FLAGS_FINUP))) {
-			/* not last sg must be SHA1_MD5_BLOCK_SIZE aligned */
-			tail = length & (SHA1_MD5_BLOCK_SIZE - 1);
+			/* not last sg must be BLOCK_SIZE aligned */
+			tail = length & (bs - 1);
 			/* without finup() we need one block to close hash */
 			if (!tail)
-				tail = SHA1_MD5_BLOCK_SIZE;
+				tail = bs;
 			length -= tail;
 		}
 	}
@@ -737,13 +777,22 @@ static int omap_sham_update_dma_start(struct omap_sham_dev *dd)
 static int omap_sham_update_cpu(struct omap_sham_dev *dd)
 {
 	struct omap_sham_reqctx *ctx = ahash_request_ctx(dd->req);
-	int bufcnt;
+	int bufcnt, final;
+
+	if (!ctx->total)
+		return 0;
 
 	omap_sham_append_sg(ctx);
+
+	final = (ctx->flags & BIT(FLAGS_FINUP)) && !ctx->total;
+
+	dev_dbg(dd->dev, "cpu: bufcnt: %u, digcnt: %d, final: %d\n",
+		ctx->bufcnt, ctx->digcnt, final);
+
 	bufcnt = ctx->bufcnt;
 	ctx->bufcnt = 0;
 
-	return omap_sham_xmit_cpu(dd, ctx->buffer, bufcnt, 1);
+	return omap_sham_xmit_cpu(dd, ctx->buffer, bufcnt, final);
 }
 
 static int omap_sham_update_dma_stop(struct omap_sham_dev *dd)
@@ -773,6 +822,7 @@ static int omap_sham_init(struct ahash_request *req)
 	struct omap_sham_ctx *tctx = crypto_ahash_ctx(tfm);
 	struct omap_sham_reqctx *ctx = ahash_request_ctx(req);
 	struct omap_sham_dev *dd = NULL, *tmp;
+	int bs = 0;
 
 	spin_lock_bh(&sham.lock);
 	if (!tctx->dd) {
@@ -796,15 +846,27 @@ static int omap_sham_init(struct ahash_request *req)
 	switch (crypto_ahash_digestsize(tfm)) {
 	case MD5_DIGEST_SIZE:
 		ctx->flags |= FLAGS_MODE_MD5;
+		bs = SHA1_BLOCK_SIZE;
 		break;
 	case SHA1_DIGEST_SIZE:
 		ctx->flags |= FLAGS_MODE_SHA1;
+		bs = SHA1_BLOCK_SIZE;
 		break;
 	case SHA224_DIGEST_SIZE:
 		ctx->flags |= FLAGS_MODE_SHA224;
+		bs = SHA224_BLOCK_SIZE;
 		break;
 	case SHA256_DIGEST_SIZE:
 		ctx->flags |= FLAGS_MODE_SHA256;
+		bs = SHA256_BLOCK_SIZE;
+		break;
+	case SHA384_DIGEST_SIZE:
+		ctx->flags |= FLAGS_MODE_SHA384;
+		bs = SHA384_BLOCK_SIZE;
+		break;
+	case SHA512_DIGEST_SIZE:
+		ctx->flags |= FLAGS_MODE_SHA512;
+		bs = SHA512_BLOCK_SIZE;
 		break;
 	}
 
@@ -816,8 +878,8 @@ static int omap_sham_init(struct ahash_request *req)
 		if (!test_bit(FLAGS_AUTO_XOR, &dd->flags)) {
 			struct omap_sham_hmac_ctx *bctx = tctx->base;
 
-			memcpy(ctx->buffer, bctx->ipad, SHA1_MD5_BLOCK_SIZE);
-			ctx->bufcnt = SHA1_MD5_BLOCK_SIZE;
+			memcpy(ctx->buffer, bctx->ipad, bs);
+			ctx->bufcnt = bs;
 		}
 
 		ctx->flags |= BIT(FLAGS_HMAC);
@@ -853,8 +915,11 @@ static int omap_sham_final_req(struct omap_sham_dev *dd)
 	struct omap_sham_reqctx *ctx = ahash_request_ctx(req);
 	int err = 0, use_dma = 1;
 
-	if (ctx->bufcnt <= DMA_MIN)
-		/* faster to handle last block with cpu */
+	if ((ctx->bufcnt <= get_block_size(ctx)) || dd->polling_mode)
+		/*
+		 * faster to handle last block with cpu or
+		 * use cpu when dma is not present.
+		 */
 		use_dma = 0;
 
 	if (use_dma)
@@ -1006,6 +1071,8 @@ static int omap_sham_enqueue(struct ahash_request *req, unsigned int op)
 static int omap_sham_update(struct ahash_request *req)
 {
 	struct omap_sham_reqctx *ctx = ahash_request_ctx(req);
+	struct omap_sham_dev *dd = ctx->dd;
+	int bs = get_block_size(ctx);
 
 	if (!req->nbytes)
 		return 0;
@@ -1023,10 +1090,12 @@ static int omap_sham_update(struct ahash_request *req)
 			*/
 			omap_sham_append_sg(ctx);
 			return 0;
-		} else if (ctx->bufcnt + ctx->total <= SHA1_MD5_BLOCK_SIZE) {
+		} else if ((ctx->bufcnt + ctx->total <= bs) ||
+			   dd->polling_mode) {
 			/*
-			* faster to use CPU for short transfers
-			*/
+			 * faster to use CPU for short transfers or
+			 * use cpu when dma is not present.
+			 */
 			ctx->flags |= BIT(FLAGS_CPU);
 		}
 	} else if (ctx->bufcnt + ctx->total < ctx->buflen) {
@@ -1214,6 +1283,16 @@ static int omap_sham_cra_md5_init(struct crypto_tfm *tfm)
 	return omap_sham_cra_init_alg(tfm, "md5");
 }
 
+static int omap_sham_cra_sha384_init(struct crypto_tfm *tfm)
+{
+	return omap_sham_cra_init_alg(tfm, "sha384");
+}
+
+static int omap_sham_cra_sha512_init(struct crypto_tfm *tfm)
+{
+	return omap_sham_cra_init_alg(tfm, "sha512");
+}
+
 static void omap_sham_cra_exit(struct crypto_tfm *tfm)
 {
 	struct omap_sham_ctx *tctx = crypto_tfm_ctx(tfm);
@@ -1422,6 +1501,101 @@ static struct ahash_alg algs_sha224_sha256[] = {
 },
 };
 
+static struct ahash_alg algs_sha384_sha512[] = {
+{
+	.init		= omap_sham_init,
+	.update		= omap_sham_update,
+	.final		= omap_sham_final,
+	.finup		= omap_sham_finup,
+	.digest		= omap_sham_digest,
+	.halg.digestsize	= SHA384_DIGEST_SIZE,
+	.halg.base	= {
+		.cra_name		= "sha384",
+		.cra_driver_name	= "omap-sha384",
+		.cra_priority		= 100,
+		.cra_flags		= CRYPTO_ALG_TYPE_AHASH |
+						CRYPTO_ALG_ASYNC |
+						CRYPTO_ALG_NEED_FALLBACK,
+		.cra_blocksize		= SHA384_BLOCK_SIZE,
+		.cra_ctxsize		= sizeof(struct omap_sham_ctx),
+		.cra_alignmask		= 0,
+		.cra_module		= THIS_MODULE,
+		.cra_init		= omap_sham_cra_init,
+		.cra_exit		= omap_sham_cra_exit,
+	}
+},
+{
+	.init		= omap_sham_init,
+	.update		= omap_sham_update,
+	.final		= omap_sham_final,
+	.finup		= omap_sham_finup,
+	.digest		= omap_sham_digest,
+	.halg.digestsize	= SHA512_DIGEST_SIZE,
+	.halg.base	= {
+		.cra_name		= "sha512",
+		.cra_driver_name	= "omap-sha512",
+		.cra_priority		= 100,
+		.cra_flags		= CRYPTO_ALG_TYPE_AHASH |
+						CRYPTO_ALG_ASYNC |
+						CRYPTO_ALG_NEED_FALLBACK,
+		.cra_blocksize		= SHA512_BLOCK_SIZE,
+		.cra_ctxsize		= sizeof(struct omap_sham_ctx),
+		.cra_alignmask		= 0,
+		.cra_module		= THIS_MODULE,
+		.cra_init		= omap_sham_cra_init,
+		.cra_exit		= omap_sham_cra_exit,
+	}
+},
+{
+	.init		= omap_sham_init,
+	.update		= omap_sham_update,
+	.final		= omap_sham_final,
+	.finup		= omap_sham_finup,
+	.digest		= omap_sham_digest,
+	.setkey		= omap_sham_setkey,
+	.halg.digestsize	= SHA384_DIGEST_SIZE,
+	.halg.base	= {
+		.cra_name		= "hmac(sha384)",
+		.cra_driver_name	= "omap-hmac-sha384",
+		.cra_priority		= 100,
+		.cra_flags		= CRYPTO_ALG_TYPE_AHASH |
+						CRYPTO_ALG_ASYNC |
+						CRYPTO_ALG_NEED_FALLBACK,
+		.cra_blocksize		= SHA384_BLOCK_SIZE,
+		.cra_ctxsize		= sizeof(struct omap_sham_ctx) +
+					sizeof(struct omap_sham_hmac_ctx),
+		.cra_alignmask		= OMAP_ALIGN_MASK,
+		.cra_module		= THIS_MODULE,
+		.cra_init		= omap_sham_cra_sha384_init,
+		.cra_exit		= omap_sham_cra_exit,
+	}
+},
+{
+	.init		= omap_sham_init,
+	.update		= omap_sham_update,
+	.final		= omap_sham_final,
+	.finup		= omap_sham_finup,
+	.digest		= omap_sham_digest,
+	.setkey		= omap_sham_setkey,
+	.halg.digestsize	= SHA512_DIGEST_SIZE,
+	.halg.base	= {
+		.cra_name		= "hmac(sha512)",
+		.cra_driver_name	= "omap-hmac-sha512",
+		.cra_priority		= 100,
+		.cra_flags		= CRYPTO_ALG_TYPE_AHASH |
+						CRYPTO_ALG_ASYNC |
+						CRYPTO_ALG_NEED_FALLBACK,
+		.cra_blocksize		= SHA512_BLOCK_SIZE,
+		.cra_ctxsize		= sizeof(struct omap_sham_ctx) +
+					sizeof(struct omap_sham_hmac_ctx),
+		.cra_alignmask		= OMAP_ALIGN_MASK,
+		.cra_module		= THIS_MODULE,
+		.cra_init		= omap_sham_cra_sha512_init,
+		.cra_exit		= omap_sham_cra_exit,
+	}
+},
+};
+
 static void omap_sham_done_task(unsigned long data)
 {
 	struct omap_sham_dev *dd = (struct omap_sham_dev *)data;
@@ -1433,8 +1607,12 @@ static void omap_sham_done_task(unsigned long data)
 	}
 
 	if (test_bit(FLAGS_CPU, &dd->flags)) {
-		if (test_and_clear_bit(FLAGS_OUTPUT_READY, &dd->flags))
-			goto finish;
+		if (test_and_clear_bit(FLAGS_OUTPUT_READY, &dd->flags)) {
+			/* hash or semi-hash ready */
+			err = omap_sham_update_cpu(dd);
+			if (err != -EINPROGRESS)
+				goto finish;
+		}
 	} else if (test_bit(FLAGS_DMA_READY, &dd->flags)) {
 		if (test_and_clear_bit(FLAGS_DMA_ACTIVE, &dd->flags)) {
 			omap_sham_update_dma_stop(dd);
@@ -1548,11 +1726,54 @@ static const struct omap_sham_pdata omap_sham_pdata_omap4 = {
 	.poll_irq	= omap_sham_poll_irq_omap4,
 	.intr_hdlr	= omap_sham_irq_omap4,
 	.idigest_ofs	= 0x020,
+	.odigest_ofs	= 0x0,
 	.din_ofs	= 0x080,
 	.digcnt_ofs	= 0x040,
 	.rev_ofs	= 0x100,
 	.mask_ofs	= 0x110,
 	.sysstatus_ofs	= 0x114,
+	.mode_ofs	= 0x44,
+	.length_ofs	= 0x48,
+	.major_mask	= 0x0700,
+	.major_shift	= 8,
+	.minor_mask	= 0x003f,
+	.minor_shift	= 0,
+};
+
+static struct omap_sham_algs_info omap_sham_algs_info_omap5[] = {
+	{
+		.algs_list	= algs_sha1_md5,
+		.size		= ARRAY_SIZE(algs_sha1_md5),
+	},
+	{
+		.algs_list	= algs_sha224_sha256,
+		.size		= ARRAY_SIZE(algs_sha224_sha256),
+	},
+	{
+		.algs_list	= algs_sha384_sha512,
+		.size		= ARRAY_SIZE(algs_sha384_sha512),
+	},
+};
+
+static const struct omap_sham_pdata omap_sham_pdata_omap5 = {
+	.algs_info	= omap_sham_algs_info_omap5,
+	.algs_info_size	= ARRAY_SIZE(omap_sham_algs_info_omap5),
+	.flags		= BIT(FLAGS_AUTO_XOR),
+	.digest_size	= SHA512_DIGEST_SIZE,
+	.copy_hash	= omap_sham_copy_hash_omap4,
+	.write_ctrl	= omap_sham_write_ctrl_omap4,
+	.trigger	= omap_sham_trigger_omap4,
+	.poll_irq	= omap_sham_poll_irq_omap4,
+	.intr_hdlr	= omap_sham_irq_omap4,
+	.idigest_ofs	= 0x240,
+	.odigest_ofs	= 0x200,
+	.din_ofs	= 0x080,
+	.digcnt_ofs	= 0x280,
+	.rev_ofs	= 0x100,
+	.mask_ofs	= 0x110,
+	.sysstatus_ofs	= 0x114,
+	.mode_ofs	= 0x284,
+	.length_ofs	= 0x288,
 	.major_mask	= 0x0700,
 	.major_shift	= 8,
 	.minor_mask	= 0x003f,
@@ -1568,6 +1789,10 @@ static const struct of_device_id omap_sham_of_match[] = {
 		.compatible	= "ti,omap4-sham",
 		.data		= &omap_sham_pdata_omap4,
 	},
+	{
+		.compatible	= "ti,omap5-sham",
+		.data		= &omap_sham_pdata_omap5,
+	},
 	{},
 };
 MODULE_DEVICE_TABLE(of, omap_sham_of_match);
@@ -1667,7 +1892,7 @@ static int omap_sham_probe(struct platform_device *pdev)
 	int err, i, j;
 	u32 rev;
 
-	dd = kzalloc(sizeof(struct omap_sham_dev), GFP_KERNEL);
+	dd = devm_kzalloc(dev, sizeof(struct omap_sham_dev), GFP_KERNEL);
 	if (dd == NULL) {
 		dev_err(dev, "unable to alloc data struct.\n");
 		err = -ENOMEM;
@@ -1684,20 +1909,21 @@ static int omap_sham_probe(struct platform_device *pdev)
 	err = (dev->of_node) ? omap_sham_get_res_of(dd, dev, &res) :
 			       omap_sham_get_res_pdev(dd, pdev, &res);
 	if (err)
-		goto res_err;
+		goto data_err;
 
 	dd->io_base = devm_ioremap_resource(dev, &res);
 	if (IS_ERR(dd->io_base)) {
 		err = PTR_ERR(dd->io_base);
-		goto res_err;
+		goto data_err;
 	}
 	dd->phys_base = res.start;
 
-	err = request_irq(dd->irq, dd->pdata->intr_hdlr, IRQF_TRIGGER_LOW,
-			  dev_name(dev), dd);
+	err = devm_request_irq(dev, dd->irq, dd->pdata->intr_hdlr,
+			       IRQF_TRIGGER_NONE, dev_name(dev), dd);
 	if (err) {
-		dev_err(dev, "unable to request irq.\n");
-		goto res_err;
+		dev_err(dev, "unable to request irq %d, err = %d\n",
+			dd->irq, err);
+		goto data_err;
 	}
 
 	dma_cap_zero(mask);
@@ -1706,10 +1932,8 @@ static int omap_sham_probe(struct platform_device *pdev)
 	dd->dma_lch = dma_request_slave_channel_compat(mask, omap_dma_filter_fn,
 						       &dd->dma, dev, "rx");
 	if (!dd->dma_lch) {
-		dev_err(dev, "unable to obtain RX DMA engine channel %u\n",
-			dd->dma);
-		err = -ENXIO;
-		goto dma_err;
+		dd->polling_mode = 1;
+		dev_dbg(dev, "using polling mode instead of dma\n");
 	}
 
 	dd->flags |= dd->pdata->flags;
@@ -1747,11 +1971,6 @@ err_algs:
 					&dd->pdata->algs_info[i].algs_list[j]);
 	pm_runtime_disable(dev);
 	dma_release_channel(dd->dma_lch);
-dma_err:
-	free_irq(dd->irq, dd);
-res_err:
-	kfree(dd);
-	dd = NULL;
 data_err:
 	dev_err(dev, "initialization failed.\n");
 
@@ -1776,9 +1995,6 @@ static int omap_sham_remove(struct platform_device *pdev)
 	tasklet_kill(&dd->done_task);
 	pm_runtime_disable(&pdev->dev);
 	dma_release_channel(dd->dma_lch);
-	free_irq(dd->irq, dd);
-	kfree(dd);
-	dd = NULL;
 
 	return 0;
 }
diff --git a/drivers/crypto/sahara.c b/drivers/crypto/sahara.c
index c3dc1c04a5df..d7bb8bac36e9 100644
--- a/drivers/crypto/sahara.c
+++ b/drivers/crypto/sahara.c
@@ -417,7 +417,7 @@ static void sahara_aes_done_task(unsigned long data)
 	dev->req->base.complete(&dev->req->base, dev->error);
 }
 
-void sahara_watchdog(unsigned long data)
+static void sahara_watchdog(unsigned long data)
 {
 	struct sahara_dev *dev = (struct sahara_dev *)data;
 	unsigned int err = sahara_read(dev, SAHARA_REG_ERRSTATUS);
@@ -955,7 +955,7 @@ static int sahara_probe(struct platform_device *pdev)
 	dev->hw_link[0] = dma_alloc_coherent(&pdev->dev,
 			SAHARA_MAX_HW_LINK * sizeof(struct sahara_hw_link),
 			&dev->hw_phys_link[0], GFP_KERNEL);
-	if (!dev->hw_link) {
+	if (!dev->hw_link[0]) {
 		dev_err(&pdev->dev, "Could not allocate hw links\n");
 		err = -ENOMEM;
 		goto err_link;
diff --git a/drivers/crypto/tegra-aes.c b/drivers/crypto/tegra-aes.c
index 85ea7525fa36..2d58da972ae2 100644
--- a/drivers/crypto/tegra-aes.c
+++ b/drivers/crypto/tegra-aes.c
@@ -275,7 +275,7 @@ static int aes_start_crypt(struct tegra_aes_dev *dd, u32 in_addr, u32 out_addr,
 			value = aes_readl(dd, TEGRA_AES_INTR_STATUS);
 			eng_busy = value & TEGRA_AES_ENGINE_BUSY_FIELD;
 			icq_empty = value & TEGRA_AES_ICQ_EMPTY_FIELD;
-		} while (eng_busy & (!icq_empty));
+		} while (eng_busy && !icq_empty);
 		aes_writel(dd, cmdq[i], TEGRA_AES_ICMDQUE_WR);
 	}
 
@@ -365,7 +365,7 @@ static int aes_set_key(struct tegra_aes_dev *dd)
 		eng_busy = value & TEGRA_AES_ENGINE_BUSY_FIELD;
 		icq_empty = value & TEGRA_AES_ICQ_EMPTY_FIELD;
 		dma_busy = value & TEGRA_AES_DMA_BUSY_FIELD;
-	} while (eng_busy & (!icq_empty) & dma_busy);
+	} while (eng_busy && !icq_empty && dma_busy);
 
 	/* settable command to get key into internal registers */
 	value = CMD_SETTABLE << CMDQ_OPCODE_SHIFT |
@@ -379,7 +379,7 @@ static int aes_set_key(struct tegra_aes_dev *dd)
 		value = aes_readl(dd, TEGRA_AES_INTR_STATUS);
 		eng_busy = value & TEGRA_AES_ENGINE_BUSY_FIELD;
 		icq_empty = value & TEGRA_AES_ICQ_EMPTY_FIELD;
-	} while (eng_busy & (!icq_empty));
+	} while (eng_busy && !icq_empty);
 
 	return 0;
 }
diff --git a/drivers/crypto/ux500/hash/hash_core.c b/drivers/crypto/ux500/hash/hash_core.c
index 496ae6aae316..1c73f4fbc252 100644
--- a/drivers/crypto/ux500/hash/hash_core.c
+++ b/drivers/crypto/ux500/hash/hash_core.c
@@ -11,6 +11,8 @@
  * License terms: GNU General Public License (GPL) version 2
  */
 
+#define pr_fmt(fmt) "hashX hashX: " fmt
+
 #include <linux/clk.h>
 #include <linux/device.h>
 #include <linux/err.h>
@@ -35,8 +37,6 @@
 
 #include "hash_alg.h"
 
-#define DEV_DBG_NAME "hashX hashX:"
-
 static int hash_mode;
 module_param(hash_mode, int, 0);
 MODULE_PARM_DESC(hash_mode, "CPU or DMA mode. CPU = 0 (default), DMA = 1");
@@ -44,13 +44,13 @@ MODULE_PARM_DESC(hash_mode, "CPU or DMA mode. CPU = 0 (default), DMA = 1");
 /**
  * Pre-calculated empty message digests.
  */
-static u8 zero_message_hash_sha1[SHA1_DIGEST_SIZE] = {
+static const u8 zero_message_hash_sha1[SHA1_DIGEST_SIZE] = {
 	0xda, 0x39, 0xa3, 0xee, 0x5e, 0x6b, 0x4b, 0x0d,
 	0x32, 0x55, 0xbf, 0xef, 0x95, 0x60, 0x18, 0x90,
 	0xaf, 0xd8, 0x07, 0x09
 };
 
-static u8 zero_message_hash_sha256[SHA256_DIGEST_SIZE] = {
+static const u8 zero_message_hash_sha256[SHA256_DIGEST_SIZE] = {
 	0xe3, 0xb0, 0xc4, 0x42, 0x98, 0xfc, 0x1c, 0x14,
 	0x9a, 0xfb, 0xf4, 0xc8, 0x99, 0x6f, 0xb9, 0x24,
 	0x27, 0xae, 0x41, 0xe4, 0x64, 0x9b, 0x93, 0x4c,
@@ -58,14 +58,14 @@ static u8 zero_message_hash_sha256[SHA256_DIGEST_SIZE] = {
 };
 
 /* HMAC-SHA1, no key */
-static u8 zero_message_hmac_sha1[SHA1_DIGEST_SIZE] = {
+static const u8 zero_message_hmac_sha1[SHA1_DIGEST_SIZE] = {
 	0xfb, 0xdb, 0x1d, 0x1b, 0x18, 0xaa, 0x6c, 0x08,
 	0x32, 0x4b, 0x7d, 0x64, 0xb7, 0x1f, 0xb7, 0x63,
 	0x70, 0x69, 0x0e, 0x1d
 };
 
 /* HMAC-SHA256, no key */
-static u8 zero_message_hmac_sha256[SHA256_DIGEST_SIZE] = {
+static const u8 zero_message_hmac_sha256[SHA256_DIGEST_SIZE] = {
 	0xb6, 0x13, 0x67, 0x9a, 0x08, 0x14, 0xd9, 0xec,
 	0x77, 0x2f, 0x95, 0xd7, 0x78, 0xc3, 0x5f, 0xc5,
 	0xff, 0x16, 0x97, 0xc4, 0x93, 0x71, 0x56, 0x53,
@@ -97,7 +97,7 @@ static struct hash_driver_data	driver_data;
  *
  */
 static void hash_messagepad(struct hash_device_data *device_data,
-		const u32 *message, u8 index_bytes);
+			    const u32 *message, u8 index_bytes);
 
 /**
  * release_hash_device - Releases a previously allocated hash device.
@@ -119,7 +119,7 @@ static void release_hash_device(struct hash_device_data *device_data)
 }
 
 static void hash_dma_setup_channel(struct hash_device_data *device_data,
-				struct device *dev)
+				   struct device *dev)
 {
 	struct hash_platform_data *platform_data = dev->platform_data;
 	struct dma_slave_config conf = {
@@ -127,7 +127,7 @@ static void hash_dma_setup_channel(struct hash_device_data *device_data,
 		.dst_addr = device_data->phybase + HASH_DMA_FIFO,
 		.dst_addr_width = DMA_SLAVE_BUSWIDTH_2_BYTES,
 		.dst_maxburst = 16,
-        };
+	};
 
 	dma_cap_zero(device_data->dma.mask);
 	dma_cap_set(DMA_SLAVE, device_data->dma.mask);
@@ -135,8 +135,8 @@ static void hash_dma_setup_channel(struct hash_device_data *device_data,
 	device_data->dma.cfg_mem2hash = platform_data->mem_to_engine;
 	device_data->dma.chan_mem2hash =
 		dma_request_channel(device_data->dma.mask,
-				platform_data->dma_filter,
-				device_data->dma.cfg_mem2hash);
+				    platform_data->dma_filter,
+				    device_data->dma.cfg_mem2hash);
 
 	dmaengine_slave_config(device_data->dma.chan_mem2hash, &conf);
 
@@ -145,21 +145,21 @@ static void hash_dma_setup_channel(struct hash_device_data *device_data,
 
 static void hash_dma_callback(void *data)
 {
-	struct hash_ctx *ctx = (struct hash_ctx *) data;
+	struct hash_ctx *ctx = data;
 
 	complete(&ctx->device->dma.complete);
 }
 
 static int hash_set_dma_transfer(struct hash_ctx *ctx, struct scatterlist *sg,
-		int len, enum dma_data_direction direction)
+				 int len, enum dma_data_direction direction)
 {
 	struct dma_async_tx_descriptor *desc = NULL;
 	struct dma_chan *channel = NULL;
 	dma_cookie_t cookie;
 
 	if (direction != DMA_TO_DEVICE) {
-		dev_err(ctx->device->dev, "[%s] Invalid DMA direction",
-				__func__);
+		dev_err(ctx->device->dev, "%s: Invalid DMA direction\n",
+			__func__);
 		return -EFAULT;
 	}
 
@@ -172,20 +172,19 @@ static int hash_set_dma_transfer(struct hash_ctx *ctx, struct scatterlist *sg,
 			direction);
 
 	if (!ctx->device->dma.sg_len) {
-		dev_err(ctx->device->dev,
-				"[%s]: Could not map the sg list (TO_DEVICE)",
-				__func__);
+		dev_err(ctx->device->dev, "%s: Could not map the sg list (TO_DEVICE)\n",
+			__func__);
 		return -EFAULT;
 	}
 
-	dev_dbg(ctx->device->dev, "[%s]: Setting up DMA for buffer "
-			"(TO_DEVICE)", __func__);
+	dev_dbg(ctx->device->dev, "%s: Setting up DMA for buffer (TO_DEVICE)\n",
+		__func__);
 	desc = dmaengine_prep_slave_sg(channel,
 			ctx->device->dma.sg, ctx->device->dma.sg_len,
 			direction, DMA_CTRL_ACK | DMA_PREP_INTERRUPT);
 	if (!desc) {
 		dev_err(ctx->device->dev,
-			"[%s]: device_prep_slave_sg() failed!", __func__);
+			"%s: device_prep_slave_sg() failed!\n", __func__);
 		return -EFAULT;
 	}
 
@@ -205,17 +204,16 @@ static void hash_dma_done(struct hash_ctx *ctx)
 	chan = ctx->device->dma.chan_mem2hash;
 	dmaengine_device_control(chan, DMA_TERMINATE_ALL, 0);
 	dma_unmap_sg(chan->device->dev, ctx->device->dma.sg,
-			ctx->device->dma.sg_len, DMA_TO_DEVICE);
-
+		     ctx->device->dma.sg_len, DMA_TO_DEVICE);
 }
 
 static int hash_dma_write(struct hash_ctx *ctx,
-		struct scatterlist *sg, int len)
+			  struct scatterlist *sg, int len)
 {
 	int error = hash_set_dma_transfer(ctx, sg, len, DMA_TO_DEVICE);
 	if (error) {
-		dev_dbg(ctx->device->dev, "[%s]: hash_set_dma_transfer() "
-			"failed", __func__);
+		dev_dbg(ctx->device->dev,
+			"%s: hash_set_dma_transfer() failed\n", __func__);
 		return error;
 	}
 
@@ -245,19 +243,18 @@ static int get_empty_message_digest(
 	if (HASH_OPER_MODE_HASH == ctx->config.oper_mode) {
 		if (HASH_ALGO_SHA1 == ctx->config.algorithm) {
 			memcpy(zero_hash, &zero_message_hash_sha1[0],
-					SHA1_DIGEST_SIZE);
+			       SHA1_DIGEST_SIZE);
 			*zero_hash_size = SHA1_DIGEST_SIZE;
 			*zero_digest = true;
 		} else if (HASH_ALGO_SHA256 ==
 				ctx->config.algorithm) {
 			memcpy(zero_hash, &zero_message_hash_sha256[0],
-					SHA256_DIGEST_SIZE);
+			       SHA256_DIGEST_SIZE);
 			*zero_hash_size = SHA256_DIGEST_SIZE;
 			*zero_digest = true;
 		} else {
-			dev_err(device_data->dev, "[%s] "
-					"Incorrect algorithm!"
-					, __func__);
+			dev_err(device_data->dev, "%s: Incorrect algorithm!\n",
+				__func__);
 			ret = -EINVAL;
 			goto out;
 		}
@@ -265,25 +262,24 @@ static int get_empty_message_digest(
 		if (!ctx->keylen) {
 			if (HASH_ALGO_SHA1 == ctx->config.algorithm) {
 				memcpy(zero_hash, &zero_message_hmac_sha1[0],
-						SHA1_DIGEST_SIZE);
+				       SHA1_DIGEST_SIZE);
 				*zero_hash_size = SHA1_DIGEST_SIZE;
 				*zero_digest = true;
 			} else if (HASH_ALGO_SHA256 == ctx->config.algorithm) {
 				memcpy(zero_hash, &zero_message_hmac_sha256[0],
-						SHA256_DIGEST_SIZE);
+				       SHA256_DIGEST_SIZE);
 				*zero_hash_size = SHA256_DIGEST_SIZE;
 				*zero_digest = true;
 			} else {
-				dev_err(device_data->dev, "[%s] "
-						"Incorrect algorithm!"
-						, __func__);
+				dev_err(device_data->dev, "%s: Incorrect algorithm!\n",
+					__func__);
 				ret = -EINVAL;
 				goto out;
 			}
 		} else {
-			dev_dbg(device_data->dev, "[%s] Continue hash "
-					"calculation, since hmac key avalable",
-					__func__);
+			dev_dbg(device_data->dev,
+				"%s: Continue hash calculation, since hmac key available\n",
+				__func__);
 		}
 	}
 out:
@@ -299,9 +295,8 @@ out:
  * This function request for disabling power (regulator) and clock,
  * and could also save current hw state.
  */
-static int hash_disable_power(
-		struct hash_device_data *device_data,
-		bool			save_device_state)
+static int hash_disable_power(struct hash_device_data *device_data,
+			      bool save_device_state)
 {
 	int ret = 0;
 	struct device *dev = device_data->dev;
@@ -319,7 +314,7 @@ static int hash_disable_power(
 	clk_disable(device_data->clk);
 	ret = regulator_disable(device_data->regulator);
 	if (ret)
-		dev_err(dev, "[%s] regulator_disable() failed!", __func__);
+		dev_err(dev, "%s: regulator_disable() failed!\n", __func__);
 
 	device_data->power_state = false;
 
@@ -337,9 +332,8 @@ out:
  * This function request for enabling power (regulator) and clock,
  * and could also restore a previously saved hw state.
  */
-static int hash_enable_power(
-		struct hash_device_data *device_data,
-		bool			restore_device_state)
+static int hash_enable_power(struct hash_device_data *device_data,
+			     bool restore_device_state)
 {
 	int ret = 0;
 	struct device *dev = device_data->dev;
@@ -348,14 +342,13 @@ static int hash_enable_power(
 	if (!device_data->power_state) {
 		ret = regulator_enable(device_data->regulator);
 		if (ret) {
-			dev_err(dev, "[%s]: regulator_enable() failed!",
-					__func__);
+			dev_err(dev, "%s: regulator_enable() failed!\n",
+				__func__);
 			goto out;
 		}
 		ret = clk_enable(device_data->clk);
 		if (ret) {
-			dev_err(dev, "[%s]: clk_enable() failed!",
-					__func__);
+			dev_err(dev, "%s: clk_enable() failed!\n", __func__);
 			ret = regulator_disable(
 					device_data->regulator);
 			goto out;
@@ -366,8 +359,7 @@ static int hash_enable_power(
 	if (device_data->restore_dev_state) {
 		if (restore_device_state) {
 			device_data->restore_dev_state = false;
-			hash_resume_state(device_data,
-				&device_data->state);
+			hash_resume_state(device_data, &device_data->state);
 		}
 	}
 out:
@@ -447,7 +439,7 @@ static int hash_get_device_data(struct hash_ctx *ctx,
  * spec or due to a bug in the hw.
  */
 static void hash_hw_write_key(struct hash_device_data *device_data,
-		const u8 *key, unsigned int keylen)
+			      const u8 *key, unsigned int keylen)
 {
 	u32 word = 0;
 	int nwords = 1;
@@ -491,14 +483,14 @@ static void hash_hw_write_key(struct hash_device_data *device_data,
  * calculation.
  */
 static int init_hash_hw(struct hash_device_data *device_data,
-		struct hash_ctx *ctx)
+			struct hash_ctx *ctx)
 {
 	int ret = 0;
 
 	ret = hash_setconfiguration(device_data, &ctx->config);
 	if (ret) {
-		dev_err(device_data->dev, "[%s] hash_setconfiguration() "
-				"failed!", __func__);
+		dev_err(device_data->dev, "%s: hash_setconfiguration() failed!\n",
+			__func__);
 		return ret;
 	}
 
@@ -528,9 +520,8 @@ static int hash_get_nents(struct scatterlist *sg, int size, bool *aligned)
 		size -= sg->length;
 
 		/* hash_set_dma_transfer will align last nent */
-		if ((aligned && !IS_ALIGNED(sg->offset, HASH_DMA_ALIGN_SIZE))
-			|| (!IS_ALIGNED(sg->length, HASH_DMA_ALIGN_SIZE) &&
-				size > 0))
+		if ((aligned && !IS_ALIGNED(sg->offset, HASH_DMA_ALIGN_SIZE)) ||
+		    (!IS_ALIGNED(sg->length, HASH_DMA_ALIGN_SIZE) && size > 0))
 			aligned_data = false;
 
 		sg = sg_next(sg);
@@ -585,21 +576,17 @@ static int hash_init(struct ahash_request *req)
 		if (req->nbytes < HASH_DMA_ALIGN_SIZE) {
 			req_ctx->dma_mode = false; /* Don't use DMA */
 
-			pr_debug(DEV_DBG_NAME " [%s] DMA mode, but direct "
-					"to CPU mode for data size < %d",
-					__func__, HASH_DMA_ALIGN_SIZE);
+			pr_debug("%s: DMA mode, but direct to CPU mode for data size < %d\n",
+				 __func__, HASH_DMA_ALIGN_SIZE);
 		} else {
 			if (req->nbytes >= HASH_DMA_PERFORMANCE_MIN_SIZE &&
-					hash_dma_valid_data(req->src,
-						req->nbytes)) {
+			    hash_dma_valid_data(req->src, req->nbytes)) {
 				req_ctx->dma_mode = true;
 			} else {
 				req_ctx->dma_mode = false;
-				pr_debug(DEV_DBG_NAME " [%s] DMA mode, but use"
-						" CPU mode for datalength < %d"
-						" or non-aligned data, except "
-						"in last nent", __func__,
-						HASH_DMA_PERFORMANCE_MIN_SIZE);
+				pr_debug("%s: DMA mode, but use CPU mode for datalength < %d or non-aligned data, except in last nent\n",
+					 __func__,
+					 HASH_DMA_PERFORMANCE_MIN_SIZE);
 			}
 		}
 	}
@@ -614,9 +601,8 @@ static int hash_init(struct ahash_request *req)
  *			the HASH hardware.
  *
  */
-static void hash_processblock(
-		struct hash_device_data *device_data,
-		const u32 *message, int length)
+static void hash_processblock(struct hash_device_data *device_data,
+			      const u32 *message, int length)
 {
 	int len = length / HASH_BYTES_PER_WORD;
 	/*
@@ -641,7 +627,7 @@ static void hash_processblock(
  *
  */
 static void hash_messagepad(struct hash_device_data *device_data,
-		const u32 *message, u8 index_bytes)
+			    const u32 *message, u8 index_bytes)
 {
 	int nwords = 1;
 
@@ -666,15 +652,13 @@ static void hash_messagepad(struct hash_device_data *device_data,
 
 	/* num_of_bytes == 0 => NBLW <- 0 (32 bits valid in DATAIN) */
 	HASH_SET_NBLW(index_bytes * 8);
-	dev_dbg(device_data->dev, "[%s] DIN=0x%08x NBLW=%d", __func__,
-			readl_relaxed(&device_data->base->din),
-			(int)(readl_relaxed(&device_data->base->str) &
-				HASH_STR_NBLW_MASK));
+	dev_dbg(device_data->dev, "%s: DIN=0x%08x NBLW=%lu\n",
+		__func__, readl_relaxed(&device_data->base->din),
+		readl_relaxed(&device_data->base->str) & HASH_STR_NBLW_MASK);
 	HASH_SET_DCAL;
-	dev_dbg(device_data->dev, "[%s] after dcal -> DIN=0x%08x NBLW=%d",
-			__func__, readl_relaxed(&device_data->base->din),
-			(int)(readl_relaxed(&device_data->base->str) &
-				HASH_STR_NBLW_MASK));
+	dev_dbg(device_data->dev, "%s: after dcal -> DIN=0x%08x NBLW=%lu\n",
+		__func__, readl_relaxed(&device_data->base->din),
+		readl_relaxed(&device_data->base->str) & HASH_STR_NBLW_MASK);
 
 	while (readl(&device_data->base->str) & HASH_STR_DCAL_MASK)
 		cpu_relax();
@@ -704,7 +688,7 @@ static void hash_incrementlength(struct hash_req_ctx *ctx, u32 incr)
  * @config:		Pointer to a configuration structure.
  */
 int hash_setconfiguration(struct hash_device_data *device_data,
-		struct hash_config *config)
+			  struct hash_config *config)
 {
 	int ret = 0;
 
@@ -731,8 +715,8 @@ int hash_setconfiguration(struct hash_device_data *device_data,
 		break;
 
 	default:
-		dev_err(device_data->dev, "[%s] Incorrect algorithm.",
-				__func__);
+		dev_err(device_data->dev, "%s: Incorrect algorithm\n",
+			__func__);
 		return -EPERM;
 	}
 
@@ -744,23 +728,22 @@ int hash_setconfiguration(struct hash_device_data *device_data,
 		HASH_CLEAR_BITS(&device_data->base->cr,
 				HASH_CR_MODE_MASK);
 	else if (HASH_OPER_MODE_HMAC == config->oper_mode) {
-		HASH_SET_BITS(&device_data->base->cr,
-				HASH_CR_MODE_MASK);
+		HASH_SET_BITS(&device_data->base->cr, HASH_CR_MODE_MASK);
 		if (device_data->current_ctx->keylen > HASH_BLOCK_SIZE) {
 			/* Truncate key to blocksize */
-			dev_dbg(device_data->dev, "[%s] LKEY set", __func__);
+			dev_dbg(device_data->dev, "%s: LKEY set\n", __func__);
 			HASH_SET_BITS(&device_data->base->cr,
-					HASH_CR_LKEY_MASK);
+				      HASH_CR_LKEY_MASK);
 		} else {
-			dev_dbg(device_data->dev, "[%s] LKEY cleared",
-					__func__);
+			dev_dbg(device_data->dev, "%s: LKEY cleared\n",
+				__func__);
 			HASH_CLEAR_BITS(&device_data->base->cr,
 					HASH_CR_LKEY_MASK);
 		}
 	} else {	/* Wrong hash mode */
 		ret = -EPERM;
-		dev_err(device_data->dev, "[%s] HASH_INVALID_PARAMETER!",
-				__func__);
+		dev_err(device_data->dev, "%s: HASH_INVALID_PARAMETER!\n",
+			__func__);
 	}
 	return ret;
 }
@@ -793,8 +776,9 @@ void hash_begin(struct hash_device_data *device_data, struct hash_ctx *ctx)
 }
 
 static int hash_process_data(struct hash_device_data *device_data,
-		struct hash_ctx *ctx, struct hash_req_ctx *req_ctx,
-		int msg_length, u8 *data_buffer, u8 *buffer, u8 *index)
+			     struct hash_ctx *ctx, struct hash_req_ctx *req_ctx,
+			     int msg_length, u8 *data_buffer, u8 *buffer,
+			     u8 *index)
 {
 	int ret = 0;
 	u32 count;
@@ -809,24 +793,23 @@ static int hash_process_data(struct hash_device_data *device_data,
 			msg_length = 0;
 		} else {
 			if (req_ctx->updated) {
-
 				ret = hash_resume_state(device_data,
 						&device_data->state);
 				memmove(req_ctx->state.buffer,
-						device_data->state.buffer,
-						HASH_BLOCK_SIZE / sizeof(u32));
+					device_data->state.buffer,
+					HASH_BLOCK_SIZE / sizeof(u32));
 				if (ret) {
-					dev_err(device_data->dev, "[%s] "
-							"hash_resume_state()"
-							" failed!", __func__);
+					dev_err(device_data->dev,
+						"%s: hash_resume_state() failed!\n",
+						__func__);
 					goto out;
 				}
 			} else {
 				ret = init_hash_hw(device_data, ctx);
 				if (ret) {
-					dev_err(device_data->dev, "[%s] "
-							"init_hash_hw()"
-							" failed!", __func__);
+					dev_err(device_data->dev,
+						"%s: init_hash_hw() failed!\n",
+						__func__);
 					goto out;
 				}
 				req_ctx->updated = 1;
@@ -838,22 +821,21 @@ static int hash_process_data(struct hash_device_data *device_data,
 			 * HW peripheral, otherwise we first copy data
 			 * to a local buffer
 			 */
-			if ((0 == (((u32)data_buffer) % 4))
-					&& (0 == *index))
+			if ((0 == (((u32)data_buffer) % 4)) &&
+			    (0 == *index))
 				hash_processblock(device_data,
-						(const u32 *)
-						data_buffer, HASH_BLOCK_SIZE);
+						  (const u32 *)data_buffer,
+						  HASH_BLOCK_SIZE);
 			else {
-				for (count = 0; count <
-						(u32)(HASH_BLOCK_SIZE -
-							*index);
-						count++) {
+				for (count = 0;
+				     count < (u32)(HASH_BLOCK_SIZE - *index);
+				     count++) {
 					buffer[*index + count] =
 						*(data_buffer + count);
 				}
 				hash_processblock(device_data,
-						(const u32 *)buffer,
-						HASH_BLOCK_SIZE);
+						  (const u32 *)buffer,
+						  HASH_BLOCK_SIZE);
 			}
 			hash_incrementlength(req_ctx, HASH_BLOCK_SIZE);
 			data_buffer += (HASH_BLOCK_SIZE - *index);
@@ -865,12 +847,11 @@ static int hash_process_data(struct hash_device_data *device_data,
 					&device_data->state);
 
 			memmove(device_data->state.buffer,
-					req_ctx->state.buffer,
-					HASH_BLOCK_SIZE / sizeof(u32));
+				req_ctx->state.buffer,
+				HASH_BLOCK_SIZE / sizeof(u32));
 			if (ret) {
-				dev_err(device_data->dev, "[%s] "
-						"hash_save_state()"
-						" failed!", __func__);
+				dev_err(device_data->dev, "%s: hash_save_state() failed!\n",
+					__func__);
 				goto out;
 			}
 		}
@@ -898,25 +879,24 @@ static int hash_dma_final(struct ahash_request *req)
 	if (ret)
 		return ret;
 
-	dev_dbg(device_data->dev, "[%s] (ctx=0x%x)!", __func__, (u32) ctx);
+	dev_dbg(device_data->dev, "%s: (ctx=0x%x)!\n", __func__, (u32) ctx);
 
 	if (req_ctx->updated) {
 		ret = hash_resume_state(device_data, &device_data->state);
 
 		if (ret) {
-			dev_err(device_data->dev, "[%s] hash_resume_state() "
-					"failed!", __func__);
+			dev_err(device_data->dev, "%s: hash_resume_state() failed!\n",
+				__func__);
 			goto out;
 		}
-
 	}
 
 	if (!req_ctx->updated) {
 		ret = hash_setconfiguration(device_data, &ctx->config);
 		if (ret) {
-			dev_err(device_data->dev, "[%s] "
-					"hash_setconfiguration() failed!",
-					__func__);
+			dev_err(device_data->dev,
+				"%s: hash_setconfiguration() failed!\n",
+				__func__);
 			goto out;
 		}
 
@@ -926,9 +906,9 @@ static int hash_dma_final(struct ahash_request *req)
 					HASH_CR_DMAE_MASK);
 		} else {
 			HASH_SET_BITS(&device_data->base->cr,
-					HASH_CR_DMAE_MASK);
+				      HASH_CR_DMAE_MASK);
 			HASH_SET_BITS(&device_data->base->cr,
-					HASH_CR_PRIVN_MASK);
+				      HASH_CR_PRIVN_MASK);
 		}
 
 		HASH_INITIALIZE;
@@ -944,16 +924,16 @@ static int hash_dma_final(struct ahash_request *req)
 	/* Store the nents in the dma struct. */
 	ctx->device->dma.nents = hash_get_nents(req->src, req->nbytes, NULL);
 	if (!ctx->device->dma.nents) {
-		dev_err(device_data->dev, "[%s] "
-				"ctx->device->dma.nents = 0", __func__);
+		dev_err(device_data->dev, "%s: ctx->device->dma.nents = 0\n",
+			__func__);
 		ret = ctx->device->dma.nents;
 		goto out;
 	}
 
 	bytes_written = hash_dma_write(ctx, req->src, req->nbytes);
 	if (bytes_written != req->nbytes) {
-		dev_err(device_data->dev, "[%s] "
-				"hash_dma_write() failed!", __func__);
+		dev_err(device_data->dev, "%s: hash_dma_write() failed!\n",
+			__func__);
 		ret = bytes_written;
 		goto out;
 	}
@@ -968,8 +948,8 @@ static int hash_dma_final(struct ahash_request *req)
 		unsigned int keylen = ctx->keylen;
 		u8 *key = ctx->key;
 
-		dev_dbg(device_data->dev, "[%s] keylen: %d", __func__,
-				ctx->keylen);
+		dev_dbg(device_data->dev, "%s: keylen: %d\n",
+			__func__, ctx->keylen);
 		hash_hw_write_key(device_data, key, keylen);
 	}
 
@@ -1004,14 +984,14 @@ static int hash_hw_final(struct ahash_request *req)
 	if (ret)
 		return ret;
 
-	dev_dbg(device_data->dev, "[%s] (ctx=0x%x)!", __func__, (u32) ctx);
+	dev_dbg(device_data->dev, "%s: (ctx=0x%x)!\n", __func__, (u32) ctx);
 
 	if (req_ctx->updated) {
 		ret = hash_resume_state(device_data, &device_data->state);
 
 		if (ret) {
-			dev_err(device_data->dev, "[%s] hash_resume_state() "
-					"failed!", __func__);
+			dev_err(device_data->dev,
+				"%s: hash_resume_state() failed!\n", __func__);
 			goto out;
 		}
 	} else if (req->nbytes == 0 && ctx->keylen == 0) {
@@ -1025,31 +1005,33 @@ static int hash_hw_final(struct ahash_request *req)
 		ret = get_empty_message_digest(device_data, &zero_hash[0],
 				&zero_hash_size, &zero_digest);
 		if (!ret && likely(zero_hash_size == ctx->digestsize) &&
-				zero_digest) {
+		    zero_digest) {
 			memcpy(req->result, &zero_hash[0], ctx->digestsize);
 			goto out;
 		} else if (!ret && !zero_digest) {
-			dev_dbg(device_data->dev, "[%s] HMAC zero msg with "
-					"key, continue...", __func__);
+			dev_dbg(device_data->dev,
+				"%s: HMAC zero msg with key, continue...\n",
+				__func__);
 		} else {
-			dev_err(device_data->dev, "[%s] ret=%d, or wrong "
-					"digest size? %s", __func__, ret,
-					(zero_hash_size == ctx->digestsize) ?
-					"true" : "false");
+			dev_err(device_data->dev,
+				"%s: ret=%d, or wrong digest size? %s\n",
+				__func__, ret,
+				zero_hash_size == ctx->digestsize ?
+				"true" : "false");
 			/* Return error */
 			goto out;
 		}
 	} else if (req->nbytes == 0 && ctx->keylen > 0) {
-		dev_err(device_data->dev, "[%s] Empty message with "
-				"keylength > 0, NOT supported.", __func__);
+		dev_err(device_data->dev, "%s: Empty message with keylength > 0, NOT supported\n",
+			__func__);
 		goto out;
 	}
 
 	if (!req_ctx->updated) {
 		ret = init_hash_hw(device_data, ctx);
 		if (ret) {
-			dev_err(device_data->dev, "[%s] init_hash_hw() "
-					"failed!", __func__);
+			dev_err(device_data->dev,
+				"%s: init_hash_hw() failed!\n", __func__);
 			goto out;
 		}
 	}
@@ -1067,8 +1049,8 @@ static int hash_hw_final(struct ahash_request *req)
 		unsigned int keylen = ctx->keylen;
 		u8 *key = ctx->key;
 
-		dev_dbg(device_data->dev, "[%s] keylen: %d", __func__,
-				ctx->keylen);
+		dev_dbg(device_data->dev, "%s: keylen: %d\n",
+			__func__, ctx->keylen);
 		hash_hw_write_key(device_data, key, keylen);
 	}
 
@@ -1115,10 +1097,8 @@ int hash_hw_update(struct ahash_request *req)
 	/* Check if ctx->state.length + msg_length
 	   overflows */
 	if (msg_length > (req_ctx->state.length.low_word + msg_length) &&
-			HASH_HIGH_WORD_MAX_VAL ==
-			req_ctx->state.length.high_word) {
-		pr_err(DEV_DBG_NAME " [%s] HASH_MSG_LENGTH_OVERFLOW!",
-				__func__);
+	    HASH_HIGH_WORD_MAX_VAL == req_ctx->state.length.high_word) {
+		pr_err("%s: HASH_MSG_LENGTH_OVERFLOW!\n", __func__);
 		return -EPERM;
 	}
 
@@ -1133,8 +1113,8 @@ int hash_hw_update(struct ahash_request *req)
 				data_buffer, buffer, &index);
 
 		if (ret) {
-			dev_err(device_data->dev, "[%s] hash_internal_hw_"
-					"update() failed!", __func__);
+			dev_err(device_data->dev, "%s: hash_internal_hw_update() failed!\n",
+				__func__);
 			goto out;
 		}
 
@@ -1142,9 +1122,8 @@ int hash_hw_update(struct ahash_request *req)
 	}
 
 	req_ctx->state.index = index;
-	dev_dbg(device_data->dev, "[%s] indata length=%d, bin=%d))",
-			__func__, req_ctx->state.index,
-			req_ctx->state.bit_index);
+	dev_dbg(device_data->dev, "%s: indata length=%d, bin=%d\n",
+		__func__, req_ctx->state.index, req_ctx->state.bit_index);
 
 out:
 	release_hash_device(device_data);
@@ -1158,23 +1137,23 @@ out:
  * @device_state:	The state to be restored in the hash hardware
  */
 int hash_resume_state(struct hash_device_data *device_data,
-		const struct hash_state *device_state)
+		      const struct hash_state *device_state)
 {
 	u32 temp_cr;
 	s32 count;
 	int hash_mode = HASH_OPER_MODE_HASH;
 
 	if (NULL == device_state) {
-		dev_err(device_data->dev, "[%s] HASH_INVALID_PARAMETER!",
-				__func__);
+		dev_err(device_data->dev, "%s: HASH_INVALID_PARAMETER!\n",
+			__func__);
 		return -EPERM;
 	}
 
 	/* Check correctness of index and length members */
-	if (device_state->index > HASH_BLOCK_SIZE
-	    || (device_state->length.low_word % HASH_BLOCK_SIZE) != 0) {
-		dev_err(device_data->dev, "[%s] HASH_INVALID_PARAMETER!",
-				__func__);
+	if (device_state->index > HASH_BLOCK_SIZE ||
+	    (device_state->length.low_word % HASH_BLOCK_SIZE) != 0) {
+		dev_err(device_data->dev, "%s: HASH_INVALID_PARAMETER!\n",
+			__func__);
 		return -EPERM;
 	}
 
@@ -1198,7 +1177,7 @@ int hash_resume_state(struct hash_device_data *device_data,
 			break;
 
 		writel_relaxed(device_state->csr[count],
-				&device_data->base->csrx[count]);
+			       &device_data->base->csrx[count]);
 	}
 
 	writel_relaxed(device_state->csfull, &device_data->base->csfull);
@@ -1216,15 +1195,15 @@ int hash_resume_state(struct hash_device_data *device_data,
  * @device_state:	The strucure where the hardware state should be saved.
  */
 int hash_save_state(struct hash_device_data *device_data,
-		struct hash_state *device_state)
+		    struct hash_state *device_state)
 {
 	u32 temp_cr;
 	u32 count;
 	int hash_mode = HASH_OPER_MODE_HASH;
 
 	if (NULL == device_state) {
-		dev_err(device_data->dev, "[%s] HASH_INVALID_PARAMETER!",
-				__func__);
+		dev_err(device_data->dev, "%s: HASH_INVALID_PARAMETER!\n",
+			__func__);
 		return -ENOTSUPP;
 	}
 
@@ -1270,20 +1249,18 @@ int hash_save_state(struct hash_device_data *device_data,
 int hash_check_hw(struct hash_device_data *device_data)
 {
 	/* Checking Peripheral Ids  */
-	if (HASH_P_ID0 == readl_relaxed(&device_data->base->periphid0)
-		&& HASH_P_ID1 == readl_relaxed(&device_data->base->periphid1)
-		&& HASH_P_ID2 == readl_relaxed(&device_data->base->periphid2)
-		&& HASH_P_ID3 == readl_relaxed(&device_data->base->periphid3)
-		&& HASH_CELL_ID0 == readl_relaxed(&device_data->base->cellid0)
-		&& HASH_CELL_ID1 == readl_relaxed(&device_data->base->cellid1)
-		&& HASH_CELL_ID2 == readl_relaxed(&device_data->base->cellid2)
-		&& HASH_CELL_ID3 == readl_relaxed(&device_data->base->cellid3)
-	   ) {
+	if (HASH_P_ID0 == readl_relaxed(&device_data->base->periphid0) &&
+	    HASH_P_ID1 == readl_relaxed(&device_data->base->periphid1) &&
+	    HASH_P_ID2 == readl_relaxed(&device_data->base->periphid2) &&
+	    HASH_P_ID3 == readl_relaxed(&device_data->base->periphid3) &&
+	    HASH_CELL_ID0 == readl_relaxed(&device_data->base->cellid0) &&
+	    HASH_CELL_ID1 == readl_relaxed(&device_data->base->cellid1) &&
+	    HASH_CELL_ID2 == readl_relaxed(&device_data->base->cellid2) &&
+	    HASH_CELL_ID3 == readl_relaxed(&device_data->base->cellid3)) {
 		return 0;
 	}
 
-	dev_err(device_data->dev, "[%s] HASH_UNSUPPORTED_HW!",
-			__func__);
+	dev_err(device_data->dev, "%s: HASH_UNSUPPORTED_HW!\n", __func__);
 	return -ENOTSUPP;
 }
 
@@ -1294,14 +1271,14 @@ int hash_check_hw(struct hash_device_data *device_data)
  * @algorithm:		The algorithm in use.
  */
 void hash_get_digest(struct hash_device_data *device_data,
-		u8 *digest, int algorithm)
+		     u8 *digest, int algorithm)
 {
 	u32 temp_hx_val, count;
 	int loop_ctr;
 
 	if (algorithm != HASH_ALGO_SHA1 && algorithm != HASH_ALGO_SHA256) {
-		dev_err(device_data->dev, "[%s] Incorrect algorithm %d",
-				__func__, algorithm);
+		dev_err(device_data->dev, "%s: Incorrect algorithm %d\n",
+			__func__, algorithm);
 		return;
 	}
 
@@ -1310,8 +1287,8 @@ void hash_get_digest(struct hash_device_data *device_data,
 	else
 		loop_ctr = SHA256_DIGEST_SIZE / sizeof(u32);
 
-	dev_dbg(device_data->dev, "[%s] digest array:(0x%x)",
-			__func__, (u32) digest);
+	dev_dbg(device_data->dev, "%s: digest array:(0x%x)\n",
+		__func__, (u32) digest);
 
 	/* Copy result into digest array */
 	for (count = 0; count < loop_ctr; count++) {
@@ -1337,8 +1314,7 @@ static int ahash_update(struct ahash_request *req)
 	/* Skip update for DMA, all data will be passed to DMA in final */
 
 	if (ret) {
-		pr_err(DEV_DBG_NAME " [%s] hash_hw_update() failed!",
-				__func__);
+		pr_err("%s: hash_hw_update() failed!\n", __func__);
 	}
 
 	return ret;
@@ -1353,7 +1329,7 @@ static int ahash_final(struct ahash_request *req)
 	int ret = 0;
 	struct hash_req_ctx *req_ctx = ahash_request_ctx(req);
 
-	pr_debug(DEV_DBG_NAME " [%s] data size: %d", __func__, req->nbytes);
+	pr_debug("%s: data size: %d\n", __func__, req->nbytes);
 
 	if ((hash_mode == HASH_MODE_DMA) && req_ctx->dma_mode)
 		ret = hash_dma_final(req);
@@ -1361,15 +1337,14 @@ static int ahash_final(struct ahash_request *req)
 		ret = hash_hw_final(req);
 
 	if (ret) {
-		pr_err(DEV_DBG_NAME " [%s] hash_hw/dma_final() failed",
-				__func__);
+		pr_err("%s: hash_hw/dma_final() failed\n", __func__);
 	}
 
 	return ret;
 }
 
 static int hash_setkey(struct crypto_ahash *tfm,
-		const u8 *key, unsigned int keylen, int alg)
+		       const u8 *key, unsigned int keylen, int alg)
 {
 	int ret = 0;
 	struct hash_ctx *ctx = crypto_ahash_ctx(tfm);
@@ -1379,8 +1354,8 @@ static int hash_setkey(struct crypto_ahash *tfm,
 	 */
 	ctx->key = kmemdup(key, keylen, GFP_KERNEL);
 	if (!ctx->key) {
-		pr_err(DEV_DBG_NAME " [%s] Failed to allocate ctx->key "
-		       "for %d\n", __func__, alg);
+		pr_err("%s: Failed to allocate ctx->key for %d\n",
+		       __func__, alg);
 		return -ENOMEM;
 	}
 	ctx->keylen = keylen;
@@ -1501,13 +1476,13 @@ out:
 }
 
 static int hmac_sha1_setkey(struct crypto_ahash *tfm,
-		const u8 *key, unsigned int keylen)
+			    const u8 *key, unsigned int keylen)
 {
 	return hash_setkey(tfm, key, keylen, HASH_ALGO_SHA1);
 }
 
 static int hmac_sha256_setkey(struct crypto_ahash *tfm,
-		const u8 *key, unsigned int keylen)
+			      const u8 *key, unsigned int keylen)
 {
 	return hash_setkey(tfm, key, keylen, HASH_ALGO_SHA256);
 }
@@ -1528,7 +1503,7 @@ static int hash_cra_init(struct crypto_tfm *tfm)
 			hash);
 
 	crypto_ahash_set_reqsize(__crypto_ahash_cast(tfm),
-			sizeof(struct hash_req_ctx));
+				 sizeof(struct hash_req_ctx));
 
 	ctx->config.data_format = HASH_DATA_8_BITS;
 	ctx->config.algorithm = hash_alg->conf.algorithm;
@@ -1541,98 +1516,97 @@ static int hash_cra_init(struct crypto_tfm *tfm)
 
 static struct hash_algo_template hash_algs[] = {
 	{
-			.conf.algorithm	= HASH_ALGO_SHA1,
-			.conf.oper_mode	= HASH_OPER_MODE_HASH,
-			.hash = {
-				.init = hash_init,
-				.update = ahash_update,
-				.final = ahash_final,
-				.digest = ahash_sha1_digest,
-				.halg.digestsize = SHA1_DIGEST_SIZE,
-				.halg.statesize = sizeof(struct hash_ctx),
-				.halg.base = {
-					.cra_name = "sha1",
-					.cra_driver_name = "sha1-ux500",
-					.cra_flags = CRYPTO_ALG_TYPE_AHASH |
-							CRYPTO_ALG_ASYNC,
-					.cra_blocksize = SHA1_BLOCK_SIZE,
-					.cra_ctxsize = sizeof(struct hash_ctx),
-					.cra_init = hash_cra_init,
-					.cra_module = THIS_MODULE,
+		.conf.algorithm = HASH_ALGO_SHA1,
+		.conf.oper_mode = HASH_OPER_MODE_HASH,
+		.hash = {
+			.init = hash_init,
+			.update = ahash_update,
+			.final = ahash_final,
+			.digest = ahash_sha1_digest,
+			.halg.digestsize = SHA1_DIGEST_SIZE,
+			.halg.statesize = sizeof(struct hash_ctx),
+			.halg.base = {
+				.cra_name = "sha1",
+				.cra_driver_name = "sha1-ux500",
+				.cra_flags = (CRYPTO_ALG_TYPE_AHASH |
+					      CRYPTO_ALG_ASYNC),
+				.cra_blocksize = SHA1_BLOCK_SIZE,
+				.cra_ctxsize = sizeof(struct hash_ctx),
+				.cra_init = hash_cra_init,
+				.cra_module = THIS_MODULE,
 			}
 		}
 	},
 	{
-			.conf.algorithm		= HASH_ALGO_SHA256,
-			.conf.oper_mode		= HASH_OPER_MODE_HASH,
-			.hash = {
-				.init = hash_init,
-				.update	= ahash_update,
-				.final = ahash_final,
-				.digest = ahash_sha256_digest,
-				.halg.digestsize = SHA256_DIGEST_SIZE,
-				.halg.statesize = sizeof(struct hash_ctx),
-				.halg.base = {
-					.cra_name = "sha256",
-					.cra_driver_name = "sha256-ux500",
-					.cra_flags = CRYPTO_ALG_TYPE_AHASH |
-							CRYPTO_ALG_ASYNC,
-					.cra_blocksize = SHA256_BLOCK_SIZE,
-					.cra_ctxsize = sizeof(struct hash_ctx),
-					.cra_type = &crypto_ahash_type,
-					.cra_init = hash_cra_init,
-					.cra_module = THIS_MODULE,
-				}
+		.conf.algorithm	= HASH_ALGO_SHA256,
+		.conf.oper_mode	= HASH_OPER_MODE_HASH,
+		.hash = {
+			.init = hash_init,
+			.update	= ahash_update,
+			.final = ahash_final,
+			.digest = ahash_sha256_digest,
+			.halg.digestsize = SHA256_DIGEST_SIZE,
+			.halg.statesize = sizeof(struct hash_ctx),
+			.halg.base = {
+				.cra_name = "sha256",
+				.cra_driver_name = "sha256-ux500",
+				.cra_flags = (CRYPTO_ALG_TYPE_AHASH |
+					      CRYPTO_ALG_ASYNC),
+				.cra_blocksize = SHA256_BLOCK_SIZE,
+				.cra_ctxsize = sizeof(struct hash_ctx),
+				.cra_type = &crypto_ahash_type,
+				.cra_init = hash_cra_init,
+				.cra_module = THIS_MODULE,
 			}
-
+		}
 	},
 	{
-			.conf.algorithm		= HASH_ALGO_SHA1,
-			.conf.oper_mode		= HASH_OPER_MODE_HMAC,
+		.conf.algorithm = HASH_ALGO_SHA1,
+		.conf.oper_mode = HASH_OPER_MODE_HMAC,
 			.hash = {
-				.init = hash_init,
-				.update = ahash_update,
-				.final = ahash_final,
-				.digest = hmac_sha1_digest,
-				.setkey = hmac_sha1_setkey,
-				.halg.digestsize = SHA1_DIGEST_SIZE,
-				.halg.statesize = sizeof(struct hash_ctx),
-				.halg.base = {
-					.cra_name = "hmac(sha1)",
-					.cra_driver_name = "hmac-sha1-ux500",
-					.cra_flags = CRYPTO_ALG_TYPE_AHASH |
-							CRYPTO_ALG_ASYNC,
-					.cra_blocksize = SHA1_BLOCK_SIZE,
-					.cra_ctxsize = sizeof(struct hash_ctx),
-					.cra_type = &crypto_ahash_type,
-					.cra_init = hash_cra_init,
-					.cra_module = THIS_MODULE,
-				}
+			.init = hash_init,
+			.update = ahash_update,
+			.final = ahash_final,
+			.digest = hmac_sha1_digest,
+			.setkey = hmac_sha1_setkey,
+			.halg.digestsize = SHA1_DIGEST_SIZE,
+			.halg.statesize = sizeof(struct hash_ctx),
+			.halg.base = {
+				.cra_name = "hmac(sha1)",
+				.cra_driver_name = "hmac-sha1-ux500",
+				.cra_flags = (CRYPTO_ALG_TYPE_AHASH |
+					      CRYPTO_ALG_ASYNC),
+				.cra_blocksize = SHA1_BLOCK_SIZE,
+				.cra_ctxsize = sizeof(struct hash_ctx),
+				.cra_type = &crypto_ahash_type,
+				.cra_init = hash_cra_init,
+				.cra_module = THIS_MODULE,
 			}
+		}
 	},
 	{
-			.conf.algorithm		= HASH_ALGO_SHA256,
-			.conf.oper_mode		= HASH_OPER_MODE_HMAC,
-			.hash = {
-				.init = hash_init,
-				.update = ahash_update,
-				.final = ahash_final,
-				.digest = hmac_sha256_digest,
-				.setkey = hmac_sha256_setkey,
-				.halg.digestsize = SHA256_DIGEST_SIZE,
-				.halg.statesize = sizeof(struct hash_ctx),
-				.halg.base = {
-					.cra_name = "hmac(sha256)",
-					.cra_driver_name = "hmac-sha256-ux500",
-					.cra_flags = CRYPTO_ALG_TYPE_AHASH |
-							CRYPTO_ALG_ASYNC,
-					.cra_blocksize = SHA256_BLOCK_SIZE,
-					.cra_ctxsize = sizeof(struct hash_ctx),
-					.cra_type = &crypto_ahash_type,
-					.cra_init = hash_cra_init,
-					.cra_module = THIS_MODULE,
-				}
+		.conf.algorithm = HASH_ALGO_SHA256,
+		.conf.oper_mode = HASH_OPER_MODE_HMAC,
+		.hash = {
+			.init = hash_init,
+			.update = ahash_update,
+			.final = ahash_final,
+			.digest = hmac_sha256_digest,
+			.setkey = hmac_sha256_setkey,
+			.halg.digestsize = SHA256_DIGEST_SIZE,
+			.halg.statesize = sizeof(struct hash_ctx),
+			.halg.base = {
+				.cra_name = "hmac(sha256)",
+				.cra_driver_name = "hmac-sha256-ux500",
+				.cra_flags = (CRYPTO_ALG_TYPE_AHASH |
+					      CRYPTO_ALG_ASYNC),
+				.cra_blocksize = SHA256_BLOCK_SIZE,
+				.cra_ctxsize = sizeof(struct hash_ctx),
+				.cra_type = &crypto_ahash_type,
+				.cra_init = hash_cra_init,
+				.cra_module = THIS_MODULE,
 			}
+		}
 	}
 };
 
@@ -1649,7 +1623,7 @@ static int ahash_algs_register_all(struct hash_device_data *device_data)
 		ret = crypto_register_ahash(&hash_algs[i].hash);
 		if (ret) {
 			count = i;
-			dev_err(device_data->dev, "[%s] alg registration failed",
+			dev_err(device_data->dev, "%s: alg registration failed\n",
 				hash_algs[i].hash.halg.base.cra_driver_name);
 			goto unreg;
 		}
@@ -1683,9 +1657,8 @@ static int ux500_hash_probe(struct platform_device *pdev)
 	struct hash_device_data *device_data;
 	struct device		*dev = &pdev->dev;
 
-	device_data = kzalloc(sizeof(struct hash_device_data), GFP_ATOMIC);
+	device_data = kzalloc(sizeof(*device_data), GFP_ATOMIC);
 	if (!device_data) {
-		dev_dbg(dev, "[%s] kzalloc() failed!", __func__);
 		ret = -ENOMEM;
 		goto out;
 	}
@@ -1695,14 +1668,14 @@ static int ux500_hash_probe(struct platform_device *pdev)
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	if (!res) {
-		dev_dbg(dev, "[%s] platform_get_resource() failed!", __func__);
+		dev_dbg(dev, "%s: platform_get_resource() failed!\n", __func__);
 		ret = -ENODEV;
 		goto out_kfree;
 	}
 
 	res = request_mem_region(res->start, resource_size(res), pdev->name);
 	if (res == NULL) {
-		dev_dbg(dev, "[%s] request_mem_region() failed!", __func__);
+		dev_dbg(dev, "%s: request_mem_region() failed!\n", __func__);
 		ret = -EBUSY;
 		goto out_kfree;
 	}
@@ -1710,8 +1683,7 @@ static int ux500_hash_probe(struct platform_device *pdev)
 	device_data->phybase = res->start;
 	device_data->base = ioremap(res->start, resource_size(res));
 	if (!device_data->base) {
-		dev_err(dev, "[%s] ioremap() failed!",
-				__func__);
+		dev_err(dev, "%s: ioremap() failed!\n", __func__);
 		ret = -ENOMEM;
 		goto out_free_mem;
 	}
@@ -1721,7 +1693,7 @@ static int ux500_hash_probe(struct platform_device *pdev)
 	/* Enable power for HASH1 hardware block */
 	device_data->regulator = regulator_get(dev, "v-ape");
 	if (IS_ERR(device_data->regulator)) {
-		dev_err(dev, "[%s] regulator_get() failed!", __func__);
+		dev_err(dev, "%s: regulator_get() failed!\n", __func__);
 		ret = PTR_ERR(device_data->regulator);
 		device_data->regulator = NULL;
 		goto out_unmap;
@@ -1730,27 +1702,27 @@ static int ux500_hash_probe(struct platform_device *pdev)
 	/* Enable the clock for HASH1 hardware block */
 	device_data->clk = clk_get(dev, NULL);
 	if (IS_ERR(device_data->clk)) {
-		dev_err(dev, "[%s] clk_get() failed!", __func__);
+		dev_err(dev, "%s: clk_get() failed!\n", __func__);
 		ret = PTR_ERR(device_data->clk);
 		goto out_regulator;
 	}
 
 	ret = clk_prepare(device_data->clk);
 	if (ret) {
-		dev_err(dev, "[%s] clk_prepare() failed!", __func__);
+		dev_err(dev, "%s: clk_prepare() failed!\n", __func__);
 		goto out_clk;
 	}
 
 	/* Enable device power (and clock) */
 	ret = hash_enable_power(device_data, false);
 	if (ret) {
-		dev_err(dev, "[%s]: hash_enable_power() failed!", __func__);
+		dev_err(dev, "%s: hash_enable_power() failed!\n", __func__);
 		goto out_clk_unprepare;
 	}
 
 	ret = hash_check_hw(device_data);
 	if (ret) {
-		dev_err(dev, "[%s] hash_check_hw() failed!", __func__);
+		dev_err(dev, "%s: hash_check_hw() failed!\n", __func__);
 		goto out_power;
 	}
 
@@ -1766,8 +1738,8 @@ static int ux500_hash_probe(struct platform_device *pdev)
 
 	ret = ahash_algs_register_all(device_data);
 	if (ret) {
-		dev_err(dev, "[%s] ahash_algs_register_all() "
-				"failed!", __func__);
+		dev_err(dev, "%s: ahash_algs_register_all() failed!\n",
+			__func__);
 		goto out_power;
 	}
 
@@ -1810,8 +1782,7 @@ static int ux500_hash_remove(struct platform_device *pdev)
 
 	device_data = platform_get_drvdata(pdev);
 	if (!device_data) {
-		dev_err(dev, "[%s]: platform_get_drvdata() failed!",
-			__func__);
+		dev_err(dev, "%s: platform_get_drvdata() failed!\n", __func__);
 		return -ENOMEM;
 	}
 
@@ -1841,7 +1812,7 @@ static int ux500_hash_remove(struct platform_device *pdev)
 		ahash_algs_unregister_all(device_data);
 
 	if (hash_disable_power(device_data, false))
-		dev_err(dev, "[%s]: hash_disable_power() failed",
+		dev_err(dev, "%s: hash_disable_power() failed\n",
 			__func__);
 
 	clk_unprepare(device_data->clk);
@@ -1870,8 +1841,8 @@ static void ux500_hash_shutdown(struct platform_device *pdev)
 
 	device_data = platform_get_drvdata(pdev);
 	if (!device_data) {
-		dev_err(&pdev->dev, "[%s] platform_get_drvdata() failed!",
-				__func__);
+		dev_err(&pdev->dev, "%s: platform_get_drvdata() failed!\n",
+			__func__);
 		return;
 	}
 
@@ -1880,8 +1851,8 @@ static void ux500_hash_shutdown(struct platform_device *pdev)
 	/* current_ctx allocates a device, NULL = unallocated */
 	if (!device_data->current_ctx) {
 		if (down_trylock(&driver_data.device_allocation))
-			dev_dbg(&pdev->dev, "[%s]: Cryp still in use!"
-				"Shutting down anyway...", __func__);
+			dev_dbg(&pdev->dev, "%s: Cryp still in use! Shutting down anyway...\n",
+				__func__);
 		/**
 		 * (Allocate the device)
 		 * Need to set this to non-null (dummy) value,
@@ -1906,8 +1877,8 @@ static void ux500_hash_shutdown(struct platform_device *pdev)
 		release_mem_region(res->start, resource_size(res));
 
 	if (hash_disable_power(device_data, false))
-		dev_err(&pdev->dev, "[%s] hash_disable_power() failed",
-				__func__);
+		dev_err(&pdev->dev, "%s: hash_disable_power() failed\n",
+			__func__);
 }
 
 /**
@@ -1922,7 +1893,7 @@ static int ux500_hash_suspend(struct device *dev)
 
 	device_data = dev_get_drvdata(dev);
 	if (!device_data) {
-		dev_err(dev, "[%s] platform_get_drvdata() failed!", __func__);
+		dev_err(dev, "%s: platform_get_drvdata() failed!\n", __func__);
 		return -ENOMEM;
 	}
 
@@ -1933,15 +1904,16 @@ static int ux500_hash_suspend(struct device *dev)
 
 	if (device_data->current_ctx == ++temp_ctx) {
 		if (down_interruptible(&driver_data.device_allocation))
-			dev_dbg(dev, "[%s]: down_interruptible() failed",
+			dev_dbg(dev, "%s: down_interruptible() failed\n",
 				__func__);
 		ret = hash_disable_power(device_data, false);
 
-	} else
+	} else {
 		ret = hash_disable_power(device_data, true);
+	}
 
 	if (ret)
-		dev_err(dev, "[%s]: hash_disable_power()", __func__);
+		dev_err(dev, "%s: hash_disable_power()\n", __func__);
 
 	return ret;
 }
@@ -1958,7 +1930,7 @@ static int ux500_hash_resume(struct device *dev)
 
 	device_data = dev_get_drvdata(dev);
 	if (!device_data) {
-		dev_err(dev, "[%s] platform_get_drvdata() failed!", __func__);
+		dev_err(dev, "%s: platform_get_drvdata() failed!\n", __func__);
 		return -ENOMEM;
 	}
 
@@ -1973,7 +1945,7 @@ static int ux500_hash_resume(struct device *dev)
 		ret = hash_enable_power(device_data, true);
 
 	if (ret)
-		dev_err(dev, "[%s]: hash_enable_power() failed!", __func__);
+		dev_err(dev, "%s: hash_enable_power() failed!\n", __func__);
 
 	return ret;
 }
@@ -1981,8 +1953,8 @@ static int ux500_hash_resume(struct device *dev)
 static SIMPLE_DEV_PM_OPS(ux500_hash_pm, ux500_hash_suspend, ux500_hash_resume);
 
 static const struct of_device_id ux500_hash_match[] = {
-        { .compatible = "stericsson,ux500-hash" },
-        { },
+	{ .compatible = "stericsson,ux500-hash" },
+	{ },
 };
 
 static struct platform_driver hash_driver = {
diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c
index e94e619fe050..c99c00d35d34 100644
--- a/drivers/devfreq/devfreq.c
+++ b/drivers/devfreq/devfreq.c
@@ -703,7 +703,7 @@ err_out:
 }
 EXPORT_SYMBOL(devfreq_remove_governor);
 
-static ssize_t show_governor(struct device *dev,
+static ssize_t governor_show(struct device *dev,
 			     struct device_attribute *attr, char *buf)
 {
 	if (!to_devfreq(dev)->governor)
@@ -712,7 +712,7 @@ static ssize_t show_governor(struct device *dev,
 	return sprintf(buf, "%s\n", to_devfreq(dev)->governor->name);
 }
 
-static ssize_t store_governor(struct device *dev, struct device_attribute *attr,
+static ssize_t governor_store(struct device *dev, struct device_attribute *attr,
 			      const char *buf, size_t count)
 {
 	struct devfreq *df = to_devfreq(dev);
@@ -754,9 +754,11 @@ out:
 		ret = count;
 	return ret;
 }
-static ssize_t show_available_governors(struct device *d,
-				    struct device_attribute *attr,
-				    char *buf)
+static DEVICE_ATTR_RW(governor);
+
+static ssize_t available_governors_show(struct device *d,
+					struct device_attribute *attr,
+					char *buf)
 {
 	struct devfreq_governor *tmp_governor;
 	ssize_t count = 0;
@@ -775,9 +777,10 @@ static ssize_t show_available_governors(struct device *d,
 
 	return count;
 }
+static DEVICE_ATTR_RO(available_governors);
 
-static ssize_t show_freq(struct device *dev,
-			 struct device_attribute *attr, char *buf)
+static ssize_t cur_freq_show(struct device *dev, struct device_attribute *attr,
+			     char *buf)
 {
 	unsigned long freq;
 	struct devfreq *devfreq = to_devfreq(dev);
@@ -788,20 +791,22 @@ static ssize_t show_freq(struct device *dev,
 
 	return sprintf(buf, "%lu\n", devfreq->previous_freq);
 }
+static DEVICE_ATTR_RO(cur_freq);
 
-static ssize_t show_target_freq(struct device *dev,
-			struct device_attribute *attr, char *buf)
+static ssize_t target_freq_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
 {
 	return sprintf(buf, "%lu\n", to_devfreq(dev)->previous_freq);
 }
+static DEVICE_ATTR_RO(target_freq);
 
-static ssize_t show_polling_interval(struct device *dev,
+static ssize_t polling_interval_show(struct device *dev,
 				     struct device_attribute *attr, char *buf)
 {
 	return sprintf(buf, "%d\n", to_devfreq(dev)->profile->polling_ms);
 }
 
-static ssize_t store_polling_interval(struct device *dev,
+static ssize_t polling_interval_store(struct device *dev,
 				      struct device_attribute *attr,
 				      const char *buf, size_t count)
 {
@@ -821,8 +826,9 @@ static ssize_t store_polling_interval(struct device *dev,
 
 	return ret;
 }
+static DEVICE_ATTR_RW(polling_interval);
 
-static ssize_t store_min_freq(struct device *dev, struct device_attribute *attr,
+static ssize_t min_freq_store(struct device *dev, struct device_attribute *attr,
 			      const char *buf, size_t count)
 {
 	struct devfreq *df = to_devfreq(dev);
@@ -849,13 +855,13 @@ unlock:
 	return ret;
 }
 
-static ssize_t show_min_freq(struct device *dev, struct device_attribute *attr,
+static ssize_t min_freq_show(struct device *dev, struct device_attribute *attr,
 			     char *buf)
 {
 	return sprintf(buf, "%lu\n", to_devfreq(dev)->min_freq);
 }
 
-static ssize_t store_max_freq(struct device *dev, struct device_attribute *attr,
+static ssize_t max_freq_store(struct device *dev, struct device_attribute *attr,
 			      const char *buf, size_t count)
 {
 	struct devfreq *df = to_devfreq(dev);
@@ -881,16 +887,18 @@ unlock:
 	mutex_unlock(&df->lock);
 	return ret;
 }
+static DEVICE_ATTR_RW(min_freq);
 
-static ssize_t show_max_freq(struct device *dev, struct device_attribute *attr,
+static ssize_t max_freq_show(struct device *dev, struct device_attribute *attr,
 			     char *buf)
 {
 	return sprintf(buf, "%lu\n", to_devfreq(dev)->max_freq);
 }
+static DEVICE_ATTR_RW(max_freq);
 
-static ssize_t show_available_freqs(struct device *d,
-				    struct device_attribute *attr,
-				    char *buf)
+static ssize_t available_frequencies_show(struct device *d,
+					  struct device_attribute *attr,
+					  char *buf)
 {
 	struct devfreq *df = to_devfreq(d);
 	struct device *dev = df->dev.parent;
@@ -918,9 +926,10 @@ static ssize_t show_available_freqs(struct device *d,
 
 	return count;
 }
+static DEVICE_ATTR_RO(available_frequencies);
 
-static ssize_t show_trans_table(struct device *dev, struct device_attribute *attr,
-				char *buf)
+static ssize_t trans_stat_show(struct device *dev,
+			       struct device_attribute *attr, char *buf)
 {
 	struct devfreq *devfreq = to_devfreq(dev);
 	ssize_t len;
@@ -959,20 +968,21 @@ static ssize_t show_trans_table(struct device *dev, struct device_attribute *att
 					devfreq->total_trans);
 	return len;
 }
-
-static struct device_attribute devfreq_attrs[] = {
-	__ATTR(governor, S_IRUGO | S_IWUSR, show_governor, store_governor),
-	__ATTR(available_governors, S_IRUGO, show_available_governors, NULL),
-	__ATTR(cur_freq, S_IRUGO, show_freq, NULL),
-	__ATTR(available_frequencies, S_IRUGO, show_available_freqs, NULL),
-	__ATTR(target_freq, S_IRUGO, show_target_freq, NULL),
-	__ATTR(polling_interval, S_IRUGO | S_IWUSR, show_polling_interval,
-	       store_polling_interval),
-	__ATTR(min_freq, S_IRUGO | S_IWUSR, show_min_freq, store_min_freq),
-	__ATTR(max_freq, S_IRUGO | S_IWUSR, show_max_freq, store_max_freq),
-	__ATTR(trans_stat, S_IRUGO, show_trans_table, NULL),
-	{ },
+static DEVICE_ATTR_RO(trans_stat);
+
+static struct attribute *devfreq_attrs[] = {
+	&dev_attr_governor.attr,
+	&dev_attr_available_governors.attr,
+	&dev_attr_cur_freq.attr,
+	&dev_attr_available_frequencies.attr,
+	&dev_attr_target_freq.attr,
+	&dev_attr_polling_interval.attr,
+	&dev_attr_min_freq.attr,
+	&dev_attr_max_freq.attr,
+	&dev_attr_trans_stat.attr,
+	NULL,
 };
+ATTRIBUTE_GROUPS(devfreq);
 
 static int __init devfreq_init(void)
 {
@@ -988,7 +998,7 @@ static int __init devfreq_init(void)
 		pr_err("%s: couldn't create workqueue\n", __FILE__);
 		return PTR_ERR(devfreq_wq);
 	}
-	devfreq_class->dev_attrs = devfreq_attrs;
+	devfreq_class->dev_groups = devfreq_groups;
 
 	return 0;
 }
diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig
index 643d7c7a0d8e..f238cfd33847 100644
--- a/drivers/dma/Kconfig
+++ b/drivers/dma/Kconfig
@@ -198,6 +198,7 @@ config TI_EDMA
 	depends on ARCH_DAVINCI || ARCH_OMAP
 	select DMA_ENGINE
 	select DMA_VIRTUAL_CHANNELS
+	select TI_PRIV_EDMA
 	default n
 	help
 	  Enable support for the TI EDMA controller. This DMA
@@ -287,6 +288,14 @@ config DMA_OMAP
 	select DMA_ENGINE
 	select DMA_VIRTUAL_CHANNELS
 
+config TI_CPPI41
+	tristate "AM33xx CPPI41 DMA support"
+	depends on ARCH_OMAP
+	select DMA_ENGINE
+	help
+	  The Communications Port Programming Interface (CPPI) 4.1 DMA engine
+	  is currently used by the USB driver on AM335x platforms.
+
 config MMP_PDMA
 	bool "MMP PDMA support"
 	depends on (ARCH_MMP || ARCH_PXA)
@@ -300,6 +309,15 @@ config DMA_JZ4740
 	select DMA_ENGINE
 	select DMA_VIRTUAL_CHANNELS
 
+config K3_DMA
+	tristate "Hisilicon K3 DMA support"
+	depends on ARCH_HI3xxx
+	select DMA_ENGINE
+	select DMA_VIRTUAL_CHANNELS
+	help
+	  Support the DMA engine for Hisilicon K3 platform
+	  devices.
+
 config DMA_ENGINE
 	bool
 
diff --git a/drivers/dma/Makefile b/drivers/dma/Makefile
index 5e0f2ef85614..db89035b3626 100644
--- a/drivers/dma/Makefile
+++ b/drivers/dma/Makefile
@@ -39,3 +39,5 @@ obj-$(CONFIG_MMP_TDMA) += mmp_tdma.o
 obj-$(CONFIG_DMA_OMAP) += omap-dma.o
 obj-$(CONFIG_MMP_PDMA) += mmp_pdma.o
 obj-$(CONFIG_DMA_JZ4740) += dma-jz4740.o
+obj-$(CONFIG_TI_CPPI41) += cppi41.o
+obj-$(CONFIG_K3_DMA) += k3dma.o
diff --git a/drivers/dma/acpi-dma.c b/drivers/dma/acpi-dma.c
index 5a18f82f732a..e69b03c0fa50 100644
--- a/drivers/dma/acpi-dma.c
+++ b/drivers/dma/acpi-dma.c
@@ -43,7 +43,6 @@ static int acpi_dma_parse_resource_group(const struct acpi_csrt_group *grp,
 	struct list_head resource_list;
 	struct resource_list_entry *rentry;
 	resource_size_t mem = 0, irq = 0;
-	u32 vendor_id;
 	int ret;
 
 	if (grp->shared_info_length != sizeof(struct acpi_csrt_shared_info))
@@ -73,9 +72,8 @@ static int acpi_dma_parse_resource_group(const struct acpi_csrt_group *grp,
 	if (si->mmio_base_low != mem || si->gsi_interrupt != irq)
 		return 0;
 
-	vendor_id = le32_to_cpu(grp->vendor_id);
 	dev_dbg(&adev->dev, "matches with %.4s%04X (rev %u)\n",
-		(char *)&vendor_id, grp->device_id, grp->revision);
+		(char *)&grp->vendor_id, grp->device_id, grp->revision);
 
 	/* Check if the request line range is available */
 	if (si->base_request_line == 0 && si->num_handshake_signals == 0)
diff --git a/drivers/dma/amba-pl08x.c b/drivers/dma/amba-pl08x.c
index 06fe45c74de5..fce46c5bf1c7 100644
--- a/drivers/dma/amba-pl08x.c
+++ b/drivers/dma/amba-pl08x.c
@@ -24,6 +24,7 @@
  *
  * Documentation: ARM DDI 0196G == PL080
  * Documentation: ARM DDI 0218E == PL081
+ * Documentation: S3C6410 User's Manual == PL080S
  *
  * PL080 & PL081 both have 16 sets of DMA signals that can be routed to any
  * channel.
@@ -36,6 +37,14 @@
  *
  * The PL080 has a dual bus master, PL081 has a single master.
  *
+ * PL080S is a version modified by Samsung and used in S3C64xx SoCs.
+ * It differs in following aspects:
+ * - CH_CONFIG register at different offset,
+ * - separate CH_CONTROL2 register for transfer size,
+ * - bigger maximum transfer size,
+ * - 8-word aligned LLI, instead of 4-word, due to extra CCTL2 word,
+ * - no support for peripheral flow control.
+ *
  * Memory to peripheral transfer may be visualized as
  *	Get data from memory to DMAC
  *	Until no data left
@@ -64,10 +73,7 @@
  *  - Peripheral flow control: the transfer size is ignored (and should be
  *    zero).  The data is transferred from the current LLI entry, until
  *    after the final transfer signalled by LBREQ or LSREQ.  The DMAC
- *    will then move to the next LLI entry.
- *
- * Global TODO:
- * - Break out common code from arch/arm/mach-s3c64xx and share
+ *    will then move to the next LLI entry. Unsupported by PL080S.
  */
 #include <linux/amba/bus.h>
 #include <linux/amba/pl08x.h>
@@ -100,24 +106,16 @@ struct pl08x_driver_data;
  * @nomadik: whether the channels have Nomadik security extension bits
  *	that need to be checked for permission before use and some registers are
  *	missing
+ * @pl080s: whether this version is a PL080S, which has separate register and
+ *	LLI word for transfer size.
  */
 struct vendor_data {
+	u8 config_offset;
 	u8 channels;
 	bool dualmaster;
 	bool nomadik;
-};
-
-/*
- * PL08X private data structures
- * An LLI struct - see PL08x TRM.  Note that next uses bit[0] as a bus bit,
- * start & end do not - their bus bit info is in cctl.  Also note that these
- * are fixed 32-bit quantities.
- */
-struct pl08x_lli {
-	u32 src;
-	u32 dst;
-	u32 lli;
-	u32 cctl;
+	bool pl080s;
+	u32 max_transfer_size;
 };
 
 /**
@@ -133,6 +131,8 @@ struct pl08x_bus_data {
 	u8 buswidth;
 };
 
+#define IS_BUS_ALIGNED(bus) IS_ALIGNED((bus)->addr, (bus)->buswidth)
+
 /**
  * struct pl08x_phy_chan - holder for the physical channels
  * @id: physical index to this channel
@@ -145,6 +145,7 @@ struct pl08x_bus_data {
 struct pl08x_phy_chan {
 	unsigned int id;
 	void __iomem *base;
+	void __iomem *reg_config;
 	spinlock_t lock;
 	struct pl08x_dma_chan *serving;
 	bool locked;
@@ -174,12 +175,13 @@ struct pl08x_sg {
  * @ccfg: config reg values for current txd
  * @done: this marks completed descriptors, which should not have their
  *   mux released.
+ * @cyclic: indicate cyclic transfers
  */
 struct pl08x_txd {
 	struct virt_dma_desc vd;
 	struct list_head dsg_list;
 	dma_addr_t llis_bus;
-	struct pl08x_lli *llis_va;
+	u32 *llis_va;
 	/* Default cctl value for LLIs */
 	u32 cctl;
 	/*
@@ -188,6 +190,7 @@ struct pl08x_txd {
 	 */
 	u32 ccfg;
 	bool done;
+	bool cyclic;
 };
 
 /**
@@ -263,17 +266,29 @@ struct pl08x_driver_data {
 	struct dma_pool *pool;
 	u8 lli_buses;
 	u8 mem_buses;
+	u8 lli_words;
 };
 
 /*
  * PL08X specific defines
  */
 
-/* Size (bytes) of each LLI buffer allocated for one transfer */
-# define PL08X_LLI_TSFR_SIZE	0x2000
+/* The order of words in an LLI. */
+#define PL080_LLI_SRC		0
+#define PL080_LLI_DST		1
+#define PL080_LLI_LLI		2
+#define PL080_LLI_CCTL		3
+#define PL080S_LLI_CCTL2	4
+
+/* Total words in an LLI. */
+#define PL080_LLI_WORDS		4
+#define PL080S_LLI_WORDS	8
 
-/* Maximum times we call dma_pool_alloc on this pool without freeing */
-#define MAX_NUM_TSFR_LLIS	(PL08X_LLI_TSFR_SIZE/sizeof(struct pl08x_lli))
+/*
+ * Number of LLIs in each LLI buffer allocated for one transfer
+ * (maximum times we call dma_pool_alloc on this pool without freeing)
+ */
+#define MAX_NUM_TSFR_LLIS	512
 #define PL08X_ALIGN		8
 
 static inline struct pl08x_dma_chan *to_pl08x_chan(struct dma_chan *chan)
@@ -334,10 +349,39 @@ static int pl08x_phy_channel_busy(struct pl08x_phy_chan *ch)
 {
 	unsigned int val;
 
-	val = readl(ch->base + PL080_CH_CONFIG);
+	val = readl(ch->reg_config);
 	return val & PL080_CONFIG_ACTIVE;
 }
 
+static void pl08x_write_lli(struct pl08x_driver_data *pl08x,
+		struct pl08x_phy_chan *phychan, const u32 *lli, u32 ccfg)
+{
+	if (pl08x->vd->pl080s)
+		dev_vdbg(&pl08x->adev->dev,
+			"WRITE channel %d: csrc=0x%08x, cdst=0x%08x, "
+			"clli=0x%08x, cctl=0x%08x, cctl2=0x%08x, ccfg=0x%08x\n",
+			phychan->id, lli[PL080_LLI_SRC], lli[PL080_LLI_DST],
+			lli[PL080_LLI_LLI], lli[PL080_LLI_CCTL],
+			lli[PL080S_LLI_CCTL2], ccfg);
+	else
+		dev_vdbg(&pl08x->adev->dev,
+			"WRITE channel %d: csrc=0x%08x, cdst=0x%08x, "
+			"clli=0x%08x, cctl=0x%08x, ccfg=0x%08x\n",
+			phychan->id, lli[PL080_LLI_SRC], lli[PL080_LLI_DST],
+			lli[PL080_LLI_LLI], lli[PL080_LLI_CCTL], ccfg);
+
+	writel_relaxed(lli[PL080_LLI_SRC], phychan->base + PL080_CH_SRC_ADDR);
+	writel_relaxed(lli[PL080_LLI_DST], phychan->base + PL080_CH_DST_ADDR);
+	writel_relaxed(lli[PL080_LLI_LLI], phychan->base + PL080_CH_LLI);
+	writel_relaxed(lli[PL080_LLI_CCTL], phychan->base + PL080_CH_CONTROL);
+
+	if (pl08x->vd->pl080s)
+		writel_relaxed(lli[PL080S_LLI_CCTL2],
+				phychan->base + PL080S_CH_CONTROL2);
+
+	writel(ccfg, phychan->reg_config);
+}
+
 /*
  * Set the initial DMA register values i.e. those for the first LLI
  * The next LLI pointer and the configuration interrupt bit have
@@ -350,7 +394,6 @@ static void pl08x_start_next_txd(struct pl08x_dma_chan *plchan)
 	struct pl08x_phy_chan *phychan = plchan->phychan;
 	struct virt_dma_desc *vd = vchan_next_desc(&plchan->vc);
 	struct pl08x_txd *txd = to_pl08x_txd(&vd->tx);
-	struct pl08x_lli *lli;
 	u32 val;
 
 	list_del(&txd->vd.node);
@@ -361,19 +404,7 @@ static void pl08x_start_next_txd(struct pl08x_dma_chan *plchan)
 	while (pl08x_phy_channel_busy(phychan))
 		cpu_relax();
 
-	lli = &txd->llis_va[0];
-
-	dev_vdbg(&pl08x->adev->dev,
-		"WRITE channel %d: csrc=0x%08x, cdst=0x%08x, "
-		"clli=0x%08x, cctl=0x%08x, ccfg=0x%08x\n",
-		phychan->id, lli->src, lli->dst, lli->lli, lli->cctl,
-		txd->ccfg);
-
-	writel(lli->src, phychan->base + PL080_CH_SRC_ADDR);
-	writel(lli->dst, phychan->base + PL080_CH_DST_ADDR);
-	writel(lli->lli, phychan->base + PL080_CH_LLI);
-	writel(lli->cctl, phychan->base + PL080_CH_CONTROL);
-	writel(txd->ccfg, phychan->base + PL080_CH_CONFIG);
+	pl08x_write_lli(pl08x, phychan, &txd->llis_va[0], txd->ccfg);
 
 	/* Enable the DMA channel */
 	/* Do not access config register until channel shows as disabled */
@@ -381,11 +412,11 @@ static void pl08x_start_next_txd(struct pl08x_dma_chan *plchan)
 		cpu_relax();
 
 	/* Do not access config register until channel shows as inactive */
-	val = readl(phychan->base + PL080_CH_CONFIG);
+	val = readl(phychan->reg_config);
 	while ((val & PL080_CONFIG_ACTIVE) || (val & PL080_CONFIG_ENABLE))
-		val = readl(phychan->base + PL080_CH_CONFIG);
+		val = readl(phychan->reg_config);
 
-	writel(val | PL080_CONFIG_ENABLE, phychan->base + PL080_CH_CONFIG);
+	writel(val | PL080_CONFIG_ENABLE, phychan->reg_config);
 }
 
 /*
@@ -404,9 +435,9 @@ static void pl08x_pause_phy_chan(struct pl08x_phy_chan *ch)
 	int timeout;
 
 	/* Set the HALT bit and wait for the FIFO to drain */
-	val = readl(ch->base + PL080_CH_CONFIG);
+	val = readl(ch->reg_config);
 	val |= PL080_CONFIG_HALT;
-	writel(val, ch->base + PL080_CH_CONFIG);
+	writel(val, ch->reg_config);
 
 	/* Wait for channel inactive */
 	for (timeout = 1000; timeout; timeout--) {
@@ -423,9 +454,9 @@ static void pl08x_resume_phy_chan(struct pl08x_phy_chan *ch)
 	u32 val;
 
 	/* Clear the HALT bit */
-	val = readl(ch->base + PL080_CH_CONFIG);
+	val = readl(ch->reg_config);
 	val &= ~PL080_CONFIG_HALT;
-	writel(val, ch->base + PL080_CH_CONFIG);
+	writel(val, ch->reg_config);
 }
 
 /*
@@ -437,12 +468,12 @@ static void pl08x_resume_phy_chan(struct pl08x_phy_chan *ch)
 static void pl08x_terminate_phy_chan(struct pl08x_driver_data *pl08x,
 	struct pl08x_phy_chan *ch)
 {
-	u32 val = readl(ch->base + PL080_CH_CONFIG);
+	u32 val = readl(ch->reg_config);
 
 	val &= ~(PL080_CONFIG_ENABLE | PL080_CONFIG_ERR_IRQ_MASK |
 	         PL080_CONFIG_TC_IRQ_MASK);
 
-	writel(val, ch->base + PL080_CH_CONFIG);
+	writel(val, ch->reg_config);
 
 	writel(1 << ch->id, pl08x->base + PL080_ERR_CLEAR);
 	writel(1 << ch->id, pl08x->base + PL080_TC_CLEAR);
@@ -453,6 +484,28 @@ static inline u32 get_bytes_in_cctl(u32 cctl)
 	/* The source width defines the number of bytes */
 	u32 bytes = cctl & PL080_CONTROL_TRANSFER_SIZE_MASK;
 
+	cctl &= PL080_CONTROL_SWIDTH_MASK;
+
+	switch (cctl >> PL080_CONTROL_SWIDTH_SHIFT) {
+	case PL080_WIDTH_8BIT:
+		break;
+	case PL080_WIDTH_16BIT:
+		bytes *= 2;
+		break;
+	case PL080_WIDTH_32BIT:
+		bytes *= 4;
+		break;
+	}
+	return bytes;
+}
+
+static inline u32 get_bytes_in_cctl_pl080s(u32 cctl, u32 cctl1)
+{
+	/* The source width defines the number of bytes */
+	u32 bytes = cctl1 & PL080S_CONTROL_TRANSFER_SIZE_MASK;
+
+	cctl &= PL080_CONTROL_SWIDTH_MASK;
+
 	switch (cctl >> PL080_CONTROL_SWIDTH_SHIFT) {
 	case PL080_WIDTH_8BIT:
 		break;
@@ -469,47 +522,66 @@ static inline u32 get_bytes_in_cctl(u32 cctl)
 /* The channel should be paused when calling this */
 static u32 pl08x_getbytes_chan(struct pl08x_dma_chan *plchan)
 {
+	struct pl08x_driver_data *pl08x = plchan->host;
+	const u32 *llis_va, *llis_va_limit;
 	struct pl08x_phy_chan *ch;
+	dma_addr_t llis_bus;
 	struct pl08x_txd *txd;
-	size_t bytes = 0;
+	u32 llis_max_words;
+	size_t bytes;
+	u32 clli;
 
 	ch = plchan->phychan;
 	txd = plchan->at;
 
+	if (!ch || !txd)
+		return 0;
+
 	/*
 	 * Follow the LLIs to get the number of remaining
 	 * bytes in the currently active transaction.
 	 */
-	if (ch && txd) {
-		u32 clli = readl(ch->base + PL080_CH_LLI) & ~PL080_LLI_LM_AHB2;
+	clli = readl(ch->base + PL080_CH_LLI) & ~PL080_LLI_LM_AHB2;
 
-		/* First get the remaining bytes in the active transfer */
+	/* First get the remaining bytes in the active transfer */
+	if (pl08x->vd->pl080s)
+		bytes = get_bytes_in_cctl_pl080s(
+				readl(ch->base + PL080_CH_CONTROL),
+				readl(ch->base + PL080S_CH_CONTROL2));
+	else
 		bytes = get_bytes_in_cctl(readl(ch->base + PL080_CH_CONTROL));
 
-		if (clli) {
-			struct pl08x_lli *llis_va = txd->llis_va;
-			dma_addr_t llis_bus = txd->llis_bus;
-			int index;
+	if (!clli)
+		return bytes;
 
-			BUG_ON(clli < llis_bus || clli >= llis_bus +
-				sizeof(struct pl08x_lli) * MAX_NUM_TSFR_LLIS);
+	llis_va = txd->llis_va;
+	llis_bus = txd->llis_bus;
 
-			/*
-			 * Locate the next LLI - as this is an array,
-			 * it's simple maths to find.
-			 */
-			index = (clli - llis_bus) / sizeof(struct pl08x_lli);
+	llis_max_words = pl08x->lli_words * MAX_NUM_TSFR_LLIS;
+	BUG_ON(clli < llis_bus || clli >= llis_bus +
+						sizeof(u32) * llis_max_words);
 
-			for (; index < MAX_NUM_TSFR_LLIS; index++) {
-				bytes += get_bytes_in_cctl(llis_va[index].cctl);
+	/*
+	 * Locate the next LLI - as this is an array,
+	 * it's simple maths to find.
+	 */
+	llis_va += (clli - llis_bus) / sizeof(u32);
 
-				/*
-				 * A LLI pointer of 0 terminates the LLI list
-				 */
-				if (!llis_va[index].lli)
-					break;
-			}
-		}
+	llis_va_limit = llis_va + llis_max_words;
+
+	for (; llis_va < llis_va_limit; llis_va += pl08x->lli_words) {
+		if (pl08x->vd->pl080s)
+			bytes += get_bytes_in_cctl_pl080s(
+						llis_va[PL080_LLI_CCTL],
+						llis_va[PL080S_LLI_CCTL2]);
+		else
+			bytes += get_bytes_in_cctl(llis_va[PL080_LLI_CCTL]);
+
+		/*
+		 * A LLI pointer going backward terminates the LLI list
+		 */
+		if (llis_va[PL080_LLI_LLI] <= clli)
+			break;
 	}
 
 	return bytes;
@@ -720,6 +792,7 @@ static inline u32 pl08x_cctl_bits(u32 cctl, u8 srcwidth, u8 dstwidth,
 		break;
 	}
 
+	tsize &= PL080_CONTROL_TRANSFER_SIZE_MASK;
 	retbits |= tsize << PL080_CONTROL_TRANSFER_SIZE_SHIFT;
 	return retbits;
 }
@@ -764,20 +837,26 @@ static void pl08x_choose_master_bus(struct pl08x_lli_build_data *bd,
 /*
  * Fills in one LLI for a certain transfer descriptor and advance the counter
  */
-static void pl08x_fill_lli_for_desc(struct pl08x_lli_build_data *bd,
-	int num_llis, int len, u32 cctl)
+static void pl08x_fill_lli_for_desc(struct pl08x_driver_data *pl08x,
+				    struct pl08x_lli_build_data *bd,
+				    int num_llis, int len, u32 cctl, u32 cctl2)
 {
-	struct pl08x_lli *llis_va = bd->txd->llis_va;
+	u32 offset = num_llis * pl08x->lli_words;
+	u32 *llis_va = bd->txd->llis_va + offset;
 	dma_addr_t llis_bus = bd->txd->llis_bus;
 
 	BUG_ON(num_llis >= MAX_NUM_TSFR_LLIS);
 
-	llis_va[num_llis].cctl = cctl;
-	llis_va[num_llis].src = bd->srcbus.addr;
-	llis_va[num_llis].dst = bd->dstbus.addr;
-	llis_va[num_llis].lli = llis_bus + (num_llis + 1) *
-		sizeof(struct pl08x_lli);
-	llis_va[num_llis].lli |= bd->lli_bus;
+	/* Advance the offset to next LLI. */
+	offset += pl08x->lli_words;
+
+	llis_va[PL080_LLI_SRC] = bd->srcbus.addr;
+	llis_va[PL080_LLI_DST] = bd->dstbus.addr;
+	llis_va[PL080_LLI_LLI] = (llis_bus + sizeof(u32) * offset);
+	llis_va[PL080_LLI_LLI] |= bd->lli_bus;
+	llis_va[PL080_LLI_CCTL] = cctl;
+	if (pl08x->vd->pl080s)
+		llis_va[PL080S_LLI_CCTL2] = cctl2;
 
 	if (cctl & PL080_CONTROL_SRC_INCR)
 		bd->srcbus.addr += len;
@@ -789,14 +868,53 @@ static void pl08x_fill_lli_for_desc(struct pl08x_lli_build_data *bd,
 	bd->remainder -= len;
 }
 
-static inline void prep_byte_width_lli(struct pl08x_lli_build_data *bd,
-		u32 *cctl, u32 len, int num_llis, size_t *total_bytes)
+static inline void prep_byte_width_lli(struct pl08x_driver_data *pl08x,
+			struct pl08x_lli_build_data *bd, u32 *cctl, u32 len,
+			int num_llis, size_t *total_bytes)
 {
 	*cctl = pl08x_cctl_bits(*cctl, 1, 1, len);
-	pl08x_fill_lli_for_desc(bd, num_llis, len, *cctl);
+	pl08x_fill_lli_for_desc(pl08x, bd, num_llis, len, *cctl, len);
 	(*total_bytes) += len;
 }
 
+#ifdef VERBOSE_DEBUG
+static void pl08x_dump_lli(struct pl08x_driver_data *pl08x,
+			   const u32 *llis_va, int num_llis)
+{
+	int i;
+
+	if (pl08x->vd->pl080s) {
+		dev_vdbg(&pl08x->adev->dev,
+			"%-3s %-9s  %-10s %-10s %-10s %-10s %s\n",
+			"lli", "", "csrc", "cdst", "clli", "cctl", "cctl2");
+		for (i = 0; i < num_llis; i++) {
+			dev_vdbg(&pl08x->adev->dev,
+				"%3d @%p: 0x%08x 0x%08x 0x%08x 0x%08x 0x%08x\n",
+				i, llis_va, llis_va[PL080_LLI_SRC],
+				llis_va[PL080_LLI_DST], llis_va[PL080_LLI_LLI],
+				llis_va[PL080_LLI_CCTL],
+				llis_va[PL080S_LLI_CCTL2]);
+			llis_va += pl08x->lli_words;
+		}
+	} else {
+		dev_vdbg(&pl08x->adev->dev,
+			"%-3s %-9s  %-10s %-10s %-10s %s\n",
+			"lli", "", "csrc", "cdst", "clli", "cctl");
+		for (i = 0; i < num_llis; i++) {
+			dev_vdbg(&pl08x->adev->dev,
+				"%3d @%p: 0x%08x 0x%08x 0x%08x 0x%08x\n",
+				i, llis_va, llis_va[PL080_LLI_SRC],
+				llis_va[PL080_LLI_DST], llis_va[PL080_LLI_LLI],
+				llis_va[PL080_LLI_CCTL]);
+			llis_va += pl08x->lli_words;
+		}
+	}
+}
+#else
+static inline void pl08x_dump_lli(struct pl08x_driver_data *pl08x,
+				  const u32 *llis_va, int num_llis) {}
+#endif
+
 /*
  * This fills in the table of LLIs for the transfer descriptor
  * Note that we assume we never have to change the burst sizes
@@ -810,7 +928,7 @@ static int pl08x_fill_llis_for_desc(struct pl08x_driver_data *pl08x,
 	int num_llis = 0;
 	u32 cctl, early_bytes = 0;
 	size_t max_bytes_per_lli, total_bytes;
-	struct pl08x_lli *llis_va;
+	u32 *llis_va, *last_lli;
 	struct pl08x_sg *dsg;
 
 	txd->llis_va = dma_pool_alloc(pl08x->pool, GFP_NOWAIT, &txd->llis_bus);
@@ -845,10 +963,13 @@ static int pl08x_fill_llis_for_desc(struct pl08x_driver_data *pl08x,
 
 		pl08x_choose_master_bus(&bd, &mbus, &sbus, cctl);
 
-		dev_vdbg(&pl08x->adev->dev, "src=0x%08x%s/%u dst=0x%08x%s/%u len=%zu\n",
-			bd.srcbus.addr, cctl & PL080_CONTROL_SRC_INCR ? "+" : "",
+		dev_vdbg(&pl08x->adev->dev,
+			"src=0x%08llx%s/%u dst=0x%08llx%s/%u len=%zu\n",
+			(u64)bd.srcbus.addr,
+			cctl & PL080_CONTROL_SRC_INCR ? "+" : "",
 			bd.srcbus.buswidth,
-			bd.dstbus.addr, cctl & PL080_CONTROL_DST_INCR ? "+" : "",
+			(u64)bd.dstbus.addr,
+			cctl & PL080_CONTROL_DST_INCR ? "+" : "",
 			bd.dstbus.buswidth,
 			bd.remainder);
 		dev_vdbg(&pl08x->adev->dev, "mbus=%s sbus=%s\n",
@@ -886,8 +1007,8 @@ static int pl08x_fill_llis_for_desc(struct pl08x_driver_data *pl08x,
 				return 0;
 			}
 
-			if ((bd.srcbus.addr % bd.srcbus.buswidth) ||
-					(bd.dstbus.addr % bd.dstbus.buswidth)) {
+			if (!IS_BUS_ALIGNED(&bd.srcbus) ||
+				!IS_BUS_ALIGNED(&bd.dstbus)) {
 				dev_err(&pl08x->adev->dev,
 					"%s src & dst address must be aligned to src"
 					" & dst width if peripheral is flow controller",
@@ -897,7 +1018,8 @@ static int pl08x_fill_llis_for_desc(struct pl08x_driver_data *pl08x,
 
 			cctl = pl08x_cctl_bits(cctl, bd.srcbus.buswidth,
 					bd.dstbus.buswidth, 0);
-			pl08x_fill_lli_for_desc(&bd, num_llis++, 0, cctl);
+			pl08x_fill_lli_for_desc(pl08x, &bd, num_llis++,
+					0, cctl, 0);
 			break;
 		}
 
@@ -908,9 +1030,9 @@ static int pl08x_fill_llis_for_desc(struct pl08x_driver_data *pl08x,
 		 */
 		if (bd.remainder < mbus->buswidth)
 			early_bytes = bd.remainder;
-		else if ((mbus->addr) % (mbus->buswidth)) {
-			early_bytes = mbus->buswidth - (mbus->addr) %
-				(mbus->buswidth);
+		else if (!IS_BUS_ALIGNED(mbus)) {
+			early_bytes = mbus->buswidth -
+				(mbus->addr & (mbus->buswidth - 1));
 			if ((bd.remainder - early_bytes) < mbus->buswidth)
 				early_bytes = bd.remainder;
 		}
@@ -919,8 +1041,8 @@ static int pl08x_fill_llis_for_desc(struct pl08x_driver_data *pl08x,
 			dev_vdbg(&pl08x->adev->dev,
 				"%s byte width LLIs (remain 0x%08x)\n",
 				__func__, bd.remainder);
-			prep_byte_width_lli(&bd, &cctl, early_bytes, num_llis++,
-				&total_bytes);
+			prep_byte_width_lli(pl08x, &bd, &cctl, early_bytes,
+				num_llis++, &total_bytes);
 		}
 
 		if (bd.remainder) {
@@ -928,7 +1050,7 @@ static int pl08x_fill_llis_for_desc(struct pl08x_driver_data *pl08x,
 			 * Master now aligned
 			 * - if slave is not then we must set its width down
 			 */
-			if (sbus->addr % sbus->buswidth) {
+			if (!IS_BUS_ALIGNED(sbus)) {
 				dev_dbg(&pl08x->adev->dev,
 					"%s set down bus width to one byte\n",
 					__func__);
@@ -941,7 +1063,7 @@ static int pl08x_fill_llis_for_desc(struct pl08x_driver_data *pl08x,
 			 * MIN(buswidths)
 			 */
 			max_bytes_per_lli = bd.srcbus.buswidth *
-				PL080_CONTROL_TRANSFER_SIZE_MASK;
+						pl08x->vd->max_transfer_size;
 			dev_vdbg(&pl08x->adev->dev,
 				"%s max bytes per lli = %zu\n",
 				__func__, max_bytes_per_lli);
@@ -976,8 +1098,8 @@ static int pl08x_fill_llis_for_desc(struct pl08x_driver_data *pl08x,
 
 				cctl = pl08x_cctl_bits(cctl, bd.srcbus.buswidth,
 					bd.dstbus.buswidth, tsize);
-				pl08x_fill_lli_for_desc(&bd, num_llis++,
-						lli_len, cctl);
+				pl08x_fill_lli_for_desc(pl08x, &bd, num_llis++,
+						lli_len, cctl, tsize);
 				total_bytes += lli_len;
 			}
 
@@ -988,8 +1110,8 @@ static int pl08x_fill_llis_for_desc(struct pl08x_driver_data *pl08x,
 				dev_vdbg(&pl08x->adev->dev,
 					"%s align with boundary, send odd bytes (remain %zu)\n",
 					__func__, bd.remainder);
-				prep_byte_width_lli(&bd, &cctl, bd.remainder,
-						num_llis++, &total_bytes);
+				prep_byte_width_lli(pl08x, &bd, &cctl,
+					bd.remainder, num_llis++, &total_bytes);
 			}
 		}
 
@@ -1003,33 +1125,25 @@ static int pl08x_fill_llis_for_desc(struct pl08x_driver_data *pl08x,
 		if (num_llis >= MAX_NUM_TSFR_LLIS) {
 			dev_err(&pl08x->adev->dev,
 				"%s need to increase MAX_NUM_TSFR_LLIS from 0x%08x\n",
-				__func__, (u32) MAX_NUM_TSFR_LLIS);
+				__func__, MAX_NUM_TSFR_LLIS);
 			return 0;
 		}
 	}
 
 	llis_va = txd->llis_va;
-	/* The final LLI terminates the LLI. */
-	llis_va[num_llis - 1].lli = 0;
-	/* The final LLI element shall also fire an interrupt. */
-	llis_va[num_llis - 1].cctl |= PL080_CONTROL_TC_IRQ_EN;
+	last_lli = llis_va + (num_llis - 1) * pl08x->lli_words;
 
-#ifdef VERBOSE_DEBUG
-	{
-		int i;
-
-		dev_vdbg(&pl08x->adev->dev,
-			 "%-3s %-9s  %-10s %-10s %-10s %s\n",
-			 "lli", "", "csrc", "cdst", "clli", "cctl");
-		for (i = 0; i < num_llis; i++) {
-			dev_vdbg(&pl08x->adev->dev,
-				 "%3d @%p: 0x%08x 0x%08x 0x%08x 0x%08x\n",
-				 i, &llis_va[i], llis_va[i].src,
-				 llis_va[i].dst, llis_va[i].lli, llis_va[i].cctl
-				);
-		}
+	if (txd->cyclic) {
+		/* Link back to the first LLI. */
+		last_lli[PL080_LLI_LLI] = txd->llis_bus | bd.lli_bus;
+	} else {
+		/* The final LLI terminates the LLI. */
+		last_lli[PL080_LLI_LLI] = 0;
+		/* The final LLI element shall also fire an interrupt. */
+		last_lli[PL080_LLI_CCTL] |= PL080_CONTROL_TC_IRQ_EN;
 	}
-#endif
+
+	pl08x_dump_lli(pl08x, llis_va, num_llis);
 
 	return num_llis;
 }
@@ -1305,6 +1419,7 @@ static int dma_set_runtime_config(struct dma_chan *chan,
 				  struct dma_slave_config *config)
 {
 	struct pl08x_dma_chan *plchan = to_pl08x_chan(chan);
+	struct pl08x_driver_data *pl08x = plchan->host;
 
 	if (!plchan->slave)
 		return -EINVAL;
@@ -1314,6 +1429,13 @@ static int dma_set_runtime_config(struct dma_chan *chan,
 	    config->dst_addr_width == DMA_SLAVE_BUSWIDTH_8_BYTES)
 		return -EINVAL;
 
+	if (config->device_fc && pl08x->vd->pl080s) {
+		dev_err(&pl08x->adev->dev,
+			"%s: PL080S does not support peripheral flow control\n",
+			__func__);
+		return -EINVAL;
+	}
+
 	plchan->cfg = *config;
 
 	return 0;
@@ -1404,25 +1526,19 @@ static struct dma_async_tx_descriptor *pl08x_prep_dma_memcpy(
 	return vchan_tx_prep(&plchan->vc, &txd->vd, flags);
 }
 
-static struct dma_async_tx_descriptor *pl08x_prep_slave_sg(
-		struct dma_chan *chan, struct scatterlist *sgl,
-		unsigned int sg_len, enum dma_transfer_direction direction,
-		unsigned long flags, void *context)
+static struct pl08x_txd *pl08x_init_txd(
+		struct dma_chan *chan,
+		enum dma_transfer_direction direction,
+		dma_addr_t *slave_addr)
 {
 	struct pl08x_dma_chan *plchan = to_pl08x_chan(chan);
 	struct pl08x_driver_data *pl08x = plchan->host;
 	struct pl08x_txd *txd;
-	struct pl08x_sg *dsg;
-	struct scatterlist *sg;
 	enum dma_slave_buswidth addr_width;
-	dma_addr_t slave_addr;
 	int ret, tmp;
 	u8 src_buses, dst_buses;
 	u32 maxburst, cctl;
 
-	dev_dbg(&pl08x->adev->dev, "%s prepare transaction of %d bytes from %s\n",
-			__func__, sg_dma_len(sgl), plchan->name);
-
 	txd = pl08x_get_txd(plchan);
 	if (!txd) {
 		dev_err(&pl08x->adev->dev, "%s no txd\n", __func__);
@@ -1436,14 +1552,14 @@ static struct dma_async_tx_descriptor *pl08x_prep_slave_sg(
 	 */
 	if (direction == DMA_MEM_TO_DEV) {
 		cctl = PL080_CONTROL_SRC_INCR;
-		slave_addr = plchan->cfg.dst_addr;
+		*slave_addr = plchan->cfg.dst_addr;
 		addr_width = plchan->cfg.dst_addr_width;
 		maxburst = plchan->cfg.dst_maxburst;
 		src_buses = pl08x->mem_buses;
 		dst_buses = plchan->cd->periph_buses;
 	} else if (direction == DMA_DEV_TO_MEM) {
 		cctl = PL080_CONTROL_DST_INCR;
-		slave_addr = plchan->cfg.src_addr;
+		*slave_addr = plchan->cfg.src_addr;
 		addr_width = plchan->cfg.src_addr_width;
 		maxburst = plchan->cfg.src_maxburst;
 		src_buses = plchan->cd->periph_buses;
@@ -1492,24 +1608,107 @@ static struct dma_async_tx_descriptor *pl08x_prep_slave_sg(
 	else
 		txd->ccfg |= plchan->signal << PL080_CONFIG_SRC_SEL_SHIFT;
 
+	return txd;
+}
+
+static int pl08x_tx_add_sg(struct pl08x_txd *txd,
+			   enum dma_transfer_direction direction,
+			   dma_addr_t slave_addr,
+			   dma_addr_t buf_addr,
+			   unsigned int len)
+{
+	struct pl08x_sg *dsg;
+
+	dsg = kzalloc(sizeof(struct pl08x_sg), GFP_NOWAIT);
+	if (!dsg)
+		return -ENOMEM;
+
+	list_add_tail(&dsg->node, &txd->dsg_list);
+
+	dsg->len = len;
+	if (direction == DMA_MEM_TO_DEV) {
+		dsg->src_addr = buf_addr;
+		dsg->dst_addr = slave_addr;
+	} else {
+		dsg->src_addr = slave_addr;
+		dsg->dst_addr = buf_addr;
+	}
+
+	return 0;
+}
+
+static struct dma_async_tx_descriptor *pl08x_prep_slave_sg(
+		struct dma_chan *chan, struct scatterlist *sgl,
+		unsigned int sg_len, enum dma_transfer_direction direction,
+		unsigned long flags, void *context)
+{
+	struct pl08x_dma_chan *plchan = to_pl08x_chan(chan);
+	struct pl08x_driver_data *pl08x = plchan->host;
+	struct pl08x_txd *txd;
+	struct scatterlist *sg;
+	int ret, tmp;
+	dma_addr_t slave_addr;
+
+	dev_dbg(&pl08x->adev->dev, "%s prepare transaction of %d bytes from %s\n",
+			__func__, sg_dma_len(sgl), plchan->name);
+
+	txd = pl08x_init_txd(chan, direction, &slave_addr);
+	if (!txd)
+		return NULL;
+
 	for_each_sg(sgl, sg, sg_len, tmp) {
-		dsg = kzalloc(sizeof(struct pl08x_sg), GFP_NOWAIT);
-		if (!dsg) {
+		ret = pl08x_tx_add_sg(txd, direction, slave_addr,
+				      sg_dma_address(sg),
+				      sg_dma_len(sg));
+		if (ret) {
 			pl08x_release_mux(plchan);
 			pl08x_free_txd(pl08x, txd);
 			dev_err(&pl08x->adev->dev, "%s no mem for pl080 sg\n",
 					__func__);
 			return NULL;
 		}
-		list_add_tail(&dsg->node, &txd->dsg_list);
+	}
 
-		dsg->len = sg_dma_len(sg);
-		if (direction == DMA_MEM_TO_DEV) {
-			dsg->src_addr = sg_dma_address(sg);
-			dsg->dst_addr = slave_addr;
-		} else {
-			dsg->src_addr = slave_addr;
-			dsg->dst_addr = sg_dma_address(sg);
+	ret = pl08x_fill_llis_for_desc(plchan->host, txd);
+	if (!ret) {
+		pl08x_release_mux(plchan);
+		pl08x_free_txd(pl08x, txd);
+		return NULL;
+	}
+
+	return vchan_tx_prep(&plchan->vc, &txd->vd, flags);
+}
+
+static struct dma_async_tx_descriptor *pl08x_prep_dma_cyclic(
+		struct dma_chan *chan, dma_addr_t buf_addr, size_t buf_len,
+		size_t period_len, enum dma_transfer_direction direction,
+		unsigned long flags, void *context)
+{
+	struct pl08x_dma_chan *plchan = to_pl08x_chan(chan);
+	struct pl08x_driver_data *pl08x = plchan->host;
+	struct pl08x_txd *txd;
+	int ret, tmp;
+	dma_addr_t slave_addr;
+
+	dev_dbg(&pl08x->adev->dev,
+		"%s prepare cyclic transaction of %d/%d bytes %s %s\n",
+		__func__, period_len, buf_len,
+		direction == DMA_MEM_TO_DEV ? "to" : "from",
+		plchan->name);
+
+	txd = pl08x_init_txd(chan, direction, &slave_addr);
+	if (!txd)
+		return NULL;
+
+	txd->cyclic = true;
+	txd->cctl |= PL080_CONTROL_TC_IRQ_EN;
+	for (tmp = 0; tmp < buf_len; tmp += period_len) {
+		ret = pl08x_tx_add_sg(txd, direction, slave_addr,
+				      buf_addr + tmp, period_len);
+		if (ret) {
+			pl08x_release_mux(plchan);
+			pl08x_free_txd(pl08x, txd);
+			return NULL;
 		}
 	}
 
@@ -1652,7 +1851,9 @@ static irqreturn_t pl08x_irq(int irq, void *dev)
 
 			spin_lock(&plchan->vc.lock);
 			tx = plchan->at;
-			if (tx) {
+			if (tx && tx->cyclic) {
+				vchan_cyclic_callback(&tx->vd);
+			} else if (tx) {
 				plchan->at = NULL;
 				/*
 				 * This descriptor is done, release its mux
@@ -1846,6 +2047,7 @@ static int pl08x_probe(struct amba_device *adev, const struct amba_id *id)
 {
 	struct pl08x_driver_data *pl08x;
 	const struct vendor_data *vd = id->data;
+	u32 tsfr_size;
 	int ret = 0;
 	int i;
 
@@ -1873,6 +2075,7 @@ static int pl08x_probe(struct amba_device *adev, const struct amba_id *id)
 
 	/* Initialize slave engine */
 	dma_cap_set(DMA_SLAVE, pl08x->slave.cap_mask);
+	dma_cap_set(DMA_CYCLIC, pl08x->slave.cap_mask);
 	pl08x->slave.dev = &adev->dev;
 	pl08x->slave.device_alloc_chan_resources = pl08x_alloc_chan_resources;
 	pl08x->slave.device_free_chan_resources = pl08x_free_chan_resources;
@@ -1880,6 +2083,7 @@ static int pl08x_probe(struct amba_device *adev, const struct amba_id *id)
 	pl08x->slave.device_tx_status = pl08x_dma_tx_status;
 	pl08x->slave.device_issue_pending = pl08x_issue_pending;
 	pl08x->slave.device_prep_slave_sg = pl08x_prep_slave_sg;
+	pl08x->slave.device_prep_dma_cyclic = pl08x_prep_dma_cyclic;
 	pl08x->slave.device_control = pl08x_control;
 
 	/* Get the platform data */
@@ -1902,9 +2106,15 @@ static int pl08x_probe(struct amba_device *adev, const struct amba_id *id)
 		pl08x->mem_buses = pl08x->pd->mem_buses;
 	}
 
+	if (vd->pl080s)
+		pl08x->lli_words = PL080S_LLI_WORDS;
+	else
+		pl08x->lli_words = PL080_LLI_WORDS;
+	tsfr_size = MAX_NUM_TSFR_LLIS * pl08x->lli_words * sizeof(u32);
+
 	/* A DMA memory pool for LLIs, align on 1-byte boundary */
 	pl08x->pool = dma_pool_create(DRIVER_NAME, &pl08x->adev->dev,
-			PL08X_LLI_TSFR_SIZE, PL08X_ALIGN, 0);
+						tsfr_size, PL08X_ALIGN, 0);
 	if (!pl08x->pool) {
 		ret = -ENOMEM;
 		goto out_no_lli_pool;
@@ -1947,6 +2157,7 @@ static int pl08x_probe(struct amba_device *adev, const struct amba_id *id)
 
 		ch->id = i;
 		ch->base = pl08x->base + PL080_Cx_BASE(i);
+		ch->reg_config = ch->base + vd->config_offset;
 		spin_lock_init(&ch->lock);
 
 		/*
@@ -1957,7 +2168,7 @@ static int pl08x_probe(struct amba_device *adev, const struct amba_id *id)
 		if (vd->nomadik) {
 			u32 val;
 
-			val = readl(ch->base + PL080_CH_CONFIG);
+			val = readl(ch->reg_config);
 			if (val & (PL080N_CONFIG_ITPROT | PL080N_CONFIG_SECPROT)) {
 				dev_info(&adev->dev, "physical channel %d reserved for secure access only\n", i);
 				ch->locked = true;
@@ -2008,8 +2219,8 @@ static int pl08x_probe(struct amba_device *adev, const struct amba_id *id)
 
 	amba_set_drvdata(adev, pl08x);
 	init_pl08x_debugfs(pl08x);
-	dev_info(&pl08x->adev->dev, "DMA: PL%03x rev%u at 0x%08llx irq %d\n",
-		 amba_part(adev), amba_rev(adev),
+	dev_info(&pl08x->adev->dev, "DMA: PL%03x%s rev%u at 0x%08llx irq %d\n",
+		 amba_part(adev), pl08x->vd->pl080s ? "s" : "", amba_rev(adev),
 		 (unsigned long long)adev->res.start, adev->irq[0]);
 
 	return 0;
@@ -2038,22 +2249,41 @@ out_no_pl08x:
 
 /* PL080 has 8 channels and the PL080 have just 2 */
 static struct vendor_data vendor_pl080 = {
+	.config_offset = PL080_CH_CONFIG,
 	.channels = 8,
 	.dualmaster = true,
+	.max_transfer_size = PL080_CONTROL_TRANSFER_SIZE_MASK,
 };
 
 static struct vendor_data vendor_nomadik = {
+	.config_offset = PL080_CH_CONFIG,
 	.channels = 8,
 	.dualmaster = true,
 	.nomadik = true,
+	.max_transfer_size = PL080_CONTROL_TRANSFER_SIZE_MASK,
+};
+
+static struct vendor_data vendor_pl080s = {
+	.config_offset = PL080S_CH_CONFIG,
+	.channels = 8,
+	.pl080s = true,
+	.max_transfer_size = PL080S_CONTROL_TRANSFER_SIZE_MASK,
 };
 
 static struct vendor_data vendor_pl081 = {
+	.config_offset = PL080_CH_CONFIG,
 	.channels = 2,
 	.dualmaster = false,
+	.max_transfer_size = PL080_CONTROL_TRANSFER_SIZE_MASK,
 };
 
 static struct amba_id pl08x_ids[] = {
+	/* Samsung PL080S variant */
+	{
+		.id	= 0x0a141080,
+		.mask	= 0xffffffff,
+		.data	= &vendor_pl080s,
+	},
 	/* PL080 */
 	{
 		.id	= 0x00041080,
diff --git a/drivers/dma/coh901318.c b/drivers/dma/coh901318.c
index 9bfaddd57ef1..31011d2a26fc 100644
--- a/drivers/dma/coh901318.c
+++ b/drivers/dma/coh901318.c
@@ -1339,15 +1339,14 @@ static int coh901318_debugfs_read(struct file *file, char __user *buf,
 {
 	u64 started_channels = debugfs_dma_base->pm.started_channels;
 	int pool_count = debugfs_dma_base->pool.debugfs_pool_counter;
-	int i;
-	int ret = 0;
 	char *dev_buf;
 	char *tmp;
-	int dev_size;
+	int ret;
+	int i;
 
 	dev_buf = kmalloc(4*1024, GFP_KERNEL);
 	if (dev_buf == NULL)
-		goto err_kmalloc;
+		return -ENOMEM;
 	tmp = dev_buf;
 
 	tmp += sprintf(tmp, "DMA -- enabled dma channels\n");
@@ -1357,26 +1356,11 @@ static int coh901318_debugfs_read(struct file *file, char __user *buf,
 			tmp += sprintf(tmp, "channel %d\n", i);
 
 	tmp += sprintf(tmp, "Pool alloc nbr %d\n", pool_count);
-	dev_size = tmp  - dev_buf;
-
-	/* No more to read if offset != 0 */
-	if (*f_pos > dev_size)
-		goto out;
 
-	if (count > dev_size - *f_pos)
-		count = dev_size - *f_pos;
-
-	if (copy_to_user(buf, dev_buf + *f_pos, count))
-		ret = -EINVAL;
-	ret = count;
-	*f_pos += count;
-
- out:
+	ret = simple_read_from_buffer(buf, count, f_pos, dev_buf, 
+					tmp - dev_buf);
 	kfree(dev_buf);
 	return ret;
-
- err_kmalloc:
-	return 0;
 }
 
 static const struct file_operations coh901318_debugfs_status_operations = {
diff --git a/drivers/dma/cppi41.c b/drivers/dma/cppi41.c
new file mode 100644
index 000000000000..7c82b92f9b16
--- /dev/null
+++ b/drivers/dma/cppi41.c
@@ -0,0 +1,1059 @@
+#include <linux/dmaengine.h>
+#include <linux/dma-mapping.h>
+#include <linux/platform_device.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/slab.h>
+#include <linux/of_dma.h>
+#include <linux/of_irq.h>
+#include <linux/dmapool.h>
+#include <linux/interrupt.h>
+#include <linux/of_address.h>
+#include <linux/pm_runtime.h>
+#include "dmaengine.h"
+
+#define DESC_TYPE	27
+#define DESC_TYPE_HOST	0x10
+#define DESC_TYPE_TEARD	0x13
+
+#define TD_DESC_IS_RX	(1 << 16)
+#define TD_DESC_DMA_NUM	10
+
+#define DESC_LENGTH_BITS_NUM	21
+
+#define DESC_TYPE_USB	(5 << 26)
+#define DESC_PD_COMPLETE	(1 << 31)
+
+/* DMA engine */
+#define DMA_TDFDQ	4
+#define DMA_TXGCR(x)	(0x800 + (x) * 0x20)
+#define DMA_RXGCR(x)	(0x808 + (x) * 0x20)
+#define RXHPCRA0		4
+
+#define GCR_CHAN_ENABLE		(1 << 31)
+#define GCR_TEARDOWN		(1 << 30)
+#define GCR_STARV_RETRY		(1 << 24)
+#define GCR_DESC_TYPE_HOST	(1 << 14)
+
+/* DMA scheduler */
+#define DMA_SCHED_CTRL		0
+#define DMA_SCHED_CTRL_EN	(1 << 31)
+#define DMA_SCHED_WORD(x)	((x) * 4 + 0x800)
+
+#define SCHED_ENTRY0_CHAN(x)	((x) << 0)
+#define SCHED_ENTRY0_IS_RX	(1 << 7)
+
+#define SCHED_ENTRY1_CHAN(x)	((x) << 8)
+#define SCHED_ENTRY1_IS_RX	(1 << 15)
+
+#define SCHED_ENTRY2_CHAN(x)	((x) << 16)
+#define SCHED_ENTRY2_IS_RX	(1 << 23)
+
+#define SCHED_ENTRY3_CHAN(x)	((x) << 24)
+#define SCHED_ENTRY3_IS_RX	(1 << 31)
+
+/* Queue manager */
+/* 4 KiB of memory for descriptors, 2 for each endpoint */
+#define ALLOC_DECS_NUM		128
+#define DESCS_AREAS		1
+#define TOTAL_DESCS_NUM		(ALLOC_DECS_NUM * DESCS_AREAS)
+#define QMGR_SCRATCH_SIZE	(TOTAL_DESCS_NUM * 4)
+
+#define QMGR_LRAM0_BASE		0x80
+#define QMGR_LRAM_SIZE		0x84
+#define QMGR_LRAM1_BASE		0x88
+#define QMGR_MEMBASE(x)		(0x1000 + (x) * 0x10)
+#define QMGR_MEMCTRL(x)		(0x1004 + (x) * 0x10)
+#define QMGR_MEMCTRL_IDX_SH	16
+#define QMGR_MEMCTRL_DESC_SH	8
+
+#define QMGR_NUM_PEND	5
+#define QMGR_PEND(x)	(0x90 + (x) * 4)
+
+#define QMGR_PENDING_SLOT_Q(x)	(x / 32)
+#define QMGR_PENDING_BIT_Q(x)	(x % 32)
+
+#define QMGR_QUEUE_A(n)	(0x2000 + (n) * 0x10)
+#define QMGR_QUEUE_B(n)	(0x2004 + (n) * 0x10)
+#define QMGR_QUEUE_C(n)	(0x2008 + (n) * 0x10)
+#define QMGR_QUEUE_D(n)	(0x200c + (n) * 0x10)
+
+/* Glue layer specific */
+/* USBSS  / USB AM335x */
+#define USBSS_IRQ_STATUS	0x28
+#define USBSS_IRQ_ENABLER	0x2c
+#define USBSS_IRQ_CLEARR	0x30
+
+#define USBSS_IRQ_PD_COMP	(1 <<  2)
+
+struct cppi41_channel {
+	struct dma_chan chan;
+	struct dma_async_tx_descriptor txd;
+	struct cppi41_dd *cdd;
+	struct cppi41_desc *desc;
+	dma_addr_t desc_phys;
+	void __iomem *gcr_reg;
+	int is_tx;
+	u32 residue;
+
+	unsigned int q_num;
+	unsigned int q_comp_num;
+	unsigned int port_num;
+
+	unsigned td_retry;
+	unsigned td_queued:1;
+	unsigned td_seen:1;
+	unsigned td_desc_seen:1;
+};
+
+struct cppi41_desc {
+	u32 pd0;
+	u32 pd1;
+	u32 pd2;
+	u32 pd3;
+	u32 pd4;
+	u32 pd5;
+	u32 pd6;
+	u32 pd7;
+} __aligned(32);
+
+struct chan_queues {
+	u16 submit;
+	u16 complete;
+};
+
+struct cppi41_dd {
+	struct dma_device ddev;
+
+	void *qmgr_scratch;
+	dma_addr_t scratch_phys;
+
+	struct cppi41_desc *cd;
+	dma_addr_t descs_phys;
+	u32 first_td_desc;
+	struct cppi41_channel *chan_busy[ALLOC_DECS_NUM];
+
+	void __iomem *usbss_mem;
+	void __iomem *ctrl_mem;
+	void __iomem *sched_mem;
+	void __iomem *qmgr_mem;
+	unsigned int irq;
+	const struct chan_queues *queues_rx;
+	const struct chan_queues *queues_tx;
+	struct chan_queues td_queue;
+};
+
+#define FIST_COMPLETION_QUEUE	93
+static struct chan_queues usb_queues_tx[] = {
+	/* USB0 ENDP 1 */
+	[ 0] = { .submit = 32, .complete =  93},
+	[ 1] = { .submit = 34, .complete =  94},
+	[ 2] = { .submit = 36, .complete =  95},
+	[ 3] = { .submit = 38, .complete =  96},
+	[ 4] = { .submit = 40, .complete =  97},
+	[ 5] = { .submit = 42, .complete =  98},
+	[ 6] = { .submit = 44, .complete =  99},
+	[ 7] = { .submit = 46, .complete = 100},
+	[ 8] = { .submit = 48, .complete = 101},
+	[ 9] = { .submit = 50, .complete = 102},
+	[10] = { .submit = 52, .complete = 103},
+	[11] = { .submit = 54, .complete = 104},
+	[12] = { .submit = 56, .complete = 105},
+	[13] = { .submit = 58, .complete = 106},
+	[14] = { .submit = 60, .complete = 107},
+
+	/* USB1 ENDP1 */
+	[15] = { .submit = 62, .complete = 125},
+	[16] = { .submit = 64, .complete = 126},
+	[17] = { .submit = 66, .complete = 127},
+	[18] = { .submit = 68, .complete = 128},
+	[19] = { .submit = 70, .complete = 129},
+	[20] = { .submit = 72, .complete = 130},
+	[21] = { .submit = 74, .complete = 131},
+	[22] = { .submit = 76, .complete = 132},
+	[23] = { .submit = 78, .complete = 133},
+	[24] = { .submit = 80, .complete = 134},
+	[25] = { .submit = 82, .complete = 135},
+	[26] = { .submit = 84, .complete = 136},
+	[27] = { .submit = 86, .complete = 137},
+	[28] = { .submit = 88, .complete = 138},
+	[29] = { .submit = 90, .complete = 139},
+};
+
+static const struct chan_queues usb_queues_rx[] = {
+	/* USB0 ENDP 1 */
+	[ 0] = { .submit =  1, .complete = 109},
+	[ 1] = { .submit =  2, .complete = 110},
+	[ 2] = { .submit =  3, .complete = 111},
+	[ 3] = { .submit =  4, .complete = 112},
+	[ 4] = { .submit =  5, .complete = 113},
+	[ 5] = { .submit =  6, .complete = 114},
+	[ 6] = { .submit =  7, .complete = 115},
+	[ 7] = { .submit =  8, .complete = 116},
+	[ 8] = { .submit =  9, .complete = 117},
+	[ 9] = { .submit = 10, .complete = 118},
+	[10] = { .submit = 11, .complete = 119},
+	[11] = { .submit = 12, .complete = 120},
+	[12] = { .submit = 13, .complete = 121},
+	[13] = { .submit = 14, .complete = 122},
+	[14] = { .submit = 15, .complete = 123},
+
+	/* USB1 ENDP 1 */
+	[15] = { .submit = 16, .complete = 141},
+	[16] = { .submit = 17, .complete = 142},
+	[17] = { .submit = 18, .complete = 143},
+	[18] = { .submit = 19, .complete = 144},
+	[19] = { .submit = 20, .complete = 145},
+	[20] = { .submit = 21, .complete = 146},
+	[21] = { .submit = 22, .complete = 147},
+	[22] = { .submit = 23, .complete = 148},
+	[23] = { .submit = 24, .complete = 149},
+	[24] = { .submit = 25, .complete = 150},
+	[25] = { .submit = 26, .complete = 151},
+	[26] = { .submit = 27, .complete = 152},
+	[27] = { .submit = 28, .complete = 153},
+	[28] = { .submit = 29, .complete = 154},
+	[29] = { .submit = 30, .complete = 155},
+};
+
+struct cppi_glue_infos {
+	irqreturn_t (*isr)(int irq, void *data);
+	const struct chan_queues *queues_rx;
+	const struct chan_queues *queues_tx;
+	struct chan_queues td_queue;
+};
+
+static struct cppi41_channel *to_cpp41_chan(struct dma_chan *c)
+{
+	return container_of(c, struct cppi41_channel, chan);
+}
+
+static struct cppi41_channel *desc_to_chan(struct cppi41_dd *cdd, u32 desc)
+{
+	struct cppi41_channel *c;
+	u32 descs_size;
+	u32 desc_num;
+
+	descs_size = sizeof(struct cppi41_desc) * ALLOC_DECS_NUM;
+
+	if (!((desc >= cdd->descs_phys) &&
+			(desc < (cdd->descs_phys + descs_size)))) {
+		return NULL;
+	}
+
+	desc_num = (desc - cdd->descs_phys) / sizeof(struct cppi41_desc);
+	BUG_ON(desc_num >= ALLOC_DECS_NUM);
+	c = cdd->chan_busy[desc_num];
+	cdd->chan_busy[desc_num] = NULL;
+	return c;
+}
+
+static void cppi_writel(u32 val, void *__iomem *mem)
+{
+	__raw_writel(val, mem);
+}
+
+static u32 cppi_readl(void *__iomem *mem)
+{
+	return __raw_readl(mem);
+}
+
+static u32 pd_trans_len(u32 val)
+{
+	return val & ((1 << (DESC_LENGTH_BITS_NUM + 1)) - 1);
+}
+
+static irqreturn_t cppi41_irq(int irq, void *data)
+{
+	struct cppi41_dd *cdd = data;
+	struct cppi41_channel *c;
+	u32 status;
+	int i;
+
+	status = cppi_readl(cdd->usbss_mem + USBSS_IRQ_STATUS);
+	if (!(status & USBSS_IRQ_PD_COMP))
+		return IRQ_NONE;
+	cppi_writel(status, cdd->usbss_mem + USBSS_IRQ_STATUS);
+
+	for (i = QMGR_PENDING_SLOT_Q(FIST_COMPLETION_QUEUE); i < QMGR_NUM_PEND;
+			i++) {
+		u32 val;
+		u32 q_num;
+
+		val = cppi_readl(cdd->qmgr_mem + QMGR_PEND(i));
+		if (i == QMGR_PENDING_SLOT_Q(FIST_COMPLETION_QUEUE) && val) {
+			u32 mask;
+			/* set corresponding bit for completetion Q 93 */
+			mask = 1 << QMGR_PENDING_BIT_Q(FIST_COMPLETION_QUEUE);
+			/* not set all bits for queues less than Q 93 */
+			mask--;
+			/* now invert and keep only Q 93+ set */
+			val &= ~mask;
+		}
+
+		if (val)
+			__iormb();
+
+		while (val) {
+			u32 desc;
+
+			q_num = __fls(val);
+			val &= ~(1 << q_num);
+			q_num += 32 * i;
+			desc = cppi_readl(cdd->qmgr_mem + QMGR_QUEUE_D(q_num));
+			desc &= ~0x1f;
+			c = desc_to_chan(cdd, desc);
+			if (WARN_ON(!c)) {
+				pr_err("%s() q %d desc %08x\n", __func__,
+						q_num, desc);
+				continue;
+			}
+			c->residue = pd_trans_len(c->desc->pd6) -
+				pd_trans_len(c->desc->pd0);
+
+			dma_cookie_complete(&c->txd);
+			c->txd.callback(c->txd.callback_param);
+		}
+	}
+	return IRQ_HANDLED;
+}
+
+static dma_cookie_t cppi41_tx_submit(struct dma_async_tx_descriptor *tx)
+{
+	dma_cookie_t cookie;
+
+	cookie = dma_cookie_assign(tx);
+
+	return cookie;
+}
+
+static int cppi41_dma_alloc_chan_resources(struct dma_chan *chan)
+{
+	struct cppi41_channel *c = to_cpp41_chan(chan);
+
+	dma_cookie_init(chan);
+	dma_async_tx_descriptor_init(&c->txd, chan);
+	c->txd.tx_submit = cppi41_tx_submit;
+
+	if (!c->is_tx)
+		cppi_writel(c->q_num, c->gcr_reg + RXHPCRA0);
+
+	return 0;
+}
+
+static void cppi41_dma_free_chan_resources(struct dma_chan *chan)
+{
+}
+
+static enum dma_status cppi41_dma_tx_status(struct dma_chan *chan,
+	dma_cookie_t cookie, struct dma_tx_state *txstate)
+{
+	struct cppi41_channel *c = to_cpp41_chan(chan);
+	enum dma_status ret;
+
+	/* lock */
+	ret = dma_cookie_status(chan, cookie, txstate);
+	if (txstate && ret == DMA_SUCCESS)
+		txstate->residue = c->residue;
+	/* unlock */
+
+	return ret;
+}
+
+static void push_desc_queue(struct cppi41_channel *c)
+{
+	struct cppi41_dd *cdd = c->cdd;
+	u32 desc_num;
+	u32 desc_phys;
+	u32 reg;
+
+	desc_phys = lower_32_bits(c->desc_phys);
+	desc_num = (desc_phys - cdd->descs_phys) / sizeof(struct cppi41_desc);
+	WARN_ON(cdd->chan_busy[desc_num]);
+	cdd->chan_busy[desc_num] = c;
+
+	reg = (sizeof(struct cppi41_desc) - 24) / 4;
+	reg |= desc_phys;
+	cppi_writel(reg, cdd->qmgr_mem + QMGR_QUEUE_D(c->q_num));
+}
+
+static void cppi41_dma_issue_pending(struct dma_chan *chan)
+{
+	struct cppi41_channel *c = to_cpp41_chan(chan);
+	u32 reg;
+
+	c->residue = 0;
+
+	reg = GCR_CHAN_ENABLE;
+	if (!c->is_tx) {
+		reg |= GCR_STARV_RETRY;
+		reg |= GCR_DESC_TYPE_HOST;
+		reg |= c->q_comp_num;
+	}
+
+	cppi_writel(reg, c->gcr_reg);
+
+	/*
+	 * We don't use writel() but __raw_writel() so we have to make sure
+	 * that the DMA descriptor in coherent memory made to the main memory
+	 * before starting the dma engine.
+	 */
+	__iowmb();
+	push_desc_queue(c);
+}
+
+static u32 get_host_pd0(u32 length)
+{
+	u32 reg;
+
+	reg = DESC_TYPE_HOST << DESC_TYPE;
+	reg |= length;
+
+	return reg;
+}
+
+static u32 get_host_pd1(struct cppi41_channel *c)
+{
+	u32 reg;
+
+	reg = 0;
+
+	return reg;
+}
+
+static u32 get_host_pd2(struct cppi41_channel *c)
+{
+	u32 reg;
+
+	reg = DESC_TYPE_USB;
+	reg |= c->q_comp_num;
+
+	return reg;
+}
+
+static u32 get_host_pd3(u32 length)
+{
+	u32 reg;
+
+	/* PD3 = packet size */
+	reg = length;
+
+	return reg;
+}
+
+static u32 get_host_pd6(u32 length)
+{
+	u32 reg;
+
+	/* PD6 buffer size */
+	reg = DESC_PD_COMPLETE;
+	reg |= length;
+
+	return reg;
+}
+
+static u32 get_host_pd4_or_7(u32 addr)
+{
+	u32 reg;
+
+	reg = addr;
+
+	return reg;
+}
+
+static u32 get_host_pd5(void)
+{
+	u32 reg;
+
+	reg = 0;
+
+	return reg;
+}
+
+static struct dma_async_tx_descriptor *cppi41_dma_prep_slave_sg(
+	struct dma_chan *chan, struct scatterlist *sgl, unsigned sg_len,
+	enum dma_transfer_direction dir, unsigned long tx_flags, void *context)
+{
+	struct cppi41_channel *c = to_cpp41_chan(chan);
+	struct cppi41_desc *d;
+	struct scatterlist *sg;
+	unsigned int i;
+	unsigned int num;
+
+	num = 0;
+	d = c->desc;
+	for_each_sg(sgl, sg, sg_len, i) {
+		u32 addr;
+		u32 len;
+
+		/* We need to use more than one desc once musb supports sg */
+		BUG_ON(num > 0);
+		addr = lower_32_bits(sg_dma_address(sg));
+		len = sg_dma_len(sg);
+
+		d->pd0 = get_host_pd0(len);
+		d->pd1 = get_host_pd1(c);
+		d->pd2 = get_host_pd2(c);
+		d->pd3 = get_host_pd3(len);
+		d->pd4 = get_host_pd4_or_7(addr);
+		d->pd5 = get_host_pd5();
+		d->pd6 = get_host_pd6(len);
+		d->pd7 = get_host_pd4_or_7(addr);
+
+		d++;
+	}
+
+	return &c->txd;
+}
+
+static int cpp41_cfg_chan(struct cppi41_channel *c,
+		struct dma_slave_config *cfg)
+{
+	return 0;
+}
+
+static void cppi41_compute_td_desc(struct cppi41_desc *d)
+{
+	d->pd0 = DESC_TYPE_TEARD << DESC_TYPE;
+}
+
+static u32 cppi41_pop_desc(struct cppi41_dd *cdd, unsigned queue_num)
+{
+	u32 desc;
+
+	desc = cppi_readl(cdd->qmgr_mem + QMGR_QUEUE_D(queue_num));
+	desc &= ~0x1f;
+	return desc;
+}
+
+static int cppi41_tear_down_chan(struct cppi41_channel *c)
+{
+	struct cppi41_dd *cdd = c->cdd;
+	struct cppi41_desc *td;
+	u32 reg;
+	u32 desc_phys;
+	u32 td_desc_phys;
+
+	td = cdd->cd;
+	td += cdd->first_td_desc;
+
+	td_desc_phys = cdd->descs_phys;
+	td_desc_phys += cdd->first_td_desc * sizeof(struct cppi41_desc);
+
+	if (!c->td_queued) {
+		cppi41_compute_td_desc(td);
+		__iowmb();
+
+		reg = (sizeof(struct cppi41_desc) - 24) / 4;
+		reg |= td_desc_phys;
+		cppi_writel(reg, cdd->qmgr_mem +
+				QMGR_QUEUE_D(cdd->td_queue.submit));
+
+		reg = GCR_CHAN_ENABLE;
+		if (!c->is_tx) {
+			reg |= GCR_STARV_RETRY;
+			reg |= GCR_DESC_TYPE_HOST;
+			reg |= c->q_comp_num;
+		}
+		reg |= GCR_TEARDOWN;
+		cppi_writel(reg, c->gcr_reg);
+		c->td_queued = 1;
+		c->td_retry = 100;
+	}
+
+	if (!c->td_seen) {
+		unsigned td_comp_queue;
+
+		if (c->is_tx)
+			td_comp_queue =  cdd->td_queue.complete;
+		else
+			td_comp_queue =  c->q_comp_num;
+
+		desc_phys = cppi41_pop_desc(cdd, td_comp_queue);
+		if (desc_phys) {
+			__iormb();
+
+			if (desc_phys == td_desc_phys) {
+				u32 pd0;
+				pd0 = td->pd0;
+				WARN_ON((pd0 >> DESC_TYPE) != DESC_TYPE_TEARD);
+				WARN_ON(!c->is_tx && !(pd0 & TD_DESC_IS_RX));
+				WARN_ON((pd0 & 0x1f) != c->port_num);
+			} else {
+				WARN_ON_ONCE(1);
+			}
+			c->td_seen = 1;
+		}
+	}
+	if (!c->td_desc_seen) {
+		desc_phys = cppi41_pop_desc(cdd, c->q_comp_num);
+		if (desc_phys) {
+			__iormb();
+			WARN_ON(c->desc_phys != desc_phys);
+			c->td_desc_seen = 1;
+		}
+	}
+	c->td_retry--;
+	/*
+	 * If the TX descriptor / channel is in use, the caller needs to poke
+	 * his TD bit multiple times. After that he hardware releases the
+	 * transfer descriptor followed by TD descriptor. Waiting seems not to
+	 * cause any difference.
+	 * RX seems to be thrown out right away. However once the TearDown
+	 * descriptor gets through we are done. If we have seens the transfer
+	 * descriptor before the TD we fetch it from enqueue, it has to be
+	 * there waiting for us.
+	 */
+	if (!c->td_seen && c->td_retry)
+		return -EAGAIN;
+
+	WARN_ON(!c->td_retry);
+	if (!c->td_desc_seen) {
+		desc_phys = cppi_readl(cdd->qmgr_mem + QMGR_QUEUE_D(c->q_num));
+		WARN_ON(!desc_phys);
+	}
+
+	c->td_queued = 0;
+	c->td_seen = 0;
+	c->td_desc_seen = 0;
+	cppi_writel(0, c->gcr_reg);
+	return 0;
+}
+
+static int cppi41_stop_chan(struct dma_chan *chan)
+{
+	struct cppi41_channel *c = to_cpp41_chan(chan);
+	struct cppi41_dd *cdd = c->cdd;
+	u32 desc_num;
+	u32 desc_phys;
+	int ret;
+
+	ret = cppi41_tear_down_chan(c);
+	if (ret)
+		return ret;
+
+	desc_phys = lower_32_bits(c->desc_phys);
+	desc_num = (desc_phys - cdd->descs_phys) / sizeof(struct cppi41_desc);
+	WARN_ON(!cdd->chan_busy[desc_num]);
+	cdd->chan_busy[desc_num] = NULL;
+
+	return 0;
+}
+
+static int cppi41_dma_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd,
+	unsigned long arg)
+{
+	struct cppi41_channel *c = to_cpp41_chan(chan);
+	int ret;
+
+	switch (cmd) {
+	case DMA_SLAVE_CONFIG:
+		ret = cpp41_cfg_chan(c, (struct dma_slave_config *) arg);
+		break;
+
+	case DMA_TERMINATE_ALL:
+		ret = cppi41_stop_chan(chan);
+		break;
+
+	default:
+		ret = -ENXIO;
+		break;
+	}
+	return ret;
+}
+
+static void cleanup_chans(struct cppi41_dd *cdd)
+{
+	while (!list_empty(&cdd->ddev.channels)) {
+		struct cppi41_channel *cchan;
+
+		cchan = list_first_entry(&cdd->ddev.channels,
+				struct cppi41_channel, chan.device_node);
+		list_del(&cchan->chan.device_node);
+		kfree(cchan);
+	}
+}
+
+static int cppi41_add_chans(struct platform_device *pdev, struct cppi41_dd *cdd)
+{
+	struct cppi41_channel *cchan;
+	int i;
+	int ret;
+	u32 n_chans;
+
+	ret = of_property_read_u32(pdev->dev.of_node, "#dma-channels",
+			&n_chans);
+	if (ret)
+		return ret;
+	/*
+	 * The channels can only be used as TX or as RX. So we add twice
+	 * that much dma channels because USB can only do RX or TX.
+	 */
+	n_chans *= 2;
+
+	for (i = 0; i < n_chans; i++) {
+		cchan = kzalloc(sizeof(*cchan), GFP_KERNEL);
+		if (!cchan)
+			goto err;
+
+		cchan->cdd = cdd;
+		if (i & 1) {
+			cchan->gcr_reg = cdd->ctrl_mem + DMA_TXGCR(i >> 1);
+			cchan->is_tx = 1;
+		} else {
+			cchan->gcr_reg = cdd->ctrl_mem + DMA_RXGCR(i >> 1);
+			cchan->is_tx = 0;
+		}
+		cchan->port_num = i >> 1;
+		cchan->desc = &cdd->cd[i];
+		cchan->desc_phys = cdd->descs_phys;
+		cchan->desc_phys += i * sizeof(struct cppi41_desc);
+		cchan->chan.device = &cdd->ddev;
+		list_add_tail(&cchan->chan.device_node, &cdd->ddev.channels);
+	}
+	cdd->first_td_desc = n_chans;
+
+	return 0;
+err:
+	cleanup_chans(cdd);
+	return -ENOMEM;
+}
+
+static void purge_descs(struct platform_device *pdev, struct cppi41_dd *cdd)
+{
+	unsigned int mem_decs;
+	int i;
+
+	mem_decs = ALLOC_DECS_NUM * sizeof(struct cppi41_desc);
+
+	for (i = 0; i < DESCS_AREAS; i++) {
+
+		cppi_writel(0, cdd->qmgr_mem + QMGR_MEMBASE(i));
+		cppi_writel(0, cdd->qmgr_mem + QMGR_MEMCTRL(i));
+
+		dma_free_coherent(&pdev->dev, mem_decs, cdd->cd,
+				cdd->descs_phys);
+	}
+}
+
+static void disable_sched(struct cppi41_dd *cdd)
+{
+	cppi_writel(0, cdd->sched_mem + DMA_SCHED_CTRL);
+}
+
+static void deinit_cpii41(struct platform_device *pdev, struct cppi41_dd *cdd)
+{
+	disable_sched(cdd);
+
+	purge_descs(pdev, cdd);
+
+	cppi_writel(0, cdd->qmgr_mem + QMGR_LRAM0_BASE);
+	cppi_writel(0, cdd->qmgr_mem + QMGR_LRAM0_BASE);
+	dma_free_coherent(&pdev->dev, QMGR_SCRATCH_SIZE, cdd->qmgr_scratch,
+			cdd->scratch_phys);
+}
+
+static int init_descs(struct platform_device *pdev, struct cppi41_dd *cdd)
+{
+	unsigned int desc_size;
+	unsigned int mem_decs;
+	int i;
+	u32 reg;
+	u32 idx;
+
+	BUILD_BUG_ON(sizeof(struct cppi41_desc) &
+			(sizeof(struct cppi41_desc) - 1));
+	BUILD_BUG_ON(sizeof(struct cppi41_desc) < 32);
+	BUILD_BUG_ON(ALLOC_DECS_NUM < 32);
+
+	desc_size = sizeof(struct cppi41_desc);
+	mem_decs = ALLOC_DECS_NUM * desc_size;
+
+	idx = 0;
+	for (i = 0; i < DESCS_AREAS; i++) {
+
+		reg = idx << QMGR_MEMCTRL_IDX_SH;
+		reg |= (ilog2(desc_size) - 5) << QMGR_MEMCTRL_DESC_SH;
+		reg |= ilog2(ALLOC_DECS_NUM) - 5;
+
+		BUILD_BUG_ON(DESCS_AREAS != 1);
+		cdd->cd = dma_alloc_coherent(&pdev->dev, mem_decs,
+				&cdd->descs_phys, GFP_KERNEL);
+		if (!cdd->cd)
+			return -ENOMEM;
+
+		cppi_writel(cdd->descs_phys, cdd->qmgr_mem + QMGR_MEMBASE(i));
+		cppi_writel(reg, cdd->qmgr_mem + QMGR_MEMCTRL(i));
+
+		idx += ALLOC_DECS_NUM;
+	}
+	return 0;
+}
+
+static void init_sched(struct cppi41_dd *cdd)
+{
+	unsigned ch;
+	unsigned word;
+	u32 reg;
+
+	word = 0;
+	cppi_writel(0, cdd->sched_mem + DMA_SCHED_CTRL);
+	for (ch = 0; ch < 15 * 2; ch += 2) {
+
+		reg = SCHED_ENTRY0_CHAN(ch);
+		reg |= SCHED_ENTRY1_CHAN(ch) | SCHED_ENTRY1_IS_RX;
+
+		reg |= SCHED_ENTRY2_CHAN(ch + 1);
+		reg |= SCHED_ENTRY3_CHAN(ch + 1) | SCHED_ENTRY3_IS_RX;
+		cppi_writel(reg, cdd->sched_mem + DMA_SCHED_WORD(word));
+		word++;
+	}
+	reg = 15 * 2 * 2 - 1;
+	reg |= DMA_SCHED_CTRL_EN;
+	cppi_writel(reg, cdd->sched_mem + DMA_SCHED_CTRL);
+}
+
+static int init_cppi41(struct platform_device *pdev, struct cppi41_dd *cdd)
+{
+	int ret;
+
+	BUILD_BUG_ON(QMGR_SCRATCH_SIZE > ((1 << 14) - 1));
+	cdd->qmgr_scratch = dma_alloc_coherent(&pdev->dev, QMGR_SCRATCH_SIZE,
+			&cdd->scratch_phys, GFP_KERNEL);
+	if (!cdd->qmgr_scratch)
+		return -ENOMEM;
+
+	cppi_writel(cdd->scratch_phys, cdd->qmgr_mem + QMGR_LRAM0_BASE);
+	cppi_writel(QMGR_SCRATCH_SIZE, cdd->qmgr_mem + QMGR_LRAM_SIZE);
+	cppi_writel(0, cdd->qmgr_mem + QMGR_LRAM1_BASE);
+
+	ret = init_descs(pdev, cdd);
+	if (ret)
+		goto err_td;
+
+	cppi_writel(cdd->td_queue.submit, cdd->ctrl_mem + DMA_TDFDQ);
+	init_sched(cdd);
+	return 0;
+err_td:
+	deinit_cpii41(pdev, cdd);
+	return ret;
+}
+
+static struct platform_driver cpp41_dma_driver;
+/*
+ * The param format is:
+ * X Y
+ * X: Port
+ * Y: 0 = RX else TX
+ */
+#define INFO_PORT	0
+#define INFO_IS_TX	1
+
+static bool cpp41_dma_filter_fn(struct dma_chan *chan, void *param)
+{
+	struct cppi41_channel *cchan;
+	struct cppi41_dd *cdd;
+	const struct chan_queues *queues;
+	u32 *num = param;
+
+	if (chan->device->dev->driver != &cpp41_dma_driver.driver)
+		return false;
+
+	cchan = to_cpp41_chan(chan);
+
+	if (cchan->port_num != num[INFO_PORT])
+		return false;
+
+	if (cchan->is_tx && !num[INFO_IS_TX])
+		return false;
+	cdd = cchan->cdd;
+	if (cchan->is_tx)
+		queues = cdd->queues_tx;
+	else
+		queues = cdd->queues_rx;
+
+	BUILD_BUG_ON(ARRAY_SIZE(usb_queues_rx) != ARRAY_SIZE(usb_queues_tx));
+	if (WARN_ON(cchan->port_num > ARRAY_SIZE(usb_queues_rx)))
+		return false;
+
+	cchan->q_num = queues[cchan->port_num].submit;
+	cchan->q_comp_num = queues[cchan->port_num].complete;
+	return true;
+}
+
+static struct of_dma_filter_info cpp41_dma_info = {
+	.filter_fn = cpp41_dma_filter_fn,
+};
+
+static struct dma_chan *cppi41_dma_xlate(struct of_phandle_args *dma_spec,
+		struct of_dma *ofdma)
+{
+	int count = dma_spec->args_count;
+	struct of_dma_filter_info *info = ofdma->of_dma_data;
+
+	if (!info || !info->filter_fn)
+		return NULL;
+
+	if (count != 2)
+		return NULL;
+
+	return dma_request_channel(info->dma_cap, info->filter_fn,
+			&dma_spec->args[0]);
+}
+
+static const struct cppi_glue_infos usb_infos = {
+	.isr = cppi41_irq,
+	.queues_rx = usb_queues_rx,
+	.queues_tx = usb_queues_tx,
+	.td_queue = { .submit = 31, .complete = 0 },
+};
+
+static const struct of_device_id cppi41_dma_ids[] = {
+	{ .compatible = "ti,am3359-cppi41", .data = &usb_infos},
+	{},
+};
+MODULE_DEVICE_TABLE(of, cppi41_dma_ids);
+
+static const struct cppi_glue_infos *get_glue_info(struct platform_device *pdev)
+{
+	const struct of_device_id *of_id;
+
+	of_id = of_match_node(cppi41_dma_ids, pdev->dev.of_node);
+	if (!of_id)
+		return NULL;
+	return of_id->data;
+}
+
+static int cppi41_dma_probe(struct platform_device *pdev)
+{
+	struct cppi41_dd *cdd;
+	const struct cppi_glue_infos *glue_info;
+	int irq;
+	int ret;
+
+	glue_info = get_glue_info(pdev);
+	if (!glue_info)
+		return -EINVAL;
+
+	cdd = kzalloc(sizeof(*cdd), GFP_KERNEL);
+	if (!cdd)
+		return -ENOMEM;
+
+	dma_cap_set(DMA_SLAVE, cdd->ddev.cap_mask);
+	cdd->ddev.device_alloc_chan_resources = cppi41_dma_alloc_chan_resources;
+	cdd->ddev.device_free_chan_resources = cppi41_dma_free_chan_resources;
+	cdd->ddev.device_tx_status = cppi41_dma_tx_status;
+	cdd->ddev.device_issue_pending = cppi41_dma_issue_pending;
+	cdd->ddev.device_prep_slave_sg = cppi41_dma_prep_slave_sg;
+	cdd->ddev.device_control = cppi41_dma_control;
+	cdd->ddev.dev = &pdev->dev;
+	INIT_LIST_HEAD(&cdd->ddev.channels);
+	cpp41_dma_info.dma_cap = cdd->ddev.cap_mask;
+
+	cdd->usbss_mem = of_iomap(pdev->dev.of_node, 0);
+	cdd->ctrl_mem = of_iomap(pdev->dev.of_node, 1);
+	cdd->sched_mem = of_iomap(pdev->dev.of_node, 2);
+	cdd->qmgr_mem = of_iomap(pdev->dev.of_node, 3);
+
+	if (!cdd->usbss_mem || !cdd->ctrl_mem || !cdd->sched_mem ||
+			!cdd->qmgr_mem) {
+		ret = -ENXIO;
+		goto err_remap;
+	}
+
+	pm_runtime_enable(&pdev->dev);
+	ret = pm_runtime_get_sync(&pdev->dev);
+	if (ret)
+		goto err_get_sync;
+
+	cdd->queues_rx = glue_info->queues_rx;
+	cdd->queues_tx = glue_info->queues_tx;
+	cdd->td_queue = glue_info->td_queue;
+
+	ret = init_cppi41(pdev, cdd);
+	if (ret)
+		goto err_init_cppi;
+
+	ret = cppi41_add_chans(pdev, cdd);
+	if (ret)
+		goto err_chans;
+
+	irq = irq_of_parse_and_map(pdev->dev.of_node, 0);
+	if (!irq)
+		goto err_irq;
+
+	cppi_writel(USBSS_IRQ_PD_COMP, cdd->usbss_mem + USBSS_IRQ_ENABLER);
+
+	ret = request_irq(irq, glue_info->isr, IRQF_SHARED,
+			dev_name(&pdev->dev), cdd);
+	if (ret)
+		goto err_irq;
+	cdd->irq = irq;
+
+	ret = dma_async_device_register(&cdd->ddev);
+	if (ret)
+		goto err_dma_reg;
+
+	ret = of_dma_controller_register(pdev->dev.of_node,
+			cppi41_dma_xlate, &cpp41_dma_info);
+	if (ret)
+		goto err_of;
+
+	platform_set_drvdata(pdev, cdd);
+	return 0;
+err_of:
+	dma_async_device_unregister(&cdd->ddev);
+err_dma_reg:
+	free_irq(irq, cdd);
+err_irq:
+	cppi_writel(0, cdd->usbss_mem + USBSS_IRQ_CLEARR);
+	cleanup_chans(cdd);
+err_chans:
+	deinit_cpii41(pdev, cdd);
+err_init_cppi:
+	pm_runtime_put(&pdev->dev);
+err_get_sync:
+	pm_runtime_disable(&pdev->dev);
+	iounmap(cdd->usbss_mem);
+	iounmap(cdd->ctrl_mem);
+	iounmap(cdd->sched_mem);
+	iounmap(cdd->qmgr_mem);
+err_remap:
+	kfree(cdd);
+	return ret;
+}
+
+static int cppi41_dma_remove(struct platform_device *pdev)
+{
+	struct cppi41_dd *cdd = platform_get_drvdata(pdev);
+
+	of_dma_controller_free(pdev->dev.of_node);
+	dma_async_device_unregister(&cdd->ddev);
+
+	cppi_writel(0, cdd->usbss_mem + USBSS_IRQ_CLEARR);
+	free_irq(cdd->irq, cdd);
+	cleanup_chans(cdd);
+	deinit_cpii41(pdev, cdd);
+	iounmap(cdd->usbss_mem);
+	iounmap(cdd->ctrl_mem);
+	iounmap(cdd->sched_mem);
+	iounmap(cdd->qmgr_mem);
+	pm_runtime_put(&pdev->dev);
+	pm_runtime_disable(&pdev->dev);
+	kfree(cdd);
+	return 0;
+}
+
+static struct platform_driver cpp41_dma_driver = {
+	.probe  = cppi41_dma_probe,
+	.remove = cppi41_dma_remove,
+	.driver = {
+		.name = "cppi41-dma-engine",
+		.owner = THIS_MODULE,
+		.of_match_table = of_match_ptr(cppi41_dma_ids),
+	},
+};
+
+module_platform_driver(cpp41_dma_driver);
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Sebastian Andrzej Siewior <bigeasy@linutronix.de>");
diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c
index 9e56745f87bf..9162ac80c18f 100644
--- a/drivers/dma/dmaengine.c
+++ b/drivers/dma/dmaengine.c
@@ -87,7 +87,8 @@ static struct dma_chan *dev_to_dma_chan(struct device *dev)
 	return chan_dev->chan;
 }
 
-static ssize_t show_memcpy_count(struct device *dev, struct device_attribute *attr, char *buf)
+static ssize_t memcpy_count_show(struct device *dev,
+				 struct device_attribute *attr, char *buf)
 {
 	struct dma_chan *chan;
 	unsigned long count = 0;
@@ -106,9 +107,10 @@ static ssize_t show_memcpy_count(struct device *dev, struct device_attribute *at
 
 	return err;
 }
+static DEVICE_ATTR_RO(memcpy_count);
 
-static ssize_t show_bytes_transferred(struct device *dev, struct device_attribute *attr,
-				      char *buf)
+static ssize_t bytes_transferred_show(struct device *dev,
+				      struct device_attribute *attr, char *buf)
 {
 	struct dma_chan *chan;
 	unsigned long count = 0;
@@ -127,8 +129,10 @@ static ssize_t show_bytes_transferred(struct device *dev, struct device_attribut
 
 	return err;
 }
+static DEVICE_ATTR_RO(bytes_transferred);
 
-static ssize_t show_in_use(struct device *dev, struct device_attribute *attr, char *buf)
+static ssize_t in_use_show(struct device *dev, struct device_attribute *attr,
+			   char *buf)
 {
 	struct dma_chan *chan;
 	int err;
@@ -143,13 +147,15 @@ static ssize_t show_in_use(struct device *dev, struct device_attribute *attr, ch
 
 	return err;
 }
+static DEVICE_ATTR_RO(in_use);
 
-static struct device_attribute dma_attrs[] = {
-	__ATTR(memcpy_count, S_IRUGO, show_memcpy_count, NULL),
-	__ATTR(bytes_transferred, S_IRUGO, show_bytes_transferred, NULL),
-	__ATTR(in_use, S_IRUGO, show_in_use, NULL),
-	__ATTR_NULL
+static struct attribute *dma_dev_attrs[] = {
+	&dev_attr_memcpy_count.attr,
+	&dev_attr_bytes_transferred.attr,
+	&dev_attr_in_use.attr,
+	NULL,
 };
+ATTRIBUTE_GROUPS(dma_dev);
 
 static void chan_dev_release(struct device *dev)
 {
@@ -167,7 +173,7 @@ static void chan_dev_release(struct device *dev)
 
 static struct class dma_devclass = {
 	.name		= "dma",
-	.dev_attrs	= dma_attrs,
+	.dev_groups	= dma_dev_groups,
 	.dev_release	= chan_dev_release,
 };
 
@@ -376,20 +382,30 @@ void dma_issue_pending_all(void)
 EXPORT_SYMBOL(dma_issue_pending_all);
 
 /**
- * nth_chan - returns the nth channel of the given capability
+ * dma_chan_is_local - returns true if the channel is in the same numa-node as the cpu
+ */
+static bool dma_chan_is_local(struct dma_chan *chan, int cpu)
+{
+	int node = dev_to_node(chan->device->dev);
+	return node == -1 || cpumask_test_cpu(cpu, cpumask_of_node(node));
+}
+
+/**
+ * min_chan - returns the channel with min count and in the same numa-node as the cpu
  * @cap: capability to match
- * @n: nth channel desired
+ * @cpu: cpu index which the channel should be close to
  *
- * Defaults to returning the channel with the desired capability and the
- * lowest reference count when 'n' cannot be satisfied.  Must be called
- * under dma_list_mutex.
+ * If some channels are close to the given cpu, the one with the lowest
+ * reference count is returned. Otherwise, cpu is ignored and only the
+ * reference count is taken into account.
+ * Must be called under dma_list_mutex.
  */
-static struct dma_chan *nth_chan(enum dma_transaction_type cap, int n)
+static struct dma_chan *min_chan(enum dma_transaction_type cap, int cpu)
 {
 	struct dma_device *device;
 	struct dma_chan *chan;
-	struct dma_chan *ret = NULL;
 	struct dma_chan *min = NULL;
+	struct dma_chan *localmin = NULL;
 
 	list_for_each_entry(device, &dma_device_list, global_node) {
 		if (!dma_has_cap(cap, device->cap_mask) ||
@@ -398,27 +414,22 @@ static struct dma_chan *nth_chan(enum dma_transaction_type cap, int n)
 		list_for_each_entry(chan, &device->channels, device_node) {
 			if (!chan->client_count)
 				continue;
-			if (!min)
-				min = chan;
-			else if (chan->table_count < min->table_count)
+			if (!min || chan->table_count < min->table_count)
 				min = chan;
 
-			if (n-- == 0) {
-				ret = chan;
-				break; /* done */
-			}
+			if (dma_chan_is_local(chan, cpu))
+				if (!localmin ||
+				    chan->table_count < localmin->table_count)
+					localmin = chan;
 		}
-		if (ret)
-			break; /* done */
 	}
 
-	if (!ret)
-		ret = min;
+	chan = localmin ? localmin : min;
 
-	if (ret)
-		ret->table_count++;
+	if (chan)
+		chan->table_count++;
 
-	return ret;
+	return chan;
 }
 
 /**
@@ -435,7 +446,6 @@ static void dma_channel_rebalance(void)
 	struct dma_device *device;
 	int cpu;
 	int cap;
-	int n;
 
 	/* undo the last distribution */
 	for_each_dma_cap_mask(cap, dma_cap_mask_all)
@@ -454,14 +464,9 @@ static void dma_channel_rebalance(void)
 		return;
 
 	/* redistribute available channels */
-	n = 0;
 	for_each_dma_cap_mask(cap, dma_cap_mask_all)
 		for_each_online_cpu(cpu) {
-			if (num_possible_cpus() > 1)
-				chan = nth_chan(cap, n++);
-			else
-				chan = nth_chan(cap, -1);
-
+			chan = min_chan(cap, cpu);
 			per_cpu_ptr(channel_table[cap], cpu)->chan = chan;
 		}
 }
@@ -504,7 +509,33 @@ static struct dma_chan *private_candidate(const dma_cap_mask_t *mask,
 }
 
 /**
- * dma_request_channel - try to allocate an exclusive channel
+ * dma_request_slave_channel - try to get specific channel exclusively
+ * @chan: target channel
+ */
+struct dma_chan *dma_get_slave_channel(struct dma_chan *chan)
+{
+	int err = -EBUSY;
+
+	/* lock against __dma_request_channel */
+	mutex_lock(&dma_list_mutex);
+
+	if (chan->client_count == 0) {
+		err = dma_chan_get(chan);
+		if (err)
+			pr_debug("%s: failed to get %s: (%d)\n",
+				__func__, dma_chan_name(chan), err);
+	} else
+		chan = NULL;
+
+	mutex_unlock(&dma_list_mutex);
+
+
+	return chan;
+}
+EXPORT_SYMBOL_GPL(dma_get_slave_channel);
+
+/**
+ * __dma_request_channel - try to allocate an exclusive channel
  * @mask: capabilities that the channel must satisfy
  * @fn: optional callback to disposition available channels
  * @fn_param: opaque parameter to pass to dma_filter_fn
diff --git a/drivers/dma/dmatest.c b/drivers/dma/dmatest.c
index e88ded2c8d2f..92f796cdc6ab 100644
--- a/drivers/dma/dmatest.c
+++ b/drivers/dma/dmatest.c
@@ -25,44 +25,46 @@
 #include <linux/seq_file.h>
 
 static unsigned int test_buf_size = 16384;
-module_param(test_buf_size, uint, S_IRUGO);
+module_param(test_buf_size, uint, S_IRUGO | S_IWUSR);
 MODULE_PARM_DESC(test_buf_size, "Size of the memcpy test buffer");
 
 static char test_channel[20];
-module_param_string(channel, test_channel, sizeof(test_channel), S_IRUGO);
+module_param_string(channel, test_channel, sizeof(test_channel),
+		S_IRUGO | S_IWUSR);
 MODULE_PARM_DESC(channel, "Bus ID of the channel to test (default: any)");
 
 static char test_device[20];
-module_param_string(device, test_device, sizeof(test_device), S_IRUGO);
+module_param_string(device, test_device, sizeof(test_device),
+		S_IRUGO | S_IWUSR);
 MODULE_PARM_DESC(device, "Bus ID of the DMA Engine to test (default: any)");
 
 static unsigned int threads_per_chan = 1;
-module_param(threads_per_chan, uint, S_IRUGO);
+module_param(threads_per_chan, uint, S_IRUGO | S_IWUSR);
 MODULE_PARM_DESC(threads_per_chan,
 		"Number of threads to start per channel (default: 1)");
 
 static unsigned int max_channels;
-module_param(max_channels, uint, S_IRUGO);
+module_param(max_channels, uint, S_IRUGO | S_IWUSR);
 MODULE_PARM_DESC(max_channels,
 		"Maximum number of channels to use (default: all)");
 
 static unsigned int iterations;
-module_param(iterations, uint, S_IRUGO);
+module_param(iterations, uint, S_IRUGO | S_IWUSR);
 MODULE_PARM_DESC(iterations,
 		"Iterations before stopping test (default: infinite)");
 
 static unsigned int xor_sources = 3;
-module_param(xor_sources, uint, S_IRUGO);
+module_param(xor_sources, uint, S_IRUGO | S_IWUSR);
 MODULE_PARM_DESC(xor_sources,
 		"Number of xor source buffers (default: 3)");
 
 static unsigned int pq_sources = 3;
-module_param(pq_sources, uint, S_IRUGO);
+module_param(pq_sources, uint, S_IRUGO | S_IWUSR);
 MODULE_PARM_DESC(pq_sources,
 		"Number of p+q source buffers (default: 3)");
 
 static int timeout = 3000;
-module_param(timeout, uint, S_IRUGO);
+module_param(timeout, uint, S_IRUGO | S_IWUSR);
 MODULE_PARM_DESC(timeout, "Transfer Timeout in msec (default: 3000), "
 		 "Pass -1 for infinite timeout");
 
@@ -193,7 +195,6 @@ struct dmatest_info {
 
 	/* debugfs related stuff */
 	struct dentry		*root;
-	struct dmatest_params	dbgfs_params;
 
 	/* Test results */
 	struct list_head	results;
@@ -406,7 +407,11 @@ static int thread_result_add(struct dmatest_info *info,
 	list_add_tail(&tr->node, &r->results);
 	mutex_unlock(&info->results_lock);
 
-	pr_warn("%s\n", thread_result_get(r->name, tr));
+	if (tr->type == DMATEST_ET_OK)
+		pr_debug("%s\n", thread_result_get(r->name, tr));
+	else
+		pr_warn("%s\n", thread_result_get(r->name, tr));
+
 	return 0;
 }
 
@@ -1007,7 +1012,15 @@ static int __restart_threaded_test(struct dmatest_info *info, bool run)
 	result_free(info, NULL);
 
 	/* Copy test parameters */
-	memcpy(params, &info->dbgfs_params, sizeof(*params));
+	params->buf_size = test_buf_size;
+	strlcpy(params->channel, strim(test_channel), sizeof(params->channel));
+	strlcpy(params->device, strim(test_device), sizeof(params->device));
+	params->threads_per_chan = threads_per_chan;
+	params->max_channels = max_channels;
+	params->iterations = iterations;
+	params->xor_sources = xor_sources;
+	params->pq_sources = pq_sources;
+	params->timeout = timeout;
 
 	/* Run test with new parameters */
 	return __run_threaded_test(info);
@@ -1029,71 +1042,6 @@ static bool __is_threaded_test_run(struct dmatest_info *info)
 	return false;
 }
 
-static ssize_t dtf_write_string(void *to, size_t available, loff_t *ppos,
-		const void __user *from, size_t count)
-{
-	char tmp[20];
-	ssize_t len;
-
-	len = simple_write_to_buffer(tmp, sizeof(tmp) - 1, ppos, from, count);
-	if (len >= 0) {
-		tmp[len] = '\0';
-		strlcpy(to, strim(tmp), available);
-	}
-
-	return len;
-}
-
-static ssize_t dtf_read_channel(struct file *file, char __user *buf,
-		size_t count, loff_t *ppos)
-{
-	struct dmatest_info *info = file->private_data;
-	return simple_read_from_buffer(buf, count, ppos,
-			info->dbgfs_params.channel,
-			strlen(info->dbgfs_params.channel));
-}
-
-static ssize_t dtf_write_channel(struct file *file, const char __user *buf,
-		size_t size, loff_t *ppos)
-{
-	struct dmatest_info *info = file->private_data;
-	return dtf_write_string(info->dbgfs_params.channel,
-				sizeof(info->dbgfs_params.channel),
-				ppos, buf, size);
-}
-
-static const struct file_operations dtf_channel_fops = {
-	.read	= dtf_read_channel,
-	.write	= dtf_write_channel,
-	.open	= simple_open,
-	.llseek	= default_llseek,
-};
-
-static ssize_t dtf_read_device(struct file *file, char __user *buf,
-		size_t count, loff_t *ppos)
-{
-	struct dmatest_info *info = file->private_data;
-	return simple_read_from_buffer(buf, count, ppos,
-			info->dbgfs_params.device,
-			strlen(info->dbgfs_params.device));
-}
-
-static ssize_t dtf_write_device(struct file *file, const char __user *buf,
-		size_t size, loff_t *ppos)
-{
-	struct dmatest_info *info = file->private_data;
-	return dtf_write_string(info->dbgfs_params.device,
-				sizeof(info->dbgfs_params.device),
-				ppos, buf, size);
-}
-
-static const struct file_operations dtf_device_fops = {
-	.read	= dtf_read_device,
-	.write	= dtf_write_device,
-	.open	= simple_open,
-	.llseek	= default_llseek,
-};
-
 static ssize_t dtf_read_run(struct file *file, char __user *user_buf,
 		size_t count, loff_t *ppos)
 {
@@ -1187,8 +1135,6 @@ static const struct file_operations dtf_results_fops = {
 static int dmatest_register_dbgfs(struct dmatest_info *info)
 {
 	struct dentry *d;
-	struct dmatest_params *params = &info->dbgfs_params;
-	int ret = -ENOMEM;
 
 	d = debugfs_create_dir("dmatest", NULL);
 	if (IS_ERR(d))
@@ -1198,81 +1144,24 @@ static int dmatest_register_dbgfs(struct dmatest_info *info)
 
 	info->root = d;
 
-	/* Copy initial values */
-	memcpy(params, &info->params, sizeof(*params));
-
-	/* Test parameters */
-
-	d = debugfs_create_u32("test_buf_size", S_IWUSR | S_IRUGO, info->root,
-			       (u32 *)&params->buf_size);
-	if (IS_ERR_OR_NULL(d))
-		goto err_node;
-
-	d = debugfs_create_file("channel", S_IRUGO | S_IWUSR, info->root,
-				info, &dtf_channel_fops);
-	if (IS_ERR_OR_NULL(d))
-		goto err_node;
-
-	d = debugfs_create_file("device", S_IRUGO | S_IWUSR, info->root,
-				info, &dtf_device_fops);
-	if (IS_ERR_OR_NULL(d))
-		goto err_node;
-
-	d = debugfs_create_u32("threads_per_chan", S_IWUSR | S_IRUGO, info->root,
-			       (u32 *)&params->threads_per_chan);
-	if (IS_ERR_OR_NULL(d))
-		goto err_node;
-
-	d = debugfs_create_u32("max_channels", S_IWUSR | S_IRUGO, info->root,
-			       (u32 *)&params->max_channels);
-	if (IS_ERR_OR_NULL(d))
-		goto err_node;
-
-	d = debugfs_create_u32("iterations", S_IWUSR | S_IRUGO, info->root,
-			       (u32 *)&params->iterations);
-	if (IS_ERR_OR_NULL(d))
-		goto err_node;
-
-	d = debugfs_create_u32("xor_sources", S_IWUSR | S_IRUGO, info->root,
-			       (u32 *)&params->xor_sources);
-	if (IS_ERR_OR_NULL(d))
-		goto err_node;
-
-	d = debugfs_create_u32("pq_sources", S_IWUSR | S_IRUGO, info->root,
-			       (u32 *)&params->pq_sources);
-	if (IS_ERR_OR_NULL(d))
-		goto err_node;
-
-	d = debugfs_create_u32("timeout", S_IWUSR | S_IRUGO, info->root,
-			       (u32 *)&params->timeout);
-	if (IS_ERR_OR_NULL(d))
-		goto err_node;
-
 	/* Run or stop threaded test */
-	d = debugfs_create_file("run", S_IWUSR | S_IRUGO, info->root,
-				info, &dtf_run_fops);
-	if (IS_ERR_OR_NULL(d))
-		goto err_node;
+	debugfs_create_file("run", S_IWUSR | S_IRUGO, info->root, info,
+			    &dtf_run_fops);
 
 	/* Results of test in progress */
-	d = debugfs_create_file("results", S_IRUGO, info->root, info,
-				&dtf_results_fops);
-	if (IS_ERR_OR_NULL(d))
-		goto err_node;
+	debugfs_create_file("results", S_IRUGO, info->root, info,
+			    &dtf_results_fops);
 
 	return 0;
 
-err_node:
-	debugfs_remove_recursive(info->root);
 err_root:
 	pr_err("dmatest: Failed to initialize debugfs\n");
-	return ret;
+	return -ENOMEM;
 }
 
 static int __init dmatest_init(void)
 {
 	struct dmatest_info *info = &test_info;
-	struct dmatest_params *params = &info->params;
 	int ret;
 
 	memset(info, 0, sizeof(*info));
@@ -1283,17 +1172,6 @@ static int __init dmatest_init(void)
 	mutex_init(&info->results_lock);
 	INIT_LIST_HEAD(&info->results);
 
-	/* Set default parameters */
-	params->buf_size = test_buf_size;
-	strlcpy(params->channel, test_channel, sizeof(params->channel));
-	strlcpy(params->device, test_device, sizeof(params->device));
-	params->threads_per_chan = threads_per_chan;
-	params->max_channels = max_channels;
-	params->iterations = iterations;
-	params->xor_sources = xor_sources;
-	params->pq_sources = pq_sources;
-	params->timeout = timeout;
-
 	ret = dmatest_register_dbgfs(info);
 	if (ret)
 		return ret;
diff --git a/drivers/dma/dw/Kconfig b/drivers/dma/dw/Kconfig
index dde13248b681..dcfe964cc8dc 100644
--- a/drivers/dma/dw/Kconfig
+++ b/drivers/dma/dw/Kconfig
@@ -4,7 +4,6 @@
 
 config DW_DMAC_CORE
 	tristate "Synopsys DesignWare AHB DMA support"
-	depends on GENERIC_HARDIRQS
 	select DMA_ENGINE
 
 config DW_DMAC
diff --git a/drivers/dma/dw/core.c b/drivers/dma/dw/core.c
index eea479c12173..89eb89f22284 100644
--- a/drivers/dma/dw/core.c
+++ b/drivers/dma/dw/core.c
@@ -37,16 +37,22 @@
  * which does not support descriptor writeback.
  */
 
+static inline bool is_request_line_unset(struct dw_dma_chan *dwc)
+{
+	return dwc->request_line == (typeof(dwc->request_line))~0;
+}
+
 static inline void dwc_set_masters(struct dw_dma_chan *dwc)
 {
 	struct dw_dma *dw = to_dw_dma(dwc->chan.device);
 	struct dw_dma_slave *dws = dwc->chan.private;
 	unsigned char mmax = dw->nr_masters - 1;
 
-	if (dwc->request_line == ~0) {
-		dwc->src_master = min_t(unsigned char, mmax, dwc_get_sms(dws));
-		dwc->dst_master = min_t(unsigned char, mmax, dwc_get_dms(dws));
-	}
+	if (!is_request_line_unset(dwc))
+		return;
+
+	dwc->src_master = min_t(unsigned char, mmax, dwc_get_sms(dws));
+	dwc->dst_master = min_t(unsigned char, mmax, dwc_get_dms(dws));
 }
 
 #define DWC_DEFAULT_CTLLO(_chan) ({				\
@@ -644,10 +650,13 @@ static void dw_dma_tasklet(unsigned long data)
 static irqreturn_t dw_dma_interrupt(int irq, void *dev_id)
 {
 	struct dw_dma *dw = dev_id;
-	u32 status;
+	u32 status = dma_readl(dw, STATUS_INT);
+
+	dev_vdbg(dw->dma.dev, "%s: status=0x%x\n", __func__, status);
 
-	dev_vdbg(dw->dma.dev, "%s: status=0x%x\n", __func__,
-			dma_readl(dw, STATUS_INT));
+	/* Check if we have any interrupt from the DMAC */
+	if (!status)
+		return IRQ_NONE;
 
 	/*
 	 * Just disable the interrupts. We'll turn them back on in the
@@ -984,7 +993,7 @@ set_runtime_config(struct dma_chan *chan, struct dma_slave_config *sconfig)
 	dwc->direction = sconfig->direction;
 
 	/* Take the request line from slave_id member */
-	if (dwc->request_line == ~0)
+	if (is_request_line_unset(dwc))
 		dwc->request_line = sconfig->slave_id;
 
 	convert_burst(&dwc->dma_sconfig.src_maxburst);
@@ -1089,16 +1098,16 @@ dwc_tx_status(struct dma_chan *chan,
 	enum dma_status		ret;
 
 	ret = dma_cookie_status(chan, cookie, txstate);
-	if (ret != DMA_SUCCESS) {
-		dwc_scan_descriptors(to_dw_dma(chan->device), dwc);
+	if (ret == DMA_SUCCESS)
+		return ret;
 
-		ret = dma_cookie_status(chan, cookie, txstate);
-	}
+	dwc_scan_descriptors(to_dw_dma(chan->device), dwc);
 
+	ret = dma_cookie_status(chan, cookie, txstate);
 	if (ret != DMA_SUCCESS)
 		dma_set_residue(txstate, dwc_get_residue(dwc));
 
-	if (dwc->paused)
+	if (dwc->paused && ret == DMA_IN_PROGRESS)
 		return DMA_PAUSED;
 
 	return ret;
@@ -1560,8 +1569,8 @@ int dw_dma_probe(struct dw_dma_chip *chip, struct dw_dma_platform_data *pdata)
 	/* Disable BLOCK interrupts as well */
 	channel_clear_bit(dw, MASK.BLOCK, dw->all_chan_mask);
 
-	err = devm_request_irq(chip->dev, chip->irq, dw_dma_interrupt, 0,
-			       "dw_dmac", dw);
+	err = devm_request_irq(chip->dev, chip->irq, dw_dma_interrupt,
+			       IRQF_SHARED, "dw_dmac", dw);
 	if (err)
 		return err;
 
diff --git a/drivers/dma/dw/platform.c b/drivers/dma/dw/platform.c
index 6c9449cffae8..e35d97590311 100644
--- a/drivers/dma/dw/platform.c
+++ b/drivers/dma/dw/platform.c
@@ -253,6 +253,7 @@ static const struct acpi_device_id dw_dma_acpi_id_table[] = {
 	{ "INTL9C60", 0 },
 	{ }
 };
+MODULE_DEVICE_TABLE(acpi, dw_dma_acpi_id_table);
 #endif
 
 #ifdef CONFIG_PM_SLEEP
diff --git a/drivers/dma/edma.c b/drivers/dma/edma.c
index 5f3e532436ee..3519111c566b 100644
--- a/drivers/dma/edma.c
+++ b/drivers/dma/edma.c
@@ -56,6 +56,7 @@ struct edma_desc {
 	struct list_head		node;
 	int				absync;
 	int				pset_nr;
+	int				processed;
 	struct edmacc_param		pset[0];
 };
 
@@ -69,6 +70,7 @@ struct edma_chan {
 	int				ch_num;
 	bool				alloced;
 	int				slot[EDMA_MAX_SLOTS];
+	int				missed;
 	struct dma_slave_config		cfg;
 };
 
@@ -104,22 +106,34 @@ static void edma_desc_free(struct virt_dma_desc *vdesc)
 /* Dispatch a queued descriptor to the controller (caller holds lock) */
 static void edma_execute(struct edma_chan *echan)
 {
-	struct virt_dma_desc *vdesc = vchan_next_desc(&echan->vchan);
+	struct virt_dma_desc *vdesc;
 	struct edma_desc *edesc;
-	int i;
-
-	if (!vdesc) {
-		echan->edesc = NULL;
-		return;
+	struct device *dev = echan->vchan.chan.device->dev;
+	int i, j, left, nslots;
+
+	/* If either we processed all psets or we're still not started */
+	if (!echan->edesc ||
+	    echan->edesc->pset_nr == echan->edesc->processed) {
+		/* Get next vdesc */
+		vdesc = vchan_next_desc(&echan->vchan);
+		if (!vdesc) {
+			echan->edesc = NULL;
+			return;
+		}
+		list_del(&vdesc->node);
+		echan->edesc = to_edma_desc(&vdesc->tx);
 	}
 
-	list_del(&vdesc->node);
+	edesc = echan->edesc;
 
-	echan->edesc = edesc = to_edma_desc(&vdesc->tx);
+	/* Find out how many left */
+	left = edesc->pset_nr - edesc->processed;
+	nslots = min(MAX_NR_SG, left);
 
 	/* Write descriptor PaRAM set(s) */
-	for (i = 0; i < edesc->pset_nr; i++) {
-		edma_write_slot(echan->slot[i], &edesc->pset[i]);
+	for (i = 0; i < nslots; i++) {
+		j = i + edesc->processed;
+		edma_write_slot(echan->slot[i], &edesc->pset[j]);
 		dev_dbg(echan->vchan.chan.device->dev,
 			"\n pset[%d]:\n"
 			"  chnum\t%d\n"
@@ -132,24 +146,50 @@ static void edma_execute(struct edma_chan *echan)
 			"  bidx\t%08x\n"
 			"  cidx\t%08x\n"
 			"  lkrld\t%08x\n",
-			i, echan->ch_num, echan->slot[i],
-			edesc->pset[i].opt,
-			edesc->pset[i].src,
-			edesc->pset[i].dst,
-			edesc->pset[i].a_b_cnt,
-			edesc->pset[i].ccnt,
-			edesc->pset[i].src_dst_bidx,
-			edesc->pset[i].src_dst_cidx,
-			edesc->pset[i].link_bcntrld);
+			j, echan->ch_num, echan->slot[i],
+			edesc->pset[j].opt,
+			edesc->pset[j].src,
+			edesc->pset[j].dst,
+			edesc->pset[j].a_b_cnt,
+			edesc->pset[j].ccnt,
+			edesc->pset[j].src_dst_bidx,
+			edesc->pset[j].src_dst_cidx,
+			edesc->pset[j].link_bcntrld);
 		/* Link to the previous slot if not the last set */
-		if (i != (edesc->pset_nr - 1))
+		if (i != (nslots - 1))
 			edma_link(echan->slot[i], echan->slot[i+1]);
-		/* Final pset links to the dummy pset */
-		else
-			edma_link(echan->slot[i], echan->ecc->dummy_slot);
 	}
 
-	edma_start(echan->ch_num);
+	edesc->processed += nslots;
+
+	/*
+	 * If this is either the last set in a set of SG-list transactions
+	 * then setup a link to the dummy slot, this results in all future
+	 * events being absorbed and that's OK because we're done
+	 */
+	if (edesc->processed == edesc->pset_nr)
+		edma_link(echan->slot[nslots-1], echan->ecc->dummy_slot);
+
+	edma_resume(echan->ch_num);
+
+	if (edesc->processed <= MAX_NR_SG) {
+		dev_dbg(dev, "first transfer starting %d\n", echan->ch_num);
+		edma_start(echan->ch_num);
+	}
+
+	/*
+	 * This happens due to setup times between intermediate transfers
+	 * in long SG lists which have to be broken up into transfers of
+	 * MAX_NR_SG
+	 */
+	if (echan->missed) {
+		dev_dbg(dev, "missed event in execute detected\n");
+		edma_clean_channel(echan->ch_num);
+		edma_stop(echan->ch_num);
+		edma_start(echan->ch_num);
+		edma_trigger_channel(echan->ch_num);
+		echan->missed = 0;
+	}
 }
 
 static int edma_terminate_all(struct edma_chan *echan)
@@ -222,9 +262,9 @@ static struct dma_async_tx_descriptor *edma_prep_slave_sg(
 	enum dma_slave_buswidth dev_width;
 	u32 burst;
 	struct scatterlist *sg;
-	int i;
 	int acnt, bcnt, ccnt, src, dst, cidx;
 	int src_bidx, dst_bidx, src_cidx, dst_cidx;
+	int i, nslots;
 
 	if (unlikely(!echan || !sgl || !sg_len))
 		return NULL;
@@ -247,12 +287,6 @@ static struct dma_async_tx_descriptor *edma_prep_slave_sg(
 		return NULL;
 	}
 
-	if (sg_len > MAX_NR_SG) {
-		dev_err(dev, "Exceeded max SG segments %d > %d\n",
-			sg_len, MAX_NR_SG);
-		return NULL;
-	}
-
 	edesc = kzalloc(sizeof(*edesc) + sg_len *
 		sizeof(edesc->pset[0]), GFP_ATOMIC);
 	if (!edesc) {
@@ -262,17 +296,24 @@ static struct dma_async_tx_descriptor *edma_prep_slave_sg(
 
 	edesc->pset_nr = sg_len;
 
-	for_each_sg(sgl, sg, sg_len, i) {
-		/* Allocate a PaRAM slot, if needed */
+	/* Allocate a PaRAM slot, if needed */
+	nslots = min_t(unsigned, MAX_NR_SG, sg_len);
+
+	for (i = 0; i < nslots; i++) {
 		if (echan->slot[i] < 0) {
 			echan->slot[i] =
 				edma_alloc_slot(EDMA_CTLR(echan->ch_num),
 						EDMA_SLOT_ANY);
 			if (echan->slot[i] < 0) {
 				dev_err(dev, "Failed to allocate slot\n");
+				kfree(edesc);
 				return NULL;
 			}
 		}
+	}
+
+	/* Configure PaRAM sets for each SG */
+	for_each_sg(sgl, sg, sg_len, i) {
 
 		acnt = dev_width;
 
@@ -330,6 +371,12 @@ static struct dma_async_tx_descriptor *edma_prep_slave_sg(
 		/* Configure A or AB synchronized transfers */
 		if (edesc->absync)
 			edesc->pset[i].opt |= SYNCDIM;
+
+		/* If this is the last in a current SG set of transactions,
+		   enable interrupts so that next set is processed */
+		if (!((i+1) % MAX_NR_SG))
+			edesc->pset[i].opt |= TCINTEN;
+
 		/* If this is the last set, enable completion interrupt flag */
 		if (i == sg_len - 1)
 			edesc->pset[i].opt |= TCINTEN;
@@ -355,27 +402,65 @@ static void edma_callback(unsigned ch_num, u16 ch_status, void *data)
 	struct device *dev = echan->vchan.chan.device->dev;
 	struct edma_desc *edesc;
 	unsigned long flags;
+	struct edmacc_param p;
 
-	/* Stop the channel */
-	edma_stop(echan->ch_num);
+	/* Pause the channel */
+	edma_pause(echan->ch_num);
 
 	switch (ch_status) {
 	case DMA_COMPLETE:
-		dev_dbg(dev, "transfer complete on channel %d\n", ch_num);
-
 		spin_lock_irqsave(&echan->vchan.lock, flags);
 
 		edesc = echan->edesc;
 		if (edesc) {
+			if (edesc->processed == edesc->pset_nr) {
+				dev_dbg(dev, "Transfer complete, stopping channel %d\n", ch_num);
+				edma_stop(echan->ch_num);
+				vchan_cookie_complete(&edesc->vdesc);
+			} else {
+				dev_dbg(dev, "Intermediate transfer complete on channel %d\n", ch_num);
+			}
+
 			edma_execute(echan);
-			vchan_cookie_complete(&edesc->vdesc);
 		}
 
 		spin_unlock_irqrestore(&echan->vchan.lock, flags);
 
 		break;
 	case DMA_CC_ERROR:
-		dev_dbg(dev, "transfer error on channel %d\n", ch_num);
+		spin_lock_irqsave(&echan->vchan.lock, flags);
+
+		edma_read_slot(EDMA_CHAN_SLOT(echan->slot[0]), &p);
+
+		/*
+		 * Issue later based on missed flag which will be sure
+		 * to happen as:
+		 * (1) we finished transmitting an intermediate slot and
+		 *     edma_execute is coming up.
+		 * (2) or we finished current transfer and issue will
+		 *     call edma_execute.
+		 *
+		 * Important note: issuing can be dangerous here and
+		 * lead to some nasty recursion when we are in a NULL
+		 * slot. So we avoid doing so and set the missed flag.
+		 */
+		if (p.a_b_cnt == 0 && p.ccnt == 0) {
+			dev_dbg(dev, "Error occurred, looks like slot is null, just setting miss\n");
+			echan->missed = 1;
+		} else {
+			/*
+			 * The slot is already programmed but the event got
+			 * missed, so its safe to issue it here.
+			 */
+			dev_dbg(dev, "Error occurred but slot is non-null, TRIGGERING\n");
+			edma_clean_channel(echan->ch_num);
+			edma_stop(echan->ch_num);
+			edma_start(echan->ch_num);
+			edma_trigger_channel(echan->ch_num);
+		}
+
+		spin_unlock_irqrestore(&echan->vchan.lock, flags);
+
 		break;
 	default:
 		break;
@@ -502,8 +587,6 @@ static enum dma_status edma_tx_status(struct dma_chan *chan,
 	} else if (echan->edesc && echan->edesc->vdesc.tx.cookie == cookie) {
 		struct edma_desc *edesc = echan->edesc;
 		txstate->residue = edma_desc_size(edesc);
-	} else {
-		txstate->residue = 0;
 	}
 	spin_unlock_irqrestore(&echan->vchan.lock, flags);
 
@@ -667,6 +750,6 @@ static void __exit edma_exit(void)
 }
 module_exit(edma_exit);
 
-MODULE_AUTHOR("Matt Porter <mporter@ti.com>");
+MODULE_AUTHOR("Matt Porter <matt.porter@linaro.org>");
 MODULE_DESCRIPTION("TI EDMA DMA engine driver");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/dma/ep93xx_dma.c b/drivers/dma/ep93xx_dma.c
index f2bf8c0c4675..591cd8c63abb 100644
--- a/drivers/dma/ep93xx_dma.c
+++ b/drivers/dma/ep93xx_dma.c
@@ -1313,15 +1313,7 @@ static enum dma_status ep93xx_dma_tx_status(struct dma_chan *chan,
 					    dma_cookie_t cookie,
 					    struct dma_tx_state *state)
 {
-	struct ep93xx_dma_chan *edmac = to_ep93xx_dma_chan(chan);
-	enum dma_status ret;
-	unsigned long flags;
-
-	spin_lock_irqsave(&edmac->lock, flags);
-	ret = dma_cookie_status(chan, cookie, state);
-	spin_unlock_irqrestore(&edmac->lock, flags);
-
-	return ret;
+	return dma_cookie_status(chan, cookie, state);
 }
 
 /**
diff --git a/drivers/dma/fsldma.c b/drivers/dma/fsldma.c
index 49e8fbdb8983..b3f3e90054f2 100644
--- a/drivers/dma/fsldma.c
+++ b/drivers/dma/fsldma.c
@@ -979,15 +979,7 @@ static enum dma_status fsl_tx_status(struct dma_chan *dchan,
 					dma_cookie_t cookie,
 					struct dma_tx_state *txstate)
 {
-	struct fsldma_chan *chan = to_fsl_chan(dchan);
-	enum dma_status ret;
-	unsigned long flags;
-
-	spin_lock_irqsave(&chan->desc_lock, flags);
-	ret = dma_cookie_status(dchan, cookie, txstate);
-	spin_unlock_irqrestore(&chan->desc_lock, flags);
-
-	return ret;
+	return dma_cookie_status(dchan, cookie, txstate);
 }
 
 /*----------------------------------------------------------------------------*/
diff --git a/drivers/dma/imx-dma.c b/drivers/dma/imx-dma.c
index ff2aab973b45..55852c026791 100644
--- a/drivers/dma/imx-dma.c
+++ b/drivers/dma/imx-dma.c
@@ -437,17 +437,18 @@ static void dma_irq_handle_channel(struct imxdma_channel *imxdmac)
 	struct imxdma_engine *imxdma = imxdmac->imxdma;
 	int chno = imxdmac->channel;
 	struct imxdma_desc *desc;
+	unsigned long flags;
 
-	spin_lock(&imxdma->lock);
+	spin_lock_irqsave(&imxdma->lock, flags);
 	if (list_empty(&imxdmac->ld_active)) {
-		spin_unlock(&imxdma->lock);
+		spin_unlock_irqrestore(&imxdma->lock, flags);
 		goto out;
 	}
 
 	desc = list_first_entry(&imxdmac->ld_active,
 				struct imxdma_desc,
 				node);
-	spin_unlock(&imxdma->lock);
+	spin_unlock_irqrestore(&imxdma->lock, flags);
 
 	if (desc->sg) {
 		u32 tmp;
@@ -519,7 +520,6 @@ static int imxdma_xfer_desc(struct imxdma_desc *d)
 {
 	struct imxdma_channel *imxdmac = to_imxdma_chan(d->desc.chan);
 	struct imxdma_engine *imxdma = imxdmac->imxdma;
-	unsigned long flags;
 	int slot = -1;
 	int i;
 
@@ -527,7 +527,6 @@ static int imxdma_xfer_desc(struct imxdma_desc *d)
 	switch (d->type) {
 	case IMXDMA_DESC_INTERLEAVED:
 		/* Try to get a free 2D slot */
-		spin_lock_irqsave(&imxdma->lock, flags);
 		for (i = 0; i < IMX_DMA_2D_SLOTS; i++) {
 			if ((imxdma->slots_2d[i].count > 0) &&
 			((imxdma->slots_2d[i].xsr != d->x) ||
@@ -537,10 +536,8 @@ static int imxdma_xfer_desc(struct imxdma_desc *d)
 			slot = i;
 			break;
 		}
-		if (slot < 0) {
-			spin_unlock_irqrestore(&imxdma->lock, flags);
+		if (slot < 0)
 			return -EBUSY;
-		}
 
 		imxdma->slots_2d[slot].xsr = d->x;
 		imxdma->slots_2d[slot].ysr = d->y;
@@ -549,7 +546,6 @@ static int imxdma_xfer_desc(struct imxdma_desc *d)
 
 		imxdmac->slot_2d = slot;
 		imxdmac->enabled_2d = true;
-		spin_unlock_irqrestore(&imxdma->lock, flags);
 
 		if (slot == IMX_DMA_2D_SLOT_A) {
 			d->config_mem &= ~CCR_MSEL_B;
@@ -625,18 +621,17 @@ static void imxdma_tasklet(unsigned long data)
 	struct imxdma_channel *imxdmac = (void *)data;
 	struct imxdma_engine *imxdma = imxdmac->imxdma;
 	struct imxdma_desc *desc;
+	unsigned long flags;
 
-	spin_lock(&imxdma->lock);
+	spin_lock_irqsave(&imxdma->lock, flags);
 
 	if (list_empty(&imxdmac->ld_active)) {
 		/* Someone might have called terminate all */
-		goto out;
+		spin_unlock_irqrestore(&imxdma->lock, flags);
+		return;
 	}
 	desc = list_first_entry(&imxdmac->ld_active, struct imxdma_desc, node);
 
-	if (desc->desc.callback)
-		desc->desc.callback(desc->desc.callback_param);
-
 	/* If we are dealing with a cyclic descriptor, keep it on ld_active
 	 * and dont mark the descriptor as complete.
 	 * Only in non-cyclic cases it would be marked as complete
@@ -663,7 +658,11 @@ static void imxdma_tasklet(unsigned long data)
 				 __func__, imxdmac->channel);
 	}
 out:
-	spin_unlock(&imxdma->lock);
+	spin_unlock_irqrestore(&imxdma->lock, flags);
+
+	if (desc->desc.callback)
+		desc->desc.callback(desc->desc.callback_param);
+
 }
 
 static int imxdma_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd,
@@ -805,10 +804,8 @@ static void imxdma_free_chan_resources(struct dma_chan *chan)
 	}
 	INIT_LIST_HEAD(&imxdmac->ld_free);
 
-	if (imxdmac->sg_list) {
-		kfree(imxdmac->sg_list);
-		imxdmac->sg_list = NULL;
-	}
+	kfree(imxdmac->sg_list);
+	imxdmac->sg_list = NULL;
 }
 
 static struct dma_async_tx_descriptor *imxdma_prep_slave_sg(
@@ -885,7 +882,7 @@ static struct dma_async_tx_descriptor *imxdma_prep_dma_cyclic(
 	kfree(imxdmac->sg_list);
 
 	imxdmac->sg_list = kcalloc(periods + 1,
-			sizeof(struct scatterlist), GFP_KERNEL);
+			sizeof(struct scatterlist), GFP_ATOMIC);
 	if (!imxdmac->sg_list)
 		return NULL;
 
diff --git a/drivers/dma/imx-sdma.c b/drivers/dma/imx-sdma.c
index 1e44b8cf95da..fc43603cf0bb 100644
--- a/drivers/dma/imx-sdma.c
+++ b/drivers/dma/imx-sdma.c
@@ -243,7 +243,6 @@ struct sdma_engine;
  * @event_id1		for channels that use 2 events
  * @word_size		peripheral access size
  * @buf_tail		ID of the buffer that was processed
- * @done		channel completion
  * @num_bd		max NUM_BD. number of descriptors currently handling
  */
 struct sdma_channel {
@@ -255,7 +254,6 @@ struct sdma_channel {
 	unsigned int			event_id1;
 	enum dma_slave_buswidth		word_size;
 	unsigned int			buf_tail;
-	struct completion		done;
 	unsigned int			num_bd;
 	struct sdma_buffer_descriptor	*bd;
 	dma_addr_t			bd_phys;
@@ -307,9 +305,10 @@ struct sdma_firmware_header {
 	u32	ram_code_size;
 };
 
-enum sdma_devtype {
-	IMX31_SDMA,	/* runs on i.mx31 */
-	IMX35_SDMA,	/* runs on i.mx35 and later */
+struct sdma_driver_data {
+	int chnenbl0;
+	int num_events;
+	struct sdma_script_start_addrs	*script_addrs;
 };
 
 struct sdma_engine {
@@ -318,8 +317,6 @@ struct sdma_engine {
 	struct sdma_channel		channel[MAX_DMA_CHANNELS];
 	struct sdma_channel_control	*channel_control;
 	void __iomem			*regs;
-	enum sdma_devtype		devtype;
-	unsigned int			num_events;
 	struct sdma_context_data	*context;
 	dma_addr_t			context_phys;
 	struct dma_device		dma_device;
@@ -327,15 +324,118 @@ struct sdma_engine {
 	struct clk			*clk_ahb;
 	spinlock_t			channel_0_lock;
 	struct sdma_script_start_addrs	*script_addrs;
+	const struct sdma_driver_data	*drvdata;
+};
+
+static struct sdma_driver_data sdma_imx31 = {
+	.chnenbl0 = SDMA_CHNENBL0_IMX31,
+	.num_events = 32,
+};
+
+static struct sdma_script_start_addrs sdma_script_imx25 = {
+	.ap_2_ap_addr = 729,
+	.uart_2_mcu_addr = 904,
+	.per_2_app_addr = 1255,
+	.mcu_2_app_addr = 834,
+	.uartsh_2_mcu_addr = 1120,
+	.per_2_shp_addr = 1329,
+	.mcu_2_shp_addr = 1048,
+	.ata_2_mcu_addr = 1560,
+	.mcu_2_ata_addr = 1479,
+	.app_2_per_addr = 1189,
+	.app_2_mcu_addr = 770,
+	.shp_2_per_addr = 1407,
+	.shp_2_mcu_addr = 979,
+};
+
+static struct sdma_driver_data sdma_imx25 = {
+	.chnenbl0 = SDMA_CHNENBL0_IMX35,
+	.num_events = 48,
+	.script_addrs = &sdma_script_imx25,
+};
+
+static struct sdma_driver_data sdma_imx35 = {
+	.chnenbl0 = SDMA_CHNENBL0_IMX35,
+	.num_events = 48,
+};
+
+static struct sdma_script_start_addrs sdma_script_imx51 = {
+	.ap_2_ap_addr = 642,
+	.uart_2_mcu_addr = 817,
+	.mcu_2_app_addr = 747,
+	.mcu_2_shp_addr = 961,
+	.ata_2_mcu_addr = 1473,
+	.mcu_2_ata_addr = 1392,
+	.app_2_per_addr = 1033,
+	.app_2_mcu_addr = 683,
+	.shp_2_per_addr = 1251,
+	.shp_2_mcu_addr = 892,
+};
+
+static struct sdma_driver_data sdma_imx51 = {
+	.chnenbl0 = SDMA_CHNENBL0_IMX35,
+	.num_events = 48,
+	.script_addrs = &sdma_script_imx51,
+};
+
+static struct sdma_script_start_addrs sdma_script_imx53 = {
+	.ap_2_ap_addr = 642,
+	.app_2_mcu_addr = 683,
+	.mcu_2_app_addr = 747,
+	.uart_2_mcu_addr = 817,
+	.shp_2_mcu_addr = 891,
+	.mcu_2_shp_addr = 960,
+	.uartsh_2_mcu_addr = 1032,
+	.spdif_2_mcu_addr = 1100,
+	.mcu_2_spdif_addr = 1134,
+	.firi_2_mcu_addr = 1193,
+	.mcu_2_firi_addr = 1290,
+};
+
+static struct sdma_driver_data sdma_imx53 = {
+	.chnenbl0 = SDMA_CHNENBL0_IMX35,
+	.num_events = 48,
+	.script_addrs = &sdma_script_imx53,
+};
+
+static struct sdma_script_start_addrs sdma_script_imx6q = {
+	.ap_2_ap_addr = 642,
+	.uart_2_mcu_addr = 817,
+	.mcu_2_app_addr = 747,
+	.per_2_per_addr = 6331,
+	.uartsh_2_mcu_addr = 1032,
+	.mcu_2_shp_addr = 960,
+	.app_2_mcu_addr = 683,
+	.shp_2_mcu_addr = 891,
+	.spdif_2_mcu_addr = 1100,
+	.mcu_2_spdif_addr = 1134,
+};
+
+static struct sdma_driver_data sdma_imx6q = {
+	.chnenbl0 = SDMA_CHNENBL0_IMX35,
+	.num_events = 48,
+	.script_addrs = &sdma_script_imx6q,
 };
 
 static struct platform_device_id sdma_devtypes[] = {
 	{
+		.name = "imx25-sdma",
+		.driver_data = (unsigned long)&sdma_imx25,
+	}, {
 		.name = "imx31-sdma",
-		.driver_data = IMX31_SDMA,
+		.driver_data = (unsigned long)&sdma_imx31,
 	}, {
 		.name = "imx35-sdma",
-		.driver_data = IMX35_SDMA,
+		.driver_data = (unsigned long)&sdma_imx35,
+	}, {
+		.name = "imx51-sdma",
+		.driver_data = (unsigned long)&sdma_imx51,
+	}, {
+		.name = "imx53-sdma",
+		.driver_data = (unsigned long)&sdma_imx53,
+	}, {
+		.name = "imx6q-sdma",
+		.driver_data = (unsigned long)&sdma_imx6q,
 	}, {
 		/* sentinel */
 	}
@@ -343,8 +443,11 @@ static struct platform_device_id sdma_devtypes[] = {
 MODULE_DEVICE_TABLE(platform, sdma_devtypes);
 
 static const struct of_device_id sdma_dt_ids[] = {
-	{ .compatible = "fsl,imx31-sdma", .data = &sdma_devtypes[IMX31_SDMA], },
-	{ .compatible = "fsl,imx35-sdma", .data = &sdma_devtypes[IMX35_SDMA], },
+	{ .compatible = "fsl,imx6q-sdma", .data = &sdma_imx6q, },
+	{ .compatible = "fsl,imx53-sdma", .data = &sdma_imx53, },
+	{ .compatible = "fsl,imx51-sdma", .data = &sdma_imx51, },
+	{ .compatible = "fsl,imx35-sdma", .data = &sdma_imx35, },
+	{ .compatible = "fsl,imx31-sdma", .data = &sdma_imx31, },
 	{ /* sentinel */ }
 };
 MODULE_DEVICE_TABLE(of, sdma_dt_ids);
@@ -356,8 +459,7 @@ MODULE_DEVICE_TABLE(of, sdma_dt_ids);
 
 static inline u32 chnenbl_ofs(struct sdma_engine *sdma, unsigned int event)
 {
-	u32 chnenbl0 = (sdma->devtype == IMX31_SDMA ? SDMA_CHNENBL0_IMX31 :
-						      SDMA_CHNENBL0_IMX35);
+	u32 chnenbl0 = sdma->drvdata->chnenbl0;
 	return chnenbl0 + event * 4;
 }
 
@@ -547,8 +649,6 @@ static void sdma_tasklet(unsigned long data)
 {
 	struct sdma_channel *sdmac = (struct sdma_channel *) data;
 
-	complete(&sdmac->done);
-
 	if (sdmac->flags & IMX_DMA_SG_LOOP)
 		sdma_handle_channel_loop(sdmac);
 	else
@@ -733,7 +833,7 @@ static int sdma_config_channel(struct sdma_channel *sdmac)
 	sdmac->per_addr = 0;
 
 	if (sdmac->event_id0) {
-		if (sdmac->event_id0 >= sdmac->sdma->num_events)
+		if (sdmac->event_id0 >= sdmac->sdma->drvdata->num_events)
 			return -EINVAL;
 		sdma_event_enable(sdmac, sdmac->event_id0);
 	}
@@ -812,9 +912,6 @@ static int sdma_request_channel(struct sdma_channel *sdmac)
 	sdma->channel_control[channel].current_bd_ptr = sdmac->bd_phys;
 
 	sdma_set_channel_priority(sdmac, MXC_SDMA_DEFAULT_PRIORITY);
-
-	init_completion(&sdmac->done);
-
 	return 0;
 out:
 
@@ -1120,15 +1217,12 @@ static int sdma_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd,
 }
 
 static enum dma_status sdma_tx_status(struct dma_chan *chan,
-					    dma_cookie_t cookie,
-					    struct dma_tx_state *txstate)
+				      dma_cookie_t cookie,
+				      struct dma_tx_state *txstate)
 {
 	struct sdma_channel *sdmac = to_sdma_chan(chan);
-	dma_cookie_t last_used;
-
-	last_used = chan->cookie;
 
-	dma_set_tx_state(txstate, chan->completed_cookie, last_used,
+	dma_set_tx_state(txstate, chan->completed_cookie, chan->cookie,
 			sdmac->chn_count - sdmac->chn_real_count);
 
 	return sdmac->status;
@@ -1218,19 +1312,6 @@ static int __init sdma_init(struct sdma_engine *sdma)
 	int i, ret;
 	dma_addr_t ccb_phys;
 
-	switch (sdma->devtype) {
-	case IMX31_SDMA:
-		sdma->num_events = 32;
-		break;
-	case IMX35_SDMA:
-		sdma->num_events = 48;
-		break;
-	default:
-		dev_err(sdma->dev, "Unknown sdma type %d. aborting\n",
-			sdma->devtype);
-		return -ENODEV;
-	}
-
 	clk_enable(sdma->clk_ipg);
 	clk_enable(sdma->clk_ahb);
 
@@ -1257,7 +1338,7 @@ static int __init sdma_init(struct sdma_engine *sdma)
 			MAX_DMA_CHANNELS * sizeof (struct sdma_channel_control));
 
 	/* disable all channels */
-	for (i = 0; i < sdma->num_events; i++)
+	for (i = 0; i < sdma->drvdata->num_events; i++)
 		writel_relaxed(0, sdma->regs + chnenbl_ofs(sdma, i));
 
 	/* All channels have priority 0 */
@@ -1335,10 +1416,21 @@ static int __init sdma_probe(struct platform_device *pdev)
 	int ret;
 	int irq;
 	struct resource *iores;
-	struct sdma_platform_data *pdata = pdev->dev.platform_data;
+	struct sdma_platform_data *pdata = dev_get_platdata(&pdev->dev);
 	int i;
 	struct sdma_engine *sdma;
 	s32 *saddr_arr;
+	const struct sdma_driver_data *drvdata = NULL;
+
+	if (of_id)
+		drvdata = of_id->data;
+	else if (pdev->id_entry)
+		drvdata = (void *)pdev->id_entry->driver_data;
+
+	if (!drvdata) {
+		dev_err(&pdev->dev, "unable to find driver data\n");
+		return -EINVAL;
+	}
 
 	sdma = kzalloc(sizeof(*sdma), GFP_KERNEL);
 	if (!sdma)
@@ -1347,6 +1439,7 @@ static int __init sdma_probe(struct platform_device *pdev)
 	spin_lock_init(&sdma->channel_0_lock);
 
 	sdma->dev = &pdev->dev;
+	sdma->drvdata = drvdata;
 
 	iores = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	irq = platform_get_irq(pdev, 0);
@@ -1396,10 +1489,6 @@ static int __init sdma_probe(struct platform_device *pdev)
 	for (i = 0; i < SDMA_SCRIPT_ADDRS_ARRAY_SIZE_V1; i++)
 		saddr_arr[i] = -EINVAL;
 
-	if (of_id)
-		pdev->id_entry = of_id->data;
-	sdma->devtype = pdev->id_entry->driver_data;
-
 	dma_cap_set(DMA_SLAVE, sdma->dma_device.cap_mask);
 	dma_cap_set(DMA_CYCLIC, sdma->dma_device.cap_mask);
 
@@ -1431,6 +1520,8 @@ static int __init sdma_probe(struct platform_device *pdev)
 	if (ret)
 		goto err_init;
 
+	if (sdma->drvdata->script_addrs)
+		sdma_add_scripts(sdma, sdma->drvdata->script_addrs);
 	if (pdata && pdata->script_addrs)
 		sdma_add_scripts(sdma, pdata->script_addrs);
 
diff --git a/drivers/dma/ioat/dma_v3.c b/drivers/dma/ioat/dma_v3.c
index b642e035579b..d8ececaf1b57 100644
--- a/drivers/dma/ioat/dma_v3.c
+++ b/drivers/dma/ioat/dma_v3.c
@@ -251,7 +251,7 @@ static bool is_bwd_noraid(struct pci_dev *pdev)
 }
 
 static void pq16_set_src(struct ioat_raw_descriptor *desc[3],
-			dma_addr_t addr, u32 offset, u8 coef, int idx)
+			dma_addr_t addr, u32 offset, u8 coef, unsigned idx)
 {
 	struct ioat_pq_descriptor *pq = (struct ioat_pq_descriptor *)desc[0];
 	struct ioat_pq16a_descriptor *pq16 =
@@ -1775,15 +1775,12 @@ int ioat3_dma_probe(struct ioatdma_device *device, int dca)
 	dma->device_alloc_chan_resources = ioat2_alloc_chan_resources;
 	dma->device_free_chan_resources = ioat2_free_chan_resources;
 
-	if (is_xeon_cb32(pdev))
-		dma->copy_align = 6;
-
 	dma_cap_set(DMA_INTERRUPT, dma->cap_mask);
 	dma->device_prep_dma_interrupt = ioat3_prep_interrupt_lock;
 
 	device->cap = readl(device->reg_base + IOAT_DMA_CAP_OFFSET);
 
-	if (is_bwd_noraid(pdev))
+	if (is_xeon_cb32(pdev) || is_bwd_noraid(pdev))
 		device->cap &= ~(IOAT_CAP_XOR | IOAT_CAP_PQ | IOAT_CAP_RAID16SS);
 
 	/* dca is incompatible with raid operations */
@@ -1793,7 +1790,6 @@ int ioat3_dma_probe(struct ioatdma_device *device, int dca)
 	if (device->cap & IOAT_CAP_XOR) {
 		is_raid_device = true;
 		dma->max_xor = 8;
-		dma->xor_align = 6;
 
 		dma_cap_set(DMA_XOR, dma->cap_mask);
 		dma->device_prep_dma_xor = ioat3_prep_xor;
@@ -1812,13 +1808,8 @@ int ioat3_dma_probe(struct ioatdma_device *device, int dca)
 
 		if (device->cap & IOAT_CAP_RAID16SS) {
 			dma_set_maxpq(dma, 16, 0);
-			dma->pq_align = 0;
 		} else {
 			dma_set_maxpq(dma, 8, 0);
-			if (is_xeon_cb32(pdev))
-				dma->pq_align = 6;
-			else
-				dma->pq_align = 0;
 		}
 
 		if (!(device->cap & IOAT_CAP_XOR)) {
@@ -1829,13 +1820,8 @@ int ioat3_dma_probe(struct ioatdma_device *device, int dca)
 
 			if (device->cap & IOAT_CAP_RAID16SS) {
 				dma->max_xor = 16;
-				dma->xor_align = 0;
 			} else {
 				dma->max_xor = 8;
-				if (is_xeon_cb32(pdev))
-					dma->xor_align = 6;
-				else
-					dma->xor_align = 0;
 			}
 		}
 	}
@@ -1844,14 +1830,6 @@ int ioat3_dma_probe(struct ioatdma_device *device, int dca)
 	device->cleanup_fn = ioat3_cleanup_event;
 	device->timer_fn = ioat3_timer_event;
 
-	if (is_xeon_cb32(pdev)) {
-		dma_cap_clear(DMA_XOR_VAL, dma->cap_mask);
-		dma->device_prep_dma_xor_val = NULL;
-
-		dma_cap_clear(DMA_PQ_VAL, dma->cap_mask);
-		dma->device_prep_dma_pq_val = NULL;
-	}
-
 	/* starting with CB3.3 super extended descriptors are supported */
 	if (device->cap & IOAT_CAP_RAID16SS) {
 		char pool_name[14];
diff --git a/drivers/dma/iop-adma.c b/drivers/dma/iop-adma.c
index cc727ec78c4e..dd8b44a56e5d 100644
--- a/drivers/dma/iop-adma.c
+++ b/drivers/dma/iop-adma.c
@@ -518,7 +518,7 @@ static int iop_adma_alloc_chan_resources(struct dma_chan *chan)
 	struct iop_adma_desc_slot *slot = NULL;
 	int init = iop_chan->slots_allocated ? 0 : 1;
 	struct iop_adma_platform_data *plat_data =
-		iop_chan->device->pdev->dev.platform_data;
+		dev_get_platdata(&iop_chan->device->pdev->dev);
 	int num_descs_in_pool = plat_data->pool_size/IOP_ADMA_SLOT_SIZE;
 
 	/* Allocate descriptor slots */
@@ -1351,7 +1351,7 @@ static int iop_adma_remove(struct platform_device *dev)
 	struct iop_adma_device *device = platform_get_drvdata(dev);
 	struct dma_chan *chan, *_chan;
 	struct iop_adma_chan *iop_chan;
-	struct iop_adma_platform_data *plat_data = dev->dev.platform_data;
+	struct iop_adma_platform_data *plat_data = dev_get_platdata(&dev->dev);
 
 	dma_async_device_unregister(&device->common);
 
@@ -1376,7 +1376,7 @@ static int iop_adma_probe(struct platform_device *pdev)
 	struct iop_adma_device *adev;
 	struct iop_adma_chan *iop_chan;
 	struct dma_device *dma_dev;
-	struct iop_adma_platform_data *plat_data = pdev->dev.platform_data;
+	struct iop_adma_platform_data *plat_data = dev_get_platdata(&pdev->dev);
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	if (!res)
diff --git a/drivers/dma/ipu/ipu_idmac.c b/drivers/dma/ipu/ipu_idmac.c
index d39c2cd0795d..cb9c0bc317e8 100644
--- a/drivers/dma/ipu/ipu_idmac.c
+++ b/drivers/dma/ipu/ipu_idmac.c
@@ -1593,10 +1593,7 @@ static void idmac_free_chan_resources(struct dma_chan *chan)
 static enum dma_status idmac_tx_status(struct dma_chan *chan,
 		       dma_cookie_t cookie, struct dma_tx_state *txstate)
 {
-	dma_set_tx_state(txstate, chan->completed_cookie, chan->cookie, 0);
-	if (cookie != chan->cookie)
-		return DMA_ERROR;
-	return DMA_SUCCESS;
+	return dma_cookie_status(chan, cookie, txstate);
 }
 
 static int __init ipu_idmac_init(struct ipu *ipu)
@@ -1767,7 +1764,6 @@ static int ipu_remove(struct platform_device *pdev)
 	iounmap(ipu->reg_ic);
 	iounmap(ipu->reg_ipu);
 	tasklet_kill(&ipu->tasklet);
-	platform_set_drvdata(pdev, NULL);
 
 	return 0;
 }
diff --git a/drivers/dma/k3dma.c b/drivers/dma/k3dma.c
new file mode 100644
index 000000000000..a2c330f5f952
--- /dev/null
+++ b/drivers/dma/k3dma.c
@@ -0,0 +1,837 @@
+/*
+ * Copyright (c) 2013 Linaro Ltd.
+ * Copyright (c) 2013 Hisilicon Limited.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/sched.h>
+#include <linux/device.h>
+#include <linux/dmaengine.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/of_device.h>
+#include <linux/of.h>
+#include <linux/clk.h>
+#include <linux/of_dma.h>
+
+#include "virt-dma.h"
+
+#define DRIVER_NAME		"k3-dma"
+#define DMA_ALIGN		3
+#define DMA_MAX_SIZE		0x1ffc
+
+#define INT_STAT		0x00
+#define INT_TC1			0x04
+#define INT_ERR1		0x0c
+#define INT_ERR2		0x10
+#define INT_TC1_MASK		0x18
+#define INT_ERR1_MASK		0x20
+#define INT_ERR2_MASK		0x24
+#define INT_TC1_RAW		0x600
+#define INT_ERR1_RAW		0x608
+#define INT_ERR2_RAW		0x610
+#define CH_PRI			0x688
+#define CH_STAT			0x690
+#define CX_CUR_CNT		0x704
+#define CX_LLI			0x800
+#define CX_CNT			0x810
+#define CX_SRC			0x814
+#define CX_DST			0x818
+#define CX_CFG			0x81c
+#define AXI_CFG			0x820
+#define AXI_CFG_DEFAULT		0x201201
+
+#define CX_LLI_CHAIN_EN		0x2
+#define CX_CFG_EN		0x1
+#define CX_CFG_MEM2PER		(0x1 << 2)
+#define CX_CFG_PER2MEM		(0x2 << 2)
+#define CX_CFG_SRCINCR		(0x1 << 31)
+#define CX_CFG_DSTINCR		(0x1 << 30)
+
+struct k3_desc_hw {
+	u32 lli;
+	u32 reserved[3];
+	u32 count;
+	u32 saddr;
+	u32 daddr;
+	u32 config;
+} __aligned(32);
+
+struct k3_dma_desc_sw {
+	struct virt_dma_desc	vd;
+	dma_addr_t		desc_hw_lli;
+	size_t			desc_num;
+	size_t			size;
+	struct k3_desc_hw	desc_hw[0];
+};
+
+struct k3_dma_phy;
+
+struct k3_dma_chan {
+	u32			ccfg;
+	struct virt_dma_chan	vc;
+	struct k3_dma_phy	*phy;
+	struct list_head	node;
+	enum dma_transfer_direction dir;
+	dma_addr_t		dev_addr;
+	enum dma_status		status;
+};
+
+struct k3_dma_phy {
+	u32			idx;
+	void __iomem		*base;
+	struct k3_dma_chan	*vchan;
+	struct k3_dma_desc_sw	*ds_run;
+	struct k3_dma_desc_sw	*ds_done;
+};
+
+struct k3_dma_dev {
+	struct dma_device	slave;
+	void __iomem		*base;
+	struct tasklet_struct	task;
+	spinlock_t		lock;
+	struct list_head	chan_pending;
+	struct k3_dma_phy	*phy;
+	struct k3_dma_chan	*chans;
+	struct clk		*clk;
+	u32			dma_channels;
+	u32			dma_requests;
+};
+
+#define to_k3_dma(dmadev) container_of(dmadev, struct k3_dma_dev, slave)
+
+static struct k3_dma_chan *to_k3_chan(struct dma_chan *chan)
+{
+	return container_of(chan, struct k3_dma_chan, vc.chan);
+}
+
+static void k3_dma_pause_dma(struct k3_dma_phy *phy, bool on)
+{
+	u32 val = 0;
+
+	if (on) {
+		val = readl_relaxed(phy->base + CX_CFG);
+		val |= CX_CFG_EN;
+		writel_relaxed(val, phy->base + CX_CFG);
+	} else {
+		val = readl_relaxed(phy->base + CX_CFG);
+		val &= ~CX_CFG_EN;
+		writel_relaxed(val, phy->base + CX_CFG);
+	}
+}
+
+static void k3_dma_terminate_chan(struct k3_dma_phy *phy, struct k3_dma_dev *d)
+{
+	u32 val = 0;
+
+	k3_dma_pause_dma(phy, false);
+
+	val = 0x1 << phy->idx;
+	writel_relaxed(val, d->base + INT_TC1_RAW);
+	writel_relaxed(val, d->base + INT_ERR1_RAW);
+	writel_relaxed(val, d->base + INT_ERR2_RAW);
+}
+
+static void k3_dma_set_desc(struct k3_dma_phy *phy, struct k3_desc_hw *hw)
+{
+	writel_relaxed(hw->lli, phy->base + CX_LLI);
+	writel_relaxed(hw->count, phy->base + CX_CNT);
+	writel_relaxed(hw->saddr, phy->base + CX_SRC);
+	writel_relaxed(hw->daddr, phy->base + CX_DST);
+	writel_relaxed(AXI_CFG_DEFAULT, phy->base + AXI_CFG);
+	writel_relaxed(hw->config, phy->base + CX_CFG);
+}
+
+static u32 k3_dma_get_curr_cnt(struct k3_dma_dev *d, struct k3_dma_phy *phy)
+{
+	u32 cnt = 0;
+
+	cnt = readl_relaxed(d->base + CX_CUR_CNT + phy->idx * 0x10);
+	cnt &= 0xffff;
+	return cnt;
+}
+
+static u32 k3_dma_get_curr_lli(struct k3_dma_phy *phy)
+{
+	return readl_relaxed(phy->base + CX_LLI);
+}
+
+static u32 k3_dma_get_chan_stat(struct k3_dma_dev *d)
+{
+	return readl_relaxed(d->base + CH_STAT);
+}
+
+static void k3_dma_enable_dma(struct k3_dma_dev *d, bool on)
+{
+	if (on) {
+		/* set same priority */
+		writel_relaxed(0x0, d->base + CH_PRI);
+
+		/* unmask irq */
+		writel_relaxed(0xffff, d->base + INT_TC1_MASK);
+		writel_relaxed(0xffff, d->base + INT_ERR1_MASK);
+		writel_relaxed(0xffff, d->base + INT_ERR2_MASK);
+	} else {
+		/* mask irq */
+		writel_relaxed(0x0, d->base + INT_TC1_MASK);
+		writel_relaxed(0x0, d->base + INT_ERR1_MASK);
+		writel_relaxed(0x0, d->base + INT_ERR2_MASK);
+	}
+}
+
+static irqreturn_t k3_dma_int_handler(int irq, void *dev_id)
+{
+	struct k3_dma_dev *d = (struct k3_dma_dev *)dev_id;
+	struct k3_dma_phy *p;
+	struct k3_dma_chan *c;
+	u32 stat = readl_relaxed(d->base + INT_STAT);
+	u32 tc1  = readl_relaxed(d->base + INT_TC1);
+	u32 err1 = readl_relaxed(d->base + INT_ERR1);
+	u32 err2 = readl_relaxed(d->base + INT_ERR2);
+	u32 i, irq_chan = 0;
+
+	while (stat) {
+		i = __ffs(stat);
+		stat &= (stat - 1);
+		if (likely(tc1 & BIT(i))) {
+			p = &d->phy[i];
+			c = p->vchan;
+			if (c) {
+				unsigned long flags;
+
+				spin_lock_irqsave(&c->vc.lock, flags);
+				vchan_cookie_complete(&p->ds_run->vd);
+				p->ds_done = p->ds_run;
+				spin_unlock_irqrestore(&c->vc.lock, flags);
+			}
+			irq_chan |= BIT(i);
+		}
+		if (unlikely((err1 & BIT(i)) || (err2 & BIT(i))))
+			dev_warn(d->slave.dev, "DMA ERR\n");
+	}
+
+	writel_relaxed(irq_chan, d->base + INT_TC1_RAW);
+	writel_relaxed(err1, d->base + INT_ERR1_RAW);
+	writel_relaxed(err2, d->base + INT_ERR2_RAW);
+
+	if (irq_chan) {
+		tasklet_schedule(&d->task);
+		return IRQ_HANDLED;
+	} else
+		return IRQ_NONE;
+}
+
+static int k3_dma_start_txd(struct k3_dma_chan *c)
+{
+	struct k3_dma_dev *d = to_k3_dma(c->vc.chan.device);
+	struct virt_dma_desc *vd = vchan_next_desc(&c->vc);
+
+	if (!c->phy)
+		return -EAGAIN;
+
+	if (BIT(c->phy->idx) & k3_dma_get_chan_stat(d))
+		return -EAGAIN;
+
+	if (vd) {
+		struct k3_dma_desc_sw *ds =
+			container_of(vd, struct k3_dma_desc_sw, vd);
+		/*
+		 * fetch and remove request from vc->desc_issued
+		 * so vc->desc_issued only contains desc pending
+		 */
+		list_del(&ds->vd.node);
+		c->phy->ds_run = ds;
+		c->phy->ds_done = NULL;
+		/* start dma */
+		k3_dma_set_desc(c->phy, &ds->desc_hw[0]);
+		return 0;
+	}
+	c->phy->ds_done = NULL;
+	c->phy->ds_run = NULL;
+	return -EAGAIN;
+}
+
+static void k3_dma_tasklet(unsigned long arg)
+{
+	struct k3_dma_dev *d = (struct k3_dma_dev *)arg;
+	struct k3_dma_phy *p;
+	struct k3_dma_chan *c, *cn;
+	unsigned pch, pch_alloc = 0;
+
+	/* check new dma request of running channel in vc->desc_issued */
+	list_for_each_entry_safe(c, cn, &d->slave.channels, vc.chan.device_node) {
+		spin_lock_irq(&c->vc.lock);
+		p = c->phy;
+		if (p && p->ds_done) {
+			if (k3_dma_start_txd(c)) {
+				/* No current txd associated with this channel */
+				dev_dbg(d->slave.dev, "pchan %u: free\n", p->idx);
+				/* Mark this channel free */
+				c->phy = NULL;
+				p->vchan = NULL;
+			}
+		}
+		spin_unlock_irq(&c->vc.lock);
+	}
+
+	/* check new channel request in d->chan_pending */
+	spin_lock_irq(&d->lock);
+	for (pch = 0; pch < d->dma_channels; pch++) {
+		p = &d->phy[pch];
+
+		if (p->vchan == NULL && !list_empty(&d->chan_pending)) {
+			c = list_first_entry(&d->chan_pending,
+				struct k3_dma_chan, node);
+			/* remove from d->chan_pending */
+			list_del_init(&c->node);
+			pch_alloc |= 1 << pch;
+			/* Mark this channel allocated */
+			p->vchan = c;
+			c->phy = p;
+			dev_dbg(d->slave.dev, "pchan %u: alloc vchan %p\n", pch, &c->vc);
+		}
+	}
+	spin_unlock_irq(&d->lock);
+
+	for (pch = 0; pch < d->dma_channels; pch++) {
+		if (pch_alloc & (1 << pch)) {
+			p = &d->phy[pch];
+			c = p->vchan;
+			if (c) {
+				spin_lock_irq(&c->vc.lock);
+				k3_dma_start_txd(c);
+				spin_unlock_irq(&c->vc.lock);
+			}
+		}
+	}
+}
+
+static int k3_dma_alloc_chan_resources(struct dma_chan *chan)
+{
+	return 0;
+}
+
+static void k3_dma_free_chan_resources(struct dma_chan *chan)
+{
+	struct k3_dma_chan *c = to_k3_chan(chan);
+	struct k3_dma_dev *d = to_k3_dma(chan->device);
+	unsigned long flags;
+
+	spin_lock_irqsave(&d->lock, flags);
+	list_del_init(&c->node);
+	spin_unlock_irqrestore(&d->lock, flags);
+
+	vchan_free_chan_resources(&c->vc);
+	c->ccfg = 0;
+}
+
+static enum dma_status k3_dma_tx_status(struct dma_chan *chan,
+	dma_cookie_t cookie, struct dma_tx_state *state)
+{
+	struct k3_dma_chan *c = to_k3_chan(chan);
+	struct k3_dma_dev *d = to_k3_dma(chan->device);
+	struct k3_dma_phy *p;
+	struct virt_dma_desc *vd;
+	unsigned long flags;
+	enum dma_status ret;
+	size_t bytes = 0;
+
+	ret = dma_cookie_status(&c->vc.chan, cookie, state);
+	if (ret == DMA_SUCCESS)
+		return ret;
+
+	spin_lock_irqsave(&c->vc.lock, flags);
+	p = c->phy;
+	ret = c->status;
+
+	/*
+	 * If the cookie is on our issue queue, then the residue is
+	 * its total size.
+	 */
+	vd = vchan_find_desc(&c->vc, cookie);
+	if (vd) {
+		bytes = container_of(vd, struct k3_dma_desc_sw, vd)->size;
+	} else if ((!p) || (!p->ds_run)) {
+		bytes = 0;
+	} else {
+		struct k3_dma_desc_sw *ds = p->ds_run;
+		u32 clli = 0, index = 0;
+
+		bytes = k3_dma_get_curr_cnt(d, p);
+		clli = k3_dma_get_curr_lli(p);
+		index = (clli - ds->desc_hw_lli) / sizeof(struct k3_desc_hw);
+		for (; index < ds->desc_num; index++) {
+			bytes += ds->desc_hw[index].count;
+			/* end of lli */
+			if (!ds->desc_hw[index].lli)
+				break;
+		}
+	}
+	spin_unlock_irqrestore(&c->vc.lock, flags);
+	dma_set_residue(state, bytes);
+	return ret;
+}
+
+static void k3_dma_issue_pending(struct dma_chan *chan)
+{
+	struct k3_dma_chan *c = to_k3_chan(chan);
+	struct k3_dma_dev *d = to_k3_dma(chan->device);
+	unsigned long flags;
+
+	spin_lock_irqsave(&c->vc.lock, flags);
+	/* add request to vc->desc_issued */
+	if (vchan_issue_pending(&c->vc)) {
+		spin_lock(&d->lock);
+		if (!c->phy) {
+			if (list_empty(&c->node)) {
+				/* if new channel, add chan_pending */
+				list_add_tail(&c->node, &d->chan_pending);
+				/* check in tasklet */
+				tasklet_schedule(&d->task);
+				dev_dbg(d->slave.dev, "vchan %p: issued\n", &c->vc);
+			}
+		}
+		spin_unlock(&d->lock);
+	} else
+		dev_dbg(d->slave.dev, "vchan %p: nothing to issue\n", &c->vc);
+	spin_unlock_irqrestore(&c->vc.lock, flags);
+}
+
+static void k3_dma_fill_desc(struct k3_dma_desc_sw *ds, dma_addr_t dst,
+			dma_addr_t src, size_t len, u32 num, u32 ccfg)
+{
+	if ((num + 1) < ds->desc_num)
+		ds->desc_hw[num].lli = ds->desc_hw_lli + (num + 1) *
+			sizeof(struct k3_desc_hw);
+	ds->desc_hw[num].lli |= CX_LLI_CHAIN_EN;
+	ds->desc_hw[num].count = len;
+	ds->desc_hw[num].saddr = src;
+	ds->desc_hw[num].daddr = dst;
+	ds->desc_hw[num].config = ccfg;
+}
+
+static struct dma_async_tx_descriptor *k3_dma_prep_memcpy(
+	struct dma_chan *chan,	dma_addr_t dst, dma_addr_t src,
+	size_t len, unsigned long flags)
+{
+	struct k3_dma_chan *c = to_k3_chan(chan);
+	struct k3_dma_desc_sw *ds;
+	size_t copy = 0;
+	int num = 0;
+
+	if (!len)
+		return NULL;
+
+	num = DIV_ROUND_UP(len, DMA_MAX_SIZE);
+	ds = kzalloc(sizeof(*ds) + num * sizeof(ds->desc_hw[0]), GFP_ATOMIC);
+	if (!ds) {
+		dev_dbg(chan->device->dev, "vchan %p: kzalloc fail\n", &c->vc);
+		return NULL;
+	}
+	ds->desc_hw_lli = __virt_to_phys((unsigned long)&ds->desc_hw[0]);
+	ds->size = len;
+	ds->desc_num = num;
+	num = 0;
+
+	if (!c->ccfg) {
+		/* default is memtomem, without calling device_control */
+		c->ccfg = CX_CFG_SRCINCR | CX_CFG_DSTINCR | CX_CFG_EN;
+		c->ccfg |= (0xf << 20) | (0xf << 24);	/* burst = 16 */
+		c->ccfg |= (0x3 << 12) | (0x3 << 16);	/* width = 64 bit */
+	}
+
+	do {
+		copy = min_t(size_t, len, DMA_MAX_SIZE);
+		k3_dma_fill_desc(ds, dst, src, copy, num++, c->ccfg);
+
+		if (c->dir == DMA_MEM_TO_DEV) {
+			src += copy;
+		} else if (c->dir == DMA_DEV_TO_MEM) {
+			dst += copy;
+		} else {
+			src += copy;
+			dst += copy;
+		}
+		len -= copy;
+	} while (len);
+
+	ds->desc_hw[num-1].lli = 0;	/* end of link */
+	return vchan_tx_prep(&c->vc, &ds->vd, flags);
+}
+
+static struct dma_async_tx_descriptor *k3_dma_prep_slave_sg(
+	struct dma_chan *chan, struct scatterlist *sgl, unsigned int sglen,
+	enum dma_transfer_direction dir, unsigned long flags, void *context)
+{
+	struct k3_dma_chan *c = to_k3_chan(chan);
+	struct k3_dma_desc_sw *ds;
+	size_t len, avail, total = 0;
+	struct scatterlist *sg;
+	dma_addr_t addr, src = 0, dst = 0;
+	int num = sglen, i;
+
+	if (sgl == 0)
+		return NULL;
+
+	for_each_sg(sgl, sg, sglen, i) {
+		avail = sg_dma_len(sg);
+		if (avail > DMA_MAX_SIZE)
+			num += DIV_ROUND_UP(avail, DMA_MAX_SIZE) - 1;
+	}
+
+	ds = kzalloc(sizeof(*ds) + num * sizeof(ds->desc_hw[0]), GFP_ATOMIC);
+	if (!ds) {
+		dev_dbg(chan->device->dev, "vchan %p: kzalloc fail\n", &c->vc);
+		return NULL;
+	}
+	ds->desc_hw_lli = __virt_to_phys((unsigned long)&ds->desc_hw[0]);
+	ds->desc_num = num;
+	num = 0;
+
+	for_each_sg(sgl, sg, sglen, i) {
+		addr = sg_dma_address(sg);
+		avail = sg_dma_len(sg);
+		total += avail;
+
+		do {
+			len = min_t(size_t, avail, DMA_MAX_SIZE);
+
+			if (dir == DMA_MEM_TO_DEV) {
+				src = addr;
+				dst = c->dev_addr;
+			} else if (dir == DMA_DEV_TO_MEM) {
+				src = c->dev_addr;
+				dst = addr;
+			}
+
+			k3_dma_fill_desc(ds, dst, src, len, num++, c->ccfg);
+
+			addr += len;
+			avail -= len;
+		} while (avail);
+	}
+
+	ds->desc_hw[num-1].lli = 0;	/* end of link */
+	ds->size = total;
+	return vchan_tx_prep(&c->vc, &ds->vd, flags);
+}
+
+static int k3_dma_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd,
+	unsigned long arg)
+{
+	struct k3_dma_chan *c = to_k3_chan(chan);
+	struct k3_dma_dev *d = to_k3_dma(chan->device);
+	struct dma_slave_config *cfg = (void *)arg;
+	struct k3_dma_phy *p = c->phy;
+	unsigned long flags;
+	u32 maxburst = 0, val = 0;
+	enum dma_slave_buswidth width = DMA_SLAVE_BUSWIDTH_UNDEFINED;
+	LIST_HEAD(head);
+
+	switch (cmd) {
+	case DMA_SLAVE_CONFIG:
+		if (cfg == NULL)
+			return -EINVAL;
+		c->dir = cfg->direction;
+		if (c->dir == DMA_DEV_TO_MEM) {
+			c->ccfg = CX_CFG_DSTINCR;
+			c->dev_addr = cfg->src_addr;
+			maxburst = cfg->src_maxburst;
+			width = cfg->src_addr_width;
+		} else if (c->dir == DMA_MEM_TO_DEV) {
+			c->ccfg = CX_CFG_SRCINCR;
+			c->dev_addr = cfg->dst_addr;
+			maxburst = cfg->dst_maxburst;
+			width = cfg->dst_addr_width;
+		}
+		switch (width) {
+		case DMA_SLAVE_BUSWIDTH_1_BYTE:
+		case DMA_SLAVE_BUSWIDTH_2_BYTES:
+		case DMA_SLAVE_BUSWIDTH_4_BYTES:
+		case DMA_SLAVE_BUSWIDTH_8_BYTES:
+			val =  __ffs(width);
+			break;
+		default:
+			val = 3;
+			break;
+		}
+		c->ccfg |= (val << 12) | (val << 16);
+
+		if ((maxburst == 0) || (maxburst > 16))
+			val = 16;
+		else
+			val = maxburst - 1;
+		c->ccfg |= (val << 20) | (val << 24);
+		c->ccfg |= CX_CFG_MEM2PER | CX_CFG_EN;
+
+		/* specific request line */
+		c->ccfg |= c->vc.chan.chan_id << 4;
+		break;
+
+	case DMA_TERMINATE_ALL:
+		dev_dbg(d->slave.dev, "vchan %p: terminate all\n", &c->vc);
+
+		/* Prevent this channel being scheduled */
+		spin_lock(&d->lock);
+		list_del_init(&c->node);
+		spin_unlock(&d->lock);
+
+		/* Clear the tx descriptor lists */
+		spin_lock_irqsave(&c->vc.lock, flags);
+		vchan_get_all_descriptors(&c->vc, &head);
+		if (p) {
+			/* vchan is assigned to a pchan - stop the channel */
+			k3_dma_terminate_chan(p, d);
+			c->phy = NULL;
+			p->vchan = NULL;
+			p->ds_run = p->ds_done = NULL;
+		}
+		spin_unlock_irqrestore(&c->vc.lock, flags);
+		vchan_dma_desc_free_list(&c->vc, &head);
+		break;
+
+	case DMA_PAUSE:
+		dev_dbg(d->slave.dev, "vchan %p: pause\n", &c->vc);
+		if (c->status == DMA_IN_PROGRESS) {
+			c->status = DMA_PAUSED;
+			if (p) {
+				k3_dma_pause_dma(p, false);
+			} else {
+				spin_lock(&d->lock);
+				list_del_init(&c->node);
+				spin_unlock(&d->lock);
+			}
+		}
+		break;
+
+	case DMA_RESUME:
+		dev_dbg(d->slave.dev, "vchan %p: resume\n", &c->vc);
+		spin_lock_irqsave(&c->vc.lock, flags);
+		if (c->status == DMA_PAUSED) {
+			c->status = DMA_IN_PROGRESS;
+			if (p) {
+				k3_dma_pause_dma(p, true);
+			} else if (!list_empty(&c->vc.desc_issued)) {
+				spin_lock(&d->lock);
+				list_add_tail(&c->node, &d->chan_pending);
+				spin_unlock(&d->lock);
+			}
+		}
+		spin_unlock_irqrestore(&c->vc.lock, flags);
+		break;
+	default:
+		return -ENXIO;
+	}
+	return 0;
+}
+
+static void k3_dma_free_desc(struct virt_dma_desc *vd)
+{
+	struct k3_dma_desc_sw *ds =
+		container_of(vd, struct k3_dma_desc_sw, vd);
+
+	kfree(ds);
+}
+
+static struct of_device_id k3_pdma_dt_ids[] = {
+	{ .compatible = "hisilicon,k3-dma-1.0", },
+	{}
+};
+MODULE_DEVICE_TABLE(of, k3_pdma_dt_ids);
+
+static struct dma_chan *k3_of_dma_simple_xlate(struct of_phandle_args *dma_spec,
+						struct of_dma *ofdma)
+{
+	struct k3_dma_dev *d = ofdma->of_dma_data;
+	unsigned int request = dma_spec->args[0];
+
+	if (request > d->dma_requests)
+		return NULL;
+
+	return dma_get_slave_channel(&(d->chans[request].vc.chan));
+}
+
+static int k3_dma_probe(struct platform_device *op)
+{
+	struct k3_dma_dev *d;
+	const struct of_device_id *of_id;
+	struct resource *iores;
+	int i, ret, irq = 0;
+
+	iores = platform_get_resource(op, IORESOURCE_MEM, 0);
+	if (!iores)
+		return -EINVAL;
+
+	d = devm_kzalloc(&op->dev, sizeof(*d), GFP_KERNEL);
+	if (!d)
+		return -ENOMEM;
+
+	d->base = devm_ioremap_resource(&op->dev, iores);
+	if (IS_ERR(d->base))
+		return PTR_ERR(d->base);
+
+	of_id = of_match_device(k3_pdma_dt_ids, &op->dev);
+	if (of_id) {
+		of_property_read_u32((&op->dev)->of_node,
+				"dma-channels", &d->dma_channels);
+		of_property_read_u32((&op->dev)->of_node,
+				"dma-requests", &d->dma_requests);
+	}
+
+	d->clk = devm_clk_get(&op->dev, NULL);
+	if (IS_ERR(d->clk)) {
+		dev_err(&op->dev, "no dma clk\n");
+		return PTR_ERR(d->clk);
+	}
+
+	irq = platform_get_irq(op, 0);
+	ret = devm_request_irq(&op->dev, irq,
+			k3_dma_int_handler, IRQF_DISABLED, DRIVER_NAME, d);
+	if (ret)
+		return ret;
+
+	/* init phy channel */
+	d->phy = devm_kzalloc(&op->dev,
+		d->dma_channels * sizeof(struct k3_dma_phy), GFP_KERNEL);
+	if (d->phy == NULL)
+		return -ENOMEM;
+
+	for (i = 0; i < d->dma_channels; i++) {
+		struct k3_dma_phy *p = &d->phy[i];
+
+		p->idx = i;
+		p->base = d->base + i * 0x40;
+	}
+
+	INIT_LIST_HEAD(&d->slave.channels);
+	dma_cap_set(DMA_SLAVE, d->slave.cap_mask);
+	dma_cap_set(DMA_MEMCPY, d->slave.cap_mask);
+	d->slave.dev = &op->dev;
+	d->slave.device_alloc_chan_resources = k3_dma_alloc_chan_resources;
+	d->slave.device_free_chan_resources = k3_dma_free_chan_resources;
+	d->slave.device_tx_status = k3_dma_tx_status;
+	d->slave.device_prep_dma_memcpy = k3_dma_prep_memcpy;
+	d->slave.device_prep_slave_sg = k3_dma_prep_slave_sg;
+	d->slave.device_issue_pending = k3_dma_issue_pending;
+	d->slave.device_control = k3_dma_control;
+	d->slave.copy_align = DMA_ALIGN;
+	d->slave.chancnt = d->dma_requests;
+
+	/* init virtual channel */
+	d->chans = devm_kzalloc(&op->dev,
+		d->dma_requests * sizeof(struct k3_dma_chan), GFP_KERNEL);
+	if (d->chans == NULL)
+		return -ENOMEM;
+
+	for (i = 0; i < d->dma_requests; i++) {
+		struct k3_dma_chan *c = &d->chans[i];
+
+		c->status = DMA_IN_PROGRESS;
+		INIT_LIST_HEAD(&c->node);
+		c->vc.desc_free = k3_dma_free_desc;
+		vchan_init(&c->vc, &d->slave);
+	}
+
+	/* Enable clock before accessing registers */
+	ret = clk_prepare_enable(d->clk);
+	if (ret < 0) {
+		dev_err(&op->dev, "clk_prepare_enable failed: %d\n", ret);
+		return ret;
+	}
+
+	k3_dma_enable_dma(d, true);
+
+	ret = dma_async_device_register(&d->slave);
+	if (ret)
+		return ret;
+
+	ret = of_dma_controller_register((&op->dev)->of_node,
+					k3_of_dma_simple_xlate, d);
+	if (ret)
+		goto of_dma_register_fail;
+
+	spin_lock_init(&d->lock);
+	INIT_LIST_HEAD(&d->chan_pending);
+	tasklet_init(&d->task, k3_dma_tasklet, (unsigned long)d);
+	platform_set_drvdata(op, d);
+	dev_info(&op->dev, "initialized\n");
+
+	return 0;
+
+of_dma_register_fail:
+	dma_async_device_unregister(&d->slave);
+	return ret;
+}
+
+static int k3_dma_remove(struct platform_device *op)
+{
+	struct k3_dma_chan *c, *cn;
+	struct k3_dma_dev *d = platform_get_drvdata(op);
+
+	dma_async_device_unregister(&d->slave);
+	of_dma_controller_free((&op->dev)->of_node);
+
+	list_for_each_entry_safe(c, cn, &d->slave.channels, vc.chan.device_node) {
+		list_del(&c->vc.chan.device_node);
+		tasklet_kill(&c->vc.task);
+	}
+	tasklet_kill(&d->task);
+	clk_disable_unprepare(d->clk);
+	return 0;
+}
+
+static int k3_dma_suspend(struct device *dev)
+{
+	struct k3_dma_dev *d = dev_get_drvdata(dev);
+	u32 stat = 0;
+
+	stat = k3_dma_get_chan_stat(d);
+	if (stat) {
+		dev_warn(d->slave.dev,
+			"chan %d is running fail to suspend\n", stat);
+		return -1;
+	}
+	k3_dma_enable_dma(d, false);
+	clk_disable_unprepare(d->clk);
+	return 0;
+}
+
+static int k3_dma_resume(struct device *dev)
+{
+	struct k3_dma_dev *d = dev_get_drvdata(dev);
+	int ret = 0;
+
+	ret = clk_prepare_enable(d->clk);
+	if (ret < 0) {
+		dev_err(d->slave.dev, "clk_prepare_enable failed: %d\n", ret);
+		return ret;
+	}
+	k3_dma_enable_dma(d, true);
+	return 0;
+}
+
+SIMPLE_DEV_PM_OPS(k3_dma_pmops, k3_dma_suspend, k3_dma_resume);
+
+static struct platform_driver k3_pdma_driver = {
+	.driver		= {
+		.name	= DRIVER_NAME,
+		.owner  = THIS_MODULE,
+		.pm	= &k3_dma_pmops,
+		.of_match_table = k3_pdma_dt_ids,
+	},
+	.probe		= k3_dma_probe,
+	.remove		= k3_dma_remove,
+};
+
+module_platform_driver(k3_pdma_driver);
+
+MODULE_DESCRIPTION("Hisilicon k3 DMA Driver");
+MODULE_ALIAS("platform:k3dma");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/dma/mmp_pdma.c b/drivers/dma/mmp_pdma.c
index c26699f9c4df..ff8d7827f8cb 100644
--- a/drivers/dma/mmp_pdma.c
+++ b/drivers/dma/mmp_pdma.c
@@ -18,7 +18,9 @@
 #include <linux/platform_data/mmp_dma.h>
 #include <linux/dmapool.h>
 #include <linux/of_device.h>
+#include <linux/of_dma.h>
 #include <linux/of.h>
+#include <linux/dma/mmp-pdma.h>
 
 #include "dmaengine.h"
 
@@ -47,6 +49,8 @@
 #define DCSR_CMPST	(1 << 10)       /* The Descriptor Compare Status */
 #define DCSR_EORINTR	(1 << 9)        /* The end of Receive */
 
+#define DRCMR(n)	((((n) < 64) ? 0x0100 : 0x1100) + \
+				 (((n) & 0x3f) << 2))
 #define DRCMR_MAPVLD	(1 << 7)	/* Map Valid (read / write) */
 #define DRCMR_CHLNUM	0x1f		/* mask for Channel Number (read / write) */
 
@@ -69,7 +73,7 @@
 #define DCMD_LENGTH	0x01fff		/* length mask (max = 8K - 1) */
 
 #define PDMA_ALIGNMENT		3
-#define PDMA_MAX_DESC_BYTES	0x1000
+#define PDMA_MAX_DESC_BYTES	DCMD_LENGTH
 
 struct mmp_pdma_desc_hw {
 	u32 ddadr;	/* Points to the next descriptor + flags */
@@ -94,6 +98,9 @@ struct mmp_pdma_chan {
 	struct mmp_pdma_phy *phy;
 	enum dma_transfer_direction dir;
 
+	struct mmp_pdma_desc_sw *cyclic_first;	/* first desc_sw if channel
+						 * is in cyclic mode */
+
 	/* channel's basic info */
 	struct tasklet_struct tasklet;
 	u32 dcmd;
@@ -105,6 +112,7 @@ struct mmp_pdma_chan {
 	struct list_head chain_pending;	/* Link descriptors queue for pending */
 	struct list_head chain_running;	/* Link descriptors queue for running */
 	bool idle;			/* channel statue machine */
+	bool byte_align;
 
 	struct dma_pool *desc_pool;	/* Descriptors pool */
 };
@@ -121,6 +129,7 @@ struct mmp_pdma_device {
 	struct device			*dev;
 	struct dma_device		device;
 	struct mmp_pdma_phy		*phy;
+	spinlock_t phy_lock; /* protect alloc/free phy channels */
 };
 
 #define tx_to_mmp_pdma_desc(tx) container_of(tx, struct mmp_pdma_desc_sw, async_tx)
@@ -137,15 +146,21 @@ static void set_desc(struct mmp_pdma_phy *phy, dma_addr_t addr)
 
 static void enable_chan(struct mmp_pdma_phy *phy)
 {
-	u32 reg;
+	u32 reg, dalgn;
 
 	if (!phy->vchan)
 		return;
 
-	reg = phy->vchan->drcmr;
-	reg = (((reg) < 64) ? 0x0100 : 0x1100) + (((reg) & 0x3f) << 2);
+	reg = DRCMR(phy->vchan->drcmr);
 	writel(DRCMR_MAPVLD | phy->idx, phy->base + reg);
 
+	dalgn = readl(phy->base + DALGN);
+	if (phy->vchan->byte_align)
+		dalgn |= 1 << phy->idx;
+	else
+		dalgn &= ~(1 << phy->idx);
+	writel(dalgn, phy->base + DALGN);
+
 	reg = (phy->idx << 2) + DCSR;
 	writel(readl(phy->base + reg) | DCSR_RUN,
 					phy->base + reg);
@@ -218,7 +233,8 @@ static struct mmp_pdma_phy *lookup_phy(struct mmp_pdma_chan *pchan)
 {
 	int prio, i;
 	struct mmp_pdma_device *pdev = to_mmp_pdma_dev(pchan->chan.device);
-	struct mmp_pdma_phy *phy;
+	struct mmp_pdma_phy *phy, *found = NULL;
+	unsigned long flags;
 
 	/*
 	 * dma channel priorities
@@ -227,6 +243,8 @@ static struct mmp_pdma_phy *lookup_phy(struct mmp_pdma_chan *pchan)
 	 * ch 8 - 11, 24 - 27  <--> (2)
 	 * ch 12 - 15, 28 - 31  <--> (3)
 	 */
+
+	spin_lock_irqsave(&pdev->phy_lock, flags);
 	for (prio = 0; prio <= (((pdev->dma_channels - 1) & 0xf) >> 2); prio++) {
 		for (i = 0; i < pdev->dma_channels; i++) {
 			if (prio != ((i & 0xf) >> 2))
@@ -234,31 +252,34 @@ static struct mmp_pdma_phy *lookup_phy(struct mmp_pdma_chan *pchan)
 			phy = &pdev->phy[i];
 			if (!phy->vchan) {
 				phy->vchan = pchan;
-				return phy;
+				found = phy;
+				goto out_unlock;
 			}
 		}
 	}
 
-	return NULL;
+out_unlock:
+	spin_unlock_irqrestore(&pdev->phy_lock, flags);
+	return found;
 }
 
-/* desc->tx_list ==> pending list */
-static void append_pending_queue(struct mmp_pdma_chan *chan,
-					struct mmp_pdma_desc_sw *desc)
+static void mmp_pdma_free_phy(struct mmp_pdma_chan *pchan)
 {
-	struct mmp_pdma_desc_sw *tail =
-				to_mmp_pdma_desc(chan->chain_pending.prev);
+	struct mmp_pdma_device *pdev = to_mmp_pdma_dev(pchan->chan.device);
+	unsigned long flags;
+	u32 reg;
 
-	if (list_empty(&chan->chain_pending))
-		goto out_splice;
+	if (!pchan->phy)
+		return;
 
-	/* one irq per queue, even appended */
-	tail->desc.ddadr = desc->async_tx.phys;
-	tail->desc.dcmd &= ~DCMD_ENDIRQEN;
+	/* clear the channel mapping in DRCMR */
+	reg = DRCMR(pchan->phy->vchan->drcmr);
+	writel(0, pchan->phy->base + reg);
 
-	/* softly link to pending list */
-out_splice:
-	list_splice_tail_init(&desc->tx_list, &chan->chain_pending);
+	spin_lock_irqsave(&pdev->phy_lock, flags);
+	pchan->phy->vchan = NULL;
+	pchan->phy = NULL;
+	spin_unlock_irqrestore(&pdev->phy_lock, flags);
 }
 
 /**
@@ -277,10 +298,7 @@ static void start_pending_queue(struct mmp_pdma_chan *chan)
 
 	if (list_empty(&chan->chain_pending)) {
 		/* chance to re-fetch phy channel with higher prio */
-		if (chan->phy) {
-			chan->phy->vchan = NULL;
-			chan->phy = NULL;
-		}
+		mmp_pdma_free_phy(chan);
 		dev_dbg(chan->dev, "no pending list\n");
 		return;
 	}
@@ -326,14 +344,16 @@ static dma_cookie_t mmp_pdma_tx_submit(struct dma_async_tx_descriptor *tx)
 		cookie = dma_cookie_assign(&child->async_tx);
 	}
 
-	append_pending_queue(chan, desc);
+	/* softly link to pending list - desc->tx_list ==> pending list */
+	list_splice_tail_init(&desc->tx_list, &chan->chain_pending);
 
 	spin_unlock_irqrestore(&chan->desc_lock, flags);
 
 	return cookie;
 }
 
-struct mmp_pdma_desc_sw *mmp_pdma_alloc_descriptor(struct mmp_pdma_chan *chan)
+static struct mmp_pdma_desc_sw *
+mmp_pdma_alloc_descriptor(struct mmp_pdma_chan *chan)
 {
 	struct mmp_pdma_desc_sw *desc;
 	dma_addr_t pdesc;
@@ -377,10 +397,7 @@ static int mmp_pdma_alloc_chan_resources(struct dma_chan *dchan)
 		dev_err(chan->dev, "unable to allocate descriptor pool\n");
 		return -ENOMEM;
 	}
-	if (chan->phy) {
-		chan->phy->vchan = NULL;
-		chan->phy = NULL;
-	}
+	mmp_pdma_free_phy(chan);
 	chan->idle = true;
 	chan->dev_addr = 0;
 	return 1;
@@ -411,10 +428,7 @@ static void mmp_pdma_free_chan_resources(struct dma_chan *dchan)
 	chan->desc_pool = NULL;
 	chan->idle = true;
 	chan->dev_addr = 0;
-	if (chan->phy) {
-		chan->phy->vchan = NULL;
-		chan->phy = NULL;
-	}
+	mmp_pdma_free_phy(chan);
 	return;
 }
 
@@ -434,6 +448,7 @@ mmp_pdma_prep_memcpy(struct dma_chan *dchan,
 		return NULL;
 
 	chan = to_mmp_pdma_chan(dchan);
+	chan->byte_align = false;
 
 	if (!chan->dir) {
 		chan->dir = DMA_MEM_TO_MEM;
@@ -450,6 +465,8 @@ mmp_pdma_prep_memcpy(struct dma_chan *dchan,
 		}
 
 		copy = min_t(size_t, len, PDMA_MAX_DESC_BYTES);
+		if (dma_src & 0x7 || dma_dst & 0x7)
+			chan->byte_align = true;
 
 		new->desc.dcmd = chan->dcmd | (DCMD_LENGTH & copy);
 		new->desc.dsadr = dma_src;
@@ -486,6 +503,8 @@ mmp_pdma_prep_memcpy(struct dma_chan *dchan,
 	new->desc.ddadr = DDADR_STOP;
 	new->desc.dcmd |= DCMD_ENDIRQEN;
 
+	chan->cyclic_first = NULL;
+
 	return &first->async_tx;
 
 fail:
@@ -509,12 +528,16 @@ mmp_pdma_prep_slave_sg(struct dma_chan *dchan, struct scatterlist *sgl,
 	if ((sgl == NULL) || (sg_len == 0))
 		return NULL;
 
+	chan->byte_align = false;
+
 	for_each_sg(sgl, sg, sg_len, i) {
 		addr = sg_dma_address(sg);
 		avail = sg_dma_len(sgl);
 
 		do {
 			len = min_t(size_t, avail, PDMA_MAX_DESC_BYTES);
+			if (addr & 0x7)
+				chan->byte_align = true;
 
 			/* allocate and populate the descriptor */
 			new = mmp_pdma_alloc_descriptor(chan);
@@ -557,6 +580,94 @@ mmp_pdma_prep_slave_sg(struct dma_chan *dchan, struct scatterlist *sgl,
 	new->desc.ddadr = DDADR_STOP;
 	new->desc.dcmd |= DCMD_ENDIRQEN;
 
+	chan->dir = dir;
+	chan->cyclic_first = NULL;
+
+	return &first->async_tx;
+
+fail:
+	if (first)
+		mmp_pdma_free_desc_list(chan, &first->tx_list);
+	return NULL;
+}
+
+static struct dma_async_tx_descriptor *mmp_pdma_prep_dma_cyclic(
+	struct dma_chan *dchan, dma_addr_t buf_addr, size_t len,
+	size_t period_len, enum dma_transfer_direction direction,
+	unsigned long flags, void *context)
+{
+	struct mmp_pdma_chan *chan;
+	struct mmp_pdma_desc_sw *first = NULL, *prev = NULL, *new;
+	dma_addr_t dma_src, dma_dst;
+
+	if (!dchan || !len || !period_len)
+		return NULL;
+
+	/* the buffer length must be a multiple of period_len */
+	if (len % period_len != 0)
+		return NULL;
+
+	if (period_len > PDMA_MAX_DESC_BYTES)
+		return NULL;
+
+	chan = to_mmp_pdma_chan(dchan);
+
+	switch (direction) {
+	case DMA_MEM_TO_DEV:
+		dma_src = buf_addr;
+		dma_dst = chan->dev_addr;
+		break;
+	case DMA_DEV_TO_MEM:
+		dma_dst = buf_addr;
+		dma_src = chan->dev_addr;
+		break;
+	default:
+		dev_err(chan->dev, "Unsupported direction for cyclic DMA\n");
+		return NULL;
+	}
+
+	chan->dir = direction;
+
+	do {
+		/* Allocate the link descriptor from DMA pool */
+		new = mmp_pdma_alloc_descriptor(chan);
+		if (!new) {
+			dev_err(chan->dev, "no memory for desc\n");
+			goto fail;
+		}
+
+		new->desc.dcmd = chan->dcmd | DCMD_ENDIRQEN |
+					(DCMD_LENGTH & period_len);
+		new->desc.dsadr = dma_src;
+		new->desc.dtadr = dma_dst;
+
+		if (!first)
+			first = new;
+		else
+			prev->desc.ddadr = new->async_tx.phys;
+
+		new->async_tx.cookie = 0;
+		async_tx_ack(&new->async_tx);
+
+		prev = new;
+		len -= period_len;
+
+		if (chan->dir == DMA_MEM_TO_DEV)
+			dma_src += period_len;
+		else
+			dma_dst += period_len;
+
+		/* Insert the link descriptor to the LD ring */
+		list_add_tail(&new->node, &first->tx_list);
+	} while (len);
+
+	first->async_tx.flags = flags; /* client is in control of this ack */
+	first->async_tx.cookie = -EBUSY;
+
+	/* make the cyclic link */
+	new->desc.ddadr = first->async_tx.phys;
+	chan->cyclic_first = first;
+
 	return &first->async_tx;
 
 fail:
@@ -581,10 +692,7 @@ static int mmp_pdma_control(struct dma_chan *dchan, enum dma_ctrl_cmd cmd,
 	switch (cmd) {
 	case DMA_TERMINATE_ALL:
 		disable_chan(chan->phy);
-		if (chan->phy) {
-			chan->phy->vchan = NULL;
-			chan->phy = NULL;
-		}
+		mmp_pdma_free_phy(chan);
 		spin_lock_irqsave(&chan->desc_lock, flags);
 		mmp_pdma_free_desc_list(chan, &chan->chain_pending);
 		mmp_pdma_free_desc_list(chan, &chan->chain_running);
@@ -619,8 +727,13 @@ static int mmp_pdma_control(struct dma_chan *dchan, enum dma_ctrl_cmd cmd,
 			chan->dcmd |= DCMD_BURST32;
 
 		chan->dir = cfg->direction;
-		chan->drcmr = cfg->slave_id;
 		chan->dev_addr = addr;
+		/* FIXME: drivers should be ported over to use the filter
+		 * function. Once that's done, the following two lines can
+		 * be removed.
+		 */
+		if (cfg->slave_id)
+			chan->drcmr = cfg->slave_id;
 		break;
 	default:
 		return -ENOSYS;
@@ -632,15 +745,7 @@ static int mmp_pdma_control(struct dma_chan *dchan, enum dma_ctrl_cmd cmd,
 static enum dma_status mmp_pdma_tx_status(struct dma_chan *dchan,
 			dma_cookie_t cookie, struct dma_tx_state *txstate)
 {
-	struct mmp_pdma_chan *chan = to_mmp_pdma_chan(dchan);
-	enum dma_status ret;
-	unsigned long flags;
-
-	spin_lock_irqsave(&chan->desc_lock, flags);
-	ret = dma_cookie_status(dchan, cookie, txstate);
-	spin_unlock_irqrestore(&chan->desc_lock, flags);
-
-	return ret;
+	return dma_cookie_status(dchan, cookie, txstate);
 }
 
 /**
@@ -669,29 +774,51 @@ static void dma_do_tasklet(unsigned long data)
 	LIST_HEAD(chain_cleanup);
 	unsigned long flags;
 
-	/* submit pending list; callback for each desc; free desc */
+	if (chan->cyclic_first) {
+		dma_async_tx_callback cb = NULL;
+		void *cb_data = NULL;
 
-	spin_lock_irqsave(&chan->desc_lock, flags);
+		spin_lock_irqsave(&chan->desc_lock, flags);
+		desc = chan->cyclic_first;
+		cb = desc->async_tx.callback;
+		cb_data = desc->async_tx.callback_param;
+		spin_unlock_irqrestore(&chan->desc_lock, flags);
+
+		if (cb)
+			cb(cb_data);
 
-	/* update the cookie if we have some descriptors to cleanup */
-	if (!list_empty(&chan->chain_running)) {
-		dma_cookie_t cookie;
+		return;
+	}
 
-		desc = to_mmp_pdma_desc(chan->chain_running.prev);
-		cookie = desc->async_tx.cookie;
-		dma_cookie_complete(&desc->async_tx);
+	/* submit pending list; callback for each desc; free desc */
+	spin_lock_irqsave(&chan->desc_lock, flags);
 
-		dev_dbg(chan->dev, "completed_cookie=%d\n", cookie);
+	list_for_each_entry_safe(desc, _desc, &chan->chain_running, node) {
+		/*
+		 * move the descriptors to a temporary list so we can drop
+		 * the lock during the entire cleanup operation
+		 */
+		list_del(&desc->node);
+		list_add(&desc->node, &chain_cleanup);
+
+		/*
+		 * Look for the first list entry which has the ENDIRQEN flag
+		 * set. That is the descriptor we got an interrupt for, so
+		 * complete that transaction and its cookie.
+		 */
+		if (desc->desc.dcmd & DCMD_ENDIRQEN) {
+			dma_cookie_t cookie = desc->async_tx.cookie;
+			dma_cookie_complete(&desc->async_tx);
+			dev_dbg(chan->dev, "completed_cookie=%d\n", cookie);
+			break;
+		}
 	}
 
 	/*
-	 * move the descriptors to a temporary list so we can drop the lock
-	 * during the entire cleanup operation
+	 * The hardware is idle and ready for more when the
+	 * chain_running list is empty.
 	 */
-	list_splice_tail_init(&chan->chain_running, &chain_cleanup);
-
-	/* the hardware is now idle and ready for more */
-	chan->idle = true;
+	chan->idle = list_empty(&chan->chain_running);
 
 	/* Start any pending transactions automatically */
 	start_pending_queue(chan);
@@ -763,6 +890,39 @@ static struct of_device_id mmp_pdma_dt_ids[] = {
 };
 MODULE_DEVICE_TABLE(of, mmp_pdma_dt_ids);
 
+static struct dma_chan *mmp_pdma_dma_xlate(struct of_phandle_args *dma_spec,
+					   struct of_dma *ofdma)
+{
+	struct mmp_pdma_device *d = ofdma->of_dma_data;
+	struct dma_chan *chan, *candidate;
+
+retry:
+	candidate = NULL;
+
+	/* walk the list of channels registered with the current instance and
+	 * find one that is currently unused */
+	list_for_each_entry(chan, &d->device.channels, device_node)
+		if (chan->client_count == 0) {
+			candidate = chan;
+			break;
+		}
+
+	if (!candidate)
+		return NULL;
+
+	/* dma_get_slave_channel will return NULL if we lost a race between
+	 * the lookup and the reservation */
+	chan = dma_get_slave_channel(candidate);
+
+	if (chan) {
+		struct mmp_pdma_chan *c = to_mmp_pdma_chan(chan);
+		c->drcmr = dma_spec->args[0];
+		return chan;
+	}
+
+	goto retry;
+}
+
 static int mmp_pdma_probe(struct platform_device *op)
 {
 	struct mmp_pdma_device *pdev;
@@ -777,10 +937,9 @@ static int mmp_pdma_probe(struct platform_device *op)
 		return -ENOMEM;
 	pdev->dev = &op->dev;
 
-	iores = platform_get_resource(op, IORESOURCE_MEM, 0);
-	if (!iores)
-		return -EINVAL;
+	spin_lock_init(&pdev->phy_lock);
 
+	iores = platform_get_resource(op, IORESOURCE_MEM, 0);
 	pdev->base = devm_ioremap_resource(pdev->dev, iores);
 	if (IS_ERR(pdev->base))
 		return PTR_ERR(pdev->base);
@@ -825,13 +984,15 @@ static int mmp_pdma_probe(struct platform_device *op)
 
 	dma_cap_set(DMA_SLAVE, pdev->device.cap_mask);
 	dma_cap_set(DMA_MEMCPY, pdev->device.cap_mask);
-	dma_cap_set(DMA_SLAVE, pdev->device.cap_mask);
+	dma_cap_set(DMA_CYCLIC, pdev->device.cap_mask);
+	dma_cap_set(DMA_PRIVATE, pdev->device.cap_mask);
 	pdev->device.dev = &op->dev;
 	pdev->device.device_alloc_chan_resources = mmp_pdma_alloc_chan_resources;
 	pdev->device.device_free_chan_resources = mmp_pdma_free_chan_resources;
 	pdev->device.device_tx_status = mmp_pdma_tx_status;
 	pdev->device.device_prep_dma_memcpy = mmp_pdma_prep_memcpy;
 	pdev->device.device_prep_slave_sg = mmp_pdma_prep_slave_sg;
+	pdev->device.device_prep_dma_cyclic = mmp_pdma_prep_dma_cyclic;
 	pdev->device.device_issue_pending = mmp_pdma_issue_pending;
 	pdev->device.device_control = mmp_pdma_control;
 	pdev->device.copy_align = PDMA_ALIGNMENT;
@@ -847,7 +1008,17 @@ static int mmp_pdma_probe(struct platform_device *op)
 		return ret;
 	}
 
-	dev_info(pdev->device.dev, "initialized\n");
+	if (op->dev.of_node) {
+		/* Device-tree DMA controller registration */
+		ret = of_dma_controller_register(op->dev.of_node,
+						 mmp_pdma_dma_xlate, pdev);
+		if (ret < 0) {
+			dev_err(&op->dev, "of_dma_controller_register failed\n");
+			return ret;
+		}
+	}
+
+	dev_info(pdev->device.dev, "initialized %d channels\n", dma_channels);
 	return 0;
 }
 
@@ -867,6 +1038,19 @@ static struct platform_driver mmp_pdma_driver = {
 	.remove		= mmp_pdma_remove,
 };
 
+bool mmp_pdma_filter_fn(struct dma_chan *chan, void *param)
+{
+	struct mmp_pdma_chan *c = to_mmp_pdma_chan(chan);
+
+	if (chan->device->dev->driver != &mmp_pdma_driver.driver)
+		return false;
+
+	c->drcmr = *(unsigned int *) param;
+
+	return true;
+}
+EXPORT_SYMBOL_GPL(mmp_pdma_filter_fn);
+
 module_platform_driver(mmp_pdma_driver);
 
 MODULE_DESCRIPTION("MARVELL MMP Periphera DMA Driver");
diff --git a/drivers/dma/mmp_tdma.c b/drivers/dma/mmp_tdma.c
index 9b9366537d73..38cb517fb2eb 100644
--- a/drivers/dma/mmp_tdma.c
+++ b/drivers/dma/mmp_tdma.c
@@ -460,7 +460,8 @@ static enum dma_status mmp_tdma_tx_status(struct dma_chan *chan,
 {
 	struct mmp_tdma_chan *tdmac = to_mmp_tdma_chan(chan);
 
-	dma_set_residue(txstate, tdmac->buf_len - tdmac->pos);
+	dma_set_tx_state(txstate, chan->completed_cookie, chan->cookie,
+			 tdmac->buf_len - tdmac->pos);
 
 	return tdmac->status;
 }
@@ -549,9 +550,6 @@ static int mmp_tdma_probe(struct platform_device *pdev)
 	}
 
 	iores = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!iores)
-		return -EINVAL;
-
 	tdev->base = devm_ioremap_resource(&pdev->dev, iores);
 	if (IS_ERR(tdev->base))
 		return PTR_ERR(tdev->base);
diff --git a/drivers/dma/mpc512x_dma.c b/drivers/dma/mpc512x_dma.c
index 2d956732aa3d..2fe435377333 100644
--- a/drivers/dma/mpc512x_dma.c
+++ b/drivers/dma/mpc512x_dma.c
@@ -556,15 +556,7 @@ static enum dma_status
 mpc_dma_tx_status(struct dma_chan *chan, dma_cookie_t cookie,
 	       struct dma_tx_state *txstate)
 {
-	struct mpc_dma_chan *mchan = dma_chan_to_mpc_dma_chan(chan);
-	enum dma_status ret;
-	unsigned long flags;
-
-	spin_lock_irqsave(&mchan->lock, flags);
-	ret = dma_cookie_status(chan, cookie, txstate);
-	spin_unlock_irqrestore(&mchan->lock, flags);
-
-	return ret;
+	return dma_cookie_status(chan, cookie, txstate);
 }
 
 /* Prepare descriptor for memory to memory copy */
diff --git a/drivers/dma/mv_xor.c b/drivers/dma/mv_xor.c
index 200f1a3c9a44..536dcb8ba5fd 100644
--- a/drivers/dma/mv_xor.c
+++ b/drivers/dma/mv_xor.c
@@ -64,7 +64,7 @@ static u32 mv_desc_get_src_addr(struct mv_xor_desc_slot *desc,
 				int src_idx)
 {
 	struct mv_xor_desc *hw_desc = desc->hw_desc;
-	return hw_desc->phy_src_addr[src_idx];
+	return hw_desc->phy_src_addr[mv_phy_src_idx(src_idx)];
 }
 
 
@@ -107,32 +107,32 @@ static void mv_desc_set_src_addr(struct mv_xor_desc_slot *desc,
 				 int index, dma_addr_t addr)
 {
 	struct mv_xor_desc *hw_desc = desc->hw_desc;
-	hw_desc->phy_src_addr[index] = addr;
+	hw_desc->phy_src_addr[mv_phy_src_idx(index)] = addr;
 	if (desc->type == DMA_XOR)
 		hw_desc->desc_command |= (1 << index);
 }
 
 static u32 mv_chan_get_current_desc(struct mv_xor_chan *chan)
 {
-	return __raw_readl(XOR_CURR_DESC(chan));
+	return readl_relaxed(XOR_CURR_DESC(chan));
 }
 
 static void mv_chan_set_next_descriptor(struct mv_xor_chan *chan,
 					u32 next_desc_addr)
 {
-	__raw_writel(next_desc_addr, XOR_NEXT_DESC(chan));
+	writel_relaxed(next_desc_addr, XOR_NEXT_DESC(chan));
 }
 
 static void mv_chan_unmask_interrupts(struct mv_xor_chan *chan)
 {
-	u32 val = __raw_readl(XOR_INTR_MASK(chan));
+	u32 val = readl_relaxed(XOR_INTR_MASK(chan));
 	val |= XOR_INTR_MASK_VALUE << (chan->idx * 16);
-	__raw_writel(val, XOR_INTR_MASK(chan));
+	writel_relaxed(val, XOR_INTR_MASK(chan));
 }
 
 static u32 mv_chan_get_intr_cause(struct mv_xor_chan *chan)
 {
-	u32 intr_cause = __raw_readl(XOR_INTR_CAUSE(chan));
+	u32 intr_cause = readl_relaxed(XOR_INTR_CAUSE(chan));
 	intr_cause = (intr_cause >> (chan->idx * 16)) & 0xFFFF;
 	return intr_cause;
 }
@@ -149,13 +149,13 @@ static void mv_xor_device_clear_eoc_cause(struct mv_xor_chan *chan)
 {
 	u32 val = ~(1 << (chan->idx * 16));
 	dev_dbg(mv_chan_to_devp(chan), "%s, val 0x%08x\n", __func__, val);
-	__raw_writel(val, XOR_INTR_CAUSE(chan));
+	writel_relaxed(val, XOR_INTR_CAUSE(chan));
 }
 
 static void mv_xor_device_clear_err_status(struct mv_xor_chan *chan)
 {
 	u32 val = 0xFFFF0000 >> (chan->idx * 16);
-	__raw_writel(val, XOR_INTR_CAUSE(chan));
+	writel_relaxed(val, XOR_INTR_CAUSE(chan));
 }
 
 static int mv_can_chain(struct mv_xor_desc_slot *desc)
@@ -173,7 +173,7 @@ static void mv_set_mode(struct mv_xor_chan *chan,
 			       enum dma_transaction_type type)
 {
 	u32 op_mode;
-	u32 config = __raw_readl(XOR_CONFIG(chan));
+	u32 config = readl_relaxed(XOR_CONFIG(chan));
 
 	switch (type) {
 	case DMA_XOR:
@@ -192,7 +192,14 @@ static void mv_set_mode(struct mv_xor_chan *chan,
 
 	config &= ~0x7;
 	config |= op_mode;
-	__raw_writel(config, XOR_CONFIG(chan));
+
+#if defined(__BIG_ENDIAN)
+	config |= XOR_DESCRIPTOR_SWAP;
+#else
+	config &= ~XOR_DESCRIPTOR_SWAP;
+#endif
+
+	writel_relaxed(config, XOR_CONFIG(chan));
 	chan->current_type = type;
 }
 
@@ -201,14 +208,14 @@ static void mv_chan_activate(struct mv_xor_chan *chan)
 	u32 activation;
 
 	dev_dbg(mv_chan_to_devp(chan), " activate chan.\n");
-	activation = __raw_readl(XOR_ACTIVATION(chan));
+	activation = readl_relaxed(XOR_ACTIVATION(chan));
 	activation |= 0x1;
-	__raw_writel(activation, XOR_ACTIVATION(chan));
+	writel_relaxed(activation, XOR_ACTIVATION(chan));
 }
 
 static char mv_chan_is_busy(struct mv_xor_chan *chan)
 {
-	u32 state = __raw_readl(XOR_ACTIVATION(chan));
+	u32 state = readl_relaxed(XOR_ACTIVATION(chan));
 
 	state = (state >> 4) & 0x3;
 
@@ -647,7 +654,7 @@ mv_xor_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src,
 
 	dev_dbg(mv_chan_to_devp(mv_chan),
 		"%s sw_desc %p async_tx %p\n",
-		__func__, sw_desc, sw_desc ? &sw_desc->async_tx : 0);
+		__func__, sw_desc, sw_desc ? &sw_desc->async_tx : NULL);
 
 	return sw_desc ? &sw_desc->async_tx : NULL;
 }
@@ -755,22 +762,22 @@ static void mv_dump_xor_regs(struct mv_xor_chan *chan)
 {
 	u32 val;
 
-	val = __raw_readl(XOR_CONFIG(chan));
+	val = readl_relaxed(XOR_CONFIG(chan));
 	dev_err(mv_chan_to_devp(chan), "config       0x%08x\n", val);
 
-	val = __raw_readl(XOR_ACTIVATION(chan));
+	val = readl_relaxed(XOR_ACTIVATION(chan));
 	dev_err(mv_chan_to_devp(chan), "activation   0x%08x\n", val);
 
-	val = __raw_readl(XOR_INTR_CAUSE(chan));
+	val = readl_relaxed(XOR_INTR_CAUSE(chan));
 	dev_err(mv_chan_to_devp(chan), "intr cause   0x%08x\n", val);
 
-	val = __raw_readl(XOR_INTR_MASK(chan));
+	val = readl_relaxed(XOR_INTR_MASK(chan));
 	dev_err(mv_chan_to_devp(chan), "intr mask    0x%08x\n", val);
 
-	val = __raw_readl(XOR_ERROR_CAUSE(chan));
+	val = readl_relaxed(XOR_ERROR_CAUSE(chan));
 	dev_err(mv_chan_to_devp(chan), "error cause  0x%08x\n", val);
 
-	val = __raw_readl(XOR_ERROR_ADDR(chan));
+	val = readl_relaxed(XOR_ERROR_ADDR(chan));
 	dev_err(mv_chan_to_devp(chan), "error addr   0x%08x\n", val);
 }
 
@@ -1029,10 +1036,8 @@ mv_xor_channel_add(struct mv_xor_device *xordev,
 	struct dma_device *dma_dev;
 
 	mv_chan = devm_kzalloc(&pdev->dev, sizeof(*mv_chan), GFP_KERNEL);
-	if (!mv_chan) {
-		ret = -ENOMEM;
-		goto err_free_dma;
-	}
+	if (!mv_chan)
+		return ERR_PTR(-ENOMEM);
 
 	mv_chan->idx = idx;
 	mv_chan->irq = irq;
@@ -1166,7 +1171,7 @@ static int mv_xor_probe(struct platform_device *pdev)
 {
 	const struct mbus_dram_target_info *dram;
 	struct mv_xor_device *xordev;
-	struct mv_xor_platform_data *pdata = pdev->dev.platform_data;
+	struct mv_xor_platform_data *pdata = dev_get_platdata(&pdev->dev);
 	struct resource *res;
 	int i, ret;
 
diff --git a/drivers/dma/mv_xor.h b/drivers/dma/mv_xor.h
index c619359cb7fe..06b067f24c9b 100644
--- a/drivers/dma/mv_xor.h
+++ b/drivers/dma/mv_xor.h
@@ -29,8 +29,10 @@
 #define MV_XOR_THRESHOLD		1
 #define MV_XOR_MAX_CHANNELS             2
 
+/* Values for the XOR_CONFIG register */
 #define XOR_OPERATION_MODE_XOR		0
 #define XOR_OPERATION_MODE_MEMCPY	2
+#define XOR_DESCRIPTOR_SWAP		BIT(14)
 
 #define XOR_CURR_DESC(chan)	(chan->mmr_base + 0x210 + (chan->idx * 4))
 #define XOR_NEXT_DESC(chan)	(chan->mmr_base + 0x200 + (chan->idx * 4))
@@ -143,7 +145,16 @@ struct mv_xor_desc_slot {
 #endif
 };
 
-/* This structure describes XOR descriptor size 64bytes	*/
+/*
+ * This structure describes XOR descriptor size 64bytes. The
+ * mv_phy_src_idx() macro must be used when indexing the values of the
+ * phy_src_addr[] array. This is due to the fact that the 'descriptor
+ * swap' feature, used on big endian systems, swaps descriptors data
+ * within blocks of 8 bytes. So two consecutive values of the
+ * phy_src_addr[] array are actually swapped in big-endian, which
+ * explains the different mv_phy_src_idx() implementation.
+ */
+#if defined(__LITTLE_ENDIAN)
 struct mv_xor_desc {
 	u32 status;		/* descriptor execution status */
 	u32 crc32_result;	/* result of CRC-32 calculation */
@@ -155,6 +166,21 @@ struct mv_xor_desc {
 	u32 reserved0;
 	u32 reserved1;
 };
+#define mv_phy_src_idx(src_idx) (src_idx)
+#else
+struct mv_xor_desc {
+	u32 crc32_result;	/* result of CRC-32 calculation */
+	u32 status;		/* descriptor execution status */
+	u32 phy_next_desc;	/* next descriptor address pointer */
+	u32 desc_command;	/* type of operation to be carried out */
+	u32 phy_dest_addr;	/* destination block address */
+	u32 byte_count;		/* size of src/dst blocks in bytes */
+	u32 phy_src_addr[8];	/* source block addresses */
+	u32 reserved1;
+	u32 reserved0;
+};
+#define mv_phy_src_idx(src_idx) (src_idx ^ 1)
+#endif
 
 #define to_mv_sw_desc(addr_hw_desc)		\
 	container_of(addr_hw_desc, struct mv_xor_desc_slot, hw_desc)
diff --git a/drivers/dma/mxs-dma.c b/drivers/dma/mxs-dma.c
index 719593002ab7..ccd13df841db 100644
--- a/drivers/dma/mxs-dma.c
+++ b/drivers/dma/mxs-dma.c
@@ -23,7 +23,6 @@
 #include <linux/dmaengine.h>
 #include <linux/delay.h>
 #include <linux/module.h>
-#include <linux/fsl/mxs-dma.h>
 #include <linux/stmp_device.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
@@ -197,24 +196,6 @@ static struct mxs_dma_chan *to_mxs_dma_chan(struct dma_chan *chan)
 	return container_of(chan, struct mxs_dma_chan, chan);
 }
 
-int mxs_dma_is_apbh(struct dma_chan *chan)
-{
-	struct mxs_dma_chan *mxs_chan = to_mxs_dma_chan(chan);
-	struct mxs_dma_engine *mxs_dma = mxs_chan->mxs_dma;
-
-	return dma_is_apbh(mxs_dma);
-}
-EXPORT_SYMBOL_GPL(mxs_dma_is_apbh);
-
-int mxs_dma_is_apbx(struct dma_chan *chan)
-{
-	struct mxs_dma_chan *mxs_chan = to_mxs_dma_chan(chan);
-	struct mxs_dma_engine *mxs_dma = mxs_chan->mxs_dma;
-
-	return !dma_is_apbh(mxs_dma);
-}
-EXPORT_SYMBOL_GPL(mxs_dma_is_apbx);
-
 static void mxs_dma_reset_chan(struct mxs_dma_chan *mxs_chan)
 {
 	struct mxs_dma_engine *mxs_dma = mxs_chan->mxs_dma;
@@ -349,13 +330,9 @@ static irqreturn_t mxs_dma_int_handler(int irq, void *dev_id)
 static int mxs_dma_alloc_chan_resources(struct dma_chan *chan)
 {
 	struct mxs_dma_chan *mxs_chan = to_mxs_dma_chan(chan);
-	struct mxs_dma_data *data = chan->private;
 	struct mxs_dma_engine *mxs_dma = mxs_chan->mxs_dma;
 	int ret;
 
-	if (data)
-		mxs_chan->chan_irq = data->chan_irq;
-
 	mxs_chan->ccw = dma_alloc_coherent(mxs_dma->dma_device.dev,
 				CCW_BLOCK_SIZE, &mxs_chan->ccw_phys,
 				GFP_KERNEL);
@@ -622,10 +599,8 @@ static enum dma_status mxs_dma_tx_status(struct dma_chan *chan,
 			dma_cookie_t cookie, struct dma_tx_state *txstate)
 {
 	struct mxs_dma_chan *mxs_chan = to_mxs_dma_chan(chan);
-	dma_cookie_t last_used;
 
-	last_used = chan->cookie;
-	dma_set_tx_state(txstate, chan->completed_cookie, last_used, 0);
+	dma_set_tx_state(txstate, chan->completed_cookie, chan->cookie, 0);
 
 	return mxs_chan->status;
 }
diff --git a/drivers/dma/of-dma.c b/drivers/dma/of-dma.c
index 75334bdd2c56..0b88dd3d05f4 100644
--- a/drivers/dma/of-dma.c
+++ b/drivers/dma/of-dma.c
@@ -160,7 +160,8 @@ struct dma_chan *of_dma_request_slave_channel(struct device_node *np,
 
 	count = of_property_count_strings(np, "dma-names");
 	if (count < 0) {
-		pr_err("%s: dma-names property missing or empty\n", __func__);
+		pr_err("%s: dma-names property of node '%s' missing or empty\n",
+			__func__, np->full_name);
 		return NULL;
 	}
 
diff --git a/drivers/dma/pch_dma.c b/drivers/dma/pch_dma.c
index 0bbdea5059f3..61fdc54a3c88 100644
--- a/drivers/dma/pch_dma.c
+++ b/drivers/dma/pch_dma.c
@@ -564,14 +564,7 @@ static void pd_free_chan_resources(struct dma_chan *chan)
 static enum dma_status pd_tx_status(struct dma_chan *chan, dma_cookie_t cookie,
 				    struct dma_tx_state *txstate)
 {
-	struct pch_dma_chan *pd_chan = to_pd_chan(chan);
-	enum dma_status ret;
-
-	spin_lock_irq(&pd_chan->lock);
-	ret = dma_cookie_status(chan, cookie, txstate);
-	spin_unlock_irq(&pd_chan->lock);
-
-	return ret;
+	return dma_cookie_status(chan, cookie, txstate);
 }
 
 static void pd_issue_pending(struct dma_chan *chan)
@@ -1036,3 +1029,4 @@ MODULE_DESCRIPTION("Intel EG20T PCH / LAPIS Semicon ML7213/ML7223/ML7831 IOH "
 		   "DMA controller driver");
 MODULE_AUTHOR("Yong Wang <yong.y.wang@intel.com>");
 MODULE_LICENSE("GPL v2");
+MODULE_DEVICE_TABLE(pci, pch_dma_id_table);
diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c
index fa645d825009..a562d24d20bf 100644
--- a/drivers/dma/pl330.c
+++ b/drivers/dma/pl330.c
@@ -545,6 +545,8 @@ struct dma_pl330_chan {
 
 	/* List of to be xfered descriptors */
 	struct list_head work_list;
+	/* List of completed descriptors */
+	struct list_head completed_list;
 
 	/* Pointer to the DMAC that manages this channel,
 	 * NULL if the channel is available to be acquired.
@@ -2198,66 +2200,6 @@ to_desc(struct dma_async_tx_descriptor *tx)
 	return container_of(tx, struct dma_pl330_desc, txd);
 }
 
-static inline void free_desc_list(struct list_head *list)
-{
-	struct dma_pl330_dmac *pdmac;
-	struct dma_pl330_desc *desc;
-	struct dma_pl330_chan *pch = NULL;
-	unsigned long flags;
-
-	/* Finish off the work list */
-	list_for_each_entry(desc, list, node) {
-		dma_async_tx_callback callback;
-		void *param;
-
-		/* All desc in a list belong to same channel */
-		pch = desc->pchan;
-		callback = desc->txd.callback;
-		param = desc->txd.callback_param;
-
-		if (callback)
-			callback(param);
-
-		desc->pchan = NULL;
-	}
-
-	/* pch will be unset if list was empty */
-	if (!pch)
-		return;
-
-	pdmac = pch->dmac;
-
-	spin_lock_irqsave(&pdmac->pool_lock, flags);
-	list_splice_tail_init(list, &pdmac->desc_pool);
-	spin_unlock_irqrestore(&pdmac->pool_lock, flags);
-}
-
-static inline void handle_cyclic_desc_list(struct list_head *list)
-{
-	struct dma_pl330_desc *desc;
-	struct dma_pl330_chan *pch = NULL;
-	unsigned long flags;
-
-	list_for_each_entry(desc, list, node) {
-		dma_async_tx_callback callback;
-
-		/* Change status to reload it */
-		desc->status = PREP;
-		pch = desc->pchan;
-		callback = desc->txd.callback;
-		if (callback)
-			callback(desc->txd.callback_param);
-	}
-
-	/* pch will be unset if list was empty */
-	if (!pch)
-		return;
-
-	spin_lock_irqsave(&pch->lock, flags);
-	list_splice_tail_init(list, &pch->work_list);
-	spin_unlock_irqrestore(&pch->lock, flags);
-}
-
 static inline void fill_queue(struct dma_pl330_chan *pch)
 {
 	struct dma_pl330_desc *desc;
@@ -2291,7 +2233,6 @@ static void pl330_tasklet(unsigned long data)
 	struct dma_pl330_chan *pch = (struct dma_pl330_chan *)data;
 	struct dma_pl330_desc *desc, *_dt;
 	unsigned long flags;
-	LIST_HEAD(list);
 
 	spin_lock_irqsave(&pch->lock, flags);
 
@@ -2300,7 +2241,7 @@ static void pl330_tasklet(unsigned long data)
 		if (desc->status == DONE) {
 			if (!pch->cyclic)
 				dma_cookie_complete(&desc->txd);
-			list_move_tail(&desc->node, &list);
+			list_move_tail(&desc->node, &pch->completed_list);
 		}
 
 	/* Try to submit a req imm. next to the last completed cookie */
@@ -2309,12 +2250,31 @@ static void pl330_tasklet(unsigned long data)
 	/* Make sure the PL330 Channel thread is active */
 	pl330_chan_ctrl(pch->pl330_chid, PL330_OP_START);
 
-	spin_unlock_irqrestore(&pch->lock, flags);
+	while (!list_empty(&pch->completed_list)) {
+		dma_async_tx_callback callback;
+		void *callback_param;
 
-	if (pch->cyclic)
-		handle_cyclic_desc_list(&list);
-	else
-		free_desc_list(&list);
+		desc = list_first_entry(&pch->completed_list,
+					struct dma_pl330_desc, node);
+
+		callback = desc->txd.callback;
+		callback_param = desc->txd.callback_param;
+
+		if (pch->cyclic) {
+			desc->status = PREP;
+			list_move_tail(&desc->node, &pch->work_list);
+		} else {
+			desc->status = FREE;
+			list_move_tail(&desc->node, &pch->dmac->desc_pool);
+		}
+
+		if (callback) {
+			spin_unlock_irqrestore(&pch->lock, flags);
+			callback(callback_param);
+			spin_lock_irqsave(&pch->lock, flags);
+		}
+	}
+	spin_unlock_irqrestore(&pch->lock, flags);
 }
 
 static void dma_pl330_rqcb(void *token, enum pl330_op_err err)
@@ -2409,7 +2369,7 @@ static int pl330_alloc_chan_resources(struct dma_chan *chan)
 static int pl330_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd, unsigned long arg)
 {
 	struct dma_pl330_chan *pch = to_pchan(chan);
-	struct dma_pl330_desc *desc, *_dt;
+	struct dma_pl330_desc *desc;
 	unsigned long flags;
 	struct dma_pl330_dmac *pdmac = pch->dmac;
 	struct dma_slave_config *slave_config;
@@ -2423,12 +2383,18 @@ static int pl330_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd, unsigned
 		pl330_chan_ctrl(pch->pl330_chid, PL330_OP_FLUSH);
 
 		/* Mark all desc done */
-		list_for_each_entry_safe(desc, _dt, &pch->work_list , node) {
-			desc->status = DONE;
-			list_move_tail(&desc->node, &list);
+		list_for_each_entry(desc, &pch->work_list , node) {
+			desc->status = FREE;
+			dma_cookie_complete(&desc->txd);
 		}
 
-		list_splice_tail_init(&list, &pdmac->desc_pool);
+		list_for_each_entry(desc, &pch->completed_list , node) {
+			desc->status = FREE;
+			dma_cookie_complete(&desc->txd);
+		}
+
+		list_splice_tail_init(&pch->work_list, &pdmac->desc_pool);
+		list_splice_tail_init(&pch->completed_list, &pdmac->desc_pool);
 		spin_unlock_irqrestore(&pch->lock, flags);
 		break;
 	case DMA_SLAVE_CONFIG:
@@ -2814,6 +2780,28 @@ pl330_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dst,
 	return &desc->txd;
 }
 
+static void __pl330_giveback_desc(struct dma_pl330_dmac *pdmac,
+				  struct dma_pl330_desc *first)
+{
+	unsigned long flags;
+	struct dma_pl330_desc *desc;
+
+	if (!first)
+		return;
+
+	spin_lock_irqsave(&pdmac->pool_lock, flags);
+
+	while (!list_empty(&first->node)) {
+		desc = list_entry(first->node.next,
+				struct dma_pl330_desc, node);
+		list_move_tail(&desc->node, &pdmac->desc_pool);
+	}
+
+	list_move_tail(&first->node, &pdmac->desc_pool);
+
+	spin_unlock_irqrestore(&pdmac->pool_lock, flags);
+}
+
 static struct dma_async_tx_descriptor *
 pl330_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 		unsigned int sg_len, enum dma_transfer_direction direction,
@@ -2822,7 +2810,6 @@ pl330_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 	struct dma_pl330_desc *first, *desc = NULL;
 	struct dma_pl330_chan *pch = to_pchan(chan);
 	struct scatterlist *sg;
-	unsigned long flags;
 	int i;
 	dma_addr_t addr;
 
@@ -2842,20 +2829,7 @@ pl330_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 			dev_err(pch->dmac->pif.dev,
 				"%s:%d Unable to fetch desc\n",
 				__func__, __LINE__);
-			if (!first)
-				return NULL;
-
-			spin_lock_irqsave(&pdmac->pool_lock, flags);
-
-			while (!list_empty(&first->node)) {
-				desc = list_entry(first->node.next,
-						struct dma_pl330_desc, node);
-				list_move_tail(&desc->node, &pdmac->desc_pool);
-			}
-
-			list_move_tail(&first->node, &pdmac->desc_pool);
-
-			spin_unlock_irqrestore(&pdmac->pool_lock, flags);
+			__pl330_giveback_desc(pdmac, first);
 
 			return NULL;
 		}
@@ -2896,6 +2870,25 @@ static irqreturn_t pl330_irq_handler(int irq, void *data)
 		return IRQ_NONE;
 }
 
+#define PL330_DMA_BUSWIDTHS \
+	BIT(DMA_SLAVE_BUSWIDTH_UNDEFINED) | \
+	BIT(DMA_SLAVE_BUSWIDTH_1_BYTE) | \
+	BIT(DMA_SLAVE_BUSWIDTH_2_BYTES) | \
+	BIT(DMA_SLAVE_BUSWIDTH_4_BYTES) | \
+	BIT(DMA_SLAVE_BUSWIDTH_8_BYTES)
+
+static int pl330_dma_device_slave_caps(struct dma_chan *dchan,
+	struct dma_slave_caps *caps)
+{
+	caps->src_addr_widths = PL330_DMA_BUSWIDTHS;
+	caps->dstn_addr_widths = PL330_DMA_BUSWIDTHS;
+	caps->directions = BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV);
+	caps->cmd_pause = false;
+	caps->cmd_terminate = true;
+
+	return 0;
+}
+
 static int
 pl330_probe(struct amba_device *adev, const struct amba_id *id)
 {
@@ -2908,7 +2901,7 @@ pl330_probe(struct amba_device *adev, const struct amba_id *id)
 	int i, ret, irq;
 	int num_chan;
 
-	pdat = adev->dev.platform_data;
+	pdat = dev_get_platdata(&adev->dev);
 
 	/* Allocate a new DMAC and its Channels */
 	pdmac = devm_kzalloc(&adev->dev, sizeof(*pdmac), GFP_KERNEL);
@@ -2971,6 +2964,7 @@ pl330_probe(struct amba_device *adev, const struct amba_id *id)
 			pch->chan.private = adev->dev.of_node;
 
 		INIT_LIST_HEAD(&pch->work_list);
+		INIT_LIST_HEAD(&pch->completed_list);
 		spin_lock_init(&pch->lock);
 		pch->pl330_chid = NULL;
 		pch->chan.device = pd;
@@ -3000,6 +2994,7 @@ pl330_probe(struct amba_device *adev, const struct amba_id *id)
 	pd->device_prep_slave_sg = pl330_prep_slave_sg;
 	pd->device_control = pl330_control;
 	pd->device_issue_pending = pl330_issue_pending;
+	pd->device_slave_caps = pl330_dma_device_slave_caps;
 
 	ret = dma_async_device_register(pd);
 	if (ret) {
@@ -3015,6 +3010,14 @@ pl330_probe(struct amba_device *adev, const struct amba_id *id)
 			"unable to register DMA to the generic DT DMA helpers\n");
 		}
 	}
+	/*
+	 * This is the limit for transfers with a buswidth of 1, larger
+	 * buswidths will have larger limits.
+	 */
+	ret = dma_set_max_seg_size(&adev->dev, 1900800);
+	if (ret)
+		dev_err(&adev->dev, "unable to set the seg size\n");
+
 
 	dev_info(&adev->dev,
 		"Loaded driver for PL330 DMAC-%d\n", adev->periphid);
diff --git a/drivers/dma/sh/Kconfig b/drivers/dma/sh/Kconfig
index 5c1dee20c13e..dadd9e010c0b 100644
--- a/drivers/dma/sh/Kconfig
+++ b/drivers/dma/sh/Kconfig
@@ -22,3 +22,13 @@ config SUDMAC
 	depends on SH_DMAE_BASE
 	help
 	  Enable support for the Renesas SUDMAC controllers.
+
+config RCAR_HPB_DMAE
+	tristate "Renesas R-Car HPB DMAC support"
+	depends on SH_DMAE_BASE
+	help
+	  Enable support for the Renesas R-Car series DMA controllers.
+
+config SHDMA_R8A73A4
+	def_bool y
+	depends on ARCH_R8A73A4 && SH_DMAE != n
diff --git a/drivers/dma/sh/Makefile b/drivers/dma/sh/Makefile
index c962138dde96..e856af23b789 100644
--- a/drivers/dma/sh/Makefile
+++ b/drivers/dma/sh/Makefile
@@ -1,3 +1,9 @@
 obj-$(CONFIG_SH_DMAE_BASE) += shdma-base.o shdma-of.o
 obj-$(CONFIG_SH_DMAE) += shdma.o
+shdma-y := shdmac.o
+ifeq ($(CONFIG_OF),y)
+shdma-$(CONFIG_SHDMA_R8A73A4) += shdma-r8a73a4.o
+endif
+shdma-objs := $(shdma-y)
 obj-$(CONFIG_SUDMAC) += sudmac.o
+obj-$(CONFIG_RCAR_HPB_DMAE) += rcar-hpbdma.o
diff --git a/drivers/dma/sh/rcar-hpbdma.c b/drivers/dma/sh/rcar-hpbdma.c
new file mode 100644
index 000000000000..ebad84591a6e
--- /dev/null
+++ b/drivers/dma/sh/rcar-hpbdma.c
@@ -0,0 +1,656 @@
+/*
+ * Copyright (C) 2011-2013 Renesas Electronics Corporation
+ * Copyright (C) 2013 Cogent Embedded, Inc.
+ *
+ * This file is based on the drivers/dma/sh/shdma.c
+ *
+ * Renesas SuperH DMA Engine support
+ *
+ * This is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * - DMA of SuperH does not have Hardware DMA chain mode.
+ * - max DMA size is 16MB.
+ *
+ */
+
+#include <linux/dmaengine.h>
+#include <linux/delay.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/platform_data/dma-rcar-hpbdma.h>
+#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
+#include <linux/shdma-base.h>
+#include <linux/slab.h>
+
+/* DMA channel registers */
+#define HPB_DMAE_DSAR0	0x00
+#define HPB_DMAE_DDAR0	0x04
+#define HPB_DMAE_DTCR0	0x08
+#define HPB_DMAE_DSAR1	0x0C
+#define HPB_DMAE_DDAR1	0x10
+#define HPB_DMAE_DTCR1	0x14
+#define HPB_DMAE_DSASR	0x18
+#define HPB_DMAE_DDASR	0x1C
+#define HPB_DMAE_DTCSR	0x20
+#define HPB_DMAE_DPTR	0x24
+#define HPB_DMAE_DCR	0x28
+#define HPB_DMAE_DCMDR	0x2C
+#define HPB_DMAE_DSTPR	0x30
+#define HPB_DMAE_DSTSR	0x34
+#define HPB_DMAE_DDBGR	0x38
+#define HPB_DMAE_DDBGR2	0x3C
+#define HPB_DMAE_CHAN(n)	(0x40 * (n))
+
+/* DMA command register (DCMDR) bits */
+#define HPB_DMAE_DCMDR_BDOUT	BIT(7)
+#define HPB_DMAE_DCMDR_DQSPD	BIT(6)
+#define HPB_DMAE_DCMDR_DQSPC	BIT(5)
+#define HPB_DMAE_DCMDR_DMSPD	BIT(4)
+#define HPB_DMAE_DCMDR_DMSPC	BIT(3)
+#define HPB_DMAE_DCMDR_DQEND	BIT(2)
+#define HPB_DMAE_DCMDR_DNXT	BIT(1)
+#define HPB_DMAE_DCMDR_DMEN	BIT(0)
+
+/* DMA forced stop register (DSTPR) bits */
+#define HPB_DMAE_DSTPR_DMSTP	BIT(0)
+
+/* DMA status register (DSTSR) bits */
+#define HPB_DMAE_DSTSR_DMSTS	BIT(0)
+
+/* DMA common registers */
+#define HPB_DMAE_DTIMR		0x00
+#define HPB_DMAE_DINTSR0		0x0C
+#define HPB_DMAE_DINTSR1		0x10
+#define HPB_DMAE_DINTCR0		0x14
+#define HPB_DMAE_DINTCR1		0x18
+#define HPB_DMAE_DINTMR0		0x1C
+#define HPB_DMAE_DINTMR1		0x20
+#define HPB_DMAE_DACTSR0		0x24
+#define HPB_DMAE_DACTSR1		0x28
+#define HPB_DMAE_HSRSTR(n)	(0x40 + (n) * 4)
+#define HPB_DMAE_HPB_DMASPR(n)	(0x140 + (n) * 4)
+#define HPB_DMAE_HPB_DMLVLR0	0x160
+#define HPB_DMAE_HPB_DMLVLR1	0x164
+#define HPB_DMAE_HPB_DMSHPT0	0x168
+#define HPB_DMAE_HPB_DMSHPT1	0x16C
+
+#define HPB_DMA_SLAVE_NUMBER 256
+#define HPB_DMA_TCR_MAX 0x01000000	/* 16 MiB */
+
+struct hpb_dmae_chan {
+	struct shdma_chan shdma_chan;
+	int xfer_mode;			/* DMA transfer mode */
+#define XFER_SINGLE	1
+#define XFER_DOUBLE	2
+	unsigned plane_idx;		/* current DMA information set */
+	bool first_desc;		/* first/next transfer */
+	int xmit_shift;			/* log_2(bytes_per_xfer) */
+	void __iomem *base;
+	const struct hpb_dmae_slave_config *cfg;
+	char dev_id[16];		/* unique name per DMAC of channel */
+	dma_addr_t slave_addr;
+};
+
+struct hpb_dmae_device {
+	struct shdma_dev shdma_dev;
+	spinlock_t reg_lock;		/* comm_reg operation lock */
+	struct hpb_dmae_pdata *pdata;
+	void __iomem *chan_reg;
+	void __iomem *comm_reg;
+	void __iomem *reset_reg;
+	void __iomem *mode_reg;
+};
+
+struct hpb_dmae_regs {
+	u32 sar; /* SAR / source address */
+	u32 dar; /* DAR / destination address */
+	u32 tcr; /* TCR / transfer count */
+};
+
+struct hpb_desc {
+	struct shdma_desc shdma_desc;
+	struct hpb_dmae_regs hw;
+	unsigned plane_idx;
+};
+
+#define to_chan(schan) container_of(schan, struct hpb_dmae_chan, shdma_chan)
+#define to_desc(sdesc) container_of(sdesc, struct hpb_desc, shdma_desc)
+#define to_dev(sc) container_of(sc->shdma_chan.dma_chan.device, \
+				struct hpb_dmae_device, shdma_dev.dma_dev)
+
+static void ch_reg_write(struct hpb_dmae_chan *hpb_dc, u32 data, u32 reg)
+{
+	iowrite32(data, hpb_dc->base + reg);
+}
+
+static u32 ch_reg_read(struct hpb_dmae_chan *hpb_dc, u32 reg)
+{
+	return ioread32(hpb_dc->base + reg);
+}
+
+static void dcmdr_write(struct hpb_dmae_device *hpbdev, u32 data)
+{
+	iowrite32(data, hpbdev->chan_reg + HPB_DMAE_DCMDR);
+}
+
+static void hsrstr_write(struct hpb_dmae_device *hpbdev, u32 ch)
+{
+	iowrite32(0x1, hpbdev->comm_reg + HPB_DMAE_HSRSTR(ch));
+}
+
+static u32 dintsr_read(struct hpb_dmae_device *hpbdev, u32 ch)
+{
+	u32 v;
+
+	if (ch < 32)
+		v = ioread32(hpbdev->comm_reg + HPB_DMAE_DINTSR0) >> ch;
+	else
+		v = ioread32(hpbdev->comm_reg + HPB_DMAE_DINTSR1) >> (ch - 32);
+	return v & 0x1;
+}
+
+static void dintcr_write(struct hpb_dmae_device *hpbdev, u32 ch)
+{
+	if (ch < 32)
+		iowrite32((0x1 << ch), hpbdev->comm_reg + HPB_DMAE_DINTCR0);
+	else
+		iowrite32((0x1 << (ch - 32)),
+			  hpbdev->comm_reg + HPB_DMAE_DINTCR1);
+}
+
+static void asyncmdr_write(struct hpb_dmae_device *hpbdev, u32 data)
+{
+	iowrite32(data, hpbdev->mode_reg);
+}
+
+static u32 asyncmdr_read(struct hpb_dmae_device *hpbdev)
+{
+	return ioread32(hpbdev->mode_reg);
+}
+
+static void hpb_dmae_enable_int(struct hpb_dmae_device *hpbdev, u32 ch)
+{
+	u32 intreg;
+
+	spin_lock_irq(&hpbdev->reg_lock);
+	if (ch < 32) {
+		intreg = ioread32(hpbdev->comm_reg + HPB_DMAE_DINTMR0);
+		iowrite32(BIT(ch) | intreg,
+			  hpbdev->comm_reg + HPB_DMAE_DINTMR0);
+	} else {
+		intreg = ioread32(hpbdev->comm_reg + HPB_DMAE_DINTMR1);
+		iowrite32(BIT(ch - 32) | intreg,
+			  hpbdev->comm_reg + HPB_DMAE_DINTMR1);
+	}
+	spin_unlock_irq(&hpbdev->reg_lock);
+}
+
+static void hpb_dmae_async_reset(struct hpb_dmae_device *hpbdev, u32 data)
+{
+	u32 rstr;
+	int timeout = 10000;	/* 100 ms */
+
+	spin_lock(&hpbdev->reg_lock);
+	rstr = ioread32(hpbdev->reset_reg);
+	rstr |= data;
+	iowrite32(rstr, hpbdev->reset_reg);
+	do {
+		rstr = ioread32(hpbdev->reset_reg);
+		if ((rstr & data) == data)
+			break;
+		udelay(10);
+	} while (timeout--);
+
+	if (timeout < 0)
+		dev_err(hpbdev->shdma_dev.dma_dev.dev,
+			"%s timeout\n", __func__);
+
+	rstr &= ~data;
+	iowrite32(rstr, hpbdev->reset_reg);
+	spin_unlock(&hpbdev->reg_lock);
+}
+
+static void hpb_dmae_set_async_mode(struct hpb_dmae_device *hpbdev,
+				    u32 mask, u32 data)
+{
+	u32 mode;
+
+	spin_lock_irq(&hpbdev->reg_lock);
+	mode = asyncmdr_read(hpbdev);
+	mode &= ~mask;
+	mode |= data;
+	asyncmdr_write(hpbdev, mode);
+	spin_unlock_irq(&hpbdev->reg_lock);
+}
+
+static void hpb_dmae_ctl_stop(struct hpb_dmae_device *hpbdev)
+{
+	dcmdr_write(hpbdev, HPB_DMAE_DCMDR_DQSPD);
+}
+
+static void hpb_dmae_reset(struct hpb_dmae_device *hpbdev)
+{
+	u32 ch;
+
+	for (ch = 0; ch < hpbdev->pdata->num_hw_channels; ch++)
+		hsrstr_write(hpbdev, ch);
+}
+
+static unsigned int calc_xmit_shift(struct hpb_dmae_chan *hpb_chan)
+{
+	struct hpb_dmae_device *hpbdev = to_dev(hpb_chan);
+	struct hpb_dmae_pdata *pdata = hpbdev->pdata;
+	int width = ch_reg_read(hpb_chan, HPB_DMAE_DCR);
+	int i;
+
+	switch (width & (HPB_DMAE_DCR_SPDS_MASK | HPB_DMAE_DCR_DPDS_MASK)) {
+	case HPB_DMAE_DCR_SPDS_8BIT | HPB_DMAE_DCR_DPDS_8BIT:
+	default:
+		i = XMIT_SZ_8BIT;
+		break;
+	case HPB_DMAE_DCR_SPDS_16BIT | HPB_DMAE_DCR_DPDS_16BIT:
+		i = XMIT_SZ_16BIT;
+		break;
+	case HPB_DMAE_DCR_SPDS_32BIT | HPB_DMAE_DCR_DPDS_32BIT:
+		i = XMIT_SZ_32BIT;
+		break;
+	}
+	return pdata->ts_shift[i];
+}
+
+static void hpb_dmae_set_reg(struct hpb_dmae_chan *hpb_chan,
+			     struct hpb_dmae_regs *hw, unsigned plane)
+{
+	ch_reg_write(hpb_chan, hw->sar,
+		     plane ? HPB_DMAE_DSAR1 : HPB_DMAE_DSAR0);
+	ch_reg_write(hpb_chan, hw->dar,
+		     plane ? HPB_DMAE_DDAR1 : HPB_DMAE_DDAR0);
+	ch_reg_write(hpb_chan, hw->tcr >> hpb_chan->xmit_shift,
+		     plane ? HPB_DMAE_DTCR1 : HPB_DMAE_DTCR0);
+}
+
+static void hpb_dmae_start(struct hpb_dmae_chan *hpb_chan, bool next)
+{
+	ch_reg_write(hpb_chan, (next ? HPB_DMAE_DCMDR_DNXT : 0) |
+		     HPB_DMAE_DCMDR_DMEN, HPB_DMAE_DCMDR);
+}
+
+static void hpb_dmae_halt(struct shdma_chan *schan)
+{
+	struct hpb_dmae_chan *chan = to_chan(schan);
+
+	ch_reg_write(chan, HPB_DMAE_DCMDR_DQEND, HPB_DMAE_DCMDR);
+	ch_reg_write(chan, HPB_DMAE_DSTPR_DMSTP, HPB_DMAE_DSTPR);
+}
+
+static const struct hpb_dmae_slave_config *
+hpb_dmae_find_slave(struct hpb_dmae_chan *hpb_chan, int slave_id)
+{
+	struct hpb_dmae_device *hpbdev = to_dev(hpb_chan);
+	struct hpb_dmae_pdata *pdata = hpbdev->pdata;
+	int i;
+
+	if (slave_id >= HPB_DMA_SLAVE_NUMBER)
+		return NULL;
+
+	for (i = 0; i < pdata->num_slaves; i++)
+		if (pdata->slaves[i].id == slave_id)
+			return pdata->slaves + i;
+
+	return NULL;
+}
+
+static void hpb_dmae_start_xfer(struct shdma_chan *schan,
+				struct shdma_desc *sdesc)
+{
+	struct hpb_dmae_chan *chan = to_chan(schan);
+	struct hpb_dmae_device *hpbdev = to_dev(chan);
+	struct hpb_desc *desc = to_desc(sdesc);
+
+	if (chan->cfg->flags & HPB_DMAE_SET_ASYNC_RESET)
+		hpb_dmae_async_reset(hpbdev, chan->cfg->rstr);
+
+	desc->plane_idx = chan->plane_idx;
+	hpb_dmae_set_reg(chan, &desc->hw, chan->plane_idx);
+	hpb_dmae_start(chan, !chan->first_desc);
+
+	if (chan->xfer_mode == XFER_DOUBLE) {
+		chan->plane_idx ^= 1;
+		chan->first_desc = false;
+	}
+}
+
+static bool hpb_dmae_desc_completed(struct shdma_chan *schan,
+				    struct shdma_desc *sdesc)
+{
+	/*
+	 * This is correct since we always have at most single
+	 * outstanding DMA transfer per channel, and by the time
+	 * we get completion interrupt the transfer is completed.
+	 * This will change if we ever use alternating DMA
+	 * information sets and submit two descriptors at once.
+	 */
+	return true;
+}
+
+static bool hpb_dmae_chan_irq(struct shdma_chan *schan, int irq)
+{
+	struct hpb_dmae_chan *chan = to_chan(schan);
+	struct hpb_dmae_device *hpbdev = to_dev(chan);
+	int ch = chan->cfg->dma_ch;
+
+	/* Check Complete DMA Transfer */
+	if (dintsr_read(hpbdev, ch)) {
+		/* Clear Interrupt status */
+		dintcr_write(hpbdev, ch);
+		return true;
+	}
+	return false;
+}
+
+static int hpb_dmae_desc_setup(struct shdma_chan *schan,
+			       struct shdma_desc *sdesc,
+			       dma_addr_t src, dma_addr_t dst, size_t *len)
+{
+	struct hpb_desc *desc = to_desc(sdesc);
+
+	if (*len > (size_t)HPB_DMA_TCR_MAX)
+		*len = (size_t)HPB_DMA_TCR_MAX;
+
+	desc->hw.sar = src;
+	desc->hw.dar = dst;
+	desc->hw.tcr = *len;
+
+	return 0;
+}
+
+static size_t hpb_dmae_get_partial(struct shdma_chan *schan,
+				   struct shdma_desc *sdesc)
+{
+	struct hpb_desc *desc = to_desc(sdesc);
+	struct hpb_dmae_chan *chan = to_chan(schan);
+	u32 tcr = ch_reg_read(chan, desc->plane_idx ?
+			      HPB_DMAE_DTCR1 : HPB_DMAE_DTCR0);
+
+	return (desc->hw.tcr - tcr) << chan->xmit_shift;
+}
+
+static bool hpb_dmae_channel_busy(struct shdma_chan *schan)
+{
+	struct hpb_dmae_chan *chan = to_chan(schan);
+	u32 dstsr = ch_reg_read(chan, HPB_DMAE_DSTSR);
+
+	return (dstsr & HPB_DMAE_DSTSR_DMSTS) == HPB_DMAE_DSTSR_DMSTS;
+}
+
+static int
+hpb_dmae_alloc_chan_resources(struct hpb_dmae_chan *hpb_chan,
+			      const struct hpb_dmae_slave_config *cfg)
+{
+	struct hpb_dmae_device *hpbdev = to_dev(hpb_chan);
+	struct hpb_dmae_pdata *pdata = hpbdev->pdata;
+	const struct hpb_dmae_channel *channel = pdata->channels;
+	int slave_id = cfg->id;
+	int i, err;
+
+	for (i = 0; i < pdata->num_channels; i++, channel++) {
+		if (channel->s_id == slave_id) {
+			struct device *dev = hpb_chan->shdma_chan.dev;
+
+			hpb_chan->base = hpbdev->chan_reg +
+				HPB_DMAE_CHAN(cfg->dma_ch);
+
+			dev_dbg(dev, "Detected Slave device\n");
+			dev_dbg(dev, " -- slave_id       : 0x%x\n", slave_id);
+			dev_dbg(dev, " -- cfg->dma_ch    : %d\n", cfg->dma_ch);
+			dev_dbg(dev, " -- channel->ch_irq: %d\n",
+				channel->ch_irq);
+			break;
+		}
+	}
+
+	err = shdma_request_irq(&hpb_chan->shdma_chan, channel->ch_irq,
+				IRQF_SHARED, hpb_chan->dev_id);
+	if (err) {
+		dev_err(hpb_chan->shdma_chan.dev,
+			"DMA channel request_irq %d failed with error %d\n",
+			channel->ch_irq, err);
+		return err;
+	}
+
+	hpb_chan->plane_idx = 0;
+	hpb_chan->first_desc = true;
+
+	if ((cfg->dcr & (HPB_DMAE_DCR_CT | HPB_DMAE_DCR_DIP)) == 0) {
+		hpb_chan->xfer_mode = XFER_SINGLE;
+	} else if ((cfg->dcr & (HPB_DMAE_DCR_CT | HPB_DMAE_DCR_DIP)) ==
+		   (HPB_DMAE_DCR_CT | HPB_DMAE_DCR_DIP)) {
+		hpb_chan->xfer_mode = XFER_DOUBLE;
+	} else {
+		dev_err(hpb_chan->shdma_chan.dev, "DCR setting error");
+		return -EINVAL;
+	}
+
+	if (cfg->flags & HPB_DMAE_SET_ASYNC_MODE)
+		hpb_dmae_set_async_mode(hpbdev, cfg->mdm, cfg->mdr);
+	ch_reg_write(hpb_chan, cfg->dcr, HPB_DMAE_DCR);
+	ch_reg_write(hpb_chan, cfg->port, HPB_DMAE_DPTR);
+	hpb_chan->xmit_shift = calc_xmit_shift(hpb_chan);
+	hpb_dmae_enable_int(hpbdev, cfg->dma_ch);
+
+	return 0;
+}
+
+static int hpb_dmae_set_slave(struct shdma_chan *schan, int slave_id,
+			      dma_addr_t slave_addr, bool try)
+{
+	struct hpb_dmae_chan *chan = to_chan(schan);
+	const struct hpb_dmae_slave_config *sc =
+		hpb_dmae_find_slave(chan, slave_id);
+
+	if (!sc)
+		return -ENODEV;
+	if (try)
+		return 0;
+	chan->cfg = sc;
+	chan->slave_addr = slave_addr ? : sc->addr;
+	return hpb_dmae_alloc_chan_resources(chan, sc);
+}
+
+static void hpb_dmae_setup_xfer(struct shdma_chan *schan, int slave_id)
+{
+}
+
+static dma_addr_t hpb_dmae_slave_addr(struct shdma_chan *schan)
+{
+	struct hpb_dmae_chan *chan = to_chan(schan);
+
+	return chan->slave_addr;
+}
+
+static struct shdma_desc *hpb_dmae_embedded_desc(void *buf, int i)
+{
+	return &((struct hpb_desc *)buf)[i].shdma_desc;
+}
+
+static const struct shdma_ops hpb_dmae_ops = {
+	.desc_completed = hpb_dmae_desc_completed,
+	.halt_channel = hpb_dmae_halt,
+	.channel_busy = hpb_dmae_channel_busy,
+	.slave_addr = hpb_dmae_slave_addr,
+	.desc_setup = hpb_dmae_desc_setup,
+	.set_slave = hpb_dmae_set_slave,
+	.setup_xfer = hpb_dmae_setup_xfer,
+	.start_xfer = hpb_dmae_start_xfer,
+	.embedded_desc = hpb_dmae_embedded_desc,
+	.chan_irq = hpb_dmae_chan_irq,
+	.get_partial = hpb_dmae_get_partial,
+};
+
+static int hpb_dmae_chan_probe(struct hpb_dmae_device *hpbdev, int id)
+{
+	struct shdma_dev *sdev = &hpbdev->shdma_dev;
+	struct platform_device *pdev =
+		to_platform_device(hpbdev->shdma_dev.dma_dev.dev);
+	struct hpb_dmae_chan *new_hpb_chan;
+	struct shdma_chan *schan;
+
+	/* Alloc channel */
+	new_hpb_chan = devm_kzalloc(&pdev->dev,
+				    sizeof(struct hpb_dmae_chan), GFP_KERNEL);
+	if (!new_hpb_chan) {
+		dev_err(hpbdev->shdma_dev.dma_dev.dev,
+			"No free memory for allocating DMA channels!\n");
+		return -ENOMEM;
+	}
+
+	schan = &new_hpb_chan->shdma_chan;
+	shdma_chan_probe(sdev, schan, id);
+
+	if (pdev->id >= 0)
+		snprintf(new_hpb_chan->dev_id, sizeof(new_hpb_chan->dev_id),
+			 "hpb-dmae%d.%d", pdev->id, id);
+	else
+		snprintf(new_hpb_chan->dev_id, sizeof(new_hpb_chan->dev_id),
+			 "hpb-dma.%d", id);
+
+	return 0;
+}
+
+static int hpb_dmae_probe(struct platform_device *pdev)
+{
+	struct hpb_dmae_pdata *pdata = pdev->dev.platform_data;
+	struct hpb_dmae_device *hpbdev;
+	struct dma_device *dma_dev;
+	struct resource *chan, *comm, *rest, *mode, *irq_res;
+	int err, i;
+
+	/* Get platform data */
+	if (!pdata || !pdata->num_channels)
+		return -ENODEV;
+
+	chan = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	comm = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+	rest = platform_get_resource(pdev, IORESOURCE_MEM, 2);
+	mode = platform_get_resource(pdev, IORESOURCE_MEM, 3);
+
+	irq_res = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
+	if (!irq_res)
+		return -ENODEV;
+
+	hpbdev = devm_kzalloc(&pdev->dev, sizeof(struct hpb_dmae_device),
+			      GFP_KERNEL);
+	if (!hpbdev) {
+		dev_err(&pdev->dev, "Not enough memory\n");
+		return -ENOMEM;
+	}
+
+	hpbdev->chan_reg = devm_ioremap_resource(&pdev->dev, chan);
+	if (IS_ERR(hpbdev->chan_reg))
+		return PTR_ERR(hpbdev->chan_reg);
+
+	hpbdev->comm_reg = devm_ioremap_resource(&pdev->dev, comm);
+	if (IS_ERR(hpbdev->comm_reg))
+		return PTR_ERR(hpbdev->comm_reg);
+
+	hpbdev->reset_reg = devm_ioremap_resource(&pdev->dev, rest);
+	if (IS_ERR(hpbdev->reset_reg))
+		return PTR_ERR(hpbdev->reset_reg);
+
+	hpbdev->mode_reg = devm_ioremap_resource(&pdev->dev, mode);
+	if (IS_ERR(hpbdev->mode_reg))
+		return PTR_ERR(hpbdev->mode_reg);
+
+	dma_dev = &hpbdev->shdma_dev.dma_dev;
+
+	spin_lock_init(&hpbdev->reg_lock);
+
+	/* Platform data */
+	hpbdev->pdata = pdata;
+
+	pm_runtime_enable(&pdev->dev);
+	err = pm_runtime_get_sync(&pdev->dev);
+	if (err < 0)
+		dev_err(&pdev->dev, "%s(): GET = %d\n", __func__, err);
+
+	/* Reset DMA controller */
+	hpb_dmae_reset(hpbdev);
+
+	pm_runtime_put(&pdev->dev);
+
+	dma_cap_set(DMA_MEMCPY, dma_dev->cap_mask);
+	dma_cap_set(DMA_SLAVE, dma_dev->cap_mask);
+
+	hpbdev->shdma_dev.ops = &hpb_dmae_ops;
+	hpbdev->shdma_dev.desc_size = sizeof(struct hpb_desc);
+	err = shdma_init(&pdev->dev, &hpbdev->shdma_dev, pdata->num_channels);
+	if (err < 0)
+		goto error;
+
+	/* Create DMA channels */
+	for (i = 0; i < pdata->num_channels; i++)
+		hpb_dmae_chan_probe(hpbdev, i);
+
+	platform_set_drvdata(pdev, hpbdev);
+	err = dma_async_device_register(dma_dev);
+	if (!err)
+		return 0;
+
+	shdma_cleanup(&hpbdev->shdma_dev);
+error:
+	pm_runtime_disable(&pdev->dev);
+	return err;
+}
+
+static void hpb_dmae_chan_remove(struct hpb_dmae_device *hpbdev)
+{
+	struct dma_device *dma_dev = &hpbdev->shdma_dev.dma_dev;
+	struct shdma_chan *schan;
+	int i;
+
+	shdma_for_each_chan(schan, &hpbdev->shdma_dev, i) {
+		BUG_ON(!schan);
+
+		shdma_chan_remove(schan);
+	}
+	dma_dev->chancnt = 0;
+}
+
+static int hpb_dmae_remove(struct platform_device *pdev)
+{
+	struct hpb_dmae_device *hpbdev = platform_get_drvdata(pdev);
+
+	dma_async_device_unregister(&hpbdev->shdma_dev.dma_dev);
+
+	pm_runtime_disable(&pdev->dev);
+
+	hpb_dmae_chan_remove(hpbdev);
+
+	return 0;
+}
+
+static void hpb_dmae_shutdown(struct platform_device *pdev)
+{
+	struct hpb_dmae_device *hpbdev = platform_get_drvdata(pdev);
+	hpb_dmae_ctl_stop(hpbdev);
+}
+
+static struct platform_driver hpb_dmae_driver = {
+	.probe		= hpb_dmae_probe,
+	.remove		= hpb_dmae_remove,
+	.shutdown	= hpb_dmae_shutdown,
+	.driver = {
+		.owner	= THIS_MODULE,
+		.name	= "hpb-dma-engine",
+	},
+};
+module_platform_driver(hpb_dmae_driver);
+
+MODULE_AUTHOR("Max Filippov <max.filippov@cogentembedded.com>");
+MODULE_DESCRIPTION("Renesas HPB DMA Engine driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/dma/sh/shdma-arm.h b/drivers/dma/sh/shdma-arm.h
new file mode 100644
index 000000000000..a2b8258426c9
--- /dev/null
+++ b/drivers/dma/sh/shdma-arm.h
@@ -0,0 +1,51 @@
+/*
+ * Renesas SuperH DMA Engine support
+ *
+ * Copyright (C) 2013 Renesas Electronics, Inc.
+ *
+ * This is free software; you can redistribute it and/or modify it under the
+ * terms of version 2 the GNU General Public License as published by the Free
+ * Software Foundation.
+ */
+
+#ifndef SHDMA_ARM_H
+#define SHDMA_ARM_H
+
+#include "shdma.h"
+
+/* Transmit sizes and respective CHCR register values */
+enum {
+	XMIT_SZ_8BIT		= 0,
+	XMIT_SZ_16BIT		= 1,
+	XMIT_SZ_32BIT		= 2,
+	XMIT_SZ_64BIT		= 7,
+	XMIT_SZ_128BIT		= 3,
+	XMIT_SZ_256BIT		= 4,
+	XMIT_SZ_512BIT		= 5,
+};
+
+/* log2(size / 8) - used to calculate number of transfers */
+#define SH_DMAE_TS_SHIFT {		\
+	[XMIT_SZ_8BIT]		= 0,	\
+	[XMIT_SZ_16BIT]		= 1,	\
+	[XMIT_SZ_32BIT]		= 2,	\
+	[XMIT_SZ_64BIT]		= 3,	\
+	[XMIT_SZ_128BIT]	= 4,	\
+	[XMIT_SZ_256BIT]	= 5,	\
+	[XMIT_SZ_512BIT]	= 6,	\
+}
+
+#define TS_LOW_BIT	0x3 /* --xx */
+#define TS_HI_BIT	0xc /* xx-- */
+
+#define TS_LOW_SHIFT	(3)
+#define TS_HI_SHIFT	(20 - 2)	/* 2 bits for shifted low TS */
+
+#define TS_INDEX2VAL(i) \
+	((((i) & TS_LOW_BIT) << TS_LOW_SHIFT) |\
+	 (((i) & TS_HI_BIT)  << TS_HI_SHIFT))
+
+#define CHCR_TX(xmit_sz) (DM_FIX | SM_INC | 0x800 | TS_INDEX2VAL((xmit_sz)))
+#define CHCR_RX(xmit_sz) (DM_INC | SM_FIX | 0x800 | TS_INDEX2VAL((xmit_sz)))
+
+#endif
diff --git a/drivers/dma/sh/shdma-base.c b/drivers/dma/sh/shdma-base.c
index 28ca36121631..d94ab592cc1b 100644
--- a/drivers/dma/sh/shdma-base.c
+++ b/drivers/dma/sh/shdma-base.c
@@ -171,7 +171,8 @@ static struct shdma_desc *shdma_get_desc(struct shdma_chan *schan)
 	return NULL;
 }
 
-static int shdma_setup_slave(struct shdma_chan *schan, int slave_id)
+static int shdma_setup_slave(struct shdma_chan *schan, int slave_id,
+			     dma_addr_t slave_addr)
 {
 	struct shdma_dev *sdev = to_shdma_dev(schan->dma_chan.device);
 	const struct shdma_ops *ops = sdev->ops;
@@ -179,7 +180,7 @@ static int shdma_setup_slave(struct shdma_chan *schan, int slave_id)
 
 	if (schan->dev->of_node) {
 		match = schan->hw_req;
-		ret = ops->set_slave(schan, match, true);
+		ret = ops->set_slave(schan, match, slave_addr, true);
 		if (ret < 0)
 			return ret;
 
@@ -194,7 +195,7 @@ static int shdma_setup_slave(struct shdma_chan *schan, int slave_id)
 	if (test_and_set_bit(slave_id, shdma_slave_used))
 		return -EBUSY;
 
-	ret = ops->set_slave(schan, match, false);
+	ret = ops->set_slave(schan, match, slave_addr, false);
 	if (ret < 0) {
 		clear_bit(slave_id, shdma_slave_used);
 		return ret;
@@ -236,7 +237,7 @@ bool shdma_chan_filter(struct dma_chan *chan, void *arg)
 	if (!schan->dev->of_node && match >= slave_num)
 		return false;
 
-	ret = ops->set_slave(schan, match, true);
+	ret = ops->set_slave(schan, match, 0, true);
 	if (ret < 0)
 		return false;
 
@@ -259,7 +260,7 @@ static int shdma_alloc_chan_resources(struct dma_chan *chan)
 	 */
 	if (slave) {
 		/* Legacy mode: .private is set in filter */
-		ret = shdma_setup_slave(schan, slave->slave_id);
+		ret = shdma_setup_slave(schan, slave->slave_id, 0);
 		if (ret < 0)
 			goto esetslave;
 	} else {
@@ -680,7 +681,9 @@ static int shdma_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd,
 		 * channel, while using it...
 		 */
 		config = (struct dma_slave_config *)arg;
-		ret = shdma_setup_slave(schan, config->slave_id);
+		ret = shdma_setup_slave(schan, config->slave_id,
+					config->direction == DMA_DEV_TO_MEM ?
+					config->src_addr : config->dst_addr);
 		if (ret < 0)
 			return ret;
 		break;
@@ -831,8 +834,8 @@ static irqreturn_t chan_irqt(int irq, void *dev)
 int shdma_request_irq(struct shdma_chan *schan, int irq,
 			   unsigned long flags, const char *name)
 {
-	int ret = request_threaded_irq(irq, chan_irq, chan_irqt,
-				       flags, name, schan);
+	int ret = devm_request_threaded_irq(schan->dev, irq, chan_irq,
+					    chan_irqt, flags, name, schan);
 
 	schan->irq = ret < 0 ? ret : irq;
 
@@ -840,13 +843,6 @@ int shdma_request_irq(struct shdma_chan *schan, int irq,
 }
 EXPORT_SYMBOL(shdma_request_irq);
 
-void shdma_free_irq(struct shdma_chan *schan)
-{
-	if (schan->irq >= 0)
-		free_irq(schan->irq, schan);
-}
-EXPORT_SYMBOL(shdma_free_irq);
-
 void shdma_chan_probe(struct shdma_dev *sdev,
 			   struct shdma_chan *schan, int id)
 {
diff --git a/drivers/dma/sh/shdma-of.c b/drivers/dma/sh/shdma-of.c
index 11bcb05cd79c..06473a05fe4e 100644
--- a/drivers/dma/sh/shdma-of.c
+++ b/drivers/dma/sh/shdma-of.c
@@ -42,12 +42,9 @@ static struct dma_chan *shdma_of_xlate(struct of_phandle_args *dma_spec,
 
 static int shdma_of_probe(struct platform_device *pdev)
 {
-	const struct of_dev_auxdata *lookup = pdev->dev.platform_data;
+	const struct of_dev_auxdata *lookup = dev_get_platdata(&pdev->dev);
 	int ret;
 
-	if (!lookup)
-		return -EINVAL;
-
 	ret = of_dma_controller_register(pdev->dev.of_node,
 					 shdma_of_xlate, pdev);
 	if (ret < 0)
diff --git a/drivers/dma/sh/shdma-r8a73a4.c b/drivers/dma/sh/shdma-r8a73a4.c
new file mode 100644
index 000000000000..4fb99970a3ea
--- /dev/null
+++ b/drivers/dma/sh/shdma-r8a73a4.c
@@ -0,0 +1,77 @@
+/*
+ * Renesas SuperH DMA Engine support for r8a73a4 (APE6) SoCs
+ *
+ * Copyright (C) 2013 Renesas Electronics, Inc.
+ *
+ * This is free software; you can redistribute it and/or modify it under the
+ * terms of version 2 the GNU General Public License as published by the Free
+ * Software Foundation.
+ */
+#include <linux/sh_dma.h>
+
+#include "shdma-arm.h"
+
+const unsigned int dma_ts_shift[] = SH_DMAE_TS_SHIFT;
+
+static const struct sh_dmae_slave_config dma_slaves[] = {
+	{
+		.chcr		= CHCR_TX(XMIT_SZ_32BIT),
+		.mid_rid	= 0xd1,		/* MMC0 Tx */
+	}, {
+		.chcr		= CHCR_RX(XMIT_SZ_32BIT),
+		.mid_rid	= 0xd2,		/* MMC0 Rx */
+	}, {
+		.chcr		= CHCR_TX(XMIT_SZ_32BIT),
+		.mid_rid	= 0xe1,		/* MMC1 Tx */
+	}, {
+		.chcr		= CHCR_RX(XMIT_SZ_32BIT),
+		.mid_rid	= 0xe2,		/* MMC1 Rx */
+	},
+};
+
+#define DMAE_CHANNEL(a, b)				\
+	{						\
+		.offset         = (a) - 0x20,		\
+		.dmars          = (a) - 0x20 + 0x40,	\
+		.chclr_bit	= (b),			\
+		.chclr_offset	= 0x80 - 0x20,		\
+	}
+
+static const struct sh_dmae_channel dma_channels[] = {
+	DMAE_CHANNEL(0x8000, 0),
+	DMAE_CHANNEL(0x8080, 1),
+	DMAE_CHANNEL(0x8100, 2),
+	DMAE_CHANNEL(0x8180, 3),
+	DMAE_CHANNEL(0x8200, 4),
+	DMAE_CHANNEL(0x8280, 5),
+	DMAE_CHANNEL(0x8300, 6),
+	DMAE_CHANNEL(0x8380, 7),
+	DMAE_CHANNEL(0x8400, 8),
+	DMAE_CHANNEL(0x8480, 9),
+	DMAE_CHANNEL(0x8500, 10),
+	DMAE_CHANNEL(0x8580, 11),
+	DMAE_CHANNEL(0x8600, 12),
+	DMAE_CHANNEL(0x8680, 13),
+	DMAE_CHANNEL(0x8700, 14),
+	DMAE_CHANNEL(0x8780, 15),
+	DMAE_CHANNEL(0x8800, 16),
+	DMAE_CHANNEL(0x8880, 17),
+	DMAE_CHANNEL(0x8900, 18),
+	DMAE_CHANNEL(0x8980, 19),
+};
+
+const struct sh_dmae_pdata r8a73a4_dma_pdata = {
+	.slave		= dma_slaves,
+	.slave_num	= ARRAY_SIZE(dma_slaves),
+	.channel	= dma_channels,
+	.channel_num	= ARRAY_SIZE(dma_channels),
+	.ts_low_shift	= TS_LOW_SHIFT,
+	.ts_low_mask	= TS_LOW_BIT << TS_LOW_SHIFT,
+	.ts_high_shift	= TS_HI_SHIFT,
+	.ts_high_mask	= TS_HI_BIT << TS_HI_SHIFT,
+	.ts_shift	= dma_ts_shift,
+	.ts_shift_num	= ARRAY_SIZE(dma_ts_shift),
+	.dmaor_init     = DMAOR_DME,
+	.chclr_present	= 1,
+	.chclr_bitwise	= 1,
+};
diff --git a/drivers/dma/sh/shdma.h b/drivers/dma/sh/shdma.h
index 9314e93225db..758a57b51875 100644
--- a/drivers/dma/sh/shdma.h
+++ b/drivers/dma/sh/shdma.h
@@ -28,18 +28,19 @@ struct sh_dmae_chan {
 	struct shdma_chan shdma_chan;
 	const struct sh_dmae_slave_config *config; /* Slave DMA configuration */
 	int xmit_shift;			/* log_2(bytes_per_xfer) */
-	u32 __iomem *base;
+	void __iomem *base;
 	char dev_id[16];		/* unique name per DMAC of channel */
 	int pm_error;
+	dma_addr_t slave_addr;
 };
 
 struct sh_dmae_device {
 	struct shdma_dev shdma_dev;
 	struct sh_dmae_chan *chan[SH_DMAE_MAX_CHANNELS];
-	struct sh_dmae_pdata *pdata;
+	const struct sh_dmae_pdata *pdata;
 	struct list_head node;
-	u32 __iomem *chan_reg;
-	u16 __iomem *dmars;
+	void __iomem *chan_reg;
+	void __iomem *dmars;
 	unsigned int chcr_offset;
 	u32 chcr_ie_bit;
 };
@@ -61,4 +62,11 @@ struct sh_dmae_desc {
 #define to_sh_dev(chan) container_of(chan->shdma_chan.dma_chan.device,\
 				     struct sh_dmae_device, shdma_dev.dma_dev)
 
+#ifdef CONFIG_SHDMA_R8A73A4
+extern const struct sh_dmae_pdata r8a73a4_dma_pdata;
+#define r8a73a4_shdma_devid (&r8a73a4_dma_pdata)
+#else
+#define r8a73a4_shdma_devid NULL
+#endif
+
 #endif	/* __DMA_SHDMA_H */
diff --git a/drivers/dma/sh/shdma.c b/drivers/dma/sh/shdmac.c
index 5039fbc88254..1069e8869f20 100644
--- a/drivers/dma/sh/shdma.c
+++ b/drivers/dma/sh/shdmac.c
@@ -20,6 +20,8 @@
 
 #include <linux/init.h>
 #include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
 #include <linux/slab.h>
 #include <linux/interrupt.h>
 #include <linux/dmaengine.h>
@@ -35,6 +37,15 @@
 #include "../dmaengine.h"
 #include "shdma.h"
 
+/* DMA register */
+#define SAR	0x00
+#define DAR	0x04
+#define TCR	0x08
+#define CHCR	0x0C
+#define DMAOR	0x40
+
+#define TEND	0x18 /* USB-DMAC */
+
 #define SH_DMAE_DRV_NAME "sh-dma-engine"
 
 /* Default MEMCPY transfer size = 2^2 = 4 bytes */
@@ -49,27 +60,37 @@
 static DEFINE_SPINLOCK(sh_dmae_lock);
 static LIST_HEAD(sh_dmae_devices);
 
-static void chclr_write(struct sh_dmae_chan *sh_dc, u32 data)
+/*
+ * Different DMAC implementations provide different ways to clear DMA channels:
+ * (1) none - no CHCLR registers are available
+ * (2) one CHCLR register per channel - 0 has to be written to it to clear
+ *     channel buffers
+ * (3) one CHCLR per several channels - 1 has to be written to the bit,
+ *     corresponding to the specific channel to reset it
+ */
+static void channel_clear(struct sh_dmae_chan *sh_dc)
 {
 	struct sh_dmae_device *shdev = to_sh_dev(sh_dc);
+	const struct sh_dmae_channel *chan_pdata = shdev->pdata->channel +
+		sh_dc->shdma_chan.id;
+	u32 val = shdev->pdata->chclr_bitwise ? 1 << chan_pdata->chclr_bit : 0;
 
-	__raw_writel(data, shdev->chan_reg +
-		     shdev->pdata->channel[sh_dc->shdma_chan.id].chclr_offset);
+	__raw_writel(val, shdev->chan_reg + chan_pdata->chclr_offset);
 }
 
 static void sh_dmae_writel(struct sh_dmae_chan *sh_dc, u32 data, u32 reg)
 {
-	__raw_writel(data, sh_dc->base + reg / sizeof(u32));
+	__raw_writel(data, sh_dc->base + reg);
 }
 
 static u32 sh_dmae_readl(struct sh_dmae_chan *sh_dc, u32 reg)
 {
-	return __raw_readl(sh_dc->base + reg / sizeof(u32));
+	return __raw_readl(sh_dc->base + reg);
 }
 
 static u16 dmaor_read(struct sh_dmae_device *shdev)
 {
-	u32 __iomem *addr = shdev->chan_reg + DMAOR / sizeof(u32);
+	void __iomem *addr = shdev->chan_reg + DMAOR;
 
 	if (shdev->pdata->dmaor_is_32bit)
 		return __raw_readl(addr);
@@ -79,7 +100,7 @@ static u16 dmaor_read(struct sh_dmae_device *shdev)
 
 static void dmaor_write(struct sh_dmae_device *shdev, u16 data)
 {
-	u32 __iomem *addr = shdev->chan_reg + DMAOR / sizeof(u32);
+	void __iomem *addr = shdev->chan_reg + DMAOR;
 
 	if (shdev->pdata->dmaor_is_32bit)
 		__raw_writel(data, addr);
@@ -91,14 +112,14 @@ static void chcr_write(struct sh_dmae_chan *sh_dc, u32 data)
 {
 	struct sh_dmae_device *shdev = to_sh_dev(sh_dc);
 
-	__raw_writel(data, sh_dc->base + shdev->chcr_offset / sizeof(u32));
+	__raw_writel(data, sh_dc->base + shdev->chcr_offset);
 }
 
 static u32 chcr_read(struct sh_dmae_chan *sh_dc)
 {
 	struct sh_dmae_device *shdev = to_sh_dev(sh_dc);
 
-	return __raw_readl(sh_dc->base + shdev->chcr_offset / sizeof(u32));
+	return __raw_readl(sh_dc->base + shdev->chcr_offset);
 }
 
 /*
@@ -133,7 +154,7 @@ static int sh_dmae_rst(struct sh_dmae_device *shdev)
 		for (i = 0; i < shdev->pdata->channel_num; i++) {
 			struct sh_dmae_chan *sh_chan = shdev->chan[i];
 			if (sh_chan)
-				chclr_write(sh_chan, 0);
+				channel_clear(sh_chan);
 		}
 	}
 
@@ -167,7 +188,7 @@ static bool dmae_is_busy(struct sh_dmae_chan *sh_chan)
 static unsigned int calc_xmit_shift(struct sh_dmae_chan *sh_chan, u32 chcr)
 {
 	struct sh_dmae_device *shdev = to_sh_dev(sh_chan);
-	struct sh_dmae_pdata *pdata = shdev->pdata;
+	const struct sh_dmae_pdata *pdata = shdev->pdata;
 	int cnt = ((chcr & pdata->ts_low_mask) >> pdata->ts_low_shift) |
 		((chcr & pdata->ts_high_mask) >> pdata->ts_high_shift);
 
@@ -180,7 +201,7 @@ static unsigned int calc_xmit_shift(struct sh_dmae_chan *sh_chan, u32 chcr)
 static u32 log2size_to_chcr(struct sh_dmae_chan *sh_chan, int l2size)
 {
 	struct sh_dmae_device *shdev = to_sh_dev(sh_chan);
-	struct sh_dmae_pdata *pdata = shdev->pdata;
+	const struct sh_dmae_pdata *pdata = shdev->pdata;
 	int i;
 
 	for (i = 0; i < pdata->ts_shift_num; i++)
@@ -240,9 +261,9 @@ static int dmae_set_chcr(struct sh_dmae_chan *sh_chan, u32 val)
 static int dmae_set_dmars(struct sh_dmae_chan *sh_chan, u16 val)
 {
 	struct sh_dmae_device *shdev = to_sh_dev(sh_chan);
-	struct sh_dmae_pdata *pdata = shdev->pdata;
+	const struct sh_dmae_pdata *pdata = shdev->pdata;
 	const struct sh_dmae_channel *chan_pdata = &pdata->channel[sh_chan->shdma_chan.id];
-	u16 __iomem *addr = shdev->dmars;
+	void __iomem *addr = shdev->dmars;
 	unsigned int shift = chan_pdata->dmars_bit;
 
 	if (dmae_is_busy(sh_chan))
@@ -253,8 +274,8 @@ static int dmae_set_dmars(struct sh_dmae_chan *sh_chan, u16 val)
 
 	/* in the case of a missing DMARS resource use first memory window */
 	if (!addr)
-		addr = (u16 __iomem *)shdev->chan_reg;
-	addr += chan_pdata->dmars / sizeof(u16);
+		addr = shdev->chan_reg;
+	addr += chan_pdata->dmars;
 
 	__raw_writew((__raw_readw(addr) & (0xff00 >> shift)) | (val << shift),
 		     addr);
@@ -309,7 +330,7 @@ static const struct sh_dmae_slave_config *dmae_find_slave(
 	struct sh_dmae_chan *sh_chan, int match)
 {
 	struct sh_dmae_device *shdev = to_sh_dev(sh_chan);
-	struct sh_dmae_pdata *pdata = shdev->pdata;
+	const struct sh_dmae_pdata *pdata = shdev->pdata;
 	const struct sh_dmae_slave_config *cfg;
 	int i;
 
@@ -323,7 +344,7 @@ static const struct sh_dmae_slave_config *dmae_find_slave(
 	} else {
 		for (i = 0, cfg = pdata->slave; i < pdata->slave_num; i++, cfg++)
 			if (cfg->mid_rid == match) {
-				sh_chan->shdma_chan.slave_id = cfg->slave_id;
+				sh_chan->shdma_chan.slave_id = i;
 				return cfg;
 			}
 	}
@@ -332,7 +353,7 @@ static const struct sh_dmae_slave_config *dmae_find_slave(
 }
 
 static int sh_dmae_set_slave(struct shdma_chan *schan,
-			     int slave_id, bool try)
+			     int slave_id, dma_addr_t slave_addr, bool try)
 {
 	struct sh_dmae_chan *sh_chan = container_of(schan, struct sh_dmae_chan,
 						    shdma_chan);
@@ -340,8 +361,10 @@ static int sh_dmae_set_slave(struct shdma_chan *schan,
 	if (!cfg)
 		return -ENXIO;
 
-	if (!try)
+	if (!try) {
 		sh_chan->config = cfg;
+		sh_chan->slave_addr = slave_addr ? : cfg->addr;
+	}
 
 	return 0;
 }
@@ -505,7 +528,8 @@ static int sh_dmae_chan_probe(struct sh_dmae_device *shdev, int id,
 	struct shdma_chan *schan;
 	int err;
 
-	sh_chan = kzalloc(sizeof(struct sh_dmae_chan), GFP_KERNEL);
+	sh_chan = devm_kzalloc(sdev->dma_dev.dev, sizeof(struct sh_dmae_chan),
+			       GFP_KERNEL);
 	if (!sh_chan) {
 		dev_err(sdev->dma_dev.dev,
 			"No free memory for allocating dma channels!\n");
@@ -517,7 +541,7 @@ static int sh_dmae_chan_probe(struct sh_dmae_device *shdev, int id,
 
 	shdma_chan_probe(sdev, schan, id);
 
-	sh_chan->base = shdev->chan_reg + chan_pdata->offset / sizeof(u32);
+	sh_chan->base = shdev->chan_reg + chan_pdata->offset;
 
 	/* set up channel irq */
 	if (pdev->id >= 0)
@@ -541,7 +565,6 @@ static int sh_dmae_chan_probe(struct sh_dmae_device *shdev, int id,
 err_no_irq:
 	/* remove from dmaengine device node */
 	shdma_chan_remove(schan);
-	kfree(sh_chan);
 	return err;
 }
 
@@ -552,14 +575,9 @@ static void sh_dmae_chan_remove(struct sh_dmae_device *shdev)
 	int i;
 
 	shdma_for_each_chan(schan, &shdev->shdma_dev, i) {
-		struct sh_dmae_chan *sh_chan = container_of(schan,
-					struct sh_dmae_chan, shdma_chan);
 		BUG_ON(!schan);
 
-		shdma_free_irq(&sh_chan->shdma_chan);
-
 		shdma_chan_remove(schan);
-		kfree(sh_chan);
 	}
 	dma_dev->chancnt = 0;
 }
@@ -636,7 +654,7 @@ static dma_addr_t sh_dmae_slave_addr(struct shdma_chan *schan)
 	 * This is an exclusive slave DMA operation, may only be called after a
 	 * successful slave configuration.
 	 */
-	return sh_chan->config->addr;
+	return sh_chan->slave_addr;
 }
 
 static struct shdma_desc *sh_dmae_embedded_desc(void *buf, int i)
@@ -658,9 +676,15 @@ static const struct shdma_ops sh_dmae_shdma_ops = {
 	.get_partial = sh_dmae_get_partial,
 };
 
+static const struct of_device_id sh_dmae_of_match[] = {
+	{.compatible = "renesas,shdma-r8a73a4", .data = r8a73a4_shdma_devid,},
+	{}
+};
+MODULE_DEVICE_TABLE(of, sh_dmae_of_match);
+
 static int sh_dmae_probe(struct platform_device *pdev)
 {
-	struct sh_dmae_pdata *pdata = pdev->dev.platform_data;
+	const struct sh_dmae_pdata *pdata;
 	unsigned long irqflags = IRQF_DISABLED,
 		chan_flag[SH_DMAE_MAX_CHANNELS] = {};
 	int errirq, chan_irq[SH_DMAE_MAX_CHANNELS];
@@ -669,6 +693,11 @@ static int sh_dmae_probe(struct platform_device *pdev)
 	struct dma_device *dma_dev;
 	struct resource *chan, *dmars, *errirq_res, *chanirq_res;
 
+	if (pdev->dev.of_node)
+		pdata = of_match_device(sh_dmae_of_match, &pdev->dev)->data;
+	else
+		pdata = dev_get_platdata(&pdev->dev);
+
 	/* get platform data */
 	if (!pdata || !pdata->channel_num)
 		return -ENODEV;
@@ -696,33 +725,22 @@ static int sh_dmae_probe(struct platform_device *pdev)
 	if (!chan || !errirq_res)
 		return -ENODEV;
 
-	if (!request_mem_region(chan->start, resource_size(chan), pdev->name)) {
-		dev_err(&pdev->dev, "DMAC register region already claimed\n");
-		return -EBUSY;
-	}
-
-	if (dmars && !request_mem_region(dmars->start, resource_size(dmars), pdev->name)) {
-		dev_err(&pdev->dev, "DMAC DMARS region already claimed\n");
-		err = -EBUSY;
-		goto ermrdmars;
-	}
-
-	err = -ENOMEM;
-	shdev = kzalloc(sizeof(struct sh_dmae_device), GFP_KERNEL);
+	shdev = devm_kzalloc(&pdev->dev, sizeof(struct sh_dmae_device),
+			     GFP_KERNEL);
 	if (!shdev) {
 		dev_err(&pdev->dev, "Not enough memory\n");
-		goto ealloc;
+		return -ENOMEM;
 	}
 
 	dma_dev = &shdev->shdma_dev.dma_dev;
 
-	shdev->chan_reg = ioremap(chan->start, resource_size(chan));
-	if (!shdev->chan_reg)
-		goto emapchan;
+	shdev->chan_reg = devm_ioremap_resource(&pdev->dev, chan);
+	if (IS_ERR(shdev->chan_reg))
+		return PTR_ERR(shdev->chan_reg);
 	if (dmars) {
-		shdev->dmars = ioremap(dmars->start, resource_size(dmars));
-		if (!shdev->dmars)
-			goto emapdmars;
+		shdev->dmars = devm_ioremap_resource(&pdev->dev, dmars);
+		if (IS_ERR(shdev->dmars))
+			return PTR_ERR(shdev->dmars);
 	}
 
 	if (!pdata->slave_only)
@@ -783,8 +801,8 @@ static int sh_dmae_probe(struct platform_device *pdev)
 
 	errirq = errirq_res->start;
 
-	err = request_irq(errirq, sh_dmae_err, irqflags,
-			  "DMAC Address Error", shdev);
+	err = devm_request_irq(&pdev->dev, errirq, sh_dmae_err, irqflags,
+			       "DMAC Address Error", shdev);
 	if (err) {
 		dev_err(&pdev->dev,
 			"DMA failed requesting irq #%d, error %d\n",
@@ -862,7 +880,6 @@ chan_probe_err:
 	sh_dmae_chan_remove(shdev);
 
 #if defined(CONFIG_CPU_SH4) || defined(CONFIG_ARCH_SHMOBILE)
-	free_irq(errirq, shdev);
 eirq_err:
 #endif
 rst_err:
@@ -873,21 +890,9 @@ rst_err:
 	pm_runtime_put(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
 
-	platform_set_drvdata(pdev, NULL);
 	shdma_cleanup(&shdev->shdma_dev);
 eshdma:
-	if (dmars)
-		iounmap(shdev->dmars);
-emapdmars:
-	iounmap(shdev->chan_reg);
 	synchronize_rcu();
-emapchan:
-	kfree(shdev);
-ealloc:
-	if (dmars)
-		release_mem_region(dmars->start, resource_size(dmars));
-ermrdmars:
-	release_mem_region(chan->start, resource_size(chan));
 
 	return err;
 }
@@ -896,14 +901,9 @@ static int sh_dmae_remove(struct platform_device *pdev)
 {
 	struct sh_dmae_device *shdev = platform_get_drvdata(pdev);
 	struct dma_device *dma_dev = &shdev->shdma_dev.dma_dev;
-	struct resource *res;
-	int errirq = platform_get_irq(pdev, 0);
 
 	dma_async_device_unregister(dma_dev);
 
-	if (errirq > 0)
-		free_irq(errirq, shdev);
-
 	spin_lock_irq(&sh_dmae_lock);
 	list_del_rcu(&shdev->node);
 	spin_unlock_irq(&sh_dmae_lock);
@@ -913,31 +913,11 @@ static int sh_dmae_remove(struct platform_device *pdev)
 	sh_dmae_chan_remove(shdev);
 	shdma_cleanup(&shdev->shdma_dev);
 
-	if (shdev->dmars)
-		iounmap(shdev->dmars);
-	iounmap(shdev->chan_reg);
-
-	platform_set_drvdata(pdev, NULL);
-
 	synchronize_rcu();
-	kfree(shdev);
-
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (res)
-		release_mem_region(res->start, resource_size(res));
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
-	if (res)
-		release_mem_region(res->start, resource_size(res));
 
 	return 0;
 }
 
-static const struct of_device_id sh_dmae_of_match[] = {
-	{ .compatible = "renesas,shdma", },
-	{ }
-};
-MODULE_DEVICE_TABLE(of, sh_dmae_of_match);
-
 static struct platform_driver sh_dmae_driver = {
 	.driver 	= {
 		.owner	= THIS_MODULE,
diff --git a/drivers/dma/sh/sudmac.c b/drivers/dma/sh/sudmac.c
index e7c94bbddb53..c7e9cdff0708 100644
--- a/drivers/dma/sh/sudmac.c
+++ b/drivers/dma/sh/sudmac.c
@@ -150,7 +150,8 @@ static const struct sudmac_slave_config *sudmac_find_slave(
 	return NULL;
 }
 
-static int sudmac_set_slave(struct shdma_chan *schan, int slave_id, bool try)
+static int sudmac_set_slave(struct shdma_chan *schan, int slave_id,
+			    dma_addr_t slave_addr, bool try)
 {
 	struct sudmac_chan *sc = to_chan(schan);
 	const struct sudmac_slave_config *cfg = sudmac_find_slave(sc, slave_id);
@@ -298,11 +299,8 @@ static void sudmac_chan_remove(struct sudmac_device *su_dev)
 	int i;
 
 	shdma_for_each_chan(schan, &su_dev->shdma_dev, i) {
-		struct sudmac_chan *sc = to_chan(schan);
-
 		BUG_ON(!schan);
 
-		shdma_free_irq(&sc->shdma_chan);
 		shdma_chan_remove(schan);
 	}
 	dma_dev->chancnt = 0;
@@ -335,7 +333,7 @@ static const struct shdma_ops sudmac_shdma_ops = {
 
 static int sudmac_probe(struct platform_device *pdev)
 {
-	struct sudmac_pdata *pdata = pdev->dev.platform_data;
+	struct sudmac_pdata *pdata = dev_get_platdata(&pdev->dev);
 	int err, i;
 	struct sudmac_device *su_dev;
 	struct dma_device *dma_dev;
@@ -345,9 +343,8 @@ static int sudmac_probe(struct platform_device *pdev)
 	if (!pdata)
 		return -ENODEV;
 
-	chan = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	irq_res = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
-	if (!chan || !irq_res)
+	if (!irq_res)
 		return -ENODEV;
 
 	err = -ENOMEM;
@@ -360,9 +357,10 @@ static int sudmac_probe(struct platform_device *pdev)
 
 	dma_dev = &su_dev->shdma_dev.dma_dev;
 
-	su_dev->chan_reg = devm_request_and_ioremap(&pdev->dev, chan);
-	if (!su_dev->chan_reg)
-		return err;
+	chan = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	su_dev->chan_reg = devm_ioremap_resource(&pdev->dev, chan);
+	if (IS_ERR(su_dev->chan_reg))
+		return PTR_ERR(su_dev->chan_reg);
 
 	dma_cap_set(DMA_SLAVE, dma_dev->cap_mask);
 
@@ -373,7 +371,7 @@ static int sudmac_probe(struct platform_device *pdev)
 		return err;
 
 	/* platform data */
-	su_dev->pdata = pdev->dev.platform_data;
+	su_dev->pdata = dev_get_platdata(&pdev->dev);
 
 	platform_set_drvdata(pdev, su_dev);
 
@@ -393,7 +391,6 @@ static int sudmac_probe(struct platform_device *pdev)
 chan_probe_err:
 	sudmac_chan_remove(su_dev);
 
-	platform_set_drvdata(pdev, NULL);
 	shdma_cleanup(&su_dev->shdma_dev);
 
 	return err;
@@ -407,7 +404,6 @@ static int sudmac_remove(struct platform_device *pdev)
 	dma_async_device_unregister(dma_dev);
 	sudmac_chan_remove(su_dev);
 	shdma_cleanup(&su_dev->shdma_dev);
-	platform_set_drvdata(pdev, NULL);
 
 	return 0;
 }
diff --git a/drivers/dma/sirf-dma.c b/drivers/dma/sirf-dma.c
index 716b23e4f327..6aec3ad814d3 100644
--- a/drivers/dma/sirf-dma.c
+++ b/drivers/dma/sirf-dma.c
@@ -9,6 +9,7 @@
 #include <linux/module.h>
 #include <linux/dmaengine.h>
 #include <linux/dma-mapping.h>
+#include <linux/pm_runtime.h>
 #include <linux/interrupt.h>
 #include <linux/io.h>
 #include <linux/slab.h>
@@ -73,6 +74,11 @@ struct sirfsoc_dma_chan {
 	int				mode;
 };
 
+struct sirfsoc_dma_regs {
+	u32				ctrl[SIRFSOC_DMA_CHANNELS];
+	u32				interrupt_en;
+};
+
 struct sirfsoc_dma {
 	struct dma_device		dma;
 	struct tasklet_struct		tasklet;
@@ -81,10 +87,13 @@ struct sirfsoc_dma {
 	int				irq;
 	struct clk			*clk;
 	bool				is_marco;
+	struct sirfsoc_dma_regs		regs_save;
 };
 
 #define DRV_NAME	"sirfsoc_dma"
 
+static int sirfsoc_dma_runtime_suspend(struct device *dev);
+
 /* Convert struct dma_chan to struct sirfsoc_dma_chan */
 static inline
 struct sirfsoc_dma_chan *dma_chan_to_sirfsoc_dma_chan(struct dma_chan *c)
@@ -393,6 +402,8 @@ static int sirfsoc_dma_alloc_chan_resources(struct dma_chan *chan)
 	LIST_HEAD(descs);
 	int i;
 
+	pm_runtime_get_sync(sdma->dma.dev);
+
 	/* Alloc descriptors for this channel */
 	for (i = 0; i < SIRFSOC_DMA_DESCRIPTORS; i++) {
 		sdesc = kzalloc(sizeof(*sdesc), GFP_KERNEL);
@@ -425,6 +436,7 @@ static int sirfsoc_dma_alloc_chan_resources(struct dma_chan *chan)
 static void sirfsoc_dma_free_chan_resources(struct dma_chan *chan)
 {
 	struct sirfsoc_dma_chan *schan = dma_chan_to_sirfsoc_dma_chan(chan);
+	struct sirfsoc_dma *sdma = dma_chan_to_sirfsoc_dma(chan);
 	struct sirfsoc_dma_desc *sdesc, *tmp;
 	unsigned long flags;
 	LIST_HEAD(descs);
@@ -445,6 +457,8 @@ static void sirfsoc_dma_free_chan_resources(struct dma_chan *chan)
 	/* Free descriptors */
 	list_for_each_entry_safe(sdesc, tmp, &descs, node)
 		kfree(sdesc);
+
+	pm_runtime_put(sdma->dma.dev);
 }
 
 /* Send pending descriptor to hardware */
@@ -595,7 +609,7 @@ sirfsoc_dma_prep_cyclic(struct dma_chan *chan, dma_addr_t addr,
 	spin_unlock_irqrestore(&schan->lock, iflags);
 
 	if (!sdesc)
-		return 0;
+		return NULL;
 
 	/* Place descriptor in prepared list */
 	spin_lock_irqsave(&schan->lock, iflags);
@@ -723,14 +737,14 @@ static int sirfsoc_dma_probe(struct platform_device *op)
 
 	tasklet_init(&sdma->tasklet, sirfsoc_dma_tasklet, (unsigned long)sdma);
 
-	clk_prepare_enable(sdma->clk);
-
 	/* Register DMA engine */
 	dev_set_drvdata(dev, sdma);
+
 	ret = dma_async_device_register(dma);
 	if (ret)
 		goto free_irq;
 
+	pm_runtime_enable(&op->dev);
 	dev_info(dev, "initialized SIRFSOC DMAC driver\n");
 
 	return 0;
@@ -747,13 +761,124 @@ static int sirfsoc_dma_remove(struct platform_device *op)
 	struct device *dev = &op->dev;
 	struct sirfsoc_dma *sdma = dev_get_drvdata(dev);
 
-	clk_disable_unprepare(sdma->clk);
 	dma_async_device_unregister(&sdma->dma);
 	free_irq(sdma->irq, sdma);
 	irq_dispose_mapping(sdma->irq);
+	pm_runtime_disable(&op->dev);
+	if (!pm_runtime_status_suspended(&op->dev))
+		sirfsoc_dma_runtime_suspend(&op->dev);
+
+	return 0;
+}
+
+static int sirfsoc_dma_runtime_suspend(struct device *dev)
+{
+	struct sirfsoc_dma *sdma = dev_get_drvdata(dev);
+
+	clk_disable_unprepare(sdma->clk);
+	return 0;
+}
+
+static int sirfsoc_dma_runtime_resume(struct device *dev)
+{
+	struct sirfsoc_dma *sdma = dev_get_drvdata(dev);
+	int ret;
+
+	ret = clk_prepare_enable(sdma->clk);
+	if (ret < 0) {
+		dev_err(dev, "clk_enable failed: %d\n", ret);
+		return ret;
+	}
+	return 0;
+}
+
+static int sirfsoc_dma_pm_suspend(struct device *dev)
+{
+	struct sirfsoc_dma *sdma = dev_get_drvdata(dev);
+	struct sirfsoc_dma_regs *save = &sdma->regs_save;
+	struct sirfsoc_dma_desc *sdesc;
+	struct sirfsoc_dma_chan *schan;
+	int ch;
+	int ret;
+
+	/*
+	 * if we were runtime-suspended before, resume to enable clock
+	 * before accessing register
+	 */
+	if (pm_runtime_status_suspended(dev)) {
+		ret = sirfsoc_dma_runtime_resume(dev);
+		if (ret < 0)
+			return ret;
+	}
+
+	/*
+	 * DMA controller will lose all registers while suspending
+	 * so we need to save registers for active channels
+	 */
+	for (ch = 0; ch < SIRFSOC_DMA_CHANNELS; ch++) {
+		schan = &sdma->channels[ch];
+		if (list_empty(&schan->active))
+			continue;
+		sdesc = list_first_entry(&schan->active,
+			struct sirfsoc_dma_desc,
+			node);
+		save->ctrl[ch] = readl_relaxed(sdma->base +
+			ch * 0x10 + SIRFSOC_DMA_CH_CTRL);
+	}
+	save->interrupt_en = readl_relaxed(sdma->base + SIRFSOC_DMA_INT_EN);
+
+	/* Disable clock */
+	sirfsoc_dma_runtime_suspend(dev);
+
+	return 0;
+}
+
+static int sirfsoc_dma_pm_resume(struct device *dev)
+{
+	struct sirfsoc_dma *sdma = dev_get_drvdata(dev);
+	struct sirfsoc_dma_regs *save = &sdma->regs_save;
+	struct sirfsoc_dma_desc *sdesc;
+	struct sirfsoc_dma_chan *schan;
+	int ch;
+	int ret;
+
+	/* Enable clock before accessing register */
+	ret = sirfsoc_dma_runtime_resume(dev);
+	if (ret < 0)
+		return ret;
+
+	writel_relaxed(save->interrupt_en, sdma->base + SIRFSOC_DMA_INT_EN);
+	for (ch = 0; ch < SIRFSOC_DMA_CHANNELS; ch++) {
+		schan = &sdma->channels[ch];
+		if (list_empty(&schan->active))
+			continue;
+		sdesc = list_first_entry(&schan->active,
+			struct sirfsoc_dma_desc,
+			node);
+		writel_relaxed(sdesc->width,
+			sdma->base + SIRFSOC_DMA_WIDTH_0 + ch * 4);
+		writel_relaxed(sdesc->xlen,
+			sdma->base + ch * 0x10 + SIRFSOC_DMA_CH_XLEN);
+		writel_relaxed(sdesc->ylen,
+			sdma->base + ch * 0x10 + SIRFSOC_DMA_CH_YLEN);
+		writel_relaxed(save->ctrl[ch],
+			sdma->base + ch * 0x10 + SIRFSOC_DMA_CH_CTRL);
+		writel_relaxed(sdesc->addr >> 2,
+			sdma->base + ch * 0x10 + SIRFSOC_DMA_CH_ADDR);
+	}
+
+	/* if we were runtime-suspended before, suspend again */
+	if (pm_runtime_status_suspended(dev))
+		sirfsoc_dma_runtime_suspend(dev);
+
 	return 0;
 }
 
+static const struct dev_pm_ops sirfsoc_dma_pm_ops = {
+	SET_RUNTIME_PM_OPS(sirfsoc_dma_runtime_suspend, sirfsoc_dma_runtime_resume, NULL)
+	SET_SYSTEM_SLEEP_PM_OPS(sirfsoc_dma_pm_suspend, sirfsoc_dma_pm_resume)
+};
+
 static struct of_device_id sirfsoc_dma_match[] = {
 	{ .compatible = "sirf,prima2-dmac", },
 	{ .compatible = "sirf,marco-dmac", },
@@ -766,6 +891,7 @@ static struct platform_driver sirfsoc_dma_driver = {
 	.driver = {
 		.name = DRV_NAME,
 		.owner = THIS_MODULE,
+		.pm = &sirfsoc_dma_pm_ops,
 		.of_match_table	= sirfsoc_dma_match,
 	},
 };
diff --git a/drivers/dma/ste_dma40.c b/drivers/dma/ste_dma40.c
index 5ab5880d5c90..82d2b97ad942 100644
--- a/drivers/dma/ste_dma40.c
+++ b/drivers/dma/ste_dma40.c
@@ -2591,6 +2591,9 @@ dma40_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t dma_addr,
 	int i;
 
 	sg = kcalloc(periods + 1, sizeof(struct scatterlist), GFP_NOWAIT);
+	if (!sg)
+		return NULL;
+
 	for (i = 0; i < periods; i++) {
 		sg_dma_address(&sg[i]) = dma_addr;
 		sg_dma_len(&sg[i]) = period_len;
@@ -3139,7 +3142,7 @@ static int __init d40_phy_res_init(struct d40_base *base)
 
 static struct d40_base * __init d40_hw_detect_init(struct platform_device *pdev)
 {
-	struct stedma40_platform_data *plat_data = pdev->dev.platform_data;
+	struct stedma40_platform_data *plat_data = dev_get_platdata(&pdev->dev);
 	struct clk *clk = NULL;
 	void __iomem *virtbase = NULL;
 	struct resource *res = NULL;
@@ -3226,8 +3229,8 @@ static struct d40_base * __init d40_hw_detect_init(struct platform_device *pdev)
 	num_log_chans = num_phy_chans * D40_MAX_LOG_CHAN_PER_PHY;
 
 	dev_info(&pdev->dev,
-		 "hardware rev: %d @ 0x%x with %d physical and %d logical channels\n",
-		 rev, res->start, num_phy_chans, num_log_chans);
+		 "hardware rev: %d @ %pa with %d physical and %d logical channels\n",
+		 rev, &res->start, num_phy_chans, num_log_chans);
 
 	base = kzalloc(ALIGN(sizeof(struct d40_base), 4) +
 		       (num_phy_chans + num_log_chans + num_memcpy_chans) *
@@ -3485,7 +3488,7 @@ static int __init d40_of_probe(struct platform_device *pdev,
 {
 	struct stedma40_platform_data *pdata;
 	int num_phy = 0, num_memcpy = 0, num_disabled = 0;
-	const const __be32 *list;
+	const __be32 *list;
 
 	pdata = devm_kzalloc(&pdev->dev,
 			     sizeof(struct stedma40_platform_data),
@@ -3516,7 +3519,7 @@ static int __init d40_of_probe(struct platform_device *pdev,
 	list = of_get_property(np, "disabled-channels", &num_disabled);
 	num_disabled /= sizeof(*list);
 
-	if (num_disabled > STEDMA40_MAX_PHYS || num_disabled < 0) {
+	if (num_disabled >= STEDMA40_MAX_PHYS || num_disabled < 0) {
 		d40_err(&pdev->dev,
 			"Invalid number of disabled channels specified (%d)\n",
 			num_disabled);
@@ -3535,7 +3538,7 @@ static int __init d40_of_probe(struct platform_device *pdev,
 
 static int __init d40_probe(struct platform_device *pdev)
 {
-	struct stedma40_platform_data *plat_data = pdev->dev.platform_data;
+	struct stedma40_platform_data *plat_data = dev_get_platdata(&pdev->dev);
 	struct device_node *np = pdev->dev.of_node;
 	int ret = -ENOENT;
 	struct d40_base *base = NULL;
@@ -3579,9 +3582,7 @@ static int __init d40_probe(struct platform_device *pdev)
 	if (request_mem_region(res->start, resource_size(res),
 			       D40_NAME " I/O lcpa") == NULL) {
 		ret = -EBUSY;
-		d40_err(&pdev->dev,
-			"Failed to request LCPA region 0x%x-0x%x\n",
-			res->start, res->end);
+		d40_err(&pdev->dev, "Failed to request LCPA region %pR\n", res);
 		goto failure;
 	}
 
@@ -3589,8 +3590,8 @@ static int __init d40_probe(struct platform_device *pdev)
 	val = readl(base->virtbase + D40_DREG_LCPA);
 	if (res->start != val && val != 0) {
 		dev_warn(&pdev->dev,
-			 "[%s] Mismatch LCPA dma 0x%x, def 0x%x\n",
-			 __func__, val, res->start);
+			 "[%s] Mismatch LCPA dma 0x%x, def %pa\n",
+			 __func__, val, &res->start);
 	} else
 		writel(res->start, base->virtbase + D40_DREG_LCPA);
 
diff --git a/drivers/dma/tegra20-apb-dma.c b/drivers/dma/tegra20-apb-dma.c
index f137914d7b16..5d4986e5f5fa 100644
--- a/drivers/dma/tegra20-apb-dma.c
+++ b/drivers/dma/tegra20-apb-dma.c
@@ -767,13 +767,11 @@ static enum dma_status tegra_dma_tx_status(struct dma_chan *dc,
 	unsigned long flags;
 	unsigned int residual;
 
-	spin_lock_irqsave(&tdc->lock, flags);
-
 	ret = dma_cookie_status(dc, cookie, txstate);
-	if (ret == DMA_SUCCESS) {
-		spin_unlock_irqrestore(&tdc->lock, flags);
+	if (ret == DMA_SUCCESS)
 		return ret;
-	}
+
+	spin_lock_irqsave(&tdc->lock, flags);
 
 	/* Check on wait_ack desc status */
 	list_for_each_entry(dma_desc, &tdc->free_dma_desc, node) {
diff --git a/drivers/dma/timb_dma.c b/drivers/dma/timb_dma.c
index 0ef43c136aa7..28af214fce04 100644
--- a/drivers/dma/timb_dma.c
+++ b/drivers/dma/timb_dma.c
@@ -669,7 +669,7 @@ static irqreturn_t td_irq(int irq, void *devid)
 
 static int td_probe(struct platform_device *pdev)
 {
-	struct timb_dma_platform_data *pdata = pdev->dev.platform_data;
+	struct timb_dma_platform_data *pdata = dev_get_platdata(&pdev->dev);
 	struct timb_dma *td;
 	struct resource *iomem;
 	int irq;
diff --git a/drivers/dma/txx9dmac.c b/drivers/dma/txx9dmac.c
index a59fb4841d4c..71e8e775189e 100644
--- a/drivers/dma/txx9dmac.c
+++ b/drivers/dma/txx9dmac.c
@@ -962,15 +962,14 @@ txx9dmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie,
 	enum dma_status ret;
 
 	ret = dma_cookie_status(chan, cookie, txstate);
-	if (ret != DMA_SUCCESS) {
-		spin_lock_bh(&dc->lock);
-		txx9dmac_scan_descriptors(dc);
-		spin_unlock_bh(&dc->lock);
+	if (ret == DMA_SUCCESS)
+		return DMA_SUCCESS;
 
-		ret = dma_cookie_status(chan, cookie, txstate);
-	}
+	spin_lock_bh(&dc->lock);
+	txx9dmac_scan_descriptors(dc);
+	spin_unlock_bh(&dc->lock);
 
-	return ret;
+	return dma_cookie_status(chan, cookie, txstate);
 }
 
 static void txx9dmac_chain_dynamic(struct txx9dmac_chan *dc,
@@ -1118,9 +1117,10 @@ static void txx9dmac_off(struct txx9dmac_dev *ddev)
 
 static int __init txx9dmac_chan_probe(struct platform_device *pdev)
 {
-	struct txx9dmac_chan_platform_data *cpdata = pdev->dev.platform_data;
+	struct txx9dmac_chan_platform_data *cpdata =
+			dev_get_platdata(&pdev->dev);
 	struct platform_device *dmac_dev = cpdata->dmac_dev;
-	struct txx9dmac_platform_data *pdata = dmac_dev->dev.platform_data;
+	struct txx9dmac_platform_data *pdata = dev_get_platdata(&dmac_dev->dev);
 	struct txx9dmac_chan *dc;
 	int err;
 	int ch = pdev->id % TXX9_DMA_MAX_NR_CHANNELS;
@@ -1203,7 +1203,7 @@ static int txx9dmac_chan_remove(struct platform_device *pdev)
 
 static int __init txx9dmac_probe(struct platform_device *pdev)
 {
-	struct txx9dmac_platform_data *pdata = pdev->dev.platform_data;
+	struct txx9dmac_platform_data *pdata = dev_get_platdata(&pdev->dev);
 	struct resource *io;
 	struct txx9dmac_dev *ddev;
 	u32 mcr;
@@ -1282,7 +1282,7 @@ static int txx9dmac_resume_noirq(struct device *dev)
 {
 	struct platform_device *pdev = to_platform_device(dev);
 	struct txx9dmac_dev *ddev = platform_get_drvdata(pdev);
-	struct txx9dmac_platform_data *pdata = pdev->dev.platform_data;
+	struct txx9dmac_platform_data *pdata = dev_get_platdata(&pdev->dev);
 	u32 mcr;
 
 	mcr = TXX9_DMA_MCR_MSTEN | MCR_LE;
diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c
index 8b6a0343c220..3c9e4e98c651 100644
--- a/drivers/edac/amd64_edac.c
+++ b/drivers/edac/amd64_edac.c
@@ -123,7 +123,7 @@ static void f15h_select_dct(struct amd64_pvt *pvt, u8 dct)
 	u32 reg = 0;
 
 	amd64_read_pci_cfg(pvt->F1, DCT_CFG_SEL, &reg);
-	reg &= 0xfffffffe;
+	reg &= (pvt->model >= 0x30) ? ~3 : ~1;
 	reg |= dct;
 	amd64_write_pci_cfg(pvt->F1, DCT_CFG_SEL, reg);
 }
@@ -133,8 +133,9 @@ static int f15_read_dct_pci_cfg(struct amd64_pvt *pvt, int addr, u32 *val,
 {
 	u8 dct  = 0;
 
+	/* For F15 M30h, the second dct is DCT 3, refer to BKDG Section 2.10 */
 	if (addr >= 0x140 && addr <= 0x1a0) {
-		dct   = 1;
+		dct   = (pvt->model >= 0x30) ? 3 : 1;
 		addr -= 0x100;
 	}
 
@@ -202,11 +203,11 @@ static int amd64_set_scrub_rate(struct mem_ctl_info *mci, u32 bw)
 	struct amd64_pvt *pvt = mci->pvt_info;
 	u32 min_scrubrate = 0x5;
 
-	if (boot_cpu_data.x86 == 0xf)
+	if (pvt->fam == 0xf)
 		min_scrubrate = 0x0;
 
-	/* F15h Erratum #505 */
-	if (boot_cpu_data.x86 == 0x15)
+	/* Erratum #505 */
+	if (pvt->fam == 0x15 && pvt->model < 0x10)
 		f15h_select_dct(pvt, 0);
 
 	return __amd64_set_scrub_rate(pvt->F3, bw, min_scrubrate);
@@ -218,8 +219,8 @@ static int amd64_get_scrub_rate(struct mem_ctl_info *mci)
 	u32 scrubval = 0;
 	int i, retval = -EINVAL;
 
-	/* F15h Erratum #505 */
-	if (boot_cpu_data.x86 == 0x15)
+	/* Erratum #505 */
+	if (pvt->fam == 0x15 && pvt->model < 0x10)
 		f15h_select_dct(pvt, 0);
 
 	amd64_read_pci_cfg(pvt->F3, SCRCTRL, &scrubval);
@@ -335,7 +336,7 @@ static void get_cs_base_and_mask(struct amd64_pvt *pvt, int csrow, u8 dct,
 	u64 csbase, csmask, base_bits, mask_bits;
 	u8 addr_shift;
 
-	if (boot_cpu_data.x86 == 0xf && pvt->ext_model < K8_REV_F) {
+	if (pvt->fam == 0xf && pvt->ext_model < K8_REV_F) {
 		csbase		= pvt->csels[dct].csbases[csrow];
 		csmask		= pvt->csels[dct].csmasks[csrow];
 		base_bits	= GENMASK(21, 31) | GENMASK(9, 15);
@@ -343,10 +344,11 @@ static void get_cs_base_and_mask(struct amd64_pvt *pvt, int csrow, u8 dct,
 		addr_shift	= 4;
 
 	/*
-	* F16h needs two addr_shift values: 8 for high and 6 for low
-	* (cf. F16h BKDG).
-	*/
-	} else if (boot_cpu_data.x86 == 0x16) {
+	 * F16h and F15h, models 30h and later need two addr_shift values:
+	 * 8 for high and 6 for low (cf. F16h BKDG).
+	 */
+	} else if (pvt->fam == 0x16 ||
+		  (pvt->fam == 0x15 && pvt->model >= 0x30)) {
 		csbase          = pvt->csels[dct].csbases[csrow];
 		csmask          = pvt->csels[dct].csmasks[csrow >> 1];
 
@@ -367,7 +369,7 @@ static void get_cs_base_and_mask(struct amd64_pvt *pvt, int csrow, u8 dct,
 		csmask		= pvt->csels[dct].csmasks[csrow >> 1];
 		addr_shift	= 8;
 
-		if (boot_cpu_data.x86 == 0x15)
+		if (pvt->fam == 0x15)
 			base_bits = mask_bits = GENMASK(19,30) | GENMASK(5,13);
 		else
 			base_bits = mask_bits = GENMASK(19,28) | GENMASK(5,13);
@@ -447,14 +449,14 @@ int amd64_get_dram_hole_info(struct mem_ctl_info *mci, u64 *hole_base,
 	struct amd64_pvt *pvt = mci->pvt_info;
 
 	/* only revE and later have the DRAM Hole Address Register */
-	if (boot_cpu_data.x86 == 0xf && pvt->ext_model < K8_REV_E) {
+	if (pvt->fam == 0xf && pvt->ext_model < K8_REV_E) {
 		edac_dbg(1, "  revision %d for node %d does not support DHAR\n",
 			 pvt->ext_model, pvt->mc_node_id);
 		return 1;
 	}
 
 	/* valid for Fam10h and above */
-	if (boot_cpu_data.x86 >= 0x10 && !dhar_mem_hoist_valid(pvt)) {
+	if (pvt->fam >= 0x10 && !dhar_mem_hoist_valid(pvt)) {
 		edac_dbg(1, "  Dram Memory Hoisting is DISABLED on this system\n");
 		return 1;
 	}
@@ -486,10 +488,8 @@ int amd64_get_dram_hole_info(struct mem_ctl_info *mci, u64 *hole_base,
 	*hole_base = dhar_base(pvt);
 	*hole_size = (1ULL << 32) - *hole_base;
 
-	if (boot_cpu_data.x86 > 0xf)
-		*hole_offset = f10_dhar_offset(pvt);
-	else
-		*hole_offset = k8_dhar_offset(pvt);
+	*hole_offset = (pvt->fam > 0xf) ? f10_dhar_offset(pvt)
+					: k8_dhar_offset(pvt);
 
 	edac_dbg(1, "  DHAR info for node %d base 0x%lx offset 0x%lx size 0x%lx\n",
 		 pvt->mc_node_id, (unsigned long)*hole_base,
@@ -663,7 +663,7 @@ static unsigned long amd64_determine_edac_cap(struct amd64_pvt *pvt)
 	u8 bit;
 	unsigned long edac_cap = EDAC_FLAG_NONE;
 
-	bit = (boot_cpu_data.x86 > 0xf || pvt->ext_model >= K8_REV_F)
+	bit = (pvt->fam > 0xf || pvt->ext_model >= K8_REV_F)
 		? 19
 		: 17;
 
@@ -675,7 +675,7 @@ static unsigned long amd64_determine_edac_cap(struct amd64_pvt *pvt)
 
 static void amd64_debug_display_dimm_sizes(struct amd64_pvt *, u8);
 
-static void amd64_dump_dramcfg_low(u32 dclr, int chan)
+static void amd64_dump_dramcfg_low(struct amd64_pvt *pvt, u32 dclr, int chan)
 {
 	edac_dbg(1, "F2x%d90 (DRAM Cfg Low): 0x%08x\n", chan, dclr);
 
@@ -686,7 +686,7 @@ static void amd64_dump_dramcfg_low(u32 dclr, int chan)
 	edac_dbg(1, "  PAR/ERR parity: %s\n",
 		 (dclr & BIT(8)) ?  "enabled" : "disabled");
 
-	if (boot_cpu_data.x86 == 0x10)
+	if (pvt->fam == 0x10)
 		edac_dbg(1, "  DCT 128bit mode width: %s\n",
 			 (dclr & BIT(11)) ?  "128b" : "64b");
 
@@ -709,21 +709,21 @@ static void dump_misc_regs(struct amd64_pvt *pvt)
 		 (pvt->nbcap & NBCAP_SECDED) ? "yes" : "no",
 		 (pvt->nbcap & NBCAP_CHIPKILL) ? "yes" : "no");
 
-	amd64_dump_dramcfg_low(pvt->dclr0, 0);
+	amd64_dump_dramcfg_low(pvt, pvt->dclr0, 0);
 
 	edac_dbg(1, "F3xB0 (Online Spare): 0x%08x\n", pvt->online_spare);
 
 	edac_dbg(1, "F1xF0 (DRAM Hole Address): 0x%08x, base: 0x%08x, offset: 0x%08x\n",
 		 pvt->dhar, dhar_base(pvt),
-		 (boot_cpu_data.x86 == 0xf) ? k8_dhar_offset(pvt)
-		 : f10_dhar_offset(pvt));
+		 (pvt->fam == 0xf) ? k8_dhar_offset(pvt)
+				   : f10_dhar_offset(pvt));
 
 	edac_dbg(1, "  DramHoleValid: %s\n", dhar_valid(pvt) ? "yes" : "no");
 
 	amd64_debug_display_dimm_sizes(pvt, 0);
 
 	/* everything below this point is Fam10h and above */
-	if (boot_cpu_data.x86 == 0xf)
+	if (pvt->fam == 0xf)
 		return;
 
 	amd64_debug_display_dimm_sizes(pvt, 1);
@@ -732,17 +732,20 @@ static void dump_misc_regs(struct amd64_pvt *pvt)
 
 	/* Only if NOT ganged does dclr1 have valid info */
 	if (!dct_ganging_enabled(pvt))
-		amd64_dump_dramcfg_low(pvt->dclr1, 1);
+		amd64_dump_dramcfg_low(pvt, pvt->dclr1, 1);
 }
 
 /*
- * see BKDG, F2x[1,0][5C:40], F2[1,0][6C:60]
+ * See BKDG, F2x[1,0][5C:40], F2[1,0][6C:60]
  */
 static void prep_chip_selects(struct amd64_pvt *pvt)
 {
-	if (boot_cpu_data.x86 == 0xf && pvt->ext_model < K8_REV_F) {
+	if (pvt->fam == 0xf && pvt->ext_model < K8_REV_F) {
 		pvt->csels[0].b_cnt = pvt->csels[1].b_cnt = 8;
 		pvt->csels[0].m_cnt = pvt->csels[1].m_cnt = 8;
+	} else if (pvt->fam == 0x15 && pvt->model >= 0x30) {
+		pvt->csels[0].b_cnt = pvt->csels[1].b_cnt = 4;
+		pvt->csels[0].m_cnt = pvt->csels[1].m_cnt = 2;
 	} else {
 		pvt->csels[0].b_cnt = pvt->csels[1].b_cnt = 8;
 		pvt->csels[0].m_cnt = pvt->csels[1].m_cnt = 4;
@@ -768,7 +771,7 @@ static void read_dct_base_mask(struct amd64_pvt *pvt)
 			edac_dbg(0, "  DCSB0[%d]=0x%08x reg: F2x%x\n",
 				 cs, *base0, reg0);
 
-		if (boot_cpu_data.x86 == 0xf || dct_ganging_enabled(pvt))
+		if (pvt->fam == 0xf || dct_ganging_enabled(pvt))
 			continue;
 
 		if (!amd64_read_dct_pci_cfg(pvt, reg1, base1))
@@ -786,7 +789,7 @@ static void read_dct_base_mask(struct amd64_pvt *pvt)
 			edac_dbg(0, "    DCSM0[%d]=0x%08x reg: F2x%x\n",
 				 cs, *mask0, reg0);
 
-		if (boot_cpu_data.x86 == 0xf || dct_ganging_enabled(pvt))
+		if (pvt->fam == 0xf || dct_ganging_enabled(pvt))
 			continue;
 
 		if (!amd64_read_dct_pci_cfg(pvt, reg1, mask1))
@@ -800,9 +803,9 @@ static enum mem_type amd64_determine_memory_type(struct amd64_pvt *pvt, int cs)
 	enum mem_type type;
 
 	/* F15h supports only DDR3 */
-	if (boot_cpu_data.x86 >= 0x15)
+	if (pvt->fam >= 0x15)
 		type = (pvt->dclr0 & BIT(16)) ?	MEM_DDR3 : MEM_RDDR3;
-	else if (boot_cpu_data.x86 == 0x10 || pvt->ext_model >= K8_REV_F) {
+	else if (pvt->fam == 0x10 || pvt->ext_model >= K8_REV_F) {
 		if (pvt->dchr0 & DDR3_MODE)
 			type = (pvt->dclr0 & BIT(16)) ?	MEM_DDR3 : MEM_RDDR3;
 		else
@@ -835,14 +838,13 @@ static int k8_early_channel_count(struct amd64_pvt *pvt)
 }
 
 /* On F10h and later ErrAddr is MC4_ADDR[47:1] */
-static u64 get_error_address(struct mce *m)
+static u64 get_error_address(struct amd64_pvt *pvt, struct mce *m)
 {
-	struct cpuinfo_x86 *c = &boot_cpu_data;
 	u64 addr;
 	u8 start_bit = 1;
 	u8 end_bit   = 47;
 
-	if (c->x86 == 0xf) {
+	if (pvt->fam == 0xf) {
 		start_bit = 3;
 		end_bit   = 39;
 	}
@@ -852,7 +854,7 @@ static u64 get_error_address(struct mce *m)
 	/*
 	 * Erratum 637 workaround
 	 */
-	if (c->x86 == 0x15) {
+	if (pvt->fam == 0x15) {
 		struct amd64_pvt *pvt;
 		u64 cc6_base, tmp_addr;
 		u32 tmp;
@@ -916,15 +918,15 @@ static struct pci_dev *pci_get_related_function(unsigned int vendor,
 static void read_dram_base_limit_regs(struct amd64_pvt *pvt, unsigned range)
 {
 	struct amd_northbridge *nb;
-	struct pci_dev *misc, *f1 = NULL;
-	struct cpuinfo_x86 *c = &boot_cpu_data;
+	struct pci_dev *f1 = NULL;
+	unsigned int pci_func;
 	int off = range << 3;
 	u32 llim;
 
 	amd64_read_pci_cfg(pvt->F1, DRAM_BASE_LO + off,  &pvt->ranges[range].base.lo);
 	amd64_read_pci_cfg(pvt->F1, DRAM_LIMIT_LO + off, &pvt->ranges[range].lim.lo);
 
-	if (c->x86 == 0xf)
+	if (pvt->fam == 0xf)
 		return;
 
 	if (!dram_rw(pvt, range))
@@ -934,15 +936,17 @@ static void read_dram_base_limit_regs(struct amd64_pvt *pvt, unsigned range)
 	amd64_read_pci_cfg(pvt->F1, DRAM_LIMIT_HI + off, &pvt->ranges[range].lim.hi);
 
 	/* F15h: factor in CC6 save area by reading dst node's limit reg */
-	if (c->x86 != 0x15)
+	if (pvt->fam != 0x15)
 		return;
 
 	nb = node_to_amd_nb(dram_dst_node(pvt, range));
 	if (WARN_ON(!nb))
 		return;
 
-	misc = nb->misc;
-	f1 = pci_get_related_function(misc->vendor, PCI_DEVICE_ID_AMD_15H_NB_F1, misc);
+	pci_func = (pvt->model == 0x30) ? PCI_DEVICE_ID_AMD_15H_M30H_NB_F1
+					: PCI_DEVICE_ID_AMD_15H_NB_F1;
+
+	f1 = pci_get_related_function(nb->misc->vendor, pci_func, nb->misc);
 	if (WARN_ON(!f1))
 		return;
 
@@ -1089,7 +1093,7 @@ static int f1x_early_channel_count(struct amd64_pvt *pvt)
 	int i, j, channels = 0;
 
 	/* On F10h, if we are in 128 bit mode, then we are using 2 channels */
-	if (boot_cpu_data.x86 == 0x10 && (pvt->dclr0 & WIDTH_128))
+	if (pvt->fam == 0x10 && (pvt->dclr0 & WIDTH_128))
 		return 2;
 
 	/*
@@ -1173,7 +1177,7 @@ static int f15_dbam_to_chip_select(struct amd64_pvt *pvt, u8 dct,
 }
 
 /*
- * F16h has only limited cs_modes
+ * F16h and F15h model 30h have only limited cs_modes.
  */
 static int f16_dbam_to_chip_select(struct amd64_pvt *pvt, u8 dct,
 				unsigned cs_mode)
@@ -1190,7 +1194,7 @@ static int f16_dbam_to_chip_select(struct amd64_pvt *pvt, u8 dct,
 static void read_dram_ctl_register(struct amd64_pvt *pvt)
 {
 
-	if (boot_cpu_data.x86 == 0xf)
+	if (pvt->fam == 0xf)
 		return;
 
 	if (!amd64_read_dct_pci_cfg(pvt, DCT_SEL_LO, &pvt->dct_sel_lo)) {
@@ -1218,6 +1222,29 @@ static void read_dram_ctl_register(struct amd64_pvt *pvt)
 }
 
 /*
+ * Determine channel (DCT) based on the interleaving mode (see F15h M30h BKDG,
+ * 2.10.12 Memory Interleaving Modes).
+ */
+static u8 f15_m30h_determine_channel(struct amd64_pvt *pvt, u64 sys_addr,
+				     u8 intlv_en, int num_dcts_intlv,
+				     u32 dct_sel)
+{
+	u8 channel = 0;
+	u8 select;
+
+	if (!(intlv_en))
+		return (u8)(dct_sel);
+
+	if (num_dcts_intlv == 2) {
+		select = (sys_addr >> 8) & 0x3;
+		channel = select ? 0x3 : 0;
+	} else if (num_dcts_intlv == 4)
+		channel = (sys_addr >> 8) & 0x7;
+
+	return channel;
+}
+
+/*
  * Determine channel (DCT) based on the interleaving mode: F10h BKDG, 2.8.9 Memory
  * Interleaving Modes.
  */
@@ -1366,6 +1393,10 @@ static int f1x_lookup_addr_in_dct(u64 in_addr, u8 nid, u8 dct)
 			 (in_addr & cs_mask), (cs_base & cs_mask));
 
 		if ((in_addr & cs_mask) == (cs_base & cs_mask)) {
+			if (pvt->fam == 0x15 && pvt->model >= 0x30) {
+				cs_found =  csrow;
+				break;
+			}
 			cs_found = f10_process_possible_spare(pvt, dct, csrow);
 
 			edac_dbg(1, " MATCH csrow=%d\n", cs_found);
@@ -1384,11 +1415,9 @@ static u64 f1x_swap_interleaved_region(struct amd64_pvt *pvt, u64 sys_addr)
 {
 	u32 swap_reg, swap_base, swap_limit, rgn_size, tmp_addr;
 
-	if (boot_cpu_data.x86 == 0x10) {
+	if (pvt->fam == 0x10) {
 		/* only revC3 and revE have that feature */
-		if (boot_cpu_data.x86_model < 4 ||
-		    (boot_cpu_data.x86_model < 0xa &&
-		     boot_cpu_data.x86_mask < 3))
+		if (pvt->model < 4 || (pvt->model < 0xa && pvt->stepping < 3))
 			return sys_addr;
 	}
 
@@ -1492,20 +1521,143 @@ static int f1x_match_to_this_node(struct amd64_pvt *pvt, unsigned range,
 	return cs_found;
 }
 
-static int f1x_translate_sysaddr_to_cs(struct amd64_pvt *pvt, u64 sys_addr,
-				       int *chan_sel)
+static int f15_m30h_match_to_this_node(struct amd64_pvt *pvt, unsigned range,
+					u64 sys_addr, int *chan_sel)
+{
+	int cs_found = -EINVAL;
+	int num_dcts_intlv = 0;
+	u64 chan_addr, chan_offset;
+	u64 dct_base, dct_limit;
+	u32 dct_cont_base_reg, dct_cont_limit_reg, tmp;
+	u8 channel, alias_channel, leg_mmio_hole, dct_sel, dct_offset_en;
+
+	u64 dhar_offset		= f10_dhar_offset(pvt);
+	u8 intlv_addr		= dct_sel_interleave_addr(pvt);
+	u8 node_id		= dram_dst_node(pvt, range);
+	u8 intlv_en		= dram_intlv_en(pvt, range);
+
+	amd64_read_pci_cfg(pvt->F1, DRAM_CONT_BASE, &dct_cont_base_reg);
+	amd64_read_pci_cfg(pvt->F1, DRAM_CONT_LIMIT, &dct_cont_limit_reg);
+
+	dct_offset_en		= (u8) ((dct_cont_base_reg >> 3) & BIT(0));
+	dct_sel			= (u8) ((dct_cont_base_reg >> 4) & 0x7);
+
+	edac_dbg(1, "(range %d) SystemAddr= 0x%llx Limit=0x%llx\n",
+		 range, sys_addr, get_dram_limit(pvt, range));
+
+	if (!(get_dram_base(pvt, range)  <= sys_addr) &&
+	    !(get_dram_limit(pvt, range) >= sys_addr))
+		return -EINVAL;
+
+	if (dhar_valid(pvt) &&
+	    dhar_base(pvt) <= sys_addr &&
+	    sys_addr < BIT_64(32)) {
+		amd64_warn("Huh? Address is in the MMIO hole: 0x%016llx\n",
+			    sys_addr);
+		return -EINVAL;
+	}
+
+	/* Verify sys_addr is within DCT Range. */
+	dct_base = (u64) dct_sel_baseaddr(pvt);
+	dct_limit = (dct_cont_limit_reg >> 11) & 0x1FFF;
+
+	if (!(dct_cont_base_reg & BIT(0)) &&
+	    !(dct_base <= (sys_addr >> 27) &&
+	      dct_limit >= (sys_addr >> 27)))
+		return -EINVAL;
+
+	/* Verify number of dct's that participate in channel interleaving. */
+	num_dcts_intlv = (int) hweight8(intlv_en);
+
+	if (!(num_dcts_intlv % 2 == 0) || (num_dcts_intlv > 4))
+		return -EINVAL;
+
+	channel = f15_m30h_determine_channel(pvt, sys_addr, intlv_en,
+					     num_dcts_intlv, dct_sel);
+
+	/* Verify we stay within the MAX number of channels allowed */
+	if (channel > 4 || channel < 0)
+		return -EINVAL;
+
+	leg_mmio_hole = (u8) (dct_cont_base_reg >> 1 & BIT(0));
+
+	/* Get normalized DCT addr */
+	if (leg_mmio_hole && (sys_addr >= BIT_64(32)))
+		chan_offset = dhar_offset;
+	else
+		chan_offset = dct_base << 27;
+
+	chan_addr = sys_addr - chan_offset;
+
+	/* remove channel interleave */
+	if (num_dcts_intlv == 2) {
+		if (intlv_addr == 0x4)
+			chan_addr = ((chan_addr >> 9) << 8) |
+						(chan_addr & 0xff);
+		else if (intlv_addr == 0x5)
+			chan_addr = ((chan_addr >> 10) << 9) |
+						(chan_addr & 0x1ff);
+		else
+			return -EINVAL;
+
+	} else if (num_dcts_intlv == 4) {
+		if (intlv_addr == 0x4)
+			chan_addr = ((chan_addr >> 10) << 8) |
+							(chan_addr & 0xff);
+		else if (intlv_addr == 0x5)
+			chan_addr = ((chan_addr >> 11) << 9) |
+							(chan_addr & 0x1ff);
+		else
+			return -EINVAL;
+	}
+
+	if (dct_offset_en) {
+		amd64_read_pci_cfg(pvt->F1,
+				   DRAM_CONT_HIGH_OFF + (int) channel * 4,
+				   &tmp);
+		chan_addr +=  (u64) ((tmp >> 11) & 0xfff) << 27;
+	}
+
+	f15h_select_dct(pvt, channel);
+
+	edac_dbg(1, "   Normalized DCT addr: 0x%llx\n", chan_addr);
+
+	/*
+	 * Find Chip select:
+	 * if channel = 3, then alias it to 1. This is because, in F15 M30h,
+	 * there is support for 4 DCT's, but only 2 are currently functional.
+	 * They are DCT0 and DCT3. But we have read all registers of DCT3 into
+	 * pvt->csels[1]. So we need to use '1' here to get correct info.
+	 * Refer F15 M30h BKDG Section 2.10 and 2.10.3 for clarifications.
+	 */
+	alias_channel =  (channel == 3) ? 1 : channel;
+
+	cs_found = f1x_lookup_addr_in_dct(chan_addr, node_id, alias_channel);
+
+	if (cs_found >= 0)
+		*chan_sel = alias_channel;
+
+	return cs_found;
+}
+
+static int f1x_translate_sysaddr_to_cs(struct amd64_pvt *pvt,
+					u64 sys_addr,
+					int *chan_sel)
 {
 	int cs_found = -EINVAL;
 	unsigned range;
 
 	for (range = 0; range < DRAM_RANGES; range++) {
-
 		if (!dram_rw(pvt, range))
 			continue;
 
-		if ((get_dram_base(pvt, range)  <= sys_addr) &&
-		    (get_dram_limit(pvt, range) >= sys_addr)) {
+		if (pvt->fam == 0x15 && pvt->model >= 0x30)
+			cs_found = f15_m30h_match_to_this_node(pvt, range,
+							       sys_addr,
+							       chan_sel);
 
+		else if ((get_dram_base(pvt, range)  <= sys_addr) &&
+			 (get_dram_limit(pvt, range) >= sys_addr)) {
 			cs_found = f1x_match_to_this_node(pvt, range,
 							  sys_addr, chan_sel);
 			if (cs_found >= 0)
@@ -1554,7 +1706,7 @@ static void amd64_debug_display_dimm_sizes(struct amd64_pvt *pvt, u8 ctrl)
 	u32 *dcsb = ctrl ? pvt->csels[1].csbases : pvt->csels[0].csbases;
 	u32 dbam  = ctrl ? pvt->dbam1 : pvt->dbam0;
 
-	if (boot_cpu_data.x86 == 0xf) {
+	if (pvt->fam == 0xf) {
 		/* K8 families < revF not supported yet */
 	       if (pvt->ext_model < K8_REV_F)
 			return;
@@ -1624,6 +1776,17 @@ static struct amd64_family_type amd64_family_types[] = {
 			.read_dct_pci_cfg	= f15_read_dct_pci_cfg,
 		}
 	},
+	[F15_M30H_CPUS] = {
+		.ctl_name = "F15h_M30h",
+		.f1_id = PCI_DEVICE_ID_AMD_15H_M30H_NB_F1,
+		.f3_id = PCI_DEVICE_ID_AMD_15H_M30H_NB_F3,
+		.ops = {
+			.early_channel_count	= f1x_early_channel_count,
+			.map_sysaddr_to_csrow	= f1x_map_sysaddr_to_csrow,
+			.dbam_to_cs		= f16_dbam_to_chip_select,
+			.read_dct_pci_cfg	= f15_read_dct_pci_cfg,
+		}
+	},
 	[F16_CPUS] = {
 		.ctl_name = "F16h",
 		.f1_id = PCI_DEVICE_ID_AMD_16H_NB_F1,
@@ -1860,7 +2023,7 @@ static inline void __amd64_decode_bus_error(struct mem_ctl_info *mci,
 
 	memset(&err, 0, sizeof(err));
 
-	sys_addr = get_error_address(m);
+	sys_addr = get_error_address(pvt, m);
 
 	if (ecc_type == 2)
 		err.syndrome = extract_syndrome(m->status);
@@ -1921,10 +2084,9 @@ static void free_mc_sibling_devs(struct amd64_pvt *pvt)
  */
 static void read_mc_regs(struct amd64_pvt *pvt)
 {
-	struct cpuinfo_x86 *c = &boot_cpu_data;
+	unsigned range;
 	u64 msr_val;
 	u32 tmp;
-	unsigned range;
 
 	/*
 	 * Retrieve TOP_MEM and TOP_MEM2; no masking off of reserved bits since
@@ -1985,14 +2147,14 @@ static void read_mc_regs(struct amd64_pvt *pvt)
 
 	pvt->ecc_sym_sz = 4;
 
-	if (c->x86 >= 0x10) {
+	if (pvt->fam >= 0x10) {
 		amd64_read_pci_cfg(pvt->F3, EXT_NB_MCA_CFG, &tmp);
-		if (c->x86 != 0x16)
+		if (pvt->fam != 0x16)
 			/* F16h has only DCT0 */
 			amd64_read_dct_pci_cfg(pvt, DBAM1, &pvt->dbam1);
 
 		/* F10h, revD and later can do x8 ECC too */
-		if ((c->x86 > 0x10 || c->x86_model > 7) && tmp & BIT(25))
+		if ((pvt->fam > 0x10 || pvt->model > 7) && tmp & BIT(25))
 			pvt->ecc_sym_sz = 8;
 	}
 	dump_misc_regs(pvt);
@@ -2086,7 +2248,7 @@ static int init_csrows(struct mem_ctl_info *mci)
 		bool row_dct0 = !!csrow_enabled(i, 0, pvt);
 		bool row_dct1 = false;
 
-		if (boot_cpu_data.x86 != 0xf)
+		if (pvt->fam != 0xf)
 			row_dct1 = !!csrow_enabled(i, 1, pvt);
 
 		if (!row_dct0 && !row_dct1)
@@ -2104,7 +2266,7 @@ static int init_csrows(struct mem_ctl_info *mci)
 		}
 
 		/* K8 has only one DCT */
-		if (boot_cpu_data.x86 != 0xf && row_dct1) {
+		if (pvt->fam != 0xf && row_dct1) {
 			int row_dct1_pages = amd64_csrow_nr_pages(pvt, 1, i);
 
 			csrow->channels[1]->dimm->nr_pages = row_dct1_pages;
@@ -2333,13 +2495,14 @@ static bool ecc_enabled(struct pci_dev *F3, u16 nid)
 
 static int set_mc_sysfs_attrs(struct mem_ctl_info *mci)
 {
+	struct amd64_pvt *pvt = mci->pvt_info;
 	int rc;
 
 	rc = amd64_create_sysfs_dbg_files(mci);
 	if (rc < 0)
 		return rc;
 
-	if (boot_cpu_data.x86 >= 0x10) {
+	if (pvt->fam >= 0x10) {
 		rc = amd64_create_sysfs_inject_files(mci);
 		if (rc < 0)
 			return rc;
@@ -2350,9 +2513,11 @@ static int set_mc_sysfs_attrs(struct mem_ctl_info *mci)
 
 static void del_mc_sysfs_attrs(struct mem_ctl_info *mci)
 {
+	struct amd64_pvt *pvt = mci->pvt_info;
+
 	amd64_remove_sysfs_dbg_files(mci);
 
-	if (boot_cpu_data.x86 >= 0x10)
+	if (pvt->fam >= 0x10)
 		amd64_remove_sysfs_inject_files(mci);
 }
 
@@ -2387,10 +2552,14 @@ static void setup_mci_misc_attrs(struct mem_ctl_info *mci,
  */
 static struct amd64_family_type *amd64_per_family_init(struct amd64_pvt *pvt)
 {
-	u8 fam = boot_cpu_data.x86;
 	struct amd64_family_type *fam_type = NULL;
 
-	switch (fam) {
+	pvt->ext_model  = boot_cpu_data.x86_model >> 4;
+	pvt->stepping	= boot_cpu_data.x86_mask;
+	pvt->model	= boot_cpu_data.x86_model;
+	pvt->fam	= boot_cpu_data.x86;
+
+	switch (pvt->fam) {
 	case 0xf:
 		fam_type		= &amd64_family_types[K8_CPUS];
 		pvt->ops		= &amd64_family_types[K8_CPUS].ops;
@@ -2402,6 +2571,12 @@ static struct amd64_family_type *amd64_per_family_init(struct amd64_pvt *pvt)
 		break;
 
 	case 0x15:
+		if (pvt->model == 0x30) {
+			fam_type	= &amd64_family_types[F15_M30H_CPUS];
+			pvt->ops	= &amd64_family_types[F15_M30H_CPUS].ops;
+			break;
+		}
+
 		fam_type		= &amd64_family_types[F15_CPUS];
 		pvt->ops		= &amd64_family_types[F15_CPUS].ops;
 		break;
@@ -2416,10 +2591,8 @@ static struct amd64_family_type *amd64_per_family_init(struct amd64_pvt *pvt)
 		return NULL;
 	}
 
-	pvt->ext_model = boot_cpu_data.x86_model >> 4;
-
 	amd64_info("%s %sdetected (node %d).\n", fam_type->ctl_name,
-		     (fam == 0xf ?
+		     (pvt->fam == 0xf ?
 				(pvt->ext_model >= K8_REV_F  ? "revF or later "
 							     : "revE or earlier ")
 				 : ""), pvt->mc_node_id);
@@ -2470,8 +2643,15 @@ static int amd64_init_one_instance(struct pci_dev *F2)
 	layers[0].size = pvt->csels[0].b_cnt;
 	layers[0].is_virt_csrow = true;
 	layers[1].type = EDAC_MC_LAYER_CHANNEL;
-	layers[1].size = pvt->channel_count;
+
+	/*
+	 * Always allocate two channels since we can have setups with DIMMs on
+	 * only one channel. Also, this simplifies handling later for the price
+	 * of a couple of KBs tops.
+	 */
+	layers[1].size = 2;
 	layers[1].is_virt_csrow = false;
+
 	mci = edac_mc_alloc(nid, ARRAY_SIZE(layers), layers, 0);
 	if (!mci)
 		goto err_siblings;
@@ -2579,6 +2759,8 @@ static void amd64_remove_one_instance(struct pci_dev *pdev)
 	struct ecc_settings *s = ecc_stngs[nid];
 
 	mci = find_mci_by_dev(&pdev->dev);
+	WARN_ON(!mci);
+
 	del_mc_sysfs_attrs(mci);
 	/* Remove from EDAC CORE tracking list */
 	mci = edac_mc_del_mc(&pdev->dev);
@@ -2638,6 +2820,14 @@ static DEFINE_PCI_DEVICE_TABLE(amd64_pci_table) = {
 	},
 	{
 		.vendor		= PCI_VENDOR_ID_AMD,
+		.device		= PCI_DEVICE_ID_AMD_15H_M30H_NB_F2,
+		.subvendor	= PCI_ANY_ID,
+		.subdevice	= PCI_ANY_ID,
+		.class		= 0,
+		.class_mask	= 0,
+	},
+	{
+		.vendor		= PCI_VENDOR_ID_AMD,
 		.device		= PCI_DEVICE_ID_AMD_16H_NB_F2,
 		.subvendor	= PCI_ANY_ID,
 		.subdevice	= PCI_ANY_ID,
diff --git a/drivers/edac/amd64_edac.h b/drivers/edac/amd64_edac.h
index 2c6f113bae2b..d2443cfa0698 100644
--- a/drivers/edac/amd64_edac.h
+++ b/drivers/edac/amd64_edac.h
@@ -170,6 +170,8 @@
 /*
  * PCI-defined configuration space registers
  */
+#define PCI_DEVICE_ID_AMD_15H_M30H_NB_F1 0x141b
+#define PCI_DEVICE_ID_AMD_15H_M30H_NB_F2 0x141c
 #define PCI_DEVICE_ID_AMD_15H_NB_F1	0x1601
 #define PCI_DEVICE_ID_AMD_15H_NB_F2	0x1602
 #define PCI_DEVICE_ID_AMD_16H_NB_F1	0x1531
@@ -181,13 +183,22 @@
 #define DRAM_BASE_LO			0x40
 #define DRAM_LIMIT_LO			0x44
 
-#define dram_intlv_en(pvt, i)		((u8)((pvt->ranges[i].base.lo >> 8) & 0x7))
+/*
+ * F15 M30h D18F1x2[1C:00]
+ */
+#define DRAM_CONT_BASE			0x200
+#define DRAM_CONT_LIMIT			0x204
+
+/*
+ * F15 M30h D18F1x2[4C:40]
+ */
+#define DRAM_CONT_HIGH_OFF		0x240
+
 #define dram_rw(pvt, i)			((u8)(pvt->ranges[i].base.lo & 0x3))
 #define dram_intlv_sel(pvt, i)		((u8)((pvt->ranges[i].lim.lo >> 8) & 0x7))
 #define dram_dst_node(pvt, i)		((u8)(pvt->ranges[i].lim.lo & 0x7))
 
 #define DHAR				0xf0
-#define dhar_valid(pvt)			((pvt)->dhar & BIT(0))
 #define dhar_mem_hoist_valid(pvt)	((pvt)->dhar & BIT(1))
 #define dhar_base(pvt)			((pvt)->dhar & 0xff000000)
 #define k8_dhar_offset(pvt)		(((pvt)->dhar & 0x0000ff00) << 16)
@@ -234,8 +245,6 @@
 #define DDR3_MODE			BIT(8)
 
 #define DCT_SEL_LO			0x110
-#define dct_sel_baseaddr(pvt)		((pvt)->dct_sel_lo & 0xFFFFF800)
-#define dct_sel_interleave_addr(pvt)	(((pvt)->dct_sel_lo >> 6) & 0x3)
 #define dct_high_range_enabled(pvt)	((pvt)->dct_sel_lo & BIT(0))
 #define dct_interleave_enabled(pvt)	((pvt)->dct_sel_lo & BIT(2))
 
@@ -297,6 +306,7 @@ enum amd_families {
 	K8_CPUS = 0,
 	F10_CPUS,
 	F15_CPUS,
+	F15_M30H_CPUS,
 	F16_CPUS,
 	NUM_FAMILIES,
 };
@@ -337,6 +347,10 @@ struct amd64_pvt {
 	struct pci_dev *F1, *F2, *F3;
 
 	u16 mc_node_id;		/* MC index of this MC node */
+	u8 fam;			/* CPU family */
+	u8 model;		/* ... model */
+	u8 stepping;		/* ... stepping */
+
 	int ext_model;		/* extended model value of this node */
 	int channel_count;
 
@@ -414,6 +428,14 @@ static inline u16 extract_syndrome(u64 status)
 	return ((status >> 47) & 0xff) | ((status >> 16) & 0xff00);
 }
 
+static inline u8 dct_sel_interleave_addr(struct amd64_pvt *pvt)
+{
+	if (pvt->fam == 0x15 && pvt->model >= 0x30)
+		return (((pvt->dct_sel_hi >> 9) & 0x1) << 2) |
+			((pvt->dct_sel_lo >> 6) & 0x3);
+
+	return	((pvt)->dct_sel_lo >> 6) & 0x3;
+}
 /*
  * per-node ECC settings descriptor
  */
@@ -504,3 +526,33 @@ static inline void enable_caches(void *dummy)
 {
 	write_cr0(read_cr0() & ~X86_CR0_CD);
 }
+
+static inline u8 dram_intlv_en(struct amd64_pvt *pvt, unsigned int i)
+{
+	if (pvt->fam == 0x15 && pvt->model >= 0x30) {
+		u32 tmp;
+		amd64_read_pci_cfg(pvt->F1, DRAM_CONT_LIMIT, &tmp);
+		return (u8) tmp & 0xF;
+	}
+	return (u8) (pvt->ranges[i].base.lo >> 8) & 0x7;
+}
+
+static inline u8 dhar_valid(struct amd64_pvt *pvt)
+{
+	if (pvt->fam == 0x15 && pvt->model >= 0x30) {
+		u32 tmp;
+		amd64_read_pci_cfg(pvt->F1, DRAM_CONT_BASE, &tmp);
+		return (tmp >> 1) & BIT(0);
+	}
+	return (pvt)->dhar & BIT(0);
+}
+
+static inline u32 dct_sel_baseaddr(struct amd64_pvt *pvt)
+{
+	if (pvt->fam == 0x15 && pvt->model >= 0x30) {
+		u32 tmp;
+		amd64_read_pci_cfg(pvt->F1, DRAM_CONT_BASE, &tmp);
+		return (tmp >> 11) & 0x1FFF;
+	}
+	return (pvt)->dct_sel_lo & 0xFFFFF800;
+}
diff --git a/drivers/edac/cpc925_edac.c b/drivers/edac/cpc925_edac.c
index 7f3c57113ba1..df6575f1430d 100644
--- a/drivers/edac/cpc925_edac.c
+++ b/drivers/edac/cpc925_edac.c
@@ -789,7 +789,7 @@ static struct cpc925_dev_info cpc925_devs[] = {
 	.exit = cpc925_htlink_exit,
 	.check = cpc925_htlink_check,
 	},
-	{0}, /* Terminated by NULL */
+	{ }
 };
 
 /*
diff --git a/drivers/edac/edac_mc_sysfs.c b/drivers/edac/edac_mc_sysfs.c
index e7c32c4f7837..9f7e0e609516 100644
--- a/drivers/edac/edac_mc_sysfs.c
+++ b/drivers/edac/edac_mc_sysfs.c
@@ -58,8 +58,10 @@ static int edac_set_poll_msec(const char *val, struct kernel_param *kp)
 	if (!val)
 		return -EINVAL;
 
-	ret = strict_strtol(val, 0, &l);
-	if (ret == -EINVAL || ((int)l != l))
+	ret = kstrtol(val, 0, &l);
+	if (ret)
+		return ret;
+	if ((int)l != l)
 		return -EINVAL;
 	*((int *)kp->arg) = l;
 
diff --git a/drivers/edac/i3200_edac.c b/drivers/edac/i3200_edac.c
index aa44c1718f50..be10a74b16ea 100644
--- a/drivers/edac/i3200_edac.c
+++ b/drivers/edac/i3200_edac.c
@@ -260,8 +260,7 @@ static void i3200_check(struct mem_ctl_info *mci)
 	i3200_process_error_info(mci, &info);
 }
 
-
-void __iomem *i3200_map_mchbar(struct pci_dev *pdev)
+static void __iomem *i3200_map_mchbar(struct pci_dev *pdev)
 {
 	union {
 		u64 mchbar;
diff --git a/drivers/edac/tile_edac.c b/drivers/edac/tile_edac.c
index a0820536b7d9..578f915ee195 100644
--- a/drivers/edac/tile_edac.c
+++ b/drivers/edac/tile_edac.c
@@ -257,7 +257,6 @@ static void __exit tile_edac_exit(void)
 		if (!pdev)
 			continue;
 
-		platform_set_drvdata(pdev, NULL);
 		platform_device_unregister(pdev);
 	}
 	platform_driver_unregister(&tile_edac_mc_driver);
diff --git a/drivers/edac/x38_edac.c b/drivers/edac/x38_edac.c
index c9db24d95caa..1a4df82376ba 100644
--- a/drivers/edac/x38_edac.c
+++ b/drivers/edac/x38_edac.c
@@ -248,8 +248,7 @@ static void x38_check(struct mem_ctl_info *mci)
 	x38_process_error_info(mci, &info);
 }
 
-
-void __iomem *x38_map_mchbar(struct pci_dev *pdev)
+static void __iomem *x38_map_mchbar(struct pci_dev *pdev)
 {
 	union {
 		u64 mchbar;
diff --git a/drivers/extcon/Kconfig b/drivers/extcon/Kconfig
index 63f454e20576..f1d54a3985bd 100644
--- a/drivers/extcon/Kconfig
+++ b/drivers/extcon/Kconfig
@@ -14,6 +14,10 @@ if EXTCON
 
 comment "Extcon Device Drivers"
 
+config OF_EXTCON
+	def_tristate y
+	depends on OF
+
 config EXTCON_GPIO
 	tristate "GPIO extcon support"
 	depends on GPIOLIB
diff --git a/drivers/extcon/Makefile b/drivers/extcon/Makefile
index 540e2c3a4431..759fdae46f95 100644
--- a/drivers/extcon/Makefile
+++ b/drivers/extcon/Makefile
@@ -2,6 +2,8 @@
 # Makefile for external connector class (extcon) devices
 #
 
+obj-$(CONFIG_OF_EXTCON)		+= of_extcon.o
+
 obj-$(CONFIG_EXTCON)		+= extcon-class.o
 obj-$(CONFIG_EXTCON_GPIO)	+= extcon-gpio.o
 obj-$(CONFIG_EXTCON_ADC_JACK)	+= extcon-adc-jack.o
diff --git a/drivers/extcon/extcon-adc-jack.c b/drivers/extcon/extcon-adc-jack.c
index d0233cd18ffa..5985807e52c9 100644
--- a/drivers/extcon/extcon-adc-jack.c
+++ b/drivers/extcon/extcon-adc-jack.c
@@ -87,7 +87,8 @@ static irqreturn_t adc_jack_irq_thread(int irq, void *_data)
 {
 	struct adc_jack_data *data = _data;
 
-	schedule_delayed_work(&data->handler, data->handling_delay);
+	queue_delayed_work(system_power_efficient_wq,
+			   &data->handler, data->handling_delay);
 	return IRQ_HANDLED;
 }
 
diff --git a/drivers/extcon/extcon-arizona.c b/drivers/extcon/extcon-arizona.c
index 7a1b4a7791ba..e55713083c78 100644
--- a/drivers/extcon/extcon-arizona.c
+++ b/drivers/extcon/extcon-arizona.c
@@ -890,8 +890,9 @@ static void arizona_micd_detect(struct work_struct *work)
 
 handled:
 	if (info->detecting)
-		schedule_delayed_work(&info->micd_timeout_work,
-				      msecs_to_jiffies(info->micd_timeout));
+		queue_delayed_work(system_power_efficient_wq,
+				   &info->micd_timeout_work,
+				   msecs_to_jiffies(info->micd_timeout));
 
 	pm_runtime_mark_last_busy(info->dev);
 	mutex_unlock(&info->lock);
@@ -912,8 +913,9 @@ static irqreturn_t arizona_micdet(int irq, void *data)
 	mutex_unlock(&info->lock);
 
 	if (debounce)
-		schedule_delayed_work(&info->micd_detect_work,
-				      msecs_to_jiffies(debounce));
+		queue_delayed_work(system_power_efficient_wq,
+				   &info->micd_detect_work,
+				   msecs_to_jiffies(debounce));
 	else
 		arizona_micd_detect(&info->micd_detect_work.work);
 
@@ -967,12 +969,14 @@ static irqreturn_t arizona_jackdet(int irq, void *data)
 	if (val == info->last_jackdet) {
 		dev_dbg(arizona->dev, "Suppressing duplicate JACKDET\n");
 		if (cancelled_hp)
-			schedule_delayed_work(&info->hpdet_work,
-					      msecs_to_jiffies(HPDET_DEBOUNCE));
+			queue_delayed_work(system_power_efficient_wq,
+					   &info->hpdet_work,
+					   msecs_to_jiffies(HPDET_DEBOUNCE));
 
 		if (cancelled_mic)
-			schedule_delayed_work(&info->micd_timeout_work,
-					      msecs_to_jiffies(info->micd_timeout));
+			queue_delayed_work(system_power_efficient_wq,
+					   &info->micd_timeout_work,
+					   msecs_to_jiffies(info->micd_timeout));
 
 		goto out;
 	}
@@ -994,8 +998,9 @@ static irqreturn_t arizona_jackdet(int irq, void *data)
 
 			arizona_start_mic(info);
 		} else {
-			schedule_delayed_work(&info->hpdet_work,
-					      msecs_to_jiffies(HPDET_DEBOUNCE));
+			queue_delayed_work(system_power_efficient_wq,
+					   &info->hpdet_work,
+					   msecs_to_jiffies(HPDET_DEBOUNCE));
 		}
 
 		regmap_update_bits(arizona->regmap,
diff --git a/drivers/extcon/extcon-class.c b/drivers/extcon/extcon-class.c
index 18ccadef43fd..148382faded9 100644
--- a/drivers/extcon/extcon-class.c
+++ b/drivers/extcon/extcon-class.c
@@ -148,6 +148,7 @@ static ssize_t state_store(struct device *dev, struct device_attribute *attr,
 
 	return count;
 }
+static DEVICE_ATTR_RW(state);
 
 static ssize_t name_show(struct device *dev, struct device_attribute *attr,
 		char *buf)
@@ -163,6 +164,7 @@ static ssize_t name_show(struct device *dev, struct device_attribute *attr,
 
 	return sprintf(buf, "%s\n", dev_name(edev->dev));
 }
+static DEVICE_ATTR_RO(name);
 
 static ssize_t cable_name_show(struct device *dev,
 			       struct device_attribute *attr, char *buf)
@@ -527,11 +529,12 @@ int extcon_unregister_notifier(struct extcon_dev *edev,
 }
 EXPORT_SYMBOL_GPL(extcon_unregister_notifier);
 
-static struct device_attribute extcon_attrs[] = {
-	__ATTR(state, S_IRUGO | S_IWUSR, state_show, state_store),
-	__ATTR_RO(name),
-	__ATTR_NULL,
+static struct attribute *extcon_attrs[] = {
+	&dev_attr_state.attr,
+	&dev_attr_name.attr,
+	NULL,
 };
+ATTRIBUTE_GROUPS(extcon);
 
 static int create_extcon_class(void)
 {
@@ -539,7 +542,7 @@ static int create_extcon_class(void)
 		extcon_class = class_create(THIS_MODULE, "extcon");
 		if (IS_ERR(extcon_class))
 			return PTR_ERR(extcon_class);
-		extcon_class->dev_attrs = extcon_attrs;
+		extcon_class->dev_groups = extcon_groups;
 
 #if defined(CONFIG_ANDROID)
 		switch_class = class_compat_register("switch");
@@ -602,7 +605,8 @@ int extcon_dev_register(struct extcon_dev *edev, struct device *dev)
 	edev->dev->class = extcon_class;
 	edev->dev->release = extcon_dev_release;
 
-	dev_set_name(edev->dev, "%s", edev->name ? edev->name : dev_name(dev));
+	edev->name = edev->name ? edev->name : dev_name(dev);
+	dev_set_name(edev->dev, "%s", edev->name);
 
 	if (edev->max_supported) {
 		char buf[10];
diff --git a/drivers/extcon/extcon-gpio.c b/drivers/extcon/extcon-gpio.c
index 02bec32adde4..f874c30ddbff 100644
--- a/drivers/extcon/extcon-gpio.c
+++ b/drivers/extcon/extcon-gpio.c
@@ -56,7 +56,7 @@ static irqreturn_t gpio_irq_handler(int irq, void *dev_id)
 {
 	struct gpio_extcon_data *extcon_data = dev_id;
 
-	schedule_delayed_work(&extcon_data->work,
+	queue_delayed_work(system_power_efficient_wq, &extcon_data->work,
 			      extcon_data->debounce_jiffies);
 	return IRQ_HANDLED;
 }
diff --git a/drivers/extcon/extcon-palmas.c b/drivers/extcon/extcon-palmas.c
index b752a0ad7b63..89fdd05c5fd6 100644
--- a/drivers/extcon/extcon-palmas.c
+++ b/drivers/extcon/extcon-palmas.c
@@ -57,6 +57,7 @@ static irqreturn_t palmas_vbus_irq_handler(int irq, void *_palmas_usb)
 		if (palmas_usb->linkstat != PALMAS_USB_STATE_VBUS) {
 			palmas_usb->linkstat = PALMAS_USB_STATE_VBUS;
 			extcon_set_cable_state(&palmas_usb->edev, "USB", true);
+			dev_info(palmas_usb->dev, "USB cable is attached\n");
 		} else {
 			dev_dbg(palmas_usb->dev,
 				"Spurious connect event detected\n");
@@ -65,6 +66,7 @@ static irqreturn_t palmas_vbus_irq_handler(int irq, void *_palmas_usb)
 		if (palmas_usb->linkstat == PALMAS_USB_STATE_VBUS) {
 			palmas_usb->linkstat = PALMAS_USB_STATE_DISCONNECT;
 			extcon_set_cable_state(&palmas_usb->edev, "USB", false);
+			dev_info(palmas_usb->dev, "USB cable is detached\n");
 		} else {
 			dev_dbg(palmas_usb->dev,
 				"Spurious disconnect event detected\n");
@@ -84,28 +86,23 @@ static irqreturn_t palmas_id_irq_handler(int irq, void *_palmas_usb)
 
 	if (set & PALMAS_USB_ID_INT_SRC_ID_GND) {
 		palmas_write(palmas_usb->palmas, PALMAS_USB_OTG_BASE,
-			PALMAS_USB_ID_INT_EN_HI_SET,
-			PALMAS_USB_ID_INT_EN_HI_SET_ID_FLOAT);
-		palmas_write(palmas_usb->palmas, PALMAS_USB_OTG_BASE,
-			PALMAS_USB_ID_INT_EN_HI_CLR,
-			PALMAS_USB_ID_INT_EN_HI_CLR_ID_GND);
-		palmas_write(palmas_usb->palmas, PALMAS_USB_OTG_BASE,
 			PALMAS_USB_ID_INT_LATCH_CLR,
 			PALMAS_USB_ID_INT_EN_HI_CLR_ID_GND);
 		palmas_usb->linkstat = PALMAS_USB_STATE_ID;
 		extcon_set_cable_state(&palmas_usb->edev, "USB-HOST", true);
+		dev_info(palmas_usb->dev, "USB-HOST cable is attached\n");
 	} else if (set & PALMAS_USB_ID_INT_SRC_ID_FLOAT) {
 		palmas_write(palmas_usb->palmas, PALMAS_USB_OTG_BASE,
-			PALMAS_USB_ID_INT_EN_HI_SET,
-			PALMAS_USB_ID_INT_EN_HI_SET_ID_GND);
-		palmas_write(palmas_usb->palmas, PALMAS_USB_OTG_BASE,
-			PALMAS_USB_ID_INT_EN_HI_CLR,
-			PALMAS_USB_ID_INT_EN_HI_CLR_ID_FLOAT);
-		palmas_write(palmas_usb->palmas, PALMAS_USB_OTG_BASE,
 			PALMAS_USB_ID_INT_LATCH_CLR,
 			PALMAS_USB_ID_INT_EN_HI_CLR_ID_FLOAT);
 		palmas_usb->linkstat = PALMAS_USB_STATE_DISCONNECT;
 		extcon_set_cable_state(&palmas_usb->edev, "USB-HOST", false);
+		dev_info(palmas_usb->dev, "USB-HOST cable is detached\n");
+	} else if ((palmas_usb->linkstat == PALMAS_USB_STATE_ID) &&
+				(!(set & PALMAS_USB_ID_INT_SRC_ID_GND))) {
+		palmas_usb->linkstat = PALMAS_USB_STATE_DISCONNECT;
+		extcon_set_cable_state(&palmas_usb->edev, "USB-HOST", false);
+		dev_info(palmas_usb->dev, "USB-HOST cable is detached\n");
 	}
 
 	return IRQ_HANDLED;
@@ -122,13 +119,17 @@ static void palmas_enable_irq(struct palmas_usb *palmas_usb)
 
 	palmas_write(palmas_usb->palmas, PALMAS_USB_OTG_BASE,
 		PALMAS_USB_ID_INT_EN_HI_SET,
-		PALMAS_USB_ID_INT_EN_HI_SET_ID_GND);
+		PALMAS_USB_ID_INT_EN_HI_SET_ID_GND |
+		PALMAS_USB_ID_INT_EN_HI_SET_ID_FLOAT);
 
-	palmas_vbus_irq_handler(palmas_usb->vbus_irq, palmas_usb);
+	if (palmas_usb->enable_vbus_detection)
+		palmas_vbus_irq_handler(palmas_usb->vbus_irq, palmas_usb);
 
 	/* cold plug for host mode needs this delay */
-	msleep(30);
-	palmas_id_irq_handler(palmas_usb->id_irq, palmas_usb);
+	if (palmas_usb->enable_id_detection) {
+		msleep(30);
+		palmas_id_irq_handler(palmas_usb->id_irq, palmas_usb);
+	}
 }
 
 static int palmas_usb_probe(struct platform_device *pdev)
@@ -139,21 +140,25 @@ static int palmas_usb_probe(struct platform_device *pdev)
 	struct palmas_usb *palmas_usb;
 	int status;
 
-	if (node && !pdata) {
-		pdata = devm_kzalloc(&pdev->dev, sizeof(*pdata), GFP_KERNEL);
-
-		if (!pdata)
-			return -ENOMEM;
-
-		pdata->wakeup = of_property_read_bool(node, "ti,wakeup");
-	} else if (!pdata) {
-		return -EINVAL;
-	}
-
 	palmas_usb = devm_kzalloc(&pdev->dev, sizeof(*palmas_usb), GFP_KERNEL);
 	if (!palmas_usb)
 		return -ENOMEM;
 
+	if (node && !pdata) {
+		palmas_usb->wakeup = of_property_read_bool(node, "ti,wakeup");
+		palmas_usb->enable_id_detection = of_property_read_bool(node,
+						"ti,enable-id-detection");
+		palmas_usb->enable_vbus_detection = of_property_read_bool(node,
+						"ti,enable-vbus-detection");
+	} else {
+		palmas_usb->wakeup = true;
+		palmas_usb->enable_id_detection = true;
+		palmas_usb->enable_vbus_detection = true;
+
+		if (pdata)
+			palmas_usb->wakeup = pdata->wakeup;
+	}
+
 	palmas->usb = palmas_usb;
 	palmas_usb->palmas = palmas;
 
@@ -168,11 +173,10 @@ static int palmas_usb_probe(struct platform_device *pdev)
 	palmas_usb->vbus_irq = regmap_irq_get_virq(palmas->irq_data,
 						PALMAS_VBUS_IRQ);
 
-	palmas_usb_wakeup(palmas, pdata->wakeup);
+	palmas_usb_wakeup(palmas, palmas_usb->wakeup);
 
 	platform_set_drvdata(pdev, palmas_usb);
 
-	palmas_usb->edev.name = "palmas-usb";
 	palmas_usb->edev.supported_cable = palmas_extcon_cable;
 	palmas_usb->edev.mutually_exclusive = mutually_exclusive;
 
@@ -182,28 +186,36 @@ static int palmas_usb_probe(struct platform_device *pdev)
 		return status;
 	}
 
-	status = devm_request_threaded_irq(palmas_usb->dev, palmas_usb->id_irq,
-			NULL, palmas_id_irq_handler,
-			IRQF_TRIGGER_FALLING | IRQF_TRIGGER_RISING,
-			"palmas_usb_id", palmas_usb);
-	if (status < 0) {
-		dev_err(&pdev->dev, "can't get IRQ %d, err %d\n",
+	if (palmas_usb->enable_id_detection) {
+		status = devm_request_threaded_irq(palmas_usb->dev,
+				palmas_usb->id_irq,
+				NULL, palmas_id_irq_handler,
+				IRQF_TRIGGER_FALLING | IRQF_TRIGGER_RISING |
+				IRQF_ONESHOT | IRQF_EARLY_RESUME,
+				"palmas_usb_id", palmas_usb);
+		if (status < 0) {
+			dev_err(&pdev->dev, "can't get IRQ %d, err %d\n",
 					palmas_usb->id_irq, status);
-		goto fail_extcon;
+			goto fail_extcon;
+		}
 	}
 
-	status = devm_request_threaded_irq(palmas_usb->dev,
-			palmas_usb->vbus_irq, NULL, palmas_vbus_irq_handler,
-			IRQF_TRIGGER_FALLING | IRQF_TRIGGER_RISING,
-			"palmas_usb_vbus", palmas_usb);
-	if (status < 0) {
-		dev_err(&pdev->dev, "can't get IRQ %d, err %d\n",
+	if (palmas_usb->enable_vbus_detection) {
+		status = devm_request_threaded_irq(palmas_usb->dev,
+				palmas_usb->vbus_irq, NULL,
+				palmas_vbus_irq_handler,
+				IRQF_TRIGGER_FALLING | IRQF_TRIGGER_RISING |
+				IRQF_ONESHOT | IRQF_EARLY_RESUME,
+				"palmas_usb_vbus", palmas_usb);
+		if (status < 0) {
+			dev_err(&pdev->dev, "can't get IRQ %d, err %d\n",
 					palmas_usb->vbus_irq, status);
-		goto fail_extcon;
+			goto fail_extcon;
+		}
 	}
 
 	palmas_enable_irq(palmas_usb);
-
+	device_set_wakeup_capable(&pdev->dev, true);
 	return 0;
 
 fail_extcon:
@@ -221,6 +233,39 @@ static int palmas_usb_remove(struct platform_device *pdev)
 	return 0;
 }
 
+#ifdef CONFIG_PM_SLEEP
+static int palmas_usb_suspend(struct device *dev)
+{
+	struct palmas_usb *palmas_usb = dev_get_drvdata(dev);
+
+	if (device_may_wakeup(dev)) {
+		if (palmas_usb->enable_vbus_detection)
+			enable_irq_wake(palmas_usb->vbus_irq);
+		if (palmas_usb->enable_id_detection)
+			enable_irq_wake(palmas_usb->id_irq);
+	}
+	return 0;
+}
+
+static int palmas_usb_resume(struct device *dev)
+{
+	struct palmas_usb *palmas_usb = dev_get_drvdata(dev);
+
+	if (device_may_wakeup(dev)) {
+		if (palmas_usb->enable_vbus_detection)
+			disable_irq_wake(palmas_usb->vbus_irq);
+		if (palmas_usb->enable_id_detection)
+			disable_irq_wake(palmas_usb->id_irq);
+	}
+	return 0;
+};
+#endif
+
+static const struct dev_pm_ops palmas_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(palmas_usb_suspend,
+				palmas_usb_resume)
+};
+
 static struct of_device_id of_palmas_match_tbl[] = {
 	{ .compatible = "ti,palmas-usb", },
 	{ .compatible = "ti,twl6035-usb", },
@@ -234,6 +279,7 @@ static struct platform_driver palmas_usb_driver = {
 		.name = "palmas-usb",
 		.of_match_table = of_palmas_match_tbl,
 		.owner = THIS_MODULE,
+		.pm = &palmas_pm_ops,
 	},
 };
 
diff --git a/drivers/extcon/of_extcon.c b/drivers/extcon/of_extcon.c
new file mode 100644
index 000000000000..72173ecbb311
--- /dev/null
+++ b/drivers/extcon/of_extcon.c
@@ -0,0 +1,64 @@
+/*
+ * OF helpers for External connector (extcon) framework
+ *
+ * Copyright (C) 2013 Texas Instruments, Inc.
+ * Kishon Vijay Abraham I <kishon@ti.com>
+ *
+ * Copyright (C) 2013 Samsung Electronics
+ * Chanwoo Choi <cw00.choi@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/err.h>
+#include <linux/extcon.h>
+#include <linux/of.h>
+#include <linux/of_platform.h>
+#include <linux/extcon/of_extcon.h>
+
+/*
+ * of_extcon_get_extcon_dev - Get the name of extcon device from devicetree
+ * @dev - instance to the given device
+ * @index - index into list of extcon_dev
+ *
+ * return the instance of extcon device
+ */
+struct extcon_dev *of_extcon_get_extcon_dev(struct device *dev, int index)
+{
+	struct device_node *node;
+	struct extcon_dev *edev;
+	struct platform_device *extcon_parent_dev;
+
+	if (!dev->of_node) {
+		dev_dbg(dev, "device does not have a device node entry\n");
+		return ERR_PTR(-EINVAL);
+	}
+
+	node = of_parse_phandle(dev->of_node, "extcon", index);
+	if (!node) {
+		dev_dbg(dev, "failed to get phandle in %s node\n",
+			dev->of_node->full_name);
+		return ERR_PTR(-ENODEV);
+	}
+
+	extcon_parent_dev = of_find_device_by_node(node);
+	if (!extcon_parent_dev) {
+		dev_dbg(dev, "unable to find device by node\n");
+		return ERR_PTR(-EPROBE_DEFER);
+	}
+
+	edev = extcon_get_extcon_dev(dev_name(&extcon_parent_dev->dev));
+	if (!edev) {
+		dev_dbg(dev, "unable to get extcon device : %s\n",
+				dev_name(&extcon_parent_dev->dev));
+		return ERR_PTR(-ENODEV);
+	}
+
+	return edev;
+}
+EXPORT_SYMBOL_GPL(of_extcon_get_extcon_dev);
diff --git a/drivers/firewire/core-cdev.c b/drivers/firewire/core-cdev.c
index ac1b43a04285..d7d5c8af92b9 100644
--- a/drivers/firewire/core-cdev.c
+++ b/drivers/firewire/core-cdev.c
@@ -486,7 +486,7 @@ static int ioctl_get_info(struct client *client, union ioctl_arg *arg)
 static int add_client_resource(struct client *client,
 			       struct client_resource *resource, gfp_t gfp_mask)
 {
-	bool preload = gfp_mask & __GFP_WAIT;
+	bool preload = !!(gfp_mask & __GFP_WAIT);
 	unsigned long flags;
 	int ret;
 
diff --git a/drivers/firewire/core-transaction.c b/drivers/firewire/core-transaction.c
index 28a94c7ec6e5..e5af0e3a26ec 100644
--- a/drivers/firewire/core-transaction.c
+++ b/drivers/firewire/core-transaction.c
@@ -1262,8 +1262,7 @@ static int __init fw_core_init(void)
 {
 	int ret;
 
-	fw_workqueue = alloc_workqueue("firewire",
-				       WQ_NON_REENTRANT | WQ_MEM_RECLAIM, 0);
+	fw_workqueue = alloc_workqueue("firewire", WQ_MEM_RECLAIM, 0);
 	if (!fw_workqueue)
 		return -ENOMEM;
 
diff --git a/drivers/firewire/ohci.c b/drivers/firewire/ohci.c
index afb701ec90ca..6aa8a86cb83b 100644
--- a/drivers/firewire/ohci.c
+++ b/drivers/firewire/ohci.c
@@ -235,13 +235,15 @@ struct fw_ohci {
 	dma_addr_t next_config_rom_bus;
 	__be32     next_header;
 
-	__le32    *self_id_cpu;
+	__le32    *self_id;
 	dma_addr_t self_id_bus;
 	struct work_struct bus_reset_work;
 
 	u32 self_id_buffer[512];
 };
 
+static struct workqueue_struct *selfid_workqueue;
+
 static inline struct fw_ohci *fw_ohci(struct fw_card *card)
 {
 	return container_of(card, struct fw_ohci, card);
@@ -271,6 +273,7 @@ static inline struct fw_ohci *fw_ohci(struct fw_card *card)
 
 static char ohci_driver_name[] = KBUILD_MODNAME;
 
+#define PCI_VENDOR_ID_PINNACLE_SYSTEMS	0x11bd
 #define PCI_DEVICE_ID_AGERE_FW643	0x5901
 #define PCI_DEVICE_ID_CREATIVE_SB1394	0x4001
 #define PCI_DEVICE_ID_JMICRON_JMB38X_FW	0x2380
@@ -278,17 +281,16 @@ static char ohci_driver_name[] = KBUILD_MODNAME;
 #define PCI_DEVICE_ID_TI_TSB12LV26	0x8020
 #define PCI_DEVICE_ID_TI_TSB82AA2	0x8025
 #define PCI_DEVICE_ID_VIA_VT630X	0x3044
-#define PCI_VENDOR_ID_PINNACLE_SYSTEMS	0x11bd
 #define PCI_REV_ID_VIA_VT6306		0x46
 
-#define QUIRK_CYCLE_TIMER		1
-#define QUIRK_RESET_PACKET		2
-#define QUIRK_BE_HEADERS		4
-#define QUIRK_NO_1394A			8
-#define QUIRK_NO_MSI			16
-#define QUIRK_TI_SLLZ059		32
-#define QUIRK_IR_WAKE			64
-#define QUIRK_PHY_LCTRL_TIMEOUT		128
+#define QUIRK_CYCLE_TIMER		0x1
+#define QUIRK_RESET_PACKET		0x2
+#define QUIRK_BE_HEADERS		0x4
+#define QUIRK_NO_1394A			0x8
+#define QUIRK_NO_MSI			0x10
+#define QUIRK_TI_SLLZ059		0x20
+#define QUIRK_IR_WAKE			0x40
+#define QUIRK_PHY_LCTRL_TIMEOUT		0x80
 
 /* In case of multiple matches in ohci_quirks[], only the first one is used. */
 static const struct {
@@ -1929,12 +1931,12 @@ static void bus_reset_work(struct work_struct *work)
 		return;
 	}
 
-	generation = (cond_le32_to_cpu(ohci->self_id_cpu[0]) >> 16) & 0xff;
+	generation = (cond_le32_to_cpu(ohci->self_id[0]) >> 16) & 0xff;
 	rmb();
 
 	for (i = 1, j = 0; j < self_id_count; i += 2, j++) {
-		u32 id  = cond_le32_to_cpu(ohci->self_id_cpu[i]);
-		u32 id2 = cond_le32_to_cpu(ohci->self_id_cpu[i + 1]);
+		u32 id  = cond_le32_to_cpu(ohci->self_id[i]);
+		u32 id2 = cond_le32_to_cpu(ohci->self_id[i + 1]);
 
 		if (id != ~id2) {
 			/*
@@ -2087,7 +2089,7 @@ static irqreturn_t irq_handler(int irq, void *data)
 	log_irqs(ohci, event);
 
 	if (event & OHCI1394_selfIDComplete)
-		queue_work(fw_workqueue, &ohci->bus_reset_work);
+		queue_work(selfid_workqueue, &ohci->bus_reset_work);
 
 	if (event & OHCI1394_RQPkt)
 		tasklet_schedule(&ohci->ar_request_ctx.tasklet);
@@ -3692,7 +3694,7 @@ static int pci_probe(struct pci_dev *dev,
 		goto fail_contexts;
 	}
 
-	ohci->self_id_cpu = ohci->misc_buffer     + PAGE_SIZE/2;
+	ohci->self_id     = ohci->misc_buffer     + PAGE_SIZE/2;
 	ohci->self_id_bus = ohci->misc_buffer_bus + PAGE_SIZE/2;
 
 	bus_options = reg_read(ohci, OHCI1394_BusOptions);
@@ -3870,7 +3872,23 @@ static struct pci_driver fw_ohci_pci_driver = {
 #endif
 };
 
-module_pci_driver(fw_ohci_pci_driver);
+static int __init fw_ohci_init(void)
+{
+	selfid_workqueue = alloc_workqueue(KBUILD_MODNAME, WQ_MEM_RECLAIM, 0);
+	if (!selfid_workqueue)
+		return -ENOMEM;
+
+	return pci_register_driver(&fw_ohci_pci_driver);
+}
+
+static void __exit fw_ohci_cleanup(void)
+{
+	pci_unregister_driver(&fw_ohci_pci_driver);
+	destroy_workqueue(selfid_workqueue);
+}
+
+module_init(fw_ohci_init);
+module_exit(fw_ohci_cleanup);
 
 MODULE_AUTHOR("Kristian Hoegsberg <krh@bitplanet.net>");
 MODULE_DESCRIPTION("Driver for PCI OHCI IEEE1394 controllers");
diff --git a/drivers/firmware/dcdbas.c b/drivers/firmware/dcdbas.c
index 8e77c02edb24..ff080ee20197 100644
--- a/drivers/firmware/dcdbas.c
+++ b/drivers/firmware/dcdbas.c
@@ -535,11 +535,12 @@ static struct attribute *dcdbas_dev_attrs[] = {
 
 static struct attribute_group dcdbas_attr_group = {
 	.attrs = dcdbas_dev_attrs,
+	.bin_attrs = dcdbas_bin_attrs,
 };
 
 static int dcdbas_probe(struct platform_device *dev)
 {
-	int i, error;
+	int error;
 
 	host_control_action = HC_ACTION_NONE;
 	host_control_smi_type = HC_SMITYPE_NONE;
@@ -555,18 +556,6 @@ static int dcdbas_probe(struct platform_device *dev)
 	if (error)
 		return error;
 
-	for (i = 0; dcdbas_bin_attrs[i]; i++) {
-		error = sysfs_create_bin_file(&dev->dev.kobj,
-					      dcdbas_bin_attrs[i]);
-		if (error) {
-			while (--i >= 0)
-				sysfs_remove_bin_file(&dev->dev.kobj,
-						      dcdbas_bin_attrs[i]);
-			sysfs_remove_group(&dev->dev.kobj, &dcdbas_attr_group);
-			return error;
-		}
-	}
-
 	register_reboot_notifier(&dcdbas_reboot_nb);
 
 	dev_info(&dev->dev, "%s (version %s)\n",
@@ -577,11 +566,7 @@ static int dcdbas_probe(struct platform_device *dev)
 
 static int dcdbas_remove(struct platform_device *dev)
 {
-	int i;
-
 	unregister_reboot_notifier(&dcdbas_reboot_nb);
-	for (i = 0; dcdbas_bin_attrs[i]; i++)
-		sysfs_remove_bin_file(&dev->dev.kobj, dcdbas_bin_attrs[i]);
 	sysfs_remove_group(&dev->dev.kobj, &dcdbas_attr_group);
 
 	return 0;
diff --git a/drivers/firmware/dmi_scan.c b/drivers/firmware/dmi_scan.c
index 232fa8fce26a..fa0affb699b4 100644
--- a/drivers/firmware/dmi_scan.c
+++ b/drivers/firmware/dmi_scan.c
@@ -14,7 +14,7 @@
  * of and an antecedent to, SMBIOS, which stands for System
  * Management BIOS.  See further: http://www.dmtf.org/standards
  */
-static char dmi_empty_string[] = "        ";
+static const char dmi_empty_string[] = "        ";
 
 static u16 __initdata dmi_ver;
 /*
@@ -49,7 +49,7 @@ static const char * __init dmi_string_nosave(const struct dmi_header *dm, u8 s)
 	return "";
 }
 
-static char * __init dmi_string(const struct dmi_header *dm, u8 s)
+static const char * __init dmi_string(const struct dmi_header *dm, u8 s)
 {
 	const char *bp = dmi_string_nosave(dm, s);
 	char *str;
@@ -62,8 +62,6 @@ static char * __init dmi_string(const struct dmi_header *dm, u8 s)
 	str = dmi_alloc(len);
 	if (str != NULL)
 		strcpy(str, bp);
-	else
-		printk(KERN_ERR "dmi_string: cannot allocate %Zu bytes.\n", len);
 
 	return str;
 }
@@ -133,17 +131,18 @@ static int __init dmi_checksum(const u8 *buf, u8 len)
 	return sum == 0;
 }
 
-static char *dmi_ident[DMI_STRING_MAX];
+static const char *dmi_ident[DMI_STRING_MAX];
 static LIST_HEAD(dmi_devices);
 int dmi_available;
 
 /*
  *	Save a DMI string
  */
-static void __init dmi_save_ident(const struct dmi_header *dm, int slot, int string)
+static void __init dmi_save_ident(const struct dmi_header *dm, int slot,
+		int string)
 {
-	const char *d = (const char*) dm;
-	char *p;
+	const char *d = (const char *) dm;
+	const char *p;
 
 	if (dmi_ident[slot])
 		return;
@@ -155,9 +154,10 @@ static void __init dmi_save_ident(const struct dmi_header *dm, int slot, int str
 	dmi_ident[slot] = p;
 }
 
-static void __init dmi_save_uuid(const struct dmi_header *dm, int slot, int index)
+static void __init dmi_save_uuid(const struct dmi_header *dm, int slot,
+		int index)
 {
-	const u8 *d = (u8*) dm + index;
+	const u8 *d = (u8 *) dm + index;
 	char *s;
 	int is_ff = 1, is_00 = 1, i;
 
@@ -188,12 +188,13 @@ static void __init dmi_save_uuid(const struct dmi_header *dm, int slot, int inde
 	else
 		sprintf(s, "%pUB", d);
 
-        dmi_ident[slot] = s;
+	dmi_ident[slot] = s;
 }
 
-static void __init dmi_save_type(const struct dmi_header *dm, int slot, int index)
+static void __init dmi_save_type(const struct dmi_header *dm, int slot,
+		int index)
 {
-	const u8 *d = (u8*) dm + index;
+	const u8 *d = (u8 *) dm + index;
 	char *s;
 
 	if (dmi_ident[slot])
@@ -216,10 +217,8 @@ static void __init dmi_save_one_device(int type, const char *name)
 		return;
 
 	dev = dmi_alloc(sizeof(*dev) + strlen(name) + 1);
-	if (!dev) {
-		printk(KERN_ERR "dmi_save_one_device: out of memory.\n");
+	if (!dev)
 		return;
-	}
 
 	dev->type = type;
 	strcpy((char *)(dev + 1), name);
@@ -249,17 +248,14 @@ static void __init dmi_save_oem_strings_devices(const struct dmi_header *dm)
 	struct dmi_device *dev;
 
 	for (i = 1; i <= count; i++) {
-		char *devname = dmi_string(dm, i);
+		const char *devname = dmi_string(dm, i);
 
 		if (devname == dmi_empty_string)
 			continue;
 
 		dev = dmi_alloc(sizeof(*dev));
-		if (!dev) {
-			printk(KERN_ERR
-			   "dmi_save_oem_strings_devices: out of memory.\n");
+		if (!dev)
 			break;
-		}
 
 		dev->type = DMI_DEV_TYPE_OEM_STRING;
 		dev->name = devname;
@@ -272,21 +268,17 @@ static void __init dmi_save_oem_strings_devices(const struct dmi_header *dm)
 static void __init dmi_save_ipmi_device(const struct dmi_header *dm)
 {
 	struct dmi_device *dev;
-	void * data;
+	void *data;
 
 	data = dmi_alloc(dm->length);
-	if (data == NULL) {
-		printk(KERN_ERR "dmi_save_ipmi_device: out of memory.\n");
+	if (data == NULL)
 		return;
-	}
 
 	memcpy(data, dm, dm->length);
 
 	dev = dmi_alloc(sizeof(*dev));
-	if (!dev) {
-		printk(KERN_ERR "dmi_save_ipmi_device: out of memory.\n");
+	if (!dev)
 		return;
-	}
 
 	dev->type = DMI_DEV_TYPE_IPMI;
 	dev->name = "IPMI controller";
@@ -301,10 +293,9 @@ static void __init dmi_save_dev_onboard(int instance, int segment, int bus,
 	struct dmi_dev_onboard *onboard_dev;
 
 	onboard_dev = dmi_alloc(sizeof(*onboard_dev) + strlen(name) + 1);
-	if (!onboard_dev) {
-		printk(KERN_ERR "dmi_save_dev_onboard: out of memory.\n");
+	if (!onboard_dev)
 		return;
-	}
+
 	onboard_dev->instance = instance;
 	onboard_dev->segment = segment;
 	onboard_dev->bus = bus;
@@ -320,7 +311,7 @@ static void __init dmi_save_dev_onboard(int instance, int segment, int bus,
 
 static void __init dmi_save_extended_devices(const struct dmi_header *dm)
 {
-	const u8 *d = (u8*) dm + 5;
+	const u8 *d = (u8 *) dm + 5;
 
 	/* Skip disabled device */
 	if ((*d & 0x80) == 0)
@@ -338,7 +329,7 @@ static void __init dmi_save_extended_devices(const struct dmi_header *dm)
  */
 static void __init dmi_decode(const struct dmi_header *dm, void *dummy)
 {
-	switch(dm->type) {
+	switch (dm->type) {
 	case 0:		/* BIOS Information */
 		dmi_save_ident(dm, DMI_BIOS_VENDOR, 4);
 		dmi_save_ident(dm, DMI_BIOS_VERSION, 5);
@@ -502,13 +493,7 @@ void __init dmi_scan_machine(void)
 			dmi_available = 1;
 			goto out;
 		}
-	}
-	else {
-		/*
-		 * no iounmap() for that ioremap(); it would be a no-op, but
-		 * it's so early in setup that sucker gets confused into doing
-		 * what it shouldn't if we actually call it.
-		 */
+	} else {
 		p = dmi_ioremap(0xF0000, 0x10000);
 		if (p == NULL)
 			goto error;
@@ -533,7 +518,7 @@ void __init dmi_scan_machine(void)
 		dmi_iounmap(p, 0x10000);
 	}
  error:
-	printk(KERN_INFO "DMI not present or invalid.\n");
+	pr_info("DMI not present or invalid.\n");
  out:
 	dmi_initialized = 1;
 }
@@ -669,7 +654,7 @@ int dmi_name_in_serial(const char *str)
 
 /**
  *	dmi_name_in_vendors - Check if string is in the DMI system or board vendor name
- *	@str: 	Case sensitive Name
+ *	@str: Case sensitive Name
  */
 int dmi_name_in_vendors(const char *str)
 {
@@ -696,13 +681,13 @@ EXPORT_SYMBOL(dmi_name_in_vendors);
  *	A new search is initiated by passing %NULL as the @from argument.
  *	If @from is not %NULL, searches continue from next device.
  */
-const struct dmi_device * dmi_find_device(int type, const char *name,
+const struct dmi_device *dmi_find_device(int type, const char *name,
 				    const struct dmi_device *from)
 {
 	const struct list_head *head = from ? &from->list : &dmi_devices;
 	struct list_head *d;
 
-	for(d = head->next; d != &dmi_devices; d = d->next) {
+	for (d = head->next; d != &dmi_devices; d = d->next) {
 		const struct dmi_device *dev =
 			list_entry(d, struct dmi_device, list);
 
diff --git a/drivers/firmware/efi/efi-pstore.c b/drivers/firmware/efi/efi-pstore.c
index 73de5a9c2247..5002d50e3781 100644
--- a/drivers/firmware/efi/efi-pstore.c
+++ b/drivers/firmware/efi/efi-pstore.c
@@ -35,6 +35,7 @@ struct pstore_read_data {
 	enum pstore_type_id *type;
 	int *count;
 	struct timespec *timespec;
+	bool *compressed;
 	char **buf;
 };
 
@@ -42,7 +43,7 @@ static int efi_pstore_read_func(struct efivar_entry *entry, void *data)
 {
 	efi_guid_t vendor = LINUX_EFI_CRASH_GUID;
 	struct pstore_read_data *cb_data = data;
-	char name[DUMP_NAME_LEN];
+	char name[DUMP_NAME_LEN], data_type;
 	int i;
 	int cnt;
 	unsigned int part;
@@ -54,12 +55,23 @@ static int efi_pstore_read_func(struct efivar_entry *entry, void *data)
 	for (i = 0; i < DUMP_NAME_LEN; i++)
 		name[i] = entry->var.VariableName[i];
 
-	if (sscanf(name, "dump-type%u-%u-%d-%lu",
+	if (sscanf(name, "dump-type%u-%u-%d-%lu-%c",
+		   cb_data->type, &part, &cnt, &time, &data_type) == 5) {
+		*cb_data->id = part;
+		*cb_data->count = cnt;
+		cb_data->timespec->tv_sec = time;
+		cb_data->timespec->tv_nsec = 0;
+		if (data_type == 'C')
+			*cb_data->compressed = true;
+		else
+			*cb_data->compressed = false;
+	} else if (sscanf(name, "dump-type%u-%u-%d-%lu",
 		   cb_data->type, &part, &cnt, &time) == 4) {
 		*cb_data->id = part;
 		*cb_data->count = cnt;
 		cb_data->timespec->tv_sec = time;
 		cb_data->timespec->tv_nsec = 0;
+		*cb_data->compressed = false;
 	} else if (sscanf(name, "dump-type%u-%u-%lu",
 			  cb_data->type, &part, &time) == 3) {
 		/*
@@ -71,6 +83,7 @@ static int efi_pstore_read_func(struct efivar_entry *entry, void *data)
 		*cb_data->count = 0;
 		cb_data->timespec->tv_sec = time;
 		cb_data->timespec->tv_nsec = 0;
+		*cb_data->compressed = false;
 	} else
 		return 0;
 
@@ -87,7 +100,8 @@ static int efi_pstore_read_func(struct efivar_entry *entry, void *data)
 
 static ssize_t efi_pstore_read(u64 *id, enum pstore_type_id *type,
 			       int *count, struct timespec *timespec,
-			       char **buf, struct pstore_info *psi)
+			       char **buf, bool *compressed,
+			       struct pstore_info *psi)
 {
 	struct pstore_read_data data;
 
@@ -95,6 +109,7 @@ static ssize_t efi_pstore_read(u64 *id, enum pstore_type_id *type,
 	data.type = type;
 	data.count = count;
 	data.timespec = timespec;
+	data.compressed = compressed;
 	data.buf = buf;
 
 	return __efivar_entry_iter(efi_pstore_read_func, &efivar_sysfs_list, &data,
@@ -103,7 +118,7 @@ static ssize_t efi_pstore_read(u64 *id, enum pstore_type_id *type,
 
 static int efi_pstore_write(enum pstore_type_id type,
 		enum kmsg_dump_reason reason, u64 *id,
-		unsigned int part, int count, size_t hsize, size_t size,
+		unsigned int part, int count, bool compressed, size_t size,
 		struct pstore_info *psi)
 {
 	char name[DUMP_NAME_LEN];
@@ -111,8 +126,8 @@ static int efi_pstore_write(enum pstore_type_id type,
 	efi_guid_t vendor = LINUX_EFI_CRASH_GUID;
 	int i, ret = 0;
 
-	sprintf(name, "dump-type%u-%u-%d-%lu", type, part, count,
-		get_seconds());
+	sprintf(name, "dump-type%u-%u-%d-%lu-%c", type, part, count,
+		get_seconds(), compressed ? 'C' : 'D');
 
 	for (i = 0; i < DUMP_NAME_LEN; i++)
 		efi_name[i] = name[i];
diff --git a/drivers/firmware/google/gsmi.c b/drivers/firmware/google/gsmi.c
index acba0b9f4406..6eb535ffeddc 100644
--- a/drivers/firmware/google/gsmi.c
+++ b/drivers/firmware/google/gsmi.c
@@ -525,7 +525,7 @@ static ssize_t gsmi_clear_eventlog_store(struct kobject *kobj,
 		u32 data_type;
 	} param;
 
-	rc = strict_strtoul(buf, 0, &val);
+	rc = kstrtoul(buf, 0, &val);
 	if (rc)
 		return rc;
 
diff --git a/drivers/fmc/fmc-chardev.c b/drivers/fmc/fmc-chardev.c
index cc031db2d2a3..ace6ef24d15e 100644
--- a/drivers/fmc/fmc-chardev.c
+++ b/drivers/fmc/fmc-chardev.c
@@ -143,18 +143,17 @@ static int fc_probe(struct fmc_device *fmc)
 	fc->misc.fops = &fc_fops;
 	fc->misc.name = kstrdup(dev_name(&fmc->dev), GFP_KERNEL);
 
-	spin_lock(&fc_lock);
 	ret = misc_register(&fc->misc);
 	if (ret < 0)
-		goto err_unlock;
+		goto out;
+	spin_lock(&fc_lock);
 	list_add(&fc->list, &fc_devices);
 	spin_unlock(&fc_lock);
 	dev_info(&fc->fmc->dev, "Created misc device \"%s\"\n",
 		 fc->misc.name);
 	return 0;
 
-err_unlock:
-	spin_unlock(&fc_lock);
+out:
 	kfree(fc->misc.name);
 	kfree(fc);
 	return ret;
@@ -174,10 +173,10 @@ static int fc_remove(struct fmc_device *fmc)
 
 	spin_lock(&fc_lock);
 	list_del(&fc->list);
+	spin_unlock(&fc_lock);
 	misc_deregister(&fc->misc);
 	kfree(fc->misc.name);
 	kfree(fc);
-	spin_unlock(&fc_lock);
 
 	return 0;
 }
diff --git a/drivers/fmc/fmc-write-eeprom.c b/drivers/fmc/fmc-write-eeprom.c
index 2cc680dd604d..ee5b47904130 100644
--- a/drivers/fmc/fmc-write-eeprom.c
+++ b/drivers/fmc/fmc-write-eeprom.c
@@ -103,7 +103,7 @@ static int fwe_run(struct fmc_device *fmc, const struct firmware *fw, char *s)
  * difficult to know in advance when probing the first card if others
  * are there.
  */
-int fwe_probe(struct fmc_device *fmc)
+static int fwe_probe(struct fmc_device *fmc)
 {
 	int err, index = 0;
 	const struct firmware *fw;
@@ -144,7 +144,7 @@ int fwe_probe(struct fmc_device *fmc)
 	return 0;
 }
 
-int fwe_remove(struct fmc_device *fmc)
+static int fwe_remove(struct fmc_device *fmc)
 {
 	return 0;
 }
diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig
index b2450ba14138..b6ed304863eb 100644
--- a/drivers/gpio/Kconfig
+++ b/drivers/gpio/Kconfig
@@ -146,6 +146,16 @@ config GPIO_MM_LANTIQ
 	  (EBU) found on Lantiq SoCs. The gpios are output only as they are
 	  created by attaching a 16bit latch to the bus.
 
+config GPIO_F7188X
+	tristate "F71882FG and F71889F GPIO support"
+	depends on X86
+	help
+	  This option enables support for GPIOs found on Fintek Super-I/O
+	  chips F71882FG and F71889F.
+
+	  To compile this driver as a module, choose M here: the module will
+	  be called f7188x-gpio.
+
 config GPIO_MPC5200
 	def_bool y
 	depends on PPC_MPC52xx
@@ -193,6 +203,14 @@ config GPIO_MXS
 	select GPIO_GENERIC
 	select GENERIC_IRQ_CHIP
 
+config GPIO_OCTEON
+	tristate "Cavium OCTEON GPIO"
+	depends on GPIOLIB && CAVIUM_OCTEON_SOC
+	default y
+	help
+	  Say yes here to support the on-chip GPIO lines on the OCTEON
+	  family of SOCs.
+
 config GPIO_PL061
 	bool "PrimeCell PL061 GPIO support"
 	depends on ARM && ARM_AMBA
@@ -242,6 +260,21 @@ config GPIO_TS5500
 	  blocks of the TS-5500: DIO1, DIO2 and the LCD port, and the TS-5600
 	  LCD port.
 
+config GPIO_TZ1090
+	bool "Toumaz Xenif TZ1090 GPIO support"
+	depends on SOC_TZ1090
+	select GENERIC_IRQ_CHIP
+	default y
+	help
+	  Say yes here to support Toumaz Xenif TZ1090 GPIOs.
+
+config GPIO_TZ1090_PDC
+	bool "Toumaz Xenif TZ1090 PDC GPIO support"
+	depends on SOC_TZ1090
+	default y
+	help
+	  Say yes here to support Toumaz Xenif TZ1090 PDC GPIOs.
+
 config GPIO_XILINX
 	bool "Xilinx GPIO support"
 	depends on PPC_OF || MICROBLAZE || ARCH_ZYNQ
@@ -289,7 +322,7 @@ config GPIO_ICH
 
 config GPIO_VX855
 	tristate "VIA VX855/VX875 GPIO"
-	depends on PCI && GENERIC_HARDIRQS
+	depends on PCI
 	select MFD_CORE
 	select MFD_VX855
 	help
@@ -363,7 +396,7 @@ config GPIO_MAX732X
 
 config GPIO_MAX732X_IRQ
 	bool "Interrupt controller support for MAX732x"
-	depends on GPIO_MAX732X=y && GENERIC_HARDIRQS
+	depends on GPIO_MAX732X=y
 	help
 	  Say yes here to enable the max732x to be used as an interrupt
 	  controller. It requires the driver to be built in the kernel.
@@ -628,7 +661,7 @@ config GPIO_TIMBERDALE
 
 config GPIO_RDC321X
 	tristate "RDC R-321x GPIO support"
-	depends on PCI && GENERIC_HARDIRQS
+	depends on PCI
 	select MFD_CORE
 	select MFD_RDC321X
 	help
@@ -676,6 +709,18 @@ config GPIO_UCB1400
 	  This enables support for the Philips UCB1400 GPIO pins.
 	  The UCB1400 is an AC97 audio codec.
 
+comment "LPC GPIO expanders:"
+
+config GPIO_KEMPLD
+	tristate "Kontron ETX / COMexpress GPIO"
+	depends on MFD_KEMPLD
+	help
+	  This enables support for the PLD GPIO interface on some Kontron ETX
+	  and COMexpress (ETXexpress) modules.
+
+	  This driver can also be built as a module. If so, the module will be
+	  called gpio-kempld.
+
 comment "MODULbus GPIO expanders:"
 
 config GPIO_JANZ_TTL
diff --git a/drivers/gpio/Makefile b/drivers/gpio/Makefile
index ef3e983a2f1e..98e23ebba2cf 100644
--- a/drivers/gpio/Makefile
+++ b/drivers/gpio/Makefile
@@ -24,11 +24,13 @@ obj-$(CONFIG_GPIO_DA9055)	+= gpio-da9055.o
 obj-$(CONFIG_ARCH_DAVINCI)	+= gpio-davinci.o
 obj-$(CONFIG_GPIO_EM)		+= gpio-em.o
 obj-$(CONFIG_GPIO_EP93XX)	+= gpio-ep93xx.o
+obj-$(CONFIG_GPIO_F7188X)	+= gpio-f7188x.o
 obj-$(CONFIG_GPIO_GE_FPGA)	+= gpio-ge.o
 obj-$(CONFIG_GPIO_GRGPIO)	+= gpio-grgpio.o
 obj-$(CONFIG_GPIO_ICH)		+= gpio-ich.o
 obj-$(CONFIG_GPIO_IT8761E)	+= gpio-it8761e.o
 obj-$(CONFIG_GPIO_JANZ_TTL)	+= gpio-janz-ttl.o
+obj-$(CONFIG_GPIO_KEMPLD)	+= gpio-kempld.o
 obj-$(CONFIG_ARCH_KS8695)	+= gpio-ks8695.o
 obj-$(CONFIG_GPIO_LANGWELL)	+= gpio-langwell.o
 obj-$(CONFIG_ARCH_LPC32XX)	+= gpio-lpc32xx.o
@@ -50,6 +52,7 @@ obj-$(CONFIG_GPIO_MSM_V2)	+= gpio-msm-v2.o
 obj-$(CONFIG_GPIO_MVEBU)        += gpio-mvebu.o
 obj-$(CONFIG_GPIO_MXC)		+= gpio-mxc.o
 obj-$(CONFIG_GPIO_MXS)		+= gpio-mxs.o
+obj-$(CONFIG_GPIO_OCTEON)	+= gpio-octeon.o
 obj-$(CONFIG_ARCH_OMAP)		+= gpio-omap.o
 obj-$(CONFIG_GPIO_PCA953X)	+= gpio-pca953x.o
 obj-$(CONFIG_GPIO_PCF857X)	+= gpio-pcf857x.o
@@ -79,6 +82,8 @@ obj-$(CONFIG_GPIO_TPS65912)	+= gpio-tps65912.o
 obj-$(CONFIG_GPIO_TS5500)	+= gpio-ts5500.o
 obj-$(CONFIG_GPIO_TWL4030)	+= gpio-twl4030.o
 obj-$(CONFIG_GPIO_TWL6040)	+= gpio-twl6040.o
+obj-$(CONFIG_GPIO_TZ1090)	+= gpio-tz1090.o
+obj-$(CONFIG_GPIO_TZ1090_PDC)	+= gpio-tz1090-pdc.o
 obj-$(CONFIG_GPIO_UCB1400)	+= gpio-ucb1400.o
 obj-$(CONFIG_GPIO_VIPERBOARD)	+= gpio-viperboard.o
 obj-$(CONFIG_GPIO_VR41XX)	+= gpio-vr41xx.o
diff --git a/drivers/gpio/gpio-74x164.c b/drivers/gpio/gpio-74x164.c
index 721607904d0a..5d518d5db7a0 100644
--- a/drivers/gpio/gpio-74x164.c
+++ b/drivers/gpio/gpio-74x164.c
@@ -129,7 +129,7 @@ static int gen_74x164_probe(struct spi_device *spi)
 	if (!chip)
 		return -ENOMEM;
 
-	pdata = spi->dev.platform_data;
+	pdata = dev_get_platdata(&spi->dev);
 	if (pdata && pdata->base)
 		chip->gpio_chip.base = pdata->base;
 	else
diff --git a/drivers/gpio/gpio-adnp.c b/drivers/gpio/gpio-adnp.c
index e60567fc5073..c0f3fc44ab0e 100644
--- a/drivers/gpio/gpio-adnp.c
+++ b/drivers/gpio/gpio-adnp.c
@@ -490,15 +490,11 @@ static int adnp_irq_setup(struct adnp *adnp)
 	if (err != 0) {
 		dev_err(chip->dev, "can't request IRQ#%d: %d\n",
 			adnp->client->irq, err);
-		goto error;
+		return err;
 	}
 
 	chip->to_irq = adnp_gpio_to_irq;
 	return 0;
-
-error:
-	irq_domain_remove(adnp->domain);
-	return err;
 }
 
 static void adnp_irq_teardown(struct adnp *adnp)
diff --git a/drivers/gpio/gpio-adp5520.c b/drivers/gpio/gpio-adp5520.c
index f33f78dcadaa..084337d5514d 100644
--- a/drivers/gpio/gpio-adp5520.c
+++ b/drivers/gpio/gpio-adp5520.c
@@ -89,7 +89,7 @@ static int adp5520_gpio_direction_output(struct gpio_chip *chip,
 
 static int adp5520_gpio_probe(struct platform_device *pdev)
 {
-	struct adp5520_gpio_platform_data *pdata = pdev->dev.platform_data;
+	struct adp5520_gpio_platform_data *pdata = dev_get_platdata(&pdev->dev);
 	struct adp5520_gpio *dev;
 	struct gpio_chip *gc;
 	int ret, i, gpios;
diff --git a/drivers/gpio/gpio-adp5588.c b/drivers/gpio/gpio-adp5588.c
index 2ba56987db04..90fc4c99c024 100644
--- a/drivers/gpio/gpio-adp5588.c
+++ b/drivers/gpio/gpio-adp5588.c
@@ -276,7 +276,8 @@ static irqreturn_t adp5588_irq_handler(int irq, void *devid)
 static int adp5588_irq_setup(struct adp5588_gpio *dev)
 {
 	struct i2c_client *client = dev->client;
-	struct adp5588_gpio_platform_data *pdata = client->dev.platform_data;
+	struct adp5588_gpio_platform_data *pdata =
+			dev_get_platdata(&client->dev);
 	unsigned gpio;
 	int ret;
 
@@ -349,7 +350,8 @@ static void adp5588_irq_teardown(struct adp5588_gpio *dev)
 static int adp5588_gpio_probe(struct i2c_client *client,
 					const struct i2c_device_id *id)
 {
-	struct adp5588_gpio_platform_data *pdata = client->dev.platform_data;
+	struct adp5588_gpio_platform_data *pdata =
+			dev_get_platdata(&client->dev);
 	struct adp5588_gpio *dev;
 	struct gpio_chip *gc;
 	int ret, i, revid;
@@ -440,7 +442,8 @@ err:
 
 static int adp5588_gpio_remove(struct i2c_client *client)
 {
-	struct adp5588_gpio_platform_data *pdata = client->dev.platform_data;
+	struct adp5588_gpio_platform_data *pdata =
+			dev_get_platdata(&client->dev);
 	struct adp5588_gpio *dev = i2c_get_clientdata(client);
 	int ret;
 
diff --git a/drivers/gpio/gpio-arizona.c b/drivers/gpio/gpio-arizona.c
index 0ea853f68db2..fa8b6a762761 100644
--- a/drivers/gpio/gpio-arizona.c
+++ b/drivers/gpio/gpio-arizona.c
@@ -97,7 +97,7 @@ static struct gpio_chip template_chip = {
 static int arizona_gpio_probe(struct platform_device *pdev)
 {
 	struct arizona *arizona = dev_get_drvdata(pdev->dev.parent);
-	struct arizona_pdata *pdata = arizona->dev->platform_data;
+	struct arizona_pdata *pdata = dev_get_platdata(arizona->dev);
 	struct arizona_gpio *arizona_gpio;
 	int ret;
 
diff --git a/drivers/gpio/gpio-da9052.c b/drivers/gpio/gpio-da9052.c
index 29b11e9b6a78..9b77dc05d4ad 100644
--- a/drivers/gpio/gpio-da9052.c
+++ b/drivers/gpio/gpio-da9052.c
@@ -216,7 +216,7 @@ static int da9052_gpio_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	gpio->da9052 = dev_get_drvdata(pdev->dev.parent);
-	pdata = gpio->da9052->dev->platform_data;
+	pdata = dev_get_platdata(gpio->da9052->dev);
 
 	gpio->gp = reference_gp;
 	if (pdata && pdata->gpio_base)
diff --git a/drivers/gpio/gpio-da9055.c b/drivers/gpio/gpio-da9055.c
index fd6dfe382f13..7ef0820032bd 100644
--- a/drivers/gpio/gpio-da9055.c
+++ b/drivers/gpio/gpio-da9055.c
@@ -150,7 +150,7 @@ static int da9055_gpio_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	gpio->da9055 = dev_get_drvdata(pdev->dev.parent);
-	pdata = gpio->da9055->dev->platform_data;
+	pdata = dev_get_platdata(gpio->da9055->dev);
 
 	gpio->gp = reference_gp;
 	if (pdata && pdata->gpio_base)
diff --git a/drivers/gpio/gpio-em.c b/drivers/gpio/gpio-em.c
index 5cba855638bf..c6e1f086efe8 100644
--- a/drivers/gpio/gpio-em.c
+++ b/drivers/gpio/gpio-em.c
@@ -30,6 +30,7 @@
 #include <linux/gpio.h>
 #include <linux/slab.h>
 #include <linux/module.h>
+#include <linux/pinctrl/consumer.h>
 #include <linux/platform_data/gpio-em.h>
 
 struct em_gio_priv {
@@ -216,6 +217,21 @@ static int em_gio_to_irq(struct gpio_chip *chip, unsigned offset)
 	return irq_create_mapping(gpio_to_priv(chip)->irq_domain, offset);
 }
 
+static int em_gio_request(struct gpio_chip *chip, unsigned offset)
+{
+	return pinctrl_request_gpio(chip->base + offset);
+}
+
+static void em_gio_free(struct gpio_chip *chip, unsigned offset)
+{
+	pinctrl_free_gpio(chip->base + offset);
+
+	/* Set the GPIO as an input to ensure that the next GPIO request won't
+	* drive the GPIO pin as an output.
+	*/
+	em_gio_direction_input(chip, offset);
+}
+
 static int em_gio_irq_domain_map(struct irq_domain *h, unsigned int virq,
 				 irq_hw_number_t hw)
 {
@@ -237,7 +253,7 @@ static struct irq_domain_ops em_gio_irq_domain_ops = {
 static int em_gio_probe(struct platform_device *pdev)
 {
 	struct gpio_em_config pdata_dt;
-	struct gpio_em_config *pdata = pdev->dev.platform_data;
+	struct gpio_em_config *pdata = dev_get_platdata(&pdev->dev);
 	struct em_gio_priv *p;
 	struct resource *io[2], *irq[2];
 	struct gpio_chip *gpio_chip;
@@ -308,6 +324,8 @@ static int em_gio_probe(struct platform_device *pdev)
 	gpio_chip->direction_output = em_gio_direction_output;
 	gpio_chip->set = em_gio_set;
 	gpio_chip->to_irq = em_gio_to_irq;
+	gpio_chip->request = em_gio_request;
+	gpio_chip->free = em_gio_free;
 	gpio_chip->label = name;
 	gpio_chip->owner = THIS_MODULE;
 	gpio_chip->base = pdata->gpio_base;
@@ -351,6 +369,13 @@ static int em_gio_probe(struct platform_device *pdev)
 		dev_err(&pdev->dev, "failed to add GPIO controller\n");
 		goto err1;
 	}
+
+	if (pdata->pctl_name) {
+		ret = gpiochip_add_pin_range(gpio_chip, pdata->pctl_name, 0,
+					     gpio_chip->base, gpio_chip->ngpio);
+		if (ret < 0)
+			dev_warn(&pdev->dev, "failed to add pin range\n");
+	}
 	return 0;
 
 err1:
diff --git a/drivers/gpio/gpio-f7188x.c b/drivers/gpio/gpio-f7188x.c
new file mode 100644
index 000000000000..9cb8320e1181
--- /dev/null
+++ b/drivers/gpio/gpio-f7188x.c
@@ -0,0 +1,469 @@
+/*
+ * GPIO driver for Fintek Super-I/O F71882 and F71889
+ *
+ * Copyright (C) 2010-2013 LaCie
+ *
+ * Author: Simon Guinot <simon.guinot@sequanux.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/platform_device.h>
+#include <linux/io.h>
+#include <linux/gpio.h>
+
+#define DRVNAME "gpio-f7188x"
+
+/*
+ * Super-I/O registers
+ */
+#define SIO_LDSEL		0x07	/* Logical device select */
+#define SIO_DEVID		0x20	/* Device ID (2 bytes) */
+#define SIO_DEVREV		0x22	/* Device revision */
+#define SIO_MANID		0x23	/* Fintek ID (2 bytes) */
+
+#define SIO_LD_GPIO		0x06	/* GPIO logical device */
+#define SIO_UNLOCK_KEY		0x87	/* Key to enable Super-I/O */
+#define SIO_LOCK_KEY		0xAA	/* Key to disable Super-I/O */
+
+#define SIO_FINTEK_ID		0x1934	/* Manufacturer ID */
+#define SIO_F71882_ID		0x0541	/* F71882 chipset ID */
+#define SIO_F71889_ID		0x0909	/* F71889 chipset ID */
+
+enum chips { f71882fg, f71889f };
+
+static const char * const f7188x_names[] = {
+	"f71882fg",
+	"f71889f",
+};
+
+struct f7188x_sio {
+	int addr;
+	enum chips type;
+};
+
+struct f7188x_gpio_bank {
+	struct gpio_chip chip;
+	unsigned int regbase;
+	struct f7188x_gpio_data *data;
+};
+
+struct f7188x_gpio_data {
+	struct f7188x_sio *sio;
+	int nr_bank;
+	struct f7188x_gpio_bank *bank;
+};
+
+/*
+ * Super-I/O functions.
+ */
+
+static inline int superio_inb(int base, int reg)
+{
+	outb(reg, base);
+	return inb(base + 1);
+}
+
+static int superio_inw(int base, int reg)
+{
+	int val;
+
+	outb(reg++, base);
+	val = inb(base + 1) << 8;
+	outb(reg, base);
+	val |= inb(base + 1);
+
+	return val;
+}
+
+static inline void superio_outb(int base, int reg, int val)
+{
+	outb(reg, base);
+	outb(val, base + 1);
+}
+
+static inline int superio_enter(int base)
+{
+	/* Don't step on other drivers' I/O space by accident. */
+	if (!request_muxed_region(base, 2, DRVNAME)) {
+		pr_err(DRVNAME "I/O address 0x%04x already in use\n", base);
+		return -EBUSY;
+	}
+
+	/* According to the datasheet the key must be send twice. */
+	outb(SIO_UNLOCK_KEY, base);
+	outb(SIO_UNLOCK_KEY, base);
+
+	return 0;
+}
+
+static inline void superio_select(int base, int ld)
+{
+	outb(SIO_LDSEL, base);
+	outb(ld, base + 1);
+}
+
+static inline void superio_exit(int base)
+{
+	outb(SIO_LOCK_KEY, base);
+	release_region(base, 2);
+}
+
+/*
+ * GPIO chip.
+ */
+
+static int f7188x_gpio_direction_in(struct gpio_chip *chip, unsigned offset);
+static int f7188x_gpio_get(struct gpio_chip *chip, unsigned offset);
+static int f7188x_gpio_direction_out(struct gpio_chip *chip,
+				     unsigned offset, int value);
+static void f7188x_gpio_set(struct gpio_chip *chip, unsigned offset, int value);
+
+#define F7188X_GPIO_BANK(_base, _ngpio, _regbase)			\
+	{								\
+		.chip = {						\
+			.label            = DRVNAME,			\
+			.owner            = THIS_MODULE,		\
+			.direction_input  = f7188x_gpio_direction_in,	\
+			.get              = f7188x_gpio_get,		\
+			.direction_output = f7188x_gpio_direction_out,	\
+			.set              = f7188x_gpio_set,		\
+			.base             = _base,			\
+			.ngpio            = _ngpio,			\
+		},							\
+		.regbase = _regbase,					\
+	}
+
+#define gpio_dir(base) (base + 0)
+#define gpio_data_out(base) (base + 1)
+#define gpio_data_in(base) (base + 2)
+/* Output mode register (0:open drain 1:push-pull). */
+#define gpio_out_mode(base) (base + 3)
+
+static struct f7188x_gpio_bank f71882_gpio_bank[] = {
+	F7188X_GPIO_BANK(0 , 8, 0xF0),
+	F7188X_GPIO_BANK(10, 8, 0xE0),
+	F7188X_GPIO_BANK(20, 8, 0xD0),
+	F7188X_GPIO_BANK(30, 4, 0xC0),
+	F7188X_GPIO_BANK(40, 4, 0xB0),
+};
+
+static struct f7188x_gpio_bank f71889_gpio_bank[] = {
+	F7188X_GPIO_BANK(0 , 7, 0xF0),
+	F7188X_GPIO_BANK(10, 7, 0xE0),
+	F7188X_GPIO_BANK(20, 8, 0xD0),
+	F7188X_GPIO_BANK(30, 8, 0xC0),
+	F7188X_GPIO_BANK(40, 8, 0xB0),
+	F7188X_GPIO_BANK(50, 5, 0xA0),
+	F7188X_GPIO_BANK(60, 8, 0x90),
+	F7188X_GPIO_BANK(70, 8, 0x80),
+};
+
+static int f7188x_gpio_direction_in(struct gpio_chip *chip, unsigned offset)
+{
+	int err;
+	struct f7188x_gpio_bank *bank =
+		container_of(chip, struct f7188x_gpio_bank, chip);
+	struct f7188x_sio *sio = bank->data->sio;
+	u8 dir;
+
+	err = superio_enter(sio->addr);
+	if (err)
+		return err;
+	superio_select(sio->addr, SIO_LD_GPIO);
+
+	dir = superio_inb(sio->addr, gpio_dir(bank->regbase));
+	dir &= ~(1 << offset);
+	superio_outb(sio->addr, gpio_dir(bank->regbase), dir);
+
+	superio_exit(sio->addr);
+
+	return 0;
+}
+
+static int f7188x_gpio_get(struct gpio_chip *chip, unsigned offset)
+{
+	int err;
+	struct f7188x_gpio_bank *bank =
+		container_of(chip, struct f7188x_gpio_bank, chip);
+	struct f7188x_sio *sio = bank->data->sio;
+	u8 dir, data;
+
+	err = superio_enter(sio->addr);
+	if (err)
+		return err;
+	superio_select(sio->addr, SIO_LD_GPIO);
+
+	dir = superio_inb(sio->addr, gpio_dir(bank->regbase));
+	dir = !!(dir & (1 << offset));
+	if (dir)
+		data = superio_inb(sio->addr, gpio_data_out(bank->regbase));
+	else
+		data = superio_inb(sio->addr, gpio_data_in(bank->regbase));
+
+	superio_exit(sio->addr);
+
+	return !!(data & 1 << offset);
+}
+
+static int f7188x_gpio_direction_out(struct gpio_chip *chip,
+				     unsigned offset, int value)
+{
+	int err;
+	struct f7188x_gpio_bank *bank =
+		container_of(chip, struct f7188x_gpio_bank, chip);
+	struct f7188x_sio *sio = bank->data->sio;
+	u8 dir, data_out;
+
+	err = superio_enter(sio->addr);
+	if (err)
+		return err;
+	superio_select(sio->addr, SIO_LD_GPIO);
+
+	data_out = superio_inb(sio->addr, gpio_data_out(bank->regbase));
+	if (value)
+		data_out |= (1 << offset);
+	else
+		data_out &= ~(1 << offset);
+	superio_outb(sio->addr, gpio_data_out(bank->regbase), data_out);
+
+	dir = superio_inb(sio->addr, gpio_dir(bank->regbase));
+	dir |= (1 << offset);
+	superio_outb(sio->addr, gpio_dir(bank->regbase), dir);
+
+	superio_exit(sio->addr);
+
+	return 0;
+}
+
+static void f7188x_gpio_set(struct gpio_chip *chip, unsigned offset, int value)
+{
+	int err;
+	struct f7188x_gpio_bank *bank =
+		container_of(chip, struct f7188x_gpio_bank, chip);
+	struct f7188x_sio *sio = bank->data->sio;
+	u8 data_out;
+
+	err = superio_enter(sio->addr);
+	if (err)
+		return;
+	superio_select(sio->addr, SIO_LD_GPIO);
+
+	data_out = superio_inb(sio->addr, gpio_data_out(bank->regbase));
+	if (value)
+		data_out |= (1 << offset);
+	else
+		data_out &= ~(1 << offset);
+	superio_outb(sio->addr, gpio_data_out(bank->regbase), data_out);
+
+	superio_exit(sio->addr);
+}
+
+/*
+ * Platform device and driver.
+ */
+
+static int f7188x_gpio_probe(struct platform_device *pdev)
+{
+	int err;
+	int i;
+	struct f7188x_sio *sio = pdev->dev.platform_data;
+	struct f7188x_gpio_data *data;
+
+	data = devm_kzalloc(&pdev->dev, sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	switch (sio->type) {
+	case f71882fg:
+		data->nr_bank = ARRAY_SIZE(f71882_gpio_bank);
+		data->bank = f71882_gpio_bank;
+		break;
+	case f71889f:
+		data->nr_bank = ARRAY_SIZE(f71889_gpio_bank);
+		data->bank = f71889_gpio_bank;
+		break;
+	default:
+		return -ENODEV;
+	}
+	data->sio = sio;
+
+	platform_set_drvdata(pdev, data);
+
+	/* For each GPIO bank, register a GPIO chip. */
+	for (i = 0; i < data->nr_bank; i++) {
+		struct f7188x_gpio_bank *bank = &data->bank[i];
+
+		bank->chip.dev = &pdev->dev;
+		bank->data = data;
+
+		err = gpiochip_add(&bank->chip);
+		if (err) {
+			dev_err(&pdev->dev,
+				"Failed to register gpiochip %d: %d\n",
+				i, err);
+			goto err_gpiochip;
+		}
+	}
+
+	return 0;
+
+err_gpiochip:
+	for (i = i - 1; i >= 0; i--) {
+		struct f7188x_gpio_bank *bank = &data->bank[i];
+		int tmp;
+
+		tmp = gpiochip_remove(&bank->chip);
+		if (tmp < 0)
+			dev_err(&pdev->dev,
+				"Failed to remove gpiochip %d: %d\n",
+				i, tmp);
+	}
+
+	return err;
+}
+
+static int f7188x_gpio_remove(struct platform_device *pdev)
+{
+	int err;
+	int i;
+	struct f7188x_gpio_data *data = platform_get_drvdata(pdev);
+
+	for (i = 0; i < data->nr_bank; i++) {
+		struct f7188x_gpio_bank *bank = &data->bank[i];
+
+		err = gpiochip_remove(&bank->chip);
+		if (err) {
+			dev_err(&pdev->dev,
+				"Failed to remove GPIO gpiochip %d: %d\n",
+				i, err);
+			return err;
+		}
+	}
+
+	return 0;
+}
+
+static int __init f7188x_find(int addr, struct f7188x_sio *sio)
+{
+	int err;
+	u16 devid;
+
+	err = superio_enter(addr);
+	if (err)
+		return err;
+
+	err = -ENODEV;
+	devid = superio_inw(addr, SIO_MANID);
+	if (devid != SIO_FINTEK_ID) {
+		pr_debug(DRVNAME ": Not a Fintek device at 0x%08x\n", addr);
+		goto err;
+	}
+
+	devid = superio_inw(addr, SIO_DEVID);
+	switch (devid) {
+	case SIO_F71882_ID:
+		sio->type = f71882fg;
+		break;
+	case SIO_F71889_ID:
+		sio->type = f71889f;
+		break;
+	default:
+		pr_info(DRVNAME ": Unsupported Fintek device 0x%04x\n", devid);
+		goto err;
+	}
+	sio->addr = addr;
+	err = 0;
+
+	pr_info(DRVNAME ": Found %s at %#x, revision %d\n",
+		f7188x_names[sio->type],
+		(unsigned int) addr,
+		(int) superio_inb(addr, SIO_DEVREV));
+
+err:
+	superio_exit(addr);
+	return err;
+}
+
+static struct platform_device *f7188x_gpio_pdev;
+
+static int __init
+f7188x_gpio_device_add(const struct f7188x_sio *sio)
+{
+	int err;
+
+	f7188x_gpio_pdev = platform_device_alloc(DRVNAME, -1);
+	if (!f7188x_gpio_pdev)
+		return -ENOMEM;
+
+	err = platform_device_add_data(f7188x_gpio_pdev,
+				       sio, sizeof(*sio));
+	if (err) {
+		pr_err(DRVNAME "Platform data allocation failed\n");
+		goto err;
+	}
+
+	err = platform_device_add(f7188x_gpio_pdev);
+	if (err) {
+		pr_err(DRVNAME "Device addition failed\n");
+		goto err;
+	}
+
+	return 0;
+
+err:
+	platform_device_put(f7188x_gpio_pdev);
+
+	return err;
+}
+
+/*
+ * Try to match a supported Fintech device by reading the (hard-wired)
+ * configuration I/O ports. If available, then register both the platform
+ * device and driver to support the GPIOs.
+ */
+
+static struct platform_driver f7188x_gpio_driver = {
+	.driver = {
+		.owner	= THIS_MODULE,
+		.name	= DRVNAME,
+	},
+	.probe		= f7188x_gpio_probe,
+	.remove		= f7188x_gpio_remove,
+};
+
+static int __init f7188x_gpio_init(void)
+{
+	int err;
+	struct f7188x_sio sio;
+
+	if (f7188x_find(0x2e, &sio) &&
+	    f7188x_find(0x4e, &sio))
+		return -ENODEV;
+
+	err = platform_driver_register(&f7188x_gpio_driver);
+	if (!err) {
+		err = f7188x_gpio_device_add(&sio);
+		if (err)
+			platform_driver_unregister(&f7188x_gpio_driver);
+	}
+
+	return err;
+}
+subsys_initcall(f7188x_gpio_init);
+
+static void __exit f7188x_gpio_exit(void)
+{
+	platform_device_unregister(f7188x_gpio_pdev);
+	platform_driver_unregister(&f7188x_gpio_driver);
+}
+module_exit(f7188x_gpio_exit);
+
+MODULE_DESCRIPTION("GPIO driver for Super-I/O chips F71882FG and F71889F");
+MODULE_AUTHOR("Simon Guinot <simon.guinot@sequanux.org>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/gpio/gpio-ich.c b/drivers/gpio/gpio-ich.c
index 2729e3d2d5bb..814addb62d2c 100644
--- a/drivers/gpio/gpio-ich.c
+++ b/drivers/gpio/gpio-ich.c
@@ -354,7 +354,7 @@ static int ichx_gpio_probe(struct platform_device *pdev)
 {
 	struct resource *res_base, *res_pm;
 	int err;
-	struct lpc_ich_info *ich_info = pdev->dev.platform_data;
+	struct lpc_ich_info *ich_info = dev_get_platdata(&pdev->dev);
 
 	if (!ich_info)
 		return -ENODEV;
diff --git a/drivers/gpio/gpio-janz-ttl.c b/drivers/gpio/gpio-janz-ttl.c
index 7d0a04169a35..2ecd3a09c743 100644
--- a/drivers/gpio/gpio-janz-ttl.c
+++ b/drivers/gpio/gpio-janz-ttl.c
@@ -149,7 +149,7 @@ static int ttl_probe(struct platform_device *pdev)
 	struct resource *res;
 	int ret;
 
-	pdata = pdev->dev.platform_data;
+	pdata = dev_get_platdata(&pdev->dev);
 	if (!pdata) {
 		dev_err(dev, "no platform data\n");
 		ret = -ENXIO;
diff --git a/drivers/gpio/gpio-kempld.c b/drivers/gpio/gpio-kempld.c
new file mode 100644
index 000000000000..efdc3924d7df
--- /dev/null
+++ b/drivers/gpio/gpio-kempld.c
@@ -0,0 +1,219 @@
+/*
+ * Kontron PLD GPIO driver
+ *
+ * Copyright (c) 2010-2013 Kontron Europe GmbH
+ * Author: Michael Brunner <michael.brunner@kontron.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License 2 as published
+ * by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/bitops.h>
+#include <linux/errno.h>
+#include <linux/platform_device.h>
+#include <linux/gpio.h>
+#include <linux/mfd/kempld.h>
+
+#define KEMPLD_GPIO_MAX_NUM		16
+#define KEMPLD_GPIO_MASK(x)		(1 << ((x) % 8))
+#define KEMPLD_GPIO_DIR_NUM(x)		(0x40 + (x) / 8)
+#define KEMPLD_GPIO_LVL_NUM(x)		(0x42 + (x) / 8)
+#define KEMPLD_GPIO_EVT_LVL_EDGE	0x46
+#define KEMPLD_GPIO_IEN			0x4A
+
+struct kempld_gpio_data {
+	struct gpio_chip		chip;
+	struct kempld_device_data	*pld;
+};
+
+/*
+ * Set or clear GPIO bit
+ * kempld_get_mutex must be called prior to calling this function.
+ */
+static void kempld_gpio_bitop(struct kempld_device_data *pld,
+			      u8 reg, u8 bit, u8 val)
+{
+	u8 status;
+
+	status = kempld_read8(pld, reg);
+	if (val)
+		status |= KEMPLD_GPIO_MASK(bit);
+	else
+		status &= ~KEMPLD_GPIO_MASK(bit);
+	kempld_write8(pld, reg, status);
+}
+
+static int kempld_gpio_get_bit(struct kempld_device_data *pld, u8 reg, u8 bit)
+{
+	u8 status;
+
+	kempld_get_mutex(pld);
+	status = kempld_read8(pld, reg);
+	kempld_release_mutex(pld);
+
+	return !!(status & KEMPLD_GPIO_MASK(bit));
+}
+
+static int kempld_gpio_get(struct gpio_chip *chip, unsigned offset)
+{
+	struct kempld_gpio_data *gpio
+		= container_of(chip, struct kempld_gpio_data, chip);
+	struct kempld_device_data *pld = gpio->pld;
+
+	return kempld_gpio_get_bit(pld, KEMPLD_GPIO_LVL_NUM(offset), offset);
+}
+
+static void kempld_gpio_set(struct gpio_chip *chip, unsigned offset, int value)
+{
+	struct kempld_gpio_data *gpio
+		= container_of(chip, struct kempld_gpio_data, chip);
+	struct kempld_device_data *pld = gpio->pld;
+
+	kempld_get_mutex(pld);
+	kempld_gpio_bitop(pld, KEMPLD_GPIO_LVL_NUM(offset), offset, value);
+	kempld_release_mutex(pld);
+}
+
+static int kempld_gpio_direction_input(struct gpio_chip *chip, unsigned offset)
+{
+	struct kempld_gpio_data *gpio
+		= container_of(chip, struct kempld_gpio_data, chip);
+	struct kempld_device_data *pld = gpio->pld;
+
+	kempld_get_mutex(pld);
+	kempld_gpio_bitop(pld, KEMPLD_GPIO_DIR_NUM(offset), offset, 0);
+	kempld_release_mutex(pld);
+
+	return 0;
+}
+
+static int kempld_gpio_direction_output(struct gpio_chip *chip, unsigned offset,
+					int value)
+{
+	struct kempld_gpio_data *gpio
+		= container_of(chip, struct kempld_gpio_data, chip);
+	struct kempld_device_data *pld = gpio->pld;
+
+	kempld_get_mutex(pld);
+	kempld_gpio_bitop(pld, KEMPLD_GPIO_LVL_NUM(offset), offset, value);
+	kempld_gpio_bitop(pld, KEMPLD_GPIO_DIR_NUM(offset), offset, 1);
+	kempld_release_mutex(pld);
+
+	return 0;
+}
+
+static int kempld_gpio_get_direction(struct gpio_chip *chip, unsigned offset)
+{
+	struct kempld_gpio_data *gpio
+		= container_of(chip, struct kempld_gpio_data, chip);
+	struct kempld_device_data *pld = gpio->pld;
+
+	return kempld_gpio_get_bit(pld, KEMPLD_GPIO_DIR_NUM(offset), offset);
+}
+
+static int kempld_gpio_pincount(struct kempld_device_data *pld)
+{
+	u16 evt, evt_back;
+
+	kempld_get_mutex(pld);
+
+	/* Backup event register as it might be already initialized */
+	evt_back = kempld_read16(pld, KEMPLD_GPIO_EVT_LVL_EDGE);
+	/* Clear event register */
+	kempld_write16(pld, KEMPLD_GPIO_EVT_LVL_EDGE, 0x0000);
+	/* Read back event register */
+	evt = kempld_read16(pld, KEMPLD_GPIO_EVT_LVL_EDGE);
+	/* Restore event register */
+	kempld_write16(pld, KEMPLD_GPIO_EVT_LVL_EDGE, evt_back);
+
+	kempld_release_mutex(pld);
+
+	return evt ? __ffs(evt) : 16;
+}
+
+static int kempld_gpio_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct kempld_device_data *pld = dev_get_drvdata(dev->parent);
+	struct kempld_platform_data *pdata = dev_get_platdata(pld->dev);
+	struct kempld_gpio_data *gpio;
+	struct gpio_chip *chip;
+	int ret;
+
+	if (pld->info.spec_major < 2) {
+		dev_err(dev,
+			"Driver only supports GPIO devices compatible to PLD spec. rev. 2.0 or higher\n");
+		return -ENODEV;
+	}
+
+	gpio = devm_kzalloc(dev, sizeof(*gpio), GFP_KERNEL);
+	if (gpio == NULL)
+		return -ENOMEM;
+
+	gpio->pld = pld;
+
+	platform_set_drvdata(pdev, gpio);
+
+	chip = &gpio->chip;
+	chip->label = "gpio-kempld";
+	chip->owner = THIS_MODULE;
+	chip->dev = dev;
+	chip->can_sleep = 1;
+	if (pdata && pdata->gpio_base)
+		chip->base = pdata->gpio_base;
+	else
+		chip->base = -1;
+	chip->direction_input = kempld_gpio_direction_input;
+	chip->direction_output = kempld_gpio_direction_output;
+	chip->get_direction = kempld_gpio_get_direction;
+	chip->get = kempld_gpio_get;
+	chip->set = kempld_gpio_set;
+	chip->ngpio = kempld_gpio_pincount(pld);
+	if (chip->ngpio == 0) {
+		dev_err(dev, "No GPIO pins detected\n");
+		return -ENODEV;
+	}
+
+	ret = gpiochip_add(chip);
+	if (ret) {
+		dev_err(dev, "Could not register GPIO chip\n");
+		return ret;
+	}
+
+	dev_info(dev, "GPIO functionality initialized with %d pins\n",
+		 chip->ngpio);
+
+	return 0;
+}
+
+static int kempld_gpio_remove(struct platform_device *pdev)
+{
+	struct kempld_gpio_data *gpio = platform_get_drvdata(pdev);
+
+	return gpiochip_remove(&gpio->chip);
+}
+
+static struct platform_driver kempld_gpio_driver = {
+	.driver = {
+		.name = "kempld-gpio",
+		.owner = THIS_MODULE,
+	},
+	.probe		= kempld_gpio_probe,
+	.remove		= kempld_gpio_remove,
+};
+
+module_platform_driver(kempld_gpio_driver);
+
+MODULE_DESCRIPTION("KEM PLD GPIO Driver");
+MODULE_AUTHOR("Michael Brunner <michael.brunner@kontron.com>");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:gpio-kempld");
diff --git a/drivers/gpio/gpio-lynxpoint.c b/drivers/gpio/gpio-lynxpoint.c
index 761c4705dfbb..41b5913ddabe 100644
--- a/drivers/gpio/gpio-lynxpoint.c
+++ b/drivers/gpio/gpio-lynxpoint.c
@@ -248,14 +248,15 @@ static void lp_gpio_irq_handler(unsigned irq, struct irq_desc *desc)
 	struct lp_gpio *lg = irq_data_get_irq_handler_data(data);
 	struct irq_chip *chip = irq_data_get_irq_chip(data);
 	u32 base, pin, mask;
-	unsigned long reg, pending;
+	unsigned long reg, ena, pending;
 	unsigned virq;
 
 	/* check from GPIO controller which pin triggered the interrupt */
 	for (base = 0; base < lg->chip.ngpio; base += 32) {
 		reg = lp_gpio_reg(&lg->chip, base, LP_INT_STAT);
+		ena = lp_gpio_reg(&lg->chip, base, LP_INT_ENABLE);
 
-		while ((pending = inl(reg))) {
+		while ((pending = (inl(reg) & inl(ena)))) {
 			pin = __ffs(pending);
 			mask = BIT(pin);
 			/* Clear before handling so we don't lose an edge */
@@ -444,6 +445,7 @@ static int lp_gpio_remove(struct platform_device *pdev)
 {
 	struct lp_gpio *lg = platform_get_drvdata(pdev);
 	int err;
+	pm_runtime_disable(&pdev->dev);
 	err = gpiochip_remove(&lg->chip);
 	if (err)
 		dev_warn(&pdev->dev, "failed to remove gpio_chip.\n");
diff --git a/drivers/gpio/gpio-max7301.c b/drivers/gpio/gpio-max7301.c
index 3b16ab701630..6e1c984a75d4 100644
--- a/drivers/gpio/gpio-max7301.c
+++ b/drivers/gpio/gpio-max7301.c
@@ -56,8 +56,7 @@ static int max7301_probe(struct spi_device *spi)
 	int ret;
 
 	/* bits_per_word cannot be configured in platform data */
-	if (spi->dev.platform_data)
-		spi->bits_per_word = 16;
+	spi->bits_per_word = 16;
 	ret = spi_setup(spi);
 	if (ret < 0)
 		return ret;
diff --git a/drivers/gpio/gpio-max730x.c b/drivers/gpio/gpio-max730x.c
index 00092342b84c..f4f4ed19bdc1 100644
--- a/drivers/gpio/gpio-max730x.c
+++ b/drivers/gpio/gpio-max730x.c
@@ -166,7 +166,7 @@ int __max730x_probe(struct max7301 *ts)
 	struct max7301_platform_data *pdata;
 	int i, ret;
 
-	pdata = dev->platform_data;
+	pdata = dev_get_platdata(dev);
 
 	mutex_init(&ts->lock);
 	dev_set_drvdata(dev, ts);
diff --git a/drivers/gpio/gpio-max732x.c b/drivers/gpio/gpio-max732x.c
index d4b51b163b03..91ad74dea8ce 100644
--- a/drivers/gpio/gpio-max732x.c
+++ b/drivers/gpio/gpio-max732x.c
@@ -453,7 +453,7 @@ static int max732x_irq_setup(struct max732x_chip *chip,
 			     const struct i2c_device_id *id)
 {
 	struct i2c_client *client = chip->client;
-	struct max732x_platform_data *pdata = client->dev.platform_data;
+	struct max732x_platform_data *pdata = dev_get_platdata(&client->dev);
 	int has_irq = max732x_features[id->driver_data] >> 32;
 	int ret;
 
@@ -512,7 +512,7 @@ static int max732x_irq_setup(struct max732x_chip *chip,
 			     const struct i2c_device_id *id)
 {
 	struct i2c_client *client = chip->client;
-	struct max732x_platform_data *pdata = client->dev.platform_data;
+	struct max732x_platform_data *pdata = dev_get_platdata(&client->dev);
 	int has_irq = max732x_features[id->driver_data] >> 32;
 
 	if (pdata->irq_base && has_irq != INT_NONE)
@@ -583,7 +583,7 @@ static int max732x_probe(struct i2c_client *client,
 	uint16_t addr_a, addr_b;
 	int ret, nr_port;
 
-	pdata = client->dev.platform_data;
+	pdata = dev_get_platdata(&client->dev);
 	if (pdata == NULL) {
 		dev_dbg(&client->dev, "no platform data\n");
 		return -EINVAL;
@@ -653,7 +653,7 @@ out_failed:
 
 static int max732x_remove(struct i2c_client *client)
 {
-	struct max732x_platform_data *pdata = client->dev.platform_data;
+	struct max732x_platform_data *pdata = dev_get_platdata(&client->dev);
 	struct max732x_chip *chip = i2c_get_clientdata(client);
 	int ret;
 
diff --git a/drivers/gpio/gpio-mc33880.c b/drivers/gpio/gpio-mc33880.c
index 63a7a1bfb2d9..3fd2caa4a2e0 100644
--- a/drivers/gpio/gpio-mc33880.c
+++ b/drivers/gpio/gpio-mc33880.c
@@ -86,7 +86,7 @@ static int mc33880_probe(struct spi_device *spi)
 	struct mc33880_platform_data *pdata;
 	int ret;
 
-	pdata = spi->dev.platform_data;
+	pdata = dev_get_platdata(&spi->dev);
 	if (!pdata || !pdata->base) {
 		dev_dbg(&spi->dev, "incorrect or missing platform data\n");
 		return -EINVAL;
diff --git a/drivers/gpio/gpio-mcp23s08.c b/drivers/gpio/gpio-mcp23s08.c
index 6a4470b84488..2deb0c5e54a4 100644
--- a/drivers/gpio/gpio-mcp23s08.c
+++ b/drivers/gpio/gpio-mcp23s08.c
@@ -483,10 +483,21 @@ fail:
 #ifdef CONFIG_SPI_MASTER
 static struct of_device_id mcp23s08_spi_of_match[] = {
 	{
-		.compatible = "mcp,mcp23s08", .data = (void *) MCP_TYPE_S08,
+		.compatible = "microchip,mcp23s08",
+		.data = (void *) MCP_TYPE_S08,
 	},
 	{
-		.compatible = "mcp,mcp23s17", .data = (void *) MCP_TYPE_S17,
+		.compatible = "microchip,mcp23s17",
+		.data = (void *) MCP_TYPE_S17,
+	},
+/* NOTE: The use of the mcp prefix is deprecated and will be removed. */
+	{
+		.compatible = "mcp,mcp23s08",
+		.data = (void *) MCP_TYPE_S08,
+	},
+	{
+		.compatible = "mcp,mcp23s17",
+		.data = (void *) MCP_TYPE_S17,
 	},
 	{ },
 };
@@ -496,10 +507,21 @@ MODULE_DEVICE_TABLE(of, mcp23s08_spi_of_match);
 #if IS_ENABLED(CONFIG_I2C)
 static struct of_device_id mcp23s08_i2c_of_match[] = {
 	{
-		.compatible = "mcp,mcp23008", .data = (void *) MCP_TYPE_008,
+		.compatible = "microchip,mcp23008",
+		.data = (void *) MCP_TYPE_008,
+	},
+	{
+		.compatible = "microchip,mcp23017",
+		.data = (void *) MCP_TYPE_017,
+	},
+/* NOTE: The use of the mcp prefix is deprecated and will be removed. */
+	{
+		.compatible = "mcp,mcp23008",
+		.data = (void *) MCP_TYPE_008,
 	},
 	{
-		.compatible = "mcp,mcp23017", .data = (void *) MCP_TYPE_017,
+		.compatible = "mcp,mcp23017",
+		.data = (void *) MCP_TYPE_017,
 	},
 	{ },
 };
@@ -520,14 +542,13 @@ static int mcp230xx_probe(struct i2c_client *client,
 
 	match = of_match_device(of_match_ptr(mcp23s08_i2c_of_match),
 					&client->dev);
-	if (match) {
+	pdata = dev_get_platdata(&client->dev);
+	if (match || !pdata) {
 		base = -1;
 		pullups = 0;
 	} else {
-		pdata = client->dev.platform_data;
-		if (!pdata || !gpio_is_valid(pdata->base)) {
-			dev_dbg(&client->dev,
-					"invalid or missing platform data\n");
+		if (!gpio_is_valid(pdata->base)) {
+			dev_dbg(&client->dev, "invalid platform data\n");
 			return -EINVAL;
 		}
 		base = pdata->base;
@@ -621,10 +642,15 @@ static int mcp23s08_probe(struct spi_device *spi)
 	if (match) {
 		type = (int)match->data;
 		status = of_property_read_u32(spi->dev.of_node,
-				"mcp,spi-present-mask", &spi_present_mask);
+			    "microchip,spi-present-mask", &spi_present_mask);
 		if (status) {
-			dev_err(&spi->dev, "DT has no spi-present-mask\n");
-			return -ENODEV;
+			status = of_property_read_u32(spi->dev.of_node,
+				    "mcp,spi-present-mask", &spi_present_mask);
+			if (status) {
+				dev_err(&spi->dev,
+					"DT has no spi-present-mask\n");
+				return -ENODEV;
+			}
 		}
 		if ((spi_present_mask <= 0) || (spi_present_mask >= 256)) {
 			dev_err(&spi->dev, "invalid spi-present-mask\n");
@@ -635,7 +661,7 @@ static int mcp23s08_probe(struct spi_device *spi)
 			pullups[addr] = 0;
 	} else {
 		type = spi_get_device_id(spi)->driver_data;
-		pdata = spi->dev.platform_data;
+		pdata = dev_get_platdata(&spi->dev);
 		if (!pdata || !gpio_is_valid(pdata->base)) {
 			dev_dbg(&spi->dev,
 					"invalid or missing platform data\n");
diff --git a/drivers/gpio/gpio-msic.c b/drivers/gpio/gpio-msic.c
index 27ea7b9257ff..d75eaa3a1dcc 100644
--- a/drivers/gpio/gpio-msic.c
+++ b/drivers/gpio/gpio-msic.c
@@ -259,7 +259,7 @@ static void msic_gpio_irq_handler(unsigned irq, struct irq_desc *desc)
 static int platform_msic_gpio_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
-	struct intel_msic_gpio_pdata *pdata = dev->platform_data;
+	struct intel_msic_gpio_pdata *pdata = dev_get_platdata(dev);
 	struct msic_gpio *mg;
 	int irq = platform_get_irq(pdev, 0);
 	int retval;
diff --git a/drivers/gpio/gpio-msm-v2.c b/drivers/gpio/gpio-msm-v2.c
index c2fa77086eb5..f7a0cc4da950 100644
--- a/drivers/gpio/gpio-msm-v2.c
+++ b/drivers/gpio/gpio-msm-v2.c
@@ -106,7 +106,7 @@ struct msm_gpio_dev {
 	void __iomem *msm_tlmm_base;
 };
 
-struct msm_gpio_dev msm_gpio;
+static struct msm_gpio_dev msm_gpio;
 
 #define GPIO_INTR_CFG_SU(gpio)    (msm_gpio.msm_tlmm_base + 0x0400 + \
 								(0x04 * (gpio)))
diff --git a/drivers/gpio/gpio-mvebu.c b/drivers/gpio/gpio-mvebu.c
index 80ad35e2a8cd..3c3321f94053 100644
--- a/drivers/gpio/gpio-mvebu.c
+++ b/drivers/gpio/gpio-mvebu.c
@@ -566,12 +566,6 @@ static int mvebu_gpio_probe(struct platform_device *pdev)
 	else
 		soc_variant = MVEBU_GPIO_SOC_VARIANT_ORION;
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!res) {
-		dev_err(&pdev->dev, "Cannot get memory resource\n");
-		return -ENODEV;
-	}
-
 	mvchip = devm_kzalloc(&pdev->dev, sizeof(struct mvebu_gpio_chip), GFP_KERNEL);
 	if (!mvchip) {
 		dev_err(&pdev->dev, "Cannot allocate memory\n");
@@ -611,6 +605,7 @@ static int mvebu_gpio_probe(struct platform_device *pdev)
 	mvchip->chip.dbg_show = mvebu_gpio_dbg_show;
 
 	spin_lock_init(&mvchip->lock);
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	mvchip->membase = devm_ioremap_resource(&pdev->dev, res);
 	if (IS_ERR(mvchip->membase))
 		return PTR_ERR(mvchip->membase);
diff --git a/drivers/gpio/gpio-mxc.c b/drivers/gpio/gpio-mxc.c
index 7176743915d3..3307f6db3a92 100644
--- a/drivers/gpio/gpio-mxc.c
+++ b/drivers/gpio/gpio-mxc.c
@@ -19,6 +19,7 @@
  * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
  */
 
+#include <linux/err.h>
 #include <linux/init.h>
 #include <linux/interrupt.h>
 #include <linux/io.h>
@@ -291,6 +292,9 @@ static void mx2_gpio_irq_handler(u32 irq, struct irq_desc *desc)
 {
 	u32 irq_msk, irq_stat;
 	struct mxc_gpio_port *port;
+	struct irq_chip *chip = irq_get_chip(irq);
+
+	chained_irq_enter(chip, desc);
 
 	/* walk through all interrupt status registers */
 	list_for_each_entry(port, &mxc_gpio_ports, node) {
@@ -302,6 +306,7 @@ static void mx2_gpio_irq_handler(u32 irq, struct irq_desc *desc)
 		if (irq_stat)
 			mxc_gpio_irq_handler(port, irq_stat);
 	}
+	chained_irq_exit(chip, desc);
 }
 
 /*
@@ -405,34 +410,19 @@ static int mxc_gpio_probe(struct platform_device *pdev)
 
 	mxc_gpio_get_hw(pdev);
 
-	port = kzalloc(sizeof(struct mxc_gpio_port), GFP_KERNEL);
+	port = devm_kzalloc(&pdev->dev, sizeof(*port), GFP_KERNEL);
 	if (!port)
 		return -ENOMEM;
 
 	iores = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!iores) {
-		err = -ENODEV;
-		goto out_kfree;
-	}
-
-	if (!request_mem_region(iores->start, resource_size(iores),
-				pdev->name)) {
-		err = -EBUSY;
-		goto out_kfree;
-	}
-
-	port->base = ioremap(iores->start, resource_size(iores));
-	if (!port->base) {
-		err = -ENOMEM;
-		goto out_release_mem;
-	}
+	port->base = devm_ioremap_resource(&pdev->dev, iores);
+	if (IS_ERR(port->base))
+		return PTR_ERR(port->base);
 
 	port->irq_high = platform_get_irq(pdev, 1);
 	port->irq = platform_get_irq(pdev, 0);
-	if (port->irq < 0) {
-		err = -EINVAL;
-		goto out_iounmap;
-	}
+	if (port->irq < 0)
+		return -EINVAL;
 
 	/* disable the interrupt and clear the status */
 	writel(0, port->base + GPIO_IMR);
@@ -462,7 +452,7 @@ static int mxc_gpio_probe(struct platform_device *pdev)
 			 port->base + GPIO_DR, NULL,
 			 port->base + GPIO_GDIR, NULL, 0);
 	if (err)
-		goto out_iounmap;
+		goto out_bgio;
 
 	port->bgc.gc.to_irq = mxc_gpio_to_irq;
 	port->bgc.gc.base = (pdev->id < 0) ? of_alias_get_id(np, "gpio") * 32 :
@@ -498,12 +488,7 @@ out_gpiochip_remove:
 	WARN_ON(gpiochip_remove(&port->bgc.gc) < 0);
 out_bgpio_remove:
 	bgpio_remove(&port->bgc);
-out_iounmap:
-	iounmap(port->base);
-out_release_mem:
-	release_mem_region(iores->start, resource_size(iores));
-out_kfree:
-	kfree(port);
+out_bgio:
 	dev_info(&pdev->dev, "%s failed with errno %d\n", __func__, err);
 	return err;
 }
diff --git a/drivers/gpio/gpio-octeon.c b/drivers/gpio/gpio-octeon.c
new file mode 100644
index 000000000000..71a4a318315d
--- /dev/null
+++ b/drivers/gpio/gpio-octeon.c
@@ -0,0 +1,157 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 2011, 2012 Cavium Inc.
+ */
+
+#include <linux/platform_device.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/gpio.h>
+#include <linux/io.h>
+
+#include <asm/octeon/octeon.h>
+#include <asm/octeon/cvmx-gpio-defs.h>
+
+#define RX_DAT 0x80
+#define TX_SET 0x88
+#define TX_CLEAR 0x90
+/*
+ * The address offset of the GPIO configuration register for a given
+ * line.
+ */
+static unsigned int bit_cfg_reg(unsigned int offset)
+{
+	/*
+	 * The register stride is 8, with a discontinuity after the
+	 * first 16.
+	 */
+	if (offset < 16)
+		return 8 * offset;
+	else
+		return 8 * (offset - 16) + 0x100;
+}
+
+struct octeon_gpio {
+	struct gpio_chip chip;
+	u64 register_base;
+};
+
+static int octeon_gpio_dir_in(struct gpio_chip *chip, unsigned offset)
+{
+	struct octeon_gpio *gpio = container_of(chip, struct octeon_gpio, chip);
+
+	cvmx_write_csr(gpio->register_base + bit_cfg_reg(offset), 0);
+	return 0;
+}
+
+static void octeon_gpio_set(struct gpio_chip *chip, unsigned offset, int value)
+{
+	struct octeon_gpio *gpio = container_of(chip, struct octeon_gpio, chip);
+	u64 mask = 1ull << offset;
+	u64 reg = gpio->register_base + (value ? TX_SET : TX_CLEAR);
+	cvmx_write_csr(reg, mask);
+}
+
+static int octeon_gpio_dir_out(struct gpio_chip *chip, unsigned offset,
+			       int value)
+{
+	struct octeon_gpio *gpio = container_of(chip, struct octeon_gpio, chip);
+	union cvmx_gpio_bit_cfgx cfgx;
+
+	octeon_gpio_set(chip, offset, value);
+
+	cfgx.u64 = 0;
+	cfgx.s.tx_oe = 1;
+
+	cvmx_write_csr(gpio->register_base + bit_cfg_reg(offset), cfgx.u64);
+	return 0;
+}
+
+static int octeon_gpio_get(struct gpio_chip *chip, unsigned offset)
+{
+	struct octeon_gpio *gpio = container_of(chip, struct octeon_gpio, chip);
+	u64 read_bits = cvmx_read_csr(gpio->register_base + RX_DAT);
+
+	return ((1ull << offset) & read_bits) != 0;
+}
+
+static int octeon_gpio_probe(struct platform_device *pdev)
+{
+	struct octeon_gpio *gpio;
+	struct gpio_chip *chip;
+	struct resource *res_mem;
+	int err = 0;
+
+	gpio = devm_kzalloc(&pdev->dev, sizeof(*gpio), GFP_KERNEL);
+	if (!gpio)
+		return -ENOMEM;
+	chip = &gpio->chip;
+
+	res_mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (res_mem == NULL) {
+		dev_err(&pdev->dev, "found no memory resource\n");
+		err = -ENXIO;
+		goto out;
+	}
+	if (!devm_request_mem_region(&pdev->dev, res_mem->start,
+					resource_size(res_mem),
+				     res_mem->name)) {
+		dev_err(&pdev->dev, "request_mem_region failed\n");
+		err = -ENXIO;
+		goto out;
+	}
+	gpio->register_base = (u64)devm_ioremap(&pdev->dev, res_mem->start,
+						resource_size(res_mem));
+
+	pdev->dev.platform_data = chip;
+	chip->label = "octeon-gpio";
+	chip->dev = &pdev->dev;
+	chip->owner = THIS_MODULE;
+	chip->base = 0;
+	chip->can_sleep = 0;
+	chip->ngpio = 20;
+	chip->direction_input = octeon_gpio_dir_in;
+	chip->get = octeon_gpio_get;
+	chip->direction_output = octeon_gpio_dir_out;
+	chip->set = octeon_gpio_set;
+	err = gpiochip_add(chip);
+	if (err)
+		goto out;
+
+	dev_info(&pdev->dev, "OCTEON GPIO driver probed.\n");
+out:
+	return err;
+}
+
+static int octeon_gpio_remove(struct platform_device *pdev)
+{
+	struct gpio_chip *chip = pdev->dev.platform_data;
+	return gpiochip_remove(chip);
+}
+
+static struct of_device_id octeon_gpio_match[] = {
+	{
+		.compatible = "cavium,octeon-3860-gpio",
+	},
+	{},
+};
+MODULE_DEVICE_TABLE(of, octeon_gpio_match);
+
+static struct platform_driver octeon_gpio_driver = {
+	.driver = {
+		.name		= "octeon_gpio",
+		.owner		= THIS_MODULE,
+		.of_match_table = octeon_gpio_match,
+	},
+	.probe		= octeon_gpio_probe,
+	.remove		= octeon_gpio_remove,
+};
+
+module_platform_driver(octeon_gpio_driver);
+
+MODULE_DESCRIPTION("Cavium Inc. OCTEON GPIO Driver");
+MODULE_AUTHOR("David Daney");
+MODULE_LICENSE("GPL");
diff --git a/drivers/gpio/gpio-omap.c b/drivers/gpio/gpio-omap.c
index dfeb3a3a8f20..89675f862308 100644
--- a/drivers/gpio/gpio-omap.c
+++ b/drivers/gpio/gpio-omap.c
@@ -63,6 +63,7 @@ struct gpio_bank {
 	struct gpio_chip chip;
 	struct clk *dbck;
 	u32 mod_usage;
+	u32 irq_usage;
 	u32 dbck_enable_mask;
 	bool dbck_enabled;
 	struct device *dev;
@@ -86,6 +87,9 @@ struct gpio_bank {
 #define GPIO_BIT(bank, gpio) (1 << GPIO_INDEX(bank, gpio))
 #define GPIO_MOD_CTRL_BIT	BIT(0)
 
+#define BANK_USED(bank) (bank->mod_usage || bank->irq_usage)
+#define LINE_USED(line, offset) (line & (1 << offset))
+
 static int irq_to_gpio(struct gpio_bank *bank, unsigned int gpio_irq)
 {
 	return bank->chip.base + gpio_irq;
@@ -420,15 +424,69 @@ static int _set_gpio_triggering(struct gpio_bank *bank, int gpio,
 	return 0;
 }
 
+static void _enable_gpio_module(struct gpio_bank *bank, unsigned offset)
+{
+	if (bank->regs->pinctrl) {
+		void __iomem *reg = bank->base + bank->regs->pinctrl;
+
+		/* Claim the pin for MPU */
+		__raw_writel(__raw_readl(reg) | (1 << offset), reg);
+	}
+
+	if (bank->regs->ctrl && !BANK_USED(bank)) {
+		void __iomem *reg = bank->base + bank->regs->ctrl;
+		u32 ctrl;
+
+		ctrl = __raw_readl(reg);
+		/* Module is enabled, clocks are not gated */
+		ctrl &= ~GPIO_MOD_CTRL_BIT;
+		__raw_writel(ctrl, reg);
+		bank->context.ctrl = ctrl;
+	}
+}
+
+static void _disable_gpio_module(struct gpio_bank *bank, unsigned offset)
+{
+	void __iomem *base = bank->base;
+
+	if (bank->regs->wkup_en &&
+	    !LINE_USED(bank->mod_usage, offset) &&
+	    !LINE_USED(bank->irq_usage, offset)) {
+		/* Disable wake-up during idle for dynamic tick */
+		_gpio_rmw(base, bank->regs->wkup_en, 1 << offset, 0);
+		bank->context.wake_en =
+			__raw_readl(bank->base + bank->regs->wkup_en);
+	}
+
+	if (bank->regs->ctrl && !BANK_USED(bank)) {
+		void __iomem *reg = bank->base + bank->regs->ctrl;
+		u32 ctrl;
+
+		ctrl = __raw_readl(reg);
+		/* Module is disabled, clocks are gated */
+		ctrl |= GPIO_MOD_CTRL_BIT;
+		__raw_writel(ctrl, reg);
+		bank->context.ctrl = ctrl;
+	}
+}
+
+static int gpio_is_input(struct gpio_bank *bank, int mask)
+{
+	void __iomem *reg = bank->base + bank->regs->direction;
+
+	return __raw_readl(reg) & mask;
+}
+
 static int gpio_irq_type(struct irq_data *d, unsigned type)
 {
 	struct gpio_bank *bank = irq_data_get_irq_chip_data(d);
 	unsigned gpio = 0;
 	int retval;
 	unsigned long flags;
+	unsigned offset;
 
-	if (WARN_ON(!bank->mod_usage))
-		return -EINVAL;
+	if (!BANK_USED(bank))
+		pm_runtime_get_sync(bank->dev);
 
 #ifdef CONFIG_ARCH_OMAP1
 	if (d->irq > IH_MPUIO_BASE)
@@ -446,7 +504,17 @@ static int gpio_irq_type(struct irq_data *d, unsigned type)
 		return -EINVAL;
 
 	spin_lock_irqsave(&bank->lock, flags);
-	retval = _set_gpio_triggering(bank, GPIO_INDEX(bank, gpio), type);
+	offset = GPIO_INDEX(bank, gpio);
+	retval = _set_gpio_triggering(bank, offset, type);
+	if (!LINE_USED(bank->mod_usage, offset)) {
+		_enable_gpio_module(bank, offset);
+		_set_gpio_direction(bank, offset, 1);
+	} else if (!gpio_is_input(bank, 1 << offset)) {
+		spin_unlock_irqrestore(&bank->lock, flags);
+		return -EINVAL;
+	}
+
+	bank->irq_usage |= 1 << GPIO_INDEX(bank, gpio);
 	spin_unlock_irqrestore(&bank->lock, flags);
 
 	if (type & (IRQ_TYPE_LEVEL_LOW | IRQ_TYPE_LEVEL_HIGH))
@@ -603,35 +671,19 @@ static int omap_gpio_request(struct gpio_chip *chip, unsigned offset)
 	 * If this is the first gpio_request for the bank,
 	 * enable the bank module.
 	 */
-	if (!bank->mod_usage)
+	if (!BANK_USED(bank))
 		pm_runtime_get_sync(bank->dev);
 
 	spin_lock_irqsave(&bank->lock, flags);
 	/* Set trigger to none. You need to enable the desired trigger with
-	 * request_irq() or set_irq_type().
+	 * request_irq() or set_irq_type(). Only do this if the IRQ line has
+	 * not already been requested.
 	 */
-	_set_gpio_triggering(bank, offset, IRQ_TYPE_NONE);
-
-	if (bank->regs->pinctrl) {
-		void __iomem *reg = bank->base + bank->regs->pinctrl;
-
-		/* Claim the pin for MPU */
-		__raw_writel(__raw_readl(reg) | (1 << offset), reg);
-	}
-
-	if (bank->regs->ctrl && !bank->mod_usage) {
-		void __iomem *reg = bank->base + bank->regs->ctrl;
-		u32 ctrl;
-
-		ctrl = __raw_readl(reg);
-		/* Module is enabled, clocks are not gated */
-		ctrl &= ~GPIO_MOD_CTRL_BIT;
-		__raw_writel(ctrl, reg);
-		bank->context.ctrl = ctrl;
+	if (!LINE_USED(bank->irq_usage, offset)) {
+		_set_gpio_triggering(bank, offset, IRQ_TYPE_NONE);
+		_enable_gpio_module(bank, offset);
 	}
-
 	bank->mod_usage |= 1 << offset;
-
 	spin_unlock_irqrestore(&bank->lock, flags);
 
 	return 0;
@@ -640,31 +692,11 @@ static int omap_gpio_request(struct gpio_chip *chip, unsigned offset)
 static void omap_gpio_free(struct gpio_chip *chip, unsigned offset)
 {
 	struct gpio_bank *bank = container_of(chip, struct gpio_bank, chip);
-	void __iomem *base = bank->base;
 	unsigned long flags;
 
 	spin_lock_irqsave(&bank->lock, flags);
-
-	if (bank->regs->wkup_en) {
-		/* Disable wake-up during idle for dynamic tick */
-		_gpio_rmw(base, bank->regs->wkup_en, 1 << offset, 0);
-		bank->context.wake_en =
-			__raw_readl(bank->base + bank->regs->wkup_en);
-	}
-
 	bank->mod_usage &= ~(1 << offset);
-
-	if (bank->regs->ctrl && !bank->mod_usage) {
-		void __iomem *reg = bank->base + bank->regs->ctrl;
-		u32 ctrl;
-
-		ctrl = __raw_readl(reg);
-		/* Module is disabled, clocks are gated */
-		ctrl |= GPIO_MOD_CTRL_BIT;
-		__raw_writel(ctrl, reg);
-		bank->context.ctrl = ctrl;
-	}
-
+	_disable_gpio_module(bank, offset);
 	_reset_gpio(bank, bank->chip.base + offset);
 	spin_unlock_irqrestore(&bank->lock, flags);
 
@@ -672,7 +704,7 @@ static void omap_gpio_free(struct gpio_chip *chip, unsigned offset)
 	 * If this is the last gpio to be freed in the bank,
 	 * disable the bank module.
 	 */
-	if (!bank->mod_usage)
+	if (!BANK_USED(bank))
 		pm_runtime_put(bank->dev);
 }
 
@@ -762,10 +794,20 @@ static void gpio_irq_shutdown(struct irq_data *d)
 	struct gpio_bank *bank = irq_data_get_irq_chip_data(d);
 	unsigned int gpio = irq_to_gpio(bank, d->hwirq);
 	unsigned long flags;
+	unsigned offset = GPIO_INDEX(bank, gpio);
 
 	spin_lock_irqsave(&bank->lock, flags);
+	bank->irq_usage &= ~(1 << offset);
+	_disable_gpio_module(bank, offset);
 	_reset_gpio(bank, gpio);
 	spin_unlock_irqrestore(&bank->lock, flags);
+
+	/*
+	 * If this is the last IRQ to be freed in the bank,
+	 * disable the bank module.
+	 */
+	if (!BANK_USED(bank))
+		pm_runtime_put(bank->dev);
 }
 
 static void gpio_ack_irq(struct irq_data *d)
@@ -897,13 +939,6 @@ static int gpio_input(struct gpio_chip *chip, unsigned offset)
 	return 0;
 }
 
-static int gpio_is_input(struct gpio_bank *bank, int mask)
-{
-	void __iomem *reg = bank->base + bank->regs->direction;
-
-	return __raw_readl(reg) & mask;
-}
-
 static int gpio_get(struct gpio_chip *chip, unsigned offset)
 {
 	struct gpio_bank *bank;
@@ -922,13 +957,22 @@ static int gpio_output(struct gpio_chip *chip, unsigned offset, int value)
 {
 	struct gpio_bank *bank;
 	unsigned long flags;
+	int retval = 0;
 
 	bank = container_of(chip, struct gpio_bank, chip);
 	spin_lock_irqsave(&bank->lock, flags);
+
+	if (LINE_USED(bank->irq_usage, offset)) {
+			retval = -EINVAL;
+			goto exit;
+	}
+
 	bank->set_dataout(bank, offset, value);
 	_set_gpio_direction(bank, offset, 0);
+
+exit:
 	spin_unlock_irqrestore(&bank->lock, flags);
-	return 0;
+	return retval;
 }
 
 static int gpio_debounce(struct gpio_chip *chip, unsigned offset,
@@ -1030,7 +1074,7 @@ omap_mpuio_alloc_gc(struct gpio_bank *bank, unsigned int irq_start,
 	ct->chip.irq_set_type = gpio_irq_type;
 
 	if (bank->regs->wkup_en)
-		ct->chip.irq_set_wake = gpio_wake_enable,
+		ct->chip.irq_set_wake = gpio_wake_enable;
 
 	ct->regs.mask = OMAP_MPUIO_GPIO_INT / bank->stride;
 	irq_setup_generic_chip(gc, IRQ_MSK(num), IRQ_GC_INIT_MASK_CACHE,
@@ -1100,7 +1144,7 @@ static int omap_gpio_probe(struct platform_device *pdev)
 
 	match = of_match_device(of_match_ptr(omap_gpio_match), dev);
 
-	pdata = match ? match->data : dev->platform_data;
+	pdata = match ? match->data : dev_get_platdata(dev);
 	if (!pdata)
 		return -EINVAL;
 
@@ -1400,7 +1444,7 @@ void omap2_gpio_prepare_for_idle(int pwr_mode)
 	struct gpio_bank *bank;
 
 	list_for_each_entry(bank, &omap_gpio_list, node) {
-		if (!bank->mod_usage || !bank->loses_context)
+		if (!BANK_USED(bank) || !bank->loses_context)
 			continue;
 
 		bank->power_mode = pwr_mode;
@@ -1414,7 +1458,7 @@ void omap2_gpio_resume_after_idle(void)
 	struct gpio_bank *bank;
 
 	list_for_each_entry(bank, &omap_gpio_list, node) {
-		if (!bank->mod_usage || !bank->loses_context)
+		if (!BANK_USED(bank) || !bank->loses_context)
 			continue;
 
 		pm_runtime_get_sync(bank->dev);
diff --git a/drivers/gpio/gpio-palmas.c b/drivers/gpio/gpio-palmas.c
index e3a4e56f5a42..8588af0f7661 100644
--- a/drivers/gpio/gpio-palmas.c
+++ b/drivers/gpio/gpio-palmas.c
@@ -43,9 +43,22 @@ static int palmas_gpio_get(struct gpio_chip *gc, unsigned offset)
 	unsigned int val;
 	int ret;
 
-	ret = palmas_read(palmas, PALMAS_GPIO_BASE, PALMAS_GPIO_DATA_IN, &val);
+	ret = palmas_read(palmas, PALMAS_GPIO_BASE, PALMAS_GPIO_DATA_DIR, &val);
 	if (ret < 0) {
-		dev_err(gc->dev, "GPIO_DATA_IN read failed, err = %d\n", ret);
+		dev_err(gc->dev, "GPIO_DATA_DIR read failed, err = %d\n", ret);
+		return ret;
+	}
+
+	if (val & (1 << offset)) {
+		ret = palmas_read(palmas, PALMAS_GPIO_BASE,
+				  PALMAS_GPIO_DATA_OUT, &val);
+	} else {
+		ret = palmas_read(palmas, PALMAS_GPIO_BASE,
+				  PALMAS_GPIO_DATA_IN, &val);
+	}
+	if (ret < 0) {
+		dev_err(gc->dev, "GPIO_DATA_IN/OUT read failed, err = %d\n",
+			ret);
 		return ret;
 	}
 	return !!(val & BIT(offset));
@@ -134,7 +147,7 @@ static int palmas_gpio_probe(struct platform_device *pdev)
 	palmas_gpio->gpio_chip.get	= palmas_gpio_get;
 	palmas_gpio->gpio_chip.dev = &pdev->dev;
 #ifdef CONFIG_OF_GPIO
-	palmas_gpio->gpio_chip.of_node = palmas->dev->of_node;
+	palmas_gpio->gpio_chip.of_node = pdev->dev.of_node;
 #endif
 	palmas_pdata = dev_get_platdata(palmas->dev);
 	if (palmas_pdata && palmas_pdata->gpio_base)
@@ -159,9 +172,19 @@ static int palmas_gpio_remove(struct platform_device *pdev)
 	return gpiochip_remove(&palmas_gpio->gpio_chip);
 }
 
+static struct of_device_id of_palmas_gpio_match[] = {
+	{ .compatible = "ti,palmas-gpio"},
+	{ .compatible = "ti,tps65913-gpio"},
+	{ .compatible = "ti,tps65914-gpio"},
+	{ .compatible = "ti,tps80036-gpio"},
+	{ },
+};
+MODULE_DEVICE_TABLE(of, of_palmas_gpio_match);
+
 static struct platform_driver palmas_gpio_driver = {
 	.driver.name	= "palmas-gpio",
 	.driver.owner	= THIS_MODULE,
+	.driver.of_match_table = of_palmas_gpio_match,
 	.probe		= palmas_gpio_probe,
 	.remove		= palmas_gpio_remove,
 };
diff --git a/drivers/gpio/gpio-pca953x.c b/drivers/gpio/gpio-pca953x.c
index 426c51dd420c..cdd1aa12b895 100644
--- a/drivers/gpio/gpio-pca953x.c
+++ b/drivers/gpio/gpio-pca953x.c
@@ -18,7 +18,7 @@
 #include <linux/irq.h>
 #include <linux/irqdomain.h>
 #include <linux/i2c.h>
-#include <linux/i2c/pca953x.h>
+#include <linux/platform_data/pca953x.h>
 #include <linux/slab.h>
 #ifdef CONFIG_OF_GPIO
 #include <linux/of_platform.h>
@@ -308,7 +308,7 @@ static int pca953x_gpio_get_value(struct gpio_chip *gc, unsigned off)
 		return 0;
 	}
 
-	return (reg_val & (1u << off)) ? 1 : 0;
+	return (reg_val & (1u << (off % BANK_SZ))) ? 1 : 0;
 }
 
 static void pca953x_gpio_set_value(struct gpio_chip *gc, unsigned off, int val)
@@ -731,7 +731,7 @@ static int pca953x_probe(struct i2c_client *client,
 	if (chip == NULL)
 		return -ENOMEM;
 
-	pdata = client->dev.platform_data;
+	pdata = dev_get_platdata(&client->dev);
 	if (pdata) {
 		irq_base = pdata->irq_base;
 		chip->gpio_start = pdata->gpio_base;
@@ -785,7 +785,7 @@ static int pca953x_probe(struct i2c_client *client,
 
 static int pca953x_remove(struct i2c_client *client)
 {
-	struct pca953x_platform_data *pdata = client->dev.platform_data;
+	struct pca953x_platform_data *pdata = dev_get_platdata(&client->dev);
 	struct pca953x_chip *chip = i2c_get_clientdata(client);
 	int ret = 0;
 
diff --git a/drivers/gpio/gpio-pcf857x.c b/drivers/gpio/gpio-pcf857x.c
index e8faf53f3875..9e61bb0719d0 100644
--- a/drivers/gpio/gpio-pcf857x.c
+++ b/drivers/gpio/gpio-pcf857x.c
@@ -18,15 +18,15 @@
  * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
-#include <linux/kernel.h>
-#include <linux/slab.h>
 #include <linux/gpio.h>
 #include <linux/i2c.h>
 #include <linux/i2c/pcf857x.h>
 #include <linux/interrupt.h>
 #include <linux/irq.h>
 #include <linux/irqdomain.h>
+#include <linux/kernel.h>
 #include <linux/module.h>
+#include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/workqueue.h>
 
@@ -223,7 +223,6 @@ static void pcf857x_irq_domain_cleanup(struct pcf857x *gpio)
 }
 
 static int pcf857x_irq_domain_init(struct pcf857x *gpio,
-				   struct pcf857x_platform_data *pdata,
 				   struct i2c_client *client)
 {
 	int status;
@@ -262,7 +261,7 @@ static int pcf857x_probe(struct i2c_client *client,
 	struct pcf857x			*gpio;
 	int				status;
 
-	pdata = client->dev.platform_data;
+	pdata = dev_get_platdata(&client->dev);
 	if (!pdata) {
 		dev_dbg(&client->dev, "no platform data\n");
 	}
@@ -286,8 +285,8 @@ static int pcf857x_probe(struct i2c_client *client,
 	gpio->chip.ngpio		= id->driver_data;
 
 	/* enable gpio_to_irq() if platform has settings */
-	if (pdata && client->irq) {
-		status = pcf857x_irq_domain_init(gpio, pdata, client);
+	if (client->irq) {
+		status = pcf857x_irq_domain_init(gpio, client);
 		if (status < 0) {
 			dev_err(&client->dev, "irq_domain init failed\n");
 			goto fail;
@@ -388,7 +387,7 @@ fail:
 	dev_dbg(&client->dev, "probe error %d for '%s'\n",
 			status, client->name);
 
-	if (pdata && client->irq)
+	if (client->irq)
 		pcf857x_irq_domain_cleanup(gpio);
 
 	return status;
@@ -396,7 +395,7 @@ fail:
 
 static int pcf857x_remove(struct i2c_client *client)
 {
-	struct pcf857x_platform_data	*pdata = client->dev.platform_data;
+	struct pcf857x_platform_data	*pdata = dev_get_platdata(&client->dev);
 	struct pcf857x			*gpio = i2c_get_clientdata(client);
 	int				status = 0;
 
@@ -411,7 +410,7 @@ static int pcf857x_remove(struct i2c_client *client)
 		}
 	}
 
-	if (pdata && client->irq)
+	if (client->irq)
 		pcf857x_irq_domain_cleanup(gpio);
 
 	status = gpiochip_remove(&gpio->chip);
diff --git a/drivers/gpio/gpio-pl061.c b/drivers/gpio/gpio-pl061.c
index 6a4bd0dae0ce..4274e2e70ef8 100644
--- a/drivers/gpio/gpio-pl061.c
+++ b/drivers/gpio/gpio-pl061.c
@@ -259,7 +259,7 @@ static const struct irq_domain_ops pl061_domain_ops = {
 static int pl061_probe(struct amba_device *adev, const struct amba_id *id)
 {
 	struct device *dev = &adev->dev;
-	struct pl061_platform_data *pdata = dev->platform_data;
+	struct pl061_platform_data *pdata = dev_get_platdata(dev);
 	struct pl061_gpio *chip;
 	int ret, irq, i, irq_base;
 
diff --git a/drivers/gpio/gpio-pxa.c b/drivers/gpio/gpio-pxa.c
index df2199dd1499..cc13d1b74fad 100644
--- a/drivers/gpio/gpio-pxa.c
+++ b/drivers/gpio/gpio-pxa.c
@@ -524,8 +524,8 @@ const struct irq_domain_ops pxa_irq_domain_ops = {
 
 static int pxa_gpio_probe_dt(struct platform_device *pdev)
 {
-	int ret, nr_gpios;
-	struct device_node *prev, *next, *np = pdev->dev.of_node;
+	int ret = 0, nr_gpios;
+	struct device_node *np = pdev->dev.of_node;
 	const struct of_device_id *of_id =
 				of_match_device(pxa_gpio_dt_ids, &pdev->dev);
 	const struct pxa_gpio_id *gpio_id;
@@ -537,20 +537,13 @@ static int pxa_gpio_probe_dt(struct platform_device *pdev)
 	gpio_id = of_id->data;
 	gpio_type = gpio_id->type;
 
-	next = of_get_next_child(np, NULL);
-	prev = next;
-	if (!next) {
-		dev_err(&pdev->dev, "Failed to find child gpio node\n");
-		ret = -EINVAL;
-		goto err;
-	}
-	of_node_put(prev);
 	nr_gpios = gpio_id->gpio_nums;
 	pxa_last_gpio = nr_gpios - 1;
 
 	irq_base = irq_alloc_descs(-1, 0, nr_gpios, 0);
 	if (irq_base < 0) {
 		dev_err(&pdev->dev, "Failed to allocate IRQ numbers\n");
+		ret = irq_base;
 		goto err;
 	}
 	domain = irq_domain_add_legacy(np, nr_gpios, irq_base, 0,
diff --git a/drivers/gpio/gpio-rcar.c b/drivers/gpio/gpio-rcar.c
index e8198dd68615..6038966ab045 100644
--- a/drivers/gpio/gpio-rcar.c
+++ b/drivers/gpio/gpio-rcar.c
@@ -285,7 +285,7 @@ static struct irq_domain_ops gpio_rcar_irq_domain_ops = {
 
 static void gpio_rcar_parse_pdata(struct gpio_rcar_priv *p)
 {
-	struct gpio_rcar_config *pdata = p->pdev->dev.platform_data;
+	struct gpio_rcar_config *pdata = dev_get_platdata(&p->pdev->dev);
 	struct device_node *np = p->pdev->dev.of_node;
 	struct of_phandle_args args;
 	int ret;
@@ -293,10 +293,9 @@ static void gpio_rcar_parse_pdata(struct gpio_rcar_priv *p)
 	if (pdata) {
 		p->config = *pdata;
 	} else if (IS_ENABLED(CONFIG_OF) && np) {
-		ret = of_parse_phandle_with_args(np, "gpio-ranges",
-				"#gpio-range-cells", 0, &args);
-		p->config.number_of_pins = ret == 0 && args.args_count == 3
-					 ? args.args[2]
+		ret = of_parse_phandle_with_fixed_args(np, "gpio-ranges", 3, 0,
+						       &args);
+		p->config.number_of_pins = ret == 0 ? args.args[2]
 					 : RCAR_MAX_GPIO_PER_BANK;
 		p->config.gpio_base = -1;
 	}
diff --git a/drivers/gpio/gpio-rdc321x.c b/drivers/gpio/gpio-rdc321x.c
index 368c3c00fca5..88577c3272a5 100644
--- a/drivers/gpio/gpio-rdc321x.c
+++ b/drivers/gpio/gpio-rdc321x.c
@@ -135,7 +135,7 @@ static int rdc321x_gpio_probe(struct platform_device *pdev)
 	struct rdc321x_gpio *rdc321x_gpio_dev;
 	struct rdc321x_gpio_pdata *pdata;
 
-	pdata = pdev->dev.platform_data;
+	pdata = dev_get_platdata(&pdev->dev);
 	if (!pdata) {
 		dev_err(&pdev->dev, "no platform data supplied\n");
 		return -ENODEV;
diff --git a/drivers/gpio/gpio-samsung.c b/drivers/gpio/gpio-samsung.c
index a1392f47bbda..358a21c2d811 100644
--- a/drivers/gpio/gpio-samsung.c
+++ b/drivers/gpio/gpio-samsung.c
@@ -161,28 +161,6 @@ int s3c24xx_gpio_setpull_1down(struct samsung_gpio_chip *chip,
 	return s3c24xx_gpio_setpull_1(chip, off, pull, S3C_GPIO_PULL_DOWN);
 }
 
-static int exynos_gpio_setpull(struct samsung_gpio_chip *chip,
-				unsigned int off, samsung_gpio_pull_t pull)
-{
-	if (pull == S3C_GPIO_PULL_UP)
-		pull = 3;
-
-	return samsung_gpio_setpull_updown(chip, off, pull);
-}
-
-static samsung_gpio_pull_t exynos_gpio_getpull(struct samsung_gpio_chip *chip,
-						unsigned int off)
-{
-	samsung_gpio_pull_t pull;
-
-	pull = samsung_gpio_getpull_updown(chip, off);
-
-	if (pull == 3)
-		pull = S3C_GPIO_PULL_UP;
-
-	return pull;
-}
-
 /*
  * samsung_gpio_setcfg_2bit - Samsung 2bit style GPIO configuration.
  * @chip: The gpio chip that is being configured.
@@ -444,15 +422,6 @@ static struct samsung_gpio_cfg s3c24xx_gpiocfg_banka = {
 };
 #endif
 
-#if defined(CONFIG_ARCH_EXYNOS4) || defined(CONFIG_SOC_EXYNOS5250)
-static struct samsung_gpio_cfg exynos_gpio_cfg = {
-	.set_pull	= exynos_gpio_setpull,
-	.get_pull	= exynos_gpio_getpull,
-	.set_config	= samsung_gpio_setcfg_4bit,
-	.get_config	= samsung_gpio_getcfg_4bit,
-};
-#endif
-
 #if defined(CONFIG_CPU_S5P6440) || defined(CONFIG_CPU_S5P6450)
 static struct samsung_gpio_cfg s5p64x0_gpio_cfg_rbank = {
 	.cfg_eint	= 0x3,
@@ -495,15 +464,6 @@ static struct samsung_gpio_cfg samsung_gpio_cfgs[] = {
 		.set_config	= samsung_gpio_setcfg_2bit,
 		.get_config	= samsung_gpio_getcfg_2bit,
 	},
-	[8] = {
-		.set_pull	= exynos_gpio_setpull,
-		.get_pull	= exynos_gpio_getpull,
-	},
-	[9] = {
-		.cfg_eint	= 0x3,
-		.set_pull	= exynos_gpio_setpull,
-		.get_pull	= exynos_gpio_getpull,
-	}
 };
 
 /*
@@ -2115,833 +2075,6 @@ static struct samsung_gpio_chip s5pv210_gpios_4bit[] = {
 #endif
 };
 
-/*
- * Followings are the gpio banks in EXYNOS SoCs
- *
- * The 'config' member when left to NULL, is initialized to the default
- * structure exynos_gpio_cfg in the init function below.
- *
- * The 'base' member is also initialized in the init function below.
- * Note: The initialization of 'base' member of samsung_gpio_chip structure
- * uses the above macro and depends on the banks being listed in order here.
- */
-
-#ifdef CONFIG_ARCH_EXYNOS4
-static struct samsung_gpio_chip exynos4_gpios_1[] = {
-	{
-		.chip	= {
-			.base	= EXYNOS4_GPA0(0),
-			.ngpio	= EXYNOS4_GPIO_A0_NR,
-			.label	= "GPA0",
-		},
-	}, {
-		.chip	= {
-			.base	= EXYNOS4_GPA1(0),
-			.ngpio	= EXYNOS4_GPIO_A1_NR,
-			.label	= "GPA1",
-		},
-	}, {
-		.chip	= {
-			.base	= EXYNOS4_GPB(0),
-			.ngpio	= EXYNOS4_GPIO_B_NR,
-			.label	= "GPB",
-		},
-	}, {
-		.chip	= {
-			.base	= EXYNOS4_GPC0(0),
-			.ngpio	= EXYNOS4_GPIO_C0_NR,
-			.label	= "GPC0",
-		},
-	}, {
-		.chip	= {
-			.base	= EXYNOS4_GPC1(0),
-			.ngpio	= EXYNOS4_GPIO_C1_NR,
-			.label	= "GPC1",
-		},
-	}, {
-		.chip	= {
-			.base	= EXYNOS4_GPD0(0),
-			.ngpio	= EXYNOS4_GPIO_D0_NR,
-			.label	= "GPD0",
-		},
-	}, {
-		.chip	= {
-			.base	= EXYNOS4_GPD1(0),
-			.ngpio	= EXYNOS4_GPIO_D1_NR,
-			.label	= "GPD1",
-		},
-	}, {
-		.chip	= {
-			.base	= EXYNOS4_GPE0(0),
-			.ngpio	= EXYNOS4_GPIO_E0_NR,
-			.label	= "GPE0",
-		},
-	}, {
-		.chip	= {
-			.base	= EXYNOS4_GPE1(0),
-			.ngpio	= EXYNOS4_GPIO_E1_NR,
-			.label	= "GPE1",
-		},
-	}, {
-		.chip	= {
-			.base	= EXYNOS4_GPE2(0),
-			.ngpio	= EXYNOS4_GPIO_E2_NR,
-			.label	= "GPE2",
-		},
-	}, {
-		.chip	= {
-			.base	= EXYNOS4_GPE3(0),
-			.ngpio	= EXYNOS4_GPIO_E3_NR,
-			.label	= "GPE3",
-		},
-	}, {
-		.chip	= {
-			.base	= EXYNOS4_GPE4(0),
-			.ngpio	= EXYNOS4_GPIO_E4_NR,
-			.label	= "GPE4",
-		},
-	}, {
-		.chip	= {
-			.base	= EXYNOS4_GPF0(0),
-			.ngpio	= EXYNOS4_GPIO_F0_NR,
-			.label	= "GPF0",
-		},
-	}, {
-		.chip	= {
-			.base	= EXYNOS4_GPF1(0),
-			.ngpio	= EXYNOS4_GPIO_F1_NR,
-			.label	= "GPF1",
-		},
-	}, {
-		.chip	= {
-			.base	= EXYNOS4_GPF2(0),
-			.ngpio	= EXYNOS4_GPIO_F2_NR,
-			.label	= "GPF2",
-		},
-	}, {
-		.chip	= {
-			.base	= EXYNOS4_GPF3(0),
-			.ngpio	= EXYNOS4_GPIO_F3_NR,
-			.label	= "GPF3",
-		},
-	},
-};
-#endif
-
-#ifdef CONFIG_ARCH_EXYNOS4
-static struct samsung_gpio_chip exynos4_gpios_2[] = {
-	{
-		.chip	= {
-			.base	= EXYNOS4_GPJ0(0),
-			.ngpio	= EXYNOS4_GPIO_J0_NR,
-			.label	= "GPJ0",
-		},
-	}, {
-		.chip	= {
-			.base	= EXYNOS4_GPJ1(0),
-			.ngpio	= EXYNOS4_GPIO_J1_NR,
-			.label	= "GPJ1",
-		},
-	}, {
-		.chip	= {
-			.base	= EXYNOS4_GPK0(0),
-			.ngpio	= EXYNOS4_GPIO_K0_NR,
-			.label	= "GPK0",
-		},
-	}, {
-		.chip	= {
-			.base	= EXYNOS4_GPK1(0),
-			.ngpio	= EXYNOS4_GPIO_K1_NR,
-			.label	= "GPK1",
-		},
-	}, {
-		.chip	= {
-			.base	= EXYNOS4_GPK2(0),
-			.ngpio	= EXYNOS4_GPIO_K2_NR,
-			.label	= "GPK2",
-		},
-	}, {
-		.chip	= {
-			.base	= EXYNOS4_GPK3(0),
-			.ngpio	= EXYNOS4_GPIO_K3_NR,
-			.label	= "GPK3",
-		},
-	}, {
-		.chip	= {
-			.base	= EXYNOS4_GPL0(0),
-			.ngpio	= EXYNOS4_GPIO_L0_NR,
-			.label	= "GPL0",
-		},
-	}, {
-		.chip	= {
-			.base	= EXYNOS4_GPL1(0),
-			.ngpio	= EXYNOS4_GPIO_L1_NR,
-			.label	= "GPL1",
-		},
-	}, {
-		.chip	= {
-			.base	= EXYNOS4_GPL2(0),
-			.ngpio	= EXYNOS4_GPIO_L2_NR,
-			.label	= "GPL2",
-		},
-	}, {
-		.config	= &samsung_gpio_cfgs[8],
-		.chip	= {
-			.base	= EXYNOS4_GPY0(0),
-			.ngpio	= EXYNOS4_GPIO_Y0_NR,
-			.label	= "GPY0",
-		},
-	}, {
-		.config	= &samsung_gpio_cfgs[8],
-		.chip	= {
-			.base	= EXYNOS4_GPY1(0),
-			.ngpio	= EXYNOS4_GPIO_Y1_NR,
-			.label	= "GPY1",
-		},
-	}, {
-		.config	= &samsung_gpio_cfgs[8],
-		.chip	= {
-			.base	= EXYNOS4_GPY2(0),
-			.ngpio	= EXYNOS4_GPIO_Y2_NR,
-			.label	= "GPY2",
-		},
-	}, {
-		.config	= &samsung_gpio_cfgs[8],
-		.chip	= {
-			.base	= EXYNOS4_GPY3(0),
-			.ngpio	= EXYNOS4_GPIO_Y3_NR,
-			.label	= "GPY3",
-		},
-	}, {
-		.config	= &samsung_gpio_cfgs[8],
-		.chip	= {
-			.base	= EXYNOS4_GPY4(0),
-			.ngpio	= EXYNOS4_GPIO_Y4_NR,
-			.label	= "GPY4",
-		},
-	}, {
-		.config	= &samsung_gpio_cfgs[8],
-		.chip	= {
-			.base	= EXYNOS4_GPY5(0),
-			.ngpio	= EXYNOS4_GPIO_Y5_NR,
-			.label	= "GPY5",
-		},
-	}, {
-		.config	= &samsung_gpio_cfgs[8],
-		.chip	= {
-			.base	= EXYNOS4_GPY6(0),
-			.ngpio	= EXYNOS4_GPIO_Y6_NR,
-			.label	= "GPY6",
-		},
-	}, {
-		.config	= &samsung_gpio_cfgs[9],
-		.irq_base = IRQ_EINT(0),
-		.chip	= {
-			.base	= EXYNOS4_GPX0(0),
-			.ngpio	= EXYNOS4_GPIO_X0_NR,
-			.label	= "GPX0",
-			.to_irq	= samsung_gpiolib_to_irq,
-		},
-	}, {
-		.config	= &samsung_gpio_cfgs[9],
-		.irq_base = IRQ_EINT(8),
-		.chip	= {
-			.base	= EXYNOS4_GPX1(0),
-			.ngpio	= EXYNOS4_GPIO_X1_NR,
-			.label	= "GPX1",
-			.to_irq	= samsung_gpiolib_to_irq,
-		},
-	}, {
-		.config	= &samsung_gpio_cfgs[9],
-		.irq_base = IRQ_EINT(16),
-		.chip	= {
-			.base	= EXYNOS4_GPX2(0),
-			.ngpio	= EXYNOS4_GPIO_X2_NR,
-			.label	= "GPX2",
-			.to_irq	= samsung_gpiolib_to_irq,
-		},
-	}, {
-		.config	= &samsung_gpio_cfgs[9],
-		.irq_base = IRQ_EINT(24),
-		.chip	= {
-			.base	= EXYNOS4_GPX3(0),
-			.ngpio	= EXYNOS4_GPIO_X3_NR,
-			.label	= "GPX3",
-			.to_irq	= samsung_gpiolib_to_irq,
-		},
-	},
-};
-#endif
-
-#ifdef CONFIG_ARCH_EXYNOS4
-static struct samsung_gpio_chip exynos4_gpios_3[] = {
-	{
-		.chip	= {
-			.base	= EXYNOS4_GPZ(0),
-			.ngpio	= EXYNOS4_GPIO_Z_NR,
-			.label	= "GPZ",
-		},
-	},
-};
-#endif
-
-#ifdef CONFIG_SOC_EXYNOS5250
-static struct samsung_gpio_chip exynos5_gpios_1[] = {
-	{
-		.chip	= {
-			.base	= EXYNOS5_GPA0(0),
-			.ngpio	= EXYNOS5_GPIO_A0_NR,
-			.label	= "GPA0",
-		},
-	}, {
-		.chip	= {
-			.base	= EXYNOS5_GPA1(0),
-			.ngpio	= EXYNOS5_GPIO_A1_NR,
-			.label	= "GPA1",
-		},
-	}, {
-		.chip	= {
-			.base	= EXYNOS5_GPA2(0),
-			.ngpio	= EXYNOS5_GPIO_A2_NR,
-			.label	= "GPA2",
-		},
-	}, {
-		.chip	= {
-			.base	= EXYNOS5_GPB0(0),
-			.ngpio	= EXYNOS5_GPIO_B0_NR,
-			.label	= "GPB0",
-		},
-	}, {
-		.chip	= {
-			.base	= EXYNOS5_GPB1(0),
-			.ngpio	= EXYNOS5_GPIO_B1_NR,
-			.label	= "GPB1",
-		},
-	}, {
-		.chip	= {
-			.base	= EXYNOS5_GPB2(0),
-			.ngpio	= EXYNOS5_GPIO_B2_NR,
-			.label	= "GPB2",
-		},
-	}, {
-		.chip	= {
-			.base	= EXYNOS5_GPB3(0),
-			.ngpio	= EXYNOS5_GPIO_B3_NR,
-			.label	= "GPB3",
-		},
-	}, {
-		.chip	= {
-			.base	= EXYNOS5_GPC0(0),
-			.ngpio	= EXYNOS5_GPIO_C0_NR,
-			.label	= "GPC0",
-		},
-	}, {
-		.chip	= {
-			.base	= EXYNOS5_GPC1(0),
-			.ngpio	= EXYNOS5_GPIO_C1_NR,
-			.label	= "GPC1",
-		},
-	}, {
-		.chip	= {
-			.base	= EXYNOS5_GPC2(0),
-			.ngpio	= EXYNOS5_GPIO_C2_NR,
-			.label	= "GPC2",
-		},
-	}, {
-		.chip	= {
-			.base	= EXYNOS5_GPC3(0),
-			.ngpio	= EXYNOS5_GPIO_C3_NR,
-			.label	= "GPC3",
-		},
-	}, {
-		.chip	= {
-			.base	= EXYNOS5_GPD0(0),
-			.ngpio	= EXYNOS5_GPIO_D0_NR,
-			.label	= "GPD0",
-		},
-	}, {
-		.chip	= {
-			.base	= EXYNOS5_GPD1(0),
-			.ngpio	= EXYNOS5_GPIO_D1_NR,
-			.label	= "GPD1",
-		},
-	}, {
-		.chip	= {
-			.base	= EXYNOS5_GPY0(0),
-			.ngpio	= EXYNOS5_GPIO_Y0_NR,
-			.label	= "GPY0",
-		},
-	}, {
-		.chip	= {
-			.base	= EXYNOS5_GPY1(0),
-			.ngpio	= EXYNOS5_GPIO_Y1_NR,
-			.label	= "GPY1",
-		},
-	}, {
-		.chip	= {
-			.base	= EXYNOS5_GPY2(0),
-			.ngpio	= EXYNOS5_GPIO_Y2_NR,
-			.label	= "GPY2",
-		},
-	}, {
-		.chip	= {
-			.base	= EXYNOS5_GPY3(0),
-			.ngpio	= EXYNOS5_GPIO_Y3_NR,
-			.label	= "GPY3",
-		},
-	}, {
-		.chip	= {
-			.base	= EXYNOS5_GPY4(0),
-			.ngpio	= EXYNOS5_GPIO_Y4_NR,
-			.label	= "GPY4",
-		},
-	}, {
-		.chip	= {
-			.base	= EXYNOS5_GPY5(0),
-			.ngpio	= EXYNOS5_GPIO_Y5_NR,
-			.label	= "GPY5",
-		},
-	}, {
-		.chip	= {
-			.base	= EXYNOS5_GPY6(0),
-			.ngpio	= EXYNOS5_GPIO_Y6_NR,
-			.label	= "GPY6",
-		},
-	}, {
-		.chip	= {
-			.base	= EXYNOS5_GPC4(0),
-			.ngpio	= EXYNOS5_GPIO_C4_NR,
-			.label	= "GPC4",
-		},
-	}, {
-		.config	= &samsung_gpio_cfgs[9],
-		.irq_base = IRQ_EINT(0),
-		.chip	= {
-			.base	= EXYNOS5_GPX0(0),
-			.ngpio	= EXYNOS5_GPIO_X0_NR,
-			.label	= "GPX0",
-			.to_irq	= samsung_gpiolib_to_irq,
-		},
-	}, {
-		.config	= &samsung_gpio_cfgs[9],
-		.irq_base = IRQ_EINT(8),
-		.chip	= {
-			.base	= EXYNOS5_GPX1(0),
-			.ngpio	= EXYNOS5_GPIO_X1_NR,
-			.label	= "GPX1",
-			.to_irq	= samsung_gpiolib_to_irq,
-		},
-	}, {
-		.config	= &samsung_gpio_cfgs[9],
-		.irq_base = IRQ_EINT(16),
-		.chip	= {
-			.base	= EXYNOS5_GPX2(0),
-			.ngpio	= EXYNOS5_GPIO_X2_NR,
-			.label	= "GPX2",
-			.to_irq	= samsung_gpiolib_to_irq,
-		},
-	}, {
-		.config	= &samsung_gpio_cfgs[9],
-		.irq_base = IRQ_EINT(24),
-		.chip	= {
-			.base	= EXYNOS5_GPX3(0),
-			.ngpio	= EXYNOS5_GPIO_X3_NR,
-			.label	= "GPX3",
-			.to_irq	= samsung_gpiolib_to_irq,
-		},
-	},
-};
-#endif
-
-#ifdef CONFIG_SOC_EXYNOS5250
-static struct samsung_gpio_chip exynos5_gpios_2[] = {
-	{
-		.chip	= {
-			.base	= EXYNOS5_GPE0(0),
-			.ngpio	= EXYNOS5_GPIO_E0_NR,
-			.label	= "GPE0",
-		},
-	}, {
-		.chip	= {
-			.base	= EXYNOS5_GPE1(0),
-			.ngpio	= EXYNOS5_GPIO_E1_NR,
-			.label	= "GPE1",
-		},
-	}, {
-		.chip	= {
-			.base	= EXYNOS5_GPF0(0),
-			.ngpio	= EXYNOS5_GPIO_F0_NR,
-			.label	= "GPF0",
-		},
-	}, {
-		.chip	= {
-			.base	= EXYNOS5_GPF1(0),
-			.ngpio	= EXYNOS5_GPIO_F1_NR,
-			.label	= "GPF1",
-		},
-	}, {
-		.chip	= {
-			.base	= EXYNOS5_GPG0(0),
-			.ngpio	= EXYNOS5_GPIO_G0_NR,
-			.label	= "GPG0",
-		},
-	}, {
-		.chip	= {
-			.base	= EXYNOS5_GPG1(0),
-			.ngpio	= EXYNOS5_GPIO_G1_NR,
-			.label	= "GPG1",
-		},
-	}, {
-		.chip	= {
-			.base	= EXYNOS5_GPG2(0),
-			.ngpio	= EXYNOS5_GPIO_G2_NR,
-			.label	= "GPG2",
-		},
-	}, {
-		.chip	= {
-			.base	= EXYNOS5_GPH0(0),
-			.ngpio	= EXYNOS5_GPIO_H0_NR,
-			.label	= "GPH0",
-		},
-	}, {
-		.chip	= {
-			.base	= EXYNOS5_GPH1(0),
-			.ngpio	= EXYNOS5_GPIO_H1_NR,
-			.label	= "GPH1",
-
-		},
-	},
-};
-#endif
-
-#ifdef CONFIG_SOC_EXYNOS5250
-static struct samsung_gpio_chip exynos5_gpios_3[] = {
-	{
-		.chip	= {
-			.base	= EXYNOS5_GPV0(0),
-			.ngpio	= EXYNOS5_GPIO_V0_NR,
-			.label	= "GPV0",
-		},
-	}, {
-		.chip	= {
-			.base	= EXYNOS5_GPV1(0),
-			.ngpio	= EXYNOS5_GPIO_V1_NR,
-			.label	= "GPV1",
-		},
-	}, {
-		.chip	= {
-			.base	= EXYNOS5_GPV2(0),
-			.ngpio	= EXYNOS5_GPIO_V2_NR,
-			.label	= "GPV2",
-		},
-	}, {
-		.chip	= {
-			.base	= EXYNOS5_GPV3(0),
-			.ngpio	= EXYNOS5_GPIO_V3_NR,
-			.label	= "GPV3",
-		},
-	}, {
-		.chip	= {
-			.base	= EXYNOS5_GPV4(0),
-			.ngpio	= EXYNOS5_GPIO_V4_NR,
-			.label	= "GPV4",
-		},
-	},
-};
-#endif
-
-#ifdef CONFIG_SOC_EXYNOS5250
-static struct samsung_gpio_chip exynos5_gpios_4[] = {
-	{
-		.chip	= {
-			.base	= EXYNOS5_GPZ(0),
-			.ngpio	= EXYNOS5_GPIO_Z_NR,
-			.label	= "GPZ",
-		},
-	},
-};
-#endif
-
-
-#if defined(CONFIG_ARCH_EXYNOS) && defined(CONFIG_OF)
-static int exynos_gpio_xlate(struct gpio_chip *gc,
-			const struct of_phandle_args *gpiospec, u32 *flags)
-{
-	unsigned int pin;
-
-	if (WARN_ON(gc->of_gpio_n_cells < 4))
-		return -EINVAL;
-
-	if (WARN_ON(gpiospec->args_count < gc->of_gpio_n_cells))
-		return -EINVAL;
-
-	if (gpiospec->args[0] > gc->ngpio)
-		return -EINVAL;
-
-	pin = gc->base + gpiospec->args[0];
-
-	if (s3c_gpio_cfgpin(pin, S3C_GPIO_SFN(gpiospec->args[1])))
-		pr_warn("gpio_xlate: failed to set pin function\n");
-	if (s3c_gpio_setpull(pin, gpiospec->args[2] & 0xffff))
-		pr_warn("gpio_xlate: failed to set pin pull up/down\n");
-	if (s5p_gpio_set_drvstr(pin, gpiospec->args[3]))
-		pr_warn("gpio_xlate: failed to set pin drive strength\n");
-
-	if (flags)
-		*flags = gpiospec->args[2] >> 16;
-
-	return gpiospec->args[0];
-}
-
-static const struct of_device_id exynos_gpio_dt_match[] __initdata = {
-	{ .compatible = "samsung,exynos4-gpio", },
-	{}
-};
-
-static __init void exynos_gpiolib_attach_ofnode(struct samsung_gpio_chip *chip,
-						u64 base, u64 offset)
-{
-	struct gpio_chip *gc =  &chip->chip;
-	u64 address;
-
-	if (!of_have_populated_dt())
-		return;
-
-	address = chip->base ? base + ((u32)chip->base & 0xfff) : base + offset;
-	gc->of_node = of_find_matching_node_by_address(NULL,
-			exynos_gpio_dt_match, address);
-	if (!gc->of_node) {
-		pr_info("gpio: device tree node not found for gpio controller"
-			" with base address %08llx\n", address);
-		return;
-	}
-	gc->of_gpio_n_cells = 4;
-	gc->of_xlate = exynos_gpio_xlate;
-}
-#elif defined(CONFIG_ARCH_EXYNOS)
-static __init void exynos_gpiolib_attach_ofnode(struct samsung_gpio_chip *chip,
-						u64 base, u64 offset)
-{
-	return;
-}
-#endif /* defined(CONFIG_ARCH_EXYNOS) && defined(CONFIG_OF) */
-
-static __init void exynos4_gpiolib_init(void)
-{
-#ifdef CONFIG_CPU_EXYNOS4210
-	struct samsung_gpio_chip *chip;
-	int i, nr_chips;
-	void __iomem *gpio_base1, *gpio_base2, *gpio_base3;
-	int group = 0;
-	void __iomem *gpx_base;
-
-	/* gpio part1 */
-	gpio_base1 = ioremap(EXYNOS4_PA_GPIO1, SZ_4K);
-	if (gpio_base1 == NULL) {
-		pr_err("unable to ioremap for gpio_base1\n");
-		goto err_ioremap1;
-	}
-
-	chip = exynos4_gpios_1;
-	nr_chips = ARRAY_SIZE(exynos4_gpios_1);
-
-	for (i = 0; i < nr_chips; i++, chip++) {
-		if (!chip->config) {
-			chip->config = &exynos_gpio_cfg;
-			chip->group = group++;
-		}
-		exynos_gpiolib_attach_ofnode(chip,
-				EXYNOS4_PA_GPIO1, i * 0x20);
-	}
-	samsung_gpiolib_add_4bit_chips(exynos4_gpios_1,
-				       nr_chips, gpio_base1);
-
-	/* gpio part2 */
-	gpio_base2 = ioremap(EXYNOS4_PA_GPIO2, SZ_4K);
-	if (gpio_base2 == NULL) {
-		pr_err("unable to ioremap for gpio_base2\n");
-		goto err_ioremap2;
-	}
-
-	/* need to set base address for gpx */
-	chip = &exynos4_gpios_2[16];
-	gpx_base = gpio_base2 + 0xC00;
-	for (i = 0; i < 4; i++, chip++, gpx_base += 0x20)
-		chip->base = gpx_base;
-
-	chip = exynos4_gpios_2;
-	nr_chips = ARRAY_SIZE(exynos4_gpios_2);
-
-	for (i = 0; i < nr_chips; i++, chip++) {
-		if (!chip->config) {
-			chip->config = &exynos_gpio_cfg;
-			chip->group = group++;
-		}
-		exynos_gpiolib_attach_ofnode(chip,
-				EXYNOS4_PA_GPIO2, i * 0x20);
-	}
-	samsung_gpiolib_add_4bit_chips(exynos4_gpios_2,
-				       nr_chips, gpio_base2);
-
-	/* gpio part3 */
-	gpio_base3 = ioremap(EXYNOS4_PA_GPIO3, SZ_256);
-	if (gpio_base3 == NULL) {
-		pr_err("unable to ioremap for gpio_base3\n");
-		goto err_ioremap3;
-	}
-
-	chip = exynos4_gpios_3;
-	nr_chips = ARRAY_SIZE(exynos4_gpios_3);
-
-	for (i = 0; i < nr_chips; i++, chip++) {
-		if (!chip->config) {
-			chip->config = &exynos_gpio_cfg;
-			chip->group = group++;
-		}
-		exynos_gpiolib_attach_ofnode(chip,
-				EXYNOS4_PA_GPIO3, i * 0x20);
-	}
-	samsung_gpiolib_add_4bit_chips(exynos4_gpios_3,
-				       nr_chips, gpio_base3);
-
-#if defined(CONFIG_CPU_EXYNOS4210) && defined(CONFIG_S5P_GPIO_INT)
-	s5p_register_gpioint_bank(IRQ_GPIO_XA, 0, IRQ_GPIO1_NR_GROUPS);
-	s5p_register_gpioint_bank(IRQ_GPIO_XB, IRQ_GPIO1_NR_GROUPS, IRQ_GPIO2_NR_GROUPS);
-#endif
-
-	return;
-
-err_ioremap3:
-	iounmap(gpio_base2);
-err_ioremap2:
-	iounmap(gpio_base1);
-err_ioremap1:
-	return;
-#endif	/* CONFIG_CPU_EXYNOS4210 */
-}
-
-static __init void exynos5_gpiolib_init(void)
-{
-#ifdef CONFIG_SOC_EXYNOS5250
-	struct samsung_gpio_chip *chip;
-	int i, nr_chips;
-	void __iomem *gpio_base1, *gpio_base2, *gpio_base3, *gpio_base4;
-	int group = 0;
-	void __iomem *gpx_base;
-
-	/* gpio part1 */
-	gpio_base1 = ioremap(EXYNOS5_PA_GPIO1, SZ_4K);
-	if (gpio_base1 == NULL) {
-		pr_err("unable to ioremap for gpio_base1\n");
-		goto err_ioremap1;
-	}
-
-	/* need to set base address for gpc4 */
-	exynos5_gpios_1[20].base = gpio_base1 + 0x2E0;
-
-	/* need to set base address for gpx */
-	chip = &exynos5_gpios_1[21];
-	gpx_base = gpio_base1 + 0xC00;
-	for (i = 0; i < 4; i++, chip++, gpx_base += 0x20)
-		chip->base = gpx_base;
-
-	chip = exynos5_gpios_1;
-	nr_chips = ARRAY_SIZE(exynos5_gpios_1);
-
-	for (i = 0; i < nr_chips; i++, chip++) {
-		if (!chip->config) {
-			chip->config = &exynos_gpio_cfg;
-			chip->group = group++;
-		}
-		exynos_gpiolib_attach_ofnode(chip,
-				EXYNOS5_PA_GPIO1, i * 0x20);
-	}
-	samsung_gpiolib_add_4bit_chips(exynos5_gpios_1,
-				       nr_chips, gpio_base1);
-
-	/* gpio part2 */
-	gpio_base2 = ioremap(EXYNOS5_PA_GPIO2, SZ_4K);
-	if (gpio_base2 == NULL) {
-		pr_err("unable to ioremap for gpio_base2\n");
-		goto err_ioremap2;
-	}
-
-	chip = exynos5_gpios_2;
-	nr_chips = ARRAY_SIZE(exynos5_gpios_2);
-
-	for (i = 0; i < nr_chips; i++, chip++) {
-		if (!chip->config) {
-			chip->config = &exynos_gpio_cfg;
-			chip->group = group++;
-		}
-		exynos_gpiolib_attach_ofnode(chip,
-				EXYNOS5_PA_GPIO2, i * 0x20);
-	}
-	samsung_gpiolib_add_4bit_chips(exynos5_gpios_2,
-				       nr_chips, gpio_base2);
-
-	/* gpio part3 */
-	gpio_base3 = ioremap(EXYNOS5_PA_GPIO3, SZ_4K);
-	if (gpio_base3 == NULL) {
-		pr_err("unable to ioremap for gpio_base3\n");
-		goto err_ioremap3;
-	}
-
-	/* need to set base address for gpv */
-	exynos5_gpios_3[0].base = gpio_base3;
-	exynos5_gpios_3[1].base = gpio_base3 + 0x20;
-	exynos5_gpios_3[2].base = gpio_base3 + 0x60;
-	exynos5_gpios_3[3].base = gpio_base3 + 0x80;
-	exynos5_gpios_3[4].base = gpio_base3 + 0xC0;
-
-	chip = exynos5_gpios_3;
-	nr_chips = ARRAY_SIZE(exynos5_gpios_3);
-
-	for (i = 0; i < nr_chips; i++, chip++) {
-		if (!chip->config) {
-			chip->config = &exynos_gpio_cfg;
-			chip->group = group++;
-		}
-		exynos_gpiolib_attach_ofnode(chip,
-				EXYNOS5_PA_GPIO3, i * 0x20);
-	}
-	samsung_gpiolib_add_4bit_chips(exynos5_gpios_3,
-				       nr_chips, gpio_base3);
-
-	/* gpio part4 */
-	gpio_base4 = ioremap(EXYNOS5_PA_GPIO4, SZ_4K);
-	if (gpio_base4 == NULL) {
-		pr_err("unable to ioremap for gpio_base4\n");
-		goto err_ioremap4;
-	}
-
-	chip = exynos5_gpios_4;
-	nr_chips = ARRAY_SIZE(exynos5_gpios_4);
-
-	for (i = 0; i < nr_chips; i++, chip++) {
-		if (!chip->config) {
-			chip->config = &exynos_gpio_cfg;
-			chip->group = group++;
-		}
-		exynos_gpiolib_attach_ofnode(chip,
-				EXYNOS5_PA_GPIO4, i * 0x20);
-	}
-	samsung_gpiolib_add_4bit_chips(exynos5_gpios_4,
-				       nr_chips, gpio_base4);
-	return;
-
-err_ioremap4:
-	iounmap(gpio_base3);
-err_ioremap3:
-	iounmap(gpio_base2);
-err_ioremap2:
-	iounmap(gpio_base1);
-err_ioremap1:
-	return;
-
-#endif	/* CONFIG_SOC_EXYNOS5250 */
-}
-
 /* TODO: cleanup soc_is_* */
 static __init int samsung_gpiolib_init(void)
 {
@@ -3040,10 +2173,6 @@ static __init int samsung_gpiolib_init(void)
 #if defined(CONFIG_CPU_S5PV210) && defined(CONFIG_S5P_GPIO_INT)
 		s5p_register_gpioint_bank(IRQ_GPIOINT, 0, S5P_GPIOINT_GROUP_MAXNR);
 #endif
-	} else if (soc_is_exynos4210()) {
-		exynos4_gpiolib_init();
-	} else if (soc_is_exynos5250()) {
-		exynos5_gpiolib_init();
 	} else {
 		WARN(1, "Unknown SoC in gpio-samsung, no GPIOs added\n");
 		return -ENODEV;
diff --git a/drivers/gpio/gpio-spear-spics.c b/drivers/gpio/gpio-spear-spics.c
index 7a4bf7c0d98f..e9a0415834ea 100644
--- a/drivers/gpio/gpio-spear-spics.c
+++ b/drivers/gpio/gpio-spear-spics.c
@@ -128,18 +128,13 @@ static int spics_gpio_probe(struct platform_device *pdev)
 	struct resource *res;
 	int ret;
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!res) {
-		dev_err(&pdev->dev, "invalid IORESOURCE_MEM\n");
-		return -EBUSY;
-	}
-
 	spics = devm_kzalloc(&pdev->dev, sizeof(*spics), GFP_KERNEL);
 	if (!spics) {
 		dev_err(&pdev->dev, "memory allocation fail\n");
 		return -ENOMEM;
 	}
 
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	spics->base = devm_ioremap_resource(&pdev->dev, res);
 	if (IS_ERR(spics->base))
 		return PTR_ERR(spics->base);
diff --git a/drivers/gpio/gpio-sta2x11.c b/drivers/gpio/gpio-sta2x11.c
index f43ab6aea281..f2fb12c18da9 100644
--- a/drivers/gpio/gpio-sta2x11.c
+++ b/drivers/gpio/gpio-sta2x11.c
@@ -361,7 +361,7 @@ static int gsta_probe(struct platform_device *dev)
 	struct gsta_gpio *chip;
 	struct resource *res;
 
-	pdev = *(struct pci_dev **)(dev->dev.platform_data);
+	pdev = *(struct pci_dev **)dev_get_platdata(&dev->dev);
 	gpio_pdata = dev_get_platdata(&pdev->dev);
 
 	if (gpio_pdata == NULL)
diff --git a/drivers/gpio/gpio-sx150x.c b/drivers/gpio/gpio-sx150x.c
index f371732591d2..d2983e9ad6af 100644
--- a/drivers/gpio/gpio-sx150x.c
+++ b/drivers/gpio/gpio-sx150x.c
@@ -583,7 +583,7 @@ static int sx150x_probe(struct i2c_client *client,
 	struct sx150x_chip *chip;
 	int rc;
 
-	pdata = client->dev.platform_data;
+	pdata = dev_get_platdata(&client->dev);
 	if (!pdata)
 		return -EINVAL;
 
diff --git a/drivers/gpio/gpio-timberdale.c b/drivers/gpio/gpio-timberdale.c
index 4c65f8883204..7a0e956ef1ed 100644
--- a/drivers/gpio/gpio-timberdale.c
+++ b/drivers/gpio/gpio-timberdale.c
@@ -227,7 +227,7 @@ static int timbgpio_probe(struct platform_device *pdev)
 	struct gpio_chip *gc;
 	struct timbgpio *tgpio;
 	struct resource *iomem;
-	struct timbgpio_platform_data *pdata = pdev->dev.platform_data;
+	struct timbgpio_platform_data *pdata = dev_get_platdata(&pdev->dev);
 	int irq = platform_get_irq(pdev, 0);
 
 	if (!pdata || pdata->nr_pins > 32) {
@@ -318,7 +318,7 @@ err_mem:
 static int timbgpio_remove(struct platform_device *pdev)
 {
 	int err;
-	struct timbgpio_platform_data *pdata = pdev->dev.platform_data;
+	struct timbgpio_platform_data *pdata = dev_get_platdata(&pdev->dev);
 	struct timbgpio *tgpio = platform_get_drvdata(pdev);
 	struct resource *iomem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	int irq = platform_get_irq(pdev, 0);
diff --git a/drivers/gpio/gpio-tps65912.c b/drivers/gpio/gpio-tps65912.c
index 30a5844a7dca..276a4229b032 100644
--- a/drivers/gpio/gpio-tps65912.c
+++ b/drivers/gpio/gpio-tps65912.c
@@ -87,7 +87,7 @@ static struct gpio_chip template_chip = {
 static int tps65912_gpio_probe(struct platform_device *pdev)
 {
 	struct tps65912 *tps65912 = dev_get_drvdata(pdev->dev.parent);
-	struct tps65912_board *pdata = tps65912->dev->platform_data;
+	struct tps65912_board *pdata = dev_get_platdata(tps65912->dev);
 	struct tps65912_gpio_data *tps65912_gpio;
 	int ret;
 
diff --git a/drivers/gpio/gpio-ts5500.c b/drivers/gpio/gpio-ts5500.c
index cc53cab8df2a..3df3ebdb3e52 100644
--- a/drivers/gpio/gpio-ts5500.c
+++ b/drivers/gpio/gpio-ts5500.c
@@ -322,7 +322,7 @@ static void ts5500_disable_irq(struct ts5500_priv *priv)
 static int ts5500_dio_probe(struct platform_device *pdev)
 {
 	enum ts5500_blocks block = platform_get_device_id(pdev)->driver_data;
-	struct ts5500_dio_platform_data *pdata = pdev->dev.platform_data;
+	struct ts5500_dio_platform_data *pdata = dev_get_platdata(&pdev->dev);
 	struct device *dev = &pdev->dev;
 	const char *name = dev_name(dev);
 	struct ts5500_priv *priv;
diff --git a/drivers/gpio/gpio-twl4030.c b/drivers/gpio/gpio-twl4030.c
index 4d330e36da1d..d8e4f6efcb29 100644
--- a/drivers/gpio/gpio-twl4030.c
+++ b/drivers/gpio/gpio-twl4030.c
@@ -256,7 +256,7 @@ static int twl_request(struct gpio_chip *chip, unsigned offset)
 		/* optionally have the first two GPIOs switch vMMC1
 		 * and vMMC2 power supplies based on card presence.
 		 */
-		pdata = chip->dev->platform_data;
+		pdata = dev_get_platdata(chip->dev);
 		if (pdata)
 			value |= pdata->mmc_cd & 0x03;
 
@@ -460,7 +460,7 @@ static struct twl4030_gpio_platform_data *of_gpio_twl4030(struct device *dev)
 
 static int gpio_twl4030_probe(struct platform_device *pdev)
 {
-	struct twl4030_gpio_platform_data *pdata = pdev->dev.platform_data;
+	struct twl4030_gpio_platform_data *pdata = dev_get_platdata(&pdev->dev);
 	struct device_node *node = pdev->dev.of_node;
 	struct gpio_twl4030_priv *priv;
 	int ret, irq_base;
@@ -556,7 +556,7 @@ out:
 /* Cannot use as gpio_twl4030_probe() calls us */
 static int gpio_twl4030_remove(struct platform_device *pdev)
 {
-	struct twl4030_gpio_platform_data *pdata = pdev->dev.platform_data;
+	struct twl4030_gpio_platform_data *pdata = dev_get_platdata(&pdev->dev);
 	struct gpio_twl4030_priv *priv = platform_get_drvdata(pdev);
 	int status;
 
diff --git a/drivers/gpio/gpio-twl6040.c b/drivers/gpio/gpio-twl6040.c
index 0be82c6dd796..d420d30b86e7 100644
--- a/drivers/gpio/gpio-twl6040.c
+++ b/drivers/gpio/gpio-twl6040.c
@@ -84,15 +84,11 @@ static struct gpio_chip twl6040gpo_chip = {
 
 static int gpo_twl6040_probe(struct platform_device *pdev)
 {
-	struct twl6040_gpo_data *pdata = pdev->dev.platform_data;
 	struct device *twl6040_core_dev = pdev->dev.parent;
 	struct twl6040 *twl6040 = dev_get_drvdata(twl6040_core_dev);
 	int ret;
 
-	if (pdata)
-		twl6040gpo_chip.base = pdata->gpio_base;
-	else
-		twl6040gpo_chip.base = -1;
+	twl6040gpo_chip.base = -1;
 
 	if (twl6040_get_revid(twl6040) < TWL6041_REV_ES2_0)
 		twl6040gpo_chip.ngpio = 3; /* twl6040 have 3 GPO */
diff --git a/drivers/gpio/gpio-tz1090-pdc.c b/drivers/gpio/gpio-tz1090-pdc.c
new file mode 100644
index 000000000000..f512da299b3d
--- /dev/null
+++ b/drivers/gpio/gpio-tz1090-pdc.c
@@ -0,0 +1,243 @@
+/*
+ * Toumaz Xenif TZ1090 PDC GPIO handling.
+ *
+ * Copyright (C) 2012-2013 Imagination Technologies Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/bitops.h>
+#include <linux/gpio.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/of_irq.h>
+#include <linux/pinctrl/consumer.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/syscore_ops.h>
+#include <asm/global_lock.h>
+
+/* Register offsets from SOC_GPIO_CONTROL0 */
+#define REG_SOC_GPIO_CONTROL0	0x00
+#define REG_SOC_GPIO_CONTROL1	0x04
+#define REG_SOC_GPIO_CONTROL2	0x08
+#define REG_SOC_GPIO_CONTROL3	0x0c
+#define REG_SOC_GPIO_STATUS	0x80
+
+/* PDC GPIOs go after normal GPIOs */
+#define GPIO_PDC_BASE		90
+#define GPIO_PDC_NGPIO		7
+
+/* Out of PDC gpios, only syswakes have irqs */
+#define GPIO_PDC_IRQ_FIRST	2
+#define GPIO_PDC_NIRQ		3
+
+/**
+ * struct tz1090_pdc_gpio - GPIO bank private data
+ * @chip:	Generic GPIO chip for GPIO bank
+ * @reg:	Base of registers, offset for this GPIO bank
+ * @irq:	IRQ numbers for Syswake GPIOs
+ *
+ * This is the main private data for the PDC GPIO driver. It encapsulates a
+ * gpio_chip, and the callbacks for the gpio_chip can access the private data
+ * with the to_pdc() macro below.
+ */
+struct tz1090_pdc_gpio {
+	struct gpio_chip chip;
+	void __iomem *reg;
+	int irq[GPIO_PDC_NIRQ];
+};
+#define to_pdc(c)	container_of(c, struct tz1090_pdc_gpio, chip)
+
+/* Register accesses into the PDC MMIO area */
+
+static inline void pdc_write(struct tz1090_pdc_gpio *priv, unsigned int reg_offs,
+		      unsigned int data)
+{
+	writel(data, priv->reg + reg_offs);
+}
+
+static inline unsigned int pdc_read(struct tz1090_pdc_gpio *priv,
+			     unsigned int reg_offs)
+{
+	return readl(priv->reg + reg_offs);
+}
+
+/* Generic GPIO interface */
+
+static int tz1090_pdc_gpio_direction_input(struct gpio_chip *chip,
+					   unsigned int offset)
+{
+	struct tz1090_pdc_gpio *priv = to_pdc(chip);
+	u32 value;
+	int lstat;
+
+	__global_lock2(lstat);
+	value = pdc_read(priv, REG_SOC_GPIO_CONTROL1);
+	value |= BIT(offset);
+	pdc_write(priv, REG_SOC_GPIO_CONTROL1, value);
+	__global_unlock2(lstat);
+
+	return 0;
+}
+
+static int tz1090_pdc_gpio_direction_output(struct gpio_chip *chip,
+					    unsigned int offset,
+					    int output_value)
+{
+	struct tz1090_pdc_gpio *priv = to_pdc(chip);
+	u32 value;
+	int lstat;
+
+	__global_lock2(lstat);
+	/* EXT_POWER doesn't seem to have an output value bit */
+	if (offset < 6) {
+		value = pdc_read(priv, REG_SOC_GPIO_CONTROL0);
+		if (output_value)
+			value |= BIT(offset);
+		else
+			value &= ~BIT(offset);
+		pdc_write(priv, REG_SOC_GPIO_CONTROL0, value);
+	}
+
+	value = pdc_read(priv, REG_SOC_GPIO_CONTROL1);
+	value &= ~BIT(offset);
+	pdc_write(priv, REG_SOC_GPIO_CONTROL1, value);
+	__global_unlock2(lstat);
+
+	return 0;
+}
+
+static int tz1090_pdc_gpio_get(struct gpio_chip *chip, unsigned int offset)
+{
+	struct tz1090_pdc_gpio *priv = to_pdc(chip);
+	return pdc_read(priv, REG_SOC_GPIO_STATUS) & BIT(offset);
+}
+
+static void tz1090_pdc_gpio_set(struct gpio_chip *chip, unsigned int offset,
+				int output_value)
+{
+	struct tz1090_pdc_gpio *priv = to_pdc(chip);
+	u32 value;
+	int lstat;
+
+	/* EXT_POWER doesn't seem to have an output value bit */
+	if (offset >= 6)
+		return;
+
+	__global_lock2(lstat);
+	value = pdc_read(priv, REG_SOC_GPIO_CONTROL0);
+	if (output_value)
+		value |= BIT(offset);
+	else
+		value &= ~BIT(offset);
+	pdc_write(priv, REG_SOC_GPIO_CONTROL0, value);
+	__global_unlock2(lstat);
+}
+
+static int tz1090_pdc_gpio_request(struct gpio_chip *chip, unsigned int offset)
+{
+	return pinctrl_request_gpio(chip->base + offset);
+}
+
+static void tz1090_pdc_gpio_free(struct gpio_chip *chip, unsigned int offset)
+{
+	pinctrl_free_gpio(chip->base + offset);
+}
+
+static int tz1090_pdc_gpio_to_irq(struct gpio_chip *chip, unsigned int offset)
+{
+	struct tz1090_pdc_gpio *priv = to_pdc(chip);
+	unsigned int syswake = offset - GPIO_PDC_IRQ_FIRST;
+	int irq;
+
+	/* only syswakes have irqs */
+	if (syswake >= GPIO_PDC_NIRQ)
+		return -EINVAL;
+
+	irq = priv->irq[syswake];
+	if (!irq)
+		return -EINVAL;
+
+	return irq;
+}
+
+static int tz1090_pdc_gpio_probe(struct platform_device *pdev)
+{
+	struct device_node *np = pdev->dev.of_node;
+	struct resource *res_regs;
+	struct tz1090_pdc_gpio *priv;
+	unsigned int i;
+
+	if (!np) {
+		dev_err(&pdev->dev, "must be instantiated via devicetree\n");
+		return -ENOENT;
+	}
+
+	res_regs = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!res_regs) {
+		dev_err(&pdev->dev, "cannot find registers resource\n");
+		return -ENOENT;
+	}
+
+	priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv) {
+		dev_err(&pdev->dev, "unable to allocate driver data\n");
+		return -ENOMEM;
+	}
+
+	/* Ioremap the registers */
+	priv->reg = devm_ioremap(&pdev->dev, res_regs->start,
+				 res_regs->end - res_regs->start);
+	if (!priv->reg) {
+		dev_err(&pdev->dev, "unable to ioremap registers\n");
+		return -ENOMEM;
+	}
+
+	/* Set up GPIO chip */
+	priv->chip.label		= "tz1090-pdc-gpio";
+	priv->chip.dev			= &pdev->dev;
+	priv->chip.direction_input	= tz1090_pdc_gpio_direction_input;
+	priv->chip.direction_output	= tz1090_pdc_gpio_direction_output;
+	priv->chip.get			= tz1090_pdc_gpio_get;
+	priv->chip.set			= tz1090_pdc_gpio_set;
+	priv->chip.free			= tz1090_pdc_gpio_free;
+	priv->chip.request		= tz1090_pdc_gpio_request;
+	priv->chip.to_irq		= tz1090_pdc_gpio_to_irq;
+	priv->chip.of_node		= np;
+
+	/* GPIO numbering */
+	priv->chip.base			= GPIO_PDC_BASE;
+	priv->chip.ngpio		= GPIO_PDC_NGPIO;
+
+	/* Map the syswake irqs */
+	for (i = 0; i < GPIO_PDC_NIRQ; ++i)
+		priv->irq[i] = irq_of_parse_and_map(np, i);
+
+	/* Add the GPIO bank */
+	gpiochip_add(&priv->chip);
+
+	return 0;
+}
+
+static struct of_device_id tz1090_pdc_gpio_of_match[] = {
+	{ .compatible = "img,tz1090-pdc-gpio" },
+	{ },
+};
+
+static struct platform_driver tz1090_pdc_gpio_driver = {
+	.driver = {
+		.name		= "tz1090-pdc-gpio",
+		.owner		= THIS_MODULE,
+		.of_match_table	= tz1090_pdc_gpio_of_match,
+	},
+	.probe		= tz1090_pdc_gpio_probe,
+};
+
+static int __init tz1090_pdc_gpio_init(void)
+{
+	return platform_driver_register(&tz1090_pdc_gpio_driver);
+}
+subsys_initcall(tz1090_pdc_gpio_init);
diff --git a/drivers/gpio/gpio-tz1090.c b/drivers/gpio/gpio-tz1090.c
new file mode 100644
index 000000000000..23e061392411
--- /dev/null
+++ b/drivers/gpio/gpio-tz1090.c
@@ -0,0 +1,606 @@
+/*
+ * Toumaz Xenif TZ1090 GPIO handling.
+ *
+ * Copyright (C) 2008-2013 Imagination Technologies Ltd.
+ *
+ *  Based on ARM PXA code and others.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/bitops.h>
+#include <linux/export.h>
+#include <linux/gpio.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/irq.h>
+#include <linux/irqdomain.h>
+#include <linux/kernel.h>
+#include <linux/of_irq.h>
+#include <linux/pinctrl/consumer.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/syscore_ops.h>
+#include <asm/global_lock.h>
+
+/* Register offsets from bank base address */
+#define REG_GPIO_DIR		0x00
+#define REG_GPIO_IRQ_PLRT	0x20
+#define REG_GPIO_IRQ_TYPE	0x30
+#define REG_GPIO_IRQ_EN		0x40
+#define REG_GPIO_IRQ_STS	0x50
+#define REG_GPIO_BIT_EN		0x60
+#define REG_GPIO_DIN		0x70
+#define REG_GPIO_DOUT		0x80
+
+/* REG_GPIO_IRQ_PLRT */
+#define REG_GPIO_IRQ_PLRT_LOW	0
+#define REG_GPIO_IRQ_PLRT_HIGH	1
+
+/* REG_GPIO_IRQ_TYPE */
+#define REG_GPIO_IRQ_TYPE_LEVEL	0
+#define REG_GPIO_IRQ_TYPE_EDGE	1
+
+/**
+ * struct tz1090_gpio_bank - GPIO bank private data
+ * @chip:	Generic GPIO chip for GPIO bank
+ * @domain:	IRQ domain for GPIO bank (may be NULL)
+ * @reg:	Base of registers, offset for this GPIO bank
+ * @irq:	IRQ number for GPIO bank
+ * @label:	Debug GPIO bank label, used for storage of chip->label
+ *
+ * This is the main private data for a GPIO bank. It encapsulates a gpio_chip,
+ * and the callbacks for the gpio_chip can access the private data with the
+ * to_bank() macro below.
+ */
+struct tz1090_gpio_bank {
+	struct gpio_chip chip;
+	struct irq_domain *domain;
+	void __iomem *reg;
+	int irq;
+	char label[16];
+};
+#define to_bank(c)	container_of(c, struct tz1090_gpio_bank, chip)
+
+/**
+ * struct tz1090_gpio - Overall GPIO device private data
+ * @dev:	Device (from platform device)
+ * @reg:	Base of GPIO registers
+ *
+ * Represents the overall GPIO device. This structure is actually only
+ * temporary, and used during init.
+ */
+struct tz1090_gpio {
+	struct device *dev;
+	void __iomem *reg;
+};
+
+/**
+ * struct tz1090_gpio_bank_info - Temporary registration info for GPIO bank
+ * @priv:	Overall GPIO device private data
+ * @node:	Device tree node specific to this GPIO bank
+ * @index:	Index of bank in range 0-2
+ */
+struct tz1090_gpio_bank_info {
+	struct tz1090_gpio *priv;
+	struct device_node *node;
+	unsigned int index;
+};
+
+/* Convenience register accessors */
+static inline void tz1090_gpio_write(struct tz1090_gpio_bank *bank,
+			      unsigned int reg_offs, u32 data)
+{
+	iowrite32(data, bank->reg + reg_offs);
+}
+
+static inline u32 tz1090_gpio_read(struct tz1090_gpio_bank *bank,
+			    unsigned int reg_offs)
+{
+	return ioread32(bank->reg + reg_offs);
+}
+
+/* caller must hold LOCK2 */
+static inline void _tz1090_gpio_clear_bit(struct tz1090_gpio_bank *bank,
+					  unsigned int reg_offs,
+					  unsigned int offset)
+{
+	u32 value;
+
+	value = tz1090_gpio_read(bank, reg_offs);
+	value &= ~BIT(offset);
+	tz1090_gpio_write(bank, reg_offs, value);
+}
+
+static void tz1090_gpio_clear_bit(struct tz1090_gpio_bank *bank,
+				  unsigned int reg_offs,
+				  unsigned int offset)
+{
+	int lstat;
+
+	__global_lock2(lstat);
+	_tz1090_gpio_clear_bit(bank, reg_offs, offset);
+	__global_unlock2(lstat);
+}
+
+/* caller must hold LOCK2 */
+static inline void _tz1090_gpio_set_bit(struct tz1090_gpio_bank *bank,
+					unsigned int reg_offs,
+					unsigned int offset)
+{
+	u32 value;
+
+	value = tz1090_gpio_read(bank, reg_offs);
+	value |= BIT(offset);
+	tz1090_gpio_write(bank, reg_offs, value);
+}
+
+static void tz1090_gpio_set_bit(struct tz1090_gpio_bank *bank,
+				unsigned int reg_offs,
+				unsigned int offset)
+{
+	int lstat;
+
+	__global_lock2(lstat);
+	_tz1090_gpio_set_bit(bank, reg_offs, offset);
+	__global_unlock2(lstat);
+}
+
+/* caller must hold LOCK2 */
+static inline void _tz1090_gpio_mod_bit(struct tz1090_gpio_bank *bank,
+					unsigned int reg_offs,
+					unsigned int offset,
+					bool val)
+{
+	u32 value;
+
+	value = tz1090_gpio_read(bank, reg_offs);
+	value &= ~BIT(offset);
+	if (val)
+		value |= BIT(offset);
+	tz1090_gpio_write(bank, reg_offs, value);
+}
+
+static void tz1090_gpio_mod_bit(struct tz1090_gpio_bank *bank,
+				unsigned int reg_offs,
+				unsigned int offset,
+				bool val)
+{
+	int lstat;
+
+	__global_lock2(lstat);
+	_tz1090_gpio_mod_bit(bank, reg_offs, offset, val);
+	__global_unlock2(lstat);
+}
+
+static inline int tz1090_gpio_read_bit(struct tz1090_gpio_bank *bank,
+				       unsigned int reg_offs,
+				       unsigned int offset)
+{
+	return tz1090_gpio_read(bank, reg_offs) & BIT(offset);
+}
+
+/* GPIO chip callbacks */
+
+static int tz1090_gpio_direction_input(struct gpio_chip *chip,
+				       unsigned int offset)
+{
+	struct tz1090_gpio_bank *bank = to_bank(chip);
+	tz1090_gpio_set_bit(bank, REG_GPIO_DIR, offset);
+
+	return 0;
+}
+
+static int tz1090_gpio_direction_output(struct gpio_chip *chip,
+					unsigned int offset, int output_value)
+{
+	struct tz1090_gpio_bank *bank = to_bank(chip);
+	int lstat;
+
+	__global_lock2(lstat);
+	_tz1090_gpio_mod_bit(bank, REG_GPIO_DOUT, offset, output_value);
+	_tz1090_gpio_clear_bit(bank, REG_GPIO_DIR, offset);
+	__global_unlock2(lstat);
+
+	return 0;
+}
+
+/*
+ * Return GPIO level
+ */
+static int tz1090_gpio_get(struct gpio_chip *chip, unsigned int offset)
+{
+	struct tz1090_gpio_bank *bank = to_bank(chip);
+
+	return tz1090_gpio_read_bit(bank, REG_GPIO_DIN, offset);
+}
+
+/*
+ * Set output GPIO level
+ */
+static void tz1090_gpio_set(struct gpio_chip *chip, unsigned int offset,
+			    int output_value)
+{
+	struct tz1090_gpio_bank *bank = to_bank(chip);
+
+	tz1090_gpio_mod_bit(bank, REG_GPIO_DOUT, offset, output_value);
+}
+
+static int tz1090_gpio_request(struct gpio_chip *chip, unsigned int offset)
+{
+	struct tz1090_gpio_bank *bank = to_bank(chip);
+	int ret;
+
+	ret = pinctrl_request_gpio(chip->base + offset);
+	if (ret)
+		return ret;
+
+	tz1090_gpio_set_bit(bank, REG_GPIO_DIR, offset);
+	tz1090_gpio_set_bit(bank, REG_GPIO_BIT_EN, offset);
+
+	return 0;
+}
+
+static void tz1090_gpio_free(struct gpio_chip *chip, unsigned int offset)
+{
+	struct tz1090_gpio_bank *bank = to_bank(chip);
+
+	pinctrl_free_gpio(chip->base + offset);
+
+	tz1090_gpio_clear_bit(bank, REG_GPIO_BIT_EN, offset);
+}
+
+static int tz1090_gpio_to_irq(struct gpio_chip *chip, unsigned int offset)
+{
+	struct tz1090_gpio_bank *bank = to_bank(chip);
+
+	if (!bank->domain)
+		return -EINVAL;
+
+	return irq_create_mapping(bank->domain, offset);
+}
+
+/* IRQ chip handlers */
+
+/* Get TZ1090 GPIO chip from irq data provided to generic IRQ callbacks */
+static inline struct tz1090_gpio_bank *irqd_to_gpio_bank(struct irq_data *data)
+{
+	return (struct tz1090_gpio_bank *)data->domain->host_data;
+}
+
+static void tz1090_gpio_irq_polarity(struct tz1090_gpio_bank *bank,
+				     unsigned int offset, unsigned int polarity)
+{
+	tz1090_gpio_mod_bit(bank, REG_GPIO_IRQ_PLRT, offset, polarity);
+}
+
+static void tz1090_gpio_irq_type(struct tz1090_gpio_bank *bank,
+				 unsigned int offset, unsigned int type)
+{
+	tz1090_gpio_mod_bit(bank, REG_GPIO_IRQ_TYPE, offset, type);
+}
+
+/* set polarity to trigger on next edge, whether rising or falling */
+static void tz1090_gpio_irq_next_edge(struct tz1090_gpio_bank *bank,
+				      unsigned int offset)
+{
+	unsigned int value_p, value_i;
+	int lstat;
+
+	/*
+	 * Set the GPIO's interrupt polarity to the opposite of the current
+	 * input value so that the next edge triggers an interrupt.
+	 */
+	__global_lock2(lstat);
+	value_i = ~tz1090_gpio_read(bank, REG_GPIO_DIN);
+	value_p = tz1090_gpio_read(bank, REG_GPIO_IRQ_PLRT);
+	value_p &= ~BIT(offset);
+	value_p |= value_i & BIT(offset);
+	tz1090_gpio_write(bank, REG_GPIO_IRQ_PLRT, value_p);
+	__global_unlock2(lstat);
+}
+
+static unsigned int gpio_startup_irq(struct irq_data *data)
+{
+	/*
+	 * This warning indicates that the type of the irq hasn't been set
+	 * before enabling the irq. This would normally be done by passing some
+	 * trigger flags to request_irq().
+	 */
+	WARN(irqd_get_trigger_type(data) == IRQ_TYPE_NONE,
+		"irq type not set before enabling gpio irq %d", data->irq);
+
+	irq_gc_ack_clr_bit(data);
+	irq_gc_mask_set_bit(data);
+	return 0;
+}
+
+static int gpio_set_irq_type(struct irq_data *data, unsigned int flow_type)
+{
+	struct tz1090_gpio_bank *bank = irqd_to_gpio_bank(data);
+	unsigned int type;
+	unsigned int polarity;
+
+	switch (flow_type) {
+	case IRQ_TYPE_EDGE_BOTH:
+		type = REG_GPIO_IRQ_TYPE_EDGE;
+		polarity = REG_GPIO_IRQ_PLRT_LOW;
+		break;
+	case IRQ_TYPE_EDGE_RISING:
+		type = REG_GPIO_IRQ_TYPE_EDGE;
+		polarity = REG_GPIO_IRQ_PLRT_HIGH;
+		break;
+	case IRQ_TYPE_EDGE_FALLING:
+		type = REG_GPIO_IRQ_TYPE_EDGE;
+		polarity = REG_GPIO_IRQ_PLRT_LOW;
+		break;
+	case IRQ_TYPE_LEVEL_HIGH:
+		type = REG_GPIO_IRQ_TYPE_LEVEL;
+		polarity = REG_GPIO_IRQ_PLRT_HIGH;
+		break;
+	case IRQ_TYPE_LEVEL_LOW:
+		type = REG_GPIO_IRQ_TYPE_LEVEL;
+		polarity = REG_GPIO_IRQ_PLRT_LOW;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	tz1090_gpio_irq_type(bank, data->hwirq, type);
+	irq_setup_alt_chip(data, flow_type);
+
+	if (flow_type == IRQ_TYPE_EDGE_BOTH)
+		tz1090_gpio_irq_next_edge(bank, data->hwirq);
+	else
+		tz1090_gpio_irq_polarity(bank, data->hwirq, polarity);
+
+	return 0;
+}
+
+#ifdef CONFIG_SUSPEND
+static int gpio_set_irq_wake(struct irq_data *data, unsigned int on)
+{
+	struct tz1090_gpio_bank *bank = irqd_to_gpio_bank(data);
+
+#ifdef CONFIG_PM_DEBUG
+	pr_info("irq_wake irq%d state:%d\n", data->irq, on);
+#endif
+
+	/* wake on gpio block interrupt */
+	return irq_set_irq_wake(bank->irq, on);
+}
+#else
+#define gpio_set_irq_wake NULL
+#endif
+
+static void tz1090_gpio_irq_handler(unsigned int irq, struct irq_desc *desc)
+{
+	irq_hw_number_t hw;
+	unsigned int irq_stat, irq_no;
+	struct tz1090_gpio_bank *bank;
+	struct irq_desc *child_desc;
+
+	bank = (struct tz1090_gpio_bank *)irq_desc_get_handler_data(desc);
+	irq_stat = tz1090_gpio_read(bank, REG_GPIO_DIR) &
+		   tz1090_gpio_read(bank, REG_GPIO_IRQ_STS) &
+		   tz1090_gpio_read(bank, REG_GPIO_IRQ_EN) &
+		   0x3FFFFFFF; /* 30 bits only */
+
+	for (hw = 0; irq_stat; irq_stat >>= 1, ++hw) {
+		if (!(irq_stat & 1))
+			continue;
+
+		irq_no = irq_linear_revmap(bank->domain, hw);
+		child_desc = irq_to_desc(irq_no);
+
+		/* Toggle edge for pin with both edges triggering enabled */
+		if (irqd_get_trigger_type(&child_desc->irq_data)
+				== IRQ_TYPE_EDGE_BOTH)
+			tz1090_gpio_irq_next_edge(bank, hw);
+
+		generic_handle_irq_desc(irq_no, child_desc);
+	}
+}
+
+static int tz1090_gpio_bank_probe(struct tz1090_gpio_bank_info *info)
+{
+	struct device_node *np = info->node;
+	struct device *dev = info->priv->dev;
+	struct tz1090_gpio_bank *bank;
+	struct irq_chip_generic *gc;
+	int err;
+
+	bank = devm_kzalloc(dev, sizeof(*bank), GFP_KERNEL);
+	if (!bank) {
+		dev_err(dev, "unable to allocate driver data\n");
+		return -ENOMEM;
+	}
+
+	/* Offset the main registers to the first register in this bank */
+	bank->reg = info->priv->reg + info->index * 4;
+
+	/* Set up GPIO chip */
+	snprintf(bank->label, sizeof(bank->label), "tz1090-gpio-%u",
+		 info->index);
+	bank->chip.label		= bank->label;
+	bank->chip.dev			= dev;
+	bank->chip.direction_input	= tz1090_gpio_direction_input;
+	bank->chip.direction_output	= tz1090_gpio_direction_output;
+	bank->chip.get			= tz1090_gpio_get;
+	bank->chip.set			= tz1090_gpio_set;
+	bank->chip.free			= tz1090_gpio_free;
+	bank->chip.request		= tz1090_gpio_request;
+	bank->chip.to_irq		= tz1090_gpio_to_irq;
+	bank->chip.of_node		= np;
+
+	/* GPIO numbering from 0 */
+	bank->chip.base			= info->index * 30;
+	bank->chip.ngpio		= 30;
+
+	/* Add the GPIO bank */
+	gpiochip_add(&bank->chip);
+
+	/* Get the GPIO bank IRQ if provided */
+	bank->irq = irq_of_parse_and_map(np, 0);
+
+	/* The interrupt is optional (it may be used by another core on chip) */
+	if (bank->irq < 0) {
+		dev_info(dev, "IRQ not provided for bank %u, IRQs disabled\n",
+			 info->index);
+		return 0;
+	}
+
+	dev_info(dev, "Setting up IRQs for GPIO bank %u\n",
+		 info->index);
+
+	/*
+	 * Initialise all interrupts to disabled so we don't get
+	 * spurious ones on a dirty boot and hit the BUG_ON in the
+	 * handler.
+	 */
+	tz1090_gpio_write(bank, REG_GPIO_IRQ_EN, 0);
+
+	/* Add a virtual IRQ for each GPIO */
+	bank->domain = irq_domain_add_linear(np,
+					     bank->chip.ngpio,
+					     &irq_generic_chip_ops,
+					     bank);
+
+	/* Set up a generic irq chip with 2 chip types (level and edge) */
+	err = irq_alloc_domain_generic_chips(bank->domain, bank->chip.ngpio, 2,
+					     bank->label, handle_bad_irq, 0, 0,
+					     IRQ_GC_INIT_NESTED_LOCK);
+	if (err) {
+		dev_info(dev,
+			 "irq_alloc_domain_generic_chips failed for bank %u, IRQs disabled\n",
+			 info->index);
+		irq_domain_remove(bank->domain);
+		return 0;
+	}
+
+	gc = irq_get_domain_generic_chip(bank->domain, 0);
+	gc->reg_base	= bank->reg;
+
+	/* level chip type */
+	gc->chip_types[0].type			= IRQ_TYPE_LEVEL_MASK;
+	gc->chip_types[0].handler		= handle_level_irq;
+	gc->chip_types[0].regs.ack		= REG_GPIO_IRQ_STS;
+	gc->chip_types[0].regs.mask		= REG_GPIO_IRQ_EN;
+	gc->chip_types[0].chip.irq_startup	= gpio_startup_irq,
+	gc->chip_types[0].chip.irq_ack		= irq_gc_ack_clr_bit,
+	gc->chip_types[0].chip.irq_mask		= irq_gc_mask_clr_bit,
+	gc->chip_types[0].chip.irq_unmask	= irq_gc_mask_set_bit,
+	gc->chip_types[0].chip.irq_set_type	= gpio_set_irq_type,
+	gc->chip_types[0].chip.irq_set_wake	= gpio_set_irq_wake,
+	gc->chip_types[0].chip.flags		= IRQCHIP_MASK_ON_SUSPEND,
+
+	/* edge chip type */
+	gc->chip_types[1].type			= IRQ_TYPE_EDGE_BOTH;
+	gc->chip_types[1].handler		= handle_edge_irq;
+	gc->chip_types[1].regs.ack		= REG_GPIO_IRQ_STS;
+	gc->chip_types[1].regs.mask		= REG_GPIO_IRQ_EN;
+	gc->chip_types[1].chip.irq_startup	= gpio_startup_irq,
+	gc->chip_types[1].chip.irq_ack		= irq_gc_ack_clr_bit,
+	gc->chip_types[1].chip.irq_mask		= irq_gc_mask_clr_bit,
+	gc->chip_types[1].chip.irq_unmask	= irq_gc_mask_set_bit,
+	gc->chip_types[1].chip.irq_set_type	= gpio_set_irq_type,
+	gc->chip_types[1].chip.irq_set_wake	= gpio_set_irq_wake,
+	gc->chip_types[1].chip.flags		= IRQCHIP_MASK_ON_SUSPEND,
+
+	/* Setup chained handler for this GPIO bank */
+	irq_set_handler_data(bank->irq, bank);
+	irq_set_chained_handler(bank->irq, tz1090_gpio_irq_handler);
+
+	return 0;
+}
+
+static void tz1090_gpio_register_banks(struct tz1090_gpio *priv)
+{
+	struct device_node *np = priv->dev->of_node;
+	struct device_node *node;
+
+	for_each_available_child_of_node(np, node) {
+		struct tz1090_gpio_bank_info info;
+		u32 addr;
+		int ret;
+
+		ret = of_property_read_u32(node, "reg", &addr);
+		if (ret) {
+			dev_err(priv->dev, "invalid reg on %s\n",
+				node->full_name);
+			continue;
+		}
+		if (addr >= 3) {
+			dev_err(priv->dev, "index %u in %s out of range\n",
+				addr, node->full_name);
+			continue;
+		}
+
+		info.index = addr;
+		info.node = of_node_get(node);
+		info.priv = priv;
+
+		ret = tz1090_gpio_bank_probe(&info);
+		if (ret) {
+			dev_err(priv->dev, "failure registering %s\n",
+				node->full_name);
+			of_node_put(node);
+			continue;
+		}
+	}
+}
+
+static int tz1090_gpio_probe(struct platform_device *pdev)
+{
+	struct device_node *np = pdev->dev.of_node;
+	struct resource *res_regs;
+	struct tz1090_gpio priv;
+
+	if (!np) {
+		dev_err(&pdev->dev, "must be instantiated via devicetree\n");
+		return -ENOENT;
+	}
+
+	res_regs = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!res_regs) {
+		dev_err(&pdev->dev, "cannot find registers resource\n");
+		return -ENOENT;
+	}
+
+	priv.dev = &pdev->dev;
+
+	/* Ioremap the registers */
+	priv.reg = devm_ioremap(&pdev->dev, res_regs->start,
+				 res_regs->end - res_regs->start);
+	if (!priv.reg) {
+		dev_err(&pdev->dev, "unable to ioremap registers\n");
+		return -ENOMEM;
+	}
+
+	/* Look for banks */
+	tz1090_gpio_register_banks(&priv);
+
+	return 0;
+}
+
+static struct of_device_id tz1090_gpio_of_match[] = {
+	{ .compatible = "img,tz1090-gpio" },
+	{ },
+};
+
+static struct platform_driver tz1090_gpio_driver = {
+	.driver = {
+		.name		= "tz1090-gpio",
+		.owner		= THIS_MODULE,
+		.of_match_table	= tz1090_gpio_of_match,
+	},
+	.probe		= tz1090_gpio_probe,
+};
+
+static int __init tz1090_gpio_init(void)
+{
+	return platform_driver_register(&tz1090_gpio_driver);
+}
+subsys_initcall(tz1090_gpio_init);
diff --git a/drivers/gpio/gpio-ucb1400.c b/drivers/gpio/gpio-ucb1400.c
index 6d0feb234d3c..1a605f2a0f55 100644
--- a/drivers/gpio/gpio-ucb1400.c
+++ b/drivers/gpio/gpio-ucb1400.c
@@ -45,7 +45,7 @@ static void ucb1400_gpio_set(struct gpio_chip *gc, unsigned off, int val)
 
 static int ucb1400_gpio_probe(struct platform_device *dev)
 {
-	struct ucb1400_gpio *ucb = dev->dev.platform_data;
+	struct ucb1400_gpio *ucb = dev_get_platdata(&dev->dev);
 	int err = 0;
 
 	if (!(ucb && ucb->gpio_offset)) {
diff --git a/drivers/gpio/gpio-wm831x.c b/drivers/gpio/gpio-wm831x.c
index 2a743e10ecb6..456000c5c457 100644
--- a/drivers/gpio/gpio-wm831x.c
+++ b/drivers/gpio/gpio-wm831x.c
@@ -246,7 +246,7 @@ static struct gpio_chip template_chip = {
 static int wm831x_gpio_probe(struct platform_device *pdev)
 {
 	struct wm831x *wm831x = dev_get_drvdata(pdev->dev.parent);
-	struct wm831x_pdata *pdata = wm831x->dev->platform_data;
+	struct wm831x_pdata *pdata = dev_get_platdata(wm831x->dev);
 	struct wm831x_gpio *wm831x_gpio;
 	int ret;
 
diff --git a/drivers/gpio/gpio-wm8350.c b/drivers/gpio/gpio-wm8350.c
index 0b598cf3df9d..fc49154be7b1 100644
--- a/drivers/gpio/gpio-wm8350.c
+++ b/drivers/gpio/gpio-wm8350.c
@@ -112,7 +112,7 @@ static struct gpio_chip template_chip = {
 static int wm8350_gpio_probe(struct platform_device *pdev)
 {
 	struct wm8350 *wm8350 = dev_get_drvdata(pdev->dev.parent);
-	struct wm8350_platform_data *pdata = wm8350->dev->platform_data;
+	struct wm8350_platform_data *pdata = dev_get_platdata(wm8350->dev);
 	struct wm8350_gpio_data *wm8350_gpio;
 	int ret;
 
diff --git a/drivers/gpio/gpio-wm8994.c b/drivers/gpio/gpio-wm8994.c
index ae409fd94af7..a53dbdefc7ee 100644
--- a/drivers/gpio/gpio-wm8994.c
+++ b/drivers/gpio/gpio-wm8994.c
@@ -248,7 +248,7 @@ static struct gpio_chip template_chip = {
 static int wm8994_gpio_probe(struct platform_device *pdev)
 {
 	struct wm8994 *wm8994 = dev_get_drvdata(pdev->dev.parent);
-	struct wm8994_pdata *pdata = wm8994->dev->platform_data;
+	struct wm8994_pdata *pdata = dev_get_platdata(wm8994->dev);
 	struct wm8994_gpio *wm8994_gpio;
 	int ret;
 
diff --git a/drivers/gpio/gpiolib-of.c b/drivers/gpio/gpiolib-of.c
index 665f9530c950..0dfaf20e4dad 100644
--- a/drivers/gpio/gpiolib-of.c
+++ b/drivers/gpio/gpiolib-of.c
@@ -76,7 +76,8 @@ int of_get_named_gpio_flags(struct device_node *np, const char *propname,
 	ret = of_parse_phandle_with_args(np, propname, "#gpio-cells", index,
 					 &gg_data.gpiospec);
 	if (ret) {
-		pr_debug("%s: can't parse gpios property\n", __func__);
+		pr_debug("%s: can't parse gpios property of node '%s[%d]'\n",
+			__func__, np->full_name, index);
 		return ret;
 	}
 
@@ -194,8 +195,8 @@ static void of_gpiochip_add_pin_range(struct gpio_chip *chip)
 		return;
 
 	for (;; index++) {
-		ret = of_parse_phandle_with_args(np, "gpio-ranges",
-				"#gpio-range-cells", index, &pinspec);
+		ret = of_parse_phandle_with_fixed_args(np, "gpio-ranges", 3,
+				index, &pinspec);
 		if (ret)
 			break;
 
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index ff0fd655729f..0dee0e0c247a 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -136,7 +136,7 @@ static struct gpio_desc *gpio_to_desc(unsigned gpio)
  */
 static int desc_to_gpio(const struct gpio_desc *desc)
 {
-	return desc->chip->base + gpio_chip_hwgpio(desc);
+	return desc - &gpio_desc[0];
 }
 
 
@@ -349,7 +349,7 @@ static ssize_t gpio_value_store(struct device *dev,
 	else {
 		long		value;
 
-		status = strict_strtol(buf, 0, &value);
+		status = kstrtol(buf, 0, &value);
 		if (status == 0) {
 			if (test_bit(FLAG_ACTIVE_LOW, &desc->flags))
 				value = !value;
@@ -570,7 +570,7 @@ static ssize_t gpio_active_low_store(struct device *dev,
 	} else {
 		long		value;
 
-		status = strict_strtol(buf, 0, &value);
+		status = kstrtol(buf, 0, &value);
 		if (status == 0)
 			status = sysfs_set_active_low(desc, dev, value != 0);
 	}
@@ -652,7 +652,7 @@ static ssize_t export_store(struct class *class,
 	struct gpio_desc	*desc;
 	int			status;
 
-	status = strict_strtol(buf, 0, &gpio);
+	status = kstrtol(buf, 0, &gpio);
 	if (status < 0)
 		goto done;
 
@@ -694,7 +694,7 @@ static ssize_t unexport_store(struct class *class,
 	struct gpio_desc	*desc;
 	int			status;
 
-	status = strict_strtol(buf, 0, &gpio);
+	status = kstrtol(buf, 0, &gpio);
 	if (status < 0)
 		goto done;
 
@@ -1630,16 +1630,20 @@ static int gpiod_direction_input(struct gpio_desc *desc)
 	int			status = -EINVAL;
 	int			offset;
 
-	if (!desc) {
+	if (!desc || !desc->chip) {
 		pr_warn("%s: invalid GPIO\n", __func__);
 		return -EINVAL;
 	}
 
+	chip = desc->chip;
+	if (!chip->get || !chip->direction_input) {
+		pr_warn("%s: missing get() or direction_input() operations\n",
+			__func__);
+		return -EIO;
+	}
+
 	spin_lock_irqsave(&gpio_lock, flags);
 
-	chip = desc->chip;
-	if (!chip || !chip->get || !chip->direction_input)
-		goto fail;
 	status = gpio_ensure_requested(desc);
 	if (status < 0)
 		goto fail;
@@ -1691,7 +1695,7 @@ static int gpiod_direction_output(struct gpio_desc *desc, int value)
 	int			status = -EINVAL;
 	int offset;
 
-	if (!desc) {
+	if (!desc || !desc->chip) {
 		pr_warn("%s: invalid GPIO\n", __func__);
 		return -EINVAL;
 	}
@@ -1704,11 +1708,15 @@ static int gpiod_direction_output(struct gpio_desc *desc, int value)
 	if (!value && test_bit(FLAG_OPEN_SOURCE,  &desc->flags))
 		return gpiod_direction_input(desc);
 
+	chip = desc->chip;
+	if (!chip->set || !chip->direction_output) {
+		pr_warn("%s: missing set() or direction_output() operations\n",
+			__func__);
+		return -EIO;
+	}
+
 	spin_lock_irqsave(&gpio_lock, flags);
 
-	chip = desc->chip;
-	if (!chip || !chip->set || !chip->direction_output)
-		goto fail;
 	status = gpio_ensure_requested(desc);
 	if (status < 0)
 		goto fail;
@@ -1757,6 +1765,9 @@ EXPORT_SYMBOL_GPL(gpio_direction_output);
  * gpio_set_debounce - sets @debounce time for a @gpio
  * @gpio: the gpio to set debounce time
  * @debounce: debounce time is microseconds
+ *
+ * returns -ENOTSUPP if the controller does not support setting
+ * debounce.
  */
 static int gpiod_set_debounce(struct gpio_desc *desc, unsigned debounce)
 {
@@ -1765,16 +1776,19 @@ static int gpiod_set_debounce(struct gpio_desc *desc, unsigned debounce)
 	int			status = -EINVAL;
 	int			offset;
 
-	if (!desc) {
+	if (!desc || !desc->chip) {
 		pr_warn("%s: invalid GPIO\n", __func__);
 		return -EINVAL;
 	}
 
-	spin_lock_irqsave(&gpio_lock, flags);
-
 	chip = desc->chip;
-	if (!chip || !chip->set || !chip->set_debounce)
-		goto fail;
+	if (!chip->set || !chip->set_debounce) {
+		pr_debug("%s: missing set() or set_debounce() operations\n",
+			__func__);
+		return -ENOTSUPP;
+	}
+
+	spin_lock_irqsave(&gpio_lock, flags);
 
 	status = gpio_ensure_requested(desc);
 	if (status < 0)
diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig
index a7c54c843291..955555d6ec88 100644
--- a/drivers/gpu/drm/Kconfig
+++ b/drivers/gpu/drm/Kconfig
@@ -6,7 +6,7 @@
 #
 menuconfig DRM
 	tristate "Direct Rendering Manager (XFree86 4.1.0 and higher DRI support)"
-	depends on (AGP || AGP=n) && !EMULATED_CMPXCHG && MMU
+	depends on (AGP || AGP=n) && !EMULATED_CMPXCHG && MMU && HAS_DMA
 	select HDMI
 	select I2C
 	select I2C_ALGOBIT
@@ -168,6 +168,17 @@ config DRM_I915_KMS
 	  the driver to bind to PCI devices, which precludes loading things
 	  like intelfb.
 
+config DRM_I915_PRELIMINARY_HW_SUPPORT
+	bool "Enable preliminary support for prerelease Intel hardware by default"
+	depends on DRM_I915
+	help
+	  Choose this option if you have prerelease Intel hardware and want the
+	  i915 driver to support it by default.  You can enable such support at
+	  runtime with the module option i915.preliminary_hw_support=1; this
+	  option changes the default for that module option.
+
+	  If in doubt, say "N".
+
 config DRM_MGA
 	tristate "Matrox g200/g400"
 	depends on DRM && PCI
@@ -223,3 +234,5 @@ source "drivers/gpu/drm/omapdrm/Kconfig"
 source "drivers/gpu/drm/tilcdc/Kconfig"
 
 source "drivers/gpu/drm/qxl/Kconfig"
+
+source "drivers/gpu/drm/msm/Kconfig"
diff --git a/drivers/gpu/drm/Makefile b/drivers/gpu/drm/Makefile
index 801bcafa3028..f089adfe70ee 100644
--- a/drivers/gpu/drm/Makefile
+++ b/drivers/gpu/drm/Makefile
@@ -7,13 +7,13 @@ ccflags-y := -Iinclude/drm
 drm-y       :=	drm_auth.o drm_buffer.o drm_bufs.o drm_cache.o \
 		drm_context.o drm_dma.o \
 		drm_drv.o drm_fops.o drm_gem.o drm_ioctl.o drm_irq.o \
-		drm_lock.o drm_memory.o drm_proc.o drm_stub.o drm_vm.o \
+		drm_lock.o drm_memory.o drm_stub.o drm_vm.o \
 		drm_agpsupport.o drm_scatter.o drm_pci.o \
 		drm_platform.o drm_sysfs.o drm_hashtab.o drm_mm.o \
 		drm_crtc.o drm_modes.o drm_edid.o \
 		drm_info.o drm_debugfs.o drm_encoder_slave.o \
 		drm_trace_points.o drm_global.o drm_prime.o \
-		drm_rect.o
+		drm_rect.o drm_vma_manager.o drm_flip_work.o
 
 drm-$(CONFIG_COMPAT) += drm_ioc32.o
 drm-$(CONFIG_DRM_GEM_CMA_HELPER) += drm_gem_cma_helper.o
@@ -54,4 +54,5 @@ obj-$(CONFIG_DRM_SHMOBILE) +=shmobile/
 obj-$(CONFIG_DRM_OMAP)	+= omapdrm/
 obj-$(CONFIG_DRM_TILCDC)	+= tilcdc/
 obj-$(CONFIG_DRM_QXL) += qxl/
+obj-$(CONFIG_DRM_MSM) += msm/
 obj-y			+= i2c/
diff --git a/drivers/gpu/drm/ast/ast_drv.c b/drivers/gpu/drm/ast/ast_drv.c
index df0d0a08097a..32e270dc714e 100644
--- a/drivers/gpu/drm/ast/ast_drv.c
+++ b/drivers/gpu/drm/ast/ast_drv.c
@@ -190,7 +190,6 @@ static const struct file_operations ast_fops = {
 	.unlocked_ioctl = drm_ioctl,
 	.mmap = ast_mmap,
 	.poll = drm_poll,
-	.fasync = drm_fasync,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl = drm_compat_ioctl,
 #endif
@@ -198,7 +197,7 @@ static const struct file_operations ast_fops = {
 };
 
 static struct drm_driver driver = {
-	.driver_features = DRIVER_USE_MTRR | DRIVER_MODESET | DRIVER_GEM,
+	.driver_features = DRIVER_MODESET | DRIVER_GEM,
 	.dev_priv_size = 0,
 
 	.load = ast_driver_load,
@@ -216,7 +215,7 @@ static struct drm_driver driver = {
 	.gem_free_object = ast_gem_free_object,
 	.dumb_create = ast_dumb_create,
 	.dumb_map_offset = ast_dumb_mmap_offset,
-	.dumb_destroy = ast_dumb_destroy,
+	.dumb_destroy = drm_gem_dumb_destroy,
 
 };
 
diff --git a/drivers/gpu/drm/ast/ast_drv.h b/drivers/gpu/drm/ast/ast_drv.h
index 622d4ae7eb9e..8492b68e873c 100644
--- a/drivers/gpu/drm/ast/ast_drv.h
+++ b/drivers/gpu/drm/ast/ast_drv.h
@@ -177,7 +177,7 @@ uint8_t ast_get_index_reg_mask(struct ast_private *ast,
 
 static inline void ast_open_key(struct ast_private *ast)
 {
-	ast_set_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xA1, 0xFF, 0x04);
+	ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x80, 0xA8);
 }
 
 #define AST_VIDMEM_SIZE_8M    0x00800000
@@ -322,9 +322,6 @@ ast_bo(struct ttm_buffer_object *bo)
 extern int ast_dumb_create(struct drm_file *file,
 			   struct drm_device *dev,
 			   struct drm_mode_create_dumb *args);
-extern int ast_dumb_destroy(struct drm_file *file,
-			    struct drm_device *dev,
-			    uint32_t handle);
 
 extern int ast_gem_init_object(struct drm_gem_object *obj);
 extern void ast_gem_free_object(struct drm_gem_object *obj);
diff --git a/drivers/gpu/drm/ast/ast_main.c b/drivers/gpu/drm/ast/ast_main.c
index f60fd7bd1183..7f6152d374ca 100644
--- a/drivers/gpu/drm/ast/ast_main.c
+++ b/drivers/gpu/drm/ast/ast_main.c
@@ -449,13 +449,6 @@ int ast_dumb_create(struct drm_file *file,
 	return 0;
 }
 
-int ast_dumb_destroy(struct drm_file *file,
-		     struct drm_device *dev,
-		     uint32_t handle)
-{
-	return drm_gem_handle_delete(file, handle);
-}
-
 int ast_gem_init_object(struct drm_gem_object *obj)
 {
 	BUG();
@@ -487,7 +480,7 @@ void ast_gem_free_object(struct drm_gem_object *obj)
 
 static inline u64 ast_bo_mmap_offset(struct ast_bo *bo)
 {
-	return bo->bo.addr_space_offset;
+	return drm_vma_node_offset_addr(&bo->bo.vma_node);
 }
 int
 ast_dumb_mmap_offset(struct drm_file *file,
diff --git a/drivers/gpu/drm/ast/ast_ttm.c b/drivers/gpu/drm/ast/ast_ttm.c
index 6e8887fe6c1b..32aecb34dbce 100644
--- a/drivers/gpu/drm/ast/ast_ttm.c
+++ b/drivers/gpu/drm/ast/ast_ttm.c
@@ -148,7 +148,9 @@ ast_bo_evict_flags(struct ttm_buffer_object *bo, struct ttm_placement *pl)
 
 static int ast_bo_verify_access(struct ttm_buffer_object *bo, struct file *filp)
 {
-	return 0;
+	struct ast_bo *astbo = ast_bo(bo);
+
+	return drm_vma_node_verify_access(&astbo->gem.vma_node, filp);
 }
 
 static int ast_ttm_io_mem_reserve(struct ttm_bo_device *bdev,
@@ -321,7 +323,6 @@ int ast_bo_create(struct drm_device *dev, int size, int align,
 		return ret;
 	}
 
-	astbo->gem.driver_private = NULL;
 	astbo->bo.bdev = &ast->ttm.bdev;
 	astbo->bo.bdev->dev_mapping = dev->dev_mapping;
 
diff --git a/drivers/gpu/drm/cirrus/cirrus_drv.c b/drivers/gpu/drm/cirrus/cirrus_drv.c
index 8ecb601152ef..138364d91782 100644
--- a/drivers/gpu/drm/cirrus/cirrus_drv.c
+++ b/drivers/gpu/drm/cirrus/cirrus_drv.c
@@ -85,10 +85,9 @@ static const struct file_operations cirrus_driver_fops = {
 #ifdef CONFIG_COMPAT
 	.compat_ioctl = drm_compat_ioctl,
 #endif
-	.fasync = drm_fasync,
 };
 static struct drm_driver driver = {
-	.driver_features = DRIVER_MODESET | DRIVER_GEM | DRIVER_USE_MTRR,
+	.driver_features = DRIVER_MODESET | DRIVER_GEM,
 	.load = cirrus_driver_load,
 	.unload = cirrus_driver_unload,
 	.fops = &cirrus_driver_fops,
@@ -102,7 +101,7 @@ static struct drm_driver driver = {
 	.gem_free_object = cirrus_gem_free_object,
 	.dumb_create = cirrus_dumb_create,
 	.dumb_map_offset = cirrus_dumb_mmap_offset,
-	.dumb_destroy = cirrus_dumb_destroy,
+	.dumb_destroy = drm_gem_dumb_destroy,
 };
 
 static struct pci_driver cirrus_pci_driver = {
diff --git a/drivers/gpu/drm/cirrus/cirrus_drv.h b/drivers/gpu/drm/cirrus/cirrus_drv.h
index bae55609e6c3..9b0bb9184afd 100644
--- a/drivers/gpu/drm/cirrus/cirrus_drv.h
+++ b/drivers/gpu/drm/cirrus/cirrus_drv.h
@@ -203,9 +203,6 @@ int cirrus_gem_create(struct drm_device *dev,
 int cirrus_dumb_create(struct drm_file *file,
 		    struct drm_device *dev,
 		       struct drm_mode_create_dumb *args);
-int cirrus_dumb_destroy(struct drm_file *file,
-		     struct drm_device *dev,
-			uint32_t handle);
 
 int cirrus_framebuffer_init(struct drm_device *dev,
 			   struct cirrus_framebuffer *gfb,
diff --git a/drivers/gpu/drm/cirrus/cirrus_main.c b/drivers/gpu/drm/cirrus/cirrus_main.c
index 35cbae827771..f130a533a512 100644
--- a/drivers/gpu/drm/cirrus/cirrus_main.c
+++ b/drivers/gpu/drm/cirrus/cirrus_main.c
@@ -255,13 +255,6 @@ int cirrus_dumb_create(struct drm_file *file,
 	return 0;
 }
 
-int cirrus_dumb_destroy(struct drm_file *file,
-		     struct drm_device *dev,
-		     uint32_t handle)
-{
-	return drm_gem_handle_delete(file, handle);
-}
-
 int cirrus_gem_init_object(struct drm_gem_object *obj)
 {
 	BUG();
@@ -294,7 +287,7 @@ void cirrus_gem_free_object(struct drm_gem_object *obj)
 
 static inline u64 cirrus_bo_mmap_offset(struct cirrus_bo *bo)
 {
-	return bo->bo.addr_space_offset;
+	return drm_vma_node_offset_addr(&bo->bo.vma_node);
 }
 
 int
diff --git a/drivers/gpu/drm/cirrus/cirrus_ttm.c b/drivers/gpu/drm/cirrus/cirrus_ttm.c
index 69fd8f1ac8df..75becdeac07d 100644
--- a/drivers/gpu/drm/cirrus/cirrus_ttm.c
+++ b/drivers/gpu/drm/cirrus/cirrus_ttm.c
@@ -148,7 +148,9 @@ cirrus_bo_evict_flags(struct ttm_buffer_object *bo, struct ttm_placement *pl)
 
 static int cirrus_bo_verify_access(struct ttm_buffer_object *bo, struct file *filp)
 {
-	return 0;
+	struct cirrus_bo *cirrusbo = cirrus_bo(bo);
+
+	return drm_vma_node_verify_access(&cirrusbo->gem.vma_node, filp);
 }
 
 static int cirrus_ttm_io_mem_reserve(struct ttm_bo_device *bdev,
@@ -326,7 +328,6 @@ int cirrus_bo_create(struct drm_device *dev, int size, int align,
 		return ret;
 	}
 
-	cirrusbo->gem.driver_private = NULL;
 	cirrusbo->bo.bdev = &cirrus->ttm.bdev;
 	cirrusbo->bo.bdev->dev_mapping = dev->dev_mapping;
 
diff --git a/drivers/gpu/drm/drm_agpsupport.c b/drivers/gpu/drm/drm_agpsupport.c
index 3d8fed179797..e301d653d97e 100644
--- a/drivers/gpu/drm/drm_agpsupport.c
+++ b/drivers/gpu/drm/drm_agpsupport.c
@@ -424,6 +424,57 @@ struct drm_agp_head *drm_agp_init(struct drm_device *dev)
 }
 
 /**
+ * drm_agp_clear - Clear AGP resource list
+ * @dev: DRM device
+ *
+ * Iterate over all AGP resources and remove them. But keep the AGP head
+ * intact so it can still be used. It is safe to call this if AGP is disabled or
+ * was already removed.
+ *
+ * If DRIVER_MODESET is active, nothing is done to protect the modesetting
+ * resources from getting destroyed. Drivers are responsible of cleaning them up
+ * during device shutdown.
+ */
+void drm_agp_clear(struct drm_device *dev)
+{
+	struct drm_agp_mem *entry, *tempe;
+
+	if (!drm_core_has_AGP(dev) || !dev->agp)
+		return;
+	if (drm_core_check_feature(dev, DRIVER_MODESET))
+		return;
+
+	list_for_each_entry_safe(entry, tempe, &dev->agp->memory, head) {
+		if (entry->bound)
+			drm_unbind_agp(entry->memory);
+		drm_free_agp(entry->memory, entry->pages);
+		kfree(entry);
+	}
+	INIT_LIST_HEAD(&dev->agp->memory);
+
+	if (dev->agp->acquired)
+		drm_agp_release(dev);
+
+	dev->agp->acquired = 0;
+	dev->agp->enabled = 0;
+}
+
+/**
+ * drm_agp_destroy - Destroy AGP head
+ * @dev: DRM device
+ *
+ * Destroy resources that were previously allocated via drm_agp_initp. Caller
+ * must ensure to clean up all AGP resources before calling this. See
+ * drm_agp_clear().
+ *
+ * Call this to destroy AGP heads allocated via drm_agp_init().
+ */
+void drm_agp_destroy(struct drm_agp_head *agp)
+{
+	kfree(agp);
+}
+
+/**
  * Binds a collection of pages into AGP memory at the given offset, returning
  * the AGP memory structure containing them.
  *
diff --git a/drivers/gpu/drm/drm_bufs.c b/drivers/gpu/drm/drm_bufs.c
index 5a4dbb410b71..471e051d295e 100644
--- a/drivers/gpu/drm/drm_bufs.c
+++ b/drivers/gpu/drm/drm_bufs.c
@@ -207,12 +207,10 @@ static int drm_addmap_core(struct drm_device * dev, resource_size_t offset,
 			return 0;
 		}
 
-		if (drm_core_has_MTRR(dev)) {
-			if (map->type == _DRM_FRAME_BUFFER ||
-			    (map->flags & _DRM_WRITE_COMBINING)) {
-				map->mtrr =
-					arch_phys_wc_add(map->offset, map->size);
-			}
+		if (map->type == _DRM_FRAME_BUFFER ||
+		    (map->flags & _DRM_WRITE_COMBINING)) {
+			map->mtrr =
+				arch_phys_wc_add(map->offset, map->size);
 		}
 		if (map->type == _DRM_REGISTERS) {
 			if (map->flags & _DRM_WRITE_COMBINING)
@@ -243,7 +241,7 @@ static int drm_addmap_core(struct drm_device * dev, resource_size_t offset,
 		}
 		map->handle = vmalloc_user(map->size);
 		DRM_DEBUG("%lu %d %p\n",
-			  map->size, drm_order(map->size), map->handle);
+			  map->size, order_base_2(map->size), map->handle);
 		if (!map->handle) {
 			kfree(map);
 			return -ENOMEM;
@@ -464,8 +462,7 @@ int drm_rmmap_locked(struct drm_device *dev, struct drm_local_map *map)
 		iounmap(map->handle);
 		/* FALLTHROUGH */
 	case _DRM_FRAME_BUFFER:
-		if (drm_core_has_MTRR(dev))
-			arch_phys_wc_del(map->mtrr);
+		arch_phys_wc_del(map->mtrr);
 		break;
 	case _DRM_SHM:
 		vfree(map->handle);
@@ -630,7 +627,7 @@ int drm_addbufs_agp(struct drm_device * dev, struct drm_buf_desc * request)
 		return -EINVAL;
 
 	count = request->count;
-	order = drm_order(request->size);
+	order = order_base_2(request->size);
 	size = 1 << order;
 
 	alignment = (request->flags & _DRM_PAGE_ALIGN)
@@ -800,7 +797,7 @@ int drm_addbufs_pci(struct drm_device * dev, struct drm_buf_desc * request)
 		return -EPERM;
 
 	count = request->count;
-	order = drm_order(request->size);
+	order = order_base_2(request->size);
 	size = 1 << order;
 
 	DRM_DEBUG("count=%d, size=%d (%d), order=%d\n",
@@ -1002,7 +999,7 @@ static int drm_addbufs_sg(struct drm_device * dev, struct drm_buf_desc * request
 		return -EPERM;
 
 	count = request->count;
-	order = drm_order(request->size);
+	order = order_base_2(request->size);
 	size = 1 << order;
 
 	alignment = (request->flags & _DRM_PAGE_ALIGN)
@@ -1130,161 +1127,6 @@ static int drm_addbufs_sg(struct drm_device * dev, struct drm_buf_desc * request
 	return 0;
 }
 
-static int drm_addbufs_fb(struct drm_device * dev, struct drm_buf_desc * request)
-{
-	struct drm_device_dma *dma = dev->dma;
-	struct drm_buf_entry *entry;
-	struct drm_buf *buf;
-	unsigned long offset;
-	unsigned long agp_offset;
-	int count;
-	int order;
-	int size;
-	int alignment;
-	int page_order;
-	int total;
-	int byte_count;
-	int i;
-	struct drm_buf **temp_buflist;
-
-	if (!drm_core_check_feature(dev, DRIVER_FB_DMA))
-		return -EINVAL;
-
-	if (!dma)
-		return -EINVAL;
-
-	if (!capable(CAP_SYS_ADMIN))
-		return -EPERM;
-
-	count = request->count;
-	order = drm_order(request->size);
-	size = 1 << order;
-
-	alignment = (request->flags & _DRM_PAGE_ALIGN)
-	    ? PAGE_ALIGN(size) : size;
-	page_order = order - PAGE_SHIFT > 0 ? order - PAGE_SHIFT : 0;
-	total = PAGE_SIZE << page_order;
-
-	byte_count = 0;
-	agp_offset = request->agp_start;
-
-	DRM_DEBUG("count:      %d\n", count);
-	DRM_DEBUG("order:      %d\n", order);
-	DRM_DEBUG("size:       %d\n", size);
-	DRM_DEBUG("agp_offset: %lu\n", agp_offset);
-	DRM_DEBUG("alignment:  %d\n", alignment);
-	DRM_DEBUG("page_order: %d\n", page_order);
-	DRM_DEBUG("total:      %d\n", total);
-
-	if (order < DRM_MIN_ORDER || order > DRM_MAX_ORDER)
-		return -EINVAL;
-
-	spin_lock(&dev->count_lock);
-	if (dev->buf_use) {
-		spin_unlock(&dev->count_lock);
-		return -EBUSY;
-	}
-	atomic_inc(&dev->buf_alloc);
-	spin_unlock(&dev->count_lock);
-
-	mutex_lock(&dev->struct_mutex);
-	entry = &dma->bufs[order];
-	if (entry->buf_count) {
-		mutex_unlock(&dev->struct_mutex);
-		atomic_dec(&dev->buf_alloc);
-		return -ENOMEM;	/* May only call once for each order */
-	}
-
-	if (count < 0 || count > 4096) {
-		mutex_unlock(&dev->struct_mutex);
-		atomic_dec(&dev->buf_alloc);
-		return -EINVAL;
-	}
-
-	entry->buflist = kzalloc(count * sizeof(*entry->buflist),
-				GFP_KERNEL);
-	if (!entry->buflist) {
-		mutex_unlock(&dev->struct_mutex);
-		atomic_dec(&dev->buf_alloc);
-		return -ENOMEM;
-	}
-
-	entry->buf_size = size;
-	entry->page_order = page_order;
-
-	offset = 0;
-
-	while (entry->buf_count < count) {
-		buf = &entry->buflist[entry->buf_count];
-		buf->idx = dma->buf_count + entry->buf_count;
-		buf->total = alignment;
-		buf->order = order;
-		buf->used = 0;
-
-		buf->offset = (dma->byte_count + offset);
-		buf->bus_address = agp_offset + offset;
-		buf->address = (void *)(agp_offset + offset);
-		buf->next = NULL;
-		buf->waiting = 0;
-		buf->pending = 0;
-		buf->file_priv = NULL;
-
-		buf->dev_priv_size = dev->driver->dev_priv_size;
-		buf->dev_private = kzalloc(buf->dev_priv_size, GFP_KERNEL);
-		if (!buf->dev_private) {
-			/* Set count correctly so we free the proper amount. */
-			entry->buf_count = count;
-			drm_cleanup_buf_error(dev, entry);
-			mutex_unlock(&dev->struct_mutex);
-			atomic_dec(&dev->buf_alloc);
-			return -ENOMEM;
-		}
-
-		DRM_DEBUG("buffer %d @ %p\n", entry->buf_count, buf->address);
-
-		offset += alignment;
-		entry->buf_count++;
-		byte_count += PAGE_SIZE << page_order;
-	}
-
-	DRM_DEBUG("byte_count: %d\n", byte_count);
-
-	temp_buflist = krealloc(dma->buflist,
-				(dma->buf_count + entry->buf_count) *
-				sizeof(*dma->buflist), GFP_KERNEL);
-	if (!temp_buflist) {
-		/* Free the entry because it isn't valid */
-		drm_cleanup_buf_error(dev, entry);
-		mutex_unlock(&dev->struct_mutex);
-		atomic_dec(&dev->buf_alloc);
-		return -ENOMEM;
-	}
-	dma->buflist = temp_buflist;
-
-	for (i = 0; i < entry->buf_count; i++) {
-		dma->buflist[i + dma->buf_count] = &entry->buflist[i];
-	}
-
-	dma->buf_count += entry->buf_count;
-	dma->seg_count += entry->seg_count;
-	dma->page_count += byte_count >> PAGE_SHIFT;
-	dma->byte_count += byte_count;
-
-	DRM_DEBUG("dma->buf_count : %d\n", dma->buf_count);
-	DRM_DEBUG("entry->buf_count : %d\n", entry->buf_count);
-
-	mutex_unlock(&dev->struct_mutex);
-
-	request->count = entry->buf_count;
-	request->size = size;
-
-	dma->flags = _DRM_DMA_USE_FB;
-
-	atomic_dec(&dev->buf_alloc);
-	return 0;
-}
-
-
 /**
  * Add buffers for DMA transfers (ioctl).
  *
@@ -1305,6 +1147,9 @@ int drm_addbufs(struct drm_device *dev, void *data,
 	struct drm_buf_desc *request = data;
 	int ret;
 
+	if (drm_core_check_feature(dev, DRIVER_MODESET))
+		return -EINVAL;
+
 	if (!drm_core_check_feature(dev, DRIVER_HAVE_DMA))
 		return -EINVAL;
 
@@ -1316,7 +1161,7 @@ int drm_addbufs(struct drm_device *dev, void *data,
 	if (request->flags & _DRM_SG_BUFFER)
 		ret = drm_addbufs_sg(dev, request);
 	else if (request->flags & _DRM_FB_BUFFER)
-		ret = drm_addbufs_fb(dev, request);
+		ret = -EINVAL;
 	else
 		ret = drm_addbufs_pci(dev, request);
 
@@ -1348,6 +1193,9 @@ int drm_infobufs(struct drm_device *dev, void *data,
 	int i;
 	int count;
 
+	if (drm_core_check_feature(dev, DRIVER_MODESET))
+		return -EINVAL;
+
 	if (!drm_core_check_feature(dev, DRIVER_HAVE_DMA))
 		return -EINVAL;
 
@@ -1427,6 +1275,9 @@ int drm_markbufs(struct drm_device *dev, void *data,
 	int order;
 	struct drm_buf_entry *entry;
 
+	if (drm_core_check_feature(dev, DRIVER_MODESET))
+		return -EINVAL;
+
 	if (!drm_core_check_feature(dev, DRIVER_HAVE_DMA))
 		return -EINVAL;
 
@@ -1435,7 +1286,7 @@ int drm_markbufs(struct drm_device *dev, void *data,
 
 	DRM_DEBUG("%d, %d, %d\n",
 		  request->size, request->low_mark, request->high_mark);
-	order = drm_order(request->size);
+	order = order_base_2(request->size);
 	if (order < DRM_MIN_ORDER || order > DRM_MAX_ORDER)
 		return -EINVAL;
 	entry = &dma->bufs[order];
@@ -1472,6 +1323,9 @@ int drm_freebufs(struct drm_device *dev, void *data,
 	int idx;
 	struct drm_buf *buf;
 
+	if (drm_core_check_feature(dev, DRIVER_MODESET))
+		return -EINVAL;
+
 	if (!drm_core_check_feature(dev, DRIVER_HAVE_DMA))
 		return -EINVAL;
 
@@ -1524,6 +1378,9 @@ int drm_mapbufs(struct drm_device *dev, void *data,
 	struct drm_buf_map *request = data;
 	int i;
 
+	if (drm_core_check_feature(dev, DRIVER_MODESET))
+		return -EINVAL;
+
 	if (!drm_core_check_feature(dev, DRIVER_HAVE_DMA))
 		return -EINVAL;
 
@@ -1541,9 +1398,7 @@ int drm_mapbufs(struct drm_device *dev, void *data,
 	if (request->count >= dma->buf_count) {
 		if ((drm_core_has_AGP(dev) && (dma->flags & _DRM_DMA_USE_AGP))
 		    || (drm_core_check_feature(dev, DRIVER_SG)
-			&& (dma->flags & _DRM_DMA_USE_SG))
-		    || (drm_core_check_feature(dev, DRIVER_FB_DMA)
-			&& (dma->flags & _DRM_DMA_USE_FB))) {
+			&& (dma->flags & _DRM_DMA_USE_SG))) {
 			struct drm_local_map *map = dev->agp_buffer_map;
 			unsigned long token = dev->agp_buffer_token;
 
@@ -1600,25 +1455,28 @@ int drm_mapbufs(struct drm_device *dev, void *data,
 	return retcode;
 }
 
-/**
- * Compute size order.  Returns the exponent of the smaller power of two which
- * is greater or equal to given number.
- *
- * \param size size.
- * \return order.
- *
- * \todo Can be made faster.
- */
-int drm_order(unsigned long size)
+int drm_dma_ioctl(struct drm_device *dev, void *data,
+		  struct drm_file *file_priv)
 {
-	int order;
-	unsigned long tmp;
+	if (drm_core_check_feature(dev, DRIVER_MODESET))
+		return -EINVAL;
 
-	for (order = 0, tmp = size >> 1; tmp; tmp >>= 1, order++) ;
+	if (dev->driver->dma_ioctl)
+		return dev->driver->dma_ioctl(dev, data, file_priv);
+	else
+		return -EINVAL;
+}
 
-	if (size & (size - 1))
-		++order;
+struct drm_local_map *drm_getsarea(struct drm_device *dev)
+{
+	struct drm_map_list *entry;
 
-	return order;
+	list_for_each_entry(entry, &dev->maplist, head) {
+		if (entry->map && entry->map->type == _DRM_SHM &&
+		    (entry->map->flags & _DRM_CONTAINS_LOCK)) {
+			return entry->map;
+		}
+	}
+	return NULL;
 }
-EXPORT_SYMBOL(drm_order);
+EXPORT_SYMBOL(drm_getsarea);
diff --git a/drivers/gpu/drm/drm_context.c b/drivers/gpu/drm/drm_context.c
index 725968d38976..224ff965bcf7 100644
--- a/drivers/gpu/drm/drm_context.c
+++ b/drivers/gpu/drm/drm_context.c
@@ -251,7 +251,6 @@ static int drm_context_switch_complete(struct drm_device *dev,
 				       struct drm_file *file_priv, int new)
 {
 	dev->last_context = new;	/* PRE/POST: This is the _only_ writer. */
-	dev->last_switch = jiffies;
 
 	if (!_DRM_LOCK_IS_HELD(file_priv->master->lock.hw_lock->lock)) {
 		DRM_ERROR("Lock isn't held after context switch\n");
@@ -261,7 +260,6 @@ static int drm_context_switch_complete(struct drm_device *dev,
 	   when the kernel holds the lock, release
 	   that lock here. */
 	clear_bit(0, &dev->context_flag);
-	wake_up(&dev->context_wait);
 
 	return 0;
 }
@@ -342,12 +340,6 @@ int drm_addctx(struct drm_device *dev, void *data,
 	return 0;
 }
 
-int drm_modctx(struct drm_device *dev, void *data, struct drm_file *file_priv)
-{
-	/* This does nothing */
-	return 0;
-}
-
 /**
  * Get context.
  *
diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c
index fc83bb9eb514..bff2fa941f60 100644
--- a/drivers/gpu/drm/drm_crtc.c
+++ b/drivers/gpu/drm/drm_crtc.c
@@ -125,13 +125,6 @@ static const struct drm_prop_enum_list drm_scaling_mode_enum_list[] =
 	{ DRM_MODE_SCALE_ASPECT, "Full aspect" },
 };
 
-static const struct drm_prop_enum_list drm_dithering_mode_enum_list[] =
-{
-	{ DRM_MODE_DITHERING_OFF, "Off" },
-	{ DRM_MODE_DITHERING_ON, "On" },
-	{ DRM_MODE_DITHERING_AUTO, "Automatic" },
-};
-
 /*
  * Non-global properties, but "required" for certain connectors.
  */
@@ -186,29 +179,29 @@ static const struct drm_prop_enum_list drm_dirty_info_enum_list[] = {
 struct drm_conn_prop_enum_list {
 	int type;
 	const char *name;
-	int count;
+	struct ida ida;
 };
 
 /*
  * Connector and encoder types.
  */
 static struct drm_conn_prop_enum_list drm_connector_enum_list[] =
-{	{ DRM_MODE_CONNECTOR_Unknown, "Unknown", 0 },
-	{ DRM_MODE_CONNECTOR_VGA, "VGA", 0 },
-	{ DRM_MODE_CONNECTOR_DVII, "DVI-I", 0 },
-	{ DRM_MODE_CONNECTOR_DVID, "DVI-D", 0 },
-	{ DRM_MODE_CONNECTOR_DVIA, "DVI-A", 0 },
-	{ DRM_MODE_CONNECTOR_Composite, "Composite", 0 },
-	{ DRM_MODE_CONNECTOR_SVIDEO, "SVIDEO", 0 },
-	{ DRM_MODE_CONNECTOR_LVDS, "LVDS", 0 },
-	{ DRM_MODE_CONNECTOR_Component, "Component", 0 },
-	{ DRM_MODE_CONNECTOR_9PinDIN, "DIN", 0 },
-	{ DRM_MODE_CONNECTOR_DisplayPort, "DP", 0 },
-	{ DRM_MODE_CONNECTOR_HDMIA, "HDMI-A", 0 },
-	{ DRM_MODE_CONNECTOR_HDMIB, "HDMI-B", 0 },
-	{ DRM_MODE_CONNECTOR_TV, "TV", 0 },
-	{ DRM_MODE_CONNECTOR_eDP, "eDP", 0 },
-	{ DRM_MODE_CONNECTOR_VIRTUAL, "Virtual", 0},
+{	{ DRM_MODE_CONNECTOR_Unknown, "Unknown" },
+	{ DRM_MODE_CONNECTOR_VGA, "VGA" },
+	{ DRM_MODE_CONNECTOR_DVII, "DVI-I" },
+	{ DRM_MODE_CONNECTOR_DVID, "DVI-D" },
+	{ DRM_MODE_CONNECTOR_DVIA, "DVI-A" },
+	{ DRM_MODE_CONNECTOR_Composite, "Composite" },
+	{ DRM_MODE_CONNECTOR_SVIDEO, "SVIDEO" },
+	{ DRM_MODE_CONNECTOR_LVDS, "LVDS" },
+	{ DRM_MODE_CONNECTOR_Component, "Component" },
+	{ DRM_MODE_CONNECTOR_9PinDIN, "DIN" },
+	{ DRM_MODE_CONNECTOR_DisplayPort, "DP" },
+	{ DRM_MODE_CONNECTOR_HDMIA, "HDMI-A" },
+	{ DRM_MODE_CONNECTOR_HDMIB, "HDMI-B" },
+	{ DRM_MODE_CONNECTOR_TV, "TV" },
+	{ DRM_MODE_CONNECTOR_eDP, "eDP" },
+	{ DRM_MODE_CONNECTOR_VIRTUAL, "Virtual" },
 };
 
 static const struct drm_prop_enum_list drm_encoder_enum_list[] =
@@ -220,6 +213,22 @@ static const struct drm_prop_enum_list drm_encoder_enum_list[] =
 	{ DRM_MODE_ENCODER_VIRTUAL, "Virtual" },
 };
 
+void drm_connector_ida_init(void)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(drm_connector_enum_list); i++)
+		ida_init(&drm_connector_enum_list[i].ida);
+}
+
+void drm_connector_ida_destroy(void)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(drm_connector_enum_list); i++)
+		ida_destroy(&drm_connector_enum_list[i].ida);
+}
+
 const char *drm_get_encoder_name(const struct drm_encoder *encoder)
 {
 	static char buf[32];
@@ -677,20 +686,19 @@ void drm_mode_probed_add(struct drm_connector *connector,
 }
 EXPORT_SYMBOL(drm_mode_probed_add);
 
-/**
+/*
  * drm_mode_remove - remove and free a mode
  * @connector: connector list to modify
  * @mode: mode to remove
  *
  * Remove @mode from @connector's mode list, then free it.
  */
-void drm_mode_remove(struct drm_connector *connector,
-		     struct drm_display_mode *mode)
+static void drm_mode_remove(struct drm_connector *connector,
+			    struct drm_display_mode *mode)
 {
 	list_del(&mode->head);
 	drm_mode_destroy(connector->dev, mode);
 }
-EXPORT_SYMBOL(drm_mode_remove);
 
 /**
  * drm_connector_init - Init a preallocated connector
@@ -711,6 +719,8 @@ int drm_connector_init(struct drm_device *dev,
 		       int connector_type)
 {
 	int ret;
+	struct ida *connector_ida =
+		&drm_connector_enum_list[connector_type].ida;
 
 	drm_modeset_lock_all(dev);
 
@@ -723,7 +733,12 @@ int drm_connector_init(struct drm_device *dev,
 	connector->funcs = funcs;
 	connector->connector_type = connector_type;
 	connector->connector_type_id =
-		++drm_connector_enum_list[connector_type].count; /* TODO */
+		ida_simple_get(connector_ida, 1, 0, GFP_KERNEL);
+	if (connector->connector_type_id < 0) {
+		ret = connector->connector_type_id;
+		drm_mode_object_put(dev, &connector->base);
+		goto out;
+	}
 	INIT_LIST_HEAD(&connector->probed_modes);
 	INIT_LIST_HEAD(&connector->modes);
 	connector->edid_blob_ptr = NULL;
@@ -764,6 +779,9 @@ void drm_connector_cleanup(struct drm_connector *connector)
 	list_for_each_entry_safe(mode, t, &connector->modes, head)
 		drm_mode_remove(connector, mode);
 
+	ida_remove(&drm_connector_enum_list[connector->connector_type].ida,
+		   connector->connector_type_id);
+
 	drm_mode_object_put(dev, &connector->base);
 	list_del(&connector->head);
 	dev->mode_config.num_connector--;
@@ -781,6 +799,41 @@ void drm_connector_unplug_all(struct drm_device *dev)
 }
 EXPORT_SYMBOL(drm_connector_unplug_all);
 
+int drm_bridge_init(struct drm_device *dev, struct drm_bridge *bridge,
+		const struct drm_bridge_funcs *funcs)
+{
+	int ret;
+
+	drm_modeset_lock_all(dev);
+
+	ret = drm_mode_object_get(dev, &bridge->base, DRM_MODE_OBJECT_BRIDGE);
+	if (ret)
+		goto out;
+
+	bridge->dev = dev;
+	bridge->funcs = funcs;
+
+	list_add_tail(&bridge->head, &dev->mode_config.bridge_list);
+	dev->mode_config.num_bridge++;
+
+ out:
+	drm_modeset_unlock_all(dev);
+	return ret;
+}
+EXPORT_SYMBOL(drm_bridge_init);
+
+void drm_bridge_cleanup(struct drm_bridge *bridge)
+{
+	struct drm_device *dev = bridge->dev;
+
+	drm_modeset_lock_all(dev);
+	drm_mode_object_put(dev, &bridge->base);
+	list_del(&bridge->head);
+	dev->mode_config.num_bridge--;
+	drm_modeset_unlock_all(dev);
+}
+EXPORT_SYMBOL(drm_bridge_cleanup);
+
 int drm_encoder_init(struct drm_device *dev,
 		      struct drm_encoder *encoder,
 		      const struct drm_encoder_funcs *funcs,
@@ -1135,30 +1188,6 @@ int drm_mode_create_scaling_mode_property(struct drm_device *dev)
 EXPORT_SYMBOL(drm_mode_create_scaling_mode_property);
 
 /**
- * drm_mode_create_dithering_property - create dithering property
- * @dev: DRM device
- *
- * Called by a driver the first time it's needed, must be attached to desired
- * connectors.
- */
-int drm_mode_create_dithering_property(struct drm_device *dev)
-{
-	struct drm_property *dithering_mode;
-
-	if (dev->mode_config.dithering_mode_property)
-		return 0;
-
-	dithering_mode =
-		drm_property_create_enum(dev, 0, "dithering",
-				drm_dithering_mode_enum_list,
-				    ARRAY_SIZE(drm_dithering_mode_enum_list));
-	dev->mode_config.dithering_mode_property = dithering_mode;
-
-	return 0;
-}
-EXPORT_SYMBOL(drm_mode_create_dithering_property);
-
-/**
  * drm_mode_create_dirty_property - create dirty property
  * @dev: DRM device
  *
@@ -1190,6 +1219,7 @@ static int drm_mode_group_init(struct drm_device *dev, struct drm_mode_group *gr
 	total_objects += dev->mode_config.num_crtc;
 	total_objects += dev->mode_config.num_connector;
 	total_objects += dev->mode_config.num_encoder;
+	total_objects += dev->mode_config.num_bridge;
 
 	group->id_list = kzalloc(total_objects * sizeof(uint32_t), GFP_KERNEL);
 	if (!group->id_list)
@@ -1198,6 +1228,7 @@ static int drm_mode_group_init(struct drm_device *dev, struct drm_mode_group *gr
 	group->num_crtcs = 0;
 	group->num_connectors = 0;
 	group->num_encoders = 0;
+	group->num_bridges = 0;
 	return 0;
 }
 
@@ -1207,6 +1238,7 @@ int drm_mode_group_init_legacy_group(struct drm_device *dev,
 	struct drm_crtc *crtc;
 	struct drm_encoder *encoder;
 	struct drm_connector *connector;
+	struct drm_bridge *bridge;
 	int ret;
 
 	if ((ret = drm_mode_group_init(dev, group)))
@@ -1223,6 +1255,11 @@ int drm_mode_group_init_legacy_group(struct drm_device *dev,
 		group->id_list[group->num_crtcs + group->num_encoders +
 			       group->num_connectors++] = connector->base.id;
 
+	list_for_each_entry(bridge, &dev->mode_config.bridge_list, head)
+		group->id_list[group->num_crtcs + group->num_encoders +
+			       group->num_connectors + group->num_bridges++] =
+					bridge->base.id;
+
 	return 0;
 }
 EXPORT_SYMBOL(drm_mode_group_init_legacy_group);
@@ -2604,10 +2641,22 @@ int drm_mode_getfb(struct drm_device *dev,
 	r->depth = fb->depth;
 	r->bpp = fb->bits_per_pixel;
 	r->pitch = fb->pitches[0];
-	if (fb->funcs->create_handle)
-		ret = fb->funcs->create_handle(fb, file_priv, &r->handle);
-	else
+	if (fb->funcs->create_handle) {
+		if (file_priv->is_master || capable(CAP_SYS_ADMIN)) {
+			ret = fb->funcs->create_handle(fb, file_priv,
+						       &r->handle);
+		} else {
+			/* GET_FB() is an unprivileged ioctl so we must not
+			 * return a buffer-handle to non-master processes! For
+			 * backwards-compatibility reasons, we cannot make
+			 * GET_FB() privileged, so just return an invalid handle
+			 * for non-masters. */
+			r->handle = 0;
+			ret = 0;
+		}
+	} else {
 		ret = -ENODEV;
+	}
 
 	drm_framebuffer_unreference(fb);
 
@@ -3514,6 +3563,9 @@ int drm_mode_page_flip_ioctl(struct drm_device *dev,
 	    page_flip->reserved != 0)
 		return -EINVAL;
 
+	if ((page_flip->flags & DRM_MODE_PAGE_FLIP_ASYNC) && !dev->mode_config.async_page_flip)
+		return -EINVAL;
+
 	obj = drm_mode_object_find(dev, page_flip->crtc_id, DRM_MODE_OBJECT_CRTC);
 	if (!obj)
 		return -EINVAL;
@@ -3587,7 +3639,7 @@ int drm_mode_page_flip_ioctl(struct drm_device *dev,
 	}
 
 	old_fb = crtc->fb;
-	ret = crtc->funcs->page_flip(crtc, fb, e);
+	ret = crtc->funcs->page_flip(crtc, fb, e, page_flip->flags);
 	if (ret) {
 		if (page_flip->flags & DRM_MODE_PAGE_FLIP_EVENT) {
 			spin_lock_irqsave(&dev->event_lock, flags);
@@ -3905,6 +3957,7 @@ void drm_mode_config_init(struct drm_device *dev)
 	INIT_LIST_HEAD(&dev->mode_config.fb_list);
 	INIT_LIST_HEAD(&dev->mode_config.crtc_list);
 	INIT_LIST_HEAD(&dev->mode_config.connector_list);
+	INIT_LIST_HEAD(&dev->mode_config.bridge_list);
 	INIT_LIST_HEAD(&dev->mode_config.encoder_list);
 	INIT_LIST_HEAD(&dev->mode_config.property_list);
 	INIT_LIST_HEAD(&dev->mode_config.property_blob_list);
@@ -3941,6 +3994,7 @@ void drm_mode_config_cleanup(struct drm_device *dev)
 	struct drm_connector *connector, *ot;
 	struct drm_crtc *crtc, *ct;
 	struct drm_encoder *encoder, *enct;
+	struct drm_bridge *bridge, *brt;
 	struct drm_framebuffer *fb, *fbt;
 	struct drm_property *property, *pt;
 	struct drm_property_blob *blob, *bt;
@@ -3951,6 +4005,11 @@ void drm_mode_config_cleanup(struct drm_device *dev)
 		encoder->funcs->destroy(encoder);
 	}
 
+	list_for_each_entry_safe(bridge, brt,
+				 &dev->mode_config.bridge_list, head) {
+		bridge->funcs->destroy(bridge);
+	}
+
 	list_for_each_entry_safe(connector, ot,
 				 &dev->mode_config.connector_list, head) {
 		connector->funcs->destroy(connector);
diff --git a/drivers/gpu/drm/drm_crtc_helper.c b/drivers/gpu/drm/drm_crtc_helper.c
index 6a647493ca7f..c722c3b5404d 100644
--- a/drivers/gpu/drm/drm_crtc_helper.c
+++ b/drivers/gpu/drm/drm_crtc_helper.c
@@ -257,10 +257,16 @@ drm_encoder_disable(struct drm_encoder *encoder)
 {
 	struct drm_encoder_helper_funcs *encoder_funcs = encoder->helper_private;
 
+	if (encoder->bridge)
+		encoder->bridge->funcs->disable(encoder->bridge);
+
 	if (encoder_funcs->disable)
 		(*encoder_funcs->disable)(encoder);
 	else
 		(*encoder_funcs->dpms)(encoder, DRM_MODE_DPMS_OFF);
+
+	if (encoder->bridge)
+		encoder->bridge->funcs->post_disable(encoder->bridge);
 }
 
 /**
@@ -424,6 +430,16 @@ bool drm_crtc_helper_set_mode(struct drm_crtc *crtc,
 
 		if (encoder->crtc != crtc)
 			continue;
+
+		if (encoder->bridge && encoder->bridge->funcs->mode_fixup) {
+			ret = encoder->bridge->funcs->mode_fixup(
+					encoder->bridge, mode, adjusted_mode);
+			if (!ret) {
+				DRM_DEBUG_KMS("Bridge fixup failed\n");
+				goto done;
+			}
+		}
+
 		encoder_funcs = encoder->helper_private;
 		if (!(ret = encoder_funcs->mode_fixup(encoder, mode,
 						      adjusted_mode))) {
@@ -443,9 +459,16 @@ bool drm_crtc_helper_set_mode(struct drm_crtc *crtc,
 
 		if (encoder->crtc != crtc)
 			continue;
+
+		if (encoder->bridge)
+			encoder->bridge->funcs->disable(encoder->bridge);
+
 		encoder_funcs = encoder->helper_private;
 		/* Disable the encoders as the first thing we do. */
 		encoder_funcs->prepare(encoder);
+
+		if (encoder->bridge)
+			encoder->bridge->funcs->post_disable(encoder->bridge);
 	}
 
 	drm_crtc_prepare_encoders(dev);
@@ -469,6 +492,10 @@ bool drm_crtc_helper_set_mode(struct drm_crtc *crtc,
 			mode->base.id, mode->name);
 		encoder_funcs = encoder->helper_private;
 		encoder_funcs->mode_set(encoder, mode, adjusted_mode);
+
+		if (encoder->bridge && encoder->bridge->funcs->mode_set)
+			encoder->bridge->funcs->mode_set(encoder->bridge, mode,
+					adjusted_mode);
 	}
 
 	/* Now enable the clocks, plane, pipe, and connectors that we set up. */
@@ -479,9 +506,14 @@ bool drm_crtc_helper_set_mode(struct drm_crtc *crtc,
 		if (encoder->crtc != crtc)
 			continue;
 
+		if (encoder->bridge)
+			encoder->bridge->funcs->pre_enable(encoder->bridge);
+
 		encoder_funcs = encoder->helper_private;
 		encoder_funcs->commit(encoder);
 
+		if (encoder->bridge)
+			encoder->bridge->funcs->enable(encoder->bridge);
 	}
 
 	/* Store real post-adjustment hardware mode. */
@@ -830,6 +862,31 @@ static int drm_helper_choose_encoder_dpms(struct drm_encoder *encoder)
 	return dpms;
 }
 
+/* Helper which handles bridge ordering around encoder dpms */
+static void drm_helper_encoder_dpms(struct drm_encoder *encoder, int mode)
+{
+	struct drm_bridge *bridge = encoder->bridge;
+	struct drm_encoder_helper_funcs *encoder_funcs;
+
+	if (bridge) {
+		if (mode == DRM_MODE_DPMS_ON)
+			bridge->funcs->pre_enable(bridge);
+		else
+			bridge->funcs->disable(bridge);
+	}
+
+	encoder_funcs = encoder->helper_private;
+	if (encoder_funcs->dpms)
+		encoder_funcs->dpms(encoder, mode);
+
+	if (bridge) {
+		if (mode == DRM_MODE_DPMS_ON)
+			bridge->funcs->enable(bridge);
+		else
+			bridge->funcs->post_disable(bridge);
+	}
+}
+
 static int drm_helper_choose_crtc_dpms(struct drm_crtc *crtc)
 {
 	int dpms = DRM_MODE_DPMS_OFF;
@@ -857,7 +914,7 @@ void drm_helper_connector_dpms(struct drm_connector *connector, int mode)
 {
 	struct drm_encoder *encoder = connector->encoder;
 	struct drm_crtc *crtc = encoder ? encoder->crtc : NULL;
-	int old_dpms;
+	int old_dpms, encoder_dpms = DRM_MODE_DPMS_OFF;
 
 	if (mode == connector->dpms)
 		return;
@@ -865,6 +922,9 @@ void drm_helper_connector_dpms(struct drm_connector *connector, int mode)
 	old_dpms = connector->dpms;
 	connector->dpms = mode;
 
+	if (encoder)
+		encoder_dpms = drm_helper_choose_encoder_dpms(encoder);
+
 	/* from off to on, do crtc then encoder */
 	if (mode < old_dpms) {
 		if (crtc) {
@@ -873,22 +933,14 @@ void drm_helper_connector_dpms(struct drm_connector *connector, int mode)
 				(*crtc_funcs->dpms) (crtc,
 						     drm_helper_choose_crtc_dpms(crtc));
 		}
-		if (encoder) {
-			struct drm_encoder_helper_funcs *encoder_funcs = encoder->helper_private;
-			if (encoder_funcs->dpms)
-				(*encoder_funcs->dpms) (encoder,
-							drm_helper_choose_encoder_dpms(encoder));
-		}
+		if (encoder)
+			drm_helper_encoder_dpms(encoder, encoder_dpms);
 	}
 
 	/* from on to off, do encoder then crtc */
 	if (mode > old_dpms) {
-		if (encoder) {
-			struct drm_encoder_helper_funcs *encoder_funcs = encoder->helper_private;
-			if (encoder_funcs->dpms)
-				(*encoder_funcs->dpms) (encoder,
-							drm_helper_choose_encoder_dpms(encoder));
-		}
+		if (encoder)
+			drm_helper_encoder_dpms(encoder, encoder_dpms);
 		if (crtc) {
 			struct drm_crtc_helper_funcs *crtc_funcs = crtc->helper_private;
 			if (crtc_funcs->dpms)
@@ -924,9 +976,8 @@ int drm_helper_resume_force_mode(struct drm_device *dev)
 {
 	struct drm_crtc *crtc;
 	struct drm_encoder *encoder;
-	struct drm_encoder_helper_funcs *encoder_funcs;
 	struct drm_crtc_helper_funcs *crtc_funcs;
-	int ret;
+	int ret, encoder_dpms;
 
 	list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
 
@@ -946,10 +997,10 @@ int drm_helper_resume_force_mode(struct drm_device *dev)
 				if(encoder->crtc != crtc)
 					continue;
 
-				encoder_funcs = encoder->helper_private;
-				if (encoder_funcs->dpms)
-					(*encoder_funcs->dpms) (encoder,
-								drm_helper_choose_encoder_dpms(encoder));
+				encoder_dpms = drm_helper_choose_encoder_dpms(
+							encoder);
+
+				drm_helper_encoder_dpms(encoder, encoder_dpms);
 			}
 
 			crtc_funcs = crtc->helper_private;
diff --git a/drivers/gpu/drm/drm_dma.c b/drivers/gpu/drm/drm_dma.c
index 495b5fd2787c..8a140a953754 100644
--- a/drivers/gpu/drm/drm_dma.c
+++ b/drivers/gpu/drm/drm_dma.c
@@ -44,10 +44,18 @@
  *
  * Allocate and initialize a drm_device_dma structure.
  */
-int drm_dma_setup(struct drm_device *dev)
+int drm_legacy_dma_setup(struct drm_device *dev)
 {
 	int i;
 
+	if (!drm_core_check_feature(dev, DRIVER_HAVE_DMA) ||
+	    drm_core_check_feature(dev, DRIVER_MODESET)) {
+		return 0;
+	}
+
+	dev->buf_use = 0;
+	atomic_set(&dev->buf_alloc, 0);
+
 	dev->dma = kzalloc(sizeof(*dev->dma), GFP_KERNEL);
 	if (!dev->dma)
 		return -ENOMEM;
@@ -66,11 +74,16 @@ int drm_dma_setup(struct drm_device *dev)
  * Free all pages associated with DMA buffers, the buffers and pages lists, and
  * finally the drm_device::dma structure itself.
  */
-void drm_dma_takedown(struct drm_device *dev)
+void drm_legacy_dma_takedown(struct drm_device *dev)
 {
 	struct drm_device_dma *dma = dev->dma;
 	int i, j;
 
+	if (!drm_core_check_feature(dev, DRIVER_HAVE_DMA) ||
+	    drm_core_check_feature(dev, DRIVER_MODESET)) {
+		return;
+	}
+
 	if (!dma)
 		return;
 
diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c
index 99fcd7c32ea2..e572dd20bdee 100644
--- a/drivers/gpu/drm/drm_drv.c
+++ b/drivers/gpu/drm/drm_drv.c
@@ -68,7 +68,7 @@ static const struct drm_ioctl_desc drm_ioctls[] = {
 	DRM_IOCTL_DEF(DRM_IOCTL_GET_MAP, drm_getmap, DRM_UNLOCKED),
 	DRM_IOCTL_DEF(DRM_IOCTL_GET_CLIENT, drm_getclient, DRM_UNLOCKED),
 	DRM_IOCTL_DEF(DRM_IOCTL_GET_STATS, drm_getstats, DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_GET_CAP, drm_getcap, DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_GET_CAP, drm_getcap, DRM_UNLOCKED|DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF(DRM_IOCTL_SET_VERSION, drm_setversion, DRM_MASTER),
 
 	DRM_IOCTL_DEF(DRM_IOCTL_SET_UNIQUE, drm_setunique, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
@@ -87,7 +87,7 @@ static const struct drm_ioctl_desc drm_ioctls[] = {
 
 	DRM_IOCTL_DEF(DRM_IOCTL_ADD_CTX, drm_addctx, DRM_AUTH|DRM_ROOT_ONLY),
 	DRM_IOCTL_DEF(DRM_IOCTL_RM_CTX, drm_rmctx, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
-	DRM_IOCTL_DEF(DRM_IOCTL_MOD_CTX, drm_modctx, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
+	DRM_IOCTL_DEF(DRM_IOCTL_MOD_CTX, drm_noop, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
 	DRM_IOCTL_DEF(DRM_IOCTL_GET_CTX, drm_getctx, DRM_AUTH),
 	DRM_IOCTL_DEF(DRM_IOCTL_SWITCH_CTX, drm_switchctx, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
 	DRM_IOCTL_DEF(DRM_IOCTL_NEW_CTX, drm_newctx, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
@@ -106,8 +106,7 @@ static const struct drm_ioctl_desc drm_ioctls[] = {
 	DRM_IOCTL_DEF(DRM_IOCTL_INFO_BUFS, drm_infobufs, DRM_AUTH),
 	DRM_IOCTL_DEF(DRM_IOCTL_MAP_BUFS, drm_mapbufs, DRM_AUTH),
 	DRM_IOCTL_DEF(DRM_IOCTL_FREE_BUFS, drm_freebufs, DRM_AUTH),
-	/* The DRM_IOCTL_DMA ioctl should be defined by the driver. */
-	DRM_IOCTL_DEF(DRM_IOCTL_DMA, NULL, DRM_AUTH),
+	DRM_IOCTL_DEF(DRM_IOCTL_DMA, drm_dma_ioctl, DRM_AUTH),
 
 	DRM_IOCTL_DEF(DRM_IOCTL_CONTROL, drm_control, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
 
@@ -122,7 +121,7 @@ static const struct drm_ioctl_desc drm_ioctls[] = {
 	DRM_IOCTL_DEF(DRM_IOCTL_AGP_UNBIND, drm_agp_unbind_ioctl, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
 #endif
 
-	DRM_IOCTL_DEF(DRM_IOCTL_SG_ALLOC, drm_sg_alloc_ioctl, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
+	DRM_IOCTL_DEF(DRM_IOCTL_SG_ALLOC, drm_sg_alloc, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
 	DRM_IOCTL_DEF(DRM_IOCTL_SG_FREE, drm_sg_free, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
 
 	DRM_IOCTL_DEF(DRM_IOCTL_WAIT_VBLANK, drm_wait_vblank, DRM_UNLOCKED),
@@ -131,14 +130,14 @@ static const struct drm_ioctl_desc drm_ioctls[] = {
 
 	DRM_IOCTL_DEF(DRM_IOCTL_UPDATE_DRAW, drm_noop, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
 
-	DRM_IOCTL_DEF(DRM_IOCTL_GEM_CLOSE, drm_gem_close_ioctl, DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_GEM_CLOSE, drm_gem_close_ioctl, DRM_UNLOCKED|DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF(DRM_IOCTL_GEM_FLINK, drm_gem_flink_ioctl, DRM_AUTH|DRM_UNLOCKED),
 	DRM_IOCTL_DEF(DRM_IOCTL_GEM_OPEN, drm_gem_open_ioctl, DRM_AUTH|DRM_UNLOCKED),
 
 	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETRESOURCES, drm_mode_getresources, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
 
-	DRM_IOCTL_DEF(DRM_IOCTL_PRIME_HANDLE_TO_FD, drm_prime_handle_to_fd_ioctl, DRM_AUTH|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_PRIME_FD_TO_HANDLE, drm_prime_fd_to_handle_ioctl, DRM_AUTH|DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_PRIME_HANDLE_TO_FD, drm_prime_handle_to_fd_ioctl, DRM_AUTH|DRM_UNLOCKED|DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF(DRM_IOCTL_PRIME_FD_TO_HANDLE, drm_prime_fd_to_handle_ioctl, DRM_AUTH|DRM_UNLOCKED|DRM_RENDER_ALLOW),
 
 	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETPLANERESOURCES, drm_mode_getplane_res, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
 	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETCRTC, drm_mode_getcrtc, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
@@ -172,6 +171,31 @@ static const struct drm_ioctl_desc drm_ioctls[] = {
 #define DRM_CORE_IOCTL_COUNT	ARRAY_SIZE( drm_ioctls )
 
 /**
+ * drm_legacy_dev_reinit
+ *
+ * Reinitializes a legacy/ums drm device in it's lastclose function.
+ */
+static void drm_legacy_dev_reinit(struct drm_device *dev)
+{
+	int i;
+
+	if (drm_core_check_feature(dev, DRIVER_MODESET))
+		return;
+
+	atomic_set(&dev->ioctl_count, 0);
+	atomic_set(&dev->vma_count, 0);
+
+	for (i = 0; i < ARRAY_SIZE(dev->counts); i++)
+		atomic_set(&dev->counts[i], 0);
+
+	dev->sigdata.lock = NULL;
+
+	dev->context_flag = 0;
+	dev->last_context = 0;
+	dev->if_version = 0;
+}
+
+/**
  * Take down the DRM device.
  *
  * \param dev DRM device structure.
@@ -195,32 +219,9 @@ int drm_lastclose(struct drm_device * dev)
 
 	mutex_lock(&dev->struct_mutex);
 
-	/* Clear AGP information */
-	if (drm_core_has_AGP(dev) && dev->agp &&
-			!drm_core_check_feature(dev, DRIVER_MODESET)) {
-		struct drm_agp_mem *entry, *tempe;
-
-		/* Remove AGP resources, but leave dev->agp
-		   intact until drv_cleanup is called. */
-		list_for_each_entry_safe(entry, tempe, &dev->agp->memory, head) {
-			if (entry->bound)
-				drm_unbind_agp(entry->memory);
-			drm_free_agp(entry->memory, entry->pages);
-			kfree(entry);
-		}
-		INIT_LIST_HEAD(&dev->agp->memory);
+	drm_agp_clear(dev);
 
-		if (dev->agp->acquired)
-			drm_agp_release(dev);
-
-		dev->agp->acquired = 0;
-		dev->agp->enabled = 0;
-	}
-	if (drm_core_check_feature(dev, DRIVER_SG) && dev->sg &&
-	    !drm_core_check_feature(dev, DRIVER_MODESET)) {
-		drm_sg_cleanup(dev->sg);
-		dev->sg = NULL;
-	}
+	drm_legacy_sg_cleanup(dev);
 
 	/* Clear vma list (only built for debugging) */
 	list_for_each_entry_safe(vma, vma_temp, &dev->vmalist, head) {
@@ -228,13 +229,13 @@ int drm_lastclose(struct drm_device * dev)
 		kfree(vma);
 	}
 
-	if (drm_core_check_feature(dev, DRIVER_HAVE_DMA) &&
-	    !drm_core_check_feature(dev, DRIVER_MODESET))
-		drm_dma_takedown(dev);
+	drm_legacy_dma_takedown(dev);
 
 	dev->dev_mapping = NULL;
 	mutex_unlock(&dev->struct_mutex);
 
+	drm_legacy_dev_reinit(dev);
+
 	DRM_DEBUG("lastclose completed\n");
 	return 0;
 }
@@ -251,6 +252,7 @@ static int __init drm_core_init(void)
 	int ret = -ENOMEM;
 
 	drm_global_init();
+	drm_connector_ida_init();
 	idr_init(&drm_minors_idr);
 
 	if (register_chrdev(DRM_MAJOR, "drm", &drm_stub_fops))
@@ -263,13 +265,6 @@ static int __init drm_core_init(void)
 		goto err_p2;
 	}
 
-	drm_proc_root = proc_mkdir("dri", NULL);
-	if (!drm_proc_root) {
-		DRM_ERROR("Cannot create /proc/dri\n");
-		ret = -1;
-		goto err_p3;
-	}
-
 	drm_debugfs_root = debugfs_create_dir("dri", NULL);
 	if (!drm_debugfs_root) {
 		DRM_ERROR("Cannot create /sys/kernel/debug/dri\n");
@@ -292,12 +287,12 @@ err_p1:
 
 static void __exit drm_core_exit(void)
 {
-	remove_proc_entry("dri", NULL);
 	debugfs_remove(drm_debugfs_root);
 	drm_sysfs_destroy();
 
 	unregister_chrdev(DRM_MAJOR, "drm");
 
+	drm_connector_ida_destroy();
 	idr_destroy(&drm_minors_idr);
 }
 
@@ -420,17 +415,15 @@ long drm_ioctl(struct file *filp,
 
 	/* Do not trust userspace, use our own definition */
 	func = ioctl->func;
-	/* is there a local override? */
-	if ((nr == DRM_IOCTL_NR(DRM_IOCTL_DMA)) && dev->driver->dma_ioctl)
-		func = dev->driver->dma_ioctl;
 
 	if (!func) {
 		DRM_DEBUG("no function\n");
 		retcode = -EINVAL;
 	} else if (((ioctl->flags & DRM_ROOT_ONLY) && !capable(CAP_SYS_ADMIN)) ||
-		   ((ioctl->flags & DRM_AUTH) && !file_priv->authenticated) ||
+		   ((ioctl->flags & DRM_AUTH) && !drm_is_render_client(file_priv) && !file_priv->authenticated) ||
 		   ((ioctl->flags & DRM_MASTER) && !file_priv->is_master) ||
-		   (!(ioctl->flags & DRM_CONTROL_ALLOW) && (file_priv->minor->type == DRM_MINOR_CONTROL))) {
+		   (!(ioctl->flags & DRM_CONTROL_ALLOW) && (file_priv->minor->type == DRM_MINOR_CONTROL)) ||
+		   (!(ioctl->flags & DRM_RENDER_ALLOW) && drm_is_render_client(file_priv))) {
 		retcode = -EACCES;
 	} else {
 		if (cmd & (IOC_IN | IOC_OUT)) {
@@ -485,19 +478,4 @@ long drm_ioctl(struct file *filp,
 		DRM_DEBUG("ret = %d\n", retcode);
 	return retcode;
 }
-
 EXPORT_SYMBOL(drm_ioctl);
-
-struct drm_local_map *drm_getsarea(struct drm_device *dev)
-{
-	struct drm_map_list *entry;
-
-	list_for_each_entry(entry, &dev->maplist, head) {
-		if (entry->map && entry->map->type == _DRM_SHM &&
-		    (entry->map->flags & _DRM_CONTAINS_LOCK)) {
-			return entry->map;
-		}
-	}
-	return NULL;
-}
-EXPORT_SYMBOL(drm_getsarea);
diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c
index 95d6f4b6967c..830f7501cb4d 100644
--- a/drivers/gpu/drm/drm_edid.c
+++ b/drivers/gpu/drm/drm_edid.c
@@ -125,6 +125,9 @@ static struct edid_quirk {
 
 	/* ViewSonic VA2026w */
 	{ "VSC", 5020, EDID_QUIRK_FORCE_REDUCED_BLANKING },
+
+	/* Medion MD 30217 PG */
+	{ "MED", 0x7b8, EDID_QUIRK_PREFER_LARGE_75 },
 };
 
 /*
@@ -931,6 +934,36 @@ static const struct drm_display_mode edid_cea_modes[] = {
 	 .vrefresh = 100, },
 };
 
+/*
+ * HDMI 1.4 4k modes.
+ */
+static const struct drm_display_mode edid_4k_modes[] = {
+	/* 1 - 3840x2160@30Hz */
+	{ DRM_MODE("3840x2160", DRM_MODE_TYPE_DRIVER, 297000,
+		   3840, 4016, 4104, 4400, 0,
+		   2160, 2168, 2178, 2250, 0,
+		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
+	  .vrefresh = 30, },
+	/* 2 - 3840x2160@25Hz */
+	{ DRM_MODE("3840x2160", DRM_MODE_TYPE_DRIVER, 297000,
+		   3840, 4896, 4984, 5280, 0,
+		   2160, 2168, 2178, 2250, 0,
+		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
+	  .vrefresh = 25, },
+	/* 3 - 3840x2160@24Hz */
+	{ DRM_MODE("3840x2160", DRM_MODE_TYPE_DRIVER, 297000,
+		   3840, 5116, 5204, 5500, 0,
+		   2160, 2168, 2178, 2250, 0,
+		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
+	  .vrefresh = 24, },
+	/* 4 - 4096x2160@24Hz (SMPTE) */
+	{ DRM_MODE("4096x2160", DRM_MODE_TYPE_DRIVER, 297000,
+		   4096, 5116, 5204, 5500, 0,
+		   2160, 2168, 2178, 2250, 0,
+		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
+	  .vrefresh = 24, },
+};
+
 /*** DDC fetch and block validation ***/
 
 static const u8 edid_header[] = {
@@ -2287,7 +2320,6 @@ add_detailed_modes(struct drm_connector *connector, struct edid *edid,
 	return closure.modes;
 }
 
-#define HDMI_IDENTIFIER 0x000C03
 #define AUDIO_BLOCK	0x01
 #define VIDEO_BLOCK     0x02
 #define VENDOR_BLOCK    0x03
@@ -2298,10 +2330,10 @@ add_detailed_modes(struct drm_connector *connector, struct edid *edid,
 #define EDID_CEA_YCRCB422	(1 << 4)
 #define EDID_CEA_VCDB_QS	(1 << 6)
 
-/**
+/*
  * Search EDID for CEA extension block.
  */
-u8 *drm_find_cea_extension(struct edid *edid)
+static u8 *drm_find_cea_extension(struct edid *edid)
 {
 	u8 *edid_ext = NULL;
 	int i;
@@ -2322,7 +2354,6 @@ u8 *drm_find_cea_extension(struct edid *edid)
 
 	return edid_ext;
 }
-EXPORT_SYMBOL(drm_find_cea_extension);
 
 /*
  * Calculate the alternate clock for the CEA mode
@@ -2380,6 +2411,54 @@ u8 drm_match_cea_mode(const struct drm_display_mode *to_match)
 }
 EXPORT_SYMBOL(drm_match_cea_mode);
 
+/*
+ * Calculate the alternate clock for HDMI modes (those from the HDMI vendor
+ * specific block).
+ *
+ * It's almost like cea_mode_alternate_clock(), we just need to add an
+ * exception for the VIC 4 mode (4096x2160@24Hz): no alternate clock for this
+ * one.
+ */
+static unsigned int
+hdmi_mode_alternate_clock(const struct drm_display_mode *hdmi_mode)
+{
+	if (hdmi_mode->vdisplay == 4096 && hdmi_mode->hdisplay == 2160)
+		return hdmi_mode->clock;
+
+	return cea_mode_alternate_clock(hdmi_mode);
+}
+
+/*
+ * drm_match_hdmi_mode - look for a HDMI mode matching given mode
+ * @to_match: display mode
+ *
+ * An HDMI mode is one defined in the HDMI vendor specific block.
+ *
+ * Returns the HDMI Video ID (VIC) of the mode or 0 if it isn't one.
+ */
+static u8 drm_match_hdmi_mode(const struct drm_display_mode *to_match)
+{
+	u8 mode;
+
+	if (!to_match->clock)
+		return 0;
+
+	for (mode = 0; mode < ARRAY_SIZE(edid_4k_modes); mode++) {
+		const struct drm_display_mode *hdmi_mode = &edid_4k_modes[mode];
+		unsigned int clock1, clock2;
+
+		/* Make sure to also match alternate clocks */
+		clock1 = hdmi_mode->clock;
+		clock2 = hdmi_mode_alternate_clock(hdmi_mode);
+
+		if ((KHZ2PICOS(to_match->clock) == KHZ2PICOS(clock1) ||
+		     KHZ2PICOS(to_match->clock) == KHZ2PICOS(clock2)) &&
+		    drm_mode_equal_no_clocks(to_match, hdmi_mode))
+			return mode + 1;
+	}
+	return 0;
+}
+
 static int
 add_alternate_cea_modes(struct drm_connector *connector, struct edid *edid)
 {
@@ -2397,18 +2476,26 @@ add_alternate_cea_modes(struct drm_connector *connector, struct edid *edid)
 	 * with the alternate clock for certain CEA modes.
 	 */
 	list_for_each_entry(mode, &connector->probed_modes, head) {
-		const struct drm_display_mode *cea_mode;
+		const struct drm_display_mode *cea_mode = NULL;
 		struct drm_display_mode *newmode;
-		u8 cea_mode_idx = drm_match_cea_mode(mode) - 1;
+		u8 mode_idx = drm_match_cea_mode(mode) - 1;
 		unsigned int clock1, clock2;
 
-		if (cea_mode_idx >= ARRAY_SIZE(edid_cea_modes))
-			continue;
+		if (mode_idx < ARRAY_SIZE(edid_cea_modes)) {
+			cea_mode = &edid_cea_modes[mode_idx];
+			clock2 = cea_mode_alternate_clock(cea_mode);
+		} else {
+			mode_idx = drm_match_hdmi_mode(mode) - 1;
+			if (mode_idx < ARRAY_SIZE(edid_4k_modes)) {
+				cea_mode = &edid_4k_modes[mode_idx];
+				clock2 = hdmi_mode_alternate_clock(cea_mode);
+			}
+		}
 
-		cea_mode = &edid_cea_modes[cea_mode_idx];
+		if (!cea_mode)
+			continue;
 
 		clock1 = cea_mode->clock;
-		clock2 = cea_mode_alternate_clock(cea_mode);
 
 		if (clock1 == clock2)
 			continue;
@@ -2442,10 +2529,11 @@ add_alternate_cea_modes(struct drm_connector *connector, struct edid *edid)
 }
 
 static int
-do_cea_modes (struct drm_connector *connector, u8 *db, u8 len)
+do_cea_modes(struct drm_connector *connector, const u8 *db, u8 len)
 {
 	struct drm_device *dev = connector->dev;
-	u8 * mode, cea_mode;
+	const u8 *mode;
+	u8 cea_mode;
 	int modes = 0;
 
 	for (mode = db; mode < db + len; mode++) {
@@ -2465,6 +2553,68 @@ do_cea_modes (struct drm_connector *connector, u8 *db, u8 len)
 	return modes;
 }
 
+/*
+ * do_hdmi_vsdb_modes - Parse the HDMI Vendor Specific data block
+ * @connector: connector corresponding to the HDMI sink
+ * @db: start of the CEA vendor specific block
+ * @len: length of the CEA block payload, ie. one can access up to db[len]
+ *
+ * Parses the HDMI VSDB looking for modes to add to @connector.
+ */
+static int
+do_hdmi_vsdb_modes(struct drm_connector *connector, const u8 *db, u8 len)
+{
+	struct drm_device *dev = connector->dev;
+	int modes = 0, offset = 0, i;
+	u8 vic_len;
+
+	if (len < 8)
+		goto out;
+
+	/* no HDMI_Video_Present */
+	if (!(db[8] & (1 << 5)))
+		goto out;
+
+	/* Latency_Fields_Present */
+	if (db[8] & (1 << 7))
+		offset += 2;
+
+	/* I_Latency_Fields_Present */
+	if (db[8] & (1 << 6))
+		offset += 2;
+
+	/* the declared length is not long enough for the 2 first bytes
+	 * of additional video format capabilities */
+	offset += 2;
+	if (len < (8 + offset))
+		goto out;
+
+	vic_len = db[8 + offset] >> 5;
+
+	for (i = 0; i < vic_len && len >= (9 + offset + i); i++) {
+		struct drm_display_mode *newmode;
+		u8 vic;
+
+		vic = db[9 + offset + i];
+
+		vic--; /* VICs start at 1 */
+		if (vic >= ARRAY_SIZE(edid_4k_modes)) {
+			DRM_ERROR("Unknown HDMI VIC: %d\n", vic);
+			continue;
+		}
+
+		newmode = drm_mode_duplicate(dev, &edid_4k_modes[vic]);
+		if (!newmode)
+			continue;
+
+		drm_mode_probed_add(connector, newmode);
+		modes++;
+	}
+
+out:
+	return modes;
+}
+
 static int
 cea_db_payload_len(const u8 *db)
 {
@@ -2496,14 +2646,30 @@ cea_db_offsets(const u8 *cea, int *start, int *end)
 	return 0;
 }
 
+static bool cea_db_is_hdmi_vsdb(const u8 *db)
+{
+	int hdmi_id;
+
+	if (cea_db_tag(db) != VENDOR_BLOCK)
+		return false;
+
+	if (cea_db_payload_len(db) < 5)
+		return false;
+
+	hdmi_id = db[1] | (db[2] << 8) | (db[3] << 16);
+
+	return hdmi_id == HDMI_IEEE_OUI;
+}
+
 #define for_each_cea_db(cea, i, start, end) \
 	for ((i) = (start); (i) < (end) && (i) + cea_db_payload_len(&(cea)[(i)]) < (end); (i) += cea_db_payload_len(&(cea)[(i)]) + 1)
 
 static int
 add_cea_modes(struct drm_connector *connector, struct edid *edid)
 {
-	u8 * cea = drm_find_cea_extension(edid);
-	u8 * db, dbl;
+	const u8 *cea = drm_find_cea_extension(edid);
+	const u8 *db;
+	u8 dbl;
 	int modes = 0;
 
 	if (cea && cea_revision(cea) >= 3) {
@@ -2517,7 +2683,9 @@ add_cea_modes(struct drm_connector *connector, struct edid *edid)
 			dbl = cea_db_payload_len(db);
 
 			if (cea_db_tag(db) == VIDEO_BLOCK)
-				modes += do_cea_modes (connector, db+1, dbl);
+				modes += do_cea_modes(connector, db + 1, dbl);
+			else if (cea_db_is_hdmi_vsdb(db))
+				modes += do_hdmi_vsdb_modes(connector, db, dbl);
 		}
 	}
 
@@ -2570,21 +2738,6 @@ monitor_name(struct detailed_timing *t, void *data)
 		*(u8 **)data = t->data.other_data.data.str.str;
 }
 
-static bool cea_db_is_hdmi_vsdb(const u8 *db)
-{
-	int hdmi_id;
-
-	if (cea_db_tag(db) != VENDOR_BLOCK)
-		return false;
-
-	if (cea_db_payload_len(db) < 5)
-		return false;
-
-	hdmi_id = db[1] | (db[2] << 8) | (db[3] << 16);
-
-	return hdmi_id == HDMI_IDENTIFIER;
-}
-
 /**
  * drm_edid_to_eld - build ELD from EDID
  * @connector: connector corresponding to the HDMI/DP sink
@@ -2732,6 +2885,60 @@ int drm_edid_to_sad(struct edid *edid, struct cea_sad **sads)
 EXPORT_SYMBOL(drm_edid_to_sad);
 
 /**
+ * drm_edid_to_speaker_allocation - extracts Speaker Allocation Data Blocks from EDID
+ * @edid: EDID to parse
+ * @sadb: pointer to the speaker block
+ *
+ * Looks for CEA EDID block and extracts the Speaker Allocation Data Block from it.
+ * Note: returned pointer needs to be kfreed
+ *
+ * Return number of found Speaker Allocation Blocks or negative number on error.
+ */
+int drm_edid_to_speaker_allocation(struct edid *edid, u8 **sadb)
+{
+	int count = 0;
+	int i, start, end, dbl;
+	const u8 *cea;
+
+	cea = drm_find_cea_extension(edid);
+	if (!cea) {
+		DRM_DEBUG_KMS("SAD: no CEA Extension found\n");
+		return -ENOENT;
+	}
+
+	if (cea_revision(cea) < 3) {
+		DRM_DEBUG_KMS("SAD: wrong CEA revision\n");
+		return -ENOTSUPP;
+	}
+
+	if (cea_db_offsets(cea, &start, &end)) {
+		DRM_DEBUG_KMS("SAD: invalid data block offsets\n");
+		return -EPROTO;
+	}
+
+	for_each_cea_db(cea, i, start, end) {
+		const u8 *db = &cea[i];
+
+		if (cea_db_tag(db) == SPEAKER_BLOCK) {
+			dbl = cea_db_payload_len(db);
+
+			/* Speaker Allocation Data Block */
+			if (dbl == 3) {
+				*sadb = kmalloc(dbl, GFP_KERNEL);
+				if (!*sadb)
+					return -ENOMEM;
+				memcpy(*sadb, &db[1], dbl);
+				count = dbl;
+				break;
+			}
+		}
+	}
+
+	return count;
+}
+EXPORT_SYMBOL(drm_edid_to_speaker_allocation);
+
+/**
  * drm_av_sync_delay - HDMI/DP sink audio-video sync delay in millisecond
  * @connector: connector associated with the HDMI/DP sink
  * @mode: the display mode
@@ -3102,9 +3309,10 @@ drm_hdmi_avi_infoframe_from_display_mode(struct hdmi_avi_infoframe *frame,
 	if (err < 0)
 		return err;
 
+	if (mode->flags & DRM_MODE_FLAG_DBLCLK)
+		frame->pixel_repeat = 1;
+
 	frame->video_code = drm_match_cea_mode(mode);
-	if (!frame->video_code)
-		return 0;
 
 	frame->picture_aspect = HDMI_PICTURE_ASPECT_NONE;
 	frame->active_aspect = HDMI_ACTIVE_ASPECT_PICTURE;
@@ -3112,3 +3320,39 @@ drm_hdmi_avi_infoframe_from_display_mode(struct hdmi_avi_infoframe *frame,
 	return 0;
 }
 EXPORT_SYMBOL(drm_hdmi_avi_infoframe_from_display_mode);
+
+/**
+ * drm_hdmi_vendor_infoframe_from_display_mode() - fill an HDMI infoframe with
+ * data from a DRM display mode
+ * @frame: HDMI vendor infoframe
+ * @mode: DRM display mode
+ *
+ * Note that there's is a need to send HDMI vendor infoframes only when using a
+ * 4k or stereoscopic 3D mode. So when giving any other mode as input this
+ * function will return -EINVAL, error that can be safely ignored.
+ *
+ * Returns 0 on success or a negative error code on failure.
+ */
+int
+drm_hdmi_vendor_infoframe_from_display_mode(struct hdmi_vendor_infoframe *frame,
+					    const struct drm_display_mode *mode)
+{
+	int err;
+	u8 vic;
+
+	if (!frame || !mode)
+		return -EINVAL;
+
+	vic = drm_match_hdmi_mode(mode);
+	if (!vic)
+		return -EINVAL;
+
+	err = hdmi_vendor_infoframe_init(frame);
+	if (err < 0)
+		return err;
+
+	frame->vic = vic;
+
+	return 0;
+}
+EXPORT_SYMBOL(drm_hdmi_vendor_infoframe_from_display_mode);
diff --git a/drivers/gpu/drm/drm_fb_cma_helper.c b/drivers/gpu/drm/drm_fb_cma_helper.c
index c385cc5e730e..61b5a47ad239 100644
--- a/drivers/gpu/drm/drm_fb_cma_helper.c
+++ b/drivers/gpu/drm/drm_fb_cma_helper.c
@@ -181,11 +181,11 @@ struct drm_gem_cma_object *drm_fb_cma_get_gem_obj(struct drm_framebuffer *fb,
 EXPORT_SYMBOL_GPL(drm_fb_cma_get_gem_obj);
 
 #ifdef CONFIG_DEBUG_FS
-/**
+/*
  * drm_fb_cma_describe() - Helper to dump information about a single
  * CMA framebuffer object
  */
-void drm_fb_cma_describe(struct drm_framebuffer *fb, struct seq_file *m)
+static void drm_fb_cma_describe(struct drm_framebuffer *fb, struct seq_file *m)
 {
 	struct drm_fb_cma *fb_cma = to_fb_cma(fb);
 	int i, n = drm_format_num_planes(fb->pixel_format);
@@ -199,7 +199,6 @@ void drm_fb_cma_describe(struct drm_framebuffer *fb, struct seq_file *m)
 		drm_gem_cma_describe(fb_cma->obj[i], m);
 	}
 }
-EXPORT_SYMBOL_GPL(drm_fb_cma_describe);
 
 /**
  * drm_fb_cma_debugfs_show() - Helper to list CMA framebuffer objects
diff --git a/drivers/gpu/drm/drm_flip_work.c b/drivers/gpu/drm/drm_flip_work.c
new file mode 100644
index 000000000000..e788882d9021
--- /dev/null
+++ b/drivers/gpu/drm/drm_flip_work.c
@@ -0,0 +1,124 @@
+/*
+ * Copyright (C) 2013 Red Hat
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the next
+ * paragraph) shall be included in all copies or substantial portions of the
+ * Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include "drmP.h"
+#include "drm_flip_work.h"
+
+/**
+ * drm_flip_work_queue - queue work
+ * @work: the flip-work
+ * @val: the value to queue
+ *
+ * Queues work, that will later be run (passed back to drm_flip_func_t
+ * func) on a work queue after drm_flip_work_commit() is called.
+ */
+void drm_flip_work_queue(struct drm_flip_work *work, void *val)
+{
+	if (kfifo_put(&work->fifo, (const void **)&val)) {
+		atomic_inc(&work->pending);
+	} else {
+		DRM_ERROR("%s fifo full!\n", work->name);
+		work->func(work, val);
+	}
+}
+EXPORT_SYMBOL(drm_flip_work_queue);
+
+/**
+ * drm_flip_work_commit - commit queued work
+ * @work: the flip-work
+ * @wq: the work-queue to run the queued work on
+ *
+ * Trigger work previously queued by drm_flip_work_queue() to run
+ * on a workqueue.  The typical usage would be to queue work (via
+ * drm_flip_work_queue()) at any point (from vblank irq and/or
+ * prior), and then from vblank irq commit the queued work.
+ */
+void drm_flip_work_commit(struct drm_flip_work *work,
+		struct workqueue_struct *wq)
+{
+	uint32_t pending = atomic_read(&work->pending);
+	atomic_add(pending, &work->count);
+	atomic_sub(pending, &work->pending);
+	queue_work(wq, &work->worker);
+}
+EXPORT_SYMBOL(drm_flip_work_commit);
+
+static void flip_worker(struct work_struct *w)
+{
+	struct drm_flip_work *work = container_of(w, struct drm_flip_work, worker);
+	uint32_t count = atomic_read(&work->count);
+	void *val = NULL;
+
+	atomic_sub(count, &work->count);
+
+	while(count--)
+		if (!WARN_ON(!kfifo_get(&work->fifo, &val)))
+			work->func(work, val);
+}
+
+/**
+ * drm_flip_work_init - initialize flip-work
+ * @work: the flip-work to initialize
+ * @size: the max queue depth
+ * @name: debug name
+ * @func: the callback work function
+ *
+ * Initializes/allocates resources for the flip-work
+ *
+ * RETURNS:
+ * Zero on success, error code on failure.
+ */
+int drm_flip_work_init(struct drm_flip_work *work, int size,
+		const char *name, drm_flip_func_t func)
+{
+	int ret;
+
+	work->name = name;
+	atomic_set(&work->count, 0);
+	atomic_set(&work->pending, 0);
+	work->func = func;
+
+	ret = kfifo_alloc(&work->fifo, size, GFP_KERNEL);
+	if (ret) {
+		DRM_ERROR("could not allocate %s fifo\n", name);
+		return ret;
+	}
+
+	INIT_WORK(&work->worker, flip_worker);
+
+	return 0;
+}
+EXPORT_SYMBOL(drm_flip_work_init);
+
+/**
+ * drm_flip_work_cleanup - cleans up flip-work
+ * @work: the flip-work to cleanup
+ *
+ * Destroy resources allocated for the flip-work
+ */
+void drm_flip_work_cleanup(struct drm_flip_work *work)
+{
+	WARN_ON(!kfifo_is_empty(&work->fifo));
+	kfifo_free(&work->fifo);
+}
+EXPORT_SYMBOL(drm_flip_work_cleanup);
diff --git a/drivers/gpu/drm/drm_fops.c b/drivers/gpu/drm/drm_fops.c
index 3a24385e0368..3f84277d7036 100644
--- a/drivers/gpu/drm/drm_fops.c
+++ b/drivers/gpu/drm/drm_fops.c
@@ -48,59 +48,21 @@ static int drm_open_helper(struct inode *inode, struct file *filp,
 
 static int drm_setup(struct drm_device * dev)
 {
-	int i;
 	int ret;
 
-	if (dev->driver->firstopen) {
+	if (dev->driver->firstopen &&
+	    !drm_core_check_feature(dev, DRIVER_MODESET)) {
 		ret = dev->driver->firstopen(dev);
 		if (ret != 0)
 			return ret;
 	}
 
-	atomic_set(&dev->ioctl_count, 0);
-	atomic_set(&dev->vma_count, 0);
-
-	if (drm_core_check_feature(dev, DRIVER_HAVE_DMA) &&
-	    !drm_core_check_feature(dev, DRIVER_MODESET)) {
-		dev->buf_use = 0;
-		atomic_set(&dev->buf_alloc, 0);
-
-		i = drm_dma_setup(dev);
-		if (i < 0)
-			return i;
-	}
-
-	for (i = 0; i < ARRAY_SIZE(dev->counts); i++)
-		atomic_set(&dev->counts[i], 0);
-
-	dev->sigdata.lock = NULL;
-
-	dev->context_flag = 0;
-	dev->interrupt_flag = 0;
-	dev->dma_flag = 0;
-	dev->last_context = 0;
-	dev->last_switch = 0;
-	dev->last_checked = 0;
-	init_waitqueue_head(&dev->context_wait);
-	dev->if_version = 0;
-
-	dev->ctx_start = 0;
-	dev->lck_start = 0;
+	ret = drm_legacy_dma_setup(dev);
+	if (ret < 0)
+		return ret;
 
-	dev->buf_async = NULL;
-	init_waitqueue_head(&dev->buf_readers);
-	init_waitqueue_head(&dev->buf_writers);
 
 	DRM_DEBUG("\n");
-
-	/*
-	 * The kernel's context could be created here, but is now created
-	 * in drm_dma_enqueue.  This is more resource-efficient for
-	 * hardware that does not do DMA, but may mean that
-	 * drm_select_queue fails between the time the interrupt is
-	 * initialized and the time the queues are initialized.
-	 */
-
 	return 0;
 }
 
@@ -257,7 +219,7 @@ static int drm_open_helper(struct inode *inode, struct file *filp,
 		return -EBUSY;	/* No exclusive opens */
 	if (!drm_cpu_valid())
 		return -EINVAL;
-	if (dev->switch_power_state != DRM_SWITCH_POWER_ON)
+	if (dev->switch_power_state != DRM_SWITCH_POWER_ON && dev->switch_power_state != DRM_SWITCH_POWER_DYNAMIC_OFF)
 		return -EINVAL;
 
 	DRM_DEBUG("pid = %d, minor = %d\n", task_pid_nr(current), minor_id);
@@ -300,10 +262,10 @@ static int drm_open_helper(struct inode *inode, struct file *filp,
 			goto out_prime_destroy;
 	}
 
-
-	/* if there is no current master make this fd it */
+	/* if there is no current master make this fd it, but do not create
+	 * any master object for render clients */
 	mutex_lock(&dev->struct_mutex);
-	if (!priv->minor->master) {
+	if (!priv->minor->master && !drm_is_render_client(priv)) {
 		/* create a new master */
 		priv->minor->master = drm_master_create(priv->minor);
 		if (!priv->minor->master) {
@@ -341,12 +303,11 @@ static int drm_open_helper(struct inode *inode, struct file *filp,
 				goto out_close;
 			}
 		}
-		mutex_unlock(&dev->struct_mutex);
-	} else {
+	} else if (!drm_is_render_client(priv)) {
 		/* get a reference to the master */
 		priv->master = drm_master_get(priv->minor->master);
-		mutex_unlock(&dev->struct_mutex);
 	}
+	mutex_unlock(&dev->struct_mutex);
 
 	mutex_lock(&dev->struct_mutex);
 	list_add(&priv->lhead, &dev->filelist);
@@ -388,18 +349,6 @@ out_put_pid:
 	return ret;
 }
 
-/** No-op. */
-int drm_fasync(int fd, struct file *filp, int on)
-{
-	struct drm_file *priv = filp->private_data;
-	struct drm_device *dev = priv->minor->dev;
-
-	DRM_DEBUG("fd = %d, device = 0x%lx\n", fd,
-		  (long)old_encode_dev(priv->minor->device));
-	return fasync_helper(fd, filp, on, &dev->buf_async);
-}
-EXPORT_SYMBOL(drm_fasync);
-
 static void drm_master_release(struct drm_device *dev, struct file *filp)
 {
 	struct drm_file *file_priv = filp->private_data;
@@ -547,7 +496,8 @@ int drm_release(struct inode *inode, struct file *filp)
 	iput(container_of(dev->dev_mapping, struct inode, i_data));
 
 	/* drop the reference held my the file priv */
-	drm_master_put(&file_priv->master);
+	if (file_priv->master)
+		drm_master_put(&file_priv->master);
 	file_priv->is_master = 0;
 	list_del(&file_priv->lhead);
 	mutex_unlock(&dev->struct_mutex);
@@ -555,6 +505,7 @@ int drm_release(struct inode *inode, struct file *filp)
 	if (dev->driver->postclose)
 		dev->driver->postclose(dev, file_priv);
 
+
 	if (drm_core_check_feature(dev, DRIVER_PRIME))
 		drm_prime_destroy_file_private(&file_priv->prime);
 
diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c
index 603f256152ef..49293bdc972a 100644
--- a/drivers/gpu/drm/drm_gem.c
+++ b/drivers/gpu/drm/drm_gem.c
@@ -37,6 +37,7 @@
 #include <linux/shmem_fs.h>
 #include <linux/dma-buf.h>
 #include <drm/drmP.h>
+#include <drm/drm_vma_manager.h>
 
 /** @file drm_gem.c
  *
@@ -92,7 +93,7 @@ drm_gem_init(struct drm_device *dev)
 {
 	struct drm_gem_mm *mm;
 
-	spin_lock_init(&dev->object_name_lock);
+	mutex_init(&dev->object_name_lock);
 	idr_init(&dev->object_name_idr);
 
 	mm = kzalloc(sizeof(struct drm_gem_mm), GFP_KERNEL);
@@ -102,14 +103,9 @@ drm_gem_init(struct drm_device *dev)
 	}
 
 	dev->mm_private = mm;
-
-	if (drm_ht_create(&mm->offset_hash, 12)) {
-		kfree(mm);
-		return -ENOMEM;
-	}
-
-	drm_mm_init(&mm->offset_manager, DRM_FILE_PAGE_OFFSET_START,
-		    DRM_FILE_PAGE_OFFSET_SIZE);
+	drm_vma_offset_manager_init(&mm->vma_manager,
+				    DRM_FILE_PAGE_OFFSET_START,
+				    DRM_FILE_PAGE_OFFSET_SIZE);
 
 	return 0;
 }
@@ -119,8 +115,7 @@ drm_gem_destroy(struct drm_device *dev)
 {
 	struct drm_gem_mm *mm = dev->mm_private;
 
-	drm_mm_takedown(&mm->offset_manager);
-	drm_ht_remove(&mm->offset_hash);
+	drm_vma_offset_manager_destroy(&mm->vma_manager);
 	kfree(mm);
 	dev->mm_private = NULL;
 }
@@ -132,16 +127,14 @@ drm_gem_destroy(struct drm_device *dev)
 int drm_gem_object_init(struct drm_device *dev,
 			struct drm_gem_object *obj, size_t size)
 {
-	BUG_ON((size & (PAGE_SIZE - 1)) != 0);
+	struct file *filp;
 
-	obj->dev = dev;
-	obj->filp = shmem_file_setup("drm mm object", size, VM_NORESERVE);
-	if (IS_ERR(obj->filp))
-		return PTR_ERR(obj->filp);
+	filp = shmem_file_setup("drm mm object", size, VM_NORESERVE);
+	if (IS_ERR(filp))
+		return PTR_ERR(filp);
 
-	kref_init(&obj->refcount);
-	atomic_set(&obj->handle_count, 0);
-	obj->size = size;
+	drm_gem_private_object_init(dev, obj, size);
+	obj->filp = filp;
 
 	return 0;
 }
@@ -152,8 +145,8 @@ EXPORT_SYMBOL(drm_gem_object_init);
  * no GEM provided backing store. Instead the caller is responsible for
  * backing the object and handling it.
  */
-int drm_gem_private_object_init(struct drm_device *dev,
-			struct drm_gem_object *obj, size_t size)
+void drm_gem_private_object_init(struct drm_device *dev,
+				 struct drm_gem_object *obj, size_t size)
 {
 	BUG_ON((size & (PAGE_SIZE - 1)) != 0);
 
@@ -161,10 +154,9 @@ int drm_gem_private_object_init(struct drm_device *dev,
 	obj->filp = NULL;
 
 	kref_init(&obj->refcount);
-	atomic_set(&obj->handle_count, 0);
+	obj->handle_count = 0;
 	obj->size = size;
-
-	return 0;
+	drm_vma_node_reset(&obj->vma_node);
 }
 EXPORT_SYMBOL(drm_gem_private_object_init);
 
@@ -200,16 +192,79 @@ EXPORT_SYMBOL(drm_gem_object_alloc);
 static void
 drm_gem_remove_prime_handles(struct drm_gem_object *obj, struct drm_file *filp)
 {
-	if (obj->import_attach) {
-		drm_prime_remove_buf_handle(&filp->prime,
-				obj->import_attach->dmabuf);
+	/*
+	 * Note: obj->dma_buf can't disappear as long as we still hold a
+	 * handle reference in obj->handle_count.
+	 */
+	mutex_lock(&filp->prime.lock);
+	if (obj->dma_buf) {
+		drm_prime_remove_buf_handle_locked(&filp->prime,
+						   obj->dma_buf);
 	}
-	if (obj->export_dma_buf) {
-		drm_prime_remove_buf_handle(&filp->prime,
-				obj->export_dma_buf);
+	mutex_unlock(&filp->prime.lock);
+}
+
+static void drm_gem_object_ref_bug(struct kref *list_kref)
+{
+	BUG();
+}
+
+/**
+ * Called after the last handle to the object has been closed
+ *
+ * Removes any name for the object. Note that this must be
+ * called before drm_gem_object_free or we'll be touching
+ * freed memory
+ */
+static void drm_gem_object_handle_free(struct drm_gem_object *obj)
+{
+	struct drm_device *dev = obj->dev;
+
+	/* Remove any name for this object */
+	if (obj->name) {
+		idr_remove(&dev->object_name_idr, obj->name);
+		obj->name = 0;
+		/*
+		 * The object name held a reference to this object, drop
+		 * that now.
+		*
+		* This cannot be the last reference, since the handle holds one too.
+		 */
+		kref_put(&obj->refcount, drm_gem_object_ref_bug);
 	}
 }
 
+static void drm_gem_object_exported_dma_buf_free(struct drm_gem_object *obj)
+{
+	/* Unbreak the reference cycle if we have an exported dma_buf. */
+	if (obj->dma_buf) {
+		dma_buf_put(obj->dma_buf);
+		obj->dma_buf = NULL;
+	}
+}
+
+static void
+drm_gem_object_handle_unreference_unlocked(struct drm_gem_object *obj)
+{
+	if (WARN_ON(obj->handle_count == 0))
+		return;
+
+	/*
+	* Must bump handle count first as this may be the last
+	* ref, in which case the object would disappear before we
+	* checked for a name
+	*/
+
+	mutex_lock(&obj->dev->object_name_lock);
+	if (--obj->handle_count == 0) {
+		drm_gem_object_handle_free(obj);
+		drm_gem_object_exported_dma_buf_free(obj);
+	}
+	mutex_unlock(&obj->dev->object_name_lock);
+
+	drm_gem_object_unreference_unlocked(obj);
+}
+
 /**
  * Removes the mapping from handle to filp for this object.
  */
@@ -242,7 +297,9 @@ drm_gem_handle_delete(struct drm_file *filp, u32 handle)
 	idr_remove(&filp->object_idr, handle);
 	spin_unlock(&filp->table_lock);
 
-	drm_gem_remove_prime_handles(obj, filp);
+	if (drm_core_check_feature(dev, DRIVER_PRIME))
+		drm_gem_remove_prime_handles(obj, filp);
+	drm_vma_node_revoke(&obj->vma_node, filp->filp);
 
 	if (dev->driver->gem_close_object)
 		dev->driver->gem_close_object(obj, filp);
@@ -253,18 +310,36 @@ drm_gem_handle_delete(struct drm_file *filp, u32 handle)
 EXPORT_SYMBOL(drm_gem_handle_delete);
 
 /**
- * Create a handle for this object. This adds a handle reference
- * to the object, which includes a regular reference count. Callers
- * will likely want to dereference the object afterwards.
+ * drm_gem_dumb_destroy - dumb fb callback helper for gem based drivers
+ * 
+ * This implements the ->dumb_destroy kms driver callback for drivers which use
+ * gem to manage their backing storage.
+ */
+int drm_gem_dumb_destroy(struct drm_file *file,
+			 struct drm_device *dev,
+			 uint32_t handle)
+{
+	return drm_gem_handle_delete(file, handle);
+}
+EXPORT_SYMBOL(drm_gem_dumb_destroy);
+
+/**
+ * drm_gem_handle_create_tail - internal functions to create a handle
+ * 
+ * This expects the dev->object_name_lock to be held already and will drop it
+ * before returning. Used to avoid races in establishing new handles when
+ * importing an object from either an flink name or a dma-buf.
  */
 int
-drm_gem_handle_create(struct drm_file *file_priv,
-		       struct drm_gem_object *obj,
-		       u32 *handlep)
+drm_gem_handle_create_tail(struct drm_file *file_priv,
+			   struct drm_gem_object *obj,
+			   u32 *handlep)
 {
 	struct drm_device *dev = obj->dev;
 	int ret;
 
+	WARN_ON(!mutex_is_locked(&dev->object_name_lock));
+
 	/*
 	 * Get the user-visible handle using idr.  Preload and perform
 	 * allocation under our spinlock.
@@ -273,14 +348,22 @@ drm_gem_handle_create(struct drm_file *file_priv,
 	spin_lock(&file_priv->table_lock);
 
 	ret = idr_alloc(&file_priv->object_idr, obj, 1, 0, GFP_NOWAIT);
-
+	drm_gem_object_reference(obj);
+	obj->handle_count++;
 	spin_unlock(&file_priv->table_lock);
 	idr_preload_end();
-	if (ret < 0)
+	mutex_unlock(&dev->object_name_lock);
+	if (ret < 0) {
+		drm_gem_object_handle_unreference_unlocked(obj);
 		return ret;
+	}
 	*handlep = ret;
 
-	drm_gem_object_handle_reference(obj);
+	ret = drm_vma_node_allow(&obj->vma_node, file_priv->filp);
+	if (ret) {
+		drm_gem_handle_delete(file_priv, *handlep);
+		return ret;
+	}
 
 	if (dev->driver->gem_open_object) {
 		ret = dev->driver->gem_open_object(obj, file_priv);
@@ -292,6 +375,21 @@ drm_gem_handle_create(struct drm_file *file_priv,
 
 	return 0;
 }
+
+/**
+ * Create a handle for this object. This adds a handle reference
+ * to the object, which includes a regular reference count. Callers
+ * will likely want to dereference the object afterwards.
+ */
+int
+drm_gem_handle_create(struct drm_file *file_priv,
+		       struct drm_gem_object *obj,
+		       u32 *handlep)
+{
+	mutex_lock(&obj->dev->object_name_lock);
+
+	return drm_gem_handle_create_tail(file_priv, obj, handlep);
+}
 EXPORT_SYMBOL(drm_gem_handle_create);
 
 
@@ -306,81 +404,155 @@ drm_gem_free_mmap_offset(struct drm_gem_object *obj)
 {
 	struct drm_device *dev = obj->dev;
 	struct drm_gem_mm *mm = dev->mm_private;
-	struct drm_map_list *list = &obj->map_list;
 
-	drm_ht_remove_item(&mm->offset_hash, &list->hash);
-	drm_mm_put_block(list->file_offset_node);
-	kfree(list->map);
-	list->map = NULL;
+	drm_vma_offset_remove(&mm->vma_manager, &obj->vma_node);
 }
 EXPORT_SYMBOL(drm_gem_free_mmap_offset);
 
 /**
- * drm_gem_create_mmap_offset - create a fake mmap offset for an object
+ * drm_gem_create_mmap_offset_size - create a fake mmap offset for an object
  * @obj: obj in question
+ * @size: the virtual size
  *
  * GEM memory mapping works by handing back to userspace a fake mmap offset
  * it can use in a subsequent mmap(2) call.  The DRM core code then looks
  * up the object based on the offset and sets up the various memory mapping
  * structures.
  *
- * This routine allocates and attaches a fake offset for @obj.
+ * This routine allocates and attaches a fake offset for @obj, in cases where
+ * the virtual size differs from the physical size (ie. obj->size).  Otherwise
+ * just use drm_gem_create_mmap_offset().
  */
 int
-drm_gem_create_mmap_offset(struct drm_gem_object *obj)
+drm_gem_create_mmap_offset_size(struct drm_gem_object *obj, size_t size)
 {
 	struct drm_device *dev = obj->dev;
 	struct drm_gem_mm *mm = dev->mm_private;
-	struct drm_map_list *list;
-	struct drm_local_map *map;
-	int ret;
 
-	/* Set the object up for mmap'ing */
-	list = &obj->map_list;
-	list->map = kzalloc(sizeof(struct drm_map_list), GFP_KERNEL);
-	if (!list->map)
-		return -ENOMEM;
-
-	map = list->map;
-	map->type = _DRM_GEM;
-	map->size = obj->size;
-	map->handle = obj;
+	return drm_vma_offset_add(&mm->vma_manager, &obj->vma_node,
+				  size / PAGE_SIZE);
+}
+EXPORT_SYMBOL(drm_gem_create_mmap_offset_size);
 
-	/* Get a DRM GEM mmap offset allocated... */
-	list->file_offset_node = drm_mm_search_free(&mm->offset_manager,
-			obj->size / PAGE_SIZE, 0, false);
+/**
+ * drm_gem_create_mmap_offset - create a fake mmap offset for an object
+ * @obj: obj in question
+ *
+ * GEM memory mapping works by handing back to userspace a fake mmap offset
+ * it can use in a subsequent mmap(2) call.  The DRM core code then looks
+ * up the object based on the offset and sets up the various memory mapping
+ * structures.
+ *
+ * This routine allocates and attaches a fake offset for @obj.
+ */
+int drm_gem_create_mmap_offset(struct drm_gem_object *obj)
+{
+	return drm_gem_create_mmap_offset_size(obj, obj->size);
+}
+EXPORT_SYMBOL(drm_gem_create_mmap_offset);
 
-	if (!list->file_offset_node) {
-		DRM_ERROR("failed to allocate offset for bo %d\n", obj->name);
-		ret = -ENOSPC;
-		goto out_free_list;
+/**
+ * drm_gem_get_pages - helper to allocate backing pages for a GEM object
+ * from shmem
+ * @obj: obj in question
+ * @gfpmask: gfp mask of requested pages
+ */
+struct page **drm_gem_get_pages(struct drm_gem_object *obj, gfp_t gfpmask)
+{
+	struct inode *inode;
+	struct address_space *mapping;
+	struct page *p, **pages;
+	int i, npages;
+
+	/* This is the shared memory object that backs the GEM resource */
+	inode = file_inode(obj->filp);
+	mapping = inode->i_mapping;
+
+	/* We already BUG_ON() for non-page-aligned sizes in
+	 * drm_gem_object_init(), so we should never hit this unless
+	 * driver author is doing something really wrong:
+	 */
+	WARN_ON((obj->size & (PAGE_SIZE - 1)) != 0);
+
+	npages = obj->size >> PAGE_SHIFT;
+
+	pages = drm_malloc_ab(npages, sizeof(struct page *));
+	if (pages == NULL)
+		return ERR_PTR(-ENOMEM);
+
+	gfpmask |= mapping_gfp_mask(mapping);
+
+	for (i = 0; i < npages; i++) {
+		p = shmem_read_mapping_page_gfp(mapping, i, gfpmask);
+		if (IS_ERR(p))
+			goto fail;
+		pages[i] = p;
+
+		/* There is a hypothetical issue w/ drivers that require
+		 * buffer memory in the low 4GB.. if the pages are un-
+		 * pinned, and swapped out, they can end up swapped back
+		 * in above 4GB.  If pages are already in memory, then
+		 * shmem_read_mapping_page_gfp will ignore the gfpmask,
+		 * even if the already in-memory page disobeys the mask.
+		 *
+		 * It is only a theoretical issue today, because none of
+		 * the devices with this limitation can be populated with
+		 * enough memory to trigger the issue.  But this BUG_ON()
+		 * is here as a reminder in case the problem with
+		 * shmem_read_mapping_page_gfp() isn't solved by the time
+		 * it does become a real issue.
+		 *
+		 * See this thread: http://lkml.org/lkml/2011/7/11/238
+		 */
+		BUG_ON((gfpmask & __GFP_DMA32) &&
+				(page_to_pfn(p) >= 0x00100000UL));
 	}
 
-	list->file_offset_node = drm_mm_get_block(list->file_offset_node,
-			obj->size / PAGE_SIZE, 0);
-	if (!list->file_offset_node) {
-		ret = -ENOMEM;
-		goto out_free_list;
-	}
+	return pages;
 
-	list->hash.key = list->file_offset_node->start;
-	ret = drm_ht_insert_item(&mm->offset_hash, &list->hash);
-	if (ret) {
-		DRM_ERROR("failed to add to map hash\n");
-		goto out_free_mm;
-	}
+fail:
+	while (i--)
+		page_cache_release(pages[i]);
 
-	return 0;
+	drm_free_large(pages);
+	return ERR_CAST(p);
+}
+EXPORT_SYMBOL(drm_gem_get_pages);
 
-out_free_mm:
-	drm_mm_put_block(list->file_offset_node);
-out_free_list:
-	kfree(list->map);
-	list->map = NULL;
+/**
+ * drm_gem_put_pages - helper to free backing pages for a GEM object
+ * @obj: obj in question
+ * @pages: pages to free
+ * @dirty: if true, pages will be marked as dirty
+ * @accessed: if true, the pages will be marked as accessed
+ */
+void drm_gem_put_pages(struct drm_gem_object *obj, struct page **pages,
+		bool dirty, bool accessed)
+{
+	int i, npages;
 
-	return ret;
+	/* We already BUG_ON() for non-page-aligned sizes in
+	 * drm_gem_object_init(), so we should never hit this unless
+	 * driver author is doing something really wrong:
+	 */
+	WARN_ON((obj->size & (PAGE_SIZE - 1)) != 0);
+
+	npages = obj->size >> PAGE_SHIFT;
+
+	for (i = 0; i < npages; i++) {
+		if (dirty)
+			set_page_dirty(pages[i]);
+
+		if (accessed)
+			mark_page_accessed(pages[i]);
+
+		/* Undo the reference we took when populating the table */
+		page_cache_release(pages[i]);
+	}
+
+	drm_free_large(pages);
 }
-EXPORT_SYMBOL(drm_gem_create_mmap_offset);
+EXPORT_SYMBOL(drm_gem_put_pages);
 
 /** Returns a reference to the object named by the handle. */
 struct drm_gem_object *
@@ -445,8 +617,14 @@ drm_gem_flink_ioctl(struct drm_device *dev, void *data,
 	if (obj == NULL)
 		return -ENOENT;
 
+	mutex_lock(&dev->object_name_lock);
 	idr_preload(GFP_KERNEL);
-	spin_lock(&dev->object_name_lock);
+	/* prevent races with concurrent gem_close. */
+	if (obj->handle_count == 0) {
+		ret = -ENOENT;
+		goto err;
+	}
+
 	if (!obj->name) {
 		ret = idr_alloc(&dev->object_name_idr, obj, 1, 0, GFP_NOWAIT);
 		if (ret < 0)
@@ -462,8 +640,8 @@ drm_gem_flink_ioctl(struct drm_device *dev, void *data,
 	ret = 0;
 
 err:
-	spin_unlock(&dev->object_name_lock);
 	idr_preload_end();
+	mutex_unlock(&dev->object_name_lock);
 	drm_gem_object_unreference_unlocked(obj);
 	return ret;
 }
@@ -486,15 +664,17 @@ drm_gem_open_ioctl(struct drm_device *dev, void *data,
 	if (!(dev->driver->driver_features & DRIVER_GEM))
 		return -ENODEV;
 
-	spin_lock(&dev->object_name_lock);
+	mutex_lock(&dev->object_name_lock);
 	obj = idr_find(&dev->object_name_idr, (int) args->name);
-	if (obj)
+	if (obj) {
 		drm_gem_object_reference(obj);
-	spin_unlock(&dev->object_name_lock);
-	if (!obj)
+	} else {
+		mutex_unlock(&dev->object_name_lock);
 		return -ENOENT;
+	}
 
-	ret = drm_gem_handle_create(file_priv, obj, &handle);
+	/* drm_gem_handle_create_tail unlocks dev->object_name_lock. */
+	ret = drm_gem_handle_create_tail(file_priv, obj, &handle);
 	drm_gem_object_unreference_unlocked(obj);
 	if (ret)
 		return ret;
@@ -527,7 +707,9 @@ drm_gem_object_release_handle(int id, void *ptr, void *data)
 	struct drm_gem_object *obj = ptr;
 	struct drm_device *dev = obj->dev;
 
-	drm_gem_remove_prime_handles(obj, file_priv);
+	if (drm_core_check_feature(dev, DRIVER_PRIME))
+		drm_gem_remove_prime_handles(obj, file_priv);
+	drm_vma_node_revoke(&obj->vma_node, file_priv->filp);
 
 	if (dev->driver->gem_close_object)
 		dev->driver->gem_close_object(obj, file_priv);
@@ -553,6 +735,8 @@ drm_gem_release(struct drm_device *dev, struct drm_file *file_private)
 void
 drm_gem_object_release(struct drm_gem_object *obj)
 {
+	WARN_ON(obj->dma_buf);
+
 	if (obj->filp)
 	    fput(obj->filp);
 }
@@ -577,41 +761,6 @@ drm_gem_object_free(struct kref *kref)
 }
 EXPORT_SYMBOL(drm_gem_object_free);
 
-static void drm_gem_object_ref_bug(struct kref *list_kref)
-{
-	BUG();
-}
-
-/**
- * Called after the last handle to the object has been closed
- *
- * Removes any name for the object. Note that this must be
- * called before drm_gem_object_free or we'll be touching
- * freed memory
- */
-void drm_gem_object_handle_free(struct drm_gem_object *obj)
-{
-	struct drm_device *dev = obj->dev;
-
-	/* Remove any name for this object */
-	spin_lock(&dev->object_name_lock);
-	if (obj->name) {
-		idr_remove(&dev->object_name_idr, obj->name);
-		obj->name = 0;
-		spin_unlock(&dev->object_name_lock);
-		/*
-		 * The object name held a reference to this object, drop
-		 * that now.
-		*
-		* This cannot be the last reference, since the handle holds one too.
-		 */
-		kref_put(&obj->refcount, drm_gem_object_ref_bug);
-	} else
-		spin_unlock(&dev->object_name_lock);
-
-}
-EXPORT_SYMBOL(drm_gem_object_handle_free);
-
 void drm_gem_vm_open(struct vm_area_struct *vma)
 {
 	struct drm_gem_object *obj = vma->vm_private_data;
@@ -653,6 +802,10 @@ EXPORT_SYMBOL(drm_gem_vm_close);
  * the GEM object is not looked up based on its fake offset. To implement the
  * DRM mmap operation, drivers should use the drm_gem_mmap() function.
  *
+ * drm_gem_mmap_obj() assumes the user is granted access to the buffer while
+ * drm_gem_mmap() prevents unprivileged users from mapping random objects. So
+ * callers must verify access restrictions before calling this helper.
+ *
  * NOTE: This function has to be protected with dev->struct_mutex
  *
  * Return 0 or success or -EINVAL if the object size is smaller than the VMA
@@ -701,14 +854,17 @@ EXPORT_SYMBOL(drm_gem_mmap_obj);
  * Look up the GEM object based on the offset passed in (vma->vm_pgoff will
  * contain the fake offset we created when the GTT map ioctl was called on
  * the object) and map it with a call to drm_gem_mmap_obj().
+ *
+ * If the caller is not granted access to the buffer object, the mmap will fail
+ * with EACCES. Please see the vma manager for more information.
  */
 int drm_gem_mmap(struct file *filp, struct vm_area_struct *vma)
 {
 	struct drm_file *priv = filp->private_data;
 	struct drm_device *dev = priv->minor->dev;
 	struct drm_gem_mm *mm = dev->mm_private;
-	struct drm_local_map *map = NULL;
-	struct drm_hash_item *hash;
+	struct drm_gem_object *obj;
+	struct drm_vma_offset_node *node;
 	int ret = 0;
 
 	if (drm_device_is_unplugged(dev))
@@ -716,21 +872,19 @@ int drm_gem_mmap(struct file *filp, struct vm_area_struct *vma)
 
 	mutex_lock(&dev->struct_mutex);
 
-	if (drm_ht_find_item(&mm->offset_hash, vma->vm_pgoff, &hash)) {
+	node = drm_vma_offset_exact_lookup(&mm->vma_manager, vma->vm_pgoff,
+					   vma_pages(vma));
+	if (!node) {
 		mutex_unlock(&dev->struct_mutex);
 		return drm_mmap(filp, vma);
+	} else if (!drm_vma_node_is_allowed(node, filp)) {
+		mutex_unlock(&dev->struct_mutex);
+		return -EACCES;
 	}
 
-	map = drm_hash_entry(hash, struct drm_map_list, hash)->map;
-	if (!map ||
-	    ((map->flags & _DRM_RESTRICTED) && !capable(CAP_SYS_ADMIN))) {
-		ret =  -EPERM;
-		goto out_unlock;
-	}
-
-	ret = drm_gem_mmap_obj(map->handle, map->size, vma);
+	obj = container_of(node, struct drm_gem_object, vma_node);
+	ret = drm_gem_mmap_obj(obj, drm_vma_node_size(node) << PAGE_SHIFT, vma);
 
-out_unlock:
 	mutex_unlock(&dev->struct_mutex);
 
 	return ret;
diff --git a/drivers/gpu/drm/drm_gem_cma_helper.c b/drivers/gpu/drm/drm_gem_cma_helper.c
index ece72a8ac245..6b51bf90df0e 100644
--- a/drivers/gpu/drm/drm_gem_cma_helper.c
+++ b/drivers/gpu/drm/drm_gem_cma_helper.c
@@ -27,11 +27,7 @@
 #include <drm/drmP.h>
 #include <drm/drm.h>
 #include <drm/drm_gem_cma_helper.h>
-
-static unsigned int get_gem_mmap_offset(struct drm_gem_object *obj)
-{
-	return (unsigned int)obj->map_list.hash.key << PAGE_SHIFT;
-}
+#include <drm/drm_vma_manager.h>
 
 /*
  * __drm_gem_cma_create - Create a GEM CMA object without allocating memory
@@ -172,8 +168,7 @@ void drm_gem_cma_free_object(struct drm_gem_object *gem_obj)
 {
 	struct drm_gem_cma_object *cma_obj;
 
-	if (gem_obj->map_list.map)
-		drm_gem_free_mmap_offset(gem_obj);
+	drm_gem_free_mmap_offset(gem_obj);
 
 	cma_obj = to_drm_gem_cma_obj(gem_obj);
 
@@ -215,7 +210,7 @@ int drm_gem_cma_dumb_create(struct drm_file *file_priv,
 
 	cma_obj = drm_gem_cma_create_with_handle(file_priv, dev,
 			args->size, &args->handle);
-	return PTR_RET(cma_obj);
+	return PTR_ERR_OR_ZERO(cma_obj);
 }
 EXPORT_SYMBOL_GPL(drm_gem_cma_dumb_create);
 
@@ -237,7 +232,7 @@ int drm_gem_cma_dumb_map_offset(struct drm_file *file_priv,
 		return -EINVAL;
 	}
 
-	*offset = get_gem_mmap_offset(gem_obj);
+	*offset = drm_vma_node_offset_addr(&gem_obj->vma_node);
 
 	drm_gem_object_unreference(gem_obj);
 
@@ -286,27 +281,16 @@ int drm_gem_cma_mmap(struct file *filp, struct vm_area_struct *vma)
 }
 EXPORT_SYMBOL_GPL(drm_gem_cma_mmap);
 
-/*
- * drm_gem_cma_dumb_destroy - (struct drm_driver)->dumb_destroy callback function
- */
-int drm_gem_cma_dumb_destroy(struct drm_file *file_priv,
-		struct drm_device *drm, unsigned int handle)
-{
-	return drm_gem_handle_delete(file_priv, handle);
-}
-EXPORT_SYMBOL_GPL(drm_gem_cma_dumb_destroy);
-
 #ifdef CONFIG_DEBUG_FS
 void drm_gem_cma_describe(struct drm_gem_cma_object *cma_obj, struct seq_file *m)
 {
 	struct drm_gem_object *obj = &cma_obj->base;
 	struct drm_device *dev = obj->dev;
-	uint64_t off = 0;
+	uint64_t off;
 
 	WARN_ON(!mutex_is_locked(&dev->struct_mutex));
 
-	if (obj->map_list.map)
-		off = (uint64_t)obj->map_list.hash.key;
+	off = drm_vma_node_start(&obj->vma_node);
 
 	seq_printf(m, "%2d (%2d) %08llx %08Zx %p %d",
 			obj->name, obj->refcount.refcount.counter,
diff --git a/drivers/gpu/drm/drm_info.c b/drivers/gpu/drm/drm_info.c
index d4b20ceda3fb..53298320080b 100644
--- a/drivers/gpu/drm/drm_info.c
+++ b/drivers/gpu/drm/drm_info.c
@@ -207,7 +207,7 @@ static int drm_gem_one_name_info(int id, void *ptr, void *data)
 
 	seq_printf(m, "%6d %8zd %7d %8d\n",
 		   obj->name, obj->size,
-		   atomic_read(&obj->handle_count),
+		   obj->handle_count,
 		   atomic_read(&obj->refcount.refcount));
 	return 0;
 }
@@ -218,7 +218,11 @@ int drm_gem_name_info(struct seq_file *m, void *data)
 	struct drm_device *dev = node->minor->dev;
 
 	seq_printf(m, "  name     size handles refcount\n");
+
+	mutex_lock(&dev->object_name_lock);
 	idr_for_each(&dev->object_name_idr, drm_gem_one_name_info, m);
+	mutex_unlock(&dev->object_name_lock);
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/drm_ioctl.c b/drivers/gpu/drm/drm_ioctl.c
index ffd7a7ba70d4..07247e2855a2 100644
--- a/drivers/gpu/drm/drm_ioctl.c
+++ b/drivers/gpu/drm/drm_ioctl.c
@@ -217,29 +217,30 @@ int drm_getclient(struct drm_device *dev, void *data,
 		  struct drm_file *file_priv)
 {
 	struct drm_client *client = data;
-	struct drm_file *pt;
-	int idx;
-	int i;
 
-	idx = client->idx;
-	i = 0;
-
-	mutex_lock(&dev->struct_mutex);
-	list_for_each_entry(pt, &dev->filelist, lhead) {
-		if (i++ >= idx) {
-			client->auth = pt->authenticated;
-			client->pid = pid_vnr(pt->pid);
-			client->uid = from_kuid_munged(current_user_ns(), pt->uid);
-			client->magic = pt->magic;
-			client->iocs = pt->ioctl_count;
-			mutex_unlock(&dev->struct_mutex);
-
-			return 0;
-		}
+	/*
+	 * Hollowed-out getclient ioctl to keep some dead old drm tests/tools
+	 * not breaking completely. Userspace tools stop enumerating one they
+	 * get -EINVAL, hence this is the return value we need to hand back for
+	 * no clients tracked.
+	 *
+	 * Unfortunately some clients (*cough* libva *cough*) use this in a fun
+	 * attempt to figure out whether they're authenticated or not. Since
+	 * that's the only thing they care about, give it to the directly
+	 * instead of walking one giant list.
+	 */
+	if (client->idx == 0) {
+		client->auth = file_priv->authenticated;
+		client->pid = pid_vnr(file_priv->pid);
+		client->uid = from_kuid_munged(current_user_ns(),
+					       file_priv->uid);
+		client->magic = 0;
+		client->iocs = 0;
+
+		return 0;
+	} else {
+		return -EINVAL;
 	}
-	mutex_unlock(&dev->struct_mutex);
-
-	return -EINVAL;
 }
 
 /**
@@ -256,21 +257,10 @@ int drm_getstats(struct drm_device *dev, void *data,
 		 struct drm_file *file_priv)
 {
 	struct drm_stats *stats = data;
-	int i;
 
+	/* Clear stats to prevent userspace from eating its stack garbage. */
 	memset(stats, 0, sizeof(*stats));
 
-	for (i = 0; i < dev->counters; i++) {
-		if (dev->types[i] == _DRM_STAT_LOCK)
-			stats->data[i].value =
-			    (file_priv->master->lock.hw_lock ? file_priv->master->lock.hw_lock->lock : 0);
-		else
-			stats->data[i].value = atomic_read(&dev->counts[i]);
-		stats->data[i].type = dev->types[i];
-	}
-
-	stats->count = dev->counters;
-
 	return 0;
 }
 
@@ -303,6 +293,9 @@ int drm_getcap(struct drm_device *dev, void *data, struct drm_file *file_priv)
 	case DRM_CAP_TIMESTAMP_MONOTONIC:
 		req->value = drm_timestamp_monotonic;
 		break;
+	case DRM_CAP_ASYNC_PAGE_FLIP:
+		req->value = dev->mode_config.async_page_flip;
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -352,9 +345,6 @@ int drm_setversion(struct drm_device *dev, void *data, struct drm_file *file_pri
 			retcode = -EINVAL;
 			goto done;
 		}
-
-		if (dev->driver->set_version)
-			dev->driver->set_version(dev, sv);
 	}
 
 done:
diff --git a/drivers/gpu/drm/drm_memory.c b/drivers/gpu/drm/drm_memory.c
index 126d50ea181f..64e44fad8ae8 100644
--- a/drivers/gpu/drm/drm_memory.c
+++ b/drivers/gpu/drm/drm_memory.c
@@ -86,7 +86,6 @@ void drm_free_agp(DRM_AGP_MEM * handle, int pages)
 {
 	agp_free_memory(handle);
 }
-EXPORT_SYMBOL(drm_free_agp);
 
 /** Wrapper around agp_bind_memory() */
 int drm_bind_agp(DRM_AGP_MEM * handle, unsigned int start)
@@ -99,7 +98,6 @@ int drm_unbind_agp(DRM_AGP_MEM * handle)
 {
 	return agp_unbind_memory(handle);
 }
-EXPORT_SYMBOL(drm_unbind_agp);
 
 #else  /*  __OS_HAS_AGP  */
 static inline void *agp_remap(unsigned long offset, unsigned long size,
diff --git a/drivers/gpu/drm/drm_mm.c b/drivers/gpu/drm/drm_mm.c
index 543b9b3171d3..af93cc55259f 100644
--- a/drivers/gpu/drm/drm_mm.c
+++ b/drivers/gpu/drm/drm_mm.c
@@ -49,58 +49,18 @@
 
 #define MM_UNUSED_TARGET 4
 
-static struct drm_mm_node *drm_mm_kmalloc(struct drm_mm *mm, int atomic)
-{
-	struct drm_mm_node *child;
-
-	if (atomic)
-		child = kzalloc(sizeof(*child), GFP_ATOMIC);
-	else
-		child = kzalloc(sizeof(*child), GFP_KERNEL);
-
-	if (unlikely(child == NULL)) {
-		spin_lock(&mm->unused_lock);
-		if (list_empty(&mm->unused_nodes))
-			child = NULL;
-		else {
-			child =
-			    list_entry(mm->unused_nodes.next,
-				       struct drm_mm_node, node_list);
-			list_del(&child->node_list);
-			--mm->num_unused;
-		}
-		spin_unlock(&mm->unused_lock);
-	}
-	return child;
-}
-
-/* drm_mm_pre_get() - pre allocate drm_mm_node structure
- * drm_mm:	memory manager struct we are pre-allocating for
- *
- * Returns 0 on success or -ENOMEM if allocation fails.
- */
-int drm_mm_pre_get(struct drm_mm *mm)
-{
-	struct drm_mm_node *node;
-
-	spin_lock(&mm->unused_lock);
-	while (mm->num_unused < MM_UNUSED_TARGET) {
-		spin_unlock(&mm->unused_lock);
-		node = kzalloc(sizeof(*node), GFP_KERNEL);
-		spin_lock(&mm->unused_lock);
-
-		if (unlikely(node == NULL)) {
-			int ret = (mm->num_unused < 2) ? -ENOMEM : 0;
-			spin_unlock(&mm->unused_lock);
-			return ret;
-		}
-		++mm->num_unused;
-		list_add_tail(&node->node_list, &mm->unused_nodes);
-	}
-	spin_unlock(&mm->unused_lock);
-	return 0;
-}
-EXPORT_SYMBOL(drm_mm_pre_get);
+static struct drm_mm_node *drm_mm_search_free_generic(const struct drm_mm *mm,
+						unsigned long size,
+						unsigned alignment,
+						unsigned long color,
+						enum drm_mm_search_flags flags);
+static struct drm_mm_node *drm_mm_search_free_in_range_generic(const struct drm_mm *mm,
+						unsigned long size,
+						unsigned alignment,
+						unsigned long color,
+						unsigned long start,
+						unsigned long end,
+						enum drm_mm_search_flags flags);
 
 static void drm_mm_insert_helper(struct drm_mm_node *hole_node,
 				 struct drm_mm_node *node,
@@ -147,33 +107,27 @@ static void drm_mm_insert_helper(struct drm_mm_node *hole_node,
 	}
 }
 
-struct drm_mm_node *drm_mm_create_block(struct drm_mm *mm,
-					unsigned long start,
-					unsigned long size,
-					bool atomic)
+int drm_mm_reserve_node(struct drm_mm *mm, struct drm_mm_node *node)
 {
-	struct drm_mm_node *hole, *node;
-	unsigned long end = start + size;
+	struct drm_mm_node *hole;
+	unsigned long end = node->start + node->size;
 	unsigned long hole_start;
 	unsigned long hole_end;
 
+	BUG_ON(node == NULL);
+
+	/* Find the relevant hole to add our node to */
 	drm_mm_for_each_hole(hole, mm, hole_start, hole_end) {
-		if (hole_start > start || hole_end < end)
+		if (hole_start > node->start || hole_end < end)
 			continue;
 
-		node = drm_mm_kmalloc(mm, atomic);
-		if (unlikely(node == NULL))
-			return NULL;
-
-		node->start = start;
-		node->size = size;
 		node->mm = mm;
 		node->allocated = 1;
 
 		INIT_LIST_HEAD(&node->hole_stack);
 		list_add(&node->node_list, &hole->node_list);
 
-		if (start == hole_start) {
+		if (node->start == hole_start) {
 			hole->hole_follows = 0;
 			list_del_init(&hole->hole_stack);
 		}
@@ -184,31 +138,14 @@ struct drm_mm_node *drm_mm_create_block(struct drm_mm *mm,
 			node->hole_follows = 1;
 		}
 
-		return node;
+		return 0;
 	}
 
-	WARN(1, "no hole found for block 0x%lx + 0x%lx\n", start, size);
-	return NULL;
-}
-EXPORT_SYMBOL(drm_mm_create_block);
-
-struct drm_mm_node *drm_mm_get_block_generic(struct drm_mm_node *hole_node,
-					     unsigned long size,
-					     unsigned alignment,
-					     unsigned long color,
-					     int atomic)
-{
-	struct drm_mm_node *node;
-
-	node = drm_mm_kmalloc(hole_node->mm, atomic);
-	if (unlikely(node == NULL))
-		return NULL;
-
-	drm_mm_insert_helper(hole_node, node, size, alignment, color);
-
-	return node;
+	WARN(1, "no hole found for node 0x%lx + 0x%lx\n",
+	     node->start, node->size);
+	return -ENOSPC;
 }
-EXPORT_SYMBOL(drm_mm_get_block_generic);
+EXPORT_SYMBOL(drm_mm_reserve_node);
 
 /**
  * Search for free space and insert a preallocated memory node. Returns
@@ -217,12 +154,13 @@ EXPORT_SYMBOL(drm_mm_get_block_generic);
  */
 int drm_mm_insert_node_generic(struct drm_mm *mm, struct drm_mm_node *node,
 			       unsigned long size, unsigned alignment,
-			       unsigned long color)
+			       unsigned long color,
+			       enum drm_mm_search_flags flags)
 {
 	struct drm_mm_node *hole_node;
 
 	hole_node = drm_mm_search_free_generic(mm, size, alignment,
-					       color, 0);
+					       color, flags);
 	if (!hole_node)
 		return -ENOSPC;
 
@@ -231,13 +169,6 @@ int drm_mm_insert_node_generic(struct drm_mm *mm, struct drm_mm_node *node,
 }
 EXPORT_SYMBOL(drm_mm_insert_node_generic);
 
-int drm_mm_insert_node(struct drm_mm *mm, struct drm_mm_node *node,
-		       unsigned long size, unsigned alignment)
-{
-	return drm_mm_insert_node_generic(mm, node, size, alignment, 0);
-}
-EXPORT_SYMBOL(drm_mm_insert_node);
-
 static void drm_mm_insert_helper_range(struct drm_mm_node *hole_node,
 				       struct drm_mm_node *node,
 				       unsigned long size, unsigned alignment,
@@ -290,27 +221,6 @@ static void drm_mm_insert_helper_range(struct drm_mm_node *hole_node,
 	}
 }
 
-struct drm_mm_node *drm_mm_get_block_range_generic(struct drm_mm_node *hole_node,
-						unsigned long size,
-						unsigned alignment,
-						unsigned long color,
-						unsigned long start,
-						unsigned long end,
-						int atomic)
-{
-	struct drm_mm_node *node;
-
-	node = drm_mm_kmalloc(hole_node->mm, atomic);
-	if (unlikely(node == NULL))
-		return NULL;
-
-	drm_mm_insert_helper_range(hole_node, node, size, alignment, color,
-				   start, end);
-
-	return node;
-}
-EXPORT_SYMBOL(drm_mm_get_block_range_generic);
-
 /**
  * Search for free space and insert a preallocated memory node. Returns
  * -ENOSPC if no suitable free area is available. This is for range
@@ -318,13 +228,14 @@ EXPORT_SYMBOL(drm_mm_get_block_range_generic);
  */
 int drm_mm_insert_node_in_range_generic(struct drm_mm *mm, struct drm_mm_node *node,
 					unsigned long size, unsigned alignment, unsigned long color,
-					unsigned long start, unsigned long end)
+					unsigned long start, unsigned long end,
+					enum drm_mm_search_flags flags)
 {
 	struct drm_mm_node *hole_node;
 
 	hole_node = drm_mm_search_free_in_range_generic(mm,
 							size, alignment, color,
-							start, end, 0);
+							start, end, flags);
 	if (!hole_node)
 		return -ENOSPC;
 
@@ -335,14 +246,6 @@ int drm_mm_insert_node_in_range_generic(struct drm_mm *mm, struct drm_mm_node *n
 }
 EXPORT_SYMBOL(drm_mm_insert_node_in_range_generic);
 
-int drm_mm_insert_node_in_range(struct drm_mm *mm, struct drm_mm_node *node,
-				unsigned long size, unsigned alignment,
-				unsigned long start, unsigned long end)
-{
-	return drm_mm_insert_node_in_range_generic(mm, node, size, alignment, 0, start, end);
-}
-EXPORT_SYMBOL(drm_mm_insert_node_in_range);
-
 /**
  * Remove a memory node from the allocator.
  */
@@ -351,6 +254,9 @@ void drm_mm_remove_node(struct drm_mm_node *node)
 	struct drm_mm *mm = node->mm;
 	struct drm_mm_node *prev_node;
 
+	if (WARN_ON(!node->allocated))
+		return;
+
 	BUG_ON(node->scanned_block || node->scanned_prev_free
 				   || node->scanned_next_free);
 
@@ -377,28 +283,6 @@ void drm_mm_remove_node(struct drm_mm_node *node)
 }
 EXPORT_SYMBOL(drm_mm_remove_node);
 
-/*
- * Remove a memory node from the allocator and free the allocated struct
- * drm_mm_node. Only to be used on a struct drm_mm_node obtained by one of the
- * drm_mm_get_block functions.
- */
-void drm_mm_put_block(struct drm_mm_node *node)
-{
-
-	struct drm_mm *mm = node->mm;
-
-	drm_mm_remove_node(node);
-
-	spin_lock(&mm->unused_lock);
-	if (mm->num_unused < MM_UNUSED_TARGET) {
-		list_add(&node->node_list, &mm->unused_nodes);
-		++mm->num_unused;
-	} else
-		kfree(node);
-	spin_unlock(&mm->unused_lock);
-}
-EXPORT_SYMBOL(drm_mm_put_block);
-
 static int check_free_hole(unsigned long start, unsigned long end,
 			   unsigned long size, unsigned alignment)
 {
@@ -414,11 +298,11 @@ static int check_free_hole(unsigned long start, unsigned long end,
 	return end >= start + size;
 }
 
-struct drm_mm_node *drm_mm_search_free_generic(const struct drm_mm *mm,
-					       unsigned long size,
-					       unsigned alignment,
-					       unsigned long color,
-					       bool best_match)
+static struct drm_mm_node *drm_mm_search_free_generic(const struct drm_mm *mm,
+						      unsigned long size,
+						      unsigned alignment,
+						      unsigned long color,
+						      enum drm_mm_search_flags flags)
 {
 	struct drm_mm_node *entry;
 	struct drm_mm_node *best;
@@ -441,7 +325,7 @@ struct drm_mm_node *drm_mm_search_free_generic(const struct drm_mm *mm,
 		if (!check_free_hole(adj_start, adj_end, size, alignment))
 			continue;
 
-		if (!best_match)
+		if (!(flags & DRM_MM_SEARCH_BEST))
 			return entry;
 
 		if (entry->size < best_size) {
@@ -452,15 +336,14 @@ struct drm_mm_node *drm_mm_search_free_generic(const struct drm_mm *mm,
 
 	return best;
 }
-EXPORT_SYMBOL(drm_mm_search_free_generic);
 
-struct drm_mm_node *drm_mm_search_free_in_range_generic(const struct drm_mm *mm,
+static struct drm_mm_node *drm_mm_search_free_in_range_generic(const struct drm_mm *mm,
 							unsigned long size,
 							unsigned alignment,
 							unsigned long color,
 							unsigned long start,
 							unsigned long end,
-							bool best_match)
+							enum drm_mm_search_flags flags)
 {
 	struct drm_mm_node *entry;
 	struct drm_mm_node *best;
@@ -488,7 +371,7 @@ struct drm_mm_node *drm_mm_search_free_in_range_generic(const struct drm_mm *mm,
 		if (!check_free_hole(adj_start, adj_end, size, alignment))
 			continue;
 
-		if (!best_match)
+		if (!(flags & DRM_MM_SEARCH_BEST))
 			return entry;
 
 		if (entry->size < best_size) {
@@ -499,7 +382,6 @@ struct drm_mm_node *drm_mm_search_free_in_range_generic(const struct drm_mm *mm,
 
 	return best;
 }
-EXPORT_SYMBOL(drm_mm_search_free_in_range_generic);
 
 /**
  * Moves an allocation. To be used with embedded struct drm_mm_node.
@@ -634,8 +516,8 @@ EXPORT_SYMBOL(drm_mm_scan_add_block);
  * corrupted.
  *
  * When the scan list is empty, the selected memory nodes can be freed. An
- * immediately following drm_mm_search_free with best_match = 0 will then return
- * the just freed block (because its at the top of the free_stack list).
+ * immediately following drm_mm_search_free with !DRM_MM_SEARCH_BEST will then
+ * return the just freed block (because its at the top of the free_stack list).
  *
  * Returns one if this block should be evicted, zero otherwise. Will always
  * return zero when no hole has been found.
@@ -672,10 +554,7 @@ EXPORT_SYMBOL(drm_mm_clean);
 void drm_mm_init(struct drm_mm * mm, unsigned long start, unsigned long size)
 {
 	INIT_LIST_HEAD(&mm->hole_stack);
-	INIT_LIST_HEAD(&mm->unused_nodes);
-	mm->num_unused = 0;
 	mm->scanned_blocks = 0;
-	spin_lock_init(&mm->unused_lock);
 
 	/* Clever trick to avoid a special case in the free hole tracking. */
 	INIT_LIST_HEAD(&mm->head_node.node_list);
@@ -695,22 +574,8 @@ EXPORT_SYMBOL(drm_mm_init);
 
 void drm_mm_takedown(struct drm_mm * mm)
 {
-	struct drm_mm_node *entry, *next;
-
-	if (WARN(!list_empty(&mm->head_node.node_list),
-		 "Memory manager not clean. Delaying takedown\n")) {
-		return;
-	}
-
-	spin_lock(&mm->unused_lock);
-	list_for_each_entry_safe(entry, next, &mm->unused_nodes, node_list) {
-		list_del(&entry->node_list);
-		kfree(entry);
-		--mm->num_unused;
-	}
-	spin_unlock(&mm->unused_lock);
-
-	BUG_ON(mm->num_unused != 0);
+	WARN(!list_empty(&mm->head_node.node_list),
+	     "Memory manager not clean during takedown.\n");
 }
 EXPORT_SYMBOL(drm_mm_takedown);
 
diff --git a/drivers/gpu/drm/drm_modes.c b/drivers/gpu/drm/drm_modes.c
index a6729bfe6860..fc2adb62b757 100644
--- a/drivers/gpu/drm/drm_modes.c
+++ b/drivers/gpu/drm/drm_modes.c
@@ -596,27 +596,6 @@ void drm_mode_set_name(struct drm_display_mode *mode)
 EXPORT_SYMBOL(drm_mode_set_name);
 
 /**
- * drm_mode_list_concat - move modes from one list to another
- * @head: source list
- * @new: dst list
- *
- * LOCKING:
- * Caller must ensure both lists are locked.
- *
- * Move all the modes from @head to @new.
- */
-void drm_mode_list_concat(struct list_head *head, struct list_head *new)
-{
-
-	struct list_head *entry, *tmp;
-
-	list_for_each_safe(entry, tmp, head) {
-		list_move_tail(entry, new);
-	}
-}
-EXPORT_SYMBOL(drm_mode_list_concat);
-
-/**
  * drm_mode_width - get the width of a mode
  * @mode: mode
  *
@@ -923,43 +902,6 @@ void drm_mode_validate_size(struct drm_device *dev,
 EXPORT_SYMBOL(drm_mode_validate_size);
 
 /**
- * drm_mode_validate_clocks - validate modes against clock limits
- * @dev: DRM device
- * @mode_list: list of modes to check
- * @min: minimum clock rate array
- * @max: maximum clock rate array
- * @n_ranges: number of clock ranges (size of arrays)
- *
- * LOCKING:
- * Caller must hold a lock protecting @mode_list.
- *
- * Some code may need to check a mode list against the clock limits of the
- * device in question.  This function walks the mode list, testing to make
- * sure each mode falls within a given range (defined by @min and @max
- * arrays) and sets @mode->status as needed.
- */
-void drm_mode_validate_clocks(struct drm_device *dev,
-			      struct list_head *mode_list,
-			      int *min, int *max, int n_ranges)
-{
-	struct drm_display_mode *mode;
-	int i;
-
-	list_for_each_entry(mode, mode_list, head) {
-		bool good = false;
-		for (i = 0; i < n_ranges; i++) {
-			if (mode->clock >= min[i] && mode->clock <= max[i]) {
-				good = true;
-				break;
-			}
-		}
-		if (!good)
-			mode->status = MODE_CLOCK_RANGE;
-	}
-}
-EXPORT_SYMBOL(drm_mode_validate_clocks);
-
-/**
  * drm_mode_prune_invalid - remove invalid modes from mode list
  * @dev: DRM device
  * @mode_list: list of modes to check
diff --git a/drivers/gpu/drm/drm_pci.c b/drivers/gpu/drm/drm_pci.c
index 80c0b2b29801..1f96cee6eee8 100644
--- a/drivers/gpu/drm/drm_pci.c
+++ b/drivers/gpu/drm/drm_pci.c
@@ -52,10 +52,8 @@
 drm_dma_handle_t *drm_pci_alloc(struct drm_device * dev, size_t size, size_t align)
 {
 	drm_dma_handle_t *dmah;
-#if 1
 	unsigned long addr;
 	size_t sz;
-#endif
 
 	/* pci_alloc_consistent only guarantees alignment to the smallest
 	 * PAGE_SIZE order which is greater than or equal to the requested size.
@@ -97,10 +95,8 @@ EXPORT_SYMBOL(drm_pci_alloc);
  */
 void __drm_pci_free(struct drm_device * dev, drm_dma_handle_t * dmah)
 {
-#if 1
 	unsigned long addr;
 	size_t sz;
-#endif
 
 	if (dmah->vaddr) {
 		/* XXX - Is virt_to_page() legal for consistent mem? */
@@ -276,17 +272,26 @@ static int drm_pci_agp_init(struct drm_device *dev)
 			DRM_ERROR("Cannot initialize the agpgart module.\n");
 			return -EINVAL;
 		}
-		if (drm_core_has_MTRR(dev)) {
-			if (dev->agp)
-				dev->agp->agp_mtrr = arch_phys_wc_add(
-					dev->agp->agp_info.aper_base,
-					dev->agp->agp_info.aper_size *
-					1024 * 1024);
+		if (dev->agp) {
+			dev->agp->agp_mtrr = arch_phys_wc_add(
+				dev->agp->agp_info.aper_base,
+				dev->agp->agp_info.aper_size *
+				1024 * 1024);
 		}
 	}
 	return 0;
 }
 
+static void drm_pci_agp_destroy(struct drm_device *dev)
+{
+	if (drm_core_has_AGP(dev) && dev->agp) {
+		arch_phys_wc_del(dev->agp->agp_mtrr);
+		drm_agp_clear(dev);
+		drm_agp_destroy(dev->agp);
+		dev->agp = NULL;
+	}
+}
+
 static struct drm_bus drm_pci_bus = {
 	.bus_type = DRIVER_BUS_PCI,
 	.get_irq = drm_pci_get_irq,
@@ -295,6 +300,7 @@ static struct drm_bus drm_pci_bus = {
 	.set_unique = drm_pci_set_unique,
 	.irq_by_busid = drm_pci_irq_by_busid,
 	.agp_init = drm_pci_agp_init,
+	.agp_destroy = drm_pci_agp_destroy,
 };
 
 /**
@@ -348,6 +354,12 @@ int drm_get_pci_dev(struct pci_dev *pdev, const struct pci_device_id *ent,
 			goto err_g2;
 	}
 
+	if (drm_core_check_feature(dev, DRIVER_RENDER) && drm_rnodes) {
+		ret = drm_get_minor(dev, &dev->render, DRM_MINOR_RENDER);
+		if (ret)
+			goto err_g21;
+	}
+
 	if ((ret = drm_get_minor(dev, &dev->primary, DRM_MINOR_LEGACY)))
 		goto err_g3;
 
@@ -377,6 +389,9 @@ int drm_get_pci_dev(struct pci_dev *pdev, const struct pci_device_id *ent,
 err_g4:
 	drm_put_minor(&dev->primary);
 err_g3:
+	if (dev->render)
+		drm_put_minor(&dev->render);
+err_g21:
 	if (drm_core_check_feature(dev, DRIVER_MODESET))
 		drm_put_minor(&dev->control);
 err_g2:
diff --git a/drivers/gpu/drm/drm_platform.c b/drivers/gpu/drm/drm_platform.c
index b8a282ea8751..f7a18c6ba4c4 100644
--- a/drivers/gpu/drm/drm_platform.c
+++ b/drivers/gpu/drm/drm_platform.c
@@ -28,7 +28,7 @@
 #include <linux/export.h>
 #include <drm/drmP.h>
 
-/**
+/*
  * Register.
  *
  * \param platdev - Platform device struture
@@ -39,8 +39,8 @@
  * Try and register, if we fail to register, backout previous work.
  */
 
-int drm_get_platform_dev(struct platform_device *platdev,
-			 struct drm_driver *driver)
+static int drm_get_platform_dev(struct platform_device *platdev,
+				struct drm_driver *driver)
 {
 	struct drm_device *dev;
 	int ret;
@@ -69,6 +69,12 @@ int drm_get_platform_dev(struct platform_device *platdev,
 			goto err_g1;
 	}
 
+	if (drm_core_check_feature(dev, DRIVER_RENDER) && drm_rnodes) {
+		ret = drm_get_minor(dev, &dev->render, DRM_MINOR_RENDER);
+		if (ret)
+			goto err_g11;
+	}
+
 	ret = drm_get_minor(dev, &dev->primary, DRM_MINOR_LEGACY);
 	if (ret)
 		goto err_g2;
@@ -100,6 +106,9 @@ int drm_get_platform_dev(struct platform_device *platdev,
 err_g3:
 	drm_put_minor(&dev->primary);
 err_g2:
+	if (dev->render)
+		drm_put_minor(&dev->render);
+err_g11:
 	if (drm_core_check_feature(dev, DRIVER_MODESET))
 		drm_put_minor(&dev->control);
 err_g1:
@@ -107,7 +116,6 @@ err_g1:
 	mutex_unlock(&drm_global_mutex);
 	return ret;
 }
-EXPORT_SYMBOL(drm_get_platform_dev);
 
 static int drm_platform_get_irq(struct drm_device *dev)
 {
diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c
index 85e450e3241c..276d470f7b3e 100644
--- a/drivers/gpu/drm/drm_prime.c
+++ b/drivers/gpu/drm/drm_prime.c
@@ -83,6 +83,34 @@ static int drm_prime_add_buf_handle(struct drm_prime_file_private *prime_fpriv,
 	return 0;
 }
 
+static struct dma_buf *drm_prime_lookup_buf_by_handle(struct drm_prime_file_private *prime_fpriv,
+						      uint32_t handle)
+{
+	struct drm_prime_member *member;
+
+	list_for_each_entry(member, &prime_fpriv->head, entry) {
+		if (member->handle == handle)
+			return member->dma_buf;
+	}
+
+	return NULL;
+}
+
+static int drm_prime_lookup_buf_handle(struct drm_prime_file_private *prime_fpriv,
+				       struct dma_buf *dma_buf,
+				       uint32_t *handle)
+{
+	struct drm_prime_member *member;
+
+	list_for_each_entry(member, &prime_fpriv->head, entry) {
+		if (member->dma_buf == dma_buf) {
+			*handle = member->handle;
+			return 0;
+		}
+	}
+	return -ENOENT;
+}
+
 static int drm_gem_map_attach(struct dma_buf *dma_buf,
 			      struct device *target_dev,
 			      struct dma_buf_attachment *attach)
@@ -131,9 +159,8 @@ static void drm_gem_map_detach(struct dma_buf *dma_buf,
 	attach->priv = NULL;
 }
 
-static void drm_prime_remove_buf_handle_locked(
-		struct drm_prime_file_private *prime_fpriv,
-		struct dma_buf *dma_buf)
+void drm_prime_remove_buf_handle_locked(struct drm_prime_file_private *prime_fpriv,
+					struct dma_buf *dma_buf)
 {
 	struct drm_prime_member *member, *safe;
 
@@ -167,8 +194,6 @@ static struct sg_table *drm_gem_map_dma_buf(struct dma_buf_attachment *attach,
 	if (WARN_ON(prime_attach->dir != DMA_NONE))
 		return ERR_PTR(-EBUSY);
 
-	mutex_lock(&obj->dev->struct_mutex);
-
 	sgt = obj->dev->driver->gem_prime_get_sg_table(obj);
 
 	if (!IS_ERR(sgt)) {
@@ -182,7 +207,6 @@ static struct sg_table *drm_gem_map_dma_buf(struct dma_buf_attachment *attach,
 		}
 	}
 
-	mutex_unlock(&obj->dev->struct_mutex);
 	return sgt;
 }
 
@@ -192,16 +216,14 @@ static void drm_gem_unmap_dma_buf(struct dma_buf_attachment *attach,
 	/* nothing to be done here */
 }
 
-static void drm_gem_dmabuf_release(struct dma_buf *dma_buf)
+void drm_gem_dmabuf_release(struct dma_buf *dma_buf)
 {
 	struct drm_gem_object *obj = dma_buf->priv;
 
-	if (obj->export_dma_buf == dma_buf) {
-		/* drop the reference on the export fd holds */
-		obj->export_dma_buf = NULL;
-		drm_gem_object_unreference_unlocked(obj);
-	}
+	/* drop the reference on the export fd holds */
+	drm_gem_object_unreference_unlocked(obj);
 }
+EXPORT_SYMBOL(drm_gem_dmabuf_release);
 
 static void *drm_gem_dmabuf_vmap(struct dma_buf *dma_buf)
 {
@@ -300,62 +322,107 @@ struct dma_buf *drm_gem_prime_export(struct drm_device *dev,
 }
 EXPORT_SYMBOL(drm_gem_prime_export);
 
+static struct dma_buf *export_and_register_object(struct drm_device *dev,
+						  struct drm_gem_object *obj,
+						  uint32_t flags)
+{
+	struct dma_buf *dmabuf;
+
+	/* prevent races with concurrent gem_close. */
+	if (obj->handle_count == 0) {
+		dmabuf = ERR_PTR(-ENOENT);
+		return dmabuf;
+	}
+
+	dmabuf = dev->driver->gem_prime_export(dev, obj, flags);
+	if (IS_ERR(dmabuf)) {
+		/* normally the created dma-buf takes ownership of the ref,
+		 * but if that fails then drop the ref
+		 */
+		return dmabuf;
+	}
+
+	/*
+	 * Note that callers do not need to clean up the export cache
+	 * since the check for obj->handle_count guarantees that someone
+	 * will clean it up.
+	 */
+	obj->dma_buf = dmabuf;
+	get_dma_buf(obj->dma_buf);
+	/* Grab a new ref since the callers is now used by the dma-buf */
+	drm_gem_object_reference(obj);
+
+	return dmabuf;
+}
+
 int drm_gem_prime_handle_to_fd(struct drm_device *dev,
 		struct drm_file *file_priv, uint32_t handle, uint32_t flags,
 		int *prime_fd)
 {
 	struct drm_gem_object *obj;
-	void *buf;
 	int ret = 0;
 	struct dma_buf *dmabuf;
 
+	mutex_lock(&file_priv->prime.lock);
 	obj = drm_gem_object_lookup(dev, file_priv, handle);
-	if (!obj)
-		return -ENOENT;
+	if (!obj)  {
+		ret = -ENOENT;
+		goto out_unlock;
+	}
 
-	mutex_lock(&file_priv->prime.lock);
+	dmabuf = drm_prime_lookup_buf_by_handle(&file_priv->prime, handle);
+	if (dmabuf) {
+		get_dma_buf(dmabuf);
+		goto out_have_handle;
+	}
+
+	mutex_lock(&dev->object_name_lock);
 	/* re-export the original imported object */
 	if (obj->import_attach) {
 		dmabuf = obj->import_attach->dmabuf;
+		get_dma_buf(dmabuf);
 		goto out_have_obj;
 	}
 
-	if (obj->export_dma_buf) {
-		dmabuf = obj->export_dma_buf;
+	if (obj->dma_buf) {
+		get_dma_buf(obj->dma_buf);
+		dmabuf = obj->dma_buf;
 		goto out_have_obj;
 	}
 
-	buf = dev->driver->gem_prime_export(dev, obj, flags);
-	if (IS_ERR(buf)) {
+	dmabuf = export_and_register_object(dev, obj, flags);
+	if (IS_ERR(dmabuf)) {
 		/* normally the created dma-buf takes ownership of the ref,
 		 * but if that fails then drop the ref
 		 */
-		ret = PTR_ERR(buf);
+		ret = PTR_ERR(dmabuf);
+		mutex_unlock(&dev->object_name_lock);
 		goto out;
 	}
-	obj->export_dma_buf = buf;
 
-	/* if we've exported this buffer the cheat and add it to the import list
-	 * so we get the correct handle back
+out_have_obj:
+	/*
+	 * If we've exported this buffer then cheat and add it to the import list
+	 * so we get the correct handle back. We must do this under the
+	 * protection of dev->object_name_lock to ensure that a racing gem close
+	 * ioctl doesn't miss to remove this buffer handle from the cache.
 	 */
 	ret = drm_prime_add_buf_handle(&file_priv->prime,
-				       obj->export_dma_buf, handle);
+				       dmabuf, handle);
+	mutex_unlock(&dev->object_name_lock);
 	if (ret)
 		goto fail_put_dmabuf;
 
-	ret = dma_buf_fd(buf, flags);
-	if (ret < 0)
-		goto fail_rm_handle;
-
-	*prime_fd = ret;
-	mutex_unlock(&file_priv->prime.lock);
-	return 0;
-
-out_have_obj:
-	get_dma_buf(dmabuf);
+out_have_handle:
 	ret = dma_buf_fd(dmabuf, flags);
+	/*
+	 * We must _not_ remove the buffer from the handle cache since the newly
+	 * created dma buf is already linked in the global obj->dma_buf pointer,
+	 * and that is invariant as long as a userspace gem handle exists.
+	 * Closing the handle will clean out the cache anyway, so we don't leak.
+	 */
 	if (ret < 0) {
-		dma_buf_put(dmabuf);
+		goto fail_put_dmabuf;
 	} else {
 		*prime_fd = ret;
 		ret = 0;
@@ -363,15 +430,13 @@ out_have_obj:
 
 	goto out;
 
-fail_rm_handle:
-	drm_prime_remove_buf_handle_locked(&file_priv->prime, buf);
 fail_put_dmabuf:
-	/* clear NOT to be checked when releasing dma_buf */
-	obj->export_dma_buf = NULL;
-	dma_buf_put(buf);
+	dma_buf_put(dmabuf);
 out:
 	drm_gem_object_unreference_unlocked(obj);
+out_unlock:
 	mutex_unlock(&file_priv->prime.lock);
+
 	return ret;
 }
 EXPORT_SYMBOL(drm_gem_prime_handle_to_fd);
@@ -446,19 +511,26 @@ int drm_gem_prime_fd_to_handle(struct drm_device *dev,
 
 	ret = drm_prime_lookup_buf_handle(&file_priv->prime,
 			dma_buf, handle);
-	if (!ret) {
-		ret = 0;
+	if (ret == 0)
 		goto out_put;
-	}
 
 	/* never seen this one, need to import */
+	mutex_lock(&dev->object_name_lock);
 	obj = dev->driver->gem_prime_import(dev, dma_buf);
 	if (IS_ERR(obj)) {
 		ret = PTR_ERR(obj);
-		goto out_put;
+		goto out_unlock;
 	}
 
-	ret = drm_gem_handle_create(file_priv, obj, handle);
+	if (obj->dma_buf) {
+		WARN_ON(obj->dma_buf != dma_buf);
+	} else {
+		obj->dma_buf = dma_buf;
+		get_dma_buf(dma_buf);
+	}
+
+	/* drm_gem_handle_create_tail unlocks dev->object_name_lock. */
+	ret = drm_gem_handle_create_tail(file_priv, obj, handle);
 	drm_gem_object_unreference_unlocked(obj);
 	if (ret)
 		goto out_put;
@@ -478,7 +550,9 @@ fail:
 	/* hmm, if driver attached, we are relying on the free-object path
 	 * to detach.. which seems ok..
 	 */
-	drm_gem_object_handle_unreference_unlocked(obj);
+	drm_gem_handle_delete(file_priv, *handle);
+out_unlock:
+	mutex_unlock(&dev->object_name_lock);
 out_put:
 	dma_buf_put(dma_buf);
 	mutex_unlock(&file_priv->prime.lock);
@@ -618,25 +692,3 @@ void drm_prime_destroy_file_private(struct drm_prime_file_private *prime_fpriv)
 	WARN_ON(!list_empty(&prime_fpriv->head));
 }
 EXPORT_SYMBOL(drm_prime_destroy_file_private);
-
-int drm_prime_lookup_buf_handle(struct drm_prime_file_private *prime_fpriv, struct dma_buf *dma_buf, uint32_t *handle)
-{
-	struct drm_prime_member *member;
-
-	list_for_each_entry(member, &prime_fpriv->head, entry) {
-		if (member->dma_buf == dma_buf) {
-			*handle = member->handle;
-			return 0;
-		}
-	}
-	return -ENOENT;
-}
-EXPORT_SYMBOL(drm_prime_lookup_buf_handle);
-
-void drm_prime_remove_buf_handle(struct drm_prime_file_private *prime_fpriv, struct dma_buf *dma_buf)
-{
-	mutex_lock(&prime_fpriv->lock);
-	drm_prime_remove_buf_handle_locked(prime_fpriv, dma_buf);
-	mutex_unlock(&prime_fpriv->lock);
-}
-EXPORT_SYMBOL(drm_prime_remove_buf_handle);
diff --git a/drivers/gpu/drm/drm_proc.c b/drivers/gpu/drm/drm_proc.c
deleted file mode 100644
index d7f2324b4fb1..000000000000
--- a/drivers/gpu/drm/drm_proc.c
+++ /dev/null
@@ -1,209 +0,0 @@
-/**
- * \file drm_proc.c
- * /proc support for DRM
- *
- * \author Rickard E. (Rik) Faith <faith@valinux.com>
- * \author Gareth Hughes <gareth@valinux.com>
- *
- * \par Acknowledgements:
- *    Matthew J Sottek <matthew.j.sottek@intel.com> sent in a patch to fix
- *    the problem with the proc files not outputting all their information.
- */
-
-/*
- * Created: Mon Jan 11 09:48:47 1999 by faith@valinux.com
- *
- * Copyright 1999 Precision Insight, Inc., Cedar Park, Texas.
- * Copyright 2000 VA Linux Systems, Inc., Sunnyvale, California.
- * All Rights Reserved.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice (including the next
- * paragraph) shall be included in all copies or substantial portions of the
- * Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * VA LINUX SYSTEMS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM, DAMAGES OR
- * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
- * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
- * OTHER DEALINGS IN THE SOFTWARE.
- */
-
-#include <linux/seq_file.h>
-#include <linux/slab.h>
-#include <linux/export.h>
-#include <drm/drmP.h>
-
-/***************************************************
- * Initialization, etc.
- **************************************************/
-
-/**
- * Proc file list.
- */
-static const struct drm_info_list drm_proc_list[] = {
-	{"name", drm_name_info, 0},
-	{"vm", drm_vm_info, 0},
-	{"clients", drm_clients_info, 0},
-	{"bufs", drm_bufs_info, 0},
-	{"gem_names", drm_gem_name_info, DRIVER_GEM},
-#if DRM_DEBUG_CODE
-	{"vma", drm_vma_info, 0},
-#endif
-};
-#define DRM_PROC_ENTRIES ARRAY_SIZE(drm_proc_list)
-
-static int drm_proc_open(struct inode *inode, struct file *file)
-{
-	struct drm_info_node* node = PDE_DATA(inode);
-
-	return single_open(file, node->info_ent->show, node);
-}
-
-static const struct file_operations drm_proc_fops = {
-	.owner = THIS_MODULE,
-	.open = drm_proc_open,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.release = single_release,
-};
-
-
-/**
- * Initialize a given set of proc files for a device
- *
- * \param files The array of files to create
- * \param count The number of files given
- * \param root DRI proc dir entry.
- * \param minor device minor number
- * \return Zero on success, non-zero on failure
- *
- * Create a given set of proc files represented by an array of
- * gdm_proc_lists in the given root directory.
- */
-static int drm_proc_create_files(const struct drm_info_list *files, int count,
-			  struct proc_dir_entry *root, struct drm_minor *minor)
-{
-	struct drm_device *dev = minor->dev;
-	struct proc_dir_entry *ent;
-	struct drm_info_node *tmp;
-	int i;
-
-	for (i = 0; i < count; i++) {
-		u32 features = files[i].driver_features;
-
-		if (features != 0 &&
-		    (dev->driver->driver_features & features) != features)
-			continue;
-
-		tmp = kmalloc(sizeof(struct drm_info_node), GFP_KERNEL);
-		if (!tmp)
-			return -1;
-
-		tmp->minor = minor;
-		tmp->info_ent = &files[i];
-		list_add(&tmp->list, &minor->proc_nodes.list);
-
-		ent = proc_create_data(files[i].name, S_IRUGO, root,
-				       &drm_proc_fops, tmp);
-		if (!ent) {
-			DRM_ERROR("Cannot create /proc/dri/%u/%s\n",
-				  minor->index, files[i].name);
-			list_del(&tmp->list);
-			kfree(tmp);
-			return -1;
-		}
-	}
-	return 0;
-}
-
-/**
- * Initialize the DRI proc filesystem for a device
- *
- * \param dev DRM device
- * \param root DRI proc dir entry.
- * \param dev_root resulting DRI device proc dir entry.
- * \return root entry pointer on success, or NULL on failure.
- *
- * Create the DRI proc root entry "/proc/dri", the device proc root entry
- * "/proc/dri/%minor%/", and each entry in proc_list as
- * "/proc/dri/%minor%/%name%".
- */
-int drm_proc_init(struct drm_minor *minor, struct proc_dir_entry *root)
-{
-	char name[12];
-	int ret;
-
-	INIT_LIST_HEAD(&minor->proc_nodes.list);
-	sprintf(name, "%u", minor->index);
-	minor->proc_root = proc_mkdir(name, root);
-	if (!minor->proc_root) {
-		DRM_ERROR("Cannot create /proc/dri/%s\n", name);
-		return -1;
-	}
-
-	ret = drm_proc_create_files(drm_proc_list, DRM_PROC_ENTRIES,
-				    minor->proc_root, minor);
-	if (ret) {
-		remove_proc_subtree(name, root);
-		minor->proc_root = NULL;
-		DRM_ERROR("Failed to create core drm proc files\n");
-		return ret;
-	}
-
-	return 0;
-}
-
-static int drm_proc_remove_files(const struct drm_info_list *files, int count,
-			  struct drm_minor *minor)
-{
-	struct list_head *pos, *q;
-	struct drm_info_node *tmp;
-	int i;
-
-	for (i = 0; i < count; i++) {
-		list_for_each_safe(pos, q, &minor->proc_nodes.list) {
-			tmp = list_entry(pos, struct drm_info_node, list);
-			if (tmp->info_ent == &files[i]) {
-				remove_proc_entry(files[i].name,
-						  minor->proc_root);
-				list_del(pos);
-				kfree(tmp);
-			}
-		}
-	}
-	return 0;
-}
-
-/**
- * Cleanup the proc filesystem resources.
- *
- * \param minor device minor number.
- * \param root DRI proc dir entry.
- * \param dev_root DRI device proc dir entry.
- * \return always zero.
- *
- * Remove all proc entries created by proc_init().
- */
-int drm_proc_cleanup(struct drm_minor *minor, struct proc_dir_entry *root)
-{
-	char name[64];
-
-	if (!root || !minor->proc_root)
-		return 0;
-
-	drm_proc_remove_files(drm_proc_list, DRM_PROC_ENTRIES, minor);
-
-	sprintf(name, "%d", minor->index);
-	remove_proc_subtree(name, root);
-	return 0;
-}
-
diff --git a/drivers/gpu/drm/drm_scatter.c b/drivers/gpu/drm/drm_scatter.c
index d87f60bbc330..1c78406f6e71 100644
--- a/drivers/gpu/drm/drm_scatter.c
+++ b/drivers/gpu/drm/drm_scatter.c
@@ -46,7 +46,7 @@ static inline void *drm_vmalloc_dma(unsigned long size)
 #endif
 }
 
-void drm_sg_cleanup(struct drm_sg_mem * entry)
+static void drm_sg_cleanup(struct drm_sg_mem * entry)
 {
 	struct page *page;
 	int i;
@@ -64,19 +64,32 @@ void drm_sg_cleanup(struct drm_sg_mem * entry)
 	kfree(entry);
 }
 
+void drm_legacy_sg_cleanup(struct drm_device *dev)
+{
+	if (drm_core_check_feature(dev, DRIVER_SG) && dev->sg &&
+	    !drm_core_check_feature(dev, DRIVER_MODESET)) {
+		drm_sg_cleanup(dev->sg);
+		dev->sg = NULL;
+	}
+}
 #ifdef _LP64
 # define ScatterHandle(x) (unsigned int)((x >> 32) + (x & ((1L << 32) - 1)))
 #else
 # define ScatterHandle(x) (unsigned int)(x)
 #endif
 
-int drm_sg_alloc(struct drm_device *dev, struct drm_scatter_gather * request)
+int drm_sg_alloc(struct drm_device *dev, void *data,
+		 struct drm_file *file_priv)
 {
+	struct drm_scatter_gather *request = data;
 	struct drm_sg_mem *entry;
 	unsigned long pages, i, j;
 
 	DRM_DEBUG("\n");
 
+	if (drm_core_check_feature(dev, DRIVER_MODESET))
+		return -EINVAL;
+
 	if (!drm_core_check_feature(dev, DRIVER_SG))
 		return -EINVAL;
 
@@ -181,21 +194,15 @@ int drm_sg_alloc(struct drm_device *dev, struct drm_scatter_gather * request)
 	return -ENOMEM;
 }
 
-int drm_sg_alloc_ioctl(struct drm_device *dev, void *data,
-		       struct drm_file *file_priv)
-{
-	struct drm_scatter_gather *request = data;
-
-	return drm_sg_alloc(dev, request);
-
-}
-
 int drm_sg_free(struct drm_device *dev, void *data,
 		struct drm_file *file_priv)
 {
 	struct drm_scatter_gather *request = data;
 	struct drm_sg_mem *entry;
 
+	if (drm_core_check_feature(dev, DRIVER_MODESET))
+		return -EINVAL;
+
 	if (!drm_core_check_feature(dev, DRIVER_SG))
 		return -EINVAL;
 
diff --git a/drivers/gpu/drm/drm_stub.c b/drivers/gpu/drm/drm_stub.c
index 327ca19cda85..39d864576be4 100644
--- a/drivers/gpu/drm/drm_stub.c
+++ b/drivers/gpu/drm/drm_stub.c
@@ -40,6 +40,9 @@
 unsigned int drm_debug = 0;	/* 1 to enable debug output */
 EXPORT_SYMBOL(drm_debug);
 
+unsigned int drm_rnodes = 0;	/* 1 to enable experimental render nodes API */
+EXPORT_SYMBOL(drm_rnodes);
+
 unsigned int drm_vblank_offdelay = 5000;    /* Default to 5000 msecs. */
 EXPORT_SYMBOL(drm_vblank_offdelay);
 
@@ -56,11 +59,13 @@ MODULE_AUTHOR(CORE_AUTHOR);
 MODULE_DESCRIPTION(CORE_DESC);
 MODULE_LICENSE("GPL and additional rights");
 MODULE_PARM_DESC(debug, "Enable debug output");
+MODULE_PARM_DESC(rnodes, "Enable experimental render nodes API");
 MODULE_PARM_DESC(vblankoffdelay, "Delay until vblank irq auto-disable [msecs]");
 MODULE_PARM_DESC(timestamp_precision_usec, "Max. error on timestamps [usecs]");
 MODULE_PARM_DESC(timestamp_monotonic, "Use monotonic timestamps");
 
 module_param_named(debug, drm_debug, int, 0600);
+module_param_named(rnodes, drm_rnodes, int, 0600);
 module_param_named(vblankoffdelay, drm_vblank_offdelay, int, 0600);
 module_param_named(timestamp_precision_usec, drm_timestamp_precision, int, 0600);
 module_param_named(timestamp_monotonic, drm_timestamp_monotonic, int, 0600);
@@ -68,7 +73,6 @@ module_param_named(timestamp_monotonic, drm_timestamp_monotonic, int, 0600);
 struct idr drm_minors_idr;
 
 struct class *drm_class;
-struct proc_dir_entry *drm_proc_root;
 struct dentry *drm_debugfs_root;
 
 int drm_err(const char *func, const char *format, ...)
@@ -113,12 +117,12 @@ static int drm_minor_get_id(struct drm_device *dev, int type)
 	int base = 0, limit = 63;
 
 	if (type == DRM_MINOR_CONTROL) {
-                base += 64;
-                limit = base + 127;
-        } else if (type == DRM_MINOR_RENDER) {
-                base += 128;
-                limit = base + 255;
-        }
+		base += 64;
+		limit = base + 63;
+	} else if (type == DRM_MINOR_RENDER) {
+		base += 128;
+		limit = base + 63;
+	}
 
 	mutex_lock(&dev->struct_mutex);
 	ret = idr_alloc(&drm_minors_idr, NULL, base, limit, GFP_KERNEL);
@@ -321,9 +325,8 @@ EXPORT_SYMBOL(drm_fill_in_dev);
  * \param sec-minor structure to hold the assigned minor
  * \return negative number on failure.
  *
- * Search an empty entry and initialize it to the given parameters, and
- * create the proc init entry via proc_init(). This routines assigns
- * minor numbers to secondary heads of multi-headed cards
+ * Search an empty entry and initialize it to the given parameters. This
+ * routines assigns minor numbers to secondary heads of multi-headed cards
  */
 int drm_get_minor(struct drm_device *dev, struct drm_minor **minor, int type)
 {
@@ -351,20 +354,11 @@ int drm_get_minor(struct drm_device *dev, struct drm_minor **minor, int type)
 
 	idr_replace(&drm_minors_idr, new_minor, minor_id);
 
-	if (type == DRM_MINOR_LEGACY) {
-		ret = drm_proc_init(new_minor, drm_proc_root);
-		if (ret) {
-			DRM_ERROR("DRM: Failed to initialize /proc/dri.\n");
-			goto err_mem;
-		}
-	} else
-		new_minor->proc_root = NULL;
-
 #if defined(CONFIG_DEBUG_FS)
 	ret = drm_debugfs_init(new_minor, minor_id, drm_debugfs_root);
 	if (ret) {
 		DRM_ERROR("DRM: Failed to initialize /sys/kernel/debug/dri.\n");
-		goto err_g2;
+		goto err_mem;
 	}
 #endif
 
@@ -372,7 +366,7 @@ int drm_get_minor(struct drm_device *dev, struct drm_minor **minor, int type)
 	if (ret) {
 		printk(KERN_ERR
 		       "DRM: Error sysfs_device_add.\n");
-		goto err_g2;
+		goto err_debugfs;
 	}
 	*minor = new_minor;
 
@@ -380,10 +374,11 @@ int drm_get_minor(struct drm_device *dev, struct drm_minor **minor, int type)
 	return 0;
 
 
-err_g2:
-	if (new_minor->type == DRM_MINOR_LEGACY)
-		drm_proc_cleanup(new_minor, drm_proc_root);
+err_debugfs:
+#if defined(CONFIG_DEBUG_FS)
+	drm_debugfs_cleanup(new_minor);
 err_mem:
+#endif
 	kfree(new_minor);
 err_idr:
 	idr_remove(&drm_minors_idr, minor_id);
@@ -397,10 +392,6 @@ EXPORT_SYMBOL(drm_get_minor);
  *
  * \param sec_minor - structure to be released
  * \return always zero
- *
- * Cleans up the proc resources. Not legal for this to be the
- * last minor released.
- *
  */
 int drm_put_minor(struct drm_minor **minor_p)
 {
@@ -408,8 +399,6 @@ int drm_put_minor(struct drm_minor **minor_p)
 
 	DRM_DEBUG("release secondary minor %d\n", minor->index);
 
-	if (minor->type == DRM_MINOR_LEGACY)
-		drm_proc_cleanup(minor, drm_proc_root);
 #if defined(CONFIG_DEBUG_FS)
 	drm_debugfs_cleanup(minor);
 #endif
@@ -451,16 +440,11 @@ void drm_put_dev(struct drm_device *dev)
 
 	drm_lastclose(dev);
 
-	if (drm_core_has_MTRR(dev) && drm_core_has_AGP(dev) && dev->agp)
-		arch_phys_wc_del(dev->agp->agp_mtrr);
-
 	if (dev->driver->unload)
 		dev->driver->unload(dev);
 
-	if (drm_core_has_AGP(dev) && dev->agp) {
-		kfree(dev->agp);
-		dev->agp = NULL;
-	}
+	if (dev->driver->bus->agp_destroy)
+		dev->driver->bus->agp_destroy(dev);
 
 	drm_vblank_cleanup(dev);
 
@@ -473,6 +457,9 @@ void drm_put_dev(struct drm_device *dev)
 	if (drm_core_check_feature(dev, DRIVER_MODESET))
 		drm_put_minor(&dev->control);
 
+	if (dev->render)
+		drm_put_minor(&dev->render);
+
 	if (driver->driver_features & DRIVER_GEM)
 		drm_gem_destroy(dev);
 
@@ -489,6 +476,8 @@ void drm_unplug_dev(struct drm_device *dev)
 	/* for a USB device */
 	if (drm_core_check_feature(dev, DRIVER_MODESET))
 		drm_unplug_minor(dev->control);
+	if (dev->render)
+		drm_unplug_minor(dev->render);
 	drm_unplug_minor(dev->primary);
 
 	mutex_lock(&drm_global_mutex);
diff --git a/drivers/gpu/drm/drm_usb.c b/drivers/gpu/drm/drm_usb.c
index 34a156f0c336..87664723b9ce 100644
--- a/drivers/gpu/drm/drm_usb.c
+++ b/drivers/gpu/drm/drm_usb.c
@@ -33,6 +33,12 @@ int drm_get_usb_dev(struct usb_interface *interface,
 	if (ret)
 		goto err_g1;
 
+	if (drm_core_check_feature(dev, DRIVER_RENDER) && drm_rnodes) {
+		ret = drm_get_minor(dev, &dev->render, DRM_MINOR_RENDER);
+		if (ret)
+			goto err_g11;
+	}
+
 	ret = drm_get_minor(dev, &dev->primary, DRM_MINOR_LEGACY);
 	if (ret)
 		goto err_g2;
@@ -62,6 +68,9 @@ int drm_get_usb_dev(struct usb_interface *interface,
 err_g3:
 	drm_put_minor(&dev->primary);
 err_g2:
+	if (dev->render)
+		drm_put_minor(&dev->render);
+err_g11:
 	drm_put_minor(&dev->control);
 err_g1:
 	kfree(dev);
diff --git a/drivers/gpu/drm/drm_vm.c b/drivers/gpu/drm/drm_vm.c
index feb20035b2c4..b5c5af7328df 100644
--- a/drivers/gpu/drm/drm_vm.c
+++ b/drivers/gpu/drm/drm_vm.c
@@ -251,8 +251,7 @@ static void drm_vm_shm_close(struct vm_area_struct *vma)
 			switch (map->type) {
 			case _DRM_REGISTERS:
 			case _DRM_FRAME_BUFFER:
-				if (drm_core_has_MTRR(dev))
-					arch_phys_wc_del(map->mtrr);
+				arch_phys_wc_del(map->mtrr);
 				iounmap(map->handle);
 				break;
 			case _DRM_SHM:
diff --git a/drivers/gpu/drm/drm_vma_manager.c b/drivers/gpu/drm/drm_vma_manager.c
new file mode 100644
index 000000000000..63b471205072
--- /dev/null
+++ b/drivers/gpu/drm/drm_vma_manager.c
@@ -0,0 +1,436 @@
+/*
+ * Copyright (c) 2006-2009 VMware, Inc., Palo Alto, CA., USA
+ * Copyright (c) 2012 David Airlie <airlied@linux.ie>
+ * Copyright (c) 2013 David Herrmann <dh.herrmann@gmail.com>
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+#include <drm/drmP.h>
+#include <drm/drm_mm.h>
+#include <drm/drm_vma_manager.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/rbtree.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/types.h>
+
+/**
+ * DOC: vma offset manager
+ *
+ * The vma-manager is responsible to map arbitrary driver-dependent memory
+ * regions into the linear user address-space. It provides offsets to the
+ * caller which can then be used on the address_space of the drm-device. It
+ * takes care to not overlap regions, size them appropriately and to not
+ * confuse mm-core by inconsistent fake vm_pgoff fields.
+ * Drivers shouldn't use this for object placement in VMEM. This manager should
+ * only be used to manage mappings into linear user-space VMs.
+ *
+ * We use drm_mm as backend to manage object allocations. But it is highly
+ * optimized for alloc/free calls, not lookups. Hence, we use an rb-tree to
+ * speed up offset lookups.
+ *
+ * You must not use multiple offset managers on a single address_space.
+ * Otherwise, mm-core will be unable to tear down memory mappings as the VM will
+ * no longer be linear. Please use VM_NONLINEAR in that case and implement your
+ * own offset managers.
+ *
+ * This offset manager works on page-based addresses. That is, every argument
+ * and return code (with the exception of drm_vma_node_offset_addr()) is given
+ * in number of pages, not number of bytes. That means, object sizes and offsets
+ * must always be page-aligned (as usual).
+ * If you want to get a valid byte-based user-space address for a given offset,
+ * please see drm_vma_node_offset_addr().
+ *
+ * Additionally to offset management, the vma offset manager also handles access
+ * management. For every open-file context that is allowed to access a given
+ * node, you must call drm_vma_node_allow(). Otherwise, an mmap() call on this
+ * open-file with the offset of the node will fail with -EACCES. To revoke
+ * access again, use drm_vma_node_revoke(). However, the caller is responsible
+ * for destroying already existing mappings, if required.
+ */
+
+/**
+ * drm_vma_offset_manager_init - Initialize new offset-manager
+ * @mgr: Manager object
+ * @page_offset: Offset of available memory area (page-based)
+ * @size: Size of available address space range (page-based)
+ *
+ * Initialize a new offset-manager. The offset and area size available for the
+ * manager are given as @page_offset and @size. Both are interpreted as
+ * page-numbers, not bytes.
+ *
+ * Adding/removing nodes from the manager is locked internally and protected
+ * against concurrent access. However, node allocation and destruction is left
+ * for the caller. While calling into the vma-manager, a given node must
+ * always be guaranteed to be referenced.
+ */
+void drm_vma_offset_manager_init(struct drm_vma_offset_manager *mgr,
+				 unsigned long page_offset, unsigned long size)
+{
+	rwlock_init(&mgr->vm_lock);
+	mgr->vm_addr_space_rb = RB_ROOT;
+	drm_mm_init(&mgr->vm_addr_space_mm, page_offset, size);
+}
+EXPORT_SYMBOL(drm_vma_offset_manager_init);
+
+/**
+ * drm_vma_offset_manager_destroy() - Destroy offset manager
+ * @mgr: Manager object
+ *
+ * Destroy an object manager which was previously created via
+ * drm_vma_offset_manager_init(). The caller must remove all allocated nodes
+ * before destroying the manager. Otherwise, drm_mm will refuse to free the
+ * requested resources.
+ *
+ * The manager must not be accessed after this function is called.
+ */
+void drm_vma_offset_manager_destroy(struct drm_vma_offset_manager *mgr)
+{
+	/* take the lock to protect against buggy drivers */
+	write_lock(&mgr->vm_lock);
+	drm_mm_takedown(&mgr->vm_addr_space_mm);
+	write_unlock(&mgr->vm_lock);
+}
+EXPORT_SYMBOL(drm_vma_offset_manager_destroy);
+
+/**
+ * drm_vma_offset_lookup() - Find node in offset space
+ * @mgr: Manager object
+ * @start: Start address for object (page-based)
+ * @pages: Size of object (page-based)
+ *
+ * Find a node given a start address and object size. This returns the _best_
+ * match for the given node. That is, @start may point somewhere into a valid
+ * region and the given node will be returned, as long as the node spans the
+ * whole requested area (given the size in number of pages as @pages).
+ *
+ * RETURNS:
+ * Returns NULL if no suitable node can be found. Otherwise, the best match
+ * is returned. It's the caller's responsibility to make sure the node doesn't
+ * get destroyed before the caller can access it.
+ */
+struct drm_vma_offset_node *drm_vma_offset_lookup(struct drm_vma_offset_manager *mgr,
+						  unsigned long start,
+						  unsigned long pages)
+{
+	struct drm_vma_offset_node *node;
+
+	read_lock(&mgr->vm_lock);
+	node = drm_vma_offset_lookup_locked(mgr, start, pages);
+	read_unlock(&mgr->vm_lock);
+
+	return node;
+}
+EXPORT_SYMBOL(drm_vma_offset_lookup);
+
+/**
+ * drm_vma_offset_lookup_locked() - Find node in offset space
+ * @mgr: Manager object
+ * @start: Start address for object (page-based)
+ * @pages: Size of object (page-based)
+ *
+ * Same as drm_vma_offset_lookup() but requires the caller to lock offset lookup
+ * manually. See drm_vma_offset_lock_lookup() for an example.
+ *
+ * RETURNS:
+ * Returns NULL if no suitable node can be found. Otherwise, the best match
+ * is returned.
+ */
+struct drm_vma_offset_node *drm_vma_offset_lookup_locked(struct drm_vma_offset_manager *mgr,
+							 unsigned long start,
+							 unsigned long pages)
+{
+	struct drm_vma_offset_node *node, *best;
+	struct rb_node *iter;
+	unsigned long offset;
+
+	iter = mgr->vm_addr_space_rb.rb_node;
+	best = NULL;
+
+	while (likely(iter)) {
+		node = rb_entry(iter, struct drm_vma_offset_node, vm_rb);
+		offset = node->vm_node.start;
+		if (start >= offset) {
+			iter = iter->rb_right;
+			best = node;
+			if (start == offset)
+				break;
+		} else {
+			iter = iter->rb_left;
+		}
+	}
+
+	/* verify that the node spans the requested area */
+	if (best) {
+		offset = best->vm_node.start + best->vm_node.size;
+		if (offset < start + pages)
+			best = NULL;
+	}
+
+	return best;
+}
+EXPORT_SYMBOL(drm_vma_offset_lookup_locked);
+
+/* internal helper to link @node into the rb-tree */
+static void _drm_vma_offset_add_rb(struct drm_vma_offset_manager *mgr,
+				   struct drm_vma_offset_node *node)
+{
+	struct rb_node **iter = &mgr->vm_addr_space_rb.rb_node;
+	struct rb_node *parent = NULL;
+	struct drm_vma_offset_node *iter_node;
+
+	while (likely(*iter)) {
+		parent = *iter;
+		iter_node = rb_entry(*iter, struct drm_vma_offset_node, vm_rb);
+
+		if (node->vm_node.start < iter_node->vm_node.start)
+			iter = &(*iter)->rb_left;
+		else if (node->vm_node.start > iter_node->vm_node.start)
+			iter = &(*iter)->rb_right;
+		else
+			BUG();
+	}
+
+	rb_link_node(&node->vm_rb, parent, iter);
+	rb_insert_color(&node->vm_rb, &mgr->vm_addr_space_rb);
+}
+
+/**
+ * drm_vma_offset_add() - Add offset node to manager
+ * @mgr: Manager object
+ * @node: Node to be added
+ * @pages: Allocation size visible to user-space (in number of pages)
+ *
+ * Add a node to the offset-manager. If the node was already added, this does
+ * nothing and return 0. @pages is the size of the object given in number of
+ * pages.
+ * After this call succeeds, you can access the offset of the node until it
+ * is removed again.
+ *
+ * If this call fails, it is safe to retry the operation or call
+ * drm_vma_offset_remove(), anyway. However, no cleanup is required in that
+ * case.
+ *
+ * @pages is not required to be the same size as the underlying memory object
+ * that you want to map. It only limits the size that user-space can map into
+ * their address space.
+ *
+ * RETURNS:
+ * 0 on success, negative error code on failure.
+ */
+int drm_vma_offset_add(struct drm_vma_offset_manager *mgr,
+		       struct drm_vma_offset_node *node, unsigned long pages)
+{
+	int ret;
+
+	write_lock(&mgr->vm_lock);
+
+	if (drm_mm_node_allocated(&node->vm_node)) {
+		ret = 0;
+		goto out_unlock;
+	}
+
+	ret = drm_mm_insert_node(&mgr->vm_addr_space_mm, &node->vm_node,
+				 pages, 0, DRM_MM_SEARCH_DEFAULT);
+	if (ret)
+		goto out_unlock;
+
+	_drm_vma_offset_add_rb(mgr, node);
+
+out_unlock:
+	write_unlock(&mgr->vm_lock);
+	return ret;
+}
+EXPORT_SYMBOL(drm_vma_offset_add);
+
+/**
+ * drm_vma_offset_remove() - Remove offset node from manager
+ * @mgr: Manager object
+ * @node: Node to be removed
+ *
+ * Remove a node from the offset manager. If the node wasn't added before, this
+ * does nothing. After this call returns, the offset and size will be 0 until a
+ * new offset is allocated via drm_vma_offset_add() again. Helper functions like
+ * drm_vma_node_start() and drm_vma_node_offset_addr() will return 0 if no
+ * offset is allocated.
+ */
+void drm_vma_offset_remove(struct drm_vma_offset_manager *mgr,
+			   struct drm_vma_offset_node *node)
+{
+	write_lock(&mgr->vm_lock);
+
+	if (drm_mm_node_allocated(&node->vm_node)) {
+		rb_erase(&node->vm_rb, &mgr->vm_addr_space_rb);
+		drm_mm_remove_node(&node->vm_node);
+		memset(&node->vm_node, 0, sizeof(node->vm_node));
+	}
+
+	write_unlock(&mgr->vm_lock);
+}
+EXPORT_SYMBOL(drm_vma_offset_remove);
+
+/**
+ * drm_vma_node_allow - Add open-file to list of allowed users
+ * @node: Node to modify
+ * @filp: Open file to add
+ *
+ * Add @filp to the list of allowed open-files for this node. If @filp is
+ * already on this list, the ref-count is incremented.
+ *
+ * The list of allowed-users is preserved across drm_vma_offset_add() and
+ * drm_vma_offset_remove() calls. You may even call it if the node is currently
+ * not added to any offset-manager.
+ *
+ * You must remove all open-files the same number of times as you added them
+ * before destroying the node. Otherwise, you will leak memory.
+ *
+ * This is locked against concurrent access internally.
+ *
+ * RETURNS:
+ * 0 on success, negative error code on internal failure (out-of-mem)
+ */
+int drm_vma_node_allow(struct drm_vma_offset_node *node, struct file *filp)
+{
+	struct rb_node **iter;
+	struct rb_node *parent = NULL;
+	struct drm_vma_offset_file *new, *entry;
+	int ret = 0;
+
+	/* Preallocate entry to avoid atomic allocations below. It is quite
+	 * unlikely that an open-file is added twice to a single node so we
+	 * don't optimize for this case. OOM is checked below only if the entry
+	 * is actually used. */
+	new = kmalloc(sizeof(*entry), GFP_KERNEL);
+
+	write_lock(&node->vm_lock);
+
+	iter = &node->vm_files.rb_node;
+
+	while (likely(*iter)) {
+		parent = *iter;
+		entry = rb_entry(*iter, struct drm_vma_offset_file, vm_rb);
+
+		if (filp == entry->vm_filp) {
+			entry->vm_count++;
+			goto unlock;
+		} else if (filp > entry->vm_filp) {
+			iter = &(*iter)->rb_right;
+		} else {
+			iter = &(*iter)->rb_left;
+		}
+	}
+
+	if (!new) {
+		ret = -ENOMEM;
+		goto unlock;
+	}
+
+	new->vm_filp = filp;
+	new->vm_count = 1;
+	rb_link_node(&new->vm_rb, parent, iter);
+	rb_insert_color(&new->vm_rb, &node->vm_files);
+	new = NULL;
+
+unlock:
+	write_unlock(&node->vm_lock);
+	kfree(new);
+	return ret;
+}
+EXPORT_SYMBOL(drm_vma_node_allow);
+
+/**
+ * drm_vma_node_revoke - Remove open-file from list of allowed users
+ * @node: Node to modify
+ * @filp: Open file to remove
+ *
+ * Decrement the ref-count of @filp in the list of allowed open-files on @node.
+ * If the ref-count drops to zero, remove @filp from the list. You must call
+ * this once for every drm_vma_node_allow() on @filp.
+ *
+ * This is locked against concurrent access internally.
+ *
+ * If @filp is not on the list, nothing is done.
+ */
+void drm_vma_node_revoke(struct drm_vma_offset_node *node, struct file *filp)
+{
+	struct drm_vma_offset_file *entry;
+	struct rb_node *iter;
+
+	write_lock(&node->vm_lock);
+
+	iter = node->vm_files.rb_node;
+	while (likely(iter)) {
+		entry = rb_entry(iter, struct drm_vma_offset_file, vm_rb);
+		if (filp == entry->vm_filp) {
+			if (!--entry->vm_count) {
+				rb_erase(&entry->vm_rb, &node->vm_files);
+				kfree(entry);
+			}
+			break;
+		} else if (filp > entry->vm_filp) {
+			iter = iter->rb_right;
+		} else {
+			iter = iter->rb_left;
+		}
+	}
+
+	write_unlock(&node->vm_lock);
+}
+EXPORT_SYMBOL(drm_vma_node_revoke);
+
+/**
+ * drm_vma_node_is_allowed - Check whether an open-file is granted access
+ * @node: Node to check
+ * @filp: Open-file to check for
+ *
+ * Search the list in @node whether @filp is currently on the list of allowed
+ * open-files (see drm_vma_node_allow()).
+ *
+ * This is locked against concurrent access internally.
+ *
+ * RETURNS:
+ * true iff @filp is on the list
+ */
+bool drm_vma_node_is_allowed(struct drm_vma_offset_node *node,
+			     struct file *filp)
+{
+	struct drm_vma_offset_file *entry;
+	struct rb_node *iter;
+
+	read_lock(&node->vm_lock);
+
+	iter = node->vm_files.rb_node;
+	while (likely(iter)) {
+		entry = rb_entry(iter, struct drm_vma_offset_file, vm_rb);
+		if (filp == entry->vm_filp)
+			break;
+		else if (filp > entry->vm_filp)
+			iter = iter->rb_right;
+		else
+			iter = iter->rb_left;
+	}
+
+	read_unlock(&node->vm_lock);
+
+	return iter;
+}
+EXPORT_SYMBOL(drm_vma_node_is_allowed);
diff --git a/drivers/gpu/drm/exynos/Kconfig b/drivers/gpu/drm/exynos/Kconfig
index 772c62a6e2ac..45b6ef595965 100644
--- a/drivers/gpu/drm/exynos/Kconfig
+++ b/drivers/gpu/drm/exynos/Kconfig
@@ -1,11 +1,12 @@
 config DRM_EXYNOS
 	tristate "DRM Support for Samsung SoC EXYNOS Series"
-	depends on DRM && (PLAT_SAMSUNG || ARCH_MULTIPLATFORM)
+	depends on OF && DRM && (PLAT_SAMSUNG || ARCH_MULTIPLATFORM)
 	select DRM_KMS_HELPER
 	select FB_CFB_FILLRECT
 	select FB_CFB_COPYAREA
 	select FB_CFB_IMAGEBLIT
 	select VT_HW_CONSOLE_BINDING if FRAMEBUFFER_CONSOLE
+	select VIDEOMODE_HELPERS
 	help
 	  Choose this option if you have a Samsung SoC EXYNOS chipset.
 	  If M is selected the module will be called exynosdrm.
@@ -24,9 +25,8 @@ config DRM_EXYNOS_DMABUF
 
 config DRM_EXYNOS_FIMD
 	bool "Exynos DRM FIMD"
-	depends on OF && DRM_EXYNOS && !FB_S3C && !ARCH_MULTIPLATFORM
+	depends on DRM_EXYNOS && !FB_S3C && !ARCH_MULTIPLATFORM
 	select FB_MODE_HELPERS
-	select VIDEOMODE_HELPERS
 	help
 	  Choose this option if you want to use Exynos FIMD for DRM.
 
@@ -56,7 +56,7 @@ config DRM_EXYNOS_IPP
 
 config DRM_EXYNOS_FIMC
 	bool "Exynos DRM FIMC"
-	depends on DRM_EXYNOS_IPP && MFD_SYSCON && OF
+	depends on DRM_EXYNOS_IPP && MFD_SYSCON
 	help
 	  Choose this option if you want to use Exynos FIMC for DRM.
 
diff --git a/drivers/gpu/drm/exynos/exynos_ddc.c b/drivers/gpu/drm/exynos/exynos_ddc.c
index 30ef41bcd7b8..6a8c84e7c839 100644
--- a/drivers/gpu/drm/exynos/exynos_ddc.c
+++ b/drivers/gpu/drm/exynos/exynos_ddc.c
@@ -15,7 +15,7 @@
 
 #include <linux/kernel.h>
 #include <linux/i2c.h>
-
+#include <linux/of.h>
 
 #include "exynos_drm_drv.h"
 #include "exynos_hdmi.h"
@@ -41,13 +41,6 @@ static int s5p_ddc_remove(struct i2c_client *client)
 	return 0;
 }
 
-static struct i2c_device_id ddc_idtable[] = {
-	{"s5p_ddc", 0},
-	{"exynos5-hdmiddc", 0},
-	{ },
-};
-
-#ifdef CONFIG_OF
 static struct of_device_id hdmiddc_match_types[] = {
 	{
 		.compatible = "samsung,exynos5-hdmiddc",
@@ -57,15 +50,13 @@ static struct of_device_id hdmiddc_match_types[] = {
 		/* end node */
 	}
 };
-#endif
 
 struct i2c_driver ddc_driver = {
 	.driver = {
 		.name = "exynos-hdmiddc",
 		.owner = THIS_MODULE,
-		.of_match_table = of_match_ptr(hdmiddc_match_types),
+		.of_match_table = hdmiddc_match_types,
 	},
-	.id_table	= ddc_idtable,
 	.probe		= s5p_ddc_probe,
 	.remove		= s5p_ddc_remove,
 	.command		= NULL,
diff --git a/drivers/gpu/drm/exynos/exynos_drm_buf.c b/drivers/gpu/drm/exynos/exynos_drm_buf.c
index b8ac06d92fbf..9c8088462c26 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_buf.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_buf.c
@@ -63,7 +63,8 @@ static int lowlevel_buffer_allocate(struct drm_device *dev,
 			return -ENOMEM;
 		}
 
-		buf->kvaddr = dma_alloc_attrs(dev->dev, buf->size,
+		buf->kvaddr = (void __iomem *)dma_alloc_attrs(dev->dev,
+					buf->size,
 					&buf->dma_addr, GFP_KERNEL,
 					&buf->dma_attrs);
 		if (!buf->kvaddr) {
@@ -90,9 +91,9 @@ static int lowlevel_buffer_allocate(struct drm_device *dev,
 	}
 
 	buf->sgt = drm_prime_pages_to_sg(buf->pages, nr_pages);
-	if (!buf->sgt) {
+	if (IS_ERR(buf->sgt)) {
 		DRM_ERROR("failed to get sg table.\n");
-		ret = -ENOMEM;
+		ret = PTR_ERR(buf->sgt);
 		goto err_free_attrs;
 	}
 
@@ -149,10 +150,8 @@ struct exynos_drm_gem_buf *exynos_drm_init_buf(struct drm_device *dev,
 	DRM_DEBUG_KMS("desired size = 0x%x\n", size);
 
 	buffer = kzalloc(sizeof(*buffer), GFP_KERNEL);
-	if (!buffer) {
-		DRM_ERROR("failed to allocate exynos_drm_gem_buf.\n");
+	if (!buffer)
 		return NULL;
-	}
 
 	buffer->size = size;
 	return buffer;
@@ -161,11 +160,6 @@ struct exynos_drm_gem_buf *exynos_drm_init_buf(struct drm_device *dev,
 void exynos_drm_fini_buf(struct drm_device *dev,
 				struct exynos_drm_gem_buf *buffer)
 {
-	if (!buffer) {
-		DRM_DEBUG_KMS("buffer is null.\n");
-		return;
-	}
-
 	kfree(buffer);
 	buffer = NULL;
 }
diff --git a/drivers/gpu/drm/exynos/exynos_drm_connector.c b/drivers/gpu/drm/exynos/exynos_drm_connector.c
index 02a8bc5226ca..e082efb2fece 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_connector.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_connector.c
@@ -17,6 +17,7 @@
 #include <drm/exynos_drm.h>
 #include "exynos_drm_drv.h"
 #include "exynos_drm_encoder.h"
+#include "exynos_drm_connector.h"
 
 #define to_exynos_connector(x)	container_of(x, struct exynos_drm_connector,\
 				drm_connector)
@@ -28,35 +29,6 @@ struct exynos_drm_connector {
 	uint32_t		dpms;
 };
 
-/* convert exynos_video_timings to drm_display_mode */
-static inline void
-convert_to_display_mode(struct drm_display_mode *mode,
-			struct exynos_drm_panel_info *panel)
-{
-	struct fb_videomode *timing = &panel->timing;
-
-	mode->clock = timing->pixclock / 1000;
-	mode->vrefresh = timing->refresh;
-
-	mode->hdisplay = timing->xres;
-	mode->hsync_start = mode->hdisplay + timing->right_margin;
-	mode->hsync_end = mode->hsync_start + timing->hsync_len;
-	mode->htotal = mode->hsync_end + timing->left_margin;
-
-	mode->vdisplay = timing->yres;
-	mode->vsync_start = mode->vdisplay + timing->lower_margin;
-	mode->vsync_end = mode->vsync_start + timing->vsync_len;
-	mode->vtotal = mode->vsync_end + timing->upper_margin;
-	mode->width_mm = panel->width_mm;
-	mode->height_mm = panel->height_mm;
-
-	if (timing->vmode & FB_VMODE_INTERLACED)
-		mode->flags |= DRM_MODE_FLAG_INTERLACE;
-
-	if (timing->vmode & FB_VMODE_DOUBLE)
-		mode->flags |= DRM_MODE_FLAG_DBLSCAN;
-}
-
 static int exynos_drm_connector_get_modes(struct drm_connector *connector)
 {
 	struct exynos_drm_connector *exynos_connector =
@@ -111,7 +83,9 @@ static int exynos_drm_connector_get_modes(struct drm_connector *connector)
 			return 0;
 		}
 
-		convert_to_display_mode(mode, panel);
+		drm_display_mode_from_videomode(&panel->vm, mode);
+		mode->width_mm = panel->width_mm;
+		mode->height_mm = panel->height_mm;
 		connector->display_info.width_mm = mode->width_mm;
 		connector->display_info.height_mm = mode->height_mm;
 
@@ -278,10 +252,8 @@ struct drm_connector *exynos_drm_connector_create(struct drm_device *dev,
 	int err;
 
 	exynos_connector = kzalloc(sizeof(*exynos_connector), GFP_KERNEL);
-	if (!exynos_connector) {
-		DRM_ERROR("failed to allocate connector\n");
+	if (!exynos_connector)
 		return NULL;
-	}
 
 	connector = &exynos_connector->drm_connector;
 
diff --git a/drivers/gpu/drm/exynos/exynos_drm_crtc.c b/drivers/gpu/drm/exynos/exynos_drm_crtc.c
index 9a35d171a6d3..ebc01503d50e 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_crtc.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_crtc.c
@@ -15,6 +15,7 @@
 #include <drm/drmP.h>
 #include <drm/drm_crtc_helper.h>
 
+#include "exynos_drm_crtc.h"
 #include "exynos_drm_drv.h"
 #include "exynos_drm_encoder.h"
 #include "exynos_drm_plane.h"
@@ -184,8 +185,9 @@ static struct drm_crtc_helper_funcs exynos_crtc_helper_funcs = {
 };
 
 static int exynos_drm_crtc_page_flip(struct drm_crtc *crtc,
-				      struct drm_framebuffer *fb,
-				      struct drm_pending_vblank_event *event)
+				     struct drm_framebuffer *fb,
+				     struct drm_pending_vblank_event *event,
+				     uint32_t page_flip_flags)
 {
 	struct drm_device *dev = crtc->dev;
 	struct exynos_drm_private *dev_priv = dev->dev_private;
@@ -323,10 +325,8 @@ int exynos_drm_crtc_create(struct drm_device *dev, unsigned int nr)
 	struct drm_crtc *crtc;
 
 	exynos_crtc = kzalloc(sizeof(*exynos_crtc), GFP_KERNEL);
-	if (!exynos_crtc) {
-		DRM_ERROR("failed to allocate exynos crtc\n");
+	if (!exynos_crtc)
 		return -ENOMEM;
-	}
 
 	exynos_crtc->pipe = nr;
 	exynos_crtc->dpms = DRM_MODE_DPMS_OFF;
diff --git a/drivers/gpu/drm/exynos/exynos_drm_dmabuf.c b/drivers/gpu/drm/exynos/exynos_drm_dmabuf.c
index a0f997e0cbdf..59827cc5e770 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_dmabuf.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_dmabuf.c
@@ -11,6 +11,7 @@
 
 #include <drm/drmP.h>
 #include <drm/exynos_drm.h>
+#include "exynos_drm_dmabuf.h"
 #include "exynos_drm_drv.h"
 #include "exynos_drm_gem.h"
 
@@ -22,6 +23,11 @@ struct exynos_drm_dmabuf_attachment {
 	bool is_mapped;
 };
 
+static struct exynos_drm_gem_obj *dma_buf_to_obj(struct dma_buf *buf)
+{
+	return to_exynos_gem_obj(buf->priv);
+}
+
 static int exynos_gem_attach_dma_buf(struct dma_buf *dmabuf,
 					struct device *dev,
 					struct dma_buf_attachment *attach)
@@ -63,7 +69,7 @@ static struct sg_table *
 					enum dma_data_direction dir)
 {
 	struct exynos_drm_dmabuf_attachment *exynos_attach = attach->priv;
-	struct exynos_drm_gem_obj *gem_obj = attach->dmabuf->priv;
+	struct exynos_drm_gem_obj *gem_obj = dma_buf_to_obj(attach->dmabuf);
 	struct drm_device *dev = gem_obj->base.dev;
 	struct exynos_drm_gem_buf *buf;
 	struct scatterlist *rd, *wr;
@@ -127,27 +133,6 @@ static void exynos_gem_unmap_dma_buf(struct dma_buf_attachment *attach,
 	/* Nothing to do. */
 }
 
-static void exynos_dmabuf_release(struct dma_buf *dmabuf)
-{
-	struct exynos_drm_gem_obj *exynos_gem_obj = dmabuf->priv;
-
-	/*
-	 * exynos_dmabuf_release() call means that file object's
-	 * f_count is 0 and it calls drm_gem_object_handle_unreference()
-	 * to drop the references that these values had been increased
-	 * at drm_prime_handle_to_fd()
-	 */
-	if (exynos_gem_obj->base.export_dma_buf == dmabuf) {
-		exynos_gem_obj->base.export_dma_buf = NULL;
-
-		/*
-		 * drop this gem object refcount to release allocated buffer
-		 * and resources.
-		 */
-		drm_gem_object_unreference_unlocked(&exynos_gem_obj->base);
-	}
-}
-
 static void *exynos_gem_dmabuf_kmap_atomic(struct dma_buf *dma_buf,
 						unsigned long page_num)
 {
@@ -193,7 +178,7 @@ static struct dma_buf_ops exynos_dmabuf_ops = {
 	.kunmap			= exynos_gem_dmabuf_kunmap,
 	.kunmap_atomic		= exynos_gem_dmabuf_kunmap_atomic,
 	.mmap			= exynos_gem_dmabuf_mmap,
-	.release		= exynos_dmabuf_release,
+	.release		= drm_gem_dmabuf_release,
 };
 
 struct dma_buf *exynos_dmabuf_prime_export(struct drm_device *drm_dev,
@@ -201,7 +186,7 @@ struct dma_buf *exynos_dmabuf_prime_export(struct drm_device *drm_dev,
 {
 	struct exynos_drm_gem_obj *exynos_gem_obj = to_exynos_gem_obj(obj);
 
-	return dma_buf_export(exynos_gem_obj, &exynos_dmabuf_ops,
+	return dma_buf_export(obj, &exynos_dmabuf_ops,
 				exynos_gem_obj->base.size, flags);
 }
 
@@ -219,8 +204,7 @@ struct drm_gem_object *exynos_dmabuf_prime_import(struct drm_device *drm_dev,
 	if (dma_buf->ops == &exynos_dmabuf_ops) {
 		struct drm_gem_object *obj;
 
-		exynos_gem_obj = dma_buf->priv;
-		obj = &exynos_gem_obj->base;
+		obj = dma_buf->priv;
 
 		/* is it from our device? */
 		if (obj->dev == drm_dev) {
@@ -247,7 +231,6 @@ struct drm_gem_object *exynos_dmabuf_prime_import(struct drm_device *drm_dev,
 
 	buffer = kzalloc(sizeof(*buffer), GFP_KERNEL);
 	if (!buffer) {
-		DRM_ERROR("failed to allocate exynos_drm_gem_buf.\n");
 		ret = -ENOMEM;
 		goto err_unmap_attach;
 	}
diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.c b/drivers/gpu/drm/exynos/exynos_drm_drv.c
index ca2729a85129..bb82ef78ca85 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_drv.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_drv.c
@@ -47,10 +47,8 @@ static int exynos_drm_load(struct drm_device *dev, unsigned long flags)
 	int nr;
 
 	private = kzalloc(sizeof(struct exynos_drm_private), GFP_KERNEL);
-	if (!private) {
-		DRM_ERROR("failed to allocate private\n");
+	if (!private)
 		return -ENOMEM;
-	}
 
 	INIT_LIST_HEAD(&private->pageflip_event_list);
 	dev->dev_private = (void *)private;
@@ -213,7 +211,7 @@ static const struct vm_operations_struct exynos_drm_gem_vm_ops = {
 	.close = drm_gem_vm_close,
 };
 
-static struct drm_ioctl_desc exynos_ioctls[] = {
+static const struct drm_ioctl_desc exynos_ioctls[] = {
 	DRM_IOCTL_DEF_DRV(EXYNOS_GEM_CREATE, exynos_drm_gem_create_ioctl,
 			DRM_UNLOCKED | DRM_AUTH),
 	DRM_IOCTL_DEF_DRV(EXYNOS_GEM_MAP_OFFSET,
@@ -271,12 +269,13 @@ static struct drm_driver exynos_drm_driver = {
 	.gem_vm_ops		= &exynos_drm_gem_vm_ops,
 	.dumb_create		= exynos_drm_gem_dumb_create,
 	.dumb_map_offset	= exynos_drm_gem_dumb_map_offset,
-	.dumb_destroy		= exynos_drm_gem_dumb_destroy,
+	.dumb_destroy		= drm_gem_dumb_destroy,
 	.prime_handle_to_fd	= drm_gem_prime_handle_to_fd,
 	.prime_fd_to_handle	= drm_gem_prime_fd_to_handle,
 	.gem_prime_export	= exynos_dmabuf_prime_export,
 	.gem_prime_import	= exynos_dmabuf_prime_import,
 	.ioctls			= exynos_ioctls,
+	.num_ioctls		= ARRAY_SIZE(exynos_ioctls),
 	.fops			= &exynos_drm_driver_fops,
 	.name	= DRIVER_NAME,
 	.desc	= DRIVER_DESC,
@@ -288,7 +287,6 @@ static struct drm_driver exynos_drm_driver = {
 static int exynos_drm_platform_probe(struct platform_device *pdev)
 {
 	pdev->dev.coherent_dma_mask = DMA_BIT_MASK(32);
-	exynos_drm_driver.num_ioctls = DRM_ARRAY_SIZE(exynos_ioctls);
 
 	return drm_platform_init(&exynos_drm_driver, pdev);
 }
diff --git a/drivers/gpu/drm/exynos/exynos_drm_encoder.c b/drivers/gpu/drm/exynos/exynos_drm_encoder.c
index a99a033793bc..06f1b2a09da7 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_encoder.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_encoder.c
@@ -324,10 +324,8 @@ exynos_drm_encoder_create(struct drm_device *dev,
 		return NULL;
 
 	exynos_encoder = kzalloc(sizeof(*exynos_encoder), GFP_KERNEL);
-	if (!exynos_encoder) {
-		DRM_ERROR("failed to allocate encoder\n");
+	if (!exynos_encoder)
 		return NULL;
-	}
 
 	exynos_encoder->dpms = DRM_MODE_DPMS_OFF;
 	exynos_encoder->manager = manager;
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fb.c b/drivers/gpu/drm/exynos/exynos_drm_fb.c
index c2d149f0408a..ea39e0ef2ae4 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fb.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fb.c
@@ -156,10 +156,8 @@ exynos_drm_framebuffer_init(struct drm_device *dev,
 	}
 
 	exynos_fb = kzalloc(sizeof(*exynos_fb), GFP_KERNEL);
-	if (!exynos_fb) {
-		DRM_ERROR("failed to allocate exynos drm framebuffer\n");
+	if (!exynos_fb)
 		return ERR_PTR(-ENOMEM);
-	}
 
 	drm_helper_mode_fill_fb_struct(&exynos_fb->fb, mode_cmd);
 	exynos_fb->exynos_gem_obj[0] = exynos_gem_obj;
@@ -220,10 +218,8 @@ exynos_user_fb_create(struct drm_device *dev, struct drm_file *file_priv,
 	int i, ret;
 
 	exynos_fb = kzalloc(sizeof(*exynos_fb), GFP_KERNEL);
-	if (!exynos_fb) {
-		DRM_ERROR("failed to allocate exynos drm framebuffer\n");
+	if (!exynos_fb)
 		return ERR_PTR(-ENOMEM);
-	}
 
 	obj = drm_gem_object_lookup(dev, file_priv, mode_cmd->handles[0]);
 	if (!obj) {
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fbdev.c b/drivers/gpu/drm/exynos/exynos_drm_fbdev.c
index 8e60bd61137f..e7c2f2d07f19 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fbdev.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fbdev.c
@@ -16,9 +16,11 @@
 #include <drm/drm_crtc.h>
 #include <drm/drm_fb_helper.h>
 #include <drm/drm_crtc_helper.h>
+#include <drm/exynos_drm.h>
 
 #include "exynos_drm_drv.h"
 #include "exynos_drm_fb.h"
+#include "exynos_drm_fbdev.h"
 #include "exynos_drm_gem.h"
 #include "exynos_drm_iommu.h"
 
@@ -97,12 +99,13 @@ static int exynos_drm_fbdev_update(struct drm_fb_helper *helper,
 		if (is_drm_iommu_supported(dev)) {
 			unsigned int nr_pages = buffer->size >> PAGE_SHIFT;
 
-			buffer->kvaddr = vmap(buffer->pages, nr_pages, VM_MAP,
+			buffer->kvaddr = (void __iomem *) vmap(buffer->pages,
+					nr_pages, VM_MAP,
 					pgprot_writecombine(PAGE_KERNEL));
 		} else {
 			phys_addr_t dma_addr = buffer->dma_addr;
 			if (dma_addr)
-				buffer->kvaddr = phys_to_virt(dma_addr);
+				buffer->kvaddr = (void __iomem *)phys_to_virt(dma_addr);
 			else
 				buffer->kvaddr = (void __iomem *)NULL;
 		}
@@ -165,8 +168,18 @@ static int exynos_drm_fbdev_create(struct drm_fb_helper *helper,
 
 	size = mode_cmd.pitches[0] * mode_cmd.height;
 
-	/* 0 means to allocate physically continuous memory */
-	exynos_gem_obj = exynos_drm_gem_create(dev, 0, size);
+	exynos_gem_obj = exynos_drm_gem_create(dev, EXYNOS_BO_CONTIG, size);
+	/*
+	 * If physically contiguous memory allocation fails and if IOMMU is
+	 * supported then try to get buffer from non physically contiguous
+	 * memory area.
+	 */
+	if (IS_ERR(exynos_gem_obj) && is_drm_iommu_supported(dev)) {
+		dev_warn(&pdev->dev, "contiguous FB allocation failed, falling back to non-contiguous\n");
+		exynos_gem_obj = exynos_drm_gem_create(dev, EXYNOS_BO_NONCONTIG,
+							size);
+	}
+
 	if (IS_ERR(exynos_gem_obj)) {
 		ret = PTR_ERR(exynos_gem_obj);
 		goto err_release_framebuffer;
@@ -236,10 +249,8 @@ int exynos_drm_fbdev_init(struct drm_device *dev)
 		return 0;
 
 	fbdev = kzalloc(sizeof(*fbdev), GFP_KERNEL);
-	if (!fbdev) {
-		DRM_ERROR("failed to allocate drm fbdev.\n");
+	if (!fbdev)
 		return -ENOMEM;
-	}
 
 	private->fb_helper = helper = &fbdev->drm_fb_helper;
 	helper->funcs = &exynos_drm_fb_helper_funcs;
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimc.c b/drivers/gpu/drm/exynos/exynos_drm_fimc.c
index 6e047bd53e2f..8adfc8f1e08f 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fimc.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fimc.c
@@ -17,10 +17,12 @@
 #include <linux/regmap.h>
 #include <linux/clk.h>
 #include <linux/pm_runtime.h>
+#include <linux/of.h>
 
 #include <drm/drmP.h>
 #include <drm/exynos_drm.h>
 #include "regs-fimc.h"
+#include "exynos_drm_drv.h"
 #include "exynos_drm_ipp.h"
 #include "exynos_drm_fimc.h"
 
@@ -1343,10 +1345,8 @@ static int fimc_init_prop_list(struct exynos_drm_ippdrv *ippdrv)
 	struct drm_exynos_ipp_prop_list *prop_list;
 
 	prop_list = devm_kzalloc(ippdrv->dev, sizeof(*prop_list), GFP_KERNEL);
-	if (!prop_list) {
-		DRM_ERROR("failed to alloc property list.\n");
+	if (!prop_list)
 		return -ENOMEM;
-	}
 
 	prop_list->version = 1;
 	prop_list->writeback = 1;
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimd.c b/drivers/gpu/drm/exynos/exynos_drm_fimd.c
index 1c263dac3c1c..868a14d52995 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fimd.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fimd.c
@@ -16,10 +16,12 @@
 #include <linux/kernel.h>
 #include <linux/platform_device.h>
 #include <linux/clk.h>
+#include <linux/of.h>
 #include <linux/of_device.h>
 #include <linux/pm_runtime.h>
 
 #include <video/of_display_timing.h>
+#include <video/of_videomode.h>
 #include <video/samsung_fimd.h>
 #include <drm/exynos_drm.h>
 
@@ -35,6 +37,8 @@
  * CPU Interface.
  */
 
+#define FIMD_DEFAULT_FRAMERATE 60
+
 /* position control register for hardware window 0, 2 ~ 4.*/
 #define VIDOSD_A(win)		(VIDOSD_BASE + 0x00 + (win) * 16)
 #define VIDOSD_B(win)		(VIDOSD_BASE + 0x04 + (win) * 16)
@@ -65,11 +69,13 @@ struct fimd_driver_data {
 
 	unsigned int has_shadowcon:1;
 	unsigned int has_clksel:1;
+	unsigned int has_limited_fmt:1;
 };
 
 static struct fimd_driver_data s3c64xx_fimd_driver_data = {
 	.timing_base = 0x0,
 	.has_clksel = 1,
+	.has_limited_fmt = 1,
 };
 
 static struct fimd_driver_data exynos4_fimd_driver_data = {
@@ -90,6 +96,7 @@ struct fimd_win_data {
 	unsigned int		fb_width;
 	unsigned int		fb_height;
 	unsigned int		bpp;
+	unsigned int		pixel_format;
 	dma_addr_t		dma_addr;
 	unsigned int		buf_offsize;
 	unsigned int		line_size;	/* bytes */
@@ -115,11 +122,10 @@ struct fimd_context {
 	wait_queue_head_t		wait_vsync_queue;
 	atomic_t			wait_vsync_event;
 
-	struct exynos_drm_panel_info *panel;
+	struct exynos_drm_panel_info panel;
 	struct fimd_driver_data *driver_data;
 };
 
-#ifdef CONFIG_OF
 static const struct of_device_id fimd_driver_dt_match[] = {
 	{ .compatible = "samsung,s3c6400-fimd",
 	  .data = &s3c64xx_fimd_driver_data },
@@ -129,21 +135,14 @@ static const struct of_device_id fimd_driver_dt_match[] = {
 	  .data = &exynos5_fimd_driver_data },
 	{},
 };
-#endif
 
 static inline struct fimd_driver_data *drm_fimd_get_driver_data(
 	struct platform_device *pdev)
 {
-#ifdef CONFIG_OF
 	const struct of_device_id *of_id =
 			of_match_device(fimd_driver_dt_match, &pdev->dev);
 
-	if (of_id)
-		return (struct fimd_driver_data *)of_id->data;
-#endif
-
-	return (struct fimd_driver_data *)
-		platform_get_device_id(pdev)->driver_data;
+	return (struct fimd_driver_data *)of_id->data;
 }
 
 static bool fimd_display_is_connected(struct device *dev)
@@ -157,7 +156,7 @@ static void *fimd_get_panel(struct device *dev)
 {
 	struct fimd_context *ctx = get_fimd_context(dev);
 
-	return ctx->panel;
+	return &ctx->panel;
 }
 
 static int fimd_check_mode(struct device *dev, struct drm_display_mode *mode)
@@ -237,8 +236,8 @@ static void fimd_apply(struct device *subdrv_dev)
 static void fimd_commit(struct device *dev)
 {
 	struct fimd_context *ctx = get_fimd_context(dev);
-	struct exynos_drm_panel_info *panel = ctx->panel;
-	struct fb_videomode *timing = &panel->timing;
+	struct exynos_drm_panel_info *panel = &ctx->panel;
+	struct videomode *vm = &panel->vm;
 	struct fimd_driver_data *driver_data;
 	u32 val;
 
@@ -250,22 +249,22 @@ static void fimd_commit(struct device *dev)
 	writel(ctx->vidcon1, ctx->regs + driver_data->timing_base + VIDCON1);
 
 	/* setup vertical timing values. */
-	val = VIDTCON0_VBPD(timing->upper_margin - 1) |
-	       VIDTCON0_VFPD(timing->lower_margin - 1) |
-	       VIDTCON0_VSPW(timing->vsync_len - 1);
+	val = VIDTCON0_VBPD(vm->vback_porch - 1) |
+	       VIDTCON0_VFPD(vm->vfront_porch - 1) |
+	       VIDTCON0_VSPW(vm->vsync_len - 1);
 	writel(val, ctx->regs + driver_data->timing_base + VIDTCON0);
 
 	/* setup horizontal timing values.  */
-	val = VIDTCON1_HBPD(timing->left_margin - 1) |
-	       VIDTCON1_HFPD(timing->right_margin - 1) |
-	       VIDTCON1_HSPW(timing->hsync_len - 1);
+	val = VIDTCON1_HBPD(vm->hback_porch - 1) |
+	       VIDTCON1_HFPD(vm->hfront_porch - 1) |
+	       VIDTCON1_HSPW(vm->hsync_len - 1);
 	writel(val, ctx->regs + driver_data->timing_base + VIDTCON1);
 
 	/* setup horizontal and vertical display size. */
-	val = VIDTCON2_LINEVAL(timing->yres - 1) |
-	       VIDTCON2_HOZVAL(timing->xres - 1) |
-	       VIDTCON2_LINEVAL_E(timing->yres - 1) |
-	       VIDTCON2_HOZVAL_E(timing->xres - 1);
+	val = VIDTCON2_LINEVAL(vm->vactive - 1) |
+	       VIDTCON2_HOZVAL(vm->hactive - 1) |
+	       VIDTCON2_LINEVAL_E(vm->vactive - 1) |
+	       VIDTCON2_HOZVAL_E(vm->hactive - 1);
 	writel(val, ctx->regs + driver_data->timing_base + VIDTCON2);
 
 	/* setup clock source, clock divider, enable dma. */
@@ -396,6 +395,7 @@ static void fimd_win_mode_set(struct device *dev,
 	win_data->fb_height = overlay->fb_height;
 	win_data->dma_addr = overlay->dma_addr[0] + offset;
 	win_data->bpp = overlay->bpp;
+	win_data->pixel_format = overlay->pixel_format;
 	win_data->buf_offsize = (overlay->fb_width - overlay->crtc_width) *
 				(overlay->bpp >> 3);
 	win_data->line_size = overlay->crtc_width * (overlay->bpp >> 3);
@@ -417,39 +417,38 @@ static void fimd_win_set_pixfmt(struct device *dev, unsigned int win)
 
 	val = WINCONx_ENWIN;
 
-	switch (win_data->bpp) {
-	case 1:
-		val |= WINCON0_BPPMODE_1BPP;
-		val |= WINCONx_BITSWP;
-		val |= WINCONx_BURSTLEN_4WORD;
-		break;
-	case 2:
-		val |= WINCON0_BPPMODE_2BPP;
-		val |= WINCONx_BITSWP;
-		val |= WINCONx_BURSTLEN_8WORD;
-		break;
-	case 4:
-		val |= WINCON0_BPPMODE_4BPP;
-		val |= WINCONx_BITSWP;
-		val |= WINCONx_BURSTLEN_8WORD;
-		break;
-	case 8:
+	/*
+	 * In case of s3c64xx, window 0 doesn't support alpha channel.
+	 * So the request format is ARGB8888 then change it to XRGB8888.
+	 */
+	if (ctx->driver_data->has_limited_fmt && !win) {
+		if (win_data->pixel_format == DRM_FORMAT_ARGB8888)
+			win_data->pixel_format = DRM_FORMAT_XRGB8888;
+	}
+
+	switch (win_data->pixel_format) {
+	case DRM_FORMAT_C8:
 		val |= WINCON0_BPPMODE_8BPP_PALETTE;
 		val |= WINCONx_BURSTLEN_8WORD;
 		val |= WINCONx_BYTSWP;
 		break;
-	case 16:
+	case DRM_FORMAT_XRGB1555:
+		val |= WINCON0_BPPMODE_16BPP_1555;
+		val |= WINCONx_HAWSWP;
+		val |= WINCONx_BURSTLEN_16WORD;
+		break;
+	case DRM_FORMAT_RGB565:
 		val |= WINCON0_BPPMODE_16BPP_565;
 		val |= WINCONx_HAWSWP;
 		val |= WINCONx_BURSTLEN_16WORD;
 		break;
-	case 24:
+	case DRM_FORMAT_XRGB8888:
 		val |= WINCON0_BPPMODE_24BPP_888;
 		val |= WINCONx_WSWP;
 		val |= WINCONx_BURSTLEN_16WORD;
 		break;
-	case 32:
-		val |= WINCON1_BPPMODE_28BPP_A4888
+	case DRM_FORMAT_ARGB8888:
+		val |= WINCON1_BPPMODE_25BPP_A1888
 			| WINCON1_BLD_PIX | WINCON1_ALPHA_SEL;
 		val |= WINCONx_WSWP;
 		val |= WINCONx_BURSTLEN_16WORD;
@@ -746,45 +745,54 @@ static void fimd_subdrv_remove(struct drm_device *drm_dev, struct device *dev)
 		drm_iommu_detach_device(drm_dev, dev);
 }
 
-static int fimd_calc_clkdiv(struct fimd_context *ctx,
-			    struct fb_videomode *timing)
+static int fimd_configure_clocks(struct fimd_context *ctx, struct device *dev)
 {
-	unsigned long clk = clk_get_rate(ctx->lcd_clk);
-	u32 retrace;
-	u32 clkdiv;
-	u32 best_framerate = 0;
-	u32 framerate;
-
-	retrace = timing->left_margin + timing->hsync_len +
-				timing->right_margin + timing->xres;
-	retrace *= timing->upper_margin + timing->vsync_len +
-				timing->lower_margin + timing->yres;
-
-	/* default framerate is 60Hz */
-	if (!timing->refresh)
-		timing->refresh = 60;
-
-	clk /= retrace;
-
-	for (clkdiv = 1; clkdiv < 0x100; clkdiv++) {
-		int tmp;
-
-		/* get best framerate */
-		framerate = clk / clkdiv;
-		tmp = timing->refresh - framerate;
-		if (tmp < 0) {
-			best_framerate = framerate;
-			continue;
-		} else {
-			if (!best_framerate)
-				best_framerate = framerate;
-			else if (tmp < (best_framerate - framerate))
-				best_framerate = framerate;
-			break;
+	struct videomode *vm = &ctx->panel.vm;
+	unsigned long clk;
+
+	ctx->bus_clk = devm_clk_get(dev, "fimd");
+	if (IS_ERR(ctx->bus_clk)) {
+		dev_err(dev, "failed to get bus clock\n");
+		return PTR_ERR(ctx->bus_clk);
+	}
+
+	ctx->lcd_clk = devm_clk_get(dev, "sclk_fimd");
+	if (IS_ERR(ctx->lcd_clk)) {
+		dev_err(dev, "failed to get lcd clock\n");
+		return PTR_ERR(ctx->lcd_clk);
+	}
+
+	clk = clk_get_rate(ctx->lcd_clk);
+	if (clk == 0) {
+		dev_err(dev, "error getting sclk_fimd clock rate\n");
+		return -EINVAL;
+	}
+
+	if (vm->pixelclock == 0) {
+		unsigned long c;
+		c = vm->hactive + vm->hback_porch + vm->hfront_porch +
+		    vm->hsync_len;
+		c *= vm->vactive + vm->vback_porch + vm->vfront_porch +
+		     vm->vsync_len;
+		vm->pixelclock = c * FIMD_DEFAULT_FRAMERATE;
+		if (vm->pixelclock == 0) {
+			dev_err(dev, "incorrect display timings\n");
+			return -EINVAL;
 		}
+		dev_warn(dev, "pixel clock recalculated to %luHz (%dHz frame rate)\n",
+			 vm->pixelclock, FIMD_DEFAULT_FRAMERATE);
 	}
+	ctx->clkdiv = DIV_ROUND_UP(clk, vm->pixelclock);
+	if (ctx->clkdiv > 256) {
+		dev_warn(dev, "calculated pixel clock divider too high (%u), lowered to 256\n",
+			 ctx->clkdiv);
+		ctx->clkdiv = 256;
+	}
+	vm->pixelclock = clk / ctx->clkdiv;
+	DRM_DEBUG_KMS("pixel clock = %lu, clkdiv = %d\n", vm->pixelclock,
+		      ctx->clkdiv);
 
-	return clkdiv;
+	return 0;
 }
 
 static void fimd_clear_win(struct fimd_context *ctx, int win)
@@ -876,59 +884,53 @@ static int fimd_activate(struct fimd_context *ctx, bool enable)
 	return 0;
 }
 
+static int fimd_get_platform_data(struct fimd_context *ctx, struct device *dev)
+{
+	struct videomode *vm;
+	int ret;
+
+	vm = &ctx->panel.vm;
+	ret = of_get_videomode(dev->of_node, vm, OF_USE_NATIVE_MODE);
+	if (ret) {
+		DRM_ERROR("failed: of_get_videomode() : %d\n", ret);
+		return ret;
+	}
+
+	if (vm->flags & DISPLAY_FLAGS_VSYNC_LOW)
+		ctx->vidcon1 |= VIDCON1_INV_VSYNC;
+	if (vm->flags & DISPLAY_FLAGS_HSYNC_LOW)
+		ctx->vidcon1 |= VIDCON1_INV_HSYNC;
+	if (vm->flags & DISPLAY_FLAGS_DE_LOW)
+		ctx->vidcon1 |= VIDCON1_INV_VDEN;
+	if (vm->flags & DISPLAY_FLAGS_PIXDATA_NEGEDGE)
+		ctx->vidcon1 |= VIDCON1_INV_VCLK;
+
+	return 0;
+}
+
 static int fimd_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct fimd_context *ctx;
 	struct exynos_drm_subdrv *subdrv;
-	struct exynos_drm_fimd_pdata *pdata;
-	struct exynos_drm_panel_info *panel;
 	struct resource *res;
 	int win;
 	int ret = -EINVAL;
 
-	if (dev->of_node) {
-		pdata = devm_kzalloc(dev, sizeof(*pdata), GFP_KERNEL);
-		if (!pdata) {
-			DRM_ERROR("memory allocation for pdata failed\n");
-			return -ENOMEM;
-		}
-
-		ret = of_get_fb_videomode(dev->of_node, &pdata->panel.timing,
-					OF_USE_NATIVE_MODE);
-		if (ret) {
-			DRM_ERROR("failed: of_get_fb_videomode() : %d\n", ret);
-			return ret;
-		}
-	} else {
-		pdata = dev->platform_data;
-		if (!pdata) {
-			DRM_ERROR("no platform data specified\n");
-			return -EINVAL;
-		}
-	}
-
-	panel = &pdata->panel;
-	if (!panel) {
-		dev_err(dev, "panel is null.\n");
-		return -EINVAL;
-	}
+	if (!dev->of_node)
+		return -ENODEV;
 
 	ctx = devm_kzalloc(dev, sizeof(*ctx), GFP_KERNEL);
 	if (!ctx)
 		return -ENOMEM;
 
-	ctx->bus_clk = devm_clk_get(dev, "fimd");
-	if (IS_ERR(ctx->bus_clk)) {
-		dev_err(dev, "failed to get bus clock\n");
-		return PTR_ERR(ctx->bus_clk);
-	}
+	ret = fimd_get_platform_data(ctx, dev);
+	if (ret)
+		return ret;
 
-	ctx->lcd_clk = devm_clk_get(dev, "sclk_fimd");
-	if (IS_ERR(ctx->lcd_clk)) {
-		dev_err(dev, "failed to get lcd clock\n");
-		return PTR_ERR(ctx->lcd_clk);
-	}
+	ret = fimd_configure_clocks(ctx, dev);
+	if (ret)
+		return ret;
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 
@@ -952,10 +954,6 @@ static int fimd_probe(struct platform_device *pdev)
 	}
 
 	ctx->driver_data = drm_fimd_get_driver_data(pdev);
-	ctx->vidcon0 = pdata->vidcon0;
-	ctx->vidcon1 = pdata->vidcon1;
-	ctx->default_win = pdata->default_win;
-	ctx->panel = panel;
 	DRM_INIT_WAITQUEUE(&ctx->wait_vsync_queue);
 	atomic_set(&ctx->wait_vsync_event, 0);
 
@@ -973,12 +971,6 @@ static int fimd_probe(struct platform_device *pdev)
 	pm_runtime_enable(dev);
 	pm_runtime_get_sync(dev);
 
-	ctx->clkdiv = fimd_calc_clkdiv(ctx, &panel->timing);
-	panel->timing.pixclock = clk_get_rate(ctx->lcd_clk) / ctx->clkdiv;
-
-	DRM_DEBUG_KMS("pixel clock = %d, clkdiv = %d\n",
-			panel->timing.pixclock, ctx->clkdiv);
-
 	for (win = 0; win < WINDOWS_NR; win++)
 		fimd_clear_win(ctx, win);
 
@@ -1067,20 +1059,6 @@ static int fimd_runtime_resume(struct device *dev)
 }
 #endif
 
-static struct platform_device_id fimd_driver_ids[] = {
-	{
-		.name		= "s3c64xx-fb",
-		.driver_data	= (unsigned long)&s3c64xx_fimd_driver_data,
-	}, {
-		.name		= "exynos4-fb",
-		.driver_data	= (unsigned long)&exynos4_fimd_driver_data,
-	}, {
-		.name		= "exynos5-fb",
-		.driver_data	= (unsigned long)&exynos5_fimd_driver_data,
-	},
-	{},
-};
-
 static const struct dev_pm_ops fimd_pm_ops = {
 	SET_SYSTEM_SLEEP_PM_OPS(fimd_suspend, fimd_resume)
 	SET_RUNTIME_PM_OPS(fimd_runtime_suspend, fimd_runtime_resume, NULL)
@@ -1089,11 +1067,10 @@ static const struct dev_pm_ops fimd_pm_ops = {
 struct platform_driver fimd_driver = {
 	.probe		= fimd_probe,
 	.remove		= fimd_remove,
-	.id_table       = fimd_driver_ids,
 	.driver		= {
 		.name	= "exynos4-fb",
 		.owner	= THIS_MODULE,
 		.pm	= &fimd_pm_ops,
-		.of_match_table = of_match_ptr(fimd_driver_dt_match),
+		.of_match_table = fimd_driver_dt_match,
 	},
 };
diff --git a/drivers/gpu/drm/exynos/exynos_drm_g2d.c b/drivers/gpu/drm/exynos/exynos_drm_g2d.c
index eddea4941483..3271fd4b1724 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_g2d.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_g2d.c
@@ -23,6 +23,7 @@
 #include <drm/drmP.h>
 #include <drm/exynos_drm.h>
 #include "exynos_drm_drv.h"
+#include "exynos_drm_g2d.h"
 #include "exynos_drm_gem.h"
 #include "exynos_drm_iommu.h"
 
@@ -446,10 +447,8 @@ static dma_addr_t *g2d_userptr_get_dma_addr(struct drm_device *drm_dev,
 	}
 
 	g2d_userptr = kzalloc(sizeof(*g2d_userptr), GFP_KERNEL);
-	if (!g2d_userptr) {
-		DRM_ERROR("failed to allocate g2d_userptr.\n");
+	if (!g2d_userptr)
 		return ERR_PTR(-ENOMEM);
-	}
 
 	atomic_set(&g2d_userptr->refcount, 1);
 
@@ -499,7 +498,6 @@ static dma_addr_t *g2d_userptr_get_dma_addr(struct drm_device *drm_dev,
 
 	sgt = kzalloc(sizeof(*sgt), GFP_KERNEL);
 	if (!sgt) {
-		DRM_ERROR("failed to allocate sg table.\n");
 		ret = -ENOMEM;
 		goto err_free_userptr;
 	}
@@ -808,17 +806,8 @@ static void g2d_dma_start(struct g2d_data *g2d,
 	int ret;
 
 	ret = pm_runtime_get_sync(g2d->dev);
-	if (ret < 0) {
-		dev_warn(g2d->dev, "failed pm power on.\n");
-		return;
-	}
-
-	ret = clk_prepare_enable(g2d->gate_clk);
-	if (ret < 0) {
-		dev_warn(g2d->dev, "failed to enable clock.\n");
-		pm_runtime_put_sync(g2d->dev);
+	if (ret < 0)
 		return;
-	}
 
 	writel_relaxed(node->dma_addr, g2d->regs + G2D_DMA_SFR_BASE_ADDR);
 	writel_relaxed(G2D_DMA_START, g2d->regs + G2D_DMA_COMMAND);
@@ -871,7 +860,6 @@ static void g2d_runqueue_worker(struct work_struct *work)
 					    runqueue_work);
 
 	mutex_lock(&g2d->runqueue_mutex);
-	clk_disable_unprepare(g2d->gate_clk);
 	pm_runtime_put_sync(g2d->dev);
 
 	complete(&g2d->runqueue_node->complete);
@@ -1096,8 +1084,6 @@ int exynos_g2d_set_cmdlist_ioctl(struct drm_device *drm_dev, void *data,
 
 		e = kzalloc(sizeof(*node->event), GFP_KERNEL);
 		if (!e) {
-			dev_err(dev, "failed to allocate event\n");
-
 			spin_lock_irqsave(&drm_dev->event_lock, flags);
 			file->event_space += sizeof(e->event);
 			spin_unlock_irqrestore(&drm_dev->event_lock, flags);
@@ -1327,10 +1313,8 @@ static int g2d_open(struct drm_device *drm_dev, struct device *dev,
 	struct exynos_drm_g2d_private *g2d_priv;
 
 	g2d_priv = kzalloc(sizeof(*g2d_priv), GFP_KERNEL);
-	if (!g2d_priv) {
-		dev_err(dev, "failed to allocate g2d private data\n");
+	if (!g2d_priv)
 		return -ENOMEM;
-	}
 
 	g2d_priv->dev = dev;
 	file_priv->g2d_priv = g2d_priv;
@@ -1386,10 +1370,8 @@ static int g2d_probe(struct platform_device *pdev)
 	int ret;
 
 	g2d = devm_kzalloc(dev, sizeof(*g2d), GFP_KERNEL);
-	if (!g2d) {
-		dev_err(dev, "failed to allocate driver data\n");
+	if (!g2d)
 		return -ENOMEM;
-	}
 
 	g2d->runqueue_slab = kmem_cache_create("g2d_runqueue_slab",
 			sizeof(struct g2d_runqueue_node), 0, 0, NULL);
@@ -1524,14 +1506,38 @@ static int g2d_resume(struct device *dev)
 }
 #endif
 
-static SIMPLE_DEV_PM_OPS(g2d_pm_ops, g2d_suspend, g2d_resume);
+#ifdef CONFIG_PM_RUNTIME
+static int g2d_runtime_suspend(struct device *dev)
+{
+	struct g2d_data *g2d = dev_get_drvdata(dev);
+
+	clk_disable_unprepare(g2d->gate_clk);
+
+	return 0;
+}
+
+static int g2d_runtime_resume(struct device *dev)
+{
+	struct g2d_data *g2d = dev_get_drvdata(dev);
+	int ret;
+
+	ret = clk_prepare_enable(g2d->gate_clk);
+	if (ret < 0)
+		dev_warn(dev, "failed to enable clock.\n");
+
+	return ret;
+}
+#endif
+
+static const struct dev_pm_ops g2d_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(g2d_suspend, g2d_resume)
+	SET_RUNTIME_PM_OPS(g2d_runtime_suspend, g2d_runtime_resume, NULL)
+};
 
-#ifdef CONFIG_OF
 static const struct of_device_id exynos_g2d_match[] = {
 	{ .compatible = "samsung,exynos5250-g2d" },
 	{},
 };
-#endif
 
 struct platform_driver g2d_driver = {
 	.probe		= g2d_probe,
@@ -1540,6 +1546,6 @@ struct platform_driver g2d_driver = {
 		.name	= "s5p-g2d",
 		.owner	= THIS_MODULE,
 		.pm	= &g2d_pm_ops,
-		.of_match_table = of_match_ptr(exynos_g2d_match),
+		.of_match_table = exynos_g2d_match,
 	},
 };
diff --git a/drivers/gpu/drm/exynos/exynos_drm_gem.c b/drivers/gpu/drm/exynos/exynos_drm_gem.c
index 24c22a8c3364..49f9cd232757 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_gem.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_gem.c
@@ -10,6 +10,7 @@
  */
 
 #include <drm/drmP.h>
+#include <drm/drm_vma_manager.h>
 
 #include <linux/shmem_fs.h>
 #include <drm/exynos_drm.h>
@@ -17,6 +18,7 @@
 #include "exynos_drm_drv.h"
 #include "exynos_drm_gem.h"
 #include "exynos_drm_buf.h"
+#include "exynos_drm_iommu.h"
 
 static unsigned int convert_to_vm_err_msg(int msg)
 {
@@ -135,7 +137,7 @@ void exynos_drm_gem_destroy(struct exynos_drm_gem_obj *exynos_gem_obj)
 	obj = &exynos_gem_obj->base;
 	buf = exynos_gem_obj->buffer;
 
-	DRM_DEBUG_KMS("handle count = %d\n", atomic_read(&obj->handle_count));
+	DRM_DEBUG_KMS("handle count = %d\n", obj->handle_count);
 
 	/*
 	 * do not release memory region from exporter.
@@ -152,8 +154,7 @@ out:
 	exynos_drm_fini_buf(obj->dev, buf);
 	exynos_gem_obj->buffer = NULL;
 
-	if (obj->map_list.map)
-		drm_gem_free_mmap_offset(obj);
+	drm_gem_free_mmap_offset(obj);
 
 	/* release file pointer to gem object. */
 	drm_gem_object_release(obj);
@@ -191,10 +192,8 @@ struct exynos_drm_gem_obj *exynos_drm_gem_init(struct drm_device *dev,
 	int ret;
 
 	exynos_gem_obj = kzalloc(sizeof(*exynos_gem_obj), GFP_KERNEL);
-	if (!exynos_gem_obj) {
-		DRM_ERROR("failed to allocate exynos gem object\n");
+	if (!exynos_gem_obj)
 		return NULL;
-	}
 
 	exynos_gem_obj->size = size;
 	obj = &exynos_gem_obj->base;
@@ -668,6 +667,18 @@ int exynos_drm_gem_dumb_create(struct drm_file *file_priv,
 
 	exynos_gem_obj = exynos_drm_gem_create(dev, EXYNOS_BO_CONTIG |
 						EXYNOS_BO_WC, args->size);
+	/*
+	 * If physically contiguous memory allocation fails and if IOMMU is
+	 * supported then try to get buffer from non physically contiguous
+	 * memory area.
+	 */
+	if (IS_ERR(exynos_gem_obj) && is_drm_iommu_supported(dev)) {
+		dev_warn(dev->dev, "contiguous FB allocation failed, falling back to non-contiguous\n");
+		exynos_gem_obj = exynos_drm_gem_create(dev,
+					EXYNOS_BO_NONCONTIG | EXYNOS_BO_WC,
+					args->size);
+	}
+
 	if (IS_ERR(exynos_gem_obj))
 		return PTR_ERR(exynos_gem_obj);
 
@@ -703,13 +714,11 @@ int exynos_drm_gem_dumb_map_offset(struct drm_file *file_priv,
 		goto unlock;
 	}
 
-	if (!obj->map_list.map) {
-		ret = drm_gem_create_mmap_offset(obj);
-		if (ret)
-			goto out;
-	}
+	ret = drm_gem_create_mmap_offset(obj);
+	if (ret)
+		goto out;
 
-	*offset = (u64)obj->map_list.hash.key << PAGE_SHIFT;
+	*offset = drm_vma_node_offset_addr(&obj->vma_node);
 	DRM_DEBUG_KMS("offset = 0x%lx\n", (unsigned long)*offset);
 
 out:
@@ -719,26 +728,6 @@ unlock:
 	return ret;
 }
 
-int exynos_drm_gem_dumb_destroy(struct drm_file *file_priv,
-				struct drm_device *dev,
-				unsigned int handle)
-{
-	int ret;
-
-	/*
-	 * obj->refcount and obj->handle_count are decreased and
-	 * if both them are 0 then exynos_drm_gem_free_object()
-	 * would be called by callback to release resources.
-	 */
-	ret = drm_gem_handle_delete(file_priv, handle);
-	if (ret < 0) {
-		DRM_ERROR("failed to delete drm_gem_handle.\n");
-		return ret;
-	}
-
-	return 0;
-}
-
 int exynos_drm_gem_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
 	struct drm_gem_object *obj = vma->vm_private_data;
diff --git a/drivers/gpu/drm/exynos/exynos_drm_gem.h b/drivers/gpu/drm/exynos/exynos_drm_gem.h
index 468766bee450..09555afdfe9c 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_gem.h
+++ b/drivers/gpu/drm/exynos/exynos_drm_gem.h
@@ -151,15 +151,6 @@ int exynos_drm_gem_dumb_map_offset(struct drm_file *file_priv,
 				   struct drm_device *dev, uint32_t handle,
 				   uint64_t *offset);
 
-/*
- * destroy memory region allocated.
- *	- a gem handle and physical memory region pointed by a gem object
- *	would be released by drm_gem_handle_delete().
- */
-int exynos_drm_gem_dumb_destroy(struct drm_file *file_priv,
-				struct drm_device *dev,
-				unsigned int handle);
-
 /* page fault handler and mmap fault address(virtual) to physical memory. */
 int exynos_drm_gem_fault(struct vm_area_struct *vma, struct vm_fault *vmf);
 
diff --git a/drivers/gpu/drm/exynos/exynos_drm_gsc.c b/drivers/gpu/drm/exynos/exynos_drm_gsc.c
index 90b8a1a5344c..cd6aebd53bd0 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_gsc.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_gsc.c
@@ -20,6 +20,7 @@
 #include <drm/drmP.h>
 #include <drm/exynos_drm.h>
 #include "regs-gsc.h"
+#include "exynos_drm_drv.h"
 #include "exynos_drm_ipp.h"
 #include "exynos_drm_gsc.h"
 
@@ -1337,10 +1338,8 @@ static int gsc_init_prop_list(struct exynos_drm_ippdrv *ippdrv)
 	struct drm_exynos_ipp_prop_list *prop_list;
 
 	prop_list = devm_kzalloc(ippdrv->dev, sizeof(*prop_list), GFP_KERNEL);
-	if (!prop_list) {
-		DRM_ERROR("failed to alloc property list.\n");
+	if (!prop_list)
 		return -ENOMEM;
-	}
 
 	prop_list->version = 1;
 	prop_list->writeback = 1;
diff --git a/drivers/gpu/drm/exynos/exynos_drm_hdmi.c b/drivers/gpu/drm/exynos/exynos_drm_hdmi.c
index 8d3bc01d6834..8548b974bd59 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_hdmi.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_hdmi.c
@@ -403,10 +403,8 @@ static int exynos_drm_hdmi_probe(struct platform_device *pdev)
 	struct drm_hdmi_context *ctx;
 
 	ctx = devm_kzalloc(dev, sizeof(*ctx), GFP_KERNEL);
-	if (!ctx) {
-		DRM_LOG_KMS("failed to alloc common hdmi context.\n");
+	if (!ctx)
 		return -ENOMEM;
-	}
 
 	subdrv = &ctx->subdrv;
 
diff --git a/drivers/gpu/drm/exynos/exynos_drm_iommu.c b/drivers/gpu/drm/exynos/exynos_drm_iommu.c
index 3799d5c2b5df..fb8db0378274 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_iommu.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_iommu.c
@@ -47,10 +47,16 @@ int drm_create_iommu_mapping(struct drm_device *drm_dev)
 
 	dev->dma_parms = devm_kzalloc(dev, sizeof(*dev->dma_parms),
 					GFP_KERNEL);
+	if (!dev->dma_parms)
+		goto error;
+
 	dma_set_max_seg_size(dev, 0xffffffffu);
 	dev->archdata.mapping = mapping;
 
 	return 0;
+error:
+	arm_iommu_release_mapping(mapping);
+	return -ENOMEM;
 }
 
 /*
@@ -91,6 +97,9 @@ int drm_iommu_attach_device(struct drm_device *drm_dev,
 	subdrv_dev->dma_parms = devm_kzalloc(subdrv_dev,
 					sizeof(*subdrv_dev->dma_parms),
 					GFP_KERNEL);
+	if (!subdrv_dev->dma_parms)
+		return -ENOMEM;
+
 	dma_set_max_seg_size(subdrv_dev, 0xffffffffu);
 
 	ret = arm_iommu_attach_device(subdrv_dev, dev->archdata.mapping);
diff --git a/drivers/gpu/drm/exynos/exynos_drm_ipp.c b/drivers/gpu/drm/exynos/exynos_drm_ipp.c
index d2b6ab4def93..824e0705c8d3 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_ipp.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_ipp.c
@@ -408,10 +408,8 @@ static struct drm_exynos_ipp_cmd_work *ipp_create_cmd_work(void)
 	struct drm_exynos_ipp_cmd_work *cmd_work;
 
 	cmd_work = kzalloc(sizeof(*cmd_work), GFP_KERNEL);
-	if (!cmd_work) {
-		DRM_ERROR("failed to alloc cmd_work.\n");
+	if (!cmd_work)
 		return ERR_PTR(-ENOMEM);
-	}
 
 	INIT_WORK((struct work_struct *)cmd_work, ipp_sched_cmd);
 
@@ -423,10 +421,8 @@ static struct drm_exynos_ipp_event_work *ipp_create_event_work(void)
 	struct drm_exynos_ipp_event_work *event_work;
 
 	event_work = kzalloc(sizeof(*event_work), GFP_KERNEL);
-	if (!event_work) {
-		DRM_ERROR("failed to alloc event_work.\n");
+	if (!event_work)
 		return ERR_PTR(-ENOMEM);
-	}
 
 	INIT_WORK((struct work_struct *)event_work, ipp_sched_event);
 
@@ -482,10 +478,8 @@ int exynos_drm_ipp_set_property(struct drm_device *drm_dev, void *data,
 
 	/* allocate command node */
 	c_node = kzalloc(sizeof(*c_node), GFP_KERNEL);
-	if (!c_node) {
-		DRM_ERROR("failed to allocate map node.\n");
+	if (!c_node)
 		return -ENOMEM;
-	}
 
 	/* create property id */
 	ret = ipp_create_id(&ctx->prop_idr, &ctx->prop_lock, c_node,
@@ -694,10 +688,8 @@ static struct drm_exynos_ipp_mem_node
 	mutex_lock(&c_node->mem_lock);
 
 	m_node = kzalloc(sizeof(*m_node), GFP_KERNEL);
-	if (!m_node) {
-		DRM_ERROR("failed to allocate queue node.\n");
+	if (!m_node)
 		goto err_unlock;
-	}
 
 	/* clear base address for error handling */
 	memset(&buf_info, 0x0, sizeof(buf_info));
@@ -798,9 +790,7 @@ static int ipp_get_event(struct drm_device *drm_dev,
 	DRM_DEBUG_KMS("ops_id[%d]buf_id[%d]\n", qbuf->ops_id, qbuf->buf_id);
 
 	e = kzalloc(sizeof(*e), GFP_KERNEL);
-
 	if (!e) {
-		DRM_ERROR("failed to allocate event.\n");
 		spin_lock_irqsave(&drm_dev->event_lock, flags);
 		file->event_space += sizeof(e->event);
 		spin_unlock_irqrestore(&drm_dev->event_lock, flags);
@@ -1780,10 +1770,8 @@ static int ipp_subdrv_open(struct drm_device *drm_dev, struct device *dev,
 	struct exynos_drm_ipp_private *priv;
 
 	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
-	if (!priv) {
-		DRM_ERROR("failed to allocate priv.\n");
+	if (!priv)
 		return -ENOMEM;
-	}
 	priv->dev = dev;
 	file_priv->ipp_priv = priv;
 
diff --git a/drivers/gpu/drm/exynos/exynos_drm_plane.c b/drivers/gpu/drm/exynos/exynos_drm_plane.c
index 6ee55e68e0a2..fcb0652e77d0 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_plane.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_plane.c
@@ -16,6 +16,7 @@
 #include "exynos_drm_encoder.h"
 #include "exynos_drm_fb.h"
 #include "exynos_drm_gem.h"
+#include "exynos_drm_plane.h"
 
 #define to_exynos_plane(x)	container_of(x, struct exynos_plane, base)
 
@@ -264,10 +265,8 @@ struct drm_plane *exynos_plane_init(struct drm_device *dev,
 	int err;
 
 	exynos_plane = kzalloc(sizeof(struct exynos_plane), GFP_KERNEL);
-	if (!exynos_plane) {
-		DRM_ERROR("failed to allocate plane\n");
+	if (!exynos_plane)
 		return NULL;
-	}
 
 	err = drm_plane_init(dev, &exynos_plane->base, possible_crtcs,
 			      &exynos_plane_funcs, formats, ARRAY_SIZE(formats),
diff --git a/drivers/gpu/drm/exynos/exynos_drm_rotator.c b/drivers/gpu/drm/exynos/exynos_drm_rotator.c
index 49669aa24c45..7b901688defa 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_rotator.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_rotator.c
@@ -21,6 +21,7 @@
 #include <drm/exynos_drm.h>
 #include "regs-rotator.h"
 #include "exynos_drm.h"
+#include "exynos_drm_drv.h"
 #include "exynos_drm_ipp.h"
 
 /*
@@ -471,10 +472,8 @@ static int rotator_init_prop_list(struct exynos_drm_ippdrv *ippdrv)
 	struct drm_exynos_ipp_prop_list *prop_list;
 
 	prop_list = devm_kzalloc(ippdrv->dev, sizeof(*prop_list), GFP_KERNEL);
-	if (!prop_list) {
-		DRM_ERROR("failed to alloc property list.\n");
+	if (!prop_list)
 		return -ENOMEM;
-	}
 
 	prop_list->version = 1;
 	prop_list->flip = (1 << EXYNOS_DRM_FLIP_VERTICAL) |
@@ -631,21 +630,96 @@ static int rotator_ippdrv_start(struct device *dev, enum drm_exynos_ipp_cmd cmd)
 	return 0;
 }
 
+static struct rot_limit_table rot_limit_tbl_4210 = {
+	.ycbcr420_2p = {
+		.min_w = 32,
+		.min_h = 32,
+		.max_w = SZ_64K,
+		.max_h = SZ_64K,
+		.align = 3,
+	},
+	.rgb888 = {
+		.min_w = 8,
+		.min_h = 8,
+		.max_w = SZ_16K,
+		.max_h = SZ_16K,
+		.align = 2,
+	},
+};
+
+static struct rot_limit_table rot_limit_tbl_4x12 = {
+	.ycbcr420_2p = {
+		.min_w = 32,
+		.min_h = 32,
+		.max_w = SZ_32K,
+		.max_h = SZ_32K,
+		.align = 3,
+	},
+	.rgb888 = {
+		.min_w = 8,
+		.min_h = 8,
+		.max_w = SZ_8K,
+		.max_h = SZ_8K,
+		.align = 2,
+	},
+};
+
+static struct rot_limit_table rot_limit_tbl_5250 = {
+	.ycbcr420_2p = {
+		.min_w = 32,
+		.min_h = 32,
+		.max_w = SZ_32K,
+		.max_h = SZ_32K,
+		.align = 3,
+	},
+	.rgb888 = {
+		.min_w = 8,
+		.min_h = 8,
+		.max_w = SZ_8K,
+		.max_h = SZ_8K,
+		.align = 1,
+	},
+};
+
+static const struct of_device_id exynos_rotator_match[] = {
+	{
+		.compatible = "samsung,exynos4210-rotator",
+		.data = &rot_limit_tbl_4210,
+	},
+	{
+		.compatible = "samsung,exynos4212-rotator",
+		.data = &rot_limit_tbl_4x12,
+	},
+	{
+		.compatible = "samsung,exynos5250-rotator",
+		.data = &rot_limit_tbl_5250,
+	},
+	{},
+};
+
 static int rotator_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct rot_context *rot;
 	struct exynos_drm_ippdrv *ippdrv;
+	const struct of_device_id *match;
 	int ret;
 
+	if (!dev->of_node) {
+		dev_err(dev, "cannot find of_node.\n");
+		return -ENODEV;
+	}
+
 	rot = devm_kzalloc(dev, sizeof(*rot), GFP_KERNEL);
-	if (!rot) {
-		dev_err(dev, "failed to allocate rot\n");
+	if (!rot)
 		return -ENOMEM;
-	}
 
-	rot->limit_tbl = (struct rot_limit_table *)
-				platform_get_device_id(pdev)->driver_data;
+	match = of_match_node(exynos_rotator_match, dev->of_node);
+	if (!match) {
+		dev_err(dev, "failed to match node\n");
+		return -ENODEV;
+	}
+	rot->limit_tbl = (struct rot_limit_table *)match->data;
 
 	rot->regs_res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	rot->regs = devm_ioremap_resource(dev, rot->regs_res);
@@ -717,31 +791,6 @@ static int rotator_remove(struct platform_device *pdev)
 	return 0;
 }
 
-static struct rot_limit_table rot_limit_tbl = {
-	.ycbcr420_2p = {
-		.min_w = 32,
-		.min_h = 32,
-		.max_w = SZ_32K,
-		.max_h = SZ_32K,
-		.align = 3,
-	},
-	.rgb888 = {
-		.min_w = 8,
-		.min_h = 8,
-		.max_w = SZ_8K,
-		.max_h = SZ_8K,
-		.align = 2,
-	},
-};
-
-static struct platform_device_id rotator_driver_ids[] = {
-	{
-		.name		= "exynos-rot",
-		.driver_data	= (unsigned long)&rot_limit_tbl,
-	},
-	{},
-};
-
 static int rotator_clk_crtl(struct rot_context *rot, bool enable)
 {
 	if (enable) {
@@ -803,10 +852,10 @@ static const struct dev_pm_ops rotator_pm_ops = {
 struct platform_driver rotator_driver = {
 	.probe		= rotator_probe,
 	.remove		= rotator_remove,
-	.id_table	= rotator_driver_ids,
 	.driver		= {
 		.name	= "exynos-rot",
 		.owner	= THIS_MODULE,
 		.pm	= &rotator_pm_ops,
+		.of_match_table = exynos_rotator_match,
 	},
 };
diff --git a/drivers/gpu/drm/exynos/exynos_drm_vidi.c b/drivers/gpu/drm/exynos/exynos_drm_vidi.c
index c57c56519add..4400330e4449 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_vidi.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_vidi.c
@@ -23,6 +23,7 @@
 #include "exynos_drm_drv.h"
 #include "exynos_drm_crtc.h"
 #include "exynos_drm_encoder.h"
+#include "exynos_drm_vidi.h"
 
 /* vidi has totally three virtual windows. */
 #define WINDOWS_NR		3
diff --git a/drivers/gpu/drm/exynos/exynos_hdmi.c b/drivers/gpu/drm/exynos/exynos_hdmi.c
index 2f5c6942c968..a0e10aeb0e67 100644
--- a/drivers/gpu/drm/exynos/exynos_hdmi.c
+++ b/drivers/gpu/drm/exynos/exynos_hdmi.c
@@ -32,6 +32,7 @@
 #include <linux/clk.h>
 #include <linux/regulator/consumer.h>
 #include <linux/io.h>
+#include <linux/of.h>
 #include <linux/of_gpio.h>
 
 #include <drm/exynos_drm.h>
@@ -1824,10 +1825,8 @@ static int hdmi_resources_init(struct hdmi_context *hdata)
 
 	res->regul_bulk = devm_kzalloc(dev, ARRAY_SIZE(supply) *
 		sizeof(res->regul_bulk[0]), GFP_KERNEL);
-	if (!res->regul_bulk) {
-		DRM_ERROR("failed to get memory for regulators\n");
+	if (!res->regul_bulk)
 		goto fail;
-	}
 	for (i = 0; i < ARRAY_SIZE(supply); ++i) {
 		res->regul_bulk[i].supply = supply[i];
 		res->regul_bulk[i].consumer = NULL;
@@ -1859,7 +1858,6 @@ void hdmi_attach_hdmiphy_client(struct i2c_client *hdmiphy)
 		hdmi_hdmiphy = hdmiphy;
 }
 
-#ifdef CONFIG_OF
 static struct s5p_hdmi_platform_data *drm_hdmi_dt_parse_pdata
 					(struct device *dev)
 {
@@ -1868,10 +1866,8 @@ static struct s5p_hdmi_platform_data *drm_hdmi_dt_parse_pdata
 	u32 value;
 
 	pd = devm_kzalloc(dev, sizeof(*pd), GFP_KERNEL);
-	if (!pd) {
-		DRM_ERROR("memory allocation for pdata failed\n");
+	if (!pd)
 		goto err_data;
-	}
 
 	if (!of_find_property(np, "hpd-gpio", &value)) {
 		DRM_ERROR("no hpd gpio property found\n");
@@ -1885,33 +1881,7 @@ static struct s5p_hdmi_platform_data *drm_hdmi_dt_parse_pdata
 err_data:
 	return NULL;
 }
-#else
-static struct s5p_hdmi_platform_data *drm_hdmi_dt_parse_pdata
-					(struct device *dev)
-{
-	return NULL;
-}
-#endif
-
-static struct platform_device_id hdmi_driver_types[] = {
-	{
-		.name		= "s5pv210-hdmi",
-		.driver_data    = HDMI_TYPE13,
-	}, {
-		.name		= "exynos4-hdmi",
-		.driver_data    = HDMI_TYPE13,
-	}, {
-		.name		= "exynos4-hdmi14",
-		.driver_data	= HDMI_TYPE14,
-	}, {
-		.name		= "exynos5-hdmi",
-		.driver_data	= HDMI_TYPE14,
-	}, {
-		/* end node */
-	}
-};
 
-#ifdef CONFIG_OF
 static struct of_device_id hdmi_match_types[] = {
 	{
 		.compatible = "samsung,exynos5-hdmi",
@@ -1923,7 +1893,6 @@ static struct of_device_id hdmi_match_types[] = {
 		/* end node */
 	}
 };
-#endif
 
 static int hdmi_probe(struct platform_device *pdev)
 {
@@ -1932,36 +1901,23 @@ static int hdmi_probe(struct platform_device *pdev)
 	struct hdmi_context *hdata;
 	struct s5p_hdmi_platform_data *pdata;
 	struct resource *res;
+	const struct of_device_id *match;
 	int ret;
 
-	if (dev->of_node) {
-		pdata = drm_hdmi_dt_parse_pdata(dev);
-		if (IS_ERR(pdata)) {
-			DRM_ERROR("failed to parse dt\n");
-			return PTR_ERR(pdata);
-		}
-	} else {
-		pdata = dev->platform_data;
-	}
+	 if (!dev->of_node)
+		return -ENODEV;
 
-	if (!pdata) {
-		DRM_ERROR("no platform data specified\n");
+	pdata = drm_hdmi_dt_parse_pdata(dev);
+	if (!pdata)
 		return -EINVAL;
-	}
 
-	drm_hdmi_ctx = devm_kzalloc(dev, sizeof(*drm_hdmi_ctx),
-								GFP_KERNEL);
-	if (!drm_hdmi_ctx) {
-		DRM_ERROR("failed to allocate common hdmi context.\n");
+	drm_hdmi_ctx = devm_kzalloc(dev, sizeof(*drm_hdmi_ctx), GFP_KERNEL);
+	if (!drm_hdmi_ctx)
 		return -ENOMEM;
-	}
 
-	hdata = devm_kzalloc(dev, sizeof(struct hdmi_context),
-								GFP_KERNEL);
-	if (!hdata) {
-		DRM_ERROR("out of memory\n");
+	hdata = devm_kzalloc(dev, sizeof(struct hdmi_context), GFP_KERNEL);
+	if (!hdata)
 		return -ENOMEM;
-	}
 
 	mutex_init(&hdata->hdmi_mutex);
 
@@ -1970,23 +1926,15 @@ static int hdmi_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, drm_hdmi_ctx);
 
-	if (dev->of_node) {
-		const struct of_device_id *match;
-		match = of_match_node(of_match_ptr(hdmi_match_types),
-					dev->of_node);
-		if (match == NULL)
-			return -ENODEV;
-		hdata->type = (enum hdmi_type)match->data;
-	} else {
-		hdata->type = (enum hdmi_type)platform_get_device_id
-					(pdev)->driver_data;
-	}
+	match = of_match_node(hdmi_match_types, dev->of_node);
+	if (!match)
+		return -ENODEV;
+	hdata->type = (enum hdmi_type)match->data;
 
 	hdata->hpd_gpio = pdata->hpd_gpio;
 	hdata->dev = dev;
 
 	ret = hdmi_resources_init(hdata);
-
 	if (ret) {
 		DRM_ERROR("hdmi_resources_init failed\n");
 		return -EINVAL;
@@ -2141,11 +2089,10 @@ static const struct dev_pm_ops hdmi_pm_ops = {
 struct platform_driver hdmi_driver = {
 	.probe		= hdmi_probe,
 	.remove		= hdmi_remove,
-	.id_table = hdmi_driver_types,
 	.driver		= {
 		.name	= "exynos-hdmi",
 		.owner	= THIS_MODULE,
 		.pm	= &hdmi_pm_ops,
-		.of_match_table = of_match_ptr(hdmi_match_types),
+		.of_match_table = hdmi_match_types,
 	},
 };
diff --git a/drivers/gpu/drm/exynos/exynos_hdmiphy.c b/drivers/gpu/drm/exynos/exynos_hdmiphy.c
index 6e320ae9afed..59abb1494ceb 100644
--- a/drivers/gpu/drm/exynos/exynos_hdmiphy.c
+++ b/drivers/gpu/drm/exynos/exynos_hdmiphy.c
@@ -15,6 +15,7 @@
 
 #include <linux/kernel.h>
 #include <linux/i2c.h>
+#include <linux/of.h>
 
 #include "exynos_drm_drv.h"
 #include "exynos_hdmi.h"
@@ -39,13 +40,6 @@ static int hdmiphy_remove(struct i2c_client *client)
 	return 0;
 }
 
-static const struct i2c_device_id hdmiphy_id[] = {
-	{ "s5p_hdmiphy", 0 },
-	{ "exynos5-hdmiphy", 0 },
-	{ },
-};
-
-#ifdef CONFIG_OF
 static struct of_device_id hdmiphy_match_types[] = {
 	{
 		.compatible = "samsung,exynos5-hdmiphy",
@@ -57,15 +51,13 @@ static struct of_device_id hdmiphy_match_types[] = {
 		/* end node */
 	}
 };
-#endif
 
 struct i2c_driver hdmiphy_driver = {
 	.driver = {
 		.name	= "exynos-hdmiphy",
 		.owner	= THIS_MODULE,
-		.of_match_table = of_match_ptr(hdmiphy_match_types),
+		.of_match_table = hdmiphy_match_types,
 	},
-	.id_table = hdmiphy_id,
 	.probe		= hdmiphy_probe,
 	.remove		= hdmiphy_remove,
 	.command		= NULL,
diff --git a/drivers/gpu/drm/exynos/exynos_mixer.c b/drivers/gpu/drm/exynos/exynos_mixer.c
index c9a137caea41..63bc5f92fbb3 100644
--- a/drivers/gpu/drm/exynos/exynos_mixer.c
+++ b/drivers/gpu/drm/exynos/exynos_mixer.c
@@ -30,6 +30,7 @@
 #include <linux/pm_runtime.h>
 #include <linux/clk.h>
 #include <linux/regulator/consumer.h>
+#include <linux/of.h>
 
 #include <drm/exynos_drm.h>
 
@@ -1185,16 +1186,12 @@ static int mixer_probe(struct platform_device *pdev)
 
 	drm_hdmi_ctx = devm_kzalloc(dev, sizeof(*drm_hdmi_ctx),
 								GFP_KERNEL);
-	if (!drm_hdmi_ctx) {
-		DRM_ERROR("failed to allocate common hdmi context.\n");
+	if (!drm_hdmi_ctx)
 		return -ENOMEM;
-	}
 
 	ctx = devm_kzalloc(dev, sizeof(*ctx), GFP_KERNEL);
-	if (!ctx) {
-		DRM_ERROR("failed to alloc mixer context.\n");
+	if (!ctx)
 		return -ENOMEM;
-	}
 
 	mutex_init(&ctx->mixer_mutex);
 
diff --git a/drivers/gpu/drm/gma500/Makefile b/drivers/gpu/drm/gma500/Makefile
index 7a2d40a5c1e1..e9064dd9045d 100644
--- a/drivers/gpu/drm/gma500/Makefile
+++ b/drivers/gpu/drm/gma500/Makefile
@@ -15,6 +15,7 @@ gma500_gfx-y += \
 	  mmu.o \
 	  power.o \
 	  psb_drv.o \
+	  gma_display.o \
 	  psb_intel_display.o \
 	  psb_intel_lvds.o \
 	  psb_intel_modes.o \
diff --git a/drivers/gpu/drm/gma500/cdv_device.c b/drivers/gpu/drm/gma500/cdv_device.c
index 23e14e93991f..162f686c532d 100644
--- a/drivers/gpu/drm/gma500/cdv_device.c
+++ b/drivers/gpu/drm/gma500/cdv_device.c
@@ -641,6 +641,7 @@ const struct psb_ops cdv_chip_ops = {
 
 	.crtc_helper = &cdv_intel_helper_funcs,
 	.crtc_funcs = &cdv_intel_crtc_funcs,
+	.clock_funcs = &cdv_clock_funcs,
 
 	.output_init = cdv_output_init,
 	.hotplug = cdv_hotplug_event,
@@ -655,4 +656,6 @@ const struct psb_ops cdv_chip_ops = {
 	.restore_regs = cdv_restore_display_registers,
 	.power_down = cdv_power_down,
 	.power_up = cdv_power_up,
+	.update_wm = cdv_update_wm,
+	.disable_sr = cdv_disable_sr,
 };
diff --git a/drivers/gpu/drm/gma500/cdv_device.h b/drivers/gpu/drm/gma500/cdv_device.h
index 9561e17621b3..705c11d47d45 100644
--- a/drivers/gpu/drm/gma500/cdv_device.h
+++ b/drivers/gpu/drm/gma500/cdv_device.h
@@ -17,6 +17,7 @@
 
 extern const struct drm_crtc_helper_funcs cdv_intel_helper_funcs;
 extern const struct drm_crtc_funcs cdv_intel_crtc_funcs;
+extern const struct gma_clock_funcs cdv_clock_funcs;
 extern void cdv_intel_crt_init(struct drm_device *dev,
 			struct psb_intel_mode_device *mode_dev);
 extern void cdv_intel_lvds_init(struct drm_device *dev,
@@ -25,12 +26,5 @@ extern void cdv_hdmi_init(struct drm_device *dev, struct psb_intel_mode_device *
 			int reg);
 extern struct drm_display_mode *cdv_intel_crtc_mode_get(struct drm_device *dev,
 					     struct drm_crtc *crtc);
-
-static inline void cdv_intel_wait_for_vblank(struct drm_device *dev)
-{
-	/* Wait for 20ms, i.e. one cycle at 50hz. */
-        /* FIXME: msleep ?? */
-	mdelay(20);
-}
-
-
+extern void cdv_update_wm(struct drm_device *dev, struct drm_crtc *crtc);
+extern void cdv_disable_sr(struct drm_device *dev);
diff --git a/drivers/gpu/drm/gma500/cdv_intel_crt.c b/drivers/gpu/drm/gma500/cdv_intel_crt.c
index 7b8386fc3024..661af492173d 100644
--- a/drivers/gpu/drm/gma500/cdv_intel_crt.c
+++ b/drivers/gpu/drm/gma500/cdv_intel_crt.c
@@ -95,13 +95,12 @@ static void cdv_intel_crt_mode_set(struct drm_encoder *encoder,
 
 	struct drm_device *dev = encoder->dev;
 	struct drm_crtc *crtc = encoder->crtc;
-	struct psb_intel_crtc *psb_intel_crtc =
-					to_psb_intel_crtc(crtc);
+	struct gma_crtc *gma_crtc = to_gma_crtc(crtc);
 	int dpll_md_reg;
 	u32 adpa, dpll_md;
 	u32 adpa_reg;
 
-	if (psb_intel_crtc->pipe == 0)
+	if (gma_crtc->pipe == 0)
 		dpll_md_reg = DPLL_A_MD;
 	else
 		dpll_md_reg = DPLL_B_MD;
@@ -124,7 +123,7 @@ static void cdv_intel_crt_mode_set(struct drm_encoder *encoder,
 	if (adjusted_mode->flags & DRM_MODE_FLAG_PVSYNC)
 		adpa |= ADPA_VSYNC_ACTIVE_HIGH;
 
-	if (psb_intel_crtc->pipe == 0)
+	if (gma_crtc->pipe == 0)
 		adpa |= ADPA_PIPE_A_SELECT;
 	else
 		adpa |= ADPA_PIPE_B_SELECT;
@@ -197,10 +196,9 @@ static enum drm_connector_status cdv_intel_crt_detect(
 
 static void cdv_intel_crt_destroy(struct drm_connector *connector)
 {
-	struct psb_intel_encoder *psb_intel_encoder =
-					psb_intel_attached_encoder(connector);
+	struct gma_encoder *gma_encoder = gma_attached_encoder(connector);
 
-	psb_intel_i2c_destroy(psb_intel_encoder->ddc_bus);
+	psb_intel_i2c_destroy(gma_encoder->ddc_bus);
 	drm_sysfs_connector_remove(connector);
 	drm_connector_cleanup(connector);
 	kfree(connector);
@@ -208,9 +206,9 @@ static void cdv_intel_crt_destroy(struct drm_connector *connector)
 
 static int cdv_intel_crt_get_modes(struct drm_connector *connector)
 {
-	struct psb_intel_encoder *psb_intel_encoder =
-				psb_intel_attached_encoder(connector);
-	return psb_intel_ddc_get_modes(connector, &psb_intel_encoder->ddc_bus->adapter);
+	struct gma_encoder *gma_encoder = gma_attached_encoder(connector);
+	return psb_intel_ddc_get_modes(connector,
+				       &gma_encoder->ddc_bus->adapter);
 }
 
 static int cdv_intel_crt_set_property(struct drm_connector *connector,
@@ -227,8 +225,8 @@ static int cdv_intel_crt_set_property(struct drm_connector *connector,
 static const struct drm_encoder_helper_funcs cdv_intel_crt_helper_funcs = {
 	.dpms = cdv_intel_crt_dpms,
 	.mode_fixup = cdv_intel_crt_mode_fixup,
-	.prepare = psb_intel_encoder_prepare,
-	.commit = psb_intel_encoder_commit,
+	.prepare = gma_encoder_prepare,
+	.commit = gma_encoder_commit,
 	.mode_set = cdv_intel_crt_mode_set,
 };
 
@@ -244,7 +242,7 @@ static const struct drm_connector_helper_funcs
 				cdv_intel_crt_connector_helper_funcs = {
 	.mode_valid = cdv_intel_crt_mode_valid,
 	.get_modes = cdv_intel_crt_get_modes,
-	.best_encoder = psb_intel_best_encoder,
+	.best_encoder = gma_best_encoder,
 };
 
 static void cdv_intel_crt_enc_destroy(struct drm_encoder *encoder)
@@ -260,32 +258,31 @@ void cdv_intel_crt_init(struct drm_device *dev,
 			struct psb_intel_mode_device *mode_dev)
 {
 
-	struct psb_intel_connector *psb_intel_connector;
-	struct psb_intel_encoder *psb_intel_encoder;
+	struct gma_connector *gma_connector;
+	struct gma_encoder *gma_encoder;
 	struct drm_connector *connector;
 	struct drm_encoder *encoder;
 
 	u32 i2c_reg;
 
-	psb_intel_encoder = kzalloc(sizeof(struct psb_intel_encoder), GFP_KERNEL);
-	if (!psb_intel_encoder)
+	gma_encoder = kzalloc(sizeof(struct gma_encoder), GFP_KERNEL);
+	if (!gma_encoder)
 		return;
 
-	psb_intel_connector = kzalloc(sizeof(struct psb_intel_connector), GFP_KERNEL);
-	if (!psb_intel_connector)
+	gma_connector = kzalloc(sizeof(struct gma_connector), GFP_KERNEL);
+	if (!gma_connector)
 		goto failed_connector;
 
-	connector = &psb_intel_connector->base;
+	connector = &gma_connector->base;
 	connector->polled = DRM_CONNECTOR_POLL_HPD;
 	drm_connector_init(dev, connector,
 		&cdv_intel_crt_connector_funcs, DRM_MODE_CONNECTOR_VGA);
 
-	encoder = &psb_intel_encoder->base;
+	encoder = &gma_encoder->base;
 	drm_encoder_init(dev, encoder,
 		&cdv_intel_crt_enc_funcs, DRM_MODE_ENCODER_DAC);
 
-	psb_intel_connector_attach_encoder(psb_intel_connector,
-					   psb_intel_encoder);
+	gma_connector_attach_encoder(gma_connector, gma_encoder);
 
 	/* Set up the DDC bus. */
 	i2c_reg = GPIOA;
@@ -294,15 +291,15 @@ void cdv_intel_crt_init(struct drm_device *dev,
 	if (dev_priv->crt_ddc_bus != 0)
 		i2c_reg = dev_priv->crt_ddc_bus;
 	}*/
-	psb_intel_encoder->ddc_bus = psb_intel_i2c_create(dev,
+	gma_encoder->ddc_bus = psb_intel_i2c_create(dev,
 							  i2c_reg, "CRTDDC_A");
-	if (!psb_intel_encoder->ddc_bus) {
+	if (!gma_encoder->ddc_bus) {
 		dev_printk(KERN_ERR, &dev->pdev->dev, "DDC bus registration "
 			   "failed.\n");
 		goto failed_ddc;
 	}
 
-	psb_intel_encoder->type = INTEL_OUTPUT_ANALOG;
+	gma_encoder->type = INTEL_OUTPUT_ANALOG;
 	/*
 	psb_intel_output->clone_mask = (1 << INTEL_ANALOG_CLONE_BIT);
 	psb_intel_output->crtc_mask = (1 << 0) | (1 << 1);
@@ -318,10 +315,10 @@ void cdv_intel_crt_init(struct drm_device *dev,
 
 	return;
 failed_ddc:
-	drm_encoder_cleanup(&psb_intel_encoder->base);
-	drm_connector_cleanup(&psb_intel_connector->base);
-	kfree(psb_intel_connector);
+	drm_encoder_cleanup(&gma_encoder->base);
+	drm_connector_cleanup(&gma_connector->base);
+	kfree(gma_connector);
 failed_connector:
-	kfree(psb_intel_encoder);
+	kfree(gma_encoder);
 	return;
 }
diff --git a/drivers/gpu/drm/gma500/cdv_intel_display.c b/drivers/gpu/drm/gma500/cdv_intel_display.c
index 82430ad8ba62..8fbfa06da62d 100644
--- a/drivers/gpu/drm/gma500/cdv_intel_display.c
+++ b/drivers/gpu/drm/gma500/cdv_intel_display.c
@@ -19,54 +19,20 @@
  */
 
 #include <linux/i2c.h>
-#include <linux/pm_runtime.h>
 
 #include <drm/drmP.h>
 #include "framebuffer.h"
 #include "psb_drv.h"
 #include "psb_intel_drv.h"
 #include "psb_intel_reg.h"
-#include "psb_intel_display.h"
+#include "gma_display.h"
 #include "power.h"
 #include "cdv_device.h"
 
+static bool cdv_intel_find_dp_pll(const struct gma_limit_t *limit,
+				  struct drm_crtc *crtc, int target,
+				  int refclk, struct gma_clock_t *best_clock);
 
-struct cdv_intel_range_t {
-	int min, max;
-};
-
-struct cdv_intel_p2_t {
-	int dot_limit;
-	int p2_slow, p2_fast;
-};
-
-struct cdv_intel_clock_t {
-	/* given values */
-	int n;
-	int m1, m2;
-	int p1, p2;
-	/* derived values */
-	int dot;
-	int vco;
-	int m;
-	int p;
-};
-
-#define INTEL_P2_NUM		      2
-
-struct cdv_intel_limit_t {
-	struct cdv_intel_range_t dot, vco, n, m, m1, m2, p, p1;
-	struct cdv_intel_p2_t p2;
-	bool (*find_pll)(const struct cdv_intel_limit_t *, struct drm_crtc *,
-			int, int, struct cdv_intel_clock_t *);
-};
-
-static bool cdv_intel_find_best_PLL(const struct cdv_intel_limit_t *limit,
-	struct drm_crtc *crtc, int target, int refclk,
-	struct cdv_intel_clock_t *best_clock);
-static bool cdv_intel_find_dp_pll(const struct cdv_intel_limit_t *limit, struct drm_crtc *crtc, int target,
-				int refclk,
-				struct cdv_intel_clock_t *best_clock);
 
 #define CDV_LIMIT_SINGLE_LVDS_96	0
 #define CDV_LIMIT_SINGLE_LVDS_100	1
@@ -75,7 +41,7 @@ static bool cdv_intel_find_dp_pll(const struct cdv_intel_limit_t *limit, struct
 #define CDV_LIMIT_DP_27			4
 #define CDV_LIMIT_DP_100		5
 
-static const struct cdv_intel_limit_t cdv_intel_limits[] = {
+static const struct gma_limit_t cdv_intel_limits[] = {
 	{			/* CDV_SINGLE_LVDS_96MHz */
 	 .dot = {.min = 20000, .max = 115500},
 	 .vco = {.min = 1800000, .max = 3600000},
@@ -85,9 +51,8 @@ static const struct cdv_intel_limit_t cdv_intel_limits[] = {
 	 .m2 = {.min = 58, .max = 158},
 	 .p = {.min = 28, .max = 140},
 	 .p1 = {.min = 2, .max = 10},
-	 .p2 = {.dot_limit = 200000,
-		.p2_slow = 14, .p2_fast = 14},
-		.find_pll = cdv_intel_find_best_PLL,
+	 .p2 = {.dot_limit = 200000, .p2_slow = 14, .p2_fast = 14},
+	 .find_pll = gma_find_best_pll,
 	 },
 	{			/* CDV_SINGLE_LVDS_100MHz */
 	 .dot = {.min = 20000, .max = 115500},
@@ -102,7 +67,7 @@ static const struct cdv_intel_limit_t cdv_intel_limits[] = {
 	  * is 80-224Mhz.  Prefer single channel as much as possible.
 	  */
 	 .p2 = {.dot_limit = 200000, .p2_slow = 14, .p2_fast = 14},
-	.find_pll = cdv_intel_find_best_PLL,
+	 .find_pll = gma_find_best_pll,
 	 },
 	{			/* CDV_DAC_HDMI_27MHz */
 	 .dot = {.min = 20000, .max = 400000},
@@ -114,7 +79,7 @@ static const struct cdv_intel_limit_t cdv_intel_limits[] = {
 	 .p = {.min = 5, .max = 90},
 	 .p1 = {.min = 1, .max = 9},
 	 .p2 = {.dot_limit = 225000, .p2_slow = 10, .p2_fast = 5},
-	.find_pll = cdv_intel_find_best_PLL,
+	 .find_pll = gma_find_best_pll,
 	 },
 	{			/* CDV_DAC_HDMI_96MHz */
 	 .dot = {.min = 20000, .max = 400000},
@@ -126,7 +91,7 @@ static const struct cdv_intel_limit_t cdv_intel_limits[] = {
 	 .p = {.min = 5, .max = 100},
 	 .p1 = {.min = 1, .max = 10},
 	 .p2 = {.dot_limit = 225000, .p2_slow = 10, .p2_fast = 5},
-	.find_pll = cdv_intel_find_best_PLL,
+	 .find_pll = gma_find_best_pll,
 	 },
 	{			/* CDV_DP_27MHz */
 	 .dot = {.min = 160000, .max = 272000},
@@ -255,10 +220,10 @@ void cdv_sb_reset(struct drm_device *dev)
  */
 static int
 cdv_dpll_set_clock_cdv(struct drm_device *dev, struct drm_crtc *crtc,
-			       struct cdv_intel_clock_t *clock, bool is_lvds, u32 ddi_select)
+		       struct gma_clock_t *clock, bool is_lvds, u32 ddi_select)
 {
-	struct psb_intel_crtc *psb_crtc = to_psb_intel_crtc(crtc);
-	int pipe = psb_crtc->pipe;
+	struct gma_crtc *gma_crtc = to_gma_crtc(crtc);
+	int pipe = gma_crtc->pipe;
 	u32 m, n_vco, p;
 	int ret = 0;
 	int dpll_reg = (pipe == 0) ? DPLL_A : DPLL_B;
@@ -405,31 +370,11 @@ cdv_dpll_set_clock_cdv(struct drm_device *dev, struct drm_crtc *crtc,
 	return 0;
 }
 
-/*
- * Returns whether any encoder on the specified pipe is of the specified type
- */
-static bool cdv_intel_pipe_has_type(struct drm_crtc *crtc, int type)
-{
-	struct drm_device *dev = crtc->dev;
-	struct drm_mode_config *mode_config = &dev->mode_config;
-	struct drm_connector *l_entry;
-
-	list_for_each_entry(l_entry, &mode_config->connector_list, head) {
-		if (l_entry->encoder && l_entry->encoder->crtc == crtc) {
-			struct psb_intel_encoder *psb_intel_encoder =
-					psb_intel_attached_encoder(l_entry);
-			if (psb_intel_encoder->type == type)
-				return true;
-		}
-	}
-	return false;
-}
-
-static const struct cdv_intel_limit_t *cdv_intel_limit(struct drm_crtc *crtc,
-							int refclk)
+static const struct gma_limit_t *cdv_intel_limit(struct drm_crtc *crtc,
+						 int refclk)
 {
-	const struct cdv_intel_limit_t *limit;
-	if (cdv_intel_pipe_has_type(crtc, INTEL_OUTPUT_LVDS)) {
+	const struct gma_limit_t *limit;
+	if (gma_pipe_has_type(crtc, INTEL_OUTPUT_LVDS)) {
 		/*
 		 * Now only single-channel LVDS is supported on CDV. If it is
 		 * incorrect, please add the dual-channel LVDS.
@@ -438,8 +383,8 @@ static const struct cdv_intel_limit_t *cdv_intel_limit(struct drm_crtc *crtc,
 			limit = &cdv_intel_limits[CDV_LIMIT_SINGLE_LVDS_96];
 		else
 			limit = &cdv_intel_limits[CDV_LIMIT_SINGLE_LVDS_100];
-	} else if (psb_intel_pipe_has_type(crtc, INTEL_OUTPUT_DISPLAYPORT) ||
-			psb_intel_pipe_has_type(crtc, INTEL_OUTPUT_EDP)) {
+	} else if (gma_pipe_has_type(crtc, INTEL_OUTPUT_DISPLAYPORT) ||
+			gma_pipe_has_type(crtc, INTEL_OUTPUT_EDP)) {
 		if (refclk == 27000)
 			limit = &cdv_intel_limits[CDV_LIMIT_DP_27];
 		else
@@ -454,8 +399,7 @@ static const struct cdv_intel_limit_t *cdv_intel_limit(struct drm_crtc *crtc,
 }
 
 /* m1 is reserved as 0 in CDV, n is a ring counter */
-static void cdv_intel_clock(struct drm_device *dev,
-			int refclk, struct cdv_intel_clock_t *clock)
+static void cdv_intel_clock(int refclk, struct gma_clock_t *clock)
 {
 	clock->m = clock->m2 + 2;
 	clock->p = clock->p1 * clock->p2;
@@ -463,93 +407,12 @@ static void cdv_intel_clock(struct drm_device *dev,
 	clock->dot = clock->vco / clock->p;
 }
 
-
-#define INTELPllInvalid(s)   { /* ErrorF (s) */; return false; }
-static bool cdv_intel_PLL_is_valid(struct drm_crtc *crtc,
-				const struct cdv_intel_limit_t *limit,
-			       struct cdv_intel_clock_t *clock)
-{
-	if (clock->p1 < limit->p1.min || limit->p1.max < clock->p1)
-		INTELPllInvalid("p1 out of range\n");
-	if (clock->p < limit->p.min || limit->p.max < clock->p)
-		INTELPllInvalid("p out of range\n");
-	/* unnecessary to check the range of m(m1/M2)/n again */
-	if (clock->vco < limit->vco.min || limit->vco.max < clock->vco)
-		INTELPllInvalid("vco out of range\n");
-	/* XXX: We may need to be checking "Dot clock"
-	 * depending on the multiplier, connector, etc.,
-	 * rather than just a single range.
-	 */
-	if (clock->dot < limit->dot.min || limit->dot.max < clock->dot)
-		INTELPllInvalid("dot out of range\n");
-
-	return true;
-}
-
-static bool cdv_intel_find_best_PLL(const struct cdv_intel_limit_t *limit,
-	struct drm_crtc *crtc, int target, int refclk,
-	struct cdv_intel_clock_t *best_clock)
+static bool cdv_intel_find_dp_pll(const struct gma_limit_t *limit,
+				  struct drm_crtc *crtc, int target,
+				  int refclk,
+				  struct gma_clock_t *best_clock)
 {
-	struct drm_device *dev = crtc->dev;
-	struct cdv_intel_clock_t clock;
-	int err = target;
-
-
-	if (cdv_intel_pipe_has_type(crtc, INTEL_OUTPUT_LVDS) &&
-	    (REG_READ(LVDS) & LVDS_PORT_EN) != 0) {
-		/*
-		 * For LVDS, if the panel is on, just rely on its current
-		 * settings for dual-channel.  We haven't figured out how to
-		 * reliably set up different single/dual channel state, if we
-		 * even can.
-		 */
-		if ((REG_READ(LVDS) & LVDS_CLKB_POWER_MASK) ==
-		    LVDS_CLKB_POWER_UP)
-			clock.p2 = limit->p2.p2_fast;
-		else
-			clock.p2 = limit->p2.p2_slow;
-	} else {
-		if (target < limit->p2.dot_limit)
-			clock.p2 = limit->p2.p2_slow;
-		else
-			clock.p2 = limit->p2.p2_fast;
-	}
-
-	memset(best_clock, 0, sizeof(*best_clock));
-	clock.m1 = 0;
-	/* m1 is reserved as 0 in CDV, n is a ring counter.
-	   So skip the m1 loop */
-	for (clock.n = limit->n.min; clock.n <= limit->n.max; clock.n++) {
-		for (clock.m2 = limit->m2.min; clock.m2 <= limit->m2.max;
-					     clock.m2++) {
-			for (clock.p1 = limit->p1.min;
-					clock.p1 <= limit->p1.max;
-					clock.p1++) {
-				int this_err;
-
-				cdv_intel_clock(dev, refclk, &clock);
-
-				if (!cdv_intel_PLL_is_valid(crtc,
-								limit, &clock))
-						continue;
-
-				this_err = abs(clock.dot - target);
-				if (this_err < err) {
-					*best_clock = clock;
-					err = this_err;
-				}
-			}
-		}
-	}
-
-	return err != target;
-}
-
-static bool cdv_intel_find_dp_pll(const struct cdv_intel_limit_t *limit, struct drm_crtc *crtc, int target,
-				int refclk,
-				struct cdv_intel_clock_t *best_clock)
-{
-	struct cdv_intel_clock_t clock;
+	struct gma_clock_t clock;
 	if (refclk == 27000) {
 		if (target < 200000) {
 			clock.p1 = 2;
@@ -584,85 +447,10 @@ static bool cdv_intel_find_dp_pll(const struct cdv_intel_limit_t *limit, struct
 	clock.p = clock.p1 * clock.p2;
 	clock.vco = (refclk * clock.m) / clock.n;
 	clock.dot = clock.vco / clock.p;
-	memcpy(best_clock, &clock, sizeof(struct cdv_intel_clock_t));
+	memcpy(best_clock, &clock, sizeof(struct gma_clock_t));
 	return true;
 }
 
-static int cdv_intel_pipe_set_base(struct drm_crtc *crtc,
-			    int x, int y, struct drm_framebuffer *old_fb)
-{
-	struct drm_device *dev = crtc->dev;
-	struct drm_psb_private *dev_priv = dev->dev_private;
-	struct psb_intel_crtc *psb_intel_crtc = to_psb_intel_crtc(crtc);
-	struct psb_framebuffer *psbfb = to_psb_fb(crtc->fb);
-	int pipe = psb_intel_crtc->pipe;
-	const struct psb_offset *map = &dev_priv->regmap[pipe];
-	unsigned long start, offset;
-	u32 dspcntr;
-	int ret = 0;
-
-	if (!gma_power_begin(dev, true))
-		return 0;
-
-	/* no fb bound */
-	if (!crtc->fb) {
-		dev_err(dev->dev, "No FB bound\n");
-		goto psb_intel_pipe_cleaner;
-	}
-
-
-	/* We are displaying this buffer, make sure it is actually loaded
-	   into the GTT */
-	ret = psb_gtt_pin(psbfb->gtt);
-	if (ret < 0)
-		goto psb_intel_pipe_set_base_exit;
-	start = psbfb->gtt->offset;
-	offset = y * crtc->fb->pitches[0] + x * (crtc->fb->bits_per_pixel / 8);
-
-	REG_WRITE(map->stride, crtc->fb->pitches[0]);
-
-	dspcntr = REG_READ(map->cntr);
-	dspcntr &= ~DISPPLANE_PIXFORMAT_MASK;
-
-	switch (crtc->fb->bits_per_pixel) {
-	case 8:
-		dspcntr |= DISPPLANE_8BPP;
-		break;
-	case 16:
-		if (crtc->fb->depth == 15)
-			dspcntr |= DISPPLANE_15_16BPP;
-		else
-			dspcntr |= DISPPLANE_16BPP;
-		break;
-	case 24:
-	case 32:
-		dspcntr |= DISPPLANE_32BPP_NO_ALPHA;
-		break;
-	default:
-		dev_err(dev->dev, "Unknown color depth\n");
-		ret = -EINVAL;
-		goto psb_intel_pipe_set_base_exit;
-	}
-	REG_WRITE(map->cntr, dspcntr);
-
-	dev_dbg(dev->dev,
-		"Writing base %08lX %08lX %d %d\n", start, offset, x, y);
-
-	REG_WRITE(map->base, offset);
-	REG_READ(map->base);
-	REG_WRITE(map->surf, start);
-	REG_READ(map->surf);
-
-psb_intel_pipe_cleaner:
-	/* If there was a previous display we can now unpin it */
-	if (old_fb)
-		psb_gtt_unpin(to_psb_fb(old_fb)->gtt);
-
-psb_intel_pipe_set_base_exit:
-	gma_power_end(dev);
-	return ret;
-}
-
 #define		FIFO_PIPEA		(1 << 0)
 #define		FIFO_PIPEB		(1 << 1)
 
@@ -670,12 +458,12 @@ static bool cdv_intel_pipe_enabled(struct drm_device *dev, int pipe)
 {
 	struct drm_crtc *crtc;
 	struct drm_psb_private *dev_priv = dev->dev_private;
-	struct psb_intel_crtc *psb_intel_crtc = NULL;
+	struct gma_crtc *gma_crtc = NULL;
 
 	crtc = dev_priv->pipe_to_crtc_mapping[pipe];
-	psb_intel_crtc = to_psb_intel_crtc(crtc);
+	gma_crtc = to_gma_crtc(crtc);
 
-	if (crtc->fb == NULL || !psb_intel_crtc->active)
+	if (crtc->fb == NULL || !gma_crtc->active)
 		return false;
 	return true;
 }
@@ -701,29 +489,29 @@ static bool cdv_intel_single_pipe_active (struct drm_device *dev)
 
 static bool is_pipeb_lvds(struct drm_device *dev, struct drm_crtc *crtc)
 {
-	struct psb_intel_crtc *psb_intel_crtc = to_psb_intel_crtc(crtc);
+	struct gma_crtc *gma_crtc = to_gma_crtc(crtc);
 	struct drm_mode_config *mode_config = &dev->mode_config;
 	struct drm_connector *connector;
 
-	if (psb_intel_crtc->pipe != 1)
+	if (gma_crtc->pipe != 1)
 		return false;
 
 	list_for_each_entry(connector, &mode_config->connector_list, head) {
-		struct psb_intel_encoder *psb_intel_encoder =
-					psb_intel_attached_encoder(connector);
+		struct gma_encoder *gma_encoder =
+					gma_attached_encoder(connector);
 
 		if (!connector->encoder
 		    || connector->encoder->crtc != crtc)
 			continue;
 
-		if (psb_intel_encoder->type == INTEL_OUTPUT_LVDS)
+		if (gma_encoder->type == INTEL_OUTPUT_LVDS)
 			return true;
 	}
 
 	return false;
 }
 
-static void cdv_intel_disable_self_refresh (struct drm_device *dev)
+void cdv_disable_sr(struct drm_device *dev)
 {
 	if (REG_READ(FW_BLC_SELF) & FW_BLC_SELF_EN) {
 
@@ -731,7 +519,7 @@ static void cdv_intel_disable_self_refresh (struct drm_device *dev)
 		REG_WRITE(FW_BLC_SELF, (REG_READ(FW_BLC_SELF) & ~FW_BLC_SELF_EN));
 		REG_READ(FW_BLC_SELF);
 
-		cdv_intel_wait_for_vblank(dev);
+		gma_wait_for_vblank(dev);
 
 		/* Cedarview workaround to write ovelay plane, which force to leave
 		 * MAX_FIFO state.
@@ -739,13 +527,14 @@ static void cdv_intel_disable_self_refresh (struct drm_device *dev)
 		REG_WRITE(OV_OVADD, 0/*dev_priv->ovl_offset*/);
 		REG_READ(OV_OVADD);
 
-		cdv_intel_wait_for_vblank(dev);
+		gma_wait_for_vblank(dev);
 	}
 
 }
 
-static void cdv_intel_update_watermark (struct drm_device *dev, struct drm_crtc *crtc)
+void cdv_update_wm(struct drm_device *dev, struct drm_crtc *crtc)
 {
+	struct drm_psb_private *dev_priv = dev->dev_private;
 
 	if (cdv_intel_single_pipe_active(dev)) {
 		u32 fw;
@@ -780,12 +569,12 @@ static void cdv_intel_update_watermark (struct drm_device *dev, struct drm_crtc
 
 		REG_WRITE(DSPFW6, 0x10);
 
-		cdv_intel_wait_for_vblank(dev);
+		gma_wait_for_vblank(dev);
 
 		/* enable self-refresh for single pipe active */
 		REG_WRITE(FW_BLC_SELF, FW_BLC_SELF_EN);
 		REG_READ(FW_BLC_SELF);
-		cdv_intel_wait_for_vblank(dev);
+		gma_wait_for_vblank(dev);
 
 	} else {
 
@@ -797,216 +586,12 @@ static void cdv_intel_update_watermark (struct drm_device *dev, struct drm_crtc
 		REG_WRITE(DSPFW5, 0x01010101);
 		REG_WRITE(DSPFW6, 0x1d0);
 
-		cdv_intel_wait_for_vblank(dev);
-
-		cdv_intel_disable_self_refresh(dev);
-	
-	}
-}
-
-/** Loads the palette/gamma unit for the CRTC with the prepared values */
-static void cdv_intel_crtc_load_lut(struct drm_crtc *crtc)
-{
-	struct drm_device *dev = crtc->dev;
-	struct drm_psb_private *dev_priv = dev->dev_private;
-	struct psb_intel_crtc *psb_intel_crtc = to_psb_intel_crtc(crtc);
-	int palreg = PALETTE_A;
-	int i;
-
-	/* The clocks have to be on to load the palette. */
-	if (!crtc->enabled)
-		return;
-
-	switch (psb_intel_crtc->pipe) {
-	case 0:
-		break;
-	case 1:
-		palreg = PALETTE_B;
-		break;
-	case 2:
-		palreg = PALETTE_C;
-		break;
-	default:
-		dev_err(dev->dev, "Illegal Pipe Number.\n");
-		return;
-	}
-
-	if (gma_power_begin(dev, false)) {
-		for (i = 0; i < 256; i++) {
-			REG_WRITE(palreg + 4 * i,
-				  ((psb_intel_crtc->lut_r[i] +
-				  psb_intel_crtc->lut_adj[i]) << 16) |
-				  ((psb_intel_crtc->lut_g[i] +
-				  psb_intel_crtc->lut_adj[i]) << 8) |
-				  (psb_intel_crtc->lut_b[i] +
-				  psb_intel_crtc->lut_adj[i]));
-		}
-		gma_power_end(dev);
-	} else {
-		for (i = 0; i < 256; i++) {
-			dev_priv->regs.pipe[0].palette[i] =
-				  ((psb_intel_crtc->lut_r[i] +
-				  psb_intel_crtc->lut_adj[i]) << 16) |
-				  ((psb_intel_crtc->lut_g[i] +
-				  psb_intel_crtc->lut_adj[i]) << 8) |
-				  (psb_intel_crtc->lut_b[i] +
-				  psb_intel_crtc->lut_adj[i]);
-		}
-
-	}
-}
-
-/**
- * Sets the power management mode of the pipe and plane.
- *
- * This code should probably grow support for turning the cursor off and back
- * on appropriately at the same time as we're turning the pipe off/on.
- */
-static void cdv_intel_crtc_dpms(struct drm_crtc *crtc, int mode)
-{
-	struct drm_device *dev = crtc->dev;
-	struct drm_psb_private *dev_priv = dev->dev_private;
-	struct psb_intel_crtc *psb_intel_crtc = to_psb_intel_crtc(crtc);
-	int pipe = psb_intel_crtc->pipe;
-	const struct psb_offset *map = &dev_priv->regmap[pipe];
-	u32 temp;
-
-	/* XXX: When our outputs are all unaware of DPMS modes other than off
-	 * and on, we should map those modes to DRM_MODE_DPMS_OFF in the CRTC.
-	 */
-	cdv_intel_disable_self_refresh(dev);
-
-	switch (mode) {
-	case DRM_MODE_DPMS_ON:
-	case DRM_MODE_DPMS_STANDBY:
-	case DRM_MODE_DPMS_SUSPEND:
-		if (psb_intel_crtc->active)
-			break;
-
-		psb_intel_crtc->active = true;
-
-		/* Enable the DPLL */
-		temp = REG_READ(map->dpll);
-		if ((temp & DPLL_VCO_ENABLE) == 0) {
-			REG_WRITE(map->dpll, temp);
-			REG_READ(map->dpll);
-			/* Wait for the clocks to stabilize. */
-			udelay(150);
-			REG_WRITE(map->dpll, temp | DPLL_VCO_ENABLE);
-			REG_READ(map->dpll);
-			/* Wait for the clocks to stabilize. */
-			udelay(150);
-			REG_WRITE(map->dpll, temp | DPLL_VCO_ENABLE);
-			REG_READ(map->dpll);
-			/* Wait for the clocks to stabilize. */
-			udelay(150);
-		}
-
-		/* Jim Bish - switch plan and pipe per scott */
-		/* Enable the plane */
-		temp = REG_READ(map->cntr);
-		if ((temp & DISPLAY_PLANE_ENABLE) == 0) {
-			REG_WRITE(map->cntr,
-				  temp | DISPLAY_PLANE_ENABLE);
-			/* Flush the plane changes */
-			REG_WRITE(map->base, REG_READ(map->base));
-		}
-
-		udelay(150);
-
-		/* Enable the pipe */
-		temp = REG_READ(map->conf);
-		if ((temp & PIPEACONF_ENABLE) == 0)
-			REG_WRITE(map->conf, temp | PIPEACONF_ENABLE);
-
-		temp = REG_READ(map->status);
-		temp &= ~(0xFFFF);
-		temp |= PIPE_FIFO_UNDERRUN;
-		REG_WRITE(map->status, temp);
-		REG_READ(map->status);
-
-		cdv_intel_crtc_load_lut(crtc);
-
-		/* Give the overlay scaler a chance to enable
-		 * if it's on this pipe */
-		/* psb_intel_crtc_dpms_video(crtc, true); TODO */
-		break;
-	case DRM_MODE_DPMS_OFF:
-		if (!psb_intel_crtc->active)
-			break;
-
-		psb_intel_crtc->active = false;
-
-		/* Give the overlay scaler a chance to disable
-		 * if it's on this pipe */
-		/* psb_intel_crtc_dpms_video(crtc, FALSE); TODO */
-
-		/* Disable the VGA plane that we never use */
-		REG_WRITE(VGACNTRL, VGA_DISP_DISABLE);
-
-		/* Jim Bish - changed pipe/plane here as well. */
-
-		drm_vblank_off(dev, pipe);
-		/* Wait for vblank for the disable to take effect */
-		cdv_intel_wait_for_vblank(dev);
-
-		/* Next, disable display pipes */
-		temp = REG_READ(map->conf);
-		if ((temp & PIPEACONF_ENABLE) != 0) {
-			REG_WRITE(map->conf, temp & ~PIPEACONF_ENABLE);
-			REG_READ(map->conf);
-		}
-
-		/* Wait for vblank for the disable to take effect. */
-		cdv_intel_wait_for_vblank(dev);
-
-		udelay(150);
-
-		/* Disable display plane */
-		temp = REG_READ(map->cntr);
-		if ((temp & DISPLAY_PLANE_ENABLE) != 0) {
-			REG_WRITE(map->cntr,
-				  temp & ~DISPLAY_PLANE_ENABLE);
-			/* Flush the plane changes */
-			REG_WRITE(map->base, REG_READ(map->base));
-			REG_READ(map->base);
-		}
-
-		temp = REG_READ(map->dpll);
-		if ((temp & DPLL_VCO_ENABLE) != 0) {
-			REG_WRITE(map->dpll, temp & ~DPLL_VCO_ENABLE);
-			REG_READ(map->dpll);
-		}
+		gma_wait_for_vblank(dev);
 
-		/* Wait for the clocks to turn off. */
-		udelay(150);
-		break;
+		dev_priv->ops->disable_sr(dev);
 	}
-	cdv_intel_update_watermark(dev, crtc);
-	/*Set FIFO Watermarks*/
-	REG_WRITE(DSPARB, 0x3F3E);
-}
-
-static void cdv_intel_crtc_prepare(struct drm_crtc *crtc)
-{
-	struct drm_crtc_helper_funcs *crtc_funcs = crtc->helper_private;
-	crtc_funcs->dpms(crtc, DRM_MODE_DPMS_OFF);
-}
-
-static void cdv_intel_crtc_commit(struct drm_crtc *crtc)
-{
-	struct drm_crtc_helper_funcs *crtc_funcs = crtc->helper_private;
-	crtc_funcs->dpms(crtc, DRM_MODE_DPMS_ON);
-}
-
-static bool cdv_intel_crtc_mode_fixup(struct drm_crtc *crtc,
-				  const struct drm_display_mode *mode,
-				  struct drm_display_mode *adjusted_mode)
-{
-	return true;
 }
 
-
 /**
  * Return the pipe currently connected to the panel fitter,
  * or -1 if the panel fitter is not present or not in use
@@ -1031,31 +616,31 @@ static int cdv_intel_crtc_mode_set(struct drm_crtc *crtc,
 {
 	struct drm_device *dev = crtc->dev;
 	struct drm_psb_private *dev_priv = dev->dev_private;
-	struct psb_intel_crtc *psb_intel_crtc = to_psb_intel_crtc(crtc);
-	int pipe = psb_intel_crtc->pipe;
+	struct gma_crtc *gma_crtc = to_gma_crtc(crtc);
+	int pipe = gma_crtc->pipe;
 	const struct psb_offset *map = &dev_priv->regmap[pipe];
 	int refclk;
-	struct cdv_intel_clock_t clock;
+	struct gma_clock_t clock;
 	u32 dpll = 0, dspcntr, pipeconf;
 	bool ok;
 	bool is_crt = false, is_lvds = false, is_tv = false;
 	bool is_hdmi = false, is_dp = false;
 	struct drm_mode_config *mode_config = &dev->mode_config;
 	struct drm_connector *connector;
-	const struct cdv_intel_limit_t *limit;
+	const struct gma_limit_t *limit;
 	u32 ddi_select = 0;
 	bool is_edp = false;
 
 	list_for_each_entry(connector, &mode_config->connector_list, head) {
-		struct psb_intel_encoder *psb_intel_encoder =
-					psb_intel_attached_encoder(connector);
+		struct gma_encoder *gma_encoder =
+					gma_attached_encoder(connector);
 
 		if (!connector->encoder
 		    || connector->encoder->crtc != crtc)
 			continue;
 
-		ddi_select = psb_intel_encoder->ddi_select;
-		switch (psb_intel_encoder->type) {
+		ddi_select = gma_encoder->ddi_select;
+		switch (gma_encoder->type) {
 		case INTEL_OUTPUT_LVDS:
 			is_lvds = true;
 			break;
@@ -1108,12 +693,13 @@ static int cdv_intel_crtc_mode_set(struct drm_crtc *crtc,
 
 	drm_mode_debug_printmodeline(adjusted_mode);
 	
-	limit = cdv_intel_limit(crtc, refclk);
+	limit = gma_crtc->clock_funcs->limit(crtc, refclk);
 
 	ok = limit->find_pll(limit, crtc, adjusted_mode->clock, refclk,
 				 &clock);
 	if (!ok) {
-		dev_err(dev->dev, "Couldn't find PLL settings for mode!\n");
+		DRM_ERROR("Couldn't find PLL settings for mode! target: %d, actual: %d",
+			  adjusted_mode->clock, clock.dot);
 		return 0;
 	}
 
@@ -1264,7 +850,7 @@ static int cdv_intel_crtc_mode_set(struct drm_crtc *crtc,
 	REG_WRITE(map->conf, pipeconf);
 	REG_READ(map->conf);
 
-	cdv_intel_wait_for_vblank(dev);
+	gma_wait_for_vblank(dev);
 
 	REG_WRITE(map->cntr, dspcntr);
 
@@ -1275,344 +861,16 @@ static int cdv_intel_crtc_mode_set(struct drm_crtc *crtc,
 		crtc_funcs->mode_set_base(crtc, x, y, old_fb);
 	}
 
-	cdv_intel_wait_for_vblank(dev);
-
-	return 0;
-}
-
-
-/**
- * Save HW states of giving crtc
- */
-static void cdv_intel_crtc_save(struct drm_crtc *crtc)
-{
-	struct drm_device *dev = crtc->dev;
-	struct drm_psb_private *dev_priv = dev->dev_private;
-	struct psb_intel_crtc *psb_intel_crtc = to_psb_intel_crtc(crtc);
-	struct psb_intel_crtc_state *crtc_state = psb_intel_crtc->crtc_state;
-	const struct psb_offset *map = &dev_priv->regmap[psb_intel_crtc->pipe];
-	uint32_t paletteReg;
-	int i;
-
-	if (!crtc_state) {
-		dev_dbg(dev->dev, "No CRTC state found\n");
-		return;
-	}
-
-	crtc_state->saveDSPCNTR = REG_READ(map->cntr);
-	crtc_state->savePIPECONF = REG_READ(map->conf);
-	crtc_state->savePIPESRC = REG_READ(map->src);
-	crtc_state->saveFP0 = REG_READ(map->fp0);
-	crtc_state->saveFP1 = REG_READ(map->fp1);
-	crtc_state->saveDPLL = REG_READ(map->dpll);
-	crtc_state->saveHTOTAL = REG_READ(map->htotal);
-	crtc_state->saveHBLANK = REG_READ(map->hblank);
-	crtc_state->saveHSYNC = REG_READ(map->hsync);
-	crtc_state->saveVTOTAL = REG_READ(map->vtotal);
-	crtc_state->saveVBLANK = REG_READ(map->vblank);
-	crtc_state->saveVSYNC = REG_READ(map->vsync);
-	crtc_state->saveDSPSTRIDE = REG_READ(map->stride);
-
-	/*NOTE: DSPSIZE DSPPOS only for psb*/
-	crtc_state->saveDSPSIZE = REG_READ(map->size);
-	crtc_state->saveDSPPOS = REG_READ(map->pos);
-
-	crtc_state->saveDSPBASE = REG_READ(map->base);
-
-	DRM_DEBUG("(%x %x %x %x %x %x %x %x %x %x %x %x %x %x %x %x)\n",
-			crtc_state->saveDSPCNTR,
-			crtc_state->savePIPECONF,
-			crtc_state->savePIPESRC,
-			crtc_state->saveFP0,
-			crtc_state->saveFP1,
-			crtc_state->saveDPLL,
-			crtc_state->saveHTOTAL,
-			crtc_state->saveHBLANK,
-			crtc_state->saveHSYNC,
-			crtc_state->saveVTOTAL,
-			crtc_state->saveVBLANK,
-			crtc_state->saveVSYNC,
-			crtc_state->saveDSPSTRIDE,
-			crtc_state->saveDSPSIZE,
-			crtc_state->saveDSPPOS,
-			crtc_state->saveDSPBASE
-		);
-
-	paletteReg = map->palette;
-	for (i = 0; i < 256; ++i)
-		crtc_state->savePalette[i] = REG_READ(paletteReg + (i << 2));
-}
-
-/**
- * Restore HW states of giving crtc
- */
-static void cdv_intel_crtc_restore(struct drm_crtc *crtc)
-{
-	struct drm_device *dev = crtc->dev;
-	struct drm_psb_private *dev_priv = dev->dev_private;
-	struct psb_intel_crtc *psb_intel_crtc =  to_psb_intel_crtc(crtc);
-	struct psb_intel_crtc_state *crtc_state = psb_intel_crtc->crtc_state;
-	const struct psb_offset *map = &dev_priv->regmap[psb_intel_crtc->pipe];
-	uint32_t paletteReg;
-	int i;
-
-	if (!crtc_state) {
-		dev_dbg(dev->dev, "No crtc state\n");
-		return;
-	}
-
-	DRM_DEBUG(
-		"current:(%x %x %x %x %x %x %x %x %x %x %x %x %x %x %x %x)\n",
-		REG_READ(map->cntr),
-		REG_READ(map->conf),
-		REG_READ(map->src),
-		REG_READ(map->fp0),
-		REG_READ(map->fp1),
-		REG_READ(map->dpll),
-		REG_READ(map->htotal),
-		REG_READ(map->hblank),
-		REG_READ(map->hsync),
-		REG_READ(map->vtotal),
-		REG_READ(map->vblank),
-		REG_READ(map->vsync),
-		REG_READ(map->stride),
-		REG_READ(map->size),
-		REG_READ(map->pos),
-		REG_READ(map->base)
-	);
-
-	DRM_DEBUG(
-		"saved: (%x %x %x %x %x %x %x %x %x %x %x %x %x %x %x %x)\n",
-		crtc_state->saveDSPCNTR,
-		crtc_state->savePIPECONF,
-		crtc_state->savePIPESRC,
-		crtc_state->saveFP0,
-		crtc_state->saveFP1,
-		crtc_state->saveDPLL,
-		crtc_state->saveHTOTAL,
-		crtc_state->saveHBLANK,
-		crtc_state->saveHSYNC,
-		crtc_state->saveVTOTAL,
-		crtc_state->saveVBLANK,
-		crtc_state->saveVSYNC,
-		crtc_state->saveDSPSTRIDE,
-		crtc_state->saveDSPSIZE,
-		crtc_state->saveDSPPOS,
-		crtc_state->saveDSPBASE
-	);
-
-
-	if (crtc_state->saveDPLL & DPLL_VCO_ENABLE) {
-		REG_WRITE(map->dpll,
-				crtc_state->saveDPLL & ~DPLL_VCO_ENABLE);
-		REG_READ(map->dpll);
-		DRM_DEBUG("write dpll: %x\n",
-				REG_READ(map->dpll));
-		udelay(150);
-	}
-
-	REG_WRITE(map->fp0, crtc_state->saveFP0);
-	REG_READ(map->fp0);
-
-	REG_WRITE(map->fp1, crtc_state->saveFP1);
-	REG_READ(map->fp1);
-
-	REG_WRITE(map->dpll, crtc_state->saveDPLL);
-	REG_READ(map->dpll);
-	udelay(150);
-
-	REG_WRITE(map->htotal, crtc_state->saveHTOTAL);
-	REG_WRITE(map->hblank, crtc_state->saveHBLANK);
-	REG_WRITE(map->hsync, crtc_state->saveHSYNC);
-	REG_WRITE(map->vtotal, crtc_state->saveVTOTAL);
-	REG_WRITE(map->vblank, crtc_state->saveVBLANK);
-	REG_WRITE(map->vsync, crtc_state->saveVSYNC);
-	REG_WRITE(map->stride, crtc_state->saveDSPSTRIDE);
-
-	REG_WRITE(map->size, crtc_state->saveDSPSIZE);
-	REG_WRITE(map->pos, crtc_state->saveDSPPOS);
-
-	REG_WRITE(map->src, crtc_state->savePIPESRC);
-	REG_WRITE(map->base, crtc_state->saveDSPBASE);
-	REG_WRITE(map->conf, crtc_state->savePIPECONF);
-
-	cdv_intel_wait_for_vblank(dev);
-
-	REG_WRITE(map->cntr, crtc_state->saveDSPCNTR);
-	REG_WRITE(map->base, crtc_state->saveDSPBASE);
-
-	cdv_intel_wait_for_vblank(dev);
-
-	paletteReg = map->palette;
-	for (i = 0; i < 256; ++i)
-		REG_WRITE(paletteReg + (i << 2), crtc_state->savePalette[i]);
-}
-
-static int cdv_intel_crtc_cursor_set(struct drm_crtc *crtc,
-				 struct drm_file *file_priv,
-				 uint32_t handle,
-				 uint32_t width, uint32_t height)
-{
-	struct drm_device *dev = crtc->dev;
-	struct psb_intel_crtc *psb_intel_crtc = to_psb_intel_crtc(crtc);
-	int pipe = psb_intel_crtc->pipe;
-	uint32_t control = (pipe == 0) ? CURACNTR : CURBCNTR;
-	uint32_t base = (pipe == 0) ? CURABASE : CURBBASE;
-	uint32_t temp;
-	size_t addr = 0;
-	struct gtt_range *gt;
-	struct drm_gem_object *obj;
-	int ret = 0;
-
-	/* if we want to turn of the cursor ignore width and height */
-	if (!handle) {
-		/* turn off the cursor */
-		temp = CURSOR_MODE_DISABLE;
-
-		if (gma_power_begin(dev, false)) {
-			REG_WRITE(control, temp);
-			REG_WRITE(base, 0);
-			gma_power_end(dev);
-		}
-
-		/* unpin the old GEM object */
-		if (psb_intel_crtc->cursor_obj) {
-			gt = container_of(psb_intel_crtc->cursor_obj,
-							struct gtt_range, gem);
-			psb_gtt_unpin(gt);
-			drm_gem_object_unreference(psb_intel_crtc->cursor_obj);
-			psb_intel_crtc->cursor_obj = NULL;
-		}
-
-		return 0;
-	}
-
-	/* Currently we only support 64x64 cursors */
-	if (width != 64 || height != 64) {
-		dev_dbg(dev->dev, "we currently only support 64x64 cursors\n");
-		return -EINVAL;
-	}
-
-	obj = drm_gem_object_lookup(dev, file_priv, handle);
-	if (!obj)
-		return -ENOENT;
-
-	if (obj->size < width * height * 4) {
-		dev_dbg(dev->dev, "buffer is to small\n");
-		ret = -ENOMEM;
-		goto unref_cursor;
-	}
-
-	gt = container_of(obj, struct gtt_range, gem);
-
-	/* Pin the memory into the GTT */
-	ret = psb_gtt_pin(gt);
-	if (ret) {
-		dev_err(dev->dev, "Can not pin down handle 0x%x\n", handle);
-		goto unref_cursor;
-	}
-
-	addr = gt->offset;	/* Or resource.start ??? */
-
-	psb_intel_crtc->cursor_addr = addr;
-
-	temp = 0;
-	/* set the pipe for the cursor */
-	temp |= (pipe << 28);
-	temp |= CURSOR_MODE_64_ARGB_AX | MCURSOR_GAMMA_ENABLE;
-
-	if (gma_power_begin(dev, false)) {
-		REG_WRITE(control, temp);
-		REG_WRITE(base, addr);
-		gma_power_end(dev);
-	}
-
-	/* unpin the old GEM object */
-	if (psb_intel_crtc->cursor_obj) {
-		gt = container_of(psb_intel_crtc->cursor_obj,
-							struct gtt_range, gem);
-		psb_gtt_unpin(gt);
-		drm_gem_object_unreference(psb_intel_crtc->cursor_obj);
-	}
-
-	psb_intel_crtc->cursor_obj = obj;
-	return ret;
-
-unref_cursor:
-	drm_gem_object_unreference(obj);
-	return ret;
-}
-
-static int cdv_intel_crtc_cursor_move(struct drm_crtc *crtc, int x, int y)
-{
-	struct drm_device *dev = crtc->dev;
-	struct psb_intel_crtc *psb_intel_crtc = to_psb_intel_crtc(crtc);
-	int pipe = psb_intel_crtc->pipe;
-	uint32_t temp = 0;
-	uint32_t adder;
-
-
-	if (x < 0) {
-		temp |= (CURSOR_POS_SIGN << CURSOR_X_SHIFT);
-		x = -x;
-	}
-	if (y < 0) {
-		temp |= (CURSOR_POS_SIGN << CURSOR_Y_SHIFT);
-		y = -y;
-	}
-
-	temp |= ((x & CURSOR_POS_MASK) << CURSOR_X_SHIFT);
-	temp |= ((y & CURSOR_POS_MASK) << CURSOR_Y_SHIFT);
+	gma_wait_for_vblank(dev);
 
-	adder = psb_intel_crtc->cursor_addr;
-
-	if (gma_power_begin(dev, false)) {
-		REG_WRITE((pipe == 0) ? CURAPOS : CURBPOS, temp);
-		REG_WRITE((pipe == 0) ? CURABASE : CURBBASE, adder);
-		gma_power_end(dev);
-	}
 	return 0;
 }
 
-static void cdv_intel_crtc_gamma_set(struct drm_crtc *crtc, u16 *red,
-			 u16 *green, u16 *blue, uint32_t start, uint32_t size)
-{
-	struct psb_intel_crtc *psb_intel_crtc = to_psb_intel_crtc(crtc);
-	int i;
-	int end = (start + size > 256) ? 256 : start + size;
-
-	for (i = start; i < end; i++) {
-		psb_intel_crtc->lut_r[i] = red[i] >> 8;
-		psb_intel_crtc->lut_g[i] = green[i] >> 8;
-		psb_intel_crtc->lut_b[i] = blue[i] >> 8;
-	}
-
-	cdv_intel_crtc_load_lut(crtc);
-}
-
-static int cdv_crtc_set_config(struct drm_mode_set *set)
-{
-	int ret = 0;
-	struct drm_device *dev = set->crtc->dev;
-	struct drm_psb_private *dev_priv = dev->dev_private;
-
-	if (!dev_priv->rpm_enabled)
-		return drm_crtc_helper_set_config(set);
-
-	pm_runtime_forbid(&dev->pdev->dev);
-
-	ret = drm_crtc_helper_set_config(set);
-
-	pm_runtime_allow(&dev->pdev->dev);
-
-	return ret;
-}
-
 /** Derive the pixel clock for the given refclk and divisors for 8xx chips. */
 
 /* FIXME: why are we using this, should it be cdv_ in this tree ? */
 
-static void i8xx_clock(int refclk, struct cdv_intel_clock_t *clock)
+static void i8xx_clock(int refclk, struct gma_clock_t *clock)
 {
 	clock->m = 5 * (clock->m1 + 2) + (clock->m2 + 2);
 	clock->p = clock->p1 * clock->p2;
@@ -1625,12 +883,12 @@ static int cdv_intel_crtc_clock_get(struct drm_device *dev,
 				struct drm_crtc *crtc)
 {
 	struct drm_psb_private *dev_priv = dev->dev_private;
-	struct psb_intel_crtc *psb_intel_crtc = to_psb_intel_crtc(crtc);
-	int pipe = psb_intel_crtc->pipe;
+	struct gma_crtc *gma_crtc = to_gma_crtc(crtc);
+	int pipe = gma_crtc->pipe;
 	const struct psb_offset *map = &dev_priv->regmap[pipe];
 	u32 dpll;
 	u32 fp;
-	struct cdv_intel_clock_t clock;
+	struct gma_clock_t clock;
 	bool is_lvds;
 	struct psb_pipe *p = &dev_priv->regs.pipe[pipe];
 
@@ -1703,8 +961,8 @@ static int cdv_intel_crtc_clock_get(struct drm_device *dev,
 struct drm_display_mode *cdv_intel_crtc_mode_get(struct drm_device *dev,
 					     struct drm_crtc *crtc)
 {
-	struct psb_intel_crtc *psb_intel_crtc = to_psb_intel_crtc(crtc);
-	int pipe = psb_intel_crtc->pipe;
+	struct gma_crtc *gma_crtc = to_gma_crtc(crtc);
+	int pipe = gma_crtc->pipe;
 	struct drm_psb_private *dev_priv = dev->dev_private;
 	struct psb_pipe *p = &dev_priv->regs.pipe[pipe];
 	const struct psb_offset *map = &dev_priv->regmap[pipe];
@@ -1747,44 +1005,28 @@ struct drm_display_mode *cdv_intel_crtc_mode_get(struct drm_device *dev,
 	return mode;
 }
 
-static void cdv_intel_crtc_destroy(struct drm_crtc *crtc)
-{
-	struct psb_intel_crtc *psb_intel_crtc = to_psb_intel_crtc(crtc);
-
-	kfree(psb_intel_crtc->crtc_state);
-	drm_crtc_cleanup(crtc);
-	kfree(psb_intel_crtc);
-}
-
-static void cdv_intel_crtc_disable(struct drm_crtc *crtc)
-{
-	struct gtt_range *gt;
-	struct drm_crtc_helper_funcs *crtc_funcs = crtc->helper_private;
-
-	crtc_funcs->dpms(crtc, DRM_MODE_DPMS_OFF);
-
-	if (crtc->fb) {
-		gt = to_psb_fb(crtc->fb)->gtt;
-		psb_gtt_unpin(gt);
-	}
-}
-
 const struct drm_crtc_helper_funcs cdv_intel_helper_funcs = {
-	.dpms = cdv_intel_crtc_dpms,
-	.mode_fixup = cdv_intel_crtc_mode_fixup,
+	.dpms = gma_crtc_dpms,
+	.mode_fixup = gma_crtc_mode_fixup,
 	.mode_set = cdv_intel_crtc_mode_set,
-	.mode_set_base = cdv_intel_pipe_set_base,
-	.prepare = cdv_intel_crtc_prepare,
-	.commit = cdv_intel_crtc_commit,
-	.disable = cdv_intel_crtc_disable,
+	.mode_set_base = gma_pipe_set_base,
+	.prepare = gma_crtc_prepare,
+	.commit = gma_crtc_commit,
+	.disable = gma_crtc_disable,
 };
 
 const struct drm_crtc_funcs cdv_intel_crtc_funcs = {
-	.save = cdv_intel_crtc_save,
-	.restore = cdv_intel_crtc_restore,
-	.cursor_set = cdv_intel_crtc_cursor_set,
-	.cursor_move = cdv_intel_crtc_cursor_move,
-	.gamma_set = cdv_intel_crtc_gamma_set,
-	.set_config = cdv_crtc_set_config,
-	.destroy = cdv_intel_crtc_destroy,
+	.save = gma_crtc_save,
+	.restore = gma_crtc_restore,
+	.cursor_set = gma_crtc_cursor_set,
+	.cursor_move = gma_crtc_cursor_move,
+	.gamma_set = gma_crtc_gamma_set,
+	.set_config = gma_crtc_set_config,
+	.destroy = gma_crtc_destroy,
+};
+
+const struct gma_clock_funcs cdv_clock_funcs = {
+	.clock = cdv_intel_clock,
+	.limit = cdv_intel_limit,
+	.pll_is_valid = gma_pll_is_valid,
 };
diff --git a/drivers/gpu/drm/gma500/cdv_intel_dp.c b/drivers/gpu/drm/gma500/cdv_intel_dp.c
index 88d9ef6b5b4a..f4eb43573cad 100644
--- a/drivers/gpu/drm/gma500/cdv_intel_dp.c
+++ b/drivers/gpu/drm/gma500/cdv_intel_dp.c
@@ -34,6 +34,7 @@
 #include "psb_drv.h"
 #include "psb_intel_drv.h"
 #include "psb_intel_reg.h"
+#include "gma_display.h"
 #include <drm/drm_dp_helper.h>
 
 #define _wait_for(COND, MS, W) ({ \
@@ -68,7 +69,7 @@ struct cdv_intel_dp {
 	uint8_t link_bw;
 	uint8_t lane_count;
 	uint8_t dpcd[4];
-	struct psb_intel_encoder *encoder;
+	struct gma_encoder *encoder;
 	struct i2c_adapter adapter;
 	struct i2c_algo_dp_aux_data algo;
 	uint8_t	train_set[4];
@@ -114,18 +115,18 @@ static uint32_t dp_vswing_premph_table[] = {
  * If a CPU or PCH DP output is attached to an eDP panel, this function
  * will return true, and false otherwise.
  */
-static bool is_edp(struct psb_intel_encoder *encoder)
+static bool is_edp(struct gma_encoder *encoder)
 {
 	return encoder->type == INTEL_OUTPUT_EDP;
 }
 
 
-static void cdv_intel_dp_start_link_train(struct psb_intel_encoder *encoder);
-static void cdv_intel_dp_complete_link_train(struct psb_intel_encoder *encoder);
-static void cdv_intel_dp_link_down(struct psb_intel_encoder *encoder);
+static void cdv_intel_dp_start_link_train(struct gma_encoder *encoder);
+static void cdv_intel_dp_complete_link_train(struct gma_encoder *encoder);
+static void cdv_intel_dp_link_down(struct gma_encoder *encoder);
 
 static int
-cdv_intel_dp_max_lane_count(struct psb_intel_encoder *encoder)
+cdv_intel_dp_max_lane_count(struct gma_encoder *encoder)
 {
 	struct cdv_intel_dp *intel_dp = encoder->dev_priv;
 	int max_lane_count = 4;
@@ -143,7 +144,7 @@ cdv_intel_dp_max_lane_count(struct psb_intel_encoder *encoder)
 }
 
 static int
-cdv_intel_dp_max_link_bw(struct psb_intel_encoder *encoder)
+cdv_intel_dp_max_link_bw(struct gma_encoder *encoder)
 {
 	struct cdv_intel_dp *intel_dp = encoder->dev_priv;
 	int max_link_bw = intel_dp->dpcd[DP_MAX_LINK_RATE];
@@ -180,7 +181,7 @@ cdv_intel_dp_max_data_rate(int max_link_clock, int max_lanes)
 	return (max_link_clock * max_lanes * 19) / 20;
 }
 
-static void cdv_intel_edp_panel_vdd_on(struct psb_intel_encoder *intel_encoder)
+static void cdv_intel_edp_panel_vdd_on(struct gma_encoder *intel_encoder)
 {
 	struct drm_device *dev = intel_encoder->base.dev;
 	struct cdv_intel_dp *intel_dp = intel_encoder->dev_priv;
@@ -200,7 +201,7 @@ static void cdv_intel_edp_panel_vdd_on(struct psb_intel_encoder *intel_encoder)
 	msleep(intel_dp->panel_power_up_delay);
 }
 
-static void cdv_intel_edp_panel_vdd_off(struct psb_intel_encoder *intel_encoder)
+static void cdv_intel_edp_panel_vdd_off(struct gma_encoder *intel_encoder)
 {
 	struct drm_device *dev = intel_encoder->base.dev;
 	u32 pp;
@@ -215,7 +216,7 @@ static void cdv_intel_edp_panel_vdd_off(struct psb_intel_encoder *intel_encoder)
 }
 
 /* Returns true if the panel was already on when called */
-static bool cdv_intel_edp_panel_on(struct psb_intel_encoder *intel_encoder)
+static bool cdv_intel_edp_panel_on(struct gma_encoder *intel_encoder)
 {
 	struct drm_device *dev = intel_encoder->base.dev;
 	struct cdv_intel_dp *intel_dp = intel_encoder->dev_priv;
@@ -242,7 +243,7 @@ static bool cdv_intel_edp_panel_on(struct psb_intel_encoder *intel_encoder)
 	return false;
 }
 
-static void cdv_intel_edp_panel_off (struct psb_intel_encoder *intel_encoder)
+static void cdv_intel_edp_panel_off (struct gma_encoder *intel_encoder)
 {
 	struct drm_device *dev = intel_encoder->base.dev;
 	u32 pp, idle_off_mask = PP_ON ;
@@ -274,7 +275,7 @@ static void cdv_intel_edp_panel_off (struct psb_intel_encoder *intel_encoder)
 	DRM_DEBUG_KMS("Over\n");
 }
 
-static void cdv_intel_edp_backlight_on (struct psb_intel_encoder *intel_encoder)
+static void cdv_intel_edp_backlight_on (struct gma_encoder *intel_encoder)
 {
 	struct drm_device *dev = intel_encoder->base.dev;
 	u32 pp;
@@ -294,7 +295,7 @@ static void cdv_intel_edp_backlight_on (struct psb_intel_encoder *intel_encoder)
 	gma_backlight_enable(dev);
 }
 
-static void cdv_intel_edp_backlight_off (struct psb_intel_encoder *intel_encoder)
+static void cdv_intel_edp_backlight_off (struct gma_encoder *intel_encoder)
 {
 	struct drm_device *dev = intel_encoder->base.dev;
 	struct cdv_intel_dp *intel_dp = intel_encoder->dev_priv;
@@ -314,7 +315,7 @@ static int
 cdv_intel_dp_mode_valid(struct drm_connector *connector,
 		    struct drm_display_mode *mode)
 {
-	struct psb_intel_encoder *encoder = psb_intel_attached_encoder(connector);
+	struct gma_encoder *encoder = gma_attached_encoder(connector);
 	struct cdv_intel_dp *intel_dp = encoder->dev_priv;
 	int max_link_clock = cdv_intel_dp_link_clock(cdv_intel_dp_max_link_bw(encoder));
 	int max_lanes = cdv_intel_dp_max_lane_count(encoder);
@@ -370,7 +371,7 @@ unpack_aux(uint32_t src, uint8_t *dst, int dst_bytes)
 }
 
 static int
-cdv_intel_dp_aux_ch(struct psb_intel_encoder *encoder,
+cdv_intel_dp_aux_ch(struct gma_encoder *encoder,
 		uint8_t *send, int send_bytes,
 		uint8_t *recv, int recv_size)
 {
@@ -472,7 +473,7 @@ cdv_intel_dp_aux_ch(struct psb_intel_encoder *encoder,
 
 /* Write data to the aux channel in native mode */
 static int
-cdv_intel_dp_aux_native_write(struct psb_intel_encoder *encoder,
+cdv_intel_dp_aux_native_write(struct gma_encoder *encoder,
 			  uint16_t address, uint8_t *send, int send_bytes)
 {
 	int ret;
@@ -504,7 +505,7 @@ cdv_intel_dp_aux_native_write(struct psb_intel_encoder *encoder,
 
 /* Write a single byte to the aux channel in native mode */
 static int
-cdv_intel_dp_aux_native_write_1(struct psb_intel_encoder *encoder,
+cdv_intel_dp_aux_native_write_1(struct gma_encoder *encoder,
 			    uint16_t address, uint8_t byte)
 {
 	return cdv_intel_dp_aux_native_write(encoder, address, &byte, 1);
@@ -512,7 +513,7 @@ cdv_intel_dp_aux_native_write_1(struct psb_intel_encoder *encoder,
 
 /* read bytes from a native aux channel */
 static int
-cdv_intel_dp_aux_native_read(struct psb_intel_encoder *encoder,
+cdv_intel_dp_aux_native_read(struct gma_encoder *encoder,
 			 uint16_t address, uint8_t *recv, int recv_bytes)
 {
 	uint8_t msg[4];
@@ -557,7 +558,7 @@ cdv_intel_dp_i2c_aux_ch(struct i2c_adapter *adapter, int mode,
 	struct cdv_intel_dp *intel_dp = container_of(adapter,
 						struct cdv_intel_dp,
 						adapter);
-	struct psb_intel_encoder *encoder = intel_dp->encoder;
+	struct gma_encoder *encoder = intel_dp->encoder;
 	uint16_t address = algo_data->address;
 	uint8_t msg[5];
 	uint8_t reply[2];
@@ -647,7 +648,8 @@ cdv_intel_dp_i2c_aux_ch(struct i2c_adapter *adapter, int mode,
 }
 
 static int
-cdv_intel_dp_i2c_init(struct psb_intel_connector *connector, struct psb_intel_encoder *encoder, const char *name)
+cdv_intel_dp_i2c_init(struct gma_connector *connector,
+		      struct gma_encoder *encoder, const char *name)
 {
 	struct cdv_intel_dp *intel_dp = encoder->dev_priv;
 	int ret;
@@ -698,7 +700,7 @@ cdv_intel_dp_mode_fixup(struct drm_encoder *encoder, const struct drm_display_mo
 		    struct drm_display_mode *adjusted_mode)
 {
 	struct drm_psb_private *dev_priv = encoder->dev->dev_private;
-	struct psb_intel_encoder *intel_encoder = to_psb_intel_encoder(encoder);
+	struct gma_encoder *intel_encoder = to_gma_encoder(encoder);
 	struct cdv_intel_dp *intel_dp = intel_encoder->dev_priv;
 	int lane_count, clock;
 	int max_lane_count = cdv_intel_dp_max_lane_count(intel_encoder);
@@ -792,22 +794,22 @@ cdv_intel_dp_set_m_n(struct drm_crtc *crtc, struct drm_display_mode *mode,
 	struct drm_psb_private *dev_priv = dev->dev_private;
 	struct drm_mode_config *mode_config = &dev->mode_config;
 	struct drm_encoder *encoder;
-	struct psb_intel_crtc *intel_crtc = to_psb_intel_crtc(crtc);
+	struct gma_crtc *gma_crtc = to_gma_crtc(crtc);
 	int lane_count = 4, bpp = 24;
 	struct cdv_intel_dp_m_n m_n;
-	int pipe = intel_crtc->pipe;
+	int pipe = gma_crtc->pipe;
 
 	/*
 	 * Find the lane count in the intel_encoder private
 	 */
 	list_for_each_entry(encoder, &mode_config->encoder_list, head) {
-		struct psb_intel_encoder *intel_encoder;
+		struct gma_encoder *intel_encoder;
 		struct cdv_intel_dp *intel_dp;
 
 		if (encoder->crtc != crtc)
 			continue;
 
-		intel_encoder = to_psb_intel_encoder(encoder);
+		intel_encoder = to_gma_encoder(encoder);
 		intel_dp = intel_encoder->dev_priv;
 		if (intel_encoder->type == INTEL_OUTPUT_DISPLAYPORT) {
 			lane_count = intel_dp->lane_count;
@@ -841,9 +843,9 @@ static void
 cdv_intel_dp_mode_set(struct drm_encoder *encoder, struct drm_display_mode *mode,
 		  struct drm_display_mode *adjusted_mode)
 {
-	struct psb_intel_encoder *intel_encoder = to_psb_intel_encoder(encoder);
+	struct gma_encoder *intel_encoder = to_gma_encoder(encoder);
 	struct drm_crtc *crtc = encoder->crtc;
-	struct psb_intel_crtc *intel_crtc = to_psb_intel_crtc(crtc);
+	struct gma_crtc *gma_crtc = to_gma_crtc(crtc);
 	struct cdv_intel_dp *intel_dp = intel_encoder->dev_priv;
 	struct drm_device *dev = encoder->dev;
 
@@ -885,7 +887,7 @@ cdv_intel_dp_mode_set(struct drm_encoder *encoder, struct drm_display_mode *mode
 	}
 
 	/* CPT DP's pipe select is decided in TRANS_DP_CTL */
-	if (intel_crtc->pipe == 1)
+	if (gma_crtc->pipe == 1)
 		intel_dp->DP |= DP_PIPEB_SELECT;
 
 	REG_WRITE(intel_dp->output_reg, (intel_dp->DP | DP_PORT_EN));
@@ -900,7 +902,7 @@ cdv_intel_dp_mode_set(struct drm_encoder *encoder, struct drm_display_mode *mode
 		else
 			pfit_control = 0;
 
-		pfit_control |= intel_crtc->pipe << PFIT_PIPE_SHIFT;
+		pfit_control |= gma_crtc->pipe << PFIT_PIPE_SHIFT;
 
 		REG_WRITE(PFIT_CONTROL, pfit_control);
 	}
@@ -908,7 +910,7 @@ cdv_intel_dp_mode_set(struct drm_encoder *encoder, struct drm_display_mode *mode
 
 
 /* If the sink supports it, try to set the power state appropriately */
-static void cdv_intel_dp_sink_dpms(struct psb_intel_encoder *encoder, int mode)
+static void cdv_intel_dp_sink_dpms(struct gma_encoder *encoder, int mode)
 {
 	struct cdv_intel_dp *intel_dp = encoder->dev_priv;
 	int ret, i;
@@ -940,7 +942,7 @@ static void cdv_intel_dp_sink_dpms(struct psb_intel_encoder *encoder, int mode)
 
 static void cdv_intel_dp_prepare(struct drm_encoder *encoder)
 {
-	struct psb_intel_encoder *intel_encoder = to_psb_intel_encoder(encoder);
+	struct gma_encoder *intel_encoder = to_gma_encoder(encoder);
 	int edp = is_edp(intel_encoder);
 
 	if (edp) {
@@ -957,7 +959,7 @@ static void cdv_intel_dp_prepare(struct drm_encoder *encoder)
 
 static void cdv_intel_dp_commit(struct drm_encoder *encoder)
 {
-	struct psb_intel_encoder *intel_encoder = to_psb_intel_encoder(encoder);
+	struct gma_encoder *intel_encoder = to_gma_encoder(encoder);
 	int edp = is_edp(intel_encoder);
 
 	if (edp)
@@ -971,7 +973,7 @@ static void cdv_intel_dp_commit(struct drm_encoder *encoder)
 static void
 cdv_intel_dp_dpms(struct drm_encoder *encoder, int mode)
 {
-	struct psb_intel_encoder *intel_encoder = to_psb_intel_encoder(encoder);
+	struct gma_encoder *intel_encoder = to_gma_encoder(encoder);
 	struct cdv_intel_dp *intel_dp = intel_encoder->dev_priv;
 	struct drm_device *dev = encoder->dev;
 	uint32_t dp_reg = REG_READ(intel_dp->output_reg);
@@ -1006,7 +1008,7 @@ cdv_intel_dp_dpms(struct drm_encoder *encoder, int mode)
  * cases where the sink may still be asleep.
  */
 static bool
-cdv_intel_dp_aux_native_read_retry(struct psb_intel_encoder *encoder, uint16_t address,
+cdv_intel_dp_aux_native_read_retry(struct gma_encoder *encoder, uint16_t address,
 			       uint8_t *recv, int recv_bytes)
 {
 	int ret, i;
@@ -1031,7 +1033,7 @@ cdv_intel_dp_aux_native_read_retry(struct psb_intel_encoder *encoder, uint16_t a
  * link status information
  */
 static bool
-cdv_intel_dp_get_link_status(struct psb_intel_encoder *encoder)
+cdv_intel_dp_get_link_status(struct gma_encoder *encoder)
 {
 	struct cdv_intel_dp *intel_dp = encoder->dev_priv;
 	return cdv_intel_dp_aux_native_read_retry(encoder,
@@ -1105,7 +1107,7 @@ cdv_intel_dp_pre_emphasis_max(uint8_t voltage_swing)
 }
 */
 static void
-cdv_intel_get_adjust_train(struct psb_intel_encoder *encoder)
+cdv_intel_get_adjust_train(struct gma_encoder *encoder)
 {
 	struct cdv_intel_dp *intel_dp = encoder->dev_priv;
 	uint8_t v = 0;
@@ -1164,7 +1166,7 @@ cdv_intel_clock_recovery_ok(uint8_t link_status[DP_LINK_STATUS_SIZE], int lane_c
 			 DP_LANE_CHANNEL_EQ_DONE|\
 			 DP_LANE_SYMBOL_LOCKED)
 static bool
-cdv_intel_channel_eq_ok(struct psb_intel_encoder *encoder)
+cdv_intel_channel_eq_ok(struct gma_encoder *encoder)
 {
 	struct cdv_intel_dp *intel_dp = encoder->dev_priv;
 	uint8_t lane_align;
@@ -1184,7 +1186,7 @@ cdv_intel_channel_eq_ok(struct psb_intel_encoder *encoder)
 }
 
 static bool
-cdv_intel_dp_set_link_train(struct psb_intel_encoder *encoder,
+cdv_intel_dp_set_link_train(struct gma_encoder *encoder,
 			uint32_t dp_reg_value,
 			uint8_t dp_train_pat)
 {
@@ -1211,7 +1213,7 @@ cdv_intel_dp_set_link_train(struct psb_intel_encoder *encoder,
 
 
 static bool
-cdv_intel_dplink_set_level(struct psb_intel_encoder *encoder,
+cdv_intel_dplink_set_level(struct gma_encoder *encoder,
 			uint8_t dp_train_pat)
 {
 	
@@ -1232,7 +1234,7 @@ cdv_intel_dplink_set_level(struct psb_intel_encoder *encoder,
 }
 
 static void
-cdv_intel_dp_set_vswing_premph(struct psb_intel_encoder *encoder, uint8_t signal_level)
+cdv_intel_dp_set_vswing_premph(struct gma_encoder *encoder, uint8_t signal_level)
 {
 	struct drm_device *dev = encoder->base.dev;
 	struct cdv_intel_dp *intel_dp = encoder->dev_priv;
@@ -1298,7 +1300,7 @@ cdv_intel_dp_set_vswing_premph(struct psb_intel_encoder *encoder, uint8_t signal
 
 /* Enable corresponding port and start training pattern 1 */
 static void
-cdv_intel_dp_start_link_train(struct psb_intel_encoder *encoder)
+cdv_intel_dp_start_link_train(struct gma_encoder *encoder)
 {
 	struct drm_device *dev = encoder->base.dev;
 	struct cdv_intel_dp *intel_dp = encoder->dev_priv;
@@ -1317,7 +1319,7 @@ cdv_intel_dp_start_link_train(struct psb_intel_encoder *encoder)
 	/* Enable output, wait for it to become active */
 	REG_WRITE(intel_dp->output_reg, reg);
 	REG_READ(intel_dp->output_reg);
-	psb_intel_wait_for_vblank(dev);
+	gma_wait_for_vblank(dev);
 
 	DRM_DEBUG_KMS("Link config\n");
 	/* Write the link configuration data */
@@ -1392,7 +1394,7 @@ cdv_intel_dp_start_link_train(struct psb_intel_encoder *encoder)
 }
 
 static void
-cdv_intel_dp_complete_link_train(struct psb_intel_encoder *encoder)
+cdv_intel_dp_complete_link_train(struct gma_encoder *encoder)
 {
 	struct drm_device *dev = encoder->base.dev;
 	struct cdv_intel_dp *intel_dp = encoder->dev_priv;
@@ -1478,7 +1480,7 @@ cdv_intel_dp_complete_link_train(struct psb_intel_encoder *encoder)
 }
 
 static void
-cdv_intel_dp_link_down(struct psb_intel_encoder *encoder)
+cdv_intel_dp_link_down(struct gma_encoder *encoder)
 {
 	struct drm_device *dev = encoder->base.dev;
 	struct cdv_intel_dp *intel_dp = encoder->dev_priv;
@@ -1502,8 +1504,7 @@ cdv_intel_dp_link_down(struct psb_intel_encoder *encoder)
 	REG_READ(intel_dp->output_reg);
 }
 
-static enum drm_connector_status
-cdv_dp_detect(struct psb_intel_encoder *encoder)
+static enum drm_connector_status cdv_dp_detect(struct gma_encoder *encoder)
 {
 	struct cdv_intel_dp *intel_dp = encoder->dev_priv;
 	enum drm_connector_status status;
@@ -1531,7 +1532,7 @@ cdv_dp_detect(struct psb_intel_encoder *encoder)
 static enum drm_connector_status
 cdv_intel_dp_detect(struct drm_connector *connector, bool force)
 {
-	struct psb_intel_encoder *encoder = psb_intel_attached_encoder(connector);
+	struct gma_encoder *encoder = gma_attached_encoder(connector);
 	struct cdv_intel_dp *intel_dp = encoder->dev_priv;
 	enum drm_connector_status status;
 	struct edid *edid = NULL;
@@ -1565,7 +1566,7 @@ cdv_intel_dp_detect(struct drm_connector *connector, bool force)
 
 static int cdv_intel_dp_get_modes(struct drm_connector *connector)
 {
-	struct psb_intel_encoder *intel_encoder = psb_intel_attached_encoder(connector);
+	struct gma_encoder *intel_encoder = gma_attached_encoder(connector);
 	struct cdv_intel_dp *intel_dp = intel_encoder->dev_priv;
 	struct edid *edid = NULL;
 	int ret = 0;
@@ -1621,7 +1622,7 @@ static int cdv_intel_dp_get_modes(struct drm_connector *connector)
 static bool
 cdv_intel_dp_detect_audio(struct drm_connector *connector)
 {
-	struct psb_intel_encoder *encoder = psb_intel_attached_encoder(connector);
+	struct gma_encoder *encoder = gma_attached_encoder(connector);
 	struct cdv_intel_dp *intel_dp = encoder->dev_priv;
 	struct edid *edid;
 	bool has_audio = false;
@@ -1647,7 +1648,7 @@ cdv_intel_dp_set_property(struct drm_connector *connector,
 		      uint64_t val)
 {
 	struct drm_psb_private *dev_priv = connector->dev->dev_private;
-	struct psb_intel_encoder *encoder = psb_intel_attached_encoder(connector);
+	struct gma_encoder *encoder = gma_attached_encoder(connector);
 	struct cdv_intel_dp *intel_dp = encoder->dev_priv;
 	int ret;
 
@@ -1700,11 +1701,10 @@ done:
 static void
 cdv_intel_dp_destroy(struct drm_connector *connector)
 {
-	struct psb_intel_encoder *psb_intel_encoder =
-					psb_intel_attached_encoder(connector);
-	struct cdv_intel_dp *intel_dp = psb_intel_encoder->dev_priv;
+	struct gma_encoder *gma_encoder = gma_attached_encoder(connector);
+	struct cdv_intel_dp *intel_dp = gma_encoder->dev_priv;
 
-	if (is_edp(psb_intel_encoder)) {
+	if (is_edp(gma_encoder)) {
 	/*	cdv_intel_panel_destroy_backlight(connector->dev); */
 		if (intel_dp->panel_fixed_mode) {
 			kfree(intel_dp->panel_fixed_mode);
@@ -1741,7 +1741,7 @@ static const struct drm_connector_funcs cdv_intel_dp_connector_funcs = {
 static const struct drm_connector_helper_funcs cdv_intel_dp_connector_helper_funcs = {
 	.get_modes = cdv_intel_dp_get_modes,
 	.mode_valid = cdv_intel_dp_mode_valid,
-	.best_encoder = psb_intel_best_encoder,
+	.best_encoder = gma_best_encoder,
 };
 
 static const struct drm_encoder_funcs cdv_intel_dp_enc_funcs = {
@@ -1800,19 +1800,19 @@ static void cdv_disable_intel_clock_gating(struct drm_device *dev)
 void
 cdv_intel_dp_init(struct drm_device *dev, struct psb_intel_mode_device *mode_dev, int output_reg)
 {
-	struct psb_intel_encoder *psb_intel_encoder;
-	struct psb_intel_connector *psb_intel_connector;
+	struct gma_encoder *gma_encoder;
+	struct gma_connector *gma_connector;
 	struct drm_connector *connector;
 	struct drm_encoder *encoder;
 	struct cdv_intel_dp *intel_dp;
 	const char *name = NULL;
 	int type = DRM_MODE_CONNECTOR_DisplayPort;
 
-	psb_intel_encoder = kzalloc(sizeof(struct psb_intel_encoder), GFP_KERNEL);
-	if (!psb_intel_encoder)
+	gma_encoder = kzalloc(sizeof(struct gma_encoder), GFP_KERNEL);
+	if (!gma_encoder)
 		return;
-        psb_intel_connector = kzalloc(sizeof(struct psb_intel_connector), GFP_KERNEL);
-        if (!psb_intel_connector)
+        gma_connector = kzalloc(sizeof(struct gma_connector), GFP_KERNEL);
+        if (!gma_connector)
                 goto err_connector;
 	intel_dp = kzalloc(sizeof(struct cdv_intel_dp), GFP_KERNEL);
 	if (!intel_dp)
@@ -1821,22 +1821,22 @@ cdv_intel_dp_init(struct drm_device *dev, struct psb_intel_mode_device *mode_dev
 	if ((output_reg == DP_C) && cdv_intel_dpc_is_edp(dev))
 		type = DRM_MODE_CONNECTOR_eDP;
 
-	connector = &psb_intel_connector->base;
-	encoder = &psb_intel_encoder->base;
+	connector = &gma_connector->base;
+	encoder = &gma_encoder->base;
 
 	drm_connector_init(dev, connector, &cdv_intel_dp_connector_funcs, type);
 	drm_encoder_init(dev, encoder, &cdv_intel_dp_enc_funcs, DRM_MODE_ENCODER_TMDS);
 
-	psb_intel_connector_attach_encoder(psb_intel_connector, psb_intel_encoder);
+	gma_connector_attach_encoder(gma_connector, gma_encoder);
 
 	if (type == DRM_MODE_CONNECTOR_DisplayPort)
-        	psb_intel_encoder->type = INTEL_OUTPUT_DISPLAYPORT;
+		gma_encoder->type = INTEL_OUTPUT_DISPLAYPORT;
         else
-		psb_intel_encoder->type = INTEL_OUTPUT_EDP;
+		gma_encoder->type = INTEL_OUTPUT_EDP;
 
 
-	psb_intel_encoder->dev_priv=intel_dp;
-	intel_dp->encoder = psb_intel_encoder;
+	gma_encoder->dev_priv=intel_dp;
+	intel_dp->encoder = gma_encoder;
 	intel_dp->output_reg = output_reg;
 	
 	drm_encoder_helper_add(encoder, &cdv_intel_dp_helper_funcs);
@@ -1852,21 +1852,21 @@ cdv_intel_dp_init(struct drm_device *dev, struct psb_intel_mode_device *mode_dev
 	switch (output_reg) {
 		case DP_B:
 			name = "DPDDC-B";
-			psb_intel_encoder->ddi_select = (DP_MASK | DDI0_SELECT);
+			gma_encoder->ddi_select = (DP_MASK | DDI0_SELECT);
 			break;
 		case DP_C:
 			name = "DPDDC-C";
-			psb_intel_encoder->ddi_select = (DP_MASK | DDI1_SELECT);
+			gma_encoder->ddi_select = (DP_MASK | DDI1_SELECT);
 			break;
 	}
 
 	cdv_disable_intel_clock_gating(dev);
 
-	cdv_intel_dp_i2c_init(psb_intel_connector, psb_intel_encoder, name);
+	cdv_intel_dp_i2c_init(gma_connector, gma_encoder, name);
         /* FIXME:fail check */
 	cdv_intel_dp_add_properties(connector);
 
-	if (is_edp(psb_intel_encoder)) {
+	if (is_edp(gma_encoder)) {
 		int ret;
 		struct edp_power_seq cur;
                 u32 pp_on, pp_off, pp_div;
@@ -1920,11 +1920,11 @@ cdv_intel_dp_init(struct drm_device *dev, struct psb_intel_mode_device *mode_dev
                               intel_dp->backlight_on_delay, intel_dp->backlight_off_delay);
 
 
-		cdv_intel_edp_panel_vdd_on(psb_intel_encoder);
-		ret = cdv_intel_dp_aux_native_read(psb_intel_encoder, DP_DPCD_REV,
+		cdv_intel_edp_panel_vdd_on(gma_encoder);
+		ret = cdv_intel_dp_aux_native_read(gma_encoder, DP_DPCD_REV,
 					       intel_dp->dpcd,
 					       sizeof(intel_dp->dpcd));
-		cdv_intel_edp_panel_vdd_off(psb_intel_encoder);
+		cdv_intel_edp_panel_vdd_off(gma_encoder);
 		if (ret == 0) {
 			/* if this fails, presume the device is a ghost */
 			DRM_INFO("failed to retrieve link info, disabling eDP\n");
@@ -1945,7 +1945,7 @@ cdv_intel_dp_init(struct drm_device *dev, struct psb_intel_mode_device *mode_dev
 	return;
 
 err_priv:
-	kfree(psb_intel_connector);
+	kfree(gma_connector);
 err_connector:
-	kfree(psb_intel_encoder);
+	kfree(gma_encoder);
 }
diff --git a/drivers/gpu/drm/gma500/cdv_intel_hdmi.c b/drivers/gpu/drm/gma500/cdv_intel_hdmi.c
index 464153d9d2df..1c0d723b8d24 100644
--- a/drivers/gpu/drm/gma500/cdv_intel_hdmi.c
+++ b/drivers/gpu/drm/gma500/cdv_intel_hdmi.c
@@ -64,11 +64,11 @@ static void cdv_hdmi_mode_set(struct drm_encoder *encoder,
 			struct drm_display_mode *adjusted_mode)
 {
 	struct drm_device *dev = encoder->dev;
-	struct psb_intel_encoder *psb_intel_encoder = to_psb_intel_encoder(encoder);
-	struct mid_intel_hdmi_priv *hdmi_priv = psb_intel_encoder->dev_priv;
+	struct gma_encoder *gma_encoder = to_gma_encoder(encoder);
+	struct mid_intel_hdmi_priv *hdmi_priv = gma_encoder->dev_priv;
 	u32 hdmib;
 	struct drm_crtc *crtc = encoder->crtc;
-	struct psb_intel_crtc *intel_crtc = to_psb_intel_crtc(crtc);
+	struct gma_crtc *gma_crtc = to_gma_crtc(crtc);
 
 	hdmib = (2 << 10);
 
@@ -77,7 +77,7 @@ static void cdv_hdmi_mode_set(struct drm_encoder *encoder,
 	if (adjusted_mode->flags & DRM_MODE_FLAG_PHSYNC)
 		hdmib |= HDMI_HSYNC_ACTIVE_HIGH;
 
-	if (intel_crtc->pipe == 1)
+	if (gma_crtc->pipe == 1)
 		hdmib |= HDMIB_PIPE_B_SELECT;
 
 	if (hdmi_priv->has_hdmi_audio) {
@@ -99,9 +99,8 @@ static bool cdv_hdmi_mode_fixup(struct drm_encoder *encoder,
 static void cdv_hdmi_dpms(struct drm_encoder *encoder, int mode)
 {
 	struct drm_device *dev = encoder->dev;
-	struct psb_intel_encoder *psb_intel_encoder =
-						to_psb_intel_encoder(encoder);
-	struct mid_intel_hdmi_priv *hdmi_priv = psb_intel_encoder->dev_priv;
+	struct gma_encoder *gma_encoder = to_gma_encoder(encoder);
+	struct mid_intel_hdmi_priv *hdmi_priv = gma_encoder->dev_priv;
 	u32 hdmib;
 
 	hdmib = REG_READ(hdmi_priv->hdmi_reg);
@@ -116,9 +115,8 @@ static void cdv_hdmi_dpms(struct drm_encoder *encoder, int mode)
 static void cdv_hdmi_save(struct drm_connector *connector)
 {
 	struct drm_device *dev = connector->dev;
-	struct psb_intel_encoder *psb_intel_encoder =
-					psb_intel_attached_encoder(connector);
-	struct mid_intel_hdmi_priv *hdmi_priv = psb_intel_encoder->dev_priv;
+	struct gma_encoder *gma_encoder = gma_attached_encoder(connector);
+	struct mid_intel_hdmi_priv *hdmi_priv = gma_encoder->dev_priv;
 
 	hdmi_priv->save_HDMIB = REG_READ(hdmi_priv->hdmi_reg);
 }
@@ -126,9 +124,8 @@ static void cdv_hdmi_save(struct drm_connector *connector)
 static void cdv_hdmi_restore(struct drm_connector *connector)
 {
 	struct drm_device *dev = connector->dev;
-	struct psb_intel_encoder *psb_intel_encoder =
-					psb_intel_attached_encoder(connector);
-	struct mid_intel_hdmi_priv *hdmi_priv = psb_intel_encoder->dev_priv;
+	struct gma_encoder *gma_encoder = gma_attached_encoder(connector);
+	struct mid_intel_hdmi_priv *hdmi_priv = gma_encoder->dev_priv;
 
 	REG_WRITE(hdmi_priv->hdmi_reg, hdmi_priv->save_HDMIB);
 	REG_READ(hdmi_priv->hdmi_reg);
@@ -137,13 +134,12 @@ static void cdv_hdmi_restore(struct drm_connector *connector)
 static enum drm_connector_status cdv_hdmi_detect(
 				struct drm_connector *connector, bool force)
 {
-	struct psb_intel_encoder *psb_intel_encoder =
-					psb_intel_attached_encoder(connector);
-	struct mid_intel_hdmi_priv *hdmi_priv = psb_intel_encoder->dev_priv;
+	struct gma_encoder *gma_encoder = gma_attached_encoder(connector);
+	struct mid_intel_hdmi_priv *hdmi_priv = gma_encoder->dev_priv;
 	struct edid *edid = NULL;
 	enum drm_connector_status status = connector_status_disconnected;
 
-	edid = drm_get_edid(connector, &psb_intel_encoder->i2c_bus->adapter);
+	edid = drm_get_edid(connector, &gma_encoder->i2c_bus->adapter);
 
 	hdmi_priv->has_hdmi_sink = false;
 	hdmi_priv->has_hdmi_audio = false;
@@ -167,7 +163,7 @@ static int cdv_hdmi_set_property(struct drm_connector *connector,
 	struct drm_encoder *encoder = connector->encoder;
 
 	if (!strcmp(property->name, "scaling mode") && encoder) {
-		struct psb_intel_crtc *crtc = to_psb_intel_crtc(encoder->crtc);
+		struct gma_crtc *crtc = to_gma_crtc(encoder->crtc);
 		bool centre;
 		uint64_t curValue;
 
@@ -221,12 +217,11 @@ static int cdv_hdmi_set_property(struct drm_connector *connector,
  */
 static int cdv_hdmi_get_modes(struct drm_connector *connector)
 {
-	struct psb_intel_encoder *psb_intel_encoder =
-					psb_intel_attached_encoder(connector);
+	struct gma_encoder *gma_encoder = gma_attached_encoder(connector);
 	struct edid *edid = NULL;
 	int ret = 0;
 
-	edid = drm_get_edid(connector, &psb_intel_encoder->i2c_bus->adapter);
+	edid = drm_get_edid(connector, &gma_encoder->i2c_bus->adapter);
 	if (edid) {
 		drm_mode_connector_update_edid_property(connector, edid);
 		ret = drm_add_edid_modes(connector, edid);
@@ -256,11 +251,10 @@ static int cdv_hdmi_mode_valid(struct drm_connector *connector,
 
 static void cdv_hdmi_destroy(struct drm_connector *connector)
 {
-	struct psb_intel_encoder *psb_intel_encoder =
-					psb_intel_attached_encoder(connector);
+	struct gma_encoder *gma_encoder = gma_attached_encoder(connector);
 
-	if (psb_intel_encoder->i2c_bus)
-		psb_intel_i2c_destroy(psb_intel_encoder->i2c_bus);
+	if (gma_encoder->i2c_bus)
+		psb_intel_i2c_destroy(gma_encoder->i2c_bus);
 	drm_sysfs_connector_remove(connector);
 	drm_connector_cleanup(connector);
 	kfree(connector);
@@ -269,16 +263,16 @@ static void cdv_hdmi_destroy(struct drm_connector *connector)
 static const struct drm_encoder_helper_funcs cdv_hdmi_helper_funcs = {
 	.dpms = cdv_hdmi_dpms,
 	.mode_fixup = cdv_hdmi_mode_fixup,
-	.prepare = psb_intel_encoder_prepare,
+	.prepare = gma_encoder_prepare,
 	.mode_set = cdv_hdmi_mode_set,
-	.commit = psb_intel_encoder_commit,
+	.commit = gma_encoder_commit,
 };
 
 static const struct drm_connector_helper_funcs
 					cdv_hdmi_connector_helper_funcs = {
 	.get_modes = cdv_hdmi_get_modes,
 	.mode_valid = cdv_hdmi_mode_valid,
-	.best_encoder = psb_intel_best_encoder,
+	.best_encoder = gma_best_encoder,
 };
 
 static const struct drm_connector_funcs cdv_hdmi_connector_funcs = {
@@ -294,23 +288,22 @@ static const struct drm_connector_funcs cdv_hdmi_connector_funcs = {
 void cdv_hdmi_init(struct drm_device *dev,
 			struct psb_intel_mode_device *mode_dev, int reg)
 {
-	struct psb_intel_encoder *psb_intel_encoder;
-	struct psb_intel_connector *psb_intel_connector;
+	struct gma_encoder *gma_encoder;
+	struct gma_connector *gma_connector;
 	struct drm_connector *connector;
 	struct drm_encoder *encoder;
 	struct mid_intel_hdmi_priv *hdmi_priv;
 	int ddc_bus;
 
-	psb_intel_encoder = kzalloc(sizeof(struct psb_intel_encoder),
-				    GFP_KERNEL);
+	gma_encoder = kzalloc(sizeof(struct gma_encoder), GFP_KERNEL);
 
-	if (!psb_intel_encoder)
+	if (!gma_encoder)
 		return;
 
-	psb_intel_connector = kzalloc(sizeof(struct psb_intel_connector),
+	gma_connector = kzalloc(sizeof(struct gma_connector),
 				      GFP_KERNEL);
 
-	if (!psb_intel_connector)
+	if (!gma_connector)
 		goto err_connector;
 
 	hdmi_priv = kzalloc(sizeof(struct mid_intel_hdmi_priv), GFP_KERNEL);
@@ -318,9 +311,9 @@ void cdv_hdmi_init(struct drm_device *dev,
 	if (!hdmi_priv)
 		goto err_priv;
 
-	connector = &psb_intel_connector->base;
+	connector = &gma_connector->base;
 	connector->polled = DRM_CONNECTOR_POLL_HPD;
-	encoder = &psb_intel_encoder->base;
+	encoder = &gma_encoder->base;
 	drm_connector_init(dev, connector,
 			   &cdv_hdmi_connector_funcs,
 			   DRM_MODE_CONNECTOR_DVID);
@@ -328,12 +321,11 @@ void cdv_hdmi_init(struct drm_device *dev,
 	drm_encoder_init(dev, encoder, &psb_intel_lvds_enc_funcs,
 			 DRM_MODE_ENCODER_TMDS);
 
-	psb_intel_connector_attach_encoder(psb_intel_connector,
-					   psb_intel_encoder);
-	psb_intel_encoder->type = INTEL_OUTPUT_HDMI;
+	gma_connector_attach_encoder(gma_connector, gma_encoder);
+	gma_encoder->type = INTEL_OUTPUT_HDMI;
 	hdmi_priv->hdmi_reg = reg;
 	hdmi_priv->has_hdmi_sink = false;
-	psb_intel_encoder->dev_priv = hdmi_priv;
+	gma_encoder->dev_priv = hdmi_priv;
 
 	drm_encoder_helper_add(encoder, &cdv_hdmi_helper_funcs);
 	drm_connector_helper_add(connector,
@@ -349,11 +341,11 @@ void cdv_hdmi_init(struct drm_device *dev,
 	switch (reg) {
 	case SDVOB:
 		ddc_bus = GPIOE;
-		psb_intel_encoder->ddi_select = DDI0_SELECT;
+		gma_encoder->ddi_select = DDI0_SELECT;
 		break;
 	case SDVOC:
 		ddc_bus = GPIOD;
-		psb_intel_encoder->ddi_select = DDI1_SELECT;
+		gma_encoder->ddi_select = DDI1_SELECT;
 		break;
 	default:
 		DRM_ERROR("unknown reg 0x%x for HDMI\n", reg);
@@ -361,16 +353,15 @@ void cdv_hdmi_init(struct drm_device *dev,
 		break;
 	}
 
-	psb_intel_encoder->i2c_bus = psb_intel_i2c_create(dev,
+	gma_encoder->i2c_bus = psb_intel_i2c_create(dev,
 				ddc_bus, (reg == SDVOB) ? "HDMIB" : "HDMIC");
 
-	if (!psb_intel_encoder->i2c_bus) {
+	if (!gma_encoder->i2c_bus) {
 		dev_err(dev->dev, "No ddc adapter available!\n");
 		goto failed_ddc;
 	}
 
-	hdmi_priv->hdmi_i2c_adapter =
-				&(psb_intel_encoder->i2c_bus->adapter);
+	hdmi_priv->hdmi_i2c_adapter = &(gma_encoder->i2c_bus->adapter);
 	hdmi_priv->dev = dev;
 	drm_sysfs_connector_add(connector);
 	return;
@@ -379,7 +370,7 @@ failed_ddc:
 	drm_encoder_cleanup(encoder);
 	drm_connector_cleanup(connector);
 err_priv:
-	kfree(psb_intel_connector);
+	kfree(gma_connector);
 err_connector:
-	kfree(psb_intel_encoder);
+	kfree(gma_encoder);
 }
diff --git a/drivers/gpu/drm/gma500/cdv_intel_lvds.c b/drivers/gpu/drm/gma500/cdv_intel_lvds.c
index d81dbc3368f0..20e08e65d46c 100644
--- a/drivers/gpu/drm/gma500/cdv_intel_lvds.c
+++ b/drivers/gpu/drm/gma500/cdv_intel_lvds.c
@@ -356,8 +356,7 @@ static void cdv_intel_lvds_mode_set(struct drm_encoder *encoder,
 {
 	struct drm_device *dev = encoder->dev;
 	struct drm_psb_private *dev_priv = dev->dev_private;
-	struct psb_intel_crtc *psb_intel_crtc = to_psb_intel_crtc(
-							encoder->crtc);
+	struct gma_crtc *gma_crtc = to_gma_crtc(encoder->crtc);
 	u32 pfit_control;
 
 	/*
@@ -379,7 +378,7 @@ static void cdv_intel_lvds_mode_set(struct drm_encoder *encoder,
 	else
 		pfit_control = 0;
 
-	pfit_control |= psb_intel_crtc->pipe << PFIT_PIPE_SHIFT;
+	pfit_control |= gma_crtc->pipe << PFIT_PIPE_SHIFT;
 
 	if (dev_priv->lvds_dither)
 		pfit_control |= PANEL_8TO6_DITHER_ENABLE;
@@ -407,12 +406,11 @@ static int cdv_intel_lvds_get_modes(struct drm_connector *connector)
 {
 	struct drm_device *dev = connector->dev;
 	struct drm_psb_private *dev_priv = dev->dev_private;
-	struct psb_intel_encoder *psb_intel_encoder =
-					psb_intel_attached_encoder(connector);
+	struct gma_encoder *gma_encoder = gma_attached_encoder(connector);
 	struct psb_intel_mode_device *mode_dev = &dev_priv->mode_dev;
 	int ret;
 
-	ret = psb_intel_ddc_get_modes(connector, &psb_intel_encoder->i2c_bus->adapter);
+	ret = psb_intel_ddc_get_modes(connector, &gma_encoder->i2c_bus->adapter);
 
 	if (ret)
 		return ret;
@@ -444,11 +442,10 @@ static int cdv_intel_lvds_get_modes(struct drm_connector *connector)
  */
 static void cdv_intel_lvds_destroy(struct drm_connector *connector)
 {
-	struct psb_intel_encoder *psb_intel_encoder =
-					psb_intel_attached_encoder(connector);
+	struct gma_encoder *gma_encoder = gma_attached_encoder(connector);
 
-	if (psb_intel_encoder->i2c_bus)
-		psb_intel_i2c_destroy(psb_intel_encoder->i2c_bus);
+	if (gma_encoder->i2c_bus)
+		psb_intel_i2c_destroy(gma_encoder->i2c_bus);
 	drm_sysfs_connector_remove(connector);
 	drm_connector_cleanup(connector);
 	kfree(connector);
@@ -461,8 +458,7 @@ static int cdv_intel_lvds_set_property(struct drm_connector *connector,
 	struct drm_encoder *encoder = connector->encoder;
 
 	if (!strcmp(property->name, "scaling mode") && encoder) {
-		struct psb_intel_crtc *crtc =
-					to_psb_intel_crtc(encoder->crtc);
+		struct gma_crtc *crtc = to_gma_crtc(encoder->crtc);
 		uint64_t curValue;
 
 		if (!crtc)
@@ -529,7 +525,7 @@ static const struct drm_connector_helper_funcs
 				cdv_intel_lvds_connector_helper_funcs = {
 	.get_modes = cdv_intel_lvds_get_modes,
 	.mode_valid = cdv_intel_lvds_mode_valid,
-	.best_encoder = psb_intel_best_encoder,
+	.best_encoder = gma_best_encoder,
 };
 
 static const struct drm_connector_funcs cdv_intel_lvds_connector_funcs = {
@@ -612,8 +608,8 @@ static bool lvds_is_present_in_vbt(struct drm_device *dev,
 void cdv_intel_lvds_init(struct drm_device *dev,
 		     struct psb_intel_mode_device *mode_dev)
 {
-	struct psb_intel_encoder *psb_intel_encoder;
-	struct psb_intel_connector *psb_intel_connector;
+	struct gma_encoder *gma_encoder;
+	struct gma_connector *gma_connector;
 	struct cdv_intel_lvds_priv *lvds_priv;
 	struct drm_connector *connector;
 	struct drm_encoder *encoder;
@@ -630,24 +626,24 @@ void cdv_intel_lvds_init(struct drm_device *dev,
 		return;
 	}
 
-	psb_intel_encoder = kzalloc(sizeof(struct psb_intel_encoder),
+	gma_encoder = kzalloc(sizeof(struct gma_encoder),
 				    GFP_KERNEL);
-	if (!psb_intel_encoder)
+	if (!gma_encoder)
 		return;
 
-	psb_intel_connector = kzalloc(sizeof(struct psb_intel_connector),
+	gma_connector = kzalloc(sizeof(struct gma_connector),
 				      GFP_KERNEL);
-	if (!psb_intel_connector)
+	if (!gma_connector)
 		goto failed_connector;
 
 	lvds_priv = kzalloc(sizeof(struct cdv_intel_lvds_priv), GFP_KERNEL);
 	if (!lvds_priv)
 		goto failed_lvds_priv;
 
-	psb_intel_encoder->dev_priv = lvds_priv;
+	gma_encoder->dev_priv = lvds_priv;
 
-	connector = &psb_intel_connector->base;
-	encoder = &psb_intel_encoder->base;
+	connector = &gma_connector->base;
+	encoder = &gma_encoder->base;
 
 
 	drm_connector_init(dev, connector,
@@ -659,9 +655,8 @@ void cdv_intel_lvds_init(struct drm_device *dev,
 			 DRM_MODE_ENCODER_LVDS);
 
 
-	psb_intel_connector_attach_encoder(psb_intel_connector,
-					   psb_intel_encoder);
-	psb_intel_encoder->type = INTEL_OUTPUT_LVDS;
+	gma_connector_attach_encoder(gma_connector, gma_encoder);
+	gma_encoder->type = INTEL_OUTPUT_LVDS;
 
 	drm_encoder_helper_add(encoder, &cdv_intel_lvds_helper_funcs);
 	drm_connector_helper_add(connector,
@@ -682,16 +677,16 @@ void cdv_intel_lvds_init(struct drm_device *dev,
 	 * Set up I2C bus
 	 * FIXME: distroy i2c_bus when exit
 	 */
-	psb_intel_encoder->i2c_bus = psb_intel_i2c_create(dev,
+	gma_encoder->i2c_bus = psb_intel_i2c_create(dev,
 							 GPIOB,
 							 "LVDSBLC_B");
-	if (!psb_intel_encoder->i2c_bus) {
+	if (!gma_encoder->i2c_bus) {
 		dev_printk(KERN_ERR,
 			&dev->pdev->dev, "I2C bus registration failed.\n");
 		goto failed_blc_i2c;
 	}
-	psb_intel_encoder->i2c_bus->slave_addr = 0x2C;
-	dev_priv->lvds_i2c_bus = psb_intel_encoder->i2c_bus;
+	gma_encoder->i2c_bus->slave_addr = 0x2C;
+	dev_priv->lvds_i2c_bus = gma_encoder->i2c_bus;
 
 	/*
 	 * LVDS discovery:
@@ -704,10 +699,10 @@ void cdv_intel_lvds_init(struct drm_device *dev,
 	 */
 
 	/* Set up the DDC bus. */
-	psb_intel_encoder->ddc_bus = psb_intel_i2c_create(dev,
+	gma_encoder->ddc_bus = psb_intel_i2c_create(dev,
 							 GPIOC,
 							 "LVDSDDC_C");
-	if (!psb_intel_encoder->ddc_bus) {
+	if (!gma_encoder->ddc_bus) {
 		dev_printk(KERN_ERR, &dev->pdev->dev,
 			   "DDC bus registration " "failed.\n");
 		goto failed_ddc;
@@ -718,7 +713,7 @@ void cdv_intel_lvds_init(struct drm_device *dev,
 	 * preferred mode is the right one.
 	 */
 	psb_intel_ddc_get_modes(connector,
-				&psb_intel_encoder->ddc_bus->adapter);
+				&gma_encoder->ddc_bus->adapter);
 	list_for_each_entry(scan, &connector->probed_modes, head) {
 		if (scan->type & DRM_MODE_TYPE_PREFERRED) {
 			mode_dev->panel_fixed_mode =
@@ -782,19 +777,19 @@ out:
 
 failed_find:
 	printk(KERN_ERR "Failed find\n");
-	if (psb_intel_encoder->ddc_bus)
-		psb_intel_i2c_destroy(psb_intel_encoder->ddc_bus);
+	if (gma_encoder->ddc_bus)
+		psb_intel_i2c_destroy(gma_encoder->ddc_bus);
 failed_ddc:
 	printk(KERN_ERR "Failed DDC\n");
-	if (psb_intel_encoder->i2c_bus)
-		psb_intel_i2c_destroy(psb_intel_encoder->i2c_bus);
+	if (gma_encoder->i2c_bus)
+		psb_intel_i2c_destroy(gma_encoder->i2c_bus);
 failed_blc_i2c:
 	printk(KERN_ERR "Failed BLC\n");
 	drm_encoder_cleanup(encoder);
 	drm_connector_cleanup(connector);
 	kfree(lvds_priv);
 failed_lvds_priv:
-	kfree(psb_intel_connector);
+	kfree(gma_connector);
 failed_connector:
-	kfree(psb_intel_encoder);
+	kfree(gma_encoder);
 }
diff --git a/drivers/gpu/drm/gma500/framebuffer.c b/drivers/gpu/drm/gma500/framebuffer.c
index 8b1b6d923abe..01dd7d225762 100644
--- a/drivers/gpu/drm/gma500/framebuffer.c
+++ b/drivers/gpu/drm/gma500/framebuffer.c
@@ -321,10 +321,8 @@ static struct gtt_range *psbfb_alloc(struct drm_device *dev, int aligned_size)
 	/* Begin by trying to use stolen memory backing */
 	backing = psb_gtt_alloc_range(dev, aligned_size, "fb", 1);
 	if (backing) {
-		if (drm_gem_private_object_init(dev,
-					&backing->gem, aligned_size) == 0)
-			return backing;
-		psb_gtt_free_range(dev, backing);
+		drm_gem_private_object_init(dev, &backing->gem, aligned_size);
+		return backing;
 	}
 	return NULL;
 }
@@ -522,21 +520,21 @@ static struct drm_framebuffer *psb_user_framebuffer_create
 static void psbfb_gamma_set(struct drm_crtc *crtc, u16 red, u16 green,
 							u16 blue, int regno)
 {
-	struct psb_intel_crtc *intel_crtc = to_psb_intel_crtc(crtc);
+	struct gma_crtc *gma_crtc = to_gma_crtc(crtc);
 
-	intel_crtc->lut_r[regno] = red >> 8;
-	intel_crtc->lut_g[regno] = green >> 8;
-	intel_crtc->lut_b[regno] = blue >> 8;
+	gma_crtc->lut_r[regno] = red >> 8;
+	gma_crtc->lut_g[regno] = green >> 8;
+	gma_crtc->lut_b[regno] = blue >> 8;
 }
 
 static void psbfb_gamma_get(struct drm_crtc *crtc, u16 *red,
 					u16 *green, u16 *blue, int regno)
 {
-	struct psb_intel_crtc *intel_crtc = to_psb_intel_crtc(crtc);
+	struct gma_crtc *gma_crtc = to_gma_crtc(crtc);
 
-	*red = intel_crtc->lut_r[regno] << 8;
-	*green = intel_crtc->lut_g[regno] << 8;
-	*blue = intel_crtc->lut_b[regno] << 8;
+	*red = gma_crtc->lut_r[regno] << 8;
+	*green = gma_crtc->lut_g[regno] << 8;
+	*blue = gma_crtc->lut_b[regno] << 8;
 }
 
 static int psbfb_probe(struct drm_fb_helper *helper,
@@ -705,13 +703,12 @@ static void psb_setup_outputs(struct drm_device *dev)
 
 	list_for_each_entry(connector, &dev->mode_config.connector_list,
 			    head) {
-		struct psb_intel_encoder *psb_intel_encoder =
-			psb_intel_attached_encoder(connector);
-		struct drm_encoder *encoder = &psb_intel_encoder->base;
+		struct gma_encoder *gma_encoder = gma_attached_encoder(connector);
+		struct drm_encoder *encoder = &gma_encoder->base;
 		int crtc_mask = 0, clone_mask = 0;
 
 		/* valid crtcs */
-		switch (psb_intel_encoder->type) {
+		switch (gma_encoder->type) {
 		case INTEL_OUTPUT_ANALOG:
 			crtc_mask = (1 << 0);
 			clone_mask = (1 << INTEL_OUTPUT_ANALOG);
@@ -746,7 +743,7 @@ static void psb_setup_outputs(struct drm_device *dev)
 		}
 		encoder->possible_crtcs = crtc_mask;
 		encoder->possible_clones =
-		    psb_intel_connector_clones(dev, clone_mask);
+		    gma_connector_clones(dev, clone_mask);
 	}
 }
 
diff --git a/drivers/gpu/drm/gma500/framebuffer.h b/drivers/gpu/drm/gma500/framebuffer.h
index 989558a9e6ee..395f20b07aab 100644
--- a/drivers/gpu/drm/gma500/framebuffer.h
+++ b/drivers/gpu/drm/gma500/framebuffer.h
@@ -41,7 +41,7 @@ struct psb_fbdev {
 
 #define to_psb_fb(x) container_of(x, struct psb_framebuffer, base)
 
-extern int psb_intel_connector_clones(struct drm_device *dev, int type_mask);
+extern int gma_connector_clones(struct drm_device *dev, int type_mask);
 
 #endif
 
diff --git a/drivers/gpu/drm/gma500/gem.c b/drivers/gpu/drm/gma500/gem.c
index eefd6cc5b80d..10ae8c52d06f 100644
--- a/drivers/gpu/drm/gma500/gem.c
+++ b/drivers/gpu/drm/gma500/gem.c
@@ -26,6 +26,7 @@
 #include <drm/drmP.h>
 #include <drm/drm.h>
 #include <drm/gma_drm.h>
+#include <drm/drm_vma_manager.h>
 #include "psb_drv.h"
 
 int psb_gem_init_object(struct drm_gem_object *obj)
@@ -38,8 +39,7 @@ void psb_gem_free_object(struct drm_gem_object *obj)
 	struct gtt_range *gtt = container_of(obj, struct gtt_range, gem);
 
 	/* Remove the list map if one is present */
-	if (obj->map_list.map)
-		drm_gem_free_mmap_offset(obj);
+	drm_gem_free_mmap_offset(obj);
 	drm_gem_object_release(obj);
 
 	/* This must occur last as it frees up the memory of the GEM object */
@@ -81,13 +81,10 @@ int psb_gem_dumb_map_gtt(struct drm_file *file, struct drm_device *dev,
 	/* What validation is needed here ? */
 
 	/* Make it mmapable */
-	if (!obj->map_list.map) {
-		ret = drm_gem_create_mmap_offset(obj);
-		if (ret)
-			goto out;
-	}
-	/* GEM should really work out the hash offsets for us */
-	*offset = (u64)obj->map_list.hash.key << PAGE_SHIFT;
+	ret = drm_gem_create_mmap_offset(obj);
+	if (ret)
+		goto out;
+	*offset = drm_vma_node_offset_addr(&obj->vma_node);
 out:
 	drm_gem_object_unreference(obj);
 unlock:
@@ -165,23 +162,6 @@ int psb_gem_dumb_create(struct drm_file *file, struct drm_device *dev,
 }
 
 /**
- *	psb_gem_dumb_destroy	-	destroy a dumb buffer
- *	@file: client file
- *	@dev: our DRM device
- *	@handle: the object handle
- *
- *	Destroy a handle that was created via psb_gem_dumb_create, at least
- *	we hope it was created that way. i915 seems to assume the caller
- *	does the checking but that might be worth review ! FIXME
- */
-int psb_gem_dumb_destroy(struct drm_file *file, struct drm_device *dev,
-			uint32_t handle)
-{
-	/* No special work needed, drop the reference and see what falls out */
-	return drm_gem_handle_delete(file, handle);
-}
-
-/**
  *	psb_gem_fault		-	pagefault handler for GEM objects
  *	@vma: the VMA of the GEM object
  *	@vmf: fault detail
@@ -261,11 +241,12 @@ static int psb_gem_create_stolen(struct drm_file *file, struct drm_device *dev,
 	struct gtt_range *gtt = psb_gtt_alloc_range(dev, size, "gem", 1);
 	if (gtt == NULL)
 		return -ENOMEM;
-	if (drm_gem_private_object_init(dev, &gtt->gem, size) != 0)
-		goto free_gtt;
+
+	drm_gem_private_object_init(dev, &gtt->gem, size);
 	if (drm_gem_handle_create(file, &gtt->gem, handle) == 0)
 		return 0;
-free_gtt:
+
+	drm_gem_object_release(&gtt->gem);
 	psb_gtt_free_range(dev, gtt);
 	return -ENOMEM;
 }
diff --git a/drivers/gpu/drm/gma500/gma_display.c b/drivers/gpu/drm/gma500/gma_display.c
new file mode 100644
index 000000000000..24e8af3d22bf
--- /dev/null
+++ b/drivers/gpu/drm/gma500/gma_display.c
@@ -0,0 +1,776 @@
+/*
+ * Copyright © 2006-2011 Intel Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc.,
+ * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ *
+ * Authors:
+ *	Eric Anholt <eric@anholt.net>
+ *	Patrik Jakobsson <patrik.r.jakobsson@gmail.com>
+ */
+
+#include <drm/drmP.h>
+#include "gma_display.h"
+#include "psb_intel_drv.h"
+#include "psb_intel_reg.h"
+#include "psb_drv.h"
+#include "framebuffer.h"
+
+/**
+ * Returns whether any output on the specified pipe is of the specified type
+ */
+bool gma_pipe_has_type(struct drm_crtc *crtc, int type)
+{
+	struct drm_device *dev = crtc->dev;
+	struct drm_mode_config *mode_config = &dev->mode_config;
+	struct drm_connector *l_entry;
+
+	list_for_each_entry(l_entry, &mode_config->connector_list, head) {
+		if (l_entry->encoder && l_entry->encoder->crtc == crtc) {
+			struct gma_encoder *gma_encoder =
+						gma_attached_encoder(l_entry);
+			if (gma_encoder->type == type)
+				return true;
+		}
+	}
+
+	return false;
+}
+
+void gma_wait_for_vblank(struct drm_device *dev)
+{
+	/* Wait for 20ms, i.e. one cycle at 50hz. */
+	mdelay(20);
+}
+
+int gma_pipe_set_base(struct drm_crtc *crtc, int x, int y,
+		      struct drm_framebuffer *old_fb)
+{
+	struct drm_device *dev = crtc->dev;
+	struct drm_psb_private *dev_priv = dev->dev_private;
+	struct gma_crtc *gma_crtc = to_gma_crtc(crtc);
+	struct psb_framebuffer *psbfb = to_psb_fb(crtc->fb);
+	int pipe = gma_crtc->pipe;
+	const struct psb_offset *map = &dev_priv->regmap[pipe];
+	unsigned long start, offset;
+	u32 dspcntr;
+	int ret = 0;
+
+	if (!gma_power_begin(dev, true))
+		return 0;
+
+	/* no fb bound */
+	if (!crtc->fb) {
+		dev_err(dev->dev, "No FB bound\n");
+		goto gma_pipe_cleaner;
+	}
+
+	/* We are displaying this buffer, make sure it is actually loaded
+	   into the GTT */
+	ret = psb_gtt_pin(psbfb->gtt);
+	if (ret < 0)
+		goto gma_pipe_set_base_exit;
+	start = psbfb->gtt->offset;
+	offset = y * crtc->fb->pitches[0] + x * (crtc->fb->bits_per_pixel / 8);
+
+	REG_WRITE(map->stride, crtc->fb->pitches[0]);
+
+	dspcntr = REG_READ(map->cntr);
+	dspcntr &= ~DISPPLANE_PIXFORMAT_MASK;
+
+	switch (crtc->fb->bits_per_pixel) {
+	case 8:
+		dspcntr |= DISPPLANE_8BPP;
+		break;
+	case 16:
+		if (crtc->fb->depth == 15)
+			dspcntr |= DISPPLANE_15_16BPP;
+		else
+			dspcntr |= DISPPLANE_16BPP;
+		break;
+	case 24:
+	case 32:
+		dspcntr |= DISPPLANE_32BPP_NO_ALPHA;
+		break;
+	default:
+		dev_err(dev->dev, "Unknown color depth\n");
+		ret = -EINVAL;
+		goto gma_pipe_set_base_exit;
+	}
+	REG_WRITE(map->cntr, dspcntr);
+
+	dev_dbg(dev->dev,
+		"Writing base %08lX %08lX %d %d\n", start, offset, x, y);
+
+	/* FIXME: Investigate whether this really is the base for psb and why
+		  the linear offset is named base for the other chips. map->surf
+		  should be the base and map->linoff the offset for all chips */
+	if (IS_PSB(dev)) {
+		REG_WRITE(map->base, offset + start);
+		REG_READ(map->base);
+	} else {
+		REG_WRITE(map->base, offset);
+		REG_READ(map->base);
+		REG_WRITE(map->surf, start);
+		REG_READ(map->surf);
+	}
+
+gma_pipe_cleaner:
+	/* If there was a previous display we can now unpin it */
+	if (old_fb)
+		psb_gtt_unpin(to_psb_fb(old_fb)->gtt);
+
+gma_pipe_set_base_exit:
+	gma_power_end(dev);
+	return ret;
+}
+
+/* Loads the palette/gamma unit for the CRTC with the prepared values */
+void gma_crtc_load_lut(struct drm_crtc *crtc)
+{
+	struct drm_device *dev = crtc->dev;
+	struct drm_psb_private *dev_priv = dev->dev_private;
+	struct gma_crtc *gma_crtc = to_gma_crtc(crtc);
+	const struct psb_offset *map = &dev_priv->regmap[gma_crtc->pipe];
+	int palreg = map->palette;
+	int i;
+
+	/* The clocks have to be on to load the palette. */
+	if (!crtc->enabled)
+		return;
+
+	if (gma_power_begin(dev, false)) {
+		for (i = 0; i < 256; i++) {
+			REG_WRITE(palreg + 4 * i,
+				  ((gma_crtc->lut_r[i] +
+				  gma_crtc->lut_adj[i]) << 16) |
+				  ((gma_crtc->lut_g[i] +
+				  gma_crtc->lut_adj[i]) << 8) |
+				  (gma_crtc->lut_b[i] +
+				  gma_crtc->lut_adj[i]));
+		}
+		gma_power_end(dev);
+	} else {
+		for (i = 0; i < 256; i++) {
+			/* FIXME: Why pipe[0] and not pipe[..._crtc->pipe]? */
+			dev_priv->regs.pipe[0].palette[i] =
+				  ((gma_crtc->lut_r[i] +
+				  gma_crtc->lut_adj[i]) << 16) |
+				  ((gma_crtc->lut_g[i] +
+				  gma_crtc->lut_adj[i]) << 8) |
+				  (gma_crtc->lut_b[i] +
+				  gma_crtc->lut_adj[i]);
+		}
+
+	}
+}
+
+void gma_crtc_gamma_set(struct drm_crtc *crtc, u16 *red, u16 *green, u16 *blue,
+			u32 start, u32 size)
+{
+	struct gma_crtc *gma_crtc = to_gma_crtc(crtc);
+	int i;
+	int end = (start + size > 256) ? 256 : start + size;
+
+	for (i = start; i < end; i++) {
+		gma_crtc->lut_r[i] = red[i] >> 8;
+		gma_crtc->lut_g[i] = green[i] >> 8;
+		gma_crtc->lut_b[i] = blue[i] >> 8;
+	}
+
+	gma_crtc_load_lut(crtc);
+}
+
+/**
+ * Sets the power management mode of the pipe and plane.
+ *
+ * This code should probably grow support for turning the cursor off and back
+ * on appropriately at the same time as we're turning the pipe off/on.
+ */
+void gma_crtc_dpms(struct drm_crtc *crtc, int mode)
+{
+	struct drm_device *dev = crtc->dev;
+	struct drm_psb_private *dev_priv = dev->dev_private;
+	struct gma_crtc *gma_crtc = to_gma_crtc(crtc);
+	int pipe = gma_crtc->pipe;
+	const struct psb_offset *map = &dev_priv->regmap[pipe];
+	u32 temp;
+
+	/* XXX: When our outputs are all unaware of DPMS modes other than off
+	 * and on, we should map those modes to DRM_MODE_DPMS_OFF in the CRTC.
+	 */
+
+	if (IS_CDV(dev))
+		dev_priv->ops->disable_sr(dev);
+
+	switch (mode) {
+	case DRM_MODE_DPMS_ON:
+	case DRM_MODE_DPMS_STANDBY:
+	case DRM_MODE_DPMS_SUSPEND:
+		if (gma_crtc->active)
+			break;
+
+		gma_crtc->active = true;
+
+		/* Enable the DPLL */
+		temp = REG_READ(map->dpll);
+		if ((temp & DPLL_VCO_ENABLE) == 0) {
+			REG_WRITE(map->dpll, temp);
+			REG_READ(map->dpll);
+			/* Wait for the clocks to stabilize. */
+			udelay(150);
+			REG_WRITE(map->dpll, temp | DPLL_VCO_ENABLE);
+			REG_READ(map->dpll);
+			/* Wait for the clocks to stabilize. */
+			udelay(150);
+			REG_WRITE(map->dpll, temp | DPLL_VCO_ENABLE);
+			REG_READ(map->dpll);
+			/* Wait for the clocks to stabilize. */
+			udelay(150);
+		}
+
+		/* Enable the plane */
+		temp = REG_READ(map->cntr);
+		if ((temp & DISPLAY_PLANE_ENABLE) == 0) {
+			REG_WRITE(map->cntr,
+				  temp | DISPLAY_PLANE_ENABLE);
+			/* Flush the plane changes */
+			REG_WRITE(map->base, REG_READ(map->base));
+		}
+
+		udelay(150);
+
+		/* Enable the pipe */
+		temp = REG_READ(map->conf);
+		if ((temp & PIPEACONF_ENABLE) == 0)
+			REG_WRITE(map->conf, temp | PIPEACONF_ENABLE);
+
+		temp = REG_READ(map->status);
+		temp &= ~(0xFFFF);
+		temp |= PIPE_FIFO_UNDERRUN;
+		REG_WRITE(map->status, temp);
+		REG_READ(map->status);
+
+		gma_crtc_load_lut(crtc);
+
+		/* Give the overlay scaler a chance to enable
+		 * if it's on this pipe */
+		/* psb_intel_crtc_dpms_video(crtc, true); TODO */
+		break;
+	case DRM_MODE_DPMS_OFF:
+		if (!gma_crtc->active)
+			break;
+
+		gma_crtc->active = false;
+
+		/* Give the overlay scaler a chance to disable
+		 * if it's on this pipe */
+		/* psb_intel_crtc_dpms_video(crtc, FALSE); TODO */
+
+		/* Disable the VGA plane that we never use */
+		REG_WRITE(VGACNTRL, VGA_DISP_DISABLE);
+
+		/* Turn off vblank interrupts */
+		drm_vblank_off(dev, pipe);
+
+		/* Wait for vblank for the disable to take effect */
+		gma_wait_for_vblank(dev);
+
+		/* Disable plane */
+		temp = REG_READ(map->cntr);
+		if ((temp & DISPLAY_PLANE_ENABLE) != 0) {
+			REG_WRITE(map->cntr,
+				  temp & ~DISPLAY_PLANE_ENABLE);
+			/* Flush the plane changes */
+			REG_WRITE(map->base, REG_READ(map->base));
+			REG_READ(map->base);
+		}
+
+		/* Disable pipe */
+		temp = REG_READ(map->conf);
+		if ((temp & PIPEACONF_ENABLE) != 0) {
+			REG_WRITE(map->conf, temp & ~PIPEACONF_ENABLE);
+			REG_READ(map->conf);
+		}
+
+		/* Wait for vblank for the disable to take effect. */
+		gma_wait_for_vblank(dev);
+
+		udelay(150);
+
+		/* Disable DPLL */
+		temp = REG_READ(map->dpll);
+		if ((temp & DPLL_VCO_ENABLE) != 0) {
+			REG_WRITE(map->dpll, temp & ~DPLL_VCO_ENABLE);
+			REG_READ(map->dpll);
+		}
+
+		/* Wait for the clocks to turn off. */
+		udelay(150);
+		break;
+	}
+
+	if (IS_CDV(dev))
+		dev_priv->ops->update_wm(dev, crtc);
+
+	/* Set FIFO watermarks */
+	REG_WRITE(DSPARB, 0x3F3E);
+}
+
+int gma_crtc_cursor_set(struct drm_crtc *crtc,
+			struct drm_file *file_priv,
+			uint32_t handle,
+			uint32_t width, uint32_t height)
+{
+	struct drm_device *dev = crtc->dev;
+	struct drm_psb_private *dev_priv = dev->dev_private;
+	struct gma_crtc *gma_crtc = to_gma_crtc(crtc);
+	int pipe = gma_crtc->pipe;
+	uint32_t control = (pipe == 0) ? CURACNTR : CURBCNTR;
+	uint32_t base = (pipe == 0) ? CURABASE : CURBBASE;
+	uint32_t temp;
+	size_t addr = 0;
+	struct gtt_range *gt;
+	struct gtt_range *cursor_gt = gma_crtc->cursor_gt;
+	struct drm_gem_object *obj;
+	void *tmp_dst, *tmp_src;
+	int ret = 0, i, cursor_pages;
+
+	/* If we didn't get a handle then turn the cursor off */
+	if (!handle) {
+		temp = CURSOR_MODE_DISABLE;
+
+		if (gma_power_begin(dev, false)) {
+			REG_WRITE(control, temp);
+			REG_WRITE(base, 0);
+			gma_power_end(dev);
+		}
+
+		/* Unpin the old GEM object */
+		if (gma_crtc->cursor_obj) {
+			gt = container_of(gma_crtc->cursor_obj,
+					  struct gtt_range, gem);
+			psb_gtt_unpin(gt);
+			drm_gem_object_unreference(gma_crtc->cursor_obj);
+			gma_crtc->cursor_obj = NULL;
+		}
+
+		return 0;
+	}
+
+	/* Currently we only support 64x64 cursors */
+	if (width != 64 || height != 64) {
+		dev_dbg(dev->dev, "We currently only support 64x64 cursors\n");
+		return -EINVAL;
+	}
+
+	obj = drm_gem_object_lookup(dev, file_priv, handle);
+	if (!obj)
+		return -ENOENT;
+
+	if (obj->size < width * height * 4) {
+		dev_dbg(dev->dev, "Buffer is too small\n");
+		ret = -ENOMEM;
+		goto unref_cursor;
+	}
+
+	gt = container_of(obj, struct gtt_range, gem);
+
+	/* Pin the memory into the GTT */
+	ret = psb_gtt_pin(gt);
+	if (ret) {
+		dev_err(dev->dev, "Can not pin down handle 0x%x\n", handle);
+		goto unref_cursor;
+	}
+
+	if (dev_priv->ops->cursor_needs_phys) {
+		if (cursor_gt == NULL) {
+			dev_err(dev->dev, "No hardware cursor mem available");
+			ret = -ENOMEM;
+			goto unref_cursor;
+		}
+
+		/* Prevent overflow */
+		if (gt->npage > 4)
+			cursor_pages = 4;
+		else
+			cursor_pages = gt->npage;
+
+		/* Copy the cursor to cursor mem */
+		tmp_dst = dev_priv->vram_addr + cursor_gt->offset;
+		for (i = 0; i < cursor_pages; i++) {
+			tmp_src = kmap(gt->pages[i]);
+			memcpy(tmp_dst, tmp_src, PAGE_SIZE);
+			kunmap(gt->pages[i]);
+			tmp_dst += PAGE_SIZE;
+		}
+
+		addr = gma_crtc->cursor_addr;
+	} else {
+		addr = gt->offset;
+		gma_crtc->cursor_addr = addr;
+	}
+
+	temp = 0;
+	/* set the pipe for the cursor */
+	temp |= (pipe << 28);
+	temp |= CURSOR_MODE_64_ARGB_AX | MCURSOR_GAMMA_ENABLE;
+
+	if (gma_power_begin(dev, false)) {
+		REG_WRITE(control, temp);
+		REG_WRITE(base, addr);
+		gma_power_end(dev);
+	}
+
+	/* unpin the old bo */
+	if (gma_crtc->cursor_obj) {
+		gt = container_of(gma_crtc->cursor_obj, struct gtt_range, gem);
+		psb_gtt_unpin(gt);
+		drm_gem_object_unreference(gma_crtc->cursor_obj);
+	}
+
+	gma_crtc->cursor_obj = obj;
+	return ret;
+
+unref_cursor:
+	drm_gem_object_unreference(obj);
+	return ret;
+}
+
+int gma_crtc_cursor_move(struct drm_crtc *crtc, int x, int y)
+{
+	struct drm_device *dev = crtc->dev;
+	struct gma_crtc *gma_crtc = to_gma_crtc(crtc);
+	int pipe = gma_crtc->pipe;
+	uint32_t temp = 0;
+	uint32_t addr;
+
+	if (x < 0) {
+		temp |= (CURSOR_POS_SIGN << CURSOR_X_SHIFT);
+		x = -x;
+	}
+	if (y < 0) {
+		temp |= (CURSOR_POS_SIGN << CURSOR_Y_SHIFT);
+		y = -y;
+	}
+
+	temp |= ((x & CURSOR_POS_MASK) << CURSOR_X_SHIFT);
+	temp |= ((y & CURSOR_POS_MASK) << CURSOR_Y_SHIFT);
+
+	addr = gma_crtc->cursor_addr;
+
+	if (gma_power_begin(dev, false)) {
+		REG_WRITE((pipe == 0) ? CURAPOS : CURBPOS, temp);
+		REG_WRITE((pipe == 0) ? CURABASE : CURBBASE, addr);
+		gma_power_end(dev);
+	}
+	return 0;
+}
+
+bool gma_crtc_mode_fixup(struct drm_crtc *crtc,
+			 const struct drm_display_mode *mode,
+			 struct drm_display_mode *adjusted_mode)
+{
+	return true;
+}
+
+void gma_crtc_prepare(struct drm_crtc *crtc)
+{
+	struct drm_crtc_helper_funcs *crtc_funcs = crtc->helper_private;
+	crtc_funcs->dpms(crtc, DRM_MODE_DPMS_OFF);
+}
+
+void gma_crtc_commit(struct drm_crtc *crtc)
+{
+	struct drm_crtc_helper_funcs *crtc_funcs = crtc->helper_private;
+	crtc_funcs->dpms(crtc, DRM_MODE_DPMS_ON);
+}
+
+void gma_crtc_disable(struct drm_crtc *crtc)
+{
+	struct gtt_range *gt;
+	struct drm_crtc_helper_funcs *crtc_funcs = crtc->helper_private;
+
+	crtc_funcs->dpms(crtc, DRM_MODE_DPMS_OFF);
+
+	if (crtc->fb) {
+		gt = to_psb_fb(crtc->fb)->gtt;
+		psb_gtt_unpin(gt);
+	}
+}
+
+void gma_crtc_destroy(struct drm_crtc *crtc)
+{
+	struct gma_crtc *gma_crtc = to_gma_crtc(crtc);
+
+	kfree(gma_crtc->crtc_state);
+	drm_crtc_cleanup(crtc);
+	kfree(gma_crtc);
+}
+
+int gma_crtc_set_config(struct drm_mode_set *set)
+{
+	struct drm_device *dev = set->crtc->dev;
+	struct drm_psb_private *dev_priv = dev->dev_private;
+	int ret;
+
+	if (!dev_priv->rpm_enabled)
+		return drm_crtc_helper_set_config(set);
+
+	pm_runtime_forbid(&dev->pdev->dev);
+	ret = drm_crtc_helper_set_config(set);
+	pm_runtime_allow(&dev->pdev->dev);
+
+	return ret;
+}
+
+/**
+ * Save HW states of given crtc
+ */
+void gma_crtc_save(struct drm_crtc *crtc)
+{
+	struct drm_device *dev = crtc->dev;
+	struct drm_psb_private *dev_priv = dev->dev_private;
+	struct gma_crtc *gma_crtc = to_gma_crtc(crtc);
+	struct psb_intel_crtc_state *crtc_state = gma_crtc->crtc_state;
+	const struct psb_offset *map = &dev_priv->regmap[gma_crtc->pipe];
+	uint32_t palette_reg;
+	int i;
+
+	if (!crtc_state) {
+		dev_err(dev->dev, "No CRTC state found\n");
+		return;
+	}
+
+	crtc_state->saveDSPCNTR = REG_READ(map->cntr);
+	crtc_state->savePIPECONF = REG_READ(map->conf);
+	crtc_state->savePIPESRC = REG_READ(map->src);
+	crtc_state->saveFP0 = REG_READ(map->fp0);
+	crtc_state->saveFP1 = REG_READ(map->fp1);
+	crtc_state->saveDPLL = REG_READ(map->dpll);
+	crtc_state->saveHTOTAL = REG_READ(map->htotal);
+	crtc_state->saveHBLANK = REG_READ(map->hblank);
+	crtc_state->saveHSYNC = REG_READ(map->hsync);
+	crtc_state->saveVTOTAL = REG_READ(map->vtotal);
+	crtc_state->saveVBLANK = REG_READ(map->vblank);
+	crtc_state->saveVSYNC = REG_READ(map->vsync);
+	crtc_state->saveDSPSTRIDE = REG_READ(map->stride);
+
+	/* NOTE: DSPSIZE DSPPOS only for psb */
+	crtc_state->saveDSPSIZE = REG_READ(map->size);
+	crtc_state->saveDSPPOS = REG_READ(map->pos);
+
+	crtc_state->saveDSPBASE = REG_READ(map->base);
+
+	palette_reg = map->palette;
+	for (i = 0; i < 256; ++i)
+		crtc_state->savePalette[i] = REG_READ(palette_reg + (i << 2));
+}
+
+/**
+ * Restore HW states of given crtc
+ */
+void gma_crtc_restore(struct drm_crtc *crtc)
+{
+	struct drm_device *dev = crtc->dev;
+	struct drm_psb_private *dev_priv = dev->dev_private;
+	struct gma_crtc *gma_crtc =  to_gma_crtc(crtc);
+	struct psb_intel_crtc_state *crtc_state = gma_crtc->crtc_state;
+	const struct psb_offset *map = &dev_priv->regmap[gma_crtc->pipe];
+	uint32_t palette_reg;
+	int i;
+
+	if (!crtc_state) {
+		dev_err(dev->dev, "No crtc state\n");
+		return;
+	}
+
+	if (crtc_state->saveDPLL & DPLL_VCO_ENABLE) {
+		REG_WRITE(map->dpll,
+			crtc_state->saveDPLL & ~DPLL_VCO_ENABLE);
+		REG_READ(map->dpll);
+		udelay(150);
+	}
+
+	REG_WRITE(map->fp0, crtc_state->saveFP0);
+	REG_READ(map->fp0);
+
+	REG_WRITE(map->fp1, crtc_state->saveFP1);
+	REG_READ(map->fp1);
+
+	REG_WRITE(map->dpll, crtc_state->saveDPLL);
+	REG_READ(map->dpll);
+	udelay(150);
+
+	REG_WRITE(map->htotal, crtc_state->saveHTOTAL);
+	REG_WRITE(map->hblank, crtc_state->saveHBLANK);
+	REG_WRITE(map->hsync, crtc_state->saveHSYNC);
+	REG_WRITE(map->vtotal, crtc_state->saveVTOTAL);
+	REG_WRITE(map->vblank, crtc_state->saveVBLANK);
+	REG_WRITE(map->vsync, crtc_state->saveVSYNC);
+	REG_WRITE(map->stride, crtc_state->saveDSPSTRIDE);
+
+	REG_WRITE(map->size, crtc_state->saveDSPSIZE);
+	REG_WRITE(map->pos, crtc_state->saveDSPPOS);
+
+	REG_WRITE(map->src, crtc_state->savePIPESRC);
+	REG_WRITE(map->base, crtc_state->saveDSPBASE);
+	REG_WRITE(map->conf, crtc_state->savePIPECONF);
+
+	gma_wait_for_vblank(dev);
+
+	REG_WRITE(map->cntr, crtc_state->saveDSPCNTR);
+	REG_WRITE(map->base, crtc_state->saveDSPBASE);
+
+	gma_wait_for_vblank(dev);
+
+	palette_reg = map->palette;
+	for (i = 0; i < 256; ++i)
+		REG_WRITE(palette_reg + (i << 2), crtc_state->savePalette[i]);
+}
+
+void gma_encoder_prepare(struct drm_encoder *encoder)
+{
+	struct drm_encoder_helper_funcs *encoder_funcs =
+	    encoder->helper_private;
+	/* lvds has its own version of prepare see psb_intel_lvds_prepare */
+	encoder_funcs->dpms(encoder, DRM_MODE_DPMS_OFF);
+}
+
+void gma_encoder_commit(struct drm_encoder *encoder)
+{
+	struct drm_encoder_helper_funcs *encoder_funcs =
+	    encoder->helper_private;
+	/* lvds has its own version of commit see psb_intel_lvds_commit */
+	encoder_funcs->dpms(encoder, DRM_MODE_DPMS_ON);
+}
+
+void gma_encoder_destroy(struct drm_encoder *encoder)
+{
+	struct gma_encoder *intel_encoder = to_gma_encoder(encoder);
+
+	drm_encoder_cleanup(encoder);
+	kfree(intel_encoder);
+}
+
+/* Currently there is only a 1:1 mapping of encoders and connectors */
+struct drm_encoder *gma_best_encoder(struct drm_connector *connector)
+{
+	struct gma_encoder *gma_encoder = gma_attached_encoder(connector);
+
+	return &gma_encoder->base;
+}
+
+void gma_connector_attach_encoder(struct gma_connector *connector,
+				  struct gma_encoder *encoder)
+{
+	connector->encoder = encoder;
+	drm_mode_connector_attach_encoder(&connector->base,
+					  &encoder->base);
+}
+
+#define GMA_PLL_INVALID(s) { /* DRM_ERROR(s); */ return false; }
+
+bool gma_pll_is_valid(struct drm_crtc *crtc,
+		      const struct gma_limit_t *limit,
+		      struct gma_clock_t *clock)
+{
+	if (clock->p1 < limit->p1.min || limit->p1.max < clock->p1)
+		GMA_PLL_INVALID("p1 out of range");
+	if (clock->p < limit->p.min || limit->p.max < clock->p)
+		GMA_PLL_INVALID("p out of range");
+	if (clock->m2 < limit->m2.min || limit->m2.max < clock->m2)
+		GMA_PLL_INVALID("m2 out of range");
+	if (clock->m1 < limit->m1.min || limit->m1.max < clock->m1)
+		GMA_PLL_INVALID("m1 out of range");
+	/* On CDV m1 is always 0 */
+	if (clock->m1 <= clock->m2 && clock->m1 != 0)
+		GMA_PLL_INVALID("m1 <= m2 && m1 != 0");
+	if (clock->m < limit->m.min || limit->m.max < clock->m)
+		GMA_PLL_INVALID("m out of range");
+	if (clock->n < limit->n.min || limit->n.max < clock->n)
+		GMA_PLL_INVALID("n out of range");
+	if (clock->vco < limit->vco.min || limit->vco.max < clock->vco)
+		GMA_PLL_INVALID("vco out of range");
+	/* XXX: We may need to be checking "Dot clock"
+	 * depending on the multiplier, connector, etc.,
+	 * rather than just a single range.
+	 */
+	if (clock->dot < limit->dot.min || limit->dot.max < clock->dot)
+		GMA_PLL_INVALID("dot out of range");
+
+	return true;
+}
+
+bool gma_find_best_pll(const struct gma_limit_t *limit,
+		       struct drm_crtc *crtc, int target, int refclk,
+		       struct gma_clock_t *best_clock)
+{
+	struct drm_device *dev = crtc->dev;
+	const struct gma_clock_funcs *clock_funcs =
+						to_gma_crtc(crtc)->clock_funcs;
+	struct gma_clock_t clock;
+	int err = target;
+
+	if (gma_pipe_has_type(crtc, INTEL_OUTPUT_LVDS) &&
+	    (REG_READ(LVDS) & LVDS_PORT_EN) != 0) {
+		/*
+		 * For LVDS, if the panel is on, just rely on its current
+		 * settings for dual-channel.  We haven't figured out how to
+		 * reliably set up different single/dual channel state, if we
+		 * even can.
+		 */
+		if ((REG_READ(LVDS) & LVDS_CLKB_POWER_MASK) ==
+		    LVDS_CLKB_POWER_UP)
+			clock.p2 = limit->p2.p2_fast;
+		else
+			clock.p2 = limit->p2.p2_slow;
+	} else {
+		if (target < limit->p2.dot_limit)
+			clock.p2 = limit->p2.p2_slow;
+		else
+			clock.p2 = limit->p2.p2_fast;
+	}
+
+	memset(best_clock, 0, sizeof(*best_clock));
+
+	/* m1 is always 0 on CDV so the outmost loop will run just once */
+	for (clock.m1 = limit->m1.min; clock.m1 <= limit->m1.max; clock.m1++) {
+		for (clock.m2 = limit->m2.min;
+		     (clock.m2 < clock.m1 || clock.m1 == 0) &&
+		      clock.m2 <= limit->m2.max; clock.m2++) {
+			for (clock.n = limit->n.min;
+			     clock.n <= limit->n.max; clock.n++) {
+				for (clock.p1 = limit->p1.min;
+				     clock.p1 <= limit->p1.max;
+				     clock.p1++) {
+					int this_err;
+
+					clock_funcs->clock(refclk, &clock);
+
+					if (!clock_funcs->pll_is_valid(crtc,
+								limit, &clock))
+						continue;
+
+					this_err = abs(clock.dot - target);
+					if (this_err < err) {
+						*best_clock = clock;
+						err = this_err;
+					}
+				}
+			}
+		}
+	}
+
+	return err != target;
+}
diff --git a/drivers/gpu/drm/gma500/gma_display.h b/drivers/gpu/drm/gma500/gma_display.h
new file mode 100644
index 000000000000..78b9f986a6e5
--- /dev/null
+++ b/drivers/gpu/drm/gma500/gma_display.h
@@ -0,0 +1,103 @@
+/*
+ * Copyright © 2006-2011 Intel Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc.,
+ * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ *
+ * Authors:
+ *	Eric Anholt <eric@anholt.net>
+ *	Patrik Jakobsson <patrik.r.jakobsson@gmail.com>
+ */
+
+#ifndef _GMA_DISPLAY_H_
+#define _GMA_DISPLAY_H_
+
+#include <linux/pm_runtime.h>
+
+struct gma_clock_t {
+	/* given values */
+	int n;
+	int m1, m2;
+	int p1, p2;
+	/* derived values */
+	int dot;
+	int vco;
+	int m;
+	int p;
+};
+
+struct gma_range_t {
+	int min, max;
+};
+
+struct gma_p2_t {
+	int dot_limit;
+	int p2_slow, p2_fast;
+};
+
+struct gma_limit_t {
+	struct gma_range_t dot, vco, n, m, m1, m2, p, p1;
+	struct gma_p2_t p2;
+	bool (*find_pll)(const struct gma_limit_t *, struct drm_crtc *,
+			 int target, int refclk,
+			 struct gma_clock_t *best_clock);
+};
+
+struct gma_clock_funcs {
+	void (*clock)(int refclk, struct gma_clock_t *clock);
+	const struct gma_limit_t *(*limit)(struct drm_crtc *crtc, int refclk);
+	bool (*pll_is_valid)(struct drm_crtc *crtc,
+			     const struct gma_limit_t *limit,
+			     struct gma_clock_t *clock);
+};
+
+/* Common pipe related functions */
+extern bool gma_pipe_has_type(struct drm_crtc *crtc, int type);
+extern void gma_wait_for_vblank(struct drm_device *dev);
+extern int gma_pipe_set_base(struct drm_crtc *crtc, int x, int y,
+			     struct drm_framebuffer *old_fb);
+extern int gma_crtc_cursor_set(struct drm_crtc *crtc,
+			       struct drm_file *file_priv,
+			       uint32_t handle,
+			       uint32_t width, uint32_t height);
+extern int gma_crtc_cursor_move(struct drm_crtc *crtc, int x, int y);
+extern void gma_crtc_load_lut(struct drm_crtc *crtc);
+extern void gma_crtc_gamma_set(struct drm_crtc *crtc, u16 *red, u16 *green,
+			       u16 *blue, u32 start, u32 size);
+extern void gma_crtc_dpms(struct drm_crtc *crtc, int mode);
+extern bool gma_crtc_mode_fixup(struct drm_crtc *crtc,
+				const struct drm_display_mode *mode,
+				struct drm_display_mode *adjusted_mode);
+extern void gma_crtc_prepare(struct drm_crtc *crtc);
+extern void gma_crtc_commit(struct drm_crtc *crtc);
+extern void gma_crtc_disable(struct drm_crtc *crtc);
+extern void gma_crtc_destroy(struct drm_crtc *crtc);
+extern int gma_crtc_set_config(struct drm_mode_set *set);
+
+extern void gma_crtc_save(struct drm_crtc *crtc);
+extern void gma_crtc_restore(struct drm_crtc *crtc);
+
+extern void gma_encoder_prepare(struct drm_encoder *encoder);
+extern void gma_encoder_commit(struct drm_encoder *encoder);
+extern void gma_encoder_destroy(struct drm_encoder *encoder);
+
+/* Common clock related functions */
+extern const struct gma_limit_t *gma_limit(struct drm_crtc *crtc, int refclk);
+extern void gma_clock(int refclk, struct gma_clock_t *clock);
+extern bool gma_pll_is_valid(struct drm_crtc *crtc,
+			     const struct gma_limit_t *limit,
+			     struct gma_clock_t *clock);
+extern bool gma_find_best_pll(const struct gma_limit_t *limit,
+			      struct drm_crtc *crtc, int target, int refclk,
+			      struct gma_clock_t *best_clock);
+#endif
diff --git a/drivers/gpu/drm/gma500/gtt.c b/drivers/gpu/drm/gma500/gtt.c
index 1f82183536a3..2db731f00930 100644
--- a/drivers/gpu/drm/gma500/gtt.c
+++ b/drivers/gpu/drm/gma500/gtt.c
@@ -196,37 +196,18 @@ void psb_gtt_roll(struct drm_device *dev, struct gtt_range *r, int roll)
  */
 static int psb_gtt_attach_pages(struct gtt_range *gt)
 {
-	struct inode *inode;
-	struct address_space *mapping;
-	int i;
-	struct page *p;
-	int pages = gt->gem.size / PAGE_SIZE;
+	struct page **pages;
 
 	WARN_ON(gt->pages);
 
-	/* This is the shared memory object that backs the GEM resource */
-	inode = file_inode(gt->gem.filp);
-	mapping = inode->i_mapping;
+	pages = drm_gem_get_pages(&gt->gem, 0);
+	if (IS_ERR(pages))
+		return PTR_ERR(pages);
 
-	gt->pages = kmalloc(pages * sizeof(struct page *), GFP_KERNEL);
-	if (gt->pages == NULL)
-		return -ENOMEM;
-	gt->npage = pages;
+	gt->npage = gt->gem.size / PAGE_SIZE;
+	gt->pages = pages;
 
-	for (i = 0; i < pages; i++) {
-		p = shmem_read_mapping_page(mapping, i);
-		if (IS_ERR(p))
-			goto err;
-		gt->pages[i] = p;
-	}
 	return 0;
-
-err:
-	while (i--)
-		page_cache_release(gt->pages[i]);
-	kfree(gt->pages);
-	gt->pages = NULL;
-	return PTR_ERR(p);
 }
 
 /**
@@ -240,13 +221,7 @@ err:
  */
 static void psb_gtt_detach_pages(struct gtt_range *gt)
 {
-	int i;
-	for (i = 0; i < gt->npage; i++) {
-		/* FIXME: do we need to force dirty */
-		set_page_dirty(gt->pages[i]);
-		page_cache_release(gt->pages[i]);
-	}
-	kfree(gt->pages);
+	drm_gem_put_pages(&gt->gem, gt->pages, true, false);
 	gt->pages = NULL;
 }
 
diff --git a/drivers/gpu/drm/gma500/mdfld_dsi_output.c b/drivers/gpu/drm/gma500/mdfld_dsi_output.c
index 3abf8315f57c..860a4ee9baaf 100644
--- a/drivers/gpu/drm/gma500/mdfld_dsi_output.c
+++ b/drivers/gpu/drm/gma500/mdfld_dsi_output.c
@@ -249,12 +249,11 @@ static int mdfld_dsi_connector_set_property(struct drm_connector *connector,
 	struct drm_encoder *encoder = connector->encoder;
 
 	if (!strcmp(property->name, "scaling mode") && encoder) {
-		struct psb_intel_crtc *psb_crtc =
-					to_psb_intel_crtc(encoder->crtc);
+		struct gma_crtc *gma_crtc = to_gma_crtc(encoder->crtc);
 		bool centerechange;
 		uint64_t val;
 
-		if (!psb_crtc)
+		if (!gma_crtc)
 			goto set_prop_error;
 
 		switch (value) {
@@ -281,11 +280,11 @@ static int mdfld_dsi_connector_set_property(struct drm_connector *connector,
 		centerechange = (val == DRM_MODE_SCALE_NO_SCALE) ||
 			(value == DRM_MODE_SCALE_NO_SCALE);
 
-		if (psb_crtc->saved_mode.hdisplay != 0 &&
-		    psb_crtc->saved_mode.vdisplay != 0) {
+		if (gma_crtc->saved_mode.hdisplay != 0 &&
+		    gma_crtc->saved_mode.vdisplay != 0) {
 			if (centerechange) {
 				if (!drm_crtc_helper_set_mode(encoder->crtc,
-						&psb_crtc->saved_mode,
+						&gma_crtc->saved_mode,
 						encoder->crtc->x,
 						encoder->crtc->y,
 						encoder->crtc->fb))
@@ -294,8 +293,8 @@ static int mdfld_dsi_connector_set_property(struct drm_connector *connector,
 				struct drm_encoder_helper_funcs *funcs =
 						encoder->helper_private;
 				funcs->mode_set(encoder,
-					&psb_crtc->saved_mode,
-					&psb_crtc->saved_adjusted_mode);
+					&gma_crtc->saved_mode,
+					&gma_crtc->saved_adjusted_mode);
 			}
 		}
 	} else if (!strcmp(property->name, "backlight") && encoder) {
diff --git a/drivers/gpu/drm/gma500/mdfld_dsi_output.h b/drivers/gpu/drm/gma500/mdfld_dsi_output.h
index 36eb0744841c..45d5af0546bf 100644
--- a/drivers/gpu/drm/gma500/mdfld_dsi_output.h
+++ b/drivers/gpu/drm/gma500/mdfld_dsi_output.h
@@ -227,7 +227,7 @@ enum {
 #define DSI_DPI_DISABLE_BTA					BIT(3)
 
 struct mdfld_dsi_connector {
-	struct psb_intel_connector base;
+	struct gma_connector base;
 
 	int pipe;
 	void *private;
@@ -238,7 +238,7 @@ struct mdfld_dsi_connector {
 };
 
 struct mdfld_dsi_encoder {
-	struct psb_intel_encoder base;
+	struct gma_encoder base;
 	void *private;
 };
 
@@ -269,21 +269,21 @@ struct mdfld_dsi_config {
 static inline struct mdfld_dsi_connector *mdfld_dsi_connector(
 		struct drm_connector *connector)
 {
-	struct psb_intel_connector *psb_connector;
+	struct gma_connector *gma_connector;
 
-	psb_connector = to_psb_intel_connector(connector);
+	gma_connector = to_gma_connector(connector);
 
-	return container_of(psb_connector, struct mdfld_dsi_connector, base);
+	return container_of(gma_connector, struct mdfld_dsi_connector, base);
 }
 
 static inline struct mdfld_dsi_encoder *mdfld_dsi_encoder(
 		struct drm_encoder *encoder)
 {
-	struct psb_intel_encoder *psb_encoder;
+	struct gma_encoder *gma_encoder;
 
-	psb_encoder = to_psb_intel_encoder(encoder);
+	gma_encoder = to_gma_encoder(encoder);
 
-	return container_of(psb_encoder, struct mdfld_dsi_encoder, base);
+	return container_of(gma_encoder, struct mdfld_dsi_encoder, base);
 }
 
 static inline struct mdfld_dsi_config *
diff --git a/drivers/gpu/drm/gma500/mdfld_intel_display.c b/drivers/gpu/drm/gma500/mdfld_intel_display.c
index 74485dc43945..321c00a944e9 100644
--- a/drivers/gpu/drm/gma500/mdfld_intel_display.c
+++ b/drivers/gpu/drm/gma500/mdfld_intel_display.c
@@ -23,7 +23,7 @@
 
 #include <drm/drmP.h>
 #include "psb_intel_reg.h"
-#include "psb_intel_display.h"
+#include "gma_display.h"
 #include "framebuffer.h"
 #include "mdfld_output.h"
 #include "mdfld_dsi_output.h"
@@ -65,7 +65,7 @@ void mdfldWaitForPipeDisable(struct drm_device *dev, int pipe)
 	}
 
 	/* FIXME JLIU7_PO */
-	psb_intel_wait_for_vblank(dev);
+	gma_wait_for_vblank(dev);
 	return;
 
 	/* Wait for for the pipe disable to take effect. */
@@ -93,7 +93,7 @@ void mdfldWaitForPipeEnable(struct drm_device *dev, int pipe)
 	}
 
 	/* FIXME JLIU7_PO */
-	psb_intel_wait_for_vblank(dev);
+	gma_wait_for_vblank(dev);
 	return;
 
 	/* Wait for for the pipe enable to take effect. */
@@ -104,25 +104,6 @@ void mdfldWaitForPipeEnable(struct drm_device *dev, int pipe)
 	}
 }
 
-static void psb_intel_crtc_prepare(struct drm_crtc *crtc)
-{
-	struct drm_crtc_helper_funcs *crtc_funcs = crtc->helper_private;
-	crtc_funcs->dpms(crtc, DRM_MODE_DPMS_OFF);
-}
-
-static void psb_intel_crtc_commit(struct drm_crtc *crtc)
-{
-	struct drm_crtc_helper_funcs *crtc_funcs = crtc->helper_private;
-	crtc_funcs->dpms(crtc, DRM_MODE_DPMS_ON);
-}
-
-static bool psb_intel_crtc_mode_fixup(struct drm_crtc *crtc,
-				  const struct drm_display_mode *mode,
-				  struct drm_display_mode *adjusted_mode)
-{
-	return true;
-}
-
 /**
  * Return the pipe currently connected to the panel fitter,
  * or -1 if the panel fitter is not present or not in use
@@ -184,9 +165,9 @@ static int mdfld__intel_pipe_set_base(struct drm_crtc *crtc, int x, int y,
 {
 	struct drm_device *dev = crtc->dev;
 	struct drm_psb_private *dev_priv = dev->dev_private;
-	struct psb_intel_crtc *psb_intel_crtc = to_psb_intel_crtc(crtc);
+	struct gma_crtc *gma_crtc = to_gma_crtc(crtc);
 	struct psb_framebuffer *psbfb = to_psb_fb(crtc->fb);
-	int pipe = psb_intel_crtc->pipe;
+	int pipe = gma_crtc->pipe;
 	const struct psb_offset *map = &dev_priv->regmap[pipe];
 	unsigned long start, offset;
 	u32 dspcntr;
@@ -324,8 +305,8 @@ static void mdfld_crtc_dpms(struct drm_crtc *crtc, int mode)
 {
 	struct drm_device *dev = crtc->dev;
 	struct drm_psb_private *dev_priv = dev->dev_private;
-	struct psb_intel_crtc *psb_intel_crtc = to_psb_intel_crtc(crtc);
-	int pipe = psb_intel_crtc->pipe;
+	struct gma_crtc *gma_crtc = to_gma_crtc(crtc);
+	int pipe = gma_crtc->pipe;
 	const struct psb_offset *map = &dev_priv->regmap[pipe];
 	u32 pipeconf = dev_priv->pipeconf[pipe];
 	u32 temp;
@@ -436,7 +417,7 @@ static void mdfld_crtc_dpms(struct drm_crtc *crtc, int mode)
 			}
 		}
 
-		psb_intel_crtc_load_lut(crtc);
+		gma_crtc_load_lut(crtc);
 
 		/* Give the overlay scaler a chance to enable
 		   if it's on this pipe */
@@ -611,8 +592,8 @@ static const struct mrst_limit_t *mdfld_limit(struct drm_crtc *crtc)
 	struct drm_device *dev = crtc->dev;
 	struct drm_psb_private *dev_priv = dev->dev_private;
 
-	if (psb_intel_pipe_has_type(crtc, INTEL_OUTPUT_MIPI)
-	    || psb_intel_pipe_has_type(crtc, INTEL_OUTPUT_MIPI2)) {
+	if (gma_pipe_has_type(crtc, INTEL_OUTPUT_MIPI)
+	    || gma_pipe_has_type(crtc, INTEL_OUTPUT_MIPI2)) {
 		if ((ksel == KSEL_CRYSTAL_19) || (ksel == KSEL_BYPASS_19))
 			limit = &mdfld_limits[MDFLD_LIMT_DSIPLL_19];
 		else if (ksel == KSEL_BYPASS_25)
@@ -624,7 +605,7 @@ static const struct mrst_limit_t *mdfld_limit(struct drm_crtc *crtc)
 			 (dev_priv->core_freq == 100 ||
 				dev_priv->core_freq == 200))
 			limit = &mdfld_limits[MDFLD_LIMT_DSIPLL_100];
-	} else if (psb_intel_pipe_has_type(crtc, INTEL_OUTPUT_HDMI)) {
+	} else if (gma_pipe_has_type(crtc, INTEL_OUTPUT_HDMI)) {
 		if ((ksel == KSEL_CRYSTAL_19) || (ksel == KSEL_BYPASS_19))
 			limit = &mdfld_limits[MDFLD_LIMT_DPLL_19];
 		else if (ksel == KSEL_BYPASS_25)
@@ -688,9 +669,9 @@ static int mdfld_crtc_mode_set(struct drm_crtc *crtc,
 			      struct drm_framebuffer *old_fb)
 {
 	struct drm_device *dev = crtc->dev;
-	struct psb_intel_crtc *psb_intel_crtc = to_psb_intel_crtc(crtc);
+	struct gma_crtc *gma_crtc = to_gma_crtc(crtc);
 	struct drm_psb_private *dev_priv = dev->dev_private;
-	int pipe = psb_intel_crtc->pipe;
+	int pipe = gma_crtc->pipe;
 	const struct psb_offset *map = &dev_priv->regmap[pipe];
 	int refclk = 0;
 	int clk_n = 0, clk_p2 = 0, clk_byte = 1, clk = 0, m_conv = 0,
@@ -700,7 +681,7 @@ static int mdfld_crtc_mode_set(struct drm_crtc *crtc,
 	u32 dpll = 0, fp = 0;
 	bool is_mipi = false, is_mipi2 = false, is_hdmi = false;
 	struct drm_mode_config *mode_config = &dev->mode_config;
-	struct psb_intel_encoder *psb_intel_encoder = NULL;
+	struct gma_encoder *gma_encoder = NULL;
 	uint64_t scalingType = DRM_MODE_SCALE_FULLSCREEN;
 	struct drm_encoder *encoder;
 	struct drm_connector *connector;
@@ -749,9 +730,9 @@ static int mdfld_crtc_mode_set(struct drm_crtc *crtc,
 	if (!gma_power_begin(dev, true))
 		return 0;
 
-	memcpy(&psb_intel_crtc->saved_mode, mode,
+	memcpy(&gma_crtc->saved_mode, mode,
 					sizeof(struct drm_display_mode));
-	memcpy(&psb_intel_crtc->saved_adjusted_mode, adjusted_mode,
+	memcpy(&gma_crtc->saved_adjusted_mode, adjusted_mode,
 					sizeof(struct drm_display_mode));
 
 	list_for_each_entry(connector, &mode_config->connector_list, head) {
@@ -766,9 +747,9 @@ static int mdfld_crtc_mode_set(struct drm_crtc *crtc,
 		if (encoder->crtc != crtc)
 			continue;
 
-		psb_intel_encoder = psb_intel_attached_encoder(connector);
+		gma_encoder = gma_attached_encoder(connector);
 
-		switch (psb_intel_encoder->type) {
+		switch (gma_encoder->type) {
 		case INTEL_OUTPUT_MIPI:
 			is_mipi = true;
 			break;
@@ -819,7 +800,7 @@ static int mdfld_crtc_mode_set(struct drm_crtc *crtc,
 
 	REG_WRITE(map->pos, 0);
 
-	if (psb_intel_encoder)
+	if (gma_encoder)
 		drm_object_property_get_value(&connector->base,
 			dev->mode_config.scaling_mode_property, &scalingType);
 
@@ -1034,7 +1015,7 @@ static int mdfld_crtc_mode_set(struct drm_crtc *crtc,
 
 	/* Wait for for the pipe enable to take effect. */
 	REG_WRITE(map->cntr, dev_priv->dspcntr[pipe]);
-	psb_intel_wait_for_vblank(dev);
+	gma_wait_for_vblank(dev);
 
 mrst_crtc_mode_set_exit:
 
@@ -1045,10 +1026,10 @@ mrst_crtc_mode_set_exit:
 
 const struct drm_crtc_helper_funcs mdfld_helper_funcs = {
 	.dpms = mdfld_crtc_dpms,
-	.mode_fixup = psb_intel_crtc_mode_fixup,
+	.mode_fixup = gma_crtc_mode_fixup,
 	.mode_set = mdfld_crtc_mode_set,
 	.mode_set_base = mdfld__intel_pipe_set_base,
-	.prepare = psb_intel_crtc_prepare,
-	.commit = psb_intel_crtc_commit,
+	.prepare = gma_crtc_prepare,
+	.commit = gma_crtc_commit,
 };
 
diff --git a/drivers/gpu/drm/gma500/oaktrail_crtc.c b/drivers/gpu/drm/gma500/oaktrail_crtc.c
index 3071526bc3c1..54c98962b73e 100644
--- a/drivers/gpu/drm/gma500/oaktrail_crtc.c
+++ b/drivers/gpu/drm/gma500/oaktrail_crtc.c
@@ -23,7 +23,7 @@
 #include "psb_drv.h"
 #include "psb_intel_drv.h"
 #include "psb_intel_reg.h"
-#include "psb_intel_display.h"
+#include "gma_display.h"
 #include "power.h"
 
 struct psb_intel_range_t {
@@ -88,8 +88,8 @@ static const struct oaktrail_limit_t *oaktrail_limit(struct drm_crtc *crtc)
 	struct drm_device *dev = crtc->dev;
 	struct drm_psb_private *dev_priv = dev->dev_private;
 
-	if (psb_intel_pipe_has_type(crtc, INTEL_OUTPUT_LVDS)
-	    || psb_intel_pipe_has_type(crtc, INTEL_OUTPUT_MIPI)) {
+	if (gma_pipe_has_type(crtc, INTEL_OUTPUT_LVDS)
+	    || gma_pipe_has_type(crtc, INTEL_OUTPUT_MIPI)) {
 		switch (dev_priv->core_freq) {
 		case 100:
 			limit = &oaktrail_limits[MRST_LIMIT_LVDS_100L];
@@ -163,8 +163,8 @@ static void oaktrail_crtc_dpms(struct drm_crtc *crtc, int mode)
 {
 	struct drm_device *dev = crtc->dev;
 	struct drm_psb_private *dev_priv = dev->dev_private;
-	struct psb_intel_crtc *psb_intel_crtc = to_psb_intel_crtc(crtc);
-	int pipe = psb_intel_crtc->pipe;
+	struct gma_crtc *gma_crtc = to_gma_crtc(crtc);
+	int pipe = gma_crtc->pipe;
 	const struct psb_offset *map = &dev_priv->regmap[pipe];
 	u32 temp;
 
@@ -212,7 +212,7 @@ static void oaktrail_crtc_dpms(struct drm_crtc *crtc, int mode)
 			REG_WRITE(map->base, REG_READ(map->base));
 		}
 
-		psb_intel_crtc_load_lut(crtc);
+		gma_crtc_load_lut(crtc);
 
 		/* Give the overlay scaler a chance to enable
 		   if it's on this pipe */
@@ -242,7 +242,7 @@ static void oaktrail_crtc_dpms(struct drm_crtc *crtc, int mode)
 			REG_READ(map->conf);
 		}
 		/* Wait for for the pipe disable to take effect. */
-		psb_intel_wait_for_vblank(dev);
+		gma_wait_for_vblank(dev);
 
 		temp = REG_READ(map->dpll);
 		if ((temp & DPLL_VCO_ENABLE) != 0) {
@@ -292,9 +292,9 @@ static int oaktrail_crtc_mode_set(struct drm_crtc *crtc,
 			      struct drm_framebuffer *old_fb)
 {
 	struct drm_device *dev = crtc->dev;
-	struct psb_intel_crtc *psb_intel_crtc = to_psb_intel_crtc(crtc);
+	struct gma_crtc *gma_crtc = to_gma_crtc(crtc);
 	struct drm_psb_private *dev_priv = dev->dev_private;
-	int pipe = psb_intel_crtc->pipe;
+	int pipe = gma_crtc->pipe;
 	const struct psb_offset *map = &dev_priv->regmap[pipe];
 	int refclk = 0;
 	struct oaktrail_clock_t clock;
@@ -303,7 +303,7 @@ static int oaktrail_crtc_mode_set(struct drm_crtc *crtc,
 	bool is_lvds = false;
 	bool is_mipi = false;
 	struct drm_mode_config *mode_config = &dev->mode_config;
-	struct psb_intel_encoder *psb_intel_encoder = NULL;
+	struct gma_encoder *gma_encoder = NULL;
 	uint64_t scalingType = DRM_MODE_SCALE_FULLSCREEN;
 	struct drm_connector *connector;
 
@@ -313,10 +313,10 @@ static int oaktrail_crtc_mode_set(struct drm_crtc *crtc,
 	if (!gma_power_begin(dev, true))
 		return 0;
 
-	memcpy(&psb_intel_crtc->saved_mode,
+	memcpy(&gma_crtc->saved_mode,
 		mode,
 		sizeof(struct drm_display_mode));
-	memcpy(&psb_intel_crtc->saved_adjusted_mode,
+	memcpy(&gma_crtc->saved_adjusted_mode,
 		adjusted_mode,
 		sizeof(struct drm_display_mode));
 
@@ -324,9 +324,9 @@ static int oaktrail_crtc_mode_set(struct drm_crtc *crtc,
 		if (!connector->encoder || connector->encoder->crtc != crtc)
 			continue;
 
-		psb_intel_encoder = psb_intel_attached_encoder(connector);
+		gma_encoder = gma_attached_encoder(connector);
 
-		switch (psb_intel_encoder->type) {
+		switch (gma_encoder->type) {
 		case INTEL_OUTPUT_LVDS:
 			is_lvds = true;
 			break;
@@ -350,7 +350,7 @@ static int oaktrail_crtc_mode_set(struct drm_crtc *crtc,
 		  ((mode->crtc_hdisplay - 1) << 16) |
 		  (mode->crtc_vdisplay - 1));
 
-	if (psb_intel_encoder)
+	if (gma_encoder)
 		drm_object_property_get_value(&connector->base,
 			dev->mode_config.scaling_mode_property, &scalingType);
 
@@ -484,31 +484,24 @@ static int oaktrail_crtc_mode_set(struct drm_crtc *crtc,
 
 	REG_WRITE(map->conf, pipeconf);
 	REG_READ(map->conf);
-	psb_intel_wait_for_vblank(dev);
+	gma_wait_for_vblank(dev);
 
 	REG_WRITE(map->cntr, dspcntr);
-	psb_intel_wait_for_vblank(dev);
+	gma_wait_for_vblank(dev);
 
 oaktrail_crtc_mode_set_exit:
 	gma_power_end(dev);
 	return 0;
 }
 
-static bool oaktrail_crtc_mode_fixup(struct drm_crtc *crtc,
-				  const struct drm_display_mode *mode,
-				  struct drm_display_mode *adjusted_mode)
-{
-	return true;
-}
-
 static int oaktrail_pipe_set_base(struct drm_crtc *crtc,
 			    int x, int y, struct drm_framebuffer *old_fb)
 {
 	struct drm_device *dev = crtc->dev;
 	struct drm_psb_private *dev_priv = dev->dev_private;
-	struct psb_intel_crtc *psb_intel_crtc = to_psb_intel_crtc(crtc);
+	struct gma_crtc *gma_crtc = to_gma_crtc(crtc);
 	struct psb_framebuffer *psbfb = to_psb_fb(crtc->fb);
-	int pipe = psb_intel_crtc->pipe;
+	int pipe = gma_crtc->pipe;
 	const struct psb_offset *map = &dev_priv->regmap[pipe];
 	unsigned long start, offset;
 
@@ -563,24 +556,12 @@ pipe_set_base_exit:
 	return ret;
 }
 
-static void oaktrail_crtc_prepare(struct drm_crtc *crtc)
-{
-	struct drm_crtc_helper_funcs *crtc_funcs = crtc->helper_private;
-	crtc_funcs->dpms(crtc, DRM_MODE_DPMS_OFF);
-}
-
-static void oaktrail_crtc_commit(struct drm_crtc *crtc)
-{
-	struct drm_crtc_helper_funcs *crtc_funcs = crtc->helper_private;
-	crtc_funcs->dpms(crtc, DRM_MODE_DPMS_ON);
-}
-
 const struct drm_crtc_helper_funcs oaktrail_helper_funcs = {
 	.dpms = oaktrail_crtc_dpms,
-	.mode_fixup = oaktrail_crtc_mode_fixup,
+	.mode_fixup = gma_crtc_mode_fixup,
 	.mode_set = oaktrail_crtc_mode_set,
 	.mode_set_base = oaktrail_pipe_set_base,
-	.prepare = oaktrail_crtc_prepare,
-	.commit = oaktrail_crtc_commit,
+	.prepare = gma_crtc_prepare,
+	.commit = gma_crtc_commit,
 };
 
diff --git a/drivers/gpu/drm/gma500/oaktrail_hdmi.c b/drivers/gpu/drm/gma500/oaktrail_hdmi.c
index f036f1fc161e..38153143ed8c 100644
--- a/drivers/gpu/drm/gma500/oaktrail_hdmi.c
+++ b/drivers/gpu/drm/gma500/oaktrail_hdmi.c
@@ -155,12 +155,6 @@ static void oaktrail_hdmi_audio_disable(struct drm_device *dev)
 	HDMI_READ(HDMI_HCR);
 }
 
-static void wait_for_vblank(struct drm_device *dev)
-{
-	/* Wait for 20ms, i.e. one cycle at 50hz. */
-	mdelay(20);
-}
-
 static unsigned int htotal_calculate(struct drm_display_mode *mode)
 {
 	u32 htotal, new_crtc_htotal;
@@ -372,10 +366,10 @@ int oaktrail_crtc_hdmi_mode_set(struct drm_crtc *crtc,
 
 	REG_WRITE(PCH_PIPEBCONF, pipeconf);
 	REG_READ(PCH_PIPEBCONF);
-	wait_for_vblank(dev);
+	gma_wait_for_vblank(dev);
 
 	REG_WRITE(dspcntr_reg, dspcntr);
-	wait_for_vblank(dev);
+	gma_wait_for_vblank(dev);
 
 	gma_power_end(dev);
 
@@ -459,7 +453,7 @@ void oaktrail_crtc_hdmi_dpms(struct drm_crtc *crtc, int mode)
 			REG_READ(PCH_PIPEBCONF);
 		}
 
-		wait_for_vblank(dev);
+		gma_wait_for_vblank(dev);
 
 		/* Enable plane */
 		temp = REG_READ(DSPBCNTR);
@@ -470,7 +464,7 @@ void oaktrail_crtc_hdmi_dpms(struct drm_crtc *crtc, int mode)
 			REG_READ(DSPBSURF);
 		}
 
-		psb_intel_crtc_load_lut(crtc);
+		gma_crtc_load_lut(crtc);
 	}
 
 	/* DSPARB */
@@ -615,16 +609,16 @@ static void oaktrail_hdmi_destroy(struct drm_connector *connector)
 static const struct drm_encoder_helper_funcs oaktrail_hdmi_helper_funcs = {
 	.dpms = oaktrail_hdmi_dpms,
 	.mode_fixup = oaktrail_hdmi_mode_fixup,
-	.prepare = psb_intel_encoder_prepare,
+	.prepare = gma_encoder_prepare,
 	.mode_set = oaktrail_hdmi_mode_set,
-	.commit = psb_intel_encoder_commit,
+	.commit = gma_encoder_commit,
 };
 
 static const struct drm_connector_helper_funcs
 					oaktrail_hdmi_connector_helper_funcs = {
 	.get_modes = oaktrail_hdmi_get_modes,
 	.mode_valid = oaktrail_hdmi_mode_valid,
-	.best_encoder = psb_intel_best_encoder,
+	.best_encoder = gma_best_encoder,
 };
 
 static const struct drm_connector_funcs oaktrail_hdmi_connector_funcs = {
@@ -646,21 +640,21 @@ static const struct drm_encoder_funcs oaktrail_hdmi_enc_funcs = {
 void oaktrail_hdmi_init(struct drm_device *dev,
 					struct psb_intel_mode_device *mode_dev)
 {
-	struct psb_intel_encoder *psb_intel_encoder;
-	struct psb_intel_connector *psb_intel_connector;
+	struct gma_encoder *gma_encoder;
+	struct gma_connector *gma_connector;
 	struct drm_connector *connector;
 	struct drm_encoder *encoder;
 
-	psb_intel_encoder = kzalloc(sizeof(struct psb_intel_encoder), GFP_KERNEL);
-	if (!psb_intel_encoder)
+	gma_encoder = kzalloc(sizeof(struct gma_encoder), GFP_KERNEL);
+	if (!gma_encoder)
 		return;
 
-	psb_intel_connector = kzalloc(sizeof(struct psb_intel_connector), GFP_KERNEL);
-	if (!psb_intel_connector)
+	gma_connector = kzalloc(sizeof(struct gma_connector), GFP_KERNEL);
+	if (!gma_connector)
 		goto failed_connector;
 
-	connector = &psb_intel_connector->base;
-	encoder = &psb_intel_encoder->base;
+	connector = &gma_connector->base;
+	encoder = &gma_encoder->base;
 	drm_connector_init(dev, connector,
 			   &oaktrail_hdmi_connector_funcs,
 			   DRM_MODE_CONNECTOR_DVID);
@@ -669,10 +663,9 @@ void oaktrail_hdmi_init(struct drm_device *dev,
 			 &oaktrail_hdmi_enc_funcs,
 			 DRM_MODE_ENCODER_TMDS);
 
-	psb_intel_connector_attach_encoder(psb_intel_connector,
-					   psb_intel_encoder);
+	gma_connector_attach_encoder(gma_connector, gma_encoder);
 
-	psb_intel_encoder->type = INTEL_OUTPUT_HDMI;
+	gma_encoder->type = INTEL_OUTPUT_HDMI;
 	drm_encoder_helper_add(encoder, &oaktrail_hdmi_helper_funcs);
 	drm_connector_helper_add(connector, &oaktrail_hdmi_connector_helper_funcs);
 
@@ -685,7 +678,7 @@ void oaktrail_hdmi_init(struct drm_device *dev,
 	return;
 
 failed_connector:
-	kfree(psb_intel_encoder);
+	kfree(gma_encoder);
 }
 
 static DEFINE_PCI_DEVICE_TABLE(hdmi_ids) = {
diff --git a/drivers/gpu/drm/gma500/oaktrail_lvds.c b/drivers/gpu/drm/gma500/oaktrail_lvds.c
index 325013a9c48c..e77d7214fca4 100644
--- a/drivers/gpu/drm/gma500/oaktrail_lvds.c
+++ b/drivers/gpu/drm/gma500/oaktrail_lvds.c
@@ -43,7 +43,7 @@
  * Sets the power state for the panel.
  */
 static void oaktrail_lvds_set_power(struct drm_device *dev,
-				struct psb_intel_encoder *psb_intel_encoder,
+				struct gma_encoder *gma_encoder,
 				bool on)
 {
 	u32 pp_status;
@@ -78,13 +78,12 @@ static void oaktrail_lvds_set_power(struct drm_device *dev,
 static void oaktrail_lvds_dpms(struct drm_encoder *encoder, int mode)
 {
 	struct drm_device *dev = encoder->dev;
-	struct psb_intel_encoder *psb_intel_encoder =
-						to_psb_intel_encoder(encoder);
+	struct gma_encoder *gma_encoder = to_gma_encoder(encoder);
 
 	if (mode == DRM_MODE_DPMS_ON)
-		oaktrail_lvds_set_power(dev, psb_intel_encoder, true);
+		oaktrail_lvds_set_power(dev, gma_encoder, true);
 	else
-		oaktrail_lvds_set_power(dev, psb_intel_encoder, false);
+		oaktrail_lvds_set_power(dev, gma_encoder, false);
 
 	/* XXX: We never power down the LVDS pairs. */
 }
@@ -166,8 +165,7 @@ static void oaktrail_lvds_prepare(struct drm_encoder *encoder)
 {
 	struct drm_device *dev = encoder->dev;
 	struct drm_psb_private *dev_priv = dev->dev_private;
-	struct psb_intel_encoder *psb_intel_encoder =
-						to_psb_intel_encoder(encoder);
+	struct gma_encoder *gma_encoder = to_gma_encoder(encoder);
 	struct psb_intel_mode_device *mode_dev = &dev_priv->mode_dev;
 
 	if (!gma_power_begin(dev, true))
@@ -176,7 +174,7 @@ static void oaktrail_lvds_prepare(struct drm_encoder *encoder)
 	mode_dev->saveBLC_PWM_CTL = REG_READ(BLC_PWM_CTL);
 	mode_dev->backlight_duty_cycle = (mode_dev->saveBLC_PWM_CTL &
 					  BACKLIGHT_DUTY_CYCLE_MASK);
-	oaktrail_lvds_set_power(dev, psb_intel_encoder, false);
+	oaktrail_lvds_set_power(dev, gma_encoder, false);
 	gma_power_end(dev);
 }
 
@@ -203,14 +201,13 @@ static void oaktrail_lvds_commit(struct drm_encoder *encoder)
 {
 	struct drm_device *dev = encoder->dev;
 	struct drm_psb_private *dev_priv = dev->dev_private;
-	struct psb_intel_encoder *psb_intel_encoder =
-						to_psb_intel_encoder(encoder);
+	struct gma_encoder *gma_encoder = to_gma_encoder(encoder);
 	struct psb_intel_mode_device *mode_dev = &dev_priv->mode_dev;
 
 	if (mode_dev->backlight_duty_cycle == 0)
 		mode_dev->backlight_duty_cycle =
 					oaktrail_lvds_get_max_backlight(dev);
-	oaktrail_lvds_set_power(dev, psb_intel_encoder, true);
+	oaktrail_lvds_set_power(dev, gma_encoder, true);
 }
 
 static const struct drm_encoder_helper_funcs oaktrail_lvds_helper_funcs = {
@@ -325,8 +322,8 @@ static void oaktrail_lvds_get_configuration_mode(struct drm_device *dev,
 void oaktrail_lvds_init(struct drm_device *dev,
 		    struct psb_intel_mode_device *mode_dev)
 {
-	struct psb_intel_encoder *psb_intel_encoder;
-	struct psb_intel_connector *psb_intel_connector;
+	struct gma_encoder *gma_encoder;
+	struct gma_connector *gma_connector;
 	struct drm_connector *connector;
 	struct drm_encoder *encoder;
 	struct drm_psb_private *dev_priv = dev->dev_private;
@@ -334,16 +331,16 @@ void oaktrail_lvds_init(struct drm_device *dev,
 	struct i2c_adapter *i2c_adap;
 	struct drm_display_mode *scan;	/* *modes, *bios_mode; */
 
-	psb_intel_encoder = kzalloc(sizeof(struct psb_intel_encoder), GFP_KERNEL);
-	if (!psb_intel_encoder)
+	gma_encoder = kzalloc(sizeof(struct gma_encoder), GFP_KERNEL);
+	if (!gma_encoder)
 		return;
 
-	psb_intel_connector = kzalloc(sizeof(struct psb_intel_connector), GFP_KERNEL);
-	if (!psb_intel_connector)
+	gma_connector = kzalloc(sizeof(struct gma_connector), GFP_KERNEL);
+	if (!gma_connector)
 		goto failed_connector;
 
-	connector = &psb_intel_connector->base;
-	encoder = &psb_intel_encoder->base;
+	connector = &gma_connector->base;
+	encoder = &gma_encoder->base;
 	dev_priv->is_lvds_on = true;
 	drm_connector_init(dev, connector,
 			   &psb_intel_lvds_connector_funcs,
@@ -352,9 +349,8 @@ void oaktrail_lvds_init(struct drm_device *dev,
 	drm_encoder_init(dev, encoder, &psb_intel_lvds_enc_funcs,
 			 DRM_MODE_ENCODER_LVDS);
 
-	psb_intel_connector_attach_encoder(psb_intel_connector,
-					   psb_intel_encoder);
-	psb_intel_encoder->type = INTEL_OUTPUT_LVDS;
+	gma_connector_attach_encoder(gma_connector, gma_encoder);
+	gma_encoder->type = INTEL_OUTPUT_LVDS;
 
 	drm_encoder_helper_add(encoder, &oaktrail_lvds_helper_funcs);
 	drm_connector_helper_add(connector,
@@ -434,15 +430,15 @@ out:
 
 failed_find:
 	dev_dbg(dev->dev, "No LVDS modes found, disabling.\n");
-	if (psb_intel_encoder->ddc_bus)
-		psb_intel_i2c_destroy(psb_intel_encoder->ddc_bus);
+	if (gma_encoder->ddc_bus)
+		psb_intel_i2c_destroy(gma_encoder->ddc_bus);
 
 /* failed_ddc: */
 
 	drm_encoder_cleanup(encoder);
 	drm_connector_cleanup(connector);
-	kfree(psb_intel_connector);
+	kfree(gma_connector);
 failed_connector:
-	kfree(psb_intel_encoder);
+	kfree(gma_encoder);
 }
 
diff --git a/drivers/gpu/drm/gma500/psb_device.c b/drivers/gpu/drm/gma500/psb_device.c
index f6f534b4197e..697678619bd1 100644
--- a/drivers/gpu/drm/gma500/psb_device.c
+++ b/drivers/gpu/drm/gma500/psb_device.c
@@ -25,7 +25,7 @@
 #include "psb_reg.h"
 #include "psb_intel_reg.h"
 #include "intel_bios.h"
-
+#include "psb_device.h"
 
 static int psb_output_init(struct drm_device *dev)
 {
@@ -380,6 +380,7 @@ const struct psb_ops psb_chip_ops = {
 
 	.crtc_helper = &psb_intel_helper_funcs,
 	.crtc_funcs = &psb_intel_crtc_funcs,
+	.clock_funcs = &psb_clock_funcs,
 
 	.output_init = psb_output_init,
 
diff --git a/drivers/gpu/drm/gma500/psb_intel_display.h b/drivers/gpu/drm/gma500/psb_device.h
index 3724b971e91c..35e304c7f85a 100644
--- a/drivers/gpu/drm/gma500/psb_intel_display.h
+++ b/drivers/gpu/drm/gma500/psb_device.h
@@ -1,4 +1,6 @@
-/* copyright (c) 2008, Intel Corporation
+/*
+ * Copyright © 2013 Patrik Jakobsson
+ * Copyright © 2011 Intel Corporation
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms and conditions of the GNU General Public License,
@@ -12,14 +14,11 @@
  * You should have received a copy of the GNU General Public License along with
  * this program; if not, write to the Free Software Foundation, Inc.,
  * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
- *
- * Authors:
- * Eric Anholt <eric@anholt.net>
  */
 
-#ifndef _INTEL_DISPLAY_H_
-#define _INTEL_DISPLAY_H_
+#ifndef _PSB_DEVICE_H_
+#define _PSB_DEVICE_H_
 
-bool psb_intel_pipe_has_type(struct drm_crtc *crtc, int type);
+extern const struct gma_clock_funcs psb_clock_funcs;
 
 #endif
diff --git a/drivers/gpu/drm/gma500/psb_drv.c b/drivers/gpu/drm/gma500/psb_drv.c
index bddea5807442..fcb4e9ff1f20 100644
--- a/drivers/gpu/drm/gma500/psb_drv.c
+++ b/drivers/gpu/drm/gma500/psb_drv.c
@@ -131,7 +131,7 @@ static int psb_gamma_ioctl(struct drm_device *dev, void *data,
 static int psb_dpst_bl_ioctl(struct drm_device *dev, void *data,
 			     struct drm_file *file_priv);
 
-static struct drm_ioctl_desc psb_ioctls[] = {
+static const struct drm_ioctl_desc psb_ioctls[] = {
 	DRM_IOCTL_DEF_DRV(GMA_ADB, psb_adb_ioctl, DRM_AUTH),
 	DRM_IOCTL_DEF_DRV(GMA_MODE_OPERATION, psb_mode_operation_ioctl,
 		      DRM_AUTH),
@@ -270,7 +270,7 @@ static int psb_driver_load(struct drm_device *dev, unsigned long chipset)
 	unsigned long irqflags;
 	int ret = -ENOMEM;
 	struct drm_connector *connector;
-	struct psb_intel_encoder *psb_intel_encoder;
+	struct gma_encoder *gma_encoder;
 
 	dev_priv = kzalloc(sizeof(*dev_priv), GFP_KERNEL);
 	if (dev_priv == NULL)
@@ -372,9 +372,9 @@ static int psb_driver_load(struct drm_device *dev, unsigned long chipset)
 	/* Only add backlight support if we have LVDS output */
 	list_for_each_entry(connector, &dev->mode_config.connector_list,
 			    head) {
-		psb_intel_encoder = psb_intel_attached_encoder(connector);
+		gma_encoder = gma_attached_encoder(connector);
 
-		switch (psb_intel_encoder->type) {
+		switch (gma_encoder->type) {
 		case INTEL_OUTPUT_LVDS:
 		case INTEL_OUTPUT_MIPI:
 			ret = gma_backlight_init(dev);
@@ -441,7 +441,7 @@ static int psb_gamma_ioctl(struct drm_device *dev, void *data,
 	struct drm_mode_object *obj;
 	struct drm_crtc *crtc;
 	struct drm_connector *connector;
-	struct psb_intel_crtc *psb_intel_crtc;
+	struct gma_crtc *gma_crtc;
 	int i = 0;
 	int32_t obj_id;
 
@@ -454,12 +454,12 @@ static int psb_gamma_ioctl(struct drm_device *dev, void *data,
 
 	connector = obj_to_connector(obj);
 	crtc = connector->encoder->crtc;
-	psb_intel_crtc = to_psb_intel_crtc(crtc);
+	gma_crtc = to_gma_crtc(crtc);
 
 	for (i = 0; i < 256; i++)
-		psb_intel_crtc->lut_adj[i] = lut_arg->lut[i];
+		gma_crtc->lut_adj[i] = lut_arg->lut[i];
 
-	psb_intel_crtc_load_lut(crtc);
+	gma_crtc_load_lut(crtc);
 
 	return 0;
 }
@@ -622,13 +622,12 @@ static const struct file_operations psb_gem_fops = {
 	.unlocked_ioctl = psb_unlocked_ioctl,
 	.mmap = drm_gem_mmap,
 	.poll = drm_poll,
-	.fasync = drm_fasync,
 	.read = drm_read,
 };
 
 static struct drm_driver driver = {
 	.driver_features = DRIVER_HAVE_IRQ | DRIVER_IRQ_SHARED | \
-			   DRIVER_IRQ_VBL | DRIVER_MODESET | DRIVER_GEM ,
+			   DRIVER_MODESET | DRIVER_GEM ,
 	.load = psb_driver_load,
 	.unload = psb_driver_unload,
 
@@ -652,7 +651,7 @@ static struct drm_driver driver = {
 	.gem_vm_ops = &psb_gem_vm_ops,
 	.dumb_create = psb_gem_dumb_create,
 	.dumb_map_offset = psb_gem_dumb_map_gtt,
-	.dumb_destroy = psb_gem_dumb_destroy,
+	.dumb_destroy = drm_gem_dumb_destroy,
 	.fops = &psb_gem_fops,
 	.name = DRIVER_NAME,
 	.desc = DRIVER_DESC,
diff --git a/drivers/gpu/drm/gma500/psb_drv.h b/drivers/gpu/drm/gma500/psb_drv.h
index 6053b8abcd12..4535ac7708f8 100644
--- a/drivers/gpu/drm/gma500/psb_drv.h
+++ b/drivers/gpu/drm/gma500/psb_drv.h
@@ -27,6 +27,7 @@
 #include <drm/gma_drm.h>
 #include "psb_reg.h"
 #include "psb_intel_drv.h"
+#include "gma_display.h"
 #include "intel_bios.h"
 #include "gtt.h"
 #include "power.h"
@@ -46,6 +47,7 @@ enum {
 #define IS_PSB(dev) (((dev)->pci_device & 0xfffe) == 0x8108)
 #define IS_MRST(dev) (((dev)->pci_device & 0xfffc) == 0x4100)
 #define IS_MFLD(dev) (((dev)->pci_device & 0xfff8) == 0x0130)
+#define IS_CDV(dev) (((dev)->pci_device & 0xfff0) == 0x0be0)
 
 /*
  * Driver definitions
@@ -675,6 +677,7 @@ struct psb_ops {
 	/* Sub functions */
 	struct drm_crtc_helper_funcs const *crtc_helper;
 	struct drm_crtc_funcs const *crtc_funcs;
+	const struct gma_clock_funcs *clock_funcs;
 
 	/* Setup hooks */
 	int (*chip_setup)(struct drm_device *dev);
@@ -692,6 +695,8 @@ struct psb_ops {
 	int (*restore_regs)(struct drm_device *dev);
 	int (*power_up)(struct drm_device *dev);
 	int (*power_down)(struct drm_device *dev);
+	void (*update_wm)(struct drm_device *dev, struct drm_crtc *crtc);
+	void (*disable_sr)(struct drm_device *dev);
 
 	void (*lvds_bl_power)(struct drm_device *dev, bool on);
 #ifdef CONFIG_BACKLIGHT_CLASS_DEVICE
@@ -838,8 +843,6 @@ extern int psb_gem_get_aperture(struct drm_device *dev, void *data,
 			struct drm_file *file);
 extern int psb_gem_dumb_create(struct drm_file *file, struct drm_device *dev,
 			struct drm_mode_create_dumb *args);
-extern int psb_gem_dumb_destroy(struct drm_file *file, struct drm_device *dev,
-			uint32_t handle);
 extern int psb_gem_dumb_map_gtt(struct drm_file *file, struct drm_device *dev,
 			uint32_t handle, uint64_t *offset);
 extern int psb_gem_fault(struct vm_area_struct *vma, struct vm_fault *vmf);
diff --git a/drivers/gpu/drm/gma500/psb_intel_display.c b/drivers/gpu/drm/gma500/psb_intel_display.c
index 6666493789d1..97f8a03fee43 100644
--- a/drivers/gpu/drm/gma500/psb_intel_display.c
+++ b/drivers/gpu/drm/gma500/psb_intel_display.c
@@ -19,46 +19,19 @@
  */
 
 #include <linux/i2c.h>
-#include <linux/pm_runtime.h>
 
 #include <drm/drmP.h>
 #include "framebuffer.h"
 #include "psb_drv.h"
 #include "psb_intel_drv.h"
 #include "psb_intel_reg.h"
-#include "psb_intel_display.h"
+#include "gma_display.h"
 #include "power.h"
 
-struct psb_intel_clock_t {
-	/* given values */
-	int n;
-	int m1, m2;
-	int p1, p2;
-	/* derived values */
-	int dot;
-	int vco;
-	int m;
-	int p;
-};
-
-struct psb_intel_range_t {
-	int min, max;
-};
-
-struct psb_intel_p2_t {
-	int dot_limit;
-	int p2_slow, p2_fast;
-};
-
-struct psb_intel_limit_t {
-	struct psb_intel_range_t dot, vco, n, m, m1, m2, p, p1;
-	struct psb_intel_p2_t p2;
-};
-
 #define INTEL_LIMIT_I9XX_SDVO_DAC   0
 #define INTEL_LIMIT_I9XX_LVDS	    1
 
-static const struct psb_intel_limit_t psb_intel_limits[] = {
+static const struct gma_limit_t psb_intel_limits[] = {
 	{			/* INTEL_LIMIT_I9XX_SDVO_DAC */
 	 .dot = {.min = 20000, .max = 400000},
 	 .vco = {.min = 1400000, .max = 2800000},
@@ -68,8 +41,8 @@ static const struct psb_intel_limit_t psb_intel_limits[] = {
 	 .m2 = {.min = 3, .max = 7},
 	 .p = {.min = 5, .max = 80},
 	 .p1 = {.min = 1, .max = 8},
-	 .p2 = {.dot_limit = 200000,
-		.p2_slow = 10, .p2_fast = 5},
+	 .p2 = {.dot_limit = 200000, .p2_slow = 10, .p2_fast = 5},
+	 .find_pll = gma_find_best_pll,
 	 },
 	{			/* INTEL_LIMIT_I9XX_LVDS */
 	 .dot = {.min = 20000, .max = 400000},
@@ -83,23 +56,24 @@ static const struct psb_intel_limit_t psb_intel_limits[] = {
 	 /* The single-channel range is 25-112Mhz, and dual-channel
 	  * is 80-224Mhz.  Prefer single channel as much as possible.
 	  */
-	 .p2 = {.dot_limit = 112000,
-		.p2_slow = 14, .p2_fast = 7},
+	 .p2 = {.dot_limit = 112000, .p2_slow = 14, .p2_fast = 7},
+	 .find_pll = gma_find_best_pll,
 	 },
 };
 
-static const struct psb_intel_limit_t *psb_intel_limit(struct drm_crtc *crtc)
+static const struct gma_limit_t *psb_intel_limit(struct drm_crtc *crtc,
+						 int refclk)
 {
-	const struct psb_intel_limit_t *limit;
+	const struct gma_limit_t *limit;
 
-	if (psb_intel_pipe_has_type(crtc, INTEL_OUTPUT_LVDS))
+	if (gma_pipe_has_type(crtc, INTEL_OUTPUT_LVDS))
 		limit = &psb_intel_limits[INTEL_LIMIT_I9XX_LVDS];
 	else
 		limit = &psb_intel_limits[INTEL_LIMIT_I9XX_SDVO_DAC];
 	return limit;
 }
 
-static void psb_intel_clock(int refclk, struct psb_intel_clock_t *clock)
+static void psb_intel_clock(int refclk, struct gma_clock_t *clock)
 {
 	clock->m = 5 * (clock->m1 + 2) + (clock->m2 + 2);
 	clock->p = clock->p1 * clock->p2;
@@ -108,353 +82,6 @@ static void psb_intel_clock(int refclk, struct psb_intel_clock_t *clock)
 }
 
 /**
- * Returns whether any output on the specified pipe is of the specified type
- */
-bool psb_intel_pipe_has_type(struct drm_crtc *crtc, int type)
-{
-	struct drm_device *dev = crtc->dev;
-	struct drm_mode_config *mode_config = &dev->mode_config;
-	struct drm_connector *l_entry;
-
-	list_for_each_entry(l_entry, &mode_config->connector_list, head) {
-		if (l_entry->encoder && l_entry->encoder->crtc == crtc) {
-			struct psb_intel_encoder *psb_intel_encoder =
-					psb_intel_attached_encoder(l_entry);
-			if (psb_intel_encoder->type == type)
-				return true;
-		}
-	}
-	return false;
-}
-
-#define INTELPllInvalid(s)   { /* ErrorF (s) */; return false; }
-/**
- * Returns whether the given set of divisors are valid for a given refclk with
- * the given connectors.
- */
-
-static bool psb_intel_PLL_is_valid(struct drm_crtc *crtc,
-			       struct psb_intel_clock_t *clock)
-{
-	const struct psb_intel_limit_t *limit = psb_intel_limit(crtc);
-
-	if (clock->p1 < limit->p1.min || limit->p1.max < clock->p1)
-		INTELPllInvalid("p1 out of range\n");
-	if (clock->p < limit->p.min || limit->p.max < clock->p)
-		INTELPllInvalid("p out of range\n");
-	if (clock->m2 < limit->m2.min || limit->m2.max < clock->m2)
-		INTELPllInvalid("m2 out of range\n");
-	if (clock->m1 < limit->m1.min || limit->m1.max < clock->m1)
-		INTELPllInvalid("m1 out of range\n");
-	if (clock->m1 <= clock->m2)
-		INTELPllInvalid("m1 <= m2\n");
-	if (clock->m < limit->m.min || limit->m.max < clock->m)
-		INTELPllInvalid("m out of range\n");
-	if (clock->n < limit->n.min || limit->n.max < clock->n)
-		INTELPllInvalid("n out of range\n");
-	if (clock->vco < limit->vco.min || limit->vco.max < clock->vco)
-		INTELPllInvalid("vco out of range\n");
-	/* XXX: We may need to be checking "Dot clock"
-	 * depending on the multiplier, connector, etc.,
-	 * rather than just a single range.
-	 */
-	if (clock->dot < limit->dot.min || limit->dot.max < clock->dot)
-		INTELPllInvalid("dot out of range\n");
-
-	return true;
-}
-
-/**
- * Returns a set of divisors for the desired target clock with the given
- * refclk, or FALSE.  The returned values represent the clock equation:
- * reflck * (5 * (m1 + 2) + (m2 + 2)) / (n + 2) / p1 / p2.
- */
-static bool psb_intel_find_best_PLL(struct drm_crtc *crtc, int target,
-				int refclk,
-				struct psb_intel_clock_t *best_clock)
-{
-	struct drm_device *dev = crtc->dev;
-	struct psb_intel_clock_t clock;
-	const struct psb_intel_limit_t *limit = psb_intel_limit(crtc);
-	int err = target;
-
-	if (psb_intel_pipe_has_type(crtc, INTEL_OUTPUT_LVDS) &&
-	    (REG_READ(LVDS) & LVDS_PORT_EN) != 0) {
-		/*
-		 * For LVDS, if the panel is on, just rely on its current
-		 * settings for dual-channel.  We haven't figured out how to
-		 * reliably set up different single/dual channel state, if we
-		 * even can.
-		 */
-		if ((REG_READ(LVDS) & LVDS_CLKB_POWER_MASK) ==
-		    LVDS_CLKB_POWER_UP)
-			clock.p2 = limit->p2.p2_fast;
-		else
-			clock.p2 = limit->p2.p2_slow;
-	} else {
-		if (target < limit->p2.dot_limit)
-			clock.p2 = limit->p2.p2_slow;
-		else
-			clock.p2 = limit->p2.p2_fast;
-	}
-
-	memset(best_clock, 0, sizeof(*best_clock));
-
-	for (clock.m1 = limit->m1.min; clock.m1 <= limit->m1.max;
-	     clock.m1++) {
-		for (clock.m2 = limit->m2.min;
-		     clock.m2 < clock.m1 && clock.m2 <= limit->m2.max;
-		     clock.m2++) {
-			for (clock.n = limit->n.min;
-			     clock.n <= limit->n.max; clock.n++) {
-				for (clock.p1 = limit->p1.min;
-				     clock.p1 <= limit->p1.max;
-				     clock.p1++) {
-					int this_err;
-
-					psb_intel_clock(refclk, &clock);
-
-					if (!psb_intel_PLL_is_valid
-					    (crtc, &clock))
-						continue;
-
-					this_err = abs(clock.dot - target);
-					if (this_err < err) {
-						*best_clock = clock;
-						err = this_err;
-					}
-				}
-			}
-		}
-	}
-
-	return err != target;
-}
-
-void psb_intel_wait_for_vblank(struct drm_device *dev)
-{
-	/* Wait for 20ms, i.e. one cycle at 50hz. */
-	mdelay(20);
-}
-
-static int psb_intel_pipe_set_base(struct drm_crtc *crtc,
-			    int x, int y, struct drm_framebuffer *old_fb)
-{
-	struct drm_device *dev = crtc->dev;
-	struct drm_psb_private *dev_priv = dev->dev_private;
-	struct psb_intel_crtc *psb_intel_crtc = to_psb_intel_crtc(crtc);
-	struct psb_framebuffer *psbfb = to_psb_fb(crtc->fb);
-	int pipe = psb_intel_crtc->pipe;
-	const struct psb_offset *map = &dev_priv->regmap[pipe];
-	unsigned long start, offset;
-	u32 dspcntr;
-	int ret = 0;
-
-	if (!gma_power_begin(dev, true))
-		return 0;
-
-	/* no fb bound */
-	if (!crtc->fb) {
-		dev_dbg(dev->dev, "No FB bound\n");
-		goto psb_intel_pipe_cleaner;
-	}
-
-	/* We are displaying this buffer, make sure it is actually loaded
-	   into the GTT */
-	ret = psb_gtt_pin(psbfb->gtt);
-	if (ret < 0)
-		goto psb_intel_pipe_set_base_exit;
-	start = psbfb->gtt->offset;
-
-	offset = y * crtc->fb->pitches[0] + x * (crtc->fb->bits_per_pixel / 8);
-
-	REG_WRITE(map->stride, crtc->fb->pitches[0]);
-
-	dspcntr = REG_READ(map->cntr);
-	dspcntr &= ~DISPPLANE_PIXFORMAT_MASK;
-
-	switch (crtc->fb->bits_per_pixel) {
-	case 8:
-		dspcntr |= DISPPLANE_8BPP;
-		break;
-	case 16:
-		if (crtc->fb->depth == 15)
-			dspcntr |= DISPPLANE_15_16BPP;
-		else
-			dspcntr |= DISPPLANE_16BPP;
-		break;
-	case 24:
-	case 32:
-		dspcntr |= DISPPLANE_32BPP_NO_ALPHA;
-		break;
-	default:
-		dev_err(dev->dev, "Unknown color depth\n");
-		ret = -EINVAL;
-		psb_gtt_unpin(psbfb->gtt);
-		goto psb_intel_pipe_set_base_exit;
-	}
-	REG_WRITE(map->cntr, dspcntr);
-
-	REG_WRITE(map->base, start + offset);
-	REG_READ(map->base);
-
-psb_intel_pipe_cleaner:
-	/* If there was a previous display we can now unpin it */
-	if (old_fb)
-		psb_gtt_unpin(to_psb_fb(old_fb)->gtt);
-
-psb_intel_pipe_set_base_exit:
-	gma_power_end(dev);
-	return ret;
-}
-
-/**
- * Sets the power management mode of the pipe and plane.
- *
- * This code should probably grow support for turning the cursor off and back
- * on appropriately at the same time as we're turning the pipe off/on.
- */
-static void psb_intel_crtc_dpms(struct drm_crtc *crtc, int mode)
-{
-	struct drm_device *dev = crtc->dev;
-	struct drm_psb_private *dev_priv = dev->dev_private;
-	struct psb_intel_crtc *psb_intel_crtc = to_psb_intel_crtc(crtc);
-	int pipe = psb_intel_crtc->pipe;
-	const struct psb_offset *map = &dev_priv->regmap[pipe];
-	u32 temp;
-
-	/* XXX: When our outputs are all unaware of DPMS modes other than off
-	 * and on, we should map those modes to DRM_MODE_DPMS_OFF in the CRTC.
-	 */
-	switch (mode) {
-	case DRM_MODE_DPMS_ON:
-	case DRM_MODE_DPMS_STANDBY:
-	case DRM_MODE_DPMS_SUSPEND:
-		/* Enable the DPLL */
-		temp = REG_READ(map->dpll);
-		if ((temp & DPLL_VCO_ENABLE) == 0) {
-			REG_WRITE(map->dpll, temp);
-			REG_READ(map->dpll);
-			/* Wait for the clocks to stabilize. */
-			udelay(150);
-			REG_WRITE(map->dpll, temp | DPLL_VCO_ENABLE);
-			REG_READ(map->dpll);
-			/* Wait for the clocks to stabilize. */
-			udelay(150);
-			REG_WRITE(map->dpll, temp | DPLL_VCO_ENABLE);
-			REG_READ(map->dpll);
-			/* Wait for the clocks to stabilize. */
-			udelay(150);
-		}
-
-		/* Enable the pipe */
-		temp = REG_READ(map->conf);
-		if ((temp & PIPEACONF_ENABLE) == 0)
-			REG_WRITE(map->conf, temp | PIPEACONF_ENABLE);
-
-		/* Enable the plane */
-		temp = REG_READ(map->cntr);
-		if ((temp & DISPLAY_PLANE_ENABLE) == 0) {
-			REG_WRITE(map->cntr,
-				  temp | DISPLAY_PLANE_ENABLE);
-			/* Flush the plane changes */
-			REG_WRITE(map->base, REG_READ(map->base));
-		}
-
-		psb_intel_crtc_load_lut(crtc);
-
-		/* Give the overlay scaler a chance to enable
-		 * if it's on this pipe */
-		/* psb_intel_crtc_dpms_video(crtc, true); TODO */
-		break;
-	case DRM_MODE_DPMS_OFF:
-		/* Give the overlay scaler a chance to disable
-		 * if it's on this pipe */
-		/* psb_intel_crtc_dpms_video(crtc, FALSE); TODO */
-
-		/* Disable the VGA plane that we never use */
-		REG_WRITE(VGACNTRL, VGA_DISP_DISABLE);
-
-		/* Disable display plane */
-		temp = REG_READ(map->cntr);
-		if ((temp & DISPLAY_PLANE_ENABLE) != 0) {
-			REG_WRITE(map->cntr,
-				  temp & ~DISPLAY_PLANE_ENABLE);
-			/* Flush the plane changes */
-			REG_WRITE(map->base, REG_READ(map->base));
-			REG_READ(map->base);
-		}
-
-		/* Next, disable display pipes */
-		temp = REG_READ(map->conf);
-		if ((temp & PIPEACONF_ENABLE) != 0) {
-			REG_WRITE(map->conf, temp & ~PIPEACONF_ENABLE);
-			REG_READ(map->conf);
-		}
-
-		/* Wait for vblank for the disable to take effect. */
-		psb_intel_wait_for_vblank(dev);
-
-		temp = REG_READ(map->dpll);
-		if ((temp & DPLL_VCO_ENABLE) != 0) {
-			REG_WRITE(map->dpll, temp & ~DPLL_VCO_ENABLE);
-			REG_READ(map->dpll);
-		}
-
-		/* Wait for the clocks to turn off. */
-		udelay(150);
-		break;
-	}
-
-	/*Set FIFO Watermarks*/
-	REG_WRITE(DSPARB, 0x3F3E);
-}
-
-static void psb_intel_crtc_prepare(struct drm_crtc *crtc)
-{
-	struct drm_crtc_helper_funcs *crtc_funcs = crtc->helper_private;
-	crtc_funcs->dpms(crtc, DRM_MODE_DPMS_OFF);
-}
-
-static void psb_intel_crtc_commit(struct drm_crtc *crtc)
-{
-	struct drm_crtc_helper_funcs *crtc_funcs = crtc->helper_private;
-	crtc_funcs->dpms(crtc, DRM_MODE_DPMS_ON);
-}
-
-void psb_intel_encoder_prepare(struct drm_encoder *encoder)
-{
-	struct drm_encoder_helper_funcs *encoder_funcs =
-	    encoder->helper_private;
-	/* lvds has its own version of prepare see psb_intel_lvds_prepare */
-	encoder_funcs->dpms(encoder, DRM_MODE_DPMS_OFF);
-}
-
-void psb_intel_encoder_commit(struct drm_encoder *encoder)
-{
-	struct drm_encoder_helper_funcs *encoder_funcs =
-	    encoder->helper_private;
-	/* lvds has its own version of commit see psb_intel_lvds_commit */
-	encoder_funcs->dpms(encoder, DRM_MODE_DPMS_ON);
-}
-
-void psb_intel_encoder_destroy(struct drm_encoder *encoder)
-{
-	struct psb_intel_encoder *intel_encoder = to_psb_intel_encoder(encoder);
-
-	drm_encoder_cleanup(encoder);
-	kfree(intel_encoder);
-}
-
-static bool psb_intel_crtc_mode_fixup(struct drm_crtc *crtc,
-				  const struct drm_display_mode *mode,
-				  struct drm_display_mode *adjusted_mode)
-{
-	return true;
-}
-
-
-/**
  * Return the pipe currently connected to the panel fitter,
  * or -1 if the panel fitter is not present or not in use
  */
@@ -479,17 +106,18 @@ static int psb_intel_crtc_mode_set(struct drm_crtc *crtc,
 {
 	struct drm_device *dev = crtc->dev;
 	struct drm_psb_private *dev_priv = dev->dev_private;
-	struct psb_intel_crtc *psb_intel_crtc = to_psb_intel_crtc(crtc);
+	struct gma_crtc *gma_crtc = to_gma_crtc(crtc);
 	struct drm_crtc_helper_funcs *crtc_funcs = crtc->helper_private;
-	int pipe = psb_intel_crtc->pipe;
+	int pipe = gma_crtc->pipe;
 	const struct psb_offset *map = &dev_priv->regmap[pipe];
 	int refclk;
-	struct psb_intel_clock_t clock;
+	struct gma_clock_t clock;
 	u32 dpll = 0, fp = 0, dspcntr, pipeconf;
 	bool ok, is_sdvo = false;
 	bool is_lvds = false, is_tv = false;
 	struct drm_mode_config *mode_config = &dev->mode_config;
 	struct drm_connector *connector;
+	const struct gma_limit_t *limit;
 
 	/* No scan out no play */
 	if (crtc->fb == NULL) {
@@ -498,14 +126,13 @@ static int psb_intel_crtc_mode_set(struct drm_crtc *crtc,
 	}
 
 	list_for_each_entry(connector, &mode_config->connector_list, head) {
-		struct psb_intel_encoder *psb_intel_encoder =
-					psb_intel_attached_encoder(connector);
+		struct gma_encoder *gma_encoder = gma_attached_encoder(connector);
 
 		if (!connector->encoder
 		    || connector->encoder->crtc != crtc)
 			continue;
 
-		switch (psb_intel_encoder->type) {
+		switch (gma_encoder->type) {
 		case INTEL_OUTPUT_LVDS:
 			is_lvds = true;
 			break;
@@ -520,10 +147,13 @@ static int psb_intel_crtc_mode_set(struct drm_crtc *crtc,
 
 	refclk = 96000;
 
-	ok = psb_intel_find_best_PLL(crtc, adjusted_mode->clock, refclk,
+	limit = gma_crtc->clock_funcs->limit(crtc, refclk);
+
+	ok = limit->find_pll(limit, crtc, adjusted_mode->clock, refclk,
 				 &clock);
 	if (!ok) {
-		dev_err(dev->dev, "Couldn't find PLL settings for mode!\n");
+		DRM_ERROR("Couldn't find PLL settings for mode! target: %d, actual: %d",
+			  adjusted_mode->clock, clock.dot);
 		return 0;
 	}
 
@@ -661,368 +291,29 @@ static int psb_intel_crtc_mode_set(struct drm_crtc *crtc,
 	REG_WRITE(map->conf, pipeconf);
 	REG_READ(map->conf);
 
-	psb_intel_wait_for_vblank(dev);
+	gma_wait_for_vblank(dev);
 
 	REG_WRITE(map->cntr, dspcntr);
 
 	/* Flush the plane changes */
 	crtc_funcs->mode_set_base(crtc, x, y, old_fb);
 
-	psb_intel_wait_for_vblank(dev);
-
-	return 0;
-}
-
-/** Loads the palette/gamma unit for the CRTC with the prepared values */
-void psb_intel_crtc_load_lut(struct drm_crtc *crtc)
-{
-	struct drm_device *dev = crtc->dev;
-	struct drm_psb_private *dev_priv = dev->dev_private;
-	struct psb_intel_crtc *psb_intel_crtc = to_psb_intel_crtc(crtc);
-	const struct psb_offset *map = &dev_priv->regmap[psb_intel_crtc->pipe];
-	int palreg = map->palette;
-	int i;
-
-	/* The clocks have to be on to load the palette. */
-	if (!crtc->enabled)
-		return;
-
-	switch (psb_intel_crtc->pipe) {
-	case 0:
-	case 1:
-		break;
-	default:
-		dev_err(dev->dev, "Illegal Pipe Number.\n");
-		return;
-	}
-
-	if (gma_power_begin(dev, false)) {
-		for (i = 0; i < 256; i++) {
-			REG_WRITE(palreg + 4 * i,
-				  ((psb_intel_crtc->lut_r[i] +
-				  psb_intel_crtc->lut_adj[i]) << 16) |
-				  ((psb_intel_crtc->lut_g[i] +
-				  psb_intel_crtc->lut_adj[i]) << 8) |
-				  (psb_intel_crtc->lut_b[i] +
-				  psb_intel_crtc->lut_adj[i]));
-		}
-		gma_power_end(dev);
-	} else {
-		for (i = 0; i < 256; i++) {
-			dev_priv->regs.pipe[0].palette[i] =
-				  ((psb_intel_crtc->lut_r[i] +
-				  psb_intel_crtc->lut_adj[i]) << 16) |
-				  ((psb_intel_crtc->lut_g[i] +
-				  psb_intel_crtc->lut_adj[i]) << 8) |
-				  (psb_intel_crtc->lut_b[i] +
-				  psb_intel_crtc->lut_adj[i]);
-		}
-
-	}
-}
-
-/**
- * Save HW states of giving crtc
- */
-static void psb_intel_crtc_save(struct drm_crtc *crtc)
-{
-	struct drm_device *dev = crtc->dev;
-	struct drm_psb_private *dev_priv = dev->dev_private;
-	struct psb_intel_crtc *psb_intel_crtc = to_psb_intel_crtc(crtc);
-	struct psb_intel_crtc_state *crtc_state = psb_intel_crtc->crtc_state;
-	const struct psb_offset *map = &dev_priv->regmap[psb_intel_crtc->pipe];
-	uint32_t paletteReg;
-	int i;
-
-	if (!crtc_state) {
-		dev_err(dev->dev, "No CRTC state found\n");
-		return;
-	}
-
-	crtc_state->saveDSPCNTR = REG_READ(map->cntr);
-	crtc_state->savePIPECONF = REG_READ(map->conf);
-	crtc_state->savePIPESRC = REG_READ(map->src);
-	crtc_state->saveFP0 = REG_READ(map->fp0);
-	crtc_state->saveFP1 = REG_READ(map->fp1);
-	crtc_state->saveDPLL = REG_READ(map->dpll);
-	crtc_state->saveHTOTAL = REG_READ(map->htotal);
-	crtc_state->saveHBLANK = REG_READ(map->hblank);
-	crtc_state->saveHSYNC = REG_READ(map->hsync);
-	crtc_state->saveVTOTAL = REG_READ(map->vtotal);
-	crtc_state->saveVBLANK = REG_READ(map->vblank);
-	crtc_state->saveVSYNC = REG_READ(map->vsync);
-	crtc_state->saveDSPSTRIDE = REG_READ(map->stride);
-
-	/*NOTE: DSPSIZE DSPPOS only for psb*/
-	crtc_state->saveDSPSIZE = REG_READ(map->size);
-	crtc_state->saveDSPPOS = REG_READ(map->pos);
-
-	crtc_state->saveDSPBASE = REG_READ(map->base);
-
-	paletteReg = map->palette;
-	for (i = 0; i < 256; ++i)
-		crtc_state->savePalette[i] = REG_READ(paletteReg + (i << 2));
-}
-
-/**
- * Restore HW states of giving crtc
- */
-static void psb_intel_crtc_restore(struct drm_crtc *crtc)
-{
-	struct drm_device *dev = crtc->dev;
-	struct drm_psb_private *dev_priv = dev->dev_private;
-	struct psb_intel_crtc *psb_intel_crtc =  to_psb_intel_crtc(crtc);
-	struct psb_intel_crtc_state *crtc_state = psb_intel_crtc->crtc_state;
-	const struct psb_offset *map = &dev_priv->regmap[psb_intel_crtc->pipe];
-	uint32_t paletteReg;
-	int i;
-
-	if (!crtc_state) {
-		dev_err(dev->dev, "No crtc state\n");
-		return;
-	}
-
-	if (crtc_state->saveDPLL & DPLL_VCO_ENABLE) {
-		REG_WRITE(map->dpll,
-			crtc_state->saveDPLL & ~DPLL_VCO_ENABLE);
-		REG_READ(map->dpll);
-		udelay(150);
-	}
-
-	REG_WRITE(map->fp0, crtc_state->saveFP0);
-	REG_READ(map->fp0);
-
-	REG_WRITE(map->fp1, crtc_state->saveFP1);
-	REG_READ(map->fp1);
-
-	REG_WRITE(map->dpll, crtc_state->saveDPLL);
-	REG_READ(map->dpll);
-	udelay(150);
-
-	REG_WRITE(map->htotal, crtc_state->saveHTOTAL);
-	REG_WRITE(map->hblank, crtc_state->saveHBLANK);
-	REG_WRITE(map->hsync, crtc_state->saveHSYNC);
-	REG_WRITE(map->vtotal, crtc_state->saveVTOTAL);
-	REG_WRITE(map->vblank, crtc_state->saveVBLANK);
-	REG_WRITE(map->vsync, crtc_state->saveVSYNC);
-	REG_WRITE(map->stride, crtc_state->saveDSPSTRIDE);
-
-	REG_WRITE(map->size, crtc_state->saveDSPSIZE);
-	REG_WRITE(map->pos, crtc_state->saveDSPPOS);
-
-	REG_WRITE(map->src, crtc_state->savePIPESRC);
-	REG_WRITE(map->base, crtc_state->saveDSPBASE);
-	REG_WRITE(map->conf, crtc_state->savePIPECONF);
-
-	psb_intel_wait_for_vblank(dev);
-
-	REG_WRITE(map->cntr, crtc_state->saveDSPCNTR);
-	REG_WRITE(map->base, crtc_state->saveDSPBASE);
-
-	psb_intel_wait_for_vblank(dev);
-
-	paletteReg = map->palette;
-	for (i = 0; i < 256; ++i)
-		REG_WRITE(paletteReg + (i << 2), crtc_state->savePalette[i]);
-}
-
-static int psb_intel_crtc_cursor_set(struct drm_crtc *crtc,
-				 struct drm_file *file_priv,
-				 uint32_t handle,
-				 uint32_t width, uint32_t height)
-{
-	struct drm_device *dev = crtc->dev;
-	struct drm_psb_private *dev_priv = dev->dev_private;
-	struct psb_intel_crtc *psb_intel_crtc = to_psb_intel_crtc(crtc);
-	int pipe = psb_intel_crtc->pipe;
-	uint32_t control = (pipe == 0) ? CURACNTR : CURBCNTR;
-	uint32_t base = (pipe == 0) ? CURABASE : CURBBASE;
-	uint32_t temp;
-	size_t addr = 0;
-	struct gtt_range *gt;
-	struct gtt_range *cursor_gt = psb_intel_crtc->cursor_gt;
-	struct drm_gem_object *obj;
-	void *tmp_dst, *tmp_src;
-	int ret = 0, i, cursor_pages;
-
-	/* if we want to turn of the cursor ignore width and height */
-	if (!handle) {
-		/* turn off the cursor */
-		temp = CURSOR_MODE_DISABLE;
-
-		if (gma_power_begin(dev, false)) {
-			REG_WRITE(control, temp);
-			REG_WRITE(base, 0);
-			gma_power_end(dev);
-		}
-
-		/* Unpin the old GEM object */
-		if (psb_intel_crtc->cursor_obj) {
-			gt = container_of(psb_intel_crtc->cursor_obj,
-							struct gtt_range, gem);
-			psb_gtt_unpin(gt);
-			drm_gem_object_unreference(psb_intel_crtc->cursor_obj);
-			psb_intel_crtc->cursor_obj = NULL;
-		}
-
-		return 0;
-	}
-
-	/* Currently we only support 64x64 cursors */
-	if (width != 64 || height != 64) {
-		dev_dbg(dev->dev, "we currently only support 64x64 cursors\n");
-		return -EINVAL;
-	}
-
-	obj = drm_gem_object_lookup(dev, file_priv, handle);
-	if (!obj)
-		return -ENOENT;
-
-	if (obj->size < width * height * 4) {
-		dev_dbg(dev->dev, "buffer is to small\n");
-		ret = -ENOMEM;
-		goto unref_cursor;
-	}
-
-	gt = container_of(obj, struct gtt_range, gem);
-
-	/* Pin the memory into the GTT */
-	ret = psb_gtt_pin(gt);
-	if (ret) {
-		dev_err(dev->dev, "Can not pin down handle 0x%x\n", handle);
-		goto unref_cursor;
-	}
-
-	if (dev_priv->ops->cursor_needs_phys) {
-		if (cursor_gt == NULL) {
-			dev_err(dev->dev, "No hardware cursor mem available");
-			ret = -ENOMEM;
-			goto unref_cursor;
-		}
-
-		/* Prevent overflow */
-		if (gt->npage > 4)
-			cursor_pages = 4;
-		else
-			cursor_pages = gt->npage;
-
-		/* Copy the cursor to cursor mem */
-		tmp_dst = dev_priv->vram_addr + cursor_gt->offset;
-		for (i = 0; i < cursor_pages; i++) {
-			tmp_src = kmap(gt->pages[i]);
-			memcpy(tmp_dst, tmp_src, PAGE_SIZE);
-			kunmap(gt->pages[i]);
-			tmp_dst += PAGE_SIZE;
-		}
-
-		addr = psb_intel_crtc->cursor_addr;
-	} else {
-		addr = gt->offset;      /* Or resource.start ??? */
-		psb_intel_crtc->cursor_addr = addr;
-	}
-
-	temp = 0;
-	/* set the pipe for the cursor */
-	temp |= (pipe << 28);
-	temp |= CURSOR_MODE_64_ARGB_AX | MCURSOR_GAMMA_ENABLE;
-
-	if (gma_power_begin(dev, false)) {
-		REG_WRITE(control, temp);
-		REG_WRITE(base, addr);
-		gma_power_end(dev);
-	}
-
-	/* unpin the old bo */
-	if (psb_intel_crtc->cursor_obj) {
-		gt = container_of(psb_intel_crtc->cursor_obj,
-							struct gtt_range, gem);
-		psb_gtt_unpin(gt);
-		drm_gem_object_unreference(psb_intel_crtc->cursor_obj);
-	}
-
-	psb_intel_crtc->cursor_obj = obj;
-	return ret;
-
-unref_cursor:
-	drm_gem_object_unreference(obj);
-	return ret;
-}
-
-static int psb_intel_crtc_cursor_move(struct drm_crtc *crtc, int x, int y)
-{
-	struct drm_device *dev = crtc->dev;
-	struct psb_intel_crtc *psb_intel_crtc = to_psb_intel_crtc(crtc);
-	int pipe = psb_intel_crtc->pipe;
-	uint32_t temp = 0;
-	uint32_t addr;
-
-
-	if (x < 0) {
-		temp |= (CURSOR_POS_SIGN << CURSOR_X_SHIFT);
-		x = -x;
-	}
-	if (y < 0) {
-		temp |= (CURSOR_POS_SIGN << CURSOR_Y_SHIFT);
-		y = -y;
-	}
-
-	temp |= ((x & CURSOR_POS_MASK) << CURSOR_X_SHIFT);
-	temp |= ((y & CURSOR_POS_MASK) << CURSOR_Y_SHIFT);
-
-	addr = psb_intel_crtc->cursor_addr;
+	gma_wait_for_vblank(dev);
 
-	if (gma_power_begin(dev, false)) {
-		REG_WRITE((pipe == 0) ? CURAPOS : CURBPOS, temp);
-		REG_WRITE((pipe == 0) ? CURABASE : CURBBASE, addr);
-		gma_power_end(dev);
-	}
 	return 0;
 }
 
-static void psb_intel_crtc_gamma_set(struct drm_crtc *crtc, u16 *red,
-			 u16 *green, u16 *blue, uint32_t type, uint32_t size)
-{
-	struct psb_intel_crtc *psb_intel_crtc = to_psb_intel_crtc(crtc);
-	int i;
-
-	if (size != 256)
-		return;
-
-	for (i = 0; i < 256; i++) {
-		psb_intel_crtc->lut_r[i] = red[i] >> 8;
-		psb_intel_crtc->lut_g[i] = green[i] >> 8;
-		psb_intel_crtc->lut_b[i] = blue[i] >> 8;
-	}
-
-	psb_intel_crtc_load_lut(crtc);
-}
-
-static int psb_crtc_set_config(struct drm_mode_set *set)
-{
-	int ret;
-	struct drm_device *dev = set->crtc->dev;
-	struct drm_psb_private *dev_priv = dev->dev_private;
-
-	if (!dev_priv->rpm_enabled)
-		return drm_crtc_helper_set_config(set);
-
-	pm_runtime_forbid(&dev->pdev->dev);
-	ret = drm_crtc_helper_set_config(set);
-	pm_runtime_allow(&dev->pdev->dev);
-	return ret;
-}
-
 /* Returns the clock of the currently programmed mode of the given pipe. */
 static int psb_intel_crtc_clock_get(struct drm_device *dev,
 				struct drm_crtc *crtc)
 {
-	struct psb_intel_crtc *psb_intel_crtc = to_psb_intel_crtc(crtc);
+	struct gma_crtc *gma_crtc = to_gma_crtc(crtc);
 	struct drm_psb_private *dev_priv = dev->dev_private;
-	int pipe = psb_intel_crtc->pipe;
+	int pipe = gma_crtc->pipe;
 	const struct psb_offset *map = &dev_priv->regmap[pipe];
 	u32 dpll;
 	u32 fp;
-	struct psb_intel_clock_t clock;
+	struct gma_clock_t clock;
 	bool is_lvds;
 	struct psb_pipe *p = &dev_priv->regs.pipe[pipe];
 
@@ -1092,8 +383,8 @@ static int psb_intel_crtc_clock_get(struct drm_device *dev,
 struct drm_display_mode *psb_intel_crtc_mode_get(struct drm_device *dev,
 					     struct drm_crtc *crtc)
 {
-	struct psb_intel_crtc *psb_intel_crtc = to_psb_intel_crtc(crtc);
-	int pipe = psb_intel_crtc->pipe;
+	struct gma_crtc *gma_crtc = to_gma_crtc(crtc);
+	int pipe = gma_crtc->pipe;
 	struct drm_display_mode *mode;
 	int htot;
 	int hsync;
@@ -1136,58 +427,30 @@ struct drm_display_mode *psb_intel_crtc_mode_get(struct drm_device *dev,
 	return mode;
 }
 
-static void psb_intel_crtc_destroy(struct drm_crtc *crtc)
-{
-	struct psb_intel_crtc *psb_intel_crtc = to_psb_intel_crtc(crtc);
-	struct gtt_range *gt;
-
-	/* Unpin the old GEM object */
-	if (psb_intel_crtc->cursor_obj) {
-		gt = container_of(psb_intel_crtc->cursor_obj,
-						struct gtt_range, gem);
-		psb_gtt_unpin(gt);
-		drm_gem_object_unreference(psb_intel_crtc->cursor_obj);
-		psb_intel_crtc->cursor_obj = NULL;
-	}
-
-	if (psb_intel_crtc->cursor_gt != NULL)
-		psb_gtt_free_range(crtc->dev, psb_intel_crtc->cursor_gt);
-	kfree(psb_intel_crtc->crtc_state);
-	drm_crtc_cleanup(crtc);
-	kfree(psb_intel_crtc);
-}
-
-static void psb_intel_crtc_disable(struct drm_crtc *crtc)
-{
-	struct gtt_range *gt;
-	struct drm_crtc_helper_funcs *crtc_funcs = crtc->helper_private;
-
-	crtc_funcs->dpms(crtc, DRM_MODE_DPMS_OFF);
-
-	if (crtc->fb) {
-		gt = to_psb_fb(crtc->fb)->gtt;
-		psb_gtt_unpin(gt);
-	}
-}
-
 const struct drm_crtc_helper_funcs psb_intel_helper_funcs = {
-	.dpms = psb_intel_crtc_dpms,
-	.mode_fixup = psb_intel_crtc_mode_fixup,
+	.dpms = gma_crtc_dpms,
+	.mode_fixup = gma_crtc_mode_fixup,
 	.mode_set = psb_intel_crtc_mode_set,
-	.mode_set_base = psb_intel_pipe_set_base,
-	.prepare = psb_intel_crtc_prepare,
-	.commit = psb_intel_crtc_commit,
-	.disable = psb_intel_crtc_disable,
+	.mode_set_base = gma_pipe_set_base,
+	.prepare = gma_crtc_prepare,
+	.commit = gma_crtc_commit,
+	.disable = gma_crtc_disable,
 };
 
 const struct drm_crtc_funcs psb_intel_crtc_funcs = {
-	.save = psb_intel_crtc_save,
-	.restore = psb_intel_crtc_restore,
-	.cursor_set = psb_intel_crtc_cursor_set,
-	.cursor_move = psb_intel_crtc_cursor_move,
-	.gamma_set = psb_intel_crtc_gamma_set,
-	.set_config = psb_crtc_set_config,
-	.destroy = psb_intel_crtc_destroy,
+	.save = gma_crtc_save,
+	.restore = gma_crtc_restore,
+	.cursor_set = gma_crtc_cursor_set,
+	.cursor_move = gma_crtc_cursor_move,
+	.gamma_set = gma_crtc_gamma_set,
+	.set_config = gma_crtc_set_config,
+	.destroy = gma_crtc_destroy,
+};
+
+const struct gma_clock_funcs psb_clock_funcs = {
+	.clock = psb_intel_clock,
+	.limit = psb_intel_limit,
+	.pll_is_valid = gma_pll_is_valid,
 };
 
 /*
@@ -1195,7 +458,7 @@ const struct drm_crtc_funcs psb_intel_crtc_funcs = {
  * to zero. This is a workaround for h/w defect on Oaktrail
  */
 static void psb_intel_cursor_init(struct drm_device *dev,
-				  struct psb_intel_crtc *psb_intel_crtc)
+				  struct gma_crtc *gma_crtc)
 {
 	struct drm_psb_private *dev_priv = dev->dev_private;
 	u32 control[3] = { CURACNTR, CURBCNTR, CURCCNTR };
@@ -1208,88 +471,87 @@ static void psb_intel_cursor_init(struct drm_device *dev,
 		 */
 		cursor_gt = psb_gtt_alloc_range(dev, 4 * PAGE_SIZE, "cursor", 1);
 		if (!cursor_gt) {
-			psb_intel_crtc->cursor_gt = NULL;
+			gma_crtc->cursor_gt = NULL;
 			goto out;
 		}
-		psb_intel_crtc->cursor_gt = cursor_gt;
-		psb_intel_crtc->cursor_addr = dev_priv->stolen_base +
+		gma_crtc->cursor_gt = cursor_gt;
+		gma_crtc->cursor_addr = dev_priv->stolen_base +
 							cursor_gt->offset;
 	} else {
-		psb_intel_crtc->cursor_gt = NULL;
+		gma_crtc->cursor_gt = NULL;
 	}
 
 out:
-	REG_WRITE(control[psb_intel_crtc->pipe], 0);
-	REG_WRITE(base[psb_intel_crtc->pipe], 0);
+	REG_WRITE(control[gma_crtc->pipe], 0);
+	REG_WRITE(base[gma_crtc->pipe], 0);
 }
 
 void psb_intel_crtc_init(struct drm_device *dev, int pipe,
 		     struct psb_intel_mode_device *mode_dev)
 {
 	struct drm_psb_private *dev_priv = dev->dev_private;
-	struct psb_intel_crtc *psb_intel_crtc;
+	struct gma_crtc *gma_crtc;
 	int i;
 	uint16_t *r_base, *g_base, *b_base;
 
 	/* We allocate a extra array of drm_connector pointers
 	 * for fbdev after the crtc */
-	psb_intel_crtc =
-	    kzalloc(sizeof(struct psb_intel_crtc) +
-		    (INTELFB_CONN_LIMIT * sizeof(struct drm_connector *)),
-		    GFP_KERNEL);
-	if (psb_intel_crtc == NULL)
+	gma_crtc = kzalloc(sizeof(struct gma_crtc) +
+			(INTELFB_CONN_LIMIT * sizeof(struct drm_connector *)),
+			GFP_KERNEL);
+	if (gma_crtc == NULL)
 		return;
 
-	psb_intel_crtc->crtc_state =
+	gma_crtc->crtc_state =
 		kzalloc(sizeof(struct psb_intel_crtc_state), GFP_KERNEL);
-	if (!psb_intel_crtc->crtc_state) {
+	if (!gma_crtc->crtc_state) {
 		dev_err(dev->dev, "Crtc state error: No memory\n");
-		kfree(psb_intel_crtc);
+		kfree(gma_crtc);
 		return;
 	}
 
 	/* Set the CRTC operations from the chip specific data */
-	drm_crtc_init(dev, &psb_intel_crtc->base, dev_priv->ops->crtc_funcs);
+	drm_crtc_init(dev, &gma_crtc->base, dev_priv->ops->crtc_funcs);
 
-	drm_mode_crtc_set_gamma_size(&psb_intel_crtc->base, 256);
-	psb_intel_crtc->pipe = pipe;
-	psb_intel_crtc->plane = pipe;
+	/* Set the CRTC clock functions from chip specific data */
+	gma_crtc->clock_funcs = dev_priv->ops->clock_funcs;
 
-	r_base = psb_intel_crtc->base.gamma_store;
+	drm_mode_crtc_set_gamma_size(&gma_crtc->base, 256);
+	gma_crtc->pipe = pipe;
+	gma_crtc->plane = pipe;
+
+	r_base = gma_crtc->base.gamma_store;
 	g_base = r_base + 256;
 	b_base = g_base + 256;
 	for (i = 0; i < 256; i++) {
-		psb_intel_crtc->lut_r[i] = i;
-		psb_intel_crtc->lut_g[i] = i;
-		psb_intel_crtc->lut_b[i] = i;
+		gma_crtc->lut_r[i] = i;
+		gma_crtc->lut_g[i] = i;
+		gma_crtc->lut_b[i] = i;
 		r_base[i] = i << 8;
 		g_base[i] = i << 8;
 		b_base[i] = i << 8;
 
-		psb_intel_crtc->lut_adj[i] = 0;
+		gma_crtc->lut_adj[i] = 0;
 	}
 
-	psb_intel_crtc->mode_dev = mode_dev;
-	psb_intel_crtc->cursor_addr = 0;
+	gma_crtc->mode_dev = mode_dev;
+	gma_crtc->cursor_addr = 0;
 
-	drm_crtc_helper_add(&psb_intel_crtc->base,
+	drm_crtc_helper_add(&gma_crtc->base,
 						dev_priv->ops->crtc_helper);
 
 	/* Setup the array of drm_connector pointer array */
-	psb_intel_crtc->mode_set.crtc = &psb_intel_crtc->base;
+	gma_crtc->mode_set.crtc = &gma_crtc->base;
 	BUG_ON(pipe >= ARRAY_SIZE(dev_priv->plane_to_crtc_mapping) ||
-	       dev_priv->plane_to_crtc_mapping[psb_intel_crtc->plane] != NULL);
-	dev_priv->plane_to_crtc_mapping[psb_intel_crtc->plane] =
-							&psb_intel_crtc->base;
-	dev_priv->pipe_to_crtc_mapping[psb_intel_crtc->pipe] =
-							&psb_intel_crtc->base;
-	psb_intel_crtc->mode_set.connectors =
-	    (struct drm_connector **) (psb_intel_crtc + 1);
-	psb_intel_crtc->mode_set.num_connectors = 0;
-	psb_intel_cursor_init(dev, psb_intel_crtc);
+	       dev_priv->plane_to_crtc_mapping[gma_crtc->plane] != NULL);
+	dev_priv->plane_to_crtc_mapping[gma_crtc->plane] = &gma_crtc->base;
+	dev_priv->pipe_to_crtc_mapping[gma_crtc->pipe] = &gma_crtc->base;
+	gma_crtc->mode_set.connectors = (struct drm_connector **)(gma_crtc + 1);
+	gma_crtc->mode_set.num_connectors = 0;
+	psb_intel_cursor_init(dev, gma_crtc);
 
 	/* Set to true so that the pipe is forced off on initial config. */
-	psb_intel_crtc->active = true;
+	gma_crtc->active = true;
 }
 
 int psb_intel_get_pipe_from_crtc_id(struct drm_device *dev, void *data,
@@ -1298,7 +560,7 @@ int psb_intel_get_pipe_from_crtc_id(struct drm_device *dev, void *data,
 	struct drm_psb_private *dev_priv = dev->dev_private;
 	struct drm_psb_get_pipe_from_crtc_id_arg *pipe_from_crtc_id = data;
 	struct drm_mode_object *drmmode_obj;
-	struct psb_intel_crtc *crtc;
+	struct gma_crtc *crtc;
 
 	if (!dev_priv) {
 		dev_err(dev->dev, "called with no initialization\n");
@@ -1313,7 +575,7 @@ int psb_intel_get_pipe_from_crtc_id(struct drm_device *dev, void *data,
 		return -EINVAL;
 	}
 
-	crtc = to_psb_intel_crtc(obj_to_crtc(drmmode_obj));
+	crtc = to_gma_crtc(obj_to_crtc(drmmode_obj));
 	pipe_from_crtc_id->pipe = crtc->pipe;
 
 	return 0;
@@ -1324,14 +586,14 @@ struct drm_crtc *psb_intel_get_crtc_from_pipe(struct drm_device *dev, int pipe)
 	struct drm_crtc *crtc = NULL;
 
 	list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
-		struct psb_intel_crtc *psb_intel_crtc = to_psb_intel_crtc(crtc);
-		if (psb_intel_crtc->pipe == pipe)
+		struct gma_crtc *gma_crtc = to_gma_crtc(crtc);
+		if (gma_crtc->pipe == pipe)
 			break;
 	}
 	return crtc;
 }
 
-int psb_intel_connector_clones(struct drm_device *dev, int type_mask)
+int gma_connector_clones(struct drm_device *dev, int type_mask)
 {
 	int index_mask = 0;
 	struct drm_connector *connector;
@@ -1339,30 +601,10 @@ int psb_intel_connector_clones(struct drm_device *dev, int type_mask)
 
 	list_for_each_entry(connector, &dev->mode_config.connector_list,
 			    head) {
-		struct psb_intel_encoder *psb_intel_encoder =
-					psb_intel_attached_encoder(connector);
-		if (type_mask & (1 << psb_intel_encoder->type))
+		struct gma_encoder *gma_encoder = gma_attached_encoder(connector);
+		if (type_mask & (1 << gma_encoder->type))
 			index_mask |= (1 << entry);
 		entry++;
 	}
 	return index_mask;
 }
-
-/* current intel driver doesn't take advantage of encoders
-   always give back the encoder for the connector
-*/
-struct drm_encoder *psb_intel_best_encoder(struct drm_connector *connector)
-{
-	struct psb_intel_encoder *psb_intel_encoder =
-					psb_intel_attached_encoder(connector);
-
-	return &psb_intel_encoder->base;
-}
-
-void psb_intel_connector_attach_encoder(struct psb_intel_connector *connector,
-					struct psb_intel_encoder *encoder)
-{
-	connector->encoder = encoder;
-	drm_mode_connector_attach_encoder(&connector->base,
-					  &encoder->base);
-}
diff --git a/drivers/gpu/drm/gma500/psb_intel_drv.h b/drivers/gpu/drm/gma500/psb_intel_drv.h
index 4dcae421a58d..bde27fdb41bf 100644
--- a/drivers/gpu/drm/gma500/psb_intel_drv.h
+++ b/drivers/gpu/drm/gma500/psb_intel_drv.h
@@ -24,6 +24,7 @@
 #include <drm/drm_crtc.h>
 #include <drm/drm_crtc_helper.h>
 #include <linux/gpio.h>
+#include "gma_display.h"
 
 /*
  * Display related stuff
@@ -116,11 +117,11 @@ struct psb_intel_i2c_chan {
 	u8 slave_addr;
 };
 
-struct psb_intel_encoder {
+struct gma_encoder {
 	struct drm_encoder base;
 	int type;
 	bool needs_tv_clock;
-	void (*hot_plug)(struct psb_intel_encoder *);
+	void (*hot_plug)(struct gma_encoder *);
 	int crtc_mask;
 	int clone_mask;
 	u32 ddi_select;	/* Channel info */
@@ -136,9 +137,9 @@ struct psb_intel_encoder {
 	struct psb_intel_i2c_chan *ddc_bus;
 };
 
-struct psb_intel_connector {
+struct gma_connector {
 	struct drm_connector base;
-	struct psb_intel_encoder *encoder;
+	struct gma_encoder *encoder;
 };
 
 struct psb_intel_crtc_state {
@@ -161,7 +162,7 @@ struct psb_intel_crtc_state {
 	uint32_t savePalette[256];
 };
 
-struct psb_intel_crtc {
+struct gma_crtc {
 	struct drm_crtc base;
 	int pipe;
 	int plane;
@@ -188,14 +189,16 @@ struct psb_intel_crtc {
 
 	/* Saved Crtc HW states */
 	struct psb_intel_crtc_state *crtc_state;
+
+	const struct gma_clock_funcs *clock_funcs;
 };
 
-#define to_psb_intel_crtc(x)	\
-		container_of(x, struct psb_intel_crtc, base)
-#define to_psb_intel_connector(x) \
-		container_of(x, struct psb_intel_connector, base)
-#define to_psb_intel_encoder(x)	\
-		container_of(x, struct psb_intel_encoder, base)
+#define to_gma_crtc(x)	\
+		container_of(x, struct gma_crtc, base)
+#define to_gma_connector(x) \
+		container_of(x, struct gma_connector, base)
+#define to_gma_encoder(x)	\
+		container_of(x, struct gma_encoder, base)
 #define to_psb_intel_framebuffer(x)	\
 		container_of(x, struct psb_intel_framebuffer, base)
 
@@ -223,27 +226,18 @@ extern void oaktrail_dsi_init(struct drm_device *dev,
 extern void mid_dsi_init(struct drm_device *dev,
 		    struct psb_intel_mode_device *mode_dev, int dsi_num);
 
-extern void psb_intel_crtc_load_lut(struct drm_crtc *crtc);
-extern void psb_intel_encoder_prepare(struct drm_encoder *encoder);
-extern void psb_intel_encoder_commit(struct drm_encoder *encoder);
-extern void psb_intel_encoder_destroy(struct drm_encoder *encoder);
+extern struct drm_encoder *gma_best_encoder(struct drm_connector *connector);
+extern void gma_connector_attach_encoder(struct gma_connector *connector,
+					 struct gma_encoder *encoder);
 
-static inline struct psb_intel_encoder *psb_intel_attached_encoder(
+static inline struct gma_encoder *gma_attached_encoder(
 						struct drm_connector *connector)
 {
-	return to_psb_intel_connector(connector)->encoder;
+	return to_gma_connector(connector)->encoder;
 }
 
-extern void psb_intel_connector_attach_encoder(
-					struct psb_intel_connector *connector,
-					struct psb_intel_encoder *encoder);
-
-extern struct drm_encoder *psb_intel_best_encoder(struct drm_connector
-					      *connector);
-
 extern struct drm_display_mode *psb_intel_crtc_mode_get(struct drm_device *dev,
 						    struct drm_crtc *crtc);
-extern void psb_intel_wait_for_vblank(struct drm_device *dev);
 extern int psb_intel_get_pipe_from_crtc_id(struct drm_device *dev, void *data,
 				struct drm_file *file_priv);
 extern struct drm_crtc *psb_intel_get_crtc_from_pipe(struct drm_device *dev,
diff --git a/drivers/gpu/drm/gma500/psb_intel_lvds.c b/drivers/gpu/drm/gma500/psb_intel_lvds.c
index 9fa5fa2e6192..32342f6990d9 100644
--- a/drivers/gpu/drm/gma500/psb_intel_lvds.c
+++ b/drivers/gpu/drm/gma500/psb_intel_lvds.c
@@ -267,10 +267,9 @@ static void psb_intel_lvds_save(struct drm_connector *connector)
 	struct drm_device *dev = connector->dev;
 	struct drm_psb_private *dev_priv =
 		(struct drm_psb_private *)dev->dev_private;
-	struct psb_intel_encoder *psb_intel_encoder =
-					psb_intel_attached_encoder(connector);
+	struct gma_encoder *gma_encoder = gma_attached_encoder(connector);
 	struct psb_intel_lvds_priv *lvds_priv =
-		(struct psb_intel_lvds_priv *)psb_intel_encoder->dev_priv;
+		(struct psb_intel_lvds_priv *)gma_encoder->dev_priv;
 
 	lvds_priv->savePP_ON = REG_READ(LVDSPP_ON);
 	lvds_priv->savePP_OFF = REG_READ(LVDSPP_OFF);
@@ -307,10 +306,9 @@ static void psb_intel_lvds_restore(struct drm_connector *connector)
 {
 	struct drm_device *dev = connector->dev;
 	u32 pp_status;
-	struct psb_intel_encoder *psb_intel_encoder =
-					psb_intel_attached_encoder(connector);
+	struct gma_encoder *gma_encoder = gma_attached_encoder(connector);
 	struct psb_intel_lvds_priv *lvds_priv =
-		(struct psb_intel_lvds_priv *)psb_intel_encoder->dev_priv;
+		(struct psb_intel_lvds_priv *)gma_encoder->dev_priv;
 
 	dev_dbg(dev->dev, "(0x%x, 0x%x, 0x%x, 0x%x, 0x%x, 0x%x)\n",
 			lvds_priv->savePP_ON,
@@ -349,12 +347,11 @@ int psb_intel_lvds_mode_valid(struct drm_connector *connector,
 				 struct drm_display_mode *mode)
 {
 	struct drm_psb_private *dev_priv = connector->dev->dev_private;
-	struct psb_intel_encoder *psb_intel_encoder =
-					psb_intel_attached_encoder(connector);
+	struct gma_encoder *gma_encoder = gma_attached_encoder(connector);
 	struct drm_display_mode *fixed_mode =
 					dev_priv->mode_dev.panel_fixed_mode;
 
-	if (psb_intel_encoder->type == INTEL_OUTPUT_MIPI2)
+	if (gma_encoder->type == INTEL_OUTPUT_MIPI2)
 		fixed_mode = dev_priv->mode_dev.panel_fixed_mode2;
 
 	/* just in case */
@@ -381,22 +378,20 @@ bool psb_intel_lvds_mode_fixup(struct drm_encoder *encoder,
 	struct drm_device *dev = encoder->dev;
 	struct drm_psb_private *dev_priv = dev->dev_private;
 	struct psb_intel_mode_device *mode_dev = &dev_priv->mode_dev;
-	struct psb_intel_crtc *psb_intel_crtc =
-				to_psb_intel_crtc(encoder->crtc);
+	struct gma_crtc *gma_crtc = to_gma_crtc(encoder->crtc);
 	struct drm_encoder *tmp_encoder;
 	struct drm_display_mode *panel_fixed_mode = mode_dev->panel_fixed_mode;
-	struct psb_intel_encoder *psb_intel_encoder =
-						to_psb_intel_encoder(encoder);
+	struct gma_encoder *gma_encoder = to_gma_encoder(encoder);
 
-	if (psb_intel_encoder->type == INTEL_OUTPUT_MIPI2)
+	if (gma_encoder->type == INTEL_OUTPUT_MIPI2)
 		panel_fixed_mode = mode_dev->panel_fixed_mode2;
 
 	/* PSB requires the LVDS is on pipe B, MRST has only one pipe anyway */
-	if (!IS_MRST(dev) && psb_intel_crtc->pipe == 0) {
+	if (!IS_MRST(dev) && gma_crtc->pipe == 0) {
 		printk(KERN_ERR "Can't support LVDS on pipe A\n");
 		return false;
 	}
-	if (IS_MRST(dev) && psb_intel_crtc->pipe != 0) {
+	if (IS_MRST(dev) && gma_crtc->pipe != 0) {
 		printk(KERN_ERR "Must use PIPE A\n");
 		return false;
 	}
@@ -525,9 +520,8 @@ static int psb_intel_lvds_get_modes(struct drm_connector *connector)
 	struct drm_device *dev = connector->dev;
 	struct drm_psb_private *dev_priv = dev->dev_private;
 	struct psb_intel_mode_device *mode_dev = &dev_priv->mode_dev;
-	struct psb_intel_encoder *psb_intel_encoder =
-					psb_intel_attached_encoder(connector);
-	struct psb_intel_lvds_priv *lvds_priv = psb_intel_encoder->dev_priv;
+	struct gma_encoder *gma_encoder = gma_attached_encoder(connector);
+	struct psb_intel_lvds_priv *lvds_priv = gma_encoder->dev_priv;
 	int ret = 0;
 
 	if (!IS_MRST(dev))
@@ -564,9 +558,8 @@ static int psb_intel_lvds_get_modes(struct drm_connector *connector)
  */
 void psb_intel_lvds_destroy(struct drm_connector *connector)
 {
-	struct psb_intel_encoder *psb_intel_encoder =
-					psb_intel_attached_encoder(connector);
-	struct psb_intel_lvds_priv *lvds_priv = psb_intel_encoder->dev_priv;
+	struct gma_encoder *gma_encoder = gma_attached_encoder(connector);
+	struct psb_intel_lvds_priv *lvds_priv = gma_encoder->dev_priv;
 
 	if (lvds_priv->ddc_bus)
 		psb_intel_i2c_destroy(lvds_priv->ddc_bus);
@@ -585,8 +578,7 @@ int psb_intel_lvds_set_property(struct drm_connector *connector,
 		return -1;
 
 	if (!strcmp(property->name, "scaling mode")) {
-		struct psb_intel_crtc *crtc =
-					to_psb_intel_crtc(encoder->crtc);
+		struct gma_crtc *crtc = to_gma_crtc(encoder->crtc);
 		uint64_t curval;
 
 		if (!crtc)
@@ -656,7 +648,7 @@ const struct drm_connector_helper_funcs
 				psb_intel_lvds_connector_helper_funcs = {
 	.get_modes = psb_intel_lvds_get_modes,
 	.mode_valid = psb_intel_lvds_mode_valid,
-	.best_encoder = psb_intel_best_encoder,
+	.best_encoder = gma_best_encoder,
 };
 
 const struct drm_connector_funcs psb_intel_lvds_connector_funcs = {
@@ -691,8 +683,8 @@ const struct drm_encoder_funcs psb_intel_lvds_enc_funcs = {
 void psb_intel_lvds_init(struct drm_device *dev,
 			 struct psb_intel_mode_device *mode_dev)
 {
-	struct psb_intel_encoder *psb_intel_encoder;
-	struct psb_intel_connector *psb_intel_connector;
+	struct gma_encoder *gma_encoder;
+	struct gma_connector *gma_connector;
 	struct psb_intel_lvds_priv *lvds_priv;
 	struct drm_connector *connector;
 	struct drm_encoder *encoder;
@@ -702,17 +694,15 @@ void psb_intel_lvds_init(struct drm_device *dev,
 	u32 lvds;
 	int pipe;
 
-	psb_intel_encoder =
-			kzalloc(sizeof(struct psb_intel_encoder), GFP_KERNEL);
-	if (!psb_intel_encoder) {
-		dev_err(dev->dev, "psb_intel_encoder allocation error\n");
+	gma_encoder = kzalloc(sizeof(struct gma_encoder), GFP_KERNEL);
+	if (!gma_encoder) {
+		dev_err(dev->dev, "gma_encoder allocation error\n");
 		return;
 	}
 
-	psb_intel_connector =
-		kzalloc(sizeof(struct psb_intel_connector), GFP_KERNEL);
-	if (!psb_intel_connector) {
-		dev_err(dev->dev, "psb_intel_connector allocation error\n");
+	gma_connector = kzalloc(sizeof(struct gma_connector), GFP_KERNEL);
+	if (!gma_connector) {
+		dev_err(dev->dev, "gma_connector allocation error\n");
 		goto failed_encoder;
 	}
 
@@ -722,10 +712,10 @@ void psb_intel_lvds_init(struct drm_device *dev,
 		goto failed_connector;
 	}
 
-	psb_intel_encoder->dev_priv = lvds_priv;
+	gma_encoder->dev_priv = lvds_priv;
 
-	connector = &psb_intel_connector->base;
-	encoder = &psb_intel_encoder->base;
+	connector = &gma_connector->base;
+	encoder = &gma_encoder->base;
 	drm_connector_init(dev, connector,
 			   &psb_intel_lvds_connector_funcs,
 			   DRM_MODE_CONNECTOR_LVDS);
@@ -734,9 +724,8 @@ void psb_intel_lvds_init(struct drm_device *dev,
 			 &psb_intel_lvds_enc_funcs,
 			 DRM_MODE_ENCODER_LVDS);
 
-	psb_intel_connector_attach_encoder(psb_intel_connector,
-					   psb_intel_encoder);
-	psb_intel_encoder->type = INTEL_OUTPUT_LVDS;
+	gma_connector_attach_encoder(gma_connector, gma_encoder);
+	gma_encoder->type = INTEL_OUTPUT_LVDS;
 
 	drm_encoder_helper_add(encoder, &psb_intel_lvds_helper_funcs);
 	drm_connector_helper_add(connector,
@@ -851,8 +840,8 @@ failed_blc_i2c:
 	drm_encoder_cleanup(encoder);
 	drm_connector_cleanup(connector);
 failed_connector:
-	kfree(psb_intel_connector);
+	kfree(gma_connector);
 failed_encoder:
-	kfree(psb_intel_encoder);
+	kfree(gma_encoder);
 }
 
diff --git a/drivers/gpu/drm/gma500/psb_intel_sdvo.c b/drivers/gpu/drm/gma500/psb_intel_sdvo.c
index 3bc8414533c9..6f01cdf5e125 100644
--- a/drivers/gpu/drm/gma500/psb_intel_sdvo.c
+++ b/drivers/gpu/drm/gma500/psb_intel_sdvo.c
@@ -65,7 +65,7 @@ static const char *tv_format_names[] = {
 #define TV_FORMAT_NUM  (sizeof(tv_format_names) / sizeof(*tv_format_names))
 
 struct psb_intel_sdvo {
-	struct psb_intel_encoder base;
+	struct gma_encoder base;
 
 	struct i2c_adapter *i2c;
 	u8 slave_addr;
@@ -140,7 +140,7 @@ struct psb_intel_sdvo {
 };
 
 struct psb_intel_sdvo_connector {
-	struct psb_intel_connector base;
+	struct gma_connector base;
 
 	/* Mark the type of connector */
 	uint16_t output_flag;
@@ -200,13 +200,13 @@ static struct psb_intel_sdvo *to_psb_intel_sdvo(struct drm_encoder *encoder)
 
 static struct psb_intel_sdvo *intel_attached_sdvo(struct drm_connector *connector)
 {
-	return container_of(psb_intel_attached_encoder(connector),
+	return container_of(gma_attached_encoder(connector),
 			    struct psb_intel_sdvo, base);
 }
 
 static struct psb_intel_sdvo_connector *to_psb_intel_sdvo_connector(struct drm_connector *connector)
 {
-	return container_of(to_psb_intel_connector(connector), struct psb_intel_sdvo_connector, base);
+	return container_of(to_gma_connector(connector), struct psb_intel_sdvo_connector, base);
 }
 
 static bool
@@ -988,7 +988,7 @@ static void psb_intel_sdvo_mode_set(struct drm_encoder *encoder,
 {
 	struct drm_device *dev = encoder->dev;
 	struct drm_crtc *crtc = encoder->crtc;
-	struct psb_intel_crtc *psb_intel_crtc = to_psb_intel_crtc(crtc);
+	struct gma_crtc *gma_crtc = to_gma_crtc(crtc);
 	struct psb_intel_sdvo *psb_intel_sdvo = to_psb_intel_sdvo(encoder);
 	u32 sdvox;
 	struct psb_intel_sdvo_in_out_map in_out;
@@ -1071,7 +1071,7 @@ static void psb_intel_sdvo_mode_set(struct drm_encoder *encoder,
 	}
 	sdvox |= (9 << 19) | SDVO_BORDER_ENABLE;
 
-	if (psb_intel_crtc->pipe == 1)
+	if (gma_crtc->pipe == 1)
 		sdvox |= SDVO_PIPE_B_SELECT;
 	if (psb_intel_sdvo->has_hdmi_audio)
 		sdvox |= SDVO_AUDIO_ENABLE;
@@ -1122,7 +1122,7 @@ static void psb_intel_sdvo_dpms(struct drm_encoder *encoder, int mode)
 		if ((temp & SDVO_ENABLE) == 0)
 			psb_intel_sdvo_write_sdvox(psb_intel_sdvo, temp | SDVO_ENABLE);
 		for (i = 0; i < 2; i++)
-			psb_intel_wait_for_vblank(dev);
+			gma_wait_for_vblank(dev);
 
 		status = psb_intel_sdvo_get_trained_inputs(psb_intel_sdvo, &input1, &input2);
 		/* Warn if the device reported failure to sync.
@@ -1837,10 +1837,8 @@ done:
 static void psb_intel_sdvo_save(struct drm_connector *connector)
 {
 	struct drm_device *dev = connector->dev;
-	struct psb_intel_encoder *psb_intel_encoder =
-					psb_intel_attached_encoder(connector);
-	struct psb_intel_sdvo *sdvo =
-				to_psb_intel_sdvo(&psb_intel_encoder->base);
+	struct gma_encoder *gma_encoder = gma_attached_encoder(connector);
+	struct psb_intel_sdvo *sdvo = to_psb_intel_sdvo(&gma_encoder->base);
 
 	sdvo->saveSDVO = REG_READ(sdvo->sdvo_reg);
 }
@@ -1848,8 +1846,7 @@ static void psb_intel_sdvo_save(struct drm_connector *connector)
 static void psb_intel_sdvo_restore(struct drm_connector *connector)
 {
 	struct drm_device *dev = connector->dev;
-	struct drm_encoder *encoder =
-				&psb_intel_attached_encoder(connector)->base;
+	struct drm_encoder *encoder = &gma_attached_encoder(connector)->base;
 	struct psb_intel_sdvo *sdvo = to_psb_intel_sdvo(encoder);
 	struct drm_crtc *crtc = encoder->crtc;
 
@@ -1865,9 +1862,9 @@ static void psb_intel_sdvo_restore(struct drm_connector *connector)
 static const struct drm_encoder_helper_funcs psb_intel_sdvo_helper_funcs = {
 	.dpms = psb_intel_sdvo_dpms,
 	.mode_fixup = psb_intel_sdvo_mode_fixup,
-	.prepare = psb_intel_encoder_prepare,
+	.prepare = gma_encoder_prepare,
 	.mode_set = psb_intel_sdvo_mode_set,
-	.commit = psb_intel_encoder_commit,
+	.commit = gma_encoder_commit,
 };
 
 static const struct drm_connector_funcs psb_intel_sdvo_connector_funcs = {
@@ -1883,7 +1880,7 @@ static const struct drm_connector_funcs psb_intel_sdvo_connector_funcs = {
 static const struct drm_connector_helper_funcs psb_intel_sdvo_connector_helper_funcs = {
 	.get_modes = psb_intel_sdvo_get_modes,
 	.mode_valid = psb_intel_sdvo_mode_valid,
-	.best_encoder = psb_intel_best_encoder,
+	.best_encoder = gma_best_encoder,
 };
 
 static void psb_intel_sdvo_enc_destroy(struct drm_encoder *encoder)
@@ -1895,7 +1892,7 @@ static void psb_intel_sdvo_enc_destroy(struct drm_encoder *encoder)
 				 psb_intel_sdvo->sdvo_lvds_fixed_mode);
 
 	i2c_del_adapter(&psb_intel_sdvo->ddc);
-	psb_intel_encoder_destroy(encoder);
+	gma_encoder_destroy(encoder);
 }
 
 static const struct drm_encoder_funcs psb_intel_sdvo_enc_funcs = {
@@ -2056,7 +2053,7 @@ psb_intel_sdvo_connector_init(struct psb_intel_sdvo_connector *connector,
 	connector->base.base.doublescan_allowed = 0;
 	connector->base.base.display_info.subpixel_order = SubPixelHorizontalRGB;
 
-	psb_intel_connector_attach_encoder(&connector->base, &encoder->base);
+	gma_connector_attach_encoder(&connector->base, &encoder->base);
 	drm_sysfs_connector_add(&connector->base.base);
 }
 
@@ -2076,7 +2073,7 @@ psb_intel_sdvo_dvi_init(struct psb_intel_sdvo *psb_intel_sdvo, int device)
 {
 	struct drm_encoder *encoder = &psb_intel_sdvo->base.base;
 	struct drm_connector *connector;
-	struct psb_intel_connector *intel_connector;
+	struct gma_connector *intel_connector;
 	struct psb_intel_sdvo_connector *psb_intel_sdvo_connector;
 
 	psb_intel_sdvo_connector = kzalloc(sizeof(struct psb_intel_sdvo_connector), GFP_KERNEL);
@@ -2116,7 +2113,7 @@ psb_intel_sdvo_tv_init(struct psb_intel_sdvo *psb_intel_sdvo, int type)
 {
 	struct drm_encoder *encoder = &psb_intel_sdvo->base.base;
 	struct drm_connector *connector;
-	struct psb_intel_connector *intel_connector;
+	struct gma_connector *intel_connector;
 	struct psb_intel_sdvo_connector *psb_intel_sdvo_connector;
 
 	psb_intel_sdvo_connector = kzalloc(sizeof(struct psb_intel_sdvo_connector), GFP_KERNEL);
@@ -2155,7 +2152,7 @@ psb_intel_sdvo_analog_init(struct psb_intel_sdvo *psb_intel_sdvo, int device)
 {
 	struct drm_encoder *encoder = &psb_intel_sdvo->base.base;
 	struct drm_connector *connector;
-	struct psb_intel_connector *intel_connector;
+	struct gma_connector *intel_connector;
 	struct psb_intel_sdvo_connector *psb_intel_sdvo_connector;
 
 	psb_intel_sdvo_connector = kzalloc(sizeof(struct psb_intel_sdvo_connector), GFP_KERNEL);
@@ -2189,7 +2186,7 @@ psb_intel_sdvo_lvds_init(struct psb_intel_sdvo *psb_intel_sdvo, int device)
 {
 	struct drm_encoder *encoder = &psb_intel_sdvo->base.base;
 	struct drm_connector *connector;
-	struct psb_intel_connector *intel_connector;
+	struct gma_connector *intel_connector;
 	struct psb_intel_sdvo_connector *psb_intel_sdvo_connector;
 
 	psb_intel_sdvo_connector = kzalloc(sizeof(struct psb_intel_sdvo_connector), GFP_KERNEL);
@@ -2541,7 +2538,7 @@ psb_intel_sdvo_init_ddc_proxy(struct psb_intel_sdvo *sdvo,
 bool psb_intel_sdvo_init(struct drm_device *dev, int sdvo_reg)
 {
 	struct drm_psb_private *dev_priv = dev->dev_private;
-	struct psb_intel_encoder *psb_intel_encoder;
+	struct gma_encoder *gma_encoder;
 	struct psb_intel_sdvo *psb_intel_sdvo;
 	int i;
 
@@ -2558,9 +2555,9 @@ bool psb_intel_sdvo_init(struct drm_device *dev, int sdvo_reg)
 	}
 
 	/* encoder type will be decided later */
-	psb_intel_encoder = &psb_intel_sdvo->base;
-	psb_intel_encoder->type = INTEL_OUTPUT_SDVO;
-	drm_encoder_init(dev, &psb_intel_encoder->base, &psb_intel_sdvo_enc_funcs, 0);
+	gma_encoder = &psb_intel_sdvo->base;
+	gma_encoder->type = INTEL_OUTPUT_SDVO;
+	drm_encoder_init(dev, &gma_encoder->base, &psb_intel_sdvo_enc_funcs, 0);
 
 	/* Read the regs to test if we can talk to the device */
 	for (i = 0; i < 0x40; i++) {
@@ -2578,7 +2575,7 @@ bool psb_intel_sdvo_init(struct drm_device *dev, int sdvo_reg)
 	else
 		dev_priv->hotplug_supported_mask |= SDVOC_HOTPLUG_INT_STATUS;
 
-	drm_encoder_helper_add(&psb_intel_encoder->base, &psb_intel_sdvo_helper_funcs);
+	drm_encoder_helper_add(&gma_encoder->base, &psb_intel_sdvo_helper_funcs);
 
 	/* In default case sdvo lvds is false */
 	if (!psb_intel_sdvo_get_capabilities(psb_intel_sdvo, &psb_intel_sdvo->caps))
@@ -2621,7 +2618,7 @@ bool psb_intel_sdvo_init(struct drm_device *dev, int sdvo_reg)
 	return true;
 
 err:
-	drm_encoder_cleanup(&psb_intel_encoder->base);
+	drm_encoder_cleanup(&gma_encoder->base);
 	i2c_del_adapter(&psb_intel_sdvo->ddc);
 	kfree(psb_intel_sdvo);
 
diff --git a/drivers/gpu/drm/i2c/tda998x_drv.c b/drivers/gpu/drm/i2c/tda998x_drv.c
index e68b58a1aaf9..60e84043aa34 100644
--- a/drivers/gpu/drm/i2c/tda998x_drv.c
+++ b/drivers/gpu/drm/i2c/tda998x_drv.c
@@ -23,7 +23,7 @@
 #include <drm/drm_crtc_helper.h>
 #include <drm/drm_encoder_slave.h>
 #include <drm/drm_edid.h>
-
+#include <drm/i2c/tda998x.h>
 
 #define DBG(fmt, ...) DRM_DEBUG(fmt"\n", ##__VA_ARGS__)
 
@@ -32,6 +32,11 @@ struct tda998x_priv {
 	uint16_t rev;
 	uint8_t current_page;
 	int dpms;
+	bool is_hdmi_sink;
+	u8 vip_cntrl_0;
+	u8 vip_cntrl_1;
+	u8 vip_cntrl_2;
+	struct tda998x_encoder_params params;
 };
 
 #define to_tda998x_priv(x)  ((struct tda998x_priv *)to_encoder_slave(x)->slave_priv)
@@ -68,10 +73,13 @@ struct tda998x_priv {
 # define I2C_MASTER_DIS_MM        (1 << 0)
 # define I2C_MASTER_DIS_FILT      (1 << 1)
 # define I2C_MASTER_APP_STRT_LAT  (1 << 2)
+#define REG_FEAT_POWERDOWN        REG(0x00, 0x0e)     /* read/write */
+# define FEAT_POWERDOWN_SPDIF     (1 << 3)
 #define REG_INT_FLAGS_0           REG(0x00, 0x0f)     /* read/write */
 #define REG_INT_FLAGS_1           REG(0x00, 0x10)     /* read/write */
 #define REG_INT_FLAGS_2           REG(0x00, 0x11)     /* read/write */
 # define INT_FLAGS_2_EDID_BLK_RD  (1 << 1)
+#define REG_ENA_ACLK              REG(0x00, 0x16)     /* read/write */
 #define REG_ENA_VP_0              REG(0x00, 0x18)     /* read/write */
 #define REG_ENA_VP_1              REG(0x00, 0x19)     /* read/write */
 #define REG_ENA_VP_2              REG(0x00, 0x1a)     /* read/write */
@@ -110,6 +118,8 @@ struct tda998x_priv {
 #define REG_VIP_CNTRL_5           REG(0x00, 0x25)     /* write */
 # define VIP_CNTRL_5_CKCASE       (1 << 0)
 # define VIP_CNTRL_5_SP_CNT(x)    (((x) & 3) << 1)
+#define REG_MUX_AP                REG(0x00, 0x26)     /* read/write */
+#define REG_MUX_VP_VIP_OUT        REG(0x00, 0x27)     /* read/write */
 #define REG_MAT_CONTRL            REG(0x00, 0x80)     /* write */
 # define MAT_CONTRL_MAT_SC(x)     (((x) & 3) << 0)
 # define MAT_CONTRL_MAT_BP        (1 << 2)
@@ -130,8 +140,12 @@ struct tda998x_priv {
 #define REG_VS_LINE_END_1_LSB     REG(0x00, 0xae)     /* write */
 #define REG_VS_PIX_END_1_MSB      REG(0x00, 0xaf)     /* write */
 #define REG_VS_PIX_END_1_LSB      REG(0x00, 0xb0)     /* write */
+#define REG_VS_LINE_STRT_2_MSB    REG(0x00, 0xb1)     /* write */
+#define REG_VS_LINE_STRT_2_LSB    REG(0x00, 0xb2)     /* write */
 #define REG_VS_PIX_STRT_2_MSB     REG(0x00, 0xb3)     /* write */
 #define REG_VS_PIX_STRT_2_LSB     REG(0x00, 0xb4)     /* write */
+#define REG_VS_LINE_END_2_MSB     REG(0x00, 0xb5)     /* write */
+#define REG_VS_LINE_END_2_LSB     REG(0x00, 0xb6)     /* write */
 #define REG_VS_PIX_END_2_MSB      REG(0x00, 0xb7)     /* write */
 #define REG_VS_PIX_END_2_LSB      REG(0x00, 0xb8)     /* write */
 #define REG_HS_PIX_START_MSB      REG(0x00, 0xb9)     /* write */
@@ -142,21 +156,29 @@ struct tda998x_priv {
 #define REG_VWIN_START_1_LSB      REG(0x00, 0xbe)     /* write */
 #define REG_VWIN_END_1_MSB        REG(0x00, 0xbf)     /* write */
 #define REG_VWIN_END_1_LSB        REG(0x00, 0xc0)     /* write */
+#define REG_VWIN_START_2_MSB      REG(0x00, 0xc1)     /* write */
+#define REG_VWIN_START_2_LSB      REG(0x00, 0xc2)     /* write */
+#define REG_VWIN_END_2_MSB        REG(0x00, 0xc3)     /* write */
+#define REG_VWIN_END_2_LSB        REG(0x00, 0xc4)     /* write */
 #define REG_DE_START_MSB          REG(0x00, 0xc5)     /* write */
 #define REG_DE_START_LSB          REG(0x00, 0xc6)     /* write */
 #define REG_DE_STOP_MSB           REG(0x00, 0xc7)     /* write */
 #define REG_DE_STOP_LSB           REG(0x00, 0xc8)     /* write */
 #define REG_TBG_CNTRL_0           REG(0x00, 0xca)     /* write */
+# define TBG_CNTRL_0_TOP_TGL      (1 << 0)
+# define TBG_CNTRL_0_TOP_SEL      (1 << 1)
+# define TBG_CNTRL_0_DE_EXT       (1 << 2)
+# define TBG_CNTRL_0_TOP_EXT      (1 << 3)
 # define TBG_CNTRL_0_FRAME_DIS    (1 << 5)
 # define TBG_CNTRL_0_SYNC_MTHD    (1 << 6)
 # define TBG_CNTRL_0_SYNC_ONCE    (1 << 7)
 #define REG_TBG_CNTRL_1           REG(0x00, 0xcb)     /* write */
-# define TBG_CNTRL_1_VH_TGL_0     (1 << 0)
-# define TBG_CNTRL_1_VH_TGL_1     (1 << 1)
-# define TBG_CNTRL_1_VH_TGL_2     (1 << 2)
-# define TBG_CNTRL_1_VHX_EXT_DE   (1 << 3)
-# define TBG_CNTRL_1_VHX_EXT_HS   (1 << 4)
-# define TBG_CNTRL_1_VHX_EXT_VS   (1 << 5)
+# define TBG_CNTRL_1_H_TGL        (1 << 0)
+# define TBG_CNTRL_1_V_TGL        (1 << 1)
+# define TBG_CNTRL_1_TGL_EN       (1 << 2)
+# define TBG_CNTRL_1_X_EXT        (1 << 3)
+# define TBG_CNTRL_1_H_EXT        (1 << 4)
+# define TBG_CNTRL_1_V_EXT        (1 << 5)
 # define TBG_CNTRL_1_DWIN_DIS     (1 << 6)
 #define REG_ENABLE_SPACE          REG(0x00, 0xd6)     /* write */
 #define REG_HVF_CNTRL_0           REG(0x00, 0xe4)     /* write */
@@ -171,6 +193,12 @@ struct tda998x_priv {
 # define HVF_CNTRL_1_PAD(x)       (((x) & 3) << 4)
 # define HVF_CNTRL_1_SEMI_PLANAR  (1 << 6)
 #define REG_RPT_CNTRL             REG(0x00, 0xf0)     /* write */
+#define REG_I2S_FORMAT            REG(0x00, 0xfc)     /* read/write */
+# define I2S_FORMAT(x)            (((x) & 3) << 0)
+#define REG_AIP_CLKSEL            REG(0x00, 0xfd)     /* write */
+# define AIP_CLKSEL_FS(x)         (((x) & 3) << 0)
+# define AIP_CLKSEL_CLK_POL(x)    (((x) & 1) << 2)
+# define AIP_CLKSEL_AIP(x)        (((x) & 7) << 3)
 
 
 /* Page 02h: PLL settings */
@@ -194,6 +222,12 @@ struct tda998x_priv {
 #define REG_PLL_SCGR1             REG(0x02, 0x09)     /* read/write */
 #define REG_PLL_SCGR2             REG(0x02, 0x0a)     /* read/write */
 #define REG_AUDIO_DIV             REG(0x02, 0x0e)     /* read/write */
+# define AUDIO_DIV_SERCLK_1       0
+# define AUDIO_DIV_SERCLK_2       1
+# define AUDIO_DIV_SERCLK_4       2
+# define AUDIO_DIV_SERCLK_8       3
+# define AUDIO_DIV_SERCLK_16      4
+# define AUDIO_DIV_SERCLK_32      5
 #define REG_SEL_CLK               REG(0x02, 0x11)     /* read/write */
 # define SEL_CLK_SEL_CLK1         (1 << 0)
 # define SEL_CLK_SEL_VRF_CLK(x)   (((x) & 3) << 1)
@@ -212,6 +246,11 @@ struct tda998x_priv {
 
 
 /* Page 10h: information frames and packets */
+#define REG_IF1_HB0               REG(0x10, 0x20)     /* read/write */
+#define REG_IF2_HB0               REG(0x10, 0x40)     /* read/write */
+#define REG_IF3_HB0               REG(0x10, 0x60)     /* read/write */
+#define REG_IF4_HB0               REG(0x10, 0x80)     /* read/write */
+#define REG_IF5_HB0               REG(0x10, 0xa0)     /* read/write */
 
 
 /* Page 11h: audio settings and content info packets */
@@ -221,14 +260,39 @@ struct tda998x_priv {
 # define AIP_CNTRL_0_LAYOUT       (1 << 2)
 # define AIP_CNTRL_0_ACR_MAN      (1 << 5)
 # define AIP_CNTRL_0_RST_CTS      (1 << 6)
+#define REG_CA_I2S                REG(0x11, 0x01)     /* read/write */
+# define CA_I2S_CA_I2S(x)         (((x) & 31) << 0)
+# define CA_I2S_HBR_CHSTAT        (1 << 6)
+#define REG_LATENCY_RD            REG(0x11, 0x04)     /* read/write */
+#define REG_ACR_CTS_0             REG(0x11, 0x05)     /* read/write */
+#define REG_ACR_CTS_1             REG(0x11, 0x06)     /* read/write */
+#define REG_ACR_CTS_2             REG(0x11, 0x07)     /* read/write */
+#define REG_ACR_N_0               REG(0x11, 0x08)     /* read/write */
+#define REG_ACR_N_1               REG(0x11, 0x09)     /* read/write */
+#define REG_ACR_N_2               REG(0x11, 0x0a)     /* read/write */
+#define REG_CTS_N                 REG(0x11, 0x0c)     /* read/write */
+# define CTS_N_K(x)               (((x) & 7) << 0)
+# define CTS_N_M(x)               (((x) & 3) << 4)
 #define REG_ENC_CNTRL             REG(0x11, 0x0d)     /* read/write */
 # define ENC_CNTRL_RST_ENC        (1 << 0)
 # define ENC_CNTRL_RST_SEL        (1 << 1)
 # define ENC_CNTRL_CTL_CODE(x)    (((x) & 3) << 2)
+#define REG_DIP_FLAGS             REG(0x11, 0x0e)     /* read/write */
+# define DIP_FLAGS_ACR            (1 << 0)
+# define DIP_FLAGS_GC             (1 << 1)
+#define REG_DIP_IF_FLAGS          REG(0x11, 0x0f)     /* read/write */
+# define DIP_IF_FLAGS_IF1         (1 << 1)
+# define DIP_IF_FLAGS_IF2         (1 << 2)
+# define DIP_IF_FLAGS_IF3         (1 << 3)
+# define DIP_IF_FLAGS_IF4         (1 << 4)
+# define DIP_IF_FLAGS_IF5         (1 << 5)
+#define REG_CH_STAT_B(x)          REG(0x11, 0x14 + (x)) /* read/write */
 
 
 /* Page 12h: HDCP and OTP */
 #define REG_TX3                   REG(0x12, 0x9a)     /* read/write */
+#define REG_TX4                   REG(0x12, 0x9b)     /* read/write */
+# define TX4_PD_RAM               (1 << 1)
 #define REG_TX33                  REG(0x12, 0xb8)     /* read/write */
 # define TX33_HDMI                (1 << 1)
 
@@ -338,6 +402,23 @@ fail:
 	return ret;
 }
 
+static void
+reg_write_range(struct drm_encoder *encoder, uint16_t reg, uint8_t *p, int cnt)
+{
+	struct i2c_client *client = drm_i2c_encoder_get_client(encoder);
+	uint8_t buf[cnt+1];
+	int ret;
+
+	buf[0] = REG2ADDR(reg);
+	memcpy(&buf[1], p, cnt);
+
+	set_page(encoder, reg);
+
+	ret = i2c_master_send(client, buf, cnt + 1);
+	if (ret < 0)
+		dev_err(&client->dev, "Error %d writing to 0x%x\n", ret, reg);
+}
+
 static uint8_t
 reg_read(struct drm_encoder *encoder, uint16_t reg)
 {
@@ -406,13 +487,176 @@ tda998x_reset(struct drm_encoder *encoder)
 	reg_write(encoder, REG_SERIALIZER,   0x00);
 	reg_write(encoder, REG_BUFFER_OUT,   0x00);
 	reg_write(encoder, REG_PLL_SCG1,     0x00);
-	reg_write(encoder, REG_AUDIO_DIV,    0x03);
+	reg_write(encoder, REG_AUDIO_DIV,    AUDIO_DIV_SERCLK_8);
 	reg_write(encoder, REG_SEL_CLK,      SEL_CLK_SEL_CLK1 | SEL_CLK_ENA_SC_CLK);
 	reg_write(encoder, REG_PLL_SCGN1,    0xfa);
 	reg_write(encoder, REG_PLL_SCGN2,    0x00);
 	reg_write(encoder, REG_PLL_SCGR1,    0x5b);
 	reg_write(encoder, REG_PLL_SCGR2,    0x00);
 	reg_write(encoder, REG_PLL_SCG2,     0x10);
+
+	/* Write the default value MUX register */
+	reg_write(encoder, REG_MUX_VP_VIP_OUT, 0x24);
+}
+
+static uint8_t tda998x_cksum(uint8_t *buf, size_t bytes)
+{
+	uint8_t sum = 0;
+
+	while (bytes--)
+		sum += *buf++;
+	return (255 - sum) + 1;
+}
+
+#define HB(x) (x)
+#define PB(x) (HB(2) + 1 + (x))
+
+static void
+tda998x_write_if(struct drm_encoder *encoder, uint8_t bit, uint16_t addr,
+		 uint8_t *buf, size_t size)
+{
+	buf[PB(0)] = tda998x_cksum(buf, size);
+
+	reg_clear(encoder, REG_DIP_IF_FLAGS, bit);
+	reg_write_range(encoder, addr, buf, size);
+	reg_set(encoder, REG_DIP_IF_FLAGS, bit);
+}
+
+static void
+tda998x_write_aif(struct drm_encoder *encoder, struct tda998x_encoder_params *p)
+{
+	uint8_t buf[PB(5) + 1];
+
+	buf[HB(0)] = 0x84;
+	buf[HB(1)] = 0x01;
+	buf[HB(2)] = 10;
+	buf[PB(0)] = 0;
+	buf[PB(1)] = p->audio_frame[1] & 0x07; /* CC */
+	buf[PB(2)] = p->audio_frame[2] & 0x1c; /* SF */
+	buf[PB(4)] = p->audio_frame[4];
+	buf[PB(5)] = p->audio_frame[5] & 0xf8; /* DM_INH + LSV */
+
+	tda998x_write_if(encoder, DIP_IF_FLAGS_IF4, REG_IF4_HB0, buf,
+			 sizeof(buf));
+}
+
+static void
+tda998x_write_avi(struct drm_encoder *encoder, struct drm_display_mode *mode)
+{
+	uint8_t buf[PB(13) + 1];
+
+	memset(buf, 0, sizeof(buf));
+	buf[HB(0)] = 0x82;
+	buf[HB(1)] = 0x02;
+	buf[HB(2)] = 13;
+	buf[PB(4)] = drm_match_cea_mode(mode);
+
+	tda998x_write_if(encoder, DIP_IF_FLAGS_IF2, REG_IF2_HB0, buf,
+			 sizeof(buf));
+}
+
+static void tda998x_audio_mute(struct drm_encoder *encoder, bool on)
+{
+	if (on) {
+		reg_set(encoder, REG_SOFTRESET, SOFTRESET_AUDIO);
+		reg_clear(encoder, REG_SOFTRESET, SOFTRESET_AUDIO);
+		reg_set(encoder, REG_AIP_CNTRL_0, AIP_CNTRL_0_RST_FIFO);
+	} else {
+		reg_clear(encoder, REG_AIP_CNTRL_0, AIP_CNTRL_0_RST_FIFO);
+	}
+}
+
+static void
+tda998x_configure_audio(struct drm_encoder *encoder,
+		struct drm_display_mode *mode, struct tda998x_encoder_params *p)
+{
+	uint8_t buf[6], clksel_aip, clksel_fs, ca_i2s, cts_n, adiv;
+	uint32_t n;
+
+	/* Enable audio ports */
+	reg_write(encoder, REG_ENA_AP, p->audio_cfg);
+	reg_write(encoder, REG_ENA_ACLK, p->audio_clk_cfg);
+
+	/* Set audio input source */
+	switch (p->audio_format) {
+	case AFMT_SPDIF:
+		reg_write(encoder, REG_MUX_AP, 0x40);
+		clksel_aip = AIP_CLKSEL_AIP(0);
+		/* FS64SPDIF */
+		clksel_fs = AIP_CLKSEL_FS(2);
+		cts_n = CTS_N_M(3) | CTS_N_K(3);
+		ca_i2s = 0;
+		break;
+
+	case AFMT_I2S:
+		reg_write(encoder, REG_MUX_AP, 0x64);
+		clksel_aip = AIP_CLKSEL_AIP(1);
+		/* ACLK */
+		clksel_fs = AIP_CLKSEL_FS(0);
+		cts_n = CTS_N_M(3) | CTS_N_K(3);
+		ca_i2s = CA_I2S_CA_I2S(0);
+		break;
+
+	default:
+		BUG();
+		return;
+	}
+
+	reg_write(encoder, REG_AIP_CLKSEL, clksel_aip);
+	reg_clear(encoder, REG_AIP_CNTRL_0, AIP_CNTRL_0_LAYOUT);
+
+	/* Enable automatic CTS generation */
+	reg_clear(encoder, REG_AIP_CNTRL_0, AIP_CNTRL_0_ACR_MAN);
+	reg_write(encoder, REG_CTS_N, cts_n);
+
+	/*
+	 * Audio input somehow depends on HDMI line rate which is
+	 * related to pixclk. Testing showed that modes with pixclk
+	 * >100MHz need a larger divider while <40MHz need the default.
+	 * There is no detailed info in the datasheet, so we just
+	 * assume 100MHz requires larger divider.
+	 */
+	if (mode->clock > 100000)
+		adiv = AUDIO_DIV_SERCLK_16;
+	else
+		adiv = AUDIO_DIV_SERCLK_8;
+	reg_write(encoder, REG_AUDIO_DIV, adiv);
+
+	/*
+	 * This is the approximate value of N, which happens to be
+	 * the recommended values for non-coherent clocks.
+	 */
+	n = 128 * p->audio_sample_rate / 1000;
+
+	/* Write the CTS and N values */
+	buf[0] = 0x44;
+	buf[1] = 0x42;
+	buf[2] = 0x01;
+	buf[3] = n;
+	buf[4] = n >> 8;
+	buf[5] = n >> 16;
+	reg_write_range(encoder, REG_ACR_CTS_0, buf, 6);
+
+	/* Set CTS clock reference */
+	reg_write(encoder, REG_AIP_CLKSEL, clksel_aip | clksel_fs);
+
+	/* Reset CTS generator */
+	reg_set(encoder, REG_AIP_CNTRL_0, AIP_CNTRL_0_RST_CTS);
+	reg_clear(encoder, REG_AIP_CNTRL_0, AIP_CNTRL_0_RST_CTS);
+
+	/* Write the channel status */
+	buf[0] = 0x04;
+	buf[1] = 0x00;
+	buf[2] = 0x00;
+	buf[3] = 0xf1;
+	reg_write_range(encoder, REG_CH_STAT_B(0), buf, 4);
+
+	tda998x_audio_mute(encoder, true);
+	mdelay(20);
+	tda998x_audio_mute(encoder, false);
+
+	/* Write the audio information packet */
+	tda998x_write_aif(encoder, p);
 }
 
 /* DRM encoder functions */
@@ -420,6 +664,23 @@ tda998x_reset(struct drm_encoder *encoder)
 static void
 tda998x_encoder_set_config(struct drm_encoder *encoder, void *params)
 {
+	struct tda998x_priv *priv = to_tda998x_priv(encoder);
+	struct tda998x_encoder_params *p = params;
+
+	priv->vip_cntrl_0 = VIP_CNTRL_0_SWAP_A(p->swap_a) |
+			    (p->mirr_a ? VIP_CNTRL_0_MIRR_A : 0) |
+			    VIP_CNTRL_0_SWAP_B(p->swap_b) |
+			    (p->mirr_b ? VIP_CNTRL_0_MIRR_B : 0);
+	priv->vip_cntrl_1 = VIP_CNTRL_1_SWAP_C(p->swap_c) |
+			    (p->mirr_c ? VIP_CNTRL_1_MIRR_C : 0) |
+			    VIP_CNTRL_1_SWAP_D(p->swap_d) |
+			    (p->mirr_d ? VIP_CNTRL_1_MIRR_D : 0);
+	priv->vip_cntrl_2 = VIP_CNTRL_2_SWAP_E(p->swap_e) |
+			    (p->mirr_e ? VIP_CNTRL_2_MIRR_E : 0) |
+			    VIP_CNTRL_2_SWAP_F(p->swap_f) |
+			    (p->mirr_f ? VIP_CNTRL_2_MIRR_F : 0);
+
+	priv->params = *p;
 }
 
 static void
@@ -436,22 +697,17 @@ tda998x_encoder_dpms(struct drm_encoder *encoder, int mode)
 
 	switch (mode) {
 	case DRM_MODE_DPMS_ON:
-		/* enable audio and video ports */
-		reg_write(encoder, REG_ENA_AP, 0xff);
+		/* enable video ports, audio will be enabled later */
 		reg_write(encoder, REG_ENA_VP_0, 0xff);
 		reg_write(encoder, REG_ENA_VP_1, 0xff);
 		reg_write(encoder, REG_ENA_VP_2, 0xff);
 		/* set muxing after enabling ports: */
-		reg_write(encoder, REG_VIP_CNTRL_0,
-				VIP_CNTRL_0_SWAP_A(2) | VIP_CNTRL_0_SWAP_B(3));
-		reg_write(encoder, REG_VIP_CNTRL_1,
-				VIP_CNTRL_1_SWAP_C(0) | VIP_CNTRL_1_SWAP_D(1));
-		reg_write(encoder, REG_VIP_CNTRL_2,
-				VIP_CNTRL_2_SWAP_E(4) | VIP_CNTRL_2_SWAP_F(5));
+		reg_write(encoder, REG_VIP_CNTRL_0, priv->vip_cntrl_0);
+		reg_write(encoder, REG_VIP_CNTRL_1, priv->vip_cntrl_1);
+		reg_write(encoder, REG_VIP_CNTRL_2, priv->vip_cntrl_2);
 		break;
 	case DRM_MODE_DPMS_OFF:
-		/* disable audio and video ports */
-		reg_write(encoder, REG_ENA_AP, 0x00);
+		/* disable video ports */
 		reg_write(encoder, REG_ENA_VP_0, 0x00);
 		reg_write(encoder, REG_ENA_VP_1, 0x00);
 		reg_write(encoder, REG_ENA_VP_2, 0x00);
@@ -494,43 +750,78 @@ tda998x_encoder_mode_set(struct drm_encoder *encoder,
 			struct drm_display_mode *adjusted_mode)
 {
 	struct tda998x_priv *priv = to_tda998x_priv(encoder);
-	uint16_t hs_start, hs_end, line_start, line_end;
-	uint16_t vwin_start, vwin_end, de_start, de_end;
-	uint16_t ref_pix, ref_line, pix_start2;
+	uint16_t ref_pix, ref_line, n_pix, n_line;
+	uint16_t hs_pix_s, hs_pix_e;
+	uint16_t vs1_pix_s, vs1_pix_e, vs1_line_s, vs1_line_e;
+	uint16_t vs2_pix_s, vs2_pix_e, vs2_line_s, vs2_line_e;
+	uint16_t vwin1_line_s, vwin1_line_e;
+	uint16_t vwin2_line_s, vwin2_line_e;
+	uint16_t de_pix_s, de_pix_e;
 	uint8_t reg, div, rep;
 
-	hs_start   = mode->hsync_start - mode->hdisplay;
-	hs_end     = mode->hsync_end - mode->hdisplay;
-	line_start = 1;
-	line_end   = 1 + mode->vsync_end - mode->vsync_start;
-	vwin_start = mode->vtotal - mode->vsync_start;
-	vwin_end   = vwin_start + mode->vdisplay;
-	de_start   = mode->htotal - mode->hdisplay;
-	de_end     = mode->htotal;
-
-	pix_start2 = 0;
-	if (mode->flags & DRM_MODE_FLAG_INTERLACE)
-		pix_start2 = (mode->htotal / 2) + hs_start;
-
-	/* TODO how is this value calculated?  It is 2 for all common
-	 * formats in the tables in out of tree nxp driver (assuming
-	 * I've properly deciphered their byzantine table system)
+	/*
+	 * Internally TDA998x is using ITU-R BT.656 style sync but
+	 * we get VESA style sync. TDA998x is using a reference pixel
+	 * relative to ITU to sync to the input frame and for output
+	 * sync generation. Currently, we are using reference detection
+	 * from HS/VS, i.e. REFPIX/REFLINE denote frame start sync point
+	 * which is position of rising VS with coincident rising HS.
+	 *
+	 * Now there is some issues to take care of:
+	 * - HDMI data islands require sync-before-active
+	 * - TDA998x register values must be > 0 to be enabled
+	 * - REFLINE needs an additional offset of +1
+	 * - REFPIX needs an addtional offset of +1 for UYUV and +3 for RGB
+	 *
+	 * So we add +1 to all horizontal and vertical register values,
+	 * plus an additional +3 for REFPIX as we are using RGB input only.
 	 */
-	ref_line = 2;
-
-	/* this might changes for other color formats from the CRTC: */
-	ref_pix = 3 + hs_start;
+	n_pix        = mode->htotal;
+	n_line       = mode->vtotal;
+
+	hs_pix_e     = mode->hsync_end - mode->hdisplay;
+	hs_pix_s     = mode->hsync_start - mode->hdisplay;
+	de_pix_e     = mode->htotal;
+	de_pix_s     = mode->htotal - mode->hdisplay;
+	ref_pix      = 3 + hs_pix_s;
+
+	/*
+	 * Attached LCD controllers may generate broken sync. Allow
+	 * those to adjust the position of the rising VS edge by adding
+	 * HSKEW to ref_pix.
+	 */
+	if (adjusted_mode->flags & DRM_MODE_FLAG_HSKEW)
+		ref_pix += adjusted_mode->hskew;
+
+	if ((mode->flags & DRM_MODE_FLAG_INTERLACE) == 0) {
+		ref_line     = 1 + mode->vsync_start - mode->vdisplay;
+		vwin1_line_s = mode->vtotal - mode->vdisplay - 1;
+		vwin1_line_e = vwin1_line_s + mode->vdisplay;
+		vs1_pix_s    = vs1_pix_e = hs_pix_s;
+		vs1_line_s   = mode->vsync_start - mode->vdisplay;
+		vs1_line_e   = vs1_line_s +
+			       mode->vsync_end - mode->vsync_start;
+		vwin2_line_s = vwin2_line_e = 0;
+		vs2_pix_s    = vs2_pix_e  = 0;
+		vs2_line_s   = vs2_line_e = 0;
+	} else {
+		ref_line     = 1 + (mode->vsync_start - mode->vdisplay)/2;
+		vwin1_line_s = (mode->vtotal - mode->vdisplay)/2;
+		vwin1_line_e = vwin1_line_s + mode->vdisplay/2;
+		vs1_pix_s    = vs1_pix_e = hs_pix_s;
+		vs1_line_s   = (mode->vsync_start - mode->vdisplay)/2;
+		vs1_line_e   = vs1_line_s +
+			       (mode->vsync_end - mode->vsync_start)/2;
+		vwin2_line_s = vwin1_line_s + mode->vtotal/2;
+		vwin2_line_e = vwin2_line_s + mode->vdisplay/2;
+		vs2_pix_s    = vs2_pix_e = hs_pix_s + mode->htotal/2;
+		vs2_line_s   = vs1_line_s + mode->vtotal/2 ;
+		vs2_line_e   = vs2_line_s +
+			       (mode->vsync_end - mode->vsync_start)/2;
+	}
 
 	div = 148500 / mode->clock;
 
-	DBG("clock=%d, div=%u", mode->clock, div);
-	DBG("hs_start=%u, hs_end=%u, line_start=%u, line_end=%u",
-			hs_start, hs_end, line_start, line_end);
-	DBG("vwin_start=%u, vwin_end=%u, de_start=%u, de_end=%u",
-			vwin_start, vwin_end, de_start, de_end);
-	DBG("ref_line=%u, ref_pix=%u, pix_start2=%u",
-			ref_line, ref_pix, pix_start2);
-
 	/* mute the audio FIFO: */
 	reg_set(encoder, REG_AIP_CNTRL_0, AIP_CNTRL_0_RST_FIFO);
 
@@ -561,9 +852,6 @@ tda998x_encoder_mode_set(struct drm_encoder *encoder,
 	reg_write(encoder, REG_PLL_SERIAL_2, PLL_SERIAL_2_SRL_NOSC(div) |
 			PLL_SERIAL_2_SRL_PR(rep));
 
-	reg_write16(encoder, REG_VS_PIX_STRT_2_MSB, pix_start2);
-	reg_write16(encoder, REG_VS_PIX_END_2_MSB, pix_start2);
-
 	/* set color matrix bypass flag: */
 	reg_set(encoder, REG_MAT_CONTRL, MAT_CONTRL_MAT_BP);
 
@@ -572,47 +860,75 @@ tda998x_encoder_mode_set(struct drm_encoder *encoder,
 
 	reg_clear(encoder, REG_TBG_CNTRL_0, TBG_CNTRL_0_SYNC_MTHD);
 
+	/*
+	 * Sync on rising HSYNC/VSYNC
+	 */
 	reg_write(encoder, REG_VIP_CNTRL_3, 0);
 	reg_set(encoder, REG_VIP_CNTRL_3, VIP_CNTRL_3_SYNC_HS);
+
+	/*
+	 * TDA19988 requires high-active sync at input stage,
+	 * so invert low-active sync provided by master encoder here
+	 */
+	if (mode->flags & DRM_MODE_FLAG_NHSYNC)
+		reg_set(encoder, REG_VIP_CNTRL_3, VIP_CNTRL_3_H_TGL);
 	if (mode->flags & DRM_MODE_FLAG_NVSYNC)
 		reg_set(encoder, REG_VIP_CNTRL_3, VIP_CNTRL_3_V_TGL);
 
+	/*
+	 * Always generate sync polarity relative to input sync and
+	 * revert input stage toggled sync at output stage
+	 */
+	reg = TBG_CNTRL_1_TGL_EN;
 	if (mode->flags & DRM_MODE_FLAG_NHSYNC)
-		reg_set(encoder, REG_VIP_CNTRL_3, VIP_CNTRL_3_H_TGL);
+		reg |= TBG_CNTRL_1_H_TGL;
+	if (mode->flags & DRM_MODE_FLAG_NVSYNC)
+		reg |= TBG_CNTRL_1_V_TGL;
+	reg_write(encoder, REG_TBG_CNTRL_1, reg);
 
 	reg_write(encoder, REG_VIDFORMAT, 0x00);
-	reg_write16(encoder, REG_NPIX_MSB, mode->hdisplay - 1);
-	reg_write16(encoder, REG_NLINE_MSB, mode->vdisplay - 1);
-	reg_write16(encoder, REG_VS_LINE_STRT_1_MSB, line_start);
-	reg_write16(encoder, REG_VS_LINE_END_1_MSB, line_end);
-	reg_write16(encoder, REG_VS_PIX_STRT_1_MSB, hs_start);
-	reg_write16(encoder, REG_VS_PIX_END_1_MSB, hs_start);
-	reg_write16(encoder, REG_HS_PIX_START_MSB, hs_start);
-	reg_write16(encoder, REG_HS_PIX_STOP_MSB, hs_end);
-	reg_write16(encoder, REG_VWIN_START_1_MSB, vwin_start);
-	reg_write16(encoder, REG_VWIN_END_1_MSB, vwin_end);
-	reg_write16(encoder, REG_DE_START_MSB, de_start);
-	reg_write16(encoder, REG_DE_STOP_MSB, de_end);
+	reg_write16(encoder, REG_REFPIX_MSB, ref_pix);
+	reg_write16(encoder, REG_REFLINE_MSB, ref_line);
+	reg_write16(encoder, REG_NPIX_MSB, n_pix);
+	reg_write16(encoder, REG_NLINE_MSB, n_line);
+	reg_write16(encoder, REG_VS_LINE_STRT_1_MSB, vs1_line_s);
+	reg_write16(encoder, REG_VS_PIX_STRT_1_MSB, vs1_pix_s);
+	reg_write16(encoder, REG_VS_LINE_END_1_MSB, vs1_line_e);
+	reg_write16(encoder, REG_VS_PIX_END_1_MSB, vs1_pix_e);
+	reg_write16(encoder, REG_VS_LINE_STRT_2_MSB, vs2_line_s);
+	reg_write16(encoder, REG_VS_PIX_STRT_2_MSB, vs2_pix_s);
+	reg_write16(encoder, REG_VS_LINE_END_2_MSB, vs2_line_e);
+	reg_write16(encoder, REG_VS_PIX_END_2_MSB, vs2_pix_e);
+	reg_write16(encoder, REG_HS_PIX_START_MSB, hs_pix_s);
+	reg_write16(encoder, REG_HS_PIX_STOP_MSB, hs_pix_e);
+	reg_write16(encoder, REG_VWIN_START_1_MSB, vwin1_line_s);
+	reg_write16(encoder, REG_VWIN_END_1_MSB, vwin1_line_e);
+	reg_write16(encoder, REG_VWIN_START_2_MSB, vwin2_line_s);
+	reg_write16(encoder, REG_VWIN_END_2_MSB, vwin2_line_e);
+	reg_write16(encoder, REG_DE_START_MSB, de_pix_s);
+	reg_write16(encoder, REG_DE_STOP_MSB, de_pix_e);
 
 	if (priv->rev == TDA19988) {
 		/* let incoming pixels fill the active space (if any) */
 		reg_write(encoder, REG_ENABLE_SPACE, 0x01);
 	}
 
-	reg_write16(encoder, REG_REFPIX_MSB, ref_pix);
-	reg_write16(encoder, REG_REFLINE_MSB, ref_line);
-
-	reg = TBG_CNTRL_1_VHX_EXT_DE |
-			TBG_CNTRL_1_VHX_EXT_HS |
-			TBG_CNTRL_1_VHX_EXT_VS |
-			TBG_CNTRL_1_DWIN_DIS | /* HDCP off */
-			TBG_CNTRL_1_VH_TGL_2;
-	if (mode->flags & (DRM_MODE_FLAG_NVSYNC | DRM_MODE_FLAG_NHSYNC))
-		reg |= TBG_CNTRL_1_VH_TGL_0;
-	reg_set(encoder, REG_TBG_CNTRL_1, reg);
-
 	/* must be last register set: */
 	reg_clear(encoder, REG_TBG_CNTRL_0, TBG_CNTRL_0_SYNC_ONCE);
+
+	/* Only setup the info frames if the sink is HDMI */
+	if (priv->is_hdmi_sink) {
+		/* We need to turn HDMI HDCP stuff on to get audio through */
+		reg_clear(encoder, REG_TBG_CNTRL_1, TBG_CNTRL_1_DWIN_DIS);
+		reg_write(encoder, REG_ENC_CNTRL, ENC_CNTRL_CTL_CODE(1));
+		reg_set(encoder, REG_TX33, TX33_HDMI);
+
+		tda998x_write_avi(encoder, adjusted_mode);
+
+		if (priv->params.audio_cfg)
+			tda998x_configure_audio(encoder, adjusted_mode,
+						&priv->params);
+	}
 }
 
 static enum drm_connector_status
@@ -673,6 +989,7 @@ read_edid_block(struct drm_encoder *encoder, uint8_t *buf, int blk)
 static uint8_t *
 do_get_edid(struct drm_encoder *encoder)
 {
+	struct tda998x_priv *priv = to_tda998x_priv(encoder);
 	int j = 0, valid_extensions = 0;
 	uint8_t *block, *new;
 	bool print_bad_edid = drm_debug & DRM_UT_KMS;
@@ -680,6 +997,9 @@ do_get_edid(struct drm_encoder *encoder)
 	if ((block = kmalloc(EDID_LENGTH, GFP_KERNEL)) == NULL)
 		return NULL;
 
+	if (priv->rev == TDA19988)
+		reg_clear(encoder, REG_TX4, TX4_PD_RAM);
+
 	/* base block fetch */
 	if (read_edid_block(encoder, block, 0))
 		goto fail;
@@ -689,7 +1009,7 @@ do_get_edid(struct drm_encoder *encoder)
 
 	/* if there's no extensions, we're done */
 	if (block[0x7e] == 0)
-		return block;
+		goto done;
 
 	new = krealloc(block, (block[0x7e] + 1) * EDID_LENGTH, GFP_KERNEL);
 	if (!new)
@@ -716,9 +1036,15 @@ do_get_edid(struct drm_encoder *encoder)
 		block = new;
 	}
 
+done:
+	if (priv->rev == TDA19988)
+		reg_set(encoder, REG_TX4, TX4_PD_RAM);
+
 	return block;
 
 fail:
+	if (priv->rev == TDA19988)
+		reg_set(encoder, REG_TX4, TX4_PD_RAM);
 	dev_warn(encoder->dev->dev, "failed to read EDID\n");
 	kfree(block);
 	return NULL;
@@ -728,12 +1054,14 @@ static int
 tda998x_encoder_get_modes(struct drm_encoder *encoder,
 			 struct drm_connector *connector)
 {
+	struct tda998x_priv *priv = to_tda998x_priv(encoder);
 	struct edid *edid = (struct edid *)do_get_edid(encoder);
 	int n = 0;
 
 	if (edid) {
 		drm_mode_connector_update_edid_property(connector, edid);
 		n = drm_add_edid_modes(connector, edid);
+		priv->is_hdmi_sink = drm_detect_hdmi_monitor(edid);
 		kfree(edid);
 	}
 
@@ -807,6 +1135,10 @@ tda998x_encoder_init(struct i2c_client *client,
 	if (!priv)
 		return -ENOMEM;
 
+	priv->vip_cntrl_0 = VIP_CNTRL_0_SWAP_A(2) | VIP_CNTRL_0_SWAP_B(3);
+	priv->vip_cntrl_1 = VIP_CNTRL_1_SWAP_C(0) | VIP_CNTRL_1_SWAP_D(1);
+	priv->vip_cntrl_2 = VIP_CNTRL_2_SWAP_E(4) | VIP_CNTRL_2_SWAP_F(5);
+
 	priv->current_page = 0;
 	priv->cec = i2c_new_dummy(client->adapter, 0x34);
 	priv->dpms = DRM_MODE_DPMS_OFF;
diff --git a/drivers/gpu/drm/i810/i810_dma.c b/drivers/gpu/drm/i810/i810_dma.c
index ada49eda489f..ab1892eb1074 100644
--- a/drivers/gpu/drm/i810/i810_dma.c
+++ b/drivers/gpu/drm/i810/i810_dma.c
@@ -113,7 +113,6 @@ static const struct file_operations i810_buffer_fops = {
 	.release = drm_release,
 	.unlocked_ioctl = drm_ioctl,
 	.mmap = i810_mmap_buffers,
-	.fasync = drm_fasync,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl = drm_compat_ioctl,
 #endif
@@ -1241,7 +1240,7 @@ int i810_driver_dma_quiescent(struct drm_device *dev)
 	return 0;
 }
 
-struct drm_ioctl_desc i810_ioctls[] = {
+const struct drm_ioctl_desc i810_ioctls[] = {
 	DRM_IOCTL_DEF_DRV(I810_INIT, i810_dma_init, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY|DRM_UNLOCKED),
 	DRM_IOCTL_DEF_DRV(I810_VERTEX, i810_dma_vertex, DRM_AUTH|DRM_UNLOCKED),
 	DRM_IOCTL_DEF_DRV(I810_CLEAR, i810_clear_bufs, DRM_AUTH|DRM_UNLOCKED),
diff --git a/drivers/gpu/drm/i810/i810_drv.c b/drivers/gpu/drm/i810/i810_drv.c
index 2e91fc3580b4..d8180d22cedd 100644
--- a/drivers/gpu/drm/i810/i810_drv.c
+++ b/drivers/gpu/drm/i810/i810_drv.c
@@ -49,7 +49,6 @@ static const struct file_operations i810_driver_fops = {
 	.unlocked_ioctl = drm_ioctl,
 	.mmap = drm_mmap,
 	.poll = drm_poll,
-	.fasync = drm_fasync,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl = drm_compat_ioctl,
 #endif
@@ -58,7 +57,7 @@ static const struct file_operations i810_driver_fops = {
 
 static struct drm_driver driver = {
 	.driver_features =
-	    DRIVER_USE_AGP | DRIVER_REQUIRE_AGP | DRIVER_USE_MTRR |
+	    DRIVER_USE_AGP | DRIVER_REQUIRE_AGP |
 	    DRIVER_HAVE_DMA,
 	.dev_priv_size = sizeof(drm_i810_buf_priv_t),
 	.load = i810_driver_load,
diff --git a/drivers/gpu/drm/i810/i810_drv.h b/drivers/gpu/drm/i810/i810_drv.h
index 6e0acad9e0f5..d4d16eddd651 100644
--- a/drivers/gpu/drm/i810/i810_drv.h
+++ b/drivers/gpu/drm/i810/i810_drv.h
@@ -125,7 +125,7 @@ extern void i810_driver_preclose(struct drm_device *dev,
 extern int i810_driver_device_is_agp(struct drm_device *dev);
 
 extern long i810_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
-extern struct drm_ioctl_desc i810_ioctls[];
+extern const struct drm_ioctl_desc i810_ioctls[];
 extern int i810_max_ioctl;
 
 #define I810_BASE(reg)		((unsigned long) \
diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile
index 40034ecefd3b..b8449a84a0dc 100644
--- a/drivers/gpu/drm/i915/Makefile
+++ b/drivers/gpu/drm/i915/Makefile
@@ -5,6 +5,7 @@
 ccflags-y := -Iinclude/drm
 i915-y := i915_drv.o i915_dma.o i915_irq.o \
 	  i915_debugfs.o \
+	  i915_gpu_error.o \
           i915_suspend.o \
 	  i915_gem.o \
 	  i915_gem_context.o \
@@ -37,6 +38,7 @@ i915-y := i915_drv.o i915_dma.o i915_irq.o \
 	  intel_sprite.o \
 	  intel_opregion.o \
 	  intel_sideband.o \
+	  intel_uncore.o \
 	  dvo_ch7xxx.o \
 	  dvo_ch7017.o \
 	  dvo_ivch.o \
diff --git a/drivers/gpu/drm/i915/dvo_ch7xxx.c b/drivers/gpu/drm/i915/dvo_ch7xxx.c
index 757e0fa11043..af42e94f6846 100644
--- a/drivers/gpu/drm/i915/dvo_ch7xxx.c
+++ b/drivers/gpu/drm/i915/dvo_ch7xxx.c
@@ -307,7 +307,7 @@ static void ch7xxx_mode_set(struct intel_dvo_device *dvo,
 		idf |= CH7xxx_IDF_HSP;
 
 	if (mode->flags & DRM_MODE_FLAG_PVSYNC)
-		idf |= CH7xxx_IDF_HSP;
+		idf |= CH7xxx_IDF_VSP;
 
 	ch7xxx_writeb(dvo, CH7xxx_IDF, idf);
 }
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 47d6c748057e..a6f4cb5af185 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -30,7 +30,8 @@
 #include <linux/debugfs.h>
 #include <linux/slab.h>
 #include <linux/export.h>
-#include <generated/utsrelease.h>
+#include <linux/list_sort.h>
+#include <asm/msr-index.h>
 #include <drm/drmP.h>
 #include "intel_drv.h"
 #include "intel_ringbuffer.h"
@@ -90,41 +91,45 @@ static const char *get_tiling_flag(struct drm_i915_gem_object *obj)
 	}
 }
 
-static const char *cache_level_str(int type)
+static inline const char *get_global_flag(struct drm_i915_gem_object *obj)
 {
-	switch (type) {
-	case I915_CACHE_NONE: return " uncached";
-	case I915_CACHE_LLC: return " snooped (LLC)";
-	case I915_CACHE_LLC_MLC: return " snooped (LLC+MLC)";
-	default: return "";
-	}
+	return obj->has_global_gtt_mapping ? "g" : " ";
 }
 
 static void
 describe_obj(struct seq_file *m, struct drm_i915_gem_object *obj)
 {
-	seq_printf(m, "%pK: %s%s %8zdKiB %02x %02x %d %d %d%s%s%s",
+	struct i915_vma *vma;
+	seq_printf(m, "%pK: %s%s%s %8zdKiB %02x %02x %u %u %u%s%s%s",
 		   &obj->base,
 		   get_pin_flag(obj),
 		   get_tiling_flag(obj),
+		   get_global_flag(obj),
 		   obj->base.size / 1024,
 		   obj->base.read_domains,
 		   obj->base.write_domain,
 		   obj->last_read_seqno,
 		   obj->last_write_seqno,
 		   obj->last_fenced_seqno,
-		   cache_level_str(obj->cache_level),
+		   i915_cache_level_str(obj->cache_level),
 		   obj->dirty ? " dirty" : "",
 		   obj->madv == I915_MADV_DONTNEED ? " purgeable" : "");
 	if (obj->base.name)
 		seq_printf(m, " (name: %d)", obj->base.name);
 	if (obj->pin_count)
 		seq_printf(m, " (pinned x %d)", obj->pin_count);
+	if (obj->pin_display)
+		seq_printf(m, " (display)");
 	if (obj->fence_reg != I915_FENCE_REG_NONE)
 		seq_printf(m, " (fence: %d)", obj->fence_reg);
-	if (obj->gtt_space != NULL)
-		seq_printf(m, " (gtt offset: %08x, size: %08x)",
-			   obj->gtt_offset, (unsigned int)obj->gtt_space->size);
+	list_for_each_entry(vma, &obj->vma_list, vma_link) {
+		if (!i915_is_ggtt(vma->vm))
+			seq_puts(m, " (pp");
+		else
+			seq_puts(m, " (g");
+		seq_printf(m, "gtt offset: %08lx, size: %08lx)",
+			   vma->node.start, vma->node.size);
+	}
 	if (obj->stolen)
 		seq_printf(m, " (stolen: %08lx)", obj->stolen->start);
 	if (obj->pin_mappable || obj->fault_mappable) {
@@ -146,8 +151,9 @@ static int i915_gem_object_list_info(struct seq_file *m, void *data)
 	uintptr_t list = (uintptr_t) node->info_ent->data;
 	struct list_head *head;
 	struct drm_device *dev = node->minor->dev;
-	drm_i915_private_t *dev_priv = dev->dev_private;
-	struct drm_i915_gem_object *obj;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct i915_address_space *vm = &dev_priv->gtt.base;
+	struct i915_vma *vma;
 	size_t total_obj_size, total_gtt_size;
 	int count, ret;
 
@@ -155,14 +161,15 @@ static int i915_gem_object_list_info(struct seq_file *m, void *data)
 	if (ret)
 		return ret;
 
+	/* FIXME: the user of this interface might want more than just GGTT */
 	switch (list) {
 	case ACTIVE_LIST:
-		seq_printf(m, "Active:\n");
-		head = &dev_priv->mm.active_list;
+		seq_puts(m, "Active:\n");
+		head = &vm->active_list;
 		break;
 	case INACTIVE_LIST:
-		seq_printf(m, "Inactive:\n");
-		head = &dev_priv->mm.inactive_list;
+		seq_puts(m, "Inactive:\n");
+		head = &vm->inactive_list;
 		break;
 	default:
 		mutex_unlock(&dev->struct_mutex);
@@ -170,14 +177,75 @@ static int i915_gem_object_list_info(struct seq_file *m, void *data)
 	}
 
 	total_obj_size = total_gtt_size = count = 0;
-	list_for_each_entry(obj, head, mm_list) {
+	list_for_each_entry(vma, head, mm_list) {
 		seq_printf(m, "   ");
-		describe_obj(m, obj);
+		describe_obj(m, vma->obj);
 		seq_printf(m, "\n");
+		total_obj_size += vma->obj->base.size;
+		total_gtt_size += vma->node.size;
+		count++;
+	}
+	mutex_unlock(&dev->struct_mutex);
+
+	seq_printf(m, "Total %d objects, %zu bytes, %zu GTT size\n",
+		   count, total_obj_size, total_gtt_size);
+	return 0;
+}
+
+static int obj_rank_by_stolen(void *priv,
+			      struct list_head *A, struct list_head *B)
+{
+	struct drm_i915_gem_object *a =
+		container_of(A, struct drm_i915_gem_object, obj_exec_link);
+	struct drm_i915_gem_object *b =
+		container_of(B, struct drm_i915_gem_object, obj_exec_link);
+
+	return a->stolen->start - b->stolen->start;
+}
+
+static int i915_gem_stolen_list_info(struct seq_file *m, void *data)
+{
+	struct drm_info_node *node = (struct drm_info_node *) m->private;
+	struct drm_device *dev = node->minor->dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_gem_object *obj;
+	size_t total_obj_size, total_gtt_size;
+	LIST_HEAD(stolen);
+	int count, ret;
+
+	ret = mutex_lock_interruptible(&dev->struct_mutex);
+	if (ret)
+		return ret;
+
+	total_obj_size = total_gtt_size = count = 0;
+	list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) {
+		if (obj->stolen == NULL)
+			continue;
+
+		list_add(&obj->obj_exec_link, &stolen);
+
 		total_obj_size += obj->base.size;
-		total_gtt_size += obj->gtt_space->size;
+		total_gtt_size += i915_gem_obj_ggtt_size(obj);
 		count++;
 	}
+	list_for_each_entry(obj, &dev_priv->mm.unbound_list, global_list) {
+		if (obj->stolen == NULL)
+			continue;
+
+		list_add(&obj->obj_exec_link, &stolen);
+
+		total_obj_size += obj->base.size;
+		count++;
+	}
+	list_sort(NULL, &stolen, obj_rank_by_stolen);
+	seq_puts(m, "Stolen:\n");
+	while (!list_empty(&stolen)) {
+		obj = list_first_entry(&stolen, typeof(*obj), obj_exec_link);
+		seq_puts(m, "   ");
+		describe_obj(m, obj);
+		seq_putc(m, '\n');
+		list_del_init(&obj->obj_exec_link);
+	}
 	mutex_unlock(&dev->struct_mutex);
 
 	seq_printf(m, "Total %d objects, %zu bytes, %zu GTT size\n",
@@ -187,10 +255,10 @@ static int i915_gem_object_list_info(struct seq_file *m, void *data)
 
 #define count_objects(list, member) do { \
 	list_for_each_entry(obj, list, member) { \
-		size += obj->gtt_space->size; \
+		size += i915_gem_obj_ggtt_size(obj); \
 		++count; \
 		if (obj->map_and_fenceable) { \
-			mappable_size += obj->gtt_space->size; \
+			mappable_size += i915_gem_obj_ggtt_size(obj); \
 			++mappable_count; \
 		} \
 	} \
@@ -209,7 +277,7 @@ static int per_file_stats(int id, void *ptr, void *data)
 	stats->count++;
 	stats->total += obj->base.size;
 
-	if (obj->gtt_space) {
+	if (i915_gem_obj_ggtt_bound(obj)) {
 		if (!list_empty(&obj->ring_list))
 			stats->active += obj->base.size;
 		else
@@ -222,6 +290,17 @@ static int per_file_stats(int id, void *ptr, void *data)
 	return 0;
 }
 
+#define count_vmas(list, member) do { \
+	list_for_each_entry(vma, list, member) { \
+		size += i915_gem_obj_ggtt_size(vma->obj); \
+		++count; \
+		if (vma->obj->map_and_fenceable) { \
+			mappable_size += i915_gem_obj_ggtt_size(vma->obj); \
+			++mappable_count; \
+		} \
+	} \
+} while (0)
+
 static int i915_gem_object_info(struct seq_file *m, void* data)
 {
 	struct drm_info_node *node = (struct drm_info_node *) m->private;
@@ -230,7 +309,9 @@ static int i915_gem_object_info(struct seq_file *m, void* data)
 	u32 count, mappable_count, purgeable_count;
 	size_t size, mappable_size, purgeable_size;
 	struct drm_i915_gem_object *obj;
+	struct i915_address_space *vm = &dev_priv->gtt.base;
 	struct drm_file *file;
+	struct i915_vma *vma;
 	int ret;
 
 	ret = mutex_lock_interruptible(&dev->struct_mutex);
@@ -247,12 +328,12 @@ static int i915_gem_object_info(struct seq_file *m, void* data)
 		   count, mappable_count, size, mappable_size);
 
 	size = count = mappable_size = mappable_count = 0;
-	count_objects(&dev_priv->mm.active_list, mm_list);
+	count_vmas(&vm->active_list, mm_list);
 	seq_printf(m, "  %u [%u] active objects, %zu [%zu] bytes\n",
 		   count, mappable_count, size, mappable_size);
 
 	size = count = mappable_size = mappable_count = 0;
-	count_objects(&dev_priv->mm.inactive_list, mm_list);
+	count_vmas(&vm->inactive_list, mm_list);
 	seq_printf(m, "  %u [%u] inactive objects, %zu [%zu] bytes\n",
 		   count, mappable_count, size, mappable_size);
 
@@ -267,11 +348,11 @@ static int i915_gem_object_info(struct seq_file *m, void* data)
 	size = count = mappable_size = mappable_count = 0;
 	list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) {
 		if (obj->fault_mappable) {
-			size += obj->gtt_space->size;
+			size += i915_gem_obj_ggtt_size(obj);
 			++count;
 		}
 		if (obj->pin_mappable) {
-			mappable_size += obj->gtt_space->size;
+			mappable_size += i915_gem_obj_ggtt_size(obj);
 			++mappable_count;
 		}
 		if (obj->madv == I915_MADV_DONTNEED) {
@@ -287,10 +368,10 @@ static int i915_gem_object_info(struct seq_file *m, void* data)
 		   count, size);
 
 	seq_printf(m, "%zu [%lu] gtt total\n",
-		   dev_priv->gtt.total,
-		   dev_priv->gtt.mappable_end - dev_priv->gtt.start);
+		   dev_priv->gtt.base.total,
+		   dev_priv->gtt.mappable_end - dev_priv->gtt.base.start);
 
-	seq_printf(m, "\n");
+	seq_putc(m, '\n');
 	list_for_each_entry_reverse(file, &dev->filelist, lhead) {
 		struct file_stats stats;
 
@@ -310,7 +391,7 @@ static int i915_gem_object_info(struct seq_file *m, void* data)
 	return 0;
 }
 
-static int i915_gem_gtt_info(struct seq_file *m, void* data)
+static int i915_gem_gtt_info(struct seq_file *m, void *data)
 {
 	struct drm_info_node *node = (struct drm_info_node *) m->private;
 	struct drm_device *dev = node->minor->dev;
@@ -329,11 +410,11 @@ static int i915_gem_gtt_info(struct seq_file *m, void* data)
 		if (list == PINNED_LIST && obj->pin_count == 0)
 			continue;
 
-		seq_printf(m, "   ");
+		seq_puts(m, "   ");
 		describe_obj(m, obj);
-		seq_printf(m, "\n");
+		seq_putc(m, '\n');
 		total_obj_size += obj->base.size;
-		total_gtt_size += obj->gtt_space->size;
+		total_gtt_size += i915_gem_obj_ggtt_size(obj);
 		count++;
 	}
 
@@ -371,20 +452,22 @@ static int i915_gem_pageflip_info(struct seq_file *m, void *data)
 					   pipe, plane);
 			}
 			if (work->enable_stall_check)
-				seq_printf(m, "Stall check enabled, ");
+				seq_puts(m, "Stall check enabled, ");
 			else
-				seq_printf(m, "Stall check waiting for page flip ioctl, ");
+				seq_puts(m, "Stall check waiting for page flip ioctl, ");
 			seq_printf(m, "%d prepares\n", atomic_read(&work->pending));
 
 			if (work->old_fb_obj) {
 				struct drm_i915_gem_object *obj = work->old_fb_obj;
 				if (obj)
-					seq_printf(m, "Old framebuffer gtt_offset 0x%08x\n", obj->gtt_offset);
+					seq_printf(m, "Old framebuffer gtt_offset 0x%08lx\n",
+						   i915_gem_obj_ggtt_offset(obj));
 			}
 			if (work->pending_flip_obj) {
 				struct drm_i915_gem_object *obj = work->pending_flip_obj;
 				if (obj)
-					seq_printf(m, "New framebuffer gtt_offset 0x%08x\n", obj->gtt_offset);
+					seq_printf(m, "New framebuffer gtt_offset 0x%08lx\n",
+						   i915_gem_obj_ggtt_offset(obj));
 			}
 		}
 		spin_unlock_irqrestore(&dev->event_lock, flags);
@@ -424,7 +507,7 @@ static int i915_gem_request_info(struct seq_file *m, void *data)
 	mutex_unlock(&dev->struct_mutex);
 
 	if (count == 0)
-		seq_printf(m, "No requests\n");
+		seq_puts(m, "No requests\n");
 
 	return 0;
 }
@@ -574,10 +657,10 @@ static int i915_gem_fence_regs_info(struct seq_file *m, void *data)
 		seq_printf(m, "Fence %d, pin count = %d, object = ",
 			   i, dev_priv->fence_regs[i].pin_count);
 		if (obj == NULL)
-			seq_printf(m, "unused");
+			seq_puts(m, "unused");
 		else
 			describe_obj(m, obj);
-		seq_printf(m, "\n");
+		seq_putc(m, '\n');
 	}
 
 	mutex_unlock(&dev->struct_mutex);
@@ -606,361 +689,6 @@ static int i915_hws_info(struct seq_file *m, void *data)
 	return 0;
 }
 
-static const char *ring_str(int ring)
-{
-	switch (ring) {
-	case RCS: return "render";
-	case VCS: return "bsd";
-	case BCS: return "blt";
-	case VECS: return "vebox";
-	default: return "";
-	}
-}
-
-static const char *pin_flag(int pinned)
-{
-	if (pinned > 0)
-		return " P";
-	else if (pinned < 0)
-		return " p";
-	else
-		return "";
-}
-
-static const char *tiling_flag(int tiling)
-{
-	switch (tiling) {
-	default:
-	case I915_TILING_NONE: return "";
-	case I915_TILING_X: return " X";
-	case I915_TILING_Y: return " Y";
-	}
-}
-
-static const char *dirty_flag(int dirty)
-{
-	return dirty ? " dirty" : "";
-}
-
-static const char *purgeable_flag(int purgeable)
-{
-	return purgeable ? " purgeable" : "";
-}
-
-static bool __i915_error_ok(struct drm_i915_error_state_buf *e)
-{
-
-	if (!e->err && WARN(e->bytes > (e->size - 1), "overflow")) {
-		e->err = -ENOSPC;
-		return false;
-	}
-
-	if (e->bytes == e->size - 1 || e->err)
-		return false;
-
-	return true;
-}
-
-static bool __i915_error_seek(struct drm_i915_error_state_buf *e,
-			      unsigned len)
-{
-	if (e->pos + len <= e->start) {
-		e->pos += len;
-		return false;
-	}
-
-	/* First vsnprintf needs to fit in its entirety for memmove */
-	if (len >= e->size) {
-		e->err = -EIO;
-		return false;
-	}
-
-	return true;
-}
-
-static void __i915_error_advance(struct drm_i915_error_state_buf *e,
-				 unsigned len)
-{
-	/* If this is first printf in this window, adjust it so that
-	 * start position matches start of the buffer
-	 */
-
-	if (e->pos < e->start) {
-		const size_t off = e->start - e->pos;
-
-		/* Should not happen but be paranoid */
-		if (off > len || e->bytes) {
-			e->err = -EIO;
-			return;
-		}
-
-		memmove(e->buf, e->buf + off, len - off);
-		e->bytes = len - off;
-		e->pos = e->start;
-		return;
-	}
-
-	e->bytes += len;
-	e->pos += len;
-}
-
-static void i915_error_vprintf(struct drm_i915_error_state_buf *e,
-			       const char *f, va_list args)
-{
-	unsigned len;
-
-	if (!__i915_error_ok(e))
-		return;
-
-	/* Seek the first printf which is hits start position */
-	if (e->pos < e->start) {
-		len = vsnprintf(NULL, 0, f, args);
-		if (!__i915_error_seek(e, len))
-			return;
-	}
-
-	len = vsnprintf(e->buf + e->bytes, e->size - e->bytes, f, args);
-	if (len >= e->size - e->bytes)
-		len = e->size - e->bytes - 1;
-
-	__i915_error_advance(e, len);
-}
-
-static void i915_error_puts(struct drm_i915_error_state_buf *e,
-			    const char *str)
-{
-	unsigned len;
-
-	if (!__i915_error_ok(e))
-		return;
-
-	len = strlen(str);
-
-	/* Seek the first printf which is hits start position */
-	if (e->pos < e->start) {
-		if (!__i915_error_seek(e, len))
-			return;
-	}
-
-	if (len >= e->size - e->bytes)
-		len = e->size - e->bytes - 1;
-	memcpy(e->buf + e->bytes, str, len);
-
-	__i915_error_advance(e, len);
-}
-
-void i915_error_printf(struct drm_i915_error_state_buf *e, const char *f, ...)
-{
-	va_list args;
-
-	va_start(args, f);
-	i915_error_vprintf(e, f, args);
-	va_end(args);
-}
-
-#define err_printf(e, ...) i915_error_printf(e, __VA_ARGS__)
-#define err_puts(e, s) i915_error_puts(e, s)
-
-static void print_error_buffers(struct drm_i915_error_state_buf *m,
-				const char *name,
-				struct drm_i915_error_buffer *err,
-				int count)
-{
-	err_printf(m, "%s [%d]:\n", name, count);
-
-	while (count--) {
-		err_printf(m, "  %08x %8u %02x %02x %x %x",
-			   err->gtt_offset,
-			   err->size,
-			   err->read_domains,
-			   err->write_domain,
-			   err->rseqno, err->wseqno);
-		err_puts(m, pin_flag(err->pinned));
-		err_puts(m, tiling_flag(err->tiling));
-		err_puts(m, dirty_flag(err->dirty));
-		err_puts(m, purgeable_flag(err->purgeable));
-		err_puts(m, err->ring != -1 ? " " : "");
-		err_puts(m, ring_str(err->ring));
-		err_puts(m, cache_level_str(err->cache_level));
-
-		if (err->name)
-			err_printf(m, " (name: %d)", err->name);
-		if (err->fence_reg != I915_FENCE_REG_NONE)
-			err_printf(m, " (fence: %d)", err->fence_reg);
-
-		err_puts(m, "\n");
-		err++;
-	}
-}
-
-static void i915_ring_error_state(struct drm_i915_error_state_buf *m,
-				  struct drm_device *dev,
-				  struct drm_i915_error_state *error,
-				  unsigned ring)
-{
-	BUG_ON(ring >= I915_NUM_RINGS); /* shut up confused gcc */
-	err_printf(m, "%s command stream:\n", ring_str(ring));
-	err_printf(m, "  HEAD: 0x%08x\n", error->head[ring]);
-	err_printf(m, "  TAIL: 0x%08x\n", error->tail[ring]);
-	err_printf(m, "  CTL: 0x%08x\n", error->ctl[ring]);
-	err_printf(m, "  ACTHD: 0x%08x\n", error->acthd[ring]);
-	err_printf(m, "  IPEIR: 0x%08x\n", error->ipeir[ring]);
-	err_printf(m, "  IPEHR: 0x%08x\n", error->ipehr[ring]);
-	err_printf(m, "  INSTDONE: 0x%08x\n", error->instdone[ring]);
-	if (ring == RCS && INTEL_INFO(dev)->gen >= 4)
-		err_printf(m, "  BBADDR: 0x%08llx\n", error->bbaddr);
-
-	if (INTEL_INFO(dev)->gen >= 4)
-		err_printf(m, "  INSTPS: 0x%08x\n", error->instps[ring]);
-	err_printf(m, "  INSTPM: 0x%08x\n", error->instpm[ring]);
-	err_printf(m, "  FADDR: 0x%08x\n", error->faddr[ring]);
-	if (INTEL_INFO(dev)->gen >= 6) {
-		err_printf(m, "  RC PSMI: 0x%08x\n", error->rc_psmi[ring]);
-		err_printf(m, "  FAULT_REG: 0x%08x\n", error->fault_reg[ring]);
-		err_printf(m, "  SYNC_0: 0x%08x [last synced 0x%08x]\n",
-			   error->semaphore_mboxes[ring][0],
-			   error->semaphore_seqno[ring][0]);
-		err_printf(m, "  SYNC_1: 0x%08x [last synced 0x%08x]\n",
-			   error->semaphore_mboxes[ring][1],
-			   error->semaphore_seqno[ring][1]);
-	}
-	err_printf(m, "  seqno: 0x%08x\n", error->seqno[ring]);
-	err_printf(m, "  waiting: %s\n", yesno(error->waiting[ring]));
-	err_printf(m, "  ring->head: 0x%08x\n", error->cpu_ring_head[ring]);
-	err_printf(m, "  ring->tail: 0x%08x\n", error->cpu_ring_tail[ring]);
-}
-
-struct i915_error_state_file_priv {
-	struct drm_device *dev;
-	struct drm_i915_error_state *error;
-};
-
-
-static int i915_error_state(struct i915_error_state_file_priv *error_priv,
-			    struct drm_i915_error_state_buf *m)
-
-{
-	struct drm_device *dev = error_priv->dev;
-	drm_i915_private_t *dev_priv = dev->dev_private;
-	struct drm_i915_error_state *error = error_priv->error;
-	struct intel_ring_buffer *ring;
-	int i, j, page, offset, elt;
-
-	if (!error) {
-		err_printf(m, "no error state collected\n");
-		return 0;
-	}
-
-	err_printf(m, "Time: %ld s %ld us\n", error->time.tv_sec,
-		   error->time.tv_usec);
-	err_printf(m, "Kernel: " UTS_RELEASE "\n");
-	err_printf(m, "PCI ID: 0x%04x\n", dev->pci_device);
-	err_printf(m, "EIR: 0x%08x\n", error->eir);
-	err_printf(m, "IER: 0x%08x\n", error->ier);
-	err_printf(m, "PGTBL_ER: 0x%08x\n", error->pgtbl_er);
-	err_printf(m, "FORCEWAKE: 0x%08x\n", error->forcewake);
-	err_printf(m, "DERRMR: 0x%08x\n", error->derrmr);
-	err_printf(m, "CCID: 0x%08x\n", error->ccid);
-
-	for (i = 0; i < dev_priv->num_fence_regs; i++)
-		err_printf(m, "  fence[%d] = %08llx\n", i, error->fence[i]);
-
-	for (i = 0; i < ARRAY_SIZE(error->extra_instdone); i++)
-		err_printf(m, "  INSTDONE_%d: 0x%08x\n", i,
-			   error->extra_instdone[i]);
-
-	if (INTEL_INFO(dev)->gen >= 6) {
-		err_printf(m, "ERROR: 0x%08x\n", error->error);
-		err_printf(m, "DONE_REG: 0x%08x\n", error->done_reg);
-	}
-
-	if (INTEL_INFO(dev)->gen == 7)
-		err_printf(m, "ERR_INT: 0x%08x\n", error->err_int);
-
-	for_each_ring(ring, dev_priv, i)
-		i915_ring_error_state(m, dev, error, i);
-
-	if (error->active_bo)
-		print_error_buffers(m, "Active",
-				    error->active_bo,
-				    error->active_bo_count);
-
-	if (error->pinned_bo)
-		print_error_buffers(m, "Pinned",
-				    error->pinned_bo,
-				    error->pinned_bo_count);
-
-	for (i = 0; i < ARRAY_SIZE(error->ring); i++) {
-		struct drm_i915_error_object *obj;
-
-		if ((obj = error->ring[i].batchbuffer)) {
-			err_printf(m, "%s --- gtt_offset = 0x%08x\n",
-				   dev_priv->ring[i].name,
-				   obj->gtt_offset);
-			offset = 0;
-			for (page = 0; page < obj->page_count; page++) {
-				for (elt = 0; elt < PAGE_SIZE/4; elt++) {
-					err_printf(m, "%08x :  %08x\n", offset,
-						   obj->pages[page][elt]);
-					offset += 4;
-				}
-			}
-		}
-
-		if (error->ring[i].num_requests) {
-			err_printf(m, "%s --- %d requests\n",
-				   dev_priv->ring[i].name,
-				   error->ring[i].num_requests);
-			for (j = 0; j < error->ring[i].num_requests; j++) {
-				err_printf(m, "  seqno 0x%08x, emitted %ld, tail 0x%08x\n",
-					   error->ring[i].requests[j].seqno,
-					   error->ring[i].requests[j].jiffies,
-					   error->ring[i].requests[j].tail);
-			}
-		}
-
-		if ((obj = error->ring[i].ringbuffer)) {
-			err_printf(m, "%s --- ringbuffer = 0x%08x\n",
-				   dev_priv->ring[i].name,
-				   obj->gtt_offset);
-			offset = 0;
-			for (page = 0; page < obj->page_count; page++) {
-				for (elt = 0; elt < PAGE_SIZE/4; elt++) {
-					err_printf(m, "%08x :  %08x\n",
-						   offset,
-						   obj->pages[page][elt]);
-					offset += 4;
-				}
-			}
-		}
-
-		obj = error->ring[i].ctx;
-		if (obj) {
-			err_printf(m, "%s --- HW Context = 0x%08x\n",
-				   dev_priv->ring[i].name,
-				   obj->gtt_offset);
-			offset = 0;
-			for (elt = 0; elt < PAGE_SIZE/16; elt += 4) {
-				err_printf(m, "[%04x] %08x %08x %08x %08x\n",
-					   offset,
-					   obj->pages[0][elt],
-					   obj->pages[0][elt+1],
-					   obj->pages[0][elt+2],
-					   obj->pages[0][elt+3]);
-					offset += 16;
-			}
-		}
-	}
-
-	if (error->overlay)
-		intel_overlay_print_error_state(m, error->overlay);
-
-	if (error->display)
-		intel_display_print_error_state(m, dev, error->display);
-
-	return 0;
-}
-
 static ssize_t
 i915_error_state_write(struct file *filp,
 		       const char __user *ubuf,
@@ -986,9 +714,7 @@ i915_error_state_write(struct file *filp,
 static int i915_error_state_open(struct inode *inode, struct file *file)
 {
 	struct drm_device *dev = inode->i_private;
-	drm_i915_private_t *dev_priv = dev->dev_private;
 	struct i915_error_state_file_priv *error_priv;
-	unsigned long flags;
 
 	error_priv = kzalloc(sizeof(*error_priv), GFP_KERNEL);
 	if (!error_priv)
@@ -996,11 +722,7 @@ static int i915_error_state_open(struct inode *inode, struct file *file)
 
 	error_priv->dev = dev;
 
-	spin_lock_irqsave(&dev_priv->gpu_error.lock, flags);
-	error_priv->error = dev_priv->gpu_error.first_error;
-	if (error_priv->error)
-		kref_get(&error_priv->error->ref);
-	spin_unlock_irqrestore(&dev_priv->gpu_error.lock, flags);
+	i915_error_state_get(dev, error_priv);
 
 	file->private_data = error_priv;
 
@@ -1011,8 +733,7 @@ static int i915_error_state_release(struct inode *inode, struct file *file)
 {
 	struct i915_error_state_file_priv *error_priv = file->private_data;
 
-	if (error_priv->error)
-		kref_put(&error_priv->error->ref, i915_error_state_free);
+	i915_error_state_put(error_priv);
 	kfree(error_priv);
 
 	return 0;
@@ -1025,40 +746,15 @@ static ssize_t i915_error_state_read(struct file *file, char __user *userbuf,
 	struct drm_i915_error_state_buf error_str;
 	loff_t tmp_pos = 0;
 	ssize_t ret_count = 0;
-	int ret = 0;
-
-	memset(&error_str, 0, sizeof(error_str));
-
-	/* We need to have enough room to store any i915_error_state printf
-	 * so that we can move it to start position.
-	 */
-	error_str.size = count + 1 > PAGE_SIZE ? count + 1 : PAGE_SIZE;
-	error_str.buf = kmalloc(error_str.size,
-				GFP_TEMPORARY | __GFP_NORETRY | __GFP_NOWARN);
-
-	if (error_str.buf == NULL) {
-		error_str.size = PAGE_SIZE;
-		error_str.buf = kmalloc(error_str.size, GFP_TEMPORARY);
-	}
-
-	if (error_str.buf == NULL) {
-		error_str.size = 128;
-		error_str.buf = kmalloc(error_str.size, GFP_TEMPORARY);
-	}
-
-	if (error_str.buf == NULL)
-		return -ENOMEM;
-
-	error_str.start = *pos;
+	int ret;
 
-	ret = i915_error_state(error_priv, &error_str);
+	ret = i915_error_state_buf_init(&error_str, count, *pos);
 	if (ret)
-		goto out;
+		return ret;
 
-	if (error_str.bytes == 0 && error_str.err) {
-		ret = error_str.err;
+	ret = i915_error_state_to_str(&error_str, error_priv);
+	if (ret)
 		goto out;
-	}
 
 	ret_count = simple_read_from_buffer(userbuf, count, &tmp_pos,
 					    error_str.buf,
@@ -1069,7 +765,7 @@ static ssize_t i915_error_state_read(struct file *file, char __user *userbuf,
 	else
 		*pos = error_str.start + ret_count;
 out:
-	kfree(error_str.buf);
+	i915_error_state_buf_release(&error_str);
 	return ret ?: ret_count;
 }
 
@@ -1161,7 +857,7 @@ static int i915_cur_delayinfo(struct seq_file *m, void *unused)
 		u32 gt_perf_status = I915_READ(GEN6_GT_PERF_STATUS);
 		u32 rp_state_limits = I915_READ(GEN6_RP_STATE_LIMITS);
 		u32 rp_state_cap = I915_READ(GEN6_RP_STATE_CAP);
-		u32 rpstat, cagf;
+		u32 rpstat, cagf, reqf;
 		u32 rpupei, rpcurup, rpprevup;
 		u32 rpdownei, rpcurdown, rpprevdown;
 		int max_freq;
@@ -1173,6 +869,14 @@ static int i915_cur_delayinfo(struct seq_file *m, void *unused)
 
 		gen6_gt_force_wake_get(dev_priv);
 
+		reqf = I915_READ(GEN6_RPNSWREQ);
+		reqf &= ~GEN6_TURBO_DISABLE;
+		if (IS_HASWELL(dev))
+			reqf >>= 24;
+		else
+			reqf >>= 25;
+		reqf *= GT_FREQUENCY_MULTIPLIER;
+
 		rpstat = I915_READ(GEN6_RPSTAT1);
 		rpupei = I915_READ(GEN6_RP_CUR_UP_EI);
 		rpcurup = I915_READ(GEN6_RP_CUR_UP);
@@ -1197,6 +901,7 @@ static int i915_cur_delayinfo(struct seq_file *m, void *unused)
 			   gt_perf_status & 0xff);
 		seq_printf(m, "Render p-state limit: %d\n",
 			   rp_state_limits & 0xff);
+		seq_printf(m, "RPNSWREQ: %dMHz\n", reqf);
 		seq_printf(m, "CAGF: %dMHz\n", cagf);
 		seq_printf(m, "RP CUR UP EI: %dus\n", rpupei &
 			   GEN6_CURICONT_MASK);
@@ -1246,7 +951,7 @@ static int i915_cur_delayinfo(struct seq_file *m, void *unused)
 					(freq_sts >> 8) & 0xff));
 		mutex_unlock(&dev_priv->rps.hw_lock);
 	} else {
-		seq_printf(m, "no P-state info available\n");
+		seq_puts(m, "no P-state info available\n");
 	}
 
 	return 0;
@@ -1341,28 +1046,28 @@ static int ironlake_drpc_info(struct seq_file *m)
 	seq_printf(m, "RS2 VID: %d\n", ((crstandvid >> 8) & 0x3f));
 	seq_printf(m, "Render standby enabled: %s\n",
 		   (rstdbyctl & RCX_SW_EXIT) ? "no" : "yes");
-	seq_printf(m, "Current RS state: ");
+	seq_puts(m, "Current RS state: ");
 	switch (rstdbyctl & RSX_STATUS_MASK) {
 	case RSX_STATUS_ON:
-		seq_printf(m, "on\n");
+		seq_puts(m, "on\n");
 		break;
 	case RSX_STATUS_RC1:
-		seq_printf(m, "RC1\n");
+		seq_puts(m, "RC1\n");
 		break;
 	case RSX_STATUS_RC1E:
-		seq_printf(m, "RC1E\n");
+		seq_puts(m, "RC1E\n");
 		break;
 	case RSX_STATUS_RS1:
-		seq_printf(m, "RS1\n");
+		seq_puts(m, "RS1\n");
 		break;
 	case RSX_STATUS_RS2:
-		seq_printf(m, "RS2 (RC6)\n");
+		seq_puts(m, "RS2 (RC6)\n");
 		break;
 	case RSX_STATUS_RS3:
-		seq_printf(m, "RC3 (RC6+)\n");
+		seq_puts(m, "RC3 (RC6+)\n");
 		break;
 	default:
-		seq_printf(m, "unknown\n");
+		seq_puts(m, "unknown\n");
 		break;
 	}
 
@@ -1377,20 +1082,19 @@ static int gen6_drpc_info(struct seq_file *m)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	u32 rpmodectl1, gt_core_status, rcctl1, rc6vids = 0;
 	unsigned forcewake_count;
-	int count=0, ret;
-
+	int count = 0, ret;
 
 	ret = mutex_lock_interruptible(&dev->struct_mutex);
 	if (ret)
 		return ret;
 
-	spin_lock_irq(&dev_priv->gt_lock);
-	forcewake_count = dev_priv->forcewake_count;
-	spin_unlock_irq(&dev_priv->gt_lock);
+	spin_lock_irq(&dev_priv->uncore.lock);
+	forcewake_count = dev_priv->uncore.forcewake_count;
+	spin_unlock_irq(&dev_priv->uncore.lock);
 
 	if (forcewake_count) {
-		seq_printf(m, "RC information inaccurate because somebody "
-			      "holds a forcewake reference \n");
+		seq_puts(m, "RC information inaccurate because somebody "
+			    "holds a forcewake reference \n");
 	} else {
 		/* NB: we cannot use forcewake, else we read the wrong values */
 		while (count++ < 50 && (I915_READ_NOTRACE(FORCEWAKE_ACK) & 1))
@@ -1399,7 +1103,7 @@ static int gen6_drpc_info(struct seq_file *m)
 	}
 
 	gt_core_status = readl(dev_priv->regs + GEN6_GT_CORE_STATUS);
-	trace_i915_reg_rw(false, GEN6_GT_CORE_STATUS, gt_core_status, 4);
+	trace_i915_reg_rw(false, GEN6_GT_CORE_STATUS, gt_core_status, 4, true);
 
 	rpmodectl1 = I915_READ(GEN6_RP_CONTROL);
 	rcctl1 = I915_READ(GEN6_RC_CONTROL);
@@ -1423,25 +1127,25 @@ static int gen6_drpc_info(struct seq_file *m)
 		   yesno(rcctl1 & GEN6_RC_CTL_RC6p_ENABLE));
 	seq_printf(m, "Deepest RC6 Enabled: %s\n",
 		   yesno(rcctl1 & GEN6_RC_CTL_RC6pp_ENABLE));
-	seq_printf(m, "Current RC state: ");
+	seq_puts(m, "Current RC state: ");
 	switch (gt_core_status & GEN6_RCn_MASK) {
 	case GEN6_RC0:
 		if (gt_core_status & GEN6_CORE_CPD_STATE_MASK)
-			seq_printf(m, "Core Power Down\n");
+			seq_puts(m, "Core Power Down\n");
 		else
-			seq_printf(m, "on\n");
+			seq_puts(m, "on\n");
 		break;
 	case GEN6_RC3:
-		seq_printf(m, "RC3\n");
+		seq_puts(m, "RC3\n");
 		break;
 	case GEN6_RC6:
-		seq_printf(m, "RC6\n");
+		seq_puts(m, "RC6\n");
 		break;
 	case GEN6_RC7:
-		seq_printf(m, "RC7\n");
+		seq_puts(m, "RC7\n");
 		break;
 	default:
-		seq_printf(m, "Unknown\n");
+		seq_puts(m, "Unknown\n");
 		break;
 	}
 
@@ -1485,43 +1189,52 @@ static int i915_fbc_status(struct seq_file *m, void *unused)
 	drm_i915_private_t *dev_priv = dev->dev_private;
 
 	if (!I915_HAS_FBC(dev)) {
-		seq_printf(m, "FBC unsupported on this chipset\n");
+		seq_puts(m, "FBC unsupported on this chipset\n");
 		return 0;
 	}
 
 	if (intel_fbc_enabled(dev)) {
-		seq_printf(m, "FBC enabled\n");
+		seq_puts(m, "FBC enabled\n");
 	} else {
-		seq_printf(m, "FBC disabled: ");
-		switch (dev_priv->no_fbc_reason) {
+		seq_puts(m, "FBC disabled: ");
+		switch (dev_priv->fbc.no_fbc_reason) {
+		case FBC_OK:
+			seq_puts(m, "FBC actived, but currently disabled in hardware");
+			break;
+		case FBC_UNSUPPORTED:
+			seq_puts(m, "unsupported by this chipset");
+			break;
 		case FBC_NO_OUTPUT:
-			seq_printf(m, "no outputs");
+			seq_puts(m, "no outputs");
 			break;
 		case FBC_STOLEN_TOO_SMALL:
-			seq_printf(m, "not enough stolen memory");
+			seq_puts(m, "not enough stolen memory");
 			break;
 		case FBC_UNSUPPORTED_MODE:
-			seq_printf(m, "mode not supported");
+			seq_puts(m, "mode not supported");
 			break;
 		case FBC_MODE_TOO_LARGE:
-			seq_printf(m, "mode too large");
+			seq_puts(m, "mode too large");
 			break;
 		case FBC_BAD_PLANE:
-			seq_printf(m, "FBC unsupported on plane");
+			seq_puts(m, "FBC unsupported on plane");
 			break;
 		case FBC_NOT_TILED:
-			seq_printf(m, "scanout buffer not tiled");
+			seq_puts(m, "scanout buffer not tiled");
 			break;
 		case FBC_MULTIPLE_PIPES:
-			seq_printf(m, "multiple pipes are enabled");
+			seq_puts(m, "multiple pipes are enabled");
 			break;
 		case FBC_MODULE_PARAM:
-			seq_printf(m, "disabled per module param (default off)");
+			seq_puts(m, "disabled per module param (default off)");
+			break;
+		case FBC_CHIP_DEFAULT:
+			seq_puts(m, "disabled per chip default");
 			break;
 		default:
-			seq_printf(m, "unknown reason");
+			seq_puts(m, "unknown reason");
 		}
-		seq_printf(m, "\n");
+		seq_putc(m, '\n');
 	}
 	return 0;
 }
@@ -1604,7 +1317,7 @@ static int i915_ring_freq_table(struct seq_file *m, void *unused)
 	int gpu_freq, ia_freq;
 
 	if (!(IS_GEN6(dev) || IS_GEN7(dev))) {
-		seq_printf(m, "unsupported on this chipset\n");
+		seq_puts(m, "unsupported on this chipset\n");
 		return 0;
 	}
 
@@ -1612,7 +1325,7 @@ static int i915_ring_freq_table(struct seq_file *m, void *unused)
 	if (ret)
 		return ret;
 
-	seq_printf(m, "GPU freq (MHz)\tEffective CPU freq (MHz)\tEffective Ring freq (MHz)\n");
+	seq_puts(m, "GPU freq (MHz)\tEffective CPU freq (MHz)\tEffective Ring freq (MHz)\n");
 
 	for (gpu_freq = dev_priv->rps.min_delay;
 	     gpu_freq <= dev_priv->rps.max_delay;
@@ -1701,7 +1414,7 @@ static int i915_gem_framebuffer_info(struct seq_file *m, void *data)
 		   fb->base.bits_per_pixel,
 		   atomic_read(&fb->base.refcount.refcount));
 	describe_obj(m, fb->obj);
-	seq_printf(m, "\n");
+	seq_putc(m, '\n');
 	mutex_unlock(&dev->mode_config.mutex);
 
 	mutex_lock(&dev->mode_config.fb_lock);
@@ -1716,7 +1429,7 @@ static int i915_gem_framebuffer_info(struct seq_file *m, void *data)
 			   fb->base.bits_per_pixel,
 			   atomic_read(&fb->base.refcount.refcount));
 		describe_obj(m, fb->obj);
-		seq_printf(m, "\n");
+		seq_putc(m, '\n');
 	}
 	mutex_unlock(&dev->mode_config.fb_lock);
 
@@ -1736,22 +1449,22 @@ static int i915_context_status(struct seq_file *m, void *unused)
 		return ret;
 
 	if (dev_priv->ips.pwrctx) {
-		seq_printf(m, "power context ");
+		seq_puts(m, "power context ");
 		describe_obj(m, dev_priv->ips.pwrctx);
-		seq_printf(m, "\n");
+		seq_putc(m, '\n');
 	}
 
 	if (dev_priv->ips.renderctx) {
-		seq_printf(m, "render context ");
+		seq_puts(m, "render context ");
 		describe_obj(m, dev_priv->ips.renderctx);
-		seq_printf(m, "\n");
+		seq_putc(m, '\n');
 	}
 
 	for_each_ring(ring, dev_priv, i) {
 		if (ring->default_context) {
 			seq_printf(m, "HW default context %s ring ", ring->name);
 			describe_obj(m, ring->default_context->obj);
-			seq_printf(m, "\n");
+			seq_putc(m, '\n');
 		}
 	}
 
@@ -1767,9 +1480,9 @@ static int i915_gen6_forcewake_count_info(struct seq_file *m, void *data)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	unsigned forcewake_count;
 
-	spin_lock_irq(&dev_priv->gt_lock);
-	forcewake_count = dev_priv->forcewake_count;
-	spin_unlock_irq(&dev_priv->gt_lock);
+	spin_lock_irq(&dev_priv->uncore.lock);
+	forcewake_count = dev_priv->uncore.forcewake_count;
+	spin_unlock_irq(&dev_priv->uncore.lock);
 
 	seq_printf(m, "forcewake count = %u\n", forcewake_count);
 
@@ -1778,7 +1491,7 @@ static int i915_gen6_forcewake_count_info(struct seq_file *m, void *data)
 
 static const char *swizzle_string(unsigned swizzle)
 {
-	switch(swizzle) {
+	switch (swizzle) {
 	case I915_BIT_6_SWIZZLE_NONE:
 		return "none";
 	case I915_BIT_6_SWIZZLE_9:
@@ -1868,7 +1581,7 @@ static int i915_ppgtt_info(struct seq_file *m, void *data)
 	if (dev_priv->mm.aliasing_ppgtt) {
 		struct i915_hw_ppgtt *ppgtt = dev_priv->mm.aliasing_ppgtt;
 
-		seq_printf(m, "aliasing PPGTT:\n");
+		seq_puts(m, "aliasing PPGTT:\n");
 		seq_printf(m, "pd gtt offset: 0x%08x\n", ppgtt->pd_offset);
 	}
 	seq_printf(m, "ECOCHK: 0x%08x\n", I915_READ(GAM_ECOCHK));
@@ -1886,7 +1599,7 @@ static int i915_dpio_info(struct seq_file *m, void *data)
 
 
 	if (!IS_VALLEYVIEW(dev)) {
-		seq_printf(m, "unsupported\n");
+		seq_puts(m, "unsupported\n");
 		return 0;
 	}
 
@@ -1924,6 +1637,194 @@ static int i915_dpio_info(struct seq_file *m, void *data)
 	return 0;
 }
 
+static int i915_llc(struct seq_file *m, void *data)
+{
+	struct drm_info_node *node = (struct drm_info_node *) m->private;
+	struct drm_device *dev = node->minor->dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	/* Size calculation for LLC is a bit of a pain. Ignore for now. */
+	seq_printf(m, "LLC: %s\n", yesno(HAS_LLC(dev)));
+	seq_printf(m, "eLLC: %zuMB\n", dev_priv->ellc_size);
+
+	return 0;
+}
+
+static int i915_edp_psr_status(struct seq_file *m, void *data)
+{
+	struct drm_info_node *node = m->private;
+	struct drm_device *dev = node->minor->dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	u32 psrstat, psrperf;
+
+	if (!IS_HASWELL(dev)) {
+		seq_puts(m, "PSR not supported on this platform\n");
+	} else if (IS_HASWELL(dev) && I915_READ(EDP_PSR_CTL) & EDP_PSR_ENABLE) {
+		seq_puts(m, "PSR enabled\n");
+	} else {
+		seq_puts(m, "PSR disabled: ");
+		switch (dev_priv->no_psr_reason) {
+		case PSR_NO_SOURCE:
+			seq_puts(m, "not supported on this platform");
+			break;
+		case PSR_NO_SINK:
+			seq_puts(m, "not supported by panel");
+			break;
+		case PSR_MODULE_PARAM:
+			seq_puts(m, "disabled by flag");
+			break;
+		case PSR_CRTC_NOT_ACTIVE:
+			seq_puts(m, "crtc not active");
+			break;
+		case PSR_PWR_WELL_ENABLED:
+			seq_puts(m, "power well enabled");
+			break;
+		case PSR_NOT_TILED:
+			seq_puts(m, "not tiled");
+			break;
+		case PSR_SPRITE_ENABLED:
+			seq_puts(m, "sprite enabled");
+			break;
+		case PSR_S3D_ENABLED:
+			seq_puts(m, "stereo 3d enabled");
+			break;
+		case PSR_INTERLACED_ENABLED:
+			seq_puts(m, "interlaced enabled");
+			break;
+		case PSR_HSW_NOT_DDIA:
+			seq_puts(m, "HSW ties PSR to DDI A (eDP)");
+			break;
+		default:
+			seq_puts(m, "unknown reason");
+		}
+		seq_puts(m, "\n");
+		return 0;
+	}
+
+	psrstat = I915_READ(EDP_PSR_STATUS_CTL);
+
+	seq_puts(m, "PSR Current State: ");
+	switch (psrstat & EDP_PSR_STATUS_STATE_MASK) {
+	case EDP_PSR_STATUS_STATE_IDLE:
+		seq_puts(m, "Reset state\n");
+		break;
+	case EDP_PSR_STATUS_STATE_SRDONACK:
+		seq_puts(m, "Wait for TG/Stream to send on frame of data after SRD conditions are met\n");
+		break;
+	case EDP_PSR_STATUS_STATE_SRDENT:
+		seq_puts(m, "SRD entry\n");
+		break;
+	case EDP_PSR_STATUS_STATE_BUFOFF:
+		seq_puts(m, "Wait for buffer turn off\n");
+		break;
+	case EDP_PSR_STATUS_STATE_BUFON:
+		seq_puts(m, "Wait for buffer turn on\n");
+		break;
+	case EDP_PSR_STATUS_STATE_AUXACK:
+		seq_puts(m, "Wait for AUX to acknowledge on SRD exit\n");
+		break;
+	case EDP_PSR_STATUS_STATE_SRDOFFACK:
+		seq_puts(m, "Wait for TG/Stream to acknowledge the SRD VDM exit\n");
+		break;
+	default:
+		seq_puts(m, "Unknown\n");
+		break;
+	}
+
+	seq_puts(m, "Link Status: ");
+	switch (psrstat & EDP_PSR_STATUS_LINK_MASK) {
+	case EDP_PSR_STATUS_LINK_FULL_OFF:
+		seq_puts(m, "Link is fully off\n");
+		break;
+	case EDP_PSR_STATUS_LINK_FULL_ON:
+		seq_puts(m, "Link is fully on\n");
+		break;
+	case EDP_PSR_STATUS_LINK_STANDBY:
+		seq_puts(m, "Link is in standby\n");
+		break;
+	default:
+		seq_puts(m, "Unknown\n");
+		break;
+	}
+
+	seq_printf(m, "PSR Entry Count: %u\n",
+		   psrstat >> EDP_PSR_STATUS_COUNT_SHIFT &
+		   EDP_PSR_STATUS_COUNT_MASK);
+
+	seq_printf(m, "Max Sleep Timer Counter: %u\n",
+		   psrstat >> EDP_PSR_STATUS_MAX_SLEEP_TIMER_SHIFT &
+		   EDP_PSR_STATUS_MAX_SLEEP_TIMER_MASK);
+
+	seq_printf(m, "Had AUX error: %s\n",
+		   yesno(psrstat & EDP_PSR_STATUS_AUX_ERROR));
+
+	seq_printf(m, "Sending AUX: %s\n",
+		   yesno(psrstat & EDP_PSR_STATUS_AUX_SENDING));
+
+	seq_printf(m, "Sending Idle: %s\n",
+		   yesno(psrstat & EDP_PSR_STATUS_SENDING_IDLE));
+
+	seq_printf(m, "Sending TP2 TP3: %s\n",
+		   yesno(psrstat & EDP_PSR_STATUS_SENDING_TP2_TP3));
+
+	seq_printf(m, "Sending TP1: %s\n",
+		   yesno(psrstat & EDP_PSR_STATUS_SENDING_TP1));
+
+	seq_printf(m, "Idle Count: %u\n",
+		   psrstat & EDP_PSR_STATUS_IDLE_MASK);
+
+	psrperf = (I915_READ(EDP_PSR_PERF_CNT)) & EDP_PSR_PERF_CNT_MASK;
+	seq_printf(m, "Performance Counter: %u\n", psrperf);
+
+	return 0;
+}
+
+static int i915_energy_uJ(struct seq_file *m, void *data)
+{
+	struct drm_info_node *node = m->private;
+	struct drm_device *dev = node->minor->dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	u64 power;
+	u32 units;
+
+	if (INTEL_INFO(dev)->gen < 6)
+		return -ENODEV;
+
+	rdmsrl(MSR_RAPL_POWER_UNIT, power);
+	power = (power & 0x1f00) >> 8;
+	units = 1000000 / (1 << power); /* convert to uJ */
+	power = I915_READ(MCH_SECP_NRG_STTS);
+	power *= units;
+
+	seq_printf(m, "%llu", (long long unsigned)power);
+
+	return 0;
+}
+
+static int i915_pc8_status(struct seq_file *m, void *unused)
+{
+	struct drm_info_node *node = (struct drm_info_node *) m->private;
+	struct drm_device *dev = node->minor->dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	if (!IS_HASWELL(dev)) {
+		seq_puts(m, "not supported\n");
+		return 0;
+	}
+
+	mutex_lock(&dev_priv->pc8.lock);
+	seq_printf(m, "Requirements met: %s\n",
+		   yesno(dev_priv->pc8.requirements_met));
+	seq_printf(m, "GPU idle: %s\n", yesno(dev_priv->pc8.gpu_idle));
+	seq_printf(m, "Disable count: %d\n", dev_priv->pc8.disable_count);
+	seq_printf(m, "IRQs disabled: %s\n",
+		   yesno(dev_priv->pc8.irqs_disabled));
+	seq_printf(m, "Enabled: %s\n", yesno(dev_priv->pc8.enabled));
+	mutex_unlock(&dev_priv->pc8.lock);
+
+	return 0;
+}
+
 static int
 i915_wedged_get(void *data, u64 *val)
 {
@@ -2006,6 +1907,8 @@ i915_drop_caches_set(void *data, u64 val)
 	struct drm_device *dev = data;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_i915_gem_object *obj, *next;
+	struct i915_address_space *vm;
+	struct i915_vma *vma, *x;
 	int ret;
 
 	DRM_DEBUG_DRIVER("Dropping caches: 0x%08llx\n", val);
@@ -2026,12 +1929,17 @@ i915_drop_caches_set(void *data, u64 val)
 		i915_gem_retire_requests(dev);
 
 	if (val & DROP_BOUND) {
-		list_for_each_entry_safe(obj, next, &dev_priv->mm.inactive_list, mm_list)
-			if (obj->pin_count == 0) {
-				ret = i915_gem_object_unbind(obj);
+		list_for_each_entry(vm, &dev_priv->vm_list, global_link) {
+			list_for_each_entry_safe(vma, x, &vm->inactive_list,
+						 mm_list) {
+				if (vma->obj->pin_count)
+					continue;
+
+				ret = i915_vma_unbind(vma);
 				if (ret)
 					goto unlock;
 			}
+		}
 	}
 
 	if (val & DROP_UNBOUND) {
@@ -2326,6 +2234,7 @@ static struct drm_info_list i915_debugfs_list[] = {
 	{"i915_gem_pinned", i915_gem_gtt_info, 0, (void *) PINNED_LIST},
 	{"i915_gem_active", i915_gem_object_list_info, 0, (void *) ACTIVE_LIST},
 	{"i915_gem_inactive", i915_gem_object_list_info, 0, (void *) INACTIVE_LIST},
+	{"i915_gem_stolen", i915_gem_stolen_list_info },
 	{"i915_gem_pageflip", i915_gem_pageflip_info, 0},
 	{"i915_gem_request", i915_gem_request_info, 0},
 	{"i915_gem_seqno", i915_gem_seqno_info, 0},
@@ -2353,64 +2262,42 @@ static struct drm_info_list i915_debugfs_list[] = {
 	{"i915_swizzle_info", i915_swizzle_info, 0},
 	{"i915_ppgtt_info", i915_ppgtt_info, 0},
 	{"i915_dpio", i915_dpio_info, 0},
+	{"i915_llc", i915_llc, 0},
+	{"i915_edp_psr_status", i915_edp_psr_status, 0},
+	{"i915_energy_uJ", i915_energy_uJ, 0},
+	{"i915_pc8_status", i915_pc8_status, 0},
 };
 #define I915_DEBUGFS_ENTRIES ARRAY_SIZE(i915_debugfs_list)
 
+static struct i915_debugfs_files {
+	const char *name;
+	const struct file_operations *fops;
+} i915_debugfs_files[] = {
+	{"i915_wedged", &i915_wedged_fops},
+	{"i915_max_freq", &i915_max_freq_fops},
+	{"i915_min_freq", &i915_min_freq_fops},
+	{"i915_cache_sharing", &i915_cache_sharing_fops},
+	{"i915_ring_stop", &i915_ring_stop_fops},
+	{"i915_gem_drop_caches", &i915_drop_caches_fops},
+	{"i915_error_state", &i915_error_state_fops},
+	{"i915_next_seqno", &i915_next_seqno_fops},
+};
+
 int i915_debugfs_init(struct drm_minor *minor)
 {
-	int ret;
-
-	ret = i915_debugfs_create(minor->debugfs_root, minor,
-				  "i915_wedged",
-				  &i915_wedged_fops);
-	if (ret)
-		return ret;
+	int ret, i;
 
 	ret = i915_forcewake_create(minor->debugfs_root, minor);
 	if (ret)
 		return ret;
 
-	ret = i915_debugfs_create(minor->debugfs_root, minor,
-				  "i915_max_freq",
-				  &i915_max_freq_fops);
-	if (ret)
-		return ret;
-
-	ret = i915_debugfs_create(minor->debugfs_root, minor,
-				  "i915_min_freq",
-				  &i915_min_freq_fops);
-	if (ret)
-		return ret;
-
-	ret = i915_debugfs_create(minor->debugfs_root, minor,
-				  "i915_cache_sharing",
-				  &i915_cache_sharing_fops);
-	if (ret)
-		return ret;
-
-	ret = i915_debugfs_create(minor->debugfs_root, minor,
-				  "i915_ring_stop",
-				  &i915_ring_stop_fops);
-	if (ret)
-		return ret;
-
-	ret = i915_debugfs_create(minor->debugfs_root, minor,
-				  "i915_gem_drop_caches",
-				  &i915_drop_caches_fops);
-	if (ret)
-		return ret;
-
-	ret = i915_debugfs_create(minor->debugfs_root, minor,
-				  "i915_error_state",
-				  &i915_error_state_fops);
-	if (ret)
-		return ret;
-
-	ret = i915_debugfs_create(minor->debugfs_root, minor,
-				 "i915_next_seqno",
-				 &i915_next_seqno_fops);
-	if (ret)
-		return ret;
+	for (i = 0; i < ARRAY_SIZE(i915_debugfs_files); i++) {
+		ret = i915_debugfs_create(minor->debugfs_root, minor,
+					  i915_debugfs_files[i].name,
+					  i915_debugfs_files[i].fops);
+		if (ret)
+			return ret;
+	}
 
 	return drm_debugfs_create_files(i915_debugfs_list,
 					I915_DEBUGFS_ENTRIES,
@@ -2419,26 +2306,18 @@ int i915_debugfs_init(struct drm_minor *minor)
 
 void i915_debugfs_cleanup(struct drm_minor *minor)
 {
+	int i;
+
 	drm_debugfs_remove_files(i915_debugfs_list,
 				 I915_DEBUGFS_ENTRIES, minor);
 	drm_debugfs_remove_files((struct drm_info_list *) &i915_forcewake_fops,
 				 1, minor);
-	drm_debugfs_remove_files((struct drm_info_list *) &i915_wedged_fops,
-				 1, minor);
-	drm_debugfs_remove_files((struct drm_info_list *) &i915_max_freq_fops,
-				 1, minor);
-	drm_debugfs_remove_files((struct drm_info_list *) &i915_min_freq_fops,
-				 1, minor);
-	drm_debugfs_remove_files((struct drm_info_list *) &i915_cache_sharing_fops,
-				 1, minor);
-	drm_debugfs_remove_files((struct drm_info_list *) &i915_drop_caches_fops,
-				 1, minor);
-	drm_debugfs_remove_files((struct drm_info_list *) &i915_ring_stop_fops,
-				 1, minor);
-	drm_debugfs_remove_files((struct drm_info_list *) &i915_error_state_fops,
-				 1, minor);
-	drm_debugfs_remove_files((struct drm_info_list *) &i915_next_seqno_fops,
-				 1, minor);
+	for (i = 0; i < ARRAY_SIZE(i915_debugfs_files); i++) {
+		struct drm_info_list *info_list =
+			(struct drm_info_list *) i915_debugfs_files[i].fops;
+
+		drm_debugfs_remove_files(info_list, 1, minor);
+	}
 }
 
 #endif /* CONFIG_DEBUG_FS */
diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c
index f4669802a0fb..d5c784d48671 100644
--- a/drivers/gpu/drm/i915/i915_dma.c
+++ b/drivers/gpu/drm/i915/i915_dma.c
@@ -976,6 +976,9 @@ static int i915_getparam(struct drm_device *dev, void *data,
 	case I915_PARAM_HAS_LLC:
 		value = HAS_LLC(dev);
 		break;
+	case I915_PARAM_HAS_WT:
+		value = HAS_WT(dev);
+		break;
 	case I915_PARAM_HAS_ALIASING_PPGTT:
 		value = dev_priv->mm.aliasing_ppgtt ? 1 : 0;
 		break;
@@ -1293,7 +1296,7 @@ static int i915_load_modeset_init(struct drm_device *dev)
 
 	intel_register_dsm_handler();
 
-	ret = vga_switcheroo_register_client(dev->pdev, &i915_switcheroo_ops);
+	ret = vga_switcheroo_register_client(dev->pdev, &i915_switcheroo_ops, false);
 	if (ret)
 		goto cleanup_vga_client;
 
@@ -1323,10 +1326,8 @@ static int i915_load_modeset_init(struct drm_device *dev)
 	/* Always safe in the mode setting case. */
 	/* FIXME: do pre/post-mode set stuff in core KMS code */
 	dev->vblank_disable_allowed = 1;
-	if (INTEL_INFO(dev)->num_pipes == 0) {
-		dev_priv->mm.suspended = 0;
+	if (INTEL_INFO(dev)->num_pipes == 0)
 		return 0;
-	}
 
 	ret = intel_fbdev_init(dev);
 	if (ret)
@@ -1352,9 +1353,6 @@ static int i915_load_modeset_init(struct drm_device *dev)
 
 	drm_kms_helper_poll_init(dev);
 
-	/* We're off and running w/KMS */
-	dev_priv->mm.suspended = 0;
-
 	return 0;
 
 cleanup_gem:
@@ -1363,7 +1361,7 @@ cleanup_gem:
 	i915_gem_context_fini(dev);
 	mutex_unlock(&dev->struct_mutex);
 	i915_gem_cleanup_aliasing_ppgtt(dev);
-	drm_mm_takedown(&dev_priv->mm.gtt_space);
+	drm_mm_takedown(&dev_priv->gtt.base.mm);
 cleanup_irq:
 	drm_irq_uninstall(dev);
 cleanup_gem_stolen:
@@ -1441,22 +1439,6 @@ static void i915_dump_device_info(struct drm_i915_private *dev_priv)
 }
 
 /**
- * intel_early_sanitize_regs - clean up BIOS state
- * @dev: DRM device
- *
- * This function must be called before we do any I915_READ or I915_WRITE. Its
- * purpose is to clean up any state left by the BIOS that may affect us when
- * reading and/or writing registers.
- */
-static void intel_early_sanitize_regs(struct drm_device *dev)
-{
-	struct drm_i915_private *dev_priv = dev->dev_private;
-
-	if (HAS_FPGA_DBG_UNCLAIMED(dev))
-		I915_WRITE_NOTRACE(FPGA_DBG, FPGA_DBG_RM_NOCLAIM);
-}
-
-/**
  * i915_driver_load - setup chip and create an initial config
  * @dev: DRM device
  * @flags: startup flags
@@ -1497,15 +1479,31 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags)
 
 	spin_lock_init(&dev_priv->irq_lock);
 	spin_lock_init(&dev_priv->gpu_error.lock);
-	spin_lock_init(&dev_priv->rps.lock);
-	spin_lock_init(&dev_priv->gt_lock);
 	spin_lock_init(&dev_priv->backlight.lock);
+	spin_lock_init(&dev_priv->uncore.lock);
+	spin_lock_init(&dev_priv->mm.object_stat_lock);
 	mutex_init(&dev_priv->dpio_lock);
 	mutex_init(&dev_priv->rps.hw_lock);
 	mutex_init(&dev_priv->modeset_restore_lock);
 
+	mutex_init(&dev_priv->pc8.lock);
+	dev_priv->pc8.requirements_met = false;
+	dev_priv->pc8.gpu_idle = false;
+	dev_priv->pc8.irqs_disabled = false;
+	dev_priv->pc8.enabled = false;
+	dev_priv->pc8.disable_count = 2; /* requirements_met + gpu_idle */
+	INIT_DELAYED_WORK(&dev_priv->pc8.enable_work, hsw_enable_pc8_work);
+
 	i915_dump_device_info(dev_priv);
 
+	/* Not all pre-production machines fall into this category, only the
+	 * very first ones. Almost everything should work, except for maybe
+	 * suspend/resume. And we don't implement workarounds that affect only
+	 * pre-production machines. */
+	if (IS_HSW_EARLY_SDV(dev))
+		DRM_INFO("This is an early pre-production Haswell machine. "
+			 "It may not be fully functional.\n");
+
 	if (i915_get_bridge_dev(dev)) {
 		ret = -EIO;
 		goto free_priv;
@@ -1531,7 +1529,17 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags)
 		goto put_bridge;
 	}
 
-	intel_early_sanitize_regs(dev);
+	intel_uncore_early_sanitize(dev);
+
+	if (IS_HASWELL(dev) && (I915_READ(HSW_EDRAM_PRESENT) == 1)) {
+		/* The docs do not explain exactly how the calculation can be
+		 * made. It is somewhat guessable, but for now, it's always
+		 * 128MB.
+		 * NB: We can't write IDICR yet because we do not have gt funcs
+		 * set up */
+		dev_priv->ellc_size = 128;
+		DRM_INFO("Found %zuMB of eLLC\n", dev_priv->ellc_size);
+	}
 
 	ret = i915_gem_gtt_init(dev);
 	if (ret)
@@ -1567,8 +1575,8 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags)
 		goto out_rmmap;
 	}
 
-	dev_priv->mm.gtt_mtrr = arch_phys_wc_add(dev_priv->gtt.mappable_base,
-						 aperture_size);
+	dev_priv->gtt.mtrr = arch_phys_wc_add(dev_priv->gtt.mappable_base,
+					      aperture_size);
 
 	/* The i915 workqueue is primarily used for batched retirement of
 	 * requests (and thus managing bo) once the task has been completed
@@ -1595,8 +1603,8 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags)
 
 	intel_irq_init(dev);
 	intel_pm_init(dev);
-	intel_gt_sanitize(dev);
-	intel_gt_init(dev);
+	intel_uncore_sanitize(dev);
+	intel_uncore_init(dev);
 
 	/* Try to make sure MCHBAR is enabled before poking at it */
 	intel_setup_mchbar(dev);
@@ -1631,9 +1639,6 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags)
 			goto out_gem_unload;
 	}
 
-	/* Start out suspended */
-	dev_priv->mm.suspended = 1;
-
 	if (HAS_POWER_WELL(dev))
 		i915_init_power_well(dev);
 
@@ -1643,6 +1648,9 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags)
 			DRM_ERROR("failed to init modeset\n");
 			goto out_gem_unload;
 		}
+	} else {
+		/* Start out suspended in ums mode. */
+		dev_priv->ums.mm_suspended = 1;
 	}
 
 	i915_setup_sysfs(dev);
@@ -1659,7 +1667,7 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags)
 	return 0;
 
 out_gem_unload:
-	if (dev_priv->mm.inactive_shrinker.shrink)
+	if (dev_priv->mm.inactive_shrinker.scan_objects)
 		unregister_shrinker(&dev_priv->mm.inactive_shrinker);
 
 	if (dev->pdev->msi_enabled)
@@ -1669,9 +1677,9 @@ out_gem_unload:
 	intel_teardown_mchbar(dev);
 	destroy_workqueue(dev_priv->wq);
 out_mtrrfree:
-	arch_phys_wc_del(dev_priv->mm.gtt_mtrr);
+	arch_phys_wc_del(dev_priv->gtt.mtrr);
 	io_mapping_free(dev_priv->gtt.mappable);
-	dev_priv->gtt.gtt_remove(dev);
+	dev_priv->gtt.base.cleanup(&dev_priv->gtt.base);
 out_rmmap:
 	pci_iounmap(dev->pdev, dev_priv->regs);
 put_bridge:
@@ -1688,12 +1696,17 @@ int i915_driver_unload(struct drm_device *dev)
 
 	intel_gpu_ips_teardown();
 
-	if (HAS_POWER_WELL(dev))
+	if (HAS_POWER_WELL(dev)) {
+		/* The i915.ko module is still not prepared to be loaded when
+		 * the power well is not enabled, so just enable it in case
+		 * we're going to unload/reload. */
+		intel_set_power_well(dev, true);
 		i915_remove_power_well(dev);
+	}
 
 	i915_teardown_sysfs(dev);
 
-	if (dev_priv->mm.inactive_shrinker.shrink)
+	if (dev_priv->mm.inactive_shrinker.scan_objects)
 		unregister_shrinker(&dev_priv->mm.inactive_shrinker);
 
 	mutex_lock(&dev->struct_mutex);
@@ -1707,7 +1720,7 @@ int i915_driver_unload(struct drm_device *dev)
 	cancel_delayed_work_sync(&dev_priv->mm.retire_work);
 
 	io_mapping_free(dev_priv->gtt.mappable);
-	arch_phys_wc_del(dev_priv->mm.gtt_mtrr);
+	arch_phys_wc_del(dev_priv->gtt.mtrr);
 
 	acpi_video_unregister();
 
@@ -1735,6 +1748,8 @@ int i915_driver_unload(struct drm_device *dev)
 	cancel_work_sync(&dev_priv->gpu_error.work);
 	i915_destroy_error_state(dev);
 
+	cancel_delayed_work_sync(&dev_priv->pc8.enable_work);
+
 	if (dev->pdev->msi_enabled)
 		pci_disable_msi(dev->pdev);
 
@@ -1756,7 +1771,9 @@ int i915_driver_unload(struct drm_device *dev)
 			i915_free_hws(dev);
 	}
 
-	drm_mm_takedown(&dev_priv->mm.gtt_space);
+	list_del(&dev_priv->gtt.base.global_link);
+	WARN_ON(!list_empty(&dev_priv->vm_list));
+	drm_mm_takedown(&dev_priv->gtt.base.mm);
 	if (dev_priv->regs != NULL)
 		pci_iounmap(dev->pdev, dev_priv->regs);
 
@@ -1766,7 +1783,7 @@ int i915_driver_unload(struct drm_device *dev)
 	destroy_workqueue(dev_priv->wq);
 	pm_qos_remove_request(&dev_priv->pm_qos);
 
-	dev_priv->gtt.gtt_remove(dev);
+	dev_priv->gtt.base.cleanup(&dev_priv->gtt.base);
 
 	if (dev_priv->slab)
 		kmem_cache_destroy(dev_priv->slab);
@@ -1842,14 +1859,14 @@ void i915_driver_postclose(struct drm_device *dev, struct drm_file *file)
 	kfree(file_priv);
 }
 
-struct drm_ioctl_desc i915_ioctls[] = {
+const struct drm_ioctl_desc i915_ioctls[] = {
 	DRM_IOCTL_DEF_DRV(I915_INIT, i915_dma_init, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
 	DRM_IOCTL_DEF_DRV(I915_FLUSH, i915_flush_ioctl, DRM_AUTH),
 	DRM_IOCTL_DEF_DRV(I915_FLIP, i915_flip_bufs, DRM_AUTH),
 	DRM_IOCTL_DEF_DRV(I915_BATCHBUFFER, i915_batchbuffer, DRM_AUTH),
 	DRM_IOCTL_DEF_DRV(I915_IRQ_EMIT, i915_irq_emit, DRM_AUTH),
 	DRM_IOCTL_DEF_DRV(I915_IRQ_WAIT, i915_irq_wait, DRM_AUTH),
-	DRM_IOCTL_DEF_DRV(I915_GETPARAM, i915_getparam, DRM_AUTH),
+	DRM_IOCTL_DEF_DRV(I915_GETPARAM, i915_getparam, DRM_AUTH|DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(I915_SETPARAM, i915_setparam, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
 	DRM_IOCTL_DEF_DRV(I915_ALLOC, drm_noop, DRM_AUTH),
 	DRM_IOCTL_DEF_DRV(I915_FREE, drm_noop, DRM_AUTH),
@@ -1862,35 +1879,35 @@ struct drm_ioctl_desc i915_ioctls[] = {
 	DRM_IOCTL_DEF_DRV(I915_HWS_ADDR, i915_set_status_page, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
 	DRM_IOCTL_DEF_DRV(I915_GEM_INIT, i915_gem_init_ioctl, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY|DRM_UNLOCKED),
 	DRM_IOCTL_DEF_DRV(I915_GEM_EXECBUFFER, i915_gem_execbuffer, DRM_AUTH|DRM_UNLOCKED),
-	DRM_IOCTL_DEF_DRV(I915_GEM_EXECBUFFER2, i915_gem_execbuffer2, DRM_AUTH|DRM_UNLOCKED),
+	DRM_IOCTL_DEF_DRV(I915_GEM_EXECBUFFER2, i915_gem_execbuffer2, DRM_AUTH|DRM_UNLOCKED|DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(I915_GEM_PIN, i915_gem_pin_ioctl, DRM_AUTH|DRM_ROOT_ONLY|DRM_UNLOCKED),
 	DRM_IOCTL_DEF_DRV(I915_GEM_UNPIN, i915_gem_unpin_ioctl, DRM_AUTH|DRM_ROOT_ONLY|DRM_UNLOCKED),
-	DRM_IOCTL_DEF_DRV(I915_GEM_BUSY, i915_gem_busy_ioctl, DRM_AUTH|DRM_UNLOCKED),
-	DRM_IOCTL_DEF_DRV(I915_GEM_SET_CACHING, i915_gem_set_caching_ioctl, DRM_UNLOCKED),
-	DRM_IOCTL_DEF_DRV(I915_GEM_GET_CACHING, i915_gem_get_caching_ioctl, DRM_UNLOCKED),
-	DRM_IOCTL_DEF_DRV(I915_GEM_THROTTLE, i915_gem_throttle_ioctl, DRM_AUTH|DRM_UNLOCKED),
+	DRM_IOCTL_DEF_DRV(I915_GEM_BUSY, i915_gem_busy_ioctl, DRM_AUTH|DRM_UNLOCKED|DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(I915_GEM_SET_CACHING, i915_gem_set_caching_ioctl, DRM_UNLOCKED|DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(I915_GEM_GET_CACHING, i915_gem_get_caching_ioctl, DRM_UNLOCKED|DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(I915_GEM_THROTTLE, i915_gem_throttle_ioctl, DRM_AUTH|DRM_UNLOCKED|DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(I915_GEM_ENTERVT, i915_gem_entervt_ioctl, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY|DRM_UNLOCKED),
 	DRM_IOCTL_DEF_DRV(I915_GEM_LEAVEVT, i915_gem_leavevt_ioctl, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY|DRM_UNLOCKED),
-	DRM_IOCTL_DEF_DRV(I915_GEM_CREATE, i915_gem_create_ioctl, DRM_UNLOCKED),
-	DRM_IOCTL_DEF_DRV(I915_GEM_PREAD, i915_gem_pread_ioctl, DRM_UNLOCKED),
-	DRM_IOCTL_DEF_DRV(I915_GEM_PWRITE, i915_gem_pwrite_ioctl, DRM_UNLOCKED),
-	DRM_IOCTL_DEF_DRV(I915_GEM_MMAP, i915_gem_mmap_ioctl, DRM_UNLOCKED),
-	DRM_IOCTL_DEF_DRV(I915_GEM_MMAP_GTT, i915_gem_mmap_gtt_ioctl, DRM_UNLOCKED),
-	DRM_IOCTL_DEF_DRV(I915_GEM_SET_DOMAIN, i915_gem_set_domain_ioctl, DRM_UNLOCKED),
-	DRM_IOCTL_DEF_DRV(I915_GEM_SW_FINISH, i915_gem_sw_finish_ioctl, DRM_UNLOCKED),
-	DRM_IOCTL_DEF_DRV(I915_GEM_SET_TILING, i915_gem_set_tiling, DRM_UNLOCKED),
-	DRM_IOCTL_DEF_DRV(I915_GEM_GET_TILING, i915_gem_get_tiling, DRM_UNLOCKED),
-	DRM_IOCTL_DEF_DRV(I915_GEM_GET_APERTURE, i915_gem_get_aperture_ioctl, DRM_UNLOCKED),
+	DRM_IOCTL_DEF_DRV(I915_GEM_CREATE, i915_gem_create_ioctl, DRM_UNLOCKED|DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(I915_GEM_PREAD, i915_gem_pread_ioctl, DRM_UNLOCKED|DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(I915_GEM_PWRITE, i915_gem_pwrite_ioctl, DRM_UNLOCKED|DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(I915_GEM_MMAP, i915_gem_mmap_ioctl, DRM_UNLOCKED|DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(I915_GEM_MMAP_GTT, i915_gem_mmap_gtt_ioctl, DRM_UNLOCKED|DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(I915_GEM_SET_DOMAIN, i915_gem_set_domain_ioctl, DRM_UNLOCKED|DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(I915_GEM_SW_FINISH, i915_gem_sw_finish_ioctl, DRM_UNLOCKED|DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(I915_GEM_SET_TILING, i915_gem_set_tiling, DRM_UNLOCKED|DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(I915_GEM_GET_TILING, i915_gem_get_tiling, DRM_UNLOCKED|DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(I915_GEM_GET_APERTURE, i915_gem_get_aperture_ioctl, DRM_UNLOCKED|DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(I915_GET_PIPE_FROM_CRTC_ID, intel_get_pipe_from_crtc_id, DRM_UNLOCKED),
-	DRM_IOCTL_DEF_DRV(I915_GEM_MADVISE, i915_gem_madvise_ioctl, DRM_UNLOCKED),
+	DRM_IOCTL_DEF_DRV(I915_GEM_MADVISE, i915_gem_madvise_ioctl, DRM_UNLOCKED|DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(I915_OVERLAY_PUT_IMAGE, intel_overlay_put_image, DRM_MASTER|DRM_CONTROL_ALLOW|DRM_UNLOCKED),
 	DRM_IOCTL_DEF_DRV(I915_OVERLAY_ATTRS, intel_overlay_attrs, DRM_MASTER|DRM_CONTROL_ALLOW|DRM_UNLOCKED),
 	DRM_IOCTL_DEF_DRV(I915_SET_SPRITE_COLORKEY, intel_sprite_set_colorkey, DRM_MASTER|DRM_CONTROL_ALLOW|DRM_UNLOCKED),
 	DRM_IOCTL_DEF_DRV(I915_GET_SPRITE_COLORKEY, intel_sprite_get_colorkey, DRM_MASTER|DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-	DRM_IOCTL_DEF_DRV(I915_GEM_WAIT, i915_gem_wait_ioctl, DRM_AUTH|DRM_UNLOCKED),
-	DRM_IOCTL_DEF_DRV(I915_GEM_CONTEXT_CREATE, i915_gem_context_create_ioctl, DRM_UNLOCKED),
-	DRM_IOCTL_DEF_DRV(I915_GEM_CONTEXT_DESTROY, i915_gem_context_destroy_ioctl, DRM_UNLOCKED),
-	DRM_IOCTL_DEF_DRV(I915_REG_READ, i915_reg_read_ioctl, DRM_UNLOCKED),
+	DRM_IOCTL_DEF_DRV(I915_GEM_WAIT, i915_gem_wait_ioctl, DRM_AUTH|DRM_UNLOCKED|DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(I915_GEM_CONTEXT_CREATE, i915_gem_context_create_ioctl, DRM_UNLOCKED|DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(I915_GEM_CONTEXT_DESTROY, i915_gem_context_destroy_ioctl, DRM_UNLOCKED|DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(I915_REG_READ, i915_reg_read_ioctl, DRM_UNLOCKED|DRM_RENDER_ALLOW),
 };
 
 int i915_max_ioctl = DRM_ARRAY_SIZE(i915_ioctls);
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 45b3c030f483..69d8ed5416c3 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -118,10 +118,14 @@ module_param_named(i915_enable_ppgtt, i915_enable_ppgtt, int, 0600);
 MODULE_PARM_DESC(i915_enable_ppgtt,
 		"Enable PPGTT (default: true)");
 
-unsigned int i915_preliminary_hw_support __read_mostly = 0;
+int i915_enable_psr __read_mostly = 0;
+module_param_named(enable_psr, i915_enable_psr, int, 0600);
+MODULE_PARM_DESC(enable_psr, "Enable PSR (default: false)");
+
+unsigned int i915_preliminary_hw_support __read_mostly = IS_ENABLED(CONFIG_DRM_I915_PRELIMINARY_HW_SUPPORT);
 module_param_named(preliminary_hw_support, i915_preliminary_hw_support, int, 0600);
 MODULE_PARM_DESC(preliminary_hw_support,
-		"Enable preliminary hardware support. (default: false)");
+		"Enable preliminary hardware support.");
 
 int i915_disable_power_well __read_mostly = 1;
 module_param_named(disable_power_well, i915_disable_power_well, int, 0600);
@@ -132,27 +136,26 @@ int i915_enable_ips __read_mostly = 1;
 module_param_named(enable_ips, i915_enable_ips, int, 0600);
 MODULE_PARM_DESC(enable_ips, "Enable IPS (default: true)");
 
-static struct drm_driver driver;
-extern int intel_agp_enabled;
+bool i915_fastboot __read_mostly = 0;
+module_param_named(fastboot, i915_fastboot, bool, 0600);
+MODULE_PARM_DESC(fastboot, "Try to skip unnecessary mode sets at boot time "
+		 "(default: false)");
+
+int i915_enable_pc8 __read_mostly = 1;
+module_param_named(enable_pc8, i915_enable_pc8, int, 0600);
+MODULE_PARM_DESC(enable_pc8, "Enable support for low power package C states (PC8+) (default: true)");
 
-#define INTEL_VGA_DEVICE(id, info) {		\
-	.class = PCI_BASE_CLASS_DISPLAY << 16,	\
-	.class_mask = 0xff0000,			\
-	.vendor = 0x8086,			\
-	.device = id,				\
-	.subvendor = PCI_ANY_ID,		\
-	.subdevice = PCI_ANY_ID,		\
-	.driver_data = (unsigned long) info }
-
-#define INTEL_QUANTA_VGA_DEVICE(info) {		\
-	.class = PCI_BASE_CLASS_DISPLAY << 16,	\
-	.class_mask = 0xff0000,			\
-	.vendor = 0x8086,			\
-	.device = 0x16a,			\
-	.subvendor = 0x152d,			\
-	.subdevice = 0x8990,			\
-	.driver_data = (unsigned long) info }
+int i915_pc8_timeout __read_mostly = 5000;
+module_param_named(pc8_timeout, i915_pc8_timeout, int, 0600);
+MODULE_PARM_DESC(pc8_timeout, "Number of msecs of idleness required to enter PC8+ (default: 5000)");
 
+bool i915_prefault_disable __read_mostly;
+module_param_named(prefault_disable, i915_prefault_disable, bool, 0600);
+MODULE_PARM_DESC(prefault_disable,
+		"Disable page prefaulting for pread/pwrite/reloc (default:false). For developers only.");
+
+static struct drm_driver driver;
+extern int intel_agp_enabled;
 
 static const struct intel_device_info intel_i830_info = {
 	.gen = 2, .is_mobile = 1, .cursor_needs_physical = 1, .num_pipes = 2,
@@ -328,118 +331,41 @@ static const struct intel_device_info intel_haswell_m_info = {
 	.has_vebox_ring = 1,
 };
 
+/*
+ * Make sure any device matches here are from most specific to most
+ * general.  For example, since the Quanta match is based on the subsystem
+ * and subvendor IDs, we need it to come before the more general IVB
+ * PCI ID matches, otherwise we'll use the wrong info struct above.
+ */
+#define INTEL_PCI_IDS \
+	INTEL_I830_IDS(&intel_i830_info),	\
+	INTEL_I845G_IDS(&intel_845g_info),	\
+	INTEL_I85X_IDS(&intel_i85x_info),	\
+	INTEL_I865G_IDS(&intel_i865g_info),	\
+	INTEL_I915G_IDS(&intel_i915g_info),	\
+	INTEL_I915GM_IDS(&intel_i915gm_info),	\
+	INTEL_I945G_IDS(&intel_i945g_info),	\
+	INTEL_I945GM_IDS(&intel_i945gm_info),	\
+	INTEL_I965G_IDS(&intel_i965g_info),	\
+	INTEL_G33_IDS(&intel_g33_info),		\
+	INTEL_I965GM_IDS(&intel_i965gm_info),	\
+	INTEL_GM45_IDS(&intel_gm45_info), 	\
+	INTEL_G45_IDS(&intel_g45_info), 	\
+	INTEL_PINEVIEW_IDS(&intel_pineview_info),	\
+	INTEL_IRONLAKE_D_IDS(&intel_ironlake_d_info),	\
+	INTEL_IRONLAKE_M_IDS(&intel_ironlake_m_info),	\
+	INTEL_SNB_D_IDS(&intel_sandybridge_d_info),	\
+	INTEL_SNB_M_IDS(&intel_sandybridge_m_info),	\
+	INTEL_IVB_Q_IDS(&intel_ivybridge_q_info), /* must be first IVB */ \
+	INTEL_IVB_M_IDS(&intel_ivybridge_m_info),	\
+	INTEL_IVB_D_IDS(&intel_ivybridge_d_info),	\
+	INTEL_HSW_D_IDS(&intel_haswell_d_info), \
+	INTEL_HSW_M_IDS(&intel_haswell_m_info), \
+	INTEL_VLV_M_IDS(&intel_valleyview_m_info),	\
+	INTEL_VLV_D_IDS(&intel_valleyview_d_info)
+
 static const struct pci_device_id pciidlist[] = {		/* aka */
-	INTEL_VGA_DEVICE(0x3577, &intel_i830_info),		/* I830_M */
-	INTEL_VGA_DEVICE(0x2562, &intel_845g_info),		/* 845_G */
-	INTEL_VGA_DEVICE(0x3582, &intel_i85x_info),		/* I855_GM */
-	INTEL_VGA_DEVICE(0x358e, &intel_i85x_info),
-	INTEL_VGA_DEVICE(0x2572, &intel_i865g_info),		/* I865_G */
-	INTEL_VGA_DEVICE(0x2582, &intel_i915g_info),		/* I915_G */
-	INTEL_VGA_DEVICE(0x258a, &intel_i915g_info),		/* E7221_G */
-	INTEL_VGA_DEVICE(0x2592, &intel_i915gm_info),		/* I915_GM */
-	INTEL_VGA_DEVICE(0x2772, &intel_i945g_info),		/* I945_G */
-	INTEL_VGA_DEVICE(0x27a2, &intel_i945gm_info),		/* I945_GM */
-	INTEL_VGA_DEVICE(0x27ae, &intel_i945gm_info),		/* I945_GME */
-	INTEL_VGA_DEVICE(0x2972, &intel_i965g_info),		/* I946_GZ */
-	INTEL_VGA_DEVICE(0x2982, &intel_i965g_info),		/* G35_G */
-	INTEL_VGA_DEVICE(0x2992, &intel_i965g_info),		/* I965_Q */
-	INTEL_VGA_DEVICE(0x29a2, &intel_i965g_info),		/* I965_G */
-	INTEL_VGA_DEVICE(0x29b2, &intel_g33_info),		/* Q35_G */
-	INTEL_VGA_DEVICE(0x29c2, &intel_g33_info),		/* G33_G */
-	INTEL_VGA_DEVICE(0x29d2, &intel_g33_info),		/* Q33_G */
-	INTEL_VGA_DEVICE(0x2a02, &intel_i965gm_info),		/* I965_GM */
-	INTEL_VGA_DEVICE(0x2a12, &intel_i965gm_info),		/* I965_GME */
-	INTEL_VGA_DEVICE(0x2a42, &intel_gm45_info),		/* GM45_G */
-	INTEL_VGA_DEVICE(0x2e02, &intel_g45_info),		/* IGD_E_G */
-	INTEL_VGA_DEVICE(0x2e12, &intel_g45_info),		/* Q45_G */
-	INTEL_VGA_DEVICE(0x2e22, &intel_g45_info),		/* G45_G */
-	INTEL_VGA_DEVICE(0x2e32, &intel_g45_info),		/* G41_G */
-	INTEL_VGA_DEVICE(0x2e42, &intel_g45_info),		/* B43_G */
-	INTEL_VGA_DEVICE(0x2e92, &intel_g45_info),		/* B43_G.1 */
-	INTEL_VGA_DEVICE(0xa001, &intel_pineview_info),
-	INTEL_VGA_DEVICE(0xa011, &intel_pineview_info),
-	INTEL_VGA_DEVICE(0x0042, &intel_ironlake_d_info),
-	INTEL_VGA_DEVICE(0x0046, &intel_ironlake_m_info),
-	INTEL_VGA_DEVICE(0x0102, &intel_sandybridge_d_info),
-	INTEL_VGA_DEVICE(0x0112, &intel_sandybridge_d_info),
-	INTEL_VGA_DEVICE(0x0122, &intel_sandybridge_d_info),
-	INTEL_VGA_DEVICE(0x0106, &intel_sandybridge_m_info),
-	INTEL_VGA_DEVICE(0x0116, &intel_sandybridge_m_info),
-	INTEL_VGA_DEVICE(0x0126, &intel_sandybridge_m_info),
-	INTEL_VGA_DEVICE(0x010A, &intel_sandybridge_d_info),
-	INTEL_VGA_DEVICE(0x0156, &intel_ivybridge_m_info), /* GT1 mobile */
-	INTEL_VGA_DEVICE(0x0166, &intel_ivybridge_m_info), /* GT2 mobile */
-	INTEL_VGA_DEVICE(0x0152, &intel_ivybridge_d_info), /* GT1 desktop */
-	INTEL_VGA_DEVICE(0x0162, &intel_ivybridge_d_info), /* GT2 desktop */
-	INTEL_VGA_DEVICE(0x015a, &intel_ivybridge_d_info), /* GT1 server */
-	INTEL_QUANTA_VGA_DEVICE(&intel_ivybridge_q_info), /* Quanta transcode */
-	INTEL_VGA_DEVICE(0x016a, &intel_ivybridge_d_info), /* GT2 server */
-	INTEL_VGA_DEVICE(0x0402, &intel_haswell_d_info), /* GT1 desktop */
-	INTEL_VGA_DEVICE(0x0412, &intel_haswell_d_info), /* GT2 desktop */
-	INTEL_VGA_DEVICE(0x0422, &intel_haswell_d_info), /* GT3 desktop */
-	INTEL_VGA_DEVICE(0x040a, &intel_haswell_d_info), /* GT1 server */
-	INTEL_VGA_DEVICE(0x041a, &intel_haswell_d_info), /* GT2 server */
-	INTEL_VGA_DEVICE(0x042a, &intel_haswell_d_info), /* GT3 server */
-	INTEL_VGA_DEVICE(0x0406, &intel_haswell_m_info), /* GT1 mobile */
-	INTEL_VGA_DEVICE(0x0416, &intel_haswell_m_info), /* GT2 mobile */
-	INTEL_VGA_DEVICE(0x0426, &intel_haswell_m_info), /* GT2 mobile */
-	INTEL_VGA_DEVICE(0x040B, &intel_haswell_d_info), /* GT1 reserved */
-	INTEL_VGA_DEVICE(0x041B, &intel_haswell_d_info), /* GT2 reserved */
-	INTEL_VGA_DEVICE(0x042B, &intel_haswell_d_info), /* GT3 reserved */
-	INTEL_VGA_DEVICE(0x040E, &intel_haswell_d_info), /* GT1 reserved */
-	INTEL_VGA_DEVICE(0x041E, &intel_haswell_d_info), /* GT2 reserved */
-	INTEL_VGA_DEVICE(0x042E, &intel_haswell_d_info), /* GT3 reserved */
-	INTEL_VGA_DEVICE(0x0C02, &intel_haswell_d_info), /* SDV GT1 desktop */
-	INTEL_VGA_DEVICE(0x0C12, &intel_haswell_d_info), /* SDV GT2 desktop */
-	INTEL_VGA_DEVICE(0x0C22, &intel_haswell_d_info), /* SDV GT3 desktop */
-	INTEL_VGA_DEVICE(0x0C0A, &intel_haswell_d_info), /* SDV GT1 server */
-	INTEL_VGA_DEVICE(0x0C1A, &intel_haswell_d_info), /* SDV GT2 server */
-	INTEL_VGA_DEVICE(0x0C2A, &intel_haswell_d_info), /* SDV GT3 server */
-	INTEL_VGA_DEVICE(0x0C06, &intel_haswell_m_info), /* SDV GT1 mobile */
-	INTEL_VGA_DEVICE(0x0C16, &intel_haswell_m_info), /* SDV GT2 mobile */
-	INTEL_VGA_DEVICE(0x0C26, &intel_haswell_m_info), /* SDV GT3 mobile */
-	INTEL_VGA_DEVICE(0x0C0B, &intel_haswell_d_info), /* SDV GT1 reserved */
-	INTEL_VGA_DEVICE(0x0C1B, &intel_haswell_d_info), /* SDV GT2 reserved */
-	INTEL_VGA_DEVICE(0x0C2B, &intel_haswell_d_info), /* SDV GT3 reserved */
-	INTEL_VGA_DEVICE(0x0C0E, &intel_haswell_d_info), /* SDV GT1 reserved */
-	INTEL_VGA_DEVICE(0x0C1E, &intel_haswell_d_info), /* SDV GT2 reserved */
-	INTEL_VGA_DEVICE(0x0C2E, &intel_haswell_d_info), /* SDV GT3 reserved */
-	INTEL_VGA_DEVICE(0x0A02, &intel_haswell_d_info), /* ULT GT1 desktop */
-	INTEL_VGA_DEVICE(0x0A12, &intel_haswell_d_info), /* ULT GT2 desktop */
-	INTEL_VGA_DEVICE(0x0A22, &intel_haswell_d_info), /* ULT GT3 desktop */
-	INTEL_VGA_DEVICE(0x0A0A, &intel_haswell_d_info), /* ULT GT1 server */
-	INTEL_VGA_DEVICE(0x0A1A, &intel_haswell_d_info), /* ULT GT2 server */
-	INTEL_VGA_DEVICE(0x0A2A, &intel_haswell_d_info), /* ULT GT3 server */
-	INTEL_VGA_DEVICE(0x0A06, &intel_haswell_m_info), /* ULT GT1 mobile */
-	INTEL_VGA_DEVICE(0x0A16, &intel_haswell_m_info), /* ULT GT2 mobile */
-	INTEL_VGA_DEVICE(0x0A26, &intel_haswell_m_info), /* ULT GT3 mobile */
-	INTEL_VGA_DEVICE(0x0A0B, &intel_haswell_d_info), /* ULT GT1 reserved */
-	INTEL_VGA_DEVICE(0x0A1B, &intel_haswell_d_info), /* ULT GT2 reserved */
-	INTEL_VGA_DEVICE(0x0A2B, &intel_haswell_d_info), /* ULT GT3 reserved */
-	INTEL_VGA_DEVICE(0x0A0E, &intel_haswell_m_info), /* ULT GT1 reserved */
-	INTEL_VGA_DEVICE(0x0A1E, &intel_haswell_m_info), /* ULT GT2 reserved */
-	INTEL_VGA_DEVICE(0x0A2E, &intel_haswell_m_info), /* ULT GT3 reserved */
-	INTEL_VGA_DEVICE(0x0D02, &intel_haswell_d_info), /* CRW GT1 desktop */
-	INTEL_VGA_DEVICE(0x0D12, &intel_haswell_d_info), /* CRW GT2 desktop */
-	INTEL_VGA_DEVICE(0x0D22, &intel_haswell_d_info), /* CRW GT3 desktop */
-	INTEL_VGA_DEVICE(0x0D0A, &intel_haswell_d_info), /* CRW GT1 server */
-	INTEL_VGA_DEVICE(0x0D1A, &intel_haswell_d_info), /* CRW GT2 server */
-	INTEL_VGA_DEVICE(0x0D2A, &intel_haswell_d_info), /* CRW GT3 server */
-	INTEL_VGA_DEVICE(0x0D06, &intel_haswell_m_info), /* CRW GT1 mobile */
-	INTEL_VGA_DEVICE(0x0D16, &intel_haswell_m_info), /* CRW GT2 mobile */
-	INTEL_VGA_DEVICE(0x0D26, &intel_haswell_m_info), /* CRW GT3 mobile */
-	INTEL_VGA_DEVICE(0x0D0B, &intel_haswell_d_info), /* CRW GT1 reserved */
-	INTEL_VGA_DEVICE(0x0D1B, &intel_haswell_d_info), /* CRW GT2 reserved */
-	INTEL_VGA_DEVICE(0x0D2B, &intel_haswell_d_info), /* CRW GT3 reserved */
-	INTEL_VGA_DEVICE(0x0D0E, &intel_haswell_d_info), /* CRW GT1 reserved */
-	INTEL_VGA_DEVICE(0x0D1E, &intel_haswell_d_info), /* CRW GT2 reserved */
-	INTEL_VGA_DEVICE(0x0D2E, &intel_haswell_d_info), /* CRW GT3 reserved */
-	INTEL_VGA_DEVICE(0x0f30, &intel_valleyview_m_info),
-	INTEL_VGA_DEVICE(0x0f31, &intel_valleyview_m_info),
-	INTEL_VGA_DEVICE(0x0f32, &intel_valleyview_m_info),
-	INTEL_VGA_DEVICE(0x0f33, &intel_valleyview_m_info),
-	INTEL_VGA_DEVICE(0x0157, &intel_valleyview_m_info),
-	INTEL_VGA_DEVICE(0x0155, &intel_valleyview_d_info),
+	INTEL_PCI_IDS,
 	{0, 0, 0}
 };
 
@@ -543,6 +469,9 @@ static int i915_drm_freeze(struct drm_device *dev)
 	dev_priv->modeset_restore = MODESET_SUSPENDED;
 	mutex_unlock(&dev_priv->modeset_restore_lock);
 
+	/* We do a lot of poking in a lot of registers, make sure they work
+	 * properly. */
+	hsw_disable_package_c8(dev_priv);
 	intel_set_power_well(dev, true);
 
 	drm_kms_helper_poll_disable(dev);
@@ -551,7 +480,11 @@ static int i915_drm_freeze(struct drm_device *dev)
 
 	/* If KMS is active, we do the leavevt stuff here */
 	if (drm_core_check_feature(dev, DRIVER_MODESET)) {
-		int error = i915_gem_idle(dev);
+		int error;
+
+		mutex_lock(&dev->struct_mutex);
+		error = i915_gem_idle(dev);
+		mutex_unlock(&dev->struct_mutex);
 		if (error) {
 			dev_err(&dev->pdev->dev,
 				"GEM idle failed, resume might fail\n");
@@ -656,7 +589,6 @@ static int __i915_drm_thaw(struct drm_device *dev)
 		intel_init_pch_refclk(dev);
 
 		mutex_lock(&dev->struct_mutex);
-		dev_priv->mm.suspended = 0;
 
 		error = i915_gem_init_hw(dev);
 		mutex_unlock(&dev->struct_mutex);
@@ -696,6 +628,10 @@ static int __i915_drm_thaw(struct drm_device *dev)
 		schedule_work(&dev_priv->console_resume_work);
 	}
 
+	/* Undo what we did at i915_drm_freeze so the refcount goes back to the
+	 * expected level. */
+	hsw_enable_package_c8(dev_priv);
+
 	mutex_lock(&dev_priv->modeset_restore_lock);
 	dev_priv->modeset_restore = MODESET_DONE;
 	mutex_unlock(&dev_priv->modeset_restore_lock);
@@ -706,7 +642,7 @@ static int i915_drm_thaw(struct drm_device *dev)
 {
 	int error = 0;
 
-	intel_gt_sanitize(dev);
+	intel_uncore_sanitize(dev);
 
 	if (drm_core_check_feature(dev, DRIVER_MODESET)) {
 		mutex_lock(&dev->struct_mutex);
@@ -732,7 +668,7 @@ int i915_resume(struct drm_device *dev)
 
 	pci_set_master(dev->pdev);
 
-	intel_gt_sanitize(dev);
+	intel_uncore_sanitize(dev);
 
 	/*
 	 * Platforms with opregion should have sane BIOS, older ones (gen3 and
@@ -753,139 +689,6 @@ int i915_resume(struct drm_device *dev)
 	return 0;
 }
 
-static int i8xx_do_reset(struct drm_device *dev)
-{
-	struct drm_i915_private *dev_priv = dev->dev_private;
-
-	if (IS_I85X(dev))
-		return -ENODEV;
-
-	I915_WRITE(D_STATE, I915_READ(D_STATE) | DSTATE_GFX_RESET_I830);
-	POSTING_READ(D_STATE);
-
-	if (IS_I830(dev) || IS_845G(dev)) {
-		I915_WRITE(DEBUG_RESET_I830,
-			   DEBUG_RESET_DISPLAY |
-			   DEBUG_RESET_RENDER |
-			   DEBUG_RESET_FULL);
-		POSTING_READ(DEBUG_RESET_I830);
-		msleep(1);
-
-		I915_WRITE(DEBUG_RESET_I830, 0);
-		POSTING_READ(DEBUG_RESET_I830);
-	}
-
-	msleep(1);
-
-	I915_WRITE(D_STATE, I915_READ(D_STATE) & ~DSTATE_GFX_RESET_I830);
-	POSTING_READ(D_STATE);
-
-	return 0;
-}
-
-static int i965_reset_complete(struct drm_device *dev)
-{
-	u8 gdrst;
-	pci_read_config_byte(dev->pdev, I965_GDRST, &gdrst);
-	return (gdrst & GRDOM_RESET_ENABLE) == 0;
-}
-
-static int i965_do_reset(struct drm_device *dev)
-{
-	int ret;
-	u8 gdrst;
-
-	/*
-	 * Set the domains we want to reset (GRDOM/bits 2 and 3) as
-	 * well as the reset bit (GR/bit 0).  Setting the GR bit
-	 * triggers the reset; when done, the hardware will clear it.
-	 */
-	pci_read_config_byte(dev->pdev, I965_GDRST, &gdrst);
-	pci_write_config_byte(dev->pdev, I965_GDRST,
-			      gdrst | GRDOM_RENDER |
-			      GRDOM_RESET_ENABLE);
-	ret =  wait_for(i965_reset_complete(dev), 500);
-	if (ret)
-		return ret;
-
-	/* We can't reset render&media without also resetting display ... */
-	pci_read_config_byte(dev->pdev, I965_GDRST, &gdrst);
-	pci_write_config_byte(dev->pdev, I965_GDRST,
-			      gdrst | GRDOM_MEDIA |
-			      GRDOM_RESET_ENABLE);
-
-	return wait_for(i965_reset_complete(dev), 500);
-}
-
-static int ironlake_do_reset(struct drm_device *dev)
-{
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	u32 gdrst;
-	int ret;
-
-	gdrst = I915_READ(MCHBAR_MIRROR_BASE + ILK_GDSR);
-	gdrst &= ~GRDOM_MASK;
-	I915_WRITE(MCHBAR_MIRROR_BASE + ILK_GDSR,
-		   gdrst | GRDOM_RENDER | GRDOM_RESET_ENABLE);
-	ret = wait_for(I915_READ(MCHBAR_MIRROR_BASE + ILK_GDSR) & 0x1, 500);
-	if (ret)
-		return ret;
-
-	/* We can't reset render&media without also resetting display ... */
-	gdrst = I915_READ(MCHBAR_MIRROR_BASE + ILK_GDSR);
-	gdrst &= ~GRDOM_MASK;
-	I915_WRITE(MCHBAR_MIRROR_BASE + ILK_GDSR,
-		   gdrst | GRDOM_MEDIA | GRDOM_RESET_ENABLE);
-	return wait_for(I915_READ(MCHBAR_MIRROR_BASE + ILK_GDSR) & 0x1, 500);
-}
-
-static int gen6_do_reset(struct drm_device *dev)
-{
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	int	ret;
-	unsigned long irqflags;
-
-	/* Hold gt_lock across reset to prevent any register access
-	 * with forcewake not set correctly
-	 */
-	spin_lock_irqsave(&dev_priv->gt_lock, irqflags);
-
-	/* Reset the chip */
-
-	/* GEN6_GDRST is not in the gt power well, no need to check
-	 * for fifo space for the write or forcewake the chip for
-	 * the read
-	 */
-	I915_WRITE_NOTRACE(GEN6_GDRST, GEN6_GRDOM_FULL);
-
-	/* Spin waiting for the device to ack the reset request */
-	ret = wait_for((I915_READ_NOTRACE(GEN6_GDRST) & GEN6_GRDOM_FULL) == 0, 500);
-
-	/* If reset with a user forcewake, try to restore, otherwise turn it off */
-	if (dev_priv->forcewake_count)
-		dev_priv->gt.force_wake_get(dev_priv);
-	else
-		dev_priv->gt.force_wake_put(dev_priv);
-
-	/* Restore fifo count */
-	dev_priv->gt_fifo_count = I915_READ_NOTRACE(GT_FIFO_FREE_ENTRIES);
-
-	spin_unlock_irqrestore(&dev_priv->gt_lock, irqflags);
-	return ret;
-}
-
-int intel_gpu_reset(struct drm_device *dev)
-{
-	switch (INTEL_INFO(dev)->gen) {
-	case 7:
-	case 6: return gen6_do_reset(dev);
-	case 5: return ironlake_do_reset(dev);
-	case 4: return i965_do_reset(dev);
-	case 2: return i8xx_do_reset(dev);
-	default: return -ENODEV;
-	}
-}
-
 /**
  * i915_reset - reset chip after a hang
  * @dev: drm device to reset
@@ -955,11 +758,11 @@ int i915_reset(struct drm_device *dev)
 	 * switched away).
 	 */
 	if (drm_core_check_feature(dev, DRIVER_MODESET) ||
-			!dev_priv->mm.suspended) {
+			!dev_priv->ums.mm_suspended) {
 		struct intel_ring_buffer *ring;
 		int i;
 
-		dev_priv->mm.suspended = 0;
+		dev_priv->ums.mm_suspended = 0;
 
 		i915_gem_init_swizzling(dev);
 
@@ -1110,7 +913,6 @@ static const struct file_operations i915_driver_fops = {
 	.unlocked_ioctl = drm_ioctl,
 	.mmap = drm_gem_mmap,
 	.poll = drm_poll,
-	.fasync = drm_fasync,
 	.read = drm_read,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl = i915_compat_ioctl,
@@ -1123,8 +925,9 @@ static struct drm_driver driver = {
 	 * deal with them for Intel hardware.
 	 */
 	.driver_features =
-	    DRIVER_USE_AGP | DRIVER_REQUIRE_AGP | /* DRIVER_USE_MTRR |*/
-	    DRIVER_HAVE_IRQ | DRIVER_IRQ_SHARED | DRIVER_GEM | DRIVER_PRIME,
+	    DRIVER_USE_AGP | DRIVER_REQUIRE_AGP |
+	    DRIVER_HAVE_IRQ | DRIVER_IRQ_SHARED | DRIVER_GEM | DRIVER_PRIME |
+	    DRIVER_RENDER,
 	.load = i915_driver_load,
 	.unload = i915_driver_unload,
 	.open = i915_driver_open,
@@ -1154,7 +957,7 @@ static struct drm_driver driver = {
 
 	.dumb_create = i915_gem_dumb_create,
 	.dumb_map_offset = i915_gem_mmap_gtt,
-	.dumb_destroy = i915_gem_dumb_destroy,
+	.dumb_destroy = drm_gem_dumb_destroy,
 	.ioctls = i915_ioctls,
 	.fops = &i915_driver_fops,
 	.name = DRIVER_NAME,
@@ -1215,136 +1018,3 @@ module_exit(i915_exit);
 MODULE_AUTHOR(DRIVER_AUTHOR);
 MODULE_DESCRIPTION(DRIVER_DESC);
 MODULE_LICENSE("GPL and additional rights");
-
-/* We give fast paths for the really cool registers */
-#define NEEDS_FORCE_WAKE(dev_priv, reg) \
-	((HAS_FORCE_WAKE((dev_priv)->dev)) && \
-	 ((reg) < 0x40000) &&            \
-	 ((reg) != FORCEWAKE))
-static void
-ilk_dummy_write(struct drm_i915_private *dev_priv)
-{
-	/* WaIssueDummyWriteToWakeupFromRC6:ilk Issue a dummy write to wake up
-	 * the chip from rc6 before touching it for real. MI_MODE is masked,
-	 * hence harmless to write 0 into. */
-	I915_WRITE_NOTRACE(MI_MODE, 0);
-}
-
-static void
-hsw_unclaimed_reg_clear(struct drm_i915_private *dev_priv, u32 reg)
-{
-	if (HAS_FPGA_DBG_UNCLAIMED(dev_priv->dev) &&
-	    (I915_READ_NOTRACE(FPGA_DBG) & FPGA_DBG_RM_NOCLAIM)) {
-		DRM_ERROR("Unknown unclaimed register before writing to %x\n",
-			  reg);
-		I915_WRITE_NOTRACE(FPGA_DBG, FPGA_DBG_RM_NOCLAIM);
-	}
-}
-
-static void
-hsw_unclaimed_reg_check(struct drm_i915_private *dev_priv, u32 reg)
-{
-	if (HAS_FPGA_DBG_UNCLAIMED(dev_priv->dev) &&
-	    (I915_READ_NOTRACE(FPGA_DBG) & FPGA_DBG_RM_NOCLAIM)) {
-		DRM_ERROR("Unclaimed write to %x\n", reg);
-		I915_WRITE_NOTRACE(FPGA_DBG, FPGA_DBG_RM_NOCLAIM);
-	}
-}
-
-#define __i915_read(x, y) \
-u##x i915_read##x(struct drm_i915_private *dev_priv, u32 reg) { \
-	unsigned long irqflags; \
-	u##x val = 0; \
-	spin_lock_irqsave(&dev_priv->gt_lock, irqflags); \
-	if (IS_GEN5(dev_priv->dev)) \
-		ilk_dummy_write(dev_priv); \
-	if (NEEDS_FORCE_WAKE((dev_priv), (reg))) { \
-		if (dev_priv->forcewake_count == 0) \
-			dev_priv->gt.force_wake_get(dev_priv); \
-		val = read##y(dev_priv->regs + reg); \
-		if (dev_priv->forcewake_count == 0) \
-			dev_priv->gt.force_wake_put(dev_priv); \
-	} else { \
-		val = read##y(dev_priv->regs + reg); \
-	} \
-	spin_unlock_irqrestore(&dev_priv->gt_lock, irqflags); \
-	trace_i915_reg_rw(false, reg, val, sizeof(val)); \
-	return val; \
-}
-
-__i915_read(8, b)
-__i915_read(16, w)
-__i915_read(32, l)
-__i915_read(64, q)
-#undef __i915_read
-
-#define __i915_write(x, y) \
-void i915_write##x(struct drm_i915_private *dev_priv, u32 reg, u##x val) { \
-	unsigned long irqflags; \
-	u32 __fifo_ret = 0; \
-	trace_i915_reg_rw(true, reg, val, sizeof(val)); \
-	spin_lock_irqsave(&dev_priv->gt_lock, irqflags); \
-	if (NEEDS_FORCE_WAKE((dev_priv), (reg))) { \
-		__fifo_ret = __gen6_gt_wait_for_fifo(dev_priv); \
-	} \
-	if (IS_GEN5(dev_priv->dev)) \
-		ilk_dummy_write(dev_priv); \
-	hsw_unclaimed_reg_clear(dev_priv, reg); \
-	write##y(val, dev_priv->regs + reg); \
-	if (unlikely(__fifo_ret)) { \
-		gen6_gt_check_fifodbg(dev_priv); \
-	} \
-	hsw_unclaimed_reg_check(dev_priv, reg); \
-	spin_unlock_irqrestore(&dev_priv->gt_lock, irqflags); \
-}
-__i915_write(8, b)
-__i915_write(16, w)
-__i915_write(32, l)
-__i915_write(64, q)
-#undef __i915_write
-
-static const struct register_whitelist {
-	uint64_t offset;
-	uint32_t size;
-	uint32_t gen_bitmask; /* support gens, 0x10 for 4, 0x30 for 4 and 5, etc. */
-} whitelist[] = {
-	{ RING_TIMESTAMP(RENDER_RING_BASE), 8, 0xF0 },
-};
-
-int i915_reg_read_ioctl(struct drm_device *dev,
-			void *data, struct drm_file *file)
-{
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct drm_i915_reg_read *reg = data;
-	struct register_whitelist const *entry = whitelist;
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(whitelist); i++, entry++) {
-		if (entry->offset == reg->offset &&
-		    (1 << INTEL_INFO(dev)->gen & entry->gen_bitmask))
-			break;
-	}
-
-	if (i == ARRAY_SIZE(whitelist))
-		return -EINVAL;
-
-	switch (entry->size) {
-	case 8:
-		reg->val = I915_READ64(reg->offset);
-		break;
-	case 4:
-		reg->val = I915_READ(reg->offset);
-		break;
-	case 2:
-		reg->val = I915_READ16(reg->offset);
-		break;
-	case 1:
-		reg->val = I915_READ8(reg->offset);
-		break;
-	default:
-		WARN_ON(1);
-		return -EINVAL;
-	}
-
-	return 0;
-}
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 1929bffc1c77..35874b3a86dc 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -144,6 +144,7 @@ enum intel_dpll_id {
 
 struct intel_dpll_hw_state {
 	uint32_t dpll;
+	uint32_t dpll_md;
 	uint32_t fp0;
 	uint32_t fp1;
 };
@@ -156,6 +157,8 @@ struct intel_shared_dpll {
 	/* should match the index in the dev_priv->shared_dplls array */
 	enum intel_dpll_id id;
 	struct intel_dpll_hw_state hw_state;
+	void (*mode_set)(struct drm_i915_private *dev_priv,
+			 struct intel_shared_dpll *pll);
 	void (*enable)(struct drm_i915_private *dev_priv,
 		       struct intel_shared_dpll *pll);
 	void (*disable)(struct drm_i915_private *dev_priv,
@@ -198,7 +201,6 @@ struct intel_ddi_plls {
 #define DRIVER_MINOR		6
 #define DRIVER_PATCHLEVEL	0
 
-#define WATCH_COHERENCY	0
 #define WATCH_LISTS	0
 #define WATCH_GTT	0
 
@@ -320,8 +322,8 @@ struct drm_i915_error_state {
 		u32 purgeable:1;
 		s32 ring:4;
 		u32 cache_level:2;
-	} *active_bo, *pinned_bo;
-	u32 active_bo_count, pinned_bo_count;
+	} **active_bo, **pinned_bo;
+	u32 *active_bo_count, *pinned_bo_count;
 	struct intel_overlay_error_state *overlay;
 	struct intel_display_error_state *display;
 };
@@ -356,14 +358,16 @@ struct drm_i915_display_funcs {
 			  struct dpll *match_clock,
 			  struct dpll *best_clock);
 	void (*update_wm)(struct drm_device *dev);
-	void (*update_sprite_wm)(struct drm_device *dev, int pipe,
+	void (*update_sprite_wm)(struct drm_plane *plane,
+				 struct drm_crtc *crtc,
 				 uint32_t sprite_width, int pixel_size,
-				 bool enable);
+				 bool enable, bool scaled);
 	void (*modeset_global_resources)(struct drm_device *dev);
 	/* Returns the active state of the crtc, and if the crtc is active,
 	 * fills out the pipe-config with the hw state. */
 	bool (*get_pipe_config)(struct intel_crtc *,
 				struct intel_crtc_config *);
+	void (*get_clock)(struct intel_crtc *, struct intel_crtc_config *);
 	int (*crtc_mode_set)(struct drm_crtc *crtc,
 			     int x, int y,
 			     struct drm_framebuffer *old_fb);
@@ -376,7 +380,8 @@ struct drm_i915_display_funcs {
 	void (*init_clock_gating)(struct drm_device *dev);
 	int (*queue_flip)(struct drm_device *dev, struct drm_crtc *crtc,
 			  struct drm_framebuffer *fb,
-			  struct drm_i915_gem_object *obj);
+			  struct drm_i915_gem_object *obj,
+			  uint32_t flags);
 	int (*update_plane)(struct drm_crtc *crtc, struct drm_framebuffer *fb,
 			    int x, int y);
 	void (*hpd_irq_setup)(struct drm_device *dev);
@@ -387,11 +392,20 @@ struct drm_i915_display_funcs {
 	/* pll clock increase/decrease */
 };
 
-struct drm_i915_gt_funcs {
+struct intel_uncore_funcs {
 	void (*force_wake_get)(struct drm_i915_private *dev_priv);
 	void (*force_wake_put)(struct drm_i915_private *dev_priv);
 };
 
+struct intel_uncore {
+	spinlock_t lock; /** lock is also taken in irq contexts. */
+
+	struct intel_uncore_funcs funcs;
+
+	unsigned fifo_count;
+	unsigned forcewake_count;
+};
+
 #define DEV_INFO_FOR_EACH_FLAG(func, sep) \
 	func(is_mobile) sep \
 	func(is_i85x) sep \
@@ -436,12 +450,64 @@ struct intel_device_info {
 
 enum i915_cache_level {
 	I915_CACHE_NONE = 0,
-	I915_CACHE_LLC,
-	I915_CACHE_LLC_MLC, /* gen6+, in docs at least! */
+	I915_CACHE_LLC, /* also used for snoopable memory on non-LLC */
+	I915_CACHE_L3_LLC, /* gen7+, L3 sits between the domain specifc
+			      caches, eg sampler/render caches, and the
+			      large Last-Level-Cache. LLC is coherent with
+			      the CPU, but L3 is only visible to the GPU. */
+	I915_CACHE_WT, /* hsw:gt3e WriteThrough for scanouts */
 };
 
 typedef uint32_t gen6_gtt_pte_t;
 
+struct i915_address_space {
+	struct drm_mm mm;
+	struct drm_device *dev;
+	struct list_head global_link;
+	unsigned long start;		/* Start offset always 0 for dri2 */
+	size_t total;		/* size addr space maps (ex. 2GB for ggtt) */
+
+	struct {
+		dma_addr_t addr;
+		struct page *page;
+	} scratch;
+
+	/**
+	 * List of objects currently involved in rendering.
+	 *
+	 * Includes buffers having the contents of their GPU caches
+	 * flushed, not necessarily primitives.  last_rendering_seqno
+	 * represents when the rendering involved will be completed.
+	 *
+	 * A reference is held on the buffer while on this list.
+	 */
+	struct list_head active_list;
+
+	/**
+	 * LRU list of objects which are not in the ringbuffer and
+	 * are ready to unbind, but are still in the GTT.
+	 *
+	 * last_rendering_seqno is 0 while an object is in this list.
+	 *
+	 * A reference is not held on the buffer while on this list,
+	 * as merely being GTT-bound shouldn't prevent its being
+	 * freed, and we'll pull it off the list in the free path.
+	 */
+	struct list_head inactive_list;
+
+	/* FIXME: Need a more generic return type */
+	gen6_gtt_pte_t (*pte_encode)(dma_addr_t addr,
+				     enum i915_cache_level level);
+	void (*clear_range)(struct i915_address_space *vm,
+			    unsigned int first_entry,
+			    unsigned int num_entries);
+	void (*insert_entries)(struct i915_address_space *vm,
+			       struct sg_table *st,
+			       unsigned int first_entry,
+			       enum i915_cache_level cache_level);
+	void (*cleanup)(struct i915_address_space *vm);
+};
+
 /* The Graphics Translation Table is the way in which GEN hardware translates a
  * Graphics Virtual Address into a Physical Address. In addition to the normal
  * collateral associated with any va->pa translations GEN hardware also has a
@@ -450,8 +516,7 @@ typedef uint32_t gen6_gtt_pte_t;
  * the spec.
  */
 struct i915_gtt {
-	unsigned long start;		/* Start offset of used GTT */
-	size_t total;			/* Total size GTT can map */
+	struct i915_address_space base;
 	size_t stolen_size;		/* Total size of stolen memory */
 
 	unsigned long mappable_end;	/* End offset that we can CPU map */
@@ -462,50 +527,47 @@ struct i915_gtt {
 	void __iomem *gsm;
 
 	bool do_idle_maps;
-	dma_addr_t scratch_page_dma;
-	struct page *scratch_page;
+
+	int mtrr;
 
 	/* global gtt ops */
 	int (*gtt_probe)(struct drm_device *dev, size_t *gtt_total,
 			  size_t *stolen, phys_addr_t *mappable_base,
 			  unsigned long *mappable_end);
-	void (*gtt_remove)(struct drm_device *dev);
-	void (*gtt_clear_range)(struct drm_device *dev,
-				unsigned int first_entry,
-				unsigned int num_entries);
-	void (*gtt_insert_entries)(struct drm_device *dev,
-				   struct sg_table *st,
-				   unsigned int pg_start,
-				   enum i915_cache_level cache_level);
-	gen6_gtt_pte_t (*pte_encode)(struct drm_device *dev,
-				     dma_addr_t addr,
-				     enum i915_cache_level level);
 };
-#define gtt_total_entries(gtt) ((gtt).total >> PAGE_SHIFT)
+#define gtt_total_entries(gtt) ((gtt).base.total >> PAGE_SHIFT)
 
-#define I915_PPGTT_PD_ENTRIES 512
-#define I915_PPGTT_PT_ENTRIES 1024
 struct i915_hw_ppgtt {
-	struct drm_device *dev;
+	struct i915_address_space base;
 	unsigned num_pd_entries;
 	struct page **pt_pages;
 	uint32_t pd_offset;
 	dma_addr_t *pt_dma_addr;
-	dma_addr_t scratch_page_dma_addr;
 
-	/* pte functions, mirroring the interface of the global gtt. */
-	void (*clear_range)(struct i915_hw_ppgtt *ppgtt,
-			    unsigned int first_entry,
-			    unsigned int num_entries);
-	void (*insert_entries)(struct i915_hw_ppgtt *ppgtt,
-			       struct sg_table *st,
-			       unsigned int pg_start,
-			       enum i915_cache_level cache_level);
-	gen6_gtt_pte_t (*pte_encode)(struct drm_device *dev,
-				     dma_addr_t addr,
-				     enum i915_cache_level level);
 	int (*enable)(struct drm_device *dev);
-	void (*cleanup)(struct i915_hw_ppgtt *ppgtt);
+};
+
+/**
+ * A VMA represents a GEM BO that is bound into an address space. Therefore, a
+ * VMA's presence cannot be guaranteed before binding, or after unbinding the
+ * object into/from the address space.
+ *
+ * To make things as simple as possible (ie. no refcounting), a VMA's lifetime
+ * will always be <= an objects lifetime. So object refcounting should cover us.
+ */
+struct i915_vma {
+	struct drm_mm_node node;
+	struct drm_i915_gem_object *obj;
+	struct i915_address_space *vm;
+
+	/** This object's place on the active/inactive lists */
+	struct list_head mm_list;
+
+	struct list_head vma_link; /* Link in the object's VMA list */
+
+	/** This vma's place in the batchbuffer or on the eviction list */
+	struct list_head exec_list;
+
 };
 
 struct i915_ctx_hang_stats {
@@ -528,15 +590,48 @@ struct i915_hw_context {
 	struct i915_ctx_hang_stats hang_stats;
 };
 
-enum no_fbc_reason {
-	FBC_NO_OUTPUT, /* no outputs enabled to compress */
-	FBC_STOLEN_TOO_SMALL, /* not enough space to hold compressed buffers */
-	FBC_UNSUPPORTED_MODE, /* interlace or doublescanned mode */
-	FBC_MODE_TOO_LARGE, /* mode too large for compression */
-	FBC_BAD_PLANE, /* fbc not supported on plane */
-	FBC_NOT_TILED, /* buffer not tiled */
-	FBC_MULTIPLE_PIPES, /* more than one pipe active */
-	FBC_MODULE_PARAM,
+struct i915_fbc {
+	unsigned long size;
+	unsigned int fb_id;
+	enum plane plane;
+	int y;
+
+	struct drm_mm_node *compressed_fb;
+	struct drm_mm_node *compressed_llb;
+
+	struct intel_fbc_work {
+		struct delayed_work work;
+		struct drm_crtc *crtc;
+		struct drm_framebuffer *fb;
+		int interval;
+	} *fbc_work;
+
+	enum no_fbc_reason {
+		FBC_OK, /* FBC is enabled */
+		FBC_UNSUPPORTED, /* FBC is not supported by this chipset */
+		FBC_NO_OUTPUT, /* no outputs enabled to compress */
+		FBC_STOLEN_TOO_SMALL, /* not enough space for buffers */
+		FBC_UNSUPPORTED_MODE, /* interlace or doublescanned mode */
+		FBC_MODE_TOO_LARGE, /* mode too large for compression */
+		FBC_BAD_PLANE, /* fbc not supported on plane */
+		FBC_NOT_TILED, /* buffer not tiled */
+		FBC_MULTIPLE_PIPES, /* more than one pipe active */
+		FBC_MODULE_PARAM,
+		FBC_CHIP_DEFAULT, /* disabled by default on this chip */
+	} no_fbc_reason;
+};
+
+enum no_psr_reason {
+	PSR_NO_SOURCE, /* Not supported on platform */
+	PSR_NO_SINK, /* Not supported by panel */
+	PSR_MODULE_PARAM,
+	PSR_CRTC_NOT_ACTIVE,
+	PSR_PWR_WELL_ENABLED,
+	PSR_NOT_TILED,
+	PSR_SPRITE_ENABLED,
+	PSR_S3D_ENABLED,
+	PSR_INTERLACED_ENABLED,
+	PSR_HSW_NOT_DDIA,
 };
 
 enum intel_pch {
@@ -722,12 +817,12 @@ struct i915_suspend_saved_registers {
 };
 
 struct intel_gen6_power_mgmt {
+	/* work and pm_iir are protected by dev_priv->irq_lock */
 	struct work_struct work;
-	struct delayed_work vlv_work;
 	u32 pm_iir;
-	/* lock - irqsave spinlock that protectects the work_struct and
-	 * pm_iir. */
-	spinlock_t lock;
+
+	/* On vlv we need to manually drop to Vmin with a delayed work. */
+	struct delayed_work vlv_work;
 
 	/* The below variables an all the rps hw state are protected by
 	 * dev->struct mutext. */
@@ -793,6 +888,18 @@ struct i915_dri1_state {
 	uint32_t counter;
 };
 
+struct i915_ums_state {
+	/**
+	 * Flag if the X Server, and thus DRM, is not currently in
+	 * control of the device.
+	 *
+	 * This is set between LeaveVT and EnterVT.  It needs to be
+	 * replaced with a semaphore.  It also needs to be
+	 * transitioned away from for kernel modesetting.
+	 */
+	int mm_suspended;
+};
+
 struct intel_l3_parity {
 	u32 *remap_info;
 	struct work_struct error_work;
@@ -801,8 +908,6 @@ struct intel_l3_parity {
 struct i915_gem_mm {
 	/** Memory allocator for GTT stolen memory */
 	struct drm_mm stolen;
-	/** Memory allocator for GTT */
-	struct drm_mm gtt_space;
 	/** List of all objects in gtt_space. Used to restore gtt
 	 * mappings on resume */
 	struct list_head bound_list;
@@ -816,37 +921,12 @@ struct i915_gem_mm {
 	/** Usable portion of the GTT for GEM */
 	unsigned long stolen_base; /* limited to low memory (32-bit) */
 
-	int gtt_mtrr;
-
 	/** PPGTT used for aliasing the PPGTT with the GTT */
 	struct i915_hw_ppgtt *aliasing_ppgtt;
 
 	struct shrinker inactive_shrinker;
 	bool shrinker_no_lock_stealing;
 
-	/**
-	 * List of objects currently involved in rendering.
-	 *
-	 * Includes buffers having the contents of their GPU caches
-	 * flushed, not necessarily primitives.  last_rendering_seqno
-	 * represents when the rendering involved will be completed.
-	 *
-	 * A reference is held on the buffer while on this list.
-	 */
-	struct list_head active_list;
-
-	/**
-	 * LRU list of objects which are not in the ringbuffer and
-	 * are ready to unbind, but are still in the GTT.
-	 *
-	 * last_rendering_seqno is 0 while an object is in this list.
-	 *
-	 * A reference is not held on the buffer while on this list,
-	 * as merely being GTT-bound shouldn't prevent its being
-	 * freed, and we'll pull it off the list in the free path.
-	 */
-	struct list_head inactive_list;
-
 	/** LRU list of objects with fence regs on them. */
 	struct list_head fence_list;
 
@@ -865,16 +945,6 @@ struct i915_gem_mm {
 	 */
 	bool interruptible;
 
-	/**
-	 * Flag if the X Server, and thus DRM, is not currently in
-	 * control of the device.
-	 *
-	 * This is set between LeaveVT and EnterVT.  It needs to be
-	 * replaced with a semaphore.  It also needs to be
-	 * transitioned away from for kernel modesetting.
-	 */
-	int suspended;
-
 	/** Bit 6 swizzling required for X tiling */
 	uint32_t bit_6_swizzle_x;
 	/** Bit 6 swizzling required for Y tiling */
@@ -884,6 +954,7 @@ struct i915_gem_mm {
 	struct drm_i915_gem_phys_object *phys_objs[I915_MAX_PHYS_OBJECT];
 
 	/* accounting, useful for userland debugging */
+	spinlock_t object_stat_lock;
 	size_t object_memory;
 	u32 object_count;
 };
@@ -897,6 +968,11 @@ struct drm_i915_error_state_buf {
 	loff_t pos;
 };
 
+struct i915_error_state_file_priv {
+	struct drm_device *dev;
+	struct drm_i915_error_state *error;
+};
+
 struct i915_gpu_error {
 	/* For hangcheck timer */
 #define DRM_I915_HANGCHECK_PERIOD 1500 /* in ms */
@@ -988,6 +1064,88 @@ struct intel_vbt_data {
 	struct child_device_config *child_dev;
 };
 
+enum intel_ddb_partitioning {
+	INTEL_DDB_PART_1_2,
+	INTEL_DDB_PART_5_6, /* IVB+ */
+};
+
+struct intel_wm_level {
+	bool enable;
+	uint32_t pri_val;
+	uint32_t spr_val;
+	uint32_t cur_val;
+	uint32_t fbc_val;
+};
+
+/*
+ * This struct tracks the state needed for the Package C8+ feature.
+ *
+ * Package states C8 and deeper are really deep PC states that can only be
+ * reached when all the devices on the system allow it, so even if the graphics
+ * device allows PC8+, it doesn't mean the system will actually get to these
+ * states.
+ *
+ * Our driver only allows PC8+ when all the outputs are disabled, the power well
+ * is disabled and the GPU is idle. When these conditions are met, we manually
+ * do the other conditions: disable the interrupts, clocks and switch LCPLL
+ * refclk to Fclk.
+ *
+ * When we really reach PC8 or deeper states (not just when we allow it) we lose
+ * the state of some registers, so when we come back from PC8+ we need to
+ * restore this state. We don't get into PC8+ if we're not in RC6, so we don't
+ * need to take care of the registers kept by RC6.
+ *
+ * The interrupt disabling is part of the requirements. We can only leave the
+ * PCH HPD interrupts enabled. If we're in PC8+ and we get another interrupt we
+ * can lock the machine.
+ *
+ * Ideally every piece of our code that needs PC8+ disabled would call
+ * hsw_disable_package_c8, which would increment disable_count and prevent the
+ * system from reaching PC8+. But we don't have a symmetric way to do this for
+ * everything, so we have the requirements_met and gpu_idle variables. When we
+ * switch requirements_met or gpu_idle to true we decrease disable_count, and
+ * increase it in the opposite case. The requirements_met variable is true when
+ * all the CRTCs, encoders and the power well are disabled. The gpu_idle
+ * variable is true when the GPU is idle.
+ *
+ * In addition to everything, we only actually enable PC8+ if disable_count
+ * stays at zero for at least some seconds. This is implemented with the
+ * enable_work variable. We do this so we don't enable/disable PC8 dozens of
+ * consecutive times when all screens are disabled and some background app
+ * queries the state of our connectors, or we have some application constantly
+ * waking up to use the GPU. Only after the enable_work function actually
+ * enables PC8+ the "enable" variable will become true, which means that it can
+ * be false even if disable_count is 0.
+ *
+ * The irqs_disabled variable becomes true exactly after we disable the IRQs and
+ * goes back to false exactly before we reenable the IRQs. We use this variable
+ * to check if someone is trying to enable/disable IRQs while they're supposed
+ * to be disabled. This shouldn't happen and we'll print some error messages in
+ * case it happens, but if it actually happens we'll also update the variables
+ * inside struct regsave so when we restore the IRQs they will contain the
+ * latest expected values.
+ *
+ * For more, read "Display Sequences for Package C8" on our documentation.
+ */
+struct i915_package_c8 {
+	bool requirements_met;
+	bool gpu_idle;
+	bool irqs_disabled;
+	/* Only true after the delayed work task actually enables it. */
+	bool enabled;
+	int disable_count;
+	struct mutex lock;
+	struct delayed_work enable_work;
+
+	struct {
+		uint32_t deimr;
+		uint32_t sdeimr;
+		uint32_t gtimr;
+		uint32_t gtier;
+		uint32_t gen6_pmimr;
+	} regsave;
+};
+
 typedef struct drm_i915_private {
 	struct drm_device *dev;
 	struct kmem_cache *slab;
@@ -998,14 +1156,7 @@ typedef struct drm_i915_private {
 
 	void __iomem *regs;
 
-	struct drm_i915_gt_funcs gt;
-	/** gt_fifo_count and the subsequent register write are synchronized
-	 * with dev->struct_mutex. */
-	unsigned gt_fifo_count;
-	/** forcewake_count is protected by gt_lock */
-	unsigned forcewake_count;
-	/** gt_lock is also taken in irq contexts. */
-	spinlock_t gt_lock;
+	struct intel_uncore uncore;
 
 	struct intel_gmbus gmbus[GMBUS_NUM_PORTS];
 
@@ -1042,6 +1193,7 @@ typedef struct drm_i915_private {
 	/** Cached value of IMR to avoid reads in updating the bitfield */
 	u32 irq_mask;
 	u32 gt_irq_mask;
+	u32 pm_irq_mask;
 
 	struct work_struct hotplug_work;
 	bool enable_hotplug_processing;
@@ -1059,12 +1211,7 @@ typedef struct drm_i915_private {
 
 	int num_plane;
 
-	unsigned long cfb_size;
-	unsigned int cfb_fb;
-	enum plane cfb_plane;
-	int cfb_y;
-	struct intel_fbc_work *fbc_work;
-
+	struct i915_fbc fbc;
 	struct intel_opregion opregion;
 	struct intel_vbt_data vbt;
 
@@ -1081,8 +1228,6 @@ typedef struct drm_i915_private {
 	} backlight;
 
 	/* LVDS info */
-	struct drm_display_mode *lfp_lvds_vbt_mode; /* if any */
-	struct drm_display_mode *sdvo_lvds_vbt_mode; /* if any */
 	bool no_aux_handshake;
 
 	struct drm_i915_fence_reg fence_regs[I915_MAX_NUM_FENCES]; /* assume 965 */
@@ -1091,6 +1236,13 @@ typedef struct drm_i915_private {
 
 	unsigned int fsb_freq, mem_freq, is_ddr3;
 
+	/**
+	 * wq - Driver workqueue for GEM.
+	 *
+	 * NOTE: Work items scheduled here are not allowed to grab any modeset
+	 * locks, for otherwise the flushing done in the pageflip code will
+	 * result in deadlocks.
+	 */
 	struct workqueue_struct *wq;
 
 	/* Display functions */
@@ -1105,7 +1257,8 @@ typedef struct drm_i915_private {
 	enum modeset_restore modeset_restore;
 	struct mutex modeset_restore_lock;
 
-	struct i915_gtt gtt;
+	struct list_head vm_list; /* Global list of all address spaces */
+	struct i915_gtt gtt; /* VMA representing the global address space */
 
 	struct i915_gem_mm mm;
 
@@ -1132,6 +1285,9 @@ typedef struct drm_i915_private {
 
 	struct intel_l3_parity l3_parity;
 
+	/* Cannot be determined by PCIID. You must always read a register. */
+	size_t ellc_size;
+
 	/* gen6+ rps state */
 	struct intel_gen6_power_mgmt rps;
 
@@ -1142,10 +1298,7 @@ typedef struct drm_i915_private {
 	/* Haswell power well */
 	struct i915_power_well power_well;
 
-	enum no_fbc_reason no_fbc_reason;
-
-	struct drm_mm_node *compressed_fb;
-	struct drm_mm_node *compressed_llb;
+	enum no_psr_reason no_psr_reason;
 
 	struct i915_gpu_error gpu_error;
 
@@ -1170,11 +1323,34 @@ typedef struct drm_i915_private {
 
 	struct i915_suspend_saved_registers regfile;
 
+	struct {
+		/*
+		 * Raw watermark latency values:
+		 * in 0.1us units for WM0,
+		 * in 0.5us units for WM1+.
+		 */
+		/* primary */
+		uint16_t pri_latency[5];
+		/* sprite */
+		uint16_t spr_latency[5];
+		/* cursor */
+		uint16_t cur_latency[5];
+	} wm;
+
+	struct i915_package_c8 pc8;
+
 	/* Old dri1 support infrastructure, beware the dragons ya fools entering
 	 * here! */
 	struct i915_dri1_state dri1;
+	/* Old ums support infrastructure, same warning applies. */
+	struct i915_ums_state ums;
 } drm_i915_private_t;
 
+static inline struct drm_i915_private *to_i915(const struct drm_device *dev)
+{
+	return dev->dev_private;
+}
+
 /* Iterate over initialised rings */
 #define for_each_ring(ring__, dev_priv__, i__) \
 	for ((i__) = 0; (i__) < I915_NUM_RINGS; (i__)++) \
@@ -1187,7 +1363,7 @@ enum hdmi_force_audio {
 	HDMI_AUDIO_ON,			/* force turn on HDMI audio */
 };
 
-#define I915_GTT_RESERVED ((struct drm_mm_node *)0x1)
+#define I915_GTT_OFFSET_NONE ((u32)-1)
 
 struct drm_i915_gem_object_ops {
 	/* Interface between the GEM object and its backing storage.
@@ -1212,15 +1388,16 @@ struct drm_i915_gem_object {
 
 	const struct drm_i915_gem_object_ops *ops;
 
-	/** Current space allocated to this object in the GTT, if any. */
-	struct drm_mm_node *gtt_space;
+	/** List of VMAs backed by this object */
+	struct list_head vma_list;
+
 	/** Stolen memory for this object, instead of being backed by shmem. */
 	struct drm_mm_node *stolen;
 	struct list_head global_list;
 
-	/** This object's place on the active/inactive lists */
 	struct list_head ring_list;
-	struct list_head mm_list;
+	/** Used in execbuf to temporarily hold a ref */
+	struct list_head obj_exec_link;
 	/** This object's place in the batchbuffer or on the eviction list */
 	struct list_head exec_list;
 
@@ -1287,6 +1464,7 @@ struct drm_i915_gem_object {
 	 */
 	unsigned int fault_mappable:1;
 	unsigned int pin_mappable:1;
+	unsigned int pin_display:1;
 
 	/*
 	 * Is the GPU currently using a fence to access this buffer,
@@ -1294,7 +1472,7 @@ struct drm_i915_gem_object {
 	unsigned int pending_fenced_gpu_access:1;
 	unsigned int fenced_gpu_access:1;
 
-	unsigned int cache_level:2;
+	unsigned int cache_level:3;
 
 	unsigned int has_aliasing_ppgtt_mapping:1;
 	unsigned int has_global_gtt_mapping:1;
@@ -1314,13 +1492,6 @@ struct drm_i915_gem_object {
 	unsigned long exec_handle;
 	struct drm_i915_gem_exec_object2 *exec_entry;
 
-	/**
-	 * Current offset of the object in GTT space.
-	 *
-	 * This is the same as gtt_space->start
-	 */
-	uint32_t gtt_offset;
-
 	struct intel_ring_buffer *ring;
 
 	/** Breadcrumb of last rendering to the buffer. */
@@ -1396,7 +1567,7 @@ struct drm_i915_file_private {
 	struct i915_ctx_hang_stats hang_stats;
 };
 
-#define INTEL_INFO(dev)	(((struct drm_i915_private *) (dev)->dev_private)->info)
+#define INTEL_INFO(dev)	(to_i915(dev)->info)
 
 #define IS_I830(dev)		((dev)->pci_device == 0x3577)
 #define IS_845G(dev)		((dev)->pci_device == 0x2562)
@@ -1414,7 +1585,6 @@ struct drm_i915_file_private {
 #define IS_PINEVIEW_M(dev)	((dev)->pci_device == 0xa011)
 #define IS_PINEVIEW(dev)	(INTEL_INFO(dev)->is_pineview)
 #define IS_G33(dev)		(INTEL_INFO(dev)->is_g33)
-#define IS_IRONLAKE_D(dev)	((dev)->pci_device == 0x0042)
 #define IS_IRONLAKE_M(dev)	((dev)->pci_device == 0x0046)
 #define IS_IVYBRIDGE(dev)	(INTEL_INFO(dev)->is_ivybridge)
 #define IS_IVB_GT1(dev)		((dev)->pci_device == 0x0156 || \
@@ -1426,6 +1596,8 @@ struct drm_i915_file_private {
 #define IS_VALLEYVIEW(dev)	(INTEL_INFO(dev)->is_valleyview)
 #define IS_HASWELL(dev)	(INTEL_INFO(dev)->is_haswell)
 #define IS_MOBILE(dev)		(INTEL_INFO(dev)->is_mobile)
+#define IS_HSW_EARLY_SDV(dev)	(IS_HASWELL(dev) && \
+				 ((dev)->pci_device & 0xFF00) == 0x0C00)
 #define IS_ULT(dev)		(IS_HASWELL(dev) && \
 				 ((dev)->pci_device & 0xFF00) == 0x0A00)
 
@@ -1446,6 +1618,7 @@ struct drm_i915_file_private {
 #define HAS_BLT(dev)            (INTEL_INFO(dev)->has_blt_ring)
 #define HAS_VEBOX(dev)          (INTEL_INFO(dev)->has_vebox_ring)
 #define HAS_LLC(dev)            (INTEL_INFO(dev)->has_llc)
+#define HAS_WT(dev)            (IS_HASWELL(dev) && to_i915(dev)->ellc_size)
 #define I915_NEED_GFX_HWS(dev)	(INTEL_INFO(dev)->need_gfx_hws)
 
 #define HAS_HW_CONTEXTS(dev)	(INTEL_INFO(dev)->gen >= 6)
@@ -1468,8 +1641,6 @@ struct drm_i915_file_private {
 #define SUPPORTS_EDP(dev)		(IS_IRONLAKE_M(dev))
 #define SUPPORTS_TV(dev)		(INTEL_INFO(dev)->supports_tv)
 #define I915_HAS_HOTPLUG(dev)		 (INTEL_INFO(dev)->has_hotplug)
-/* dsparb controlled by hw only */
-#define DSPARB_HWCONTROL(dev) (IS_G4X(dev) || IS_IRONLAKE(dev))
 
 #define HAS_FW_BLC(dev) (INTEL_INFO(dev)->gen > 2)
 #define HAS_PIPE_CXSR(dev) (INTEL_INFO(dev)->has_pipe_cxsr)
@@ -1477,8 +1648,6 @@ struct drm_i915_file_private {
 
 #define HAS_IPS(dev)		(IS_ULT(dev))
 
-#define HAS_PIPE_CONTROL(dev) (INTEL_INFO(dev)->gen >= 5)
-
 #define HAS_DDI(dev)		(INTEL_INFO(dev)->has_ddi)
 #define HAS_POWER_WELL(dev)	(IS_HASWELL(dev))
 #define HAS_FPGA_DBG_UNCLAIMED(dev)	(INTEL_INFO(dev)->has_fpga_dbg)
@@ -1490,7 +1659,7 @@ struct drm_i915_file_private {
 #define INTEL_PCH_LPT_DEVICE_ID_TYPE		0x8c00
 #define INTEL_PCH_LPT_LP_DEVICE_ID_TYPE		0x9c00
 
-#define INTEL_PCH_TYPE(dev) (((struct drm_i915_private *)(dev)->dev_private)->pch_type)
+#define INTEL_PCH_TYPE(dev) (to_i915(dev)->pch_type)
 #define HAS_PCH_LPT(dev) (INTEL_PCH_TYPE(dev) == PCH_LPT)
 #define HAS_PCH_CPT(dev) (INTEL_PCH_TYPE(dev) == PCH_CPT)
 #define HAS_PCH_IBX(dev) (INTEL_PCH_TYPE(dev) == PCH_IBX)
@@ -1526,7 +1695,7 @@ struct drm_i915_file_private {
 #define INTEL_RC6p_ENABLE			(1<<1)
 #define INTEL_RC6pp_ENABLE			(1<<2)
 
-extern struct drm_ioctl_desc i915_ioctls[];
+extern const struct drm_ioctl_desc i915_ioctls[];
 extern int i915_max_ioctl;
 extern unsigned int i915_fbpercrtc __always_unused;
 extern int i915_panel_ignore_lid __read_mostly;
@@ -1540,9 +1709,14 @@ extern int i915_enable_rc6 __read_mostly;
 extern int i915_enable_fbc __read_mostly;
 extern bool i915_enable_hangcheck __read_mostly;
 extern int i915_enable_ppgtt __read_mostly;
+extern int i915_enable_psr __read_mostly;
 extern unsigned int i915_preliminary_hw_support __read_mostly;
 extern int i915_disable_power_well __read_mostly;
 extern int i915_enable_ips __read_mostly;
+extern bool i915_fastboot __read_mostly;
+extern int i915_enable_pc8 __read_mostly;
+extern int i915_pc8_timeout __read_mostly;
+extern bool i915_prefault_disable __read_mostly;
 
 extern int i915_suspend(struct drm_device *dev, pm_message_t state);
 extern int i915_resume(struct drm_device *dev);
@@ -1578,16 +1752,19 @@ extern void i915_update_gfx_val(struct drm_i915_private *dev_priv);
 extern void intel_console_resume(struct work_struct *work);
 
 /* i915_irq.c */
-void i915_hangcheck_elapsed(unsigned long data);
+void i915_queue_hangcheck(struct drm_device *dev);
 void i915_handle_error(struct drm_device *dev, bool wedged);
 
 extern void intel_irq_init(struct drm_device *dev);
 extern void intel_pm_init(struct drm_device *dev);
 extern void intel_hpd_init(struct drm_device *dev);
-extern void intel_gt_init(struct drm_device *dev);
-extern void intel_gt_sanitize(struct drm_device *dev);
+extern void intel_pm_init(struct drm_device *dev);
 
-void i915_error_state_free(struct kref *error_ref);
+extern void intel_uncore_sanitize(struct drm_device *dev);
+extern void intel_uncore_early_sanitize(struct drm_device *dev);
+extern void intel_uncore_init(struct drm_device *dev);
+extern void intel_uncore_clear_errors(struct drm_device *dev);
+extern void intel_uncore_check_errors(struct drm_device *dev);
 
 void
 i915_enable_pipestat(drm_i915_private_t *dev_priv, int pipe, u32 mask);
@@ -1595,13 +1772,6 @@ i915_enable_pipestat(drm_i915_private_t *dev_priv, int pipe, u32 mask);
 void
 i915_disable_pipestat(drm_i915_private_t *dev_priv, int pipe, u32 mask);
 
-#ifdef CONFIG_DEBUG_FS
-extern void i915_destroy_error_state(struct drm_device *dev);
-#else
-#define i915_destroy_error_state(x)
-#endif
-
-
 /* i915_gem.c */
 int i915_gem_init_ioctl(struct drm_device *dev, void *data,
 			struct drm_file *file_priv);
@@ -1658,13 +1828,18 @@ void i915_gem_object_init(struct drm_i915_gem_object *obj,
 struct drm_i915_gem_object *i915_gem_alloc_object(struct drm_device *dev,
 						  size_t size);
 void i915_gem_free_object(struct drm_gem_object *obj);
+struct i915_vma *i915_gem_vma_create(struct drm_i915_gem_object *obj,
+				     struct i915_address_space *vm);
+void i915_gem_vma_destroy(struct i915_vma *vma);
 
 int __must_check i915_gem_object_pin(struct drm_i915_gem_object *obj,
+				     struct i915_address_space *vm,
 				     uint32_t alignment,
 				     bool map_and_fenceable,
 				     bool nonblocking);
 void i915_gem_object_unpin(struct drm_i915_gem_object *obj);
-int __must_check i915_gem_object_unbind(struct drm_i915_gem_object *obj);
+int __must_check i915_vma_unbind(struct i915_vma *vma);
+int __must_check i915_gem_object_ggtt_unbind(struct drm_i915_gem_object *obj);
 int i915_gem_object_put_pages(struct drm_i915_gem_object *obj);
 void i915_gem_release_mmap(struct drm_i915_gem_object *obj);
 void i915_gem_lastclose(struct drm_device *dev);
@@ -1701,8 +1876,6 @@ int i915_gem_dumb_create(struct drm_file *file_priv,
 			 struct drm_mode_create_dumb *args);
 int i915_gem_mmap_gtt(struct drm_file *file_priv, struct drm_device *dev,
 		      uint32_t handle, uint64_t *offset);
-int i915_gem_dumb_destroy(struct drm_file *file_priv, struct drm_device *dev,
-			  uint32_t handle);
 /**
  * Returns true if seq1 is later than seq2.
  */
@@ -1754,10 +1927,7 @@ static inline bool i915_terminally_wedged(struct i915_gpu_error *error)
 }
 
 void i915_gem_reset(struct drm_device *dev);
-void i915_gem_clflush_object(struct drm_i915_gem_object *obj);
-int __must_check i915_gem_object_set_domain(struct drm_i915_gem_object *obj,
-					    uint32_t read_domains,
-					    uint32_t write_domain);
+bool i915_gem_clflush_object(struct drm_i915_gem_object *obj, bool force);
 int __must_check i915_gem_object_finish_gpu(struct drm_i915_gem_object *obj);
 int __must_check i915_gem_init(struct drm_device *dev);
 int __must_check i915_gem_init_hw(struct drm_device *dev);
@@ -1784,6 +1954,7 @@ int __must_check
 i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj,
 				     u32 alignment,
 				     struct intel_ring_buffer *pipelined);
+void i915_gem_object_unpin_from_display_plane(struct drm_i915_gem_object *obj);
 int i915_gem_attach_phys_object(struct drm_device *dev,
 				struct drm_i915_gem_object *obj,
 				int id,
@@ -1810,6 +1981,56 @@ struct dma_buf *i915_gem_prime_export(struct drm_device *dev,
 
 void i915_gem_restore_fences(struct drm_device *dev);
 
+unsigned long i915_gem_obj_offset(struct drm_i915_gem_object *o,
+				  struct i915_address_space *vm);
+bool i915_gem_obj_bound_any(struct drm_i915_gem_object *o);
+bool i915_gem_obj_bound(struct drm_i915_gem_object *o,
+			struct i915_address_space *vm);
+unsigned long i915_gem_obj_size(struct drm_i915_gem_object *o,
+				struct i915_address_space *vm);
+struct i915_vma *i915_gem_obj_to_vma(struct drm_i915_gem_object *obj,
+				     struct i915_address_space *vm);
+struct i915_vma *
+i915_gem_obj_lookup_or_create_vma(struct drm_i915_gem_object *obj,
+				  struct i915_address_space *vm);
+/* Some GGTT VM helpers */
+#define obj_to_ggtt(obj) \
+	(&((struct drm_i915_private *)(obj)->base.dev->dev_private)->gtt.base)
+static inline bool i915_is_ggtt(struct i915_address_space *vm)
+{
+	struct i915_address_space *ggtt =
+		&((struct drm_i915_private *)(vm)->dev->dev_private)->gtt.base;
+	return vm == ggtt;
+}
+
+static inline bool i915_gem_obj_ggtt_bound(struct drm_i915_gem_object *obj)
+{
+	return i915_gem_obj_bound(obj, obj_to_ggtt(obj));
+}
+
+static inline unsigned long
+i915_gem_obj_ggtt_offset(struct drm_i915_gem_object *obj)
+{
+	return i915_gem_obj_offset(obj, obj_to_ggtt(obj));
+}
+
+static inline unsigned long
+i915_gem_obj_ggtt_size(struct drm_i915_gem_object *obj)
+{
+	return i915_gem_obj_size(obj, obj_to_ggtt(obj));
+}
+
+static inline int __must_check
+i915_gem_obj_ggtt_pin(struct drm_i915_gem_object *obj,
+		      uint32_t alignment,
+		      bool map_and_fenceable,
+		      bool nonblocking)
+{
+	return i915_gem_object_pin(obj, obj_to_ggtt(obj), alignment,
+				   map_and_fenceable, nonblocking);
+}
+#undef obj_to_ggtt
+
 /* i915_gem_context.c */
 void i915_gem_context_init(struct drm_device *dev);
 void i915_gem_context_fini(struct drm_device *dev);
@@ -1828,7 +2049,7 @@ static inline void i915_gem_context_unreference(struct i915_hw_context *ctx)
 }
 
 struct i915_ctx_hang_stats * __must_check
-i915_gem_context_get_hang_stats(struct intel_ring_buffer *ring,
+i915_gem_context_get_hang_stats(struct drm_device *dev,
 				struct drm_file *file,
 				u32 id);
 int i915_gem_context_create_ioctl(struct drm_device *dev, void *data,
@@ -1862,7 +2083,9 @@ static inline void i915_gem_chipset_flush(struct drm_device *dev)
 
 
 /* i915_gem_evict.c */
-int __must_check i915_gem_evict_something(struct drm_device *dev, int min_size,
+int __must_check i915_gem_evict_something(struct drm_device *dev,
+					  struct i915_address_space *vm,
+					  int min_size,
 					  unsigned alignment,
 					  unsigned cache_level,
 					  bool mappable,
@@ -1884,7 +2107,7 @@ i915_gem_object_create_stolen_for_preallocated(struct drm_device *dev,
 void i915_gem_object_release_stolen(struct drm_i915_gem_object *obj);
 
 /* i915_gem_tiling.c */
-inline static bool i915_gem_object_needs_bit17_swizzle(struct drm_i915_gem_object *obj)
+static inline bool i915_gem_object_needs_bit17_swizzle(struct drm_i915_gem_object *obj)
 {
 	drm_i915_private_t *dev_priv = obj->base.dev->dev_private;
 
@@ -1897,23 +2120,36 @@ void i915_gem_object_do_bit_17_swizzle(struct drm_i915_gem_object *obj);
 void i915_gem_object_save_bit_17_swizzle(struct drm_i915_gem_object *obj);
 
 /* i915_gem_debug.c */
-void i915_gem_dump_object(struct drm_i915_gem_object *obj, int len,
-			  const char *where, uint32_t mark);
 #if WATCH_LISTS
 int i915_verify_lists(struct drm_device *dev);
 #else
 #define i915_verify_lists(dev) 0
 #endif
-void i915_gem_object_check_coherency(struct drm_i915_gem_object *obj,
-				     int handle);
-void i915_gem_dump_object(struct drm_i915_gem_object *obj, int len,
-			  const char *where, uint32_t mark);
 
 /* i915_debugfs.c */
 int i915_debugfs_init(struct drm_minor *minor);
 void i915_debugfs_cleanup(struct drm_minor *minor);
+
+/* i915_gpu_error.c */
 __printf(2, 3)
 void i915_error_printf(struct drm_i915_error_state_buf *e, const char *f, ...);
+int i915_error_state_to_str(struct drm_i915_error_state_buf *estr,
+			    const struct i915_error_state_file_priv *error);
+int i915_error_state_buf_init(struct drm_i915_error_state_buf *eb,
+			      size_t count, loff_t pos);
+static inline void i915_error_state_buf_release(
+	struct drm_i915_error_state_buf *eb)
+{
+	kfree(eb->buf);
+}
+void i915_capture_error_state(struct drm_device *dev);
+void i915_error_state_get(struct drm_device *dev,
+			  struct i915_error_state_file_priv *error_priv);
+void i915_error_state_put(struct i915_error_state_file_priv *error_priv);
+void i915_destroy_error_state(struct drm_device *dev);
+
+void i915_get_extra_instdone(struct drm_device *dev, uint32_t *instdone);
+const char *i915_cache_level_str(int type);
 
 /* i915_suspend.c */
 extern int i915_save_state(struct drm_device *dev);
@@ -1993,7 +2229,6 @@ int i915_reg_read_ioctl(struct drm_device *dev, void *data,
 			struct drm_file *file);
 
 /* overlay */
-#ifdef CONFIG_DEBUG_FS
 extern struct intel_overlay_error_state *intel_overlay_capture_error_state(struct drm_device *dev);
 extern void intel_overlay_print_error_state(struct drm_i915_error_state_buf *e,
 					    struct intel_overlay_error_state *error);
@@ -2002,7 +2237,6 @@ extern struct intel_display_error_state *intel_display_capture_error_state(struc
 extern void intel_display_print_error_state(struct drm_i915_error_state_buf *e,
 					    struct drm_device *dev,
 					    struct intel_display_error_state *error);
-#endif
 
 /* On SNB platform, before reading ring registers forcewake bit
  * must be set to prevent GT core from power down and stale values being
@@ -2010,7 +2244,6 @@ extern void intel_display_print_error_state(struct drm_i915_error_state_buf *e,
  */
 void gen6_gt_force_wake_get(struct drm_i915_private *dev_priv);
 void gen6_gt_force_wake_put(struct drm_i915_private *dev_priv);
-int __gen6_gt_wait_for_fifo(struct drm_i915_private *dev_priv);
 
 int sandybridge_pcode_read(struct drm_i915_private *dev_priv, u8 mbox, u32 *val);
 int sandybridge_pcode_write(struct drm_i915_private *dev_priv, u8 mbox, u32 val);
@@ -2029,39 +2262,37 @@ void intel_sbi_write(struct drm_i915_private *dev_priv, u16 reg, u32 value,
 int vlv_gpu_freq(int ddr_freq, int val);
 int vlv_freq_opcode(int ddr_freq, int val);
 
-#define __i915_read(x, y) \
-	u##x i915_read##x(struct drm_i915_private *dev_priv, u32 reg);
-
-__i915_read(8, b)
-__i915_read(16, w)
-__i915_read(32, l)
-__i915_read(64, q)
+#define __i915_read(x) \
+	u##x i915_read##x(struct drm_i915_private *dev_priv, u32 reg, bool trace);
+__i915_read(8)
+__i915_read(16)
+__i915_read(32)
+__i915_read(64)
 #undef __i915_read
 
-#define __i915_write(x, y) \
-	void i915_write##x(struct drm_i915_private *dev_priv, u32 reg, u##x val);
-
-__i915_write(8, b)
-__i915_write(16, w)
-__i915_write(32, l)
-__i915_write(64, q)
+#define __i915_write(x) \
+	void i915_write##x(struct drm_i915_private *dev_priv, u32 reg, u##x val, bool trace);
+__i915_write(8)
+__i915_write(16)
+__i915_write(32)
+__i915_write(64)
 #undef __i915_write
 
-#define I915_READ8(reg)		i915_read8(dev_priv, (reg))
-#define I915_WRITE8(reg, val)	i915_write8(dev_priv, (reg), (val))
+#define I915_READ8(reg)		i915_read8(dev_priv, (reg), true)
+#define I915_WRITE8(reg, val)	i915_write8(dev_priv, (reg), (val), true)
 
-#define I915_READ16(reg)	i915_read16(dev_priv, (reg))
-#define I915_WRITE16(reg, val)	i915_write16(dev_priv, (reg), (val))
-#define I915_READ16_NOTRACE(reg)	readw(dev_priv->regs + (reg))
-#define I915_WRITE16_NOTRACE(reg, val)	writew(val, dev_priv->regs + (reg))
+#define I915_READ16(reg)	i915_read16(dev_priv, (reg), true)
+#define I915_WRITE16(reg, val)	i915_write16(dev_priv, (reg), (val), true)
+#define I915_READ16_NOTRACE(reg)	i915_read16(dev_priv, (reg), false)
+#define I915_WRITE16_NOTRACE(reg, val)	i915_write16(dev_priv, (reg), (val), false)
 
-#define I915_READ(reg)		i915_read32(dev_priv, (reg))
-#define I915_WRITE(reg, val)	i915_write32(dev_priv, (reg), (val))
-#define I915_READ_NOTRACE(reg)		readl(dev_priv->regs + (reg))
-#define I915_WRITE_NOTRACE(reg, val)	writel(val, dev_priv->regs + (reg))
+#define I915_READ(reg)		i915_read32(dev_priv, (reg), true)
+#define I915_WRITE(reg, val)	i915_write32(dev_priv, (reg), (val), true)
+#define I915_READ_NOTRACE(reg)		i915_read32(dev_priv, (reg), false)
+#define I915_WRITE_NOTRACE(reg, val)	i915_write32(dev_priv, (reg), (val), false)
 
-#define I915_WRITE64(reg, val)	i915_write64(dev_priv, (reg), (val))
-#define I915_READ64(reg)	i915_read64(dev_priv, (reg))
+#define I915_WRITE64(reg, val)	i915_write64(dev_priv, (reg), (val), true)
+#define I915_READ64(reg)	i915_read64(dev_priv, (reg), true)
 
 #define POSTING_READ(reg)	(void)I915_READ_NOTRACE(reg)
 #define POSTING_READ16(reg)	(void)I915_READ16_NOTRACE(reg)
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index d9e2208cfe98..cdfb9da0e4ce 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -26,6 +26,7 @@
  */
 
 #include <drm/drmP.h>
+#include <drm/drm_vma_manager.h>
 #include <drm/i915_drm.h>
 #include "i915_drv.h"
 #include "i915_trace.h"
@@ -37,11 +38,14 @@
 #include <linux/dma-buf.h>
 
 static void i915_gem_object_flush_gtt_write_domain(struct drm_i915_gem_object *obj);
-static void i915_gem_object_flush_cpu_write_domain(struct drm_i915_gem_object *obj);
-static __must_check int i915_gem_object_bind_to_gtt(struct drm_i915_gem_object *obj,
-						    unsigned alignment,
-						    bool map_and_fenceable,
-						    bool nonblocking);
+static void i915_gem_object_flush_cpu_write_domain(struct drm_i915_gem_object *obj,
+						   bool force);
+static __must_check int
+i915_gem_object_bind_to_vm(struct drm_i915_gem_object *obj,
+			   struct i915_address_space *vm,
+			   unsigned alignment,
+			   bool map_and_fenceable,
+			   bool nonblocking);
 static int i915_gem_phys_pwrite(struct drm_device *dev,
 				struct drm_i915_gem_object *obj,
 				struct drm_i915_gem_pwrite *args,
@@ -53,12 +57,28 @@ static void i915_gem_object_update_fence(struct drm_i915_gem_object *obj,
 					 struct drm_i915_fence_reg *fence,
 					 bool enable);
 
-static int i915_gem_inactive_shrink(struct shrinker *shrinker,
-				    struct shrink_control *sc);
+static unsigned long i915_gem_inactive_count(struct shrinker *shrinker,
+					     struct shrink_control *sc);
+static unsigned long i915_gem_inactive_scan(struct shrinker *shrinker,
+					    struct shrink_control *sc);
 static long i915_gem_purge(struct drm_i915_private *dev_priv, long target);
-static void i915_gem_shrink_all(struct drm_i915_private *dev_priv);
+static long i915_gem_shrink_all(struct drm_i915_private *dev_priv);
 static void i915_gem_object_truncate(struct drm_i915_gem_object *obj);
 
+static bool cpu_cache_is_coherent(struct drm_device *dev,
+				  enum i915_cache_level level)
+{
+	return HAS_LLC(dev) || level != I915_CACHE_NONE;
+}
+
+static bool cpu_write_needs_clflush(struct drm_i915_gem_object *obj)
+{
+	if (!cpu_cache_is_coherent(obj->base.dev, obj->cache_level))
+		return true;
+
+	return obj->pin_display;
+}
+
 static inline void i915_gem_object_fence_lost(struct drm_i915_gem_object *obj)
 {
 	if (obj->tiling_mode)
@@ -75,15 +95,19 @@ static inline void i915_gem_object_fence_lost(struct drm_i915_gem_object *obj)
 static void i915_gem_info_add_obj(struct drm_i915_private *dev_priv,
 				  size_t size)
 {
+	spin_lock(&dev_priv->mm.object_stat_lock);
 	dev_priv->mm.object_count++;
 	dev_priv->mm.object_memory += size;
+	spin_unlock(&dev_priv->mm.object_stat_lock);
 }
 
 static void i915_gem_info_remove_obj(struct drm_i915_private *dev_priv,
 				     size_t size)
 {
+	spin_lock(&dev_priv->mm.object_stat_lock);
 	dev_priv->mm.object_count--;
 	dev_priv->mm.object_memory -= size;
+	spin_unlock(&dev_priv->mm.object_stat_lock);
 }
 
 static int
@@ -135,7 +159,7 @@ int i915_mutex_lock_interruptible(struct drm_device *dev)
 static inline bool
 i915_gem_object_is_inactive(struct drm_i915_gem_object *obj)
 {
-	return obj->gtt_space && !obj->active;
+	return i915_gem_obj_bound_any(obj) && !obj->active;
 }
 
 int
@@ -178,10 +202,10 @@ i915_gem_get_aperture_ioctl(struct drm_device *dev, void *data,
 	mutex_lock(&dev->struct_mutex);
 	list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list)
 		if (obj->pin_count)
-			pinned += obj->gtt_space->size;
+			pinned += i915_gem_obj_ggtt_size(obj);
 	mutex_unlock(&dev->struct_mutex);
 
-	args->aper_size = dev_priv->gtt.total;
+	args->aper_size = dev_priv->gtt.base.total;
 	args->aper_available_size = args->aper_size - pinned;
 
 	return 0;
@@ -190,7 +214,7 @@ i915_gem_get_aperture_ioctl(struct drm_device *dev, void *data,
 void *i915_gem_object_alloc(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	return kmem_cache_alloc(dev_priv->slab, GFP_KERNEL | __GFP_ZERO);
+	return kmem_cache_zalloc(dev_priv->slab, GFP_KERNEL);
 }
 
 void i915_gem_object_free(struct drm_i915_gem_object *obj)
@@ -219,16 +243,10 @@ i915_gem_create(struct drm_file *file,
 		return -ENOMEM;
 
 	ret = drm_gem_handle_create(file, &obj->base, &handle);
-	if (ret) {
-		drm_gem_object_release(&obj->base);
-		i915_gem_info_remove_obj(dev->dev_private, obj->base.size);
-		i915_gem_object_free(obj);
-		return ret;
-	}
-
 	/* drop reference from allocate - handle holds it now */
-	drm_gem_object_unreference(&obj->base);
-	trace_i915_gem_object_create(obj);
+	drm_gem_object_unreference_unlocked(&obj->base);
+	if (ret)
+		return ret;
 
 	*handle_p = handle;
 	return 0;
@@ -246,13 +264,6 @@ i915_gem_dumb_create(struct drm_file *file,
 			       args->size, &args->handle);
 }
 
-int i915_gem_dumb_destroy(struct drm_file *file,
-			  struct drm_device *dev,
-			  uint32_t handle)
-{
-	return drm_gem_handle_delete(file, handle);
-}
-
 /**
  * Creates a new mm object and returns a handle to it.
  */
@@ -420,9 +431,8 @@ i915_gem_shmem_pread(struct drm_device *dev,
 		 * read domain and manually flush cachelines (if required). This
 		 * optimizes for the case when the gpu will dirty the data
 		 * anyway again before the next pread happens. */
-		if (obj->cache_level == I915_CACHE_NONE)
-			needs_clflush = 1;
-		if (obj->gtt_space) {
+		needs_clflush = !cpu_cache_is_coherent(dev, obj->cache_level);
+		if (i915_gem_obj_bound_any(obj)) {
 			ret = i915_gem_object_set_to_gtt_domain(obj, false);
 			if (ret)
 				return ret;
@@ -465,7 +475,7 @@ i915_gem_shmem_pread(struct drm_device *dev,
 
 		mutex_unlock(&dev->struct_mutex);
 
-		if (!prefaulted) {
+		if (likely(!i915_prefault_disable) && !prefaulted) {
 			ret = fault_in_multipages_writeable(user_data, remain);
 			/* Userspace is tricking us, but we've already clobbered
 			 * its pages with the prefault and promised to write the
@@ -594,7 +604,7 @@ i915_gem_gtt_pwrite_fast(struct drm_device *dev,
 	char __user *user_data;
 	int page_offset, page_length, ret;
 
-	ret = i915_gem_object_pin(obj, 0, true, true);
+	ret = i915_gem_obj_ggtt_pin(obj, 0, true, true);
 	if (ret)
 		goto out;
 
@@ -609,7 +619,7 @@ i915_gem_gtt_pwrite_fast(struct drm_device *dev,
 	user_data = to_user_ptr(args->data_ptr);
 	remain = args->size;
 
-	offset = obj->gtt_offset + args->offset;
+	offset = i915_gem_obj_ggtt_offset(obj) + args->offset;
 
 	while (remain > 0) {
 		/* Operation in this page
@@ -737,19 +747,18 @@ i915_gem_shmem_pwrite(struct drm_device *dev,
 		 * write domain and manually flush cachelines (if required). This
 		 * optimizes for the case when the gpu will use the data
 		 * right away and we therefore have to clflush anyway. */
-		if (obj->cache_level == I915_CACHE_NONE)
-			needs_clflush_after = 1;
-		if (obj->gtt_space) {
+		needs_clflush_after = cpu_write_needs_clflush(obj);
+		if (i915_gem_obj_bound_any(obj)) {
 			ret = i915_gem_object_set_to_gtt_domain(obj, true);
 			if (ret)
 				return ret;
 		}
 	}
-	/* Same trick applies for invalidate partially written cachelines before
-	 * writing.  */
-	if (!(obj->base.read_domains & I915_GEM_DOMAIN_CPU)
-	    && obj->cache_level == I915_CACHE_NONE)
-		needs_clflush_before = 1;
+	/* Same trick applies to invalidate partially written cachelines read
+	 * before writing. */
+	if ((obj->base.read_domains & I915_GEM_DOMAIN_CPU) == 0)
+		needs_clflush_before =
+			!cpu_cache_is_coherent(dev, obj->cache_level);
 
 	ret = i915_gem_object_get_pages(obj);
 	if (ret)
@@ -828,8 +837,8 @@ out:
 		 */
 		if (!needs_clflush_after &&
 		    obj->base.write_domain != I915_GEM_DOMAIN_CPU) {
-			i915_gem_clflush_object(obj);
-			i915_gem_chipset_flush(dev);
+			if (i915_gem_clflush_object(obj, obj->pin_display))
+				i915_gem_chipset_flush(dev);
 		}
 	}
 
@@ -860,10 +869,12 @@ i915_gem_pwrite_ioctl(struct drm_device *dev, void *data,
 		       args->size))
 		return -EFAULT;
 
-	ret = fault_in_multipages_readable(to_user_ptr(args->data_ptr),
-					   args->size);
-	if (ret)
-		return -EFAULT;
+	if (likely(!i915_prefault_disable)) {
+		ret = fault_in_multipages_readable(to_user_ptr(args->data_ptr),
+						   args->size);
+		if (ret)
+			return -EFAULT;
+	}
 
 	ret = i915_mutex_lock_interruptible(dev);
 	if (ret)
@@ -904,9 +915,9 @@ i915_gem_pwrite_ioctl(struct drm_device *dev, void *data,
 		goto out;
 	}
 
-	if (obj->cache_level == I915_CACHE_NONE &&
-	    obj->tiling_mode == I915_TILING_NONE &&
-	    obj->base.write_domain != I915_GEM_DOMAIN_CPU) {
+	if (obj->tiling_mode == I915_TILING_NONE &&
+	    obj->base.write_domain != I915_GEM_DOMAIN_CPU &&
+	    cpu_write_needs_clflush(obj)) {
 		ret = i915_gem_gtt_pwrite_fast(dev, obj, args, file);
 		/* Note that the gtt paths might fail with non-page-backed user
 		 * pointers (e.g. gtt mappings when moving data between
@@ -990,6 +1001,8 @@ static int __wait_seqno(struct intel_ring_buffer *ring, u32 seqno,
 	bool wait_forever = true;
 	int ret;
 
+	WARN(dev_priv->pc8.irqs_disabled, "IRQs disabled\n");
+
 	if (i915_seqno_passed(ring->get_seqno(ring, true), seqno))
 		return 0;
 
@@ -1255,8 +1268,8 @@ i915_gem_sw_finish_ioctl(struct drm_device *dev, void *data,
 	}
 
 	/* Pinned buffers may be scanout, so flush the cache */
-	if (obj->pin_count)
-		i915_gem_object_flush_cpu_write_domain(obj);
+	if (obj->pin_display)
+		i915_gem_object_flush_cpu_write_domain(obj, true);
 
 	drm_gem_object_unreference(&obj->base);
 unlock:
@@ -1346,7 +1359,7 @@ int i915_gem_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	}
 
 	/* Now bind it into the GTT if needed */
-	ret = i915_gem_object_pin(obj, 0, true, false);
+	ret = i915_gem_obj_ggtt_pin(obj,  0, true, false);
 	if (ret)
 		goto unlock;
 
@@ -1360,8 +1373,9 @@ int i915_gem_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 
 	obj->fault_mappable = true;
 
-	pfn = ((dev_priv->gtt.mappable_base + obj->gtt_offset) >> PAGE_SHIFT) +
-		page_offset;
+	pfn = dev_priv->gtt.mappable_base + i915_gem_obj_ggtt_offset(obj);
+	pfn >>= PAGE_SHIFT;
+	pfn += page_offset;
 
 	/* Finally, remap it using the new GTT offset */
 	ret = vm_insert_pfn(vma, (unsigned long)vmf->virtual_address, pfn);
@@ -1378,14 +1392,11 @@ out:
 		if (i915_terminally_wedged(&dev_priv->gpu_error))
 			return VM_FAULT_SIGBUS;
 	case -EAGAIN:
-		/* Give the error handler a chance to run and move the
-		 * objects off the GPU active list. Next time we service the
-		 * fault, we should be able to transition the page into the
-		 * GTT without touching the GPU (and so avoid further
-		 * EIO/EGAIN). If the GPU is wedged, then there is no issue
-		 * with coherency, just lost writes.
+		/*
+		 * EAGAIN means the gpu is hung and we'll wait for the error
+		 * handler to reset everything when re-faulting in
+		 * i915_mutex_lock_interruptible.
 		 */
-		set_need_resched();
 	case 0:
 	case -ERESTARTSYS:
 	case -EINTR:
@@ -1425,11 +1436,7 @@ i915_gem_release_mmap(struct drm_i915_gem_object *obj)
 	if (!obj->fault_mappable)
 		return;
 
-	if (obj->base.dev->dev_mapping)
-		unmap_mapping_range(obj->base.dev->dev_mapping,
-				    (loff_t)obj->base.map_list.hash.key<<PAGE_SHIFT,
-				    obj->base.size, 1);
-
+	drm_vma_node_unmap(&obj->base.vma_node, obj->base.dev->dev_mapping);
 	obj->fault_mappable = false;
 }
 
@@ -1485,7 +1492,7 @@ static int i915_gem_object_create_mmap_offset(struct drm_i915_gem_object *obj)
 	struct drm_i915_private *dev_priv = obj->base.dev->dev_private;
 	int ret;
 
-	if (obj->base.map_list.map)
+	if (drm_vma_node_has_offset(&obj->base.vma_node))
 		return 0;
 
 	dev_priv->mm.shrinker_no_lock_stealing = true;
@@ -1516,9 +1523,6 @@ out:
 
 static void i915_gem_object_free_mmap_offset(struct drm_i915_gem_object *obj)
 {
-	if (!obj->base.map_list.map)
-		return;
-
 	drm_gem_free_mmap_offset(&obj->base);
 }
 
@@ -1557,7 +1561,7 @@ i915_gem_mmap_gtt(struct drm_file *file,
 	if (ret)
 		goto out;
 
-	*offset = (u64)obj->base.map_list.hash.key << PAGE_SHIFT;
+	*offset = drm_vma_node_offset_addr(&obj->base.vma_node);
 
 out:
 	drm_gem_object_unreference(&obj->base);
@@ -1632,7 +1636,7 @@ i915_gem_object_put_pages_gtt(struct drm_i915_gem_object *obj)
 		 * hope for the best.
 		 */
 		WARN_ON(ret != -EIO);
-		i915_gem_clflush_object(obj);
+		i915_gem_clflush_object(obj, true);
 		obj->base.read_domains = obj->base.write_domain = I915_GEM_DOMAIN_CPU;
 	}
 
@@ -1667,11 +1671,11 @@ i915_gem_object_put_pages(struct drm_i915_gem_object *obj)
 	if (obj->pages == NULL)
 		return 0;
 
-	BUG_ON(obj->gtt_space);
-
 	if (obj->pages_pin_count)
 		return -EBUSY;
 
+	BUG_ON(i915_gem_obj_bound_any(obj));
+
 	/* ->put_pages might need to allocate memory for the bit17 swizzle
 	 * array, hence protect them from being reaped by removing them from gtt
 	 * lists early. */
@@ -1690,6 +1694,7 @@ static long
 __i915_gem_shrink(struct drm_i915_private *dev_priv, long target,
 		  bool purgeable_only)
 {
+	struct list_head still_bound_list;
 	struct drm_i915_gem_object *obj, *next;
 	long count = 0;
 
@@ -1704,17 +1709,55 @@ __i915_gem_shrink(struct drm_i915_private *dev_priv, long target,
 		}
 	}
 
-	list_for_each_entry_safe(obj, next,
-				 &dev_priv->mm.inactive_list,
-				 mm_list) {
-		if ((i915_gem_object_is_purgeable(obj) || !purgeable_only) &&
-		    i915_gem_object_unbind(obj) == 0 &&
-		    i915_gem_object_put_pages(obj) == 0) {
+	/*
+	 * As we may completely rewrite the bound list whilst unbinding
+	 * (due to retiring requests) we have to strictly process only
+	 * one element of the list at the time, and recheck the list
+	 * on every iteration.
+	 */
+	INIT_LIST_HEAD(&still_bound_list);
+	while (count < target && !list_empty(&dev_priv->mm.bound_list)) {
+		struct i915_vma *vma, *v;
+
+		obj = list_first_entry(&dev_priv->mm.bound_list,
+				       typeof(*obj), global_list);
+		list_move_tail(&obj->global_list, &still_bound_list);
+
+		if (!i915_gem_object_is_purgeable(obj) && purgeable_only)
+			continue;
+
+		/*
+		 * Hold a reference whilst we unbind this object, as we may
+		 * end up waiting for and retiring requests. This might
+		 * release the final reference (held by the active list)
+		 * and result in the object being freed from under us.
+		 * in this object being freed.
+		 *
+		 * Note 1: Shrinking the bound list is special since only active
+		 * (and hence bound objects) can contain such limbo objects, so
+		 * we don't need special tricks for shrinking the unbound list.
+		 * The only other place where we have to be careful with active
+		 * objects suddenly disappearing due to retiring requests is the
+		 * eviction code.
+		 *
+		 * Note 2: Even though the bound list doesn't hold a reference
+		 * to the object we can safely grab one here: The final object
+		 * unreferencing and the bound_list are both protected by the
+		 * dev->struct_mutex and so we won't ever be able to observe an
+		 * object on the bound_list with a reference count equals 0.
+		 */
+		drm_gem_object_reference(&obj->base);
+
+		list_for_each_entry_safe(vma, v, &obj->vma_list, vma_link)
+			if (i915_vma_unbind(vma))
+				break;
+
+		if (i915_gem_object_put_pages(obj) == 0)
 			count += obj->base.size >> PAGE_SHIFT;
-			if (count >= target)
-				return count;
-		}
+
+		drm_gem_object_unreference(&obj->base);
 	}
+	list_splice(&still_bound_list, &dev_priv->mm.bound_list);
 
 	return count;
 }
@@ -1725,16 +1768,21 @@ i915_gem_purge(struct drm_i915_private *dev_priv, long target)
 	return __i915_gem_shrink(dev_priv, target, true);
 }
 
-static void
+static long
 i915_gem_shrink_all(struct drm_i915_private *dev_priv)
 {
 	struct drm_i915_gem_object *obj, *next;
+	long freed = 0;
 
 	i915_gem_evict_everything(dev_priv->dev);
 
 	list_for_each_entry_safe(obj, next, &dev_priv->mm.unbound_list,
-				 global_list)
+				 global_list) {
+		if (obj->pages_pin_count == 0)
+			freed += obj->base.size >> PAGE_SHIFT;
 		i915_gem_object_put_pages(obj);
+	}
+	return freed;
 }
 
 static int
@@ -1763,7 +1811,6 @@ i915_gem_object_get_pages_gtt(struct drm_i915_gem_object *obj)
 
 	page_count = obj->base.size / PAGE_SIZE;
 	if (sg_alloc_table(st, page_count, GFP_KERNEL)) {
-		sg_free_table(st);
 		kfree(st);
 		return -ENOMEM;
 	}
@@ -1892,8 +1939,6 @@ i915_gem_object_move_to_active(struct drm_i915_gem_object *obj,
 		obj->active = 1;
 	}
 
-	/* Move from whatever list we were on to the tail of execution. */
-	list_move_tail(&obj->mm_list, &dev_priv->mm.active_list);
 	list_move_tail(&obj->ring_list, &ring->active_list);
 
 	obj->last_read_seqno = seqno;
@@ -1915,13 +1960,14 @@ i915_gem_object_move_to_active(struct drm_i915_gem_object *obj,
 static void
 i915_gem_object_move_to_inactive(struct drm_i915_gem_object *obj)
 {
-	struct drm_device *dev = obj->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = obj->base.dev->dev_private;
+	struct i915_address_space *ggtt_vm = &dev_priv->gtt.base;
+	struct i915_vma *vma = i915_gem_obj_to_vma(obj, ggtt_vm);
 
 	BUG_ON(obj->base.write_domain & ~I915_GEM_GPU_DOMAINS);
 	BUG_ON(!obj->active);
 
-	list_move_tail(&obj->mm_list, &dev_priv->mm.inactive_list);
+	list_move_tail(&vma->mm_list, &ggtt_vm->inactive_list);
 
 	list_del_init(&obj->ring_list);
 	obj->ring = NULL;
@@ -2085,11 +2131,9 @@ int __i915_add_request(struct intel_ring_buffer *ring,
 	trace_i915_gem_request_add(ring, request->seqno);
 	ring->outstanding_lazy_request = 0;
 
-	if (!dev_priv->mm.suspended) {
-		if (i915_enable_hangcheck) {
-			mod_timer(&dev_priv->gpu_error.hangcheck_timer,
-				  round_jiffies_up(jiffies + DRM_I915_HANGCHECK_JIFFIES));
-		}
+	if (!dev_priv->ums.mm_suspended) {
+		i915_queue_hangcheck(ring->dev);
+
 		if (was_empty) {
 			queue_delayed_work(dev_priv->wq,
 					   &dev_priv->mm.retire_work,
@@ -2119,10 +2163,11 @@ i915_gem_request_remove_from_client(struct drm_i915_gem_request *request)
 	spin_unlock(&file_priv->mm.lock);
 }
 
-static bool i915_head_inside_object(u32 acthd, struct drm_i915_gem_object *obj)
+static bool i915_head_inside_object(u32 acthd, struct drm_i915_gem_object *obj,
+				    struct i915_address_space *vm)
 {
-	if (acthd >= obj->gtt_offset &&
-	    acthd < obj->gtt_offset + obj->base.size)
+	if (acthd >= i915_gem_obj_offset(obj, vm) &&
+	    acthd < i915_gem_obj_offset(obj, vm) + obj->base.size)
 		return true;
 
 	return false;
@@ -2145,6 +2190,17 @@ static bool i915_head_inside_request(const u32 acthd_unmasked,
 	return false;
 }
 
+static struct i915_address_space *
+request_to_vm(struct drm_i915_gem_request *request)
+{
+	struct drm_i915_private *dev_priv = request->ring->dev->dev_private;
+	struct i915_address_space *vm;
+
+	vm = &dev_priv->gtt.base;
+
+	return vm;
+}
+
 static bool i915_request_guilty(struct drm_i915_gem_request *request,
 				const u32 acthd, bool *inside)
 {
@@ -2152,9 +2208,9 @@ static bool i915_request_guilty(struct drm_i915_gem_request *request,
 	 * pointing inside the ring, matches the batch_obj address range.
 	 * However this is extremely unlikely.
 	 */
-
 	if (request->batch_obj) {
-		if (i915_head_inside_object(acthd, request->batch_obj)) {
+		if (i915_head_inside_object(acthd, request->batch_obj,
+					    request_to_vm(request))) {
 			*inside = true;
 			return true;
 		}
@@ -2174,17 +2230,21 @@ static void i915_set_reset_status(struct intel_ring_buffer *ring,
 {
 	struct i915_ctx_hang_stats *hs = NULL;
 	bool inside, guilty;
+	unsigned long offset = 0;
 
 	/* Innocent until proven guilty */
 	guilty = false;
 
-	if (ring->hangcheck.action != wait &&
+	if (request->batch_obj)
+		offset = i915_gem_obj_offset(request->batch_obj,
+					     request_to_vm(request));
+
+	if (ring->hangcheck.action != HANGCHECK_WAIT &&
 	    i915_request_guilty(request, acthd, &inside)) {
-		DRM_ERROR("%s hung %s bo (0x%x ctx %d) at 0x%x\n",
+		DRM_ERROR("%s hung %s bo (0x%lx ctx %d) at 0x%x\n",
 			  ring->name,
 			  inside ? "inside" : "flushing",
-			  request->batch_obj ?
-			  request->batch_obj->gtt_offset : 0,
+			  offset,
 			  request->ctx ? request->ctx->id : 0,
 			  acthd);
 
@@ -2275,23 +2335,12 @@ void i915_gem_restore_fences(struct drm_device *dev)
 void i915_gem_reset(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct drm_i915_gem_object *obj;
 	struct intel_ring_buffer *ring;
 	int i;
 
 	for_each_ring(ring, dev_priv, i)
 		i915_gem_reset_ring_lists(dev_priv, ring);
 
-	/* Move everything out of the GPU domains to ensure we do any
-	 * necessary invalidation upon reuse.
-	 */
-	list_for_each_entry(obj,
-			    &dev_priv->mm.inactive_list,
-			    mm_list)
-	{
-		obj->base.read_domains &= ~I915_GEM_GPU_DOMAINS;
-	}
-
 	i915_gem_restore_fences(dev);
 }
 
@@ -2400,7 +2449,7 @@ i915_gem_retire_work_handler(struct work_struct *work)
 		idle &= list_empty(&ring->request_list);
 	}
 
-	if (!dev_priv->mm.suspended && !idle)
+	if (!dev_priv->ums.mm_suspended && !idle)
 		queue_delayed_work(dev_priv->wq, &dev_priv->mm.retire_work,
 				   round_jiffies_up_relative(HZ));
 	if (idle)
@@ -2586,18 +2635,18 @@ static void i915_gem_object_finish_gtt(struct drm_i915_gem_object *obj)
 					    old_write_domain);
 }
 
-/**
- * Unbinds an object from the GTT aperture.
- */
-int
-i915_gem_object_unbind(struct drm_i915_gem_object *obj)
+int i915_vma_unbind(struct i915_vma *vma)
 {
+	struct drm_i915_gem_object *obj = vma->obj;
 	drm_i915_private_t *dev_priv = obj->base.dev->dev_private;
 	int ret;
 
-	if (obj->gtt_space == NULL)
+	if (list_empty(&vma->vma_link))
 		return 0;
 
+	if (!drm_mm_node_allocated(&vma->node))
+		goto destroy;
+
 	if (obj->pin_count)
 		return -EBUSY;
 
@@ -2618,7 +2667,7 @@ i915_gem_object_unbind(struct drm_i915_gem_object *obj)
 	if (ret)
 		return ret;
 
-	trace_i915_gem_object_unbind(obj);
+	trace_i915_vma_unbind(vma);
 
 	if (obj->has_global_gtt_mapping)
 		i915_gem_gtt_unbind_object(obj);
@@ -2629,18 +2678,46 @@ i915_gem_object_unbind(struct drm_i915_gem_object *obj)
 	i915_gem_gtt_finish_object(obj);
 	i915_gem_object_unpin_pages(obj);
 
-	list_del(&obj->mm_list);
-	list_move_tail(&obj->global_list, &dev_priv->mm.unbound_list);
+	list_del(&vma->mm_list);
 	/* Avoid an unnecessary call to unbind on rebind. */
-	obj->map_and_fenceable = true;
+	if (i915_is_ggtt(vma->vm))
+		obj->map_and_fenceable = true;
 
-	drm_mm_put_block(obj->gtt_space);
-	obj->gtt_space = NULL;
-	obj->gtt_offset = 0;
+	drm_mm_remove_node(&vma->node);
+
+destroy:
+	i915_gem_vma_destroy(vma);
+
+	/* Since the unbound list is global, only move to that list if
+	 * no more VMAs exist.
+	 * NB: Until we have real VMAs there will only ever be one */
+	WARN_ON(!list_empty(&obj->vma_list));
+	if (list_empty(&obj->vma_list))
+		list_move_tail(&obj->global_list, &dev_priv->mm.unbound_list);
 
 	return 0;
 }
 
+/**
+ * Unbinds an object from the global GTT aperture.
+ */
+int
+i915_gem_object_ggtt_unbind(struct drm_i915_gem_object *obj)
+{
+	struct drm_i915_private *dev_priv = obj->base.dev->dev_private;
+	struct i915_address_space *ggtt = &dev_priv->gtt.base;
+
+	if (!i915_gem_obj_ggtt_bound(obj))
+		return 0;
+
+	if (obj->pin_count)
+		return -EBUSY;
+
+	BUG_ON(obj->pages == NULL);
+
+	return i915_vma_unbind(i915_gem_obj_to_vma(obj, ggtt));
+}
+
 int i915_gpu_idle(struct drm_device *dev)
 {
 	drm_i915_private_t *dev_priv = dev->dev_private;
@@ -2691,12 +2768,12 @@ static void i965_write_fence_reg(struct drm_device *dev, int reg,
 	POSTING_READ(fence_reg);
 
 	if (obj) {
-		u32 size = obj->gtt_space->size;
+		u32 size = i915_gem_obj_ggtt_size(obj);
 		uint64_t val;
 
-		val = (uint64_t)((obj->gtt_offset + size - 4096) &
+		val = (uint64_t)((i915_gem_obj_ggtt_offset(obj) + size - 4096) &
 				 0xfffff000) << 32;
-		val |= obj->gtt_offset & 0xfffff000;
+		val |= i915_gem_obj_ggtt_offset(obj) & 0xfffff000;
 		val |= (uint64_t)((obj->stride / 128) - 1) << fence_pitch_shift;
 		if (obj->tiling_mode == I915_TILING_Y)
 			val |= 1 << I965_FENCE_TILING_Y_SHIFT;
@@ -2720,15 +2797,15 @@ static void i915_write_fence_reg(struct drm_device *dev, int reg,
 	u32 val;
 
 	if (obj) {
-		u32 size = obj->gtt_space->size;
+		u32 size = i915_gem_obj_ggtt_size(obj);
 		int pitch_val;
 		int tile_width;
 
-		WARN((obj->gtt_offset & ~I915_FENCE_START_MASK) ||
+		WARN((i915_gem_obj_ggtt_offset(obj) & ~I915_FENCE_START_MASK) ||
 		     (size & -size) != size ||
-		     (obj->gtt_offset & (size - 1)),
-		     "object 0x%08x [fenceable? %d] not 1M or pot-size (0x%08x) aligned\n",
-		     obj->gtt_offset, obj->map_and_fenceable, size);
+		     (i915_gem_obj_ggtt_offset(obj) & (size - 1)),
+		     "object 0x%08lx [fenceable? %d] not 1M or pot-size (0x%08x) aligned\n",
+		     i915_gem_obj_ggtt_offset(obj), obj->map_and_fenceable, size);
 
 		if (obj->tiling_mode == I915_TILING_Y && HAS_128_BYTE_Y_TILING(dev))
 			tile_width = 128;
@@ -2739,7 +2816,7 @@ static void i915_write_fence_reg(struct drm_device *dev, int reg,
 		pitch_val = obj->stride / tile_width;
 		pitch_val = ffs(pitch_val) - 1;
 
-		val = obj->gtt_offset;
+		val = i915_gem_obj_ggtt_offset(obj);
 		if (obj->tiling_mode == I915_TILING_Y)
 			val |= 1 << I830_FENCE_TILING_Y_SHIFT;
 		val |= I915_FENCE_SIZE_BITS(size);
@@ -2764,19 +2841,19 @@ static void i830_write_fence_reg(struct drm_device *dev, int reg,
 	uint32_t val;
 
 	if (obj) {
-		u32 size = obj->gtt_space->size;
+		u32 size = i915_gem_obj_ggtt_size(obj);
 		uint32_t pitch_val;
 
-		WARN((obj->gtt_offset & ~I830_FENCE_START_MASK) ||
+		WARN((i915_gem_obj_ggtt_offset(obj) & ~I830_FENCE_START_MASK) ||
 		     (size & -size) != size ||
-		     (obj->gtt_offset & (size - 1)),
-		     "object 0x%08x not 512K or pot-size 0x%08x aligned\n",
-		     obj->gtt_offset, size);
+		     (i915_gem_obj_ggtt_offset(obj) & (size - 1)),
+		     "object 0x%08lx not 512K or pot-size 0x%08x aligned\n",
+		     i915_gem_obj_ggtt_offset(obj), size);
 
 		pitch_val = obj->stride / 128;
 		pitch_val = ffs(pitch_val) - 1;
 
-		val = obj->gtt_offset;
+		val = i915_gem_obj_ggtt_offset(obj);
 		if (obj->tiling_mode == I915_TILING_Y)
 			val |= 1 << I830_FENCE_TILING_Y_SHIFT;
 		val |= I830_FENCE_SIZE_BITS(size);
@@ -2997,7 +3074,7 @@ static bool i915_gem_valid_gtt_space(struct drm_device *dev,
 	if (HAS_LLC(dev))
 		return true;
 
-	if (gtt_space == NULL)
+	if (!drm_mm_node_allocated(gtt_space))
 		return true;
 
 	if (list_empty(&gtt_space->node_list))
@@ -3030,8 +3107,8 @@ static void i915_gem_verify_gtt(struct drm_device *dev)
 
 		if (obj->cache_level != obj->gtt_space->color) {
 			printk(KERN_ERR "object reserved space [%08lx, %08lx] with wrong color, cache_level=%x, color=%lx\n",
-			       obj->gtt_space->start,
-			       obj->gtt_space->start + obj->gtt_space->size,
+			       i915_gem_obj_ggtt_offset(obj),
+			       i915_gem_obj_ggtt_offset(obj) + i915_gem_obj_ggtt_size(obj),
 			       obj->cache_level,
 			       obj->gtt_space->color);
 			err++;
@@ -3042,8 +3119,8 @@ static void i915_gem_verify_gtt(struct drm_device *dev)
 					      obj->gtt_space,
 					      obj->cache_level)) {
 			printk(KERN_ERR "invalid GTT space found at [%08lx, %08lx] - color=%x\n",
-			       obj->gtt_space->start,
-			       obj->gtt_space->start + obj->gtt_space->size,
+			       i915_gem_obj_ggtt_offset(obj),
+			       i915_gem_obj_ggtt_offset(obj) + i915_gem_obj_ggtt_size(obj),
 			       obj->cache_level);
 			err++;
 			continue;
@@ -3058,18 +3135,18 @@ static void i915_gem_verify_gtt(struct drm_device *dev)
  * Finds free space in the GTT aperture and binds the object there.
  */
 static int
-i915_gem_object_bind_to_gtt(struct drm_i915_gem_object *obj,
-			    unsigned alignment,
-			    bool map_and_fenceable,
-			    bool nonblocking)
+i915_gem_object_bind_to_vm(struct drm_i915_gem_object *obj,
+			   struct i915_address_space *vm,
+			   unsigned alignment,
+			   bool map_and_fenceable,
+			   bool nonblocking)
 {
 	struct drm_device *dev = obj->base.dev;
 	drm_i915_private_t *dev_priv = dev->dev_private;
-	struct drm_mm_node *node;
 	u32 size, fence_size, fence_alignment, unfenced_alignment;
-	bool mappable, fenceable;
-	size_t gtt_max = map_and_fenceable ?
-		dev_priv->gtt.mappable_end : dev_priv->gtt.total;
+	size_t gtt_max =
+		map_and_fenceable ? dev_priv->gtt.mappable_end : vm->total;
+	struct i915_vma *vma;
 	int ret;
 
 	fence_size = i915_gem_get_gtt_size(dev,
@@ -3110,77 +3187,89 @@ i915_gem_object_bind_to_gtt(struct drm_i915_gem_object *obj,
 
 	i915_gem_object_pin_pages(obj);
 
-	node = kzalloc(sizeof(*node), GFP_KERNEL);
-	if (node == NULL) {
-		i915_gem_object_unpin_pages(obj);
-		return -ENOMEM;
+	BUG_ON(!i915_is_ggtt(vm));
+
+	vma = i915_gem_obj_lookup_or_create_vma(obj, vm);
+	if (IS_ERR(vma)) {
+		ret = PTR_ERR(vma);
+		goto err_unpin;
 	}
 
+	/* For now we only ever use 1 vma per object */
+	WARN_ON(!list_is_singular(&obj->vma_list));
+
 search_free:
-	ret = drm_mm_insert_node_in_range_generic(&dev_priv->mm.gtt_space, node,
+	ret = drm_mm_insert_node_in_range_generic(&vm->mm, &vma->node,
 						  size, alignment,
-						  obj->cache_level, 0, gtt_max);
+						  obj->cache_level, 0, gtt_max,
+						  DRM_MM_SEARCH_DEFAULT);
 	if (ret) {
-		ret = i915_gem_evict_something(dev, size, alignment,
+		ret = i915_gem_evict_something(dev, vm, size, alignment,
 					       obj->cache_level,
 					       map_and_fenceable,
 					       nonblocking);
 		if (ret == 0)
 			goto search_free;
 
-		i915_gem_object_unpin_pages(obj);
-		kfree(node);
-		return ret;
+		goto err_free_vma;
 	}
-	if (WARN_ON(!i915_gem_valid_gtt_space(dev, node, obj->cache_level))) {
-		i915_gem_object_unpin_pages(obj);
-		drm_mm_put_block(node);
-		return -EINVAL;
+	if (WARN_ON(!i915_gem_valid_gtt_space(dev, &vma->node,
+					      obj->cache_level))) {
+		ret = -EINVAL;
+		goto err_remove_node;
 	}
 
 	ret = i915_gem_gtt_prepare_object(obj);
-	if (ret) {
-		i915_gem_object_unpin_pages(obj);
-		drm_mm_put_block(node);
-		return ret;
-	}
+	if (ret)
+		goto err_remove_node;
 
 	list_move_tail(&obj->global_list, &dev_priv->mm.bound_list);
-	list_add_tail(&obj->mm_list, &dev_priv->mm.inactive_list);
+	list_add_tail(&vma->mm_list, &vm->inactive_list);
 
-	obj->gtt_space = node;
-	obj->gtt_offset = node->start;
+	if (i915_is_ggtt(vm)) {
+		bool mappable, fenceable;
 
-	fenceable =
-		node->size == fence_size &&
-		(node->start & (fence_alignment - 1)) == 0;
+		fenceable = (vma->node.size == fence_size &&
+			     (vma->node.start & (fence_alignment - 1)) == 0);
 
-	mappable =
-		obj->gtt_offset + obj->base.size <= dev_priv->gtt.mappable_end;
+		mappable = (vma->node.start + obj->base.size <=
+			    dev_priv->gtt.mappable_end);
 
-	obj->map_and_fenceable = mappable && fenceable;
+		obj->map_and_fenceable = mappable && fenceable;
+	}
+
+	WARN_ON(map_and_fenceable && !obj->map_and_fenceable);
 
-	trace_i915_gem_object_bind(obj, map_and_fenceable);
+	trace_i915_vma_bind(vma, map_and_fenceable);
 	i915_gem_verify_gtt(dev);
 	return 0;
+
+err_remove_node:
+	drm_mm_remove_node(&vma->node);
+err_free_vma:
+	i915_gem_vma_destroy(vma);
+err_unpin:
+	i915_gem_object_unpin_pages(obj);
+	return ret;
 }
 
-void
-i915_gem_clflush_object(struct drm_i915_gem_object *obj)
+bool
+i915_gem_clflush_object(struct drm_i915_gem_object *obj,
+			bool force)
 {
 	/* If we don't have a page list set up, then we're not pinned
 	 * to GPU, and we can ignore the cache flush because it'll happen
 	 * again at bind time.
 	 */
 	if (obj->pages == NULL)
-		return;
+		return false;
 
 	/*
 	 * Stolen memory is always coherent with the GPU as it is explicitly
 	 * marked as wc by the system, or the system is cache-coherent.
 	 */
 	if (obj->stolen)
-		return;
+		return false;
 
 	/* If the GPU is snooping the contents of the CPU cache,
 	 * we do not need to manually clear the CPU cache lines.  However,
@@ -3190,12 +3279,13 @@ i915_gem_clflush_object(struct drm_i915_gem_object *obj)
 	 * snooping behaviour occurs naturally as the result of our domain
 	 * tracking.
 	 */
-	if (obj->cache_level != I915_CACHE_NONE)
-		return;
+	if (!force && cpu_cache_is_coherent(obj->base.dev, obj->cache_level))
+		return false;
 
 	trace_i915_gem_object_clflush(obj);
-
 	drm_clflush_sg(obj->pages);
+
+	return true;
 }
 
 /** Flushes the GTT write domain for the object if it's dirty. */
@@ -3227,15 +3317,17 @@ i915_gem_object_flush_gtt_write_domain(struct drm_i915_gem_object *obj)
 
 /** Flushes the CPU write domain for the object if it's dirty. */
 static void
-i915_gem_object_flush_cpu_write_domain(struct drm_i915_gem_object *obj)
+i915_gem_object_flush_cpu_write_domain(struct drm_i915_gem_object *obj,
+				       bool force)
 {
 	uint32_t old_write_domain;
 
 	if (obj->base.write_domain != I915_GEM_DOMAIN_CPU)
 		return;
 
-	i915_gem_clflush_object(obj);
-	i915_gem_chipset_flush(obj->base.dev);
+	if (i915_gem_clflush_object(obj, force))
+		i915_gem_chipset_flush(obj->base.dev);
+
 	old_write_domain = obj->base.write_domain;
 	obj->base.write_domain = 0;
 
@@ -3258,7 +3350,7 @@ i915_gem_object_set_to_gtt_domain(struct drm_i915_gem_object *obj, bool write)
 	int ret;
 
 	/* Not valid to be called on unbound objects. */
-	if (obj->gtt_space == NULL)
+	if (!i915_gem_obj_bound_any(obj))
 		return -EINVAL;
 
 	if (obj->base.write_domain == I915_GEM_DOMAIN_GTT)
@@ -3268,7 +3360,7 @@ i915_gem_object_set_to_gtt_domain(struct drm_i915_gem_object *obj, bool write)
 	if (ret)
 		return ret;
 
-	i915_gem_object_flush_cpu_write_domain(obj);
+	i915_gem_object_flush_cpu_write_domain(obj, false);
 
 	/* Serialise direct access to this object with the barriers for
 	 * coherent writes from the GPU, by effectively invalidating the
@@ -3296,8 +3388,14 @@ i915_gem_object_set_to_gtt_domain(struct drm_i915_gem_object *obj, bool write)
 					    old_write_domain);
 
 	/* And bump the LRU for this access */
-	if (i915_gem_object_is_inactive(obj))
-		list_move_tail(&obj->mm_list, &dev_priv->mm.inactive_list);
+	if (i915_gem_object_is_inactive(obj)) {
+		struct i915_vma *vma = i915_gem_obj_to_vma(obj,
+							   &dev_priv->gtt.base);
+		if (vma)
+			list_move_tail(&vma->mm_list,
+				       &dev_priv->gtt.base.inactive_list);
+
+	}
 
 	return 0;
 }
@@ -3307,6 +3405,7 @@ int i915_gem_object_set_cache_level(struct drm_i915_gem_object *obj,
 {
 	struct drm_device *dev = obj->base.dev;
 	drm_i915_private_t *dev_priv = dev->dev_private;
+	struct i915_vma *vma;
 	int ret;
 
 	if (obj->cache_level == cache_level)
@@ -3317,13 +3416,17 @@ int i915_gem_object_set_cache_level(struct drm_i915_gem_object *obj,
 		return -EBUSY;
 	}
 
-	if (!i915_gem_valid_gtt_space(dev, obj->gtt_space, cache_level)) {
-		ret = i915_gem_object_unbind(obj);
-		if (ret)
-			return ret;
+	list_for_each_entry(vma, &obj->vma_list, vma_link) {
+		if (!i915_gem_valid_gtt_space(dev, &vma->node, cache_level)) {
+			ret = i915_vma_unbind(vma);
+			if (ret)
+				return ret;
+
+			break;
+		}
 	}
 
-	if (obj->gtt_space) {
+	if (i915_gem_obj_bound_any(obj)) {
 		ret = i915_gem_object_finish_gpu(obj);
 		if (ret)
 			return ret;
@@ -3345,11 +3448,13 @@ int i915_gem_object_set_cache_level(struct drm_i915_gem_object *obj,
 		if (obj->has_aliasing_ppgtt_mapping)
 			i915_ppgtt_bind_object(dev_priv->mm.aliasing_ppgtt,
 					       obj, cache_level);
-
-		obj->gtt_space->color = cache_level;
 	}
 
-	if (cache_level == I915_CACHE_NONE) {
+	list_for_each_entry(vma, &obj->vma_list, vma_link)
+		vma->node.color = cache_level;
+	obj->cache_level = cache_level;
+
+	if (cpu_write_needs_clflush(obj)) {
 		u32 old_read_domains, old_write_domain;
 
 		/* If we're coming from LLC cached, then we haven't
@@ -3359,7 +3464,6 @@ int i915_gem_object_set_cache_level(struct drm_i915_gem_object *obj,
 		 * Just set it to the CPU cache for now.
 		 */
 		WARN_ON(obj->base.write_domain & ~I915_GEM_DOMAIN_CPU);
-		WARN_ON(obj->base.read_domains & ~I915_GEM_DOMAIN_CPU);
 
 		old_read_domains = obj->base.read_domains;
 		old_write_domain = obj->base.write_domain;
@@ -3372,7 +3476,6 @@ int i915_gem_object_set_cache_level(struct drm_i915_gem_object *obj,
 						    old_write_domain);
 	}
 
-	obj->cache_level = cache_level;
 	i915_gem_verify_gtt(dev);
 	return 0;
 }
@@ -3394,7 +3497,20 @@ int i915_gem_get_caching_ioctl(struct drm_device *dev, void *data,
 		goto unlock;
 	}
 
-	args->caching = obj->cache_level != I915_CACHE_NONE;
+	switch (obj->cache_level) {
+	case I915_CACHE_LLC:
+	case I915_CACHE_L3_LLC:
+		args->caching = I915_CACHING_CACHED;
+		break;
+
+	case I915_CACHE_WT:
+		args->caching = I915_CACHING_DISPLAY;
+		break;
+
+	default:
+		args->caching = I915_CACHING_NONE;
+		break;
+	}
 
 	drm_gem_object_unreference(&obj->base);
 unlock:
@@ -3417,6 +3533,9 @@ int i915_gem_set_caching_ioctl(struct drm_device *dev, void *data,
 	case I915_CACHING_CACHED:
 		level = I915_CACHE_LLC;
 		break;
+	case I915_CACHING_DISPLAY:
+		level = HAS_WT(dev) ? I915_CACHE_WT : I915_CACHE_NONE;
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -3439,6 +3558,22 @@ unlock:
 	return ret;
 }
 
+static bool is_pin_display(struct drm_i915_gem_object *obj)
+{
+	/* There are 3 sources that pin objects:
+	 *   1. The display engine (scanouts, sprites, cursors);
+	 *   2. Reservations for execbuffer;
+	 *   3. The user.
+	 *
+	 * We can ignore reservations as we hold the struct_mutex and
+	 * are only called outside of the reservation path.  The user
+	 * can only increment pin_count once, and so if after
+	 * subtracting the potential reference by the user, any pin_count
+	 * remains, it must be due to another use by the display engine.
+	 */
+	return obj->pin_count - !!obj->user_pin_count;
+}
+
 /*
  * Prepare buffer for display plane (scanout, cursors, etc).
  * Can be called from an uninterruptible phase (modesetting) and allows
@@ -3458,6 +3593,11 @@ i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj,
 			return ret;
 	}
 
+	/* Mark the pin_display early so that we account for the
+	 * display coherency whilst setting up the cache domains.
+	 */
+	obj->pin_display = true;
+
 	/* The display engine is not coherent with the LLC cache on gen6.  As
 	 * a result, we make sure that the pinning that is about to occur is
 	 * done with uncached PTEs. This is lowest common denominator for all
@@ -3467,19 +3607,20 @@ i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj,
 	 * of uncaching, which would allow us to flush all the LLC-cached data
 	 * with that bit in the PTE to main memory with just one PIPE_CONTROL.
 	 */
-	ret = i915_gem_object_set_cache_level(obj, I915_CACHE_NONE);
+	ret = i915_gem_object_set_cache_level(obj,
+					      HAS_WT(obj->base.dev) ? I915_CACHE_WT : I915_CACHE_NONE);
 	if (ret)
-		return ret;
+		goto err_unpin_display;
 
 	/* As the user may map the buffer once pinned in the display plane
 	 * (e.g. libkms for the bootup splash), we have to ensure that we
 	 * always use map_and_fenceable for all scanout buffers.
 	 */
-	ret = i915_gem_object_pin(obj, alignment, true, false);
+	ret = i915_gem_obj_ggtt_pin(obj, alignment, true, false);
 	if (ret)
-		return ret;
+		goto err_unpin_display;
 
-	i915_gem_object_flush_cpu_write_domain(obj);
+	i915_gem_object_flush_cpu_write_domain(obj, true);
 
 	old_write_domain = obj->base.write_domain;
 	old_read_domains = obj->base.read_domains;
@@ -3495,6 +3636,17 @@ i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj,
 					    old_write_domain);
 
 	return 0;
+
+err_unpin_display:
+	obj->pin_display = is_pin_display(obj);
+	return ret;
+}
+
+void
+i915_gem_object_unpin_from_display_plane(struct drm_i915_gem_object *obj)
+{
+	i915_gem_object_unpin(obj);
+	obj->pin_display = is_pin_display(obj);
 }
 
 int
@@ -3540,7 +3692,7 @@ i915_gem_object_set_to_cpu_domain(struct drm_i915_gem_object *obj, bool write)
 
 	/* Flush the CPU cache if it's still invalid. */
 	if ((obj->base.read_domains & I915_GEM_DOMAIN_CPU) == 0) {
-		i915_gem_clflush_object(obj);
+		i915_gem_clflush_object(obj, false);
 
 		obj->base.read_domains |= I915_GEM_DOMAIN_CPU;
 	}
@@ -3618,37 +3770,44 @@ i915_gem_ring_throttle(struct drm_device *dev, struct drm_file *file)
 
 int
 i915_gem_object_pin(struct drm_i915_gem_object *obj,
+		    struct i915_address_space *vm,
 		    uint32_t alignment,
 		    bool map_and_fenceable,
 		    bool nonblocking)
 {
+	struct i915_vma *vma;
 	int ret;
 
 	if (WARN_ON(obj->pin_count == DRM_I915_GEM_OBJECT_MAX_PIN_COUNT))
 		return -EBUSY;
 
-	if (obj->gtt_space != NULL) {
-		if ((alignment && obj->gtt_offset & (alignment - 1)) ||
+	WARN_ON(map_and_fenceable && !i915_is_ggtt(vm));
+
+	vma = i915_gem_obj_to_vma(obj, vm);
+
+	if (vma) {
+		if ((alignment &&
+		     vma->node.start & (alignment - 1)) ||
 		    (map_and_fenceable && !obj->map_and_fenceable)) {
 			WARN(obj->pin_count,
 			     "bo is already pinned with incorrect alignment:"
-			     " offset=%x, req.alignment=%x, req.map_and_fenceable=%d,"
+			     " offset=%lx, req.alignment=%x, req.map_and_fenceable=%d,"
 			     " obj->map_and_fenceable=%d\n",
-			     obj->gtt_offset, alignment,
+			     i915_gem_obj_offset(obj, vm), alignment,
 			     map_and_fenceable,
 			     obj->map_and_fenceable);
-			ret = i915_gem_object_unbind(obj);
+			ret = i915_vma_unbind(vma);
 			if (ret)
 				return ret;
 		}
 	}
 
-	if (obj->gtt_space == NULL) {
+	if (!i915_gem_obj_bound(obj, vm)) {
 		struct drm_i915_private *dev_priv = obj->base.dev->dev_private;
 
-		ret = i915_gem_object_bind_to_gtt(obj, alignment,
-						  map_and_fenceable,
-						  nonblocking);
+		ret = i915_gem_object_bind_to_vm(obj, vm, alignment,
+						 map_and_fenceable,
+						 nonblocking);
 		if (ret)
 			return ret;
 
@@ -3669,7 +3828,7 @@ void
 i915_gem_object_unpin(struct drm_i915_gem_object *obj)
 {
 	BUG_ON(obj->pin_count == 0);
-	BUG_ON(obj->gtt_space == NULL);
+	BUG_ON(!i915_gem_obj_bound_any(obj));
 
 	if (--obj->pin_count == 0)
 		obj->pin_mappable = false;
@@ -3707,7 +3866,7 @@ i915_gem_pin_ioctl(struct drm_device *dev, void *data,
 	}
 
 	if (obj->user_pin_count == 0) {
-		ret = i915_gem_object_pin(obj, args->alignment, true, false);
+		ret = i915_gem_obj_ggtt_pin(obj, args->alignment, true, false);
 		if (ret)
 			goto out;
 	}
@@ -3715,11 +3874,7 @@ i915_gem_pin_ioctl(struct drm_device *dev, void *data,
 	obj->user_pin_count++;
 	obj->pin_filp = file;
 
-	/* XXX - flush the CPU caches for pinned objects
-	 * as the X server doesn't manage domains yet
-	 */
-	i915_gem_object_flush_cpu_write_domain(obj);
-	args->offset = obj->gtt_offset;
+	args->offset = i915_gem_obj_ggtt_offset(obj);
 out:
 	drm_gem_object_unreference(&obj->base);
 unlock:
@@ -3858,10 +4013,11 @@ unlock:
 void i915_gem_object_init(struct drm_i915_gem_object *obj,
 			  const struct drm_i915_gem_object_ops *ops)
 {
-	INIT_LIST_HEAD(&obj->mm_list);
 	INIT_LIST_HEAD(&obj->global_list);
 	INIT_LIST_HEAD(&obj->ring_list);
 	INIT_LIST_HEAD(&obj->exec_list);
+	INIT_LIST_HEAD(&obj->obj_exec_link);
+	INIT_LIST_HEAD(&obj->vma_list);
 
 	obj->ops = ops;
 
@@ -3926,6 +4082,8 @@ struct drm_i915_gem_object *i915_gem_alloc_object(struct drm_device *dev,
 	} else
 		obj->cache_level = I915_CACHE_NONE;
 
+	trace_i915_gem_object_create(obj);
+
 	return obj;
 }
 
@@ -3941,6 +4099,7 @@ void i915_gem_free_object(struct drm_gem_object *gem_obj)
 	struct drm_i915_gem_object *obj = to_intel_bo(gem_obj);
 	struct drm_device *dev = obj->base.dev;
 	drm_i915_private_t *dev_priv = dev->dev_private;
+	struct i915_vma *vma, *next;
 
 	trace_i915_gem_object_destroy(obj);
 
@@ -3948,15 +4107,21 @@ void i915_gem_free_object(struct drm_gem_object *gem_obj)
 		i915_gem_detach_phys_object(dev, obj);
 
 	obj->pin_count = 0;
-	if (WARN_ON(i915_gem_object_unbind(obj) == -ERESTARTSYS)) {
-		bool was_interruptible;
+	/* NB: 0 or 1 elements */
+	WARN_ON(!list_empty(&obj->vma_list) &&
+		!list_is_singular(&obj->vma_list));
+	list_for_each_entry_safe(vma, next, &obj->vma_list, vma_link) {
+		int ret = i915_vma_unbind(vma);
+		if (WARN_ON(ret == -ERESTARTSYS)) {
+			bool was_interruptible;
 
-		was_interruptible = dev_priv->mm.interruptible;
-		dev_priv->mm.interruptible = false;
+			was_interruptible = dev_priv->mm.interruptible;
+			dev_priv->mm.interruptible = false;
 
-		WARN_ON(i915_gem_object_unbind(obj));
+			WARN_ON(i915_vma_unbind(vma));
 
-		dev_priv->mm.interruptible = was_interruptible;
+			dev_priv->mm.interruptible = was_interruptible;
+		}
 	}
 
 	/* Stolen objects don't hold a ref, but do hold pin count. Fix that up
@@ -3982,15 +4147,42 @@ void i915_gem_free_object(struct drm_gem_object *gem_obj)
 	i915_gem_object_free(obj);
 }
 
+struct i915_vma *i915_gem_vma_create(struct drm_i915_gem_object *obj,
+				     struct i915_address_space *vm)
+{
+	struct i915_vma *vma = kzalloc(sizeof(*vma), GFP_KERNEL);
+	if (vma == NULL)
+		return ERR_PTR(-ENOMEM);
+
+	INIT_LIST_HEAD(&vma->vma_link);
+	INIT_LIST_HEAD(&vma->mm_list);
+	INIT_LIST_HEAD(&vma->exec_list);
+	vma->vm = vm;
+	vma->obj = obj;
+
+	/* Keep GGTT vmas first to make debug easier */
+	if (i915_is_ggtt(vm))
+		list_add(&vma->vma_link, &obj->vma_list);
+	else
+		list_add_tail(&vma->vma_link, &obj->vma_list);
+
+	return vma;
+}
+
+void i915_gem_vma_destroy(struct i915_vma *vma)
+{
+	WARN_ON(vma->node.allocated);
+	list_del(&vma->vma_link);
+	kfree(vma);
+}
+
 int
 i915_gem_idle(struct drm_device *dev)
 {
 	drm_i915_private_t *dev_priv = dev->dev_private;
 	int ret;
 
-	mutex_lock(&dev->struct_mutex);
-
-	if (dev_priv->mm.suspended) {
+	if (dev_priv->ums.mm_suspended) {
 		mutex_unlock(&dev->struct_mutex);
 		return 0;
 	}
@@ -4006,18 +4198,11 @@ i915_gem_idle(struct drm_device *dev)
 	if (!drm_core_check_feature(dev, DRIVER_MODESET))
 		i915_gem_evict_everything(dev);
 
-	/* Hack!  Don't let anybody do execbuf while we don't control the chip.
-	 * We need to replace this with a semaphore, or something.
-	 * And not confound mm.suspended!
-	 */
-	dev_priv->mm.suspended = 1;
 	del_timer_sync(&dev_priv->gpu_error.hangcheck_timer);
 
 	i915_kernel_lost_context(dev);
 	i915_gem_cleanup_ringbuffer(dev);
 
-	mutex_unlock(&dev->struct_mutex);
-
 	/* Cancel the retire work handler, which should be idle now. */
 	cancel_delayed_work_sync(&dev_priv->mm.retire_work);
 
@@ -4150,8 +4335,8 @@ i915_gem_init_hw(struct drm_device *dev)
 	if (INTEL_INFO(dev)->gen < 6 && !intel_enable_gtt())
 		return -EIO;
 
-	if (IS_HASWELL(dev) && (I915_READ(0x120010) == 1))
-		I915_WRITE(0x9008, I915_READ(0x9008) | 0xf0000);
+	if (dev_priv->ellc_size)
+		I915_WRITE(HSW_IDICR, I915_READ(HSW_IDICR) | IDIHASHMSK(0xf));
 
 	if (HAS_PCH_NOP(dev)) {
 		u32 temp = I915_READ(GEN7_MSG_CTL);
@@ -4227,7 +4412,7 @@ int
 i915_gem_entervt_ioctl(struct drm_device *dev, void *data,
 		       struct drm_file *file_priv)
 {
-	drm_i915_private_t *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = dev->dev_private;
 	int ret;
 
 	if (drm_core_check_feature(dev, DRIVER_MODESET))
@@ -4239,7 +4424,7 @@ i915_gem_entervt_ioctl(struct drm_device *dev, void *data,
 	}
 
 	mutex_lock(&dev->struct_mutex);
-	dev_priv->mm.suspended = 0;
+	dev_priv->ums.mm_suspended = 0;
 
 	ret = i915_gem_init_hw(dev);
 	if (ret != 0) {
@@ -4247,7 +4432,7 @@ i915_gem_entervt_ioctl(struct drm_device *dev, void *data,
 		return ret;
 	}
 
-	BUG_ON(!list_empty(&dev_priv->mm.active_list));
+	BUG_ON(!list_empty(&dev_priv->gtt.base.active_list));
 	mutex_unlock(&dev->struct_mutex);
 
 	ret = drm_irq_install(dev);
@@ -4259,7 +4444,7 @@ i915_gem_entervt_ioctl(struct drm_device *dev, void *data,
 cleanup_ringbuffer:
 	mutex_lock(&dev->struct_mutex);
 	i915_gem_cleanup_ringbuffer(dev);
-	dev_priv->mm.suspended = 1;
+	dev_priv->ums.mm_suspended = 1;
 	mutex_unlock(&dev->struct_mutex);
 
 	return ret;
@@ -4269,11 +4454,26 @@ int
 i915_gem_leavevt_ioctl(struct drm_device *dev, void *data,
 		       struct drm_file *file_priv)
 {
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	int ret;
+
 	if (drm_core_check_feature(dev, DRIVER_MODESET))
 		return 0;
 
 	drm_irq_uninstall(dev);
-	return i915_gem_idle(dev);
+
+	mutex_lock(&dev->struct_mutex);
+	ret =  i915_gem_idle(dev);
+
+	/* Hack!  Don't let anybody do execbuf while we don't control the chip.
+	 * We need to replace this with a semaphore, or something.
+	 * And not confound ums.mm_suspended!
+	 */
+	if (ret != 0)
+		dev_priv->ums.mm_suspended = 1;
+	mutex_unlock(&dev->struct_mutex);
+
+	return ret;
 }
 
 void
@@ -4284,9 +4484,11 @@ i915_gem_lastclose(struct drm_device *dev)
 	if (drm_core_check_feature(dev, DRIVER_MODESET))
 		return;
 
+	mutex_lock(&dev->struct_mutex);
 	ret = i915_gem_idle(dev);
 	if (ret)
 		DRM_ERROR("failed to idle hardware: %d\n", ret);
+	mutex_unlock(&dev->struct_mutex);
 }
 
 static void
@@ -4296,6 +4498,16 @@ init_ring_lists(struct intel_ring_buffer *ring)
 	INIT_LIST_HEAD(&ring->request_list);
 }
 
+static void i915_init_vm(struct drm_i915_private *dev_priv,
+			 struct i915_address_space *vm)
+{
+	vm->dev = dev_priv->dev;
+	INIT_LIST_HEAD(&vm->active_list);
+	INIT_LIST_HEAD(&vm->inactive_list);
+	INIT_LIST_HEAD(&vm->global_link);
+	list_add(&vm->global_link, &dev_priv->vm_list);
+}
+
 void
 i915_gem_load(struct drm_device *dev)
 {
@@ -4308,8 +4520,9 @@ i915_gem_load(struct drm_device *dev)
 				  SLAB_HWCACHE_ALIGN,
 				  NULL);
 
-	INIT_LIST_HEAD(&dev_priv->mm.active_list);
-	INIT_LIST_HEAD(&dev_priv->mm.inactive_list);
+	INIT_LIST_HEAD(&dev_priv->vm_list);
+	i915_init_vm(dev_priv, &dev_priv->gtt.base);
+
 	INIT_LIST_HEAD(&dev_priv->mm.unbound_list);
 	INIT_LIST_HEAD(&dev_priv->mm.bound_list);
 	INIT_LIST_HEAD(&dev_priv->mm.fence_list);
@@ -4349,7 +4562,8 @@ i915_gem_load(struct drm_device *dev)
 
 	dev_priv->mm.interruptible = true;
 
-	dev_priv->mm.inactive_shrinker.shrink = i915_gem_inactive_shrink;
+	dev_priv->mm.inactive_shrinker.scan_objects = i915_gem_inactive_scan;
+	dev_priv->mm.inactive_shrinker.count_objects = i915_gem_inactive_count;
 	dev_priv->mm.inactive_shrinker.seeks = DEFAULT_SEEKS;
 	register_shrinker(&dev_priv->mm.inactive_shrinker);
 }
@@ -4572,8 +4786,8 @@ static bool mutex_is_locked_by(struct mutex *mutex, struct task_struct *task)
 #endif
 }
 
-static int
-i915_gem_inactive_shrink(struct shrinker *shrinker, struct shrink_control *sc)
+static unsigned long
+i915_gem_inactive_count(struct shrinker *shrinker, struct shrink_control *sc)
 {
 	struct drm_i915_private *dev_priv =
 		container_of(shrinker,
@@ -4581,9 +4795,8 @@ i915_gem_inactive_shrink(struct shrinker *shrinker, struct shrink_control *sc)
 			     mm.inactive_shrinker);
 	struct drm_device *dev = dev_priv->dev;
 	struct drm_i915_gem_object *obj;
-	int nr_to_scan = sc->nr_to_scan;
 	bool unlock = true;
-	int cnt;
+	unsigned long count;
 
 	if (!mutex_trylock(&dev->struct_mutex)) {
 		if (!mutex_is_locked_by(&dev->struct_mutex, current))
@@ -4595,24 +4808,139 @@ i915_gem_inactive_shrink(struct shrinker *shrinker, struct shrink_control *sc)
 		unlock = false;
 	}
 
-	if (nr_to_scan) {
-		nr_to_scan -= i915_gem_purge(dev_priv, nr_to_scan);
-		if (nr_to_scan > 0)
-			nr_to_scan -= __i915_gem_shrink(dev_priv, nr_to_scan,
-							false);
-		if (nr_to_scan > 0)
-			i915_gem_shrink_all(dev_priv);
-	}
-
-	cnt = 0;
+	count = 0;
 	list_for_each_entry(obj, &dev_priv->mm.unbound_list, global_list)
 		if (obj->pages_pin_count == 0)
-			cnt += obj->base.size >> PAGE_SHIFT;
-	list_for_each_entry(obj, &dev_priv->mm.inactive_list, mm_list)
+			count += obj->base.size >> PAGE_SHIFT;
+
+	list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) {
+		if (obj->active)
+			continue;
+
 		if (obj->pin_count == 0 && obj->pages_pin_count == 0)
-			cnt += obj->base.size >> PAGE_SHIFT;
+			count += obj->base.size >> PAGE_SHIFT;
+	}
+
+	if (unlock)
+		mutex_unlock(&dev->struct_mutex);
+	return count;
+}
+
+/* All the new VM stuff */
+unsigned long i915_gem_obj_offset(struct drm_i915_gem_object *o,
+				  struct i915_address_space *vm)
+{
+	struct drm_i915_private *dev_priv = o->base.dev->dev_private;
+	struct i915_vma *vma;
+
+	if (vm == &dev_priv->mm.aliasing_ppgtt->base)
+		vm = &dev_priv->gtt.base;
+
+	BUG_ON(list_empty(&o->vma_list));
+	list_for_each_entry(vma, &o->vma_list, vma_link) {
+		if (vma->vm == vm)
+			return vma->node.start;
+
+	}
+	return -1;
+}
+
+bool i915_gem_obj_bound(struct drm_i915_gem_object *o,
+			struct i915_address_space *vm)
+{
+	struct i915_vma *vma;
+
+	list_for_each_entry(vma, &o->vma_list, vma_link)
+		if (vma->vm == vm && drm_mm_node_allocated(&vma->node))
+			return true;
+
+	return false;
+}
+
+bool i915_gem_obj_bound_any(struct drm_i915_gem_object *o)
+{
+	struct drm_i915_private *dev_priv = o->base.dev->dev_private;
+	struct i915_address_space *vm;
+
+	list_for_each_entry(vm, &dev_priv->vm_list, global_link)
+		if (i915_gem_obj_bound(o, vm))
+			return true;
+
+	return false;
+}
+
+unsigned long i915_gem_obj_size(struct drm_i915_gem_object *o,
+				struct i915_address_space *vm)
+{
+	struct drm_i915_private *dev_priv = o->base.dev->dev_private;
+	struct i915_vma *vma;
+
+	if (vm == &dev_priv->mm.aliasing_ppgtt->base)
+		vm = &dev_priv->gtt.base;
+
+	BUG_ON(list_empty(&o->vma_list));
+
+	list_for_each_entry(vma, &o->vma_list, vma_link)
+		if (vma->vm == vm)
+			return vma->node.size;
+
+	return 0;
+}
+
+static unsigned long
+i915_gem_inactive_scan(struct shrinker *shrinker, struct shrink_control *sc)
+{
+	struct drm_i915_private *dev_priv =
+		container_of(shrinker,
+			     struct drm_i915_private,
+			     mm.inactive_shrinker);
+	struct drm_device *dev = dev_priv->dev;
+	int nr_to_scan = sc->nr_to_scan;
+	unsigned long freed;
+	bool unlock = true;
+
+	if (!mutex_trylock(&dev->struct_mutex)) {
+		if (!mutex_is_locked_by(&dev->struct_mutex, current))
+			return SHRINK_STOP;
+
+		if (dev_priv->mm.shrinker_no_lock_stealing)
+			return SHRINK_STOP;
+
+		unlock = false;
+	}
+
+	freed = i915_gem_purge(dev_priv, nr_to_scan);
+	if (freed < nr_to_scan)
+		freed += __i915_gem_shrink(dev_priv, nr_to_scan,
+							false);
+	if (freed < nr_to_scan)
+		freed += i915_gem_shrink_all(dev_priv);
 
 	if (unlock)
 		mutex_unlock(&dev->struct_mutex);
-	return cnt;
+	return freed;
+}
+
+struct i915_vma *i915_gem_obj_to_vma(struct drm_i915_gem_object *obj,
+				     struct i915_address_space *vm)
+{
+	struct i915_vma *vma;
+	list_for_each_entry(vma, &obj->vma_list, vma_link)
+		if (vma->vm == vm)
+			return vma;
+
+	return NULL;
+}
+
+struct i915_vma *
+i915_gem_obj_lookup_or_create_vma(struct drm_i915_gem_object *obj,
+				  struct i915_address_space *vm)
+{
+	struct i915_vma *vma;
+
+	vma = i915_gem_obj_to_vma(obj, vm);
+	if (!vma)
+		vma = i915_gem_vma_create(obj, vm);
+
+	return vma;
 }
diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index 51b7a2171cae..403309c2a7d6 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -155,7 +155,7 @@ create_hw_context(struct drm_device *dev,
 
 	if (INTEL_INFO(dev)->gen >= 7) {
 		ret = i915_gem_object_set_cache_level(ctx->obj,
-						      I915_CACHE_LLC_MLC);
+						      I915_CACHE_L3_LLC);
 		/* Failure shouldn't ever happen this early */
 		if (WARN_ON(ret))
 			goto err_out;
@@ -214,7 +214,7 @@ static int create_default_context(struct drm_i915_private *dev_priv)
 	 * default context.
 	 */
 	dev_priv->ring[RCS].default_context = ctx;
-	ret = i915_gem_object_pin(ctx->obj, CONTEXT_ALIGN, false, false);
+	ret = i915_gem_obj_ggtt_pin(ctx->obj, CONTEXT_ALIGN, false, false);
 	if (ret) {
 		DRM_DEBUG_DRIVER("Couldn't pin %d\n", ret);
 		goto err_destroy;
@@ -304,31 +304,24 @@ static int context_idr_cleanup(int id, void *p, void *data)
 }
 
 struct i915_ctx_hang_stats *
-i915_gem_context_get_hang_stats(struct intel_ring_buffer *ring,
+i915_gem_context_get_hang_stats(struct drm_device *dev,
 				struct drm_file *file,
 				u32 id)
 {
-	struct drm_i915_private *dev_priv = ring->dev->dev_private;
+	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_i915_file_private *file_priv = file->driver_priv;
-	struct i915_hw_context *to;
-
-	if (dev_priv->hw_contexts_disabled)
-		return ERR_PTR(-ENOENT);
-
-	if (ring->id != RCS)
-		return ERR_PTR(-EINVAL);
-
-	if (file == NULL)
-		return ERR_PTR(-EINVAL);
+	struct i915_hw_context *ctx;
 
 	if (id == DEFAULT_CONTEXT_ID)
 		return &file_priv->hang_stats;
 
-	to = i915_gem_context_get(file->driver_priv, id);
-	if (to == NULL)
+	ctx = NULL;
+	if (!dev_priv->hw_contexts_disabled)
+		ctx = i915_gem_context_get(file->driver_priv, id);
+	if (ctx == NULL)
 		return ERR_PTR(-ENOENT);
 
-	return &to->hang_stats;
+	return &ctx->hang_stats;
 }
 
 void i915_gem_context_close(struct drm_device *dev, struct drm_file *file)
@@ -377,7 +370,7 @@ mi_set_context(struct intel_ring_buffer *ring,
 
 	intel_ring_emit(ring, MI_NOOP);
 	intel_ring_emit(ring, MI_SET_CONTEXT);
-	intel_ring_emit(ring, new_context->obj->gtt_offset |
+	intel_ring_emit(ring, i915_gem_obj_ggtt_offset(new_context->obj) |
 			MI_MM_SPACE_GTT |
 			MI_SAVE_EXT_STATE_EN |
 			MI_RESTORE_EXT_STATE_EN |
@@ -407,7 +400,7 @@ static int do_switch(struct i915_hw_context *to)
 	if (from == to)
 		return 0;
 
-	ret = i915_gem_object_pin(to->obj, CONTEXT_ALIGN, false, false);
+	ret = i915_gem_obj_ggtt_pin(to->obj, CONTEXT_ALIGN, false, false);
 	if (ret)
 		return ret;
 
@@ -443,7 +436,10 @@ static int do_switch(struct i915_hw_context *to)
 	 * MI_SET_CONTEXT instead of when the next seqno has completed.
 	 */
 	if (from != NULL) {
+		struct drm_i915_private *dev_priv = from->obj->base.dev->dev_private;
+		struct i915_address_space *ggtt = &dev_priv->gtt.base;
 		from->obj->base.read_domains = I915_GEM_DOMAIN_INSTRUCTION;
+		list_move_tail(&i915_gem_obj_to_vma(from->obj, ggtt)->mm_list, &ggtt->active_list);
 		i915_gem_object_move_to_active(from->obj, ring);
 		/* As long as MI_SET_CONTEXT is serializing, ie. it flushes the
 		 * whole damn pipeline, we don't need to explicitly mark the
diff --git a/drivers/gpu/drm/i915/i915_gem_debug.c b/drivers/gpu/drm/i915/i915_gem_debug.c
index 582e6a5f3dac..775d506b3208 100644
--- a/drivers/gpu/drm/i915/i915_gem_debug.c
+++ b/drivers/gpu/drm/i915/i915_gem_debug.c
@@ -97,7 +97,7 @@ i915_verify_lists(struct drm_device *dev)
 		}
 	}
 
-	list_for_each_entry(obj, &dev_priv->mm.inactive_list, list) {
+	list_for_each_entry(obj, &i915_gtt_vm->inactive_list, list) {
 		if (obj->base.dev != dev ||
 		    !atomic_read(&obj->base.refcount.refcount)) {
 			DRM_ERROR("freed inactive %p\n", obj);
@@ -115,73 +115,4 @@ i915_verify_lists(struct drm_device *dev)
 
 	return warned = err;
 }
-#endif /* WATCH_INACTIVE */
-
-#if WATCH_COHERENCY
-void
-i915_gem_object_check_coherency(struct drm_i915_gem_object *obj, int handle)
-{
-	struct drm_device *dev = obj->base.dev;
-	int page;
-	uint32_t *gtt_mapping;
-	uint32_t *backing_map = NULL;
-	int bad_count = 0;
-
-	DRM_INFO("%s: checking coherency of object %p@0x%08x (%d, %zdkb):\n",
-		 __func__, obj, obj->gtt_offset, handle,
-		 obj->size / 1024);
-
-	gtt_mapping = ioremap(dev_priv->mm.gtt_base_addr + obj->gtt_offset,
-			      obj->base.size);
-	if (gtt_mapping == NULL) {
-		DRM_ERROR("failed to map GTT space\n");
-		return;
-	}
-
-	for (page = 0; page < obj->size / PAGE_SIZE; page++) {
-		int i;
-
-		backing_map = kmap_atomic(obj->pages[page]);
-
-		if (backing_map == NULL) {
-			DRM_ERROR("failed to map backing page\n");
-			goto out;
-		}
-
-		for (i = 0; i < PAGE_SIZE / 4; i++) {
-			uint32_t cpuval = backing_map[i];
-			uint32_t gttval = readl(gtt_mapping +
-						page * 1024 + i);
-
-			if (cpuval != gttval) {
-				DRM_INFO("incoherent CPU vs GPU at 0x%08x: "
-					 "0x%08x vs 0x%08x\n",
-					 (int)(obj->gtt_offset +
-					       page * PAGE_SIZE + i * 4),
-					 cpuval, gttval);
-				if (bad_count++ >= 8) {
-					DRM_INFO("...\n");
-					goto out;
-				}
-			}
-		}
-		kunmap_atomic(backing_map);
-		backing_map = NULL;
-	}
-
- out:
-	if (backing_map != NULL)
-		kunmap_atomic(backing_map);
-	iounmap(gtt_mapping);
-
-	/* give syslog time to catch up */
-	msleep(1);
-
-	/* Directly flush the object, since we just loaded values with the CPU
-	 * from the backing pages and we don't want to disturb the cache
-	 * management that we're trying to observe.
-	 */
-
-	i915_gem_clflush_object(obj);
-}
-#endif
+#endif /* WATCH_LIST */
diff --git a/drivers/gpu/drm/i915/i915_gem_dmabuf.c b/drivers/gpu/drm/i915/i915_gem_dmabuf.c
index 9e6578330801..7d5752fda5f1 100644
--- a/drivers/gpu/drm/i915/i915_gem_dmabuf.c
+++ b/drivers/gpu/drm/i915/i915_gem_dmabuf.c
@@ -27,37 +27,39 @@
 #include "i915_drv.h"
 #include <linux/dma-buf.h>
 
+static struct drm_i915_gem_object *dma_buf_to_obj(struct dma_buf *buf)
+{
+	return to_intel_bo(buf->priv);
+}
+
 static struct sg_table *i915_gem_map_dma_buf(struct dma_buf_attachment *attachment,
 					     enum dma_data_direction dir)
 {
-	struct drm_i915_gem_object *obj = attachment->dmabuf->priv;
+	struct drm_i915_gem_object *obj = dma_buf_to_obj(attachment->dmabuf);
 	struct sg_table *st;
 	struct scatterlist *src, *dst;
 	int ret, i;
 
 	ret = i915_mutex_lock_interruptible(obj->base.dev);
 	if (ret)
-		return ERR_PTR(ret);
+		goto err;
 
 	ret = i915_gem_object_get_pages(obj);
-	if (ret) {
-		st = ERR_PTR(ret);
-		goto out;
-	}
+	if (ret)
+		goto err_unlock;
+
+	i915_gem_object_pin_pages(obj);
 
 	/* Copy sg so that we make an independent mapping */
 	st = kmalloc(sizeof(struct sg_table), GFP_KERNEL);
 	if (st == NULL) {
-		st = ERR_PTR(-ENOMEM);
-		goto out;
+		ret = -ENOMEM;
+		goto err_unpin;
 	}
 
 	ret = sg_alloc_table(st, obj->pages->nents, GFP_KERNEL);
-	if (ret) {
-		kfree(st);
-		st = ERR_PTR(ret);
-		goto out;
-	}
+	if (ret)
+		goto err_free;
 
 	src = obj->pages->sgl;
 	dst = st->sgl;
@@ -68,24 +70,30 @@ static struct sg_table *i915_gem_map_dma_buf(struct dma_buf_attachment *attachme
 	}
 
 	if (!dma_map_sg(attachment->dev, st->sgl, st->nents, dir)) {
-		sg_free_table(st);
-		kfree(st);
-		st = ERR_PTR(-ENOMEM);
-		goto out;
+		ret =-ENOMEM;
+		goto err_free_sg;
 	}
 
-	i915_gem_object_pin_pages(obj);
-
-out:
 	mutex_unlock(&obj->base.dev->struct_mutex);
 	return st;
+
+err_free_sg:
+	sg_free_table(st);
+err_free:
+	kfree(st);
+err_unpin:
+	i915_gem_object_unpin_pages(obj);
+err_unlock:
+	mutex_unlock(&obj->base.dev->struct_mutex);
+err:
+	return ERR_PTR(ret);
 }
 
 static void i915_gem_unmap_dma_buf(struct dma_buf_attachment *attachment,
 				   struct sg_table *sg,
 				   enum dma_data_direction dir)
 {
-	struct drm_i915_gem_object *obj = attachment->dmabuf->priv;
+	struct drm_i915_gem_object *obj = dma_buf_to_obj(attachment->dmabuf);
 
 	mutex_lock(&obj->base.dev->struct_mutex);
 
@@ -98,20 +106,9 @@ static void i915_gem_unmap_dma_buf(struct dma_buf_attachment *attachment,
 	mutex_unlock(&obj->base.dev->struct_mutex);
 }
 
-static void i915_gem_dmabuf_release(struct dma_buf *dma_buf)
-{
-	struct drm_i915_gem_object *obj = dma_buf->priv;
-
-	if (obj->base.export_dma_buf == dma_buf) {
-		/* drop the reference on the export fd holds */
-		obj->base.export_dma_buf = NULL;
-		drm_gem_object_unreference_unlocked(&obj->base);
-	}
-}
-
 static void *i915_gem_dmabuf_vmap(struct dma_buf *dma_buf)
 {
-	struct drm_i915_gem_object *obj = dma_buf->priv;
+	struct drm_i915_gem_object *obj = dma_buf_to_obj(dma_buf);
 	struct drm_device *dev = obj->base.dev;
 	struct sg_page_iter sg_iter;
 	struct page **pages;
@@ -159,7 +156,7 @@ error:
 
 static void i915_gem_dmabuf_vunmap(struct dma_buf *dma_buf, void *vaddr)
 {
-	struct drm_i915_gem_object *obj = dma_buf->priv;
+	struct drm_i915_gem_object *obj = dma_buf_to_obj(dma_buf);
 	struct drm_device *dev = obj->base.dev;
 	int ret;
 
@@ -202,7 +199,7 @@ static int i915_gem_dmabuf_mmap(struct dma_buf *dma_buf, struct vm_area_struct *
 
 static int i915_gem_begin_cpu_access(struct dma_buf *dma_buf, size_t start, size_t length, enum dma_data_direction direction)
 {
-	struct drm_i915_gem_object *obj = dma_buf->priv;
+	struct drm_i915_gem_object *obj = dma_buf_to_obj(dma_buf);
 	struct drm_device *dev = obj->base.dev;
 	int ret;
 	bool write = (direction == DMA_BIDIRECTIONAL || direction == DMA_TO_DEVICE);
@@ -219,7 +216,7 @@ static int i915_gem_begin_cpu_access(struct dma_buf *dma_buf, size_t start, size
 static const struct dma_buf_ops i915_dmabuf_ops =  {
 	.map_dma_buf = i915_gem_map_dma_buf,
 	.unmap_dma_buf = i915_gem_unmap_dma_buf,
-	.release = i915_gem_dmabuf_release,
+	.release = drm_gem_dmabuf_release,
 	.kmap = i915_gem_dmabuf_kmap,
 	.kmap_atomic = i915_gem_dmabuf_kmap_atomic,
 	.kunmap = i915_gem_dmabuf_kunmap,
@@ -233,9 +230,7 @@ static const struct dma_buf_ops i915_dmabuf_ops =  {
 struct dma_buf *i915_gem_prime_export(struct drm_device *dev,
 				      struct drm_gem_object *gem_obj, int flags)
 {
-	struct drm_i915_gem_object *obj = to_intel_bo(gem_obj);
-
-	return dma_buf_export(obj, &i915_dmabuf_ops, obj->base.size, flags);
+	return dma_buf_export(gem_obj, &i915_dmabuf_ops, gem_obj->size, flags);
 }
 
 static int i915_gem_object_get_pages_dmabuf(struct drm_i915_gem_object *obj)
@@ -272,7 +267,7 @@ struct drm_gem_object *i915_gem_prime_import(struct drm_device *dev,
 
 	/* is this one of own objects? */
 	if (dma_buf->ops == &i915_dmabuf_ops) {
-		obj = dma_buf->priv;
+		obj = dma_buf_to_obj(dma_buf);
 		/* is it from our device? */
 		if (obj->base.dev == dev) {
 			/*
@@ -297,12 +292,7 @@ struct drm_gem_object *i915_gem_prime_import(struct drm_device *dev,
 		goto fail_detach;
 	}
 
-	ret = drm_gem_private_object_init(dev, &obj->base, dma_buf->size);
-	if (ret) {
-		i915_gem_object_free(obj);
-		goto fail_detach;
-	}
-
+	drm_gem_private_object_init(dev, &obj->base, dma_buf->size);
 	i915_gem_object_init(obj, &i915_gem_object_dmabuf_ops);
 	obj->base.import_attach = attach;
 
diff --git a/drivers/gpu/drm/i915/i915_gem_evict.c b/drivers/gpu/drm/i915/i915_gem_evict.c
index c86d5d9356fd..91b700155850 100644
--- a/drivers/gpu/drm/i915/i915_gem_evict.c
+++ b/drivers/gpu/drm/i915/i915_gem_evict.c
@@ -32,23 +32,23 @@
 #include "i915_trace.h"
 
 static bool
-mark_free(struct drm_i915_gem_object *obj, struct list_head *unwind)
+mark_free(struct i915_vma *vma, struct list_head *unwind)
 {
-	if (obj->pin_count)
+	if (vma->obj->pin_count)
 		return false;
 
-	list_add(&obj->exec_list, unwind);
-	return drm_mm_scan_add_block(obj->gtt_space);
+	list_add(&vma->exec_list, unwind);
+	return drm_mm_scan_add_block(&vma->node);
 }
 
 int
-i915_gem_evict_something(struct drm_device *dev, int min_size,
-			 unsigned alignment, unsigned cache_level,
+i915_gem_evict_something(struct drm_device *dev, struct i915_address_space *vm,
+			 int min_size, unsigned alignment, unsigned cache_level,
 			 bool mappable, bool nonblocking)
 {
 	drm_i915_private_t *dev_priv = dev->dev_private;
 	struct list_head eviction_list, unwind_list;
-	struct drm_i915_gem_object *obj;
+	struct i915_vma *vma;
 	int ret = 0;
 
 	trace_i915_gem_evict(dev, min_size, alignment, mappable);
@@ -77,17 +77,17 @@ i915_gem_evict_something(struct drm_device *dev, int min_size,
 	 */
 
 	INIT_LIST_HEAD(&unwind_list);
-	if (mappable)
-		drm_mm_init_scan_with_range(&dev_priv->mm.gtt_space,
-					    min_size, alignment, cache_level,
-					    0, dev_priv->gtt.mappable_end);
-	else
-		drm_mm_init_scan(&dev_priv->mm.gtt_space,
-				 min_size, alignment, cache_level);
+	if (mappable) {
+		BUG_ON(!i915_is_ggtt(vm));
+		drm_mm_init_scan_with_range(&vm->mm, min_size,
+					    alignment, cache_level, 0,
+					    dev_priv->gtt.mappable_end);
+	} else
+		drm_mm_init_scan(&vm->mm, min_size, alignment, cache_level);
 
 	/* First see if there is a large enough contiguous idle region... */
-	list_for_each_entry(obj, &dev_priv->mm.inactive_list, mm_list) {
-		if (mark_free(obj, &unwind_list))
+	list_for_each_entry(vma, &vm->inactive_list, mm_list) {
+		if (mark_free(vma, &unwind_list))
 			goto found;
 	}
 
@@ -95,22 +95,21 @@ i915_gem_evict_something(struct drm_device *dev, int min_size,
 		goto none;
 
 	/* Now merge in the soon-to-be-expired objects... */
-	list_for_each_entry(obj, &dev_priv->mm.active_list, mm_list) {
-		if (mark_free(obj, &unwind_list))
+	list_for_each_entry(vma, &vm->active_list, mm_list) {
+		if (mark_free(vma, &unwind_list))
 			goto found;
 	}
 
 none:
 	/* Nothing found, clean up and bail out! */
 	while (!list_empty(&unwind_list)) {
-		obj = list_first_entry(&unwind_list,
-				       struct drm_i915_gem_object,
+		vma = list_first_entry(&unwind_list,
+				       struct i915_vma,
 				       exec_list);
-
-		ret = drm_mm_scan_remove_block(obj->gtt_space);
+		ret = drm_mm_scan_remove_block(&vma->node);
 		BUG_ON(ret);
 
-		list_del_init(&obj->exec_list);
+		list_del_init(&vma->exec_list);
 	}
 
 	/* We expect the caller to unpin, evict all and try again, or give up.
@@ -124,27 +123,30 @@ found:
 	 * temporary list. */
 	INIT_LIST_HEAD(&eviction_list);
 	while (!list_empty(&unwind_list)) {
-		obj = list_first_entry(&unwind_list,
-				       struct drm_i915_gem_object,
+		vma = list_first_entry(&unwind_list,
+				       struct i915_vma,
 				       exec_list);
-		if (drm_mm_scan_remove_block(obj->gtt_space)) {
-			list_move(&obj->exec_list, &eviction_list);
-			drm_gem_object_reference(&obj->base);
+		if (drm_mm_scan_remove_block(&vma->node)) {
+			list_move(&vma->exec_list, &eviction_list);
+			drm_gem_object_reference(&vma->obj->base);
 			continue;
 		}
-		list_del_init(&obj->exec_list);
+		list_del_init(&vma->exec_list);
 	}
 
 	/* Unbinding will emit any required flushes */
 	while (!list_empty(&eviction_list)) {
-		obj = list_first_entry(&eviction_list,
-				       struct drm_i915_gem_object,
+		struct drm_gem_object *obj;
+		vma = list_first_entry(&eviction_list,
+				       struct i915_vma,
 				       exec_list);
+
+		obj =  &vma->obj->base;
+		list_del_init(&vma->exec_list);
 		if (ret == 0)
-			ret = i915_gem_object_unbind(obj);
+			ret = i915_vma_unbind(vma);
 
-		list_del_init(&obj->exec_list);
-		drm_gem_object_unreference(&obj->base);
+		drm_gem_object_unreference(obj);
 	}
 
 	return ret;
@@ -154,12 +156,18 @@ int
 i915_gem_evict_everything(struct drm_device *dev)
 {
 	drm_i915_private_t *dev_priv = dev->dev_private;
-	struct drm_i915_gem_object *obj, *next;
-	bool lists_empty;
+	struct i915_address_space *vm;
+	struct i915_vma *vma, *next;
+	bool lists_empty = true;
 	int ret;
 
-	lists_empty = (list_empty(&dev_priv->mm.inactive_list) &&
-		       list_empty(&dev_priv->mm.active_list));
+	list_for_each_entry(vm, &dev_priv->vm_list, global_link) {
+		lists_empty = (list_empty(&vm->inactive_list) &&
+			       list_empty(&vm->active_list));
+		if (!lists_empty)
+			lists_empty = false;
+	}
+
 	if (lists_empty)
 		return -ENOSPC;
 
@@ -176,10 +184,11 @@ i915_gem_evict_everything(struct drm_device *dev)
 	i915_gem_retire_requests(dev);
 
 	/* Having flushed everything, unbind() should never raise an error */
-	list_for_each_entry_safe(obj, next,
-				 &dev_priv->mm.inactive_list, mm_list)
-		if (obj->pin_count == 0)
-			WARN_ON(i915_gem_object_unbind(obj));
+	list_for_each_entry(vm, &dev_priv->vm_list, global_link) {
+		list_for_each_entry_safe(vma, next, &vm->inactive_list, mm_list)
+			if (vma->obj->pin_count == 0)
+				WARN_ON(i915_vma_unbind(vma));
+	}
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 87a3227e5179..bf345777ae9f 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -172,9 +172,60 @@ static inline int use_cpu_reloc(struct drm_i915_gem_object *obj)
 }
 
 static int
+relocate_entry_cpu(struct drm_i915_gem_object *obj,
+		   struct drm_i915_gem_relocation_entry *reloc)
+{
+	uint32_t page_offset = offset_in_page(reloc->offset);
+	char *vaddr;
+	int ret = -EINVAL;
+
+	ret = i915_gem_object_set_to_cpu_domain(obj, 1);
+	if (ret)
+		return ret;
+
+	vaddr = kmap_atomic(i915_gem_object_get_page(obj,
+				reloc->offset >> PAGE_SHIFT));
+	*(uint32_t *)(vaddr + page_offset) = reloc->delta;
+	kunmap_atomic(vaddr);
+
+	return 0;
+}
+
+static int
+relocate_entry_gtt(struct drm_i915_gem_object *obj,
+		   struct drm_i915_gem_relocation_entry *reloc)
+{
+	struct drm_device *dev = obj->base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	uint32_t __iomem *reloc_entry;
+	void __iomem *reloc_page;
+	int ret = -EINVAL;
+
+	ret = i915_gem_object_set_to_gtt_domain(obj, true);
+	if (ret)
+		return ret;
+
+	ret = i915_gem_object_put_fence(obj);
+	if (ret)
+		return ret;
+
+	/* Map the page containing the relocation we're going to perform.  */
+	reloc->offset += i915_gem_obj_ggtt_offset(obj);
+	reloc_page = io_mapping_map_atomic_wc(dev_priv->gtt.mappable,
+			reloc->offset & PAGE_MASK);
+	reloc_entry = (uint32_t __iomem *)
+		(reloc_page + offset_in_page(reloc->offset));
+	iowrite32(reloc->delta, reloc_entry);
+	io_mapping_unmap_atomic(reloc_page);
+
+	return 0;
+}
+
+static int
 i915_gem_execbuffer_relocate_entry(struct drm_i915_gem_object *obj,
 				   struct eb_objects *eb,
-				   struct drm_i915_gem_relocation_entry *reloc)
+				   struct drm_i915_gem_relocation_entry *reloc,
+				   struct i915_address_space *vm)
 {
 	struct drm_device *dev = obj->base.dev;
 	struct drm_gem_object *target_obj;
@@ -188,7 +239,7 @@ i915_gem_execbuffer_relocate_entry(struct drm_i915_gem_object *obj,
 		return -ENOENT;
 
 	target_i915_obj = to_intel_bo(target_obj);
-	target_offset = target_i915_obj->gtt_offset;
+	target_offset = i915_gem_obj_ggtt_offset(target_i915_obj);
 
 	/* Sandybridge PPGTT errata: We need a global gtt mapping for MI and
 	 * pipe_control writes because the gpu doesn't properly redirect them
@@ -254,40 +305,13 @@ i915_gem_execbuffer_relocate_entry(struct drm_i915_gem_object *obj,
 		return -EFAULT;
 
 	reloc->delta += target_offset;
-	if (use_cpu_reloc(obj)) {
-		uint32_t page_offset = reloc->offset & ~PAGE_MASK;
-		char *vaddr;
-
-		ret = i915_gem_object_set_to_cpu_domain(obj, 1);
-		if (ret)
-			return ret;
-
-		vaddr = kmap_atomic(i915_gem_object_get_page(obj,
-							     reloc->offset >> PAGE_SHIFT));
-		*(uint32_t *)(vaddr + page_offset) = reloc->delta;
-		kunmap_atomic(vaddr);
-	} else {
-		struct drm_i915_private *dev_priv = dev->dev_private;
-		uint32_t __iomem *reloc_entry;
-		void __iomem *reloc_page;
-
-		ret = i915_gem_object_set_to_gtt_domain(obj, true);
-		if (ret)
-			return ret;
-
-		ret = i915_gem_object_put_fence(obj);
-		if (ret)
-			return ret;
+	if (use_cpu_reloc(obj))
+		ret = relocate_entry_cpu(obj, reloc);
+	else
+		ret = relocate_entry_gtt(obj, reloc);
 
-		/* Map the page containing the relocation we're going to perform.  */
-		reloc->offset += obj->gtt_offset;
-		reloc_page = io_mapping_map_atomic_wc(dev_priv->gtt.mappable,
-						      reloc->offset & PAGE_MASK);
-		reloc_entry = (uint32_t __iomem *)
-			(reloc_page + (reloc->offset & ~PAGE_MASK));
-		iowrite32(reloc->delta, reloc_entry);
-		io_mapping_unmap_atomic(reloc_page);
-	}
+	if (ret)
+		return ret;
 
 	/* and update the user's relocation entry */
 	reloc->presumed_offset = target_offset;
@@ -297,7 +321,8 @@ i915_gem_execbuffer_relocate_entry(struct drm_i915_gem_object *obj,
 
 static int
 i915_gem_execbuffer_relocate_object(struct drm_i915_gem_object *obj,
-				    struct eb_objects *eb)
+				    struct eb_objects *eb,
+				    struct i915_address_space *vm)
 {
 #define N_RELOC(x) ((x) / sizeof(struct drm_i915_gem_relocation_entry))
 	struct drm_i915_gem_relocation_entry stack_reloc[N_RELOC(512)];
@@ -321,7 +346,8 @@ i915_gem_execbuffer_relocate_object(struct drm_i915_gem_object *obj,
 		do {
 			u64 offset = r->presumed_offset;
 
-			ret = i915_gem_execbuffer_relocate_entry(obj, eb, r);
+			ret = i915_gem_execbuffer_relocate_entry(obj, eb, r,
+								 vm);
 			if (ret)
 				return ret;
 
@@ -344,13 +370,15 @@ i915_gem_execbuffer_relocate_object(struct drm_i915_gem_object *obj,
 static int
 i915_gem_execbuffer_relocate_object_slow(struct drm_i915_gem_object *obj,
 					 struct eb_objects *eb,
-					 struct drm_i915_gem_relocation_entry *relocs)
+					 struct drm_i915_gem_relocation_entry *relocs,
+					 struct i915_address_space *vm)
 {
 	const struct drm_i915_gem_exec_object2 *entry = obj->exec_entry;
 	int i, ret;
 
 	for (i = 0; i < entry->relocation_count; i++) {
-		ret = i915_gem_execbuffer_relocate_entry(obj, eb, &relocs[i]);
+		ret = i915_gem_execbuffer_relocate_entry(obj, eb, &relocs[i],
+							 vm);
 		if (ret)
 			return ret;
 	}
@@ -359,7 +387,8 @@ i915_gem_execbuffer_relocate_object_slow(struct drm_i915_gem_object *obj,
 }
 
 static int
-i915_gem_execbuffer_relocate(struct eb_objects *eb)
+i915_gem_execbuffer_relocate(struct eb_objects *eb,
+			     struct i915_address_space *vm)
 {
 	struct drm_i915_gem_object *obj;
 	int ret = 0;
@@ -373,7 +402,7 @@ i915_gem_execbuffer_relocate(struct eb_objects *eb)
 	 */
 	pagefault_disable();
 	list_for_each_entry(obj, &eb->objects, exec_list) {
-		ret = i915_gem_execbuffer_relocate_object(obj, eb);
+		ret = i915_gem_execbuffer_relocate_object(obj, eb, vm);
 		if (ret)
 			break;
 	}
@@ -395,6 +424,7 @@ need_reloc_mappable(struct drm_i915_gem_object *obj)
 static int
 i915_gem_execbuffer_reserve_object(struct drm_i915_gem_object *obj,
 				   struct intel_ring_buffer *ring,
+				   struct i915_address_space *vm,
 				   bool *need_reloc)
 {
 	struct drm_i915_private *dev_priv = obj->base.dev->dev_private;
@@ -409,7 +439,8 @@ i915_gem_execbuffer_reserve_object(struct drm_i915_gem_object *obj,
 		obj->tiling_mode != I915_TILING_NONE;
 	need_mappable = need_fence || need_reloc_mappable(obj);
 
-	ret = i915_gem_object_pin(obj, entry->alignment, need_mappable, false);
+	ret = i915_gem_object_pin(obj, vm, entry->alignment, need_mappable,
+				  false);
 	if (ret)
 		return ret;
 
@@ -436,8 +467,8 @@ i915_gem_execbuffer_reserve_object(struct drm_i915_gem_object *obj,
 		obj->has_aliasing_ppgtt_mapping = 1;
 	}
 
-	if (entry->offset != obj->gtt_offset) {
-		entry->offset = obj->gtt_offset;
+	if (entry->offset != i915_gem_obj_offset(obj, vm)) {
+		entry->offset = i915_gem_obj_offset(obj, vm);
 		*need_reloc = true;
 	}
 
@@ -458,7 +489,7 @@ i915_gem_execbuffer_unreserve_object(struct drm_i915_gem_object *obj)
 {
 	struct drm_i915_gem_exec_object2 *entry;
 
-	if (!obj->gtt_space)
+	if (!i915_gem_obj_bound_any(obj))
 		return;
 
 	entry = obj->exec_entry;
@@ -475,6 +506,7 @@ i915_gem_execbuffer_unreserve_object(struct drm_i915_gem_object *obj)
 static int
 i915_gem_execbuffer_reserve(struct intel_ring_buffer *ring,
 			    struct list_head *objects,
+			    struct i915_address_space *vm,
 			    bool *need_relocs)
 {
 	struct drm_i915_gem_object *obj;
@@ -529,31 +561,37 @@ i915_gem_execbuffer_reserve(struct intel_ring_buffer *ring,
 		list_for_each_entry(obj, objects, exec_list) {
 			struct drm_i915_gem_exec_object2 *entry = obj->exec_entry;
 			bool need_fence, need_mappable;
+			u32 obj_offset;
 
-			if (!obj->gtt_space)
+			if (!i915_gem_obj_bound(obj, vm))
 				continue;
 
+			obj_offset = i915_gem_obj_offset(obj, vm);
 			need_fence =
 				has_fenced_gpu_access &&
 				entry->flags & EXEC_OBJECT_NEEDS_FENCE &&
 				obj->tiling_mode != I915_TILING_NONE;
 			need_mappable = need_fence || need_reloc_mappable(obj);
 
-			if ((entry->alignment && obj->gtt_offset & (entry->alignment - 1)) ||
+			WARN_ON((need_mappable || need_fence) &&
+				!i915_is_ggtt(vm));
+
+			if ((entry->alignment &&
+			     obj_offset & (entry->alignment - 1)) ||
 			    (need_mappable && !obj->map_and_fenceable))
-				ret = i915_gem_object_unbind(obj);
+				ret = i915_vma_unbind(i915_gem_obj_to_vma(obj, vm));
 			else
-				ret = i915_gem_execbuffer_reserve_object(obj, ring, need_relocs);
+				ret = i915_gem_execbuffer_reserve_object(obj, ring, vm, need_relocs);
 			if (ret)
 				goto err;
 		}
 
 		/* Bind fresh objects */
 		list_for_each_entry(obj, objects, exec_list) {
-			if (obj->gtt_space)
+			if (i915_gem_obj_bound(obj, vm))
 				continue;
 
-			ret = i915_gem_execbuffer_reserve_object(obj, ring, need_relocs);
+			ret = i915_gem_execbuffer_reserve_object(obj, ring, vm, need_relocs);
 			if (ret)
 				goto err;
 		}
@@ -577,7 +615,8 @@ i915_gem_execbuffer_relocate_slow(struct drm_device *dev,
 				  struct drm_file *file,
 				  struct intel_ring_buffer *ring,
 				  struct eb_objects *eb,
-				  struct drm_i915_gem_exec_object2 *exec)
+				  struct drm_i915_gem_exec_object2 *exec,
+				  struct i915_address_space *vm)
 {
 	struct drm_i915_gem_relocation_entry *reloc;
 	struct drm_i915_gem_object *obj;
@@ -661,14 +700,15 @@ i915_gem_execbuffer_relocate_slow(struct drm_device *dev,
 		goto err;
 
 	need_relocs = (args->flags & I915_EXEC_NO_RELOC) == 0;
-	ret = i915_gem_execbuffer_reserve(ring, &eb->objects, &need_relocs);
+	ret = i915_gem_execbuffer_reserve(ring, &eb->objects, vm, &need_relocs);
 	if (ret)
 		goto err;
 
 	list_for_each_entry(obj, &eb->objects, exec_list) {
 		int offset = obj->exec_entry - exec;
 		ret = i915_gem_execbuffer_relocate_object_slow(obj, eb,
-							       reloc + reloc_offset[offset]);
+							       reloc + reloc_offset[offset],
+							       vm);
 		if (ret)
 			goto err;
 	}
@@ -691,6 +731,7 @@ i915_gem_execbuffer_move_to_gpu(struct intel_ring_buffer *ring,
 {
 	struct drm_i915_gem_object *obj;
 	uint32_t flush_domains = 0;
+	bool flush_chipset = false;
 	int ret;
 
 	list_for_each_entry(obj, objects, exec_list) {
@@ -699,12 +740,12 @@ i915_gem_execbuffer_move_to_gpu(struct intel_ring_buffer *ring,
 			return ret;
 
 		if (obj->base.write_domain & I915_GEM_DOMAIN_CPU)
-			i915_gem_clflush_object(obj);
+			flush_chipset |= i915_gem_clflush_object(obj, false);
 
 		flush_domains |= obj->base.write_domain;
 	}
 
-	if (flush_domains & I915_GEM_DOMAIN_CPU)
+	if (flush_chipset)
 		i915_gem_chipset_flush(ring->dev);
 
 	if (flush_domains & I915_GEM_DOMAIN_GTT)
@@ -758,8 +799,10 @@ validate_exec_list(struct drm_i915_gem_exec_object2 *exec,
 		if (!access_ok(VERIFY_WRITE, ptr, length))
 			return -EFAULT;
 
-		if (fault_in_multipages_readable(ptr, length))
-			return -EFAULT;
+		if (likely(!i915_prefault_disable)) {
+			if (fault_in_multipages_readable(ptr, length))
+				return -EFAULT;
+		}
 	}
 
 	return 0;
@@ -767,6 +810,7 @@ validate_exec_list(struct drm_i915_gem_exec_object2 *exec,
 
 static void
 i915_gem_execbuffer_move_to_active(struct list_head *objects,
+				   struct i915_address_space *vm,
 				   struct intel_ring_buffer *ring)
 {
 	struct drm_i915_gem_object *obj;
@@ -781,6 +825,8 @@ i915_gem_execbuffer_move_to_active(struct list_head *objects,
 		obj->base.read_domains = obj->base.pending_read_domains;
 		obj->fenced_gpu_access = obj->pending_fenced_gpu_access;
 
+		/* FIXME: This lookup gets fixed later <-- danvet */
+		list_move_tail(&i915_gem_obj_to_vma(obj, vm)->mm_list, &vm->active_list);
 		i915_gem_object_move_to_active(obj, ring);
 		if (obj->base.write_domain) {
 			obj->dirty = 1;
@@ -835,7 +881,8 @@ static int
 i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 		       struct drm_file *file,
 		       struct drm_i915_gem_execbuffer2 *args,
-		       struct drm_i915_gem_exec_object2 *exec)
+		       struct drm_i915_gem_exec_object2 *exec,
+		       struct i915_address_space *vm)
 {
 	drm_i915_private_t *dev_priv = dev->dev_private;
 	struct eb_objects *eb;
@@ -872,7 +919,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 		break;
 	case I915_EXEC_BSD:
 		ring = &dev_priv->ring[VCS];
-		if (ctx_id != 0) {
+		if (ctx_id != DEFAULT_CONTEXT_ID) {
 			DRM_DEBUG("Ring %s doesn't support contexts\n",
 				  ring->name);
 			return -EPERM;
@@ -880,7 +927,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 		break;
 	case I915_EXEC_BLT:
 		ring = &dev_priv->ring[BCS];
-		if (ctx_id != 0) {
+		if (ctx_id != DEFAULT_CONTEXT_ID) {
 			DRM_DEBUG("Ring %s doesn't support contexts\n",
 				  ring->name);
 			return -EPERM;
@@ -888,7 +935,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 		break;
 	case I915_EXEC_VEBOX:
 		ring = &dev_priv->ring[VECS];
-		if (ctx_id != 0) {
+		if (ctx_id != DEFAULT_CONTEXT_ID) {
 			DRM_DEBUG("Ring %s doesn't support contexts\n",
 				  ring->name);
 			return -EPERM;
@@ -972,7 +1019,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 	if (ret)
 		goto pre_mutex_err;
 
-	if (dev_priv->mm.suspended) {
+	if (dev_priv->ums.mm_suspended) {
 		mutex_unlock(&dev->struct_mutex);
 		ret = -EBUSY;
 		goto pre_mutex_err;
@@ -997,17 +1044,17 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 
 	/* Move the objects en-masse into the GTT, evicting if necessary. */
 	need_relocs = (args->flags & I915_EXEC_NO_RELOC) == 0;
-	ret = i915_gem_execbuffer_reserve(ring, &eb->objects, &need_relocs);
+	ret = i915_gem_execbuffer_reserve(ring, &eb->objects, vm, &need_relocs);
 	if (ret)
 		goto err;
 
 	/* The objects are in their final locations, apply the relocations. */
 	if (need_relocs)
-		ret = i915_gem_execbuffer_relocate(eb);
+		ret = i915_gem_execbuffer_relocate(eb, vm);
 	if (ret) {
 		if (ret == -EFAULT) {
 			ret = i915_gem_execbuffer_relocate_slow(dev, args, file, ring,
-								eb, exec);
+								eb, exec, vm);
 			BUG_ON(!mutex_is_locked(&dev->struct_mutex));
 		}
 		if (ret)
@@ -1058,7 +1105,8 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 			goto err;
 	}
 
-	exec_start = batch_obj->gtt_offset + args->batch_start_offset;
+	exec_start = i915_gem_obj_offset(batch_obj, vm) +
+		args->batch_start_offset;
 	exec_len = args->batch_len;
 	if (cliprects) {
 		for (i = 0; i < args->num_cliprects; i++) {
@@ -1083,7 +1131,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 
 	trace_i915_gem_ring_dispatch(ring, intel_ring_get_seqno(ring), flags);
 
-	i915_gem_execbuffer_move_to_active(&eb->objects, ring);
+	i915_gem_execbuffer_move_to_active(&eb->objects, vm, ring);
 	i915_gem_execbuffer_retire_commands(dev, file, ring, batch_obj);
 
 err:
@@ -1104,6 +1152,7 @@ int
 i915_gem_execbuffer(struct drm_device *dev, void *data,
 		    struct drm_file *file)
 {
+	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_i915_gem_execbuffer *args = data;
 	struct drm_i915_gem_execbuffer2 exec2;
 	struct drm_i915_gem_exec_object *exec_list = NULL;
@@ -1159,7 +1208,8 @@ i915_gem_execbuffer(struct drm_device *dev, void *data,
 	exec2.flags = I915_EXEC_RENDER;
 	i915_execbuffer2_set_context_id(exec2, 0);
 
-	ret = i915_gem_do_execbuffer(dev, data, file, &exec2, exec2_list);
+	ret = i915_gem_do_execbuffer(dev, data, file, &exec2, exec2_list,
+				     &dev_priv->gtt.base);
 	if (!ret) {
 		/* Copy the new buffer offsets back to the user's exec list. */
 		for (i = 0; i < args->buffer_count; i++)
@@ -1185,6 +1235,7 @@ int
 i915_gem_execbuffer2(struct drm_device *dev, void *data,
 		     struct drm_file *file)
 {
+	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_i915_gem_execbuffer2 *args = data;
 	struct drm_i915_gem_exec_object2 *exec2_list = NULL;
 	int ret;
@@ -1215,7 +1266,8 @@ i915_gem_execbuffer2(struct drm_device *dev, void *data,
 		return -EFAULT;
 	}
 
-	ret = i915_gem_do_execbuffer(dev, data, file, args, exec2_list);
+	ret = i915_gem_do_execbuffer(dev, data, file, args, exec2_list,
+				     &dev_priv->gtt.base);
 	if (!ret) {
 		/* Copy the new buffer offsets back to the user's exec list. */
 		ret = copy_to_user(to_user_ptr(args->buffers_ptr),
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 5101ab6869b4..212f6d8c35ec 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -28,8 +28,12 @@
 #include "i915_trace.h"
 #include "intel_drv.h"
 
+#define GEN6_PPGTT_PD_ENTRIES 512
+#define I915_PPGTT_PT_ENTRIES (PAGE_SIZE / sizeof(gen6_gtt_pte_t))
+
 /* PPGTT stuff */
 #define GEN6_GTT_ADDR_ENCODE(addr)	((addr) | (((addr) >> 28) & 0xff0))
+#define HSW_GTT_ADDR_ENCODE(addr)	((addr) | (((addr) >> 28) & 0x7f0))
 
 #define GEN6_PDE_VALID			(1 << 0)
 /* gen6+ has bit 11-4 for physical addr bit 39-32 */
@@ -39,19 +43,50 @@
 #define GEN6_PTE_UNCACHED		(1 << 1)
 #define HSW_PTE_UNCACHED		(0)
 #define GEN6_PTE_CACHE_LLC		(2 << 1)
-#define GEN6_PTE_CACHE_LLC_MLC		(3 << 1)
+#define GEN7_PTE_CACHE_L3_LLC		(3 << 1)
 #define GEN6_PTE_ADDR_ENCODE(addr)	GEN6_GTT_ADDR_ENCODE(addr)
+#define HSW_PTE_ADDR_ENCODE(addr)	HSW_GTT_ADDR_ENCODE(addr)
 
-static gen6_gtt_pte_t gen6_pte_encode(struct drm_device *dev,
-				      dma_addr_t addr,
-				      enum i915_cache_level level)
+/* Cacheability Control is a 4-bit value. The low three bits are stored in *
+ * bits 3:1 of the PTE, while the fourth bit is stored in bit 11 of the PTE.
+ */
+#define HSW_CACHEABILITY_CONTROL(bits)	((((bits) & 0x7) << 1) | \
+					 (((bits) & 0x8) << (11 - 3)))
+#define HSW_WB_LLC_AGE3			HSW_CACHEABILITY_CONTROL(0x2)
+#define HSW_WB_LLC_AGE0			HSW_CACHEABILITY_CONTROL(0x3)
+#define HSW_WB_ELLC_LLC_AGE0		HSW_CACHEABILITY_CONTROL(0xb)
+#define HSW_WT_ELLC_LLC_AGE0		HSW_CACHEABILITY_CONTROL(0x6)
+
+static gen6_gtt_pte_t snb_pte_encode(dma_addr_t addr,
+				     enum i915_cache_level level)
 {
 	gen6_gtt_pte_t pte = GEN6_PTE_VALID;
 	pte |= GEN6_PTE_ADDR_ENCODE(addr);
 
 	switch (level) {
-	case I915_CACHE_LLC_MLC:
-		pte |= GEN6_PTE_CACHE_LLC_MLC;
+	case I915_CACHE_L3_LLC:
+	case I915_CACHE_LLC:
+		pte |= GEN6_PTE_CACHE_LLC;
+		break;
+	case I915_CACHE_NONE:
+		pte |= GEN6_PTE_UNCACHED;
+		break;
+	default:
+		WARN_ON(1);
+	}
+
+	return pte;
+}
+
+static gen6_gtt_pte_t ivb_pte_encode(dma_addr_t addr,
+				     enum i915_cache_level level)
+{
+	gen6_gtt_pte_t pte = GEN6_PTE_VALID;
+	pte |= GEN6_PTE_ADDR_ENCODE(addr);
+
+	switch (level) {
+	case I915_CACHE_L3_LLC:
+		pte |= GEN7_PTE_CACHE_L3_LLC;
 		break;
 	case I915_CACHE_LLC:
 		pte |= GEN6_PTE_CACHE_LLC;
@@ -60,7 +95,7 @@ static gen6_gtt_pte_t gen6_pte_encode(struct drm_device *dev,
 		pte |= GEN6_PTE_UNCACHED;
 		break;
 	default:
-		BUG();
+		WARN_ON(1);
 	}
 
 	return pte;
@@ -69,8 +104,7 @@ static gen6_gtt_pte_t gen6_pte_encode(struct drm_device *dev,
 #define BYT_PTE_WRITEABLE		(1 << 1)
 #define BYT_PTE_SNOOPED_BY_CPU_CACHES	(1 << 2)
 
-static gen6_gtt_pte_t byt_pte_encode(struct drm_device *dev,
-				     dma_addr_t addr,
+static gen6_gtt_pte_t byt_pte_encode(dma_addr_t addr,
 				     enum i915_cache_level level)
 {
 	gen6_gtt_pte_t pte = GEN6_PTE_VALID;
@@ -87,22 +121,41 @@ static gen6_gtt_pte_t byt_pte_encode(struct drm_device *dev,
 	return pte;
 }
 
-static gen6_gtt_pte_t hsw_pte_encode(struct drm_device *dev,
-				     dma_addr_t addr,
+static gen6_gtt_pte_t hsw_pte_encode(dma_addr_t addr,
 				     enum i915_cache_level level)
 {
 	gen6_gtt_pte_t pte = GEN6_PTE_VALID;
-	pte |= GEN6_PTE_ADDR_ENCODE(addr);
+	pte |= HSW_PTE_ADDR_ENCODE(addr);
 
 	if (level != I915_CACHE_NONE)
-		pte |= GEN6_PTE_CACHE_LLC;
+		pte |= HSW_WB_LLC_AGE3;
+
+	return pte;
+}
+
+static gen6_gtt_pte_t iris_pte_encode(dma_addr_t addr,
+				      enum i915_cache_level level)
+{
+	gen6_gtt_pte_t pte = GEN6_PTE_VALID;
+	pte |= HSW_PTE_ADDR_ENCODE(addr);
+
+	switch (level) {
+	case I915_CACHE_NONE:
+		break;
+	case I915_CACHE_WT:
+		pte |= HSW_WT_ELLC_LLC_AGE0;
+		break;
+	default:
+		pte |= HSW_WB_ELLC_LLC_AGE0;
+		break;
+	}
 
 	return pte;
 }
 
 static void gen6_write_pdes(struct i915_hw_ppgtt *ppgtt)
 {
-	struct drm_i915_private *dev_priv = ppgtt->dev->dev_private;
+	struct drm_i915_private *dev_priv = ppgtt->base.dev->dev_private;
 	gen6_gtt_pte_t __iomem *pd_addr;
 	uint32_t pd_entry;
 	int i;
@@ -181,18 +234,18 @@ static int gen6_ppgtt_enable(struct drm_device *dev)
 }
 
 /* PPGTT support for Sandybdrige/Gen6 and later */
-static void gen6_ppgtt_clear_range(struct i915_hw_ppgtt *ppgtt,
+static void gen6_ppgtt_clear_range(struct i915_address_space *vm,
 				   unsigned first_entry,
 				   unsigned num_entries)
 {
+	struct i915_hw_ppgtt *ppgtt =
+		container_of(vm, struct i915_hw_ppgtt, base);
 	gen6_gtt_pte_t *pt_vaddr, scratch_pte;
 	unsigned act_pt = first_entry / I915_PPGTT_PT_ENTRIES;
 	unsigned first_pte = first_entry % I915_PPGTT_PT_ENTRIES;
 	unsigned last_pte, i;
 
-	scratch_pte = ppgtt->pte_encode(ppgtt->dev,
-					ppgtt->scratch_page_dma_addr,
-					I915_CACHE_LLC);
+	scratch_pte = vm->pte_encode(vm->scratch.addr, I915_CACHE_LLC);
 
 	while (num_entries) {
 		last_pte = first_pte + num_entries;
@@ -212,11 +265,13 @@ static void gen6_ppgtt_clear_range(struct i915_hw_ppgtt *ppgtt,
 	}
 }
 
-static void gen6_ppgtt_insert_entries(struct i915_hw_ppgtt *ppgtt,
+static void gen6_ppgtt_insert_entries(struct i915_address_space *vm,
 				      struct sg_table *pages,
 				      unsigned first_entry,
 				      enum i915_cache_level cache_level)
 {
+	struct i915_hw_ppgtt *ppgtt =
+		container_of(vm, struct i915_hw_ppgtt, base);
 	gen6_gtt_pte_t *pt_vaddr;
 	unsigned act_pt = first_entry / I915_PPGTT_PT_ENTRIES;
 	unsigned act_pte = first_entry % I915_PPGTT_PT_ENTRIES;
@@ -227,8 +282,7 @@ static void gen6_ppgtt_insert_entries(struct i915_hw_ppgtt *ppgtt,
 		dma_addr_t page_addr;
 
 		page_addr = sg_page_iter_dma_address(&sg_iter);
-		pt_vaddr[act_pte] = ppgtt->pte_encode(ppgtt->dev, page_addr,
-						      cache_level);
+		pt_vaddr[act_pte] = vm->pte_encode(page_addr, cache_level);
 		if (++act_pte == I915_PPGTT_PT_ENTRIES) {
 			kunmap_atomic(pt_vaddr);
 			act_pt++;
@@ -240,13 +294,17 @@ static void gen6_ppgtt_insert_entries(struct i915_hw_ppgtt *ppgtt,
 	kunmap_atomic(pt_vaddr);
 }
 
-static void gen6_ppgtt_cleanup(struct i915_hw_ppgtt *ppgtt)
+static void gen6_ppgtt_cleanup(struct i915_address_space *vm)
 {
+	struct i915_hw_ppgtt *ppgtt =
+		container_of(vm, struct i915_hw_ppgtt, base);
 	int i;
 
+	drm_mm_takedown(&ppgtt->base.mm);
+
 	if (ppgtt->pt_dma_addr) {
 		for (i = 0; i < ppgtt->num_pd_entries; i++)
-			pci_unmap_page(ppgtt->dev->pdev,
+			pci_unmap_page(ppgtt->base.dev->pdev,
 				       ppgtt->pt_dma_addr[i],
 				       4096, PCI_DMA_BIDIRECTIONAL);
 	}
@@ -260,7 +318,7 @@ static void gen6_ppgtt_cleanup(struct i915_hw_ppgtt *ppgtt)
 
 static int gen6_ppgtt_init(struct i915_hw_ppgtt *ppgtt)
 {
-	struct drm_device *dev = ppgtt->dev;
+	struct drm_device *dev = ppgtt->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	unsigned first_pd_entry_in_global_pt;
 	int i;
@@ -271,18 +329,13 @@ static int gen6_ppgtt_init(struct i915_hw_ppgtt *ppgtt)
 	 * now. */
 	first_pd_entry_in_global_pt = gtt_total_entries(dev_priv->gtt);
 
-	if (IS_HASWELL(dev)) {
-		ppgtt->pte_encode = hsw_pte_encode;
-	} else if (IS_VALLEYVIEW(dev)) {
-		ppgtt->pte_encode = byt_pte_encode;
-	} else {
-		ppgtt->pte_encode = gen6_pte_encode;
-	}
-	ppgtt->num_pd_entries = I915_PPGTT_PD_ENTRIES;
+	ppgtt->base.pte_encode = dev_priv->gtt.base.pte_encode;
+	ppgtt->num_pd_entries = GEN6_PPGTT_PD_ENTRIES;
 	ppgtt->enable = gen6_ppgtt_enable;
-	ppgtt->clear_range = gen6_ppgtt_clear_range;
-	ppgtt->insert_entries = gen6_ppgtt_insert_entries;
-	ppgtt->cleanup = gen6_ppgtt_cleanup;
+	ppgtt->base.clear_range = gen6_ppgtt_clear_range;
+	ppgtt->base.insert_entries = gen6_ppgtt_insert_entries;
+	ppgtt->base.cleanup = gen6_ppgtt_cleanup;
+	ppgtt->base.scratch = dev_priv->gtt.base.scratch;
 	ppgtt->pt_pages = kzalloc(sizeof(struct page *)*ppgtt->num_pd_entries,
 				  GFP_KERNEL);
 	if (!ppgtt->pt_pages)
@@ -313,8 +366,8 @@ static int gen6_ppgtt_init(struct i915_hw_ppgtt *ppgtt)
 		ppgtt->pt_dma_addr[i] = pt_addr;
 	}
 
-	ppgtt->clear_range(ppgtt, 0,
-			   ppgtt->num_pd_entries*I915_PPGTT_PT_ENTRIES);
+	ppgtt->base.clear_range(&ppgtt->base, 0,
+				ppgtt->num_pd_entries * I915_PPGTT_PT_ENTRIES);
 
 	ppgtt->pd_offset = first_pd_entry_in_global_pt * sizeof(gen6_gtt_pte_t);
 
@@ -347,8 +400,7 @@ static int i915_gem_init_aliasing_ppgtt(struct drm_device *dev)
 	if (!ppgtt)
 		return -ENOMEM;
 
-	ppgtt->dev = dev;
-	ppgtt->scratch_page_dma_addr = dev_priv->gtt.scratch_page_dma;
+	ppgtt->base.dev = dev;
 
 	if (INTEL_INFO(dev)->gen < 8)
 		ret = gen6_ppgtt_init(ppgtt);
@@ -357,8 +409,11 @@ static int i915_gem_init_aliasing_ppgtt(struct drm_device *dev)
 
 	if (ret)
 		kfree(ppgtt);
-	else
+	else {
 		dev_priv->mm.aliasing_ppgtt = ppgtt;
+		drm_mm_init(&ppgtt->base.mm, ppgtt->base.start,
+			    ppgtt->base.total);
+	}
 
 	return ret;
 }
@@ -371,7 +426,7 @@ void i915_gem_cleanup_aliasing_ppgtt(struct drm_device *dev)
 	if (!ppgtt)
 		return;
 
-	ppgtt->cleanup(ppgtt);
+	ppgtt->base.cleanup(&ppgtt->base);
 	dev_priv->mm.aliasing_ppgtt = NULL;
 }
 
@@ -379,17 +434,17 @@ void i915_ppgtt_bind_object(struct i915_hw_ppgtt *ppgtt,
 			    struct drm_i915_gem_object *obj,
 			    enum i915_cache_level cache_level)
 {
-	ppgtt->insert_entries(ppgtt, obj->pages,
-			      obj->gtt_space->start >> PAGE_SHIFT,
-			      cache_level);
+	ppgtt->base.insert_entries(&ppgtt->base, obj->pages,
+				   i915_gem_obj_ggtt_offset(obj) >> PAGE_SHIFT,
+				   cache_level);
 }
 
 void i915_ppgtt_unbind_object(struct i915_hw_ppgtt *ppgtt,
 			      struct drm_i915_gem_object *obj)
 {
-	ppgtt->clear_range(ppgtt,
-			   obj->gtt_space->start >> PAGE_SHIFT,
-			   obj->base.size >> PAGE_SHIFT);
+	ppgtt->base.clear_range(&ppgtt->base,
+				i915_gem_obj_ggtt_offset(obj) >> PAGE_SHIFT,
+				obj->base.size >> PAGE_SHIFT);
 }
 
 extern int intel_iommu_gfx_mapped;
@@ -436,11 +491,12 @@ void i915_gem_restore_gtt_mappings(struct drm_device *dev)
 	struct drm_i915_gem_object *obj;
 
 	/* First fill our portion of the GTT with scratch pages */
-	dev_priv->gtt.gtt_clear_range(dev, dev_priv->gtt.start / PAGE_SIZE,
-				      dev_priv->gtt.total / PAGE_SIZE);
+	dev_priv->gtt.base.clear_range(&dev_priv->gtt.base,
+				       dev_priv->gtt.base.start / PAGE_SIZE,
+				       dev_priv->gtt.base.total / PAGE_SIZE);
 
 	list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) {
-		i915_gem_clflush_object(obj);
+		i915_gem_clflush_object(obj, obj->pin_display);
 		i915_gem_gtt_bind_object(obj, obj->cache_level);
 	}
 
@@ -466,12 +522,12 @@ int i915_gem_gtt_prepare_object(struct drm_i915_gem_object *obj)
  * within the global GTT as well as accessible by the GPU through the GMADR
  * mapped BAR (dev_priv->mm.gtt->gtt).
  */
-static void gen6_ggtt_insert_entries(struct drm_device *dev,
+static void gen6_ggtt_insert_entries(struct i915_address_space *vm,
 				     struct sg_table *st,
 				     unsigned int first_entry,
 				     enum i915_cache_level level)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = vm->dev->dev_private;
 	gen6_gtt_pte_t __iomem *gtt_entries =
 		(gen6_gtt_pte_t __iomem *)dev_priv->gtt.gsm + first_entry;
 	int i = 0;
@@ -480,8 +536,7 @@ static void gen6_ggtt_insert_entries(struct drm_device *dev,
 
 	for_each_sg_page(st->sgl, &sg_iter, st->nents, 0) {
 		addr = sg_page_iter_dma_address(&sg_iter);
-		iowrite32(dev_priv->gtt.pte_encode(dev, addr, level),
-			  &gtt_entries[i]);
+		iowrite32(vm->pte_encode(addr, level), &gtt_entries[i]);
 		i++;
 	}
 
@@ -492,8 +547,8 @@ static void gen6_ggtt_insert_entries(struct drm_device *dev,
 	 * hardware should work, we must keep this posting read for paranoia.
 	 */
 	if (i != 0)
-		WARN_ON(readl(&gtt_entries[i-1])
-			!= dev_priv->gtt.pte_encode(dev, addr, level));
+		WARN_ON(readl(&gtt_entries[i-1]) !=
+			vm->pte_encode(addr, level));
 
 	/* This next bit makes the above posting read even more important. We
 	 * want to flush the TLBs only after we're certain all the PTE updates
@@ -503,11 +558,11 @@ static void gen6_ggtt_insert_entries(struct drm_device *dev,
 	POSTING_READ(GFX_FLSH_CNTL_GEN6);
 }
 
-static void gen6_ggtt_clear_range(struct drm_device *dev,
+static void gen6_ggtt_clear_range(struct i915_address_space *vm,
 				  unsigned int first_entry,
 				  unsigned int num_entries)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = vm->dev->dev_private;
 	gen6_gtt_pte_t scratch_pte, __iomem *gtt_base =
 		(gen6_gtt_pte_t __iomem *) dev_priv->gtt.gsm + first_entry;
 	const int max_entries = gtt_total_entries(dev_priv->gtt) - first_entry;
@@ -518,16 +573,14 @@ static void gen6_ggtt_clear_range(struct drm_device *dev,
 		 first_entry, num_entries, max_entries))
 		num_entries = max_entries;
 
-	scratch_pte = dev_priv->gtt.pte_encode(dev,
-					       dev_priv->gtt.scratch_page_dma,
-					       I915_CACHE_LLC);
+	scratch_pte = vm->pte_encode(vm->scratch.addr, I915_CACHE_LLC);
 	for (i = 0; i < num_entries; i++)
 		iowrite32(scratch_pte, &gtt_base[i]);
 	readl(gtt_base);
 }
 
 
-static void i915_ggtt_insert_entries(struct drm_device *dev,
+static void i915_ggtt_insert_entries(struct i915_address_space *vm,
 				     struct sg_table *st,
 				     unsigned int pg_start,
 				     enum i915_cache_level cache_level)
@@ -539,7 +592,7 @@ static void i915_ggtt_insert_entries(struct drm_device *dev,
 
 }
 
-static void i915_ggtt_clear_range(struct drm_device *dev,
+static void i915_ggtt_clear_range(struct i915_address_space *vm,
 				  unsigned int first_entry,
 				  unsigned int num_entries)
 {
@@ -552,10 +605,11 @@ void i915_gem_gtt_bind_object(struct drm_i915_gem_object *obj,
 {
 	struct drm_device *dev = obj->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
+	const unsigned long entry = i915_gem_obj_ggtt_offset(obj) >> PAGE_SHIFT;
 
-	dev_priv->gtt.gtt_insert_entries(dev, obj->pages,
-					 obj->gtt_space->start >> PAGE_SHIFT,
-					 cache_level);
+	dev_priv->gtt.base.insert_entries(&dev_priv->gtt.base, obj->pages,
+					  entry,
+					  cache_level);
 
 	obj->has_global_gtt_mapping = 1;
 }
@@ -564,10 +618,11 @@ void i915_gem_gtt_unbind_object(struct drm_i915_gem_object *obj)
 {
 	struct drm_device *dev = obj->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
+	const unsigned long entry = i915_gem_obj_ggtt_offset(obj) >> PAGE_SHIFT;
 
-	dev_priv->gtt.gtt_clear_range(obj->base.dev,
-				      obj->gtt_space->start >> PAGE_SHIFT,
-				      obj->base.size >> PAGE_SHIFT);
+	dev_priv->gtt.base.clear_range(&dev_priv->gtt.base,
+				       entry,
+				       obj->base.size >> PAGE_SHIFT);
 
 	obj->has_global_gtt_mapping = 0;
 }
@@ -618,7 +673,8 @@ void i915_gem_setup_global_gtt(struct drm_device *dev,
 	 * aperture.  One page should be enough to keep any prefetching inside
 	 * of the aperture.
 	 */
-	drm_i915_private_t *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct i915_address_space *ggtt_vm = &dev_priv->gtt.base;
 	struct drm_mm_node *entry;
 	struct drm_i915_gem_object *obj;
 	unsigned long hole_start, hole_end;
@@ -626,37 +682,38 @@ void i915_gem_setup_global_gtt(struct drm_device *dev,
 	BUG_ON(mappable_end > end);
 
 	/* Subtract the guard page ... */
-	drm_mm_init(&dev_priv->mm.gtt_space, start, end - start - PAGE_SIZE);
+	drm_mm_init(&ggtt_vm->mm, start, end - start - PAGE_SIZE);
 	if (!HAS_LLC(dev))
-		dev_priv->mm.gtt_space.color_adjust = i915_gtt_color_adjust;
+		dev_priv->gtt.base.mm.color_adjust = i915_gtt_color_adjust;
 
 	/* Mark any preallocated objects as occupied */
 	list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) {
-		DRM_DEBUG_KMS("reserving preallocated space: %x + %zx\n",
-			      obj->gtt_offset, obj->base.size);
-
-		BUG_ON(obj->gtt_space != I915_GTT_RESERVED);
-		obj->gtt_space = drm_mm_create_block(&dev_priv->mm.gtt_space,
-						     obj->gtt_offset,
-						     obj->base.size,
-						     false);
+		struct i915_vma *vma = i915_gem_obj_to_vma(obj, ggtt_vm);
+		int ret;
+		DRM_DEBUG_KMS("reserving preallocated space: %lx + %zx\n",
+			      i915_gem_obj_ggtt_offset(obj), obj->base.size);
+
+		WARN_ON(i915_gem_obj_ggtt_bound(obj));
+		ret = drm_mm_reserve_node(&ggtt_vm->mm, &vma->node);
+		if (ret)
+			DRM_DEBUG_KMS("Reservation failed\n");
 		obj->has_global_gtt_mapping = 1;
+		list_add(&vma->vma_link, &obj->vma_list);
 	}
 
-	dev_priv->gtt.start = start;
-	dev_priv->gtt.total = end - start;
+	dev_priv->gtt.base.start = start;
+	dev_priv->gtt.base.total = end - start;
 
 	/* Clear any non-preallocated blocks */
-	drm_mm_for_each_hole(entry, &dev_priv->mm.gtt_space,
-			     hole_start, hole_end) {
+	drm_mm_for_each_hole(entry, &ggtt_vm->mm, hole_start, hole_end) {
+		const unsigned long count = (hole_end - hole_start) / PAGE_SIZE;
 		DRM_DEBUG_KMS("clearing unused GTT space: [%lx, %lx]\n",
 			      hole_start, hole_end);
-		dev_priv->gtt.gtt_clear_range(dev, hole_start / PAGE_SIZE,
-					      (hole_end-hole_start) / PAGE_SIZE);
+		ggtt_vm->clear_range(ggtt_vm, hole_start / PAGE_SIZE, count);
 	}
 
 	/* And finally clear the reserved guard page */
-	dev_priv->gtt.gtt_clear_range(dev, end / PAGE_SIZE - 1, 1);
+	ggtt_vm->clear_range(ggtt_vm, end / PAGE_SIZE - 1, 1);
 }
 
 static bool
@@ -679,7 +736,7 @@ void i915_gem_init_global_gtt(struct drm_device *dev)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	unsigned long gtt_size, mappable_size;
 
-	gtt_size = dev_priv->gtt.total;
+	gtt_size = dev_priv->gtt.base.total;
 	mappable_size = dev_priv->gtt.mappable_end;
 
 	if (intel_enable_ppgtt(dev) && HAS_ALIASING_PPGTT(dev)) {
@@ -688,7 +745,7 @@ void i915_gem_init_global_gtt(struct drm_device *dev)
 		if (INTEL_INFO(dev)->gen <= 7) {
 			/* PPGTT pdes are stolen from global gtt ptes, so shrink the
 			 * aperture accordingly when using aliasing ppgtt. */
-			gtt_size -= I915_PPGTT_PD_ENTRIES*PAGE_SIZE;
+			gtt_size -= GEN6_PPGTT_PD_ENTRIES * PAGE_SIZE;
 		}
 
 		i915_gem_setup_global_gtt(dev, 0, mappable_size, gtt_size);
@@ -698,8 +755,8 @@ void i915_gem_init_global_gtt(struct drm_device *dev)
 			return;
 
 		DRM_ERROR("Aliased PPGTT setup failed %d\n", ret);
-		drm_mm_takedown(&dev_priv->mm.gtt_space);
-		gtt_size += I915_PPGTT_PD_ENTRIES*PAGE_SIZE;
+		drm_mm_takedown(&dev_priv->gtt.base.mm);
+		gtt_size += GEN6_PPGTT_PD_ENTRIES * PAGE_SIZE;
 	}
 	i915_gem_setup_global_gtt(dev, 0, mappable_size, gtt_size);
 }
@@ -724,8 +781,8 @@ static int setup_scratch_page(struct drm_device *dev)
 #else
 	dma_addr = page_to_phys(page);
 #endif
-	dev_priv->gtt.scratch_page = page;
-	dev_priv->gtt.scratch_page_dma = dma_addr;
+	dev_priv->gtt.base.scratch.page = page;
+	dev_priv->gtt.base.scratch.addr = dma_addr;
 
 	return 0;
 }
@@ -733,11 +790,13 @@ static int setup_scratch_page(struct drm_device *dev)
 static void teardown_scratch_page(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	set_pages_wb(dev_priv->gtt.scratch_page, 1);
-	pci_unmap_page(dev->pdev, dev_priv->gtt.scratch_page_dma,
+	struct page *page = dev_priv->gtt.base.scratch.page;
+
+	set_pages_wb(page, 1);
+	pci_unmap_page(dev->pdev, dev_priv->gtt.base.scratch.addr,
 		       PAGE_SIZE, PCI_DMA_BIDIRECTIONAL);
-	put_page(dev_priv->gtt.scratch_page);
-	__free_page(dev_priv->gtt.scratch_page);
+	put_page(page);
+	__free_page(page);
 }
 
 static inline unsigned int gen6_get_total_gtt_size(u16 snb_gmch_ctl)
@@ -800,17 +859,18 @@ static int gen6_gmch_probe(struct drm_device *dev,
 	if (ret)
 		DRM_ERROR("Scratch setup failed\n");
 
-	dev_priv->gtt.gtt_clear_range = gen6_ggtt_clear_range;
-	dev_priv->gtt.gtt_insert_entries = gen6_ggtt_insert_entries;
+	dev_priv->gtt.base.clear_range = gen6_ggtt_clear_range;
+	dev_priv->gtt.base.insert_entries = gen6_ggtt_insert_entries;
 
 	return ret;
 }
 
-static void gen6_gmch_remove(struct drm_device *dev)
+static void gen6_gmch_remove(struct i915_address_space *vm)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	iounmap(dev_priv->gtt.gsm);
-	teardown_scratch_page(dev_priv->dev);
+
+	struct i915_gtt *gtt = container_of(vm, struct i915_gtt, base);
+	iounmap(gtt->gsm);
+	teardown_scratch_page(vm->dev);
 }
 
 static int i915_gmch_probe(struct drm_device *dev,
@@ -831,13 +891,13 @@ static int i915_gmch_probe(struct drm_device *dev,
 	intel_gtt_get(gtt_total, stolen, mappable_base, mappable_end);
 
 	dev_priv->gtt.do_idle_maps = needs_idle_maps(dev_priv->dev);
-	dev_priv->gtt.gtt_clear_range = i915_ggtt_clear_range;
-	dev_priv->gtt.gtt_insert_entries = i915_ggtt_insert_entries;
+	dev_priv->gtt.base.clear_range = i915_ggtt_clear_range;
+	dev_priv->gtt.base.insert_entries = i915_ggtt_insert_entries;
 
 	return 0;
 }
 
-static void i915_gmch_remove(struct drm_device *dev)
+static void i915_gmch_remove(struct i915_address_space *vm)
 {
 	intel_gmch_remove();
 }
@@ -849,34 +909,35 @@ int i915_gem_gtt_init(struct drm_device *dev)
 	int ret;
 
 	if (INTEL_INFO(dev)->gen <= 5) {
-		dev_priv->gtt.gtt_probe = i915_gmch_probe;
-		dev_priv->gtt.gtt_remove = i915_gmch_remove;
+		gtt->gtt_probe = i915_gmch_probe;
+		gtt->base.cleanup = i915_gmch_remove;
 	} else {
-		dev_priv->gtt.gtt_probe = gen6_gmch_probe;
-		dev_priv->gtt.gtt_remove = gen6_gmch_remove;
-		if (IS_HASWELL(dev)) {
-			dev_priv->gtt.pte_encode = hsw_pte_encode;
-		} else if (IS_VALLEYVIEW(dev)) {
-			dev_priv->gtt.pte_encode = byt_pte_encode;
-		} else {
-			dev_priv->gtt.pte_encode = gen6_pte_encode;
-		}
+		gtt->gtt_probe = gen6_gmch_probe;
+		gtt->base.cleanup = gen6_gmch_remove;
+		if (IS_HASWELL(dev) && dev_priv->ellc_size)
+			gtt->base.pte_encode = iris_pte_encode;
+		else if (IS_HASWELL(dev))
+			gtt->base.pte_encode = hsw_pte_encode;
+		else if (IS_VALLEYVIEW(dev))
+			gtt->base.pte_encode = byt_pte_encode;
+		else if (INTEL_INFO(dev)->gen >= 7)
+			gtt->base.pte_encode = ivb_pte_encode;
+		else
+			gtt->base.pte_encode = snb_pte_encode;
 	}
 
-	ret = dev_priv->gtt.gtt_probe(dev, &dev_priv->gtt.total,
-				     &dev_priv->gtt.stolen_size,
-				     &gtt->mappable_base,
-				     &gtt->mappable_end);
+	ret = gtt->gtt_probe(dev, &gtt->base.total, &gtt->stolen_size,
+			     &gtt->mappable_base, &gtt->mappable_end);
 	if (ret)
 		return ret;
 
+	gtt->base.dev = dev;
+
 	/* GMADR is the PCI mmio aperture into the global GTT. */
 	DRM_INFO("Memory usable by graphics device = %zdM\n",
-		 dev_priv->gtt.total >> 20);
-	DRM_DEBUG_DRIVER("GMADR size = %ldM\n",
-			 dev_priv->gtt.mappable_end >> 20);
-	DRM_DEBUG_DRIVER("GTT stolen size = %zdM\n",
-			 dev_priv->gtt.stolen_size >> 20);
+		 gtt->base.total >> 20);
+	DRM_DEBUG_DRIVER("GMADR size = %ldM\n", gtt->mappable_end >> 20);
+	DRM_DEBUG_DRIVER("GTT stolen size = %zdM\n", gtt->stolen_size >> 20);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/i915/i915_gem_stolen.c b/drivers/gpu/drm/i915/i915_gem_stolen.c
index 982d4732cecf..e15a1d90037d 100644
--- a/drivers/gpu/drm/i915/i915_gem_stolen.c
+++ b/drivers/gpu/drm/i915/i915_gem_stolen.c
@@ -45,49 +45,48 @@
 static unsigned long i915_stolen_to_physical(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct pci_dev *pdev = dev_priv->bridge_dev;
+	struct resource *r;
 	u32 base;
 
-	/* On the machines I have tested the Graphics Base of Stolen Memory
-	 * is unreliable, so on those compute the base by subtracting the
-	 * stolen memory from the Top of Low Usable DRAM which is where the
-	 * BIOS places the graphics stolen memory.
+	/* Almost universally we can find the Graphics Base of Stolen Memory
+	 * at offset 0x5c in the igfx configuration space. On a few (desktop)
+	 * machines this is also mirrored in the bridge device at different
+	 * locations, or in the MCHBAR. On gen2, the layout is again slightly
+	 * different with the Graphics Segment immediately following Top of
+	 * Memory (or Top of Usable DRAM). Note it appears that TOUD is only
+	 * reported by 865g, so we just use the top of memory as determined
+	 * by the e820 probe.
 	 *
-	 * On gen2, the layout is slightly different with the Graphics Segment
-	 * immediately following Top of Memory (or Top of Usable DRAM). Note
-	 * it appears that TOUD is only reported by 865g, so we just use the
-	 * top of memory as determined by the e820 probe.
-	 *
-	 * XXX gen2 requires an unavailable symbol and 945gm fails with
-	 * its value of TOLUD.
+	 * XXX However gen2 requires an unavailable symbol.
 	 */
 	base = 0;
-	if (IS_VALLEYVIEW(dev)) {
+	if (INTEL_INFO(dev)->gen >= 3) {
+		/* Read Graphics Base of Stolen Memory directly */
 		pci_read_config_dword(dev->pdev, 0x5c, &base);
 		base &= ~((1<<20) - 1);
-	} else if (INTEL_INFO(dev)->gen >= 6) {
-		/* Read Base Data of Stolen Memory Register (BDSM) directly.
-		 * Note that there is also a MCHBAR miror at 0x1080c0 or
-		 * we could use device 2:0x5c instead.
-		*/
-		pci_read_config_dword(pdev, 0xB0, &base);
-		base &= ~4095; /* lower bits used for locking register */
-	} else if (INTEL_INFO(dev)->gen > 3 || IS_G33(dev)) {
-		/* Read Graphics Base of Stolen Memory directly */
-		pci_read_config_dword(pdev, 0xA4, &base);
+	} else { /* GEN2 */
 #if 0
-	} else if (IS_GEN3(dev)) {
-		u8 val;
-		/* Stolen is immediately below Top of Low Usable DRAM */
-		pci_read_config_byte(pdev, 0x9c, &val);
-		base = val >> 3 << 27;
-		base -= dev_priv->mm.gtt->stolen_size;
-	} else {
 		/* Stolen is immediately above Top of Memory */
 		base = max_low_pfn_mapped << PAGE_SHIFT;
 #endif
 	}
 
+	if (base == 0)
+		return 0;
+
+	/* Verify that nothing else uses this physical address. Stolen
+	 * memory should be reserved by the BIOS and hidden from the
+	 * kernel. So if the region is already marked as busy, something
+	 * is seriously wrong.
+	 */
+	r = devm_request_mem_region(dev->dev, base, dev_priv->gtt.stolen_size,
+				    "Graphics Stolen Memory");
+	if (r == NULL) {
+		DRM_ERROR("conflict detected with stolen region: [0x%08x - 0x%08x]\n",
+			  base, base + (uint32_t)dev_priv->gtt.stolen_size);
+		base = 0;
+	}
+
 	return base;
 }
 
@@ -95,32 +94,37 @@ static int i915_setup_compression(struct drm_device *dev, int size)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_mm_node *compressed_fb, *uninitialized_var(compressed_llb);
+	int ret;
 
-	/* Try to over-allocate to reduce reallocations and fragmentation */
-	compressed_fb = drm_mm_search_free(&dev_priv->mm.stolen,
-					   size <<= 1, 4096, 0);
-	if (!compressed_fb)
-		compressed_fb = drm_mm_search_free(&dev_priv->mm.stolen,
-						   size >>= 1, 4096, 0);
-	if (compressed_fb)
-		compressed_fb = drm_mm_get_block(compressed_fb, size, 4096);
+	compressed_fb = kzalloc(sizeof(*compressed_fb), GFP_KERNEL);
 	if (!compressed_fb)
-		goto err;
+		goto err_llb;
+
+	/* Try to over-allocate to reduce reallocations and fragmentation */
+	ret = drm_mm_insert_node(&dev_priv->mm.stolen, compressed_fb,
+				 size <<= 1, 4096, DRM_MM_SEARCH_DEFAULT);
+	if (ret)
+		ret = drm_mm_insert_node(&dev_priv->mm.stolen, compressed_fb,
+					 size >>= 1, 4096,
+					 DRM_MM_SEARCH_DEFAULT);
+	if (ret)
+		goto err_llb;
 
 	if (HAS_PCH_SPLIT(dev))
 		I915_WRITE(ILK_DPFC_CB_BASE, compressed_fb->start);
 	else if (IS_GM45(dev)) {
 		I915_WRITE(DPFC_CB_BASE, compressed_fb->start);
 	} else {
-		compressed_llb = drm_mm_search_free(&dev_priv->mm.stolen,
-						    4096, 4096, 0);
-		if (compressed_llb)
-			compressed_llb = drm_mm_get_block(compressed_llb,
-							  4096, 4096);
+		compressed_llb = kzalloc(sizeof(*compressed_llb), GFP_KERNEL);
 		if (!compressed_llb)
 			goto err_fb;
 
-		dev_priv->compressed_llb = compressed_llb;
+		ret = drm_mm_insert_node(&dev_priv->mm.stolen, compressed_llb,
+					 4096, 4096, DRM_MM_SEARCH_DEFAULT);
+		if (ret)
+			goto err_fb;
+
+		dev_priv->fbc.compressed_llb = compressed_llb;
 
 		I915_WRITE(FBC_CFB_BASE,
 			   dev_priv->mm.stolen_base + compressed_fb->start);
@@ -128,8 +132,8 @@ static int i915_setup_compression(struct drm_device *dev, int size)
 			   dev_priv->mm.stolen_base + compressed_llb->start);
 	}
 
-	dev_priv->compressed_fb = compressed_fb;
-	dev_priv->cfb_size = size;
+	dev_priv->fbc.compressed_fb = compressed_fb;
+	dev_priv->fbc.size = size;
 
 	DRM_DEBUG_KMS("reserved %d bytes of contiguous stolen space for FBC\n",
 		      size);
@@ -137,8 +141,10 @@ static int i915_setup_compression(struct drm_device *dev, int size)
 	return 0;
 
 err_fb:
-	drm_mm_put_block(compressed_fb);
-err:
+	kfree(compressed_llb);
+	drm_mm_remove_node(compressed_fb);
+err_llb:
+	kfree(compressed_fb);
 	pr_info_once("drm: not enough stolen space for compressed buffer (need %d more bytes), disabling. Hint: you may be able to increase stolen memory size in the BIOS to avoid this.\n", size);
 	return -ENOSPC;
 }
@@ -150,7 +156,7 @@ int i915_gem_stolen_setup_compression(struct drm_device *dev, int size)
 	if (!drm_mm_initialized(&dev_priv->mm.stolen))
 		return -ENODEV;
 
-	if (size < dev_priv->cfb_size)
+	if (size < dev_priv->fbc.size)
 		return 0;
 
 	/* Release any current block */
@@ -163,16 +169,20 @@ void i915_gem_stolen_cleanup_compression(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
-	if (dev_priv->cfb_size == 0)
+	if (dev_priv->fbc.size == 0)
 		return;
 
-	if (dev_priv->compressed_fb)
-		drm_mm_put_block(dev_priv->compressed_fb);
+	if (dev_priv->fbc.compressed_fb) {
+		drm_mm_remove_node(dev_priv->fbc.compressed_fb);
+		kfree(dev_priv->fbc.compressed_fb);
+	}
 
-	if (dev_priv->compressed_llb)
-		drm_mm_put_block(dev_priv->compressed_llb);
+	if (dev_priv->fbc.compressed_llb) {
+		drm_mm_remove_node(dev_priv->fbc.compressed_llb);
+		kfree(dev_priv->fbc.compressed_llb);
+	}
 
-	dev_priv->cfb_size = 0;
+	dev_priv->fbc.size = 0;
 }
 
 void i915_gem_cleanup_stolen(struct drm_device *dev)
@@ -191,6 +201,9 @@ int i915_gem_init_stolen(struct drm_device *dev)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	int bios_reserved = 0;
 
+	if (dev_priv->gtt.stolen_size == 0)
+		return 0;
+
 	dev_priv->mm.stolen_base = i915_stolen_to_physical(dev);
 	if (dev_priv->mm.stolen_base == 0)
 		return 0;
@@ -201,6 +214,9 @@ int i915_gem_init_stolen(struct drm_device *dev)
 	if (IS_VALLEYVIEW(dev))
 		bios_reserved = 1024*1024; /* top 1M on VLV/BYT */
 
+	if (WARN_ON(bios_reserved > dev_priv->gtt.stolen_size))
+		return 0;
+
 	/* Basic memrange allocator for stolen space */
 	drm_mm_init(&dev_priv->mm.stolen, 0, dev_priv->gtt.stolen_size -
 		    bios_reserved);
@@ -271,9 +287,7 @@ _i915_gem_object_create_stolen(struct drm_device *dev,
 	if (obj == NULL)
 		return NULL;
 
-	if (drm_gem_private_object_init(dev, &obj->base, stolen->size))
-		goto cleanup;
-
+	drm_gem_private_object_init(dev, &obj->base, stolen->size);
 	i915_gem_object_init(obj, &i915_gem_object_stolen_ops);
 
 	obj->pages = i915_pages_create_for_stolen(dev,
@@ -285,9 +299,8 @@ _i915_gem_object_create_stolen(struct drm_device *dev,
 	i915_gem_object_pin_pages(obj);
 	obj->stolen = stolen;
 
-	obj->base.write_domain = I915_GEM_DOMAIN_GTT;
-	obj->base.read_domains = I915_GEM_DOMAIN_GTT;
-	obj->cache_level = I915_CACHE_NONE;
+	obj->base.read_domains = I915_GEM_DOMAIN_CPU | I915_GEM_DOMAIN_GTT;
+	obj->cache_level = HAS_LLC(dev) ? I915_CACHE_LLC : I915_CACHE_NONE;
 
 	return obj;
 
@@ -302,6 +315,7 @@ i915_gem_object_create_stolen(struct drm_device *dev, u32 size)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_i915_gem_object *obj;
 	struct drm_mm_node *stolen;
+	int ret;
 
 	if (!drm_mm_initialized(&dev_priv->mm.stolen))
 		return NULL;
@@ -310,17 +324,23 @@ i915_gem_object_create_stolen(struct drm_device *dev, u32 size)
 	if (size == 0)
 		return NULL;
 
-	stolen = drm_mm_search_free(&dev_priv->mm.stolen, size, 4096, 0);
-	if (stolen)
-		stolen = drm_mm_get_block(stolen, size, 4096);
-	if (stolen == NULL)
+	stolen = kzalloc(sizeof(*stolen), GFP_KERNEL);
+	if (!stolen)
+		return NULL;
+
+	ret = drm_mm_insert_node(&dev_priv->mm.stolen, stolen, size,
+				 4096, DRM_MM_SEARCH_DEFAULT);
+	if (ret) {
+		kfree(stolen);
 		return NULL;
+	}
 
 	obj = _i915_gem_object_create_stolen(dev, stolen);
 	if (obj)
 		return obj;
 
-	drm_mm_put_block(stolen);
+	drm_mm_remove_node(stolen);
+	kfree(stolen);
 	return NULL;
 }
 
@@ -331,8 +351,11 @@ i915_gem_object_create_stolen_for_preallocated(struct drm_device *dev,
 					       u32 size)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct i915_address_space *ggtt = &dev_priv->gtt.base;
 	struct drm_i915_gem_object *obj;
 	struct drm_mm_node *stolen;
+	struct i915_vma *vma;
+	int ret;
 
 	if (!drm_mm_initialized(&dev_priv->mm.stolen))
 		return NULL;
@@ -347,56 +370,74 @@ i915_gem_object_create_stolen_for_preallocated(struct drm_device *dev,
 	if (WARN_ON(size == 0))
 		return NULL;
 
-	stolen = drm_mm_create_block(&dev_priv->mm.stolen,
-				     stolen_offset, size,
-				     false);
-	if (stolen == NULL) {
+	stolen = kzalloc(sizeof(*stolen), GFP_KERNEL);
+	if (!stolen)
+		return NULL;
+
+	stolen->start = stolen_offset;
+	stolen->size = size;
+	ret = drm_mm_reserve_node(&dev_priv->mm.stolen, stolen);
+	if (ret) {
 		DRM_DEBUG_KMS("failed to allocate stolen space\n");
+		kfree(stolen);
 		return NULL;
 	}
 
 	obj = _i915_gem_object_create_stolen(dev, stolen);
 	if (obj == NULL) {
 		DRM_DEBUG_KMS("failed to allocate stolen object\n");
-		drm_mm_put_block(stolen);
+		drm_mm_remove_node(stolen);
+		kfree(stolen);
 		return NULL;
 	}
 
 	/* Some objects just need physical mem from stolen space */
-	if (gtt_offset == -1)
+	if (gtt_offset == I915_GTT_OFFSET_NONE)
 		return obj;
 
+	vma = i915_gem_vma_create(obj, ggtt);
+	if (IS_ERR(vma)) {
+		ret = PTR_ERR(vma);
+		goto err_out;
+	}
+
 	/* To simplify the initialisation sequence between KMS and GTT,
 	 * we allow construction of the stolen object prior to
 	 * setting up the GTT space. The actual reservation will occur
 	 * later.
 	 */
-	if (drm_mm_initialized(&dev_priv->mm.gtt_space)) {
-		obj->gtt_space = drm_mm_create_block(&dev_priv->mm.gtt_space,
-						     gtt_offset, size,
-						     false);
-		if (obj->gtt_space == NULL) {
+	vma->node.start = gtt_offset;
+	vma->node.size = size;
+	if (drm_mm_initialized(&ggtt->mm)) {
+		ret = drm_mm_reserve_node(&ggtt->mm, &vma->node);
+		if (ret) {
 			DRM_DEBUG_KMS("failed to allocate stolen GTT space\n");
-			drm_gem_object_unreference(&obj->base);
-			return NULL;
+			goto err_vma;
 		}
-	} else
-		obj->gtt_space = I915_GTT_RESERVED;
+	}
 
-	obj->gtt_offset = gtt_offset;
 	obj->has_global_gtt_mapping = 1;
 
 	list_add_tail(&obj->global_list, &dev_priv->mm.bound_list);
-	list_add_tail(&obj->mm_list, &dev_priv->mm.inactive_list);
+	list_add_tail(&vma->mm_list, &ggtt->inactive_list);
 
 	return obj;
+
+err_vma:
+	i915_gem_vma_destroy(vma);
+err_out:
+	drm_mm_remove_node(stolen);
+	kfree(stolen);
+	drm_gem_object_unreference(&obj->base);
+	return NULL;
 }
 
 void
 i915_gem_object_release_stolen(struct drm_i915_gem_object *obj)
 {
 	if (obj->stolen) {
-		drm_mm_put_block(obj->stolen);
+		drm_mm_remove_node(obj->stolen);
+		kfree(obj->stolen);
 		obj->stolen = NULL;
 	}
 }
diff --git a/drivers/gpu/drm/i915/i915_gem_tiling.c b/drivers/gpu/drm/i915/i915_gem_tiling.c
index 537545be69db..032e9ef9c896 100644
--- a/drivers/gpu/drm/i915/i915_gem_tiling.c
+++ b/drivers/gpu/drm/i915/i915_gem_tiling.c
@@ -268,18 +268,18 @@ i915_gem_object_fence_ok(struct drm_i915_gem_object *obj, int tiling_mode)
 		return true;
 
 	if (INTEL_INFO(obj->base.dev)->gen == 3) {
-		if (obj->gtt_offset & ~I915_FENCE_START_MASK)
+		if (i915_gem_obj_ggtt_offset(obj) & ~I915_FENCE_START_MASK)
 			return false;
 	} else {
-		if (obj->gtt_offset & ~I830_FENCE_START_MASK)
+		if (i915_gem_obj_ggtt_offset(obj) & ~I830_FENCE_START_MASK)
 			return false;
 	}
 
 	size = i915_gem_get_gtt_size(obj->base.dev, obj->base.size, tiling_mode);
-	if (obj->gtt_space->size != size)
+	if (i915_gem_obj_ggtt_size(obj) != size)
 		return false;
 
-	if (obj->gtt_offset & (size - 1))
+	if (i915_gem_obj_ggtt_offset(obj) & (size - 1))
 		return false;
 
 	return true;
@@ -359,18 +359,19 @@ i915_gem_set_tiling(struct drm_device *dev, void *data,
 		 */
 
 		obj->map_and_fenceable =
-			obj->gtt_space == NULL ||
-			(obj->gtt_offset + obj->base.size <= dev_priv->gtt.mappable_end &&
+			!i915_gem_obj_ggtt_bound(obj) ||
+			(i915_gem_obj_ggtt_offset(obj) +
+			 obj->base.size <= dev_priv->gtt.mappable_end &&
 			 i915_gem_object_fence_ok(obj, args->tiling_mode));
 
 		/* Rebind if we need a change of alignment */
 		if (!obj->map_and_fenceable) {
-			u32 unfenced_alignment =
+			u32 unfenced_align =
 				i915_gem_get_gtt_alignment(dev, obj->base.size,
 							    args->tiling_mode,
 							    false);
-			if (obj->gtt_offset & (unfenced_alignment - 1))
-				ret = i915_gem_object_unbind(obj);
+			if (i915_gem_obj_ggtt_offset(obj) & (unfenced_align - 1))
+				ret = i915_gem_object_ggtt_unbind(obj);
 		}
 
 		if (ret == 0) {
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
new file mode 100644
index 000000000000..dae364f0028c
--- /dev/null
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -0,0 +1,1021 @@
+/*
+ * Copyright (c) 2008 Intel Corporation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the next
+ * paragraph) shall be included in all copies or substantial portions of the
+ * Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ *
+ * Authors:
+ *    Eric Anholt <eric@anholt.net>
+ *    Keith Packard <keithp@keithp.com>
+ *    Mika Kuoppala <mika.kuoppala@intel.com>
+ *
+ */
+
+#include <generated/utsrelease.h>
+#include "i915_drv.h"
+
+static const char *yesno(int v)
+{
+	return v ? "yes" : "no";
+}
+
+static const char *ring_str(int ring)
+{
+	switch (ring) {
+	case RCS: return "render";
+	case VCS: return "bsd";
+	case BCS: return "blt";
+	case VECS: return "vebox";
+	default: return "";
+	}
+}
+
+static const char *pin_flag(int pinned)
+{
+	if (pinned > 0)
+		return " P";
+	else if (pinned < 0)
+		return " p";
+	else
+		return "";
+}
+
+static const char *tiling_flag(int tiling)
+{
+	switch (tiling) {
+	default:
+	case I915_TILING_NONE: return "";
+	case I915_TILING_X: return " X";
+	case I915_TILING_Y: return " Y";
+	}
+}
+
+static const char *dirty_flag(int dirty)
+{
+	return dirty ? " dirty" : "";
+}
+
+static const char *purgeable_flag(int purgeable)
+{
+	return purgeable ? " purgeable" : "";
+}
+
+static bool __i915_error_ok(struct drm_i915_error_state_buf *e)
+{
+
+	if (!e->err && WARN(e->bytes > (e->size - 1), "overflow")) {
+		e->err = -ENOSPC;
+		return false;
+	}
+
+	if (e->bytes == e->size - 1 || e->err)
+		return false;
+
+	return true;
+}
+
+static bool __i915_error_seek(struct drm_i915_error_state_buf *e,
+			      unsigned len)
+{
+	if (e->pos + len <= e->start) {
+		e->pos += len;
+		return false;
+	}
+
+	/* First vsnprintf needs to fit in its entirety for memmove */
+	if (len >= e->size) {
+		e->err = -EIO;
+		return false;
+	}
+
+	return true;
+}
+
+static void __i915_error_advance(struct drm_i915_error_state_buf *e,
+				 unsigned len)
+{
+	/* If this is first printf in this window, adjust it so that
+	 * start position matches start of the buffer
+	 */
+
+	if (e->pos < e->start) {
+		const size_t off = e->start - e->pos;
+
+		/* Should not happen but be paranoid */
+		if (off > len || e->bytes) {
+			e->err = -EIO;
+			return;
+		}
+
+		memmove(e->buf, e->buf + off, len - off);
+		e->bytes = len - off;
+		e->pos = e->start;
+		return;
+	}
+
+	e->bytes += len;
+	e->pos += len;
+}
+
+static void i915_error_vprintf(struct drm_i915_error_state_buf *e,
+			       const char *f, va_list args)
+{
+	unsigned len;
+
+	if (!__i915_error_ok(e))
+		return;
+
+	/* Seek the first printf which is hits start position */
+	if (e->pos < e->start) {
+		va_list tmp;
+
+		va_copy(tmp, args);
+		if (!__i915_error_seek(e, vsnprintf(NULL, 0, f, tmp)))
+			return;
+	}
+
+	len = vsnprintf(e->buf + e->bytes, e->size - e->bytes, f, args);
+	if (len >= e->size - e->bytes)
+		len = e->size - e->bytes - 1;
+
+	__i915_error_advance(e, len);
+}
+
+static void i915_error_puts(struct drm_i915_error_state_buf *e,
+			    const char *str)
+{
+	unsigned len;
+
+	if (!__i915_error_ok(e))
+		return;
+
+	len = strlen(str);
+
+	/* Seek the first printf which is hits start position */
+	if (e->pos < e->start) {
+		if (!__i915_error_seek(e, len))
+			return;
+	}
+
+	if (len >= e->size - e->bytes)
+		len = e->size - e->bytes - 1;
+	memcpy(e->buf + e->bytes, str, len);
+
+	__i915_error_advance(e, len);
+}
+
+#define err_printf(e, ...) i915_error_printf(e, __VA_ARGS__)
+#define err_puts(e, s) i915_error_puts(e, s)
+
+static void print_error_buffers(struct drm_i915_error_state_buf *m,
+				const char *name,
+				struct drm_i915_error_buffer *err,
+				int count)
+{
+	err_printf(m, "%s [%d]:\n", name, count);
+
+	while (count--) {
+		err_printf(m, "  %08x %8u %02x %02x %x %x",
+			   err->gtt_offset,
+			   err->size,
+			   err->read_domains,
+			   err->write_domain,
+			   err->rseqno, err->wseqno);
+		err_puts(m, pin_flag(err->pinned));
+		err_puts(m, tiling_flag(err->tiling));
+		err_puts(m, dirty_flag(err->dirty));
+		err_puts(m, purgeable_flag(err->purgeable));
+		err_puts(m, err->ring != -1 ? " " : "");
+		err_puts(m, ring_str(err->ring));
+		err_puts(m, i915_cache_level_str(err->cache_level));
+
+		if (err->name)
+			err_printf(m, " (name: %d)", err->name);
+		if (err->fence_reg != I915_FENCE_REG_NONE)
+			err_printf(m, " (fence: %d)", err->fence_reg);
+
+		err_puts(m, "\n");
+		err++;
+	}
+}
+
+static void i915_ring_error_state(struct drm_i915_error_state_buf *m,
+				  struct drm_device *dev,
+				  struct drm_i915_error_state *error,
+				  unsigned ring)
+{
+	BUG_ON(ring >= I915_NUM_RINGS); /* shut up confused gcc */
+	err_printf(m, "%s command stream:\n", ring_str(ring));
+	err_printf(m, "  HEAD: 0x%08x\n", error->head[ring]);
+	err_printf(m, "  TAIL: 0x%08x\n", error->tail[ring]);
+	err_printf(m, "  CTL: 0x%08x\n", error->ctl[ring]);
+	err_printf(m, "  ACTHD: 0x%08x\n", error->acthd[ring]);
+	err_printf(m, "  IPEIR: 0x%08x\n", error->ipeir[ring]);
+	err_printf(m, "  IPEHR: 0x%08x\n", error->ipehr[ring]);
+	err_printf(m, "  INSTDONE: 0x%08x\n", error->instdone[ring]);
+	if (ring == RCS && INTEL_INFO(dev)->gen >= 4)
+		err_printf(m, "  BBADDR: 0x%08llx\n", error->bbaddr);
+
+	if (INTEL_INFO(dev)->gen >= 4)
+		err_printf(m, "  INSTPS: 0x%08x\n", error->instps[ring]);
+	err_printf(m, "  INSTPM: 0x%08x\n", error->instpm[ring]);
+	err_printf(m, "  FADDR: 0x%08x\n", error->faddr[ring]);
+	if (INTEL_INFO(dev)->gen >= 6) {
+		err_printf(m, "  RC PSMI: 0x%08x\n", error->rc_psmi[ring]);
+		err_printf(m, "  FAULT_REG: 0x%08x\n", error->fault_reg[ring]);
+		err_printf(m, "  SYNC_0: 0x%08x [last synced 0x%08x]\n",
+			   error->semaphore_mboxes[ring][0],
+			   error->semaphore_seqno[ring][0]);
+		err_printf(m, "  SYNC_1: 0x%08x [last synced 0x%08x]\n",
+			   error->semaphore_mboxes[ring][1],
+			   error->semaphore_seqno[ring][1]);
+		if (HAS_VEBOX(dev)) {
+			err_printf(m, "  SYNC_2: 0x%08x [last synced 0x%08x]\n",
+				   error->semaphore_mboxes[ring][2],
+				   error->semaphore_seqno[ring][2]);
+		}
+	}
+	err_printf(m, "  seqno: 0x%08x\n", error->seqno[ring]);
+	err_printf(m, "  waiting: %s\n", yesno(error->waiting[ring]));
+	err_printf(m, "  ring->head: 0x%08x\n", error->cpu_ring_head[ring]);
+	err_printf(m, "  ring->tail: 0x%08x\n", error->cpu_ring_tail[ring]);
+}
+
+void i915_error_printf(struct drm_i915_error_state_buf *e, const char *f, ...)
+{
+	va_list args;
+
+	va_start(args, f);
+	i915_error_vprintf(e, f, args);
+	va_end(args);
+}
+
+int i915_error_state_to_str(struct drm_i915_error_state_buf *m,
+			    const struct i915_error_state_file_priv *error_priv)
+{
+	struct drm_device *dev = error_priv->dev;
+	drm_i915_private_t *dev_priv = dev->dev_private;
+	struct drm_i915_error_state *error = error_priv->error;
+	struct intel_ring_buffer *ring;
+	int i, j, page, offset, elt;
+
+	if (!error) {
+		err_printf(m, "no error state collected\n");
+		goto out;
+	}
+
+	err_printf(m, "Time: %ld s %ld us\n", error->time.tv_sec,
+		   error->time.tv_usec);
+	err_printf(m, "Kernel: " UTS_RELEASE "\n");
+	err_printf(m, "PCI ID: 0x%04x\n", dev->pci_device);
+	err_printf(m, "EIR: 0x%08x\n", error->eir);
+	err_printf(m, "IER: 0x%08x\n", error->ier);
+	err_printf(m, "PGTBL_ER: 0x%08x\n", error->pgtbl_er);
+	err_printf(m, "FORCEWAKE: 0x%08x\n", error->forcewake);
+	err_printf(m, "DERRMR: 0x%08x\n", error->derrmr);
+	err_printf(m, "CCID: 0x%08x\n", error->ccid);
+
+	for (i = 0; i < dev_priv->num_fence_regs; i++)
+		err_printf(m, "  fence[%d] = %08llx\n", i, error->fence[i]);
+
+	for (i = 0; i < ARRAY_SIZE(error->extra_instdone); i++)
+		err_printf(m, "  INSTDONE_%d: 0x%08x\n", i,
+			   error->extra_instdone[i]);
+
+	if (INTEL_INFO(dev)->gen >= 6) {
+		err_printf(m, "ERROR: 0x%08x\n", error->error);
+		err_printf(m, "DONE_REG: 0x%08x\n", error->done_reg);
+	}
+
+	if (INTEL_INFO(dev)->gen == 7)
+		err_printf(m, "ERR_INT: 0x%08x\n", error->err_int);
+
+	for_each_ring(ring, dev_priv, i)
+		i915_ring_error_state(m, dev, error, i);
+
+	if (error->active_bo)
+		print_error_buffers(m, "Active",
+				    error->active_bo[0],
+				    error->active_bo_count[0]);
+
+	if (error->pinned_bo)
+		print_error_buffers(m, "Pinned",
+				    error->pinned_bo[0],
+				    error->pinned_bo_count[0]);
+
+	for (i = 0; i < ARRAY_SIZE(error->ring); i++) {
+		struct drm_i915_error_object *obj;
+
+		if ((obj = error->ring[i].batchbuffer)) {
+			err_printf(m, "%s --- gtt_offset = 0x%08x\n",
+				   dev_priv->ring[i].name,
+				   obj->gtt_offset);
+			offset = 0;
+			for (page = 0; page < obj->page_count; page++) {
+				for (elt = 0; elt < PAGE_SIZE/4; elt++) {
+					err_printf(m, "%08x :  %08x\n", offset,
+						   obj->pages[page][elt]);
+					offset += 4;
+				}
+			}
+		}
+
+		if (error->ring[i].num_requests) {
+			err_printf(m, "%s --- %d requests\n",
+				   dev_priv->ring[i].name,
+				   error->ring[i].num_requests);
+			for (j = 0; j < error->ring[i].num_requests; j++) {
+				err_printf(m, "  seqno 0x%08x, emitted %ld, tail 0x%08x\n",
+					   error->ring[i].requests[j].seqno,
+					   error->ring[i].requests[j].jiffies,
+					   error->ring[i].requests[j].tail);
+			}
+		}
+
+		if ((obj = error->ring[i].ringbuffer)) {
+			err_printf(m, "%s --- ringbuffer = 0x%08x\n",
+				   dev_priv->ring[i].name,
+				   obj->gtt_offset);
+			offset = 0;
+			for (page = 0; page < obj->page_count; page++) {
+				for (elt = 0; elt < PAGE_SIZE/4; elt++) {
+					err_printf(m, "%08x :  %08x\n",
+						   offset,
+						   obj->pages[page][elt]);
+					offset += 4;
+				}
+			}
+		}
+
+		obj = error->ring[i].ctx;
+		if (obj) {
+			err_printf(m, "%s --- HW Context = 0x%08x\n",
+				   dev_priv->ring[i].name,
+				   obj->gtt_offset);
+			offset = 0;
+			for (elt = 0; elt < PAGE_SIZE/16; elt += 4) {
+				err_printf(m, "[%04x] %08x %08x %08x %08x\n",
+					   offset,
+					   obj->pages[0][elt],
+					   obj->pages[0][elt+1],
+					   obj->pages[0][elt+2],
+					   obj->pages[0][elt+3]);
+					offset += 16;
+			}
+		}
+	}
+
+	if (error->overlay)
+		intel_overlay_print_error_state(m, error->overlay);
+
+	if (error->display)
+		intel_display_print_error_state(m, dev, error->display);
+
+out:
+	if (m->bytes == 0 && m->err)
+		return m->err;
+
+	return 0;
+}
+
+int i915_error_state_buf_init(struct drm_i915_error_state_buf *ebuf,
+			      size_t count, loff_t pos)
+{
+	memset(ebuf, 0, sizeof(*ebuf));
+
+	/* We need to have enough room to store any i915_error_state printf
+	 * so that we can move it to start position.
+	 */
+	ebuf->size = count + 1 > PAGE_SIZE ? count + 1 : PAGE_SIZE;
+	ebuf->buf = kmalloc(ebuf->size,
+				GFP_TEMPORARY | __GFP_NORETRY | __GFP_NOWARN);
+
+	if (ebuf->buf == NULL) {
+		ebuf->size = PAGE_SIZE;
+		ebuf->buf = kmalloc(ebuf->size, GFP_TEMPORARY);
+	}
+
+	if (ebuf->buf == NULL) {
+		ebuf->size = 128;
+		ebuf->buf = kmalloc(ebuf->size, GFP_TEMPORARY);
+	}
+
+	if (ebuf->buf == NULL)
+		return -ENOMEM;
+
+	ebuf->start = pos;
+
+	return 0;
+}
+
+static void i915_error_object_free(struct drm_i915_error_object *obj)
+{
+	int page;
+
+	if (obj == NULL)
+		return;
+
+	for (page = 0; page < obj->page_count; page++)
+		kfree(obj->pages[page]);
+
+	kfree(obj);
+}
+
+static void i915_error_state_free(struct kref *error_ref)
+{
+	struct drm_i915_error_state *error = container_of(error_ref,
+							  typeof(*error), ref);
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(error->ring); i++) {
+		i915_error_object_free(error->ring[i].batchbuffer);
+		i915_error_object_free(error->ring[i].ringbuffer);
+		i915_error_object_free(error->ring[i].ctx);
+		kfree(error->ring[i].requests);
+	}
+
+	kfree(error->active_bo);
+	kfree(error->overlay);
+	kfree(error->display);
+	kfree(error);
+}
+
+static struct drm_i915_error_object *
+i915_error_object_create_sized(struct drm_i915_private *dev_priv,
+			       struct drm_i915_gem_object *src,
+			       const int num_pages)
+{
+	struct drm_i915_error_object *dst;
+	int i;
+	u32 reloc_offset;
+
+	if (src == NULL || src->pages == NULL)
+		return NULL;
+
+	dst = kmalloc(sizeof(*dst) + num_pages * sizeof(u32 *), GFP_ATOMIC);
+	if (dst == NULL)
+		return NULL;
+
+	reloc_offset = dst->gtt_offset = i915_gem_obj_ggtt_offset(src);
+	for (i = 0; i < num_pages; i++) {
+		unsigned long flags;
+		void *d;
+
+		d = kmalloc(PAGE_SIZE, GFP_ATOMIC);
+		if (d == NULL)
+			goto unwind;
+
+		local_irq_save(flags);
+		if (reloc_offset < dev_priv->gtt.mappable_end &&
+		    src->has_global_gtt_mapping) {
+			void __iomem *s;
+
+			/* Simply ignore tiling or any overlapping fence.
+			 * It's part of the error state, and this hopefully
+			 * captures what the GPU read.
+			 */
+
+			s = io_mapping_map_atomic_wc(dev_priv->gtt.mappable,
+						     reloc_offset);
+			memcpy_fromio(d, s, PAGE_SIZE);
+			io_mapping_unmap_atomic(s);
+		} else if (src->stolen) {
+			unsigned long offset;
+
+			offset = dev_priv->mm.stolen_base;
+			offset += src->stolen->start;
+			offset += i << PAGE_SHIFT;
+
+			memcpy_fromio(d, (void __iomem *) offset, PAGE_SIZE);
+		} else {
+			struct page *page;
+			void *s;
+
+			page = i915_gem_object_get_page(src, i);
+
+			drm_clflush_pages(&page, 1);
+
+			s = kmap_atomic(page);
+			memcpy(d, s, PAGE_SIZE);
+			kunmap_atomic(s);
+
+			drm_clflush_pages(&page, 1);
+		}
+		local_irq_restore(flags);
+
+		dst->pages[i] = d;
+
+		reloc_offset += PAGE_SIZE;
+	}
+	dst->page_count = num_pages;
+
+	return dst;
+
+unwind:
+	while (i--)
+		kfree(dst->pages[i]);
+	kfree(dst);
+	return NULL;
+}
+#define i915_error_object_create(dev_priv, src) \
+	i915_error_object_create_sized((dev_priv), (src), \
+				       (src)->base.size>>PAGE_SHIFT)
+
+static void capture_bo(struct drm_i915_error_buffer *err,
+		       struct drm_i915_gem_object *obj)
+{
+	err->size = obj->base.size;
+	err->name = obj->base.name;
+	err->rseqno = obj->last_read_seqno;
+	err->wseqno = obj->last_write_seqno;
+	err->gtt_offset = i915_gem_obj_ggtt_offset(obj);
+	err->read_domains = obj->base.read_domains;
+	err->write_domain = obj->base.write_domain;
+	err->fence_reg = obj->fence_reg;
+	err->pinned = 0;
+	if (obj->pin_count > 0)
+		err->pinned = 1;
+	if (obj->user_pin_count > 0)
+		err->pinned = -1;
+	err->tiling = obj->tiling_mode;
+	err->dirty = obj->dirty;
+	err->purgeable = obj->madv != I915_MADV_WILLNEED;
+	err->ring = obj->ring ? obj->ring->id : -1;
+	err->cache_level = obj->cache_level;
+}
+
+static u32 capture_active_bo(struct drm_i915_error_buffer *err,
+			     int count, struct list_head *head)
+{
+	struct i915_vma *vma;
+	int i = 0;
+
+	list_for_each_entry(vma, head, mm_list) {
+		capture_bo(err++, vma->obj);
+		if (++i == count)
+			break;
+	}
+
+	return i;
+}
+
+static u32 capture_pinned_bo(struct drm_i915_error_buffer *err,
+			     int count, struct list_head *head)
+{
+	struct drm_i915_gem_object *obj;
+	int i = 0;
+
+	list_for_each_entry(obj, head, global_list) {
+		if (obj->pin_count == 0)
+			continue;
+
+		capture_bo(err++, obj);
+		if (++i == count)
+			break;
+	}
+
+	return i;
+}
+
+static void i915_gem_record_fences(struct drm_device *dev,
+				   struct drm_i915_error_state *error)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	int i;
+
+	/* Fences */
+	switch (INTEL_INFO(dev)->gen) {
+	case 7:
+	case 6:
+		for (i = 0; i < dev_priv->num_fence_regs; i++)
+			error->fence[i] = I915_READ64(FENCE_REG_SANDYBRIDGE_0 + (i * 8));
+		break;
+	case 5:
+	case 4:
+		for (i = 0; i < 16; i++)
+			error->fence[i] = I915_READ64(FENCE_REG_965_0 + (i * 8));
+		break;
+	case 3:
+		if (IS_I945G(dev) || IS_I945GM(dev) || IS_G33(dev))
+			for (i = 0; i < 8; i++)
+				error->fence[i+8] = I915_READ(FENCE_REG_945_8 + (i * 4));
+	case 2:
+		for (i = 0; i < 8; i++)
+			error->fence[i] = I915_READ(FENCE_REG_830_0 + (i * 4));
+		break;
+
+	default:
+		BUG();
+	}
+}
+
+static struct drm_i915_error_object *
+i915_error_first_batchbuffer(struct drm_i915_private *dev_priv,
+			     struct intel_ring_buffer *ring)
+{
+	struct i915_address_space *vm;
+	struct i915_vma *vma;
+	struct drm_i915_gem_object *obj;
+	u32 seqno;
+
+	if (!ring->get_seqno)
+		return NULL;
+
+	if (HAS_BROKEN_CS_TLB(dev_priv->dev)) {
+		u32 acthd = I915_READ(ACTHD);
+
+		if (WARN_ON(ring->id != RCS))
+			return NULL;
+
+		obj = ring->scratch.obj;
+		if (acthd >= i915_gem_obj_ggtt_offset(obj) &&
+		    acthd < i915_gem_obj_ggtt_offset(obj) + obj->base.size)
+			return i915_error_object_create(dev_priv, obj);
+	}
+
+	seqno = ring->get_seqno(ring, false);
+	list_for_each_entry(vm, &dev_priv->vm_list, global_link) {
+		list_for_each_entry(vma, &vm->active_list, mm_list) {
+			obj = vma->obj;
+			if (obj->ring != ring)
+				continue;
+
+			if (i915_seqno_passed(seqno, obj->last_read_seqno))
+				continue;
+
+			if ((obj->base.read_domains & I915_GEM_DOMAIN_COMMAND) == 0)
+				continue;
+
+			/* We need to copy these to an anonymous buffer as the simplest
+			 * method to avoid being overwritten by userspace.
+			 */
+			return i915_error_object_create(dev_priv, obj);
+		}
+	}
+
+	return NULL;
+}
+
+static void i915_record_ring_state(struct drm_device *dev,
+				   struct drm_i915_error_state *error,
+				   struct intel_ring_buffer *ring)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	if (INTEL_INFO(dev)->gen >= 6) {
+		error->rc_psmi[ring->id] = I915_READ(ring->mmio_base + 0x50);
+		error->fault_reg[ring->id] = I915_READ(RING_FAULT_REG(ring));
+		error->semaphore_mboxes[ring->id][0]
+			= I915_READ(RING_SYNC_0(ring->mmio_base));
+		error->semaphore_mboxes[ring->id][1]
+			= I915_READ(RING_SYNC_1(ring->mmio_base));
+		error->semaphore_seqno[ring->id][0] = ring->sync_seqno[0];
+		error->semaphore_seqno[ring->id][1] = ring->sync_seqno[1];
+	}
+
+	if (HAS_VEBOX(dev)) {
+		error->semaphore_mboxes[ring->id][2] =
+			I915_READ(RING_SYNC_2(ring->mmio_base));
+		error->semaphore_seqno[ring->id][2] = ring->sync_seqno[2];
+	}
+
+	if (INTEL_INFO(dev)->gen >= 4) {
+		error->faddr[ring->id] = I915_READ(RING_DMA_FADD(ring->mmio_base));
+		error->ipeir[ring->id] = I915_READ(RING_IPEIR(ring->mmio_base));
+		error->ipehr[ring->id] = I915_READ(RING_IPEHR(ring->mmio_base));
+		error->instdone[ring->id] = I915_READ(RING_INSTDONE(ring->mmio_base));
+		error->instps[ring->id] = I915_READ(RING_INSTPS(ring->mmio_base));
+		if (ring->id == RCS)
+			error->bbaddr = I915_READ64(BB_ADDR);
+	} else {
+		error->faddr[ring->id] = I915_READ(DMA_FADD_I8XX);
+		error->ipeir[ring->id] = I915_READ(IPEIR);
+		error->ipehr[ring->id] = I915_READ(IPEHR);
+		error->instdone[ring->id] = I915_READ(INSTDONE);
+	}
+
+	error->waiting[ring->id] = waitqueue_active(&ring->irq_queue);
+	error->instpm[ring->id] = I915_READ(RING_INSTPM(ring->mmio_base));
+	error->seqno[ring->id] = ring->get_seqno(ring, false);
+	error->acthd[ring->id] = intel_ring_get_active_head(ring);
+	error->head[ring->id] = I915_READ_HEAD(ring);
+	error->tail[ring->id] = I915_READ_TAIL(ring);
+	error->ctl[ring->id] = I915_READ_CTL(ring);
+
+	error->cpu_ring_head[ring->id] = ring->head;
+	error->cpu_ring_tail[ring->id] = ring->tail;
+}
+
+
+static void i915_gem_record_active_context(struct intel_ring_buffer *ring,
+					   struct drm_i915_error_state *error,
+					   struct drm_i915_error_ring *ering)
+{
+	struct drm_i915_private *dev_priv = ring->dev->dev_private;
+	struct drm_i915_gem_object *obj;
+
+	/* Currently render ring is the only HW context user */
+	if (ring->id != RCS || !error->ccid)
+		return;
+
+	list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) {
+		if ((error->ccid & PAGE_MASK) == i915_gem_obj_ggtt_offset(obj)) {
+			ering->ctx = i915_error_object_create_sized(dev_priv,
+								    obj, 1);
+			break;
+		}
+	}
+}
+
+static void i915_gem_record_rings(struct drm_device *dev,
+				  struct drm_i915_error_state *error)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_ring_buffer *ring;
+	struct drm_i915_gem_request *request;
+	int i, count;
+
+	for_each_ring(ring, dev_priv, i) {
+		i915_record_ring_state(dev, error, ring);
+
+		error->ring[i].batchbuffer =
+			i915_error_first_batchbuffer(dev_priv, ring);
+
+		error->ring[i].ringbuffer =
+			i915_error_object_create(dev_priv, ring->obj);
+
+
+		i915_gem_record_active_context(ring, error, &error->ring[i]);
+
+		count = 0;
+		list_for_each_entry(request, &ring->request_list, list)
+			count++;
+
+		error->ring[i].num_requests = count;
+		error->ring[i].requests =
+			kmalloc(count*sizeof(struct drm_i915_error_request),
+				GFP_ATOMIC);
+		if (error->ring[i].requests == NULL) {
+			error->ring[i].num_requests = 0;
+			continue;
+		}
+
+		count = 0;
+		list_for_each_entry(request, &ring->request_list, list) {
+			struct drm_i915_error_request *erq;
+
+			erq = &error->ring[i].requests[count++];
+			erq->seqno = request->seqno;
+			erq->jiffies = request->emitted_jiffies;
+			erq->tail = request->tail;
+		}
+	}
+}
+
+/* FIXME: Since pin count/bound list is global, we duplicate what we capture per
+ * VM.
+ */
+static void i915_gem_capture_vm(struct drm_i915_private *dev_priv,
+				struct drm_i915_error_state *error,
+				struct i915_address_space *vm,
+				const int ndx)
+{
+	struct drm_i915_error_buffer *active_bo = NULL, *pinned_bo = NULL;
+	struct drm_i915_gem_object *obj;
+	struct i915_vma *vma;
+	int i;
+
+	i = 0;
+	list_for_each_entry(vma, &vm->active_list, mm_list)
+		i++;
+	error->active_bo_count[ndx] = i;
+	list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list)
+		if (obj->pin_count)
+			i++;
+	error->pinned_bo_count[ndx] = i - error->active_bo_count[ndx];
+
+	if (i) {
+		active_bo = kmalloc(sizeof(*active_bo)*i, GFP_ATOMIC);
+		if (active_bo)
+			pinned_bo = active_bo + error->active_bo_count[ndx];
+	}
+
+	if (active_bo)
+		error->active_bo_count[ndx] =
+			capture_active_bo(active_bo,
+					  error->active_bo_count[ndx],
+					  &vm->active_list);
+
+	if (pinned_bo)
+		error->pinned_bo_count[ndx] =
+			capture_pinned_bo(pinned_bo,
+					  error->pinned_bo_count[ndx],
+					  &dev_priv->mm.bound_list);
+	error->active_bo[ndx] = active_bo;
+	error->pinned_bo[ndx] = pinned_bo;
+}
+
+static void i915_gem_capture_buffers(struct drm_i915_private *dev_priv,
+				     struct drm_i915_error_state *error)
+{
+	struct i915_address_space *vm;
+	int cnt = 0, i = 0;
+
+	list_for_each_entry(vm, &dev_priv->vm_list, global_link)
+		cnt++;
+
+	if (WARN(cnt > 1, "Multiple VMs not yet supported\n"))
+		cnt = 1;
+
+	vm = &dev_priv->gtt.base;
+
+	error->active_bo = kcalloc(cnt, sizeof(*error->active_bo), GFP_ATOMIC);
+	error->pinned_bo = kcalloc(cnt, sizeof(*error->pinned_bo), GFP_ATOMIC);
+	error->active_bo_count = kcalloc(cnt, sizeof(*error->active_bo_count),
+					 GFP_ATOMIC);
+	error->pinned_bo_count = kcalloc(cnt, sizeof(*error->pinned_bo_count),
+					 GFP_ATOMIC);
+
+	list_for_each_entry(vm, &dev_priv->vm_list, global_link)
+		i915_gem_capture_vm(dev_priv, error, vm, i++);
+}
+
+/**
+ * i915_capture_error_state - capture an error record for later analysis
+ * @dev: drm device
+ *
+ * Should be called when an error is detected (either a hang or an error
+ * interrupt) to capture error state from the time of the error.  Fills
+ * out a structure which becomes available in debugfs for user level tools
+ * to pick up.
+ */
+void i915_capture_error_state(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_error_state *error;
+	unsigned long flags;
+	int pipe;
+
+	spin_lock_irqsave(&dev_priv->gpu_error.lock, flags);
+	error = dev_priv->gpu_error.first_error;
+	spin_unlock_irqrestore(&dev_priv->gpu_error.lock, flags);
+	if (error)
+		return;
+
+	/* Account for pipe specific data like PIPE*STAT */
+	error = kzalloc(sizeof(*error), GFP_ATOMIC);
+	if (!error) {
+		DRM_DEBUG_DRIVER("out of memory, not capturing error state\n");
+		return;
+	}
+
+	DRM_INFO("capturing error event; look for more information in "
+		 "/sys/class/drm/card%d/error\n", dev->primary->index);
+
+	kref_init(&error->ref);
+	error->eir = I915_READ(EIR);
+	error->pgtbl_er = I915_READ(PGTBL_ER);
+	if (HAS_HW_CONTEXTS(dev))
+		error->ccid = I915_READ(CCID);
+
+	if (HAS_PCH_SPLIT(dev))
+		error->ier = I915_READ(DEIER) | I915_READ(GTIER);
+	else if (IS_VALLEYVIEW(dev))
+		error->ier = I915_READ(GTIER) | I915_READ(VLV_IER);
+	else if (IS_GEN2(dev))
+		error->ier = I915_READ16(IER);
+	else
+		error->ier = I915_READ(IER);
+
+	if (INTEL_INFO(dev)->gen >= 6)
+		error->derrmr = I915_READ(DERRMR);
+
+	if (IS_VALLEYVIEW(dev))
+		error->forcewake = I915_READ(FORCEWAKE_VLV);
+	else if (INTEL_INFO(dev)->gen >= 7)
+		error->forcewake = I915_READ(FORCEWAKE_MT);
+	else if (INTEL_INFO(dev)->gen == 6)
+		error->forcewake = I915_READ(FORCEWAKE);
+
+	if (!HAS_PCH_SPLIT(dev))
+		for_each_pipe(pipe)
+			error->pipestat[pipe] = I915_READ(PIPESTAT(pipe));
+
+	if (INTEL_INFO(dev)->gen >= 6) {
+		error->error = I915_READ(ERROR_GEN6);
+		error->done_reg = I915_READ(DONE_REG);
+	}
+
+	if (INTEL_INFO(dev)->gen == 7)
+		error->err_int = I915_READ(GEN7_ERR_INT);
+
+	i915_get_extra_instdone(dev, error->extra_instdone);
+
+	i915_gem_capture_buffers(dev_priv, error);
+	i915_gem_record_fences(dev, error);
+	i915_gem_record_rings(dev, error);
+
+	do_gettimeofday(&error->time);
+
+	error->overlay = intel_overlay_capture_error_state(dev);
+	error->display = intel_display_capture_error_state(dev);
+
+	spin_lock_irqsave(&dev_priv->gpu_error.lock, flags);
+	if (dev_priv->gpu_error.first_error == NULL) {
+		dev_priv->gpu_error.first_error = error;
+		error = NULL;
+	}
+	spin_unlock_irqrestore(&dev_priv->gpu_error.lock, flags);
+
+	if (error)
+		i915_error_state_free(&error->ref);
+}
+
+void i915_error_state_get(struct drm_device *dev,
+			  struct i915_error_state_file_priv *error_priv)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	unsigned long flags;
+
+	spin_lock_irqsave(&dev_priv->gpu_error.lock, flags);
+	error_priv->error = dev_priv->gpu_error.first_error;
+	if (error_priv->error)
+		kref_get(&error_priv->error->ref);
+	spin_unlock_irqrestore(&dev_priv->gpu_error.lock, flags);
+
+}
+
+void i915_error_state_put(struct i915_error_state_file_priv *error_priv)
+{
+	if (error_priv->error)
+		kref_put(&error_priv->error->ref, i915_error_state_free);
+}
+
+void i915_destroy_error_state(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_error_state *error;
+	unsigned long flags;
+
+	spin_lock_irqsave(&dev_priv->gpu_error.lock, flags);
+	error = dev_priv->gpu_error.first_error;
+	dev_priv->gpu_error.first_error = NULL;
+	spin_unlock_irqrestore(&dev_priv->gpu_error.lock, flags);
+
+	if (error)
+		kref_put(&error->ref, i915_error_state_free);
+}
+
+const char *i915_cache_level_str(int type)
+{
+	switch (type) {
+	case I915_CACHE_NONE: return " uncached";
+	case I915_CACHE_LLC: return " snooped or LLC";
+	case I915_CACHE_L3_LLC: return " L3+LLC";
+	default: return "";
+	}
+}
+
+/* NB: please notice the memset */
+void i915_get_extra_instdone(struct drm_device *dev, uint32_t *instdone)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	memset(instdone, 0, sizeof(*instdone) * I915_NUM_INSTDONE_REG);
+
+	switch (INTEL_INFO(dev)->gen) {
+	case 2:
+	case 3:
+		instdone[0] = I915_READ(INSTDONE);
+		break;
+	case 4:
+	case 5:
+	case 6:
+		instdone[0] = I915_READ(INSTDONE_I965);
+		instdone[1] = I915_READ(INSTDONE1);
+		break;
+	default:
+		WARN_ONCE(1, "Unsupported platform\n");
+	case 7:
+		instdone[0] = I915_READ(GEN7_INSTDONE_1);
+		instdone[1] = I915_READ(GEN7_SC_INSTDONE);
+		instdone[2] = I915_READ(GEN7_SAMPLER_INSTDONE);
+		instdone[3] = I915_READ(GEN7_ROW_INSTDONE);
+		break;
+	}
+}
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 3d92a7cef154..4b91228fd9bd 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -85,6 +85,12 @@ ironlake_enable_display_irq(drm_i915_private_t *dev_priv, u32 mask)
 {
 	assert_spin_locked(&dev_priv->irq_lock);
 
+	if (dev_priv->pc8.irqs_disabled) {
+		WARN(1, "IRQs disabled\n");
+		dev_priv->pc8.regsave.deimr &= ~mask;
+		return;
+	}
+
 	if ((dev_priv->irq_mask & mask) != 0) {
 		dev_priv->irq_mask &= ~mask;
 		I915_WRITE(DEIMR, dev_priv->irq_mask);
@@ -97,6 +103,12 @@ ironlake_disable_display_irq(drm_i915_private_t *dev_priv, u32 mask)
 {
 	assert_spin_locked(&dev_priv->irq_lock);
 
+	if (dev_priv->pc8.irqs_disabled) {
+		WARN(1, "IRQs disabled\n");
+		dev_priv->pc8.regsave.deimr |= mask;
+		return;
+	}
+
 	if ((dev_priv->irq_mask & mask) != mask) {
 		dev_priv->irq_mask |= mask;
 		I915_WRITE(DEIMR, dev_priv->irq_mask);
@@ -104,6 +116,85 @@ ironlake_disable_display_irq(drm_i915_private_t *dev_priv, u32 mask)
 	}
 }
 
+/**
+ * ilk_update_gt_irq - update GTIMR
+ * @dev_priv: driver private
+ * @interrupt_mask: mask of interrupt bits to update
+ * @enabled_irq_mask: mask of interrupt bits to enable
+ */
+static void ilk_update_gt_irq(struct drm_i915_private *dev_priv,
+			      uint32_t interrupt_mask,
+			      uint32_t enabled_irq_mask)
+{
+	assert_spin_locked(&dev_priv->irq_lock);
+
+	if (dev_priv->pc8.irqs_disabled) {
+		WARN(1, "IRQs disabled\n");
+		dev_priv->pc8.regsave.gtimr &= ~interrupt_mask;
+		dev_priv->pc8.regsave.gtimr |= (~enabled_irq_mask &
+						interrupt_mask);
+		return;
+	}
+
+	dev_priv->gt_irq_mask &= ~interrupt_mask;
+	dev_priv->gt_irq_mask |= (~enabled_irq_mask & interrupt_mask);
+	I915_WRITE(GTIMR, dev_priv->gt_irq_mask);
+	POSTING_READ(GTIMR);
+}
+
+void ilk_enable_gt_irq(struct drm_i915_private *dev_priv, uint32_t mask)
+{
+	ilk_update_gt_irq(dev_priv, mask, mask);
+}
+
+void ilk_disable_gt_irq(struct drm_i915_private *dev_priv, uint32_t mask)
+{
+	ilk_update_gt_irq(dev_priv, mask, 0);
+}
+
+/**
+  * snb_update_pm_irq - update GEN6_PMIMR
+  * @dev_priv: driver private
+  * @interrupt_mask: mask of interrupt bits to update
+  * @enabled_irq_mask: mask of interrupt bits to enable
+  */
+static void snb_update_pm_irq(struct drm_i915_private *dev_priv,
+			      uint32_t interrupt_mask,
+			      uint32_t enabled_irq_mask)
+{
+	uint32_t new_val;
+
+	assert_spin_locked(&dev_priv->irq_lock);
+
+	if (dev_priv->pc8.irqs_disabled) {
+		WARN(1, "IRQs disabled\n");
+		dev_priv->pc8.regsave.gen6_pmimr &= ~interrupt_mask;
+		dev_priv->pc8.regsave.gen6_pmimr |= (~enabled_irq_mask &
+						     interrupt_mask);
+		return;
+	}
+
+	new_val = dev_priv->pm_irq_mask;
+	new_val &= ~interrupt_mask;
+	new_val |= (~enabled_irq_mask & interrupt_mask);
+
+	if (new_val != dev_priv->pm_irq_mask) {
+		dev_priv->pm_irq_mask = new_val;
+		I915_WRITE(GEN6_PMIMR, dev_priv->pm_irq_mask);
+		POSTING_READ(GEN6_PMIMR);
+	}
+}
+
+void snb_enable_pm_irq(struct drm_i915_private *dev_priv, uint32_t mask)
+{
+	snb_update_pm_irq(dev_priv, mask, mask);
+}
+
+void snb_disable_pm_irq(struct drm_i915_private *dev_priv, uint32_t mask)
+{
+	snb_update_pm_irq(dev_priv, mask, 0);
+}
+
 static bool ivb_can_enable_err_int(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -128,6 +219,8 @@ static bool cpt_can_enable_serr_int(struct drm_device *dev)
 	enum pipe pipe;
 	struct intel_crtc *crtc;
 
+	assert_spin_locked(&dev_priv->irq_lock);
+
 	for_each_pipe(pipe) {
 		crtc = to_intel_crtc(dev_priv->pipe_to_crtc_mapping[pipe]);
 
@@ -152,38 +245,75 @@ static void ironlake_set_fifo_underrun_reporting(struct drm_device *dev,
 }
 
 static void ivybridge_set_fifo_underrun_reporting(struct drm_device *dev,
-						  bool enable)
+						  enum pipe pipe, bool enable)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-
 	if (enable) {
+		I915_WRITE(GEN7_ERR_INT, ERR_INT_FIFO_UNDERRUN(pipe));
+
 		if (!ivb_can_enable_err_int(dev))
 			return;
 
-		I915_WRITE(GEN7_ERR_INT, ERR_INT_FIFO_UNDERRUN_A |
-					 ERR_INT_FIFO_UNDERRUN_B |
-					 ERR_INT_FIFO_UNDERRUN_C);
-
 		ironlake_enable_display_irq(dev_priv, DE_ERR_INT_IVB);
 	} else {
+		bool was_enabled = !(I915_READ(DEIMR) & DE_ERR_INT_IVB);
+
+		/* Change the state _after_ we've read out the current one. */
 		ironlake_disable_display_irq(dev_priv, DE_ERR_INT_IVB);
+
+		if (!was_enabled &&
+		    (I915_READ(GEN7_ERR_INT) & ERR_INT_FIFO_UNDERRUN(pipe))) {
+			DRM_DEBUG_KMS("uncleared fifo underrun on pipe %c\n",
+				      pipe_name(pipe));
+		}
 	}
 }
 
-static void ibx_set_fifo_underrun_reporting(struct intel_crtc *crtc,
+/**
+ * ibx_display_interrupt_update - update SDEIMR
+ * @dev_priv: driver private
+ * @interrupt_mask: mask of interrupt bits to update
+ * @enabled_irq_mask: mask of interrupt bits to enable
+ */
+static void ibx_display_interrupt_update(struct drm_i915_private *dev_priv,
+					 uint32_t interrupt_mask,
+					 uint32_t enabled_irq_mask)
+{
+	uint32_t sdeimr = I915_READ(SDEIMR);
+	sdeimr &= ~interrupt_mask;
+	sdeimr |= (~enabled_irq_mask & interrupt_mask);
+
+	assert_spin_locked(&dev_priv->irq_lock);
+
+	if (dev_priv->pc8.irqs_disabled &&
+	    (interrupt_mask & SDE_HOTPLUG_MASK_CPT)) {
+		WARN(1, "IRQs disabled\n");
+		dev_priv->pc8.regsave.sdeimr &= ~interrupt_mask;
+		dev_priv->pc8.regsave.sdeimr |= (~enabled_irq_mask &
+						 interrupt_mask);
+		return;
+	}
+
+	I915_WRITE(SDEIMR, sdeimr);
+	POSTING_READ(SDEIMR);
+}
+#define ibx_enable_display_interrupt(dev_priv, bits) \
+	ibx_display_interrupt_update((dev_priv), (bits), (bits))
+#define ibx_disable_display_interrupt(dev_priv, bits) \
+	ibx_display_interrupt_update((dev_priv), (bits), 0)
+
+static void ibx_set_fifo_underrun_reporting(struct drm_device *dev,
+					    enum transcoder pch_transcoder,
 					    bool enable)
 {
-	struct drm_device *dev = crtc->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	uint32_t bit = (crtc->pipe == PIPE_A) ? SDE_TRANSA_FIFO_UNDER :
-						SDE_TRANSB_FIFO_UNDER;
+	uint32_t bit = (pch_transcoder == TRANSCODER_A) ?
+		       SDE_TRANSA_FIFO_UNDER : SDE_TRANSB_FIFO_UNDER;
 
 	if (enable)
-		I915_WRITE(SDEIMR, I915_READ(SDEIMR) & ~bit);
+		ibx_enable_display_interrupt(dev_priv, bit);
 	else
-		I915_WRITE(SDEIMR, I915_READ(SDEIMR) | bit);
-
-	POSTING_READ(SDEIMR);
+		ibx_disable_display_interrupt(dev_priv, bit);
 }
 
 static void cpt_set_fifo_underrun_reporting(struct drm_device *dev,
@@ -193,19 +323,26 @@ static void cpt_set_fifo_underrun_reporting(struct drm_device *dev,
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
 	if (enable) {
+		I915_WRITE(SERR_INT,
+			   SERR_INT_TRANS_FIFO_UNDERRUN(pch_transcoder));
+
 		if (!cpt_can_enable_serr_int(dev))
 			return;
 
-		I915_WRITE(SERR_INT, SERR_INT_TRANS_A_FIFO_UNDERRUN |
-				     SERR_INT_TRANS_B_FIFO_UNDERRUN |
-				     SERR_INT_TRANS_C_FIFO_UNDERRUN);
-
-		I915_WRITE(SDEIMR, I915_READ(SDEIMR) & ~SDE_ERROR_CPT);
+		ibx_enable_display_interrupt(dev_priv, SDE_ERROR_CPT);
 	} else {
-		I915_WRITE(SDEIMR, I915_READ(SDEIMR) | SDE_ERROR_CPT);
-	}
+		uint32_t tmp = I915_READ(SERR_INT);
+		bool was_enabled = !(I915_READ(SDEIMR) & SDE_ERROR_CPT);
 
-	POSTING_READ(SDEIMR);
+		/* Change the state _after_ we've read out the current one. */
+		ibx_disable_display_interrupt(dev_priv, SDE_ERROR_CPT);
+
+		if (!was_enabled &&
+		    (tmp & SERR_INT_TRANS_FIFO_UNDERRUN(pch_transcoder))) {
+			DRM_DEBUG_KMS("uncleared pch fifo underrun on pch transcoder %c\n",
+				      transcoder_name(pch_transcoder));
+		}
+	}
 }
 
 /**
@@ -243,7 +380,7 @@ bool intel_set_cpu_fifo_underrun_reporting(struct drm_device *dev,
 	if (IS_GEN5(dev) || IS_GEN6(dev))
 		ironlake_set_fifo_underrun_reporting(dev, pipe, enable);
 	else if (IS_GEN7(dev))
-		ivybridge_set_fifo_underrun_reporting(dev, enable);
+		ivybridge_set_fifo_underrun_reporting(dev, pipe, enable);
 
 done:
 	spin_unlock_irqrestore(&dev_priv->irq_lock, flags);
@@ -269,29 +406,19 @@ bool intel_set_pch_fifo_underrun_reporting(struct drm_device *dev,
 					   bool enable)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	enum pipe p;
-	struct drm_crtc *crtc;
-	struct intel_crtc *intel_crtc;
+	struct drm_crtc *crtc = dev_priv->pipe_to_crtc_mapping[pch_transcoder];
+	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	unsigned long flags;
 	bool ret;
 
-	if (HAS_PCH_LPT(dev)) {
-		crtc = NULL;
-		for_each_pipe(p) {
-			struct drm_crtc *c = dev_priv->pipe_to_crtc_mapping[p];
-			if (intel_pipe_has_type(c, INTEL_OUTPUT_ANALOG)) {
-				crtc = c;
-				break;
-			}
-		}
-		if (!crtc) {
-			DRM_ERROR("PCH FIFO underrun, but no CRTC using the PCH found\n");
-			return false;
-		}
-	} else {
-		crtc = dev_priv->pipe_to_crtc_mapping[pch_transcoder];
-	}
-	intel_crtc = to_intel_crtc(crtc);
+	/*
+	 * NOTE: Pre-LPT has a fixed cpu pipe -> pch transcoder mapping, but LPT
+	 * has only one pch transcoder A that all pipes can use. To avoid racy
+	 * pch transcoder -> pipe lookups from interrupt code simply store the
+	 * underrun statistics in crtc A. Since we never expose this anywhere
+	 * nor use it outside of the fifo underrun code here using the "wrong"
+	 * crtc on LPT won't cause issues.
+	 */
 
 	spin_lock_irqsave(&dev_priv->irq_lock, flags);
 
@@ -303,7 +430,7 @@ bool intel_set_pch_fifo_underrun_reporting(struct drm_device *dev,
 	intel_crtc->pch_fifo_underrun_disabled = !enable;
 
 	if (HAS_PCH_IBX(dev))
-		ibx_set_fifo_underrun_reporting(intel_crtc, enable);
+		ibx_set_fifo_underrun_reporting(dev, pch_transcoder, enable);
 	else
 		cpt_set_fifo_underrun_reporting(dev, pch_transcoder, enable);
 
@@ -319,6 +446,8 @@ i915_enable_pipestat(drm_i915_private_t *dev_priv, int pipe, u32 mask)
 	u32 reg = PIPESTAT(pipe);
 	u32 pipestat = I915_READ(reg) & 0x7fff0000;
 
+	assert_spin_locked(&dev_priv->irq_lock);
+
 	if ((pipestat & mask) == mask)
 		return;
 
@@ -334,6 +463,8 @@ i915_disable_pipestat(drm_i915_private_t *dev_priv, int pipe, u32 mask)
 	u32 reg = PIPESTAT(pipe);
 	u32 pipestat = I915_READ(reg) & 0x7fff0000;
 
+	assert_spin_locked(&dev_priv->irq_lock);
+
 	if ((pipestat & mask) == 0)
 		return;
 
@@ -625,14 +756,13 @@ static void i915_hotplug_work_func(struct work_struct *work)
 		drm_kms_helper_hotplug_event(dev);
 }
 
-static void ironlake_handle_rps_change(struct drm_device *dev)
+static void ironlake_rps_change_irq_handler(struct drm_device *dev)
 {
 	drm_i915_private_t *dev_priv = dev->dev_private;
 	u32 busy_up, busy_down, max_avg, min_avg;
 	u8 new_delay;
-	unsigned long flags;
 
-	spin_lock_irqsave(&mchdev_lock, flags);
+	spin_lock(&mchdev_lock);
 
 	I915_WRITE16(MEMINTRSTS, I915_READ(MEMINTRSTS));
 
@@ -660,7 +790,7 @@ static void ironlake_handle_rps_change(struct drm_device *dev)
 	if (ironlake_set_drps(dev, new_delay))
 		dev_priv->ips.cur_delay = new_delay;
 
-	spin_unlock_irqrestore(&mchdev_lock, flags);
+	spin_unlock(&mchdev_lock);
 
 	return;
 }
@@ -668,34 +798,31 @@ static void ironlake_handle_rps_change(struct drm_device *dev)
 static void notify_ring(struct drm_device *dev,
 			struct intel_ring_buffer *ring)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
-
 	if (ring->obj == NULL)
 		return;
 
 	trace_i915_gem_request_complete(ring, ring->get_seqno(ring, false));
 
 	wake_up_all(&ring->irq_queue);
-	if (i915_enable_hangcheck) {
-		mod_timer(&dev_priv->gpu_error.hangcheck_timer,
-			  round_jiffies_up(jiffies + DRM_I915_HANGCHECK_JIFFIES));
-	}
+	i915_queue_hangcheck(dev);
 }
 
 static void gen6_pm_rps_work(struct work_struct *work)
 {
 	drm_i915_private_t *dev_priv = container_of(work, drm_i915_private_t,
 						    rps.work);
-	u32 pm_iir, pm_imr;
+	u32 pm_iir;
 	u8 new_delay;
 
-	spin_lock_irq(&dev_priv->rps.lock);
+	spin_lock_irq(&dev_priv->irq_lock);
 	pm_iir = dev_priv->rps.pm_iir;
 	dev_priv->rps.pm_iir = 0;
-	pm_imr = I915_READ(GEN6_PMIMR);
 	/* Make sure not to corrupt PMIMR state used by ringbuffer code */
-	I915_WRITE(GEN6_PMIMR, pm_imr & ~GEN6_PM_RPS_EVENTS);
-	spin_unlock_irq(&dev_priv->rps.lock);
+	snb_enable_pm_irq(dev_priv, GEN6_PM_RPS_EVENTS);
+	spin_unlock_irq(&dev_priv->irq_lock);
+
+	/* Make sure we didn't queue anything we're not going to process. */
+	WARN_ON(pm_iir & ~GEN6_PM_RPS_EVENTS);
 
 	if ((pm_iir & GEN6_PM_RPS_EVENTS) == 0)
 		return;
@@ -781,13 +908,12 @@ static void ivybridge_parity_work(struct work_struct *work)
 	I915_WRITE(GEN7_MISCCPCTL, misccpctl);
 
 	spin_lock_irqsave(&dev_priv->irq_lock, flags);
-	dev_priv->gt_irq_mask &= ~GT_RENDER_L3_PARITY_ERROR_INTERRUPT;
-	I915_WRITE(GTIMR, dev_priv->gt_irq_mask);
+	ilk_enable_gt_irq(dev_priv, GT_RENDER_L3_PARITY_ERROR_INTERRUPT);
 	spin_unlock_irqrestore(&dev_priv->irq_lock, flags);
 
 	mutex_unlock(&dev_priv->dev->struct_mutex);
 
-	parity_event[0] = "L3_PARITY_ERROR=1";
+	parity_event[0] = I915_L3_PARITY_UEVENT "=1";
 	parity_event[1] = kasprintf(GFP_KERNEL, "ROW=%d", row);
 	parity_event[2] = kasprintf(GFP_KERNEL, "BANK=%d", bank);
 	parity_event[3] = kasprintf(GFP_KERNEL, "SUBBANK=%d", subbank);
@@ -804,22 +930,31 @@ static void ivybridge_parity_work(struct work_struct *work)
 	kfree(parity_event[1]);
 }
 
-static void ivybridge_handle_parity_error(struct drm_device *dev)
+static void ivybridge_parity_error_irq_handler(struct drm_device *dev)
 {
 	drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private;
-	unsigned long flags;
 
 	if (!HAS_L3_GPU_CACHE(dev))
 		return;
 
-	spin_lock_irqsave(&dev_priv->irq_lock, flags);
-	dev_priv->gt_irq_mask |= GT_RENDER_L3_PARITY_ERROR_INTERRUPT;
-	I915_WRITE(GTIMR, dev_priv->gt_irq_mask);
-	spin_unlock_irqrestore(&dev_priv->irq_lock, flags);
+	spin_lock(&dev_priv->irq_lock);
+	ilk_disable_gt_irq(dev_priv, GT_RENDER_L3_PARITY_ERROR_INTERRUPT);
+	spin_unlock(&dev_priv->irq_lock);
 
 	queue_work(dev_priv->wq, &dev_priv->l3_parity.error_work);
 }
 
+static void ilk_gt_irq_handler(struct drm_device *dev,
+			       struct drm_i915_private *dev_priv,
+			       u32 gt_iir)
+{
+	if (gt_iir &
+	    (GT_RENDER_USER_INTERRUPT | GT_RENDER_PIPECTL_NOTIFY_INTERRUPT))
+		notify_ring(dev, &dev_priv->ring[RCS]);
+	if (gt_iir & ILK_BSD_USER_INTERRUPT)
+		notify_ring(dev, &dev_priv->ring[VCS]);
+}
+
 static void snb_gt_irq_handler(struct drm_device *dev,
 			       struct drm_i915_private *dev_priv,
 			       u32 gt_iir)
@@ -841,32 +976,7 @@ static void snb_gt_irq_handler(struct drm_device *dev,
 	}
 
 	if (gt_iir & GT_RENDER_L3_PARITY_ERROR_INTERRUPT)
-		ivybridge_handle_parity_error(dev);
-}
-
-/* Legacy way of handling PM interrupts */
-static void gen6_queue_rps_work(struct drm_i915_private *dev_priv,
-				u32 pm_iir)
-{
-	unsigned long flags;
-
-	/*
-	 * IIR bits should never already be set because IMR should
-	 * prevent an interrupt from being shown in IIR. The warning
-	 * displays a case where we've unsafely cleared
-	 * dev_priv->rps.pm_iir. Although missing an interrupt of the same
-	 * type is not a problem, it displays a problem in the logic.
-	 *
-	 * The mask bit in IMR is cleared by dev_priv->rps.work.
-	 */
-
-	spin_lock_irqsave(&dev_priv->rps.lock, flags);
-	dev_priv->rps.pm_iir |= pm_iir;
-	I915_WRITE(GEN6_PMIMR, dev_priv->rps.pm_iir);
-	POSTING_READ(GEN6_PMIMR);
-	spin_unlock_irqrestore(&dev_priv->rps.lock, flags);
-
-	queue_work(dev_priv->wq, &dev_priv->rps.work);
+		ivybridge_parity_error_irq_handler(dev);
 }
 
 #define HPD_STORM_DETECT_PERIOD 1000
@@ -886,6 +996,10 @@ static inline void intel_hpd_irq_handler(struct drm_device *dev,
 	spin_lock(&dev_priv->irq_lock);
 	for (i = 1; i < HPD_NUM_PINS; i++) {
 
+		WARN(((hpd[i] & hotplug_trigger) &&
+		      dev_priv->hpd_stats[i].hpd_mark != HPD_ENABLED),
+		     "Received HPD interrupt although disabled\n");
+
 		if (!(hpd[i] & hotplug_trigger) ||
 		    dev_priv->hpd_stats[i].hpd_mark != HPD_ENABLED)
 			continue;
@@ -896,6 +1010,7 @@ static inline void intel_hpd_irq_handler(struct drm_device *dev,
 				   + msecs_to_jiffies(HPD_STORM_DETECT_PERIOD))) {
 			dev_priv->hpd_stats[i].hpd_last_jiffies = jiffies;
 			dev_priv->hpd_stats[i].hpd_cnt = 0;
+			DRM_DEBUG_KMS("Received HPD interrupt on PIN %d - cnt: 0\n", i);
 		} else if (dev_priv->hpd_stats[i].hpd_cnt > HPD_STORM_THRESHOLD) {
 			dev_priv->hpd_stats[i].hpd_mark = HPD_MARK_DISABLED;
 			dev_priv->hpd_event_bits &= ~(1 << i);
@@ -903,6 +1018,8 @@ static inline void intel_hpd_irq_handler(struct drm_device *dev,
 			storm_detected = true;
 		} else {
 			dev_priv->hpd_stats[i].hpd_cnt++;
+			DRM_DEBUG_KMS("Received HPD interrupt on PIN %d - cnt: %d\n", i,
+				      dev_priv->hpd_stats[i].hpd_cnt);
 		}
 	}
 
@@ -910,8 +1027,13 @@ static inline void intel_hpd_irq_handler(struct drm_device *dev,
 		dev_priv->display.hpd_irq_setup(dev);
 	spin_unlock(&dev_priv->irq_lock);
 
-	queue_work(dev_priv->wq,
-		   &dev_priv->hotplug_work);
+	/*
+	 * Our hotplug handler can grab modeset locks (by calling down into the
+	 * fb helpers). Hence it must not be run on our own dev-priv->wq work
+	 * queue for otherwise the flush_work in the pageflip code will
+	 * deadlock.
+	 */
+	schedule_work(&dev_priv->hotplug_work);
 }
 
 static void gmbus_irq_handler(struct drm_device *dev)
@@ -928,28 +1050,21 @@ static void dp_aux_irq_handler(struct drm_device *dev)
 	wake_up_all(&dev_priv->gmbus_wait_queue);
 }
 
-/* Unlike gen6_queue_rps_work() from which this function is originally derived,
- * we must be able to deal with other PM interrupts. This is complicated because
- * of the way in which we use the masks to defer the RPS work (which for
- * posterity is necessary because of forcewake).
- */
-static void hsw_pm_irq_handler(struct drm_i915_private *dev_priv,
-			       u32 pm_iir)
+/* The RPS events need forcewake, so we add them to a work queue and mask their
+ * IMR bits until the work is done. Other interrupts can be processed without
+ * the work queue. */
+static void gen6_rps_irq_handler(struct drm_i915_private *dev_priv, u32 pm_iir)
 {
-	unsigned long flags;
+	if (pm_iir & GEN6_PM_RPS_EVENTS) {
+		spin_lock(&dev_priv->irq_lock);
+		dev_priv->rps.pm_iir |= pm_iir & GEN6_PM_RPS_EVENTS;
+		snb_disable_pm_irq(dev_priv, pm_iir & GEN6_PM_RPS_EVENTS);
+		spin_unlock(&dev_priv->irq_lock);
 
-	spin_lock_irqsave(&dev_priv->rps.lock, flags);
-	dev_priv->rps.pm_iir |= pm_iir & GEN6_PM_RPS_EVENTS;
-	if (dev_priv->rps.pm_iir) {
-		I915_WRITE(GEN6_PMIMR, dev_priv->rps.pm_iir);
-		/* never want to mask useful interrupts. (also posting read) */
-		WARN_ON(I915_READ_NOTRACE(GEN6_PMIMR) & ~GEN6_PM_RPS_EVENTS);
-		/* TODO: if queue_work is slow, move it out of the spinlock */
 		queue_work(dev_priv->wq, &dev_priv->rps.work);
 	}
-	spin_unlock_irqrestore(&dev_priv->rps.lock, flags);
 
-	if (pm_iir & ~GEN6_PM_RPS_EVENTS) {
+	if (HAS_VEBOX(dev_priv->dev)) {
 		if (pm_iir & PM_VEBOX_USER_INTERRUPT)
 			notify_ring(dev_priv->dev, &dev_priv->ring[VECS]);
 
@@ -1028,8 +1143,8 @@ static irqreturn_t valleyview_irq_handler(int irq, void *arg)
 		if (pipe_stats[0] & PIPE_GMBUS_INTERRUPT_STATUS)
 			gmbus_irq_handler(dev);
 
-		if (pm_iir & GEN6_PM_RPS_EVENTS)
-			gen6_queue_rps_work(dev_priv, pm_iir);
+		if (pm_iir)
+			gen6_rps_irq_handler(dev_priv, pm_iir);
 
 		I915_WRITE(GTIIR, gt_iir);
 		I915_WRITE(GEN6_PMIIR, pm_iir);
@@ -1179,27 +1294,112 @@ static void cpt_irq_handler(struct drm_device *dev, u32 pch_iir)
 		cpt_serr_int_handler(dev);
 }
 
-static irqreturn_t ivybridge_irq_handler(int irq, void *arg)
+static void ilk_display_irq_handler(struct drm_device *dev, u32 de_iir)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	if (de_iir & DE_AUX_CHANNEL_A)
+		dp_aux_irq_handler(dev);
+
+	if (de_iir & DE_GSE)
+		intel_opregion_asle_intr(dev);
+
+	if (de_iir & DE_PIPEA_VBLANK)
+		drm_handle_vblank(dev, 0);
+
+	if (de_iir & DE_PIPEB_VBLANK)
+		drm_handle_vblank(dev, 1);
+
+	if (de_iir & DE_POISON)
+		DRM_ERROR("Poison interrupt\n");
+
+	if (de_iir & DE_PIPEA_FIFO_UNDERRUN)
+		if (intel_set_cpu_fifo_underrun_reporting(dev, PIPE_A, false))
+			DRM_DEBUG_DRIVER("Pipe A FIFO underrun\n");
+
+	if (de_iir & DE_PIPEB_FIFO_UNDERRUN)
+		if (intel_set_cpu_fifo_underrun_reporting(dev, PIPE_B, false))
+			DRM_DEBUG_DRIVER("Pipe B FIFO underrun\n");
+
+	if (de_iir & DE_PLANEA_FLIP_DONE) {
+		intel_prepare_page_flip(dev, 0);
+		intel_finish_page_flip_plane(dev, 0);
+	}
+
+	if (de_iir & DE_PLANEB_FLIP_DONE) {
+		intel_prepare_page_flip(dev, 1);
+		intel_finish_page_flip_plane(dev, 1);
+	}
+
+	/* check event from PCH */
+	if (de_iir & DE_PCH_EVENT) {
+		u32 pch_iir = I915_READ(SDEIIR);
+
+		if (HAS_PCH_CPT(dev))
+			cpt_irq_handler(dev, pch_iir);
+		else
+			ibx_irq_handler(dev, pch_iir);
+
+		/* should clear PCH hotplug event before clear CPU irq */
+		I915_WRITE(SDEIIR, pch_iir);
+	}
+
+	if (IS_GEN5(dev) && de_iir & DE_PCU_EVENT)
+		ironlake_rps_change_irq_handler(dev);
+}
+
+static void ivb_display_irq_handler(struct drm_device *dev, u32 de_iir)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	int i;
+
+	if (de_iir & DE_ERR_INT_IVB)
+		ivb_err_int_handler(dev);
+
+	if (de_iir & DE_AUX_CHANNEL_A_IVB)
+		dp_aux_irq_handler(dev);
+
+	if (de_iir & DE_GSE_IVB)
+		intel_opregion_asle_intr(dev);
+
+	for (i = 0; i < 3; i++) {
+		if (de_iir & (DE_PIPEA_VBLANK_IVB << (5 * i)))
+			drm_handle_vblank(dev, i);
+		if (de_iir & (DE_PLANEA_FLIP_DONE_IVB << (5 * i))) {
+			intel_prepare_page_flip(dev, i);
+			intel_finish_page_flip_plane(dev, i);
+		}
+	}
+
+	/* check event from PCH */
+	if (!HAS_PCH_NOP(dev) && (de_iir & DE_PCH_EVENT_IVB)) {
+		u32 pch_iir = I915_READ(SDEIIR);
+
+		cpt_irq_handler(dev, pch_iir);
+
+		/* clear PCH hotplug event before clear CPU irq */
+		I915_WRITE(SDEIIR, pch_iir);
+	}
+}
+
+static irqreturn_t ironlake_irq_handler(int irq, void *arg)
 {
 	struct drm_device *dev = (struct drm_device *) arg;
 	drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private;
-	u32 de_iir, gt_iir, de_ier, pm_iir, sde_ier = 0;
+	u32 de_iir, gt_iir, de_ier, sde_ier = 0;
 	irqreturn_t ret = IRQ_NONE;
-	int i;
+	bool err_int_reenable = false;
 
 	atomic_inc(&dev_priv->irq_received);
 
 	/* We get interrupts on unclaimed registers, so check for this before we
 	 * do any I915_{READ,WRITE}. */
-	if (IS_HASWELL(dev) &&
-	    (I915_READ_NOTRACE(FPGA_DBG) & FPGA_DBG_RM_NOCLAIM)) {
-		DRM_ERROR("Unclaimed register before interrupt\n");
-		I915_WRITE_NOTRACE(FPGA_DBG, FPGA_DBG_RM_NOCLAIM);
-	}
+	intel_uncore_check_errors(dev);
 
 	/* disable master interrupt before clearing iir  */
 	de_ier = I915_READ(DEIER);
 	I915_WRITE(DEIER, de_ier & ~DE_MASTER_IRQ_CONTROL);
+	POSTING_READ(DEIER);
 
 	/* Disable south interrupts. We'll only write to SDEIIR once, so further
 	 * interrupts will will be stored on its back queue, and then we'll be
@@ -1217,62 +1417,42 @@ static irqreturn_t ivybridge_irq_handler(int irq, void *arg)
 	 * handler. */
 	if (IS_HASWELL(dev)) {
 		spin_lock(&dev_priv->irq_lock);
-		ironlake_disable_display_irq(dev_priv, DE_ERR_INT_IVB);
+		err_int_reenable = ~dev_priv->irq_mask & DE_ERR_INT_IVB;
+		if (err_int_reenable)
+			ironlake_disable_display_irq(dev_priv, DE_ERR_INT_IVB);
 		spin_unlock(&dev_priv->irq_lock);
 	}
 
 	gt_iir = I915_READ(GTIIR);
 	if (gt_iir) {
-		snb_gt_irq_handler(dev, dev_priv, gt_iir);
+		if (INTEL_INFO(dev)->gen >= 6)
+			snb_gt_irq_handler(dev, dev_priv, gt_iir);
+		else
+			ilk_gt_irq_handler(dev, dev_priv, gt_iir);
 		I915_WRITE(GTIIR, gt_iir);
 		ret = IRQ_HANDLED;
 	}
 
 	de_iir = I915_READ(DEIIR);
 	if (de_iir) {
-		if (de_iir & DE_ERR_INT_IVB)
-			ivb_err_int_handler(dev);
-
-		if (de_iir & DE_AUX_CHANNEL_A_IVB)
-			dp_aux_irq_handler(dev);
-
-		if (de_iir & DE_GSE_IVB)
-			intel_opregion_asle_intr(dev);
-
-		for (i = 0; i < 3; i++) {
-			if (de_iir & (DE_PIPEA_VBLANK_IVB << (5 * i)))
-				drm_handle_vblank(dev, i);
-			if (de_iir & (DE_PLANEA_FLIP_DONE_IVB << (5 * i))) {
-				intel_prepare_page_flip(dev, i);
-				intel_finish_page_flip_plane(dev, i);
-			}
-		}
-
-		/* check event from PCH */
-		if (!HAS_PCH_NOP(dev) && (de_iir & DE_PCH_EVENT_IVB)) {
-			u32 pch_iir = I915_READ(SDEIIR);
-
-			cpt_irq_handler(dev, pch_iir);
-
-			/* clear PCH hotplug event before clear CPU irq */
-			I915_WRITE(SDEIIR, pch_iir);
-		}
-
+		if (INTEL_INFO(dev)->gen >= 7)
+			ivb_display_irq_handler(dev, de_iir);
+		else
+			ilk_display_irq_handler(dev, de_iir);
 		I915_WRITE(DEIIR, de_iir);
 		ret = IRQ_HANDLED;
 	}
 
-	pm_iir = I915_READ(GEN6_PMIIR);
-	if (pm_iir) {
-		if (IS_HASWELL(dev))
-			hsw_pm_irq_handler(dev_priv, pm_iir);
-		else if (pm_iir & GEN6_PM_RPS_EVENTS)
-			gen6_queue_rps_work(dev_priv, pm_iir);
-		I915_WRITE(GEN6_PMIIR, pm_iir);
-		ret = IRQ_HANDLED;
+	if (INTEL_INFO(dev)->gen >= 6) {
+		u32 pm_iir = I915_READ(GEN6_PMIIR);
+		if (pm_iir) {
+			gen6_rps_irq_handler(dev_priv, pm_iir);
+			I915_WRITE(GEN6_PMIIR, pm_iir);
+			ret = IRQ_HANDLED;
+		}
 	}
 
-	if (IS_HASWELL(dev)) {
+	if (err_int_reenable) {
 		spin_lock(&dev_priv->irq_lock);
 		if (ivb_can_enable_err_int(dev))
 			ironlake_enable_display_irq(dev_priv, DE_ERR_INT_IVB);
@@ -1289,117 +1469,32 @@ static irqreturn_t ivybridge_irq_handler(int irq, void *arg)
 	return ret;
 }
 
-static void ilk_gt_irq_handler(struct drm_device *dev,
-			       struct drm_i915_private *dev_priv,
-			       u32 gt_iir)
-{
-	if (gt_iir &
-	    (GT_RENDER_USER_INTERRUPT | GT_RENDER_PIPECTL_NOTIFY_INTERRUPT))
-		notify_ring(dev, &dev_priv->ring[RCS]);
-	if (gt_iir & ILK_BSD_USER_INTERRUPT)
-		notify_ring(dev, &dev_priv->ring[VCS]);
-}
-
-static irqreturn_t ironlake_irq_handler(int irq, void *arg)
+static void i915_error_wake_up(struct drm_i915_private *dev_priv,
+			       bool reset_completed)
 {
-	struct drm_device *dev = (struct drm_device *) arg;
-	drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private;
-	int ret = IRQ_NONE;
-	u32 de_iir, gt_iir, de_ier, pm_iir, sde_ier;
-
-	atomic_inc(&dev_priv->irq_received);
-
-	/* disable master interrupt before clearing iir  */
-	de_ier = I915_READ(DEIER);
-	I915_WRITE(DEIER, de_ier & ~DE_MASTER_IRQ_CONTROL);
-	POSTING_READ(DEIER);
-
-	/* Disable south interrupts. We'll only write to SDEIIR once, so further
-	 * interrupts will will be stored on its back queue, and then we'll be
-	 * able to process them after we restore SDEIER (as soon as we restore
-	 * it, we'll get an interrupt if SDEIIR still has something to process
-	 * due to its back queue). */
-	sde_ier = I915_READ(SDEIER);
-	I915_WRITE(SDEIER, 0);
-	POSTING_READ(SDEIER);
-
-	de_iir = I915_READ(DEIIR);
-	gt_iir = I915_READ(GTIIR);
-	pm_iir = I915_READ(GEN6_PMIIR);
-
-	if (de_iir == 0 && gt_iir == 0 && (!IS_GEN6(dev) || pm_iir == 0))
-		goto done;
-
-	ret = IRQ_HANDLED;
-
-	if (IS_GEN5(dev))
-		ilk_gt_irq_handler(dev, dev_priv, gt_iir);
-	else
-		snb_gt_irq_handler(dev, dev_priv, gt_iir);
-
-	if (de_iir & DE_AUX_CHANNEL_A)
-		dp_aux_irq_handler(dev);
-
-	if (de_iir & DE_GSE)
-		intel_opregion_asle_intr(dev);
-
-	if (de_iir & DE_PIPEA_VBLANK)
-		drm_handle_vblank(dev, 0);
-
-	if (de_iir & DE_PIPEB_VBLANK)
-		drm_handle_vblank(dev, 1);
-
-	if (de_iir & DE_POISON)
-		DRM_ERROR("Poison interrupt\n");
-
-	if (de_iir & DE_PIPEA_FIFO_UNDERRUN)
-		if (intel_set_cpu_fifo_underrun_reporting(dev, PIPE_A, false))
-			DRM_DEBUG_DRIVER("Pipe A FIFO underrun\n");
-
-	if (de_iir & DE_PIPEB_FIFO_UNDERRUN)
-		if (intel_set_cpu_fifo_underrun_reporting(dev, PIPE_B, false))
-			DRM_DEBUG_DRIVER("Pipe B FIFO underrun\n");
-
-	if (de_iir & DE_PLANEA_FLIP_DONE) {
-		intel_prepare_page_flip(dev, 0);
-		intel_finish_page_flip_plane(dev, 0);
-	}
-
-	if (de_iir & DE_PLANEB_FLIP_DONE) {
-		intel_prepare_page_flip(dev, 1);
-		intel_finish_page_flip_plane(dev, 1);
-	}
-
-	/* check event from PCH */
-	if (de_iir & DE_PCH_EVENT) {
-		u32 pch_iir = I915_READ(SDEIIR);
-
-		if (HAS_PCH_CPT(dev))
-			cpt_irq_handler(dev, pch_iir);
-		else
-			ibx_irq_handler(dev, pch_iir);
-
-		/* should clear PCH hotplug event before clear CPU irq */
-		I915_WRITE(SDEIIR, pch_iir);
-	}
-
-	if (IS_GEN5(dev) &&  de_iir & DE_PCU_EVENT)
-		ironlake_handle_rps_change(dev);
+	struct intel_ring_buffer *ring;
+	int i;
 
-	if (IS_GEN6(dev) && pm_iir & GEN6_PM_RPS_EVENTS)
-		gen6_queue_rps_work(dev_priv, pm_iir);
+	/*
+	 * Notify all waiters for GPU completion events that reset state has
+	 * been changed, and that they need to restart their wait after
+	 * checking for potential errors (and bail out to drop locks if there is
+	 * a gpu reset pending so that i915_error_work_func can acquire them).
+	 */
 
-	I915_WRITE(GTIIR, gt_iir);
-	I915_WRITE(DEIIR, de_iir);
-	I915_WRITE(GEN6_PMIIR, pm_iir);
+	/* Wake up __wait_seqno, potentially holding dev->struct_mutex. */
+	for_each_ring(ring, dev_priv, i)
+		wake_up_all(&ring->irq_queue);
 
-done:
-	I915_WRITE(DEIER, de_ier);
-	POSTING_READ(DEIER);
-	I915_WRITE(SDEIER, sde_ier);
-	POSTING_READ(SDEIER);
+	/* Wake up intel_crtc_wait_for_pending_flips, holding crtc->mutex. */
+	wake_up_all(&dev_priv->pending_flip_queue);
 
-	return ret;
+	/*
+	 * Signal tasks blocked in i915_gem_wait_for_error that the pending
+	 * reset state is cleared.
+	 */
+	if (reset_completed)
+		wake_up_all(&dev_priv->gpu_error.reset_queue);
 }
 
 /**
@@ -1416,11 +1511,10 @@ static void i915_error_work_func(struct work_struct *work)
 	drm_i915_private_t *dev_priv = container_of(error, drm_i915_private_t,
 						    gpu_error);
 	struct drm_device *dev = dev_priv->dev;
-	struct intel_ring_buffer *ring;
-	char *error_event[] = { "ERROR=1", NULL };
-	char *reset_event[] = { "RESET=1", NULL };
-	char *reset_done_event[] = { "ERROR=0", NULL };
-	int i, ret;
+	char *error_event[] = { I915_ERROR_UEVENT "=1", NULL };
+	char *reset_event[] = { I915_RESET_UEVENT "=1", NULL };
+	char *reset_done_event[] = { I915_ERROR_UEVENT "=0", NULL };
+	int ret;
 
 	kobject_uevent_env(&dev->primary->kdev.kobj, KOBJ_CHANGE, error_event);
 
@@ -1439,8 +1533,16 @@ static void i915_error_work_func(struct work_struct *work)
 		kobject_uevent_env(&dev->primary->kdev.kobj, KOBJ_CHANGE,
 				   reset_event);
 
+		/*
+		 * All state reset _must_ be completed before we update the
+		 * reset counter, for otherwise waiters might miss the reset
+		 * pending state and not properly drop locks, resulting in
+		 * deadlocks with the reset work.
+		 */
 		ret = i915_reset(dev);
 
+		intel_display_handle_reset(dev);
+
 		if (ret == 0) {
 			/*
 			 * After all the gem state is reset, increment the reset
@@ -1461,544 +1563,14 @@ static void i915_error_work_func(struct work_struct *work)
 			atomic_set(&error->reset_counter, I915_WEDGED);
 		}
 
-		for_each_ring(ring, dev_priv, i)
-			wake_up_all(&ring->irq_queue);
-
-		intel_display_handle_reset(dev);
-
-		wake_up_all(&dev_priv->gpu_error.reset_queue);
-	}
-}
-
-/* NB: please notice the memset */
-static void i915_get_extra_instdone(struct drm_device *dev,
-				    uint32_t *instdone)
-{
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	memset(instdone, 0, sizeof(*instdone) * I915_NUM_INSTDONE_REG);
-
-	switch(INTEL_INFO(dev)->gen) {
-	case 2:
-	case 3:
-		instdone[0] = I915_READ(INSTDONE);
-		break;
-	case 4:
-	case 5:
-	case 6:
-		instdone[0] = I915_READ(INSTDONE_I965);
-		instdone[1] = I915_READ(INSTDONE1);
-		break;
-	default:
-		WARN_ONCE(1, "Unsupported platform\n");
-	case 7:
-		instdone[0] = I915_READ(GEN7_INSTDONE_1);
-		instdone[1] = I915_READ(GEN7_SC_INSTDONE);
-		instdone[2] = I915_READ(GEN7_SAMPLER_INSTDONE);
-		instdone[3] = I915_READ(GEN7_ROW_INSTDONE);
-		break;
-	}
-}
-
-#ifdef CONFIG_DEBUG_FS
-static struct drm_i915_error_object *
-i915_error_object_create_sized(struct drm_i915_private *dev_priv,
-			       struct drm_i915_gem_object *src,
-			       const int num_pages)
-{
-	struct drm_i915_error_object *dst;
-	int i;
-	u32 reloc_offset;
-
-	if (src == NULL || src->pages == NULL)
-		return NULL;
-
-	dst = kmalloc(sizeof(*dst) + num_pages * sizeof(u32 *), GFP_ATOMIC);
-	if (dst == NULL)
-		return NULL;
-
-	reloc_offset = src->gtt_offset;
-	for (i = 0; i < num_pages; i++) {
-		unsigned long flags;
-		void *d;
-
-		d = kmalloc(PAGE_SIZE, GFP_ATOMIC);
-		if (d == NULL)
-			goto unwind;
-
-		local_irq_save(flags);
-		if (reloc_offset < dev_priv->gtt.mappable_end &&
-		    src->has_global_gtt_mapping) {
-			void __iomem *s;
-
-			/* Simply ignore tiling or any overlapping fence.
-			 * It's part of the error state, and this hopefully
-			 * captures what the GPU read.
-			 */
-
-			s = io_mapping_map_atomic_wc(dev_priv->gtt.mappable,
-						     reloc_offset);
-			memcpy_fromio(d, s, PAGE_SIZE);
-			io_mapping_unmap_atomic(s);
-		} else if (src->stolen) {
-			unsigned long offset;
-
-			offset = dev_priv->mm.stolen_base;
-			offset += src->stolen->start;
-			offset += i << PAGE_SHIFT;
-
-			memcpy_fromio(d, (void __iomem *) offset, PAGE_SIZE);
-		} else {
-			struct page *page;
-			void *s;
-
-			page = i915_gem_object_get_page(src, i);
-
-			drm_clflush_pages(&page, 1);
-
-			s = kmap_atomic(page);
-			memcpy(d, s, PAGE_SIZE);
-			kunmap_atomic(s);
-
-			drm_clflush_pages(&page, 1);
-		}
-		local_irq_restore(flags);
-
-		dst->pages[i] = d;
-
-		reloc_offset += PAGE_SIZE;
-	}
-	dst->page_count = num_pages;
-	dst->gtt_offset = src->gtt_offset;
-
-	return dst;
-
-unwind:
-	while (i--)
-		kfree(dst->pages[i]);
-	kfree(dst);
-	return NULL;
-}
-#define i915_error_object_create(dev_priv, src) \
-	i915_error_object_create_sized((dev_priv), (src), \
-				       (src)->base.size>>PAGE_SHIFT)
-
-static void
-i915_error_object_free(struct drm_i915_error_object *obj)
-{
-	int page;
-
-	if (obj == NULL)
-		return;
-
-	for (page = 0; page < obj->page_count; page++)
-		kfree(obj->pages[page]);
-
-	kfree(obj);
-}
-
-void
-i915_error_state_free(struct kref *error_ref)
-{
-	struct drm_i915_error_state *error = container_of(error_ref,
-							  typeof(*error), ref);
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(error->ring); i++) {
-		i915_error_object_free(error->ring[i].batchbuffer);
-		i915_error_object_free(error->ring[i].ringbuffer);
-		i915_error_object_free(error->ring[i].ctx);
-		kfree(error->ring[i].requests);
-	}
-
-	kfree(error->active_bo);
-	kfree(error->overlay);
-	kfree(error->display);
-	kfree(error);
-}
-static void capture_bo(struct drm_i915_error_buffer *err,
-		       struct drm_i915_gem_object *obj)
-{
-	err->size = obj->base.size;
-	err->name = obj->base.name;
-	err->rseqno = obj->last_read_seqno;
-	err->wseqno = obj->last_write_seqno;
-	err->gtt_offset = obj->gtt_offset;
-	err->read_domains = obj->base.read_domains;
-	err->write_domain = obj->base.write_domain;
-	err->fence_reg = obj->fence_reg;
-	err->pinned = 0;
-	if (obj->pin_count > 0)
-		err->pinned = 1;
-	if (obj->user_pin_count > 0)
-		err->pinned = -1;
-	err->tiling = obj->tiling_mode;
-	err->dirty = obj->dirty;
-	err->purgeable = obj->madv != I915_MADV_WILLNEED;
-	err->ring = obj->ring ? obj->ring->id : -1;
-	err->cache_level = obj->cache_level;
-}
-
-static u32 capture_active_bo(struct drm_i915_error_buffer *err,
-			     int count, struct list_head *head)
-{
-	struct drm_i915_gem_object *obj;
-	int i = 0;
-
-	list_for_each_entry(obj, head, mm_list) {
-		capture_bo(err++, obj);
-		if (++i == count)
-			break;
-	}
-
-	return i;
-}
-
-static u32 capture_pinned_bo(struct drm_i915_error_buffer *err,
-			     int count, struct list_head *head)
-{
-	struct drm_i915_gem_object *obj;
-	int i = 0;
-
-	list_for_each_entry(obj, head, global_list) {
-		if (obj->pin_count == 0)
-			continue;
-
-		capture_bo(err++, obj);
-		if (++i == count)
-			break;
-	}
-
-	return i;
-}
-
-static void i915_gem_record_fences(struct drm_device *dev,
-				   struct drm_i915_error_state *error)
-{
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	int i;
-
-	/* Fences */
-	switch (INTEL_INFO(dev)->gen) {
-	case 7:
-	case 6:
-		for (i = 0; i < dev_priv->num_fence_regs; i++)
-			error->fence[i] = I915_READ64(FENCE_REG_SANDYBRIDGE_0 + (i * 8));
-		break;
-	case 5:
-	case 4:
-		for (i = 0; i < 16; i++)
-			error->fence[i] = I915_READ64(FENCE_REG_965_0 + (i * 8));
-		break;
-	case 3:
-		if (IS_I945G(dev) || IS_I945GM(dev) || IS_G33(dev))
-			for (i = 0; i < 8; i++)
-				error->fence[i+8] = I915_READ(FENCE_REG_945_8 + (i * 4));
-	case 2:
-		for (i = 0; i < 8; i++)
-			error->fence[i] = I915_READ(FENCE_REG_830_0 + (i * 4));
-		break;
-
-	default:
-		BUG();
-	}
-}
-
-static struct drm_i915_error_object *
-i915_error_first_batchbuffer(struct drm_i915_private *dev_priv,
-			     struct intel_ring_buffer *ring)
-{
-	struct drm_i915_gem_object *obj;
-	u32 seqno;
-
-	if (!ring->get_seqno)
-		return NULL;
-
-	if (HAS_BROKEN_CS_TLB(dev_priv->dev)) {
-		u32 acthd = I915_READ(ACTHD);
-
-		if (WARN_ON(ring->id != RCS))
-			return NULL;
-
-		obj = ring->private;
-		if (acthd >= obj->gtt_offset &&
-		    acthd < obj->gtt_offset + obj->base.size)
-			return i915_error_object_create(dev_priv, obj);
-	}
-
-	seqno = ring->get_seqno(ring, false);
-	list_for_each_entry(obj, &dev_priv->mm.active_list, mm_list) {
-		if (obj->ring != ring)
-			continue;
-
-		if (i915_seqno_passed(seqno, obj->last_read_seqno))
-			continue;
-
-		if ((obj->base.read_domains & I915_GEM_DOMAIN_COMMAND) == 0)
-			continue;
-
-		/* We need to copy these to an anonymous buffer as the simplest
-		 * method to avoid being overwritten by userspace.
+		/*
+		 * Note: The wake_up also serves as a memory barrier so that
+		 * waiters see the update value of the reset counter atomic_t.
 		 */
-		return i915_error_object_create(dev_priv, obj);
+		i915_error_wake_up(dev_priv, true);
 	}
-
-	return NULL;
 }
 
-static void i915_record_ring_state(struct drm_device *dev,
-				   struct drm_i915_error_state *error,
-				   struct intel_ring_buffer *ring)
-{
-	struct drm_i915_private *dev_priv = dev->dev_private;
-
-	if (INTEL_INFO(dev)->gen >= 6) {
-		error->rc_psmi[ring->id] = I915_READ(ring->mmio_base + 0x50);
-		error->fault_reg[ring->id] = I915_READ(RING_FAULT_REG(ring));
-		error->semaphore_mboxes[ring->id][0]
-			= I915_READ(RING_SYNC_0(ring->mmio_base));
-		error->semaphore_mboxes[ring->id][1]
-			= I915_READ(RING_SYNC_1(ring->mmio_base));
-		error->semaphore_seqno[ring->id][0] = ring->sync_seqno[0];
-		error->semaphore_seqno[ring->id][1] = ring->sync_seqno[1];
-	}
-
-	if (INTEL_INFO(dev)->gen >= 4) {
-		error->faddr[ring->id] = I915_READ(RING_DMA_FADD(ring->mmio_base));
-		error->ipeir[ring->id] = I915_READ(RING_IPEIR(ring->mmio_base));
-		error->ipehr[ring->id] = I915_READ(RING_IPEHR(ring->mmio_base));
-		error->instdone[ring->id] = I915_READ(RING_INSTDONE(ring->mmio_base));
-		error->instps[ring->id] = I915_READ(RING_INSTPS(ring->mmio_base));
-		if (ring->id == RCS)
-			error->bbaddr = I915_READ64(BB_ADDR);
-	} else {
-		error->faddr[ring->id] = I915_READ(DMA_FADD_I8XX);
-		error->ipeir[ring->id] = I915_READ(IPEIR);
-		error->ipehr[ring->id] = I915_READ(IPEHR);
-		error->instdone[ring->id] = I915_READ(INSTDONE);
-	}
-
-	error->waiting[ring->id] = waitqueue_active(&ring->irq_queue);
-	error->instpm[ring->id] = I915_READ(RING_INSTPM(ring->mmio_base));
-	error->seqno[ring->id] = ring->get_seqno(ring, false);
-	error->acthd[ring->id] = intel_ring_get_active_head(ring);
-	error->head[ring->id] = I915_READ_HEAD(ring);
-	error->tail[ring->id] = I915_READ_TAIL(ring);
-	error->ctl[ring->id] = I915_READ_CTL(ring);
-
-	error->cpu_ring_head[ring->id] = ring->head;
-	error->cpu_ring_tail[ring->id] = ring->tail;
-}
-
-
-static void i915_gem_record_active_context(struct intel_ring_buffer *ring,
-					   struct drm_i915_error_state *error,
-					   struct drm_i915_error_ring *ering)
-{
-	struct drm_i915_private *dev_priv = ring->dev->dev_private;
-	struct drm_i915_gem_object *obj;
-
-	/* Currently render ring is the only HW context user */
-	if (ring->id != RCS || !error->ccid)
-		return;
-
-	list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) {
-		if ((error->ccid & PAGE_MASK) == obj->gtt_offset) {
-			ering->ctx = i915_error_object_create_sized(dev_priv,
-								    obj, 1);
-		}
-	}
-}
-
-static void i915_gem_record_rings(struct drm_device *dev,
-				  struct drm_i915_error_state *error)
-{
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_ring_buffer *ring;
-	struct drm_i915_gem_request *request;
-	int i, count;
-
-	for_each_ring(ring, dev_priv, i) {
-		i915_record_ring_state(dev, error, ring);
-
-		error->ring[i].batchbuffer =
-			i915_error_first_batchbuffer(dev_priv, ring);
-
-		error->ring[i].ringbuffer =
-			i915_error_object_create(dev_priv, ring->obj);
-
-
-		i915_gem_record_active_context(ring, error, &error->ring[i]);
-
-		count = 0;
-		list_for_each_entry(request, &ring->request_list, list)
-			count++;
-
-		error->ring[i].num_requests = count;
-		error->ring[i].requests =
-			kmalloc(count*sizeof(struct drm_i915_error_request),
-				GFP_ATOMIC);
-		if (error->ring[i].requests == NULL) {
-			error->ring[i].num_requests = 0;
-			continue;
-		}
-
-		count = 0;
-		list_for_each_entry(request, &ring->request_list, list) {
-			struct drm_i915_error_request *erq;
-
-			erq = &error->ring[i].requests[count++];
-			erq->seqno = request->seqno;
-			erq->jiffies = request->emitted_jiffies;
-			erq->tail = request->tail;
-		}
-	}
-}
-
-/**
- * i915_capture_error_state - capture an error record for later analysis
- * @dev: drm device
- *
- * Should be called when an error is detected (either a hang or an error
- * interrupt) to capture error state from the time of the error.  Fills
- * out a structure which becomes available in debugfs for user level tools
- * to pick up.
- */
-static void i915_capture_error_state(struct drm_device *dev)
-{
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct drm_i915_gem_object *obj;
-	struct drm_i915_error_state *error;
-	unsigned long flags;
-	int i, pipe;
-
-	spin_lock_irqsave(&dev_priv->gpu_error.lock, flags);
-	error = dev_priv->gpu_error.first_error;
-	spin_unlock_irqrestore(&dev_priv->gpu_error.lock, flags);
-	if (error)
-		return;
-
-	/* Account for pipe specific data like PIPE*STAT */
-	error = kzalloc(sizeof(*error), GFP_ATOMIC);
-	if (!error) {
-		DRM_DEBUG_DRIVER("out of memory, not capturing error state\n");
-		return;
-	}
-
-	DRM_INFO("capturing error event; look for more information in "
-		 "/sys/kernel/debug/dri/%d/i915_error_state\n",
-		 dev->primary->index);
-
-	kref_init(&error->ref);
-	error->eir = I915_READ(EIR);
-	error->pgtbl_er = I915_READ(PGTBL_ER);
-	if (HAS_HW_CONTEXTS(dev))
-		error->ccid = I915_READ(CCID);
-
-	if (HAS_PCH_SPLIT(dev))
-		error->ier = I915_READ(DEIER) | I915_READ(GTIER);
-	else if (IS_VALLEYVIEW(dev))
-		error->ier = I915_READ(GTIER) | I915_READ(VLV_IER);
-	else if (IS_GEN2(dev))
-		error->ier = I915_READ16(IER);
-	else
-		error->ier = I915_READ(IER);
-
-	if (INTEL_INFO(dev)->gen >= 6)
-		error->derrmr = I915_READ(DERRMR);
-
-	if (IS_VALLEYVIEW(dev))
-		error->forcewake = I915_READ(FORCEWAKE_VLV);
-	else if (INTEL_INFO(dev)->gen >= 7)
-		error->forcewake = I915_READ(FORCEWAKE_MT);
-	else if (INTEL_INFO(dev)->gen == 6)
-		error->forcewake = I915_READ(FORCEWAKE);
-
-	if (!HAS_PCH_SPLIT(dev))
-		for_each_pipe(pipe)
-			error->pipestat[pipe] = I915_READ(PIPESTAT(pipe));
-
-	if (INTEL_INFO(dev)->gen >= 6) {
-		error->error = I915_READ(ERROR_GEN6);
-		error->done_reg = I915_READ(DONE_REG);
-	}
-
-	if (INTEL_INFO(dev)->gen == 7)
-		error->err_int = I915_READ(GEN7_ERR_INT);
-
-	i915_get_extra_instdone(dev, error->extra_instdone);
-
-	i915_gem_record_fences(dev, error);
-	i915_gem_record_rings(dev, error);
-
-	/* Record buffers on the active and pinned lists. */
-	error->active_bo = NULL;
-	error->pinned_bo = NULL;
-
-	i = 0;
-	list_for_each_entry(obj, &dev_priv->mm.active_list, mm_list)
-		i++;
-	error->active_bo_count = i;
-	list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list)
-		if (obj->pin_count)
-			i++;
-	error->pinned_bo_count = i - error->active_bo_count;
-
-	error->active_bo = NULL;
-	error->pinned_bo = NULL;
-	if (i) {
-		error->active_bo = kmalloc(sizeof(*error->active_bo)*i,
-					   GFP_ATOMIC);
-		if (error->active_bo)
-			error->pinned_bo =
-				error->active_bo + error->active_bo_count;
-	}
-
-	if (error->active_bo)
-		error->active_bo_count =
-			capture_active_bo(error->active_bo,
-					  error->active_bo_count,
-					  &dev_priv->mm.active_list);
-
-	if (error->pinned_bo)
-		error->pinned_bo_count =
-			capture_pinned_bo(error->pinned_bo,
-					  error->pinned_bo_count,
-					  &dev_priv->mm.bound_list);
-
-	do_gettimeofday(&error->time);
-
-	error->overlay = intel_overlay_capture_error_state(dev);
-	error->display = intel_display_capture_error_state(dev);
-
-	spin_lock_irqsave(&dev_priv->gpu_error.lock, flags);
-	if (dev_priv->gpu_error.first_error == NULL) {
-		dev_priv->gpu_error.first_error = error;
-		error = NULL;
-	}
-	spin_unlock_irqrestore(&dev_priv->gpu_error.lock, flags);
-
-	if (error)
-		i915_error_state_free(&error->ref);
-}
-
-void i915_destroy_error_state(struct drm_device *dev)
-{
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct drm_i915_error_state *error;
-	unsigned long flags;
-
-	spin_lock_irqsave(&dev_priv->gpu_error.lock, flags);
-	error = dev_priv->gpu_error.first_error;
-	dev_priv->gpu_error.first_error = NULL;
-	spin_unlock_irqrestore(&dev_priv->gpu_error.lock, flags);
-
-	if (error)
-		kref_put(&error->ref, i915_error_state_free);
-}
-#else
-#define i915_capture_error_state(x)
-#endif
-
 static void i915_report_and_clear_eir(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -2104,8 +1676,6 @@ static void i915_report_and_clear_eir(struct drm_device *dev)
 void i915_handle_error(struct drm_device *dev, bool wedged)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_ring_buffer *ring;
-	int i;
 
 	i915_capture_error_state(dev);
 	i915_report_and_clear_eir(dev);
@@ -2115,14 +1685,28 @@ void i915_handle_error(struct drm_device *dev, bool wedged)
 				&dev_priv->gpu_error.reset_counter);
 
 		/*
-		 * Wakeup waiting processes so that the reset work item
-		 * doesn't deadlock trying to grab various locks.
+		 * Wakeup waiting processes so that the reset work function
+		 * i915_error_work_func doesn't deadlock trying to grab various
+		 * locks. By bumping the reset counter first, the woken
+		 * processes will see a reset in progress and back off,
+		 * releasing their locks and then wait for the reset completion.
+		 * We must do this for _all_ gpu waiters that might hold locks
+		 * that the reset work needs to acquire.
+		 *
+		 * Note: The wake_up serves as the required memory barrier to
+		 * ensure that the waiters see the updated value of the reset
+		 * counter atomic_t.
 		 */
-		for_each_ring(ring, dev_priv, i)
-			wake_up_all(&ring->irq_queue);
+		i915_error_wake_up(dev_priv, false);
 	}
 
-	queue_work(dev_priv->wq, &dev_priv->gpu_error.work);
+	/*
+	 * Our reset work can grab modeset locks (since it needs to reset the
+	 * state of outstanding pagelips). Hence it must not be run on our own
+	 * dev-priv->wq work queue for otherwise the flush_work in the pageflip
+	 * code will deadlock.
+	 */
+	schedule_work(&dev_priv->gpu_error.work);
 }
 
 static void __always_unused i915_pageflip_stall_check(struct drm_device *dev, int pipe)
@@ -2155,10 +1739,10 @@ static void __always_unused i915_pageflip_stall_check(struct drm_device *dev, in
 	if (INTEL_INFO(dev)->gen >= 4) {
 		int dspsurf = DSPSURF(intel_crtc->plane);
 		stall_detected = I915_HI_DISPBASE(I915_READ(dspsurf)) ==
-					obj->gtt_offset;
+					i915_gem_obj_ggtt_offset(obj);
 	} else {
 		int dspaddr = DSPADDR(intel_crtc->plane);
-		stall_detected = I915_READ(dspaddr) == (obj->gtt_offset +
+		stall_detected = I915_READ(dspaddr) == (i915_gem_obj_ggtt_offset(obj) +
 							crtc->y * crtc->fb->pitches[0] +
 							crtc->x * crtc->fb->bits_per_pixel/8);
 	}
@@ -2202,29 +1786,14 @@ static int ironlake_enable_vblank(struct drm_device *dev, int pipe)
 {
 	drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private;
 	unsigned long irqflags;
+	uint32_t bit = (INTEL_INFO(dev)->gen >= 7) ? DE_PIPE_VBLANK_IVB(pipe) :
+						     DE_PIPE_VBLANK_ILK(pipe);
 
 	if (!i915_pipe_enabled(dev, pipe))
 		return -EINVAL;
 
 	spin_lock_irqsave(&dev_priv->irq_lock, irqflags);
-	ironlake_enable_display_irq(dev_priv, (pipe == 0) ?
-				    DE_PIPEA_VBLANK : DE_PIPEB_VBLANK);
-	spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags);
-
-	return 0;
-}
-
-static int ivybridge_enable_vblank(struct drm_device *dev, int pipe)
-{
-	drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private;
-	unsigned long irqflags;
-
-	if (!i915_pipe_enabled(dev, pipe))
-		return -EINVAL;
-
-	spin_lock_irqsave(&dev_priv->irq_lock, irqflags);
-	ironlake_enable_display_irq(dev_priv,
-				    DE_PIPEA_VBLANK_IVB << (5 * pipe));
+	ironlake_enable_display_irq(dev_priv, bit);
 	spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags);
 
 	return 0;
@@ -2275,21 +1844,11 @@ static void ironlake_disable_vblank(struct drm_device *dev, int pipe)
 {
 	drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private;
 	unsigned long irqflags;
+	uint32_t bit = (INTEL_INFO(dev)->gen >= 7) ? DE_PIPE_VBLANK_IVB(pipe) :
+						     DE_PIPE_VBLANK_ILK(pipe);
 
 	spin_lock_irqsave(&dev_priv->irq_lock, irqflags);
-	ironlake_disable_display_irq(dev_priv, (pipe == 0) ?
-				     DE_PIPEA_VBLANK : DE_PIPEB_VBLANK);
-	spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags);
-}
-
-static void ivybridge_disable_vblank(struct drm_device *dev, int pipe)
-{
-	drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private;
-	unsigned long irqflags;
-
-	spin_lock_irqsave(&dev_priv->irq_lock, irqflags);
-	ironlake_disable_display_irq(dev_priv,
-				     DE_PIPEA_VBLANK_IVB << (pipe * 5));
+	ironlake_disable_display_irq(dev_priv, bit);
 	spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags);
 }
 
@@ -2392,10 +1951,10 @@ ring_stuck(struct intel_ring_buffer *ring, u32 acthd)
 	u32 tmp;
 
 	if (ring->hangcheck.acthd != acthd)
-		return active;
+		return HANGCHECK_ACTIVE;
 
 	if (IS_GEN2(dev))
-		return hung;
+		return HANGCHECK_HUNG;
 
 	/* Is the chip hanging on a WAIT_FOR_EVENT?
 	 * If so we can simply poke the RB_WAIT bit
@@ -2407,24 +1966,24 @@ ring_stuck(struct intel_ring_buffer *ring, u32 acthd)
 		DRM_ERROR("Kicking stuck wait on %s\n",
 			  ring->name);
 		I915_WRITE_CTL(ring, tmp);
-		return kick;
+		return HANGCHECK_KICK;
 	}
 
 	if (INTEL_INFO(dev)->gen >= 6 && tmp & RING_WAIT_SEMAPHORE) {
 		switch (semaphore_passed(ring)) {
 		default:
-			return hung;
+			return HANGCHECK_HUNG;
 		case 1:
 			DRM_ERROR("Kicking stuck semaphore on %s\n",
 				  ring->name);
 			I915_WRITE_CTL(ring, tmp);
-			return kick;
+			return HANGCHECK_KICK;
 		case 0:
-			return wait;
+			return HANGCHECK_WAIT;
 		}
 	}
 
-	return hung;
+	return HANGCHECK_HUNG;
 }
 
 /**
@@ -2435,7 +1994,7 @@ ring_stuck(struct intel_ring_buffer *ring, u32 acthd)
  * we kick the ring. If we see no progress on three subsequent calls
  * we assume chip is wedged and try to fix it by resetting the chip.
  */
-void i915_hangcheck_elapsed(unsigned long data)
+static void i915_hangcheck_elapsed(unsigned long data)
 {
 	struct drm_device *dev = (struct drm_device *)data;
 	drm_i915_private_t *dev_priv = dev->dev_private;
@@ -2471,8 +2030,6 @@ void i915_hangcheck_elapsed(unsigned long data)
 				} else
 					busy = false;
 			} else {
-				int score;
-
 				/* We always increment the hangcheck score
 				 * if the ring is busy and still processing
 				 * the same request, so that no single request
@@ -2492,21 +2049,19 @@ void i915_hangcheck_elapsed(unsigned long data)
 								    acthd);
 
 				switch (ring->hangcheck.action) {
-				case wait:
-					score = 0;
+				case HANGCHECK_WAIT:
 					break;
-				case active:
-					score = BUSY;
+				case HANGCHECK_ACTIVE:
+					ring->hangcheck.score += BUSY;
 					break;
-				case kick:
-					score = KICK;
+				case HANGCHECK_KICK:
+					ring->hangcheck.score += KICK;
 					break;
-				case hung:
-					score = HUNG;
+				case HANGCHECK_HUNG:
+					ring->hangcheck.score += HUNG;
 					stuck[i] = true;
 					break;
 				}
-				ring->hangcheck.score += score;
 			}
 		} else {
 			/* Gradually reduce the count so that we catch DoS
@@ -2523,9 +2078,9 @@ void i915_hangcheck_elapsed(unsigned long data)
 
 	for_each_ring(ring, dev_priv, i) {
 		if (ring->hangcheck.score > FIRE) {
-			DRM_ERROR("%s on %s\n",
-				  stuck[i] ? "stuck" : "no progress",
-				  ring->name);
+			DRM_INFO("%s on %s\n",
+				 stuck[i] ? "stuck" : "no progress",
+				 ring->name);
 			rings_hung++;
 		}
 	}
@@ -2536,9 +2091,17 @@ void i915_hangcheck_elapsed(unsigned long data)
 	if (busy_count)
 		/* Reset timer case chip hangs without another request
 		 * being added */
-		mod_timer(&dev_priv->gpu_error.hangcheck_timer,
-			  round_jiffies_up(jiffies +
-					   DRM_I915_HANGCHECK_JIFFIES));
+		i915_queue_hangcheck(dev);
+}
+
+void i915_queue_hangcheck(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	if (!i915_enable_hangcheck)
+		return;
+
+	mod_timer(&dev_priv->gpu_error.hangcheck_timer,
+		  round_jiffies_up(jiffies + DRM_I915_HANGCHECK_JIFFIES));
 }
 
 static void ibx_irq_preinstall(struct drm_device *dev)
@@ -2560,31 +2123,26 @@ static void ibx_irq_preinstall(struct drm_device *dev)
 	POSTING_READ(SDEIER);
 }
 
-/* drm_dma.h hooks
-*/
-static void ironlake_irq_preinstall(struct drm_device *dev)
+static void gen5_gt_irq_preinstall(struct drm_device *dev)
 {
-	drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private;
-
-	atomic_set(&dev_priv->irq_received, 0);
-
-	I915_WRITE(HWSTAM, 0xeffe);
-
-	/* XXX hotplug from PCH */
-
-	I915_WRITE(DEIMR, 0xffffffff);
-	I915_WRITE(DEIER, 0x0);
-	POSTING_READ(DEIER);
+	struct drm_i915_private *dev_priv = dev->dev_private;
 
 	/* and GT */
 	I915_WRITE(GTIMR, 0xffffffff);
 	I915_WRITE(GTIER, 0x0);
 	POSTING_READ(GTIER);
 
-	ibx_irq_preinstall(dev);
+	if (INTEL_INFO(dev)->gen >= 6) {
+		/* and PM */
+		I915_WRITE(GEN6_PMIMR, 0xffffffff);
+		I915_WRITE(GEN6_PMIER, 0x0);
+		POSTING_READ(GEN6_PMIER);
+	}
 }
 
-static void ivybridge_irq_preinstall(struct drm_device *dev)
+/* drm_dma.h hooks
+*/
+static void ironlake_irq_preinstall(struct drm_device *dev)
 {
 	drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private;
 
@@ -2592,21 +2150,11 @@ static void ivybridge_irq_preinstall(struct drm_device *dev)
 
 	I915_WRITE(HWSTAM, 0xeffe);
 
-	/* XXX hotplug from PCH */
-
 	I915_WRITE(DEIMR, 0xffffffff);
 	I915_WRITE(DEIER, 0x0);
 	POSTING_READ(DEIER);
 
-	/* and GT */
-	I915_WRITE(GTIMR, 0xffffffff);
-	I915_WRITE(GTIER, 0x0);
-	POSTING_READ(GTIER);
-
-	/* Power management */
-	I915_WRITE(GEN6_PMIMR, 0xffffffff);
-	I915_WRITE(GEN6_PMIER, 0x0);
-	POSTING_READ(GEN6_PMIER);
+	gen5_gt_irq_preinstall(dev);
 
 	ibx_irq_preinstall(dev);
 }
@@ -2627,9 +2175,8 @@ static void valleyview_irq_preinstall(struct drm_device *dev)
 	/* and GT */
 	I915_WRITE(GTIIR, I915_READ(GTIIR));
 	I915_WRITE(GTIIR, I915_READ(GTIIR));
-	I915_WRITE(GTIMR, 0xffffffff);
-	I915_WRITE(GTIER, 0x0);
-	POSTING_READ(GTIER);
+
+	gen5_gt_irq_preinstall(dev);
 
 	I915_WRITE(DPINVGTT, 0xff);
 
@@ -2648,22 +2195,21 @@ static void ibx_hpd_irq_setup(struct drm_device *dev)
 	drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private;
 	struct drm_mode_config *mode_config = &dev->mode_config;
 	struct intel_encoder *intel_encoder;
-	u32 mask = ~I915_READ(SDEIMR);
-	u32 hotplug;
+	u32 hotplug_irqs, hotplug, enabled_irqs = 0;
 
 	if (HAS_PCH_IBX(dev)) {
-		mask &= ~SDE_HOTPLUG_MASK;
+		hotplug_irqs = SDE_HOTPLUG_MASK;
 		list_for_each_entry(intel_encoder, &mode_config->encoder_list, base.head)
 			if (dev_priv->hpd_stats[intel_encoder->hpd_pin].hpd_mark == HPD_ENABLED)
-				mask |= hpd_ibx[intel_encoder->hpd_pin];
+				enabled_irqs |= hpd_ibx[intel_encoder->hpd_pin];
 	} else {
-		mask &= ~SDE_HOTPLUG_MASK_CPT;
+		hotplug_irqs = SDE_HOTPLUG_MASK_CPT;
 		list_for_each_entry(intel_encoder, &mode_config->encoder_list, base.head)
 			if (dev_priv->hpd_stats[intel_encoder->hpd_pin].hpd_mark == HPD_ENABLED)
-				mask |= hpd_cpt[intel_encoder->hpd_pin];
+				enabled_irqs |= hpd_cpt[intel_encoder->hpd_pin];
 	}
 
-	I915_WRITE(SDEIMR, ~mask);
+	ibx_display_interrupt_update(dev_priv, hotplug_irqs, enabled_irqs);
 
 	/*
 	 * Enable digital hotplug on the PCH, and configure the DP short pulse
@@ -2700,123 +2246,103 @@ static void ibx_irq_postinstall(struct drm_device *dev)
 	I915_WRITE(SDEIMR, ~mask);
 }
 
-static int ironlake_irq_postinstall(struct drm_device *dev)
+static void gen5_gt_irq_postinstall(struct drm_device *dev)
 {
-	unsigned long irqflags;
-
-	drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private;
-	/* enable kind of interrupts always enabled */
-	u32 display_mask = DE_MASTER_IRQ_CONTROL | DE_GSE | DE_PCH_EVENT |
-			   DE_PLANEA_FLIP_DONE | DE_PLANEB_FLIP_DONE |
-			   DE_AUX_CHANNEL_A | DE_PIPEB_FIFO_UNDERRUN |
-			   DE_PIPEA_FIFO_UNDERRUN | DE_POISON;
-	u32 gt_irqs;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	u32 pm_irqs, gt_irqs;
 
-	dev_priv->irq_mask = ~display_mask;
-
-	/* should always can generate irq */
-	I915_WRITE(DEIIR, I915_READ(DEIIR));
-	I915_WRITE(DEIMR, dev_priv->irq_mask);
-	I915_WRITE(DEIER, display_mask |
-			  DE_PIPEA_VBLANK | DE_PIPEB_VBLANK | DE_PCU_EVENT);
-	POSTING_READ(DEIER);
+	pm_irqs = gt_irqs = 0;
 
 	dev_priv->gt_irq_mask = ~0;
+	if (HAS_L3_GPU_CACHE(dev)) {
+		/* L3 parity interrupt is always unmasked. */
+		dev_priv->gt_irq_mask = ~GT_RENDER_L3_PARITY_ERROR_INTERRUPT;
+		gt_irqs |= GT_RENDER_L3_PARITY_ERROR_INTERRUPT;
+	}
 
-	I915_WRITE(GTIIR, I915_READ(GTIIR));
-	I915_WRITE(GTIMR, dev_priv->gt_irq_mask);
-
-	gt_irqs = GT_RENDER_USER_INTERRUPT;
-
-	if (IS_GEN6(dev))
-		gt_irqs |= GT_BLT_USER_INTERRUPT | GT_BSD_USER_INTERRUPT;
-	else
+	gt_irqs |= GT_RENDER_USER_INTERRUPT;
+	if (IS_GEN5(dev)) {
 		gt_irqs |= GT_RENDER_PIPECTL_NOTIFY_INTERRUPT |
 			   ILK_BSD_USER_INTERRUPT;
+	} else {
+		gt_irqs |= GT_BLT_USER_INTERRUPT | GT_BSD_USER_INTERRUPT;
+	}
 
+	I915_WRITE(GTIIR, I915_READ(GTIIR));
+	I915_WRITE(GTIMR, dev_priv->gt_irq_mask);
 	I915_WRITE(GTIER, gt_irqs);
 	POSTING_READ(GTIER);
 
-	ibx_irq_postinstall(dev);
+	if (INTEL_INFO(dev)->gen >= 6) {
+		pm_irqs |= GEN6_PM_RPS_EVENTS;
 
-	if (IS_IRONLAKE_M(dev)) {
-		/* Enable PCU event interrupts
-		 *
-		 * spinlocking not required here for correctness since interrupt
-		 * setup is guaranteed to run in single-threaded context. But we
-		 * need it to make the assert_spin_locked happy. */
-		spin_lock_irqsave(&dev_priv->irq_lock, irqflags);
-		ironlake_enable_display_irq(dev_priv, DE_PCU_EVENT);
-		spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags);
-	}
+		if (HAS_VEBOX(dev))
+			pm_irqs |= PM_VEBOX_USER_INTERRUPT;
 
-	return 0;
+		dev_priv->pm_irq_mask = 0xffffffff;
+		I915_WRITE(GEN6_PMIIR, I915_READ(GEN6_PMIIR));
+		I915_WRITE(GEN6_PMIMR, dev_priv->pm_irq_mask);
+		I915_WRITE(GEN6_PMIER, pm_irqs);
+		POSTING_READ(GEN6_PMIER);
+	}
 }
 
-static int ivybridge_irq_postinstall(struct drm_device *dev)
+static int ironlake_irq_postinstall(struct drm_device *dev)
 {
+	unsigned long irqflags;
 	drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private;
-	/* enable kind of interrupts always enabled */
-	u32 display_mask =
-		DE_MASTER_IRQ_CONTROL | DE_GSE_IVB | DE_PCH_EVENT_IVB |
-		DE_PLANEC_FLIP_DONE_IVB |
-		DE_PLANEB_FLIP_DONE_IVB |
-		DE_PLANEA_FLIP_DONE_IVB |
-		DE_AUX_CHANNEL_A_IVB |
-		DE_ERR_INT_IVB;
-	u32 pm_irqs = GEN6_PM_RPS_EVENTS;
-	u32 gt_irqs;
+	u32 display_mask, extra_mask;
+
+	if (INTEL_INFO(dev)->gen >= 7) {
+		display_mask = (DE_MASTER_IRQ_CONTROL | DE_GSE_IVB |
+				DE_PCH_EVENT_IVB | DE_PLANEC_FLIP_DONE_IVB |
+				DE_PLANEB_FLIP_DONE_IVB |
+				DE_PLANEA_FLIP_DONE_IVB | DE_AUX_CHANNEL_A_IVB |
+				DE_ERR_INT_IVB);
+		extra_mask = (DE_PIPEC_VBLANK_IVB | DE_PIPEB_VBLANK_IVB |
+			      DE_PIPEA_VBLANK_IVB);
+
+		I915_WRITE(GEN7_ERR_INT, I915_READ(GEN7_ERR_INT));
+	} else {
+		display_mask = (DE_MASTER_IRQ_CONTROL | DE_GSE | DE_PCH_EVENT |
+				DE_PLANEA_FLIP_DONE | DE_PLANEB_FLIP_DONE |
+				DE_AUX_CHANNEL_A | DE_PIPEB_FIFO_UNDERRUN |
+				DE_PIPEA_FIFO_UNDERRUN | DE_POISON);
+		extra_mask = DE_PIPEA_VBLANK | DE_PIPEB_VBLANK | DE_PCU_EVENT;
+	}
 
 	dev_priv->irq_mask = ~display_mask;
 
 	/* should always can generate irq */
-	I915_WRITE(GEN7_ERR_INT, I915_READ(GEN7_ERR_INT));
 	I915_WRITE(DEIIR, I915_READ(DEIIR));
 	I915_WRITE(DEIMR, dev_priv->irq_mask);
-	I915_WRITE(DEIER,
-		   display_mask |
-		   DE_PIPEC_VBLANK_IVB |
-		   DE_PIPEB_VBLANK_IVB |
-		   DE_PIPEA_VBLANK_IVB);
+	I915_WRITE(DEIER, display_mask | extra_mask);
 	POSTING_READ(DEIER);
 
-	dev_priv->gt_irq_mask = ~GT_RENDER_L3_PARITY_ERROR_INTERRUPT;
-
-	I915_WRITE(GTIIR, I915_READ(GTIIR));
-	I915_WRITE(GTIMR, dev_priv->gt_irq_mask);
-
-	gt_irqs = GT_RENDER_USER_INTERRUPT | GT_BSD_USER_INTERRUPT |
-		  GT_BLT_USER_INTERRUPT | GT_RENDER_L3_PARITY_ERROR_INTERRUPT;
-	I915_WRITE(GTIER, gt_irqs);
-	POSTING_READ(GTIER);
-
-	I915_WRITE(GEN6_PMIIR, I915_READ(GEN6_PMIIR));
-	if (HAS_VEBOX(dev))
-		pm_irqs |= PM_VEBOX_USER_INTERRUPT |
-			PM_VEBOX_CS_ERROR_INTERRUPT;
-
-	/* Our enable/disable rps functions may touch these registers so
-	 * make sure to set a known state for only the non-RPS bits.
-	 * The RMW is extra paranoia since this should be called after being set
-	 * to a known state in preinstall.
-	 * */
-	I915_WRITE(GEN6_PMIMR,
-		   (I915_READ(GEN6_PMIMR) | ~GEN6_PM_RPS_EVENTS) & ~pm_irqs);
-	I915_WRITE(GEN6_PMIER,
-		   (I915_READ(GEN6_PMIER) & GEN6_PM_RPS_EVENTS) | pm_irqs);
-	POSTING_READ(GEN6_PMIER);
+	gen5_gt_irq_postinstall(dev);
 
 	ibx_irq_postinstall(dev);
 
+	if (IS_IRONLAKE_M(dev)) {
+		/* Enable PCU event interrupts
+		 *
+		 * spinlocking not required here for correctness since interrupt
+		 * setup is guaranteed to run in single-threaded context. But we
+		 * need it to make the assert_spin_locked happy. */
+		spin_lock_irqsave(&dev_priv->irq_lock, irqflags);
+		ironlake_enable_display_irq(dev_priv, DE_PCU_EVENT);
+		spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags);
+	}
+
 	return 0;
 }
 
 static int valleyview_irq_postinstall(struct drm_device *dev)
 {
 	drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private;
-	u32 gt_irqs;
 	u32 enable_mask;
 	u32 pipestat_enable = PLANE_FLIP_DONE_INT_EN_VLV;
+	unsigned long irqflags;
 
 	enable_mask = I915_DISPLAY_PORT_INTERRUPT;
 	enable_mask |= I915_DISPLAY_PIPE_A_EVENT_INTERRUPT |
@@ -2842,20 +2368,18 @@ static int valleyview_irq_postinstall(struct drm_device *dev)
 	I915_WRITE(PIPESTAT(1), 0xffff);
 	POSTING_READ(VLV_IER);
 
+	/* Interrupt setup is already guaranteed to be single-threaded, this is
+	 * just to make the assert_spin_locked check happy. */
+	spin_lock_irqsave(&dev_priv->irq_lock, irqflags);
 	i915_enable_pipestat(dev_priv, 0, pipestat_enable);
 	i915_enable_pipestat(dev_priv, 0, PIPE_GMBUS_EVENT_ENABLE);
 	i915_enable_pipestat(dev_priv, 1, pipestat_enable);
+	spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags);
 
 	I915_WRITE(VLV_IIR, 0xffffffff);
 	I915_WRITE(VLV_IIR, 0xffffffff);
 
-	I915_WRITE(GTIIR, I915_READ(GTIIR));
-	I915_WRITE(GTIMR, dev_priv->gt_irq_mask);
-
-	gt_irqs = GT_RENDER_USER_INTERRUPT | GT_BSD_USER_INTERRUPT |
-		GT_BLT_USER_INTERRUPT;
-	I915_WRITE(GTIER, gt_irqs);
-	POSTING_READ(GTIER);
+	gen5_gt_irq_postinstall(dev);
 
 	/* ack & enable invalid PTE error interrupts */
 #if 0 /* FIXME: add support to irq handler for checking these bits */
@@ -3001,7 +2525,6 @@ static irqreturn_t i8xx_irq_handler(int irq, void *arg)
 	u16 iir, new_iir;
 	u32 pipe_stats[2];
 	unsigned long irqflags;
-	int irq_received;
 	int pipe;
 	u16 flip_mask =
 		I915_DISPLAY_PLANE_A_FLIP_PENDING_INTERRUPT |
@@ -3035,7 +2558,6 @@ static irqreturn_t i8xx_irq_handler(int irq, void *arg)
 					DRM_DEBUG_DRIVER("pipe %c underrun\n",
 							 pipe_name(pipe));
 				I915_WRITE(reg, pipe_stats[pipe]);
-				irq_received = 1;
 			}
 		}
 		spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags);
@@ -3323,6 +2845,7 @@ static int i965_irq_postinstall(struct drm_device *dev)
 	drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private;
 	u32 enable_mask;
 	u32 error_mask;
+	unsigned long irqflags;
 
 	/* Unmask the interrupts that we always want on. */
 	dev_priv->irq_mask = ~(I915_ASLE_INTERRUPT |
@@ -3341,7 +2864,11 @@ static int i965_irq_postinstall(struct drm_device *dev)
 	if (IS_G4X(dev))
 		enable_mask |= I915_BSD_USER_INTERRUPT;
 
+	/* Interrupt setup is already guaranteed to be single-threaded, this is
+	 * just to make the assert_spin_locked check happy. */
+	spin_lock_irqsave(&dev_priv->irq_lock, irqflags);
 	i915_enable_pipestat(dev_priv, 0, PIPE_GMBUS_EVENT_ENABLE);
+	spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags);
 
 	/*
 	 * Enable some error detection, note the instruction error mask
@@ -3616,15 +3143,6 @@ void intel_irq_init(struct drm_device *dev)
 		dev->driver->enable_vblank = valleyview_enable_vblank;
 		dev->driver->disable_vblank = valleyview_disable_vblank;
 		dev_priv->display.hpd_irq_setup = i915_hpd_irq_setup;
-	} else if (IS_IVYBRIDGE(dev) || IS_HASWELL(dev)) {
-		/* Share uninstall handlers with ILK/SNB */
-		dev->driver->irq_handler = ivybridge_irq_handler;
-		dev->driver->irq_preinstall = ivybridge_irq_preinstall;
-		dev->driver->irq_postinstall = ivybridge_irq_postinstall;
-		dev->driver->irq_uninstall = ironlake_irq_uninstall;
-		dev->driver->enable_vblank = ivybridge_enable_vblank;
-		dev->driver->disable_vblank = ivybridge_disable_vblank;
-		dev_priv->display.hpd_irq_setup = ibx_hpd_irq_setup;
 	} else if (HAS_PCH_SPLIT(dev)) {
 		dev->driver->irq_handler = ironlake_irq_handler;
 		dev->driver->irq_preinstall = ironlake_irq_preinstall;
@@ -3683,3 +3201,67 @@ void intel_hpd_init(struct drm_device *dev)
 		dev_priv->display.hpd_irq_setup(dev);
 	spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags);
 }
+
+/* Disable interrupts so we can allow Package C8+. */
+void hsw_pc8_disable_interrupts(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	unsigned long irqflags;
+
+	spin_lock_irqsave(&dev_priv->irq_lock, irqflags);
+
+	dev_priv->pc8.regsave.deimr = I915_READ(DEIMR);
+	dev_priv->pc8.regsave.sdeimr = I915_READ(SDEIMR);
+	dev_priv->pc8.regsave.gtimr = I915_READ(GTIMR);
+	dev_priv->pc8.regsave.gtier = I915_READ(GTIER);
+	dev_priv->pc8.regsave.gen6_pmimr = I915_READ(GEN6_PMIMR);
+
+	ironlake_disable_display_irq(dev_priv, ~DE_PCH_EVENT_IVB);
+	ibx_disable_display_interrupt(dev_priv, ~SDE_HOTPLUG_MASK_CPT);
+	ilk_disable_gt_irq(dev_priv, 0xffffffff);
+	snb_disable_pm_irq(dev_priv, 0xffffffff);
+
+	dev_priv->pc8.irqs_disabled = true;
+
+	spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags);
+}
+
+/* Restore interrupts so we can recover from Package C8+. */
+void hsw_pc8_restore_interrupts(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	unsigned long irqflags;
+	uint32_t val, expected;
+
+	spin_lock_irqsave(&dev_priv->irq_lock, irqflags);
+
+	val = I915_READ(DEIMR);
+	expected = ~DE_PCH_EVENT_IVB;
+	WARN(val != expected, "DEIMR is 0x%08x, not 0x%08x\n", val, expected);
+
+	val = I915_READ(SDEIMR) & ~SDE_HOTPLUG_MASK_CPT;
+	expected = ~SDE_HOTPLUG_MASK_CPT;
+	WARN(val != expected, "SDEIMR non-HPD bits are 0x%08x, not 0x%08x\n",
+	     val, expected);
+
+	val = I915_READ(GTIMR);
+	expected = 0xffffffff;
+	WARN(val != expected, "GTIMR is 0x%08x, not 0x%08x\n", val, expected);
+
+	val = I915_READ(GEN6_PMIMR);
+	expected = 0xffffffff;
+	WARN(val != expected, "GEN6_PMIMR is 0x%08x, not 0x%08x\n", val,
+	     expected);
+
+	dev_priv->pc8.irqs_disabled = false;
+
+	ironlake_enable_display_irq(dev_priv, ~dev_priv->pc8.regsave.deimr);
+	ibx_enable_display_interrupt(dev_priv,
+				     ~dev_priv->pc8.regsave.sdeimr &
+				     ~SDE_HOTPLUG_MASK_CPT);
+	ilk_enable_gt_irq(dev_priv, ~dev_priv->pc8.regsave.gtimr);
+	snb_enable_pm_irq(dev_priv, ~dev_priv->pc8.regsave.gen6_pmimr);
+	I915_WRITE(GTIER, dev_priv->pc8.regsave.gtier);
+
+	spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags);
+}
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 342f1f336168..38f96f65d87a 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -33,21 +33,6 @@
 #define _MASKED_BIT_ENABLE(a) (((a) << 16) | (a))
 #define _MASKED_BIT_DISABLE(a) ((a) << 16)
 
-/*
- * The Bridge device's PCI config space has information about the
- * fb aperture size and the amount of pre-reserved memory.
- * This is all handled in the intel-gtt.ko module. i915.ko only
- * cares about the vga bit for the vga rbiter.
- */
-#define INTEL_GMCH_CTRL		0x52
-#define INTEL_GMCH_VGA_DISABLE  (1 << 1)
-#define SNB_GMCH_CTRL		0x50
-#define    SNB_GMCH_GGMS_SHIFT	8 /* GTT Graphics Memory Size */
-#define    SNB_GMCH_GGMS_MASK	0x3
-#define    SNB_GMCH_GMS_SHIFT   3 /* Graphics Mode Select */
-#define    SNB_GMCH_GMS_MASK    0x1f
-
-
 /* PCI config space */
 
 #define HPLLCC	0xc0 /* 855 only */
@@ -61,6 +46,12 @@
 #define   GC_LOW_FREQUENCY_ENABLE	(1 << 7)
 #define   GC_DISPLAY_CLOCK_190_200_MHZ	(0 << 4)
 #define   GC_DISPLAY_CLOCK_333_MHZ	(4 << 4)
+#define   GC_DISPLAY_CLOCK_267_MHZ_PNV	(0 << 4)
+#define   GC_DISPLAY_CLOCK_333_MHZ_PNV	(1 << 4)
+#define   GC_DISPLAY_CLOCK_444_MHZ_PNV	(2 << 4)
+#define   GC_DISPLAY_CLOCK_200_MHZ_PNV	(5 << 4)
+#define   GC_DISPLAY_CLOCK_133_MHZ_PNV	(6 << 4)
+#define   GC_DISPLAY_CLOCK_167_MHZ_PNV	(7 << 4)
 #define   GC_DISPLAY_CLOCK_MASK		(7 << 4)
 #define   GM45_GC_RENDER_CLOCK_MASK	(0xf << 0)
 #define   GM45_GC_RENDER_CLOCK_266_MHZ	(8 << 0)
@@ -239,6 +230,7 @@
  *   address/value pairs. Don't overdue it, though, x <= 2^4 must hold!
  */
 #define MI_LOAD_REGISTER_IMM(x)	MI_INSTR(0x22, 2*x-1)
+#define MI_STORE_REGISTER_MEM(x) MI_INSTR(0x24, 2*x-1)
 #define MI_FLUSH_DW		MI_INSTR(0x26, 1) /* for GEN6 */
 #define   MI_FLUSH_DW_STORE_INDEX	(1<<21)
 #define   MI_INVALIDATE_TLB		(1<<18)
@@ -363,6 +355,7 @@
 #define PUNIT_REG_GPU_LFM			0xd3
 #define PUNIT_REG_GPU_FREQ_REQ			0xd4
 #define PUNIT_REG_GPU_FREQ_STS			0xd8
+#define   GENFREQSTATUS				(1<<0)
 #define PUNIT_REG_MEDIA_TURBO_FREQ_REQ		0xdc
 
 #define PUNIT_FUSE_BUS2				0xf6 /* bits 47:40 */
@@ -680,11 +673,29 @@
 #define   ERR_INT_FIFO_UNDERRUN_C	(1<<6)
 #define   ERR_INT_FIFO_UNDERRUN_B	(1<<3)
 #define   ERR_INT_FIFO_UNDERRUN_A	(1<<0)
+#define   ERR_INT_FIFO_UNDERRUN(pipe)	(1<<(pipe*3))
 
 #define FPGA_DBG		0x42300
 #define   FPGA_DBG_RM_NOCLAIM	(1<<31)
 
 #define DERRMR		0x44050
+#define   DERRMR_PIPEA_SCANLINE		(1<<0)
+#define   DERRMR_PIPEA_PRI_FLIP_DONE	(1<<1)
+#define   DERRMR_PIPEA_SPR_FLIP_DONE	(1<<2)
+#define   DERRMR_PIPEA_VBLANK		(1<<3)
+#define   DERRMR_PIPEA_HBLANK		(1<<5)
+#define   DERRMR_PIPEB_SCANLINE 	(1<<8)
+#define   DERRMR_PIPEB_PRI_FLIP_DONE	(1<<9)
+#define   DERRMR_PIPEB_SPR_FLIP_DONE	(1<<10)
+#define   DERRMR_PIPEB_VBLANK		(1<<11)
+#define   DERRMR_PIPEB_HBLANK		(1<<13)
+/* Note that PIPEC is not a simple translation of PIPEA/PIPEB */
+#define   DERRMR_PIPEC_SCANLINE		(1<<14)
+#define   DERRMR_PIPEC_PRI_FLIP_DONE	(1<<15)
+#define   DERRMR_PIPEC_SPR_FLIP_DONE	(1<<20)
+#define   DERRMR_PIPEC_VBLANK		(1<<21)
+#define   DERRMR_PIPEC_HBLANK		(1<<22)
+
 
 /* GM45+ chicken bits -- debug workaround bits that may be required
  * for various sorts of correct behavior.  The top 16 bits of each are
@@ -1127,7 +1138,8 @@
 #define _DPLL_B	(dev_priv->info->display_mmio_offset + 0x6018)
 #define DPLL(pipe) _PIPE(pipe, _DPLL_A, _DPLL_B)
 #define   DPLL_VCO_ENABLE		(1 << 31)
-#define   DPLL_DVO_HIGH_SPEED		(1 << 30)
+#define   DPLL_SDVO_HIGH_SPEED		(1 << 30)
+#define   DPLL_DVO_2X_MODE		(1 << 30)
 #define   DPLL_EXT_BUFFER_ENABLE_VLV	(1 << 30)
 #define   DPLL_SYNCLOCK_ENABLE		(1 << 29)
 #define   DPLL_REFA_CLK_ENABLE_VLV	(1 << 29)
@@ -1440,6 +1452,8 @@
 #define   MCH_SSKPD_WM0_MASK		0x3f
 #define   MCH_SSKPD_WM0_VAL		0xc
 
+#define MCH_SECP_NRG_STTS		(MCHBAR_MIRROR_BASE_SNB + 0x592c)
+
 /* Clocking configuration register */
 #define CLKCFG			0x10c00
 #define CLKCFG_FSB_400					(5 << 0)	/* hrawclk 100 */
@@ -1696,15 +1710,26 @@
  */
 #define CCID			0x2180
 #define   CCID_EN		(1<<0)
+/*
+ * Notes on SNB/IVB/VLV context size:
+ * - Power context is saved elsewhere (LLC or stolen)
+ * - Ring/execlist context is saved on SNB, not on IVB
+ * - Extended context size already includes render context size
+ * - We always need to follow the extended context size.
+ *   SNB BSpec has comments indicating that we should use the
+ *   render context size instead if execlists are disabled, but
+ *   based on empirical testing that's just nonsense.
+ * - Pipelined/VF state is saved on SNB/IVB respectively
+ * - GT1 size just indicates how much of render context
+ *   doesn't need saving on GT1
+ */
 #define CXT_SIZE		0x21a0
 #define GEN6_CXT_POWER_SIZE(cxt_reg)	((cxt_reg >> 24) & 0x3f)
 #define GEN6_CXT_RING_SIZE(cxt_reg)	((cxt_reg >> 18) & 0x3f)
 #define GEN6_CXT_RENDER_SIZE(cxt_reg)	((cxt_reg >> 12) & 0x3f)
 #define GEN6_CXT_EXTENDED_SIZE(cxt_reg)	((cxt_reg >> 6) & 0x3f)
 #define GEN6_CXT_PIPELINE_SIZE(cxt_reg)	((cxt_reg >> 0) & 0x3f)
-#define GEN6_CXT_TOTAL_SIZE(cxt_reg)	(GEN6_CXT_POWER_SIZE(cxt_reg) + \
-					GEN6_CXT_RING_SIZE(cxt_reg) + \
-					GEN6_CXT_RENDER_SIZE(cxt_reg) + \
+#define GEN6_CXT_TOTAL_SIZE(cxt_reg)	(GEN6_CXT_RING_SIZE(cxt_reg) + \
 					GEN6_CXT_EXTENDED_SIZE(cxt_reg) + \
 					GEN6_CXT_PIPELINE_SIZE(cxt_reg))
 #define GEN7_CXT_SIZE		0x21a8
@@ -1714,11 +1739,7 @@
 #define GEN7_CXT_EXTENDED_SIZE(ctx_reg)	((ctx_reg >> 9) & 0x7f)
 #define GEN7_CXT_GT1_SIZE(ctx_reg)	((ctx_reg >> 6) & 0x7)
 #define GEN7_CXT_VFSTATE_SIZE(ctx_reg)	((ctx_reg >> 0) & 0x3f)
-#define GEN7_CXT_TOTAL_SIZE(ctx_reg)	(GEN7_CXT_POWER_SIZE(ctx_reg) + \
-					 GEN7_CXT_RING_SIZE(ctx_reg) + \
-					 GEN7_CXT_RENDER_SIZE(ctx_reg) + \
-					 GEN7_CXT_EXTENDED_SIZE(ctx_reg) + \
-					 GEN7_CXT_GT1_SIZE(ctx_reg) + \
+#define GEN7_CXT_TOTAL_SIZE(ctx_reg)	(GEN7_CXT_EXTENDED_SIZE(ctx_reg) + \
 					 GEN7_CXT_VFSTATE_SIZE(ctx_reg))
 /* Haswell does have the CXT_SIZE register however it does not appear to be
  * valid. Now, docs explain in dwords what is in the context object. The full
@@ -1778,6 +1799,71 @@
 #define BCLRPAT(pipe) _PIPE(pipe, _BCLRPAT_A, _BCLRPAT_B)
 #define VSYNCSHIFT(trans) _TRANSCODER(trans, _VSYNCSHIFT_A, _VSYNCSHIFT_B)
 
+/* HSW eDP PSR registers */
+#define EDP_PSR_CTL				0x64800
+#define   EDP_PSR_ENABLE			(1<<31)
+#define   EDP_PSR_LINK_DISABLE			(0<<27)
+#define   EDP_PSR_LINK_STANDBY			(1<<27)
+#define   EDP_PSR_MIN_LINK_ENTRY_TIME_MASK	(3<<25)
+#define   EDP_PSR_MIN_LINK_ENTRY_TIME_8_LINES	(0<<25)
+#define   EDP_PSR_MIN_LINK_ENTRY_TIME_4_LINES	(1<<25)
+#define   EDP_PSR_MIN_LINK_ENTRY_TIME_2_LINES	(2<<25)
+#define   EDP_PSR_MIN_LINK_ENTRY_TIME_0_LINES	(3<<25)
+#define   EDP_PSR_MAX_SLEEP_TIME_SHIFT		20
+#define   EDP_PSR_SKIP_AUX_EXIT			(1<<12)
+#define   EDP_PSR_TP1_TP2_SEL			(0<<11)
+#define   EDP_PSR_TP1_TP3_SEL			(1<<11)
+#define   EDP_PSR_TP2_TP3_TIME_500us		(0<<8)
+#define   EDP_PSR_TP2_TP3_TIME_100us		(1<<8)
+#define   EDP_PSR_TP2_TP3_TIME_2500us		(2<<8)
+#define   EDP_PSR_TP2_TP3_TIME_0us		(3<<8)
+#define   EDP_PSR_TP1_TIME_500us		(0<<4)
+#define   EDP_PSR_TP1_TIME_100us		(1<<4)
+#define   EDP_PSR_TP1_TIME_2500us		(2<<4)
+#define   EDP_PSR_TP1_TIME_0us			(3<<4)
+#define   EDP_PSR_IDLE_FRAME_SHIFT		0
+
+#define EDP_PSR_AUX_CTL			0x64810
+#define EDP_PSR_AUX_DATA1		0x64814
+#define   EDP_PSR_DPCD_COMMAND		0x80060000
+#define EDP_PSR_AUX_DATA2		0x64818
+#define   EDP_PSR_DPCD_NORMAL_OPERATION	(1<<24)
+#define EDP_PSR_AUX_DATA3		0x6481c
+#define EDP_PSR_AUX_DATA4		0x64820
+#define EDP_PSR_AUX_DATA5		0x64824
+
+#define EDP_PSR_STATUS_CTL			0x64840
+#define   EDP_PSR_STATUS_STATE_MASK		(7<<29)
+#define   EDP_PSR_STATUS_STATE_IDLE		(0<<29)
+#define   EDP_PSR_STATUS_STATE_SRDONACK		(1<<29)
+#define   EDP_PSR_STATUS_STATE_SRDENT		(2<<29)
+#define   EDP_PSR_STATUS_STATE_BUFOFF		(3<<29)
+#define   EDP_PSR_STATUS_STATE_BUFON		(4<<29)
+#define   EDP_PSR_STATUS_STATE_AUXACK		(5<<29)
+#define   EDP_PSR_STATUS_STATE_SRDOFFACK	(6<<29)
+#define   EDP_PSR_STATUS_LINK_MASK		(3<<26)
+#define   EDP_PSR_STATUS_LINK_FULL_OFF		(0<<26)
+#define   EDP_PSR_STATUS_LINK_FULL_ON		(1<<26)
+#define   EDP_PSR_STATUS_LINK_STANDBY		(2<<26)
+#define   EDP_PSR_STATUS_MAX_SLEEP_TIMER_SHIFT	20
+#define   EDP_PSR_STATUS_MAX_SLEEP_TIMER_MASK	0x1f
+#define   EDP_PSR_STATUS_COUNT_SHIFT		16
+#define   EDP_PSR_STATUS_COUNT_MASK		0xf
+#define   EDP_PSR_STATUS_AUX_ERROR		(1<<15)
+#define   EDP_PSR_STATUS_AUX_SENDING		(1<<12)
+#define   EDP_PSR_STATUS_SENDING_IDLE		(1<<9)
+#define   EDP_PSR_STATUS_SENDING_TP2_TP3	(1<<8)
+#define   EDP_PSR_STATUS_SENDING_TP1		(1<<4)
+#define   EDP_PSR_STATUS_IDLE_MASK		0xf
+
+#define EDP_PSR_PERF_CNT		0x64844
+#define   EDP_PSR_PERF_CNT_MASK		0xffffff
+
+#define EDP_PSR_DEBUG_CTL		0x64860
+#define   EDP_PSR_DEBUG_MASK_LPSP	(1<<27)
+#define   EDP_PSR_DEBUG_MASK_MEMUP	(1<<26)
+#define   EDP_PSR_DEBUG_MASK_HPD	(1<<25)
+
 /* VGA port control */
 #define ADPA			0x61100
 #define PCH_ADPA                0xe1100
@@ -2053,6 +2139,7 @@
  * (Haswell and newer) to see which VIDEO_DIP_DATA byte corresponds to each byte
  * of the infoframe structure specified by CEA-861. */
 #define   VIDEO_DIP_DATA_SIZE	32
+#define   VIDEO_DIP_VSC_DATA_SIZE	36
 #define VIDEO_DIP_CTL		0x61170
 /* Pre HSW: */
 #define   VIDEO_DIP_ENABLE		(1 << 31)
@@ -2200,6 +2287,8 @@
 #define BLC_PWM_CPU_CTL2	0x48250
 #define BLC_PWM_CPU_CTL		0x48254
 
+#define HSW_BLC_PWM2_CTL	0x48350
+
 /* PCH CTL1 is totally different, all but the below bits are reserved. CTL2 is
  * like the normal CTL from gen4 and earlier. Hooray for confusing naming. */
 #define BLC_PWM_PCH_CTL1	0xc8250
@@ -2208,6 +2297,12 @@
 #define   BLM_PCH_POLARITY			(1 << 29)
 #define BLC_PWM_PCH_CTL2	0xc8254
 
+#define UTIL_PIN_CTL		0x48400
+#define   UTIL_PIN_ENABLE	(1 << 31)
+
+#define PCH_GTC_CTL		0xe7000
+#define   PCH_GTC_ENABLE	(1 << 31)
+
 /* TV port control */
 #define TV_CTL			0x68000
 /** Enables the TV encoder */
@@ -3121,9 +3216,6 @@
 #define  MLTR_WM2_SHIFT		8
 /* the unit of memory self-refresh latency time is 0.5us */
 #define  ILK_SRLT_MASK		0x3f
-#define ILK_LATENCY(shift)	(I915_READ(MLTR_ILK) >> (shift) & ILK_SRLT_MASK)
-#define ILK_READ_WM1_LATENCY()	ILK_LATENCY(MLTR_WM1_SHIFT)
-#define ILK_READ_WM2_LATENCY()	ILK_LATENCY(MLTR_WM2_SHIFT)
 
 /* define the fifo size on Ironlake */
 #define ILK_DISPLAY_FIFO	128
@@ -3170,12 +3262,6 @@
 #define SSKPD_WM2_SHIFT		16
 #define SSKPD_WM3_SHIFT		24
 
-#define SNB_LATENCY(shift)	(I915_READ(MCHBAR_MIRROR_BASE_SNB + SSKPD) >> (shift) & SSKPD_WM_MASK)
-#define SNB_READ_WM0_LATENCY()		SNB_LATENCY(SSKPD_WM0_SHIFT)
-#define SNB_READ_WM1_LATENCY()		SNB_LATENCY(SSKPD_WM1_SHIFT)
-#define SNB_READ_WM2_LATENCY()		SNB_LATENCY(SSKPD_WM2_SHIFT)
-#define SNB_READ_WM3_LATENCY()		SNB_LATENCY(SSKPD_WM3_SHIFT)
-
 /*
  * The two pipe frame counter registers are not synchronized, so
  * reading a stable value is somewhat tricky. The following code
@@ -3227,6 +3313,7 @@
 #define   MCURSOR_PIPE_A	0x00
 #define   MCURSOR_PIPE_B	(1 << 28)
 #define   MCURSOR_GAMMA_ENABLE  (1 << 26)
+#define   CURSOR_TRICKLE_FEED_DISABLE	(1 << 14)
 #define _CURABASE		(dev_priv->info->display_mmio_offset + 0x70084)
 #define _CURAPOS		(dev_priv->info->display_mmio_offset + 0x70088)
 #define   CURSOR_POS_MASK       0x007FF
@@ -3726,6 +3813,9 @@
 #define DE_PLANEA_FLIP_DONE_IVB		(1<<3)
 #define DE_PIPEA_VBLANK_IVB		(1<<0)
 
+#define DE_PIPE_VBLANK_ILK(pipe)	(1 << ((pipe * 8) + 7))
+#define DE_PIPE_VBLANK_IVB(pipe)	(1 << (pipe * 5))
+
 #define VLV_MASTER_IER			0x4400c /* Gunit master IER */
 #define   MASTER_INTERRUPT_ENABLE	(1<<31)
 
@@ -3791,6 +3881,9 @@
 #define GEN7_SQ_CHICKEN_MBCUNIT_CONFIG		0x9030
 #define  GEN7_SQ_CHICKEN_MBCUNIT_SQINTMOB	(1<<11)
 
+#define HSW_SCRATCH1				0xb038
+#define  HSW_SCRATCH1_L3_DATA_ATOMICS_DISABLE	(1<<27)
+
 #define HSW_FUSE_STRAP		0x42014
 #define  HSW_CDCLK_LIMIT	(1 << 24)
 
@@ -3888,6 +3981,7 @@
 #define  SERR_INT_TRANS_C_FIFO_UNDERRUN	(1<<6)
 #define  SERR_INT_TRANS_B_FIFO_UNDERRUN	(1<<3)
 #define  SERR_INT_TRANS_A_FIFO_UNDERRUN	(1<<0)
+#define  SERR_INT_TRANS_FIFO_UNDERRUN(pipe)	(1<<(pipe*3))
 
 /* digital port hotplug */
 #define PCH_PORT_HOTPLUG        0xc4030		/* SHOTPLUG_CTL */
@@ -4081,6 +4175,8 @@
 	 _TRANSCODER(trans, HSW_VIDEO_DIP_CTL_A, HSW_VIDEO_DIP_CTL_B)
 #define HSW_TVIDEO_DIP_AVI_DATA(trans) \
 	 _TRANSCODER(trans, HSW_VIDEO_DIP_AVI_DATA_A, HSW_VIDEO_DIP_AVI_DATA_B)
+#define HSW_TVIDEO_DIP_VS_DATA(trans) \
+	 _TRANSCODER(trans, HSW_VIDEO_DIP_VS_DATA_A, HSW_VIDEO_DIP_VS_DATA_B)
 #define HSW_TVIDEO_DIP_SPD_DATA(trans) \
 	 _TRANSCODER(trans, HSW_VIDEO_DIP_SPD_DATA_A, HSW_VIDEO_DIP_SPD_DATA_B)
 #define HSW_TVIDEO_DIP_GCP(trans) \
@@ -4088,6 +4184,13 @@
 #define HSW_TVIDEO_DIP_VSC_DATA(trans) \
 	 _TRANSCODER(trans, HSW_VIDEO_DIP_VSC_DATA_A, HSW_VIDEO_DIP_VSC_DATA_B)
 
+#define HSW_STEREO_3D_CTL_A	0x70020
+#define   S3D_ENABLE		(1<<31)
+#define HSW_STEREO_3D_CTL_B	0x71020
+
+#define HSW_STEREO_3D_CTL(trans) \
+	_TRANSCODER(trans, HSW_STEREO_3D_CTL_A, HSW_STEREO_3D_CTL_A)
+
 #define _PCH_TRANS_HTOTAL_B          0xe1000
 #define _PCH_TRANS_HBLANK_B          0xe1004
 #define _PCH_TRANS_HSYNC_B           0xe1008
@@ -4476,6 +4579,10 @@
 #define  GT_FIFO_FREE_ENTRIES			0x120008
 #define    GT_FIFO_NUM_RESERVED_ENTRIES		20
 
+#define  HSW_IDICR				0x9008
+#define    IDIHASHMSK(x)			(((x) & 0x3f) << 16)
+#define  HSW_EDRAM_PRESENT			0x120010
+
 #define GEN6_UCGCTL1				0x9400
 # define GEN6_BLBUNIT_CLOCK_GATE_DISABLE		(1 << 5)
 # define GEN6_CSUNIT_CLOCK_GATE_DISABLE			(1 << 7)
@@ -4624,6 +4731,9 @@
 #define GEN7_ROW_CHICKEN2_GT2		0xf4f4
 #define   DOP_CLOCK_GATING_DISABLE	(1<<0)
 
+#define HSW_ROW_CHICKEN3		0xe49c
+#define  HSW_ROW_CHICKEN3_L3_GLOBAL_ATOMICS_DISABLE    (1 << 6)
+
 #define G4X_AUD_VID_DID			(dev_priv->info->display_mmio_offset + 0x62020)
 #define INTEL_AUDIO_DEVCL		0x808629FB
 #define INTEL_AUDIO_DEVBLC		0x80862801
@@ -4744,8 +4854,8 @@
 #define HSW_PWR_WELL_DRIVER			0x45404 /* CTL2 */
 #define HSW_PWR_WELL_KVMR			0x45408 /* CTL3 */
 #define HSW_PWR_WELL_DEBUG			0x4540C /* CTL4 */
-#define   HSW_PWR_WELL_ENABLE			(1<<31)
-#define   HSW_PWR_WELL_STATE			(1<<30)
+#define   HSW_PWR_WELL_ENABLE_REQUEST		(1<<31)
+#define   HSW_PWR_WELL_STATE_ENABLED		(1<<30)
 #define HSW_PWR_WELL_CTL5			0x45410
 #define   HSW_PWR_WELL_ENABLE_SINGLE_STEP	(1<<31)
 #define   HSW_PWR_WELL_PWR_GATE_OVERRIDE	(1<<20)
@@ -4866,7 +4976,8 @@
 #define  SBI_SSCAUXDIV6				0x0610
 #define   SBI_SSCAUXDIV_FINALDIV2SEL(x)		((x)<<4)
 #define  SBI_DBUFF0				0x2a00
-#define   SBI_DBUFF0_ENABLE			(1<<0)
+#define  SBI_GEN0				0x1f00
+#define   SBI_GEN0_CFG_BUFFENABLE_DISABLE	(1<<0)
 
 /* LPT PIXCLK_GATE */
 #define PIXCLK_GATE			0xC6020
@@ -4932,7 +5043,14 @@
 #define  LCPLL_CLK_FREQ_450		(0<<26)
 #define  LCPLL_CD_CLOCK_DISABLE		(1<<25)
 #define  LCPLL_CD2X_CLOCK_DISABLE	(1<<23)
+#define  LCPLL_POWER_DOWN_ALLOW		(1<<22)
 #define  LCPLL_CD_SOURCE_FCLK		(1<<21)
+#define  LCPLL_CD_SOURCE_FCLK_DONE	(1<<19)
+
+#define D_COMP				(MCHBAR_MIRROR_BASE_SNB + 0x5F0C)
+#define  D_COMP_RCOMP_IN_PROGRESS	(1<<9)
+#define  D_COMP_COMP_FORCE		(1<<8)
+#define  D_COMP_COMP_DISABLE		(1<<0)
 
 /* Pipe WM_LINETIME - watermark line time */
 #define PIPE_WM_LINETIME_A		0x45270
diff --git a/drivers/gpu/drm/i915/i915_sysfs.c b/drivers/gpu/drm/i915/i915_sysfs.c
index 6875b5654c63..c8c4112de110 100644
--- a/drivers/gpu/drm/i915/i915_sysfs.c
+++ b/drivers/gpu/drm/i915/i915_sysfs.c
@@ -224,6 +224,18 @@ static ssize_t gt_cur_freq_mhz_show(struct device *kdev,
 	return snprintf(buf, PAGE_SIZE, "%d\n", ret);
 }
 
+static ssize_t vlv_rpe_freq_mhz_show(struct device *kdev,
+				     struct device_attribute *attr, char *buf)
+{
+	struct drm_minor *minor = container_of(kdev, struct drm_minor, kdev);
+	struct drm_device *dev = minor->dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	return snprintf(buf, PAGE_SIZE, "%d\n",
+			vlv_gpu_freq(dev_priv->mem_freq,
+				     dev_priv->rps.rpe_delay));
+}
+
 static ssize_t gt_max_freq_mhz_show(struct device *kdev, struct device_attribute *attr, char *buf)
 {
 	struct drm_minor *minor = container_of(kdev, struct drm_minor, kdev);
@@ -366,6 +378,7 @@ static DEVICE_ATTR(gt_cur_freq_mhz, S_IRUGO, gt_cur_freq_mhz_show, NULL);
 static DEVICE_ATTR(gt_max_freq_mhz, S_IRUGO | S_IWUSR, gt_max_freq_mhz_show, gt_max_freq_mhz_store);
 static DEVICE_ATTR(gt_min_freq_mhz, S_IRUGO | S_IWUSR, gt_min_freq_mhz_show, gt_min_freq_mhz_store);
 
+static DEVICE_ATTR(vlv_rpe_freq_mhz, S_IRUGO, vlv_rpe_freq_mhz_show, NULL);
 
 static ssize_t gt_rp_mhz_show(struct device *kdev, struct device_attribute *attr, char *buf);
 static DEVICE_ATTR(gt_RP0_freq_mhz, S_IRUGO, gt_rp_mhz_show, NULL);
@@ -409,6 +422,79 @@ static const struct attribute *gen6_attrs[] = {
 	NULL,
 };
 
+static const struct attribute *vlv_attrs[] = {
+	&dev_attr_gt_cur_freq_mhz.attr,
+	&dev_attr_gt_max_freq_mhz.attr,
+	&dev_attr_gt_min_freq_mhz.attr,
+	&dev_attr_vlv_rpe_freq_mhz.attr,
+	NULL,
+};
+
+static ssize_t error_state_read(struct file *filp, struct kobject *kobj,
+				struct bin_attribute *attr, char *buf,
+				loff_t off, size_t count)
+{
+
+	struct device *kdev = container_of(kobj, struct device, kobj);
+	struct drm_minor *minor = container_of(kdev, struct drm_minor, kdev);
+	struct drm_device *dev = minor->dev;
+	struct i915_error_state_file_priv error_priv;
+	struct drm_i915_error_state_buf error_str;
+	ssize_t ret_count = 0;
+	int ret;
+
+	memset(&error_priv, 0, sizeof(error_priv));
+
+	ret = i915_error_state_buf_init(&error_str, count, off);
+	if (ret)
+		return ret;
+
+	error_priv.dev = dev;
+	i915_error_state_get(dev, &error_priv);
+
+	ret = i915_error_state_to_str(&error_str, &error_priv);
+	if (ret)
+		goto out;
+
+	ret_count = count < error_str.bytes ? count : error_str.bytes;
+
+	memcpy(buf, error_str.buf, ret_count);
+out:
+	i915_error_state_put(&error_priv);
+	i915_error_state_buf_release(&error_str);
+
+	return ret ?: ret_count;
+}
+
+static ssize_t error_state_write(struct file *file, struct kobject *kobj,
+				 struct bin_attribute *attr, char *buf,
+				 loff_t off, size_t count)
+{
+	struct device *kdev = container_of(kobj, struct device, kobj);
+	struct drm_minor *minor = container_of(kdev, struct drm_minor, kdev);
+	struct drm_device *dev = minor->dev;
+	int ret;
+
+	DRM_DEBUG_DRIVER("Resetting error state\n");
+
+	ret = mutex_lock_interruptible(&dev->struct_mutex);
+	if (ret)
+		return ret;
+
+	i915_destroy_error_state(dev);
+	mutex_unlock(&dev->struct_mutex);
+
+	return count;
+}
+
+static struct bin_attribute error_state_attr = {
+	.attr.name = "error",
+	.attr.mode = S_IRUSR | S_IWUSR,
+	.size = 0,
+	.read = error_state_read,
+	.write = error_state_write,
+};
+
 void i915_setup_sysfs(struct drm_device *dev)
 {
 	int ret;
@@ -427,16 +513,27 @@ void i915_setup_sysfs(struct drm_device *dev)
 			DRM_ERROR("l3 parity sysfs setup failed\n");
 	}
 
-	if (INTEL_INFO(dev)->gen >= 6) {
+	ret = 0;
+	if (IS_VALLEYVIEW(dev))
+		ret = sysfs_create_files(&dev->primary->kdev.kobj, vlv_attrs);
+	else if (INTEL_INFO(dev)->gen >= 6)
 		ret = sysfs_create_files(&dev->primary->kdev.kobj, gen6_attrs);
-		if (ret)
-			DRM_ERROR("gen6 sysfs setup failed\n");
-	}
+	if (ret)
+		DRM_ERROR("RPS sysfs setup failed\n");
+
+	ret = sysfs_create_bin_file(&dev->primary->kdev.kobj,
+				    &error_state_attr);
+	if (ret)
+		DRM_ERROR("error_state sysfs setup failed\n");
 }
 
 void i915_teardown_sysfs(struct drm_device *dev)
 {
-	sysfs_remove_files(&dev->primary->kdev.kobj, gen6_attrs);
+	sysfs_remove_bin_file(&dev->primary->kdev.kobj, &error_state_attr);
+	if (IS_VALLEYVIEW(dev))
+		sysfs_remove_files(&dev->primary->kdev.kobj, vlv_attrs);
+	else
+		sysfs_remove_files(&dev->primary->kdev.kobj, gen6_attrs);
 	device_remove_bin_file(&dev->primary->kdev,  &dpf_attrs);
 #ifdef CONFIG_PM
 	sysfs_unmerge_group(&dev->primary->kdev.kobj, &rc6_attr_group);
diff --git a/drivers/gpu/drm/i915/i915_trace.h b/drivers/gpu/drm/i915/i915_trace.h
index 3db4a6817713..e2c5ee6f6194 100644
--- a/drivers/gpu/drm/i915/i915_trace.h
+++ b/drivers/gpu/drm/i915/i915_trace.h
@@ -33,47 +33,52 @@ TRACE_EVENT(i915_gem_object_create,
 	    TP_printk("obj=%p, size=%u", __entry->obj, __entry->size)
 );
 
-TRACE_EVENT(i915_gem_object_bind,
-	    TP_PROTO(struct drm_i915_gem_object *obj, bool mappable),
-	    TP_ARGS(obj, mappable),
+TRACE_EVENT(i915_vma_bind,
+	    TP_PROTO(struct i915_vma *vma, bool mappable),
+	    TP_ARGS(vma, mappable),
 
 	    TP_STRUCT__entry(
 			     __field(struct drm_i915_gem_object *, obj)
+			     __field(struct i915_address_space *, vm)
 			     __field(u32, offset)
 			     __field(u32, size)
 			     __field(bool, mappable)
 			     ),
 
 	    TP_fast_assign(
-			   __entry->obj = obj;
-			   __entry->offset = obj->gtt_space->start;
-			   __entry->size = obj->gtt_space->size;
+			   __entry->obj = vma->obj;
+			   __entry->vm = vma->vm;
+			   __entry->offset = vma->node.start;
+			   __entry->size = vma->node.size;
 			   __entry->mappable = mappable;
 			   ),
 
-	    TP_printk("obj=%p, offset=%08x size=%x%s",
+	    TP_printk("obj=%p, offset=%08x size=%x%s vm=%p",
 		      __entry->obj, __entry->offset, __entry->size,
-		      __entry->mappable ? ", mappable" : "")
+		      __entry->mappable ? ", mappable" : "",
+		      __entry->vm)
 );
 
-TRACE_EVENT(i915_gem_object_unbind,
-	    TP_PROTO(struct drm_i915_gem_object *obj),
-	    TP_ARGS(obj),
+TRACE_EVENT(i915_vma_unbind,
+	    TP_PROTO(struct i915_vma *vma),
+	    TP_ARGS(vma),
 
 	    TP_STRUCT__entry(
 			     __field(struct drm_i915_gem_object *, obj)
+			     __field(struct i915_address_space *, vm)
 			     __field(u32, offset)
 			     __field(u32, size)
 			     ),
 
 	    TP_fast_assign(
-			   __entry->obj = obj;
-			   __entry->offset = obj->gtt_space->start;
-			   __entry->size = obj->gtt_space->size;
+			   __entry->obj = vma->obj;
+			   __entry->vm = vma->vm;
+			   __entry->offset = vma->node.start;
+			   __entry->size = vma->node.size;
 			   ),
 
-	    TP_printk("obj=%p, offset=%08x size=%x",
-		      __entry->obj, __entry->offset, __entry->size)
+	    TP_printk("obj=%p, offset=%08x size=%x vm=%p",
+		      __entry->obj, __entry->offset, __entry->size, __entry->vm)
 );
 
 TRACE_EVENT(i915_gem_object_change_domain,
@@ -406,10 +411,12 @@ TRACE_EVENT(i915_flip_complete,
 	    TP_printk("plane=%d, obj=%p", __entry->plane, __entry->obj)
 );
 
-TRACE_EVENT(i915_reg_rw,
-	TP_PROTO(bool write, u32 reg, u64 val, int len),
+TRACE_EVENT_CONDITION(i915_reg_rw,
+	TP_PROTO(bool write, u32 reg, u64 val, int len, bool trace),
+
+	TP_ARGS(write, reg, val, len, trace),
 
-	TP_ARGS(write, reg, val, len),
+	TP_CONDITION(trace),
 
 	TP_STRUCT__entry(
 		__field(u64, val)
diff --git a/drivers/gpu/drm/i915/intel_acpi.c b/drivers/gpu/drm/i915/intel_acpi.c
index bcbbaea2a78e..57fe1ae32a0d 100644
--- a/drivers/gpu/drm/i915/intel_acpi.c
+++ b/drivers/gpu/drm/i915/intel_acpi.c
@@ -28,7 +28,7 @@ static const u8 intel_dsm_guid[] = {
 	0x0f, 0x13, 0x17, 0xb0, 0x1c, 0x2c
 };
 
-static int intel_dsm(acpi_handle handle, int func, int arg)
+static int intel_dsm(acpi_handle handle, int func)
 {
 	struct acpi_buffer output = { ACPI_ALLOCATE_BUFFER, NULL };
 	struct acpi_object_list input;
@@ -46,8 +46,9 @@ static int intel_dsm(acpi_handle handle, int func, int arg)
 	params[1].integer.value = INTEL_DSM_REVISION_ID;
 	params[2].type = ACPI_TYPE_INTEGER;
 	params[2].integer.value = func;
-	params[3].type = ACPI_TYPE_INTEGER;
-	params[3].integer.value = arg;
+	params[3].type = ACPI_TYPE_PACKAGE;
+	params[3].package.count = 0;
+	params[3].package.elements = NULL;
 
 	ret = acpi_evaluate_object(handle, "_DSM", &input, &output);
 	if (ret) {
@@ -151,8 +152,9 @@ static void intel_dsm_platform_mux_info(void)
 	params[1].integer.value = INTEL_DSM_REVISION_ID;
 	params[2].type = ACPI_TYPE_INTEGER;
 	params[2].integer.value = INTEL_DSM_FN_PLATFORM_MUX_INFO;
-	params[3].type = ACPI_TYPE_INTEGER;
-	params[3].integer.value = 0;
+	params[3].type = ACPI_TYPE_PACKAGE;
+	params[3].package.count = 0;
+	params[3].package.elements = NULL;
 
 	ret = acpi_evaluate_object(intel_dsm_priv.dhandle, "_DSM", &input,
 				   &output);
@@ -205,7 +207,7 @@ static bool intel_dsm_pci_probe(struct pci_dev *pdev)
 		return false;
 	}
 
-	ret = intel_dsm(dhandle, INTEL_DSM_FN_SUPPORTED_FUNCTIONS, 0);
+	ret = intel_dsm(dhandle, INTEL_DSM_FN_SUPPORTED_FUNCTIONS);
 	if (ret < 0) {
 		DRM_DEBUG_KMS("failed to get supported _DSM functions\n");
 		return false;
diff --git a/drivers/gpu/drm/i915/intel_crt.c b/drivers/gpu/drm/i915/intel_crt.c
index 3acec8c48166..ea9022ef15d5 100644
--- a/drivers/gpu/drm/i915/intel_crt.c
+++ b/drivers/gpu/drm/i915/intel_crt.c
@@ -52,15 +52,14 @@ struct intel_crt {
 	u32 adpa_reg;
 };
 
-static struct intel_crt *intel_attached_crt(struct drm_connector *connector)
+static struct intel_crt *intel_encoder_to_crt(struct intel_encoder *encoder)
 {
-	return container_of(intel_attached_encoder(connector),
-			    struct intel_crt, base);
+	return container_of(encoder, struct intel_crt, base);
 }
 
-static struct intel_crt *intel_encoder_to_crt(struct intel_encoder *encoder)
+static struct intel_crt *intel_attached_crt(struct drm_connector *connector)
 {
-	return container_of(encoder, struct intel_crt, base);
+	return intel_encoder_to_crt(intel_attached_encoder(connector));
 }
 
 static bool intel_crt_get_hw_state(struct intel_encoder *encoder,
@@ -238,17 +237,14 @@ static bool intel_crt_compute_config(struct intel_encoder *encoder,
 	return true;
 }
 
-static void intel_crt_mode_set(struct drm_encoder *encoder,
-			       struct drm_display_mode *mode,
-			       struct drm_display_mode *adjusted_mode)
+static void intel_crt_mode_set(struct intel_encoder *encoder)
 {
 
-	struct drm_device *dev = encoder->dev;
-	struct drm_crtc *crtc = encoder->crtc;
-	struct intel_crt *crt =
-		intel_encoder_to_crt(to_intel_encoder(encoder));
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
+	struct drm_device *dev = encoder->base.dev;
+	struct intel_crt *crt = intel_encoder_to_crt(encoder);
+	struct intel_crtc *crtc = to_intel_crtc(encoder->base.crtc);
 	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_display_mode *adjusted_mode = &crtc->config.adjusted_mode;
 	u32 adpa;
 
 	if (HAS_PCH_SPLIT(dev))
@@ -265,14 +261,14 @@ static void intel_crt_mode_set(struct drm_encoder *encoder,
 	if (HAS_PCH_LPT(dev))
 		; /* Those bits don't exist here */
 	else if (HAS_PCH_CPT(dev))
-		adpa |= PORT_TRANS_SEL_CPT(intel_crtc->pipe);
-	else if (intel_crtc->pipe == 0)
+		adpa |= PORT_TRANS_SEL_CPT(crtc->pipe);
+	else if (crtc->pipe == 0)
 		adpa |= ADPA_PIPE_A_SELECT;
 	else
 		adpa |= ADPA_PIPE_B_SELECT;
 
 	if (!HAS_PCH_SPLIT(dev))
-		I915_WRITE(BCLRPAT(intel_crtc->pipe), 0);
+		I915_WRITE(BCLRPAT(crtc->pipe), 0);
 
 	I915_WRITE(crt->adpa_reg, adpa);
 }
@@ -613,6 +609,10 @@ intel_crt_detect(struct drm_connector *connector, bool force)
 	enum drm_connector_status status;
 	struct intel_load_detect_pipe tmp;
 
+	DRM_DEBUG_KMS("[CONNECTOR:%d:%s] force=%d\n",
+		      connector->base.id, drm_get_connector_name(connector),
+		      force);
+
 	if (I915_HAS_HOTPLUG(dev)) {
 		/* We can not rely on the HPD pin always being correctly wired
 		 * up, for example many KVM do not pass it through, and so
@@ -688,7 +688,7 @@ static void intel_crt_reset(struct drm_connector *connector)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_crt *crt = intel_attached_crt(connector);
 
-	if (HAS_PCH_SPLIT(dev)) {
+	if (INTEL_INFO(dev)->gen >= 5) {
 		u32 adpa;
 
 		adpa = I915_READ(crt->adpa_reg);
@@ -707,10 +707,6 @@ static void intel_crt_reset(struct drm_connector *connector)
  * Routines for controlling stuff on the analog port
  */
 
-static const struct drm_encoder_helper_funcs crt_encoder_funcs = {
-	.mode_set = intel_crt_mode_set,
-};
-
 static const struct drm_connector_funcs intel_crt_connector_funcs = {
 	.reset = intel_crt_reset,
 	.dpms = intel_crt_dpms,
@@ -800,6 +796,7 @@ void intel_crt_init(struct drm_device *dev)
 		crt->adpa_reg = ADPA;
 
 	crt->base.compute_config = intel_crt_compute_config;
+	crt->base.mode_set = intel_crt_mode_set;
 	crt->base.disable = intel_disable_crt;
 	crt->base.enable = intel_enable_crt;
 	crt->base.get_config = intel_crt_get_config;
@@ -811,7 +808,6 @@ void intel_crt_init(struct drm_device *dev)
 		crt->base.get_hw_state = intel_crt_get_hw_state;
 	intel_connector->get_hw_state = intel_connector_get_hw_state;
 
-	drm_encoder_helper_add(&crt->base.base, &crt_encoder_funcs);
 	drm_connector_helper_add(connector, &intel_crt_connector_helper_funcs);
 
 	drm_sysfs_connector_add(connector);
diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c
index b042ee5c4070..63de2701b974 100644
--- a/drivers/gpu/drm/i915/intel_ddi.c
+++ b/drivers/gpu/drm/i915/intel_ddi.c
@@ -84,25 +84,17 @@ static enum port intel_ddi_get_encoder_port(struct intel_encoder *intel_encoder)
  * in either FDI or DP modes only, as HDMI connections will work with both
  * of those
  */
-static void intel_prepare_ddi_buffers(struct drm_device *dev, enum port port,
-				      bool use_fdi_mode)
+static void intel_prepare_ddi_buffers(struct drm_device *dev, enum port port)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	u32 reg;
 	int i;
-	const u32 *ddi_translations = ((use_fdi_mode) ?
+	const u32 *ddi_translations = (port == PORT_E) ?
 		hsw_ddi_translations_fdi :
-		hsw_ddi_translations_dp);
+		hsw_ddi_translations_dp;
 
-	DRM_DEBUG_DRIVER("Initializing DDI buffers for port %c in %s mode\n",
-			port_name(port),
-			use_fdi_mode ? "FDI" : "DP");
-
-	WARN((use_fdi_mode && (port != PORT_E)),
-		"Programming port %c in FDI mode, this probably will not work.\n",
-		port_name(port));
-
-	for (i=0, reg=DDI_BUF_TRANS(port); i < ARRAY_SIZE(hsw_ddi_translations_fdi); i++) {
+	for (i = 0, reg = DDI_BUF_TRANS(port);
+	     i < ARRAY_SIZE(hsw_ddi_translations_fdi); i++) {
 		I915_WRITE(reg, ddi_translations[i]);
 		reg += 4;
 	}
@@ -118,14 +110,8 @@ void intel_prepare_ddi(struct drm_device *dev)
 	if (!HAS_DDI(dev))
 		return;
 
-	for (port = PORT_A; port < PORT_E; port++)
-		intel_prepare_ddi_buffers(dev, port, false);
-
-	/* DDI E is the suggested one to work in FDI mode, so program is as such
-	 * by default. It will have to be re-programmed in case a digital DP
-	 * output will be detected on it
-	 */
-	intel_prepare_ddi_buffers(dev, PORT_E, true);
+	for (port = PORT_A; port <= PORT_E; port++)
+		intel_prepare_ddi_buffers(dev, port);
 }
 
 static const long hsw_ddi_buf_ctl_values[] = {
@@ -281,25 +267,22 @@ void hsw_fdi_link_train(struct drm_crtc *crtc)
 	DRM_ERROR("FDI link training failed!\n");
 }
 
-static void intel_ddi_mode_set(struct drm_encoder *encoder,
-			       struct drm_display_mode *mode,
-			       struct drm_display_mode *adjusted_mode)
+static void intel_ddi_mode_set(struct intel_encoder *encoder)
 {
-	struct drm_crtc *crtc = encoder->crtc;
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	struct intel_encoder *intel_encoder = to_intel_encoder(encoder);
-	int port = intel_ddi_get_encoder_port(intel_encoder);
-	int pipe = intel_crtc->pipe;
-	int type = intel_encoder->type;
+	struct intel_crtc *crtc = to_intel_crtc(encoder->base.crtc);
+	int port = intel_ddi_get_encoder_port(encoder);
+	int pipe = crtc->pipe;
+	int type = encoder->type;
+	struct drm_display_mode *adjusted_mode = &crtc->config.adjusted_mode;
 
 	DRM_DEBUG_KMS("Preparing DDI mode on port %c, pipe %c\n",
 		      port_name(port), pipe_name(pipe));
 
-	intel_crtc->eld_vld = false;
+	crtc->eld_vld = false;
 	if (type == INTEL_OUTPUT_DISPLAYPORT || type == INTEL_OUTPUT_EDP) {
-		struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
+		struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
 		struct intel_digital_port *intel_dig_port =
-			enc_to_dig_port(encoder);
+			enc_to_dig_port(&encoder->base);
 
 		intel_dp->DP = intel_dig_port->saved_port_bits |
 			       DDI_BUF_CTL_ENABLE | DDI_BUF_EMP_400MV_0DB_HSW;
@@ -307,17 +290,17 @@ static void intel_ddi_mode_set(struct drm_encoder *encoder,
 
 		if (intel_dp->has_audio) {
 			DRM_DEBUG_DRIVER("DP audio on pipe %c on DDI\n",
-					 pipe_name(intel_crtc->pipe));
+					 pipe_name(crtc->pipe));
 
 			/* write eld */
 			DRM_DEBUG_DRIVER("DP audio: write eld information\n");
-			intel_write_eld(encoder, adjusted_mode);
+			intel_write_eld(&encoder->base, adjusted_mode);
 		}
 
 		intel_dp_init_link_config(intel_dp);
 
 	} else if (type == INTEL_OUTPUT_HDMI) {
-		struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(encoder);
+		struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(&encoder->base);
 
 		if (intel_hdmi->has_audio) {
 			/* Proper support for digital audio needs a new logic
@@ -325,14 +308,14 @@ static void intel_ddi_mode_set(struct drm_encoder *encoder,
 			 * patch bombing.
 			 */
 			DRM_DEBUG_DRIVER("HDMI audio on pipe %c on DDI\n",
-					 pipe_name(intel_crtc->pipe));
+					 pipe_name(crtc->pipe));
 
 			/* write eld */
 			DRM_DEBUG_DRIVER("HDMI audio: write eld information\n");
-			intel_write_eld(encoder, adjusted_mode);
+			intel_write_eld(&encoder->base, adjusted_mode);
 		}
 
-		intel_hdmi->set_infoframes(encoder, adjusted_mode);
+		intel_hdmi->set_infoframes(&encoder->base, adjusted_mode);
 	}
 }
 
@@ -795,7 +778,7 @@ void intel_ddi_enable_transcoder_func(struct drm_crtc *crtc)
 			/* Can only use the always-on power well for eDP when
 			 * not using the panel fitter, and when not using motion
 			  * blur mitigation (which we don't support). */
-			if (intel_crtc->config.pch_pfit.size)
+			if (intel_crtc->config.pch_pfit.enabled)
 				temp |= TRANS_DDI_EDP_INPUT_A_ONOFF;
 			else
 				temp |= TRANS_DDI_EDP_INPUT_A_ON;
@@ -1118,6 +1101,7 @@ static void intel_enable_ddi(struct intel_encoder *intel_encoder)
 			intel_dp_stop_link_train(intel_dp);
 
 		ironlake_edp_backlight_on(intel_dp);
+		intel_edp_psr_enable(intel_dp);
 	}
 
 	if (intel_crtc->eld_vld && type != INTEL_OUTPUT_EDP) {
@@ -1148,16 +1132,20 @@ static void intel_disable_ddi(struct intel_encoder *intel_encoder)
 	if (type == INTEL_OUTPUT_EDP) {
 		struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
 
+		intel_edp_psr_disable(intel_dp);
 		ironlake_edp_backlight_off(intel_dp);
 	}
 }
 
 int intel_ddi_get_cdclk_freq(struct drm_i915_private *dev_priv)
 {
-	if (I915_READ(HSW_FUSE_STRAP) & HSW_CDCLK_LIMIT)
+	uint32_t lcpll = I915_READ(LCPLL_CTL);
+
+	if (lcpll & LCPLL_CD_SOURCE_FCLK)
+		return 800000;
+	else if (I915_READ(HSW_FUSE_STRAP) & HSW_CDCLK_LIMIT)
 		return 450000;
-	else if ((I915_READ(LCPLL_CTL) & LCPLL_CLK_FREQ_MASK) ==
-		 LCPLL_CLK_FREQ_450)
+	else if ((lcpll & LCPLL_CLK_FREQ_MASK) == LCPLL_CLK_FREQ_450)
 		return 450000;
 	else if (IS_ULT(dev_priv->dev))
 		return 337500;
@@ -1309,10 +1297,6 @@ static const struct drm_encoder_funcs intel_ddi_funcs = {
 	.destroy = intel_ddi_destroy,
 };
 
-static const struct drm_encoder_helper_funcs intel_ddi_helper_funcs = {
-	.mode_set = intel_ddi_mode_set,
-};
-
 void intel_ddi_init(struct drm_device *dev, enum port port)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -1337,9 +1321,9 @@ void intel_ddi_init(struct drm_device *dev, enum port port)
 
 	drm_encoder_init(dev, encoder, &intel_ddi_funcs,
 			 DRM_MODE_ENCODER_TMDS);
-	drm_encoder_helper_add(encoder, &intel_ddi_helper_funcs);
 
 	intel_encoder->compute_config = intel_ddi_compute_config;
+	intel_encoder->mode_set = intel_ddi_mode_set;
 	intel_encoder->enable = intel_enable_ddi;
 	intel_encoder->pre_enable = intel_ddi_pre_enable;
 	intel_encoder->disable = intel_disable_ddi;
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index be79f477a38f..581fb4b2f766 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -45,6 +45,15 @@ bool intel_pipe_has_type(struct drm_crtc *crtc, int type);
 static void intel_increase_pllclock(struct drm_crtc *crtc);
 static void intel_crtc_update_cursor(struct drm_crtc *crtc, bool on);
 
+static void i9xx_crtc_clock_get(struct intel_crtc *crtc,
+				struct intel_crtc_config *pipe_config);
+static void ironlake_crtc_clock_get(struct intel_crtc *crtc,
+				    struct intel_crtc_config *pipe_config);
+
+static int intel_set_mode(struct drm_crtc *crtc, struct drm_display_mode *mode,
+			  int x, int y, struct drm_framebuffer *old_fb);
+
+
 typedef struct {
 	int	min, max;
 } intel_range_t;
@@ -54,7 +63,6 @@ typedef struct {
 	int	p2_slow, p2_fast;
 } intel_p2_t;
 
-#define INTEL_P2_NUM		      2
 typedef struct intel_limit intel_limit_t;
 struct intel_limit {
 	intel_range_t   dot, vco, n, m, m1, m2, p, p1;
@@ -84,7 +92,7 @@ intel_fdi_link_freq(struct drm_device *dev)
 		return 27;
 }
 
-static const intel_limit_t intel_limits_i8xx_dvo = {
+static const intel_limit_t intel_limits_i8xx_dac = {
 	.dot = { .min = 25000, .max = 350000 },
 	.vco = { .min = 930000, .max = 1400000 },
 	.n = { .min = 3, .max = 16 },
@@ -97,6 +105,19 @@ static const intel_limit_t intel_limits_i8xx_dvo = {
 		.p2_slow = 4, .p2_fast = 2 },
 };
 
+static const intel_limit_t intel_limits_i8xx_dvo = {
+	.dot = { .min = 25000, .max = 350000 },
+	.vco = { .min = 930000, .max = 1400000 },
+	.n = { .min = 3, .max = 16 },
+	.m = { .min = 96, .max = 140 },
+	.m1 = { .min = 18, .max = 26 },
+	.m2 = { .min = 6, .max = 16 },
+	.p = { .min = 4, .max = 128 },
+	.p1 = { .min = 2, .max = 33 },
+	.p2 = { .dot_limit = 165000,
+		.p2_slow = 4, .p2_fast = 4 },
+};
+
 static const intel_limit_t intel_limits_i8xx_lvds = {
 	.dot = { .min = 25000, .max = 350000 },
 	.vco = { .min = 930000, .max = 1400000 },
@@ -405,8 +426,10 @@ static const intel_limit_t *intel_limit(struct drm_crtc *crtc, int refclk)
 	} else {
 		if (intel_pipe_has_type(crtc, INTEL_OUTPUT_LVDS))
 			limit = &intel_limits_i8xx_lvds;
-		else
+		else if (intel_pipe_has_type(crtc, INTEL_OUTPUT_DVO))
 			limit = &intel_limits_i8xx_dvo;
+		else
+			limit = &intel_limits_i8xx_dac;
 	}
 	return limit;
 }
@@ -667,7 +690,7 @@ vlv_find_best_dpll(const intel_limit_t *limit, struct drm_crtc *crtc,
 {
 	u32 p1, p2, m1, m2, vco, bestn, bestm1, bestm2, bestp1, bestp2;
 	u32 m, n, fastclk;
-	u32 updrate, minupdate, fracbits, p;
+	u32 updrate, minupdate, p;
 	unsigned long bestppm, ppm, absppm;
 	int dotclk, flag;
 
@@ -678,7 +701,6 @@ vlv_find_best_dpll(const intel_limit_t *limit, struct drm_crtc *crtc,
 	fastclk = dotclk / (2*100);
 	updrate = 0;
 	minupdate = 19200;
-	fracbits = 1;
 	n = p = p1 = p2 = m = m1 = m2 = vco = bestn = 0;
 	bestm1 = bestm2 = bestp1 = bestp2 = 0;
 
@@ -892,8 +914,8 @@ static const char *state_string(bool enabled)
 }
 
 /* Only for pre-ILK configs */
-static void assert_pll(struct drm_i915_private *dev_priv,
-		       enum pipe pipe, bool state)
+void assert_pll(struct drm_i915_private *dev_priv,
+		enum pipe pipe, bool state)
 {
 	int reg;
 	u32 val;
@@ -906,10 +928,8 @@ static void assert_pll(struct drm_i915_private *dev_priv,
 	     "PLL state assertion failure (expected %s, current %s)\n",
 	     state_string(state), state_string(cur_state));
 }
-#define assert_pll_enabled(d, p) assert_pll(d, p, true)
-#define assert_pll_disabled(d, p) assert_pll(d, p, false)
 
-static struct intel_shared_dpll *
+struct intel_shared_dpll *
 intel_crtc_to_shared_dpll(struct intel_crtc *crtc)
 {
 	struct drm_i915_private *dev_priv = crtc->base.dev->dev_private;
@@ -921,9 +941,9 @@ intel_crtc_to_shared_dpll(struct intel_crtc *crtc)
 }
 
 /* For ILK+ */
-static void assert_shared_dpll(struct drm_i915_private *dev_priv,
-			       struct intel_shared_dpll *pll,
-			       bool state)
+void assert_shared_dpll(struct drm_i915_private *dev_priv,
+			struct intel_shared_dpll *pll,
+			bool state)
 {
 	bool cur_state;
 	struct intel_dpll_hw_state hw_state;
@@ -942,8 +962,6 @@ static void assert_shared_dpll(struct drm_i915_private *dev_priv,
 	     "%s assertion failure (expected %s, current %s)\n",
 	     pll->name, state_string(state), state_string(cur_state));
 }
-#define assert_shared_dpll_enabled(d, p) assert_shared_dpll(d, p, true)
-#define assert_shared_dpll_disabled(d, p) assert_shared_dpll(d, p, false)
 
 static void assert_fdi_tx(struct drm_i915_private *dev_priv,
 			  enum pipe pipe, bool state)
@@ -1007,15 +1025,19 @@ static void assert_fdi_tx_pll_enabled(struct drm_i915_private *dev_priv,
 	WARN(!(val & FDI_TX_PLL_ENABLE), "FDI TX PLL assertion failure, should be active but is disabled\n");
 }
 
-static void assert_fdi_rx_pll_enabled(struct drm_i915_private *dev_priv,
-				      enum pipe pipe)
+void assert_fdi_rx_pll(struct drm_i915_private *dev_priv,
+		       enum pipe pipe, bool state)
 {
 	int reg;
 	u32 val;
+	bool cur_state;
 
 	reg = FDI_RX_CTL(pipe);
 	val = I915_READ(reg);
-	WARN(!(val & FDI_RX_PLL_ENABLE), "FDI RX PLL assertion failure, should be active but is disabled\n");
+	cur_state = !!(val & FDI_RX_PLL_ENABLE);
+	WARN(cur_state != state,
+	     "FDI RX PLL assertion failure (expected %s, current %s)\n",
+	     state_string(state), state_string(cur_state));
 }
 
 static void assert_panel_unlocked(struct drm_i915_private *dev_priv,
@@ -1111,7 +1133,7 @@ static void assert_planes_disabled(struct drm_i915_private *dev_priv,
 	}
 
 	/* Need to check both planes against the pipe */
-	for (i = 0; i < INTEL_INFO(dev)->num_pipes; i++) {
+	for_each_pipe(i) {
 		reg = DSPCNTR(i);
 		val = I915_READ(reg);
 		cur_pipe = (val & DISPPLANE_SEL_PIPE_MASK) >>
@@ -1301,51 +1323,92 @@ static void assert_pch_ports_disabled(struct drm_i915_private *dev_priv,
 	assert_pch_hdmi_disabled(dev_priv, pipe, PCH_HDMID);
 }
 
-/**
- * intel_enable_pll - enable a PLL
- * @dev_priv: i915 private structure
- * @pipe: pipe PLL to enable
- *
- * Enable @pipe's PLL so we can start pumping pixels from a plane.  Check to
- * make sure the PLL reg is writable first though, since the panel write
- * protect mechanism may be enabled.
- *
- * Note!  This is for pre-ILK only.
- *
- * Unfortunately needed by dvo_ns2501 since the dvo depends on it running.
- */
-static void intel_enable_pll(struct drm_i915_private *dev_priv, enum pipe pipe)
+static void vlv_enable_pll(struct intel_crtc *crtc)
 {
-	int reg;
-	u32 val;
+	struct drm_device *dev = crtc->base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	int reg = DPLL(crtc->pipe);
+	u32 dpll = crtc->config.dpll_hw_state.dpll;
 
-	assert_pipe_disabled(dev_priv, pipe);
+	assert_pipe_disabled(dev_priv, crtc->pipe);
 
 	/* No really, not for ILK+ */
-	BUG_ON(!IS_VALLEYVIEW(dev_priv->dev) && dev_priv->info->gen >= 5);
+	BUG_ON(!IS_VALLEYVIEW(dev_priv->dev));
 
 	/* PLL is protected by panel, make sure we can write it */
 	if (IS_MOBILE(dev_priv->dev) && !IS_I830(dev_priv->dev))
-		assert_panel_unlocked(dev_priv, pipe);
+		assert_panel_unlocked(dev_priv, crtc->pipe);
 
-	reg = DPLL(pipe);
-	val = I915_READ(reg);
-	val |= DPLL_VCO_ENABLE;
+	I915_WRITE(reg, dpll);
+	POSTING_READ(reg);
+	udelay(150);
+
+	if (wait_for(((I915_READ(reg) & DPLL_LOCK_VLV) == DPLL_LOCK_VLV), 1))
+		DRM_ERROR("DPLL %d failed to lock\n", crtc->pipe);
+
+	I915_WRITE(DPLL_MD(crtc->pipe), crtc->config.dpll_hw_state.dpll_md);
+	POSTING_READ(DPLL_MD(crtc->pipe));
 
 	/* We do this three times for luck */
-	I915_WRITE(reg, val);
+	I915_WRITE(reg, dpll);
 	POSTING_READ(reg);
 	udelay(150); /* wait for warmup */
-	I915_WRITE(reg, val);
+	I915_WRITE(reg, dpll);
 	POSTING_READ(reg);
 	udelay(150); /* wait for warmup */
-	I915_WRITE(reg, val);
+	I915_WRITE(reg, dpll);
+	POSTING_READ(reg);
+	udelay(150); /* wait for warmup */
+}
+
+static void i9xx_enable_pll(struct intel_crtc *crtc)
+{
+	struct drm_device *dev = crtc->base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	int reg = DPLL(crtc->pipe);
+	u32 dpll = crtc->config.dpll_hw_state.dpll;
+
+	assert_pipe_disabled(dev_priv, crtc->pipe);
+
+	/* No really, not for ILK+ */
+	BUG_ON(dev_priv->info->gen >= 5);
+
+	/* PLL is protected by panel, make sure we can write it */
+	if (IS_MOBILE(dev) && !IS_I830(dev))
+		assert_panel_unlocked(dev_priv, crtc->pipe);
+
+	I915_WRITE(reg, dpll);
+
+	/* Wait for the clocks to stabilize. */
+	POSTING_READ(reg);
+	udelay(150);
+
+	if (INTEL_INFO(dev)->gen >= 4) {
+		I915_WRITE(DPLL_MD(crtc->pipe),
+			   crtc->config.dpll_hw_state.dpll_md);
+	} else {
+		/* The pixel multiplier can only be updated once the
+		 * DPLL is enabled and the clocks are stable.
+		 *
+		 * So write it again.
+		 */
+		I915_WRITE(reg, dpll);
+	}
+
+	/* We do this three times for luck */
+	I915_WRITE(reg, dpll);
+	POSTING_READ(reg);
+	udelay(150); /* wait for warmup */
+	I915_WRITE(reg, dpll);
+	POSTING_READ(reg);
+	udelay(150); /* wait for warmup */
+	I915_WRITE(reg, dpll);
 	POSTING_READ(reg);
 	udelay(150); /* wait for warmup */
 }
 
 /**
- * intel_disable_pll - disable a PLL
+ * i9xx_disable_pll - disable a PLL
  * @dev_priv: i915 private structure
  * @pipe: pipe PLL to disable
  *
@@ -1353,11 +1416,8 @@ static void intel_enable_pll(struct drm_i915_private *dev_priv, enum pipe pipe)
  *
  * Note!  This is for pre-ILK only.
  */
-static void intel_disable_pll(struct drm_i915_private *dev_priv, enum pipe pipe)
+static void i9xx_disable_pll(struct drm_i915_private *dev_priv, enum pipe pipe)
 {
-	int reg;
-	u32 val;
-
 	/* Don't disable pipe A or pipe A PLLs if needed */
 	if (pipe == PIPE_A && (dev_priv->quirks & QUIRK_PIPEA_FORCE))
 		return;
@@ -1365,11 +1425,8 @@ static void intel_disable_pll(struct drm_i915_private *dev_priv, enum pipe pipe)
 	/* Make sure the pipe isn't still relying on us */
 	assert_pipe_disabled(dev_priv, pipe);
 
-	reg = DPLL(pipe);
-	val = I915_READ(reg);
-	val &= ~DPLL_VCO_ENABLE;
-	I915_WRITE(reg, val);
-	POSTING_READ(reg);
+	I915_WRITE(DPLL(pipe), 0);
+	POSTING_READ(DPLL(pipe));
 }
 
 void vlv_wait_port_ready(struct drm_i915_private *dev_priv, int port)
@@ -1819,7 +1876,7 @@ intel_pin_and_fence_fb_obj(struct drm_device *dev,
 	return 0;
 
 err_unpin:
-	i915_gem_object_unpin(obj);
+	i915_gem_object_unpin_from_display_plane(obj);
 err_interruptible:
 	dev_priv->mm.interruptible = true;
 	return ret;
@@ -1828,7 +1885,7 @@ err_interruptible:
 void intel_unpin_fb_obj(struct drm_i915_gem_object *obj)
 {
 	i915_gem_object_unpin_fence(obj);
-	i915_gem_object_unpin(obj);
+	i915_gem_object_unpin_from_display_plane(obj);
 }
 
 /* Computes the linear offset to the base tile and adjusts x, y. bytes per pixel
@@ -1942,16 +1999,17 @@ static int i9xx_update_plane(struct drm_crtc *crtc, struct drm_framebuffer *fb,
 		intel_crtc->dspaddr_offset = linear_offset;
 	}
 
-	DRM_DEBUG_KMS("Writing base %08X %08lX %d %d %d\n",
-		      obj->gtt_offset, linear_offset, x, y, fb->pitches[0]);
+	DRM_DEBUG_KMS("Writing base %08lX %08lX %d %d %d\n",
+		      i915_gem_obj_ggtt_offset(obj), linear_offset, x, y,
+		      fb->pitches[0]);
 	I915_WRITE(DSPSTRIDE(plane), fb->pitches[0]);
 	if (INTEL_INFO(dev)->gen >= 4) {
 		I915_MODIFY_DISPBASE(DSPSURF(plane),
-				     obj->gtt_offset + intel_crtc->dspaddr_offset);
+				     i915_gem_obj_ggtt_offset(obj) + intel_crtc->dspaddr_offset);
 		I915_WRITE(DSPTILEOFF(plane), (y << 16) | x);
 		I915_WRITE(DSPLINOFF(plane), linear_offset);
 	} else
-		I915_WRITE(DSPADDR(plane), obj->gtt_offset + linear_offset);
+		I915_WRITE(DSPADDR(plane), i915_gem_obj_ggtt_offset(obj) + linear_offset);
 	POSTING_READ(reg);
 
 	return 0;
@@ -2019,8 +2077,10 @@ static int ironlake_update_plane(struct drm_crtc *crtc,
 	else
 		dspcntr &= ~DISPPLANE_TILED;
 
-	/* must disable */
-	dspcntr |= DISPPLANE_TRICKLE_FEED_DISABLE;
+	if (IS_HASWELL(dev))
+		dspcntr &= ~DISPPLANE_TRICKLE_FEED_DISABLE;
+	else
+		dspcntr |= DISPPLANE_TRICKLE_FEED_DISABLE;
 
 	I915_WRITE(reg, dspcntr);
 
@@ -2031,11 +2091,12 @@ static int ironlake_update_plane(struct drm_crtc *crtc,
 					       fb->pitches[0]);
 	linear_offset -= intel_crtc->dspaddr_offset;
 
-	DRM_DEBUG_KMS("Writing base %08X %08lX %d %d %d\n",
-		      obj->gtt_offset, linear_offset, x, y, fb->pitches[0]);
+	DRM_DEBUG_KMS("Writing base %08lX %08lX %d %d %d\n",
+		      i915_gem_obj_ggtt_offset(obj), linear_offset, x, y,
+		      fb->pitches[0]);
 	I915_WRITE(DSPSTRIDE(plane), fb->pitches[0]);
 	I915_MODIFY_DISPBASE(DSPSURF(plane),
-			     obj->gtt_offset + intel_crtc->dspaddr_offset);
+			     i915_gem_obj_ggtt_offset(obj) + intel_crtc->dspaddr_offset);
 	if (IS_HASWELL(dev)) {
 		I915_WRITE(DSPOFFSET(plane), (y << 16) | x);
 	} else {
@@ -2183,6 +2244,20 @@ intel_pipe_set_base(struct drm_crtc *crtc, int x, int y,
 		return ret;
 	}
 
+	/* Update pipe size and adjust fitter if needed */
+	if (i915_fastboot) {
+		I915_WRITE(PIPESRC(intel_crtc->pipe),
+			   ((crtc->mode.hdisplay - 1) << 16) |
+			   (crtc->mode.vdisplay - 1));
+		if (!intel_crtc->config.pch_pfit.enabled &&
+		    (intel_pipe_has_type(crtc, INTEL_OUTPUT_LVDS) ||
+		     intel_pipe_has_type(crtc, INTEL_OUTPUT_EDP))) {
+			I915_WRITE(PF_CTL(intel_crtc->pipe), 0);
+			I915_WRITE(PF_WIN_POS(intel_crtc->pipe), 0);
+			I915_WRITE(PF_WIN_SZ(intel_crtc->pipe), 0);
+		}
+	}
+
 	ret = dev_priv->display.update_plane(crtc, fb, x, y);
 	if (ret) {
 		intel_unpin_fb_obj(to_intel_framebuffer(fb)->obj);
@@ -2203,6 +2278,7 @@ intel_pipe_set_base(struct drm_crtc *crtc, int x, int y,
 	}
 
 	intel_update_fbc(dev);
+	intel_edp_psr_update(dev);
 	mutex_unlock(&dev->struct_mutex);
 
 	intel_crtc_update_sarea_pos(crtc, x, y);
@@ -2523,7 +2599,7 @@ static void ivb_manual_fdi_link_train(struct drm_crtc *crtc)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	int pipe = intel_crtc->pipe;
-	u32 reg, temp, i;
+	u32 reg, temp, i, j;
 
 	/* Train 1: umask FDI RX Interrupt symbol_lock and bit_lock bit
 	   for train result */
@@ -2539,97 +2615,99 @@ static void ivb_manual_fdi_link_train(struct drm_crtc *crtc)
 	DRM_DEBUG_KMS("FDI_RX_IIR before link train 0x%x\n",
 		      I915_READ(FDI_RX_IIR(pipe)));
 
-	/* enable CPU FDI TX and PCH FDI RX */
-	reg = FDI_TX_CTL(pipe);
-	temp = I915_READ(reg);
-	temp &= ~FDI_DP_PORT_WIDTH_MASK;
-	temp |= FDI_DP_PORT_WIDTH(intel_crtc->config.fdi_lanes);
-	temp &= ~(FDI_LINK_TRAIN_AUTO | FDI_LINK_TRAIN_NONE_IVB);
-	temp |= FDI_LINK_TRAIN_PATTERN_1_IVB;
-	temp &= ~FDI_LINK_TRAIN_VOL_EMP_MASK;
-	temp |= FDI_LINK_TRAIN_400MV_0DB_SNB_B;
-	temp |= FDI_COMPOSITE_SYNC;
-	I915_WRITE(reg, temp | FDI_TX_ENABLE);
-
-	I915_WRITE(FDI_RX_MISC(pipe),
-		   FDI_RX_TP1_TO_TP2_48 | FDI_RX_FDI_DELAY_90);
-
-	reg = FDI_RX_CTL(pipe);
-	temp = I915_READ(reg);
-	temp &= ~FDI_LINK_TRAIN_AUTO;
-	temp &= ~FDI_LINK_TRAIN_PATTERN_MASK_CPT;
-	temp |= FDI_LINK_TRAIN_PATTERN_1_CPT;
-	temp |= FDI_COMPOSITE_SYNC;
-	I915_WRITE(reg, temp | FDI_RX_ENABLE);
+	/* Try each vswing and preemphasis setting twice before moving on */
+	for (j = 0; j < ARRAY_SIZE(snb_b_fdi_train_param) * 2; j++) {
+		/* disable first in case we need to retry */
+		reg = FDI_TX_CTL(pipe);
+		temp = I915_READ(reg);
+		temp &= ~(FDI_LINK_TRAIN_AUTO | FDI_LINK_TRAIN_NONE_IVB);
+		temp &= ~FDI_TX_ENABLE;
+		I915_WRITE(reg, temp);
 
-	POSTING_READ(reg);
-	udelay(150);
+		reg = FDI_RX_CTL(pipe);
+		temp = I915_READ(reg);
+		temp &= ~FDI_LINK_TRAIN_AUTO;
+		temp &= ~FDI_LINK_TRAIN_PATTERN_MASK_CPT;
+		temp &= ~FDI_RX_ENABLE;
+		I915_WRITE(reg, temp);
 
-	for (i = 0; i < 4; i++) {
+		/* enable CPU FDI TX and PCH FDI RX */
 		reg = FDI_TX_CTL(pipe);
 		temp = I915_READ(reg);
+		temp &= ~FDI_DP_PORT_WIDTH_MASK;
+		temp |= FDI_DP_PORT_WIDTH(intel_crtc->config.fdi_lanes);
+		temp |= FDI_LINK_TRAIN_PATTERN_1_IVB;
 		temp &= ~FDI_LINK_TRAIN_VOL_EMP_MASK;
-		temp |= snb_b_fdi_train_param[i];
-		I915_WRITE(reg, temp);
+		temp |= snb_b_fdi_train_param[j/2];
+		temp |= FDI_COMPOSITE_SYNC;
+		I915_WRITE(reg, temp | FDI_TX_ENABLE);
 
-		POSTING_READ(reg);
-		udelay(500);
+		I915_WRITE(FDI_RX_MISC(pipe),
+			   FDI_RX_TP1_TO_TP2_48 | FDI_RX_FDI_DELAY_90);
 
-		reg = FDI_RX_IIR(pipe);
+		reg = FDI_RX_CTL(pipe);
 		temp = I915_READ(reg);
-		DRM_DEBUG_KMS("FDI_RX_IIR 0x%x\n", temp);
-
-		if (temp & FDI_RX_BIT_LOCK ||
-		    (I915_READ(reg) & FDI_RX_BIT_LOCK)) {
-			I915_WRITE(reg, temp | FDI_RX_BIT_LOCK);
-			DRM_DEBUG_KMS("FDI train 1 done, level %i.\n", i);
-			break;
-		}
-	}
-	if (i == 4)
-		DRM_ERROR("FDI train 1 fail!\n");
+		temp |= FDI_LINK_TRAIN_PATTERN_1_CPT;
+		temp |= FDI_COMPOSITE_SYNC;
+		I915_WRITE(reg, temp | FDI_RX_ENABLE);
 
-	/* Train 2 */
-	reg = FDI_TX_CTL(pipe);
-	temp = I915_READ(reg);
-	temp &= ~FDI_LINK_TRAIN_NONE_IVB;
-	temp |= FDI_LINK_TRAIN_PATTERN_2_IVB;
-	temp &= ~FDI_LINK_TRAIN_VOL_EMP_MASK;
-	temp |= FDI_LINK_TRAIN_400MV_0DB_SNB_B;
-	I915_WRITE(reg, temp);
+		POSTING_READ(reg);
+		udelay(1); /* should be 0.5us */
 
-	reg = FDI_RX_CTL(pipe);
-	temp = I915_READ(reg);
-	temp &= ~FDI_LINK_TRAIN_PATTERN_MASK_CPT;
-	temp |= FDI_LINK_TRAIN_PATTERN_2_CPT;
-	I915_WRITE(reg, temp);
+		for (i = 0; i < 4; i++) {
+			reg = FDI_RX_IIR(pipe);
+			temp = I915_READ(reg);
+			DRM_DEBUG_KMS("FDI_RX_IIR 0x%x\n", temp);
 
-	POSTING_READ(reg);
-	udelay(150);
+			if (temp & FDI_RX_BIT_LOCK ||
+			    (I915_READ(reg) & FDI_RX_BIT_LOCK)) {
+				I915_WRITE(reg, temp | FDI_RX_BIT_LOCK);
+				DRM_DEBUG_KMS("FDI train 1 done, level %i.\n",
+					      i);
+				break;
+			}
+			udelay(1); /* should be 0.5us */
+		}
+		if (i == 4) {
+			DRM_DEBUG_KMS("FDI train 1 fail on vswing %d\n", j / 2);
+			continue;
+		}
 
-	for (i = 0; i < 4; i++) {
+		/* Train 2 */
 		reg = FDI_TX_CTL(pipe);
 		temp = I915_READ(reg);
-		temp &= ~FDI_LINK_TRAIN_VOL_EMP_MASK;
-		temp |= snb_b_fdi_train_param[i];
+		temp &= ~FDI_LINK_TRAIN_NONE_IVB;
+		temp |= FDI_LINK_TRAIN_PATTERN_2_IVB;
+		I915_WRITE(reg, temp);
+
+		reg = FDI_RX_CTL(pipe);
+		temp = I915_READ(reg);
+		temp &= ~FDI_LINK_TRAIN_PATTERN_MASK_CPT;
+		temp |= FDI_LINK_TRAIN_PATTERN_2_CPT;
 		I915_WRITE(reg, temp);
 
 		POSTING_READ(reg);
-		udelay(500);
+		udelay(2); /* should be 1.5us */
 
-		reg = FDI_RX_IIR(pipe);
-		temp = I915_READ(reg);
-		DRM_DEBUG_KMS("FDI_RX_IIR 0x%x\n", temp);
+		for (i = 0; i < 4; i++) {
+			reg = FDI_RX_IIR(pipe);
+			temp = I915_READ(reg);
+			DRM_DEBUG_KMS("FDI_RX_IIR 0x%x\n", temp);
 
-		if (temp & FDI_RX_SYMBOL_LOCK) {
-			I915_WRITE(reg, temp | FDI_RX_SYMBOL_LOCK);
-			DRM_DEBUG_KMS("FDI train 2 done, level %i.\n", i);
-			break;
+			if (temp & FDI_RX_SYMBOL_LOCK ||
+			    (I915_READ(reg) & FDI_RX_SYMBOL_LOCK)) {
+				I915_WRITE(reg, temp | FDI_RX_SYMBOL_LOCK);
+				DRM_DEBUG_KMS("FDI train 2 done, level %i.\n",
+					      i);
+				goto train_done;
+			}
+			udelay(2); /* should be 1.5us */
 		}
+		if (i == 4)
+			DRM_DEBUG_KMS("FDI train 2 fail on vswing %d\n", j / 2);
 	}
-	if (i == 4)
-		DRM_ERROR("FDI train 2 fail!\n");
 
+train_done:
 	DRM_DEBUG_KMS("FDI train done.\n");
 }
 
@@ -2927,15 +3005,8 @@ static void ironlake_pch_enable(struct drm_crtc *crtc)
 	/* For PCH output, training FDI link */
 	dev_priv->display.fdi_link_train(crtc);
 
-	/* XXX: pch pll's can be enabled any time before we enable the PCH
-	 * transcoder, and we actually should do this to not upset any PCH
-	 * transcoder that already use the clock when we share it.
-	 *
-	 * Note that enable_shared_dpll tries to do the right thing, but
-	 * get_shared_dpll unconditionally resets the pll - we need that to have
-	 * the right LVDS enable sequence. */
-	ironlake_enable_shared_dpll(intel_crtc);
-
+	/* We need to program the right clock selection before writing the pixel
+	 * mutliplier into the DPLL. */
 	if (HAS_PCH_CPT(dev)) {
 		u32 sel;
 
@@ -2949,6 +3020,15 @@ static void ironlake_pch_enable(struct drm_crtc *crtc)
 		I915_WRITE(PCH_DPLL_SEL, temp);
 	}
 
+	/* XXX: pch pll's can be enabled any time before we enable the PCH
+	 * transcoder, and we actually should do this to not upset any PCH
+	 * transcoder that already use the clock when we share it.
+	 *
+	 * Note that enable_shared_dpll tries to do the right thing, but
+	 * get_shared_dpll unconditionally resets the pll - we need that to have
+	 * the right LVDS enable sequence. */
+	ironlake_enable_shared_dpll(intel_crtc);
+
 	/* set transcoder timing, panel must allow it */
 	assert_panel_unlocked(dev_priv, pipe);
 	ironlake_pch_transcoder_set_timings(intel_crtc, pipe);
@@ -3031,7 +3111,7 @@ static void intel_put_shared_dpll(struct intel_crtc *crtc)
 	crtc->config.shared_dpll = DPLL_ID_PRIVATE;
 }
 
-static struct intel_shared_dpll *intel_get_shared_dpll(struct intel_crtc *crtc, u32 dpll, u32 fp)
+static struct intel_shared_dpll *intel_get_shared_dpll(struct intel_crtc *crtc)
 {
 	struct drm_i915_private *dev_priv = crtc->base.dev->dev_private;
 	struct intel_shared_dpll *pll = intel_crtc_to_shared_dpll(crtc);
@@ -3045,7 +3125,7 @@ static struct intel_shared_dpll *intel_get_shared_dpll(struct intel_crtc *crtc,
 
 	if (HAS_PCH_IBX(dev_priv->dev)) {
 		/* Ironlake PCH has a fixed PLL->PCH pipe mapping. */
-		i = crtc->pipe;
+		i = (enum intel_dpll_id) crtc->pipe;
 		pll = &dev_priv->shared_dplls[i];
 
 		DRM_DEBUG_KMS("CRTC:%d using pre-allocated %s\n",
@@ -3061,8 +3141,8 @@ static struct intel_shared_dpll *intel_get_shared_dpll(struct intel_crtc *crtc,
 		if (pll->refcount == 0)
 			continue;
 
-		if (dpll == (I915_READ(PCH_DPLL(pll->id)) & 0x7fffffff) &&
-		    fp == I915_READ(PCH_FP0(pll->id))) {
+		if (memcmp(&crtc->config.dpll_hw_state, &pll->hw_state,
+			   sizeof(pll->hw_state)) == 0) {
 			DRM_DEBUG_KMS("CRTC:%d sharing existing %s (refcount %d, ative %d)\n",
 				      crtc->base.base.id,
 				      pll->name, pll->refcount, pll->active);
@@ -3096,13 +3176,7 @@ found:
 		WARN_ON(pll->on);
 		assert_shared_dpll_disabled(dev_priv, pll);
 
-		/* Wait for the clocks to stabilize before rewriting the regs */
-		I915_WRITE(PCH_DPLL(pll->id), dpll & ~DPLL_VCO_ENABLE);
-		POSTING_READ(PCH_DPLL(pll->id));
-		udelay(150);
-
-		I915_WRITE(PCH_FP0(pll->id), fp);
-		I915_WRITE(PCH_DPLL(pll->id), dpll & ~DPLL_VCO_ENABLE);
+		pll->mode_set(dev_priv, pll);
 	}
 	pll->refcount++;
 
@@ -3129,7 +3203,7 @@ static void ironlake_pfit_enable(struct intel_crtc *crtc)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	int pipe = crtc->pipe;
 
-	if (crtc->config.pch_pfit.size) {
+	if (crtc->config.pch_pfit.enabled) {
 		/* Force use of hard-coded filter coefficients
 		 * as some pre-programmed values are broken,
 		 * e.g. x201.
@@ -3174,7 +3248,6 @@ static void ironlake_crtc_enable(struct drm_crtc *crtc)
 	struct intel_encoder *encoder;
 	int pipe = intel_crtc->pipe;
 	int plane = intel_crtc->plane;
-	u32 temp;
 
 	WARN_ON(!crtc->enabled);
 
@@ -3188,12 +3261,9 @@ static void ironlake_crtc_enable(struct drm_crtc *crtc)
 
 	intel_update_watermarks(dev);
 
-	if (intel_pipe_has_type(crtc, INTEL_OUTPUT_LVDS)) {
-		temp = I915_READ(PCH_LVDS);
-		if ((temp & LVDS_PORT_EN) == 0)
-			I915_WRITE(PCH_LVDS, temp | LVDS_PORT_EN);
-	}
-
+	for_each_encoder_on_crtc(dev, crtc, encoder)
+		if (encoder->pre_enable)
+			encoder->pre_enable(encoder);
 
 	if (intel_crtc->config.has_pch_encoder) {
 		/* Note: FDI PLL enabling _must_ be done before we enable the
@@ -3205,10 +3275,6 @@ static void ironlake_crtc_enable(struct drm_crtc *crtc)
 		assert_fdi_rx_disabled(dev_priv, pipe);
 	}
 
-	for_each_encoder_on_crtc(dev, crtc, encoder)
-		if (encoder->pre_enable)
-			encoder->pre_enable(encoder);
-
 	ironlake_pfit_enable(intel_crtc);
 
 	/*
@@ -3362,7 +3428,7 @@ static void ironlake_pfit_disable(struct intel_crtc *crtc)
 
 	/* To avoid upsetting the power well on haswell only disable the pfit if
 	 * it's in use. The hw state code will make sure we get this right. */
-	if (crtc->config.pch_pfit.size) {
+	if (crtc->config.pch_pfit.enabled) {
 		I915_WRITE(PF_CTL(pipe), 0);
 		I915_WRITE(PF_WIN_POS(pipe), 0);
 		I915_WRITE(PF_WIN_SZ(pipe), 0);
@@ -3389,7 +3455,7 @@ static void ironlake_crtc_disable(struct drm_crtc *crtc)
 	intel_crtc_wait_for_pending_flips(crtc);
 	drm_vblank_off(dev, pipe);
 
-	if (dev_priv->cfb_plane == plane)
+	if (dev_priv->fbc.plane == plane)
 		intel_disable_fbc(dev);
 
 	intel_crtc_update_cursor(crtc, false);
@@ -3462,7 +3528,7 @@ static void haswell_crtc_disable(struct drm_crtc *crtc)
 	drm_vblank_off(dev, pipe);
 
 	/* FBC must be disabled before disabling the plane on HSW. */
-	if (dev_priv->cfb_plane == plane)
+	if (dev_priv->fbc.plane == plane)
 		intel_disable_fbc(dev);
 
 	hsw_disable_ips(intel_crtc);
@@ -3593,22 +3659,16 @@ static void valleyview_crtc_enable(struct drm_crtc *crtc)
 	intel_crtc->active = true;
 	intel_update_watermarks(dev);
 
-	mutex_lock(&dev_priv->dpio_lock);
-
 	for_each_encoder_on_crtc(dev, crtc, encoder)
 		if (encoder->pre_pll_enable)
 			encoder->pre_pll_enable(encoder);
 
-	intel_enable_pll(dev_priv, pipe);
+	vlv_enable_pll(intel_crtc);
 
 	for_each_encoder_on_crtc(dev, crtc, encoder)
 		if (encoder->pre_enable)
 			encoder->pre_enable(encoder);
 
-	/* VLV wants encoder enabling _before_ the pipe is up. */
-	for_each_encoder_on_crtc(dev, crtc, encoder)
-		encoder->enable(encoder);
-
 	i9xx_pfit_enable(intel_crtc);
 
 	intel_crtc_load_lut(crtc);
@@ -3620,7 +3680,8 @@ static void valleyview_crtc_enable(struct drm_crtc *crtc)
 
 	intel_update_fbc(dev);
 
-	mutex_unlock(&dev_priv->dpio_lock);
+	for_each_encoder_on_crtc(dev, crtc, encoder)
+		encoder->enable(encoder);
 }
 
 static void i9xx_crtc_enable(struct drm_crtc *crtc)
@@ -3640,12 +3701,12 @@ static void i9xx_crtc_enable(struct drm_crtc *crtc)
 	intel_crtc->active = true;
 	intel_update_watermarks(dev);
 
-	intel_enable_pll(dev_priv, pipe);
-
 	for_each_encoder_on_crtc(dev, crtc, encoder)
 		if (encoder->pre_enable)
 			encoder->pre_enable(encoder);
 
+	i9xx_enable_pll(intel_crtc);
+
 	i9xx_pfit_enable(intel_crtc);
 
 	intel_crtc_load_lut(crtc);
@@ -3701,7 +3762,7 @@ static void i9xx_crtc_disable(struct drm_crtc *crtc)
 	intel_crtc_wait_for_pending_flips(crtc);
 	drm_vblank_off(dev, pipe);
 
-	if (dev_priv->cfb_plane == plane)
+	if (dev_priv->fbc.plane == plane)
 		intel_disable_fbc(dev);
 
 	intel_crtc_dpms_overlay(intel_crtc, false);
@@ -3717,7 +3778,7 @@ static void i9xx_crtc_disable(struct drm_crtc *crtc)
 		if (encoder->post_disable)
 			encoder->post_disable(encoder);
 
-	intel_disable_pll(dev_priv, pipe);
+	i9xx_disable_pll(dev_priv, pipe);
 
 	intel_crtc->active = false;
 	intel_update_fbc(dev);
@@ -3817,16 +3878,6 @@ static void intel_crtc_disable(struct drm_crtc *crtc)
 	}
 }
 
-void intel_modeset_disable(struct drm_device *dev)
-{
-	struct drm_crtc *crtc;
-
-	list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
-		if (crtc->enabled)
-			intel_crtc_disable(crtc);
-	}
-}
-
 void intel_encoder_destroy(struct drm_encoder *encoder)
 {
 	struct intel_encoder *intel_encoder = to_intel_encoder(encoder);
@@ -3835,10 +3886,10 @@ void intel_encoder_destroy(struct drm_encoder *encoder)
 	kfree(intel_encoder);
 }
 
-/* Simple dpms helper for encodres with just one connector, no cloning and only
+/* Simple dpms helper for encoders with just one connector, no cloning and only
  * one kind of off state. It clamps all !ON modes to fully OFF and changes the
  * state of the entire output pipe. */
-void intel_encoder_dpms(struct intel_encoder *encoder, int mode)
+static void intel_encoder_dpms(struct intel_encoder *encoder, int mode)
 {
 	if (mode == DRM_MODE_DPMS_ON) {
 		encoder->connectors_active = true;
@@ -3890,8 +3941,6 @@ static void intel_connector_check_state(struct intel_connector *connector)
  * consider. */
 void intel_connector_dpms(struct drm_connector *connector, int mode)
 {
-	struct intel_encoder *encoder = intel_attached_encoder(connector);
-
 	/* All the simple cases only support two dpms states. */
 	if (mode != DRM_MODE_DPMS_ON)
 		mode = DRM_MODE_DPMS_OFF;
@@ -3902,10 +3951,8 @@ void intel_connector_dpms(struct drm_connector *connector, int mode)
 	connector->dpms = mode;
 
 	/* Only need to change hw state when actually enabled */
-	if (encoder->base.crtc)
-		intel_encoder_dpms(encoder, mode);
-	else
-		WARN_ON(encoder->connectors_active != false);
+	if (connector->encoder)
+		intel_encoder_dpms(to_intel_encoder(connector->encoder), mode);
 
 	intel_modeset_check_state(connector->dev);
 }
@@ -4032,7 +4079,7 @@ static void hsw_compute_ips_config(struct intel_crtc *crtc,
 {
 	pipe_config->ips_enabled = i915_enable_ips &&
 				   hsw_crtc_supports_ips(crtc) &&
-				   pipe_config->pipe_bpp == 24;
+				   pipe_config->pipe_bpp <= 24;
 }
 
 static int intel_crtc_compute_config(struct intel_crtc *crtc,
@@ -4048,12 +4095,6 @@ static int intel_crtc_compute_config(struct intel_crtc *crtc,
 			return -EINVAL;
 	}
 
-	/* All interlaced capable intel hw wants timings in frames. Note though
-	 * that intel_lvds_mode_fixup does some funny tricks with the crtc
-	 * timings, so we need to be careful not to clobber these.*/
-	if (!pipe_config->timings_set)
-		drm_mode_set_crtcinfo(adjusted_mode, 0);
-
 	/* Cantiga+ cannot handle modes with a hsync front porch of 0.
 	 * WaPruneModeWithIncorrectHsyncOffset:ctg,elk,ilk,snb,ivb,vlv,hsw.
 	 */
@@ -4103,6 +4144,30 @@ static int i9xx_misc_get_display_clock_speed(struct drm_device *dev)
 	return 200000;
 }
 
+static int pnv_get_display_clock_speed(struct drm_device *dev)
+{
+	u16 gcfgc = 0;
+
+	pci_read_config_word(dev->pdev, GCFGC, &gcfgc);
+
+	switch (gcfgc & GC_DISPLAY_CLOCK_MASK) {
+	case GC_DISPLAY_CLOCK_267_MHZ_PNV:
+		return 267000;
+	case GC_DISPLAY_CLOCK_333_MHZ_PNV:
+		return 333000;
+	case GC_DISPLAY_CLOCK_444_MHZ_PNV:
+		return 444000;
+	case GC_DISPLAY_CLOCK_200_MHZ_PNV:
+		return 200000;
+	default:
+		DRM_ERROR("Unknown pnv display core clock 0x%04x\n", gcfgc);
+	case GC_DISPLAY_CLOCK_133_MHZ_PNV:
+		return 133000;
+	case GC_DISPLAY_CLOCK_167_MHZ_PNV:
+		return 167000;
+	}
+}
+
 static int i915gm_get_display_clock_speed(struct drm_device *dev)
 {
 	u16 gcfgc = 0;
@@ -4266,14 +4331,17 @@ static void i9xx_update_pll_dividers(struct intel_crtc *crtc,
 	}
 
 	I915_WRITE(FP0(pipe), fp);
+	crtc->config.dpll_hw_state.fp0 = fp;
 
 	crtc->lowfreq_avail = false;
 	if (intel_pipe_has_type(&crtc->base, INTEL_OUTPUT_LVDS) &&
 	    reduced_clock && i915_powersave) {
 		I915_WRITE(FP1(pipe), fp2);
+		crtc->config.dpll_hw_state.fp1 = fp2;
 		crtc->lowfreq_avail = true;
 	} else {
 		I915_WRITE(FP1(pipe), fp);
+		crtc->config.dpll_hw_state.fp1 = fp;
 	}
 }
 
@@ -4351,17 +4419,13 @@ static void vlv_update_pll(struct intel_crtc *crtc)
 {
 	struct drm_device *dev = crtc->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_encoder *encoder;
 	int pipe = crtc->pipe;
 	u32 dpll, mdiv;
 	u32 bestn, bestm1, bestm2, bestp1, bestp2;
-	bool is_hdmi;
 	u32 coreclk, reg_val, dpll_md;
 
 	mutex_lock(&dev_priv->dpio_lock);
 
-	is_hdmi = intel_pipe_has_type(&crtc->base, INTEL_OUTPUT_HDMI);
-
 	bestn = crtc->config.dpll.n;
 	bestm1 = crtc->config.dpll.m1;
 	bestm2 = crtc->config.dpll.m2;
@@ -4407,7 +4471,7 @@ static void vlv_update_pll(struct intel_crtc *crtc)
 	    intel_pipe_has_type(&crtc->base, INTEL_OUTPUT_ANALOG) ||
 	    intel_pipe_has_type(&crtc->base, INTEL_OUTPUT_HDMI))
 		vlv_dpio_write(dev_priv, DPIO_LPF_COEFF(pipe),
-				 0x005f0021);
+				 0x009f0003);
 	else
 		vlv_dpio_write(dev_priv, DPIO_LPF_COEFF(pipe),
 				 0x00d0000f);
@@ -4440,10 +4504,6 @@ static void vlv_update_pll(struct intel_crtc *crtc)
 
 	vlv_dpio_write(dev_priv, DPIO_PLL_CML(pipe), 0x87871000);
 
-	for_each_encoder_on_crtc(dev, &crtc->base, encoder)
-		if (encoder->pre_pll_enable)
-			encoder->pre_pll_enable(encoder);
-
 	/* Enable DPIO clock input */
 	dpll = DPLL_EXT_BUFFER_ENABLE_VLV | DPLL_REFA_CLK_ENABLE_VLV |
 		DPLL_VGA_MODE_DIS | DPLL_INTEGRATED_CLOCK_VLV;
@@ -4451,17 +4511,11 @@ static void vlv_update_pll(struct intel_crtc *crtc)
 		dpll |= DPLL_INTEGRATED_CRI_CLK_VLV;
 
 	dpll |= DPLL_VCO_ENABLE;
-	I915_WRITE(DPLL(pipe), dpll);
-	POSTING_READ(DPLL(pipe));
-	udelay(150);
-
-	if (wait_for(((I915_READ(DPLL(pipe)) & DPLL_LOCK_VLV) == DPLL_LOCK_VLV), 1))
-		DRM_ERROR("DPLL %d failed to lock\n", pipe);
+	crtc->config.dpll_hw_state.dpll = dpll;
 
 	dpll_md = (crtc->config.pixel_multiplier - 1)
 		<< DPLL_MD_UDI_MULTIPLIER_SHIFT;
-	I915_WRITE(DPLL_MD(pipe), dpll_md);
-	POSTING_READ(DPLL_MD(pipe));
+	crtc->config.dpll_hw_state.dpll_md = dpll_md;
 
 	if (crtc->config.has_dp_encoder)
 		intel_dp_set_m_n(crtc);
@@ -4475,8 +4529,6 @@ static void i9xx_update_pll(struct intel_crtc *crtc,
 {
 	struct drm_device *dev = crtc->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_encoder *encoder;
-	int pipe = crtc->pipe;
 	u32 dpll;
 	bool is_sdvo;
 	struct dpll *clock = &crtc->config.dpll;
@@ -4499,10 +4551,10 @@ static void i9xx_update_pll(struct intel_crtc *crtc,
 	}
 
 	if (is_sdvo)
-		dpll |= DPLL_DVO_HIGH_SPEED;
+		dpll |= DPLL_SDVO_HIGH_SPEED;
 
 	if (intel_pipe_has_type(&crtc->base, INTEL_OUTPUT_DISPLAYPORT))
-		dpll |= DPLL_DVO_HIGH_SPEED;
+		dpll |= DPLL_SDVO_HIGH_SPEED;
 
 	/* compute bitmask from p1 value */
 	if (IS_PINEVIEW(dev))
@@ -4538,35 +4590,16 @@ static void i9xx_update_pll(struct intel_crtc *crtc,
 		dpll |= PLL_REF_INPUT_DREFCLK;
 
 	dpll |= DPLL_VCO_ENABLE;
-	I915_WRITE(DPLL(pipe), dpll & ~DPLL_VCO_ENABLE);
-	POSTING_READ(DPLL(pipe));
-	udelay(150);
-
-	for_each_encoder_on_crtc(dev, &crtc->base, encoder)
-		if (encoder->pre_pll_enable)
-			encoder->pre_pll_enable(encoder);
-
-	if (crtc->config.has_dp_encoder)
-		intel_dp_set_m_n(crtc);
-
-	I915_WRITE(DPLL(pipe), dpll);
-
-	/* Wait for the clocks to stabilize. */
-	POSTING_READ(DPLL(pipe));
-	udelay(150);
+	crtc->config.dpll_hw_state.dpll = dpll;
 
 	if (INTEL_INFO(dev)->gen >= 4) {
 		u32 dpll_md = (crtc->config.pixel_multiplier - 1)
 			<< DPLL_MD_UDI_MULTIPLIER_SHIFT;
-		I915_WRITE(DPLL_MD(pipe), dpll_md);
-	} else {
-		/* The pixel multiplier can only be updated once the
-		 * DPLL is enabled and the clocks are stable.
-		 *
-		 * So write it again.
-		 */
-		I915_WRITE(DPLL(pipe), dpll);
+		crtc->config.dpll_hw_state.dpll_md = dpll_md;
 	}
+
+	if (crtc->config.has_dp_encoder)
+		intel_dp_set_m_n(crtc);
 }
 
 static void i8xx_update_pll(struct intel_crtc *crtc,
@@ -4575,8 +4608,6 @@ static void i8xx_update_pll(struct intel_crtc *crtc,
 {
 	struct drm_device *dev = crtc->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_encoder *encoder;
-	int pipe = crtc->pipe;
 	u32 dpll;
 	struct dpll *clock = &crtc->config.dpll;
 
@@ -4595,6 +4626,9 @@ static void i8xx_update_pll(struct intel_crtc *crtc,
 			dpll |= PLL_P2_DIVIDE_BY_4;
 	}
 
+	if (intel_pipe_has_type(&crtc->base, INTEL_OUTPUT_DVO))
+		dpll |= DPLL_DVO_2X_MODE;
+
 	if (intel_pipe_has_type(&crtc->base, INTEL_OUTPUT_LVDS) &&
 		 intel_panel_use_ssc(dev_priv) && num_connectors < 2)
 		dpll |= PLLB_REF_INPUT_SPREADSPECTRUMIN;
@@ -4602,26 +4636,7 @@ static void i8xx_update_pll(struct intel_crtc *crtc,
 		dpll |= PLL_REF_INPUT_DREFCLK;
 
 	dpll |= DPLL_VCO_ENABLE;
-	I915_WRITE(DPLL(pipe), dpll & ~DPLL_VCO_ENABLE);
-	POSTING_READ(DPLL(pipe));
-	udelay(150);
-
-	for_each_encoder_on_crtc(dev, &crtc->base, encoder)
-		if (encoder->pre_pll_enable)
-			encoder->pre_pll_enable(encoder);
-
-	I915_WRITE(DPLL(pipe), dpll);
-
-	/* Wait for the clocks to stabilize. */
-	POSTING_READ(DPLL(pipe));
-	udelay(150);
-
-	/* The pixel multiplier can only be updated once the
-	 * DPLL is enabled and the clocks are stable.
-	 *
-	 * So write it again.
-	 */
-	I915_WRITE(DPLL(pipe), dpll);
+	crtc->config.dpll_hw_state.dpll = dpll;
 }
 
 static void intel_set_pipe_timings(struct intel_crtc *intel_crtc)
@@ -4727,6 +4742,27 @@ static void intel_get_pipe_timings(struct intel_crtc *crtc,
 	pipe_config->requested_mode.hdisplay = ((tmp >> 16) & 0xffff) + 1;
 }
 
+static void intel_crtc_mode_from_pipe_config(struct intel_crtc *intel_crtc,
+					     struct intel_crtc_config *pipe_config)
+{
+	struct drm_crtc *crtc = &intel_crtc->base;
+
+	crtc->mode.hdisplay = pipe_config->adjusted_mode.crtc_hdisplay;
+	crtc->mode.htotal = pipe_config->adjusted_mode.crtc_htotal;
+	crtc->mode.hsync_start = pipe_config->adjusted_mode.crtc_hsync_start;
+	crtc->mode.hsync_end = pipe_config->adjusted_mode.crtc_hsync_end;
+
+	crtc->mode.vdisplay = pipe_config->adjusted_mode.crtc_vdisplay;
+	crtc->mode.vtotal = pipe_config->adjusted_mode.crtc_vtotal;
+	crtc->mode.vsync_start = pipe_config->adjusted_mode.crtc_vsync_start;
+	crtc->mode.vsync_end = pipe_config->adjusted_mode.crtc_vsync_end;
+
+	crtc->mode.flags = pipe_config->adjusted_mode.flags;
+
+	crtc->mode.clock = pipe_config->adjusted_mode.clock;
+	crtc->mode.flags |= pipe_config->adjusted_mode.flags;
+}
+
 static void i9xx_set_pipeconf(struct intel_crtc *intel_crtc)
 {
 	struct drm_device *dev = intel_crtc->base.dev;
@@ -4735,6 +4771,10 @@ static void i9xx_set_pipeconf(struct intel_crtc *intel_crtc)
 
 	pipeconf = 0;
 
+	if (dev_priv->quirks & QUIRK_PIPEA_FORCE &&
+	    I915_READ(PIPECONF(intel_crtc->pipe)) & PIPECONF_ENABLE)
+		pipeconf |= PIPECONF_ENABLE;
+
 	if (intel_crtc->pipe == 0 && INTEL_INFO(dev)->gen < 4) {
 		/* Enable pixel doubling when the dot clock is > 90% of the (display)
 		 * core speed.
@@ -4837,9 +4877,6 @@ static int i9xx_crtc_mode_set(struct drm_crtc *crtc,
 		return -EINVAL;
 	}
 
-	/* Ensure that the cursor is valid for the new mode before changing... */
-	intel_crtc_update_cursor(crtc, true);
-
 	if (is_lvds && dev_priv->lvds_downclock_avail) {
 		/*
 		 * Ensure we match the reduced clock's P to the target clock.
@@ -4939,7 +4976,7 @@ static bool i9xx_get_pipe_config(struct intel_crtc *crtc,
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	uint32_t tmp;
 
-	pipe_config->cpu_transcoder = crtc->pipe;
+	pipe_config->cpu_transcoder = (enum transcoder) crtc->pipe;
 	pipe_config->shared_dpll = DPLL_ID_PRIVATE;
 
 	tmp = I915_READ(PIPECONF(crtc->pipe));
@@ -4955,6 +4992,7 @@ static bool i9xx_get_pipe_config(struct intel_crtc *crtc,
 		pipe_config->pixel_multiplier =
 			((tmp & DPLL_MD_UDI_MULTIPLIER_MASK)
 			 >> DPLL_MD_UDI_MULTIPLIER_SHIFT) + 1;
+		pipe_config->dpll_hw_state.dpll_md = tmp;
 	} else if (IS_I945G(dev) || IS_I945GM(dev) || IS_G33(dev)) {
 		tmp = I915_READ(DPLL(crtc->pipe));
 		pipe_config->pixel_multiplier =
@@ -4966,6 +5004,16 @@ static bool i9xx_get_pipe_config(struct intel_crtc *crtc,
 		 * function. */
 		pipe_config->pixel_multiplier = 1;
 	}
+	pipe_config->dpll_hw_state.dpll = I915_READ(DPLL(crtc->pipe));
+	if (!IS_VALLEYVIEW(dev)) {
+		pipe_config->dpll_hw_state.fp0 = I915_READ(FP0(crtc->pipe));
+		pipe_config->dpll_hw_state.fp1 = I915_READ(FP1(crtc->pipe));
+	} else {
+		/* Mask out read-only status bits. */
+		pipe_config->dpll_hw_state.dpll &= ~(DPLL_LOCK_VLV |
+						     DPLL_PORTC_READY_MASK |
+						     DPLL_PORTB_READY_MASK);
+	}
 
 	return true;
 }
@@ -5119,74 +5167,37 @@ static void ironlake_init_pch_refclk(struct drm_device *dev)
 	BUG_ON(val != final);
 }
 
-/* Sequence to enable CLKOUT_DP for FDI usage and configure PCH FDI I/O. */
-static void lpt_init_pch_refclk(struct drm_device *dev)
+static void lpt_reset_fdi_mphy(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct drm_mode_config *mode_config = &dev->mode_config;
-	struct intel_encoder *encoder;
-	bool has_vga = false;
-	bool is_sdv = false;
-	u32 tmp;
-
-	list_for_each_entry(encoder, &mode_config->encoder_list, base.head) {
-		switch (encoder->type) {
-		case INTEL_OUTPUT_ANALOG:
-			has_vga = true;
-			break;
-		}
-	}
-
-	if (!has_vga)
-		return;
-
-	mutex_lock(&dev_priv->dpio_lock);
-
-	/* XXX: Rip out SDV support once Haswell ships for real. */
-	if (IS_HASWELL(dev) && (dev->pci_device & 0xFF00) == 0x0C00)
-		is_sdv = true;
-
-	tmp = intel_sbi_read(dev_priv, SBI_SSCCTL, SBI_ICLK);
-	tmp &= ~SBI_SSCCTL_DISABLE;
-	tmp |= SBI_SSCCTL_PATHALT;
-	intel_sbi_write(dev_priv, SBI_SSCCTL, tmp, SBI_ICLK);
-
-	udelay(24);
+	uint32_t tmp;
 
-	tmp = intel_sbi_read(dev_priv, SBI_SSCCTL, SBI_ICLK);
-	tmp &= ~SBI_SSCCTL_PATHALT;
-	intel_sbi_write(dev_priv, SBI_SSCCTL, tmp, SBI_ICLK);
+	tmp = I915_READ(SOUTH_CHICKEN2);
+	tmp |= FDI_MPHY_IOSFSB_RESET_CTL;
+	I915_WRITE(SOUTH_CHICKEN2, tmp);
 
-	if (!is_sdv) {
-		tmp = I915_READ(SOUTH_CHICKEN2);
-		tmp |= FDI_MPHY_IOSFSB_RESET_CTL;
-		I915_WRITE(SOUTH_CHICKEN2, tmp);
+	if (wait_for_atomic_us(I915_READ(SOUTH_CHICKEN2) &
+			       FDI_MPHY_IOSFSB_RESET_STATUS, 100))
+		DRM_ERROR("FDI mPHY reset assert timeout\n");
 
-		if (wait_for_atomic_us(I915_READ(SOUTH_CHICKEN2) &
-				       FDI_MPHY_IOSFSB_RESET_STATUS, 100))
-			DRM_ERROR("FDI mPHY reset assert timeout\n");
+	tmp = I915_READ(SOUTH_CHICKEN2);
+	tmp &= ~FDI_MPHY_IOSFSB_RESET_CTL;
+	I915_WRITE(SOUTH_CHICKEN2, tmp);
 
-		tmp = I915_READ(SOUTH_CHICKEN2);
-		tmp &= ~FDI_MPHY_IOSFSB_RESET_CTL;
-		I915_WRITE(SOUTH_CHICKEN2, tmp);
+	if (wait_for_atomic_us((I915_READ(SOUTH_CHICKEN2) &
+				FDI_MPHY_IOSFSB_RESET_STATUS) == 0, 100))
+		DRM_ERROR("FDI mPHY reset de-assert timeout\n");
+}
 
-		if (wait_for_atomic_us((I915_READ(SOUTH_CHICKEN2) &
-				        FDI_MPHY_IOSFSB_RESET_STATUS) == 0,
-				       100))
-			DRM_ERROR("FDI mPHY reset de-assert timeout\n");
-	}
+/* WaMPhyProgramming:hsw */
+static void lpt_program_fdi_mphy(struct drm_i915_private *dev_priv)
+{
+	uint32_t tmp;
 
 	tmp = intel_sbi_read(dev_priv, 0x8008, SBI_MPHY);
 	tmp &= ~(0xFF << 24);
 	tmp |= (0x12 << 24);
 	intel_sbi_write(dev_priv, 0x8008, tmp, SBI_MPHY);
 
-	if (is_sdv) {
-		tmp = intel_sbi_read(dev_priv, 0x800C, SBI_MPHY);
-		tmp |= 0x7FFF;
-		intel_sbi_write(dev_priv, 0x800C, tmp, SBI_MPHY);
-	}
-
 	tmp = intel_sbi_read(dev_priv, 0x2008, SBI_MPHY);
 	tmp |= (1 << 11);
 	intel_sbi_write(dev_priv, 0x2008, tmp, SBI_MPHY);
@@ -5195,24 +5206,6 @@ static void lpt_init_pch_refclk(struct drm_device *dev)
 	tmp |= (1 << 11);
 	intel_sbi_write(dev_priv, 0x2108, tmp, SBI_MPHY);
 
-	if (is_sdv) {
-		tmp = intel_sbi_read(dev_priv, 0x2038, SBI_MPHY);
-		tmp |= (0x3F << 24) | (0xF << 20) | (0xF << 16);
-		intel_sbi_write(dev_priv, 0x2038, tmp, SBI_MPHY);
-
-		tmp = intel_sbi_read(dev_priv, 0x2138, SBI_MPHY);
-		tmp |= (0x3F << 24) | (0xF << 20) | (0xF << 16);
-		intel_sbi_write(dev_priv, 0x2138, tmp, SBI_MPHY);
-
-		tmp = intel_sbi_read(dev_priv, 0x203C, SBI_MPHY);
-		tmp |= (0x3F << 8);
-		intel_sbi_write(dev_priv, 0x203C, tmp, SBI_MPHY);
-
-		tmp = intel_sbi_read(dev_priv, 0x213C, SBI_MPHY);
-		tmp |= (0x3F << 8);
-		intel_sbi_write(dev_priv, 0x213C, tmp, SBI_MPHY);
-	}
-
 	tmp = intel_sbi_read(dev_priv, 0x206C, SBI_MPHY);
 	tmp |= (1 << 24) | (1 << 21) | (1 << 18);
 	intel_sbi_write(dev_priv, 0x206C, tmp, SBI_MPHY);
@@ -5221,17 +5214,15 @@ static void lpt_init_pch_refclk(struct drm_device *dev)
 	tmp |= (1 << 24) | (1 << 21) | (1 << 18);
 	intel_sbi_write(dev_priv, 0x216C, tmp, SBI_MPHY);
 
-	if (!is_sdv) {
-		tmp = intel_sbi_read(dev_priv, 0x2080, SBI_MPHY);
-		tmp &= ~(7 << 13);
-		tmp |= (5 << 13);
-		intel_sbi_write(dev_priv, 0x2080, tmp, SBI_MPHY);
+	tmp = intel_sbi_read(dev_priv, 0x2080, SBI_MPHY);
+	tmp &= ~(7 << 13);
+	tmp |= (5 << 13);
+	intel_sbi_write(dev_priv, 0x2080, tmp, SBI_MPHY);
 
-		tmp = intel_sbi_read(dev_priv, 0x2180, SBI_MPHY);
-		tmp &= ~(7 << 13);
-		tmp |= (5 << 13);
-		intel_sbi_write(dev_priv, 0x2180, tmp, SBI_MPHY);
-	}
+	tmp = intel_sbi_read(dev_priv, 0x2180, SBI_MPHY);
+	tmp &= ~(7 << 13);
+	tmp |= (5 << 13);
+	intel_sbi_write(dev_priv, 0x2180, tmp, SBI_MPHY);
 
 	tmp = intel_sbi_read(dev_priv, 0x208C, SBI_MPHY);
 	tmp &= ~0xFF;
@@ -5253,34 +5244,120 @@ static void lpt_init_pch_refclk(struct drm_device *dev)
 	tmp |= (0x1C << 16);
 	intel_sbi_write(dev_priv, 0x2198, tmp, SBI_MPHY);
 
-	if (!is_sdv) {
-		tmp = intel_sbi_read(dev_priv, 0x20C4, SBI_MPHY);
-		tmp |= (1 << 27);
-		intel_sbi_write(dev_priv, 0x20C4, tmp, SBI_MPHY);
+	tmp = intel_sbi_read(dev_priv, 0x20C4, SBI_MPHY);
+	tmp |= (1 << 27);
+	intel_sbi_write(dev_priv, 0x20C4, tmp, SBI_MPHY);
+
+	tmp = intel_sbi_read(dev_priv, 0x21C4, SBI_MPHY);
+	tmp |= (1 << 27);
+	intel_sbi_write(dev_priv, 0x21C4, tmp, SBI_MPHY);
+
+	tmp = intel_sbi_read(dev_priv, 0x20EC, SBI_MPHY);
+	tmp &= ~(0xF << 28);
+	tmp |= (4 << 28);
+	intel_sbi_write(dev_priv, 0x20EC, tmp, SBI_MPHY);
+
+	tmp = intel_sbi_read(dev_priv, 0x21EC, SBI_MPHY);
+	tmp &= ~(0xF << 28);
+	tmp |= (4 << 28);
+	intel_sbi_write(dev_priv, 0x21EC, tmp, SBI_MPHY);
+}
+
+/* Implements 3 different sequences from BSpec chapter "Display iCLK
+ * Programming" based on the parameters passed:
+ * - Sequence to enable CLKOUT_DP
+ * - Sequence to enable CLKOUT_DP without spread
+ * - Sequence to enable CLKOUT_DP for FDI usage and configure PCH FDI I/O
+ */
+static void lpt_enable_clkout_dp(struct drm_device *dev, bool with_spread,
+				 bool with_fdi)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	uint32_t reg, tmp;
+
+	if (WARN(with_fdi && !with_spread, "FDI requires downspread\n"))
+		with_spread = true;
+	if (WARN(dev_priv->pch_id == INTEL_PCH_LPT_LP_DEVICE_ID_TYPE &&
+		 with_fdi, "LP PCH doesn't have FDI\n"))
+		with_fdi = false;
+
+	mutex_lock(&dev_priv->dpio_lock);
+
+	tmp = intel_sbi_read(dev_priv, SBI_SSCCTL, SBI_ICLK);
+	tmp &= ~SBI_SSCCTL_DISABLE;
+	tmp |= SBI_SSCCTL_PATHALT;
+	intel_sbi_write(dev_priv, SBI_SSCCTL, tmp, SBI_ICLK);
 
-		tmp = intel_sbi_read(dev_priv, 0x21C4, SBI_MPHY);
-		tmp |= (1 << 27);
-		intel_sbi_write(dev_priv, 0x21C4, tmp, SBI_MPHY);
+	udelay(24);
 
-		tmp = intel_sbi_read(dev_priv, 0x20EC, SBI_MPHY);
-		tmp &= ~(0xF << 28);
-		tmp |= (4 << 28);
-		intel_sbi_write(dev_priv, 0x20EC, tmp, SBI_MPHY);
+	if (with_spread) {
+		tmp = intel_sbi_read(dev_priv, SBI_SSCCTL, SBI_ICLK);
+		tmp &= ~SBI_SSCCTL_PATHALT;
+		intel_sbi_write(dev_priv, SBI_SSCCTL, tmp, SBI_ICLK);
 
-		tmp = intel_sbi_read(dev_priv, 0x21EC, SBI_MPHY);
-		tmp &= ~(0xF << 28);
-		tmp |= (4 << 28);
-		intel_sbi_write(dev_priv, 0x21EC, tmp, SBI_MPHY);
+		if (with_fdi) {
+			lpt_reset_fdi_mphy(dev_priv);
+			lpt_program_fdi_mphy(dev_priv);
+		}
 	}
 
-	/* ULT uses SBI_GEN0, but ULT doesn't have VGA, so we don't care. */
-	tmp = intel_sbi_read(dev_priv, SBI_DBUFF0, SBI_ICLK);
-	tmp |= SBI_DBUFF0_ENABLE;
-	intel_sbi_write(dev_priv, SBI_DBUFF0, tmp, SBI_ICLK);
+	reg = (dev_priv->pch_id == INTEL_PCH_LPT_LP_DEVICE_ID_TYPE) ?
+	       SBI_GEN0 : SBI_DBUFF0;
+	tmp = intel_sbi_read(dev_priv, reg, SBI_ICLK);
+	tmp |= SBI_GEN0_CFG_BUFFENABLE_DISABLE;
+	intel_sbi_write(dev_priv, reg, tmp, SBI_ICLK);
 
 	mutex_unlock(&dev_priv->dpio_lock);
 }
 
+/* Sequence to disable CLKOUT_DP */
+static void lpt_disable_clkout_dp(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	uint32_t reg, tmp;
+
+	mutex_lock(&dev_priv->dpio_lock);
+
+	reg = (dev_priv->pch_id == INTEL_PCH_LPT_LP_DEVICE_ID_TYPE) ?
+	       SBI_GEN0 : SBI_DBUFF0;
+	tmp = intel_sbi_read(dev_priv, reg, SBI_ICLK);
+	tmp &= ~SBI_GEN0_CFG_BUFFENABLE_DISABLE;
+	intel_sbi_write(dev_priv, reg, tmp, SBI_ICLK);
+
+	tmp = intel_sbi_read(dev_priv, SBI_SSCCTL, SBI_ICLK);
+	if (!(tmp & SBI_SSCCTL_DISABLE)) {
+		if (!(tmp & SBI_SSCCTL_PATHALT)) {
+			tmp |= SBI_SSCCTL_PATHALT;
+			intel_sbi_write(dev_priv, SBI_SSCCTL, tmp, SBI_ICLK);
+			udelay(32);
+		}
+		tmp |= SBI_SSCCTL_DISABLE;
+		intel_sbi_write(dev_priv, SBI_SSCCTL, tmp, SBI_ICLK);
+	}
+
+	mutex_unlock(&dev_priv->dpio_lock);
+}
+
+static void lpt_init_pch_refclk(struct drm_device *dev)
+{
+	struct drm_mode_config *mode_config = &dev->mode_config;
+	struct intel_encoder *encoder;
+	bool has_vga = false;
+
+	list_for_each_entry(encoder, &mode_config->encoder_list, base.head) {
+		switch (encoder->type) {
+		case INTEL_OUTPUT_ANALOG:
+			has_vga = true;
+			break;
+		}
+	}
+
+	if (has_vga)
+		lpt_enable_clkout_dp(dev, true, true);
+	else
+		lpt_disable_clkout_dp(dev);
+}
+
 /*
  * Initialize reference clocks when the driver loads
  */
@@ -5610,9 +5687,9 @@ static uint32_t ironlake_compute_dpll(struct intel_crtc *intel_crtc,
 		<< PLL_REF_SDVO_HDMI_MULTIPLIER_SHIFT;
 
 	if (is_sdvo)
-		dpll |= DPLL_DVO_HIGH_SPEED;
+		dpll |= DPLL_SDVO_HIGH_SPEED;
 	if (intel_crtc->config.has_dp_encoder)
-		dpll |= DPLL_DVO_HIGH_SPEED;
+		dpll |= DPLL_SDVO_HIGH_SPEED;
 
 	/* compute bitmask from p1 value */
 	dpll |= (1 << (intel_crtc->config.dpll.p1 - 1)) << DPLL_FPA01_P1_POST_DIV_SHIFT;
@@ -5688,9 +5765,6 @@ static int ironlake_crtc_mode_set(struct drm_crtc *crtc,
 		intel_crtc->config.dpll.p2 = clock.p2;
 	}
 
-	/* Ensure that the cursor is valid for the new mode before changing... */
-	intel_crtc_update_cursor(crtc, true);
-
 	/* CPU eDP is the only output that doesn't need a PCH PLL of its own. */
 	if (intel_crtc->config.has_pch_encoder) {
 		fp = i9xx_dpll_compute_fp(&intel_crtc->config.dpll);
@@ -5708,7 +5782,7 @@ static int ironlake_crtc_mode_set(struct drm_crtc *crtc,
 		else
 			intel_crtc->config.dpll_hw_state.fp1 = fp;
 
-		pll = intel_get_shared_dpll(intel_crtc, dpll, fp);
+		pll = intel_get_shared_dpll(intel_crtc);
 		if (pll == NULL) {
 			DRM_DEBUG_DRIVER("failed to find PLL for pipe %c\n",
 					 pipe_name(pipe));
@@ -5720,10 +5794,6 @@ static int ironlake_crtc_mode_set(struct drm_crtc *crtc,
 	if (intel_crtc->config.has_dp_encoder)
 		intel_dp_set_m_n(intel_crtc);
 
-	for_each_encoder_on_crtc(dev, crtc, encoder)
-		if (encoder->pre_pll_enable)
-			encoder->pre_pll_enable(encoder);
-
 	if (is_lvds && has_reduced_clock && i915_powersave)
 		intel_crtc->lowfreq_avail = true;
 	else
@@ -5732,23 +5802,6 @@ static int ironlake_crtc_mode_set(struct drm_crtc *crtc,
 	if (intel_crtc->config.has_pch_encoder) {
 		pll = intel_crtc_to_shared_dpll(intel_crtc);
 
-		I915_WRITE(PCH_DPLL(pll->id), dpll);
-
-		/* Wait for the clocks to stabilize. */
-		POSTING_READ(PCH_DPLL(pll->id));
-		udelay(150);
-
-		/* The pixel multiplier can only be updated once the
-		 * DPLL is enabled and the clocks are stable.
-		 *
-		 * So write it again.
-		 */
-		I915_WRITE(PCH_DPLL(pll->id), dpll);
-
-		if (has_reduced_clock)
-			I915_WRITE(PCH_FP1(pll->id), fp2);
-		else
-			I915_WRITE(PCH_FP1(pll->id), fp);
 	}
 
 	intel_set_pipe_timings(intel_crtc);
@@ -5800,6 +5853,7 @@ static void ironlake_get_pfit_config(struct intel_crtc *crtc,
 	tmp = I915_READ(PF_CTL(crtc->pipe));
 
 	if (tmp & PF_ENABLE) {
+		pipe_config->pch_pfit.enabled = true;
 		pipe_config->pch_pfit.pos = I915_READ(PF_WIN_POS(crtc->pipe));
 		pipe_config->pch_pfit.size = I915_READ(PF_WIN_SZ(crtc->pipe));
 
@@ -5820,7 +5874,7 @@ static bool ironlake_get_pipe_config(struct intel_crtc *crtc,
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	uint32_t tmp;
 
-	pipe_config->cpu_transcoder = crtc->pipe;
+	pipe_config->cpu_transcoder = (enum transcoder) crtc->pipe;
 	pipe_config->shared_dpll = DPLL_ID_PRIVATE;
 
 	tmp = I915_READ(PIPECONF(crtc->pipe));
@@ -5838,12 +5892,9 @@ static bool ironlake_get_pipe_config(struct intel_crtc *crtc,
 
 		ironlake_get_fdi_m_n_config(crtc, pipe_config);
 
-		/* XXX: Can't properly read out the pch dpll pixel multiplier
-		 * since we don't have state tracking for pch clocks yet. */
-		pipe_config->pixel_multiplier = 1;
-
 		if (HAS_PCH_IBX(dev_priv->dev)) {
-			pipe_config->shared_dpll = crtc->pipe;
+			pipe_config->shared_dpll =
+				(enum intel_dpll_id) crtc->pipe;
 		} else {
 			tmp = I915_READ(PCH_DPLL_SEL);
 			if (tmp & TRANS_DPLLB_SEL(crtc->pipe))
@@ -5856,6 +5907,11 @@ static bool ironlake_get_pipe_config(struct intel_crtc *crtc,
 
 		WARN_ON(!pll->get_hw_state(dev_priv, pll,
 					   &pipe_config->dpll_hw_state));
+
+		tmp = pipe_config->dpll_hw_state.dpll;
+		pipe_config->pixel_multiplier =
+			((tmp & PLL_REF_SDVO_HDMI_MULTIPLIER_MASK)
+			 >> PLL_REF_SDVO_HDMI_MULTIPLIER_SHIFT) + 1;
 	} else {
 		pipe_config->pixel_multiplier = 1;
 	}
@@ -5867,6 +5923,305 @@ static bool ironlake_get_pipe_config(struct intel_crtc *crtc,
 	return true;
 }
 
+static void assert_can_disable_lcpll(struct drm_i915_private *dev_priv)
+{
+	struct drm_device *dev = dev_priv->dev;
+	struct intel_ddi_plls *plls = &dev_priv->ddi_plls;
+	struct intel_crtc *crtc;
+	unsigned long irqflags;
+	uint32_t val;
+
+	list_for_each_entry(crtc, &dev->mode_config.crtc_list, base.head)
+		WARN(crtc->base.enabled, "CRTC for pipe %c enabled\n",
+		     pipe_name(crtc->pipe));
+
+	WARN(I915_READ(HSW_PWR_WELL_DRIVER), "Power well on\n");
+	WARN(plls->spll_refcount, "SPLL enabled\n");
+	WARN(plls->wrpll1_refcount, "WRPLL1 enabled\n");
+	WARN(plls->wrpll2_refcount, "WRPLL2 enabled\n");
+	WARN(I915_READ(PCH_PP_STATUS) & PP_ON, "Panel power on\n");
+	WARN(I915_READ(BLC_PWM_CPU_CTL2) & BLM_PWM_ENABLE,
+	     "CPU PWM1 enabled\n");
+	WARN(I915_READ(HSW_BLC_PWM2_CTL) & BLM_PWM_ENABLE,
+	     "CPU PWM2 enabled\n");
+	WARN(I915_READ(BLC_PWM_PCH_CTL1) & BLM_PCH_PWM_ENABLE,
+	     "PCH PWM1 enabled\n");
+	WARN(I915_READ(UTIL_PIN_CTL) & UTIL_PIN_ENABLE,
+	     "Utility pin enabled\n");
+	WARN(I915_READ(PCH_GTC_CTL) & PCH_GTC_ENABLE, "PCH GTC enabled\n");
+
+	spin_lock_irqsave(&dev_priv->irq_lock, irqflags);
+	val = I915_READ(DEIMR);
+	WARN((val & ~DE_PCH_EVENT_IVB) != val,
+	     "Unexpected DEIMR bits enabled: 0x%x\n", val);
+	val = I915_READ(SDEIMR);
+	WARN((val | SDE_HOTPLUG_MASK_CPT) != 0xffffffff,
+	     "Unexpected SDEIMR bits enabled: 0x%x\n", val);
+	spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags);
+}
+
+/*
+ * This function implements pieces of two sequences from BSpec:
+ * - Sequence for display software to disable LCPLL
+ * - Sequence for display software to allow package C8+
+ * The steps implemented here are just the steps that actually touch the LCPLL
+ * register. Callers should take care of disabling all the display engine
+ * functions, doing the mode unset, fixing interrupts, etc.
+ */
+void hsw_disable_lcpll(struct drm_i915_private *dev_priv,
+		       bool switch_to_fclk, bool allow_power_down)
+{
+	uint32_t val;
+
+	assert_can_disable_lcpll(dev_priv);
+
+	val = I915_READ(LCPLL_CTL);
+
+	if (switch_to_fclk) {
+		val |= LCPLL_CD_SOURCE_FCLK;
+		I915_WRITE(LCPLL_CTL, val);
+
+		if (wait_for_atomic_us(I915_READ(LCPLL_CTL) &
+				       LCPLL_CD_SOURCE_FCLK_DONE, 1))
+			DRM_ERROR("Switching to FCLK failed\n");
+
+		val = I915_READ(LCPLL_CTL);
+	}
+
+	val |= LCPLL_PLL_DISABLE;
+	I915_WRITE(LCPLL_CTL, val);
+	POSTING_READ(LCPLL_CTL);
+
+	if (wait_for((I915_READ(LCPLL_CTL) & LCPLL_PLL_LOCK) == 0, 1))
+		DRM_ERROR("LCPLL still locked\n");
+
+	val = I915_READ(D_COMP);
+	val |= D_COMP_COMP_DISABLE;
+	I915_WRITE(D_COMP, val);
+	POSTING_READ(D_COMP);
+	ndelay(100);
+
+	if (wait_for((I915_READ(D_COMP) & D_COMP_RCOMP_IN_PROGRESS) == 0, 1))
+		DRM_ERROR("D_COMP RCOMP still in progress\n");
+
+	if (allow_power_down) {
+		val = I915_READ(LCPLL_CTL);
+		val |= LCPLL_POWER_DOWN_ALLOW;
+		I915_WRITE(LCPLL_CTL, val);
+		POSTING_READ(LCPLL_CTL);
+	}
+}
+
+/*
+ * Fully restores LCPLL, disallowing power down and switching back to LCPLL
+ * source.
+ */
+void hsw_restore_lcpll(struct drm_i915_private *dev_priv)
+{
+	uint32_t val;
+
+	val = I915_READ(LCPLL_CTL);
+
+	if ((val & (LCPLL_PLL_LOCK | LCPLL_PLL_DISABLE | LCPLL_CD_SOURCE_FCLK |
+		    LCPLL_POWER_DOWN_ALLOW)) == LCPLL_PLL_LOCK)
+		return;
+
+	/* Make sure we're not on PC8 state before disabling PC8, otherwise
+	 * we'll hang the machine! */
+	dev_priv->uncore.funcs.force_wake_get(dev_priv);
+
+	if (val & LCPLL_POWER_DOWN_ALLOW) {
+		val &= ~LCPLL_POWER_DOWN_ALLOW;
+		I915_WRITE(LCPLL_CTL, val);
+		POSTING_READ(LCPLL_CTL);
+	}
+
+	val = I915_READ(D_COMP);
+	val |= D_COMP_COMP_FORCE;
+	val &= ~D_COMP_COMP_DISABLE;
+	I915_WRITE(D_COMP, val);
+	POSTING_READ(D_COMP);
+
+	val = I915_READ(LCPLL_CTL);
+	val &= ~LCPLL_PLL_DISABLE;
+	I915_WRITE(LCPLL_CTL, val);
+
+	if (wait_for(I915_READ(LCPLL_CTL) & LCPLL_PLL_LOCK, 5))
+		DRM_ERROR("LCPLL not locked yet\n");
+
+	if (val & LCPLL_CD_SOURCE_FCLK) {
+		val = I915_READ(LCPLL_CTL);
+		val &= ~LCPLL_CD_SOURCE_FCLK;
+		I915_WRITE(LCPLL_CTL, val);
+
+		if (wait_for_atomic_us((I915_READ(LCPLL_CTL) &
+					LCPLL_CD_SOURCE_FCLK_DONE) == 0, 1))
+			DRM_ERROR("Switching back to LCPLL failed\n");
+	}
+
+	dev_priv->uncore.funcs.force_wake_put(dev_priv);
+}
+
+void hsw_enable_pc8_work(struct work_struct *__work)
+{
+	struct drm_i915_private *dev_priv =
+		container_of(to_delayed_work(__work), struct drm_i915_private,
+			     pc8.enable_work);
+	struct drm_device *dev = dev_priv->dev;
+	uint32_t val;
+
+	if (dev_priv->pc8.enabled)
+		return;
+
+	DRM_DEBUG_KMS("Enabling package C8+\n");
+
+	dev_priv->pc8.enabled = true;
+
+	if (dev_priv->pch_id == INTEL_PCH_LPT_LP_DEVICE_ID_TYPE) {
+		val = I915_READ(SOUTH_DSPCLK_GATE_D);
+		val &= ~PCH_LP_PARTITION_LEVEL_DISABLE;
+		I915_WRITE(SOUTH_DSPCLK_GATE_D, val);
+	}
+
+	lpt_disable_clkout_dp(dev);
+	hsw_pc8_disable_interrupts(dev);
+	hsw_disable_lcpll(dev_priv, true, true);
+}
+
+static void __hsw_enable_package_c8(struct drm_i915_private *dev_priv)
+{
+	WARN_ON(!mutex_is_locked(&dev_priv->pc8.lock));
+	WARN(dev_priv->pc8.disable_count < 1,
+	     "pc8.disable_count: %d\n", dev_priv->pc8.disable_count);
+
+	dev_priv->pc8.disable_count--;
+	if (dev_priv->pc8.disable_count != 0)
+		return;
+
+	schedule_delayed_work(&dev_priv->pc8.enable_work,
+			      msecs_to_jiffies(i915_pc8_timeout));
+}
+
+static void __hsw_disable_package_c8(struct drm_i915_private *dev_priv)
+{
+	struct drm_device *dev = dev_priv->dev;
+	uint32_t val;
+
+	WARN_ON(!mutex_is_locked(&dev_priv->pc8.lock));
+	WARN(dev_priv->pc8.disable_count < 0,
+	     "pc8.disable_count: %d\n", dev_priv->pc8.disable_count);
+
+	dev_priv->pc8.disable_count++;
+	if (dev_priv->pc8.disable_count != 1)
+		return;
+
+	cancel_delayed_work_sync(&dev_priv->pc8.enable_work);
+	if (!dev_priv->pc8.enabled)
+		return;
+
+	DRM_DEBUG_KMS("Disabling package C8+\n");
+
+	hsw_restore_lcpll(dev_priv);
+	hsw_pc8_restore_interrupts(dev);
+	lpt_init_pch_refclk(dev);
+
+	if (dev_priv->pch_id == INTEL_PCH_LPT_LP_DEVICE_ID_TYPE) {
+		val = I915_READ(SOUTH_DSPCLK_GATE_D);
+		val |= PCH_LP_PARTITION_LEVEL_DISABLE;
+		I915_WRITE(SOUTH_DSPCLK_GATE_D, val);
+	}
+
+	intel_prepare_ddi(dev);
+	i915_gem_init_swizzling(dev);
+	mutex_lock(&dev_priv->rps.hw_lock);
+	gen6_update_ring_freq(dev);
+	mutex_unlock(&dev_priv->rps.hw_lock);
+	dev_priv->pc8.enabled = false;
+}
+
+void hsw_enable_package_c8(struct drm_i915_private *dev_priv)
+{
+	mutex_lock(&dev_priv->pc8.lock);
+	__hsw_enable_package_c8(dev_priv);
+	mutex_unlock(&dev_priv->pc8.lock);
+}
+
+void hsw_disable_package_c8(struct drm_i915_private *dev_priv)
+{
+	mutex_lock(&dev_priv->pc8.lock);
+	__hsw_disable_package_c8(dev_priv);
+	mutex_unlock(&dev_priv->pc8.lock);
+}
+
+static bool hsw_can_enable_package_c8(struct drm_i915_private *dev_priv)
+{
+	struct drm_device *dev = dev_priv->dev;
+	struct intel_crtc *crtc;
+	uint32_t val;
+
+	list_for_each_entry(crtc, &dev->mode_config.crtc_list, base.head)
+		if (crtc->base.enabled)
+			return false;
+
+	/* This case is still possible since we have the i915.disable_power_well
+	 * parameter and also the KVMr or something else might be requesting the
+	 * power well. */
+	val = I915_READ(HSW_PWR_WELL_DRIVER);
+	if (val != 0) {
+		DRM_DEBUG_KMS("Not enabling PC8: power well on\n");
+		return false;
+	}
+
+	return true;
+}
+
+/* Since we're called from modeset_global_resources there's no way to
+ * symmetrically increase and decrease the refcount, so we use
+ * dev_priv->pc8.requirements_met to track whether we already have the refcount
+ * or not.
+ */
+static void hsw_update_package_c8(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	bool allow;
+
+	if (!i915_enable_pc8)
+		return;
+
+	mutex_lock(&dev_priv->pc8.lock);
+
+	allow = hsw_can_enable_package_c8(dev_priv);
+
+	if (allow == dev_priv->pc8.requirements_met)
+		goto done;
+
+	dev_priv->pc8.requirements_met = allow;
+
+	if (allow)
+		__hsw_enable_package_c8(dev_priv);
+	else
+		__hsw_disable_package_c8(dev_priv);
+
+done:
+	mutex_unlock(&dev_priv->pc8.lock);
+}
+
+static void hsw_package_c8_gpu_idle(struct drm_i915_private *dev_priv)
+{
+	if (!dev_priv->pc8.gpu_idle) {
+		dev_priv->pc8.gpu_idle = true;
+		hsw_enable_package_c8(dev_priv);
+	}
+}
+
+static void hsw_package_c8_gpu_busy(struct drm_i915_private *dev_priv)
+{
+	if (dev_priv->pc8.gpu_idle) {
+		dev_priv->pc8.gpu_idle = false;
+		hsw_disable_package_c8(dev_priv);
+	}
+}
+
 static void haswell_modeset_global_resources(struct drm_device *dev)
 {
 	bool enable = false;
@@ -5876,12 +6231,14 @@ static void haswell_modeset_global_resources(struct drm_device *dev)
 		if (!crtc->base.enabled)
 			continue;
 
-		if (crtc->pipe != PIPE_A || crtc->config.pch_pfit.size ||
+		if (crtc->pipe != PIPE_A || crtc->config.pch_pfit.enabled ||
 		    crtc->config.cpu_transcoder != TRANSCODER_EDP)
 			enable = true;
 	}
 
 	intel_set_power_well(dev, enable);
+
+	hsw_update_package_c8(dev);
 }
 
 static int haswell_crtc_mode_set(struct drm_crtc *crtc,
@@ -5897,9 +6254,6 @@ static int haswell_crtc_mode_set(struct drm_crtc *crtc,
 	if (!intel_ddi_pll_mode_set(crtc))
 		return -EINVAL;
 
-	/* Ensure that the cursor is valid for the new mode before changing... */
-	intel_crtc_update_cursor(crtc, true);
-
 	if (intel_crtc->config.has_dp_encoder)
 		intel_dp_set_m_n(intel_crtc);
 
@@ -5935,7 +6289,7 @@ static bool haswell_get_pipe_config(struct intel_crtc *crtc,
 	enum intel_display_power_domain pfit_domain;
 	uint32_t tmp;
 
-	pipe_config->cpu_transcoder = crtc->pipe;
+	pipe_config->cpu_transcoder = (enum transcoder) crtc->pipe;
 	pipe_config->shared_dpll = DPLL_ID_PRIVATE;
 
 	tmp = I915_READ(TRANS_DDI_FUNC_CTL(TRANSCODER_EDP));
@@ -6005,11 +6359,8 @@ static int intel_crtc_mode_set(struct drm_crtc *crtc,
 {
 	struct drm_device *dev = crtc->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct drm_encoder_helper_funcs *encoder_funcs;
 	struct intel_encoder *encoder;
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	struct drm_display_mode *adjusted_mode =
-		&intel_crtc->config.adjusted_mode;
 	struct drm_display_mode *mode = &intel_crtc->config.requested_mode;
 	int pipe = intel_crtc->pipe;
 	int ret;
@@ -6028,12 +6379,7 @@ static int intel_crtc_mode_set(struct drm_crtc *crtc,
 			encoder->base.base.id,
 			drm_get_encoder_name(&encoder->base),
 			mode->base.id, mode->name);
-		if (encoder->mode_set) {
-			encoder->mode_set(encoder);
-		} else {
-			encoder_funcs = encoder->base.helper_private;
-			encoder_funcs->mode_set(&encoder->base, mode, adjusted_mode);
-		}
+		encoder->mode_set(encoder);
 	}
 
 	return 0;
@@ -6140,15 +6486,15 @@ static void haswell_write_eld(struct drm_connector *connector,
 
 	/* Set ELD valid state */
 	tmp = I915_READ(aud_cntrl_st2);
-	DRM_DEBUG_DRIVER("HDMI audio: pin eld vld status=0x%8x\n", tmp);
+	DRM_DEBUG_DRIVER("HDMI audio: pin eld vld status=0x%08x\n", tmp);
 	tmp |= (AUDIO_ELD_VALID_A << (pipe * 4));
 	I915_WRITE(aud_cntrl_st2, tmp);
 	tmp = I915_READ(aud_cntrl_st2);
-	DRM_DEBUG_DRIVER("HDMI audio: eld vld status=0x%8x\n", tmp);
+	DRM_DEBUG_DRIVER("HDMI audio: eld vld status=0x%08x\n", tmp);
 
 	/* Enable HDMI mode */
 	tmp = I915_READ(aud_config);
-	DRM_DEBUG_DRIVER("HDMI audio: audio conf: 0x%8x\n", tmp);
+	DRM_DEBUG_DRIVER("HDMI audio: audio conf: 0x%08x\n", tmp);
 	/* clear N_programing_enable and N_value_index */
 	tmp &= ~(AUD_CONFIG_N_VALUE_INDEX | AUD_CONFIG_N_PROG_ENABLE);
 	I915_WRITE(aud_config, tmp);
@@ -6410,8 +6756,10 @@ static void ivb_update_cursor(struct drm_crtc *crtc, u32 base)
 			cntl &= ~(CURSOR_MODE | MCURSOR_GAMMA_ENABLE);
 			cntl |= CURSOR_MODE_DISABLE;
 		}
-		if (IS_HASWELL(dev))
+		if (IS_HASWELL(dev)) {
 			cntl |= CURSOR_PIPE_CSC_ENABLE;
+			cntl &= ~CURSOR_TRICKLE_FEED_DISABLE;
+		}
 		I915_WRITE(CURCNTR_IVB(pipe), cntl);
 
 		intel_crtc->cursor_visible = visible;
@@ -6548,7 +6896,7 @@ static int intel_crtc_cursor_set(struct drm_crtc *crtc,
 			goto fail_unpin;
 		}
 
-		addr = obj->gtt_offset;
+		addr = i915_gem_obj_ggtt_offset(obj);
 	} else {
 		int align = IS_I830(dev) ? 16 * 1024 : 256;
 		ret = i915_gem_attach_phys_object(dev, obj,
@@ -6570,7 +6918,7 @@ static int intel_crtc_cursor_set(struct drm_crtc *crtc,
 			if (intel_crtc->cursor_bo != obj)
 				i915_gem_detach_phys_object(dev, intel_crtc->cursor_bo);
 		} else
-			i915_gem_object_unpin(intel_crtc->cursor_bo);
+			i915_gem_object_unpin_from_display_plane(intel_crtc->cursor_bo);
 		drm_gem_object_unreference(&intel_crtc->cursor_bo->base);
 	}
 
@@ -6581,11 +6929,12 @@ static int intel_crtc_cursor_set(struct drm_crtc *crtc,
 	intel_crtc->cursor_width = width;
 	intel_crtc->cursor_height = height;
 
-	intel_crtc_update_cursor(crtc, intel_crtc->cursor_bo != NULL);
+	if (intel_crtc->active)
+		intel_crtc_update_cursor(crtc, intel_crtc->cursor_bo != NULL);
 
 	return 0;
 fail_unpin:
-	i915_gem_object_unpin(obj);
+	i915_gem_object_unpin_from_display_plane(obj);
 fail_locked:
 	mutex_unlock(&dev->struct_mutex);
 fail:
@@ -6600,7 +6949,8 @@ static int intel_crtc_cursor_move(struct drm_crtc *crtc, int x, int y)
 	intel_crtc->cursor_x = x;
 	intel_crtc->cursor_y = y;
 
-	intel_crtc_update_cursor(crtc, intel_crtc->cursor_bo != NULL);
+	if (intel_crtc->active)
+		intel_crtc_update_cursor(crtc, intel_crtc->cursor_bo != NULL);
 
 	return 0;
 }
@@ -6875,11 +7225,12 @@ void intel_release_load_detect_pipe(struct drm_connector *connector,
 }
 
 /* Returns the clock of the currently programmed mode of the given pipe. */
-static int intel_crtc_clock_get(struct drm_device *dev, struct drm_crtc *crtc)
+static void i9xx_crtc_clock_get(struct intel_crtc *crtc,
+				struct intel_crtc_config *pipe_config)
 {
+	struct drm_device *dev = crtc->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	int pipe = intel_crtc->pipe;
+	int pipe = pipe_config->cpu_transcoder;
 	u32 dpll = I915_READ(DPLL(pipe));
 	u32 fp;
 	intel_clock_t clock;
@@ -6918,7 +7269,8 @@ static int intel_crtc_clock_get(struct drm_device *dev, struct drm_crtc *crtc)
 		default:
 			DRM_DEBUG_KMS("Unknown DPLL mode %08x in programmed "
 				  "mode\n", (int)(dpll & DPLL_MODE_MASK));
-			return 0;
+			pipe_config->adjusted_mode.clock = 0;
+			return;
 		}
 
 		if (IS_PINEVIEW(dev))
@@ -6955,12 +7307,54 @@ static int intel_crtc_clock_get(struct drm_device *dev, struct drm_crtc *crtc)
 		}
 	}
 
-	/* XXX: It would be nice to validate the clocks, but we can't reuse
-	 * i830PllIsValid() because it relies on the xf86_config connector
-	 * configuration being accurate, which it isn't necessarily.
+	pipe_config->adjusted_mode.clock = clock.dot;
+}
+
+static void ironlake_crtc_clock_get(struct intel_crtc *crtc,
+				    struct intel_crtc_config *pipe_config)
+{
+	struct drm_device *dev = crtc->base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	enum transcoder cpu_transcoder = pipe_config->cpu_transcoder;
+	int link_freq, repeat;
+	u64 clock;
+	u32 link_m, link_n;
+
+	repeat = pipe_config->pixel_multiplier;
+
+	/*
+	 * The calculation for the data clock is:
+	 * pixel_clock = ((m/n)*(link_clock * nr_lanes * repeat))/bpp
+	 * But we want to avoid losing precison if possible, so:
+	 * pixel_clock = ((m * link_clock * nr_lanes * repeat)/(n*bpp))
+	 *
+	 * and the link clock is simpler:
+	 * link_clock = (m * link_clock * repeat) / n
+	 */
+
+	/*
+	 * We need to get the FDI or DP link clock here to derive
+	 * the M/N dividers.
+	 *
+	 * For FDI, we read it from the BIOS or use a fixed 2.7GHz.
+	 * For DP, it's either 1.62GHz or 2.7GHz.
+	 * We do our calculations in 10*MHz since we don't need much precison.
 	 */
+	if (pipe_config->has_pch_encoder)
+		link_freq = intel_fdi_link_freq(dev) * 10000;
+	else
+		link_freq = pipe_config->port_clock;
 
-	return clock.dot;
+	link_m = I915_READ(PIPE_LINK_M1(cpu_transcoder));
+	link_n = I915_READ(PIPE_LINK_N1(cpu_transcoder));
+
+	if (!link_m || !link_n)
+		return;
+
+	clock = ((u64)link_m * (u64)link_freq * (u64)repeat);
+	do_div(clock, link_n);
+
+	pipe_config->adjusted_mode.clock = clock;
 }
 
 /** Returns the currently programmed mode of the given pipe. */
@@ -6971,6 +7365,7 @@ struct drm_display_mode *intel_crtc_mode_get(struct drm_device *dev,
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	enum transcoder cpu_transcoder = intel_crtc->config.cpu_transcoder;
 	struct drm_display_mode *mode;
+	struct intel_crtc_config pipe_config;
 	int htot = I915_READ(HTOTAL(cpu_transcoder));
 	int hsync = I915_READ(HSYNC(cpu_transcoder));
 	int vtot = I915_READ(VTOTAL(cpu_transcoder));
@@ -6980,7 +7375,18 @@ struct drm_display_mode *intel_crtc_mode_get(struct drm_device *dev,
 	if (!mode)
 		return NULL;
 
-	mode->clock = intel_crtc_clock_get(dev, crtc);
+	/*
+	 * Construct a pipe_config sufficient for getting the clock info
+	 * back out of crtc_clock_get.
+	 *
+	 * Note, if LVDS ever uses a non-1 pixel multiplier, we'll need
+	 * to use a real value here instead.
+	 */
+	pipe_config.cpu_transcoder = (enum transcoder) intel_crtc->pipe;
+	pipe_config.pixel_multiplier = 1;
+	i9xx_crtc_clock_get(intel_crtc, &pipe_config);
+
+	mode->clock = pipe_config.adjusted_mode.clock;
 	mode->hdisplay = (htot & 0xffff) + 1;
 	mode->htotal = ((htot & 0xffff0000) >> 16) + 1;
 	mode->hsync_start = (hsync & 0xffff) + 1;
@@ -7064,13 +7470,19 @@ static void intel_decrease_pllclock(struct drm_crtc *crtc)
 
 void intel_mark_busy(struct drm_device *dev)
 {
-	i915_update_gfx_val(dev->dev_private);
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	hsw_package_c8_gpu_busy(dev_priv);
+	i915_update_gfx_val(dev_priv);
 }
 
 void intel_mark_idle(struct drm_device *dev)
 {
+	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_crtc *crtc;
 
+	hsw_package_c8_gpu_idle(dev_priv);
+
 	if (!i915_powersave)
 		return;
 
@@ -7235,7 +7647,8 @@ inline static void intel_mark_page_flip_active(struct intel_crtc *intel_crtc)
 static int intel_gen2_queue_flip(struct drm_device *dev,
 				 struct drm_crtc *crtc,
 				 struct drm_framebuffer *fb,
-				 struct drm_i915_gem_object *obj)
+				 struct drm_i915_gem_object *obj,
+				 uint32_t flags)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
@@ -7263,7 +7676,7 @@ static int intel_gen2_queue_flip(struct drm_device *dev,
 	intel_ring_emit(ring, MI_DISPLAY_FLIP |
 			MI_DISPLAY_FLIP_PLANE(intel_crtc->plane));
 	intel_ring_emit(ring, fb->pitches[0]);
-	intel_ring_emit(ring, obj->gtt_offset + intel_crtc->dspaddr_offset);
+	intel_ring_emit(ring, i915_gem_obj_ggtt_offset(obj) + intel_crtc->dspaddr_offset);
 	intel_ring_emit(ring, 0); /* aux display base address, unused */
 
 	intel_mark_page_flip_active(intel_crtc);
@@ -7279,7 +7692,8 @@ err:
 static int intel_gen3_queue_flip(struct drm_device *dev,
 				 struct drm_crtc *crtc,
 				 struct drm_framebuffer *fb,
-				 struct drm_i915_gem_object *obj)
+				 struct drm_i915_gem_object *obj,
+				 uint32_t flags)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
@@ -7304,7 +7718,7 @@ static int intel_gen3_queue_flip(struct drm_device *dev,
 	intel_ring_emit(ring, MI_DISPLAY_FLIP_I915 |
 			MI_DISPLAY_FLIP_PLANE(intel_crtc->plane));
 	intel_ring_emit(ring, fb->pitches[0]);
-	intel_ring_emit(ring, obj->gtt_offset + intel_crtc->dspaddr_offset);
+	intel_ring_emit(ring, i915_gem_obj_ggtt_offset(obj) + intel_crtc->dspaddr_offset);
 	intel_ring_emit(ring, MI_NOOP);
 
 	intel_mark_page_flip_active(intel_crtc);
@@ -7320,7 +7734,8 @@ err:
 static int intel_gen4_queue_flip(struct drm_device *dev,
 				 struct drm_crtc *crtc,
 				 struct drm_framebuffer *fb,
-				 struct drm_i915_gem_object *obj)
+				 struct drm_i915_gem_object *obj,
+				 uint32_t flags)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
@@ -7344,7 +7759,7 @@ static int intel_gen4_queue_flip(struct drm_device *dev,
 			MI_DISPLAY_FLIP_PLANE(intel_crtc->plane));
 	intel_ring_emit(ring, fb->pitches[0]);
 	intel_ring_emit(ring,
-			(obj->gtt_offset + intel_crtc->dspaddr_offset) |
+			(i915_gem_obj_ggtt_offset(obj) + intel_crtc->dspaddr_offset) |
 			obj->tiling_mode);
 
 	/* XXX Enabling the panel-fitter across page-flip is so far
@@ -7368,7 +7783,8 @@ err:
 static int intel_gen6_queue_flip(struct drm_device *dev,
 				 struct drm_crtc *crtc,
 				 struct drm_framebuffer *fb,
-				 struct drm_i915_gem_object *obj)
+				 struct drm_i915_gem_object *obj,
+				 uint32_t flags)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
@@ -7387,7 +7803,7 @@ static int intel_gen6_queue_flip(struct drm_device *dev,
 	intel_ring_emit(ring, MI_DISPLAY_FLIP |
 			MI_DISPLAY_FLIP_PLANE(intel_crtc->plane));
 	intel_ring_emit(ring, fb->pitches[0] | obj->tiling_mode);
-	intel_ring_emit(ring, obj->gtt_offset + intel_crtc->dspaddr_offset);
+	intel_ring_emit(ring, i915_gem_obj_ggtt_offset(obj) + intel_crtc->dspaddr_offset);
 
 	/* Contrary to the suggestions in the documentation,
 	 * "Enable Panel Fitter" does not seem to be required when page
@@ -7409,22 +7825,21 @@ err:
 	return ret;
 }
 
-/*
- * On gen7 we currently use the blit ring because (in early silicon at least)
- * the render ring doesn't give us interrpts for page flip completion, which
- * means clients will hang after the first flip is queued.  Fortunately the
- * blit ring generates interrupts properly, so use it instead.
- */
 static int intel_gen7_queue_flip(struct drm_device *dev,
 				 struct drm_crtc *crtc,
 				 struct drm_framebuffer *fb,
-				 struct drm_i915_gem_object *obj)
+				 struct drm_i915_gem_object *obj,
+				 uint32_t flags)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	struct intel_ring_buffer *ring = &dev_priv->ring[BCS];
+	struct intel_ring_buffer *ring;
 	uint32_t plane_bit = 0;
-	int ret;
+	int len, ret;
+
+	ring = obj->ring;
+	if (IS_VALLEYVIEW(dev) || ring == NULL || ring->id != RCS)
+		ring = &dev_priv->ring[BCS];
 
 	ret = intel_pin_and_fence_fb_obj(dev, obj, ring);
 	if (ret)
@@ -7446,13 +7861,37 @@ static int intel_gen7_queue_flip(struct drm_device *dev,
 		goto err_unpin;
 	}
 
-	ret = intel_ring_begin(ring, 4);
+	len = 4;
+	if (ring->id == RCS)
+		len += 6;
+
+	ret = intel_ring_begin(ring, len);
 	if (ret)
 		goto err_unpin;
 
+	/* Unmask the flip-done completion message. Note that the bspec says that
+	 * we should do this for both the BCS and RCS, and that we must not unmask
+	 * more than one flip event at any time (or ensure that one flip message
+	 * can be sent by waiting for flip-done prior to queueing new flips).
+	 * Experimentation says that BCS works despite DERRMR masking all
+	 * flip-done completion events and that unmasking all planes at once
+	 * for the RCS also doesn't appear to drop events. Setting the DERRMR
+	 * to zero does lead to lockups within MI_DISPLAY_FLIP.
+	 */
+	if (ring->id == RCS) {
+		intel_ring_emit(ring, MI_LOAD_REGISTER_IMM(1));
+		intel_ring_emit(ring, DERRMR);
+		intel_ring_emit(ring, ~(DERRMR_PIPEA_PRI_FLIP_DONE |
+					DERRMR_PIPEB_PRI_FLIP_DONE |
+					DERRMR_PIPEC_PRI_FLIP_DONE));
+		intel_ring_emit(ring, MI_STORE_REGISTER_MEM(1));
+		intel_ring_emit(ring, DERRMR);
+		intel_ring_emit(ring, ring->scratch.gtt_offset + 256);
+	}
+
 	intel_ring_emit(ring, MI_DISPLAY_FLIP_I915 | plane_bit);
 	intel_ring_emit(ring, (fb->pitches[0] | obj->tiling_mode));
-	intel_ring_emit(ring, obj->gtt_offset + intel_crtc->dspaddr_offset);
+	intel_ring_emit(ring, i915_gem_obj_ggtt_offset(obj) + intel_crtc->dspaddr_offset);
 	intel_ring_emit(ring, (MI_NOOP));
 
 	intel_mark_page_flip_active(intel_crtc);
@@ -7468,14 +7907,16 @@ err:
 static int intel_default_queue_flip(struct drm_device *dev,
 				    struct drm_crtc *crtc,
 				    struct drm_framebuffer *fb,
-				    struct drm_i915_gem_object *obj)
+				    struct drm_i915_gem_object *obj,
+				    uint32_t flags)
 {
 	return -ENODEV;
 }
 
 static int intel_crtc_page_flip(struct drm_crtc *crtc,
 				struct drm_framebuffer *fb,
-				struct drm_pending_vblank_event *event)
+				struct drm_pending_vblank_event *event,
+				uint32_t page_flip_flags)
 {
 	struct drm_device *dev = crtc->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -7545,7 +7986,7 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc,
 	atomic_inc(&intel_crtc->unpin_work_count);
 	intel_crtc->reset_counter = atomic_read(&dev_priv->gpu_error.reset_counter);
 
-	ret = dev_priv->display.queue_flip(dev, crtc, fb, obj);
+	ret = dev_priv->display.queue_flip(dev, crtc, fb, obj, page_flip_flags);
 	if (ret)
 		goto cleanup_pending;
 
@@ -7758,9 +8199,10 @@ static void intel_dump_pipe_config(struct intel_crtc *crtc,
 		      pipe_config->gmch_pfit.control,
 		      pipe_config->gmch_pfit.pgm_ratios,
 		      pipe_config->gmch_pfit.lvds_border_bits);
-	DRM_DEBUG_KMS("pch pfit: pos: 0x%08x, size: 0x%08x\n",
+	DRM_DEBUG_KMS("pch pfit: pos: 0x%08x, size: 0x%08x, %s\n",
 		      pipe_config->pch_pfit.pos,
-		      pipe_config->pch_pfit.size);
+		      pipe_config->pch_pfit.size,
+		      pipe_config->pch_pfit.enabled ? "enabled" : "disabled");
 	DRM_DEBUG_KMS("ips: %i\n", pipe_config->ips_enabled);
 }
 
@@ -7789,7 +8231,6 @@ intel_modeset_pipe_config(struct drm_crtc *crtc,
 			  struct drm_display_mode *mode)
 {
 	struct drm_device *dev = crtc->dev;
-	struct drm_encoder_helper_funcs *encoder_funcs;
 	struct intel_encoder *encoder;
 	struct intel_crtc_config *pipe_config;
 	int plane_bpp, ret = -EINVAL;
@@ -7806,9 +8247,23 @@ intel_modeset_pipe_config(struct drm_crtc *crtc,
 
 	drm_mode_copy(&pipe_config->adjusted_mode, mode);
 	drm_mode_copy(&pipe_config->requested_mode, mode);
-	pipe_config->cpu_transcoder = to_intel_crtc(crtc)->pipe;
+	pipe_config->cpu_transcoder =
+		(enum transcoder) to_intel_crtc(crtc)->pipe;
 	pipe_config->shared_dpll = DPLL_ID_PRIVATE;
 
+	/*
+	 * Sanitize sync polarity flags based on requested ones. If neither
+	 * positive or negative polarity is requested, treat this as meaning
+	 * negative polarity.
+	 */
+	if (!(pipe_config->adjusted_mode.flags &
+	      (DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_NHSYNC)))
+		pipe_config->adjusted_mode.flags |= DRM_MODE_FLAG_NHSYNC;
+
+	if (!(pipe_config->adjusted_mode.flags &
+	      (DRM_MODE_FLAG_PVSYNC | DRM_MODE_FLAG_NVSYNC)))
+		pipe_config->adjusted_mode.flags |= DRM_MODE_FLAG_NVSYNC;
+
 	/* Compute a starting value for pipe_config->pipe_bpp taking the source
 	 * plane pixel format and any sink constraints into account. Returns the
 	 * source plane bpp so that dithering can be selected on mismatches
@@ -7823,6 +8278,9 @@ encoder_retry:
 	pipe_config->port_clock = 0;
 	pipe_config->pixel_multiplier = 1;
 
+	/* Fill in default crtc timings, allow encoders to overwrite them. */
+	drm_mode_set_crtcinfo(&pipe_config->adjusted_mode, 0);
+
 	/* Pass our mode to the connectors and the CRTC to give them a chance to
 	 * adjust it according to limitations or connector properties, and also
 	 * a chance to reject the mode entirely.
@@ -7833,20 +8291,8 @@ encoder_retry:
 		if (&encoder->new_crtc->base != crtc)
 			continue;
 
-		if (encoder->compute_config) {
-			if (!(encoder->compute_config(encoder, pipe_config))) {
-				DRM_DEBUG_KMS("Encoder config failure\n");
-				goto fail;
-			}
-
-			continue;
-		}
-
-		encoder_funcs = encoder->base.helper_private;
-		if (!(encoder_funcs->mode_fixup(&encoder->base,
-						&pipe_config->requested_mode,
-						&pipe_config->adjusted_mode))) {
-			DRM_DEBUG_KMS("Encoder fixup failed\n");
+		if (!(encoder->compute_config(encoder, pipe_config))) {
+			DRM_DEBUG_KMS("Encoder config failure\n");
 			goto fail;
 		}
 	}
@@ -8041,6 +8487,28 @@ intel_modeset_update_state(struct drm_device *dev, unsigned prepare_pipes)
 
 }
 
+static bool intel_fuzzy_clock_check(struct intel_crtc_config *cur,
+				    struct intel_crtc_config *new)
+{
+	int clock1, clock2, diff;
+
+	clock1 = cur->adjusted_mode.clock;
+	clock2 = new->adjusted_mode.clock;
+
+	if (clock1 == clock2)
+		return true;
+
+	if (!clock1 || !clock2)
+		return false;
+
+	diff = abs(clock1 - clock2);
+
+	if (((((diff + clock1 + clock2) * 100)) / (clock1 + clock2)) < 105)
+		return true;
+
+	return false;
+}
+
 #define for_each_intel_crtc_masked(dev, mask, intel_crtc) \
 	list_for_each_entry((intel_crtc), \
 			    &(dev)->mode_config.crtc_list, \
@@ -8072,7 +8540,7 @@ intel_pipe_config_compare(struct drm_device *dev,
 
 #define PIPE_CONF_CHECK_FLAGS(name, mask)	\
 	if ((current_config->name ^ pipe_config->name) & (mask)) { \
-		DRM_ERROR("mismatch in " #name " " \
+		DRM_ERROR("mismatch in " #name "(" #mask ") "	   \
 			  "(expected %i, found %i)\n", \
 			  current_config->name & (mask), \
 			  pipe_config->name & (mask)); \
@@ -8106,8 +8574,7 @@ intel_pipe_config_compare(struct drm_device *dev,
 	PIPE_CONF_CHECK_I(adjusted_mode.crtc_vsync_start);
 	PIPE_CONF_CHECK_I(adjusted_mode.crtc_vsync_end);
 
-	if (!HAS_PCH_SPLIT(dev))
-		PIPE_CONF_CHECK_I(pixel_multiplier);
+	PIPE_CONF_CHECK_I(pixel_multiplier);
 
 	PIPE_CONF_CHECK_FLAGS(adjusted_mode.flags,
 			      DRM_MODE_FLAG_INTERLACE);
@@ -8131,13 +8598,17 @@ intel_pipe_config_compare(struct drm_device *dev,
 	if (INTEL_INFO(dev)->gen < 4)
 		PIPE_CONF_CHECK_I(gmch_pfit.pgm_ratios);
 	PIPE_CONF_CHECK_I(gmch_pfit.lvds_border_bits);
-	PIPE_CONF_CHECK_I(pch_pfit.pos);
-	PIPE_CONF_CHECK_I(pch_pfit.size);
+	PIPE_CONF_CHECK_I(pch_pfit.enabled);
+	if (current_config->pch_pfit.enabled) {
+		PIPE_CONF_CHECK_I(pch_pfit.pos);
+		PIPE_CONF_CHECK_I(pch_pfit.size);
+	}
 
 	PIPE_CONF_CHECK_I(ips_enabled);
 
 	PIPE_CONF_CHECK_I(shared_dpll);
 	PIPE_CONF_CHECK_X(dpll_hw_state.dpll);
+	PIPE_CONF_CHECK_X(dpll_hw_state.dpll_md);
 	PIPE_CONF_CHECK_X(dpll_hw_state.fp0);
 	PIPE_CONF_CHECK_X(dpll_hw_state.fp1);
 
@@ -8146,6 +8617,15 @@ intel_pipe_config_compare(struct drm_device *dev,
 #undef PIPE_CONF_CHECK_FLAGS
 #undef PIPE_CONF_QUIRK
 
+	if (!IS_HASWELL(dev)) {
+		if (!intel_fuzzy_clock_check(current_config, pipe_config)) {
+			DRM_ERROR("mismatch in clock (expected %d, found %d)\n",
+				  current_config->adjusted_mode.clock,
+				  pipe_config->adjusted_mode.clock);
+			return false;
+		}
+	}
+
 	return true;
 }
 
@@ -8277,6 +8757,9 @@ check_crtc_state(struct drm_device *dev)
 				encoder->get_config(encoder, &pipe_config);
 		}
 
+		if (dev_priv->display.get_clock)
+			dev_priv->display.get_clock(crtc, &pipe_config);
+
 		WARN(crtc->active != active,
 		     "crtc active state doesn't match with hw state "
 		     "(expected %i, found %i)\n", crtc->active, active);
@@ -8454,9 +8937,9 @@ out:
 	return ret;
 }
 
-int intel_set_mode(struct drm_crtc *crtc,
-		     struct drm_display_mode *mode,
-		     int x, int y, struct drm_framebuffer *fb)
+static int intel_set_mode(struct drm_crtc *crtc,
+			  struct drm_display_mode *mode,
+			  int x, int y, struct drm_framebuffer *fb)
 {
 	int ret;
 
@@ -8573,8 +9056,16 @@ intel_set_config_compute_mode_changes(struct drm_mode_set *set,
 	} else if (set->crtc->fb != set->fb) {
 		/* If we have no fb then treat it as a full mode set */
 		if (set->crtc->fb == NULL) {
-			DRM_DEBUG_KMS("crtc has no fb, full mode set\n");
-			config->mode_changed = true;
+			struct intel_crtc *intel_crtc =
+				to_intel_crtc(set->crtc);
+
+			if (intel_crtc->active && i915_fastboot) {
+				DRM_DEBUG_KMS("crtc has no fb, will flip\n");
+				config->fb_changed = true;
+			} else {
+				DRM_DEBUG_KMS("inactive crtc, full mode set\n");
+				config->mode_changed = true;
+			}
 		} else if (set->fb == NULL) {
 			config->mode_changed = true;
 		} else if (set->fb->pixel_format !=
@@ -8594,6 +9085,9 @@ intel_set_config_compute_mode_changes(struct drm_mode_set *set,
 		drm_mode_debug_printmodeline(set->mode);
 		config->mode_changed = true;
 	}
+
+	DRM_DEBUG_KMS("computed changes for [CRTC:%d], mode_changed=%d, fb_changed=%d\n",
+			set->crtc->base.id, config->mode_changed, config->fb_changed);
 }
 
 static int
@@ -8604,14 +9098,13 @@ intel_modeset_stage_output_state(struct drm_device *dev,
 	struct drm_crtc *new_crtc;
 	struct intel_connector *connector;
 	struct intel_encoder *encoder;
-	int count, ro;
+	int ro;
 
 	/* The upper layers ensure that we either disable a crtc or have a list
 	 * of connectors. For paranoia, double-check this. */
 	WARN_ON(!set->fb && (set->num_connectors != 0));
 	WARN_ON(set->fb && (set->num_connectors == 0));
 
-	count = 0;
 	list_for_each_entry(connector, &dev->mode_config.connector_list,
 			    base.head) {
 		/* Otherwise traverse passed in connector list and get encoders
@@ -8645,7 +9138,6 @@ intel_modeset_stage_output_state(struct drm_device *dev,
 	/* connector->new_encoder is now updated for all connectors. */
 
 	/* Update crtc of enabled connectors. */
-	count = 0;
 	list_for_each_entry(connector, &dev->mode_config.connector_list,
 			    base.head) {
 		if (!connector->new_encoder)
@@ -8804,19 +9296,32 @@ static bool ibx_pch_dpll_get_hw_state(struct drm_i915_private *dev_priv,
 	return val & DPLL_VCO_ENABLE;
 }
 
+static void ibx_pch_dpll_mode_set(struct drm_i915_private *dev_priv,
+				  struct intel_shared_dpll *pll)
+{
+	I915_WRITE(PCH_FP0(pll->id), pll->hw_state.fp0);
+	I915_WRITE(PCH_FP1(pll->id), pll->hw_state.fp1);
+}
+
 static void ibx_pch_dpll_enable(struct drm_i915_private *dev_priv,
 				struct intel_shared_dpll *pll)
 {
-	uint32_t reg, val;
-
 	/* PCH refclock must be enabled first */
 	assert_pch_refclk_enabled(dev_priv);
 
-	reg = PCH_DPLL(pll->id);
-	val = I915_READ(reg);
-	val |= DPLL_VCO_ENABLE;
-	I915_WRITE(reg, val);
-	POSTING_READ(reg);
+	I915_WRITE(PCH_DPLL(pll->id), pll->hw_state.dpll);
+
+	/* Wait for the clocks to stabilize. */
+	POSTING_READ(PCH_DPLL(pll->id));
+	udelay(150);
+
+	/* The pixel multiplier can only be updated once the
+	 * DPLL is enabled and the clocks are stable.
+	 *
+	 * So write it again.
+	 */
+	I915_WRITE(PCH_DPLL(pll->id), pll->hw_state.dpll);
+	POSTING_READ(PCH_DPLL(pll->id));
 	udelay(200);
 }
 
@@ -8825,7 +9330,6 @@ static void ibx_pch_dpll_disable(struct drm_i915_private *dev_priv,
 {
 	struct drm_device *dev = dev_priv->dev;
 	struct intel_crtc *crtc;
-	uint32_t reg, val;
 
 	/* Make sure no transcoder isn't still depending on us. */
 	list_for_each_entry(crtc, &dev->mode_config.crtc_list, base.head) {
@@ -8833,11 +9337,8 @@ static void ibx_pch_dpll_disable(struct drm_i915_private *dev_priv,
 			assert_pch_transcoder_disabled(dev_priv, crtc->pipe);
 	}
 
-	reg = PCH_DPLL(pll->id);
-	val = I915_READ(reg);
-	val &= ~DPLL_VCO_ENABLE;
-	I915_WRITE(reg, val);
-	POSTING_READ(reg);
+	I915_WRITE(PCH_DPLL(pll->id), 0);
+	POSTING_READ(PCH_DPLL(pll->id));
 	udelay(200);
 }
 
@@ -8856,6 +9357,7 @@ static void ibx_pch_dpll_init(struct drm_device *dev)
 	for (i = 0; i < dev_priv->num_shared_dpll; i++) {
 		dev_priv->shared_dplls[i].id = i;
 		dev_priv->shared_dplls[i].name = ibx_pch_dpll_names[i];
+		dev_priv->shared_dplls[i].mode_set = ibx_pch_dpll_mode_set;
 		dev_priv->shared_dplls[i].enable = ibx_pch_dpll_enable;
 		dev_priv->shared_dplls[i].disable = ibx_pch_dpll_disable;
 		dev_priv->shared_dplls[i].get_hw_state =
@@ -9035,8 +9537,13 @@ static void intel_setup_outputs(struct drm_device *dev)
 			intel_dp_init(dev, PCH_DP_D, PORT_D);
 	} else if (IS_VALLEYVIEW(dev)) {
 		/* Check for built-in panel first. Shares lanes with HDMI on SDVOC */
-		if (I915_READ(VLV_DISPLAY_BASE + DP_C) & DP_DETECTED)
-			intel_dp_init(dev, VLV_DISPLAY_BASE + DP_C, PORT_C);
+		if (I915_READ(VLV_DISPLAY_BASE + GEN4_HDMIC) & SDVO_DETECTED) {
+			intel_hdmi_init(dev, VLV_DISPLAY_BASE + GEN4_HDMIC,
+					PORT_C);
+			if (I915_READ(VLV_DISPLAY_BASE + DP_C) & DP_DETECTED)
+				intel_dp_init(dev, VLV_DISPLAY_BASE + DP_C,
+					      PORT_C);
+		}
 
 		if (I915_READ(VLV_DISPLAY_BASE + GEN4_HDMIB) & SDVO_DETECTED) {
 			intel_hdmi_init(dev, VLV_DISPLAY_BASE + GEN4_HDMIB,
@@ -9096,13 +9603,17 @@ static void intel_setup_outputs(struct drm_device *dev)
 	drm_helper_move_panel_connectors_to_head(dev);
 }
 
+void intel_framebuffer_fini(struct intel_framebuffer *fb)
+{
+	drm_framebuffer_cleanup(&fb->base);
+	drm_gem_object_unreference_unlocked(&fb->obj->base);
+}
+
 static void intel_user_framebuffer_destroy(struct drm_framebuffer *fb)
 {
 	struct intel_framebuffer *intel_fb = to_intel_framebuffer(fb);
 
-	drm_framebuffer_cleanup(fb);
-	drm_gem_object_unreference_unlocked(&intel_fb->obj->base);
-
+	intel_framebuffer_fini(intel_fb);
 	kfree(intel_fb);
 }
 
@@ -9272,6 +9783,7 @@ static void intel_init_display(struct drm_device *dev)
 		dev_priv->display.update_plane = ironlake_update_plane;
 	} else if (HAS_PCH_SPLIT(dev)) {
 		dev_priv->display.get_pipe_config = ironlake_get_pipe_config;
+		dev_priv->display.get_clock = ironlake_crtc_clock_get;
 		dev_priv->display.crtc_mode_set = ironlake_crtc_mode_set;
 		dev_priv->display.crtc_enable = ironlake_crtc_enable;
 		dev_priv->display.crtc_disable = ironlake_crtc_disable;
@@ -9279,6 +9791,7 @@ static void intel_init_display(struct drm_device *dev)
 		dev_priv->display.update_plane = ironlake_update_plane;
 	} else if (IS_VALLEYVIEW(dev)) {
 		dev_priv->display.get_pipe_config = i9xx_get_pipe_config;
+		dev_priv->display.get_clock = i9xx_crtc_clock_get;
 		dev_priv->display.crtc_mode_set = i9xx_crtc_mode_set;
 		dev_priv->display.crtc_enable = valleyview_crtc_enable;
 		dev_priv->display.crtc_disable = i9xx_crtc_disable;
@@ -9286,6 +9799,7 @@ static void intel_init_display(struct drm_device *dev)
 		dev_priv->display.update_plane = i9xx_update_plane;
 	} else {
 		dev_priv->display.get_pipe_config = i9xx_get_pipe_config;
+		dev_priv->display.get_clock = i9xx_crtc_clock_get;
 		dev_priv->display.crtc_mode_set = i9xx_crtc_mode_set;
 		dev_priv->display.crtc_enable = i9xx_crtc_enable;
 		dev_priv->display.crtc_disable = i9xx_crtc_disable;
@@ -9303,9 +9817,12 @@ static void intel_init_display(struct drm_device *dev)
 	else if (IS_I915G(dev))
 		dev_priv->display.get_display_clock_speed =
 			i915_get_display_clock_speed;
-	else if (IS_I945GM(dev) || IS_845G(dev) || IS_PINEVIEW_M(dev))
+	else if (IS_I945GM(dev) || IS_845G(dev))
 		dev_priv->display.get_display_clock_speed =
 			i9xx_misc_get_display_clock_speed;
+	else if (IS_PINEVIEW(dev))
+		dev_priv->display.get_display_clock_speed =
+			pnv_get_display_clock_speed;
 	else if (IS_I915GM(dev))
 		dev_priv->display.get_display_clock_speed =
 			i915gm_get_display_clock_speed;
@@ -9586,7 +10103,7 @@ void intel_modeset_init(struct drm_device *dev)
 		      INTEL_INFO(dev)->num_pipes,
 		      INTEL_INFO(dev)->num_pipes > 1 ? "s" : "");
 
-	for (i = 0; i < INTEL_INFO(dev)->num_pipes; i++) {
+	for_each_pipe(i) {
 		intel_crtc_init(dev, i);
 		for (j = 0; j < dev_priv->num_plane; j++) {
 			ret = intel_plane_init(dev, i, j);
@@ -9792,6 +10309,17 @@ void i915_redisable_vga(struct drm_device *dev)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	u32 vga_reg = i915_vgacntrl_reg(dev);
 
+	/* This function can be called both from intel_modeset_setup_hw_state or
+	 * at a very early point in our resume sequence, where the power well
+	 * structures are not yet restored. Since this function is at a very
+	 * paranoid "someone might have enabled VGA while we were not looking"
+	 * level, just check if the power well is enabled instead of trying to
+	 * follow the "don't touch the power well if we don't need it" policy
+	 * the rest of the driver uses. */
+	if (HAS_POWER_WELL(dev) &&
+	    (I915_READ(HSW_PWR_WELL_DRIVER) & HSW_PWR_WELL_STATE_ENABLED) == 0)
+		return;
+
 	if (I915_READ(vga_reg) != VGA_DISP_DISABLE) {
 		DRM_DEBUG_KMS("Something enabled VGA plane, disabling it\n");
 		i915_disable_vga(dev);
@@ -9862,6 +10390,15 @@ static void intel_modeset_readout_hw_state(struct drm_device *dev)
 			      pipe);
 	}
 
+	list_for_each_entry(crtc, &dev->mode_config.crtc_list,
+			    base.head) {
+		if (!crtc->active)
+			continue;
+		if (dev_priv->display.get_clock)
+			dev_priv->display.get_clock(crtc,
+						    &crtc->config);
+	}
+
 	list_for_each_entry(connector, &dev->mode_config.connector_list,
 			    base.head) {
 		if (connector->get_hw_state(connector)) {
@@ -9893,6 +10430,22 @@ void intel_modeset_setup_hw_state(struct drm_device *dev,
 
 	intel_modeset_readout_hw_state(dev);
 
+	/*
+	 * Now that we have the config, copy it to each CRTC struct
+	 * Note that this could go away if we move to using crtc_config
+	 * checking everywhere.
+	 */
+	list_for_each_entry(crtc, &dev->mode_config.crtc_list,
+			    base.head) {
+		if (crtc->active && i915_fastboot) {
+			intel_crtc_mode_from_pipe_config(crtc, &crtc->config);
+
+			DRM_DEBUG_KMS("[CRTC:%d] found active mode: ",
+				      crtc->base.base.id);
+			drm_mode_debug_printmodeline(&crtc->base.mode);
+		}
+	}
+
 	/* HW state is read out, now we need to sanitize this mess. */
 	list_for_each_entry(encoder, &dev->mode_config.encoder_list,
 			    base.head) {
@@ -9955,7 +10508,6 @@ void intel_modeset_cleanup(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_crtc *crtc;
-	struct intel_crtc *intel_crtc;
 
 	/*
 	 * Interrupts and polling as the first thing to avoid creating havoc.
@@ -9979,7 +10531,6 @@ void intel_modeset_cleanup(struct drm_device *dev)
 		if (!crtc->fb)
 			continue;
 
-		intel_crtc = to_intel_crtc(crtc);
 		intel_increase_pllclock(crtc);
 	}
 
@@ -10035,9 +10586,6 @@ int intel_modeset_vga_set_state(struct drm_device *dev, bool state)
 	return 0;
 }
 
-#ifdef CONFIG_DEBUG_FS
-#include <linux/seq_file.h>
-
 struct intel_display_error_state {
 
 	u32 power_well_driver;
@@ -10151,8 +10699,7 @@ intel_display_capture_error_state(struct drm_device *dev)
 	 * well was on, so here we have to clear the FPGA_DBG_RM_NOCLAIM bit to
 	 * prevent the next I915_WRITE from detecting it and printing an error
 	 * message. */
-	if (HAS_POWER_WELL(dev))
-		I915_WRITE_NOTRACE(FPGA_DBG, FPGA_DBG_RM_NOCLAIM);
+	intel_uncore_clear_errors(dev);
 
 	return error;
 }
@@ -10209,4 +10756,3 @@ intel_display_print_error_state(struct drm_i915_error_state_buf *m,
 		err_printf(m, "  VSYNC: %08x\n", error->transcoder[i].vsync);
 	}
 }
-#endif
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 26e162bb3a51..2c555f91bfae 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -276,29 +276,13 @@ intel_dp_aux_wait_done(struct intel_dp *intel_dp, bool has_aux_irq)
 	return status;
 }
 
-static int
-intel_dp_aux_ch(struct intel_dp *intel_dp,
-		uint8_t *send, int send_bytes,
-		uint8_t *recv, int recv_size)
+static uint32_t get_aux_clock_divider(struct intel_dp *intel_dp,
+				      int index)
 {
 	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
 	struct drm_device *dev = intel_dig_port->base.base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	uint32_t ch_ctl = intel_dp->aux_ch_ctl_reg;
-	uint32_t ch_data = ch_ctl + 4;
-	int i, ret, recv_bytes;
-	uint32_t status;
-	uint32_t aux_clock_divider;
-	int try, precharge;
-	bool has_aux_irq = INTEL_INFO(dev)->gen >= 5 && !IS_VALLEYVIEW(dev);
 
-	/* dp aux is extremely sensitive to irq latency, hence request the
-	 * lowest possible wakeup latency and so prevent the cpu from going into
-	 * deep sleep states.
-	 */
-	pm_qos_update_request(&dev_priv->pm_qos, 0);
-
-	intel_dp_check_edp(intel_dp);
 	/* The clock divider is based off the hrawclk,
 	 * and would like to run at 2MHz. So, take the
 	 * hrawclk value and divide by 2 and use that
@@ -307,29 +291,61 @@ intel_dp_aux_ch(struct intel_dp *intel_dp,
 	 * clock divider.
 	 */
 	if (IS_VALLEYVIEW(dev)) {
-		aux_clock_divider = 100;
+		return index ? 0 : 100;
 	} else if (intel_dig_port->port == PORT_A) {
+		if (index)
+			return 0;
 		if (HAS_DDI(dev))
-			aux_clock_divider = DIV_ROUND_CLOSEST(
-				intel_ddi_get_cdclk_freq(dev_priv), 2000);
+			return DIV_ROUND_CLOSEST(intel_ddi_get_cdclk_freq(dev_priv), 2000);
 		else if (IS_GEN6(dev) || IS_GEN7(dev))
-			aux_clock_divider = 200; /* SNB & IVB eDP input clock at 400Mhz */
+			return 200; /* SNB & IVB eDP input clock at 400Mhz */
 		else
-			aux_clock_divider = 225; /* eDP input clock at 450Mhz */
+			return 225; /* eDP input clock at 450Mhz */
 	} else if (dev_priv->pch_id == INTEL_PCH_LPT_DEVICE_ID_TYPE) {
 		/* Workaround for non-ULT HSW */
-		aux_clock_divider = 74;
+		switch (index) {
+		case 0: return 63;
+		case 1: return 72;
+		default: return 0;
+		}
 	} else if (HAS_PCH_SPLIT(dev)) {
-		aux_clock_divider = DIV_ROUND_UP(intel_pch_rawclk(dev), 2);
+		return index ? 0 : DIV_ROUND_UP(intel_pch_rawclk(dev), 2);
 	} else {
-		aux_clock_divider = intel_hrawclk(dev) / 2;
+		return index ? 0 :intel_hrawclk(dev) / 2;
 	}
+}
+
+static int
+intel_dp_aux_ch(struct intel_dp *intel_dp,
+		uint8_t *send, int send_bytes,
+		uint8_t *recv, int recv_size)
+{
+	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
+	struct drm_device *dev = intel_dig_port->base.base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	uint32_t ch_ctl = intel_dp->aux_ch_ctl_reg;
+	uint32_t ch_data = ch_ctl + 4;
+	uint32_t aux_clock_divider;
+	int i, ret, recv_bytes;
+	uint32_t status;
+	int try, precharge, clock = 0;
+	bool has_aux_irq = INTEL_INFO(dev)->gen >= 5 && !IS_VALLEYVIEW(dev);
+
+	/* dp aux is extremely sensitive to irq latency, hence request the
+	 * lowest possible wakeup latency and so prevent the cpu from going into
+	 * deep sleep states.
+	 */
+	pm_qos_update_request(&dev_priv->pm_qos, 0);
+
+	intel_dp_check_edp(intel_dp);
 
 	if (IS_GEN6(dev))
 		precharge = 3;
 	else
 		precharge = 5;
 
+	intel_aux_display_runtime_get(dev_priv);
+
 	/* Try to wait for any previous AUX channel activity */
 	for (try = 0; try < 3; try++) {
 		status = I915_READ_NOTRACE(ch_ctl);
@@ -345,37 +361,41 @@ intel_dp_aux_ch(struct intel_dp *intel_dp,
 		goto out;
 	}
 
-	/* Must try at least 3 times according to DP spec */
-	for (try = 0; try < 5; try++) {
-		/* Load the send data into the aux channel data registers */
-		for (i = 0; i < send_bytes; i += 4)
-			I915_WRITE(ch_data + i,
-				   pack_aux(send + i, send_bytes - i));
-
-		/* Send the command and wait for it to complete */
-		I915_WRITE(ch_ctl,
-			   DP_AUX_CH_CTL_SEND_BUSY |
-			   (has_aux_irq ? DP_AUX_CH_CTL_INTERRUPT : 0) |
-			   DP_AUX_CH_CTL_TIME_OUT_400us |
-			   (send_bytes << DP_AUX_CH_CTL_MESSAGE_SIZE_SHIFT) |
-			   (precharge << DP_AUX_CH_CTL_PRECHARGE_2US_SHIFT) |
-			   (aux_clock_divider << DP_AUX_CH_CTL_BIT_CLOCK_2X_SHIFT) |
-			   DP_AUX_CH_CTL_DONE |
-			   DP_AUX_CH_CTL_TIME_OUT_ERROR |
-			   DP_AUX_CH_CTL_RECEIVE_ERROR);
-
-		status = intel_dp_aux_wait_done(intel_dp, has_aux_irq);
-
-		/* Clear done status and any errors */
-		I915_WRITE(ch_ctl,
-			   status |
-			   DP_AUX_CH_CTL_DONE |
-			   DP_AUX_CH_CTL_TIME_OUT_ERROR |
-			   DP_AUX_CH_CTL_RECEIVE_ERROR);
-
-		if (status & (DP_AUX_CH_CTL_TIME_OUT_ERROR |
-			      DP_AUX_CH_CTL_RECEIVE_ERROR))
-			continue;
+	while ((aux_clock_divider = get_aux_clock_divider(intel_dp, clock++))) {
+		/* Must try at least 3 times according to DP spec */
+		for (try = 0; try < 5; try++) {
+			/* Load the send data into the aux channel data registers */
+			for (i = 0; i < send_bytes; i += 4)
+				I915_WRITE(ch_data + i,
+					   pack_aux(send + i, send_bytes - i));
+
+			/* Send the command and wait for it to complete */
+			I915_WRITE(ch_ctl,
+				   DP_AUX_CH_CTL_SEND_BUSY |
+				   (has_aux_irq ? DP_AUX_CH_CTL_INTERRUPT : 0) |
+				   DP_AUX_CH_CTL_TIME_OUT_400us |
+				   (send_bytes << DP_AUX_CH_CTL_MESSAGE_SIZE_SHIFT) |
+				   (precharge << DP_AUX_CH_CTL_PRECHARGE_2US_SHIFT) |
+				   (aux_clock_divider << DP_AUX_CH_CTL_BIT_CLOCK_2X_SHIFT) |
+				   DP_AUX_CH_CTL_DONE |
+				   DP_AUX_CH_CTL_TIME_OUT_ERROR |
+				   DP_AUX_CH_CTL_RECEIVE_ERROR);
+
+			status = intel_dp_aux_wait_done(intel_dp, has_aux_irq);
+
+			/* Clear done status and any errors */
+			I915_WRITE(ch_ctl,
+				   status |
+				   DP_AUX_CH_CTL_DONE |
+				   DP_AUX_CH_CTL_TIME_OUT_ERROR |
+				   DP_AUX_CH_CTL_RECEIVE_ERROR);
+
+			if (status & (DP_AUX_CH_CTL_TIME_OUT_ERROR |
+				      DP_AUX_CH_CTL_RECEIVE_ERROR))
+				continue;
+			if (status & DP_AUX_CH_CTL_DONE)
+				break;
+		}
 		if (status & DP_AUX_CH_CTL_DONE)
 			break;
 	}
@@ -416,6 +436,7 @@ intel_dp_aux_ch(struct intel_dp *intel_dp,
 	ret = recv_bytes;
 out:
 	pm_qos_update_request(&dev_priv->pm_qos, PM_QOS_DEFAULT_VALUE);
+	intel_aux_display_runtime_put(dev_priv);
 
 	return ret;
 }
@@ -567,7 +588,18 @@ intel_dp_i2c_aux_ch(struct i2c_adapter *adapter, int mode,
 			DRM_DEBUG_KMS("aux_ch native nack\n");
 			return -EREMOTEIO;
 		case AUX_NATIVE_REPLY_DEFER:
-			udelay(100);
+			/*
+			 * For now, just give more slack to branch devices. We
+			 * could check the DPCD for I2C bit rate capabilities,
+			 * and if available, adjust the interval. We could also
+			 * be more careful with DP-to-Legacy adapters where a
+			 * long legacy cable may force very low I2C bit rates.
+			 */
+			if (intel_dp->dpcd[DP_DOWNSTREAMPORT_PRESENT] &
+			    DP_DWN_STRM_PORT_PRESENT)
+				usleep_range(500, 600);
+			else
+				usleep_range(300, 400);
 			continue;
 		default:
 			DRM_ERROR("aux_ch invalid native reply 0x%02x\n",
@@ -710,8 +742,11 @@ intel_dp_compute_config(struct intel_encoder *encoder,
 	/* Walk through all bpp values. Luckily they're all nicely spaced with 2
 	 * bpc in between. */
 	bpp = pipe_config->pipe_bpp;
-	if (is_edp(intel_dp) && dev_priv->vbt.edp_bpp)
+	if (is_edp(intel_dp) && dev_priv->vbt.edp_bpp) {
+		DRM_DEBUG_KMS("clamping bpp for eDP panel to BIOS-provided %i\n",
+			      dev_priv->vbt.edp_bpp);
 		bpp = min_t(int, bpp, dev_priv->vbt.edp_bpp);
+	}
 
 	for (; bpp >= 6*3; bpp -= 2*3) {
 		mode_rate = intel_dp_link_required(adjusted_mode->clock, bpp);
@@ -812,15 +847,14 @@ static void ironlake_set_pll_cpu_edp(struct intel_dp *intel_dp)
 	udelay(500);
 }
 
-static void
-intel_dp_mode_set(struct drm_encoder *encoder, struct drm_display_mode *mode,
-		  struct drm_display_mode *adjusted_mode)
+static void intel_dp_mode_set(struct intel_encoder *encoder)
 {
-	struct drm_device *dev = encoder->dev;
+	struct drm_device *dev = encoder->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
+	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
 	enum port port = dp_to_dig_port(intel_dp)->port;
-	struct intel_crtc *crtc = to_intel_crtc(encoder->crtc);
+	struct intel_crtc *crtc = to_intel_crtc(encoder->base.crtc);
+	struct drm_display_mode *adjusted_mode = &crtc->config.adjusted_mode;
 
 	/*
 	 * There are four kinds of DP registers:
@@ -852,7 +886,7 @@ intel_dp_mode_set(struct drm_encoder *encoder, struct drm_display_mode *mode,
 		DRM_DEBUG_DRIVER("Enabling DP audio on pipe %c\n",
 				 pipe_name(crtc->pipe));
 		intel_dp->DP |= DP_AUDIO_OUTPUT_ENABLE;
-		intel_write_eld(encoder, adjusted_mode);
+		intel_write_eld(&encoder->base, adjusted_mode);
 	}
 
 	intel_dp_init_link_config(intel_dp);
@@ -1360,6 +1394,275 @@ static void intel_dp_get_config(struct intel_encoder *encoder,
 	}
 
 	pipe_config->adjusted_mode.flags |= flags;
+
+	if (dp_to_dig_port(intel_dp)->port == PORT_A) {
+		if ((I915_READ(DP_A) & DP_PLL_FREQ_MASK) == DP_PLL_FREQ_160MHZ)
+			pipe_config->port_clock = 162000;
+		else
+			pipe_config->port_clock = 270000;
+	}
+}
+
+static bool is_edp_psr(struct intel_dp *intel_dp)
+{
+	return is_edp(intel_dp) &&
+		intel_dp->psr_dpcd[0] & DP_PSR_IS_SUPPORTED;
+}
+
+static bool intel_edp_is_psr_enabled(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	if (!IS_HASWELL(dev))
+		return false;
+
+	return I915_READ(EDP_PSR_CTL) & EDP_PSR_ENABLE;
+}
+
+static void intel_edp_psr_write_vsc(struct intel_dp *intel_dp,
+				    struct edp_vsc_psr *vsc_psr)
+{
+	struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp);
+	struct drm_device *dev = dig_port->base.base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_crtc *crtc = to_intel_crtc(dig_port->base.base.crtc);
+	u32 ctl_reg = HSW_TVIDEO_DIP_CTL(crtc->config.cpu_transcoder);
+	u32 data_reg = HSW_TVIDEO_DIP_VSC_DATA(crtc->config.cpu_transcoder);
+	uint32_t *data = (uint32_t *) vsc_psr;
+	unsigned int i;
+
+	/* As per BSPec (Pipe Video Data Island Packet), we need to disable
+	   the video DIP being updated before program video DIP data buffer
+	   registers for DIP being updated. */
+	I915_WRITE(ctl_reg, 0);
+	POSTING_READ(ctl_reg);
+
+	for (i = 0; i < VIDEO_DIP_VSC_DATA_SIZE; i += 4) {
+		if (i < sizeof(struct edp_vsc_psr))
+			I915_WRITE(data_reg + i, *data++);
+		else
+			I915_WRITE(data_reg + i, 0);
+	}
+
+	I915_WRITE(ctl_reg, VIDEO_DIP_ENABLE_VSC_HSW);
+	POSTING_READ(ctl_reg);
+}
+
+static void intel_edp_psr_setup(struct intel_dp *intel_dp)
+{
+	struct drm_device *dev = intel_dp_to_dev(intel_dp);
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct edp_vsc_psr psr_vsc;
+
+	if (intel_dp->psr_setup_done)
+		return;
+
+	/* Prepare VSC packet as per EDP 1.3 spec, Table 3.10 */
+	memset(&psr_vsc, 0, sizeof(psr_vsc));
+	psr_vsc.sdp_header.HB0 = 0;
+	psr_vsc.sdp_header.HB1 = 0x7;
+	psr_vsc.sdp_header.HB2 = 0x2;
+	psr_vsc.sdp_header.HB3 = 0x8;
+	intel_edp_psr_write_vsc(intel_dp, &psr_vsc);
+
+	/* Avoid continuous PSR exit by masking memup and hpd */
+	I915_WRITE(EDP_PSR_DEBUG_CTL, EDP_PSR_DEBUG_MASK_MEMUP |
+		   EDP_PSR_DEBUG_MASK_HPD | EDP_PSR_DEBUG_MASK_LPSP);
+
+	intel_dp->psr_setup_done = true;
+}
+
+static void intel_edp_psr_enable_sink(struct intel_dp *intel_dp)
+{
+	struct drm_device *dev = intel_dp_to_dev(intel_dp);
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	uint32_t aux_clock_divider = get_aux_clock_divider(intel_dp, 0);
+	int precharge = 0x3;
+	int msg_size = 5;       /* Header(4) + Message(1) */
+
+	/* Enable PSR in sink */
+	if (intel_dp->psr_dpcd[1] & DP_PSR_NO_TRAIN_ON_EXIT)
+		intel_dp_aux_native_write_1(intel_dp, DP_PSR_EN_CFG,
+					    DP_PSR_ENABLE &
+					    ~DP_PSR_MAIN_LINK_ACTIVE);
+	else
+		intel_dp_aux_native_write_1(intel_dp, DP_PSR_EN_CFG,
+					    DP_PSR_ENABLE |
+					    DP_PSR_MAIN_LINK_ACTIVE);
+
+	/* Setup AUX registers */
+	I915_WRITE(EDP_PSR_AUX_DATA1, EDP_PSR_DPCD_COMMAND);
+	I915_WRITE(EDP_PSR_AUX_DATA2, EDP_PSR_DPCD_NORMAL_OPERATION);
+	I915_WRITE(EDP_PSR_AUX_CTL,
+		   DP_AUX_CH_CTL_TIME_OUT_400us |
+		   (msg_size << DP_AUX_CH_CTL_MESSAGE_SIZE_SHIFT) |
+		   (precharge << DP_AUX_CH_CTL_PRECHARGE_2US_SHIFT) |
+		   (aux_clock_divider << DP_AUX_CH_CTL_BIT_CLOCK_2X_SHIFT));
+}
+
+static void intel_edp_psr_enable_source(struct intel_dp *intel_dp)
+{
+	struct drm_device *dev = intel_dp_to_dev(intel_dp);
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	uint32_t max_sleep_time = 0x1f;
+	uint32_t idle_frames = 1;
+	uint32_t val = 0x0;
+
+	if (intel_dp->psr_dpcd[1] & DP_PSR_NO_TRAIN_ON_EXIT) {
+		val |= EDP_PSR_LINK_STANDBY;
+		val |= EDP_PSR_TP2_TP3_TIME_0us;
+		val |= EDP_PSR_TP1_TIME_0us;
+		val |= EDP_PSR_SKIP_AUX_EXIT;
+	} else
+		val |= EDP_PSR_LINK_DISABLE;
+
+	I915_WRITE(EDP_PSR_CTL, val |
+		   EDP_PSR_MIN_LINK_ENTRY_TIME_8_LINES |
+		   max_sleep_time << EDP_PSR_MAX_SLEEP_TIME_SHIFT |
+		   idle_frames << EDP_PSR_IDLE_FRAME_SHIFT |
+		   EDP_PSR_ENABLE);
+}
+
+static bool intel_edp_psr_match_conditions(struct intel_dp *intel_dp)
+{
+	struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp);
+	struct drm_device *dev = dig_port->base.base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_crtc *crtc = dig_port->base.base.crtc;
+	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
+	struct drm_i915_gem_object *obj = to_intel_framebuffer(crtc->fb)->obj;
+	struct intel_encoder *intel_encoder = &dp_to_dig_port(intel_dp)->base;
+
+	if (!IS_HASWELL(dev)) {
+		DRM_DEBUG_KMS("PSR not supported on this platform\n");
+		dev_priv->no_psr_reason = PSR_NO_SOURCE;
+		return false;
+	}
+
+	if ((intel_encoder->type != INTEL_OUTPUT_EDP) ||
+	    (dig_port->port != PORT_A)) {
+		DRM_DEBUG_KMS("HSW ties PSR to DDI A (eDP)\n");
+		dev_priv->no_psr_reason = PSR_HSW_NOT_DDIA;
+		return false;
+	}
+
+	if (!is_edp_psr(intel_dp)) {
+		DRM_DEBUG_KMS("PSR not supported by this panel\n");
+		dev_priv->no_psr_reason = PSR_NO_SINK;
+		return false;
+	}
+
+	if (!i915_enable_psr) {
+		DRM_DEBUG_KMS("PSR disable by flag\n");
+		dev_priv->no_psr_reason = PSR_MODULE_PARAM;
+		return false;
+	}
+
+	crtc = dig_port->base.base.crtc;
+	if (crtc == NULL) {
+		DRM_DEBUG_KMS("crtc not active for PSR\n");
+		dev_priv->no_psr_reason = PSR_CRTC_NOT_ACTIVE;
+		return false;
+	}
+
+	intel_crtc = to_intel_crtc(crtc);
+	if (!intel_crtc->active || !crtc->fb || !crtc->mode.clock) {
+		DRM_DEBUG_KMS("crtc not active for PSR\n");
+		dev_priv->no_psr_reason = PSR_CRTC_NOT_ACTIVE;
+		return false;
+	}
+
+	obj = to_intel_framebuffer(crtc->fb)->obj;
+	if (obj->tiling_mode != I915_TILING_X ||
+	    obj->fence_reg == I915_FENCE_REG_NONE) {
+		DRM_DEBUG_KMS("PSR condition failed: fb not tiled or fenced\n");
+		dev_priv->no_psr_reason = PSR_NOT_TILED;
+		return false;
+	}
+
+	if (I915_READ(SPRCTL(intel_crtc->pipe)) & SPRITE_ENABLE) {
+		DRM_DEBUG_KMS("PSR condition failed: Sprite is Enabled\n");
+		dev_priv->no_psr_reason = PSR_SPRITE_ENABLED;
+		return false;
+	}
+
+	if (I915_READ(HSW_STEREO_3D_CTL(intel_crtc->config.cpu_transcoder)) &
+	    S3D_ENABLE) {
+		DRM_DEBUG_KMS("PSR condition failed: Stereo 3D is Enabled\n");
+		dev_priv->no_psr_reason = PSR_S3D_ENABLED;
+		return false;
+	}
+
+	if (crtc->mode.flags & DRM_MODE_FLAG_INTERLACE) {
+		DRM_DEBUG_KMS("PSR condition failed: Interlaced is Enabled\n");
+		dev_priv->no_psr_reason = PSR_INTERLACED_ENABLED;
+		return false;
+	}
+
+	return true;
+}
+
+static void intel_edp_psr_do_enable(struct intel_dp *intel_dp)
+{
+	struct drm_device *dev = intel_dp_to_dev(intel_dp);
+
+	if (!intel_edp_psr_match_conditions(intel_dp) ||
+	    intel_edp_is_psr_enabled(dev))
+		return;
+
+	/* Setup PSR once */
+	intel_edp_psr_setup(intel_dp);
+
+	/* Enable PSR on the panel */
+	intel_edp_psr_enable_sink(intel_dp);
+
+	/* Enable PSR on the host */
+	intel_edp_psr_enable_source(intel_dp);
+}
+
+void intel_edp_psr_enable(struct intel_dp *intel_dp)
+{
+	struct drm_device *dev = intel_dp_to_dev(intel_dp);
+
+	if (intel_edp_psr_match_conditions(intel_dp) &&
+	    !intel_edp_is_psr_enabled(dev))
+		intel_edp_psr_do_enable(intel_dp);
+}
+
+void intel_edp_psr_disable(struct intel_dp *intel_dp)
+{
+	struct drm_device *dev = intel_dp_to_dev(intel_dp);
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	if (!intel_edp_is_psr_enabled(dev))
+		return;
+
+	I915_WRITE(EDP_PSR_CTL, I915_READ(EDP_PSR_CTL) & ~EDP_PSR_ENABLE);
+
+	/* Wait till PSR is idle */
+	if (_wait_for((I915_READ(EDP_PSR_STATUS_CTL) &
+		       EDP_PSR_STATUS_STATE_MASK) == 0, 2000, 10))
+		DRM_ERROR("Timed out waiting for PSR Idle State\n");
+}
+
+void intel_edp_psr_update(struct drm_device *dev)
+{
+	struct intel_encoder *encoder;
+	struct intel_dp *intel_dp = NULL;
+
+	list_for_each_entry(encoder, &dev->mode_config.encoder_list, base.head)
+		if (encoder->type == INTEL_OUTPUT_EDP) {
+			intel_dp = enc_to_intel_dp(&encoder->base);
+
+			if (!is_edp_psr(intel_dp))
+				return;
+
+			if (!intel_edp_psr_match_conditions(intel_dp))
+				intel_edp_psr_disable(intel_dp);
+			else
+				if (!intel_edp_is_psr_enabled(dev))
+					intel_edp_psr_do_enable(intel_dp);
+		}
 }
 
 static void intel_disable_dp(struct intel_encoder *encoder)
@@ -1411,47 +1714,50 @@ static void intel_enable_dp(struct intel_encoder *encoder)
 	intel_dp_complete_link_train(intel_dp);
 	intel_dp_stop_link_train(intel_dp);
 	ironlake_edp_backlight_on(intel_dp);
+}
 
-	if (IS_VALLEYVIEW(dev)) {
-		struct intel_digital_port *dport =
-			enc_to_dig_port(&encoder->base);
-		int channel = vlv_dport_to_channel(dport);
-
-		vlv_wait_port_ready(dev_priv, channel);
-	}
+static void vlv_enable_dp(struct intel_encoder *encoder)
+{
 }
 
 static void intel_pre_enable_dp(struct intel_encoder *encoder)
 {
 	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
 	struct intel_digital_port *dport = dp_to_dig_port(intel_dp);
+
+	if (dport->port == PORT_A)
+		ironlake_edp_pll_on(intel_dp);
+}
+
+static void vlv_pre_enable_dp(struct intel_encoder *encoder)
+{
+	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
+	struct intel_digital_port *dport = dp_to_dig_port(intel_dp);
 	struct drm_device *dev = encoder->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_crtc *intel_crtc = to_intel_crtc(encoder->base.crtc);
+	int port = vlv_dport_to_channel(dport);
+	int pipe = intel_crtc->pipe;
+	u32 val;
 
-	if (dport->port == PORT_A && !IS_VALLEYVIEW(dev))
-		ironlake_edp_pll_on(intel_dp);
+	mutex_lock(&dev_priv->dpio_lock);
 
-	if (IS_VALLEYVIEW(dev)) {
-		struct intel_crtc *intel_crtc =
-			to_intel_crtc(encoder->base.crtc);
-		int port = vlv_dport_to_channel(dport);
-		int pipe = intel_crtc->pipe;
-		u32 val;
-
-		val = vlv_dpio_read(dev_priv, DPIO_DATA_LANE_A(port));
-		val = 0;
-		if (pipe)
-			val |= (1<<21);
-		else
-			val &= ~(1<<21);
-		val |= 0x001000c4;
-		vlv_dpio_write(dev_priv, DPIO_DATA_CHANNEL(port), val);
+	val = vlv_dpio_read(dev_priv, DPIO_DATA_LANE_A(port));
+	val = 0;
+	if (pipe)
+		val |= (1<<21);
+	else
+		val &= ~(1<<21);
+	val |= 0x001000c4;
+	vlv_dpio_write(dev_priv, DPIO_DATA_CHANNEL(port), val);
+	vlv_dpio_write(dev_priv, DPIO_PCS_CLOCKBUF0(port), 0x00760018);
+	vlv_dpio_write(dev_priv, DPIO_PCS_CLOCKBUF8(port), 0x00400888);
 
-		vlv_dpio_write(dev_priv, DPIO_PCS_CLOCKBUF0(port),
-				 0x00760018);
-		vlv_dpio_write(dev_priv, DPIO_PCS_CLOCKBUF8(port),
-				 0x00400888);
-	}
+	mutex_unlock(&dev_priv->dpio_lock);
+
+	intel_enable_dp(encoder);
+
+	vlv_wait_port_ready(dev_priv, port);
 }
 
 static void intel_dp_pre_pll_enable(struct intel_encoder *encoder)
@@ -1465,6 +1771,7 @@ static void intel_dp_pre_pll_enable(struct intel_encoder *encoder)
 		return;
 
 	/* Program Tx lane resets to default */
+	mutex_lock(&dev_priv->dpio_lock);
 	vlv_dpio_write(dev_priv, DPIO_PCS_TX(port),
 			 DPIO_PCS_TX_LANE2_RESET |
 			 DPIO_PCS_TX_LANE1_RESET);
@@ -1478,6 +1785,7 @@ static void intel_dp_pre_pll_enable(struct intel_encoder *encoder)
 	vlv_dpio_write(dev_priv, DPIO_PCS_STAGGER1(port), 0x00750f00);
 	vlv_dpio_write(dev_priv, DPIO_TX_CTL(port), 0x00001500);
 	vlv_dpio_write(dev_priv, DPIO_TX_LANE(port), 0x40400000);
+	mutex_unlock(&dev_priv->dpio_lock);
 }
 
 /*
@@ -1689,6 +1997,7 @@ static uint32_t intel_vlv_signal_levels(struct intel_dp *intel_dp)
 		return 0;
 	}
 
+	mutex_lock(&dev_priv->dpio_lock);
 	vlv_dpio_write(dev_priv, DPIO_TX_OCALINIT(port), 0x00000000);
 	vlv_dpio_write(dev_priv, DPIO_TX_SWING_CTL4(port), demph_reg_value);
 	vlv_dpio_write(dev_priv, DPIO_TX_SWING_CTL2(port),
@@ -1697,6 +2006,7 @@ static uint32_t intel_vlv_signal_levels(struct intel_dp *intel_dp)
 	vlv_dpio_write(dev_priv, DPIO_PCS_STAGGER0(port), 0x00030000);
 	vlv_dpio_write(dev_priv, DPIO_PCS_CTL_OVER1(port), preemph_reg_value);
 	vlv_dpio_write(dev_priv, DPIO_TX_OCALINIT(port), 0x80000000);
+	mutex_unlock(&dev_priv->dpio_lock);
 
 	return 0;
 }
@@ -2030,7 +2340,6 @@ intel_dp_start_link_train(struct intel_dp *intel_dp)
 	struct drm_device *dev = encoder->dev;
 	int i;
 	uint8_t voltage;
-	bool clock_recovery = false;
 	int voltage_tries, loop_tries;
 	uint32_t DP = intel_dp->DP;
 
@@ -2048,7 +2357,6 @@ intel_dp_start_link_train(struct intel_dp *intel_dp)
 	voltage = 0xff;
 	voltage_tries = 0;
 	loop_tries = 0;
-	clock_recovery = false;
 	for (;;) {
 		/* Use intel_dp->train_set[0] to set the voltage and pre emphasis values */
 		uint8_t	    link_status[DP_LINK_STATUS_SIZE];
@@ -2069,7 +2377,6 @@ intel_dp_start_link_train(struct intel_dp *intel_dp)
 
 		if (drm_dp_clock_recovery_ok(link_status, intel_dp->lane_count)) {
 			DRM_DEBUG_KMS("clock recovery OK\n");
-			clock_recovery = true;
 			break;
 		}
 
@@ -2275,6 +2582,13 @@ intel_dp_get_dpcd(struct intel_dp *intel_dp)
 	if (intel_dp->dpcd[DP_DPCD_REV] == 0)
 		return false; /* DPCD not present */
 
+	/* Check if the panel supports PSR */
+	memset(intel_dp->psr_dpcd, 0, sizeof(intel_dp->psr_dpcd));
+	intel_dp_aux_native_read_retry(intel_dp, DP_PSR_SUPPORT,
+				       intel_dp->psr_dpcd,
+				       sizeof(intel_dp->psr_dpcd));
+	if (is_edp_psr(intel_dp))
+		DRM_DEBUG_KMS("Detected EDP PSR Panel.\n");
 	if (!(intel_dp->dpcd[DP_DOWNSTREAMPORT_PRESENT] &
 	      DP_DWN_STRM_PORT_PRESENT))
 		return true; /* native DP sink */
@@ -2542,6 +2856,9 @@ intel_dp_detect(struct drm_connector *connector, bool force)
 	enum drm_connector_status status;
 	struct edid *edid = NULL;
 
+	DRM_DEBUG_KMS("[CONNECTOR:%d:%s]\n",
+		      connector->base.id, drm_get_connector_name(connector));
+
 	intel_dp->has_audio = false;
 
 	if (HAS_PCH_SPLIT(dev))
@@ -2735,10 +3052,6 @@ void intel_dp_encoder_destroy(struct drm_encoder *encoder)
 	kfree(intel_dig_port);
 }
 
-static const struct drm_encoder_helper_funcs intel_dp_helper_funcs = {
-	.mode_set = intel_dp_mode_set,
-};
-
 static const struct drm_connector_funcs intel_dp_connector_funcs = {
 	.dpms = intel_connector_dpms,
 	.detect = intel_dp_detect,
@@ -3166,6 +3479,8 @@ intel_dp_init_connector(struct intel_digital_port *intel_dig_port,
 	WARN(error, "intel_dp_i2c_init failed with error %d for port %c\n",
 	     error, port_name(port));
 
+	intel_dp->psr_setup_done = false;
+
 	if (!intel_edp_init_connector(intel_dp, intel_connector)) {
 		i2c_del_adapter(&intel_dp->adapter);
 		if (is_edp(intel_dp)) {
@@ -3216,17 +3531,21 @@ intel_dp_init(struct drm_device *dev, int output_reg, enum port port)
 
 	drm_encoder_init(dev, &intel_encoder->base, &intel_dp_enc_funcs,
 			 DRM_MODE_ENCODER_TMDS);
-	drm_encoder_helper_add(&intel_encoder->base, &intel_dp_helper_funcs);
 
 	intel_encoder->compute_config = intel_dp_compute_config;
-	intel_encoder->enable = intel_enable_dp;
-	intel_encoder->pre_enable = intel_pre_enable_dp;
+	intel_encoder->mode_set = intel_dp_mode_set;
 	intel_encoder->disable = intel_disable_dp;
 	intel_encoder->post_disable = intel_post_disable_dp;
 	intel_encoder->get_hw_state = intel_dp_get_hw_state;
 	intel_encoder->get_config = intel_dp_get_config;
-	if (IS_VALLEYVIEW(dev))
+	if (IS_VALLEYVIEW(dev)) {
 		intel_encoder->pre_pll_enable = intel_dp_pre_pll_enable;
+		intel_encoder->pre_enable = vlv_pre_enable_dp;
+		intel_encoder->enable = vlv_enable_dp;
+	} else {
+		intel_encoder->pre_enable = intel_pre_enable_dp;
+		intel_encoder->enable = intel_enable_dp;
+	}
 
 	intel_dig_port->port = port;
 	intel_dig_port->dp.output_reg = output_reg;
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index b7d6e09456ce..9b7b68fd5d47 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -26,6 +26,7 @@
 #define __INTEL_DRV_H__
 
 #include <linux/i2c.h>
+#include <linux/hdmi.h>
 #include <drm/i915_drm.h>
 #include "i915_drv.h"
 #include <drm/drm_crtc.h>
@@ -208,10 +209,6 @@ struct intel_crtc_config {
 
 	struct drm_display_mode requested_mode;
 	struct drm_display_mode adjusted_mode;
-	/* This flag must be set by the encoder's compute_config callback if it
-	 * changes the crtc timings in the mode to prevent the crtc fixup from
-	 * overwriting them.  Currently only lvds needs that. */
-	bool timings_set;
 	/* Whether to set up the PCH/FDI. Note that we never allow sharing
 	 * between pch encoders and cpu encoders. */
 	bool has_pch_encoder;
@@ -283,6 +280,7 @@ struct intel_crtc_config {
 	struct {
 		u32 pos;
 		u32 size;
+		bool enabled;
 	} pch_pfit;
 
 	/* FDI configuration, only valid if has_pch_encoder is set. */
@@ -334,6 +332,13 @@ struct intel_crtc {
 	bool pch_fifo_underrun_disabled;
 };
 
+struct intel_plane_wm_parameters {
+	uint32_t horiz_pixels;
+	uint8_t bytes_per_pixel;
+	bool enabled;
+	bool scaled;
+};
+
 struct intel_plane {
 	struct drm_plane base;
 	int plane;
@@ -352,20 +357,18 @@ struct intel_plane {
 	 * as the other pieces of the struct may not reflect the values we want
 	 * for the watermark calculations. Currently only Haswell uses this.
 	 */
-	struct {
-		bool enable;
-		uint8_t bytes_per_pixel;
-		uint32_t horiz_pixels;
-	} wm;
+	struct intel_plane_wm_parameters wm;
 
 	void (*update_plane)(struct drm_plane *plane,
+			     struct drm_crtc *crtc,
 			     struct drm_framebuffer *fb,
 			     struct drm_i915_gem_object *obj,
 			     int crtc_x, int crtc_y,
 			     unsigned int crtc_w, unsigned int crtc_h,
 			     uint32_t x, uint32_t y,
 			     uint32_t src_w, uint32_t src_h);
-	void (*disable_plane)(struct drm_plane *plane);
+	void (*disable_plane)(struct drm_plane *plane,
+			      struct drm_crtc *crtc);
 	int (*update_colorkey)(struct drm_plane *plane,
 			       struct drm_intel_sprite_colorkey *key);
 	void (*get_colorkey)(struct drm_plane *plane,
@@ -397,66 +400,6 @@ struct cxsr_latency {
 #define to_intel_framebuffer(x) container_of(x, struct intel_framebuffer, base)
 #define to_intel_plane(x) container_of(x, struct intel_plane, base)
 
-#define DIP_HEADER_SIZE	5
-
-#define DIP_TYPE_AVI    0x82
-#define DIP_VERSION_AVI 0x2
-#define DIP_LEN_AVI     13
-#define DIP_AVI_PR_1    0
-#define DIP_AVI_PR_2    1
-#define DIP_AVI_RGB_QUANT_RANGE_DEFAULT	(0 << 2)
-#define DIP_AVI_RGB_QUANT_RANGE_LIMITED	(1 << 2)
-#define DIP_AVI_RGB_QUANT_RANGE_FULL	(2 << 2)
-
-#define DIP_TYPE_SPD	0x83
-#define DIP_VERSION_SPD	0x1
-#define DIP_LEN_SPD	25
-#define DIP_SPD_UNKNOWN	0
-#define DIP_SPD_DSTB	0x1
-#define DIP_SPD_DVDP	0x2
-#define DIP_SPD_DVHS	0x3
-#define DIP_SPD_HDDVR	0x4
-#define DIP_SPD_DVC	0x5
-#define DIP_SPD_DSC	0x6
-#define DIP_SPD_VCD	0x7
-#define DIP_SPD_GAME	0x8
-#define DIP_SPD_PC	0x9
-#define DIP_SPD_BD	0xa
-#define DIP_SPD_SCD	0xb
-
-struct dip_infoframe {
-	uint8_t type;		/* HB0 */
-	uint8_t ver;		/* HB1 */
-	uint8_t len;		/* HB2 - body len, not including checksum */
-	uint8_t ecc;		/* Header ECC */
-	uint8_t checksum;	/* PB0 */
-	union {
-		struct {
-			/* PB1 - Y 6:5, A 4:4, B 3:2, S 1:0 */
-			uint8_t Y_A_B_S;
-			/* PB2 - C 7:6, M 5:4, R 3:0 */
-			uint8_t C_M_R;
-			/* PB3 - ITC 7:7, EC 6:4, Q 3:2, SC 1:0 */
-			uint8_t ITC_EC_Q_SC;
-			/* PB4 - VIC 6:0 */
-			uint8_t VIC;
-			/* PB5 - YQ 7:6, CN 5:4, PR 3:0 */
-			uint8_t YQ_CN_PR;
-			/* PB6 to PB13 */
-			uint16_t top_bar_end;
-			uint16_t bottom_bar_start;
-			uint16_t left_bar_end;
-			uint16_t right_bar_start;
-		} __attribute__ ((packed)) avi;
-		struct {
-			uint8_t vn[8];
-			uint8_t pd[16];
-			uint8_t sdi;
-		} __attribute__ ((packed)) spd;
-		uint8_t payload[27];
-	} __attribute__ ((packed)) body;
-} __attribute__((packed));
-
 struct intel_hdmi {
 	u32 hdmi_reg;
 	int ddc_bus;
@@ -467,7 +410,8 @@ struct intel_hdmi {
 	enum hdmi_force_audio force_audio;
 	bool rgb_quant_range_selectable;
 	void (*write_infoframe)(struct drm_encoder *encoder,
-				struct dip_infoframe *frame);
+				enum hdmi_infoframe_type type,
+				const uint8_t *frame, ssize_t len);
 	void (*set_infoframes)(struct drm_encoder *encoder,
 			       struct drm_display_mode *adjusted_mode);
 };
@@ -487,6 +431,7 @@ struct intel_dp {
 	uint8_t link_bw;
 	uint8_t lane_count;
 	uint8_t dpcd[DP_RECEIVER_CAP_SIZE];
+	uint8_t psr_dpcd[EDP_PSR_RECEIVER_CAP_SIZE];
 	uint8_t downstream_ports[DP_MAX_DOWNSTREAM_PORTS];
 	struct i2c_adapter adapter;
 	struct i2c_algo_dp_aux_data algo;
@@ -498,6 +443,7 @@ struct intel_dp {
 	int backlight_off_delay;
 	struct delayed_work panel_vdd_work;
 	bool want_panel_vdd;
+	bool psr_setup_done;
 	struct intel_connector *attached_connector;
 };
 
@@ -549,13 +495,6 @@ struct intel_unpin_work {
 	bool enable_stall_check;
 };
 
-struct intel_fbc_work {
-	struct delayed_work work;
-	struct drm_crtc *crtc;
-	struct drm_framebuffer *fb;
-	int interval;
-};
-
 int intel_pch_rawclk(struct drm_device *dev);
 
 int intel_connector_update_modes(struct drm_connector *connector,
@@ -574,7 +513,6 @@ extern void intel_hdmi_init_connector(struct intel_digital_port *intel_dig_port,
 extern struct intel_hdmi *enc_to_intel_hdmi(struct drm_encoder *encoder);
 extern bool intel_hdmi_compute_config(struct intel_encoder *encoder,
 				      struct intel_crtc_config *pipe_config);
-extern void intel_dip_infoframe_csum(struct dip_infoframe *avi_if);
 extern bool intel_sdvo_init(struct drm_device *dev, uint32_t sdvo_reg,
 			    bool is_sdvob);
 extern void intel_dvo_init(struct drm_device *dev);
@@ -614,7 +552,7 @@ extern int intel_panel_init(struct intel_panel *panel,
 			    struct drm_display_mode *fixed_mode);
 extern void intel_panel_fini(struct intel_panel *panel);
 
-extern void intel_fixed_panel_mode(struct drm_display_mode *fixed_mode,
+extern void intel_fixed_panel_mode(const struct drm_display_mode *fixed_mode,
 				   struct drm_display_mode *adjusted_mode);
 extern void intel_pch_panel_fitting(struct intel_crtc *crtc,
 				    struct intel_crtc_config *pipe_config,
@@ -639,14 +577,10 @@ struct intel_set_config {
 	bool mode_changed;
 };
 
-extern int intel_set_mode(struct drm_crtc *crtc, struct drm_display_mode *mode,
-			  int x, int y, struct drm_framebuffer *old_fb);
-extern void intel_modeset_disable(struct drm_device *dev);
 extern void intel_crtc_restore_mode(struct drm_crtc *crtc);
 extern void intel_crtc_load_lut(struct drm_crtc *crtc);
 extern void intel_crtc_update_dpms(struct drm_crtc *crtc);
 extern void intel_encoder_destroy(struct drm_encoder *encoder);
-extern void intel_encoder_dpms(struct intel_encoder *encoder, int mode);
 extern void intel_connector_dpms(struct drm_connector *, int mode);
 extern bool intel_connector_get_hw_state(struct intel_connector *connector);
 extern void intel_modeset_check_state(struct drm_device *dev);
@@ -712,12 +646,10 @@ extern bool intel_get_load_detect_pipe(struct drm_connector *connector,
 extern void intel_release_load_detect_pipe(struct drm_connector *connector,
 					   struct intel_load_detect_pipe *old);
 
-extern void intelfb_restore(void);
 extern void intel_crtc_fb_gamma_set(struct drm_crtc *crtc, u16 red, u16 green,
 				    u16 blue, int regno);
 extern void intel_crtc_fb_gamma_get(struct drm_crtc *crtc, u16 *red, u16 *green,
 				    u16 *blue, int regno);
-extern void intel_enable_clock_gating(struct drm_device *dev);
 
 extern int intel_pin_and_fence_fb_obj(struct drm_device *dev,
 				      struct drm_i915_gem_object *obj,
@@ -728,6 +660,7 @@ extern int intel_framebuffer_init(struct drm_device *dev,
 				  struct intel_framebuffer *ifb,
 				  struct drm_mode_fb_cmd2 *mode_cmd,
 				  struct drm_i915_gem_object *obj);
+extern void intel_framebuffer_fini(struct intel_framebuffer *fb);
 extern int intel_fbdev_init(struct drm_device *dev);
 extern void intel_fbdev_initial_config(struct drm_device *dev);
 extern void intel_fbdev_fini(struct drm_device *dev);
@@ -747,6 +680,22 @@ extern int intel_overlay_attrs(struct drm_device *dev, void *data,
 extern void intel_fb_output_poll_changed(struct drm_device *dev);
 extern void intel_fb_restore_mode(struct drm_device *dev);
 
+struct intel_shared_dpll *
+intel_crtc_to_shared_dpll(struct intel_crtc *crtc);
+
+void assert_shared_dpll(struct drm_i915_private *dev_priv,
+			struct intel_shared_dpll *pll,
+			bool state);
+#define assert_shared_dpll_enabled(d, p) assert_shared_dpll(d, p, true)
+#define assert_shared_dpll_disabled(d, p) assert_shared_dpll(d, p, false)
+void assert_pll(struct drm_i915_private *dev_priv,
+		enum pipe pipe, bool state);
+#define assert_pll_enabled(d, p) assert_pll(d, p, true)
+#define assert_pll_disabled(d, p) assert_pll(d, p, false)
+void assert_fdi_rx_pll(struct drm_i915_private *dev_priv,
+		       enum pipe pipe, bool state);
+#define assert_fdi_rx_pll_enabled(d, p) assert_fdi_rx_pll(d, p, true)
+#define assert_fdi_rx_pll_disabled(d, p) assert_fdi_rx_pll(d, p, false)
 extern void assert_pipe(struct drm_i915_private *dev_priv, enum pipe pipe,
 			bool state);
 #define assert_pipe_enabled(d, p) assert_pipe(d, p, true)
@@ -762,9 +711,10 @@ extern void intel_ddi_init(struct drm_device *dev, enum port port);
 
 /* For use by IVB LP watermark workaround in intel_sprite.c */
 extern void intel_update_watermarks(struct drm_device *dev);
-extern void intel_update_sprite_watermarks(struct drm_device *dev, int pipe,
-					   uint32_t sprite_width,
-					   int pixel_size, bool enable);
+extern void intel_update_sprite_watermarks(struct drm_plane *plane,
+					   struct drm_crtc *crtc,
+					   uint32_t sprite_width, int pixel_size,
+					   bool enabled, bool scaled);
 
 extern unsigned long intel_gen4_compute_page_offset(int *x, int *y,
 						    unsigned int tiling_mode,
@@ -780,7 +730,6 @@ extern int intel_sprite_get_colorkey(struct drm_device *dev, void *data,
 extern void intel_init_pm(struct drm_device *dev);
 /* FBC */
 extern bool intel_fbc_enabled(struct drm_device *dev);
-extern void intel_enable_fbc(struct drm_crtc *crtc, unsigned long interval);
 extern void intel_update_fbc(struct drm_device *dev);
 /* IPS */
 extern void intel_gpu_ips_init(struct drm_i915_private *dev_priv);
@@ -796,8 +745,8 @@ extern void intel_init_power_well(struct drm_device *dev);
 extern void intel_set_power_well(struct drm_device *dev, bool enable);
 extern void intel_enable_gt_powersave(struct drm_device *dev);
 extern void intel_disable_gt_powersave(struct drm_device *dev);
-extern void gen6_gt_check_fifodbg(struct drm_i915_private *dev_priv);
 extern void ironlake_teardown_rc6(struct drm_device *dev);
+void gen6_update_ring_freq(struct drm_device *dev);
 
 extern bool intel_ddi_get_hw_state(struct intel_encoder *encoder,
 				   enum pipe *pipe);
@@ -825,4 +774,24 @@ extern bool intel_set_pch_fifo_underrun_reporting(struct drm_device *dev,
 						 enum transcoder pch_transcoder,
 						 bool enable);
 
+extern void intel_edp_psr_enable(struct intel_dp *intel_dp);
+extern void intel_edp_psr_disable(struct intel_dp *intel_dp);
+extern void intel_edp_psr_update(struct drm_device *dev);
+extern void hsw_disable_lcpll(struct drm_i915_private *dev_priv,
+			      bool switch_to_fclk, bool allow_power_down);
+extern void hsw_restore_lcpll(struct drm_i915_private *dev_priv);
+extern void ilk_enable_gt_irq(struct drm_i915_private *dev_priv, uint32_t mask);
+extern void ilk_disable_gt_irq(struct drm_i915_private *dev_priv,
+			       uint32_t mask);
+extern void snb_enable_pm_irq(struct drm_i915_private *dev_priv, uint32_t mask);
+extern void snb_disable_pm_irq(struct drm_i915_private *dev_priv,
+			       uint32_t mask);
+extern void hsw_enable_pc8_work(struct work_struct *__work);
+extern void hsw_enable_package_c8(struct drm_i915_private *dev_priv);
+extern void hsw_disable_package_c8(struct drm_i915_private *dev_priv);
+extern void hsw_pc8_disable_interrupts(struct drm_device *dev);
+extern void hsw_pc8_restore_interrupts(struct drm_device *dev);
+extern void intel_aux_display_runtime_get(struct drm_i915_private *dev_priv);
+extern void intel_aux_display_runtime_put(struct drm_i915_private *dev_priv);
+
 #endif /* __INTEL_DRV_H__ */
diff --git a/drivers/gpu/drm/i915/intel_dvo.c b/drivers/gpu/drm/i915/intel_dvo.c
index eb2020eb2b7e..7fa7df546c1e 100644
--- a/drivers/gpu/drm/i915/intel_dvo.c
+++ b/drivers/gpu/drm/i915/intel_dvo.c
@@ -100,15 +100,14 @@ struct intel_dvo {
 	bool panel_wants_dither;
 };
 
-static struct intel_dvo *enc_to_intel_dvo(struct drm_encoder *encoder)
+static struct intel_dvo *enc_to_dvo(struct intel_encoder *encoder)
 {
-	return container_of(encoder, struct intel_dvo, base.base);
+	return container_of(encoder, struct intel_dvo, base);
 }
 
 static struct intel_dvo *intel_attached_dvo(struct drm_connector *connector)
 {
-	return container_of(intel_attached_encoder(connector),
-			    struct intel_dvo, base);
+	return enc_to_dvo(intel_attached_encoder(connector));
 }
 
 static bool intel_dvo_connector_get_hw_state(struct intel_connector *connector)
@@ -123,7 +122,7 @@ static bool intel_dvo_get_hw_state(struct intel_encoder *encoder,
 {
 	struct drm_device *dev = encoder->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_dvo *intel_dvo = enc_to_intel_dvo(&encoder->base);
+	struct intel_dvo *intel_dvo = enc_to_dvo(encoder);
 	u32 tmp;
 
 	tmp = I915_READ(intel_dvo->dev.dvo_reg);
@@ -140,7 +139,7 @@ static void intel_dvo_get_config(struct intel_encoder *encoder,
 				 struct intel_crtc_config *pipe_config)
 {
 	struct drm_i915_private *dev_priv = encoder->base.dev->dev_private;
-	struct intel_dvo *intel_dvo = enc_to_intel_dvo(&encoder->base);
+	struct intel_dvo *intel_dvo = enc_to_dvo(encoder);
 	u32 tmp, flags = 0;
 
 	tmp = I915_READ(intel_dvo->dev.dvo_reg);
@@ -159,7 +158,7 @@ static void intel_dvo_get_config(struct intel_encoder *encoder,
 static void intel_disable_dvo(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = encoder->base.dev->dev_private;
-	struct intel_dvo *intel_dvo = enc_to_intel_dvo(&encoder->base);
+	struct intel_dvo *intel_dvo = enc_to_dvo(encoder);
 	u32 dvo_reg = intel_dvo->dev.dvo_reg;
 	u32 temp = I915_READ(dvo_reg);
 
@@ -171,7 +170,7 @@ static void intel_disable_dvo(struct intel_encoder *encoder)
 static void intel_enable_dvo(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = encoder->base.dev->dev_private;
-	struct intel_dvo *intel_dvo = enc_to_intel_dvo(&encoder->base);
+	struct intel_dvo *intel_dvo = enc_to_dvo(encoder);
 	u32 dvo_reg = intel_dvo->dev.dvo_reg;
 	u32 temp = I915_READ(dvo_reg);
 
@@ -241,11 +240,11 @@ static int intel_dvo_mode_valid(struct drm_connector *connector,
 	return intel_dvo->dev.dev_ops->mode_valid(&intel_dvo->dev, mode);
 }
 
-static bool intel_dvo_mode_fixup(struct drm_encoder *encoder,
-				 const struct drm_display_mode *mode,
-				 struct drm_display_mode *adjusted_mode)
+static bool intel_dvo_compute_config(struct intel_encoder *encoder,
+				     struct intel_crtc_config *pipe_config)
 {
-	struct intel_dvo *intel_dvo = enc_to_intel_dvo(encoder);
+	struct intel_dvo *intel_dvo = enc_to_dvo(encoder);
+	struct drm_display_mode *adjusted_mode = &pipe_config->adjusted_mode;
 
 	/* If we have timings from the BIOS for the panel, put them in
 	 * to the adjusted mode.  The CRTC will be set up for this mode,
@@ -264,26 +263,28 @@ static bool intel_dvo_mode_fixup(struct drm_encoder *encoder,
 		C(vtotal);
 		C(clock);
 #undef C
+
+		drm_mode_set_crtcinfo(adjusted_mode, 0);
 	}
 
 	if (intel_dvo->dev.dev_ops->mode_fixup)
-		return intel_dvo->dev.dev_ops->mode_fixup(&intel_dvo->dev, mode, adjusted_mode);
+		return intel_dvo->dev.dev_ops->mode_fixup(&intel_dvo->dev,
+							  &pipe_config->requested_mode,
+							  adjusted_mode);
 
 	return true;
 }
 
-static void intel_dvo_mode_set(struct drm_encoder *encoder,
-			       struct drm_display_mode *mode,
-			       struct drm_display_mode *adjusted_mode)
+static void intel_dvo_mode_set(struct intel_encoder *encoder)
 {
-	struct drm_device *dev = encoder->dev;
+	struct drm_device *dev = encoder->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_crtc *intel_crtc = to_intel_crtc(encoder->crtc);
-	struct intel_dvo *intel_dvo = enc_to_intel_dvo(encoder);
-	int pipe = intel_crtc->pipe;
+	struct intel_crtc *crtc = to_intel_crtc(encoder->base.crtc);
+	struct drm_display_mode *adjusted_mode = &crtc->config.adjusted_mode;
+	struct intel_dvo *intel_dvo = enc_to_dvo(encoder);
+	int pipe = crtc->pipe;
 	u32 dvo_val;
 	u32 dvo_reg = intel_dvo->dev.dvo_reg, dvo_srcdim_reg;
-	int dpll_reg = DPLL(pipe);
 
 	switch (dvo_reg) {
 	case DVOA:
@@ -298,7 +299,9 @@ static void intel_dvo_mode_set(struct drm_encoder *encoder,
 		break;
 	}
 
-	intel_dvo->dev.dev_ops->mode_set(&intel_dvo->dev, mode, adjusted_mode);
+	intel_dvo->dev.dev_ops->mode_set(&intel_dvo->dev,
+					 &crtc->config.requested_mode,
+					 adjusted_mode);
 
 	/* Save the data order, since I don't know what it should be set to. */
 	dvo_val = I915_READ(dvo_reg) &
@@ -314,8 +317,6 @@ static void intel_dvo_mode_set(struct drm_encoder *encoder,
 	if (adjusted_mode->flags & DRM_MODE_FLAG_PVSYNC)
 		dvo_val |= DVO_VSYNC_ACTIVE_HIGH;
 
-	I915_WRITE(dpll_reg, I915_READ(dpll_reg) | DPLL_DVO_HIGH_SPEED);
-
 	/*I915_WRITE(DVOB_SRCDIM,
 	  (adjusted_mode->hdisplay << DVO_SRCDIM_HORIZONTAL_SHIFT) |
 	  (adjusted_mode->VDisplay << DVO_SRCDIM_VERTICAL_SHIFT));*/
@@ -335,6 +336,8 @@ static enum drm_connector_status
 intel_dvo_detect(struct drm_connector *connector, bool force)
 {
 	struct intel_dvo *intel_dvo = intel_attached_dvo(connector);
+	DRM_DEBUG_KMS("[CONNECTOR:%d:%s]\n",
+		      connector->base.id, drm_get_connector_name(connector));
 	return intel_dvo->dev.dev_ops->detect(&intel_dvo->dev);
 }
 
@@ -372,11 +375,6 @@ static void intel_dvo_destroy(struct drm_connector *connector)
 	kfree(connector);
 }
 
-static const struct drm_encoder_helper_funcs intel_dvo_helper_funcs = {
-	.mode_fixup = intel_dvo_mode_fixup,
-	.mode_set = intel_dvo_mode_set,
-};
-
 static const struct drm_connector_funcs intel_dvo_connector_funcs = {
 	.dpms = intel_dvo_dpms,
 	.detect = intel_dvo_detect,
@@ -392,7 +390,7 @@ static const struct drm_connector_helper_funcs intel_dvo_connector_helper_funcs
 
 static void intel_dvo_enc_destroy(struct drm_encoder *encoder)
 {
-	struct intel_dvo *intel_dvo = enc_to_intel_dvo(encoder);
+	struct intel_dvo *intel_dvo = enc_to_dvo(to_intel_encoder(encoder));
 
 	if (intel_dvo->dev.dev_ops->destroy)
 		intel_dvo->dev.dev_ops->destroy(&intel_dvo->dev);
@@ -471,6 +469,8 @@ void intel_dvo_init(struct drm_device *dev)
 	intel_encoder->enable = intel_enable_dvo;
 	intel_encoder->get_hw_state = intel_dvo_get_hw_state;
 	intel_encoder->get_config = intel_dvo_get_config;
+	intel_encoder->compute_config = intel_dvo_compute_config;
+	intel_encoder->mode_set = intel_dvo_mode_set;
 	intel_connector->get_hw_state = intel_dvo_connector_get_hw_state;
 
 	/* Now, try to find a controller */
@@ -537,9 +537,6 @@ void intel_dvo_init(struct drm_device *dev)
 		connector->interlace_allowed = false;
 		connector->doublescan_allowed = false;
 
-		drm_encoder_helper_add(&intel_encoder->base,
-				       &intel_dvo_helper_funcs);
-
 		intel_connector_attach_encoder(intel_connector, intel_encoder);
 		if (dvo->type == INTEL_DVO_CHIP_LVDS) {
 			/* For our LVDS chipsets, we should hopefully be able
diff --git a/drivers/gpu/drm/i915/intel_fb.c b/drivers/gpu/drm/i915/intel_fb.c
index dff669e2387f..bc2100007b21 100644
--- a/drivers/gpu/drm/i915/intel_fb.c
+++ b/drivers/gpu/drm/i915/intel_fb.c
@@ -139,11 +139,11 @@ static int intelfb_create(struct drm_fb_helper *helper,
 	info->apertures->ranges[0].base = dev->mode_config.fb_base;
 	info->apertures->ranges[0].size = dev_priv->gtt.mappable_end;
 
-	info->fix.smem_start = dev->mode_config.fb_base + obj->gtt_offset;
+	info->fix.smem_start = dev->mode_config.fb_base + i915_gem_obj_ggtt_offset(obj);
 	info->fix.smem_len = size;
 
 	info->screen_base =
-		ioremap_wc(dev_priv->gtt.mappable_base + obj->gtt_offset,
+		ioremap_wc(dev_priv->gtt.mappable_base + i915_gem_obj_ggtt_offset(obj),
 			   size);
 	if (!info->screen_base) {
 		ret = -ENOSPC;
@@ -166,9 +166,9 @@ static int intelfb_create(struct drm_fb_helper *helper,
 
 	/* Use default scratch pixmap (info->pixmap.flags = FB_PIXMAP_SYSTEM) */
 
-	DRM_DEBUG_KMS("allocated %dx%d fb: 0x%08x, bo %p\n",
+	DRM_DEBUG_KMS("allocated %dx%d fb: 0x%08lx, bo %p\n",
 		      fb->width, fb->height,
-		      obj->gtt_offset, obj);
+		      i915_gem_obj_ggtt_offset(obj), obj);
 
 
 	mutex_unlock(&dev->struct_mutex);
@@ -193,26 +193,21 @@ static struct drm_fb_helper_funcs intel_fb_helper_funcs = {
 static void intel_fbdev_destroy(struct drm_device *dev,
 				struct intel_fbdev *ifbdev)
 {
-	struct fb_info *info;
-	struct intel_framebuffer *ifb = &ifbdev->ifb;
-
 	if (ifbdev->helper.fbdev) {
-		info = ifbdev->helper.fbdev;
+		struct fb_info *info = ifbdev->helper.fbdev;
+
 		unregister_framebuffer(info);
 		iounmap(info->screen_base);
 		if (info->cmap.len)
 			fb_dealloc_cmap(&info->cmap);
+
 		framebuffer_release(info);
 	}
 
 	drm_fb_helper_fini(&ifbdev->helper);
 
-	drm_framebuffer_unregister_private(&ifb->base);
-	drm_framebuffer_cleanup(&ifb->base);
-	if (ifb->obj) {
-		drm_gem_object_unreference_unlocked(&ifb->obj->base);
-		ifb->obj = NULL;
-	}
+	drm_framebuffer_unregister_private(&ifbdev->ifb.base);
+	intel_framebuffer_fini(&ifbdev->ifb);
 }
 
 int intel_fbdev_init(struct drm_device *dev)
diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c
index 2fd3fd5b943e..4148cc85bf7f 100644
--- a/drivers/gpu/drm/i915/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/intel_hdmi.c
@@ -29,6 +29,7 @@
 #include <linux/i2c.h>
 #include <linux/slab.h>
 #include <linux/delay.h>
+#include <linux/hdmi.h>
 #include <drm/drmP.h>
 #include <drm/drm_crtc.h>
 #include <drm/drm_edid.h>
@@ -66,89 +67,83 @@ static struct intel_hdmi *intel_attached_hdmi(struct drm_connector *connector)
 	return enc_to_intel_hdmi(&intel_attached_encoder(connector)->base);
 }
 
-void intel_dip_infoframe_csum(struct dip_infoframe *frame)
+static u32 g4x_infoframe_index(enum hdmi_infoframe_type type)
 {
-	uint8_t *data = (uint8_t *)frame;
-	uint8_t sum = 0;
-	unsigned i;
-
-	frame->checksum = 0;
-	frame->ecc = 0;
-
-	for (i = 0; i < frame->len + DIP_HEADER_SIZE; i++)
-		sum += data[i];
-
-	frame->checksum = 0x100 - sum;
-}
-
-static u32 g4x_infoframe_index(struct dip_infoframe *frame)
-{
-	switch (frame->type) {
-	case DIP_TYPE_AVI:
+	switch (type) {
+	case HDMI_INFOFRAME_TYPE_AVI:
 		return VIDEO_DIP_SELECT_AVI;
-	case DIP_TYPE_SPD:
+	case HDMI_INFOFRAME_TYPE_SPD:
 		return VIDEO_DIP_SELECT_SPD;
+	case HDMI_INFOFRAME_TYPE_VENDOR:
+		return VIDEO_DIP_SELECT_VENDOR;
 	default:
-		DRM_DEBUG_DRIVER("unknown info frame type %d\n", frame->type);
+		DRM_DEBUG_DRIVER("unknown info frame type %d\n", type);
 		return 0;
 	}
 }
 
-static u32 g4x_infoframe_enable(struct dip_infoframe *frame)
+static u32 g4x_infoframe_enable(enum hdmi_infoframe_type type)
 {
-	switch (frame->type) {
-	case DIP_TYPE_AVI:
+	switch (type) {
+	case HDMI_INFOFRAME_TYPE_AVI:
 		return VIDEO_DIP_ENABLE_AVI;
-	case DIP_TYPE_SPD:
+	case HDMI_INFOFRAME_TYPE_SPD:
 		return VIDEO_DIP_ENABLE_SPD;
+	case HDMI_INFOFRAME_TYPE_VENDOR:
+		return VIDEO_DIP_ENABLE_VENDOR;
 	default:
-		DRM_DEBUG_DRIVER("unknown info frame type %d\n", frame->type);
+		DRM_DEBUG_DRIVER("unknown info frame type %d\n", type);
 		return 0;
 	}
 }
 
-static u32 hsw_infoframe_enable(struct dip_infoframe *frame)
+static u32 hsw_infoframe_enable(enum hdmi_infoframe_type type)
 {
-	switch (frame->type) {
-	case DIP_TYPE_AVI:
+	switch (type) {
+	case HDMI_INFOFRAME_TYPE_AVI:
 		return VIDEO_DIP_ENABLE_AVI_HSW;
-	case DIP_TYPE_SPD:
+	case HDMI_INFOFRAME_TYPE_SPD:
 		return VIDEO_DIP_ENABLE_SPD_HSW;
+	case HDMI_INFOFRAME_TYPE_VENDOR:
+		return VIDEO_DIP_ENABLE_VS_HSW;
 	default:
-		DRM_DEBUG_DRIVER("unknown info frame type %d\n", frame->type);
+		DRM_DEBUG_DRIVER("unknown info frame type %d\n", type);
 		return 0;
 	}
 }
 
-static u32 hsw_infoframe_data_reg(struct dip_infoframe *frame,
+static u32 hsw_infoframe_data_reg(enum hdmi_infoframe_type type,
 				  enum transcoder cpu_transcoder)
 {
-	switch (frame->type) {
-	case DIP_TYPE_AVI:
+	switch (type) {
+	case HDMI_INFOFRAME_TYPE_AVI:
 		return HSW_TVIDEO_DIP_AVI_DATA(cpu_transcoder);
-	case DIP_TYPE_SPD:
+	case HDMI_INFOFRAME_TYPE_SPD:
 		return HSW_TVIDEO_DIP_SPD_DATA(cpu_transcoder);
+	case HDMI_INFOFRAME_TYPE_VENDOR:
+		return HSW_TVIDEO_DIP_VS_DATA(cpu_transcoder);
 	default:
-		DRM_DEBUG_DRIVER("unknown info frame type %d\n", frame->type);
+		DRM_DEBUG_DRIVER("unknown info frame type %d\n", type);
 		return 0;
 	}
 }
 
 static void g4x_write_infoframe(struct drm_encoder *encoder,
-				struct dip_infoframe *frame)
+				enum hdmi_infoframe_type type,
+				const uint8_t *frame, ssize_t len)
 {
 	uint32_t *data = (uint32_t *)frame;
 	struct drm_device *dev = encoder->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	u32 val = I915_READ(VIDEO_DIP_CTL);
-	unsigned i, len = DIP_HEADER_SIZE + frame->len;
+	int i;
 
 	WARN(!(val & VIDEO_DIP_ENABLE), "Writing DIP with CTL reg disabled\n");
 
 	val &= ~(VIDEO_DIP_SELECT_MASK | 0xf); /* clear DIP data offset */
-	val |= g4x_infoframe_index(frame);
+	val |= g4x_infoframe_index(type);
 
-	val &= ~g4x_infoframe_enable(frame);
+	val &= ~g4x_infoframe_enable(type);
 
 	I915_WRITE(VIDEO_DIP_CTL, val);
 
@@ -162,7 +157,7 @@ static void g4x_write_infoframe(struct drm_encoder *encoder,
 		I915_WRITE(VIDEO_DIP_DATA, 0);
 	mmiowb();
 
-	val |= g4x_infoframe_enable(frame);
+	val |= g4x_infoframe_enable(type);
 	val &= ~VIDEO_DIP_FREQ_MASK;
 	val |= VIDEO_DIP_FREQ_VSYNC;
 
@@ -171,22 +166,22 @@ static void g4x_write_infoframe(struct drm_encoder *encoder,
 }
 
 static void ibx_write_infoframe(struct drm_encoder *encoder,
-				struct dip_infoframe *frame)
+				enum hdmi_infoframe_type type,
+				const uint8_t *frame, ssize_t len)
 {
 	uint32_t *data = (uint32_t *)frame;
 	struct drm_device *dev = encoder->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_crtc *intel_crtc = to_intel_crtc(encoder->crtc);
-	int reg = TVIDEO_DIP_CTL(intel_crtc->pipe);
-	unsigned i, len = DIP_HEADER_SIZE + frame->len;
+	int i, reg = TVIDEO_DIP_CTL(intel_crtc->pipe);
 	u32 val = I915_READ(reg);
 
 	WARN(!(val & VIDEO_DIP_ENABLE), "Writing DIP with CTL reg disabled\n");
 
 	val &= ~(VIDEO_DIP_SELECT_MASK | 0xf); /* clear DIP data offset */
-	val |= g4x_infoframe_index(frame);
+	val |= g4x_infoframe_index(type);
 
-	val &= ~g4x_infoframe_enable(frame);
+	val &= ~g4x_infoframe_enable(type);
 
 	I915_WRITE(reg, val);
 
@@ -200,7 +195,7 @@ static void ibx_write_infoframe(struct drm_encoder *encoder,
 		I915_WRITE(TVIDEO_DIP_DATA(intel_crtc->pipe), 0);
 	mmiowb();
 
-	val |= g4x_infoframe_enable(frame);
+	val |= g4x_infoframe_enable(type);
 	val &= ~VIDEO_DIP_FREQ_MASK;
 	val |= VIDEO_DIP_FREQ_VSYNC;
 
@@ -209,25 +204,25 @@ static void ibx_write_infoframe(struct drm_encoder *encoder,
 }
 
 static void cpt_write_infoframe(struct drm_encoder *encoder,
-				struct dip_infoframe *frame)
+				enum hdmi_infoframe_type type,
+				const uint8_t *frame, ssize_t len)
 {
 	uint32_t *data = (uint32_t *)frame;
 	struct drm_device *dev = encoder->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_crtc *intel_crtc = to_intel_crtc(encoder->crtc);
-	int reg = TVIDEO_DIP_CTL(intel_crtc->pipe);
-	unsigned i, len = DIP_HEADER_SIZE + frame->len;
+	int i, reg = TVIDEO_DIP_CTL(intel_crtc->pipe);
 	u32 val = I915_READ(reg);
 
 	WARN(!(val & VIDEO_DIP_ENABLE), "Writing DIP with CTL reg disabled\n");
 
 	val &= ~(VIDEO_DIP_SELECT_MASK | 0xf); /* clear DIP data offset */
-	val |= g4x_infoframe_index(frame);
+	val |= g4x_infoframe_index(type);
 
 	/* The DIP control register spec says that we need to update the AVI
 	 * infoframe without clearing its enable bit */
-	if (frame->type != DIP_TYPE_AVI)
-		val &= ~g4x_infoframe_enable(frame);
+	if (type != HDMI_INFOFRAME_TYPE_AVI)
+		val &= ~g4x_infoframe_enable(type);
 
 	I915_WRITE(reg, val);
 
@@ -241,7 +236,7 @@ static void cpt_write_infoframe(struct drm_encoder *encoder,
 		I915_WRITE(TVIDEO_DIP_DATA(intel_crtc->pipe), 0);
 	mmiowb();
 
-	val |= g4x_infoframe_enable(frame);
+	val |= g4x_infoframe_enable(type);
 	val &= ~VIDEO_DIP_FREQ_MASK;
 	val |= VIDEO_DIP_FREQ_VSYNC;
 
@@ -250,22 +245,22 @@ static void cpt_write_infoframe(struct drm_encoder *encoder,
 }
 
 static void vlv_write_infoframe(struct drm_encoder *encoder,
-				     struct dip_infoframe *frame)
+				enum hdmi_infoframe_type type,
+				const uint8_t *frame, ssize_t len)
 {
 	uint32_t *data = (uint32_t *)frame;
 	struct drm_device *dev = encoder->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_crtc *intel_crtc = to_intel_crtc(encoder->crtc);
-	int reg = VLV_TVIDEO_DIP_CTL(intel_crtc->pipe);
-	unsigned i, len = DIP_HEADER_SIZE + frame->len;
+	int i, reg = VLV_TVIDEO_DIP_CTL(intel_crtc->pipe);
 	u32 val = I915_READ(reg);
 
 	WARN(!(val & VIDEO_DIP_ENABLE), "Writing DIP with CTL reg disabled\n");
 
 	val &= ~(VIDEO_DIP_SELECT_MASK | 0xf); /* clear DIP data offset */
-	val |= g4x_infoframe_index(frame);
+	val |= g4x_infoframe_index(type);
 
-	val &= ~g4x_infoframe_enable(frame);
+	val &= ~g4x_infoframe_enable(type);
 
 	I915_WRITE(reg, val);
 
@@ -279,7 +274,7 @@ static void vlv_write_infoframe(struct drm_encoder *encoder,
 		I915_WRITE(VLV_TVIDEO_DIP_DATA(intel_crtc->pipe), 0);
 	mmiowb();
 
-	val |= g4x_infoframe_enable(frame);
+	val |= g4x_infoframe_enable(type);
 	val &= ~VIDEO_DIP_FREQ_MASK;
 	val |= VIDEO_DIP_FREQ_VSYNC;
 
@@ -288,21 +283,24 @@ static void vlv_write_infoframe(struct drm_encoder *encoder,
 }
 
 static void hsw_write_infoframe(struct drm_encoder *encoder,
-				struct dip_infoframe *frame)
+				enum hdmi_infoframe_type type,
+				const uint8_t *frame, ssize_t len)
 {
 	uint32_t *data = (uint32_t *)frame;
 	struct drm_device *dev = encoder->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_crtc *intel_crtc = to_intel_crtc(encoder->crtc);
 	u32 ctl_reg = HSW_TVIDEO_DIP_CTL(intel_crtc->config.cpu_transcoder);
-	u32 data_reg = hsw_infoframe_data_reg(frame, intel_crtc->config.cpu_transcoder);
-	unsigned int i, len = DIP_HEADER_SIZE + frame->len;
+	u32 data_reg;
+	int i;
 	u32 val = I915_READ(ctl_reg);
 
+	data_reg = hsw_infoframe_data_reg(type,
+					  intel_crtc->config.cpu_transcoder);
 	if (data_reg == 0)
 		return;
 
-	val &= ~hsw_infoframe_enable(frame);
+	val &= ~hsw_infoframe_enable(type);
 	I915_WRITE(ctl_reg, val);
 
 	mmiowb();
@@ -315,18 +313,48 @@ static void hsw_write_infoframe(struct drm_encoder *encoder,
 		I915_WRITE(data_reg + i, 0);
 	mmiowb();
 
-	val |= hsw_infoframe_enable(frame);
+	val |= hsw_infoframe_enable(type);
 	I915_WRITE(ctl_reg, val);
 	POSTING_READ(ctl_reg);
 }
 
-static void intel_set_infoframe(struct drm_encoder *encoder,
-				struct dip_infoframe *frame)
+/*
+ * The data we write to the DIP data buffer registers is 1 byte bigger than the
+ * HDMI infoframe size because of an ECC/reserved byte at position 3 (starting
+ * at 0). It's also a byte used by DisplayPort so the same DIP registers can be
+ * used for both technologies.
+ *
+ * DW0: Reserved/ECC/DP | HB2 | HB1 | HB0
+ * DW1:       DB3       | DB2 | DB1 | DB0
+ * DW2:       DB7       | DB6 | DB5 | DB4
+ * DW3: ...
+ *
+ * (HB is Header Byte, DB is Data Byte)
+ *
+ * The hdmi pack() functions don't know about that hardware specific hole so we
+ * trick them by giving an offset into the buffer and moving back the header
+ * bytes by one.
+ */
+static void intel_write_infoframe(struct drm_encoder *encoder,
+				  union hdmi_infoframe *frame)
 {
 	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(encoder);
+	uint8_t buffer[VIDEO_DIP_DATA_SIZE];
+	ssize_t len;
+
+	/* see comment above for the reason for this offset */
+	len = hdmi_infoframe_pack(frame, buffer + 1, sizeof(buffer) - 1);
+	if (len < 0)
+		return;
 
-	intel_dip_infoframe_csum(frame);
-	intel_hdmi->write_infoframe(encoder, frame);
+	/* Insert the 'hole' (see big comment above) at position 3 */
+	buffer[0] = buffer[1];
+	buffer[1] = buffer[2];
+	buffer[2] = buffer[3];
+	buffer[3] = 0;
+	len++;
+
+	intel_hdmi->write_infoframe(encoder, frame->any.type, buffer, len);
 }
 
 static void intel_hdmi_set_avi_infoframe(struct drm_encoder *encoder,
@@ -334,40 +362,57 @@ static void intel_hdmi_set_avi_infoframe(struct drm_encoder *encoder,
 {
 	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(encoder);
 	struct intel_crtc *intel_crtc = to_intel_crtc(encoder->crtc);
-	struct dip_infoframe avi_if = {
-		.type = DIP_TYPE_AVI,
-		.ver = DIP_VERSION_AVI,
-		.len = DIP_LEN_AVI,
-	};
+	union hdmi_infoframe frame;
+	int ret;
 
-	if (adjusted_mode->flags & DRM_MODE_FLAG_DBLCLK)
-		avi_if.body.avi.YQ_CN_PR |= DIP_AVI_PR_2;
+	ret = drm_hdmi_avi_infoframe_from_display_mode(&frame.avi,
+						       adjusted_mode);
+	if (ret < 0) {
+		DRM_ERROR("couldn't fill AVI infoframe\n");
+		return;
+	}
 
 	if (intel_hdmi->rgb_quant_range_selectable) {
 		if (intel_crtc->config.limited_color_range)
-			avi_if.body.avi.ITC_EC_Q_SC |= DIP_AVI_RGB_QUANT_RANGE_LIMITED;
+			frame.avi.quantization_range =
+				HDMI_QUANTIZATION_RANGE_LIMITED;
 		else
-			avi_if.body.avi.ITC_EC_Q_SC |= DIP_AVI_RGB_QUANT_RANGE_FULL;
+			frame.avi.quantization_range =
+				HDMI_QUANTIZATION_RANGE_FULL;
 	}
 
-	avi_if.body.avi.VIC = drm_match_cea_mode(adjusted_mode);
-
-	intel_set_infoframe(encoder, &avi_if);
+	intel_write_infoframe(encoder, &frame);
 }
 
 static void intel_hdmi_set_spd_infoframe(struct drm_encoder *encoder)
 {
-	struct dip_infoframe spd_if;
+	union hdmi_infoframe frame;
+	int ret;
+
+	ret = hdmi_spd_infoframe_init(&frame.spd, "Intel", "Integrated gfx");
+	if (ret < 0) {
+		DRM_ERROR("couldn't fill SPD infoframe\n");
+		return;
+	}
+
+	frame.spd.sdi = HDMI_SPD_SDI_PC;
+
+	intel_write_infoframe(encoder, &frame);
+}
+
+static void
+intel_hdmi_set_hdmi_infoframe(struct drm_encoder *encoder,
+			      struct drm_display_mode *adjusted_mode)
+{
+	union hdmi_infoframe frame;
+	int ret;
 
-	memset(&spd_if, 0, sizeof(spd_if));
-	spd_if.type = DIP_TYPE_SPD;
-	spd_if.ver = DIP_VERSION_SPD;
-	spd_if.len = DIP_LEN_SPD;
-	strcpy(spd_if.body.spd.vn, "Intel");
-	strcpy(spd_if.body.spd.pd, "Integrated gfx");
-	spd_if.body.spd.sdi = DIP_SPD_PC;
+	ret = drm_hdmi_vendor_infoframe_from_display_mode(&frame.vendor.hdmi,
+							  adjusted_mode);
+	if (ret < 0)
+		return;
 
-	intel_set_infoframe(encoder, &spd_if);
+	intel_write_infoframe(encoder, &frame);
 }
 
 static void g4x_set_infoframes(struct drm_encoder *encoder,
@@ -432,6 +477,7 @@ static void g4x_set_infoframes(struct drm_encoder *encoder,
 
 	intel_hdmi_set_avi_infoframe(encoder, adjusted_mode);
 	intel_hdmi_set_spd_infoframe(encoder);
+	intel_hdmi_set_hdmi_infoframe(encoder, adjusted_mode);
 }
 
 static void ibx_set_infoframes(struct drm_encoder *encoder,
@@ -493,6 +539,7 @@ static void ibx_set_infoframes(struct drm_encoder *encoder,
 
 	intel_hdmi_set_avi_infoframe(encoder, adjusted_mode);
 	intel_hdmi_set_spd_infoframe(encoder);
+	intel_hdmi_set_hdmi_infoframe(encoder, adjusted_mode);
 }
 
 static void cpt_set_infoframes(struct drm_encoder *encoder,
@@ -528,6 +575,7 @@ static void cpt_set_infoframes(struct drm_encoder *encoder,
 
 	intel_hdmi_set_avi_infoframe(encoder, adjusted_mode);
 	intel_hdmi_set_spd_infoframe(encoder);
+	intel_hdmi_set_hdmi_infoframe(encoder, adjusted_mode);
 }
 
 static void vlv_set_infoframes(struct drm_encoder *encoder,
@@ -562,6 +610,7 @@ static void vlv_set_infoframes(struct drm_encoder *encoder,
 
 	intel_hdmi_set_avi_infoframe(encoder, adjusted_mode);
 	intel_hdmi_set_spd_infoframe(encoder);
+	intel_hdmi_set_hdmi_infoframe(encoder, adjusted_mode);
 }
 
 static void hsw_set_infoframes(struct drm_encoder *encoder,
@@ -589,16 +638,16 @@ static void hsw_set_infoframes(struct drm_encoder *encoder,
 
 	intel_hdmi_set_avi_infoframe(encoder, adjusted_mode);
 	intel_hdmi_set_spd_infoframe(encoder);
+	intel_hdmi_set_hdmi_infoframe(encoder, adjusted_mode);
 }
 
-static void intel_hdmi_mode_set(struct drm_encoder *encoder,
-				struct drm_display_mode *mode,
-				struct drm_display_mode *adjusted_mode)
+static void intel_hdmi_mode_set(struct intel_encoder *encoder)
 {
-	struct drm_device *dev = encoder->dev;
+	struct drm_device *dev = encoder->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_crtc *intel_crtc = to_intel_crtc(encoder->crtc);
-	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(encoder);
+	struct intel_crtc *crtc = to_intel_crtc(encoder->base.crtc);
+	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(&encoder->base);
+	struct drm_display_mode *adjusted_mode = &crtc->config.adjusted_mode;
 	u32 hdmi_val;
 
 	hdmi_val = SDVO_ENCODING_HDMI;
@@ -609,7 +658,7 @@ static void intel_hdmi_mode_set(struct drm_encoder *encoder,
 	if (adjusted_mode->flags & DRM_MODE_FLAG_PHSYNC)
 		hdmi_val |= SDVO_HSYNC_ACTIVE_HIGH;
 
-	if (intel_crtc->config.pipe_bpp > 24)
+	if (crtc->config.pipe_bpp > 24)
 		hdmi_val |= HDMI_COLOR_FORMAT_12bpc;
 	else
 		hdmi_val |= SDVO_COLOR_FORMAT_8bpc;
@@ -620,21 +669,21 @@ static void intel_hdmi_mode_set(struct drm_encoder *encoder,
 
 	if (intel_hdmi->has_audio) {
 		DRM_DEBUG_DRIVER("Enabling HDMI audio on pipe %c\n",
-				 pipe_name(intel_crtc->pipe));
+				 pipe_name(crtc->pipe));
 		hdmi_val |= SDVO_AUDIO_ENABLE;
 		hdmi_val |= HDMI_MODE_SELECT_HDMI;
-		intel_write_eld(encoder, adjusted_mode);
+		intel_write_eld(&encoder->base, adjusted_mode);
 	}
 
 	if (HAS_PCH_CPT(dev))
-		hdmi_val |= SDVO_PIPE_SEL_CPT(intel_crtc->pipe);
+		hdmi_val |= SDVO_PIPE_SEL_CPT(crtc->pipe);
 	else
-		hdmi_val |= SDVO_PIPE_SEL(intel_crtc->pipe);
+		hdmi_val |= SDVO_PIPE_SEL(crtc->pipe);
 
 	I915_WRITE(intel_hdmi->hdmi_reg, hdmi_val);
 	POSTING_READ(intel_hdmi->hdmi_reg);
 
-	intel_hdmi->set_infoframes(encoder, adjusted_mode);
+	intel_hdmi->set_infoframes(&encoder->base, adjusted_mode);
 }
 
 static bool intel_hdmi_get_hw_state(struct intel_encoder *encoder,
@@ -719,14 +768,10 @@ static void intel_enable_hdmi(struct intel_encoder *encoder)
 		I915_WRITE(intel_hdmi->hdmi_reg, temp);
 		POSTING_READ(intel_hdmi->hdmi_reg);
 	}
+}
 
-	if (IS_VALLEYVIEW(dev)) {
-		struct intel_digital_port *dport =
-			enc_to_dig_port(&encoder->base);
-		int channel = vlv_dport_to_channel(dport);
-
-		vlv_wait_port_ready(dev_priv, channel);
-	}
+static void vlv_enable_hdmi(struct intel_encoder *encoder)
+{
 }
 
 static void intel_disable_hdmi(struct intel_encoder *encoder)
@@ -879,6 +924,9 @@ intel_hdmi_detect(struct drm_connector *connector, bool force)
 	struct edid *edid;
 	enum drm_connector_status status = connector_status_disconnected;
 
+	DRM_DEBUG_KMS("[CONNECTOR:%d:%s]\n",
+		      connector->base.id, drm_get_connector_name(connector));
+
 	intel_hdmi->has_hdmi_sink = false;
 	intel_hdmi->has_audio = false;
 	intel_hdmi->rgb_quant_range_selectable = false;
@@ -1030,6 +1078,7 @@ static void intel_hdmi_pre_enable(struct intel_encoder *encoder)
 		return;
 
 	/* Enable clock channels for this port */
+	mutex_lock(&dev_priv->dpio_lock);
 	val = vlv_dpio_read(dev_priv, DPIO_DATA_LANE_A(port));
 	val = 0;
 	if (pipe)
@@ -1060,6 +1109,11 @@ static void intel_hdmi_pre_enable(struct intel_encoder *encoder)
 			 0x00760018);
 	vlv_dpio_write(dev_priv, DPIO_PCS_CLOCKBUF8(port),
 			 0x00400888);
+	mutex_unlock(&dev_priv->dpio_lock);
+
+	intel_enable_hdmi(encoder);
+
+	vlv_wait_port_ready(dev_priv, port);
 }
 
 static void intel_hdmi_pre_pll_enable(struct intel_encoder *encoder)
@@ -1073,6 +1127,7 @@ static void intel_hdmi_pre_pll_enable(struct intel_encoder *encoder)
 		return;
 
 	/* Program Tx lane resets to default */
+	mutex_lock(&dev_priv->dpio_lock);
 	vlv_dpio_write(dev_priv, DPIO_PCS_TX(port),
 			 DPIO_PCS_TX_LANE2_RESET |
 			 DPIO_PCS_TX_LANE1_RESET);
@@ -1091,6 +1146,7 @@ static void intel_hdmi_pre_pll_enable(struct intel_encoder *encoder)
 			 0x00002000);
 	vlv_dpio_write(dev_priv, DPIO_TX_OCALINIT(port),
 			 DPIO_TX_OCALINIT_EN);
+	mutex_unlock(&dev_priv->dpio_lock);
 }
 
 static void intel_hdmi_post_disable(struct intel_encoder *encoder)
@@ -1113,10 +1169,6 @@ static void intel_hdmi_destroy(struct drm_connector *connector)
 	kfree(connector);
 }
 
-static const struct drm_encoder_helper_funcs intel_hdmi_helper_funcs = {
-	.mode_set = intel_hdmi_mode_set,
-};
-
 static const struct drm_connector_funcs intel_hdmi_connector_funcs = {
 	.dpms = intel_connector_dpms,
 	.detect = intel_hdmi_detect,
@@ -1221,7 +1273,6 @@ void intel_hdmi_init(struct drm_device *dev, int hdmi_reg, enum port port)
 {
 	struct intel_digital_port *intel_dig_port;
 	struct intel_encoder *intel_encoder;
-	struct drm_encoder *encoder;
 	struct intel_connector *intel_connector;
 
 	intel_dig_port = kzalloc(sizeof(struct intel_digital_port), GFP_KERNEL);
@@ -1235,21 +1286,22 @@ void intel_hdmi_init(struct drm_device *dev, int hdmi_reg, enum port port)
 	}
 
 	intel_encoder = &intel_dig_port->base;
-	encoder = &intel_encoder->base;
 
 	drm_encoder_init(dev, &intel_encoder->base, &intel_hdmi_enc_funcs,
 			 DRM_MODE_ENCODER_TMDS);
-	drm_encoder_helper_add(&intel_encoder->base, &intel_hdmi_helper_funcs);
 
 	intel_encoder->compute_config = intel_hdmi_compute_config;
-	intel_encoder->enable = intel_enable_hdmi;
+	intel_encoder->mode_set = intel_hdmi_mode_set;
 	intel_encoder->disable = intel_disable_hdmi;
 	intel_encoder->get_hw_state = intel_hdmi_get_hw_state;
 	intel_encoder->get_config = intel_hdmi_get_config;
 	if (IS_VALLEYVIEW(dev)) {
-		intel_encoder->pre_enable = intel_hdmi_pre_enable;
 		intel_encoder->pre_pll_enable = intel_hdmi_pre_pll_enable;
+		intel_encoder->pre_enable = intel_hdmi_pre_enable;
+		intel_encoder->enable = vlv_enable_hdmi;
 		intel_encoder->post_disable = intel_hdmi_post_disable;
+	} else {
+		intel_encoder->enable = intel_enable_hdmi;
 	}
 
 	intel_encoder->type = INTEL_OUTPUT_HDMI;
diff --git a/drivers/gpu/drm/i915/intel_i2c.c b/drivers/gpu/drm/i915/intel_i2c.c
index 639fe192997c..d1c1e0f7f262 100644
--- a/drivers/gpu/drm/i915/intel_i2c.c
+++ b/drivers/gpu/drm/i915/intel_i2c.c
@@ -398,6 +398,7 @@ gmbus_xfer(struct i2c_adapter *adapter,
 	int i, reg_offset;
 	int ret = 0;
 
+	intel_aux_display_runtime_get(dev_priv);
 	mutex_lock(&dev_priv->gmbus_mutex);
 
 	if (bus->force_bit) {
@@ -497,6 +498,7 @@ timeout:
 
 out:
 	mutex_unlock(&dev_priv->gmbus_mutex);
+	intel_aux_display_runtime_put(dev_priv);
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c
index 61348eae2f04..831a5c021c4b 100644
--- a/drivers/gpu/drm/i915/intel_lvds.c
+++ b/drivers/gpu/drm/i915/intel_lvds.c
@@ -122,17 +122,25 @@ static void intel_lvds_get_config(struct intel_encoder *encoder,
  * This is an exception to the general rule that mode_set doesn't turn
  * things on.
  */
-static void intel_pre_pll_enable_lvds(struct intel_encoder *encoder)
+static void intel_pre_enable_lvds(struct intel_encoder *encoder)
 {
 	struct intel_lvds_encoder *lvds_encoder = to_lvds_encoder(&encoder->base);
 	struct drm_device *dev = encoder->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_crtc *intel_crtc = to_intel_crtc(encoder->base.crtc);
-	struct drm_display_mode *fixed_mode =
-		lvds_encoder->attached_connector->base.panel.fixed_mode;
-	int pipe = intel_crtc->pipe;
+	struct intel_crtc *crtc = to_intel_crtc(encoder->base.crtc);
+	const struct drm_display_mode *adjusted_mode =
+		&crtc->config.adjusted_mode;
+	int pipe = crtc->pipe;
 	u32 temp;
 
+	if (HAS_PCH_SPLIT(dev)) {
+		assert_fdi_rx_pll_disabled(dev_priv, pipe);
+		assert_shared_dpll_disabled(dev_priv,
+					    intel_crtc_to_shared_dpll(crtc));
+	} else {
+		assert_pll_disabled(dev_priv, pipe);
+	}
+
 	temp = I915_READ(lvds_encoder->reg);
 	temp |= LVDS_PORT_EN | LVDS_A0A2_CLKA_POWER_UP;
 
@@ -149,7 +157,7 @@ static void intel_pre_pll_enable_lvds(struct intel_encoder *encoder)
 
 	/* set the corresponsding LVDS_BORDER bit */
 	temp &= ~LVDS_BORDER_ENABLE;
-	temp |= intel_crtc->config.gmch_pfit.lvds_border_bits;
+	temp |= crtc->config.gmch_pfit.lvds_border_bits;
 	/* Set the B0-B3 data pairs corresponding to whether we're going to
 	 * set the DPLLs for dual-channel mode or not.
 	 */
@@ -169,16 +177,15 @@ static void intel_pre_pll_enable_lvds(struct intel_encoder *encoder)
 	if (INTEL_INFO(dev)->gen == 4) {
 		/* Bspec wording suggests that LVDS port dithering only exists
 		 * for 18bpp panels. */
-		if (intel_crtc->config.dither &&
-		    intel_crtc->config.pipe_bpp == 18)
+		if (crtc->config.dither && crtc->config.pipe_bpp == 18)
 			temp |= LVDS_ENABLE_DITHER;
 		else
 			temp &= ~LVDS_ENABLE_DITHER;
 	}
 	temp &= ~(LVDS_HSYNC_POLARITY | LVDS_VSYNC_POLARITY);
-	if (fixed_mode->flags & DRM_MODE_FLAG_NHSYNC)
+	if (adjusted_mode->flags & DRM_MODE_FLAG_NHSYNC)
 		temp |= LVDS_HSYNC_POLARITY;
-	if (fixed_mode->flags & DRM_MODE_FLAG_NVSYNC)
+	if (adjusted_mode->flags & DRM_MODE_FLAG_NVSYNC)
 		temp |= LVDS_VSYNC_POLARITY;
 
 	I915_WRITE(lvds_encoder->reg, temp);
@@ -312,14 +319,12 @@ static bool intel_lvds_compute_config(struct intel_encoder *intel_encoder,
 	return true;
 }
 
-static void intel_lvds_mode_set(struct drm_encoder *encoder,
-				struct drm_display_mode *mode,
-				struct drm_display_mode *adjusted_mode)
+static void intel_lvds_mode_set(struct intel_encoder *encoder)
 {
 	/*
-	 * The LVDS pin pair will already have been turned on in the
-	 * intel_crtc_mode_set since it has a large impact on the DPLL
-	 * settings.
+	 * We don't do anything here, the LVDS port is fully set up in the pre
+	 * enable hook - the ordering constraints for enabling the lvds port vs.
+	 * enabling the display pll are too strict.
 	 */
 }
 
@@ -336,6 +341,9 @@ intel_lvds_detect(struct drm_connector *connector, bool force)
 	struct drm_device *dev = connector->dev;
 	enum drm_connector_status status;
 
+	DRM_DEBUG_KMS("[CONNECTOR:%d:%s]\n",
+		      connector->base.id, drm_get_connector_name(connector));
+
 	status = intel_panel_detect(dev);
 	if (status != connector_status_unknown)
 		return status;
@@ -497,10 +505,6 @@ static int intel_lvds_set_property(struct drm_connector *connector,
 	return 0;
 }
 
-static const struct drm_encoder_helper_funcs intel_lvds_helper_funcs = {
-	.mode_set = intel_lvds_mode_set,
-};
-
 static const struct drm_connector_helper_funcs intel_lvds_connector_helper_funcs = {
 	.get_modes = intel_lvds_get_modes,
 	.mode_valid = intel_lvds_mode_valid,
@@ -959,8 +963,9 @@ void intel_lvds_init(struct drm_device *dev)
 			 DRM_MODE_ENCODER_LVDS);
 
 	intel_encoder->enable = intel_enable_lvds;
-	intel_encoder->pre_pll_enable = intel_pre_pll_enable_lvds;
+	intel_encoder->pre_enable = intel_pre_enable_lvds;
 	intel_encoder->compute_config = intel_lvds_compute_config;
+	intel_encoder->mode_set = intel_lvds_mode_set;
 	intel_encoder->disable = intel_disable_lvds;
 	intel_encoder->get_hw_state = intel_lvds_get_hw_state;
 	intel_encoder->get_config = intel_lvds_get_config;
@@ -977,7 +982,6 @@ void intel_lvds_init(struct drm_device *dev)
 	else
 		intel_encoder->crtc_mask = (1 << 1);
 
-	drm_encoder_helper_add(encoder, &intel_lvds_helper_funcs);
 	drm_connector_helper_add(connector, &intel_lvds_connector_helper_funcs);
 	connector->display_info.subpixel_order = SubPixelHorizontalRGB;
 	connector->interlace_allowed = false;
diff --git a/drivers/gpu/drm/i915/intel_opregion.c b/drivers/gpu/drm/i915/intel_opregion.c
index cfb8fb68f09c..119771ff46ab 100644
--- a/drivers/gpu/drm/i915/intel_opregion.c
+++ b/drivers/gpu/drm/i915/intel_opregion.c
@@ -173,7 +173,7 @@ static u32 asle_set_backlight(struct drm_device *dev, u32 bclp)
 		return ASLE_BACKLIGHT_FAILED;
 
 	intel_panel_set_backlight(dev, bclp, 255);
-	iowrite32((bclp*0x64)/0xff | ASLE_CBLV_VALID, &asle->cblv);
+	iowrite32(DIV_ROUND_UP(bclp * 100, 255) | ASLE_CBLV_VALID, &asle->cblv);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/i915/intel_overlay.c b/drivers/gpu/drm/i915/intel_overlay.c
index a3698812e9c7..ddfd0aefe0c0 100644
--- a/drivers/gpu/drm/i915/intel_overlay.c
+++ b/drivers/gpu/drm/i915/intel_overlay.c
@@ -196,7 +196,7 @@ intel_overlay_map_regs(struct intel_overlay *overlay)
 		regs = (struct overlay_registers __iomem *)overlay->reg_bo->phys_obj->handle->vaddr;
 	else
 		regs = io_mapping_map_wc(dev_priv->gtt.mappable,
-					 overlay->reg_bo->gtt_offset);
+					 i915_gem_obj_ggtt_offset(overlay->reg_bo));
 
 	return regs;
 }
@@ -740,7 +740,7 @@ static int intel_overlay_do_put_image(struct intel_overlay *overlay,
 	swidth = params->src_w;
 	swidthsw = calc_swidthsw(overlay->dev, params->offset_Y, tmp_width);
 	sheight = params->src_h;
-	iowrite32(new_bo->gtt_offset + params->offset_Y, &regs->OBUF_0Y);
+	iowrite32(i915_gem_obj_ggtt_offset(new_bo) + params->offset_Y, &regs->OBUF_0Y);
 	ostride = params->stride_Y;
 
 	if (params->format & I915_OVERLAY_YUV_PLANAR) {
@@ -754,8 +754,8 @@ static int intel_overlay_do_put_image(struct intel_overlay *overlay,
 				      params->src_w/uv_hscale);
 		swidthsw |= max_t(u32, tmp_U, tmp_V) << 16;
 		sheight |= (params->src_h/uv_vscale) << 16;
-		iowrite32(new_bo->gtt_offset + params->offset_U, &regs->OBUF_0U);
-		iowrite32(new_bo->gtt_offset + params->offset_V, &regs->OBUF_0V);
+		iowrite32(i915_gem_obj_ggtt_offset(new_bo) + params->offset_U, &regs->OBUF_0U);
+		iowrite32(i915_gem_obj_ggtt_offset(new_bo) + params->offset_V, &regs->OBUF_0V);
 		ostride |= params->stride_UV << 16;
 	}
 
@@ -1333,7 +1333,9 @@ void intel_setup_overlay(struct drm_device *dev)
 
 	overlay->dev = dev;
 
-	reg_bo = i915_gem_object_create_stolen(dev, PAGE_SIZE);
+	reg_bo = NULL;
+	if (!OVERLAY_NEEDS_PHYSICAL(dev))
+		reg_bo = i915_gem_object_create_stolen(dev, PAGE_SIZE);
 	if (reg_bo == NULL)
 		reg_bo = i915_gem_alloc_object(dev, PAGE_SIZE);
 	if (reg_bo == NULL)
@@ -1350,12 +1352,12 @@ void intel_setup_overlay(struct drm_device *dev)
 		}
 		overlay->flip_addr = reg_bo->phys_obj->handle->busaddr;
 	} else {
-		ret = i915_gem_object_pin(reg_bo, PAGE_SIZE, true, false);
+		ret = i915_gem_obj_ggtt_pin(reg_bo, PAGE_SIZE, true, false);
 		if (ret) {
 			DRM_ERROR("failed to pin overlay register bo\n");
 			goto out_free_bo;
 		}
-		overlay->flip_addr = reg_bo->gtt_offset;
+		overlay->flip_addr = i915_gem_obj_ggtt_offset(reg_bo);
 
 		ret = i915_gem_object_set_to_gtt_domain(reg_bo, true);
 		if (ret) {
@@ -1412,9 +1414,6 @@ void intel_cleanup_overlay(struct drm_device *dev)
 	kfree(dev_priv->overlay);
 }
 
-#ifdef CONFIG_DEBUG_FS
-#include <linux/seq_file.h>
-
 struct intel_overlay_error_state {
 	struct overlay_registers regs;
 	unsigned long base;
@@ -1435,7 +1434,7 @@ intel_overlay_map_regs_atomic(struct intel_overlay *overlay)
 			overlay->reg_bo->phys_obj->handle->vaddr;
 	else
 		regs = io_mapping_map_atomic_wc(dev_priv->gtt.mappable,
-						overlay->reg_bo->gtt_offset);
+						i915_gem_obj_ggtt_offset(overlay->reg_bo));
 
 	return regs;
 }
@@ -1468,7 +1467,7 @@ intel_overlay_capture_error_state(struct drm_device *dev)
 	if (OVERLAY_NEEDS_PHYSICAL(overlay->dev))
 		error->base = (__force long)overlay->reg_bo->phys_obj->handle->vaddr;
 	else
-		error->base = overlay->reg_bo->gtt_offset;
+		error->base = i915_gem_obj_ggtt_offset(overlay->reg_bo);
 
 	regs = intel_overlay_map_regs_atomic(overlay);
 	if (!regs)
@@ -1537,4 +1536,3 @@ intel_overlay_print_error_state(struct drm_i915_error_state_buf *m,
 	P(UVSCALEV);
 #undef P
 }
-#endif
diff --git a/drivers/gpu/drm/i915/intel_panel.c b/drivers/gpu/drm/i915/intel_panel.c
index 5950888ae1d0..293564a2896a 100644
--- a/drivers/gpu/drm/i915/intel_panel.c
+++ b/drivers/gpu/drm/i915/intel_panel.c
@@ -36,20 +36,12 @@
 #define PCI_LBPC 0xf4 /* legacy/combination backlight modes */
 
 void
-intel_fixed_panel_mode(struct drm_display_mode *fixed_mode,
+intel_fixed_panel_mode(const struct drm_display_mode *fixed_mode,
 		       struct drm_display_mode *adjusted_mode)
 {
-	adjusted_mode->hdisplay = fixed_mode->hdisplay;
-	adjusted_mode->hsync_start = fixed_mode->hsync_start;
-	adjusted_mode->hsync_end = fixed_mode->hsync_end;
-	adjusted_mode->htotal = fixed_mode->htotal;
+	drm_mode_copy(adjusted_mode, fixed_mode);
 
-	adjusted_mode->vdisplay = fixed_mode->vdisplay;
-	adjusted_mode->vsync_start = fixed_mode->vsync_start;
-	adjusted_mode->vsync_end = fixed_mode->vsync_end;
-	adjusted_mode->vtotal = fixed_mode->vtotal;
-
-	adjusted_mode->clock = fixed_mode->clock;
+	drm_mode_set_crtcinfo(adjusted_mode, 0);
 }
 
 /* adjusted_mode has been preset to be the panel's fixed mode */
@@ -120,6 +112,7 @@ intel_pch_panel_fitting(struct intel_crtc *intel_crtc,
 done:
 	pipe_config->pch_pfit.pos = (x << 16) | y;
 	pipe_config->pch_pfit.size = (width << 16) | height;
+	pipe_config->pch_pfit.enabled = pipe_config->pch_pfit.size != 0;
 }
 
 static void
@@ -194,9 +187,6 @@ void intel_gmch_panel_fitting(struct intel_crtc *intel_crtc,
 	    adjusted_mode->vdisplay == mode->vdisplay)
 		goto out;
 
-	drm_mode_set_crtcinfo(adjusted_mode, 0);
-	pipe_config->timings_set = true;
-
 	switch (fitting_mode) {
 	case DRM_MODE_SCALE_CENTER:
 		/*
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index b0e4a0bd1313..f4c5e95b2d6f 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -30,8 +30,7 @@
 #include "intel_drv.h"
 #include "../../../platform/x86/intel_ips.h"
 #include <linux/module.h>
-
-#define FORCEWAKE_ACK_TIMEOUT_MS 2
+#include <drm/i915_powerwell.h>
 
 /* FBC, or Frame Buffer Compression, is a technique employed to compress the
  * framebuffer contents in-memory, aiming at reducing the required bandwidth
@@ -86,7 +85,7 @@ static void i8xx_enable_fbc(struct drm_crtc *crtc, unsigned long interval)
 	int plane, i;
 	u32 fbc_ctl, fbc_ctl2;
 
-	cfb_pitch = dev_priv->cfb_size / FBC_LL_SIZE;
+	cfb_pitch = dev_priv->fbc.size / FBC_LL_SIZE;
 	if (fb->pitches[0] < cfb_pitch)
 		cfb_pitch = fb->pitches[0];
 
@@ -217,7 +216,7 @@ static void ironlake_enable_fbc(struct drm_crtc *crtc, unsigned long interval)
 		   (stall_watermark << DPFC_RECOMP_STALL_WM_SHIFT) |
 		   (interval << DPFC_RECOMP_TIMER_COUNT_SHIFT));
 	I915_WRITE(ILK_DPFC_FENCE_YOFF, crtc->y);
-	I915_WRITE(ILK_FBC_RT_BASE, obj->gtt_offset | ILK_FBC_RT_VALID);
+	I915_WRITE(ILK_FBC_RT_BASE, i915_gem_obj_ggtt_offset(obj) | ILK_FBC_RT_VALID);
 	/* enable it... */
 	I915_WRITE(ILK_DPFC_CONTROL, dpfc_ctl | DPFC_CTL_EN);
 
@@ -274,7 +273,7 @@ static void gen7_enable_fbc(struct drm_crtc *crtc, unsigned long interval)
 	struct drm_i915_gem_object *obj = intel_fb->obj;
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 
-	I915_WRITE(IVB_FBC_RT_BASE, obj->gtt_offset);
+	I915_WRITE(IVB_FBC_RT_BASE, i915_gem_obj_ggtt_offset(obj));
 
 	I915_WRITE(ILK_DPFC_CONTROL, DPFC_CTL_EN | DPFC_CTL_LIMIT_1X |
 		   IVB_DPFC_CTL_FENCE_EN |
@@ -325,7 +324,7 @@ static void intel_fbc_work_fn(struct work_struct *__work)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
 	mutex_lock(&dev->struct_mutex);
-	if (work == dev_priv->fbc_work) {
+	if (work == dev_priv->fbc.fbc_work) {
 		/* Double check that we haven't switched fb without cancelling
 		 * the prior work.
 		 */
@@ -333,12 +332,12 @@ static void intel_fbc_work_fn(struct work_struct *__work)
 			dev_priv->display.enable_fbc(work->crtc,
 						     work->interval);
 
-			dev_priv->cfb_plane = to_intel_crtc(work->crtc)->plane;
-			dev_priv->cfb_fb = work->crtc->fb->base.id;
-			dev_priv->cfb_y = work->crtc->y;
+			dev_priv->fbc.plane = to_intel_crtc(work->crtc)->plane;
+			dev_priv->fbc.fb_id = work->crtc->fb->base.id;
+			dev_priv->fbc.y = work->crtc->y;
 		}
 
-		dev_priv->fbc_work = NULL;
+		dev_priv->fbc.fbc_work = NULL;
 	}
 	mutex_unlock(&dev->struct_mutex);
 
@@ -347,28 +346,28 @@ static void intel_fbc_work_fn(struct work_struct *__work)
 
 static void intel_cancel_fbc_work(struct drm_i915_private *dev_priv)
 {
-	if (dev_priv->fbc_work == NULL)
+	if (dev_priv->fbc.fbc_work == NULL)
 		return;
 
 	DRM_DEBUG_KMS("cancelling pending FBC enable\n");
 
 	/* Synchronisation is provided by struct_mutex and checking of
-	 * dev_priv->fbc_work, so we can perform the cancellation
+	 * dev_priv->fbc.fbc_work, so we can perform the cancellation
 	 * entirely asynchronously.
 	 */
-	if (cancel_delayed_work(&dev_priv->fbc_work->work))
+	if (cancel_delayed_work(&dev_priv->fbc.fbc_work->work))
 		/* tasklet was killed before being run, clean up */
-		kfree(dev_priv->fbc_work);
+		kfree(dev_priv->fbc.fbc_work);
 
 	/* Mark the work as no longer wanted so that if it does
 	 * wake-up (because the work was already running and waiting
 	 * for our mutex), it will discover that is no longer
 	 * necessary to run.
 	 */
-	dev_priv->fbc_work = NULL;
+	dev_priv->fbc.fbc_work = NULL;
 }
 
-void intel_enable_fbc(struct drm_crtc *crtc, unsigned long interval)
+static void intel_enable_fbc(struct drm_crtc *crtc, unsigned long interval)
 {
 	struct intel_fbc_work *work;
 	struct drm_device *dev = crtc->dev;
@@ -381,6 +380,7 @@ void intel_enable_fbc(struct drm_crtc *crtc, unsigned long interval)
 
 	work = kzalloc(sizeof *work, GFP_KERNEL);
 	if (work == NULL) {
+		DRM_ERROR("Failed to allocate FBC work structure\n");
 		dev_priv->display.enable_fbc(crtc, interval);
 		return;
 	}
@@ -390,9 +390,7 @@ void intel_enable_fbc(struct drm_crtc *crtc, unsigned long interval)
 	work->interval = interval;
 	INIT_DELAYED_WORK(&work->work, intel_fbc_work_fn);
 
-	dev_priv->fbc_work = work;
-
-	DRM_DEBUG_KMS("scheduling delayed FBC enable\n");
+	dev_priv->fbc.fbc_work = work;
 
 	/* Delay the actual enabling to let pageflipping cease and the
 	 * display to settle before starting the compression. Note that
@@ -404,6 +402,8 @@ void intel_enable_fbc(struct drm_crtc *crtc, unsigned long interval)
 	 * following the termination of the page-flipping sequence
 	 * and indeed performing the enable as a co-routine and not
 	 * waiting synchronously upon the vblank.
+	 *
+	 * WaFbcWaitForVBlankBeforeEnable:ilk,snb
 	 */
 	schedule_delayed_work(&work->work, msecs_to_jiffies(50));
 }
@@ -418,7 +418,17 @@ void intel_disable_fbc(struct drm_device *dev)
 		return;
 
 	dev_priv->display.disable_fbc(dev);
-	dev_priv->cfb_plane = -1;
+	dev_priv->fbc.plane = -1;
+}
+
+static bool set_no_fbc_reason(struct drm_i915_private *dev_priv,
+			      enum no_fbc_reason reason)
+{
+	if (dev_priv->fbc.no_fbc_reason == reason)
+		return false;
+
+	dev_priv->fbc.no_fbc_reason = reason;
+	return true;
 }
 
 /**
@@ -448,14 +458,18 @@ void intel_update_fbc(struct drm_device *dev)
 	struct drm_framebuffer *fb;
 	struct intel_framebuffer *intel_fb;
 	struct drm_i915_gem_object *obj;
-	int enable_fbc;
 	unsigned int max_hdisplay, max_vdisplay;
 
-	if (!i915_powersave)
+	if (!I915_HAS_FBC(dev)) {
+		set_no_fbc_reason(dev_priv, FBC_UNSUPPORTED);
 		return;
+	}
 
-	if (!I915_HAS_FBC(dev))
+	if (!i915_powersave) {
+		if (set_no_fbc_reason(dev_priv, FBC_MODULE_PARAM))
+			DRM_DEBUG_KMS("fbc disabled per module param\n");
 		return;
+	}
 
 	/*
 	 * If FBC is already on, we just have to verify that we can
@@ -470,8 +484,8 @@ void intel_update_fbc(struct drm_device *dev)
 		if (intel_crtc_active(tmp_crtc) &&
 		    !to_intel_crtc(tmp_crtc)->primary_disabled) {
 			if (crtc) {
-				DRM_DEBUG_KMS("more than one pipe active, disabling compression\n");
-				dev_priv->no_fbc_reason = FBC_MULTIPLE_PIPES;
+				if (set_no_fbc_reason(dev_priv, FBC_MULTIPLE_PIPES))
+					DRM_DEBUG_KMS("more than one pipe active, disabling compression\n");
 				goto out_disable;
 			}
 			crtc = tmp_crtc;
@@ -479,8 +493,8 @@ void intel_update_fbc(struct drm_device *dev)
 	}
 
 	if (!crtc || crtc->fb == NULL) {
-		DRM_DEBUG_KMS("no output, disabling\n");
-		dev_priv->no_fbc_reason = FBC_NO_OUTPUT;
+		if (set_no_fbc_reason(dev_priv, FBC_NO_OUTPUT))
+			DRM_DEBUG_KMS("no output, disabling\n");
 		goto out_disable;
 	}
 
@@ -489,23 +503,22 @@ void intel_update_fbc(struct drm_device *dev)
 	intel_fb = to_intel_framebuffer(fb);
 	obj = intel_fb->obj;
 
-	enable_fbc = i915_enable_fbc;
-	if (enable_fbc < 0) {
-		DRM_DEBUG_KMS("fbc set to per-chip default\n");
-		enable_fbc = 1;
-		if (INTEL_INFO(dev)->gen <= 7 && !IS_HASWELL(dev))
-			enable_fbc = 0;
+	if (i915_enable_fbc < 0 &&
+	    INTEL_INFO(dev)->gen <= 7 && !IS_HASWELL(dev)) {
+		if (set_no_fbc_reason(dev_priv, FBC_CHIP_DEFAULT))
+			DRM_DEBUG_KMS("disabled per chip default\n");
+		goto out_disable;
 	}
-	if (!enable_fbc) {
-		DRM_DEBUG_KMS("fbc disabled per module param\n");
-		dev_priv->no_fbc_reason = FBC_MODULE_PARAM;
+	if (!i915_enable_fbc) {
+		if (set_no_fbc_reason(dev_priv, FBC_MODULE_PARAM))
+			DRM_DEBUG_KMS("fbc disabled per module param\n");
 		goto out_disable;
 	}
 	if ((crtc->mode.flags & DRM_MODE_FLAG_INTERLACE) ||
 	    (crtc->mode.flags & DRM_MODE_FLAG_DBLSCAN)) {
-		DRM_DEBUG_KMS("mode incompatible with compression, "
-			      "disabling\n");
-		dev_priv->no_fbc_reason = FBC_UNSUPPORTED_MODE;
+		if (set_no_fbc_reason(dev_priv, FBC_UNSUPPORTED_MODE))
+			DRM_DEBUG_KMS("mode incompatible with compression, "
+				      "disabling\n");
 		goto out_disable;
 	}
 
@@ -518,14 +531,14 @@ void intel_update_fbc(struct drm_device *dev)
 	}
 	if ((crtc->mode.hdisplay > max_hdisplay) ||
 	    (crtc->mode.vdisplay > max_vdisplay)) {
-		DRM_DEBUG_KMS("mode too large for compression, disabling\n");
-		dev_priv->no_fbc_reason = FBC_MODE_TOO_LARGE;
+		if (set_no_fbc_reason(dev_priv, FBC_MODE_TOO_LARGE))
+			DRM_DEBUG_KMS("mode too large for compression, disabling\n");
 		goto out_disable;
 	}
 	if ((IS_I915GM(dev) || IS_I945GM(dev) || IS_HASWELL(dev)) &&
 	    intel_crtc->plane != 0) {
-		DRM_DEBUG_KMS("plane not 0, disabling compression\n");
-		dev_priv->no_fbc_reason = FBC_BAD_PLANE;
+		if (set_no_fbc_reason(dev_priv, FBC_BAD_PLANE))
+			DRM_DEBUG_KMS("plane not 0, disabling compression\n");
 		goto out_disable;
 	}
 
@@ -534,8 +547,8 @@ void intel_update_fbc(struct drm_device *dev)
 	 */
 	if (obj->tiling_mode != I915_TILING_X ||
 	    obj->fence_reg == I915_FENCE_REG_NONE) {
-		DRM_DEBUG_KMS("framebuffer not tiled or fenced, disabling compression\n");
-		dev_priv->no_fbc_reason = FBC_NOT_TILED;
+		if (set_no_fbc_reason(dev_priv, FBC_NOT_TILED))
+			DRM_DEBUG_KMS("framebuffer not tiled or fenced, disabling compression\n");
 		goto out_disable;
 	}
 
@@ -544,8 +557,8 @@ void intel_update_fbc(struct drm_device *dev)
 		goto out_disable;
 
 	if (i915_gem_stolen_setup_compression(dev, intel_fb->obj->base.size)) {
-		DRM_DEBUG_KMS("framebuffer too large, disabling compression\n");
-		dev_priv->no_fbc_reason = FBC_STOLEN_TOO_SMALL;
+		if (set_no_fbc_reason(dev_priv, FBC_STOLEN_TOO_SMALL))
+			DRM_DEBUG_KMS("framebuffer too large, disabling compression\n");
 		goto out_disable;
 	}
 
@@ -554,9 +567,9 @@ void intel_update_fbc(struct drm_device *dev)
 	 * cannot be unpinned (and have its GTT offset and fence revoked)
 	 * without first being decoupled from the scanout and FBC disabled.
 	 */
-	if (dev_priv->cfb_plane == intel_crtc->plane &&
-	    dev_priv->cfb_fb == fb->base.id &&
-	    dev_priv->cfb_y == crtc->y)
+	if (dev_priv->fbc.plane == intel_crtc->plane &&
+	    dev_priv->fbc.fb_id == fb->base.id &&
+	    dev_priv->fbc.y == crtc->y)
 		return;
 
 	if (intel_fbc_enabled(dev)) {
@@ -588,6 +601,7 @@ void intel_update_fbc(struct drm_device *dev)
 	}
 
 	intel_enable_fbc(crtc, 500);
+	dev_priv->fbc.no_fbc_reason = FBC_OK;
 	return;
 
 out_disable:
@@ -1666,9 +1680,6 @@ static void i830_update_wm(struct drm_device *dev)
 	I915_WRITE(FW_BLC, fwater_lo);
 }
 
-#define ILK_LP0_PLANE_LATENCY		700
-#define ILK_LP0_CURSOR_LATENCY		1300
-
 /*
  * Check the wm result.
  *
@@ -1783,9 +1794,9 @@ static void ironlake_update_wm(struct drm_device *dev)
 	enabled = 0;
 	if (g4x_compute_wm0(dev, PIPE_A,
 			    &ironlake_display_wm_info,
-			    ILK_LP0_PLANE_LATENCY,
+			    dev_priv->wm.pri_latency[0] * 100,
 			    &ironlake_cursor_wm_info,
-			    ILK_LP0_CURSOR_LATENCY,
+			    dev_priv->wm.cur_latency[0] * 100,
 			    &plane_wm, &cursor_wm)) {
 		I915_WRITE(WM0_PIPEA_ILK,
 			   (plane_wm << WM0_PIPE_PLANE_SHIFT) | cursor_wm);
@@ -1797,9 +1808,9 @@ static void ironlake_update_wm(struct drm_device *dev)
 
 	if (g4x_compute_wm0(dev, PIPE_B,
 			    &ironlake_display_wm_info,
-			    ILK_LP0_PLANE_LATENCY,
+			    dev_priv->wm.pri_latency[0] * 100,
 			    &ironlake_cursor_wm_info,
-			    ILK_LP0_CURSOR_LATENCY,
+			    dev_priv->wm.cur_latency[0] * 100,
 			    &plane_wm, &cursor_wm)) {
 		I915_WRITE(WM0_PIPEB_ILK,
 			   (plane_wm << WM0_PIPE_PLANE_SHIFT) | cursor_wm);
@@ -1823,7 +1834,7 @@ static void ironlake_update_wm(struct drm_device *dev)
 
 	/* WM1 */
 	if (!ironlake_compute_srwm(dev, 1, enabled,
-				   ILK_READ_WM1_LATENCY() * 500,
+				   dev_priv->wm.pri_latency[1] * 500,
 				   &ironlake_display_srwm_info,
 				   &ironlake_cursor_srwm_info,
 				   &fbc_wm, &plane_wm, &cursor_wm))
@@ -1831,14 +1842,14 @@ static void ironlake_update_wm(struct drm_device *dev)
 
 	I915_WRITE(WM1_LP_ILK,
 		   WM1_LP_SR_EN |
-		   (ILK_READ_WM1_LATENCY() << WM1_LP_LATENCY_SHIFT) |
+		   (dev_priv->wm.pri_latency[1] << WM1_LP_LATENCY_SHIFT) |
 		   (fbc_wm << WM1_LP_FBC_SHIFT) |
 		   (plane_wm << WM1_LP_SR_SHIFT) |
 		   cursor_wm);
 
 	/* WM2 */
 	if (!ironlake_compute_srwm(dev, 2, enabled,
-				   ILK_READ_WM2_LATENCY() * 500,
+				   dev_priv->wm.pri_latency[2] * 500,
 				   &ironlake_display_srwm_info,
 				   &ironlake_cursor_srwm_info,
 				   &fbc_wm, &plane_wm, &cursor_wm))
@@ -1846,7 +1857,7 @@ static void ironlake_update_wm(struct drm_device *dev)
 
 	I915_WRITE(WM2_LP_ILK,
 		   WM2_LP_EN |
-		   (ILK_READ_WM2_LATENCY() << WM1_LP_LATENCY_SHIFT) |
+		   (dev_priv->wm.pri_latency[2] << WM1_LP_LATENCY_SHIFT) |
 		   (fbc_wm << WM1_LP_FBC_SHIFT) |
 		   (plane_wm << WM1_LP_SR_SHIFT) |
 		   cursor_wm);
@@ -1860,7 +1871,7 @@ static void ironlake_update_wm(struct drm_device *dev)
 static void sandybridge_update_wm(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	int latency = SNB_READ_WM0_LATENCY() * 100;	/* In unit 0.1us */
+	int latency = dev_priv->wm.pri_latency[0] * 100;	/* In unit 0.1us */
 	u32 val;
 	int fbc_wm, plane_wm, cursor_wm;
 	unsigned int enabled;
@@ -1915,7 +1926,7 @@ static void sandybridge_update_wm(struct drm_device *dev)
 
 	/* WM1 */
 	if (!ironlake_compute_srwm(dev, 1, enabled,
-				   SNB_READ_WM1_LATENCY() * 500,
+				   dev_priv->wm.pri_latency[1] * 500,
 				   &sandybridge_display_srwm_info,
 				   &sandybridge_cursor_srwm_info,
 				   &fbc_wm, &plane_wm, &cursor_wm))
@@ -1923,14 +1934,14 @@ static void sandybridge_update_wm(struct drm_device *dev)
 
 	I915_WRITE(WM1_LP_ILK,
 		   WM1_LP_SR_EN |
-		   (SNB_READ_WM1_LATENCY() << WM1_LP_LATENCY_SHIFT) |
+		   (dev_priv->wm.pri_latency[1] << WM1_LP_LATENCY_SHIFT) |
 		   (fbc_wm << WM1_LP_FBC_SHIFT) |
 		   (plane_wm << WM1_LP_SR_SHIFT) |
 		   cursor_wm);
 
 	/* WM2 */
 	if (!ironlake_compute_srwm(dev, 2, enabled,
-				   SNB_READ_WM2_LATENCY() * 500,
+				   dev_priv->wm.pri_latency[2] * 500,
 				   &sandybridge_display_srwm_info,
 				   &sandybridge_cursor_srwm_info,
 				   &fbc_wm, &plane_wm, &cursor_wm))
@@ -1938,14 +1949,14 @@ static void sandybridge_update_wm(struct drm_device *dev)
 
 	I915_WRITE(WM2_LP_ILK,
 		   WM2_LP_EN |
-		   (SNB_READ_WM2_LATENCY() << WM1_LP_LATENCY_SHIFT) |
+		   (dev_priv->wm.pri_latency[2] << WM1_LP_LATENCY_SHIFT) |
 		   (fbc_wm << WM1_LP_FBC_SHIFT) |
 		   (plane_wm << WM1_LP_SR_SHIFT) |
 		   cursor_wm);
 
 	/* WM3 */
 	if (!ironlake_compute_srwm(dev, 3, enabled,
-				   SNB_READ_WM3_LATENCY() * 500,
+				   dev_priv->wm.pri_latency[3] * 500,
 				   &sandybridge_display_srwm_info,
 				   &sandybridge_cursor_srwm_info,
 				   &fbc_wm, &plane_wm, &cursor_wm))
@@ -1953,7 +1964,7 @@ static void sandybridge_update_wm(struct drm_device *dev)
 
 	I915_WRITE(WM3_LP_ILK,
 		   WM3_LP_EN |
-		   (SNB_READ_WM3_LATENCY() << WM1_LP_LATENCY_SHIFT) |
+		   (dev_priv->wm.pri_latency[3] << WM1_LP_LATENCY_SHIFT) |
 		   (fbc_wm << WM1_LP_FBC_SHIFT) |
 		   (plane_wm << WM1_LP_SR_SHIFT) |
 		   cursor_wm);
@@ -1962,7 +1973,7 @@ static void sandybridge_update_wm(struct drm_device *dev)
 static void ivybridge_update_wm(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	int latency = SNB_READ_WM0_LATENCY() * 100;	/* In unit 0.1us */
+	int latency = dev_priv->wm.pri_latency[0] * 100;	/* In unit 0.1us */
 	u32 val;
 	int fbc_wm, plane_wm, cursor_wm;
 	int ignore_fbc_wm, ignore_plane_wm, ignore_cursor_wm;
@@ -2032,7 +2043,7 @@ static void ivybridge_update_wm(struct drm_device *dev)
 
 	/* WM1 */
 	if (!ironlake_compute_srwm(dev, 1, enabled,
-				   SNB_READ_WM1_LATENCY() * 500,
+				   dev_priv->wm.pri_latency[1] * 500,
 				   &sandybridge_display_srwm_info,
 				   &sandybridge_cursor_srwm_info,
 				   &fbc_wm, &plane_wm, &cursor_wm))
@@ -2040,14 +2051,14 @@ static void ivybridge_update_wm(struct drm_device *dev)
 
 	I915_WRITE(WM1_LP_ILK,
 		   WM1_LP_SR_EN |
-		   (SNB_READ_WM1_LATENCY() << WM1_LP_LATENCY_SHIFT) |
+		   (dev_priv->wm.pri_latency[1] << WM1_LP_LATENCY_SHIFT) |
 		   (fbc_wm << WM1_LP_FBC_SHIFT) |
 		   (plane_wm << WM1_LP_SR_SHIFT) |
 		   cursor_wm);
 
 	/* WM2 */
 	if (!ironlake_compute_srwm(dev, 2, enabled,
-				   SNB_READ_WM2_LATENCY() * 500,
+				   dev_priv->wm.pri_latency[2] * 500,
 				   &sandybridge_display_srwm_info,
 				   &sandybridge_cursor_srwm_info,
 				   &fbc_wm, &plane_wm, &cursor_wm))
@@ -2055,19 +2066,19 @@ static void ivybridge_update_wm(struct drm_device *dev)
 
 	I915_WRITE(WM2_LP_ILK,
 		   WM2_LP_EN |
-		   (SNB_READ_WM2_LATENCY() << WM1_LP_LATENCY_SHIFT) |
+		   (dev_priv->wm.pri_latency[2] << WM1_LP_LATENCY_SHIFT) |
 		   (fbc_wm << WM1_LP_FBC_SHIFT) |
 		   (plane_wm << WM1_LP_SR_SHIFT) |
 		   cursor_wm);
 
 	/* WM3, note we have to correct the cursor latency */
 	if (!ironlake_compute_srwm(dev, 3, enabled,
-				   SNB_READ_WM3_LATENCY() * 500,
+				   dev_priv->wm.pri_latency[3] * 500,
 				   &sandybridge_display_srwm_info,
 				   &sandybridge_cursor_srwm_info,
 				   &fbc_wm, &plane_wm, &ignore_cursor_wm) ||
 	    !ironlake_compute_srwm(dev, 3, enabled,
-				   2 * SNB_READ_WM3_LATENCY() * 500,
+				   dev_priv->wm.cur_latency[3] * 500,
 				   &sandybridge_display_srwm_info,
 				   &sandybridge_cursor_srwm_info,
 				   &ignore_fbc_wm, &ignore_plane_wm, &cursor_wm))
@@ -2075,26 +2086,26 @@ static void ivybridge_update_wm(struct drm_device *dev)
 
 	I915_WRITE(WM3_LP_ILK,
 		   WM3_LP_EN |
-		   (SNB_READ_WM3_LATENCY() << WM1_LP_LATENCY_SHIFT) |
+		   (dev_priv->wm.pri_latency[3] << WM1_LP_LATENCY_SHIFT) |
 		   (fbc_wm << WM1_LP_FBC_SHIFT) |
 		   (plane_wm << WM1_LP_SR_SHIFT) |
 		   cursor_wm);
 }
 
-static uint32_t hsw_wm_get_pixel_rate(struct drm_device *dev,
-				      struct drm_crtc *crtc)
+static uint32_t ilk_pipe_pixel_rate(struct drm_device *dev,
+				    struct drm_crtc *crtc)
 {
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	uint32_t pixel_rate, pfit_size;
+	uint32_t pixel_rate;
 
 	pixel_rate = intel_crtc->config.adjusted_mode.clock;
 
 	/* We only use IF-ID interlacing. If we ever use PF-ID we'll need to
 	 * adjust the pixel_rate here. */
 
-	pfit_size = intel_crtc->config.pch_pfit.size;
-	if (pfit_size) {
+	if (intel_crtc->config.pch_pfit.enabled) {
 		uint64_t pipe_w, pipe_h, pfit_w, pfit_h;
+		uint32_t pfit_size = intel_crtc->config.pch_pfit.size;
 
 		pipe_w = intel_crtc->config.requested_mode.hdisplay;
 		pipe_h = intel_crtc->config.requested_mode.vdisplay;
@@ -2112,30 +2123,38 @@ static uint32_t hsw_wm_get_pixel_rate(struct drm_device *dev,
 	return pixel_rate;
 }
 
-static uint32_t hsw_wm_method1(uint32_t pixel_rate, uint8_t bytes_per_pixel,
+/* latency must be in 0.1us units. */
+static uint32_t ilk_wm_method1(uint32_t pixel_rate, uint8_t bytes_per_pixel,
 			       uint32_t latency)
 {
 	uint64_t ret;
 
+	if (WARN(latency == 0, "Latency value missing\n"))
+		return UINT_MAX;
+
 	ret = (uint64_t) pixel_rate * bytes_per_pixel * latency;
 	ret = DIV_ROUND_UP_ULL(ret, 64 * 10000) + 2;
 
 	return ret;
 }
 
-static uint32_t hsw_wm_method2(uint32_t pixel_rate, uint32_t pipe_htotal,
+/* latency must be in 0.1us units. */
+static uint32_t ilk_wm_method2(uint32_t pixel_rate, uint32_t pipe_htotal,
 			       uint32_t horiz_pixels, uint8_t bytes_per_pixel,
 			       uint32_t latency)
 {
 	uint32_t ret;
 
+	if (WARN(latency == 0, "Latency value missing\n"))
+		return UINT_MAX;
+
 	ret = (latency * pixel_rate) / (pipe_htotal * 10000);
 	ret = (ret + 1) * horiz_pixels * bytes_per_pixel;
 	ret = DIV_ROUND_UP(ret, 64) + 2;
 	return ret;
 }
 
-static uint32_t hsw_wm_fbc(uint32_t pri_val, uint32_t horiz_pixels,
+static uint32_t ilk_wm_fbc(uint32_t pri_val, uint32_t horiz_pixels,
 			   uint8_t bytes_per_pixel)
 {
 	return DIV_ROUND_UP(pri_val * 64, horiz_pixels * bytes_per_pixel) + 2;
@@ -2143,15 +2162,11 @@ static uint32_t hsw_wm_fbc(uint32_t pri_val, uint32_t horiz_pixels,
 
 struct hsw_pipe_wm_parameters {
 	bool active;
-	bool sprite_enabled;
-	uint8_t pri_bytes_per_pixel;
-	uint8_t spr_bytes_per_pixel;
-	uint8_t cur_bytes_per_pixel;
-	uint32_t pri_horiz_pixels;
-	uint32_t spr_horiz_pixels;
-	uint32_t cur_horiz_pixels;
 	uint32_t pipe_htotal;
 	uint32_t pixel_rate;
+	struct intel_plane_wm_parameters pri;
+	struct intel_plane_wm_parameters spr;
+	struct intel_plane_wm_parameters cur;
 };
 
 struct hsw_wm_maximums {
@@ -2161,15 +2176,6 @@ struct hsw_wm_maximums {
 	uint16_t fbc;
 };
 
-struct hsw_lp_wm_result {
-	bool enable;
-	bool fbc_enable;
-	uint32_t pri_val;
-	uint32_t spr_val;
-	uint32_t cur_val;
-	uint32_t fbc_val;
-};
-
 struct hsw_wm_values {
 	uint32_t wm_pipe[3];
 	uint32_t wm_lp[3];
@@ -2178,128 +2184,289 @@ struct hsw_wm_values {
 	bool enable_fbc_wm;
 };
 
-enum hsw_data_buf_partitioning {
-	HSW_DATA_BUF_PART_1_2,
-	HSW_DATA_BUF_PART_5_6,
+/* used in computing the new watermarks state */
+struct intel_wm_config {
+	unsigned int num_pipes_active;
+	bool sprites_enabled;
+	bool sprites_scaled;
+	bool fbc_wm_enabled;
 };
 
-/* For both WM_PIPE and WM_LP. */
-static uint32_t hsw_compute_pri_wm(struct hsw_pipe_wm_parameters *params,
+/*
+ * For both WM_PIPE and WM_LP.
+ * mem_value must be in 0.1us units.
+ */
+static uint32_t ilk_compute_pri_wm(struct hsw_pipe_wm_parameters *params,
 				   uint32_t mem_value,
 				   bool is_lp)
 {
 	uint32_t method1, method2;
 
-	/* TODO: for now, assume the primary plane is always enabled. */
-	if (!params->active)
+	if (!params->active || !params->pri.enabled)
 		return 0;
 
-	method1 = hsw_wm_method1(params->pixel_rate,
-				 params->pri_bytes_per_pixel,
+	method1 = ilk_wm_method1(params->pixel_rate,
+				 params->pri.bytes_per_pixel,
 				 mem_value);
 
 	if (!is_lp)
 		return method1;
 
-	method2 = hsw_wm_method2(params->pixel_rate,
+	method2 = ilk_wm_method2(params->pixel_rate,
 				 params->pipe_htotal,
-				 params->pri_horiz_pixels,
-				 params->pri_bytes_per_pixel,
+				 params->pri.horiz_pixels,
+				 params->pri.bytes_per_pixel,
 				 mem_value);
 
 	return min(method1, method2);
 }
 
-/* For both WM_PIPE and WM_LP. */
-static uint32_t hsw_compute_spr_wm(struct hsw_pipe_wm_parameters *params,
+/*
+ * For both WM_PIPE and WM_LP.
+ * mem_value must be in 0.1us units.
+ */
+static uint32_t ilk_compute_spr_wm(struct hsw_pipe_wm_parameters *params,
 				   uint32_t mem_value)
 {
 	uint32_t method1, method2;
 
-	if (!params->active || !params->sprite_enabled)
+	if (!params->active || !params->spr.enabled)
 		return 0;
 
-	method1 = hsw_wm_method1(params->pixel_rate,
-				 params->spr_bytes_per_pixel,
+	method1 = ilk_wm_method1(params->pixel_rate,
+				 params->spr.bytes_per_pixel,
 				 mem_value);
-	method2 = hsw_wm_method2(params->pixel_rate,
+	method2 = ilk_wm_method2(params->pixel_rate,
 				 params->pipe_htotal,
-				 params->spr_horiz_pixels,
-				 params->spr_bytes_per_pixel,
+				 params->spr.horiz_pixels,
+				 params->spr.bytes_per_pixel,
 				 mem_value);
 	return min(method1, method2);
 }
 
-/* For both WM_PIPE and WM_LP. */
-static uint32_t hsw_compute_cur_wm(struct hsw_pipe_wm_parameters *params,
+/*
+ * For both WM_PIPE and WM_LP.
+ * mem_value must be in 0.1us units.
+ */
+static uint32_t ilk_compute_cur_wm(struct hsw_pipe_wm_parameters *params,
 				   uint32_t mem_value)
 {
-	if (!params->active)
+	if (!params->active || !params->cur.enabled)
 		return 0;
 
-	return hsw_wm_method2(params->pixel_rate,
+	return ilk_wm_method2(params->pixel_rate,
 			      params->pipe_htotal,
-			      params->cur_horiz_pixels,
-			      params->cur_bytes_per_pixel,
+			      params->cur.horiz_pixels,
+			      params->cur.bytes_per_pixel,
 			      mem_value);
 }
 
 /* Only for WM_LP. */
-static uint32_t hsw_compute_fbc_wm(struct hsw_pipe_wm_parameters *params,
-				   uint32_t pri_val,
-				   uint32_t mem_value)
+static uint32_t ilk_compute_fbc_wm(struct hsw_pipe_wm_parameters *params,
+				   uint32_t pri_val)
 {
-	if (!params->active)
+	if (!params->active || !params->pri.enabled)
 		return 0;
 
-	return hsw_wm_fbc(pri_val,
-			  params->pri_horiz_pixels,
-			  params->pri_bytes_per_pixel);
+	return ilk_wm_fbc(pri_val,
+			  params->pri.horiz_pixels,
+			  params->pri.bytes_per_pixel);
 }
 
-static bool hsw_compute_lp_wm(uint32_t mem_value, struct hsw_wm_maximums *max,
-			      struct hsw_pipe_wm_parameters *params,
-			      struct hsw_lp_wm_result *result)
+static unsigned int ilk_display_fifo_size(const struct drm_device *dev)
 {
-	enum pipe pipe;
-	uint32_t pri_val[3], spr_val[3], cur_val[3], fbc_val[3];
+	if (INTEL_INFO(dev)->gen >= 7)
+		return 768;
+	else
+		return 512;
+}
 
-	for (pipe = PIPE_A; pipe <= PIPE_C; pipe++) {
-		struct hsw_pipe_wm_parameters *p = &params[pipe];
+/* Calculate the maximum primary/sprite plane watermark */
+static unsigned int ilk_plane_wm_max(const struct drm_device *dev,
+				     int level,
+				     const struct intel_wm_config *config,
+				     enum intel_ddb_partitioning ddb_partitioning,
+				     bool is_sprite)
+{
+	unsigned int fifo_size = ilk_display_fifo_size(dev);
+	unsigned int max;
 
-		pri_val[pipe] = hsw_compute_pri_wm(p, mem_value, true);
-		spr_val[pipe] = hsw_compute_spr_wm(p, mem_value);
-		cur_val[pipe] = hsw_compute_cur_wm(p, mem_value);
-		fbc_val[pipe] = hsw_compute_fbc_wm(p, pri_val[pipe], mem_value);
-	}
+	/* if sprites aren't enabled, sprites get nothing */
+	if (is_sprite && !config->sprites_enabled)
+		return 0;
 
-	result->pri_val = max3(pri_val[0], pri_val[1], pri_val[2]);
-	result->spr_val = max3(spr_val[0], spr_val[1], spr_val[2]);
-	result->cur_val = max3(cur_val[0], cur_val[1], cur_val[2]);
-	result->fbc_val = max3(fbc_val[0], fbc_val[1], fbc_val[2]);
+	/* HSW allows LP1+ watermarks even with multiple pipes */
+	if (level == 0 || config->num_pipes_active > 1) {
+		fifo_size /= INTEL_INFO(dev)->num_pipes;
 
-	if (result->fbc_val > max->fbc) {
-		result->fbc_enable = false;
-		result->fbc_val = 0;
-	} else {
-		result->fbc_enable = true;
+		/*
+		 * For some reason the non self refresh
+		 * FIFO size is only half of the self
+		 * refresh FIFO size on ILK/SNB.
+		 */
+		if (INTEL_INFO(dev)->gen <= 6)
+			fifo_size /= 2;
+	}
+
+	if (config->sprites_enabled) {
+		/* level 0 is always calculated with 1:1 split */
+		if (level > 0 && ddb_partitioning == INTEL_DDB_PART_5_6) {
+			if (is_sprite)
+				fifo_size *= 5;
+			fifo_size /= 6;
+		} else {
+			fifo_size /= 2;
+		}
 	}
 
+	/* clamp to max that the registers can hold */
+	if (INTEL_INFO(dev)->gen >= 7)
+		/* IVB/HSW primary/sprite plane watermarks */
+		max = level == 0 ? 127 : 1023;
+	else if (!is_sprite)
+		/* ILK/SNB primary plane watermarks */
+		max = level == 0 ? 127 : 511;
+	else
+		/* ILK/SNB sprite plane watermarks */
+		max = level == 0 ? 63 : 255;
+
+	return min(fifo_size, max);
+}
+
+/* Calculate the maximum cursor plane watermark */
+static unsigned int ilk_cursor_wm_max(const struct drm_device *dev,
+				      int level,
+				      const struct intel_wm_config *config)
+{
+	/* HSW LP1+ watermarks w/ multiple pipes */
+	if (level > 0 && config->num_pipes_active > 1)
+		return 64;
+
+	/* otherwise just report max that registers can hold */
+	if (INTEL_INFO(dev)->gen >= 7)
+		return level == 0 ? 63 : 255;
+	else
+		return level == 0 ? 31 : 63;
+}
+
+/* Calculate the maximum FBC watermark */
+static unsigned int ilk_fbc_wm_max(void)
+{
+	/* max that registers can hold */
+	return 15;
+}
+
+static void ilk_wm_max(struct drm_device *dev,
+		       int level,
+		       const struct intel_wm_config *config,
+		       enum intel_ddb_partitioning ddb_partitioning,
+		       struct hsw_wm_maximums *max)
+{
+	max->pri = ilk_plane_wm_max(dev, level, config, ddb_partitioning, false);
+	max->spr = ilk_plane_wm_max(dev, level, config, ddb_partitioning, true);
+	max->cur = ilk_cursor_wm_max(dev, level, config);
+	max->fbc = ilk_fbc_wm_max();
+}
+
+static bool ilk_check_wm(int level,
+			 const struct hsw_wm_maximums *max,
+			 struct intel_wm_level *result)
+{
+	bool ret;
+
+	/* already determined to be invalid? */
+	if (!result->enable)
+		return false;
+
 	result->enable = result->pri_val <= max->pri &&
 			 result->spr_val <= max->spr &&
 			 result->cur_val <= max->cur;
-	return result->enable;
+
+	ret = result->enable;
+
+	/*
+	 * HACK until we can pre-compute everything,
+	 * and thus fail gracefully if LP0 watermarks
+	 * are exceeded...
+	 */
+	if (level == 0 && !result->enable) {
+		if (result->pri_val > max->pri)
+			DRM_DEBUG_KMS("Primary WM%d too large %u (max %u)\n",
+				      level, result->pri_val, max->pri);
+		if (result->spr_val > max->spr)
+			DRM_DEBUG_KMS("Sprite WM%d too large %u (max %u)\n",
+				      level, result->spr_val, max->spr);
+		if (result->cur_val > max->cur)
+			DRM_DEBUG_KMS("Cursor WM%d too large %u (max %u)\n",
+				      level, result->cur_val, max->cur);
+
+		result->pri_val = min_t(uint32_t, result->pri_val, max->pri);
+		result->spr_val = min_t(uint32_t, result->spr_val, max->spr);
+		result->cur_val = min_t(uint32_t, result->cur_val, max->cur);
+		result->enable = true;
+	}
+
+	DRM_DEBUG_KMS("WM%d: %sabled\n", level, result->enable ? "en" : "dis");
+
+	return ret;
+}
+
+static void ilk_compute_wm_level(struct drm_i915_private *dev_priv,
+				 int level,
+				 struct hsw_pipe_wm_parameters *p,
+				 struct intel_wm_level *result)
+{
+	uint16_t pri_latency = dev_priv->wm.pri_latency[level];
+	uint16_t spr_latency = dev_priv->wm.spr_latency[level];
+	uint16_t cur_latency = dev_priv->wm.cur_latency[level];
+
+	/* WM1+ latency values stored in 0.5us units */
+	if (level > 0) {
+		pri_latency *= 5;
+		spr_latency *= 5;
+		cur_latency *= 5;
+	}
+
+	result->pri_val = ilk_compute_pri_wm(p, pri_latency, level);
+	result->spr_val = ilk_compute_spr_wm(p, spr_latency);
+	result->cur_val = ilk_compute_cur_wm(p, cur_latency);
+	result->fbc_val = ilk_compute_fbc_wm(p, result->pri_val);
+	result->enable = true;
+}
+
+static bool hsw_compute_lp_wm(struct drm_i915_private *dev_priv,
+			      int level, struct hsw_wm_maximums *max,
+			      struct hsw_pipe_wm_parameters *params,
+			      struct intel_wm_level *result)
+{
+	enum pipe pipe;
+	struct intel_wm_level res[3];
+
+	for (pipe = PIPE_A; pipe <= PIPE_C; pipe++)
+		ilk_compute_wm_level(dev_priv, level, &params[pipe], &res[pipe]);
+
+	result->pri_val = max3(res[0].pri_val, res[1].pri_val, res[2].pri_val);
+	result->spr_val = max3(res[0].spr_val, res[1].spr_val, res[2].spr_val);
+	result->cur_val = max3(res[0].cur_val, res[1].cur_val, res[2].cur_val);
+	result->fbc_val = max3(res[0].fbc_val, res[1].fbc_val, res[2].fbc_val);
+	result->enable = true;
+
+	return ilk_check_wm(level, max, result);
 }
 
 static uint32_t hsw_compute_wm_pipe(struct drm_i915_private *dev_priv,
-				    uint32_t mem_value, enum pipe pipe,
+				    enum pipe pipe,
 				    struct hsw_pipe_wm_parameters *params)
 {
 	uint32_t pri_val, cur_val, spr_val;
+	/* WM0 latency values stored in 0.1us units */
+	uint16_t pri_latency = dev_priv->wm.pri_latency[0];
+	uint16_t spr_latency = dev_priv->wm.spr_latency[0];
+	uint16_t cur_latency = dev_priv->wm.cur_latency[0];
 
-	pri_val = hsw_compute_pri_wm(params, mem_value, false);
-	spr_val = hsw_compute_spr_wm(params, mem_value);
-	cur_val = hsw_compute_cur_wm(params, mem_value);
+	pri_val = ilk_compute_pri_wm(params, pri_latency, false);
+	spr_val = ilk_compute_spr_wm(params, spr_latency);
+	cur_val = ilk_compute_cur_wm(params, cur_latency);
 
 	WARN(pri_val > 127,
 	     "Primary WM error, mode not supported for pipe %c\n",
@@ -2338,27 +2505,116 @@ hsw_compute_linetime_wm(struct drm_device *dev, struct drm_crtc *crtc)
 	       PIPE_WM_LINETIME_TIME(linetime);
 }
 
+static void intel_read_wm_latency(struct drm_device *dev, uint16_t wm[5])
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	if (IS_HASWELL(dev)) {
+		uint64_t sskpd = I915_READ64(MCH_SSKPD);
+
+		wm[0] = (sskpd >> 56) & 0xFF;
+		if (wm[0] == 0)
+			wm[0] = sskpd & 0xF;
+		wm[1] = (sskpd >> 4) & 0xFF;
+		wm[2] = (sskpd >> 12) & 0xFF;
+		wm[3] = (sskpd >> 20) & 0x1FF;
+		wm[4] = (sskpd >> 32) & 0x1FF;
+	} else if (INTEL_INFO(dev)->gen >= 6) {
+		uint32_t sskpd = I915_READ(MCH_SSKPD);
+
+		wm[0] = (sskpd >> SSKPD_WM0_SHIFT) & SSKPD_WM_MASK;
+		wm[1] = (sskpd >> SSKPD_WM1_SHIFT) & SSKPD_WM_MASK;
+		wm[2] = (sskpd >> SSKPD_WM2_SHIFT) & SSKPD_WM_MASK;
+		wm[3] = (sskpd >> SSKPD_WM3_SHIFT) & SSKPD_WM_MASK;
+	} else if (INTEL_INFO(dev)->gen >= 5) {
+		uint32_t mltr = I915_READ(MLTR_ILK);
+
+		/* ILK primary LP0 latency is 700 ns */
+		wm[0] = 7;
+		wm[1] = (mltr >> MLTR_WM1_SHIFT) & ILK_SRLT_MASK;
+		wm[2] = (mltr >> MLTR_WM2_SHIFT) & ILK_SRLT_MASK;
+	}
+}
+
+static void intel_fixup_spr_wm_latency(struct drm_device *dev, uint16_t wm[5])
+{
+	/* ILK sprite LP0 latency is 1300 ns */
+	if (INTEL_INFO(dev)->gen == 5)
+		wm[0] = 13;
+}
+
+static void intel_fixup_cur_wm_latency(struct drm_device *dev, uint16_t wm[5])
+{
+	/* ILK cursor LP0 latency is 1300 ns */
+	if (INTEL_INFO(dev)->gen == 5)
+		wm[0] = 13;
+
+	/* WaDoubleCursorLP3Latency:ivb */
+	if (IS_IVYBRIDGE(dev))
+		wm[3] *= 2;
+}
+
+static void intel_print_wm_latency(struct drm_device *dev,
+				   const char *name,
+				   const uint16_t wm[5])
+{
+	int level, max_level;
+
+	/* how many WM levels are we expecting */
+	if (IS_HASWELL(dev))
+		max_level = 4;
+	else if (INTEL_INFO(dev)->gen >= 6)
+		max_level = 3;
+	else
+		max_level = 2;
+
+	for (level = 0; level <= max_level; level++) {
+		unsigned int latency = wm[level];
+
+		if (latency == 0) {
+			DRM_ERROR("%s WM%d latency not provided\n",
+				  name, level);
+			continue;
+		}
+
+		/* WM1+ latency values in 0.5us units */
+		if (level > 0)
+			latency *= 5;
+
+		DRM_DEBUG_KMS("%s WM%d latency %u (%u.%u usec)\n",
+			      name, level, wm[level],
+			      latency / 10, latency % 10);
+	}
+}
+
+static void intel_setup_wm_latency(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	intel_read_wm_latency(dev, dev_priv->wm.pri_latency);
+
+	memcpy(dev_priv->wm.spr_latency, dev_priv->wm.pri_latency,
+	       sizeof(dev_priv->wm.pri_latency));
+	memcpy(dev_priv->wm.cur_latency, dev_priv->wm.pri_latency,
+	       sizeof(dev_priv->wm.pri_latency));
+
+	intel_fixup_spr_wm_latency(dev, dev_priv->wm.spr_latency);
+	intel_fixup_cur_wm_latency(dev, dev_priv->wm.cur_latency);
+
+	intel_print_wm_latency(dev, "Primary", dev_priv->wm.pri_latency);
+	intel_print_wm_latency(dev, "Sprite", dev_priv->wm.spr_latency);
+	intel_print_wm_latency(dev, "Cursor", dev_priv->wm.cur_latency);
+}
+
 static void hsw_compute_wm_parameters(struct drm_device *dev,
 				      struct hsw_pipe_wm_parameters *params,
-				      uint32_t *wm,
 				      struct hsw_wm_maximums *lp_max_1_2,
 				      struct hsw_wm_maximums *lp_max_5_6)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_crtc *crtc;
 	struct drm_plane *plane;
-	uint64_t sskpd = I915_READ64(MCH_SSKPD);
 	enum pipe pipe;
-	int pipes_active = 0, sprites_enabled = 0;
-
-	if ((sskpd >> 56) & 0xFF)
-		wm[0] = (sskpd >> 56) & 0xFF;
-	else
-		wm[0] = sskpd & 0xF;
-	wm[1] = ((sskpd >> 4) & 0xFF) * 5;
-	wm[2] = ((sskpd >> 12) & 0xFF) * 5;
-	wm[3] = ((sskpd >> 20) & 0x1FF) * 5;
-	wm[4] = ((sskpd >> 32) & 0x1FF) * 5;
+	struct intel_wm_config config = {};
 
 	list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
 		struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
@@ -2371,15 +2627,18 @@ static void hsw_compute_wm_parameters(struct drm_device *dev,
 		if (!p->active)
 			continue;
 
-		pipes_active++;
+		config.num_pipes_active++;
 
 		p->pipe_htotal = intel_crtc->config.adjusted_mode.htotal;
-		p->pixel_rate = hsw_wm_get_pixel_rate(dev, crtc);
-		p->pri_bytes_per_pixel = crtc->fb->bits_per_pixel / 8;
-		p->cur_bytes_per_pixel = 4;
-		p->pri_horiz_pixels =
+		p->pixel_rate = ilk_pipe_pixel_rate(dev, crtc);
+		p->pri.bytes_per_pixel = crtc->fb->bits_per_pixel / 8;
+		p->cur.bytes_per_pixel = 4;
+		p->pri.horiz_pixels =
 			intel_crtc->config.requested_mode.hdisplay;
-		p->cur_horiz_pixels = 64;
+		p->cur.horiz_pixels = 64;
+		/* TODO: for now, assume primary and cursor planes are always enabled. */
+		p->pri.enabled = true;
+		p->cur.enabled = true;
 	}
 
 	list_for_each_entry(plane, &dev->mode_config.plane_list, head) {
@@ -2389,59 +2648,53 @@ static void hsw_compute_wm_parameters(struct drm_device *dev,
 		pipe = intel_plane->pipe;
 		p = &params[pipe];
 
-		p->sprite_enabled = intel_plane->wm.enable;
-		p->spr_bytes_per_pixel = intel_plane->wm.bytes_per_pixel;
-		p->spr_horiz_pixels = intel_plane->wm.horiz_pixels;
+		p->spr = intel_plane->wm;
 
-		if (p->sprite_enabled)
-			sprites_enabled++;
+		config.sprites_enabled |= p->spr.enabled;
+		config.sprites_scaled |= p->spr.scaled;
 	}
 
-	if (pipes_active > 1) {
-		lp_max_1_2->pri = lp_max_5_6->pri = sprites_enabled ? 128 : 256;
-		lp_max_1_2->spr = lp_max_5_6->spr = 128;
-		lp_max_1_2->cur = lp_max_5_6->cur = 64;
-	} else {
-		lp_max_1_2->pri = sprites_enabled ? 384 : 768;
-		lp_max_5_6->pri = sprites_enabled ? 128 : 768;
-		lp_max_1_2->spr = 384;
-		lp_max_5_6->spr = 640;
-		lp_max_1_2->cur = lp_max_5_6->cur = 255;
-	}
-	lp_max_1_2->fbc = lp_max_5_6->fbc = 15;
+	ilk_wm_max(dev, 1, &config, INTEL_DDB_PART_1_2, lp_max_1_2);
+
+	/* 5/6 split only in single pipe config on IVB+ */
+	if (INTEL_INFO(dev)->gen >= 7 && config.num_pipes_active <= 1)
+		ilk_wm_max(dev, 1, &config, INTEL_DDB_PART_5_6, lp_max_5_6);
+	else
+		*lp_max_5_6 = *lp_max_1_2;
 }
 
 static void hsw_compute_wm_results(struct drm_device *dev,
 				   struct hsw_pipe_wm_parameters *params,
-				   uint32_t *wm,
 				   struct hsw_wm_maximums *lp_maximums,
 				   struct hsw_wm_values *results)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_crtc *crtc;
-	struct hsw_lp_wm_result lp_results[4] = {};
+	struct intel_wm_level lp_results[4] = {};
 	enum pipe pipe;
 	int level, max_level, wm_lp;
 
 	for (level = 1; level <= 4; level++)
-		if (!hsw_compute_lp_wm(wm[level], lp_maximums, params,
+		if (!hsw_compute_lp_wm(dev_priv, level,
+				       lp_maximums, params,
 				       &lp_results[level - 1]))
 			break;
 	max_level = level - 1;
 
+	memset(results, 0, sizeof(*results));
+
 	/* The spec says it is preferred to disable FBC WMs instead of disabling
 	 * a WM level. */
 	results->enable_fbc_wm = true;
 	for (level = 1; level <= max_level; level++) {
-		if (!lp_results[level - 1].fbc_enable) {
+		if (lp_results[level - 1].fbc_val > lp_maximums->fbc) {
 			results->enable_fbc_wm = false;
-			break;
+			lp_results[level - 1].fbc_val = 0;
 		}
 	}
 
-	memset(results, 0, sizeof(*results));
 	for (wm_lp = 1; wm_lp <= 3; wm_lp++) {
-		const struct hsw_lp_wm_result *r;
+		const struct intel_wm_level *r;
 
 		level = (max_level == 4 && wm_lp > 1) ? wm_lp + 1 : wm_lp;
 		if (level > max_level)
@@ -2456,8 +2709,7 @@ static void hsw_compute_wm_results(struct drm_device *dev,
 	}
 
 	for_each_pipe(pipe)
-		results->wm_pipe[pipe] = hsw_compute_wm_pipe(dev_priv, wm[0],
-							     pipe,
+		results->wm_pipe[pipe] = hsw_compute_wm_pipe(dev_priv, pipe,
 							     &params[pipe]);
 
 	for_each_pipe(pipe) {
@@ -2468,8 +2720,8 @@ static void hsw_compute_wm_results(struct drm_device *dev,
 
 /* Find the result with the highest level enabled. Check for enable_fbc_wm in
  * case both are at the same level. Prefer r1 in case they're the same. */
-struct hsw_wm_values *hsw_find_best_result(struct hsw_wm_values *r1,
-					   struct hsw_wm_values *r2)
+static struct hsw_wm_values *hsw_find_best_result(struct hsw_wm_values *r1,
+						  struct hsw_wm_values *r2)
 {
 	int i, val_r1 = 0, val_r2 = 0;
 
@@ -2498,11 +2750,11 @@ struct hsw_wm_values *hsw_find_best_result(struct hsw_wm_values *r1,
  */
 static void hsw_write_wm_values(struct drm_i915_private *dev_priv,
 				struct hsw_wm_values *results,
-				enum hsw_data_buf_partitioning partitioning)
+				enum intel_ddb_partitioning partitioning)
 {
 	struct hsw_wm_values previous;
 	uint32_t val;
-	enum hsw_data_buf_partitioning prev_partitioning;
+	enum intel_ddb_partitioning prev_partitioning;
 	bool prev_enable_fbc_wm;
 
 	previous.wm_pipe[0] = I915_READ(WM0_PIPEA_ILK);
@@ -2519,7 +2771,7 @@ static void hsw_write_wm_values(struct drm_i915_private *dev_priv,
 	previous.wm_linetime[2] = I915_READ(PIPE_WM_LINETIME(PIPE_C));
 
 	prev_partitioning = (I915_READ(WM_MISC) & WM_MISC_DATA_PARTITION_5_6) ?
-			    HSW_DATA_BUF_PART_5_6 : HSW_DATA_BUF_PART_1_2;
+				INTEL_DDB_PART_5_6 : INTEL_DDB_PART_1_2;
 
 	prev_enable_fbc_wm = !(I915_READ(DISP_ARB_CTL) & DISP_FBC_WM_DIS);
 
@@ -2558,7 +2810,7 @@ static void hsw_write_wm_values(struct drm_i915_private *dev_priv,
 
 	if (prev_partitioning != partitioning) {
 		val = I915_READ(WM_MISC);
-		if (partitioning == HSW_DATA_BUF_PART_1_2)
+		if (partitioning == INTEL_DDB_PART_1_2)
 			val &= ~WM_MISC_DATA_PARTITION_5_6;
 		else
 			val |= WM_MISC_DATA_PARTITION_5_6;
@@ -2595,44 +2847,39 @@ static void haswell_update_wm(struct drm_device *dev)
 	struct hsw_wm_maximums lp_max_1_2, lp_max_5_6;
 	struct hsw_pipe_wm_parameters params[3];
 	struct hsw_wm_values results_1_2, results_5_6, *best_results;
-	uint32_t wm[5];
-	enum hsw_data_buf_partitioning partitioning;
+	enum intel_ddb_partitioning partitioning;
 
-	hsw_compute_wm_parameters(dev, params, wm, &lp_max_1_2, &lp_max_5_6);
+	hsw_compute_wm_parameters(dev, params, &lp_max_1_2, &lp_max_5_6);
 
-	hsw_compute_wm_results(dev, params, wm, &lp_max_1_2, &results_1_2);
+	hsw_compute_wm_results(dev, params,
+			       &lp_max_1_2, &results_1_2);
 	if (lp_max_1_2.pri != lp_max_5_6.pri) {
-		hsw_compute_wm_results(dev, params, wm, &lp_max_5_6,
-				       &results_5_6);
+		hsw_compute_wm_results(dev, params,
+				       &lp_max_5_6, &results_5_6);
 		best_results = hsw_find_best_result(&results_1_2, &results_5_6);
 	} else {
 		best_results = &results_1_2;
 	}
 
 	partitioning = (best_results == &results_1_2) ?
-		       HSW_DATA_BUF_PART_1_2 : HSW_DATA_BUF_PART_5_6;
+		       INTEL_DDB_PART_1_2 : INTEL_DDB_PART_5_6;
 
 	hsw_write_wm_values(dev_priv, best_results, partitioning);
 }
 
-static void haswell_update_sprite_wm(struct drm_device *dev, int pipe,
+static void haswell_update_sprite_wm(struct drm_plane *plane,
+				     struct drm_crtc *crtc,
 				     uint32_t sprite_width, int pixel_size,
-				     bool enable)
+				     bool enabled, bool scaled)
 {
-	struct drm_plane *plane;
+	struct intel_plane *intel_plane = to_intel_plane(plane);
 
-	list_for_each_entry(plane, &dev->mode_config.plane_list, head) {
-		struct intel_plane *intel_plane = to_intel_plane(plane);
-
-		if (intel_plane->pipe == pipe) {
-			intel_plane->wm.enable = enable;
-			intel_plane->wm.horiz_pixels = sprite_width + 1;
-			intel_plane->wm.bytes_per_pixel = pixel_size;
-			break;
-		}
-	}
+	intel_plane->wm.enabled = enabled;
+	intel_plane->wm.scaled = scaled;
+	intel_plane->wm.horiz_pixels = sprite_width;
+	intel_plane->wm.bytes_per_pixel = pixel_size;
 
-	haswell_update_wm(dev);
+	haswell_update_wm(plane->dev);
 }
 
 static bool
@@ -2711,17 +2958,20 @@ sandybridge_compute_sprite_srwm(struct drm_device *dev, int plane,
 	return *sprite_wm > 0x3ff ? false : true;
 }
 
-static void sandybridge_update_sprite_wm(struct drm_device *dev, int pipe,
+static void sandybridge_update_sprite_wm(struct drm_plane *plane,
+					 struct drm_crtc *crtc,
 					 uint32_t sprite_width, int pixel_size,
-					 bool enable)
+					 bool enabled, bool scaled)
 {
+	struct drm_device *dev = plane->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	int latency = SNB_READ_WM0_LATENCY() * 100;	/* In unit 0.1us */
+	int pipe = to_intel_plane(plane)->pipe;
+	int latency = dev_priv->wm.spr_latency[0] * 100;	/* In unit 0.1us */
 	u32 val;
 	int sprite_wm, reg;
 	int ret;
 
-	if (!enable)
+	if (!enabled)
 		return;
 
 	switch (pipe) {
@@ -2756,7 +3006,7 @@ static void sandybridge_update_sprite_wm(struct drm_device *dev, int pipe,
 	ret = sandybridge_compute_sprite_srwm(dev, pipe, sprite_width,
 					      pixel_size,
 					      &sandybridge_display_srwm_info,
-					      SNB_READ_WM1_LATENCY() * 500,
+					      dev_priv->wm.spr_latency[1] * 500,
 					      &sprite_wm);
 	if (!ret) {
 		DRM_DEBUG_KMS("failed to compute sprite lp1 wm on pipe %c\n",
@@ -2772,7 +3022,7 @@ static void sandybridge_update_sprite_wm(struct drm_device *dev, int pipe,
 	ret = sandybridge_compute_sprite_srwm(dev, pipe, sprite_width,
 					      pixel_size,
 					      &sandybridge_display_srwm_info,
-					      SNB_READ_WM2_LATENCY() * 500,
+					      dev_priv->wm.spr_latency[2] * 500,
 					      &sprite_wm);
 	if (!ret) {
 		DRM_DEBUG_KMS("failed to compute sprite lp2 wm on pipe %c\n",
@@ -2784,7 +3034,7 @@ static void sandybridge_update_sprite_wm(struct drm_device *dev, int pipe,
 	ret = sandybridge_compute_sprite_srwm(dev, pipe, sprite_width,
 					      pixel_size,
 					      &sandybridge_display_srwm_info,
-					      SNB_READ_WM3_LATENCY() * 500,
+					      dev_priv->wm.spr_latency[3] * 500,
 					      &sprite_wm);
 	if (!ret) {
 		DRM_DEBUG_KMS("failed to compute sprite lp3 wm on pipe %c\n",
@@ -2834,15 +3084,16 @@ void intel_update_watermarks(struct drm_device *dev)
 		dev_priv->display.update_wm(dev);
 }
 
-void intel_update_sprite_watermarks(struct drm_device *dev, int pipe,
+void intel_update_sprite_watermarks(struct drm_plane *plane,
+				    struct drm_crtc *crtc,
 				    uint32_t sprite_width, int pixel_size,
-				    bool enable)
+				    bool enabled, bool scaled)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = plane->dev->dev_private;
 
 	if (dev_priv->display.update_sprite_wm)
-		dev_priv->display.update_sprite_wm(dev, pipe, sprite_width,
-						   pixel_size, enable);
+		dev_priv->display.update_sprite_wm(plane, crtc, sprite_width,
+						   pixel_size, enabled, scaled);
 }
 
 static struct drm_i915_gem_object *
@@ -2859,7 +3110,7 @@ intel_alloc_context_page(struct drm_device *dev)
 		return NULL;
 	}
 
-	ret = i915_gem_object_pin(ctx, 4096, true, false);
+	ret = i915_gem_obj_ggtt_pin(ctx, 4096, true, false);
 	if (ret) {
 		DRM_ERROR("failed to pin power context: %d\n", ret);
 		goto err_unref;
@@ -3076,19 +3327,12 @@ void gen6_set_rps(struct drm_device *dev, u8 val)
  */
 static void vlv_update_rps_cur_delay(struct drm_i915_private *dev_priv)
 {
-	unsigned long timeout = jiffies + msecs_to_jiffies(10);
 	u32 pval;
 
 	WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock));
 
-	do {
-		pval = vlv_punit_read(dev_priv, PUNIT_REG_GPU_FREQ_STS);
-		if (time_after(jiffies, timeout)) {
-			DRM_DEBUG_DRIVER("timed out waiting for Punit\n");
-			break;
-		}
-		udelay(10);
-	} while (pval & 1);
+	if (wait_for(((pval = vlv_punit_read(dev_priv, PUNIT_REG_GPU_FREQ_STS)) & GENFREQSTATUS) == 0, 10))
+		DRM_DEBUG_DRIVER("timed out waiting for Punit\n");
 
 	pval >>= 8;
 
@@ -3129,13 +3373,10 @@ void valleyview_set_rps(struct drm_device *dev, u8 val)
 	trace_intel_gpu_freq_change(vlv_gpu_freq(dev_priv->mem_freq, val));
 }
 
-
-static void gen6_disable_rps(struct drm_device *dev)
+static void gen6_disable_rps_interrupts(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
-	I915_WRITE(GEN6_RC_CONTROL, 0);
-	I915_WRITE(GEN6_RPNSWREQ, 1 << 31);
 	I915_WRITE(GEN6_PMINTRMSK, 0xffffffff);
 	I915_WRITE(GEN6_PMIER, I915_READ(GEN6_PMIER) & ~GEN6_PM_RPS_EVENTS);
 	/* Complete PM interrupt masking here doesn't race with the rps work
@@ -3143,30 +3384,30 @@ static void gen6_disable_rps(struct drm_device *dev)
 	 * register (PMIMR) to mask PM interrupts. The only risk is in leaving
 	 * stale bits in PMIIR and PMIMR which gen6_enable_rps will clean up. */
 
-	spin_lock_irq(&dev_priv->rps.lock);
+	spin_lock_irq(&dev_priv->irq_lock);
 	dev_priv->rps.pm_iir = 0;
-	spin_unlock_irq(&dev_priv->rps.lock);
+	spin_unlock_irq(&dev_priv->irq_lock);
 
 	I915_WRITE(GEN6_PMIIR, GEN6_PM_RPS_EVENTS);
 }
 
-static void valleyview_disable_rps(struct drm_device *dev)
+static void gen6_disable_rps(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
 	I915_WRITE(GEN6_RC_CONTROL, 0);
-	I915_WRITE(GEN6_PMINTRMSK, 0xffffffff);
-	I915_WRITE(GEN6_PMIER, 0);
-	/* Complete PM interrupt masking here doesn't race with the rps work
-	 * item again unmasking PM interrupts because that is using a different
-	 * register (PMIMR) to mask PM interrupts. The only risk is in leaving
-	 * stale bits in PMIIR and PMIMR which gen6_enable_rps will clean up. */
+	I915_WRITE(GEN6_RPNSWREQ, 1 << 31);
 
-	spin_lock_irq(&dev_priv->rps.lock);
-	dev_priv->rps.pm_iir = 0;
-	spin_unlock_irq(&dev_priv->rps.lock);
+	gen6_disable_rps_interrupts(dev);
+}
+
+static void valleyview_disable_rps(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	I915_WRITE(GEN6_RC_CONTROL, 0);
 
-	I915_WRITE(GEN6_PMIIR, I915_READ(GEN6_PMIIR));
+	gen6_disable_rps_interrupts(dev);
 
 	if (dev_priv->vlv_pctx) {
 		drm_gem_object_unreference(&dev_priv->vlv_pctx->base);
@@ -3176,6 +3417,10 @@ static void valleyview_disable_rps(struct drm_device *dev)
 
 int intel_enable_rc6(const struct drm_device *dev)
 {
+	/* No RC6 before Ironlake */
+	if (INTEL_INFO(dev)->gen < 5)
+		return 0;
+
 	/* Respect the kernel parameter if it is set */
 	if (i915_enable_rc6 >= 0)
 		return i915_enable_rc6;
@@ -3199,6 +3444,29 @@ int intel_enable_rc6(const struct drm_device *dev)
 	return (INTEL_RC6_ENABLE | INTEL_RC6p_ENABLE);
 }
 
+static void gen6_enable_rps_interrupts(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	u32 enabled_intrs;
+
+	spin_lock_irq(&dev_priv->irq_lock);
+	WARN_ON(dev_priv->rps.pm_iir);
+	snb_enable_pm_irq(dev_priv, GEN6_PM_RPS_EVENTS);
+	I915_WRITE(GEN6_PMIIR, GEN6_PM_RPS_EVENTS);
+	spin_unlock_irq(&dev_priv->irq_lock);
+
+	/* only unmask PM interrupts we need. Mask all others. */
+	enabled_intrs = GEN6_PM_RPS_EVENTS;
+
+	/* IVB and SNB hard hangs on looping batchbuffer
+	 * if GEN6_PM_UP_EI_EXPIRED is masked.
+	 */
+	if (INTEL_INFO(dev)->gen <= 7 && !IS_HASWELL(dev))
+		enabled_intrs |= GEN6_PM_RP_UP_EI_EXPIRED;
+
+	I915_WRITE(GEN6_PMINTRMSK, ~enabled_intrs);
+}
+
 static void gen6_enable_rps(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -3250,7 +3518,10 @@ static void gen6_enable_rps(struct drm_device *dev)
 
 	I915_WRITE(GEN6_RC_SLEEP, 0);
 	I915_WRITE(GEN6_RC1e_THRESHOLD, 1000);
-	I915_WRITE(GEN6_RC6_THRESHOLD, 50000);
+	if (INTEL_INFO(dev)->gen <= 6 || IS_IVYBRIDGE(dev))
+		I915_WRITE(GEN6_RC6_THRESHOLD, 125000);
+	else
+		I915_WRITE(GEN6_RC6_THRESHOLD, 50000);
 	I915_WRITE(GEN6_RC6p_THRESHOLD, 150000);
 	I915_WRITE(GEN6_RC6pp_THRESHOLD, 64000); /* unused */
 
@@ -3327,17 +3598,7 @@ static void gen6_enable_rps(struct drm_device *dev)
 
 	gen6_set_rps(dev_priv->dev, (gt_perf_status & 0xff00) >> 8);
 
-	/* requires MSI enabled */
-	I915_WRITE(GEN6_PMIER, I915_READ(GEN6_PMIER) | GEN6_PM_RPS_EVENTS);
-	spin_lock_irq(&dev_priv->rps.lock);
-	/* FIXME: Our interrupt enabling sequence is bonghits.
-	 * dev_priv->rps.pm_iir really should be 0 here. */
-	dev_priv->rps.pm_iir = 0;
-	I915_WRITE(GEN6_PMIMR, I915_READ(GEN6_PMIMR) & ~GEN6_PM_RPS_EVENTS);
-	I915_WRITE(GEN6_PMIIR, GEN6_PM_RPS_EVENTS);
-	spin_unlock_irq(&dev_priv->rps.lock);
-	/* unmask all PM interrupts */
-	I915_WRITE(GEN6_PMINTRMSK, 0);
+	gen6_enable_rps_interrupts(dev);
 
 	rc6vids = 0;
 	ret = sandybridge_pcode_read(dev_priv, GEN6_PCODE_READ_RC6VIDS, &rc6vids);
@@ -3356,7 +3617,7 @@ static void gen6_enable_rps(struct drm_device *dev)
 	gen6_gt_force_wake_put(dev_priv);
 }
 
-static void gen6_update_ring_freq(struct drm_device *dev)
+void gen6_update_ring_freq(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	int min_freq = 15;
@@ -3482,7 +3743,7 @@ static void valleyview_setup_pctx(struct drm_device *dev)
 		pcbr_offset = (pcbr & (~4095)) - dev_priv->mm.stolen_base;
 		pctx = i915_gem_object_create_stolen_for_preallocated(dev_priv->dev,
 								      pcbr_offset,
-								      -1,
+								      I915_GTT_OFFSET_NONE,
 								      pctx_size);
 		goto out;
 	}
@@ -3603,18 +3864,9 @@ static void valleyview_enable_rps(struct drm_device *dev)
 				      dev_priv->rps.rpe_delay),
 			 dev_priv->rps.rpe_delay);
 
-	INIT_DELAYED_WORK(&dev_priv->rps.vlv_work, vlv_rps_timer_work);
-
 	valleyview_set_rps(dev_priv->dev, dev_priv->rps.rpe_delay);
 
-	/* requires MSI enabled */
-	I915_WRITE(GEN6_PMIER, GEN6_PM_RPS_EVENTS);
-	spin_lock_irq(&dev_priv->rps.lock);
-	WARN_ON(dev_priv->rps.pm_iir != 0);
-	I915_WRITE(GEN6_PMIMR, 0);
-	spin_unlock_irq(&dev_priv->rps.lock);
-	/* enable all PM interrupts */
-	I915_WRITE(GEN6_PMINTRMSK, 0);
+	gen6_enable_rps_interrupts(dev);
 
 	gen6_gt_force_wake_put(dev_priv);
 }
@@ -3708,7 +3960,7 @@ static void ironlake_enable_rc6(struct drm_device *dev)
 
 	intel_ring_emit(ring, MI_SUSPEND_FLUSH | MI_SUSPEND_FLUSH_EN);
 	intel_ring_emit(ring, MI_SET_CONTEXT);
-	intel_ring_emit(ring, dev_priv->ips.renderctx->gtt_offset |
+	intel_ring_emit(ring, i915_gem_obj_ggtt_offset(dev_priv->ips.renderctx) |
 			MI_MM_SPACE_GTT |
 			MI_SAVE_EXT_STATE_EN |
 			MI_RESTORE_EXT_STATE_EN |
@@ -3731,7 +3983,7 @@ static void ironlake_enable_rc6(struct drm_device *dev)
 		return;
 	}
 
-	I915_WRITE(PWRCTXA, dev_priv->ips.pwrctx->gtt_offset | PWRCTX_EN);
+	I915_WRITE(PWRCTXA, i915_gem_obj_ggtt_offset(dev_priv->ips.pwrctx) | PWRCTX_EN);
 	I915_WRITE(RSTDBYCTL, I915_READ(RSTDBYCTL) & ~RCX_SW_EXIT);
 }
 
@@ -4429,7 +4681,10 @@ static void ironlake_init_clock_gating(struct drm_device *dev)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	uint32_t dspclk_gate = ILK_VRHUNIT_CLOCK_GATE_DISABLE;
 
-	/* Required for FBC */
+	/*
+	 * Required for FBC
+	 * WaFbcDisableDpfcClockGating:ilk
+	 */
 	dspclk_gate |= ILK_DPFCRUNIT_CLOCK_GATE_DISABLE |
 		   ILK_DPFCUNIT_CLOCK_GATE_DISABLE |
 		   ILK_DPFDUNIT_CLOCK_GATE_ENABLE;
@@ -4466,6 +4721,7 @@ static void ironlake_init_clock_gating(struct drm_device *dev)
 	 * The bit 7,8,9 of 0x42020.
 	 */
 	if (IS_IRONLAKE_M(dev)) {
+		/* WaFbcAsynchFlipDisableFbcQueue:ilk */
 		I915_WRITE(ILK_DISPLAY_CHICKEN1,
 			   I915_READ(ILK_DISPLAY_CHICKEN1) |
 			   ILK_FBCQ_DIS);
@@ -4602,6 +4858,8 @@ static void gen6_init_clock_gating(struct drm_device *dev)
 	 * The bit5 and bit7 of 0x42020
 	 * The bit14 of 0x70180
 	 * The bit14 of 0x71180
+	 *
+	 * WaFbcAsynchFlipDisableFbcQueue:snb
 	 */
 	I915_WRITE(ILK_DISPLAY_CHICKEN1,
 		   I915_READ(ILK_DISPLAY_CHICKEN1) |
@@ -4614,10 +4872,6 @@ static void gen6_init_clock_gating(struct drm_device *dev)
 		   ILK_DPARBUNIT_CLOCK_GATE_ENABLE  |
 		   ILK_DPFDUNIT_CLOCK_GATE_ENABLE);
 
-	/* WaMbcDriverBootEnable:snb */
-	I915_WRITE(GEN6_MBCTL, I915_READ(GEN6_MBCTL) |
-		   GEN6_MBCTL_ENABLE_BOOT_FETCH);
-
 	g4x_disable_trickle_feed(dev);
 
 	/* The default value should be 0x200 according to docs, but the two
@@ -4699,13 +4953,16 @@ static void haswell_init_clock_gating(struct drm_device *dev)
 	I915_WRITE(GEN7_L3_CHICKEN_MODE_REGISTER,
 			GEN7_WA_L3_CHICKEN_MODE);
 
+	/* L3 caching of data atomics doesn't work -- disable it. */
+	I915_WRITE(HSW_SCRATCH1, HSW_SCRATCH1_L3_DATA_ATOMICS_DISABLE);
+	I915_WRITE(HSW_ROW_CHICKEN3,
+		   _MASKED_BIT_ENABLE(HSW_ROW_CHICKEN3_L3_GLOBAL_ATOMICS_DISABLE));
+
 	/* This is required by WaCatErrorRejectionIssue:hsw */
 	I915_WRITE(GEN7_SQ_CHICKEN_MBCUNIT_CONFIG,
 			I915_READ(GEN7_SQ_CHICKEN_MBCUNIT_CONFIG) |
 			GEN7_SQ_CHICKEN_MBCUNIT_SQINTMOB);
 
-	g4x_disable_trickle_feed(dev);
-
 	/* WaVSRefCountFullforceMissDisable:hsw */
 	gen7_setup_fixed_func_scheduler(dev_priv);
 
@@ -4713,10 +4970,6 @@ static void haswell_init_clock_gating(struct drm_device *dev)
 	I915_WRITE(CACHE_MODE_1,
 		   _MASKED_BIT_ENABLE(PIXEL_SUBSPAN_COLLECT_OPT_DISABLE));
 
-	/* WaMbcDriverBootEnable:hsw */
-	I915_WRITE(GEN6_MBCTL, I915_READ(GEN6_MBCTL) |
-		   GEN6_MBCTL_ENABLE_BOOT_FETCH);
-
 	/* WaSwitchSolVfFArbitrationPriority:hsw */
 	I915_WRITE(GAM_ECOCHK, I915_READ(GAM_ECOCHK) | HSW_ECOCHK_ARB_PRIO_SOL);
 
@@ -4800,10 +5053,6 @@ static void ivybridge_init_clock_gating(struct drm_device *dev)
 
 	g4x_disable_trickle_feed(dev);
 
-	/* WaMbcDriverBootEnable:ivb */
-	I915_WRITE(GEN6_MBCTL, I915_READ(GEN6_MBCTL) |
-		   GEN6_MBCTL_ENABLE_BOOT_FETCH);
-
 	/* WaVSRefCountFullforceMissDisable:ivb */
 	gen7_setup_fixed_func_scheduler(dev_priv);
 
@@ -4863,11 +5112,6 @@ static void valleyview_init_clock_gating(struct drm_device *dev)
 		   I915_READ(GEN7_SQ_CHICKEN_MBCUNIT_CONFIG) |
 		   GEN7_SQ_CHICKEN_MBCUNIT_SQINTMOB);
 
-	/* WaMbcDriverBootEnable:vlv */
-	I915_WRITE(GEN6_MBCTL, I915_READ(GEN6_MBCTL) |
-		   GEN6_MBCTL_ENABLE_BOOT_FETCH);
-
-
 	/* According to the BSpec vol1g, bit 12 (RCPBUNIT) clock
 	 * gating disable must be set.  Failure to set it results in
 	 * flickering pixels due to Z write ordering failures after
@@ -5035,7 +5279,7 @@ bool intel_display_power_enabled(struct drm_device *dev,
 	case POWER_DOMAIN_TRANSCODER_B:
 	case POWER_DOMAIN_TRANSCODER_C:
 		return I915_READ(HSW_PWR_WELL_DRIVER) ==
-		       (HSW_PWR_WELL_ENABLE | HSW_PWR_WELL_STATE);
+		     (HSW_PWR_WELL_ENABLE_REQUEST | HSW_PWR_WELL_STATE_ENABLED);
 	default:
 		BUG();
 	}
@@ -5048,17 +5292,18 @@ static void __intel_set_power_well(struct drm_device *dev, bool enable)
 	uint32_t tmp;
 
 	tmp = I915_READ(HSW_PWR_WELL_DRIVER);
-	is_enabled = tmp & HSW_PWR_WELL_STATE;
-	enable_requested = tmp & HSW_PWR_WELL_ENABLE;
+	is_enabled = tmp & HSW_PWR_WELL_STATE_ENABLED;
+	enable_requested = tmp & HSW_PWR_WELL_ENABLE_REQUEST;
 
 	if (enable) {
 		if (!enable_requested)
-			I915_WRITE(HSW_PWR_WELL_DRIVER, HSW_PWR_WELL_ENABLE);
+			I915_WRITE(HSW_PWR_WELL_DRIVER,
+				   HSW_PWR_WELL_ENABLE_REQUEST);
 
 		if (!is_enabled) {
 			DRM_DEBUG_KMS("Enabling power well\n");
 			if (wait_for((I915_READ(HSW_PWR_WELL_DRIVER) &
-				      HSW_PWR_WELL_STATE), 20))
+				      HSW_PWR_WELL_STATE_ENABLED), 20))
 				DRM_ERROR("Timeout enabling power well\n");
 		}
 	} else {
@@ -5178,10 +5423,21 @@ void intel_init_power_well(struct drm_device *dev)
 
 	/* We're taking over the BIOS, so clear any requests made by it since
 	 * the driver is in charge now. */
-	if (I915_READ(HSW_PWR_WELL_BIOS) & HSW_PWR_WELL_ENABLE)
+	if (I915_READ(HSW_PWR_WELL_BIOS) & HSW_PWR_WELL_ENABLE_REQUEST)
 		I915_WRITE(HSW_PWR_WELL_BIOS, 0);
 }
 
+/* Disables PC8 so we can use the GMBUS and DP AUX interrupts. */
+void intel_aux_display_runtime_get(struct drm_i915_private *dev_priv)
+{
+	hsw_disable_package_c8(dev_priv);
+}
+
+void intel_aux_display_runtime_put(struct drm_i915_private *dev_priv)
+{
+	hsw_enable_package_c8(dev_priv);
+}
+
 /* Set up chip specific power management-related functions */
 void intel_init_pm(struct drm_device *dev)
 {
@@ -5217,8 +5473,12 @@ void intel_init_pm(struct drm_device *dev)
 
 	/* For FIFO watermark updates */
 	if (HAS_PCH_SPLIT(dev)) {
+		intel_setup_wm_latency(dev);
+
 		if (IS_GEN5(dev)) {
-			if (I915_READ(MLTR_ILK) & ILK_SRLT_MASK)
+			if (dev_priv->wm.pri_latency[1] &&
+			    dev_priv->wm.spr_latency[1] &&
+			    dev_priv->wm.cur_latency[1])
 				dev_priv->display.update_wm = ironlake_update_wm;
 			else {
 				DRM_DEBUG_KMS("Failed to get proper latency. "
@@ -5227,7 +5487,9 @@ void intel_init_pm(struct drm_device *dev)
 			}
 			dev_priv->display.init_clock_gating = ironlake_init_clock_gating;
 		} else if (IS_GEN6(dev)) {
-			if (SNB_READ_WM0_LATENCY()) {
+			if (dev_priv->wm.pri_latency[0] &&
+			    dev_priv->wm.spr_latency[0] &&
+			    dev_priv->wm.cur_latency[0]) {
 				dev_priv->display.update_wm = sandybridge_update_wm;
 				dev_priv->display.update_sprite_wm = sandybridge_update_sprite_wm;
 			} else {
@@ -5237,7 +5499,9 @@ void intel_init_pm(struct drm_device *dev)
 			}
 			dev_priv->display.init_clock_gating = gen6_init_clock_gating;
 		} else if (IS_IVYBRIDGE(dev)) {
-			if (SNB_READ_WM0_LATENCY()) {
+			if (dev_priv->wm.pri_latency[0] &&
+			    dev_priv->wm.spr_latency[0] &&
+			    dev_priv->wm.cur_latency[0]) {
 				dev_priv->display.update_wm = ivybridge_update_wm;
 				dev_priv->display.update_sprite_wm = sandybridge_update_sprite_wm;
 			} else {
@@ -5247,7 +5511,9 @@ void intel_init_pm(struct drm_device *dev)
 			}
 			dev_priv->display.init_clock_gating = ivybridge_init_clock_gating;
 		} else if (IS_HASWELL(dev)) {
-			if (I915_READ64(MCH_SSKPD)) {
+			if (dev_priv->wm.pri_latency[0] &&
+			    dev_priv->wm.spr_latency[0] &&
+			    dev_priv->wm.cur_latency[0]) {
 				dev_priv->display.update_wm = haswell_update_wm;
 				dev_priv->display.update_sprite_wm =
 					haswell_update_sprite_wm;
@@ -5310,260 +5576,6 @@ void intel_init_pm(struct drm_device *dev)
 	}
 }
 
-static void __gen6_gt_wait_for_thread_c0(struct drm_i915_private *dev_priv)
-{
-	u32 gt_thread_status_mask;
-
-	if (IS_HASWELL(dev_priv->dev))
-		gt_thread_status_mask = GEN6_GT_THREAD_STATUS_CORE_MASK_HSW;
-	else
-		gt_thread_status_mask = GEN6_GT_THREAD_STATUS_CORE_MASK;
-
-	/* w/a for a sporadic read returning 0 by waiting for the GT
-	 * thread to wake up.
-	 */
-	if (wait_for_atomic_us((I915_READ_NOTRACE(GEN6_GT_THREAD_STATUS_REG) & gt_thread_status_mask) == 0, 500))
-		DRM_ERROR("GT thread status wait timed out\n");
-}
-
-static void __gen6_gt_force_wake_reset(struct drm_i915_private *dev_priv)
-{
-	I915_WRITE_NOTRACE(FORCEWAKE, 0);
-	POSTING_READ(ECOBUS); /* something from same cacheline, but !FORCEWAKE */
-}
-
-static void __gen6_gt_force_wake_get(struct drm_i915_private *dev_priv)
-{
-	if (wait_for_atomic((I915_READ_NOTRACE(FORCEWAKE_ACK) & 1) == 0,
-			    FORCEWAKE_ACK_TIMEOUT_MS))
-		DRM_ERROR("Timed out waiting for forcewake old ack to clear.\n");
-
-	I915_WRITE_NOTRACE(FORCEWAKE, 1);
-	POSTING_READ(ECOBUS); /* something from same cacheline, but !FORCEWAKE */
-
-	if (wait_for_atomic((I915_READ_NOTRACE(FORCEWAKE_ACK) & 1),
-			    FORCEWAKE_ACK_TIMEOUT_MS))
-		DRM_ERROR("Timed out waiting for forcewake to ack request.\n");
-
-	/* WaRsForcewakeWaitTC0:snb */
-	__gen6_gt_wait_for_thread_c0(dev_priv);
-}
-
-static void __gen6_gt_force_wake_mt_reset(struct drm_i915_private *dev_priv)
-{
-	I915_WRITE_NOTRACE(FORCEWAKE_MT, _MASKED_BIT_DISABLE(0xffff));
-	/* something from same cacheline, but !FORCEWAKE_MT */
-	POSTING_READ(ECOBUS);
-}
-
-static void __gen6_gt_force_wake_mt_get(struct drm_i915_private *dev_priv)
-{
-	u32 forcewake_ack;
-
-	if (IS_HASWELL(dev_priv->dev))
-		forcewake_ack = FORCEWAKE_ACK_HSW;
-	else
-		forcewake_ack = FORCEWAKE_MT_ACK;
-
-	if (wait_for_atomic((I915_READ_NOTRACE(forcewake_ack) & FORCEWAKE_KERNEL) == 0,
-			    FORCEWAKE_ACK_TIMEOUT_MS))
-		DRM_ERROR("Timed out waiting for forcewake old ack to clear.\n");
-
-	I915_WRITE_NOTRACE(FORCEWAKE_MT, _MASKED_BIT_ENABLE(FORCEWAKE_KERNEL));
-	/* something from same cacheline, but !FORCEWAKE_MT */
-	POSTING_READ(ECOBUS);
-
-	if (wait_for_atomic((I915_READ_NOTRACE(forcewake_ack) & FORCEWAKE_KERNEL),
-			    FORCEWAKE_ACK_TIMEOUT_MS))
-		DRM_ERROR("Timed out waiting for forcewake to ack request.\n");
-
-	/* WaRsForcewakeWaitTC0:ivb,hsw */
-	__gen6_gt_wait_for_thread_c0(dev_priv);
-}
-
-/*
- * Generally this is called implicitly by the register read function. However,
- * if some sequence requires the GT to not power down then this function should
- * be called at the beginning of the sequence followed by a call to
- * gen6_gt_force_wake_put() at the end of the sequence.
- */
-void gen6_gt_force_wake_get(struct drm_i915_private *dev_priv)
-{
-	unsigned long irqflags;
-
-	spin_lock_irqsave(&dev_priv->gt_lock, irqflags);
-	if (dev_priv->forcewake_count++ == 0)
-		dev_priv->gt.force_wake_get(dev_priv);
-	spin_unlock_irqrestore(&dev_priv->gt_lock, irqflags);
-}
-
-void gen6_gt_check_fifodbg(struct drm_i915_private *dev_priv)
-{
-	u32 gtfifodbg;
-	gtfifodbg = I915_READ_NOTRACE(GTFIFODBG);
-	if (WARN(gtfifodbg & GT_FIFO_CPU_ERROR_MASK,
-	     "MMIO read or write has been dropped %x\n", gtfifodbg))
-		I915_WRITE_NOTRACE(GTFIFODBG, GT_FIFO_CPU_ERROR_MASK);
-}
-
-static void __gen6_gt_force_wake_put(struct drm_i915_private *dev_priv)
-{
-	I915_WRITE_NOTRACE(FORCEWAKE, 0);
-	/* something from same cacheline, but !FORCEWAKE */
-	POSTING_READ(ECOBUS);
-	gen6_gt_check_fifodbg(dev_priv);
-}
-
-static void __gen6_gt_force_wake_mt_put(struct drm_i915_private *dev_priv)
-{
-	I915_WRITE_NOTRACE(FORCEWAKE_MT, _MASKED_BIT_DISABLE(FORCEWAKE_KERNEL));
-	/* something from same cacheline, but !FORCEWAKE_MT */
-	POSTING_READ(ECOBUS);
-	gen6_gt_check_fifodbg(dev_priv);
-}
-
-/*
- * see gen6_gt_force_wake_get()
- */
-void gen6_gt_force_wake_put(struct drm_i915_private *dev_priv)
-{
-	unsigned long irqflags;
-
-	spin_lock_irqsave(&dev_priv->gt_lock, irqflags);
-	if (--dev_priv->forcewake_count == 0)
-		dev_priv->gt.force_wake_put(dev_priv);
-	spin_unlock_irqrestore(&dev_priv->gt_lock, irqflags);
-}
-
-int __gen6_gt_wait_for_fifo(struct drm_i915_private *dev_priv)
-{
-	int ret = 0;
-
-	if (dev_priv->gt_fifo_count < GT_FIFO_NUM_RESERVED_ENTRIES) {
-		int loop = 500;
-		u32 fifo = I915_READ_NOTRACE(GT_FIFO_FREE_ENTRIES);
-		while (fifo <= GT_FIFO_NUM_RESERVED_ENTRIES && loop--) {
-			udelay(10);
-			fifo = I915_READ_NOTRACE(GT_FIFO_FREE_ENTRIES);
-		}
-		if (WARN_ON(loop < 0 && fifo <= GT_FIFO_NUM_RESERVED_ENTRIES))
-			++ret;
-		dev_priv->gt_fifo_count = fifo;
-	}
-	dev_priv->gt_fifo_count--;
-
-	return ret;
-}
-
-static void vlv_force_wake_reset(struct drm_i915_private *dev_priv)
-{
-	I915_WRITE_NOTRACE(FORCEWAKE_VLV, _MASKED_BIT_DISABLE(0xffff));
-	/* something from same cacheline, but !FORCEWAKE_VLV */
-	POSTING_READ(FORCEWAKE_ACK_VLV);
-}
-
-static void vlv_force_wake_get(struct drm_i915_private *dev_priv)
-{
-	if (wait_for_atomic((I915_READ_NOTRACE(FORCEWAKE_ACK_VLV) & FORCEWAKE_KERNEL) == 0,
-			    FORCEWAKE_ACK_TIMEOUT_MS))
-		DRM_ERROR("Timed out waiting for forcewake old ack to clear.\n");
-
-	I915_WRITE_NOTRACE(FORCEWAKE_VLV, _MASKED_BIT_ENABLE(FORCEWAKE_KERNEL));
-	I915_WRITE_NOTRACE(FORCEWAKE_MEDIA_VLV,
-			   _MASKED_BIT_ENABLE(FORCEWAKE_KERNEL));
-
-	if (wait_for_atomic((I915_READ_NOTRACE(FORCEWAKE_ACK_VLV) & FORCEWAKE_KERNEL),
-			    FORCEWAKE_ACK_TIMEOUT_MS))
-		DRM_ERROR("Timed out waiting for GT to ack forcewake request.\n");
-
-	if (wait_for_atomic((I915_READ_NOTRACE(FORCEWAKE_ACK_MEDIA_VLV) &
-			     FORCEWAKE_KERNEL),
-			    FORCEWAKE_ACK_TIMEOUT_MS))
-		DRM_ERROR("Timed out waiting for media to ack forcewake request.\n");
-
-	/* WaRsForcewakeWaitTC0:vlv */
-	__gen6_gt_wait_for_thread_c0(dev_priv);
-}
-
-static void vlv_force_wake_put(struct drm_i915_private *dev_priv)
-{
-	I915_WRITE_NOTRACE(FORCEWAKE_VLV, _MASKED_BIT_DISABLE(FORCEWAKE_KERNEL));
-	I915_WRITE_NOTRACE(FORCEWAKE_MEDIA_VLV,
-			   _MASKED_BIT_DISABLE(FORCEWAKE_KERNEL));
-	/* The below doubles as a POSTING_READ */
-	gen6_gt_check_fifodbg(dev_priv);
-}
-
-void intel_gt_sanitize(struct drm_device *dev)
-{
-	struct drm_i915_private *dev_priv = dev->dev_private;
-
-	if (IS_VALLEYVIEW(dev)) {
-		vlv_force_wake_reset(dev_priv);
-	} else if (INTEL_INFO(dev)->gen >= 6) {
-		__gen6_gt_force_wake_reset(dev_priv);
-		if (IS_IVYBRIDGE(dev) || IS_HASWELL(dev))
-			__gen6_gt_force_wake_mt_reset(dev_priv);
-	}
-
-	/* BIOS often leaves RC6 enabled, but disable it for hw init */
-	if (INTEL_INFO(dev)->gen >= 6)
-		intel_disable_gt_powersave(dev);
-}
-
-void intel_gt_init(struct drm_device *dev)
-{
-	struct drm_i915_private *dev_priv = dev->dev_private;
-
-	if (IS_VALLEYVIEW(dev)) {
-		dev_priv->gt.force_wake_get = vlv_force_wake_get;
-		dev_priv->gt.force_wake_put = vlv_force_wake_put;
-	} else if (IS_HASWELL(dev)) {
-		dev_priv->gt.force_wake_get = __gen6_gt_force_wake_mt_get;
-		dev_priv->gt.force_wake_put = __gen6_gt_force_wake_mt_put;
-	} else if (IS_IVYBRIDGE(dev)) {
-		u32 ecobus;
-
-		/* IVB configs may use multi-threaded forcewake */
-
-		/* A small trick here - if the bios hasn't configured
-		 * MT forcewake, and if the device is in RC6, then
-		 * force_wake_mt_get will not wake the device and the
-		 * ECOBUS read will return zero. Which will be
-		 * (correctly) interpreted by the test below as MT
-		 * forcewake being disabled.
-		 */
-		mutex_lock(&dev->struct_mutex);
-		__gen6_gt_force_wake_mt_get(dev_priv);
-		ecobus = I915_READ_NOTRACE(ECOBUS);
-		__gen6_gt_force_wake_mt_put(dev_priv);
-		mutex_unlock(&dev->struct_mutex);
-
-		if (ecobus & FORCEWAKE_MT_ENABLE) {
-			dev_priv->gt.force_wake_get =
-						__gen6_gt_force_wake_mt_get;
-			dev_priv->gt.force_wake_put =
-						__gen6_gt_force_wake_mt_put;
-		} else {
-			DRM_INFO("No MT forcewake available on Ivybridge, this can result in issues\n");
-			DRM_INFO("when using vblank-synced partial screen updates.\n");
-			dev_priv->gt.force_wake_get = __gen6_gt_force_wake_get;
-			dev_priv->gt.force_wake_put = __gen6_gt_force_wake_put;
-		}
-	} else if (IS_GEN6(dev)) {
-		dev_priv->gt.force_wake_get = __gen6_gt_force_wake_get;
-		dev_priv->gt.force_wake_put = __gen6_gt_force_wake_put;
-	}
-}
-
-void intel_pm_init(struct drm_device *dev)
-{
-	struct drm_i915_private *dev_priv = dev->dev_private;
-
-	INIT_DELAYED_WORK(&dev_priv->rps.delayed_resume_work,
-			  intel_gen6_powersave_work);
-}
-
 int sandybridge_pcode_read(struct drm_i915_private *dev_priv, u8 mbox, u32 *val)
 {
 	WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock));
@@ -5666,3 +5678,13 @@ int vlv_freq_opcode(int ddr_freq, int val)
 	return val;
 }
 
+void intel_pm_init(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	INIT_DELAYED_WORK(&dev_priv->rps.delayed_resume_work,
+			  intel_gen6_powersave_work);
+
+	INIT_DELAYED_WORK(&dev_priv->rps.vlv_work, vlv_rps_timer_work);
+}
+
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 079ef0129e74..460ee1026fca 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -33,16 +33,6 @@
 #include "i915_trace.h"
 #include "intel_drv.h"
 
-/*
- * 965+ support PIPE_CONTROL commands, which provide finer grained control
- * over cache flushing.
- */
-struct pipe_control {
-	struct drm_i915_gem_object *obj;
-	volatile u32 *cpu_page;
-	u32 gtt_offset;
-};
-
 static inline int ring_space(struct intel_ring_buffer *ring)
 {
 	int space = (ring->head & HEAD_ADDR) - (ring->tail + I915_RING_FREE_SPACE);
@@ -175,8 +165,7 @@ gen4_render_ring_flush(struct intel_ring_buffer *ring,
 static int
 intel_emit_post_sync_nonzero_flush(struct intel_ring_buffer *ring)
 {
-	struct pipe_control *pc = ring->private;
-	u32 scratch_addr = pc->gtt_offset + 128;
+	u32 scratch_addr = ring->scratch.gtt_offset + 128;
 	int ret;
 
 
@@ -213,8 +202,7 @@ gen6_render_ring_flush(struct intel_ring_buffer *ring,
                          u32 invalidate_domains, u32 flush_domains)
 {
 	u32 flags = 0;
-	struct pipe_control *pc = ring->private;
-	u32 scratch_addr = pc->gtt_offset + 128;
+	u32 scratch_addr = ring->scratch.gtt_offset + 128;
 	int ret;
 
 	/* Force SNB workarounds for PIPE_CONTROL flushes */
@@ -306,8 +294,7 @@ gen7_render_ring_flush(struct intel_ring_buffer *ring,
 		       u32 invalidate_domains, u32 flush_domains)
 {
 	u32 flags = 0;
-	struct pipe_control *pc = ring->private;
-	u32 scratch_addr = pc->gtt_offset + 128;
+	u32 scratch_addr = ring->scratch.gtt_offset + 128;
 	int ret;
 
 	/*
@@ -440,14 +427,14 @@ static int init_ring_common(struct intel_ring_buffer *ring)
 	 * registers with the above sequence (the readback of the HEAD registers
 	 * also enforces ordering), otherwise the hw might lose the new ring
 	 * register values. */
-	I915_WRITE_START(ring, obj->gtt_offset);
+	I915_WRITE_START(ring, i915_gem_obj_ggtt_offset(obj));
 	I915_WRITE_CTL(ring,
 			((ring->size - PAGE_SIZE) & RING_NR_PAGES)
 			| RING_VALID);
 
 	/* If the head is still not zero, the ring is dead */
 	if (wait_for((I915_READ_CTL(ring) & RING_VALID) != 0 &&
-		     I915_READ_START(ring) == obj->gtt_offset &&
+		     I915_READ_START(ring) == i915_gem_obj_ggtt_offset(obj) &&
 		     (I915_READ_HEAD(ring) & HEAD_ADDR) == 0, 50)) {
 		DRM_ERROR("%s initialization failed "
 				"ctl %08x head %08x tail %08x start %08x\n",
@@ -481,68 +468,43 @@ out:
 static int
 init_pipe_control(struct intel_ring_buffer *ring)
 {
-	struct pipe_control *pc;
-	struct drm_i915_gem_object *obj;
 	int ret;
 
-	if (ring->private)
+	if (ring->scratch.obj)
 		return 0;
 
-	pc = kmalloc(sizeof(*pc), GFP_KERNEL);
-	if (!pc)
-		return -ENOMEM;
-
-	obj = i915_gem_alloc_object(ring->dev, 4096);
-	if (obj == NULL) {
+	ring->scratch.obj = i915_gem_alloc_object(ring->dev, 4096);
+	if (ring->scratch.obj == NULL) {
 		DRM_ERROR("Failed to allocate seqno page\n");
 		ret = -ENOMEM;
 		goto err;
 	}
 
-	i915_gem_object_set_cache_level(obj, I915_CACHE_LLC);
+	i915_gem_object_set_cache_level(ring->scratch.obj, I915_CACHE_LLC);
 
-	ret = i915_gem_object_pin(obj, 4096, true, false);
+	ret = i915_gem_obj_ggtt_pin(ring->scratch.obj, 4096, true, false);
 	if (ret)
 		goto err_unref;
 
-	pc->gtt_offset = obj->gtt_offset;
-	pc->cpu_page = kmap(sg_page(obj->pages->sgl));
-	if (pc->cpu_page == NULL) {
+	ring->scratch.gtt_offset = i915_gem_obj_ggtt_offset(ring->scratch.obj);
+	ring->scratch.cpu_page = kmap(sg_page(ring->scratch.obj->pages->sgl));
+	if (ring->scratch.cpu_page == NULL) {
 		ret = -ENOMEM;
 		goto err_unpin;
 	}
 
 	DRM_DEBUG_DRIVER("%s pipe control offset: 0x%08x\n",
-			 ring->name, pc->gtt_offset);
-
-	pc->obj = obj;
-	ring->private = pc;
+			 ring->name, ring->scratch.gtt_offset);
 	return 0;
 
 err_unpin:
-	i915_gem_object_unpin(obj);
+	i915_gem_object_unpin(ring->scratch.obj);
 err_unref:
-	drm_gem_object_unreference(&obj->base);
+	drm_gem_object_unreference(&ring->scratch.obj->base);
 err:
-	kfree(pc);
 	return ret;
 }
 
-static void
-cleanup_pipe_control(struct intel_ring_buffer *ring)
-{
-	struct pipe_control *pc = ring->private;
-	struct drm_i915_gem_object *obj;
-
-	obj = pc->obj;
-
-	kunmap(sg_page(obj->pages->sgl));
-	i915_gem_object_unpin(obj);
-	drm_gem_object_unreference(&obj->base);
-
-	kfree(pc);
-}
-
 static int init_render_ring(struct intel_ring_buffer *ring)
 {
 	struct drm_device *dev = ring->dev;
@@ -607,16 +569,16 @@ static void render_ring_cleanup(struct intel_ring_buffer *ring)
 {
 	struct drm_device *dev = ring->dev;
 
-	if (!ring->private)
+	if (ring->scratch.obj == NULL)
 		return;
 
-	if (HAS_BROKEN_CS_TLB(dev))
-		drm_gem_object_unreference(to_gem_object(ring->private));
-
-	if (INTEL_INFO(dev)->gen >= 5)
-		cleanup_pipe_control(ring);
+	if (INTEL_INFO(dev)->gen >= 5) {
+		kunmap(sg_page(ring->scratch.obj->pages->sgl));
+		i915_gem_object_unpin(ring->scratch.obj);
+	}
 
-	ring->private = NULL;
+	drm_gem_object_unreference(&ring->scratch.obj->base);
+	ring->scratch.obj = NULL;
 }
 
 static void
@@ -742,8 +704,7 @@ do {									\
 static int
 pc_render_add_request(struct intel_ring_buffer *ring)
 {
-	struct pipe_control *pc = ring->private;
-	u32 scratch_addr = pc->gtt_offset + 128;
+	u32 scratch_addr = ring->scratch.gtt_offset + 128;
 	int ret;
 
 	/* For Ironlake, MI_USER_INTERRUPT was deprecated and apparently
@@ -761,7 +722,7 @@ pc_render_add_request(struct intel_ring_buffer *ring)
 	intel_ring_emit(ring, GFX_OP_PIPE_CONTROL(4) | PIPE_CONTROL_QW_WRITE |
 			PIPE_CONTROL_WRITE_FLUSH |
 			PIPE_CONTROL_TEXTURE_CACHE_INVALIDATE);
-	intel_ring_emit(ring, pc->gtt_offset | PIPE_CONTROL_GLOBAL_GTT);
+	intel_ring_emit(ring, ring->scratch.gtt_offset | PIPE_CONTROL_GLOBAL_GTT);
 	intel_ring_emit(ring, ring->outstanding_lazy_request);
 	intel_ring_emit(ring, 0);
 	PIPE_CONTROL_FLUSH(ring, scratch_addr);
@@ -780,7 +741,7 @@ pc_render_add_request(struct intel_ring_buffer *ring)
 			PIPE_CONTROL_WRITE_FLUSH |
 			PIPE_CONTROL_TEXTURE_CACHE_INVALIDATE |
 			PIPE_CONTROL_NOTIFY);
-	intel_ring_emit(ring, pc->gtt_offset | PIPE_CONTROL_GLOBAL_GTT);
+	intel_ring_emit(ring, ring->scratch.gtt_offset | PIPE_CONTROL_GLOBAL_GTT);
 	intel_ring_emit(ring, ring->outstanding_lazy_request);
 	intel_ring_emit(ring, 0);
 	intel_ring_advance(ring);
@@ -814,15 +775,13 @@ ring_set_seqno(struct intel_ring_buffer *ring, u32 seqno)
 static u32
 pc_render_get_seqno(struct intel_ring_buffer *ring, bool lazy_coherency)
 {
-	struct pipe_control *pc = ring->private;
-	return pc->cpu_page[0];
+	return ring->scratch.cpu_page[0];
 }
 
 static void
 pc_render_set_seqno(struct intel_ring_buffer *ring, u32 seqno)
 {
-	struct pipe_control *pc = ring->private;
-	pc->cpu_page[0] = seqno;
+	ring->scratch.cpu_page[0] = seqno;
 }
 
 static bool
@@ -836,11 +795,8 @@ gen5_ring_get_irq(struct intel_ring_buffer *ring)
 		return false;
 
 	spin_lock_irqsave(&dev_priv->irq_lock, flags);
-	if (ring->irq_refcount.gt++ == 0) {
-		dev_priv->gt_irq_mask &= ~ring->irq_enable_mask;
-		I915_WRITE(GTIMR, dev_priv->gt_irq_mask);
-		POSTING_READ(GTIMR);
-	}
+	if (ring->irq_refcount++ == 0)
+		ilk_enable_gt_irq(dev_priv, ring->irq_enable_mask);
 	spin_unlock_irqrestore(&dev_priv->irq_lock, flags);
 
 	return true;
@@ -854,11 +810,8 @@ gen5_ring_put_irq(struct intel_ring_buffer *ring)
 	unsigned long flags;
 
 	spin_lock_irqsave(&dev_priv->irq_lock, flags);
-	if (--ring->irq_refcount.gt == 0) {
-		dev_priv->gt_irq_mask |= ring->irq_enable_mask;
-		I915_WRITE(GTIMR, dev_priv->gt_irq_mask);
-		POSTING_READ(GTIMR);
-	}
+	if (--ring->irq_refcount == 0)
+		ilk_disable_gt_irq(dev_priv, ring->irq_enable_mask);
 	spin_unlock_irqrestore(&dev_priv->irq_lock, flags);
 }
 
@@ -873,7 +826,7 @@ i9xx_ring_get_irq(struct intel_ring_buffer *ring)
 		return false;
 
 	spin_lock_irqsave(&dev_priv->irq_lock, flags);
-	if (ring->irq_refcount.gt++ == 0) {
+	if (ring->irq_refcount++ == 0) {
 		dev_priv->irq_mask &= ~ring->irq_enable_mask;
 		I915_WRITE(IMR, dev_priv->irq_mask);
 		POSTING_READ(IMR);
@@ -891,7 +844,7 @@ i9xx_ring_put_irq(struct intel_ring_buffer *ring)
 	unsigned long flags;
 
 	spin_lock_irqsave(&dev_priv->irq_lock, flags);
-	if (--ring->irq_refcount.gt == 0) {
+	if (--ring->irq_refcount == 0) {
 		dev_priv->irq_mask |= ring->irq_enable_mask;
 		I915_WRITE(IMR, dev_priv->irq_mask);
 		POSTING_READ(IMR);
@@ -910,7 +863,7 @@ i8xx_ring_get_irq(struct intel_ring_buffer *ring)
 		return false;
 
 	spin_lock_irqsave(&dev_priv->irq_lock, flags);
-	if (ring->irq_refcount.gt++ == 0) {
+	if (ring->irq_refcount++ == 0) {
 		dev_priv->irq_mask &= ~ring->irq_enable_mask;
 		I915_WRITE16(IMR, dev_priv->irq_mask);
 		POSTING_READ16(IMR);
@@ -928,7 +881,7 @@ i8xx_ring_put_irq(struct intel_ring_buffer *ring)
 	unsigned long flags;
 
 	spin_lock_irqsave(&dev_priv->irq_lock, flags);
-	if (--ring->irq_refcount.gt == 0) {
+	if (--ring->irq_refcount == 0) {
 		dev_priv->irq_mask |= ring->irq_enable_mask;
 		I915_WRITE16(IMR, dev_priv->irq_mask);
 		POSTING_READ16(IMR);
@@ -1033,16 +986,14 @@ gen6_ring_get_irq(struct intel_ring_buffer *ring)
 	gen6_gt_force_wake_get(dev_priv);
 
 	spin_lock_irqsave(&dev_priv->irq_lock, flags);
-	if (ring->irq_refcount.gt++ == 0) {
+	if (ring->irq_refcount++ == 0) {
 		if (HAS_L3_GPU_CACHE(dev) && ring->id == RCS)
 			I915_WRITE_IMR(ring,
 				       ~(ring->irq_enable_mask |
 					 GT_RENDER_L3_PARITY_ERROR_INTERRUPT));
 		else
 			I915_WRITE_IMR(ring, ~ring->irq_enable_mask);
-		dev_priv->gt_irq_mask &= ~ring->irq_enable_mask;
-		I915_WRITE(GTIMR, dev_priv->gt_irq_mask);
-		POSTING_READ(GTIMR);
+		ilk_enable_gt_irq(dev_priv, ring->irq_enable_mask);
 	}
 	spin_unlock_irqrestore(&dev_priv->irq_lock, flags);
 
@@ -1057,15 +1008,13 @@ gen6_ring_put_irq(struct intel_ring_buffer *ring)
 	unsigned long flags;
 
 	spin_lock_irqsave(&dev_priv->irq_lock, flags);
-	if (--ring->irq_refcount.gt == 0) {
+	if (--ring->irq_refcount == 0) {
 		if (HAS_L3_GPU_CACHE(dev) && ring->id == RCS)
 			I915_WRITE_IMR(ring,
 				       ~GT_RENDER_L3_PARITY_ERROR_INTERRUPT);
 		else
 			I915_WRITE_IMR(ring, ~0);
-		dev_priv->gt_irq_mask |= ring->irq_enable_mask;
-		I915_WRITE(GTIMR, dev_priv->gt_irq_mask);
-		POSTING_READ(GTIMR);
+		ilk_disable_gt_irq(dev_priv, ring->irq_enable_mask);
 	}
 	spin_unlock_irqrestore(&dev_priv->irq_lock, flags);
 
@@ -1082,14 +1031,12 @@ hsw_vebox_get_irq(struct intel_ring_buffer *ring)
 	if (!dev->irq_enabled)
 		return false;
 
-	spin_lock_irqsave(&dev_priv->rps.lock, flags);
-	if (ring->irq_refcount.pm++ == 0) {
-		u32 pm_imr = I915_READ(GEN6_PMIMR);
+	spin_lock_irqsave(&dev_priv->irq_lock, flags);
+	if (ring->irq_refcount++ == 0) {
 		I915_WRITE_IMR(ring, ~ring->irq_enable_mask);
-		I915_WRITE(GEN6_PMIMR, pm_imr & ~ring->irq_enable_mask);
-		POSTING_READ(GEN6_PMIMR);
+		snb_enable_pm_irq(dev_priv, ring->irq_enable_mask);
 	}
-	spin_unlock_irqrestore(&dev_priv->rps.lock, flags);
+	spin_unlock_irqrestore(&dev_priv->irq_lock, flags);
 
 	return true;
 }
@@ -1104,14 +1051,12 @@ hsw_vebox_put_irq(struct intel_ring_buffer *ring)
 	if (!dev->irq_enabled)
 		return;
 
-	spin_lock_irqsave(&dev_priv->rps.lock, flags);
-	if (--ring->irq_refcount.pm == 0) {
-		u32 pm_imr = I915_READ(GEN6_PMIMR);
+	spin_lock_irqsave(&dev_priv->irq_lock, flags);
+	if (--ring->irq_refcount == 0) {
 		I915_WRITE_IMR(ring, ~0);
-		I915_WRITE(GEN6_PMIMR, pm_imr | ring->irq_enable_mask);
-		POSTING_READ(GEN6_PMIMR);
+		snb_disable_pm_irq(dev_priv, ring->irq_enable_mask);
 	}
-	spin_unlock_irqrestore(&dev_priv->rps.lock, flags);
+	spin_unlock_irqrestore(&dev_priv->irq_lock, flags);
 }
 
 static int
@@ -1155,8 +1100,7 @@ i830_dispatch_execbuffer(struct intel_ring_buffer *ring,
 		intel_ring_emit(ring, MI_NOOP);
 		intel_ring_advance(ring);
 	} else {
-		struct drm_i915_gem_object *obj = ring->private;
-		u32 cs_offset = obj->gtt_offset;
+		u32 cs_offset = ring->scratch.gtt_offset;
 
 		if (len > I830_BATCH_LIMIT)
 			return -ENOSPC;
@@ -1236,12 +1180,12 @@ static int init_status_page(struct intel_ring_buffer *ring)
 
 	i915_gem_object_set_cache_level(obj, I915_CACHE_LLC);
 
-	ret = i915_gem_object_pin(obj, 4096, true, false);
+	ret = i915_gem_obj_ggtt_pin(obj, 4096, true, false);
 	if (ret != 0) {
 		goto err_unref;
 	}
 
-	ring->status_page.gfx_addr = obj->gtt_offset;
+	ring->status_page.gfx_addr = i915_gem_obj_ggtt_offset(obj);
 	ring->status_page.page_addr = kmap(sg_page(obj->pages->sgl));
 	if (ring->status_page.page_addr == NULL) {
 		ret = -ENOMEM;
@@ -1319,7 +1263,7 @@ static int intel_init_ring_buffer(struct drm_device *dev,
 
 	ring->obj = obj;
 
-	ret = i915_gem_object_pin(obj, PAGE_SIZE, true, false);
+	ret = i915_gem_obj_ggtt_pin(obj, PAGE_SIZE, true, false);
 	if (ret)
 		goto err_unref;
 
@@ -1328,7 +1272,7 @@ static int intel_init_ring_buffer(struct drm_device *dev,
 		goto err_unpin;
 
 	ring->virtual_start =
-		ioremap_wc(dev_priv->gtt.mappable_base + obj->gtt_offset,
+		ioremap_wc(dev_priv->gtt.mappable_base + i915_gem_obj_ggtt_offset(obj),
 			   ring->size);
 	if (ring->virtual_start == NULL) {
 		DRM_ERROR("Failed to map ringbuffer.\n");
@@ -1606,6 +1550,8 @@ void intel_ring_init_seqno(struct intel_ring_buffer *ring, u32 seqno)
 	if (INTEL_INFO(ring->dev)->gen >= 6) {
 		I915_WRITE(RING_SYNC_0(ring->mmio_base), 0);
 		I915_WRITE(RING_SYNC_1(ring->mmio_base), 0);
+		if (HAS_VEBOX(ring->dev))
+			I915_WRITE(RING_SYNC_2(ring->mmio_base), 0);
 	}
 
 	ring->set_seqno(ring, seqno);
@@ -1840,14 +1786,15 @@ int intel_init_render_ring_buffer(struct drm_device *dev)
 			return -ENOMEM;
 		}
 
-		ret = i915_gem_object_pin(obj, 0, true, false);
+		ret = i915_gem_obj_ggtt_pin(obj, 0, true, false);
 		if (ret != 0) {
 			drm_gem_object_unreference(&obj->base);
 			DRM_ERROR("Failed to ping batch bo\n");
 			return ret;
 		}
 
-		ring->private = obj;
+		ring->scratch.obj = obj;
+		ring->scratch.gtt_offset = i915_gem_obj_ggtt_offset(obj);
 	}
 
 	return intel_init_ring_buffer(dev, ring);
@@ -2020,8 +1967,7 @@ int intel_init_vebox_ring_buffer(struct drm_device *dev)
 	ring->add_request = gen6_add_request;
 	ring->get_seqno = gen6_ring_get_seqno;
 	ring->set_seqno = ring_set_seqno;
-	ring->irq_enable_mask = PM_VEBOX_USER_INTERRUPT |
-		PM_VEBOX_CS_ERROR_INTERRUPT;
+	ring->irq_enable_mask = PM_VEBOX_USER_INTERRUPT;
 	ring->irq_get = hsw_vebox_get_irq;
 	ring->irq_put = hsw_vebox_put_irq;
 	ring->dispatch_execbuffer = gen6_ring_dispatch_execbuffer;
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 799f04c9da45..68b1ca974d59 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -33,11 +33,12 @@ struct  intel_hw_status_page {
 #define I915_READ_IMR(ring) I915_READ(RING_IMR((ring)->mmio_base))
 #define I915_WRITE_IMR(ring, val) I915_WRITE(RING_IMR((ring)->mmio_base), val)
 
-#define I915_READ_NOPID(ring) I915_READ(RING_NOPID((ring)->mmio_base))
-#define I915_READ_SYNC_0(ring) I915_READ(RING_SYNC_0((ring)->mmio_base))
-#define I915_READ_SYNC_1(ring) I915_READ(RING_SYNC_1((ring)->mmio_base))
-
-enum intel_ring_hangcheck_action { wait, active, kick, hung };
+enum intel_ring_hangcheck_action {
+	HANGCHECK_WAIT,
+	HANGCHECK_ACTIVE,
+	HANGCHECK_KICK,
+	HANGCHECK_HUNG,
+};
 
 struct intel_ring_hangcheck {
 	bool deadlock;
@@ -78,10 +79,7 @@ struct  intel_ring_buffer {
 	 */
 	u32		last_retired_head;
 
-	struct {
-		u32	gt; /*  protected by dev_priv->irq_lock */
-		u32	pm; /*  protected by dev_priv->rps.lock (sucks) */
-	} irq_refcount;
+	unsigned irq_refcount; /* protected by dev_priv->irq_lock */
 	u32		irq_enable_mask;	/* bitmask to enable ring interrupt */
 	u32		trace_irq_seqno;
 	u32		sync_seqno[I915_NUM_RINGS-1];
@@ -157,7 +155,11 @@ struct  intel_ring_buffer {
 
 	struct intel_ring_hangcheck hangcheck;
 
-	void *private;
+	struct {
+		struct drm_i915_gem_object *obj;
+		u32 gtt_offset;
+		volatile u32 *cpu_page;
+	} scratch;
 };
 
 static inline bool
diff --git a/drivers/gpu/drm/i915/intel_sdvo.c b/drivers/gpu/drm/i915/intel_sdvo.c
index 2628d5622449..49482fd5b76c 100644
--- a/drivers/gpu/drm/i915/intel_sdvo.c
+++ b/drivers/gpu/drm/i915/intel_sdvo.c
@@ -202,15 +202,14 @@ struct intel_sdvo_connector {
 	u32	cur_dot_crawl,	max_dot_crawl;
 };
 
-static struct intel_sdvo *to_intel_sdvo(struct drm_encoder *encoder)
+static struct intel_sdvo *to_sdvo(struct intel_encoder *encoder)
 {
-	return container_of(encoder, struct intel_sdvo, base.base);
+	return container_of(encoder, struct intel_sdvo, base);
 }
 
 static struct intel_sdvo *intel_attached_sdvo(struct drm_connector *connector)
 {
-	return container_of(intel_attached_encoder(connector),
-			    struct intel_sdvo, base);
+	return to_sdvo(intel_attached_encoder(connector));
 }
 
 static struct intel_sdvo_connector *to_intel_sdvo_connector(struct drm_connector *connector)
@@ -539,7 +538,8 @@ static bool intel_sdvo_read_response(struct intel_sdvo *intel_sdvo,
 				  &status))
 		goto log_fail;
 
-	while (status == SDVO_CMD_STATUS_PENDING && --retry) {
+	while ((status == SDVO_CMD_STATUS_PENDING ||
+			status == SDVO_CMD_STATUS_TARGET_NOT_SPECIFIED) && --retry) {
 		if (retry < 10)
 			msleep(15);
 		else
@@ -788,6 +788,8 @@ static void intel_sdvo_get_dtd_from_mode(struct intel_sdvo_dtd *dtd,
 	uint16_t h_sync_offset, v_sync_offset;
 	int mode_clock;
 
+	memset(dtd, 0, sizeof(*dtd));
+
 	width = mode->hdisplay;
 	height = mode->vdisplay;
 
@@ -830,44 +832,51 @@ static void intel_sdvo_get_dtd_from_mode(struct intel_sdvo_dtd *dtd,
 	if (mode->flags & DRM_MODE_FLAG_PVSYNC)
 		dtd->part2.dtd_flags |= DTD_FLAG_VSYNC_POSITIVE;
 
-	dtd->part2.sdvo_flags = 0;
 	dtd->part2.v_sync_off_high = v_sync_offset & 0xc0;
-	dtd->part2.reserved = 0;
 }
 
-static void intel_sdvo_get_mode_from_dtd(struct drm_display_mode * mode,
+static void intel_sdvo_get_mode_from_dtd(struct drm_display_mode *pmode,
 					 const struct intel_sdvo_dtd *dtd)
 {
-	mode->hdisplay = dtd->part1.h_active;
-	mode->hdisplay += ((dtd->part1.h_high >> 4) & 0x0f) << 8;
-	mode->hsync_start = mode->hdisplay + dtd->part2.h_sync_off;
-	mode->hsync_start += (dtd->part2.sync_off_width_high & 0xc0) << 2;
-	mode->hsync_end = mode->hsync_start + dtd->part2.h_sync_width;
-	mode->hsync_end += (dtd->part2.sync_off_width_high & 0x30) << 4;
-	mode->htotal = mode->hdisplay + dtd->part1.h_blank;
-	mode->htotal += (dtd->part1.h_high & 0xf) << 8;
-
-	mode->vdisplay = dtd->part1.v_active;
-	mode->vdisplay += ((dtd->part1.v_high >> 4) & 0x0f) << 8;
-	mode->vsync_start = mode->vdisplay;
-	mode->vsync_start += (dtd->part2.v_sync_off_width >> 4) & 0xf;
-	mode->vsync_start += (dtd->part2.sync_off_width_high & 0x0c) << 2;
-	mode->vsync_start += dtd->part2.v_sync_off_high & 0xc0;
-	mode->vsync_end = mode->vsync_start +
+	struct drm_display_mode mode = {};
+
+	mode.hdisplay = dtd->part1.h_active;
+	mode.hdisplay += ((dtd->part1.h_high >> 4) & 0x0f) << 8;
+	mode.hsync_start = mode.hdisplay + dtd->part2.h_sync_off;
+	mode.hsync_start += (dtd->part2.sync_off_width_high & 0xc0) << 2;
+	mode.hsync_end = mode.hsync_start + dtd->part2.h_sync_width;
+	mode.hsync_end += (dtd->part2.sync_off_width_high & 0x30) << 4;
+	mode.htotal = mode.hdisplay + dtd->part1.h_blank;
+	mode.htotal += (dtd->part1.h_high & 0xf) << 8;
+
+	mode.vdisplay = dtd->part1.v_active;
+	mode.vdisplay += ((dtd->part1.v_high >> 4) & 0x0f) << 8;
+	mode.vsync_start = mode.vdisplay;
+	mode.vsync_start += (dtd->part2.v_sync_off_width >> 4) & 0xf;
+	mode.vsync_start += (dtd->part2.sync_off_width_high & 0x0c) << 2;
+	mode.vsync_start += dtd->part2.v_sync_off_high & 0xc0;
+	mode.vsync_end = mode.vsync_start +
 		(dtd->part2.v_sync_off_width & 0xf);
-	mode->vsync_end += (dtd->part2.sync_off_width_high & 0x3) << 4;
-	mode->vtotal = mode->vdisplay + dtd->part1.v_blank;
-	mode->vtotal += (dtd->part1.v_high & 0xf) << 8;
+	mode.vsync_end += (dtd->part2.sync_off_width_high & 0x3) << 4;
+	mode.vtotal = mode.vdisplay + dtd->part1.v_blank;
+	mode.vtotal += (dtd->part1.v_high & 0xf) << 8;
 
-	mode->clock = dtd->part1.clock * 10;
+	mode.clock = dtd->part1.clock * 10;
 
-	mode->flags &= ~(DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC);
 	if (dtd->part2.dtd_flags & DTD_FLAG_INTERLACE)
-		mode->flags |= DRM_MODE_FLAG_INTERLACE;
+		mode.flags |= DRM_MODE_FLAG_INTERLACE;
 	if (dtd->part2.dtd_flags & DTD_FLAG_HSYNC_POSITIVE)
-		mode->flags |= DRM_MODE_FLAG_PHSYNC;
+		mode.flags |= DRM_MODE_FLAG_PHSYNC;
+	else
+		mode.flags |= DRM_MODE_FLAG_NHSYNC;
 	if (dtd->part2.dtd_flags & DTD_FLAG_VSYNC_POSITIVE)
-		mode->flags |= DRM_MODE_FLAG_PVSYNC;
+		mode.flags |= DRM_MODE_FLAG_PVSYNC;
+	else
+		mode.flags |= DRM_MODE_FLAG_NVSYNC;
+
+	drm_mode_set_crtcinfo(&mode, 0);
+
+	drm_mode_copy(pmode, &mode);
 }
 
 static bool intel_sdvo_check_supp_encode(struct intel_sdvo *intel_sdvo)
@@ -964,30 +973,32 @@ static bool intel_sdvo_write_infoframe(struct intel_sdvo *intel_sdvo,
 static bool intel_sdvo_set_avi_infoframe(struct intel_sdvo *intel_sdvo,
 					 const struct drm_display_mode *adjusted_mode)
 {
-	struct dip_infoframe avi_if = {
-		.type = DIP_TYPE_AVI,
-		.ver = DIP_VERSION_AVI,
-		.len = DIP_LEN_AVI,
-	};
-	uint8_t sdvo_data[4 + sizeof(avi_if.body.avi)];
-	struct intel_crtc *intel_crtc = to_intel_crtc(intel_sdvo->base.base.crtc);
+	uint8_t sdvo_data[HDMI_INFOFRAME_SIZE(AVI)];
+	struct drm_crtc *crtc = intel_sdvo->base.base.crtc;
+	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
+	union hdmi_infoframe frame;
+	int ret;
+	ssize_t len;
+
+	ret = drm_hdmi_avi_infoframe_from_display_mode(&frame.avi,
+						       adjusted_mode);
+	if (ret < 0) {
+		DRM_ERROR("couldn't fill AVI infoframe\n");
+		return false;
+	}
 
 	if (intel_sdvo->rgb_quant_range_selectable) {
 		if (intel_crtc->config.limited_color_range)
-			avi_if.body.avi.ITC_EC_Q_SC |= DIP_AVI_RGB_QUANT_RANGE_LIMITED;
+			frame.avi.quantization_range =
+				HDMI_QUANTIZATION_RANGE_LIMITED;
 		else
-			avi_if.body.avi.ITC_EC_Q_SC |= DIP_AVI_RGB_QUANT_RANGE_FULL;
+			frame.avi.quantization_range =
+				HDMI_QUANTIZATION_RANGE_FULL;
 	}
 
-	avi_if.body.avi.VIC = drm_match_cea_mode(adjusted_mode);
-
-	intel_dip_infoframe_csum(&avi_if);
-
-	/* sdvo spec says that the ecc is handled by the hw, and it looks like
-	 * we must not send the ecc field, either. */
-	memcpy(sdvo_data, &avi_if, 3);
-	sdvo_data[3] = avi_if.checksum;
-	memcpy(&sdvo_data[4], &avi_if.body, sizeof(avi_if.body.avi));
+	len = hdmi_infoframe_pack(&frame, sdvo_data, sizeof(sdvo_data));
+	if (len < 0)
+		return false;
 
 	return intel_sdvo_write_infoframe(intel_sdvo, SDVO_HBUF_INDEX_AVI_IF,
 					  SDVO_HBUF_TX_VSYNC,
@@ -1084,7 +1095,7 @@ static void i9xx_adjust_sdvo_tv_clock(struct intel_crtc_config *pipe_config)
 static bool intel_sdvo_compute_config(struct intel_encoder *encoder,
 				      struct intel_crtc_config *pipe_config)
 {
-	struct intel_sdvo *intel_sdvo = to_intel_sdvo(&encoder->base);
+	struct intel_sdvo *intel_sdvo = to_sdvo(encoder);
 	struct drm_display_mode *adjusted_mode = &pipe_config->adjusted_mode;
 	struct drm_display_mode *mode = &pipe_config->requested_mode;
 
@@ -1149,12 +1160,11 @@ static void intel_sdvo_mode_set(struct intel_encoder *intel_encoder)
 {
 	struct drm_device *dev = intel_encoder->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct drm_crtc *crtc = intel_encoder->base.crtc;
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
+	struct intel_crtc *crtc = to_intel_crtc(intel_encoder->base.crtc);
 	struct drm_display_mode *adjusted_mode =
-		&intel_crtc->config.adjusted_mode;
-	struct drm_display_mode *mode = &intel_crtc->config.requested_mode;
-	struct intel_sdvo *intel_sdvo = to_intel_sdvo(&intel_encoder->base);
+		&crtc->config.adjusted_mode;
+	struct drm_display_mode *mode = &crtc->config.requested_mode;
+	struct intel_sdvo *intel_sdvo = to_sdvo(intel_encoder);
 	u32 sdvox;
 	struct intel_sdvo_in_out_map in_out;
 	struct intel_sdvo_dtd input_dtd, output_dtd;
@@ -1211,13 +1221,15 @@ static void intel_sdvo_mode_set(struct intel_encoder *intel_encoder)
 	 * adjusted_mode.
 	 */
 	intel_sdvo_get_dtd_from_mode(&input_dtd, adjusted_mode);
+	input_dtd.part1.clock /= crtc->config.pixel_multiplier;
+
 	if (intel_sdvo->is_tv || intel_sdvo->is_lvds)
 		input_dtd.part2.sdvo_flags = intel_sdvo->dtd_sdvo_flags;
 	if (!intel_sdvo_set_input_timing(intel_sdvo, &input_dtd))
 		DRM_INFO("Setting input timings on %s failed\n",
 			 SDVO_NAME(intel_sdvo));
 
-	switch (intel_crtc->config.pixel_multiplier) {
+	switch (crtc->config.pixel_multiplier) {
 	default:
 		WARN(1, "unknown pixel mutlipler specified\n");
 	case 1: rate = SDVO_CLOCK_RATE_MULT_1X; break;
@@ -1250,9 +1262,9 @@ static void intel_sdvo_mode_set(struct intel_encoder *intel_encoder)
 	}
 
 	if (INTEL_PCH_TYPE(dev) >= PCH_CPT)
-		sdvox |= SDVO_PIPE_SEL_CPT(intel_crtc->pipe);
+		sdvox |= SDVO_PIPE_SEL_CPT(crtc->pipe);
 	else
-		sdvox |= SDVO_PIPE_SEL(intel_crtc->pipe);
+		sdvox |= SDVO_PIPE_SEL(crtc->pipe);
 
 	if (intel_sdvo->has_hdmi_audio)
 		sdvox |= SDVO_AUDIO_ENABLE;
@@ -1262,7 +1274,7 @@ static void intel_sdvo_mode_set(struct intel_encoder *intel_encoder)
 	} else if (IS_I945G(dev) || IS_I945GM(dev) || IS_G33(dev)) {
 		/* done in crtc_mode_set as it lives inside the dpll register */
 	} else {
-		sdvox |= (intel_crtc->config.pixel_multiplier - 1)
+		sdvox |= (crtc->config.pixel_multiplier - 1)
 			<< SDVO_PORT_MULTIPLY_SHIFT;
 	}
 
@@ -1292,7 +1304,7 @@ static bool intel_sdvo_get_hw_state(struct intel_encoder *encoder,
 {
 	struct drm_device *dev = encoder->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_sdvo *intel_sdvo = to_intel_sdvo(&encoder->base);
+	struct intel_sdvo *intel_sdvo = to_sdvo(encoder);
 	u16 active_outputs = 0;
 	u32 tmp;
 
@@ -1315,7 +1327,7 @@ static void intel_sdvo_get_config(struct intel_encoder *encoder,
 {
 	struct drm_device *dev = encoder->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_sdvo *intel_sdvo = to_intel_sdvo(&encoder->base);
+	struct intel_sdvo *intel_sdvo = to_sdvo(encoder);
 	struct intel_sdvo_dtd dtd;
 	int encoder_pixel_multiplier = 0;
 	u32 flags = 0, sdvox;
@@ -1357,22 +1369,21 @@ static void intel_sdvo_get_config(struct intel_encoder *encoder,
 	}
 
 	/* Cross check the port pixel multiplier with the sdvo encoder state. */
-	intel_sdvo_get_value(intel_sdvo, SDVO_CMD_GET_CLOCK_RATE_MULT, &val, 1);
-	switch (val) {
-	case SDVO_CLOCK_RATE_MULT_1X:
-		encoder_pixel_multiplier = 1;
-		break;
-	case SDVO_CLOCK_RATE_MULT_2X:
-		encoder_pixel_multiplier = 2;
-		break;
-	case SDVO_CLOCK_RATE_MULT_4X:
-		encoder_pixel_multiplier = 4;
-		break;
+	if (intel_sdvo_get_value(intel_sdvo, SDVO_CMD_GET_CLOCK_RATE_MULT,
+				 &val, 1)) {
+		switch (val) {
+		case SDVO_CLOCK_RATE_MULT_1X:
+			encoder_pixel_multiplier = 1;
+			break;
+		case SDVO_CLOCK_RATE_MULT_2X:
+			encoder_pixel_multiplier = 2;
+			break;
+		case SDVO_CLOCK_RATE_MULT_4X:
+			encoder_pixel_multiplier = 4;
+			break;
+		}
 	}
 
-	if(HAS_PCH_SPLIT(dev))
-		return; /* no pixel multiplier readout support yet */
-
 	WARN(encoder_pixel_multiplier != pipe_config->pixel_multiplier,
 	     "SDVO pixel multiplier mismatch, port: %i, encoder: %i\n",
 	     pipe_config->pixel_multiplier, encoder_pixel_multiplier);
@@ -1381,7 +1392,7 @@ static void intel_sdvo_get_config(struct intel_encoder *encoder,
 static void intel_disable_sdvo(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = encoder->base.dev->dev_private;
-	struct intel_sdvo *intel_sdvo = to_intel_sdvo(&encoder->base);
+	struct intel_sdvo *intel_sdvo = to_sdvo(encoder);
 	u32 temp;
 
 	intel_sdvo_set_active_outputs(intel_sdvo, 0);
@@ -1423,7 +1434,7 @@ static void intel_enable_sdvo(struct intel_encoder *encoder)
 {
 	struct drm_device *dev = encoder->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_sdvo *intel_sdvo = to_intel_sdvo(&encoder->base);
+	struct intel_sdvo *intel_sdvo = to_sdvo(encoder);
 	struct intel_crtc *intel_crtc = to_intel_crtc(encoder->base.crtc);
 	u32 temp;
 	bool input1, input2;
@@ -1584,7 +1595,7 @@ static uint16_t intel_sdvo_get_hotplug_support(struct intel_sdvo *intel_sdvo)
 
 static void intel_sdvo_enable_hotplug(struct intel_encoder *encoder)
 {
-	struct intel_sdvo *intel_sdvo = to_intel_sdvo(&encoder->base);
+	struct intel_sdvo *intel_sdvo = to_sdvo(encoder);
 
 	intel_sdvo_write_cmd(intel_sdvo, SDVO_CMD_SET_ACTIVE_HOT_PLUG,
 			&intel_sdvo->hotplug_active, 2);
@@ -1697,6 +1708,9 @@ intel_sdvo_detect(struct drm_connector *connector, bool force)
 	struct intel_sdvo_connector *intel_sdvo_connector = to_intel_sdvo_connector(connector);
 	enum drm_connector_status ret;
 
+	DRM_DEBUG_KMS("[CONNECTOR:%d:%s]\n",
+		      connector->base.id, drm_get_connector_name(connector));
+
 	if (!intel_sdvo_get_value(intel_sdvo,
 				  SDVO_CMD_GET_ATTACHED_DISPLAYS,
 				  &response, 2))
@@ -2188,7 +2202,7 @@ static const struct drm_connector_helper_funcs intel_sdvo_connector_helper_funcs
 
 static void intel_sdvo_enc_destroy(struct drm_encoder *encoder)
 {
-	struct intel_sdvo *intel_sdvo = to_intel_sdvo(encoder);
+	struct intel_sdvo *intel_sdvo = to_sdvo(to_intel_encoder(encoder));
 
 	if (intel_sdvo->sdvo_lvds_fixed_mode != NULL)
 		drm_mode_destroy(encoder->dev,
diff --git a/drivers/gpu/drm/i915/intel_sprite.c b/drivers/gpu/drm/i915/intel_sprite.c
index 1fa5612a4572..ad6ec4b39005 100644
--- a/drivers/gpu/drm/i915/intel_sprite.c
+++ b/drivers/gpu/drm/i915/intel_sprite.c
@@ -38,7 +38,8 @@
 #include "i915_drv.h"
 
 static void
-vlv_update_plane(struct drm_plane *dplane, struct drm_framebuffer *fb,
+vlv_update_plane(struct drm_plane *dplane, struct drm_crtc *crtc,
+		 struct drm_framebuffer *fb,
 		 struct drm_i915_gem_object *obj, int crtc_x, int crtc_y,
 		 unsigned int crtc_w, unsigned int crtc_h,
 		 uint32_t x, uint32_t y,
@@ -108,14 +109,15 @@ vlv_update_plane(struct drm_plane *dplane, struct drm_framebuffer *fb,
 
 	sprctl |= SP_ENABLE;
 
+	intel_update_sprite_watermarks(dplane, crtc, src_w, pixel_size, true,
+				       src_w != crtc_w || src_h != crtc_h);
+
 	/* Sizes are 0 based */
 	src_w--;
 	src_h--;
 	crtc_w--;
 	crtc_h--;
 
-	intel_update_sprite_watermarks(dev, pipe, crtc_w, pixel_size, true);
-
 	I915_WRITE(SPSTRIDE(pipe, plane), fb->pitches[0]);
 	I915_WRITE(SPPOS(pipe, plane), (crtc_y << 16) | crtc_x);
 
@@ -133,13 +135,13 @@ vlv_update_plane(struct drm_plane *dplane, struct drm_framebuffer *fb,
 
 	I915_WRITE(SPSIZE(pipe, plane), (crtc_h << 16) | crtc_w);
 	I915_WRITE(SPCNTR(pipe, plane), sprctl);
-	I915_MODIFY_DISPBASE(SPSURF(pipe, plane), obj->gtt_offset +
+	I915_MODIFY_DISPBASE(SPSURF(pipe, plane), i915_gem_obj_ggtt_offset(obj) +
 			     sprsurf_offset);
 	POSTING_READ(SPSURF(pipe, plane));
 }
 
 static void
-vlv_disable_plane(struct drm_plane *dplane)
+vlv_disable_plane(struct drm_plane *dplane, struct drm_crtc *crtc)
 {
 	struct drm_device *dev = dplane->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -152,6 +154,8 @@ vlv_disable_plane(struct drm_plane *dplane)
 	/* Activate double buffered register update */
 	I915_MODIFY_DISPBASE(SPSURF(pipe, plane), 0);
 	POSTING_READ(SPSURF(pipe, plane));
+
+	intel_update_sprite_watermarks(dplane, crtc, 0, 0, false, false);
 }
 
 static int
@@ -206,7 +210,8 @@ vlv_get_colorkey(struct drm_plane *dplane,
 }
 
 static void
-ivb_update_plane(struct drm_plane *plane, struct drm_framebuffer *fb,
+ivb_update_plane(struct drm_plane *plane, struct drm_crtc *crtc,
+		 struct drm_framebuffer *fb,
 		 struct drm_i915_gem_object *obj, int crtc_x, int crtc_y,
 		 unsigned int crtc_w, unsigned int crtc_h,
 		 uint32_t x, uint32_t y,
@@ -255,21 +260,25 @@ ivb_update_plane(struct drm_plane *plane, struct drm_framebuffer *fb,
 	if (obj->tiling_mode != I915_TILING_NONE)
 		sprctl |= SPRITE_TILED;
 
-	/* must disable */
-	sprctl |= SPRITE_TRICKLE_FEED_DISABLE;
+	if (IS_HASWELL(dev))
+		sprctl &= ~SPRITE_TRICKLE_FEED_DISABLE;
+	else
+		sprctl |= SPRITE_TRICKLE_FEED_DISABLE;
+
 	sprctl |= SPRITE_ENABLE;
 
 	if (IS_HASWELL(dev))
 		sprctl |= SPRITE_PIPE_CSC_ENABLE;
 
+	intel_update_sprite_watermarks(plane, crtc, src_w, pixel_size, true,
+				       src_w != crtc_w || src_h != crtc_h);
+
 	/* Sizes are 0 based */
 	src_w--;
 	src_h--;
 	crtc_w--;
 	crtc_h--;
 
-	intel_update_sprite_watermarks(dev, pipe, crtc_w, pixel_size, true);
-
 	/*
 	 * IVB workaround: must disable low power watermarks for at least
 	 * one frame before enabling scaling.  LP watermarks can be re-enabled
@@ -308,7 +317,8 @@ ivb_update_plane(struct drm_plane *plane, struct drm_framebuffer *fb,
 	if (intel_plane->can_scale)
 		I915_WRITE(SPRSCALE(pipe), sprscale);
 	I915_WRITE(SPRCTL(pipe), sprctl);
-	I915_MODIFY_DISPBASE(SPRSURF(pipe), obj->gtt_offset + sprsurf_offset);
+	I915_MODIFY_DISPBASE(SPRSURF(pipe),
+			     i915_gem_obj_ggtt_offset(obj) + sprsurf_offset);
 	POSTING_READ(SPRSURF(pipe));
 
 	/* potentially re-enable LP watermarks */
@@ -317,7 +327,7 @@ ivb_update_plane(struct drm_plane *plane, struct drm_framebuffer *fb,
 }
 
 static void
-ivb_disable_plane(struct drm_plane *plane)
+ivb_disable_plane(struct drm_plane *plane, struct drm_crtc *crtc)
 {
 	struct drm_device *dev = plane->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -335,7 +345,7 @@ ivb_disable_plane(struct drm_plane *plane)
 
 	dev_priv->sprite_scaling_enabled &= ~(1 << pipe);
 
-	intel_update_sprite_watermarks(dev, pipe, 0, 0, false);
+	intel_update_sprite_watermarks(plane, crtc, 0, 0, false, false);
 
 	/* potentially re-enable LP watermarks */
 	if (scaling_was_enabled && !dev_priv->sprite_scaling_enabled)
@@ -397,7 +407,8 @@ ivb_get_colorkey(struct drm_plane *plane, struct drm_intel_sprite_colorkey *key)
 }
 
 static void
-ilk_update_plane(struct drm_plane *plane, struct drm_framebuffer *fb,
+ilk_update_plane(struct drm_plane *plane, struct drm_crtc *crtc,
+		 struct drm_framebuffer *fb,
 		 struct drm_i915_gem_object *obj, int crtc_x, int crtc_y,
 		 unsigned int crtc_w, unsigned int crtc_h,
 		 uint32_t x, uint32_t y,
@@ -449,14 +460,15 @@ ilk_update_plane(struct drm_plane *plane, struct drm_framebuffer *fb,
 		dvscntr |= DVS_TRICKLE_FEED_DISABLE; /* must disable */
 	dvscntr |= DVS_ENABLE;
 
+	intel_update_sprite_watermarks(plane, crtc, src_w, pixel_size, true,
+				       src_w != crtc_w || src_h != crtc_h);
+
 	/* Sizes are 0 based */
 	src_w--;
 	src_h--;
 	crtc_w--;
 	crtc_h--;
 
-	intel_update_sprite_watermarks(dev, pipe, crtc_w, pixel_size, true);
-
 	dvsscale = 0;
 	if (IS_GEN5(dev) || crtc_w != src_w || crtc_h != src_h)
 		dvsscale = DVS_SCALE_ENABLE | (src_w << 16) | src_h;
@@ -478,12 +490,13 @@ ilk_update_plane(struct drm_plane *plane, struct drm_framebuffer *fb,
 	I915_WRITE(DVSSIZE(pipe), (crtc_h << 16) | crtc_w);
 	I915_WRITE(DVSSCALE(pipe), dvsscale);
 	I915_WRITE(DVSCNTR(pipe), dvscntr);
-	I915_MODIFY_DISPBASE(DVSSURF(pipe), obj->gtt_offset + dvssurf_offset);
+	I915_MODIFY_DISPBASE(DVSSURF(pipe),
+			     i915_gem_obj_ggtt_offset(obj) + dvssurf_offset);
 	POSTING_READ(DVSSURF(pipe));
 }
 
 static void
-ilk_disable_plane(struct drm_plane *plane)
+ilk_disable_plane(struct drm_plane *plane, struct drm_crtc *crtc)
 {
 	struct drm_device *dev = plane->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -496,6 +509,8 @@ ilk_disable_plane(struct drm_plane *plane)
 	/* Flush double buffered register updates */
 	I915_MODIFY_DISPBASE(DVSSURF(pipe), 0);
 	POSTING_READ(DVSSURF(pipe));
+
+	intel_update_sprite_watermarks(plane, crtc, 0, 0, false, false);
 }
 
 static void
@@ -818,11 +833,11 @@ intel_update_plane(struct drm_plane *plane, struct drm_crtc *crtc,
 		intel_enable_primary(crtc);
 
 	if (visible)
-		intel_plane->update_plane(plane, fb, obj,
+		intel_plane->update_plane(plane, crtc, fb, obj,
 					  crtc_x, crtc_y, crtc_w, crtc_h,
 					  src_x, src_y, src_w, src_h);
 	else
-		intel_plane->disable_plane(plane);
+		intel_plane->disable_plane(plane, crtc);
 
 	if (disable_primary)
 		intel_disable_primary(crtc);
@@ -855,9 +870,14 @@ intel_disable_plane(struct drm_plane *plane)
 	struct intel_plane *intel_plane = to_intel_plane(plane);
 	int ret = 0;
 
-	if (plane->crtc)
-		intel_enable_primary(plane->crtc);
-	intel_plane->disable_plane(plane);
+	if (!plane->fb)
+		return 0;
+
+	if (WARN_ON(!plane->crtc))
+		return -EINVAL;
+
+	intel_enable_primary(plane->crtc);
+	intel_plane->disable_plane(plane, plane->crtc);
 
 	if (!intel_plane->obj)
 		goto out;
diff --git a/drivers/gpu/drm/i915/intel_tv.c b/drivers/gpu/drm/i915/intel_tv.c
index 39debd80d190..dd6f84bf6c22 100644
--- a/drivers/gpu/drm/i915/intel_tv.c
+++ b/drivers/gpu/drm/i915/intel_tv.c
@@ -823,16 +823,14 @@ static const struct tv_mode tv_modes[] = {
 	},
 };
 
-static struct intel_tv *enc_to_intel_tv(struct drm_encoder *encoder)
+static struct intel_tv *enc_to_tv(struct intel_encoder *encoder)
 {
-	return container_of(encoder, struct intel_tv, base.base);
+	return container_of(encoder, struct intel_tv, base);
 }
 
 static struct intel_tv *intel_attached_tv(struct drm_connector *connector)
 {
-	return container_of(intel_attached_encoder(connector),
-			    struct intel_tv,
-			    base);
+	return enc_to_tv(intel_attached_encoder(connector));
 }
 
 static bool
@@ -908,7 +906,7 @@ static bool
 intel_tv_compute_config(struct intel_encoder *encoder,
 			struct intel_crtc_config *pipe_config)
 {
-	struct intel_tv *intel_tv = enc_to_intel_tv(&encoder->base);
+	struct intel_tv *intel_tv = enc_to_tv(encoder);
 	const struct tv_mode *tv_mode = intel_tv_mode_find(intel_tv);
 
 	if (!tv_mode)
@@ -918,18 +916,23 @@ intel_tv_compute_config(struct intel_encoder *encoder,
 	DRM_DEBUG_KMS("forcing bpc to 8 for TV\n");
 	pipe_config->pipe_bpp = 8*3;
 
+	/* TV has it's own notion of sync and other mode flags, so clear them. */
+	pipe_config->adjusted_mode.flags = 0;
+
+	/*
+	 * FIXME: We don't check whether the input mode is actually what we want
+	 * or whether userspace is doing something stupid.
+	 */
+
 	return true;
 }
 
-static void
-intel_tv_mode_set(struct drm_encoder *encoder, struct drm_display_mode *mode,
-		  struct drm_display_mode *adjusted_mode)
+static void intel_tv_mode_set(struct intel_encoder *encoder)
 {
-	struct drm_device *dev = encoder->dev;
+	struct drm_device *dev = encoder->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct drm_crtc *crtc = encoder->crtc;
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	struct intel_tv *intel_tv = enc_to_intel_tv(encoder);
+	struct intel_crtc *intel_crtc = to_intel_crtc(encoder->base.crtc);
+	struct intel_tv *intel_tv = enc_to_tv(encoder);
 	const struct tv_mode *tv_mode = intel_tv_mode_find(intel_tv);
 	u32 tv_ctl;
 	u32 hctl1, hctl2, hctl3;
@@ -1305,6 +1308,10 @@ intel_tv_detect(struct drm_connector *connector, bool force)
 	struct intel_tv *intel_tv = intel_attached_tv(connector);
 	int type;
 
+	DRM_DEBUG_KMS("[CONNECTOR:%d:%s] force=%d\n",
+		      connector->base.id, drm_get_connector_name(connector),
+		      force);
+
 	mode = reported_modes[0];
 
 	if (force) {
@@ -1483,10 +1490,6 @@ out:
 	return ret;
 }
 
-static const struct drm_encoder_helper_funcs intel_tv_helper_funcs = {
-	.mode_set = intel_tv_mode_set,
-};
-
 static const struct drm_connector_funcs intel_tv_connector_funcs = {
 	.dpms = intel_connector_dpms,
 	.detect = intel_tv_detect,
@@ -1619,6 +1622,7 @@ intel_tv_init(struct drm_device *dev)
 			 DRM_MODE_ENCODER_TVDAC);
 
 	intel_encoder->compute_config = intel_tv_compute_config;
+	intel_encoder->mode_set = intel_tv_mode_set;
 	intel_encoder->enable = intel_enable_tv;
 	intel_encoder->disable = intel_disable_tv;
 	intel_encoder->get_hw_state = intel_tv_get_hw_state;
@@ -1640,7 +1644,6 @@ intel_tv_init(struct drm_device *dev)
 
 	intel_tv->tv_format = tv_modes[initial_mode].name;
 
-	drm_encoder_helper_add(&intel_encoder->base, &intel_tv_helper_funcs);
 	drm_connector_helper_add(connector, &intel_tv_connector_helper_funcs);
 	connector->interlace_allowed = false;
 	connector->doublescan_allowed = false;
diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
new file mode 100644
index 000000000000..8649f1c36b00
--- /dev/null
+++ b/drivers/gpu/drm/i915/intel_uncore.c
@@ -0,0 +1,602 @@
+/*
+ * Copyright © 2013 Intel Corporation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the next
+ * paragraph) shall be included in all copies or substantial portions of the
+ * Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ */
+
+#include "i915_drv.h"
+#include "intel_drv.h"
+
+#define FORCEWAKE_ACK_TIMEOUT_MS 2
+
+#define __raw_i915_read8(dev_priv__, reg__) readb((dev_priv__)->regs + (reg__))
+#define __raw_i915_write8(dev_priv__, reg__, val__) writeb(val__, (dev_priv__)->regs + (reg__))
+
+#define __raw_i915_read16(dev_priv__, reg__) readw((dev_priv__)->regs + (reg__))
+#define __raw_i915_write16(dev_priv__, reg__, val__) writew(val__, (dev_priv__)->regs + (reg__))
+
+#define __raw_i915_read32(dev_priv__, reg__) readl((dev_priv__)->regs + (reg__))
+#define __raw_i915_write32(dev_priv__, reg__, val__) writel(val__, (dev_priv__)->regs + (reg__))
+
+#define __raw_i915_read64(dev_priv__, reg__) readq((dev_priv__)->regs + (reg__))
+#define __raw_i915_write64(dev_priv__, reg__, val__) writeq(val__, (dev_priv__)->regs + (reg__))
+
+#define __raw_posting_read(dev_priv__, reg__) (void)__raw_i915_read32(dev_priv__, reg__)
+
+
+static void __gen6_gt_wait_for_thread_c0(struct drm_i915_private *dev_priv)
+{
+	u32 gt_thread_status_mask;
+
+	if (IS_HASWELL(dev_priv->dev))
+		gt_thread_status_mask = GEN6_GT_THREAD_STATUS_CORE_MASK_HSW;
+	else
+		gt_thread_status_mask = GEN6_GT_THREAD_STATUS_CORE_MASK;
+
+	/* w/a for a sporadic read returning 0 by waiting for the GT
+	 * thread to wake up.
+	 */
+	if (wait_for_atomic_us((__raw_i915_read32(dev_priv, GEN6_GT_THREAD_STATUS_REG) & gt_thread_status_mask) == 0, 500))
+		DRM_ERROR("GT thread status wait timed out\n");
+}
+
+static void __gen6_gt_force_wake_reset(struct drm_i915_private *dev_priv)
+{
+	__raw_i915_write32(dev_priv, FORCEWAKE, 0);
+	/* something from same cacheline, but !FORCEWAKE */
+	__raw_posting_read(dev_priv, ECOBUS);
+}
+
+static void __gen6_gt_force_wake_get(struct drm_i915_private *dev_priv)
+{
+	if (wait_for_atomic((__raw_i915_read32(dev_priv, FORCEWAKE_ACK) & 1) == 0,
+			    FORCEWAKE_ACK_TIMEOUT_MS))
+		DRM_ERROR("Timed out waiting for forcewake old ack to clear.\n");
+
+	__raw_i915_write32(dev_priv, FORCEWAKE, 1);
+	/* something from same cacheline, but !FORCEWAKE */
+	__raw_posting_read(dev_priv, ECOBUS);
+
+	if (wait_for_atomic((__raw_i915_read32(dev_priv, FORCEWAKE_ACK) & 1),
+			    FORCEWAKE_ACK_TIMEOUT_MS))
+		DRM_ERROR("Timed out waiting for forcewake to ack request.\n");
+
+	/* WaRsForcewakeWaitTC0:snb */
+	__gen6_gt_wait_for_thread_c0(dev_priv);
+}
+
+static void __gen6_gt_force_wake_mt_reset(struct drm_i915_private *dev_priv)
+{
+	__raw_i915_write32(dev_priv, FORCEWAKE_MT, _MASKED_BIT_DISABLE(0xffff));
+	/* something from same cacheline, but !FORCEWAKE_MT */
+	__raw_posting_read(dev_priv, ECOBUS);
+}
+
+static void __gen6_gt_force_wake_mt_get(struct drm_i915_private *dev_priv)
+{
+	u32 forcewake_ack;
+
+	if (IS_HASWELL(dev_priv->dev))
+		forcewake_ack = FORCEWAKE_ACK_HSW;
+	else
+		forcewake_ack = FORCEWAKE_MT_ACK;
+
+	if (wait_for_atomic((__raw_i915_read32(dev_priv, forcewake_ack) & FORCEWAKE_KERNEL) == 0,
+			    FORCEWAKE_ACK_TIMEOUT_MS))
+		DRM_ERROR("Timed out waiting for forcewake old ack to clear.\n");
+
+	__raw_i915_write32(dev_priv, FORCEWAKE_MT,
+			   _MASKED_BIT_ENABLE(FORCEWAKE_KERNEL));
+	/* something from same cacheline, but !FORCEWAKE_MT */
+	__raw_posting_read(dev_priv, ECOBUS);
+
+	if (wait_for_atomic((__raw_i915_read32(dev_priv, forcewake_ack) & FORCEWAKE_KERNEL),
+			    FORCEWAKE_ACK_TIMEOUT_MS))
+		DRM_ERROR("Timed out waiting for forcewake to ack request.\n");
+
+	/* WaRsForcewakeWaitTC0:ivb,hsw */
+	__gen6_gt_wait_for_thread_c0(dev_priv);
+}
+
+static void gen6_gt_check_fifodbg(struct drm_i915_private *dev_priv)
+{
+	u32 gtfifodbg;
+
+	gtfifodbg = __raw_i915_read32(dev_priv, GTFIFODBG);
+	if (WARN(gtfifodbg & GT_FIFO_CPU_ERROR_MASK,
+	     "MMIO read or write has been dropped %x\n", gtfifodbg))
+		__raw_i915_write32(dev_priv, GTFIFODBG, GT_FIFO_CPU_ERROR_MASK);
+}
+
+static void __gen6_gt_force_wake_put(struct drm_i915_private *dev_priv)
+{
+	__raw_i915_write32(dev_priv, FORCEWAKE, 0);
+	/* something from same cacheline, but !FORCEWAKE */
+	__raw_posting_read(dev_priv, ECOBUS);
+	gen6_gt_check_fifodbg(dev_priv);
+}
+
+static void __gen6_gt_force_wake_mt_put(struct drm_i915_private *dev_priv)
+{
+	__raw_i915_write32(dev_priv, FORCEWAKE_MT,
+			   _MASKED_BIT_DISABLE(FORCEWAKE_KERNEL));
+	/* something from same cacheline, but !FORCEWAKE_MT */
+	__raw_posting_read(dev_priv, ECOBUS);
+	gen6_gt_check_fifodbg(dev_priv);
+}
+
+static int __gen6_gt_wait_for_fifo(struct drm_i915_private *dev_priv)
+{
+	int ret = 0;
+
+	if (dev_priv->uncore.fifo_count < GT_FIFO_NUM_RESERVED_ENTRIES) {
+		int loop = 500;
+		u32 fifo = __raw_i915_read32(dev_priv, GT_FIFO_FREE_ENTRIES);
+		while (fifo <= GT_FIFO_NUM_RESERVED_ENTRIES && loop--) {
+			udelay(10);
+			fifo = __raw_i915_read32(dev_priv, GT_FIFO_FREE_ENTRIES);
+		}
+		if (WARN_ON(loop < 0 && fifo <= GT_FIFO_NUM_RESERVED_ENTRIES))
+			++ret;
+		dev_priv->uncore.fifo_count = fifo;
+	}
+	dev_priv->uncore.fifo_count--;
+
+	return ret;
+}
+
+static void vlv_force_wake_reset(struct drm_i915_private *dev_priv)
+{
+	__raw_i915_write32(dev_priv, FORCEWAKE_VLV,
+			   _MASKED_BIT_DISABLE(0xffff));
+	/* something from same cacheline, but !FORCEWAKE_VLV */
+	__raw_posting_read(dev_priv, FORCEWAKE_ACK_VLV);
+}
+
+static void vlv_force_wake_get(struct drm_i915_private *dev_priv)
+{
+	if (wait_for_atomic((__raw_i915_read32(dev_priv, FORCEWAKE_ACK_VLV) & FORCEWAKE_KERNEL) == 0,
+			    FORCEWAKE_ACK_TIMEOUT_MS))
+		DRM_ERROR("Timed out waiting for forcewake old ack to clear.\n");
+
+	__raw_i915_write32(dev_priv, FORCEWAKE_VLV,
+			   _MASKED_BIT_ENABLE(FORCEWAKE_KERNEL));
+	__raw_i915_write32(dev_priv, FORCEWAKE_MEDIA_VLV,
+			   _MASKED_BIT_ENABLE(FORCEWAKE_KERNEL));
+
+	if (wait_for_atomic((__raw_i915_read32(dev_priv, FORCEWAKE_ACK_VLV) & FORCEWAKE_KERNEL),
+			    FORCEWAKE_ACK_TIMEOUT_MS))
+		DRM_ERROR("Timed out waiting for GT to ack forcewake request.\n");
+
+	if (wait_for_atomic((__raw_i915_read32(dev_priv, FORCEWAKE_ACK_MEDIA_VLV) &
+			     FORCEWAKE_KERNEL),
+			    FORCEWAKE_ACK_TIMEOUT_MS))
+		DRM_ERROR("Timed out waiting for media to ack forcewake request.\n");
+
+	/* WaRsForcewakeWaitTC0:vlv */
+	__gen6_gt_wait_for_thread_c0(dev_priv);
+}
+
+static void vlv_force_wake_put(struct drm_i915_private *dev_priv)
+{
+	__raw_i915_write32(dev_priv, FORCEWAKE_VLV,
+			   _MASKED_BIT_DISABLE(FORCEWAKE_KERNEL));
+	__raw_i915_write32(dev_priv, FORCEWAKE_MEDIA_VLV,
+			   _MASKED_BIT_DISABLE(FORCEWAKE_KERNEL));
+	/* The below doubles as a POSTING_READ */
+	gen6_gt_check_fifodbg(dev_priv);
+}
+
+void intel_uncore_early_sanitize(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	if (HAS_FPGA_DBG_UNCLAIMED(dev))
+		__raw_i915_write32(dev_priv, FPGA_DBG, FPGA_DBG_RM_NOCLAIM);
+}
+
+void intel_uncore_init(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	if (IS_VALLEYVIEW(dev)) {
+		dev_priv->uncore.funcs.force_wake_get = vlv_force_wake_get;
+		dev_priv->uncore.funcs.force_wake_put = vlv_force_wake_put;
+	} else if (IS_HASWELL(dev)) {
+		dev_priv->uncore.funcs.force_wake_get = __gen6_gt_force_wake_mt_get;
+		dev_priv->uncore.funcs.force_wake_put = __gen6_gt_force_wake_mt_put;
+	} else if (IS_IVYBRIDGE(dev)) {
+		u32 ecobus;
+
+		/* IVB configs may use multi-threaded forcewake */
+
+		/* A small trick here - if the bios hasn't configured
+		 * MT forcewake, and if the device is in RC6, then
+		 * force_wake_mt_get will not wake the device and the
+		 * ECOBUS read will return zero. Which will be
+		 * (correctly) interpreted by the test below as MT
+		 * forcewake being disabled.
+		 */
+		mutex_lock(&dev->struct_mutex);
+		__gen6_gt_force_wake_mt_get(dev_priv);
+		ecobus = __raw_i915_read32(dev_priv, ECOBUS);
+		__gen6_gt_force_wake_mt_put(dev_priv);
+		mutex_unlock(&dev->struct_mutex);
+
+		if (ecobus & FORCEWAKE_MT_ENABLE) {
+			dev_priv->uncore.funcs.force_wake_get =
+				__gen6_gt_force_wake_mt_get;
+			dev_priv->uncore.funcs.force_wake_put =
+				__gen6_gt_force_wake_mt_put;
+		} else {
+			DRM_INFO("No MT forcewake available on Ivybridge, this can result in issues\n");
+			DRM_INFO("when using vblank-synced partial screen updates.\n");
+			dev_priv->uncore.funcs.force_wake_get =
+				__gen6_gt_force_wake_get;
+			dev_priv->uncore.funcs.force_wake_put =
+				__gen6_gt_force_wake_put;
+		}
+	} else if (IS_GEN6(dev)) {
+		dev_priv->uncore.funcs.force_wake_get =
+			__gen6_gt_force_wake_get;
+		dev_priv->uncore.funcs.force_wake_put =
+			__gen6_gt_force_wake_put;
+	}
+}
+
+static void intel_uncore_forcewake_reset(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	if (IS_VALLEYVIEW(dev)) {
+		vlv_force_wake_reset(dev_priv);
+	} else if (INTEL_INFO(dev)->gen >= 6) {
+		__gen6_gt_force_wake_reset(dev_priv);
+		if (IS_IVYBRIDGE(dev) || IS_HASWELL(dev))
+			__gen6_gt_force_wake_mt_reset(dev_priv);
+	}
+}
+
+void intel_uncore_sanitize(struct drm_device *dev)
+{
+	intel_uncore_forcewake_reset(dev);
+
+	/* BIOS often leaves RC6 enabled, but disable it for hw init */
+	intel_disable_gt_powersave(dev);
+}
+
+/*
+ * Generally this is called implicitly by the register read function. However,
+ * if some sequence requires the GT to not power down then this function should
+ * be called at the beginning of the sequence followed by a call to
+ * gen6_gt_force_wake_put() at the end of the sequence.
+ */
+void gen6_gt_force_wake_get(struct drm_i915_private *dev_priv)
+{
+	unsigned long irqflags;
+
+	spin_lock_irqsave(&dev_priv->uncore.lock, irqflags);
+	if (dev_priv->uncore.forcewake_count++ == 0)
+		dev_priv->uncore.funcs.force_wake_get(dev_priv);
+	spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags);
+}
+
+/*
+ * see gen6_gt_force_wake_get()
+ */
+void gen6_gt_force_wake_put(struct drm_i915_private *dev_priv)
+{
+	unsigned long irqflags;
+
+	spin_lock_irqsave(&dev_priv->uncore.lock, irqflags);
+	if (--dev_priv->uncore.forcewake_count == 0)
+		dev_priv->uncore.funcs.force_wake_put(dev_priv);
+	spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags);
+}
+
+/* We give fast paths for the really cool registers */
+#define NEEDS_FORCE_WAKE(dev_priv, reg) \
+	((HAS_FORCE_WAKE((dev_priv)->dev)) && \
+	 ((reg) < 0x40000) &&            \
+	 ((reg) != FORCEWAKE))
+
+static void
+ilk_dummy_write(struct drm_i915_private *dev_priv)
+{
+	/* WaIssueDummyWriteToWakeupFromRC6:ilk Issue a dummy write to wake up
+	 * the chip from rc6 before touching it for real. MI_MODE is masked,
+	 * hence harmless to write 0 into. */
+	__raw_i915_write32(dev_priv, MI_MODE, 0);
+}
+
+static void
+hsw_unclaimed_reg_clear(struct drm_i915_private *dev_priv, u32 reg)
+{
+	if (HAS_FPGA_DBG_UNCLAIMED(dev_priv->dev) &&
+	    (__raw_i915_read32(dev_priv, FPGA_DBG) & FPGA_DBG_RM_NOCLAIM)) {
+		DRM_ERROR("Unknown unclaimed register before writing to %x\n",
+			  reg);
+		__raw_i915_write32(dev_priv, FPGA_DBG, FPGA_DBG_RM_NOCLAIM);
+	}
+}
+
+static void
+hsw_unclaimed_reg_check(struct drm_i915_private *dev_priv, u32 reg)
+{
+	if (HAS_FPGA_DBG_UNCLAIMED(dev_priv->dev) &&
+	    (__raw_i915_read32(dev_priv, FPGA_DBG) & FPGA_DBG_RM_NOCLAIM)) {
+		DRM_ERROR("Unclaimed write to %x\n", reg);
+		__raw_i915_write32(dev_priv, FPGA_DBG, FPGA_DBG_RM_NOCLAIM);
+	}
+}
+
+#define __i915_read(x) \
+u##x i915_read##x(struct drm_i915_private *dev_priv, u32 reg, bool trace) { \
+	unsigned long irqflags; \
+	u##x val = 0; \
+	spin_lock_irqsave(&dev_priv->uncore.lock, irqflags); \
+	if (dev_priv->info->gen == 5) \
+		ilk_dummy_write(dev_priv); \
+	if (NEEDS_FORCE_WAKE((dev_priv), (reg))) { \
+		if (dev_priv->uncore.forcewake_count == 0) \
+			dev_priv->uncore.funcs.force_wake_get(dev_priv); \
+		val = __raw_i915_read##x(dev_priv, reg); \
+		if (dev_priv->uncore.forcewake_count == 0) \
+			dev_priv->uncore.funcs.force_wake_put(dev_priv); \
+	} else { \
+		val = __raw_i915_read##x(dev_priv, reg); \
+	} \
+	spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags); \
+	trace_i915_reg_rw(false, reg, val, sizeof(val), trace); \
+	return val; \
+}
+
+__i915_read(8)
+__i915_read(16)
+__i915_read(32)
+__i915_read(64)
+#undef __i915_read
+
+#define __i915_write(x) \
+void i915_write##x(struct drm_i915_private *dev_priv, u32 reg, u##x val, bool trace) { \
+	unsigned long irqflags; \
+	u32 __fifo_ret = 0; \
+	trace_i915_reg_rw(true, reg, val, sizeof(val), trace); \
+	spin_lock_irqsave(&dev_priv->uncore.lock, irqflags); \
+	if (NEEDS_FORCE_WAKE((dev_priv), (reg))) { \
+		__fifo_ret = __gen6_gt_wait_for_fifo(dev_priv); \
+	} \
+	if (dev_priv->info->gen == 5) \
+		ilk_dummy_write(dev_priv); \
+	hsw_unclaimed_reg_clear(dev_priv, reg); \
+	__raw_i915_write##x(dev_priv, reg, val); \
+	if (unlikely(__fifo_ret)) { \
+		gen6_gt_check_fifodbg(dev_priv); \
+	} \
+	hsw_unclaimed_reg_check(dev_priv, reg); \
+	spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags); \
+}
+__i915_write(8)
+__i915_write(16)
+__i915_write(32)
+__i915_write(64)
+#undef __i915_write
+
+static const struct register_whitelist {
+	uint64_t offset;
+	uint32_t size;
+	uint32_t gen_bitmask; /* support gens, 0x10 for 4, 0x30 for 4 and 5, etc. */
+} whitelist[] = {
+	{ RING_TIMESTAMP(RENDER_RING_BASE), 8, 0xF0 },
+};
+
+int i915_reg_read_ioctl(struct drm_device *dev,
+			void *data, struct drm_file *file)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_reg_read *reg = data;
+	struct register_whitelist const *entry = whitelist;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(whitelist); i++, entry++) {
+		if (entry->offset == reg->offset &&
+		    (1 << INTEL_INFO(dev)->gen & entry->gen_bitmask))
+			break;
+	}
+
+	if (i == ARRAY_SIZE(whitelist))
+		return -EINVAL;
+
+	switch (entry->size) {
+	case 8:
+		reg->val = I915_READ64(reg->offset);
+		break;
+	case 4:
+		reg->val = I915_READ(reg->offset);
+		break;
+	case 2:
+		reg->val = I915_READ16(reg->offset);
+		break;
+	case 1:
+		reg->val = I915_READ8(reg->offset);
+		break;
+	default:
+		WARN_ON(1);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int i8xx_do_reset(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	if (IS_I85X(dev))
+		return -ENODEV;
+
+	I915_WRITE(D_STATE, I915_READ(D_STATE) | DSTATE_GFX_RESET_I830);
+	POSTING_READ(D_STATE);
+
+	if (IS_I830(dev) || IS_845G(dev)) {
+		I915_WRITE(DEBUG_RESET_I830,
+			   DEBUG_RESET_DISPLAY |
+			   DEBUG_RESET_RENDER |
+			   DEBUG_RESET_FULL);
+		POSTING_READ(DEBUG_RESET_I830);
+		msleep(1);
+
+		I915_WRITE(DEBUG_RESET_I830, 0);
+		POSTING_READ(DEBUG_RESET_I830);
+	}
+
+	msleep(1);
+
+	I915_WRITE(D_STATE, I915_READ(D_STATE) & ~DSTATE_GFX_RESET_I830);
+	POSTING_READ(D_STATE);
+
+	return 0;
+}
+
+static int i965_reset_complete(struct drm_device *dev)
+{
+	u8 gdrst;
+	pci_read_config_byte(dev->pdev, I965_GDRST, &gdrst);
+	return (gdrst & GRDOM_RESET_ENABLE) == 0;
+}
+
+static int i965_do_reset(struct drm_device *dev)
+{
+	int ret;
+
+	/*
+	 * Set the domains we want to reset (GRDOM/bits 2 and 3) as
+	 * well as the reset bit (GR/bit 0).  Setting the GR bit
+	 * triggers the reset; when done, the hardware will clear it.
+	 */
+	pci_write_config_byte(dev->pdev, I965_GDRST,
+			      GRDOM_RENDER | GRDOM_RESET_ENABLE);
+	ret =  wait_for(i965_reset_complete(dev), 500);
+	if (ret)
+		return ret;
+
+	/* We can't reset render&media without also resetting display ... */
+	pci_write_config_byte(dev->pdev, I965_GDRST,
+			      GRDOM_MEDIA | GRDOM_RESET_ENABLE);
+
+	ret =  wait_for(i965_reset_complete(dev), 500);
+	if (ret)
+		return ret;
+
+	pci_write_config_byte(dev->pdev, I965_GDRST, 0);
+
+	return 0;
+}
+
+static int ironlake_do_reset(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	u32 gdrst;
+	int ret;
+
+	gdrst = I915_READ(MCHBAR_MIRROR_BASE + ILK_GDSR);
+	gdrst &= ~GRDOM_MASK;
+	I915_WRITE(MCHBAR_MIRROR_BASE + ILK_GDSR,
+		   gdrst | GRDOM_RENDER | GRDOM_RESET_ENABLE);
+	ret = wait_for(I915_READ(MCHBAR_MIRROR_BASE + ILK_GDSR) & 0x1, 500);
+	if (ret)
+		return ret;
+
+	/* We can't reset render&media without also resetting display ... */
+	gdrst = I915_READ(MCHBAR_MIRROR_BASE + ILK_GDSR);
+	gdrst &= ~GRDOM_MASK;
+	I915_WRITE(MCHBAR_MIRROR_BASE + ILK_GDSR,
+		   gdrst | GRDOM_MEDIA | GRDOM_RESET_ENABLE);
+	return wait_for(I915_READ(MCHBAR_MIRROR_BASE + ILK_GDSR) & 0x1, 500);
+}
+
+static int gen6_do_reset(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	int	ret;
+	unsigned long irqflags;
+
+	/* Hold uncore.lock across reset to prevent any register access
+	 * with forcewake not set correctly
+	 */
+	spin_lock_irqsave(&dev_priv->uncore.lock, irqflags);
+
+	/* Reset the chip */
+
+	/* GEN6_GDRST is not in the gt power well, no need to check
+	 * for fifo space for the write or forcewake the chip for
+	 * the read
+	 */
+	__raw_i915_write32(dev_priv, GEN6_GDRST, GEN6_GRDOM_FULL);
+
+	/* Spin waiting for the device to ack the reset request */
+	ret = wait_for((__raw_i915_read32(dev_priv, GEN6_GDRST) & GEN6_GRDOM_FULL) == 0, 500);
+
+	intel_uncore_forcewake_reset(dev);
+
+	/* If reset with a user forcewake, try to restore, otherwise turn it off */
+	if (dev_priv->uncore.forcewake_count)
+		dev_priv->uncore.funcs.force_wake_get(dev_priv);
+	else
+		dev_priv->uncore.funcs.force_wake_put(dev_priv);
+
+	/* Restore fifo count */
+	dev_priv->uncore.fifo_count = __raw_i915_read32(dev_priv, GT_FIFO_FREE_ENTRIES);
+
+	spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags);
+	return ret;
+}
+
+int intel_gpu_reset(struct drm_device *dev)
+{
+	switch (INTEL_INFO(dev)->gen) {
+	case 7:
+	case 6: return gen6_do_reset(dev);
+	case 5: return ironlake_do_reset(dev);
+	case 4: return i965_do_reset(dev);
+	case 2: return i8xx_do_reset(dev);
+	default: return -ENODEV;
+	}
+}
+
+void intel_uncore_clear_errors(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	/* XXX needs spinlock around caller's grouping */
+	if (HAS_FPGA_DBG_UNCLAIMED(dev))
+		__raw_i915_write32(dev_priv, FPGA_DBG, FPGA_DBG_RM_NOCLAIM);
+}
+
+void intel_uncore_check_errors(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	if (HAS_FPGA_DBG_UNCLAIMED(dev) &&
+	    (__raw_i915_read32(dev_priv, FPGA_DBG) & FPGA_DBG_RM_NOCLAIM)) {
+		DRM_ERROR("Unclaimed register before interrupt\n");
+		__raw_i915_write32(dev_priv, FPGA_DBG, FPGA_DBG_RM_NOCLAIM);
+	}
+}
diff --git a/drivers/gpu/drm/mga/mga_drv.c b/drivers/gpu/drm/mga/mga_drv.c
index 17d0a637e4fb..6b1a87c8aac5 100644
--- a/drivers/gpu/drm/mga/mga_drv.c
+++ b/drivers/gpu/drm/mga/mga_drv.c
@@ -50,7 +50,6 @@ static const struct file_operations mga_driver_fops = {
 	.unlocked_ioctl = drm_ioctl,
 	.mmap = drm_mmap,
 	.poll = drm_poll,
-	.fasync = drm_fasync,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl = mga_compat_ioctl,
 #endif
@@ -59,7 +58,7 @@ static const struct file_operations mga_driver_fops = {
 
 static struct drm_driver driver = {
 	.driver_features =
-	    DRIVER_USE_AGP | DRIVER_USE_MTRR | DRIVER_PCI_DMA |
+	    DRIVER_USE_AGP | DRIVER_PCI_DMA |
 	    DRIVER_HAVE_DMA | DRIVER_HAVE_IRQ | DRIVER_IRQ_SHARED,
 	.dev_priv_size = sizeof(drm_mga_buf_priv_t),
 	.load = mga_driver_load,
diff --git a/drivers/gpu/drm/mga/mga_drv.h b/drivers/gpu/drm/mga/mga_drv.h
index 54558a01969a..ca4bc54ea214 100644
--- a/drivers/gpu/drm/mga/mga_drv.h
+++ b/drivers/gpu/drm/mga/mga_drv.h
@@ -149,7 +149,7 @@ typedef struct drm_mga_private {
 	unsigned int agp_size;
 } drm_mga_private_t;
 
-extern struct drm_ioctl_desc mga_ioctls[];
+extern const struct drm_ioctl_desc mga_ioctls[];
 extern int mga_max_ioctl;
 
 				/* mga_dma.c */
diff --git a/drivers/gpu/drm/mga/mga_state.c b/drivers/gpu/drm/mga/mga_state.c
index 9c145143ad0f..37cc2fb4eadd 100644
--- a/drivers/gpu/drm/mga/mga_state.c
+++ b/drivers/gpu/drm/mga/mga_state.c
@@ -1083,7 +1083,7 @@ file_priv)
 	return 0;
 }
 
-struct drm_ioctl_desc mga_ioctls[] = {
+const struct drm_ioctl_desc mga_ioctls[] = {
 	DRM_IOCTL_DEF_DRV(MGA_INIT, mga_dma_init, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
 	DRM_IOCTL_DEF_DRV(MGA_FLUSH, mga_dma_flush, DRM_AUTH),
 	DRM_IOCTL_DEF_DRV(MGA_RESET, mga_dma_reset, DRM_AUTH),
diff --git a/drivers/gpu/drm/mgag200/mgag200_drv.c b/drivers/gpu/drm/mgag200/mgag200_drv.c
index 122b571ccc7c..fcce7b2f8011 100644
--- a/drivers/gpu/drm/mgag200/mgag200_drv.c
+++ b/drivers/gpu/drm/mgag200/mgag200_drv.c
@@ -81,7 +81,6 @@ static const struct file_operations mgag200_driver_fops = {
 	.unlocked_ioctl = drm_ioctl,
 	.mmap = mgag200_mmap,
 	.poll = drm_poll,
-	.fasync = drm_fasync,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl = drm_compat_ioctl,
 #endif
@@ -89,7 +88,7 @@ static const struct file_operations mgag200_driver_fops = {
 };
 
 static struct drm_driver driver = {
-	.driver_features = DRIVER_GEM | DRIVER_MODESET | DRIVER_USE_MTRR,
+	.driver_features = DRIVER_GEM | DRIVER_MODESET,
 	.load = mgag200_driver_load,
 	.unload = mgag200_driver_unload,
 	.fops = &mgag200_driver_fops,
@@ -104,7 +103,7 @@ static struct drm_driver driver = {
 	.gem_free_object = mgag200_gem_free_object,
 	.dumb_create = mgag200_dumb_create,
 	.dumb_map_offset = mgag200_dumb_mmap_offset,
-	.dumb_destroy = mgag200_dumb_destroy,
+	.dumb_destroy = drm_gem_dumb_destroy,
 };
 
 static struct pci_driver mgag200_pci_driver = {
diff --git a/drivers/gpu/drm/mgag200/mgag200_drv.h b/drivers/gpu/drm/mgag200/mgag200_drv.h
index 12e2499d9352..baaae19332e2 100644
--- a/drivers/gpu/drm/mgag200/mgag200_drv.h
+++ b/drivers/gpu/drm/mgag200/mgag200_drv.h
@@ -264,9 +264,6 @@ int mgag200_gem_init_object(struct drm_gem_object *obj);
 int mgag200_dumb_create(struct drm_file *file,
 			struct drm_device *dev,
 			struct drm_mode_create_dumb *args);
-int mgag200_dumb_destroy(struct drm_file *file,
-			 struct drm_device *dev,
-			 uint32_t handle);
 void mgag200_gem_free_object(struct drm_gem_object *obj);
 int
 mgag200_dumb_mmap_offset(struct drm_file *file,
diff --git a/drivers/gpu/drm/mgag200/mgag200_main.c b/drivers/gpu/drm/mgag200/mgag200_main.c
index 9fa5685baee0..0f8b861b10b3 100644
--- a/drivers/gpu/drm/mgag200/mgag200_main.c
+++ b/drivers/gpu/drm/mgag200/mgag200_main.c
@@ -310,13 +310,6 @@ int mgag200_dumb_create(struct drm_file *file,
 	return 0;
 }
 
-int mgag200_dumb_destroy(struct drm_file *file,
-		     struct drm_device *dev,
-		     uint32_t handle)
-{
-	return drm_gem_handle_delete(file, handle);
-}
-
 int mgag200_gem_init_object(struct drm_gem_object *obj)
 {
 	BUG();
@@ -349,7 +342,7 @@ void mgag200_gem_free_object(struct drm_gem_object *obj)
 
 static inline u64 mgag200_bo_mmap_offset(struct mgag200_bo *bo)
 {
-	return bo->bo.addr_space_offset;
+	return drm_vma_node_offset_addr(&bo->bo.vma_node);
 }
 
 int
diff --git a/drivers/gpu/drm/mgag200/mgag200_ttm.c b/drivers/gpu/drm/mgag200/mgag200_ttm.c
index d70e4a92773b..07b192fe15c6 100644
--- a/drivers/gpu/drm/mgag200/mgag200_ttm.c
+++ b/drivers/gpu/drm/mgag200/mgag200_ttm.c
@@ -148,7 +148,9 @@ mgag200_bo_evict_flags(struct ttm_buffer_object *bo, struct ttm_placement *pl)
 
 static int mgag200_bo_verify_access(struct ttm_buffer_object *bo, struct file *filp)
 {
-	return 0;
+	struct mgag200_bo *mgabo = mgag200_bo(bo);
+
+	return drm_vma_node_verify_access(&mgabo->gem.vma_node, filp);
 }
 
 static int mgag200_ttm_io_mem_reserve(struct ttm_bo_device *bdev,
@@ -321,7 +323,6 @@ int mgag200_bo_create(struct drm_device *dev, int size, int align,
 		return ret;
 	}
 
-	mgabo->gem.driver_private = NULL;
 	mgabo->bo.bdev = &mdev->ttm.bdev;
 	mgabo->bo.bdev->dev_mapping = dev->dev_mapping;
 
diff --git a/drivers/gpu/drm/msm/Kconfig b/drivers/gpu/drm/msm/Kconfig
new file mode 100644
index 000000000000..a06c19cc56f8
--- /dev/null
+++ b/drivers/gpu/drm/msm/Kconfig
@@ -0,0 +1,34 @@
+
+config DRM_MSM
+	tristate "MSM DRM"
+	depends on DRM
+	depends on ARCH_MSM
+	depends on ARCH_MSM8960
+	select DRM_KMS_HELPER
+	select SHMEM
+	select TMPFS
+	default y
+	help
+	  DRM/KMS driver for MSM/snapdragon.
+
+config DRM_MSM_FBDEV
+	bool "Enable legacy fbdev support for MSM modesetting driver"
+	depends on DRM_MSM
+	select FB_SYS_FILLRECT
+	select FB_SYS_COPYAREA
+	select FB_SYS_IMAGEBLIT
+	select FB_SYS_FOPS
+	default y
+	help
+	  Choose this option if you have a need for the legacy fbdev
+	  support. Note that this support also provide the linux console
+	  support on top of the MSM modesetting driver.
+
+config DRM_MSM_REGISTER_LOGGING
+	bool "MSM DRM register logging"
+	depends on DRM_MSM
+	default n
+	help
+	  Compile in support for logging register reads/writes in a format
+	  that can be parsed by envytools demsm tool.  If enabled, register
+	  logging can be switched on via msm.reglog=y module param.
diff --git a/drivers/gpu/drm/msm/Makefile b/drivers/gpu/drm/msm/Makefile
new file mode 100644
index 000000000000..e17914889e54
--- /dev/null
+++ b/drivers/gpu/drm/msm/Makefile
@@ -0,0 +1,30 @@
+ccflags-y := -Iinclude/drm -Idrivers/gpu/drm/msm
+ifeq (, $(findstring -W,$(EXTRA_CFLAGS)))
+	ccflags-y += -Werror
+endif
+
+msm-y := \
+	adreno/adreno_gpu.o \
+	adreno/a3xx_gpu.o \
+	hdmi/hdmi.o \
+	hdmi/hdmi_bridge.o \
+	hdmi/hdmi_connector.o \
+	hdmi/hdmi_i2c.o \
+	hdmi/hdmi_phy_8960.o \
+	hdmi/hdmi_phy_8x60.o \
+	mdp4/mdp4_crtc.o \
+	mdp4/mdp4_dtv_encoder.o \
+	mdp4/mdp4_format.o \
+	mdp4/mdp4_irq.o \
+	mdp4/mdp4_kms.o \
+	mdp4/mdp4_plane.o \
+	msm_drv.o \
+	msm_fb.o \
+	msm_gem.o \
+	msm_gem_submit.o \
+	msm_gpu.o \
+	msm_ringbuffer.o
+
+msm-$(CONFIG_DRM_MSM_FBDEV) += msm_fbdev.o
+
+obj-$(CONFIG_DRM_MSM)	+= msm.o
diff --git a/drivers/gpu/drm/msm/NOTES b/drivers/gpu/drm/msm/NOTES
new file mode 100644
index 000000000000..e036f6c1db94
--- /dev/null
+++ b/drivers/gpu/drm/msm/NOTES
@@ -0,0 +1,69 @@
+NOTES about msm drm/kms driver:
+
+In the current snapdragon SoC's, we have (at least) 3 different
+display controller blocks at play:
+ + MDP3 - ?? seems to be what is on geeksphone peak device
+ + MDP4 - S3 (APQ8060, touchpad), S4-pro (APQ8064, nexus4 & ifc6410)
+ + MDSS - snapdragon 800
+
+(I don't have a completely clear picture on which display controller
+maps to which part #)
+
+Plus a handful of blocks around them for HDMI/DSI/etc output.
+
+And on gpu side of things:
+ + zero, one, or two 2d cores (z180)
+ + and either a2xx or a3xx 3d core.
+
+But, HDMI/DSI/etc blocks seem like they can be shared across multiple
+display controller blocks.  And I for sure don't want to have to deal
+with N different kms devices from xf86-video-freedreno.  Plus, it
+seems like we can do some clever tricks like use GPU to trigger
+pageflip after rendering completes (ie. have the kms/crtc code build
+up gpu cmdstream to update scanout and write FLUSH register after).
+
+So, the approach is one drm driver, with some modularity.  Different
+'struct msm_kms' implementations, depending on display controller.
+And one or more 'struct msm_gpu' for the various different gpu sub-
+modules.
+
+(Second part is not implemented yet.  So far this is just basic KMS
+driver, and not exposing any custom ioctls to userspace for now.)
+
+The kms module provides the plane, crtc, and encoder objects, and
+loads whatever connectors are appropriate.
+
+For MDP4, the mapping is:
+
+  plane   -> PIPE{RGBn,VGn}              \
+  crtc    -> OVLP{n} + DMA{P,S,E} (??)   |-> MDP "device"
+  encoder -> DTV/LCDC/DSI (within MDP4)  /
+  connector -> HDMI/DSI/etc              --> other device(s)
+
+Since the irq's that drm core mostly cares about are vblank/framedone,
+we'll let msm_mdp4_kms provide the irq install/uninstall/etc functions
+and treat the MDP4 block's irq as "the" irq.  Even though the connectors
+may have their own irqs which they install themselves.  For this reason
+the display controller is the "master" device.
+
+Each connector probably ends up being a separate device, just for the
+logistics of finding/mapping io region, irq, etc.  Idealy we would
+have a better way than just stashing the platform device in a global
+(ie. like DT super-node.. but I don't have any snapdragon hw yet that
+is using DT).
+
+Note that so far I've not been able to get any docs on the hw, and it
+seems that access to such docs would prevent me from working on the
+freedreno gallium driver.  So there may be some mistakes in register
+names (I had to invent a few, since no sufficient hint was given in
+the downstream android fbdev driver), bitfield sizes, etc.  My current
+state of understanding the registers is given in the envytools rnndb
+files at:
+
+  https://github.com/freedreno/envytools/tree/master/rnndb
+  (the mdp4/hdmi/dsi directories)
+
+These files are used both for a parser tool (in the same tree) to
+parse logged register reads/writes (both from downstream android fbdev
+driver, and this driver with register logging enabled), as well as to
+generate the register level headers.
diff --git a/drivers/gpu/drm/msm/adreno/a2xx.xml.h b/drivers/gpu/drm/msm/adreno/a2xx.xml.h
new file mode 100644
index 000000000000..35463864b959
--- /dev/null
+++ b/drivers/gpu/drm/msm/adreno/a2xx.xml.h
@@ -0,0 +1,1438 @@
+#ifndef A2XX_XML
+#define A2XX_XML
+
+/* Autogenerated file, DO NOT EDIT manually!
+
+This file was generated by the rules-ng-ng headergen tool in this git repository:
+http://0x04.net/cgit/index.cgi/rules-ng-ng
+git clone git://0x04.net/rules-ng-ng
+
+The rules-ng-ng source files this header was generated from are:
+- /home/robclark/src/freedreno/envytools/rnndb/adreno.xml              (    327 bytes, from 2013-07-05 19:21:12)
+- /home/robclark/src/freedreno/envytools/rnndb/freedreno_copyright.xml (   1453 bytes, from 2013-03-31 16:51:27)
+- /home/robclark/src/freedreno/envytools/rnndb/a2xx/a2xx.xml           (  30005 bytes, from 2013-07-19 21:30:48)
+- /home/robclark/src/freedreno/envytools/rnndb/adreno_common.xml       (   8983 bytes, from 2013-07-24 01:38:36)
+- /home/robclark/src/freedreno/envytools/rnndb/adreno_pm4.xml          (   9712 bytes, from 2013-05-26 15:22:37)
+- /home/robclark/src/freedreno/envytools/rnndb/a3xx/a3xx.xml           (  51415 bytes, from 2013-08-03 14:26:05)
+
+Copyright (C) 2013 by the following authors:
+- Rob Clark <robdclark@gmail.com> (robclark)
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice (including the
+next paragraph) shall be included in all copies or substantial
+portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
+IN NO EVENT SHALL THE COPYRIGHT OWNER(S) AND/OR ITS SUPPLIERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+*/
+
+
+enum a2xx_rb_dither_type {
+	DITHER_PIXEL = 0,
+	DITHER_SUBPIXEL = 1,
+};
+
+enum a2xx_colorformatx {
+	COLORX_4_4_4_4 = 0,
+	COLORX_1_5_5_5 = 1,
+	COLORX_5_6_5 = 2,
+	COLORX_8 = 3,
+	COLORX_8_8 = 4,
+	COLORX_8_8_8_8 = 5,
+	COLORX_S8_8_8_8 = 6,
+	COLORX_16_FLOAT = 7,
+	COLORX_16_16_FLOAT = 8,
+	COLORX_16_16_16_16_FLOAT = 9,
+	COLORX_32_FLOAT = 10,
+	COLORX_32_32_FLOAT = 11,
+	COLORX_32_32_32_32_FLOAT = 12,
+	COLORX_2_3_3 = 13,
+	COLORX_8_8_8 = 14,
+};
+
+enum a2xx_sq_surfaceformat {
+	FMT_1_REVERSE = 0,
+	FMT_1 = 1,
+	FMT_8 = 2,
+	FMT_1_5_5_5 = 3,
+	FMT_5_6_5 = 4,
+	FMT_6_5_5 = 5,
+	FMT_8_8_8_8 = 6,
+	FMT_2_10_10_10 = 7,
+	FMT_8_A = 8,
+	FMT_8_B = 9,
+	FMT_8_8 = 10,
+	FMT_Cr_Y1_Cb_Y0 = 11,
+	FMT_Y1_Cr_Y0_Cb = 12,
+	FMT_5_5_5_1 = 13,
+	FMT_8_8_8_8_A = 14,
+	FMT_4_4_4_4 = 15,
+	FMT_10_11_11 = 16,
+	FMT_11_11_10 = 17,
+	FMT_DXT1 = 18,
+	FMT_DXT2_3 = 19,
+	FMT_DXT4_5 = 20,
+	FMT_24_8 = 22,
+	FMT_24_8_FLOAT = 23,
+	FMT_16 = 24,
+	FMT_16_16 = 25,
+	FMT_16_16_16_16 = 26,
+	FMT_16_EXPAND = 27,
+	FMT_16_16_EXPAND = 28,
+	FMT_16_16_16_16_EXPAND = 29,
+	FMT_16_FLOAT = 30,
+	FMT_16_16_FLOAT = 31,
+	FMT_16_16_16_16_FLOAT = 32,
+	FMT_32 = 33,
+	FMT_32_32 = 34,
+	FMT_32_32_32_32 = 35,
+	FMT_32_FLOAT = 36,
+	FMT_32_32_FLOAT = 37,
+	FMT_32_32_32_32_FLOAT = 38,
+	FMT_32_AS_8 = 39,
+	FMT_32_AS_8_8 = 40,
+	FMT_16_MPEG = 41,
+	FMT_16_16_MPEG = 42,
+	FMT_8_INTERLACED = 43,
+	FMT_32_AS_8_INTERLACED = 44,
+	FMT_32_AS_8_8_INTERLACED = 45,
+	FMT_16_INTERLACED = 46,
+	FMT_16_MPEG_INTERLACED = 47,
+	FMT_16_16_MPEG_INTERLACED = 48,
+	FMT_DXN = 49,
+	FMT_8_8_8_8_AS_16_16_16_16 = 50,
+	FMT_DXT1_AS_16_16_16_16 = 51,
+	FMT_DXT2_3_AS_16_16_16_16 = 52,
+	FMT_DXT4_5_AS_16_16_16_16 = 53,
+	FMT_2_10_10_10_AS_16_16_16_16 = 54,
+	FMT_10_11_11_AS_16_16_16_16 = 55,
+	FMT_11_11_10_AS_16_16_16_16 = 56,
+	FMT_32_32_32_FLOAT = 57,
+	FMT_DXT3A = 58,
+	FMT_DXT5A = 59,
+	FMT_CTX1 = 60,
+	FMT_DXT3A_AS_1_1_1_1 = 61,
+};
+
+enum a2xx_sq_ps_vtx_mode {
+	POSITION_1_VECTOR = 0,
+	POSITION_2_VECTORS_UNUSED = 1,
+	POSITION_2_VECTORS_SPRITE = 2,
+	POSITION_2_VECTORS_EDGE = 3,
+	POSITION_2_VECTORS_KILL = 4,
+	POSITION_2_VECTORS_SPRITE_KILL = 5,
+	POSITION_2_VECTORS_EDGE_KILL = 6,
+	MULTIPASS = 7,
+};
+
+enum a2xx_sq_sample_cntl {
+	CENTROIDS_ONLY = 0,
+	CENTERS_ONLY = 1,
+	CENTROIDS_AND_CENTERS = 2,
+};
+
+enum a2xx_dx_clip_space {
+	DXCLIP_OPENGL = 0,
+	DXCLIP_DIRECTX = 1,
+};
+
+enum a2xx_pa_su_sc_polymode {
+	POLY_DISABLED = 0,
+	POLY_DUALMODE = 1,
+};
+
+enum a2xx_rb_edram_mode {
+	EDRAM_NOP = 0,
+	COLOR_DEPTH = 4,
+	DEPTH_ONLY = 5,
+	EDRAM_COPY = 6,
+};
+
+enum a2xx_pa_sc_pattern_bit_order {
+	LITTLE = 0,
+	BIG = 1,
+};
+
+enum a2xx_pa_sc_auto_reset_cntl {
+	NEVER = 0,
+	EACH_PRIMITIVE = 1,
+	EACH_PACKET = 2,
+};
+
+enum a2xx_pa_pixcenter {
+	PIXCENTER_D3D = 0,
+	PIXCENTER_OGL = 1,
+};
+
+enum a2xx_pa_roundmode {
+	TRUNCATE = 0,
+	ROUND = 1,
+	ROUNDTOEVEN = 2,
+	ROUNDTOODD = 3,
+};
+
+enum a2xx_pa_quantmode {
+	ONE_SIXTEENTH = 0,
+	ONE_EIGTH = 1,
+	ONE_QUARTER = 2,
+	ONE_HALF = 3,
+	ONE = 4,
+};
+
+enum a2xx_rb_copy_sample_select {
+	SAMPLE_0 = 0,
+	SAMPLE_1 = 1,
+	SAMPLE_2 = 2,
+	SAMPLE_3 = 3,
+	SAMPLE_01 = 4,
+	SAMPLE_23 = 5,
+	SAMPLE_0123 = 6,
+};
+
+enum sq_tex_clamp {
+	SQ_TEX_WRAP = 0,
+	SQ_TEX_MIRROR = 1,
+	SQ_TEX_CLAMP_LAST_TEXEL = 2,
+	SQ_TEX_MIRROR_ONCE_LAST_TEXEL = 3,
+	SQ_TEX_CLAMP_HALF_BORDER = 4,
+	SQ_TEX_MIRROR_ONCE_HALF_BORDER = 5,
+	SQ_TEX_CLAMP_BORDER = 6,
+	SQ_TEX_MIRROR_ONCE_BORDER = 7,
+};
+
+enum sq_tex_swiz {
+	SQ_TEX_X = 0,
+	SQ_TEX_Y = 1,
+	SQ_TEX_Z = 2,
+	SQ_TEX_W = 3,
+	SQ_TEX_ZERO = 4,
+	SQ_TEX_ONE = 5,
+};
+
+enum sq_tex_filter {
+	SQ_TEX_FILTER_POINT = 0,
+	SQ_TEX_FILTER_BILINEAR = 1,
+	SQ_TEX_FILTER_BICUBIC = 2,
+};
+
+#define REG_A2XX_RBBM_PATCH_RELEASE				0x00000001
+
+#define REG_A2XX_RBBM_CNTL					0x0000003b
+
+#define REG_A2XX_RBBM_SOFT_RESET				0x0000003c
+
+#define REG_A2XX_CP_PFP_UCODE_ADDR				0x000000c0
+
+#define REG_A2XX_CP_PFP_UCODE_DATA				0x000000c1
+
+#define REG_A2XX_RBBM_PERFCOUNTER1_SELECT			0x00000395
+
+#define REG_A2XX_RBBM_PERFCOUNTER1_LO				0x00000397
+
+#define REG_A2XX_RBBM_PERFCOUNTER1_HI				0x00000398
+
+#define REG_A2XX_RBBM_DEBUG					0x0000039b
+
+#define REG_A2XX_RBBM_PM_OVERRIDE1				0x0000039c
+
+#define REG_A2XX_RBBM_PM_OVERRIDE2				0x0000039d
+
+#define REG_A2XX_RBBM_DEBUG_OUT					0x000003a0
+
+#define REG_A2XX_RBBM_DEBUG_CNTL				0x000003a1
+
+#define REG_A2XX_RBBM_READ_ERROR				0x000003b3
+
+#define REG_A2XX_RBBM_INT_CNTL					0x000003b4
+
+#define REG_A2XX_RBBM_INT_STATUS				0x000003b5
+
+#define REG_A2XX_RBBM_INT_ACK					0x000003b6
+
+#define REG_A2XX_MASTER_INT_SIGNAL				0x000003b7
+
+#define REG_A2XX_RBBM_PERIPHID1					0x000003f9
+
+#define REG_A2XX_RBBM_PERIPHID2					0x000003fa
+
+#define REG_A2XX_CP_PERFMON_CNTL				0x00000444
+
+#define REG_A2XX_CP_PERFCOUNTER_SELECT				0x00000445
+
+#define REG_A2XX_CP_PERFCOUNTER_LO				0x00000446
+
+#define REG_A2XX_CP_PERFCOUNTER_HI				0x00000447
+
+#define REG_A2XX_CP_ST_BASE					0x0000044d
+
+#define REG_A2XX_CP_ST_BUFSZ					0x0000044e
+
+#define REG_A2XX_CP_IB1_BASE					0x00000458
+
+#define REG_A2XX_CP_IB1_BUFSZ					0x00000459
+
+#define REG_A2XX_CP_IB2_BASE					0x0000045a
+
+#define REG_A2XX_CP_IB2_BUFSZ					0x0000045b
+
+#define REG_A2XX_CP_STAT					0x0000047f
+
+#define REG_A2XX_RBBM_STATUS					0x000005d0
+#define A2XX_RBBM_STATUS_CMDFIFO_AVAIL__MASK			0x0000001f
+#define A2XX_RBBM_STATUS_CMDFIFO_AVAIL__SHIFT			0
+static inline uint32_t A2XX_RBBM_STATUS_CMDFIFO_AVAIL(uint32_t val)
+{
+	return ((val) << A2XX_RBBM_STATUS_CMDFIFO_AVAIL__SHIFT) & A2XX_RBBM_STATUS_CMDFIFO_AVAIL__MASK;
+}
+#define A2XX_RBBM_STATUS_TC_BUSY				0x00000020
+#define A2XX_RBBM_STATUS_HIRQ_PENDING				0x00000100
+#define A2XX_RBBM_STATUS_CPRQ_PENDING				0x00000200
+#define A2XX_RBBM_STATUS_CFRQ_PENDING				0x00000400
+#define A2XX_RBBM_STATUS_PFRQ_PENDING				0x00000800
+#define A2XX_RBBM_STATUS_VGT_BUSY_NO_DMA			0x00001000
+#define A2XX_RBBM_STATUS_RBBM_WU_BUSY				0x00004000
+#define A2XX_RBBM_STATUS_CP_NRT_BUSY				0x00010000
+#define A2XX_RBBM_STATUS_MH_BUSY				0x00040000
+#define A2XX_RBBM_STATUS_MH_COHERENCY_BUSY			0x00080000
+#define A2XX_RBBM_STATUS_SX_BUSY				0x00200000
+#define A2XX_RBBM_STATUS_TPC_BUSY				0x00400000
+#define A2XX_RBBM_STATUS_SC_CNTX_BUSY				0x01000000
+#define A2XX_RBBM_STATUS_PA_BUSY				0x02000000
+#define A2XX_RBBM_STATUS_VGT_BUSY				0x04000000
+#define A2XX_RBBM_STATUS_SQ_CNTX17_BUSY				0x08000000
+#define A2XX_RBBM_STATUS_SQ_CNTX0_BUSY				0x10000000
+#define A2XX_RBBM_STATUS_RB_CNTX_BUSY				0x40000000
+#define A2XX_RBBM_STATUS_GUI_ACTIVE				0x80000000
+
+#define REG_A2XX_A220_VSC_BIN_SIZE				0x00000c01
+#define A2XX_A220_VSC_BIN_SIZE_WIDTH__MASK			0x0000001f
+#define A2XX_A220_VSC_BIN_SIZE_WIDTH__SHIFT			0
+static inline uint32_t A2XX_A220_VSC_BIN_SIZE_WIDTH(uint32_t val)
+{
+	return ((val >> 5) << A2XX_A220_VSC_BIN_SIZE_WIDTH__SHIFT) & A2XX_A220_VSC_BIN_SIZE_WIDTH__MASK;
+}
+#define A2XX_A220_VSC_BIN_SIZE_HEIGHT__MASK			0x000003e0
+#define A2XX_A220_VSC_BIN_SIZE_HEIGHT__SHIFT			5
+static inline uint32_t A2XX_A220_VSC_BIN_SIZE_HEIGHT(uint32_t val)
+{
+	return ((val >> 5) << A2XX_A220_VSC_BIN_SIZE_HEIGHT__SHIFT) & A2XX_A220_VSC_BIN_SIZE_HEIGHT__MASK;
+}
+
+static inline uint32_t REG_A2XX_VSC_PIPE(uint32_t i0) { return 0x00000c06 + 0x3*i0; }
+
+static inline uint32_t REG_A2XX_VSC_PIPE_CONFIG(uint32_t i0) { return 0x00000c06 + 0x3*i0; }
+
+static inline uint32_t REG_A2XX_VSC_PIPE_DATA_ADDRESS(uint32_t i0) { return 0x00000c07 + 0x3*i0; }
+
+static inline uint32_t REG_A2XX_VSC_PIPE_DATA_LENGTH(uint32_t i0) { return 0x00000c08 + 0x3*i0; }
+
+#define REG_A2XX_PC_DEBUG_CNTL					0x00000c38
+
+#define REG_A2XX_PC_DEBUG_DATA					0x00000c39
+
+#define REG_A2XX_PA_SC_VIZ_QUERY_STATUS				0x00000c44
+
+#define REG_A2XX_GRAS_DEBUG_CNTL				0x00000c80
+
+#define REG_A2XX_PA_SU_DEBUG_CNTL				0x00000c80
+
+#define REG_A2XX_GRAS_DEBUG_DATA				0x00000c81
+
+#define REG_A2XX_PA_SU_DEBUG_DATA				0x00000c81
+
+#define REG_A2XX_PA_SU_FACE_DATA				0x00000c86
+
+#define REG_A2XX_SQ_GPR_MANAGEMENT				0x00000d00
+
+#define REG_A2XX_SQ_FLOW_CONTROL				0x00000d01
+
+#define REG_A2XX_SQ_INST_STORE_MANAGMENT			0x00000d02
+
+#define REG_A2XX_SQ_DEBUG_MISC					0x00000d05
+
+#define REG_A2XX_SQ_INT_CNTL					0x00000d34
+
+#define REG_A2XX_SQ_INT_STATUS					0x00000d35
+
+#define REG_A2XX_SQ_INT_ACK					0x00000d36
+
+#define REG_A2XX_SQ_DEBUG_INPUT_FSM				0x00000dae
+
+#define REG_A2XX_SQ_DEBUG_CONST_MGR_FSM				0x00000daf
+
+#define REG_A2XX_SQ_DEBUG_TP_FSM				0x00000db0
+
+#define REG_A2XX_SQ_DEBUG_FSM_ALU_0				0x00000db1
+
+#define REG_A2XX_SQ_DEBUG_FSM_ALU_1				0x00000db2
+
+#define REG_A2XX_SQ_DEBUG_EXP_ALLOC				0x00000db3
+
+#define REG_A2XX_SQ_DEBUG_PTR_BUFF				0x00000db4
+
+#define REG_A2XX_SQ_DEBUG_GPR_VTX				0x00000db5
+
+#define REG_A2XX_SQ_DEBUG_GPR_PIX				0x00000db6
+
+#define REG_A2XX_SQ_DEBUG_TB_STATUS_SEL				0x00000db7
+
+#define REG_A2XX_SQ_DEBUG_VTX_TB_0				0x00000db8
+
+#define REG_A2XX_SQ_DEBUG_VTX_TB_1				0x00000db9
+
+#define REG_A2XX_SQ_DEBUG_VTX_TB_STATUS_REG			0x00000dba
+
+#define REG_A2XX_SQ_DEBUG_VTX_TB_STATE_MEM			0x00000dbb
+
+#define REG_A2XX_SQ_DEBUG_PIX_TB_0				0x00000dbc
+
+#define REG_A2XX_SQ_DEBUG_PIX_TB_STATUS_REG_0			0x00000dbd
+
+#define REG_A2XX_SQ_DEBUG_PIX_TB_STATUS_REG_1			0x00000dbe
+
+#define REG_A2XX_SQ_DEBUG_PIX_TB_STATUS_REG_2			0x00000dbf
+
+#define REG_A2XX_SQ_DEBUG_PIX_TB_STATUS_REG_3			0x00000dc0
+
+#define REG_A2XX_SQ_DEBUG_PIX_TB_STATE_MEM			0x00000dc1
+
+#define REG_A2XX_TC_CNTL_STATUS					0x00000e00
+#define A2XX_TC_CNTL_STATUS_L2_INVALIDATE			0x00000001
+
+#define REG_A2XX_TP0_CHICKEN					0x00000e1e
+
+#define REG_A2XX_RB_BC_CONTROL					0x00000f01
+#define A2XX_RB_BC_CONTROL_ACCUM_LINEAR_MODE_ENABLE		0x00000001
+#define A2XX_RB_BC_CONTROL_ACCUM_TIMEOUT_SELECT__MASK		0x00000006
+#define A2XX_RB_BC_CONTROL_ACCUM_TIMEOUT_SELECT__SHIFT		1
+static inline uint32_t A2XX_RB_BC_CONTROL_ACCUM_TIMEOUT_SELECT(uint32_t val)
+{
+	return ((val) << A2XX_RB_BC_CONTROL_ACCUM_TIMEOUT_SELECT__SHIFT) & A2XX_RB_BC_CONTROL_ACCUM_TIMEOUT_SELECT__MASK;
+}
+#define A2XX_RB_BC_CONTROL_DISABLE_EDRAM_CAM			0x00000008
+#define A2XX_RB_BC_CONTROL_DISABLE_EZ_FAST_CONTEXT_SWITCH	0x00000010
+#define A2XX_RB_BC_CONTROL_DISABLE_EZ_NULL_ZCMD_DROP		0x00000020
+#define A2XX_RB_BC_CONTROL_DISABLE_LZ_NULL_ZCMD_DROP		0x00000040
+#define A2XX_RB_BC_CONTROL_ENABLE_AZ_THROTTLE			0x00000080
+#define A2XX_RB_BC_CONTROL_AZ_THROTTLE_COUNT__MASK		0x00001f00
+#define A2XX_RB_BC_CONTROL_AZ_THROTTLE_COUNT__SHIFT		8
+static inline uint32_t A2XX_RB_BC_CONTROL_AZ_THROTTLE_COUNT(uint32_t val)
+{
+	return ((val) << A2XX_RB_BC_CONTROL_AZ_THROTTLE_COUNT__SHIFT) & A2XX_RB_BC_CONTROL_AZ_THROTTLE_COUNT__MASK;
+}
+#define A2XX_RB_BC_CONTROL_ENABLE_CRC_UPDATE			0x00004000
+#define A2XX_RB_BC_CONTROL_CRC_MODE				0x00008000
+#define A2XX_RB_BC_CONTROL_DISABLE_SAMPLE_COUNTERS		0x00010000
+#define A2XX_RB_BC_CONTROL_DISABLE_ACCUM			0x00020000
+#define A2XX_RB_BC_CONTROL_ACCUM_ALLOC_MASK__MASK		0x003c0000
+#define A2XX_RB_BC_CONTROL_ACCUM_ALLOC_MASK__SHIFT		18
+static inline uint32_t A2XX_RB_BC_CONTROL_ACCUM_ALLOC_MASK(uint32_t val)
+{
+	return ((val) << A2XX_RB_BC_CONTROL_ACCUM_ALLOC_MASK__SHIFT) & A2XX_RB_BC_CONTROL_ACCUM_ALLOC_MASK__MASK;
+}
+#define A2XX_RB_BC_CONTROL_LINEAR_PERFORMANCE_ENABLE		0x00400000
+#define A2XX_RB_BC_CONTROL_ACCUM_DATA_FIFO_LIMIT__MASK		0x07800000
+#define A2XX_RB_BC_CONTROL_ACCUM_DATA_FIFO_LIMIT__SHIFT		23
+static inline uint32_t A2XX_RB_BC_CONTROL_ACCUM_DATA_FIFO_LIMIT(uint32_t val)
+{
+	return ((val) << A2XX_RB_BC_CONTROL_ACCUM_DATA_FIFO_LIMIT__SHIFT) & A2XX_RB_BC_CONTROL_ACCUM_DATA_FIFO_LIMIT__MASK;
+}
+#define A2XX_RB_BC_CONTROL_MEM_EXPORT_TIMEOUT_SELECT__MASK	0x18000000
+#define A2XX_RB_BC_CONTROL_MEM_EXPORT_TIMEOUT_SELECT__SHIFT	27
+static inline uint32_t A2XX_RB_BC_CONTROL_MEM_EXPORT_TIMEOUT_SELECT(uint32_t val)
+{
+	return ((val) << A2XX_RB_BC_CONTROL_MEM_EXPORT_TIMEOUT_SELECT__SHIFT) & A2XX_RB_BC_CONTROL_MEM_EXPORT_TIMEOUT_SELECT__MASK;
+}
+#define A2XX_RB_BC_CONTROL_MEM_EXPORT_LINEAR_MODE_ENABLE	0x20000000
+#define A2XX_RB_BC_CONTROL_CRC_SYSTEM				0x40000000
+#define A2XX_RB_BC_CONTROL_RESERVED6				0x80000000
+
+#define REG_A2XX_RB_EDRAM_INFO					0x00000f02
+
+#define REG_A2XX_RB_DEBUG_CNTL					0x00000f26
+
+#define REG_A2XX_RB_DEBUG_DATA					0x00000f27
+
+#define REG_A2XX_RB_SURFACE_INFO				0x00002000
+
+#define REG_A2XX_RB_COLOR_INFO					0x00002001
+#define A2XX_RB_COLOR_INFO_FORMAT__MASK				0x0000000f
+#define A2XX_RB_COLOR_INFO_FORMAT__SHIFT			0
+static inline uint32_t A2XX_RB_COLOR_INFO_FORMAT(enum a2xx_colorformatx val)
+{
+	return ((val) << A2XX_RB_COLOR_INFO_FORMAT__SHIFT) & A2XX_RB_COLOR_INFO_FORMAT__MASK;
+}
+#define A2XX_RB_COLOR_INFO_ROUND_MODE__MASK			0x00000030
+#define A2XX_RB_COLOR_INFO_ROUND_MODE__SHIFT			4
+static inline uint32_t A2XX_RB_COLOR_INFO_ROUND_MODE(uint32_t val)
+{
+	return ((val) << A2XX_RB_COLOR_INFO_ROUND_MODE__SHIFT) & A2XX_RB_COLOR_INFO_ROUND_MODE__MASK;
+}
+#define A2XX_RB_COLOR_INFO_LINEAR				0x00000040
+#define A2XX_RB_COLOR_INFO_ENDIAN__MASK				0x00000180
+#define A2XX_RB_COLOR_INFO_ENDIAN__SHIFT			7
+static inline uint32_t A2XX_RB_COLOR_INFO_ENDIAN(uint32_t val)
+{
+	return ((val) << A2XX_RB_COLOR_INFO_ENDIAN__SHIFT) & A2XX_RB_COLOR_INFO_ENDIAN__MASK;
+}
+#define A2XX_RB_COLOR_INFO_SWAP__MASK				0x00000600
+#define A2XX_RB_COLOR_INFO_SWAP__SHIFT				9
+static inline uint32_t A2XX_RB_COLOR_INFO_SWAP(uint32_t val)
+{
+	return ((val) << A2XX_RB_COLOR_INFO_SWAP__SHIFT) & A2XX_RB_COLOR_INFO_SWAP__MASK;
+}
+#define A2XX_RB_COLOR_INFO_BASE__MASK				0xfffff000
+#define A2XX_RB_COLOR_INFO_BASE__SHIFT				12
+static inline uint32_t A2XX_RB_COLOR_INFO_BASE(uint32_t val)
+{
+	return ((val >> 10) << A2XX_RB_COLOR_INFO_BASE__SHIFT) & A2XX_RB_COLOR_INFO_BASE__MASK;
+}
+
+#define REG_A2XX_RB_DEPTH_INFO					0x00002002
+#define A2XX_RB_DEPTH_INFO_DEPTH_FORMAT__MASK			0x00000001
+#define A2XX_RB_DEPTH_INFO_DEPTH_FORMAT__SHIFT			0
+static inline uint32_t A2XX_RB_DEPTH_INFO_DEPTH_FORMAT(enum adreno_rb_depth_format val)
+{
+	return ((val) << A2XX_RB_DEPTH_INFO_DEPTH_FORMAT__SHIFT) & A2XX_RB_DEPTH_INFO_DEPTH_FORMAT__MASK;
+}
+#define A2XX_RB_DEPTH_INFO_DEPTH_BASE__MASK			0xfffff000
+#define A2XX_RB_DEPTH_INFO_DEPTH_BASE__SHIFT			12
+static inline uint32_t A2XX_RB_DEPTH_INFO_DEPTH_BASE(uint32_t val)
+{
+	return ((val >> 10) << A2XX_RB_DEPTH_INFO_DEPTH_BASE__SHIFT) & A2XX_RB_DEPTH_INFO_DEPTH_BASE__MASK;
+}
+
+#define REG_A2XX_A225_RB_COLOR_INFO3				0x00002005
+
+#define REG_A2XX_COHER_DEST_BASE_0				0x00002006
+
+#define REG_A2XX_PA_SC_SCREEN_SCISSOR_TL			0x0000200e
+#define A2XX_PA_SC_SCREEN_SCISSOR_TL_WINDOW_OFFSET_DISABLE	0x80000000
+#define A2XX_PA_SC_SCREEN_SCISSOR_TL_X__MASK			0x00007fff
+#define A2XX_PA_SC_SCREEN_SCISSOR_TL_X__SHIFT			0
+static inline uint32_t A2XX_PA_SC_SCREEN_SCISSOR_TL_X(uint32_t val)
+{
+	return ((val) << A2XX_PA_SC_SCREEN_SCISSOR_TL_X__SHIFT) & A2XX_PA_SC_SCREEN_SCISSOR_TL_X__MASK;
+}
+#define A2XX_PA_SC_SCREEN_SCISSOR_TL_Y__MASK			0x7fff0000
+#define A2XX_PA_SC_SCREEN_SCISSOR_TL_Y__SHIFT			16
+static inline uint32_t A2XX_PA_SC_SCREEN_SCISSOR_TL_Y(uint32_t val)
+{
+	return ((val) << A2XX_PA_SC_SCREEN_SCISSOR_TL_Y__SHIFT) & A2XX_PA_SC_SCREEN_SCISSOR_TL_Y__MASK;
+}
+
+#define REG_A2XX_PA_SC_SCREEN_SCISSOR_BR			0x0000200f
+#define A2XX_PA_SC_SCREEN_SCISSOR_BR_WINDOW_OFFSET_DISABLE	0x80000000
+#define A2XX_PA_SC_SCREEN_SCISSOR_BR_X__MASK			0x00007fff
+#define A2XX_PA_SC_SCREEN_SCISSOR_BR_X__SHIFT			0
+static inline uint32_t A2XX_PA_SC_SCREEN_SCISSOR_BR_X(uint32_t val)
+{
+	return ((val) << A2XX_PA_SC_SCREEN_SCISSOR_BR_X__SHIFT) & A2XX_PA_SC_SCREEN_SCISSOR_BR_X__MASK;
+}
+#define A2XX_PA_SC_SCREEN_SCISSOR_BR_Y__MASK			0x7fff0000
+#define A2XX_PA_SC_SCREEN_SCISSOR_BR_Y__SHIFT			16
+static inline uint32_t A2XX_PA_SC_SCREEN_SCISSOR_BR_Y(uint32_t val)
+{
+	return ((val) << A2XX_PA_SC_SCREEN_SCISSOR_BR_Y__SHIFT) & A2XX_PA_SC_SCREEN_SCISSOR_BR_Y__MASK;
+}
+
+#define REG_A2XX_PA_SC_WINDOW_OFFSET				0x00002080
+#define A2XX_PA_SC_WINDOW_OFFSET_X__MASK			0x00007fff
+#define A2XX_PA_SC_WINDOW_OFFSET_X__SHIFT			0
+static inline uint32_t A2XX_PA_SC_WINDOW_OFFSET_X(int32_t val)
+{
+	return ((val) << A2XX_PA_SC_WINDOW_OFFSET_X__SHIFT) & A2XX_PA_SC_WINDOW_OFFSET_X__MASK;
+}
+#define A2XX_PA_SC_WINDOW_OFFSET_Y__MASK			0x7fff0000
+#define A2XX_PA_SC_WINDOW_OFFSET_Y__SHIFT			16
+static inline uint32_t A2XX_PA_SC_WINDOW_OFFSET_Y(int32_t val)
+{
+	return ((val) << A2XX_PA_SC_WINDOW_OFFSET_Y__SHIFT) & A2XX_PA_SC_WINDOW_OFFSET_Y__MASK;
+}
+#define A2XX_PA_SC_WINDOW_OFFSET_DISABLE			0x80000000
+
+#define REG_A2XX_PA_SC_WINDOW_SCISSOR_TL			0x00002081
+#define A2XX_PA_SC_WINDOW_SCISSOR_TL_WINDOW_OFFSET_DISABLE	0x80000000
+#define A2XX_PA_SC_WINDOW_SCISSOR_TL_X__MASK			0x00007fff
+#define A2XX_PA_SC_WINDOW_SCISSOR_TL_X__SHIFT			0
+static inline uint32_t A2XX_PA_SC_WINDOW_SCISSOR_TL_X(uint32_t val)
+{
+	return ((val) << A2XX_PA_SC_WINDOW_SCISSOR_TL_X__SHIFT) & A2XX_PA_SC_WINDOW_SCISSOR_TL_X__MASK;
+}
+#define A2XX_PA_SC_WINDOW_SCISSOR_TL_Y__MASK			0x7fff0000
+#define A2XX_PA_SC_WINDOW_SCISSOR_TL_Y__SHIFT			16
+static inline uint32_t A2XX_PA_SC_WINDOW_SCISSOR_TL_Y(uint32_t val)
+{
+	return ((val) << A2XX_PA_SC_WINDOW_SCISSOR_TL_Y__SHIFT) & A2XX_PA_SC_WINDOW_SCISSOR_TL_Y__MASK;
+}
+
+#define REG_A2XX_PA_SC_WINDOW_SCISSOR_BR			0x00002082
+#define A2XX_PA_SC_WINDOW_SCISSOR_BR_WINDOW_OFFSET_DISABLE	0x80000000
+#define A2XX_PA_SC_WINDOW_SCISSOR_BR_X__MASK			0x00007fff
+#define A2XX_PA_SC_WINDOW_SCISSOR_BR_X__SHIFT			0
+static inline uint32_t A2XX_PA_SC_WINDOW_SCISSOR_BR_X(uint32_t val)
+{
+	return ((val) << A2XX_PA_SC_WINDOW_SCISSOR_BR_X__SHIFT) & A2XX_PA_SC_WINDOW_SCISSOR_BR_X__MASK;
+}
+#define A2XX_PA_SC_WINDOW_SCISSOR_BR_Y__MASK			0x7fff0000
+#define A2XX_PA_SC_WINDOW_SCISSOR_BR_Y__SHIFT			16
+static inline uint32_t A2XX_PA_SC_WINDOW_SCISSOR_BR_Y(uint32_t val)
+{
+	return ((val) << A2XX_PA_SC_WINDOW_SCISSOR_BR_Y__SHIFT) & A2XX_PA_SC_WINDOW_SCISSOR_BR_Y__MASK;
+}
+
+#define REG_A2XX_UNKNOWN_2010					0x00002010
+
+#define REG_A2XX_VGT_MAX_VTX_INDX				0x00002100
+
+#define REG_A2XX_VGT_MIN_VTX_INDX				0x00002101
+
+#define REG_A2XX_VGT_INDX_OFFSET				0x00002102
+
+#define REG_A2XX_A225_PC_MULTI_PRIM_IB_RESET_INDX		0x00002103
+
+#define REG_A2XX_RB_COLOR_MASK					0x00002104
+#define A2XX_RB_COLOR_MASK_WRITE_RED				0x00000001
+#define A2XX_RB_COLOR_MASK_WRITE_GREEN				0x00000002
+#define A2XX_RB_COLOR_MASK_WRITE_BLUE				0x00000004
+#define A2XX_RB_COLOR_MASK_WRITE_ALPHA				0x00000008
+
+#define REG_A2XX_RB_BLEND_RED					0x00002105
+
+#define REG_A2XX_RB_BLEND_GREEN					0x00002106
+
+#define REG_A2XX_RB_BLEND_BLUE					0x00002107
+
+#define REG_A2XX_RB_BLEND_ALPHA					0x00002108
+
+#define REG_A2XX_RB_FOG_COLOR					0x00002109
+
+#define REG_A2XX_RB_STENCILREFMASK_BF				0x0000210c
+#define A2XX_RB_STENCILREFMASK_BF_STENCILREF__MASK		0x000000ff
+#define A2XX_RB_STENCILREFMASK_BF_STENCILREF__SHIFT		0
+static inline uint32_t A2XX_RB_STENCILREFMASK_BF_STENCILREF(uint32_t val)
+{
+	return ((val) << A2XX_RB_STENCILREFMASK_BF_STENCILREF__SHIFT) & A2XX_RB_STENCILREFMASK_BF_STENCILREF__MASK;
+}
+#define A2XX_RB_STENCILREFMASK_BF_STENCILMASK__MASK		0x0000ff00
+#define A2XX_RB_STENCILREFMASK_BF_STENCILMASK__SHIFT		8
+static inline uint32_t A2XX_RB_STENCILREFMASK_BF_STENCILMASK(uint32_t val)
+{
+	return ((val) << A2XX_RB_STENCILREFMASK_BF_STENCILMASK__SHIFT) & A2XX_RB_STENCILREFMASK_BF_STENCILMASK__MASK;
+}
+#define A2XX_RB_STENCILREFMASK_BF_STENCILWRITEMASK__MASK	0x00ff0000
+#define A2XX_RB_STENCILREFMASK_BF_STENCILWRITEMASK__SHIFT	16
+static inline uint32_t A2XX_RB_STENCILREFMASK_BF_STENCILWRITEMASK(uint32_t val)
+{
+	return ((val) << A2XX_RB_STENCILREFMASK_BF_STENCILWRITEMASK__SHIFT) & A2XX_RB_STENCILREFMASK_BF_STENCILWRITEMASK__MASK;
+}
+
+#define REG_A2XX_RB_STENCILREFMASK				0x0000210d
+#define A2XX_RB_STENCILREFMASK_STENCILREF__MASK			0x000000ff
+#define A2XX_RB_STENCILREFMASK_STENCILREF__SHIFT		0
+static inline uint32_t A2XX_RB_STENCILREFMASK_STENCILREF(uint32_t val)
+{
+	return ((val) << A2XX_RB_STENCILREFMASK_STENCILREF__SHIFT) & A2XX_RB_STENCILREFMASK_STENCILREF__MASK;
+}
+#define A2XX_RB_STENCILREFMASK_STENCILMASK__MASK		0x0000ff00
+#define A2XX_RB_STENCILREFMASK_STENCILMASK__SHIFT		8
+static inline uint32_t A2XX_RB_STENCILREFMASK_STENCILMASK(uint32_t val)
+{
+	return ((val) << A2XX_RB_STENCILREFMASK_STENCILMASK__SHIFT) & A2XX_RB_STENCILREFMASK_STENCILMASK__MASK;
+}
+#define A2XX_RB_STENCILREFMASK_STENCILWRITEMASK__MASK		0x00ff0000
+#define A2XX_RB_STENCILREFMASK_STENCILWRITEMASK__SHIFT		16
+static inline uint32_t A2XX_RB_STENCILREFMASK_STENCILWRITEMASK(uint32_t val)
+{
+	return ((val) << A2XX_RB_STENCILREFMASK_STENCILWRITEMASK__SHIFT) & A2XX_RB_STENCILREFMASK_STENCILWRITEMASK__MASK;
+}
+
+#define REG_A2XX_RB_ALPHA_REF					0x0000210e
+
+#define REG_A2XX_PA_CL_VPORT_XSCALE				0x0000210f
+#define A2XX_PA_CL_VPORT_XSCALE__MASK				0xffffffff
+#define A2XX_PA_CL_VPORT_XSCALE__SHIFT				0
+static inline uint32_t A2XX_PA_CL_VPORT_XSCALE(float val)
+{
+	return ((fui(val)) << A2XX_PA_CL_VPORT_XSCALE__SHIFT) & A2XX_PA_CL_VPORT_XSCALE__MASK;
+}
+
+#define REG_A2XX_PA_CL_VPORT_XOFFSET				0x00002110
+#define A2XX_PA_CL_VPORT_XOFFSET__MASK				0xffffffff
+#define A2XX_PA_CL_VPORT_XOFFSET__SHIFT				0
+static inline uint32_t A2XX_PA_CL_VPORT_XOFFSET(float val)
+{
+	return ((fui(val)) << A2XX_PA_CL_VPORT_XOFFSET__SHIFT) & A2XX_PA_CL_VPORT_XOFFSET__MASK;
+}
+
+#define REG_A2XX_PA_CL_VPORT_YSCALE				0x00002111
+#define A2XX_PA_CL_VPORT_YSCALE__MASK				0xffffffff
+#define A2XX_PA_CL_VPORT_YSCALE__SHIFT				0
+static inline uint32_t A2XX_PA_CL_VPORT_YSCALE(float val)
+{
+	return ((fui(val)) << A2XX_PA_CL_VPORT_YSCALE__SHIFT) & A2XX_PA_CL_VPORT_YSCALE__MASK;
+}
+
+#define REG_A2XX_PA_CL_VPORT_YOFFSET				0x00002112
+#define A2XX_PA_CL_VPORT_YOFFSET__MASK				0xffffffff
+#define A2XX_PA_CL_VPORT_YOFFSET__SHIFT				0
+static inline uint32_t A2XX_PA_CL_VPORT_YOFFSET(float val)
+{
+	return ((fui(val)) << A2XX_PA_CL_VPORT_YOFFSET__SHIFT) & A2XX_PA_CL_VPORT_YOFFSET__MASK;
+}
+
+#define REG_A2XX_PA_CL_VPORT_ZSCALE				0x00002113
+#define A2XX_PA_CL_VPORT_ZSCALE__MASK				0xffffffff
+#define A2XX_PA_CL_VPORT_ZSCALE__SHIFT				0
+static inline uint32_t A2XX_PA_CL_VPORT_ZSCALE(float val)
+{
+	return ((fui(val)) << A2XX_PA_CL_VPORT_ZSCALE__SHIFT) & A2XX_PA_CL_VPORT_ZSCALE__MASK;
+}
+
+#define REG_A2XX_PA_CL_VPORT_ZOFFSET				0x00002114
+#define A2XX_PA_CL_VPORT_ZOFFSET__MASK				0xffffffff
+#define A2XX_PA_CL_VPORT_ZOFFSET__SHIFT				0
+static inline uint32_t A2XX_PA_CL_VPORT_ZOFFSET(float val)
+{
+	return ((fui(val)) << A2XX_PA_CL_VPORT_ZOFFSET__SHIFT) & A2XX_PA_CL_VPORT_ZOFFSET__MASK;
+}
+
+#define REG_A2XX_SQ_PROGRAM_CNTL				0x00002180
+#define A2XX_SQ_PROGRAM_CNTL_VS_REGS__MASK			0x000000ff
+#define A2XX_SQ_PROGRAM_CNTL_VS_REGS__SHIFT			0
+static inline uint32_t A2XX_SQ_PROGRAM_CNTL_VS_REGS(uint32_t val)
+{
+	return ((val) << A2XX_SQ_PROGRAM_CNTL_VS_REGS__SHIFT) & A2XX_SQ_PROGRAM_CNTL_VS_REGS__MASK;
+}
+#define A2XX_SQ_PROGRAM_CNTL_PS_REGS__MASK			0x0000ff00
+#define A2XX_SQ_PROGRAM_CNTL_PS_REGS__SHIFT			8
+static inline uint32_t A2XX_SQ_PROGRAM_CNTL_PS_REGS(uint32_t val)
+{
+	return ((val) << A2XX_SQ_PROGRAM_CNTL_PS_REGS__SHIFT) & A2XX_SQ_PROGRAM_CNTL_PS_REGS__MASK;
+}
+#define A2XX_SQ_PROGRAM_CNTL_VS_RESOURCE			0x00010000
+#define A2XX_SQ_PROGRAM_CNTL_PS_RESOURCE			0x00020000
+#define A2XX_SQ_PROGRAM_CNTL_PARAM_GEN				0x00040000
+#define A2XX_SQ_PROGRAM_CNTL_GEN_INDEX_PIX			0x00080000
+#define A2XX_SQ_PROGRAM_CNTL_VS_EXPORT_COUNT__MASK		0x00f00000
+#define A2XX_SQ_PROGRAM_CNTL_VS_EXPORT_COUNT__SHIFT		20
+static inline uint32_t A2XX_SQ_PROGRAM_CNTL_VS_EXPORT_COUNT(uint32_t val)
+{
+	return ((val) << A2XX_SQ_PROGRAM_CNTL_VS_EXPORT_COUNT__SHIFT) & A2XX_SQ_PROGRAM_CNTL_VS_EXPORT_COUNT__MASK;
+}
+#define A2XX_SQ_PROGRAM_CNTL_VS_EXPORT_MODE__MASK		0x07000000
+#define A2XX_SQ_PROGRAM_CNTL_VS_EXPORT_MODE__SHIFT		24
+static inline uint32_t A2XX_SQ_PROGRAM_CNTL_VS_EXPORT_MODE(enum a2xx_sq_ps_vtx_mode val)
+{
+	return ((val) << A2XX_SQ_PROGRAM_CNTL_VS_EXPORT_MODE__SHIFT) & A2XX_SQ_PROGRAM_CNTL_VS_EXPORT_MODE__MASK;
+}
+#define A2XX_SQ_PROGRAM_CNTL_PS_EXPORT_MODE__MASK		0x78000000
+#define A2XX_SQ_PROGRAM_CNTL_PS_EXPORT_MODE__SHIFT		27
+static inline uint32_t A2XX_SQ_PROGRAM_CNTL_PS_EXPORT_MODE(uint32_t val)
+{
+	return ((val) << A2XX_SQ_PROGRAM_CNTL_PS_EXPORT_MODE__SHIFT) & A2XX_SQ_PROGRAM_CNTL_PS_EXPORT_MODE__MASK;
+}
+#define A2XX_SQ_PROGRAM_CNTL_GEN_INDEX_VTX			0x80000000
+
+#define REG_A2XX_SQ_CONTEXT_MISC				0x00002181
+#define A2XX_SQ_CONTEXT_MISC_INST_PRED_OPTIMIZE			0x00000001
+#define A2XX_SQ_CONTEXT_MISC_SC_OUTPUT_SCREEN_XY		0x00000002
+#define A2XX_SQ_CONTEXT_MISC_SC_SAMPLE_CNTL__MASK		0x0000000c
+#define A2XX_SQ_CONTEXT_MISC_SC_SAMPLE_CNTL__SHIFT		2
+static inline uint32_t A2XX_SQ_CONTEXT_MISC_SC_SAMPLE_CNTL(enum a2xx_sq_sample_cntl val)
+{
+	return ((val) << A2XX_SQ_CONTEXT_MISC_SC_SAMPLE_CNTL__SHIFT) & A2XX_SQ_CONTEXT_MISC_SC_SAMPLE_CNTL__MASK;
+}
+#define A2XX_SQ_CONTEXT_MISC_PARAM_GEN_POS__MASK		0x0000ff00
+#define A2XX_SQ_CONTEXT_MISC_PARAM_GEN_POS__SHIFT		8
+static inline uint32_t A2XX_SQ_CONTEXT_MISC_PARAM_GEN_POS(uint32_t val)
+{
+	return ((val) << A2XX_SQ_CONTEXT_MISC_PARAM_GEN_POS__SHIFT) & A2XX_SQ_CONTEXT_MISC_PARAM_GEN_POS__MASK;
+}
+#define A2XX_SQ_CONTEXT_MISC_PERFCOUNTER_REF			0x00010000
+#define A2XX_SQ_CONTEXT_MISC_YEILD_OPTIMIZE			0x00020000
+#define A2XX_SQ_CONTEXT_MISC_TX_CACHE_SEL			0x00040000
+
+#define REG_A2XX_SQ_INTERPOLATOR_CNTL				0x00002182
+
+#define REG_A2XX_SQ_WRAPPING_0					0x00002183
+
+#define REG_A2XX_SQ_WRAPPING_1					0x00002184
+
+#define REG_A2XX_SQ_PS_PROGRAM					0x000021f6
+
+#define REG_A2XX_SQ_VS_PROGRAM					0x000021f7
+
+#define REG_A2XX_RB_DEPTHCONTROL				0x00002200
+#define A2XX_RB_DEPTHCONTROL_STENCIL_ENABLE			0x00000001
+#define A2XX_RB_DEPTHCONTROL_Z_ENABLE				0x00000002
+#define A2XX_RB_DEPTHCONTROL_Z_WRITE_ENABLE			0x00000004
+#define A2XX_RB_DEPTHCONTROL_EARLY_Z_ENABLE			0x00000008
+#define A2XX_RB_DEPTHCONTROL_ZFUNC__MASK			0x00000070
+#define A2XX_RB_DEPTHCONTROL_ZFUNC__SHIFT			4
+static inline uint32_t A2XX_RB_DEPTHCONTROL_ZFUNC(enum adreno_compare_func val)
+{
+	return ((val) << A2XX_RB_DEPTHCONTROL_ZFUNC__SHIFT) & A2XX_RB_DEPTHCONTROL_ZFUNC__MASK;
+}
+#define A2XX_RB_DEPTHCONTROL_BACKFACE_ENABLE			0x00000080
+#define A2XX_RB_DEPTHCONTROL_STENCILFUNC__MASK			0x00000700
+#define A2XX_RB_DEPTHCONTROL_STENCILFUNC__SHIFT			8
+static inline uint32_t A2XX_RB_DEPTHCONTROL_STENCILFUNC(enum adreno_compare_func val)
+{
+	return ((val) << A2XX_RB_DEPTHCONTROL_STENCILFUNC__SHIFT) & A2XX_RB_DEPTHCONTROL_STENCILFUNC__MASK;
+}
+#define A2XX_RB_DEPTHCONTROL_STENCILFAIL__MASK			0x00003800
+#define A2XX_RB_DEPTHCONTROL_STENCILFAIL__SHIFT			11
+static inline uint32_t A2XX_RB_DEPTHCONTROL_STENCILFAIL(enum adreno_stencil_op val)
+{
+	return ((val) << A2XX_RB_DEPTHCONTROL_STENCILFAIL__SHIFT) & A2XX_RB_DEPTHCONTROL_STENCILFAIL__MASK;
+}
+#define A2XX_RB_DEPTHCONTROL_STENCILZPASS__MASK			0x0001c000
+#define A2XX_RB_DEPTHCONTROL_STENCILZPASS__SHIFT		14
+static inline uint32_t A2XX_RB_DEPTHCONTROL_STENCILZPASS(enum adreno_stencil_op val)
+{
+	return ((val) << A2XX_RB_DEPTHCONTROL_STENCILZPASS__SHIFT) & A2XX_RB_DEPTHCONTROL_STENCILZPASS__MASK;
+}
+#define A2XX_RB_DEPTHCONTROL_STENCILZFAIL__MASK			0x000e0000
+#define A2XX_RB_DEPTHCONTROL_STENCILZFAIL__SHIFT		17
+static inline uint32_t A2XX_RB_DEPTHCONTROL_STENCILZFAIL(enum adreno_stencil_op val)
+{
+	return ((val) << A2XX_RB_DEPTHCONTROL_STENCILZFAIL__SHIFT) & A2XX_RB_DEPTHCONTROL_STENCILZFAIL__MASK;
+}
+#define A2XX_RB_DEPTHCONTROL_STENCILFUNC_BF__MASK		0x00700000
+#define A2XX_RB_DEPTHCONTROL_STENCILFUNC_BF__SHIFT		20
+static inline uint32_t A2XX_RB_DEPTHCONTROL_STENCILFUNC_BF(enum adreno_compare_func val)
+{
+	return ((val) << A2XX_RB_DEPTHCONTROL_STENCILFUNC_BF__SHIFT) & A2XX_RB_DEPTHCONTROL_STENCILFUNC_BF__MASK;
+}
+#define A2XX_RB_DEPTHCONTROL_STENCILFAIL_BF__MASK		0x03800000
+#define A2XX_RB_DEPTHCONTROL_STENCILFAIL_BF__SHIFT		23
+static inline uint32_t A2XX_RB_DEPTHCONTROL_STENCILFAIL_BF(enum adreno_stencil_op val)
+{
+	return ((val) << A2XX_RB_DEPTHCONTROL_STENCILFAIL_BF__SHIFT) & A2XX_RB_DEPTHCONTROL_STENCILFAIL_BF__MASK;
+}
+#define A2XX_RB_DEPTHCONTROL_STENCILZPASS_BF__MASK		0x1c000000
+#define A2XX_RB_DEPTHCONTROL_STENCILZPASS_BF__SHIFT		26
+static inline uint32_t A2XX_RB_DEPTHCONTROL_STENCILZPASS_BF(enum adreno_stencil_op val)
+{
+	return ((val) << A2XX_RB_DEPTHCONTROL_STENCILZPASS_BF__SHIFT) & A2XX_RB_DEPTHCONTROL_STENCILZPASS_BF__MASK;
+}
+#define A2XX_RB_DEPTHCONTROL_STENCILZFAIL_BF__MASK		0xe0000000
+#define A2XX_RB_DEPTHCONTROL_STENCILZFAIL_BF__SHIFT		29
+static inline uint32_t A2XX_RB_DEPTHCONTROL_STENCILZFAIL_BF(enum adreno_stencil_op val)
+{
+	return ((val) << A2XX_RB_DEPTHCONTROL_STENCILZFAIL_BF__SHIFT) & A2XX_RB_DEPTHCONTROL_STENCILZFAIL_BF__MASK;
+}
+
+#define REG_A2XX_RB_BLEND_CONTROL				0x00002201
+#define A2XX_RB_BLEND_CONTROL_COLOR_SRCBLEND__MASK		0x0000001f
+#define A2XX_RB_BLEND_CONTROL_COLOR_SRCBLEND__SHIFT		0
+static inline uint32_t A2XX_RB_BLEND_CONTROL_COLOR_SRCBLEND(enum adreno_rb_blend_factor val)
+{
+	return ((val) << A2XX_RB_BLEND_CONTROL_COLOR_SRCBLEND__SHIFT) & A2XX_RB_BLEND_CONTROL_COLOR_SRCBLEND__MASK;
+}
+#define A2XX_RB_BLEND_CONTROL_COLOR_COMB_FCN__MASK		0x000000e0
+#define A2XX_RB_BLEND_CONTROL_COLOR_COMB_FCN__SHIFT		5
+static inline uint32_t A2XX_RB_BLEND_CONTROL_COLOR_COMB_FCN(enum adreno_rb_blend_opcode val)
+{
+	return ((val) << A2XX_RB_BLEND_CONTROL_COLOR_COMB_FCN__SHIFT) & A2XX_RB_BLEND_CONTROL_COLOR_COMB_FCN__MASK;
+}
+#define A2XX_RB_BLEND_CONTROL_COLOR_DESTBLEND__MASK		0x00001f00
+#define A2XX_RB_BLEND_CONTROL_COLOR_DESTBLEND__SHIFT		8
+static inline uint32_t A2XX_RB_BLEND_CONTROL_COLOR_DESTBLEND(enum adreno_rb_blend_factor val)
+{
+	return ((val) << A2XX_RB_BLEND_CONTROL_COLOR_DESTBLEND__SHIFT) & A2XX_RB_BLEND_CONTROL_COLOR_DESTBLEND__MASK;
+}
+#define A2XX_RB_BLEND_CONTROL_ALPHA_SRCBLEND__MASK		0x001f0000
+#define A2XX_RB_BLEND_CONTROL_ALPHA_SRCBLEND__SHIFT		16
+static inline uint32_t A2XX_RB_BLEND_CONTROL_ALPHA_SRCBLEND(enum adreno_rb_blend_factor val)
+{
+	return ((val) << A2XX_RB_BLEND_CONTROL_ALPHA_SRCBLEND__SHIFT) & A2XX_RB_BLEND_CONTROL_ALPHA_SRCBLEND__MASK;
+}
+#define A2XX_RB_BLEND_CONTROL_ALPHA_COMB_FCN__MASK		0x00e00000
+#define A2XX_RB_BLEND_CONTROL_ALPHA_COMB_FCN__SHIFT		21
+static inline uint32_t A2XX_RB_BLEND_CONTROL_ALPHA_COMB_FCN(enum adreno_rb_blend_opcode val)
+{
+	return ((val) << A2XX_RB_BLEND_CONTROL_ALPHA_COMB_FCN__SHIFT) & A2XX_RB_BLEND_CONTROL_ALPHA_COMB_FCN__MASK;
+}
+#define A2XX_RB_BLEND_CONTROL_ALPHA_DESTBLEND__MASK		0x1f000000
+#define A2XX_RB_BLEND_CONTROL_ALPHA_DESTBLEND__SHIFT		24
+static inline uint32_t A2XX_RB_BLEND_CONTROL_ALPHA_DESTBLEND(enum adreno_rb_blend_factor val)
+{
+	return ((val) << A2XX_RB_BLEND_CONTROL_ALPHA_DESTBLEND__SHIFT) & A2XX_RB_BLEND_CONTROL_ALPHA_DESTBLEND__MASK;
+}
+#define A2XX_RB_BLEND_CONTROL_BLEND_FORCE_ENABLE		0x20000000
+#define A2XX_RB_BLEND_CONTROL_BLEND_FORCE			0x40000000
+
+#define REG_A2XX_RB_COLORCONTROL				0x00002202
+#define A2XX_RB_COLORCONTROL_ALPHA_FUNC__MASK			0x00000007
+#define A2XX_RB_COLORCONTROL_ALPHA_FUNC__SHIFT			0
+static inline uint32_t A2XX_RB_COLORCONTROL_ALPHA_FUNC(enum adreno_compare_func val)
+{
+	return ((val) << A2XX_RB_COLORCONTROL_ALPHA_FUNC__SHIFT) & A2XX_RB_COLORCONTROL_ALPHA_FUNC__MASK;
+}
+#define A2XX_RB_COLORCONTROL_ALPHA_TEST_ENABLE			0x00000008
+#define A2XX_RB_COLORCONTROL_ALPHA_TO_MASK_ENABLE		0x00000010
+#define A2XX_RB_COLORCONTROL_BLEND_DISABLE			0x00000020
+#define A2XX_RB_COLORCONTROL_VOB_ENABLE				0x00000040
+#define A2XX_RB_COLORCONTROL_VS_EXPORTS_FOG			0x00000080
+#define A2XX_RB_COLORCONTROL_ROP_CODE__MASK			0x00000f00
+#define A2XX_RB_COLORCONTROL_ROP_CODE__SHIFT			8
+static inline uint32_t A2XX_RB_COLORCONTROL_ROP_CODE(uint32_t val)
+{
+	return ((val) << A2XX_RB_COLORCONTROL_ROP_CODE__SHIFT) & A2XX_RB_COLORCONTROL_ROP_CODE__MASK;
+}
+#define A2XX_RB_COLORCONTROL_DITHER_MODE__MASK			0x00003000
+#define A2XX_RB_COLORCONTROL_DITHER_MODE__SHIFT			12
+static inline uint32_t A2XX_RB_COLORCONTROL_DITHER_MODE(enum adreno_rb_dither_mode val)
+{
+	return ((val) << A2XX_RB_COLORCONTROL_DITHER_MODE__SHIFT) & A2XX_RB_COLORCONTROL_DITHER_MODE__MASK;
+}
+#define A2XX_RB_COLORCONTROL_DITHER_TYPE__MASK			0x0000c000
+#define A2XX_RB_COLORCONTROL_DITHER_TYPE__SHIFT			14
+static inline uint32_t A2XX_RB_COLORCONTROL_DITHER_TYPE(enum a2xx_rb_dither_type val)
+{
+	return ((val) << A2XX_RB_COLORCONTROL_DITHER_TYPE__SHIFT) & A2XX_RB_COLORCONTROL_DITHER_TYPE__MASK;
+}
+#define A2XX_RB_COLORCONTROL_PIXEL_FOG				0x00010000
+#define A2XX_RB_COLORCONTROL_ALPHA_TO_MASK_OFFSET0__MASK	0x03000000
+#define A2XX_RB_COLORCONTROL_ALPHA_TO_MASK_OFFSET0__SHIFT	24
+static inline uint32_t A2XX_RB_COLORCONTROL_ALPHA_TO_MASK_OFFSET0(uint32_t val)
+{
+	return ((val) << A2XX_RB_COLORCONTROL_ALPHA_TO_MASK_OFFSET0__SHIFT) & A2XX_RB_COLORCONTROL_ALPHA_TO_MASK_OFFSET0__MASK;
+}
+#define A2XX_RB_COLORCONTROL_ALPHA_TO_MASK_OFFSET1__MASK	0x0c000000
+#define A2XX_RB_COLORCONTROL_ALPHA_TO_MASK_OFFSET1__SHIFT	26
+static inline uint32_t A2XX_RB_COLORCONTROL_ALPHA_TO_MASK_OFFSET1(uint32_t val)
+{
+	return ((val) << A2XX_RB_COLORCONTROL_ALPHA_TO_MASK_OFFSET1__SHIFT) & A2XX_RB_COLORCONTROL_ALPHA_TO_MASK_OFFSET1__MASK;
+}
+#define A2XX_RB_COLORCONTROL_ALPHA_TO_MASK_OFFSET2__MASK	0x30000000
+#define A2XX_RB_COLORCONTROL_ALPHA_TO_MASK_OFFSET2__SHIFT	28
+static inline uint32_t A2XX_RB_COLORCONTROL_ALPHA_TO_MASK_OFFSET2(uint32_t val)
+{
+	return ((val) << A2XX_RB_COLORCONTROL_ALPHA_TO_MASK_OFFSET2__SHIFT) & A2XX_RB_COLORCONTROL_ALPHA_TO_MASK_OFFSET2__MASK;
+}
+#define A2XX_RB_COLORCONTROL_ALPHA_TO_MASK_OFFSET3__MASK	0xc0000000
+#define A2XX_RB_COLORCONTROL_ALPHA_TO_MASK_OFFSET3__SHIFT	30
+static inline uint32_t A2XX_RB_COLORCONTROL_ALPHA_TO_MASK_OFFSET3(uint32_t val)
+{
+	return ((val) << A2XX_RB_COLORCONTROL_ALPHA_TO_MASK_OFFSET3__SHIFT) & A2XX_RB_COLORCONTROL_ALPHA_TO_MASK_OFFSET3__MASK;
+}
+
+#define REG_A2XX_VGT_CURRENT_BIN_ID_MAX				0x00002203
+#define A2XX_VGT_CURRENT_BIN_ID_MAX_COLUMN__MASK		0x00000007
+#define A2XX_VGT_CURRENT_BIN_ID_MAX_COLUMN__SHIFT		0
+static inline uint32_t A2XX_VGT_CURRENT_BIN_ID_MAX_COLUMN(uint32_t val)
+{
+	return ((val) << A2XX_VGT_CURRENT_BIN_ID_MAX_COLUMN__SHIFT) & A2XX_VGT_CURRENT_BIN_ID_MAX_COLUMN__MASK;
+}
+#define A2XX_VGT_CURRENT_BIN_ID_MAX_ROW__MASK			0x00000038
+#define A2XX_VGT_CURRENT_BIN_ID_MAX_ROW__SHIFT			3
+static inline uint32_t A2XX_VGT_CURRENT_BIN_ID_MAX_ROW(uint32_t val)
+{
+	return ((val) << A2XX_VGT_CURRENT_BIN_ID_MAX_ROW__SHIFT) & A2XX_VGT_CURRENT_BIN_ID_MAX_ROW__MASK;
+}
+#define A2XX_VGT_CURRENT_BIN_ID_MAX_GUARD_BAND_MASK__MASK	0x000001c0
+#define A2XX_VGT_CURRENT_BIN_ID_MAX_GUARD_BAND_MASK__SHIFT	6
+static inline uint32_t A2XX_VGT_CURRENT_BIN_ID_MAX_GUARD_BAND_MASK(uint32_t val)
+{
+	return ((val) << A2XX_VGT_CURRENT_BIN_ID_MAX_GUARD_BAND_MASK__SHIFT) & A2XX_VGT_CURRENT_BIN_ID_MAX_GUARD_BAND_MASK__MASK;
+}
+
+#define REG_A2XX_PA_CL_CLIP_CNTL				0x00002204
+#define A2XX_PA_CL_CLIP_CNTL_CLIP_DISABLE			0x00010000
+#define A2XX_PA_CL_CLIP_CNTL_BOUNDARY_EDGE_FLAG_ENA		0x00040000
+#define A2XX_PA_CL_CLIP_CNTL_DX_CLIP_SPACE_DEF__MASK		0x00080000
+#define A2XX_PA_CL_CLIP_CNTL_DX_CLIP_SPACE_DEF__SHIFT		19
+static inline uint32_t A2XX_PA_CL_CLIP_CNTL_DX_CLIP_SPACE_DEF(enum a2xx_dx_clip_space val)
+{
+	return ((val) << A2XX_PA_CL_CLIP_CNTL_DX_CLIP_SPACE_DEF__SHIFT) & A2XX_PA_CL_CLIP_CNTL_DX_CLIP_SPACE_DEF__MASK;
+}
+#define A2XX_PA_CL_CLIP_CNTL_DIS_CLIP_ERR_DETECT		0x00100000
+#define A2XX_PA_CL_CLIP_CNTL_VTX_KILL_OR			0x00200000
+#define A2XX_PA_CL_CLIP_CNTL_XY_NAN_RETAIN			0x00400000
+#define A2XX_PA_CL_CLIP_CNTL_Z_NAN_RETAIN			0x00800000
+#define A2XX_PA_CL_CLIP_CNTL_W_NAN_RETAIN			0x01000000
+
+#define REG_A2XX_PA_SU_SC_MODE_CNTL				0x00002205
+#define A2XX_PA_SU_SC_MODE_CNTL_CULL_FRONT			0x00000001
+#define A2XX_PA_SU_SC_MODE_CNTL_CULL_BACK			0x00000002
+#define A2XX_PA_SU_SC_MODE_CNTL_FACE				0x00000004
+#define A2XX_PA_SU_SC_MODE_CNTL_POLYMODE__MASK			0x00000018
+#define A2XX_PA_SU_SC_MODE_CNTL_POLYMODE__SHIFT			3
+static inline uint32_t A2XX_PA_SU_SC_MODE_CNTL_POLYMODE(enum a2xx_pa_su_sc_polymode val)
+{
+	return ((val) << A2XX_PA_SU_SC_MODE_CNTL_POLYMODE__SHIFT) & A2XX_PA_SU_SC_MODE_CNTL_POLYMODE__MASK;
+}
+#define A2XX_PA_SU_SC_MODE_CNTL_FRONT_PTYPE__MASK		0x000000e0
+#define A2XX_PA_SU_SC_MODE_CNTL_FRONT_PTYPE__SHIFT		5
+static inline uint32_t A2XX_PA_SU_SC_MODE_CNTL_FRONT_PTYPE(enum adreno_pa_su_sc_draw val)
+{
+	return ((val) << A2XX_PA_SU_SC_MODE_CNTL_FRONT_PTYPE__SHIFT) & A2XX_PA_SU_SC_MODE_CNTL_FRONT_PTYPE__MASK;
+}
+#define A2XX_PA_SU_SC_MODE_CNTL_BACK_PTYPE__MASK		0x00000700
+#define A2XX_PA_SU_SC_MODE_CNTL_BACK_PTYPE__SHIFT		8
+static inline uint32_t A2XX_PA_SU_SC_MODE_CNTL_BACK_PTYPE(enum adreno_pa_su_sc_draw val)
+{
+	return ((val) << A2XX_PA_SU_SC_MODE_CNTL_BACK_PTYPE__SHIFT) & A2XX_PA_SU_SC_MODE_CNTL_BACK_PTYPE__MASK;
+}
+#define A2XX_PA_SU_SC_MODE_CNTL_POLY_OFFSET_FRONT_ENABLE	0x00000800
+#define A2XX_PA_SU_SC_MODE_CNTL_POLY_OFFSET_BACK_ENABLE		0x00001000
+#define A2XX_PA_SU_SC_MODE_CNTL_POLY_OFFSET_PARA_ENABLE		0x00002000
+#define A2XX_PA_SU_SC_MODE_CNTL_MSAA_ENABLE			0x00008000
+#define A2XX_PA_SU_SC_MODE_CNTL_VTX_WINDOW_OFFSET_ENABLE	0x00010000
+#define A2XX_PA_SU_SC_MODE_CNTL_LINE_STIPPLE_ENABLE		0x00040000
+#define A2XX_PA_SU_SC_MODE_CNTL_PROVOKING_VTX_LAST		0x00080000
+#define A2XX_PA_SU_SC_MODE_CNTL_PERSP_CORR_DIS			0x00100000
+#define A2XX_PA_SU_SC_MODE_CNTL_MULTI_PRIM_IB_ENA		0x00200000
+#define A2XX_PA_SU_SC_MODE_CNTL_QUAD_ORDER_ENABLE		0x00800000
+#define A2XX_PA_SU_SC_MODE_CNTL_WAIT_RB_IDLE_ALL_TRI		0x02000000
+#define A2XX_PA_SU_SC_MODE_CNTL_WAIT_RB_IDLE_FIRST_TRI_NEW_STATE	0x04000000
+#define A2XX_PA_SU_SC_MODE_CNTL_CLAMPED_FACENESS		0x10000000
+#define A2XX_PA_SU_SC_MODE_CNTL_ZERO_AREA_FACENESS		0x20000000
+#define A2XX_PA_SU_SC_MODE_CNTL_FACE_KILL_ENABLE		0x40000000
+#define A2XX_PA_SU_SC_MODE_CNTL_FACE_WRITE_ENABLE		0x80000000
+
+#define REG_A2XX_PA_CL_VTE_CNTL					0x00002206
+#define A2XX_PA_CL_VTE_CNTL_VPORT_X_SCALE_ENA			0x00000001
+#define A2XX_PA_CL_VTE_CNTL_VPORT_X_OFFSET_ENA			0x00000002
+#define A2XX_PA_CL_VTE_CNTL_VPORT_Y_SCALE_ENA			0x00000004
+#define A2XX_PA_CL_VTE_CNTL_VPORT_Y_OFFSET_ENA			0x00000008
+#define A2XX_PA_CL_VTE_CNTL_VPORT_Z_SCALE_ENA			0x00000010
+#define A2XX_PA_CL_VTE_CNTL_VPORT_Z_OFFSET_ENA			0x00000020
+#define A2XX_PA_CL_VTE_CNTL_VTX_XY_FMT				0x00000100
+#define A2XX_PA_CL_VTE_CNTL_VTX_Z_FMT				0x00000200
+#define A2XX_PA_CL_VTE_CNTL_VTX_W0_FMT				0x00000400
+#define A2XX_PA_CL_VTE_CNTL_PERFCOUNTER_REF			0x00000800
+
+#define REG_A2XX_VGT_CURRENT_BIN_ID_MIN				0x00002207
+#define A2XX_VGT_CURRENT_BIN_ID_MIN_COLUMN__MASK		0x00000007
+#define A2XX_VGT_CURRENT_BIN_ID_MIN_COLUMN__SHIFT		0
+static inline uint32_t A2XX_VGT_CURRENT_BIN_ID_MIN_COLUMN(uint32_t val)
+{
+	return ((val) << A2XX_VGT_CURRENT_BIN_ID_MIN_COLUMN__SHIFT) & A2XX_VGT_CURRENT_BIN_ID_MIN_COLUMN__MASK;
+}
+#define A2XX_VGT_CURRENT_BIN_ID_MIN_ROW__MASK			0x00000038
+#define A2XX_VGT_CURRENT_BIN_ID_MIN_ROW__SHIFT			3
+static inline uint32_t A2XX_VGT_CURRENT_BIN_ID_MIN_ROW(uint32_t val)
+{
+	return ((val) << A2XX_VGT_CURRENT_BIN_ID_MIN_ROW__SHIFT) & A2XX_VGT_CURRENT_BIN_ID_MIN_ROW__MASK;
+}
+#define A2XX_VGT_CURRENT_BIN_ID_MIN_GUARD_BAND_MASK__MASK	0x000001c0
+#define A2XX_VGT_CURRENT_BIN_ID_MIN_GUARD_BAND_MASK__SHIFT	6
+static inline uint32_t A2XX_VGT_CURRENT_BIN_ID_MIN_GUARD_BAND_MASK(uint32_t val)
+{
+	return ((val) << A2XX_VGT_CURRENT_BIN_ID_MIN_GUARD_BAND_MASK__SHIFT) & A2XX_VGT_CURRENT_BIN_ID_MIN_GUARD_BAND_MASK__MASK;
+}
+
+#define REG_A2XX_RB_MODECONTROL					0x00002208
+#define A2XX_RB_MODECONTROL_EDRAM_MODE__MASK			0x00000007
+#define A2XX_RB_MODECONTROL_EDRAM_MODE__SHIFT			0
+static inline uint32_t A2XX_RB_MODECONTROL_EDRAM_MODE(enum a2xx_rb_edram_mode val)
+{
+	return ((val) << A2XX_RB_MODECONTROL_EDRAM_MODE__SHIFT) & A2XX_RB_MODECONTROL_EDRAM_MODE__MASK;
+}
+
+#define REG_A2XX_A220_RB_LRZ_VSC_CONTROL			0x00002209
+
+#define REG_A2XX_RB_SAMPLE_POS					0x0000220a
+
+#define REG_A2XX_CLEAR_COLOR					0x0000220b
+#define A2XX_CLEAR_COLOR_RED__MASK				0x000000ff
+#define A2XX_CLEAR_COLOR_RED__SHIFT				0
+static inline uint32_t A2XX_CLEAR_COLOR_RED(uint32_t val)
+{
+	return ((val) << A2XX_CLEAR_COLOR_RED__SHIFT) & A2XX_CLEAR_COLOR_RED__MASK;
+}
+#define A2XX_CLEAR_COLOR_GREEN__MASK				0x0000ff00
+#define A2XX_CLEAR_COLOR_GREEN__SHIFT				8
+static inline uint32_t A2XX_CLEAR_COLOR_GREEN(uint32_t val)
+{
+	return ((val) << A2XX_CLEAR_COLOR_GREEN__SHIFT) & A2XX_CLEAR_COLOR_GREEN__MASK;
+}
+#define A2XX_CLEAR_COLOR_BLUE__MASK				0x00ff0000
+#define A2XX_CLEAR_COLOR_BLUE__SHIFT				16
+static inline uint32_t A2XX_CLEAR_COLOR_BLUE(uint32_t val)
+{
+	return ((val) << A2XX_CLEAR_COLOR_BLUE__SHIFT) & A2XX_CLEAR_COLOR_BLUE__MASK;
+}
+#define A2XX_CLEAR_COLOR_ALPHA__MASK				0xff000000
+#define A2XX_CLEAR_COLOR_ALPHA__SHIFT				24
+static inline uint32_t A2XX_CLEAR_COLOR_ALPHA(uint32_t val)
+{
+	return ((val) << A2XX_CLEAR_COLOR_ALPHA__SHIFT) & A2XX_CLEAR_COLOR_ALPHA__MASK;
+}
+
+#define REG_A2XX_A220_GRAS_CONTROL				0x00002210
+
+#define REG_A2XX_PA_SU_POINT_SIZE				0x00002280
+#define A2XX_PA_SU_POINT_SIZE_HEIGHT__MASK			0x0000ffff
+#define A2XX_PA_SU_POINT_SIZE_HEIGHT__SHIFT			0
+static inline uint32_t A2XX_PA_SU_POINT_SIZE_HEIGHT(float val)
+{
+	return ((((uint32_t)(val * 8.0))) << A2XX_PA_SU_POINT_SIZE_HEIGHT__SHIFT) & A2XX_PA_SU_POINT_SIZE_HEIGHT__MASK;
+}
+#define A2XX_PA_SU_POINT_SIZE_WIDTH__MASK			0xffff0000
+#define A2XX_PA_SU_POINT_SIZE_WIDTH__SHIFT			16
+static inline uint32_t A2XX_PA_SU_POINT_SIZE_WIDTH(float val)
+{
+	return ((((uint32_t)(val * 8.0))) << A2XX_PA_SU_POINT_SIZE_WIDTH__SHIFT) & A2XX_PA_SU_POINT_SIZE_WIDTH__MASK;
+}
+
+#define REG_A2XX_PA_SU_POINT_MINMAX				0x00002281
+#define A2XX_PA_SU_POINT_MINMAX_MIN__MASK			0x0000ffff
+#define A2XX_PA_SU_POINT_MINMAX_MIN__SHIFT			0
+static inline uint32_t A2XX_PA_SU_POINT_MINMAX_MIN(float val)
+{
+	return ((((uint32_t)(val * 8.0))) << A2XX_PA_SU_POINT_MINMAX_MIN__SHIFT) & A2XX_PA_SU_POINT_MINMAX_MIN__MASK;
+}
+#define A2XX_PA_SU_POINT_MINMAX_MAX__MASK			0xffff0000
+#define A2XX_PA_SU_POINT_MINMAX_MAX__SHIFT			16
+static inline uint32_t A2XX_PA_SU_POINT_MINMAX_MAX(float val)
+{
+	return ((((uint32_t)(val * 8.0))) << A2XX_PA_SU_POINT_MINMAX_MAX__SHIFT) & A2XX_PA_SU_POINT_MINMAX_MAX__MASK;
+}
+
+#define REG_A2XX_PA_SU_LINE_CNTL				0x00002282
+#define A2XX_PA_SU_LINE_CNTL_WIDTH__MASK			0x0000ffff
+#define A2XX_PA_SU_LINE_CNTL_WIDTH__SHIFT			0
+static inline uint32_t A2XX_PA_SU_LINE_CNTL_WIDTH(float val)
+{
+	return ((((uint32_t)(val * 8.0))) << A2XX_PA_SU_LINE_CNTL_WIDTH__SHIFT) & A2XX_PA_SU_LINE_CNTL_WIDTH__MASK;
+}
+
+#define REG_A2XX_PA_SC_LINE_STIPPLE				0x00002283
+#define A2XX_PA_SC_LINE_STIPPLE_LINE_PATTERN__MASK		0x0000ffff
+#define A2XX_PA_SC_LINE_STIPPLE_LINE_PATTERN__SHIFT		0
+static inline uint32_t A2XX_PA_SC_LINE_STIPPLE_LINE_PATTERN(uint32_t val)
+{
+	return ((val) << A2XX_PA_SC_LINE_STIPPLE_LINE_PATTERN__SHIFT) & A2XX_PA_SC_LINE_STIPPLE_LINE_PATTERN__MASK;
+}
+#define A2XX_PA_SC_LINE_STIPPLE_REPEAT_COUNT__MASK		0x00ff0000
+#define A2XX_PA_SC_LINE_STIPPLE_REPEAT_COUNT__SHIFT		16
+static inline uint32_t A2XX_PA_SC_LINE_STIPPLE_REPEAT_COUNT(uint32_t val)
+{
+	return ((val) << A2XX_PA_SC_LINE_STIPPLE_REPEAT_COUNT__SHIFT) & A2XX_PA_SC_LINE_STIPPLE_REPEAT_COUNT__MASK;
+}
+#define A2XX_PA_SC_LINE_STIPPLE_PATTERN_BIT_ORDER__MASK		0x10000000
+#define A2XX_PA_SC_LINE_STIPPLE_PATTERN_BIT_ORDER__SHIFT	28
+static inline uint32_t A2XX_PA_SC_LINE_STIPPLE_PATTERN_BIT_ORDER(enum a2xx_pa_sc_pattern_bit_order val)
+{
+	return ((val) << A2XX_PA_SC_LINE_STIPPLE_PATTERN_BIT_ORDER__SHIFT) & A2XX_PA_SC_LINE_STIPPLE_PATTERN_BIT_ORDER__MASK;
+}
+#define A2XX_PA_SC_LINE_STIPPLE_AUTO_RESET_CNTL__MASK		0x60000000
+#define A2XX_PA_SC_LINE_STIPPLE_AUTO_RESET_CNTL__SHIFT		29
+static inline uint32_t A2XX_PA_SC_LINE_STIPPLE_AUTO_RESET_CNTL(enum a2xx_pa_sc_auto_reset_cntl val)
+{
+	return ((val) << A2XX_PA_SC_LINE_STIPPLE_AUTO_RESET_CNTL__SHIFT) & A2XX_PA_SC_LINE_STIPPLE_AUTO_RESET_CNTL__MASK;
+}
+
+#define REG_A2XX_PA_SC_VIZ_QUERY				0x00002293
+
+#define REG_A2XX_VGT_ENHANCE					0x00002294
+
+#define REG_A2XX_PA_SC_LINE_CNTL				0x00002300
+#define A2XX_PA_SC_LINE_CNTL_BRES_CNTL__MASK			0x0000ffff
+#define A2XX_PA_SC_LINE_CNTL_BRES_CNTL__SHIFT			0
+static inline uint32_t A2XX_PA_SC_LINE_CNTL_BRES_CNTL(uint32_t val)
+{
+	return ((val) << A2XX_PA_SC_LINE_CNTL_BRES_CNTL__SHIFT) & A2XX_PA_SC_LINE_CNTL_BRES_CNTL__MASK;
+}
+#define A2XX_PA_SC_LINE_CNTL_USE_BRES_CNTL			0x00000100
+#define A2XX_PA_SC_LINE_CNTL_EXPAND_LINE_WIDTH			0x00000200
+#define A2XX_PA_SC_LINE_CNTL_LAST_PIXEL				0x00000400
+
+#define REG_A2XX_PA_SC_AA_CONFIG				0x00002301
+
+#define REG_A2XX_PA_SU_VTX_CNTL					0x00002302
+#define A2XX_PA_SU_VTX_CNTL_PIX_CENTER__MASK			0x00000001
+#define A2XX_PA_SU_VTX_CNTL_PIX_CENTER__SHIFT			0
+static inline uint32_t A2XX_PA_SU_VTX_CNTL_PIX_CENTER(enum a2xx_pa_pixcenter val)
+{
+	return ((val) << A2XX_PA_SU_VTX_CNTL_PIX_CENTER__SHIFT) & A2XX_PA_SU_VTX_CNTL_PIX_CENTER__MASK;
+}
+#define A2XX_PA_SU_VTX_CNTL_ROUND_MODE__MASK			0x00000006
+#define A2XX_PA_SU_VTX_CNTL_ROUND_MODE__SHIFT			1
+static inline uint32_t A2XX_PA_SU_VTX_CNTL_ROUND_MODE(enum a2xx_pa_roundmode val)
+{
+	return ((val) << A2XX_PA_SU_VTX_CNTL_ROUND_MODE__SHIFT) & A2XX_PA_SU_VTX_CNTL_ROUND_MODE__MASK;
+}
+#define A2XX_PA_SU_VTX_CNTL_QUANT_MODE__MASK			0x00000380
+#define A2XX_PA_SU_VTX_CNTL_QUANT_MODE__SHIFT			7
+static inline uint32_t A2XX_PA_SU_VTX_CNTL_QUANT_MODE(enum a2xx_pa_quantmode val)
+{
+	return ((val) << A2XX_PA_SU_VTX_CNTL_QUANT_MODE__SHIFT) & A2XX_PA_SU_VTX_CNTL_QUANT_MODE__MASK;
+}
+
+#define REG_A2XX_PA_CL_GB_VERT_CLIP_ADJ				0x00002303
+#define A2XX_PA_CL_GB_VERT_CLIP_ADJ__MASK			0xffffffff
+#define A2XX_PA_CL_GB_VERT_CLIP_ADJ__SHIFT			0
+static inline uint32_t A2XX_PA_CL_GB_VERT_CLIP_ADJ(float val)
+{
+	return ((fui(val)) << A2XX_PA_CL_GB_VERT_CLIP_ADJ__SHIFT) & A2XX_PA_CL_GB_VERT_CLIP_ADJ__MASK;
+}
+
+#define REG_A2XX_PA_CL_GB_VERT_DISC_ADJ				0x00002304
+#define A2XX_PA_CL_GB_VERT_DISC_ADJ__MASK			0xffffffff
+#define A2XX_PA_CL_GB_VERT_DISC_ADJ__SHIFT			0
+static inline uint32_t A2XX_PA_CL_GB_VERT_DISC_ADJ(float val)
+{
+	return ((fui(val)) << A2XX_PA_CL_GB_VERT_DISC_ADJ__SHIFT) & A2XX_PA_CL_GB_VERT_DISC_ADJ__MASK;
+}
+
+#define REG_A2XX_PA_CL_GB_HORZ_CLIP_ADJ				0x00002305
+#define A2XX_PA_CL_GB_HORZ_CLIP_ADJ__MASK			0xffffffff
+#define A2XX_PA_CL_GB_HORZ_CLIP_ADJ__SHIFT			0
+static inline uint32_t A2XX_PA_CL_GB_HORZ_CLIP_ADJ(float val)
+{
+	return ((fui(val)) << A2XX_PA_CL_GB_HORZ_CLIP_ADJ__SHIFT) & A2XX_PA_CL_GB_HORZ_CLIP_ADJ__MASK;
+}
+
+#define REG_A2XX_PA_CL_GB_HORZ_DISC_ADJ				0x00002306
+#define A2XX_PA_CL_GB_HORZ_DISC_ADJ__MASK			0xffffffff
+#define A2XX_PA_CL_GB_HORZ_DISC_ADJ__SHIFT			0
+static inline uint32_t A2XX_PA_CL_GB_HORZ_DISC_ADJ(float val)
+{
+	return ((fui(val)) << A2XX_PA_CL_GB_HORZ_DISC_ADJ__SHIFT) & A2XX_PA_CL_GB_HORZ_DISC_ADJ__MASK;
+}
+
+#define REG_A2XX_SQ_VS_CONST					0x00002307
+#define A2XX_SQ_VS_CONST_BASE__MASK				0x000001ff
+#define A2XX_SQ_VS_CONST_BASE__SHIFT				0
+static inline uint32_t A2XX_SQ_VS_CONST_BASE(uint32_t val)
+{
+	return ((val) << A2XX_SQ_VS_CONST_BASE__SHIFT) & A2XX_SQ_VS_CONST_BASE__MASK;
+}
+#define A2XX_SQ_VS_CONST_SIZE__MASK				0x001ff000
+#define A2XX_SQ_VS_CONST_SIZE__SHIFT				12
+static inline uint32_t A2XX_SQ_VS_CONST_SIZE(uint32_t val)
+{
+	return ((val) << A2XX_SQ_VS_CONST_SIZE__SHIFT) & A2XX_SQ_VS_CONST_SIZE__MASK;
+}
+
+#define REG_A2XX_SQ_PS_CONST					0x00002308
+#define A2XX_SQ_PS_CONST_BASE__MASK				0x000001ff
+#define A2XX_SQ_PS_CONST_BASE__SHIFT				0
+static inline uint32_t A2XX_SQ_PS_CONST_BASE(uint32_t val)
+{
+	return ((val) << A2XX_SQ_PS_CONST_BASE__SHIFT) & A2XX_SQ_PS_CONST_BASE__MASK;
+}
+#define A2XX_SQ_PS_CONST_SIZE__MASK				0x001ff000
+#define A2XX_SQ_PS_CONST_SIZE__SHIFT				12
+static inline uint32_t A2XX_SQ_PS_CONST_SIZE(uint32_t val)
+{
+	return ((val) << A2XX_SQ_PS_CONST_SIZE__SHIFT) & A2XX_SQ_PS_CONST_SIZE__MASK;
+}
+
+#define REG_A2XX_SQ_DEBUG_MISC_0				0x00002309
+
+#define REG_A2XX_SQ_DEBUG_MISC_1				0x0000230a
+
+#define REG_A2XX_PA_SC_AA_MASK					0x00002312
+
+#define REG_A2XX_VGT_VERTEX_REUSE_BLOCK_CNTL			0x00002316
+
+#define REG_A2XX_VGT_OUT_DEALLOC_CNTL				0x00002317
+
+#define REG_A2XX_RB_COPY_CONTROL				0x00002318
+#define A2XX_RB_COPY_CONTROL_COPY_SAMPLE_SELECT__MASK		0x00000007
+#define A2XX_RB_COPY_CONTROL_COPY_SAMPLE_SELECT__SHIFT		0
+static inline uint32_t A2XX_RB_COPY_CONTROL_COPY_SAMPLE_SELECT(enum a2xx_rb_copy_sample_select val)
+{
+	return ((val) << A2XX_RB_COPY_CONTROL_COPY_SAMPLE_SELECT__SHIFT) & A2XX_RB_COPY_CONTROL_COPY_SAMPLE_SELECT__MASK;
+}
+#define A2XX_RB_COPY_CONTROL_DEPTH_CLEAR_ENABLE			0x00000008
+#define A2XX_RB_COPY_CONTROL_CLEAR_MASK__MASK			0x000000f0
+#define A2XX_RB_COPY_CONTROL_CLEAR_MASK__SHIFT			4
+static inline uint32_t A2XX_RB_COPY_CONTROL_CLEAR_MASK(uint32_t val)
+{
+	return ((val) << A2XX_RB_COPY_CONTROL_CLEAR_MASK__SHIFT) & A2XX_RB_COPY_CONTROL_CLEAR_MASK__MASK;
+}
+
+#define REG_A2XX_RB_COPY_DEST_BASE				0x00002319
+
+#define REG_A2XX_RB_COPY_DEST_PITCH				0x0000231a
+#define A2XX_RB_COPY_DEST_PITCH__MASK				0xffffffff
+#define A2XX_RB_COPY_DEST_PITCH__SHIFT				0
+static inline uint32_t A2XX_RB_COPY_DEST_PITCH(uint32_t val)
+{
+	return ((val >> 5) << A2XX_RB_COPY_DEST_PITCH__SHIFT) & A2XX_RB_COPY_DEST_PITCH__MASK;
+}
+
+#define REG_A2XX_RB_COPY_DEST_INFO				0x0000231b
+#define A2XX_RB_COPY_DEST_INFO_DEST_ENDIAN__MASK		0x00000007
+#define A2XX_RB_COPY_DEST_INFO_DEST_ENDIAN__SHIFT		0
+static inline uint32_t A2XX_RB_COPY_DEST_INFO_DEST_ENDIAN(enum adreno_rb_surface_endian val)
+{
+	return ((val) << A2XX_RB_COPY_DEST_INFO_DEST_ENDIAN__SHIFT) & A2XX_RB_COPY_DEST_INFO_DEST_ENDIAN__MASK;
+}
+#define A2XX_RB_COPY_DEST_INFO_LINEAR				0x00000008
+#define A2XX_RB_COPY_DEST_INFO_FORMAT__MASK			0x000000f0
+#define A2XX_RB_COPY_DEST_INFO_FORMAT__SHIFT			4
+static inline uint32_t A2XX_RB_COPY_DEST_INFO_FORMAT(enum a2xx_colorformatx val)
+{
+	return ((val) << A2XX_RB_COPY_DEST_INFO_FORMAT__SHIFT) & A2XX_RB_COPY_DEST_INFO_FORMAT__MASK;
+}
+#define A2XX_RB_COPY_DEST_INFO_SWAP__MASK			0x00000300
+#define A2XX_RB_COPY_DEST_INFO_SWAP__SHIFT			8
+static inline uint32_t A2XX_RB_COPY_DEST_INFO_SWAP(uint32_t val)
+{
+	return ((val) << A2XX_RB_COPY_DEST_INFO_SWAP__SHIFT) & A2XX_RB_COPY_DEST_INFO_SWAP__MASK;
+}
+#define A2XX_RB_COPY_DEST_INFO_DITHER_MODE__MASK		0x00000c00
+#define A2XX_RB_COPY_DEST_INFO_DITHER_MODE__SHIFT		10
+static inline uint32_t A2XX_RB_COPY_DEST_INFO_DITHER_MODE(enum adreno_rb_dither_mode val)
+{
+	return ((val) << A2XX_RB_COPY_DEST_INFO_DITHER_MODE__SHIFT) & A2XX_RB_COPY_DEST_INFO_DITHER_MODE__MASK;
+}
+#define A2XX_RB_COPY_DEST_INFO_DITHER_TYPE__MASK		0x00003000
+#define A2XX_RB_COPY_DEST_INFO_DITHER_TYPE__SHIFT		12
+static inline uint32_t A2XX_RB_COPY_DEST_INFO_DITHER_TYPE(enum a2xx_rb_dither_type val)
+{
+	return ((val) << A2XX_RB_COPY_DEST_INFO_DITHER_TYPE__SHIFT) & A2XX_RB_COPY_DEST_INFO_DITHER_TYPE__MASK;
+}
+#define A2XX_RB_COPY_DEST_INFO_WRITE_RED			0x00004000
+#define A2XX_RB_COPY_DEST_INFO_WRITE_GREEN			0x00008000
+#define A2XX_RB_COPY_DEST_INFO_WRITE_BLUE			0x00010000
+#define A2XX_RB_COPY_DEST_INFO_WRITE_ALPHA			0x00020000
+
+#define REG_A2XX_RB_COPY_DEST_OFFSET				0x0000231c
+#define A2XX_RB_COPY_DEST_OFFSET_X__MASK			0x00001fff
+#define A2XX_RB_COPY_DEST_OFFSET_X__SHIFT			0
+static inline uint32_t A2XX_RB_COPY_DEST_OFFSET_X(uint32_t val)
+{
+	return ((val) << A2XX_RB_COPY_DEST_OFFSET_X__SHIFT) & A2XX_RB_COPY_DEST_OFFSET_X__MASK;
+}
+#define A2XX_RB_COPY_DEST_OFFSET_Y__MASK			0x03ffe000
+#define A2XX_RB_COPY_DEST_OFFSET_Y__SHIFT			13
+static inline uint32_t A2XX_RB_COPY_DEST_OFFSET_Y(uint32_t val)
+{
+	return ((val) << A2XX_RB_COPY_DEST_OFFSET_Y__SHIFT) & A2XX_RB_COPY_DEST_OFFSET_Y__MASK;
+}
+
+#define REG_A2XX_RB_DEPTH_CLEAR					0x0000231d
+
+#define REG_A2XX_RB_SAMPLE_COUNT_CTL				0x00002324
+
+#define REG_A2XX_RB_COLOR_DEST_MASK				0x00002326
+
+#define REG_A2XX_A225_GRAS_UCP0X				0x00002340
+
+#define REG_A2XX_A225_GRAS_UCP5W				0x00002357
+
+#define REG_A2XX_A225_GRAS_UCP_ENABLED				0x00002360
+
+#define REG_A2XX_PA_SU_POLY_OFFSET_FRONT_SCALE			0x00002380
+
+#define REG_A2XX_PA_SU_POLY_OFFSET_BACK_OFFSET			0x00002383
+
+#define REG_A2XX_SQ_CONSTANT_0					0x00004000
+
+#define REG_A2XX_SQ_FETCH_0					0x00004800
+
+#define REG_A2XX_SQ_CF_BOOLEANS					0x00004900
+
+#define REG_A2XX_SQ_CF_LOOP					0x00004908
+
+#define REG_A2XX_COHER_SIZE_PM4					0x00000a29
+
+#define REG_A2XX_COHER_BASE_PM4					0x00000a2a
+
+#define REG_A2XX_COHER_STATUS_PM4				0x00000a2b
+
+#define REG_A2XX_SQ_TEX_0					0x00000000
+#define A2XX_SQ_TEX_0_CLAMP_X__MASK				0x00001c00
+#define A2XX_SQ_TEX_0_CLAMP_X__SHIFT				10
+static inline uint32_t A2XX_SQ_TEX_0_CLAMP_X(enum sq_tex_clamp val)
+{
+	return ((val) << A2XX_SQ_TEX_0_CLAMP_X__SHIFT) & A2XX_SQ_TEX_0_CLAMP_X__MASK;
+}
+#define A2XX_SQ_TEX_0_CLAMP_Y__MASK				0x0000e000
+#define A2XX_SQ_TEX_0_CLAMP_Y__SHIFT				13
+static inline uint32_t A2XX_SQ_TEX_0_CLAMP_Y(enum sq_tex_clamp val)
+{
+	return ((val) << A2XX_SQ_TEX_0_CLAMP_Y__SHIFT) & A2XX_SQ_TEX_0_CLAMP_Y__MASK;
+}
+#define A2XX_SQ_TEX_0_CLAMP_Z__MASK				0x00070000
+#define A2XX_SQ_TEX_0_CLAMP_Z__SHIFT				16
+static inline uint32_t A2XX_SQ_TEX_0_CLAMP_Z(enum sq_tex_clamp val)
+{
+	return ((val) << A2XX_SQ_TEX_0_CLAMP_Z__SHIFT) & A2XX_SQ_TEX_0_CLAMP_Z__MASK;
+}
+#define A2XX_SQ_TEX_0_PITCH__MASK				0xffc00000
+#define A2XX_SQ_TEX_0_PITCH__SHIFT				22
+static inline uint32_t A2XX_SQ_TEX_0_PITCH(uint32_t val)
+{
+	return ((val >> 5) << A2XX_SQ_TEX_0_PITCH__SHIFT) & A2XX_SQ_TEX_0_PITCH__MASK;
+}
+
+#define REG_A2XX_SQ_TEX_1					0x00000001
+
+#define REG_A2XX_SQ_TEX_2					0x00000002
+#define A2XX_SQ_TEX_2_WIDTH__MASK				0x00001fff
+#define A2XX_SQ_TEX_2_WIDTH__SHIFT				0
+static inline uint32_t A2XX_SQ_TEX_2_WIDTH(uint32_t val)
+{
+	return ((val) << A2XX_SQ_TEX_2_WIDTH__SHIFT) & A2XX_SQ_TEX_2_WIDTH__MASK;
+}
+#define A2XX_SQ_TEX_2_HEIGHT__MASK				0x03ffe000
+#define A2XX_SQ_TEX_2_HEIGHT__SHIFT				13
+static inline uint32_t A2XX_SQ_TEX_2_HEIGHT(uint32_t val)
+{
+	return ((val) << A2XX_SQ_TEX_2_HEIGHT__SHIFT) & A2XX_SQ_TEX_2_HEIGHT__MASK;
+}
+
+#define REG_A2XX_SQ_TEX_3					0x00000003
+#define A2XX_SQ_TEX_3_SWIZ_X__MASK				0x0000000e
+#define A2XX_SQ_TEX_3_SWIZ_X__SHIFT				1
+static inline uint32_t A2XX_SQ_TEX_3_SWIZ_X(enum sq_tex_swiz val)
+{
+	return ((val) << A2XX_SQ_TEX_3_SWIZ_X__SHIFT) & A2XX_SQ_TEX_3_SWIZ_X__MASK;
+}
+#define A2XX_SQ_TEX_3_SWIZ_Y__MASK				0x00000070
+#define A2XX_SQ_TEX_3_SWIZ_Y__SHIFT				4
+static inline uint32_t A2XX_SQ_TEX_3_SWIZ_Y(enum sq_tex_swiz val)
+{
+	return ((val) << A2XX_SQ_TEX_3_SWIZ_Y__SHIFT) & A2XX_SQ_TEX_3_SWIZ_Y__MASK;
+}
+#define A2XX_SQ_TEX_3_SWIZ_Z__MASK				0x00000380
+#define A2XX_SQ_TEX_3_SWIZ_Z__SHIFT				7
+static inline uint32_t A2XX_SQ_TEX_3_SWIZ_Z(enum sq_tex_swiz val)
+{
+	return ((val) << A2XX_SQ_TEX_3_SWIZ_Z__SHIFT) & A2XX_SQ_TEX_3_SWIZ_Z__MASK;
+}
+#define A2XX_SQ_TEX_3_SWIZ_W__MASK				0x00001c00
+#define A2XX_SQ_TEX_3_SWIZ_W__SHIFT				10
+static inline uint32_t A2XX_SQ_TEX_3_SWIZ_W(enum sq_tex_swiz val)
+{
+	return ((val) << A2XX_SQ_TEX_3_SWIZ_W__SHIFT) & A2XX_SQ_TEX_3_SWIZ_W__MASK;
+}
+#define A2XX_SQ_TEX_3_XY_MAG_FILTER__MASK			0x00180000
+#define A2XX_SQ_TEX_3_XY_MAG_FILTER__SHIFT			19
+static inline uint32_t A2XX_SQ_TEX_3_XY_MAG_FILTER(enum sq_tex_filter val)
+{
+	return ((val) << A2XX_SQ_TEX_3_XY_MAG_FILTER__SHIFT) & A2XX_SQ_TEX_3_XY_MAG_FILTER__MASK;
+}
+#define A2XX_SQ_TEX_3_XY_MIN_FILTER__MASK			0x00600000
+#define A2XX_SQ_TEX_3_XY_MIN_FILTER__SHIFT			21
+static inline uint32_t A2XX_SQ_TEX_3_XY_MIN_FILTER(enum sq_tex_filter val)
+{
+	return ((val) << A2XX_SQ_TEX_3_XY_MIN_FILTER__SHIFT) & A2XX_SQ_TEX_3_XY_MIN_FILTER__MASK;
+}
+
+
+#endif /* A2XX_XML */
diff --git a/drivers/gpu/drm/msm/adreno/a3xx.xml.h b/drivers/gpu/drm/msm/adreno/a3xx.xml.h
new file mode 100644
index 000000000000..d183516067b4
--- /dev/null
+++ b/drivers/gpu/drm/msm/adreno/a3xx.xml.h
@@ -0,0 +1,2193 @@
+#ifndef A3XX_XML
+#define A3XX_XML
+
+/* Autogenerated file, DO NOT EDIT manually!
+
+This file was generated by the rules-ng-ng headergen tool in this git repository:
+http://0x04.net/cgit/index.cgi/rules-ng-ng
+git clone git://0x04.net/rules-ng-ng
+
+The rules-ng-ng source files this header was generated from are:
+- /home/robclark/src/freedreno/envytools/rnndb/adreno.xml              (    327 bytes, from 2013-07-05 19:21:12)
+- /home/robclark/src/freedreno/envytools/rnndb/freedreno_copyright.xml (   1453 bytes, from 2013-03-31 16:51:27)
+- /home/robclark/src/freedreno/envytools/rnndb/a2xx/a2xx.xml           (  30005 bytes, from 2013-07-19 21:30:48)
+- /home/robclark/src/freedreno/envytools/rnndb/adreno_common.xml       (   8983 bytes, from 2013-07-24 01:38:36)
+- /home/robclark/src/freedreno/envytools/rnndb/adreno_pm4.xml          (   9712 bytes, from 2013-05-26 15:22:37)
+- /home/robclark/src/freedreno/envytools/rnndb/a3xx/a3xx.xml           (  51415 bytes, from 2013-08-03 14:26:05)
+
+Copyright (C) 2013 by the following authors:
+- Rob Clark <robdclark@gmail.com> (robclark)
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice (including the
+next paragraph) shall be included in all copies or substantial
+portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
+IN NO EVENT SHALL THE COPYRIGHT OWNER(S) AND/OR ITS SUPPLIERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+*/
+
+
+enum a3xx_render_mode {
+	RB_RENDERING_PASS = 0,
+	RB_TILING_PASS = 1,
+	RB_RESOLVE_PASS = 2,
+};
+
+enum a3xx_tile_mode {
+	LINEAR = 0,
+	TILE_32X32 = 2,
+};
+
+enum a3xx_threadmode {
+	MULTI = 0,
+	SINGLE = 1,
+};
+
+enum a3xx_instrbuffermode {
+	BUFFER = 1,
+};
+
+enum a3xx_threadsize {
+	TWO_QUADS = 0,
+	FOUR_QUADS = 1,
+};
+
+enum a3xx_state_block_id {
+	HLSQ_BLOCK_ID_TP_TEX = 2,
+	HLSQ_BLOCK_ID_TP_MIPMAP = 3,
+	HLSQ_BLOCK_ID_SP_VS = 4,
+	HLSQ_BLOCK_ID_SP_FS = 6,
+};
+
+enum a3xx_cache_opcode {
+	INVALIDATE = 1,
+};
+
+enum a3xx_vtx_fmt {
+	VFMT_FLOAT_32 = 0,
+	VFMT_FLOAT_32_32 = 1,
+	VFMT_FLOAT_32_32_32 = 2,
+	VFMT_FLOAT_32_32_32_32 = 3,
+	VFMT_FLOAT_16 = 4,
+	VFMT_FLOAT_16_16 = 5,
+	VFMT_FLOAT_16_16_16 = 6,
+	VFMT_FLOAT_16_16_16_16 = 7,
+	VFMT_FIXED_32 = 8,
+	VFMT_FIXED_32_32 = 9,
+	VFMT_FIXED_32_32_32 = 10,
+	VFMT_FIXED_32_32_32_32 = 11,
+	VFMT_SHORT_16 = 16,
+	VFMT_SHORT_16_16 = 17,
+	VFMT_SHORT_16_16_16 = 18,
+	VFMT_SHORT_16_16_16_16 = 19,
+	VFMT_USHORT_16 = 20,
+	VFMT_USHORT_16_16 = 21,
+	VFMT_USHORT_16_16_16 = 22,
+	VFMT_USHORT_16_16_16_16 = 23,
+	VFMT_NORM_SHORT_16 = 24,
+	VFMT_NORM_SHORT_16_16 = 25,
+	VFMT_NORM_SHORT_16_16_16 = 26,
+	VFMT_NORM_SHORT_16_16_16_16 = 27,
+	VFMT_NORM_USHORT_16 = 28,
+	VFMT_NORM_USHORT_16_16 = 29,
+	VFMT_NORM_USHORT_16_16_16 = 30,
+	VFMT_NORM_USHORT_16_16_16_16 = 31,
+	VFMT_UBYTE_8 = 40,
+	VFMT_UBYTE_8_8 = 41,
+	VFMT_UBYTE_8_8_8 = 42,
+	VFMT_UBYTE_8_8_8_8 = 43,
+	VFMT_NORM_UBYTE_8 = 44,
+	VFMT_NORM_UBYTE_8_8 = 45,
+	VFMT_NORM_UBYTE_8_8_8 = 46,
+	VFMT_NORM_UBYTE_8_8_8_8 = 47,
+	VFMT_BYTE_8 = 48,
+	VFMT_BYTE_8_8 = 49,
+	VFMT_BYTE_8_8_8 = 50,
+	VFMT_BYTE_8_8_8_8 = 51,
+	VFMT_NORM_BYTE_8 = 52,
+	VFMT_NORM_BYTE_8_8 = 53,
+	VFMT_NORM_BYTE_8_8_8 = 54,
+	VFMT_NORM_BYTE_8_8_8_8 = 55,
+	VFMT_UINT_10_10_10_2 = 60,
+	VFMT_NORM_UINT_10_10_10_2 = 61,
+	VFMT_INT_10_10_10_2 = 62,
+	VFMT_NORM_INT_10_10_10_2 = 63,
+};
+
+enum a3xx_tex_fmt {
+	TFMT_NORM_USHORT_565 = 4,
+	TFMT_NORM_USHORT_5551 = 6,
+	TFMT_NORM_USHORT_4444 = 7,
+	TFMT_NORM_UINT_X8Z24 = 10,
+	TFMT_NORM_UINT_NV12_UV_TILED = 17,
+	TFMT_NORM_UINT_NV12_Y_TILED = 19,
+	TFMT_NORM_UINT_NV12_UV = 21,
+	TFMT_NORM_UINT_NV12_Y = 23,
+	TFMT_NORM_UINT_I420_Y = 24,
+	TFMT_NORM_UINT_I420_U = 26,
+	TFMT_NORM_UINT_I420_V = 27,
+	TFMT_NORM_UINT_2_10_10_10 = 41,
+	TFMT_NORM_UINT_A8 = 44,
+	TFMT_NORM_UINT_L8_A8 = 47,
+	TFMT_NORM_UINT_8 = 48,
+	TFMT_NORM_UINT_8_8 = 49,
+	TFMT_NORM_UINT_8_8_8 = 50,
+	TFMT_NORM_UINT_8_8_8_8 = 51,
+	TFMT_FLOAT_16 = 64,
+	TFMT_FLOAT_16_16 = 65,
+	TFMT_FLOAT_16_16_16_16 = 67,
+	TFMT_FLOAT_32 = 84,
+	TFMT_FLOAT_32_32 = 85,
+	TFMT_FLOAT_32_32_32_32 = 87,
+};
+
+enum a3xx_tex_fetchsize {
+	TFETCH_DISABLE = 0,
+	TFETCH_1_BYTE = 1,
+	TFETCH_2_BYTE = 2,
+	TFETCH_4_BYTE = 3,
+	TFETCH_8_BYTE = 4,
+	TFETCH_16_BYTE = 5,
+};
+
+enum a3xx_color_fmt {
+	RB_R8G8B8_UNORM = 4,
+	RB_R8G8B8A8_UNORM = 8,
+	RB_Z16_UNORM = 12,
+	RB_A8_UNORM = 20,
+};
+
+enum a3xx_color_swap {
+	WZYX = 0,
+	WXYZ = 1,
+	ZYXW = 2,
+	XYZW = 3,
+};
+
+enum a3xx_msaa_samples {
+	MSAA_ONE = 0,
+	MSAA_TWO = 1,
+	MSAA_FOUR = 2,
+};
+
+enum a3xx_sp_perfcounter_select {
+	SP_FS_CFLOW_INSTRUCTIONS = 12,
+	SP_FS_FULL_ALU_INSTRUCTIONS = 14,
+	SP0_ICL1_MISSES = 26,
+	SP_ALU_ACTIVE_CYCLES = 29,
+};
+
+enum adreno_rb_copy_control_mode {
+	RB_COPY_RESOLVE = 1,
+	RB_COPY_DEPTH_STENCIL = 5,
+};
+
+enum a3xx_tex_filter {
+	A3XX_TEX_NEAREST = 0,
+	A3XX_TEX_LINEAR = 1,
+};
+
+enum a3xx_tex_clamp {
+	A3XX_TEX_REPEAT = 0,
+	A3XX_TEX_CLAMP_TO_EDGE = 1,
+	A3XX_TEX_MIRROR_REPEAT = 2,
+	A3XX_TEX_CLAMP_NONE = 3,
+};
+
+enum a3xx_tex_swiz {
+	A3XX_TEX_X = 0,
+	A3XX_TEX_Y = 1,
+	A3XX_TEX_Z = 2,
+	A3XX_TEX_W = 3,
+	A3XX_TEX_ZERO = 4,
+	A3XX_TEX_ONE = 5,
+};
+
+enum a3xx_tex_type {
+	A3XX_TEX_1D = 0,
+	A3XX_TEX_2D = 1,
+	A3XX_TEX_CUBE = 2,
+	A3XX_TEX_3D = 3,
+};
+
+#define A3XX_INT0_RBBM_GPU_IDLE					0x00000001
+#define A3XX_INT0_RBBM_AHB_ERROR				0x00000002
+#define A3XX_INT0_RBBM_REG_TIMEOUT				0x00000004
+#define A3XX_INT0_RBBM_ME_MS_TIMEOUT				0x00000008
+#define A3XX_INT0_RBBM_PFP_MS_TIMEOUT				0x00000010
+#define A3XX_INT0_RBBM_ATB_BUS_OVERFLOW				0x00000020
+#define A3XX_INT0_VFD_ERROR					0x00000040
+#define A3XX_INT0_CP_SW_INT					0x00000080
+#define A3XX_INT0_CP_T0_PACKET_IN_IB				0x00000100
+#define A3XX_INT0_CP_OPCODE_ERROR				0x00000200
+#define A3XX_INT0_CP_RESERVED_BIT_ERROR				0x00000400
+#define A3XX_INT0_CP_HW_FAULT					0x00000800
+#define A3XX_INT0_CP_DMA					0x00001000
+#define A3XX_INT0_CP_IB2_INT					0x00002000
+#define A3XX_INT0_CP_IB1_INT					0x00004000
+#define A3XX_INT0_CP_RB_INT					0x00008000
+#define A3XX_INT0_CP_REG_PROTECT_FAULT				0x00010000
+#define A3XX_INT0_CP_RB_DONE_TS					0x00020000
+#define A3XX_INT0_CP_VS_DONE_TS					0x00040000
+#define A3XX_INT0_CP_PS_DONE_TS					0x00080000
+#define A3XX_INT0_CACHE_FLUSH_TS				0x00100000
+#define A3XX_INT0_CP_AHB_ERROR_HALT				0x00200000
+#define A3XX_INT0_MISC_HANG_DETECT				0x01000000
+#define A3XX_INT0_UCHE_OOB_ACCESS				0x02000000
+#define REG_A3XX_RBBM_HW_VERSION				0x00000000
+
+#define REG_A3XX_RBBM_HW_RELEASE				0x00000001
+
+#define REG_A3XX_RBBM_HW_CONFIGURATION				0x00000002
+
+#define REG_A3XX_RBBM_CLOCK_CTL					0x00000010
+
+#define REG_A3XX_RBBM_SP_HYST_CNT				0x00000012
+
+#define REG_A3XX_RBBM_SW_RESET_CMD				0x00000018
+
+#define REG_A3XX_RBBM_AHB_CTL0					0x00000020
+
+#define REG_A3XX_RBBM_AHB_CTL1					0x00000021
+
+#define REG_A3XX_RBBM_AHB_CMD					0x00000022
+
+#define REG_A3XX_RBBM_AHB_ERROR_STATUS				0x00000027
+
+#define REG_A3XX_RBBM_GPR0_CTL					0x0000002e
+
+#define REG_A3XX_RBBM_STATUS					0x00000030
+#define A3XX_RBBM_STATUS_HI_BUSY				0x00000001
+#define A3XX_RBBM_STATUS_CP_ME_BUSY				0x00000002
+#define A3XX_RBBM_STATUS_CP_PFP_BUSY				0x00000004
+#define A3XX_RBBM_STATUS_CP_NRT_BUSY				0x00004000
+#define A3XX_RBBM_STATUS_VBIF_BUSY				0x00008000
+#define A3XX_RBBM_STATUS_TSE_BUSY				0x00010000
+#define A3XX_RBBM_STATUS_RAS_BUSY				0x00020000
+#define A3XX_RBBM_STATUS_RB_BUSY				0x00040000
+#define A3XX_RBBM_STATUS_PC_DCALL_BUSY				0x00080000
+#define A3XX_RBBM_STATUS_PC_VSD_BUSY				0x00100000
+#define A3XX_RBBM_STATUS_VFD_BUSY				0x00200000
+#define A3XX_RBBM_STATUS_VPC_BUSY				0x00400000
+#define A3XX_RBBM_STATUS_UCHE_BUSY				0x00800000
+#define A3XX_RBBM_STATUS_SP_BUSY				0x01000000
+#define A3XX_RBBM_STATUS_TPL1_BUSY				0x02000000
+#define A3XX_RBBM_STATUS_MARB_BUSY				0x04000000
+#define A3XX_RBBM_STATUS_VSC_BUSY				0x08000000
+#define A3XX_RBBM_STATUS_ARB_BUSY				0x10000000
+#define A3XX_RBBM_STATUS_HLSQ_BUSY				0x20000000
+#define A3XX_RBBM_STATUS_GPU_BUSY_NOHC				0x40000000
+#define A3XX_RBBM_STATUS_GPU_BUSY				0x80000000
+
+#define REG_A3XX_RBBM_WAIT_IDLE_CLOCKS_CTL			0x00000033
+
+#define REG_A3XX_RBBM_INTERFACE_HANG_INT_CTL			0x00000050
+
+#define REG_A3XX_RBBM_INTERFACE_HANG_MASK_CTL0			0x00000051
+
+#define REG_A3XX_RBBM_INTERFACE_HANG_MASK_CTL1			0x00000054
+
+#define REG_A3XX_RBBM_INTERFACE_HANG_MASK_CTL2			0x00000057
+
+#define REG_A3XX_RBBM_INTERFACE_HANG_MASK_CTL3			0x0000005a
+
+#define REG_A3XX_RBBM_INT_CLEAR_CMD				0x00000061
+
+#define REG_A3XX_RBBM_INT_0_MASK				0x00000063
+
+#define REG_A3XX_RBBM_INT_0_STATUS				0x00000064
+
+#define REG_A3XX_RBBM_PERFCTR_CTL				0x00000080
+
+#define REG_A3XX_RBBM_PERFCTR_LOAD_CMD0				0x00000081
+
+#define REG_A3XX_RBBM_PERFCTR_LOAD_CMD1				0x00000082
+
+#define REG_A3XX_RBBM_PERFCTR_LOAD_VALUE_LO			0x00000084
+
+#define REG_A3XX_RBBM_PERFCTR_LOAD_VALUE_HI			0x00000085
+
+#define REG_A3XX_RBBM_PERFCOUNTER0_SELECT			0x00000086
+
+#define REG_A3XX_RBBM_PERFCOUNTER1_SELECT			0x00000087
+
+#define REG_A3XX_RBBM_GPU_BUSY_MASKED				0x00000088
+
+#define REG_A3XX_RBBM_PERFCTR_CP_0_LO				0x00000090
+
+#define REG_A3XX_RBBM_PERFCTR_CP_0_HI				0x00000091
+
+#define REG_A3XX_RBBM_PERFCTR_RBBM_0_LO				0x00000092
+
+#define REG_A3XX_RBBM_PERFCTR_RBBM_0_HI				0x00000093
+
+#define REG_A3XX_RBBM_PERFCTR_RBBM_1_LO				0x00000094
+
+#define REG_A3XX_RBBM_PERFCTR_RBBM_1_HI				0x00000095
+
+#define REG_A3XX_RBBM_PERFCTR_PC_0_LO				0x00000096
+
+#define REG_A3XX_RBBM_PERFCTR_PC_0_HI				0x00000097
+
+#define REG_A3XX_RBBM_PERFCTR_PC_1_LO				0x00000098
+
+#define REG_A3XX_RBBM_PERFCTR_PC_1_HI				0x00000099
+
+#define REG_A3XX_RBBM_PERFCTR_PC_2_LO				0x0000009a
+
+#define REG_A3XX_RBBM_PERFCTR_PC_2_HI				0x0000009b
+
+#define REG_A3XX_RBBM_PERFCTR_PC_3_LO				0x0000009c
+
+#define REG_A3XX_RBBM_PERFCTR_PC_3_HI				0x0000009d
+
+#define REG_A3XX_RBBM_PERFCTR_VFD_0_LO				0x0000009e
+
+#define REG_A3XX_RBBM_PERFCTR_VFD_0_HI				0x0000009f
+
+#define REG_A3XX_RBBM_PERFCTR_VFD_1_LO				0x000000a0
+
+#define REG_A3XX_RBBM_PERFCTR_VFD_1_HI				0x000000a1
+
+#define REG_A3XX_RBBM_PERFCTR_HLSQ_0_LO				0x000000a2
+
+#define REG_A3XX_RBBM_PERFCTR_HLSQ_0_HI				0x000000a3
+
+#define REG_A3XX_RBBM_PERFCTR_HLSQ_1_LO				0x000000a4
+
+#define REG_A3XX_RBBM_PERFCTR_HLSQ_1_HI				0x000000a5
+
+#define REG_A3XX_RBBM_PERFCTR_HLSQ_2_LO				0x000000a6
+
+#define REG_A3XX_RBBM_PERFCTR_HLSQ_2_HI				0x000000a7
+
+#define REG_A3XX_RBBM_PERFCTR_HLSQ_3_LO				0x000000a8
+
+#define REG_A3XX_RBBM_PERFCTR_HLSQ_3_HI				0x000000a9
+
+#define REG_A3XX_RBBM_PERFCTR_HLSQ_4_LO				0x000000aa
+
+#define REG_A3XX_RBBM_PERFCTR_HLSQ_4_HI				0x000000ab
+
+#define REG_A3XX_RBBM_PERFCTR_HLSQ_5_LO				0x000000ac
+
+#define REG_A3XX_RBBM_PERFCTR_HLSQ_5_HI				0x000000ad
+
+#define REG_A3XX_RBBM_PERFCTR_VPC_0_LO				0x000000ae
+
+#define REG_A3XX_RBBM_PERFCTR_VPC_0_HI				0x000000af
+
+#define REG_A3XX_RBBM_PERFCTR_VPC_1_LO				0x000000b0
+
+#define REG_A3XX_RBBM_PERFCTR_VPC_1_HI				0x000000b1
+
+#define REG_A3XX_RBBM_PERFCTR_TSE_0_LO				0x000000b2
+
+#define REG_A3XX_RBBM_PERFCTR_TSE_0_HI				0x000000b3
+
+#define REG_A3XX_RBBM_PERFCTR_TSE_1_LO				0x000000b4
+
+#define REG_A3XX_RBBM_PERFCTR_TSE_1_HI				0x000000b5
+
+#define REG_A3XX_RBBM_PERFCTR_RAS_0_LO				0x000000b6
+
+#define REG_A3XX_RBBM_PERFCTR_RAS_0_HI				0x000000b7
+
+#define REG_A3XX_RBBM_PERFCTR_RAS_1_LO				0x000000b8
+
+#define REG_A3XX_RBBM_PERFCTR_RAS_1_HI				0x000000b9
+
+#define REG_A3XX_RBBM_PERFCTR_UCHE_0_LO				0x000000ba
+
+#define REG_A3XX_RBBM_PERFCTR_UCHE_0_HI				0x000000bb
+
+#define REG_A3XX_RBBM_PERFCTR_UCHE_1_LO				0x000000bc
+
+#define REG_A3XX_RBBM_PERFCTR_UCHE_1_HI				0x000000bd
+
+#define REG_A3XX_RBBM_PERFCTR_UCHE_2_LO				0x000000be
+
+#define REG_A3XX_RBBM_PERFCTR_UCHE_2_HI				0x000000bf
+
+#define REG_A3XX_RBBM_PERFCTR_UCHE_3_LO				0x000000c0
+
+#define REG_A3XX_RBBM_PERFCTR_UCHE_3_HI				0x000000c1
+
+#define REG_A3XX_RBBM_PERFCTR_UCHE_4_LO				0x000000c2
+
+#define REG_A3XX_RBBM_PERFCTR_UCHE_4_HI				0x000000c3
+
+#define REG_A3XX_RBBM_PERFCTR_UCHE_5_LO				0x000000c4
+
+#define REG_A3XX_RBBM_PERFCTR_UCHE_5_HI				0x000000c5
+
+#define REG_A3XX_RBBM_PERFCTR_TP_0_LO				0x000000c6
+
+#define REG_A3XX_RBBM_PERFCTR_TP_0_HI				0x000000c7
+
+#define REG_A3XX_RBBM_PERFCTR_TP_1_LO				0x000000c8
+
+#define REG_A3XX_RBBM_PERFCTR_TP_1_HI				0x000000c9
+
+#define REG_A3XX_RBBM_PERFCTR_TP_2_LO				0x000000ca
+
+#define REG_A3XX_RBBM_PERFCTR_TP_2_HI				0x000000cb
+
+#define REG_A3XX_RBBM_PERFCTR_TP_3_LO				0x000000cc
+
+#define REG_A3XX_RBBM_PERFCTR_TP_3_HI				0x000000cd
+
+#define REG_A3XX_RBBM_PERFCTR_TP_4_LO				0x000000ce
+
+#define REG_A3XX_RBBM_PERFCTR_TP_4_HI				0x000000cf
+
+#define REG_A3XX_RBBM_PERFCTR_TP_5_LO				0x000000d0
+
+#define REG_A3XX_RBBM_PERFCTR_TP_5_HI				0x000000d1
+
+#define REG_A3XX_RBBM_PERFCTR_SP_0_LO				0x000000d2
+
+#define REG_A3XX_RBBM_PERFCTR_SP_0_HI				0x000000d3
+
+#define REG_A3XX_RBBM_PERFCTR_SP_1_LO				0x000000d4
+
+#define REG_A3XX_RBBM_PERFCTR_SP_1_HI				0x000000d5
+
+#define REG_A3XX_RBBM_PERFCTR_SP_2_LO				0x000000d6
+
+#define REG_A3XX_RBBM_PERFCTR_SP_2_HI				0x000000d7
+
+#define REG_A3XX_RBBM_PERFCTR_SP_3_LO				0x000000d8
+
+#define REG_A3XX_RBBM_PERFCTR_SP_3_HI				0x000000d9
+
+#define REG_A3XX_RBBM_PERFCTR_SP_4_LO				0x000000da
+
+#define REG_A3XX_RBBM_PERFCTR_SP_4_HI				0x000000db
+
+#define REG_A3XX_RBBM_PERFCTR_SP_5_LO				0x000000dc
+
+#define REG_A3XX_RBBM_PERFCTR_SP_5_HI				0x000000dd
+
+#define REG_A3XX_RBBM_PERFCTR_SP_6_LO				0x000000de
+
+#define REG_A3XX_RBBM_PERFCTR_SP_6_HI				0x000000df
+
+#define REG_A3XX_RBBM_PERFCTR_SP_7_LO				0x000000e0
+
+#define REG_A3XX_RBBM_PERFCTR_SP_7_HI				0x000000e1
+
+#define REG_A3XX_RBBM_PERFCTR_RB_0_LO				0x000000e2
+
+#define REG_A3XX_RBBM_PERFCTR_RB_0_HI				0x000000e3
+
+#define REG_A3XX_RBBM_PERFCTR_RB_1_LO				0x000000e4
+
+#define REG_A3XX_RBBM_PERFCTR_RB_1_HI				0x000000e5
+
+#define REG_A3XX_RBBM_PERFCTR_PWR_0_LO				0x000000ea
+
+#define REG_A3XX_RBBM_PERFCTR_PWR_0_HI				0x000000eb
+
+#define REG_A3XX_RBBM_PERFCTR_PWR_1_LO				0x000000ec
+
+#define REG_A3XX_RBBM_PERFCTR_PWR_1_HI				0x000000ed
+
+#define REG_A3XX_RBBM_RBBM_CTL					0x00000100
+
+#define REG_A3XX_RBBM_DEBUG_BUS_CTL				0x00000111
+
+#define REG_A3XX_RBBM_DEBUG_BUS_DATA_STATUS			0x00000112
+
+#define REG_A3XX_CP_PFP_UCODE_ADDR				0x000001c9
+
+#define REG_A3XX_CP_PFP_UCODE_DATA				0x000001ca
+
+#define REG_A3XX_CP_ROQ_ADDR					0x000001cc
+
+#define REG_A3XX_CP_ROQ_DATA					0x000001cd
+
+#define REG_A3XX_CP_MERCIU_ADDR					0x000001d1
+
+#define REG_A3XX_CP_MERCIU_DATA					0x000001d2
+
+#define REG_A3XX_CP_MERCIU_DATA2				0x000001d3
+
+#define REG_A3XX_CP_MEQ_ADDR					0x000001da
+
+#define REG_A3XX_CP_MEQ_DATA					0x000001db
+
+#define REG_A3XX_CP_PERFCOUNTER_SELECT				0x00000445
+
+#define REG_A3XX_CP_HW_FAULT					0x0000045c
+
+#define REG_A3XX_CP_PROTECT_CTRL				0x0000045e
+
+#define REG_A3XX_CP_PROTECT_STATUS				0x0000045f
+
+static inline uint32_t REG_A3XX_CP_PROTECT(uint32_t i0) { return 0x00000460 + 0x1*i0; }
+
+static inline uint32_t REG_A3XX_CP_PROTECT_REG(uint32_t i0) { return 0x00000460 + 0x1*i0; }
+
+#define REG_A3XX_CP_AHB_FAULT					0x0000054d
+
+#define REG_A3XX_GRAS_CL_CLIP_CNTL				0x00002040
+#define A3XX_GRAS_CL_CLIP_CNTL_IJ_PERSP_CENTER			0x00001000
+#define A3XX_GRAS_CL_CLIP_CNTL_CLIP_DISABLE			0x00010000
+#define A3XX_GRAS_CL_CLIP_CNTL_ZFAR_CLIP_DISABLE		0x00020000
+#define A3XX_GRAS_CL_CLIP_CNTL_VP_CLIP_CODE_IGNORE		0x00080000
+#define A3XX_GRAS_CL_CLIP_CNTL_VP_XFORM_DISABLE			0x00100000
+#define A3XX_GRAS_CL_CLIP_CNTL_PERSP_DIVISION_DISABLE		0x00200000
+
+#define REG_A3XX_GRAS_CL_GB_CLIP_ADJ				0x00002044
+#define A3XX_GRAS_CL_GB_CLIP_ADJ_HORZ__MASK			0x000003ff
+#define A3XX_GRAS_CL_GB_CLIP_ADJ_HORZ__SHIFT			0
+static inline uint32_t A3XX_GRAS_CL_GB_CLIP_ADJ_HORZ(uint32_t val)
+{
+	return ((val) << A3XX_GRAS_CL_GB_CLIP_ADJ_HORZ__SHIFT) & A3XX_GRAS_CL_GB_CLIP_ADJ_HORZ__MASK;
+}
+#define A3XX_GRAS_CL_GB_CLIP_ADJ_VERT__MASK			0x000ffc00
+#define A3XX_GRAS_CL_GB_CLIP_ADJ_VERT__SHIFT			10
+static inline uint32_t A3XX_GRAS_CL_GB_CLIP_ADJ_VERT(uint32_t val)
+{
+	return ((val) << A3XX_GRAS_CL_GB_CLIP_ADJ_VERT__SHIFT) & A3XX_GRAS_CL_GB_CLIP_ADJ_VERT__MASK;
+}
+
+#define REG_A3XX_GRAS_CL_VPORT_XOFFSET				0x00002048
+#define A3XX_GRAS_CL_VPORT_XOFFSET__MASK			0xffffffff
+#define A3XX_GRAS_CL_VPORT_XOFFSET__SHIFT			0
+static inline uint32_t A3XX_GRAS_CL_VPORT_XOFFSET(float val)
+{
+	return ((fui(val)) << A3XX_GRAS_CL_VPORT_XOFFSET__SHIFT) & A3XX_GRAS_CL_VPORT_XOFFSET__MASK;
+}
+
+#define REG_A3XX_GRAS_CL_VPORT_XSCALE				0x00002049
+#define A3XX_GRAS_CL_VPORT_XSCALE__MASK				0xffffffff
+#define A3XX_GRAS_CL_VPORT_XSCALE__SHIFT			0
+static inline uint32_t A3XX_GRAS_CL_VPORT_XSCALE(float val)
+{
+	return ((fui(val)) << A3XX_GRAS_CL_VPORT_XSCALE__SHIFT) & A3XX_GRAS_CL_VPORT_XSCALE__MASK;
+}
+
+#define REG_A3XX_GRAS_CL_VPORT_YOFFSET				0x0000204a
+#define A3XX_GRAS_CL_VPORT_YOFFSET__MASK			0xffffffff
+#define A3XX_GRAS_CL_VPORT_YOFFSET__SHIFT			0
+static inline uint32_t A3XX_GRAS_CL_VPORT_YOFFSET(float val)
+{
+	return ((fui(val)) << A3XX_GRAS_CL_VPORT_YOFFSET__SHIFT) & A3XX_GRAS_CL_VPORT_YOFFSET__MASK;
+}
+
+#define REG_A3XX_GRAS_CL_VPORT_YSCALE				0x0000204b
+#define A3XX_GRAS_CL_VPORT_YSCALE__MASK				0xffffffff
+#define A3XX_GRAS_CL_VPORT_YSCALE__SHIFT			0
+static inline uint32_t A3XX_GRAS_CL_VPORT_YSCALE(float val)
+{
+	return ((fui(val)) << A3XX_GRAS_CL_VPORT_YSCALE__SHIFT) & A3XX_GRAS_CL_VPORT_YSCALE__MASK;
+}
+
+#define REG_A3XX_GRAS_CL_VPORT_ZOFFSET				0x0000204c
+#define A3XX_GRAS_CL_VPORT_ZOFFSET__MASK			0xffffffff
+#define A3XX_GRAS_CL_VPORT_ZOFFSET__SHIFT			0
+static inline uint32_t A3XX_GRAS_CL_VPORT_ZOFFSET(float val)
+{
+	return ((fui(val)) << A3XX_GRAS_CL_VPORT_ZOFFSET__SHIFT) & A3XX_GRAS_CL_VPORT_ZOFFSET__MASK;
+}
+
+#define REG_A3XX_GRAS_CL_VPORT_ZSCALE				0x0000204d
+#define A3XX_GRAS_CL_VPORT_ZSCALE__MASK				0xffffffff
+#define A3XX_GRAS_CL_VPORT_ZSCALE__SHIFT			0
+static inline uint32_t A3XX_GRAS_CL_VPORT_ZSCALE(float val)
+{
+	return ((fui(val)) << A3XX_GRAS_CL_VPORT_ZSCALE__SHIFT) & A3XX_GRAS_CL_VPORT_ZSCALE__MASK;
+}
+
+#define REG_A3XX_GRAS_SU_POINT_MINMAX				0x00002068
+
+#define REG_A3XX_GRAS_SU_POINT_SIZE				0x00002069
+
+#define REG_A3XX_GRAS_SU_POLY_OFFSET_SCALE			0x0000206c
+#define A3XX_GRAS_SU_POLY_OFFSET_SCALE_VAL__MASK		0x00ffffff
+#define A3XX_GRAS_SU_POLY_OFFSET_SCALE_VAL__SHIFT		0
+static inline uint32_t A3XX_GRAS_SU_POLY_OFFSET_SCALE_VAL(float val)
+{
+	return ((((uint32_t)(val * 40.0))) << A3XX_GRAS_SU_POLY_OFFSET_SCALE_VAL__SHIFT) & A3XX_GRAS_SU_POLY_OFFSET_SCALE_VAL__MASK;
+}
+
+#define REG_A3XX_GRAS_SU_POLY_OFFSET_OFFSET			0x0000206d
+#define A3XX_GRAS_SU_POLY_OFFSET_OFFSET__MASK			0xffffffff
+#define A3XX_GRAS_SU_POLY_OFFSET_OFFSET__SHIFT			0
+static inline uint32_t A3XX_GRAS_SU_POLY_OFFSET_OFFSET(float val)
+{
+	return ((((uint32_t)(val * 44.0))) << A3XX_GRAS_SU_POLY_OFFSET_OFFSET__SHIFT) & A3XX_GRAS_SU_POLY_OFFSET_OFFSET__MASK;
+}
+
+#define REG_A3XX_GRAS_SU_MODE_CONTROL				0x00002070
+#define A3XX_GRAS_SU_MODE_CONTROL_CULL_FRONT			0x00000001
+#define A3XX_GRAS_SU_MODE_CONTROL_CULL_BACK			0x00000002
+#define A3XX_GRAS_SU_MODE_CONTROL_LINEHALFWIDTH__MASK		0x000007fc
+#define A3XX_GRAS_SU_MODE_CONTROL_LINEHALFWIDTH__SHIFT		2
+static inline uint32_t A3XX_GRAS_SU_MODE_CONTROL_LINEHALFWIDTH(uint32_t val)
+{
+	return ((val) << A3XX_GRAS_SU_MODE_CONTROL_LINEHALFWIDTH__SHIFT) & A3XX_GRAS_SU_MODE_CONTROL_LINEHALFWIDTH__MASK;
+}
+#define A3XX_GRAS_SU_MODE_CONTROL_POLY_OFFSET			0x00000800
+
+#define REG_A3XX_GRAS_SC_CONTROL				0x00002072
+#define A3XX_GRAS_SC_CONTROL_RENDER_MODE__MASK			0x000000f0
+#define A3XX_GRAS_SC_CONTROL_RENDER_MODE__SHIFT			4
+static inline uint32_t A3XX_GRAS_SC_CONTROL_RENDER_MODE(enum a3xx_render_mode val)
+{
+	return ((val) << A3XX_GRAS_SC_CONTROL_RENDER_MODE__SHIFT) & A3XX_GRAS_SC_CONTROL_RENDER_MODE__MASK;
+}
+#define A3XX_GRAS_SC_CONTROL_MSAA_SAMPLES__MASK			0x00000f00
+#define A3XX_GRAS_SC_CONTROL_MSAA_SAMPLES__SHIFT		8
+static inline uint32_t A3XX_GRAS_SC_CONTROL_MSAA_SAMPLES(enum a3xx_msaa_samples val)
+{
+	return ((val) << A3XX_GRAS_SC_CONTROL_MSAA_SAMPLES__SHIFT) & A3XX_GRAS_SC_CONTROL_MSAA_SAMPLES__MASK;
+}
+#define A3XX_GRAS_SC_CONTROL_RASTER_MODE__MASK			0x0000f000
+#define A3XX_GRAS_SC_CONTROL_RASTER_MODE__SHIFT			12
+static inline uint32_t A3XX_GRAS_SC_CONTROL_RASTER_MODE(uint32_t val)
+{
+	return ((val) << A3XX_GRAS_SC_CONTROL_RASTER_MODE__SHIFT) & A3XX_GRAS_SC_CONTROL_RASTER_MODE__MASK;
+}
+
+#define REG_A3XX_GRAS_SC_SCREEN_SCISSOR_TL			0x00002074
+#define A3XX_GRAS_SC_SCREEN_SCISSOR_TL_WINDOW_OFFSET_DISABLE	0x80000000
+#define A3XX_GRAS_SC_SCREEN_SCISSOR_TL_X__MASK			0x00007fff
+#define A3XX_GRAS_SC_SCREEN_SCISSOR_TL_X__SHIFT			0
+static inline uint32_t A3XX_GRAS_SC_SCREEN_SCISSOR_TL_X(uint32_t val)
+{
+	return ((val) << A3XX_GRAS_SC_SCREEN_SCISSOR_TL_X__SHIFT) & A3XX_GRAS_SC_SCREEN_SCISSOR_TL_X__MASK;
+}
+#define A3XX_GRAS_SC_SCREEN_SCISSOR_TL_Y__MASK			0x7fff0000
+#define A3XX_GRAS_SC_SCREEN_SCISSOR_TL_Y__SHIFT			16
+static inline uint32_t A3XX_GRAS_SC_SCREEN_SCISSOR_TL_Y(uint32_t val)
+{
+	return ((val) << A3XX_GRAS_SC_SCREEN_SCISSOR_TL_Y__SHIFT) & A3XX_GRAS_SC_SCREEN_SCISSOR_TL_Y__MASK;
+}
+
+#define REG_A3XX_GRAS_SC_SCREEN_SCISSOR_BR			0x00002075
+#define A3XX_GRAS_SC_SCREEN_SCISSOR_BR_WINDOW_OFFSET_DISABLE	0x80000000
+#define A3XX_GRAS_SC_SCREEN_SCISSOR_BR_X__MASK			0x00007fff
+#define A3XX_GRAS_SC_SCREEN_SCISSOR_BR_X__SHIFT			0
+static inline uint32_t A3XX_GRAS_SC_SCREEN_SCISSOR_BR_X(uint32_t val)
+{
+	return ((val) << A3XX_GRAS_SC_SCREEN_SCISSOR_BR_X__SHIFT) & A3XX_GRAS_SC_SCREEN_SCISSOR_BR_X__MASK;
+}
+#define A3XX_GRAS_SC_SCREEN_SCISSOR_BR_Y__MASK			0x7fff0000
+#define A3XX_GRAS_SC_SCREEN_SCISSOR_BR_Y__SHIFT			16
+static inline uint32_t A3XX_GRAS_SC_SCREEN_SCISSOR_BR_Y(uint32_t val)
+{
+	return ((val) << A3XX_GRAS_SC_SCREEN_SCISSOR_BR_Y__SHIFT) & A3XX_GRAS_SC_SCREEN_SCISSOR_BR_Y__MASK;
+}
+
+#define REG_A3XX_GRAS_SC_WINDOW_SCISSOR_TL			0x00002079
+#define A3XX_GRAS_SC_WINDOW_SCISSOR_TL_WINDOW_OFFSET_DISABLE	0x80000000
+#define A3XX_GRAS_SC_WINDOW_SCISSOR_TL_X__MASK			0x00007fff
+#define A3XX_GRAS_SC_WINDOW_SCISSOR_TL_X__SHIFT			0
+static inline uint32_t A3XX_GRAS_SC_WINDOW_SCISSOR_TL_X(uint32_t val)
+{
+	return ((val) << A3XX_GRAS_SC_WINDOW_SCISSOR_TL_X__SHIFT) & A3XX_GRAS_SC_WINDOW_SCISSOR_TL_X__MASK;
+}
+#define A3XX_GRAS_SC_WINDOW_SCISSOR_TL_Y__MASK			0x7fff0000
+#define A3XX_GRAS_SC_WINDOW_SCISSOR_TL_Y__SHIFT			16
+static inline uint32_t A3XX_GRAS_SC_WINDOW_SCISSOR_TL_Y(uint32_t val)
+{
+	return ((val) << A3XX_GRAS_SC_WINDOW_SCISSOR_TL_Y__SHIFT) & A3XX_GRAS_SC_WINDOW_SCISSOR_TL_Y__MASK;
+}
+
+#define REG_A3XX_GRAS_SC_WINDOW_SCISSOR_BR			0x0000207a
+#define A3XX_GRAS_SC_WINDOW_SCISSOR_BR_WINDOW_OFFSET_DISABLE	0x80000000
+#define A3XX_GRAS_SC_WINDOW_SCISSOR_BR_X__MASK			0x00007fff
+#define A3XX_GRAS_SC_WINDOW_SCISSOR_BR_X__SHIFT			0
+static inline uint32_t A3XX_GRAS_SC_WINDOW_SCISSOR_BR_X(uint32_t val)
+{
+	return ((val) << A3XX_GRAS_SC_WINDOW_SCISSOR_BR_X__SHIFT) & A3XX_GRAS_SC_WINDOW_SCISSOR_BR_X__MASK;
+}
+#define A3XX_GRAS_SC_WINDOW_SCISSOR_BR_Y__MASK			0x7fff0000
+#define A3XX_GRAS_SC_WINDOW_SCISSOR_BR_Y__SHIFT			16
+static inline uint32_t A3XX_GRAS_SC_WINDOW_SCISSOR_BR_Y(uint32_t val)
+{
+	return ((val) << A3XX_GRAS_SC_WINDOW_SCISSOR_BR_Y__SHIFT) & A3XX_GRAS_SC_WINDOW_SCISSOR_BR_Y__MASK;
+}
+
+#define REG_A3XX_RB_MODE_CONTROL				0x000020c0
+#define A3XX_RB_MODE_CONTROL_GMEM_BYPASS			0x00000080
+#define A3XX_RB_MODE_CONTROL_RENDER_MODE__MASK			0x00000700
+#define A3XX_RB_MODE_CONTROL_RENDER_MODE__SHIFT			8
+static inline uint32_t A3XX_RB_MODE_CONTROL_RENDER_MODE(enum a3xx_render_mode val)
+{
+	return ((val) << A3XX_RB_MODE_CONTROL_RENDER_MODE__SHIFT) & A3XX_RB_MODE_CONTROL_RENDER_MODE__MASK;
+}
+#define A3XX_RB_MODE_CONTROL_MARB_CACHE_SPLIT_MODE		0x00008000
+#define A3XX_RB_MODE_CONTROL_PACKER_TIMER_ENABLE		0x00010000
+
+#define REG_A3XX_RB_RENDER_CONTROL				0x000020c1
+#define A3XX_RB_RENDER_CONTROL_BIN_WIDTH__MASK			0x00000ff0
+#define A3XX_RB_RENDER_CONTROL_BIN_WIDTH__SHIFT			4
+static inline uint32_t A3XX_RB_RENDER_CONTROL_BIN_WIDTH(uint32_t val)
+{
+	return ((val >> 5) << A3XX_RB_RENDER_CONTROL_BIN_WIDTH__SHIFT) & A3XX_RB_RENDER_CONTROL_BIN_WIDTH__MASK;
+}
+#define A3XX_RB_RENDER_CONTROL_DISABLE_COLOR_PIPE		0x00001000
+#define A3XX_RB_RENDER_CONTROL_ENABLE_GMEM			0x00002000
+#define A3XX_RB_RENDER_CONTROL_ALPHA_TEST_FUNC__MASK		0x07000000
+#define A3XX_RB_RENDER_CONTROL_ALPHA_TEST_FUNC__SHIFT		24
+static inline uint32_t A3XX_RB_RENDER_CONTROL_ALPHA_TEST_FUNC(enum adreno_compare_func val)
+{
+	return ((val) << A3XX_RB_RENDER_CONTROL_ALPHA_TEST_FUNC__SHIFT) & A3XX_RB_RENDER_CONTROL_ALPHA_TEST_FUNC__MASK;
+}
+
+#define REG_A3XX_RB_MSAA_CONTROL				0x000020c2
+#define A3XX_RB_MSAA_CONTROL_DISABLE				0x00000400
+#define A3XX_RB_MSAA_CONTROL_SAMPLES__MASK			0x0000f000
+#define A3XX_RB_MSAA_CONTROL_SAMPLES__SHIFT			12
+static inline uint32_t A3XX_RB_MSAA_CONTROL_SAMPLES(enum a3xx_msaa_samples val)
+{
+	return ((val) << A3XX_RB_MSAA_CONTROL_SAMPLES__SHIFT) & A3XX_RB_MSAA_CONTROL_SAMPLES__MASK;
+}
+#define A3XX_RB_MSAA_CONTROL_SAMPLE_MASK__MASK			0xffff0000
+#define A3XX_RB_MSAA_CONTROL_SAMPLE_MASK__SHIFT			16
+static inline uint32_t A3XX_RB_MSAA_CONTROL_SAMPLE_MASK(uint32_t val)
+{
+	return ((val) << A3XX_RB_MSAA_CONTROL_SAMPLE_MASK__SHIFT) & A3XX_RB_MSAA_CONTROL_SAMPLE_MASK__MASK;
+}
+
+#define REG_A3XX_UNKNOWN_20C3					0x000020c3
+
+static inline uint32_t REG_A3XX_RB_MRT(uint32_t i0) { return 0x000020c4 + 0x4*i0; }
+
+static inline uint32_t REG_A3XX_RB_MRT_CONTROL(uint32_t i0) { return 0x000020c4 + 0x4*i0; }
+#define A3XX_RB_MRT_CONTROL_READ_DEST_ENABLE			0x00000008
+#define A3XX_RB_MRT_CONTROL_BLEND				0x00000010
+#define A3XX_RB_MRT_CONTROL_BLEND2				0x00000020
+#define A3XX_RB_MRT_CONTROL_ROP_CODE__MASK			0x00000f00
+#define A3XX_RB_MRT_CONTROL_ROP_CODE__SHIFT			8
+static inline uint32_t A3XX_RB_MRT_CONTROL_ROP_CODE(uint32_t val)
+{
+	return ((val) << A3XX_RB_MRT_CONTROL_ROP_CODE__SHIFT) & A3XX_RB_MRT_CONTROL_ROP_CODE__MASK;
+}
+#define A3XX_RB_MRT_CONTROL_DITHER_MODE__MASK			0x00003000
+#define A3XX_RB_MRT_CONTROL_DITHER_MODE__SHIFT			12
+static inline uint32_t A3XX_RB_MRT_CONTROL_DITHER_MODE(enum adreno_rb_dither_mode val)
+{
+	return ((val) << A3XX_RB_MRT_CONTROL_DITHER_MODE__SHIFT) & A3XX_RB_MRT_CONTROL_DITHER_MODE__MASK;
+}
+#define A3XX_RB_MRT_CONTROL_COMPONENT_ENABLE__MASK		0x0f000000
+#define A3XX_RB_MRT_CONTROL_COMPONENT_ENABLE__SHIFT		24
+static inline uint32_t A3XX_RB_MRT_CONTROL_COMPONENT_ENABLE(uint32_t val)
+{
+	return ((val) << A3XX_RB_MRT_CONTROL_COMPONENT_ENABLE__SHIFT) & A3XX_RB_MRT_CONTROL_COMPONENT_ENABLE__MASK;
+}
+
+static inline uint32_t REG_A3XX_RB_MRT_BUF_INFO(uint32_t i0) { return 0x000020c5 + 0x4*i0; }
+#define A3XX_RB_MRT_BUF_INFO_COLOR_FORMAT__MASK			0x0000003f
+#define A3XX_RB_MRT_BUF_INFO_COLOR_FORMAT__SHIFT		0
+static inline uint32_t A3XX_RB_MRT_BUF_INFO_COLOR_FORMAT(enum a3xx_color_fmt val)
+{
+	return ((val) << A3XX_RB_MRT_BUF_INFO_COLOR_FORMAT__SHIFT) & A3XX_RB_MRT_BUF_INFO_COLOR_FORMAT__MASK;
+}
+#define A3XX_RB_MRT_BUF_INFO_COLOR_TILE_MODE__MASK		0x000000c0
+#define A3XX_RB_MRT_BUF_INFO_COLOR_TILE_MODE__SHIFT		6
+static inline uint32_t A3XX_RB_MRT_BUF_INFO_COLOR_TILE_MODE(enum a3xx_tile_mode val)
+{
+	return ((val) << A3XX_RB_MRT_BUF_INFO_COLOR_TILE_MODE__SHIFT) & A3XX_RB_MRT_BUF_INFO_COLOR_TILE_MODE__MASK;
+}
+#define A3XX_RB_MRT_BUF_INFO_COLOR_SWAP__MASK			0x00000c00
+#define A3XX_RB_MRT_BUF_INFO_COLOR_SWAP__SHIFT			10
+static inline uint32_t A3XX_RB_MRT_BUF_INFO_COLOR_SWAP(enum a3xx_color_swap val)
+{
+	return ((val) << A3XX_RB_MRT_BUF_INFO_COLOR_SWAP__SHIFT) & A3XX_RB_MRT_BUF_INFO_COLOR_SWAP__MASK;
+}
+#define A3XX_RB_MRT_BUF_INFO_COLOR_BUF_PITCH__MASK		0xfffe0000
+#define A3XX_RB_MRT_BUF_INFO_COLOR_BUF_PITCH__SHIFT		17
+static inline uint32_t A3XX_RB_MRT_BUF_INFO_COLOR_BUF_PITCH(uint32_t val)
+{
+	return ((val >> 5) << A3XX_RB_MRT_BUF_INFO_COLOR_BUF_PITCH__SHIFT) & A3XX_RB_MRT_BUF_INFO_COLOR_BUF_PITCH__MASK;
+}
+
+static inline uint32_t REG_A3XX_RB_MRT_BUF_BASE(uint32_t i0) { return 0x000020c6 + 0x4*i0; }
+#define A3XX_RB_MRT_BUF_BASE_COLOR_BUF_BASE__MASK		0xfffffff0
+#define A3XX_RB_MRT_BUF_BASE_COLOR_BUF_BASE__SHIFT		4
+static inline uint32_t A3XX_RB_MRT_BUF_BASE_COLOR_BUF_BASE(uint32_t val)
+{
+	return ((val >> 5) << A3XX_RB_MRT_BUF_BASE_COLOR_BUF_BASE__SHIFT) & A3XX_RB_MRT_BUF_BASE_COLOR_BUF_BASE__MASK;
+}
+
+static inline uint32_t REG_A3XX_RB_MRT_BLEND_CONTROL(uint32_t i0) { return 0x000020c7 + 0x4*i0; }
+#define A3XX_RB_MRT_BLEND_CONTROL_RGB_SRC_FACTOR__MASK		0x0000001f
+#define A3XX_RB_MRT_BLEND_CONTROL_RGB_SRC_FACTOR__SHIFT		0
+static inline uint32_t A3XX_RB_MRT_BLEND_CONTROL_RGB_SRC_FACTOR(enum adreno_rb_blend_factor val)
+{
+	return ((val) << A3XX_RB_MRT_BLEND_CONTROL_RGB_SRC_FACTOR__SHIFT) & A3XX_RB_MRT_BLEND_CONTROL_RGB_SRC_FACTOR__MASK;
+}
+#define A3XX_RB_MRT_BLEND_CONTROL_RGB_BLEND_OPCODE__MASK	0x000000e0
+#define A3XX_RB_MRT_BLEND_CONTROL_RGB_BLEND_OPCODE__SHIFT	5
+static inline uint32_t A3XX_RB_MRT_BLEND_CONTROL_RGB_BLEND_OPCODE(enum adreno_rb_blend_opcode val)
+{
+	return ((val) << A3XX_RB_MRT_BLEND_CONTROL_RGB_BLEND_OPCODE__SHIFT) & A3XX_RB_MRT_BLEND_CONTROL_RGB_BLEND_OPCODE__MASK;
+}
+#define A3XX_RB_MRT_BLEND_CONTROL_RGB_DEST_FACTOR__MASK		0x00001f00
+#define A3XX_RB_MRT_BLEND_CONTROL_RGB_DEST_FACTOR__SHIFT	8
+static inline uint32_t A3XX_RB_MRT_BLEND_CONTROL_RGB_DEST_FACTOR(enum adreno_rb_blend_factor val)
+{
+	return ((val) << A3XX_RB_MRT_BLEND_CONTROL_RGB_DEST_FACTOR__SHIFT) & A3XX_RB_MRT_BLEND_CONTROL_RGB_DEST_FACTOR__MASK;
+}
+#define A3XX_RB_MRT_BLEND_CONTROL_ALPHA_SRC_FACTOR__MASK	0x001f0000
+#define A3XX_RB_MRT_BLEND_CONTROL_ALPHA_SRC_FACTOR__SHIFT	16
+static inline uint32_t A3XX_RB_MRT_BLEND_CONTROL_ALPHA_SRC_FACTOR(enum adreno_rb_blend_factor val)
+{
+	return ((val) << A3XX_RB_MRT_BLEND_CONTROL_ALPHA_SRC_FACTOR__SHIFT) & A3XX_RB_MRT_BLEND_CONTROL_ALPHA_SRC_FACTOR__MASK;
+}
+#define A3XX_RB_MRT_BLEND_CONTROL_ALPHA_BLEND_OPCODE__MASK	0x00e00000
+#define A3XX_RB_MRT_BLEND_CONTROL_ALPHA_BLEND_OPCODE__SHIFT	21
+static inline uint32_t A3XX_RB_MRT_BLEND_CONTROL_ALPHA_BLEND_OPCODE(enum adreno_rb_blend_opcode val)
+{
+	return ((val) << A3XX_RB_MRT_BLEND_CONTROL_ALPHA_BLEND_OPCODE__SHIFT) & A3XX_RB_MRT_BLEND_CONTROL_ALPHA_BLEND_OPCODE__MASK;
+}
+#define A3XX_RB_MRT_BLEND_CONTROL_ALPHA_DEST_FACTOR__MASK	0x1f000000
+#define A3XX_RB_MRT_BLEND_CONTROL_ALPHA_DEST_FACTOR__SHIFT	24
+static inline uint32_t A3XX_RB_MRT_BLEND_CONTROL_ALPHA_DEST_FACTOR(enum adreno_rb_blend_factor val)
+{
+	return ((val) << A3XX_RB_MRT_BLEND_CONTROL_ALPHA_DEST_FACTOR__SHIFT) & A3XX_RB_MRT_BLEND_CONTROL_ALPHA_DEST_FACTOR__MASK;
+}
+#define A3XX_RB_MRT_BLEND_CONTROL_CLAMP_ENABLE			0x20000000
+
+#define REG_A3XX_RB_BLEND_RED					0x000020e4
+#define A3XX_RB_BLEND_RED_UINT__MASK				0x000000ff
+#define A3XX_RB_BLEND_RED_UINT__SHIFT				0
+static inline uint32_t A3XX_RB_BLEND_RED_UINT(uint32_t val)
+{
+	return ((val) << A3XX_RB_BLEND_RED_UINT__SHIFT) & A3XX_RB_BLEND_RED_UINT__MASK;
+}
+#define A3XX_RB_BLEND_RED_FLOAT__MASK				0xffff0000
+#define A3XX_RB_BLEND_RED_FLOAT__SHIFT				16
+static inline uint32_t A3XX_RB_BLEND_RED_FLOAT(float val)
+{
+	return ((util_float_to_half(val)) << A3XX_RB_BLEND_RED_FLOAT__SHIFT) & A3XX_RB_BLEND_RED_FLOAT__MASK;
+}
+
+#define REG_A3XX_RB_BLEND_GREEN					0x000020e5
+#define A3XX_RB_BLEND_GREEN_UINT__MASK				0x000000ff
+#define A3XX_RB_BLEND_GREEN_UINT__SHIFT				0
+static inline uint32_t A3XX_RB_BLEND_GREEN_UINT(uint32_t val)
+{
+	return ((val) << A3XX_RB_BLEND_GREEN_UINT__SHIFT) & A3XX_RB_BLEND_GREEN_UINT__MASK;
+}
+#define A3XX_RB_BLEND_GREEN_FLOAT__MASK				0xffff0000
+#define A3XX_RB_BLEND_GREEN_FLOAT__SHIFT			16
+static inline uint32_t A3XX_RB_BLEND_GREEN_FLOAT(float val)
+{
+	return ((util_float_to_half(val)) << A3XX_RB_BLEND_GREEN_FLOAT__SHIFT) & A3XX_RB_BLEND_GREEN_FLOAT__MASK;
+}
+
+#define REG_A3XX_RB_BLEND_BLUE					0x000020e6
+#define A3XX_RB_BLEND_BLUE_UINT__MASK				0x000000ff
+#define A3XX_RB_BLEND_BLUE_UINT__SHIFT				0
+static inline uint32_t A3XX_RB_BLEND_BLUE_UINT(uint32_t val)
+{
+	return ((val) << A3XX_RB_BLEND_BLUE_UINT__SHIFT) & A3XX_RB_BLEND_BLUE_UINT__MASK;
+}
+#define A3XX_RB_BLEND_BLUE_FLOAT__MASK				0xffff0000
+#define A3XX_RB_BLEND_BLUE_FLOAT__SHIFT				16
+static inline uint32_t A3XX_RB_BLEND_BLUE_FLOAT(float val)
+{
+	return ((util_float_to_half(val)) << A3XX_RB_BLEND_BLUE_FLOAT__SHIFT) & A3XX_RB_BLEND_BLUE_FLOAT__MASK;
+}
+
+#define REG_A3XX_RB_BLEND_ALPHA					0x000020e7
+#define A3XX_RB_BLEND_ALPHA_UINT__MASK				0x000000ff
+#define A3XX_RB_BLEND_ALPHA_UINT__SHIFT				0
+static inline uint32_t A3XX_RB_BLEND_ALPHA_UINT(uint32_t val)
+{
+	return ((val) << A3XX_RB_BLEND_ALPHA_UINT__SHIFT) & A3XX_RB_BLEND_ALPHA_UINT__MASK;
+}
+#define A3XX_RB_BLEND_ALPHA_FLOAT__MASK				0xffff0000
+#define A3XX_RB_BLEND_ALPHA_FLOAT__SHIFT			16
+static inline uint32_t A3XX_RB_BLEND_ALPHA_FLOAT(float val)
+{
+	return ((util_float_to_half(val)) << A3XX_RB_BLEND_ALPHA_FLOAT__SHIFT) & A3XX_RB_BLEND_ALPHA_FLOAT__MASK;
+}
+
+#define REG_A3XX_UNKNOWN_20E8					0x000020e8
+
+#define REG_A3XX_UNKNOWN_20E9					0x000020e9
+
+#define REG_A3XX_UNKNOWN_20EA					0x000020ea
+
+#define REG_A3XX_UNKNOWN_20EB					0x000020eb
+
+#define REG_A3XX_RB_COPY_CONTROL				0x000020ec
+#define A3XX_RB_COPY_CONTROL_MSAA_RESOLVE__MASK			0x00000003
+#define A3XX_RB_COPY_CONTROL_MSAA_RESOLVE__SHIFT		0
+static inline uint32_t A3XX_RB_COPY_CONTROL_MSAA_RESOLVE(enum a3xx_msaa_samples val)
+{
+	return ((val) << A3XX_RB_COPY_CONTROL_MSAA_RESOLVE__SHIFT) & A3XX_RB_COPY_CONTROL_MSAA_RESOLVE__MASK;
+}
+#define A3XX_RB_COPY_CONTROL_MODE__MASK				0x00000070
+#define A3XX_RB_COPY_CONTROL_MODE__SHIFT			4
+static inline uint32_t A3XX_RB_COPY_CONTROL_MODE(enum adreno_rb_copy_control_mode val)
+{
+	return ((val) << A3XX_RB_COPY_CONTROL_MODE__SHIFT) & A3XX_RB_COPY_CONTROL_MODE__MASK;
+}
+#define A3XX_RB_COPY_CONTROL_GMEM_BASE__MASK			0xfffffc00
+#define A3XX_RB_COPY_CONTROL_GMEM_BASE__SHIFT			10
+static inline uint32_t A3XX_RB_COPY_CONTROL_GMEM_BASE(uint32_t val)
+{
+	return ((val >> 10) << A3XX_RB_COPY_CONTROL_GMEM_BASE__SHIFT) & A3XX_RB_COPY_CONTROL_GMEM_BASE__MASK;
+}
+
+#define REG_A3XX_RB_COPY_DEST_BASE				0x000020ed
+#define A3XX_RB_COPY_DEST_BASE_BASE__MASK			0xfffffff0
+#define A3XX_RB_COPY_DEST_BASE_BASE__SHIFT			4
+static inline uint32_t A3XX_RB_COPY_DEST_BASE_BASE(uint32_t val)
+{
+	return ((val >> 5) << A3XX_RB_COPY_DEST_BASE_BASE__SHIFT) & A3XX_RB_COPY_DEST_BASE_BASE__MASK;
+}
+
+#define REG_A3XX_RB_COPY_DEST_PITCH				0x000020ee
+#define A3XX_RB_COPY_DEST_PITCH_PITCH__MASK			0xffffffff
+#define A3XX_RB_COPY_DEST_PITCH_PITCH__SHIFT			0
+static inline uint32_t A3XX_RB_COPY_DEST_PITCH_PITCH(uint32_t val)
+{
+	return ((val >> 5) << A3XX_RB_COPY_DEST_PITCH_PITCH__SHIFT) & A3XX_RB_COPY_DEST_PITCH_PITCH__MASK;
+}
+
+#define REG_A3XX_RB_COPY_DEST_INFO				0x000020ef
+#define A3XX_RB_COPY_DEST_INFO_TILE__MASK			0x00000003
+#define A3XX_RB_COPY_DEST_INFO_TILE__SHIFT			0
+static inline uint32_t A3XX_RB_COPY_DEST_INFO_TILE(enum a3xx_tile_mode val)
+{
+	return ((val) << A3XX_RB_COPY_DEST_INFO_TILE__SHIFT) & A3XX_RB_COPY_DEST_INFO_TILE__MASK;
+}
+#define A3XX_RB_COPY_DEST_INFO_FORMAT__MASK			0x000000fc
+#define A3XX_RB_COPY_DEST_INFO_FORMAT__SHIFT			2
+static inline uint32_t A3XX_RB_COPY_DEST_INFO_FORMAT(enum a3xx_color_fmt val)
+{
+	return ((val) << A3XX_RB_COPY_DEST_INFO_FORMAT__SHIFT) & A3XX_RB_COPY_DEST_INFO_FORMAT__MASK;
+}
+#define A3XX_RB_COPY_DEST_INFO_SWAP__MASK			0x00000300
+#define A3XX_RB_COPY_DEST_INFO_SWAP__SHIFT			8
+static inline uint32_t A3XX_RB_COPY_DEST_INFO_SWAP(enum a3xx_color_swap val)
+{
+	return ((val) << A3XX_RB_COPY_DEST_INFO_SWAP__SHIFT) & A3XX_RB_COPY_DEST_INFO_SWAP__MASK;
+}
+#define A3XX_RB_COPY_DEST_INFO_COMPONENT_ENABLE__MASK		0x0003c000
+#define A3XX_RB_COPY_DEST_INFO_COMPONENT_ENABLE__SHIFT		14
+static inline uint32_t A3XX_RB_COPY_DEST_INFO_COMPONENT_ENABLE(uint32_t val)
+{
+	return ((val) << A3XX_RB_COPY_DEST_INFO_COMPONENT_ENABLE__SHIFT) & A3XX_RB_COPY_DEST_INFO_COMPONENT_ENABLE__MASK;
+}
+#define A3XX_RB_COPY_DEST_INFO_ENDIAN__MASK			0x001c0000
+#define A3XX_RB_COPY_DEST_INFO_ENDIAN__SHIFT			18
+static inline uint32_t A3XX_RB_COPY_DEST_INFO_ENDIAN(enum adreno_rb_surface_endian val)
+{
+	return ((val) << A3XX_RB_COPY_DEST_INFO_ENDIAN__SHIFT) & A3XX_RB_COPY_DEST_INFO_ENDIAN__MASK;
+}
+
+#define REG_A3XX_RB_DEPTH_CONTROL				0x00002100
+#define A3XX_RB_DEPTH_CONTROL_Z_ENABLE				0x00000002
+#define A3XX_RB_DEPTH_CONTROL_Z_WRITE_ENABLE			0x00000004
+#define A3XX_RB_DEPTH_CONTROL_EARLY_Z_ENABLE			0x00000008
+#define A3XX_RB_DEPTH_CONTROL_ZFUNC__MASK			0x00000070
+#define A3XX_RB_DEPTH_CONTROL_ZFUNC__SHIFT			4
+static inline uint32_t A3XX_RB_DEPTH_CONTROL_ZFUNC(enum adreno_compare_func val)
+{
+	return ((val) << A3XX_RB_DEPTH_CONTROL_ZFUNC__SHIFT) & A3XX_RB_DEPTH_CONTROL_ZFUNC__MASK;
+}
+#define A3XX_RB_DEPTH_CONTROL_BF_ENABLE				0x00000080
+#define A3XX_RB_DEPTH_CONTROL_Z_TEST_ENABLE			0x80000000
+
+#define REG_A3XX_UNKNOWN_2101					0x00002101
+
+#define REG_A3XX_RB_DEPTH_INFO					0x00002102
+#define A3XX_RB_DEPTH_INFO_DEPTH_FORMAT__MASK			0x00000001
+#define A3XX_RB_DEPTH_INFO_DEPTH_FORMAT__SHIFT			0
+static inline uint32_t A3XX_RB_DEPTH_INFO_DEPTH_FORMAT(enum adreno_rb_depth_format val)
+{
+	return ((val) << A3XX_RB_DEPTH_INFO_DEPTH_FORMAT__SHIFT) & A3XX_RB_DEPTH_INFO_DEPTH_FORMAT__MASK;
+}
+#define A3XX_RB_DEPTH_INFO_DEPTH_BASE__MASK			0xfffff800
+#define A3XX_RB_DEPTH_INFO_DEPTH_BASE__SHIFT			11
+static inline uint32_t A3XX_RB_DEPTH_INFO_DEPTH_BASE(uint32_t val)
+{
+	return ((val >> 10) << A3XX_RB_DEPTH_INFO_DEPTH_BASE__SHIFT) & A3XX_RB_DEPTH_INFO_DEPTH_BASE__MASK;
+}
+
+#define REG_A3XX_RB_DEPTH_PITCH					0x00002103
+#define A3XX_RB_DEPTH_PITCH__MASK				0xffffffff
+#define A3XX_RB_DEPTH_PITCH__SHIFT				0
+static inline uint32_t A3XX_RB_DEPTH_PITCH(uint32_t val)
+{
+	return ((val >> 3) << A3XX_RB_DEPTH_PITCH__SHIFT) & A3XX_RB_DEPTH_PITCH__MASK;
+}
+
+#define REG_A3XX_RB_STENCIL_CONTROL				0x00002104
+#define A3XX_RB_STENCIL_CONTROL_STENCIL_ENABLE			0x00000001
+#define A3XX_RB_STENCIL_CONTROL_STENCIL_ENABLE_BF		0x00000004
+#define A3XX_RB_STENCIL_CONTROL_FUNC__MASK			0x00000700
+#define A3XX_RB_STENCIL_CONTROL_FUNC__SHIFT			8
+static inline uint32_t A3XX_RB_STENCIL_CONTROL_FUNC(enum adreno_compare_func val)
+{
+	return ((val) << A3XX_RB_STENCIL_CONTROL_FUNC__SHIFT) & A3XX_RB_STENCIL_CONTROL_FUNC__MASK;
+}
+#define A3XX_RB_STENCIL_CONTROL_FAIL__MASK			0x00003800
+#define A3XX_RB_STENCIL_CONTROL_FAIL__SHIFT			11
+static inline uint32_t A3XX_RB_STENCIL_CONTROL_FAIL(enum adreno_stencil_op val)
+{
+	return ((val) << A3XX_RB_STENCIL_CONTROL_FAIL__SHIFT) & A3XX_RB_STENCIL_CONTROL_FAIL__MASK;
+}
+#define A3XX_RB_STENCIL_CONTROL_ZPASS__MASK			0x0001c000
+#define A3XX_RB_STENCIL_CONTROL_ZPASS__SHIFT			14
+static inline uint32_t A3XX_RB_STENCIL_CONTROL_ZPASS(enum adreno_stencil_op val)
+{
+	return ((val) << A3XX_RB_STENCIL_CONTROL_ZPASS__SHIFT) & A3XX_RB_STENCIL_CONTROL_ZPASS__MASK;
+}
+#define A3XX_RB_STENCIL_CONTROL_ZFAIL__MASK			0x000e0000
+#define A3XX_RB_STENCIL_CONTROL_ZFAIL__SHIFT			17
+static inline uint32_t A3XX_RB_STENCIL_CONTROL_ZFAIL(enum adreno_stencil_op val)
+{
+	return ((val) << A3XX_RB_STENCIL_CONTROL_ZFAIL__SHIFT) & A3XX_RB_STENCIL_CONTROL_ZFAIL__MASK;
+}
+#define A3XX_RB_STENCIL_CONTROL_FUNC_BF__MASK			0x00700000
+#define A3XX_RB_STENCIL_CONTROL_FUNC_BF__SHIFT			20
+static inline uint32_t A3XX_RB_STENCIL_CONTROL_FUNC_BF(enum adreno_compare_func val)
+{
+	return ((val) << A3XX_RB_STENCIL_CONTROL_FUNC_BF__SHIFT) & A3XX_RB_STENCIL_CONTROL_FUNC_BF__MASK;
+}
+#define A3XX_RB_STENCIL_CONTROL_FAIL_BF__MASK			0x03800000
+#define A3XX_RB_STENCIL_CONTROL_FAIL_BF__SHIFT			23
+static inline uint32_t A3XX_RB_STENCIL_CONTROL_FAIL_BF(enum adreno_stencil_op val)
+{
+	return ((val) << A3XX_RB_STENCIL_CONTROL_FAIL_BF__SHIFT) & A3XX_RB_STENCIL_CONTROL_FAIL_BF__MASK;
+}
+#define A3XX_RB_STENCIL_CONTROL_ZPASS_BF__MASK			0x1c000000
+#define A3XX_RB_STENCIL_CONTROL_ZPASS_BF__SHIFT			26
+static inline uint32_t A3XX_RB_STENCIL_CONTROL_ZPASS_BF(enum adreno_stencil_op val)
+{
+	return ((val) << A3XX_RB_STENCIL_CONTROL_ZPASS_BF__SHIFT) & A3XX_RB_STENCIL_CONTROL_ZPASS_BF__MASK;
+}
+#define A3XX_RB_STENCIL_CONTROL_ZFAIL_BF__MASK			0xe0000000
+#define A3XX_RB_STENCIL_CONTROL_ZFAIL_BF__SHIFT			29
+static inline uint32_t A3XX_RB_STENCIL_CONTROL_ZFAIL_BF(enum adreno_stencil_op val)
+{
+	return ((val) << A3XX_RB_STENCIL_CONTROL_ZFAIL_BF__SHIFT) & A3XX_RB_STENCIL_CONTROL_ZFAIL_BF__MASK;
+}
+
+#define REG_A3XX_UNKNOWN_2105					0x00002105
+
+#define REG_A3XX_UNKNOWN_2106					0x00002106
+
+#define REG_A3XX_UNKNOWN_2107					0x00002107
+
+#define REG_A3XX_RB_STENCILREFMASK				0x00002108
+#define A3XX_RB_STENCILREFMASK_STENCILREF__MASK			0x000000ff
+#define A3XX_RB_STENCILREFMASK_STENCILREF__SHIFT		0
+static inline uint32_t A3XX_RB_STENCILREFMASK_STENCILREF(uint32_t val)
+{
+	return ((val) << A3XX_RB_STENCILREFMASK_STENCILREF__SHIFT) & A3XX_RB_STENCILREFMASK_STENCILREF__MASK;
+}
+#define A3XX_RB_STENCILREFMASK_STENCILMASK__MASK		0x0000ff00
+#define A3XX_RB_STENCILREFMASK_STENCILMASK__SHIFT		8
+static inline uint32_t A3XX_RB_STENCILREFMASK_STENCILMASK(uint32_t val)
+{
+	return ((val) << A3XX_RB_STENCILREFMASK_STENCILMASK__SHIFT) & A3XX_RB_STENCILREFMASK_STENCILMASK__MASK;
+}
+#define A3XX_RB_STENCILREFMASK_STENCILWRITEMASK__MASK		0x00ff0000
+#define A3XX_RB_STENCILREFMASK_STENCILWRITEMASK__SHIFT		16
+static inline uint32_t A3XX_RB_STENCILREFMASK_STENCILWRITEMASK(uint32_t val)
+{
+	return ((val) << A3XX_RB_STENCILREFMASK_STENCILWRITEMASK__SHIFT) & A3XX_RB_STENCILREFMASK_STENCILWRITEMASK__MASK;
+}
+
+#define REG_A3XX_RB_STENCILREFMASK_BF				0x00002109
+#define A3XX_RB_STENCILREFMASK_BF_STENCILREF__MASK		0x000000ff
+#define A3XX_RB_STENCILREFMASK_BF_STENCILREF__SHIFT		0
+static inline uint32_t A3XX_RB_STENCILREFMASK_BF_STENCILREF(uint32_t val)
+{
+	return ((val) << A3XX_RB_STENCILREFMASK_BF_STENCILREF__SHIFT) & A3XX_RB_STENCILREFMASK_BF_STENCILREF__MASK;
+}
+#define A3XX_RB_STENCILREFMASK_BF_STENCILMASK__MASK		0x0000ff00
+#define A3XX_RB_STENCILREFMASK_BF_STENCILMASK__SHIFT		8
+static inline uint32_t A3XX_RB_STENCILREFMASK_BF_STENCILMASK(uint32_t val)
+{
+	return ((val) << A3XX_RB_STENCILREFMASK_BF_STENCILMASK__SHIFT) & A3XX_RB_STENCILREFMASK_BF_STENCILMASK__MASK;
+}
+#define A3XX_RB_STENCILREFMASK_BF_STENCILWRITEMASK__MASK	0x00ff0000
+#define A3XX_RB_STENCILREFMASK_BF_STENCILWRITEMASK__SHIFT	16
+static inline uint32_t A3XX_RB_STENCILREFMASK_BF_STENCILWRITEMASK(uint32_t val)
+{
+	return ((val) << A3XX_RB_STENCILREFMASK_BF_STENCILWRITEMASK__SHIFT) & A3XX_RB_STENCILREFMASK_BF_STENCILWRITEMASK__MASK;
+}
+
+#define REG_A3XX_PA_SC_WINDOW_OFFSET				0x0000210e
+#define A3XX_PA_SC_WINDOW_OFFSET_X__MASK			0x0000ffff
+#define A3XX_PA_SC_WINDOW_OFFSET_X__SHIFT			0
+static inline uint32_t A3XX_PA_SC_WINDOW_OFFSET_X(uint32_t val)
+{
+	return ((val) << A3XX_PA_SC_WINDOW_OFFSET_X__SHIFT) & A3XX_PA_SC_WINDOW_OFFSET_X__MASK;
+}
+#define A3XX_PA_SC_WINDOW_OFFSET_Y__MASK			0xffff0000
+#define A3XX_PA_SC_WINDOW_OFFSET_Y__SHIFT			16
+static inline uint32_t A3XX_PA_SC_WINDOW_OFFSET_Y(uint32_t val)
+{
+	return ((val) << A3XX_PA_SC_WINDOW_OFFSET_Y__SHIFT) & A3XX_PA_SC_WINDOW_OFFSET_Y__MASK;
+}
+
+#define REG_A3XX_PC_VSTREAM_CONTROL				0x000021e4
+
+#define REG_A3XX_PC_VERTEX_REUSE_BLOCK_CNTL			0x000021ea
+
+#define REG_A3XX_PC_PRIM_VTX_CNTL				0x000021ec
+#define A3XX_PC_PRIM_VTX_CNTL_STRIDE_IN_VPC__MASK		0x0000001f
+#define A3XX_PC_PRIM_VTX_CNTL_STRIDE_IN_VPC__SHIFT		0
+static inline uint32_t A3XX_PC_PRIM_VTX_CNTL_STRIDE_IN_VPC(uint32_t val)
+{
+	return ((val) << A3XX_PC_PRIM_VTX_CNTL_STRIDE_IN_VPC__SHIFT) & A3XX_PC_PRIM_VTX_CNTL_STRIDE_IN_VPC__MASK;
+}
+#define A3XX_PC_PRIM_VTX_CNTL_POLYMODE_FRONT_PTYPE__MASK	0x000000e0
+#define A3XX_PC_PRIM_VTX_CNTL_POLYMODE_FRONT_PTYPE__SHIFT	5
+static inline uint32_t A3XX_PC_PRIM_VTX_CNTL_POLYMODE_FRONT_PTYPE(enum adreno_pa_su_sc_draw val)
+{
+	return ((val) << A3XX_PC_PRIM_VTX_CNTL_POLYMODE_FRONT_PTYPE__SHIFT) & A3XX_PC_PRIM_VTX_CNTL_POLYMODE_FRONT_PTYPE__MASK;
+}
+#define A3XX_PC_PRIM_VTX_CNTL_POLYMODE_BACK_PTYPE__MASK		0x00000700
+#define A3XX_PC_PRIM_VTX_CNTL_POLYMODE_BACK_PTYPE__SHIFT	8
+static inline uint32_t A3XX_PC_PRIM_VTX_CNTL_POLYMODE_BACK_PTYPE(enum adreno_pa_su_sc_draw val)
+{
+	return ((val) << A3XX_PC_PRIM_VTX_CNTL_POLYMODE_BACK_PTYPE__SHIFT) & A3XX_PC_PRIM_VTX_CNTL_POLYMODE_BACK_PTYPE__MASK;
+}
+#define A3XX_PC_PRIM_VTX_CNTL_PROVOKING_VTX_LAST		0x02000000
+
+#define REG_A3XX_PC_RESTART_INDEX				0x000021ed
+
+#define REG_A3XX_HLSQ_CONTROL_0_REG				0x00002200
+#define A3XX_HLSQ_CONTROL_0_REG_FSTHREADSIZE__MASK		0x00000010
+#define A3XX_HLSQ_CONTROL_0_REG_FSTHREADSIZE__SHIFT		4
+static inline uint32_t A3XX_HLSQ_CONTROL_0_REG_FSTHREADSIZE(enum a3xx_threadsize val)
+{
+	return ((val) << A3XX_HLSQ_CONTROL_0_REG_FSTHREADSIZE__SHIFT) & A3XX_HLSQ_CONTROL_0_REG_FSTHREADSIZE__MASK;
+}
+#define A3XX_HLSQ_CONTROL_0_REG_FSSUPERTHREADENABLE		0x00000040
+#define A3XX_HLSQ_CONTROL_0_REG_SPSHADERRESTART			0x00000200
+#define A3XX_HLSQ_CONTROL_0_REG_RESERVED2			0x00000400
+#define A3XX_HLSQ_CONTROL_0_REG_CHUNKDISABLE			0x04000000
+#define A3XX_HLSQ_CONTROL_0_REG_CONSTSWITCHMODE			0x08000000
+#define A3XX_HLSQ_CONTROL_0_REG_LAZYUPDATEDISABLE		0x10000000
+#define A3XX_HLSQ_CONTROL_0_REG_SPCONSTFULLUPDATE		0x20000000
+#define A3XX_HLSQ_CONTROL_0_REG_TPFULLUPDATE			0x40000000
+#define A3XX_HLSQ_CONTROL_0_REG_SINGLECONTEXT			0x80000000
+
+#define REG_A3XX_HLSQ_CONTROL_1_REG				0x00002201
+#define A3XX_HLSQ_CONTROL_1_REG_VSTHREADSIZE__MASK		0x00000040
+#define A3XX_HLSQ_CONTROL_1_REG_VSTHREADSIZE__SHIFT		6
+static inline uint32_t A3XX_HLSQ_CONTROL_1_REG_VSTHREADSIZE(enum a3xx_threadsize val)
+{
+	return ((val) << A3XX_HLSQ_CONTROL_1_REG_VSTHREADSIZE__SHIFT) & A3XX_HLSQ_CONTROL_1_REG_VSTHREADSIZE__MASK;
+}
+#define A3XX_HLSQ_CONTROL_1_REG_VSSUPERTHREADENABLE		0x00000100
+#define A3XX_HLSQ_CONTROL_1_REG_RESERVED1			0x00000200
+
+#define REG_A3XX_HLSQ_CONTROL_2_REG				0x00002202
+#define A3XX_HLSQ_CONTROL_2_REG_PRIMALLOCTHRESHOLD__MASK	0xfc000000
+#define A3XX_HLSQ_CONTROL_2_REG_PRIMALLOCTHRESHOLD__SHIFT	26
+static inline uint32_t A3XX_HLSQ_CONTROL_2_REG_PRIMALLOCTHRESHOLD(uint32_t val)
+{
+	return ((val) << A3XX_HLSQ_CONTROL_2_REG_PRIMALLOCTHRESHOLD__SHIFT) & A3XX_HLSQ_CONTROL_2_REG_PRIMALLOCTHRESHOLD__MASK;
+}
+
+#define REG_A3XX_HLSQ_CONTROL_3_REG				0x00002203
+
+#define REG_A3XX_HLSQ_VS_CONTROL_REG				0x00002204
+#define A3XX_HLSQ_VS_CONTROL_REG_CONSTLENGTH__MASK		0x00000fff
+#define A3XX_HLSQ_VS_CONTROL_REG_CONSTLENGTH__SHIFT		0
+static inline uint32_t A3XX_HLSQ_VS_CONTROL_REG_CONSTLENGTH(uint32_t val)
+{
+	return ((val) << A3XX_HLSQ_VS_CONTROL_REG_CONSTLENGTH__SHIFT) & A3XX_HLSQ_VS_CONTROL_REG_CONSTLENGTH__MASK;
+}
+#define A3XX_HLSQ_VS_CONTROL_REG_CONSTSTARTOFFSET__MASK		0x00fff000
+#define A3XX_HLSQ_VS_CONTROL_REG_CONSTSTARTOFFSET__SHIFT	12
+static inline uint32_t A3XX_HLSQ_VS_CONTROL_REG_CONSTSTARTOFFSET(uint32_t val)
+{
+	return ((val) << A3XX_HLSQ_VS_CONTROL_REG_CONSTSTARTOFFSET__SHIFT) & A3XX_HLSQ_VS_CONTROL_REG_CONSTSTARTOFFSET__MASK;
+}
+#define A3XX_HLSQ_VS_CONTROL_REG_INSTRLENGTH__MASK		0xff000000
+#define A3XX_HLSQ_VS_CONTROL_REG_INSTRLENGTH__SHIFT		24
+static inline uint32_t A3XX_HLSQ_VS_CONTROL_REG_INSTRLENGTH(uint32_t val)
+{
+	return ((val) << A3XX_HLSQ_VS_CONTROL_REG_INSTRLENGTH__SHIFT) & A3XX_HLSQ_VS_CONTROL_REG_INSTRLENGTH__MASK;
+}
+
+#define REG_A3XX_HLSQ_FS_CONTROL_REG				0x00002205
+#define A3XX_HLSQ_FS_CONTROL_REG_CONSTLENGTH__MASK		0x00000fff
+#define A3XX_HLSQ_FS_CONTROL_REG_CONSTLENGTH__SHIFT		0
+static inline uint32_t A3XX_HLSQ_FS_CONTROL_REG_CONSTLENGTH(uint32_t val)
+{
+	return ((val) << A3XX_HLSQ_FS_CONTROL_REG_CONSTLENGTH__SHIFT) & A3XX_HLSQ_FS_CONTROL_REG_CONSTLENGTH__MASK;
+}
+#define A3XX_HLSQ_FS_CONTROL_REG_CONSTSTARTOFFSET__MASK		0x00fff000
+#define A3XX_HLSQ_FS_CONTROL_REG_CONSTSTARTOFFSET__SHIFT	12
+static inline uint32_t A3XX_HLSQ_FS_CONTROL_REG_CONSTSTARTOFFSET(uint32_t val)
+{
+	return ((val) << A3XX_HLSQ_FS_CONTROL_REG_CONSTSTARTOFFSET__SHIFT) & A3XX_HLSQ_FS_CONTROL_REG_CONSTSTARTOFFSET__MASK;
+}
+#define A3XX_HLSQ_FS_CONTROL_REG_INSTRLENGTH__MASK		0xff000000
+#define A3XX_HLSQ_FS_CONTROL_REG_INSTRLENGTH__SHIFT		24
+static inline uint32_t A3XX_HLSQ_FS_CONTROL_REG_INSTRLENGTH(uint32_t val)
+{
+	return ((val) << A3XX_HLSQ_FS_CONTROL_REG_INSTRLENGTH__SHIFT) & A3XX_HLSQ_FS_CONTROL_REG_INSTRLENGTH__MASK;
+}
+
+#define REG_A3XX_HLSQ_CONST_VSPRESV_RANGE_REG			0x00002206
+#define A3XX_HLSQ_CONST_VSPRESV_RANGE_REG_STARTENTRY__MASK	0x0000ffff
+#define A3XX_HLSQ_CONST_VSPRESV_RANGE_REG_STARTENTRY__SHIFT	0
+static inline uint32_t A3XX_HLSQ_CONST_VSPRESV_RANGE_REG_STARTENTRY(uint32_t val)
+{
+	return ((val) << A3XX_HLSQ_CONST_VSPRESV_RANGE_REG_STARTENTRY__SHIFT) & A3XX_HLSQ_CONST_VSPRESV_RANGE_REG_STARTENTRY__MASK;
+}
+#define A3XX_HLSQ_CONST_VSPRESV_RANGE_REG_ENDENTRY__MASK	0xffff0000
+#define A3XX_HLSQ_CONST_VSPRESV_RANGE_REG_ENDENTRY__SHIFT	16
+static inline uint32_t A3XX_HLSQ_CONST_VSPRESV_RANGE_REG_ENDENTRY(uint32_t val)
+{
+	return ((val) << A3XX_HLSQ_CONST_VSPRESV_RANGE_REG_ENDENTRY__SHIFT) & A3XX_HLSQ_CONST_VSPRESV_RANGE_REG_ENDENTRY__MASK;
+}
+
+#define REG_A3XX_HLSQ_CONST_FSPRESV_RANGE_REG			0x00002207
+#define A3XX_HLSQ_CONST_FSPRESV_RANGE_REG_STARTENTRY__MASK	0x0000ffff
+#define A3XX_HLSQ_CONST_FSPRESV_RANGE_REG_STARTENTRY__SHIFT	0
+static inline uint32_t A3XX_HLSQ_CONST_FSPRESV_RANGE_REG_STARTENTRY(uint32_t val)
+{
+	return ((val) << A3XX_HLSQ_CONST_FSPRESV_RANGE_REG_STARTENTRY__SHIFT) & A3XX_HLSQ_CONST_FSPRESV_RANGE_REG_STARTENTRY__MASK;
+}
+#define A3XX_HLSQ_CONST_FSPRESV_RANGE_REG_ENDENTRY__MASK	0xffff0000
+#define A3XX_HLSQ_CONST_FSPRESV_RANGE_REG_ENDENTRY__SHIFT	16
+static inline uint32_t A3XX_HLSQ_CONST_FSPRESV_RANGE_REG_ENDENTRY(uint32_t val)
+{
+	return ((val) << A3XX_HLSQ_CONST_FSPRESV_RANGE_REG_ENDENTRY__SHIFT) & A3XX_HLSQ_CONST_FSPRESV_RANGE_REG_ENDENTRY__MASK;
+}
+
+#define REG_A3XX_HLSQ_CL_NDRANGE_0_REG				0x0000220a
+
+#define REG_A3XX_HLSQ_CL_NDRANGE_1_REG				0x0000220b
+
+#define REG_A3XX_HLSQ_CL_NDRANGE_2_REG				0x0000220c
+
+#define REG_A3XX_HLSQ_CL_CONTROL_0_REG				0x00002211
+
+#define REG_A3XX_HLSQ_CL_CONTROL_1_REG				0x00002212
+
+#define REG_A3XX_HLSQ_CL_KERNEL_CONST_REG			0x00002214
+
+#define REG_A3XX_HLSQ_CL_KERNEL_GROUP_X_REG			0x00002215
+
+#define REG_A3XX_HLSQ_CL_KERNEL_GROUP_Z_REG			0x00002217
+
+#define REG_A3XX_HLSQ_CL_WG_OFFSET_REG				0x0000221a
+
+#define REG_A3XX_VFD_CONTROL_0					0x00002240
+#define A3XX_VFD_CONTROL_0_TOTALATTRTOVS__MASK			0x0003ffff
+#define A3XX_VFD_CONTROL_0_TOTALATTRTOVS__SHIFT			0
+static inline uint32_t A3XX_VFD_CONTROL_0_TOTALATTRTOVS(uint32_t val)
+{
+	return ((val) << A3XX_VFD_CONTROL_0_TOTALATTRTOVS__SHIFT) & A3XX_VFD_CONTROL_0_TOTALATTRTOVS__MASK;
+}
+#define A3XX_VFD_CONTROL_0_PACKETSIZE__MASK			0x003c0000
+#define A3XX_VFD_CONTROL_0_PACKETSIZE__SHIFT			18
+static inline uint32_t A3XX_VFD_CONTROL_0_PACKETSIZE(uint32_t val)
+{
+	return ((val) << A3XX_VFD_CONTROL_0_PACKETSIZE__SHIFT) & A3XX_VFD_CONTROL_0_PACKETSIZE__MASK;
+}
+#define A3XX_VFD_CONTROL_0_STRMDECINSTRCNT__MASK		0x07c00000
+#define A3XX_VFD_CONTROL_0_STRMDECINSTRCNT__SHIFT		22
+static inline uint32_t A3XX_VFD_CONTROL_0_STRMDECINSTRCNT(uint32_t val)
+{
+	return ((val) << A3XX_VFD_CONTROL_0_STRMDECINSTRCNT__SHIFT) & A3XX_VFD_CONTROL_0_STRMDECINSTRCNT__MASK;
+}
+#define A3XX_VFD_CONTROL_0_STRMFETCHINSTRCNT__MASK		0xf8000000
+#define A3XX_VFD_CONTROL_0_STRMFETCHINSTRCNT__SHIFT		27
+static inline uint32_t A3XX_VFD_CONTROL_0_STRMFETCHINSTRCNT(uint32_t val)
+{
+	return ((val) << A3XX_VFD_CONTROL_0_STRMFETCHINSTRCNT__SHIFT) & A3XX_VFD_CONTROL_0_STRMFETCHINSTRCNT__MASK;
+}
+
+#define REG_A3XX_VFD_CONTROL_1					0x00002241
+#define A3XX_VFD_CONTROL_1_MAXSTORAGE__MASK			0x0000ffff
+#define A3XX_VFD_CONTROL_1_MAXSTORAGE__SHIFT			0
+static inline uint32_t A3XX_VFD_CONTROL_1_MAXSTORAGE(uint32_t val)
+{
+	return ((val) << A3XX_VFD_CONTROL_1_MAXSTORAGE__SHIFT) & A3XX_VFD_CONTROL_1_MAXSTORAGE__MASK;
+}
+#define A3XX_VFD_CONTROL_1_REGID4VTX__MASK			0x00ff0000
+#define A3XX_VFD_CONTROL_1_REGID4VTX__SHIFT			16
+static inline uint32_t A3XX_VFD_CONTROL_1_REGID4VTX(uint32_t val)
+{
+	return ((val) << A3XX_VFD_CONTROL_1_REGID4VTX__SHIFT) & A3XX_VFD_CONTROL_1_REGID4VTX__MASK;
+}
+#define A3XX_VFD_CONTROL_1_REGID4INST__MASK			0xff000000
+#define A3XX_VFD_CONTROL_1_REGID4INST__SHIFT			24
+static inline uint32_t A3XX_VFD_CONTROL_1_REGID4INST(uint32_t val)
+{
+	return ((val) << A3XX_VFD_CONTROL_1_REGID4INST__SHIFT) & A3XX_VFD_CONTROL_1_REGID4INST__MASK;
+}
+
+#define REG_A3XX_VFD_INDEX_MIN					0x00002242
+
+#define REG_A3XX_VFD_INDEX_MAX					0x00002243
+
+#define REG_A3XX_VFD_INSTANCEID_OFFSET				0x00002244
+
+#define REG_A3XX_VFD_INDEX_OFFSET				0x00002245
+
+static inline uint32_t REG_A3XX_VFD_FETCH(uint32_t i0) { return 0x00002246 + 0x2*i0; }
+
+static inline uint32_t REG_A3XX_VFD_FETCH_INSTR_0(uint32_t i0) { return 0x00002246 + 0x2*i0; }
+#define A3XX_VFD_FETCH_INSTR_0_FETCHSIZE__MASK			0x0000007f
+#define A3XX_VFD_FETCH_INSTR_0_FETCHSIZE__SHIFT			0
+static inline uint32_t A3XX_VFD_FETCH_INSTR_0_FETCHSIZE(uint32_t val)
+{
+	return ((val) << A3XX_VFD_FETCH_INSTR_0_FETCHSIZE__SHIFT) & A3XX_VFD_FETCH_INSTR_0_FETCHSIZE__MASK;
+}
+#define A3XX_VFD_FETCH_INSTR_0_BUFSTRIDE__MASK			0x0001ff80
+#define A3XX_VFD_FETCH_INSTR_0_BUFSTRIDE__SHIFT			7
+static inline uint32_t A3XX_VFD_FETCH_INSTR_0_BUFSTRIDE(uint32_t val)
+{
+	return ((val) << A3XX_VFD_FETCH_INSTR_0_BUFSTRIDE__SHIFT) & A3XX_VFD_FETCH_INSTR_0_BUFSTRIDE__MASK;
+}
+#define A3XX_VFD_FETCH_INSTR_0_SWITCHNEXT			0x00020000
+#define A3XX_VFD_FETCH_INSTR_0_INDEXCODE__MASK			0x00fc0000
+#define A3XX_VFD_FETCH_INSTR_0_INDEXCODE__SHIFT			18
+static inline uint32_t A3XX_VFD_FETCH_INSTR_0_INDEXCODE(uint32_t val)
+{
+	return ((val) << A3XX_VFD_FETCH_INSTR_0_INDEXCODE__SHIFT) & A3XX_VFD_FETCH_INSTR_0_INDEXCODE__MASK;
+}
+#define A3XX_VFD_FETCH_INSTR_0_STEPRATE__MASK			0xff000000
+#define A3XX_VFD_FETCH_INSTR_0_STEPRATE__SHIFT			24
+static inline uint32_t A3XX_VFD_FETCH_INSTR_0_STEPRATE(uint32_t val)
+{
+	return ((val) << A3XX_VFD_FETCH_INSTR_0_STEPRATE__SHIFT) & A3XX_VFD_FETCH_INSTR_0_STEPRATE__MASK;
+}
+
+static inline uint32_t REG_A3XX_VFD_FETCH_INSTR_1(uint32_t i0) { return 0x00002247 + 0x2*i0; }
+
+static inline uint32_t REG_A3XX_VFD_DECODE(uint32_t i0) { return 0x00002266 + 0x1*i0; }
+
+static inline uint32_t REG_A3XX_VFD_DECODE_INSTR(uint32_t i0) { return 0x00002266 + 0x1*i0; }
+#define A3XX_VFD_DECODE_INSTR_WRITEMASK__MASK			0x0000000f
+#define A3XX_VFD_DECODE_INSTR_WRITEMASK__SHIFT			0
+static inline uint32_t A3XX_VFD_DECODE_INSTR_WRITEMASK(uint32_t val)
+{
+	return ((val) << A3XX_VFD_DECODE_INSTR_WRITEMASK__SHIFT) & A3XX_VFD_DECODE_INSTR_WRITEMASK__MASK;
+}
+#define A3XX_VFD_DECODE_INSTR_CONSTFILL				0x00000010
+#define A3XX_VFD_DECODE_INSTR_FORMAT__MASK			0x00000fc0
+#define A3XX_VFD_DECODE_INSTR_FORMAT__SHIFT			6
+static inline uint32_t A3XX_VFD_DECODE_INSTR_FORMAT(enum a3xx_vtx_fmt val)
+{
+	return ((val) << A3XX_VFD_DECODE_INSTR_FORMAT__SHIFT) & A3XX_VFD_DECODE_INSTR_FORMAT__MASK;
+}
+#define A3XX_VFD_DECODE_INSTR_REGID__MASK			0x000ff000
+#define A3XX_VFD_DECODE_INSTR_REGID__SHIFT			12
+static inline uint32_t A3XX_VFD_DECODE_INSTR_REGID(uint32_t val)
+{
+	return ((val) << A3XX_VFD_DECODE_INSTR_REGID__SHIFT) & A3XX_VFD_DECODE_INSTR_REGID__MASK;
+}
+#define A3XX_VFD_DECODE_INSTR_SHIFTCNT__MASK			0x1f000000
+#define A3XX_VFD_DECODE_INSTR_SHIFTCNT__SHIFT			24
+static inline uint32_t A3XX_VFD_DECODE_INSTR_SHIFTCNT(uint32_t val)
+{
+	return ((val) << A3XX_VFD_DECODE_INSTR_SHIFTCNT__SHIFT) & A3XX_VFD_DECODE_INSTR_SHIFTCNT__MASK;
+}
+#define A3XX_VFD_DECODE_INSTR_LASTCOMPVALID			0x20000000
+#define A3XX_VFD_DECODE_INSTR_SWITCHNEXT			0x40000000
+
+#define REG_A3XX_VFD_VS_THREADING_THRESHOLD			0x0000227e
+#define A3XX_VFD_VS_THREADING_THRESHOLD_REGID_THRESHOLD__MASK	0x0000000f
+#define A3XX_VFD_VS_THREADING_THRESHOLD_REGID_THRESHOLD__SHIFT	0
+static inline uint32_t A3XX_VFD_VS_THREADING_THRESHOLD_REGID_THRESHOLD(uint32_t val)
+{
+	return ((val) << A3XX_VFD_VS_THREADING_THRESHOLD_REGID_THRESHOLD__SHIFT) & A3XX_VFD_VS_THREADING_THRESHOLD_REGID_THRESHOLD__MASK;
+}
+#define A3XX_VFD_VS_THREADING_THRESHOLD_REGID_VTXCNT__MASK	0x0000ff00
+#define A3XX_VFD_VS_THREADING_THRESHOLD_REGID_VTXCNT__SHIFT	8
+static inline uint32_t A3XX_VFD_VS_THREADING_THRESHOLD_REGID_VTXCNT(uint32_t val)
+{
+	return ((val) << A3XX_VFD_VS_THREADING_THRESHOLD_REGID_VTXCNT__SHIFT) & A3XX_VFD_VS_THREADING_THRESHOLD_REGID_VTXCNT__MASK;
+}
+
+#define REG_A3XX_VPC_ATTR					0x00002280
+#define A3XX_VPC_ATTR_TOTALATTR__MASK				0x00000fff
+#define A3XX_VPC_ATTR_TOTALATTR__SHIFT				0
+static inline uint32_t A3XX_VPC_ATTR_TOTALATTR(uint32_t val)
+{
+	return ((val) << A3XX_VPC_ATTR_TOTALATTR__SHIFT) & A3XX_VPC_ATTR_TOTALATTR__MASK;
+}
+#define A3XX_VPC_ATTR_THRDASSIGN__MASK				0x0ffff000
+#define A3XX_VPC_ATTR_THRDASSIGN__SHIFT				12
+static inline uint32_t A3XX_VPC_ATTR_THRDASSIGN(uint32_t val)
+{
+	return ((val) << A3XX_VPC_ATTR_THRDASSIGN__SHIFT) & A3XX_VPC_ATTR_THRDASSIGN__MASK;
+}
+#define A3XX_VPC_ATTR_LMSIZE__MASK				0xf0000000
+#define A3XX_VPC_ATTR_LMSIZE__SHIFT				28
+static inline uint32_t A3XX_VPC_ATTR_LMSIZE(uint32_t val)
+{
+	return ((val) << A3XX_VPC_ATTR_LMSIZE__SHIFT) & A3XX_VPC_ATTR_LMSIZE__MASK;
+}
+
+#define REG_A3XX_VPC_PACK					0x00002281
+#define A3XX_VPC_PACK_NUMFPNONPOSVAR__MASK			0x0000ff00
+#define A3XX_VPC_PACK_NUMFPNONPOSVAR__SHIFT			8
+static inline uint32_t A3XX_VPC_PACK_NUMFPNONPOSVAR(uint32_t val)
+{
+	return ((val) << A3XX_VPC_PACK_NUMFPNONPOSVAR__SHIFT) & A3XX_VPC_PACK_NUMFPNONPOSVAR__MASK;
+}
+#define A3XX_VPC_PACK_NUMNONPOSVSVAR__MASK			0x00ff0000
+#define A3XX_VPC_PACK_NUMNONPOSVSVAR__SHIFT			16
+static inline uint32_t A3XX_VPC_PACK_NUMNONPOSVSVAR(uint32_t val)
+{
+	return ((val) << A3XX_VPC_PACK_NUMNONPOSVSVAR__SHIFT) & A3XX_VPC_PACK_NUMNONPOSVSVAR__MASK;
+}
+
+static inline uint32_t REG_A3XX_VPC_VARYING_INTERP(uint32_t i0) { return 0x00002282 + 0x1*i0; }
+
+static inline uint32_t REG_A3XX_VPC_VARYING_INTERP_MODE(uint32_t i0) { return 0x00002282 + 0x1*i0; }
+
+static inline uint32_t REG_A3XX_VPC_VARYING_PS_REPL(uint32_t i0) { return 0x00002286 + 0x1*i0; }
+
+static inline uint32_t REG_A3XX_VPC_VARYING_PS_REPL_MODE(uint32_t i0) { return 0x00002286 + 0x1*i0; }
+
+#define REG_A3XX_VPC_VARY_CYLWRAP_ENABLE_0			0x0000228a
+
+#define REG_A3XX_VPC_VARY_CYLWRAP_ENABLE_1			0x0000228b
+
+#define REG_A3XX_SP_SP_CTRL_REG					0x000022c0
+#define A3XX_SP_SP_CTRL_REG_RESOLVE				0x00010000
+#define A3XX_SP_SP_CTRL_REG_CONSTMODE__MASK			0x000c0000
+#define A3XX_SP_SP_CTRL_REG_CONSTMODE__SHIFT			18
+static inline uint32_t A3XX_SP_SP_CTRL_REG_CONSTMODE(uint32_t val)
+{
+	return ((val) << A3XX_SP_SP_CTRL_REG_CONSTMODE__SHIFT) & A3XX_SP_SP_CTRL_REG_CONSTMODE__MASK;
+}
+#define A3XX_SP_SP_CTRL_REG_SLEEPMODE__MASK			0x00300000
+#define A3XX_SP_SP_CTRL_REG_SLEEPMODE__SHIFT			20
+static inline uint32_t A3XX_SP_SP_CTRL_REG_SLEEPMODE(uint32_t val)
+{
+	return ((val) << A3XX_SP_SP_CTRL_REG_SLEEPMODE__SHIFT) & A3XX_SP_SP_CTRL_REG_SLEEPMODE__MASK;
+}
+#define A3XX_SP_SP_CTRL_REG_LOMODE__MASK			0x00c00000
+#define A3XX_SP_SP_CTRL_REG_LOMODE__SHIFT			22
+static inline uint32_t A3XX_SP_SP_CTRL_REG_LOMODE(uint32_t val)
+{
+	return ((val) << A3XX_SP_SP_CTRL_REG_LOMODE__SHIFT) & A3XX_SP_SP_CTRL_REG_LOMODE__MASK;
+}
+
+#define REG_A3XX_SP_VS_CTRL_REG0				0x000022c4
+#define A3XX_SP_VS_CTRL_REG0_THREADMODE__MASK			0x00000001
+#define A3XX_SP_VS_CTRL_REG0_THREADMODE__SHIFT			0
+static inline uint32_t A3XX_SP_VS_CTRL_REG0_THREADMODE(enum a3xx_threadmode val)
+{
+	return ((val) << A3XX_SP_VS_CTRL_REG0_THREADMODE__SHIFT) & A3XX_SP_VS_CTRL_REG0_THREADMODE__MASK;
+}
+#define A3XX_SP_VS_CTRL_REG0_INSTRBUFFERMODE__MASK		0x00000002
+#define A3XX_SP_VS_CTRL_REG0_INSTRBUFFERMODE__SHIFT		1
+static inline uint32_t A3XX_SP_VS_CTRL_REG0_INSTRBUFFERMODE(enum a3xx_instrbuffermode val)
+{
+	return ((val) << A3XX_SP_VS_CTRL_REG0_INSTRBUFFERMODE__SHIFT) & A3XX_SP_VS_CTRL_REG0_INSTRBUFFERMODE__MASK;
+}
+#define A3XX_SP_VS_CTRL_REG0_CACHEINVALID			0x00000004
+#define A3XX_SP_VS_CTRL_REG0_HALFREGFOOTPRINT__MASK		0x000003f0
+#define A3XX_SP_VS_CTRL_REG0_HALFREGFOOTPRINT__SHIFT		4
+static inline uint32_t A3XX_SP_VS_CTRL_REG0_HALFREGFOOTPRINT(uint32_t val)
+{
+	return ((val) << A3XX_SP_VS_CTRL_REG0_HALFREGFOOTPRINT__SHIFT) & A3XX_SP_VS_CTRL_REG0_HALFREGFOOTPRINT__MASK;
+}
+#define A3XX_SP_VS_CTRL_REG0_FULLREGFOOTPRINT__MASK		0x0003fc00
+#define A3XX_SP_VS_CTRL_REG0_FULLREGFOOTPRINT__SHIFT		10
+static inline uint32_t A3XX_SP_VS_CTRL_REG0_FULLREGFOOTPRINT(uint32_t val)
+{
+	return ((val) << A3XX_SP_VS_CTRL_REG0_FULLREGFOOTPRINT__SHIFT) & A3XX_SP_VS_CTRL_REG0_FULLREGFOOTPRINT__MASK;
+}
+#define A3XX_SP_VS_CTRL_REG0_INOUTREGOVERLAP__MASK		0x000c0000
+#define A3XX_SP_VS_CTRL_REG0_INOUTREGOVERLAP__SHIFT		18
+static inline uint32_t A3XX_SP_VS_CTRL_REG0_INOUTREGOVERLAP(uint32_t val)
+{
+	return ((val) << A3XX_SP_VS_CTRL_REG0_INOUTREGOVERLAP__SHIFT) & A3XX_SP_VS_CTRL_REG0_INOUTREGOVERLAP__MASK;
+}
+#define A3XX_SP_VS_CTRL_REG0_THREADSIZE__MASK			0x00100000
+#define A3XX_SP_VS_CTRL_REG0_THREADSIZE__SHIFT			20
+static inline uint32_t A3XX_SP_VS_CTRL_REG0_THREADSIZE(enum a3xx_threadsize val)
+{
+	return ((val) << A3XX_SP_VS_CTRL_REG0_THREADSIZE__SHIFT) & A3XX_SP_VS_CTRL_REG0_THREADSIZE__MASK;
+}
+#define A3XX_SP_VS_CTRL_REG0_SUPERTHREADMODE			0x00200000
+#define A3XX_SP_VS_CTRL_REG0_PIXLODENABLE			0x00400000
+#define A3XX_SP_VS_CTRL_REG0_LENGTH__MASK			0xff000000
+#define A3XX_SP_VS_CTRL_REG0_LENGTH__SHIFT			24
+static inline uint32_t A3XX_SP_VS_CTRL_REG0_LENGTH(uint32_t val)
+{
+	return ((val) << A3XX_SP_VS_CTRL_REG0_LENGTH__SHIFT) & A3XX_SP_VS_CTRL_REG0_LENGTH__MASK;
+}
+
+#define REG_A3XX_SP_VS_CTRL_REG1				0x000022c5
+#define A3XX_SP_VS_CTRL_REG1_CONSTLENGTH__MASK			0x000003ff
+#define A3XX_SP_VS_CTRL_REG1_CONSTLENGTH__SHIFT			0
+static inline uint32_t A3XX_SP_VS_CTRL_REG1_CONSTLENGTH(uint32_t val)
+{
+	return ((val) << A3XX_SP_VS_CTRL_REG1_CONSTLENGTH__SHIFT) & A3XX_SP_VS_CTRL_REG1_CONSTLENGTH__MASK;
+}
+#define A3XX_SP_VS_CTRL_REG1_CONSTFOOTPRINT__MASK		0x000ffc00
+#define A3XX_SP_VS_CTRL_REG1_CONSTFOOTPRINT__SHIFT		10
+static inline uint32_t A3XX_SP_VS_CTRL_REG1_CONSTFOOTPRINT(uint32_t val)
+{
+	return ((val) << A3XX_SP_VS_CTRL_REG1_CONSTFOOTPRINT__SHIFT) & A3XX_SP_VS_CTRL_REG1_CONSTFOOTPRINT__MASK;
+}
+#define A3XX_SP_VS_CTRL_REG1_INITIALOUTSTANDING__MASK		0x3f000000
+#define A3XX_SP_VS_CTRL_REG1_INITIALOUTSTANDING__SHIFT		24
+static inline uint32_t A3XX_SP_VS_CTRL_REG1_INITIALOUTSTANDING(uint32_t val)
+{
+	return ((val) << A3XX_SP_VS_CTRL_REG1_INITIALOUTSTANDING__SHIFT) & A3XX_SP_VS_CTRL_REG1_INITIALOUTSTANDING__MASK;
+}
+
+#define REG_A3XX_SP_VS_PARAM_REG				0x000022c6
+#define A3XX_SP_VS_PARAM_REG_POSREGID__MASK			0x000000ff
+#define A3XX_SP_VS_PARAM_REG_POSREGID__SHIFT			0
+static inline uint32_t A3XX_SP_VS_PARAM_REG_POSREGID(uint32_t val)
+{
+	return ((val) << A3XX_SP_VS_PARAM_REG_POSREGID__SHIFT) & A3XX_SP_VS_PARAM_REG_POSREGID__MASK;
+}
+#define A3XX_SP_VS_PARAM_REG_PSIZEREGID__MASK			0x0000ff00
+#define A3XX_SP_VS_PARAM_REG_PSIZEREGID__SHIFT			8
+static inline uint32_t A3XX_SP_VS_PARAM_REG_PSIZEREGID(uint32_t val)
+{
+	return ((val) << A3XX_SP_VS_PARAM_REG_PSIZEREGID__SHIFT) & A3XX_SP_VS_PARAM_REG_PSIZEREGID__MASK;
+}
+#define A3XX_SP_VS_PARAM_REG_TOTALVSOUTVAR__MASK		0xfff00000
+#define A3XX_SP_VS_PARAM_REG_TOTALVSOUTVAR__SHIFT		20
+static inline uint32_t A3XX_SP_VS_PARAM_REG_TOTALVSOUTVAR(uint32_t val)
+{
+	return ((val) << A3XX_SP_VS_PARAM_REG_TOTALVSOUTVAR__SHIFT) & A3XX_SP_VS_PARAM_REG_TOTALVSOUTVAR__MASK;
+}
+
+static inline uint32_t REG_A3XX_SP_VS_OUT(uint32_t i0) { return 0x000022c7 + 0x1*i0; }
+
+static inline uint32_t REG_A3XX_SP_VS_OUT_REG(uint32_t i0) { return 0x000022c7 + 0x1*i0; }
+#define A3XX_SP_VS_OUT_REG_A_REGID__MASK			0x000001ff
+#define A3XX_SP_VS_OUT_REG_A_REGID__SHIFT			0
+static inline uint32_t A3XX_SP_VS_OUT_REG_A_REGID(uint32_t val)
+{
+	return ((val) << A3XX_SP_VS_OUT_REG_A_REGID__SHIFT) & A3XX_SP_VS_OUT_REG_A_REGID__MASK;
+}
+#define A3XX_SP_VS_OUT_REG_A_COMPMASK__MASK			0x00001e00
+#define A3XX_SP_VS_OUT_REG_A_COMPMASK__SHIFT			9
+static inline uint32_t A3XX_SP_VS_OUT_REG_A_COMPMASK(uint32_t val)
+{
+	return ((val) << A3XX_SP_VS_OUT_REG_A_COMPMASK__SHIFT) & A3XX_SP_VS_OUT_REG_A_COMPMASK__MASK;
+}
+#define A3XX_SP_VS_OUT_REG_B_REGID__MASK			0x01ff0000
+#define A3XX_SP_VS_OUT_REG_B_REGID__SHIFT			16
+static inline uint32_t A3XX_SP_VS_OUT_REG_B_REGID(uint32_t val)
+{
+	return ((val) << A3XX_SP_VS_OUT_REG_B_REGID__SHIFT) & A3XX_SP_VS_OUT_REG_B_REGID__MASK;
+}
+#define A3XX_SP_VS_OUT_REG_B_COMPMASK__MASK			0x1e000000
+#define A3XX_SP_VS_OUT_REG_B_COMPMASK__SHIFT			25
+static inline uint32_t A3XX_SP_VS_OUT_REG_B_COMPMASK(uint32_t val)
+{
+	return ((val) << A3XX_SP_VS_OUT_REG_B_COMPMASK__SHIFT) & A3XX_SP_VS_OUT_REG_B_COMPMASK__MASK;
+}
+
+static inline uint32_t REG_A3XX_SP_VS_VPC_DST(uint32_t i0) { return 0x000022d0 + 0x1*i0; }
+
+static inline uint32_t REG_A3XX_SP_VS_VPC_DST_REG(uint32_t i0) { return 0x000022d0 + 0x1*i0; }
+#define A3XX_SP_VS_VPC_DST_REG_OUTLOC0__MASK			0x000000ff
+#define A3XX_SP_VS_VPC_DST_REG_OUTLOC0__SHIFT			0
+static inline uint32_t A3XX_SP_VS_VPC_DST_REG_OUTLOC0(uint32_t val)
+{
+	return ((val) << A3XX_SP_VS_VPC_DST_REG_OUTLOC0__SHIFT) & A3XX_SP_VS_VPC_DST_REG_OUTLOC0__MASK;
+}
+#define A3XX_SP_VS_VPC_DST_REG_OUTLOC1__MASK			0x0000ff00
+#define A3XX_SP_VS_VPC_DST_REG_OUTLOC1__SHIFT			8
+static inline uint32_t A3XX_SP_VS_VPC_DST_REG_OUTLOC1(uint32_t val)
+{
+	return ((val) << A3XX_SP_VS_VPC_DST_REG_OUTLOC1__SHIFT) & A3XX_SP_VS_VPC_DST_REG_OUTLOC1__MASK;
+}
+#define A3XX_SP_VS_VPC_DST_REG_OUTLOC2__MASK			0x00ff0000
+#define A3XX_SP_VS_VPC_DST_REG_OUTLOC2__SHIFT			16
+static inline uint32_t A3XX_SP_VS_VPC_DST_REG_OUTLOC2(uint32_t val)
+{
+	return ((val) << A3XX_SP_VS_VPC_DST_REG_OUTLOC2__SHIFT) & A3XX_SP_VS_VPC_DST_REG_OUTLOC2__MASK;
+}
+#define A3XX_SP_VS_VPC_DST_REG_OUTLOC3__MASK			0xff000000
+#define A3XX_SP_VS_VPC_DST_REG_OUTLOC3__SHIFT			24
+static inline uint32_t A3XX_SP_VS_VPC_DST_REG_OUTLOC3(uint32_t val)
+{
+	return ((val) << A3XX_SP_VS_VPC_DST_REG_OUTLOC3__SHIFT) & A3XX_SP_VS_VPC_DST_REG_OUTLOC3__MASK;
+}
+
+#define REG_A3XX_SP_VS_OBJ_OFFSET_REG				0x000022d4
+#define A3XX_SP_VS_OBJ_OFFSET_REG_CONSTOBJECTOFFSET__MASK	0x01ff0000
+#define A3XX_SP_VS_OBJ_OFFSET_REG_CONSTOBJECTOFFSET__SHIFT	16
+static inline uint32_t A3XX_SP_VS_OBJ_OFFSET_REG_CONSTOBJECTOFFSET(uint32_t val)
+{
+	return ((val) << A3XX_SP_VS_OBJ_OFFSET_REG_CONSTOBJECTOFFSET__SHIFT) & A3XX_SP_VS_OBJ_OFFSET_REG_CONSTOBJECTOFFSET__MASK;
+}
+#define A3XX_SP_VS_OBJ_OFFSET_REG_SHADEROBJOFFSET__MASK		0xfe000000
+#define A3XX_SP_VS_OBJ_OFFSET_REG_SHADEROBJOFFSET__SHIFT	25
+static inline uint32_t A3XX_SP_VS_OBJ_OFFSET_REG_SHADEROBJOFFSET(uint32_t val)
+{
+	return ((val) << A3XX_SP_VS_OBJ_OFFSET_REG_SHADEROBJOFFSET__SHIFT) & A3XX_SP_VS_OBJ_OFFSET_REG_SHADEROBJOFFSET__MASK;
+}
+
+#define REG_A3XX_SP_VS_OBJ_START_REG				0x000022d5
+
+#define REG_A3XX_SP_VS_PVT_MEM_CTRL_REG				0x000022d6
+
+#define REG_A3XX_SP_VS_PVT_MEM_ADDR_REG				0x000022d7
+
+#define REG_A3XX_SP_VS_PVT_MEM_SIZE_REG				0x000022d8
+
+#define REG_A3XX_SP_VS_LENGTH_REG				0x000022df
+#define A3XX_SP_VS_LENGTH_REG_SHADERLENGTH__MASK		0xffffffff
+#define A3XX_SP_VS_LENGTH_REG_SHADERLENGTH__SHIFT		0
+static inline uint32_t A3XX_SP_VS_LENGTH_REG_SHADERLENGTH(uint32_t val)
+{
+	return ((val) << A3XX_SP_VS_LENGTH_REG_SHADERLENGTH__SHIFT) & A3XX_SP_VS_LENGTH_REG_SHADERLENGTH__MASK;
+}
+
+#define REG_A3XX_SP_FS_CTRL_REG0				0x000022e0
+#define A3XX_SP_FS_CTRL_REG0_THREADMODE__MASK			0x00000001
+#define A3XX_SP_FS_CTRL_REG0_THREADMODE__SHIFT			0
+static inline uint32_t A3XX_SP_FS_CTRL_REG0_THREADMODE(enum a3xx_threadmode val)
+{
+	return ((val) << A3XX_SP_FS_CTRL_REG0_THREADMODE__SHIFT) & A3XX_SP_FS_CTRL_REG0_THREADMODE__MASK;
+}
+#define A3XX_SP_FS_CTRL_REG0_INSTRBUFFERMODE__MASK		0x00000002
+#define A3XX_SP_FS_CTRL_REG0_INSTRBUFFERMODE__SHIFT		1
+static inline uint32_t A3XX_SP_FS_CTRL_REG0_INSTRBUFFERMODE(enum a3xx_instrbuffermode val)
+{
+	return ((val) << A3XX_SP_FS_CTRL_REG0_INSTRBUFFERMODE__SHIFT) & A3XX_SP_FS_CTRL_REG0_INSTRBUFFERMODE__MASK;
+}
+#define A3XX_SP_FS_CTRL_REG0_CACHEINVALID			0x00000004
+#define A3XX_SP_FS_CTRL_REG0_HALFREGFOOTPRINT__MASK		0x000003f0
+#define A3XX_SP_FS_CTRL_REG0_HALFREGFOOTPRINT__SHIFT		4
+static inline uint32_t A3XX_SP_FS_CTRL_REG0_HALFREGFOOTPRINT(uint32_t val)
+{
+	return ((val) << A3XX_SP_FS_CTRL_REG0_HALFREGFOOTPRINT__SHIFT) & A3XX_SP_FS_CTRL_REG0_HALFREGFOOTPRINT__MASK;
+}
+#define A3XX_SP_FS_CTRL_REG0_FULLREGFOOTPRINT__MASK		0x0003fc00
+#define A3XX_SP_FS_CTRL_REG0_FULLREGFOOTPRINT__SHIFT		10
+static inline uint32_t A3XX_SP_FS_CTRL_REG0_FULLREGFOOTPRINT(uint32_t val)
+{
+	return ((val) << A3XX_SP_FS_CTRL_REG0_FULLREGFOOTPRINT__SHIFT) & A3XX_SP_FS_CTRL_REG0_FULLREGFOOTPRINT__MASK;
+}
+#define A3XX_SP_FS_CTRL_REG0_INOUTREGOVERLAP__MASK		0x000c0000
+#define A3XX_SP_FS_CTRL_REG0_INOUTREGOVERLAP__SHIFT		18
+static inline uint32_t A3XX_SP_FS_CTRL_REG0_INOUTREGOVERLAP(uint32_t val)
+{
+	return ((val) << A3XX_SP_FS_CTRL_REG0_INOUTREGOVERLAP__SHIFT) & A3XX_SP_FS_CTRL_REG0_INOUTREGOVERLAP__MASK;
+}
+#define A3XX_SP_FS_CTRL_REG0_THREADSIZE__MASK			0x00100000
+#define A3XX_SP_FS_CTRL_REG0_THREADSIZE__SHIFT			20
+static inline uint32_t A3XX_SP_FS_CTRL_REG0_THREADSIZE(enum a3xx_threadsize val)
+{
+	return ((val) << A3XX_SP_FS_CTRL_REG0_THREADSIZE__SHIFT) & A3XX_SP_FS_CTRL_REG0_THREADSIZE__MASK;
+}
+#define A3XX_SP_FS_CTRL_REG0_SUPERTHREADMODE			0x00200000
+#define A3XX_SP_FS_CTRL_REG0_PIXLODENABLE			0x00400000
+#define A3XX_SP_FS_CTRL_REG0_LENGTH__MASK			0xff000000
+#define A3XX_SP_FS_CTRL_REG0_LENGTH__SHIFT			24
+static inline uint32_t A3XX_SP_FS_CTRL_REG0_LENGTH(uint32_t val)
+{
+	return ((val) << A3XX_SP_FS_CTRL_REG0_LENGTH__SHIFT) & A3XX_SP_FS_CTRL_REG0_LENGTH__MASK;
+}
+
+#define REG_A3XX_SP_FS_CTRL_REG1				0x000022e1
+#define A3XX_SP_FS_CTRL_REG1_CONSTLENGTH__MASK			0x000003ff
+#define A3XX_SP_FS_CTRL_REG1_CONSTLENGTH__SHIFT			0
+static inline uint32_t A3XX_SP_FS_CTRL_REG1_CONSTLENGTH(uint32_t val)
+{
+	return ((val) << A3XX_SP_FS_CTRL_REG1_CONSTLENGTH__SHIFT) & A3XX_SP_FS_CTRL_REG1_CONSTLENGTH__MASK;
+}
+#define A3XX_SP_FS_CTRL_REG1_CONSTFOOTPRINT__MASK		0x000ffc00
+#define A3XX_SP_FS_CTRL_REG1_CONSTFOOTPRINT__SHIFT		10
+static inline uint32_t A3XX_SP_FS_CTRL_REG1_CONSTFOOTPRINT(uint32_t val)
+{
+	return ((val) << A3XX_SP_FS_CTRL_REG1_CONSTFOOTPRINT__SHIFT) & A3XX_SP_FS_CTRL_REG1_CONSTFOOTPRINT__MASK;
+}
+#define A3XX_SP_FS_CTRL_REG1_INITIALOUTSTANDING__MASK		0x00f00000
+#define A3XX_SP_FS_CTRL_REG1_INITIALOUTSTANDING__SHIFT		20
+static inline uint32_t A3XX_SP_FS_CTRL_REG1_INITIALOUTSTANDING(uint32_t val)
+{
+	return ((val) << A3XX_SP_FS_CTRL_REG1_INITIALOUTSTANDING__SHIFT) & A3XX_SP_FS_CTRL_REG1_INITIALOUTSTANDING__MASK;
+}
+#define A3XX_SP_FS_CTRL_REG1_HALFPRECVAROFFSET__MASK		0x3f000000
+#define A3XX_SP_FS_CTRL_REG1_HALFPRECVAROFFSET__SHIFT		24
+static inline uint32_t A3XX_SP_FS_CTRL_REG1_HALFPRECVAROFFSET(uint32_t val)
+{
+	return ((val) << A3XX_SP_FS_CTRL_REG1_HALFPRECVAROFFSET__SHIFT) & A3XX_SP_FS_CTRL_REG1_HALFPRECVAROFFSET__MASK;
+}
+
+#define REG_A3XX_SP_FS_OBJ_OFFSET_REG				0x000022e2
+#define A3XX_SP_FS_OBJ_OFFSET_REG_CONSTOBJECTOFFSET__MASK	0x01ff0000
+#define A3XX_SP_FS_OBJ_OFFSET_REG_CONSTOBJECTOFFSET__SHIFT	16
+static inline uint32_t A3XX_SP_FS_OBJ_OFFSET_REG_CONSTOBJECTOFFSET(uint32_t val)
+{
+	return ((val) << A3XX_SP_FS_OBJ_OFFSET_REG_CONSTOBJECTOFFSET__SHIFT) & A3XX_SP_FS_OBJ_OFFSET_REG_CONSTOBJECTOFFSET__MASK;
+}
+#define A3XX_SP_FS_OBJ_OFFSET_REG_SHADEROBJOFFSET__MASK		0xfe000000
+#define A3XX_SP_FS_OBJ_OFFSET_REG_SHADEROBJOFFSET__SHIFT	25
+static inline uint32_t A3XX_SP_FS_OBJ_OFFSET_REG_SHADEROBJOFFSET(uint32_t val)
+{
+	return ((val) << A3XX_SP_FS_OBJ_OFFSET_REG_SHADEROBJOFFSET__SHIFT) & A3XX_SP_FS_OBJ_OFFSET_REG_SHADEROBJOFFSET__MASK;
+}
+
+#define REG_A3XX_SP_FS_OBJ_START_REG				0x000022e3
+
+#define REG_A3XX_SP_FS_PVT_MEM_CTRL_REG				0x000022e4
+
+#define REG_A3XX_SP_FS_PVT_MEM_ADDR_REG				0x000022e5
+
+#define REG_A3XX_SP_FS_PVT_MEM_SIZE_REG				0x000022e6
+
+#define REG_A3XX_SP_FS_FLAT_SHAD_MODE_REG_0			0x000022e8
+
+#define REG_A3XX_SP_FS_FLAT_SHAD_MODE_REG_1			0x000022e9
+
+#define REG_A3XX_SP_FS_OUTPUT_REG				0x000022ec
+
+static inline uint32_t REG_A3XX_SP_FS_MRT(uint32_t i0) { return 0x000022f0 + 0x1*i0; }
+
+static inline uint32_t REG_A3XX_SP_FS_MRT_REG(uint32_t i0) { return 0x000022f0 + 0x1*i0; }
+#define A3XX_SP_FS_MRT_REG_REGID__MASK				0x000000ff
+#define A3XX_SP_FS_MRT_REG_REGID__SHIFT				0
+static inline uint32_t A3XX_SP_FS_MRT_REG_REGID(uint32_t val)
+{
+	return ((val) << A3XX_SP_FS_MRT_REG_REGID__SHIFT) & A3XX_SP_FS_MRT_REG_REGID__MASK;
+}
+#define A3XX_SP_FS_MRT_REG_HALF_PRECISION			0x00000100
+
+static inline uint32_t REG_A3XX_SP_FS_IMAGE_OUTPUT(uint32_t i0) { return 0x000022f4 + 0x1*i0; }
+
+static inline uint32_t REG_A3XX_SP_FS_IMAGE_OUTPUT_REG(uint32_t i0) { return 0x000022f4 + 0x1*i0; }
+#define A3XX_SP_FS_IMAGE_OUTPUT_REG_MRTFORMAT__MASK		0x0000003f
+#define A3XX_SP_FS_IMAGE_OUTPUT_REG_MRTFORMAT__SHIFT		0
+static inline uint32_t A3XX_SP_FS_IMAGE_OUTPUT_REG_MRTFORMAT(enum a3xx_color_fmt val)
+{
+	return ((val) << A3XX_SP_FS_IMAGE_OUTPUT_REG_MRTFORMAT__SHIFT) & A3XX_SP_FS_IMAGE_OUTPUT_REG_MRTFORMAT__MASK;
+}
+
+#define REG_A3XX_SP_FS_LENGTH_REG				0x000022ff
+#define A3XX_SP_FS_LENGTH_REG_SHADERLENGTH__MASK		0xffffffff
+#define A3XX_SP_FS_LENGTH_REG_SHADERLENGTH__SHIFT		0
+static inline uint32_t A3XX_SP_FS_LENGTH_REG_SHADERLENGTH(uint32_t val)
+{
+	return ((val) << A3XX_SP_FS_LENGTH_REG_SHADERLENGTH__SHIFT) & A3XX_SP_FS_LENGTH_REG_SHADERLENGTH__MASK;
+}
+
+#define REG_A3XX_TPL1_TP_VS_TEX_OFFSET				0x00002340
+#define A3XX_TPL1_TP_VS_TEX_OFFSET_SAMPLEROFFSET__MASK		0x000000ff
+#define A3XX_TPL1_TP_VS_TEX_OFFSET_SAMPLEROFFSET__SHIFT		0
+static inline uint32_t A3XX_TPL1_TP_VS_TEX_OFFSET_SAMPLEROFFSET(uint32_t val)
+{
+	return ((val) << A3XX_TPL1_TP_VS_TEX_OFFSET_SAMPLEROFFSET__SHIFT) & A3XX_TPL1_TP_VS_TEX_OFFSET_SAMPLEROFFSET__MASK;
+}
+#define A3XX_TPL1_TP_VS_TEX_OFFSET_MEMOBJOFFSET__MASK		0x0000ff00
+#define A3XX_TPL1_TP_VS_TEX_OFFSET_MEMOBJOFFSET__SHIFT		8
+static inline uint32_t A3XX_TPL1_TP_VS_TEX_OFFSET_MEMOBJOFFSET(uint32_t val)
+{
+	return ((val) << A3XX_TPL1_TP_VS_TEX_OFFSET_MEMOBJOFFSET__SHIFT) & A3XX_TPL1_TP_VS_TEX_OFFSET_MEMOBJOFFSET__MASK;
+}
+#define A3XX_TPL1_TP_VS_TEX_OFFSET_BASETABLEPTR__MASK		0xffff0000
+#define A3XX_TPL1_TP_VS_TEX_OFFSET_BASETABLEPTR__SHIFT		16
+static inline uint32_t A3XX_TPL1_TP_VS_TEX_OFFSET_BASETABLEPTR(uint32_t val)
+{
+	return ((val) << A3XX_TPL1_TP_VS_TEX_OFFSET_BASETABLEPTR__SHIFT) & A3XX_TPL1_TP_VS_TEX_OFFSET_BASETABLEPTR__MASK;
+}
+
+#define REG_A3XX_TPL1_TP_VS_BORDER_COLOR_BASE_ADDR		0x00002341
+
+#define REG_A3XX_TPL1_TP_FS_TEX_OFFSET				0x00002342
+#define A3XX_TPL1_TP_FS_TEX_OFFSET_SAMPLEROFFSET__MASK		0x000000ff
+#define A3XX_TPL1_TP_FS_TEX_OFFSET_SAMPLEROFFSET__SHIFT		0
+static inline uint32_t A3XX_TPL1_TP_FS_TEX_OFFSET_SAMPLEROFFSET(uint32_t val)
+{
+	return ((val) << A3XX_TPL1_TP_FS_TEX_OFFSET_SAMPLEROFFSET__SHIFT) & A3XX_TPL1_TP_FS_TEX_OFFSET_SAMPLEROFFSET__MASK;
+}
+#define A3XX_TPL1_TP_FS_TEX_OFFSET_MEMOBJOFFSET__MASK		0x0000ff00
+#define A3XX_TPL1_TP_FS_TEX_OFFSET_MEMOBJOFFSET__SHIFT		8
+static inline uint32_t A3XX_TPL1_TP_FS_TEX_OFFSET_MEMOBJOFFSET(uint32_t val)
+{
+	return ((val) << A3XX_TPL1_TP_FS_TEX_OFFSET_MEMOBJOFFSET__SHIFT) & A3XX_TPL1_TP_FS_TEX_OFFSET_MEMOBJOFFSET__MASK;
+}
+#define A3XX_TPL1_TP_FS_TEX_OFFSET_BASETABLEPTR__MASK		0xffff0000
+#define A3XX_TPL1_TP_FS_TEX_OFFSET_BASETABLEPTR__SHIFT		16
+static inline uint32_t A3XX_TPL1_TP_FS_TEX_OFFSET_BASETABLEPTR(uint32_t val)
+{
+	return ((val) << A3XX_TPL1_TP_FS_TEX_OFFSET_BASETABLEPTR__SHIFT) & A3XX_TPL1_TP_FS_TEX_OFFSET_BASETABLEPTR__MASK;
+}
+
+#define REG_A3XX_TPL1_TP_FS_BORDER_COLOR_BASE_ADDR		0x00002343
+
+#define REG_A3XX_VBIF_CLKON					0x00003001
+
+#define REG_A3XX_VBIF_FIXED_SORT_EN				0x0000300c
+
+#define REG_A3XX_VBIF_FIXED_SORT_SEL0				0x0000300d
+
+#define REG_A3XX_VBIF_FIXED_SORT_SEL1				0x0000300e
+
+#define REG_A3XX_VBIF_ABIT_SORT					0x0000301c
+
+#define REG_A3XX_VBIF_ABIT_SORT_CONF				0x0000301d
+
+#define REG_A3XX_VBIF_GATE_OFF_WRREQ_EN				0x0000302a
+
+#define REG_A3XX_VBIF_IN_RD_LIM_CONF0				0x0000302c
+
+#define REG_A3XX_VBIF_IN_RD_LIM_CONF1				0x0000302d
+
+#define REG_A3XX_VBIF_IN_WR_LIM_CONF0				0x00003030
+
+#define REG_A3XX_VBIF_IN_WR_LIM_CONF1				0x00003031
+
+#define REG_A3XX_VBIF_OUT_RD_LIM_CONF0				0x00003034
+
+#define REG_A3XX_VBIF_OUT_WR_LIM_CONF0				0x00003035
+
+#define REG_A3XX_VBIF_DDR_OUT_MAX_BURST				0x00003036
+
+#define REG_A3XX_VBIF_ARB_CTL					0x0000303c
+
+#define REG_A3XX_VBIF_ROUND_ROBIN_QOS_ARB			0x00003049
+
+#define REG_A3XX_VBIF_OUT_AXI_AMEMTYPE_CONF0			0x00003058
+
+#define REG_A3XX_VBIF_OUT_AXI_AOOO_EN				0x0000305e
+
+#define REG_A3XX_VBIF_OUT_AXI_AOOO				0x0000305f
+
+#define REG_A3XX_VSC_BIN_SIZE					0x00000c01
+#define A3XX_VSC_BIN_SIZE_WIDTH__MASK				0x0000001f
+#define A3XX_VSC_BIN_SIZE_WIDTH__SHIFT				0
+static inline uint32_t A3XX_VSC_BIN_SIZE_WIDTH(uint32_t val)
+{
+	return ((val >> 5) << A3XX_VSC_BIN_SIZE_WIDTH__SHIFT) & A3XX_VSC_BIN_SIZE_WIDTH__MASK;
+}
+#define A3XX_VSC_BIN_SIZE_HEIGHT__MASK				0x000003e0
+#define A3XX_VSC_BIN_SIZE_HEIGHT__SHIFT				5
+static inline uint32_t A3XX_VSC_BIN_SIZE_HEIGHT(uint32_t val)
+{
+	return ((val >> 5) << A3XX_VSC_BIN_SIZE_HEIGHT__SHIFT) & A3XX_VSC_BIN_SIZE_HEIGHT__MASK;
+}
+
+#define REG_A3XX_VSC_SIZE_ADDRESS				0x00000c02
+
+static inline uint32_t REG_A3XX_VSC_PIPE(uint32_t i0) { return 0x00000c06 + 0x3*i0; }
+
+static inline uint32_t REG_A3XX_VSC_PIPE_CONFIG(uint32_t i0) { return 0x00000c06 + 0x3*i0; }
+#define A3XX_VSC_PIPE_CONFIG_X__MASK				0x000003ff
+#define A3XX_VSC_PIPE_CONFIG_X__SHIFT				0
+static inline uint32_t A3XX_VSC_PIPE_CONFIG_X(uint32_t val)
+{
+	return ((val) << A3XX_VSC_PIPE_CONFIG_X__SHIFT) & A3XX_VSC_PIPE_CONFIG_X__MASK;
+}
+#define A3XX_VSC_PIPE_CONFIG_Y__MASK				0x000ffc00
+#define A3XX_VSC_PIPE_CONFIG_Y__SHIFT				10
+static inline uint32_t A3XX_VSC_PIPE_CONFIG_Y(uint32_t val)
+{
+	return ((val) << A3XX_VSC_PIPE_CONFIG_Y__SHIFT) & A3XX_VSC_PIPE_CONFIG_Y__MASK;
+}
+#define A3XX_VSC_PIPE_CONFIG_W__MASK				0x00f00000
+#define A3XX_VSC_PIPE_CONFIG_W__SHIFT				20
+static inline uint32_t A3XX_VSC_PIPE_CONFIG_W(uint32_t val)
+{
+	return ((val) << A3XX_VSC_PIPE_CONFIG_W__SHIFT) & A3XX_VSC_PIPE_CONFIG_W__MASK;
+}
+#define A3XX_VSC_PIPE_CONFIG_H__MASK				0x0f000000
+#define A3XX_VSC_PIPE_CONFIG_H__SHIFT				24
+static inline uint32_t A3XX_VSC_PIPE_CONFIG_H(uint32_t val)
+{
+	return ((val) << A3XX_VSC_PIPE_CONFIG_H__SHIFT) & A3XX_VSC_PIPE_CONFIG_H__MASK;
+}
+
+static inline uint32_t REG_A3XX_VSC_PIPE_DATA_ADDRESS(uint32_t i0) { return 0x00000c07 + 0x3*i0; }
+
+static inline uint32_t REG_A3XX_VSC_PIPE_DATA_LENGTH(uint32_t i0) { return 0x00000c08 + 0x3*i0; }
+
+#define REG_A3XX_UNKNOWN_0C3D					0x00000c3d
+
+#define REG_A3XX_PC_PERFCOUNTER0_SELECT				0x00000c48
+
+#define REG_A3XX_PC_PERFCOUNTER1_SELECT				0x00000c49
+
+#define REG_A3XX_PC_PERFCOUNTER2_SELECT				0x00000c4a
+
+#define REG_A3XX_PC_PERFCOUNTER3_SELECT				0x00000c4b
+
+#define REG_A3XX_UNKNOWN_0C81					0x00000c81
+
+#define REG_A3XX_GRAS_PERFCOUNTER0_SELECT			0x00000c88
+
+#define REG_A3XX_GRAS_PERFCOUNTER1_SELECT			0x00000c89
+
+#define REG_A3XX_GRAS_PERFCOUNTER2_SELECT			0x00000c8a
+
+#define REG_A3XX_GRAS_PERFCOUNTER3_SELECT			0x00000c8b
+
+static inline uint32_t REG_A3XX_GRAS_CL_USER_PLANE(uint32_t i0) { return 0x00000ca0 + 0x4*i0; }
+
+static inline uint32_t REG_A3XX_GRAS_CL_USER_PLANE_X(uint32_t i0) { return 0x00000ca0 + 0x4*i0; }
+
+static inline uint32_t REG_A3XX_GRAS_CL_USER_PLANE_Y(uint32_t i0) { return 0x00000ca1 + 0x4*i0; }
+
+static inline uint32_t REG_A3XX_GRAS_CL_USER_PLANE_Z(uint32_t i0) { return 0x00000ca2 + 0x4*i0; }
+
+static inline uint32_t REG_A3XX_GRAS_CL_USER_PLANE_W(uint32_t i0) { return 0x00000ca3 + 0x4*i0; }
+
+#define REG_A3XX_RB_GMEM_BASE_ADDR				0x00000cc0
+
+#define REG_A3XX_RB_PERFCOUNTER0_SELECT				0x00000cc6
+
+#define REG_A3XX_RB_PERFCOUNTER1_SELECT				0x00000cc7
+
+#define REG_A3XX_RB_WINDOW_SIZE					0x00000ce0
+#define A3XX_RB_WINDOW_SIZE_WIDTH__MASK				0x00003fff
+#define A3XX_RB_WINDOW_SIZE_WIDTH__SHIFT			0
+static inline uint32_t A3XX_RB_WINDOW_SIZE_WIDTH(uint32_t val)
+{
+	return ((val) << A3XX_RB_WINDOW_SIZE_WIDTH__SHIFT) & A3XX_RB_WINDOW_SIZE_WIDTH__MASK;
+}
+#define A3XX_RB_WINDOW_SIZE_HEIGHT__MASK			0x0fffc000
+#define A3XX_RB_WINDOW_SIZE_HEIGHT__SHIFT			14
+static inline uint32_t A3XX_RB_WINDOW_SIZE_HEIGHT(uint32_t val)
+{
+	return ((val) << A3XX_RB_WINDOW_SIZE_HEIGHT__SHIFT) & A3XX_RB_WINDOW_SIZE_HEIGHT__MASK;
+}
+
+#define REG_A3XX_HLSQ_PERFCOUNTER0_SELECT			0x00000e00
+
+#define REG_A3XX_HLSQ_PERFCOUNTER1_SELECT			0x00000e01
+
+#define REG_A3XX_HLSQ_PERFCOUNTER2_SELECT			0x00000e02
+
+#define REG_A3XX_HLSQ_PERFCOUNTER3_SELECT			0x00000e03
+
+#define REG_A3XX_HLSQ_PERFCOUNTER4_SELECT			0x00000e04
+
+#define REG_A3XX_HLSQ_PERFCOUNTER5_SELECT			0x00000e05
+
+#define REG_A3XX_UNKNOWN_0E43					0x00000e43
+
+#define REG_A3XX_VFD_PERFCOUNTER0_SELECT			0x00000e44
+
+#define REG_A3XX_VFD_PERFCOUNTER1_SELECT			0x00000e45
+
+#define REG_A3XX_VPC_VPC_DEBUG_RAM_SEL				0x00000e61
+
+#define REG_A3XX_VPC_VPC_DEBUG_RAM_READ				0x00000e62
+
+#define REG_A3XX_VPC_PERFCOUNTER0_SELECT			0x00000e64
+
+#define REG_A3XX_VPC_PERFCOUNTER1_SELECT			0x00000e65
+
+#define REG_A3XX_UCHE_CACHE_MODE_CONTROL_REG			0x00000e82
+
+#define REG_A3XX_UCHE_PERFCOUNTER0_SELECT			0x00000e84
+
+#define REG_A3XX_UCHE_PERFCOUNTER1_SELECT			0x00000e85
+
+#define REG_A3XX_UCHE_PERFCOUNTER2_SELECT			0x00000e86
+
+#define REG_A3XX_UCHE_PERFCOUNTER3_SELECT			0x00000e87
+
+#define REG_A3XX_UCHE_PERFCOUNTER4_SELECT			0x00000e88
+
+#define REG_A3XX_UCHE_PERFCOUNTER5_SELECT			0x00000e89
+
+#define REG_A3XX_UCHE_CACHE_INVALIDATE0_REG			0x00000ea0
+#define A3XX_UCHE_CACHE_INVALIDATE0_REG_ADDR__MASK		0x0fffffff
+#define A3XX_UCHE_CACHE_INVALIDATE0_REG_ADDR__SHIFT		0
+static inline uint32_t A3XX_UCHE_CACHE_INVALIDATE0_REG_ADDR(uint32_t val)
+{
+	return ((val) << A3XX_UCHE_CACHE_INVALIDATE0_REG_ADDR__SHIFT) & A3XX_UCHE_CACHE_INVALIDATE0_REG_ADDR__MASK;
+}
+
+#define REG_A3XX_UCHE_CACHE_INVALIDATE1_REG			0x00000ea1
+#define A3XX_UCHE_CACHE_INVALIDATE1_REG_ADDR__MASK		0x0fffffff
+#define A3XX_UCHE_CACHE_INVALIDATE1_REG_ADDR__SHIFT		0
+static inline uint32_t A3XX_UCHE_CACHE_INVALIDATE1_REG_ADDR(uint32_t val)
+{
+	return ((val) << A3XX_UCHE_CACHE_INVALIDATE1_REG_ADDR__SHIFT) & A3XX_UCHE_CACHE_INVALIDATE1_REG_ADDR__MASK;
+}
+#define A3XX_UCHE_CACHE_INVALIDATE1_REG_OPCODE__MASK		0x30000000
+#define A3XX_UCHE_CACHE_INVALIDATE1_REG_OPCODE__SHIFT		28
+static inline uint32_t A3XX_UCHE_CACHE_INVALIDATE1_REG_OPCODE(enum a3xx_cache_opcode val)
+{
+	return ((val) << A3XX_UCHE_CACHE_INVALIDATE1_REG_OPCODE__SHIFT) & A3XX_UCHE_CACHE_INVALIDATE1_REG_OPCODE__MASK;
+}
+#define A3XX_UCHE_CACHE_INVALIDATE1_REG_ENTIRE_CACHE		0x80000000
+
+#define REG_A3XX_SP_PERFCOUNTER0_SELECT				0x00000ec4
+
+#define REG_A3XX_SP_PERFCOUNTER1_SELECT				0x00000ec5
+
+#define REG_A3XX_SP_PERFCOUNTER2_SELECT				0x00000ec6
+
+#define REG_A3XX_SP_PERFCOUNTER3_SELECT				0x00000ec7
+
+#define REG_A3XX_SP_PERFCOUNTER4_SELECT				0x00000ec8
+
+#define REG_A3XX_SP_PERFCOUNTER5_SELECT				0x00000ec9
+
+#define REG_A3XX_SP_PERFCOUNTER6_SELECT				0x00000eca
+
+#define REG_A3XX_SP_PERFCOUNTER7_SELECT				0x00000ecb
+
+#define REG_A3XX_UNKNOWN_0EE0					0x00000ee0
+
+#define REG_A3XX_UNKNOWN_0F03					0x00000f03
+
+#define REG_A3XX_TP_PERFCOUNTER0_SELECT				0x00000f04
+
+#define REG_A3XX_TP_PERFCOUNTER1_SELECT				0x00000f05
+
+#define REG_A3XX_TP_PERFCOUNTER2_SELECT				0x00000f06
+
+#define REG_A3XX_TP_PERFCOUNTER3_SELECT				0x00000f07
+
+#define REG_A3XX_TP_PERFCOUNTER4_SELECT				0x00000f08
+
+#define REG_A3XX_TP_PERFCOUNTER5_SELECT				0x00000f09
+
+#define REG_A3XX_TEX_SAMP_0					0x00000000
+#define A3XX_TEX_SAMP_0_XY_MAG__MASK				0x0000000c
+#define A3XX_TEX_SAMP_0_XY_MAG__SHIFT				2
+static inline uint32_t A3XX_TEX_SAMP_0_XY_MAG(enum a3xx_tex_filter val)
+{
+	return ((val) << A3XX_TEX_SAMP_0_XY_MAG__SHIFT) & A3XX_TEX_SAMP_0_XY_MAG__MASK;
+}
+#define A3XX_TEX_SAMP_0_XY_MIN__MASK				0x00000030
+#define A3XX_TEX_SAMP_0_XY_MIN__SHIFT				4
+static inline uint32_t A3XX_TEX_SAMP_0_XY_MIN(enum a3xx_tex_filter val)
+{
+	return ((val) << A3XX_TEX_SAMP_0_XY_MIN__SHIFT) & A3XX_TEX_SAMP_0_XY_MIN__MASK;
+}
+#define A3XX_TEX_SAMP_0_WRAP_S__MASK				0x000001c0
+#define A3XX_TEX_SAMP_0_WRAP_S__SHIFT				6
+static inline uint32_t A3XX_TEX_SAMP_0_WRAP_S(enum a3xx_tex_clamp val)
+{
+	return ((val) << A3XX_TEX_SAMP_0_WRAP_S__SHIFT) & A3XX_TEX_SAMP_0_WRAP_S__MASK;
+}
+#define A3XX_TEX_SAMP_0_WRAP_T__MASK				0x00000e00
+#define A3XX_TEX_SAMP_0_WRAP_T__SHIFT				9
+static inline uint32_t A3XX_TEX_SAMP_0_WRAP_T(enum a3xx_tex_clamp val)
+{
+	return ((val) << A3XX_TEX_SAMP_0_WRAP_T__SHIFT) & A3XX_TEX_SAMP_0_WRAP_T__MASK;
+}
+#define A3XX_TEX_SAMP_0_WRAP_R__MASK				0x00007000
+#define A3XX_TEX_SAMP_0_WRAP_R__SHIFT				12
+static inline uint32_t A3XX_TEX_SAMP_0_WRAP_R(enum a3xx_tex_clamp val)
+{
+	return ((val) << A3XX_TEX_SAMP_0_WRAP_R__SHIFT) & A3XX_TEX_SAMP_0_WRAP_R__MASK;
+}
+#define A3XX_TEX_SAMP_0_UNNORM_COORDS				0x80000000
+
+#define REG_A3XX_TEX_SAMP_1					0x00000001
+
+#define REG_A3XX_TEX_CONST_0					0x00000000
+#define A3XX_TEX_CONST_0_TILED					0x00000001
+#define A3XX_TEX_CONST_0_SWIZ_X__MASK				0x00000070
+#define A3XX_TEX_CONST_0_SWIZ_X__SHIFT				4
+static inline uint32_t A3XX_TEX_CONST_0_SWIZ_X(enum a3xx_tex_swiz val)
+{
+	return ((val) << A3XX_TEX_CONST_0_SWIZ_X__SHIFT) & A3XX_TEX_CONST_0_SWIZ_X__MASK;
+}
+#define A3XX_TEX_CONST_0_SWIZ_Y__MASK				0x00000380
+#define A3XX_TEX_CONST_0_SWIZ_Y__SHIFT				7
+static inline uint32_t A3XX_TEX_CONST_0_SWIZ_Y(enum a3xx_tex_swiz val)
+{
+	return ((val) << A3XX_TEX_CONST_0_SWIZ_Y__SHIFT) & A3XX_TEX_CONST_0_SWIZ_Y__MASK;
+}
+#define A3XX_TEX_CONST_0_SWIZ_Z__MASK				0x00001c00
+#define A3XX_TEX_CONST_0_SWIZ_Z__SHIFT				10
+static inline uint32_t A3XX_TEX_CONST_0_SWIZ_Z(enum a3xx_tex_swiz val)
+{
+	return ((val) << A3XX_TEX_CONST_0_SWIZ_Z__SHIFT) & A3XX_TEX_CONST_0_SWIZ_Z__MASK;
+}
+#define A3XX_TEX_CONST_0_SWIZ_W__MASK				0x0000e000
+#define A3XX_TEX_CONST_0_SWIZ_W__SHIFT				13
+static inline uint32_t A3XX_TEX_CONST_0_SWIZ_W(enum a3xx_tex_swiz val)
+{
+	return ((val) << A3XX_TEX_CONST_0_SWIZ_W__SHIFT) & A3XX_TEX_CONST_0_SWIZ_W__MASK;
+}
+#define A3XX_TEX_CONST_0_FMT__MASK				0x1fc00000
+#define A3XX_TEX_CONST_0_FMT__SHIFT				22
+static inline uint32_t A3XX_TEX_CONST_0_FMT(enum a3xx_tex_fmt val)
+{
+	return ((val) << A3XX_TEX_CONST_0_FMT__SHIFT) & A3XX_TEX_CONST_0_FMT__MASK;
+}
+#define A3XX_TEX_CONST_0_TYPE__MASK				0xc0000000
+#define A3XX_TEX_CONST_0_TYPE__SHIFT				30
+static inline uint32_t A3XX_TEX_CONST_0_TYPE(enum a3xx_tex_type val)
+{
+	return ((val) << A3XX_TEX_CONST_0_TYPE__SHIFT) & A3XX_TEX_CONST_0_TYPE__MASK;
+}
+
+#define REG_A3XX_TEX_CONST_1					0x00000001
+#define A3XX_TEX_CONST_1_HEIGHT__MASK				0x00003fff
+#define A3XX_TEX_CONST_1_HEIGHT__SHIFT				0
+static inline uint32_t A3XX_TEX_CONST_1_HEIGHT(uint32_t val)
+{
+	return ((val) << A3XX_TEX_CONST_1_HEIGHT__SHIFT) & A3XX_TEX_CONST_1_HEIGHT__MASK;
+}
+#define A3XX_TEX_CONST_1_WIDTH__MASK				0x0fffc000
+#define A3XX_TEX_CONST_1_WIDTH__SHIFT				14
+static inline uint32_t A3XX_TEX_CONST_1_WIDTH(uint32_t val)
+{
+	return ((val) << A3XX_TEX_CONST_1_WIDTH__SHIFT) & A3XX_TEX_CONST_1_WIDTH__MASK;
+}
+#define A3XX_TEX_CONST_1_FETCHSIZE__MASK			0xf0000000
+#define A3XX_TEX_CONST_1_FETCHSIZE__SHIFT			28
+static inline uint32_t A3XX_TEX_CONST_1_FETCHSIZE(enum a3xx_tex_fetchsize val)
+{
+	return ((val) << A3XX_TEX_CONST_1_FETCHSIZE__SHIFT) & A3XX_TEX_CONST_1_FETCHSIZE__MASK;
+}
+
+#define REG_A3XX_TEX_CONST_2					0x00000002
+#define A3XX_TEX_CONST_2_INDX__MASK				0x000000ff
+#define A3XX_TEX_CONST_2_INDX__SHIFT				0
+static inline uint32_t A3XX_TEX_CONST_2_INDX(uint32_t val)
+{
+	return ((val) << A3XX_TEX_CONST_2_INDX__SHIFT) & A3XX_TEX_CONST_2_INDX__MASK;
+}
+#define A3XX_TEX_CONST_2_PITCH__MASK				0x3ffff000
+#define A3XX_TEX_CONST_2_PITCH__SHIFT				12
+static inline uint32_t A3XX_TEX_CONST_2_PITCH(uint32_t val)
+{
+	return ((val) << A3XX_TEX_CONST_2_PITCH__SHIFT) & A3XX_TEX_CONST_2_PITCH__MASK;
+}
+#define A3XX_TEX_CONST_2_SWAP__MASK				0xc0000000
+#define A3XX_TEX_CONST_2_SWAP__SHIFT				30
+static inline uint32_t A3XX_TEX_CONST_2_SWAP(enum a3xx_color_swap val)
+{
+	return ((val) << A3XX_TEX_CONST_2_SWAP__SHIFT) & A3XX_TEX_CONST_2_SWAP__MASK;
+}
+
+#define REG_A3XX_TEX_CONST_3					0x00000003
+
+
+#endif /* A3XX_XML */
diff --git a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
new file mode 100644
index 000000000000..035bd13dc8bd
--- /dev/null
+++ b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
@@ -0,0 +1,502 @@
+/*
+ * Copyright (C) 2013 Red Hat
+ * Author: Rob Clark <robdclark@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include "a3xx_gpu.h"
+
+#define A3XX_INT0_MASK \
+	(A3XX_INT0_RBBM_AHB_ERROR |        \
+	 A3XX_INT0_RBBM_ATB_BUS_OVERFLOW | \
+	 A3XX_INT0_CP_T0_PACKET_IN_IB |    \
+	 A3XX_INT0_CP_OPCODE_ERROR |       \
+	 A3XX_INT0_CP_RESERVED_BIT_ERROR | \
+	 A3XX_INT0_CP_HW_FAULT |           \
+	 A3XX_INT0_CP_IB1_INT |            \
+	 A3XX_INT0_CP_IB2_INT |            \
+	 A3XX_INT0_CP_RB_INT |             \
+	 A3XX_INT0_CP_REG_PROTECT_FAULT |  \
+	 A3XX_INT0_CP_AHB_ERROR_HALT |     \
+	 A3XX_INT0_UCHE_OOB_ACCESS)
+
+static struct platform_device *a3xx_pdev;
+
+static void a3xx_me_init(struct msm_gpu *gpu)
+{
+	struct msm_ringbuffer *ring = gpu->rb;
+
+	OUT_PKT3(ring, CP_ME_INIT, 17);
+	OUT_RING(ring, 0x000003f7);
+	OUT_RING(ring, 0x00000000);
+	OUT_RING(ring, 0x00000000);
+	OUT_RING(ring, 0x00000000);
+	OUT_RING(ring, 0x00000080);
+	OUT_RING(ring, 0x00000100);
+	OUT_RING(ring, 0x00000180);
+	OUT_RING(ring, 0x00006600);
+	OUT_RING(ring, 0x00000150);
+	OUT_RING(ring, 0x0000014e);
+	OUT_RING(ring, 0x00000154);
+	OUT_RING(ring, 0x00000001);
+	OUT_RING(ring, 0x00000000);
+	OUT_RING(ring, 0x00000000);
+	OUT_RING(ring, 0x00000000);
+	OUT_RING(ring, 0x00000000);
+	OUT_RING(ring, 0x00000000);
+
+	gpu->funcs->flush(gpu);
+	gpu->funcs->idle(gpu);
+}
+
+static int a3xx_hw_init(struct msm_gpu *gpu)
+{
+	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
+	uint32_t *ptr, len;
+	int i, ret;
+
+	DBG("%s", gpu->name);
+
+	if (adreno_is_a305(adreno_gpu)) {
+		/* Set up 16 deep read/write request queues: */
+		gpu_write(gpu, REG_A3XX_VBIF_IN_RD_LIM_CONF0, 0x10101010);
+		gpu_write(gpu, REG_A3XX_VBIF_IN_RD_LIM_CONF1, 0x10101010);
+		gpu_write(gpu, REG_A3XX_VBIF_OUT_RD_LIM_CONF0, 0x10101010);
+		gpu_write(gpu, REG_A3XX_VBIF_OUT_WR_LIM_CONF0, 0x10101010);
+		gpu_write(gpu, REG_A3XX_VBIF_DDR_OUT_MAX_BURST, 0x0000303);
+		gpu_write(gpu, REG_A3XX_VBIF_IN_WR_LIM_CONF0, 0x10101010);
+		gpu_write(gpu, REG_A3XX_VBIF_IN_WR_LIM_CONF1, 0x10101010);
+		/* Enable WR-REQ: */
+		gpu_write(gpu, REG_A3XX_VBIF_GATE_OFF_WRREQ_EN, 0x0000ff);
+		/* Set up round robin arbitration between both AXI ports: */
+		gpu_write(gpu, REG_A3XX_VBIF_ARB_CTL, 0x00000030);
+		/* Set up AOOO: */
+		gpu_write(gpu, REG_A3XX_VBIF_OUT_AXI_AOOO_EN, 0x0000003c);
+		gpu_write(gpu, REG_A3XX_VBIF_OUT_AXI_AOOO, 0x003c003c);
+
+	} else if (adreno_is_a320(adreno_gpu)) {
+		/* Set up 16 deep read/write request queues: */
+		gpu_write(gpu, REG_A3XX_VBIF_IN_RD_LIM_CONF0, 0x10101010);
+		gpu_write(gpu, REG_A3XX_VBIF_IN_RD_LIM_CONF1, 0x10101010);
+		gpu_write(gpu, REG_A3XX_VBIF_OUT_RD_LIM_CONF0, 0x10101010);
+		gpu_write(gpu, REG_A3XX_VBIF_OUT_WR_LIM_CONF0, 0x10101010);
+		gpu_write(gpu, REG_A3XX_VBIF_DDR_OUT_MAX_BURST, 0x0000303);
+		gpu_write(gpu, REG_A3XX_VBIF_IN_WR_LIM_CONF0, 0x10101010);
+		gpu_write(gpu, REG_A3XX_VBIF_IN_WR_LIM_CONF1, 0x10101010);
+		/* Enable WR-REQ: */
+		gpu_write(gpu, REG_A3XX_VBIF_GATE_OFF_WRREQ_EN, 0x0000ff);
+		/* Set up round robin arbitration between both AXI ports: */
+		gpu_write(gpu, REG_A3XX_VBIF_ARB_CTL, 0x00000030);
+		/* Set up AOOO: */
+		gpu_write(gpu, REG_A3XX_VBIF_OUT_AXI_AOOO_EN, 0x0000003c);
+		gpu_write(gpu, REG_A3XX_VBIF_OUT_AXI_AOOO, 0x003c003c);
+		/* Enable 1K sort: */
+		gpu_write(gpu, REG_A3XX_VBIF_ABIT_SORT, 0x000000ff);
+		gpu_write(gpu, REG_A3XX_VBIF_ABIT_SORT_CONF, 0x000000a4);
+
+	} else if (adreno_is_a330(adreno_gpu)) {
+		/* Set up 16 deep read/write request queues: */
+		gpu_write(gpu, REG_A3XX_VBIF_IN_RD_LIM_CONF0, 0x18181818);
+		gpu_write(gpu, REG_A3XX_VBIF_IN_RD_LIM_CONF1, 0x18181818);
+		gpu_write(gpu, REG_A3XX_VBIF_OUT_RD_LIM_CONF0, 0x18181818);
+		gpu_write(gpu, REG_A3XX_VBIF_OUT_WR_LIM_CONF0, 0x18181818);
+		gpu_write(gpu, REG_A3XX_VBIF_DDR_OUT_MAX_BURST, 0x0000303);
+		gpu_write(gpu, REG_A3XX_VBIF_IN_WR_LIM_CONF0, 0x18181818);
+		gpu_write(gpu, REG_A3XX_VBIF_IN_WR_LIM_CONF1, 0x18181818);
+		/* Enable WR-REQ: */
+		gpu_write(gpu, REG_A3XX_VBIF_GATE_OFF_WRREQ_EN, 0x00003f);
+		/* Set up round robin arbitration between both AXI ports: */
+		gpu_write(gpu, REG_A3XX_VBIF_ARB_CTL, 0x00000030);
+		/* Set up VBIF_ROUND_ROBIN_QOS_ARB: */
+		gpu_write(gpu, REG_A3XX_VBIF_ROUND_ROBIN_QOS_ARB, 0x0001);
+		/* Set up AOOO: */
+		gpu_write(gpu, REG_A3XX_VBIF_OUT_AXI_AOOO_EN, 0x0000ffff);
+		gpu_write(gpu, REG_A3XX_VBIF_OUT_AXI_AOOO, 0xffffffff);
+		/* Enable 1K sort: */
+		gpu_write(gpu, REG_A3XX_VBIF_ABIT_SORT, 0x0001ffff);
+		gpu_write(gpu, REG_A3XX_VBIF_ABIT_SORT_CONF, 0x000000a4);
+		/* Disable VBIF clock gating. This is to enable AXI running
+		 * higher frequency than GPU:
+		 */
+		gpu_write(gpu, REG_A3XX_VBIF_CLKON, 0x00000001);
+
+	} else {
+		BUG();
+	}
+
+	/* Make all blocks contribute to the GPU BUSY perf counter: */
+	gpu_write(gpu, REG_A3XX_RBBM_GPU_BUSY_MASKED, 0xffffffff);
+
+	/* Tune the hystersis counters for SP and CP idle detection: */
+	gpu_write(gpu, REG_A3XX_RBBM_SP_HYST_CNT, 0x10);
+	gpu_write(gpu, REG_A3XX_RBBM_WAIT_IDLE_CLOCKS_CTL, 0x10);
+
+	/* Enable the RBBM error reporting bits.  This lets us get
+	 * useful information on failure:
+	 */
+	gpu_write(gpu, REG_A3XX_RBBM_AHB_CTL0, 0x00000001);
+
+	/* Enable AHB error reporting: */
+	gpu_write(gpu, REG_A3XX_RBBM_AHB_CTL1, 0xa6ffffff);
+
+	/* Turn on the power counters: */
+	gpu_write(gpu, REG_A3XX_RBBM_RBBM_CTL, 0x00030000);
+
+	/* Turn on hang detection - this spews a lot of useful information
+	 * into the RBBM registers on a hang:
+	 */
+	gpu_write(gpu, REG_A3XX_RBBM_INTERFACE_HANG_INT_CTL, 0x00010fff);
+
+	/* Enable 64-byte cacheline size. HW Default is 32-byte (0x000000E0): */
+	gpu_write(gpu, REG_A3XX_UCHE_CACHE_MODE_CONTROL_REG, 0x00000001);
+
+	/* Enable Clock gating: */
+	gpu_write(gpu, REG_A3XX_RBBM_CLOCK_CTL, 0xbfffffff);
+
+	/* Set the OCMEM base address for A330 */
+//TODO:
+//	if (adreno_is_a330(adreno_gpu)) {
+//		gpu_write(gpu, REG_A3XX_RB_GMEM_BASE_ADDR,
+//			(unsigned int)(a3xx_gpu->ocmem_base >> 14));
+//	}
+
+	/* Turn on performance counters: */
+	gpu_write(gpu, REG_A3XX_RBBM_PERFCTR_CTL, 0x01);
+
+	/* Set SP perfcounter 7 to count SP_FS_FULL_ALU_INSTRUCTIONS
+	 * we will use this to augment our hang detection:
+	 */
+	gpu_write(gpu, REG_A3XX_SP_PERFCOUNTER7_SELECT,
+			SP_FS_FULL_ALU_INSTRUCTIONS);
+
+	gpu_write(gpu, REG_A3XX_RBBM_INT_0_MASK, A3XX_INT0_MASK);
+
+	ret = adreno_hw_init(gpu);
+	if (ret)
+		return ret;
+
+	/* setup access protection: */
+	gpu_write(gpu, REG_A3XX_CP_PROTECT_CTRL, 0x00000007);
+
+	/* RBBM registers */
+	gpu_write(gpu, REG_A3XX_CP_PROTECT(0), 0x63000040);
+	gpu_write(gpu, REG_A3XX_CP_PROTECT(1), 0x62000080);
+	gpu_write(gpu, REG_A3XX_CP_PROTECT(2), 0x600000cc);
+	gpu_write(gpu, REG_A3XX_CP_PROTECT(3), 0x60000108);
+	gpu_write(gpu, REG_A3XX_CP_PROTECT(4), 0x64000140);
+	gpu_write(gpu, REG_A3XX_CP_PROTECT(5), 0x66000400);
+
+	/* CP registers */
+	gpu_write(gpu, REG_A3XX_CP_PROTECT(6), 0x65000700);
+	gpu_write(gpu, REG_A3XX_CP_PROTECT(7), 0x610007d8);
+	gpu_write(gpu, REG_A3XX_CP_PROTECT(8), 0x620007e0);
+	gpu_write(gpu, REG_A3XX_CP_PROTECT(9), 0x61001178);
+	gpu_write(gpu, REG_A3XX_CP_PROTECT(10), 0x64001180);
+
+	/* RB registers */
+	gpu_write(gpu, REG_A3XX_CP_PROTECT(11), 0x60003300);
+
+	/* VBIF registers */
+	gpu_write(gpu, REG_A3XX_CP_PROTECT(12), 0x6b00c000);
+
+	/* NOTE: PM4/micro-engine firmware registers look to be the same
+	 * for a2xx and a3xx.. we could possibly push that part down to
+	 * adreno_gpu base class.  Or push both PM4 and PFP but
+	 * parameterize the pfp ucode addr/data registers..
+	 */
+
+	/* Load PM4: */
+	ptr = (uint32_t *)(adreno_gpu->pm4->data);
+	len = adreno_gpu->pm4->size / 4;
+	DBG("loading PM4 ucode version: %u", ptr[0]);
+
+	gpu_write(gpu, REG_AXXX_CP_DEBUG,
+			AXXX_CP_DEBUG_DYNAMIC_CLK_DISABLE |
+			AXXX_CP_DEBUG_MIU_128BIT_WRITE_ENABLE);
+	gpu_write(gpu, REG_AXXX_CP_ME_RAM_WADDR, 0);
+	for (i = 1; i < len; i++)
+		gpu_write(gpu, REG_AXXX_CP_ME_RAM_DATA, ptr[i]);
+
+	/* Load PFP: */
+	ptr = (uint32_t *)(adreno_gpu->pfp->data);
+	len = adreno_gpu->pfp->size / 4;
+	DBG("loading PFP ucode version: %u", ptr[0]);
+
+	gpu_write(gpu, REG_A3XX_CP_PFP_UCODE_ADDR, 0);
+	for (i = 1; i < len; i++)
+		gpu_write(gpu, REG_A3XX_CP_PFP_UCODE_DATA, ptr[i]);
+
+	/* CP ROQ queue sizes (bytes) - RB:16, ST:16, IB1:32, IB2:64 */
+	if (adreno_is_a305(adreno_gpu) || adreno_is_a320(adreno_gpu))
+		gpu_write(gpu, REG_AXXX_CP_QUEUE_THRESHOLDS,
+				AXXX_CP_QUEUE_THRESHOLDS_CSQ_IB1_START(2) |
+				AXXX_CP_QUEUE_THRESHOLDS_CSQ_IB2_START(6) |
+				AXXX_CP_QUEUE_THRESHOLDS_CSQ_ST_START(14));
+
+
+	/* clear ME_HALT to start micro engine */
+	gpu_write(gpu, REG_AXXX_CP_ME_CNTL, 0);
+
+	a3xx_me_init(gpu);
+
+	return 0;
+}
+
+static void a3xx_destroy(struct msm_gpu *gpu)
+{
+	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
+	struct a3xx_gpu *a3xx_gpu = to_a3xx_gpu(adreno_gpu);
+
+	DBG("%s", gpu->name);
+
+	adreno_gpu_cleanup(adreno_gpu);
+	put_device(&a3xx_gpu->pdev->dev);
+	kfree(a3xx_gpu);
+}
+
+static void a3xx_idle(struct msm_gpu *gpu)
+{
+	unsigned long t;
+
+	/* wait for ringbuffer to drain: */
+	adreno_idle(gpu);
+
+	t = jiffies + ADRENO_IDLE_TIMEOUT;
+
+	/* then wait for GPU to finish: */
+	do {
+		uint32_t rbbm_status = gpu_read(gpu, REG_A3XX_RBBM_STATUS);
+		if (!(rbbm_status & A3XX_RBBM_STATUS_GPU_BUSY))
+			return;
+	} while(time_before(jiffies, t));
+
+	DRM_ERROR("timeout waiting for %s to idle!\n", gpu->name);
+
+	/* TODO maybe we need to reset GPU here to recover from hang? */
+}
+
+static irqreturn_t a3xx_irq(struct msm_gpu *gpu)
+{
+	uint32_t status;
+
+	status = gpu_read(gpu, REG_A3XX_RBBM_INT_0_STATUS);
+	DBG("%s: %08x", gpu->name, status);
+
+	// TODO
+
+	gpu_write(gpu, REG_A3XX_RBBM_INT_CLEAR_CMD, status);
+
+	msm_gpu_retire(gpu);
+
+	return IRQ_HANDLED;
+}
+
+#ifdef CONFIG_DEBUG_FS
+static const unsigned int a3xx_registers[] = {
+	0x0000, 0x0002, 0x0010, 0x0012, 0x0018, 0x0018, 0x0020, 0x0027,
+	0x0029, 0x002b, 0x002e, 0x0033, 0x0040, 0x0042, 0x0050, 0x005c,
+	0x0060, 0x006c, 0x0080, 0x0082, 0x0084, 0x0088, 0x0090, 0x00e5,
+	0x00ea, 0x00ed, 0x0100, 0x0100, 0x0110, 0x0123, 0x01c0, 0x01c1,
+	0x01c3, 0x01c5, 0x01c7, 0x01c7, 0x01d5, 0x01d9, 0x01dc, 0x01dd,
+	0x01ea, 0x01ea, 0x01ee, 0x01f1, 0x01f5, 0x01f5, 0x01fc, 0x01ff,
+	0x0440, 0x0440, 0x0443, 0x0443, 0x0445, 0x0445, 0x044d, 0x044f,
+	0x0452, 0x0452, 0x0454, 0x046f, 0x047c, 0x047c, 0x047f, 0x047f,
+	0x0578, 0x057f, 0x0600, 0x0602, 0x0605, 0x0607, 0x060a, 0x060e,
+	0x0612, 0x0614, 0x0c01, 0x0c02, 0x0c06, 0x0c1d, 0x0c3d, 0x0c3f,
+	0x0c48, 0x0c4b, 0x0c80, 0x0c80, 0x0c88, 0x0c8b, 0x0ca0, 0x0cb7,
+	0x0cc0, 0x0cc1, 0x0cc6, 0x0cc7, 0x0ce4, 0x0ce5, 0x0e00, 0x0e05,
+	0x0e0c, 0x0e0c, 0x0e22, 0x0e23, 0x0e41, 0x0e45, 0x0e64, 0x0e65,
+	0x0e80, 0x0e82, 0x0e84, 0x0e89, 0x0ea0, 0x0ea1, 0x0ea4, 0x0ea7,
+	0x0ec4, 0x0ecb, 0x0ee0, 0x0ee0, 0x0f00, 0x0f01, 0x0f03, 0x0f09,
+	0x2040, 0x2040, 0x2044, 0x2044, 0x2048, 0x204d, 0x2068, 0x2069,
+	0x206c, 0x206d, 0x2070, 0x2070, 0x2072, 0x2072, 0x2074, 0x2075,
+	0x2079, 0x207a, 0x20c0, 0x20d3, 0x20e4, 0x20ef, 0x2100, 0x2109,
+	0x210c, 0x210c, 0x210e, 0x210e, 0x2110, 0x2111, 0x2114, 0x2115,
+	0x21e4, 0x21e4, 0x21ea, 0x21ea, 0x21ec, 0x21ed, 0x21f0, 0x21f0,
+	0x2200, 0x2212, 0x2214, 0x2217, 0x221a, 0x221a, 0x2240, 0x227e,
+	0x2280, 0x228b, 0x22c0, 0x22c0, 0x22c4, 0x22ce, 0x22d0, 0x22d8,
+	0x22df, 0x22e6, 0x22e8, 0x22e9, 0x22ec, 0x22ec, 0x22f0, 0x22f7,
+	0x22ff, 0x22ff, 0x2340, 0x2343, 0x2348, 0x2349, 0x2350, 0x2356,
+	0x2360, 0x2360, 0x2440, 0x2440, 0x2444, 0x2444, 0x2448, 0x244d,
+	0x2468, 0x2469, 0x246c, 0x246d, 0x2470, 0x2470, 0x2472, 0x2472,
+	0x2474, 0x2475, 0x2479, 0x247a, 0x24c0, 0x24d3, 0x24e4, 0x24ef,
+	0x2500, 0x2509, 0x250c, 0x250c, 0x250e, 0x250e, 0x2510, 0x2511,
+	0x2514, 0x2515, 0x25e4, 0x25e4, 0x25ea, 0x25ea, 0x25ec, 0x25ed,
+	0x25f0, 0x25f0, 0x2600, 0x2612, 0x2614, 0x2617, 0x261a, 0x261a,
+	0x2640, 0x267e, 0x2680, 0x268b, 0x26c0, 0x26c0, 0x26c4, 0x26ce,
+	0x26d0, 0x26d8, 0x26df, 0x26e6, 0x26e8, 0x26e9, 0x26ec, 0x26ec,
+	0x26f0, 0x26f7, 0x26ff, 0x26ff, 0x2740, 0x2743, 0x2748, 0x2749,
+	0x2750, 0x2756, 0x2760, 0x2760, 0x300c, 0x300e, 0x301c, 0x301d,
+	0x302a, 0x302a, 0x302c, 0x302d, 0x3030, 0x3031, 0x3034, 0x3036,
+	0x303c, 0x303c, 0x305e, 0x305f,
+};
+
+static void a3xx_show(struct msm_gpu *gpu, struct seq_file *m)
+{
+	int i;
+
+	adreno_show(gpu, m);
+	seq_printf(m, "status:   %08x\n",
+			gpu_read(gpu, REG_A3XX_RBBM_STATUS));
+
+	/* dump these out in a form that can be parsed by demsm: */
+	seq_printf(m, "IO:region %s 00000000 00020000\n", gpu->name);
+	for (i = 0; i < ARRAY_SIZE(a3xx_registers); i += 2) {
+		uint32_t start = a3xx_registers[i];
+		uint32_t end   = a3xx_registers[i+1];
+		uint32_t addr;
+
+		for (addr = start; addr <= end; addr++) {
+			uint32_t val = gpu_read(gpu, addr);
+			seq_printf(m, "IO:R %08x %08x\n", addr<<2, val);
+		}
+	}
+}
+#endif
+
+static const struct adreno_gpu_funcs funcs = {
+	.base = {
+		.get_param = adreno_get_param,
+		.hw_init = a3xx_hw_init,
+		.pm_suspend = msm_gpu_pm_suspend,
+		.pm_resume = msm_gpu_pm_resume,
+		.recover = adreno_recover,
+		.last_fence = adreno_last_fence,
+		.submit = adreno_submit,
+		.flush = adreno_flush,
+		.idle = a3xx_idle,
+		.irq = a3xx_irq,
+		.destroy = a3xx_destroy,
+#ifdef CONFIG_DEBUG_FS
+		.show = a3xx_show,
+#endif
+	},
+};
+
+struct msm_gpu *a3xx_gpu_init(struct drm_device *dev)
+{
+	struct a3xx_gpu *a3xx_gpu = NULL;
+	struct msm_gpu *gpu;
+	struct platform_device *pdev = a3xx_pdev;
+	struct adreno_platform_config *config;
+	int ret;
+
+	if (!pdev) {
+		dev_err(dev->dev, "no a3xx device\n");
+		ret = -ENXIO;
+		goto fail;
+	}
+
+	config = pdev->dev.platform_data;
+
+	a3xx_gpu = kzalloc(sizeof(*a3xx_gpu), GFP_KERNEL);
+	if (!a3xx_gpu) {
+		ret = -ENOMEM;
+		goto fail;
+	}
+
+	gpu = &a3xx_gpu->base.base;
+
+	get_device(&pdev->dev);
+	a3xx_gpu->pdev = pdev;
+
+	gpu->fast_rate = config->fast_rate;
+	gpu->slow_rate = config->slow_rate;
+	gpu->bus_freq  = config->bus_freq;
+
+	DBG("fast_rate=%u, slow_rate=%u, bus_freq=%u",
+			gpu->fast_rate, gpu->slow_rate, gpu->bus_freq);
+
+	ret = adreno_gpu_init(dev, pdev, &a3xx_gpu->base,
+			&funcs, config->rev);
+	if (ret)
+		goto fail;
+
+	return &a3xx_gpu->base.base;
+
+fail:
+	if (a3xx_gpu)
+		a3xx_destroy(&a3xx_gpu->base.base);
+
+	return ERR_PTR(ret);
+}
+
+/*
+ * The a3xx device:
+ */
+
+static int a3xx_probe(struct platform_device *pdev)
+{
+	static struct adreno_platform_config config = {};
+#ifdef CONFIG_OF
+	/* TODO */
+#else
+	uint32_t version = socinfo_get_version();
+	if (cpu_is_apq8064ab()) {
+		config.fast_rate = 450000000;
+		config.slow_rate = 27000000;
+		config.bus_freq  = 4;
+		config.rev = ADRENO_REV(3, 2, 1, 0);
+	} else if (cpu_is_apq8064() || cpu_is_msm8960ab()) {
+		config.fast_rate = 400000000;
+		config.slow_rate = 27000000;
+		config.bus_freq  = 4;
+
+		if (SOCINFO_VERSION_MAJOR(version) == 2)
+			config.rev = ADRENO_REV(3, 2, 0, 2);
+		else if ((SOCINFO_VERSION_MAJOR(version) == 1) &&
+				(SOCINFO_VERSION_MINOR(version) == 1))
+			config.rev = ADRENO_REV(3, 2, 0, 1);
+		else
+			config.rev = ADRENO_REV(3, 2, 0, 0);
+
+	} else if (cpu_is_msm8930()) {
+		config.fast_rate = 400000000;
+		config.slow_rate = 27000000;
+		config.bus_freq  = 3;
+
+		if ((SOCINFO_VERSION_MAJOR(version) == 1) &&
+			(SOCINFO_VERSION_MINOR(version) == 2))
+			config.rev = ADRENO_REV(3, 0, 5, 2);
+		else
+			config.rev = ADRENO_REV(3, 0, 5, 0);
+
+	}
+#endif
+	pdev->dev.platform_data = &config;
+	a3xx_pdev = pdev;
+	return 0;
+}
+
+static int a3xx_remove(struct platform_device *pdev)
+{
+	a3xx_pdev = NULL;
+	return 0;
+}
+
+static struct platform_driver a3xx_driver = {
+	.probe = a3xx_probe,
+	.remove = a3xx_remove,
+	.driver.name = "kgsl-3d0",
+};
+
+void __init a3xx_register(void)
+{
+	platform_driver_register(&a3xx_driver);
+}
+
+void __exit a3xx_unregister(void)
+{
+	platform_driver_unregister(&a3xx_driver);
+}
diff --git a/drivers/gpu/drm/msm/adreno/a3xx_gpu.h b/drivers/gpu/drm/msm/adreno/a3xx_gpu.h
new file mode 100644
index 000000000000..32c398c2d00a
--- /dev/null
+++ b/drivers/gpu/drm/msm/adreno/a3xx_gpu.h
@@ -0,0 +1,30 @@
+/*
+ * Copyright (C) 2013 Red Hat
+ * Author: Rob Clark <robdclark@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __A3XX_GPU_H__
+#define __A3XX_GPU_H__
+
+#include "adreno_gpu.h"
+#include "a3xx.xml.h"
+
+struct a3xx_gpu {
+	struct adreno_gpu base;
+	struct platform_device *pdev;
+};
+#define to_a3xx_gpu(x) container_of(x, struct a3xx_gpu, base)
+
+#endif /* __A3XX_GPU_H__ */
diff --git a/drivers/gpu/drm/msm/adreno/adreno_common.xml.h b/drivers/gpu/drm/msm/adreno/adreno_common.xml.h
new file mode 100644
index 000000000000..61979d458ac0
--- /dev/null
+++ b/drivers/gpu/drm/msm/adreno/adreno_common.xml.h
@@ -0,0 +1,432 @@
+#ifndef ADRENO_COMMON_XML
+#define ADRENO_COMMON_XML
+
+/* Autogenerated file, DO NOT EDIT manually!
+
+This file was generated by the rules-ng-ng headergen tool in this git repository:
+http://0x04.net/cgit/index.cgi/rules-ng-ng
+git clone git://0x04.net/rules-ng-ng
+
+The rules-ng-ng source files this header was generated from are:
+- /home/robclark/src/freedreno/envytools/rnndb/adreno.xml              (    327 bytes, from 2013-07-05 19:21:12)
+- /home/robclark/src/freedreno/envytools/rnndb/freedreno_copyright.xml (   1453 bytes, from 2013-03-31 16:51:27)
+- /home/robclark/src/freedreno/envytools/rnndb/a2xx/a2xx.xml           (  30005 bytes, from 2013-07-19 21:30:48)
+- /home/robclark/src/freedreno/envytools/rnndb/adreno_common.xml       (   8983 bytes, from 2013-07-24 01:38:36)
+- /home/robclark/src/freedreno/envytools/rnndb/adreno_pm4.xml          (   9712 bytes, from 2013-05-26 15:22:37)
+- /home/robclark/src/freedreno/envytools/rnndb/a3xx/a3xx.xml           (  51415 bytes, from 2013-08-03 14:26:05)
+
+Copyright (C) 2013 by the following authors:
+- Rob Clark <robdclark@gmail.com> (robclark)
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice (including the
+next paragraph) shall be included in all copies or substantial
+portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
+IN NO EVENT SHALL THE COPYRIGHT OWNER(S) AND/OR ITS SUPPLIERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+*/
+
+
+enum adreno_pa_su_sc_draw {
+	PC_DRAW_POINTS = 0,
+	PC_DRAW_LINES = 1,
+	PC_DRAW_TRIANGLES = 2,
+};
+
+enum adreno_compare_func {
+	FUNC_NEVER = 0,
+	FUNC_LESS = 1,
+	FUNC_EQUAL = 2,
+	FUNC_LEQUAL = 3,
+	FUNC_GREATER = 4,
+	FUNC_NOTEQUAL = 5,
+	FUNC_GEQUAL = 6,
+	FUNC_ALWAYS = 7,
+};
+
+enum adreno_stencil_op {
+	STENCIL_KEEP = 0,
+	STENCIL_ZERO = 1,
+	STENCIL_REPLACE = 2,
+	STENCIL_INCR_CLAMP = 3,
+	STENCIL_DECR_CLAMP = 4,
+	STENCIL_INVERT = 5,
+	STENCIL_INCR_WRAP = 6,
+	STENCIL_DECR_WRAP = 7,
+};
+
+enum adreno_rb_blend_factor {
+	FACTOR_ZERO = 0,
+	FACTOR_ONE = 1,
+	FACTOR_SRC_COLOR = 4,
+	FACTOR_ONE_MINUS_SRC_COLOR = 5,
+	FACTOR_SRC_ALPHA = 6,
+	FACTOR_ONE_MINUS_SRC_ALPHA = 7,
+	FACTOR_DST_COLOR = 8,
+	FACTOR_ONE_MINUS_DST_COLOR = 9,
+	FACTOR_DST_ALPHA = 10,
+	FACTOR_ONE_MINUS_DST_ALPHA = 11,
+	FACTOR_CONSTANT_COLOR = 12,
+	FACTOR_ONE_MINUS_CONSTANT_COLOR = 13,
+	FACTOR_CONSTANT_ALPHA = 14,
+	FACTOR_ONE_MINUS_CONSTANT_ALPHA = 15,
+	FACTOR_SRC_ALPHA_SATURATE = 16,
+};
+
+enum adreno_rb_blend_opcode {
+	BLEND_DST_PLUS_SRC = 0,
+	BLEND_SRC_MINUS_DST = 1,
+	BLEND_MIN_DST_SRC = 2,
+	BLEND_MAX_DST_SRC = 3,
+	BLEND_DST_MINUS_SRC = 4,
+	BLEND_DST_PLUS_SRC_BIAS = 5,
+};
+
+enum adreno_rb_surface_endian {
+	ENDIAN_NONE = 0,
+	ENDIAN_8IN16 = 1,
+	ENDIAN_8IN32 = 2,
+	ENDIAN_16IN32 = 3,
+	ENDIAN_8IN64 = 4,
+	ENDIAN_8IN128 = 5,
+};
+
+enum adreno_rb_dither_mode {
+	DITHER_DISABLE = 0,
+	DITHER_ALWAYS = 1,
+	DITHER_IF_ALPHA_OFF = 2,
+};
+
+enum adreno_rb_depth_format {
+	DEPTHX_16 = 0,
+	DEPTHX_24_8 = 1,
+};
+
+enum adreno_mmu_clnt_beh {
+	BEH_NEVR = 0,
+	BEH_TRAN_RNG = 1,
+	BEH_TRAN_FLT = 2,
+};
+
+#define REG_AXXX_MH_MMU_CONFIG					0x00000040
+#define AXXX_MH_MMU_CONFIG_MMU_ENABLE				0x00000001
+#define AXXX_MH_MMU_CONFIG_SPLIT_MODE_ENABLE			0x00000002
+#define AXXX_MH_MMU_CONFIG_RB_W_CLNT_BEHAVIOR__MASK		0x00000030
+#define AXXX_MH_MMU_CONFIG_RB_W_CLNT_BEHAVIOR__SHIFT		4
+static inline uint32_t AXXX_MH_MMU_CONFIG_RB_W_CLNT_BEHAVIOR(enum adreno_mmu_clnt_beh val)
+{
+	return ((val) << AXXX_MH_MMU_CONFIG_RB_W_CLNT_BEHAVIOR__SHIFT) & AXXX_MH_MMU_CONFIG_RB_W_CLNT_BEHAVIOR__MASK;
+}
+#define AXXX_MH_MMU_CONFIG_CP_W_CLNT_BEHAVIOR__MASK		0x000000c0
+#define AXXX_MH_MMU_CONFIG_CP_W_CLNT_BEHAVIOR__SHIFT		6
+static inline uint32_t AXXX_MH_MMU_CONFIG_CP_W_CLNT_BEHAVIOR(enum adreno_mmu_clnt_beh val)
+{
+	return ((val) << AXXX_MH_MMU_CONFIG_CP_W_CLNT_BEHAVIOR__SHIFT) & AXXX_MH_MMU_CONFIG_CP_W_CLNT_BEHAVIOR__MASK;
+}
+#define AXXX_MH_MMU_CONFIG_CP_R0_CLNT_BEHAVIOR__MASK		0x00000300
+#define AXXX_MH_MMU_CONFIG_CP_R0_CLNT_BEHAVIOR__SHIFT		8
+static inline uint32_t AXXX_MH_MMU_CONFIG_CP_R0_CLNT_BEHAVIOR(enum adreno_mmu_clnt_beh val)
+{
+	return ((val) << AXXX_MH_MMU_CONFIG_CP_R0_CLNT_BEHAVIOR__SHIFT) & AXXX_MH_MMU_CONFIG_CP_R0_CLNT_BEHAVIOR__MASK;
+}
+#define AXXX_MH_MMU_CONFIG_CP_R1_CLNT_BEHAVIOR__MASK		0x00000c00
+#define AXXX_MH_MMU_CONFIG_CP_R1_CLNT_BEHAVIOR__SHIFT		10
+static inline uint32_t AXXX_MH_MMU_CONFIG_CP_R1_CLNT_BEHAVIOR(enum adreno_mmu_clnt_beh val)
+{
+	return ((val) << AXXX_MH_MMU_CONFIG_CP_R1_CLNT_BEHAVIOR__SHIFT) & AXXX_MH_MMU_CONFIG_CP_R1_CLNT_BEHAVIOR__MASK;
+}
+#define AXXX_MH_MMU_CONFIG_CP_R2_CLNT_BEHAVIOR__MASK		0x00003000
+#define AXXX_MH_MMU_CONFIG_CP_R2_CLNT_BEHAVIOR__SHIFT		12
+static inline uint32_t AXXX_MH_MMU_CONFIG_CP_R2_CLNT_BEHAVIOR(enum adreno_mmu_clnt_beh val)
+{
+	return ((val) << AXXX_MH_MMU_CONFIG_CP_R2_CLNT_BEHAVIOR__SHIFT) & AXXX_MH_MMU_CONFIG_CP_R2_CLNT_BEHAVIOR__MASK;
+}
+#define AXXX_MH_MMU_CONFIG_CP_R3_CLNT_BEHAVIOR__MASK		0x0000c000
+#define AXXX_MH_MMU_CONFIG_CP_R3_CLNT_BEHAVIOR__SHIFT		14
+static inline uint32_t AXXX_MH_MMU_CONFIG_CP_R3_CLNT_BEHAVIOR(enum adreno_mmu_clnt_beh val)
+{
+	return ((val) << AXXX_MH_MMU_CONFIG_CP_R3_CLNT_BEHAVIOR__SHIFT) & AXXX_MH_MMU_CONFIG_CP_R3_CLNT_BEHAVIOR__MASK;
+}
+#define AXXX_MH_MMU_CONFIG_CP_R4_CLNT_BEHAVIOR__MASK		0x00030000
+#define AXXX_MH_MMU_CONFIG_CP_R4_CLNT_BEHAVIOR__SHIFT		16
+static inline uint32_t AXXX_MH_MMU_CONFIG_CP_R4_CLNT_BEHAVIOR(enum adreno_mmu_clnt_beh val)
+{
+	return ((val) << AXXX_MH_MMU_CONFIG_CP_R4_CLNT_BEHAVIOR__SHIFT) & AXXX_MH_MMU_CONFIG_CP_R4_CLNT_BEHAVIOR__MASK;
+}
+#define AXXX_MH_MMU_CONFIG_VGT_R0_CLNT_BEHAVIOR__MASK		0x000c0000
+#define AXXX_MH_MMU_CONFIG_VGT_R0_CLNT_BEHAVIOR__SHIFT		18
+static inline uint32_t AXXX_MH_MMU_CONFIG_VGT_R0_CLNT_BEHAVIOR(enum adreno_mmu_clnt_beh val)
+{
+	return ((val) << AXXX_MH_MMU_CONFIG_VGT_R0_CLNT_BEHAVIOR__SHIFT) & AXXX_MH_MMU_CONFIG_VGT_R0_CLNT_BEHAVIOR__MASK;
+}
+#define AXXX_MH_MMU_CONFIG_VGT_R1_CLNT_BEHAVIOR__MASK		0x00300000
+#define AXXX_MH_MMU_CONFIG_VGT_R1_CLNT_BEHAVIOR__SHIFT		20
+static inline uint32_t AXXX_MH_MMU_CONFIG_VGT_R1_CLNT_BEHAVIOR(enum adreno_mmu_clnt_beh val)
+{
+	return ((val) << AXXX_MH_MMU_CONFIG_VGT_R1_CLNT_BEHAVIOR__SHIFT) & AXXX_MH_MMU_CONFIG_VGT_R1_CLNT_BEHAVIOR__MASK;
+}
+#define AXXX_MH_MMU_CONFIG_TC_R_CLNT_BEHAVIOR__MASK		0x00c00000
+#define AXXX_MH_MMU_CONFIG_TC_R_CLNT_BEHAVIOR__SHIFT		22
+static inline uint32_t AXXX_MH_MMU_CONFIG_TC_R_CLNT_BEHAVIOR(enum adreno_mmu_clnt_beh val)
+{
+	return ((val) << AXXX_MH_MMU_CONFIG_TC_R_CLNT_BEHAVIOR__SHIFT) & AXXX_MH_MMU_CONFIG_TC_R_CLNT_BEHAVIOR__MASK;
+}
+#define AXXX_MH_MMU_CONFIG_PA_W_CLNT_BEHAVIOR__MASK		0x03000000
+#define AXXX_MH_MMU_CONFIG_PA_W_CLNT_BEHAVIOR__SHIFT		24
+static inline uint32_t AXXX_MH_MMU_CONFIG_PA_W_CLNT_BEHAVIOR(enum adreno_mmu_clnt_beh val)
+{
+	return ((val) << AXXX_MH_MMU_CONFIG_PA_W_CLNT_BEHAVIOR__SHIFT) & AXXX_MH_MMU_CONFIG_PA_W_CLNT_BEHAVIOR__MASK;
+}
+
+#define REG_AXXX_MH_MMU_VA_RANGE				0x00000041
+
+#define REG_AXXX_MH_MMU_PT_BASE					0x00000042
+
+#define REG_AXXX_MH_MMU_PAGE_FAULT				0x00000043
+
+#define REG_AXXX_MH_MMU_TRAN_ERROR				0x00000044
+
+#define REG_AXXX_MH_MMU_INVALIDATE				0x00000045
+
+#define REG_AXXX_MH_MMU_MPU_BASE				0x00000046
+
+#define REG_AXXX_MH_MMU_MPU_END					0x00000047
+
+#define REG_AXXX_CP_RB_BASE					0x000001c0
+
+#define REG_AXXX_CP_RB_CNTL					0x000001c1
+#define AXXX_CP_RB_CNTL_BUFSZ__MASK				0x0000003f
+#define AXXX_CP_RB_CNTL_BUFSZ__SHIFT				0
+static inline uint32_t AXXX_CP_RB_CNTL_BUFSZ(uint32_t val)
+{
+	return ((val) << AXXX_CP_RB_CNTL_BUFSZ__SHIFT) & AXXX_CP_RB_CNTL_BUFSZ__MASK;
+}
+#define AXXX_CP_RB_CNTL_BLKSZ__MASK				0x00003f00
+#define AXXX_CP_RB_CNTL_BLKSZ__SHIFT				8
+static inline uint32_t AXXX_CP_RB_CNTL_BLKSZ(uint32_t val)
+{
+	return ((val) << AXXX_CP_RB_CNTL_BLKSZ__SHIFT) & AXXX_CP_RB_CNTL_BLKSZ__MASK;
+}
+#define AXXX_CP_RB_CNTL_BUF_SWAP__MASK				0x00030000
+#define AXXX_CP_RB_CNTL_BUF_SWAP__SHIFT				16
+static inline uint32_t AXXX_CP_RB_CNTL_BUF_SWAP(uint32_t val)
+{
+	return ((val) << AXXX_CP_RB_CNTL_BUF_SWAP__SHIFT) & AXXX_CP_RB_CNTL_BUF_SWAP__MASK;
+}
+#define AXXX_CP_RB_CNTL_POLL_EN					0x00100000
+#define AXXX_CP_RB_CNTL_NO_UPDATE				0x08000000
+#define AXXX_CP_RB_CNTL_RPTR_WR_EN				0x80000000
+
+#define REG_AXXX_CP_RB_RPTR_ADDR				0x000001c3
+#define AXXX_CP_RB_RPTR_ADDR_SWAP__MASK				0x00000003
+#define AXXX_CP_RB_RPTR_ADDR_SWAP__SHIFT			0
+static inline uint32_t AXXX_CP_RB_RPTR_ADDR_SWAP(uint32_t val)
+{
+	return ((val) << AXXX_CP_RB_RPTR_ADDR_SWAP__SHIFT) & AXXX_CP_RB_RPTR_ADDR_SWAP__MASK;
+}
+#define AXXX_CP_RB_RPTR_ADDR_ADDR__MASK				0xfffffffc
+#define AXXX_CP_RB_RPTR_ADDR_ADDR__SHIFT			2
+static inline uint32_t AXXX_CP_RB_RPTR_ADDR_ADDR(uint32_t val)
+{
+	return ((val >> 2) << AXXX_CP_RB_RPTR_ADDR_ADDR__SHIFT) & AXXX_CP_RB_RPTR_ADDR_ADDR__MASK;
+}
+
+#define REG_AXXX_CP_RB_RPTR					0x000001c4
+
+#define REG_AXXX_CP_RB_WPTR					0x000001c5
+
+#define REG_AXXX_CP_RB_WPTR_DELAY				0x000001c6
+
+#define REG_AXXX_CP_RB_RPTR_WR					0x000001c7
+
+#define REG_AXXX_CP_RB_WPTR_BASE				0x000001c8
+
+#define REG_AXXX_CP_QUEUE_THRESHOLDS				0x000001d5
+#define AXXX_CP_QUEUE_THRESHOLDS_CSQ_IB1_START__MASK		0x0000000f
+#define AXXX_CP_QUEUE_THRESHOLDS_CSQ_IB1_START__SHIFT		0
+static inline uint32_t AXXX_CP_QUEUE_THRESHOLDS_CSQ_IB1_START(uint32_t val)
+{
+	return ((val) << AXXX_CP_QUEUE_THRESHOLDS_CSQ_IB1_START__SHIFT) & AXXX_CP_QUEUE_THRESHOLDS_CSQ_IB1_START__MASK;
+}
+#define AXXX_CP_QUEUE_THRESHOLDS_CSQ_IB2_START__MASK		0x00000f00
+#define AXXX_CP_QUEUE_THRESHOLDS_CSQ_IB2_START__SHIFT		8
+static inline uint32_t AXXX_CP_QUEUE_THRESHOLDS_CSQ_IB2_START(uint32_t val)
+{
+	return ((val) << AXXX_CP_QUEUE_THRESHOLDS_CSQ_IB2_START__SHIFT) & AXXX_CP_QUEUE_THRESHOLDS_CSQ_IB2_START__MASK;
+}
+#define AXXX_CP_QUEUE_THRESHOLDS_CSQ_ST_START__MASK		0x000f0000
+#define AXXX_CP_QUEUE_THRESHOLDS_CSQ_ST_START__SHIFT		16
+static inline uint32_t AXXX_CP_QUEUE_THRESHOLDS_CSQ_ST_START(uint32_t val)
+{
+	return ((val) << AXXX_CP_QUEUE_THRESHOLDS_CSQ_ST_START__SHIFT) & AXXX_CP_QUEUE_THRESHOLDS_CSQ_ST_START__MASK;
+}
+
+#define REG_AXXX_CP_MEQ_THRESHOLDS				0x000001d6
+
+#define REG_AXXX_CP_CSQ_AVAIL					0x000001d7
+#define AXXX_CP_CSQ_AVAIL_RING__MASK				0x0000007f
+#define AXXX_CP_CSQ_AVAIL_RING__SHIFT				0
+static inline uint32_t AXXX_CP_CSQ_AVAIL_RING(uint32_t val)
+{
+	return ((val) << AXXX_CP_CSQ_AVAIL_RING__SHIFT) & AXXX_CP_CSQ_AVAIL_RING__MASK;
+}
+#define AXXX_CP_CSQ_AVAIL_IB1__MASK				0x00007f00
+#define AXXX_CP_CSQ_AVAIL_IB1__SHIFT				8
+static inline uint32_t AXXX_CP_CSQ_AVAIL_IB1(uint32_t val)
+{
+	return ((val) << AXXX_CP_CSQ_AVAIL_IB1__SHIFT) & AXXX_CP_CSQ_AVAIL_IB1__MASK;
+}
+#define AXXX_CP_CSQ_AVAIL_IB2__MASK				0x007f0000
+#define AXXX_CP_CSQ_AVAIL_IB2__SHIFT				16
+static inline uint32_t AXXX_CP_CSQ_AVAIL_IB2(uint32_t val)
+{
+	return ((val) << AXXX_CP_CSQ_AVAIL_IB2__SHIFT) & AXXX_CP_CSQ_AVAIL_IB2__MASK;
+}
+
+#define REG_AXXX_CP_STQ_AVAIL					0x000001d8
+#define AXXX_CP_STQ_AVAIL_ST__MASK				0x0000007f
+#define AXXX_CP_STQ_AVAIL_ST__SHIFT				0
+static inline uint32_t AXXX_CP_STQ_AVAIL_ST(uint32_t val)
+{
+	return ((val) << AXXX_CP_STQ_AVAIL_ST__SHIFT) & AXXX_CP_STQ_AVAIL_ST__MASK;
+}
+
+#define REG_AXXX_CP_MEQ_AVAIL					0x000001d9
+#define AXXX_CP_MEQ_AVAIL_MEQ__MASK				0x0000001f
+#define AXXX_CP_MEQ_AVAIL_MEQ__SHIFT				0
+static inline uint32_t AXXX_CP_MEQ_AVAIL_MEQ(uint32_t val)
+{
+	return ((val) << AXXX_CP_MEQ_AVAIL_MEQ__SHIFT) & AXXX_CP_MEQ_AVAIL_MEQ__MASK;
+}
+
+#define REG_AXXX_SCRATCH_UMSK					0x000001dc
+#define AXXX_SCRATCH_UMSK_UMSK__MASK				0x000000ff
+#define AXXX_SCRATCH_UMSK_UMSK__SHIFT				0
+static inline uint32_t AXXX_SCRATCH_UMSK_UMSK(uint32_t val)
+{
+	return ((val) << AXXX_SCRATCH_UMSK_UMSK__SHIFT) & AXXX_SCRATCH_UMSK_UMSK__MASK;
+}
+#define AXXX_SCRATCH_UMSK_SWAP__MASK				0x00030000
+#define AXXX_SCRATCH_UMSK_SWAP__SHIFT				16
+static inline uint32_t AXXX_SCRATCH_UMSK_SWAP(uint32_t val)
+{
+	return ((val) << AXXX_SCRATCH_UMSK_SWAP__SHIFT) & AXXX_SCRATCH_UMSK_SWAP__MASK;
+}
+
+#define REG_AXXX_SCRATCH_ADDR					0x000001dd
+
+#define REG_AXXX_CP_ME_RDADDR					0x000001ea
+
+#define REG_AXXX_CP_STATE_DEBUG_INDEX				0x000001ec
+
+#define REG_AXXX_CP_STATE_DEBUG_DATA				0x000001ed
+
+#define REG_AXXX_CP_INT_CNTL					0x000001f2
+
+#define REG_AXXX_CP_INT_STATUS					0x000001f3
+
+#define REG_AXXX_CP_INT_ACK					0x000001f4
+
+#define REG_AXXX_CP_ME_CNTL					0x000001f6
+
+#define REG_AXXX_CP_ME_STATUS					0x000001f7
+
+#define REG_AXXX_CP_ME_RAM_WADDR				0x000001f8
+
+#define REG_AXXX_CP_ME_RAM_RADDR				0x000001f9
+
+#define REG_AXXX_CP_ME_RAM_DATA					0x000001fa
+
+#define REG_AXXX_CP_DEBUG					0x000001fc
+#define AXXX_CP_DEBUG_PREDICATE_DISABLE				0x00800000
+#define AXXX_CP_DEBUG_PROG_END_PTR_ENABLE			0x01000000
+#define AXXX_CP_DEBUG_MIU_128BIT_WRITE_ENABLE			0x02000000
+#define AXXX_CP_DEBUG_PREFETCH_PASS_NOPS			0x04000000
+#define AXXX_CP_DEBUG_DYNAMIC_CLK_DISABLE			0x08000000
+#define AXXX_CP_DEBUG_PREFETCH_MATCH_DISABLE			0x10000000
+#define AXXX_CP_DEBUG_SIMPLE_ME_FLOW_CONTROL			0x40000000
+#define AXXX_CP_DEBUG_MIU_WRITE_PACK_DISABLE			0x80000000
+
+#define REG_AXXX_CP_CSQ_RB_STAT					0x000001fd
+#define AXXX_CP_CSQ_RB_STAT_RPTR__MASK				0x0000007f
+#define AXXX_CP_CSQ_RB_STAT_RPTR__SHIFT				0
+static inline uint32_t AXXX_CP_CSQ_RB_STAT_RPTR(uint32_t val)
+{
+	return ((val) << AXXX_CP_CSQ_RB_STAT_RPTR__SHIFT) & AXXX_CP_CSQ_RB_STAT_RPTR__MASK;
+}
+#define AXXX_CP_CSQ_RB_STAT_WPTR__MASK				0x007f0000
+#define AXXX_CP_CSQ_RB_STAT_WPTR__SHIFT				16
+static inline uint32_t AXXX_CP_CSQ_RB_STAT_WPTR(uint32_t val)
+{
+	return ((val) << AXXX_CP_CSQ_RB_STAT_WPTR__SHIFT) & AXXX_CP_CSQ_RB_STAT_WPTR__MASK;
+}
+
+#define REG_AXXX_CP_CSQ_IB1_STAT				0x000001fe
+#define AXXX_CP_CSQ_IB1_STAT_RPTR__MASK				0x0000007f
+#define AXXX_CP_CSQ_IB1_STAT_RPTR__SHIFT			0
+static inline uint32_t AXXX_CP_CSQ_IB1_STAT_RPTR(uint32_t val)
+{
+	return ((val) << AXXX_CP_CSQ_IB1_STAT_RPTR__SHIFT) & AXXX_CP_CSQ_IB1_STAT_RPTR__MASK;
+}
+#define AXXX_CP_CSQ_IB1_STAT_WPTR__MASK				0x007f0000
+#define AXXX_CP_CSQ_IB1_STAT_WPTR__SHIFT			16
+static inline uint32_t AXXX_CP_CSQ_IB1_STAT_WPTR(uint32_t val)
+{
+	return ((val) << AXXX_CP_CSQ_IB1_STAT_WPTR__SHIFT) & AXXX_CP_CSQ_IB1_STAT_WPTR__MASK;
+}
+
+#define REG_AXXX_CP_CSQ_IB2_STAT				0x000001ff
+#define AXXX_CP_CSQ_IB2_STAT_RPTR__MASK				0x0000007f
+#define AXXX_CP_CSQ_IB2_STAT_RPTR__SHIFT			0
+static inline uint32_t AXXX_CP_CSQ_IB2_STAT_RPTR(uint32_t val)
+{
+	return ((val) << AXXX_CP_CSQ_IB2_STAT_RPTR__SHIFT) & AXXX_CP_CSQ_IB2_STAT_RPTR__MASK;
+}
+#define AXXX_CP_CSQ_IB2_STAT_WPTR__MASK				0x007f0000
+#define AXXX_CP_CSQ_IB2_STAT_WPTR__SHIFT			16
+static inline uint32_t AXXX_CP_CSQ_IB2_STAT_WPTR(uint32_t val)
+{
+	return ((val) << AXXX_CP_CSQ_IB2_STAT_WPTR__SHIFT) & AXXX_CP_CSQ_IB2_STAT_WPTR__MASK;
+}
+
+#define REG_AXXX_CP_SCRATCH_REG0				0x00000578
+
+#define REG_AXXX_CP_SCRATCH_REG1				0x00000579
+
+#define REG_AXXX_CP_SCRATCH_REG2				0x0000057a
+
+#define REG_AXXX_CP_SCRATCH_REG3				0x0000057b
+
+#define REG_AXXX_CP_SCRATCH_REG4				0x0000057c
+
+#define REG_AXXX_CP_SCRATCH_REG5				0x0000057d
+
+#define REG_AXXX_CP_SCRATCH_REG6				0x0000057e
+
+#define REG_AXXX_CP_SCRATCH_REG7				0x0000057f
+
+#define REG_AXXX_CP_ME_CF_EVENT_SRC				0x0000060a
+
+#define REG_AXXX_CP_ME_CF_EVENT_ADDR				0x0000060b
+
+#define REG_AXXX_CP_ME_CF_EVENT_DATA				0x0000060c
+
+#define REG_AXXX_CP_ME_NRT_ADDR					0x0000060d
+
+#define REG_AXXX_CP_ME_NRT_DATA					0x0000060e
+
+
+#endif /* ADRENO_COMMON_XML */
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
new file mode 100644
index 000000000000..a0b9d8a95b16
--- /dev/null
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
@@ -0,0 +1,378 @@
+/*
+ * Copyright (C) 2013 Red Hat
+ * Author: Rob Clark <robdclark@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include "adreno_gpu.h"
+#include "msm_gem.h"
+
+struct adreno_info {
+	struct adreno_rev rev;
+	uint32_t revn;
+	const char *name;
+	const char *pm4fw, *pfpfw;
+	uint32_t gmem;
+};
+
+#define ANY_ID 0xff
+
+static const struct adreno_info gpulist[] = {
+	{
+		.rev   = ADRENO_REV(3, 0, 5, ANY_ID),
+		.revn  = 305,
+		.name  = "A305",
+		.pm4fw = "a300_pm4.fw",
+		.pfpfw = "a300_pfp.fw",
+		.gmem  = SZ_256K,
+	}, {
+		.rev   = ADRENO_REV(3, 2, ANY_ID, ANY_ID),
+		.revn  = 320,
+		.name  = "A320",
+		.pm4fw = "a300_pm4.fw",
+		.pfpfw = "a300_pfp.fw",
+		.gmem  = SZ_512K,
+	}, {
+		.rev   = ADRENO_REV(3, 3, 0, 0),
+		.revn  = 330,
+		.name  = "A330",
+		.pm4fw = "a330_pm4.fw",
+		.pfpfw = "a330_pfp.fw",
+		.gmem  = SZ_1M,
+	},
+};
+
+#define RB_SIZE    SZ_32K
+#define RB_BLKSIZE 16
+
+int adreno_get_param(struct msm_gpu *gpu, uint32_t param, uint64_t *value)
+{
+	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
+
+	switch (param) {
+	case MSM_PARAM_GPU_ID:
+		*value = adreno_gpu->info->revn;
+		return 0;
+	case MSM_PARAM_GMEM_SIZE:
+		*value = adreno_gpu->info->gmem;
+		return 0;
+	default:
+		DBG("%s: invalid param: %u", gpu->name, param);
+		return -EINVAL;
+	}
+}
+
+#define rbmemptr(adreno_gpu, member)  \
+	((adreno_gpu)->memptrs_iova + offsetof(struct adreno_rbmemptrs, member))
+
+int adreno_hw_init(struct msm_gpu *gpu)
+{
+	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
+
+	DBG("%s", gpu->name);
+
+	/* Setup REG_CP_RB_CNTL: */
+	gpu_write(gpu, REG_AXXX_CP_RB_CNTL,
+			/* size is log2(quad-words): */
+			AXXX_CP_RB_CNTL_BUFSZ(ilog2(gpu->rb->size / 8)) |
+			AXXX_CP_RB_CNTL_BLKSZ(RB_BLKSIZE));
+
+	/* Setup ringbuffer address: */
+	gpu_write(gpu, REG_AXXX_CP_RB_BASE, gpu->rb_iova);
+	gpu_write(gpu, REG_AXXX_CP_RB_RPTR_ADDR, rbmemptr(adreno_gpu, rptr));
+
+	/* Setup scratch/timestamp: */
+	gpu_write(gpu, REG_AXXX_SCRATCH_ADDR, rbmemptr(adreno_gpu, fence));
+
+	gpu_write(gpu, REG_AXXX_SCRATCH_UMSK, 0x1);
+
+	return 0;
+}
+
+static uint32_t get_wptr(struct msm_ringbuffer *ring)
+{
+	return ring->cur - ring->start;
+}
+
+uint32_t adreno_last_fence(struct msm_gpu *gpu)
+{
+	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
+	return adreno_gpu->memptrs->fence;
+}
+
+void adreno_recover(struct msm_gpu *gpu)
+{
+	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
+	struct drm_device *dev = gpu->dev;
+	int ret;
+
+	gpu->funcs->pm_suspend(gpu);
+
+	/* reset ringbuffer: */
+	gpu->rb->cur = gpu->rb->start;
+
+	/* reset completed fence seqno, just discard anything pending: */
+	adreno_gpu->memptrs->fence = gpu->submitted_fence;
+	adreno_gpu->memptrs->rptr  = 0;
+	adreno_gpu->memptrs->wptr  = 0;
+
+	gpu->funcs->pm_resume(gpu);
+	ret = gpu->funcs->hw_init(gpu);
+	if (ret) {
+		dev_err(dev->dev, "gpu hw init failed: %d\n", ret);
+		/* hmm, oh well? */
+	}
+}
+
+int adreno_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit,
+		struct msm_file_private *ctx)
+{
+	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
+	struct msm_drm_private *priv = gpu->dev->dev_private;
+	struct msm_ringbuffer *ring = gpu->rb;
+	unsigned i, ibs = 0;
+
+	for (i = 0; i < submit->nr_cmds; i++) {
+		switch (submit->cmd[i].type) {
+		case MSM_SUBMIT_CMD_IB_TARGET_BUF:
+			/* ignore IB-targets */
+			break;
+		case MSM_SUBMIT_CMD_CTX_RESTORE_BUF:
+			/* ignore if there has not been a ctx switch: */
+			if (priv->lastctx == ctx)
+				break;
+		case MSM_SUBMIT_CMD_BUF:
+			OUT_PKT3(ring, CP_INDIRECT_BUFFER_PFD, 2);
+			OUT_RING(ring, submit->cmd[i].iova);
+			OUT_RING(ring, submit->cmd[i].size);
+			ibs++;
+			break;
+		}
+	}
+
+	/* on a320, at least, we seem to need to pad things out to an
+	 * even number of qwords to avoid issue w/ CP hanging on wrap-
+	 * around:
+	 */
+	if (ibs % 2)
+		OUT_PKT2(ring);
+
+	OUT_PKT0(ring, REG_AXXX_CP_SCRATCH_REG2, 1);
+	OUT_RING(ring, submit->fence);
+
+	if (adreno_is_a3xx(adreno_gpu)) {
+		/* Flush HLSQ lazy updates to make sure there is nothing
+		 * pending for indirect loads after the timestamp has
+		 * passed:
+		 */
+		OUT_PKT3(ring, CP_EVENT_WRITE, 1);
+		OUT_RING(ring, HLSQ_FLUSH);
+
+		OUT_PKT3(ring, CP_WAIT_FOR_IDLE, 1);
+		OUT_RING(ring, 0x00000000);
+	}
+
+	OUT_PKT3(ring, CP_EVENT_WRITE, 3);
+	OUT_RING(ring, CACHE_FLUSH_TS);
+	OUT_RING(ring, rbmemptr(adreno_gpu, fence));
+	OUT_RING(ring, submit->fence);
+
+	/* we could maybe be clever and only CP_COND_EXEC the interrupt: */
+	OUT_PKT3(ring, CP_INTERRUPT, 1);
+	OUT_RING(ring, 0x80000000);
+
+#if 0
+	if (adreno_is_a3xx(adreno_gpu)) {
+		/* Dummy set-constant to trigger context rollover */
+		OUT_PKT3(ring, CP_SET_CONSTANT, 2);
+		OUT_RING(ring, CP_REG(REG_A3XX_HLSQ_CL_KERNEL_GROUP_X_REG));
+		OUT_RING(ring, 0x00000000);
+	}
+#endif
+
+	gpu->funcs->flush(gpu);
+
+	return 0;
+}
+
+void adreno_flush(struct msm_gpu *gpu)
+{
+	uint32_t wptr = get_wptr(gpu->rb);
+
+	/* ensure writes to ringbuffer have hit system memory: */
+	mb();
+
+	gpu_write(gpu, REG_AXXX_CP_RB_WPTR, wptr);
+}
+
+void adreno_idle(struct msm_gpu *gpu)
+{
+	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
+	uint32_t rptr, wptr = get_wptr(gpu->rb);
+	unsigned long t;
+
+	t = jiffies + ADRENO_IDLE_TIMEOUT;
+
+	/* then wait for CP to drain ringbuffer: */
+	do {
+		rptr = adreno_gpu->memptrs->rptr;
+		if (rptr == wptr)
+			return;
+	} while(time_before(jiffies, t));
+
+	DRM_ERROR("%s: timeout waiting to drain ringbuffer!\n", gpu->name);
+
+	/* TODO maybe we need to reset GPU here to recover from hang? */
+}
+
+#ifdef CONFIG_DEBUG_FS
+void adreno_show(struct msm_gpu *gpu, struct seq_file *m)
+{
+	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
+
+	seq_printf(m, "revision: %d (%d.%d.%d.%d)\n",
+			adreno_gpu->info->revn, adreno_gpu->rev.core,
+			adreno_gpu->rev.major, adreno_gpu->rev.minor,
+			adreno_gpu->rev.patchid);
+
+	seq_printf(m, "fence:    %d/%d\n", adreno_gpu->memptrs->fence,
+			gpu->submitted_fence);
+	seq_printf(m, "rptr:     %d\n", adreno_gpu->memptrs->rptr);
+	seq_printf(m, "wptr:     %d\n", adreno_gpu->memptrs->wptr);
+	seq_printf(m, "rb wptr:  %d\n", get_wptr(gpu->rb));
+}
+#endif
+
+void adreno_wait_ring(struct msm_gpu *gpu, uint32_t ndwords)
+{
+	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
+	uint32_t freedwords;
+	unsigned long t = jiffies + ADRENO_IDLE_TIMEOUT;
+	do {
+		uint32_t size = gpu->rb->size / 4;
+		uint32_t wptr = get_wptr(gpu->rb);
+		uint32_t rptr = adreno_gpu->memptrs->rptr;
+		freedwords = (rptr + (size - 1) - wptr) % size;
+
+		if (time_after(jiffies, t)) {
+			DRM_ERROR("%s: timeout waiting for ringbuffer space\n", gpu->name);
+			break;
+		}
+	} while(freedwords < ndwords);
+}
+
+static const char *iommu_ports[] = {
+		"gfx3d_user", "gfx3d_priv",
+		"gfx3d1_user", "gfx3d1_priv",
+};
+
+static inline bool _rev_match(uint8_t entry, uint8_t id)
+{
+	return (entry == ANY_ID) || (entry == id);
+}
+
+int adreno_gpu_init(struct drm_device *drm, struct platform_device *pdev,
+		struct adreno_gpu *gpu, const struct adreno_gpu_funcs *funcs,
+		struct adreno_rev rev)
+{
+	int i, ret;
+
+	/* identify gpu: */
+	for (i = 0; i < ARRAY_SIZE(gpulist); i++) {
+		const struct adreno_info *info = &gpulist[i];
+		if (_rev_match(info->rev.core, rev.core) &&
+				_rev_match(info->rev.major, rev.major) &&
+				_rev_match(info->rev.minor, rev.minor) &&
+				_rev_match(info->rev.patchid, rev.patchid)) {
+			gpu->info = info;
+			gpu->revn = info->revn;
+			break;
+		}
+	}
+
+	if (i == ARRAY_SIZE(gpulist)) {
+		dev_err(drm->dev, "Unknown GPU revision: %u.%u.%u.%u\n",
+				rev.core, rev.major, rev.minor, rev.patchid);
+		return -ENXIO;
+	}
+
+	DBG("Found GPU: %s (%u.%u.%u.%u)", gpu->info->name,
+			rev.core, rev.major, rev.minor, rev.patchid);
+
+	gpu->funcs = funcs;
+	gpu->rev = rev;
+
+	ret = request_firmware(&gpu->pm4, gpu->info->pm4fw, drm->dev);
+	if (ret) {
+		dev_err(drm->dev, "failed to load %s PM4 firmware: %d\n",
+				gpu->info->pm4fw, ret);
+		return ret;
+	}
+
+	ret = request_firmware(&gpu->pfp, gpu->info->pfpfw, drm->dev);
+	if (ret) {
+		dev_err(drm->dev, "failed to load %s PFP firmware: %d\n",
+				gpu->info->pfpfw, ret);
+		return ret;
+	}
+
+	ret = msm_gpu_init(drm, pdev, &gpu->base, &funcs->base,
+			gpu->info->name, "kgsl_3d0_reg_memory", "kgsl_3d0_irq",
+			RB_SIZE);
+	if (ret)
+		return ret;
+
+	ret = msm_iommu_attach(drm, gpu->base.iommu,
+			iommu_ports, ARRAY_SIZE(iommu_ports));
+	if (ret)
+		return ret;
+
+	gpu->memptrs_bo = msm_gem_new(drm, sizeof(*gpu->memptrs),
+			MSM_BO_UNCACHED);
+	if (IS_ERR(gpu->memptrs_bo)) {
+		ret = PTR_ERR(gpu->memptrs_bo);
+		gpu->memptrs_bo = NULL;
+		dev_err(drm->dev, "could not allocate memptrs: %d\n", ret);
+		return ret;
+	}
+
+	gpu->memptrs = msm_gem_vaddr_locked(gpu->memptrs_bo);
+	if (!gpu->memptrs) {
+		dev_err(drm->dev, "could not vmap memptrs\n");
+		return -ENOMEM;
+	}
+
+	ret = msm_gem_get_iova_locked(gpu->memptrs_bo, gpu->base.id,
+			&gpu->memptrs_iova);
+	if (ret) {
+		dev_err(drm->dev, "could not map memptrs: %d\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+void adreno_gpu_cleanup(struct adreno_gpu *gpu)
+{
+	if (gpu->memptrs_bo) {
+		if (gpu->memptrs_iova)
+			msm_gem_put_iova(gpu->memptrs_bo, gpu->base.id);
+		drm_gem_object_unreference(gpu->memptrs_bo);
+	}
+	if (gpu->pm4)
+		release_firmware(gpu->pm4);
+	if (gpu->pfp)
+		release_firmware(gpu->pfp);
+	msm_gpu_cleanup(&gpu->base);
+}
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.h b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
new file mode 100644
index 000000000000..f73abfba7c22
--- /dev/null
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
@@ -0,0 +1,141 @@
+/*
+ * Copyright (C) 2013 Red Hat
+ * Author: Rob Clark <robdclark@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __ADRENO_GPU_H__
+#define __ADRENO_GPU_H__
+
+#include <linux/firmware.h>
+
+#include "msm_gpu.h"
+
+#include "adreno_common.xml.h"
+#include "adreno_pm4.xml.h"
+
+struct adreno_rev {
+	uint8_t  core;
+	uint8_t  major;
+	uint8_t  minor;
+	uint8_t  patchid;
+};
+
+#define ADRENO_REV(core, major, minor, patchid) \
+	((struct adreno_rev){ core, major, minor, patchid })
+
+struct adreno_gpu_funcs {
+	struct msm_gpu_funcs base;
+};
+
+struct adreno_info;
+
+struct adreno_rbmemptrs {
+	volatile uint32_t rptr;
+	volatile uint32_t wptr;
+	volatile uint32_t fence;
+};
+
+struct adreno_gpu {
+	struct msm_gpu base;
+	struct adreno_rev rev;
+	const struct adreno_info *info;
+	uint32_t revn;  /* numeric revision name */
+	const struct adreno_gpu_funcs *funcs;
+
+	/* firmware: */
+	const struct firmware *pm4, *pfp;
+
+	/* ringbuffer rptr/wptr: */
+	// TODO should this be in msm_ringbuffer?  I think it would be
+	// different for z180..
+	struct adreno_rbmemptrs *memptrs;
+	struct drm_gem_object *memptrs_bo;
+	uint32_t memptrs_iova;
+};
+#define to_adreno_gpu(x) container_of(x, struct adreno_gpu, base)
+
+/* platform config data (ie. from DT, or pdata) */
+struct adreno_platform_config {
+	struct adreno_rev rev;
+	uint32_t fast_rate, slow_rate, bus_freq;
+};
+
+#define ADRENO_IDLE_TIMEOUT (20 * 1000)
+
+static inline bool adreno_is_a3xx(struct adreno_gpu *gpu)
+{
+	return (gpu->revn >= 300) && (gpu->revn < 400);
+}
+
+static inline bool adreno_is_a305(struct adreno_gpu *gpu)
+{
+	return gpu->revn == 305;
+}
+
+static inline bool adreno_is_a320(struct adreno_gpu *gpu)
+{
+	return gpu->revn == 320;
+}
+
+static inline bool adreno_is_a330(struct adreno_gpu *gpu)
+{
+	return gpu->revn == 330;
+}
+
+int adreno_get_param(struct msm_gpu *gpu, uint32_t param, uint64_t *value);
+int adreno_hw_init(struct msm_gpu *gpu);
+uint32_t adreno_last_fence(struct msm_gpu *gpu);
+void adreno_recover(struct msm_gpu *gpu);
+int adreno_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit,
+		struct msm_file_private *ctx);
+void adreno_flush(struct msm_gpu *gpu);
+void adreno_idle(struct msm_gpu *gpu);
+#ifdef CONFIG_DEBUG_FS
+void adreno_show(struct msm_gpu *gpu, struct seq_file *m);
+#endif
+void adreno_wait_ring(struct msm_gpu *gpu, uint32_t ndwords);
+
+int adreno_gpu_init(struct drm_device *drm, struct platform_device *pdev,
+		struct adreno_gpu *gpu, const struct adreno_gpu_funcs *funcs,
+		struct adreno_rev rev);
+void adreno_gpu_cleanup(struct adreno_gpu *gpu);
+
+
+/* ringbuffer helpers (the parts that are adreno specific) */
+
+static inline void
+OUT_PKT0(struct msm_ringbuffer *ring, uint16_t regindx, uint16_t cnt)
+{
+	adreno_wait_ring(ring->gpu, cnt+1);
+	OUT_RING(ring, CP_TYPE0_PKT | ((cnt-1) << 16) | (regindx & 0x7FFF));
+}
+
+/* no-op packet: */
+static inline void
+OUT_PKT2(struct msm_ringbuffer *ring)
+{
+	adreno_wait_ring(ring->gpu, 1);
+	OUT_RING(ring, CP_TYPE2_PKT);
+}
+
+static inline void
+OUT_PKT3(struct msm_ringbuffer *ring, uint8_t opcode, uint16_t cnt)
+{
+	adreno_wait_ring(ring->gpu, cnt+1);
+	OUT_RING(ring, CP_TYPE3_PKT | ((cnt-1) << 16) | ((opcode & 0xFF) << 8));
+}
+
+
+#endif /* __ADRENO_GPU_H__ */
diff --git a/drivers/gpu/drm/msm/adreno/adreno_pm4.xml.h b/drivers/gpu/drm/msm/adreno/adreno_pm4.xml.h
new file mode 100644
index 000000000000..94c13f418e75
--- /dev/null
+++ b/drivers/gpu/drm/msm/adreno/adreno_pm4.xml.h
@@ -0,0 +1,254 @@
+#ifndef ADRENO_PM4_XML
+#define ADRENO_PM4_XML
+
+/* Autogenerated file, DO NOT EDIT manually!
+
+This file was generated by the rules-ng-ng headergen tool in this git repository:
+http://0x04.net/cgit/index.cgi/rules-ng-ng
+git clone git://0x04.net/rules-ng-ng
+
+The rules-ng-ng source files this header was generated from are:
+- /home/robclark/src/freedreno/envytools/rnndb/adreno.xml              (    327 bytes, from 2013-07-05 19:21:12)
+- /home/robclark/src/freedreno/envytools/rnndb/freedreno_copyright.xml (   1453 bytes, from 2013-03-31 16:51:27)
+- /home/robclark/src/freedreno/envytools/rnndb/a2xx/a2xx.xml           (  30005 bytes, from 2013-07-19 21:30:48)
+- /home/robclark/src/freedreno/envytools/rnndb/adreno_common.xml       (   8983 bytes, from 2013-07-24 01:38:36)
+- /home/robclark/src/freedreno/envytools/rnndb/adreno_pm4.xml          (   9712 bytes, from 2013-05-26 15:22:37)
+- /home/robclark/src/freedreno/envytools/rnndb/a3xx/a3xx.xml           (  51415 bytes, from 2013-08-03 14:26:05)
+
+Copyright (C) 2013 by the following authors:
+- Rob Clark <robdclark@gmail.com> (robclark)
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice (including the
+next paragraph) shall be included in all copies or substantial
+portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
+IN NO EVENT SHALL THE COPYRIGHT OWNER(S) AND/OR ITS SUPPLIERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+*/
+
+
+enum vgt_event_type {
+	VS_DEALLOC = 0,
+	PS_DEALLOC = 1,
+	VS_DONE_TS = 2,
+	PS_DONE_TS = 3,
+	CACHE_FLUSH_TS = 4,
+	CONTEXT_DONE = 5,
+	CACHE_FLUSH = 6,
+	HLSQ_FLUSH = 7,
+	VIZQUERY_START = 7,
+	VIZQUERY_END = 8,
+	SC_WAIT_WC = 9,
+	RST_PIX_CNT = 13,
+	RST_VTX_CNT = 14,
+	TILE_FLUSH = 15,
+	CACHE_FLUSH_AND_INV_TS_EVENT = 20,
+	ZPASS_DONE = 21,
+	CACHE_FLUSH_AND_INV_EVENT = 22,
+	PERFCOUNTER_START = 23,
+	PERFCOUNTER_STOP = 24,
+	VS_FETCH_DONE = 27,
+	FACENESS_FLUSH = 28,
+};
+
+enum pc_di_primtype {
+	DI_PT_NONE = 0,
+	DI_PT_POINTLIST = 1,
+	DI_PT_LINELIST = 2,
+	DI_PT_LINESTRIP = 3,
+	DI_PT_TRILIST = 4,
+	DI_PT_TRIFAN = 5,
+	DI_PT_TRISTRIP = 6,
+	DI_PT_RECTLIST = 8,
+	DI_PT_QUADLIST = 13,
+	DI_PT_QUADSTRIP = 14,
+	DI_PT_POLYGON = 15,
+	DI_PT_2D_COPY_RECT_LIST_V0 = 16,
+	DI_PT_2D_COPY_RECT_LIST_V1 = 17,
+	DI_PT_2D_COPY_RECT_LIST_V2 = 18,
+	DI_PT_2D_COPY_RECT_LIST_V3 = 19,
+	DI_PT_2D_FILL_RECT_LIST = 20,
+	DI_PT_2D_LINE_STRIP = 21,
+	DI_PT_2D_TRI_STRIP = 22,
+};
+
+enum pc_di_src_sel {
+	DI_SRC_SEL_DMA = 0,
+	DI_SRC_SEL_IMMEDIATE = 1,
+	DI_SRC_SEL_AUTO_INDEX = 2,
+	DI_SRC_SEL_RESERVED = 3,
+};
+
+enum pc_di_index_size {
+	INDEX_SIZE_IGN = 0,
+	INDEX_SIZE_16_BIT = 0,
+	INDEX_SIZE_32_BIT = 1,
+	INDEX_SIZE_8_BIT = 2,
+	INDEX_SIZE_INVALID = 0,
+};
+
+enum pc_di_vis_cull_mode {
+	IGNORE_VISIBILITY = 0,
+};
+
+enum adreno_pm4_packet_type {
+	CP_TYPE0_PKT = 0,
+	CP_TYPE1_PKT = 0x40000000,
+	CP_TYPE2_PKT = 0x80000000,
+	CP_TYPE3_PKT = 0xc0000000,
+};
+
+enum adreno_pm4_type3_packets {
+	CP_ME_INIT = 72,
+	CP_NOP = 16,
+	CP_INDIRECT_BUFFER = 63,
+	CP_INDIRECT_BUFFER_PFD = 55,
+	CP_WAIT_FOR_IDLE = 38,
+	CP_WAIT_REG_MEM = 60,
+	CP_WAIT_REG_EQ = 82,
+	CP_WAT_REG_GTE = 83,
+	CP_WAIT_UNTIL_READ = 92,
+	CP_WAIT_IB_PFD_COMPLETE = 93,
+	CP_REG_RMW = 33,
+	CP_SET_BIN_DATA = 47,
+	CP_REG_TO_MEM = 62,
+	CP_MEM_WRITE = 61,
+	CP_MEM_WRITE_CNTR = 79,
+	CP_COND_EXEC = 68,
+	CP_COND_WRITE = 69,
+	CP_EVENT_WRITE = 70,
+	CP_EVENT_WRITE_SHD = 88,
+	CP_EVENT_WRITE_CFL = 89,
+	CP_EVENT_WRITE_ZPD = 91,
+	CP_RUN_OPENCL = 49,
+	CP_DRAW_INDX = 34,
+	CP_DRAW_INDX_2 = 54,
+	CP_DRAW_INDX_BIN = 52,
+	CP_DRAW_INDX_2_BIN = 53,
+	CP_VIZ_QUERY = 35,
+	CP_SET_STATE = 37,
+	CP_SET_CONSTANT = 45,
+	CP_IM_LOAD = 39,
+	CP_IM_LOAD_IMMEDIATE = 43,
+	CP_LOAD_CONSTANT_CONTEXT = 46,
+	CP_INVALIDATE_STATE = 59,
+	CP_SET_SHADER_BASES = 74,
+	CP_SET_BIN_MASK = 80,
+	CP_SET_BIN_SELECT = 81,
+	CP_CONTEXT_UPDATE = 94,
+	CP_INTERRUPT = 64,
+	CP_IM_STORE = 44,
+	CP_SET_BIN_BASE_OFFSET = 75,
+	CP_SET_DRAW_INIT_FLAGS = 75,
+	CP_SET_PROTECTED_MODE = 95,
+	CP_LOAD_STATE = 48,
+	CP_COND_INDIRECT_BUFFER_PFE = 58,
+	CP_COND_INDIRECT_BUFFER_PFD = 50,
+	CP_INDIRECT_BUFFER_PFE = 63,
+	CP_SET_BIN = 76,
+};
+
+enum adreno_state_block {
+	SB_VERT_TEX = 0,
+	SB_VERT_MIPADDR = 1,
+	SB_FRAG_TEX = 2,
+	SB_FRAG_MIPADDR = 3,
+	SB_VERT_SHADER = 4,
+	SB_FRAG_SHADER = 6,
+};
+
+enum adreno_state_type {
+	ST_SHADER = 0,
+	ST_CONSTANTS = 1,
+};
+
+enum adreno_state_src {
+	SS_DIRECT = 0,
+	SS_INDIRECT = 4,
+};
+
+#define REG_CP_LOAD_STATE_0					0x00000000
+#define CP_LOAD_STATE_0_DST_OFF__MASK				0x0000ffff
+#define CP_LOAD_STATE_0_DST_OFF__SHIFT				0
+static inline uint32_t CP_LOAD_STATE_0_DST_OFF(uint32_t val)
+{
+	return ((val) << CP_LOAD_STATE_0_DST_OFF__SHIFT) & CP_LOAD_STATE_0_DST_OFF__MASK;
+}
+#define CP_LOAD_STATE_0_STATE_SRC__MASK				0x00070000
+#define CP_LOAD_STATE_0_STATE_SRC__SHIFT			16
+static inline uint32_t CP_LOAD_STATE_0_STATE_SRC(enum adreno_state_src val)
+{
+	return ((val) << CP_LOAD_STATE_0_STATE_SRC__SHIFT) & CP_LOAD_STATE_0_STATE_SRC__MASK;
+}
+#define CP_LOAD_STATE_0_STATE_BLOCK__MASK			0x00380000
+#define CP_LOAD_STATE_0_STATE_BLOCK__SHIFT			19
+static inline uint32_t CP_LOAD_STATE_0_STATE_BLOCK(enum adreno_state_block val)
+{
+	return ((val) << CP_LOAD_STATE_0_STATE_BLOCK__SHIFT) & CP_LOAD_STATE_0_STATE_BLOCK__MASK;
+}
+#define CP_LOAD_STATE_0_NUM_UNIT__MASK				0x7fc00000
+#define CP_LOAD_STATE_0_NUM_UNIT__SHIFT				22
+static inline uint32_t CP_LOAD_STATE_0_NUM_UNIT(uint32_t val)
+{
+	return ((val) << CP_LOAD_STATE_0_NUM_UNIT__SHIFT) & CP_LOAD_STATE_0_NUM_UNIT__MASK;
+}
+
+#define REG_CP_LOAD_STATE_1					0x00000001
+#define CP_LOAD_STATE_1_STATE_TYPE__MASK			0x00000003
+#define CP_LOAD_STATE_1_STATE_TYPE__SHIFT			0
+static inline uint32_t CP_LOAD_STATE_1_STATE_TYPE(enum adreno_state_type val)
+{
+	return ((val) << CP_LOAD_STATE_1_STATE_TYPE__SHIFT) & CP_LOAD_STATE_1_STATE_TYPE__MASK;
+}
+#define CP_LOAD_STATE_1_EXT_SRC_ADDR__MASK			0xfffffffc
+#define CP_LOAD_STATE_1_EXT_SRC_ADDR__SHIFT			2
+static inline uint32_t CP_LOAD_STATE_1_EXT_SRC_ADDR(uint32_t val)
+{
+	return ((val >> 2) << CP_LOAD_STATE_1_EXT_SRC_ADDR__SHIFT) & CP_LOAD_STATE_1_EXT_SRC_ADDR__MASK;
+}
+
+#define REG_CP_SET_BIN_0					0x00000000
+
+#define REG_CP_SET_BIN_1					0x00000001
+#define CP_SET_BIN_1_X1__MASK					0x0000ffff
+#define CP_SET_BIN_1_X1__SHIFT					0
+static inline uint32_t CP_SET_BIN_1_X1(uint32_t val)
+{
+	return ((val) << CP_SET_BIN_1_X1__SHIFT) & CP_SET_BIN_1_X1__MASK;
+}
+#define CP_SET_BIN_1_Y1__MASK					0xffff0000
+#define CP_SET_BIN_1_Y1__SHIFT					16
+static inline uint32_t CP_SET_BIN_1_Y1(uint32_t val)
+{
+	return ((val) << CP_SET_BIN_1_Y1__SHIFT) & CP_SET_BIN_1_Y1__MASK;
+}
+
+#define REG_CP_SET_BIN_2					0x00000002
+#define CP_SET_BIN_2_X2__MASK					0x0000ffff
+#define CP_SET_BIN_2_X2__SHIFT					0
+static inline uint32_t CP_SET_BIN_2_X2(uint32_t val)
+{
+	return ((val) << CP_SET_BIN_2_X2__SHIFT) & CP_SET_BIN_2_X2__MASK;
+}
+#define CP_SET_BIN_2_Y2__MASK					0xffff0000
+#define CP_SET_BIN_2_Y2__SHIFT					16
+static inline uint32_t CP_SET_BIN_2_Y2(uint32_t val)
+{
+	return ((val) << CP_SET_BIN_2_Y2__SHIFT) & CP_SET_BIN_2_Y2__MASK;
+}
+
+
+#endif /* ADRENO_PM4_XML */
diff --git a/drivers/gpu/drm/msm/dsi/dsi.xml.h b/drivers/gpu/drm/msm/dsi/dsi.xml.h
new file mode 100644
index 000000000000..6f8396be431d
--- /dev/null
+++ b/drivers/gpu/drm/msm/dsi/dsi.xml.h
@@ -0,0 +1,502 @@
+#ifndef DSI_XML
+#define DSI_XML
+
+/* Autogenerated file, DO NOT EDIT manually!
+
+This file was generated by the rules-ng-ng headergen tool in this git repository:
+http://0x04.net/cgit/index.cgi/rules-ng-ng
+git clone git://0x04.net/rules-ng-ng
+
+The rules-ng-ng source files this header was generated from are:
+- /home/robclark/src/freedreno/envytools/rnndb/msm.xml                 (    595 bytes, from 2013-07-05 19:21:12)
+- /home/robclark/src/freedreno/envytools/rnndb/freedreno_copyright.xml (   1453 bytes, from 2013-03-31 16:51:27)
+- /home/robclark/src/freedreno/envytools/rnndb/mdp4/mdp4.xml           (  19332 bytes, from 2013-08-16 22:16:36)
+- /home/robclark/src/freedreno/envytools/rnndb/dsi/dsi.xml             (  11712 bytes, from 2013-08-17 17:13:43)
+- /home/robclark/src/freedreno/envytools/rnndb/dsi/sfpb.xml            (    344 bytes, from 2013-08-11 19:26:32)
+- /home/robclark/src/freedreno/envytools/rnndb/dsi/mmss_cc.xml         (   1544 bytes, from 2013-08-16 19:17:05)
+- /home/robclark/src/freedreno/envytools/rnndb/hdmi/qfprom.xml         (    600 bytes, from 2013-07-05 19:21:12)
+- /home/robclark/src/freedreno/envytools/rnndb/hdmi/hdmi.xml           (  19288 bytes, from 2013-08-11 18:14:15)
+
+Copyright (C) 2013 by the following authors:
+- Rob Clark <robdclark@gmail.com> (robclark)
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice (including the
+next paragraph) shall be included in all copies or substantial
+portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
+IN NO EVENT SHALL THE COPYRIGHT OWNER(S) AND/OR ITS SUPPLIERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+*/
+
+
+enum dsi_traffic_mode {
+	NON_BURST_SYNCH_PULSE = 0,
+	NON_BURST_SYNCH_EVENT = 1,
+	BURST_MODE = 2,
+};
+
+enum dsi_dst_format {
+	DST_FORMAT_RGB565 = 0,
+	DST_FORMAT_RGB666 = 1,
+	DST_FORMAT_RGB666_LOOSE = 2,
+	DST_FORMAT_RGB888 = 3,
+};
+
+enum dsi_rgb_swap {
+	SWAP_RGB = 0,
+	SWAP_RBG = 1,
+	SWAP_BGR = 2,
+	SWAP_BRG = 3,
+	SWAP_GRB = 4,
+	SWAP_GBR = 5,
+};
+
+enum dsi_cmd_trigger {
+	TRIGGER_NONE = 0,
+	TRIGGER_TE = 2,
+	TRIGGER_SW = 4,
+	TRIGGER_SW_SEOF = 5,
+	TRIGGER_SW_TE = 6,
+};
+
+#define DSI_IRQ_CMD_DMA_DONE					0x00000001
+#define DSI_IRQ_MASK_CMD_DMA_DONE				0x00000002
+#define DSI_IRQ_CMD_MDP_DONE					0x00000100
+#define DSI_IRQ_MASK_CMD_MDP_DONE				0x00000200
+#define DSI_IRQ_VIDEO_DONE					0x00010000
+#define DSI_IRQ_MASK_VIDEO_DONE					0x00020000
+#define DSI_IRQ_ERROR						0x01000000
+#define DSI_IRQ_MASK_ERROR					0x02000000
+#define REG_DSI_CTRL						0x00000000
+#define DSI_CTRL_ENABLE						0x00000001
+#define DSI_CTRL_VID_MODE_EN					0x00000002
+#define DSI_CTRL_CMD_MODE_EN					0x00000004
+#define DSI_CTRL_LANE0						0x00000010
+#define DSI_CTRL_LANE1						0x00000020
+#define DSI_CTRL_LANE2						0x00000040
+#define DSI_CTRL_LANE3						0x00000080
+#define DSI_CTRL_CLK_EN						0x00000100
+#define DSI_CTRL_ECC_CHECK					0x00100000
+#define DSI_CTRL_CRC_CHECK					0x01000000
+
+#define REG_DSI_STATUS0						0x00000004
+#define DSI_STATUS0_CMD_MODE_DMA_BUSY				0x00000002
+#define DSI_STATUS0_VIDEO_MODE_ENGINE_BUSY			0x00000008
+#define DSI_STATUS0_DSI_BUSY					0x00000010
+
+#define REG_DSI_FIFO_STATUS					0x00000008
+
+#define REG_DSI_VID_CFG0					0x0000000c
+#define DSI_VID_CFG0_VIRT_CHANNEL__MASK				0x00000003
+#define DSI_VID_CFG0_VIRT_CHANNEL__SHIFT			0
+static inline uint32_t DSI_VID_CFG0_VIRT_CHANNEL(uint32_t val)
+{
+	return ((val) << DSI_VID_CFG0_VIRT_CHANNEL__SHIFT) & DSI_VID_CFG0_VIRT_CHANNEL__MASK;
+}
+#define DSI_VID_CFG0_DST_FORMAT__MASK				0x00000030
+#define DSI_VID_CFG0_DST_FORMAT__SHIFT				4
+static inline uint32_t DSI_VID_CFG0_DST_FORMAT(enum dsi_dst_format val)
+{
+	return ((val) << DSI_VID_CFG0_DST_FORMAT__SHIFT) & DSI_VID_CFG0_DST_FORMAT__MASK;
+}
+#define DSI_VID_CFG0_TRAFFIC_MODE__MASK				0x00000300
+#define DSI_VID_CFG0_TRAFFIC_MODE__SHIFT			8
+static inline uint32_t DSI_VID_CFG0_TRAFFIC_MODE(enum dsi_traffic_mode val)
+{
+	return ((val) << DSI_VID_CFG0_TRAFFIC_MODE__SHIFT) & DSI_VID_CFG0_TRAFFIC_MODE__MASK;
+}
+#define DSI_VID_CFG0_BLLP_POWER_STOP				0x00001000
+#define DSI_VID_CFG0_EOF_BLLP_POWER_STOP			0x00008000
+#define DSI_VID_CFG0_HSA_POWER_STOP				0x00010000
+#define DSI_VID_CFG0_HBP_POWER_STOP				0x00100000
+#define DSI_VID_CFG0_HFP_POWER_STOP				0x01000000
+#define DSI_VID_CFG0_PULSE_MODE_HSA_HE				0x10000000
+
+#define REG_DSI_VID_CFG1					0x0000001c
+#define DSI_VID_CFG1_R_SEL					0x00000010
+#define DSI_VID_CFG1_G_SEL					0x00000100
+#define DSI_VID_CFG1_B_SEL					0x00001000
+#define DSI_VID_CFG1_RGB_SWAP__MASK				0x00070000
+#define DSI_VID_CFG1_RGB_SWAP__SHIFT				16
+static inline uint32_t DSI_VID_CFG1_RGB_SWAP(enum dsi_rgb_swap val)
+{
+	return ((val) << DSI_VID_CFG1_RGB_SWAP__SHIFT) & DSI_VID_CFG1_RGB_SWAP__MASK;
+}
+#define DSI_VID_CFG1_INTERLEAVE_MAX__MASK			0x00f00000
+#define DSI_VID_CFG1_INTERLEAVE_MAX__SHIFT			20
+static inline uint32_t DSI_VID_CFG1_INTERLEAVE_MAX(uint32_t val)
+{
+	return ((val) << DSI_VID_CFG1_INTERLEAVE_MAX__SHIFT) & DSI_VID_CFG1_INTERLEAVE_MAX__MASK;
+}
+
+#define REG_DSI_ACTIVE_H					0x00000020
+#define DSI_ACTIVE_H_START__MASK				0x00000fff
+#define DSI_ACTIVE_H_START__SHIFT				0
+static inline uint32_t DSI_ACTIVE_H_START(uint32_t val)
+{
+	return ((val) << DSI_ACTIVE_H_START__SHIFT) & DSI_ACTIVE_H_START__MASK;
+}
+#define DSI_ACTIVE_H_END__MASK					0x0fff0000
+#define DSI_ACTIVE_H_END__SHIFT					16
+static inline uint32_t DSI_ACTIVE_H_END(uint32_t val)
+{
+	return ((val) << DSI_ACTIVE_H_END__SHIFT) & DSI_ACTIVE_H_END__MASK;
+}
+
+#define REG_DSI_ACTIVE_V					0x00000024
+#define DSI_ACTIVE_V_START__MASK				0x00000fff
+#define DSI_ACTIVE_V_START__SHIFT				0
+static inline uint32_t DSI_ACTIVE_V_START(uint32_t val)
+{
+	return ((val) << DSI_ACTIVE_V_START__SHIFT) & DSI_ACTIVE_V_START__MASK;
+}
+#define DSI_ACTIVE_V_END__MASK					0x0fff0000
+#define DSI_ACTIVE_V_END__SHIFT					16
+static inline uint32_t DSI_ACTIVE_V_END(uint32_t val)
+{
+	return ((val) << DSI_ACTIVE_V_END__SHIFT) & DSI_ACTIVE_V_END__MASK;
+}
+
+#define REG_DSI_TOTAL						0x00000028
+#define DSI_TOTAL_H_TOTAL__MASK					0x00000fff
+#define DSI_TOTAL_H_TOTAL__SHIFT				0
+static inline uint32_t DSI_TOTAL_H_TOTAL(uint32_t val)
+{
+	return ((val) << DSI_TOTAL_H_TOTAL__SHIFT) & DSI_TOTAL_H_TOTAL__MASK;
+}
+#define DSI_TOTAL_V_TOTAL__MASK					0x0fff0000
+#define DSI_TOTAL_V_TOTAL__SHIFT				16
+static inline uint32_t DSI_TOTAL_V_TOTAL(uint32_t val)
+{
+	return ((val) << DSI_TOTAL_V_TOTAL__SHIFT) & DSI_TOTAL_V_TOTAL__MASK;
+}
+
+#define REG_DSI_ACTIVE_HSYNC					0x0000002c
+#define DSI_ACTIVE_HSYNC_START__MASK				0x00000fff
+#define DSI_ACTIVE_HSYNC_START__SHIFT				0
+static inline uint32_t DSI_ACTIVE_HSYNC_START(uint32_t val)
+{
+	return ((val) << DSI_ACTIVE_HSYNC_START__SHIFT) & DSI_ACTIVE_HSYNC_START__MASK;
+}
+#define DSI_ACTIVE_HSYNC_END__MASK				0x0fff0000
+#define DSI_ACTIVE_HSYNC_END__SHIFT				16
+static inline uint32_t DSI_ACTIVE_HSYNC_END(uint32_t val)
+{
+	return ((val) << DSI_ACTIVE_HSYNC_END__SHIFT) & DSI_ACTIVE_HSYNC_END__MASK;
+}
+
+#define REG_DSI_ACTIVE_VSYNC					0x00000034
+#define DSI_ACTIVE_VSYNC_START__MASK				0x00000fff
+#define DSI_ACTIVE_VSYNC_START__SHIFT				0
+static inline uint32_t DSI_ACTIVE_VSYNC_START(uint32_t val)
+{
+	return ((val) << DSI_ACTIVE_VSYNC_START__SHIFT) & DSI_ACTIVE_VSYNC_START__MASK;
+}
+#define DSI_ACTIVE_VSYNC_END__MASK				0x0fff0000
+#define DSI_ACTIVE_VSYNC_END__SHIFT				16
+static inline uint32_t DSI_ACTIVE_VSYNC_END(uint32_t val)
+{
+	return ((val) << DSI_ACTIVE_VSYNC_END__SHIFT) & DSI_ACTIVE_VSYNC_END__MASK;
+}
+
+#define REG_DSI_CMD_DMA_CTRL					0x00000038
+#define DSI_CMD_DMA_CTRL_FROM_FRAME_BUFFER			0x10000000
+#define DSI_CMD_DMA_CTRL_LOW_POWER				0x04000000
+
+#define REG_DSI_CMD_CFG0					0x0000003c
+
+#define REG_DSI_CMD_CFG1					0x00000040
+
+#define REG_DSI_DMA_BASE					0x00000044
+
+#define REG_DSI_DMA_LEN						0x00000048
+
+#define REG_DSI_ACK_ERR_STATUS					0x00000064
+
+static inline uint32_t REG_DSI_RDBK(uint32_t i0) { return 0x00000068 + 0x4*i0; }
+
+static inline uint32_t REG_DSI_RDBK_DATA(uint32_t i0) { return 0x00000068 + 0x4*i0; }
+
+#define REG_DSI_TRIG_CTRL					0x00000080
+#define DSI_TRIG_CTRL_DMA_TRIGGER__MASK				0x0000000f
+#define DSI_TRIG_CTRL_DMA_TRIGGER__SHIFT			0
+static inline uint32_t DSI_TRIG_CTRL_DMA_TRIGGER(enum dsi_cmd_trigger val)
+{
+	return ((val) << DSI_TRIG_CTRL_DMA_TRIGGER__SHIFT) & DSI_TRIG_CTRL_DMA_TRIGGER__MASK;
+}
+#define DSI_TRIG_CTRL_MDP_TRIGGER__MASK				0x000000f0
+#define DSI_TRIG_CTRL_MDP_TRIGGER__SHIFT			4
+static inline uint32_t DSI_TRIG_CTRL_MDP_TRIGGER(enum dsi_cmd_trigger val)
+{
+	return ((val) << DSI_TRIG_CTRL_MDP_TRIGGER__SHIFT) & DSI_TRIG_CTRL_MDP_TRIGGER__MASK;
+}
+#define DSI_TRIG_CTRL_STREAM					0x00000100
+#define DSI_TRIG_CTRL_TE					0x80000000
+
+#define REG_DSI_TRIG_DMA					0x0000008c
+
+#define REG_DSI_DLN0_PHY_ERR					0x000000b0
+
+#define REG_DSI_TIMEOUT_STATUS					0x000000bc
+
+#define REG_DSI_CLKOUT_TIMING_CTRL				0x000000c0
+#define DSI_CLKOUT_TIMING_CTRL_T_CLK_PRE__MASK			0x0000003f
+#define DSI_CLKOUT_TIMING_CTRL_T_CLK_PRE__SHIFT			0
+static inline uint32_t DSI_CLKOUT_TIMING_CTRL_T_CLK_PRE(uint32_t val)
+{
+	return ((val) << DSI_CLKOUT_TIMING_CTRL_T_CLK_PRE__SHIFT) & DSI_CLKOUT_TIMING_CTRL_T_CLK_PRE__MASK;
+}
+#define DSI_CLKOUT_TIMING_CTRL_T_CLK_POST__MASK			0x00003f00
+#define DSI_CLKOUT_TIMING_CTRL_T_CLK_POST__SHIFT		8
+static inline uint32_t DSI_CLKOUT_TIMING_CTRL_T_CLK_POST(uint32_t val)
+{
+	return ((val) << DSI_CLKOUT_TIMING_CTRL_T_CLK_POST__SHIFT) & DSI_CLKOUT_TIMING_CTRL_T_CLK_POST__MASK;
+}
+
+#define REG_DSI_EOT_PACKET_CTRL					0x000000c8
+#define DSI_EOT_PACKET_CTRL_TX_EOT_APPEND			0x00000001
+#define DSI_EOT_PACKET_CTRL_RX_EOT_IGNORE			0x00000010
+
+#define REG_DSI_LANE_SWAP_CTRL					0x000000ac
+
+#define REG_DSI_ERR_INT_MASK0					0x00000108
+
+#define REG_DSI_INTR_CTRL					0x0000010c
+
+#define REG_DSI_RESET						0x00000114
+
+#define REG_DSI_CLK_CTRL					0x00000118
+
+#define REG_DSI_PHY_RESET					0x00000128
+
+#define REG_DSI_PHY_PLL_CTRL_0					0x00000200
+#define DSI_PHY_PLL_CTRL_0_ENABLE				0x00000001
+
+#define REG_DSI_PHY_PLL_CTRL_1					0x00000204
+
+#define REG_DSI_PHY_PLL_CTRL_2					0x00000208
+
+#define REG_DSI_PHY_PLL_CTRL_3					0x0000020c
+
+#define REG_DSI_PHY_PLL_CTRL_4					0x00000210
+
+#define REG_DSI_PHY_PLL_CTRL_5					0x00000214
+
+#define REG_DSI_PHY_PLL_CTRL_6					0x00000218
+
+#define REG_DSI_PHY_PLL_CTRL_7					0x0000021c
+
+#define REG_DSI_PHY_PLL_CTRL_8					0x00000220
+
+#define REG_DSI_PHY_PLL_CTRL_9					0x00000224
+
+#define REG_DSI_PHY_PLL_CTRL_10					0x00000228
+
+#define REG_DSI_PHY_PLL_CTRL_11					0x0000022c
+
+#define REG_DSI_PHY_PLL_CTRL_12					0x00000230
+
+#define REG_DSI_PHY_PLL_CTRL_13					0x00000234
+
+#define REG_DSI_PHY_PLL_CTRL_14					0x00000238
+
+#define REG_DSI_PHY_PLL_CTRL_15					0x0000023c
+
+#define REG_DSI_PHY_PLL_CTRL_16					0x00000240
+
+#define REG_DSI_PHY_PLL_CTRL_17					0x00000244
+
+#define REG_DSI_PHY_PLL_CTRL_18					0x00000248
+
+#define REG_DSI_PHY_PLL_CTRL_19					0x0000024c
+
+#define REG_DSI_PHY_PLL_CTRL_20					0x00000250
+
+#define REG_DSI_PHY_PLL_STATUS					0x00000280
+#define DSI_PHY_PLL_STATUS_PLL_BUSY				0x00000001
+
+#define REG_DSI_8x60_PHY_TPA_CTRL_1				0x00000258
+
+#define REG_DSI_8x60_PHY_TPA_CTRL_2				0x0000025c
+
+#define REG_DSI_8x60_PHY_TIMING_CTRL_0				0x00000260
+
+#define REG_DSI_8x60_PHY_TIMING_CTRL_1				0x00000264
+
+#define REG_DSI_8x60_PHY_TIMING_CTRL_2				0x00000268
+
+#define REG_DSI_8x60_PHY_TIMING_CTRL_3				0x0000026c
+
+#define REG_DSI_8x60_PHY_TIMING_CTRL_4				0x00000270
+
+#define REG_DSI_8x60_PHY_TIMING_CTRL_5				0x00000274
+
+#define REG_DSI_8x60_PHY_TIMING_CTRL_6				0x00000278
+
+#define REG_DSI_8x60_PHY_TIMING_CTRL_7				0x0000027c
+
+#define REG_DSI_8x60_PHY_TIMING_CTRL_8				0x00000280
+
+#define REG_DSI_8x60_PHY_TIMING_CTRL_9				0x00000284
+
+#define REG_DSI_8x60_PHY_TIMING_CTRL_10				0x00000288
+
+#define REG_DSI_8x60_PHY_TIMING_CTRL_11				0x0000028c
+
+#define REG_DSI_8x60_PHY_CTRL_0					0x00000290
+
+#define REG_DSI_8x60_PHY_CTRL_1					0x00000294
+
+#define REG_DSI_8x60_PHY_CTRL_2					0x00000298
+
+#define REG_DSI_8x60_PHY_CTRL_3					0x0000029c
+
+#define REG_DSI_8x60_PHY_STRENGTH_0				0x000002a0
+
+#define REG_DSI_8x60_PHY_STRENGTH_1				0x000002a4
+
+#define REG_DSI_8x60_PHY_STRENGTH_2				0x000002a8
+
+#define REG_DSI_8x60_PHY_STRENGTH_3				0x000002ac
+
+#define REG_DSI_8x60_PHY_REGULATOR_CTRL_0			0x000002cc
+
+#define REG_DSI_8x60_PHY_REGULATOR_CTRL_1			0x000002d0
+
+#define REG_DSI_8x60_PHY_REGULATOR_CTRL_2			0x000002d4
+
+#define REG_DSI_8x60_PHY_REGULATOR_CTRL_3			0x000002d8
+
+#define REG_DSI_8x60_PHY_REGULATOR_CTRL_4			0x000002dc
+
+#define REG_DSI_8x60_PHY_CAL_HW_TRIGGER				0x000000f0
+
+#define REG_DSI_8x60_PHY_CAL_CTRL				0x000000f4
+
+#define REG_DSI_8x60_PHY_CAL_STATUS				0x000000fc
+#define DSI_8x60_PHY_CAL_STATUS_CAL_BUSY			0x10000000
+
+static inline uint32_t REG_DSI_8960_LN(uint32_t i0) { return 0x00000300 + 0x40*i0; }
+
+static inline uint32_t REG_DSI_8960_LN_CFG_0(uint32_t i0) { return 0x00000300 + 0x40*i0; }
+
+static inline uint32_t REG_DSI_8960_LN_CFG_1(uint32_t i0) { return 0x00000304 + 0x40*i0; }
+
+static inline uint32_t REG_DSI_8960_LN_CFG_2(uint32_t i0) { return 0x00000308 + 0x40*i0; }
+
+static inline uint32_t REG_DSI_8960_LN_TEST_DATAPATH(uint32_t i0) { return 0x0000030c + 0x40*i0; }
+
+static inline uint32_t REG_DSI_8960_LN_TEST_STR_0(uint32_t i0) { return 0x00000314 + 0x40*i0; }
+
+static inline uint32_t REG_DSI_8960_LN_TEST_STR_1(uint32_t i0) { return 0x00000318 + 0x40*i0; }
+
+#define REG_DSI_8960_PHY_LNCK_CFG_0				0x00000400
+
+#define REG_DSI_8960_PHY_LNCK_CFG_1				0x00000404
+
+#define REG_DSI_8960_PHY_LNCK_CFG_2				0x00000408
+
+#define REG_DSI_8960_PHY_LNCK_TEST_DATAPATH			0x0000040c
+
+#define REG_DSI_8960_PHY_LNCK_TEST_STR0				0x00000414
+
+#define REG_DSI_8960_PHY_LNCK_TEST_STR1				0x00000418
+
+#define REG_DSI_8960_PHY_TIMING_CTRL_0				0x00000440
+
+#define REG_DSI_8960_PHY_TIMING_CTRL_1				0x00000444
+
+#define REG_DSI_8960_PHY_TIMING_CTRL_2				0x00000448
+
+#define REG_DSI_8960_PHY_TIMING_CTRL_3				0x0000044c
+
+#define REG_DSI_8960_PHY_TIMING_CTRL_4				0x00000450
+
+#define REG_DSI_8960_PHY_TIMING_CTRL_5				0x00000454
+
+#define REG_DSI_8960_PHY_TIMING_CTRL_6				0x00000458
+
+#define REG_DSI_8960_PHY_TIMING_CTRL_7				0x0000045c
+
+#define REG_DSI_8960_PHY_TIMING_CTRL_8				0x00000460
+
+#define REG_DSI_8960_PHY_TIMING_CTRL_9				0x00000464
+
+#define REG_DSI_8960_PHY_TIMING_CTRL_10				0x00000468
+
+#define REG_DSI_8960_PHY_TIMING_CTRL_11				0x0000046c
+
+#define REG_DSI_8960_PHY_CTRL_0					0x00000470
+
+#define REG_DSI_8960_PHY_CTRL_1					0x00000474
+
+#define REG_DSI_8960_PHY_CTRL_2					0x00000478
+
+#define REG_DSI_8960_PHY_CTRL_3					0x0000047c
+
+#define REG_DSI_8960_PHY_STRENGTH_0				0x00000480
+
+#define REG_DSI_8960_PHY_STRENGTH_1				0x00000484
+
+#define REG_DSI_8960_PHY_STRENGTH_2				0x00000488
+
+#define REG_DSI_8960_PHY_BIST_CTRL_0				0x0000048c
+
+#define REG_DSI_8960_PHY_BIST_CTRL_1				0x00000490
+
+#define REG_DSI_8960_PHY_BIST_CTRL_2				0x00000494
+
+#define REG_DSI_8960_PHY_BIST_CTRL_3				0x00000498
+
+#define REG_DSI_8960_PHY_BIST_CTRL_4				0x0000049c
+
+#define REG_DSI_8960_PHY_LDO_CTRL				0x000004b0
+
+#define REG_DSI_8960_PHY_REGULATOR_CTRL_0			0x00000500
+
+#define REG_DSI_8960_PHY_REGULATOR_CTRL_1			0x00000504
+
+#define REG_DSI_8960_PHY_REGULATOR_CTRL_2			0x00000508
+
+#define REG_DSI_8960_PHY_REGULATOR_CTRL_3			0x0000050c
+
+#define REG_DSI_8960_PHY_REGULATOR_CTRL_4			0x00000510
+
+#define REG_DSI_8960_PHY_REGULATOR_CAL_PWR_CFG			0x00000518
+
+#define REG_DSI_8960_PHY_CAL_HW_TRIGGER				0x00000528
+
+#define REG_DSI_8960_PHY_CAL_SW_CFG_0				0x0000052c
+
+#define REG_DSI_8960_PHY_CAL_SW_CFG_1				0x00000530
+
+#define REG_DSI_8960_PHY_CAL_SW_CFG_2				0x00000534
+
+#define REG_DSI_8960_PHY_CAL_HW_CFG_0				0x00000538
+
+#define REG_DSI_8960_PHY_CAL_HW_CFG_1				0x0000053c
+
+#define REG_DSI_8960_PHY_CAL_HW_CFG_2				0x00000540
+
+#define REG_DSI_8960_PHY_CAL_HW_CFG_3				0x00000544
+
+#define REG_DSI_8960_PHY_CAL_HW_CFG_4				0x00000548
+
+#define REG_DSI_8960_PHY_CAL_STATUS				0x00000550
+#define DSI_8960_PHY_CAL_STATUS_CAL_BUSY			0x00000010
+
+
+#endif /* DSI_XML */
diff --git a/drivers/gpu/drm/msm/dsi/mmss_cc.xml.h b/drivers/gpu/drm/msm/dsi/mmss_cc.xml.h
new file mode 100644
index 000000000000..aefc1b8feae9
--- /dev/null
+++ b/drivers/gpu/drm/msm/dsi/mmss_cc.xml.h
@@ -0,0 +1,114 @@
+#ifndef MMSS_CC_XML
+#define MMSS_CC_XML
+
+/* Autogenerated file, DO NOT EDIT manually!
+
+This file was generated by the rules-ng-ng headergen tool in this git repository:
+http://0x04.net/cgit/index.cgi/rules-ng-ng
+git clone git://0x04.net/rules-ng-ng
+
+The rules-ng-ng source files this header was generated from are:
+- /home/robclark/src/freedreno/envytools/rnndb/msm.xml                 (    595 bytes, from 2013-07-05 19:21:12)
+- /home/robclark/src/freedreno/envytools/rnndb/freedreno_copyright.xml (   1453 bytes, from 2013-03-31 16:51:27)
+- /home/robclark/src/freedreno/envytools/rnndb/mdp4/mdp4.xml           (  19332 bytes, from 2013-08-16 22:16:36)
+- /home/robclark/src/freedreno/envytools/rnndb/dsi/dsi.xml             (  11712 bytes, from 2013-08-17 17:13:43)
+- /home/robclark/src/freedreno/envytools/rnndb/dsi/sfpb.xml            (    344 bytes, from 2013-08-11 19:26:32)
+- /home/robclark/src/freedreno/envytools/rnndb/dsi/mmss_cc.xml         (   1544 bytes, from 2013-08-16 19:17:05)
+- /home/robclark/src/freedreno/envytools/rnndb/hdmi/qfprom.xml         (    600 bytes, from 2013-07-05 19:21:12)
+- /home/robclark/src/freedreno/envytools/rnndb/hdmi/hdmi.xml           (  19288 bytes, from 2013-08-11 18:14:15)
+
+Copyright (C) 2013 by the following authors:
+- Rob Clark <robdclark@gmail.com> (robclark)
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice (including the
+next paragraph) shall be included in all copies or substantial
+portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
+IN NO EVENT SHALL THE COPYRIGHT OWNER(S) AND/OR ITS SUPPLIERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+*/
+
+
+enum mmss_cc_clk {
+	CLK = 0,
+	PCLK = 1,
+};
+
+#define REG_MMSS_CC_AHB						0x00000008
+
+static inline uint32_t __offset_CLK(enum mmss_cc_clk idx)
+{
+	switch (idx) {
+		case CLK: return 0x0000004c;
+		case PCLK: return 0x00000130;
+		default: return INVALID_IDX(idx);
+	}
+}
+static inline uint32_t REG_MMSS_CC_CLK(enum mmss_cc_clk i0) { return 0x00000000 + __offset_CLK(i0); }
+
+static inline uint32_t REG_MMSS_CC_CLK_CC(enum mmss_cc_clk i0) { return 0x00000000 + __offset_CLK(i0); }
+#define MMSS_CC_CLK_CC_CLK_EN					0x00000001
+#define MMSS_CC_CLK_CC_ROOT_EN					0x00000004
+#define MMSS_CC_CLK_CC_MND_EN					0x00000020
+#define MMSS_CC_CLK_CC_MND_MODE__MASK				0x000000c0
+#define MMSS_CC_CLK_CC_MND_MODE__SHIFT				6
+static inline uint32_t MMSS_CC_CLK_CC_MND_MODE(uint32_t val)
+{
+	return ((val) << MMSS_CC_CLK_CC_MND_MODE__SHIFT) & MMSS_CC_CLK_CC_MND_MODE__MASK;
+}
+#define MMSS_CC_CLK_CC_PMXO_SEL__MASK				0x00000300
+#define MMSS_CC_CLK_CC_PMXO_SEL__SHIFT				8
+static inline uint32_t MMSS_CC_CLK_CC_PMXO_SEL(uint32_t val)
+{
+	return ((val) << MMSS_CC_CLK_CC_PMXO_SEL__SHIFT) & MMSS_CC_CLK_CC_PMXO_SEL__MASK;
+}
+
+static inline uint32_t REG_MMSS_CC_CLK_MD(enum mmss_cc_clk i0) { return 0x00000004 + __offset_CLK(i0); }
+#define MMSS_CC_CLK_MD_D__MASK					0x000000ff
+#define MMSS_CC_CLK_MD_D__SHIFT					0
+static inline uint32_t MMSS_CC_CLK_MD_D(uint32_t val)
+{
+	return ((val) << MMSS_CC_CLK_MD_D__SHIFT) & MMSS_CC_CLK_MD_D__MASK;
+}
+#define MMSS_CC_CLK_MD_M__MASK					0x0000ff00
+#define MMSS_CC_CLK_MD_M__SHIFT					8
+static inline uint32_t MMSS_CC_CLK_MD_M(uint32_t val)
+{
+	return ((val) << MMSS_CC_CLK_MD_M__SHIFT) & MMSS_CC_CLK_MD_M__MASK;
+}
+
+static inline uint32_t REG_MMSS_CC_CLK_NS(enum mmss_cc_clk i0) { return 0x00000008 + __offset_CLK(i0); }
+#define MMSS_CC_CLK_NS_SRC__MASK				0x0000000f
+#define MMSS_CC_CLK_NS_SRC__SHIFT				0
+static inline uint32_t MMSS_CC_CLK_NS_SRC(uint32_t val)
+{
+	return ((val) << MMSS_CC_CLK_NS_SRC__SHIFT) & MMSS_CC_CLK_NS_SRC__MASK;
+}
+#define MMSS_CC_CLK_NS_PRE_DIV_FUNC__MASK			0x00fff000
+#define MMSS_CC_CLK_NS_PRE_DIV_FUNC__SHIFT			12
+static inline uint32_t MMSS_CC_CLK_NS_PRE_DIV_FUNC(uint32_t val)
+{
+	return ((val) << MMSS_CC_CLK_NS_PRE_DIV_FUNC__SHIFT) & MMSS_CC_CLK_NS_PRE_DIV_FUNC__MASK;
+}
+#define MMSS_CC_CLK_NS_VAL__MASK				0xff000000
+#define MMSS_CC_CLK_NS_VAL__SHIFT				24
+static inline uint32_t MMSS_CC_CLK_NS_VAL(uint32_t val)
+{
+	return ((val) << MMSS_CC_CLK_NS_VAL__SHIFT) & MMSS_CC_CLK_NS_VAL__MASK;
+}
+
+
+#endif /* MMSS_CC_XML */
diff --git a/drivers/gpu/drm/msm/dsi/sfpb.xml.h b/drivers/gpu/drm/msm/dsi/sfpb.xml.h
new file mode 100644
index 000000000000..a225e8170b2a
--- /dev/null
+++ b/drivers/gpu/drm/msm/dsi/sfpb.xml.h
@@ -0,0 +1,48 @@
+#ifndef SFPB_XML
+#define SFPB_XML
+
+/* Autogenerated file, DO NOT EDIT manually!
+
+This file was generated by the rules-ng-ng headergen tool in this git repository:
+http://0x04.net/cgit/index.cgi/rules-ng-ng
+git clone git://0x04.net/rules-ng-ng
+
+The rules-ng-ng source files this header was generated from are:
+- /home/robclark/src/freedreno/envytools/rnndb/msm.xml                 (    595 bytes, from 2013-07-05 19:21:12)
+- /home/robclark/src/freedreno/envytools/rnndb/freedreno_copyright.xml (   1453 bytes, from 2013-03-31 16:51:27)
+- /home/robclark/src/freedreno/envytools/rnndb/mdp4/mdp4.xml           (  19332 bytes, from 2013-08-16 22:16:36)
+- /home/robclark/src/freedreno/envytools/rnndb/dsi/dsi.xml             (  11712 bytes, from 2013-08-17 17:13:43)
+- /home/robclark/src/freedreno/envytools/rnndb/dsi/sfpb.xml            (    344 bytes, from 2013-08-11 19:26:32)
+- /home/robclark/src/freedreno/envytools/rnndb/dsi/mmss_cc.xml         (   1544 bytes, from 2013-08-16 19:17:05)
+- /home/robclark/src/freedreno/envytools/rnndb/hdmi/qfprom.xml         (    600 bytes, from 2013-07-05 19:21:12)
+- /home/robclark/src/freedreno/envytools/rnndb/hdmi/hdmi.xml           (  19288 bytes, from 2013-08-11 18:14:15)
+
+Copyright (C) 2013 by the following authors:
+- Rob Clark <robdclark@gmail.com> (robclark)
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice (including the
+next paragraph) shall be included in all copies or substantial
+portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
+IN NO EVENT SHALL THE COPYRIGHT OWNER(S) AND/OR ITS SUPPLIERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+*/
+
+
+#define REG_SFPB_CFG						0x00000058
+
+
+#endif /* SFPB_XML */
diff --git a/drivers/gpu/drm/msm/hdmi/hdmi.c b/drivers/gpu/drm/msm/hdmi/hdmi.c
new file mode 100644
index 000000000000..50d11df35b21
--- /dev/null
+++ b/drivers/gpu/drm/msm/hdmi/hdmi.c
@@ -0,0 +1,272 @@
+/*
+ * Copyright (C) 2013 Red Hat
+ * Author: Rob Clark <robdclark@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include "hdmi.h"
+
+static struct platform_device *hdmi_pdev;
+
+void hdmi_set_mode(struct hdmi *hdmi, bool power_on)
+{
+	uint32_t ctrl = 0;
+
+	if (power_on) {
+		ctrl |= HDMI_CTRL_ENABLE;
+		if (!hdmi->hdmi_mode) {
+			ctrl |= HDMI_CTRL_HDMI;
+			hdmi_write(hdmi, REG_HDMI_CTRL, ctrl);
+			ctrl &= ~HDMI_CTRL_HDMI;
+		} else {
+			ctrl |= HDMI_CTRL_HDMI;
+		}
+	} else {
+		ctrl = HDMI_CTRL_HDMI;
+	}
+
+	hdmi_write(hdmi, REG_HDMI_CTRL, ctrl);
+	DBG("HDMI Core: %s, HDMI_CTRL=0x%08x",
+			power_on ? "Enable" : "Disable", ctrl);
+}
+
+static irqreturn_t hdmi_irq(int irq, void *dev_id)
+{
+	struct hdmi *hdmi = dev_id;
+
+	/* Process HPD: */
+	hdmi_connector_irq(hdmi->connector);
+
+	/* Process DDC: */
+	hdmi_i2c_irq(hdmi->i2c);
+
+	/* TODO audio.. */
+
+	return IRQ_HANDLED;
+}
+
+void hdmi_destroy(struct kref *kref)
+{
+	struct hdmi *hdmi = container_of(kref, struct hdmi, refcount);
+	struct hdmi_phy *phy = hdmi->phy;
+
+	if (phy)
+		phy->funcs->destroy(phy);
+
+	if (hdmi->i2c)
+		hdmi_i2c_destroy(hdmi->i2c);
+
+	put_device(&hdmi->pdev->dev);
+}
+
+/* initialize connector */
+int hdmi_init(struct drm_device *dev, struct drm_encoder *encoder)
+{
+	struct hdmi *hdmi = NULL;
+	struct msm_drm_private *priv = dev->dev_private;
+	struct platform_device *pdev = hdmi_pdev;
+	struct hdmi_platform_config *config;
+	int ret;
+
+	if (!pdev) {
+		dev_err(dev->dev, "no hdmi device\n");
+		ret = -ENXIO;
+		goto fail;
+	}
+
+	config = pdev->dev.platform_data;
+
+	hdmi = kzalloc(sizeof(*hdmi), GFP_KERNEL);
+	if (!hdmi) {
+		ret = -ENOMEM;
+		goto fail;
+	}
+
+	kref_init(&hdmi->refcount);
+
+	get_device(&pdev->dev);
+
+	hdmi->dev = dev;
+	hdmi->pdev = pdev;
+	hdmi->encoder = encoder;
+
+	/* not sure about which phy maps to which msm.. probably I miss some */
+	if (config->phy_init)
+		hdmi->phy = config->phy_init(hdmi);
+	else
+		hdmi->phy = ERR_PTR(-ENXIO);
+
+	if (IS_ERR(hdmi->phy)) {
+		ret = PTR_ERR(hdmi->phy);
+		dev_err(dev->dev, "failed to load phy: %d\n", ret);
+		hdmi->phy = NULL;
+		goto fail;
+	}
+
+	hdmi->mmio = msm_ioremap(pdev, "hdmi_msm_hdmi_addr", "HDMI");
+	if (IS_ERR(hdmi->mmio)) {
+		ret = PTR_ERR(hdmi->mmio);
+		goto fail;
+	}
+
+	hdmi->mvs = devm_regulator_get(&pdev->dev, "8901_hdmi_mvs");
+	if (IS_ERR(hdmi->mvs))
+		hdmi->mvs = devm_regulator_get(&pdev->dev, "hdmi_mvs");
+	if (IS_ERR(hdmi->mvs)) {
+		ret = PTR_ERR(hdmi->mvs);
+		dev_err(dev->dev, "failed to get mvs regulator: %d\n", ret);
+		goto fail;
+	}
+
+	hdmi->mpp0 = devm_regulator_get(&pdev->dev, "8901_mpp0");
+	if (IS_ERR(hdmi->mpp0))
+		hdmi->mpp0 = NULL;
+
+	hdmi->clk = devm_clk_get(&pdev->dev, "core_clk");
+	if (IS_ERR(hdmi->clk)) {
+		ret = PTR_ERR(hdmi->clk);
+		dev_err(dev->dev, "failed to get 'clk': %d\n", ret);
+		goto fail;
+	}
+
+	hdmi->m_pclk = devm_clk_get(&pdev->dev, "master_iface_clk");
+	if (IS_ERR(hdmi->m_pclk)) {
+		ret = PTR_ERR(hdmi->m_pclk);
+		dev_err(dev->dev, "failed to get 'm_pclk': %d\n", ret);
+		goto fail;
+	}
+
+	hdmi->s_pclk = devm_clk_get(&pdev->dev, "slave_iface_clk");
+	if (IS_ERR(hdmi->s_pclk)) {
+		ret = PTR_ERR(hdmi->s_pclk);
+		dev_err(dev->dev, "failed to get 's_pclk': %d\n", ret);
+		goto fail;
+	}
+
+	hdmi->i2c = hdmi_i2c_init(hdmi);
+	if (IS_ERR(hdmi->i2c)) {
+		ret = PTR_ERR(hdmi->i2c);
+		dev_err(dev->dev, "failed to get i2c: %d\n", ret);
+		hdmi->i2c = NULL;
+		goto fail;
+	}
+
+	hdmi->bridge = hdmi_bridge_init(hdmi);
+	if (IS_ERR(hdmi->bridge)) {
+		ret = PTR_ERR(hdmi->bridge);
+		dev_err(dev->dev, "failed to create HDMI bridge: %d\n", ret);
+		hdmi->bridge = NULL;
+		goto fail;
+	}
+
+	hdmi->connector = hdmi_connector_init(hdmi);
+	if (IS_ERR(hdmi->connector)) {
+		ret = PTR_ERR(hdmi->connector);
+		dev_err(dev->dev, "failed to create HDMI connector: %d\n", ret);
+		hdmi->connector = NULL;
+		goto fail;
+	}
+
+	hdmi->irq = platform_get_irq(pdev, 0);
+	if (hdmi->irq < 0) {
+		ret = hdmi->irq;
+		dev_err(dev->dev, "failed to get irq: %d\n", ret);
+		goto fail;
+	}
+
+	ret = devm_request_threaded_irq(&pdev->dev, hdmi->irq,
+			NULL, hdmi_irq, IRQF_TRIGGER_HIGH | IRQF_ONESHOT,
+			"hdmi_isr", hdmi);
+	if (ret < 0) {
+		dev_err(dev->dev, "failed to request IRQ%u: %d\n",
+				hdmi->irq, ret);
+		goto fail;
+	}
+
+	encoder->bridge = hdmi->bridge;
+
+	priv->bridges[priv->num_bridges++]       = hdmi->bridge;
+	priv->connectors[priv->num_connectors++] = hdmi->connector;
+
+	return 0;
+
+fail:
+	if (hdmi) {
+		/* bridge/connector are normally destroyed by drm: */
+		if (hdmi->bridge)
+			hdmi->bridge->funcs->destroy(hdmi->bridge);
+		if (hdmi->connector)
+			hdmi->connector->funcs->destroy(hdmi->connector);
+		hdmi_destroy(&hdmi->refcount);
+	}
+
+	return ret;
+}
+
+/*
+ * The hdmi device:
+ */
+
+static int hdmi_dev_probe(struct platform_device *pdev)
+{
+	static struct hdmi_platform_config config = {};
+#ifdef CONFIG_OF
+	/* TODO */
+#else
+	if (cpu_is_apq8064()) {
+		config.phy_init      = hdmi_phy_8960_init;
+		config.ddc_clk_gpio  = 70;
+		config.ddc_data_gpio = 71;
+		config.hpd_gpio      = 72;
+		config.pmic_gpio     = 13 + NR_GPIO_IRQS;
+	} else if (cpu_is_msm8960()) {
+		config.phy_init      = hdmi_phy_8960_init;
+		config.ddc_clk_gpio  = 100;
+		config.ddc_data_gpio = 101;
+		config.hpd_gpio      = 102;
+		config.pmic_gpio     = -1;
+	} else if (cpu_is_msm8x60()) {
+		config.phy_init      = hdmi_phy_8x60_init;
+		config.ddc_clk_gpio  = 170;
+		config.ddc_data_gpio = 171;
+		config.hpd_gpio      = 172;
+		config.pmic_gpio     = -1;
+	}
+#endif
+	pdev->dev.platform_data = &config;
+	hdmi_pdev = pdev;
+	return 0;
+}
+
+static int hdmi_dev_remove(struct platform_device *pdev)
+{
+	hdmi_pdev = NULL;
+	return 0;
+}
+
+static struct platform_driver hdmi_driver = {
+	.probe = hdmi_dev_probe,
+	.remove = hdmi_dev_remove,
+	.driver.name = "hdmi_msm",
+};
+
+void __init hdmi_register(void)
+{
+	platform_driver_register(&hdmi_driver);
+}
+
+void __exit hdmi_unregister(void)
+{
+	platform_driver_unregister(&hdmi_driver);
+}
diff --git a/drivers/gpu/drm/msm/hdmi/hdmi.h b/drivers/gpu/drm/msm/hdmi/hdmi.h
new file mode 100644
index 000000000000..2c2ec566394c
--- /dev/null
+++ b/drivers/gpu/drm/msm/hdmi/hdmi.h
@@ -0,0 +1,131 @@
+/*
+ * Copyright (C) 2013 Red Hat
+ * Author: Rob Clark <robdclark@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __HDMI_CONNECTOR_H__
+#define __HDMI_CONNECTOR_H__
+
+#include <linux/i2c.h>
+#include <linux/clk.h>
+#include <linux/platform_device.h>
+#include <linux/regulator/consumer.h>
+
+#include "msm_drv.h"
+#include "hdmi.xml.h"
+
+
+struct hdmi_phy;
+
+struct hdmi {
+	struct kref refcount;
+
+	struct drm_device *dev;
+	struct platform_device *pdev;
+
+	void __iomem *mmio;
+
+	struct regulator *mvs;        /* HDMI_5V */
+	struct regulator *mpp0;       /* External 5V */
+
+	struct clk *clk;
+	struct clk *m_pclk;
+	struct clk *s_pclk;
+
+	struct hdmi_phy *phy;
+	struct i2c_adapter *i2c;
+	struct drm_connector *connector;
+	struct drm_bridge *bridge;
+
+	/* the encoder we are hooked to (outside of hdmi block) */
+	struct drm_encoder *encoder;
+
+	bool hdmi_mode;               /* are we in hdmi mode? */
+
+	int irq;
+};
+
+/* platform config data (ie. from DT, or pdata) */
+struct hdmi_platform_config {
+	struct hdmi_phy *(*phy_init)(struct hdmi *hdmi);
+	int ddc_clk_gpio, ddc_data_gpio, hpd_gpio, pmic_gpio;
+};
+
+void hdmi_set_mode(struct hdmi *hdmi, bool power_on);
+void hdmi_destroy(struct kref *kref);
+
+static inline void hdmi_write(struct hdmi *hdmi, u32 reg, u32 data)
+{
+	msm_writel(data, hdmi->mmio + reg);
+}
+
+static inline u32 hdmi_read(struct hdmi *hdmi, u32 reg)
+{
+	return msm_readl(hdmi->mmio + reg);
+}
+
+static inline struct hdmi * hdmi_reference(struct hdmi *hdmi)
+{
+	kref_get(&hdmi->refcount);
+	return hdmi;
+}
+
+static inline void hdmi_unreference(struct hdmi *hdmi)
+{
+	kref_put(&hdmi->refcount, hdmi_destroy);
+}
+
+/*
+ * The phy appears to be different, for example between 8960 and 8x60,
+ * so split the phy related functions out and load the correct one at
+ * runtime:
+ */
+
+struct hdmi_phy_funcs {
+	void (*destroy)(struct hdmi_phy *phy);
+	void (*reset)(struct hdmi_phy *phy);
+	void (*powerup)(struct hdmi_phy *phy, unsigned long int pixclock);
+	void (*powerdown)(struct hdmi_phy *phy);
+};
+
+struct hdmi_phy {
+	const struct hdmi_phy_funcs *funcs;
+};
+
+struct hdmi_phy *hdmi_phy_8960_init(struct hdmi *hdmi);
+struct hdmi_phy *hdmi_phy_8x60_init(struct hdmi *hdmi);
+
+/*
+ * hdmi bridge:
+ */
+
+struct drm_bridge *hdmi_bridge_init(struct hdmi *hdmi);
+
+/*
+ * hdmi connector:
+ */
+
+void hdmi_connector_irq(struct drm_connector *connector);
+struct drm_connector *hdmi_connector_init(struct hdmi *hdmi);
+
+/*
+ * i2c adapter for ddc:
+ */
+
+void hdmi_i2c_irq(struct i2c_adapter *i2c);
+void hdmi_i2c_destroy(struct i2c_adapter *i2c);
+struct i2c_adapter *hdmi_i2c_init(struct hdmi *hdmi);
+
+#endif /* __HDMI_CONNECTOR_H__ */
diff --git a/drivers/gpu/drm/msm/hdmi/hdmi.xml.h b/drivers/gpu/drm/msm/hdmi/hdmi.xml.h
new file mode 100644
index 000000000000..f5fa4865e059
--- /dev/null
+++ b/drivers/gpu/drm/msm/hdmi/hdmi.xml.h
@@ -0,0 +1,508 @@
+#ifndef HDMI_XML
+#define HDMI_XML
+
+/* Autogenerated file, DO NOT EDIT manually!
+
+This file was generated by the rules-ng-ng headergen tool in this git repository:
+http://0x04.net/cgit/index.cgi/rules-ng-ng
+git clone git://0x04.net/rules-ng-ng
+
+The rules-ng-ng source files this header was generated from are:
+- /home/robclark/src/freedreno/envytools/rnndb/msm.xml                 (    595 bytes, from 2013-07-05 19:21:12)
+- /home/robclark/src/freedreno/envytools/rnndb/freedreno_copyright.xml (   1453 bytes, from 2013-03-31 16:51:27)
+- /home/robclark/src/freedreno/envytools/rnndb/mdp4/mdp4.xml           (  19332 bytes, from 2013-08-16 22:16:36)
+- /home/robclark/src/freedreno/envytools/rnndb/dsi/dsi.xml             (  11712 bytes, from 2013-08-17 17:13:43)
+- /home/robclark/src/freedreno/envytools/rnndb/dsi/sfpb.xml            (    344 bytes, from 2013-08-11 19:26:32)
+- /home/robclark/src/freedreno/envytools/rnndb/dsi/mmss_cc.xml         (   1544 bytes, from 2013-08-16 19:17:05)
+- /home/robclark/src/freedreno/envytools/rnndb/hdmi/qfprom.xml         (    600 bytes, from 2013-07-05 19:21:12)
+- /home/robclark/src/freedreno/envytools/rnndb/hdmi/hdmi.xml           (  19288 bytes, from 2013-08-11 18:14:15)
+
+Copyright (C) 2013 by the following authors:
+- Rob Clark <robdclark@gmail.com> (robclark)
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice (including the
+next paragraph) shall be included in all copies or substantial
+portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
+IN NO EVENT SHALL THE COPYRIGHT OWNER(S) AND/OR ITS SUPPLIERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+*/
+
+
+enum hdmi_hdcp_key_state {
+	NO_KEYS = 0,
+	NOT_CHECKED = 1,
+	CHECKING = 2,
+	KEYS_VALID = 3,
+	AKSV_INVALID = 4,
+	CHECKSUM_MISMATCH = 5,
+};
+
+enum hdmi_ddc_read_write {
+	DDC_WRITE = 0,
+	DDC_READ = 1,
+};
+
+enum hdmi_acr_cts {
+	ACR_NONE = 0,
+	ACR_32 = 1,
+	ACR_44 = 2,
+	ACR_48 = 3,
+};
+
+#define REG_HDMI_CTRL						0x00000000
+#define HDMI_CTRL_ENABLE					0x00000001
+#define HDMI_CTRL_HDMI						0x00000002
+#define HDMI_CTRL_ENCRYPTED					0x00000004
+
+#define REG_HDMI_AUDIO_PKT_CTRL1				0x00000020
+#define HDMI_AUDIO_PKT_CTRL1_AUDIO_SAMPLE_SEND			0x00000001
+
+#define REG_HDMI_ACR_PKT_CTRL					0x00000024
+#define HDMI_ACR_PKT_CTRL_CONT					0x00000001
+#define HDMI_ACR_PKT_CTRL_SEND					0x00000002
+#define HDMI_ACR_PKT_CTRL_SELECT__MASK				0x00000030
+#define HDMI_ACR_PKT_CTRL_SELECT__SHIFT				4
+static inline uint32_t HDMI_ACR_PKT_CTRL_SELECT(enum hdmi_acr_cts val)
+{
+	return ((val) << HDMI_ACR_PKT_CTRL_SELECT__SHIFT) & HDMI_ACR_PKT_CTRL_SELECT__MASK;
+}
+#define HDMI_ACR_PKT_CTRL_SOURCE				0x00000100
+#define HDMI_ACR_PKT_CTRL_N_MULTIPLIER__MASK			0x00070000
+#define HDMI_ACR_PKT_CTRL_N_MULTIPLIER__SHIFT			16
+static inline uint32_t HDMI_ACR_PKT_CTRL_N_MULTIPLIER(uint32_t val)
+{
+	return ((val) << HDMI_ACR_PKT_CTRL_N_MULTIPLIER__SHIFT) & HDMI_ACR_PKT_CTRL_N_MULTIPLIER__MASK;
+}
+#define HDMI_ACR_PKT_CTRL_AUDIO_PRIORITY			0x80000000
+
+#define REG_HDMI_VBI_PKT_CTRL					0x00000028
+#define HDMI_VBI_PKT_CTRL_GC_ENABLE				0x00000010
+#define HDMI_VBI_PKT_CTRL_GC_EVERY_FRAME			0x00000020
+#define HDMI_VBI_PKT_CTRL_ISRC_SEND				0x00000100
+#define HDMI_VBI_PKT_CTRL_ISRC_CONTINUOUS			0x00000200
+#define HDMI_VBI_PKT_CTRL_ACP_SEND				0x00001000
+#define HDMI_VBI_PKT_CTRL_ACP_SRC_SW				0x00002000
+
+#define REG_HDMI_INFOFRAME_CTRL0				0x0000002c
+#define HDMI_INFOFRAME_CTRL0_AVI_SEND				0x00000001
+#define HDMI_INFOFRAME_CTRL0_AVI_CONT				0x00000002
+#define HDMI_INFOFRAME_CTRL0_AUDIO_INFO_SEND			0x00000010
+#define HDMI_INFOFRAME_CTRL0_AUDIO_INFO_CONT			0x00000020
+#define HDMI_INFOFRAME_CTRL0_AUDIO_INFO_SOURCE			0x00000040
+#define HDMI_INFOFRAME_CTRL0_AUDIO_INFO_UPDATE			0x00000080
+
+#define REG_HDMI_GEN_PKT_CTRL					0x00000034
+#define HDMI_GEN_PKT_CTRL_GENERIC0_SEND				0x00000001
+#define HDMI_GEN_PKT_CTRL_GENERIC0_CONT				0x00000002
+#define HDMI_GEN_PKT_CTRL_GENERIC0_UPDATE__MASK			0x0000000c
+#define HDMI_GEN_PKT_CTRL_GENERIC0_UPDATE__SHIFT		2
+static inline uint32_t HDMI_GEN_PKT_CTRL_GENERIC0_UPDATE(uint32_t val)
+{
+	return ((val) << HDMI_GEN_PKT_CTRL_GENERIC0_UPDATE__SHIFT) & HDMI_GEN_PKT_CTRL_GENERIC0_UPDATE__MASK;
+}
+#define HDMI_GEN_PKT_CTRL_GENERIC1_SEND				0x00000010
+#define HDMI_GEN_PKT_CTRL_GENERIC1_CONT				0x00000020
+#define HDMI_GEN_PKT_CTRL_GENERIC0_LINE__MASK			0x003f0000
+#define HDMI_GEN_PKT_CTRL_GENERIC0_LINE__SHIFT			16
+static inline uint32_t HDMI_GEN_PKT_CTRL_GENERIC0_LINE(uint32_t val)
+{
+	return ((val) << HDMI_GEN_PKT_CTRL_GENERIC0_LINE__SHIFT) & HDMI_GEN_PKT_CTRL_GENERIC0_LINE__MASK;
+}
+#define HDMI_GEN_PKT_CTRL_GENERIC1_LINE__MASK			0x3f000000
+#define HDMI_GEN_PKT_CTRL_GENERIC1_LINE__SHIFT			24
+static inline uint32_t HDMI_GEN_PKT_CTRL_GENERIC1_LINE(uint32_t val)
+{
+	return ((val) << HDMI_GEN_PKT_CTRL_GENERIC1_LINE__SHIFT) & HDMI_GEN_PKT_CTRL_GENERIC1_LINE__MASK;
+}
+
+#define REG_HDMI_GC						0x00000040
+#define HDMI_GC_MUTE						0x00000001
+
+#define REG_HDMI_AUDIO_PKT_CTRL2				0x00000044
+#define HDMI_AUDIO_PKT_CTRL2_OVERRIDE				0x00000001
+#define HDMI_AUDIO_PKT_CTRL2_LAYOUT				0x00000002
+
+static inline uint32_t REG_HDMI_AVI_INFO(uint32_t i0) { return 0x0000006c + 0x4*i0; }
+
+#define REG_HDMI_GENERIC0_HDR					0x00000084
+
+static inline uint32_t REG_HDMI_GENERIC0(uint32_t i0) { return 0x00000088 + 0x4*i0; }
+
+#define REG_HDMI_GENERIC1_HDR					0x000000a4
+
+static inline uint32_t REG_HDMI_GENERIC1(uint32_t i0) { return 0x000000a8 + 0x4*i0; }
+
+static inline uint32_t REG_HDMI_ACR(uint32_t i0) { return 0x000000c4 + 0x8*i0; }
+
+static inline uint32_t REG_HDMI_ACR_0(uint32_t i0) { return 0x000000c4 + 0x8*i0; }
+#define HDMI_ACR_0_CTS__MASK					0xfffff000
+#define HDMI_ACR_0_CTS__SHIFT					12
+static inline uint32_t HDMI_ACR_0_CTS(uint32_t val)
+{
+	return ((val) << HDMI_ACR_0_CTS__SHIFT) & HDMI_ACR_0_CTS__MASK;
+}
+
+static inline uint32_t REG_HDMI_ACR_1(uint32_t i0) { return 0x000000c8 + 0x8*i0; }
+#define HDMI_ACR_1_N__MASK					0xffffffff
+#define HDMI_ACR_1_N__SHIFT					0
+static inline uint32_t HDMI_ACR_1_N(uint32_t val)
+{
+	return ((val) << HDMI_ACR_1_N__SHIFT) & HDMI_ACR_1_N__MASK;
+}
+
+#define REG_HDMI_AUDIO_INFO0					0x000000e4
+#define HDMI_AUDIO_INFO0_CHECKSUM__MASK				0x000000ff
+#define HDMI_AUDIO_INFO0_CHECKSUM__SHIFT			0
+static inline uint32_t HDMI_AUDIO_INFO0_CHECKSUM(uint32_t val)
+{
+	return ((val) << HDMI_AUDIO_INFO0_CHECKSUM__SHIFT) & HDMI_AUDIO_INFO0_CHECKSUM__MASK;
+}
+#define HDMI_AUDIO_INFO0_CC__MASK				0x00000700
+#define HDMI_AUDIO_INFO0_CC__SHIFT				8
+static inline uint32_t HDMI_AUDIO_INFO0_CC(uint32_t val)
+{
+	return ((val) << HDMI_AUDIO_INFO0_CC__SHIFT) & HDMI_AUDIO_INFO0_CC__MASK;
+}
+
+#define REG_HDMI_AUDIO_INFO1					0x000000e8
+#define HDMI_AUDIO_INFO1_CA__MASK				0x000000ff
+#define HDMI_AUDIO_INFO1_CA__SHIFT				0
+static inline uint32_t HDMI_AUDIO_INFO1_CA(uint32_t val)
+{
+	return ((val) << HDMI_AUDIO_INFO1_CA__SHIFT) & HDMI_AUDIO_INFO1_CA__MASK;
+}
+#define HDMI_AUDIO_INFO1_LSV__MASK				0x00007800
+#define HDMI_AUDIO_INFO1_LSV__SHIFT				11
+static inline uint32_t HDMI_AUDIO_INFO1_LSV(uint32_t val)
+{
+	return ((val) << HDMI_AUDIO_INFO1_LSV__SHIFT) & HDMI_AUDIO_INFO1_LSV__MASK;
+}
+#define HDMI_AUDIO_INFO1_DM_INH					0x00008000
+
+#define REG_HDMI_HDCP_CTRL					0x00000110
+#define HDMI_HDCP_CTRL_ENABLE					0x00000001
+#define HDMI_HDCP_CTRL_ENCRYPTION_ENABLE			0x00000100
+
+#define REG_HDMI_HDCP_INT_CTRL					0x00000118
+
+#define REG_HDMI_HDCP_LINK0_STATUS				0x0000011c
+#define HDMI_HDCP_LINK0_STATUS_AN_0_READY			0x00000100
+#define HDMI_HDCP_LINK0_STATUS_AN_1_READY			0x00000200
+#define HDMI_HDCP_LINK0_STATUS_KEY_STATE__MASK			0x70000000
+#define HDMI_HDCP_LINK0_STATUS_KEY_STATE__SHIFT			28
+static inline uint32_t HDMI_HDCP_LINK0_STATUS_KEY_STATE(enum hdmi_hdcp_key_state val)
+{
+	return ((val) << HDMI_HDCP_LINK0_STATUS_KEY_STATE__SHIFT) & HDMI_HDCP_LINK0_STATUS_KEY_STATE__MASK;
+}
+
+#define REG_HDMI_HDCP_RESET					0x00000130
+#define HDMI_HDCP_RESET_LINK0_DEAUTHENTICATE			0x00000001
+
+#define REG_HDMI_AUDIO_CFG					0x000001d0
+#define HDMI_AUDIO_CFG_ENGINE_ENABLE				0x00000001
+#define HDMI_AUDIO_CFG_FIFO_WATERMARK__MASK			0x000000f0
+#define HDMI_AUDIO_CFG_FIFO_WATERMARK__SHIFT			4
+static inline uint32_t HDMI_AUDIO_CFG_FIFO_WATERMARK(uint32_t val)
+{
+	return ((val) << HDMI_AUDIO_CFG_FIFO_WATERMARK__SHIFT) & HDMI_AUDIO_CFG_FIFO_WATERMARK__MASK;
+}
+
+#define REG_HDMI_USEC_REFTIMER					0x00000208
+
+#define REG_HDMI_DDC_CTRL					0x0000020c
+#define HDMI_DDC_CTRL_GO					0x00000001
+#define HDMI_DDC_CTRL_SOFT_RESET				0x00000002
+#define HDMI_DDC_CTRL_SEND_RESET				0x00000004
+#define HDMI_DDC_CTRL_SW_STATUS_RESET				0x00000008
+#define HDMI_DDC_CTRL_TRANSACTION_CNT__MASK			0x00300000
+#define HDMI_DDC_CTRL_TRANSACTION_CNT__SHIFT			20
+static inline uint32_t HDMI_DDC_CTRL_TRANSACTION_CNT(uint32_t val)
+{
+	return ((val) << HDMI_DDC_CTRL_TRANSACTION_CNT__SHIFT) & HDMI_DDC_CTRL_TRANSACTION_CNT__MASK;
+}
+
+#define REG_HDMI_DDC_INT_CTRL					0x00000214
+#define HDMI_DDC_INT_CTRL_SW_DONE_INT				0x00000001
+#define HDMI_DDC_INT_CTRL_SW_DONE_ACK				0x00000002
+#define HDMI_DDC_INT_CTRL_SW_DONE_MASK				0x00000004
+
+#define REG_HDMI_DDC_SW_STATUS					0x00000218
+#define HDMI_DDC_SW_STATUS_NACK0				0x00001000
+#define HDMI_DDC_SW_STATUS_NACK1				0x00002000
+#define HDMI_DDC_SW_STATUS_NACK2				0x00004000
+#define HDMI_DDC_SW_STATUS_NACK3				0x00008000
+
+#define REG_HDMI_DDC_HW_STATUS					0x0000021c
+
+#define REG_HDMI_DDC_SPEED					0x00000220
+#define HDMI_DDC_SPEED_THRESHOLD__MASK				0x00000003
+#define HDMI_DDC_SPEED_THRESHOLD__SHIFT				0
+static inline uint32_t HDMI_DDC_SPEED_THRESHOLD(uint32_t val)
+{
+	return ((val) << HDMI_DDC_SPEED_THRESHOLD__SHIFT) & HDMI_DDC_SPEED_THRESHOLD__MASK;
+}
+#define HDMI_DDC_SPEED_PRESCALE__MASK				0xffff0000
+#define HDMI_DDC_SPEED_PRESCALE__SHIFT				16
+static inline uint32_t HDMI_DDC_SPEED_PRESCALE(uint32_t val)
+{
+	return ((val) << HDMI_DDC_SPEED_PRESCALE__SHIFT) & HDMI_DDC_SPEED_PRESCALE__MASK;
+}
+
+#define REG_HDMI_DDC_SETUP					0x00000224
+#define HDMI_DDC_SETUP_TIMEOUT__MASK				0xff000000
+#define HDMI_DDC_SETUP_TIMEOUT__SHIFT				24
+static inline uint32_t HDMI_DDC_SETUP_TIMEOUT(uint32_t val)
+{
+	return ((val) << HDMI_DDC_SETUP_TIMEOUT__SHIFT) & HDMI_DDC_SETUP_TIMEOUT__MASK;
+}
+
+static inline uint32_t REG_HDMI_I2C_TRANSACTION(uint32_t i0) { return 0x00000228 + 0x4*i0; }
+
+static inline uint32_t REG_HDMI_I2C_TRANSACTION_REG(uint32_t i0) { return 0x00000228 + 0x4*i0; }
+#define HDMI_I2C_TRANSACTION_REG_RW__MASK			0x00000001
+#define HDMI_I2C_TRANSACTION_REG_RW__SHIFT			0
+static inline uint32_t HDMI_I2C_TRANSACTION_REG_RW(enum hdmi_ddc_read_write val)
+{
+	return ((val) << HDMI_I2C_TRANSACTION_REG_RW__SHIFT) & HDMI_I2C_TRANSACTION_REG_RW__MASK;
+}
+#define HDMI_I2C_TRANSACTION_REG_STOP_ON_NACK			0x00000100
+#define HDMI_I2C_TRANSACTION_REG_START				0x00001000
+#define HDMI_I2C_TRANSACTION_REG_STOP				0x00002000
+#define HDMI_I2C_TRANSACTION_REG_CNT__MASK			0x00ff0000
+#define HDMI_I2C_TRANSACTION_REG_CNT__SHIFT			16
+static inline uint32_t HDMI_I2C_TRANSACTION_REG_CNT(uint32_t val)
+{
+	return ((val) << HDMI_I2C_TRANSACTION_REG_CNT__SHIFT) & HDMI_I2C_TRANSACTION_REG_CNT__MASK;
+}
+
+#define REG_HDMI_DDC_DATA					0x00000238
+#define HDMI_DDC_DATA_DATA_RW__MASK				0x00000001
+#define HDMI_DDC_DATA_DATA_RW__SHIFT				0
+static inline uint32_t HDMI_DDC_DATA_DATA_RW(enum hdmi_ddc_read_write val)
+{
+	return ((val) << HDMI_DDC_DATA_DATA_RW__SHIFT) & HDMI_DDC_DATA_DATA_RW__MASK;
+}
+#define HDMI_DDC_DATA_DATA__MASK				0x0000ff00
+#define HDMI_DDC_DATA_DATA__SHIFT				8
+static inline uint32_t HDMI_DDC_DATA_DATA(uint32_t val)
+{
+	return ((val) << HDMI_DDC_DATA_DATA__SHIFT) & HDMI_DDC_DATA_DATA__MASK;
+}
+#define HDMI_DDC_DATA_INDEX__MASK				0x00ff0000
+#define HDMI_DDC_DATA_INDEX__SHIFT				16
+static inline uint32_t HDMI_DDC_DATA_INDEX(uint32_t val)
+{
+	return ((val) << HDMI_DDC_DATA_INDEX__SHIFT) & HDMI_DDC_DATA_INDEX__MASK;
+}
+#define HDMI_DDC_DATA_INDEX_WRITE				0x80000000
+
+#define REG_HDMI_HPD_INT_STATUS					0x00000250
+#define HDMI_HPD_INT_STATUS_INT					0x00000001
+#define HDMI_HPD_INT_STATUS_CABLE_DETECTED			0x00000002
+
+#define REG_HDMI_HPD_INT_CTRL					0x00000254
+#define HDMI_HPD_INT_CTRL_INT_ACK				0x00000001
+#define HDMI_HPD_INT_CTRL_INT_CONNECT				0x00000002
+#define HDMI_HPD_INT_CTRL_INT_EN				0x00000004
+#define HDMI_HPD_INT_CTRL_RX_INT_ACK				0x00000010
+#define HDMI_HPD_INT_CTRL_RX_INT_EN				0x00000020
+#define HDMI_HPD_INT_CTRL_RCV_PLUGIN_DET_MASK			0x00000200
+
+#define REG_HDMI_HPD_CTRL					0x00000258
+#define HDMI_HPD_CTRL_TIMEOUT__MASK				0x00001fff
+#define HDMI_HPD_CTRL_TIMEOUT__SHIFT				0
+static inline uint32_t HDMI_HPD_CTRL_TIMEOUT(uint32_t val)
+{
+	return ((val) << HDMI_HPD_CTRL_TIMEOUT__SHIFT) & HDMI_HPD_CTRL_TIMEOUT__MASK;
+}
+#define HDMI_HPD_CTRL_ENABLE					0x10000000
+
+#define REG_HDMI_DDC_REF					0x0000027c
+#define HDMI_DDC_REF_REFTIMER_ENABLE				0x00010000
+#define HDMI_DDC_REF_REFTIMER__MASK				0x0000ffff
+#define HDMI_DDC_REF_REFTIMER__SHIFT				0
+static inline uint32_t HDMI_DDC_REF_REFTIMER(uint32_t val)
+{
+	return ((val) << HDMI_DDC_REF_REFTIMER__SHIFT) & HDMI_DDC_REF_REFTIMER__MASK;
+}
+
+#define REG_HDMI_ACTIVE_HSYNC					0x000002b4
+#define HDMI_ACTIVE_HSYNC_START__MASK				0x00000fff
+#define HDMI_ACTIVE_HSYNC_START__SHIFT				0
+static inline uint32_t HDMI_ACTIVE_HSYNC_START(uint32_t val)
+{
+	return ((val) << HDMI_ACTIVE_HSYNC_START__SHIFT) & HDMI_ACTIVE_HSYNC_START__MASK;
+}
+#define HDMI_ACTIVE_HSYNC_END__MASK				0x0fff0000
+#define HDMI_ACTIVE_HSYNC_END__SHIFT				16
+static inline uint32_t HDMI_ACTIVE_HSYNC_END(uint32_t val)
+{
+	return ((val) << HDMI_ACTIVE_HSYNC_END__SHIFT) & HDMI_ACTIVE_HSYNC_END__MASK;
+}
+
+#define REG_HDMI_ACTIVE_VSYNC					0x000002b8
+#define HDMI_ACTIVE_VSYNC_START__MASK				0x00000fff
+#define HDMI_ACTIVE_VSYNC_START__SHIFT				0
+static inline uint32_t HDMI_ACTIVE_VSYNC_START(uint32_t val)
+{
+	return ((val) << HDMI_ACTIVE_VSYNC_START__SHIFT) & HDMI_ACTIVE_VSYNC_START__MASK;
+}
+#define HDMI_ACTIVE_VSYNC_END__MASK				0x0fff0000
+#define HDMI_ACTIVE_VSYNC_END__SHIFT				16
+static inline uint32_t HDMI_ACTIVE_VSYNC_END(uint32_t val)
+{
+	return ((val) << HDMI_ACTIVE_VSYNC_END__SHIFT) & HDMI_ACTIVE_VSYNC_END__MASK;
+}
+
+#define REG_HDMI_VSYNC_ACTIVE_F2				0x000002bc
+#define HDMI_VSYNC_ACTIVE_F2_START__MASK			0x00000fff
+#define HDMI_VSYNC_ACTIVE_F2_START__SHIFT			0
+static inline uint32_t HDMI_VSYNC_ACTIVE_F2_START(uint32_t val)
+{
+	return ((val) << HDMI_VSYNC_ACTIVE_F2_START__SHIFT) & HDMI_VSYNC_ACTIVE_F2_START__MASK;
+}
+#define HDMI_VSYNC_ACTIVE_F2_END__MASK				0x0fff0000
+#define HDMI_VSYNC_ACTIVE_F2_END__SHIFT				16
+static inline uint32_t HDMI_VSYNC_ACTIVE_F2_END(uint32_t val)
+{
+	return ((val) << HDMI_VSYNC_ACTIVE_F2_END__SHIFT) & HDMI_VSYNC_ACTIVE_F2_END__MASK;
+}
+
+#define REG_HDMI_TOTAL						0x000002c0
+#define HDMI_TOTAL_H_TOTAL__MASK				0x00000fff
+#define HDMI_TOTAL_H_TOTAL__SHIFT				0
+static inline uint32_t HDMI_TOTAL_H_TOTAL(uint32_t val)
+{
+	return ((val) << HDMI_TOTAL_H_TOTAL__SHIFT) & HDMI_TOTAL_H_TOTAL__MASK;
+}
+#define HDMI_TOTAL_V_TOTAL__MASK				0x0fff0000
+#define HDMI_TOTAL_V_TOTAL__SHIFT				16
+static inline uint32_t HDMI_TOTAL_V_TOTAL(uint32_t val)
+{
+	return ((val) << HDMI_TOTAL_V_TOTAL__SHIFT) & HDMI_TOTAL_V_TOTAL__MASK;
+}
+
+#define REG_HDMI_VSYNC_TOTAL_F2					0x000002c4
+#define HDMI_VSYNC_TOTAL_F2_V_TOTAL__MASK			0x00000fff
+#define HDMI_VSYNC_TOTAL_F2_V_TOTAL__SHIFT			0
+static inline uint32_t HDMI_VSYNC_TOTAL_F2_V_TOTAL(uint32_t val)
+{
+	return ((val) << HDMI_VSYNC_TOTAL_F2_V_TOTAL__SHIFT) & HDMI_VSYNC_TOTAL_F2_V_TOTAL__MASK;
+}
+
+#define REG_HDMI_FRAME_CTRL					0x000002c8
+#define HDMI_FRAME_CTRL_RGB_MUX_SEL_BGR				0x00001000
+#define HDMI_FRAME_CTRL_VSYNC_LOW				0x10000000
+#define HDMI_FRAME_CTRL_HSYNC_LOW				0x20000000
+#define HDMI_FRAME_CTRL_INTERLACED_EN				0x80000000
+
+#define REG_HDMI_PHY_CTRL					0x000002d4
+#define HDMI_PHY_CTRL_SW_RESET_PLL				0x00000001
+#define HDMI_PHY_CTRL_SW_RESET_PLL_LOW				0x00000002
+#define HDMI_PHY_CTRL_SW_RESET					0x00000004
+#define HDMI_PHY_CTRL_SW_RESET_LOW				0x00000008
+
+#define REG_HDMI_AUD_INT					0x000002cc
+#define HDMI_AUD_INT_AUD_FIFO_URUN_INT				0x00000001
+#define HDMI_AUD_INT_AUD_FIFO_URAN_MASK				0x00000002
+#define HDMI_AUD_INT_AUD_SAM_DROP_INT				0x00000004
+#define HDMI_AUD_INT_AUD_SAM_DROP_MASK				0x00000008
+
+#define REG_HDMI_8x60_PHY_REG0					0x00000300
+#define HDMI_8x60_PHY_REG0_DESER_DEL_CTRL__MASK			0x0000001c
+#define HDMI_8x60_PHY_REG0_DESER_DEL_CTRL__SHIFT		2
+static inline uint32_t HDMI_8x60_PHY_REG0_DESER_DEL_CTRL(uint32_t val)
+{
+	return ((val) << HDMI_8x60_PHY_REG0_DESER_DEL_CTRL__SHIFT) & HDMI_8x60_PHY_REG0_DESER_DEL_CTRL__MASK;
+}
+
+#define REG_HDMI_8x60_PHY_REG1					0x00000304
+#define HDMI_8x60_PHY_REG1_DTEST_MUX_SEL__MASK			0x000000f0
+#define HDMI_8x60_PHY_REG1_DTEST_MUX_SEL__SHIFT			4
+static inline uint32_t HDMI_8x60_PHY_REG1_DTEST_MUX_SEL(uint32_t val)
+{
+	return ((val) << HDMI_8x60_PHY_REG1_DTEST_MUX_SEL__SHIFT) & HDMI_8x60_PHY_REG1_DTEST_MUX_SEL__MASK;
+}
+#define HDMI_8x60_PHY_REG1_OUTVOL_SWING_CTRL__MASK		0x0000000f
+#define HDMI_8x60_PHY_REG1_OUTVOL_SWING_CTRL__SHIFT		0
+static inline uint32_t HDMI_8x60_PHY_REG1_OUTVOL_SWING_CTRL(uint32_t val)
+{
+	return ((val) << HDMI_8x60_PHY_REG1_OUTVOL_SWING_CTRL__SHIFT) & HDMI_8x60_PHY_REG1_OUTVOL_SWING_CTRL__MASK;
+}
+
+#define REG_HDMI_8x60_PHY_REG2					0x00000308
+#define HDMI_8x60_PHY_REG2_PD_DESER				0x00000001
+#define HDMI_8x60_PHY_REG2_PD_DRIVE_1				0x00000002
+#define HDMI_8x60_PHY_REG2_PD_DRIVE_2				0x00000004
+#define HDMI_8x60_PHY_REG2_PD_DRIVE_3				0x00000008
+#define HDMI_8x60_PHY_REG2_PD_DRIVE_4				0x00000010
+#define HDMI_8x60_PHY_REG2_PD_PLL				0x00000020
+#define HDMI_8x60_PHY_REG2_PD_PWRGEN				0x00000040
+#define HDMI_8x60_PHY_REG2_RCV_SENSE_EN				0x00000080
+
+#define REG_HDMI_8x60_PHY_REG3					0x0000030c
+#define HDMI_8x60_PHY_REG3_PLL_ENABLE				0x00000001
+
+#define REG_HDMI_8x60_PHY_REG4					0x00000310
+
+#define REG_HDMI_8x60_PHY_REG5					0x00000314
+
+#define REG_HDMI_8x60_PHY_REG6					0x00000318
+
+#define REG_HDMI_8x60_PHY_REG7					0x0000031c
+
+#define REG_HDMI_8x60_PHY_REG8					0x00000320
+
+#define REG_HDMI_8x60_PHY_REG9					0x00000324
+
+#define REG_HDMI_8x60_PHY_REG10					0x00000328
+
+#define REG_HDMI_8x60_PHY_REG11					0x0000032c
+
+#define REG_HDMI_8x60_PHY_REG12					0x00000330
+#define HDMI_8x60_PHY_REG12_RETIMING_EN				0x00000001
+#define HDMI_8x60_PHY_REG12_PLL_LOCK_DETECT_EN			0x00000002
+#define HDMI_8x60_PHY_REG12_FORCE_LOCK				0x00000010
+
+#define REG_HDMI_8960_PHY_REG0					0x00000400
+
+#define REG_HDMI_8960_PHY_REG1					0x00000404
+
+#define REG_HDMI_8960_PHY_REG2					0x00000408
+
+#define REG_HDMI_8960_PHY_REG3					0x0000040c
+
+#define REG_HDMI_8960_PHY_REG4					0x00000410
+
+#define REG_HDMI_8960_PHY_REG5					0x00000414
+
+#define REG_HDMI_8960_PHY_REG6					0x00000418
+
+#define REG_HDMI_8960_PHY_REG7					0x0000041c
+
+#define REG_HDMI_8960_PHY_REG8					0x00000420
+
+#define REG_HDMI_8960_PHY_REG9					0x00000424
+
+#define REG_HDMI_8960_PHY_REG10					0x00000428
+
+#define REG_HDMI_8960_PHY_REG11					0x0000042c
+
+#define REG_HDMI_8960_PHY_REG12					0x00000430
+
+
+#endif /* HDMI_XML */
diff --git a/drivers/gpu/drm/msm/hdmi/hdmi_bridge.c b/drivers/gpu/drm/msm/hdmi/hdmi_bridge.c
new file mode 100644
index 000000000000..5a8ee3473cf5
--- /dev/null
+++ b/drivers/gpu/drm/msm/hdmi/hdmi_bridge.c
@@ -0,0 +1,167 @@
+/*
+ * Copyright (C) 2013 Red Hat
+ * Author: Rob Clark <robdclark@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include "hdmi.h"
+
+struct hdmi_bridge {
+	struct drm_bridge base;
+
+	struct hdmi *hdmi;
+
+	unsigned long int pixclock;
+};
+#define to_hdmi_bridge(x) container_of(x, struct hdmi_bridge, base)
+
+static void hdmi_bridge_destroy(struct drm_bridge *bridge)
+{
+	struct hdmi_bridge *hdmi_bridge = to_hdmi_bridge(bridge);
+	hdmi_unreference(hdmi_bridge->hdmi);
+	drm_bridge_cleanup(bridge);
+	kfree(hdmi_bridge);
+}
+
+static void hdmi_bridge_pre_enable(struct drm_bridge *bridge)
+{
+	struct hdmi_bridge *hdmi_bridge = to_hdmi_bridge(bridge);
+	struct hdmi *hdmi = hdmi_bridge->hdmi;
+	struct hdmi_phy *phy = hdmi->phy;
+
+	DBG("power up");
+	phy->funcs->powerup(phy, hdmi_bridge->pixclock);
+	hdmi_set_mode(hdmi, true);
+}
+
+static void hdmi_bridge_enable(struct drm_bridge *bridge)
+{
+}
+
+static void hdmi_bridge_disable(struct drm_bridge *bridge)
+{
+}
+
+static void hdmi_bridge_post_disable(struct drm_bridge *bridge)
+{
+	struct hdmi_bridge *hdmi_bridge = to_hdmi_bridge(bridge);
+	struct hdmi *hdmi = hdmi_bridge->hdmi;
+	struct hdmi_phy *phy = hdmi->phy;
+
+	DBG("power down");
+	hdmi_set_mode(hdmi, false);
+	phy->funcs->powerdown(phy);
+}
+
+static void hdmi_bridge_mode_set(struct drm_bridge *bridge,
+		 struct drm_display_mode *mode,
+		 struct drm_display_mode *adjusted_mode)
+{
+	struct hdmi_bridge *hdmi_bridge = to_hdmi_bridge(bridge);
+	struct hdmi *hdmi = hdmi_bridge->hdmi;
+	int hstart, hend, vstart, vend;
+	uint32_t frame_ctrl;
+
+	mode = adjusted_mode;
+
+	hdmi_bridge->pixclock = mode->clock * 1000;
+
+	hdmi->hdmi_mode = drm_match_cea_mode(mode) > 1;
+
+	hstart = mode->htotal - mode->hsync_start;
+	hend   = mode->htotal - mode->hsync_start + mode->hdisplay;
+
+	vstart = mode->vtotal - mode->vsync_start - 1;
+	vend   = mode->vtotal - mode->vsync_start + mode->vdisplay - 1;
+
+	DBG("htotal=%d, vtotal=%d, hstart=%d, hend=%d, vstart=%d, vend=%d",
+			mode->htotal, mode->vtotal, hstart, hend, vstart, vend);
+
+	hdmi_write(hdmi, REG_HDMI_TOTAL,
+			HDMI_TOTAL_H_TOTAL(mode->htotal - 1) |
+			HDMI_TOTAL_V_TOTAL(mode->vtotal - 1));
+
+	hdmi_write(hdmi, REG_HDMI_ACTIVE_HSYNC,
+			HDMI_ACTIVE_HSYNC_START(hstart) |
+			HDMI_ACTIVE_HSYNC_END(hend));
+	hdmi_write(hdmi, REG_HDMI_ACTIVE_VSYNC,
+			HDMI_ACTIVE_VSYNC_START(vstart) |
+			HDMI_ACTIVE_VSYNC_END(vend));
+
+	if (mode->flags & DRM_MODE_FLAG_INTERLACE) {
+		hdmi_write(hdmi, REG_HDMI_VSYNC_TOTAL_F2,
+				HDMI_VSYNC_TOTAL_F2_V_TOTAL(mode->vtotal));
+		hdmi_write(hdmi, REG_HDMI_VSYNC_ACTIVE_F2,
+				HDMI_VSYNC_ACTIVE_F2_START(vstart + 1) |
+				HDMI_VSYNC_ACTIVE_F2_END(vend + 1));
+	} else {
+		hdmi_write(hdmi, REG_HDMI_VSYNC_TOTAL_F2,
+				HDMI_VSYNC_TOTAL_F2_V_TOTAL(0));
+		hdmi_write(hdmi, REG_HDMI_VSYNC_ACTIVE_F2,
+				HDMI_VSYNC_ACTIVE_F2_START(0) |
+				HDMI_VSYNC_ACTIVE_F2_END(0));
+	}
+
+	frame_ctrl = 0;
+	if (mode->flags & DRM_MODE_FLAG_NHSYNC)
+		frame_ctrl |= HDMI_FRAME_CTRL_HSYNC_LOW;
+	if (mode->flags & DRM_MODE_FLAG_NVSYNC)
+		frame_ctrl |= HDMI_FRAME_CTRL_VSYNC_LOW;
+	if (mode->flags & DRM_MODE_FLAG_INTERLACE)
+		frame_ctrl |= HDMI_FRAME_CTRL_INTERLACED_EN;
+	DBG("frame_ctrl=%08x", frame_ctrl);
+	hdmi_write(hdmi, REG_HDMI_FRAME_CTRL, frame_ctrl);
+
+	// TODO until we have audio, this might be safest:
+	if (hdmi->hdmi_mode)
+		hdmi_write(hdmi, REG_HDMI_GC, HDMI_GC_MUTE);
+}
+
+static const struct drm_bridge_funcs hdmi_bridge_funcs = {
+		.pre_enable = hdmi_bridge_pre_enable,
+		.enable = hdmi_bridge_enable,
+		.disable = hdmi_bridge_disable,
+		.post_disable = hdmi_bridge_post_disable,
+		.mode_set = hdmi_bridge_mode_set,
+		.destroy = hdmi_bridge_destroy,
+};
+
+
+/* initialize bridge */
+struct drm_bridge *hdmi_bridge_init(struct hdmi *hdmi)
+{
+	struct drm_bridge *bridge = NULL;
+	struct hdmi_bridge *hdmi_bridge;
+	int ret;
+
+	hdmi_bridge = kzalloc(sizeof(*hdmi_bridge), GFP_KERNEL);
+	if (!hdmi_bridge) {
+		ret = -ENOMEM;
+		goto fail;
+	}
+
+	hdmi_bridge->hdmi = hdmi_reference(hdmi);
+
+	bridge = &hdmi_bridge->base;
+
+	drm_bridge_init(hdmi->dev, bridge, &hdmi_bridge_funcs);
+
+	return bridge;
+
+fail:
+	if (bridge)
+		hdmi_bridge_destroy(bridge);
+
+	return ERR_PTR(ret);
+}
diff --git a/drivers/gpu/drm/msm/hdmi/hdmi_connector.c b/drivers/gpu/drm/msm/hdmi/hdmi_connector.c
new file mode 100644
index 000000000000..823eee521a31
--- /dev/null
+++ b/drivers/gpu/drm/msm/hdmi/hdmi_connector.c
@@ -0,0 +1,367 @@
+/*
+ * Copyright (C) 2013 Red Hat
+ * Author: Rob Clark <robdclark@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/gpio.h>
+
+#include "hdmi.h"
+
+struct hdmi_connector {
+	struct drm_connector base;
+	struct hdmi *hdmi;
+};
+#define to_hdmi_connector(x) container_of(x, struct hdmi_connector, base)
+
+static int gpio_config(struct hdmi *hdmi, bool on)
+{
+	struct drm_device *dev = hdmi->dev;
+	struct hdmi_platform_config *config =
+			hdmi->pdev->dev.platform_data;
+	int ret;
+
+	if (on) {
+		ret = gpio_request(config->ddc_clk_gpio, "HDMI_DDC_CLK");
+		if (ret) {
+			dev_err(dev->dev, "'%s'(%d) gpio_request failed: %d\n",
+				"HDMI_DDC_CLK", config->ddc_clk_gpio, ret);
+			goto error1;
+		}
+		ret = gpio_request(config->ddc_data_gpio, "HDMI_DDC_DATA");
+		if (ret) {
+			dev_err(dev->dev, "'%s'(%d) gpio_request failed: %d\n",
+				"HDMI_DDC_DATA", config->ddc_data_gpio, ret);
+			goto error2;
+		}
+		ret = gpio_request(config->hpd_gpio, "HDMI_HPD");
+		if (ret) {
+			dev_err(dev->dev, "'%s'(%d) gpio_request failed: %d\n",
+				"HDMI_HPD", config->hpd_gpio, ret);
+			goto error3;
+		}
+		if (config->pmic_gpio != -1) {
+			ret = gpio_request(config->pmic_gpio, "PMIC_HDMI_MUX_SEL");
+			if (ret) {
+				dev_err(dev->dev, "'%s'(%d) gpio_request failed: %d\n",
+					"PMIC_HDMI_MUX_SEL", config->pmic_gpio, ret);
+				goto error4;
+			}
+			gpio_set_value_cansleep(config->pmic_gpio, 0);
+		}
+		DBG("gpio on");
+	} else {
+		gpio_free(config->ddc_clk_gpio);
+		gpio_free(config->ddc_data_gpio);
+		gpio_free(config->hpd_gpio);
+
+		if (config->pmic_gpio != -1) {
+			gpio_set_value_cansleep(config->pmic_gpio, 1);
+			gpio_free(config->pmic_gpio);
+		}
+		DBG("gpio off");
+	}
+
+	return 0;
+
+error4:
+	gpio_free(config->hpd_gpio);
+error3:
+	gpio_free(config->ddc_data_gpio);
+error2:
+	gpio_free(config->ddc_clk_gpio);
+error1:
+	return ret;
+}
+
+static int hpd_enable(struct hdmi_connector *hdmi_connector)
+{
+	struct hdmi *hdmi = hdmi_connector->hdmi;
+	struct drm_device *dev = hdmi_connector->base.dev;
+	struct hdmi_phy *phy = hdmi->phy;
+	uint32_t hpd_ctrl;
+	int ret;
+
+	ret = gpio_config(hdmi, true);
+	if (ret) {
+		dev_err(dev->dev, "failed to configure GPIOs: %d\n", ret);
+		goto fail;
+	}
+
+	ret = clk_prepare_enable(hdmi->clk);
+	if (ret) {
+		dev_err(dev->dev, "failed to enable 'clk': %d\n", ret);
+		goto fail;
+	}
+
+	ret = clk_prepare_enable(hdmi->m_pclk);
+	if (ret) {
+		dev_err(dev->dev, "failed to enable 'm_pclk': %d\n", ret);
+		goto fail;
+	}
+
+	ret = clk_prepare_enable(hdmi->s_pclk);
+	if (ret) {
+		dev_err(dev->dev, "failed to enable 's_pclk': %d\n", ret);
+		goto fail;
+	}
+
+	if (hdmi->mpp0)
+		ret = regulator_enable(hdmi->mpp0);
+	if (!ret)
+		ret = regulator_enable(hdmi->mvs);
+	if (ret) {
+		dev_err(dev->dev, "failed to enable regulators: %d\n", ret);
+		goto fail;
+	}
+
+	hdmi_set_mode(hdmi, false);
+	phy->funcs->reset(phy);
+	hdmi_set_mode(hdmi, true);
+
+	hdmi_write(hdmi, REG_HDMI_USEC_REFTIMER, 0x0001001b);
+
+	/* enable HPD events: */
+	hdmi_write(hdmi, REG_HDMI_HPD_INT_CTRL,
+			HDMI_HPD_INT_CTRL_INT_CONNECT |
+			HDMI_HPD_INT_CTRL_INT_EN);
+
+	/* set timeout to 4.1ms (max) for hardware debounce */
+	hpd_ctrl = hdmi_read(hdmi, REG_HDMI_HPD_CTRL);
+	hpd_ctrl |= HDMI_HPD_CTRL_TIMEOUT(0x1fff);
+
+	/* Toggle HPD circuit to trigger HPD sense */
+	hdmi_write(hdmi, REG_HDMI_HPD_CTRL,
+			~HDMI_HPD_CTRL_ENABLE & hpd_ctrl);
+	hdmi_write(hdmi, REG_HDMI_HPD_CTRL,
+			HDMI_HPD_CTRL_ENABLE | hpd_ctrl);
+
+	return 0;
+
+fail:
+	return ret;
+}
+
+static int hdp_disable(struct hdmi_connector *hdmi_connector)
+{
+	struct hdmi *hdmi = hdmi_connector->hdmi;
+	struct drm_device *dev = hdmi_connector->base.dev;
+	int ret = 0;
+
+	/* Disable HPD interrupt */
+	hdmi_write(hdmi, REG_HDMI_HPD_INT_CTRL, 0);
+
+	hdmi_set_mode(hdmi, false);
+
+	if (hdmi->mpp0)
+		ret = regulator_disable(hdmi->mpp0);
+	if (!ret)
+		ret = regulator_disable(hdmi->mvs);
+	if (ret) {
+		dev_err(dev->dev, "failed to enable regulators: %d\n", ret);
+		goto fail;
+	}
+
+	clk_disable_unprepare(hdmi->clk);
+	clk_disable_unprepare(hdmi->m_pclk);
+	clk_disable_unprepare(hdmi->s_pclk);
+
+	ret = gpio_config(hdmi, false);
+	if (ret) {
+		dev_err(dev->dev, "failed to unconfigure GPIOs: %d\n", ret);
+		goto fail;
+	}
+
+	return 0;
+
+fail:
+	return ret;
+}
+
+void hdmi_connector_irq(struct drm_connector *connector)
+{
+	struct hdmi_connector *hdmi_connector = to_hdmi_connector(connector);
+	struct hdmi *hdmi = hdmi_connector->hdmi;
+	uint32_t hpd_int_status, hpd_int_ctrl;
+
+	/* Process HPD: */
+	hpd_int_status = hdmi_read(hdmi, REG_HDMI_HPD_INT_STATUS);
+	hpd_int_ctrl   = hdmi_read(hdmi, REG_HDMI_HPD_INT_CTRL);
+
+	if ((hpd_int_ctrl & HDMI_HPD_INT_CTRL_INT_EN) &&
+			(hpd_int_status & HDMI_HPD_INT_STATUS_INT)) {
+		bool detected = !!(hpd_int_status & HDMI_HPD_INT_STATUS_CABLE_DETECTED);
+
+		DBG("status=%04x, ctrl=%04x", hpd_int_status, hpd_int_ctrl);
+
+		/* ack the irq: */
+		hdmi_write(hdmi, REG_HDMI_HPD_INT_CTRL,
+				hpd_int_ctrl | HDMI_HPD_INT_CTRL_INT_ACK);
+
+		drm_helper_hpd_irq_event(connector->dev);
+
+		/* detect disconnect if we are connected or visa versa: */
+		hpd_int_ctrl = HDMI_HPD_INT_CTRL_INT_EN;
+		if (!detected)
+			hpd_int_ctrl |= HDMI_HPD_INT_CTRL_INT_CONNECT;
+		hdmi_write(hdmi, REG_HDMI_HPD_INT_CTRL, hpd_int_ctrl);
+	}
+}
+
+static enum drm_connector_status hdmi_connector_detect(
+		struct drm_connector *connector, bool force)
+{
+	struct hdmi_connector *hdmi_connector = to_hdmi_connector(connector);
+	struct hdmi *hdmi = hdmi_connector->hdmi;
+	uint32_t hpd_int_status;
+	int retry = 20;
+
+	hpd_int_status = hdmi_read(hdmi, REG_HDMI_HPD_INT_STATUS);
+
+	/* sense seems to in some cases be momentarily de-asserted, don't
+	 * let that trick us into thinking the monitor is gone:
+	 */
+	while (retry-- && !(hpd_int_status & HDMI_HPD_INT_STATUS_CABLE_DETECTED)) {
+		mdelay(10);
+		hpd_int_status = hdmi_read(hdmi, REG_HDMI_HPD_INT_STATUS);
+		DBG("status=%08x", hpd_int_status);
+	}
+
+	return (hpd_int_status & HDMI_HPD_INT_STATUS_CABLE_DETECTED) ?
+			connector_status_connected : connector_status_disconnected;
+}
+
+static void hdmi_connector_destroy(struct drm_connector *connector)
+{
+	struct hdmi_connector *hdmi_connector = to_hdmi_connector(connector);
+
+	hdp_disable(hdmi_connector);
+
+	drm_sysfs_connector_remove(connector);
+	drm_connector_cleanup(connector);
+
+	hdmi_unreference(hdmi_connector->hdmi);
+
+	kfree(hdmi_connector);
+}
+
+static int hdmi_connector_get_modes(struct drm_connector *connector)
+{
+	struct hdmi_connector *hdmi_connector = to_hdmi_connector(connector);
+	struct hdmi *hdmi = hdmi_connector->hdmi;
+	struct edid *edid;
+	uint32_t hdmi_ctrl;
+	int ret = 0;
+
+	hdmi_ctrl = hdmi_read(hdmi, REG_HDMI_CTRL);
+	hdmi_write(hdmi, REG_HDMI_CTRL, hdmi_ctrl | HDMI_CTRL_ENABLE);
+
+	edid = drm_get_edid(connector, hdmi->i2c);
+
+	hdmi_write(hdmi, REG_HDMI_CTRL, hdmi_ctrl);
+
+	drm_mode_connector_update_edid_property(connector, edid);
+
+	if (edid) {
+		ret = drm_add_edid_modes(connector, edid);
+		kfree(edid);
+	}
+
+	return ret;
+}
+
+static int hdmi_connector_mode_valid(struct drm_connector *connector,
+				 struct drm_display_mode *mode)
+{
+	struct hdmi_connector *hdmi_connector = to_hdmi_connector(connector);
+	struct msm_drm_private *priv = connector->dev->dev_private;
+	struct msm_kms *kms = priv->kms;
+	long actual, requested;
+
+	requested = 1000 * mode->clock;
+	actual = kms->funcs->round_pixclk(kms,
+			requested, hdmi_connector->hdmi->encoder);
+
+	DBG("requested=%ld, actual=%ld", requested, actual);
+
+	if (actual != requested)
+		return MODE_CLOCK_RANGE;
+
+	return 0;
+}
+
+static struct drm_encoder *
+hdmi_connector_best_encoder(struct drm_connector *connector)
+{
+	struct hdmi_connector *hdmi_connector = to_hdmi_connector(connector);
+	return hdmi_connector->hdmi->encoder;
+}
+
+static const struct drm_connector_funcs hdmi_connector_funcs = {
+	.dpms = drm_helper_connector_dpms,
+	.detect = hdmi_connector_detect,
+	.fill_modes = drm_helper_probe_single_connector_modes,
+	.destroy = hdmi_connector_destroy,
+};
+
+static const struct drm_connector_helper_funcs hdmi_connector_helper_funcs = {
+	.get_modes = hdmi_connector_get_modes,
+	.mode_valid = hdmi_connector_mode_valid,
+	.best_encoder = hdmi_connector_best_encoder,
+};
+
+/* initialize connector */
+struct drm_connector *hdmi_connector_init(struct hdmi *hdmi)
+{
+	struct drm_connector *connector = NULL;
+	struct hdmi_connector *hdmi_connector;
+	int ret;
+
+	hdmi_connector = kzalloc(sizeof(*hdmi_connector), GFP_KERNEL);
+	if (!hdmi_connector) {
+		ret = -ENOMEM;
+		goto fail;
+	}
+
+	hdmi_connector->hdmi = hdmi_reference(hdmi);
+
+	connector = &hdmi_connector->base;
+
+	drm_connector_init(hdmi->dev, connector, &hdmi_connector_funcs,
+			DRM_MODE_CONNECTOR_HDMIA);
+	drm_connector_helper_add(connector, &hdmi_connector_helper_funcs);
+
+	connector->polled = DRM_CONNECTOR_POLL_HPD;
+
+	connector->interlace_allowed = 1;
+	connector->doublescan_allowed = 0;
+
+	drm_sysfs_connector_add(connector);
+
+	ret = hpd_enable(hdmi_connector);
+	if (ret) {
+		dev_err(hdmi->dev->dev, "failed to enable HPD: %d\n", ret);
+		goto fail;
+	}
+
+	drm_mode_connector_attach_encoder(connector, hdmi->encoder);
+
+	return connector;
+
+fail:
+	if (connector)
+		hdmi_connector_destroy(connector);
+
+	return ERR_PTR(ret);
+}
diff --git a/drivers/gpu/drm/msm/hdmi/hdmi_i2c.c b/drivers/gpu/drm/msm/hdmi/hdmi_i2c.c
new file mode 100644
index 000000000000..f4ab7f70fed1
--- /dev/null
+++ b/drivers/gpu/drm/msm/hdmi/hdmi_i2c.c
@@ -0,0 +1,281 @@
+/*
+ * Copyright (C) 2013 Red Hat
+ * Author: Rob Clark <robdclark@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include "hdmi.h"
+
+struct hdmi_i2c_adapter {
+	struct i2c_adapter base;
+	struct hdmi *hdmi;
+	bool sw_done;
+	wait_queue_head_t ddc_event;
+};
+#define to_hdmi_i2c_adapter(x) container_of(x, struct hdmi_i2c_adapter, base)
+
+static void init_ddc(struct hdmi_i2c_adapter *hdmi_i2c)
+{
+	struct hdmi *hdmi = hdmi_i2c->hdmi;
+
+	hdmi_write(hdmi, REG_HDMI_DDC_CTRL,
+			HDMI_DDC_CTRL_SW_STATUS_RESET);
+	hdmi_write(hdmi, REG_HDMI_DDC_CTRL,
+			HDMI_DDC_CTRL_SOFT_RESET);
+
+	hdmi_write(hdmi, REG_HDMI_DDC_SPEED,
+			HDMI_DDC_SPEED_THRESHOLD(2) |
+			HDMI_DDC_SPEED_PRESCALE(10));
+
+	hdmi_write(hdmi, REG_HDMI_DDC_SETUP,
+			HDMI_DDC_SETUP_TIMEOUT(0xff));
+
+	/* enable reference timer for 27us */
+	hdmi_write(hdmi, REG_HDMI_DDC_REF,
+			HDMI_DDC_REF_REFTIMER_ENABLE |
+			HDMI_DDC_REF_REFTIMER(27));
+}
+
+static int ddc_clear_irq(struct hdmi_i2c_adapter *hdmi_i2c)
+{
+	struct hdmi *hdmi = hdmi_i2c->hdmi;
+	struct drm_device *dev = hdmi->dev;
+	uint32_t retry = 0xffff;
+	uint32_t ddc_int_ctrl;
+
+	do {
+		--retry;
+
+		hdmi_write(hdmi, REG_HDMI_DDC_INT_CTRL,
+				HDMI_DDC_INT_CTRL_SW_DONE_ACK |
+				HDMI_DDC_INT_CTRL_SW_DONE_MASK);
+
+		ddc_int_ctrl = hdmi_read(hdmi, REG_HDMI_DDC_INT_CTRL);
+
+	} while ((ddc_int_ctrl & HDMI_DDC_INT_CTRL_SW_DONE_INT) && retry);
+
+	if (!retry) {
+		dev_err(dev->dev, "timeout waiting for DDC\n");
+		return -ETIMEDOUT;
+	}
+
+	hdmi_i2c->sw_done = false;
+
+	return 0;
+}
+
+#define MAX_TRANSACTIONS 4
+
+static bool sw_done(struct hdmi_i2c_adapter *hdmi_i2c)
+{
+	struct hdmi *hdmi = hdmi_i2c->hdmi;
+
+	if (!hdmi_i2c->sw_done) {
+		uint32_t ddc_int_ctrl;
+
+		ddc_int_ctrl = hdmi_read(hdmi, REG_HDMI_DDC_INT_CTRL);
+
+		if ((ddc_int_ctrl & HDMI_DDC_INT_CTRL_SW_DONE_MASK) &&
+				(ddc_int_ctrl & HDMI_DDC_INT_CTRL_SW_DONE_INT)) {
+			hdmi_i2c->sw_done = true;
+			hdmi_write(hdmi, REG_HDMI_DDC_INT_CTRL,
+					HDMI_DDC_INT_CTRL_SW_DONE_ACK);
+		}
+	}
+
+	return hdmi_i2c->sw_done;
+}
+
+static int hdmi_i2c_xfer(struct i2c_adapter *i2c,
+		struct i2c_msg *msgs, int num)
+{
+	struct hdmi_i2c_adapter *hdmi_i2c = to_hdmi_i2c_adapter(i2c);
+	struct hdmi *hdmi = hdmi_i2c->hdmi;
+	struct drm_device *dev = hdmi->dev;
+	static const uint32_t nack[] = {
+			HDMI_DDC_SW_STATUS_NACK0, HDMI_DDC_SW_STATUS_NACK1,
+			HDMI_DDC_SW_STATUS_NACK2, HDMI_DDC_SW_STATUS_NACK3,
+	};
+	int indices[MAX_TRANSACTIONS];
+	int ret, i, j, index = 0;
+	uint32_t ddc_status, ddc_data, i2c_trans;
+
+	num = min(num, MAX_TRANSACTIONS);
+
+	WARN_ON(!(hdmi_read(hdmi, REG_HDMI_CTRL) & HDMI_CTRL_ENABLE));
+
+	if (num == 0)
+		return num;
+
+	init_ddc(hdmi_i2c);
+
+	ret = ddc_clear_irq(hdmi_i2c);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < num; i++) {
+		struct i2c_msg *p = &msgs[i];
+		uint32_t raw_addr = p->addr << 1;
+
+		if (p->flags & I2C_M_RD)
+			raw_addr |= 1;
+
+		ddc_data = HDMI_DDC_DATA_DATA(raw_addr) |
+				HDMI_DDC_DATA_DATA_RW(DDC_WRITE);
+
+		if (i == 0) {
+			ddc_data |= HDMI_DDC_DATA_INDEX(0) |
+					HDMI_DDC_DATA_INDEX_WRITE;
+		}
+
+		hdmi_write(hdmi, REG_HDMI_DDC_DATA, ddc_data);
+		index++;
+
+		indices[i] = index;
+
+		if (p->flags & I2C_M_RD) {
+			index += p->len;
+		} else {
+			for (j = 0; j < p->len; j++) {
+				ddc_data = HDMI_DDC_DATA_DATA(p->buf[j]) |
+						HDMI_DDC_DATA_DATA_RW(DDC_WRITE);
+				hdmi_write(hdmi, REG_HDMI_DDC_DATA, ddc_data);
+				index++;
+			}
+		}
+
+		i2c_trans = HDMI_I2C_TRANSACTION_REG_CNT(p->len) |
+				HDMI_I2C_TRANSACTION_REG_RW(
+						(p->flags & I2C_M_RD) ? DDC_READ : DDC_WRITE) |
+				HDMI_I2C_TRANSACTION_REG_START;
+
+		if (i == (num - 1))
+			i2c_trans |= HDMI_I2C_TRANSACTION_REG_STOP;
+
+		hdmi_write(hdmi, REG_HDMI_I2C_TRANSACTION(i), i2c_trans);
+	}
+
+	/* trigger the transfer: */
+	hdmi_write(hdmi, REG_HDMI_DDC_CTRL,
+			HDMI_DDC_CTRL_TRANSACTION_CNT(num - 1) |
+			HDMI_DDC_CTRL_GO);
+
+	ret = wait_event_timeout(hdmi_i2c->ddc_event, sw_done(hdmi_i2c), HZ/4);
+	if (ret <= 0) {
+		if (ret == 0)
+			ret = -ETIMEDOUT;
+		dev_warn(dev->dev, "DDC timeout: %d\n", ret);
+		DBG("sw_status=%08x, hw_status=%08x, int_ctrl=%08x",
+				hdmi_read(hdmi, REG_HDMI_DDC_SW_STATUS),
+				hdmi_read(hdmi, REG_HDMI_DDC_HW_STATUS),
+				hdmi_read(hdmi, REG_HDMI_DDC_INT_CTRL));
+		return ret;
+	}
+
+	ddc_status = hdmi_read(hdmi, REG_HDMI_DDC_SW_STATUS);
+
+	/* read back results of any read transactions: */
+	for (i = 0; i < num; i++) {
+		struct i2c_msg *p = &msgs[i];
+
+		if (!(p->flags & I2C_M_RD))
+			continue;
+
+		/* check for NACK: */
+		if (ddc_status & nack[i]) {
+			DBG("ddc_status=%08x", ddc_status);
+			break;
+		}
+
+		ddc_data = HDMI_DDC_DATA_DATA_RW(DDC_READ) |
+				HDMI_DDC_DATA_INDEX(indices[i]) |
+				HDMI_DDC_DATA_INDEX_WRITE;
+
+		hdmi_write(hdmi, REG_HDMI_DDC_DATA, ddc_data);
+
+		/* discard first byte: */
+		hdmi_read(hdmi, REG_HDMI_DDC_DATA);
+
+		for (j = 0; j < p->len; j++) {
+			ddc_data = hdmi_read(hdmi, REG_HDMI_DDC_DATA);
+			p->buf[j] = FIELD(ddc_data, HDMI_DDC_DATA_DATA);
+		}
+	}
+
+	return i;
+}
+
+static u32 hdmi_i2c_func(struct i2c_adapter *adapter)
+{
+	return I2C_FUNC_I2C | I2C_FUNC_SMBUS_EMUL;
+}
+
+static const struct i2c_algorithm hdmi_i2c_algorithm = {
+	.master_xfer	= hdmi_i2c_xfer,
+	.functionality	= hdmi_i2c_func,
+};
+
+void hdmi_i2c_irq(struct i2c_adapter *i2c)
+{
+	struct hdmi_i2c_adapter *hdmi_i2c = to_hdmi_i2c_adapter(i2c);
+
+	if (sw_done(hdmi_i2c))
+		wake_up_all(&hdmi_i2c->ddc_event);
+}
+
+void hdmi_i2c_destroy(struct i2c_adapter *i2c)
+{
+	struct hdmi_i2c_adapter *hdmi_i2c = to_hdmi_i2c_adapter(i2c);
+	i2c_del_adapter(i2c);
+	kfree(hdmi_i2c);
+}
+
+struct i2c_adapter *hdmi_i2c_init(struct hdmi *hdmi)
+{
+	struct drm_device *dev = hdmi->dev;
+	struct hdmi_i2c_adapter *hdmi_i2c;
+	struct i2c_adapter *i2c = NULL;
+	int ret;
+
+	hdmi_i2c = kzalloc(sizeof(*hdmi_i2c), GFP_KERNEL);
+	if (!hdmi_i2c) {
+		ret = -ENOMEM;
+		goto fail;
+	}
+
+	i2c = &hdmi_i2c->base;
+
+	hdmi_i2c->hdmi = hdmi;
+	init_waitqueue_head(&hdmi_i2c->ddc_event);
+
+
+	i2c->owner = THIS_MODULE;
+	i2c->class = I2C_CLASS_DDC;
+	snprintf(i2c->name, sizeof(i2c->name), "msm hdmi i2c");
+	i2c->dev.parent = &hdmi->pdev->dev;
+	i2c->algo = &hdmi_i2c_algorithm;
+
+	ret = i2c_add_adapter(i2c);
+	if (ret) {
+		dev_err(dev->dev, "failed to register hdmi i2c: %d\n", ret);
+		goto fail;
+	}
+
+	return i2c;
+
+fail:
+	if (i2c)
+		hdmi_i2c_destroy(i2c);
+	return ERR_PTR(ret);
+}
diff --git a/drivers/gpu/drm/msm/hdmi/hdmi_phy_8960.c b/drivers/gpu/drm/msm/hdmi/hdmi_phy_8960.c
new file mode 100644
index 000000000000..e5b7ed5b8f01
--- /dev/null
+++ b/drivers/gpu/drm/msm/hdmi/hdmi_phy_8960.c
@@ -0,0 +1,141 @@
+/*
+ * Copyright (C) 2013 Red Hat
+ * Author: Rob Clark <robdclark@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include "hdmi.h"
+
+struct hdmi_phy_8960 {
+	struct hdmi_phy base;
+	struct hdmi *hdmi;
+};
+#define to_hdmi_phy_8960(x) container_of(x, struct hdmi_phy_8960, base)
+
+static void hdmi_phy_8960_destroy(struct hdmi_phy *phy)
+{
+	struct hdmi_phy_8960 *phy_8960 = to_hdmi_phy_8960(phy);
+	kfree(phy_8960);
+}
+
+static void hdmi_phy_8960_reset(struct hdmi_phy *phy)
+{
+	struct hdmi_phy_8960 *phy_8960 = to_hdmi_phy_8960(phy);
+	struct hdmi *hdmi = phy_8960->hdmi;
+	unsigned int val;
+
+	val = hdmi_read(hdmi, REG_HDMI_PHY_CTRL);
+
+	if (val & HDMI_PHY_CTRL_SW_RESET_LOW) {
+		/* pull low */
+		hdmi_write(hdmi, REG_HDMI_PHY_CTRL,
+				val & ~HDMI_PHY_CTRL_SW_RESET);
+	} else {
+		/* pull high */
+		hdmi_write(hdmi, REG_HDMI_PHY_CTRL,
+				val | HDMI_PHY_CTRL_SW_RESET);
+	}
+
+	if (val & HDMI_PHY_CTRL_SW_RESET_PLL_LOW) {
+		/* pull low */
+		hdmi_write(hdmi, REG_HDMI_PHY_CTRL,
+				val & ~HDMI_PHY_CTRL_SW_RESET_PLL);
+	} else {
+		/* pull high */
+		hdmi_write(hdmi, REG_HDMI_PHY_CTRL,
+				val | HDMI_PHY_CTRL_SW_RESET_PLL);
+	}
+
+	msleep(100);
+
+	if (val & HDMI_PHY_CTRL_SW_RESET_LOW) {
+		/* pull high */
+		hdmi_write(hdmi, REG_HDMI_PHY_CTRL,
+				val | HDMI_PHY_CTRL_SW_RESET);
+	} else {
+		/* pull low */
+		hdmi_write(hdmi, REG_HDMI_PHY_CTRL,
+				val & ~HDMI_PHY_CTRL_SW_RESET);
+	}
+
+	if (val & HDMI_PHY_CTRL_SW_RESET_PLL_LOW) {
+		/* pull high */
+		hdmi_write(hdmi, REG_HDMI_PHY_CTRL,
+				val | HDMI_PHY_CTRL_SW_RESET_PLL);
+	} else {
+		/* pull low */
+		hdmi_write(hdmi, REG_HDMI_PHY_CTRL,
+				val & ~HDMI_PHY_CTRL_SW_RESET_PLL);
+	}
+}
+
+static void hdmi_phy_8960_powerup(struct hdmi_phy *phy,
+		unsigned long int pixclock)
+{
+	struct hdmi_phy_8960 *phy_8960 = to_hdmi_phy_8960(phy);
+	struct hdmi *hdmi = phy_8960->hdmi;
+
+	hdmi_write(hdmi, REG_HDMI_8960_PHY_REG0, 0x1b);
+	hdmi_write(hdmi, REG_HDMI_8960_PHY_REG1, 0xf2);
+	hdmi_write(hdmi, REG_HDMI_8960_PHY_REG4, 0x00);
+	hdmi_write(hdmi, REG_HDMI_8960_PHY_REG5, 0x00);
+	hdmi_write(hdmi, REG_HDMI_8960_PHY_REG6, 0x00);
+	hdmi_write(hdmi, REG_HDMI_8960_PHY_REG7, 0x00);
+	hdmi_write(hdmi, REG_HDMI_8960_PHY_REG8, 0x00);
+	hdmi_write(hdmi, REG_HDMI_8960_PHY_REG9, 0x00);
+	hdmi_write(hdmi, REG_HDMI_8960_PHY_REG10, 0x00);
+	hdmi_write(hdmi, REG_HDMI_8960_PHY_REG11, 0x00);
+	hdmi_write(hdmi, REG_HDMI_8960_PHY_REG3, 0x20);
+}
+
+static void hdmi_phy_8960_powerdown(struct hdmi_phy *phy)
+{
+	struct hdmi_phy_8960 *phy_8960 = to_hdmi_phy_8960(phy);
+	struct hdmi *hdmi = phy_8960->hdmi;
+
+	hdmi_write(hdmi, REG_HDMI_8960_PHY_REG2, 0x7f);
+}
+
+static const struct hdmi_phy_funcs hdmi_phy_8960_funcs = {
+		.destroy = hdmi_phy_8960_destroy,
+		.reset = hdmi_phy_8960_reset,
+		.powerup = hdmi_phy_8960_powerup,
+		.powerdown = hdmi_phy_8960_powerdown,
+};
+
+struct hdmi_phy *hdmi_phy_8960_init(struct hdmi *hdmi)
+{
+	struct hdmi_phy_8960 *phy_8960;
+	struct hdmi_phy *phy = NULL;
+	int ret;
+
+	phy_8960 = kzalloc(sizeof(*phy_8960), GFP_KERNEL);
+	if (!phy_8960) {
+		ret = -ENOMEM;
+		goto fail;
+	}
+
+	phy = &phy_8960->base;
+
+	phy->funcs = &hdmi_phy_8960_funcs;
+
+	phy_8960->hdmi = hdmi;
+
+	return phy;
+
+fail:
+	if (phy)
+		hdmi_phy_8960_destroy(phy);
+	return ERR_PTR(ret);
+}
diff --git a/drivers/gpu/drm/msm/hdmi/hdmi_phy_8x60.c b/drivers/gpu/drm/msm/hdmi/hdmi_phy_8x60.c
new file mode 100644
index 000000000000..391433c1af7c
--- /dev/null
+++ b/drivers/gpu/drm/msm/hdmi/hdmi_phy_8x60.c
@@ -0,0 +1,214 @@
+/*
+ * Copyright (C) 2013 Red Hat
+ * Author: Rob Clark <robdclark@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include "hdmi.h"
+
+struct hdmi_phy_8x60 {
+	struct hdmi_phy base;
+	struct hdmi *hdmi;
+};
+#define to_hdmi_phy_8x60(x) container_of(x, struct hdmi_phy_8x60, base)
+
+static void hdmi_phy_8x60_destroy(struct hdmi_phy *phy)
+{
+	struct hdmi_phy_8x60 *phy_8x60 = to_hdmi_phy_8x60(phy);
+	kfree(phy_8x60);
+}
+
+static void hdmi_phy_8x60_reset(struct hdmi_phy *phy)
+{
+	struct hdmi_phy_8x60 *phy_8x60 = to_hdmi_phy_8x60(phy);
+	struct hdmi *hdmi = phy_8x60->hdmi;
+	unsigned int val;
+
+	val = hdmi_read(hdmi, REG_HDMI_PHY_CTRL);
+
+	if (val & HDMI_PHY_CTRL_SW_RESET_LOW) {
+		/* pull low */
+		hdmi_write(hdmi, REG_HDMI_PHY_CTRL,
+				val & ~HDMI_PHY_CTRL_SW_RESET);
+	} else {
+		/* pull high */
+		hdmi_write(hdmi, REG_HDMI_PHY_CTRL,
+				val | HDMI_PHY_CTRL_SW_RESET);
+	}
+
+	msleep(100);
+
+	if (val & HDMI_PHY_CTRL_SW_RESET_LOW) {
+		/* pull high */
+		hdmi_write(hdmi, REG_HDMI_PHY_CTRL,
+				val | HDMI_PHY_CTRL_SW_RESET);
+	} else {
+		/* pull low */
+		hdmi_write(hdmi, REG_HDMI_PHY_CTRL,
+				val & ~HDMI_PHY_CTRL_SW_RESET);
+	}
+}
+
+static void hdmi_phy_8x60_powerup(struct hdmi_phy *phy,
+		unsigned long int pixclock)
+{
+	struct hdmi_phy_8x60 *phy_8x60 = to_hdmi_phy_8x60(phy);
+	struct hdmi *hdmi = phy_8x60->hdmi;
+
+	/* De-serializer delay D/C for non-lbk mode: */
+	hdmi_write(hdmi, REG_HDMI_8x60_PHY_REG0,
+			HDMI_8x60_PHY_REG0_DESER_DEL_CTRL(3));
+
+	if (pixclock == 27000000) {
+		/* video_format == HDMI_VFRMT_720x480p60_16_9 */
+		hdmi_write(hdmi, REG_HDMI_8x60_PHY_REG1,
+				HDMI_8x60_PHY_REG1_DTEST_MUX_SEL(5) |
+				HDMI_8x60_PHY_REG1_OUTVOL_SWING_CTRL(3));
+	} else {
+		hdmi_write(hdmi, REG_HDMI_8x60_PHY_REG1,
+				HDMI_8x60_PHY_REG1_DTEST_MUX_SEL(5) |
+				HDMI_8x60_PHY_REG1_OUTVOL_SWING_CTRL(4));
+	}
+
+	/* No matter what, start from the power down mode: */
+	hdmi_write(hdmi, REG_HDMI_8x60_PHY_REG2,
+			HDMI_8x60_PHY_REG2_PD_PWRGEN |
+			HDMI_8x60_PHY_REG2_PD_PLL |
+			HDMI_8x60_PHY_REG2_PD_DRIVE_4 |
+			HDMI_8x60_PHY_REG2_PD_DRIVE_3 |
+			HDMI_8x60_PHY_REG2_PD_DRIVE_2 |
+			HDMI_8x60_PHY_REG2_PD_DRIVE_1 |
+			HDMI_8x60_PHY_REG2_PD_DESER);
+
+	/* Turn PowerGen on: */
+	hdmi_write(hdmi, REG_HDMI_8x60_PHY_REG2,
+			HDMI_8x60_PHY_REG2_PD_PLL |
+			HDMI_8x60_PHY_REG2_PD_DRIVE_4 |
+			HDMI_8x60_PHY_REG2_PD_DRIVE_3 |
+			HDMI_8x60_PHY_REG2_PD_DRIVE_2 |
+			HDMI_8x60_PHY_REG2_PD_DRIVE_1 |
+			HDMI_8x60_PHY_REG2_PD_DESER);
+
+	/* Turn PLL power on: */
+	hdmi_write(hdmi, REG_HDMI_8x60_PHY_REG2,
+			HDMI_8x60_PHY_REG2_PD_DRIVE_4 |
+			HDMI_8x60_PHY_REG2_PD_DRIVE_3 |
+			HDMI_8x60_PHY_REG2_PD_DRIVE_2 |
+			HDMI_8x60_PHY_REG2_PD_DRIVE_1 |
+			HDMI_8x60_PHY_REG2_PD_DESER);
+
+	/* Write to HIGH after PLL power down de-assert: */
+	hdmi_write(hdmi, REG_HDMI_8x60_PHY_REG3,
+			HDMI_8x60_PHY_REG3_PLL_ENABLE);
+
+	/* ASIC power on; PHY REG9 = 0 */
+	hdmi_write(hdmi, REG_HDMI_8x60_PHY_REG9, 0);
+
+	/* Enable PLL lock detect, PLL lock det will go high after lock
+	 * Enable the re-time logic
+	 */
+	hdmi_write(hdmi, REG_HDMI_8x60_PHY_REG12,
+			HDMI_8x60_PHY_REG12_RETIMING_EN |
+			HDMI_8x60_PHY_REG12_PLL_LOCK_DETECT_EN);
+
+	/* Drivers are on: */
+	hdmi_write(hdmi, REG_HDMI_8x60_PHY_REG2,
+			HDMI_8x60_PHY_REG2_PD_DESER);
+
+	/* If the RX detector is needed: */
+	hdmi_write(hdmi, REG_HDMI_8x60_PHY_REG2,
+			HDMI_8x60_PHY_REG2_RCV_SENSE_EN |
+			HDMI_8x60_PHY_REG2_PD_DESER);
+
+	hdmi_write(hdmi, REG_HDMI_8x60_PHY_REG4, 0);
+	hdmi_write(hdmi, REG_HDMI_8x60_PHY_REG5, 0);
+	hdmi_write(hdmi, REG_HDMI_8x60_PHY_REG6, 0);
+	hdmi_write(hdmi, REG_HDMI_8x60_PHY_REG7, 0);
+	hdmi_write(hdmi, REG_HDMI_8x60_PHY_REG8, 0);
+	hdmi_write(hdmi, REG_HDMI_8x60_PHY_REG9, 0);
+	hdmi_write(hdmi, REG_HDMI_8x60_PHY_REG10, 0);
+	hdmi_write(hdmi, REG_HDMI_8x60_PHY_REG11, 0);
+
+	/* If we want to use lock enable based on counting: */
+	hdmi_write(hdmi, REG_HDMI_8x60_PHY_REG12,
+			HDMI_8x60_PHY_REG12_RETIMING_EN |
+			HDMI_8x60_PHY_REG12_PLL_LOCK_DETECT_EN |
+			HDMI_8x60_PHY_REG12_FORCE_LOCK);
+}
+
+static void hdmi_phy_8x60_powerdown(struct hdmi_phy *phy)
+{
+	struct hdmi_phy_8x60 *phy_8x60 = to_hdmi_phy_8x60(phy);
+	struct hdmi *hdmi = phy_8x60->hdmi;
+
+	/* Assert RESET PHY from controller */
+	hdmi_write(hdmi, REG_HDMI_PHY_CTRL,
+			HDMI_PHY_CTRL_SW_RESET);
+	udelay(10);
+	/* De-assert RESET PHY from controller */
+	hdmi_write(hdmi, REG_HDMI_PHY_CTRL, 0);
+	/* Turn off Driver */
+	hdmi_write(hdmi, REG_HDMI_8x60_PHY_REG2,
+			HDMI_8x60_PHY_REG2_PD_DRIVE_4 |
+			HDMI_8x60_PHY_REG2_PD_DRIVE_3 |
+			HDMI_8x60_PHY_REG2_PD_DRIVE_2 |
+			HDMI_8x60_PHY_REG2_PD_DRIVE_1 |
+			HDMI_8x60_PHY_REG2_PD_DESER);
+	udelay(10);
+	/* Disable PLL */
+	hdmi_write(hdmi, REG_HDMI_8x60_PHY_REG3, 0);
+	/* Power down PHY, but keep RX-sense: */
+	hdmi_write(hdmi, REG_HDMI_8x60_PHY_REG2,
+			HDMI_8x60_PHY_REG2_RCV_SENSE_EN |
+			HDMI_8x60_PHY_REG2_PD_PWRGEN |
+			HDMI_8x60_PHY_REG2_PD_PLL |
+			HDMI_8x60_PHY_REG2_PD_DRIVE_4 |
+			HDMI_8x60_PHY_REG2_PD_DRIVE_3 |
+			HDMI_8x60_PHY_REG2_PD_DRIVE_2 |
+			HDMI_8x60_PHY_REG2_PD_DRIVE_1 |
+			HDMI_8x60_PHY_REG2_PD_DESER);
+}
+
+static const struct hdmi_phy_funcs hdmi_phy_8x60_funcs = {
+		.destroy = hdmi_phy_8x60_destroy,
+		.reset = hdmi_phy_8x60_reset,
+		.powerup = hdmi_phy_8x60_powerup,
+		.powerdown = hdmi_phy_8x60_powerdown,
+};
+
+struct hdmi_phy *hdmi_phy_8x60_init(struct hdmi *hdmi)
+{
+	struct hdmi_phy_8x60 *phy_8x60;
+	struct hdmi_phy *phy = NULL;
+	int ret;
+
+	phy_8x60 = kzalloc(sizeof(*phy_8x60), GFP_KERNEL);
+	if (!phy_8x60) {
+		ret = -ENOMEM;
+		goto fail;
+	}
+
+	phy = &phy_8x60->base;
+
+	phy->funcs = &hdmi_phy_8x60_funcs;
+
+	phy_8x60->hdmi = hdmi;
+
+	return phy;
+
+fail:
+	if (phy)
+		hdmi_phy_8x60_destroy(phy);
+	return ERR_PTR(ret);
+}
diff --git a/drivers/gpu/drm/msm/hdmi/qfprom.xml.h b/drivers/gpu/drm/msm/hdmi/qfprom.xml.h
new file mode 100644
index 000000000000..bee36363bcd0
--- /dev/null
+++ b/drivers/gpu/drm/msm/hdmi/qfprom.xml.h
@@ -0,0 +1,50 @@
+#ifndef QFPROM_XML
+#define QFPROM_XML
+
+/* Autogenerated file, DO NOT EDIT manually!
+
+This file was generated by the rules-ng-ng headergen tool in this git repository:
+http://0x04.net/cgit/index.cgi/rules-ng-ng
+git clone git://0x04.net/rules-ng-ng
+
+The rules-ng-ng source files this header was generated from are:
+- /home/robclark/src/freedreno/envytools/rnndb/msm.xml                 (    595 bytes, from 2013-07-05 19:21:12)
+- /home/robclark/src/freedreno/envytools/rnndb/freedreno_copyright.xml (   1453 bytes, from 2013-03-31 16:51:27)
+- /home/robclark/src/freedreno/envytools/rnndb/mdp4/mdp4.xml           (  19332 bytes, from 2013-08-16 22:16:36)
+- /home/robclark/src/freedreno/envytools/rnndb/dsi/dsi.xml             (  11712 bytes, from 2013-08-17 17:13:43)
+- /home/robclark/src/freedreno/envytools/rnndb/dsi/sfpb.xml            (    344 bytes, from 2013-08-11 19:26:32)
+- /home/robclark/src/freedreno/envytools/rnndb/dsi/mmss_cc.xml         (   1544 bytes, from 2013-08-16 19:17:05)
+- /home/robclark/src/freedreno/envytools/rnndb/hdmi/qfprom.xml         (    600 bytes, from 2013-07-05 19:21:12)
+- /home/robclark/src/freedreno/envytools/rnndb/hdmi/hdmi.xml           (  19288 bytes, from 2013-08-11 18:14:15)
+
+Copyright (C) 2013 by the following authors:
+- Rob Clark <robdclark@gmail.com> (robclark)
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice (including the
+next paragraph) shall be included in all copies or substantial
+portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
+IN NO EVENT SHALL THE COPYRIGHT OWNER(S) AND/OR ITS SUPPLIERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+*/
+
+
+#define REG_QFPROM_CONFIG_ROW0_LSB				0x00000238
+#define QFPROM_CONFIG_ROW0_LSB_HDMI_DISABLE			0x00200000
+#define QFPROM_CONFIG_ROW0_LSB_HDCP_DISABLE			0x00400000
+
+
+#endif /* QFPROM_XML */
diff --git a/drivers/gpu/drm/msm/mdp4/mdp4.xml.h b/drivers/gpu/drm/msm/mdp4/mdp4.xml.h
new file mode 100644
index 000000000000..bbeeebe2db55
--- /dev/null
+++ b/drivers/gpu/drm/msm/mdp4/mdp4.xml.h
@@ -0,0 +1,1061 @@
+#ifndef MDP4_XML
+#define MDP4_XML
+
+/* Autogenerated file, DO NOT EDIT manually!
+
+This file was generated by the rules-ng-ng headergen tool in this git repository:
+http://0x04.net/cgit/index.cgi/rules-ng-ng
+git clone git://0x04.net/rules-ng-ng
+
+The rules-ng-ng source files this header was generated from are:
+- /home/robclark/src/freedreno/envytools/rnndb/msm.xml                 (    595 bytes, from 2013-07-05 19:21:12)
+- /home/robclark/src/freedreno/envytools/rnndb/freedreno_copyright.xml (   1453 bytes, from 2013-03-31 16:51:27)
+- /home/robclark/src/freedreno/envytools/rnndb/mdp4/mdp4.xml           (  19332 bytes, from 2013-08-16 22:16:36)
+- /home/robclark/src/freedreno/envytools/rnndb/dsi/dsi.xml             (  11712 bytes, from 2013-08-17 17:13:43)
+- /home/robclark/src/freedreno/envytools/rnndb/dsi/sfpb.xml            (    344 bytes, from 2013-08-11 19:26:32)
+- /home/robclark/src/freedreno/envytools/rnndb/dsi/mmss_cc.xml         (   1544 bytes, from 2013-08-16 19:17:05)
+- /home/robclark/src/freedreno/envytools/rnndb/hdmi/qfprom.xml         (    600 bytes, from 2013-07-05 19:21:12)
+- /home/robclark/src/freedreno/envytools/rnndb/hdmi/hdmi.xml           (  19288 bytes, from 2013-08-11 18:14:15)
+
+Copyright (C) 2013 by the following authors:
+- Rob Clark <robdclark@gmail.com> (robclark)
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice (including the
+next paragraph) shall be included in all copies or substantial
+portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
+IN NO EVENT SHALL THE COPYRIGHT OWNER(S) AND/OR ITS SUPPLIERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+*/
+
+
+enum mpd4_bpc {
+	BPC1 = 0,
+	BPC5 = 1,
+	BPC6 = 2,
+	BPC8 = 3,
+};
+
+enum mpd4_bpc_alpha {
+	BPC1A = 0,
+	BPC4A = 1,
+	BPC6A = 2,
+	BPC8A = 3,
+};
+
+enum mpd4_alpha_type {
+	FG_CONST = 0,
+	BG_CONST = 1,
+	FG_PIXEL = 2,
+	BG_PIXEL = 3,
+};
+
+enum mpd4_pipe {
+	VG1 = 0,
+	VG2 = 1,
+	RGB1 = 2,
+	RGB2 = 3,
+	RGB3 = 4,
+	VG3 = 5,
+	VG4 = 6,
+};
+
+enum mpd4_mixer {
+	MIXER0 = 0,
+	MIXER1 = 1,
+	MIXER2 = 2,
+};
+
+enum mpd4_mixer_stage_id {
+	STAGE_UNUSED = 0,
+	STAGE_BASE = 1,
+	STAGE0 = 2,
+	STAGE1 = 3,
+	STAGE2 = 4,
+	STAGE3 = 5,
+};
+
+enum mdp4_intf {
+	INTF_LCDC_DTV = 0,
+	INTF_DSI_VIDEO = 1,
+	INTF_DSI_CMD = 2,
+	INTF_EBI2_TV = 3,
+};
+
+enum mdp4_cursor_format {
+	CURSOR_ARGB = 1,
+	CURSOR_XRGB = 2,
+};
+
+enum mdp4_dma {
+	DMA_P = 0,
+	DMA_S = 1,
+	DMA_E = 2,
+};
+
+#define MDP4_IRQ_OVERLAY0_DONE					0x00000001
+#define MDP4_IRQ_OVERLAY1_DONE					0x00000002
+#define MDP4_IRQ_DMA_S_DONE					0x00000004
+#define MDP4_IRQ_DMA_E_DONE					0x00000008
+#define MDP4_IRQ_DMA_P_DONE					0x00000010
+#define MDP4_IRQ_VG1_HISTOGRAM					0x00000020
+#define MDP4_IRQ_VG2_HISTOGRAM					0x00000040
+#define MDP4_IRQ_PRIMARY_VSYNC					0x00000080
+#define MDP4_IRQ_PRIMARY_INTF_UDERRUN				0x00000100
+#define MDP4_IRQ_EXTERNAL_VSYNC					0x00000200
+#define MDP4_IRQ_EXTERNAL_INTF_UDERRUN				0x00000400
+#define MDP4_IRQ_PRIMARY_RDPTR					0x00000800
+#define MDP4_IRQ_DMA_P_HISTOGRAM				0x00020000
+#define MDP4_IRQ_DMA_S_HISTOGRAM				0x04000000
+#define MDP4_IRQ_OVERLAY2_DONE					0x40000000
+#define REG_MDP4_VERSION					0x00000000
+#define MDP4_VERSION_MINOR__MASK				0x00ff0000
+#define MDP4_VERSION_MINOR__SHIFT				16
+static inline uint32_t MDP4_VERSION_MINOR(uint32_t val)
+{
+	return ((val) << MDP4_VERSION_MINOR__SHIFT) & MDP4_VERSION_MINOR__MASK;
+}
+#define MDP4_VERSION_MAJOR__MASK				0xff000000
+#define MDP4_VERSION_MAJOR__SHIFT				24
+static inline uint32_t MDP4_VERSION_MAJOR(uint32_t val)
+{
+	return ((val) << MDP4_VERSION_MAJOR__SHIFT) & MDP4_VERSION_MAJOR__MASK;
+}
+
+#define REG_MDP4_OVLP0_KICK					0x00000004
+
+#define REG_MDP4_OVLP1_KICK					0x00000008
+
+#define REG_MDP4_OVLP2_KICK					0x000000d0
+
+#define REG_MDP4_DMA_P_KICK					0x0000000c
+
+#define REG_MDP4_DMA_S_KICK					0x00000010
+
+#define REG_MDP4_DMA_E_KICK					0x00000014
+
+#define REG_MDP4_DISP_STATUS					0x00000018
+
+#define REG_MDP4_DISP_INTF_SEL					0x00000038
+#define MDP4_DISP_INTF_SEL_PRIM__MASK				0x00000003
+#define MDP4_DISP_INTF_SEL_PRIM__SHIFT				0
+static inline uint32_t MDP4_DISP_INTF_SEL_PRIM(enum mdp4_intf val)
+{
+	return ((val) << MDP4_DISP_INTF_SEL_PRIM__SHIFT) & MDP4_DISP_INTF_SEL_PRIM__MASK;
+}
+#define MDP4_DISP_INTF_SEL_SEC__MASK				0x0000000c
+#define MDP4_DISP_INTF_SEL_SEC__SHIFT				2
+static inline uint32_t MDP4_DISP_INTF_SEL_SEC(enum mdp4_intf val)
+{
+	return ((val) << MDP4_DISP_INTF_SEL_SEC__SHIFT) & MDP4_DISP_INTF_SEL_SEC__MASK;
+}
+#define MDP4_DISP_INTF_SEL_EXT__MASK				0x00000030
+#define MDP4_DISP_INTF_SEL_EXT__SHIFT				4
+static inline uint32_t MDP4_DISP_INTF_SEL_EXT(enum mdp4_intf val)
+{
+	return ((val) << MDP4_DISP_INTF_SEL_EXT__SHIFT) & MDP4_DISP_INTF_SEL_EXT__MASK;
+}
+#define MDP4_DISP_INTF_SEL_DSI_VIDEO				0x00000040
+#define MDP4_DISP_INTF_SEL_DSI_CMD				0x00000080
+
+#define REG_MDP4_RESET_STATUS					0x0000003c
+
+#define REG_MDP4_READ_CNFG					0x0000004c
+
+#define REG_MDP4_INTR_ENABLE					0x00000050
+
+#define REG_MDP4_INTR_STATUS					0x00000054
+
+#define REG_MDP4_INTR_CLEAR					0x00000058
+
+#define REG_MDP4_EBI2_LCD0					0x00000060
+
+#define REG_MDP4_EBI2_LCD1					0x00000064
+
+#define REG_MDP4_PORTMAP_MODE					0x00000070
+
+#define REG_MDP4_CS_CONTROLLER0					0x000000c0
+
+#define REG_MDP4_CS_CONTROLLER1					0x000000c4
+
+#define REG_MDP4_LAYERMIXER2_IN_CFG				0x000100f0
+#define MDP4_LAYERMIXER2_IN_CFG_PIPE0__MASK			0x00000007
+#define MDP4_LAYERMIXER2_IN_CFG_PIPE0__SHIFT			0
+static inline uint32_t MDP4_LAYERMIXER2_IN_CFG_PIPE0(enum mpd4_mixer_stage_id val)
+{
+	return ((val) << MDP4_LAYERMIXER2_IN_CFG_PIPE0__SHIFT) & MDP4_LAYERMIXER2_IN_CFG_PIPE0__MASK;
+}
+#define MDP4_LAYERMIXER2_IN_CFG_PIPE0_MIXER1			0x00000008
+#define MDP4_LAYERMIXER2_IN_CFG_PIPE1__MASK			0x00000070
+#define MDP4_LAYERMIXER2_IN_CFG_PIPE1__SHIFT			4
+static inline uint32_t MDP4_LAYERMIXER2_IN_CFG_PIPE1(enum mpd4_mixer_stage_id val)
+{
+	return ((val) << MDP4_LAYERMIXER2_IN_CFG_PIPE1__SHIFT) & MDP4_LAYERMIXER2_IN_CFG_PIPE1__MASK;
+}
+#define MDP4_LAYERMIXER2_IN_CFG_PIPE1_MIXER1			0x00000080
+#define MDP4_LAYERMIXER2_IN_CFG_PIPE2__MASK			0x00000700
+#define MDP4_LAYERMIXER2_IN_CFG_PIPE2__SHIFT			8
+static inline uint32_t MDP4_LAYERMIXER2_IN_CFG_PIPE2(enum mpd4_mixer_stage_id val)
+{
+	return ((val) << MDP4_LAYERMIXER2_IN_CFG_PIPE2__SHIFT) & MDP4_LAYERMIXER2_IN_CFG_PIPE2__MASK;
+}
+#define MDP4_LAYERMIXER2_IN_CFG_PIPE2_MIXER1			0x00000800
+#define MDP4_LAYERMIXER2_IN_CFG_PIPE3__MASK			0x00007000
+#define MDP4_LAYERMIXER2_IN_CFG_PIPE3__SHIFT			12
+static inline uint32_t MDP4_LAYERMIXER2_IN_CFG_PIPE3(enum mpd4_mixer_stage_id val)
+{
+	return ((val) << MDP4_LAYERMIXER2_IN_CFG_PIPE3__SHIFT) & MDP4_LAYERMIXER2_IN_CFG_PIPE3__MASK;
+}
+#define MDP4_LAYERMIXER2_IN_CFG_PIPE3_MIXER1			0x00008000
+#define MDP4_LAYERMIXER2_IN_CFG_PIPE4__MASK			0x00070000
+#define MDP4_LAYERMIXER2_IN_CFG_PIPE4__SHIFT			16
+static inline uint32_t MDP4_LAYERMIXER2_IN_CFG_PIPE4(enum mpd4_mixer_stage_id val)
+{
+	return ((val) << MDP4_LAYERMIXER2_IN_CFG_PIPE4__SHIFT) & MDP4_LAYERMIXER2_IN_CFG_PIPE4__MASK;
+}
+#define MDP4_LAYERMIXER2_IN_CFG_PIPE4_MIXER1			0x00080000
+#define MDP4_LAYERMIXER2_IN_CFG_PIPE5__MASK			0x00700000
+#define MDP4_LAYERMIXER2_IN_CFG_PIPE5__SHIFT			20
+static inline uint32_t MDP4_LAYERMIXER2_IN_CFG_PIPE5(enum mpd4_mixer_stage_id val)
+{
+	return ((val) << MDP4_LAYERMIXER2_IN_CFG_PIPE5__SHIFT) & MDP4_LAYERMIXER2_IN_CFG_PIPE5__MASK;
+}
+#define MDP4_LAYERMIXER2_IN_CFG_PIPE5_MIXER1			0x00800000
+#define MDP4_LAYERMIXER2_IN_CFG_PIPE6__MASK			0x07000000
+#define MDP4_LAYERMIXER2_IN_CFG_PIPE6__SHIFT			24
+static inline uint32_t MDP4_LAYERMIXER2_IN_CFG_PIPE6(enum mpd4_mixer_stage_id val)
+{
+	return ((val) << MDP4_LAYERMIXER2_IN_CFG_PIPE6__SHIFT) & MDP4_LAYERMIXER2_IN_CFG_PIPE6__MASK;
+}
+#define MDP4_LAYERMIXER2_IN_CFG_PIPE6_MIXER1			0x08000000
+#define MDP4_LAYERMIXER2_IN_CFG_PIPE7__MASK			0x70000000
+#define MDP4_LAYERMIXER2_IN_CFG_PIPE7__SHIFT			28
+static inline uint32_t MDP4_LAYERMIXER2_IN_CFG_PIPE7(enum mpd4_mixer_stage_id val)
+{
+	return ((val) << MDP4_LAYERMIXER2_IN_CFG_PIPE7__SHIFT) & MDP4_LAYERMIXER2_IN_CFG_PIPE7__MASK;
+}
+#define MDP4_LAYERMIXER2_IN_CFG_PIPE7_MIXER1			0x80000000
+
+#define REG_MDP4_LAYERMIXER_IN_CFG_UPDATE_METHOD		0x000100fc
+
+#define REG_MDP4_LAYERMIXER_IN_CFG				0x00010100
+#define MDP4_LAYERMIXER_IN_CFG_PIPE0__MASK			0x00000007
+#define MDP4_LAYERMIXER_IN_CFG_PIPE0__SHIFT			0
+static inline uint32_t MDP4_LAYERMIXER_IN_CFG_PIPE0(enum mpd4_mixer_stage_id val)
+{
+	return ((val) << MDP4_LAYERMIXER_IN_CFG_PIPE0__SHIFT) & MDP4_LAYERMIXER_IN_CFG_PIPE0__MASK;
+}
+#define MDP4_LAYERMIXER_IN_CFG_PIPE0_MIXER1			0x00000008
+#define MDP4_LAYERMIXER_IN_CFG_PIPE1__MASK			0x00000070
+#define MDP4_LAYERMIXER_IN_CFG_PIPE1__SHIFT			4
+static inline uint32_t MDP4_LAYERMIXER_IN_CFG_PIPE1(enum mpd4_mixer_stage_id val)
+{
+	return ((val) << MDP4_LAYERMIXER_IN_CFG_PIPE1__SHIFT) & MDP4_LAYERMIXER_IN_CFG_PIPE1__MASK;
+}
+#define MDP4_LAYERMIXER_IN_CFG_PIPE1_MIXER1			0x00000080
+#define MDP4_LAYERMIXER_IN_CFG_PIPE2__MASK			0x00000700
+#define MDP4_LAYERMIXER_IN_CFG_PIPE2__SHIFT			8
+static inline uint32_t MDP4_LAYERMIXER_IN_CFG_PIPE2(enum mpd4_mixer_stage_id val)
+{
+	return ((val) << MDP4_LAYERMIXER_IN_CFG_PIPE2__SHIFT) & MDP4_LAYERMIXER_IN_CFG_PIPE2__MASK;
+}
+#define MDP4_LAYERMIXER_IN_CFG_PIPE2_MIXER1			0x00000800
+#define MDP4_LAYERMIXER_IN_CFG_PIPE3__MASK			0x00007000
+#define MDP4_LAYERMIXER_IN_CFG_PIPE3__SHIFT			12
+static inline uint32_t MDP4_LAYERMIXER_IN_CFG_PIPE3(enum mpd4_mixer_stage_id val)
+{
+	return ((val) << MDP4_LAYERMIXER_IN_CFG_PIPE3__SHIFT) & MDP4_LAYERMIXER_IN_CFG_PIPE3__MASK;
+}
+#define MDP4_LAYERMIXER_IN_CFG_PIPE3_MIXER1			0x00008000
+#define MDP4_LAYERMIXER_IN_CFG_PIPE4__MASK			0x00070000
+#define MDP4_LAYERMIXER_IN_CFG_PIPE4__SHIFT			16
+static inline uint32_t MDP4_LAYERMIXER_IN_CFG_PIPE4(enum mpd4_mixer_stage_id val)
+{
+	return ((val) << MDP4_LAYERMIXER_IN_CFG_PIPE4__SHIFT) & MDP4_LAYERMIXER_IN_CFG_PIPE4__MASK;
+}
+#define MDP4_LAYERMIXER_IN_CFG_PIPE4_MIXER1			0x00080000
+#define MDP4_LAYERMIXER_IN_CFG_PIPE5__MASK			0x00700000
+#define MDP4_LAYERMIXER_IN_CFG_PIPE5__SHIFT			20
+static inline uint32_t MDP4_LAYERMIXER_IN_CFG_PIPE5(enum mpd4_mixer_stage_id val)
+{
+	return ((val) << MDP4_LAYERMIXER_IN_CFG_PIPE5__SHIFT) & MDP4_LAYERMIXER_IN_CFG_PIPE5__MASK;
+}
+#define MDP4_LAYERMIXER_IN_CFG_PIPE5_MIXER1			0x00800000
+#define MDP4_LAYERMIXER_IN_CFG_PIPE6__MASK			0x07000000
+#define MDP4_LAYERMIXER_IN_CFG_PIPE6__SHIFT			24
+static inline uint32_t MDP4_LAYERMIXER_IN_CFG_PIPE6(enum mpd4_mixer_stage_id val)
+{
+	return ((val) << MDP4_LAYERMIXER_IN_CFG_PIPE6__SHIFT) & MDP4_LAYERMIXER_IN_CFG_PIPE6__MASK;
+}
+#define MDP4_LAYERMIXER_IN_CFG_PIPE6_MIXER1			0x08000000
+#define MDP4_LAYERMIXER_IN_CFG_PIPE7__MASK			0x70000000
+#define MDP4_LAYERMIXER_IN_CFG_PIPE7__SHIFT			28
+static inline uint32_t MDP4_LAYERMIXER_IN_CFG_PIPE7(enum mpd4_mixer_stage_id val)
+{
+	return ((val) << MDP4_LAYERMIXER_IN_CFG_PIPE7__SHIFT) & MDP4_LAYERMIXER_IN_CFG_PIPE7__MASK;
+}
+#define MDP4_LAYERMIXER_IN_CFG_PIPE7_MIXER1			0x80000000
+
+#define REG_MDP4_VG2_SRC_FORMAT					0x00030050
+
+#define REG_MDP4_VG2_CONST_COLOR				0x00031008
+
+#define REG_MDP4_OVERLAY_FLUSH					0x00018000
+#define MDP4_OVERLAY_FLUSH_OVLP0				0x00000001
+#define MDP4_OVERLAY_FLUSH_OVLP1				0x00000002
+#define MDP4_OVERLAY_FLUSH_VG1					0x00000004
+#define MDP4_OVERLAY_FLUSH_VG2					0x00000008
+#define MDP4_OVERLAY_FLUSH_RGB1					0x00000010
+#define MDP4_OVERLAY_FLUSH_RGB2					0x00000020
+
+static inline uint32_t __offset_OVLP(uint32_t idx)
+{
+	switch (idx) {
+		case 0: return 0x00010000;
+		case 1: return 0x00018000;
+		case 2: return 0x00088000;
+		default: return INVALID_IDX(idx);
+	}
+}
+static inline uint32_t REG_MDP4_OVLP(uint32_t i0) { return 0x00000000 + __offset_OVLP(i0); }
+
+static inline uint32_t REG_MDP4_OVLP_CFG(uint32_t i0) { return 0x00000004 + __offset_OVLP(i0); }
+
+static inline uint32_t REG_MDP4_OVLP_SIZE(uint32_t i0) { return 0x00000008 + __offset_OVLP(i0); }
+#define MDP4_OVLP_SIZE_HEIGHT__MASK				0xffff0000
+#define MDP4_OVLP_SIZE_HEIGHT__SHIFT				16
+static inline uint32_t MDP4_OVLP_SIZE_HEIGHT(uint32_t val)
+{
+	return ((val) << MDP4_OVLP_SIZE_HEIGHT__SHIFT) & MDP4_OVLP_SIZE_HEIGHT__MASK;
+}
+#define MDP4_OVLP_SIZE_WIDTH__MASK				0x0000ffff
+#define MDP4_OVLP_SIZE_WIDTH__SHIFT				0
+static inline uint32_t MDP4_OVLP_SIZE_WIDTH(uint32_t val)
+{
+	return ((val) << MDP4_OVLP_SIZE_WIDTH__SHIFT) & MDP4_OVLP_SIZE_WIDTH__MASK;
+}
+
+static inline uint32_t REG_MDP4_OVLP_BASE(uint32_t i0) { return 0x0000000c + __offset_OVLP(i0); }
+
+static inline uint32_t REG_MDP4_OVLP_STRIDE(uint32_t i0) { return 0x00000010 + __offset_OVLP(i0); }
+
+static inline uint32_t REG_MDP4_OVLP_OPMODE(uint32_t i0) { return 0x00000014 + __offset_OVLP(i0); }
+
+static inline uint32_t __offset_STAGE(uint32_t idx)
+{
+	switch (idx) {
+		case 0: return 0x00000104;
+		case 1: return 0x00000124;
+		case 2: return 0x00000144;
+		case 3: return 0x00000160;
+		default: return INVALID_IDX(idx);
+	}
+}
+static inline uint32_t REG_MDP4_OVLP_STAGE(uint32_t i0, uint32_t i1) { return 0x00000000 + __offset_OVLP(i0) + __offset_STAGE(i1); }
+
+static inline uint32_t REG_MDP4_OVLP_STAGE_OP(uint32_t i0, uint32_t i1) { return 0x00000000 + __offset_OVLP(i0) + __offset_STAGE(i1); }
+#define MDP4_OVLP_STAGE_OP_FG_ALPHA__MASK			0x00000003
+#define MDP4_OVLP_STAGE_OP_FG_ALPHA__SHIFT			0
+static inline uint32_t MDP4_OVLP_STAGE_OP_FG_ALPHA(enum mpd4_alpha_type val)
+{
+	return ((val) << MDP4_OVLP_STAGE_OP_FG_ALPHA__SHIFT) & MDP4_OVLP_STAGE_OP_FG_ALPHA__MASK;
+}
+#define MDP4_OVLP_STAGE_OP_FG_INV_ALPHA				0x00000004
+#define MDP4_OVLP_STAGE_OP_FG_MOD_ALPHA				0x00000008
+#define MDP4_OVLP_STAGE_OP_BG_ALPHA__MASK			0x00000030
+#define MDP4_OVLP_STAGE_OP_BG_ALPHA__SHIFT			4
+static inline uint32_t MDP4_OVLP_STAGE_OP_BG_ALPHA(enum mpd4_alpha_type val)
+{
+	return ((val) << MDP4_OVLP_STAGE_OP_BG_ALPHA__SHIFT) & MDP4_OVLP_STAGE_OP_BG_ALPHA__MASK;
+}
+#define MDP4_OVLP_STAGE_OP_BG_INV_ALPHA				0x00000040
+#define MDP4_OVLP_STAGE_OP_BG_MOD_ALPHA				0x00000080
+#define MDP4_OVLP_STAGE_OP_FG_TRANSP				0x00000100
+#define MDP4_OVLP_STAGE_OP_BG_TRANSP				0x00000200
+
+static inline uint32_t REG_MDP4_OVLP_STAGE_FG_ALPHA(uint32_t i0, uint32_t i1) { return 0x00000004 + __offset_OVLP(i0) + __offset_STAGE(i1); }
+
+static inline uint32_t REG_MDP4_OVLP_STAGE_BG_ALPHA(uint32_t i0, uint32_t i1) { return 0x00000008 + __offset_OVLP(i0) + __offset_STAGE(i1); }
+
+static inline uint32_t REG_MDP4_OVLP_STAGE_TRANSP_LOW0(uint32_t i0, uint32_t i1) { return 0x0000000c + __offset_OVLP(i0) + __offset_STAGE(i1); }
+
+static inline uint32_t REG_MDP4_OVLP_STAGE_TRANSP_LOW1(uint32_t i0, uint32_t i1) { return 0x00000010 + __offset_OVLP(i0) + __offset_STAGE(i1); }
+
+static inline uint32_t REG_MDP4_OVLP_STAGE_TRANSP_HIGH0(uint32_t i0, uint32_t i1) { return 0x00000014 + __offset_OVLP(i0) + __offset_STAGE(i1); }
+
+static inline uint32_t REG_MDP4_OVLP_STAGE_TRANSP_HIGH1(uint32_t i0, uint32_t i1) { return 0x00000018 + __offset_OVLP(i0) + __offset_STAGE(i1); }
+
+static inline uint32_t __offset_STAGE_CO3(uint32_t idx)
+{
+	switch (idx) {
+		case 0: return 0x00001004;
+		case 1: return 0x00001404;
+		case 2: return 0x00001804;
+		case 3: return 0x00001b84;
+		default: return INVALID_IDX(idx);
+	}
+}
+static inline uint32_t REG_MDP4_OVLP_STAGE_CO3(uint32_t i0, uint32_t i1) { return 0x00000000 + __offset_OVLP(i0) + __offset_STAGE_CO3(i1); }
+
+static inline uint32_t REG_MDP4_OVLP_STAGE_CO3_SEL(uint32_t i0, uint32_t i1) { return 0x00000000 + __offset_OVLP(i0) + __offset_STAGE_CO3(i1); }
+#define MDP4_OVLP_STAGE_CO3_SEL_FG_ALPHA			0x00000001
+
+static inline uint32_t REG_MDP4_OVLP_TRANSP_LOW0(uint32_t i0) { return 0x00000180 + __offset_OVLP(i0); }
+
+static inline uint32_t REG_MDP4_OVLP_TRANSP_LOW1(uint32_t i0) { return 0x00000184 + __offset_OVLP(i0); }
+
+static inline uint32_t REG_MDP4_OVLP_TRANSP_HIGH0(uint32_t i0) { return 0x00000188 + __offset_OVLP(i0); }
+
+static inline uint32_t REG_MDP4_OVLP_TRANSP_HIGH1(uint32_t i0) { return 0x0000018c + __offset_OVLP(i0); }
+
+static inline uint32_t REG_MDP4_OVLP_CSC_CONFIG(uint32_t i0) { return 0x00000200 + __offset_OVLP(i0); }
+
+static inline uint32_t REG_MDP4_OVLP_CSC(uint32_t i0) { return 0x00002000 + __offset_OVLP(i0); }
+
+
+static inline uint32_t REG_MDP4_OVLP_CSC_MV(uint32_t i0, uint32_t i1) { return 0x00002400 + __offset_OVLP(i0) + 0x4*i1; }
+
+static inline uint32_t REG_MDP4_OVLP_CSC_MV_VAL(uint32_t i0, uint32_t i1) { return 0x00002400 + __offset_OVLP(i0) + 0x4*i1; }
+
+static inline uint32_t REG_MDP4_OVLP_CSC_PRE_BV(uint32_t i0, uint32_t i1) { return 0x00002500 + __offset_OVLP(i0) + 0x4*i1; }
+
+static inline uint32_t REG_MDP4_OVLP_CSC_PRE_BV_VAL(uint32_t i0, uint32_t i1) { return 0x00002500 + __offset_OVLP(i0) + 0x4*i1; }
+
+static inline uint32_t REG_MDP4_OVLP_CSC_POST_BV(uint32_t i0, uint32_t i1) { return 0x00002580 + __offset_OVLP(i0) + 0x4*i1; }
+
+static inline uint32_t REG_MDP4_OVLP_CSC_POST_BV_VAL(uint32_t i0, uint32_t i1) { return 0x00002580 + __offset_OVLP(i0) + 0x4*i1; }
+
+static inline uint32_t REG_MDP4_OVLP_CSC_PRE_LV(uint32_t i0, uint32_t i1) { return 0x00002600 + __offset_OVLP(i0) + 0x4*i1; }
+
+static inline uint32_t REG_MDP4_OVLP_CSC_PRE_LV_VAL(uint32_t i0, uint32_t i1) { return 0x00002600 + __offset_OVLP(i0) + 0x4*i1; }
+
+static inline uint32_t REG_MDP4_OVLP_CSC_POST_LV(uint32_t i0, uint32_t i1) { return 0x00002680 + __offset_OVLP(i0) + 0x4*i1; }
+
+static inline uint32_t REG_MDP4_OVLP_CSC_POST_LV_VAL(uint32_t i0, uint32_t i1) { return 0x00002680 + __offset_OVLP(i0) + 0x4*i1; }
+
+#define REG_MDP4_DMA_P_OP_MODE					0x00090070
+
+static inline uint32_t REG_MDP4_LUTN(uint32_t i0) { return 0x00094800 + 0x400*i0; }
+
+static inline uint32_t REG_MDP4_LUTN_LUT(uint32_t i0, uint32_t i1) { return 0x00094800 + 0x400*i0 + 0x4*i1; }
+
+static inline uint32_t REG_MDP4_LUTN_LUT_VAL(uint32_t i0, uint32_t i1) { return 0x00094800 + 0x400*i0 + 0x4*i1; }
+
+#define REG_MDP4_DMA_S_OP_MODE					0x000a0028
+
+static inline uint32_t REG_MDP4_DMA_E_QUANT(uint32_t i0) { return 0x000b0070 + 0x4*i0; }
+
+static inline uint32_t __offset_DMA(enum mdp4_dma idx)
+{
+	switch (idx) {
+		case DMA_P: return 0x00090000;
+		case DMA_S: return 0x000a0000;
+		case DMA_E: return 0x000b0000;
+		default: return INVALID_IDX(idx);
+	}
+}
+static inline uint32_t REG_MDP4_DMA(enum mdp4_dma i0) { return 0x00000000 + __offset_DMA(i0); }
+
+static inline uint32_t REG_MDP4_DMA_CONFIG(enum mdp4_dma i0) { return 0x00000000 + __offset_DMA(i0); }
+#define MDP4_DMA_CONFIG_G_BPC__MASK				0x00000003
+#define MDP4_DMA_CONFIG_G_BPC__SHIFT				0
+static inline uint32_t MDP4_DMA_CONFIG_G_BPC(enum mpd4_bpc val)
+{
+	return ((val) << MDP4_DMA_CONFIG_G_BPC__SHIFT) & MDP4_DMA_CONFIG_G_BPC__MASK;
+}
+#define MDP4_DMA_CONFIG_B_BPC__MASK				0x0000000c
+#define MDP4_DMA_CONFIG_B_BPC__SHIFT				2
+static inline uint32_t MDP4_DMA_CONFIG_B_BPC(enum mpd4_bpc val)
+{
+	return ((val) << MDP4_DMA_CONFIG_B_BPC__SHIFT) & MDP4_DMA_CONFIG_B_BPC__MASK;
+}
+#define MDP4_DMA_CONFIG_R_BPC__MASK				0x00000030
+#define MDP4_DMA_CONFIG_R_BPC__SHIFT				4
+static inline uint32_t MDP4_DMA_CONFIG_R_BPC(enum mpd4_bpc val)
+{
+	return ((val) << MDP4_DMA_CONFIG_R_BPC__SHIFT) & MDP4_DMA_CONFIG_R_BPC__MASK;
+}
+#define MDP4_DMA_CONFIG_PACK_ALIGN_MSB				0x00000080
+#define MDP4_DMA_CONFIG_PACK__MASK				0x0000ff00
+#define MDP4_DMA_CONFIG_PACK__SHIFT				8
+static inline uint32_t MDP4_DMA_CONFIG_PACK(uint32_t val)
+{
+	return ((val) << MDP4_DMA_CONFIG_PACK__SHIFT) & MDP4_DMA_CONFIG_PACK__MASK;
+}
+#define MDP4_DMA_CONFIG_DEFLKR_EN				0x01000000
+#define MDP4_DMA_CONFIG_DITHER_EN				0x01000000
+
+static inline uint32_t REG_MDP4_DMA_SRC_SIZE(enum mdp4_dma i0) { return 0x00000004 + __offset_DMA(i0); }
+#define MDP4_DMA_SRC_SIZE_HEIGHT__MASK				0xffff0000
+#define MDP4_DMA_SRC_SIZE_HEIGHT__SHIFT				16
+static inline uint32_t MDP4_DMA_SRC_SIZE_HEIGHT(uint32_t val)
+{
+	return ((val) << MDP4_DMA_SRC_SIZE_HEIGHT__SHIFT) & MDP4_DMA_SRC_SIZE_HEIGHT__MASK;
+}
+#define MDP4_DMA_SRC_SIZE_WIDTH__MASK				0x0000ffff
+#define MDP4_DMA_SRC_SIZE_WIDTH__SHIFT				0
+static inline uint32_t MDP4_DMA_SRC_SIZE_WIDTH(uint32_t val)
+{
+	return ((val) << MDP4_DMA_SRC_SIZE_WIDTH__SHIFT) & MDP4_DMA_SRC_SIZE_WIDTH__MASK;
+}
+
+static inline uint32_t REG_MDP4_DMA_SRC_BASE(enum mdp4_dma i0) { return 0x00000008 + __offset_DMA(i0); }
+
+static inline uint32_t REG_MDP4_DMA_SRC_STRIDE(enum mdp4_dma i0) { return 0x0000000c + __offset_DMA(i0); }
+
+static inline uint32_t REG_MDP4_DMA_DST_SIZE(enum mdp4_dma i0) { return 0x00000010 + __offset_DMA(i0); }
+#define MDP4_DMA_DST_SIZE_HEIGHT__MASK				0xffff0000
+#define MDP4_DMA_DST_SIZE_HEIGHT__SHIFT				16
+static inline uint32_t MDP4_DMA_DST_SIZE_HEIGHT(uint32_t val)
+{
+	return ((val) << MDP4_DMA_DST_SIZE_HEIGHT__SHIFT) & MDP4_DMA_DST_SIZE_HEIGHT__MASK;
+}
+#define MDP4_DMA_DST_SIZE_WIDTH__MASK				0x0000ffff
+#define MDP4_DMA_DST_SIZE_WIDTH__SHIFT				0
+static inline uint32_t MDP4_DMA_DST_SIZE_WIDTH(uint32_t val)
+{
+	return ((val) << MDP4_DMA_DST_SIZE_WIDTH__SHIFT) & MDP4_DMA_DST_SIZE_WIDTH__MASK;
+}
+
+static inline uint32_t REG_MDP4_DMA_CURSOR_SIZE(enum mdp4_dma i0) { return 0x00000044 + __offset_DMA(i0); }
+#define MDP4_DMA_CURSOR_SIZE_WIDTH__MASK			0x0000007f
+#define MDP4_DMA_CURSOR_SIZE_WIDTH__SHIFT			0
+static inline uint32_t MDP4_DMA_CURSOR_SIZE_WIDTH(uint32_t val)
+{
+	return ((val) << MDP4_DMA_CURSOR_SIZE_WIDTH__SHIFT) & MDP4_DMA_CURSOR_SIZE_WIDTH__MASK;
+}
+#define MDP4_DMA_CURSOR_SIZE_HEIGHT__MASK			0x007f0000
+#define MDP4_DMA_CURSOR_SIZE_HEIGHT__SHIFT			16
+static inline uint32_t MDP4_DMA_CURSOR_SIZE_HEIGHT(uint32_t val)
+{
+	return ((val) << MDP4_DMA_CURSOR_SIZE_HEIGHT__SHIFT) & MDP4_DMA_CURSOR_SIZE_HEIGHT__MASK;
+}
+
+static inline uint32_t REG_MDP4_DMA_CURSOR_BASE(enum mdp4_dma i0) { return 0x00000048 + __offset_DMA(i0); }
+
+static inline uint32_t REG_MDP4_DMA_CURSOR_POS(enum mdp4_dma i0) { return 0x0000004c + __offset_DMA(i0); }
+#define MDP4_DMA_CURSOR_POS_X__MASK				0x0000ffff
+#define MDP4_DMA_CURSOR_POS_X__SHIFT				0
+static inline uint32_t MDP4_DMA_CURSOR_POS_X(uint32_t val)
+{
+	return ((val) << MDP4_DMA_CURSOR_POS_X__SHIFT) & MDP4_DMA_CURSOR_POS_X__MASK;
+}
+#define MDP4_DMA_CURSOR_POS_Y__MASK				0xffff0000
+#define MDP4_DMA_CURSOR_POS_Y__SHIFT				16
+static inline uint32_t MDP4_DMA_CURSOR_POS_Y(uint32_t val)
+{
+	return ((val) << MDP4_DMA_CURSOR_POS_Y__SHIFT) & MDP4_DMA_CURSOR_POS_Y__MASK;
+}
+
+static inline uint32_t REG_MDP4_DMA_CURSOR_BLEND_CONFIG(enum mdp4_dma i0) { return 0x00000060 + __offset_DMA(i0); }
+#define MDP4_DMA_CURSOR_BLEND_CONFIG_CURSOR_EN			0x00000001
+#define MDP4_DMA_CURSOR_BLEND_CONFIG_FORMAT__MASK		0x00000006
+#define MDP4_DMA_CURSOR_BLEND_CONFIG_FORMAT__SHIFT		1
+static inline uint32_t MDP4_DMA_CURSOR_BLEND_CONFIG_FORMAT(enum mdp4_cursor_format val)
+{
+	return ((val) << MDP4_DMA_CURSOR_BLEND_CONFIG_FORMAT__SHIFT) & MDP4_DMA_CURSOR_BLEND_CONFIG_FORMAT__MASK;
+}
+#define MDP4_DMA_CURSOR_BLEND_CONFIG_TRANSP_EN			0x00000008
+
+static inline uint32_t REG_MDP4_DMA_CURSOR_BLEND_PARAM(enum mdp4_dma i0) { return 0x00000064 + __offset_DMA(i0); }
+
+static inline uint32_t REG_MDP4_DMA_BLEND_TRANS_LOW(enum mdp4_dma i0) { return 0x00000068 + __offset_DMA(i0); }
+
+static inline uint32_t REG_MDP4_DMA_BLEND_TRANS_HIGH(enum mdp4_dma i0) { return 0x0000006c + __offset_DMA(i0); }
+
+static inline uint32_t REG_MDP4_DMA_FETCH_CONFIG(enum mdp4_dma i0) { return 0x00001004 + __offset_DMA(i0); }
+
+static inline uint32_t REG_MDP4_DMA_CSC(enum mdp4_dma i0) { return 0x00003000 + __offset_DMA(i0); }
+
+
+static inline uint32_t REG_MDP4_DMA_CSC_MV(enum mdp4_dma i0, uint32_t i1) { return 0x00003400 + __offset_DMA(i0) + 0x4*i1; }
+
+static inline uint32_t REG_MDP4_DMA_CSC_MV_VAL(enum mdp4_dma i0, uint32_t i1) { return 0x00003400 + __offset_DMA(i0) + 0x4*i1; }
+
+static inline uint32_t REG_MDP4_DMA_CSC_PRE_BV(enum mdp4_dma i0, uint32_t i1) { return 0x00003500 + __offset_DMA(i0) + 0x4*i1; }
+
+static inline uint32_t REG_MDP4_DMA_CSC_PRE_BV_VAL(enum mdp4_dma i0, uint32_t i1) { return 0x00003500 + __offset_DMA(i0) + 0x4*i1; }
+
+static inline uint32_t REG_MDP4_DMA_CSC_POST_BV(enum mdp4_dma i0, uint32_t i1) { return 0x00003580 + __offset_DMA(i0) + 0x4*i1; }
+
+static inline uint32_t REG_MDP4_DMA_CSC_POST_BV_VAL(enum mdp4_dma i0, uint32_t i1) { return 0x00003580 + __offset_DMA(i0) + 0x4*i1; }
+
+static inline uint32_t REG_MDP4_DMA_CSC_PRE_LV(enum mdp4_dma i0, uint32_t i1) { return 0x00003600 + __offset_DMA(i0) + 0x4*i1; }
+
+static inline uint32_t REG_MDP4_DMA_CSC_PRE_LV_VAL(enum mdp4_dma i0, uint32_t i1) { return 0x00003600 + __offset_DMA(i0) + 0x4*i1; }
+
+static inline uint32_t REG_MDP4_DMA_CSC_POST_LV(enum mdp4_dma i0, uint32_t i1) { return 0x00003680 + __offset_DMA(i0) + 0x4*i1; }
+
+static inline uint32_t REG_MDP4_DMA_CSC_POST_LV_VAL(enum mdp4_dma i0, uint32_t i1) { return 0x00003680 + __offset_DMA(i0) + 0x4*i1; }
+
+static inline uint32_t REG_MDP4_PIPE(enum mpd4_pipe i0) { return 0x00020000 + 0x10000*i0; }
+
+static inline uint32_t REG_MDP4_PIPE_SRC_SIZE(enum mpd4_pipe i0) { return 0x00020000 + 0x10000*i0; }
+#define MDP4_PIPE_SRC_SIZE_HEIGHT__MASK				0xffff0000
+#define MDP4_PIPE_SRC_SIZE_HEIGHT__SHIFT			16
+static inline uint32_t MDP4_PIPE_SRC_SIZE_HEIGHT(uint32_t val)
+{
+	return ((val) << MDP4_PIPE_SRC_SIZE_HEIGHT__SHIFT) & MDP4_PIPE_SRC_SIZE_HEIGHT__MASK;
+}
+#define MDP4_PIPE_SRC_SIZE_WIDTH__MASK				0x0000ffff
+#define MDP4_PIPE_SRC_SIZE_WIDTH__SHIFT				0
+static inline uint32_t MDP4_PIPE_SRC_SIZE_WIDTH(uint32_t val)
+{
+	return ((val) << MDP4_PIPE_SRC_SIZE_WIDTH__SHIFT) & MDP4_PIPE_SRC_SIZE_WIDTH__MASK;
+}
+
+static inline uint32_t REG_MDP4_PIPE_SRC_XY(enum mpd4_pipe i0) { return 0x00020004 + 0x10000*i0; }
+#define MDP4_PIPE_SRC_XY_Y__MASK				0xffff0000
+#define MDP4_PIPE_SRC_XY_Y__SHIFT				16
+static inline uint32_t MDP4_PIPE_SRC_XY_Y(uint32_t val)
+{
+	return ((val) << MDP4_PIPE_SRC_XY_Y__SHIFT) & MDP4_PIPE_SRC_XY_Y__MASK;
+}
+#define MDP4_PIPE_SRC_XY_X__MASK				0x0000ffff
+#define MDP4_PIPE_SRC_XY_X__SHIFT				0
+static inline uint32_t MDP4_PIPE_SRC_XY_X(uint32_t val)
+{
+	return ((val) << MDP4_PIPE_SRC_XY_X__SHIFT) & MDP4_PIPE_SRC_XY_X__MASK;
+}
+
+static inline uint32_t REG_MDP4_PIPE_DST_SIZE(enum mpd4_pipe i0) { return 0x00020008 + 0x10000*i0; }
+#define MDP4_PIPE_DST_SIZE_HEIGHT__MASK				0xffff0000
+#define MDP4_PIPE_DST_SIZE_HEIGHT__SHIFT			16
+static inline uint32_t MDP4_PIPE_DST_SIZE_HEIGHT(uint32_t val)
+{
+	return ((val) << MDP4_PIPE_DST_SIZE_HEIGHT__SHIFT) & MDP4_PIPE_DST_SIZE_HEIGHT__MASK;
+}
+#define MDP4_PIPE_DST_SIZE_WIDTH__MASK				0x0000ffff
+#define MDP4_PIPE_DST_SIZE_WIDTH__SHIFT				0
+static inline uint32_t MDP4_PIPE_DST_SIZE_WIDTH(uint32_t val)
+{
+	return ((val) << MDP4_PIPE_DST_SIZE_WIDTH__SHIFT) & MDP4_PIPE_DST_SIZE_WIDTH__MASK;
+}
+
+static inline uint32_t REG_MDP4_PIPE_DST_XY(enum mpd4_pipe i0) { return 0x0002000c + 0x10000*i0; }
+#define MDP4_PIPE_DST_XY_Y__MASK				0xffff0000
+#define MDP4_PIPE_DST_XY_Y__SHIFT				16
+static inline uint32_t MDP4_PIPE_DST_XY_Y(uint32_t val)
+{
+	return ((val) << MDP4_PIPE_DST_XY_Y__SHIFT) & MDP4_PIPE_DST_XY_Y__MASK;
+}
+#define MDP4_PIPE_DST_XY_X__MASK				0x0000ffff
+#define MDP4_PIPE_DST_XY_X__SHIFT				0
+static inline uint32_t MDP4_PIPE_DST_XY_X(uint32_t val)
+{
+	return ((val) << MDP4_PIPE_DST_XY_X__SHIFT) & MDP4_PIPE_DST_XY_X__MASK;
+}
+
+static inline uint32_t REG_MDP4_PIPE_SRCP0_BASE(enum mpd4_pipe i0) { return 0x00020010 + 0x10000*i0; }
+
+static inline uint32_t REG_MDP4_PIPE_SRCP1_BASE(enum mpd4_pipe i0) { return 0x00020014 + 0x10000*i0; }
+
+static inline uint32_t REG_MDP4_PIPE_SRCP2_BASE(enum mpd4_pipe i0) { return 0x00020018 + 0x10000*i0; }
+
+static inline uint32_t REG_MDP4_PIPE_SRC_STRIDE_A(enum mpd4_pipe i0) { return 0x00020040 + 0x10000*i0; }
+#define MDP4_PIPE_SRC_STRIDE_A_P0__MASK				0x0000ffff
+#define MDP4_PIPE_SRC_STRIDE_A_P0__SHIFT			0
+static inline uint32_t MDP4_PIPE_SRC_STRIDE_A_P0(uint32_t val)
+{
+	return ((val) << MDP4_PIPE_SRC_STRIDE_A_P0__SHIFT) & MDP4_PIPE_SRC_STRIDE_A_P0__MASK;
+}
+#define MDP4_PIPE_SRC_STRIDE_A_P1__MASK				0xffff0000
+#define MDP4_PIPE_SRC_STRIDE_A_P1__SHIFT			16
+static inline uint32_t MDP4_PIPE_SRC_STRIDE_A_P1(uint32_t val)
+{
+	return ((val) << MDP4_PIPE_SRC_STRIDE_A_P1__SHIFT) & MDP4_PIPE_SRC_STRIDE_A_P1__MASK;
+}
+
+static inline uint32_t REG_MDP4_PIPE_SRC_STRIDE_B(enum mpd4_pipe i0) { return 0x00020044 + 0x10000*i0; }
+#define MDP4_PIPE_SRC_STRIDE_B_P2__MASK				0x0000ffff
+#define MDP4_PIPE_SRC_STRIDE_B_P2__SHIFT			0
+static inline uint32_t MDP4_PIPE_SRC_STRIDE_B_P2(uint32_t val)
+{
+	return ((val) << MDP4_PIPE_SRC_STRIDE_B_P2__SHIFT) & MDP4_PIPE_SRC_STRIDE_B_P2__MASK;
+}
+#define MDP4_PIPE_SRC_STRIDE_B_P3__MASK				0xffff0000
+#define MDP4_PIPE_SRC_STRIDE_B_P3__SHIFT			16
+static inline uint32_t MDP4_PIPE_SRC_STRIDE_B_P3(uint32_t val)
+{
+	return ((val) << MDP4_PIPE_SRC_STRIDE_B_P3__SHIFT) & MDP4_PIPE_SRC_STRIDE_B_P3__MASK;
+}
+
+static inline uint32_t REG_MDP4_PIPE_FRAME_SIZE(enum mpd4_pipe i0) { return 0x00020048 + 0x10000*i0; }
+#define MDP4_PIPE_FRAME_SIZE_HEIGHT__MASK			0xffff0000
+#define MDP4_PIPE_FRAME_SIZE_HEIGHT__SHIFT			16
+static inline uint32_t MDP4_PIPE_FRAME_SIZE_HEIGHT(uint32_t val)
+{
+	return ((val) << MDP4_PIPE_FRAME_SIZE_HEIGHT__SHIFT) & MDP4_PIPE_FRAME_SIZE_HEIGHT__MASK;
+}
+#define MDP4_PIPE_FRAME_SIZE_WIDTH__MASK			0x0000ffff
+#define MDP4_PIPE_FRAME_SIZE_WIDTH__SHIFT			0
+static inline uint32_t MDP4_PIPE_FRAME_SIZE_WIDTH(uint32_t val)
+{
+	return ((val) << MDP4_PIPE_FRAME_SIZE_WIDTH__SHIFT) & MDP4_PIPE_FRAME_SIZE_WIDTH__MASK;
+}
+
+static inline uint32_t REG_MDP4_PIPE_SRC_FORMAT(enum mpd4_pipe i0) { return 0x00020050 + 0x10000*i0; }
+#define MDP4_PIPE_SRC_FORMAT_G_BPC__MASK			0x00000003
+#define MDP4_PIPE_SRC_FORMAT_G_BPC__SHIFT			0
+static inline uint32_t MDP4_PIPE_SRC_FORMAT_G_BPC(enum mpd4_bpc val)
+{
+	return ((val) << MDP4_PIPE_SRC_FORMAT_G_BPC__SHIFT) & MDP4_PIPE_SRC_FORMAT_G_BPC__MASK;
+}
+#define MDP4_PIPE_SRC_FORMAT_B_BPC__MASK			0x0000000c
+#define MDP4_PIPE_SRC_FORMAT_B_BPC__SHIFT			2
+static inline uint32_t MDP4_PIPE_SRC_FORMAT_B_BPC(enum mpd4_bpc val)
+{
+	return ((val) << MDP4_PIPE_SRC_FORMAT_B_BPC__SHIFT) & MDP4_PIPE_SRC_FORMAT_B_BPC__MASK;
+}
+#define MDP4_PIPE_SRC_FORMAT_R_BPC__MASK			0x00000030
+#define MDP4_PIPE_SRC_FORMAT_R_BPC__SHIFT			4
+static inline uint32_t MDP4_PIPE_SRC_FORMAT_R_BPC(enum mpd4_bpc val)
+{
+	return ((val) << MDP4_PIPE_SRC_FORMAT_R_BPC__SHIFT) & MDP4_PIPE_SRC_FORMAT_R_BPC__MASK;
+}
+#define MDP4_PIPE_SRC_FORMAT_A_BPC__MASK			0x000000c0
+#define MDP4_PIPE_SRC_FORMAT_A_BPC__SHIFT			6
+static inline uint32_t MDP4_PIPE_SRC_FORMAT_A_BPC(enum mpd4_bpc_alpha val)
+{
+	return ((val) << MDP4_PIPE_SRC_FORMAT_A_BPC__SHIFT) & MDP4_PIPE_SRC_FORMAT_A_BPC__MASK;
+}
+#define MDP4_PIPE_SRC_FORMAT_ALPHA_ENABLE			0x00000100
+#define MDP4_PIPE_SRC_FORMAT_CPP__MASK				0x00000600
+#define MDP4_PIPE_SRC_FORMAT_CPP__SHIFT				9
+static inline uint32_t MDP4_PIPE_SRC_FORMAT_CPP(uint32_t val)
+{
+	return ((val) << MDP4_PIPE_SRC_FORMAT_CPP__SHIFT) & MDP4_PIPE_SRC_FORMAT_CPP__MASK;
+}
+#define MDP4_PIPE_SRC_FORMAT_ROTATED_90				0x00001000
+#define MDP4_PIPE_SRC_FORMAT_UNPACK_COUNT__MASK			0x00006000
+#define MDP4_PIPE_SRC_FORMAT_UNPACK_COUNT__SHIFT		13
+static inline uint32_t MDP4_PIPE_SRC_FORMAT_UNPACK_COUNT(uint32_t val)
+{
+	return ((val) << MDP4_PIPE_SRC_FORMAT_UNPACK_COUNT__SHIFT) & MDP4_PIPE_SRC_FORMAT_UNPACK_COUNT__MASK;
+}
+#define MDP4_PIPE_SRC_FORMAT_UNPACK_TIGHT			0x00020000
+#define MDP4_PIPE_SRC_FORMAT_UNPACK_ALIGN_MSB			0x00040000
+#define MDP4_PIPE_SRC_FORMAT_SOLID_FILL				0x00400000
+
+static inline uint32_t REG_MDP4_PIPE_SRC_UNPACK(enum mpd4_pipe i0) { return 0x00020054 + 0x10000*i0; }
+#define MDP4_PIPE_SRC_UNPACK_ELEM0__MASK			0x000000ff
+#define MDP4_PIPE_SRC_UNPACK_ELEM0__SHIFT			0
+static inline uint32_t MDP4_PIPE_SRC_UNPACK_ELEM0(uint32_t val)
+{
+	return ((val) << MDP4_PIPE_SRC_UNPACK_ELEM0__SHIFT) & MDP4_PIPE_SRC_UNPACK_ELEM0__MASK;
+}
+#define MDP4_PIPE_SRC_UNPACK_ELEM1__MASK			0x0000ff00
+#define MDP4_PIPE_SRC_UNPACK_ELEM1__SHIFT			8
+static inline uint32_t MDP4_PIPE_SRC_UNPACK_ELEM1(uint32_t val)
+{
+	return ((val) << MDP4_PIPE_SRC_UNPACK_ELEM1__SHIFT) & MDP4_PIPE_SRC_UNPACK_ELEM1__MASK;
+}
+#define MDP4_PIPE_SRC_UNPACK_ELEM2__MASK			0x00ff0000
+#define MDP4_PIPE_SRC_UNPACK_ELEM2__SHIFT			16
+static inline uint32_t MDP4_PIPE_SRC_UNPACK_ELEM2(uint32_t val)
+{
+	return ((val) << MDP4_PIPE_SRC_UNPACK_ELEM2__SHIFT) & MDP4_PIPE_SRC_UNPACK_ELEM2__MASK;
+}
+#define MDP4_PIPE_SRC_UNPACK_ELEM3__MASK			0xff000000
+#define MDP4_PIPE_SRC_UNPACK_ELEM3__SHIFT			24
+static inline uint32_t MDP4_PIPE_SRC_UNPACK_ELEM3(uint32_t val)
+{
+	return ((val) << MDP4_PIPE_SRC_UNPACK_ELEM3__SHIFT) & MDP4_PIPE_SRC_UNPACK_ELEM3__MASK;
+}
+
+static inline uint32_t REG_MDP4_PIPE_OP_MODE(enum mpd4_pipe i0) { return 0x00020058 + 0x10000*i0; }
+#define MDP4_PIPE_OP_MODE_SCALEX_EN				0x00000001
+#define MDP4_PIPE_OP_MODE_SCALEY_EN				0x00000002
+#define MDP4_PIPE_OP_MODE_SRC_YCBCR				0x00000200
+#define MDP4_PIPE_OP_MODE_DST_YCBCR				0x00000400
+#define MDP4_PIPE_OP_MODE_CSC_EN				0x00000800
+#define MDP4_PIPE_OP_MODE_FLIP_LR				0x00002000
+#define MDP4_PIPE_OP_MODE_FLIP_UD				0x00004000
+#define MDP4_PIPE_OP_MODE_DITHER_EN				0x00008000
+#define MDP4_PIPE_OP_MODE_IGC_LUT_EN				0x00010000
+#define MDP4_PIPE_OP_MODE_DEINT_EN				0x00040000
+#define MDP4_PIPE_OP_MODE_DEINT_ODD_REF				0x00080000
+
+static inline uint32_t REG_MDP4_PIPE_PHASEX_STEP(enum mpd4_pipe i0) { return 0x0002005c + 0x10000*i0; }
+
+static inline uint32_t REG_MDP4_PIPE_PHASEY_STEP(enum mpd4_pipe i0) { return 0x00020060 + 0x10000*i0; }
+
+static inline uint32_t REG_MDP4_PIPE_FETCH_CONFIG(enum mpd4_pipe i0) { return 0x00021004 + 0x10000*i0; }
+
+static inline uint32_t REG_MDP4_PIPE_SOLID_COLOR(enum mpd4_pipe i0) { return 0x00021008 + 0x10000*i0; }
+
+static inline uint32_t REG_MDP4_PIPE_CSC(enum mpd4_pipe i0) { return 0x00024000 + 0x10000*i0; }
+
+
+static inline uint32_t REG_MDP4_PIPE_CSC_MV(enum mpd4_pipe i0, uint32_t i1) { return 0x00024400 + 0x10000*i0 + 0x4*i1; }
+
+static inline uint32_t REG_MDP4_PIPE_CSC_MV_VAL(enum mpd4_pipe i0, uint32_t i1) { return 0x00024400 + 0x10000*i0 + 0x4*i1; }
+
+static inline uint32_t REG_MDP4_PIPE_CSC_PRE_BV(enum mpd4_pipe i0, uint32_t i1) { return 0x00024500 + 0x10000*i0 + 0x4*i1; }
+
+static inline uint32_t REG_MDP4_PIPE_CSC_PRE_BV_VAL(enum mpd4_pipe i0, uint32_t i1) { return 0x00024500 + 0x10000*i0 + 0x4*i1; }
+
+static inline uint32_t REG_MDP4_PIPE_CSC_POST_BV(enum mpd4_pipe i0, uint32_t i1) { return 0x00024580 + 0x10000*i0 + 0x4*i1; }
+
+static inline uint32_t REG_MDP4_PIPE_CSC_POST_BV_VAL(enum mpd4_pipe i0, uint32_t i1) { return 0x00024580 + 0x10000*i0 + 0x4*i1; }
+
+static inline uint32_t REG_MDP4_PIPE_CSC_PRE_LV(enum mpd4_pipe i0, uint32_t i1) { return 0x00024600 + 0x10000*i0 + 0x4*i1; }
+
+static inline uint32_t REG_MDP4_PIPE_CSC_PRE_LV_VAL(enum mpd4_pipe i0, uint32_t i1) { return 0x00024600 + 0x10000*i0 + 0x4*i1; }
+
+static inline uint32_t REG_MDP4_PIPE_CSC_POST_LV(enum mpd4_pipe i0, uint32_t i1) { return 0x00024680 + 0x10000*i0 + 0x4*i1; }
+
+static inline uint32_t REG_MDP4_PIPE_CSC_POST_LV_VAL(enum mpd4_pipe i0, uint32_t i1) { return 0x00024680 + 0x10000*i0 + 0x4*i1; }
+
+#define REG_MDP4_LCDC						0x000c0000
+
+#define REG_MDP4_LCDC_ENABLE					0x000c0000
+
+#define REG_MDP4_LCDC_HSYNC_CTRL				0x000c0004
+#define MDP4_LCDC_HSYNC_CTRL_PULSEW__MASK			0x0000ffff
+#define MDP4_LCDC_HSYNC_CTRL_PULSEW__SHIFT			0
+static inline uint32_t MDP4_LCDC_HSYNC_CTRL_PULSEW(uint32_t val)
+{
+	return ((val) << MDP4_LCDC_HSYNC_CTRL_PULSEW__SHIFT) & MDP4_LCDC_HSYNC_CTRL_PULSEW__MASK;
+}
+#define MDP4_LCDC_HSYNC_CTRL_PERIOD__MASK			0xffff0000
+#define MDP4_LCDC_HSYNC_CTRL_PERIOD__SHIFT			16
+static inline uint32_t MDP4_LCDC_HSYNC_CTRL_PERIOD(uint32_t val)
+{
+	return ((val) << MDP4_LCDC_HSYNC_CTRL_PERIOD__SHIFT) & MDP4_LCDC_HSYNC_CTRL_PERIOD__MASK;
+}
+
+#define REG_MDP4_LCDC_VSYNC_PERIOD				0x000c0008
+
+#define REG_MDP4_LCDC_VSYNC_LEN					0x000c000c
+
+#define REG_MDP4_LCDC_DISPLAY_HCTRL				0x000c0010
+#define MDP4_LCDC_DISPLAY_HCTRL_START__MASK			0x0000ffff
+#define MDP4_LCDC_DISPLAY_HCTRL_START__SHIFT			0
+static inline uint32_t MDP4_LCDC_DISPLAY_HCTRL_START(uint32_t val)
+{
+	return ((val) << MDP4_LCDC_DISPLAY_HCTRL_START__SHIFT) & MDP4_LCDC_DISPLAY_HCTRL_START__MASK;
+}
+#define MDP4_LCDC_DISPLAY_HCTRL_END__MASK			0xffff0000
+#define MDP4_LCDC_DISPLAY_HCTRL_END__SHIFT			16
+static inline uint32_t MDP4_LCDC_DISPLAY_HCTRL_END(uint32_t val)
+{
+	return ((val) << MDP4_LCDC_DISPLAY_HCTRL_END__SHIFT) & MDP4_LCDC_DISPLAY_HCTRL_END__MASK;
+}
+
+#define REG_MDP4_LCDC_DISPLAY_VSTART				0x000c0014
+
+#define REG_MDP4_LCDC_DISPLAY_VEND				0x000c0018
+
+#define REG_MDP4_LCDC_ACTIVE_HCTL				0x000c001c
+#define MDP4_LCDC_ACTIVE_HCTL_START__MASK			0x00007fff
+#define MDP4_LCDC_ACTIVE_HCTL_START__SHIFT			0
+static inline uint32_t MDP4_LCDC_ACTIVE_HCTL_START(uint32_t val)
+{
+	return ((val) << MDP4_LCDC_ACTIVE_HCTL_START__SHIFT) & MDP4_LCDC_ACTIVE_HCTL_START__MASK;
+}
+#define MDP4_LCDC_ACTIVE_HCTL_END__MASK				0x7fff0000
+#define MDP4_LCDC_ACTIVE_HCTL_END__SHIFT			16
+static inline uint32_t MDP4_LCDC_ACTIVE_HCTL_END(uint32_t val)
+{
+	return ((val) << MDP4_LCDC_ACTIVE_HCTL_END__SHIFT) & MDP4_LCDC_ACTIVE_HCTL_END__MASK;
+}
+#define MDP4_LCDC_ACTIVE_HCTL_ACTIVE_START_X			0x80000000
+
+#define REG_MDP4_LCDC_ACTIVE_VSTART				0x000c0020
+
+#define REG_MDP4_LCDC_ACTIVE_VEND				0x000c0024
+
+#define REG_MDP4_LCDC_BORDER_CLR				0x000c0028
+
+#define REG_MDP4_LCDC_UNDERFLOW_CLR				0x000c002c
+#define MDP4_LCDC_UNDERFLOW_CLR_COLOR__MASK			0x00ffffff
+#define MDP4_LCDC_UNDERFLOW_CLR_COLOR__SHIFT			0
+static inline uint32_t MDP4_LCDC_UNDERFLOW_CLR_COLOR(uint32_t val)
+{
+	return ((val) << MDP4_LCDC_UNDERFLOW_CLR_COLOR__SHIFT) & MDP4_LCDC_UNDERFLOW_CLR_COLOR__MASK;
+}
+#define MDP4_LCDC_UNDERFLOW_CLR_ENABLE_RECOVERY			0x80000000
+
+#define REG_MDP4_LCDC_HSYNC_SKEW				0x000c0030
+
+#define REG_MDP4_LCDC_TEST_CNTL					0x000c0034
+
+#define REG_MDP4_LCDC_CTRL_POLARITY				0x000c0038
+#define MDP4_LCDC_CTRL_POLARITY_HSYNC_LOW			0x00000001
+#define MDP4_LCDC_CTRL_POLARITY_VSYNC_LOW			0x00000002
+#define MDP4_LCDC_CTRL_POLARITY_DATA_EN_LOW			0x00000004
+
+#define REG_MDP4_DTV						0x000d0000
+
+#define REG_MDP4_DTV_ENABLE					0x000d0000
+
+#define REG_MDP4_DTV_HSYNC_CTRL					0x000d0004
+#define MDP4_DTV_HSYNC_CTRL_PULSEW__MASK			0x0000ffff
+#define MDP4_DTV_HSYNC_CTRL_PULSEW__SHIFT			0
+static inline uint32_t MDP4_DTV_HSYNC_CTRL_PULSEW(uint32_t val)
+{
+	return ((val) << MDP4_DTV_HSYNC_CTRL_PULSEW__SHIFT) & MDP4_DTV_HSYNC_CTRL_PULSEW__MASK;
+}
+#define MDP4_DTV_HSYNC_CTRL_PERIOD__MASK			0xffff0000
+#define MDP4_DTV_HSYNC_CTRL_PERIOD__SHIFT			16
+static inline uint32_t MDP4_DTV_HSYNC_CTRL_PERIOD(uint32_t val)
+{
+	return ((val) << MDP4_DTV_HSYNC_CTRL_PERIOD__SHIFT) & MDP4_DTV_HSYNC_CTRL_PERIOD__MASK;
+}
+
+#define REG_MDP4_DTV_VSYNC_PERIOD				0x000d0008
+
+#define REG_MDP4_DTV_VSYNC_LEN					0x000d000c
+
+#define REG_MDP4_DTV_DISPLAY_HCTRL				0x000d0018
+#define MDP4_DTV_DISPLAY_HCTRL_START__MASK			0x0000ffff
+#define MDP4_DTV_DISPLAY_HCTRL_START__SHIFT			0
+static inline uint32_t MDP4_DTV_DISPLAY_HCTRL_START(uint32_t val)
+{
+	return ((val) << MDP4_DTV_DISPLAY_HCTRL_START__SHIFT) & MDP4_DTV_DISPLAY_HCTRL_START__MASK;
+}
+#define MDP4_DTV_DISPLAY_HCTRL_END__MASK			0xffff0000
+#define MDP4_DTV_DISPLAY_HCTRL_END__SHIFT			16
+static inline uint32_t MDP4_DTV_DISPLAY_HCTRL_END(uint32_t val)
+{
+	return ((val) << MDP4_DTV_DISPLAY_HCTRL_END__SHIFT) & MDP4_DTV_DISPLAY_HCTRL_END__MASK;
+}
+
+#define REG_MDP4_DTV_DISPLAY_VSTART				0x000d001c
+
+#define REG_MDP4_DTV_DISPLAY_VEND				0x000d0020
+
+#define REG_MDP4_DTV_ACTIVE_HCTL				0x000d002c
+#define MDP4_DTV_ACTIVE_HCTL_START__MASK			0x00007fff
+#define MDP4_DTV_ACTIVE_HCTL_START__SHIFT			0
+static inline uint32_t MDP4_DTV_ACTIVE_HCTL_START(uint32_t val)
+{
+	return ((val) << MDP4_DTV_ACTIVE_HCTL_START__SHIFT) & MDP4_DTV_ACTIVE_HCTL_START__MASK;
+}
+#define MDP4_DTV_ACTIVE_HCTL_END__MASK				0x7fff0000
+#define MDP4_DTV_ACTIVE_HCTL_END__SHIFT				16
+static inline uint32_t MDP4_DTV_ACTIVE_HCTL_END(uint32_t val)
+{
+	return ((val) << MDP4_DTV_ACTIVE_HCTL_END__SHIFT) & MDP4_DTV_ACTIVE_HCTL_END__MASK;
+}
+#define MDP4_DTV_ACTIVE_HCTL_ACTIVE_START_X			0x80000000
+
+#define REG_MDP4_DTV_ACTIVE_VSTART				0x000d0030
+
+#define REG_MDP4_DTV_ACTIVE_VEND				0x000d0038
+
+#define REG_MDP4_DTV_BORDER_CLR					0x000d0040
+
+#define REG_MDP4_DTV_UNDERFLOW_CLR				0x000d0044
+#define MDP4_DTV_UNDERFLOW_CLR_COLOR__MASK			0x00ffffff
+#define MDP4_DTV_UNDERFLOW_CLR_COLOR__SHIFT			0
+static inline uint32_t MDP4_DTV_UNDERFLOW_CLR_COLOR(uint32_t val)
+{
+	return ((val) << MDP4_DTV_UNDERFLOW_CLR_COLOR__SHIFT) & MDP4_DTV_UNDERFLOW_CLR_COLOR__MASK;
+}
+#define MDP4_DTV_UNDERFLOW_CLR_ENABLE_RECOVERY			0x80000000
+
+#define REG_MDP4_DTV_HSYNC_SKEW					0x000d0048
+
+#define REG_MDP4_DTV_TEST_CNTL					0x000d004c
+
+#define REG_MDP4_DTV_CTRL_POLARITY				0x000d0050
+#define MDP4_DTV_CTRL_POLARITY_HSYNC_LOW			0x00000001
+#define MDP4_DTV_CTRL_POLARITY_VSYNC_LOW			0x00000002
+#define MDP4_DTV_CTRL_POLARITY_DATA_EN_LOW			0x00000004
+
+#define REG_MDP4_DSI						0x000e0000
+
+#define REG_MDP4_DSI_ENABLE					0x000e0000
+
+#define REG_MDP4_DSI_HSYNC_CTRL					0x000e0004
+#define MDP4_DSI_HSYNC_CTRL_PULSEW__MASK			0x0000ffff
+#define MDP4_DSI_HSYNC_CTRL_PULSEW__SHIFT			0
+static inline uint32_t MDP4_DSI_HSYNC_CTRL_PULSEW(uint32_t val)
+{
+	return ((val) << MDP4_DSI_HSYNC_CTRL_PULSEW__SHIFT) & MDP4_DSI_HSYNC_CTRL_PULSEW__MASK;
+}
+#define MDP4_DSI_HSYNC_CTRL_PERIOD__MASK			0xffff0000
+#define MDP4_DSI_HSYNC_CTRL_PERIOD__SHIFT			16
+static inline uint32_t MDP4_DSI_HSYNC_CTRL_PERIOD(uint32_t val)
+{
+	return ((val) << MDP4_DSI_HSYNC_CTRL_PERIOD__SHIFT) & MDP4_DSI_HSYNC_CTRL_PERIOD__MASK;
+}
+
+#define REG_MDP4_DSI_VSYNC_PERIOD				0x000e0008
+
+#define REG_MDP4_DSI_VSYNC_LEN					0x000e000c
+
+#define REG_MDP4_DSI_DISPLAY_HCTRL				0x000e0010
+#define MDP4_DSI_DISPLAY_HCTRL_START__MASK			0x0000ffff
+#define MDP4_DSI_DISPLAY_HCTRL_START__SHIFT			0
+static inline uint32_t MDP4_DSI_DISPLAY_HCTRL_START(uint32_t val)
+{
+	return ((val) << MDP4_DSI_DISPLAY_HCTRL_START__SHIFT) & MDP4_DSI_DISPLAY_HCTRL_START__MASK;
+}
+#define MDP4_DSI_DISPLAY_HCTRL_END__MASK			0xffff0000
+#define MDP4_DSI_DISPLAY_HCTRL_END__SHIFT			16
+static inline uint32_t MDP4_DSI_DISPLAY_HCTRL_END(uint32_t val)
+{
+	return ((val) << MDP4_DSI_DISPLAY_HCTRL_END__SHIFT) & MDP4_DSI_DISPLAY_HCTRL_END__MASK;
+}
+
+#define REG_MDP4_DSI_DISPLAY_VSTART				0x000e0014
+
+#define REG_MDP4_DSI_DISPLAY_VEND				0x000e0018
+
+#define REG_MDP4_DSI_ACTIVE_HCTL				0x000e001c
+#define MDP4_DSI_ACTIVE_HCTL_START__MASK			0x00007fff
+#define MDP4_DSI_ACTIVE_HCTL_START__SHIFT			0
+static inline uint32_t MDP4_DSI_ACTIVE_HCTL_START(uint32_t val)
+{
+	return ((val) << MDP4_DSI_ACTIVE_HCTL_START__SHIFT) & MDP4_DSI_ACTIVE_HCTL_START__MASK;
+}
+#define MDP4_DSI_ACTIVE_HCTL_END__MASK				0x7fff0000
+#define MDP4_DSI_ACTIVE_HCTL_END__SHIFT				16
+static inline uint32_t MDP4_DSI_ACTIVE_HCTL_END(uint32_t val)
+{
+	return ((val) << MDP4_DSI_ACTIVE_HCTL_END__SHIFT) & MDP4_DSI_ACTIVE_HCTL_END__MASK;
+}
+#define MDP4_DSI_ACTIVE_HCTL_ACTIVE_START_X			0x80000000
+
+#define REG_MDP4_DSI_ACTIVE_VSTART				0x000e0020
+
+#define REG_MDP4_DSI_ACTIVE_VEND				0x000e0024
+
+#define REG_MDP4_DSI_BORDER_CLR					0x000e0028
+
+#define REG_MDP4_DSI_UNDERFLOW_CLR				0x000e002c
+#define MDP4_DSI_UNDERFLOW_CLR_COLOR__MASK			0x00ffffff
+#define MDP4_DSI_UNDERFLOW_CLR_COLOR__SHIFT			0
+static inline uint32_t MDP4_DSI_UNDERFLOW_CLR_COLOR(uint32_t val)
+{
+	return ((val) << MDP4_DSI_UNDERFLOW_CLR_COLOR__SHIFT) & MDP4_DSI_UNDERFLOW_CLR_COLOR__MASK;
+}
+#define MDP4_DSI_UNDERFLOW_CLR_ENABLE_RECOVERY			0x80000000
+
+#define REG_MDP4_DSI_HSYNC_SKEW					0x000e0030
+
+#define REG_MDP4_DSI_TEST_CNTL					0x000e0034
+
+#define REG_MDP4_DSI_CTRL_POLARITY				0x000e0038
+#define MDP4_DSI_CTRL_POLARITY_HSYNC_LOW			0x00000001
+#define MDP4_DSI_CTRL_POLARITY_VSYNC_LOW			0x00000002
+#define MDP4_DSI_CTRL_POLARITY_DATA_EN_LOW			0x00000004
+
+
+#endif /* MDP4_XML */
diff --git a/drivers/gpu/drm/msm/mdp4/mdp4_crtc.c b/drivers/gpu/drm/msm/mdp4/mdp4_crtc.c
new file mode 100644
index 000000000000..de6bea297cda
--- /dev/null
+++ b/drivers/gpu/drm/msm/mdp4/mdp4_crtc.c
@@ -0,0 +1,685 @@
+/*
+ * Copyright (C) 2013 Red Hat
+ * Author: Rob Clark <robdclark@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include "mdp4_kms.h"
+
+#include <drm/drm_mode.h>
+#include "drm_crtc.h"
+#include "drm_crtc_helper.h"
+#include "drm_flip_work.h"
+
+struct mdp4_crtc {
+	struct drm_crtc base;
+	char name[8];
+	struct drm_plane *plane;
+	int id;
+	int ovlp;
+	enum mdp4_dma dma;
+	bool enabled;
+
+	/* which mixer/encoder we route output to: */
+	int mixer;
+
+	struct {
+		spinlock_t lock;
+		bool stale;
+		uint32_t width, height;
+
+		/* next cursor to scan-out: */
+		uint32_t next_iova;
+		struct drm_gem_object *next_bo;
+
+		/* current cursor being scanned out: */
+		struct drm_gem_object *scanout_bo;
+	} cursor;
+
+
+	/* if there is a pending flip, these will be non-null: */
+	struct drm_pending_vblank_event *event;
+	struct work_struct pageflip_work;
+
+	/* the fb that we currently hold a scanout ref to: */
+	struct drm_framebuffer *fb;
+
+	/* for unref'ing framebuffers after scanout completes: */
+	struct drm_flip_work unref_fb_work;
+
+	/* for unref'ing cursor bo's after scanout completes: */
+	struct drm_flip_work unref_cursor_work;
+
+	struct mdp4_irq vblank;
+	struct mdp4_irq err;
+};
+#define to_mdp4_crtc(x) container_of(x, struct mdp4_crtc, base)
+
+static struct mdp4_kms *get_kms(struct drm_crtc *crtc)
+{
+	struct msm_drm_private *priv = crtc->dev->dev_private;
+	return to_mdp4_kms(priv->kms);
+}
+
+static void update_fb(struct drm_crtc *crtc, bool async,
+		struct drm_framebuffer *new_fb)
+{
+	struct mdp4_crtc *mdp4_crtc = to_mdp4_crtc(crtc);
+	struct drm_framebuffer *old_fb = mdp4_crtc->fb;
+
+	if (old_fb)
+		drm_flip_work_queue(&mdp4_crtc->unref_fb_work, old_fb);
+
+	/* grab reference to incoming scanout fb: */
+	drm_framebuffer_reference(new_fb);
+	mdp4_crtc->base.fb = new_fb;
+	mdp4_crtc->fb = new_fb;
+
+	if (!async) {
+		/* enable vblank to pick up the old_fb */
+		mdp4_irq_register(get_kms(crtc), &mdp4_crtc->vblank);
+	}
+}
+
+static void complete_flip(struct drm_crtc *crtc, bool canceled)
+{
+	struct mdp4_crtc *mdp4_crtc = to_mdp4_crtc(crtc);
+	struct drm_device *dev = crtc->dev;
+	struct drm_pending_vblank_event *event;
+	unsigned long flags;
+
+	spin_lock_irqsave(&dev->event_lock, flags);
+	event = mdp4_crtc->event;
+	if (event) {
+		mdp4_crtc->event = NULL;
+		if (canceled)
+			event->base.destroy(&event->base);
+		else
+			drm_send_vblank_event(dev, mdp4_crtc->id, event);
+	}
+	spin_unlock_irqrestore(&dev->event_lock, flags);
+}
+
+static void crtc_flush(struct drm_crtc *crtc)
+{
+	struct mdp4_crtc *mdp4_crtc = to_mdp4_crtc(crtc);
+	struct mdp4_kms *mdp4_kms = get_kms(crtc);
+	uint32_t flush = 0;
+
+	flush |= pipe2flush(mdp4_plane_pipe(mdp4_crtc->plane));
+	flush |= ovlp2flush(mdp4_crtc->ovlp);
+
+	DBG("%s: flush=%08x", mdp4_crtc->name, flush);
+
+	mdp4_write(mdp4_kms, REG_MDP4_OVERLAY_FLUSH, flush);
+}
+
+static void pageflip_worker(struct work_struct *work)
+{
+	struct mdp4_crtc *mdp4_crtc =
+		container_of(work, struct mdp4_crtc, pageflip_work);
+	struct drm_crtc *crtc = &mdp4_crtc->base;
+
+	mdp4_plane_set_scanout(mdp4_crtc->plane, crtc->fb);
+	crtc_flush(crtc);
+
+	/* enable vblank to complete flip: */
+	mdp4_irq_register(get_kms(crtc), &mdp4_crtc->vblank);
+}
+
+static void unref_fb_worker(struct drm_flip_work *work, void *val)
+{
+	struct mdp4_crtc *mdp4_crtc =
+		container_of(work, struct mdp4_crtc, unref_fb_work);
+	struct drm_device *dev = mdp4_crtc->base.dev;
+
+	mutex_lock(&dev->mode_config.mutex);
+	drm_framebuffer_unreference(val);
+	mutex_unlock(&dev->mode_config.mutex);
+}
+
+static void unref_cursor_worker(struct drm_flip_work *work, void *val)
+{
+	struct mdp4_crtc *mdp4_crtc =
+		container_of(work, struct mdp4_crtc, unref_cursor_work);
+	struct mdp4_kms *mdp4_kms = get_kms(&mdp4_crtc->base);
+
+	msm_gem_put_iova(val, mdp4_kms->id);
+	drm_gem_object_unreference_unlocked(val);
+}
+
+static void mdp4_crtc_destroy(struct drm_crtc *crtc)
+{
+	struct mdp4_crtc *mdp4_crtc = to_mdp4_crtc(crtc);
+
+	mdp4_crtc->plane->funcs->destroy(mdp4_crtc->plane);
+
+	drm_crtc_cleanup(crtc);
+	drm_flip_work_cleanup(&mdp4_crtc->unref_fb_work);
+	drm_flip_work_cleanup(&mdp4_crtc->unref_cursor_work);
+
+	kfree(mdp4_crtc);
+}
+
+static void mdp4_crtc_dpms(struct drm_crtc *crtc, int mode)
+{
+	struct mdp4_crtc *mdp4_crtc = to_mdp4_crtc(crtc);
+	struct mdp4_kms *mdp4_kms = get_kms(crtc);
+	bool enabled = (mode == DRM_MODE_DPMS_ON);
+
+	DBG("%s: mode=%d", mdp4_crtc->name, mode);
+
+	if (enabled != mdp4_crtc->enabled) {
+		if (enabled) {
+			mdp4_enable(mdp4_kms);
+			mdp4_irq_register(mdp4_kms, &mdp4_crtc->err);
+		} else {
+			mdp4_irq_unregister(mdp4_kms, &mdp4_crtc->err);
+			mdp4_disable(mdp4_kms);
+		}
+		mdp4_crtc->enabled = enabled;
+	}
+}
+
+static bool mdp4_crtc_mode_fixup(struct drm_crtc *crtc,
+		const struct drm_display_mode *mode,
+		struct drm_display_mode *adjusted_mode)
+{
+	return true;
+}
+
+static void blend_setup(struct drm_crtc *crtc)
+{
+	struct mdp4_crtc *mdp4_crtc = to_mdp4_crtc(crtc);
+	struct mdp4_kms *mdp4_kms = get_kms(crtc);
+	int i, ovlp = mdp4_crtc->ovlp;
+	uint32_t mixer_cfg = 0;
+
+	/*
+	 * This probably would also need to be triggered by any attached
+	 * plane when it changes.. for now since we are only using a single
+	 * private plane, the configuration is hard-coded:
+	 */
+
+	mdp4_write(mdp4_kms, REG_MDP4_OVLP_TRANSP_LOW0(ovlp), 0);
+	mdp4_write(mdp4_kms, REG_MDP4_OVLP_TRANSP_LOW1(ovlp), 0);
+	mdp4_write(mdp4_kms, REG_MDP4_OVLP_TRANSP_HIGH0(ovlp), 0);
+	mdp4_write(mdp4_kms, REG_MDP4_OVLP_TRANSP_HIGH1(ovlp), 0);
+
+	for (i = 0; i < 4; i++) {
+		mdp4_write(mdp4_kms, REG_MDP4_OVLP_STAGE_FG_ALPHA(ovlp, i), 0);
+		mdp4_write(mdp4_kms, REG_MDP4_OVLP_STAGE_BG_ALPHA(ovlp, i), 0);
+		mdp4_write(mdp4_kms, REG_MDP4_OVLP_STAGE_OP(ovlp, i),
+				MDP4_OVLP_STAGE_OP_FG_ALPHA(FG_CONST) |
+				MDP4_OVLP_STAGE_OP_BG_ALPHA(BG_CONST));
+		mdp4_write(mdp4_kms, REG_MDP4_OVLP_STAGE_CO3(ovlp, i), 0);
+		mdp4_write(mdp4_kms, REG_MDP4_OVLP_STAGE_TRANSP_LOW0(ovlp, i), 0);
+		mdp4_write(mdp4_kms, REG_MDP4_OVLP_STAGE_TRANSP_LOW1(ovlp, i), 0);
+		mdp4_write(mdp4_kms, REG_MDP4_OVLP_STAGE_TRANSP_HIGH0(ovlp, i), 0);
+		mdp4_write(mdp4_kms, REG_MDP4_OVLP_STAGE_TRANSP_HIGH1(ovlp, i), 0);
+	}
+
+	/* TODO single register for all CRTCs, so this won't work properly
+	 * when multiple CRTCs are active..
+	 */
+	switch (mdp4_plane_pipe(mdp4_crtc->plane)) {
+	case VG1:
+		mixer_cfg = MDP4_LAYERMIXER_IN_CFG_PIPE0(STAGE_BASE) |
+			COND(mdp4_crtc->mixer == 1, MDP4_LAYERMIXER_IN_CFG_PIPE0_MIXER1);
+		break;
+	case VG2:
+		mixer_cfg = MDP4_LAYERMIXER_IN_CFG_PIPE1(STAGE_BASE) |
+			COND(mdp4_crtc->mixer == 1, MDP4_LAYERMIXER_IN_CFG_PIPE1_MIXER1);
+		break;
+	case RGB1:
+		mixer_cfg = MDP4_LAYERMIXER_IN_CFG_PIPE2(STAGE_BASE) |
+			COND(mdp4_crtc->mixer == 1, MDP4_LAYERMIXER_IN_CFG_PIPE2_MIXER1);
+		break;
+	case RGB2:
+		mixer_cfg = MDP4_LAYERMIXER_IN_CFG_PIPE3(STAGE_BASE) |
+			COND(mdp4_crtc->mixer == 1, MDP4_LAYERMIXER_IN_CFG_PIPE3_MIXER1);
+		break;
+	case RGB3:
+		mixer_cfg = MDP4_LAYERMIXER_IN_CFG_PIPE4(STAGE_BASE) |
+			COND(mdp4_crtc->mixer == 1, MDP4_LAYERMIXER_IN_CFG_PIPE4_MIXER1);
+		break;
+	case VG3:
+		mixer_cfg = MDP4_LAYERMIXER_IN_CFG_PIPE5(STAGE_BASE) |
+			COND(mdp4_crtc->mixer == 1, MDP4_LAYERMIXER_IN_CFG_PIPE5_MIXER1);
+		break;
+	case VG4:
+		mixer_cfg = MDP4_LAYERMIXER_IN_CFG_PIPE6(STAGE_BASE) |
+			COND(mdp4_crtc->mixer == 1, MDP4_LAYERMIXER_IN_CFG_PIPE6_MIXER1);
+		break;
+	default:
+		WARN_ON("invalid pipe");
+		break;
+	}
+	mdp4_write(mdp4_kms, REG_MDP4_LAYERMIXER_IN_CFG, mixer_cfg);
+}
+
+static int mdp4_crtc_mode_set(struct drm_crtc *crtc,
+		struct drm_display_mode *mode,
+		struct drm_display_mode *adjusted_mode,
+		int x, int y,
+		struct drm_framebuffer *old_fb)
+{
+	struct mdp4_crtc *mdp4_crtc = to_mdp4_crtc(crtc);
+	struct mdp4_kms *mdp4_kms = get_kms(crtc);
+	enum mdp4_dma dma = mdp4_crtc->dma;
+	int ret, ovlp = mdp4_crtc->ovlp;
+
+	mode = adjusted_mode;
+
+	DBG("%s: set mode: %d:\"%s\" %d %d %d %d %d %d %d %d %d %d 0x%x 0x%x",
+			mdp4_crtc->name, mode->base.id, mode->name,
+			mode->vrefresh, mode->clock,
+			mode->hdisplay, mode->hsync_start,
+			mode->hsync_end, mode->htotal,
+			mode->vdisplay, mode->vsync_start,
+			mode->vsync_end, mode->vtotal,
+			mode->type, mode->flags);
+
+	mdp4_write(mdp4_kms, REG_MDP4_DMA_SRC_SIZE(dma),
+			MDP4_DMA_SRC_SIZE_WIDTH(mode->hdisplay) |
+			MDP4_DMA_SRC_SIZE_HEIGHT(mode->vdisplay));
+
+	/* take data from pipe: */
+	mdp4_write(mdp4_kms, REG_MDP4_DMA_SRC_BASE(dma), 0);
+	mdp4_write(mdp4_kms, REG_MDP4_DMA_SRC_STRIDE(dma),
+			crtc->fb->pitches[0]);
+	mdp4_write(mdp4_kms, REG_MDP4_DMA_DST_SIZE(dma),
+			MDP4_DMA_DST_SIZE_WIDTH(0) |
+			MDP4_DMA_DST_SIZE_HEIGHT(0));
+
+	mdp4_write(mdp4_kms, REG_MDP4_OVLP_BASE(ovlp), 0);
+	mdp4_write(mdp4_kms, REG_MDP4_OVLP_SIZE(ovlp),
+			MDP4_OVLP_SIZE_WIDTH(mode->hdisplay) |
+			MDP4_OVLP_SIZE_HEIGHT(mode->vdisplay));
+	mdp4_write(mdp4_kms, REG_MDP4_OVLP_STRIDE(ovlp),
+			crtc->fb->pitches[0]);
+
+	mdp4_write(mdp4_kms, REG_MDP4_OVLP_CFG(ovlp), 1);
+
+	update_fb(crtc, false, crtc->fb);
+
+	ret = mdp4_plane_mode_set(mdp4_crtc->plane, crtc, crtc->fb,
+			0, 0, mode->hdisplay, mode->vdisplay,
+			x << 16, y << 16,
+			mode->hdisplay << 16, mode->vdisplay << 16);
+	if (ret) {
+		dev_err(crtc->dev->dev, "%s: failed to set mode on plane: %d\n",
+				mdp4_crtc->name, ret);
+		return ret;
+	}
+
+	if (dma == DMA_E) {
+		mdp4_write(mdp4_kms, REG_MDP4_DMA_E_QUANT(0), 0x00ff0000);
+		mdp4_write(mdp4_kms, REG_MDP4_DMA_E_QUANT(1), 0x00ff0000);
+		mdp4_write(mdp4_kms, REG_MDP4_DMA_E_QUANT(2), 0x00ff0000);
+	}
+
+	return 0;
+}
+
+static void mdp4_crtc_prepare(struct drm_crtc *crtc)
+{
+	struct mdp4_crtc *mdp4_crtc = to_mdp4_crtc(crtc);
+	DBG("%s", mdp4_crtc->name);
+	/* make sure we hold a ref to mdp clks while setting up mode: */
+	mdp4_enable(get_kms(crtc));
+	mdp4_crtc_dpms(crtc, DRM_MODE_DPMS_OFF);
+}
+
+static void mdp4_crtc_commit(struct drm_crtc *crtc)
+{
+	mdp4_crtc_dpms(crtc, DRM_MODE_DPMS_ON);
+	crtc_flush(crtc);
+	/* drop the ref to mdp clk's that we got in prepare: */
+	mdp4_disable(get_kms(crtc));
+}
+
+static int mdp4_crtc_mode_set_base(struct drm_crtc *crtc, int x, int y,
+		struct drm_framebuffer *old_fb)
+{
+	struct mdp4_crtc *mdp4_crtc = to_mdp4_crtc(crtc);
+	struct drm_plane *plane = mdp4_crtc->plane;
+	struct drm_display_mode *mode = &crtc->mode;
+
+	update_fb(crtc, false, crtc->fb);
+
+	return mdp4_plane_mode_set(plane, crtc, crtc->fb,
+			0, 0, mode->hdisplay, mode->vdisplay,
+			x << 16, y << 16,
+			mode->hdisplay << 16, mode->vdisplay << 16);
+}
+
+static void mdp4_crtc_load_lut(struct drm_crtc *crtc)
+{
+}
+
+static int mdp4_crtc_page_flip(struct drm_crtc *crtc,
+		struct drm_framebuffer *new_fb,
+		struct drm_pending_vblank_event *event,
+		uint32_t page_flip_flags)
+{
+	struct mdp4_crtc *mdp4_crtc = to_mdp4_crtc(crtc);
+	struct drm_device *dev = crtc->dev;
+	struct drm_gem_object *obj;
+
+	if (mdp4_crtc->event) {
+		dev_err(dev->dev, "already pending flip!\n");
+		return -EBUSY;
+	}
+
+	obj = msm_framebuffer_bo(new_fb, 0);
+
+	mdp4_crtc->event = event;
+	update_fb(crtc, true, new_fb);
+
+	return msm_gem_queue_inactive_work(obj,
+			&mdp4_crtc->pageflip_work);
+}
+
+static int mdp4_crtc_set_property(struct drm_crtc *crtc,
+		struct drm_property *property, uint64_t val)
+{
+	// XXX
+	return -EINVAL;
+}
+
+#define CURSOR_WIDTH 64
+#define CURSOR_HEIGHT 64
+
+/* called from IRQ to update cursor related registers (if needed).  The
+ * cursor registers, other than x/y position, appear not to be double
+ * buffered, and changing them other than from vblank seems to trigger
+ * underflow.
+ */
+static void update_cursor(struct drm_crtc *crtc)
+{
+	struct mdp4_crtc *mdp4_crtc = to_mdp4_crtc(crtc);
+	enum mdp4_dma dma = mdp4_crtc->dma;
+	unsigned long flags;
+
+	spin_lock_irqsave(&mdp4_crtc->cursor.lock, flags);
+	if (mdp4_crtc->cursor.stale) {
+		struct mdp4_kms *mdp4_kms = get_kms(crtc);
+		struct drm_gem_object *next_bo = mdp4_crtc->cursor.next_bo;
+		struct drm_gem_object *prev_bo = mdp4_crtc->cursor.scanout_bo;
+		uint32_t iova = mdp4_crtc->cursor.next_iova;
+
+		if (next_bo) {
+			/* take a obj ref + iova ref when we start scanning out: */
+			drm_gem_object_reference(next_bo);
+			msm_gem_get_iova_locked(next_bo, mdp4_kms->id, &iova);
+
+			/* enable cursor: */
+			mdp4_write(mdp4_kms, REG_MDP4_DMA_CURSOR_SIZE(dma),
+					MDP4_DMA_CURSOR_SIZE_WIDTH(mdp4_crtc->cursor.width) |
+					MDP4_DMA_CURSOR_SIZE_HEIGHT(mdp4_crtc->cursor.height));
+			mdp4_write(mdp4_kms, REG_MDP4_DMA_CURSOR_BASE(dma), iova);
+			mdp4_write(mdp4_kms, REG_MDP4_DMA_CURSOR_BLEND_CONFIG(dma),
+					MDP4_DMA_CURSOR_BLEND_CONFIG_FORMAT(CURSOR_ARGB) |
+					MDP4_DMA_CURSOR_BLEND_CONFIG_CURSOR_EN);
+		} else {
+			/* disable cursor: */
+			mdp4_write(mdp4_kms, REG_MDP4_DMA_CURSOR_BASE(dma), 0);
+			mdp4_write(mdp4_kms, REG_MDP4_DMA_CURSOR_BLEND_CONFIG(dma),
+					MDP4_DMA_CURSOR_BLEND_CONFIG_FORMAT(CURSOR_ARGB));
+		}
+
+		/* and drop the iova ref + obj rev when done scanning out: */
+		if (prev_bo)
+			drm_flip_work_queue(&mdp4_crtc->unref_cursor_work, prev_bo);
+
+		mdp4_crtc->cursor.scanout_bo = next_bo;
+		mdp4_crtc->cursor.stale = false;
+	}
+	spin_unlock_irqrestore(&mdp4_crtc->cursor.lock, flags);
+}
+
+static int mdp4_crtc_cursor_set(struct drm_crtc *crtc,
+		struct drm_file *file_priv, uint32_t handle,
+		uint32_t width, uint32_t height)
+{
+	struct mdp4_crtc *mdp4_crtc = to_mdp4_crtc(crtc);
+	struct mdp4_kms *mdp4_kms = get_kms(crtc);
+	struct drm_device *dev = crtc->dev;
+	struct drm_gem_object *cursor_bo, *old_bo;
+	unsigned long flags;
+	uint32_t iova;
+	int ret;
+
+	if ((width > CURSOR_WIDTH) || (height > CURSOR_HEIGHT)) {
+		dev_err(dev->dev, "bad cursor size: %dx%d\n", width, height);
+		return -EINVAL;
+	}
+
+	if (handle) {
+		cursor_bo = drm_gem_object_lookup(dev, file_priv, handle);
+		if (!cursor_bo)
+			return -ENOENT;
+	} else {
+		cursor_bo = NULL;
+	}
+
+	if (cursor_bo) {
+		ret = msm_gem_get_iova(cursor_bo, mdp4_kms->id, &iova);
+		if (ret)
+			goto fail;
+	} else {
+		iova = 0;
+	}
+
+	spin_lock_irqsave(&mdp4_crtc->cursor.lock, flags);
+	old_bo = mdp4_crtc->cursor.next_bo;
+	mdp4_crtc->cursor.next_bo   = cursor_bo;
+	mdp4_crtc->cursor.next_iova = iova;
+	mdp4_crtc->cursor.width     = width;
+	mdp4_crtc->cursor.height    = height;
+	mdp4_crtc->cursor.stale     = true;
+	spin_unlock_irqrestore(&mdp4_crtc->cursor.lock, flags);
+
+	if (old_bo) {
+		/* drop our previous reference: */
+		msm_gem_put_iova(old_bo, mdp4_kms->id);
+		drm_gem_object_unreference_unlocked(old_bo);
+	}
+
+	return 0;
+
+fail:
+	drm_gem_object_unreference_unlocked(cursor_bo);
+	return ret;
+}
+
+static int mdp4_crtc_cursor_move(struct drm_crtc *crtc, int x, int y)
+{
+	struct mdp4_crtc *mdp4_crtc = to_mdp4_crtc(crtc);
+	struct mdp4_kms *mdp4_kms = get_kms(crtc);
+	enum mdp4_dma dma = mdp4_crtc->dma;
+
+	mdp4_write(mdp4_kms, REG_MDP4_DMA_CURSOR_POS(dma),
+			MDP4_DMA_CURSOR_POS_X(x) |
+			MDP4_DMA_CURSOR_POS_Y(y));
+
+	return 0;
+}
+
+static const struct drm_crtc_funcs mdp4_crtc_funcs = {
+	.set_config = drm_crtc_helper_set_config,
+	.destroy = mdp4_crtc_destroy,
+	.page_flip = mdp4_crtc_page_flip,
+	.set_property = mdp4_crtc_set_property,
+	.cursor_set = mdp4_crtc_cursor_set,
+	.cursor_move = mdp4_crtc_cursor_move,
+};
+
+static const struct drm_crtc_helper_funcs mdp4_crtc_helper_funcs = {
+	.dpms = mdp4_crtc_dpms,
+	.mode_fixup = mdp4_crtc_mode_fixup,
+	.mode_set = mdp4_crtc_mode_set,
+	.prepare = mdp4_crtc_prepare,
+	.commit = mdp4_crtc_commit,
+	.mode_set_base = mdp4_crtc_mode_set_base,
+	.load_lut = mdp4_crtc_load_lut,
+};
+
+static void mdp4_crtc_vblank_irq(struct mdp4_irq *irq, uint32_t irqstatus)
+{
+	struct mdp4_crtc *mdp4_crtc = container_of(irq, struct mdp4_crtc, vblank);
+	struct drm_crtc *crtc = &mdp4_crtc->base;
+	struct msm_drm_private *priv = crtc->dev->dev_private;
+
+	update_cursor(crtc);
+	complete_flip(crtc, false);
+	mdp4_irq_unregister(get_kms(crtc), &mdp4_crtc->vblank);
+
+	drm_flip_work_commit(&mdp4_crtc->unref_fb_work, priv->wq);
+	drm_flip_work_commit(&mdp4_crtc->unref_cursor_work, priv->wq);
+}
+
+static void mdp4_crtc_err_irq(struct mdp4_irq *irq, uint32_t irqstatus)
+{
+	struct mdp4_crtc *mdp4_crtc = container_of(irq, struct mdp4_crtc, err);
+	struct drm_crtc *crtc = &mdp4_crtc->base;
+	DBG("%s: error: %08x", mdp4_crtc->name, irqstatus);
+	crtc_flush(crtc);
+}
+
+uint32_t mdp4_crtc_vblank(struct drm_crtc *crtc)
+{
+	struct mdp4_crtc *mdp4_crtc = to_mdp4_crtc(crtc);
+	return mdp4_crtc->vblank.irqmask;
+}
+
+void mdp4_crtc_cancel_pending_flip(struct drm_crtc *crtc)
+{
+	complete_flip(crtc, true);
+}
+
+/* set dma config, ie. the format the encoder wants. */
+void mdp4_crtc_set_config(struct drm_crtc *crtc, uint32_t config)
+{
+	struct mdp4_crtc *mdp4_crtc = to_mdp4_crtc(crtc);
+	struct mdp4_kms *mdp4_kms = get_kms(crtc);
+
+	mdp4_write(mdp4_kms, REG_MDP4_DMA_CONFIG(mdp4_crtc->dma), config);
+}
+
+/* set interface for routing crtc->encoder: */
+void mdp4_crtc_set_intf(struct drm_crtc *crtc, enum mdp4_intf intf)
+{
+	struct mdp4_crtc *mdp4_crtc = to_mdp4_crtc(crtc);
+	struct mdp4_kms *mdp4_kms = get_kms(crtc);
+	uint32_t intf_sel;
+
+	intf_sel = mdp4_read(mdp4_kms, REG_MDP4_DISP_INTF_SEL);
+
+	switch (mdp4_crtc->dma) {
+	case DMA_P:
+		intf_sel &= ~MDP4_DISP_INTF_SEL_PRIM__MASK;
+		intf_sel |= MDP4_DISP_INTF_SEL_PRIM(intf);
+		break;
+	case DMA_S:
+		intf_sel &= ~MDP4_DISP_INTF_SEL_SEC__MASK;
+		intf_sel |= MDP4_DISP_INTF_SEL_SEC(intf);
+		break;
+	case DMA_E:
+		intf_sel &= ~MDP4_DISP_INTF_SEL_EXT__MASK;
+		intf_sel |= MDP4_DISP_INTF_SEL_EXT(intf);
+		break;
+	}
+
+	if (intf == INTF_DSI_VIDEO) {
+		intf_sel &= ~MDP4_DISP_INTF_SEL_DSI_CMD;
+		intf_sel |= MDP4_DISP_INTF_SEL_DSI_VIDEO;
+		mdp4_crtc->mixer = 0;
+	} else if (intf == INTF_DSI_CMD) {
+		intf_sel &= ~MDP4_DISP_INTF_SEL_DSI_VIDEO;
+		intf_sel |= MDP4_DISP_INTF_SEL_DSI_CMD;
+		mdp4_crtc->mixer = 0;
+	} else if (intf == INTF_LCDC_DTV){
+		mdp4_crtc->mixer = 1;
+	}
+
+	blend_setup(crtc);
+
+	DBG("%s: intf_sel=%08x", mdp4_crtc->name, intf_sel);
+
+	mdp4_write(mdp4_kms, REG_MDP4_DISP_INTF_SEL, intf_sel);
+}
+
+static const char *dma_names[] = {
+		"DMA_P", "DMA_S", "DMA_E",
+};
+
+/* initialize crtc */
+struct drm_crtc *mdp4_crtc_init(struct drm_device *dev,
+		struct drm_plane *plane, int id, int ovlp_id,
+		enum mdp4_dma dma_id)
+{
+	struct drm_crtc *crtc = NULL;
+	struct mdp4_crtc *mdp4_crtc;
+	int ret;
+
+	mdp4_crtc = kzalloc(sizeof(*mdp4_crtc), GFP_KERNEL);
+	if (!mdp4_crtc) {
+		ret = -ENOMEM;
+		goto fail;
+	}
+
+	crtc = &mdp4_crtc->base;
+
+	mdp4_crtc->plane = plane;
+	mdp4_crtc->plane->crtc = crtc;
+
+	mdp4_crtc->ovlp = ovlp_id;
+	mdp4_crtc->dma = dma_id;
+
+	mdp4_crtc->vblank.irqmask = dma2irq(mdp4_crtc->dma);
+	mdp4_crtc->vblank.irq = mdp4_crtc_vblank_irq;
+
+	mdp4_crtc->err.irqmask = dma2err(mdp4_crtc->dma);
+	mdp4_crtc->err.irq = mdp4_crtc_err_irq;
+
+	snprintf(mdp4_crtc->name, sizeof(mdp4_crtc->name), "%s:%d",
+			dma_names[dma_id], ovlp_id);
+
+	spin_lock_init(&mdp4_crtc->cursor.lock);
+
+	ret = drm_flip_work_init(&mdp4_crtc->unref_fb_work, 16,
+			"unref fb", unref_fb_worker);
+	if (ret)
+		goto fail;
+
+	ret = drm_flip_work_init(&mdp4_crtc->unref_cursor_work, 64,
+			"unref cursor", unref_cursor_worker);
+
+	INIT_WORK(&mdp4_crtc->pageflip_work, pageflip_worker);
+
+	drm_crtc_init(dev, crtc, &mdp4_crtc_funcs);
+	drm_crtc_helper_add(crtc, &mdp4_crtc_helper_funcs);
+
+	mdp4_plane_install_properties(mdp4_crtc->plane, &crtc->base);
+
+	return crtc;
+
+fail:
+	if (crtc)
+		mdp4_crtc_destroy(crtc);
+
+	return ERR_PTR(ret);
+}
diff --git a/drivers/gpu/drm/msm/mdp4/mdp4_dtv_encoder.c b/drivers/gpu/drm/msm/mdp4/mdp4_dtv_encoder.c
new file mode 100644
index 000000000000..5e0dcae70ab5
--- /dev/null
+++ b/drivers/gpu/drm/msm/mdp4/mdp4_dtv_encoder.c
@@ -0,0 +1,305 @@
+/*
+ * Copyright (C) 2013 Red Hat
+ * Author: Rob Clark <robdclark@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <mach/clk.h>
+
+#include "mdp4_kms.h"
+
+#include "drm_crtc.h"
+#include "drm_crtc_helper.h"
+
+
+struct mdp4_dtv_encoder {
+	struct drm_encoder base;
+	struct clk *src_clk;
+	struct clk *hdmi_clk;
+	struct clk *mdp_clk;
+	unsigned long int pixclock;
+	bool enabled;
+	uint32_t bsc;
+};
+#define to_mdp4_dtv_encoder(x) container_of(x, struct mdp4_dtv_encoder, base)
+
+static struct mdp4_kms *get_kms(struct drm_encoder *encoder)
+{
+	struct msm_drm_private *priv = encoder->dev->dev_private;
+	return to_mdp4_kms(priv->kms);
+}
+
+#ifdef CONFIG_MSM_BUS_SCALING
+#include <mach/board.h>
+/* not ironically named at all.. no, really.. */
+static void bs_init(struct mdp4_dtv_encoder *mdp4_dtv_encoder)
+{
+	struct drm_device *dev = mdp4_dtv_encoder->base.dev;
+	struct lcdc_platform_data *dtv_pdata = mdp4_find_pdata("dtv.0");
+
+	if (!dtv_pdata) {
+		dev_err(dev->dev, "could not find dtv pdata\n");
+		return;
+	}
+
+	if (dtv_pdata->bus_scale_table) {
+		mdp4_dtv_encoder->bsc = msm_bus_scale_register_client(
+				dtv_pdata->bus_scale_table);
+		DBG("bus scale client: %08x", mdp4_dtv_encoder->bsc);
+		DBG("lcdc_power_save: %p", dtv_pdata->lcdc_power_save);
+		if (dtv_pdata->lcdc_power_save)
+			dtv_pdata->lcdc_power_save(1);
+	}
+}
+
+static void bs_fini(struct mdp4_dtv_encoder *mdp4_dtv_encoder)
+{
+	if (mdp4_dtv_encoder->bsc) {
+		msm_bus_scale_unregister_client(mdp4_dtv_encoder->bsc);
+		mdp4_dtv_encoder->bsc = 0;
+	}
+}
+
+static void bs_set(struct mdp4_dtv_encoder *mdp4_dtv_encoder, int idx)
+{
+	if (mdp4_dtv_encoder->bsc) {
+		DBG("set bus scaling: %d", idx);
+		msm_bus_scale_client_update_request(mdp4_dtv_encoder->bsc, idx);
+	}
+}
+#else
+static void bs_init(struct mdp4_dtv_encoder *mdp4_dtv_encoder) {}
+static void bs_fini(struct mdp4_dtv_encoder *mdp4_dtv_encoder) {}
+static void bs_set(struct mdp4_dtv_encoder *mdp4_dtv_encoder, int idx) {}
+#endif
+
+static void mdp4_dtv_encoder_destroy(struct drm_encoder *encoder)
+{
+	struct mdp4_dtv_encoder *mdp4_dtv_encoder = to_mdp4_dtv_encoder(encoder);
+	bs_fini(mdp4_dtv_encoder);
+	drm_encoder_cleanup(encoder);
+	kfree(mdp4_dtv_encoder);
+}
+
+static const struct drm_encoder_funcs mdp4_dtv_encoder_funcs = {
+	.destroy = mdp4_dtv_encoder_destroy,
+};
+
+static void mdp4_dtv_encoder_dpms(struct drm_encoder *encoder, int mode)
+{
+	struct drm_device *dev = encoder->dev;
+	struct mdp4_dtv_encoder *mdp4_dtv_encoder = to_mdp4_dtv_encoder(encoder);
+	struct mdp4_kms *mdp4_kms = get_kms(encoder);
+	bool enabled = (mode == DRM_MODE_DPMS_ON);
+
+	DBG("mode=%d", mode);
+
+	if (enabled == mdp4_dtv_encoder->enabled)
+		return;
+
+	if (enabled) {
+		unsigned long pc = mdp4_dtv_encoder->pixclock;
+		int ret;
+
+		bs_set(mdp4_dtv_encoder, 1);
+
+		DBG("setting src_clk=%lu", pc);
+
+		ret = clk_set_rate(mdp4_dtv_encoder->src_clk, pc);
+		if (ret)
+			dev_err(dev->dev, "failed to set src_clk to %lu: %d\n", pc, ret);
+		clk_prepare_enable(mdp4_dtv_encoder->src_clk);
+		ret = clk_prepare_enable(mdp4_dtv_encoder->hdmi_clk);
+		if (ret)
+			dev_err(dev->dev, "failed to enable hdmi_clk: %d\n", ret);
+		ret = clk_prepare_enable(mdp4_dtv_encoder->mdp_clk);
+		if (ret)
+			dev_err(dev->dev, "failed to enabled mdp_clk: %d\n", ret);
+
+		mdp4_write(mdp4_kms, REG_MDP4_DTV_ENABLE, 1);
+	} else {
+		mdp4_write(mdp4_kms, REG_MDP4_DTV_ENABLE, 0);
+
+		/*
+		 * Wait for a vsync so we know the ENABLE=0 latched before
+		 * the (connector) source of the vsync's gets disabled,
+		 * otherwise we end up in a funny state if we re-enable
+		 * before the disable latches, which results that some of
+		 * the settings changes for the new modeset (like new
+		 * scanout buffer) don't latch properly..
+		 */
+		mdp4_irq_wait(mdp4_kms, MDP4_IRQ_EXTERNAL_VSYNC);
+
+		clk_disable_unprepare(mdp4_dtv_encoder->src_clk);
+		clk_disable_unprepare(mdp4_dtv_encoder->hdmi_clk);
+		clk_disable_unprepare(mdp4_dtv_encoder->mdp_clk);
+
+		bs_set(mdp4_dtv_encoder, 0);
+	}
+
+	mdp4_dtv_encoder->enabled = enabled;
+}
+
+static bool mdp4_dtv_encoder_mode_fixup(struct drm_encoder *encoder,
+		const struct drm_display_mode *mode,
+		struct drm_display_mode *adjusted_mode)
+{
+	return true;
+}
+
+static void mdp4_dtv_encoder_mode_set(struct drm_encoder *encoder,
+		struct drm_display_mode *mode,
+		struct drm_display_mode *adjusted_mode)
+{
+	struct mdp4_dtv_encoder *mdp4_dtv_encoder = to_mdp4_dtv_encoder(encoder);
+	struct mdp4_kms *mdp4_kms = get_kms(encoder);
+	uint32_t dtv_hsync_skew, vsync_period, vsync_len, ctrl_pol;
+	uint32_t display_v_start, display_v_end;
+	uint32_t hsync_start_x, hsync_end_x;
+
+	mode = adjusted_mode;
+
+	DBG("set mode: %d:\"%s\" %d %d %d %d %d %d %d %d %d %d 0x%x 0x%x",
+			mode->base.id, mode->name,
+			mode->vrefresh, mode->clock,
+			mode->hdisplay, mode->hsync_start,
+			mode->hsync_end, mode->htotal,
+			mode->vdisplay, mode->vsync_start,
+			mode->vsync_end, mode->vtotal,
+			mode->type, mode->flags);
+
+	mdp4_dtv_encoder->pixclock = mode->clock * 1000;
+
+	DBG("pixclock=%lu", mdp4_dtv_encoder->pixclock);
+
+	ctrl_pol = 0;
+	if (mode->flags & DRM_MODE_FLAG_NHSYNC)
+		ctrl_pol |= MDP4_DTV_CTRL_POLARITY_HSYNC_LOW;
+	if (mode->flags & DRM_MODE_FLAG_NVSYNC)
+		ctrl_pol |= MDP4_DTV_CTRL_POLARITY_VSYNC_LOW;
+	/* probably need to get DATA_EN polarity from panel.. */
+
+	dtv_hsync_skew = 0;  /* get this from panel? */
+
+	hsync_start_x = (mode->htotal - mode->hsync_start);
+	hsync_end_x = mode->htotal - (mode->hsync_start - mode->hdisplay) - 1;
+
+	vsync_period = mode->vtotal * mode->htotal;
+	vsync_len = (mode->vsync_end - mode->vsync_start) * mode->htotal;
+	display_v_start = (mode->vtotal - mode->vsync_start) * mode->htotal + dtv_hsync_skew;
+	display_v_end = vsync_period - ((mode->vsync_start - mode->vdisplay) * mode->htotal) + dtv_hsync_skew - 1;
+
+	mdp4_write(mdp4_kms, REG_MDP4_DTV_HSYNC_CTRL,
+			MDP4_DTV_HSYNC_CTRL_PULSEW(mode->hsync_end - mode->hsync_start) |
+			MDP4_DTV_HSYNC_CTRL_PERIOD(mode->htotal));
+	mdp4_write(mdp4_kms, REG_MDP4_DTV_VSYNC_PERIOD, vsync_period);
+	mdp4_write(mdp4_kms, REG_MDP4_DTV_VSYNC_LEN, vsync_len);
+	mdp4_write(mdp4_kms, REG_MDP4_DTV_DISPLAY_HCTRL,
+			MDP4_DTV_DISPLAY_HCTRL_START(hsync_start_x) |
+			MDP4_DTV_DISPLAY_HCTRL_END(hsync_end_x));
+	mdp4_write(mdp4_kms, REG_MDP4_DTV_DISPLAY_VSTART, display_v_start);
+	mdp4_write(mdp4_kms, REG_MDP4_DTV_DISPLAY_VEND, display_v_end);
+	mdp4_write(mdp4_kms, REG_MDP4_DTV_BORDER_CLR, 0);
+	mdp4_write(mdp4_kms, REG_MDP4_DTV_UNDERFLOW_CLR,
+			MDP4_DTV_UNDERFLOW_CLR_ENABLE_RECOVERY |
+			MDP4_DTV_UNDERFLOW_CLR_COLOR(0xff));
+	mdp4_write(mdp4_kms, REG_MDP4_DTV_HSYNC_SKEW, dtv_hsync_skew);
+	mdp4_write(mdp4_kms, REG_MDP4_DTV_CTRL_POLARITY, ctrl_pol);
+	mdp4_write(mdp4_kms, REG_MDP4_DTV_ACTIVE_HCTL,
+			MDP4_DTV_ACTIVE_HCTL_START(0) |
+			MDP4_DTV_ACTIVE_HCTL_END(0));
+	mdp4_write(mdp4_kms, REG_MDP4_DTV_ACTIVE_VSTART, 0);
+	mdp4_write(mdp4_kms, REG_MDP4_DTV_ACTIVE_VEND, 0);
+}
+
+static void mdp4_dtv_encoder_prepare(struct drm_encoder *encoder)
+{
+	mdp4_dtv_encoder_dpms(encoder, DRM_MODE_DPMS_OFF);
+}
+
+static void mdp4_dtv_encoder_commit(struct drm_encoder *encoder)
+{
+	mdp4_crtc_set_config(encoder->crtc,
+			MDP4_DMA_CONFIG_R_BPC(BPC8) |
+			MDP4_DMA_CONFIG_G_BPC(BPC8) |
+			MDP4_DMA_CONFIG_B_BPC(BPC8) |
+			MDP4_DMA_CONFIG_PACK(0x21));
+	mdp4_crtc_set_intf(encoder->crtc, INTF_LCDC_DTV);
+	mdp4_dtv_encoder_dpms(encoder, DRM_MODE_DPMS_ON);
+}
+
+static const struct drm_encoder_helper_funcs mdp4_dtv_encoder_helper_funcs = {
+	.dpms = mdp4_dtv_encoder_dpms,
+	.mode_fixup = mdp4_dtv_encoder_mode_fixup,
+	.mode_set = mdp4_dtv_encoder_mode_set,
+	.prepare = mdp4_dtv_encoder_prepare,
+	.commit = mdp4_dtv_encoder_commit,
+};
+
+long mdp4_dtv_round_pixclk(struct drm_encoder *encoder, unsigned long rate)
+{
+	struct mdp4_dtv_encoder *mdp4_dtv_encoder = to_mdp4_dtv_encoder(encoder);
+	return clk_round_rate(mdp4_dtv_encoder->src_clk, rate);
+}
+
+/* initialize encoder */
+struct drm_encoder *mdp4_dtv_encoder_init(struct drm_device *dev)
+{
+	struct drm_encoder *encoder = NULL;
+	struct mdp4_dtv_encoder *mdp4_dtv_encoder;
+	int ret;
+
+	mdp4_dtv_encoder = kzalloc(sizeof(*mdp4_dtv_encoder), GFP_KERNEL);
+	if (!mdp4_dtv_encoder) {
+		ret = -ENOMEM;
+		goto fail;
+	}
+
+	encoder = &mdp4_dtv_encoder->base;
+
+	drm_encoder_init(dev, encoder, &mdp4_dtv_encoder_funcs,
+			 DRM_MODE_ENCODER_TMDS);
+	drm_encoder_helper_add(encoder, &mdp4_dtv_encoder_helper_funcs);
+
+	mdp4_dtv_encoder->src_clk = devm_clk_get(dev->dev, "src_clk");
+	if (IS_ERR(mdp4_dtv_encoder->src_clk)) {
+		dev_err(dev->dev, "failed to get src_clk\n");
+		ret = PTR_ERR(mdp4_dtv_encoder->src_clk);
+		goto fail;
+	}
+
+	mdp4_dtv_encoder->hdmi_clk = devm_clk_get(dev->dev, "hdmi_clk");
+	if (IS_ERR(mdp4_dtv_encoder->hdmi_clk)) {
+		dev_err(dev->dev, "failed to get hdmi_clk\n");
+		ret = PTR_ERR(mdp4_dtv_encoder->hdmi_clk);
+		goto fail;
+	}
+
+	mdp4_dtv_encoder->mdp_clk = devm_clk_get(dev->dev, "mdp_clk");
+	if (IS_ERR(mdp4_dtv_encoder->mdp_clk)) {
+		dev_err(dev->dev, "failed to get mdp_clk\n");
+		ret = PTR_ERR(mdp4_dtv_encoder->mdp_clk);
+		goto fail;
+	}
+
+	bs_init(mdp4_dtv_encoder);
+
+	return encoder;
+
+fail:
+	if (encoder)
+		mdp4_dtv_encoder_destroy(encoder);
+
+	return ERR_PTR(ret);
+}
diff --git a/drivers/gpu/drm/msm/mdp4/mdp4_format.c b/drivers/gpu/drm/msm/mdp4/mdp4_format.c
new file mode 100644
index 000000000000..7b645f2e837a
--- /dev/null
+++ b/drivers/gpu/drm/msm/mdp4/mdp4_format.c
@@ -0,0 +1,56 @@
+/*
+ * Copyright (C) 2013 Red Hat
+ * Author: Rob Clark <robdclark@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+
+#include "msm_drv.h"
+#include "mdp4_kms.h"
+
+#define FMT(name, a, r, g, b, e0, e1, e2, e3, alpha, tight, c, cnt) { \
+		.base = { .pixel_format = DRM_FORMAT_ ## name }, \
+		.bpc_a = BPC ## a ## A,                          \
+		.bpc_r = BPC ## r,                               \
+		.bpc_g = BPC ## g,                               \
+		.bpc_b = BPC ## b,                               \
+		.unpack = { e0, e1, e2, e3 },                    \
+		.alpha_enable = alpha,                           \
+		.unpack_tight = tight,                           \
+		.cpp = c,                                        \
+		.unpack_count = cnt,                             \
+	}
+
+#define BPC0A 0
+
+static const struct mdp4_format formats[] = {
+	/*  name      a  r  g  b   e0 e1 e2 e3  alpha   tight  cpp cnt */
+	FMT(ARGB8888, 8, 8, 8, 8,  1, 0, 2, 3,  true,   true,  4,  4),
+	FMT(XRGB8888, 8, 8, 8, 8,  1, 0, 2, 3,  false,  true,  4,  4),
+	FMT(RGB888,   0, 8, 8, 8,  1, 0, 2, 0,  false,  true,  3,  3),
+	FMT(BGR888,   0, 8, 8, 8,  2, 0, 1, 0,  false,  true,  3,  3),
+	FMT(RGB565,   0, 5, 6, 5,  1, 0, 2, 0,  false,  true,  2,  3),
+	FMT(BGR565,   0, 5, 6, 5,  2, 0, 1, 0,  false,  true,  2,  3),
+};
+
+const struct msm_format *mdp4_get_format(struct msm_kms *kms, uint32_t format)
+{
+	int i;
+	for (i = 0; i < ARRAY_SIZE(formats); i++) {
+		const struct mdp4_format *f = &formats[i];
+		if (f->base.pixel_format == format)
+			return &f->base;
+	}
+	return NULL;
+}
diff --git a/drivers/gpu/drm/msm/mdp4/mdp4_irq.c b/drivers/gpu/drm/msm/mdp4/mdp4_irq.c
new file mode 100644
index 000000000000..5c6b7fca4edd
--- /dev/null
+++ b/drivers/gpu/drm/msm/mdp4/mdp4_irq.c
@@ -0,0 +1,203 @@
+/*
+ * Copyright (C) 2013 Red Hat
+ * Author: Rob Clark <robdclark@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+
+#include "msm_drv.h"
+#include "mdp4_kms.h"
+
+
+struct mdp4_irq_wait {
+	struct mdp4_irq irq;
+	int count;
+};
+
+static DECLARE_WAIT_QUEUE_HEAD(wait_event);
+
+static DEFINE_SPINLOCK(list_lock);
+
+static void update_irq(struct mdp4_kms *mdp4_kms)
+{
+	struct mdp4_irq *irq;
+	uint32_t irqmask = mdp4_kms->vblank_mask;
+
+	BUG_ON(!spin_is_locked(&list_lock));
+
+	list_for_each_entry(irq, &mdp4_kms->irq_list, node)
+		irqmask |= irq->irqmask;
+
+	mdp4_write(mdp4_kms, REG_MDP4_INTR_ENABLE, irqmask);
+}
+
+static void update_irq_unlocked(struct mdp4_kms *mdp4_kms)
+{
+	unsigned long flags;
+	spin_lock_irqsave(&list_lock, flags);
+	update_irq(mdp4_kms);
+	spin_unlock_irqrestore(&list_lock, flags);
+}
+
+static void mdp4_irq_error_handler(struct mdp4_irq *irq, uint32_t irqstatus)
+{
+	DRM_ERROR("errors: %08x\n", irqstatus);
+}
+
+void mdp4_irq_preinstall(struct msm_kms *kms)
+{
+	struct mdp4_kms *mdp4_kms = to_mdp4_kms(kms);
+	mdp4_write(mdp4_kms, REG_MDP4_INTR_CLEAR, 0xffffffff);
+}
+
+int mdp4_irq_postinstall(struct msm_kms *kms)
+{
+	struct mdp4_kms *mdp4_kms = to_mdp4_kms(kms);
+	struct mdp4_irq *error_handler = &mdp4_kms->error_handler;
+
+	INIT_LIST_HEAD(&mdp4_kms->irq_list);
+
+	error_handler->irq = mdp4_irq_error_handler;
+	error_handler->irqmask = MDP4_IRQ_PRIMARY_INTF_UDERRUN |
+			MDP4_IRQ_EXTERNAL_INTF_UDERRUN;
+
+	mdp4_irq_register(mdp4_kms, error_handler);
+
+	return 0;
+}
+
+void mdp4_irq_uninstall(struct msm_kms *kms)
+{
+	struct mdp4_kms *mdp4_kms = to_mdp4_kms(kms);
+	mdp4_write(mdp4_kms, REG_MDP4_INTR_ENABLE, 0x00000000);
+}
+
+irqreturn_t mdp4_irq(struct msm_kms *kms)
+{
+	struct mdp4_kms *mdp4_kms = to_mdp4_kms(kms);
+	struct drm_device *dev = mdp4_kms->dev;
+	struct msm_drm_private *priv = dev->dev_private;
+	struct mdp4_irq *handler, *n;
+	unsigned long flags;
+	unsigned int id;
+	uint32_t status;
+
+	status = mdp4_read(mdp4_kms, REG_MDP4_INTR_STATUS);
+	mdp4_write(mdp4_kms, REG_MDP4_INTR_CLEAR, status);
+
+	VERB("status=%08x", status);
+
+	for (id = 0; id < priv->num_crtcs; id++)
+		if (status & mdp4_crtc_vblank(priv->crtcs[id]))
+			drm_handle_vblank(dev, id);
+
+	spin_lock_irqsave(&list_lock, flags);
+	mdp4_kms->in_irq = true;
+	list_for_each_entry_safe(handler, n, &mdp4_kms->irq_list, node) {
+		if (handler->irqmask & status) {
+			spin_unlock_irqrestore(&list_lock, flags);
+			handler->irq(handler, handler->irqmask & status);
+			spin_lock_irqsave(&list_lock, flags);
+		}
+	}
+	mdp4_kms->in_irq = false;
+	update_irq(mdp4_kms);
+	spin_unlock_irqrestore(&list_lock, flags);
+
+	return IRQ_HANDLED;
+}
+
+int mdp4_enable_vblank(struct msm_kms *kms, struct drm_crtc *crtc)
+{
+	struct mdp4_kms *mdp4_kms = to_mdp4_kms(kms);
+	unsigned long flags;
+
+	spin_lock_irqsave(&list_lock, flags);
+	mdp4_kms->vblank_mask |= mdp4_crtc_vblank(crtc);
+	update_irq(mdp4_kms);
+	spin_unlock_irqrestore(&list_lock, flags);
+
+	return 0;
+}
+
+void mdp4_disable_vblank(struct msm_kms *kms, struct drm_crtc *crtc)
+{
+	struct mdp4_kms *mdp4_kms = to_mdp4_kms(kms);
+	unsigned long flags;
+
+	spin_lock_irqsave(&list_lock, flags);
+	mdp4_kms->vblank_mask &= ~mdp4_crtc_vblank(crtc);
+	update_irq(mdp4_kms);
+	spin_unlock_irqrestore(&list_lock, flags);
+}
+
+static void wait_irq(struct mdp4_irq *irq, uint32_t irqstatus)
+{
+	struct mdp4_irq_wait *wait =
+			container_of(irq, struct mdp4_irq_wait, irq);
+	wait->count--;
+	wake_up_all(&wait_event);
+}
+
+void mdp4_irq_wait(struct mdp4_kms *mdp4_kms, uint32_t irqmask)
+{
+	struct mdp4_irq_wait wait = {
+		.irq = {
+			.irq = wait_irq,
+			.irqmask = irqmask,
+		},
+		.count = 1,
+	};
+	mdp4_irq_register(mdp4_kms, &wait.irq);
+	wait_event(wait_event, (wait.count <= 0));
+	mdp4_irq_unregister(mdp4_kms, &wait.irq);
+}
+
+void mdp4_irq_register(struct mdp4_kms *mdp4_kms, struct mdp4_irq *irq)
+{
+	unsigned long flags;
+	bool needs_update = false;
+
+	spin_lock_irqsave(&list_lock, flags);
+
+	if (!irq->registered) {
+		irq->registered = true;
+		list_add(&irq->node, &mdp4_kms->irq_list);
+		needs_update = !mdp4_kms->in_irq;
+	}
+
+	spin_unlock_irqrestore(&list_lock, flags);
+
+	if (needs_update)
+		update_irq_unlocked(mdp4_kms);
+}
+
+void mdp4_irq_unregister(struct mdp4_kms *mdp4_kms, struct mdp4_irq *irq)
+{
+	unsigned long flags;
+	bool needs_update = false;
+
+	spin_lock_irqsave(&list_lock, flags);
+
+	if (irq->registered) {
+		irq->registered = false;
+		list_del(&irq->node);
+		needs_update = !mdp4_kms->in_irq;
+	}
+
+	spin_unlock_irqrestore(&list_lock, flags);
+
+	if (needs_update)
+		update_irq_unlocked(mdp4_kms);
+}
diff --git a/drivers/gpu/drm/msm/mdp4/mdp4_kms.c b/drivers/gpu/drm/msm/mdp4/mdp4_kms.c
new file mode 100644
index 000000000000..bc7fd11ad8be
--- /dev/null
+++ b/drivers/gpu/drm/msm/mdp4/mdp4_kms.c
@@ -0,0 +1,363 @@
+/*
+ * Copyright (C) 2013 Red Hat
+ * Author: Rob Clark <robdclark@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+
+#include "msm_drv.h"
+#include "mdp4_kms.h"
+
+static struct mdp4_platform_config *mdp4_get_config(struct platform_device *dev);
+
+static int mdp4_hw_init(struct msm_kms *kms)
+{
+	struct mdp4_kms *mdp4_kms = to_mdp4_kms(kms);
+	struct drm_device *dev = mdp4_kms->dev;
+	uint32_t version, major, minor, dmap_cfg, vg_cfg;
+	unsigned long clk;
+	int ret = 0;
+
+	pm_runtime_get_sync(dev->dev);
+
+	version = mdp4_read(mdp4_kms, REG_MDP4_VERSION);
+
+	major = FIELD(version, MDP4_VERSION_MAJOR);
+	minor = FIELD(version, MDP4_VERSION_MINOR);
+
+	DBG("found MDP version v%d.%d", major, minor);
+
+	if (major != 4) {
+		dev_err(dev->dev, "unexpected MDP version: v%d.%d\n",
+				major, minor);
+		ret = -ENXIO;
+		goto out;
+	}
+
+	mdp4_kms->rev = minor;
+
+	if (mdp4_kms->dsi_pll_vdda) {
+		if ((mdp4_kms->rev == 2) || (mdp4_kms->rev == 4)) {
+			ret = regulator_set_voltage(mdp4_kms->dsi_pll_vdda,
+					1200000, 1200000);
+			if (ret) {
+				dev_err(dev->dev,
+					"failed to set dsi_pll_vdda voltage: %d\n", ret);
+				goto out;
+			}
+		}
+	}
+
+	if (mdp4_kms->dsi_pll_vddio) {
+		if (mdp4_kms->rev == 2) {
+			ret = regulator_set_voltage(mdp4_kms->dsi_pll_vddio,
+					1800000, 1800000);
+			if (ret) {
+				dev_err(dev->dev,
+					"failed to set dsi_pll_vddio voltage: %d\n", ret);
+				goto out;
+			}
+		}
+	}
+
+	if (mdp4_kms->rev > 1) {
+		mdp4_write(mdp4_kms, REG_MDP4_CS_CONTROLLER0, 0x0707ffff);
+		mdp4_write(mdp4_kms, REG_MDP4_CS_CONTROLLER1, 0x03073f3f);
+	}
+
+	mdp4_write(mdp4_kms, REG_MDP4_PORTMAP_MODE, 0x3);
+
+	/* max read pending cmd config, 3 pending requests: */
+	mdp4_write(mdp4_kms, REG_MDP4_READ_CNFG, 0x02222);
+
+	clk = clk_get_rate(mdp4_kms->clk);
+
+	if ((mdp4_kms->rev >= 1) || (clk >= 90000000)) {
+		dmap_cfg = 0x47;     /* 16 bytes-burst x 8 req */
+		vg_cfg = 0x47;       /* 16 bytes-burs x 8 req */
+	} else {
+		dmap_cfg = 0x27;     /* 8 bytes-burst x 8 req */
+		vg_cfg = 0x43;       /* 16 bytes-burst x 4 req */
+	}
+
+	DBG("fetch config: dmap=%02x, vg=%02x", dmap_cfg, vg_cfg);
+
+	mdp4_write(mdp4_kms, REG_MDP4_DMA_FETCH_CONFIG(DMA_P), dmap_cfg);
+	mdp4_write(mdp4_kms, REG_MDP4_DMA_FETCH_CONFIG(DMA_E), dmap_cfg);
+
+	mdp4_write(mdp4_kms, REG_MDP4_PIPE_FETCH_CONFIG(VG1), vg_cfg);
+	mdp4_write(mdp4_kms, REG_MDP4_PIPE_FETCH_CONFIG(VG2), vg_cfg);
+	mdp4_write(mdp4_kms, REG_MDP4_PIPE_FETCH_CONFIG(RGB1), vg_cfg);
+	mdp4_write(mdp4_kms, REG_MDP4_PIPE_FETCH_CONFIG(RGB2), vg_cfg);
+
+	if (mdp4_kms->rev >= 2)
+		mdp4_write(mdp4_kms, REG_MDP4_LAYERMIXER_IN_CFG_UPDATE_METHOD, 1);
+
+	/* disable CSC matrix / YUV by default: */
+	mdp4_write(mdp4_kms, REG_MDP4_PIPE_OP_MODE(VG1), 0);
+	mdp4_write(mdp4_kms, REG_MDP4_PIPE_OP_MODE(VG2), 0);
+	mdp4_write(mdp4_kms, REG_MDP4_DMA_P_OP_MODE, 0);
+	mdp4_write(mdp4_kms, REG_MDP4_DMA_S_OP_MODE, 0);
+	mdp4_write(mdp4_kms, REG_MDP4_OVLP_CSC_CONFIG(1), 0);
+	mdp4_write(mdp4_kms, REG_MDP4_OVLP_CSC_CONFIG(2), 0);
+
+	if (mdp4_kms->rev > 1)
+		mdp4_write(mdp4_kms, REG_MDP4_RESET_STATUS, 1);
+
+out:
+	pm_runtime_put_sync(dev->dev);
+
+	return ret;
+}
+
+static long mdp4_round_pixclk(struct msm_kms *kms, unsigned long rate,
+		struct drm_encoder *encoder)
+{
+	/* if we had >1 encoder, we'd need something more clever: */
+	return mdp4_dtv_round_pixclk(encoder, rate);
+}
+
+static void mdp4_preclose(struct msm_kms *kms, struct drm_file *file)
+{
+	struct mdp4_kms *mdp4_kms = to_mdp4_kms(kms);
+	struct msm_drm_private *priv = mdp4_kms->dev->dev_private;
+	unsigned i;
+
+	for (i = 0; i < priv->num_crtcs; i++)
+		mdp4_crtc_cancel_pending_flip(priv->crtcs[i]);
+}
+
+static void mdp4_destroy(struct msm_kms *kms)
+{
+	struct mdp4_kms *mdp4_kms = to_mdp4_kms(kms);
+	kfree(mdp4_kms);
+}
+
+static const struct msm_kms_funcs kms_funcs = {
+		.hw_init         = mdp4_hw_init,
+		.irq_preinstall  = mdp4_irq_preinstall,
+		.irq_postinstall = mdp4_irq_postinstall,
+		.irq_uninstall   = mdp4_irq_uninstall,
+		.irq             = mdp4_irq,
+		.enable_vblank   = mdp4_enable_vblank,
+		.disable_vblank  = mdp4_disable_vblank,
+		.get_format      = mdp4_get_format,
+		.round_pixclk    = mdp4_round_pixclk,
+		.preclose        = mdp4_preclose,
+		.destroy         = mdp4_destroy,
+};
+
+int mdp4_disable(struct mdp4_kms *mdp4_kms)
+{
+	DBG("");
+
+	clk_disable_unprepare(mdp4_kms->clk);
+	if (mdp4_kms->pclk)
+		clk_disable_unprepare(mdp4_kms->pclk);
+	clk_disable_unprepare(mdp4_kms->lut_clk);
+
+	return 0;
+}
+
+int mdp4_enable(struct mdp4_kms *mdp4_kms)
+{
+	DBG("");
+
+	clk_prepare_enable(mdp4_kms->clk);
+	if (mdp4_kms->pclk)
+		clk_prepare_enable(mdp4_kms->pclk);
+	clk_prepare_enable(mdp4_kms->lut_clk);
+
+	return 0;
+}
+
+static int modeset_init(struct mdp4_kms *mdp4_kms)
+{
+	struct drm_device *dev = mdp4_kms->dev;
+	struct msm_drm_private *priv = dev->dev_private;
+	struct drm_plane *plane;
+	struct drm_crtc *crtc;
+	struct drm_encoder *encoder;
+	int ret;
+
+	/*
+	 *  NOTE: this is a bit simplistic until we add support
+	 * for more than just RGB1->DMA_E->DTV->HDMI
+	 */
+
+	/* the CRTCs get constructed with a private plane: */
+	plane = mdp4_plane_init(dev, RGB1, true);
+	if (IS_ERR(plane)) {
+		dev_err(dev->dev, "failed to construct plane for RGB1\n");
+		ret = PTR_ERR(plane);
+		goto fail;
+	}
+
+	crtc  = mdp4_crtc_init(dev, plane, priv->num_crtcs, 1, DMA_E);
+	if (IS_ERR(crtc)) {
+		dev_err(dev->dev, "failed to construct crtc for DMA_E\n");
+		ret = PTR_ERR(crtc);
+		goto fail;
+	}
+	priv->crtcs[priv->num_crtcs++] = crtc;
+
+	encoder = mdp4_dtv_encoder_init(dev);
+	if (IS_ERR(encoder)) {
+		dev_err(dev->dev, "failed to construct DTV encoder\n");
+		ret = PTR_ERR(encoder);
+		goto fail;
+	}
+	encoder->possible_crtcs = 0x1;     /* DTV can be hooked to DMA_E */
+	priv->encoders[priv->num_encoders++] = encoder;
+
+	ret = hdmi_init(dev, encoder);
+	if (ret) {
+		dev_err(dev->dev, "failed to initialize HDMI\n");
+		goto fail;
+	}
+
+	return 0;
+
+fail:
+	return ret;
+}
+
+static const char *iommu_ports[] = {
+		"mdp_port0_cb0", "mdp_port1_cb0",
+};
+
+struct msm_kms *mdp4_kms_init(struct drm_device *dev)
+{
+	struct platform_device *pdev = dev->platformdev;
+	struct mdp4_platform_config *config = mdp4_get_config(pdev);
+	struct mdp4_kms *mdp4_kms;
+	struct msm_kms *kms = NULL;
+	int ret;
+
+	mdp4_kms = kzalloc(sizeof(*mdp4_kms), GFP_KERNEL);
+	if (!mdp4_kms) {
+		dev_err(dev->dev, "failed to allocate kms\n");
+		ret = -ENOMEM;
+		goto fail;
+	}
+
+	kms = &mdp4_kms->base;
+	kms->funcs = &kms_funcs;
+
+	mdp4_kms->dev = dev;
+
+	mdp4_kms->mmio = msm_ioremap(pdev, NULL, "MDP4");
+	if (IS_ERR(mdp4_kms->mmio)) {
+		ret = PTR_ERR(mdp4_kms->mmio);
+		goto fail;
+	}
+
+	mdp4_kms->dsi_pll_vdda = devm_regulator_get(&pdev->dev, "dsi_pll_vdda");
+	if (IS_ERR(mdp4_kms->dsi_pll_vdda))
+		mdp4_kms->dsi_pll_vdda = NULL;
+
+	mdp4_kms->dsi_pll_vddio = devm_regulator_get(&pdev->dev, "dsi_pll_vddio");
+	if (IS_ERR(mdp4_kms->dsi_pll_vddio))
+		mdp4_kms->dsi_pll_vddio = NULL;
+
+	mdp4_kms->vdd = devm_regulator_get(&pdev->dev, "vdd");
+	if (IS_ERR(mdp4_kms->vdd))
+		mdp4_kms->vdd = NULL;
+
+	if (mdp4_kms->vdd) {
+		ret = regulator_enable(mdp4_kms->vdd);
+		if (ret) {
+			dev_err(dev->dev, "failed to enable regulator vdd: %d\n", ret);
+			goto fail;
+		}
+	}
+
+	mdp4_kms->clk = devm_clk_get(&pdev->dev, "core_clk");
+	if (IS_ERR(mdp4_kms->clk)) {
+		dev_err(dev->dev, "failed to get core_clk\n");
+		ret = PTR_ERR(mdp4_kms->clk);
+		goto fail;
+	}
+
+	mdp4_kms->pclk = devm_clk_get(&pdev->dev, "iface_clk");
+	if (IS_ERR(mdp4_kms->pclk))
+		mdp4_kms->pclk = NULL;
+
+	// XXX if (rev >= MDP_REV_42) { ???
+	mdp4_kms->lut_clk = devm_clk_get(&pdev->dev, "lut_clk");
+	if (IS_ERR(mdp4_kms->lut_clk)) {
+		dev_err(dev->dev, "failed to get lut_clk\n");
+		ret = PTR_ERR(mdp4_kms->lut_clk);
+		goto fail;
+	}
+
+	clk_set_rate(mdp4_kms->clk, config->max_clk);
+	clk_set_rate(mdp4_kms->lut_clk, config->max_clk);
+
+	if (!config->iommu) {
+		dev_err(dev->dev, "no iommu\n");
+		ret = -ENXIO;
+		goto fail;
+	}
+
+	/* make sure things are off before attaching iommu (bootloader could
+	 * have left things on, in which case we'll start getting faults if
+	 * we don't disable):
+	 */
+	mdp4_write(mdp4_kms, REG_MDP4_DTV_ENABLE, 0);
+	mdp4_write(mdp4_kms, REG_MDP4_LCDC_ENABLE, 0);
+	mdp4_write(mdp4_kms, REG_MDP4_DSI_ENABLE, 0);
+	mdelay(16);
+
+	ret = msm_iommu_attach(dev, config->iommu,
+			iommu_ports, ARRAY_SIZE(iommu_ports));
+	if (ret)
+		goto fail;
+
+	mdp4_kms->id = msm_register_iommu(dev, config->iommu);
+	if (mdp4_kms->id < 0) {
+		ret = mdp4_kms->id;
+		dev_err(dev->dev, "failed to register mdp4 iommu: %d\n", ret);
+		goto fail;
+	}
+
+	ret = modeset_init(mdp4_kms);
+	if (ret) {
+		dev_err(dev->dev, "modeset_init failed: %d\n", ret);
+		goto fail;
+	}
+
+	return kms;
+
+fail:
+	if (kms)
+		mdp4_destroy(kms);
+	return ERR_PTR(ret);
+}
+
+static struct mdp4_platform_config *mdp4_get_config(struct platform_device *dev)
+{
+	static struct mdp4_platform_config config = {};
+#ifdef CONFIG_OF
+	/* TODO */
+#else
+	if (cpu_is_apq8064())
+		config.max_clk = 266667000;
+	else
+		config.max_clk = 200000000;
+
+	config.iommu = msm_get_iommu_domain(DISPLAY_READ_DOMAIN);
+#endif
+	return &config;
+}
diff --git a/drivers/gpu/drm/msm/mdp4/mdp4_kms.h b/drivers/gpu/drm/msm/mdp4/mdp4_kms.h
new file mode 100644
index 000000000000..1e83554955f3
--- /dev/null
+++ b/drivers/gpu/drm/msm/mdp4/mdp4_kms.h
@@ -0,0 +1,194 @@
+/*
+ * Copyright (C) 2013 Red Hat
+ * Author: Rob Clark <robdclark@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __MDP4_KMS_H__
+#define __MDP4_KMS_H__
+
+#include <linux/clk.h>
+#include <linux/platform_device.h>
+#include <linux/regulator/consumer.h>
+
+#include "msm_drv.h"
+#include "mdp4.xml.h"
+
+
+/* For transiently registering for different MDP4 irqs that various parts
+ * of the KMS code need during setup/configuration.  We these are not
+ * necessarily the same as what drm_vblank_get/put() are requesting, and
+ * the hysteresis in drm_vblank_put() is not necessarily desirable for
+ * internal housekeeping related irq usage.
+ */
+struct mdp4_irq {
+	struct list_head node;
+	uint32_t irqmask;
+	bool registered;
+	void (*irq)(struct mdp4_irq *irq, uint32_t irqstatus);
+};
+
+struct mdp4_kms {
+	struct msm_kms base;
+
+	struct drm_device *dev;
+
+	int rev;
+
+	/* mapper-id used to request GEM buffer mapped for scanout: */
+	int id;
+
+	void __iomem *mmio;
+
+	struct regulator *dsi_pll_vdda;
+	struct regulator *dsi_pll_vddio;
+	struct regulator *vdd;
+
+	struct clk *clk;
+	struct clk *pclk;
+	struct clk *lut_clk;
+
+	/* irq handling: */
+	bool in_irq;
+	struct list_head irq_list;    /* list of mdp4_irq */
+	uint32_t vblank_mask;         /* irq bits set for userspace vblank */
+	struct mdp4_irq error_handler;
+};
+#define to_mdp4_kms(x) container_of(x, struct mdp4_kms, base)
+
+/* platform config data (ie. from DT, or pdata) */
+struct mdp4_platform_config {
+	struct iommu_domain *iommu;
+	uint32_t max_clk;
+};
+
+struct mdp4_format {
+	struct msm_format base;
+	enum mpd4_bpc bpc_r, bpc_g, bpc_b;
+	enum mpd4_bpc_alpha bpc_a;
+	uint8_t unpack[4];
+	bool alpha_enable, unpack_tight;
+	uint8_t cpp, unpack_count;
+};
+#define to_mdp4_format(x) container_of(x, struct mdp4_format, base)
+
+static inline void mdp4_write(struct mdp4_kms *mdp4_kms, u32 reg, u32 data)
+{
+	msm_writel(data, mdp4_kms->mmio + reg);
+}
+
+static inline u32 mdp4_read(struct mdp4_kms *mdp4_kms, u32 reg)
+{
+	return msm_readl(mdp4_kms->mmio + reg);
+}
+
+static inline uint32_t pipe2flush(enum mpd4_pipe pipe)
+{
+	switch (pipe) {
+	case VG1:      return MDP4_OVERLAY_FLUSH_VG1;
+	case VG2:      return MDP4_OVERLAY_FLUSH_VG2;
+	case RGB1:     return MDP4_OVERLAY_FLUSH_RGB1;
+	case RGB2:     return MDP4_OVERLAY_FLUSH_RGB1;
+	default:       return 0;
+	}
+}
+
+static inline uint32_t ovlp2flush(int ovlp)
+{
+	switch (ovlp) {
+	case 0:        return MDP4_OVERLAY_FLUSH_OVLP0;
+	case 1:        return MDP4_OVERLAY_FLUSH_OVLP1;
+	default:       return 0;
+	}
+}
+
+static inline uint32_t dma2irq(enum mdp4_dma dma)
+{
+	switch (dma) {
+	case DMA_P:    return MDP4_IRQ_DMA_P_DONE;
+	case DMA_S:    return MDP4_IRQ_DMA_S_DONE;
+	case DMA_E:    return MDP4_IRQ_DMA_E_DONE;
+	default:       return 0;
+	}
+}
+
+static inline uint32_t dma2err(enum mdp4_dma dma)
+{
+	switch (dma) {
+	case DMA_P:    return MDP4_IRQ_PRIMARY_INTF_UDERRUN;
+	case DMA_S:    return 0;  // ???
+	case DMA_E:    return MDP4_IRQ_EXTERNAL_INTF_UDERRUN;
+	default:       return 0;
+	}
+}
+
+int mdp4_disable(struct mdp4_kms *mdp4_kms);
+int mdp4_enable(struct mdp4_kms *mdp4_kms);
+
+void mdp4_irq_preinstall(struct msm_kms *kms);
+int mdp4_irq_postinstall(struct msm_kms *kms);
+void mdp4_irq_uninstall(struct msm_kms *kms);
+irqreturn_t mdp4_irq(struct msm_kms *kms);
+void mdp4_irq_wait(struct mdp4_kms *mdp4_kms, uint32_t irqmask);
+void mdp4_irq_register(struct mdp4_kms *mdp4_kms, struct mdp4_irq *irq);
+void mdp4_irq_unregister(struct mdp4_kms *mdp4_kms, struct mdp4_irq *irq);
+int mdp4_enable_vblank(struct msm_kms *kms, struct drm_crtc *crtc);
+void mdp4_disable_vblank(struct msm_kms *kms, struct drm_crtc *crtc);
+
+const struct msm_format *mdp4_get_format(struct msm_kms *kms, uint32_t format);
+
+void mdp4_plane_install_properties(struct drm_plane *plane,
+		struct drm_mode_object *obj);
+void mdp4_plane_set_scanout(struct drm_plane *plane,
+		struct drm_framebuffer *fb);
+int mdp4_plane_mode_set(struct drm_plane *plane,
+		struct drm_crtc *crtc, struct drm_framebuffer *fb,
+		int crtc_x, int crtc_y,
+		unsigned int crtc_w, unsigned int crtc_h,
+		uint32_t src_x, uint32_t src_y,
+		uint32_t src_w, uint32_t src_h);
+enum mpd4_pipe mdp4_plane_pipe(struct drm_plane *plane);
+struct drm_plane *mdp4_plane_init(struct drm_device *dev,
+		enum mpd4_pipe pipe_id, bool private_plane);
+
+uint32_t mdp4_crtc_vblank(struct drm_crtc *crtc);
+void mdp4_crtc_cancel_pending_flip(struct drm_crtc *crtc);
+void mdp4_crtc_set_config(struct drm_crtc *crtc, uint32_t config);
+void mdp4_crtc_set_intf(struct drm_crtc *crtc, enum mdp4_intf intf);
+struct drm_crtc *mdp4_crtc_init(struct drm_device *dev,
+		struct drm_plane *plane, int id, int ovlp_id,
+		enum mdp4_dma dma_id);
+
+long mdp4_dtv_round_pixclk(struct drm_encoder *encoder, unsigned long rate);
+struct drm_encoder *mdp4_dtv_encoder_init(struct drm_device *dev);
+
+#ifdef CONFIG_MSM_BUS_SCALING
+static inline int match_dev_name(struct device *dev, void *data)
+{
+	return !strcmp(dev_name(dev), data);
+}
+/* bus scaling data is associated with extra pointless platform devices,
+ * "dtv", etc.. this is a bit of a hack, but we need a way for encoders
+ * to find their pdata to make the bus-scaling stuff work.
+ */
+static inline void *mdp4_find_pdata(const char *devname)
+{
+	struct device *dev;
+	dev = bus_find_device(&platform_bus_type, NULL,
+			(void *)devname, match_dev_name);
+	return dev ? dev->platform_data : NULL;
+}
+#endif
+
+#endif /* __MDP4_KMS_H__ */
diff --git a/drivers/gpu/drm/msm/mdp4/mdp4_plane.c b/drivers/gpu/drm/msm/mdp4/mdp4_plane.c
new file mode 100644
index 000000000000..3468229d58b3
--- /dev/null
+++ b/drivers/gpu/drm/msm/mdp4/mdp4_plane.c
@@ -0,0 +1,243 @@
+/*
+ * Copyright (C) 2013 Red Hat
+ * Author: Rob Clark <robdclark@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include "mdp4_kms.h"
+
+
+struct mdp4_plane {
+	struct drm_plane base;
+	const char *name;
+
+	enum mpd4_pipe pipe;
+
+	uint32_t nformats;
+	uint32_t formats[32];
+
+	bool enabled;
+};
+#define to_mdp4_plane(x) container_of(x, struct mdp4_plane, base)
+
+static struct mdp4_kms *get_kms(struct drm_plane *plane)
+{
+	struct msm_drm_private *priv = plane->dev->dev_private;
+	return to_mdp4_kms(priv->kms);
+}
+
+static int mdp4_plane_update(struct drm_plane *plane,
+		struct drm_crtc *crtc, struct drm_framebuffer *fb,
+		int crtc_x, int crtc_y,
+		unsigned int crtc_w, unsigned int crtc_h,
+		uint32_t src_x, uint32_t src_y,
+		uint32_t src_w, uint32_t src_h)
+{
+	struct mdp4_plane *mdp4_plane = to_mdp4_plane(plane);
+
+	mdp4_plane->enabled = true;
+
+	if (plane->fb)
+		drm_framebuffer_unreference(plane->fb);
+
+	drm_framebuffer_reference(fb);
+
+	return mdp4_plane_mode_set(plane, crtc, fb,
+			crtc_x, crtc_y, crtc_w, crtc_h,
+			src_x, src_y, src_w, src_h);
+}
+
+static int mdp4_plane_disable(struct drm_plane *plane)
+{
+	struct mdp4_plane *mdp4_plane = to_mdp4_plane(plane);
+	DBG("%s: TODO", mdp4_plane->name); // XXX
+	return 0;
+}
+
+static void mdp4_plane_destroy(struct drm_plane *plane)
+{
+	struct mdp4_plane *mdp4_plane = to_mdp4_plane(plane);
+
+	mdp4_plane_disable(plane);
+	drm_plane_cleanup(plane);
+
+	kfree(mdp4_plane);
+}
+
+/* helper to install properties which are common to planes and crtcs */
+void mdp4_plane_install_properties(struct drm_plane *plane,
+		struct drm_mode_object *obj)
+{
+	// XXX
+}
+
+int mdp4_plane_set_property(struct drm_plane *plane,
+		struct drm_property *property, uint64_t val)
+{
+	// XXX
+	return -EINVAL;
+}
+
+static const struct drm_plane_funcs mdp4_plane_funcs = {
+		.update_plane = mdp4_plane_update,
+		.disable_plane = mdp4_plane_disable,
+		.destroy = mdp4_plane_destroy,
+		.set_property = mdp4_plane_set_property,
+};
+
+void mdp4_plane_set_scanout(struct drm_plane *plane,
+		struct drm_framebuffer *fb)
+{
+	struct mdp4_plane *mdp4_plane = to_mdp4_plane(plane);
+	struct mdp4_kms *mdp4_kms = get_kms(plane);
+	enum mpd4_pipe pipe = mdp4_plane->pipe;
+	uint32_t iova;
+
+	mdp4_write(mdp4_kms, REG_MDP4_PIPE_SRC_STRIDE_A(pipe),
+			MDP4_PIPE_SRC_STRIDE_A_P0(fb->pitches[0]) |
+			MDP4_PIPE_SRC_STRIDE_A_P1(fb->pitches[1]));
+
+	mdp4_write(mdp4_kms, REG_MDP4_PIPE_SRC_STRIDE_B(pipe),
+			MDP4_PIPE_SRC_STRIDE_B_P2(fb->pitches[2]) |
+			MDP4_PIPE_SRC_STRIDE_B_P3(fb->pitches[3]));
+
+	msm_gem_get_iova(msm_framebuffer_bo(fb, 0), mdp4_kms->id, &iova);
+	mdp4_write(mdp4_kms, REG_MDP4_PIPE_SRCP0_BASE(pipe), iova);
+
+	plane->fb = fb;
+}
+
+#define MDP4_VG_PHASE_STEP_DEFAULT	0x20000000
+
+int mdp4_plane_mode_set(struct drm_plane *plane,
+		struct drm_crtc *crtc, struct drm_framebuffer *fb,
+		int crtc_x, int crtc_y,
+		unsigned int crtc_w, unsigned int crtc_h,
+		uint32_t src_x, uint32_t src_y,
+		uint32_t src_w, uint32_t src_h)
+{
+	struct mdp4_plane *mdp4_plane = to_mdp4_plane(plane);
+	struct mdp4_kms *mdp4_kms = get_kms(plane);
+	enum mpd4_pipe pipe = mdp4_plane->pipe;
+	const struct mdp4_format *format;
+	uint32_t op_mode = 0;
+	uint32_t phasex_step = MDP4_VG_PHASE_STEP_DEFAULT;
+	uint32_t phasey_step = MDP4_VG_PHASE_STEP_DEFAULT;
+
+	/* src values are in Q16 fixed point, convert to integer: */
+	src_x = src_x >> 16;
+	src_y = src_y >> 16;
+	src_w = src_w >> 16;
+	src_h = src_h >> 16;
+
+	if (src_w != crtc_w) {
+		op_mode |= MDP4_PIPE_OP_MODE_SCALEX_EN;
+		/* TODO calc phasex_step */
+	}
+
+	if (src_h != crtc_h) {
+		op_mode |= MDP4_PIPE_OP_MODE_SCALEY_EN;
+		/* TODO calc phasey_step */
+	}
+
+	mdp4_write(mdp4_kms, REG_MDP4_PIPE_SRC_SIZE(pipe),
+			MDP4_PIPE_SRC_SIZE_WIDTH(src_w) |
+			MDP4_PIPE_SRC_SIZE_HEIGHT(src_h));
+
+	mdp4_write(mdp4_kms, REG_MDP4_PIPE_SRC_XY(pipe),
+			MDP4_PIPE_SRC_XY_X(src_x) |
+			MDP4_PIPE_SRC_XY_Y(src_y));
+
+	mdp4_write(mdp4_kms, REG_MDP4_PIPE_DST_SIZE(pipe),
+			MDP4_PIPE_DST_SIZE_WIDTH(crtc_w) |
+			MDP4_PIPE_DST_SIZE_HEIGHT(crtc_h));
+
+	mdp4_write(mdp4_kms, REG_MDP4_PIPE_DST_XY(pipe),
+			MDP4_PIPE_SRC_XY_X(crtc_x) |
+			MDP4_PIPE_SRC_XY_Y(crtc_y));
+
+	mdp4_plane_set_scanout(plane, fb);
+
+	format = to_mdp4_format(msm_framebuffer_format(fb));
+
+	mdp4_write(mdp4_kms, REG_MDP4_PIPE_SRC_FORMAT(pipe),
+			MDP4_PIPE_SRC_FORMAT_A_BPC(format->bpc_a) |
+			MDP4_PIPE_SRC_FORMAT_R_BPC(format->bpc_r) |
+			MDP4_PIPE_SRC_FORMAT_G_BPC(format->bpc_g) |
+			MDP4_PIPE_SRC_FORMAT_B_BPC(format->bpc_b) |
+			COND(format->alpha_enable, MDP4_PIPE_SRC_FORMAT_ALPHA_ENABLE) |
+			MDP4_PIPE_SRC_FORMAT_CPP(format->cpp - 1) |
+			MDP4_PIPE_SRC_FORMAT_UNPACK_COUNT(format->unpack_count - 1) |
+			COND(format->unpack_tight, MDP4_PIPE_SRC_FORMAT_UNPACK_TIGHT));
+
+	mdp4_write(mdp4_kms, REG_MDP4_PIPE_SRC_UNPACK(pipe),
+			MDP4_PIPE_SRC_UNPACK_ELEM0(format->unpack[0]) |
+			MDP4_PIPE_SRC_UNPACK_ELEM1(format->unpack[1]) |
+			MDP4_PIPE_SRC_UNPACK_ELEM2(format->unpack[2]) |
+			MDP4_PIPE_SRC_UNPACK_ELEM3(format->unpack[3]));
+
+	mdp4_write(mdp4_kms, REG_MDP4_PIPE_OP_MODE(pipe), op_mode);
+	mdp4_write(mdp4_kms, REG_MDP4_PIPE_PHASEX_STEP(pipe), phasex_step);
+	mdp4_write(mdp4_kms, REG_MDP4_PIPE_PHASEY_STEP(pipe), phasey_step);
+
+	plane->crtc = crtc;
+
+	return 0;
+}
+
+static const char *pipe_names[] = {
+		"VG1", "VG2",
+		"RGB1", "RGB2", "RGB3",
+		"VG3", "VG4",
+};
+
+enum mpd4_pipe mdp4_plane_pipe(struct drm_plane *plane)
+{
+	struct mdp4_plane *mdp4_plane = to_mdp4_plane(plane);
+	return mdp4_plane->pipe;
+}
+
+/* initialize plane */
+struct drm_plane *mdp4_plane_init(struct drm_device *dev,
+		enum mpd4_pipe pipe_id, bool private_plane)
+{
+	struct msm_drm_private *priv = dev->dev_private;
+	struct drm_plane *plane = NULL;
+	struct mdp4_plane *mdp4_plane;
+	int ret;
+
+	mdp4_plane = kzalloc(sizeof(*mdp4_plane), GFP_KERNEL);
+	if (!mdp4_plane) {
+		ret = -ENOMEM;
+		goto fail;
+	}
+
+	plane = &mdp4_plane->base;
+
+	mdp4_plane->pipe = pipe_id;
+	mdp4_plane->name = pipe_names[pipe_id];
+
+	drm_plane_init(dev, plane, (1 << priv->num_crtcs) - 1, &mdp4_plane_funcs,
+			mdp4_plane->formats, mdp4_plane->nformats, private_plane);
+
+	mdp4_plane_install_properties(plane, &plane->base);
+
+	return plane;
+
+fail:
+	if (plane)
+		mdp4_plane_destroy(plane);
+
+	return ERR_PTR(ret);
+}
diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
new file mode 100644
index 000000000000..b3a2f1629041
--- /dev/null
+++ b/drivers/gpu/drm/msm/msm_drv.c
@@ -0,0 +1,792 @@
+/*
+ * Copyright (C) 2013 Red Hat
+ * Author: Rob Clark <robdclark@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include "msm_drv.h"
+#include "msm_gpu.h"
+
+static void msm_fb_output_poll_changed(struct drm_device *dev)
+{
+	struct msm_drm_private *priv = dev->dev_private;
+	if (priv->fbdev)
+		drm_fb_helper_hotplug_event(priv->fbdev);
+}
+
+static const struct drm_mode_config_funcs mode_config_funcs = {
+	.fb_create = msm_framebuffer_create,
+	.output_poll_changed = msm_fb_output_poll_changed,
+};
+
+static int msm_fault_handler(struct iommu_domain *iommu, struct device *dev,
+		unsigned long iova, int flags, void *arg)
+{
+	DBG("*** fault: iova=%08lx, flags=%d", iova, flags);
+	return 0;
+}
+
+int msm_register_iommu(struct drm_device *dev, struct iommu_domain *iommu)
+{
+	struct msm_drm_private *priv = dev->dev_private;
+	int idx = priv->num_iommus++;
+
+	if (WARN_ON(idx >= ARRAY_SIZE(priv->iommus)))
+		return -EINVAL;
+
+	priv->iommus[idx] = iommu;
+
+	iommu_set_fault_handler(iommu, msm_fault_handler, dev);
+
+	/* need to iommu_attach_device() somewhere??  on resume?? */
+
+	return idx;
+}
+
+int msm_iommu_attach(struct drm_device *dev, struct iommu_domain *iommu,
+		const char **names, int cnt)
+{
+	int i, ret;
+
+	for (i = 0; i < cnt; i++) {
+		/* TODO maybe some day msm iommu won't require this hack: */
+		struct device *msm_iommu_get_ctx(const char *ctx_name);
+		struct device *ctx = msm_iommu_get_ctx(names[i]);
+		if (!ctx)
+			continue;
+		ret = iommu_attach_device(iommu, ctx);
+		if (ret) {
+			dev_warn(dev->dev, "could not attach iommu to %s", names[i]);
+			return ret;
+		}
+	}
+	return 0;
+}
+
+#ifdef CONFIG_DRM_MSM_REGISTER_LOGGING
+static bool reglog = false;
+MODULE_PARM_DESC(reglog, "Enable register read/write logging");
+module_param(reglog, bool, 0600);
+#else
+#define reglog 0
+#endif
+
+void __iomem *msm_ioremap(struct platform_device *pdev, const char *name,
+		const char *dbgname)
+{
+	struct resource *res;
+	unsigned long size;
+	void __iomem *ptr;
+
+	if (name)
+		res = platform_get_resource_byname(pdev, IORESOURCE_MEM, name);
+	else
+		res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+
+	if (!res) {
+		dev_err(&pdev->dev, "failed to get memory resource: %s\n", name);
+		return ERR_PTR(-EINVAL);
+	}
+
+	size = resource_size(res);
+
+	ptr = devm_ioremap_nocache(&pdev->dev, res->start, size);
+	if (!ptr) {
+		dev_err(&pdev->dev, "failed to ioremap: %s\n", name);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	if (reglog)
+		printk(KERN_DEBUG "IO:region %s %08x %08lx\n", dbgname, (u32)ptr, size);
+
+	return ptr;
+}
+
+void msm_writel(u32 data, void __iomem *addr)
+{
+	if (reglog)
+		printk(KERN_DEBUG "IO:W %08x %08x\n", (u32)addr, data);
+	writel(data, addr);
+}
+
+u32 msm_readl(const void __iomem *addr)
+{
+	u32 val = readl(addr);
+	if (reglog)
+		printk(KERN_ERR "IO:R %08x %08x\n", (u32)addr, val);
+	return val;
+}
+
+/*
+ * DRM operations:
+ */
+
+static int msm_unload(struct drm_device *dev)
+{
+	struct msm_drm_private *priv = dev->dev_private;
+	struct msm_kms *kms = priv->kms;
+	struct msm_gpu *gpu = priv->gpu;
+
+	drm_kms_helper_poll_fini(dev);
+	drm_mode_config_cleanup(dev);
+	drm_vblank_cleanup(dev);
+
+	pm_runtime_get_sync(dev->dev);
+	drm_irq_uninstall(dev);
+	pm_runtime_put_sync(dev->dev);
+
+	flush_workqueue(priv->wq);
+	destroy_workqueue(priv->wq);
+
+	if (kms) {
+		pm_runtime_disable(dev->dev);
+		kms->funcs->destroy(kms);
+	}
+
+	if (gpu) {
+		mutex_lock(&dev->struct_mutex);
+		gpu->funcs->pm_suspend(gpu);
+		gpu->funcs->destroy(gpu);
+		mutex_unlock(&dev->struct_mutex);
+	}
+
+	dev->dev_private = NULL;
+
+	kfree(priv);
+
+	return 0;
+}
+
+static int msm_load(struct drm_device *dev, unsigned long flags)
+{
+	struct platform_device *pdev = dev->platformdev;
+	struct msm_drm_private *priv;
+	struct msm_kms *kms;
+	int ret;
+
+	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
+	if (!priv) {
+		dev_err(dev->dev, "failed to allocate private data\n");
+		return -ENOMEM;
+	}
+
+	dev->dev_private = priv;
+
+	priv->wq = alloc_ordered_workqueue("msm", 0);
+	init_waitqueue_head(&priv->fence_event);
+
+	INIT_LIST_HEAD(&priv->inactive_list);
+
+	drm_mode_config_init(dev);
+
+	kms = mdp4_kms_init(dev);
+	if (IS_ERR(kms)) {
+		/*
+		 * NOTE: once we have GPU support, having no kms should not
+		 * be considered fatal.. ideally we would still support gpu
+		 * and (for example) use dmabuf/prime to share buffers with
+		 * imx drm driver on iMX5
+		 */
+		dev_err(dev->dev, "failed to load kms\n");
+		ret = PTR_ERR(kms);
+		goto fail;
+	}
+
+	priv->kms = kms;
+
+	if (kms) {
+		pm_runtime_enable(dev->dev);
+		ret = kms->funcs->hw_init(kms);
+		if (ret) {
+			dev_err(dev->dev, "kms hw init failed: %d\n", ret);
+			goto fail;
+		}
+	}
+
+	dev->mode_config.min_width = 0;
+	dev->mode_config.min_height = 0;
+	dev->mode_config.max_width = 2048;
+	dev->mode_config.max_height = 2048;
+	dev->mode_config.funcs = &mode_config_funcs;
+
+	ret = drm_vblank_init(dev, 1);
+	if (ret < 0) {
+		dev_err(dev->dev, "failed to initialize vblank\n");
+		goto fail;
+	}
+
+	pm_runtime_get_sync(dev->dev);
+	ret = drm_irq_install(dev);
+	pm_runtime_put_sync(dev->dev);
+	if (ret < 0) {
+		dev_err(dev->dev, "failed to install IRQ handler\n");
+		goto fail;
+	}
+
+	platform_set_drvdata(pdev, dev);
+
+#ifdef CONFIG_DRM_MSM_FBDEV
+	priv->fbdev = msm_fbdev_init(dev);
+#endif
+
+	drm_kms_helper_poll_init(dev);
+
+	return 0;
+
+fail:
+	msm_unload(dev);
+	return ret;
+}
+
+static void load_gpu(struct drm_device *dev)
+{
+	struct msm_drm_private *priv = dev->dev_private;
+	struct msm_gpu *gpu;
+
+	if (priv->gpu)
+		return;
+
+	mutex_lock(&dev->struct_mutex);
+	gpu = a3xx_gpu_init(dev);
+	if (IS_ERR(gpu)) {
+		dev_warn(dev->dev, "failed to load a3xx gpu\n");
+		gpu = NULL;
+		/* not fatal */
+	}
+	mutex_unlock(&dev->struct_mutex);
+
+	if (gpu) {
+		int ret;
+		gpu->funcs->pm_resume(gpu);
+		ret = gpu->funcs->hw_init(gpu);
+		if (ret) {
+			dev_err(dev->dev, "gpu hw init failed: %d\n", ret);
+			gpu->funcs->destroy(gpu);
+			gpu = NULL;
+		}
+	}
+
+	priv->gpu = gpu;
+}
+
+static int msm_open(struct drm_device *dev, struct drm_file *file)
+{
+	struct msm_file_private *ctx;
+
+	/* For now, load gpu on open.. to avoid the requirement of having
+	 * firmware in the initrd.
+	 */
+	load_gpu(dev);
+
+	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
+	if (!ctx)
+		return -ENOMEM;
+
+	file->driver_priv = ctx;
+
+	return 0;
+}
+
+static void msm_preclose(struct drm_device *dev, struct drm_file *file)
+{
+	struct msm_drm_private *priv = dev->dev_private;
+	struct msm_file_private *ctx = file->driver_priv;
+	struct msm_kms *kms = priv->kms;
+
+	if (kms)
+		kms->funcs->preclose(kms, file);
+
+	mutex_lock(&dev->struct_mutex);
+	if (ctx == priv->lastctx)
+		priv->lastctx = NULL;
+	mutex_unlock(&dev->struct_mutex);
+
+	kfree(ctx);
+}
+
+static void msm_lastclose(struct drm_device *dev)
+{
+	struct msm_drm_private *priv = dev->dev_private;
+	if (priv->fbdev) {
+		drm_modeset_lock_all(dev);
+		drm_fb_helper_restore_fbdev_mode(priv->fbdev);
+		drm_modeset_unlock_all(dev);
+	}
+}
+
+static irqreturn_t msm_irq(DRM_IRQ_ARGS)
+{
+	struct drm_device *dev = arg;
+	struct msm_drm_private *priv = dev->dev_private;
+	struct msm_kms *kms = priv->kms;
+	BUG_ON(!kms);
+	return kms->funcs->irq(kms);
+}
+
+static void msm_irq_preinstall(struct drm_device *dev)
+{
+	struct msm_drm_private *priv = dev->dev_private;
+	struct msm_kms *kms = priv->kms;
+	BUG_ON(!kms);
+	kms->funcs->irq_preinstall(kms);
+}
+
+static int msm_irq_postinstall(struct drm_device *dev)
+{
+	struct msm_drm_private *priv = dev->dev_private;
+	struct msm_kms *kms = priv->kms;
+	BUG_ON(!kms);
+	return kms->funcs->irq_postinstall(kms);
+}
+
+static void msm_irq_uninstall(struct drm_device *dev)
+{
+	struct msm_drm_private *priv = dev->dev_private;
+	struct msm_kms *kms = priv->kms;
+	BUG_ON(!kms);
+	kms->funcs->irq_uninstall(kms);
+}
+
+static int msm_enable_vblank(struct drm_device *dev, int crtc_id)
+{
+	struct msm_drm_private *priv = dev->dev_private;
+	struct msm_kms *kms = priv->kms;
+	if (!kms)
+		return -ENXIO;
+	DBG("dev=%p, crtc=%d", dev, crtc_id);
+	return kms->funcs->enable_vblank(kms, priv->crtcs[crtc_id]);
+}
+
+static void msm_disable_vblank(struct drm_device *dev, int crtc_id)
+{
+	struct msm_drm_private *priv = dev->dev_private;
+	struct msm_kms *kms = priv->kms;
+	if (!kms)
+		return;
+	DBG("dev=%p, crtc=%d", dev, crtc_id);
+	kms->funcs->disable_vblank(kms, priv->crtcs[crtc_id]);
+}
+
+/*
+ * DRM debugfs:
+ */
+
+#ifdef CONFIG_DEBUG_FS
+static int msm_gpu_show(struct drm_device *dev, struct seq_file *m)
+{
+	struct msm_drm_private *priv = dev->dev_private;
+	struct msm_gpu *gpu = priv->gpu;
+
+	if (gpu) {
+		seq_printf(m, "%s Status:\n", gpu->name);
+		gpu->funcs->show(gpu, m);
+	}
+
+	return 0;
+}
+
+static int msm_gem_show(struct drm_device *dev, struct seq_file *m)
+{
+	struct msm_drm_private *priv = dev->dev_private;
+	struct msm_gpu *gpu = priv->gpu;
+
+	if (gpu) {
+		seq_printf(m, "Active Objects (%s):\n", gpu->name);
+		msm_gem_describe_objects(&gpu->active_list, m);
+	}
+
+	seq_printf(m, "Inactive Objects:\n");
+	msm_gem_describe_objects(&priv->inactive_list, m);
+
+	return 0;
+}
+
+static int msm_mm_show(struct drm_device *dev, struct seq_file *m)
+{
+	return drm_mm_dump_table(m, dev->mm_private);
+}
+
+static int msm_fb_show(struct drm_device *dev, struct seq_file *m)
+{
+	struct msm_drm_private *priv = dev->dev_private;
+	struct drm_framebuffer *fb, *fbdev_fb = NULL;
+
+	if (priv->fbdev) {
+		seq_printf(m, "fbcon ");
+		fbdev_fb = priv->fbdev->fb;
+		msm_framebuffer_describe(fbdev_fb, m);
+	}
+
+	mutex_lock(&dev->mode_config.fb_lock);
+	list_for_each_entry(fb, &dev->mode_config.fb_list, head) {
+		if (fb == fbdev_fb)
+			continue;
+
+		seq_printf(m, "user ");
+		msm_framebuffer_describe(fb, m);
+	}
+	mutex_unlock(&dev->mode_config.fb_lock);
+
+	return 0;
+}
+
+static int show_locked(struct seq_file *m, void *arg)
+{
+	struct drm_info_node *node = (struct drm_info_node *) m->private;
+	struct drm_device *dev = node->minor->dev;
+	int (*show)(struct drm_device *dev, struct seq_file *m) =
+			node->info_ent->data;
+	int ret;
+
+	ret = mutex_lock_interruptible(&dev->struct_mutex);
+	if (ret)
+		return ret;
+
+	ret = show(dev, m);
+
+	mutex_unlock(&dev->struct_mutex);
+
+	return ret;
+}
+
+static struct drm_info_list msm_debugfs_list[] = {
+		{"gpu", show_locked, 0, msm_gpu_show},
+		{"gem", show_locked, 0, msm_gem_show},
+		{ "mm", show_locked, 0, msm_mm_show },
+		{ "fb", show_locked, 0, msm_fb_show },
+};
+
+static int msm_debugfs_init(struct drm_minor *minor)
+{
+	struct drm_device *dev = minor->dev;
+	int ret;
+
+	ret = drm_debugfs_create_files(msm_debugfs_list,
+			ARRAY_SIZE(msm_debugfs_list),
+			minor->debugfs_root, minor);
+
+	if (ret) {
+		dev_err(dev->dev, "could not install msm_debugfs_list\n");
+		return ret;
+	}
+
+	return ret;
+}
+
+static void msm_debugfs_cleanup(struct drm_minor *minor)
+{
+	drm_debugfs_remove_files(msm_debugfs_list,
+			ARRAY_SIZE(msm_debugfs_list), minor);
+}
+#endif
+
+/*
+ * Fences:
+ */
+
+int msm_wait_fence_interruptable(struct drm_device *dev, uint32_t fence,
+		struct timespec *timeout)
+{
+	struct msm_drm_private *priv = dev->dev_private;
+	int ret;
+
+	if (!priv->gpu)
+		return 0;
+
+	if (fence > priv->gpu->submitted_fence) {
+		DRM_ERROR("waiting on invalid fence: %u (of %u)\n",
+				fence, priv->gpu->submitted_fence);
+		return -EINVAL;
+	}
+
+	if (!timeout) {
+		/* no-wait: */
+		ret = fence_completed(dev, fence) ? 0 : -EBUSY;
+	} else {
+		unsigned long timeout_jiffies = timespec_to_jiffies(timeout);
+		unsigned long start_jiffies = jiffies;
+		unsigned long remaining_jiffies;
+
+		if (time_after(start_jiffies, timeout_jiffies))
+			remaining_jiffies = 0;
+		else
+			remaining_jiffies = timeout_jiffies - start_jiffies;
+
+		ret = wait_event_interruptible_timeout(priv->fence_event,
+				fence_completed(dev, fence),
+				remaining_jiffies);
+
+		if (ret == 0) {
+			DBG("timeout waiting for fence: %u (completed: %u)",
+					fence, priv->completed_fence);
+			ret = -ETIMEDOUT;
+		} else if (ret != -ERESTARTSYS) {
+			ret = 0;
+		}
+	}
+
+	return ret;
+}
+
+/* call under struct_mutex */
+void msm_update_fence(struct drm_device *dev, uint32_t fence)
+{
+	struct msm_drm_private *priv = dev->dev_private;
+
+	if (fence > priv->completed_fence) {
+		priv->completed_fence = fence;
+		wake_up_all(&priv->fence_event);
+	}
+}
+
+/*
+ * DRM ioctls:
+ */
+
+static int msm_ioctl_get_param(struct drm_device *dev, void *data,
+		struct drm_file *file)
+{
+	struct msm_drm_private *priv = dev->dev_private;
+	struct drm_msm_param *args = data;
+	struct msm_gpu *gpu;
+
+	/* for now, we just have 3d pipe.. eventually this would need to
+	 * be more clever to dispatch to appropriate gpu module:
+	 */
+	if (args->pipe != MSM_PIPE_3D0)
+		return -EINVAL;
+
+	gpu = priv->gpu;
+
+	if (!gpu)
+		return -ENXIO;
+
+	return gpu->funcs->get_param(gpu, args->param, &args->value);
+}
+
+static int msm_ioctl_gem_new(struct drm_device *dev, void *data,
+		struct drm_file *file)
+{
+	struct drm_msm_gem_new *args = data;
+	return msm_gem_new_handle(dev, file, args->size,
+			args->flags, &args->handle);
+}
+
+#define TS(t) ((struct timespec){ .tv_sec = (t).tv_sec, .tv_nsec = (t).tv_nsec })
+
+static int msm_ioctl_gem_cpu_prep(struct drm_device *dev, void *data,
+		struct drm_file *file)
+{
+	struct drm_msm_gem_cpu_prep *args = data;
+	struct drm_gem_object *obj;
+	int ret;
+
+	obj = drm_gem_object_lookup(dev, file, args->handle);
+	if (!obj)
+		return -ENOENT;
+
+	ret = msm_gem_cpu_prep(obj, args->op, &TS(args->timeout));
+
+	drm_gem_object_unreference_unlocked(obj);
+
+	return ret;
+}
+
+static int msm_ioctl_gem_cpu_fini(struct drm_device *dev, void *data,
+		struct drm_file *file)
+{
+	struct drm_msm_gem_cpu_fini *args = data;
+	struct drm_gem_object *obj;
+	int ret;
+
+	obj = drm_gem_object_lookup(dev, file, args->handle);
+	if (!obj)
+		return -ENOENT;
+
+	ret = msm_gem_cpu_fini(obj);
+
+	drm_gem_object_unreference_unlocked(obj);
+
+	return ret;
+}
+
+static int msm_ioctl_gem_info(struct drm_device *dev, void *data,
+		struct drm_file *file)
+{
+	struct drm_msm_gem_info *args = data;
+	struct drm_gem_object *obj;
+	int ret = 0;
+
+	if (args->pad)
+		return -EINVAL;
+
+	obj = drm_gem_object_lookup(dev, file, args->handle);
+	if (!obj)
+		return -ENOENT;
+
+	args->offset = msm_gem_mmap_offset(obj);
+
+	drm_gem_object_unreference_unlocked(obj);
+
+	return ret;
+}
+
+static int msm_ioctl_wait_fence(struct drm_device *dev, void *data,
+		struct drm_file *file)
+{
+	struct drm_msm_wait_fence *args = data;
+	return msm_wait_fence_interruptable(dev, args->fence, &TS(args->timeout));
+}
+
+static const struct drm_ioctl_desc msm_ioctls[] = {
+	DRM_IOCTL_DEF_DRV(MSM_GET_PARAM,    msm_ioctl_get_param,    DRM_UNLOCKED|DRM_AUTH),
+	DRM_IOCTL_DEF_DRV(MSM_GEM_NEW,      msm_ioctl_gem_new,      DRM_UNLOCKED|DRM_AUTH),
+	DRM_IOCTL_DEF_DRV(MSM_GEM_INFO,     msm_ioctl_gem_info,     DRM_UNLOCKED|DRM_AUTH),
+	DRM_IOCTL_DEF_DRV(MSM_GEM_CPU_PREP, msm_ioctl_gem_cpu_prep, DRM_UNLOCKED|DRM_AUTH),
+	DRM_IOCTL_DEF_DRV(MSM_GEM_CPU_FINI, msm_ioctl_gem_cpu_fini, DRM_UNLOCKED|DRM_AUTH),
+	DRM_IOCTL_DEF_DRV(MSM_GEM_SUBMIT,   msm_ioctl_gem_submit,   DRM_UNLOCKED|DRM_AUTH),
+	DRM_IOCTL_DEF_DRV(MSM_WAIT_FENCE,   msm_ioctl_wait_fence,   DRM_UNLOCKED|DRM_AUTH),
+};
+
+static const struct vm_operations_struct vm_ops = {
+	.fault = msm_gem_fault,
+	.open = drm_gem_vm_open,
+	.close = drm_gem_vm_close,
+};
+
+static const struct file_operations fops = {
+	.owner              = THIS_MODULE,
+	.open               = drm_open,
+	.release            = drm_release,
+	.unlocked_ioctl     = drm_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl       = drm_compat_ioctl,
+#endif
+	.poll               = drm_poll,
+	.read               = drm_read,
+	.llseek             = no_llseek,
+	.mmap               = msm_gem_mmap,
+};
+
+static struct drm_driver msm_driver = {
+	.driver_features    = DRIVER_HAVE_IRQ | DRIVER_GEM | DRIVER_MODESET,
+	.load               = msm_load,
+	.unload             = msm_unload,
+	.open               = msm_open,
+	.preclose           = msm_preclose,
+	.lastclose          = msm_lastclose,
+	.irq_handler        = msm_irq,
+	.irq_preinstall     = msm_irq_preinstall,
+	.irq_postinstall    = msm_irq_postinstall,
+	.irq_uninstall      = msm_irq_uninstall,
+	.get_vblank_counter = drm_vblank_count,
+	.enable_vblank      = msm_enable_vblank,
+	.disable_vblank     = msm_disable_vblank,
+	.gem_free_object    = msm_gem_free_object,
+	.gem_vm_ops         = &vm_ops,
+	.dumb_create        = msm_gem_dumb_create,
+	.dumb_map_offset    = msm_gem_dumb_map_offset,
+	.dumb_destroy       = drm_gem_dumb_destroy,
+#ifdef CONFIG_DEBUG_FS
+	.debugfs_init       = msm_debugfs_init,
+	.debugfs_cleanup    = msm_debugfs_cleanup,
+#endif
+	.ioctls             = msm_ioctls,
+	.num_ioctls         = DRM_MSM_NUM_IOCTLS,
+	.fops               = &fops,
+	.name               = "msm",
+	.desc               = "MSM Snapdragon DRM",
+	.date               = "20130625",
+	.major              = 1,
+	.minor              = 0,
+};
+
+#ifdef CONFIG_PM_SLEEP
+static int msm_pm_suspend(struct device *dev)
+{
+	struct drm_device *ddev = dev_get_drvdata(dev);
+
+	drm_kms_helper_poll_disable(ddev);
+
+	return 0;
+}
+
+static int msm_pm_resume(struct device *dev)
+{
+	struct drm_device *ddev = dev_get_drvdata(dev);
+
+	drm_kms_helper_poll_enable(ddev);
+
+	return 0;
+}
+#endif
+
+static const struct dev_pm_ops msm_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(msm_pm_suspend, msm_pm_resume)
+};
+
+/*
+ * Platform driver:
+ */
+
+static int msm_pdev_probe(struct platform_device *pdev)
+{
+	return drm_platform_init(&msm_driver, pdev);
+}
+
+static int msm_pdev_remove(struct platform_device *pdev)
+{
+	drm_platform_exit(&msm_driver, pdev);
+
+	return 0;
+}
+
+static const struct platform_device_id msm_id[] = {
+	{ "mdp", 0 },
+	{ }
+};
+
+static struct platform_driver msm_platform_driver = {
+	.probe      = msm_pdev_probe,
+	.remove     = msm_pdev_remove,
+	.driver     = {
+		.owner  = THIS_MODULE,
+		.name   = "msm",
+		.pm     = &msm_pm_ops,
+	},
+	.id_table   = msm_id,
+};
+
+static int __init msm_drm_register(void)
+{
+	DBG("init");
+	hdmi_register();
+	a3xx_register();
+	return platform_driver_register(&msm_platform_driver);
+}
+
+static void __exit msm_drm_unregister(void)
+{
+	DBG("fini");
+	platform_driver_unregister(&msm_platform_driver);
+	hdmi_unregister();
+	a3xx_unregister();
+}
+
+module_init(msm_drm_register);
+module_exit(msm_drm_unregister);
+
+MODULE_AUTHOR("Rob Clark <robdclark@gmail.com");
+MODULE_DESCRIPTION("MSM DRM Driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/gpu/drm/msm/msm_drv.h b/drivers/gpu/drm/msm/msm_drv.h
new file mode 100644
index 000000000000..df8f1d084bc1
--- /dev/null
+++ b/drivers/gpu/drm/msm/msm_drv.h
@@ -0,0 +1,219 @@
+/*
+ * Copyright (C) 2013 Red Hat
+ * Author: Rob Clark <robdclark@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __MSM_DRV_H__
+#define __MSM_DRV_H__
+
+#include <linux/kernel.h>
+#include <linux/clk.h>
+#include <linux/cpufreq.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/pm.h>
+#include <linux/pm_runtime.h>
+#include <linux/slab.h>
+#include <linux/list.h>
+#include <linux/iommu.h>
+#include <linux/types.h>
+#include <asm/sizes.h>
+
+#ifndef CONFIG_OF
+#include <mach/board.h>
+#include <mach/socinfo.h>
+#include <mach/iommu_domains.h>
+#endif
+
+#include <drm/drmP.h>
+#include <drm/drm_crtc_helper.h>
+#include <drm/drm_fb_helper.h>
+#include <drm/msm_drm.h>
+
+struct msm_kms;
+struct msm_gpu;
+
+#define NUM_DOMAINS 2    /* one for KMS, then one per gpu core (?) */
+
+struct msm_file_private {
+	/* currently we don't do anything useful with this.. but when
+	 * per-context address spaces are supported we'd keep track of
+	 * the context's page-tables here.
+	 */
+	int dummy;
+};
+
+struct msm_drm_private {
+
+	struct msm_kms *kms;
+
+	/* when we have more than one 'msm_gpu' these need to be an array: */
+	struct msm_gpu *gpu;
+	struct msm_file_private *lastctx;
+
+	struct drm_fb_helper *fbdev;
+
+	uint32_t next_fence, completed_fence;
+	wait_queue_head_t fence_event;
+
+	/* list of GEM objects: */
+	struct list_head inactive_list;
+
+	struct workqueue_struct *wq;
+
+	/* registered IOMMU domains: */
+	unsigned int num_iommus;
+	struct iommu_domain *iommus[NUM_DOMAINS];
+
+	unsigned int num_crtcs;
+	struct drm_crtc *crtcs[8];
+
+	unsigned int num_encoders;
+	struct drm_encoder *encoders[8];
+
+	unsigned int num_bridges;
+	struct drm_bridge *bridges[8];
+
+	unsigned int num_connectors;
+	struct drm_connector *connectors[8];
+};
+
+struct msm_format {
+	uint32_t pixel_format;
+};
+
+/* As there are different display controller blocks depending on the
+ * snapdragon version, the kms support is split out and the appropriate
+ * implementation is loaded at runtime.  The kms module is responsible
+ * for constructing the appropriate planes/crtcs/encoders/connectors.
+ */
+struct msm_kms_funcs {
+	/* hw initialization: */
+	int (*hw_init)(struct msm_kms *kms);
+	/* irq handling: */
+	void (*irq_preinstall)(struct msm_kms *kms);
+	int (*irq_postinstall)(struct msm_kms *kms);
+	void (*irq_uninstall)(struct msm_kms *kms);
+	irqreturn_t (*irq)(struct msm_kms *kms);
+	int (*enable_vblank)(struct msm_kms *kms, struct drm_crtc *crtc);
+	void (*disable_vblank)(struct msm_kms *kms, struct drm_crtc *crtc);
+	/* misc: */
+	const struct msm_format *(*get_format)(struct msm_kms *kms, uint32_t format);
+	long (*round_pixclk)(struct msm_kms *kms, unsigned long rate,
+			struct drm_encoder *encoder);
+	/* cleanup: */
+	void (*preclose)(struct msm_kms *kms, struct drm_file *file);
+	void (*destroy)(struct msm_kms *kms);
+};
+
+struct msm_kms {
+	const struct msm_kms_funcs *funcs;
+};
+
+struct msm_kms *mdp4_kms_init(struct drm_device *dev);
+
+int msm_register_iommu(struct drm_device *dev, struct iommu_domain *iommu);
+int msm_iommu_attach(struct drm_device *dev, struct iommu_domain *iommu,
+		const char **names, int cnt);
+
+int msm_wait_fence_interruptable(struct drm_device *dev, uint32_t fence,
+		struct timespec *timeout);
+void msm_update_fence(struct drm_device *dev, uint32_t fence);
+
+int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
+		struct drm_file *file);
+
+int msm_gem_mmap(struct file *filp, struct vm_area_struct *vma);
+int msm_gem_fault(struct vm_area_struct *vma, struct vm_fault *vmf);
+uint64_t msm_gem_mmap_offset(struct drm_gem_object *obj);
+int msm_gem_get_iova_locked(struct drm_gem_object *obj, int id,
+		uint32_t *iova);
+int msm_gem_get_iova(struct drm_gem_object *obj, int id, uint32_t *iova);
+void msm_gem_put_iova(struct drm_gem_object *obj, int id);
+int msm_gem_dumb_create(struct drm_file *file, struct drm_device *dev,
+		struct drm_mode_create_dumb *args);
+int msm_gem_dumb_destroy(struct drm_file *file, struct drm_device *dev,
+		uint32_t handle);
+int msm_gem_dumb_map_offset(struct drm_file *file, struct drm_device *dev,
+		uint32_t handle, uint64_t *offset);
+void *msm_gem_vaddr_locked(struct drm_gem_object *obj);
+void *msm_gem_vaddr(struct drm_gem_object *obj);
+int msm_gem_queue_inactive_work(struct drm_gem_object *obj,
+		struct work_struct *work);
+void msm_gem_move_to_active(struct drm_gem_object *obj,
+		struct msm_gpu *gpu, bool write, uint32_t fence);
+void msm_gem_move_to_inactive(struct drm_gem_object *obj);
+int msm_gem_cpu_prep(struct drm_gem_object *obj, uint32_t op,
+		struct timespec *timeout);
+int msm_gem_cpu_fini(struct drm_gem_object *obj);
+void msm_gem_free_object(struct drm_gem_object *obj);
+int msm_gem_new_handle(struct drm_device *dev, struct drm_file *file,
+		uint32_t size, uint32_t flags, uint32_t *handle);
+struct drm_gem_object *msm_gem_new(struct drm_device *dev,
+		uint32_t size, uint32_t flags);
+
+struct drm_gem_object *msm_framebuffer_bo(struct drm_framebuffer *fb, int plane);
+const struct msm_format *msm_framebuffer_format(struct drm_framebuffer *fb);
+struct drm_framebuffer *msm_framebuffer_init(struct drm_device *dev,
+		struct drm_mode_fb_cmd2 *mode_cmd, struct drm_gem_object **bos);
+struct drm_framebuffer *msm_framebuffer_create(struct drm_device *dev,
+		struct drm_file *file, struct drm_mode_fb_cmd2 *mode_cmd);
+
+struct drm_fb_helper *msm_fbdev_init(struct drm_device *dev);
+
+int hdmi_init(struct drm_device *dev, struct drm_encoder *encoder);
+void __init hdmi_register(void);
+void __exit hdmi_unregister(void);
+
+#ifdef CONFIG_DEBUG_FS
+void msm_gem_describe(struct drm_gem_object *obj, struct seq_file *m);
+void msm_gem_describe_objects(struct list_head *list, struct seq_file *m);
+void msm_framebuffer_describe(struct drm_framebuffer *fb, struct seq_file *m);
+#endif
+
+void __iomem *msm_ioremap(struct platform_device *pdev, const char *name,
+		const char *dbgname);
+void msm_writel(u32 data, void __iomem *addr);
+u32 msm_readl(const void __iomem *addr);
+
+#define DBG(fmt, ...) DRM_DEBUG(fmt"\n", ##__VA_ARGS__)
+#define VERB(fmt, ...) if (0) DRM_DEBUG(fmt"\n", ##__VA_ARGS__)
+
+static inline bool fence_completed(struct drm_device *dev, uint32_t fence)
+{
+	struct msm_drm_private *priv = dev->dev_private;
+	return priv->completed_fence >= fence;
+}
+
+static inline int align_pitch(int width, int bpp)
+{
+	int bytespp = (bpp + 7) / 8;
+	/* adreno needs pitch aligned to 32 pixels: */
+	return bytespp * ALIGN(width, 32);
+}
+
+/* for the generated headers: */
+#define INVALID_IDX(idx) ({BUG(); 0;})
+#define fui(x)                ({BUG(); 0;})
+#define util_float_to_half(x) ({BUG(); 0;})
+
+
+#define FIELD(val, name) (((val) & name ## __MASK) >> name ## __SHIFT)
+
+/* for conditionally setting boolean flag(s): */
+#define COND(bool, val) ((bool) ? (val) : 0)
+
+
+#endif /* __MSM_DRV_H__ */
diff --git a/drivers/gpu/drm/msm/msm_fb.c b/drivers/gpu/drm/msm/msm_fb.c
new file mode 100644
index 000000000000..0286c0eeb10c
--- /dev/null
+++ b/drivers/gpu/drm/msm/msm_fb.c
@@ -0,0 +1,202 @@
+/*
+ * Copyright (C) 2013 Red Hat
+ * Author: Rob Clark <robdclark@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include "msm_drv.h"
+
+#include "drm_crtc.h"
+#include "drm_crtc_helper.h"
+
+struct msm_framebuffer {
+	struct drm_framebuffer base;
+	const struct msm_format *format;
+	struct drm_gem_object *planes[2];
+};
+#define to_msm_framebuffer(x) container_of(x, struct msm_framebuffer, base)
+
+
+static int msm_framebuffer_create_handle(struct drm_framebuffer *fb,
+		struct drm_file *file_priv,
+		unsigned int *handle)
+{
+	struct msm_framebuffer *msm_fb = to_msm_framebuffer(fb);
+	return drm_gem_handle_create(file_priv,
+			msm_fb->planes[0], handle);
+}
+
+static void msm_framebuffer_destroy(struct drm_framebuffer *fb)
+{
+	struct msm_framebuffer *msm_fb = to_msm_framebuffer(fb);
+	int i, n = drm_format_num_planes(fb->pixel_format);
+
+	DBG("destroy: FB ID: %d (%p)", fb->base.id, fb);
+
+	drm_framebuffer_cleanup(fb);
+
+	for (i = 0; i < n; i++) {
+		struct drm_gem_object *bo = msm_fb->planes[i];
+		if (bo)
+			drm_gem_object_unreference_unlocked(bo);
+	}
+
+	kfree(msm_fb);
+}
+
+static int msm_framebuffer_dirty(struct drm_framebuffer *fb,
+		struct drm_file *file_priv, unsigned flags, unsigned color,
+		struct drm_clip_rect *clips, unsigned num_clips)
+{
+	return 0;
+}
+
+static const struct drm_framebuffer_funcs msm_framebuffer_funcs = {
+	.create_handle = msm_framebuffer_create_handle,
+	.destroy = msm_framebuffer_destroy,
+	.dirty = msm_framebuffer_dirty,
+};
+
+#ifdef CONFIG_DEBUG_FS
+void msm_framebuffer_describe(struct drm_framebuffer *fb, struct seq_file *m)
+{
+	struct msm_framebuffer *msm_fb = to_msm_framebuffer(fb);
+	int i, n = drm_format_num_planes(fb->pixel_format);
+
+	seq_printf(m, "fb: %dx%d@%4.4s (%2d, ID:%d)\n",
+			fb->width, fb->height, (char *)&fb->pixel_format,
+			fb->refcount.refcount.counter, fb->base.id);
+
+	for (i = 0; i < n; i++) {
+		seq_printf(m, "   %d: offset=%d pitch=%d, obj: ",
+				i, fb->offsets[i], fb->pitches[i]);
+		msm_gem_describe(msm_fb->planes[i], m);
+	}
+}
+#endif
+
+struct drm_gem_object *msm_framebuffer_bo(struct drm_framebuffer *fb, int plane)
+{
+	struct msm_framebuffer *msm_fb = to_msm_framebuffer(fb);
+	return msm_fb->planes[plane];
+}
+
+const struct msm_format *msm_framebuffer_format(struct drm_framebuffer *fb)
+{
+	struct msm_framebuffer *msm_fb = to_msm_framebuffer(fb);
+	return msm_fb->format;
+}
+
+struct drm_framebuffer *msm_framebuffer_create(struct drm_device *dev,
+		struct drm_file *file, struct drm_mode_fb_cmd2 *mode_cmd)
+{
+	struct drm_gem_object *bos[4] = {0};
+	struct drm_framebuffer *fb;
+	int ret, i, n = drm_format_num_planes(mode_cmd->pixel_format);
+
+	for (i = 0; i < n; i++) {
+		bos[i] = drm_gem_object_lookup(dev, file,
+				mode_cmd->handles[i]);
+		if (!bos[i]) {
+			ret = -ENXIO;
+			goto out_unref;
+		}
+	}
+
+	fb = msm_framebuffer_init(dev, mode_cmd, bos);
+	if (IS_ERR(fb)) {
+		ret = PTR_ERR(fb);
+		goto out_unref;
+	}
+
+	return fb;
+
+out_unref:
+	for (i = 0; i < n; i++)
+		drm_gem_object_unreference_unlocked(bos[i]);
+	return ERR_PTR(ret);
+}
+
+struct drm_framebuffer *msm_framebuffer_init(struct drm_device *dev,
+		struct drm_mode_fb_cmd2 *mode_cmd, struct drm_gem_object **bos)
+{
+	struct msm_drm_private *priv = dev->dev_private;
+	struct msm_kms *kms = priv->kms;
+	struct msm_framebuffer *msm_fb;
+	struct drm_framebuffer *fb = NULL;
+	const struct msm_format *format;
+	int ret, i, n;
+	unsigned int hsub, vsub;
+
+	DBG("create framebuffer: dev=%p, mode_cmd=%p (%dx%d@%4.4s)",
+			dev, mode_cmd, mode_cmd->width, mode_cmd->height,
+			(char *)&mode_cmd->pixel_format);
+
+	n = drm_format_num_planes(mode_cmd->pixel_format);
+	hsub = drm_format_horz_chroma_subsampling(mode_cmd->pixel_format);
+	vsub = drm_format_vert_chroma_subsampling(mode_cmd->pixel_format);
+
+	format = kms->funcs->get_format(kms, mode_cmd->pixel_format);
+	if (!format) {
+		dev_err(dev->dev, "unsupported pixel format: %4.4s\n",
+				(char *)&mode_cmd->pixel_format);
+		ret = -EINVAL;
+		goto fail;
+	}
+
+	msm_fb = kzalloc(sizeof(*msm_fb), GFP_KERNEL);
+	if (!msm_fb) {
+		ret = -ENOMEM;
+		goto fail;
+	}
+
+	fb = &msm_fb->base;
+
+	msm_fb->format = format;
+
+	for (i = 0; i < n; i++) {
+		unsigned int width = mode_cmd->width / (i ? hsub : 1);
+		unsigned int height = mode_cmd->height / (i ? vsub : 1);
+		unsigned int min_size;
+
+		min_size = (height - 1) * mode_cmd->pitches[i]
+			 + width * drm_format_plane_cpp(mode_cmd->pixel_format, i)
+			 + mode_cmd->offsets[i];
+
+		if (bos[i]->size < min_size) {
+			ret = -EINVAL;
+			goto fail;
+		}
+
+		msm_fb->planes[i] = bos[i];
+	}
+
+	drm_helper_mode_fill_fb_struct(fb, mode_cmd);
+
+	ret = drm_framebuffer_init(dev, fb, &msm_framebuffer_funcs);
+	if (ret) {
+		dev_err(dev->dev, "framebuffer init failed: %d\n", ret);
+		goto fail;
+	}
+
+	DBG("create: FB ID: %d (%p)", fb->base.id, fb);
+
+	return fb;
+
+fail:
+	if (fb)
+		msm_framebuffer_destroy(fb);
+
+	return ERR_PTR(ret);
+}
diff --git a/drivers/gpu/drm/msm/msm_fbdev.c b/drivers/gpu/drm/msm/msm_fbdev.c
new file mode 100644
index 000000000000..6c6d7d4c9b4e
--- /dev/null
+++ b/drivers/gpu/drm/msm/msm_fbdev.c
@@ -0,0 +1,258 @@
+/*
+ * Copyright (C) 2013 Red Hat
+ * Author: Rob Clark <robdclark@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include "msm_drv.h"
+
+#include "drm_crtc.h"
+#include "drm_fb_helper.h"
+
+/*
+ * fbdev funcs, to implement legacy fbdev interface on top of drm driver
+ */
+
+#define to_msm_fbdev(x) container_of(x, struct msm_fbdev, base)
+
+struct msm_fbdev {
+	struct drm_fb_helper base;
+	struct drm_framebuffer *fb;
+	struct drm_gem_object *bo;
+};
+
+static struct fb_ops msm_fb_ops = {
+	.owner = THIS_MODULE,
+
+	/* Note: to properly handle manual update displays, we wrap the
+	 * basic fbdev ops which write to the framebuffer
+	 */
+	.fb_read = fb_sys_read,
+	.fb_write = fb_sys_write,
+	.fb_fillrect = sys_fillrect,
+	.fb_copyarea = sys_copyarea,
+	.fb_imageblit = sys_imageblit,
+
+	.fb_check_var = drm_fb_helper_check_var,
+	.fb_set_par = drm_fb_helper_set_par,
+	.fb_pan_display = drm_fb_helper_pan_display,
+	.fb_blank = drm_fb_helper_blank,
+	.fb_setcmap = drm_fb_helper_setcmap,
+};
+
+static int msm_fbdev_create(struct drm_fb_helper *helper,
+		struct drm_fb_helper_surface_size *sizes)
+{
+	struct msm_fbdev *fbdev = to_msm_fbdev(helper);
+	struct drm_device *dev = helper->dev;
+	struct drm_framebuffer *fb = NULL;
+	struct fb_info *fbi = NULL;
+	struct drm_mode_fb_cmd2 mode_cmd = {0};
+	dma_addr_t paddr;
+	int ret, size;
+
+	/* only doing ARGB32 since this is what is needed to alpha-blend
+	 * with video overlays:
+	 */
+	sizes->surface_bpp = 32;
+	sizes->surface_depth = 32;
+
+	DBG("create fbdev: %dx%d@%d (%dx%d)", sizes->surface_width,
+			sizes->surface_height, sizes->surface_bpp,
+			sizes->fb_width, sizes->fb_height);
+
+	mode_cmd.pixel_format = drm_mode_legacy_fb_format(sizes->surface_bpp,
+			sizes->surface_depth);
+
+	mode_cmd.width = sizes->surface_width;
+	mode_cmd.height = sizes->surface_height;
+
+	mode_cmd.pitches[0] = align_pitch(
+			mode_cmd.width, sizes->surface_bpp);
+
+	/* allocate backing bo */
+	size = mode_cmd.pitches[0] * mode_cmd.height;
+	DBG("allocating %d bytes for fb %d", size, dev->primary->index);
+	mutex_lock(&dev->struct_mutex);
+	fbdev->bo = msm_gem_new(dev, size, MSM_BO_SCANOUT | MSM_BO_WC);
+	mutex_unlock(&dev->struct_mutex);
+	if (IS_ERR(fbdev->bo)) {
+		ret = PTR_ERR(fbdev->bo);
+		fbdev->bo = NULL;
+		dev_err(dev->dev, "failed to allocate buffer object: %d\n", ret);
+		goto fail;
+	}
+
+	fb = msm_framebuffer_init(dev, &mode_cmd, &fbdev->bo);
+	if (IS_ERR(fb)) {
+		dev_err(dev->dev, "failed to allocate fb\n");
+		/* note: if fb creation failed, we can't rely on fb destroy
+		 * to unref the bo:
+		 */
+		drm_gem_object_unreference(fbdev->bo);
+		ret = PTR_ERR(fb);
+		goto fail;
+	}
+
+	mutex_lock(&dev->struct_mutex);
+
+	/* TODO implement our own fb_mmap so we don't need this: */
+	msm_gem_get_iova_locked(fbdev->bo, 0, &paddr);
+
+	fbi = framebuffer_alloc(0, dev->dev);
+	if (!fbi) {
+		dev_err(dev->dev, "failed to allocate fb info\n");
+		ret = -ENOMEM;
+		goto fail_unlock;
+	}
+
+	DBG("fbi=%p, dev=%p", fbi, dev);
+
+	fbdev->fb = fb;
+	helper->fb = fb;
+	helper->fbdev = fbi;
+
+	fbi->par = helper;
+	fbi->flags = FBINFO_DEFAULT;
+	fbi->fbops = &msm_fb_ops;
+
+	strcpy(fbi->fix.id, "msm");
+
+	ret = fb_alloc_cmap(&fbi->cmap, 256, 0);
+	if (ret) {
+		ret = -ENOMEM;
+		goto fail_unlock;
+	}
+
+	drm_fb_helper_fill_fix(fbi, fb->pitches[0], fb->depth);
+	drm_fb_helper_fill_var(fbi, helper, sizes->fb_width, sizes->fb_height);
+
+	dev->mode_config.fb_base = paddr;
+
+	fbi->screen_base = msm_gem_vaddr_locked(fbdev->bo);
+	fbi->screen_size = fbdev->bo->size;
+	fbi->fix.smem_start = paddr;
+	fbi->fix.smem_len = fbdev->bo->size;
+
+	DBG("par=%p, %dx%d", fbi->par, fbi->var.xres, fbi->var.yres);
+	DBG("allocated %dx%d fb", fbdev->fb->width, fbdev->fb->height);
+
+	mutex_unlock(&dev->struct_mutex);
+
+	return 0;
+
+fail_unlock:
+	mutex_unlock(&dev->struct_mutex);
+fail:
+
+	if (ret) {
+		if (fbi)
+			framebuffer_release(fbi);
+		if (fb) {
+			drm_framebuffer_unregister_private(fb);
+			drm_framebuffer_remove(fb);
+		}
+	}
+
+	return ret;
+}
+
+static void msm_crtc_fb_gamma_set(struct drm_crtc *crtc,
+		u16 red, u16 green, u16 blue, int regno)
+{
+	DBG("fbdev: set gamma");
+}
+
+static void msm_crtc_fb_gamma_get(struct drm_crtc *crtc,
+		u16 *red, u16 *green, u16 *blue, int regno)
+{
+	DBG("fbdev: get gamma");
+}
+
+static struct drm_fb_helper_funcs msm_fb_helper_funcs = {
+	.gamma_set = msm_crtc_fb_gamma_set,
+	.gamma_get = msm_crtc_fb_gamma_get,
+	.fb_probe = msm_fbdev_create,
+};
+
+/* initialize fbdev helper */
+struct drm_fb_helper *msm_fbdev_init(struct drm_device *dev)
+{
+	struct msm_drm_private *priv = dev->dev_private;
+	struct msm_fbdev *fbdev = NULL;
+	struct drm_fb_helper *helper;
+	int ret = 0;
+
+	fbdev = kzalloc(sizeof(*fbdev), GFP_KERNEL);
+	if (!fbdev)
+		goto fail;
+
+	helper = &fbdev->base;
+
+	helper->funcs = &msm_fb_helper_funcs;
+
+	ret = drm_fb_helper_init(dev, helper,
+			priv->num_crtcs, priv->num_connectors);
+	if (ret) {
+		dev_err(dev->dev, "could not init fbdev: ret=%d\n", ret);
+		goto fail;
+	}
+
+	drm_fb_helper_single_add_all_connectors(helper);
+
+	/* disable all the possible outputs/crtcs before entering KMS mode */
+	drm_helper_disable_unused_functions(dev);
+
+	drm_fb_helper_initial_config(helper, 32);
+
+	priv->fbdev = helper;
+
+	return helper;
+
+fail:
+	kfree(fbdev);
+	return NULL;
+}
+
+void msm_fbdev_free(struct drm_device *dev)
+{
+	struct msm_drm_private *priv = dev->dev_private;
+	struct drm_fb_helper *helper = priv->fbdev;
+	struct msm_fbdev *fbdev;
+	struct fb_info *fbi;
+
+	DBG();
+
+	fbi = helper->fbdev;
+
+	/* only cleanup framebuffer if it is present */
+	if (fbi) {
+		unregister_framebuffer(fbi);
+		framebuffer_release(fbi);
+	}
+
+	drm_fb_helper_fini(helper);
+
+	fbdev = to_msm_fbdev(priv->fbdev);
+
+	/* this will free the backing object */
+	if (fbdev->fb) {
+		drm_framebuffer_unregister_private(fbdev->fb);
+		drm_framebuffer_remove(fbdev->fb);
+	}
+
+	kfree(fbdev);
+
+	priv->fbdev = NULL;
+}
diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c
new file mode 100644
index 000000000000..2bae46c66a30
--- /dev/null
+++ b/drivers/gpu/drm/msm/msm_gem.c
@@ -0,0 +1,604 @@
+/*
+ * Copyright (C) 2013 Red Hat
+ * Author: Rob Clark <robdclark@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/spinlock.h>
+#include <linux/shmem_fs.h>
+
+#include "msm_drv.h"
+#include "msm_gem.h"
+#include "msm_gpu.h"
+
+
+/* called with dev->struct_mutex held */
+static struct page **get_pages(struct drm_gem_object *obj)
+{
+	struct msm_gem_object *msm_obj = to_msm_bo(obj);
+
+	if (!msm_obj->pages) {
+		struct drm_device *dev = obj->dev;
+		struct page **p = drm_gem_get_pages(obj, 0);
+		int npages = obj->size >> PAGE_SHIFT;
+
+		if (IS_ERR(p)) {
+			dev_err(dev->dev, "could not get pages: %ld\n",
+					PTR_ERR(p));
+			return p;
+		}
+
+		msm_obj->sgt = drm_prime_pages_to_sg(p, npages);
+		if (IS_ERR(msm_obj->sgt)) {
+			dev_err(dev->dev, "failed to allocate sgt\n");
+			return ERR_CAST(msm_obj->sgt);
+		}
+
+		msm_obj->pages = p;
+
+		/* For non-cached buffers, ensure the new pages are clean
+		 * because display controller, GPU, etc. are not coherent:
+		 */
+		if (msm_obj->flags & (MSM_BO_WC|MSM_BO_UNCACHED))
+			dma_map_sg(dev->dev, msm_obj->sgt->sgl,
+					msm_obj->sgt->nents, DMA_BIDIRECTIONAL);
+	}
+
+	return msm_obj->pages;
+}
+
+static void put_pages(struct drm_gem_object *obj)
+{
+	struct msm_gem_object *msm_obj = to_msm_bo(obj);
+
+	if (msm_obj->pages) {
+		/* For non-cached buffers, ensure the new pages are clean
+		 * because display controller, GPU, etc. are not coherent:
+		 */
+		if (msm_obj->flags & (MSM_BO_WC|MSM_BO_UNCACHED))
+			dma_unmap_sg(obj->dev->dev, msm_obj->sgt->sgl,
+					msm_obj->sgt->nents, DMA_BIDIRECTIONAL);
+		sg_free_table(msm_obj->sgt);
+		kfree(msm_obj->sgt);
+
+		drm_gem_put_pages(obj, msm_obj->pages, true, false);
+		msm_obj->pages = NULL;
+	}
+}
+
+int msm_gem_mmap_obj(struct drm_gem_object *obj,
+		struct vm_area_struct *vma)
+{
+	struct msm_gem_object *msm_obj = to_msm_bo(obj);
+
+	vma->vm_flags &= ~VM_PFNMAP;
+	vma->vm_flags |= VM_MIXEDMAP;
+
+	if (msm_obj->flags & MSM_BO_WC) {
+		vma->vm_page_prot = pgprot_writecombine(vm_get_page_prot(vma->vm_flags));
+	} else if (msm_obj->flags & MSM_BO_UNCACHED) {
+		vma->vm_page_prot = pgprot_noncached(vm_get_page_prot(vma->vm_flags));
+	} else {
+		/*
+		 * Shunt off cached objs to shmem file so they have their own
+		 * address_space (so unmap_mapping_range does what we want,
+		 * in particular in the case of mmap'd dmabufs)
+		 */
+		fput(vma->vm_file);
+		get_file(obj->filp);
+		vma->vm_pgoff = 0;
+		vma->vm_file  = obj->filp;
+
+		vma->vm_page_prot = vm_get_page_prot(vma->vm_flags);
+	}
+
+	return 0;
+}
+
+int msm_gem_mmap(struct file *filp, struct vm_area_struct *vma)
+{
+	int ret;
+
+	ret = drm_gem_mmap(filp, vma);
+	if (ret) {
+		DBG("mmap failed: %d", ret);
+		return ret;
+	}
+
+	return msm_gem_mmap_obj(vma->vm_private_data, vma);
+}
+
+int msm_gem_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+	struct drm_gem_object *obj = vma->vm_private_data;
+	struct msm_gem_object *msm_obj = to_msm_bo(obj);
+	struct drm_device *dev = obj->dev;
+	struct page **pages;
+	unsigned long pfn;
+	pgoff_t pgoff;
+	int ret;
+
+	/* Make sure we don't parallel update on a fault, nor move or remove
+	 * something from beneath our feet
+	 */
+	ret = mutex_lock_interruptible(&dev->struct_mutex);
+	if (ret)
+		goto out;
+
+	/* make sure we have pages attached now */
+	pages = get_pages(obj);
+	if (IS_ERR(pages)) {
+		ret = PTR_ERR(pages);
+		goto out_unlock;
+	}
+
+	/* We don't use vmf->pgoff since that has the fake offset: */
+	pgoff = ((unsigned long)vmf->virtual_address -
+			vma->vm_start) >> PAGE_SHIFT;
+
+	pfn = page_to_pfn(msm_obj->pages[pgoff]);
+
+	VERB("Inserting %p pfn %lx, pa %lx", vmf->virtual_address,
+			pfn, pfn << PAGE_SHIFT);
+
+	ret = vm_insert_mixed(vma, (unsigned long)vmf->virtual_address, pfn);
+
+out_unlock:
+	mutex_unlock(&dev->struct_mutex);
+out:
+	switch (ret) {
+	case -EAGAIN:
+	case 0:
+	case -ERESTARTSYS:
+	case -EINTR:
+		return VM_FAULT_NOPAGE;
+	case -ENOMEM:
+		return VM_FAULT_OOM;
+	default:
+		return VM_FAULT_SIGBUS;
+	}
+}
+
+/** get mmap offset */
+static uint64_t mmap_offset(struct drm_gem_object *obj)
+{
+	struct drm_device *dev = obj->dev;
+	int ret;
+
+	WARN_ON(!mutex_is_locked(&dev->struct_mutex));
+
+	/* Make it mmapable */
+	ret = drm_gem_create_mmap_offset(obj);
+
+	if (ret) {
+		dev_err(dev->dev, "could not allocate mmap offset\n");
+		return 0;
+	}
+
+	return drm_vma_node_offset_addr(&obj->vma_node);
+}
+
+uint64_t msm_gem_mmap_offset(struct drm_gem_object *obj)
+{
+	uint64_t offset;
+	mutex_lock(&obj->dev->struct_mutex);
+	offset = mmap_offset(obj);
+	mutex_unlock(&obj->dev->struct_mutex);
+	return offset;
+}
+
+/* helpers for dealing w/ iommu: */
+static int map_range(struct iommu_domain *domain, unsigned int iova,
+		struct sg_table *sgt, unsigned int len, int prot)
+{
+	struct scatterlist *sg;
+	unsigned int da = iova;
+	unsigned int i, j;
+	int ret;
+
+	if (!domain || !sgt)
+		return -EINVAL;
+
+	for_each_sg(sgt->sgl, sg, sgt->nents, i) {
+		u32 pa = sg_phys(sg) - sg->offset;
+		size_t bytes = sg->length + sg->offset;
+
+		VERB("map[%d]: %08x %08x(%x)", i, iova, pa, bytes);
+
+		ret = iommu_map(domain, da, pa, bytes, prot);
+		if (ret)
+			goto fail;
+
+		da += bytes;
+	}
+
+	return 0;
+
+fail:
+	da = iova;
+
+	for_each_sg(sgt->sgl, sg, i, j) {
+		size_t bytes = sg->length + sg->offset;
+		iommu_unmap(domain, da, bytes);
+		da += bytes;
+	}
+	return ret;
+}
+
+static void unmap_range(struct iommu_domain *domain, unsigned int iova,
+		struct sg_table *sgt, unsigned int len)
+{
+	struct scatterlist *sg;
+	unsigned int da = iova;
+	int i;
+
+	for_each_sg(sgt->sgl, sg, sgt->nents, i) {
+		size_t bytes = sg->length + sg->offset;
+		size_t unmapped;
+
+		unmapped = iommu_unmap(domain, da, bytes);
+		if (unmapped < bytes)
+			break;
+
+		VERB("unmap[%d]: %08x(%x)", i, iova, bytes);
+
+		BUG_ON(!IS_ALIGNED(bytes, PAGE_SIZE));
+
+		da += bytes;
+	}
+}
+
+/* should be called under struct_mutex.. although it can be called
+ * from atomic context without struct_mutex to acquire an extra
+ * iova ref if you know one is already held.
+ *
+ * That means when I do eventually need to add support for unpinning
+ * the refcnt counter needs to be atomic_t.
+ */
+int msm_gem_get_iova_locked(struct drm_gem_object *obj, int id,
+		uint32_t *iova)
+{
+	struct msm_gem_object *msm_obj = to_msm_bo(obj);
+	int ret = 0;
+
+	if (!msm_obj->domain[id].iova) {
+		struct msm_drm_private *priv = obj->dev->dev_private;
+		uint32_t offset = (uint32_t)mmap_offset(obj);
+		struct page **pages;
+		pages = get_pages(obj);
+		if (IS_ERR(pages))
+			return PTR_ERR(pages);
+		// XXX ideally we would not map buffers writable when not needed...
+		ret = map_range(priv->iommus[id], offset, msm_obj->sgt,
+				obj->size, IOMMU_READ | IOMMU_WRITE);
+		msm_obj->domain[id].iova = offset;
+	}
+
+	if (!ret)
+		*iova = msm_obj->domain[id].iova;
+
+	return ret;
+}
+
+int msm_gem_get_iova(struct drm_gem_object *obj, int id, uint32_t *iova)
+{
+	int ret;
+	mutex_lock(&obj->dev->struct_mutex);
+	ret = msm_gem_get_iova_locked(obj, id, iova);
+	mutex_unlock(&obj->dev->struct_mutex);
+	return ret;
+}
+
+void msm_gem_put_iova(struct drm_gem_object *obj, int id)
+{
+	// XXX TODO ..
+	// NOTE: probably don't need a _locked() version.. we wouldn't
+	// normally unmap here, but instead just mark that it could be
+	// unmapped (if the iova refcnt drops to zero), but then later
+	// if another _get_iova_locked() fails we can start unmapping
+	// things that are no longer needed..
+}
+
+int msm_gem_dumb_create(struct drm_file *file, struct drm_device *dev,
+		struct drm_mode_create_dumb *args)
+{
+	args->pitch = align_pitch(args->width, args->bpp);
+	args->size  = PAGE_ALIGN(args->pitch * args->height);
+	return msm_gem_new_handle(dev, file, args->size,
+			MSM_BO_SCANOUT | MSM_BO_WC, &args->handle);
+}
+
+int msm_gem_dumb_map_offset(struct drm_file *file, struct drm_device *dev,
+		uint32_t handle, uint64_t *offset)
+{
+	struct drm_gem_object *obj;
+	int ret = 0;
+
+	/* GEM does all our handle to object mapping */
+	obj = drm_gem_object_lookup(dev, file, handle);
+	if (obj == NULL) {
+		ret = -ENOENT;
+		goto fail;
+	}
+
+	*offset = msm_gem_mmap_offset(obj);
+
+	drm_gem_object_unreference_unlocked(obj);
+
+fail:
+	return ret;
+}
+
+void *msm_gem_vaddr_locked(struct drm_gem_object *obj)
+{
+	struct msm_gem_object *msm_obj = to_msm_bo(obj);
+	WARN_ON(!mutex_is_locked(&obj->dev->struct_mutex));
+	if (!msm_obj->vaddr) {
+		struct page **pages = get_pages(obj);
+		if (IS_ERR(pages))
+			return ERR_CAST(pages);
+		msm_obj->vaddr = vmap(pages, obj->size >> PAGE_SHIFT,
+				VM_MAP, pgprot_writecombine(PAGE_KERNEL));
+	}
+	return msm_obj->vaddr;
+}
+
+void *msm_gem_vaddr(struct drm_gem_object *obj)
+{
+	void *ret;
+	mutex_lock(&obj->dev->struct_mutex);
+	ret = msm_gem_vaddr_locked(obj);
+	mutex_unlock(&obj->dev->struct_mutex);
+	return ret;
+}
+
+int msm_gem_queue_inactive_work(struct drm_gem_object *obj,
+		struct work_struct *work)
+{
+	struct drm_device *dev = obj->dev;
+	struct msm_drm_private *priv = dev->dev_private;
+	struct msm_gem_object *msm_obj = to_msm_bo(obj);
+	int ret = 0;
+
+	mutex_lock(&dev->struct_mutex);
+	if (!list_empty(&work->entry)) {
+		ret = -EINVAL;
+	} else if (is_active(msm_obj)) {
+		list_add_tail(&work->entry, &msm_obj->inactive_work);
+	} else {
+		queue_work(priv->wq, work);
+	}
+	mutex_unlock(&dev->struct_mutex);
+
+	return ret;
+}
+
+void msm_gem_move_to_active(struct drm_gem_object *obj,
+		struct msm_gpu *gpu, bool write, uint32_t fence)
+{
+	struct msm_gem_object *msm_obj = to_msm_bo(obj);
+	msm_obj->gpu = gpu;
+	if (write)
+		msm_obj->write_fence = fence;
+	else
+		msm_obj->read_fence = fence;
+	list_del_init(&msm_obj->mm_list);
+	list_add_tail(&msm_obj->mm_list, &gpu->active_list);
+}
+
+void msm_gem_move_to_inactive(struct drm_gem_object *obj)
+{
+	struct drm_device *dev = obj->dev;
+	struct msm_drm_private *priv = dev->dev_private;
+	struct msm_gem_object *msm_obj = to_msm_bo(obj);
+
+	WARN_ON(!mutex_is_locked(&dev->struct_mutex));
+
+	msm_obj->gpu = NULL;
+	msm_obj->read_fence = 0;
+	msm_obj->write_fence = 0;
+	list_del_init(&msm_obj->mm_list);
+	list_add_tail(&msm_obj->mm_list, &priv->inactive_list);
+
+	while (!list_empty(&msm_obj->inactive_work)) {
+		struct work_struct *work;
+
+		work = list_first_entry(&msm_obj->inactive_work,
+				struct work_struct, entry);
+
+		list_del_init(&work->entry);
+		queue_work(priv->wq, work);
+	}
+}
+
+int msm_gem_cpu_prep(struct drm_gem_object *obj, uint32_t op,
+		struct timespec *timeout)
+{
+	struct drm_device *dev = obj->dev;
+	struct msm_gem_object *msm_obj = to_msm_bo(obj);
+	int ret = 0;
+
+	if (is_active(msm_obj)) {
+		uint32_t fence = 0;
+
+		if (op & MSM_PREP_READ)
+			fence = msm_obj->write_fence;
+		if (op & MSM_PREP_WRITE)
+			fence = max(fence, msm_obj->read_fence);
+		if (op & MSM_PREP_NOSYNC)
+			timeout = NULL;
+
+		ret = msm_wait_fence_interruptable(dev, fence, timeout);
+	}
+
+	/* TODO cache maintenance */
+
+	return ret;
+}
+
+int msm_gem_cpu_fini(struct drm_gem_object *obj)
+{
+	/* TODO cache maintenance */
+	return 0;
+}
+
+#ifdef CONFIG_DEBUG_FS
+void msm_gem_describe(struct drm_gem_object *obj, struct seq_file *m)
+{
+	struct drm_device *dev = obj->dev;
+	struct msm_gem_object *msm_obj = to_msm_bo(obj);
+	uint64_t off = drm_vma_node_start(&obj->vma_node);
+
+	WARN_ON(!mutex_is_locked(&dev->struct_mutex));
+	seq_printf(m, "%08x: %c(r=%u,w=%u) %2d (%2d) %08llx %p %d\n",
+			msm_obj->flags, is_active(msm_obj) ? 'A' : 'I',
+			msm_obj->read_fence, msm_obj->write_fence,
+			obj->name, obj->refcount.refcount.counter,
+			off, msm_obj->vaddr, obj->size);
+}
+
+void msm_gem_describe_objects(struct list_head *list, struct seq_file *m)
+{
+	struct msm_gem_object *msm_obj;
+	int count = 0;
+	size_t size = 0;
+
+	list_for_each_entry(msm_obj, list, mm_list) {
+		struct drm_gem_object *obj = &msm_obj->base;
+		seq_printf(m, "   ");
+		msm_gem_describe(obj, m);
+		count++;
+		size += obj->size;
+	}
+
+	seq_printf(m, "Total %d objects, %zu bytes\n", count, size);
+}
+#endif
+
+void msm_gem_free_object(struct drm_gem_object *obj)
+{
+	struct drm_device *dev = obj->dev;
+	struct msm_gem_object *msm_obj = to_msm_bo(obj);
+	int id;
+
+	WARN_ON(!mutex_is_locked(&dev->struct_mutex));
+
+	/* object should not be on active list: */
+	WARN_ON(is_active(msm_obj));
+
+	list_del(&msm_obj->mm_list);
+
+	for (id = 0; id < ARRAY_SIZE(msm_obj->domain); id++) {
+		if (msm_obj->domain[id].iova) {
+			struct msm_drm_private *priv = obj->dev->dev_private;
+			uint32_t offset = (uint32_t)mmap_offset(obj);
+			unmap_range(priv->iommus[id], offset,
+					msm_obj->sgt, obj->size);
+		}
+	}
+
+	drm_gem_free_mmap_offset(obj);
+
+	if (msm_obj->vaddr)
+		vunmap(msm_obj->vaddr);
+
+	put_pages(obj);
+
+	if (msm_obj->resv == &msm_obj->_resv)
+		reservation_object_fini(msm_obj->resv);
+
+	drm_gem_object_release(obj);
+
+	kfree(msm_obj);
+}
+
+/* convenience method to construct a GEM buffer object, and userspace handle */
+int msm_gem_new_handle(struct drm_device *dev, struct drm_file *file,
+		uint32_t size, uint32_t flags, uint32_t *handle)
+{
+	struct drm_gem_object *obj;
+	int ret;
+
+	ret = mutex_lock_interruptible(&dev->struct_mutex);
+	if (ret)
+		return ret;
+
+	obj = msm_gem_new(dev, size, flags);
+
+	mutex_unlock(&dev->struct_mutex);
+
+	if (IS_ERR(obj))
+		return PTR_ERR(obj);
+
+	ret = drm_gem_handle_create(file, obj, handle);
+
+	/* drop reference from allocate - handle holds it now */
+	drm_gem_object_unreference_unlocked(obj);
+
+	return ret;
+}
+
+struct drm_gem_object *msm_gem_new(struct drm_device *dev,
+		uint32_t size, uint32_t flags)
+{
+	struct msm_drm_private *priv = dev->dev_private;
+	struct msm_gem_object *msm_obj;
+	struct drm_gem_object *obj = NULL;
+	int ret;
+
+	WARN_ON(!mutex_is_locked(&dev->struct_mutex));
+
+	size = PAGE_ALIGN(size);
+
+	switch (flags & MSM_BO_CACHE_MASK) {
+	case MSM_BO_UNCACHED:
+	case MSM_BO_CACHED:
+	case MSM_BO_WC:
+		break;
+	default:
+		dev_err(dev->dev, "invalid cache flag: %x\n",
+				(flags & MSM_BO_CACHE_MASK));
+		ret = -EINVAL;
+		goto fail;
+	}
+
+	msm_obj = kzalloc(sizeof(*msm_obj), GFP_KERNEL);
+	if (!msm_obj) {
+		ret = -ENOMEM;
+		goto fail;
+	}
+
+	obj = &msm_obj->base;
+
+	ret = drm_gem_object_init(dev, obj, size);
+	if (ret)
+		goto fail;
+
+	msm_obj->flags = flags;
+
+	msm_obj->resv = &msm_obj->_resv;
+	reservation_object_init(msm_obj->resv);
+
+	INIT_LIST_HEAD(&msm_obj->submit_entry);
+	INIT_LIST_HEAD(&msm_obj->inactive_work);
+	list_add_tail(&msm_obj->mm_list, &priv->inactive_list);
+
+	return obj;
+
+fail:
+	if (obj)
+		drm_gem_object_unreference_unlocked(obj);
+
+	return ERR_PTR(ret);
+}
diff --git a/drivers/gpu/drm/msm/msm_gem.h b/drivers/gpu/drm/msm/msm_gem.h
new file mode 100644
index 000000000000..0676f32e2c6a
--- /dev/null
+++ b/drivers/gpu/drm/msm/msm_gem.h
@@ -0,0 +1,99 @@
+/*
+ * Copyright (C) 2013 Red Hat
+ * Author: Rob Clark <robdclark@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __MSM_GEM_H__
+#define __MSM_GEM_H__
+
+#include <linux/reservation.h>
+#include "msm_drv.h"
+
+struct msm_gem_object {
+	struct drm_gem_object base;
+
+	uint32_t flags;
+
+	/* And object is either:
+	 *  inactive - on priv->inactive_list
+	 *  active   - on one one of the gpu's active_list..  well, at
+	 *     least for now we don't have (I don't think) hw sync between
+	 *     2d and 3d one devices which have both, meaning we need to
+	 *     block on submit if a bo is already on other ring
+	 *
+	 */
+	struct list_head mm_list;
+	struct msm_gpu *gpu;     /* non-null if active */
+	uint32_t read_fence, write_fence;
+
+	/* Transiently in the process of submit ioctl, objects associated
+	 * with the submit are on submit->bo_list.. this only lasts for
+	 * the duration of the ioctl, so one bo can never be on multiple
+	 * submit lists.
+	 */
+	struct list_head submit_entry;
+
+	/* work defered until bo is inactive: */
+	struct list_head inactive_work;
+
+	struct page **pages;
+	struct sg_table *sgt;
+	void *vaddr;
+
+	struct {
+		// XXX
+		uint32_t iova;
+	} domain[NUM_DOMAINS];
+
+	/* normally (resv == &_resv) except for imported bo's */
+	struct reservation_object *resv;
+	struct reservation_object _resv;
+};
+#define to_msm_bo(x) container_of(x, struct msm_gem_object, base)
+
+static inline bool is_active(struct msm_gem_object *msm_obj)
+{
+	return msm_obj->gpu != NULL;
+}
+
+#define MAX_CMDS 4
+
+/* Created per submit-ioctl, to track bo's and cmdstream bufs, etc,
+ * associated with the cmdstream submission for synchronization (and
+ * make it easier to unwind when things go wrong, etc).  This only
+ * lasts for the duration of the submit-ioctl.
+ */
+struct msm_gem_submit {
+	struct drm_device *dev;
+	struct msm_gpu *gpu;
+	struct list_head bo_list;
+	struct ww_acquire_ctx ticket;
+	uint32_t fence;
+	bool valid;
+	unsigned int nr_cmds;
+	unsigned int nr_bos;
+	struct {
+		uint32_t type;
+		uint32_t size;  /* in dwords */
+		uint32_t iova;
+	} cmd[MAX_CMDS];
+	struct {
+		uint32_t flags;
+		struct msm_gem_object *obj;
+		uint32_t iova;
+	} bos[0];
+};
+
+#endif /* __MSM_GEM_H__ */
diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c
new file mode 100644
index 000000000000..5281d4bc37f7
--- /dev/null
+++ b/drivers/gpu/drm/msm/msm_gem_submit.c
@@ -0,0 +1,414 @@
+/*
+ * Copyright (C) 2013 Red Hat
+ * Author: Rob Clark <robdclark@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include "msm_drv.h"
+#include "msm_gpu.h"
+#include "msm_gem.h"
+
+/*
+ * Cmdstream submission:
+ */
+
+#define BO_INVALID_FLAGS ~(MSM_SUBMIT_BO_READ | MSM_SUBMIT_BO_WRITE)
+/* make sure these don't conflict w/ MSM_SUBMIT_BO_x */
+#define BO_VALID    0x8000
+#define BO_LOCKED   0x4000
+#define BO_PINNED   0x2000
+
+static inline void __user *to_user_ptr(u64 address)
+{
+	return (void __user *)(uintptr_t)address;
+}
+
+static struct msm_gem_submit *submit_create(struct drm_device *dev,
+		struct msm_gpu *gpu, int nr)
+{
+	struct msm_gem_submit *submit;
+	int sz = sizeof(*submit) + (nr * sizeof(submit->bos[0]));
+
+	submit = kmalloc(sz, GFP_TEMPORARY | __GFP_NOWARN | __GFP_NORETRY);
+	if (submit) {
+		submit->dev = dev;
+		submit->gpu = gpu;
+
+		/* initially, until copy_from_user() and bo lookup succeeds: */
+		submit->nr_bos = 0;
+		submit->nr_cmds = 0;
+
+		INIT_LIST_HEAD(&submit->bo_list);
+		ww_acquire_init(&submit->ticket, &reservation_ww_class);
+	}
+
+	return submit;
+}
+
+static int submit_lookup_objects(struct msm_gem_submit *submit,
+		struct drm_msm_gem_submit *args, struct drm_file *file)
+{
+	unsigned i;
+	int ret = 0;
+
+	spin_lock(&file->table_lock);
+
+	for (i = 0; i < args->nr_bos; i++) {
+		struct drm_msm_gem_submit_bo submit_bo;
+		struct drm_gem_object *obj;
+		struct msm_gem_object *msm_obj;
+		void __user *userptr =
+			to_user_ptr(args->bos + (i * sizeof(submit_bo)));
+
+		ret = copy_from_user(&submit_bo, userptr, sizeof(submit_bo));
+		if (ret) {
+			ret = -EFAULT;
+			goto out_unlock;
+		}
+
+		if (submit_bo.flags & BO_INVALID_FLAGS) {
+			DRM_ERROR("invalid flags: %x\n", submit_bo.flags);
+			ret = -EINVAL;
+			goto out_unlock;
+		}
+
+		submit->bos[i].flags = submit_bo.flags;
+		/* in validate_objects() we figure out if this is true: */
+		submit->bos[i].iova  = submit_bo.presumed;
+
+		/* normally use drm_gem_object_lookup(), but for bulk lookup
+		 * all under single table_lock just hit object_idr directly:
+		 */
+		obj = idr_find(&file->object_idr, submit_bo.handle);
+		if (!obj) {
+			DRM_ERROR("invalid handle %u at index %u\n", submit_bo.handle, i);
+			ret = -EINVAL;
+			goto out_unlock;
+		}
+
+		msm_obj = to_msm_bo(obj);
+
+		if (!list_empty(&msm_obj->submit_entry)) {
+			DRM_ERROR("handle %u at index %u already on submit list\n",
+					submit_bo.handle, i);
+			ret = -EINVAL;
+			goto out_unlock;
+		}
+
+		drm_gem_object_reference(obj);
+
+		submit->bos[i].obj = msm_obj;
+
+		list_add_tail(&msm_obj->submit_entry, &submit->bo_list);
+	}
+
+out_unlock:
+	submit->nr_bos = i;
+	spin_unlock(&file->table_lock);
+
+	return ret;
+}
+
+static void submit_unlock_unpin_bo(struct msm_gem_submit *submit, int i)
+{
+	struct msm_gem_object *msm_obj = submit->bos[i].obj;
+
+	if (submit->bos[i].flags & BO_PINNED)
+		msm_gem_put_iova(&msm_obj->base, submit->gpu->id);
+
+	if (submit->bos[i].flags & BO_LOCKED)
+		ww_mutex_unlock(&msm_obj->resv->lock);
+
+	if (!(submit->bos[i].flags & BO_VALID))
+		submit->bos[i].iova = 0;
+
+	submit->bos[i].flags &= ~(BO_LOCKED | BO_PINNED);
+}
+
+/* This is where we make sure all the bo's are reserved and pin'd: */
+static int submit_validate_objects(struct msm_gem_submit *submit)
+{
+	int contended, slow_locked = -1, i, ret = 0;
+
+retry:
+	submit->valid = true;
+
+	for (i = 0; i < submit->nr_bos; i++) {
+		struct msm_gem_object *msm_obj = submit->bos[i].obj;
+		uint32_t iova;
+
+		if (slow_locked == i)
+			slow_locked = -1;
+
+		contended = i;
+
+		if (!(submit->bos[i].flags & BO_LOCKED)) {
+			ret = ww_mutex_lock_interruptible(&msm_obj->resv->lock,
+					&submit->ticket);
+			if (ret)
+				goto fail;
+			submit->bos[i].flags |= BO_LOCKED;
+		}
+
+
+		/* if locking succeeded, pin bo: */
+		ret = msm_gem_get_iova(&msm_obj->base,
+				submit->gpu->id, &iova);
+
+		/* this would break the logic in the fail path.. there is no
+		 * reason for this to happen, but just to be on the safe side
+		 * let's notice if this starts happening in the future:
+		 */
+		WARN_ON(ret == -EDEADLK);
+
+		if (ret)
+			goto fail;
+
+		submit->bos[i].flags |= BO_PINNED;
+
+		if (iova == submit->bos[i].iova) {
+			submit->bos[i].flags |= BO_VALID;
+		} else {
+			submit->bos[i].iova = iova;
+			submit->bos[i].flags &= ~BO_VALID;
+			submit->valid = false;
+		}
+	}
+
+	ww_acquire_done(&submit->ticket);
+
+	return 0;
+
+fail:
+	for (; i >= 0; i--)
+		submit_unlock_unpin_bo(submit, i);
+
+	if (slow_locked > 0)
+		submit_unlock_unpin_bo(submit, slow_locked);
+
+	if (ret == -EDEADLK) {
+		struct msm_gem_object *msm_obj = submit->bos[contended].obj;
+		/* we lost out in a seqno race, lock and retry.. */
+		ret = ww_mutex_lock_slow_interruptible(&msm_obj->resv->lock,
+				&submit->ticket);
+		if (!ret) {
+			submit->bos[contended].flags |= BO_LOCKED;
+			slow_locked = contended;
+			goto retry;
+		}
+	}
+
+	return ret;
+}
+
+static int submit_bo(struct msm_gem_submit *submit, uint32_t idx,
+		struct msm_gem_object **obj, uint32_t *iova, bool *valid)
+{
+	if (idx >= submit->nr_bos) {
+		DRM_ERROR("invalid buffer index: %u (out of %u)\n",
+				idx, submit->nr_bos);
+		return -EINVAL;
+	}
+
+	if (obj)
+		*obj = submit->bos[idx].obj;
+	if (iova)
+		*iova = submit->bos[idx].iova;
+	if (valid)
+		*valid = !!(submit->bos[idx].flags & BO_VALID);
+
+	return 0;
+}
+
+/* process the reloc's and patch up the cmdstream as needed: */
+static int submit_reloc(struct msm_gem_submit *submit, struct msm_gem_object *obj,
+		uint32_t offset, uint32_t nr_relocs, uint64_t relocs)
+{
+	uint32_t i, last_offset = 0;
+	uint32_t *ptr;
+	int ret;
+
+	if (offset % 4) {
+		DRM_ERROR("non-aligned cmdstream buffer: %u\n", offset);
+		return -EINVAL;
+	}
+
+	/* For now, just map the entire thing.  Eventually we probably
+	 * to do it page-by-page, w/ kmap() if not vmap()d..
+	 */
+	ptr = msm_gem_vaddr(&obj->base);
+
+	if (IS_ERR(ptr)) {
+		ret = PTR_ERR(ptr);
+		DBG("failed to map: %d", ret);
+		return ret;
+	}
+
+	for (i = 0; i < nr_relocs; i++) {
+		struct drm_msm_gem_submit_reloc submit_reloc;
+		void __user *userptr =
+			to_user_ptr(relocs + (i * sizeof(submit_reloc)));
+		uint32_t iova, off;
+		bool valid;
+
+		ret = copy_from_user(&submit_reloc, userptr, sizeof(submit_reloc));
+		if (ret)
+			return -EFAULT;
+
+		if (submit_reloc.submit_offset % 4) {
+			DRM_ERROR("non-aligned reloc offset: %u\n",
+					submit_reloc.submit_offset);
+			return -EINVAL;
+		}
+
+		/* offset in dwords: */
+		off = submit_reloc.submit_offset / 4;
+
+		if ((off >= (obj->base.size / 4)) ||
+				(off < last_offset)) {
+			DRM_ERROR("invalid offset %u at reloc %u\n", off, i);
+			return -EINVAL;
+		}
+
+		ret = submit_bo(submit, submit_reloc.reloc_idx, NULL, &iova, &valid);
+		if (ret)
+			return ret;
+
+		if (valid)
+			continue;
+
+		iova += submit_reloc.reloc_offset;
+
+		if (submit_reloc.shift < 0)
+			iova >>= -submit_reloc.shift;
+		else
+			iova <<= submit_reloc.shift;
+
+		ptr[off] = iova | submit_reloc.or;
+
+		last_offset = off;
+	}
+
+	return 0;
+}
+
+static void submit_cleanup(struct msm_gem_submit *submit, bool fail)
+{
+	unsigned i;
+
+	mutex_lock(&submit->dev->struct_mutex);
+	for (i = 0; i < submit->nr_bos; i++) {
+		struct msm_gem_object *msm_obj = submit->bos[i].obj;
+		submit_unlock_unpin_bo(submit, i);
+		list_del_init(&msm_obj->submit_entry);
+		drm_gem_object_unreference(&msm_obj->base);
+	}
+	mutex_unlock(&submit->dev->struct_mutex);
+
+	ww_acquire_fini(&submit->ticket);
+	kfree(submit);
+}
+
+int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
+		struct drm_file *file)
+{
+	struct msm_drm_private *priv = dev->dev_private;
+	struct drm_msm_gem_submit *args = data;
+	struct msm_file_private *ctx = file->driver_priv;
+	struct msm_gem_submit *submit;
+	struct msm_gpu *gpu;
+	unsigned i;
+	int ret;
+
+	/* for now, we just have 3d pipe.. eventually this would need to
+	 * be more clever to dispatch to appropriate gpu module:
+	 */
+	if (args->pipe != MSM_PIPE_3D0)
+		return -EINVAL;
+
+	gpu = priv->gpu;
+
+	if (args->nr_cmds > MAX_CMDS)
+		return -EINVAL;
+
+	submit = submit_create(dev, gpu, args->nr_bos);
+	if (!submit) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	ret = submit_lookup_objects(submit, args, file);
+	if (ret)
+		goto out;
+
+	ret = submit_validate_objects(submit);
+	if (ret)
+		goto out;
+
+	for (i = 0; i < args->nr_cmds; i++) {
+		struct drm_msm_gem_submit_cmd submit_cmd;
+		void __user *userptr =
+			to_user_ptr(args->cmds + (i * sizeof(submit_cmd)));
+		struct msm_gem_object *msm_obj;
+		uint32_t iova;
+
+		ret = copy_from_user(&submit_cmd, userptr, sizeof(submit_cmd));
+		if (ret) {
+			ret = -EFAULT;
+			goto out;
+		}
+
+		ret = submit_bo(submit, submit_cmd.submit_idx,
+				&msm_obj, &iova, NULL);
+		if (ret)
+			goto out;
+
+		if (submit_cmd.size % 4) {
+			DRM_ERROR("non-aligned cmdstream buffer size: %u\n",
+					submit_cmd.size);
+			ret = -EINVAL;
+			goto out;
+		}
+
+		if ((submit_cmd.size + submit_cmd.submit_offset) >=
+				msm_obj->base.size) {
+			DRM_ERROR("invalid cmdstream size: %u\n", submit_cmd.size);
+			ret = -EINVAL;
+			goto out;
+		}
+
+		submit->cmd[i].type = submit_cmd.type;
+		submit->cmd[i].size = submit_cmd.size / 4;
+		submit->cmd[i].iova = iova + submit_cmd.submit_offset;
+
+		if (submit->valid)
+			continue;
+
+		ret = submit_reloc(submit, msm_obj, submit_cmd.submit_offset,
+				submit_cmd.nr_relocs, submit_cmd.relocs);
+		if (ret)
+			goto out;
+	}
+
+	submit->nr_cmds = i;
+
+	ret = msm_gpu_submit(gpu, submit, ctx);
+
+	args->fence = submit->fence;
+
+out:
+	if (submit)
+		submit_cleanup(submit, !!ret);
+	return ret;
+}
diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c
new file mode 100644
index 000000000000..3bab937965d1
--- /dev/null
+++ b/drivers/gpu/drm/msm/msm_gpu.c
@@ -0,0 +1,479 @@
+/*
+ * Copyright (C) 2013 Red Hat
+ * Author: Rob Clark <robdclark@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include "msm_gpu.h"
+#include "msm_gem.h"
+
+
+/*
+ * Power Management:
+ */
+
+#ifdef CONFIG_MSM_BUS_SCALING
+#include <mach/board.h>
+#include <mach/kgsl.h>
+static void bs_init(struct msm_gpu *gpu, struct platform_device *pdev)
+{
+	struct drm_device *dev = gpu->dev;
+	struct kgsl_device_platform_data *pdata;
+
+	if (!pdev) {
+		dev_err(dev->dev, "could not find dtv pdata\n");
+		return;
+	}
+
+	pdata = pdev->dev.platform_data;
+	if (pdata->bus_scale_table) {
+		gpu->bsc = msm_bus_scale_register_client(pdata->bus_scale_table);
+		DBG("bus scale client: %08x", gpu->bsc);
+	}
+}
+
+static void bs_fini(struct msm_gpu *gpu)
+{
+	if (gpu->bsc) {
+		msm_bus_scale_unregister_client(gpu->bsc);
+		gpu->bsc = 0;
+	}
+}
+
+static void bs_set(struct msm_gpu *gpu, int idx)
+{
+	if (gpu->bsc) {
+		DBG("set bus scaling: %d", idx);
+		msm_bus_scale_client_update_request(gpu->bsc, idx);
+	}
+}
+#else
+static void bs_init(struct msm_gpu *gpu, struct platform_device *pdev) {}
+static void bs_fini(struct msm_gpu *gpu) {}
+static void bs_set(struct msm_gpu *gpu, int idx) {}
+#endif
+
+static int enable_pwrrail(struct msm_gpu *gpu)
+{
+	struct drm_device *dev = gpu->dev;
+	int ret = 0;
+
+	if (gpu->gpu_reg) {
+		ret = regulator_enable(gpu->gpu_reg);
+		if (ret) {
+			dev_err(dev->dev, "failed to enable 'gpu_reg': %d\n", ret);
+			return ret;
+		}
+	}
+
+	if (gpu->gpu_cx) {
+		ret = regulator_enable(gpu->gpu_cx);
+		if (ret) {
+			dev_err(dev->dev, "failed to enable 'gpu_cx': %d\n", ret);
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
+static int disable_pwrrail(struct msm_gpu *gpu)
+{
+	if (gpu->gpu_cx)
+		regulator_disable(gpu->gpu_cx);
+	if (gpu->gpu_reg)
+		regulator_disable(gpu->gpu_reg);
+	return 0;
+}
+
+static int enable_clk(struct msm_gpu *gpu)
+{
+	struct clk *rate_clk = NULL;
+	int i;
+
+	/* NOTE: kgsl_pwrctrl_clk() ignores grp_clks[0].. */
+	for (i = ARRAY_SIZE(gpu->grp_clks) - 1; i > 0; i--) {
+		if (gpu->grp_clks[i]) {
+			clk_prepare(gpu->grp_clks[i]);
+			rate_clk = gpu->grp_clks[i];
+		}
+	}
+
+	if (rate_clk && gpu->fast_rate)
+		clk_set_rate(rate_clk, gpu->fast_rate);
+
+	for (i = ARRAY_SIZE(gpu->grp_clks) - 1; i > 0; i--)
+		if (gpu->grp_clks[i])
+			clk_enable(gpu->grp_clks[i]);
+
+	return 0;
+}
+
+static int disable_clk(struct msm_gpu *gpu)
+{
+	struct clk *rate_clk = NULL;
+	int i;
+
+	/* NOTE: kgsl_pwrctrl_clk() ignores grp_clks[0].. */
+	for (i = ARRAY_SIZE(gpu->grp_clks) - 1; i > 0; i--) {
+		if (gpu->grp_clks[i]) {
+			clk_disable(gpu->grp_clks[i]);
+			rate_clk = gpu->grp_clks[i];
+		}
+	}
+
+	if (rate_clk && gpu->slow_rate)
+		clk_set_rate(rate_clk, gpu->slow_rate);
+
+	for (i = ARRAY_SIZE(gpu->grp_clks) - 1; i > 0; i--)
+		if (gpu->grp_clks[i])
+			clk_unprepare(gpu->grp_clks[i]);
+
+	return 0;
+}
+
+static int enable_axi(struct msm_gpu *gpu)
+{
+	if (gpu->ebi1_clk)
+		clk_prepare_enable(gpu->ebi1_clk);
+	if (gpu->bus_freq)
+		bs_set(gpu, gpu->bus_freq);
+	return 0;
+}
+
+static int disable_axi(struct msm_gpu *gpu)
+{
+	if (gpu->ebi1_clk)
+		clk_disable_unprepare(gpu->ebi1_clk);
+	if (gpu->bus_freq)
+		bs_set(gpu, 0);
+	return 0;
+}
+
+int msm_gpu_pm_resume(struct msm_gpu *gpu)
+{
+	int ret;
+
+	DBG("%s", gpu->name);
+
+	ret = enable_pwrrail(gpu);
+	if (ret)
+		return ret;
+
+	ret = enable_clk(gpu);
+	if (ret)
+		return ret;
+
+	ret = enable_axi(gpu);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+int msm_gpu_pm_suspend(struct msm_gpu *gpu)
+{
+	int ret;
+
+	DBG("%s", gpu->name);
+
+	ret = disable_axi(gpu);
+	if (ret)
+		return ret;
+
+	ret = disable_clk(gpu);
+	if (ret)
+		return ret;
+
+	ret = disable_pwrrail(gpu);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+/*
+ * Hangcheck detection for locked gpu:
+ */
+
+static void recover_worker(struct work_struct *work)
+{
+	struct msm_gpu *gpu = container_of(work, struct msm_gpu, recover_work);
+	struct drm_device *dev = gpu->dev;
+
+	dev_err(dev->dev, "%s: hangcheck recover!\n", gpu->name);
+
+	mutex_lock(&dev->struct_mutex);
+	gpu->funcs->recover(gpu);
+	mutex_unlock(&dev->struct_mutex);
+
+	msm_gpu_retire(gpu);
+}
+
+static void hangcheck_timer_reset(struct msm_gpu *gpu)
+{
+	DBG("%s", gpu->name);
+	mod_timer(&gpu->hangcheck_timer,
+			round_jiffies_up(jiffies + DRM_MSM_HANGCHECK_JIFFIES));
+}
+
+static void hangcheck_handler(unsigned long data)
+{
+	struct msm_gpu *gpu = (struct msm_gpu *)data;
+	struct drm_device *dev = gpu->dev;
+	struct msm_drm_private *priv = dev->dev_private;
+	uint32_t fence = gpu->funcs->last_fence(gpu);
+
+	if (fence != gpu->hangcheck_fence) {
+		/* some progress has been made.. ya! */
+		gpu->hangcheck_fence = fence;
+	} else if (fence < gpu->submitted_fence) {
+		/* no progress and not done.. hung! */
+		gpu->hangcheck_fence = fence;
+		dev_err(dev->dev, "%s: hangcheck detected gpu lockup!\n",
+				gpu->name);
+		dev_err(dev->dev, "%s:     completed fence: %u\n",
+				gpu->name, fence);
+		dev_err(dev->dev, "%s:     submitted fence: %u\n",
+				gpu->name, gpu->submitted_fence);
+		queue_work(priv->wq, &gpu->recover_work);
+	}
+
+	/* if still more pending work, reset the hangcheck timer: */
+	if (gpu->submitted_fence > gpu->hangcheck_fence)
+		hangcheck_timer_reset(gpu);
+
+	/* workaround for missing irq: */
+	queue_work(priv->wq, &gpu->retire_work);
+}
+
+/*
+ * Cmdstream submission/retirement:
+ */
+
+static void retire_worker(struct work_struct *work)
+{
+	struct msm_gpu *gpu = container_of(work, struct msm_gpu, retire_work);
+	struct drm_device *dev = gpu->dev;
+	uint32_t fence = gpu->funcs->last_fence(gpu);
+
+	mutex_lock(&dev->struct_mutex);
+
+	while (!list_empty(&gpu->active_list)) {
+		struct msm_gem_object *obj;
+
+		obj = list_first_entry(&gpu->active_list,
+				struct msm_gem_object, mm_list);
+
+		if ((obj->read_fence <= fence) &&
+				(obj->write_fence <= fence)) {
+			/* move to inactive: */
+			msm_gem_move_to_inactive(&obj->base);
+			msm_gem_put_iova(&obj->base, gpu->id);
+			drm_gem_object_unreference(&obj->base);
+		} else {
+			break;
+		}
+	}
+
+	msm_update_fence(gpu->dev, fence);
+
+	mutex_unlock(&dev->struct_mutex);
+}
+
+/* call from irq handler to schedule work to retire bo's */
+void msm_gpu_retire(struct msm_gpu *gpu)
+{
+	struct msm_drm_private *priv = gpu->dev->dev_private;
+	queue_work(priv->wq, &gpu->retire_work);
+}
+
+/* add bo's to gpu's ring, and kick gpu: */
+int msm_gpu_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit,
+		struct msm_file_private *ctx)
+{
+	struct drm_device *dev = gpu->dev;
+	struct msm_drm_private *priv = dev->dev_private;
+	int i, ret;
+
+	mutex_lock(&dev->struct_mutex);
+
+	submit->fence = ++priv->next_fence;
+
+	gpu->submitted_fence = submit->fence;
+
+	ret = gpu->funcs->submit(gpu, submit, ctx);
+	priv->lastctx = ctx;
+
+	for (i = 0; i < submit->nr_bos; i++) {
+		struct msm_gem_object *msm_obj = submit->bos[i].obj;
+
+		/* can't happen yet.. but when we add 2d support we'll have
+		 * to deal w/ cross-ring synchronization:
+		 */
+		WARN_ON(is_active(msm_obj) && (msm_obj->gpu != gpu));
+
+		if (!is_active(msm_obj)) {
+			uint32_t iova;
+
+			/* ring takes a reference to the bo and iova: */
+			drm_gem_object_reference(&msm_obj->base);
+			msm_gem_get_iova_locked(&msm_obj->base,
+					submit->gpu->id, &iova);
+		}
+
+		if (submit->bos[i].flags & MSM_SUBMIT_BO_READ)
+			msm_gem_move_to_active(&msm_obj->base, gpu, false, submit->fence);
+
+		if (submit->bos[i].flags & MSM_SUBMIT_BO_WRITE)
+			msm_gem_move_to_active(&msm_obj->base, gpu, true, submit->fence);
+	}
+	hangcheck_timer_reset(gpu);
+	mutex_unlock(&dev->struct_mutex);
+
+	return ret;
+}
+
+/*
+ * Init/Cleanup:
+ */
+
+static irqreturn_t irq_handler(int irq, void *data)
+{
+	struct msm_gpu *gpu = data;
+	return gpu->funcs->irq(gpu);
+}
+
+static const char *clk_names[] = {
+		"src_clk", "core_clk", "iface_clk", "mem_clk", "mem_iface_clk",
+};
+
+int msm_gpu_init(struct drm_device *drm, struct platform_device *pdev,
+		struct msm_gpu *gpu, const struct msm_gpu_funcs *funcs,
+		const char *name, const char *ioname, const char *irqname, int ringsz)
+{
+	int i, ret;
+
+	gpu->dev = drm;
+	gpu->funcs = funcs;
+	gpu->name = name;
+
+	INIT_LIST_HEAD(&gpu->active_list);
+	INIT_WORK(&gpu->retire_work, retire_worker);
+	INIT_WORK(&gpu->recover_work, recover_worker);
+
+	setup_timer(&gpu->hangcheck_timer, hangcheck_handler,
+			(unsigned long)gpu);
+
+	BUG_ON(ARRAY_SIZE(clk_names) != ARRAY_SIZE(gpu->grp_clks));
+
+	/* Map registers: */
+	gpu->mmio = msm_ioremap(pdev, ioname, name);
+	if (IS_ERR(gpu->mmio)) {
+		ret = PTR_ERR(gpu->mmio);
+		goto fail;
+	}
+
+	/* Get Interrupt: */
+	gpu->irq = platform_get_irq_byname(pdev, irqname);
+	if (gpu->irq < 0) {
+		ret = gpu->irq;
+		dev_err(drm->dev, "failed to get irq: %d\n", ret);
+		goto fail;
+	}
+
+	ret = devm_request_irq(&pdev->dev, gpu->irq, irq_handler,
+			IRQF_TRIGGER_HIGH, gpu->name, gpu);
+	if (ret) {
+		dev_err(drm->dev, "failed to request IRQ%u: %d\n", gpu->irq, ret);
+		goto fail;
+	}
+
+	/* Acquire clocks: */
+	for (i = 0; i < ARRAY_SIZE(clk_names); i++) {
+		gpu->grp_clks[i] = devm_clk_get(&pdev->dev, clk_names[i]);
+		DBG("grp_clks[%s]: %p", clk_names[i], gpu->grp_clks[i]);
+		if (IS_ERR(gpu->grp_clks[i]))
+			gpu->grp_clks[i] = NULL;
+	}
+
+	gpu->ebi1_clk = devm_clk_get(&pdev->dev, "bus_clk");
+	DBG("ebi1_clk: %p", gpu->ebi1_clk);
+	if (IS_ERR(gpu->ebi1_clk))
+		gpu->ebi1_clk = NULL;
+
+	/* Acquire regulators: */
+	gpu->gpu_reg = devm_regulator_get(&pdev->dev, "vdd");
+	DBG("gpu_reg: %p", gpu->gpu_reg);
+	if (IS_ERR(gpu->gpu_reg))
+		gpu->gpu_reg = NULL;
+
+	gpu->gpu_cx = devm_regulator_get(&pdev->dev, "vddcx");
+	DBG("gpu_cx: %p", gpu->gpu_cx);
+	if (IS_ERR(gpu->gpu_cx))
+		gpu->gpu_cx = NULL;
+
+	/* Setup IOMMU.. eventually we will (I think) do this once per context
+	 * and have separate page tables per context.  For now, to keep things
+	 * simple and to get something working, just use a single address space:
+	 */
+	gpu->iommu = iommu_domain_alloc(&platform_bus_type);
+	if (!gpu->iommu) {
+		dev_err(drm->dev, "failed to allocate IOMMU\n");
+		ret = -ENOMEM;
+		goto fail;
+	}
+	gpu->id = msm_register_iommu(drm, gpu->iommu);
+
+	/* Create ringbuffer: */
+	gpu->rb = msm_ringbuffer_new(gpu, ringsz);
+	if (IS_ERR(gpu->rb)) {
+		ret = PTR_ERR(gpu->rb);
+		gpu->rb = NULL;
+		dev_err(drm->dev, "could not create ringbuffer: %d\n", ret);
+		goto fail;
+	}
+
+	ret = msm_gem_get_iova_locked(gpu->rb->bo, gpu->id, &gpu->rb_iova);
+	if (ret) {
+		gpu->rb_iova = 0;
+		dev_err(drm->dev, "could not map ringbuffer: %d\n", ret);
+		goto fail;
+	}
+
+	bs_init(gpu, pdev);
+
+	return 0;
+
+fail:
+	return ret;
+}
+
+void msm_gpu_cleanup(struct msm_gpu *gpu)
+{
+	DBG("%s", gpu->name);
+
+	WARN_ON(!list_empty(&gpu->active_list));
+
+	bs_fini(gpu);
+
+	if (gpu->rb) {
+		if (gpu->rb_iova)
+			msm_gem_put_iova(gpu->rb->bo, gpu->id);
+		msm_ringbuffer_destroy(gpu->rb);
+	}
+
+	if (gpu->iommu)
+		iommu_domain_free(gpu->iommu);
+}
diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h
new file mode 100644
index 000000000000..8cd829e520bb
--- /dev/null
+++ b/drivers/gpu/drm/msm/msm_gpu.h
@@ -0,0 +1,124 @@
+/*
+ * Copyright (C) 2013 Red Hat
+ * Author: Rob Clark <robdclark@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __MSM_GPU_H__
+#define __MSM_GPU_H__
+
+#include <linux/clk.h>
+#include <linux/regulator/consumer.h>
+
+#include "msm_drv.h"
+#include "msm_ringbuffer.h"
+
+struct msm_gem_submit;
+
+/* So far, with hardware that I've seen to date, we can have:
+ *  + zero, one, or two z180 2d cores
+ *  + a3xx or a2xx 3d core, which share a common CP (the firmware
+ *    for the CP seems to implement some different PM4 packet types
+ *    but the basics of cmdstream submission are the same)
+ *
+ * Which means that the eventual complete "class" hierarchy, once
+ * support for all past and present hw is in place, becomes:
+ *  + msm_gpu
+ *    + adreno_gpu
+ *      + a3xx_gpu
+ *      + a2xx_gpu
+ *    + z180_gpu
+ */
+struct msm_gpu_funcs {
+	int (*get_param)(struct msm_gpu *gpu, uint32_t param, uint64_t *value);
+	int (*hw_init)(struct msm_gpu *gpu);
+	int (*pm_suspend)(struct msm_gpu *gpu);
+	int (*pm_resume)(struct msm_gpu *gpu);
+	int (*submit)(struct msm_gpu *gpu, struct msm_gem_submit *submit,
+			struct msm_file_private *ctx);
+	void (*flush)(struct msm_gpu *gpu);
+	void (*idle)(struct msm_gpu *gpu);
+	irqreturn_t (*irq)(struct msm_gpu *irq);
+	uint32_t (*last_fence)(struct msm_gpu *gpu);
+	void (*recover)(struct msm_gpu *gpu);
+	void (*destroy)(struct msm_gpu *gpu);
+#ifdef CONFIG_DEBUG_FS
+	/* show GPU status in debugfs: */
+	void (*show)(struct msm_gpu *gpu, struct seq_file *m);
+#endif
+};
+
+struct msm_gpu {
+	const char *name;
+	struct drm_device *dev;
+	const struct msm_gpu_funcs *funcs;
+
+	struct msm_ringbuffer *rb;
+	uint32_t rb_iova;
+
+	/* list of GEM active objects: */
+	struct list_head active_list;
+
+	uint32_t submitted_fence;
+
+	/* worker for handling active-list retiring: */
+	struct work_struct retire_work;
+
+	void __iomem *mmio;
+	int irq;
+
+	struct iommu_domain *iommu;
+	int id;
+
+	/* Power Control: */
+	struct regulator *gpu_reg, *gpu_cx;
+	struct clk *ebi1_clk, *grp_clks[5];
+	uint32_t fast_rate, slow_rate, bus_freq;
+	uint32_t bsc;
+
+	/* Hang Detction: */
+#define DRM_MSM_HANGCHECK_PERIOD 500 /* in ms */
+#define DRM_MSM_HANGCHECK_JIFFIES msecs_to_jiffies(DRM_MSM_HANGCHECK_PERIOD)
+	struct timer_list hangcheck_timer;
+	uint32_t hangcheck_fence;
+	struct work_struct recover_work;
+};
+
+static inline void gpu_write(struct msm_gpu *gpu, u32 reg, u32 data)
+{
+	msm_writel(data, gpu->mmio + (reg << 2));
+}
+
+static inline u32 gpu_read(struct msm_gpu *gpu, u32 reg)
+{
+	return msm_readl(gpu->mmio + (reg << 2));
+}
+
+int msm_gpu_pm_suspend(struct msm_gpu *gpu);
+int msm_gpu_pm_resume(struct msm_gpu *gpu);
+
+void msm_gpu_retire(struct msm_gpu *gpu);
+int msm_gpu_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit,
+		struct msm_file_private *ctx);
+
+int msm_gpu_init(struct drm_device *drm, struct platform_device *pdev,
+		struct msm_gpu *gpu, const struct msm_gpu_funcs *funcs,
+		const char *name, const char *ioname, const char *irqname, int ringsz);
+void msm_gpu_cleanup(struct msm_gpu *gpu);
+
+struct msm_gpu *a3xx_gpu_init(struct drm_device *dev);
+void __init a3xx_register(void);
+void __exit a3xx_unregister(void);
+
+#endif /* __MSM_GPU_H__ */
diff --git a/drivers/gpu/drm/msm/msm_ringbuffer.c b/drivers/gpu/drm/msm/msm_ringbuffer.c
new file mode 100644
index 000000000000..8171537dd7d1
--- /dev/null
+++ b/drivers/gpu/drm/msm/msm_ringbuffer.c
@@ -0,0 +1,61 @@
+/*
+ * Copyright (C) 2013 Red Hat
+ * Author: Rob Clark <robdclark@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include "msm_ringbuffer.h"
+#include "msm_gpu.h"
+
+struct msm_ringbuffer *msm_ringbuffer_new(struct msm_gpu *gpu, int size)
+{
+	struct msm_ringbuffer *ring;
+	int ret;
+
+	size = ALIGN(size, 4);   /* size should be dword aligned */
+
+	ring = kzalloc(sizeof(*ring), GFP_KERNEL);
+	if (!ring) {
+		ret = -ENOMEM;
+		goto fail;
+	}
+
+	ring->gpu = gpu;
+	ring->bo = msm_gem_new(gpu->dev, size, MSM_BO_WC);
+	if (IS_ERR(ring->bo)) {
+		ret = PTR_ERR(ring->bo);
+		ring->bo = NULL;
+		goto fail;
+	}
+
+	ring->start = msm_gem_vaddr_locked(ring->bo);
+	ring->end   = ring->start + (size / 4);
+	ring->cur   = ring->start;
+
+	ring->size = size;
+
+	return ring;
+
+fail:
+	if (ring)
+		msm_ringbuffer_destroy(ring);
+	return ERR_PTR(ret);
+}
+
+void msm_ringbuffer_destroy(struct msm_ringbuffer *ring)
+{
+	if (ring->bo)
+		drm_gem_object_unreference(ring->bo);
+	kfree(ring);
+}
diff --git a/drivers/gpu/drm/msm/msm_ringbuffer.h b/drivers/gpu/drm/msm/msm_ringbuffer.h
new file mode 100644
index 000000000000..6e0e1049fa4f
--- /dev/null
+++ b/drivers/gpu/drm/msm/msm_ringbuffer.h
@@ -0,0 +1,43 @@
+/*
+ * Copyright (C) 2013 Red Hat
+ * Author: Rob Clark <robdclark@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __MSM_RINGBUFFER_H__
+#define __MSM_RINGBUFFER_H__
+
+#include "msm_drv.h"
+
+struct msm_ringbuffer {
+	struct msm_gpu *gpu;
+	int size;
+	struct drm_gem_object *bo;
+	uint32_t *start, *end, *cur;
+};
+
+struct msm_ringbuffer *msm_ringbuffer_new(struct msm_gpu *gpu, int size);
+void msm_ringbuffer_destroy(struct msm_ringbuffer *ring);
+
+/* ringbuffer helpers (the parts that are same for a3xx/a2xx/z180..) */
+
+static inline void
+OUT_RING(struct msm_ringbuffer *ring, uint32_t data)
+{
+	if (ring->cur == ring->end)
+		ring->cur = ring->start;
+	*(ring->cur++) = data;
+}
+
+#endif /* __MSM_RINGBUFFER_H__ */
diff --git a/drivers/gpu/drm/nouveau/core/core/printk.c b/drivers/gpu/drm/nouveau/core/core/printk.c
index 6161eaf5447c..52fb2aa129e8 100644
--- a/drivers/gpu/drm/nouveau/core/core/printk.c
+++ b/drivers/gpu/drm/nouveau/core/core/printk.c
@@ -27,6 +27,8 @@
 #include <core/subdev.h>
 #include <core/printk.h>
 
+int nv_printk_suspend_level = NV_DBG_DEBUG;
+
 void
 nv_printk_(struct nouveau_object *object, const char *pfx, int level,
 	   const char *fmt, ...)
@@ -72,3 +74,20 @@ nv_printk_(struct nouveau_object *object, const char *pfx, int level,
 	vprintk(mfmt, args);
 	va_end(args);
 }
+
+#define CONV_LEVEL(x) case NV_DBG_##x: return NV_PRINTK_##x
+
+const char *nv_printk_level_to_pfx(int level)
+{
+	switch (level) {
+	CONV_LEVEL(FATAL);
+	CONV_LEVEL(ERROR);
+	CONV_LEVEL(WARN);
+	CONV_LEVEL(INFO);
+	CONV_LEVEL(DEBUG);
+	CONV_LEVEL(PARANOIA);
+	CONV_LEVEL(TRACE);
+	CONV_LEVEL(SPAM);
+	}
+	return NV_PRINTK_DEBUG;
+}
diff --git a/drivers/gpu/drm/nouveau/core/core/ramht.c b/drivers/gpu/drm/nouveau/core/core/ramht.c
index 86a64045dd60..f3b9bddc3875 100644
--- a/drivers/gpu/drm/nouveau/core/core/ramht.c
+++ b/drivers/gpu/drm/nouveau/core/core/ramht.c
@@ -22,7 +22,6 @@
 
 #include <core/object.h>
 #include <core/ramht.h>
-#include <core/math.h>
 
 #include <subdev/bar.h>
 
@@ -104,6 +103,6 @@ nouveau_ramht_new(struct nouveau_object *parent, struct nouveau_object *pargpu,
 	if (ret)
 		return ret;
 
-	ramht->bits = log2i(nv_gpuobj(ramht)->size >> 3);
+	ramht->bits = order_base_2(nv_gpuobj(ramht)->size >> 3);
 	return 0;
 }
diff --git a/drivers/gpu/drm/nouveau/core/engine/bsp/nv98.c b/drivers/gpu/drm/nouveau/core/engine/bsp/nv98.c
index 8bf92b0e6d82..6b089e022fd2 100644
--- a/drivers/gpu/drm/nouveau/core/engine/bsp/nv98.c
+++ b/drivers/gpu/drm/nouveau/core/engine/bsp/nv98.c
@@ -19,16 +19,14 @@
  * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
  * OTHER DEALINGS IN THE SOFTWARE.
  *
- * Authors: Ben Skeggs
+ * Authors: Ben Skeggs, Maarten Lankhorst, Ilia Mirkin
  */
 
-#include <core/engctx.h>
-#include <core/class.h>
-
+#include <engine/falcon.h>
 #include <engine/bsp.h>
 
 struct nv98_bsp_priv {
-	struct nouveau_engine base;
+	struct nouveau_falcon base;
 };
 
 /*******************************************************************************
@@ -37,31 +35,49 @@ struct nv98_bsp_priv {
 
 static struct nouveau_oclass
 nv98_bsp_sclass[] = {
+	{ 0x88b1, &nouveau_object_ofuncs },
+	{ 0x85b1, &nouveau_object_ofuncs },
+	{ 0x86b1, &nouveau_object_ofuncs },
 	{},
 };
 
 /*******************************************************************************
- * BSP context
+ * PBSP context
  ******************************************************************************/
 
 static struct nouveau_oclass
 nv98_bsp_cclass = {
 	.handle = NV_ENGCTX(BSP, 0x98),
 	.ofuncs = &(struct nouveau_ofuncs) {
-		.ctor = _nouveau_engctx_ctor,
-		.dtor = _nouveau_engctx_dtor,
-		.init = _nouveau_engctx_init,
-		.fini = _nouveau_engctx_fini,
-		.rd32 = _nouveau_engctx_rd32,
-		.wr32 = _nouveau_engctx_wr32,
+		.ctor = _nouveau_falcon_context_ctor,
+		.dtor = _nouveau_falcon_context_dtor,
+		.init = _nouveau_falcon_context_init,
+		.fini = _nouveau_falcon_context_fini,
+		.rd32 = _nouveau_falcon_context_rd32,
+		.wr32 = _nouveau_falcon_context_wr32,
 	},
 };
 
 /*******************************************************************************
- * BSP engine/subdev functions
+ * PBSP engine/subdev functions
  ******************************************************************************/
 
 static int
+nv98_bsp_init(struct nouveau_object *object)
+{
+	struct nv98_bsp_priv *priv = (void *)object;
+	int ret;
+
+	ret = nouveau_falcon_init(&priv->base);
+	if (ret)
+		return ret;
+
+	nv_wr32(priv, 0x084010, 0x0000ffd2);
+	nv_wr32(priv, 0x08401c, 0x0000fff2);
+	return 0;
+}
+
+static int
 nv98_bsp_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
 	      struct nouveau_oclass *oclass, void *data, u32 size,
 	      struct nouveau_object **pobject)
@@ -69,7 +85,7 @@ nv98_bsp_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
 	struct nv98_bsp_priv *priv;
 	int ret;
 
-	ret = nouveau_engine_create(parent, engine, oclass, true,
+	ret = nouveau_falcon_create(parent, engine, oclass, 0x084000, true,
 				    "PBSP", "bsp", &priv);
 	*pobject = nv_object(priv);
 	if (ret)
@@ -86,8 +102,10 @@ nv98_bsp_oclass = {
 	.handle = NV_ENGINE(BSP, 0x98),
 	.ofuncs = &(struct nouveau_ofuncs) {
 		.ctor = nv98_bsp_ctor,
-		.dtor = _nouveau_engine_dtor,
-		.init = _nouveau_engine_init,
-		.fini = _nouveau_engine_fini,
+		.dtor = _nouveau_falcon_dtor,
+		.init = nv98_bsp_init,
+		.fini = _nouveau_falcon_fini,
+		.rd32 = _nouveau_falcon_rd32,
+		.wr32 = _nouveau_falcon_wr32,
 	},
 };
diff --git a/drivers/gpu/drm/nouveau/core/engine/disp/dacnv50.c b/drivers/gpu/drm/nouveau/core/engine/disp/dacnv50.c
index f02fd9f443ff..a66b27c0fcab 100644
--- a/drivers/gpu/drm/nouveau/core/engine/disp/dacnv50.c
+++ b/drivers/gpu/drm/nouveau/core/engine/disp/dacnv50.c
@@ -49,18 +49,23 @@ int
 nv50_dac_sense(struct nv50_disp_priv *priv, int or, u32 loadval)
 {
 	const u32 doff = (or * 0x800);
-	int load = -EINVAL;
+
 	nv_mask(priv, 0x61a004 + doff, 0x807f0000, 0x80150000);
 	nv_wait(priv, 0x61a004 + doff, 0x80000000, 0x00000000);
+
 	nv_wr32(priv, 0x61a00c + doff, 0x00100000 | loadval);
 	mdelay(9);
 	udelay(500);
-	nv_wr32(priv, 0x61a00c + doff, 0x80000000);
-	load = (nv_rd32(priv, 0x61a00c + doff) & 0x38000000) >> 27;
-	nv_wr32(priv, 0x61a00c + doff, 0x00000000);
+	loadval = nv_mask(priv, 0x61a00c + doff, 0xffffffff, 0x00000000);
+
 	nv_mask(priv, 0x61a004 + doff, 0x807f0000, 0x80550000);
 	nv_wait(priv, 0x61a004 + doff, 0x80000000, 0x00000000);
-	return load;
+
+	nv_debug(priv, "DAC%d sense: 0x%08x\n", or, loadval);
+	if (!(loadval & 0x80000000))
+		return -ETIMEDOUT;
+
+	return (loadval & 0x38000000) >> 27;
 }
 
 int
diff --git a/drivers/gpu/drm/nouveau/core/engine/disp/dport.c b/drivers/gpu/drm/nouveau/core/engine/disp/dport.c
index 31cc8fe8e7f0..054d9cff4f53 100644
--- a/drivers/gpu/drm/nouveau/core/engine/disp/dport.c
+++ b/drivers/gpu/drm/nouveau/core/engine/disp/dport.c
@@ -150,7 +150,7 @@ dp_link_train_update(struct dp_state *dp, u32 delay)
 	if (ret)
 		return ret;
 
-	DBG("status %*ph\n", 6, dp->stat);
+	DBG("status %6ph\n", dp->stat);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/nouveau/core/engine/disp/nv50.c b/drivers/gpu/drm/nouveau/core/engine/disp/nv50.c
index 7ffe2f309f12..c168ae3eaa97 100644
--- a/drivers/gpu/drm/nouveau/core/engine/disp/nv50.c
+++ b/drivers/gpu/drm/nouveau/core/engine/disp/nv50.c
@@ -628,7 +628,7 @@ nv50_disp_base_init(struct nouveau_object *object)
 	}
 
 	/* ... PIOR caps */
-	for (i = 0; i < 3; i++) {
+	for (i = 0; i < priv->pior.nr; i++) {
 		tmp = nv_rd32(priv, 0x61e000 + (i * 0x800));
 		nv_wr32(priv, 0x6101f0 + (i * 0x04), tmp);
 	}
@@ -834,10 +834,11 @@ exec_script(struct nv50_disp_priv *priv, int head, int id)
 	u8  ver, hdr, cnt, len;
 	u16 data;
 	u32 ctrl = 0x00000000;
+	u32 reg;
 	int i;
 
 	/* DAC */
-	for (i = 0; !(ctrl & (1 << head)) && i < 3; i++)
+	for (i = 0; !(ctrl & (1 << head)) && i < priv->dac.nr; i++)
 		ctrl = nv_rd32(priv, 0x610b5c + (i * 8));
 
 	/* SOR */
@@ -845,19 +846,18 @@ exec_script(struct nv50_disp_priv *priv, int head, int id)
 		if (nv_device(priv)->chipset  < 0x90 ||
 		    nv_device(priv)->chipset == 0x92 ||
 		    nv_device(priv)->chipset == 0xa0) {
-			for (i = 0; !(ctrl & (1 << head)) && i < 2; i++)
-				ctrl = nv_rd32(priv, 0x610b74 + (i * 8));
-			i += 4;
+			reg = 0x610b74;
 		} else {
-			for (i = 0; !(ctrl & (1 << head)) && i < 4; i++)
-				ctrl = nv_rd32(priv, 0x610798 + (i * 8));
-			i += 4;
+			reg = 0x610798;
 		}
+		for (i = 0; !(ctrl & (1 << head)) && i < priv->sor.nr; i++)
+			ctrl = nv_rd32(priv, reg + (i * 8));
+		i += 4;
 	}
 
 	/* PIOR */
 	if (!(ctrl & (1 << head))) {
-		for (i = 0; !(ctrl & (1 << head)) && i < 3; i++)
+		for (i = 0; !(ctrl & (1 << head)) && i < priv->pior.nr; i++)
 			ctrl = nv_rd32(priv, 0x610b84 + (i * 8));
 		i += 8;
 	}
@@ -893,10 +893,11 @@ exec_clkcmp(struct nv50_disp_priv *priv, int head, int id, u32 pclk,
 	u8  ver, hdr, cnt, len;
 	u32 ctrl = 0x00000000;
 	u32 data, conf = ~0;
+	u32 reg;
 	int i;
 
 	/* DAC */
-	for (i = 0; !(ctrl & (1 << head)) && i < 3; i++)
+	for (i = 0; !(ctrl & (1 << head)) && i < priv->dac.nr; i++)
 		ctrl = nv_rd32(priv, 0x610b58 + (i * 8));
 
 	/* SOR */
@@ -904,19 +905,18 @@ exec_clkcmp(struct nv50_disp_priv *priv, int head, int id, u32 pclk,
 		if (nv_device(priv)->chipset  < 0x90 ||
 		    nv_device(priv)->chipset == 0x92 ||
 		    nv_device(priv)->chipset == 0xa0) {
-			for (i = 0; !(ctrl & (1 << head)) && i < 2; i++)
-				ctrl = nv_rd32(priv, 0x610b70 + (i * 8));
-			i += 4;
+			reg = 0x610b70;
 		} else {
-			for (i = 0; !(ctrl & (1 << head)) && i < 4; i++)
-				ctrl = nv_rd32(priv, 0x610794 + (i * 8));
-			i += 4;
+			reg = 0x610794;
 		}
+		for (i = 0; !(ctrl & (1 << head)) && i < priv->sor.nr; i++)
+			ctrl = nv_rd32(priv, reg + (i * 8));
+		i += 4;
 	}
 
 	/* PIOR */
 	if (!(ctrl & (1 << head))) {
-		for (i = 0; !(ctrl & (1 << head)) && i < 3; i++)
+		for (i = 0; !(ctrl & (1 << head)) && i < priv->pior.nr; i++)
 			ctrl = nv_rd32(priv, 0x610b80 + (i * 8));
 		i += 8;
 	}
diff --git a/drivers/gpu/drm/nouveau/core/engine/fifo/nv50.c b/drivers/gpu/drm/nouveau/core/engine/fifo/nv50.c
index e9b8217d0075..7e5dff51d3c5 100644
--- a/drivers/gpu/drm/nouveau/core/engine/fifo/nv50.c
+++ b/drivers/gpu/drm/nouveau/core/engine/fifo/nv50.c
@@ -26,7 +26,6 @@
 #include <core/engctx.h>
 #include <core/ramht.h>
 #include <core/class.h>
-#include <core/math.h>
 
 #include <subdev/timer.h>
 #include <subdev/bar.h>
@@ -278,7 +277,7 @@ nv50_fifo_chan_ctor_ind(struct nouveau_object *parent,
 		return ret;
 
 	ioffset = args->ioffset;
-	ilength = log2i(args->ilength / 8);
+	ilength = order_base_2(args->ilength / 8);
 
 	nv_wo32(base->ramfc, 0x3c, 0x403f6078);
 	nv_wo32(base->ramfc, 0x44, 0x01003fff);
diff --git a/drivers/gpu/drm/nouveau/core/engine/fifo/nv84.c b/drivers/gpu/drm/nouveau/core/engine/fifo/nv84.c
index 7f53196cff52..91a87cd7195a 100644
--- a/drivers/gpu/drm/nouveau/core/engine/fifo/nv84.c
+++ b/drivers/gpu/drm/nouveau/core/engine/fifo/nv84.c
@@ -28,7 +28,6 @@
 #include <core/ramht.h>
 #include <core/event.h>
 #include <core/class.h>
-#include <core/math.h>
 
 #include <subdev/timer.h>
 #include <subdev/bar.h>
@@ -57,6 +56,7 @@ nv84_fifo_context_attach(struct nouveau_object *parent,
 	case NVDEV_ENGINE_SW   : return 0;
 	case NVDEV_ENGINE_GR   : addr = 0x0020; break;
 	case NVDEV_ENGINE_VP   : addr = 0x0040; break;
+	case NVDEV_ENGINE_PPP  :
 	case NVDEV_ENGINE_MPEG : addr = 0x0060; break;
 	case NVDEV_ENGINE_BSP  : addr = 0x0080; break;
 	case NVDEV_ENGINE_CRYPT: addr = 0x00a0; break;
@@ -92,6 +92,7 @@ nv84_fifo_context_detach(struct nouveau_object *parent, bool suspend,
 	case NVDEV_ENGINE_SW   : return 0;
 	case NVDEV_ENGINE_GR   : engn = 0; addr = 0x0020; break;
 	case NVDEV_ENGINE_VP   : engn = 3; addr = 0x0040; break;
+	case NVDEV_ENGINE_PPP  :
 	case NVDEV_ENGINE_MPEG : engn = 1; addr = 0x0060; break;
 	case NVDEV_ENGINE_BSP  : engn = 5; addr = 0x0080; break;
 	case NVDEV_ENGINE_CRYPT: engn = 4; addr = 0x00a0; break;
@@ -258,7 +259,7 @@ nv84_fifo_chan_ctor_ind(struct nouveau_object *parent,
 	nv_parent(chan)->object_detach = nv50_fifo_object_detach;
 
 	ioffset = args->ioffset;
-	ilength = log2i(args->ilength / 8);
+	ilength = order_base_2(args->ilength / 8);
 
 	nv_wo32(base->ramfc, 0x3c, 0x403f6078);
 	nv_wo32(base->ramfc, 0x44, 0x01003fff);
diff --git a/drivers/gpu/drm/nouveau/core/engine/fifo/nvc0.c b/drivers/gpu/drm/nouveau/core/engine/fifo/nvc0.c
index 46dfa68c47bb..ce92f289e751 100644
--- a/drivers/gpu/drm/nouveau/core/engine/fifo/nvc0.c
+++ b/drivers/gpu/drm/nouveau/core/engine/fifo/nvc0.c
@@ -29,7 +29,6 @@
 #include <core/engctx.h>
 #include <core/event.h>
 #include <core/class.h>
-#include <core/math.h>
 #include <core/enum.h>
 
 #include <subdev/timer.h>
@@ -200,7 +199,7 @@ nvc0_fifo_chan_ctor(struct nouveau_object *parent,
 
 	usermem = chan->base.chid * 0x1000;
 	ioffset = args->ioffset;
-	ilength = log2i(args->ilength / 8);
+	ilength = order_base_2(args->ilength / 8);
 
 	for (i = 0; i < 0x1000; i += 4)
 		nv_wo32(priv->user.mem, usermem + i, 0x00000000);
diff --git a/drivers/gpu/drm/nouveau/core/engine/fifo/nve0.c b/drivers/gpu/drm/nouveau/core/engine/fifo/nve0.c
index 09644fa9602c..8e8121abe31b 100644
--- a/drivers/gpu/drm/nouveau/core/engine/fifo/nve0.c
+++ b/drivers/gpu/drm/nouveau/core/engine/fifo/nve0.c
@@ -29,7 +29,6 @@
 #include <core/engctx.h>
 #include <core/event.h>
 #include <core/class.h>
-#include <core/math.h>
 #include <core/enum.h>
 
 #include <subdev/timer.h>
@@ -240,7 +239,7 @@ nve0_fifo_chan_ctor(struct nouveau_object *parent,
 
 	usermem = chan->base.chid * 0x200;
 	ioffset = args->ioffset;
-	ilength = log2i(args->ilength / 8);
+	ilength = order_base_2(args->ilength / 8);
 
 	for (i = 0; i < 0x200; i += 4)
 		nv_wo32(priv->user.mem, usermem + i, 0x00000000);
diff --git a/drivers/gpu/drm/nouveau/core/engine/graph/nv40.h b/drivers/gpu/drm/nouveau/core/engine/graph/nv40.h
index 7da35a4e7970..ad8209377529 100644
--- a/drivers/gpu/drm/nouveau/core/engine/graph/nv40.h
+++ b/drivers/gpu/drm/nouveau/core/engine/graph/nv40.h
@@ -1,6 +1,9 @@
 #ifndef __NV40_GRAPH_H__
 #define __NV40_GRAPH_H__
 
+#include <core/device.h>
+#include <core/gpuobj.h>
+
 /* returns 1 if device is one of the nv4x using the 0x4497 object class,
  * helpful to determine a number of other hardware features
  */
diff --git a/drivers/gpu/drm/nouveau/core/engine/ppp/nv98.c b/drivers/gpu/drm/nouveau/core/engine/ppp/nv98.c
index 5a5b2a773ed7..13bf31c40aa1 100644
--- a/drivers/gpu/drm/nouveau/core/engine/ppp/nv98.c
+++ b/drivers/gpu/drm/nouveau/core/engine/ppp/nv98.c
@@ -19,21 +19,14 @@
  * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
  * OTHER DEALINGS IN THE SOFTWARE.
  *
- * Authors: Ben Skeggs
+ * Authors: Ben Skeggs, Maarten Lankhorst, Ilia Mirkin
  */
 
-#include <core/engine.h>
-#include <core/engctx.h>
-#include <core/class.h>
-
+#include <engine/falcon.h>
 #include <engine/ppp.h>
 
 struct nv98_ppp_priv {
-	struct nouveau_engine base;
-};
-
-struct nv98_ppp_chan {
-	struct nouveau_engctx base;
+	struct nouveau_falcon base;
 };
 
 /*******************************************************************************
@@ -42,6 +35,8 @@ struct nv98_ppp_chan {
 
 static struct nouveau_oclass
 nv98_ppp_sclass[] = {
+	{ 0x88b3, &nouveau_object_ofuncs },
+	{ 0x85b3, &nouveau_object_ofuncs },
 	{},
 };
 
@@ -53,12 +48,12 @@ static struct nouveau_oclass
 nv98_ppp_cclass = {
 	.handle = NV_ENGCTX(PPP, 0x98),
 	.ofuncs = &(struct nouveau_ofuncs) {
-		.ctor = _nouveau_engctx_ctor,
-		.dtor = _nouveau_engctx_dtor,
-		.init = _nouveau_engctx_init,
-		.fini = _nouveau_engctx_fini,
-		.rd32 = _nouveau_engctx_rd32,
-		.wr32 = _nouveau_engctx_wr32,
+		.ctor = _nouveau_falcon_context_ctor,
+		.dtor = _nouveau_falcon_context_dtor,
+		.init = _nouveau_falcon_context_init,
+		.fini = _nouveau_falcon_context_fini,
+		.rd32 = _nouveau_falcon_context_rd32,
+		.wr32 = _nouveau_falcon_context_wr32,
 	},
 };
 
@@ -67,6 +62,21 @@ nv98_ppp_cclass = {
  ******************************************************************************/
 
 static int
+nv98_ppp_init(struct nouveau_object *object)
+{
+	struct nv98_ppp_priv *priv = (void *)object;
+	int ret;
+
+	ret = nouveau_falcon_init(&priv->base);
+	if (ret)
+		return ret;
+
+	nv_wr32(priv, 0x086010, 0x0000ffd2);
+	nv_wr32(priv, 0x08601c, 0x0000fff2);
+	return 0;
+}
+
+static int
 nv98_ppp_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
 	      struct nouveau_oclass *oclass, void *data, u32 size,
 	      struct nouveau_object **pobject)
@@ -74,7 +84,7 @@ nv98_ppp_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
 	struct nv98_ppp_priv *priv;
 	int ret;
 
-	ret = nouveau_engine_create(parent, engine, oclass, true,
+	ret = nouveau_falcon_create(parent, engine, oclass, 0x086000, true,
 				    "PPPP", "ppp", &priv);
 	*pobject = nv_object(priv);
 	if (ret)
@@ -91,8 +101,10 @@ nv98_ppp_oclass = {
 	.handle = NV_ENGINE(PPP, 0x98),
 	.ofuncs = &(struct nouveau_ofuncs) {
 		.ctor = nv98_ppp_ctor,
-		.dtor = _nouveau_engine_dtor,
-		.init = _nouveau_engine_init,
-		.fini = _nouveau_engine_fini,
+		.dtor = _nouveau_falcon_dtor,
+		.init = nv98_ppp_init,
+		.fini = _nouveau_falcon_fini,
+		.rd32 = _nouveau_falcon_rd32,
+		.wr32 = _nouveau_falcon_wr32,
 	},
 };
diff --git a/drivers/gpu/drm/nouveau/core/engine/vp/nv98.c b/drivers/gpu/drm/nouveau/core/engine/vp/nv98.c
index 8a8236bc84de..fc9ae0ff1ef5 100644
--- a/drivers/gpu/drm/nouveau/core/engine/vp/nv98.c
+++ b/drivers/gpu/drm/nouveau/core/engine/vp/nv98.c
@@ -19,16 +19,14 @@
  * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
  * OTHER DEALINGS IN THE SOFTWARE.
  *
- * Authors: Ben Skeggs
+ * Authors: Ben Skeggs, Maarten Lankhorst, Ilia Mirkin
  */
 
-#include <core/engctx.h>
-#include <core/class.h>
-
+#include <engine/falcon.h>
 #include <engine/vp.h>
 
 struct nv98_vp_priv {
-	struct nouveau_engine base;
+	struct nouveau_falcon base;
 };
 
 /*******************************************************************************
@@ -37,6 +35,8 @@ struct nv98_vp_priv {
 
 static struct nouveau_oclass
 nv98_vp_sclass[] = {
+	{ 0x88b2, &nouveau_object_ofuncs },
+	{ 0x85b2, &nouveau_object_ofuncs },
 	{},
 };
 
@@ -48,12 +48,12 @@ static struct nouveau_oclass
 nv98_vp_cclass = {
 	.handle = NV_ENGCTX(VP, 0x98),
 	.ofuncs = &(struct nouveau_ofuncs) {
-		.ctor = _nouveau_engctx_ctor,
-		.dtor = _nouveau_engctx_dtor,
-		.init = _nouveau_engctx_init,
-		.fini = _nouveau_engctx_fini,
-		.rd32 = _nouveau_engctx_rd32,
-		.wr32 = _nouveau_engctx_wr32,
+		.ctor = _nouveau_falcon_context_ctor,
+		.dtor = _nouveau_falcon_context_dtor,
+		.init = _nouveau_falcon_context_init,
+		.fini = _nouveau_falcon_context_fini,
+		.rd32 = _nouveau_falcon_context_rd32,
+		.wr32 = _nouveau_falcon_context_wr32,
 	},
 };
 
@@ -62,6 +62,21 @@ nv98_vp_cclass = {
  ******************************************************************************/
 
 static int
+nv98_vp_init(struct nouveau_object *object)
+{
+	struct nv98_vp_priv *priv = (void *)object;
+	int ret;
+
+	ret = nouveau_falcon_init(&priv->base);
+	if (ret)
+		return ret;
+
+	nv_wr32(priv, 0x085010, 0x0000ffd2);
+	nv_wr32(priv, 0x08501c, 0x0000fff2);
+	return 0;
+}
+
+static int
 nv98_vp_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
 	     struct nouveau_oclass *oclass, void *data, u32 size,
 	     struct nouveau_object **pobject)
@@ -69,7 +84,7 @@ nv98_vp_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
 	struct nv98_vp_priv *priv;
 	int ret;
 
-	ret = nouveau_engine_create(parent, engine, oclass, true,
+	ret = nouveau_falcon_create(parent, engine, oclass, 0x085000, true,
 				    "PVP", "vp", &priv);
 	*pobject = nv_object(priv);
 	if (ret)
@@ -86,8 +101,10 @@ nv98_vp_oclass = {
 	.handle = NV_ENGINE(VP, 0x98),
 	.ofuncs = &(struct nouveau_ofuncs) {
 		.ctor = nv98_vp_ctor,
-		.dtor = _nouveau_engine_dtor,
-		.init = _nouveau_engine_init,
-		.fini = _nouveau_engine_fini,
+		.dtor = _nouveau_falcon_dtor,
+		.init = nv98_vp_init,
+		.fini = _nouveau_falcon_fini,
+		.rd32 = _nouveau_falcon_rd32,
+		.wr32 = _nouveau_falcon_wr32,
 	},
 };
diff --git a/drivers/gpu/drm/nouveau/core/include/core/math.h b/drivers/gpu/drm/nouveau/core/include/core/math.h
deleted file mode 100644
index f808131c5cd8..000000000000
--- a/drivers/gpu/drm/nouveau/core/include/core/math.h
+++ /dev/null
@@ -1,16 +0,0 @@
-#ifndef __NOUVEAU_MATH_H__
-#define __NOUVEAU_MATH_H__
-
-static inline int
-log2i(u64 base)
-{
-	u64 temp = base >> 1;
-	int log2;
-
-	for (log2 = 0; temp; log2++, temp >>= 1) {
-	}
-
-	return (base & (base - 1)) ? log2 + 1: log2;
-}
-
-#endif
diff --git a/drivers/gpu/drm/nouveau/core/include/core/printk.h b/drivers/gpu/drm/nouveau/core/include/core/printk.h
index febed2ea5c80..d87836e3a704 100644
--- a/drivers/gpu/drm/nouveau/core/include/core/printk.h
+++ b/drivers/gpu/drm/nouveau/core/include/core/printk.h
@@ -15,6 +15,12 @@ struct nouveau_object;
 #define NV_PRINTK_TRACE    KERN_DEBUG
 #define NV_PRINTK_SPAM     KERN_DEBUG
 
+extern int nv_printk_suspend_level;
+
+#define NV_DBG_SUSPEND (nv_printk_suspend_level)
+#define NV_PRINTK_SUSPEND  (nv_printk_level_to_pfx(nv_printk_suspend_level))
+
+const char *nv_printk_level_to_pfx(int level);
 void __printf(4, 5)
 nv_printk_(struct nouveau_object *, const char *, int, const char *, ...);
 
@@ -31,6 +37,13 @@ nv_printk_(struct nouveau_object *, const char *, int, const char *, ...);
 #define nv_trace(o,f,a...) nv_printk((o), TRACE, f, ##a)
 #define nv_spam(o,f,a...) nv_printk((o), SPAM, f, ##a)
 
+#define nv_suspend(o,f,a...) nv_printk((o), SUSPEND, f, ##a)
+
+static inline void nv_suspend_set_printk_level(int level)
+{
+	nv_printk_suspend_level = level;
+}
+
 #define nv_assert(f,a...) do {                                                 \
 	if (NV_DBG_FATAL <= CONFIG_NOUVEAU_DEBUG)                              \
 		nv_printk_(NULL, NV_PRINTK_FATAL, NV_DBG_FATAL, f "\n", ##a);  \
diff --git a/drivers/gpu/drm/nouveau/core/include/subdev/i2c.h b/drivers/gpu/drm/nouveau/core/include/subdev/i2c.h
index 888384c0bed8..7e4e2775f249 100644
--- a/drivers/gpu/drm/nouveau/core/include/subdev/i2c.h
+++ b/drivers/gpu/drm/nouveau/core/include/subdev/i2c.h
@@ -39,8 +39,8 @@ struct nouveau_i2c_func {
 	int  (*drv_ctl)(struct nouveau_i2c_port *, int lane, int sw, int pe);
 };
 
-#define nouveau_i2c_port_create(p,e,o,i,a,d)                                   \
-	nouveau_i2c_port_create_((p), (e), (o), (i), (a),                      \
+#define nouveau_i2c_port_create(p,e,o,i,a,f,d)                                 \
+	nouveau_i2c_port_create_((p), (e), (o), (i), (a), (f),                 \
 				 sizeof(**d), (void **)d)
 #define nouveau_i2c_port_destroy(p) ({                                         \
 	struct nouveau_i2c_port *port = (p);                                   \
@@ -53,7 +53,9 @@ struct nouveau_i2c_func {
 
 int nouveau_i2c_port_create_(struct nouveau_object *, struct nouveau_object *,
 			     struct nouveau_oclass *, u8,
-			     const struct i2c_algorithm *, int, void **);
+			     const struct i2c_algorithm *,
+			     const struct nouveau_i2c_func *,
+			     int, void **);
 void _nouveau_i2c_port_dtor(struct nouveau_object *);
 #define _nouveau_i2c_port_init nouveau_object_init
 #define _nouveau_i2c_port_fini nouveau_object_fini
diff --git a/drivers/gpu/drm/nouveau/core/include/subdev/mc.h b/drivers/gpu/drm/nouveau/core/include/subdev/mc.h
index 9d2cd2006250..ce6569f365a7 100644
--- a/drivers/gpu/drm/nouveau/core/include/subdev/mc.h
+++ b/drivers/gpu/drm/nouveau/core/include/subdev/mc.h
@@ -12,6 +12,7 @@ struct nouveau_mc_intr {
 struct nouveau_mc {
 	struct nouveau_subdev base;
 	const struct nouveau_mc_intr *intr_map;
+	bool use_msi;
 };
 
 static inline struct nouveau_mc *
diff --git a/drivers/gpu/drm/nouveau/core/include/subdev/timer.h b/drivers/gpu/drm/nouveau/core/include/subdev/timer.h
index e465d158d352..9ab70dfe5b02 100644
--- a/drivers/gpu/drm/nouveau/core/include/subdev/timer.h
+++ b/drivers/gpu/drm/nouveau/core/include/subdev/timer.h
@@ -22,6 +22,7 @@ bool nouveau_timer_wait_eq(void *, u64 nsec, u32 addr, u32 mask, u32 data);
 bool nouveau_timer_wait_ne(void *, u64 nsec, u32 addr, u32 mask, u32 data);
 bool nouveau_timer_wait_cb(void *, u64 nsec, bool (*func)(void *), void *data);
 void nouveau_timer_alarm(void *, u32 nsec, struct nouveau_alarm *);
+void nouveau_timer_alarm_cancel(void *, struct nouveau_alarm *);
 
 #define NV_WAIT_DEFAULT 2000000000ULL
 #define nv_wait(o,a,m,v)                                                       \
@@ -35,6 +36,7 @@ struct nouveau_timer {
 	struct nouveau_subdev base;
 	u64  (*read)(struct nouveau_timer *);
 	void (*alarm)(struct nouveau_timer *, u64 time, struct nouveau_alarm *);
+	void (*alarm_cancel)(struct nouveau_timer *, struct nouveau_alarm *);
 };
 
 static inline struct nouveau_timer *
diff --git a/drivers/gpu/drm/nouveau/core/os.h b/drivers/gpu/drm/nouveau/core/os.h
index 3bd9be2ab37f..191e739f30d1 100644
--- a/drivers/gpu/drm/nouveau/core/os.h
+++ b/drivers/gpu/drm/nouveau/core/os.h
@@ -13,11 +13,13 @@
 #include <linux/i2c-algo-bit.h>
 #include <linux/delay.h>
 #include <linux/io-mapping.h>
-#include <linux/vmalloc.h>
 #include <linux/acpi.h>
+#include <linux/vmalloc.h>
 #include <linux/dmi.h>
 #include <linux/reboot.h>
 #include <linux/interrupt.h>
+#include <linux/log2.h>
+#include <linux/pm_runtime.h>
 
 #include <asm/unaligned.h>
 
diff --git a/drivers/gpu/drm/nouveau/core/subdev/bios/init.c b/drivers/gpu/drm/nouveau/core/subdev/bios/init.c
index 0687e6481438..57cda2a1437b 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/bios/init.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/bios/init.c
@@ -579,8 +579,22 @@ static void
 init_reserved(struct nvbios_init *init)
 {
 	u8 opcode = nv_ro08(init->bios, init->offset);
-	trace("RESERVED\t0x%02x\n", opcode);
-	init->offset += 1;
+	u8 length, i;
+
+	switch (opcode) {
+	case 0xaa:
+		length = 4;
+		break;
+	default:
+		length = 1;
+		break;
+	}
+
+	trace("RESERVED 0x%02x\t", opcode);
+	for (i = 1; i < length; i++)
+		cont(" 0x%02x", nv_ro08(init->bios, init->offset + i));
+	cont("\n");
+	init->offset += length;
 }
 
 /**
@@ -1437,7 +1451,7 @@ init_configure_mem(struct nvbios_init *init)
 	data = init_rdvgai(init, 0x03c4, 0x01);
 	init_wrvgai(init, 0x03c4, 0x01, data | 0x20);
 
-	while ((addr = nv_ro32(bios, sdata)) != 0xffffffff) {
+	for (; (addr = nv_ro32(bios, sdata)) != 0xffffffff; sdata += 4) {
 		switch (addr) {
 		case 0x10021c: /* CKE_NORMAL */
 		case 0x1002d0: /* CMD_REFRESH */
@@ -2135,6 +2149,7 @@ static struct nvbios_init_opcode {
 	[0x99] = { init_zm_auxch },
 	[0x9a] = { init_i2c_long_if },
 	[0xa9] = { init_gpio_ne },
+	[0xaa] = { init_reserved },
 };
 
 #define init_opcode_nr (sizeof(init_opcode) / sizeof(init_opcode[0]))
@@ -2165,7 +2180,7 @@ nvbios_init(struct nouveau_subdev *subdev, bool execute)
 	u16 data;
 
 	if (execute)
-		nv_info(bios, "running init tables\n");
+		nv_suspend(bios, "running init tables\n");
 	while (!ret && (data = (init_script(bios, ++i)))) {
 		struct nvbios_init init = {
 			.subdev = subdev,
diff --git a/drivers/gpu/drm/nouveau/core/subdev/bios/therm.c b/drivers/gpu/drm/nouveau/core/subdev/bios/therm.c
index 22a20573ed1b..22ac6dbd6c8f 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/bios/therm.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/bios/therm.c
@@ -184,7 +184,8 @@ nvbios_therm_fan_parse(struct nouveau_bios *bios,
 			cur_trip->fan_duty = value;
 			break;
 		case 0x26:
-			fan->pwm_freq = value;
+			if (!fan->pwm_freq)
+				fan->pwm_freq = value;
 			break;
 		case 0x3b:
 			fan->bump_period = value;
diff --git a/drivers/gpu/drm/nouveau/core/subdev/i2c/anx9805.c b/drivers/gpu/drm/nouveau/core/subdev/i2c/anx9805.c
index dec94e9d776a..4b195ac4da66 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/i2c/anx9805.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/i2c/anx9805.c
@@ -118,7 +118,8 @@ anx9805_aux_chan_ctor(struct nouveau_object *parent,
 	int ret;
 
 	ret = nouveau_i2c_port_create(parent, engine, oclass, index,
-				     &nouveau_i2c_aux_algo, &chan);
+				      &nouveau_i2c_aux_algo, &anx9805_aux_func,
+				      &chan);
 	*pobject = nv_object(chan);
 	if (ret)
 		return ret;
@@ -140,8 +141,6 @@ anx9805_aux_chan_ctor(struct nouveau_object *parent,
 		struct i2c_algo_bit_data *algo = mast->adapter.algo_data;
 		algo->udelay = max(algo->udelay, 40);
 	}
-
-	chan->base.func = &anx9805_aux_func;
 	return 0;
 }
 
@@ -234,7 +233,8 @@ anx9805_ddc_port_ctor(struct nouveau_object *parent,
 	int ret;
 
 	ret = nouveau_i2c_port_create(parent, engine, oclass, index,
-				     &anx9805_i2c_algo, &port);
+				      &anx9805_i2c_algo, &anx9805_i2c_func,
+				      &port);
 	*pobject = nv_object(port);
 	if (ret)
 		return ret;
@@ -256,8 +256,6 @@ anx9805_ddc_port_ctor(struct nouveau_object *parent,
 		struct i2c_algo_bit_data *algo = mast->adapter.algo_data;
 		algo->udelay = max(algo->udelay, 40);
 	}
-
-	port->base.func = &anx9805_i2c_func;
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/nouveau/core/subdev/i2c/base.c b/drivers/gpu/drm/nouveau/core/subdev/i2c/base.c
index 8ae2625415e1..2895c19bb152 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/i2c/base.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/i2c/base.c
@@ -95,6 +95,7 @@ nouveau_i2c_port_create_(struct nouveau_object *parent,
 			 struct nouveau_object *engine,
 			 struct nouveau_oclass *oclass, u8 index,
 			 const struct i2c_algorithm *algo,
+			 const struct nouveau_i2c_func *func,
 			 int size, void **pobject)
 {
 	struct nouveau_device *device = nv_device(parent);
@@ -112,6 +113,7 @@ nouveau_i2c_port_create_(struct nouveau_object *parent,
 	port->adapter.owner = THIS_MODULE;
 	port->adapter.dev.parent = &device->pdev->dev;
 	port->index = index;
+	port->func = func;
 	i2c_set_adapdata(&port->adapter, i2c);
 
 	if ( algo == &nouveau_i2c_bit_algo &&
diff --git a/drivers/gpu/drm/nouveau/core/subdev/i2c/nv04.c b/drivers/gpu/drm/nouveau/core/subdev/i2c/nv04.c
index 2ad18840fe63..860d5d2365da 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/i2c/nv04.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/i2c/nv04.c
@@ -91,12 +91,12 @@ nv04_i2c_port_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
 	int ret;
 
 	ret = nouveau_i2c_port_create(parent, engine, oclass, index,
-				     &nouveau_i2c_bit_algo, &port);
+				      &nouveau_i2c_bit_algo, &nv04_i2c_func,
+				      &port);
 	*pobject = nv_object(port);
 	if (ret)
 		return ret;
 
-	port->base.func = &nv04_i2c_func;
 	port->drive = info->drive;
 	port->sense = info->sense;
 	return 0;
diff --git a/drivers/gpu/drm/nouveau/core/subdev/i2c/nv4e.c b/drivers/gpu/drm/nouveau/core/subdev/i2c/nv4e.c
index f501ae25dbb3..0c2655a03bb4 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/i2c/nv4e.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/i2c/nv4e.c
@@ -84,12 +84,12 @@ nv4e_i2c_port_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
 	int ret;
 
 	ret = nouveau_i2c_port_create(parent, engine, oclass, index,
-				     &nouveau_i2c_bit_algo, &port);
+				      &nouveau_i2c_bit_algo, &nv4e_i2c_func,
+				      &port);
 	*pobject = nv_object(port);
 	if (ret)
 		return ret;
 
-	port->base.func = &nv4e_i2c_func;
 	port->addr = 0x600800 + info->drive;
 	return 0;
 }
diff --git a/drivers/gpu/drm/nouveau/core/subdev/i2c/nv50.c b/drivers/gpu/drm/nouveau/core/subdev/i2c/nv50.c
index 378dfa324e5f..a8d67a287704 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/i2c/nv50.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/i2c/nv50.c
@@ -85,7 +85,8 @@ nv50_i2c_port_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
 	int ret;
 
 	ret = nouveau_i2c_port_create(parent, engine, oclass, index,
-				     &nouveau_i2c_bit_algo, &port);
+				      &nouveau_i2c_bit_algo, &nv50_i2c_func,
+				      &port);
 	*pobject = nv_object(port);
 	if (ret)
 		return ret;
@@ -93,7 +94,6 @@ nv50_i2c_port_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
 	if (info->drive >= nv50_i2c_addr_nr)
 		return -EINVAL;
 
-	port->base.func = &nv50_i2c_func;
 	port->state = 0x00000007;
 	port->addr = nv50_i2c_addr[info->drive];
 	return 0;
diff --git a/drivers/gpu/drm/nouveau/core/subdev/i2c/nv94.c b/drivers/gpu/drm/nouveau/core/subdev/i2c/nv94.c
index 61b771670bfe..df6d3e4b68be 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/i2c/nv94.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/i2c/nv94.c
@@ -186,7 +186,8 @@ nv94_i2c_port_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
 	int ret;
 
 	ret = nouveau_i2c_port_create(parent, engine, oclass, index,
-				     &nouveau_i2c_bit_algo, &port);
+				      &nouveau_i2c_bit_algo, &nv94_i2c_func,
+				      &port);
 	*pobject = nv_object(port);
 	if (ret)
 		return ret;
@@ -194,7 +195,6 @@ nv94_i2c_port_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
 	if (info->drive >= nv50_i2c_addr_nr)
 		return -EINVAL;
 
-	port->base.func = &nv94_i2c_func;
 	port->state = 7;
 	port->addr = nv50_i2c_addr[info->drive];
 	if (info->share != DCB_I2C_UNUSED) {
@@ -221,12 +221,12 @@ nv94_aux_port_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
 	int ret;
 
 	ret = nouveau_i2c_port_create(parent, engine, oclass, index,
-				     &nouveau_i2c_aux_algo, &port);
+				      &nouveau_i2c_aux_algo, &nv94_aux_func,
+				      &port);
 	*pobject = nv_object(port);
 	if (ret)
 		return ret;
 
-	port->base.func = &nv94_aux_func;
 	port->addr = info->drive;
 	if (info->share != DCB_I2C_UNUSED) {
 		port->ctrl = 0x00e500 + (info->drive * 0x50);
diff --git a/drivers/gpu/drm/nouveau/core/subdev/i2c/nvd0.c b/drivers/gpu/drm/nouveau/core/subdev/i2c/nvd0.c
index f761b8a610f1..29967d30f97c 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/i2c/nvd0.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/i2c/nvd0.c
@@ -60,12 +60,12 @@ nvd0_i2c_port_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
 	int ret;
 
 	ret = nouveau_i2c_port_create(parent, engine, oclass, index,
-				     &nouveau_i2c_bit_algo, &port);
+				      &nouveau_i2c_bit_algo, &nvd0_i2c_func,
+				      &port);
 	*pobject = nv_object(port);
 	if (ret)
 		return ret;
 
-	port->base.func = &nvd0_i2c_func;
 	port->state = 0x00000007;
 	port->addr = 0x00d014 + (info->drive * 0x20);
 	if (info->share != DCB_I2C_UNUSED) {
diff --git a/drivers/gpu/drm/nouveau/core/subdev/instmem/nv40.c b/drivers/gpu/drm/nouveau/core/subdev/instmem/nv40.c
index 716bf41bc3c1..b10a143787a7 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/instmem/nv40.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/instmem/nv40.c
@@ -22,15 +22,9 @@
  * Authors: Ben Skeggs
  */
 
-#include "nv04.h"
+#include <engine/graph/nv40.h>
 
-static inline int
-nv44_graph_class(struct nv04_instmem_priv *priv)
-{
-	if ((nv_device(priv)->chipset & 0xf0) == 0x60)
-		return 1;
-	return !(0x0baf & (1 << (nv_device(priv)->chipset & 0x0f)));
-}
+#include "nv04.h"
 
 static int
 nv40_instmem_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
diff --git a/drivers/gpu/drm/nouveau/core/subdev/mc/base.c b/drivers/gpu/drm/nouveau/core/subdev/mc/base.c
index ec9cd6f10f91..e290cfa4acee 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/mc/base.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/mc/base.c
@@ -23,16 +23,20 @@
  */
 
 #include <subdev/mc.h>
+#include <core/option.h>
 
 static irqreturn_t
 nouveau_mc_intr(int irq, void *arg)
 {
 	struct nouveau_mc *pmc = arg;
 	const struct nouveau_mc_intr *map = pmc->intr_map;
+	struct nouveau_device *device = nv_device(pmc);
 	struct nouveau_subdev *unit;
 	u32 stat, intr;
 
 	intr = stat = nv_rd32(pmc, 0x000100);
+	if (intr == 0xffffffff)
+		return IRQ_NONE;
 	while (stat && map->stat) {
 		if (stat & map->stat) {
 			unit = nouveau_subdev(pmc, map->unit);
@@ -43,10 +47,15 @@ nouveau_mc_intr(int irq, void *arg)
 		map++;
 	}
 
+	if (pmc->use_msi)
+		nv_wr08(pmc->base.base.parent, 0x00088068, 0xff);
+
 	if (intr) {
 		nv_error(pmc, "unknown intr 0x%08x\n", stat);
 	}
 
+	if (stat == IRQ_HANDLED)
+		pm_runtime_mark_last_busy(&device->pdev->dev);
 	return stat ? IRQ_HANDLED : IRQ_NONE;
 }
 
@@ -75,6 +84,8 @@ _nouveau_mc_dtor(struct nouveau_object *object)
 	struct nouveau_device *device = nv_device(object);
 	struct nouveau_mc *pmc = (void *)object;
 	free_irq(device->pdev->irq, pmc);
+	if (pmc->use_msi)
+		pci_disable_msi(device->pdev);
 	nouveau_subdev_destroy(&pmc->base);
 }
 
@@ -96,6 +107,23 @@ nouveau_mc_create_(struct nouveau_object *parent, struct nouveau_object *engine,
 
 	pmc->intr_map = intr_map;
 
+	switch (device->pdev->device & 0x0ff0) {
+	case 0x00f0: /* BR02? */
+	case 0x02e0: /* BR02? */
+		pmc->use_msi = false;
+		break;
+	default:
+		pmc->use_msi = nouveau_boolopt(device->cfgopt, "NvMSI", false);
+		if (pmc->use_msi) {
+			pmc->use_msi = pci_enable_msi(device->pdev) == 0;
+			if (pmc->use_msi) {
+				nv_info(pmc, "MSI interrupts enabled\n");
+				nv_wr08(device, 0x00088068, 0xff);
+			}
+		}
+		break;
+	}
+
 	ret = request_irq(device->pdev->irq, nouveau_mc_intr,
 			  IRQF_SHARED, "nouveau", pmc);
 	if (ret < 0)
diff --git a/drivers/gpu/drm/nouveau/core/subdev/mc/nv98.c b/drivers/gpu/drm/nouveau/core/subdev/mc/nv98.c
index 0d57b4d3e001..06710419a59b 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/mc/nv98.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/mc/nv98.c
@@ -35,6 +35,7 @@ nv98_mc_intr[] = {
 	{ 0x00001000, NVDEV_ENGINE_GR },
 	{ 0x00004000, NVDEV_ENGINE_CRYPT },	/* NV84:NVA3 */
 	{ 0x00008000, NVDEV_ENGINE_BSP },
+	{ 0x00020000, NVDEV_ENGINE_VP },
 	{ 0x00080000, NVDEV_SUBDEV_THERM },	/* NVA3:NVC0 */
 	{ 0x00100000, NVDEV_SUBDEV_TIMER },
 	{ 0x00200000, NVDEV_SUBDEV_GPIO },
@@ -42,7 +43,7 @@ nv98_mc_intr[] = {
 	{ 0x04000000, NVDEV_ENGINE_DISP },
 	{ 0x10000000, NVDEV_SUBDEV_BUS },
 	{ 0x80000000, NVDEV_ENGINE_SW },
-	{ 0x0040d101, NVDEV_SUBDEV_FB },
+	{ 0x0042d101, NVDEV_SUBDEV_FB },
 	{},
 };
 
diff --git a/drivers/gpu/drm/nouveau/core/subdev/therm/base.c b/drivers/gpu/drm/nouveau/core/subdev/therm/base.c
index a00a5a76e2d6..f1de7a9c572b 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/therm/base.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/therm/base.c
@@ -95,12 +95,14 @@ nouveau_therm_update(struct nouveau_therm *therm, int mode)
 	int duty;
 
 	spin_lock_irqsave(&priv->lock, flags);
+	nv_debug(therm, "FAN speed check\n");
 	if (mode < 0)
 		mode = priv->mode;
 	priv->mode = mode;
 
 	switch (mode) {
 	case NOUVEAU_THERM_CTRL_MANUAL:
+		ptimer->alarm_cancel(ptimer, &priv->alarm);
 		duty = nouveau_therm_fan_get(therm);
 		if (duty < 0)
 			duty = 100;
@@ -113,6 +115,7 @@ nouveau_therm_update(struct nouveau_therm *therm, int mode)
 		break;
 	case NOUVEAU_THERM_CTRL_NONE:
 	default:
+		ptimer->alarm_cancel(ptimer, &priv->alarm);
 		goto done;
 	}
 
@@ -122,6 +125,8 @@ nouveau_therm_update(struct nouveau_therm *therm, int mode)
 done:
 	if (list_empty(&priv->alarm.head) && (mode == NOUVEAU_THERM_CTRL_AUTO))
 		ptimer->alarm(ptimer, 1000000000ULL, &priv->alarm);
+	else if (!list_empty(&priv->alarm.head))
+		nv_debug(therm, "therm fan alarm list is not empty\n");
 	spin_unlock_irqrestore(&priv->lock, flags);
 }
 
@@ -267,9 +272,15 @@ _nouveau_therm_init(struct nouveau_object *object)
 	if (ret)
 		return ret;
 
-	if (priv->suspend >= 0)
-		nouveau_therm_fan_mode(therm, priv->mode);
-	priv->sensor.program_alarms(therm);
+	if (priv->suspend >= 0) {
+		/* restore the pwm value only when on manual or auto mode */
+		if (priv->suspend > 0)
+			nouveau_therm_fan_set(therm, true, priv->fan->percent);
+
+		nouveau_therm_fan_mode(therm, priv->suspend);
+	}
+	nouveau_therm_sensor_init(therm);
+	nouveau_therm_fan_init(therm);
 	return 0;
 }
 
@@ -279,6 +290,8 @@ _nouveau_therm_fini(struct nouveau_object *object, bool suspend)
 	struct nouveau_therm *therm = (void *)object;
 	struct nouveau_therm_priv *priv = (void *)therm;
 
+	nouveau_therm_fan_fini(therm, suspend);
+	nouveau_therm_sensor_fini(therm, suspend);
 	if (suspend) {
 		priv->suspend = priv->mode;
 		priv->mode = NOUVEAU_THERM_CTRL_NONE;
diff --git a/drivers/gpu/drm/nouveau/core/subdev/therm/fan.c b/drivers/gpu/drm/nouveau/core/subdev/therm/fan.c
index c728380d3d62..39f47b950ad1 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/therm/fan.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/therm/fan.c
@@ -204,6 +204,23 @@ nouveau_therm_fan_safety_checks(struct nouveau_therm *therm)
 }
 
 int
+nouveau_therm_fan_init(struct nouveau_therm *therm)
+{
+	return 0;
+}
+
+int
+nouveau_therm_fan_fini(struct nouveau_therm *therm, bool suspend)
+{
+	struct nouveau_therm_priv *priv = (void *)therm;
+	struct nouveau_timer *ptimer = nouveau_timer(therm);
+
+	if (suspend)
+		ptimer->alarm_cancel(ptimer, &priv->fan->alarm);
+	return 0;
+}
+
+int
 nouveau_therm_fan_ctor(struct nouveau_therm *therm)
 {
 	struct nouveau_therm_priv *priv = (void *)therm;
@@ -234,6 +251,9 @@ nouveau_therm_fan_ctor(struct nouveau_therm *therm)
 
 	nv_info(therm, "FAN control: %s\n", priv->fan->type);
 
+	/* read the current speed, it is useful when resuming */
+	priv->fan->percent = nouveau_therm_fan_get(therm);
+
 	/* attempt to detect a tachometer connection */
 	ret = gpio->find(gpio, 0, DCB_GPIO_FAN_SENSE, 0xff, &priv->fan->tach);
 	if (ret)
diff --git a/drivers/gpu/drm/nouveau/core/subdev/therm/priv.h b/drivers/gpu/drm/nouveau/core/subdev/therm/priv.h
index 15ca64e481f1..dd38529262fb 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/therm/priv.h
+++ b/drivers/gpu/drm/nouveau/core/subdev/therm/priv.h
@@ -113,6 +113,8 @@ void nouveau_therm_ic_ctor(struct nouveau_therm *therm);
 int nouveau_therm_sensor_ctor(struct nouveau_therm *therm);
 
 int nouveau_therm_fan_ctor(struct nouveau_therm *therm);
+int nouveau_therm_fan_init(struct nouveau_therm *therm);
+int nouveau_therm_fan_fini(struct nouveau_therm *therm, bool suspend);
 int nouveau_therm_fan_get(struct nouveau_therm *therm);
 int nouveau_therm_fan_set(struct nouveau_therm *therm, bool now, int percent);
 int nouveau_therm_fan_user_get(struct nouveau_therm *therm);
@@ -122,6 +124,8 @@ int nouveau_therm_fan_sense(struct nouveau_therm *therm);
 
 int nouveau_therm_preinit(struct nouveau_therm *);
 
+int nouveau_therm_sensor_init(struct nouveau_therm *therm);
+int nouveau_therm_sensor_fini(struct nouveau_therm *therm, bool suspend);
 void nouveau_therm_sensor_preinit(struct nouveau_therm *);
 void nouveau_therm_sensor_set_threshold_state(struct nouveau_therm *therm,
 					     enum nouveau_therm_thrs thrs,
diff --git a/drivers/gpu/drm/nouveau/core/subdev/therm/temp.c b/drivers/gpu/drm/nouveau/core/subdev/therm/temp.c
index dde746c78c8a..b80a33011b93 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/therm/temp.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/therm/temp.c
@@ -180,6 +180,8 @@ alarm_timer_callback(struct nouveau_alarm *alarm)
 
 	spin_lock_irqsave(&priv->sensor.alarm_program_lock, flags);
 
+	nv_debug(therm, "polling the internal temperature\n");
+
 	nouveau_therm_threshold_hyst_polling(therm, &sensor->thrs_fan_boost,
 					     NOUVEAU_THERM_THRS_FANBOOST);
 
@@ -216,6 +218,25 @@ nouveau_therm_program_alarms_polling(struct nouveau_therm *therm)
 	alarm_timer_callback(&priv->sensor.therm_poll_alarm);
 }
 
+int
+nouveau_therm_sensor_init(struct nouveau_therm *therm)
+{
+	struct nouveau_therm_priv *priv = (void *)therm;
+	priv->sensor.program_alarms(therm);
+	return 0;
+}
+
+int
+nouveau_therm_sensor_fini(struct nouveau_therm *therm, bool suspend)
+{
+	struct nouveau_therm_priv *priv = (void *)therm;
+	struct nouveau_timer *ptimer = nouveau_timer(therm);
+
+	if (suspend)
+		ptimer->alarm_cancel(ptimer, &priv->sensor.therm_poll_alarm);
+	return 0;
+}
+
 void
 nouveau_therm_sensor_preinit(struct nouveau_therm *therm)
 {
diff --git a/drivers/gpu/drm/nouveau/core/subdev/timer/base.c b/drivers/gpu/drm/nouveau/core/subdev/timer/base.c
index 5d417cc9949b..cf8a0e0f8ee3 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/timer/base.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/timer/base.c
@@ -85,3 +85,10 @@ nouveau_timer_alarm(void *obj, u32 nsec, struct nouveau_alarm *alarm)
 	struct nouveau_timer *ptimer = nouveau_timer(obj);
 	ptimer->alarm(ptimer, nsec, alarm);
 }
+
+void
+nouveau_timer_alarm_cancel(void *obj, struct nouveau_alarm *alarm)
+{
+	struct nouveau_timer *ptimer = nouveau_timer(obj);
+	ptimer->alarm_cancel(ptimer, alarm);
+}
diff --git a/drivers/gpu/drm/nouveau/core/subdev/timer/nv04.c b/drivers/gpu/drm/nouveau/core/subdev/timer/nv04.c
index 9469b8275675..57711ecb566c 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/timer/nv04.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/timer/nv04.c
@@ -36,6 +36,7 @@ struct nv04_timer_priv {
 	struct nouveau_timer base;
 	struct list_head alarms;
 	spinlock_t lock;
+	u64 suspend_time;
 };
 
 static u64
@@ -113,6 +114,25 @@ nv04_timer_alarm(struct nouveau_timer *ptimer, u64 time,
 }
 
 static void
+nv04_timer_alarm_cancel(struct nouveau_timer *ptimer,
+			struct nouveau_alarm *alarm)
+{
+	struct nv04_timer_priv *priv = (void *)ptimer;
+	unsigned long flags;
+
+	/* avoid deleting an entry while the alarm intr is running */
+	spin_lock_irqsave(&priv->lock, flags);
+
+	/* delete the alarm from the list */
+	list_del(&alarm->head);
+
+	/* reset the head so as list_empty returns 1 */
+	INIT_LIST_HEAD(&alarm->head);
+
+	spin_unlock_irqrestore(&priv->lock, flags);
+}
+
+static void
 nv04_timer_intr(struct nouveau_subdev *subdev)
 {
 	struct nv04_timer_priv *priv = (void *)subdev;
@@ -146,6 +166,8 @@ nv04_timer_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
 	priv->base.base.intr = nv04_timer_intr;
 	priv->base.read = nv04_timer_read;
 	priv->base.alarm = nv04_timer_alarm;
+	priv->base.alarm_cancel = nv04_timer_alarm_cancel;
+	priv->suspend_time = 0;
 
 	INIT_LIST_HEAD(&priv->alarms);
 	spin_lock_init(&priv->lock);
@@ -164,7 +186,7 @@ nv04_timer_init(struct nouveau_object *object)
 {
 	struct nouveau_device *device = nv_device(object);
 	struct nv04_timer_priv *priv = (void *)object;
-	u32 m = 1, f, n, d;
+	u32 m = 1, f, n, d, lo, hi;
 	int ret;
 
 	ret = nouveau_timer_init(&priv->base);
@@ -221,16 +243,25 @@ nv04_timer_init(struct nouveau_object *object)
 		d >>= 1;
 	}
 
+	/* restore the time before suspend */
+	lo = priv->suspend_time;
+	hi = (priv->suspend_time >> 32);
+
 	nv_debug(priv, "input frequency : %dHz\n", f);
 	nv_debug(priv, "input multiplier: %d\n", m);
 	nv_debug(priv, "numerator       : 0x%08x\n", n);
 	nv_debug(priv, "denominator     : 0x%08x\n", d);
 	nv_debug(priv, "timer frequency : %dHz\n", (f * m) * d / n);
+	nv_debug(priv, "time low        : 0x%08x\n", lo);
+	nv_debug(priv, "time high       : 0x%08x\n", hi);
 
 	nv_wr32(priv, NV04_PTIMER_NUMERATOR, n);
 	nv_wr32(priv, NV04_PTIMER_DENOMINATOR, d);
 	nv_wr32(priv, NV04_PTIMER_INTR_0, 0xffffffff);
 	nv_wr32(priv, NV04_PTIMER_INTR_EN_0, 0x00000000);
+	nv_wr32(priv, NV04_PTIMER_TIME_1, hi);
+	nv_wr32(priv, NV04_PTIMER_TIME_0, lo);
+
 	return 0;
 }
 
@@ -238,6 +269,8 @@ static int
 nv04_timer_fini(struct nouveau_object *object, bool suspend)
 {
 	struct nv04_timer_priv *priv = (void *)object;
+	if (suspend)
+		priv->suspend_time = nv04_timer_read(&priv->base);
 	nv_wr32(priv, NV04_PTIMER_INTR_EN_0, 0x00000000);
 	return nouveau_timer_fini(&priv->base, suspend);
 }
diff --git a/drivers/gpu/drm/nouveau/core/subdev/vm/nv50.c b/drivers/gpu/drm/nouveau/core/subdev/vm/nv50.c
index 07dd1fe2d6fb..a4aa81a2173b 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/vm/nv50.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/vm/nv50.c
@@ -174,6 +174,7 @@ nv50_vm_flush(struct nouveau_vm *vm)
 		case NVDEV_ENGINE_GR   : vme = 0x00; break;
 		case NVDEV_ENGINE_VP   : vme = 0x01; break;
 		case NVDEV_SUBDEV_BAR  : vme = 0x06; break;
+		case NVDEV_ENGINE_PPP  :
 		case NVDEV_ENGINE_MPEG : vme = 0x08; break;
 		case NVDEV_ENGINE_BSP  : vme = 0x09; break;
 		case NVDEV_ENGINE_CRYPT: vme = 0x0a; break;
diff --git a/drivers/gpu/drm/nouveau/dispnv04/crtc.c b/drivers/gpu/drm/nouveau/dispnv04/crtc.c
index 6a13ffb53bdb..d4fbf11360fe 100644
--- a/drivers/gpu/drm/nouveau/dispnv04/crtc.c
+++ b/drivers/gpu/drm/nouveau/dispnv04/crtc.c
@@ -22,6 +22,7 @@
  * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
  * DEALINGS IN THE SOFTWARE.
  */
+#include <linux/pm_runtime.h>
 
 #include <drm/drmP.h>
 #include <drm/drm_crtc_helper.h>
@@ -1034,13 +1035,59 @@ nv04_crtc_cursor_move(struct drm_crtc *crtc, int x, int y)
 	return 0;
 }
 
+int
+nouveau_crtc_set_config(struct drm_mode_set *set)
+{
+	struct drm_device *dev;
+	struct nouveau_drm *drm;
+	int ret;
+	struct drm_crtc *crtc;
+	bool active = false;
+	if (!set || !set->crtc)
+		return -EINVAL;
+
+	dev = set->crtc->dev;
+
+	/* get a pm reference here */
+	ret = pm_runtime_get_sync(dev->dev);
+	if (ret < 0)
+		return ret;
+
+	ret = drm_crtc_helper_set_config(set);
+
+	drm = nouveau_drm(dev);
+
+	/* if we get here with no crtcs active then we can drop a reference */
+	list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
+		if (crtc->enabled)
+			active = true;
+	}
+
+	pm_runtime_mark_last_busy(dev->dev);
+	/* if we have active crtcs and we don't have a power ref,
+	   take the current one */
+	if (active && !drm->have_disp_power_ref) {
+		drm->have_disp_power_ref = true;
+		return ret;
+	}
+	/* if we have no active crtcs, then drop the power ref
+	   we got before */
+	if (!active && drm->have_disp_power_ref) {
+		pm_runtime_put_autosuspend(dev->dev);
+		drm->have_disp_power_ref = false;
+	}
+	/* drop the power reference we got coming in here */
+	pm_runtime_put_autosuspend(dev->dev);
+	return ret;
+}
+
 static const struct drm_crtc_funcs nv04_crtc_funcs = {
 	.save = nv_crtc_save,
 	.restore = nv_crtc_restore,
 	.cursor_set = nv04_crtc_cursor_set,
 	.cursor_move = nv04_crtc_cursor_move,
 	.gamma_set = nv_crtc_gamma_set,
-	.set_config = drm_crtc_helper_set_config,
+	.set_config = nouveau_crtc_set_config,
 	.page_flip = nouveau_crtc_page_flip,
 	.destroy = nv_crtc_destroy,
 };
diff --git a/drivers/gpu/drm/nouveau/nouveau_acpi.c b/drivers/gpu/drm/nouveau/nouveau_acpi.c
index d97f20069d3e..dd7d2e182719 100644
--- a/drivers/gpu/drm/nouveau/nouveau_acpi.c
+++ b/drivers/gpu/drm/nouveau/nouveau_acpi.c
@@ -25,8 +25,27 @@
 #define NOUVEAU_DSM_POWER_SPEED 0x01
 #define NOUVEAU_DSM_POWER_STAMINA 0x02
 
-#define NOUVEAU_DSM_OPTIMUS_FN 0x1A
-#define NOUVEAU_DSM_OPTIMUS_ARGS 0x03000001
+#define NOUVEAU_DSM_OPTIMUS_CAPS 0x1A
+#define NOUVEAU_DSM_OPTIMUS_FLAGS 0x1B
+
+#define NOUVEAU_DSM_OPTIMUS_POWERDOWN_PS3 (3 << 24)
+#define NOUVEAU_DSM_OPTIMUS_NO_POWERDOWN_PS3 (2 << 24)
+#define NOUVEAU_DSM_OPTIMUS_FLAGS_CHANGED (1)
+
+#define NOUVEAU_DSM_OPTIMUS_SET_POWERDOWN (NOUVEAU_DSM_OPTIMUS_POWERDOWN_PS3 | NOUVEAU_DSM_OPTIMUS_FLAGS_CHANGED)
+
+/* result of the optimus caps function */
+#define OPTIMUS_ENABLED (1 << 0)
+#define OPTIMUS_STATUS_MASK (3 << 3)
+#define OPTIMUS_STATUS_OFF  (0 << 3)
+#define OPTIMUS_STATUS_ON_ENABLED  (1 << 3)
+#define OPTIMUS_STATUS_PWR_STABLE  (3 << 3)
+#define OPTIMUS_DISPLAY_HOTPLUG (1 << 6)
+#define OPTIMUS_CAPS_MASK (7 << 24)
+#define OPTIMUS_DYNAMIC_PWR_CAP (1 << 24)
+
+#define OPTIMUS_AUDIO_CAPS_MASK (3 << 27)
+#define OPTIMUS_HDA_CODEC_MASK (2 << 27) /* hda bios control */
 
 static struct nouveau_dsm_priv {
 	bool dsm_detected;
@@ -251,9 +270,18 @@ static int nouveau_dsm_pci_probe(struct pci_dev *pdev)
 		retval |= NOUVEAU_DSM_HAS_MUX;
 
 	if (nouveau_test_dsm(dhandle, nouveau_optimus_dsm,
-		NOUVEAU_DSM_OPTIMUS_FN))
+		NOUVEAU_DSM_OPTIMUS_CAPS))
 		retval |= NOUVEAU_DSM_HAS_OPT;
 
+	if (retval & NOUVEAU_DSM_HAS_OPT) {
+		uint32_t result;
+		nouveau_optimus_dsm(dhandle, NOUVEAU_DSM_OPTIMUS_CAPS, 0,
+				    &result);
+		dev_info(&pdev->dev, "optimus capabilities: %s, status %s%s\n",
+			 (result & OPTIMUS_ENABLED) ? "enabled" : "disabled",
+			 (result & OPTIMUS_DYNAMIC_PWR_CAP) ? "dynamic power, " : "",
+			 (result & OPTIMUS_HDA_CODEC_MASK) ? "hda bios codec supported" : "");
+	}
 	if (retval)
 		nouveau_dsm_priv.dhandle = dhandle;
 
@@ -328,8 +356,12 @@ void nouveau_switcheroo_optimus_dsm(void)
 	if (!nouveau_dsm_priv.optimus_detected)
 		return;
 
-	nouveau_optimus_dsm(nouveau_dsm_priv.dhandle, NOUVEAU_DSM_OPTIMUS_FN,
-		NOUVEAU_DSM_OPTIMUS_ARGS, &result);
+	nouveau_optimus_dsm(nouveau_dsm_priv.dhandle, NOUVEAU_DSM_OPTIMUS_FLAGS,
+			    0x3, &result);
+
+	nouveau_optimus_dsm(nouveau_dsm_priv.dhandle, NOUVEAU_DSM_OPTIMUS_CAPS,
+		NOUVEAU_DSM_OPTIMUS_SET_POWERDOWN, &result);
+
 }
 
 void nouveau_unregister_dsm_handler(void)
diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c
index af20fba3a1a4..755c38d06271 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
@@ -1265,7 +1265,9 @@ out:
 static int
 nouveau_bo_verify_access(struct ttm_buffer_object *bo, struct file *filp)
 {
-	return 0;
+	struct nouveau_bo *nvbo = nouveau_bo(bo);
+
+	return drm_vma_node_verify_access(&nvbo->gem->vma_node, filp);
 }
 
 static int
diff --git a/drivers/gpu/drm/nouveau/nouveau_connector.c b/drivers/gpu/drm/nouveau/nouveau_connector.c
index 4da776f344d7..c5b36f9e9a10 100644
--- a/drivers/gpu/drm/nouveau/nouveau_connector.c
+++ b/drivers/gpu/drm/nouveau/nouveau_connector.c
@@ -26,6 +26,8 @@
 
 #include <acpi/button.h>
 
+#include <linux/pm_runtime.h>
+
 #include <drm/drmP.h>
 #include <drm/drm_edid.h>
 #include <drm/drm_crtc_helper.h>
@@ -240,6 +242,8 @@ nouveau_connector_detect(struct drm_connector *connector, bool force)
 	struct nouveau_encoder *nv_partner;
 	struct nouveau_i2c_port *i2c;
 	int type;
+	int ret;
+	enum drm_connector_status conn_status = connector_status_disconnected;
 
 	/* Cleanup the previous EDID block. */
 	if (nv_connector->edid) {
@@ -248,6 +252,10 @@ nouveau_connector_detect(struct drm_connector *connector, bool force)
 		nv_connector->edid = NULL;
 	}
 
+	ret = pm_runtime_get_sync(connector->dev->dev);
+	if (ret < 0)
+		return conn_status;
+
 	i2c = nouveau_connector_ddc_detect(connector, &nv_encoder);
 	if (i2c) {
 		nv_connector->edid = drm_get_edid(connector, &i2c->adapter);
@@ -263,7 +271,8 @@ nouveau_connector_detect(struct drm_connector *connector, bool force)
 		    !nouveau_dp_detect(to_drm_encoder(nv_encoder))) {
 			NV_ERROR(drm, "Detected %s, but failed init\n",
 				 drm_get_connector_name(connector));
-			return connector_status_disconnected;
+			conn_status = connector_status_disconnected;
+			goto out;
 		}
 
 		/* Override encoder type for DVI-I based on whether EDID
@@ -290,13 +299,15 @@ nouveau_connector_detect(struct drm_connector *connector, bool force)
 		}
 
 		nouveau_connector_set_encoder(connector, nv_encoder);
-		return connector_status_connected;
+		conn_status = connector_status_connected;
+		goto out;
 	}
 
 	nv_encoder = nouveau_connector_of_detect(connector);
 	if (nv_encoder) {
 		nouveau_connector_set_encoder(connector, nv_encoder);
-		return connector_status_connected;
+		conn_status = connector_status_connected;
+		goto out;
 	}
 
 detect_analog:
@@ -311,12 +322,18 @@ detect_analog:
 		if (helper->detect(encoder, connector) ==
 						connector_status_connected) {
 			nouveau_connector_set_encoder(connector, nv_encoder);
-			return connector_status_connected;
+			conn_status = connector_status_connected;
+			goto out;
 		}
 
 	}
 
-	return connector_status_disconnected;
+ out:
+
+	pm_runtime_mark_last_busy(connector->dev->dev);
+	pm_runtime_put_autosuspend(connector->dev->dev);
+
+	return conn_status;
 }
 
 static enum drm_connector_status
diff --git a/drivers/gpu/drm/nouveau/nouveau_display.c b/drivers/gpu/drm/nouveau/nouveau_display.c
index a03e75deacaf..7848590f5568 100644
--- a/drivers/gpu/drm/nouveau/nouveau_display.c
+++ b/drivers/gpu/drm/nouveau/nouveau_display.c
@@ -107,6 +107,11 @@ nouveau_framebuffer_init(struct drm_device *dev,
 			 return -EINVAL;
 		}
 
+		if (nvbo->tile_flags & NOUVEAU_GEM_TILE_NONCONTIG) {
+			NV_ERROR(drm, "framebuffer requires contiguous bo\n");
+			return -EINVAL;
+		}
+
 		if (nv_device(drm->device)->chipset == 0x50)
 			nv_fb->r_format |= (tile_flags << 8);
 
@@ -273,7 +278,6 @@ nouveau_display_create(struct drm_device *dev)
 {
 	struct nouveau_drm *drm = nouveau_drm(dev);
 	struct nouveau_display *disp;
-	u32 pclass = dev->pdev->class >> 8;
 	int ret, gen;
 
 	disp = drm->display = kzalloc(sizeof(*disp), GFP_KERNEL);
@@ -335,29 +339,25 @@ nouveau_display_create(struct drm_device *dev)
 	drm_kms_helper_poll_init(dev);
 	drm_kms_helper_poll_disable(dev);
 
-	if (nouveau_modeset == 1 ||
-	    (nouveau_modeset < 0 && pclass == PCI_CLASS_DISPLAY_VGA)) {
-		if (drm->vbios.dcb.entries) {
-			if (nv_device(drm->device)->card_type < NV_50)
-				ret = nv04_display_create(dev);
-			else
-				ret = nv50_display_create(dev);
-		} else {
-			ret = 0;
-		}
-
-		if (ret)
-			goto disp_create_err;
+	if (drm->vbios.dcb.entries) {
+		if (nv_device(drm->device)->card_type < NV_50)
+			ret = nv04_display_create(dev);
+		else
+			ret = nv50_display_create(dev);
+	} else {
+		ret = 0;
+	}
 
-		if (dev->mode_config.num_crtc) {
-			ret = drm_vblank_init(dev, dev->mode_config.num_crtc);
-			if (ret)
-				goto vblank_err;
-		}
+	if (ret)
+		goto disp_create_err;
 
-		nouveau_backlight_init(dev);
+	if (dev->mode_config.num_crtc) {
+		ret = drm_vblank_init(dev, dev->mode_config.num_crtc);
+		if (ret)
+			goto vblank_err;
 	}
 
+	nouveau_backlight_init(dev);
 	return 0;
 
 vblank_err:
@@ -394,7 +394,7 @@ nouveau_display_suspend(struct drm_device *dev)
 
 	nouveau_display_fini(dev);
 
-	NV_INFO(drm, "unpinning framebuffer(s)...\n");
+	NV_SUSPEND(drm, "unpinning framebuffer(s)...\n");
 	list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
 		struct nouveau_framebuffer *nouveau_fb;
 
@@ -416,7 +416,7 @@ nouveau_display_suspend(struct drm_device *dev)
 }
 
 void
-nouveau_display_resume(struct drm_device *dev)
+nouveau_display_repin(struct drm_device *dev)
 {
 	struct nouveau_drm *drm = nouveau_drm(dev);
 	struct drm_crtc *crtc;
@@ -441,10 +441,12 @@ nouveau_display_resume(struct drm_device *dev)
 		if (ret)
 			NV_ERROR(drm, "Could not pin/map cursor.\n");
 	}
+}
 
-	nouveau_fbcon_set_suspend(dev, 0);
-	nouveau_fbcon_zfill_all(dev);
-
+void
+nouveau_display_resume(struct drm_device *dev)
+{
+	struct drm_crtc *crtc;
 	nouveau_display_init(dev);
 
 	/* Force CLUT to get re-loaded during modeset */
@@ -519,7 +521,8 @@ fail:
 
 int
 nouveau_crtc_page_flip(struct drm_crtc *crtc, struct drm_framebuffer *fb,
-		       struct drm_pending_vblank_event *event)
+		       struct drm_pending_vblank_event *event,
+		       uint32_t page_flip_flags)
 {
 	struct drm_device *dev = crtc->dev;
 	struct nouveau_drm *drm = nouveau_drm(dev);
@@ -677,13 +680,6 @@ nouveau_display_dumb_create(struct drm_file *file_priv, struct drm_device *dev,
 }
 
 int
-nouveau_display_dumb_destroy(struct drm_file *file_priv, struct drm_device *dev,
-			     uint32_t handle)
-{
-	return drm_gem_handle_delete(file_priv, handle);
-}
-
-int
 nouveau_display_dumb_map_offset(struct drm_file *file_priv,
 				struct drm_device *dev,
 				uint32_t handle, uint64_t *poffset)
@@ -693,7 +689,7 @@ nouveau_display_dumb_map_offset(struct drm_file *file_priv,
 	gem = drm_gem_object_lookup(dev, file_priv, handle);
 	if (gem) {
 		struct nouveau_bo *bo = gem->driver_private;
-		*poffset = bo->bo.addr_space_offset;
+		*poffset = drm_vma_node_offset_addr(&bo->bo.vma_node);
 		drm_gem_object_unreference_unlocked(gem);
 		return 0;
 	}
diff --git a/drivers/gpu/drm/nouveau/nouveau_display.h b/drivers/gpu/drm/nouveau/nouveau_display.h
index 1ea3e4734b62..025c66f8e0ed 100644
--- a/drivers/gpu/drm/nouveau/nouveau_display.h
+++ b/drivers/gpu/drm/nouveau/nouveau_display.h
@@ -57,10 +57,12 @@ void nouveau_display_destroy(struct drm_device *dev);
 int  nouveau_display_init(struct drm_device *dev);
 void nouveau_display_fini(struct drm_device *dev);
 int  nouveau_display_suspend(struct drm_device *dev);
+void nouveau_display_repin(struct drm_device *dev);
 void nouveau_display_resume(struct drm_device *dev);
 
 int  nouveau_crtc_page_flip(struct drm_crtc *crtc, struct drm_framebuffer *fb,
-			    struct drm_pending_vblank_event *event);
+			    struct drm_pending_vblank_event *event,
+			    uint32_t page_flip_flags);
 int  nouveau_finish_page_flip(struct nouveau_channel *,
 			      struct nouveau_page_flip_state *);
 
@@ -68,11 +70,10 @@ int  nouveau_display_dumb_create(struct drm_file *, struct drm_device *,
 				 struct drm_mode_create_dumb *args);
 int  nouveau_display_dumb_map_offset(struct drm_file *, struct drm_device *,
 				     u32 handle, u64 *offset);
-int  nouveau_display_dumb_destroy(struct drm_file *, struct drm_device *,
-				  u32 handle);
 
 void nouveau_hdmi_mode_set(struct drm_encoder *, struct drm_display_mode *);
 
+int nouveau_crtc_set_config(struct drm_mode_set *set);
 #ifdef CONFIG_DRM_NOUVEAU_BACKLIGHT
 extern int nouveau_backlight_init(struct drm_device *);
 extern void nouveau_backlight_exit(struct drm_device *);
diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c
index 61972668fd05..e893c5362402 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_drm.c
@@ -25,7 +25,10 @@
 #include <linux/console.h>
 #include <linux/module.h>
 #include <linux/pci.h>
-
+#include <linux/pm_runtime.h>
+#include <linux/vga_switcheroo.h>
+#include "drmP.h"
+#include "drm_crtc_helper.h"
 #include <core/device.h>
 #include <core/client.h>
 #include <core/gpuobj.h>
@@ -69,6 +72,10 @@ MODULE_PARM_DESC(modeset, "enable driver (default: auto, "
 int nouveau_modeset = -1;
 module_param_named(modeset, nouveau_modeset, int, 0400);
 
+MODULE_PARM_DESC(runpm, "disable (0), force enable (1), optimus only default (-1)");
+int nouveau_runtime_pm = -1;
+module_param_named(runpm, nouveau_runtime_pm, int, 0400);
+
 static struct drm_driver driver;
 
 static int
@@ -296,6 +303,31 @@ static int nouveau_drm_probe(struct pci_dev *pdev,
 	return 0;
 }
 
+#define PCI_CLASS_MULTIMEDIA_HD_AUDIO 0x0403
+
+static void
+nouveau_get_hdmi_dev(struct drm_device *dev)
+{
+	struct nouveau_drm *drm = dev->dev_private;
+	struct pci_dev *pdev = dev->pdev;
+
+	/* subfunction one is a hdmi audio device? */
+	drm->hdmi_device = pci_get_bus_and_slot((unsigned int)pdev->bus->number,
+						PCI_DEVFN(PCI_SLOT(pdev->devfn), 1));
+
+	if (!drm->hdmi_device) {
+		DRM_INFO("hdmi device  not found %d %d %d\n", pdev->bus->number, PCI_SLOT(pdev->devfn), 1);
+		return;
+	}
+
+	if ((drm->hdmi_device->class >> 8) != PCI_CLASS_MULTIMEDIA_HD_AUDIO) {
+		DRM_INFO("possible hdmi device  not audio %d\n", drm->hdmi_device->class);
+		pci_dev_put(drm->hdmi_device);
+		drm->hdmi_device = NULL;
+		return;
+	}
+}
+
 static int
 nouveau_drm_load(struct drm_device *dev, unsigned long flags)
 {
@@ -314,6 +346,8 @@ nouveau_drm_load(struct drm_device *dev, unsigned long flags)
 	INIT_LIST_HEAD(&drm->clients);
 	spin_lock_init(&drm->tile.lock);
 
+	nouveau_get_hdmi_dev(dev);
+
 	/* make sure AGP controller is in a consistent state before we
 	 * (possibly) execute vbios init tables (see nouveau_agp.h)
 	 */
@@ -388,6 +422,15 @@ nouveau_drm_load(struct drm_device *dev, unsigned long flags)
 
 	nouveau_accel_init(drm);
 	nouveau_fbcon_init(dev);
+
+	if (nouveau_runtime_pm != 0) {
+		pm_runtime_use_autosuspend(dev->dev);
+		pm_runtime_set_autosuspend_delay(dev->dev, 5000);
+		pm_runtime_set_active(dev->dev);
+		pm_runtime_allow(dev->dev);
+		pm_runtime_mark_last_busy(dev->dev);
+		pm_runtime_put(dev->dev);
+	}
 	return 0;
 
 fail_dispinit:
@@ -409,6 +452,7 @@ nouveau_drm_unload(struct drm_device *dev)
 {
 	struct nouveau_drm *drm = nouveau_drm(dev);
 
+	pm_runtime_get_sync(dev->dev);
 	nouveau_fbcon_fini(dev);
 	nouveau_accel_fini(drm);
 
@@ -424,6 +468,8 @@ nouveau_drm_unload(struct drm_device *dev)
 	nouveau_agp_fini(drm);
 	nouveau_vga_fini(drm);
 
+	if (drm->hdmi_device)
+		pci_dev_put(drm->hdmi_device);
 	nouveau_cli_destroy(&drm->client);
 	return 0;
 }
@@ -450,19 +496,16 @@ nouveau_do_suspend(struct drm_device *dev)
 	int ret;
 
 	if (dev->mode_config.num_crtc) {
-		NV_INFO(drm, "suspending fbcon...\n");
-		nouveau_fbcon_set_suspend(dev, 1);
-
-		NV_INFO(drm, "suspending display...\n");
+		NV_SUSPEND(drm, "suspending display...\n");
 		ret = nouveau_display_suspend(dev);
 		if (ret)
 			return ret;
 	}
 
-	NV_INFO(drm, "evicting buffers...\n");
+	NV_SUSPEND(drm, "evicting buffers...\n");
 	ttm_bo_evict_mm(&drm->ttm.bdev, TTM_PL_VRAM);
 
-	NV_INFO(drm, "waiting for kernel channels to go idle...\n");
+	NV_SUSPEND(drm, "waiting for kernel channels to go idle...\n");
 	if (drm->cechan) {
 		ret = nouveau_channel_idle(drm->cechan);
 		if (ret)
@@ -475,7 +518,7 @@ nouveau_do_suspend(struct drm_device *dev)
 			return ret;
 	}
 
-	NV_INFO(drm, "suspending client object trees...\n");
+	NV_SUSPEND(drm, "suspending client object trees...\n");
 	if (drm->fence && nouveau_fence(drm)->suspend) {
 		if (!nouveau_fence(drm)->suspend(drm))
 			return -ENOMEM;
@@ -487,7 +530,7 @@ nouveau_do_suspend(struct drm_device *dev)
 			goto fail_client;
 	}
 
-	NV_INFO(drm, "suspending kernel object tree...\n");
+	NV_SUSPEND(drm, "suspending kernel object tree...\n");
 	ret = nouveau_client_fini(&drm->client.base, true);
 	if (ret)
 		goto fail_client;
@@ -501,7 +544,7 @@ fail_client:
 	}
 
 	if (dev->mode_config.num_crtc) {
-		NV_INFO(drm, "resuming display...\n");
+		NV_SUSPEND(drm, "resuming display...\n");
 		nouveau_display_resume(dev);
 	}
 	return ret;
@@ -513,9 +556,14 @@ int nouveau_pmops_suspend(struct device *dev)
 	struct drm_device *drm_dev = pci_get_drvdata(pdev);
 	int ret;
 
-	if (drm_dev->switch_power_state == DRM_SWITCH_POWER_OFF)
+	if (drm_dev->switch_power_state == DRM_SWITCH_POWER_OFF ||
+	    drm_dev->switch_power_state == DRM_SWITCH_POWER_DYNAMIC_OFF)
 		return 0;
 
+	if (drm_dev->mode_config.num_crtc)
+		nouveau_fbcon_set_suspend(drm_dev, 1);
+
+	nv_suspend_set_printk_level(NV_DBG_INFO);
 	ret = nouveau_do_suspend(drm_dev);
 	if (ret)
 		return ret;
@@ -523,6 +571,7 @@ int nouveau_pmops_suspend(struct device *dev)
 	pci_save_state(pdev);
 	pci_disable_device(pdev);
 	pci_set_power_state(pdev, PCI_D3hot);
+	nv_suspend_set_printk_level(NV_DBG_DEBUG);
 
 	return 0;
 }
@@ -533,15 +582,15 @@ nouveau_do_resume(struct drm_device *dev)
 	struct nouveau_drm *drm = nouveau_drm(dev);
 	struct nouveau_cli *cli;
 
-	NV_INFO(drm, "re-enabling device...\n");
+	NV_SUSPEND(drm, "re-enabling device...\n");
 
 	nouveau_agp_reset(drm);
 
-	NV_INFO(drm, "resuming kernel object tree...\n");
+	NV_SUSPEND(drm, "resuming kernel object tree...\n");
 	nouveau_client_init(&drm->client.base);
 	nouveau_agp_init(drm);
 
-	NV_INFO(drm, "resuming client object trees...\n");
+	NV_SUSPEND(drm, "resuming client object trees...\n");
 	if (drm->fence && nouveau_fence(drm)->resume)
 		nouveau_fence(drm)->resume(drm);
 
@@ -553,9 +602,10 @@ nouveau_do_resume(struct drm_device *dev)
 	nouveau_pm_resume(dev);
 
 	if (dev->mode_config.num_crtc) {
-		NV_INFO(drm, "resuming display...\n");
-		nouveau_display_resume(dev);
+		NV_SUSPEND(drm, "resuming display...\n");
+		nouveau_display_repin(dev);
 	}
+
 	return 0;
 }
 
@@ -565,7 +615,8 @@ int nouveau_pmops_resume(struct device *dev)
 	struct drm_device *drm_dev = pci_get_drvdata(pdev);
 	int ret;
 
-	if (drm_dev->switch_power_state == DRM_SWITCH_POWER_OFF)
+	if (drm_dev->switch_power_state == DRM_SWITCH_POWER_OFF ||
+	    drm_dev->switch_power_state == DRM_SWITCH_POWER_DYNAMIC_OFF)
 		return 0;
 
 	pci_set_power_state(pdev, PCI_D0);
@@ -575,23 +626,56 @@ int nouveau_pmops_resume(struct device *dev)
 		return ret;
 	pci_set_master(pdev);
 
-	return nouveau_do_resume(drm_dev);
+	nv_suspend_set_printk_level(NV_DBG_INFO);
+	ret = nouveau_do_resume(drm_dev);
+	if (ret) {
+		nv_suspend_set_printk_level(NV_DBG_DEBUG);
+		return ret;
+	}
+	if (drm_dev->mode_config.num_crtc)
+		nouveau_fbcon_set_suspend(drm_dev, 0);
+
+	nouveau_fbcon_zfill_all(drm_dev);
+	if (drm_dev->mode_config.num_crtc)
+		nouveau_display_resume(drm_dev);
+	nv_suspend_set_printk_level(NV_DBG_DEBUG);
+	return 0;
 }
 
 static int nouveau_pmops_freeze(struct device *dev)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
 	struct drm_device *drm_dev = pci_get_drvdata(pdev);
+	int ret;
+
+	nv_suspend_set_printk_level(NV_DBG_INFO);
+	if (drm_dev->mode_config.num_crtc)
+		nouveau_fbcon_set_suspend(drm_dev, 1);
 
-	return nouveau_do_suspend(drm_dev);
+	ret = nouveau_do_suspend(drm_dev);
+	nv_suspend_set_printk_level(NV_DBG_DEBUG);
+	return ret;
 }
 
 static int nouveau_pmops_thaw(struct device *dev)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
 	struct drm_device *drm_dev = pci_get_drvdata(pdev);
+	int ret;
 
-	return nouveau_do_resume(drm_dev);
+	nv_suspend_set_printk_level(NV_DBG_INFO);
+	ret = nouveau_do_resume(drm_dev);
+	if (ret) {
+		nv_suspend_set_printk_level(NV_DBG_DEBUG);
+		return ret;
+	}
+	if (drm_dev->mode_config.num_crtc)
+		nouveau_fbcon_set_suspend(drm_dev, 0);
+	nouveau_fbcon_zfill_all(drm_dev);
+	if (drm_dev->mode_config.num_crtc)
+		nouveau_display_resume(drm_dev);
+	nv_suspend_set_printk_level(NV_DBG_DEBUG);
+	return 0;
 }
 
 
@@ -604,19 +688,24 @@ nouveau_drm_open(struct drm_device *dev, struct drm_file *fpriv)
 	char name[32], tmpname[TASK_COMM_LEN];
 	int ret;
 
+	/* need to bring up power immediately if opening device */
+	ret = pm_runtime_get_sync(dev->dev);
+	if (ret < 0)
+		return ret;
+
 	get_task_comm(tmpname, current);
 	snprintf(name, sizeof(name), "%s[%d]", tmpname, pid_nr(fpriv->pid));
 
 	ret = nouveau_cli_create(pdev, name, sizeof(*cli), (void **)&cli);
 	if (ret)
-		return ret;
+		goto out_suspend;
 
 	if (nv_device(drm->device)->card_type >= NV_50) {
 		ret = nouveau_vm_new(nv_device(drm->device), 0, (1ULL << 40),
 				     0x1000, &cli->base.vm);
 		if (ret) {
 			nouveau_cli_destroy(cli);
-			return ret;
+			goto out_suspend;
 		}
 	}
 
@@ -625,7 +714,12 @@ nouveau_drm_open(struct drm_device *dev, struct drm_file *fpriv)
 	mutex_lock(&drm->client.mutex);
 	list_add(&cli->head, &drm->clients);
 	mutex_unlock(&drm->client.mutex);
-	return 0;
+
+out_suspend:
+	pm_runtime_mark_last_busy(dev->dev);
+	pm_runtime_put_autosuspend(dev->dev);
+
+	return ret;
 }
 
 static void
@@ -634,12 +728,15 @@ nouveau_drm_preclose(struct drm_device *dev, struct drm_file *fpriv)
 	struct nouveau_cli *cli = nouveau_cli(fpriv);
 	struct nouveau_drm *drm = nouveau_drm(dev);
 
+	pm_runtime_get_sync(dev->dev);
+
 	if (cli->abi16)
 		nouveau_abi16_fini(cli->abi16);
 
 	mutex_lock(&drm->client.mutex);
 	list_del(&cli->head);
 	mutex_unlock(&drm->client.mutex);
+
 }
 
 static void
@@ -647,33 +744,52 @@ nouveau_drm_postclose(struct drm_device *dev, struct drm_file *fpriv)
 {
 	struct nouveau_cli *cli = nouveau_cli(fpriv);
 	nouveau_cli_destroy(cli);
+	pm_runtime_mark_last_busy(dev->dev);
+	pm_runtime_put_autosuspend(dev->dev);
 }
 
-static struct drm_ioctl_desc
+static const struct drm_ioctl_desc
 nouveau_ioctls[] = {
-	DRM_IOCTL_DEF_DRV(NOUVEAU_GETPARAM, nouveau_abi16_ioctl_getparam, DRM_UNLOCKED|DRM_AUTH),
+	DRM_IOCTL_DEF_DRV(NOUVEAU_GETPARAM, nouveau_abi16_ioctl_getparam, DRM_UNLOCKED|DRM_AUTH|DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(NOUVEAU_SETPARAM, nouveau_abi16_ioctl_setparam, DRM_UNLOCKED|DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
-	DRM_IOCTL_DEF_DRV(NOUVEAU_CHANNEL_ALLOC, nouveau_abi16_ioctl_channel_alloc, DRM_UNLOCKED|DRM_AUTH),
-	DRM_IOCTL_DEF_DRV(NOUVEAU_CHANNEL_FREE, nouveau_abi16_ioctl_channel_free, DRM_UNLOCKED|DRM_AUTH),
-	DRM_IOCTL_DEF_DRV(NOUVEAU_GROBJ_ALLOC, nouveau_abi16_ioctl_grobj_alloc, DRM_UNLOCKED|DRM_AUTH),
-	DRM_IOCTL_DEF_DRV(NOUVEAU_NOTIFIEROBJ_ALLOC, nouveau_abi16_ioctl_notifierobj_alloc, DRM_UNLOCKED|DRM_AUTH),
-	DRM_IOCTL_DEF_DRV(NOUVEAU_GPUOBJ_FREE, nouveau_abi16_ioctl_gpuobj_free, DRM_UNLOCKED|DRM_AUTH),
-	DRM_IOCTL_DEF_DRV(NOUVEAU_GEM_NEW, nouveau_gem_ioctl_new, DRM_UNLOCKED|DRM_AUTH),
-	DRM_IOCTL_DEF_DRV(NOUVEAU_GEM_PUSHBUF, nouveau_gem_ioctl_pushbuf, DRM_UNLOCKED|DRM_AUTH),
-	DRM_IOCTL_DEF_DRV(NOUVEAU_GEM_CPU_PREP, nouveau_gem_ioctl_cpu_prep, DRM_UNLOCKED|DRM_AUTH),
-	DRM_IOCTL_DEF_DRV(NOUVEAU_GEM_CPU_FINI, nouveau_gem_ioctl_cpu_fini, DRM_UNLOCKED|DRM_AUTH),
-	DRM_IOCTL_DEF_DRV(NOUVEAU_GEM_INFO, nouveau_gem_ioctl_info, DRM_UNLOCKED|DRM_AUTH),
+	DRM_IOCTL_DEF_DRV(NOUVEAU_CHANNEL_ALLOC, nouveau_abi16_ioctl_channel_alloc, DRM_UNLOCKED|DRM_AUTH|DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(NOUVEAU_CHANNEL_FREE, nouveau_abi16_ioctl_channel_free, DRM_UNLOCKED|DRM_AUTH|DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(NOUVEAU_GROBJ_ALLOC, nouveau_abi16_ioctl_grobj_alloc, DRM_UNLOCKED|DRM_AUTH|DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(NOUVEAU_NOTIFIEROBJ_ALLOC, nouveau_abi16_ioctl_notifierobj_alloc, DRM_UNLOCKED|DRM_AUTH|DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(NOUVEAU_GPUOBJ_FREE, nouveau_abi16_ioctl_gpuobj_free, DRM_UNLOCKED|DRM_AUTH|DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(NOUVEAU_GEM_NEW, nouveau_gem_ioctl_new, DRM_UNLOCKED|DRM_AUTH|DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(NOUVEAU_GEM_PUSHBUF, nouveau_gem_ioctl_pushbuf, DRM_UNLOCKED|DRM_AUTH|DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(NOUVEAU_GEM_CPU_PREP, nouveau_gem_ioctl_cpu_prep, DRM_UNLOCKED|DRM_AUTH|DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(NOUVEAU_GEM_CPU_FINI, nouveau_gem_ioctl_cpu_fini, DRM_UNLOCKED|DRM_AUTH|DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(NOUVEAU_GEM_INFO, nouveau_gem_ioctl_info, DRM_UNLOCKED|DRM_AUTH|DRM_RENDER_ALLOW),
 };
 
+long nouveau_drm_ioctl(struct file *filp,
+		       unsigned int cmd, unsigned long arg)
+{
+	struct drm_file *file_priv = filp->private_data;
+	struct drm_device *dev;
+	long ret;
+	dev = file_priv->minor->dev;
+
+	ret = pm_runtime_get_sync(dev->dev);
+	if (ret < 0)
+		return ret;
+
+	ret = drm_ioctl(filp, cmd, arg);
+
+	pm_runtime_mark_last_busy(dev->dev);
+	pm_runtime_put_autosuspend(dev->dev);
+	return ret;
+}
 static const struct file_operations
 nouveau_driver_fops = {
 	.owner = THIS_MODULE,
 	.open = drm_open,
 	.release = drm_release,
-	.unlocked_ioctl = drm_ioctl,
+	.unlocked_ioctl = nouveau_drm_ioctl,
 	.mmap = nouveau_ttm_mmap,
 	.poll = drm_poll,
-	.fasync = drm_fasync,
 	.read = drm_read,
 #if defined(CONFIG_COMPAT)
 	.compat_ioctl = nouveau_compat_ioctl,
@@ -684,8 +800,8 @@ nouveau_driver_fops = {
 static struct drm_driver
 driver = {
 	.driver_features =
-		DRIVER_USE_AGP | DRIVER_PCI_DMA | DRIVER_SG |
-		DRIVER_GEM | DRIVER_MODESET | DRIVER_PRIME,
+		DRIVER_USE_AGP |
+		DRIVER_GEM | DRIVER_MODESET | DRIVER_PRIME | DRIVER_RENDER,
 
 	.load = nouveau_drm_load,
 	.unload = nouveau_drm_unload,
@@ -704,6 +820,7 @@ driver = {
 	.disable_vblank = nouveau_drm_vblank_disable,
 
 	.ioctls = nouveau_ioctls,
+	.num_ioctls = ARRAY_SIZE(nouveau_ioctls),
 	.fops = &nouveau_driver_fops,
 
 	.prime_handle_to_fd = drm_gem_prime_handle_to_fd,
@@ -724,7 +841,7 @@ driver = {
 
 	.dumb_create = nouveau_display_dumb_create,
 	.dumb_map_offset = nouveau_display_dumb_map_offset,
-	.dumb_destroy = nouveau_display_dumb_destroy,
+	.dumb_destroy = drm_gem_dumb_destroy,
 
 	.name = DRIVER_NAME,
 	.desc = DRIVER_DESC,
@@ -753,6 +870,91 @@ nouveau_drm_pci_table[] = {
 	{}
 };
 
+static int nouveau_pmops_runtime_suspend(struct device *dev)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct drm_device *drm_dev = pci_get_drvdata(pdev);
+	int ret;
+
+	if (nouveau_runtime_pm == 0)
+		return -EINVAL;
+
+	drm_kms_helper_poll_disable(drm_dev);
+	vga_switcheroo_set_dynamic_switch(pdev, VGA_SWITCHEROO_OFF);
+	nouveau_switcheroo_optimus_dsm();
+	ret = nouveau_do_suspend(drm_dev);
+	pci_save_state(pdev);
+	pci_disable_device(pdev);
+	pci_set_power_state(pdev, PCI_D3cold);
+	drm_dev->switch_power_state = DRM_SWITCH_POWER_DYNAMIC_OFF;
+	return ret;
+}
+
+static int nouveau_pmops_runtime_resume(struct device *dev)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct drm_device *drm_dev = pci_get_drvdata(pdev);
+	struct nouveau_device *device = nouveau_dev(drm_dev);
+	int ret;
+
+	if (nouveau_runtime_pm == 0)
+		return -EINVAL;
+
+	pci_set_power_state(pdev, PCI_D0);
+	pci_restore_state(pdev);
+	ret = pci_enable_device(pdev);
+	if (ret)
+		return ret;
+	pci_set_master(pdev);
+
+	ret = nouveau_do_resume(drm_dev);
+	if (drm_dev->mode_config.num_crtc)
+		nouveau_display_resume(drm_dev);
+	drm_kms_helper_poll_enable(drm_dev);
+	/* do magic */
+	nv_mask(device, 0x88488, (1 << 25), (1 << 25));
+	vga_switcheroo_set_dynamic_switch(pdev, VGA_SWITCHEROO_ON);
+	drm_dev->switch_power_state = DRM_SWITCH_POWER_ON;
+	return ret;
+}
+
+static int nouveau_pmops_runtime_idle(struct device *dev)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct drm_device *drm_dev = pci_get_drvdata(pdev);
+	struct nouveau_drm *drm = nouveau_drm(drm_dev);
+	struct drm_crtc *crtc;
+
+	if (nouveau_runtime_pm == 0)
+		return -EBUSY;
+
+	/* are we optimus enabled? */
+	if (nouveau_runtime_pm == -1 && !nouveau_is_optimus() && !nouveau_is_v1_dsm()) {
+		DRM_DEBUG_DRIVER("failing to power off - not optimus\n");
+		return -EBUSY;
+	}
+
+	/* if we have a hdmi audio device - make sure it has a driver loaded */
+	if (drm->hdmi_device) {
+		if (!drm->hdmi_device->driver) {
+			DRM_DEBUG_DRIVER("failing to power off - no HDMI audio driver loaded\n");
+			pm_runtime_mark_last_busy(dev);
+			return -EBUSY;
+		}
+	}
+
+	list_for_each_entry(crtc, &drm->dev->mode_config.crtc_list, head) {
+		if (crtc->enabled) {
+			DRM_DEBUG_DRIVER("failing to power off - crtc active\n");
+			return -EBUSY;
+		}
+	}
+	pm_runtime_mark_last_busy(dev);
+	pm_runtime_autosuspend(dev);
+	/* we don't want the main rpm_idle to call suspend - we want to autosuspend */
+	return 1;
+}
+
 static const struct dev_pm_ops nouveau_pm_ops = {
 	.suspend = nouveau_pmops_suspend,
 	.resume = nouveau_pmops_resume,
@@ -760,6 +962,9 @@ static const struct dev_pm_ops nouveau_pm_ops = {
 	.thaw = nouveau_pmops_thaw,
 	.poweroff = nouveau_pmops_freeze,
 	.restore = nouveau_pmops_resume,
+	.runtime_suspend = nouveau_pmops_runtime_suspend,
+	.runtime_resume = nouveau_pmops_runtime_resume,
+	.runtime_idle = nouveau_pmops_runtime_idle,
 };
 
 static struct pci_driver
@@ -774,8 +979,6 @@ nouveau_drm_pci_driver = {
 static int __init
 nouveau_drm_init(void)
 {
-	driver.num_ioctls = ARRAY_SIZE(nouveau_ioctls);
-
 	if (nouveau_modeset == -1) {
 #ifdef CONFIG_VGA_CONSOLE
 		if (vgacon_text_force())
diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.h b/drivers/gpu/drm/nouveau/nouveau_drm.h
index 41ff7e0d403a..994fd6ec373b 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drm.h
+++ b/drivers/gpu/drm/nouveau/nouveau_drm.h
@@ -70,6 +70,8 @@ nouveau_cli(struct drm_file *fpriv)
 	return fpriv ? fpriv->driver_priv : NULL;
 }
 
+extern int nouveau_runtime_pm;
+
 struct nouveau_drm {
 	struct nouveau_cli client;
 	struct drm_device *dev;
@@ -129,6 +131,12 @@ struct nouveau_drm {
 
 	/* power management */
 	struct nouveau_pm *pm;
+
+	/* display power reference */
+	bool have_disp_power_ref;
+
+	struct dev_pm_domain vga_pm_domain;
+	struct pci_dev *hdmi_device;
 };
 
 static inline struct nouveau_drm *
@@ -146,6 +154,7 @@ nouveau_dev(struct drm_device *dev)
 int nouveau_pmops_suspend(struct device *);
 int nouveau_pmops_resume(struct device *);
 
+#define NV_SUSPEND(cli, fmt, args...) nv_suspend((cli), fmt, ##args)
 #define NV_FATAL(cli, fmt, args...) nv_fatal((cli), fmt, ##args)
 #define NV_ERROR(cli, fmt, args...) nv_error((cli), fmt, ##args)
 #define NV_WARN(cli, fmt, args...) nv_warn((cli), fmt, ##args)
diff --git a/drivers/gpu/drm/nouveau/nouveau_fbcon.c b/drivers/gpu/drm/nouveau/nouveau_fbcon.c
index 8f6d63d7edd3..a86ecf65c164 100644
--- a/drivers/gpu/drm/nouveau/nouveau_fbcon.c
+++ b/drivers/gpu/drm/nouveau/nouveau_fbcon.c
@@ -454,7 +454,8 @@ nouveau_fbcon_init(struct drm_device *dev)
 	int preferred_bpp;
 	int ret;
 
-	if (!dev->mode_config.num_crtc)
+	if (!dev->mode_config.num_crtc ||
+	    (dev->pdev->class >> 8) != PCI_CLASS_DISPLAY_VGA)
 		return 0;
 
 	fbcon = kzalloc(sizeof(struct nouveau_fbdev), GFP_KERNEL);
diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.c b/drivers/gpu/drm/nouveau/nouveau_gem.c
index 830cb7bad922..f32b71238c03 100644
--- a/drivers/gpu/drm/nouveau/nouveau_gem.c
+++ b/drivers/gpu/drm/nouveau/nouveau_gem.c
@@ -220,7 +220,7 @@ nouveau_gem_info(struct drm_file *file_priv, struct drm_gem_object *gem,
 	}
 
 	rep->size = nvbo->bo.mem.num_pages << PAGE_SHIFT;
-	rep->map_handle = nvbo->bo.addr_space_offset;
+	rep->map_handle = drm_vma_node_offset_addr(&nvbo->bo.vma_node);
 	rep->tile_mode = nvbo->tile_mode;
 	rep->tile_flags = nvbo->tile_flags;
 	return 0;
@@ -579,18 +579,31 @@ nouveau_gem_pushbuf_validate(struct nouveau_channel *chan,
 	return 0;
 }
 
+static inline void
+u_free(void *addr)
+{
+	if (!is_vmalloc_addr(addr))
+		kfree(addr);
+	else
+		vfree(addr);
+}
+
 static inline void *
 u_memcpya(uint64_t user, unsigned nmemb, unsigned size)
 {
 	void *mem;
 	void __user *userptr = (void __force __user *)(uintptr_t)user;
 
-	mem = kmalloc(nmemb * size, GFP_KERNEL);
+	size *= nmemb;
+
+	mem = kmalloc(size, GFP_KERNEL | __GFP_NOWARN);
+	if (!mem)
+		mem = vmalloc(size);
 	if (!mem)
 		return ERR_PTR(-ENOMEM);
 
-	if (DRM_COPY_FROM_USER(mem, userptr, nmemb * size)) {
-		kfree(mem);
+	if (DRM_COPY_FROM_USER(mem, userptr, size)) {
+		u_free(mem);
 		return ERR_PTR(-EFAULT);
 	}
 
@@ -676,7 +689,7 @@ nouveau_gem_pushbuf_reloc_apply(struct nouveau_cli *cli,
 		nouveau_bo_wr32(nvbo, r->reloc_bo_offset >> 2, data);
 	}
 
-	kfree(reloc);
+	u_free(reloc);
 	return ret;
 }
 
@@ -738,7 +751,7 @@ nouveau_gem_ioctl_pushbuf(struct drm_device *dev, void *data,
 
 	bo = u_memcpya(req->buffers, req->nr_buffers, sizeof(*bo));
 	if (IS_ERR(bo)) {
-		kfree(push);
+		u_free(push);
 		return nouveau_abi16_put(abi16, PTR_ERR(bo));
 	}
 
@@ -849,8 +862,8 @@ out:
 	nouveau_fence_unref(&fence);
 
 out_prevalid:
-	kfree(bo);
-	kfree(push);
+	u_free(bo);
+	u_free(push);
 
 out_next:
 	if (chan->dma.ib_max) {
diff --git a/drivers/gpu/drm/nouveau/nouveau_ioc32.c b/drivers/gpu/drm/nouveau/nouveau_ioc32.c
index 08214bcdcb12..c1a7e5a73a26 100644
--- a/drivers/gpu/drm/nouveau/nouveau_ioc32.c
+++ b/drivers/gpu/drm/nouveau/nouveau_ioc32.c
@@ -63,7 +63,7 @@ long nouveau_compat_ioctl(struct file *filp, unsigned int cmd,
 	if (fn != NULL)
 		ret = (*fn)(filp, cmd, arg);
 	else
-		ret = drm_ioctl(filp, cmd, arg);
+		ret = nouveau_drm_ioctl(filp, cmd, arg);
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/nouveau/nouveau_ioctl.h b/drivers/gpu/drm/nouveau/nouveau_ioctl.h
index ef2b2906d9e6..3b9f2e5463a7 100644
--- a/drivers/gpu/drm/nouveau/nouveau_ioctl.h
+++ b/drivers/gpu/drm/nouveau/nouveau_ioctl.h
@@ -2,5 +2,6 @@
 #define __NOUVEAU_IOCTL_H__
 
 long nouveau_compat_ioctl(struct file *, unsigned int cmd, unsigned long arg);
+long nouveau_drm_ioctl(struct file *, unsigned int cmd, unsigned long arg);
 
 #endif
diff --git a/drivers/gpu/drm/nouveau/nouveau_sgdma.c b/drivers/gpu/drm/nouveau/nouveau_sgdma.c
index ca5492ac2da5..0843ebc910d4 100644
--- a/drivers/gpu/drm/nouveau/nouveau_sgdma.c
+++ b/drivers/gpu/drm/nouveau/nouveau_sgdma.c
@@ -104,9 +104,7 @@ nouveau_sgdma_create_ttm(struct ttm_bo_device *bdev,
 	else
 		nvbe->ttm.ttm.func = &nv50_sgdma_backend;
 
-	if (ttm_dma_tt_init(&nvbe->ttm, bdev, size, page_flags, dummy_read_page)) {
-		kfree(nvbe);
+	if (ttm_dma_tt_init(&nvbe->ttm, bdev, size, page_flags, dummy_read_page))
 		return NULL;
-	}
 	return &nvbe->ttm.ttm;
 }
diff --git a/drivers/gpu/drm/nouveau/nouveau_vga.c b/drivers/gpu/drm/nouveau/nouveau_vga.c
index 25d3495725eb..81638d7f2eff 100644
--- a/drivers/gpu/drm/nouveau/nouveau_vga.c
+++ b/drivers/gpu/drm/nouveau/nouveau_vga.c
@@ -32,6 +32,9 @@ nouveau_switcheroo_set_state(struct pci_dev *pdev,
 {
 	struct drm_device *dev = pci_get_drvdata(pdev);
 
+	if ((nouveau_is_optimus() || nouveau_is_v1_dsm()) && state == VGA_SWITCHEROO_OFF)
+		return;
+
 	if (state == VGA_SWITCHEROO_ON) {
 		printk(KERN_ERR "VGA switcheroo: switched nouveau on\n");
 		dev->switch_power_state = DRM_SWITCH_POWER_CHANGING;
@@ -78,8 +81,17 @@ void
 nouveau_vga_init(struct nouveau_drm *drm)
 {
 	struct drm_device *dev = drm->dev;
+	bool runtime = false;
 	vga_client_register(dev->pdev, dev, NULL, nouveau_vga_set_decode);
-	vga_switcheroo_register_client(dev->pdev, &nouveau_switcheroo_ops);
+
+	if (nouveau_runtime_pm == 1)
+		runtime = true;
+	if ((nouveau_runtime_pm == -1) && (nouveau_is_optimus() || nouveau_is_v1_dsm()))
+		runtime = true;
+	vga_switcheroo_register_client(dev->pdev, &nouveau_switcheroo_ops, runtime);
+
+	if (runtime && nouveau_is_v1_dsm() && !nouveau_is_optimus())
+		vga_switcheroo_init_domain_pm_ops(drm->dev->dev, &drm->vga_pm_domain);
 }
 
 void
diff --git a/drivers/gpu/drm/nouveau/nv50_display.c b/drivers/gpu/drm/nouveau/nv50_display.c
index 8b40a36c1b57..f8e66c08b11a 100644
--- a/drivers/gpu/drm/nouveau/nv50_display.c
+++ b/drivers/gpu/drm/nouveau/nv50_display.c
@@ -1326,7 +1326,7 @@ static const struct drm_crtc_funcs nv50_crtc_func = {
 	.cursor_set = nv50_crtc_cursor_set,
 	.cursor_move = nv50_crtc_cursor_move,
 	.gamma_set = nv50_crtc_gamma_set,
-	.set_config = drm_crtc_helper_set_config,
+	.set_config = nouveau_crtc_set_config,
 	.destroy = nv50_crtc_destroy,
 	.page_flip = nouveau_crtc_page_flip,
 };
@@ -1583,7 +1583,7 @@ nv50_dac_detect(struct drm_encoder *encoder, struct drm_connector *connector)
 		load = 340;
 
 	ret = nv_exec(disp->core, NV50_DISP_DAC_LOAD + or, &load, sizeof(load));
-	if (ret || load != 7)
+	if (ret || !load)
 		return connector_status_disconnected;
 
 	return connector_status_connected;
diff --git a/drivers/gpu/drm/omapdrm/Makefile b/drivers/gpu/drm/omapdrm/Makefile
index d85e058f2845..778372b062ad 100644
--- a/drivers/gpu/drm/omapdrm/Makefile
+++ b/drivers/gpu/drm/omapdrm/Makefile
@@ -18,7 +18,4 @@ omapdrm-y := omap_drv.o \
 	omap_dmm_tiler.o \
 	tcm-sita.o
 
-# temporary:
-omapdrm-y += omap_gem_helpers.o
-
 obj-$(CONFIG_DRM_OMAP)	+= omapdrm.o
diff --git a/drivers/gpu/drm/omapdrm/omap_crtc.c b/drivers/gpu/drm/omapdrm/omap_crtc.c
index 11a5263a5e9f..0fd2eb139f6e 100644
--- a/drivers/gpu/drm/omapdrm/omap_crtc.c
+++ b/drivers/gpu/drm/omapdrm/omap_crtc.c
@@ -331,7 +331,8 @@ static void page_flip_cb(void *arg)
 
 static int omap_crtc_page_flip_locked(struct drm_crtc *crtc,
 		 struct drm_framebuffer *fb,
-		 struct drm_pending_vblank_event *event)
+		 struct drm_pending_vblank_event *event,
+		 uint32_t page_flip_flags)
 {
 	struct drm_device *dev = crtc->dev;
 	struct omap_crtc *omap_crtc = to_omap_crtc(crtc);
diff --git a/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c b/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c
index 9b794c933c81..acf667859cb6 100644
--- a/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c
+++ b/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c
@@ -871,7 +871,7 @@ int tiler_map_show(struct seq_file *s, void *arg)
 		goto error;
 
 	for (lut_idx = 0; lut_idx < omap_dmm->num_lut; lut_idx++) {
-		memset(map, 0, sizeof(h_adj * sizeof(*map)));
+		memset(map, 0, h_adj * sizeof(*map));
 		memset(global_map, ' ', (w_adj + 1) * h_adj);
 
 		for (i = 0; i < omap_dmm->container_height; i++) {
diff --git a/drivers/gpu/drm/omapdrm/omap_drv.c b/drivers/gpu/drm/omapdrm/omap_drv.c
index a3004f12b9a3..2603d909f49c 100644
--- a/drivers/gpu/drm/omapdrm/omap_drv.c
+++ b/drivers/gpu/drm/omapdrm/omap_drv.c
@@ -419,7 +419,7 @@ static int ioctl_gem_info(struct drm_device *dev, void *data,
 	return ret;
 }
 
-static struct drm_ioctl_desc ioctls[DRM_COMMAND_END - DRM_COMMAND_BASE] = {
+static const struct drm_ioctl_desc ioctls[DRM_COMMAND_END - DRM_COMMAND_BASE] = {
 	DRM_IOCTL_DEF_DRV(OMAP_GET_PARAM, ioctl_get_param, DRM_UNLOCKED|DRM_AUTH),
 	DRM_IOCTL_DEF_DRV(OMAP_SET_PARAM, ioctl_set_param, DRM_UNLOCKED|DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
 	DRM_IOCTL_DEF_DRV(OMAP_GEM_NEW, ioctl_gem_new, DRM_UNLOCKED|DRM_AUTH),
@@ -524,12 +524,6 @@ static int dev_open(struct drm_device *dev, struct drm_file *file)
 	return 0;
 }
 
-static int dev_firstopen(struct drm_device *dev)
-{
-	DBG("firstopen: dev=%p", dev);
-	return 0;
-}
-
 /**
  * lastclose - clean up after all DRM clients have exited
  * @dev: DRM device
@@ -598,7 +592,6 @@ static const struct file_operations omapdriver_fops = {
 		.release = drm_release,
 		.mmap = omap_gem_mmap,
 		.poll = drm_poll,
-		.fasync = drm_fasync,
 		.read = drm_read,
 		.llseek = noop_llseek,
 };
@@ -609,7 +602,6 @@ static struct drm_driver omap_drm_driver = {
 		.load = dev_load,
 		.unload = dev_unload,
 		.open = dev_open,
-		.firstopen = dev_firstopen,
 		.lastclose = dev_lastclose,
 		.preclose = dev_preclose,
 		.postclose = dev_postclose,
@@ -633,7 +625,7 @@ static struct drm_driver omap_drm_driver = {
 		.gem_vm_ops = &omap_gem_vm_ops,
 		.dumb_create = omap_gem_dumb_create,
 		.dumb_map_offset = omap_gem_dumb_map_offset,
-		.dumb_destroy = omap_gem_dumb_destroy,
+		.dumb_destroy = drm_gem_dumb_destroy,
 		.ioctls = ioctls,
 		.num_ioctls = DRM_OMAP_NUM_IOCTLS,
 		.fops = &omapdriver_fops,
diff --git a/drivers/gpu/drm/omapdrm/omap_drv.h b/drivers/gpu/drm/omapdrm/omap_drv.h
index 14f17da2ce25..30b95b736658 100644
--- a/drivers/gpu/drm/omapdrm/omap_drv.h
+++ b/drivers/gpu/drm/omapdrm/omap_drv.h
@@ -203,9 +203,8 @@ struct drm_framebuffer *omap_framebuffer_create(struct drm_device *dev,
 struct drm_framebuffer *omap_framebuffer_init(struct drm_device *dev,
 		struct drm_mode_fb_cmd2 *mode_cmd, struct drm_gem_object **bos);
 struct drm_gem_object *omap_framebuffer_bo(struct drm_framebuffer *fb, int p);
-int omap_framebuffer_replace(struct drm_framebuffer *a,
-		struct drm_framebuffer *b, void *arg,
-		void (*unpin)(void *arg, struct drm_gem_object *bo));
+int omap_framebuffer_pin(struct drm_framebuffer *fb);
+int omap_framebuffer_unpin(struct drm_framebuffer *fb);
 void omap_framebuffer_update_scanout(struct drm_framebuffer *fb,
 		struct omap_drm_window *win, struct omap_overlay_info *info);
 struct drm_connector *omap_framebuffer_get_next_connector(
@@ -225,8 +224,6 @@ int omap_gem_init_object(struct drm_gem_object *obj);
 void *omap_gem_vaddr(struct drm_gem_object *obj);
 int omap_gem_dumb_map_offset(struct drm_file *file, struct drm_device *dev,
 		uint32_t handle, uint64_t *offset);
-int omap_gem_dumb_destroy(struct drm_file *file, struct drm_device *dev,
-		uint32_t handle);
 int omap_gem_dumb_create(struct drm_file *file, struct drm_device *dev,
 		struct drm_mode_create_dumb *args);
 int omap_gem_mmap(struct file *filp, struct vm_area_struct *vma);
diff --git a/drivers/gpu/drm/omapdrm/omap_encoder.c b/drivers/gpu/drm/omapdrm/omap_encoder.c
index c29451ba65da..6a12e899235b 100644
--- a/drivers/gpu/drm/omapdrm/omap_encoder.c
+++ b/drivers/gpu/drm/omapdrm/omap_encoder.c
@@ -133,7 +133,7 @@ int omap_encoder_update(struct drm_encoder *encoder,
 	struct omap_dss_driver *dssdrv = dssdev->driver;
 	int ret;
 
-	dssdev->output->manager = mgr;
+	dssdev->src->manager = mgr;
 
 	if (dssdrv->check_timings) {
 		ret = dssdrv->check_timings(dssdev, timings);
diff --git a/drivers/gpu/drm/omapdrm/omap_fb.c b/drivers/gpu/drm/omapdrm/omap_fb.c
index 8031402e7951..f2b8f0668c0c 100644
--- a/drivers/gpu/drm/omapdrm/omap_fb.c
+++ b/drivers/gpu/drm/omapdrm/omap_fb.c
@@ -237,55 +237,49 @@ void omap_framebuffer_update_scanout(struct drm_framebuffer *fb,
 	}
 }
 
-/* Call for unpin 'a' (if not NULL), and pin 'b' (if not NULL).  Although
- * buffers to unpin are just pushed to the unpin fifo so that the
- * caller can defer unpin until vblank.
- *
- * Note if this fails (ie. something went very wrong!), all buffers are
- * unpinned, and the caller disables the overlay.  We could have tried
- * to revert back to the previous set of pinned buffers but if things are
- * hosed there is no guarantee that would succeed.
- */
-int omap_framebuffer_replace(struct drm_framebuffer *a,
-		struct drm_framebuffer *b, void *arg,
-		void (*unpin)(void *arg, struct drm_gem_object *bo))
+/* pin, prepare for scanout: */
+int omap_framebuffer_pin(struct drm_framebuffer *fb)
 {
-	int ret = 0, i, na, nb;
-	struct omap_framebuffer *ofba = to_omap_framebuffer(a);
-	struct omap_framebuffer *ofbb = to_omap_framebuffer(b);
-	uint32_t pinned_mask = 0;
+	struct omap_framebuffer *omap_fb = to_omap_framebuffer(fb);
+	int ret, i, n = drm_format_num_planes(fb->pixel_format);
 
-	na = a ? drm_format_num_planes(a->pixel_format) : 0;
-	nb = b ? drm_format_num_planes(b->pixel_format) : 0;
+	for (i = 0; i < n; i++) {
+		struct plane *plane = &omap_fb->planes[i];
+		ret = omap_gem_get_paddr(plane->bo, &plane->paddr, true);
+		if (ret)
+			goto fail;
+		omap_gem_dma_sync(plane->bo, DMA_TO_DEVICE);
+	}
 
-	for (i = 0; i < max(na, nb); i++) {
-		struct plane *pa, *pb;
+	return 0;
 
-		pa = (i < na) ? &ofba->planes[i] : NULL;
-		pb = (i < nb) ? &ofbb->planes[i] : NULL;
+fail:
+	for (i--; i >= 0; i--) {
+		struct plane *plane = &omap_fb->planes[i];
+		omap_gem_put_paddr(plane->bo);
+		plane->paddr = 0;
+	}
 
-		if (pa)
-			unpin(arg, pa->bo);
+	return ret;
+}
 
-		if (pb && !ret) {
-			ret = omap_gem_get_paddr(pb->bo, &pb->paddr, true);
-			if (!ret) {
-				omap_gem_dma_sync(pb->bo, DMA_TO_DEVICE);
-				pinned_mask |= (1 << i);
-			}
-		}
-	}
+/* unpin, no longer being scanned out: */
+int omap_framebuffer_unpin(struct drm_framebuffer *fb)
+{
+	struct omap_framebuffer *omap_fb = to_omap_framebuffer(fb);
+	int ret, i, n = drm_format_num_planes(fb->pixel_format);
 
-	if (ret) {
-		/* something went wrong.. unpin what has been pinned */
-		for (i = 0; i < nb; i++) {
-			if (pinned_mask & (1 << i)) {
-				struct plane *pb = &ofba->planes[i];
-				unpin(arg, pb->bo);
-			}
-		}
+	for (i = 0; i < n; i++) {
+		struct plane *plane = &omap_fb->planes[i];
+		ret = omap_gem_put_paddr(plane->bo);
+		if (ret)
+			goto fail;
+		plane->paddr = 0;
 	}
 
+	return 0;
+
+fail:
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/omapdrm/omap_gem.c b/drivers/gpu/drm/omapdrm/omap_gem.c
index ebbdf4132e9c..533f6ebec531 100644
--- a/drivers/gpu/drm/omapdrm/omap_gem.c
+++ b/drivers/gpu/drm/omapdrm/omap_gem.c
@@ -20,6 +20,7 @@
 
 #include <linux/spinlock.h>
 #include <linux/shmem_fs.h>
+#include <drm/drm_vma_manager.h>
 
 #include "omap_drv.h"
 #include "omap_dmm_tiler.h"
@@ -236,7 +237,7 @@ static int omap_gem_attach_pages(struct drm_gem_object *obj)
 	 * mapping_gfp_mask(mapping) which conflicts w/ GFP_DMA32.. probably
 	 * we actually want CMA memory for it all anyways..
 	 */
-	pages = _drm_gem_get_pages(obj, GFP_KERNEL);
+	pages = drm_gem_get_pages(obj, GFP_KERNEL);
 	if (IS_ERR(pages)) {
 		dev_err(obj->dev->dev, "could not get pages: %ld\n", PTR_ERR(pages));
 		return PTR_ERR(pages);
@@ -270,7 +271,7 @@ static int omap_gem_attach_pages(struct drm_gem_object *obj)
 	return 0;
 
 free_pages:
-	_drm_gem_put_pages(obj, pages, true, false);
+	drm_gem_put_pages(obj, pages, true, false);
 
 	return ret;
 }
@@ -294,7 +295,7 @@ static void omap_gem_detach_pages(struct drm_gem_object *obj)
 	kfree(omap_obj->addrs);
 	omap_obj->addrs = NULL;
 
-	_drm_gem_put_pages(obj, omap_obj->pages, true, false);
+	drm_gem_put_pages(obj, omap_obj->pages, true, false);
 	omap_obj->pages = NULL;
 }
 
@@ -308,21 +309,20 @@ uint32_t omap_gem_flags(struct drm_gem_object *obj)
 static uint64_t mmap_offset(struct drm_gem_object *obj)
 {
 	struct drm_device *dev = obj->dev;
+	int ret;
+	size_t size;
 
 	WARN_ON(!mutex_is_locked(&dev->struct_mutex));
 
-	if (!obj->map_list.map) {
-		/* Make it mmapable */
-		size_t size = omap_gem_mmap_size(obj);
-		int ret = _drm_gem_create_mmap_offset_size(obj, size);
-
-		if (ret) {
-			dev_err(dev->dev, "could not allocate mmap offset\n");
-			return 0;
-		}
+	/* Make it mmapable */
+	size = omap_gem_mmap_size(obj);
+	ret = drm_gem_create_mmap_offset_size(obj, size);
+	if (ret) {
+		dev_err(dev->dev, "could not allocate mmap offset\n");
+		return 0;
 	}
 
-	return (uint64_t)obj->map_list.hash.key << PAGE_SHIFT;
+	return drm_vma_node_offset_addr(&obj->vma_node);
 }
 
 uint64_t omap_gem_mmap_offset(struct drm_gem_object *obj)
@@ -629,21 +629,6 @@ int omap_gem_dumb_create(struct drm_file *file, struct drm_device *dev,
 }
 
 /**
- * omap_gem_dumb_destroy	-	destroy a dumb buffer
- * @file: client file
- * @dev: our DRM device
- * @handle: the object handle
- *
- * Destroy a handle that was created via omap_gem_dumb_create.
- */
-int omap_gem_dumb_destroy(struct drm_file *file, struct drm_device *dev,
-		uint32_t handle)
-{
-	/* No special work needed, drop the reference and see what falls out */
-	return drm_gem_handle_delete(file, handle);
-}
-
-/**
  * omap_gem_dumb_map	-	buffer mapping for dumb interface
  * @file: our drm client file
  * @dev: drm device
@@ -997,12 +982,11 @@ void omap_gem_describe(struct drm_gem_object *obj, struct seq_file *m)
 {
 	struct drm_device *dev = obj->dev;
 	struct omap_gem_object *omap_obj = to_omap_bo(obj);
-	uint64_t off = 0;
+	uint64_t off;
 
 	WARN_ON(!mutex_is_locked(&dev->struct_mutex));
 
-	if (obj->map_list.map)
-		off = (uint64_t)obj->map_list.hash.key;
+	off = drm_vma_node_start(&obj->vma_node);
 
 	seq_printf(m, "%08x: %2d (%2d) %08llx %08Zx (%2d) %p %4d",
 			omap_obj->flags, obj->name, obj->refcount.refcount.counter,
@@ -1309,8 +1293,7 @@ void omap_gem_free_object(struct drm_gem_object *obj)
 
 	list_del(&omap_obj->mm_list);
 
-	if (obj->map_list.map)
-		drm_gem_free_mmap_offset(obj);
+	drm_gem_free_mmap_offset(obj);
 
 	/* this means the object is still pinned.. which really should
 	 * not happen.  I think..
@@ -1427,8 +1410,9 @@ struct drm_gem_object *omap_gem_new(struct drm_device *dev,
 		omap_obj->height = gsize.tiled.height;
 	}
 
+	ret = 0;
 	if (flags & (OMAP_BO_DMA|OMAP_BO_EXT_MEM))
-		ret = drm_gem_private_object_init(dev, obj, size);
+		drm_gem_private_object_init(dev, obj, size);
 	else
 		ret = drm_gem_object_init(dev, obj, size);
 
diff --git a/drivers/gpu/drm/omapdrm/omap_gem_helpers.c b/drivers/gpu/drm/omapdrm/omap_gem_helpers.c
deleted file mode 100644
index f9eb679eb79b..000000000000
--- a/drivers/gpu/drm/omapdrm/omap_gem_helpers.c
+++ /dev/null
@@ -1,169 +0,0 @@
-/*
- * drivers/gpu/drm/omapdrm/omap_gem_helpers.c
- *
- * Copyright (C) 2011 Texas Instruments
- * Author: Rob Clark <rob.clark@linaro.org>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published by
- * the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program.  If not, see <http://www.gnu.org/licenses/>.
- */
-
-/* temporary copy of drm_gem_{get,put}_pages() until the
- * "drm/gem: add functions to get/put pages" patch is merged..
- */
-
-#include <linux/module.h>
-#include <linux/types.h>
-#include <linux/shmem_fs.h>
-
-#include <drm/drmP.h>
-
-/**
- * drm_gem_get_pages - helper to allocate backing pages for a GEM object
- * @obj: obj in question
- * @gfpmask: gfp mask of requested pages
- */
-struct page **_drm_gem_get_pages(struct drm_gem_object *obj, gfp_t gfpmask)
-{
-	struct inode *inode;
-	struct address_space *mapping;
-	struct page *p, **pages;
-	int i, npages;
-
-	/* This is the shared memory object that backs the GEM resource */
-	inode = file_inode(obj->filp);
-	mapping = inode->i_mapping;
-
-	npages = obj->size >> PAGE_SHIFT;
-
-	pages = drm_malloc_ab(npages, sizeof(struct page *));
-	if (pages == NULL)
-		return ERR_PTR(-ENOMEM);
-
-	gfpmask |= mapping_gfp_mask(mapping);
-
-	for (i = 0; i < npages; i++) {
-		p = shmem_read_mapping_page_gfp(mapping, i, gfpmask);
-		if (IS_ERR(p))
-			goto fail;
-		pages[i] = p;
-
-		/* There is a hypothetical issue w/ drivers that require
-		 * buffer memory in the low 4GB.. if the pages are un-
-		 * pinned, and swapped out, they can end up swapped back
-		 * in above 4GB.  If pages are already in memory, then
-		 * shmem_read_mapping_page_gfp will ignore the gfpmask,
-		 * even if the already in-memory page disobeys the mask.
-		 *
-		 * It is only a theoretical issue today, because none of
-		 * the devices with this limitation can be populated with
-		 * enough memory to trigger the issue.  But this BUG_ON()
-		 * is here as a reminder in case the problem with
-		 * shmem_read_mapping_page_gfp() isn't solved by the time
-		 * it does become a real issue.
-		 *
-		 * See this thread: http://lkml.org/lkml/2011/7/11/238
-		 */
-		BUG_ON((gfpmask & __GFP_DMA32) &&
-				(page_to_pfn(p) >= 0x00100000UL));
-	}
-
-	return pages;
-
-fail:
-	while (i--)
-		page_cache_release(pages[i]);
-
-	drm_free_large(pages);
-	return ERR_CAST(p);
-}
-
-/**
- * drm_gem_put_pages - helper to free backing pages for a GEM object
- * @obj: obj in question
- * @pages: pages to free
- */
-void _drm_gem_put_pages(struct drm_gem_object *obj, struct page **pages,
-		bool dirty, bool accessed)
-{
-	int i, npages;
-
-	npages = obj->size >> PAGE_SHIFT;
-
-	for (i = 0; i < npages; i++) {
-		if (dirty)
-			set_page_dirty(pages[i]);
-
-		if (accessed)
-			mark_page_accessed(pages[i]);
-
-		/* Undo the reference we took when populating the table */
-		page_cache_release(pages[i]);
-	}
-
-	drm_free_large(pages);
-}
-
-int
-_drm_gem_create_mmap_offset_size(struct drm_gem_object *obj, size_t size)
-{
-	struct drm_device *dev = obj->dev;
-	struct drm_gem_mm *mm = dev->mm_private;
-	struct drm_map_list *list;
-	struct drm_local_map *map;
-	int ret = 0;
-
-	/* Set the object up for mmap'ing */
-	list = &obj->map_list;
-	list->map = kzalloc(sizeof(struct drm_map_list), GFP_KERNEL);
-	if (!list->map)
-		return -ENOMEM;
-
-	map = list->map;
-	map->type = _DRM_GEM;
-	map->size = size;
-	map->handle = obj;
-
-	/* Get a DRM GEM mmap offset allocated... */
-	list->file_offset_node = drm_mm_search_free(&mm->offset_manager,
-			size / PAGE_SIZE, 0, 0);
-
-	if (!list->file_offset_node) {
-		DRM_ERROR("failed to allocate offset for bo %d\n", obj->name);
-		ret = -ENOSPC;
-		goto out_free_list;
-	}
-
-	list->file_offset_node = drm_mm_get_block(list->file_offset_node,
-			size / PAGE_SIZE, 0);
-	if (!list->file_offset_node) {
-		ret = -ENOMEM;
-		goto out_free_list;
-	}
-
-	list->hash.key = list->file_offset_node->start;
-	ret = drm_ht_insert_item(&mm->offset_hash, &list->hash);
-	if (ret) {
-		DRM_ERROR("failed to add to map hash\n");
-		goto out_free_mm;
-	}
-
-	return 0;
-
-out_free_mm:
-	drm_mm_put_block(list->file_offset_node);
-out_free_list:
-	kfree(list->map);
-	list->map = NULL;
-
-	return ret;
-}
diff --git a/drivers/gpu/drm/omapdrm/omap_plane.c b/drivers/gpu/drm/omapdrm/omap_plane.c
index 8d225d7ff4e3..046d5e660c04 100644
--- a/drivers/gpu/drm/omapdrm/omap_plane.c
+++ b/drivers/gpu/drm/omapdrm/omap_plane.c
@@ -17,7 +17,7 @@
  * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
-#include <linux/kfifo.h>
+#include "drm_flip_work.h"
 
 #include "omap_drv.h"
 #include "omap_dmm_tiler.h"
@@ -58,26 +58,23 @@ struct omap_plane {
 
 	struct omap_drm_irq error_irq;
 
-	/* set of bo's pending unpin until next post_apply() */
-	DECLARE_KFIFO_PTR(unpin_fifo, struct drm_gem_object *);
+	/* for deferring bo unpin's until next post_apply(): */
+	struct drm_flip_work unpin_work;
 
 	// XXX maybe get rid of this and handle vblank in crtc too?
 	struct callback apply_done_cb;
 };
 
-static void unpin(void *arg, struct drm_gem_object *bo)
+static void unpin_worker(struct drm_flip_work *work, void *val)
 {
-	struct drm_plane *plane = arg;
-	struct omap_plane *omap_plane = to_omap_plane(plane);
+	struct omap_plane *omap_plane =
+			container_of(work, struct omap_plane, unpin_work);
+	struct drm_device *dev = omap_plane->base.dev;
 
-	if (kfifo_put(&omap_plane->unpin_fifo,
-			(const struct drm_gem_object **)&bo)) {
-		/* also hold a ref so it isn't free'd while pinned */
-		drm_gem_object_reference(bo);
-	} else {
-		dev_err(plane->dev->dev, "unpin fifo full!\n");
-		omap_gem_put_paddr(bo);
-	}
+	omap_framebuffer_unpin(val);
+	mutex_lock(&dev->mode_config.mutex);
+	drm_framebuffer_unreference(val);
+	mutex_unlock(&dev->mode_config.mutex);
 }
 
 /* update which fb (if any) is pinned for scanout */
@@ -87,23 +84,22 @@ static int update_pin(struct drm_plane *plane, struct drm_framebuffer *fb)
 	struct drm_framebuffer *pinned_fb = omap_plane->pinned_fb;
 
 	if (pinned_fb != fb) {
-		int ret;
+		int ret = 0;
 
 		DBG("%p -> %p", pinned_fb, fb);
 
-		if (fb)
+		if (fb) {
 			drm_framebuffer_reference(fb);
-
-		ret = omap_framebuffer_replace(pinned_fb, fb, plane, unpin);
+			ret = omap_framebuffer_pin(fb);
+		}
 
 		if (pinned_fb)
-			drm_framebuffer_unreference(pinned_fb);
+			drm_flip_work_queue(&omap_plane->unpin_work, pinned_fb);
 
 		if (ret) {
 			dev_err(plane->dev->dev, "could not swap %p -> %p\n",
 					omap_plane->pinned_fb, fb);
-			if (fb)
-				drm_framebuffer_unreference(fb);
+			drm_framebuffer_unreference(fb);
 			omap_plane->pinned_fb = NULL;
 			return ret;
 		}
@@ -170,17 +166,14 @@ static void omap_plane_post_apply(struct omap_drm_apply *apply)
 	struct omap_plane *omap_plane =
 			container_of(apply, struct omap_plane, apply);
 	struct drm_plane *plane = &omap_plane->base;
+	struct omap_drm_private *priv = plane->dev->dev_private;
 	struct omap_overlay_info *info = &omap_plane->info;
-	struct drm_gem_object *bo = NULL;
 	struct callback cb;
 
 	cb = omap_plane->apply_done_cb;
 	omap_plane->apply_done_cb.fxn = NULL;
 
-	while (kfifo_get(&omap_plane->unpin_fifo, &bo)) {
-		omap_gem_put_paddr(bo);
-		drm_gem_object_unreference_unlocked(bo);
-	}
+	drm_flip_work_commit(&omap_plane->unpin_work, priv->wq);
 
 	if (cb.fxn)
 		cb.fxn(cb.arg);
@@ -277,8 +270,7 @@ static void omap_plane_destroy(struct drm_plane *plane)
 	omap_plane_disable(plane);
 	drm_plane_cleanup(plane);
 
-	WARN_ON(!kfifo_is_empty(&omap_plane->unpin_fifo));
-	kfifo_free(&omap_plane->unpin_fifo);
+	drm_flip_work_cleanup(&omap_plane->unpin_work);
 
 	kfree(omap_plane);
 }
@@ -399,7 +391,8 @@ struct drm_plane *omap_plane_init(struct drm_device *dev,
 	if (!omap_plane)
 		goto fail;
 
-	ret = kfifo_alloc(&omap_plane->unpin_fifo, 16, GFP_KERNEL);
+	ret = drm_flip_work_init(&omap_plane->unpin_work, 16,
+			"unpin", unpin_worker);
 	if (ret) {
 		dev_err(dev->dev, "could not allocate unpin FIFO\n");
 		goto fail;
diff --git a/drivers/gpu/drm/qxl/qxl_drv.c b/drivers/gpu/drm/qxl/qxl_drv.c
index df0b577a6608..514118ae72d4 100644
--- a/drivers/gpu/drm/qxl/qxl_drv.c
+++ b/drivers/gpu/drm/qxl/qxl_drv.c
@@ -84,7 +84,6 @@ static const struct file_operations qxl_fops = {
 	.release = drm_release,
 	.unlocked_ioctl = drm_ioctl,
 	.poll = drm_poll,
-	.fasync = drm_fasync,
 	.mmap = qxl_mmap,
 };
 
@@ -221,7 +220,7 @@ static struct drm_driver qxl_driver = {
 
 	.dumb_create = qxl_mode_dumb_create,
 	.dumb_map_offset = qxl_mode_dumb_mmap,
-	.dumb_destroy = qxl_mode_dumb_destroy,
+	.dumb_destroy = drm_gem_dumb_destroy,
 #if defined(CONFIG_DEBUG_FS)
 	.debugfs_init = qxl_debugfs_init,
 	.debugfs_cleanup = qxl_debugfs_takedown,
diff --git a/drivers/gpu/drm/qxl/qxl_drv.h b/drivers/gpu/drm/qxl/qxl_drv.h
index 7e96f4f11738..f7c9adde46a0 100644
--- a/drivers/gpu/drm/qxl/qxl_drv.h
+++ b/drivers/gpu/drm/qxl/qxl_drv.h
@@ -328,7 +328,7 @@ struct qxl_device {
 /* forward declaration for QXL_INFO_IO */
 void qxl_io_log(struct qxl_device *qdev, const char *fmt, ...);
 
-extern struct drm_ioctl_desc qxl_ioctls[];
+extern const struct drm_ioctl_desc qxl_ioctls[];
 extern int qxl_max_ioctl;
 
 int qxl_driver_load(struct drm_device *dev, unsigned long flags);
@@ -405,9 +405,6 @@ int qxl_gem_object_create(struct qxl_device *qdev, int size,
 			  bool discardable, bool kernel,
 			  struct qxl_surface *surf,
 			  struct drm_gem_object **obj);
-int qxl_gem_object_pin(struct drm_gem_object *obj, uint32_t pin_domain,
-			  uint64_t *gpu_addr);
-void qxl_gem_object_unpin(struct drm_gem_object *obj);
 int qxl_gem_object_create_with_handle(struct qxl_device *qdev,
 				      struct drm_file *file_priv,
 				      u32 domain,
@@ -427,9 +424,6 @@ int qxl_bo_kmap(struct qxl_bo *bo, void **ptr);
 int qxl_mode_dumb_create(struct drm_file *file_priv,
 			 struct drm_device *dev,
 			 struct drm_mode_create_dumb *args);
-int qxl_mode_dumb_destroy(struct drm_file *file_priv,
-			  struct drm_device *dev,
-			  uint32_t handle);
 int qxl_mode_dumb_mmap(struct drm_file *filp,
 		       struct drm_device *dev,
 		       uint32_t handle, uint64_t *offset_p);
diff --git a/drivers/gpu/drm/qxl/qxl_dumb.c b/drivers/gpu/drm/qxl/qxl_dumb.c
index 847c4ee798f7..d34bb4130ff0 100644
--- a/drivers/gpu/drm/qxl/qxl_dumb.c
+++ b/drivers/gpu/drm/qxl/qxl_dumb.c
@@ -68,13 +68,6 @@ int qxl_mode_dumb_create(struct drm_file *file_priv,
 	return 0;
 }
 
-int qxl_mode_dumb_destroy(struct drm_file *file_priv,
-			     struct drm_device *dev,
-			     uint32_t handle)
-{
-	return drm_gem_handle_delete(file_priv, handle);
-}
-
 int qxl_mode_dumb_mmap(struct drm_file *file_priv,
 		       struct drm_device *dev,
 		       uint32_t handle, uint64_t *offset_p)
diff --git a/drivers/gpu/drm/qxl/qxl_gem.c b/drivers/gpu/drm/qxl/qxl_gem.c
index 25e1777fb0a2..1648e4125af7 100644
--- a/drivers/gpu/drm/qxl/qxl_gem.c
+++ b/drivers/gpu/drm/qxl/qxl_gem.c
@@ -101,32 +101,6 @@ int qxl_gem_object_create_with_handle(struct qxl_device *qdev,
 	return 0;
 }
 
-int qxl_gem_object_pin(struct drm_gem_object *obj, uint32_t pin_domain,
-			  uint64_t *gpu_addr)
-{
-	struct qxl_bo *qobj = obj->driver_private;
-	int r;
-
-	r = qxl_bo_reserve(qobj, false);
-	if (unlikely(r != 0))
-		return r;
-	r = qxl_bo_pin(qobj, pin_domain, gpu_addr);
-	qxl_bo_unreserve(qobj);
-	return r;
-}
-
-void qxl_gem_object_unpin(struct drm_gem_object *obj)
-{
-	struct qxl_bo *qobj = obj->driver_private;
-	int r;
-
-	r = qxl_bo_reserve(qobj, false);
-	if (likely(r == 0)) {
-		qxl_bo_unpin(qobj);
-		qxl_bo_unreserve(qobj);
-	}
-}
-
 int qxl_gem_object_open(struct drm_gem_object *obj, struct drm_file *file_priv)
 {
 	return 0;
diff --git a/drivers/gpu/drm/qxl/qxl_ioctl.c b/drivers/gpu/drm/qxl/qxl_ioctl.c
index 6de33563d6f1..7b95c75e9626 100644
--- a/drivers/gpu/drm/qxl/qxl_ioctl.c
+++ b/drivers/gpu/drm/qxl/qxl_ioctl.c
@@ -433,7 +433,7 @@ static int qxl_alloc_surf_ioctl(struct drm_device *dev, void *data,
 	return ret;
 }
 
-struct drm_ioctl_desc qxl_ioctls[] = {
+const struct drm_ioctl_desc qxl_ioctls[] = {
 	DRM_IOCTL_DEF_DRV(QXL_ALLOC, qxl_alloc_ioctl, DRM_AUTH|DRM_UNLOCKED),
 
 	DRM_IOCTL_DEF_DRV(QXL_MAP, qxl_map_ioctl, DRM_AUTH|DRM_UNLOCKED),
diff --git a/drivers/gpu/drm/qxl/qxl_object.c b/drivers/gpu/drm/qxl/qxl_object.c
index aa161cddd87e..8691c76c5ef0 100644
--- a/drivers/gpu/drm/qxl/qxl_object.c
+++ b/drivers/gpu/drm/qxl/qxl_object.c
@@ -98,7 +98,6 @@ int qxl_bo_create(struct qxl_device *qdev,
 		kfree(bo);
 		return r;
 	}
-	bo->gem_base.driver_private = NULL;
 	bo->type = domain;
 	bo->pin_count = pinned ? 1 : 0;
 	bo->surface_id = 0;
diff --git a/drivers/gpu/drm/qxl/qxl_object.h b/drivers/gpu/drm/qxl/qxl_object.h
index 8cb6167038e5..d458a140c024 100644
--- a/drivers/gpu/drm/qxl/qxl_object.h
+++ b/drivers/gpu/drm/qxl/qxl_object.h
@@ -59,7 +59,7 @@ static inline unsigned long qxl_bo_size(struct qxl_bo *bo)
 
 static inline u64 qxl_bo_mmap_offset(struct qxl_bo *bo)
 {
-	return bo->tbo.addr_space_offset;
+	return drm_vma_node_offset_addr(&bo->tbo.vma_node);
 }
 
 static inline int qxl_bo_wait(struct qxl_bo *bo, u32 *mem_type,
diff --git a/drivers/gpu/drm/qxl/qxl_release.c b/drivers/gpu/drm/qxl/qxl_release.c
index b61449e52cd5..0109a9644cb2 100644
--- a/drivers/gpu/drm/qxl/qxl_release.c
+++ b/drivers/gpu/drm/qxl/qxl_release.c
@@ -88,7 +88,7 @@ qxl_release_free(struct qxl_device *qdev,
 	list_for_each_entry_safe(entry, tmp, &release->bos, tv.head) {
 		struct qxl_bo *bo = to_qxl_bo(entry->tv.bo);
 		QXL_INFO(qdev, "release %llx\n",
-			entry->tv.bo->addr_space_offset
+			drm_vma_node_offset_addr(&entry->tv.bo->vma_node)
 						- DRM_FILE_OFFSET);
 		qxl_fence_remove_release(&bo->fence, release->id);
 		qxl_bo_unref(&bo);
diff --git a/drivers/gpu/drm/qxl/qxl_ttm.c b/drivers/gpu/drm/qxl/qxl_ttm.c
index 1dfd84cda2a1..037786d7c1dc 100644
--- a/drivers/gpu/drm/qxl/qxl_ttm.c
+++ b/drivers/gpu/drm/qxl/qxl_ttm.c
@@ -212,7 +212,9 @@ static void qxl_evict_flags(struct ttm_buffer_object *bo,
 
 static int qxl_verify_access(struct ttm_buffer_object *bo, struct file *filp)
 {
-	return 0;
+	struct qxl_bo *qbo = to_qxl_bo(bo);
+
+	return drm_vma_node_verify_access(&qbo->gem_base.vma_node, filp);
 }
 
 static int qxl_ttm_io_mem_reserve(struct ttm_bo_device *bdev,
diff --git a/drivers/gpu/drm/r128/r128_cce.c b/drivers/gpu/drm/r128/r128_cce.c
index d4660cf942a5..c451257f08fb 100644
--- a/drivers/gpu/drm/r128/r128_cce.c
+++ b/drivers/gpu/drm/r128/r128_cce.c
@@ -540,7 +540,7 @@ static int r128_do_init_cce(struct drm_device *dev, drm_r128_init_t *init)
 	dev_priv->ring.end = ((u32 *) dev_priv->cce_ring->handle
 			      + init->ring_size / sizeof(u32));
 	dev_priv->ring.size = init->ring_size;
-	dev_priv->ring.size_l2qw = drm_order(init->ring_size / 8);
+	dev_priv->ring.size_l2qw = order_base_2(init->ring_size / 8);
 
 	dev_priv->ring.tail_mask = (dev_priv->ring.size / sizeof(u32)) - 1;
 
diff --git a/drivers/gpu/drm/r128/r128_drv.c b/drivers/gpu/drm/r128/r128_drv.c
index 472c38fe123f..5bd307cd8da1 100644
--- a/drivers/gpu/drm/r128/r128_drv.c
+++ b/drivers/gpu/drm/r128/r128_drv.c
@@ -48,7 +48,6 @@ static const struct file_operations r128_driver_fops = {
 	.unlocked_ioctl = drm_ioctl,
 	.mmap = drm_mmap,
 	.poll = drm_poll,
-	.fasync = drm_fasync,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl = r128_compat_ioctl,
 #endif
@@ -57,7 +56,7 @@ static const struct file_operations r128_driver_fops = {
 
 static struct drm_driver driver = {
 	.driver_features =
-	    DRIVER_USE_AGP | DRIVER_USE_MTRR | DRIVER_PCI_DMA | DRIVER_SG |
+	    DRIVER_USE_AGP | DRIVER_PCI_DMA | DRIVER_SG |
 	    DRIVER_HAVE_DMA | DRIVER_HAVE_IRQ | DRIVER_IRQ_SHARED,
 	.dev_priv_size = sizeof(drm_r128_buf_priv_t),
 	.load = r128_driver_load,
diff --git a/drivers/gpu/drm/r128/r128_drv.h b/drivers/gpu/drm/r128/r128_drv.h
index 930c71b2fb5e..56eb5e3f5439 100644
--- a/drivers/gpu/drm/r128/r128_drv.h
+++ b/drivers/gpu/drm/r128/r128_drv.h
@@ -131,7 +131,7 @@ typedef struct drm_r128_buf_priv {
 	drm_r128_freelist_t *list_entry;
 } drm_r128_buf_priv_t;
 
-extern struct drm_ioctl_desc r128_ioctls[];
+extern const struct drm_ioctl_desc r128_ioctls[];
 extern int r128_max_ioctl;
 
 				/* r128_cce.c */
diff --git a/drivers/gpu/drm/r128/r128_state.c b/drivers/gpu/drm/r128/r128_state.c
index 19bb7e6f3d9a..01dd9aef9f0e 100644
--- a/drivers/gpu/drm/r128/r128_state.c
+++ b/drivers/gpu/drm/r128/r128_state.c
@@ -1643,7 +1643,7 @@ void r128_driver_lastclose(struct drm_device *dev)
 	r128_do_cleanup_cce(dev);
 }
 
-struct drm_ioctl_desc r128_ioctls[] = {
+const struct drm_ioctl_desc r128_ioctls[] = {
 	DRM_IOCTL_DEF_DRV(R128_INIT, r128_cce_init, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
 	DRM_IOCTL_DEF_DRV(R128_CCE_START, r128_cce_start, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
 	DRM_IOCTL_DEF_DRV(R128_CCE_STOP, r128_cce_stop, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
diff --git a/drivers/gpu/drm/radeon/Makefile b/drivers/gpu/drm/radeon/Makefile
index c3df52c1a60c..306364a1ecda 100644
--- a/drivers/gpu/drm/radeon/Makefile
+++ b/drivers/gpu/drm/radeon/Makefile
@@ -72,14 +72,32 @@ radeon-y += radeon_device.o radeon_asic.o radeon_kms.o \
 	radeon_cs.o radeon_bios.o radeon_benchmark.o r100.o r300.o r420.o \
 	rs400.o rs600.o rs690.o rv515.o r520.o r600.o rv770.o radeon_test.o \
 	r200.o radeon_legacy_tv.o r600_cs.o r600_blit_shaders.o \
-	r600_blit_kms.o radeon_pm.o atombios_dp.o r600_audio.o r600_hdmi.o \
-	evergreen.o evergreen_cs.o evergreen_blit_shaders.o evergreen_blit_kms.o \
+	radeon_pm.o atombios_dp.o r600_audio.o r600_hdmi.o \
+	evergreen.o evergreen_cs.o evergreen_blit_shaders.o \
 	evergreen_hdmi.o radeon_trace_points.o ni.o cayman_blit_shaders.o \
 	atombios_encoders.o radeon_semaphore.o radeon_sa.o atombios_i2c.o si.o \
 	si_blit_shaders.o radeon_prime.o radeon_uvd.o cik.o cik_blit_shaders.o \
 	r600_dpm.o rs780_dpm.o rv6xx_dpm.o rv770_dpm.o rv730_dpm.o rv740_dpm.o \
 	rv770_smc.o cypress_dpm.o btc_dpm.o sumo_dpm.o sumo_smc.o trinity_dpm.o \
-	trinity_smc.o ni_dpm.o si_smc.o si_dpm.o
+	trinity_smc.o ni_dpm.o si_smc.o si_dpm.o kv_smc.o kv_dpm.o ci_smc.o \
+	ci_dpm.o dce6_afmt.o
+
+# add async DMA block
+radeon-y += \
+	r600_dma.o \
+	rv770_dma.o \
+	evergreen_dma.o \
+	ni_dma.o \
+	si_dma.o \
+	cik_sdma.o \
+
+# add UVD block
+radeon-y += \
+	radeon_uvd.o \
+	uvd_v1_0.o \
+	uvd_v2_2.o \
+	uvd_v3_1.o \
+	uvd_v4_2.o
 
 radeon-$(CONFIG_COMPAT) += radeon_ioc32.o
 radeon-$(CONFIG_VGA_SWITCHEROO) += radeon_atpx_handler.o
diff --git a/drivers/gpu/drm/radeon/atombios.h b/drivers/gpu/drm/radeon/atombios.h
index 16b120c3f144..af10f8571d87 100644
--- a/drivers/gpu/drm/radeon/atombios.h
+++ b/drivers/gpu/drm/radeon/atombios.h
@@ -7661,618 +7661,6 @@ typedef struct  _ATOM_POWERPLAY_INFO_V3
   ATOM_POWERMODE_INFO_V3 asPowerPlayInfo[ATOM_MAX_NUMBEROF_POWER_BLOCK];
 }ATOM_POWERPLAY_INFO_V3;
 
-/* New PPlib */
-/**************************************************************************/
-typedef struct _ATOM_PPLIB_THERMALCONTROLLER
-
-{
-    UCHAR ucType;           // one of ATOM_PP_THERMALCONTROLLER_*
-    UCHAR ucI2cLine;        // as interpreted by DAL I2C
-    UCHAR ucI2cAddress;
-    UCHAR ucFanParameters;  // Fan Control Parameters.
-    UCHAR ucFanMinRPM;      // Fan Minimum RPM (hundreds) -- for display purposes only.
-    UCHAR ucFanMaxRPM;      // Fan Maximum RPM (hundreds) -- for display purposes only.
-    UCHAR ucReserved;       // ----
-    UCHAR ucFlags;          // to be defined
-} ATOM_PPLIB_THERMALCONTROLLER;
-
-#define ATOM_PP_FANPARAMETERS_TACHOMETER_PULSES_PER_REVOLUTION_MASK 0x0f
-#define ATOM_PP_FANPARAMETERS_NOFAN                                 0x80    // No fan is connected to this controller.
-
-#define ATOM_PP_THERMALCONTROLLER_NONE      0
-#define ATOM_PP_THERMALCONTROLLER_LM63      1  // Not used by PPLib
-#define ATOM_PP_THERMALCONTROLLER_ADM1032   2  // Not used by PPLib
-#define ATOM_PP_THERMALCONTROLLER_ADM1030   3  // Not used by PPLib
-#define ATOM_PP_THERMALCONTROLLER_MUA6649   4  // Not used by PPLib
-#define ATOM_PP_THERMALCONTROLLER_LM64      5
-#define ATOM_PP_THERMALCONTROLLER_F75375    6  // Not used by PPLib
-#define ATOM_PP_THERMALCONTROLLER_RV6xx     7
-#define ATOM_PP_THERMALCONTROLLER_RV770     8
-#define ATOM_PP_THERMALCONTROLLER_ADT7473   9
-#define ATOM_PP_THERMALCONTROLLER_EXTERNAL_GPIO     11
-#define ATOM_PP_THERMALCONTROLLER_EVERGREEN 12
-#define ATOM_PP_THERMALCONTROLLER_EMC2103   13  /* 0x0D */ // Only fan control will be implemented, do NOT show this in PPGen.
-#define ATOM_PP_THERMALCONTROLLER_SUMO      14  /* 0x0E */ // Sumo type, used internally
-#define ATOM_PP_THERMALCONTROLLER_NISLANDS  15
-#define ATOM_PP_THERMALCONTROLLER_SISLANDS  16
-#define ATOM_PP_THERMALCONTROLLER_LM96163   17
-#define ATOM_PP_THERMALCONTROLLER_CISLANDS  18
-
-// Thermal controller 'combo type' to use an external controller for Fan control and an internal controller for thermal.
-// We probably should reserve the bit 0x80 for this use.
-// To keep the number of these types low we should also use the same code for all ASICs (i.e. do not distinguish RV6xx and RV7xx Internal here).
-// The driver can pick the correct internal controller based on the ASIC.
-
-#define ATOM_PP_THERMALCONTROLLER_ADT7473_WITH_INTERNAL   0x89    // ADT7473 Fan Control + Internal Thermal Controller
-#define ATOM_PP_THERMALCONTROLLER_EMC2103_WITH_INTERNAL   0x8D    // EMC2103 Fan Control + Internal Thermal Controller
-
-typedef struct _ATOM_PPLIB_STATE
-{
-    UCHAR ucNonClockStateIndex;
-    UCHAR ucClockStateIndices[1]; // variable-sized
-} ATOM_PPLIB_STATE;
-
-
-typedef struct _ATOM_PPLIB_FANTABLE
-{
-    UCHAR   ucFanTableFormat;                // Change this if the table format changes or version changes so that the other fields are not the same.
-    UCHAR   ucTHyst;                         // Temperature hysteresis. Integer.
-    USHORT  usTMin;                          // The temperature, in 0.01 centigrades, below which we just run at a minimal PWM.
-    USHORT  usTMed;                          // The middle temperature where we change slopes.
-    USHORT  usTHigh;                         // The high point above TMed for adjusting the second slope.
-    USHORT  usPWMMin;                        // The minimum PWM value in percent (0.01% increments).
-    USHORT  usPWMMed;                        // The PWM value (in percent) at TMed.
-    USHORT  usPWMHigh;                       // The PWM value at THigh.
-} ATOM_PPLIB_FANTABLE;
-
-typedef struct _ATOM_PPLIB_FANTABLE2
-{
-    ATOM_PPLIB_FANTABLE basicTable;
-    USHORT  usTMax;                          // The max temperature
-} ATOM_PPLIB_FANTABLE2;
-
-typedef struct _ATOM_PPLIB_EXTENDEDHEADER
-{
-    USHORT  usSize;
-    ULONG   ulMaxEngineClock;   // For Overdrive.
-    ULONG   ulMaxMemoryClock;   // For Overdrive.
-    // Add extra system parameters here, always adjust size to include all fields.
-    USHORT  usVCETableOffset; //points to ATOM_PPLIB_VCE_Table
-    USHORT  usUVDTableOffset;   //points to ATOM_PPLIB_UVD_Table
-    USHORT  usSAMUTableOffset;  //points to ATOM_PPLIB_SAMU_Table
-    USHORT  usPPMTableOffset;   //points to ATOM_PPLIB_PPM_Table
-} ATOM_PPLIB_EXTENDEDHEADER;
-
-//// ATOM_PPLIB_POWERPLAYTABLE::ulPlatformCaps
-#define ATOM_PP_PLATFORM_CAP_BACKBIAS 1
-#define ATOM_PP_PLATFORM_CAP_POWERPLAY 2
-#define ATOM_PP_PLATFORM_CAP_SBIOSPOWERSOURCE 4
-#define ATOM_PP_PLATFORM_CAP_ASPM_L0s 8
-#define ATOM_PP_PLATFORM_CAP_ASPM_L1 16
-#define ATOM_PP_PLATFORM_CAP_HARDWAREDC 32
-#define ATOM_PP_PLATFORM_CAP_GEMINIPRIMARY 64
-#define ATOM_PP_PLATFORM_CAP_STEPVDDC 128
-#define ATOM_PP_PLATFORM_CAP_VOLTAGECONTROL 256
-#define ATOM_PP_PLATFORM_CAP_SIDEPORTCONTROL 512
-#define ATOM_PP_PLATFORM_CAP_TURNOFFPLL_ASPML1 1024
-#define ATOM_PP_PLATFORM_CAP_HTLINKCONTROL 2048
-#define ATOM_PP_PLATFORM_CAP_MVDDCONTROL 4096
-#define ATOM_PP_PLATFORM_CAP_GOTO_BOOT_ON_ALERT 0x2000              // Go to boot state on alerts, e.g. on an AC->DC transition.
-#define ATOM_PP_PLATFORM_CAP_DONT_WAIT_FOR_VBLANK_ON_ALERT 0x4000   // Do NOT wait for VBLANK during an alert (e.g. AC->DC transition).
-#define ATOM_PP_PLATFORM_CAP_VDDCI_CONTROL 0x8000                   // Does the driver control VDDCI independently from VDDC.
-#define ATOM_PP_PLATFORM_CAP_REGULATOR_HOT 0x00010000               // Enable the 'regulator hot' feature.
-#define ATOM_PP_PLATFORM_CAP_BACO          0x00020000               // Does the driver supports BACO state.
-#define ATOM_PP_PLATFORM_CAP_NEW_CAC_VOLTAGE   0x00040000           // Does the driver supports new CAC voltage table.
-#define ATOM_PP_PLATFORM_CAP_REVERT_GPIO5_POLARITY   0x00080000     // Does the driver supports revert GPIO5 polarity.
-#define ATOM_PP_PLATFORM_CAP_OUTPUT_THERMAL2GPIO17   0x00100000     // Does the driver supports thermal2GPIO17.
-#define ATOM_PP_PLATFORM_CAP_VRHOT_GPIO_CONFIGURABLE   0x00200000   // Does the driver supports VR HOT GPIO Configurable.
-
-typedef struct _ATOM_PPLIB_POWERPLAYTABLE
-{
-      ATOM_COMMON_TABLE_HEADER sHeader;
-
-      UCHAR ucDataRevision;
-
-      UCHAR ucNumStates;
-      UCHAR ucStateEntrySize;
-      UCHAR ucClockInfoSize;
-      UCHAR ucNonClockSize;
-
-      // offset from start of this table to array of ucNumStates ATOM_PPLIB_STATE structures
-      USHORT usStateArrayOffset;
-
-      // offset from start of this table to array of ASIC-specific structures,
-      // currently ATOM_PPLIB_CLOCK_INFO.
-      USHORT usClockInfoArrayOffset;
-
-      // offset from start of this table to array of ATOM_PPLIB_NONCLOCK_INFO
-      USHORT usNonClockInfoArrayOffset;
-
-      USHORT usBackbiasTime;    // in microseconds
-      USHORT usVoltageTime;     // in microseconds
-      USHORT usTableSize;       //the size of this structure, or the extended structure
-
-      ULONG ulPlatformCaps;            // See ATOM_PPLIB_CAPS_*
-
-      ATOM_PPLIB_THERMALCONTROLLER    sThermalController;
-
-      USHORT usBootClockInfoOffset;
-      USHORT usBootNonClockInfoOffset;
-
-} ATOM_PPLIB_POWERPLAYTABLE;
-
-typedef struct _ATOM_PPLIB_POWERPLAYTABLE2
-{
-    ATOM_PPLIB_POWERPLAYTABLE basicTable;
-    UCHAR   ucNumCustomThermalPolicy;
-    USHORT  usCustomThermalPolicyArrayOffset;
-}ATOM_PPLIB_POWERPLAYTABLE2, *LPATOM_PPLIB_POWERPLAYTABLE2;
-
-typedef struct _ATOM_PPLIB_POWERPLAYTABLE3
-{
-    ATOM_PPLIB_POWERPLAYTABLE2 basicTable2;
-    USHORT                     usFormatID;                      // To be used ONLY by PPGen.
-    USHORT                     usFanTableOffset;
-    USHORT                     usExtendendedHeaderOffset;
-} ATOM_PPLIB_POWERPLAYTABLE3, *LPATOM_PPLIB_POWERPLAYTABLE3;
-
-typedef struct _ATOM_PPLIB_POWERPLAYTABLE4
-{
-    ATOM_PPLIB_POWERPLAYTABLE3 basicTable3;
-    ULONG                      ulGoldenPPID;                    // PPGen use only     
-    ULONG                      ulGoldenRevision;                // PPGen use only
-    USHORT                     usVddcDependencyOnSCLKOffset;
-    USHORT                     usVddciDependencyOnMCLKOffset;
-    USHORT                     usVddcDependencyOnMCLKOffset;
-    USHORT                     usMaxClockVoltageOnDCOffset;
-    USHORT                     usVddcPhaseShedLimitsTableOffset;    // Points to ATOM_PPLIB_PhaseSheddingLimits_Table
-    USHORT                     usMvddDependencyOnMCLKOffset;  
-} ATOM_PPLIB_POWERPLAYTABLE4, *LPATOM_PPLIB_POWERPLAYTABLE4;
-
-typedef struct _ATOM_PPLIB_POWERPLAYTABLE5
-{
-    ATOM_PPLIB_POWERPLAYTABLE4 basicTable4;
-    ULONG                      ulTDPLimit;
-    ULONG                      ulNearTDPLimit;
-    ULONG                      ulSQRampingThreshold;
-    USHORT                     usCACLeakageTableOffset;         // Points to ATOM_PPLIB_CAC_Leakage_Table
-    ULONG                      ulCACLeakage;                    // The iLeakage for driver calculated CAC leakage table
-    USHORT                     usTDPODLimit;
-    USHORT                     usLoadLineSlope;                 // in milliOhms * 100
-} ATOM_PPLIB_POWERPLAYTABLE5, *LPATOM_PPLIB_POWERPLAYTABLE5;
-
-//// ATOM_PPLIB_NONCLOCK_INFO::usClassification
-#define ATOM_PPLIB_CLASSIFICATION_UI_MASK          0x0007
-#define ATOM_PPLIB_CLASSIFICATION_UI_SHIFT         0
-#define ATOM_PPLIB_CLASSIFICATION_UI_NONE          0
-#define ATOM_PPLIB_CLASSIFICATION_UI_BATTERY       1
-#define ATOM_PPLIB_CLASSIFICATION_UI_BALANCED      3
-#define ATOM_PPLIB_CLASSIFICATION_UI_PERFORMANCE   5
-// 2, 4, 6, 7 are reserved
-
-#define ATOM_PPLIB_CLASSIFICATION_BOOT                   0x0008
-#define ATOM_PPLIB_CLASSIFICATION_THERMAL                0x0010
-#define ATOM_PPLIB_CLASSIFICATION_LIMITEDPOWERSOURCE     0x0020
-#define ATOM_PPLIB_CLASSIFICATION_REST                   0x0040
-#define ATOM_PPLIB_CLASSIFICATION_FORCED                 0x0080
-#define ATOM_PPLIB_CLASSIFICATION_3DPERFORMANCE          0x0100
-#define ATOM_PPLIB_CLASSIFICATION_OVERDRIVETEMPLATE      0x0200
-#define ATOM_PPLIB_CLASSIFICATION_UVDSTATE               0x0400
-#define ATOM_PPLIB_CLASSIFICATION_3DLOW                  0x0800
-#define ATOM_PPLIB_CLASSIFICATION_ACPI                   0x1000
-#define ATOM_PPLIB_CLASSIFICATION_HD2STATE               0x2000
-#define ATOM_PPLIB_CLASSIFICATION_HDSTATE                0x4000
-#define ATOM_PPLIB_CLASSIFICATION_SDSTATE                0x8000
-
-//// ATOM_PPLIB_NONCLOCK_INFO::usClassification2
-#define ATOM_PPLIB_CLASSIFICATION2_LIMITEDPOWERSOURCE_2     0x0001
-#define ATOM_PPLIB_CLASSIFICATION2_ULV                      0x0002
-#define ATOM_PPLIB_CLASSIFICATION2_MVC                      0x0004   //Multi-View Codec (BD-3D)
-
-//// ATOM_PPLIB_NONCLOCK_INFO::ulCapsAndSettings
-#define ATOM_PPLIB_SINGLE_DISPLAY_ONLY           0x00000001
-#define ATOM_PPLIB_SUPPORTS_VIDEO_PLAYBACK         0x00000002
-
-// 0 is 2.5Gb/s, 1 is 5Gb/s
-#define ATOM_PPLIB_PCIE_LINK_SPEED_MASK            0x00000004
-#define ATOM_PPLIB_PCIE_LINK_SPEED_SHIFT           2
-
-// lanes - 1: 1, 2, 4, 8, 12, 16 permitted by PCIE spec
-#define ATOM_PPLIB_PCIE_LINK_WIDTH_MASK            0x000000F8
-#define ATOM_PPLIB_PCIE_LINK_WIDTH_SHIFT           3
-
-// lookup into reduced refresh-rate table
-#define ATOM_PPLIB_LIMITED_REFRESHRATE_VALUE_MASK  0x00000F00
-#define ATOM_PPLIB_LIMITED_REFRESHRATE_VALUE_SHIFT 8
-
-#define ATOM_PPLIB_LIMITED_REFRESHRATE_UNLIMITED    0
-#define ATOM_PPLIB_LIMITED_REFRESHRATE_50HZ         1
-// 2-15 TBD as needed.
-
-#define ATOM_PPLIB_SOFTWARE_DISABLE_LOADBALANCING        0x00001000
-#define ATOM_PPLIB_SOFTWARE_ENABLE_SLEEP_FOR_TIMESTAMPS  0x00002000
-
-#define ATOM_PPLIB_DISALLOW_ON_DC                       0x00004000
-
-#define ATOM_PPLIB_ENABLE_VARIBRIGHT                     0x00008000
-
-//memory related flags
-#define ATOM_PPLIB_SWSTATE_MEMORY_DLL_OFF               0x000010000
-
-//M3 Arb    //2bits, current 3 sets of parameters in total
-#define ATOM_PPLIB_M3ARB_MASK                       0x00060000
-#define ATOM_PPLIB_M3ARB_SHIFT                      17
-
-#define ATOM_PPLIB_ENABLE_DRR                       0x00080000
-
-// remaining 16 bits are reserved
-typedef struct _ATOM_PPLIB_THERMAL_STATE
-{
-    UCHAR   ucMinTemperature;
-    UCHAR   ucMaxTemperature;
-    UCHAR   ucThermalAction;
-}ATOM_PPLIB_THERMAL_STATE, *LPATOM_PPLIB_THERMAL_STATE;
-
-// Contained in an array starting at the offset
-// in ATOM_PPLIB_POWERPLAYTABLE::usNonClockInfoArrayOffset.
-// referenced from ATOM_PPLIB_STATE_INFO::ucNonClockStateIndex
-#define ATOM_PPLIB_NONCLOCKINFO_VER1      12
-#define ATOM_PPLIB_NONCLOCKINFO_VER2      24
-typedef struct _ATOM_PPLIB_NONCLOCK_INFO
-{
-      USHORT usClassification;
-      UCHAR  ucMinTemperature;
-      UCHAR  ucMaxTemperature;
-      ULONG  ulCapsAndSettings;
-      UCHAR  ucRequiredPower;
-      USHORT usClassification2;
-      ULONG  ulVCLK;
-      ULONG  ulDCLK;
-      UCHAR  ucUnused[5];
-} ATOM_PPLIB_NONCLOCK_INFO;
-
-// Contained in an array starting at the offset
-// in ATOM_PPLIB_POWERPLAYTABLE::usClockInfoArrayOffset.
-// referenced from ATOM_PPLIB_STATE::ucClockStateIndices
-typedef struct _ATOM_PPLIB_R600_CLOCK_INFO
-{
-      USHORT usEngineClockLow;
-      UCHAR ucEngineClockHigh;
-
-      USHORT usMemoryClockLow;
-      UCHAR ucMemoryClockHigh;
-
-      USHORT usVDDC;
-      USHORT usUnused1;
-      USHORT usUnused2;
-
-      ULONG ulFlags; // ATOM_PPLIB_R600_FLAGS_*
-
-} ATOM_PPLIB_R600_CLOCK_INFO;
-
-// ulFlags in ATOM_PPLIB_R600_CLOCK_INFO
-#define ATOM_PPLIB_R600_FLAGS_PCIEGEN2          1
-#define ATOM_PPLIB_R600_FLAGS_UVDSAFE           2
-#define ATOM_PPLIB_R600_FLAGS_BACKBIASENABLE    4
-#define ATOM_PPLIB_R600_FLAGS_MEMORY_ODT_OFF    8
-#define ATOM_PPLIB_R600_FLAGS_MEMORY_DLL_OFF   16
-#define ATOM_PPLIB_R600_FLAGS_LOWPOWER         32   // On the RV770 use 'low power' setting (sequencer S0).
-
-typedef struct _ATOM_PPLIB_EVERGREEN_CLOCK_INFO
-{
-      USHORT usEngineClockLow;
-      UCHAR  ucEngineClockHigh;
-
-      USHORT usMemoryClockLow;
-      UCHAR  ucMemoryClockHigh;
-
-      USHORT usVDDC;
-      USHORT usVDDCI;
-      USHORT usUnused;
-
-      ULONG ulFlags; // ATOM_PPLIB_R600_FLAGS_*
-
-} ATOM_PPLIB_EVERGREEN_CLOCK_INFO;
-
-typedef struct _ATOM_PPLIB_SI_CLOCK_INFO
-{
-      USHORT usEngineClockLow;
-      UCHAR  ucEngineClockHigh;
-
-      USHORT usMemoryClockLow;
-      UCHAR  ucMemoryClockHigh;
-
-      USHORT usVDDC;
-      USHORT usVDDCI;
-      UCHAR  ucPCIEGen;
-      UCHAR  ucUnused1;
-
-      ULONG ulFlags; // ATOM_PPLIB_SI_FLAGS_*, no flag is necessary for now
-
-} ATOM_PPLIB_SI_CLOCK_INFO;
-
-typedef struct _ATOM_PPLIB_CI_CLOCK_INFO
-{
-      USHORT usEngineClockLow;
-      UCHAR  ucEngineClockHigh;
-
-      USHORT usMemoryClockLow;
-      UCHAR  ucMemoryClockHigh;
-      
-      UCHAR  ucPCIEGen;
-      USHORT usPCIELane;
-} ATOM_PPLIB_CI_CLOCK_INFO;
-
-typedef struct _ATOM_PPLIB_RS780_CLOCK_INFO
-
-{
-      USHORT usLowEngineClockLow;         // Low Engine clock in MHz (the same way as on the R600).
-      UCHAR  ucLowEngineClockHigh;
-      USHORT usHighEngineClockLow;        // High Engine clock in MHz.
-      UCHAR  ucHighEngineClockHigh;
-      USHORT usMemoryClockLow;            // For now one of the ATOM_PPLIB_RS780_SPMCLK_XXXX constants.
-      UCHAR  ucMemoryClockHigh;           // Currentyl unused.
-      UCHAR  ucPadding;                   // For proper alignment and size.
-      USHORT usVDDC;                      // For the 780, use: None, Low, High, Variable
-      UCHAR  ucMaxHTLinkWidth;            // From SBIOS - {2, 4, 8, 16}
-      UCHAR  ucMinHTLinkWidth;            // From SBIOS - {2, 4, 8, 16}. Effective only if CDLW enabled. Minimum down stream width could be bigger as display BW requriement.
-      USHORT usHTLinkFreq;                // See definition ATOM_PPLIB_RS780_HTLINKFREQ_xxx or in MHz(>=200).
-      ULONG  ulFlags; 
-} ATOM_PPLIB_RS780_CLOCK_INFO;
-
-#define ATOM_PPLIB_RS780_VOLTAGE_NONE       0 
-#define ATOM_PPLIB_RS780_VOLTAGE_LOW        1 
-#define ATOM_PPLIB_RS780_VOLTAGE_HIGH       2 
-#define ATOM_PPLIB_RS780_VOLTAGE_VARIABLE   3 
-
-#define ATOM_PPLIB_RS780_SPMCLK_NONE        0   // We cannot change the side port memory clock, leave it as it is.
-#define ATOM_PPLIB_RS780_SPMCLK_LOW         1
-#define ATOM_PPLIB_RS780_SPMCLK_HIGH        2
-
-#define ATOM_PPLIB_RS780_HTLINKFREQ_NONE       0 
-#define ATOM_PPLIB_RS780_HTLINKFREQ_LOW        1 
-#define ATOM_PPLIB_RS780_HTLINKFREQ_HIGH       2 
-
-typedef struct _ATOM_PPLIB_SUMO_CLOCK_INFO{
-      USHORT usEngineClockLow;  //clockfrequency & 0xFFFF. The unit is in 10khz
-      UCHAR  ucEngineClockHigh; //clockfrequency >> 16. 
-      UCHAR  vddcIndex;         //2-bit vddc index;
-      USHORT tdpLimit;
-      //please initalize to 0
-      USHORT rsv1;
-      //please initialize to 0s
-      ULONG rsv2[2];
-}ATOM_PPLIB_SUMO_CLOCK_INFO;
-
-
-
-typedef struct _ATOM_PPLIB_STATE_V2
-{
-      //number of valid dpm levels in this state; Driver uses it to calculate the whole 
-      //size of the state: sizeof(ATOM_PPLIB_STATE_V2) + (ucNumDPMLevels - 1) * sizeof(UCHAR)
-      UCHAR ucNumDPMLevels;
-      
-      //a index to the array of nonClockInfos
-      UCHAR nonClockInfoIndex;
-      /**
-      * Driver will read the first ucNumDPMLevels in this array
-      */
-      UCHAR clockInfoIndex[1];
-} ATOM_PPLIB_STATE_V2;
-
-typedef struct _StateArray{
-    //how many states we have 
-    UCHAR ucNumEntries;
-    
-    ATOM_PPLIB_STATE_V2 states[1];
-}StateArray;
-
-
-typedef struct _ClockInfoArray{
-    //how many clock levels we have
-    UCHAR ucNumEntries;
-    
-    //sizeof(ATOM_PPLIB_CLOCK_INFO)
-    UCHAR ucEntrySize;
-    
-    UCHAR clockInfo[1];
-}ClockInfoArray;
-
-typedef struct _NonClockInfoArray{
-
-    //how many non-clock levels we have. normally should be same as number of states
-    UCHAR ucNumEntries;
-    //sizeof(ATOM_PPLIB_NONCLOCK_INFO)
-    UCHAR ucEntrySize;
-    
-    ATOM_PPLIB_NONCLOCK_INFO nonClockInfo[1];
-}NonClockInfoArray;
-
-typedef struct _ATOM_PPLIB_Clock_Voltage_Dependency_Record
-{
-    USHORT usClockLow;
-    UCHAR  ucClockHigh;
-    USHORT usVoltage;
-}ATOM_PPLIB_Clock_Voltage_Dependency_Record;
-
-typedef struct _ATOM_PPLIB_Clock_Voltage_Dependency_Table
-{
-    UCHAR ucNumEntries;                                                // Number of entries.
-    ATOM_PPLIB_Clock_Voltage_Dependency_Record entries[1];             // Dynamically allocate entries.
-}ATOM_PPLIB_Clock_Voltage_Dependency_Table;
-
-typedef struct _ATOM_PPLIB_Clock_Voltage_Limit_Record
-{
-    USHORT usSclkLow;
-    UCHAR  ucSclkHigh;
-    USHORT usMclkLow;
-    UCHAR  ucMclkHigh;
-    USHORT usVddc;
-    USHORT usVddci;
-}ATOM_PPLIB_Clock_Voltage_Limit_Record;
-
-typedef struct _ATOM_PPLIB_Clock_Voltage_Limit_Table
-{
-    UCHAR ucNumEntries;                                                // Number of entries.
-    ATOM_PPLIB_Clock_Voltage_Limit_Record entries[1];                  // Dynamically allocate entries.
-}ATOM_PPLIB_Clock_Voltage_Limit_Table;
-
-typedef struct _ATOM_PPLIB_CAC_Leakage_Record
-{
-    USHORT usVddc;  // We use this field for the "fake" standardized VDDC for power calculations; For CI and newer, we use this as the real VDDC value.
-    ULONG  ulLeakageValue;  // For CI and newer we use this as the "fake" standar VDDC value.
-}ATOM_PPLIB_CAC_Leakage_Record;
-
-typedef struct _ATOM_PPLIB_CAC_Leakage_Table
-{
-    UCHAR ucNumEntries;                                                 // Number of entries.
-    ATOM_PPLIB_CAC_Leakage_Record entries[1];                           // Dynamically allocate entries.
-}ATOM_PPLIB_CAC_Leakage_Table;
-
-typedef struct _ATOM_PPLIB_PhaseSheddingLimits_Record
-{
-    USHORT usVoltage;
-    USHORT usSclkLow;
-    UCHAR  ucSclkHigh;
-    USHORT usMclkLow;
-    UCHAR  ucMclkHigh;
-}ATOM_PPLIB_PhaseSheddingLimits_Record;
-
-typedef struct _ATOM_PPLIB_PhaseSheddingLimits_Table
-{
-    UCHAR ucNumEntries;                                                 // Number of entries.
-    ATOM_PPLIB_PhaseSheddingLimits_Record entries[1];                   // Dynamically allocate entries.
-}ATOM_PPLIB_PhaseSheddingLimits_Table;
-
-typedef struct _VCEClockInfo{
-    USHORT usEVClkLow;
-    UCHAR  ucEVClkHigh;
-    USHORT usECClkLow;
-    UCHAR  ucECClkHigh;
-}VCEClockInfo;
-
-typedef struct _VCEClockInfoArray{
-    UCHAR ucNumEntries;
-    VCEClockInfo entries[1];
-}VCEClockInfoArray;
-
-typedef struct _ATOM_PPLIB_VCE_Clock_Voltage_Limit_Record
-{
-    USHORT usVoltage;
-    UCHAR  ucVCEClockInfoIndex;
-}ATOM_PPLIB_VCE_Clock_Voltage_Limit_Record;
-
-typedef struct _ATOM_PPLIB_VCE_Clock_Voltage_Limit_Table
-{
-    UCHAR numEntries;
-    ATOM_PPLIB_VCE_Clock_Voltage_Limit_Record entries[1];
-}ATOM_PPLIB_VCE_Clock_Voltage_Limit_Table;
-
-typedef struct _ATOM_PPLIB_VCE_State_Record
-{
-    UCHAR  ucVCEClockInfoIndex;
-    UCHAR  ucClockInfoIndex; //highest 2 bits indicates memory p-states, lower 6bits indicates index to ClockInfoArrary
-}ATOM_PPLIB_VCE_State_Record;
-
-typedef struct _ATOM_PPLIB_VCE_State_Table
-{
-    UCHAR numEntries;
-    ATOM_PPLIB_VCE_State_Record entries[1];
-}ATOM_PPLIB_VCE_State_Table;
-
-
-typedef struct _ATOM_PPLIB_VCE_Table
-{
-      UCHAR revid;
-//    VCEClockInfoArray array;
-//    ATOM_PPLIB_VCE_Clock_Voltage_Limit_Table limits;
-//    ATOM_PPLIB_VCE_State_Table states;
-}ATOM_PPLIB_VCE_Table;
-
-
-typedef struct _UVDClockInfo{
-    USHORT usVClkLow;
-    UCHAR  ucVClkHigh;
-    USHORT usDClkLow;
-    UCHAR  ucDClkHigh;
-}UVDClockInfo;
-
-typedef struct _UVDClockInfoArray{
-    UCHAR ucNumEntries;
-    UVDClockInfo entries[1];
-}UVDClockInfoArray;
-
-typedef struct _ATOM_PPLIB_UVD_Clock_Voltage_Limit_Record
-{
-    USHORT usVoltage;
-    UCHAR  ucUVDClockInfoIndex;
-}ATOM_PPLIB_UVD_Clock_Voltage_Limit_Record;
-
-typedef struct _ATOM_PPLIB_UVD_Clock_Voltage_Limit_Table
-{
-    UCHAR numEntries;
-    ATOM_PPLIB_UVD_Clock_Voltage_Limit_Record entries[1];
-}ATOM_PPLIB_UVD_Clock_Voltage_Limit_Table;
-
-typedef struct _ATOM_PPLIB_UVD_State_Record
-{
-    UCHAR  ucUVDClockInfoIndex;
-    UCHAR  ucClockInfoIndex; //highest 2 bits indicates memory p-states, lower 6bits indicates index to ClockInfoArrary
-}ATOM_PPLIB_UVD_State_Record;
-
-typedef struct _ATOM_PPLIB_UVD_State_Table
-{
-    UCHAR numEntries;
-    ATOM_PPLIB_UVD_State_Record entries[1];
-}ATOM_PPLIB_UVD_State_Table;
-
-
-typedef struct _ATOM_PPLIB_UVD_Table
-{
-      UCHAR revid;
-//    UVDClockInfoArray array;
-//    ATOM_PPLIB_UVD_Clock_Voltage_Limit_Table limits;
-//    ATOM_PPLIB_UVD_State_Table states;
-}ATOM_PPLIB_UVD_Table;
-
-
-typedef struct _ATOM_PPLIB_SAMClk_Voltage_Limit_Record
-{
-      USHORT usVoltage;
-      USHORT usSAMClockLow;
-      UCHAR  ucSAMClockHigh;
-}ATOM_PPLIB_SAMClk_Voltage_Limit_Record;
-
-typedef struct _ATOM_PPLIB_SAMClk_Voltage_Limit_Table{
-    UCHAR numEntries;
-    ATOM_PPLIB_SAMClk_Voltage_Limit_Record entries[1];
-}ATOM_PPLIB_SAMClk_Voltage_Limit_Table;
-
-typedef struct _ATOM_PPLIB_SAMU_Table
-{
-      UCHAR revid;
-      ATOM_PPLIB_SAMClk_Voltage_Limit_Table limits;
-}ATOM_PPLIB_SAMU_Table;
-
-#define ATOM_PPM_A_A    1
-#define ATOM_PPM_A_I    2
-typedef struct _ATOM_PPLIB_PPM_Table
-{
-      UCHAR  ucRevId;
-      UCHAR  ucPpmDesign;          //A+I or A+A
-      USHORT usCpuCoreNumber;
-      ULONG  ulPlatformTDP;
-      ULONG  ulSmallACPlatformTDP;
-      ULONG  ulPlatformTDC;
-      ULONG  ulSmallACPlatformTDC;
-      ULONG  ulApuTDP;
-      ULONG  ulDGpuTDP;  
-      ULONG  ulDGpuUlvPower;
-      ULONG  ulTjmax;
-} ATOM_PPLIB_PPM_Table;
-
-/**************************************************************************/
-
 
 // Following definitions are for compatibility issue in different SW components. 
 #define ATOM_MASTER_DATA_TABLE_REVISION   0x01
@@ -8485,3 +7873,6 @@ typedef struct {
 
 
 #endif /* _ATOMBIOS_H */
+
+#include "pptable.h"
+
diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c
index b9d3b43f19c0..bf87f6d435f8 100644
--- a/drivers/gpu/drm/radeon/atombios_crtc.c
+++ b/drivers/gpu/drm/radeon/atombios_crtc.c
@@ -1910,6 +1910,12 @@ static void atombios_crtc_disable(struct drm_crtc *crtc)
 	int i;
 
 	atombios_crtc_dpms(crtc, DRM_MODE_DPMS_OFF);
+	/* disable the GRPH */
+	if (ASIC_IS_DCE4(rdev))
+		WREG32(EVERGREEN_GRPH_ENABLE + radeon_crtc->crtc_offset, 0);
+	else if (ASIC_IS_AVIVO(rdev))
+		WREG32(AVIVO_D1GRPH_ENABLE + radeon_crtc->crtc_offset, 0);
+
 	if (ASIC_IS_DCE6(rdev))
 		atombios_powergate_crtc(crtc, ATOM_ENABLE);
 
diff --git a/drivers/gpu/drm/radeon/atombios_dp.c b/drivers/gpu/drm/radeon/atombios_dp.c
index 32501f6ec991..00885417ffff 100644
--- a/drivers/gpu/drm/radeon/atombios_dp.c
+++ b/drivers/gpu/drm/radeon/atombios_dp.c
@@ -50,7 +50,7 @@ static char *pre_emph_names[] = {
  * or from atom. Note that atom operates on
  * dw units.
  */
-static void radeon_copy_swap(u8 *dst, u8 *src, u8 num_bytes, bool to_le)
+void radeon_atom_copy_swap(u8 *dst, u8 *src, u8 num_bytes, bool to_le)
 {
 #ifdef __BIG_ENDIAN
 	u8 src_tmp[20], dst_tmp[20]; /* used for byteswapping */
@@ -100,7 +100,7 @@ static int radeon_process_aux_ch(struct radeon_i2c_chan *chan,
 
 	base = (unsigned char *)(rdev->mode_info.atom_context->scratch + 1);
 
-	radeon_copy_swap(base, send, send_bytes, true);
+	radeon_atom_copy_swap(base, send, send_bytes, true);
 
 	args.v1.lpAuxRequest = cpu_to_le16((u16)(0 + 4));
 	args.v1.lpDataOut = cpu_to_le16((u16)(16 + 4));
@@ -137,7 +137,7 @@ static int radeon_process_aux_ch(struct radeon_i2c_chan *chan,
 		recv_bytes = recv_size;
 
 	if (recv && recv_size)
-		radeon_copy_swap(recv, base + 16, recv_bytes, false);
+		radeon_atom_copy_swap(recv, base + 16, recv_bytes, false);
 
 	return recv_bytes;
 }
@@ -585,7 +585,7 @@ static bool radeon_dp_get_link_status(struct radeon_connector *radeon_connector,
 		return false;
 	}
 
-	DRM_DEBUG_KMS("link status %*ph\n", 6, link_status);
+	DRM_DEBUG_KMS("link status %6ph\n", link_status);
 	return true;
 }
 
diff --git a/drivers/gpu/drm/radeon/atombios_encoders.c b/drivers/gpu/drm/radeon/atombios_encoders.c
index 092275d53d4a..32923d2f6002 100644
--- a/drivers/gpu/drm/radeon/atombios_encoders.c
+++ b/drivers/gpu/drm/radeon/atombios_encoders.c
@@ -682,8 +682,6 @@ atombios_digital_setup(struct drm_encoder *encoder, int action)
 int
 atombios_get_encoder_mode(struct drm_encoder *encoder)
 {
-	struct drm_device *dev = encoder->dev;
-	struct radeon_device *rdev = dev->dev_private;
 	struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
 	struct drm_connector *connector;
 	struct radeon_connector *radeon_connector;
@@ -709,9 +707,9 @@ atombios_get_encoder_mode(struct drm_encoder *encoder)
 	switch (connector->connector_type) {
 	case DRM_MODE_CONNECTOR_DVII:
 	case DRM_MODE_CONNECTOR_HDMIB: /* HDMI-B is basically DL-DVI; analog works fine */
-		if (drm_detect_hdmi_monitor(radeon_connector->edid) &&
-		    radeon_audio &&
-		    !ASIC_IS_DCE6(rdev)) /* remove once we support DCE6 */
+		if ((radeon_connector->audio == RADEON_AUDIO_ENABLE) ||
+		    (drm_detect_hdmi_monitor(radeon_connector->edid) &&
+		     (radeon_connector->audio == RADEON_AUDIO_AUTO)))
 			return ATOM_ENCODER_MODE_HDMI;
 		else if (radeon_connector->use_digital)
 			return ATOM_ENCODER_MODE_DVI;
@@ -721,9 +719,9 @@ atombios_get_encoder_mode(struct drm_encoder *encoder)
 	case DRM_MODE_CONNECTOR_DVID:
 	case DRM_MODE_CONNECTOR_HDMIA:
 	default:
-		if (drm_detect_hdmi_monitor(radeon_connector->edid) &&
-		    radeon_audio &&
-		    !ASIC_IS_DCE6(rdev)) /* remove once we support DCE6 */
+		if ((radeon_connector->audio == RADEON_AUDIO_ENABLE) ||
+		    (drm_detect_hdmi_monitor(radeon_connector->edid) &&
+		     (radeon_connector->audio == RADEON_AUDIO_AUTO)))
 			return ATOM_ENCODER_MODE_HDMI;
 		else
 			return ATOM_ENCODER_MODE_DVI;
@@ -736,9 +734,9 @@ atombios_get_encoder_mode(struct drm_encoder *encoder)
 		if ((dig_connector->dp_sink_type == CONNECTOR_OBJECT_ID_DISPLAYPORT) ||
 		    (dig_connector->dp_sink_type == CONNECTOR_OBJECT_ID_eDP))
 			return ATOM_ENCODER_MODE_DP;
-		else if (drm_detect_hdmi_monitor(radeon_connector->edid) &&
-			 radeon_audio &&
-			 !ASIC_IS_DCE6(rdev)) /* remove once we support DCE6 */
+		else if ((radeon_connector->audio == RADEON_AUDIO_ENABLE) ||
+			 (drm_detect_hdmi_monitor(radeon_connector->edid) &&
+			  (radeon_connector->audio == RADEON_AUDIO_AUTO)))
 			return ATOM_ENCODER_MODE_HDMI;
 		else
 			return ATOM_ENCODER_MODE_DVI;
@@ -1652,8 +1650,12 @@ radeon_atom_encoder_dpms_dig(struct drm_encoder *encoder, int mode)
 			atombios_dig_encoder_setup(encoder, ATOM_ENABLE, 0);
 			atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_SETUP, 0, 0);
 			atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_ENABLE, 0, 0);
-			/* some early dce3.2 boards have a bug in their transmitter control table */
-			if ((rdev->family != CHIP_RV710) && (rdev->family != CHIP_RV730))
+			/* some dce3.x boards have a bug in their transmitter control table.
+			 * ACTION_ENABLE_OUTPUT can probably be dropped since ACTION_ENABLE
+			 * does the same thing and more.
+			 */
+			if ((rdev->family != CHIP_RV710) && (rdev->family != CHIP_RV730) &&
+			    (rdev->family != CHIP_RS880))
 				atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_ENABLE_OUTPUT, 0, 0);
 		}
 		if (ENCODER_MODE_IS_DP(atombios_get_encoder_mode(encoder)) && connector) {
diff --git a/drivers/gpu/drm/radeon/atombios_i2c.c b/drivers/gpu/drm/radeon/atombios_i2c.c
index 082338df708a..deaf98cdca3a 100644
--- a/drivers/gpu/drm/radeon/atombios_i2c.c
+++ b/drivers/gpu/drm/radeon/atombios_i2c.c
@@ -27,10 +27,12 @@
 #include "radeon.h"
 #include "atom.h"
 
+extern void radeon_atom_copy_swap(u8 *dst, u8 *src, u8 num_bytes, bool to_le);
+
 #define TARGET_HW_I2C_CLOCK 50
 
 /* these are a limitation of ProcessI2cChannelTransaction not the hw */
-#define ATOM_MAX_HW_I2C_WRITE 2
+#define ATOM_MAX_HW_I2C_WRITE 3
 #define ATOM_MAX_HW_I2C_READ  255
 
 static int radeon_process_i2c_ch(struct radeon_i2c_chan *chan,
@@ -50,20 +52,24 @@ static int radeon_process_i2c_ch(struct radeon_i2c_chan *chan,
 
 	if (flags & HW_I2C_WRITE) {
 		if (num > ATOM_MAX_HW_I2C_WRITE) {
-			DRM_ERROR("hw i2c: tried to write too many bytes (%d vs 2)\n", num);
+			DRM_ERROR("hw i2c: tried to write too many bytes (%d vs 3)\n", num);
 			return -EINVAL;
 		}
-		memcpy(&out, buf, num);
+		args.ucRegIndex = buf[0];
+		if (num > 1)
+			memcpy(&out, &buf[1], num - 1);
 		args.lpI2CDataOut = cpu_to_le16(out);
 	} else {
 		if (num > ATOM_MAX_HW_I2C_READ) {
 			DRM_ERROR("hw i2c: tried to read too many bytes (%d vs 255)\n", num);
 			return -EINVAL;
 		}
+		args.ucRegIndex = 0;
+		args.lpI2CDataOut = 0;
 	}
 
+	args.ucFlag = flags;
 	args.ucI2CSpeed = TARGET_HW_I2C_CLOCK;
-	args.ucRegIndex = 0;
 	args.ucTransBytes = num;
 	args.ucSlaveAddr = slave_addr << 1;
 	args.ucLineNumber = chan->rec.i2c_id;
@@ -77,7 +83,7 @@ static int radeon_process_i2c_ch(struct radeon_i2c_chan *chan,
 	}
 
 	if (!(flags & HW_I2C_WRITE))
-		memcpy(buf, base, num);
+		radeon_atom_copy_swap(buf, base, num, false);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/radeon/btc_dpm.c b/drivers/gpu/drm/radeon/btc_dpm.c
index 9953e1fbc46d..9b6950d9b3c0 100644
--- a/drivers/gpu/drm/radeon/btc_dpm.c
+++ b/drivers/gpu/drm/radeon/btc_dpm.c
@@ -1168,6 +1168,23 @@ static const struct radeon_blacklist_clocks btc_blacklist_clocks[] =
         { 25000, 30000, RADEON_SCLK_UP }
 };
 
+void btc_get_max_clock_from_voltage_dependency_table(struct radeon_clock_voltage_dependency_table *table,
+						     u32 *max_clock)
+{
+	u32 i, clock = 0;
+
+	if ((table == NULL) || (table->count == 0)) {
+		*max_clock = clock;
+		return;
+	}
+
+	for (i = 0; i < table->count; i++) {
+		if (clock < table->entries[i].clk)
+			clock = table->entries[i].clk;
+	}
+	*max_clock = clock;
+}
+
 void btc_apply_voltage_dependency_rules(struct radeon_clock_voltage_dependency_table *table,
 					u32 clock, u16 max_voltage, u16 *voltage)
 {
@@ -1913,7 +1930,7 @@ static int btc_set_mc_special_registers(struct radeon_device *rdev,
 			}
 			j++;
 
-			if (j > SMC_EVERGREEN_MC_REGISTER_ARRAY_SIZE)
+			if (j >= SMC_EVERGREEN_MC_REGISTER_ARRAY_SIZE)
 				return -EINVAL;
 
 			tmp = RREG32(MC_PMG_CMD_MRS);
@@ -1928,7 +1945,7 @@ static int btc_set_mc_special_registers(struct radeon_device *rdev,
 			}
 			j++;
 
-			if (j > SMC_EVERGREEN_MC_REGISTER_ARRAY_SIZE)
+			if (j >= SMC_EVERGREEN_MC_REGISTER_ARRAY_SIZE)
 				return -EINVAL;
 			break;
 		case MC_SEQ_RESERVE_M >> 2:
@@ -1942,7 +1959,7 @@ static int btc_set_mc_special_registers(struct radeon_device *rdev,
 			}
 			j++;
 
-			if (j > SMC_EVERGREEN_MC_REGISTER_ARRAY_SIZE)
+			if (j >= SMC_EVERGREEN_MC_REGISTER_ARRAY_SIZE)
 				return -EINVAL;
 			break;
 		default:
@@ -2080,6 +2097,7 @@ static void btc_apply_state_adjust_rules(struct radeon_device *rdev,
 	bool disable_mclk_switching;
 	u32 mclk, sclk;
 	u16 vddc, vddci;
+	u32 max_sclk_vddc, max_mclk_vddci, max_mclk_vddc;
 
 	if ((rdev->pm.dpm.new_active_crtc_count > 1) ||
 	    btc_dpm_vblank_too_short(rdev))
@@ -2121,6 +2139,39 @@ static void btc_apply_state_adjust_rules(struct radeon_device *rdev,
 			ps->low.vddci = max_limits->vddci;
 	}
 
+	/* limit clocks to max supported clocks based on voltage dependency tables */
+	btc_get_max_clock_from_voltage_dependency_table(&rdev->pm.dpm.dyn_state.vddc_dependency_on_sclk,
+							&max_sclk_vddc);
+	btc_get_max_clock_from_voltage_dependency_table(&rdev->pm.dpm.dyn_state.vddci_dependency_on_mclk,
+							&max_mclk_vddci);
+	btc_get_max_clock_from_voltage_dependency_table(&rdev->pm.dpm.dyn_state.vddc_dependency_on_mclk,
+							&max_mclk_vddc);
+
+	if (max_sclk_vddc) {
+		if (ps->low.sclk > max_sclk_vddc)
+			ps->low.sclk = max_sclk_vddc;
+		if (ps->medium.sclk > max_sclk_vddc)
+			ps->medium.sclk = max_sclk_vddc;
+		if (ps->high.sclk > max_sclk_vddc)
+			ps->high.sclk = max_sclk_vddc;
+	}
+	if (max_mclk_vddci) {
+		if (ps->low.mclk > max_mclk_vddci)
+			ps->low.mclk = max_mclk_vddci;
+		if (ps->medium.mclk > max_mclk_vddci)
+			ps->medium.mclk = max_mclk_vddci;
+		if (ps->high.mclk > max_mclk_vddci)
+			ps->high.mclk = max_mclk_vddci;
+	}
+	if (max_mclk_vddc) {
+		if (ps->low.mclk > max_mclk_vddc)
+			ps->low.mclk = max_mclk_vddc;
+		if (ps->medium.mclk > max_mclk_vddc)
+			ps->medium.mclk = max_mclk_vddc;
+		if (ps->high.mclk > max_mclk_vddc)
+			ps->high.mclk = max_mclk_vddc;
+	}
+
 	/* XXX validate the min clocks required for display */
 
 	if (disable_mclk_switching) {
@@ -2340,12 +2391,6 @@ int btc_dpm_set_power_state(struct radeon_device *rdev)
 		return ret;
 	}
 
-	ret = rv770_dpm_force_performance_level(rdev, RADEON_DPM_FORCED_LEVEL_AUTO);
-	if (ret) {
-		DRM_ERROR("rv770_dpm_force_performance_level failed\n");
-		return ret;
-	}
-
 	return 0;
 }
 
@@ -2699,6 +2744,12 @@ int btc_dpm_init(struct radeon_device *rdev)
 	else
 		rdev->pm.dpm.dyn_state.sclk_mclk_delta = 10000;
 
+	/* make sure dc limits are valid */
+	if ((rdev->pm.dpm.dyn_state.max_clock_voltage_on_dc.sclk == 0) ||
+	    (rdev->pm.dpm.dyn_state.max_clock_voltage_on_dc.mclk == 0))
+		rdev->pm.dpm.dyn_state.max_clock_voltage_on_dc =
+			rdev->pm.dpm.dyn_state.max_clock_voltage_on_ac;
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/radeon/btc_dpm.h b/drivers/gpu/drm/radeon/btc_dpm.h
index 1a15e0e41950..3b6f12b7760b 100644
--- a/drivers/gpu/drm/radeon/btc_dpm.h
+++ b/drivers/gpu/drm/radeon/btc_dpm.h
@@ -46,6 +46,8 @@ void btc_adjust_clock_combinations(struct radeon_device *rdev,
 				   struct rv7xx_pl *pl);
 void btc_apply_voltage_dependency_rules(struct radeon_clock_voltage_dependency_table *table,
 					u32 clock, u16 max_voltage, u16 *voltage);
+void btc_get_max_clock_from_voltage_dependency_table(struct radeon_clock_voltage_dependency_table *table,
+						     u32 *max_clock);
 void btc_apply_voltage_delta_rules(struct radeon_device *rdev,
 				   u16 max_vddc, u16 max_vddci,
 				   u16 *vddc, u16 *vddci);
diff --git a/drivers/gpu/drm/radeon/cayman_blit_shaders.c b/drivers/gpu/drm/radeon/cayman_blit_shaders.c
index 19a0114d2e3b..98d009e154bf 100644
--- a/drivers/gpu/drm/radeon/cayman_blit_shaders.c
+++ b/drivers/gpu/drm/radeon/cayman_blit_shaders.c
@@ -317,58 +317,4 @@ const u32 cayman_default_state[] =
 	0x00000010, /*  */
 };
 
-const u32 cayman_vs[] =
-{
-	0x00000004,
-	0x80400400,
-	0x0000a03c,
-	0x95000688,
-	0x00004000,
-	0x15000688,
-	0x00000000,
-	0x88000000,
-	0x04000000,
-	0x67961001,
-#ifdef __BIG_ENDIAN
-	0x00020000,
-#else
-	0x00000000,
-#endif
-	0x00000000,
-	0x04000000,
-	0x67961000,
-#ifdef __BIG_ENDIAN
-	0x00020008,
-#else
-	0x00000008,
-#endif
-	0x00000000,
-};
-
-const u32 cayman_ps[] =
-{
-	0x00000004,
-	0xa00c0000,
-	0x00000008,
-	0x80400000,
-	0x00000000,
-	0x95000688,
-	0x00000000,
-	0x88000000,
-	0x00380400,
-	0x00146b10,
-	0x00380000,
-	0x20146b10,
-	0x00380400,
-	0x40146b00,
-	0x80380000,
-	0x60146b00,
-	0x00000010,
-	0x000d1000,
-	0xb0800000,
-	0x00000000,
-};
-
-const u32 cayman_ps_size = ARRAY_SIZE(cayman_ps);
-const u32 cayman_vs_size = ARRAY_SIZE(cayman_vs);
 const u32 cayman_default_size = ARRAY_SIZE(cayman_default_state);
diff --git a/drivers/gpu/drm/radeon/ci_dpm.c b/drivers/gpu/drm/radeon/ci_dpm.c
new file mode 100644
index 000000000000..51e947a97edf
--- /dev/null
+++ b/drivers/gpu/drm/radeon/ci_dpm.c
@@ -0,0 +1,5263 @@
+/*
+ * Copyright 2013 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+
+#include "drmP.h"
+#include "radeon.h"
+#include "cikd.h"
+#include "r600_dpm.h"
+#include "ci_dpm.h"
+#include "atom.h"
+#include <linux/seq_file.h>
+
+#define MC_CG_ARB_FREQ_F0           0x0a
+#define MC_CG_ARB_FREQ_F1           0x0b
+#define MC_CG_ARB_FREQ_F2           0x0c
+#define MC_CG_ARB_FREQ_F3           0x0d
+
+#define SMC_RAM_END 0x40000
+
+#define VOLTAGE_SCALE               4
+#define VOLTAGE_VID_OFFSET_SCALE1    625
+#define VOLTAGE_VID_OFFSET_SCALE2    100
+
+static const struct ci_pt_defaults defaults_bonaire_xt =
+{
+	1, 0xF, 0xFD, 0x19, 5, 45, 0, 0xB0000,
+	{ 0x79,  0x253, 0x25D, 0xAE,  0x72,  0x80,  0x83,  0x86,  0x6F,  0xC8,  0xC9,  0xC9,  0x2F,  0x4D,  0x61  },
+	{ 0x17C, 0x172, 0x180, 0x1BC, 0x1B3, 0x1BD, 0x206, 0x200, 0x203, 0x25D, 0x25A, 0x255, 0x2C3, 0x2C5, 0x2B4 }
+};
+
+static const struct ci_pt_defaults defaults_bonaire_pro =
+{
+	1, 0xF, 0xFD, 0x19, 5, 45, 0, 0x65062,
+	{ 0x8C,  0x23F, 0x244, 0xA6,  0x83,  0x85,  0x86,  0x86,  0x83,  0xDB,  0xDB,  0xDA,  0x67,  0x60,  0x5F  },
+	{ 0x187, 0x193, 0x193, 0x1C7, 0x1D1, 0x1D1, 0x210, 0x219, 0x219, 0x266, 0x26C, 0x26C, 0x2C9, 0x2CB, 0x2CB }
+};
+
+static const struct ci_pt_defaults defaults_saturn_xt =
+{
+	1, 0xF, 0xFD, 0x19, 5, 55, 0, 0x70000,
+	{ 0x8C,  0x247, 0x249, 0xA6,  0x80,  0x81,  0x8B,  0x89,  0x86,  0xC9,  0xCA,  0xC9,  0x4D,  0x4D,  0x4D  },
+	{ 0x187, 0x187, 0x187, 0x1C7, 0x1C7, 0x1C7, 0x210, 0x210, 0x210, 0x266, 0x266, 0x266, 0x2C9, 0x2C9, 0x2C9 }
+};
+
+static const struct ci_pt_defaults defaults_saturn_pro =
+{
+	1, 0xF, 0xFD, 0x19, 5, 55, 0, 0x30000,
+	{ 0x96,  0x21D, 0x23B, 0xA1,  0x85,  0x87,  0x83,  0x84,  0x81,  0xE6,  0xE6,  0xE6,  0x71,  0x6A,  0x6A  },
+	{ 0x193, 0x19E, 0x19E, 0x1D2, 0x1DC, 0x1DC, 0x21A, 0x223, 0x223, 0x26E, 0x27E, 0x274, 0x2CF, 0x2D2, 0x2D2 }
+};
+
+static const struct ci_pt_config_reg didt_config_ci[] =
+{
+	{ 0x10, 0x000000ff, 0, 0x0, CISLANDS_CONFIGREG_DIDT_IND },
+	{ 0x10, 0x0000ff00, 8, 0x0, CISLANDS_CONFIGREG_DIDT_IND },
+	{ 0x10, 0x00ff0000, 16, 0x0, CISLANDS_CONFIGREG_DIDT_IND },
+	{ 0x10, 0xff000000, 24, 0x0, CISLANDS_CONFIGREG_DIDT_IND },
+	{ 0x11, 0x000000ff, 0, 0x0, CISLANDS_CONFIGREG_DIDT_IND },
+	{ 0x11, 0x0000ff00, 8, 0x0, CISLANDS_CONFIGREG_DIDT_IND },
+	{ 0x11, 0x00ff0000, 16, 0x0, CISLANDS_CONFIGREG_DIDT_IND },
+	{ 0x11, 0xff000000, 24, 0x0, CISLANDS_CONFIGREG_DIDT_IND },
+	{ 0x12, 0x000000ff, 0, 0x0, CISLANDS_CONFIGREG_DIDT_IND },
+	{ 0x12, 0x0000ff00, 8, 0x0, CISLANDS_CONFIGREG_DIDT_IND },
+	{ 0x12, 0x00ff0000, 16, 0x0, CISLANDS_CONFIGREG_DIDT_IND },
+	{ 0x12, 0xff000000, 24, 0x0, CISLANDS_CONFIGREG_DIDT_IND },
+	{ 0x2, 0x00003fff, 0, 0x4, CISLANDS_CONFIGREG_DIDT_IND },
+	{ 0x2, 0x03ff0000, 16, 0x80, CISLANDS_CONFIGREG_DIDT_IND },
+	{ 0x2, 0x78000000, 27, 0x3, CISLANDS_CONFIGREG_DIDT_IND },
+	{ 0x1, 0x0000ffff, 0, 0x3FFF, CISLANDS_CONFIGREG_DIDT_IND },
+	{ 0x1, 0xffff0000, 16, 0x3FFF, CISLANDS_CONFIGREG_DIDT_IND },
+	{ 0x0, 0x00000001, 0, 0x0, CISLANDS_CONFIGREG_DIDT_IND },
+	{ 0x30, 0x000000ff, 0, 0x0, CISLANDS_CONFIGREG_DIDT_IND },
+	{ 0x30, 0x0000ff00, 8, 0x0, CISLANDS_CONFIGREG_DIDT_IND },
+	{ 0x30, 0x00ff0000, 16, 0x0, CISLANDS_CONFIGREG_DIDT_IND },
+	{ 0x30, 0xff000000, 24, 0x0, CISLANDS_CONFIGREG_DIDT_IND },
+	{ 0x31, 0x000000ff, 0, 0x0, CISLANDS_CONFIGREG_DIDT_IND },
+	{ 0x31, 0x0000ff00, 8, 0x0, CISLANDS_CONFIGREG_DIDT_IND },
+	{ 0x31, 0x00ff0000, 16, 0x0, CISLANDS_CONFIGREG_DIDT_IND },
+	{ 0x31, 0xff000000, 24, 0x0, CISLANDS_CONFIGREG_DIDT_IND },
+	{ 0x32, 0x000000ff, 0, 0x0, CISLANDS_CONFIGREG_DIDT_IND },
+	{ 0x32, 0x0000ff00, 8, 0x0, CISLANDS_CONFIGREG_DIDT_IND },
+	{ 0x32, 0x00ff0000, 16, 0x0, CISLANDS_CONFIGREG_DIDT_IND },
+	{ 0x32, 0xff000000, 24, 0x0, CISLANDS_CONFIGREG_DIDT_IND },
+	{ 0x22, 0x00003fff, 0, 0x4, CISLANDS_CONFIGREG_DIDT_IND },
+	{ 0x22, 0x03ff0000, 16, 0x80, CISLANDS_CONFIGREG_DIDT_IND },
+	{ 0x22, 0x78000000, 27, 0x3, CISLANDS_CONFIGREG_DIDT_IND },
+	{ 0x21, 0x0000ffff, 0, 0x3FFF, CISLANDS_CONFIGREG_DIDT_IND },
+	{ 0x21, 0xffff0000, 16, 0x3FFF, CISLANDS_CONFIGREG_DIDT_IND },
+	{ 0x20, 0x00000001, 0, 0x0, CISLANDS_CONFIGREG_DIDT_IND },
+	{ 0x50, 0x000000ff, 0, 0x0, CISLANDS_CONFIGREG_DIDT_IND },
+	{ 0x50, 0x0000ff00, 8, 0x0, CISLANDS_CONFIGREG_DIDT_IND },
+	{ 0x50, 0x00ff0000, 16, 0x0, CISLANDS_CONFIGREG_DIDT_IND },
+	{ 0x50, 0xff000000, 24, 0x0, CISLANDS_CONFIGREG_DIDT_IND },
+	{ 0x51, 0x000000ff, 0, 0x0, CISLANDS_CONFIGREG_DIDT_IND },
+	{ 0x51, 0x0000ff00, 8, 0x0, CISLANDS_CONFIGREG_DIDT_IND },
+	{ 0x51, 0x00ff0000, 16, 0x0, CISLANDS_CONFIGREG_DIDT_IND },
+	{ 0x51, 0xff000000, 24, 0x0, CISLANDS_CONFIGREG_DIDT_IND },
+	{ 0x52, 0x000000ff, 0, 0x0, CISLANDS_CONFIGREG_DIDT_IND },
+	{ 0x52, 0x0000ff00, 8, 0x0, CISLANDS_CONFIGREG_DIDT_IND },
+	{ 0x52, 0x00ff0000, 16, 0x0, CISLANDS_CONFIGREG_DIDT_IND },
+	{ 0x52, 0xff000000, 24, 0x0, CISLANDS_CONFIGREG_DIDT_IND },
+	{ 0x42, 0x00003fff, 0, 0x4, CISLANDS_CONFIGREG_DIDT_IND },
+	{ 0x42, 0x03ff0000, 16, 0x80, CISLANDS_CONFIGREG_DIDT_IND },
+	{ 0x42, 0x78000000, 27, 0x3, CISLANDS_CONFIGREG_DIDT_IND },
+	{ 0x41, 0x0000ffff, 0, 0x3FFF, CISLANDS_CONFIGREG_DIDT_IND },
+	{ 0x41, 0xffff0000, 16, 0x3FFF, CISLANDS_CONFIGREG_DIDT_IND },
+	{ 0x40, 0x00000001, 0, 0x0, CISLANDS_CONFIGREG_DIDT_IND },
+	{ 0x70, 0x000000ff, 0, 0x0, CISLANDS_CONFIGREG_DIDT_IND },
+	{ 0x70, 0x0000ff00, 8, 0x0, CISLANDS_CONFIGREG_DIDT_IND },
+	{ 0x70, 0x00ff0000, 16, 0x0, CISLANDS_CONFIGREG_DIDT_IND },
+	{ 0x70, 0xff000000, 24, 0x0, CISLANDS_CONFIGREG_DIDT_IND },
+	{ 0x71, 0x000000ff, 0, 0x0, CISLANDS_CONFIGREG_DIDT_IND },
+	{ 0x71, 0x0000ff00, 8, 0x0, CISLANDS_CONFIGREG_DIDT_IND },
+	{ 0x71, 0x00ff0000, 16, 0x0, CISLANDS_CONFIGREG_DIDT_IND },
+	{ 0x71, 0xff000000, 24, 0x0, CISLANDS_CONFIGREG_DIDT_IND },
+	{ 0x72, 0x000000ff, 0, 0x0, CISLANDS_CONFIGREG_DIDT_IND },
+	{ 0x72, 0x0000ff00, 8, 0x0, CISLANDS_CONFIGREG_DIDT_IND },
+	{ 0x72, 0x00ff0000, 16, 0x0, CISLANDS_CONFIGREG_DIDT_IND },
+	{ 0x72, 0xff000000, 24, 0x0, CISLANDS_CONFIGREG_DIDT_IND },
+	{ 0x62, 0x00003fff, 0, 0x4, CISLANDS_CONFIGREG_DIDT_IND },
+	{ 0x62, 0x03ff0000, 16, 0x80, CISLANDS_CONFIGREG_DIDT_IND },
+	{ 0x62, 0x78000000, 27, 0x3, CISLANDS_CONFIGREG_DIDT_IND },
+	{ 0x61, 0x0000ffff, 0, 0x3FFF, CISLANDS_CONFIGREG_DIDT_IND },
+	{ 0x61, 0xffff0000, 16, 0x3FFF, CISLANDS_CONFIGREG_DIDT_IND },
+	{ 0x60, 0x00000001, 0, 0x0, CISLANDS_CONFIGREG_DIDT_IND },
+	{ 0xFFFFFFFF }
+};
+
+extern u8 rv770_get_memory_module_index(struct radeon_device *rdev);
+extern void btc_get_max_clock_from_voltage_dependency_table(struct radeon_clock_voltage_dependency_table *table,
+							    u32 *max_clock);
+extern int ni_copy_and_switch_arb_sets(struct radeon_device *rdev,
+				       u32 arb_freq_src, u32 arb_freq_dest);
+extern u8 si_get_ddr3_mclk_frequency_ratio(u32 memory_clock);
+extern u8 si_get_mclk_frequency_ratio(u32 memory_clock, bool strobe_mode);
+extern void si_trim_voltage_table_to_fit_state_table(struct radeon_device *rdev,
+						     u32 max_voltage_steps,
+						     struct atom_voltage_table *voltage_table);
+extern void cik_enter_rlc_safe_mode(struct radeon_device *rdev);
+extern void cik_exit_rlc_safe_mode(struct radeon_device *rdev);
+extern void cik_update_cg(struct radeon_device *rdev,
+			  u32 block, bool enable);
+
+static int ci_get_std_voltage_value_sidd(struct radeon_device *rdev,
+					 struct atom_voltage_table_entry *voltage_table,
+					 u16 *std_voltage_hi_sidd, u16 *std_voltage_lo_sidd);
+static int ci_set_power_limit(struct radeon_device *rdev, u32 n);
+static int ci_set_overdrive_target_tdp(struct radeon_device *rdev,
+				       u32 target_tdp);
+static int ci_update_uvd_dpm(struct radeon_device *rdev, bool gate);
+
+static struct ci_power_info *ci_get_pi(struct radeon_device *rdev)
+{
+        struct ci_power_info *pi = rdev->pm.dpm.priv;
+
+        return pi;
+}
+
+static struct ci_ps *ci_get_ps(struct radeon_ps *rps)
+{
+	struct ci_ps *ps = rps->ps_priv;
+
+	return ps;
+}
+
+static void ci_initialize_powertune_defaults(struct radeon_device *rdev)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+
+	switch (rdev->pdev->device) {
+        case 0x6650:
+        case 0x6658:
+        case 0x665C:
+        default:
+		pi->powertune_defaults = &defaults_bonaire_xt;
+		break;
+        case 0x6651:
+        case 0x665D:
+		pi->powertune_defaults = &defaults_bonaire_pro;
+		break;
+        case 0x6640:
+		pi->powertune_defaults = &defaults_saturn_xt;
+		break;
+        case 0x6641:
+		pi->powertune_defaults = &defaults_saturn_pro;
+		break;
+	}
+
+	pi->dte_tj_offset = 0;
+
+	pi->caps_power_containment = true;
+	pi->caps_cac = false;
+	pi->caps_sq_ramping = false;
+	pi->caps_db_ramping = false;
+	pi->caps_td_ramping = false;
+	pi->caps_tcp_ramping = false;
+
+	if (pi->caps_power_containment) {
+		pi->caps_cac = true;
+		pi->enable_bapm_feature = true;
+		pi->enable_tdc_limit_feature = true;
+		pi->enable_pkg_pwr_tracking_feature = true;
+	}
+}
+
+static u8 ci_convert_to_vid(u16 vddc)
+{
+	return (6200 - (vddc * VOLTAGE_SCALE)) / 25;
+}
+
+static int ci_populate_bapm_vddc_vid_sidd(struct radeon_device *rdev)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	u8 *hi_vid = pi->smc_powertune_table.BapmVddCVidHiSidd;
+	u8 *lo_vid = pi->smc_powertune_table.BapmVddCVidLoSidd;
+	u8 *hi2_vid = pi->smc_powertune_table.BapmVddCVidHiSidd2;
+	u32 i;
+
+	if (rdev->pm.dpm.dyn_state.cac_leakage_table.entries == NULL)
+		return -EINVAL;
+	if (rdev->pm.dpm.dyn_state.cac_leakage_table.count > 8)
+		return -EINVAL;
+	if (rdev->pm.dpm.dyn_state.cac_leakage_table.count !=
+	    rdev->pm.dpm.dyn_state.vddc_dependency_on_sclk.count)
+		return -EINVAL;
+
+	for (i = 0; i < rdev->pm.dpm.dyn_state.cac_leakage_table.count; i++) {
+		if (rdev->pm.dpm.platform_caps & ATOM_PP_PLATFORM_CAP_EVV) {
+			lo_vid[i] = ci_convert_to_vid(rdev->pm.dpm.dyn_state.cac_leakage_table.entries[i].vddc1);
+			hi_vid[i] = ci_convert_to_vid(rdev->pm.dpm.dyn_state.cac_leakage_table.entries[i].vddc2);
+			hi2_vid[i] = ci_convert_to_vid(rdev->pm.dpm.dyn_state.cac_leakage_table.entries[i].vddc3);
+		} else {
+			lo_vid[i] = ci_convert_to_vid(rdev->pm.dpm.dyn_state.cac_leakage_table.entries[i].vddc);
+			hi_vid[i] = ci_convert_to_vid((u16)rdev->pm.dpm.dyn_state.cac_leakage_table.entries[i].leakage);
+		}
+	}
+	return 0;
+}
+
+static int ci_populate_vddc_vid(struct radeon_device *rdev)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	u8 *vid = pi->smc_powertune_table.VddCVid;
+	u32 i;
+
+	if (pi->vddc_voltage_table.count > 8)
+		return -EINVAL;
+
+	for (i = 0; i < pi->vddc_voltage_table.count; i++)
+		vid[i] = ci_convert_to_vid(pi->vddc_voltage_table.entries[i].value);
+
+	return 0;
+}
+
+static int ci_populate_svi_load_line(struct radeon_device *rdev)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	const struct ci_pt_defaults *pt_defaults = pi->powertune_defaults;
+
+	pi->smc_powertune_table.SviLoadLineEn = pt_defaults->svi_load_line_en;
+	pi->smc_powertune_table.SviLoadLineVddC = pt_defaults->svi_load_line_vddc;
+	pi->smc_powertune_table.SviLoadLineTrimVddC = 3;
+	pi->smc_powertune_table.SviLoadLineOffsetVddC = 0;
+
+	return 0;
+}
+
+static int ci_populate_tdc_limit(struct radeon_device *rdev)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	const struct ci_pt_defaults *pt_defaults = pi->powertune_defaults;
+	u16 tdc_limit;
+
+	tdc_limit = rdev->pm.dpm.dyn_state.cac_tdp_table->tdc * 256;
+	pi->smc_powertune_table.TDC_VDDC_PkgLimit = cpu_to_be16(tdc_limit);
+	pi->smc_powertune_table.TDC_VDDC_ThrottleReleaseLimitPerc =
+		pt_defaults->tdc_vddc_throttle_release_limit_perc;
+	pi->smc_powertune_table.TDC_MAWt = pt_defaults->tdc_mawt;
+
+	return 0;
+}
+
+static int ci_populate_dw8(struct radeon_device *rdev)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	const struct ci_pt_defaults *pt_defaults = pi->powertune_defaults;
+	int ret;
+
+	ret = ci_read_smc_sram_dword(rdev,
+				     SMU7_FIRMWARE_HEADER_LOCATION +
+				     offsetof(SMU7_Firmware_Header, PmFuseTable) +
+				     offsetof(SMU7_Discrete_PmFuses, TdcWaterfallCtl),
+				     (u32 *)&pi->smc_powertune_table.TdcWaterfallCtl,
+				     pi->sram_end);
+	if (ret)
+		return -EINVAL;
+	else
+		pi->smc_powertune_table.TdcWaterfallCtl = pt_defaults->tdc_waterfall_ctl;
+
+	return 0;
+}
+
+static int ci_min_max_v_gnbl_pm_lid_from_bapm_vddc(struct radeon_device *rdev)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	u8 *hi_vid = pi->smc_powertune_table.BapmVddCVidHiSidd;
+	u8 *lo_vid = pi->smc_powertune_table.BapmVddCVidLoSidd;
+	int i, min, max;
+
+	min = max = hi_vid[0];
+	for (i = 0; i < 8; i++) {
+		if (0 != hi_vid[i]) {
+			if (min > hi_vid[i])
+				min = hi_vid[i];
+			if (max < hi_vid[i])
+				max = hi_vid[i];
+		}
+
+		if (0 != lo_vid[i]) {
+			if (min > lo_vid[i])
+				min = lo_vid[i];
+			if (max < lo_vid[i])
+				max = lo_vid[i];
+		}
+	}
+
+	if ((min == 0) || (max == 0))
+		return -EINVAL;
+	pi->smc_powertune_table.GnbLPMLMaxVid = (u8)max;
+	pi->smc_powertune_table.GnbLPMLMinVid = (u8)min;
+
+	return 0;
+}
+
+static int ci_populate_bapm_vddc_base_leakage_sidd(struct radeon_device *rdev)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	u16 hi_sidd = pi->smc_powertune_table.BapmVddCBaseLeakageHiSidd;
+	u16 lo_sidd = pi->smc_powertune_table.BapmVddCBaseLeakageLoSidd;
+	struct radeon_cac_tdp_table *cac_tdp_table =
+		rdev->pm.dpm.dyn_state.cac_tdp_table;
+
+	hi_sidd = cac_tdp_table->high_cac_leakage / 100 * 256;
+	lo_sidd = cac_tdp_table->low_cac_leakage / 100 * 256;
+
+	pi->smc_powertune_table.BapmVddCBaseLeakageHiSidd = cpu_to_be16(hi_sidd);
+	pi->smc_powertune_table.BapmVddCBaseLeakageLoSidd = cpu_to_be16(lo_sidd);
+
+	return 0;
+}
+
+static int ci_populate_bapm_parameters_in_dpm_table(struct radeon_device *rdev)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	const struct ci_pt_defaults *pt_defaults = pi->powertune_defaults;
+	SMU7_Discrete_DpmTable  *dpm_table = &pi->smc_state_table;
+	struct radeon_cac_tdp_table *cac_tdp_table =
+		rdev->pm.dpm.dyn_state.cac_tdp_table;
+	struct radeon_ppm_table *ppm = rdev->pm.dpm.dyn_state.ppm_table;
+	int i, j, k;
+	const u16 *def1;
+	const u16 *def2;
+
+	dpm_table->DefaultTdp = cac_tdp_table->tdp * 256;
+	dpm_table->TargetTdp = cac_tdp_table->configurable_tdp * 256;
+
+	dpm_table->DTETjOffset = (u8)pi->dte_tj_offset;
+	dpm_table->GpuTjMax =
+		(u8)(pi->thermal_temp_setting.temperature_high / 1000);
+	dpm_table->GpuTjHyst = 8;
+
+	dpm_table->DTEAmbientTempBase = pt_defaults->dte_ambient_temp_base;
+
+	if (ppm) {
+		dpm_table->PPM_PkgPwrLimit = cpu_to_be16((u16)ppm->dgpu_tdp * 256 / 1000);
+		dpm_table->PPM_TemperatureLimit = cpu_to_be16((u16)ppm->tj_max * 256);
+	} else {
+		dpm_table->PPM_PkgPwrLimit = cpu_to_be16(0);
+		dpm_table->PPM_TemperatureLimit = cpu_to_be16(0);
+	}
+
+	dpm_table->BAPM_TEMP_GRADIENT = cpu_to_be32(pt_defaults->bapm_temp_gradient);
+	def1 = pt_defaults->bapmti_r;
+	def2 = pt_defaults->bapmti_rc;
+
+	for (i = 0; i < SMU7_DTE_ITERATIONS; i++) {
+		for (j = 0; j < SMU7_DTE_SOURCES; j++) {
+			for (k = 0; k < SMU7_DTE_SINKS; k++) {
+				dpm_table->BAPMTI_R[i][j][k] = cpu_to_be16(*def1);
+				dpm_table->BAPMTI_RC[i][j][k] = cpu_to_be16(*def2);
+				def1++;
+				def2++;
+			}
+		}
+	}
+
+	return 0;
+}
+
+static int ci_populate_pm_base(struct radeon_device *rdev)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	u32 pm_fuse_table_offset;
+	int ret;
+
+	if (pi->caps_power_containment) {
+		ret = ci_read_smc_sram_dword(rdev,
+					     SMU7_FIRMWARE_HEADER_LOCATION +
+					     offsetof(SMU7_Firmware_Header, PmFuseTable),
+					     &pm_fuse_table_offset, pi->sram_end);
+		if (ret)
+			return ret;
+		ret = ci_populate_bapm_vddc_vid_sidd(rdev);
+		if (ret)
+			return ret;
+		ret = ci_populate_vddc_vid(rdev);
+		if (ret)
+			return ret;
+		ret = ci_populate_svi_load_line(rdev);
+		if (ret)
+			return ret;
+		ret = ci_populate_tdc_limit(rdev);
+		if (ret)
+			return ret;
+		ret = ci_populate_dw8(rdev);
+		if (ret)
+			return ret;
+		ret = ci_min_max_v_gnbl_pm_lid_from_bapm_vddc(rdev);
+		if (ret)
+			return ret;
+		ret = ci_populate_bapm_vddc_base_leakage_sidd(rdev);
+		if (ret)
+			return ret;
+		ret = ci_copy_bytes_to_smc(rdev, pm_fuse_table_offset,
+					   (u8 *)&pi->smc_powertune_table,
+					   sizeof(SMU7_Discrete_PmFuses), pi->sram_end);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static void ci_do_enable_didt(struct radeon_device *rdev, const bool enable)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	u32 data;
+
+	if (pi->caps_sq_ramping) {
+		data = RREG32_DIDT(DIDT_SQ_CTRL0);
+		if (enable)
+			data |= DIDT_CTRL_EN;
+		else
+			data &= ~DIDT_CTRL_EN;
+		WREG32_DIDT(DIDT_SQ_CTRL0, data);
+	}
+
+	if (pi->caps_db_ramping) {
+		data = RREG32_DIDT(DIDT_DB_CTRL0);
+		if (enable)
+			data |= DIDT_CTRL_EN;
+		else
+			data &= ~DIDT_CTRL_EN;
+		WREG32_DIDT(DIDT_DB_CTRL0, data);
+	}
+
+	if (pi->caps_td_ramping) {
+		data = RREG32_DIDT(DIDT_TD_CTRL0);
+		if (enable)
+			data |= DIDT_CTRL_EN;
+		else
+			data &= ~DIDT_CTRL_EN;
+		WREG32_DIDT(DIDT_TD_CTRL0, data);
+	}
+
+	if (pi->caps_tcp_ramping) {
+		data = RREG32_DIDT(DIDT_TCP_CTRL0);
+		if (enable)
+			data |= DIDT_CTRL_EN;
+		else
+			data &= ~DIDT_CTRL_EN;
+		WREG32_DIDT(DIDT_TCP_CTRL0, data);
+	}
+}
+
+static int ci_program_pt_config_registers(struct radeon_device *rdev,
+					  const struct ci_pt_config_reg *cac_config_regs)
+{
+	const struct ci_pt_config_reg *config_regs = cac_config_regs;
+	u32 data;
+	u32 cache = 0;
+
+	if (config_regs == NULL)
+		return -EINVAL;
+
+	while (config_regs->offset != 0xFFFFFFFF) {
+		if (config_regs->type == CISLANDS_CONFIGREG_CACHE) {
+			cache |= ((config_regs->value << config_regs->shift) & config_regs->mask);
+		} else {
+			switch (config_regs->type) {
+			case CISLANDS_CONFIGREG_SMC_IND:
+				data = RREG32_SMC(config_regs->offset);
+				break;
+			case CISLANDS_CONFIGREG_DIDT_IND:
+				data = RREG32_DIDT(config_regs->offset);
+				break;
+			default:
+				data = RREG32(config_regs->offset << 2);
+				break;
+			}
+
+			data &= ~config_regs->mask;
+			data |= ((config_regs->value << config_regs->shift) & config_regs->mask);
+			data |= cache;
+
+			switch (config_regs->type) {
+			case CISLANDS_CONFIGREG_SMC_IND:
+				WREG32_SMC(config_regs->offset, data);
+				break;
+			case CISLANDS_CONFIGREG_DIDT_IND:
+				WREG32_DIDT(config_regs->offset, data);
+				break;
+			default:
+				WREG32(config_regs->offset << 2, data);
+				break;
+			}
+			cache = 0;
+		}
+		config_regs++;
+	}
+	return 0;
+}
+
+static int ci_enable_didt(struct radeon_device *rdev, bool enable)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	int ret;
+
+	if (pi->caps_sq_ramping || pi->caps_db_ramping ||
+	    pi->caps_td_ramping || pi->caps_tcp_ramping) {
+		cik_enter_rlc_safe_mode(rdev);
+
+		if (enable) {
+			ret = ci_program_pt_config_registers(rdev, didt_config_ci);
+			if (ret) {
+				cik_exit_rlc_safe_mode(rdev);
+				return ret;
+			}
+		}
+
+		ci_do_enable_didt(rdev, enable);
+
+		cik_exit_rlc_safe_mode(rdev);
+	}
+
+	return 0;
+}
+
+static int ci_enable_power_containment(struct radeon_device *rdev, bool enable)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	PPSMC_Result smc_result;
+	int ret = 0;
+
+	if (enable) {
+		pi->power_containment_features = 0;
+		if (pi->caps_power_containment) {
+			if (pi->enable_bapm_feature) {
+				smc_result = ci_send_msg_to_smc(rdev, PPSMC_MSG_EnableDTE);
+				if (smc_result != PPSMC_Result_OK)
+					ret = -EINVAL;
+				else
+					pi->power_containment_features |= POWERCONTAINMENT_FEATURE_BAPM;
+			}
+
+			if (pi->enable_tdc_limit_feature) {
+				smc_result = ci_send_msg_to_smc(rdev, PPSMC_MSG_TDCLimitEnable);
+				if (smc_result != PPSMC_Result_OK)
+					ret = -EINVAL;
+				else
+					pi->power_containment_features |= POWERCONTAINMENT_FEATURE_TDCLimit;
+			}
+
+			if (pi->enable_pkg_pwr_tracking_feature) {
+				smc_result = ci_send_msg_to_smc(rdev, PPSMC_MSG_PkgPwrLimitEnable);
+				if (smc_result != PPSMC_Result_OK) {
+					ret = -EINVAL;
+				} else {
+					struct radeon_cac_tdp_table *cac_tdp_table =
+						rdev->pm.dpm.dyn_state.cac_tdp_table;
+					u32 default_pwr_limit =
+						(u32)(cac_tdp_table->maximum_power_delivery_limit * 256);
+
+					pi->power_containment_features |= POWERCONTAINMENT_FEATURE_PkgPwrLimit;
+
+					ci_set_power_limit(rdev, default_pwr_limit);
+				}
+			}
+		}
+	} else {
+		if (pi->caps_power_containment && pi->power_containment_features) {
+			if (pi->power_containment_features & POWERCONTAINMENT_FEATURE_TDCLimit)
+				ci_send_msg_to_smc(rdev, PPSMC_MSG_TDCLimitDisable);
+
+			if (pi->power_containment_features & POWERCONTAINMENT_FEATURE_BAPM)
+				ci_send_msg_to_smc(rdev, PPSMC_MSG_DisableDTE);
+
+			if (pi->power_containment_features & POWERCONTAINMENT_FEATURE_PkgPwrLimit)
+				ci_send_msg_to_smc(rdev, PPSMC_MSG_PkgPwrLimitDisable);
+			pi->power_containment_features = 0;
+		}
+	}
+
+	return ret;
+}
+
+static int ci_enable_smc_cac(struct radeon_device *rdev, bool enable)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	PPSMC_Result smc_result;
+	int ret = 0;
+
+	if (pi->caps_cac) {
+		if (enable) {
+			smc_result = ci_send_msg_to_smc(rdev, PPSMC_MSG_EnableCac);
+			if (smc_result != PPSMC_Result_OK) {
+				ret = -EINVAL;
+				pi->cac_enabled = false;
+			} else {
+				pi->cac_enabled = true;
+			}
+		} else if (pi->cac_enabled) {
+			ci_send_msg_to_smc(rdev, PPSMC_MSG_DisableCac);
+			pi->cac_enabled = false;
+		}
+	}
+
+	return ret;
+}
+
+static int ci_power_control_set_level(struct radeon_device *rdev)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	struct radeon_cac_tdp_table *cac_tdp_table =
+		rdev->pm.dpm.dyn_state.cac_tdp_table;
+	s32 adjust_percent;
+	s32 target_tdp;
+	int ret = 0;
+	bool adjust_polarity = false; /* ??? */
+
+	if (pi->caps_power_containment &&
+	    (pi->power_containment_features & POWERCONTAINMENT_FEATURE_BAPM)) {
+		adjust_percent = adjust_polarity ?
+			rdev->pm.dpm.tdp_adjustment : (-1 * rdev->pm.dpm.tdp_adjustment);
+		target_tdp = ((100 + adjust_percent) *
+			      (s32)cac_tdp_table->configurable_tdp) / 100;
+		target_tdp *= 256;
+
+		ret = ci_set_overdrive_target_tdp(rdev, (u32)target_tdp);
+	}
+
+	return ret;
+}
+
+void ci_dpm_powergate_uvd(struct radeon_device *rdev, bool gate)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+
+	if (pi->uvd_power_gated == gate)
+		return;
+
+	pi->uvd_power_gated = gate;
+
+	ci_update_uvd_dpm(rdev, gate);
+}
+
+bool ci_dpm_vblank_too_short(struct radeon_device *rdev)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	u32 vblank_time = r600_dpm_get_vblank_time(rdev);
+	u32 switch_limit = pi->mem_gddr5 ? 450 : 300;
+
+	if (vblank_time < switch_limit)
+		return true;
+	else
+		return false;
+
+}
+
+static void ci_apply_state_adjust_rules(struct radeon_device *rdev,
+					struct radeon_ps *rps)
+{
+	struct ci_ps *ps = ci_get_ps(rps);
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	struct radeon_clock_and_voltage_limits *max_limits;
+	bool disable_mclk_switching;
+	u32 sclk, mclk;
+	u32 max_sclk_vddc, max_mclk_vddci, max_mclk_vddc;
+	int i;
+
+	if ((rdev->pm.dpm.new_active_crtc_count > 1) ||
+	    ci_dpm_vblank_too_short(rdev))
+		disable_mclk_switching = true;
+	else
+		disable_mclk_switching = false;
+
+	if ((rps->class & ATOM_PPLIB_CLASSIFICATION_UI_MASK) == ATOM_PPLIB_CLASSIFICATION_UI_BATTERY)
+		pi->battery_state = true;
+	else
+		pi->battery_state = false;
+
+	if (rdev->pm.dpm.ac_power)
+		max_limits = &rdev->pm.dpm.dyn_state.max_clock_voltage_on_ac;
+	else
+		max_limits = &rdev->pm.dpm.dyn_state.max_clock_voltage_on_dc;
+
+	if (rdev->pm.dpm.ac_power == false) {
+		for (i = 0; i < ps->performance_level_count; i++) {
+			if (ps->performance_levels[i].mclk > max_limits->mclk)
+				ps->performance_levels[i].mclk = max_limits->mclk;
+			if (ps->performance_levels[i].sclk > max_limits->sclk)
+				ps->performance_levels[i].sclk = max_limits->sclk;
+		}
+	}
+
+	/* limit clocks to max supported clocks based on voltage dependency tables */
+	btc_get_max_clock_from_voltage_dependency_table(&rdev->pm.dpm.dyn_state.vddc_dependency_on_sclk,
+							&max_sclk_vddc);
+	btc_get_max_clock_from_voltage_dependency_table(&rdev->pm.dpm.dyn_state.vddci_dependency_on_mclk,
+							&max_mclk_vddci);
+	btc_get_max_clock_from_voltage_dependency_table(&rdev->pm.dpm.dyn_state.vddc_dependency_on_mclk,
+							&max_mclk_vddc);
+
+	for (i = 0; i < ps->performance_level_count; i++) {
+		if (max_sclk_vddc) {
+			if (ps->performance_levels[i].sclk > max_sclk_vddc)
+				ps->performance_levels[i].sclk = max_sclk_vddc;
+		}
+		if (max_mclk_vddci) {
+			if (ps->performance_levels[i].mclk > max_mclk_vddci)
+				ps->performance_levels[i].mclk = max_mclk_vddci;
+		}
+		if (max_mclk_vddc) {
+			if (ps->performance_levels[i].mclk > max_mclk_vddc)
+				ps->performance_levels[i].mclk = max_mclk_vddc;
+		}
+	}
+
+	/* XXX validate the min clocks required for display */
+
+	if (disable_mclk_switching) {
+		mclk  = ps->performance_levels[ps->performance_level_count - 1].mclk;
+		sclk = ps->performance_levels[0].sclk;
+	} else {
+		mclk = ps->performance_levels[0].mclk;
+		sclk = ps->performance_levels[0].sclk;
+	}
+
+	ps->performance_levels[0].sclk = sclk;
+	ps->performance_levels[0].mclk = mclk;
+
+	if (ps->performance_levels[1].sclk < ps->performance_levels[0].sclk)
+		ps->performance_levels[1].sclk = ps->performance_levels[0].sclk;
+
+	if (disable_mclk_switching) {
+		if (ps->performance_levels[0].mclk < ps->performance_levels[1].mclk)
+			ps->performance_levels[0].mclk = ps->performance_levels[1].mclk;
+	} else {
+		if (ps->performance_levels[1].mclk < ps->performance_levels[0].mclk)
+			ps->performance_levels[1].mclk = ps->performance_levels[0].mclk;
+	}
+}
+
+static int ci_set_thermal_temperature_range(struct radeon_device *rdev,
+					    int min_temp, int max_temp)
+{
+	int low_temp = 0 * 1000;
+	int high_temp = 255 * 1000;
+	u32 tmp;
+
+	if (low_temp < min_temp)
+		low_temp = min_temp;
+	if (high_temp > max_temp)
+		high_temp = max_temp;
+	if (high_temp < low_temp) {
+		DRM_ERROR("invalid thermal range: %d - %d\n", low_temp, high_temp);
+		return -EINVAL;
+	}
+
+	tmp = RREG32_SMC(CG_THERMAL_INT);
+	tmp &= ~(CI_DIG_THERM_INTH_MASK | CI_DIG_THERM_INTL_MASK);
+	tmp |= CI_DIG_THERM_INTH(high_temp / 1000) |
+		CI_DIG_THERM_INTL(low_temp / 1000);
+	WREG32_SMC(CG_THERMAL_INT, tmp);
+
+#if 0
+	/* XXX: need to figure out how to handle this properly */
+	tmp = RREG32_SMC(CG_THERMAL_CTRL);
+	tmp &= DIG_THERM_DPM_MASK;
+	tmp |= DIG_THERM_DPM(high_temp / 1000);
+	WREG32_SMC(CG_THERMAL_CTRL, tmp);
+#endif
+
+	return 0;
+}
+
+#if 0
+static int ci_read_smc_soft_register(struct radeon_device *rdev,
+				     u16 reg_offset, u32 *value)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+
+	return ci_read_smc_sram_dword(rdev,
+				      pi->soft_regs_start + reg_offset,
+				      value, pi->sram_end);
+}
+#endif
+
+static int ci_write_smc_soft_register(struct radeon_device *rdev,
+				      u16 reg_offset, u32 value)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+
+	return ci_write_smc_sram_dword(rdev,
+				       pi->soft_regs_start + reg_offset,
+				       value, pi->sram_end);
+}
+
+static void ci_init_fps_limits(struct radeon_device *rdev)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	SMU7_Discrete_DpmTable *table = &pi->smc_state_table;
+
+	if (pi->caps_fps) {
+		u16 tmp;
+
+		tmp = 45;
+		table->FpsHighT = cpu_to_be16(tmp);
+
+		tmp = 30;
+		table->FpsLowT = cpu_to_be16(tmp);
+	}
+}
+
+static int ci_update_sclk_t(struct radeon_device *rdev)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	int ret = 0;
+	u32 low_sclk_interrupt_t = 0;
+
+	if (pi->caps_sclk_throttle_low_notification) {
+		low_sclk_interrupt_t = cpu_to_be32(pi->low_sclk_interrupt_t);
+
+		ret = ci_copy_bytes_to_smc(rdev,
+					   pi->dpm_table_start +
+					   offsetof(SMU7_Discrete_DpmTable, LowSclkInterruptT),
+					   (u8 *)&low_sclk_interrupt_t,
+					   sizeof(u32), pi->sram_end);
+
+	}
+
+	return ret;
+}
+
+static void ci_get_leakage_voltages(struct radeon_device *rdev)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	u16 leakage_id, virtual_voltage_id;
+	u16 vddc, vddci;
+	int i;
+
+	pi->vddc_leakage.count = 0;
+	pi->vddci_leakage.count = 0;
+
+	if (radeon_atom_get_leakage_id_from_vbios(rdev, &leakage_id) == 0) {
+		for (i = 0; i < CISLANDS_MAX_LEAKAGE_COUNT; i++) {
+			virtual_voltage_id = ATOM_VIRTUAL_VOLTAGE_ID0 + i;
+			if (radeon_atom_get_leakage_vddc_based_on_leakage_params(rdev, &vddc, &vddci,
+										 virtual_voltage_id,
+										 leakage_id) == 0) {
+				if (vddc != 0 && vddc != virtual_voltage_id) {
+					pi->vddc_leakage.actual_voltage[pi->vddc_leakage.count] = vddc;
+					pi->vddc_leakage.leakage_id[pi->vddc_leakage.count] = virtual_voltage_id;
+					pi->vddc_leakage.count++;
+				}
+				if (vddci != 0 && vddci != virtual_voltage_id) {
+					pi->vddci_leakage.actual_voltage[pi->vddci_leakage.count] = vddci;
+					pi->vddci_leakage.leakage_id[pi->vddci_leakage.count] = virtual_voltage_id;
+					pi->vddci_leakage.count++;
+				}
+			}
+		}
+	}
+}
+
+static void ci_set_dpm_event_sources(struct radeon_device *rdev, u32 sources)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	bool want_thermal_protection;
+	enum radeon_dpm_event_src dpm_event_src;
+	u32 tmp;
+
+	switch (sources) {
+	case 0:
+	default:
+		want_thermal_protection = false;
+		break;
+	case (1 << RADEON_DPM_AUTO_THROTTLE_SRC_THERMAL):
+		want_thermal_protection = true;
+		dpm_event_src = RADEON_DPM_EVENT_SRC_DIGITAL;
+		break;
+	case (1 << RADEON_DPM_AUTO_THROTTLE_SRC_EXTERNAL):
+		want_thermal_protection = true;
+		dpm_event_src = RADEON_DPM_EVENT_SRC_EXTERNAL;
+		break;
+	case ((1 << RADEON_DPM_AUTO_THROTTLE_SRC_EXTERNAL) |
+	      (1 << RADEON_DPM_AUTO_THROTTLE_SRC_THERMAL)):
+		want_thermal_protection = true;
+		dpm_event_src = RADEON_DPM_EVENT_SRC_DIGIAL_OR_EXTERNAL;
+		break;
+	}
+
+	if (want_thermal_protection) {
+#if 0
+		/* XXX: need to figure out how to handle this properly */
+		tmp = RREG32_SMC(CG_THERMAL_CTRL);
+		tmp &= DPM_EVENT_SRC_MASK;
+		tmp |= DPM_EVENT_SRC(dpm_event_src);
+		WREG32_SMC(CG_THERMAL_CTRL, tmp);
+#endif
+
+		tmp = RREG32_SMC(GENERAL_PWRMGT);
+		if (pi->thermal_protection)
+			tmp &= ~THERMAL_PROTECTION_DIS;
+		else
+			tmp |= THERMAL_PROTECTION_DIS;
+		WREG32_SMC(GENERAL_PWRMGT, tmp);
+	} else {
+		tmp = RREG32_SMC(GENERAL_PWRMGT);
+		tmp |= THERMAL_PROTECTION_DIS;
+		WREG32_SMC(GENERAL_PWRMGT, tmp);
+	}
+}
+
+static void ci_enable_auto_throttle_source(struct radeon_device *rdev,
+					   enum radeon_dpm_auto_throttle_src source,
+					   bool enable)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+
+	if (enable) {
+		if (!(pi->active_auto_throttle_sources & (1 << source))) {
+			pi->active_auto_throttle_sources |= 1 << source;
+			ci_set_dpm_event_sources(rdev, pi->active_auto_throttle_sources);
+		}
+	} else {
+		if (pi->active_auto_throttle_sources & (1 << source)) {
+			pi->active_auto_throttle_sources &= ~(1 << source);
+			ci_set_dpm_event_sources(rdev, pi->active_auto_throttle_sources);
+		}
+	}
+}
+
+static void ci_enable_vr_hot_gpio_interrupt(struct radeon_device *rdev)
+{
+	if (rdev->pm.dpm.platform_caps & ATOM_PP_PLATFORM_CAP_REGULATOR_HOT)
+		ci_send_msg_to_smc(rdev, PPSMC_MSG_EnableVRHotGPIOInterrupt);
+}
+
+static int ci_unfreeze_sclk_mclk_dpm(struct radeon_device *rdev)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	PPSMC_Result smc_result;
+
+	if (!pi->need_update_smu7_dpm_table)
+		return 0;
+
+	if ((!pi->sclk_dpm_key_disabled) &&
+	    (pi->need_update_smu7_dpm_table & (DPMTABLE_OD_UPDATE_SCLK | DPMTABLE_UPDATE_SCLK))) {
+		smc_result = ci_send_msg_to_smc(rdev, PPSMC_MSG_SCLKDPM_UnfreezeLevel);
+		if (smc_result != PPSMC_Result_OK)
+			return -EINVAL;
+	}
+
+	if ((!pi->mclk_dpm_key_disabled) &&
+	    (pi->need_update_smu7_dpm_table & DPMTABLE_OD_UPDATE_MCLK)) {
+		smc_result = ci_send_msg_to_smc(rdev, PPSMC_MSG_MCLKDPM_UnfreezeLevel);
+		if (smc_result != PPSMC_Result_OK)
+			return -EINVAL;
+	}
+
+	pi->need_update_smu7_dpm_table = 0;
+	return 0;
+}
+
+static int ci_enable_sclk_mclk_dpm(struct radeon_device *rdev, bool enable)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	PPSMC_Result smc_result;
+
+	if (enable) {
+		if (!pi->sclk_dpm_key_disabled) {
+			smc_result = ci_send_msg_to_smc(rdev, PPSMC_MSG_DPM_Enable);
+			if (smc_result != PPSMC_Result_OK)
+				return -EINVAL;
+		}
+
+		if (!pi->mclk_dpm_key_disabled) {
+			smc_result = ci_send_msg_to_smc(rdev, PPSMC_MSG_MCLKDPM_Enable);
+			if (smc_result != PPSMC_Result_OK)
+				return -EINVAL;
+
+			WREG32_P(MC_SEQ_CNTL_3, CAC_EN, ~CAC_EN);
+
+			WREG32_SMC(LCAC_MC0_CNTL, 0x05);
+			WREG32_SMC(LCAC_MC1_CNTL, 0x05);
+			WREG32_SMC(LCAC_CPL_CNTL, 0x100005);
+
+			udelay(10);
+
+			WREG32_SMC(LCAC_MC0_CNTL, 0x400005);
+			WREG32_SMC(LCAC_MC1_CNTL, 0x400005);
+			WREG32_SMC(LCAC_CPL_CNTL, 0x500005);
+		}
+	} else {
+		if (!pi->sclk_dpm_key_disabled) {
+			smc_result = ci_send_msg_to_smc(rdev, PPSMC_MSG_DPM_Disable);
+			if (smc_result != PPSMC_Result_OK)
+				return -EINVAL;
+		}
+
+		if (!pi->mclk_dpm_key_disabled) {
+			smc_result = ci_send_msg_to_smc(rdev, PPSMC_MSG_MCLKDPM_Disable);
+			if (smc_result != PPSMC_Result_OK)
+				return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
+static int ci_start_dpm(struct radeon_device *rdev)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	PPSMC_Result smc_result;
+	int ret;
+	u32 tmp;
+
+	tmp = RREG32_SMC(GENERAL_PWRMGT);
+	tmp |= GLOBAL_PWRMGT_EN;
+	WREG32_SMC(GENERAL_PWRMGT, tmp);
+
+	tmp = RREG32_SMC(SCLK_PWRMGT_CNTL);
+	tmp |= DYNAMIC_PM_EN;
+	WREG32_SMC(SCLK_PWRMGT_CNTL, tmp);
+
+	ci_write_smc_soft_register(rdev, offsetof(SMU7_SoftRegisters, VoltageChangeTimeout), 0x1000);
+
+	WREG32_P(BIF_LNCNT_RESET, 0, ~RESET_LNCNT_EN);
+
+	smc_result = ci_send_msg_to_smc(rdev, PPSMC_MSG_Voltage_Cntl_Enable);
+	if (smc_result != PPSMC_Result_OK)
+		return -EINVAL;
+
+	ret = ci_enable_sclk_mclk_dpm(rdev, true);
+	if (ret)
+		return ret;
+
+	if (!pi->pcie_dpm_key_disabled) {
+		smc_result = ci_send_msg_to_smc(rdev, PPSMC_MSG_PCIeDPM_Enable);
+		if (smc_result != PPSMC_Result_OK)
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int ci_freeze_sclk_mclk_dpm(struct radeon_device *rdev)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	PPSMC_Result smc_result;
+
+	if (!pi->need_update_smu7_dpm_table)
+		return 0;
+
+	if ((!pi->sclk_dpm_key_disabled) &&
+	    (pi->need_update_smu7_dpm_table & (DPMTABLE_OD_UPDATE_SCLK | DPMTABLE_UPDATE_SCLK))) {
+		smc_result = ci_send_msg_to_smc(rdev, PPSMC_MSG_SCLKDPM_FreezeLevel);
+		if (smc_result != PPSMC_Result_OK)
+			return -EINVAL;
+	}
+
+	if ((!pi->mclk_dpm_key_disabled) &&
+	    (pi->need_update_smu7_dpm_table & DPMTABLE_OD_UPDATE_MCLK)) {
+		smc_result = ci_send_msg_to_smc(rdev, PPSMC_MSG_MCLKDPM_FreezeLevel);
+		if (smc_result != PPSMC_Result_OK)
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int ci_stop_dpm(struct radeon_device *rdev)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	PPSMC_Result smc_result;
+	int ret;
+	u32 tmp;
+
+	tmp = RREG32_SMC(GENERAL_PWRMGT);
+	tmp &= ~GLOBAL_PWRMGT_EN;
+	WREG32_SMC(GENERAL_PWRMGT, tmp);
+
+	tmp = RREG32(SCLK_PWRMGT_CNTL);
+	tmp &= ~DYNAMIC_PM_EN;
+	WREG32_SMC(SCLK_PWRMGT_CNTL, tmp);
+
+	if (!pi->pcie_dpm_key_disabled) {
+		smc_result = ci_send_msg_to_smc(rdev, PPSMC_MSG_PCIeDPM_Disable);
+		if (smc_result != PPSMC_Result_OK)
+			return -EINVAL;
+	}
+
+	ret = ci_enable_sclk_mclk_dpm(rdev, false);
+	if (ret)
+		return ret;
+
+	smc_result = ci_send_msg_to_smc(rdev, PPSMC_MSG_Voltage_Cntl_Disable);
+	if (smc_result != PPSMC_Result_OK)
+		return -EINVAL;
+
+	return 0;
+}
+
+static void ci_enable_sclk_control(struct radeon_device *rdev, bool enable)
+{
+	u32 tmp = RREG32_SMC(SCLK_PWRMGT_CNTL);
+
+	if (enable)
+		tmp &= ~SCLK_PWRMGT_OFF;
+	else
+		tmp |= SCLK_PWRMGT_OFF;
+	WREG32_SMC(SCLK_PWRMGT_CNTL, tmp);
+}
+
+#if 0
+static int ci_notify_hw_of_power_source(struct radeon_device *rdev,
+					bool ac_power)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	struct radeon_cac_tdp_table *cac_tdp_table =
+		rdev->pm.dpm.dyn_state.cac_tdp_table;
+	u32 power_limit;
+
+	if (ac_power)
+		power_limit = (u32)(cac_tdp_table->maximum_power_delivery_limit * 256);
+	else
+		power_limit = (u32)(cac_tdp_table->battery_power_limit * 256);
+
+        ci_set_power_limit(rdev, power_limit);
+
+	if (pi->caps_automatic_dc_transition) {
+		if (ac_power)
+			ci_send_msg_to_smc(rdev, PPSMC_MSG_RunningOnAC);
+		else
+			ci_send_msg_to_smc(rdev, PPSMC_MSG_Remove_DC_Clamp);
+	}
+
+	return 0;
+}
+#endif
+
+static PPSMC_Result ci_send_msg_to_smc_with_parameter(struct radeon_device *rdev,
+						      PPSMC_Msg msg, u32 parameter)
+{
+	WREG32(SMC_MSG_ARG_0, parameter);
+	return ci_send_msg_to_smc(rdev, msg);
+}
+
+static PPSMC_Result ci_send_msg_to_smc_return_parameter(struct radeon_device *rdev,
+							PPSMC_Msg msg, u32 *parameter)
+{
+	PPSMC_Result smc_result;
+
+	smc_result = ci_send_msg_to_smc(rdev, msg);
+
+	if ((smc_result == PPSMC_Result_OK) && parameter)
+		*parameter = RREG32(SMC_MSG_ARG_0);
+
+	return smc_result;
+}
+
+static int ci_dpm_force_state_sclk(struct radeon_device *rdev, u32 n)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+
+	if (!pi->sclk_dpm_key_disabled) {
+		PPSMC_Result smc_result =
+			ci_send_msg_to_smc_with_parameter(rdev, PPSMC_MSG_DPM_ForceState, n);
+		if (smc_result != PPSMC_Result_OK)
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int ci_dpm_force_state_mclk(struct radeon_device *rdev, u32 n)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+
+	if (!pi->mclk_dpm_key_disabled) {
+		PPSMC_Result smc_result =
+			ci_send_msg_to_smc_with_parameter(rdev, PPSMC_MSG_MCLKDPM_ForceState, n);
+		if (smc_result != PPSMC_Result_OK)
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int ci_dpm_force_state_pcie(struct radeon_device *rdev, u32 n)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+
+	if (!pi->pcie_dpm_key_disabled) {
+		PPSMC_Result smc_result =
+			ci_send_msg_to_smc_with_parameter(rdev, PPSMC_MSG_PCIeDPM_ForceLevel, n);
+		if (smc_result != PPSMC_Result_OK)
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int ci_set_power_limit(struct radeon_device *rdev, u32 n)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+
+	if (pi->power_containment_features & POWERCONTAINMENT_FEATURE_PkgPwrLimit) {
+		PPSMC_Result smc_result =
+			ci_send_msg_to_smc_with_parameter(rdev, PPSMC_MSG_PkgPwrSetLimit, n);
+		if (smc_result != PPSMC_Result_OK)
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int ci_set_overdrive_target_tdp(struct radeon_device *rdev,
+				       u32 target_tdp)
+{
+	PPSMC_Result smc_result =
+		ci_send_msg_to_smc_with_parameter(rdev, PPSMC_MSG_OverDriveSetTargetTdp, target_tdp);
+	if (smc_result != PPSMC_Result_OK)
+		return -EINVAL;
+	return 0;
+}
+
+static int ci_set_boot_state(struct radeon_device *rdev)
+{
+	return ci_enable_sclk_mclk_dpm(rdev, false);
+}
+
+static u32 ci_get_average_sclk_freq(struct radeon_device *rdev)
+{
+	u32 sclk_freq;
+	PPSMC_Result smc_result =
+		ci_send_msg_to_smc_return_parameter(rdev,
+						    PPSMC_MSG_API_GetSclkFrequency,
+						    &sclk_freq);
+	if (smc_result != PPSMC_Result_OK)
+		sclk_freq = 0;
+
+	return sclk_freq;
+}
+
+static u32 ci_get_average_mclk_freq(struct radeon_device *rdev)
+{
+	u32 mclk_freq;
+	PPSMC_Result smc_result =
+		ci_send_msg_to_smc_return_parameter(rdev,
+						    PPSMC_MSG_API_GetMclkFrequency,
+						    &mclk_freq);
+	if (smc_result != PPSMC_Result_OK)
+		mclk_freq = 0;
+
+	return mclk_freq;
+}
+
+static void ci_dpm_start_smc(struct radeon_device *rdev)
+{
+	int i;
+
+	ci_program_jump_on_start(rdev);
+	ci_start_smc_clock(rdev);
+	ci_start_smc(rdev);
+	for (i = 0; i < rdev->usec_timeout; i++) {
+		if (RREG32_SMC(FIRMWARE_FLAGS) & INTERRUPTS_ENABLED)
+			break;
+	}
+}
+
+static void ci_dpm_stop_smc(struct radeon_device *rdev)
+{
+	ci_reset_smc(rdev);
+	ci_stop_smc_clock(rdev);
+}
+
+static int ci_process_firmware_header(struct radeon_device *rdev)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	u32 tmp;
+	int ret;
+
+	ret = ci_read_smc_sram_dword(rdev,
+				     SMU7_FIRMWARE_HEADER_LOCATION +
+				     offsetof(SMU7_Firmware_Header, DpmTable),
+				     &tmp, pi->sram_end);
+	if (ret)
+		return ret;
+
+	pi->dpm_table_start = tmp;
+
+	ret = ci_read_smc_sram_dword(rdev,
+				     SMU7_FIRMWARE_HEADER_LOCATION +
+				     offsetof(SMU7_Firmware_Header, SoftRegisters),
+				     &tmp, pi->sram_end);
+	if (ret)
+		return ret;
+
+	pi->soft_regs_start = tmp;
+
+	ret = ci_read_smc_sram_dword(rdev,
+				     SMU7_FIRMWARE_HEADER_LOCATION +
+				     offsetof(SMU7_Firmware_Header, mcRegisterTable),
+				     &tmp, pi->sram_end);
+	if (ret)
+		return ret;
+
+	pi->mc_reg_table_start = tmp;
+
+	ret = ci_read_smc_sram_dword(rdev,
+				     SMU7_FIRMWARE_HEADER_LOCATION +
+				     offsetof(SMU7_Firmware_Header, FanTable),
+				     &tmp, pi->sram_end);
+	if (ret)
+		return ret;
+
+	pi->fan_table_start = tmp;
+
+	ret = ci_read_smc_sram_dword(rdev,
+				     SMU7_FIRMWARE_HEADER_LOCATION +
+				     offsetof(SMU7_Firmware_Header, mcArbDramTimingTable),
+				     &tmp, pi->sram_end);
+	if (ret)
+		return ret;
+
+	pi->arb_table_start = tmp;
+
+	return 0;
+}
+
+static void ci_read_clock_registers(struct radeon_device *rdev)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+
+	pi->clock_registers.cg_spll_func_cntl =
+		RREG32_SMC(CG_SPLL_FUNC_CNTL);
+	pi->clock_registers.cg_spll_func_cntl_2 =
+		RREG32_SMC(CG_SPLL_FUNC_CNTL_2);
+	pi->clock_registers.cg_spll_func_cntl_3 =
+		RREG32_SMC(CG_SPLL_FUNC_CNTL_3);
+	pi->clock_registers.cg_spll_func_cntl_4 =
+		RREG32_SMC(CG_SPLL_FUNC_CNTL_4);
+	pi->clock_registers.cg_spll_spread_spectrum =
+		RREG32_SMC(CG_SPLL_SPREAD_SPECTRUM);
+	pi->clock_registers.cg_spll_spread_spectrum_2 =
+		RREG32_SMC(CG_SPLL_SPREAD_SPECTRUM_2);
+	pi->clock_registers.dll_cntl = RREG32(DLL_CNTL);
+	pi->clock_registers.mclk_pwrmgt_cntl = RREG32(MCLK_PWRMGT_CNTL);
+	pi->clock_registers.mpll_ad_func_cntl = RREG32(MPLL_AD_FUNC_CNTL);
+	pi->clock_registers.mpll_dq_func_cntl = RREG32(MPLL_DQ_FUNC_CNTL);
+	pi->clock_registers.mpll_func_cntl = RREG32(MPLL_FUNC_CNTL);
+	pi->clock_registers.mpll_func_cntl_1 = RREG32(MPLL_FUNC_CNTL_1);
+	pi->clock_registers.mpll_func_cntl_2 = RREG32(MPLL_FUNC_CNTL_2);
+	pi->clock_registers.mpll_ss1 = RREG32(MPLL_SS1);
+	pi->clock_registers.mpll_ss2 = RREG32(MPLL_SS2);
+}
+
+static void ci_init_sclk_t(struct radeon_device *rdev)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+
+	pi->low_sclk_interrupt_t = 0;
+}
+
+static void ci_enable_thermal_protection(struct radeon_device *rdev,
+					 bool enable)
+{
+	u32 tmp = RREG32_SMC(GENERAL_PWRMGT);
+
+	if (enable)
+		tmp &= ~THERMAL_PROTECTION_DIS;
+	else
+		tmp |= THERMAL_PROTECTION_DIS;
+	WREG32_SMC(GENERAL_PWRMGT, tmp);
+}
+
+static void ci_enable_acpi_power_management(struct radeon_device *rdev)
+{
+	u32 tmp = RREG32_SMC(GENERAL_PWRMGT);
+
+	tmp |= STATIC_PM_EN;
+
+	WREG32_SMC(GENERAL_PWRMGT, tmp);
+}
+
+#if 0
+static int ci_enter_ulp_state(struct radeon_device *rdev)
+{
+
+	WREG32(SMC_MESSAGE_0, PPSMC_MSG_SwitchToMinimumPower);
+
+	udelay(25000);
+
+	return 0;
+}
+
+static int ci_exit_ulp_state(struct radeon_device *rdev)
+{
+	int i;
+
+	WREG32(SMC_MESSAGE_0, PPSMC_MSG_ResumeFromMinimumPower);
+
+	udelay(7000);
+
+	for (i = 0; i < rdev->usec_timeout; i++) {
+		if (RREG32(SMC_RESP_0) == 1)
+			break;
+		udelay(1000);
+	}
+
+	return 0;
+}
+#endif
+
+static int ci_notify_smc_display_change(struct radeon_device *rdev,
+					bool has_display)
+{
+	PPSMC_Msg msg = has_display ? PPSMC_MSG_HasDisplay : PPSMC_MSG_NoDisplay;
+
+	return (ci_send_msg_to_smc(rdev, msg) == PPSMC_Result_OK) ?  0 : -EINVAL;
+}
+
+static int ci_enable_ds_master_switch(struct radeon_device *rdev,
+				      bool enable)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+
+	if (enable) {
+		if (pi->caps_sclk_ds) {
+			if (ci_send_msg_to_smc(rdev, PPSMC_MSG_MASTER_DeepSleep_ON) != PPSMC_Result_OK)
+				return -EINVAL;
+		} else {
+			if (ci_send_msg_to_smc(rdev, PPSMC_MSG_MASTER_DeepSleep_OFF) != PPSMC_Result_OK)
+				return -EINVAL;
+		}
+	} else {
+		if (pi->caps_sclk_ds) {
+			if (ci_send_msg_to_smc(rdev, PPSMC_MSG_MASTER_DeepSleep_OFF) != PPSMC_Result_OK)
+				return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
+static void ci_program_display_gap(struct radeon_device *rdev)
+{
+	u32 tmp = RREG32_SMC(CG_DISPLAY_GAP_CNTL);
+	u32 pre_vbi_time_in_us;
+	u32 frame_time_in_us;
+	u32 ref_clock = rdev->clock.spll.reference_freq;
+	u32 refresh_rate = r600_dpm_get_vrefresh(rdev);
+	u32 vblank_time = r600_dpm_get_vblank_time(rdev);
+
+	tmp &= ~DISP_GAP_MASK;
+	if (rdev->pm.dpm.new_active_crtc_count > 0)
+		tmp |= DISP_GAP(R600_PM_DISPLAY_GAP_VBLANK_OR_WM);
+	else
+		tmp |= DISP_GAP(R600_PM_DISPLAY_GAP_IGNORE);
+	WREG32_SMC(CG_DISPLAY_GAP_CNTL, tmp);
+
+	if (refresh_rate == 0)
+		refresh_rate = 60;
+	if (vblank_time == 0xffffffff)
+		vblank_time = 500;
+	frame_time_in_us = 1000000 / refresh_rate;
+	pre_vbi_time_in_us =
+		frame_time_in_us - 200 - vblank_time;
+	tmp = pre_vbi_time_in_us * (ref_clock / 100);
+
+	WREG32_SMC(CG_DISPLAY_GAP_CNTL2, tmp);
+	ci_write_smc_soft_register(rdev, offsetof(SMU7_SoftRegisters, PreVBlankGap), 0x64);
+	ci_write_smc_soft_register(rdev, offsetof(SMU7_SoftRegisters, VBlankTimeout), (frame_time_in_us - pre_vbi_time_in_us));
+
+
+	ci_notify_smc_display_change(rdev, (rdev->pm.dpm.new_active_crtc_count == 1));
+
+}
+
+static void ci_enable_spread_spectrum(struct radeon_device *rdev, bool enable)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	u32 tmp;
+
+	if (enable) {
+		if (pi->caps_sclk_ss_support) {
+			tmp = RREG32_SMC(GENERAL_PWRMGT);
+			tmp |= DYN_SPREAD_SPECTRUM_EN;
+			WREG32_SMC(GENERAL_PWRMGT, tmp);
+		}
+	} else {
+		tmp = RREG32_SMC(CG_SPLL_SPREAD_SPECTRUM);
+		tmp &= ~SSEN;
+		WREG32_SMC(CG_SPLL_SPREAD_SPECTRUM, tmp);
+
+		tmp = RREG32_SMC(GENERAL_PWRMGT);
+		tmp &= ~DYN_SPREAD_SPECTRUM_EN;
+		WREG32_SMC(GENERAL_PWRMGT, tmp);
+	}
+}
+
+static void ci_program_sstp(struct radeon_device *rdev)
+{
+	WREG32_SMC(CG_SSP, (SSTU(R600_SSTU_DFLT) | SST(R600_SST_DFLT)));
+}
+
+static void ci_enable_display_gap(struct radeon_device *rdev)
+{
+	u32 tmp = RREG32_SMC(CG_DISPLAY_GAP_CNTL);
+
+        tmp &= ~(DISP_GAP_MASK | DISP_GAP_MCHG_MASK);
+        tmp |= (DISP_GAP(R600_PM_DISPLAY_GAP_IGNORE) |
+                DISP_GAP_MCHG(R600_PM_DISPLAY_GAP_VBLANK));
+
+	WREG32_SMC(CG_DISPLAY_GAP_CNTL, tmp);
+}
+
+static void ci_program_vc(struct radeon_device *rdev)
+{
+	u32 tmp;
+
+	tmp = RREG32_SMC(SCLK_PWRMGT_CNTL);
+	tmp &= ~(RESET_SCLK_CNT | RESET_BUSY_CNT);
+	WREG32_SMC(SCLK_PWRMGT_CNTL, tmp);
+
+	WREG32_SMC(CG_FTV_0, CISLANDS_VRC_DFLT0);
+	WREG32_SMC(CG_FTV_1, CISLANDS_VRC_DFLT1);
+	WREG32_SMC(CG_FTV_2, CISLANDS_VRC_DFLT2);
+	WREG32_SMC(CG_FTV_3, CISLANDS_VRC_DFLT3);
+	WREG32_SMC(CG_FTV_4, CISLANDS_VRC_DFLT4);
+	WREG32_SMC(CG_FTV_5, CISLANDS_VRC_DFLT5);
+	WREG32_SMC(CG_FTV_6, CISLANDS_VRC_DFLT6);
+	WREG32_SMC(CG_FTV_7, CISLANDS_VRC_DFLT7);
+}
+
+static void ci_clear_vc(struct radeon_device *rdev)
+{
+	u32 tmp;
+
+	tmp = RREG32_SMC(SCLK_PWRMGT_CNTL);
+	tmp |= (RESET_SCLK_CNT | RESET_BUSY_CNT);
+	WREG32_SMC(SCLK_PWRMGT_CNTL, tmp);
+
+	WREG32_SMC(CG_FTV_0, 0);
+	WREG32_SMC(CG_FTV_1, 0);
+	WREG32_SMC(CG_FTV_2, 0);
+	WREG32_SMC(CG_FTV_3, 0);
+	WREG32_SMC(CG_FTV_4, 0);
+	WREG32_SMC(CG_FTV_5, 0);
+	WREG32_SMC(CG_FTV_6, 0);
+	WREG32_SMC(CG_FTV_7, 0);
+}
+
+static int ci_upload_firmware(struct radeon_device *rdev)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	int i, ret;
+
+	for (i = 0; i < rdev->usec_timeout; i++) {
+		if (RREG32_SMC(RCU_UC_EVENTS) & BOOT_SEQ_DONE)
+			break;
+	}
+	WREG32_SMC(SMC_SYSCON_MISC_CNTL, 1);
+
+	ci_stop_smc_clock(rdev);
+	ci_reset_smc(rdev);
+
+	ret = ci_load_smc_ucode(rdev, pi->sram_end);
+
+	return ret;
+
+}
+
+static int ci_get_svi2_voltage_table(struct radeon_device *rdev,
+				     struct radeon_clock_voltage_dependency_table *voltage_dependency_table,
+				     struct atom_voltage_table *voltage_table)
+{
+	u32 i;
+
+	if (voltage_dependency_table == NULL)
+		return -EINVAL;
+
+	voltage_table->mask_low = 0;
+	voltage_table->phase_delay = 0;
+
+	voltage_table->count = voltage_dependency_table->count;
+	for (i = 0; i < voltage_table->count; i++) {
+		voltage_table->entries[i].value = voltage_dependency_table->entries[i].v;
+		voltage_table->entries[i].smio_low = 0;
+	}
+
+	return 0;
+}
+
+static int ci_construct_voltage_tables(struct radeon_device *rdev)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	int ret;
+
+	if (pi->voltage_control == CISLANDS_VOLTAGE_CONTROL_BY_GPIO) {
+		ret = radeon_atom_get_voltage_table(rdev, VOLTAGE_TYPE_VDDC,
+						    VOLTAGE_OBJ_GPIO_LUT,
+						    &pi->vddc_voltage_table);
+		if (ret)
+			return ret;
+	} else if (pi->voltage_control == CISLANDS_VOLTAGE_CONTROL_BY_SVID2) {
+		ret = ci_get_svi2_voltage_table(rdev,
+						&rdev->pm.dpm.dyn_state.vddc_dependency_on_mclk,
+						&pi->vddc_voltage_table);
+		if (ret)
+			return ret;
+	}
+
+	if (pi->vddc_voltage_table.count > SMU7_MAX_LEVELS_VDDC)
+		si_trim_voltage_table_to_fit_state_table(rdev, SMU7_MAX_LEVELS_VDDC,
+							 &pi->vddc_voltage_table);
+
+	if (pi->vddci_control == CISLANDS_VOLTAGE_CONTROL_BY_GPIO) {
+		ret = radeon_atom_get_voltage_table(rdev, VOLTAGE_TYPE_VDDCI,
+						    VOLTAGE_OBJ_GPIO_LUT,
+						    &pi->vddci_voltage_table);
+		if (ret)
+			return ret;
+	} else if (pi->vddci_control == CISLANDS_VOLTAGE_CONTROL_BY_SVID2) {
+		ret = ci_get_svi2_voltage_table(rdev,
+						&rdev->pm.dpm.dyn_state.vddci_dependency_on_mclk,
+						&pi->vddci_voltage_table);
+		if (ret)
+			return ret;
+	}
+
+	if (pi->vddci_voltage_table.count > SMU7_MAX_LEVELS_VDDCI)
+		si_trim_voltage_table_to_fit_state_table(rdev, SMU7_MAX_LEVELS_VDDCI,
+							 &pi->vddci_voltage_table);
+
+	if (pi->mvdd_control == CISLANDS_VOLTAGE_CONTROL_BY_GPIO) {
+		ret = radeon_atom_get_voltage_table(rdev, VOLTAGE_TYPE_MVDDC,
+						    VOLTAGE_OBJ_GPIO_LUT,
+						    &pi->mvdd_voltage_table);
+		if (ret)
+			return ret;
+	} else if (pi->mvdd_control == CISLANDS_VOLTAGE_CONTROL_BY_SVID2) {
+		ret = ci_get_svi2_voltage_table(rdev,
+						&rdev->pm.dpm.dyn_state.mvdd_dependency_on_mclk,
+						&pi->mvdd_voltage_table);
+		if (ret)
+			return ret;
+	}
+
+	if (pi->mvdd_voltage_table.count > SMU7_MAX_LEVELS_MVDD)
+		si_trim_voltage_table_to_fit_state_table(rdev, SMU7_MAX_LEVELS_MVDD,
+							 &pi->mvdd_voltage_table);
+
+	return 0;
+}
+
+static void ci_populate_smc_voltage_table(struct radeon_device *rdev,
+					  struct atom_voltage_table_entry *voltage_table,
+					  SMU7_Discrete_VoltageLevel *smc_voltage_table)
+{
+	int ret;
+
+	ret = ci_get_std_voltage_value_sidd(rdev, voltage_table,
+					    &smc_voltage_table->StdVoltageHiSidd,
+					    &smc_voltage_table->StdVoltageLoSidd);
+
+	if (ret) {
+		smc_voltage_table->StdVoltageHiSidd = voltage_table->value * VOLTAGE_SCALE;
+		smc_voltage_table->StdVoltageLoSidd = voltage_table->value * VOLTAGE_SCALE;
+	}
+
+	smc_voltage_table->Voltage = cpu_to_be16(voltage_table->value * VOLTAGE_SCALE);
+	smc_voltage_table->StdVoltageHiSidd =
+		cpu_to_be16(smc_voltage_table->StdVoltageHiSidd);
+	smc_voltage_table->StdVoltageLoSidd =
+		cpu_to_be16(smc_voltage_table->StdVoltageLoSidd);
+}
+
+static int ci_populate_smc_vddc_table(struct radeon_device *rdev,
+				      SMU7_Discrete_DpmTable *table)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	unsigned int count;
+
+	table->VddcLevelCount = pi->vddc_voltage_table.count;
+	for (count = 0; count < table->VddcLevelCount; count++) {
+		ci_populate_smc_voltage_table(rdev,
+					      &pi->vddc_voltage_table.entries[count],
+					      &table->VddcLevel[count]);
+
+		if (pi->voltage_control == CISLANDS_VOLTAGE_CONTROL_BY_GPIO)
+			table->VddcLevel[count].Smio |=
+				pi->vddc_voltage_table.entries[count].smio_low;
+		else
+			table->VddcLevel[count].Smio = 0;
+	}
+	table->VddcLevelCount = cpu_to_be32(table->VddcLevelCount);
+
+	return 0;
+}
+
+static int ci_populate_smc_vddci_table(struct radeon_device *rdev,
+				       SMU7_Discrete_DpmTable *table)
+{
+	unsigned int count;
+	struct ci_power_info *pi = ci_get_pi(rdev);
+
+	table->VddciLevelCount = pi->vddci_voltage_table.count;
+	for (count = 0; count < table->VddciLevelCount; count++) {
+		ci_populate_smc_voltage_table(rdev,
+					      &pi->vddci_voltage_table.entries[count],
+					      &table->VddciLevel[count]);
+
+		if (pi->vddci_control == CISLANDS_VOLTAGE_CONTROL_BY_GPIO)
+			table->VddciLevel[count].Smio |=
+				pi->vddci_voltage_table.entries[count].smio_low;
+		else
+			table->VddciLevel[count].Smio = 0;
+	}
+	table->VddciLevelCount = cpu_to_be32(table->VddciLevelCount);
+
+	return 0;
+}
+
+static int ci_populate_smc_mvdd_table(struct radeon_device *rdev,
+				      SMU7_Discrete_DpmTable *table)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	unsigned int count;
+
+	table->MvddLevelCount = pi->mvdd_voltage_table.count;
+	for (count = 0; count < table->MvddLevelCount; count++) {
+		ci_populate_smc_voltage_table(rdev,
+					      &pi->mvdd_voltage_table.entries[count],
+					      &table->MvddLevel[count]);
+
+		if (pi->mvdd_control == CISLANDS_VOLTAGE_CONTROL_BY_GPIO)
+			table->MvddLevel[count].Smio |=
+				pi->mvdd_voltage_table.entries[count].smio_low;
+		else
+			table->MvddLevel[count].Smio = 0;
+	}
+	table->MvddLevelCount = cpu_to_be32(table->MvddLevelCount);
+
+	return 0;
+}
+
+static int ci_populate_smc_voltage_tables(struct radeon_device *rdev,
+					  SMU7_Discrete_DpmTable *table)
+{
+	int ret;
+
+	ret = ci_populate_smc_vddc_table(rdev, table);
+	if (ret)
+		return ret;
+
+	ret = ci_populate_smc_vddci_table(rdev, table);
+	if (ret)
+		return ret;
+
+	ret = ci_populate_smc_mvdd_table(rdev, table);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static int ci_populate_mvdd_value(struct radeon_device *rdev, u32 mclk,
+				  SMU7_Discrete_VoltageLevel *voltage)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	u32 i = 0;
+
+	if (pi->mvdd_control != CISLANDS_VOLTAGE_CONTROL_NONE) {
+		for (i = 0; i < rdev->pm.dpm.dyn_state.mvdd_dependency_on_mclk.count; i++) {
+			if (mclk <= rdev->pm.dpm.dyn_state.mvdd_dependency_on_mclk.entries[i].clk) {
+				voltage->Voltage = pi->mvdd_voltage_table.entries[i].value;
+				break;
+			}
+		}
+
+		if (i >= rdev->pm.dpm.dyn_state.mvdd_dependency_on_mclk.count)
+			return -EINVAL;
+	}
+
+	return -EINVAL;
+}
+
+static int ci_get_std_voltage_value_sidd(struct radeon_device *rdev,
+					 struct atom_voltage_table_entry *voltage_table,
+					 u16 *std_voltage_hi_sidd, u16 *std_voltage_lo_sidd)
+{
+	u16 v_index, idx;
+	bool voltage_found = false;
+	*std_voltage_hi_sidd = voltage_table->value * VOLTAGE_SCALE;
+	*std_voltage_lo_sidd = voltage_table->value * VOLTAGE_SCALE;
+
+	if (rdev->pm.dpm.dyn_state.vddc_dependency_on_sclk.entries == NULL)
+		return -EINVAL;
+
+	if (rdev->pm.dpm.dyn_state.cac_leakage_table.entries) {
+		for (v_index = 0; (u32)v_index < rdev->pm.dpm.dyn_state.vddc_dependency_on_sclk.count; v_index++) {
+			if (voltage_table->value ==
+			    rdev->pm.dpm.dyn_state.vddc_dependency_on_sclk.entries[v_index].v) {
+				voltage_found = true;
+				if ((u32)v_index < rdev->pm.dpm.dyn_state.cac_leakage_table.count)
+					idx = v_index;
+				else
+					idx = rdev->pm.dpm.dyn_state.cac_leakage_table.count - 1;
+				*std_voltage_lo_sidd =
+					rdev->pm.dpm.dyn_state.cac_leakage_table.entries[idx].vddc * VOLTAGE_SCALE;
+				*std_voltage_hi_sidd =
+					rdev->pm.dpm.dyn_state.cac_leakage_table.entries[idx].leakage * VOLTAGE_SCALE;
+				break;
+			}
+		}
+
+		if (!voltage_found) {
+			for (v_index = 0; (u32)v_index < rdev->pm.dpm.dyn_state.vddc_dependency_on_sclk.count; v_index++) {
+				if (voltage_table->value <=
+				    rdev->pm.dpm.dyn_state.vddc_dependency_on_sclk.entries[v_index].v) {
+					voltage_found = true;
+					if ((u32)v_index < rdev->pm.dpm.dyn_state.cac_leakage_table.count)
+						idx = v_index;
+					else
+						idx = rdev->pm.dpm.dyn_state.cac_leakage_table.count - 1;
+					*std_voltage_lo_sidd =
+						rdev->pm.dpm.dyn_state.cac_leakage_table.entries[idx].vddc * VOLTAGE_SCALE;
+					*std_voltage_hi_sidd =
+						rdev->pm.dpm.dyn_state.cac_leakage_table.entries[idx].leakage * VOLTAGE_SCALE;
+					break;
+				}
+			}
+		}
+	}
+
+	return 0;
+}
+
+static void ci_populate_phase_value_based_on_sclk(struct radeon_device *rdev,
+						  const struct radeon_phase_shedding_limits_table *limits,
+						  u32 sclk,
+						  u32 *phase_shedding)
+{
+	unsigned int i;
+
+	*phase_shedding = 1;
+
+	for (i = 0; i < limits->count; i++) {
+		if (sclk < limits->entries[i].sclk) {
+			*phase_shedding = i;
+			break;
+		}
+	}
+}
+
+static void ci_populate_phase_value_based_on_mclk(struct radeon_device *rdev,
+						  const struct radeon_phase_shedding_limits_table *limits,
+						  u32 mclk,
+						  u32 *phase_shedding)
+{
+	unsigned int i;
+
+	*phase_shedding = 1;
+
+	for (i = 0; i < limits->count; i++) {
+		if (mclk < limits->entries[i].mclk) {
+			*phase_shedding = i;
+			break;
+		}
+	}
+}
+
+static int ci_init_arb_table_index(struct radeon_device *rdev)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	u32 tmp;
+	int ret;
+
+	ret = ci_read_smc_sram_dword(rdev, pi->arb_table_start,
+				     &tmp, pi->sram_end);
+	if (ret)
+		return ret;
+
+	tmp &= 0x00FFFFFF;
+	tmp |= MC_CG_ARB_FREQ_F1 << 24;
+
+	return ci_write_smc_sram_dword(rdev, pi->arb_table_start,
+				       tmp, pi->sram_end);
+}
+
+static int ci_get_dependency_volt_by_clk(struct radeon_device *rdev,
+					 struct radeon_clock_voltage_dependency_table *allowed_clock_voltage_table,
+					 u32 clock, u32 *voltage)
+{
+	u32 i = 0;
+
+	if (allowed_clock_voltage_table->count == 0)
+		return -EINVAL;
+
+	for (i = 0; i < allowed_clock_voltage_table->count; i++) {
+		if (allowed_clock_voltage_table->entries[i].clk >= clock) {
+			*voltage = allowed_clock_voltage_table->entries[i].v;
+			return 0;
+		}
+	}
+
+	*voltage = allowed_clock_voltage_table->entries[i-1].v;
+
+	return 0;
+}
+
+static u8 ci_get_sleep_divider_id_from_clock(struct radeon_device *rdev,
+					     u32 sclk, u32 min_sclk_in_sr)
+{
+	u32 i;
+	u32 tmp;
+	u32 min = (min_sclk_in_sr > CISLAND_MINIMUM_ENGINE_CLOCK) ?
+		min_sclk_in_sr : CISLAND_MINIMUM_ENGINE_CLOCK;
+
+	if (sclk < min)
+		return 0;
+
+	for (i = CISLAND_MAX_DEEPSLEEP_DIVIDER_ID;  ; i--) {
+		tmp = sclk / (1 << i);
+		if (tmp >= min || i == 0)
+			break;
+	}
+
+	return (u8)i;
+}
+
+static int ci_initial_switch_from_arb_f0_to_f1(struct radeon_device *rdev)
+{
+	return ni_copy_and_switch_arb_sets(rdev, MC_CG_ARB_FREQ_F0, MC_CG_ARB_FREQ_F1);
+}
+
+static int ci_reset_to_default(struct radeon_device *rdev)
+{
+	return (ci_send_msg_to_smc(rdev, PPSMC_MSG_ResetToDefaults) == PPSMC_Result_OK) ?
+		0 : -EINVAL;
+}
+
+static int ci_force_switch_to_arb_f0(struct radeon_device *rdev)
+{
+	u32 tmp;
+
+	tmp = (RREG32_SMC(SMC_SCRATCH9) & 0x0000ff00) >> 8;
+
+	if (tmp == MC_CG_ARB_FREQ_F0)
+		return 0;
+
+	return ni_copy_and_switch_arb_sets(rdev, tmp, MC_CG_ARB_FREQ_F0);
+}
+
+static int ci_populate_memory_timing_parameters(struct radeon_device *rdev,
+						u32 sclk,
+						u32 mclk,
+						SMU7_Discrete_MCArbDramTimingTableEntry *arb_regs)
+{
+	u32 dram_timing;
+	u32 dram_timing2;
+	u32 burst_time;
+
+	radeon_atom_set_engine_dram_timings(rdev, sclk, mclk);
+
+	dram_timing  = RREG32(MC_ARB_DRAM_TIMING);
+	dram_timing2 = RREG32(MC_ARB_DRAM_TIMING2);
+	burst_time = RREG32(MC_ARB_BURST_TIME) & STATE0_MASK;
+
+	arb_regs->McArbDramTiming  = cpu_to_be32(dram_timing);
+	arb_regs->McArbDramTiming2 = cpu_to_be32(dram_timing2);
+	arb_regs->McArbBurstTime = (u8)burst_time;
+
+	return 0;
+}
+
+static int ci_do_program_memory_timing_parameters(struct radeon_device *rdev)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	SMU7_Discrete_MCArbDramTimingTable arb_regs;
+	u32 i, j;
+	int ret =  0;
+
+	memset(&arb_regs, 0, sizeof(SMU7_Discrete_MCArbDramTimingTable));
+
+	for (i = 0; i < pi->dpm_table.sclk_table.count; i++) {
+		for (j = 0; j < pi->dpm_table.mclk_table.count; j++) {
+			ret = ci_populate_memory_timing_parameters(rdev,
+								   pi->dpm_table.sclk_table.dpm_levels[i].value,
+								   pi->dpm_table.mclk_table.dpm_levels[j].value,
+								   &arb_regs.entries[i][j]);
+			if (ret)
+				break;
+		}
+	}
+
+	if (ret == 0)
+		ret = ci_copy_bytes_to_smc(rdev,
+					   pi->arb_table_start,
+					   (u8 *)&arb_regs,
+					   sizeof(SMU7_Discrete_MCArbDramTimingTable),
+					   pi->sram_end);
+
+	return ret;
+}
+
+static int ci_program_memory_timing_parameters(struct radeon_device *rdev)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+
+	if (pi->need_update_smu7_dpm_table == 0)
+		return 0;
+
+	return ci_do_program_memory_timing_parameters(rdev);
+}
+
+static void ci_populate_smc_initial_state(struct radeon_device *rdev,
+					  struct radeon_ps *radeon_boot_state)
+{
+	struct ci_ps *boot_state = ci_get_ps(radeon_boot_state);
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	u32 level = 0;
+
+	for (level = 0; level < rdev->pm.dpm.dyn_state.vddc_dependency_on_sclk.count; level++) {
+		if (rdev->pm.dpm.dyn_state.vddc_dependency_on_sclk.entries[level].clk >=
+		    boot_state->performance_levels[0].sclk) {
+			pi->smc_state_table.GraphicsBootLevel = level;
+			break;
+		}
+	}
+
+	for (level = 0; level < rdev->pm.dpm.dyn_state.vddc_dependency_on_mclk.count; level++) {
+		if (rdev->pm.dpm.dyn_state.vddc_dependency_on_mclk.entries[level].clk >=
+		    boot_state->performance_levels[0].mclk) {
+			pi->smc_state_table.MemoryBootLevel = level;
+			break;
+		}
+	}
+}
+
+static u32 ci_get_dpm_level_enable_mask_value(struct ci_single_dpm_table *dpm_table)
+{
+	u32 i;
+	u32 mask_value = 0;
+
+	for (i = dpm_table->count; i > 0; i--) {
+		mask_value = mask_value << 1;
+		if (dpm_table->dpm_levels[i-1].enabled)
+			mask_value |= 0x1;
+		else
+			mask_value &= 0xFFFFFFFE;
+	}
+
+	return mask_value;
+}
+
+static void ci_populate_smc_link_level(struct radeon_device *rdev,
+				       SMU7_Discrete_DpmTable *table)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	struct ci_dpm_table *dpm_table = &pi->dpm_table;
+	u32 i;
+
+	for (i = 0; i < dpm_table->pcie_speed_table.count; i++) {
+		table->LinkLevel[i].PcieGenSpeed =
+			(u8)dpm_table->pcie_speed_table.dpm_levels[i].value;
+		table->LinkLevel[i].PcieLaneCount =
+			r600_encode_pci_lane_width(dpm_table->pcie_speed_table.dpm_levels[i].param1);
+		table->LinkLevel[i].EnabledForActivity = 1;
+		table->LinkLevel[i].DownT = cpu_to_be32(5);
+		table->LinkLevel[i].UpT = cpu_to_be32(30);
+	}
+
+	pi->smc_state_table.LinkLevelCount = (u8)dpm_table->pcie_speed_table.count;
+	pi->dpm_level_enable_mask.pcie_dpm_enable_mask =
+		ci_get_dpm_level_enable_mask_value(&dpm_table->pcie_speed_table);
+}
+
+static int ci_populate_smc_uvd_level(struct radeon_device *rdev,
+				     SMU7_Discrete_DpmTable *table)
+{
+	u32 count;
+	struct atom_clock_dividers dividers;
+	int ret = -EINVAL;
+
+	table->UvdLevelCount =
+		rdev->pm.dpm.dyn_state.uvd_clock_voltage_dependency_table.count;
+
+	for (count = 0; count < table->UvdLevelCount; count++) {
+		table->UvdLevel[count].VclkFrequency =
+			rdev->pm.dpm.dyn_state.uvd_clock_voltage_dependency_table.entries[count].vclk;
+		table->UvdLevel[count].DclkFrequency =
+			rdev->pm.dpm.dyn_state.uvd_clock_voltage_dependency_table.entries[count].dclk;
+		table->UvdLevel[count].MinVddc =
+			rdev->pm.dpm.dyn_state.uvd_clock_voltage_dependency_table.entries[count].v * VOLTAGE_SCALE;
+		table->UvdLevel[count].MinVddcPhases = 1;
+
+		ret = radeon_atom_get_clock_dividers(rdev,
+						     COMPUTE_GPUCLK_INPUT_FLAG_DEFAULT_GPUCLK,
+						     table->UvdLevel[count].VclkFrequency, false, &dividers);
+		if (ret)
+			return ret;
+
+		table->UvdLevel[count].VclkDivider = (u8)dividers.post_divider;
+
+		ret = radeon_atom_get_clock_dividers(rdev,
+						     COMPUTE_GPUCLK_INPUT_FLAG_DEFAULT_GPUCLK,
+						     table->UvdLevel[count].DclkFrequency, false, &dividers);
+		if (ret)
+			return ret;
+
+		table->UvdLevel[count].DclkDivider = (u8)dividers.post_divider;
+
+		table->UvdLevel[count].VclkFrequency = cpu_to_be32(table->UvdLevel[count].VclkFrequency);
+		table->UvdLevel[count].DclkFrequency = cpu_to_be32(table->UvdLevel[count].DclkFrequency);
+		table->UvdLevel[count].MinVddc = cpu_to_be16(table->UvdLevel[count].MinVddc);
+	}
+
+	return ret;
+}
+
+static int ci_populate_smc_vce_level(struct radeon_device *rdev,
+				     SMU7_Discrete_DpmTable *table)
+{
+	u32 count;
+	struct atom_clock_dividers dividers;
+	int ret = -EINVAL;
+
+	table->VceLevelCount =
+		rdev->pm.dpm.dyn_state.vce_clock_voltage_dependency_table.count;
+
+	for (count = 0; count < table->VceLevelCount; count++) {
+		table->VceLevel[count].Frequency =
+			rdev->pm.dpm.dyn_state.vce_clock_voltage_dependency_table.entries[count].evclk;
+		table->VceLevel[count].MinVoltage =
+			(u16)rdev->pm.dpm.dyn_state.vce_clock_voltage_dependency_table.entries[count].v * VOLTAGE_SCALE;
+		table->VceLevel[count].MinPhases = 1;
+
+		ret = radeon_atom_get_clock_dividers(rdev,
+						     COMPUTE_GPUCLK_INPUT_FLAG_DEFAULT_GPUCLK,
+						     table->VceLevel[count].Frequency, false, &dividers);
+		if (ret)
+			return ret;
+
+		table->VceLevel[count].Divider = (u8)dividers.post_divider;
+
+		table->VceLevel[count].Frequency = cpu_to_be32(table->VceLevel[count].Frequency);
+		table->VceLevel[count].MinVoltage = cpu_to_be16(table->VceLevel[count].MinVoltage);
+	}
+
+	return ret;
+
+}
+
+static int ci_populate_smc_acp_level(struct radeon_device *rdev,
+				     SMU7_Discrete_DpmTable *table)
+{
+	u32 count;
+	struct atom_clock_dividers dividers;
+	int ret = -EINVAL;
+
+	table->AcpLevelCount = (u8)
+		(rdev->pm.dpm.dyn_state.acp_clock_voltage_dependency_table.count);
+
+	for (count = 0; count < table->AcpLevelCount; count++) {
+		table->AcpLevel[count].Frequency =
+			rdev->pm.dpm.dyn_state.acp_clock_voltage_dependency_table.entries[count].clk;
+		table->AcpLevel[count].MinVoltage =
+			rdev->pm.dpm.dyn_state.acp_clock_voltage_dependency_table.entries[count].v;
+		table->AcpLevel[count].MinPhases = 1;
+
+		ret = radeon_atom_get_clock_dividers(rdev,
+						     COMPUTE_GPUCLK_INPUT_FLAG_DEFAULT_GPUCLK,
+						     table->AcpLevel[count].Frequency, false, &dividers);
+		if (ret)
+			return ret;
+
+		table->AcpLevel[count].Divider = (u8)dividers.post_divider;
+
+		table->AcpLevel[count].Frequency = cpu_to_be32(table->AcpLevel[count].Frequency);
+		table->AcpLevel[count].MinVoltage = cpu_to_be16(table->AcpLevel[count].MinVoltage);
+	}
+
+	return ret;
+}
+
+static int ci_populate_smc_samu_level(struct radeon_device *rdev,
+				      SMU7_Discrete_DpmTable *table)
+{
+	u32 count;
+	struct atom_clock_dividers dividers;
+	int ret = -EINVAL;
+
+	table->SamuLevelCount =
+		rdev->pm.dpm.dyn_state.samu_clock_voltage_dependency_table.count;
+
+	for (count = 0; count < table->SamuLevelCount; count++) {
+		table->SamuLevel[count].Frequency =
+			rdev->pm.dpm.dyn_state.samu_clock_voltage_dependency_table.entries[count].clk;
+		table->SamuLevel[count].MinVoltage =
+			rdev->pm.dpm.dyn_state.samu_clock_voltage_dependency_table.entries[count].v * VOLTAGE_SCALE;
+		table->SamuLevel[count].MinPhases = 1;
+
+		ret = radeon_atom_get_clock_dividers(rdev,
+						     COMPUTE_GPUCLK_INPUT_FLAG_DEFAULT_GPUCLK,
+						     table->SamuLevel[count].Frequency, false, &dividers);
+		if (ret)
+			return ret;
+
+		table->SamuLevel[count].Divider = (u8)dividers.post_divider;
+
+		table->SamuLevel[count].Frequency = cpu_to_be32(table->SamuLevel[count].Frequency);
+		table->SamuLevel[count].MinVoltage = cpu_to_be16(table->SamuLevel[count].MinVoltage);
+	}
+
+	return ret;
+}
+
+static int ci_calculate_mclk_params(struct radeon_device *rdev,
+				    u32 memory_clock,
+				    SMU7_Discrete_MemoryLevel *mclk,
+				    bool strobe_mode,
+				    bool dll_state_on)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	u32  dll_cntl = pi->clock_registers.dll_cntl;
+	u32  mclk_pwrmgt_cntl = pi->clock_registers.mclk_pwrmgt_cntl;
+	u32  mpll_ad_func_cntl = pi->clock_registers.mpll_ad_func_cntl;
+	u32  mpll_dq_func_cntl = pi->clock_registers.mpll_dq_func_cntl;
+	u32  mpll_func_cntl = pi->clock_registers.mpll_func_cntl;
+	u32  mpll_func_cntl_1 = pi->clock_registers.mpll_func_cntl_1;
+	u32  mpll_func_cntl_2 = pi->clock_registers.mpll_func_cntl_2;
+	u32  mpll_ss1 = pi->clock_registers.mpll_ss1;
+	u32  mpll_ss2 = pi->clock_registers.mpll_ss2;
+	struct atom_mpll_param mpll_param;
+	int ret;
+
+	ret = radeon_atom_get_memory_pll_dividers(rdev, memory_clock, strobe_mode, &mpll_param);
+	if (ret)
+		return ret;
+
+	mpll_func_cntl &= ~BWCTRL_MASK;
+	mpll_func_cntl |= BWCTRL(mpll_param.bwcntl);
+
+	mpll_func_cntl_1 &= ~(CLKF_MASK | CLKFRAC_MASK | VCO_MODE_MASK);
+	mpll_func_cntl_1 |= CLKF(mpll_param.clkf) |
+		CLKFRAC(mpll_param.clkfrac) | VCO_MODE(mpll_param.vco_mode);
+
+	mpll_ad_func_cntl &= ~YCLK_POST_DIV_MASK;
+	mpll_ad_func_cntl |= YCLK_POST_DIV(mpll_param.post_div);
+
+	if (pi->mem_gddr5) {
+		mpll_dq_func_cntl &= ~(YCLK_SEL_MASK | YCLK_POST_DIV_MASK);
+		mpll_dq_func_cntl |= YCLK_SEL(mpll_param.yclk_sel) |
+			YCLK_POST_DIV(mpll_param.post_div);
+	}
+
+	if (pi->caps_mclk_ss_support) {
+		struct radeon_atom_ss ss;
+		u32 freq_nom;
+		u32 tmp;
+		u32 reference_clock = rdev->clock.mpll.reference_freq;
+
+		if (pi->mem_gddr5)
+			freq_nom = memory_clock * 4;
+		else
+			freq_nom = memory_clock * 2;
+
+		tmp = (freq_nom / reference_clock);
+		tmp = tmp * tmp;
+		if (radeon_atombios_get_asic_ss_info(rdev, &ss,
+						     ASIC_INTERNAL_MEMORY_SS, freq_nom)) {
+			u32 clks = reference_clock * 5 / ss.rate;
+			u32 clkv = (u32)((((131 * ss.percentage * ss.rate) / 100) * tmp) / freq_nom);
+
+			mpll_ss1 &= ~CLKV_MASK;
+			mpll_ss1 |= CLKV(clkv);
+
+			mpll_ss2 &= ~CLKS_MASK;
+			mpll_ss2 |= CLKS(clks);
+		}
+	}
+
+	mclk_pwrmgt_cntl &= ~DLL_SPEED_MASK;
+	mclk_pwrmgt_cntl |= DLL_SPEED(mpll_param.dll_speed);
+
+	if (dll_state_on)
+		mclk_pwrmgt_cntl |= MRDCK0_PDNB | MRDCK1_PDNB;
+	else
+		mclk_pwrmgt_cntl &= ~(MRDCK0_PDNB | MRDCK1_PDNB);
+
+	mclk->MclkFrequency = memory_clock;
+	mclk->MpllFuncCntl = mpll_func_cntl;
+	mclk->MpllFuncCntl_1 = mpll_func_cntl_1;
+	mclk->MpllFuncCntl_2 = mpll_func_cntl_2;
+	mclk->MpllAdFuncCntl = mpll_ad_func_cntl;
+	mclk->MpllDqFuncCntl = mpll_dq_func_cntl;
+	mclk->MclkPwrmgtCntl = mclk_pwrmgt_cntl;
+	mclk->DllCntl = dll_cntl;
+	mclk->MpllSs1 = mpll_ss1;
+	mclk->MpllSs2 = mpll_ss2;
+
+	return 0;
+}
+
+static int ci_populate_single_memory_level(struct radeon_device *rdev,
+					   u32 memory_clock,
+					   SMU7_Discrete_MemoryLevel *memory_level)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	int ret;
+	bool dll_state_on;
+
+	if (rdev->pm.dpm.dyn_state.vddc_dependency_on_mclk.entries) {
+		ret = ci_get_dependency_volt_by_clk(rdev,
+						    &rdev->pm.dpm.dyn_state.vddc_dependency_on_mclk,
+						    memory_clock, &memory_level->MinVddc);
+		if (ret)
+			return ret;
+	}
+
+	if (rdev->pm.dpm.dyn_state.vddci_dependency_on_mclk.entries) {
+		ret = ci_get_dependency_volt_by_clk(rdev,
+						    &rdev->pm.dpm.dyn_state.vddci_dependency_on_mclk,
+						    memory_clock, &memory_level->MinVddci);
+		if (ret)
+			return ret;
+	}
+
+	if (rdev->pm.dpm.dyn_state.mvdd_dependency_on_mclk.entries) {
+		ret = ci_get_dependency_volt_by_clk(rdev,
+						    &rdev->pm.dpm.dyn_state.mvdd_dependency_on_mclk,
+						    memory_clock, &memory_level->MinMvdd);
+		if (ret)
+			return ret;
+	}
+
+	memory_level->MinVddcPhases = 1;
+
+	if (pi->vddc_phase_shed_control)
+		ci_populate_phase_value_based_on_mclk(rdev,
+						      &rdev->pm.dpm.dyn_state.phase_shedding_limits_table,
+						      memory_clock,
+						      &memory_level->MinVddcPhases);
+
+	memory_level->EnabledForThrottle = 1;
+	memory_level->EnabledForActivity = 1;
+	memory_level->UpH = 0;
+	memory_level->DownH = 100;
+	memory_level->VoltageDownH = 0;
+	memory_level->ActivityLevel = (u16)pi->mclk_activity_target;
+
+	memory_level->StutterEnable = false;
+	memory_level->StrobeEnable = false;
+	memory_level->EdcReadEnable = false;
+	memory_level->EdcWriteEnable = false;
+	memory_level->RttEnable = false;
+
+	memory_level->DisplayWatermark = PPSMC_DISPLAY_WATERMARK_LOW;
+
+	if (pi->mclk_stutter_mode_threshold &&
+	    (memory_clock <= pi->mclk_stutter_mode_threshold) &&
+	    (pi->uvd_enabled == false) &&
+	    (RREG32(DPG_PIPE_STUTTER_CONTROL) & STUTTER_ENABLE) &&
+	    (rdev->pm.dpm.new_active_crtc_count <= 2))
+		memory_level->StutterEnable = true;
+
+	if (pi->mclk_strobe_mode_threshold &&
+	    (memory_clock <= pi->mclk_strobe_mode_threshold))
+		memory_level->StrobeEnable = 1;
+
+	if (pi->mem_gddr5) {
+		memory_level->StrobeRatio =
+			si_get_mclk_frequency_ratio(memory_clock, memory_level->StrobeEnable);
+		if (pi->mclk_edc_enable_threshold &&
+		    (memory_clock > pi->mclk_edc_enable_threshold))
+			memory_level->EdcReadEnable = true;
+
+		if (pi->mclk_edc_wr_enable_threshold &&
+		    (memory_clock > pi->mclk_edc_wr_enable_threshold))
+			memory_level->EdcWriteEnable = true;
+
+		if (memory_level->StrobeEnable) {
+			if (si_get_mclk_frequency_ratio(memory_clock, true) >=
+			    ((RREG32(MC_SEQ_MISC7) >> 16) & 0xf))
+				dll_state_on = ((RREG32(MC_SEQ_MISC5) >> 1) & 0x1) ? true : false;
+			else
+				dll_state_on = ((RREG32(MC_SEQ_MISC6) >> 1) & 0x1) ? true : false;
+		} else {
+			dll_state_on = pi->dll_default_on;
+		}
+	} else {
+		memory_level->StrobeRatio = si_get_ddr3_mclk_frequency_ratio(memory_clock);
+		dll_state_on = ((RREG32(MC_SEQ_MISC5) >> 1) & 0x1) ? true : false;
+	}
+
+	ret = ci_calculate_mclk_params(rdev, memory_clock, memory_level, memory_level->StrobeEnable, dll_state_on);
+	if (ret)
+		return ret;
+
+	memory_level->MinVddc = cpu_to_be32(memory_level->MinVddc * VOLTAGE_SCALE);
+	memory_level->MinVddcPhases = cpu_to_be32(memory_level->MinVddcPhases);
+        memory_level->MinVddci = cpu_to_be32(memory_level->MinVddci * VOLTAGE_SCALE);
+        memory_level->MinMvdd = cpu_to_be32(memory_level->MinMvdd * VOLTAGE_SCALE);
+
+	memory_level->MclkFrequency = cpu_to_be32(memory_level->MclkFrequency);
+	memory_level->ActivityLevel = cpu_to_be16(memory_level->ActivityLevel);
+	memory_level->MpllFuncCntl = cpu_to_be32(memory_level->MpllFuncCntl);
+	memory_level->MpllFuncCntl_1 = cpu_to_be32(memory_level->MpllFuncCntl_1);
+	memory_level->MpllFuncCntl_2 = cpu_to_be32(memory_level->MpllFuncCntl_2);
+	memory_level->MpllAdFuncCntl = cpu_to_be32(memory_level->MpllAdFuncCntl);
+	memory_level->MpllDqFuncCntl = cpu_to_be32(memory_level->MpllDqFuncCntl);
+	memory_level->MclkPwrmgtCntl = cpu_to_be32(memory_level->MclkPwrmgtCntl);
+	memory_level->DllCntl = cpu_to_be32(memory_level->DllCntl);
+	memory_level->MpllSs1 = cpu_to_be32(memory_level->MpllSs1);
+	memory_level->MpllSs2 = cpu_to_be32(memory_level->MpllSs2);
+
+	return 0;
+}
+
+static int ci_populate_smc_acpi_level(struct radeon_device *rdev,
+				      SMU7_Discrete_DpmTable *table)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	struct atom_clock_dividers dividers;
+	SMU7_Discrete_VoltageLevel voltage_level;
+	u32 spll_func_cntl = pi->clock_registers.cg_spll_func_cntl;
+	u32 spll_func_cntl_2 = pi->clock_registers.cg_spll_func_cntl_2;
+	u32 dll_cntl = pi->clock_registers.dll_cntl;
+	u32 mclk_pwrmgt_cntl = pi->clock_registers.mclk_pwrmgt_cntl;
+	int ret;
+
+	table->ACPILevel.Flags &= ~PPSMC_SWSTATE_FLAG_DC;
+
+	if (pi->acpi_vddc)
+		table->ACPILevel.MinVddc = cpu_to_be32(pi->acpi_vddc * VOLTAGE_SCALE);
+	else
+		table->ACPILevel.MinVddc = cpu_to_be32(pi->min_vddc_in_pp_table * VOLTAGE_SCALE);
+
+	table->ACPILevel.MinVddcPhases = pi->vddc_phase_shed_control ? 0 : 1;
+
+	table->ACPILevel.SclkFrequency = rdev->clock.spll.reference_freq;
+
+	ret = radeon_atom_get_clock_dividers(rdev,
+					     COMPUTE_GPUCLK_INPUT_FLAG_SCLK,
+					     table->ACPILevel.SclkFrequency, false, &dividers);
+	if (ret)
+		return ret;
+
+	table->ACPILevel.SclkDid = (u8)dividers.post_divider;
+	table->ACPILevel.DisplayWatermark = PPSMC_DISPLAY_WATERMARK_LOW;
+	table->ACPILevel.DeepSleepDivId = 0;
+
+	spll_func_cntl &= ~SPLL_PWRON;
+	spll_func_cntl |= SPLL_RESET;
+
+	spll_func_cntl_2 &= ~SCLK_MUX_SEL_MASK;
+	spll_func_cntl_2 |= SCLK_MUX_SEL(4);
+
+	table->ACPILevel.CgSpllFuncCntl = spll_func_cntl;
+	table->ACPILevel.CgSpllFuncCntl2 = spll_func_cntl_2;
+	table->ACPILevel.CgSpllFuncCntl3 = pi->clock_registers.cg_spll_func_cntl_3;
+	table->ACPILevel.CgSpllFuncCntl4 = pi->clock_registers.cg_spll_func_cntl_4;
+	table->ACPILevel.SpllSpreadSpectrum = pi->clock_registers.cg_spll_spread_spectrum;
+	table->ACPILevel.SpllSpreadSpectrum2 = pi->clock_registers.cg_spll_spread_spectrum_2;
+	table->ACPILevel.CcPwrDynRm = 0;
+	table->ACPILevel.CcPwrDynRm1 = 0;
+
+	table->ACPILevel.Flags = cpu_to_be32(table->ACPILevel.Flags);
+	table->ACPILevel.MinVddcPhases = cpu_to_be32(table->ACPILevel.MinVddcPhases);
+	table->ACPILevel.SclkFrequency = cpu_to_be32(table->ACPILevel.SclkFrequency);
+	table->ACPILevel.CgSpllFuncCntl = cpu_to_be32(table->ACPILevel.CgSpllFuncCntl);
+	table->ACPILevel.CgSpllFuncCntl2 = cpu_to_be32(table->ACPILevel.CgSpllFuncCntl2);
+	table->ACPILevel.CgSpllFuncCntl3 = cpu_to_be32(table->ACPILevel.CgSpllFuncCntl3);
+	table->ACPILevel.CgSpllFuncCntl4 = cpu_to_be32(table->ACPILevel.CgSpllFuncCntl4);
+	table->ACPILevel.SpllSpreadSpectrum = cpu_to_be32(table->ACPILevel.SpllSpreadSpectrum);
+	table->ACPILevel.SpllSpreadSpectrum2 = cpu_to_be32(table->ACPILevel.SpllSpreadSpectrum2);
+	table->ACPILevel.CcPwrDynRm = cpu_to_be32(table->ACPILevel.CcPwrDynRm);
+	table->ACPILevel.CcPwrDynRm1 = cpu_to_be32(table->ACPILevel.CcPwrDynRm1);
+
+	table->MemoryACPILevel.MinVddc = table->ACPILevel.MinVddc;
+	table->MemoryACPILevel.MinVddcPhases = table->ACPILevel.MinVddcPhases;
+
+	if (pi->vddci_control != CISLANDS_VOLTAGE_CONTROL_NONE) {
+		if (pi->acpi_vddci)
+			table->MemoryACPILevel.MinVddci =
+				cpu_to_be32(pi->acpi_vddci * VOLTAGE_SCALE);
+		else
+			table->MemoryACPILevel.MinVddci =
+				cpu_to_be32(pi->min_vddci_in_pp_table * VOLTAGE_SCALE);
+	}
+
+	if (ci_populate_mvdd_value(rdev, 0, &voltage_level))
+		table->MemoryACPILevel.MinMvdd = 0;
+	else
+		table->MemoryACPILevel.MinMvdd =
+			cpu_to_be32(voltage_level.Voltage * VOLTAGE_SCALE);
+
+	mclk_pwrmgt_cntl |= MRDCK0_RESET | MRDCK1_RESET;
+	mclk_pwrmgt_cntl &= ~(MRDCK0_PDNB | MRDCK1_PDNB);
+
+	dll_cntl &= ~(MRDCK0_BYPASS | MRDCK1_BYPASS);
+
+	table->MemoryACPILevel.DllCntl = cpu_to_be32(dll_cntl);
+	table->MemoryACPILevel.MclkPwrmgtCntl = cpu_to_be32(mclk_pwrmgt_cntl);
+	table->MemoryACPILevel.MpllAdFuncCntl =
+		cpu_to_be32(pi->clock_registers.mpll_ad_func_cntl);
+	table->MemoryACPILevel.MpllDqFuncCntl =
+		cpu_to_be32(pi->clock_registers.mpll_dq_func_cntl);
+	table->MemoryACPILevel.MpllFuncCntl =
+		cpu_to_be32(pi->clock_registers.mpll_func_cntl);
+	table->MemoryACPILevel.MpllFuncCntl_1 =
+		cpu_to_be32(pi->clock_registers.mpll_func_cntl_1);
+	table->MemoryACPILevel.MpllFuncCntl_2 =
+		cpu_to_be32(pi->clock_registers.mpll_func_cntl_2);
+	table->MemoryACPILevel.MpllSs1 = cpu_to_be32(pi->clock_registers.mpll_ss1);
+	table->MemoryACPILevel.MpllSs2 = cpu_to_be32(pi->clock_registers.mpll_ss2);
+
+	table->MemoryACPILevel.EnabledForThrottle = 0;
+	table->MemoryACPILevel.EnabledForActivity = 0;
+	table->MemoryACPILevel.UpH = 0;
+	table->MemoryACPILevel.DownH = 100;
+	table->MemoryACPILevel.VoltageDownH = 0;
+	table->MemoryACPILevel.ActivityLevel =
+		cpu_to_be16((u16)pi->mclk_activity_target);
+
+	table->MemoryACPILevel.StutterEnable = false;
+	table->MemoryACPILevel.StrobeEnable = false;
+	table->MemoryACPILevel.EdcReadEnable = false;
+	table->MemoryACPILevel.EdcWriteEnable = false;
+	table->MemoryACPILevel.RttEnable = false;
+
+	return 0;
+}
+
+
+static int ci_enable_ulv(struct radeon_device *rdev, bool enable)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	struct ci_ulv_parm *ulv = &pi->ulv;
+
+	if (ulv->supported) {
+		if (enable)
+			return (ci_send_msg_to_smc(rdev, PPSMC_MSG_EnableULV) == PPSMC_Result_OK) ?
+				0 : -EINVAL;
+		else
+			return (ci_send_msg_to_smc(rdev, PPSMC_MSG_DisableULV) == PPSMC_Result_OK) ?
+				0 : -EINVAL;
+	}
+
+	return 0;
+}
+
+static int ci_populate_ulv_level(struct radeon_device *rdev,
+				 SMU7_Discrete_Ulv *state)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	u16 ulv_voltage = rdev->pm.dpm.backbias_response_time;
+
+	state->CcPwrDynRm = 0;
+	state->CcPwrDynRm1 = 0;
+
+	if (ulv_voltage == 0) {
+		pi->ulv.supported = false;
+		return 0;
+	}
+
+	if (pi->voltage_control != CISLANDS_VOLTAGE_CONTROL_BY_SVID2) {
+		if (ulv_voltage > rdev->pm.dpm.dyn_state.vddc_dependency_on_sclk.entries[0].v)
+			state->VddcOffset = 0;
+		else
+			state->VddcOffset =
+				rdev->pm.dpm.dyn_state.vddc_dependency_on_sclk.entries[0].v - ulv_voltage;
+	} else {
+		if (ulv_voltage > rdev->pm.dpm.dyn_state.vddc_dependency_on_sclk.entries[0].v)
+			state->VddcOffsetVid = 0;
+		else
+			state->VddcOffsetVid = (u8)
+				((rdev->pm.dpm.dyn_state.vddc_dependency_on_sclk.entries[0].v - ulv_voltage) *
+				 VOLTAGE_VID_OFFSET_SCALE2 / VOLTAGE_VID_OFFSET_SCALE1);
+	}
+	state->VddcPhase = pi->vddc_phase_shed_control ? 0 : 1;
+
+	state->CcPwrDynRm = cpu_to_be32(state->CcPwrDynRm);
+	state->CcPwrDynRm1 = cpu_to_be32(state->CcPwrDynRm1);
+	state->VddcOffset = cpu_to_be16(state->VddcOffset);
+
+	return 0;
+}
+
+static int ci_calculate_sclk_params(struct radeon_device *rdev,
+				    u32 engine_clock,
+				    SMU7_Discrete_GraphicsLevel *sclk)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	struct atom_clock_dividers dividers;
+	u32 spll_func_cntl_3 = pi->clock_registers.cg_spll_func_cntl_3;
+	u32 spll_func_cntl_4 = pi->clock_registers.cg_spll_func_cntl_4;
+	u32 cg_spll_spread_spectrum = pi->clock_registers.cg_spll_spread_spectrum;
+	u32 cg_spll_spread_spectrum_2 = pi->clock_registers.cg_spll_spread_spectrum_2;
+	u32 reference_clock = rdev->clock.spll.reference_freq;
+	u32 reference_divider;
+	u32 fbdiv;
+	int ret;
+
+	ret = radeon_atom_get_clock_dividers(rdev,
+					     COMPUTE_GPUCLK_INPUT_FLAG_SCLK,
+					     engine_clock, false, &dividers);
+	if (ret)
+		return ret;
+
+	reference_divider = 1 + dividers.ref_div;
+	fbdiv = dividers.fb_div & 0x3FFFFFF;
+
+	spll_func_cntl_3 &= ~SPLL_FB_DIV_MASK;
+	spll_func_cntl_3 |= SPLL_FB_DIV(fbdiv);
+        spll_func_cntl_3 |= SPLL_DITHEN;
+
+	if (pi->caps_sclk_ss_support) {
+		struct radeon_atom_ss ss;
+		u32 vco_freq = engine_clock * dividers.post_div;
+
+		if (radeon_atombios_get_asic_ss_info(rdev, &ss,
+						     ASIC_INTERNAL_ENGINE_SS, vco_freq)) {
+			u32 clk_s = reference_clock * 5 / (reference_divider * ss.rate);
+			u32 clk_v = 4 * ss.percentage * fbdiv / (clk_s * 10000);
+
+			cg_spll_spread_spectrum &= ~CLK_S_MASK;
+			cg_spll_spread_spectrum |= CLK_S(clk_s);
+			cg_spll_spread_spectrum |= SSEN;
+
+			cg_spll_spread_spectrum_2 &= ~CLK_V_MASK;
+			cg_spll_spread_spectrum_2 |= CLK_V(clk_v);
+		}
+	}
+
+	sclk->SclkFrequency = engine_clock;
+	sclk->CgSpllFuncCntl3 = spll_func_cntl_3;
+	sclk->CgSpllFuncCntl4 = spll_func_cntl_4;
+	sclk->SpllSpreadSpectrum = cg_spll_spread_spectrum;
+	sclk->SpllSpreadSpectrum2  = cg_spll_spread_spectrum_2;
+	sclk->SclkDid = (u8)dividers.post_divider;
+
+	return 0;
+}
+
+static int ci_populate_single_graphic_level(struct radeon_device *rdev,
+					    u32 engine_clock,
+					    u16 sclk_activity_level_t,
+					    SMU7_Discrete_GraphicsLevel *graphic_level)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	int ret;
+
+	ret = ci_calculate_sclk_params(rdev, engine_clock, graphic_level);
+	if (ret)
+		return ret;
+
+	ret = ci_get_dependency_volt_by_clk(rdev,
+					    &rdev->pm.dpm.dyn_state.vddc_dependency_on_sclk,
+					    engine_clock, &graphic_level->MinVddc);
+	if (ret)
+		return ret;
+
+	graphic_level->SclkFrequency = engine_clock;
+
+	graphic_level->Flags =  0;
+	graphic_level->MinVddcPhases = 1;
+
+	if (pi->vddc_phase_shed_control)
+		ci_populate_phase_value_based_on_sclk(rdev,
+						      &rdev->pm.dpm.dyn_state.phase_shedding_limits_table,
+						      engine_clock,
+						      &graphic_level->MinVddcPhases);
+
+	graphic_level->ActivityLevel = sclk_activity_level_t;
+
+	graphic_level->CcPwrDynRm = 0;
+	graphic_level->CcPwrDynRm1 = 0;
+	graphic_level->EnabledForActivity = 1;
+	graphic_level->EnabledForThrottle = 1;
+	graphic_level->UpH = 0;
+	graphic_level->DownH = 0;
+	graphic_level->VoltageDownH = 0;
+	graphic_level->PowerThrottle = 0;
+
+	if (pi->caps_sclk_ds)
+		graphic_level->DeepSleepDivId = ci_get_sleep_divider_id_from_clock(rdev,
+										   engine_clock,
+										   CISLAND_MINIMUM_ENGINE_CLOCK);
+
+	graphic_level->DisplayWatermark = PPSMC_DISPLAY_WATERMARK_LOW;
+
+	graphic_level->Flags = cpu_to_be32(graphic_level->Flags);
+        graphic_level->MinVddc = cpu_to_be32(graphic_level->MinVddc * VOLTAGE_SCALE);
+	graphic_level->MinVddcPhases = cpu_to_be32(graphic_level->MinVddcPhases);
+	graphic_level->SclkFrequency = cpu_to_be32(graphic_level->SclkFrequency);
+	graphic_level->ActivityLevel = cpu_to_be16(graphic_level->ActivityLevel);
+	graphic_level->CgSpllFuncCntl3 = cpu_to_be32(graphic_level->CgSpllFuncCntl3);
+	graphic_level->CgSpllFuncCntl4 = cpu_to_be32(graphic_level->CgSpllFuncCntl4);
+	graphic_level->SpllSpreadSpectrum = cpu_to_be32(graphic_level->SpllSpreadSpectrum);
+	graphic_level->SpllSpreadSpectrum2 = cpu_to_be32(graphic_level->SpllSpreadSpectrum2);
+	graphic_level->CcPwrDynRm = cpu_to_be32(graphic_level->CcPwrDynRm);
+	graphic_level->CcPwrDynRm1 = cpu_to_be32(graphic_level->CcPwrDynRm1);
+
+	return 0;
+}
+
+static int ci_populate_all_graphic_levels(struct radeon_device *rdev)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	struct ci_dpm_table *dpm_table = &pi->dpm_table;
+	u32 level_array_address = pi->dpm_table_start +
+		offsetof(SMU7_Discrete_DpmTable, GraphicsLevel);
+	u32 level_array_size = sizeof(SMU7_Discrete_GraphicsLevel) *
+		SMU7_MAX_LEVELS_GRAPHICS;
+	SMU7_Discrete_GraphicsLevel *levels = pi->smc_state_table.GraphicsLevel;
+	u32 i, ret;
+
+	memset(levels, 0, level_array_size);
+
+	for (i = 0; i < dpm_table->sclk_table.count; i++) {
+		ret = ci_populate_single_graphic_level(rdev,
+						       dpm_table->sclk_table.dpm_levels[i].value,
+						       (u16)pi->activity_target[i],
+						       &pi->smc_state_table.GraphicsLevel[i]);
+		if (ret)
+			return ret;
+		if (i == (dpm_table->sclk_table.count - 1))
+			pi->smc_state_table.GraphicsLevel[i].DisplayWatermark =
+				PPSMC_DISPLAY_WATERMARK_HIGH;
+	}
+
+	pi->smc_state_table.GraphicsDpmLevelCount = (u8)dpm_table->sclk_table.count;
+	pi->dpm_level_enable_mask.sclk_dpm_enable_mask =
+		ci_get_dpm_level_enable_mask_value(&dpm_table->sclk_table);
+
+	ret = ci_copy_bytes_to_smc(rdev, level_array_address,
+				   (u8 *)levels, level_array_size,
+				   pi->sram_end);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static int ci_populate_ulv_state(struct radeon_device *rdev,
+				 SMU7_Discrete_Ulv *ulv_level)
+{
+	return ci_populate_ulv_level(rdev, ulv_level);
+}
+
+static int ci_populate_all_memory_levels(struct radeon_device *rdev)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	struct ci_dpm_table *dpm_table = &pi->dpm_table;
+	u32 level_array_address = pi->dpm_table_start +
+		offsetof(SMU7_Discrete_DpmTable, MemoryLevel);
+	u32 level_array_size = sizeof(SMU7_Discrete_MemoryLevel) *
+		SMU7_MAX_LEVELS_MEMORY;
+	SMU7_Discrete_MemoryLevel *levels = pi->smc_state_table.MemoryLevel;
+	u32 i, ret;
+
+	memset(levels, 0, level_array_size);
+
+	for (i = 0; i < dpm_table->mclk_table.count; i++) {
+		if (dpm_table->mclk_table.dpm_levels[i].value == 0)
+			return -EINVAL;
+		ret = ci_populate_single_memory_level(rdev,
+						      dpm_table->mclk_table.dpm_levels[i].value,
+						      &pi->smc_state_table.MemoryLevel[i]);
+		if (ret)
+			return ret;
+	}
+
+	pi->smc_state_table.MemoryLevel[0].ActivityLevel = cpu_to_be16(0x1F);
+
+	pi->smc_state_table.MemoryDpmLevelCount = (u8)dpm_table->mclk_table.count;
+	pi->dpm_level_enable_mask.mclk_dpm_enable_mask =
+		ci_get_dpm_level_enable_mask_value(&dpm_table->mclk_table);
+
+	pi->smc_state_table.MemoryLevel[dpm_table->mclk_table.count - 1].DisplayWatermark =
+		PPSMC_DISPLAY_WATERMARK_HIGH;
+
+	ret = ci_copy_bytes_to_smc(rdev, level_array_address,
+				   (u8 *)levels, level_array_size,
+				   pi->sram_end);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static void ci_reset_single_dpm_table(struct radeon_device *rdev,
+				      struct ci_single_dpm_table* dpm_table,
+				      u32 count)
+{
+	u32 i;
+
+	dpm_table->count = count;
+	for (i = 0; i < MAX_REGULAR_DPM_NUMBER; i++)
+		dpm_table->dpm_levels[i].enabled = false;
+}
+
+static void ci_setup_pcie_table_entry(struct ci_single_dpm_table* dpm_table,
+				      u32 index, u32 pcie_gen, u32 pcie_lanes)
+{
+	dpm_table->dpm_levels[index].value = pcie_gen;
+	dpm_table->dpm_levels[index].param1 = pcie_lanes;
+	dpm_table->dpm_levels[index].enabled = true;
+}
+
+static int ci_setup_default_pcie_tables(struct radeon_device *rdev)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+
+	if (!pi->use_pcie_performance_levels && !pi->use_pcie_powersaving_levels)
+		return -EINVAL;
+
+	if (pi->use_pcie_performance_levels && !pi->use_pcie_powersaving_levels) {
+		pi->pcie_gen_powersaving = pi->pcie_gen_performance;
+		pi->pcie_lane_powersaving = pi->pcie_lane_performance;
+	} else if (!pi->use_pcie_performance_levels && pi->use_pcie_powersaving_levels) {
+		pi->pcie_gen_performance = pi->pcie_gen_powersaving;
+		pi->pcie_lane_performance = pi->pcie_lane_powersaving;
+	}
+
+	ci_reset_single_dpm_table(rdev,
+				  &pi->dpm_table.pcie_speed_table,
+				  SMU7_MAX_LEVELS_LINK);
+
+	ci_setup_pcie_table_entry(&pi->dpm_table.pcie_speed_table, 0,
+				  pi->pcie_gen_powersaving.min,
+				  pi->pcie_lane_powersaving.min);
+	ci_setup_pcie_table_entry(&pi->dpm_table.pcie_speed_table, 1,
+				  pi->pcie_gen_performance.min,
+				  pi->pcie_lane_performance.min);
+	ci_setup_pcie_table_entry(&pi->dpm_table.pcie_speed_table, 2,
+				  pi->pcie_gen_powersaving.min,
+				  pi->pcie_lane_powersaving.max);
+	ci_setup_pcie_table_entry(&pi->dpm_table.pcie_speed_table, 3,
+				  pi->pcie_gen_performance.min,
+				  pi->pcie_lane_performance.max);
+	ci_setup_pcie_table_entry(&pi->dpm_table.pcie_speed_table, 4,
+				  pi->pcie_gen_powersaving.max,
+				  pi->pcie_lane_powersaving.max);
+	ci_setup_pcie_table_entry(&pi->dpm_table.pcie_speed_table, 5,
+				  pi->pcie_gen_performance.max,
+				  pi->pcie_lane_performance.max);
+
+	pi->dpm_table.pcie_speed_table.count = 6;
+
+	return 0;
+}
+
+static int ci_setup_default_dpm_tables(struct radeon_device *rdev)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	struct radeon_clock_voltage_dependency_table *allowed_sclk_vddc_table =
+		&rdev->pm.dpm.dyn_state.vddc_dependency_on_sclk;
+	struct radeon_clock_voltage_dependency_table *allowed_mclk_table =
+		&rdev->pm.dpm.dyn_state.vddc_dependency_on_mclk;
+	struct radeon_cac_leakage_table *std_voltage_table =
+		&rdev->pm.dpm.dyn_state.cac_leakage_table;
+	u32 i;
+
+	if (allowed_sclk_vddc_table == NULL)
+		return -EINVAL;
+	if (allowed_sclk_vddc_table->count < 1)
+		return -EINVAL;
+	if (allowed_mclk_table == NULL)
+		return -EINVAL;
+	if (allowed_mclk_table->count < 1)
+		return -EINVAL;
+
+	memset(&pi->dpm_table, 0, sizeof(struct ci_dpm_table));
+
+	ci_reset_single_dpm_table(rdev,
+				  &pi->dpm_table.sclk_table,
+				  SMU7_MAX_LEVELS_GRAPHICS);
+	ci_reset_single_dpm_table(rdev,
+				  &pi->dpm_table.mclk_table,
+				  SMU7_MAX_LEVELS_MEMORY);
+	ci_reset_single_dpm_table(rdev,
+				  &pi->dpm_table.vddc_table,
+				  SMU7_MAX_LEVELS_VDDC);
+	ci_reset_single_dpm_table(rdev,
+				  &pi->dpm_table.vddci_table,
+				  SMU7_MAX_LEVELS_VDDCI);
+	ci_reset_single_dpm_table(rdev,
+				  &pi->dpm_table.mvdd_table,
+				  SMU7_MAX_LEVELS_MVDD);
+
+	pi->dpm_table.sclk_table.count = 0;
+	for (i = 0; i < allowed_sclk_vddc_table->count; i++) {
+		if ((i == 0) ||
+		    (pi->dpm_table.sclk_table.dpm_levels[pi->dpm_table.sclk_table.count-1].value !=
+		     allowed_sclk_vddc_table->entries[i].clk)) {
+			pi->dpm_table.sclk_table.dpm_levels[pi->dpm_table.sclk_table.count].value =
+				allowed_sclk_vddc_table->entries[i].clk;
+			pi->dpm_table.sclk_table.dpm_levels[pi->dpm_table.sclk_table.count].enabled = true;
+			pi->dpm_table.sclk_table.count++;
+		}
+	}
+
+	pi->dpm_table.mclk_table.count = 0;
+	for (i = 0; i < allowed_mclk_table->count; i++) {
+		if ((i==0) ||
+		    (pi->dpm_table.mclk_table.dpm_levels[pi->dpm_table.mclk_table.count-1].value !=
+		     allowed_mclk_table->entries[i].clk)) {
+			pi->dpm_table.mclk_table.dpm_levels[pi->dpm_table.mclk_table.count].value =
+				allowed_mclk_table->entries[i].clk;
+			pi->dpm_table.mclk_table.dpm_levels[pi->dpm_table.mclk_table.count].enabled = true;
+			pi->dpm_table.mclk_table.count++;
+		}
+	}
+
+	for (i = 0; i < allowed_sclk_vddc_table->count; i++) {
+		pi->dpm_table.vddc_table.dpm_levels[i].value =
+			allowed_sclk_vddc_table->entries[i].v;
+		pi->dpm_table.vddc_table.dpm_levels[i].param1 =
+			std_voltage_table->entries[i].leakage;
+		pi->dpm_table.vddc_table.dpm_levels[i].enabled = true;
+	}
+	pi->dpm_table.vddc_table.count = allowed_sclk_vddc_table->count;
+
+	allowed_mclk_table = &rdev->pm.dpm.dyn_state.vddci_dependency_on_mclk;
+	if (allowed_mclk_table) {
+		for (i = 0; i < allowed_mclk_table->count; i++) {
+			pi->dpm_table.vddci_table.dpm_levels[i].value =
+				allowed_mclk_table->entries[i].v;
+			pi->dpm_table.vddci_table.dpm_levels[i].enabled = true;
+		}
+		pi->dpm_table.vddci_table.count = allowed_mclk_table->count;
+	}
+
+	allowed_mclk_table = &rdev->pm.dpm.dyn_state.mvdd_dependency_on_mclk;
+	if (allowed_mclk_table) {
+		for (i = 0; i < allowed_mclk_table->count; i++) {
+			pi->dpm_table.mvdd_table.dpm_levels[i].value =
+				allowed_mclk_table->entries[i].v;
+			pi->dpm_table.mvdd_table.dpm_levels[i].enabled = true;
+		}
+		pi->dpm_table.mvdd_table.count = allowed_mclk_table->count;
+	}
+
+	ci_setup_default_pcie_tables(rdev);
+
+	return 0;
+}
+
+static int ci_find_boot_level(struct ci_single_dpm_table *table,
+			      u32 value, u32 *boot_level)
+{
+	u32 i;
+	int ret = -EINVAL;
+
+	for(i = 0; i < table->count; i++) {
+		if (value == table->dpm_levels[i].value) {
+			*boot_level = i;
+			ret = 0;
+		}
+	}
+
+	return ret;
+}
+
+static int ci_init_smc_table(struct radeon_device *rdev)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	struct ci_ulv_parm *ulv = &pi->ulv;
+	struct radeon_ps *radeon_boot_state = rdev->pm.dpm.boot_ps;
+	SMU7_Discrete_DpmTable *table = &pi->smc_state_table;
+	int ret;
+
+	ret = ci_setup_default_dpm_tables(rdev);
+	if (ret)
+		return ret;
+
+	if (pi->voltage_control != CISLANDS_VOLTAGE_CONTROL_NONE)
+		ci_populate_smc_voltage_tables(rdev, table);
+
+	ci_init_fps_limits(rdev);
+
+	if (rdev->pm.dpm.platform_caps & ATOM_PP_PLATFORM_CAP_HARDWAREDC)
+		table->SystemFlags |= PPSMC_SYSTEMFLAG_GPIO_DC;
+
+	if (rdev->pm.dpm.platform_caps & ATOM_PP_PLATFORM_CAP_STEPVDDC)
+		table->SystemFlags |= PPSMC_SYSTEMFLAG_STEPVDDC;
+
+	if (pi->mem_gddr5)
+		table->SystemFlags |= PPSMC_SYSTEMFLAG_GDDR5;
+
+	if (ulv->supported) {
+		ret = ci_populate_ulv_state(rdev, &pi->smc_state_table.Ulv);
+		if (ret)
+			return ret;
+		WREG32_SMC(CG_ULV_PARAMETER, ulv->cg_ulv_parameter);
+	}
+
+	ret = ci_populate_all_graphic_levels(rdev);
+	if (ret)
+		return ret;
+
+	ret = ci_populate_all_memory_levels(rdev);
+	if (ret)
+		return ret;
+
+	ci_populate_smc_link_level(rdev, table);
+
+	ret = ci_populate_smc_acpi_level(rdev, table);
+	if (ret)
+		return ret;
+
+	ret = ci_populate_smc_vce_level(rdev, table);
+	if (ret)
+		return ret;
+
+	ret = ci_populate_smc_acp_level(rdev, table);
+	if (ret)
+		return ret;
+
+	ret = ci_populate_smc_samu_level(rdev, table);
+	if (ret)
+		return ret;
+
+	ret = ci_do_program_memory_timing_parameters(rdev);
+	if (ret)
+		return ret;
+
+	ret = ci_populate_smc_uvd_level(rdev, table);
+	if (ret)
+		return ret;
+
+	table->UvdBootLevel  = 0;
+	table->VceBootLevel  = 0;
+	table->AcpBootLevel  = 0;
+	table->SamuBootLevel  = 0;
+	table->GraphicsBootLevel  = 0;
+	table->MemoryBootLevel  = 0;
+
+	ret = ci_find_boot_level(&pi->dpm_table.sclk_table,
+				 pi->vbios_boot_state.sclk_bootup_value,
+				 (u32 *)&pi->smc_state_table.GraphicsBootLevel);
+
+	ret = ci_find_boot_level(&pi->dpm_table.mclk_table,
+				 pi->vbios_boot_state.mclk_bootup_value,
+				 (u32 *)&pi->smc_state_table.MemoryBootLevel);
+
+	table->BootVddc = pi->vbios_boot_state.vddc_bootup_value;
+	table->BootVddci = pi->vbios_boot_state.vddci_bootup_value;
+	table->BootMVdd = pi->vbios_boot_state.mvdd_bootup_value;
+
+	ci_populate_smc_initial_state(rdev, radeon_boot_state);
+
+	ret = ci_populate_bapm_parameters_in_dpm_table(rdev);
+	if (ret)
+		return ret;
+
+	table->UVDInterval = 1;
+	table->VCEInterval = 1;
+	table->ACPInterval = 1;
+	table->SAMUInterval = 1;
+	table->GraphicsVoltageChangeEnable = 1;
+	table->GraphicsThermThrottleEnable = 1;
+	table->GraphicsInterval = 1;
+	table->VoltageInterval = 1;
+	table->ThermalInterval = 1;
+	table->TemperatureLimitHigh = (u16)((pi->thermal_temp_setting.temperature_high *
+					     CISLANDS_Q88_FORMAT_CONVERSION_UNIT) / 1000);
+	table->TemperatureLimitLow = (u16)((pi->thermal_temp_setting.temperature_low *
+					    CISLANDS_Q88_FORMAT_CONVERSION_UNIT) / 1000);
+	table->MemoryVoltageChangeEnable = 1;
+	table->MemoryInterval = 1;
+	table->VoltageResponseTime = 0;
+	table->VddcVddciDelta = 4000;
+	table->PhaseResponseTime = 0;
+	table->MemoryThermThrottleEnable = 1;
+	table->PCIeBootLinkLevel = 0;
+	table->PCIeGenInterval = 1;
+	if (pi->voltage_control == CISLANDS_VOLTAGE_CONTROL_BY_SVID2)
+		table->SVI2Enable  = 1;
+	else
+		table->SVI2Enable  = 0;
+
+	table->ThermGpio = 17;
+	table->SclkStepSize = 0x4000;
+
+	table->SystemFlags = cpu_to_be32(table->SystemFlags);
+	table->SmioMaskVddcVid = cpu_to_be32(table->SmioMaskVddcVid);
+	table->SmioMaskVddcPhase = cpu_to_be32(table->SmioMaskVddcPhase);
+	table->SmioMaskVddciVid = cpu_to_be32(table->SmioMaskVddciVid);
+	table->SmioMaskMvddVid = cpu_to_be32(table->SmioMaskMvddVid);
+	table->SclkStepSize = cpu_to_be32(table->SclkStepSize);
+	table->TemperatureLimitHigh = cpu_to_be16(table->TemperatureLimitHigh);
+	table->TemperatureLimitLow = cpu_to_be16(table->TemperatureLimitLow);
+	table->VddcVddciDelta = cpu_to_be16(table->VddcVddciDelta);
+	table->VoltageResponseTime = cpu_to_be16(table->VoltageResponseTime);
+	table->PhaseResponseTime = cpu_to_be16(table->PhaseResponseTime);
+	table->BootVddc = cpu_to_be16(table->BootVddc * VOLTAGE_SCALE);
+	table->BootVddci = cpu_to_be16(table->BootVddci * VOLTAGE_SCALE);
+	table->BootMVdd = cpu_to_be16(table->BootMVdd * VOLTAGE_SCALE);
+
+	ret = ci_copy_bytes_to_smc(rdev,
+				   pi->dpm_table_start +
+				   offsetof(SMU7_Discrete_DpmTable, SystemFlags),
+				   (u8 *)&table->SystemFlags,
+				   sizeof(SMU7_Discrete_DpmTable) - 3 * sizeof(SMU7_PIDController),
+				   pi->sram_end);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static void ci_trim_single_dpm_states(struct radeon_device *rdev,
+				      struct ci_single_dpm_table *dpm_table,
+				      u32 low_limit, u32 high_limit)
+{
+	u32 i;
+
+	for (i = 0; i < dpm_table->count; i++) {
+		if ((dpm_table->dpm_levels[i].value < low_limit) ||
+		    (dpm_table->dpm_levels[i].value > high_limit))
+			dpm_table->dpm_levels[i].enabled = false;
+		else
+			dpm_table->dpm_levels[i].enabled = true;
+	}
+}
+
+static void ci_trim_pcie_dpm_states(struct radeon_device *rdev,
+				    u32 speed_low, u32 lanes_low,
+				    u32 speed_high, u32 lanes_high)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	struct ci_single_dpm_table *pcie_table = &pi->dpm_table.pcie_speed_table;
+	u32 i, j;
+
+	for (i = 0; i < pcie_table->count; i++) {
+		if ((pcie_table->dpm_levels[i].value < speed_low) ||
+		    (pcie_table->dpm_levels[i].param1 < lanes_low) ||
+		    (pcie_table->dpm_levels[i].value > speed_high) ||
+		    (pcie_table->dpm_levels[i].param1 > lanes_high))
+			pcie_table->dpm_levels[i].enabled = false;
+		else
+			pcie_table->dpm_levels[i].enabled = true;
+	}
+
+	for (i = 0; i < pcie_table->count; i++) {
+		if (pcie_table->dpm_levels[i].enabled) {
+			for (j = i + 1; j < pcie_table->count; j++) {
+				if (pcie_table->dpm_levels[j].enabled) {
+					if ((pcie_table->dpm_levels[i].value == pcie_table->dpm_levels[j].value) &&
+					    (pcie_table->dpm_levels[i].param1 == pcie_table->dpm_levels[j].param1))
+						pcie_table->dpm_levels[j].enabled = false;
+				}
+			}
+		}
+	}
+}
+
+static int ci_trim_dpm_states(struct radeon_device *rdev,
+			      struct radeon_ps *radeon_state)
+{
+	struct ci_ps *state = ci_get_ps(radeon_state);
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	u32 high_limit_count;
+
+	if (state->performance_level_count < 1)
+		return -EINVAL;
+
+	if (state->performance_level_count == 1)
+		high_limit_count = 0;
+	else
+		high_limit_count = 1;
+
+	ci_trim_single_dpm_states(rdev,
+				  &pi->dpm_table.sclk_table,
+				  state->performance_levels[0].sclk,
+				  state->performance_levels[high_limit_count].sclk);
+
+	ci_trim_single_dpm_states(rdev,
+				  &pi->dpm_table.mclk_table,
+				  state->performance_levels[0].mclk,
+				  state->performance_levels[high_limit_count].mclk);
+
+	ci_trim_pcie_dpm_states(rdev,
+				state->performance_levels[0].pcie_gen,
+				state->performance_levels[0].pcie_lane,
+				state->performance_levels[high_limit_count].pcie_gen,
+				state->performance_levels[high_limit_count].pcie_lane);
+
+	return 0;
+}
+
+static int ci_apply_disp_minimum_voltage_request(struct radeon_device *rdev)
+{
+	struct radeon_clock_voltage_dependency_table *disp_voltage_table =
+		&rdev->pm.dpm.dyn_state.vddc_dependency_on_dispclk;
+	struct radeon_clock_voltage_dependency_table *vddc_table =
+		&rdev->pm.dpm.dyn_state.vddc_dependency_on_sclk;
+	u32 requested_voltage = 0;
+	u32 i;
+
+	if (disp_voltage_table == NULL)
+		return -EINVAL;
+	if (!disp_voltage_table->count)
+		return -EINVAL;
+
+	for (i = 0; i < disp_voltage_table->count; i++) {
+		if (rdev->clock.current_dispclk == disp_voltage_table->entries[i].clk)
+			requested_voltage = disp_voltage_table->entries[i].v;
+	}
+
+	for (i = 0; i < vddc_table->count; i++) {
+		if (requested_voltage <= vddc_table->entries[i].v) {
+			requested_voltage = vddc_table->entries[i].v;
+			return (ci_send_msg_to_smc_with_parameter(rdev,
+								  PPSMC_MSG_VddC_Request,
+								  requested_voltage * VOLTAGE_SCALE) == PPSMC_Result_OK) ?
+				0 : -EINVAL;
+		}
+	}
+
+	return -EINVAL;
+}
+
+static int ci_upload_dpm_level_enable_mask(struct radeon_device *rdev)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	PPSMC_Result result;
+
+	if (!pi->sclk_dpm_key_disabled) {
+		if (pi->dpm_level_enable_mask.sclk_dpm_enable_mask) {
+			result = ci_send_msg_to_smc_with_parameter(rdev,
+								   PPSMC_MSG_SCLKDPM_SetEnabledMask,
+								   pi->dpm_level_enable_mask.sclk_dpm_enable_mask);
+			if (result != PPSMC_Result_OK)
+				return -EINVAL;
+		}
+	}
+
+	if (!pi->mclk_dpm_key_disabled) {
+		if (pi->dpm_level_enable_mask.mclk_dpm_enable_mask) {
+			result = ci_send_msg_to_smc_with_parameter(rdev,
+								   PPSMC_MSG_MCLKDPM_SetEnabledMask,
+								   pi->dpm_level_enable_mask.mclk_dpm_enable_mask);
+			if (result != PPSMC_Result_OK)
+				return -EINVAL;
+		}
+	}
+
+	if (!pi->pcie_dpm_key_disabled) {
+		if (pi->dpm_level_enable_mask.pcie_dpm_enable_mask) {
+			result = ci_send_msg_to_smc_with_parameter(rdev,
+								   PPSMC_MSG_PCIeDPM_SetEnabledMask,
+								   pi->dpm_level_enable_mask.pcie_dpm_enable_mask);
+			if (result != PPSMC_Result_OK)
+				return -EINVAL;
+		}
+	}
+
+	ci_apply_disp_minimum_voltage_request(rdev);
+
+	return 0;
+}
+
+static void ci_find_dpm_states_clocks_in_dpm_table(struct radeon_device *rdev,
+						   struct radeon_ps *radeon_state)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	struct ci_ps *state = ci_get_ps(radeon_state);
+	struct ci_single_dpm_table *sclk_table = &pi->dpm_table.sclk_table;
+	u32 sclk = state->performance_levels[state->performance_level_count-1].sclk;
+	struct ci_single_dpm_table *mclk_table = &pi->dpm_table.mclk_table;
+	u32 mclk = state->performance_levels[state->performance_level_count-1].mclk;
+	u32 i;
+
+	pi->need_update_smu7_dpm_table = 0;
+
+	for (i = 0; i < sclk_table->count; i++) {
+		if (sclk == sclk_table->dpm_levels[i].value)
+			break;
+	}
+
+	if (i >= sclk_table->count) {
+		pi->need_update_smu7_dpm_table |= DPMTABLE_OD_UPDATE_SCLK;
+	} else {
+		/* XXX check display min clock requirements */
+		if (0 != CISLAND_MINIMUM_ENGINE_CLOCK)
+			pi->need_update_smu7_dpm_table |= DPMTABLE_UPDATE_SCLK;
+	}
+
+	for (i = 0; i < mclk_table->count; i++) {
+		if (mclk == mclk_table->dpm_levels[i].value)
+			break;
+	}
+
+	if (i >= mclk_table->count)
+		pi->need_update_smu7_dpm_table |= DPMTABLE_OD_UPDATE_MCLK;
+
+	if (rdev->pm.dpm.current_active_crtc_count !=
+	    rdev->pm.dpm.new_active_crtc_count)
+		pi->need_update_smu7_dpm_table |= DPMTABLE_UPDATE_MCLK;
+}
+
+static int ci_populate_and_upload_sclk_mclk_dpm_levels(struct radeon_device *rdev,
+						       struct radeon_ps *radeon_state)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	struct ci_ps *state = ci_get_ps(radeon_state);
+	u32 sclk = state->performance_levels[state->performance_level_count-1].sclk;
+	u32 mclk = state->performance_levels[state->performance_level_count-1].mclk;
+	struct ci_dpm_table *dpm_table = &pi->dpm_table;
+	int ret;
+
+	if (!pi->need_update_smu7_dpm_table)
+		return 0;
+
+	if (pi->need_update_smu7_dpm_table & DPMTABLE_OD_UPDATE_SCLK)
+		dpm_table->sclk_table.dpm_levels[dpm_table->sclk_table.count-1].value = sclk;
+
+	if (pi->need_update_smu7_dpm_table & DPMTABLE_OD_UPDATE_MCLK)
+		dpm_table->mclk_table.dpm_levels[dpm_table->mclk_table.count-1].value = mclk;
+
+	if (pi->need_update_smu7_dpm_table & (DPMTABLE_OD_UPDATE_SCLK | DPMTABLE_UPDATE_SCLK)) {
+		ret = ci_populate_all_graphic_levels(rdev);
+		if (ret)
+			return ret;
+	}
+
+	if (pi->need_update_smu7_dpm_table & (DPMTABLE_OD_UPDATE_MCLK | DPMTABLE_UPDATE_MCLK)) {
+		ret = ci_populate_all_memory_levels(rdev);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int ci_enable_uvd_dpm(struct radeon_device *rdev, bool enable)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	const struct radeon_clock_and_voltage_limits *max_limits;
+	int i;
+
+	if (rdev->pm.dpm.ac_power)
+		max_limits = &rdev->pm.dpm.dyn_state.max_clock_voltage_on_ac;
+	else
+		max_limits = &rdev->pm.dpm.dyn_state.max_clock_voltage_on_dc;
+
+	if (enable) {
+		pi->dpm_level_enable_mask.uvd_dpm_enable_mask = 0;
+
+		for (i = rdev->pm.dpm.dyn_state.uvd_clock_voltage_dependency_table.count - 1; i >= 0; i--) {
+			if (rdev->pm.dpm.dyn_state.uvd_clock_voltage_dependency_table.entries[i].v <= max_limits->vddc) {
+				pi->dpm_level_enable_mask.uvd_dpm_enable_mask |= 1 << i;
+
+				if (!pi->caps_uvd_dpm)
+					break;
+			}
+		}
+
+		ci_send_msg_to_smc_with_parameter(rdev,
+						  PPSMC_MSG_UVDDPM_SetEnabledMask,
+						  pi->dpm_level_enable_mask.uvd_dpm_enable_mask);
+
+		if (pi->last_mclk_dpm_enable_mask & 0x1) {
+			pi->uvd_enabled = true;
+			pi->dpm_level_enable_mask.mclk_dpm_enable_mask &= 0xFFFFFFFE;
+			ci_send_msg_to_smc_with_parameter(rdev,
+							  PPSMC_MSG_MCLKDPM_SetEnabledMask,
+							  pi->dpm_level_enable_mask.mclk_dpm_enable_mask);
+		}
+	} else {
+		if (pi->last_mclk_dpm_enable_mask & 0x1) {
+			pi->uvd_enabled = false;
+			pi->dpm_level_enable_mask.mclk_dpm_enable_mask |= 1;
+			ci_send_msg_to_smc_with_parameter(rdev,
+							  PPSMC_MSG_MCLKDPM_SetEnabledMask,
+							  pi->dpm_level_enable_mask.mclk_dpm_enable_mask);
+		}
+	}
+
+	return (ci_send_msg_to_smc(rdev, enable ?
+				   PPSMC_MSG_UVDDPM_Enable : PPSMC_MSG_UVDDPM_Disable) == PPSMC_Result_OK) ?
+		0 : -EINVAL;
+}
+
+#if 0
+static int ci_enable_vce_dpm(struct radeon_device *rdev, bool enable)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	const struct radeon_clock_and_voltage_limits *max_limits;
+	int i;
+
+	if (rdev->pm.dpm.ac_power)
+		max_limits = &rdev->pm.dpm.dyn_state.max_clock_voltage_on_ac;
+	else
+		max_limits = &rdev->pm.dpm.dyn_state.max_clock_voltage_on_dc;
+
+	if (enable) {
+		pi->dpm_level_enable_mask.vce_dpm_enable_mask = 0;
+		for (i = rdev->pm.dpm.dyn_state.vce_clock_voltage_dependency_table.count - 1; i >= 0; i--) {
+			if (rdev->pm.dpm.dyn_state.vce_clock_voltage_dependency_table.entries[i].v <= max_limits->vddc) {
+				pi->dpm_level_enable_mask.vce_dpm_enable_mask |= 1 << i;
+
+				if (!pi->caps_vce_dpm)
+					break;
+			}
+		}
+
+		ci_send_msg_to_smc_with_parameter(rdev,
+						  PPSMC_MSG_VCEDPM_SetEnabledMask,
+						  pi->dpm_level_enable_mask.vce_dpm_enable_mask);
+	}
+
+	return (ci_send_msg_to_smc(rdev, enable ?
+				   PPSMC_MSG_VCEDPM_Enable : PPSMC_MSG_VCEDPM_Disable) == PPSMC_Result_OK) ?
+		0 : -EINVAL;
+}
+
+static int ci_enable_samu_dpm(struct radeon_device *rdev, bool enable)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	const struct radeon_clock_and_voltage_limits *max_limits;
+	int i;
+
+	if (rdev->pm.dpm.ac_power)
+		max_limits = &rdev->pm.dpm.dyn_state.max_clock_voltage_on_ac;
+	else
+		max_limits = &rdev->pm.dpm.dyn_state.max_clock_voltage_on_dc;
+
+	if (enable) {
+		pi->dpm_level_enable_mask.samu_dpm_enable_mask = 0;
+		for (i = rdev->pm.dpm.dyn_state.samu_clock_voltage_dependency_table.count - 1; i >= 0; i--) {
+			if (rdev->pm.dpm.dyn_state.samu_clock_voltage_dependency_table.entries[i].v <= max_limits->vddc) {
+				pi->dpm_level_enable_mask.samu_dpm_enable_mask |= 1 << i;
+
+				if (!pi->caps_samu_dpm)
+					break;
+			}
+		}
+
+		ci_send_msg_to_smc_with_parameter(rdev,
+						  PPSMC_MSG_SAMUDPM_SetEnabledMask,
+						  pi->dpm_level_enable_mask.samu_dpm_enable_mask);
+	}
+	return (ci_send_msg_to_smc(rdev, enable ?
+				   PPSMC_MSG_SAMUDPM_Enable : PPSMC_MSG_SAMUDPM_Disable) == PPSMC_Result_OK) ?
+		0 : -EINVAL;
+}
+
+static int ci_enable_acp_dpm(struct radeon_device *rdev, bool enable)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	const struct radeon_clock_and_voltage_limits *max_limits;
+	int i;
+
+	if (rdev->pm.dpm.ac_power)
+		max_limits = &rdev->pm.dpm.dyn_state.max_clock_voltage_on_ac;
+	else
+		max_limits = &rdev->pm.dpm.dyn_state.max_clock_voltage_on_dc;
+
+	if (enable) {
+		pi->dpm_level_enable_mask.acp_dpm_enable_mask = 0;
+		for (i = rdev->pm.dpm.dyn_state.acp_clock_voltage_dependency_table.count - 1; i >= 0; i--) {
+			if (rdev->pm.dpm.dyn_state.acp_clock_voltage_dependency_table.entries[i].v <= max_limits->vddc) {
+				pi->dpm_level_enable_mask.acp_dpm_enable_mask |= 1 << i;
+
+				if (!pi->caps_acp_dpm)
+					break;
+			}
+		}
+
+		ci_send_msg_to_smc_with_parameter(rdev,
+						  PPSMC_MSG_ACPDPM_SetEnabledMask,
+						  pi->dpm_level_enable_mask.acp_dpm_enable_mask);
+	}
+
+	return (ci_send_msg_to_smc(rdev, enable ?
+				   PPSMC_MSG_ACPDPM_Enable : PPSMC_MSG_ACPDPM_Disable) == PPSMC_Result_OK) ?
+		0 : -EINVAL;
+}
+#endif
+
+static int ci_update_uvd_dpm(struct radeon_device *rdev, bool gate)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	u32 tmp;
+
+	if (!gate) {
+		if (pi->caps_uvd_dpm ||
+		    (rdev->pm.dpm.dyn_state.uvd_clock_voltage_dependency_table.count <= 0))
+			pi->smc_state_table.UvdBootLevel = 0;
+		else
+			pi->smc_state_table.UvdBootLevel =
+				rdev->pm.dpm.dyn_state.uvd_clock_voltage_dependency_table.count - 1;
+
+		tmp = RREG32_SMC(DPM_TABLE_475);
+		tmp &= ~UvdBootLevel_MASK;
+		tmp |= UvdBootLevel(pi->smc_state_table.UvdBootLevel);
+		WREG32_SMC(DPM_TABLE_475, tmp);
+	}
+
+	return ci_enable_uvd_dpm(rdev, !gate);
+}
+
+#if 0
+static u8 ci_get_vce_boot_level(struct radeon_device *rdev)
+{
+	u8 i;
+	u32 min_evclk = 30000; /* ??? */
+	struct radeon_vce_clock_voltage_dependency_table *table =
+		&rdev->pm.dpm.dyn_state.vce_clock_voltage_dependency_table;
+
+	for (i = 0; i < table->count; i++) {
+		if (table->entries[i].evclk >= min_evclk)
+			return i;
+	}
+
+	return table->count - 1;
+}
+
+static int ci_update_vce_dpm(struct radeon_device *rdev,
+			     struct radeon_ps *radeon_new_state,
+			     struct radeon_ps *radeon_current_state)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	bool new_vce_clock_non_zero = (radeon_new_state->evclk != 0);
+	bool old_vce_clock_non_zero = (radeon_current_state->evclk != 0);
+	int ret = 0;
+	u32 tmp;
+
+	if (new_vce_clock_non_zero != old_vce_clock_non_zero) {
+		if (new_vce_clock_non_zero) {
+			pi->smc_state_table.VceBootLevel = ci_get_vce_boot_level(rdev);
+
+			tmp = RREG32_SMC(DPM_TABLE_475);
+			tmp &= ~VceBootLevel_MASK;
+			tmp |= VceBootLevel(pi->smc_state_table.VceBootLevel);
+			WREG32_SMC(DPM_TABLE_475, tmp);
+
+			ret = ci_enable_vce_dpm(rdev, true);
+		} else {
+			ret = ci_enable_vce_dpm(rdev, false);
+		}
+	}
+	return ret;
+}
+
+static int ci_update_samu_dpm(struct radeon_device *rdev, bool gate)
+{
+	return ci_enable_samu_dpm(rdev, gate);
+}
+
+static int ci_update_acp_dpm(struct radeon_device *rdev, bool gate)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	u32 tmp;
+
+	if (!gate) {
+		pi->smc_state_table.AcpBootLevel = 0;
+
+		tmp = RREG32_SMC(DPM_TABLE_475);
+		tmp &= ~AcpBootLevel_MASK;
+		tmp |= AcpBootLevel(pi->smc_state_table.AcpBootLevel);
+		WREG32_SMC(DPM_TABLE_475, tmp);
+	}
+
+	return ci_enable_acp_dpm(rdev, !gate);
+}
+#endif
+
+static int ci_generate_dpm_level_enable_mask(struct radeon_device *rdev,
+					     struct radeon_ps *radeon_state)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	int ret;
+
+	ret = ci_trim_dpm_states(rdev, radeon_state);
+	if (ret)
+		return ret;
+
+	pi->dpm_level_enable_mask.sclk_dpm_enable_mask =
+		ci_get_dpm_level_enable_mask_value(&pi->dpm_table.sclk_table);
+	pi->dpm_level_enable_mask.mclk_dpm_enable_mask =
+		ci_get_dpm_level_enable_mask_value(&pi->dpm_table.mclk_table);
+	pi->last_mclk_dpm_enable_mask =
+		pi->dpm_level_enable_mask.mclk_dpm_enable_mask;
+	if (pi->uvd_enabled) {
+		if (pi->dpm_level_enable_mask.mclk_dpm_enable_mask & 1)
+			pi->dpm_level_enable_mask.mclk_dpm_enable_mask &= 0xFFFFFFFE;
+	}
+	pi->dpm_level_enable_mask.pcie_dpm_enable_mask =
+		ci_get_dpm_level_enable_mask_value(&pi->dpm_table.pcie_speed_table);
+
+	return 0;
+}
+
+static u32 ci_get_lowest_enabled_level(struct radeon_device *rdev,
+				       u32 level_mask)
+{
+	u32 level = 0;
+
+	while ((level_mask & (1 << level)) == 0)
+		level++;
+
+	return level;
+}
+
+
+int ci_dpm_force_performance_level(struct radeon_device *rdev,
+				   enum radeon_dpm_forced_level level)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	PPSMC_Result smc_result;
+	u32 tmp, levels, i;
+	int ret;
+
+	if (level == RADEON_DPM_FORCED_LEVEL_HIGH) {
+		if ((!pi->sclk_dpm_key_disabled) &&
+		    pi->dpm_level_enable_mask.sclk_dpm_enable_mask) {
+			levels = 0;
+			tmp = pi->dpm_level_enable_mask.sclk_dpm_enable_mask;
+			while (tmp >>= 1)
+				levels++;
+			if (levels) {
+				ret = ci_dpm_force_state_sclk(rdev, levels);
+				if (ret)
+					return ret;
+				for (i = 0; i < rdev->usec_timeout; i++) {
+					tmp = (RREG32_SMC(TARGET_AND_CURRENT_PROFILE_INDEX) &
+					       CURR_SCLK_INDEX_MASK) >> CURR_SCLK_INDEX_SHIFT;
+					if (tmp == levels)
+						break;
+					udelay(1);
+				}
+			}
+		}
+		if ((!pi->mclk_dpm_key_disabled) &&
+		    pi->dpm_level_enable_mask.mclk_dpm_enable_mask) {
+			levels = 0;
+			tmp = pi->dpm_level_enable_mask.mclk_dpm_enable_mask;
+			while (tmp >>= 1)
+				levels++;
+			if (levels) {
+				ret = ci_dpm_force_state_mclk(rdev, levels);
+				if (ret)
+					return ret;
+				for (i = 0; i < rdev->usec_timeout; i++) {
+					tmp = (RREG32_SMC(TARGET_AND_CURRENT_PROFILE_INDEX) &
+					       CURR_MCLK_INDEX_MASK) >> CURR_MCLK_INDEX_SHIFT;
+					if (tmp == levels)
+						break;
+					udelay(1);
+				}
+			}
+		}
+		if ((!pi->pcie_dpm_key_disabled) &&
+		    pi->dpm_level_enable_mask.pcie_dpm_enable_mask) {
+			levels = 0;
+			tmp = pi->dpm_level_enable_mask.pcie_dpm_enable_mask;
+			while (tmp >>= 1)
+				levels++;
+			if (levels) {
+				ret = ci_dpm_force_state_pcie(rdev, level);
+				if (ret)
+					return ret;
+				for (i = 0; i < rdev->usec_timeout; i++) {
+					tmp = (RREG32_SMC(TARGET_AND_CURRENT_PROFILE_INDEX_1) &
+					       CURR_PCIE_INDEX_MASK) >> CURR_PCIE_INDEX_SHIFT;
+					if (tmp == levels)
+						break;
+					udelay(1);
+				}
+			}
+		}
+	} else if (level == RADEON_DPM_FORCED_LEVEL_LOW) {
+		if ((!pi->sclk_dpm_key_disabled) &&
+		    pi->dpm_level_enable_mask.sclk_dpm_enable_mask) {
+			levels = ci_get_lowest_enabled_level(rdev,
+							     pi->dpm_level_enable_mask.sclk_dpm_enable_mask);
+			ret = ci_dpm_force_state_sclk(rdev, levels);
+			if (ret)
+				return ret;
+			for (i = 0; i < rdev->usec_timeout; i++) {
+				tmp = (RREG32_SMC(TARGET_AND_CURRENT_PROFILE_INDEX) &
+				       CURR_SCLK_INDEX_MASK) >> CURR_SCLK_INDEX_SHIFT;
+				if (tmp == levels)
+					break;
+				udelay(1);
+			}
+		}
+		if ((!pi->mclk_dpm_key_disabled) &&
+		    pi->dpm_level_enable_mask.mclk_dpm_enable_mask) {
+			levels = ci_get_lowest_enabled_level(rdev,
+							     pi->dpm_level_enable_mask.mclk_dpm_enable_mask);
+			ret = ci_dpm_force_state_mclk(rdev, levels);
+			if (ret)
+				return ret;
+			for (i = 0; i < rdev->usec_timeout; i++) {
+				tmp = (RREG32_SMC(TARGET_AND_CURRENT_PROFILE_INDEX) &
+				       CURR_MCLK_INDEX_MASK) >> CURR_MCLK_INDEX_SHIFT;
+				if (tmp == levels)
+					break;
+				udelay(1);
+			}
+		}
+		if ((!pi->pcie_dpm_key_disabled) &&
+		    pi->dpm_level_enable_mask.pcie_dpm_enable_mask) {
+			levels = ci_get_lowest_enabled_level(rdev,
+							     pi->dpm_level_enable_mask.pcie_dpm_enable_mask);
+			ret = ci_dpm_force_state_pcie(rdev, levels);
+			if (ret)
+				return ret;
+			for (i = 0; i < rdev->usec_timeout; i++) {
+				tmp = (RREG32_SMC(TARGET_AND_CURRENT_PROFILE_INDEX_1) &
+				       CURR_PCIE_INDEX_MASK) >> CURR_PCIE_INDEX_SHIFT;
+				if (tmp == levels)
+					break;
+				udelay(1);
+			}
+		}
+	} else if (level == RADEON_DPM_FORCED_LEVEL_AUTO) {
+		if (!pi->sclk_dpm_key_disabled) {
+			smc_result = ci_send_msg_to_smc(rdev, PPSMC_MSG_NoForcedLevel);
+			if (smc_result != PPSMC_Result_OK)
+				return -EINVAL;
+		}
+		if (!pi->mclk_dpm_key_disabled) {
+			smc_result = ci_send_msg_to_smc(rdev, PPSMC_MSG_MCLKDPM_NoForcedLevel);
+			if (smc_result != PPSMC_Result_OK)
+				return -EINVAL;
+		}
+		if (!pi->pcie_dpm_key_disabled) {
+			smc_result = ci_send_msg_to_smc(rdev, PPSMC_MSG_PCIeDPM_UnForceLevel);
+			if (smc_result != PPSMC_Result_OK)
+				return -EINVAL;
+		}
+	}
+
+	rdev->pm.dpm.forced_level = level;
+
+	return 0;
+}
+
+static int ci_set_mc_special_registers(struct radeon_device *rdev,
+				       struct ci_mc_reg_table *table)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	u8 i, j, k;
+	u32 temp_reg;
+
+	for (i = 0, j = table->last; i < table->last; i++) {
+		if (j >= SMU7_DISCRETE_MC_REGISTER_ARRAY_SIZE)
+			return -EINVAL;
+		switch(table->mc_reg_address[i].s1 << 2) {
+		case MC_SEQ_MISC1:
+			temp_reg = RREG32(MC_PMG_CMD_EMRS);
+			table->mc_reg_address[j].s1 = MC_PMG_CMD_EMRS >> 2;
+			table->mc_reg_address[j].s0 = MC_SEQ_PMG_CMD_EMRS_LP >> 2;
+			for (k = 0; k < table->num_entries; k++) {
+				table->mc_reg_table_entry[k].mc_data[j] =
+					((temp_reg & 0xffff0000)) | ((table->mc_reg_table_entry[k].mc_data[i] & 0xffff0000) >> 16);
+			}
+			j++;
+			if (j >= SMU7_DISCRETE_MC_REGISTER_ARRAY_SIZE)
+				return -EINVAL;
+
+			temp_reg = RREG32(MC_PMG_CMD_MRS);
+			table->mc_reg_address[j].s1 = MC_PMG_CMD_MRS >> 2;
+			table->mc_reg_address[j].s0 = MC_SEQ_PMG_CMD_MRS_LP >> 2;
+			for (k = 0; k < table->num_entries; k++) {
+				table->mc_reg_table_entry[k].mc_data[j] =
+					(temp_reg & 0xffff0000) | (table->mc_reg_table_entry[k].mc_data[i] & 0x0000ffff);
+				if (!pi->mem_gddr5)
+					table->mc_reg_table_entry[k].mc_data[j] |= 0x100;
+			}
+			j++;
+			if (j > SMU7_DISCRETE_MC_REGISTER_ARRAY_SIZE)
+				return -EINVAL;
+
+			if (!pi->mem_gddr5) {
+				table->mc_reg_address[j].s1 = MC_PMG_AUTO_CMD >> 2;
+				table->mc_reg_address[j].s0 = MC_PMG_AUTO_CMD >> 2;
+				for (k = 0; k < table->num_entries; k++) {
+					table->mc_reg_table_entry[k].mc_data[j] =
+						(table->mc_reg_table_entry[k].mc_data[i] & 0xffff0000) >> 16;
+				}
+				j++;
+				if (j > SMU7_DISCRETE_MC_REGISTER_ARRAY_SIZE)
+					return -EINVAL;
+			}
+			break;
+		case MC_SEQ_RESERVE_M:
+			temp_reg = RREG32(MC_PMG_CMD_MRS1);
+			table->mc_reg_address[j].s1 = MC_PMG_CMD_MRS1 >> 2;
+			table->mc_reg_address[j].s0 = MC_SEQ_PMG_CMD_MRS1_LP >> 2;
+			for (k = 0; k < table->num_entries; k++) {
+				table->mc_reg_table_entry[k].mc_data[j] =
+					(temp_reg & 0xffff0000) | (table->mc_reg_table_entry[k].mc_data[i] & 0x0000ffff);
+			}
+			j++;
+			if (j > SMU7_DISCRETE_MC_REGISTER_ARRAY_SIZE)
+				return -EINVAL;
+			break;
+		default:
+			break;
+		}
+
+	}
+
+	table->last = j;
+
+	return 0;
+}
+
+static bool ci_check_s0_mc_reg_index(u16 in_reg, u16 *out_reg)
+{
+	bool result = true;
+
+	switch(in_reg) {
+	case MC_SEQ_RAS_TIMING >> 2:
+		*out_reg = MC_SEQ_RAS_TIMING_LP >> 2;
+		break;
+	case MC_SEQ_DLL_STBY >> 2:
+		*out_reg = MC_SEQ_DLL_STBY_LP >> 2;
+		break;
+	case MC_SEQ_G5PDX_CMD0 >> 2:
+		*out_reg = MC_SEQ_G5PDX_CMD0_LP >> 2;
+		break;
+	case MC_SEQ_G5PDX_CMD1 >> 2:
+		*out_reg = MC_SEQ_G5PDX_CMD1_LP >> 2;
+		break;
+	case MC_SEQ_G5PDX_CTRL >> 2:
+		*out_reg = MC_SEQ_G5PDX_CTRL_LP >> 2;
+		break;
+	case MC_SEQ_CAS_TIMING >> 2:
+		*out_reg = MC_SEQ_CAS_TIMING_LP >> 2;
+            break;
+	case MC_SEQ_MISC_TIMING >> 2:
+		*out_reg = MC_SEQ_MISC_TIMING_LP >> 2;
+		break;
+	case MC_SEQ_MISC_TIMING2 >> 2:
+		*out_reg = MC_SEQ_MISC_TIMING2_LP >> 2;
+		break;
+	case MC_SEQ_PMG_DVS_CMD >> 2:
+		*out_reg = MC_SEQ_PMG_DVS_CMD_LP >> 2;
+		break;
+	case MC_SEQ_PMG_DVS_CTL >> 2:
+		*out_reg = MC_SEQ_PMG_DVS_CTL_LP >> 2;
+		break;
+	case MC_SEQ_RD_CTL_D0 >> 2:
+		*out_reg = MC_SEQ_RD_CTL_D0_LP >> 2;
+		break;
+	case MC_SEQ_RD_CTL_D1 >> 2:
+		*out_reg = MC_SEQ_RD_CTL_D1_LP >> 2;
+		break;
+	case MC_SEQ_WR_CTL_D0 >> 2:
+		*out_reg = MC_SEQ_WR_CTL_D0_LP >> 2;
+		break;
+	case MC_SEQ_WR_CTL_D1 >> 2:
+		*out_reg = MC_SEQ_WR_CTL_D1_LP >> 2;
+		break;
+	case MC_PMG_CMD_EMRS >> 2:
+		*out_reg = MC_SEQ_PMG_CMD_EMRS_LP >> 2;
+		break;
+	case MC_PMG_CMD_MRS >> 2:
+		*out_reg = MC_SEQ_PMG_CMD_MRS_LP >> 2;
+		break;
+	case MC_PMG_CMD_MRS1 >> 2:
+		*out_reg = MC_SEQ_PMG_CMD_MRS1_LP >> 2;
+		break;
+	case MC_SEQ_PMG_TIMING >> 2:
+		*out_reg = MC_SEQ_PMG_TIMING_LP >> 2;
+		break;
+	case MC_PMG_CMD_MRS2 >> 2:
+		*out_reg = MC_SEQ_PMG_CMD_MRS2_LP >> 2;
+		break;
+	case MC_SEQ_WR_CTL_2 >> 2:
+		*out_reg = MC_SEQ_WR_CTL_2_LP >> 2;
+		break;
+	default:
+		result = false;
+		break;
+	}
+
+	return result;
+}
+
+static void ci_set_valid_flag(struct ci_mc_reg_table *table)
+{
+	u8 i, j;
+
+	for (i = 0; i < table->last; i++) {
+		for (j = 1; j < table->num_entries; j++) {
+			if (table->mc_reg_table_entry[j-1].mc_data[i] !=
+			    table->mc_reg_table_entry[j].mc_data[i]) {
+				table->valid_flag |= 1 << i;
+				break;
+			}
+		}
+	}
+}
+
+static void ci_set_s0_mc_reg_index(struct ci_mc_reg_table *table)
+{
+	u32 i;
+	u16 address;
+
+	for (i = 0; i < table->last; i++) {
+		table->mc_reg_address[i].s0 =
+			ci_check_s0_mc_reg_index(table->mc_reg_address[i].s1, &address) ?
+			address : table->mc_reg_address[i].s1;
+	}
+}
+
+static int ci_copy_vbios_mc_reg_table(const struct atom_mc_reg_table *table,
+				      struct ci_mc_reg_table *ci_table)
+{
+	u8 i, j;
+
+	if (table->last > SMU7_DISCRETE_MC_REGISTER_ARRAY_SIZE)
+		return -EINVAL;
+	if (table->num_entries > MAX_AC_TIMING_ENTRIES)
+		return -EINVAL;
+
+	for (i = 0; i < table->last; i++)
+		ci_table->mc_reg_address[i].s1 = table->mc_reg_address[i].s1;
+
+	ci_table->last = table->last;
+
+	for (i = 0; i < table->num_entries; i++) {
+		ci_table->mc_reg_table_entry[i].mclk_max =
+			table->mc_reg_table_entry[i].mclk_max;
+		for (j = 0; j < table->last; j++)
+			ci_table->mc_reg_table_entry[i].mc_data[j] =
+				table->mc_reg_table_entry[i].mc_data[j];
+	}
+	ci_table->num_entries = table->num_entries;
+
+	return 0;
+}
+
+static int ci_initialize_mc_reg_table(struct radeon_device *rdev)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	struct atom_mc_reg_table *table;
+	struct ci_mc_reg_table *ci_table = &pi->mc_reg_table;
+	u8 module_index = rv770_get_memory_module_index(rdev);
+	int ret;
+
+	table = kzalloc(sizeof(struct atom_mc_reg_table), GFP_KERNEL);
+	if (!table)
+		return -ENOMEM;
+
+	WREG32(MC_SEQ_RAS_TIMING_LP, RREG32(MC_SEQ_RAS_TIMING));
+	WREG32(MC_SEQ_CAS_TIMING_LP, RREG32(MC_SEQ_CAS_TIMING));
+	WREG32(MC_SEQ_DLL_STBY_LP, RREG32(MC_SEQ_DLL_STBY));
+	WREG32(MC_SEQ_G5PDX_CMD0_LP, RREG32(MC_SEQ_G5PDX_CMD0));
+	WREG32(MC_SEQ_G5PDX_CMD1_LP, RREG32(MC_SEQ_G5PDX_CMD1));
+	WREG32(MC_SEQ_G5PDX_CTRL_LP, RREG32(MC_SEQ_G5PDX_CTRL));
+	WREG32(MC_SEQ_PMG_DVS_CMD_LP, RREG32(MC_SEQ_PMG_DVS_CMD));
+	WREG32(MC_SEQ_PMG_DVS_CTL_LP, RREG32(MC_SEQ_PMG_DVS_CTL));
+	WREG32(MC_SEQ_MISC_TIMING_LP, RREG32(MC_SEQ_MISC_TIMING));
+	WREG32(MC_SEQ_MISC_TIMING2_LP, RREG32(MC_SEQ_MISC_TIMING2));
+	WREG32(MC_SEQ_PMG_CMD_EMRS_LP, RREG32(MC_PMG_CMD_EMRS));
+	WREG32(MC_SEQ_PMG_CMD_MRS_LP, RREG32(MC_PMG_CMD_MRS));
+	WREG32(MC_SEQ_PMG_CMD_MRS1_LP, RREG32(MC_PMG_CMD_MRS1));
+	WREG32(MC_SEQ_WR_CTL_D0_LP, RREG32(MC_SEQ_WR_CTL_D0));
+	WREG32(MC_SEQ_WR_CTL_D1_LP, RREG32(MC_SEQ_WR_CTL_D1));
+	WREG32(MC_SEQ_RD_CTL_D0_LP, RREG32(MC_SEQ_RD_CTL_D0));
+	WREG32(MC_SEQ_RD_CTL_D1_LP, RREG32(MC_SEQ_RD_CTL_D1));
+	WREG32(MC_SEQ_PMG_TIMING_LP, RREG32(MC_SEQ_PMG_TIMING));
+	WREG32(MC_SEQ_PMG_CMD_MRS2_LP, RREG32(MC_PMG_CMD_MRS2));
+	WREG32(MC_SEQ_WR_CTL_2_LP, RREG32(MC_SEQ_WR_CTL_2));
+
+	ret = radeon_atom_init_mc_reg_table(rdev, module_index, table);
+	if (ret)
+		goto init_mc_done;
+
+        ret = ci_copy_vbios_mc_reg_table(table, ci_table);
+	if (ret)
+		goto init_mc_done;
+
+	ci_set_s0_mc_reg_index(ci_table);
+
+	ret = ci_set_mc_special_registers(rdev, ci_table);
+	if (ret)
+		goto init_mc_done;
+
+	ci_set_valid_flag(ci_table);
+
+init_mc_done:
+	kfree(table);
+
+	return ret;
+}
+
+static int ci_populate_mc_reg_addresses(struct radeon_device *rdev,
+					SMU7_Discrete_MCRegisters *mc_reg_table)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	u32 i, j;
+
+	for (i = 0, j = 0; j < pi->mc_reg_table.last; j++) {
+		if (pi->mc_reg_table.valid_flag & (1 << j)) {
+			if (i >= SMU7_DISCRETE_MC_REGISTER_ARRAY_SIZE)
+				return -EINVAL;
+			mc_reg_table->address[i].s0 = cpu_to_be16(pi->mc_reg_table.mc_reg_address[j].s0);
+			mc_reg_table->address[i].s1 = cpu_to_be16(pi->mc_reg_table.mc_reg_address[j].s1);
+			i++;
+		}
+	}
+
+	mc_reg_table->last = (u8)i;
+
+	return 0;
+}
+
+static void ci_convert_mc_registers(const struct ci_mc_reg_entry *entry,
+				    SMU7_Discrete_MCRegisterSet *data,
+				    u32 num_entries, u32 valid_flag)
+{
+	u32 i, j;
+
+	for (i = 0, j = 0; j < num_entries; j++) {
+		if (valid_flag & (1 << j)) {
+			data->value[i] = cpu_to_be32(entry->mc_data[j]);
+			i++;
+		}
+	}
+}
+
+static void ci_convert_mc_reg_table_entry_to_smc(struct radeon_device *rdev,
+						 const u32 memory_clock,
+						 SMU7_Discrete_MCRegisterSet *mc_reg_table_data)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	u32 i = 0;
+
+	for(i = 0; i < pi->mc_reg_table.num_entries; i++) {
+		if (memory_clock <= pi->mc_reg_table.mc_reg_table_entry[i].mclk_max)
+			break;
+	}
+
+	if ((i == pi->mc_reg_table.num_entries) && (i > 0))
+		--i;
+
+	ci_convert_mc_registers(&pi->mc_reg_table.mc_reg_table_entry[i],
+				mc_reg_table_data, pi->mc_reg_table.last,
+				pi->mc_reg_table.valid_flag);
+}
+
+static void ci_convert_mc_reg_table_to_smc(struct radeon_device *rdev,
+					   SMU7_Discrete_MCRegisters *mc_reg_table)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	u32 i;
+
+	for (i = 0; i < pi->dpm_table.mclk_table.count; i++)
+		ci_convert_mc_reg_table_entry_to_smc(rdev,
+						     pi->dpm_table.mclk_table.dpm_levels[i].value,
+						     &mc_reg_table->data[i]);
+}
+
+static int ci_populate_initial_mc_reg_table(struct radeon_device *rdev)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	int ret;
+
+	memset(&pi->smc_mc_reg_table, 0, sizeof(SMU7_Discrete_MCRegisters));
+
+	ret = ci_populate_mc_reg_addresses(rdev, &pi->smc_mc_reg_table);
+	if (ret)
+		return ret;
+	ci_convert_mc_reg_table_to_smc(rdev, &pi->smc_mc_reg_table);
+
+	return ci_copy_bytes_to_smc(rdev,
+				    pi->mc_reg_table_start,
+				    (u8 *)&pi->smc_mc_reg_table,
+				    sizeof(SMU7_Discrete_MCRegisters),
+				    pi->sram_end);
+}
+
+static int ci_update_and_upload_mc_reg_table(struct radeon_device *rdev)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+
+	if (!(pi->need_update_smu7_dpm_table & DPMTABLE_OD_UPDATE_MCLK))
+		return 0;
+
+	memset(&pi->smc_mc_reg_table, 0, sizeof(SMU7_Discrete_MCRegisters));
+
+	ci_convert_mc_reg_table_to_smc(rdev, &pi->smc_mc_reg_table);
+
+	return ci_copy_bytes_to_smc(rdev,
+				    pi->mc_reg_table_start +
+				    offsetof(SMU7_Discrete_MCRegisters, data[0]),
+				    (u8 *)&pi->smc_mc_reg_table.data[0],
+				    sizeof(SMU7_Discrete_MCRegisterSet) *
+				    pi->dpm_table.mclk_table.count,
+				    pi->sram_end);
+}
+
+static void ci_enable_voltage_control(struct radeon_device *rdev)
+{
+	u32 tmp = RREG32_SMC(GENERAL_PWRMGT);
+
+	tmp |= VOLT_PWRMGT_EN;
+	WREG32_SMC(GENERAL_PWRMGT, tmp);
+}
+
+static enum radeon_pcie_gen ci_get_maximum_link_speed(struct radeon_device *rdev,
+						      struct radeon_ps *radeon_state)
+{
+	struct ci_ps *state = ci_get_ps(radeon_state);
+	int i;
+	u16 pcie_speed, max_speed = 0;
+
+	for (i = 0; i < state->performance_level_count; i++) {
+		pcie_speed = state->performance_levels[i].pcie_gen;
+		if (max_speed < pcie_speed)
+			max_speed = pcie_speed;
+	}
+
+	return max_speed;
+}
+
+static u16 ci_get_current_pcie_speed(struct radeon_device *rdev)
+{
+	u32 speed_cntl = 0;
+
+	speed_cntl = RREG32_PCIE_PORT(PCIE_LC_SPEED_CNTL) & LC_CURRENT_DATA_RATE_MASK;
+	speed_cntl >>= LC_CURRENT_DATA_RATE_SHIFT;
+
+	return (u16)speed_cntl;
+}
+
+static int ci_get_current_pcie_lane_number(struct radeon_device *rdev)
+{
+	u32 link_width = 0;
+
+	link_width = RREG32_PCIE_PORT(PCIE_LC_LINK_WIDTH_CNTL) & LC_LINK_WIDTH_RD_MASK;
+	link_width >>= LC_LINK_WIDTH_RD_SHIFT;
+
+	switch (link_width) {
+	case RADEON_PCIE_LC_LINK_WIDTH_X1:
+		return 1;
+	case RADEON_PCIE_LC_LINK_WIDTH_X2:
+		return 2;
+	case RADEON_PCIE_LC_LINK_WIDTH_X4:
+		return 4;
+	case RADEON_PCIE_LC_LINK_WIDTH_X8:
+		return 8;
+	case RADEON_PCIE_LC_LINK_WIDTH_X12:
+		/* not actually supported */
+		return 12;
+	case RADEON_PCIE_LC_LINK_WIDTH_X0:
+	case RADEON_PCIE_LC_LINK_WIDTH_X16:
+	default:
+		return 16;
+	}
+}
+
+static void ci_request_link_speed_change_before_state_change(struct radeon_device *rdev,
+							     struct radeon_ps *radeon_new_state,
+							     struct radeon_ps *radeon_current_state)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	enum radeon_pcie_gen target_link_speed =
+		ci_get_maximum_link_speed(rdev, radeon_new_state);
+	enum radeon_pcie_gen current_link_speed;
+
+	if (pi->force_pcie_gen == RADEON_PCIE_GEN_INVALID)
+		current_link_speed = ci_get_maximum_link_speed(rdev, radeon_current_state);
+	else
+		current_link_speed = pi->force_pcie_gen;
+
+	pi->force_pcie_gen = RADEON_PCIE_GEN_INVALID;
+	pi->pspp_notify_required = false;
+	if (target_link_speed > current_link_speed) {
+		switch (target_link_speed) {
+#ifdef CONFIG_ACPI
+		case RADEON_PCIE_GEN3:
+			if (radeon_acpi_pcie_performance_request(rdev, PCIE_PERF_REQ_PECI_GEN3, false) == 0)
+				break;
+			pi->force_pcie_gen = RADEON_PCIE_GEN2;
+			if (current_link_speed == RADEON_PCIE_GEN2)
+				break;
+		case RADEON_PCIE_GEN2:
+			if (radeon_acpi_pcie_performance_request(rdev, PCIE_PERF_REQ_PECI_GEN2, false) == 0)
+				break;
+#endif
+		default:
+			pi->force_pcie_gen = ci_get_current_pcie_speed(rdev);
+			break;
+		}
+	} else {
+		if (target_link_speed < current_link_speed)
+			pi->pspp_notify_required = true;
+	}
+}
+
+static void ci_notify_link_speed_change_after_state_change(struct radeon_device *rdev,
+							   struct radeon_ps *radeon_new_state,
+							   struct radeon_ps *radeon_current_state)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	enum radeon_pcie_gen target_link_speed =
+		ci_get_maximum_link_speed(rdev, radeon_new_state);
+	u8 request;
+
+	if (pi->pspp_notify_required) {
+		if (target_link_speed == RADEON_PCIE_GEN3)
+			request = PCIE_PERF_REQ_PECI_GEN3;
+		else if (target_link_speed == RADEON_PCIE_GEN2)
+			request = PCIE_PERF_REQ_PECI_GEN2;
+		else
+			request = PCIE_PERF_REQ_PECI_GEN1;
+
+		if ((request == PCIE_PERF_REQ_PECI_GEN1) &&
+		    (ci_get_current_pcie_speed(rdev) > 0))
+			return;
+
+#ifdef CONFIG_ACPI
+		radeon_acpi_pcie_performance_request(rdev, request, false);
+#endif
+	}
+}
+
+static int ci_set_private_data_variables_based_on_pptable(struct radeon_device *rdev)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	struct radeon_clock_voltage_dependency_table *allowed_sclk_vddc_table =
+		&rdev->pm.dpm.dyn_state.vddc_dependency_on_sclk;
+	struct radeon_clock_voltage_dependency_table *allowed_mclk_vddc_table =
+		&rdev->pm.dpm.dyn_state.vddc_dependency_on_mclk;
+	struct radeon_clock_voltage_dependency_table *allowed_mclk_vddci_table =
+		&rdev->pm.dpm.dyn_state.vddci_dependency_on_mclk;
+
+	if (allowed_sclk_vddc_table == NULL)
+		return -EINVAL;
+	if (allowed_sclk_vddc_table->count < 1)
+		return -EINVAL;
+	if (allowed_mclk_vddc_table == NULL)
+		return -EINVAL;
+	if (allowed_mclk_vddc_table->count < 1)
+		return -EINVAL;
+	if (allowed_mclk_vddci_table == NULL)
+		return -EINVAL;
+	if (allowed_mclk_vddci_table->count < 1)
+		return -EINVAL;
+
+	pi->min_vddc_in_pp_table = allowed_sclk_vddc_table->entries[0].v;
+	pi->max_vddc_in_pp_table =
+		allowed_sclk_vddc_table->entries[allowed_sclk_vddc_table->count - 1].v;
+
+	pi->min_vddci_in_pp_table = allowed_mclk_vddci_table->entries[0].v;
+	pi->max_vddci_in_pp_table =
+		allowed_mclk_vddci_table->entries[allowed_mclk_vddci_table->count - 1].v;
+
+	rdev->pm.dpm.dyn_state.max_clock_voltage_on_ac.sclk =
+		allowed_sclk_vddc_table->entries[allowed_sclk_vddc_table->count - 1].clk;
+	rdev->pm.dpm.dyn_state.max_clock_voltage_on_ac.mclk =
+		allowed_mclk_vddc_table->entries[allowed_sclk_vddc_table->count - 1].clk;
+	rdev->pm.dpm.dyn_state.max_clock_voltage_on_ac.vddc =
+		allowed_sclk_vddc_table->entries[allowed_sclk_vddc_table->count - 1].v;
+        rdev->pm.dpm.dyn_state.max_clock_voltage_on_ac.vddci =
+		allowed_mclk_vddci_table->entries[allowed_mclk_vddci_table->count - 1].v;
+
+	return 0;
+}
+
+static void ci_patch_with_vddc_leakage(struct radeon_device *rdev, u16 *vddc)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	struct ci_leakage_voltage *leakage_table = &pi->vddc_leakage;
+	u32 leakage_index;
+
+	for (leakage_index = 0; leakage_index < leakage_table->count; leakage_index++) {
+		if (leakage_table->leakage_id[leakage_index] == *vddc) {
+			*vddc = leakage_table->actual_voltage[leakage_index];
+			break;
+		}
+	}
+}
+
+static void ci_patch_with_vddci_leakage(struct radeon_device *rdev, u16 *vddci)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	struct ci_leakage_voltage *leakage_table = &pi->vddci_leakage;
+	u32 leakage_index;
+
+	for (leakage_index = 0; leakage_index < leakage_table->count; leakage_index++) {
+		if (leakage_table->leakage_id[leakage_index] == *vddci) {
+			*vddci = leakage_table->actual_voltage[leakage_index];
+			break;
+		}
+	}
+}
+
+static void ci_patch_clock_voltage_dependency_table_with_vddc_leakage(struct radeon_device *rdev,
+								      struct radeon_clock_voltage_dependency_table *table)
+{
+	u32 i;
+
+	if (table) {
+		for (i = 0; i < table->count; i++)
+			ci_patch_with_vddc_leakage(rdev, &table->entries[i].v);
+	}
+}
+
+static void ci_patch_clock_voltage_dependency_table_with_vddci_leakage(struct radeon_device *rdev,
+								       struct radeon_clock_voltage_dependency_table *table)
+{
+	u32 i;
+
+	if (table) {
+		for (i = 0; i < table->count; i++)
+			ci_patch_with_vddci_leakage(rdev, &table->entries[i].v);
+	}
+}
+
+static void ci_patch_vce_clock_voltage_dependency_table_with_vddc_leakage(struct radeon_device *rdev,
+									  struct radeon_vce_clock_voltage_dependency_table *table)
+{
+	u32 i;
+
+	if (table) {
+		for (i = 0; i < table->count; i++)
+			ci_patch_with_vddc_leakage(rdev, &table->entries[i].v);
+	}
+}
+
+static void ci_patch_uvd_clock_voltage_dependency_table_with_vddc_leakage(struct radeon_device *rdev,
+									  struct radeon_uvd_clock_voltage_dependency_table *table)
+{
+	u32 i;
+
+	if (table) {
+		for (i = 0; i < table->count; i++)
+			ci_patch_with_vddc_leakage(rdev, &table->entries[i].v);
+	}
+}
+
+static void ci_patch_vddc_phase_shed_limit_table_with_vddc_leakage(struct radeon_device *rdev,
+								   struct radeon_phase_shedding_limits_table *table)
+{
+	u32 i;
+
+	if (table) {
+		for (i = 0; i < table->count; i++)
+			ci_patch_with_vddc_leakage(rdev, &table->entries[i].voltage);
+	}
+}
+
+static void ci_patch_clock_voltage_limits_with_vddc_leakage(struct radeon_device *rdev,
+							    struct radeon_clock_and_voltage_limits *table)
+{
+	if (table) {
+		ci_patch_with_vddc_leakage(rdev, (u16 *)&table->vddc);
+		ci_patch_with_vddci_leakage(rdev, (u16 *)&table->vddci);
+	}
+}
+
+static void ci_patch_cac_leakage_table_with_vddc_leakage(struct radeon_device *rdev,
+							 struct radeon_cac_leakage_table *table)
+{
+	u32 i;
+
+	if (table) {
+		for (i = 0; i < table->count; i++)
+			ci_patch_with_vddc_leakage(rdev, &table->entries[i].vddc);
+	}
+}
+
+static void ci_patch_dependency_tables_with_leakage(struct radeon_device *rdev)
+{
+
+	ci_patch_clock_voltage_dependency_table_with_vddc_leakage(rdev,
+								  &rdev->pm.dpm.dyn_state.vddc_dependency_on_sclk);
+	ci_patch_clock_voltage_dependency_table_with_vddc_leakage(rdev,
+								  &rdev->pm.dpm.dyn_state.vddc_dependency_on_mclk);
+	ci_patch_clock_voltage_dependency_table_with_vddc_leakage(rdev,
+								  &rdev->pm.dpm.dyn_state.vddc_dependency_on_dispclk);
+	ci_patch_clock_voltage_dependency_table_with_vddci_leakage(rdev,
+								   &rdev->pm.dpm.dyn_state.vddci_dependency_on_mclk);
+	ci_patch_vce_clock_voltage_dependency_table_with_vddc_leakage(rdev,
+								      &rdev->pm.dpm.dyn_state.vce_clock_voltage_dependency_table);
+	ci_patch_uvd_clock_voltage_dependency_table_with_vddc_leakage(rdev,
+								      &rdev->pm.dpm.dyn_state.uvd_clock_voltage_dependency_table);
+	ci_patch_clock_voltage_dependency_table_with_vddc_leakage(rdev,
+								  &rdev->pm.dpm.dyn_state.samu_clock_voltage_dependency_table);
+	ci_patch_clock_voltage_dependency_table_with_vddc_leakage(rdev,
+								  &rdev->pm.dpm.dyn_state.acp_clock_voltage_dependency_table);
+	ci_patch_vddc_phase_shed_limit_table_with_vddc_leakage(rdev,
+							       &rdev->pm.dpm.dyn_state.phase_shedding_limits_table);
+	ci_patch_clock_voltage_limits_with_vddc_leakage(rdev,
+							&rdev->pm.dpm.dyn_state.max_clock_voltage_on_ac);
+	ci_patch_clock_voltage_limits_with_vddc_leakage(rdev,
+							&rdev->pm.dpm.dyn_state.max_clock_voltage_on_dc);
+	ci_patch_cac_leakage_table_with_vddc_leakage(rdev,
+						     &rdev->pm.dpm.dyn_state.cac_leakage_table);
+
+}
+
+static void ci_get_memory_type(struct radeon_device *rdev)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	u32 tmp;
+
+	tmp = RREG32(MC_SEQ_MISC0);
+
+	if (((tmp & MC_SEQ_MISC0_GDDR5_MASK) >> MC_SEQ_MISC0_GDDR5_SHIFT) ==
+	    MC_SEQ_MISC0_GDDR5_VALUE)
+		pi->mem_gddr5 = true;
+	else
+		pi->mem_gddr5 = false;
+
+}
+
+void ci_update_current_ps(struct radeon_device *rdev,
+			  struct radeon_ps *rps)
+{
+	struct ci_ps *new_ps = ci_get_ps(rps);
+	struct ci_power_info *pi = ci_get_pi(rdev);
+
+	pi->current_rps = *rps;
+	pi->current_ps = *new_ps;
+	pi->current_rps.ps_priv = &pi->current_ps;
+}
+
+void ci_update_requested_ps(struct radeon_device *rdev,
+			    struct radeon_ps *rps)
+{
+	struct ci_ps *new_ps = ci_get_ps(rps);
+	struct ci_power_info *pi = ci_get_pi(rdev);
+
+	pi->requested_rps = *rps;
+	pi->requested_ps = *new_ps;
+	pi->requested_rps.ps_priv = &pi->requested_ps;
+}
+
+int ci_dpm_pre_set_power_state(struct radeon_device *rdev)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	struct radeon_ps requested_ps = *rdev->pm.dpm.requested_ps;
+	struct radeon_ps *new_ps = &requested_ps;
+
+	ci_update_requested_ps(rdev, new_ps);
+
+	ci_apply_state_adjust_rules(rdev, &pi->requested_rps);
+
+	return 0;
+}
+
+void ci_dpm_post_set_power_state(struct radeon_device *rdev)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	struct radeon_ps *new_ps = &pi->requested_rps;
+
+	ci_update_current_ps(rdev, new_ps);
+}
+
+
+void ci_dpm_setup_asic(struct radeon_device *rdev)
+{
+	ci_read_clock_registers(rdev);
+	ci_get_memory_type(rdev);
+	ci_enable_acpi_power_management(rdev);
+	ci_init_sclk_t(rdev);
+}
+
+int ci_dpm_enable(struct radeon_device *rdev)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	struct radeon_ps *boot_ps = rdev->pm.dpm.boot_ps;
+	int ret;
+
+	cik_update_cg(rdev, (RADEON_CG_BLOCK_GFX |
+			     RADEON_CG_BLOCK_MC |
+			     RADEON_CG_BLOCK_SDMA |
+			     RADEON_CG_BLOCK_BIF |
+			     RADEON_CG_BLOCK_UVD |
+			     RADEON_CG_BLOCK_HDP), false);
+
+	if (ci_is_smc_running(rdev))
+		return -EINVAL;
+	if (pi->voltage_control != CISLANDS_VOLTAGE_CONTROL_NONE) {
+		ci_enable_voltage_control(rdev);
+		ret = ci_construct_voltage_tables(rdev);
+		if (ret) {
+			DRM_ERROR("ci_construct_voltage_tables failed\n");
+			return ret;
+		}
+	}
+	if (pi->caps_dynamic_ac_timing) {
+		ret = ci_initialize_mc_reg_table(rdev);
+		if (ret)
+			pi->caps_dynamic_ac_timing = false;
+	}
+	if (pi->dynamic_ss)
+		ci_enable_spread_spectrum(rdev, true);
+	if (pi->thermal_protection)
+		ci_enable_thermal_protection(rdev, true);
+	ci_program_sstp(rdev);
+	ci_enable_display_gap(rdev);
+	ci_program_vc(rdev);
+	ret = ci_upload_firmware(rdev);
+	if (ret) {
+		DRM_ERROR("ci_upload_firmware failed\n");
+		return ret;
+	}
+	ret = ci_process_firmware_header(rdev);
+	if (ret) {
+		DRM_ERROR("ci_process_firmware_header failed\n");
+		return ret;
+	}
+	ret = ci_initial_switch_from_arb_f0_to_f1(rdev);
+	if (ret) {
+		DRM_ERROR("ci_initial_switch_from_arb_f0_to_f1 failed\n");
+		return ret;
+	}
+	ret = ci_init_smc_table(rdev);
+	if (ret) {
+		DRM_ERROR("ci_init_smc_table failed\n");
+		return ret;
+	}
+	ret = ci_init_arb_table_index(rdev);
+	if (ret) {
+		DRM_ERROR("ci_init_arb_table_index failed\n");
+		return ret;
+	}
+	if (pi->caps_dynamic_ac_timing) {
+		ret = ci_populate_initial_mc_reg_table(rdev);
+		if (ret) {
+			DRM_ERROR("ci_populate_initial_mc_reg_table failed\n");
+			return ret;
+		}
+	}
+	ret = ci_populate_pm_base(rdev);
+	if (ret) {
+		DRM_ERROR("ci_populate_pm_base failed\n");
+		return ret;
+	}
+	ci_dpm_start_smc(rdev);
+	ci_enable_vr_hot_gpio_interrupt(rdev);
+	ret = ci_notify_smc_display_change(rdev, false);
+	if (ret) {
+		DRM_ERROR("ci_notify_smc_display_change failed\n");
+		return ret;
+	}
+	ci_enable_sclk_control(rdev, true);
+	ret = ci_enable_ulv(rdev, true);
+	if (ret) {
+		DRM_ERROR("ci_enable_ulv failed\n");
+		return ret;
+	}
+	ret = ci_enable_ds_master_switch(rdev, true);
+	if (ret) {
+		DRM_ERROR("ci_enable_ds_master_switch failed\n");
+		return ret;
+	}
+	ret = ci_start_dpm(rdev);
+	if (ret) {
+		DRM_ERROR("ci_start_dpm failed\n");
+		return ret;
+	}
+	ret = ci_enable_didt(rdev, true);
+	if (ret) {
+		DRM_ERROR("ci_enable_didt failed\n");
+		return ret;
+	}
+	ret = ci_enable_smc_cac(rdev, true);
+	if (ret) {
+		DRM_ERROR("ci_enable_smc_cac failed\n");
+		return ret;
+	}
+	ret = ci_enable_power_containment(rdev, true);
+	if (ret) {
+		DRM_ERROR("ci_enable_power_containment failed\n");
+		return ret;
+	}
+	if (rdev->irq.installed &&
+	    r600_is_internal_thermal_sensor(rdev->pm.int_thermal_type)) {
+#if 0
+		PPSMC_Result result;
+#endif
+		ret = ci_set_thermal_temperature_range(rdev, R600_TEMP_RANGE_MIN, R600_TEMP_RANGE_MAX);
+		if (ret) {
+			DRM_ERROR("ci_set_thermal_temperature_range failed\n");
+			return ret;
+		}
+		rdev->irq.dpm_thermal = true;
+		radeon_irq_set(rdev);
+#if 0
+		result = ci_send_msg_to_smc(rdev, PPSMC_MSG_EnableThermalInterrupt);
+
+		if (result != PPSMC_Result_OK)
+			DRM_DEBUG_KMS("Could not enable thermal interrupts.\n");
+#endif
+	}
+
+	ci_enable_auto_throttle_source(rdev, RADEON_DPM_AUTO_THROTTLE_SRC_THERMAL, true);
+
+	ci_dpm_powergate_uvd(rdev, true);
+
+	cik_update_cg(rdev, (RADEON_CG_BLOCK_GFX |
+			     RADEON_CG_BLOCK_MC |
+			     RADEON_CG_BLOCK_SDMA |
+			     RADEON_CG_BLOCK_BIF |
+			     RADEON_CG_BLOCK_UVD |
+			     RADEON_CG_BLOCK_HDP), true);
+
+	ci_update_current_ps(rdev, boot_ps);
+
+	return 0;
+}
+
+void ci_dpm_disable(struct radeon_device *rdev)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	struct radeon_ps *boot_ps = rdev->pm.dpm.boot_ps;
+
+	cik_update_cg(rdev, (RADEON_CG_BLOCK_GFX |
+			     RADEON_CG_BLOCK_MC |
+			     RADEON_CG_BLOCK_SDMA |
+			     RADEON_CG_BLOCK_UVD |
+			     RADEON_CG_BLOCK_HDP), false);
+
+	ci_dpm_powergate_uvd(rdev, false);
+
+	if (!ci_is_smc_running(rdev))
+		return;
+
+	if (pi->thermal_protection)
+		ci_enable_thermal_protection(rdev, false);
+	ci_enable_power_containment(rdev, false);
+	ci_enable_smc_cac(rdev, false);
+	ci_enable_didt(rdev, false);
+	ci_enable_spread_spectrum(rdev, false);
+	ci_enable_auto_throttle_source(rdev, RADEON_DPM_AUTO_THROTTLE_SRC_THERMAL, false);
+	ci_stop_dpm(rdev);
+	ci_enable_ds_master_switch(rdev, true);
+	ci_enable_ulv(rdev, false);
+	ci_clear_vc(rdev);
+	ci_reset_to_default(rdev);
+	ci_dpm_stop_smc(rdev);
+	ci_force_switch_to_arb_f0(rdev);
+
+	ci_update_current_ps(rdev, boot_ps);
+}
+
+int ci_dpm_set_power_state(struct radeon_device *rdev)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	struct radeon_ps *new_ps = &pi->requested_rps;
+	struct radeon_ps *old_ps = &pi->current_rps;
+	int ret;
+
+	cik_update_cg(rdev, (RADEON_CG_BLOCK_GFX |
+			     RADEON_CG_BLOCK_MC |
+			     RADEON_CG_BLOCK_SDMA |
+			     RADEON_CG_BLOCK_BIF |
+			     RADEON_CG_BLOCK_UVD |
+			     RADEON_CG_BLOCK_HDP), false);
+
+	ci_find_dpm_states_clocks_in_dpm_table(rdev, new_ps);
+	if (pi->pcie_performance_request)
+		ci_request_link_speed_change_before_state_change(rdev, new_ps, old_ps);
+	ret = ci_freeze_sclk_mclk_dpm(rdev);
+	if (ret) {
+		DRM_ERROR("ci_freeze_sclk_mclk_dpm failed\n");
+		return ret;
+	}
+	ret = ci_populate_and_upload_sclk_mclk_dpm_levels(rdev, new_ps);
+	if (ret) {
+		DRM_ERROR("ci_populate_and_upload_sclk_mclk_dpm_levels failed\n");
+		return ret;
+	}
+	ret = ci_generate_dpm_level_enable_mask(rdev, new_ps);
+	if (ret) {
+		DRM_ERROR("ci_generate_dpm_level_enable_mask failed\n");
+		return ret;
+	}
+#if 0
+	ret = ci_update_vce_dpm(rdev, new_ps, old_ps);
+	if (ret) {
+		DRM_ERROR("ci_update_vce_dpm failed\n");
+		return ret;
+	}
+#endif
+	ret = ci_update_sclk_t(rdev);
+	if (ret) {
+		DRM_ERROR("ci_update_sclk_t failed\n");
+		return ret;
+	}
+	if (pi->caps_dynamic_ac_timing) {
+		ret = ci_update_and_upload_mc_reg_table(rdev);
+		if (ret) {
+			DRM_ERROR("ci_update_and_upload_mc_reg_table failed\n");
+			return ret;
+		}
+	}
+	ret = ci_program_memory_timing_parameters(rdev);
+	if (ret) {
+		DRM_ERROR("ci_program_memory_timing_parameters failed\n");
+		return ret;
+	}
+	ret = ci_unfreeze_sclk_mclk_dpm(rdev);
+	if (ret) {
+		DRM_ERROR("ci_unfreeze_sclk_mclk_dpm failed\n");
+		return ret;
+	}
+	ret = ci_upload_dpm_level_enable_mask(rdev);
+	if (ret) {
+		DRM_ERROR("ci_upload_dpm_level_enable_mask failed\n");
+		return ret;
+	}
+	if (pi->pcie_performance_request)
+		ci_notify_link_speed_change_after_state_change(rdev, new_ps, old_ps);
+
+	cik_update_cg(rdev, (RADEON_CG_BLOCK_GFX |
+			     RADEON_CG_BLOCK_MC |
+			     RADEON_CG_BLOCK_SDMA |
+			     RADEON_CG_BLOCK_BIF |
+			     RADEON_CG_BLOCK_UVD |
+			     RADEON_CG_BLOCK_HDP), true);
+
+	return 0;
+}
+
+int ci_dpm_power_control_set_level(struct radeon_device *rdev)
+{
+	return ci_power_control_set_level(rdev);
+}
+
+void ci_dpm_reset_asic(struct radeon_device *rdev)
+{
+	ci_set_boot_state(rdev);
+}
+
+void ci_dpm_display_configuration_changed(struct radeon_device *rdev)
+{
+	ci_program_display_gap(rdev);
+}
+
+union power_info {
+	struct _ATOM_POWERPLAY_INFO info;
+	struct _ATOM_POWERPLAY_INFO_V2 info_2;
+	struct _ATOM_POWERPLAY_INFO_V3 info_3;
+	struct _ATOM_PPLIB_POWERPLAYTABLE pplib;
+	struct _ATOM_PPLIB_POWERPLAYTABLE2 pplib2;
+	struct _ATOM_PPLIB_POWERPLAYTABLE3 pplib3;
+};
+
+union pplib_clock_info {
+	struct _ATOM_PPLIB_R600_CLOCK_INFO r600;
+	struct _ATOM_PPLIB_RS780_CLOCK_INFO rs780;
+	struct _ATOM_PPLIB_EVERGREEN_CLOCK_INFO evergreen;
+	struct _ATOM_PPLIB_SUMO_CLOCK_INFO sumo;
+	struct _ATOM_PPLIB_SI_CLOCK_INFO si;
+	struct _ATOM_PPLIB_CI_CLOCK_INFO ci;
+};
+
+union pplib_power_state {
+	struct _ATOM_PPLIB_STATE v1;
+	struct _ATOM_PPLIB_STATE_V2 v2;
+};
+
+static void ci_parse_pplib_non_clock_info(struct radeon_device *rdev,
+					  struct radeon_ps *rps,
+					  struct _ATOM_PPLIB_NONCLOCK_INFO *non_clock_info,
+					  u8 table_rev)
+{
+	rps->caps = le32_to_cpu(non_clock_info->ulCapsAndSettings);
+	rps->class = le16_to_cpu(non_clock_info->usClassification);
+	rps->class2 = le16_to_cpu(non_clock_info->usClassification2);
+
+	if (ATOM_PPLIB_NONCLOCKINFO_VER1 < table_rev) {
+		rps->vclk = le32_to_cpu(non_clock_info->ulVCLK);
+		rps->dclk = le32_to_cpu(non_clock_info->ulDCLK);
+	} else {
+		rps->vclk = 0;
+		rps->dclk = 0;
+	}
+
+	if (rps->class & ATOM_PPLIB_CLASSIFICATION_BOOT)
+		rdev->pm.dpm.boot_ps = rps;
+	if (rps->class & ATOM_PPLIB_CLASSIFICATION_UVDSTATE)
+		rdev->pm.dpm.uvd_ps = rps;
+}
+
+static void ci_parse_pplib_clock_info(struct radeon_device *rdev,
+				      struct radeon_ps *rps, int index,
+				      union pplib_clock_info *clock_info)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	struct ci_ps *ps = ci_get_ps(rps);
+	struct ci_pl *pl = &ps->performance_levels[index];
+
+	ps->performance_level_count = index + 1;
+
+	pl->sclk = le16_to_cpu(clock_info->ci.usEngineClockLow);
+	pl->sclk |= clock_info->ci.ucEngineClockHigh << 16;
+	pl->mclk = le16_to_cpu(clock_info->ci.usMemoryClockLow);
+	pl->mclk |= clock_info->ci.ucMemoryClockHigh << 16;
+
+	pl->pcie_gen = r600_get_pcie_gen_support(rdev,
+						 pi->sys_pcie_mask,
+						 pi->vbios_boot_state.pcie_gen_bootup_value,
+						 clock_info->ci.ucPCIEGen);
+	pl->pcie_lane = r600_get_pcie_lane_support(rdev,
+						   pi->vbios_boot_state.pcie_lane_bootup_value,
+						   le16_to_cpu(clock_info->ci.usPCIELane));
+
+	if (rps->class & ATOM_PPLIB_CLASSIFICATION_ACPI) {
+		pi->acpi_pcie_gen = pl->pcie_gen;
+	}
+
+	if (rps->class2 & ATOM_PPLIB_CLASSIFICATION2_ULV) {
+		pi->ulv.supported = true;
+		pi->ulv.pl = *pl;
+		pi->ulv.cg_ulv_parameter = CISLANDS_CGULVPARAMETER_DFLT;
+	}
+
+	/* patch up boot state */
+	if (rps->class & ATOM_PPLIB_CLASSIFICATION_BOOT) {
+		pl->mclk = pi->vbios_boot_state.mclk_bootup_value;
+		pl->sclk = pi->vbios_boot_state.sclk_bootup_value;
+		pl->pcie_gen = pi->vbios_boot_state.pcie_gen_bootup_value;
+		pl->pcie_lane = pi->vbios_boot_state.pcie_lane_bootup_value;
+	}
+
+	switch (rps->class & ATOM_PPLIB_CLASSIFICATION_UI_MASK) {
+	case ATOM_PPLIB_CLASSIFICATION_UI_BATTERY:
+		pi->use_pcie_powersaving_levels = true;
+		if (pi->pcie_gen_powersaving.max < pl->pcie_gen)
+			pi->pcie_gen_powersaving.max = pl->pcie_gen;
+		if (pi->pcie_gen_powersaving.min > pl->pcie_gen)
+			pi->pcie_gen_powersaving.min = pl->pcie_gen;
+		if (pi->pcie_lane_powersaving.max < pl->pcie_lane)
+			pi->pcie_lane_powersaving.max = pl->pcie_lane;
+		if (pi->pcie_lane_powersaving.min > pl->pcie_lane)
+			pi->pcie_lane_powersaving.min = pl->pcie_lane;
+		break;
+	case ATOM_PPLIB_CLASSIFICATION_UI_PERFORMANCE:
+		pi->use_pcie_performance_levels = true;
+		if (pi->pcie_gen_performance.max < pl->pcie_gen)
+			pi->pcie_gen_performance.max = pl->pcie_gen;
+		if (pi->pcie_gen_performance.min > pl->pcie_gen)
+			pi->pcie_gen_performance.min = pl->pcie_gen;
+		if (pi->pcie_lane_performance.max < pl->pcie_lane)
+			pi->pcie_lane_performance.max = pl->pcie_lane;
+		if (pi->pcie_lane_performance.min > pl->pcie_lane)
+			pi->pcie_lane_performance.min = pl->pcie_lane;
+		break;
+	default:
+		break;
+	}
+}
+
+static int ci_parse_power_table(struct radeon_device *rdev)
+{
+	struct radeon_mode_info *mode_info = &rdev->mode_info;
+	struct _ATOM_PPLIB_NONCLOCK_INFO *non_clock_info;
+	union pplib_power_state *power_state;
+	int i, j, k, non_clock_array_index, clock_array_index;
+	union pplib_clock_info *clock_info;
+	struct _StateArray *state_array;
+	struct _ClockInfoArray *clock_info_array;
+	struct _NonClockInfoArray *non_clock_info_array;
+	union power_info *power_info;
+	int index = GetIndexIntoMasterTable(DATA, PowerPlayInfo);
+        u16 data_offset;
+	u8 frev, crev;
+	u8 *power_state_offset;
+	struct ci_ps *ps;
+
+	if (!atom_parse_data_header(mode_info->atom_context, index, NULL,
+				   &frev, &crev, &data_offset))
+		return -EINVAL;
+	power_info = (union power_info *)(mode_info->atom_context->bios + data_offset);
+
+	state_array = (struct _StateArray *)
+		(mode_info->atom_context->bios + data_offset +
+		 le16_to_cpu(power_info->pplib.usStateArrayOffset));
+	clock_info_array = (struct _ClockInfoArray *)
+		(mode_info->atom_context->bios + data_offset +
+		 le16_to_cpu(power_info->pplib.usClockInfoArrayOffset));
+	non_clock_info_array = (struct _NonClockInfoArray *)
+		(mode_info->atom_context->bios + data_offset +
+		 le16_to_cpu(power_info->pplib.usNonClockInfoArrayOffset));
+
+	rdev->pm.dpm.ps = kzalloc(sizeof(struct radeon_ps) *
+				  state_array->ucNumEntries, GFP_KERNEL);
+	if (!rdev->pm.dpm.ps)
+		return -ENOMEM;
+	power_state_offset = (u8 *)state_array->states;
+	rdev->pm.dpm.platform_caps = le32_to_cpu(power_info->pplib.ulPlatformCaps);
+	rdev->pm.dpm.backbias_response_time = le16_to_cpu(power_info->pplib.usBackbiasTime);
+	rdev->pm.dpm.voltage_response_time = le16_to_cpu(power_info->pplib.usVoltageTime);
+	for (i = 0; i < state_array->ucNumEntries; i++) {
+		u8 *idx;
+		power_state = (union pplib_power_state *)power_state_offset;
+		non_clock_array_index = power_state->v2.nonClockInfoIndex;
+		non_clock_info = (struct _ATOM_PPLIB_NONCLOCK_INFO *)
+			&non_clock_info_array->nonClockInfo[non_clock_array_index];
+		if (!rdev->pm.power_state[i].clock_info)
+			return -EINVAL;
+		ps = kzalloc(sizeof(struct ci_ps), GFP_KERNEL);
+		if (ps == NULL) {
+			kfree(rdev->pm.dpm.ps);
+			return -ENOMEM;
+		}
+		rdev->pm.dpm.ps[i].ps_priv = ps;
+		ci_parse_pplib_non_clock_info(rdev, &rdev->pm.dpm.ps[i],
+					      non_clock_info,
+					      non_clock_info_array->ucEntrySize);
+		k = 0;
+		idx = (u8 *)&power_state->v2.clockInfoIndex[0];
+		for (j = 0; j < power_state->v2.ucNumDPMLevels; j++) {
+			clock_array_index = idx[j];
+			if (clock_array_index >= clock_info_array->ucNumEntries)
+				continue;
+			if (k >= CISLANDS_MAX_HARDWARE_POWERLEVELS)
+				break;
+			clock_info = (union pplib_clock_info *)
+				((u8 *)&clock_info_array->clockInfo[0] +
+				 (clock_array_index * clock_info_array->ucEntrySize));
+			ci_parse_pplib_clock_info(rdev,
+						  &rdev->pm.dpm.ps[i], k,
+						  clock_info);
+			k++;
+		}
+		power_state_offset += 2 + power_state->v2.ucNumDPMLevels;
+	}
+	rdev->pm.dpm.num_ps = state_array->ucNumEntries;
+	return 0;
+}
+
+int ci_get_vbios_boot_values(struct radeon_device *rdev,
+			     struct ci_vbios_boot_state *boot_state)
+{
+	struct radeon_mode_info *mode_info = &rdev->mode_info;
+	int index = GetIndexIntoMasterTable(DATA, FirmwareInfo);
+	ATOM_FIRMWARE_INFO_V2_2 *firmware_info;
+	u8 frev, crev;
+	u16 data_offset;
+
+	if (atom_parse_data_header(mode_info->atom_context, index, NULL,
+				   &frev, &crev, &data_offset)) {
+		firmware_info =
+			(ATOM_FIRMWARE_INFO_V2_2 *)(mode_info->atom_context->bios +
+						    data_offset);
+		boot_state->mvdd_bootup_value = le16_to_cpu(firmware_info->usBootUpMVDDCVoltage);
+		boot_state->vddc_bootup_value = le16_to_cpu(firmware_info->usBootUpVDDCVoltage);
+		boot_state->vddci_bootup_value = le16_to_cpu(firmware_info->usBootUpVDDCIVoltage);
+		boot_state->pcie_gen_bootup_value = ci_get_current_pcie_speed(rdev);
+		boot_state->pcie_lane_bootup_value = ci_get_current_pcie_lane_number(rdev);
+		boot_state->sclk_bootup_value = le32_to_cpu(firmware_info->ulDefaultEngineClock);
+		boot_state->mclk_bootup_value = le32_to_cpu(firmware_info->ulDefaultMemoryClock);
+
+		return 0;
+	}
+	return -EINVAL;
+}
+
+void ci_dpm_fini(struct radeon_device *rdev)
+{
+	int i;
+
+	for (i = 0; i < rdev->pm.dpm.num_ps; i++) {
+		kfree(rdev->pm.dpm.ps[i].ps_priv);
+	}
+	kfree(rdev->pm.dpm.ps);
+	kfree(rdev->pm.dpm.priv);
+	kfree(rdev->pm.dpm.dyn_state.vddc_dependency_on_dispclk.entries);
+	r600_free_extended_power_table(rdev);
+}
+
+int ci_dpm_init(struct radeon_device *rdev)
+{
+	int index = GetIndexIntoMasterTable(DATA, ASIC_InternalSS_Info);
+	u16 data_offset, size;
+	u8 frev, crev;
+	struct ci_power_info *pi;
+	int ret;
+	u32 mask;
+
+	pi = kzalloc(sizeof(struct ci_power_info), GFP_KERNEL);
+	if (pi == NULL)
+		return -ENOMEM;
+	rdev->pm.dpm.priv = pi;
+
+	ret = drm_pcie_get_speed_cap_mask(rdev->ddev, &mask);
+	if (ret)
+		pi->sys_pcie_mask = 0;
+	else
+		pi->sys_pcie_mask = mask;
+	pi->force_pcie_gen = RADEON_PCIE_GEN_INVALID;
+
+	pi->pcie_gen_performance.max = RADEON_PCIE_GEN1;
+	pi->pcie_gen_performance.min = RADEON_PCIE_GEN3;
+	pi->pcie_gen_powersaving.max = RADEON_PCIE_GEN1;
+	pi->pcie_gen_powersaving.min = RADEON_PCIE_GEN3;
+
+	pi->pcie_lane_performance.max = 0;
+	pi->pcie_lane_performance.min = 16;
+	pi->pcie_lane_powersaving.max = 0;
+	pi->pcie_lane_powersaving.min = 16;
+
+	ret = ci_get_vbios_boot_values(rdev, &pi->vbios_boot_state);
+	if (ret) {
+		ci_dpm_fini(rdev);
+		return ret;
+	}
+	ret = ci_parse_power_table(rdev);
+	if (ret) {
+		ci_dpm_fini(rdev);
+		return ret;
+	}
+	ret = r600_parse_extended_power_table(rdev);
+	if (ret) {
+		ci_dpm_fini(rdev);
+		return ret;
+	}
+
+        pi->dll_default_on = false;
+        pi->sram_end = SMC_RAM_END;
+
+	pi->activity_target[0] = CISLAND_TARGETACTIVITY_DFLT;
+	pi->activity_target[1] = CISLAND_TARGETACTIVITY_DFLT;
+	pi->activity_target[2] = CISLAND_TARGETACTIVITY_DFLT;
+	pi->activity_target[3] = CISLAND_TARGETACTIVITY_DFLT;
+	pi->activity_target[4] = CISLAND_TARGETACTIVITY_DFLT;
+	pi->activity_target[5] = CISLAND_TARGETACTIVITY_DFLT;
+	pi->activity_target[6] = CISLAND_TARGETACTIVITY_DFLT;
+	pi->activity_target[7] = CISLAND_TARGETACTIVITY_DFLT;
+
+	pi->mclk_activity_target = CISLAND_MCLK_TARGETACTIVITY_DFLT;
+
+	pi->sclk_dpm_key_disabled = 0;
+	pi->mclk_dpm_key_disabled = 0;
+	pi->pcie_dpm_key_disabled = 0;
+
+	pi->caps_sclk_ds = true;
+
+	pi->mclk_strobe_mode_threshold = 40000;
+	pi->mclk_stutter_mode_threshold = 40000;
+	pi->mclk_edc_enable_threshold = 40000;
+	pi->mclk_edc_wr_enable_threshold = 40000;
+
+	ci_initialize_powertune_defaults(rdev);
+
+	pi->caps_fps = false;
+
+	pi->caps_sclk_throttle_low_notification = false;
+
+	pi->caps_uvd_dpm = true;
+
+        ci_get_leakage_voltages(rdev);
+        ci_patch_dependency_tables_with_leakage(rdev);
+        ci_set_private_data_variables_based_on_pptable(rdev);
+
+	rdev->pm.dpm.dyn_state.vddc_dependency_on_dispclk.entries =
+		kzalloc(4 * sizeof(struct radeon_clock_voltage_dependency_entry), GFP_KERNEL);
+	if (!rdev->pm.dpm.dyn_state.vddc_dependency_on_dispclk.entries) {
+		ci_dpm_fini(rdev);
+		return -ENOMEM;
+	}
+	rdev->pm.dpm.dyn_state.vddc_dependency_on_dispclk.count = 4;
+	rdev->pm.dpm.dyn_state.vddc_dependency_on_dispclk.entries[0].clk = 0;
+	rdev->pm.dpm.dyn_state.vddc_dependency_on_dispclk.entries[0].v = 0;
+	rdev->pm.dpm.dyn_state.vddc_dependency_on_dispclk.entries[1].clk = 36000;
+	rdev->pm.dpm.dyn_state.vddc_dependency_on_dispclk.entries[1].v = 720;
+	rdev->pm.dpm.dyn_state.vddc_dependency_on_dispclk.entries[2].clk = 54000;
+	rdev->pm.dpm.dyn_state.vddc_dependency_on_dispclk.entries[2].v = 810;
+	rdev->pm.dpm.dyn_state.vddc_dependency_on_dispclk.entries[3].clk = 72000;
+	rdev->pm.dpm.dyn_state.vddc_dependency_on_dispclk.entries[3].v = 900;
+
+	rdev->pm.dpm.dyn_state.mclk_sclk_ratio = 4;
+	rdev->pm.dpm.dyn_state.sclk_mclk_delta = 15000;
+	rdev->pm.dpm.dyn_state.vddc_vddci_delta = 200;
+
+	rdev->pm.dpm.dyn_state.valid_sclk_values.count = 0;
+	rdev->pm.dpm.dyn_state.valid_sclk_values.values = NULL;
+	rdev->pm.dpm.dyn_state.valid_mclk_values.count = 0;
+	rdev->pm.dpm.dyn_state.valid_mclk_values.values = NULL;
+
+	pi->thermal_temp_setting.temperature_low = 99500;
+	pi->thermal_temp_setting.temperature_high = 100000;
+	pi->thermal_temp_setting.temperature_shutdown = 104000;
+
+	pi->uvd_enabled = false;
+
+	pi->voltage_control = CISLANDS_VOLTAGE_CONTROL_NONE;
+	pi->vddci_control = CISLANDS_VOLTAGE_CONTROL_NONE;
+	pi->mvdd_control = CISLANDS_VOLTAGE_CONTROL_NONE;
+	if (radeon_atom_is_voltage_gpio(rdev, VOLTAGE_TYPE_VDDC, VOLTAGE_OBJ_GPIO_LUT))
+		pi->voltage_control = CISLANDS_VOLTAGE_CONTROL_BY_GPIO;
+	else if (radeon_atom_is_voltage_gpio(rdev, VOLTAGE_TYPE_VDDC, VOLTAGE_OBJ_SVID2))
+		pi->voltage_control = CISLANDS_VOLTAGE_CONTROL_BY_SVID2;
+
+	if (rdev->pm.dpm.platform_caps & ATOM_PP_PLATFORM_CAP_VDDCI_CONTROL) {
+		if (radeon_atom_is_voltage_gpio(rdev, VOLTAGE_TYPE_VDDCI, VOLTAGE_OBJ_GPIO_LUT))
+			pi->vddci_control = CISLANDS_VOLTAGE_CONTROL_BY_GPIO;
+		else if (radeon_atom_is_voltage_gpio(rdev, VOLTAGE_TYPE_VDDCI, VOLTAGE_OBJ_SVID2))
+			pi->vddci_control = CISLANDS_VOLTAGE_CONTROL_BY_SVID2;
+		else
+			rdev->pm.dpm.platform_caps &= ~ATOM_PP_PLATFORM_CAP_VDDCI_CONTROL;
+        }
+
+	if (rdev->pm.dpm.platform_caps & ATOM_PP_PLATFORM_CAP_MVDDCONTROL) {
+		if (radeon_atom_is_voltage_gpio(rdev, VOLTAGE_TYPE_MVDDC, VOLTAGE_OBJ_GPIO_LUT))
+			pi->mvdd_control = CISLANDS_VOLTAGE_CONTROL_BY_GPIO;
+		else if (radeon_atom_is_voltage_gpio(rdev, VOLTAGE_TYPE_MVDDC, VOLTAGE_OBJ_SVID2))
+			pi->mvdd_control = CISLANDS_VOLTAGE_CONTROL_BY_SVID2;
+		else
+			rdev->pm.dpm.platform_caps &= ~ATOM_PP_PLATFORM_CAP_MVDDCONTROL;
+	}
+
+	pi->vddc_phase_shed_control = true;
+
+#if defined(CONFIG_ACPI)
+	pi->pcie_performance_request =
+		radeon_acpi_is_pcie_performance_request_supported(rdev);
+#else
+	pi->pcie_performance_request = false;
+#endif
+
+	if (atom_parse_data_header(rdev->mode_info.atom_context, index, &size,
+                                   &frev, &crev, &data_offset)) {
+		pi->caps_sclk_ss_support = true;
+		pi->caps_mclk_ss_support = true;
+		pi->dynamic_ss = true;
+	} else {
+		pi->caps_sclk_ss_support = false;
+		pi->caps_mclk_ss_support = false;
+		pi->dynamic_ss = true;
+	}
+
+	if (rdev->pm.int_thermal_type != THERMAL_TYPE_NONE)
+		pi->thermal_protection = true;
+	else
+		pi->thermal_protection = false;
+
+	pi->caps_dynamic_ac_timing = true;
+
+	pi->uvd_power_gated = false;
+
+	/* make sure dc limits are valid */
+	if ((rdev->pm.dpm.dyn_state.max_clock_voltage_on_dc.sclk == 0) ||
+	    (rdev->pm.dpm.dyn_state.max_clock_voltage_on_dc.mclk == 0))
+		rdev->pm.dpm.dyn_state.max_clock_voltage_on_dc =
+			rdev->pm.dpm.dyn_state.max_clock_voltage_on_ac;
+
+	return 0;
+}
+
+void ci_dpm_debugfs_print_current_performance_level(struct radeon_device *rdev,
+						    struct seq_file *m)
+{
+	u32 sclk = ci_get_average_sclk_freq(rdev);
+	u32 mclk = ci_get_average_mclk_freq(rdev);
+
+	seq_printf(m, "power level avg    sclk: %u mclk: %u\n",
+		   sclk, mclk);
+}
+
+void ci_dpm_print_power_state(struct radeon_device *rdev,
+			      struct radeon_ps *rps)
+{
+	struct ci_ps *ps = ci_get_ps(rps);
+	struct ci_pl *pl;
+	int i;
+
+	r600_dpm_print_class_info(rps->class, rps->class2);
+	r600_dpm_print_cap_info(rps->caps);
+	printk("\tuvd    vclk: %d dclk: %d\n", rps->vclk, rps->dclk);
+	for (i = 0; i < ps->performance_level_count; i++) {
+		pl = &ps->performance_levels[i];
+		printk("\t\tpower level %d    sclk: %u mclk: %u pcie gen: %u pcie lanes: %u\n",
+		       i, pl->sclk, pl->mclk, pl->pcie_gen + 1, pl->pcie_lane);
+	}
+	r600_dpm_print_ps_status(rdev, rps);
+}
+
+u32 ci_dpm_get_sclk(struct radeon_device *rdev, bool low)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	struct ci_ps *requested_state = ci_get_ps(&pi->requested_rps);
+
+	if (low)
+		return requested_state->performance_levels[0].sclk;
+	else
+		return requested_state->performance_levels[requested_state->performance_level_count - 1].sclk;
+}
+
+u32 ci_dpm_get_mclk(struct radeon_device *rdev, bool low)
+{
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	struct ci_ps *requested_state = ci_get_ps(&pi->requested_rps);
+
+	if (low)
+		return requested_state->performance_levels[0].mclk;
+	else
+		return requested_state->performance_levels[requested_state->performance_level_count - 1].mclk;
+}
diff --git a/drivers/gpu/drm/radeon/ci_dpm.h b/drivers/gpu/drm/radeon/ci_dpm.h
new file mode 100644
index 000000000000..93bbed977ffb
--- /dev/null
+++ b/drivers/gpu/drm/radeon/ci_dpm.h
@@ -0,0 +1,332 @@
+/*
+ * Copyright 2013 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+#ifndef __CI_DPM_H__
+#define __CI_DPM_H__
+
+#include "ppsmc.h"
+
+#define SMU__NUM_SCLK_DPM_STATE  8
+#define SMU__NUM_MCLK_DPM_LEVELS 6
+#define SMU__NUM_LCLK_DPM_LEVELS 8
+#define SMU__NUM_PCIE_DPM_LEVELS 8
+#include "smu7_discrete.h"
+
+#define CISLANDS_MAX_HARDWARE_POWERLEVELS 2
+
+struct ci_pl {
+	u32 mclk;
+	u32 sclk;
+	enum radeon_pcie_gen pcie_gen;
+	u16 pcie_lane;
+};
+
+struct ci_ps {
+	u16 performance_level_count;
+	bool dc_compatible;
+	u32 sclk_t;
+	struct ci_pl performance_levels[CISLANDS_MAX_HARDWARE_POWERLEVELS];
+};
+
+struct ci_dpm_level {
+	bool enabled;
+	u32 value;
+	u32 param1;
+};
+
+#define CISLAND_MAX_DEEPSLEEP_DIVIDER_ID 5
+#define MAX_REGULAR_DPM_NUMBER 8
+#define CISLAND_MINIMUM_ENGINE_CLOCK 800
+
+struct ci_single_dpm_table {
+	u32 count;
+	struct ci_dpm_level dpm_levels[MAX_REGULAR_DPM_NUMBER];
+};
+
+struct ci_dpm_table {
+	struct ci_single_dpm_table sclk_table;
+	struct ci_single_dpm_table mclk_table;
+	struct ci_single_dpm_table pcie_speed_table;
+	struct ci_single_dpm_table vddc_table;
+	struct ci_single_dpm_table vddci_table;
+	struct ci_single_dpm_table mvdd_table;
+};
+
+struct ci_mc_reg_entry {
+	u32 mclk_max;
+	u32 mc_data[SMU7_DISCRETE_MC_REGISTER_ARRAY_SIZE];
+};
+
+struct ci_mc_reg_table {
+	u8 last;
+	u8 num_entries;
+	u16 valid_flag;
+	struct ci_mc_reg_entry mc_reg_table_entry[MAX_AC_TIMING_ENTRIES];
+	SMU7_Discrete_MCRegisterAddress mc_reg_address[SMU7_DISCRETE_MC_REGISTER_ARRAY_SIZE];
+};
+
+struct ci_ulv_parm
+{
+	bool supported;
+	u32 cg_ulv_parameter;
+	u32 volt_change_delay;
+	struct ci_pl pl;
+};
+
+#define CISLANDS_MAX_LEAKAGE_COUNT  8
+
+struct ci_leakage_voltage {
+	u16 count;
+	u16 leakage_id[CISLANDS_MAX_LEAKAGE_COUNT];
+	u16 actual_voltage[CISLANDS_MAX_LEAKAGE_COUNT];
+};
+
+struct ci_dpm_level_enable_mask {
+	u32 uvd_dpm_enable_mask;
+	u32 vce_dpm_enable_mask;
+	u32 acp_dpm_enable_mask;
+	u32 samu_dpm_enable_mask;
+	u32 sclk_dpm_enable_mask;
+	u32 mclk_dpm_enable_mask;
+	u32 pcie_dpm_enable_mask;
+};
+
+struct ci_vbios_boot_state
+{
+	u16 mvdd_bootup_value;
+	u16 vddc_bootup_value;
+	u16 vddci_bootup_value;
+	u32 sclk_bootup_value;
+	u32 mclk_bootup_value;
+	u16 pcie_gen_bootup_value;
+	u16 pcie_lane_bootup_value;
+};
+
+struct ci_clock_registers {
+	u32 cg_spll_func_cntl;
+	u32 cg_spll_func_cntl_2;
+	u32 cg_spll_func_cntl_3;
+	u32 cg_spll_func_cntl_4;
+	u32 cg_spll_spread_spectrum;
+	u32 cg_spll_spread_spectrum_2;
+	u32 dll_cntl;
+	u32 mclk_pwrmgt_cntl;
+	u32 mpll_ad_func_cntl;
+	u32 mpll_dq_func_cntl;
+	u32 mpll_func_cntl;
+	u32 mpll_func_cntl_1;
+	u32 mpll_func_cntl_2;
+	u32 mpll_ss1;
+	u32 mpll_ss2;
+};
+
+struct ci_thermal_temperature_setting {
+	s32 temperature_low;
+	s32 temperature_high;
+	s32 temperature_shutdown;
+};
+
+struct ci_pcie_perf_range {
+	u16 max;
+	u16 min;
+};
+
+enum ci_pt_config_reg_type {
+	CISLANDS_CONFIGREG_MMR = 0,
+	CISLANDS_CONFIGREG_SMC_IND,
+	CISLANDS_CONFIGREG_DIDT_IND,
+	CISLANDS_CONFIGREG_CACHE,
+	CISLANDS_CONFIGREG_MAX
+};
+
+#define POWERCONTAINMENT_FEATURE_BAPM            0x00000001
+#define POWERCONTAINMENT_FEATURE_TDCLimit        0x00000002
+#define POWERCONTAINMENT_FEATURE_PkgPwrLimit     0x00000004
+
+struct ci_pt_config_reg {
+	u32 offset;
+	u32 mask;
+	u32 shift;
+	u32 value;
+	enum ci_pt_config_reg_type type;
+};
+
+struct ci_pt_defaults {
+	u8 svi_load_line_en;
+	u8 svi_load_line_vddc;
+	u8 tdc_vddc_throttle_release_limit_perc;
+	u8 tdc_mawt;
+	u8 tdc_waterfall_ctl;
+	u8 dte_ambient_temp_base;
+	u32 display_cac;
+	u32 bapm_temp_gradient;
+	u16 bapmti_r[SMU7_DTE_ITERATIONS * SMU7_DTE_SOURCES * SMU7_DTE_SINKS];
+	u16 bapmti_rc[SMU7_DTE_ITERATIONS * SMU7_DTE_SOURCES * SMU7_DTE_SINKS];
+};
+
+#define DPMTABLE_OD_UPDATE_SCLK     0x00000001
+#define DPMTABLE_OD_UPDATE_MCLK     0x00000002
+#define DPMTABLE_UPDATE_SCLK        0x00000004
+#define DPMTABLE_UPDATE_MCLK        0x00000008
+
+struct ci_power_info {
+	struct ci_dpm_table dpm_table;
+	u32 voltage_control;
+	u32 mvdd_control;
+	u32 vddci_control;
+	u32 active_auto_throttle_sources;
+	struct ci_clock_registers clock_registers;
+	u16 acpi_vddc;
+	u16 acpi_vddci;
+	enum radeon_pcie_gen force_pcie_gen;
+	enum radeon_pcie_gen acpi_pcie_gen;
+	struct ci_leakage_voltage vddc_leakage;
+	struct ci_leakage_voltage vddci_leakage;
+	u16 max_vddc_in_pp_table;
+	u16 min_vddc_in_pp_table;
+	u16 max_vddci_in_pp_table;
+	u16 min_vddci_in_pp_table;
+	u32 mclk_strobe_mode_threshold;
+	u32 mclk_stutter_mode_threshold;
+	u32 mclk_edc_enable_threshold;
+	u32 mclk_edc_wr_enable_threshold;
+	struct ci_vbios_boot_state vbios_boot_state;
+	/* smc offsets */
+	u32 sram_end;
+	u32 dpm_table_start;
+	u32 soft_regs_start;
+	u32 mc_reg_table_start;
+	u32 fan_table_start;
+	u32 arb_table_start;
+	/* smc tables */
+	SMU7_Discrete_DpmTable smc_state_table;
+	SMU7_Discrete_MCRegisters smc_mc_reg_table;
+	SMU7_Discrete_PmFuses smc_powertune_table;
+	/* other stuff */
+	struct ci_mc_reg_table mc_reg_table;
+	struct atom_voltage_table vddc_voltage_table;
+	struct atom_voltage_table vddci_voltage_table;
+	struct atom_voltage_table mvdd_voltage_table;
+	struct ci_ulv_parm ulv;
+	u32 power_containment_features;
+	const struct ci_pt_defaults *powertune_defaults;
+	u32 dte_tj_offset;
+	bool vddc_phase_shed_control;
+	struct ci_thermal_temperature_setting thermal_temp_setting;
+	struct ci_dpm_level_enable_mask dpm_level_enable_mask;
+	u32 need_update_smu7_dpm_table;
+	u32 sclk_dpm_key_disabled;
+	u32 mclk_dpm_key_disabled;
+	u32 pcie_dpm_key_disabled;
+	struct ci_pcie_perf_range pcie_gen_performance;
+	struct ci_pcie_perf_range pcie_lane_performance;
+	struct ci_pcie_perf_range pcie_gen_powersaving;
+	struct ci_pcie_perf_range pcie_lane_powersaving;
+	u32 activity_target[SMU7_MAX_LEVELS_GRAPHICS];
+	u32 mclk_activity_target;
+	u32 low_sclk_interrupt_t;
+	u32 last_mclk_dpm_enable_mask;
+	u32 sys_pcie_mask;
+	/* caps */
+	bool caps_power_containment;
+	bool caps_cac;
+	bool caps_sq_ramping;
+	bool caps_db_ramping;
+	bool caps_td_ramping;
+	bool caps_tcp_ramping;
+	bool caps_fps;
+	bool caps_sclk_ds;
+	bool caps_sclk_ss_support;
+	bool caps_mclk_ss_support;
+	bool caps_uvd_dpm;
+	bool caps_vce_dpm;
+	bool caps_samu_dpm;
+	bool caps_acp_dpm;
+	bool caps_automatic_dc_transition;
+	bool caps_sclk_throttle_low_notification;
+	bool caps_dynamic_ac_timing;
+	/* flags */
+	bool thermal_protection;
+	bool pcie_performance_request;
+	bool dynamic_ss;
+	bool dll_default_on;
+	bool cac_enabled;
+	bool uvd_enabled;
+	bool battery_state;
+	bool pspp_notify_required;
+	bool mem_gddr5;
+	bool enable_bapm_feature;
+	bool enable_tdc_limit_feature;
+	bool enable_pkg_pwr_tracking_feature;
+	bool use_pcie_performance_levels;
+	bool use_pcie_powersaving_levels;
+	bool uvd_power_gated;
+	/* driver states */
+	struct radeon_ps current_rps;
+	struct ci_ps current_ps;
+	struct radeon_ps requested_rps;
+	struct ci_ps requested_ps;
+};
+
+#define CISLANDS_VOLTAGE_CONTROL_NONE                   0x0
+#define CISLANDS_VOLTAGE_CONTROL_BY_GPIO                0x1
+#define CISLANDS_VOLTAGE_CONTROL_BY_SVID2               0x2
+
+#define CISLANDS_Q88_FORMAT_CONVERSION_UNIT             256
+
+#define CISLANDS_VRC_DFLT0                              0x3FFFC000
+#define CISLANDS_VRC_DFLT1                              0x000400
+#define CISLANDS_VRC_DFLT2                              0xC00080
+#define CISLANDS_VRC_DFLT3                              0xC00200
+#define CISLANDS_VRC_DFLT4                              0xC01680
+#define CISLANDS_VRC_DFLT5                              0xC00033
+#define CISLANDS_VRC_DFLT6                              0xC00033
+#define CISLANDS_VRC_DFLT7                              0x3FFFC000
+
+#define CISLANDS_CGULVPARAMETER_DFLT                    0x00040035
+#define CISLAND_TARGETACTIVITY_DFLT                     30
+#define CISLAND_MCLK_TARGETACTIVITY_DFLT                10
+
+#define PCIE_PERF_REQ_REMOVE_REGISTRY   0
+#define PCIE_PERF_REQ_FORCE_LOWPOWER    1
+#define PCIE_PERF_REQ_PECI_GEN1         2
+#define PCIE_PERF_REQ_PECI_GEN2         3
+#define PCIE_PERF_REQ_PECI_GEN3         4
+
+int ci_copy_bytes_to_smc(struct radeon_device *rdev,
+			 u32 smc_start_address,
+			 const u8 *src, u32 byte_count, u32 limit);
+void ci_start_smc(struct radeon_device *rdev);
+void ci_reset_smc(struct radeon_device *rdev);
+int ci_program_jump_on_start(struct radeon_device *rdev);
+void ci_stop_smc_clock(struct radeon_device *rdev);
+void ci_start_smc_clock(struct radeon_device *rdev);
+bool ci_is_smc_running(struct radeon_device *rdev);
+PPSMC_Result ci_send_msg_to_smc(struct radeon_device *rdev, PPSMC_Msg msg);
+PPSMC_Result ci_wait_for_smc_inactive(struct radeon_device *rdev);
+int ci_load_smc_ucode(struct radeon_device *rdev, u32 limit);
+int ci_read_smc_sram_dword(struct radeon_device *rdev,
+			   u32 smc_address, u32 *value, u32 limit);
+int ci_write_smc_sram_dword(struct radeon_device *rdev,
+			    u32 smc_address, u32 value, u32 limit);
+
+#endif
diff --git a/drivers/gpu/drm/radeon/ci_smc.c b/drivers/gpu/drm/radeon/ci_smc.c
new file mode 100644
index 000000000000..252e10a41cf5
--- /dev/null
+++ b/drivers/gpu/drm/radeon/ci_smc.c
@@ -0,0 +1,275 @@
+/*
+ * Copyright 2011 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: Alex Deucher
+ */
+
+#include <linux/firmware.h>
+#include "drmP.h"
+#include "radeon.h"
+#include "cikd.h"
+#include "ppsmc.h"
+#include "radeon_ucode.h"
+
+static int ci_set_smc_sram_address(struct radeon_device *rdev,
+				   u32 smc_address, u32 limit)
+{
+	if (smc_address & 3)
+		return -EINVAL;
+	if ((smc_address + 3) > limit)
+		return -EINVAL;
+
+	WREG32(SMC_IND_INDEX_0, smc_address);
+	WREG32_P(SMC_IND_ACCESS_CNTL, 0, ~AUTO_INCREMENT_IND_0);
+
+	return 0;
+}
+
+int ci_copy_bytes_to_smc(struct radeon_device *rdev,
+			 u32 smc_start_address,
+			 const u8 *src, u32 byte_count, u32 limit)
+{
+	unsigned long flags;
+	u32 data, original_data;
+	u32 addr;
+	u32 extra_shift;
+	int ret = 0;
+
+	if (smc_start_address & 3)
+		return -EINVAL;
+	if ((smc_start_address + byte_count) > limit)
+		return -EINVAL;
+
+	addr = smc_start_address;
+
+	spin_lock_irqsave(&rdev->smc_idx_lock, flags);
+	while (byte_count >= 4) {
+		/* SMC address space is BE */
+		data = (src[0] << 24) | (src[1] << 16) | (src[2] << 8) | src[3];
+
+		ret = ci_set_smc_sram_address(rdev, addr, limit);
+		if (ret)
+			goto done;
+
+		WREG32(SMC_IND_DATA_0, data);
+
+		src += 4;
+		byte_count -= 4;
+		addr += 4;
+	}
+
+	/* RMW for the final bytes */
+	if (byte_count > 0) {
+		data = 0;
+
+		ret = ci_set_smc_sram_address(rdev, addr, limit);
+		if (ret)
+			goto done;
+
+		original_data = RREG32(SMC_IND_DATA_0);
+
+		extra_shift = 8 * (4 - byte_count);
+
+		while (byte_count > 0) {
+			data = (data << 8) + *src++;
+			byte_count--;
+		}
+
+		data <<= extra_shift;
+
+		data |= (original_data & ~((~0UL) << extra_shift));
+
+		ret = ci_set_smc_sram_address(rdev, addr, limit);
+		if (ret)
+			goto done;
+
+		WREG32(SMC_IND_DATA_0, data);
+	}
+
+done:
+	spin_unlock_irqrestore(&rdev->smc_idx_lock, flags);
+
+	return ret;
+}
+
+void ci_start_smc(struct radeon_device *rdev)
+{
+	u32 tmp = RREG32_SMC(SMC_SYSCON_RESET_CNTL);
+
+	tmp &= ~RST_REG;
+	WREG32_SMC(SMC_SYSCON_RESET_CNTL, tmp);
+}
+
+void ci_reset_smc(struct radeon_device *rdev)
+{
+	u32 tmp = RREG32_SMC(SMC_SYSCON_RESET_CNTL);
+
+	tmp |= RST_REG;
+	WREG32_SMC(SMC_SYSCON_RESET_CNTL, tmp);
+}
+
+int ci_program_jump_on_start(struct radeon_device *rdev)
+{
+	static u8 data[] = { 0xE0, 0x00, 0x80, 0x40 };
+
+	return ci_copy_bytes_to_smc(rdev, 0x0, data, 4, sizeof(data)+1);
+}
+
+void ci_stop_smc_clock(struct radeon_device *rdev)
+{
+	u32 tmp = RREG32_SMC(SMC_SYSCON_CLOCK_CNTL_0);
+
+	tmp |= CK_DISABLE;
+
+	WREG32_SMC(SMC_SYSCON_CLOCK_CNTL_0, tmp);
+}
+
+void ci_start_smc_clock(struct radeon_device *rdev)
+{
+	u32 tmp = RREG32_SMC(SMC_SYSCON_CLOCK_CNTL_0);
+
+	tmp &= ~CK_DISABLE;
+
+	WREG32_SMC(SMC_SYSCON_CLOCK_CNTL_0, tmp);
+}
+
+bool ci_is_smc_running(struct radeon_device *rdev)
+{
+	u32 clk = RREG32_SMC(SMC_SYSCON_CLOCK_CNTL_0);
+	u32 pc_c = RREG32_SMC(SMC_PC_C);
+
+	if (!(clk & CK_DISABLE) && (0x20100 <= pc_c))
+		return true;
+
+	return false;
+}
+
+PPSMC_Result ci_send_msg_to_smc(struct radeon_device *rdev, PPSMC_Msg msg)
+{
+	u32 tmp;
+	int i;
+
+	if (!ci_is_smc_running(rdev))
+		return PPSMC_Result_Failed;
+
+	WREG32(SMC_MESSAGE_0, msg);
+
+	for (i = 0; i < rdev->usec_timeout; i++) {
+		tmp = RREG32(SMC_RESP_0);
+		if (tmp != 0)
+			break;
+		udelay(1);
+	}
+	tmp = RREG32(SMC_RESP_0);
+
+	return (PPSMC_Result)tmp;
+}
+
+PPSMC_Result ci_wait_for_smc_inactive(struct radeon_device *rdev)
+{
+	u32 tmp;
+	int i;
+
+	if (!ci_is_smc_running(rdev))
+		return PPSMC_Result_OK;
+
+	for (i = 0; i < rdev->usec_timeout; i++) {
+                tmp = RREG32_SMC(SMC_SYSCON_CLOCK_CNTL_0);
+                if ((tmp & CKEN) == 0)
+			break;
+                udelay(1);
+        }
+
+	return PPSMC_Result_OK;
+}
+
+int ci_load_smc_ucode(struct radeon_device *rdev, u32 limit)
+{
+	unsigned long flags;
+	u32 ucode_start_address;
+	u32 ucode_size;
+	const u8 *src;
+	u32 data;
+
+	if (!rdev->smc_fw)
+		return -EINVAL;
+
+	switch (rdev->family) {
+	case CHIP_BONAIRE:
+		ucode_start_address = BONAIRE_SMC_UCODE_START;
+		ucode_size = BONAIRE_SMC_UCODE_SIZE;
+		break;
+	default:
+		DRM_ERROR("unknown asic in smc ucode loader\n");
+		BUG();
+	}
+
+	if (ucode_size & 3)
+		return -EINVAL;
+
+	src = (const u8 *)rdev->smc_fw->data;
+	spin_lock_irqsave(&rdev->smc_idx_lock, flags);
+	WREG32(SMC_IND_INDEX_0, ucode_start_address);
+	WREG32_P(SMC_IND_ACCESS_CNTL, AUTO_INCREMENT_IND_0, ~AUTO_INCREMENT_IND_0);
+	while (ucode_size >= 4) {
+		/* SMC address space is BE */
+		data = (src[0] << 24) | (src[1] << 16) | (src[2] << 8) | src[3];
+
+		WREG32(SMC_IND_DATA_0, data);
+
+		src += 4;
+		ucode_size -= 4;
+	}
+	WREG32_P(SMC_IND_ACCESS_CNTL, 0, ~AUTO_INCREMENT_IND_0);
+	spin_unlock_irqrestore(&rdev->smc_idx_lock, flags);
+
+	return 0;
+}
+
+int ci_read_smc_sram_dword(struct radeon_device *rdev,
+			   u32 smc_address, u32 *value, u32 limit)
+{
+	unsigned long flags;
+	int ret;
+
+	spin_lock_irqsave(&rdev->smc_idx_lock, flags);
+	ret = ci_set_smc_sram_address(rdev, smc_address, limit);
+	if (ret == 0)
+		*value = RREG32(SMC_IND_DATA_0);
+	spin_unlock_irqrestore(&rdev->smc_idx_lock, flags);
+
+	return ret;
+}
+
+int ci_write_smc_sram_dword(struct radeon_device *rdev,
+			    u32 smc_address, u32 value, u32 limit)
+{
+	unsigned long flags;
+	int ret;
+
+	spin_lock_irqsave(&rdev->smc_idx_lock, flags);
+	ret = ci_set_smc_sram_address(rdev, smc_address, limit);
+	if (ret == 0)
+		WREG32(SMC_IND_DATA_0, value);
+	spin_unlock_irqrestore(&rdev->smc_idx_lock, flags);
+
+	return ret;
+}
diff --git a/drivers/gpu/drm/radeon/cik.c b/drivers/gpu/drm/radeon/cik.c
index 8928bd109c16..b874ccdf52f7 100644
--- a/drivers/gpu/drm/radeon/cik.c
+++ b/drivers/gpu/drm/radeon/cik.c
@@ -30,22 +30,8 @@
 #include "cikd.h"
 #include "atom.h"
 #include "cik_blit_shaders.h"
-
-/* GFX */
-#define CIK_PFP_UCODE_SIZE 2144
-#define CIK_ME_UCODE_SIZE 2144
-#define CIK_CE_UCODE_SIZE 2144
-/* compute */
-#define CIK_MEC_UCODE_SIZE 4192
-/* interrupts */
-#define BONAIRE_RLC_UCODE_SIZE 2048
-#define KB_RLC_UCODE_SIZE 2560
-#define KV_RLC_UCODE_SIZE 2560
-/* gddr controller */
-#define CIK_MC_UCODE_SIZE 7866
-/* sdma */
-#define CIK_SDMA_UCODE_SIZE 1050
-#define CIK_SDMA_UCODE_VERSION 64
+#include "radeon_ucode.h"
+#include "clearstate_ci.h"
 
 MODULE_FIRMWARE("radeon/BONAIRE_pfp.bin");
 MODULE_FIRMWARE("radeon/BONAIRE_me.bin");
@@ -54,6 +40,7 @@ MODULE_FIRMWARE("radeon/BONAIRE_mec.bin");
 MODULE_FIRMWARE("radeon/BONAIRE_mc.bin");
 MODULE_FIRMWARE("radeon/BONAIRE_rlc.bin");
 MODULE_FIRMWARE("radeon/BONAIRE_sdma.bin");
+MODULE_FIRMWARE("radeon/BONAIRE_smc.bin");
 MODULE_FIRMWARE("radeon/KAVERI_pfp.bin");
 MODULE_FIRMWARE("radeon/KAVERI_me.bin");
 MODULE_FIRMWARE("radeon/KAVERI_ce.bin");
@@ -72,32 +59,866 @@ extern void r600_ih_ring_fini(struct radeon_device *rdev);
 extern void evergreen_mc_stop(struct radeon_device *rdev, struct evergreen_mc_save *save);
 extern void evergreen_mc_resume(struct radeon_device *rdev, struct evergreen_mc_save *save);
 extern bool evergreen_is_display_hung(struct radeon_device *rdev);
+extern void sumo_rlc_fini(struct radeon_device *rdev);
+extern int sumo_rlc_init(struct radeon_device *rdev);
 extern void si_vram_gtt_location(struct radeon_device *rdev, struct radeon_mc *mc);
-extern void si_rlc_fini(struct radeon_device *rdev);
-extern int si_rlc_init(struct radeon_device *rdev);
+extern void si_rlc_reset(struct radeon_device *rdev);
+extern void si_init_uvd_internal_cg(struct radeon_device *rdev);
+extern int cik_sdma_resume(struct radeon_device *rdev);
+extern void cik_sdma_enable(struct radeon_device *rdev, bool enable);
+extern void cik_sdma_fini(struct radeon_device *rdev);
+extern void cik_sdma_vm_set_page(struct radeon_device *rdev,
+				 struct radeon_ib *ib,
+				 uint64_t pe,
+				 uint64_t addr, unsigned count,
+				 uint32_t incr, uint32_t flags);
 static void cik_rlc_stop(struct radeon_device *rdev);
+static void cik_pcie_gen3_enable(struct radeon_device *rdev);
+static void cik_program_aspm(struct radeon_device *rdev);
+static void cik_init_pg(struct radeon_device *rdev);
+static void cik_init_cg(struct radeon_device *rdev);
+static void cik_fini_pg(struct radeon_device *rdev);
+static void cik_fini_cg(struct radeon_device *rdev);
+static void cik_enable_gui_idle_interrupt(struct radeon_device *rdev,
+					  bool enable);
+
+/* get temperature in millidegrees */
+int ci_get_temp(struct radeon_device *rdev)
+{
+	u32 temp;
+	int actual_temp = 0;
+
+	temp = (RREG32_SMC(CG_MULT_THERMAL_STATUS) & CTF_TEMP_MASK) >>
+		CTF_TEMP_SHIFT;
+
+	if (temp & 0x200)
+		actual_temp = 255;
+	else
+		actual_temp = temp & 0x1ff;
+
+	actual_temp = actual_temp * 1000;
+
+	return actual_temp;
+}
+
+/* get temperature in millidegrees */
+int kv_get_temp(struct radeon_device *rdev)
+{
+	u32 temp;
+	int actual_temp = 0;
+
+	temp = RREG32_SMC(0xC0300E0C);
+
+	if (temp)
+		actual_temp = (temp / 8) - 49;
+	else
+		actual_temp = 0;
+
+	actual_temp = actual_temp * 1000;
+
+	return actual_temp;
+}
 
 /*
  * Indirect registers accessor
  */
 u32 cik_pciep_rreg(struct radeon_device *rdev, u32 reg)
 {
+	unsigned long flags;
 	u32 r;
 
+	spin_lock_irqsave(&rdev->pciep_idx_lock, flags);
 	WREG32(PCIE_INDEX, reg);
 	(void)RREG32(PCIE_INDEX);
 	r = RREG32(PCIE_DATA);
+	spin_unlock_irqrestore(&rdev->pciep_idx_lock, flags);
 	return r;
 }
 
 void cik_pciep_wreg(struct radeon_device *rdev, u32 reg, u32 v)
 {
+	unsigned long flags;
+
+	spin_lock_irqsave(&rdev->pciep_idx_lock, flags);
 	WREG32(PCIE_INDEX, reg);
 	(void)RREG32(PCIE_INDEX);
 	WREG32(PCIE_DATA, v);
 	(void)RREG32(PCIE_DATA);
+	spin_unlock_irqrestore(&rdev->pciep_idx_lock, flags);
 }
 
+static const u32 spectre_rlc_save_restore_register_list[] =
+{
+	(0x0e00 << 16) | (0xc12c >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xc140 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xc150 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xc15c >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xc168 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xc170 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xc178 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xc204 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xc2b4 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xc2b8 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xc2bc >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xc2c0 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x8228 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x829c >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x869c >> 2),
+	0x00000000,
+	(0x0600 << 16) | (0x98f4 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x98f8 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x9900 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xc260 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x90e8 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x3c000 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x3c00c >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x8c1c >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x9700 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xcd20 >> 2),
+	0x00000000,
+	(0x4e00 << 16) | (0xcd20 >> 2),
+	0x00000000,
+	(0x5e00 << 16) | (0xcd20 >> 2),
+	0x00000000,
+	(0x6e00 << 16) | (0xcd20 >> 2),
+	0x00000000,
+	(0x7e00 << 16) | (0xcd20 >> 2),
+	0x00000000,
+	(0x8e00 << 16) | (0xcd20 >> 2),
+	0x00000000,
+	(0x9e00 << 16) | (0xcd20 >> 2),
+	0x00000000,
+	(0xae00 << 16) | (0xcd20 >> 2),
+	0x00000000,
+	(0xbe00 << 16) | (0xcd20 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x89bc >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x8900 >> 2),
+	0x00000000,
+	0x3,
+	(0x0e00 << 16) | (0xc130 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xc134 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xc1fc >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xc208 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xc264 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xc268 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xc26c >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xc270 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xc274 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xc278 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xc27c >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xc280 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xc284 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xc288 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xc28c >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xc290 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xc294 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xc298 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xc29c >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xc2a0 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xc2a4 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xc2a8 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xc2ac  >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xc2b0 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x301d0 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x30238 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x30250 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x30254 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x30258 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x3025c >> 2),
+	0x00000000,
+	(0x4e00 << 16) | (0xc900 >> 2),
+	0x00000000,
+	(0x5e00 << 16) | (0xc900 >> 2),
+	0x00000000,
+	(0x6e00 << 16) | (0xc900 >> 2),
+	0x00000000,
+	(0x7e00 << 16) | (0xc900 >> 2),
+	0x00000000,
+	(0x8e00 << 16) | (0xc900 >> 2),
+	0x00000000,
+	(0x9e00 << 16) | (0xc900 >> 2),
+	0x00000000,
+	(0xae00 << 16) | (0xc900 >> 2),
+	0x00000000,
+	(0xbe00 << 16) | (0xc900 >> 2),
+	0x00000000,
+	(0x4e00 << 16) | (0xc904 >> 2),
+	0x00000000,
+	(0x5e00 << 16) | (0xc904 >> 2),
+	0x00000000,
+	(0x6e00 << 16) | (0xc904 >> 2),
+	0x00000000,
+	(0x7e00 << 16) | (0xc904 >> 2),
+	0x00000000,
+	(0x8e00 << 16) | (0xc904 >> 2),
+	0x00000000,
+	(0x9e00 << 16) | (0xc904 >> 2),
+	0x00000000,
+	(0xae00 << 16) | (0xc904 >> 2),
+	0x00000000,
+	(0xbe00 << 16) | (0xc904 >> 2),
+	0x00000000,
+	(0x4e00 << 16) | (0xc908 >> 2),
+	0x00000000,
+	(0x5e00 << 16) | (0xc908 >> 2),
+	0x00000000,
+	(0x6e00 << 16) | (0xc908 >> 2),
+	0x00000000,
+	(0x7e00 << 16) | (0xc908 >> 2),
+	0x00000000,
+	(0x8e00 << 16) | (0xc908 >> 2),
+	0x00000000,
+	(0x9e00 << 16) | (0xc908 >> 2),
+	0x00000000,
+	(0xae00 << 16) | (0xc908 >> 2),
+	0x00000000,
+	(0xbe00 << 16) | (0xc908 >> 2),
+	0x00000000,
+	(0x4e00 << 16) | (0xc90c >> 2),
+	0x00000000,
+	(0x5e00 << 16) | (0xc90c >> 2),
+	0x00000000,
+	(0x6e00 << 16) | (0xc90c >> 2),
+	0x00000000,
+	(0x7e00 << 16) | (0xc90c >> 2),
+	0x00000000,
+	(0x8e00 << 16) | (0xc90c >> 2),
+	0x00000000,
+	(0x9e00 << 16) | (0xc90c >> 2),
+	0x00000000,
+	(0xae00 << 16) | (0xc90c >> 2),
+	0x00000000,
+	(0xbe00 << 16) | (0xc90c >> 2),
+	0x00000000,
+	(0x4e00 << 16) | (0xc910 >> 2),
+	0x00000000,
+	(0x5e00 << 16) | (0xc910 >> 2),
+	0x00000000,
+	(0x6e00 << 16) | (0xc910 >> 2),
+	0x00000000,
+	(0x7e00 << 16) | (0xc910 >> 2),
+	0x00000000,
+	(0x8e00 << 16) | (0xc910 >> 2),
+	0x00000000,
+	(0x9e00 << 16) | (0xc910 >> 2),
+	0x00000000,
+	(0xae00 << 16) | (0xc910 >> 2),
+	0x00000000,
+	(0xbe00 << 16) | (0xc910 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xc99c >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x9834 >> 2),
+	0x00000000,
+	(0x0000 << 16) | (0x30f00 >> 2),
+	0x00000000,
+	(0x0001 << 16) | (0x30f00 >> 2),
+	0x00000000,
+	(0x0000 << 16) | (0x30f04 >> 2),
+	0x00000000,
+	(0x0001 << 16) | (0x30f04 >> 2),
+	0x00000000,
+	(0x0000 << 16) | (0x30f08 >> 2),
+	0x00000000,
+	(0x0001 << 16) | (0x30f08 >> 2),
+	0x00000000,
+	(0x0000 << 16) | (0x30f0c >> 2),
+	0x00000000,
+	(0x0001 << 16) | (0x30f0c >> 2),
+	0x00000000,
+	(0x0600 << 16) | (0x9b7c >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x8a14 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x8a18 >> 2),
+	0x00000000,
+	(0x0600 << 16) | (0x30a00 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x8bf0 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x8bcc >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x8b24 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x30a04 >> 2),
+	0x00000000,
+	(0x0600 << 16) | (0x30a10 >> 2),
+	0x00000000,
+	(0x0600 << 16) | (0x30a14 >> 2),
+	0x00000000,
+	(0x0600 << 16) | (0x30a18 >> 2),
+	0x00000000,
+	(0x0600 << 16) | (0x30a2c >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xc700 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xc704 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xc708 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xc768 >> 2),
+	0x00000000,
+	(0x0400 << 16) | (0xc770 >> 2),
+	0x00000000,
+	(0x0400 << 16) | (0xc774 >> 2),
+	0x00000000,
+	(0x0400 << 16) | (0xc778 >> 2),
+	0x00000000,
+	(0x0400 << 16) | (0xc77c >> 2),
+	0x00000000,
+	(0x0400 << 16) | (0xc780 >> 2),
+	0x00000000,
+	(0x0400 << 16) | (0xc784 >> 2),
+	0x00000000,
+	(0x0400 << 16) | (0xc788 >> 2),
+	0x00000000,
+	(0x0400 << 16) | (0xc78c >> 2),
+	0x00000000,
+	(0x0400 << 16) | (0xc798 >> 2),
+	0x00000000,
+	(0x0400 << 16) | (0xc79c >> 2),
+	0x00000000,
+	(0x0400 << 16) | (0xc7a0 >> 2),
+	0x00000000,
+	(0x0400 << 16) | (0xc7a4 >> 2),
+	0x00000000,
+	(0x0400 << 16) | (0xc7a8 >> 2),
+	0x00000000,
+	(0x0400 << 16) | (0xc7ac >> 2),
+	0x00000000,
+	(0x0400 << 16) | (0xc7b0 >> 2),
+	0x00000000,
+	(0x0400 << 16) | (0xc7b4 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x9100 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x3c010 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x92a8 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x92ac >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x92b4 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x92b8 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x92bc >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x92c0 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x92c4 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x92c8 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x92cc >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x92d0 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x8c00 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x8c04 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x8c20 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x8c38 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x8c3c >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xae00 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x9604 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xac08 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xac0c >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xac10 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xac14 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xac58 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xac68 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xac6c >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xac70 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xac74 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xac78 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xac7c >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xac80 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xac84 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xac88 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xac8c >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x970c >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x9714 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x9718 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x971c >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x31068 >> 2),
+	0x00000000,
+	(0x4e00 << 16) | (0x31068 >> 2),
+	0x00000000,
+	(0x5e00 << 16) | (0x31068 >> 2),
+	0x00000000,
+	(0x6e00 << 16) | (0x31068 >> 2),
+	0x00000000,
+	(0x7e00 << 16) | (0x31068 >> 2),
+	0x00000000,
+	(0x8e00 << 16) | (0x31068 >> 2),
+	0x00000000,
+	(0x9e00 << 16) | (0x31068 >> 2),
+	0x00000000,
+	(0xae00 << 16) | (0x31068 >> 2),
+	0x00000000,
+	(0xbe00 << 16) | (0x31068 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xcd10 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xcd14 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x88b0 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x88b4 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x88b8 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x88bc >> 2),
+	0x00000000,
+	(0x0400 << 16) | (0x89c0 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x88c4 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x88c8 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x88d0 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x88d4 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x88d8 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x8980 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x30938 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x3093c >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x30940 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x89a0 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x30900 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x30904 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x89b4 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x3c210 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x3c214 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x3c218 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x8904 >> 2),
+	0x00000000,
+	0x5,
+	(0x0e00 << 16) | (0x8c28 >> 2),
+	(0x0e00 << 16) | (0x8c2c >> 2),
+	(0x0e00 << 16) | (0x8c30 >> 2),
+	(0x0e00 << 16) | (0x8c34 >> 2),
+	(0x0e00 << 16) | (0x9600 >> 2),
+};
+
+static const u32 kalindi_rlc_save_restore_register_list[] =
+{
+	(0x0e00 << 16) | (0xc12c >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xc140 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xc150 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xc15c >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xc168 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xc170 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xc204 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xc2b4 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xc2b8 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xc2bc >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xc2c0 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x8228 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x829c >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x869c >> 2),
+	0x00000000,
+	(0x0600 << 16) | (0x98f4 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x98f8 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x9900 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xc260 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x90e8 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x3c000 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x3c00c >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x8c1c >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x9700 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xcd20 >> 2),
+	0x00000000,
+	(0x4e00 << 16) | (0xcd20 >> 2),
+	0x00000000,
+	(0x5e00 << 16) | (0xcd20 >> 2),
+	0x00000000,
+	(0x6e00 << 16) | (0xcd20 >> 2),
+	0x00000000,
+	(0x7e00 << 16) | (0xcd20 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x89bc >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x8900 >> 2),
+	0x00000000,
+	0x3,
+	(0x0e00 << 16) | (0xc130 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xc134 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xc1fc >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xc208 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xc264 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xc268 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xc26c >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xc270 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xc274 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xc28c >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xc290 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xc294 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xc298 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xc2a0 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xc2a4 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xc2a8 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xc2ac >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x301d0 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x30238 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x30250 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x30254 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x30258 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x3025c >> 2),
+	0x00000000,
+	(0x4e00 << 16) | (0xc900 >> 2),
+	0x00000000,
+	(0x5e00 << 16) | (0xc900 >> 2),
+	0x00000000,
+	(0x6e00 << 16) | (0xc900 >> 2),
+	0x00000000,
+	(0x7e00 << 16) | (0xc900 >> 2),
+	0x00000000,
+	(0x4e00 << 16) | (0xc904 >> 2),
+	0x00000000,
+	(0x5e00 << 16) | (0xc904 >> 2),
+	0x00000000,
+	(0x6e00 << 16) | (0xc904 >> 2),
+	0x00000000,
+	(0x7e00 << 16) | (0xc904 >> 2),
+	0x00000000,
+	(0x4e00 << 16) | (0xc908 >> 2),
+	0x00000000,
+	(0x5e00 << 16) | (0xc908 >> 2),
+	0x00000000,
+	(0x6e00 << 16) | (0xc908 >> 2),
+	0x00000000,
+	(0x7e00 << 16) | (0xc908 >> 2),
+	0x00000000,
+	(0x4e00 << 16) | (0xc90c >> 2),
+	0x00000000,
+	(0x5e00 << 16) | (0xc90c >> 2),
+	0x00000000,
+	(0x6e00 << 16) | (0xc90c >> 2),
+	0x00000000,
+	(0x7e00 << 16) | (0xc90c >> 2),
+	0x00000000,
+	(0x4e00 << 16) | (0xc910 >> 2),
+	0x00000000,
+	(0x5e00 << 16) | (0xc910 >> 2),
+	0x00000000,
+	(0x6e00 << 16) | (0xc910 >> 2),
+	0x00000000,
+	(0x7e00 << 16) | (0xc910 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xc99c >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x9834 >> 2),
+	0x00000000,
+	(0x0000 << 16) | (0x30f00 >> 2),
+	0x00000000,
+	(0x0000 << 16) | (0x30f04 >> 2),
+	0x00000000,
+	(0x0000 << 16) | (0x30f08 >> 2),
+	0x00000000,
+	(0x0000 << 16) | (0x30f0c >> 2),
+	0x00000000,
+	(0x0600 << 16) | (0x9b7c >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x8a14 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x8a18 >> 2),
+	0x00000000,
+	(0x0600 << 16) | (0x30a00 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x8bf0 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x8bcc >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x8b24 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x30a04 >> 2),
+	0x00000000,
+	(0x0600 << 16) | (0x30a10 >> 2),
+	0x00000000,
+	(0x0600 << 16) | (0x30a14 >> 2),
+	0x00000000,
+	(0x0600 << 16) | (0x30a18 >> 2),
+	0x00000000,
+	(0x0600 << 16) | (0x30a2c >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xc700 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xc704 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xc708 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xc768 >> 2),
+	0x00000000,
+	(0x0400 << 16) | (0xc770 >> 2),
+	0x00000000,
+	(0x0400 << 16) | (0xc774 >> 2),
+	0x00000000,
+	(0x0400 << 16) | (0xc798 >> 2),
+	0x00000000,
+	(0x0400 << 16) | (0xc79c >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x9100 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x3c010 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x8c00 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x8c04 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x8c20 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x8c38 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x8c3c >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xae00 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x9604 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xac08 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xac0c >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xac10 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xac14 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xac58 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xac68 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xac6c >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xac70 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xac74 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xac78 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xac7c >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xac80 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xac84 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xac88 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xac8c >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x970c >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x9714 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x9718 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x971c >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x31068 >> 2),
+	0x00000000,
+	(0x4e00 << 16) | (0x31068 >> 2),
+	0x00000000,
+	(0x5e00 << 16) | (0x31068 >> 2),
+	0x00000000,
+	(0x6e00 << 16) | (0x31068 >> 2),
+	0x00000000,
+	(0x7e00 << 16) | (0x31068 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xcd10 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0xcd14 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x88b0 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x88b4 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x88b8 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x88bc >> 2),
+	0x00000000,
+	(0x0400 << 16) | (0x89c0 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x88c4 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x88c8 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x88d0 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x88d4 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x88d8 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x8980 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x30938 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x3093c >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x30940 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x89a0 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x30900 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x30904 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x89b4 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x3e1fc >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x3c210 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x3c214 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x3c218 >> 2),
+	0x00000000,
+	(0x0e00 << 16) | (0x8904 >> 2),
+	0x00000000,
+	0x5,
+	(0x0e00 << 16) | (0x8c28 >> 2),
+	(0x0e00 << 16) | (0x8c2c >> 2),
+	(0x0e00 << 16) | (0x8c30 >> 2),
+	(0x0e00 << 16) | (0x8c34 >> 2),
+	(0x0e00 << 16) | (0x9600 >> 2),
+};
+
 static const u32 bonaire_golden_spm_registers[] =
 {
 	0x30800, 0xe0ffffff, 0xe0000000
@@ -744,7 +1565,7 @@ static int cik_init_microcode(struct radeon_device *rdev)
 	const char *chip_name;
 	size_t pfp_req_size, me_req_size, ce_req_size,
 		mec_req_size, rlc_req_size, mc_req_size,
-		sdma_req_size;
+		sdma_req_size, smc_req_size;
 	char fw_name[30];
 	int err;
 
@@ -760,6 +1581,7 @@ static int cik_init_microcode(struct radeon_device *rdev)
 		rlc_req_size = BONAIRE_RLC_UCODE_SIZE * 4;
 		mc_req_size = CIK_MC_UCODE_SIZE * 4;
 		sdma_req_size = CIK_SDMA_UCODE_SIZE * 4;
+		smc_req_size = ALIGN(BONAIRE_SMC_UCODE_SIZE, 4);
 		break;
 	case CHIP_KAVERI:
 		chip_name = "KAVERI";
@@ -851,7 +1673,7 @@ static int cik_init_microcode(struct radeon_device *rdev)
 		err = -EINVAL;
 	}
 
-	/* No MC ucode on APUs */
+	/* No SMC, MC ucode on APUs */
 	if (!(rdev->flags & RADEON_IS_IGP)) {
 		snprintf(fw_name, sizeof(fw_name), "radeon/%s_mc.bin", chip_name);
 		err = request_firmware(&rdev->mc_fw, fw_name, rdev->dev);
@@ -863,6 +1685,21 @@ static int cik_init_microcode(struct radeon_device *rdev)
 			       rdev->mc_fw->size, fw_name);
 			err = -EINVAL;
 		}
+
+		snprintf(fw_name, sizeof(fw_name), "radeon/%s_smc.bin", chip_name);
+		err = request_firmware(&rdev->smc_fw, fw_name, rdev->dev);
+		if (err) {
+			printk(KERN_ERR
+			       "smc: error loading firmware \"%s\"\n",
+			       fw_name);
+			release_firmware(rdev->smc_fw);
+			rdev->smc_fw = NULL;
+		} else if (rdev->smc_fw->size != smc_req_size) {
+			printk(KERN_ERR
+			       "cik_smc: Bogus length %zu in firmware \"%s\"\n",
+			       rdev->smc_fw->size, fw_name);
+			err = -EINVAL;
+		}
 	}
 
 out:
@@ -881,6 +1718,8 @@ out:
 		rdev->rlc_fw = NULL;
 		release_firmware(rdev->mc_fw);
 		rdev->mc_fw = NULL;
+		release_firmware(rdev->smc_fw);
+		rdev->smc_fw = NULL;
 	}
 	return err;
 }
@@ -1880,7 +2719,47 @@ static void cik_gpu_init(struct radeon_device *rdev)
 		gb_addr_config = BONAIRE_GB_ADDR_CONFIG_GOLDEN;
 		break;
 	case CHIP_KAVERI:
-		/* TODO */
+		rdev->config.cik.max_shader_engines = 1;
+		rdev->config.cik.max_tile_pipes = 4;
+		if ((rdev->pdev->device == 0x1304) ||
+		    (rdev->pdev->device == 0x1305) ||
+		    (rdev->pdev->device == 0x130C) ||
+		    (rdev->pdev->device == 0x130F) ||
+		    (rdev->pdev->device == 0x1310) ||
+		    (rdev->pdev->device == 0x1311) ||
+		    (rdev->pdev->device == 0x131C)) {
+			rdev->config.cik.max_cu_per_sh = 8;
+			rdev->config.cik.max_backends_per_se = 2;
+		} else if ((rdev->pdev->device == 0x1309) ||
+			   (rdev->pdev->device == 0x130A) ||
+			   (rdev->pdev->device == 0x130D) ||
+			   (rdev->pdev->device == 0x1313) ||
+			   (rdev->pdev->device == 0x131D)) {
+			rdev->config.cik.max_cu_per_sh = 6;
+			rdev->config.cik.max_backends_per_se = 2;
+		} else if ((rdev->pdev->device == 0x1306) ||
+			   (rdev->pdev->device == 0x1307) ||
+			   (rdev->pdev->device == 0x130B) ||
+			   (rdev->pdev->device == 0x130E) ||
+			   (rdev->pdev->device == 0x1315) ||
+			   (rdev->pdev->device == 0x131B)) {
+			rdev->config.cik.max_cu_per_sh = 4;
+			rdev->config.cik.max_backends_per_se = 1;
+		} else {
+			rdev->config.cik.max_cu_per_sh = 3;
+			rdev->config.cik.max_backends_per_se = 1;
+		}
+		rdev->config.cik.max_sh_per_se = 1;
+		rdev->config.cik.max_texture_channel_caches = 4;
+		rdev->config.cik.max_gprs = 256;
+		rdev->config.cik.max_gs_threads = 16;
+		rdev->config.cik.max_hw_contexts = 8;
+
+		rdev->config.cik.sc_prim_fifo_size_frontend = 0x20;
+		rdev->config.cik.sc_prim_fifo_size_backend = 0x100;
+		rdev->config.cik.sc_hiz_tile_fifo_size = 0x30;
+		rdev->config.cik.sc_earlyz_tile_fifo_size = 0x130;
+		gb_addr_config = BONAIRE_GB_ADDR_CONFIG_GOLDEN;
 		break;
 	case CHIP_KABINI:
 	default:
@@ -1968,10 +2847,8 @@ static void cik_gpu_init(struct radeon_device *rdev)
 		rdev->config.cik.tile_config |= (3 << 0);
 		break;
 	}
-	if ((mc_arb_ramcfg & NOOFBANK_MASK) >> NOOFBANK_SHIFT)
-		rdev->config.cik.tile_config |= 1 << 4;
-	else
-		rdev->config.cik.tile_config |= 0 << 4;
+	rdev->config.cik.tile_config |=
+		((mc_arb_ramcfg & NOOFBANK_MASK) >> NOOFBANK_SHIFT) << 4;
 	rdev->config.cik.tile_config |=
 		((gb_addr_config & PIPE_INTERLEAVE_SIZE_MASK) >> PIPE_INTERLEAVE_SIZE_SHIFT) << 8;
 	rdev->config.cik.tile_config |=
@@ -2535,8 +3412,8 @@ static int cik_cp_gfx_resume(struct radeon_device *rdev)
 	/* ring 0 - compute and gfx */
 	/* Set ring buffer size */
 	ring = &rdev->ring[RADEON_RING_TYPE_GFX_INDEX];
-	rb_bufsz = drm_order(ring->ring_size / 8);
-	tmp = (drm_order(RADEON_GPU_PAGE_SIZE/8) << 8) | rb_bufsz;
+	rb_bufsz = order_base_2(ring->ring_size / 8);
+	tmp = (order_base_2(RADEON_GPU_PAGE_SIZE/8) << 8) | rb_bufsz;
 #ifdef __BIG_ENDIAN
 	tmp |= BUF_SWAP_32BIT;
 #endif
@@ -2593,7 +3470,6 @@ u32 cik_compute_ring_get_rptr(struct radeon_device *rdev,
 		cik_srbm_select(rdev, 0, 0, 0, 0);
 		mutex_unlock(&rdev->srbm_mutex);
 	}
-	rptr = (rptr & ring->ptr_reg_mask) >> ring->ptr_reg_shift;
 
 	return rptr;
 }
@@ -2612,7 +3488,6 @@ u32 cik_compute_ring_get_wptr(struct radeon_device *rdev,
 		cik_srbm_select(rdev, 0, 0, 0, 0);
 		mutex_unlock(&rdev->srbm_mutex);
 	}
-	wptr = (wptr & ring->ptr_reg_mask) >> ring->ptr_reg_shift;
 
 	return wptr;
 }
@@ -2620,10 +3495,8 @@ u32 cik_compute_ring_get_wptr(struct radeon_device *rdev,
 void cik_compute_ring_set_wptr(struct radeon_device *rdev,
 			       struct radeon_ring *ring)
 {
-	u32 wptr = (ring->wptr << ring->ptr_reg_shift) & ring->ptr_reg_mask;
-
-	rdev->wb.wb[ring->wptr_offs/4] = cpu_to_le32(wptr);
-	WDOORBELL32(ring->doorbell_offset, wptr);
+	rdev->wb.wb[ring->wptr_offs/4] = cpu_to_le32(ring->wptr);
+	WDOORBELL32(ring->doorbell_offset, ring->wptr);
 }
 
 /**
@@ -2920,7 +3793,7 @@ static int cik_cp_compute_resume(struct radeon_device *rdev)
 		/* set the EOP size, register value is 2^(EOP_SIZE+1) dwords */
 		tmp = RREG32(CP_HPD_EOP_CONTROL);
 		tmp &= ~EOP_SIZE_MASK;
-		tmp |= drm_order(MEC_HPD_SIZE / 8);
+		tmp |= order_base_2(MEC_HPD_SIZE / 8);
 		WREG32(CP_HPD_EOP_CONTROL, tmp);
 	}
 	cik_srbm_select(rdev, 0, 0, 0, 0);
@@ -3037,9 +3910,9 @@ static int cik_cp_compute_resume(struct radeon_device *rdev)
 			~(QUEUE_SIZE_MASK | RPTR_BLOCK_SIZE_MASK);
 
 		mqd->queue_state.cp_hqd_pq_control |=
-			drm_order(rdev->ring[idx].ring_size / 8);
+			order_base_2(rdev->ring[idx].ring_size / 8);
 		mqd->queue_state.cp_hqd_pq_control |=
-			(drm_order(RADEON_GPU_PAGE_SIZE/8) << 8);
+			(order_base_2(RADEON_GPU_PAGE_SIZE/8) << 8);
 #ifdef __BIG_ENDIAN
 		mqd->queue_state.cp_hqd_pq_control |= BUF_SWAP_32BIT;
 #endif
@@ -3150,12 +4023,7 @@ static int cik_cp_resume(struct radeon_device *rdev)
 {
 	int r;
 
-	/* Reset all cp blocks */
-	WREG32(GRBM_SOFT_RESET, SOFT_RESET_CP);
-	RREG32(GRBM_SOFT_RESET);
-	mdelay(15);
-	WREG32(GRBM_SOFT_RESET, 0);
-	RREG32(GRBM_SOFT_RESET);
+	cik_enable_gui_idle_interrupt(rdev, false);
 
 	r = cik_cp_load_microcode(rdev);
 	if (r)
@@ -3168,582 +4036,11 @@ static int cik_cp_resume(struct radeon_device *rdev)
 	if (r)
 		return r;
 
-	return 0;
-}
-
-/*
- * sDMA - System DMA
- * Starting with CIK, the GPU has new asynchronous
- * DMA engines.  These engines are used for compute
- * and gfx.  There are two DMA engines (SDMA0, SDMA1)
- * and each one supports 1 ring buffer used for gfx
- * and 2 queues used for compute.
- *
- * The programming model is very similar to the CP
- * (ring buffer, IBs, etc.), but sDMA has it's own
- * packet format that is different from the PM4 format
- * used by the CP. sDMA supports copying data, writing
- * embedded data, solid fills, and a number of other
- * things.  It also has support for tiling/detiling of
- * buffers.
- */
-/**
- * cik_sdma_ring_ib_execute - Schedule an IB on the DMA engine
- *
- * @rdev: radeon_device pointer
- * @ib: IB object to schedule
- *
- * Schedule an IB in the DMA ring (CIK).
- */
-void cik_sdma_ring_ib_execute(struct radeon_device *rdev,
-			      struct radeon_ib *ib)
-{
-	struct radeon_ring *ring = &rdev->ring[ib->ring];
-	u32 extra_bits = (ib->vm ? ib->vm->id : 0) & 0xf;
-
-	if (rdev->wb.enabled) {
-		u32 next_rptr = ring->wptr + 5;
-		while ((next_rptr & 7) != 4)
-			next_rptr++;
-		next_rptr += 4;
-		radeon_ring_write(ring, SDMA_PACKET(SDMA_OPCODE_WRITE, SDMA_WRITE_SUB_OPCODE_LINEAR, 0));
-		radeon_ring_write(ring, ring->next_rptr_gpu_addr & 0xfffffffc);
-		radeon_ring_write(ring, upper_32_bits(ring->next_rptr_gpu_addr) & 0xffffffff);
-		radeon_ring_write(ring, 1); /* number of DWs to follow */
-		radeon_ring_write(ring, next_rptr);
-	}
-
-	/* IB packet must end on a 8 DW boundary */
-	while ((ring->wptr & 7) != 4)
-		radeon_ring_write(ring, SDMA_PACKET(SDMA_OPCODE_NOP, 0, 0));
-	radeon_ring_write(ring, SDMA_PACKET(SDMA_OPCODE_INDIRECT_BUFFER, 0, extra_bits));
-	radeon_ring_write(ring, ib->gpu_addr & 0xffffffe0); /* base must be 32 byte aligned */
-	radeon_ring_write(ring, upper_32_bits(ib->gpu_addr) & 0xffffffff);
-	radeon_ring_write(ring, ib->length_dw);
-
-}
-
-/**
- * cik_sdma_fence_ring_emit - emit a fence on the DMA ring
- *
- * @rdev: radeon_device pointer
- * @fence: radeon fence object
- *
- * Add a DMA fence packet to the ring to write
- * the fence seq number and DMA trap packet to generate
- * an interrupt if needed (CIK).
- */
-void cik_sdma_fence_ring_emit(struct radeon_device *rdev,
-			      struct radeon_fence *fence)
-{
-	struct radeon_ring *ring = &rdev->ring[fence->ring];
-	u64 addr = rdev->fence_drv[fence->ring].gpu_addr;
-	u32 extra_bits = (SDMA_POLL_REG_MEM_EXTRA_OP(1) |
-			  SDMA_POLL_REG_MEM_EXTRA_FUNC(3)); /* == */
-	u32 ref_and_mask;
-
-	if (fence->ring == R600_RING_TYPE_DMA_INDEX)
-		ref_and_mask = SDMA0;
-	else
-		ref_and_mask = SDMA1;
-
-	/* write the fence */
-	radeon_ring_write(ring, SDMA_PACKET(SDMA_OPCODE_FENCE, 0, 0));
-	radeon_ring_write(ring, addr & 0xffffffff);
-	radeon_ring_write(ring, upper_32_bits(addr) & 0xffffffff);
-	radeon_ring_write(ring, fence->seq);
-	/* generate an interrupt */
-	radeon_ring_write(ring, SDMA_PACKET(SDMA_OPCODE_TRAP, 0, 0));
-	/* flush HDP */
-	radeon_ring_write(ring, SDMA_PACKET(SDMA_OPCODE_POLL_REG_MEM, 0, extra_bits));
-	radeon_ring_write(ring, GPU_HDP_FLUSH_DONE);
-	radeon_ring_write(ring, GPU_HDP_FLUSH_REQ);
-	radeon_ring_write(ring, ref_and_mask); /* REFERENCE */
-	radeon_ring_write(ring, ref_and_mask); /* MASK */
-	radeon_ring_write(ring, (4 << 16) | 10); /* RETRY_COUNT, POLL_INTERVAL */
-}
-
-/**
- * cik_sdma_semaphore_ring_emit - emit a semaphore on the dma ring
- *
- * @rdev: radeon_device pointer
- * @ring: radeon_ring structure holding ring information
- * @semaphore: radeon semaphore object
- * @emit_wait: wait or signal semaphore
- *
- * Add a DMA semaphore packet to the ring wait on or signal
- * other rings (CIK).
- */
-void cik_sdma_semaphore_ring_emit(struct radeon_device *rdev,
-				  struct radeon_ring *ring,
-				  struct radeon_semaphore *semaphore,
-				  bool emit_wait)
-{
-	u64 addr = semaphore->gpu_addr;
-	u32 extra_bits = emit_wait ? 0 : SDMA_SEMAPHORE_EXTRA_S;
-
-	radeon_ring_write(ring, SDMA_PACKET(SDMA_OPCODE_SEMAPHORE, 0, extra_bits));
-	radeon_ring_write(ring, addr & 0xfffffff8);
-	radeon_ring_write(ring, upper_32_bits(addr) & 0xffffffff);
-}
-
-/**
- * cik_sdma_gfx_stop - stop the gfx async dma engines
- *
- * @rdev: radeon_device pointer
- *
- * Stop the gfx async dma ring buffers (CIK).
- */
-static void cik_sdma_gfx_stop(struct radeon_device *rdev)
-{
-	u32 rb_cntl, reg_offset;
-	int i;
-
-	radeon_ttm_set_active_vram_size(rdev, rdev->mc.visible_vram_size);
-
-	for (i = 0; i < 2; i++) {
-		if (i == 0)
-			reg_offset = SDMA0_REGISTER_OFFSET;
-		else
-			reg_offset = SDMA1_REGISTER_OFFSET;
-		rb_cntl = RREG32(SDMA0_GFX_RB_CNTL + reg_offset);
-		rb_cntl &= ~SDMA_RB_ENABLE;
-		WREG32(SDMA0_GFX_RB_CNTL + reg_offset, rb_cntl);
-		WREG32(SDMA0_GFX_IB_CNTL + reg_offset, 0);
-	}
-}
-
-/**
- * cik_sdma_rlc_stop - stop the compute async dma engines
- *
- * @rdev: radeon_device pointer
- *
- * Stop the compute async dma queues (CIK).
- */
-static void cik_sdma_rlc_stop(struct radeon_device *rdev)
-{
-	/* XXX todo */
-}
-
-/**
- * cik_sdma_enable - stop the async dma engines
- *
- * @rdev: radeon_device pointer
- * @enable: enable/disable the DMA MEs.
- *
- * Halt or unhalt the async dma engines (CIK).
- */
-static void cik_sdma_enable(struct radeon_device *rdev, bool enable)
-{
-	u32 me_cntl, reg_offset;
-	int i;
-
-	for (i = 0; i < 2; i++) {
-		if (i == 0)
-			reg_offset = SDMA0_REGISTER_OFFSET;
-		else
-			reg_offset = SDMA1_REGISTER_OFFSET;
-		me_cntl = RREG32(SDMA0_ME_CNTL + reg_offset);
-		if (enable)
-			me_cntl &= ~SDMA_HALT;
-		else
-			me_cntl |= SDMA_HALT;
-		WREG32(SDMA0_ME_CNTL + reg_offset, me_cntl);
-	}
-}
-
-/**
- * cik_sdma_gfx_resume - setup and start the async dma engines
- *
- * @rdev: radeon_device pointer
- *
- * Set up the gfx DMA ring buffers and enable them (CIK).
- * Returns 0 for success, error for failure.
- */
-static int cik_sdma_gfx_resume(struct radeon_device *rdev)
-{
-	struct radeon_ring *ring;
-	u32 rb_cntl, ib_cntl;
-	u32 rb_bufsz;
-	u32 reg_offset, wb_offset;
-	int i, r;
-
-	for (i = 0; i < 2; i++) {
-		if (i == 0) {
-			ring = &rdev->ring[R600_RING_TYPE_DMA_INDEX];
-			reg_offset = SDMA0_REGISTER_OFFSET;
-			wb_offset = R600_WB_DMA_RPTR_OFFSET;
-		} else {
-			ring = &rdev->ring[CAYMAN_RING_TYPE_DMA1_INDEX];
-			reg_offset = SDMA1_REGISTER_OFFSET;
-			wb_offset = CAYMAN_WB_DMA1_RPTR_OFFSET;
-		}
-
-		WREG32(SDMA0_SEM_INCOMPLETE_TIMER_CNTL + reg_offset, 0);
-		WREG32(SDMA0_SEM_WAIT_FAIL_TIMER_CNTL + reg_offset, 0);
-
-		/* Set ring buffer size in dwords */
-		rb_bufsz = drm_order(ring->ring_size / 4);
-		rb_cntl = rb_bufsz << 1;
-#ifdef __BIG_ENDIAN
-		rb_cntl |= SDMA_RB_SWAP_ENABLE | SDMA_RPTR_WRITEBACK_SWAP_ENABLE;
-#endif
-		WREG32(SDMA0_GFX_RB_CNTL + reg_offset, rb_cntl);
-
-		/* Initialize the ring buffer's read and write pointers */
-		WREG32(SDMA0_GFX_RB_RPTR + reg_offset, 0);
-		WREG32(SDMA0_GFX_RB_WPTR + reg_offset, 0);
-
-		/* set the wb address whether it's enabled or not */
-		WREG32(SDMA0_GFX_RB_RPTR_ADDR_HI + reg_offset,
-		       upper_32_bits(rdev->wb.gpu_addr + wb_offset) & 0xFFFFFFFF);
-		WREG32(SDMA0_GFX_RB_RPTR_ADDR_LO + reg_offset,
-		       ((rdev->wb.gpu_addr + wb_offset) & 0xFFFFFFFC));
-
-		if (rdev->wb.enabled)
-			rb_cntl |= SDMA_RPTR_WRITEBACK_ENABLE;
-
-		WREG32(SDMA0_GFX_RB_BASE + reg_offset, ring->gpu_addr >> 8);
-		WREG32(SDMA0_GFX_RB_BASE_HI + reg_offset, ring->gpu_addr >> 40);
-
-		ring->wptr = 0;
-		WREG32(SDMA0_GFX_RB_WPTR + reg_offset, ring->wptr << 2);
-
-		ring->rptr = RREG32(SDMA0_GFX_RB_RPTR + reg_offset) >> 2;
-
-		/* enable DMA RB */
-		WREG32(SDMA0_GFX_RB_CNTL + reg_offset, rb_cntl | SDMA_RB_ENABLE);
-
-		ib_cntl = SDMA_IB_ENABLE;
-#ifdef __BIG_ENDIAN
-		ib_cntl |= SDMA_IB_SWAP_ENABLE;
-#endif
-		/* enable DMA IBs */
-		WREG32(SDMA0_GFX_IB_CNTL + reg_offset, ib_cntl);
-
-		ring->ready = true;
-
-		r = radeon_ring_test(rdev, ring->idx, ring);
-		if (r) {
-			ring->ready = false;
-			return r;
-		}
-	}
-
-	radeon_ttm_set_active_vram_size(rdev, rdev->mc.real_vram_size);
-
-	return 0;
-}
-
-/**
- * cik_sdma_rlc_resume - setup and start the async dma engines
- *
- * @rdev: radeon_device pointer
- *
- * Set up the compute DMA queues and enable them (CIK).
- * Returns 0 for success, error for failure.
- */
-static int cik_sdma_rlc_resume(struct radeon_device *rdev)
-{
-	/* XXX todo */
-	return 0;
-}
-
-/**
- * cik_sdma_load_microcode - load the sDMA ME ucode
- *
- * @rdev: radeon_device pointer
- *
- * Loads the sDMA0/1 ucode.
- * Returns 0 for success, -EINVAL if the ucode is not available.
- */
-static int cik_sdma_load_microcode(struct radeon_device *rdev)
-{
-	const __be32 *fw_data;
-	int i;
-
-	if (!rdev->sdma_fw)
-		return -EINVAL;
-
-	/* stop the gfx rings and rlc compute queues */
-	cik_sdma_gfx_stop(rdev);
-	cik_sdma_rlc_stop(rdev);
-
-	/* halt the MEs */
-	cik_sdma_enable(rdev, false);
-
-	/* sdma0 */
-	fw_data = (const __be32 *)rdev->sdma_fw->data;
-	WREG32(SDMA0_UCODE_ADDR + SDMA0_REGISTER_OFFSET, 0);
-	for (i = 0; i < CIK_SDMA_UCODE_SIZE; i++)
-		WREG32(SDMA0_UCODE_DATA + SDMA0_REGISTER_OFFSET, be32_to_cpup(fw_data++));
-	WREG32(SDMA0_UCODE_DATA + SDMA0_REGISTER_OFFSET, CIK_SDMA_UCODE_VERSION);
-
-	/* sdma1 */
-	fw_data = (const __be32 *)rdev->sdma_fw->data;
-	WREG32(SDMA0_UCODE_ADDR + SDMA1_REGISTER_OFFSET, 0);
-	for (i = 0; i < CIK_SDMA_UCODE_SIZE; i++)
-		WREG32(SDMA0_UCODE_DATA + SDMA1_REGISTER_OFFSET, be32_to_cpup(fw_data++));
-	WREG32(SDMA0_UCODE_DATA + SDMA1_REGISTER_OFFSET, CIK_SDMA_UCODE_VERSION);
-
-	WREG32(SDMA0_UCODE_ADDR + SDMA0_REGISTER_OFFSET, 0);
-	WREG32(SDMA0_UCODE_ADDR + SDMA1_REGISTER_OFFSET, 0);
-	return 0;
-}
-
-/**
- * cik_sdma_resume - setup and start the async dma engines
- *
- * @rdev: radeon_device pointer
- *
- * Set up the DMA engines and enable them (CIK).
- * Returns 0 for success, error for failure.
- */
-static int cik_sdma_resume(struct radeon_device *rdev)
-{
-	int r;
-
-	/* Reset dma */
-	WREG32(SRBM_SOFT_RESET, SOFT_RESET_SDMA | SOFT_RESET_SDMA1);
-	RREG32(SRBM_SOFT_RESET);
-	udelay(50);
-	WREG32(SRBM_SOFT_RESET, 0);
-	RREG32(SRBM_SOFT_RESET);
-
-	r = cik_sdma_load_microcode(rdev);
-	if (r)
-		return r;
-
-	/* unhalt the MEs */
-	cik_sdma_enable(rdev, true);
-
-	/* start the gfx rings and rlc compute queues */
-	r = cik_sdma_gfx_resume(rdev);
-	if (r)
-		return r;
-	r = cik_sdma_rlc_resume(rdev);
-	if (r)
-		return r;
+	cik_enable_gui_idle_interrupt(rdev, true);
 
 	return 0;
 }
 
-/**
- * cik_sdma_fini - tear down the async dma engines
- *
- * @rdev: radeon_device pointer
- *
- * Stop the async dma engines and free the rings (CIK).
- */
-static void cik_sdma_fini(struct radeon_device *rdev)
-{
-	/* stop the gfx rings and rlc compute queues */
-	cik_sdma_gfx_stop(rdev);
-	cik_sdma_rlc_stop(rdev);
-	/* halt the MEs */
-	cik_sdma_enable(rdev, false);
-	radeon_ring_fini(rdev, &rdev->ring[R600_RING_TYPE_DMA_INDEX]);
-	radeon_ring_fini(rdev, &rdev->ring[CAYMAN_RING_TYPE_DMA1_INDEX]);
-	/* XXX - compute dma queue tear down */
-}
-
-/**
- * cik_copy_dma - copy pages using the DMA engine
- *
- * @rdev: radeon_device pointer
- * @src_offset: src GPU address
- * @dst_offset: dst GPU address
- * @num_gpu_pages: number of GPU pages to xfer
- * @fence: radeon fence object
- *
- * Copy GPU paging using the DMA engine (CIK).
- * Used by the radeon ttm implementation to move pages if
- * registered as the asic copy callback.
- */
-int cik_copy_dma(struct radeon_device *rdev,
-		 uint64_t src_offset, uint64_t dst_offset,
-		 unsigned num_gpu_pages,
-		 struct radeon_fence **fence)
-{
-	struct radeon_semaphore *sem = NULL;
-	int ring_index = rdev->asic->copy.dma_ring_index;
-	struct radeon_ring *ring = &rdev->ring[ring_index];
-	u32 size_in_bytes, cur_size_in_bytes;
-	int i, num_loops;
-	int r = 0;
-
-	r = radeon_semaphore_create(rdev, &sem);
-	if (r) {
-		DRM_ERROR("radeon: moving bo (%d).\n", r);
-		return r;
-	}
-
-	size_in_bytes = (num_gpu_pages << RADEON_GPU_PAGE_SHIFT);
-	num_loops = DIV_ROUND_UP(size_in_bytes, 0x1fffff);
-	r = radeon_ring_lock(rdev, ring, num_loops * 7 + 14);
-	if (r) {
-		DRM_ERROR("radeon: moving bo (%d).\n", r);
-		radeon_semaphore_free(rdev, &sem, NULL);
-		return r;
-	}
-
-	if (radeon_fence_need_sync(*fence, ring->idx)) {
-		radeon_semaphore_sync_rings(rdev, sem, (*fence)->ring,
-					    ring->idx);
-		radeon_fence_note_sync(*fence, ring->idx);
-	} else {
-		radeon_semaphore_free(rdev, &sem, NULL);
-	}
-
-	for (i = 0; i < num_loops; i++) {
-		cur_size_in_bytes = size_in_bytes;
-		if (cur_size_in_bytes > 0x1fffff)
-			cur_size_in_bytes = 0x1fffff;
-		size_in_bytes -= cur_size_in_bytes;
-		radeon_ring_write(ring, SDMA_PACKET(SDMA_OPCODE_COPY, SDMA_COPY_SUB_OPCODE_LINEAR, 0));
-		radeon_ring_write(ring, cur_size_in_bytes);
-		radeon_ring_write(ring, 0); /* src/dst endian swap */
-		radeon_ring_write(ring, src_offset & 0xffffffff);
-		radeon_ring_write(ring, upper_32_bits(src_offset) & 0xffffffff);
-		radeon_ring_write(ring, dst_offset & 0xfffffffc);
-		radeon_ring_write(ring, upper_32_bits(dst_offset) & 0xffffffff);
-		src_offset += cur_size_in_bytes;
-		dst_offset += cur_size_in_bytes;
-	}
-
-	r = radeon_fence_emit(rdev, fence, ring->idx);
-	if (r) {
-		radeon_ring_unlock_undo(rdev, ring);
-		return r;
-	}
-
-	radeon_ring_unlock_commit(rdev, ring);
-	radeon_semaphore_free(rdev, &sem, *fence);
-
-	return r;
-}
-
-/**
- * cik_sdma_ring_test - simple async dma engine test
- *
- * @rdev: radeon_device pointer
- * @ring: radeon_ring structure holding ring information
- *
- * Test the DMA engine by writing using it to write an
- * value to memory. (CIK).
- * Returns 0 for success, error for failure.
- */
-int cik_sdma_ring_test(struct radeon_device *rdev,
-		       struct radeon_ring *ring)
-{
-	unsigned i;
-	int r;
-	void __iomem *ptr = (void *)rdev->vram_scratch.ptr;
-	u32 tmp;
-
-	if (!ptr) {
-		DRM_ERROR("invalid vram scratch pointer\n");
-		return -EINVAL;
-	}
-
-	tmp = 0xCAFEDEAD;
-	writel(tmp, ptr);
-
-	r = radeon_ring_lock(rdev, ring, 4);
-	if (r) {
-		DRM_ERROR("radeon: dma failed to lock ring %d (%d).\n", ring->idx, r);
-		return r;
-	}
-	radeon_ring_write(ring, SDMA_PACKET(SDMA_OPCODE_WRITE, SDMA_WRITE_SUB_OPCODE_LINEAR, 0));
-	radeon_ring_write(ring, rdev->vram_scratch.gpu_addr & 0xfffffffc);
-	radeon_ring_write(ring, upper_32_bits(rdev->vram_scratch.gpu_addr) & 0xffffffff);
-	radeon_ring_write(ring, 1); /* number of DWs to follow */
-	radeon_ring_write(ring, 0xDEADBEEF);
-	radeon_ring_unlock_commit(rdev, ring);
-
-	for (i = 0; i < rdev->usec_timeout; i++) {
-		tmp = readl(ptr);
-		if (tmp == 0xDEADBEEF)
-			break;
-		DRM_UDELAY(1);
-	}
-
-	if (i < rdev->usec_timeout) {
-		DRM_INFO("ring test on %d succeeded in %d usecs\n", ring->idx, i);
-	} else {
-		DRM_ERROR("radeon: ring %d test failed (0x%08X)\n",
-			  ring->idx, tmp);
-		r = -EINVAL;
-	}
-	return r;
-}
-
-/**
- * cik_sdma_ib_test - test an IB on the DMA engine
- *
- * @rdev: radeon_device pointer
- * @ring: radeon_ring structure holding ring information
- *
- * Test a simple IB in the DMA ring (CIK).
- * Returns 0 on success, error on failure.
- */
-int cik_sdma_ib_test(struct radeon_device *rdev, struct radeon_ring *ring)
-{
-	struct radeon_ib ib;
-	unsigned i;
-	int r;
-	void __iomem *ptr = (void *)rdev->vram_scratch.ptr;
-	u32 tmp = 0;
-
-	if (!ptr) {
-		DRM_ERROR("invalid vram scratch pointer\n");
-		return -EINVAL;
-	}
-
-	tmp = 0xCAFEDEAD;
-	writel(tmp, ptr);
-
-	r = radeon_ib_get(rdev, ring->idx, &ib, NULL, 256);
-	if (r) {
-		DRM_ERROR("radeon: failed to get ib (%d).\n", r);
-		return r;
-	}
-
-	ib.ptr[0] = SDMA_PACKET(SDMA_OPCODE_WRITE, SDMA_WRITE_SUB_OPCODE_LINEAR, 0);
-	ib.ptr[1] = rdev->vram_scratch.gpu_addr & 0xfffffffc;
-	ib.ptr[2] = upper_32_bits(rdev->vram_scratch.gpu_addr) & 0xffffffff;
-	ib.ptr[3] = 1;
-	ib.ptr[4] = 0xDEADBEEF;
-	ib.length_dw = 5;
-
-	r = radeon_ib_schedule(rdev, &ib, NULL);
-	if (r) {
-		radeon_ib_free(rdev, &ib);
-		DRM_ERROR("radeon: failed to schedule ib (%d).\n", r);
-		return r;
-	}
-	r = radeon_fence_wait(ib.fence, false);
-	if (r) {
-		DRM_ERROR("radeon: fence wait failed (%d).\n", r);
-		return r;
-	}
-	for (i = 0; i < rdev->usec_timeout; i++) {
-		tmp = readl(ptr);
-		if (tmp == 0xDEADBEEF)
-			break;
-		DRM_UDELAY(1);
-	}
-	if (i < rdev->usec_timeout) {
-		DRM_INFO("ib test on ring %d succeeded in %u usecs\n", ib.fence->ring, i);
-	} else {
-		DRM_ERROR("radeon: ib test failed (0x%08X)\n", tmp);
-		r = -EINVAL;
-	}
-	radeon_ib_free(rdev, &ib);
-	return r;
-}
-
-
 static void cik_print_gpu_status_regs(struct radeon_device *rdev)
 {
 	dev_info(rdev->dev, "  GRBM_STATUS=0x%08X\n",
@@ -3793,7 +4090,7 @@ static void cik_print_gpu_status_regs(struct radeon_device *rdev)
  * mask to be used by cik_gpu_soft_reset().
  * Returns a mask of the blocks to be reset.
  */
-static u32 cik_gpu_check_soft_reset(struct radeon_device *rdev)
+u32 cik_gpu_check_soft_reset(struct radeon_device *rdev)
 {
 	u32 reset_mask = 0;
 	u32 tmp;
@@ -3890,6 +4187,10 @@ static void cik_gpu_soft_reset(struct radeon_device *rdev, u32 reset_mask)
 	dev_info(rdev->dev, "  VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x%08X\n",
 		 RREG32(VM_CONTEXT1_PROTECTION_FAULT_STATUS));
 
+	/* disable CG/PG */
+	cik_fini_pg(rdev);
+	cik_fini_cg(rdev);
+
 	/* stop the rlc */
 	cik_rlc_stop(rdev);
 
@@ -4044,34 +4345,6 @@ bool cik_gfx_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
 	return radeon_ring_test_lockup(rdev, ring);
 }
 
-/**
- * cik_sdma_is_lockup - Check if the DMA engine is locked up
- *
- * @rdev: radeon_device pointer
- * @ring: radeon_ring structure holding ring information
- *
- * Check if the async DMA engine is locked up (CIK).
- * Returns true if the engine appears to be locked up, false if not.
- */
-bool cik_sdma_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
-{
-	u32 reset_mask = cik_gpu_check_soft_reset(rdev);
-	u32 mask;
-
-	if (ring->idx == R600_RING_TYPE_DMA_INDEX)
-		mask = RADEON_RESET_DMA;
-	else
-		mask = RADEON_RESET_DMA1;
-
-	if (!(reset_mask & mask)) {
-		radeon_ring_lockup_update(ring);
-		return false;
-	}
-	/* force ring activities */
-	radeon_ring_force_activity(rdev, ring);
-	return radeon_ring_test_lockup(rdev, ring);
-}
-
 /* MC */
 /**
  * cik_mc_program - program the GPU memory controller
@@ -4187,8 +4460,8 @@ static int cik_mc_init(struct radeon_device *rdev)
 	rdev->mc.aper_base = pci_resource_start(rdev->pdev, 0);
 	rdev->mc.aper_size = pci_resource_len(rdev->pdev, 0);
 	/* size in MB on si */
-	rdev->mc.mc_vram_size = RREG32(CONFIG_MEMSIZE) * 1024 * 1024;
-	rdev->mc.real_vram_size = RREG32(CONFIG_MEMSIZE) * 1024 * 1024;
+	rdev->mc.mc_vram_size = RREG32(CONFIG_MEMSIZE) * 1024ULL * 1024ULL;
+	rdev->mc.real_vram_size = RREG32(CONFIG_MEMSIZE) * 1024ULL * 1024ULL;
 	rdev->mc.visible_vram_size = rdev->mc.aper_size;
 	si_vram_gtt_location(rdev, &rdev->mc);
 	radeon_update_bandwidth_info(rdev);
@@ -4466,12 +4739,13 @@ static void cik_vm_decode_fault(struct radeon_device *rdev,
 	u32 mc_id = (status & MEMORY_CLIENT_ID_MASK) >> MEMORY_CLIENT_ID_SHIFT;
 	u32 vmid = (status & FAULT_VMID_MASK) >> FAULT_VMID_SHIFT;
 	u32 protections = (status & PROTECTIONS_MASK) >> PROTECTIONS_SHIFT;
-	char *block = (char *)&mc_client;
+	char block[5] = { mc_client >> 24, (mc_client >> 16) & 0xff,
+		(mc_client >> 8) & 0xff, mc_client & 0xff, 0 };
 
-	printk("VM fault (0x%02x, vmid %d) at page %u, %s from %s (%d)\n",
+	printk("VM fault (0x%02x, vmid %d) at page %u, %s from '%s' (0x%08x) (%d)\n",
 	       protections, vmid, addr,
 	       (status & MEMORY_CLIENT_RW_MASK) ? "write" : "read",
-	       block, mc_id);
+	       block, mc_client, mc_id);
 }
 
 /**
@@ -4608,164 +4882,44 @@ void cik_vm_set_page(struct radeon_device *rdev,
 		}
 	} else {
 		/* DMA */
-		if (flags & RADEON_VM_PAGE_SYSTEM) {
-			while (count) {
-				ndw = count * 2;
-				if (ndw > 0xFFFFE)
-					ndw = 0xFFFFE;
-
-				/* for non-physically contiguous pages (system) */
-				ib->ptr[ib->length_dw++] = SDMA_PACKET(SDMA_OPCODE_WRITE, SDMA_WRITE_SUB_OPCODE_LINEAR, 0);
-				ib->ptr[ib->length_dw++] = pe;
-				ib->ptr[ib->length_dw++] = upper_32_bits(pe);
-				ib->ptr[ib->length_dw++] = ndw;
-				for (; ndw > 0; ndw -= 2, --count, pe += 8) {
-					if (flags & RADEON_VM_PAGE_SYSTEM) {
-						value = radeon_vm_map_gart(rdev, addr);
-						value &= 0xFFFFFFFFFFFFF000ULL;
-					} else if (flags & RADEON_VM_PAGE_VALID) {
-						value = addr;
-					} else {
-						value = 0;
-					}
-					addr += incr;
-					value |= r600_flags;
-					ib->ptr[ib->length_dw++] = value;
-					ib->ptr[ib->length_dw++] = upper_32_bits(value);
-				}
-			}
-		} else {
-			while (count) {
-				ndw = count;
-				if (ndw > 0x7FFFF)
-					ndw = 0x7FFFF;
-
-				if (flags & RADEON_VM_PAGE_VALID)
-					value = addr;
-				else
-					value = 0;
-				/* for physically contiguous pages (vram) */
-				ib->ptr[ib->length_dw++] = SDMA_PACKET(SDMA_OPCODE_GENERATE_PTE_PDE, 0, 0);
-				ib->ptr[ib->length_dw++] = pe; /* dst addr */
-				ib->ptr[ib->length_dw++] = upper_32_bits(pe);
-				ib->ptr[ib->length_dw++] = r600_flags; /* mask */
-				ib->ptr[ib->length_dw++] = 0;
-				ib->ptr[ib->length_dw++] = value; /* value */
-				ib->ptr[ib->length_dw++] = upper_32_bits(value);
-				ib->ptr[ib->length_dw++] = incr; /* increment size */
-				ib->ptr[ib->length_dw++] = 0;
-				ib->ptr[ib->length_dw++] = ndw; /* number of entries */
-				pe += ndw * 8;
-				addr += ndw * incr;
-				count -= ndw;
-			}
-		}
-		while (ib->length_dw & 0x7)
-			ib->ptr[ib->length_dw++] = SDMA_PACKET(SDMA_OPCODE_NOP, 0, 0);
+		cik_sdma_vm_set_page(rdev, ib, pe, addr, count, incr, flags);
 	}
 }
 
-/**
- * cik_dma_vm_flush - cik vm flush using sDMA
- *
- * @rdev: radeon_device pointer
- *
- * Update the page table base and flush the VM TLB
- * using sDMA (CIK).
- */
-void cik_dma_vm_flush(struct radeon_device *rdev, int ridx, struct radeon_vm *vm)
-{
-	struct radeon_ring *ring = &rdev->ring[ridx];
-	u32 extra_bits = (SDMA_POLL_REG_MEM_EXTRA_OP(1) |
-			  SDMA_POLL_REG_MEM_EXTRA_FUNC(3)); /* == */
-	u32 ref_and_mask;
-
-	if (vm == NULL)
-		return;
-
-	if (ridx == R600_RING_TYPE_DMA_INDEX)
-		ref_and_mask = SDMA0;
-	else
-		ref_and_mask = SDMA1;
-
-	radeon_ring_write(ring, SDMA_PACKET(SDMA_OPCODE_SRBM_WRITE, 0, 0xf000));
-	if (vm->id < 8) {
-		radeon_ring_write(ring, (VM_CONTEXT0_PAGE_TABLE_BASE_ADDR + (vm->id << 2)) >> 2);
-	} else {
-		radeon_ring_write(ring, (VM_CONTEXT8_PAGE_TABLE_BASE_ADDR + ((vm->id - 8) << 2)) >> 2);
-	}
-	radeon_ring_write(ring, vm->pd_gpu_addr >> 12);
-
-	/* update SH_MEM_* regs */
-	radeon_ring_write(ring, SDMA_PACKET(SDMA_OPCODE_SRBM_WRITE, 0, 0xf000));
-	radeon_ring_write(ring, SRBM_GFX_CNTL >> 2);
-	radeon_ring_write(ring, VMID(vm->id));
-
-	radeon_ring_write(ring, SDMA_PACKET(SDMA_OPCODE_SRBM_WRITE, 0, 0xf000));
-	radeon_ring_write(ring, SH_MEM_BASES >> 2);
-	radeon_ring_write(ring, 0);
-
-	radeon_ring_write(ring, SDMA_PACKET(SDMA_OPCODE_SRBM_WRITE, 0, 0xf000));
-	radeon_ring_write(ring, SH_MEM_CONFIG >> 2);
-	radeon_ring_write(ring, 0);
-
-	radeon_ring_write(ring, SDMA_PACKET(SDMA_OPCODE_SRBM_WRITE, 0, 0xf000));
-	radeon_ring_write(ring, SH_MEM_APE1_BASE >> 2);
-	radeon_ring_write(ring, 1);
-
-	radeon_ring_write(ring, SDMA_PACKET(SDMA_OPCODE_SRBM_WRITE, 0, 0xf000));
-	radeon_ring_write(ring, SH_MEM_APE1_LIMIT >> 2);
-	radeon_ring_write(ring, 0);
-
-	radeon_ring_write(ring, SDMA_PACKET(SDMA_OPCODE_SRBM_WRITE, 0, 0xf000));
-	radeon_ring_write(ring, SRBM_GFX_CNTL >> 2);
-	radeon_ring_write(ring, VMID(0));
-
-	/* flush HDP */
-	radeon_ring_write(ring, SDMA_PACKET(SDMA_OPCODE_POLL_REG_MEM, 0, extra_bits));
-	radeon_ring_write(ring, GPU_HDP_FLUSH_DONE);
-	radeon_ring_write(ring, GPU_HDP_FLUSH_REQ);
-	radeon_ring_write(ring, ref_and_mask); /* REFERENCE */
-	radeon_ring_write(ring, ref_and_mask); /* MASK */
-	radeon_ring_write(ring, (4 << 16) | 10); /* RETRY_COUNT, POLL_INTERVAL */
-
-	/* flush TLB */
-	radeon_ring_write(ring, SDMA_PACKET(SDMA_OPCODE_SRBM_WRITE, 0, 0xf000));
-	radeon_ring_write(ring, VM_INVALIDATE_REQUEST >> 2);
-	radeon_ring_write(ring, 1 << vm->id);
-}
-
 /*
  * RLC
  * The RLC is a multi-purpose microengine that handles a
  * variety of functions, the most important of which is
  * the interrupt controller.
  */
-/**
- * cik_rlc_stop - stop the RLC ME
- *
- * @rdev: radeon_device pointer
- *
- * Halt the RLC ME (MicroEngine) (CIK).
- */
-static void cik_rlc_stop(struct radeon_device *rdev)
+static void cik_enable_gui_idle_interrupt(struct radeon_device *rdev,
+					  bool enable)
 {
-	int i, j, k;
-	u32 mask, tmp;
+	u32 tmp = RREG32(CP_INT_CNTL_RING0);
 
-	tmp = RREG32(CP_INT_CNTL_RING0);
-	tmp &= ~(CNTX_BUSY_INT_ENABLE | CNTX_EMPTY_INT_ENABLE);
+	if (enable)
+		tmp |= (CNTX_BUSY_INT_ENABLE | CNTX_EMPTY_INT_ENABLE);
+	else
+		tmp &= ~(CNTX_BUSY_INT_ENABLE | CNTX_EMPTY_INT_ENABLE);
 	WREG32(CP_INT_CNTL_RING0, tmp);
+}
 
-	RREG32(CB_CGTT_SCLK_CTRL);
-	RREG32(CB_CGTT_SCLK_CTRL);
-	RREG32(CB_CGTT_SCLK_CTRL);
-	RREG32(CB_CGTT_SCLK_CTRL);
+static void cik_enable_lbpw(struct radeon_device *rdev, bool enable)
+{
+	u32 tmp;
 
-	tmp = RREG32(RLC_CGCG_CGLS_CTRL) & 0xfffffffc;
-	WREG32(RLC_CGCG_CGLS_CTRL, tmp);
+	tmp = RREG32(RLC_LB_CNTL);
+	if (enable)
+		tmp |= LOAD_BALANCE_ENABLE;
+	else
+		tmp &= ~LOAD_BALANCE_ENABLE;
+	WREG32(RLC_LB_CNTL, tmp);
+}
 
-	WREG32(RLC_CNTL, 0);
+static void cik_wait_for_rlc_serdes(struct radeon_device *rdev)
+{
+	u32 i, j, k;
+	u32 mask;
 
 	for (i = 0; i < rdev->config.cik.max_shader_engines; i++) {
 		for (j = 0; j < rdev->config.cik.max_sh_per_se; j++) {
@@ -4787,6 +4941,84 @@ static void cik_rlc_stop(struct radeon_device *rdev)
 	}
 }
 
+static void cik_update_rlc(struct radeon_device *rdev, u32 rlc)
+{
+	u32 tmp;
+
+	tmp = RREG32(RLC_CNTL);
+	if (tmp != rlc)
+		WREG32(RLC_CNTL, rlc);
+}
+
+static u32 cik_halt_rlc(struct radeon_device *rdev)
+{
+	u32 data, orig;
+
+	orig = data = RREG32(RLC_CNTL);
+
+	if (data & RLC_ENABLE) {
+		u32 i;
+
+		data &= ~RLC_ENABLE;
+		WREG32(RLC_CNTL, data);
+
+		for (i = 0; i < rdev->usec_timeout; i++) {
+			if ((RREG32(RLC_GPM_STAT) & RLC_GPM_BUSY) == 0)
+				break;
+			udelay(1);
+		}
+
+		cik_wait_for_rlc_serdes(rdev);
+	}
+
+	return orig;
+}
+
+void cik_enter_rlc_safe_mode(struct radeon_device *rdev)
+{
+	u32 tmp, i, mask;
+
+	tmp = REQ | MESSAGE(MSG_ENTER_RLC_SAFE_MODE);
+	WREG32(RLC_GPR_REG2, tmp);
+
+	mask = GFX_POWER_STATUS | GFX_CLOCK_STATUS;
+	for (i = 0; i < rdev->usec_timeout; i++) {
+		if ((RREG32(RLC_GPM_STAT) & mask) == mask)
+			break;
+		udelay(1);
+	}
+
+	for (i = 0; i < rdev->usec_timeout; i++) {
+		if ((RREG32(RLC_GPR_REG2) & REQ) == 0)
+			break;
+		udelay(1);
+	}
+}
+
+void cik_exit_rlc_safe_mode(struct radeon_device *rdev)
+{
+	u32 tmp;
+
+	tmp = REQ | MESSAGE(MSG_EXIT_RLC_SAFE_MODE);
+	WREG32(RLC_GPR_REG2, tmp);
+}
+
+/**
+ * cik_rlc_stop - stop the RLC ME
+ *
+ * @rdev: radeon_device pointer
+ *
+ * Halt the RLC ME (MicroEngine) (CIK).
+ */
+static void cik_rlc_stop(struct radeon_device *rdev)
+{
+	WREG32(RLC_CNTL, 0);
+
+	cik_enable_gui_idle_interrupt(rdev, false);
+
+	cik_wait_for_rlc_serdes(rdev);
+}
+
 /**
  * cik_rlc_start - start the RLC ME
  *
@@ -4796,13 +5028,9 @@ static void cik_rlc_stop(struct radeon_device *rdev)
  */
 static void cik_rlc_start(struct radeon_device *rdev)
 {
-	u32 tmp;
-
 	WREG32(RLC_CNTL, RLC_ENABLE);
 
-	tmp = RREG32(CP_INT_CNTL_RING0);
-	tmp |= (CNTX_BUSY_INT_ENABLE | CNTX_EMPTY_INT_ENABLE);
-	WREG32(CP_INT_CNTL_RING0, tmp);
+	cik_enable_gui_idle_interrupt(rdev, true);
 
 	udelay(50);
 }
@@ -4818,8 +5046,7 @@ static void cik_rlc_start(struct radeon_device *rdev)
  */
 static int cik_rlc_resume(struct radeon_device *rdev)
 {
-	u32 i, size;
-	u32 clear_state_info[3];
+	u32 i, size, tmp;
 	const __be32 *fw_data;
 
 	if (!rdev->rlc_fw)
@@ -4840,12 +5067,15 @@ static int cik_rlc_resume(struct radeon_device *rdev)
 
 	cik_rlc_stop(rdev);
 
-	WREG32(GRBM_SOFT_RESET, SOFT_RESET_RLC);
-	RREG32(GRBM_SOFT_RESET);
-	udelay(50);
-	WREG32(GRBM_SOFT_RESET, 0);
-	RREG32(GRBM_SOFT_RESET);
-	udelay(50);
+	/* disable CG */
+	tmp = RREG32(RLC_CGCG_CGLS_CTRL) & 0xfffffffc;
+	WREG32(RLC_CGCG_CGLS_CTRL, tmp);
+
+	si_rlc_reset(rdev);
+
+	cik_init_pg(rdev);
+
+	cik_init_cg(rdev);
 
 	WREG32(RLC_LB_CNTR_INIT, 0);
 	WREG32(RLC_LB_CNTR_MAX, 0x00008000);
@@ -4864,20 +5094,760 @@ static int cik_rlc_resume(struct radeon_device *rdev)
 		WREG32(RLC_GPM_UCODE_DATA, be32_to_cpup(fw_data++));
 	WREG32(RLC_GPM_UCODE_ADDR, 0);
 
-	/* XXX */
-	clear_state_info[0] = 0;//upper_32_bits(rdev->rlc.save_restore_gpu_addr);
-	clear_state_info[1] = 0;//rdev->rlc.save_restore_gpu_addr;
-	clear_state_info[2] = 0;//cik_default_size;
-	WREG32(RLC_GPM_SCRATCH_ADDR, 0x3d);
-	for (i = 0; i < 3; i++)
-		WREG32(RLC_GPM_SCRATCH_DATA, clear_state_info[i]);
-	WREG32(RLC_DRIVER_DMA_STATUS, 0);
+	/* XXX - find out what chips support lbpw */
+	cik_enable_lbpw(rdev, false);
+
+	if (rdev->family == CHIP_BONAIRE)
+		WREG32(RLC_DRIVER_DMA_STATUS, 0);
 
 	cik_rlc_start(rdev);
 
 	return 0;
 }
 
+static void cik_enable_cgcg(struct radeon_device *rdev, bool enable)
+{
+	u32 data, orig, tmp, tmp2;
+
+	orig = data = RREG32(RLC_CGCG_CGLS_CTRL);
+
+	if (enable && (rdev->cg_flags & RADEON_CG_SUPPORT_GFX_CGCG)) {
+		cik_enable_gui_idle_interrupt(rdev, true);
+
+		tmp = cik_halt_rlc(rdev);
+
+		cik_select_se_sh(rdev, 0xffffffff, 0xffffffff);
+		WREG32(RLC_SERDES_WR_CU_MASTER_MASK, 0xffffffff);
+		WREG32(RLC_SERDES_WR_NONCU_MASTER_MASK, 0xffffffff);
+		tmp2 = BPM_ADDR_MASK | CGCG_OVERRIDE_0 | CGLS_ENABLE;
+		WREG32(RLC_SERDES_WR_CTRL, tmp2);
+
+		cik_update_rlc(rdev, tmp);
+
+		data |= CGCG_EN | CGLS_EN;
+	} else {
+		cik_enable_gui_idle_interrupt(rdev, false);
+
+		RREG32(CB_CGTT_SCLK_CTRL);
+		RREG32(CB_CGTT_SCLK_CTRL);
+		RREG32(CB_CGTT_SCLK_CTRL);
+		RREG32(CB_CGTT_SCLK_CTRL);
+
+		data &= ~(CGCG_EN | CGLS_EN);
+	}
+
+	if (orig != data)
+		WREG32(RLC_CGCG_CGLS_CTRL, data);
+
+}
+
+static void cik_enable_mgcg(struct radeon_device *rdev, bool enable)
+{
+	u32 data, orig, tmp = 0;
+
+	if (enable && (rdev->cg_flags & RADEON_CG_SUPPORT_GFX_MGCG)) {
+		if (rdev->cg_flags & RADEON_CG_SUPPORT_GFX_MGLS) {
+			if (rdev->cg_flags & RADEON_CG_SUPPORT_GFX_CP_LS) {
+				orig = data = RREG32(CP_MEM_SLP_CNTL);
+				data |= CP_MEM_LS_EN;
+				if (orig != data)
+					WREG32(CP_MEM_SLP_CNTL, data);
+			}
+		}
+
+		orig = data = RREG32(RLC_CGTT_MGCG_OVERRIDE);
+		data &= 0xfffffffd;
+		if (orig != data)
+			WREG32(RLC_CGTT_MGCG_OVERRIDE, data);
+
+		tmp = cik_halt_rlc(rdev);
+
+		cik_select_se_sh(rdev, 0xffffffff, 0xffffffff);
+		WREG32(RLC_SERDES_WR_CU_MASTER_MASK, 0xffffffff);
+		WREG32(RLC_SERDES_WR_NONCU_MASTER_MASK, 0xffffffff);
+		data = BPM_ADDR_MASK | MGCG_OVERRIDE_0;
+		WREG32(RLC_SERDES_WR_CTRL, data);
+
+		cik_update_rlc(rdev, tmp);
+
+		if (rdev->cg_flags & RADEON_CG_SUPPORT_GFX_CGTS) {
+			orig = data = RREG32(CGTS_SM_CTRL_REG);
+			data &= ~SM_MODE_MASK;
+			data |= SM_MODE(0x2);
+			data |= SM_MODE_ENABLE;
+			data &= ~CGTS_OVERRIDE;
+			if ((rdev->cg_flags & RADEON_CG_SUPPORT_GFX_MGLS) &&
+			    (rdev->cg_flags & RADEON_CG_SUPPORT_GFX_CGTS_LS))
+				data &= ~CGTS_LS_OVERRIDE;
+			data &= ~ON_MONITOR_ADD_MASK;
+			data |= ON_MONITOR_ADD_EN;
+			data |= ON_MONITOR_ADD(0x96);
+			if (orig != data)
+				WREG32(CGTS_SM_CTRL_REG, data);
+		}
+	} else {
+		orig = data = RREG32(RLC_CGTT_MGCG_OVERRIDE);
+		data |= 0x00000002;
+		if (orig != data)
+			WREG32(RLC_CGTT_MGCG_OVERRIDE, data);
+
+		data = RREG32(RLC_MEM_SLP_CNTL);
+		if (data & RLC_MEM_LS_EN) {
+			data &= ~RLC_MEM_LS_EN;
+			WREG32(RLC_MEM_SLP_CNTL, data);
+		}
+
+		data = RREG32(CP_MEM_SLP_CNTL);
+		if (data & CP_MEM_LS_EN) {
+			data &= ~CP_MEM_LS_EN;
+			WREG32(CP_MEM_SLP_CNTL, data);
+		}
+
+		orig = data = RREG32(CGTS_SM_CTRL_REG);
+		data |= CGTS_OVERRIDE | CGTS_LS_OVERRIDE;
+		if (orig != data)
+			WREG32(CGTS_SM_CTRL_REG, data);
+
+		tmp = cik_halt_rlc(rdev);
+
+		cik_select_se_sh(rdev, 0xffffffff, 0xffffffff);
+		WREG32(RLC_SERDES_WR_CU_MASTER_MASK, 0xffffffff);
+		WREG32(RLC_SERDES_WR_NONCU_MASTER_MASK, 0xffffffff);
+		data = BPM_ADDR_MASK | MGCG_OVERRIDE_1;
+		WREG32(RLC_SERDES_WR_CTRL, data);
+
+		cik_update_rlc(rdev, tmp);
+	}
+}
+
+static const u32 mc_cg_registers[] =
+{
+	MC_HUB_MISC_HUB_CG,
+	MC_HUB_MISC_SIP_CG,
+	MC_HUB_MISC_VM_CG,
+	MC_XPB_CLK_GAT,
+	ATC_MISC_CG,
+	MC_CITF_MISC_WR_CG,
+	MC_CITF_MISC_RD_CG,
+	MC_CITF_MISC_VM_CG,
+	VM_L2_CG,
+};
+
+static void cik_enable_mc_ls(struct radeon_device *rdev,
+			     bool enable)
+{
+	int i;
+	u32 orig, data;
+
+	for (i = 0; i < ARRAY_SIZE(mc_cg_registers); i++) {
+		orig = data = RREG32(mc_cg_registers[i]);
+		if (enable && (rdev->cg_flags & RADEON_CG_SUPPORT_MC_LS))
+			data |= MC_LS_ENABLE;
+		else
+			data &= ~MC_LS_ENABLE;
+		if (data != orig)
+			WREG32(mc_cg_registers[i], data);
+	}
+}
+
+static void cik_enable_mc_mgcg(struct radeon_device *rdev,
+			       bool enable)
+{
+	int i;
+	u32 orig, data;
+
+	for (i = 0; i < ARRAY_SIZE(mc_cg_registers); i++) {
+		orig = data = RREG32(mc_cg_registers[i]);
+		if (enable && (rdev->cg_flags & RADEON_CG_SUPPORT_MC_MGCG))
+			data |= MC_CG_ENABLE;
+		else
+			data &= ~MC_CG_ENABLE;
+		if (data != orig)
+			WREG32(mc_cg_registers[i], data);
+	}
+}
+
+static void cik_enable_sdma_mgcg(struct radeon_device *rdev,
+				 bool enable)
+{
+	u32 orig, data;
+
+	if (enable && (rdev->cg_flags & RADEON_CG_SUPPORT_SDMA_MGCG)) {
+		WREG32(SDMA0_CLK_CTRL + SDMA0_REGISTER_OFFSET, 0x00000100);
+		WREG32(SDMA0_CLK_CTRL + SDMA1_REGISTER_OFFSET, 0x00000100);
+	} else {
+		orig = data = RREG32(SDMA0_CLK_CTRL + SDMA0_REGISTER_OFFSET);
+		data |= 0xff000000;
+		if (data != orig)
+			WREG32(SDMA0_CLK_CTRL + SDMA0_REGISTER_OFFSET, data);
+
+		orig = data = RREG32(SDMA0_CLK_CTRL + SDMA1_REGISTER_OFFSET);
+		data |= 0xff000000;
+		if (data != orig)
+			WREG32(SDMA0_CLK_CTRL + SDMA1_REGISTER_OFFSET, data);
+	}
+}
+
+static void cik_enable_sdma_mgls(struct radeon_device *rdev,
+				 bool enable)
+{
+	u32 orig, data;
+
+	if (enable && (rdev->cg_flags & RADEON_CG_SUPPORT_SDMA_LS)) {
+		orig = data = RREG32(SDMA0_POWER_CNTL + SDMA0_REGISTER_OFFSET);
+		data |= 0x100;
+		if (orig != data)
+			WREG32(SDMA0_POWER_CNTL + SDMA0_REGISTER_OFFSET, data);
+
+		orig = data = RREG32(SDMA0_POWER_CNTL + SDMA1_REGISTER_OFFSET);
+		data |= 0x100;
+		if (orig != data)
+			WREG32(SDMA0_POWER_CNTL + SDMA1_REGISTER_OFFSET, data);
+	} else {
+		orig = data = RREG32(SDMA0_POWER_CNTL + SDMA0_REGISTER_OFFSET);
+		data &= ~0x100;
+		if (orig != data)
+			WREG32(SDMA0_POWER_CNTL + SDMA0_REGISTER_OFFSET, data);
+
+		orig = data = RREG32(SDMA0_POWER_CNTL + SDMA1_REGISTER_OFFSET);
+		data &= ~0x100;
+		if (orig != data)
+			WREG32(SDMA0_POWER_CNTL + SDMA1_REGISTER_OFFSET, data);
+	}
+}
+
+static void cik_enable_uvd_mgcg(struct radeon_device *rdev,
+				bool enable)
+{
+	u32 orig, data;
+
+	if (enable && (rdev->cg_flags & RADEON_CG_SUPPORT_UVD_MGCG)) {
+		data = RREG32_UVD_CTX(UVD_CGC_MEM_CTRL);
+		data = 0xfff;
+		WREG32_UVD_CTX(UVD_CGC_MEM_CTRL, data);
+
+		orig = data = RREG32(UVD_CGC_CTRL);
+		data |= DCM;
+		if (orig != data)
+			WREG32(UVD_CGC_CTRL, data);
+	} else {
+		data = RREG32_UVD_CTX(UVD_CGC_MEM_CTRL);
+		data &= ~0xfff;
+		WREG32_UVD_CTX(UVD_CGC_MEM_CTRL, data);
+
+		orig = data = RREG32(UVD_CGC_CTRL);
+		data &= ~DCM;
+		if (orig != data)
+			WREG32(UVD_CGC_CTRL, data);
+	}
+}
+
+static void cik_enable_bif_mgls(struct radeon_device *rdev,
+			       bool enable)
+{
+	u32 orig, data;
+
+	orig = data = RREG32_PCIE_PORT(PCIE_CNTL2);
+
+	if (enable && (rdev->cg_flags & RADEON_CG_SUPPORT_BIF_LS))
+		data |= SLV_MEM_LS_EN | MST_MEM_LS_EN |
+			REPLAY_MEM_LS_EN | SLV_MEM_AGGRESSIVE_LS_EN;
+	else
+		data &= ~(SLV_MEM_LS_EN | MST_MEM_LS_EN |
+			  REPLAY_MEM_LS_EN | SLV_MEM_AGGRESSIVE_LS_EN);
+
+	if (orig != data)
+		WREG32_PCIE_PORT(PCIE_CNTL2, data);
+}
+
+static void cik_enable_hdp_mgcg(struct radeon_device *rdev,
+				bool enable)
+{
+	u32 orig, data;
+
+	orig = data = RREG32(HDP_HOST_PATH_CNTL);
+
+	if (enable && (rdev->cg_flags & RADEON_CG_SUPPORT_HDP_MGCG))
+		data &= ~CLOCK_GATING_DIS;
+	else
+		data |= CLOCK_GATING_DIS;
+
+	if (orig != data)
+		WREG32(HDP_HOST_PATH_CNTL, data);
+}
+
+static void cik_enable_hdp_ls(struct radeon_device *rdev,
+			      bool enable)
+{
+	u32 orig, data;
+
+	orig = data = RREG32(HDP_MEM_POWER_LS);
+
+	if (enable && (rdev->cg_flags & RADEON_CG_SUPPORT_HDP_LS))
+		data |= HDP_LS_ENABLE;
+	else
+		data &= ~HDP_LS_ENABLE;
+
+	if (orig != data)
+		WREG32(HDP_MEM_POWER_LS, data);
+}
+
+void cik_update_cg(struct radeon_device *rdev,
+		   u32 block, bool enable)
+{
+
+	if (block & RADEON_CG_BLOCK_GFX) {
+		cik_enable_gui_idle_interrupt(rdev, false);
+		/* order matters! */
+		if (enable) {
+			cik_enable_mgcg(rdev, true);
+			cik_enable_cgcg(rdev, true);
+		} else {
+			cik_enable_cgcg(rdev, false);
+			cik_enable_mgcg(rdev, false);
+		}
+		cik_enable_gui_idle_interrupt(rdev, true);
+	}
+
+	if (block & RADEON_CG_BLOCK_MC) {
+		if (!(rdev->flags & RADEON_IS_IGP)) {
+			cik_enable_mc_mgcg(rdev, enable);
+			cik_enable_mc_ls(rdev, enable);
+		}
+	}
+
+	if (block & RADEON_CG_BLOCK_SDMA) {
+		cik_enable_sdma_mgcg(rdev, enable);
+		cik_enable_sdma_mgls(rdev, enable);
+	}
+
+	if (block & RADEON_CG_BLOCK_BIF) {
+		cik_enable_bif_mgls(rdev, enable);
+	}
+
+	if (block & RADEON_CG_BLOCK_UVD) {
+		if (rdev->has_uvd)
+			cik_enable_uvd_mgcg(rdev, enable);
+	}
+
+	if (block & RADEON_CG_BLOCK_HDP) {
+		cik_enable_hdp_mgcg(rdev, enable);
+		cik_enable_hdp_ls(rdev, enable);
+	}
+}
+
+static void cik_init_cg(struct radeon_device *rdev)
+{
+
+	cik_update_cg(rdev, RADEON_CG_BLOCK_GFX, true);
+
+	if (rdev->has_uvd)
+		si_init_uvd_internal_cg(rdev);
+
+	cik_update_cg(rdev, (RADEON_CG_BLOCK_MC |
+			     RADEON_CG_BLOCK_SDMA |
+			     RADEON_CG_BLOCK_BIF |
+			     RADEON_CG_BLOCK_UVD |
+			     RADEON_CG_BLOCK_HDP), true);
+}
+
+static void cik_fini_cg(struct radeon_device *rdev)
+{
+	cik_update_cg(rdev, (RADEON_CG_BLOCK_MC |
+			     RADEON_CG_BLOCK_SDMA |
+			     RADEON_CG_BLOCK_BIF |
+			     RADEON_CG_BLOCK_UVD |
+			     RADEON_CG_BLOCK_HDP), false);
+
+	cik_update_cg(rdev, RADEON_CG_BLOCK_GFX, false);
+}
+
+static void cik_enable_sck_slowdown_on_pu(struct radeon_device *rdev,
+					  bool enable)
+{
+	u32 data, orig;
+
+	orig = data = RREG32(RLC_PG_CNTL);
+	if (enable && (rdev->pg_flags & RADEON_PG_SUPPORT_RLC_SMU_HS))
+		data |= SMU_CLK_SLOWDOWN_ON_PU_ENABLE;
+	else
+		data &= ~SMU_CLK_SLOWDOWN_ON_PU_ENABLE;
+	if (orig != data)
+		WREG32(RLC_PG_CNTL, data);
+}
+
+static void cik_enable_sck_slowdown_on_pd(struct radeon_device *rdev,
+					  bool enable)
+{
+	u32 data, orig;
+
+	orig = data = RREG32(RLC_PG_CNTL);
+	if (enable && (rdev->pg_flags & RADEON_PG_SUPPORT_RLC_SMU_HS))
+		data |= SMU_CLK_SLOWDOWN_ON_PD_ENABLE;
+	else
+		data &= ~SMU_CLK_SLOWDOWN_ON_PD_ENABLE;
+	if (orig != data)
+		WREG32(RLC_PG_CNTL, data);
+}
+
+static void cik_enable_cp_pg(struct radeon_device *rdev, bool enable)
+{
+	u32 data, orig;
+
+	orig = data = RREG32(RLC_PG_CNTL);
+	if (enable && (rdev->pg_flags & RADEON_PG_SUPPORT_CP))
+		data &= ~DISABLE_CP_PG;
+	else
+		data |= DISABLE_CP_PG;
+	if (orig != data)
+		WREG32(RLC_PG_CNTL, data);
+}
+
+static void cik_enable_gds_pg(struct radeon_device *rdev, bool enable)
+{
+	u32 data, orig;
+
+	orig = data = RREG32(RLC_PG_CNTL);
+	if (enable && (rdev->pg_flags & RADEON_PG_SUPPORT_GDS))
+		data &= ~DISABLE_GDS_PG;
+	else
+		data |= DISABLE_GDS_PG;
+	if (orig != data)
+		WREG32(RLC_PG_CNTL, data);
+}
+
+#define CP_ME_TABLE_SIZE    96
+#define CP_ME_TABLE_OFFSET  2048
+#define CP_MEC_TABLE_OFFSET 4096
+
+void cik_init_cp_pg_table(struct radeon_device *rdev)
+{
+	const __be32 *fw_data;
+	volatile u32 *dst_ptr;
+	int me, i, max_me = 4;
+	u32 bo_offset = 0;
+	u32 table_offset;
+
+	if (rdev->family == CHIP_KAVERI)
+		max_me = 5;
+
+	if (rdev->rlc.cp_table_ptr == NULL)
+		return;
+
+	/* write the cp table buffer */
+	dst_ptr = rdev->rlc.cp_table_ptr;
+	for (me = 0; me < max_me; me++) {
+		if (me == 0) {
+			fw_data = (const __be32 *)rdev->ce_fw->data;
+			table_offset = CP_ME_TABLE_OFFSET;
+		} else if (me == 1) {
+			fw_data = (const __be32 *)rdev->pfp_fw->data;
+			table_offset = CP_ME_TABLE_OFFSET;
+		} else if (me == 2) {
+			fw_data = (const __be32 *)rdev->me_fw->data;
+			table_offset = CP_ME_TABLE_OFFSET;
+		} else {
+			fw_data = (const __be32 *)rdev->mec_fw->data;
+			table_offset = CP_MEC_TABLE_OFFSET;
+		}
+
+		for (i = 0; i < CP_ME_TABLE_SIZE; i ++) {
+			dst_ptr[bo_offset + i] = be32_to_cpu(fw_data[table_offset + i]);
+		}
+		bo_offset += CP_ME_TABLE_SIZE;
+	}
+}
+
+static void cik_enable_gfx_cgpg(struct radeon_device *rdev,
+				bool enable)
+{
+	u32 data, orig;
+
+	if (enable && (rdev->pg_flags & RADEON_PG_SUPPORT_GFX_PG)) {
+		orig = data = RREG32(RLC_PG_CNTL);
+		data |= GFX_PG_ENABLE;
+		if (orig != data)
+			WREG32(RLC_PG_CNTL, data);
+
+		orig = data = RREG32(RLC_AUTO_PG_CTRL);
+		data |= AUTO_PG_EN;
+		if (orig != data)
+			WREG32(RLC_AUTO_PG_CTRL, data);
+	} else {
+		orig = data = RREG32(RLC_PG_CNTL);
+		data &= ~GFX_PG_ENABLE;
+		if (orig != data)
+			WREG32(RLC_PG_CNTL, data);
+
+		orig = data = RREG32(RLC_AUTO_PG_CTRL);
+		data &= ~AUTO_PG_EN;
+		if (orig != data)
+			WREG32(RLC_AUTO_PG_CTRL, data);
+
+		data = RREG32(DB_RENDER_CONTROL);
+	}
+}
+
+static u32 cik_get_cu_active_bitmap(struct radeon_device *rdev, u32 se, u32 sh)
+{
+	u32 mask = 0, tmp, tmp1;
+	int i;
+
+	cik_select_se_sh(rdev, se, sh);
+	tmp = RREG32(CC_GC_SHADER_ARRAY_CONFIG);
+	tmp1 = RREG32(GC_USER_SHADER_ARRAY_CONFIG);
+	cik_select_se_sh(rdev, 0xffffffff, 0xffffffff);
+
+	tmp &= 0xffff0000;
+
+	tmp |= tmp1;
+	tmp >>= 16;
+
+	for (i = 0; i < rdev->config.cik.max_cu_per_sh; i ++) {
+		mask <<= 1;
+		mask |= 1;
+	}
+
+	return (~tmp) & mask;
+}
+
+static void cik_init_ao_cu_mask(struct radeon_device *rdev)
+{
+	u32 i, j, k, active_cu_number = 0;
+	u32 mask, counter, cu_bitmap;
+	u32 tmp = 0;
+
+	for (i = 0; i < rdev->config.cik.max_shader_engines; i++) {
+		for (j = 0; j < rdev->config.cik.max_sh_per_se; j++) {
+			mask = 1;
+			cu_bitmap = 0;
+			counter = 0;
+			for (k = 0; k < rdev->config.cik.max_cu_per_sh; k ++) {
+				if (cik_get_cu_active_bitmap(rdev, i, j) & mask) {
+					if (counter < 2)
+						cu_bitmap |= mask;
+					counter ++;
+				}
+				mask <<= 1;
+			}
+
+			active_cu_number += counter;
+			tmp |= (cu_bitmap << (i * 16 + j * 8));
+		}
+	}
+
+	WREG32(RLC_PG_AO_CU_MASK, tmp);
+
+	tmp = RREG32(RLC_MAX_PG_CU);
+	tmp &= ~MAX_PU_CU_MASK;
+	tmp |= MAX_PU_CU(active_cu_number);
+	WREG32(RLC_MAX_PG_CU, tmp);
+}
+
+static void cik_enable_gfx_static_mgpg(struct radeon_device *rdev,
+				       bool enable)
+{
+	u32 data, orig;
+
+	orig = data = RREG32(RLC_PG_CNTL);
+	if (enable && (rdev->pg_flags & RADEON_PG_SUPPORT_GFX_SMG))
+		data |= STATIC_PER_CU_PG_ENABLE;
+	else
+		data &= ~STATIC_PER_CU_PG_ENABLE;
+	if (orig != data)
+		WREG32(RLC_PG_CNTL, data);
+}
+
+static void cik_enable_gfx_dynamic_mgpg(struct radeon_device *rdev,
+					bool enable)
+{
+	u32 data, orig;
+
+	orig = data = RREG32(RLC_PG_CNTL);
+	if (enable && (rdev->pg_flags & RADEON_PG_SUPPORT_GFX_DMG))
+		data |= DYN_PER_CU_PG_ENABLE;
+	else
+		data &= ~DYN_PER_CU_PG_ENABLE;
+	if (orig != data)
+		WREG32(RLC_PG_CNTL, data);
+}
+
+#define RLC_SAVE_AND_RESTORE_STARTING_OFFSET 0x90
+#define RLC_CLEAR_STATE_DESCRIPTOR_OFFSET    0x3D
+
+static void cik_init_gfx_cgpg(struct radeon_device *rdev)
+{
+	u32 data, orig;
+	u32 i;
+
+	if (rdev->rlc.cs_data) {
+		WREG32(RLC_GPM_SCRATCH_ADDR, RLC_CLEAR_STATE_DESCRIPTOR_OFFSET);
+		WREG32(RLC_GPM_SCRATCH_DATA, upper_32_bits(rdev->rlc.clear_state_gpu_addr));
+		WREG32(RLC_GPM_SCRATCH_DATA, lower_32_bits(rdev->rlc.clear_state_gpu_addr));
+		WREG32(RLC_GPM_SCRATCH_DATA, rdev->rlc.clear_state_size);
+	} else {
+		WREG32(RLC_GPM_SCRATCH_ADDR, RLC_CLEAR_STATE_DESCRIPTOR_OFFSET);
+		for (i = 0; i < 3; i++)
+			WREG32(RLC_GPM_SCRATCH_DATA, 0);
+	}
+	if (rdev->rlc.reg_list) {
+		WREG32(RLC_GPM_SCRATCH_ADDR, RLC_SAVE_AND_RESTORE_STARTING_OFFSET);
+		for (i = 0; i < rdev->rlc.reg_list_size; i++)
+			WREG32(RLC_GPM_SCRATCH_DATA, rdev->rlc.reg_list[i]);
+	}
+
+	orig = data = RREG32(RLC_PG_CNTL);
+	data |= GFX_PG_SRC;
+	if (orig != data)
+		WREG32(RLC_PG_CNTL, data);
+
+	WREG32(RLC_SAVE_AND_RESTORE_BASE, rdev->rlc.save_restore_gpu_addr >> 8);
+	WREG32(RLC_CP_TABLE_RESTORE, rdev->rlc.cp_table_gpu_addr >> 8);
+
+	data = RREG32(CP_RB_WPTR_POLL_CNTL);
+	data &= ~IDLE_POLL_COUNT_MASK;
+	data |= IDLE_POLL_COUNT(0x60);
+	WREG32(CP_RB_WPTR_POLL_CNTL, data);
+
+	data = 0x10101010;
+	WREG32(RLC_PG_DELAY, data);
+
+	data = RREG32(RLC_PG_DELAY_2);
+	data &= ~0xff;
+	data |= 0x3;
+	WREG32(RLC_PG_DELAY_2, data);
+
+	data = RREG32(RLC_AUTO_PG_CTRL);
+	data &= ~GRBM_REG_SGIT_MASK;
+	data |= GRBM_REG_SGIT(0x700);
+	WREG32(RLC_AUTO_PG_CTRL, data);
+
+}
+
+static void cik_update_gfx_pg(struct radeon_device *rdev, bool enable)
+{
+	cik_enable_gfx_cgpg(rdev, enable);
+	cik_enable_gfx_static_mgpg(rdev, enable);
+	cik_enable_gfx_dynamic_mgpg(rdev, enable);
+}
+
+u32 cik_get_csb_size(struct radeon_device *rdev)
+{
+	u32 count = 0;
+	const struct cs_section_def *sect = NULL;
+	const struct cs_extent_def *ext = NULL;
+
+	if (rdev->rlc.cs_data == NULL)
+		return 0;
+
+	/* begin clear state */
+	count += 2;
+	/* context control state */
+	count += 3;
+
+	for (sect = rdev->rlc.cs_data; sect->section != NULL; ++sect) {
+		for (ext = sect->section; ext->extent != NULL; ++ext) {
+			if (sect->id == SECT_CONTEXT)
+				count += 2 + ext->reg_count;
+			else
+				return 0;
+		}
+	}
+	/* pa_sc_raster_config/pa_sc_raster_config1 */
+	count += 4;
+	/* end clear state */
+	count += 2;
+	/* clear state */
+	count += 2;
+
+	return count;
+}
+
+void cik_get_csb_buffer(struct radeon_device *rdev, volatile u32 *buffer)
+{
+	u32 count = 0, i;
+	const struct cs_section_def *sect = NULL;
+	const struct cs_extent_def *ext = NULL;
+
+	if (rdev->rlc.cs_data == NULL)
+		return;
+	if (buffer == NULL)
+		return;
+
+	buffer[count++] = PACKET3(PACKET3_PREAMBLE_CNTL, 0);
+	buffer[count++] = PACKET3_PREAMBLE_BEGIN_CLEAR_STATE;
+
+	buffer[count++] = PACKET3(PACKET3_CONTEXT_CONTROL, 1);
+	buffer[count++] = 0x80000000;
+	buffer[count++] = 0x80000000;
+
+	for (sect = rdev->rlc.cs_data; sect->section != NULL; ++sect) {
+		for (ext = sect->section; ext->extent != NULL; ++ext) {
+			if (sect->id == SECT_CONTEXT) {
+				buffer[count++] = PACKET3(PACKET3_SET_CONTEXT_REG, ext->reg_count);
+				buffer[count++] = ext->reg_index - 0xa000;
+				for (i = 0; i < ext->reg_count; i++)
+					buffer[count++] = ext->extent[i];
+			} else {
+				return;
+			}
+		}
+	}
+
+	buffer[count++] = PACKET3(PACKET3_SET_CONTEXT_REG, 2);
+	buffer[count++] = PA_SC_RASTER_CONFIG - PACKET3_SET_CONTEXT_REG_START;
+	switch (rdev->family) {
+	case CHIP_BONAIRE:
+		buffer[count++] = 0x16000012;
+		buffer[count++] = 0x00000000;
+		break;
+	case CHIP_KAVERI:
+		buffer[count++] = 0x00000000; /* XXX */
+		buffer[count++] = 0x00000000;
+		break;
+	case CHIP_KABINI:
+		buffer[count++] = 0x00000000; /* XXX */
+		buffer[count++] = 0x00000000;
+		break;
+	default:
+		buffer[count++] = 0x00000000;
+		buffer[count++] = 0x00000000;
+		break;
+	}
+
+	buffer[count++] = PACKET3(PACKET3_PREAMBLE_CNTL, 0);
+	buffer[count++] = PACKET3_PREAMBLE_END_CLEAR_STATE;
+
+	buffer[count++] = PACKET3(PACKET3_CLEAR_STATE, 0);
+	buffer[count++] = 0;
+}
+
+static void cik_init_pg(struct radeon_device *rdev)
+{
+	if (rdev->pg_flags) {
+		cik_enable_sck_slowdown_on_pu(rdev, true);
+		cik_enable_sck_slowdown_on_pd(rdev, true);
+		if (rdev->pg_flags & RADEON_PG_SUPPORT_GFX_PG) {
+			cik_init_gfx_cgpg(rdev);
+			cik_enable_cp_pg(rdev, true);
+			cik_enable_gds_pg(rdev, true);
+		}
+		cik_init_ao_cu_mask(rdev);
+		cik_update_gfx_pg(rdev, true);
+	}
+}
+
+static void cik_fini_pg(struct radeon_device *rdev)
+{
+	if (rdev->pg_flags) {
+		cik_update_gfx_pg(rdev, false);
+		if (rdev->pg_flags & RADEON_PG_SUPPORT_GFX_PG) {
+			cik_enable_cp_pg(rdev, false);
+			cik_enable_gds_pg(rdev, false);
+		}
+	}
+}
+
 /*
  * Interrupts
  * Starting with r6xx, interrupts are handled via a ring buffer.
@@ -4947,7 +5917,9 @@ static void cik_disable_interrupt_state(struct radeon_device *rdev)
 	u32 tmp;
 
 	/* gfx ring */
-	WREG32(CP_INT_CNTL_RING0, CNTX_BUSY_INT_ENABLE | CNTX_EMPTY_INT_ENABLE);
+	tmp = RREG32(CP_INT_CNTL_RING0) &
+		(CNTX_BUSY_INT_ENABLE | CNTX_EMPTY_INT_ENABLE);
+	WREG32(CP_INT_CNTL_RING0, tmp);
 	/* sdma */
 	tmp = RREG32(SDMA0_CNTL + SDMA0_REGISTER_OFFSET) & ~TRAP_ENABLE;
 	WREG32(SDMA0_CNTL + SDMA0_REGISTER_OFFSET, tmp);
@@ -5040,7 +6012,7 @@ static int cik_irq_init(struct radeon_device *rdev)
 	WREG32(INTERRUPT_CNTL, interrupt_cntl);
 
 	WREG32(IH_RB_BASE, rdev->ih.gpu_addr >> 8);
-	rb_bufsz = drm_order(rdev->ih.ring_size / 4);
+	rb_bufsz = order_base_2(rdev->ih.ring_size / 4);
 
 	ih_rb_cntl = (IH_WPTR_OVERFLOW_ENABLE |
 		      IH_WPTR_OVERFLOW_CLEAR |
@@ -5088,14 +6060,14 @@ static int cik_irq_init(struct radeon_device *rdev)
  */
 int cik_irq_set(struct radeon_device *rdev)
 {
-	u32 cp_int_cntl = CNTX_BUSY_INT_ENABLE | CNTX_EMPTY_INT_ENABLE |
-		PRIV_INSTR_INT_ENABLE | PRIV_REG_INT_ENABLE;
+	u32 cp_int_cntl;
 	u32 cp_m1p0, cp_m1p1, cp_m1p2, cp_m1p3;
 	u32 cp_m2p0, cp_m2p1, cp_m2p2, cp_m2p3;
 	u32 crtc1 = 0, crtc2 = 0, crtc3 = 0, crtc4 = 0, crtc5 = 0, crtc6 = 0;
 	u32 hpd1, hpd2, hpd3, hpd4, hpd5, hpd6;
 	u32 grbm_int_cntl = 0;
 	u32 dma_cntl, dma_cntl1;
+	u32 thermal_int;
 
 	if (!rdev->irq.installed) {
 		WARN(1, "Can't enable IRQ/MSI because no handler is installed\n");
@@ -5109,6 +6081,10 @@ int cik_irq_set(struct radeon_device *rdev)
 		return 0;
 	}
 
+	cp_int_cntl = RREG32(CP_INT_CNTL_RING0) &
+		(CNTX_BUSY_INT_ENABLE | CNTX_EMPTY_INT_ENABLE);
+	cp_int_cntl |= PRIV_INSTR_INT_ENABLE | PRIV_REG_INT_ENABLE;
+
 	hpd1 = RREG32(DC_HPD1_INT_CONTROL) & ~DC_HPDx_INT_EN;
 	hpd2 = RREG32(DC_HPD2_INT_CONTROL) & ~DC_HPDx_INT_EN;
 	hpd3 = RREG32(DC_HPD3_INT_CONTROL) & ~DC_HPDx_INT_EN;
@@ -5128,6 +6104,13 @@ int cik_irq_set(struct radeon_device *rdev)
 	cp_m2p2 = RREG32(CP_ME2_PIPE2_INT_CNTL) & ~TIME_STAMP_INT_ENABLE;
 	cp_m2p3 = RREG32(CP_ME2_PIPE3_INT_CNTL) & ~TIME_STAMP_INT_ENABLE;
 
+	if (rdev->flags & RADEON_IS_IGP)
+		thermal_int = RREG32_SMC(CG_THERMAL_INT_CTRL) &
+			~(THERM_INTH_MASK | THERM_INTL_MASK);
+	else
+		thermal_int = RREG32_SMC(CG_THERMAL_INT) &
+			~(THERM_INT_MASK_HIGH | THERM_INT_MASK_LOW);
+
 	/* enable CP interrupts on all rings */
 	if (atomic_read(&rdev->irq.ring_int[RADEON_RING_TYPE_GFX_INDEX])) {
 		DRM_DEBUG("cik_irq_set: sw int gfx\n");
@@ -5285,6 +6268,14 @@ int cik_irq_set(struct radeon_device *rdev)
 		hpd6 |= DC_HPDx_INT_EN;
 	}
 
+	if (rdev->irq.dpm_thermal) {
+		DRM_DEBUG("dpm thermal\n");
+		if (rdev->flags & RADEON_IS_IGP)
+			thermal_int |= THERM_INTH_MASK | THERM_INTL_MASK;
+		else
+			thermal_int |= THERM_INT_MASK_HIGH | THERM_INT_MASK_LOW;
+	}
+
 	WREG32(CP_INT_CNTL_RING0, cp_int_cntl);
 
 	WREG32(SDMA0_CNTL + SDMA0_REGISTER_OFFSET, dma_cntl);
@@ -5319,6 +6310,11 @@ int cik_irq_set(struct radeon_device *rdev)
 	WREG32(DC_HPD5_INT_CONTROL, hpd5);
 	WREG32(DC_HPD6_INT_CONTROL, hpd6);
 
+	if (rdev->flags & RADEON_IS_IGP)
+		WREG32_SMC(CG_THERMAL_INT_CTRL, thermal_int);
+	else
+		WREG32_SMC(CG_THERMAL_INT, thermal_int);
+
 	return 0;
 }
 
@@ -5530,6 +6526,7 @@ int cik_irq_process(struct radeon_device *rdev)
 	bool queue_hotplug = false;
 	bool queue_reset = false;
 	u32 addr, status, mc_client;
+	bool queue_thermal = false;
 
 	if (!rdev->ih.enabled || rdev->shutdown)
 		return IRQ_NONE;
@@ -5763,6 +6760,10 @@ restart_ih:
 				break;
 			}
 			break;
+		case 124: /* UVD */
+			DRM_DEBUG("IH: UVD int: 0x%08x\n", src_data);
+			radeon_fence_process(rdev, R600_RING_TYPE_UVD_INDEX);
+			break;
 		case 146:
 		case 147:
 			addr = RREG32(VM_CONTEXT1_PROTECTION_FAULT_ADDR);
@@ -5880,6 +6881,19 @@ restart_ih:
 				break;
 			}
 			break;
+		case 230: /* thermal low to high */
+			DRM_DEBUG("IH: thermal low to high\n");
+			rdev->pm.dpm.thermal.high_to_low = false;
+			queue_thermal = true;
+			break;
+		case 231: /* thermal high to low */
+			DRM_DEBUG("IH: thermal high to low\n");
+			rdev->pm.dpm.thermal.high_to_low = true;
+			queue_thermal = true;
+			break;
+		case 233: /* GUI IDLE */
+			DRM_DEBUG("IH: GUI idle\n");
+			break;
 		case 241: /* SDMA Privileged inst */
 		case 247: /* SDMA Privileged inst */
 			DRM_ERROR("Illegal instruction in SDMA command stream\n");
@@ -5919,9 +6933,6 @@ restart_ih:
 				break;
 			}
 			break;
-		case 233: /* GUI IDLE */
-			DRM_DEBUG("IH: GUI idle\n");
-			break;
 		default:
 			DRM_DEBUG("Unhandled interrupt: %d %d\n", src_id, src_data);
 			break;
@@ -5935,6 +6946,8 @@ restart_ih:
 		schedule_work(&rdev->hotplug_work);
 	if (queue_reset)
 		schedule_work(&rdev->reset_work);
+	if (queue_thermal)
+		schedule_work(&rdev->pm.dpm.thermal.work);
 	rdev->ih.rptr = rptr;
 	WREG32(IH_RB_RPTR, rdev->ih.rptr);
 	atomic_set(&rdev->ih.lock, 0);
@@ -5964,6 +6977,16 @@ static int cik_startup(struct radeon_device *rdev)
 	struct radeon_ring *ring;
 	int r;
 
+	/* enable pcie gen2/3 link */
+	cik_pcie_gen3_enable(rdev);
+	/* enable aspm */
+	cik_program_aspm(rdev);
+
+	/* scratch needs to be initialized before MC */
+	r = r600_vram_scratch_init(rdev);
+	if (r)
+		return r;
+
 	cik_mc_program(rdev);
 
 	if (rdev->flags & RADEON_IS_IGP) {
@@ -5993,17 +7016,26 @@ static int cik_startup(struct radeon_device *rdev)
 		}
 	}
 
-	r = r600_vram_scratch_init(rdev);
-	if (r)
-		return r;
-
 	r = cik_pcie_gart_enable(rdev);
 	if (r)
 		return r;
 	cik_gpu_init(rdev);
 
 	/* allocate rlc buffers */
-	r = si_rlc_init(rdev);
+	if (rdev->flags & RADEON_IS_IGP) {
+		if (rdev->family == CHIP_KAVERI) {
+			rdev->rlc.reg_list = spectre_rlc_save_restore_register_list;
+			rdev->rlc.reg_list_size =
+				(u32)ARRAY_SIZE(spectre_rlc_save_restore_register_list);
+		} else {
+			rdev->rlc.reg_list = kalindi_rlc_save_restore_register_list;
+			rdev->rlc.reg_list_size =
+				(u32)ARRAY_SIZE(kalindi_rlc_save_restore_register_list);
+		}
+	}
+	rdev->rlc.cs_data = ci_cs_data;
+	rdev->rlc.cp_table_size = CP_ME_TABLE_SIZE * 5 * 4;
+	r = sumo_rlc_init(rdev);
 	if (r) {
 		DRM_ERROR("Failed to init rlc BOs!\n");
 		return r;
@@ -6051,12 +7083,15 @@ static int cik_startup(struct radeon_device *rdev)
 		return r;
 	}
 
-	r = cik_uvd_resume(rdev);
+	r = radeon_uvd_resume(rdev);
 	if (!r) {
-		r = radeon_fence_driver_start_ring(rdev,
-						   R600_RING_TYPE_UVD_INDEX);
-		if (r)
-			dev_err(rdev->dev, "UVD fences init error (%d).\n", r);
+		r = uvd_v4_2_resume(rdev);
+		if (!r) {
+			r = radeon_fence_driver_start_ring(rdev,
+							   R600_RING_TYPE_UVD_INDEX);
+			if (r)
+				dev_err(rdev->dev, "UVD fences init error (%d).\n", r);
+		}
 	}
 	if (r)
 		rdev->ring[R600_RING_TYPE_UVD_INDEX].ring_size = 0;
@@ -6079,7 +7114,7 @@ static int cik_startup(struct radeon_device *rdev)
 	ring = &rdev->ring[RADEON_RING_TYPE_GFX_INDEX];
 	r = radeon_ring_init(rdev, ring, ring->ring_size, RADEON_WB_CP_RPTR_OFFSET,
 			     CP_RB0_RPTR, CP_RB0_WPTR,
-			     0, 0xfffff, RADEON_CP_PACKET2);
+			     RADEON_CP_PACKET2);
 	if (r)
 		return r;
 
@@ -6088,7 +7123,7 @@ static int cik_startup(struct radeon_device *rdev)
 	ring = &rdev->ring[CAYMAN_RING_TYPE_CP1_INDEX];
 	r = radeon_ring_init(rdev, ring, ring->ring_size, RADEON_WB_CP1_RPTR_OFFSET,
 			     CP_HQD_PQ_RPTR, CP_HQD_PQ_WPTR,
-			     0, 0xfffff, PACKET3(PACKET3_NOP, 0x3FFF));
+			     PACKET3(PACKET3_NOP, 0x3FFF));
 	if (r)
 		return r;
 	ring->me = 1; /* first MEC */
@@ -6100,7 +7135,7 @@ static int cik_startup(struct radeon_device *rdev)
 	ring = &rdev->ring[CAYMAN_RING_TYPE_CP2_INDEX];
 	r = radeon_ring_init(rdev, ring, ring->ring_size, RADEON_WB_CP2_RPTR_OFFSET,
 			     CP_HQD_PQ_RPTR, CP_HQD_PQ_WPTR,
-			     0, 0xffffffff, PACKET3(PACKET3_NOP, 0x3FFF));
+			     PACKET3(PACKET3_NOP, 0x3FFF));
 	if (r)
 		return r;
 	/* dGPU only have 1 MEC */
@@ -6113,7 +7148,7 @@ static int cik_startup(struct radeon_device *rdev)
 	r = radeon_ring_init(rdev, ring, ring->ring_size, R600_WB_DMA_RPTR_OFFSET,
 			     SDMA0_GFX_RB_RPTR + SDMA0_REGISTER_OFFSET,
 			     SDMA0_GFX_RB_WPTR + SDMA0_REGISTER_OFFSET,
-			     2, 0xfffffffc, SDMA_PACKET(SDMA_OPCODE_NOP, 0, 0));
+			     SDMA_PACKET(SDMA_OPCODE_NOP, 0, 0));
 	if (r)
 		return r;
 
@@ -6121,7 +7156,7 @@ static int cik_startup(struct radeon_device *rdev)
 	r = radeon_ring_init(rdev, ring, ring->ring_size, CAYMAN_WB_DMA1_RPTR_OFFSET,
 			     SDMA0_GFX_RB_RPTR + SDMA1_REGISTER_OFFSET,
 			     SDMA0_GFX_RB_WPTR + SDMA1_REGISTER_OFFSET,
-			     2, 0xfffffffc, SDMA_PACKET(SDMA_OPCODE_NOP, 0, 0));
+			     SDMA_PACKET(SDMA_OPCODE_NOP, 0, 0));
 	if (r)
 		return r;
 
@@ -6135,12 +7170,11 @@ static int cik_startup(struct radeon_device *rdev)
 
 	ring = &rdev->ring[R600_RING_TYPE_UVD_INDEX];
 	if (ring->ring_size) {
-		r = radeon_ring_init(rdev, ring, ring->ring_size,
-				     R600_WB_UVD_RPTR_OFFSET,
+		r = radeon_ring_init(rdev, ring, ring->ring_size, 0,
 				     UVD_RBC_RB_RPTR, UVD_RBC_RB_WPTR,
-				     0, 0xfffff, RADEON_CP_PACKET2);
+				     RADEON_CP_PACKET2);
 		if (!r)
-			r = r600_uvd_init(rdev);
+			r = uvd_v1_0_init(rdev);
 		if (r)
 			DRM_ERROR("radeon: failed initializing UVD (%d).\n", r);
 	}
@@ -6157,6 +7191,10 @@ static int cik_startup(struct radeon_device *rdev)
 		return r;
 	}
 
+	r = dce6_audio_init(rdev);
+	if (r)
+		return r;
+
 	return 0;
 }
 
@@ -6202,11 +7240,14 @@ int cik_resume(struct radeon_device *rdev)
  */
 int cik_suspend(struct radeon_device *rdev)
 {
+	dce6_audio_fini(rdev);
 	radeon_vm_manager_fini(rdev);
 	cik_cp_enable(rdev, false);
 	cik_sdma_enable(rdev, false);
-	r600_uvd_stop(rdev);
+	uvd_v1_0_fini(rdev);
 	radeon_uvd_suspend(rdev);
+	cik_fini_pg(rdev);
+	cik_fini_cg(rdev);
 	cik_irq_suspend(rdev);
 	radeon_wb_disable(rdev);
 	cik_pcie_gart_disable(rdev);
@@ -6327,7 +7368,7 @@ int cik_init(struct radeon_device *rdev)
 		cik_cp_fini(rdev);
 		cik_sdma_fini(rdev);
 		cik_irq_fini(rdev);
-		si_rlc_fini(rdev);
+		sumo_rlc_fini(rdev);
 		cik_mec_fini(rdev);
 		radeon_wb_fini(rdev);
 		radeon_ib_pool_fini(rdev);
@@ -6362,14 +7403,16 @@ void cik_fini(struct radeon_device *rdev)
 {
 	cik_cp_fini(rdev);
 	cik_sdma_fini(rdev);
+	cik_fini_pg(rdev);
+	cik_fini_cg(rdev);
 	cik_irq_fini(rdev);
-	si_rlc_fini(rdev);
+	sumo_rlc_fini(rdev);
 	cik_mec_fini(rdev);
 	radeon_wb_fini(rdev);
 	radeon_vm_manager_fini(rdev);
 	radeon_ib_pool_fini(rdev);
 	radeon_irq_kms_fini(rdev);
-	r600_uvd_stop(rdev);
+	uvd_v1_0_fini(rdev);
 	radeon_uvd_fini(rdev);
 	cik_pcie_gart_fini(rdev);
 	r600_vram_scratch_fini(rdev);
@@ -6398,8 +7441,8 @@ static u32 dce8_line_buffer_adjust(struct radeon_device *rdev,
 				   struct radeon_crtc *radeon_crtc,
 				   struct drm_display_mode *mode)
 {
-	u32 tmp;
-
+	u32 tmp, buffer_alloc, i;
+	u32 pipe_offset = radeon_crtc->crtc_id * 0x20;
 	/*
 	 * Line Buffer Setup
 	 * There are 6 line buffers, one for each display controllers.
@@ -6409,22 +7452,37 @@ static u32 dce8_line_buffer_adjust(struct radeon_device *rdev,
 	 * them using the stereo blender.
 	 */
 	if (radeon_crtc->base.enabled && mode) {
-		if (mode->crtc_hdisplay < 1920)
+		if (mode->crtc_hdisplay < 1920) {
 			tmp = 1;
-		else if (mode->crtc_hdisplay < 2560)
+			buffer_alloc = 2;
+		} else if (mode->crtc_hdisplay < 2560) {
 			tmp = 2;
-		else if (mode->crtc_hdisplay < 4096)
+			buffer_alloc = 2;
+		} else if (mode->crtc_hdisplay < 4096) {
 			tmp = 0;
-		else {
+			buffer_alloc = (rdev->flags & RADEON_IS_IGP) ? 2 : 4;
+		} else {
 			DRM_DEBUG_KMS("Mode too big for LB!\n");
 			tmp = 0;
+			buffer_alloc = (rdev->flags & RADEON_IS_IGP) ? 2 : 4;
 		}
-	} else
+	} else {
 		tmp = 1;
+		buffer_alloc = 0;
+	}
 
 	WREG32(LB_MEMORY_CTRL + radeon_crtc->crtc_offset,
 	       LB_MEMORY_CONFIG(tmp) | LB_MEMORY_SIZE(0x6B0));
 
+	WREG32(PIPE0_DMIF_BUFFER_CONTROL + pipe_offset,
+	       DMIF_BUFFERS_ALLOCATED(buffer_alloc));
+	for (i = 0; i < rdev->usec_timeout; i++) {
+		if (RREG32(PIPE0_DMIF_BUFFER_CONTROL + pipe_offset) &
+		    DMIF_BUFFERS_ALLOCATED_COMPLETED)
+			break;
+		udelay(1);
+	}
+
 	if (radeon_crtc->base.enabled && mode) {
 		switch (tmp) {
 		case 0:
@@ -6826,7 +7884,7 @@ static void dce8_program_watermarks(struct radeon_device *rdev,
 				    u32 lb_size, u32 num_heads)
 {
 	struct drm_display_mode *mode = &radeon_crtc->base.mode;
-	struct dce8_wm_params wm;
+	struct dce8_wm_params wm_low, wm_high;
 	u32 pixel_period;
 	u32 line_time = 0;
 	u32 latency_watermark_a = 0, latency_watermark_b = 0;
@@ -6836,35 +7894,82 @@ static void dce8_program_watermarks(struct radeon_device *rdev,
 		pixel_period = 1000000 / (u32)mode->clock;
 		line_time = min((u32)mode->crtc_htotal * pixel_period, (u32)65535);
 
-		wm.yclk = rdev->pm.current_mclk * 10;
-		wm.sclk = rdev->pm.current_sclk * 10;
-		wm.disp_clk = mode->clock;
-		wm.src_width = mode->crtc_hdisplay;
-		wm.active_time = mode->crtc_hdisplay * pixel_period;
-		wm.blank_time = line_time - wm.active_time;
-		wm.interlaced = false;
+		/* watermark for high clocks */
+		if ((rdev->pm.pm_method == PM_METHOD_DPM) &&
+		    rdev->pm.dpm_enabled) {
+			wm_high.yclk =
+				radeon_dpm_get_mclk(rdev, false) * 10;
+			wm_high.sclk =
+				radeon_dpm_get_sclk(rdev, false) * 10;
+		} else {
+			wm_high.yclk = rdev->pm.current_mclk * 10;
+			wm_high.sclk = rdev->pm.current_sclk * 10;
+		}
+
+		wm_high.disp_clk = mode->clock;
+		wm_high.src_width = mode->crtc_hdisplay;
+		wm_high.active_time = mode->crtc_hdisplay * pixel_period;
+		wm_high.blank_time = line_time - wm_high.active_time;
+		wm_high.interlaced = false;
 		if (mode->flags & DRM_MODE_FLAG_INTERLACE)
-			wm.interlaced = true;
-		wm.vsc = radeon_crtc->vsc;
-		wm.vtaps = 1;
+			wm_high.interlaced = true;
+		wm_high.vsc = radeon_crtc->vsc;
+		wm_high.vtaps = 1;
 		if (radeon_crtc->rmx_type != RMX_OFF)
-			wm.vtaps = 2;
-		wm.bytes_per_pixel = 4; /* XXX: get this from fb config */
-		wm.lb_size = lb_size;
-		wm.dram_channels = cik_get_number_of_dram_channels(rdev);
-		wm.num_heads = num_heads;
+			wm_high.vtaps = 2;
+		wm_high.bytes_per_pixel = 4; /* XXX: get this from fb config */
+		wm_high.lb_size = lb_size;
+		wm_high.dram_channels = cik_get_number_of_dram_channels(rdev);
+		wm_high.num_heads = num_heads;
 
 		/* set for high clocks */
-		latency_watermark_a = min(dce8_latency_watermark(&wm), (u32)65535);
+		latency_watermark_a = min(dce8_latency_watermark(&wm_high), (u32)65535);
+
+		/* possibly force display priority to high */
+		/* should really do this at mode validation time... */
+		if (!dce8_average_bandwidth_vs_dram_bandwidth_for_display(&wm_high) ||
+		    !dce8_average_bandwidth_vs_available_bandwidth(&wm_high) ||
+		    !dce8_check_latency_hiding(&wm_high) ||
+		    (rdev->disp_priority == 2)) {
+			DRM_DEBUG_KMS("force priority to high\n");
+		}
+
+		/* watermark for low clocks */
+		if ((rdev->pm.pm_method == PM_METHOD_DPM) &&
+		    rdev->pm.dpm_enabled) {
+			wm_low.yclk =
+				radeon_dpm_get_mclk(rdev, true) * 10;
+			wm_low.sclk =
+				radeon_dpm_get_sclk(rdev, true) * 10;
+		} else {
+			wm_low.yclk = rdev->pm.current_mclk * 10;
+			wm_low.sclk = rdev->pm.current_sclk * 10;
+		}
+
+		wm_low.disp_clk = mode->clock;
+		wm_low.src_width = mode->crtc_hdisplay;
+		wm_low.active_time = mode->crtc_hdisplay * pixel_period;
+		wm_low.blank_time = line_time - wm_low.active_time;
+		wm_low.interlaced = false;
+		if (mode->flags & DRM_MODE_FLAG_INTERLACE)
+			wm_low.interlaced = true;
+		wm_low.vsc = radeon_crtc->vsc;
+		wm_low.vtaps = 1;
+		if (radeon_crtc->rmx_type != RMX_OFF)
+			wm_low.vtaps = 2;
+		wm_low.bytes_per_pixel = 4; /* XXX: get this from fb config */
+		wm_low.lb_size = lb_size;
+		wm_low.dram_channels = cik_get_number_of_dram_channels(rdev);
+		wm_low.num_heads = num_heads;
+
 		/* set for low clocks */
-		/* wm.yclk = low clk; wm.sclk = low clk */
-		latency_watermark_b = min(dce8_latency_watermark(&wm), (u32)65535);
+		latency_watermark_b = min(dce8_latency_watermark(&wm_low), (u32)65535);
 
 		/* possibly force display priority to high */
 		/* should really do this at mode validation time... */
-		if (!dce8_average_bandwidth_vs_dram_bandwidth_for_display(&wm) ||
-		    !dce8_average_bandwidth_vs_available_bandwidth(&wm) ||
-		    !dce8_check_latency_hiding(&wm) ||
+		if (!dce8_average_bandwidth_vs_dram_bandwidth_for_display(&wm_low) ||
+		    !dce8_average_bandwidth_vs_available_bandwidth(&wm_low) ||
+		    !dce8_check_latency_hiding(&wm_low) ||
 		    (rdev->disp_priority == 2)) {
 			DRM_DEBUG_KMS("force priority to high\n");
 		}
@@ -6889,6 +7994,11 @@ static void dce8_program_watermarks(struct radeon_device *rdev,
 		LATENCY_HIGH_WATERMARK(line_time)));
 	/* restore original selection */
 	WREG32(DPG_WATERMARK_MASK_CONTROL + radeon_crtc->crtc_offset, wm_mask);
+
+	/* save values for DPM */
+	radeon_crtc->line_time = line_time;
+	radeon_crtc->wm_high = latency_watermark_a;
+	radeon_crtc->wm_low = latency_watermark_b;
 }
 
 /**
@@ -6978,39 +8088,307 @@ int cik_set_uvd_clocks(struct radeon_device *rdev, u32 vclk, u32 dclk)
 	return r;
 }
 
-int cik_uvd_resume(struct radeon_device *rdev)
+static void cik_pcie_gen3_enable(struct radeon_device *rdev)
 {
-	uint64_t addr;
-	uint32_t size;
-	int r;
+	struct pci_dev *root = rdev->pdev->bus->self;
+	int bridge_pos, gpu_pos;
+	u32 speed_cntl, mask, current_data_rate;
+	int ret, i;
+	u16 tmp16;
 
-	r = radeon_uvd_resume(rdev);
-	if (r)
-		return r;
+	if (radeon_pcie_gen2 == 0)
+		return;
+
+	if (rdev->flags & RADEON_IS_IGP)
+		return;
 
-	/* programm the VCPU memory controller bits 0-27 */
-	addr = rdev->uvd.gpu_addr >> 3;
-	size = RADEON_GPU_PAGE_ALIGN(rdev->uvd_fw->size + 4) >> 3;
-	WREG32(UVD_VCPU_CACHE_OFFSET0, addr);
-	WREG32(UVD_VCPU_CACHE_SIZE0, size);
+	if (!(rdev->flags & RADEON_IS_PCIE))
+		return;
+
+	ret = drm_pcie_get_speed_cap_mask(rdev->ddev, &mask);
+	if (ret != 0)
+		return;
 
-	addr += size;
-	size = RADEON_UVD_STACK_SIZE >> 3;
-	WREG32(UVD_VCPU_CACHE_OFFSET1, addr);
-	WREG32(UVD_VCPU_CACHE_SIZE1, size);
+	if (!(mask & (DRM_PCIE_SPEED_50 | DRM_PCIE_SPEED_80)))
+		return;
+
+	speed_cntl = RREG32_PCIE_PORT(PCIE_LC_SPEED_CNTL);
+	current_data_rate = (speed_cntl & LC_CURRENT_DATA_RATE_MASK) >>
+		LC_CURRENT_DATA_RATE_SHIFT;
+	if (mask & DRM_PCIE_SPEED_80) {
+		if (current_data_rate == 2) {
+			DRM_INFO("PCIE gen 3 link speeds already enabled\n");
+			return;
+		}
+		DRM_INFO("enabling PCIE gen 3 link speeds, disable with radeon.pcie_gen2=0\n");
+	} else if (mask & DRM_PCIE_SPEED_50) {
+		if (current_data_rate == 1) {
+			DRM_INFO("PCIE gen 2 link speeds already enabled\n");
+			return;
+		}
+		DRM_INFO("enabling PCIE gen 2 link speeds, disable with radeon.pcie_gen2=0\n");
+	}
 
-	addr += size;
-	size = RADEON_UVD_HEAP_SIZE >> 3;
-	WREG32(UVD_VCPU_CACHE_OFFSET2, addr);
-	WREG32(UVD_VCPU_CACHE_SIZE2, size);
+	bridge_pos = pci_pcie_cap(root);
+	if (!bridge_pos)
+		return;
 
-	/* bits 28-31 */
-	addr = (rdev->uvd.gpu_addr >> 28) & 0xF;
-	WREG32(UVD_LMI_ADDR_EXT, (addr << 12) | (addr << 0));
+	gpu_pos = pci_pcie_cap(rdev->pdev);
+	if (!gpu_pos)
+		return;
 
-	/* bits 32-39 */
-	addr = (rdev->uvd.gpu_addr >> 32) & 0xFF;
-	WREG32(UVD_LMI_EXT40_ADDR, addr | (0x9 << 16) | (0x1 << 31));
+	if (mask & DRM_PCIE_SPEED_80) {
+		/* re-try equalization if gen3 is not already enabled */
+		if (current_data_rate != 2) {
+			u16 bridge_cfg, gpu_cfg;
+			u16 bridge_cfg2, gpu_cfg2;
+			u32 max_lw, current_lw, tmp;
+
+			pci_read_config_word(root, bridge_pos + PCI_EXP_LNKCTL, &bridge_cfg);
+			pci_read_config_word(rdev->pdev, gpu_pos + PCI_EXP_LNKCTL, &gpu_cfg);
+
+			tmp16 = bridge_cfg | PCI_EXP_LNKCTL_HAWD;
+			pci_write_config_word(root, bridge_pos + PCI_EXP_LNKCTL, tmp16);
+
+			tmp16 = gpu_cfg | PCI_EXP_LNKCTL_HAWD;
+			pci_write_config_word(rdev->pdev, gpu_pos + PCI_EXP_LNKCTL, tmp16);
+
+			tmp = RREG32_PCIE_PORT(PCIE_LC_STATUS1);
+			max_lw = (tmp & LC_DETECTED_LINK_WIDTH_MASK) >> LC_DETECTED_LINK_WIDTH_SHIFT;
+			current_lw = (tmp & LC_OPERATING_LINK_WIDTH_MASK) >> LC_OPERATING_LINK_WIDTH_SHIFT;
+
+			if (current_lw < max_lw) {
+				tmp = RREG32_PCIE_PORT(PCIE_LC_LINK_WIDTH_CNTL);
+				if (tmp & LC_RENEGOTIATION_SUPPORT) {
+					tmp &= ~(LC_LINK_WIDTH_MASK | LC_UPCONFIGURE_DIS);
+					tmp |= (max_lw << LC_LINK_WIDTH_SHIFT);
+					tmp |= LC_UPCONFIGURE_SUPPORT | LC_RENEGOTIATE_EN | LC_RECONFIG_NOW;
+					WREG32_PCIE_PORT(PCIE_LC_LINK_WIDTH_CNTL, tmp);
+				}
+			}
 
-	return 0;
+			for (i = 0; i < 10; i++) {
+				/* check status */
+				pci_read_config_word(rdev->pdev, gpu_pos + PCI_EXP_DEVSTA, &tmp16);
+				if (tmp16 & PCI_EXP_DEVSTA_TRPND)
+					break;
+
+				pci_read_config_word(root, bridge_pos + PCI_EXP_LNKCTL, &bridge_cfg);
+				pci_read_config_word(rdev->pdev, gpu_pos + PCI_EXP_LNKCTL, &gpu_cfg);
+
+				pci_read_config_word(root, bridge_pos + PCI_EXP_LNKCTL2, &bridge_cfg2);
+				pci_read_config_word(rdev->pdev, gpu_pos + PCI_EXP_LNKCTL2, &gpu_cfg2);
+
+				tmp = RREG32_PCIE_PORT(PCIE_LC_CNTL4);
+				tmp |= LC_SET_QUIESCE;
+				WREG32_PCIE_PORT(PCIE_LC_CNTL4, tmp);
+
+				tmp = RREG32_PCIE_PORT(PCIE_LC_CNTL4);
+				tmp |= LC_REDO_EQ;
+				WREG32_PCIE_PORT(PCIE_LC_CNTL4, tmp);
+
+				mdelay(100);
+
+				/* linkctl */
+				pci_read_config_word(root, bridge_pos + PCI_EXP_LNKCTL, &tmp16);
+				tmp16 &= ~PCI_EXP_LNKCTL_HAWD;
+				tmp16 |= (bridge_cfg & PCI_EXP_LNKCTL_HAWD);
+				pci_write_config_word(root, bridge_pos + PCI_EXP_LNKCTL, tmp16);
+
+				pci_read_config_word(rdev->pdev, gpu_pos + PCI_EXP_LNKCTL, &tmp16);
+				tmp16 &= ~PCI_EXP_LNKCTL_HAWD;
+				tmp16 |= (gpu_cfg & PCI_EXP_LNKCTL_HAWD);
+				pci_write_config_word(rdev->pdev, gpu_pos + PCI_EXP_LNKCTL, tmp16);
+
+				/* linkctl2 */
+				pci_read_config_word(root, bridge_pos + PCI_EXP_LNKCTL2, &tmp16);
+				tmp16 &= ~((1 << 4) | (7 << 9));
+				tmp16 |= (bridge_cfg2 & ((1 << 4) | (7 << 9)));
+				pci_write_config_word(root, bridge_pos + PCI_EXP_LNKCTL2, tmp16);
+
+				pci_read_config_word(rdev->pdev, gpu_pos + PCI_EXP_LNKCTL2, &tmp16);
+				tmp16 &= ~((1 << 4) | (7 << 9));
+				tmp16 |= (gpu_cfg2 & ((1 << 4) | (7 << 9)));
+				pci_write_config_word(rdev->pdev, gpu_pos + PCI_EXP_LNKCTL2, tmp16);
+
+				tmp = RREG32_PCIE_PORT(PCIE_LC_CNTL4);
+				tmp &= ~LC_SET_QUIESCE;
+				WREG32_PCIE_PORT(PCIE_LC_CNTL4, tmp);
+			}
+		}
+	}
+
+	/* set the link speed */
+	speed_cntl |= LC_FORCE_EN_SW_SPEED_CHANGE | LC_FORCE_DIS_HW_SPEED_CHANGE;
+	speed_cntl &= ~LC_FORCE_DIS_SW_SPEED_CHANGE;
+	WREG32_PCIE_PORT(PCIE_LC_SPEED_CNTL, speed_cntl);
+
+	pci_read_config_word(rdev->pdev, gpu_pos + PCI_EXP_LNKCTL2, &tmp16);
+	tmp16 &= ~0xf;
+	if (mask & DRM_PCIE_SPEED_80)
+		tmp16 |= 3; /* gen3 */
+	else if (mask & DRM_PCIE_SPEED_50)
+		tmp16 |= 2; /* gen2 */
+	else
+		tmp16 |= 1; /* gen1 */
+	pci_write_config_word(rdev->pdev, gpu_pos + PCI_EXP_LNKCTL2, tmp16);
+
+	speed_cntl = RREG32_PCIE_PORT(PCIE_LC_SPEED_CNTL);
+	speed_cntl |= LC_INITIATE_LINK_SPEED_CHANGE;
+	WREG32_PCIE_PORT(PCIE_LC_SPEED_CNTL, speed_cntl);
+
+	for (i = 0; i < rdev->usec_timeout; i++) {
+		speed_cntl = RREG32_PCIE_PORT(PCIE_LC_SPEED_CNTL);
+		if ((speed_cntl & LC_INITIATE_LINK_SPEED_CHANGE) == 0)
+			break;
+		udelay(1);
+	}
+}
+
+static void cik_program_aspm(struct radeon_device *rdev)
+{
+	u32 data, orig;
+	bool disable_l0s = false, disable_l1 = false, disable_plloff_in_l1 = false;
+	bool disable_clkreq = false;
+
+	if (radeon_aspm == 0)
+		return;
+
+	/* XXX double check IGPs */
+	if (rdev->flags & RADEON_IS_IGP)
+		return;
+
+	if (!(rdev->flags & RADEON_IS_PCIE))
+		return;
+
+	orig = data = RREG32_PCIE_PORT(PCIE_LC_N_FTS_CNTL);
+	data &= ~LC_XMIT_N_FTS_MASK;
+	data |= LC_XMIT_N_FTS(0x24) | LC_XMIT_N_FTS_OVERRIDE_EN;
+	if (orig != data)
+		WREG32_PCIE_PORT(PCIE_LC_N_FTS_CNTL, data);
+
+	orig = data = RREG32_PCIE_PORT(PCIE_LC_CNTL3);
+	data |= LC_GO_TO_RECOVERY;
+	if (orig != data)
+		WREG32_PCIE_PORT(PCIE_LC_CNTL3, data);
+
+	orig = data = RREG32_PCIE_PORT(PCIE_P_CNTL);
+	data |= P_IGNORE_EDB_ERR;
+	if (orig != data)
+		WREG32_PCIE_PORT(PCIE_P_CNTL, data);
+
+	orig = data = RREG32_PCIE_PORT(PCIE_LC_CNTL);
+	data &= ~(LC_L0S_INACTIVITY_MASK | LC_L1_INACTIVITY_MASK);
+	data |= LC_PMI_TO_L1_DIS;
+	if (!disable_l0s)
+		data |= LC_L0S_INACTIVITY(7);
+
+	if (!disable_l1) {
+		data |= LC_L1_INACTIVITY(7);
+		data &= ~LC_PMI_TO_L1_DIS;
+		if (orig != data)
+			WREG32_PCIE_PORT(PCIE_LC_CNTL, data);
+
+		if (!disable_plloff_in_l1) {
+			bool clk_req_support;
+
+			orig = data = RREG32_PCIE_PORT(PB0_PIF_PWRDOWN_0);
+			data &= ~(PLL_POWER_STATE_IN_OFF_0_MASK | PLL_POWER_STATE_IN_TXS2_0_MASK);
+			data |= PLL_POWER_STATE_IN_OFF_0(7) | PLL_POWER_STATE_IN_TXS2_0(7);
+			if (orig != data)
+				WREG32_PCIE_PORT(PB0_PIF_PWRDOWN_0, data);
+
+			orig = data = RREG32_PCIE_PORT(PB0_PIF_PWRDOWN_1);
+			data &= ~(PLL_POWER_STATE_IN_OFF_1_MASK | PLL_POWER_STATE_IN_TXS2_1_MASK);
+			data |= PLL_POWER_STATE_IN_OFF_1(7) | PLL_POWER_STATE_IN_TXS2_1(7);
+			if (orig != data)
+				WREG32_PCIE_PORT(PB0_PIF_PWRDOWN_1, data);
+
+			orig = data = RREG32_PCIE_PORT(PB1_PIF_PWRDOWN_0);
+			data &= ~(PLL_POWER_STATE_IN_OFF_0_MASK | PLL_POWER_STATE_IN_TXS2_0_MASK);
+			data |= PLL_POWER_STATE_IN_OFF_0(7) | PLL_POWER_STATE_IN_TXS2_0(7);
+			if (orig != data)
+				WREG32_PCIE_PORT(PB1_PIF_PWRDOWN_0, data);
+
+			orig = data = RREG32_PCIE_PORT(PB1_PIF_PWRDOWN_1);
+			data &= ~(PLL_POWER_STATE_IN_OFF_1_MASK | PLL_POWER_STATE_IN_TXS2_1_MASK);
+			data |= PLL_POWER_STATE_IN_OFF_1(7) | PLL_POWER_STATE_IN_TXS2_1(7);
+			if (orig != data)
+				WREG32_PCIE_PORT(PB1_PIF_PWRDOWN_1, data);
+
+			orig = data = RREG32_PCIE_PORT(PCIE_LC_LINK_WIDTH_CNTL);
+			data &= ~LC_DYN_LANES_PWR_STATE_MASK;
+			data |= LC_DYN_LANES_PWR_STATE(3);
+			if (orig != data)
+				WREG32_PCIE_PORT(PCIE_LC_LINK_WIDTH_CNTL, data);
+
+			if (!disable_clkreq) {
+				struct pci_dev *root = rdev->pdev->bus->self;
+				u32 lnkcap;
+
+				clk_req_support = false;
+				pcie_capability_read_dword(root, PCI_EXP_LNKCAP, &lnkcap);
+				if (lnkcap & PCI_EXP_LNKCAP_CLKPM)
+					clk_req_support = true;
+			} else {
+				clk_req_support = false;
+			}
+
+			if (clk_req_support) {
+				orig = data = RREG32_PCIE_PORT(PCIE_LC_CNTL2);
+				data |= LC_ALLOW_PDWN_IN_L1 | LC_ALLOW_PDWN_IN_L23;
+				if (orig != data)
+					WREG32_PCIE_PORT(PCIE_LC_CNTL2, data);
+
+				orig = data = RREG32_SMC(THM_CLK_CNTL);
+				data &= ~(CMON_CLK_SEL_MASK | TMON_CLK_SEL_MASK);
+				data |= CMON_CLK_SEL(1) | TMON_CLK_SEL(1);
+				if (orig != data)
+					WREG32_SMC(THM_CLK_CNTL, data);
+
+				orig = data = RREG32_SMC(MISC_CLK_CTRL);
+				data &= ~(DEEP_SLEEP_CLK_SEL_MASK | ZCLK_SEL_MASK);
+				data |= DEEP_SLEEP_CLK_SEL(1) | ZCLK_SEL(1);
+				if (orig != data)
+					WREG32_SMC(MISC_CLK_CTRL, data);
+
+				orig = data = RREG32_SMC(CG_CLKPIN_CNTL);
+				data &= ~BCLK_AS_XCLK;
+				if (orig != data)
+					WREG32_SMC(CG_CLKPIN_CNTL, data);
+
+				orig = data = RREG32_SMC(CG_CLKPIN_CNTL_2);
+				data &= ~FORCE_BIF_REFCLK_EN;
+				if (orig != data)
+					WREG32_SMC(CG_CLKPIN_CNTL_2, data);
+
+				orig = data = RREG32_SMC(MPLL_BYPASSCLK_SEL);
+				data &= ~MPLL_CLKOUT_SEL_MASK;
+				data |= MPLL_CLKOUT_SEL(4);
+				if (orig != data)
+					WREG32_SMC(MPLL_BYPASSCLK_SEL, data);
+			}
+		}
+	} else {
+		if (orig != data)
+			WREG32_PCIE_PORT(PCIE_LC_CNTL, data);
+	}
+
+	orig = data = RREG32_PCIE_PORT(PCIE_CNTL2);
+	data |= SLV_MEM_LS_EN | MST_MEM_LS_EN | REPLAY_MEM_LS_EN;
+	if (orig != data)
+		WREG32_PCIE_PORT(PCIE_CNTL2, data);
+
+	if (!disable_l0s) {
+		data = RREG32_PCIE_PORT(PCIE_LC_N_FTS_CNTL);
+		if((data & LC_N_FTS_MASK) == LC_N_FTS_MASK) {
+			data = RREG32_PCIE_PORT(PCIE_LC_STATUS1);
+			if ((data & LC_REVERSE_XMIT) && (data & LC_REVERSE_RCVR)) {
+				orig = data = RREG32_PCIE_PORT(PCIE_LC_CNTL);
+				data &= ~LC_L0S_INACTIVITY_MASK;
+				if (orig != data)
+					WREG32_PCIE_PORT(PCIE_LC_CNTL, data);
+			}
+		}
+	}
 }
diff --git a/drivers/gpu/drm/radeon/cik_reg.h b/drivers/gpu/drm/radeon/cik_reg.h
index d71e46d571f5..ca1bb6133580 100644
--- a/drivers/gpu/drm/radeon/cik_reg.h
+++ b/drivers/gpu/drm/radeon/cik_reg.h
@@ -24,6 +24,9 @@
 #ifndef __CIK_REG_H__
 #define __CIK_REG_H__
 
+#define CIK_DIDT_IND_INDEX                        0xca00
+#define CIK_DIDT_IND_DATA                         0xca04
+
 #define CIK_DC_GPIO_HPD_MASK                      0x65b0
 #define CIK_DC_GPIO_HPD_A                         0x65b4
 #define CIK_DC_GPIO_HPD_EN                        0x65b8
diff --git a/drivers/gpu/drm/radeon/cik_sdma.c b/drivers/gpu/drm/radeon/cik_sdma.c
new file mode 100644
index 000000000000..b6286068e111
--- /dev/null
+++ b/drivers/gpu/drm/radeon/cik_sdma.c
@@ -0,0 +1,785 @@
+/*
+ * Copyright 2013 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: Alex Deucher
+ */
+#include <linux/firmware.h>
+#include <drm/drmP.h>
+#include "radeon.h"
+#include "radeon_asic.h"
+#include "cikd.h"
+
+/* sdma */
+#define CIK_SDMA_UCODE_SIZE 1050
+#define CIK_SDMA_UCODE_VERSION 64
+
+u32 cik_gpu_check_soft_reset(struct radeon_device *rdev);
+
+/*
+ * sDMA - System DMA
+ * Starting with CIK, the GPU has new asynchronous
+ * DMA engines.  These engines are used for compute
+ * and gfx.  There are two DMA engines (SDMA0, SDMA1)
+ * and each one supports 1 ring buffer used for gfx
+ * and 2 queues used for compute.
+ *
+ * The programming model is very similar to the CP
+ * (ring buffer, IBs, etc.), but sDMA has it's own
+ * packet format that is different from the PM4 format
+ * used by the CP. sDMA supports copying data, writing
+ * embedded data, solid fills, and a number of other
+ * things.  It also has support for tiling/detiling of
+ * buffers.
+ */
+
+/**
+ * cik_sdma_ring_ib_execute - Schedule an IB on the DMA engine
+ *
+ * @rdev: radeon_device pointer
+ * @ib: IB object to schedule
+ *
+ * Schedule an IB in the DMA ring (CIK).
+ */
+void cik_sdma_ring_ib_execute(struct radeon_device *rdev,
+			      struct radeon_ib *ib)
+{
+	struct radeon_ring *ring = &rdev->ring[ib->ring];
+	u32 extra_bits = (ib->vm ? ib->vm->id : 0) & 0xf;
+
+	if (rdev->wb.enabled) {
+		u32 next_rptr = ring->wptr + 5;
+		while ((next_rptr & 7) != 4)
+			next_rptr++;
+		next_rptr += 4;
+		radeon_ring_write(ring, SDMA_PACKET(SDMA_OPCODE_WRITE, SDMA_WRITE_SUB_OPCODE_LINEAR, 0));
+		radeon_ring_write(ring, ring->next_rptr_gpu_addr & 0xfffffffc);
+		radeon_ring_write(ring, upper_32_bits(ring->next_rptr_gpu_addr) & 0xffffffff);
+		radeon_ring_write(ring, 1); /* number of DWs to follow */
+		radeon_ring_write(ring, next_rptr);
+	}
+
+	/* IB packet must end on a 8 DW boundary */
+	while ((ring->wptr & 7) != 4)
+		radeon_ring_write(ring, SDMA_PACKET(SDMA_OPCODE_NOP, 0, 0));
+	radeon_ring_write(ring, SDMA_PACKET(SDMA_OPCODE_INDIRECT_BUFFER, 0, extra_bits));
+	radeon_ring_write(ring, ib->gpu_addr & 0xffffffe0); /* base must be 32 byte aligned */
+	radeon_ring_write(ring, upper_32_bits(ib->gpu_addr) & 0xffffffff);
+	radeon_ring_write(ring, ib->length_dw);
+
+}
+
+/**
+ * cik_sdma_fence_ring_emit - emit a fence on the DMA ring
+ *
+ * @rdev: radeon_device pointer
+ * @fence: radeon fence object
+ *
+ * Add a DMA fence packet to the ring to write
+ * the fence seq number and DMA trap packet to generate
+ * an interrupt if needed (CIK).
+ */
+void cik_sdma_fence_ring_emit(struct radeon_device *rdev,
+			      struct radeon_fence *fence)
+{
+	struct radeon_ring *ring = &rdev->ring[fence->ring];
+	u64 addr = rdev->fence_drv[fence->ring].gpu_addr;
+	u32 extra_bits = (SDMA_POLL_REG_MEM_EXTRA_OP(1) |
+			  SDMA_POLL_REG_MEM_EXTRA_FUNC(3)); /* == */
+	u32 ref_and_mask;
+
+	if (fence->ring == R600_RING_TYPE_DMA_INDEX)
+		ref_and_mask = SDMA0;
+	else
+		ref_and_mask = SDMA1;
+
+	/* write the fence */
+	radeon_ring_write(ring, SDMA_PACKET(SDMA_OPCODE_FENCE, 0, 0));
+	radeon_ring_write(ring, addr & 0xffffffff);
+	radeon_ring_write(ring, upper_32_bits(addr) & 0xffffffff);
+	radeon_ring_write(ring, fence->seq);
+	/* generate an interrupt */
+	radeon_ring_write(ring, SDMA_PACKET(SDMA_OPCODE_TRAP, 0, 0));
+	/* flush HDP */
+	radeon_ring_write(ring, SDMA_PACKET(SDMA_OPCODE_POLL_REG_MEM, 0, extra_bits));
+	radeon_ring_write(ring, GPU_HDP_FLUSH_DONE);
+	radeon_ring_write(ring, GPU_HDP_FLUSH_REQ);
+	radeon_ring_write(ring, ref_and_mask); /* REFERENCE */
+	radeon_ring_write(ring, ref_and_mask); /* MASK */
+	radeon_ring_write(ring, (4 << 16) | 10); /* RETRY_COUNT, POLL_INTERVAL */
+}
+
+/**
+ * cik_sdma_semaphore_ring_emit - emit a semaphore on the dma ring
+ *
+ * @rdev: radeon_device pointer
+ * @ring: radeon_ring structure holding ring information
+ * @semaphore: radeon semaphore object
+ * @emit_wait: wait or signal semaphore
+ *
+ * Add a DMA semaphore packet to the ring wait on or signal
+ * other rings (CIK).
+ */
+void cik_sdma_semaphore_ring_emit(struct radeon_device *rdev,
+				  struct radeon_ring *ring,
+				  struct radeon_semaphore *semaphore,
+				  bool emit_wait)
+{
+	u64 addr = semaphore->gpu_addr;
+	u32 extra_bits = emit_wait ? 0 : SDMA_SEMAPHORE_EXTRA_S;
+
+	radeon_ring_write(ring, SDMA_PACKET(SDMA_OPCODE_SEMAPHORE, 0, extra_bits));
+	radeon_ring_write(ring, addr & 0xfffffff8);
+	radeon_ring_write(ring, upper_32_bits(addr) & 0xffffffff);
+}
+
+/**
+ * cik_sdma_gfx_stop - stop the gfx async dma engines
+ *
+ * @rdev: radeon_device pointer
+ *
+ * Stop the gfx async dma ring buffers (CIK).
+ */
+static void cik_sdma_gfx_stop(struct radeon_device *rdev)
+{
+	u32 rb_cntl, reg_offset;
+	int i;
+
+	radeon_ttm_set_active_vram_size(rdev, rdev->mc.visible_vram_size);
+
+	for (i = 0; i < 2; i++) {
+		if (i == 0)
+			reg_offset = SDMA0_REGISTER_OFFSET;
+		else
+			reg_offset = SDMA1_REGISTER_OFFSET;
+		rb_cntl = RREG32(SDMA0_GFX_RB_CNTL + reg_offset);
+		rb_cntl &= ~SDMA_RB_ENABLE;
+		WREG32(SDMA0_GFX_RB_CNTL + reg_offset, rb_cntl);
+		WREG32(SDMA0_GFX_IB_CNTL + reg_offset, 0);
+	}
+}
+
+/**
+ * cik_sdma_rlc_stop - stop the compute async dma engines
+ *
+ * @rdev: radeon_device pointer
+ *
+ * Stop the compute async dma queues (CIK).
+ */
+static void cik_sdma_rlc_stop(struct radeon_device *rdev)
+{
+	/* XXX todo */
+}
+
+/**
+ * cik_sdma_enable - stop the async dma engines
+ *
+ * @rdev: radeon_device pointer
+ * @enable: enable/disable the DMA MEs.
+ *
+ * Halt or unhalt the async dma engines (CIK).
+ */
+void cik_sdma_enable(struct radeon_device *rdev, bool enable)
+{
+	u32 me_cntl, reg_offset;
+	int i;
+
+	for (i = 0; i < 2; i++) {
+		if (i == 0)
+			reg_offset = SDMA0_REGISTER_OFFSET;
+		else
+			reg_offset = SDMA1_REGISTER_OFFSET;
+		me_cntl = RREG32(SDMA0_ME_CNTL + reg_offset);
+		if (enable)
+			me_cntl &= ~SDMA_HALT;
+		else
+			me_cntl |= SDMA_HALT;
+		WREG32(SDMA0_ME_CNTL + reg_offset, me_cntl);
+	}
+}
+
+/**
+ * cik_sdma_gfx_resume - setup and start the async dma engines
+ *
+ * @rdev: radeon_device pointer
+ *
+ * Set up the gfx DMA ring buffers and enable them (CIK).
+ * Returns 0 for success, error for failure.
+ */
+static int cik_sdma_gfx_resume(struct radeon_device *rdev)
+{
+	struct radeon_ring *ring;
+	u32 rb_cntl, ib_cntl;
+	u32 rb_bufsz;
+	u32 reg_offset, wb_offset;
+	int i, r;
+
+	for (i = 0; i < 2; i++) {
+		if (i == 0) {
+			ring = &rdev->ring[R600_RING_TYPE_DMA_INDEX];
+			reg_offset = SDMA0_REGISTER_OFFSET;
+			wb_offset = R600_WB_DMA_RPTR_OFFSET;
+		} else {
+			ring = &rdev->ring[CAYMAN_RING_TYPE_DMA1_INDEX];
+			reg_offset = SDMA1_REGISTER_OFFSET;
+			wb_offset = CAYMAN_WB_DMA1_RPTR_OFFSET;
+		}
+
+		WREG32(SDMA0_SEM_INCOMPLETE_TIMER_CNTL + reg_offset, 0);
+		WREG32(SDMA0_SEM_WAIT_FAIL_TIMER_CNTL + reg_offset, 0);
+
+		/* Set ring buffer size in dwords */
+		rb_bufsz = order_base_2(ring->ring_size / 4);
+		rb_cntl = rb_bufsz << 1;
+#ifdef __BIG_ENDIAN
+		rb_cntl |= SDMA_RB_SWAP_ENABLE | SDMA_RPTR_WRITEBACK_SWAP_ENABLE;
+#endif
+		WREG32(SDMA0_GFX_RB_CNTL + reg_offset, rb_cntl);
+
+		/* Initialize the ring buffer's read and write pointers */
+		WREG32(SDMA0_GFX_RB_RPTR + reg_offset, 0);
+		WREG32(SDMA0_GFX_RB_WPTR + reg_offset, 0);
+
+		/* set the wb address whether it's enabled or not */
+		WREG32(SDMA0_GFX_RB_RPTR_ADDR_HI + reg_offset,
+		       upper_32_bits(rdev->wb.gpu_addr + wb_offset) & 0xFFFFFFFF);
+		WREG32(SDMA0_GFX_RB_RPTR_ADDR_LO + reg_offset,
+		       ((rdev->wb.gpu_addr + wb_offset) & 0xFFFFFFFC));
+
+		if (rdev->wb.enabled)
+			rb_cntl |= SDMA_RPTR_WRITEBACK_ENABLE;
+
+		WREG32(SDMA0_GFX_RB_BASE + reg_offset, ring->gpu_addr >> 8);
+		WREG32(SDMA0_GFX_RB_BASE_HI + reg_offset, ring->gpu_addr >> 40);
+
+		ring->wptr = 0;
+		WREG32(SDMA0_GFX_RB_WPTR + reg_offset, ring->wptr << 2);
+
+		ring->rptr = RREG32(SDMA0_GFX_RB_RPTR + reg_offset) >> 2;
+
+		/* enable DMA RB */
+		WREG32(SDMA0_GFX_RB_CNTL + reg_offset, rb_cntl | SDMA_RB_ENABLE);
+
+		ib_cntl = SDMA_IB_ENABLE;
+#ifdef __BIG_ENDIAN
+		ib_cntl |= SDMA_IB_SWAP_ENABLE;
+#endif
+		/* enable DMA IBs */
+		WREG32(SDMA0_GFX_IB_CNTL + reg_offset, ib_cntl);
+
+		ring->ready = true;
+
+		r = radeon_ring_test(rdev, ring->idx, ring);
+		if (r) {
+			ring->ready = false;
+			return r;
+		}
+	}
+
+	radeon_ttm_set_active_vram_size(rdev, rdev->mc.real_vram_size);
+
+	return 0;
+}
+
+/**
+ * cik_sdma_rlc_resume - setup and start the async dma engines
+ *
+ * @rdev: radeon_device pointer
+ *
+ * Set up the compute DMA queues and enable them (CIK).
+ * Returns 0 for success, error for failure.
+ */
+static int cik_sdma_rlc_resume(struct radeon_device *rdev)
+{
+	/* XXX todo */
+	return 0;
+}
+
+/**
+ * cik_sdma_load_microcode - load the sDMA ME ucode
+ *
+ * @rdev: radeon_device pointer
+ *
+ * Loads the sDMA0/1 ucode.
+ * Returns 0 for success, -EINVAL if the ucode is not available.
+ */
+static int cik_sdma_load_microcode(struct radeon_device *rdev)
+{
+	const __be32 *fw_data;
+	int i;
+
+	if (!rdev->sdma_fw)
+		return -EINVAL;
+
+	/* stop the gfx rings and rlc compute queues */
+	cik_sdma_gfx_stop(rdev);
+	cik_sdma_rlc_stop(rdev);
+
+	/* halt the MEs */
+	cik_sdma_enable(rdev, false);
+
+	/* sdma0 */
+	fw_data = (const __be32 *)rdev->sdma_fw->data;
+	WREG32(SDMA0_UCODE_ADDR + SDMA0_REGISTER_OFFSET, 0);
+	for (i = 0; i < CIK_SDMA_UCODE_SIZE; i++)
+		WREG32(SDMA0_UCODE_DATA + SDMA0_REGISTER_OFFSET, be32_to_cpup(fw_data++));
+	WREG32(SDMA0_UCODE_DATA + SDMA0_REGISTER_OFFSET, CIK_SDMA_UCODE_VERSION);
+
+	/* sdma1 */
+	fw_data = (const __be32 *)rdev->sdma_fw->data;
+	WREG32(SDMA0_UCODE_ADDR + SDMA1_REGISTER_OFFSET, 0);
+	for (i = 0; i < CIK_SDMA_UCODE_SIZE; i++)
+		WREG32(SDMA0_UCODE_DATA + SDMA1_REGISTER_OFFSET, be32_to_cpup(fw_data++));
+	WREG32(SDMA0_UCODE_DATA + SDMA1_REGISTER_OFFSET, CIK_SDMA_UCODE_VERSION);
+
+	WREG32(SDMA0_UCODE_ADDR + SDMA0_REGISTER_OFFSET, 0);
+	WREG32(SDMA0_UCODE_ADDR + SDMA1_REGISTER_OFFSET, 0);
+	return 0;
+}
+
+/**
+ * cik_sdma_resume - setup and start the async dma engines
+ *
+ * @rdev: radeon_device pointer
+ *
+ * Set up the DMA engines and enable them (CIK).
+ * Returns 0 for success, error for failure.
+ */
+int cik_sdma_resume(struct radeon_device *rdev)
+{
+	int r;
+
+	/* Reset dma */
+	WREG32(SRBM_SOFT_RESET, SOFT_RESET_SDMA | SOFT_RESET_SDMA1);
+	RREG32(SRBM_SOFT_RESET);
+	udelay(50);
+	WREG32(SRBM_SOFT_RESET, 0);
+	RREG32(SRBM_SOFT_RESET);
+
+	r = cik_sdma_load_microcode(rdev);
+	if (r)
+		return r;
+
+	/* unhalt the MEs */
+	cik_sdma_enable(rdev, true);
+
+	/* start the gfx rings and rlc compute queues */
+	r = cik_sdma_gfx_resume(rdev);
+	if (r)
+		return r;
+	r = cik_sdma_rlc_resume(rdev);
+	if (r)
+		return r;
+
+	return 0;
+}
+
+/**
+ * cik_sdma_fini - tear down the async dma engines
+ *
+ * @rdev: radeon_device pointer
+ *
+ * Stop the async dma engines and free the rings (CIK).
+ */
+void cik_sdma_fini(struct radeon_device *rdev)
+{
+	/* stop the gfx rings and rlc compute queues */
+	cik_sdma_gfx_stop(rdev);
+	cik_sdma_rlc_stop(rdev);
+	/* halt the MEs */
+	cik_sdma_enable(rdev, false);
+	radeon_ring_fini(rdev, &rdev->ring[R600_RING_TYPE_DMA_INDEX]);
+	radeon_ring_fini(rdev, &rdev->ring[CAYMAN_RING_TYPE_DMA1_INDEX]);
+	/* XXX - compute dma queue tear down */
+}
+
+/**
+ * cik_copy_dma - copy pages using the DMA engine
+ *
+ * @rdev: radeon_device pointer
+ * @src_offset: src GPU address
+ * @dst_offset: dst GPU address
+ * @num_gpu_pages: number of GPU pages to xfer
+ * @fence: radeon fence object
+ *
+ * Copy GPU paging using the DMA engine (CIK).
+ * Used by the radeon ttm implementation to move pages if
+ * registered as the asic copy callback.
+ */
+int cik_copy_dma(struct radeon_device *rdev,
+		 uint64_t src_offset, uint64_t dst_offset,
+		 unsigned num_gpu_pages,
+		 struct radeon_fence **fence)
+{
+	struct radeon_semaphore *sem = NULL;
+	int ring_index = rdev->asic->copy.dma_ring_index;
+	struct radeon_ring *ring = &rdev->ring[ring_index];
+	u32 size_in_bytes, cur_size_in_bytes;
+	int i, num_loops;
+	int r = 0;
+
+	r = radeon_semaphore_create(rdev, &sem);
+	if (r) {
+		DRM_ERROR("radeon: moving bo (%d).\n", r);
+		return r;
+	}
+
+	size_in_bytes = (num_gpu_pages << RADEON_GPU_PAGE_SHIFT);
+	num_loops = DIV_ROUND_UP(size_in_bytes, 0x1fffff);
+	r = radeon_ring_lock(rdev, ring, num_loops * 7 + 14);
+	if (r) {
+		DRM_ERROR("radeon: moving bo (%d).\n", r);
+		radeon_semaphore_free(rdev, &sem, NULL);
+		return r;
+	}
+
+	if (radeon_fence_need_sync(*fence, ring->idx)) {
+		radeon_semaphore_sync_rings(rdev, sem, (*fence)->ring,
+					    ring->idx);
+		radeon_fence_note_sync(*fence, ring->idx);
+	} else {
+		radeon_semaphore_free(rdev, &sem, NULL);
+	}
+
+	for (i = 0; i < num_loops; i++) {
+		cur_size_in_bytes = size_in_bytes;
+		if (cur_size_in_bytes > 0x1fffff)
+			cur_size_in_bytes = 0x1fffff;
+		size_in_bytes -= cur_size_in_bytes;
+		radeon_ring_write(ring, SDMA_PACKET(SDMA_OPCODE_COPY, SDMA_COPY_SUB_OPCODE_LINEAR, 0));
+		radeon_ring_write(ring, cur_size_in_bytes);
+		radeon_ring_write(ring, 0); /* src/dst endian swap */
+		radeon_ring_write(ring, src_offset & 0xffffffff);
+		radeon_ring_write(ring, upper_32_bits(src_offset) & 0xffffffff);
+		radeon_ring_write(ring, dst_offset & 0xfffffffc);
+		radeon_ring_write(ring, upper_32_bits(dst_offset) & 0xffffffff);
+		src_offset += cur_size_in_bytes;
+		dst_offset += cur_size_in_bytes;
+	}
+
+	r = radeon_fence_emit(rdev, fence, ring->idx);
+	if (r) {
+		radeon_ring_unlock_undo(rdev, ring);
+		return r;
+	}
+
+	radeon_ring_unlock_commit(rdev, ring);
+	radeon_semaphore_free(rdev, &sem, *fence);
+
+	return r;
+}
+
+/**
+ * cik_sdma_ring_test - simple async dma engine test
+ *
+ * @rdev: radeon_device pointer
+ * @ring: radeon_ring structure holding ring information
+ *
+ * Test the DMA engine by writing using it to write an
+ * value to memory. (CIK).
+ * Returns 0 for success, error for failure.
+ */
+int cik_sdma_ring_test(struct radeon_device *rdev,
+		       struct radeon_ring *ring)
+{
+	unsigned i;
+	int r;
+	void __iomem *ptr = (void *)rdev->vram_scratch.ptr;
+	u32 tmp;
+
+	if (!ptr) {
+		DRM_ERROR("invalid vram scratch pointer\n");
+		return -EINVAL;
+	}
+
+	tmp = 0xCAFEDEAD;
+	writel(tmp, ptr);
+
+	r = radeon_ring_lock(rdev, ring, 4);
+	if (r) {
+		DRM_ERROR("radeon: dma failed to lock ring %d (%d).\n", ring->idx, r);
+		return r;
+	}
+	radeon_ring_write(ring, SDMA_PACKET(SDMA_OPCODE_WRITE, SDMA_WRITE_SUB_OPCODE_LINEAR, 0));
+	radeon_ring_write(ring, rdev->vram_scratch.gpu_addr & 0xfffffffc);
+	radeon_ring_write(ring, upper_32_bits(rdev->vram_scratch.gpu_addr) & 0xffffffff);
+	radeon_ring_write(ring, 1); /* number of DWs to follow */
+	radeon_ring_write(ring, 0xDEADBEEF);
+	radeon_ring_unlock_commit(rdev, ring);
+
+	for (i = 0; i < rdev->usec_timeout; i++) {
+		tmp = readl(ptr);
+		if (tmp == 0xDEADBEEF)
+			break;
+		DRM_UDELAY(1);
+	}
+
+	if (i < rdev->usec_timeout) {
+		DRM_INFO("ring test on %d succeeded in %d usecs\n", ring->idx, i);
+	} else {
+		DRM_ERROR("radeon: ring %d test failed (0x%08X)\n",
+			  ring->idx, tmp);
+		r = -EINVAL;
+	}
+	return r;
+}
+
+/**
+ * cik_sdma_ib_test - test an IB on the DMA engine
+ *
+ * @rdev: radeon_device pointer
+ * @ring: radeon_ring structure holding ring information
+ *
+ * Test a simple IB in the DMA ring (CIK).
+ * Returns 0 on success, error on failure.
+ */
+int cik_sdma_ib_test(struct radeon_device *rdev, struct radeon_ring *ring)
+{
+	struct radeon_ib ib;
+	unsigned i;
+	int r;
+	void __iomem *ptr = (void *)rdev->vram_scratch.ptr;
+	u32 tmp = 0;
+
+	if (!ptr) {
+		DRM_ERROR("invalid vram scratch pointer\n");
+		return -EINVAL;
+	}
+
+	tmp = 0xCAFEDEAD;
+	writel(tmp, ptr);
+
+	r = radeon_ib_get(rdev, ring->idx, &ib, NULL, 256);
+	if (r) {
+		DRM_ERROR("radeon: failed to get ib (%d).\n", r);
+		return r;
+	}
+
+	ib.ptr[0] = SDMA_PACKET(SDMA_OPCODE_WRITE, SDMA_WRITE_SUB_OPCODE_LINEAR, 0);
+	ib.ptr[1] = rdev->vram_scratch.gpu_addr & 0xfffffffc;
+	ib.ptr[2] = upper_32_bits(rdev->vram_scratch.gpu_addr) & 0xffffffff;
+	ib.ptr[3] = 1;
+	ib.ptr[4] = 0xDEADBEEF;
+	ib.length_dw = 5;
+
+	r = radeon_ib_schedule(rdev, &ib, NULL);
+	if (r) {
+		radeon_ib_free(rdev, &ib);
+		DRM_ERROR("radeon: failed to schedule ib (%d).\n", r);
+		return r;
+	}
+	r = radeon_fence_wait(ib.fence, false);
+	if (r) {
+		DRM_ERROR("radeon: fence wait failed (%d).\n", r);
+		return r;
+	}
+	for (i = 0; i < rdev->usec_timeout; i++) {
+		tmp = readl(ptr);
+		if (tmp == 0xDEADBEEF)
+			break;
+		DRM_UDELAY(1);
+	}
+	if (i < rdev->usec_timeout) {
+		DRM_INFO("ib test on ring %d succeeded in %u usecs\n", ib.fence->ring, i);
+	} else {
+		DRM_ERROR("radeon: ib test failed (0x%08X)\n", tmp);
+		r = -EINVAL;
+	}
+	radeon_ib_free(rdev, &ib);
+	return r;
+}
+
+/**
+ * cik_sdma_is_lockup - Check if the DMA engine is locked up
+ *
+ * @rdev: radeon_device pointer
+ * @ring: radeon_ring structure holding ring information
+ *
+ * Check if the async DMA engine is locked up (CIK).
+ * Returns true if the engine appears to be locked up, false if not.
+ */
+bool cik_sdma_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
+{
+	u32 reset_mask = cik_gpu_check_soft_reset(rdev);
+	u32 mask;
+
+	if (ring->idx == R600_RING_TYPE_DMA_INDEX)
+		mask = RADEON_RESET_DMA;
+	else
+		mask = RADEON_RESET_DMA1;
+
+	if (!(reset_mask & mask)) {
+		radeon_ring_lockup_update(ring);
+		return false;
+	}
+	/* force ring activities */
+	radeon_ring_force_activity(rdev, ring);
+	return radeon_ring_test_lockup(rdev, ring);
+}
+
+/**
+ * cik_sdma_vm_set_page - update the page tables using sDMA
+ *
+ * @rdev: radeon_device pointer
+ * @ib: indirect buffer to fill with commands
+ * @pe: addr of the page entry
+ * @addr: dst addr to write into pe
+ * @count: number of page entries to update
+ * @incr: increase next addr by incr bytes
+ * @flags: access flags
+ *
+ * Update the page tables using sDMA (CIK).
+ */
+void cik_sdma_vm_set_page(struct radeon_device *rdev,
+			  struct radeon_ib *ib,
+			  uint64_t pe,
+			  uint64_t addr, unsigned count,
+			  uint32_t incr, uint32_t flags)
+{
+	uint32_t r600_flags = cayman_vm_page_flags(rdev, flags);
+	uint64_t value;
+	unsigned ndw;
+
+	if (flags & RADEON_VM_PAGE_SYSTEM) {
+		while (count) {
+			ndw = count * 2;
+			if (ndw > 0xFFFFE)
+				ndw = 0xFFFFE;
+
+			/* for non-physically contiguous pages (system) */
+			ib->ptr[ib->length_dw++] = SDMA_PACKET(SDMA_OPCODE_WRITE, SDMA_WRITE_SUB_OPCODE_LINEAR, 0);
+			ib->ptr[ib->length_dw++] = pe;
+			ib->ptr[ib->length_dw++] = upper_32_bits(pe);
+			ib->ptr[ib->length_dw++] = ndw;
+			for (; ndw > 0; ndw -= 2, --count, pe += 8) {
+				if (flags & RADEON_VM_PAGE_SYSTEM) {
+					value = radeon_vm_map_gart(rdev, addr);
+					value &= 0xFFFFFFFFFFFFF000ULL;
+				} else if (flags & RADEON_VM_PAGE_VALID) {
+					value = addr;
+				} else {
+					value = 0;
+				}
+				addr += incr;
+				value |= r600_flags;
+				ib->ptr[ib->length_dw++] = value;
+				ib->ptr[ib->length_dw++] = upper_32_bits(value);
+			}
+		}
+	} else {
+		while (count) {
+			ndw = count;
+			if (ndw > 0x7FFFF)
+				ndw = 0x7FFFF;
+
+			if (flags & RADEON_VM_PAGE_VALID)
+				value = addr;
+			else
+				value = 0;
+			/* for physically contiguous pages (vram) */
+			ib->ptr[ib->length_dw++] = SDMA_PACKET(SDMA_OPCODE_GENERATE_PTE_PDE, 0, 0);
+			ib->ptr[ib->length_dw++] = pe; /* dst addr */
+			ib->ptr[ib->length_dw++] = upper_32_bits(pe);
+			ib->ptr[ib->length_dw++] = r600_flags; /* mask */
+			ib->ptr[ib->length_dw++] = 0;
+			ib->ptr[ib->length_dw++] = value; /* value */
+			ib->ptr[ib->length_dw++] = upper_32_bits(value);
+			ib->ptr[ib->length_dw++] = incr; /* increment size */
+			ib->ptr[ib->length_dw++] = 0;
+			ib->ptr[ib->length_dw++] = ndw; /* number of entries */
+			pe += ndw * 8;
+			addr += ndw * incr;
+			count -= ndw;
+		}
+	}
+	while (ib->length_dw & 0x7)
+		ib->ptr[ib->length_dw++] = SDMA_PACKET(SDMA_OPCODE_NOP, 0, 0);
+}
+
+/**
+ * cik_dma_vm_flush - cik vm flush using sDMA
+ *
+ * @rdev: radeon_device pointer
+ *
+ * Update the page table base and flush the VM TLB
+ * using sDMA (CIK).
+ */
+void cik_dma_vm_flush(struct radeon_device *rdev, int ridx, struct radeon_vm *vm)
+{
+	struct radeon_ring *ring = &rdev->ring[ridx];
+	u32 extra_bits = (SDMA_POLL_REG_MEM_EXTRA_OP(1) |
+			  SDMA_POLL_REG_MEM_EXTRA_FUNC(3)); /* == */
+	u32 ref_and_mask;
+
+	if (vm == NULL)
+		return;
+
+	if (ridx == R600_RING_TYPE_DMA_INDEX)
+		ref_and_mask = SDMA0;
+	else
+		ref_and_mask = SDMA1;
+
+	radeon_ring_write(ring, SDMA_PACKET(SDMA_OPCODE_SRBM_WRITE, 0, 0xf000));
+	if (vm->id < 8) {
+		radeon_ring_write(ring, (VM_CONTEXT0_PAGE_TABLE_BASE_ADDR + (vm->id << 2)) >> 2);
+	} else {
+		radeon_ring_write(ring, (VM_CONTEXT8_PAGE_TABLE_BASE_ADDR + ((vm->id - 8) << 2)) >> 2);
+	}
+	radeon_ring_write(ring, vm->pd_gpu_addr >> 12);
+
+	/* update SH_MEM_* regs */
+	radeon_ring_write(ring, SDMA_PACKET(SDMA_OPCODE_SRBM_WRITE, 0, 0xf000));
+	radeon_ring_write(ring, SRBM_GFX_CNTL >> 2);
+	radeon_ring_write(ring, VMID(vm->id));
+
+	radeon_ring_write(ring, SDMA_PACKET(SDMA_OPCODE_SRBM_WRITE, 0, 0xf000));
+	radeon_ring_write(ring, SH_MEM_BASES >> 2);
+	radeon_ring_write(ring, 0);
+
+	radeon_ring_write(ring, SDMA_PACKET(SDMA_OPCODE_SRBM_WRITE, 0, 0xf000));
+	radeon_ring_write(ring, SH_MEM_CONFIG >> 2);
+	radeon_ring_write(ring, 0);
+
+	radeon_ring_write(ring, SDMA_PACKET(SDMA_OPCODE_SRBM_WRITE, 0, 0xf000));
+	radeon_ring_write(ring, SH_MEM_APE1_BASE >> 2);
+	radeon_ring_write(ring, 1);
+
+	radeon_ring_write(ring, SDMA_PACKET(SDMA_OPCODE_SRBM_WRITE, 0, 0xf000));
+	radeon_ring_write(ring, SH_MEM_APE1_LIMIT >> 2);
+	radeon_ring_write(ring, 0);
+
+	radeon_ring_write(ring, SDMA_PACKET(SDMA_OPCODE_SRBM_WRITE, 0, 0xf000));
+	radeon_ring_write(ring, SRBM_GFX_CNTL >> 2);
+	radeon_ring_write(ring, VMID(0));
+
+	/* flush HDP */
+	radeon_ring_write(ring, SDMA_PACKET(SDMA_OPCODE_POLL_REG_MEM, 0, extra_bits));
+	radeon_ring_write(ring, GPU_HDP_FLUSH_DONE);
+	radeon_ring_write(ring, GPU_HDP_FLUSH_REQ);
+	radeon_ring_write(ring, ref_and_mask); /* REFERENCE */
+	radeon_ring_write(ring, ref_and_mask); /* MASK */
+	radeon_ring_write(ring, (4 << 16) | 10); /* RETRY_COUNT, POLL_INTERVAL */
+
+	/* flush TLB */
+	radeon_ring_write(ring, SDMA_PACKET(SDMA_OPCODE_SRBM_WRITE, 0, 0xf000));
+	radeon_ring_write(ring, VM_INVALIDATE_REQUEST >> 2);
+	radeon_ring_write(ring, 1 << vm->id);
+}
+
diff --git a/drivers/gpu/drm/radeon/cikd.h b/drivers/gpu/drm/radeon/cikd.h
index 7e9275eaef80..203d2a09a1f5 100644
--- a/drivers/gpu/drm/radeon/cikd.h
+++ b/drivers/gpu/drm/radeon/cikd.h
@@ -28,21 +28,375 @@
 
 #define CIK_RB_BITMAP_WIDTH_PER_SH  2
 
+/* DIDT IND registers */
+#define DIDT_SQ_CTRL0                                     0x0
+#       define DIDT_CTRL_EN                               (1 << 0)
+#define DIDT_DB_CTRL0                                     0x20
+#define DIDT_TD_CTRL0                                     0x40
+#define DIDT_TCP_CTRL0                                    0x60
+
 /* SMC IND registers */
+#define DPM_TABLE_475                                     0x3F768
+#       define SamuBootLevel(x)                           ((x) << 0)
+#       define SamuBootLevel_MASK                         0x000000ff
+#       define SamuBootLevel_SHIFT                        0
+#       define AcpBootLevel(x)                            ((x) << 8)
+#       define AcpBootLevel_MASK                          0x0000ff00
+#       define AcpBootLevel_SHIFT                         8
+#       define VceBootLevel(x)                            ((x) << 16)
+#       define VceBootLevel_MASK                          0x00ff0000
+#       define VceBootLevel_SHIFT                         16
+#       define UvdBootLevel(x)                            ((x) << 24)
+#       define UvdBootLevel_MASK                          0xff000000
+#       define UvdBootLevel_SHIFT                         24
+
+#define FIRMWARE_FLAGS                                    0x3F800
+#       define INTERRUPTS_ENABLED                         (1 << 0)
+
+#define NB_DPM_CONFIG_1                                   0x3F9E8
+#       define Dpm0PgNbPsLo(x)                            ((x) << 0)
+#       define Dpm0PgNbPsLo_MASK                          0x000000ff
+#       define Dpm0PgNbPsLo_SHIFT                         0
+#       define Dpm0PgNbPsHi(x)                            ((x) << 8)
+#       define Dpm0PgNbPsHi_MASK                          0x0000ff00
+#       define Dpm0PgNbPsHi_SHIFT                         8
+#       define DpmXNbPsLo(x)                              ((x) << 16)
+#       define DpmXNbPsLo_MASK                            0x00ff0000
+#       define DpmXNbPsLo_SHIFT                           16
+#       define DpmXNbPsHi(x)                              ((x) << 24)
+#       define DpmXNbPsHi_MASK                            0xff000000
+#       define DpmXNbPsHi_SHIFT                           24
+
+#define	SMC_SYSCON_RESET_CNTL				0x80000000
+#       define RST_REG                                  (1 << 0)
+#define	SMC_SYSCON_CLOCK_CNTL_0				0x80000004
+#       define CK_DISABLE                               (1 << 0)
+#       define CKEN                                     (1 << 24)
+
+#define	SMC_SYSCON_MISC_CNTL				0x80000010
+
+#define SMC_SYSCON_MSG_ARG_0                              0x80000068
+
+#define SMC_PC_C                                          0x80000370
+
+#define SMC_SCRATCH9                                      0x80000424
+
+#define RCU_UC_EVENTS                                     0xC0000004
+#       define BOOT_SEQ_DONE                              (1 << 7)
+
 #define GENERAL_PWRMGT                                    0xC0200000
+#       define GLOBAL_PWRMGT_EN                           (1 << 0)
+#       define STATIC_PM_EN                               (1 << 1)
+#       define THERMAL_PROTECTION_DIS                     (1 << 2)
+#       define THERMAL_PROTECTION_TYPE                    (1 << 3)
+#       define SW_SMIO_INDEX(x)                           ((x) << 6)
+#       define SW_SMIO_INDEX_MASK                         (1 << 6)
+#       define SW_SMIO_INDEX_SHIFT                        6
+#       define VOLT_PWRMGT_EN                             (1 << 10)
 #       define GPU_COUNTER_CLK                            (1 << 15)
-
+#       define DYN_SPREAD_SPECTRUM_EN                     (1 << 23)
+
+#define CNB_PWRMGT_CNTL                                   0xC0200004
+#       define GNB_SLOW_MODE(x)                           ((x) << 0)
+#       define GNB_SLOW_MODE_MASK                         (3 << 0)
+#       define GNB_SLOW_MODE_SHIFT                        0
+#       define GNB_SLOW                                   (1 << 2)
+#       define FORCE_NB_PS1                               (1 << 3)
+#       define DPM_ENABLED                                (1 << 4)
+
+#define SCLK_PWRMGT_CNTL                                  0xC0200008
+#       define SCLK_PWRMGT_OFF                            (1 << 0)
+#       define RESET_BUSY_CNT                             (1 << 4)
+#       define RESET_SCLK_CNT                             (1 << 5)
+#       define DYNAMIC_PM_EN                              (1 << 21)
+
+#define TARGET_AND_CURRENT_PROFILE_INDEX                  0xC0200014
+#       define CURRENT_STATE_MASK                         (0xf << 4)
+#       define CURRENT_STATE_SHIFT                        4
+#       define CURR_MCLK_INDEX_MASK                       (0xf << 8)
+#       define CURR_MCLK_INDEX_SHIFT                      8
+#       define CURR_SCLK_INDEX_MASK                       (0x1f << 16)
+#       define CURR_SCLK_INDEX_SHIFT                      16
+
+#define CG_SSP                                            0xC0200044
+#       define SST(x)                                     ((x) << 0)
+#       define SST_MASK                                   (0xffff << 0)
+#       define SSTU(x)                                    ((x) << 16)
+#       define SSTU_MASK                                  (0xf << 16)
+
+#define CG_DISPLAY_GAP_CNTL                               0xC0200060
+#       define DISP_GAP(x)                                ((x) << 0)
+#       define DISP_GAP_MASK                              (3 << 0)
+#       define VBI_TIMER_COUNT(x)                         ((x) << 4)
+#       define VBI_TIMER_COUNT_MASK                       (0x3fff << 4)
+#       define VBI_TIMER_UNIT(x)                          ((x) << 20)
+#       define VBI_TIMER_UNIT_MASK                        (7 << 20)
+#       define DISP_GAP_MCHG(x)                           ((x) << 24)
+#       define DISP_GAP_MCHG_MASK                         (3 << 24)
+
+#define SMU_VOLTAGE_STATUS                                0xC0200094
+#       define SMU_VOLTAGE_CURRENT_LEVEL_MASK             (0xff << 1)
+#       define SMU_VOLTAGE_CURRENT_LEVEL_SHIFT            1
+
+#define TARGET_AND_CURRENT_PROFILE_INDEX_1                0xC02000F0
+#       define CURR_PCIE_INDEX_MASK                       (0xf << 24)
+#       define CURR_PCIE_INDEX_SHIFT                      24
+
+#define CG_ULV_PARAMETER                                  0xC0200158
+
+#define CG_FTV_0                                          0xC02001A8
+#define CG_FTV_1                                          0xC02001AC
+#define CG_FTV_2                                          0xC02001B0
+#define CG_FTV_3                                          0xC02001B4
+#define CG_FTV_4                                          0xC02001B8
+#define CG_FTV_5                                          0xC02001BC
+#define CG_FTV_6                                          0xC02001C0
+#define CG_FTV_7                                          0xC02001C4
+
+#define CG_DISPLAY_GAP_CNTL2                              0xC0200230
+
+#define LCAC_SX0_OVR_SEL                                  0xC0400D04
+#define LCAC_SX0_OVR_VAL                                  0xC0400D08
+
+#define LCAC_MC0_CNTL                                     0xC0400D30
+#define LCAC_MC0_OVR_SEL                                  0xC0400D34
+#define LCAC_MC0_OVR_VAL                                  0xC0400D38
+#define LCAC_MC1_CNTL                                     0xC0400D3C
+#define LCAC_MC1_OVR_SEL                                  0xC0400D40
+#define LCAC_MC1_OVR_VAL                                  0xC0400D44
+
+#define LCAC_MC2_OVR_SEL                                  0xC0400D4C
+#define LCAC_MC2_OVR_VAL                                  0xC0400D50
+
+#define LCAC_MC3_OVR_SEL                                  0xC0400D58
+#define LCAC_MC3_OVR_VAL                                  0xC0400D5C
+
+#define LCAC_CPL_CNTL                                     0xC0400D80
+#define LCAC_CPL_OVR_SEL                                  0xC0400D84
+#define LCAC_CPL_OVR_VAL                                  0xC0400D88
+
+/* dGPU */
+#define	CG_THERMAL_CTRL					0xC0300004
+#define 	DPM_EVENT_SRC(x)			((x) << 0)
+#define 	DPM_EVENT_SRC_MASK			(7 << 0)
+#define		DIG_THERM_DPM(x)			((x) << 14)
+#define		DIG_THERM_DPM_MASK			0x003FC000
+#define		DIG_THERM_DPM_SHIFT			14
+
+#define	CG_THERMAL_INT					0xC030000C
+#define		CI_DIG_THERM_INTH(x)			((x) << 8)
+#define		CI_DIG_THERM_INTH_MASK			0x0000FF00
+#define		CI_DIG_THERM_INTH_SHIFT			8
+#define		CI_DIG_THERM_INTL(x)			((x) << 16)
+#define		CI_DIG_THERM_INTL_MASK			0x00FF0000
+#define		CI_DIG_THERM_INTL_SHIFT			16
+#define 	THERM_INT_MASK_HIGH			(1 << 24)
+#define 	THERM_INT_MASK_LOW			(1 << 25)
+
+#define	CG_MULT_THERMAL_STATUS				0xC0300014
+#define		ASIC_MAX_TEMP(x)			((x) << 0)
+#define		ASIC_MAX_TEMP_MASK			0x000001ff
+#define		ASIC_MAX_TEMP_SHIFT			0
+#define		CTF_TEMP(x)				((x) << 9)
+#define		CTF_TEMP_MASK				0x0003fe00
+#define		CTF_TEMP_SHIFT				9
+
+#define	CG_SPLL_FUNC_CNTL				0xC0500140
+#define		SPLL_RESET				(1 << 0)
+#define		SPLL_PWRON				(1 << 1)
+#define		SPLL_BYPASS_EN				(1 << 3)
+#define		SPLL_REF_DIV(x)				((x) << 5)
+#define		SPLL_REF_DIV_MASK			(0x3f << 5)
+#define		SPLL_PDIV_A(x)				((x) << 20)
+#define		SPLL_PDIV_A_MASK			(0x7f << 20)
+#define		SPLL_PDIV_A_SHIFT			20
+#define	CG_SPLL_FUNC_CNTL_2				0xC0500144
+#define		SCLK_MUX_SEL(x)				((x) << 0)
+#define		SCLK_MUX_SEL_MASK			(0x1ff << 0)
+#define	CG_SPLL_FUNC_CNTL_3				0xC0500148
+#define		SPLL_FB_DIV(x)				((x) << 0)
+#define		SPLL_FB_DIV_MASK			(0x3ffffff << 0)
+#define		SPLL_FB_DIV_SHIFT			0
+#define		SPLL_DITHEN				(1 << 28)
+#define	CG_SPLL_FUNC_CNTL_4				0xC050014C
+
+#define	CG_SPLL_SPREAD_SPECTRUM				0xC0500164
+#define		SSEN					(1 << 0)
+#define		CLK_S(x)				((x) << 4)
+#define		CLK_S_MASK				(0xfff << 4)
+#define		CLK_S_SHIFT				4
+#define	CG_SPLL_SPREAD_SPECTRUM_2			0xC0500168
+#define		CLK_V(x)				((x) << 0)
+#define		CLK_V_MASK				(0x3ffffff << 0)
+#define		CLK_V_SHIFT				0
+
+#define	MPLL_BYPASSCLK_SEL				0xC050019C
+#	define MPLL_CLKOUT_SEL(x)			((x) << 8)
+#	define MPLL_CLKOUT_SEL_MASK			0xFF00
 #define CG_CLKPIN_CNTL                                    0xC05001A0
 #       define XTALIN_DIVIDE                              (1 << 1)
-
+#       define BCLK_AS_XCLK                               (1 << 2)
+#define CG_CLKPIN_CNTL_2                                  0xC05001A4
+#       define FORCE_BIF_REFCLK_EN                        (1 << 3)
+#       define MUX_TCLK_TO_XCLK                           (1 << 8)
+#define	THM_CLK_CNTL					0xC05001A8
+#	define CMON_CLK_SEL(x)				((x) << 0)
+#	define CMON_CLK_SEL_MASK			0xFF
+#	define TMON_CLK_SEL(x)				((x) << 8)
+#	define TMON_CLK_SEL_MASK			0xFF00
+#define	MISC_CLK_CTRL					0xC05001AC
+#	define DEEP_SLEEP_CLK_SEL(x)			((x) << 0)
+#	define DEEP_SLEEP_CLK_SEL_MASK			0xFF
+#	define ZCLK_SEL(x)				((x) << 8)
+#	define ZCLK_SEL_MASK				0xFF00
+
+/* KV/KB */
+#define	CG_THERMAL_INT_CTRL				0xC2100028
+#define		DIG_THERM_INTH(x)			((x) << 0)
+#define		DIG_THERM_INTH_MASK			0x000000FF
+#define		DIG_THERM_INTH_SHIFT			0
+#define		DIG_THERM_INTL(x)			((x) << 8)
+#define		DIG_THERM_INTL_MASK			0x0000FF00
+#define		DIG_THERM_INTL_SHIFT			8
+#define 	THERM_INTH_MASK				(1 << 24)
+#define 	THERM_INTL_MASK				(1 << 25)
+
+/* PCIE registers idx/data 0x38/0x3c */
+#define PB0_PIF_PWRDOWN_0                                 0x1100012 /* PCIE */
+#       define PLL_POWER_STATE_IN_TXS2_0(x)               ((x) << 7)
+#       define PLL_POWER_STATE_IN_TXS2_0_MASK             (0x7 << 7)
+#       define PLL_POWER_STATE_IN_TXS2_0_SHIFT            7
+#       define PLL_POWER_STATE_IN_OFF_0(x)                ((x) << 10)
+#       define PLL_POWER_STATE_IN_OFF_0_MASK              (0x7 << 10)
+#       define PLL_POWER_STATE_IN_OFF_0_SHIFT             10
+#       define PLL_RAMP_UP_TIME_0(x)                      ((x) << 24)
+#       define PLL_RAMP_UP_TIME_0_MASK                    (0x7 << 24)
+#       define PLL_RAMP_UP_TIME_0_SHIFT                   24
+#define PB0_PIF_PWRDOWN_1                                 0x1100013 /* PCIE */
+#       define PLL_POWER_STATE_IN_TXS2_1(x)               ((x) << 7)
+#       define PLL_POWER_STATE_IN_TXS2_1_MASK             (0x7 << 7)
+#       define PLL_POWER_STATE_IN_TXS2_1_SHIFT            7
+#       define PLL_POWER_STATE_IN_OFF_1(x)                ((x) << 10)
+#       define PLL_POWER_STATE_IN_OFF_1_MASK              (0x7 << 10)
+#       define PLL_POWER_STATE_IN_OFF_1_SHIFT             10
+#       define PLL_RAMP_UP_TIME_1(x)                      ((x) << 24)
+#       define PLL_RAMP_UP_TIME_1_MASK                    (0x7 << 24)
+#       define PLL_RAMP_UP_TIME_1_SHIFT                   24
+
+#define PCIE_CNTL2                                        0x1001001c /* PCIE */
+#       define SLV_MEM_LS_EN                              (1 << 16)
+#       define SLV_MEM_AGGRESSIVE_LS_EN                   (1 << 17)
+#       define MST_MEM_LS_EN                              (1 << 18)
+#       define REPLAY_MEM_LS_EN                           (1 << 19)
+
+#define PCIE_LC_STATUS1                                   0x1400028 /* PCIE */
+#       define LC_REVERSE_RCVR                            (1 << 0)
+#       define LC_REVERSE_XMIT                            (1 << 1)
+#       define LC_OPERATING_LINK_WIDTH_MASK               (0x7 << 2)
+#       define LC_OPERATING_LINK_WIDTH_SHIFT              2
+#       define LC_DETECTED_LINK_WIDTH_MASK                (0x7 << 5)
+#       define LC_DETECTED_LINK_WIDTH_SHIFT               5
+
+#define PCIE_P_CNTL                                       0x1400040 /* PCIE */
+#       define P_IGNORE_EDB_ERR                           (1 << 6)
+
+#define PB1_PIF_PWRDOWN_0                                 0x2100012 /* PCIE */
+#define PB1_PIF_PWRDOWN_1                                 0x2100013 /* PCIE */
+
+#define PCIE_LC_CNTL                                      0x100100A0 /* PCIE */
+#       define LC_L0S_INACTIVITY(x)                       ((x) << 8)
+#       define LC_L0S_INACTIVITY_MASK                     (0xf << 8)
+#       define LC_L0S_INACTIVITY_SHIFT                    8
+#       define LC_L1_INACTIVITY(x)                        ((x) << 12)
+#       define LC_L1_INACTIVITY_MASK                      (0xf << 12)
+#       define LC_L1_INACTIVITY_SHIFT                     12
+#       define LC_PMI_TO_L1_DIS                           (1 << 16)
+#       define LC_ASPM_TO_L1_DIS                          (1 << 24)
+
+#define PCIE_LC_LINK_WIDTH_CNTL                           0x100100A2 /* PCIE */
+#       define LC_LINK_WIDTH_SHIFT                        0
+#       define LC_LINK_WIDTH_MASK                         0x7
+#       define LC_LINK_WIDTH_X0                           0
+#       define LC_LINK_WIDTH_X1                           1
+#       define LC_LINK_WIDTH_X2                           2
+#       define LC_LINK_WIDTH_X4                           3
+#       define LC_LINK_WIDTH_X8                           4
+#       define LC_LINK_WIDTH_X16                          6
+#       define LC_LINK_WIDTH_RD_SHIFT                     4
+#       define LC_LINK_WIDTH_RD_MASK                      0x70
+#       define LC_RECONFIG_ARC_MISSING_ESCAPE             (1 << 7)
+#       define LC_RECONFIG_NOW                            (1 << 8)
+#       define LC_RENEGOTIATION_SUPPORT                   (1 << 9)
+#       define LC_RENEGOTIATE_EN                          (1 << 10)
+#       define LC_SHORT_RECONFIG_EN                       (1 << 11)
+#       define LC_UPCONFIGURE_SUPPORT                     (1 << 12)
+#       define LC_UPCONFIGURE_DIS                         (1 << 13)
+#       define LC_DYN_LANES_PWR_STATE(x)                  ((x) << 21)
+#       define LC_DYN_LANES_PWR_STATE_MASK                (0x3 << 21)
+#       define LC_DYN_LANES_PWR_STATE_SHIFT               21
+#define PCIE_LC_N_FTS_CNTL                                0x100100a3 /* PCIE */
+#       define LC_XMIT_N_FTS(x)                           ((x) << 0)
+#       define LC_XMIT_N_FTS_MASK                         (0xff << 0)
+#       define LC_XMIT_N_FTS_SHIFT                        0
+#       define LC_XMIT_N_FTS_OVERRIDE_EN                  (1 << 8)
+#       define LC_N_FTS_MASK                              (0xff << 24)
+#define PCIE_LC_SPEED_CNTL                                0x100100A4 /* PCIE */
+#       define LC_GEN2_EN_STRAP                           (1 << 0)
+#       define LC_GEN3_EN_STRAP                           (1 << 1)
+#       define LC_TARGET_LINK_SPEED_OVERRIDE_EN           (1 << 2)
+#       define LC_TARGET_LINK_SPEED_OVERRIDE_MASK         (0x3 << 3)
+#       define LC_TARGET_LINK_SPEED_OVERRIDE_SHIFT        3
+#       define LC_FORCE_EN_SW_SPEED_CHANGE                (1 << 5)
+#       define LC_FORCE_DIS_SW_SPEED_CHANGE               (1 << 6)
+#       define LC_FORCE_EN_HW_SPEED_CHANGE                (1 << 7)
+#       define LC_FORCE_DIS_HW_SPEED_CHANGE               (1 << 8)
+#       define LC_INITIATE_LINK_SPEED_CHANGE              (1 << 9)
+#       define LC_SPEED_CHANGE_ATTEMPTS_ALLOWED_MASK      (0x3 << 10)
+#       define LC_SPEED_CHANGE_ATTEMPTS_ALLOWED_SHIFT     10
+#       define LC_CURRENT_DATA_RATE_MASK                  (0x3 << 13) /* 0/1/2 = gen1/2/3 */
+#       define LC_CURRENT_DATA_RATE_SHIFT                 13
+#       define LC_CLR_FAILED_SPD_CHANGE_CNT               (1 << 16)
+#       define LC_OTHER_SIDE_EVER_SENT_GEN2               (1 << 18)
+#       define LC_OTHER_SIDE_SUPPORTS_GEN2                (1 << 19)
+#       define LC_OTHER_SIDE_EVER_SENT_GEN3               (1 << 20)
+#       define LC_OTHER_SIDE_SUPPORTS_GEN3                (1 << 21)
+
+#define PCIE_LC_CNTL2                                     0x100100B1 /* PCIE */
+#       define LC_ALLOW_PDWN_IN_L1                        (1 << 17)
+#       define LC_ALLOW_PDWN_IN_L23                       (1 << 18)
+
+#define PCIE_LC_CNTL3                                     0x100100B5 /* PCIE */
+#       define LC_GO_TO_RECOVERY                          (1 << 30)
+#define PCIE_LC_CNTL4                                     0x100100B6 /* PCIE */
+#       define LC_REDO_EQ                                 (1 << 5)
+#       define LC_SET_QUIESCE                             (1 << 13)
+
+/* direct registers */
 #define PCIE_INDEX  					0x38
 #define PCIE_DATA  					0x3C
 
+#define SMC_IND_INDEX_0  				0x200
+#define SMC_IND_DATA_0  				0x204
+
+#define SMC_IND_ACCESS_CNTL  				0x240
+#define		AUTO_INCREMENT_IND_0			(1 << 0)
+
+#define SMC_MESSAGE_0  					0x250
+#define		SMC_MSG_MASK				0xffff
+#define SMC_RESP_0  					0x254
+#define		SMC_RESP_MASK				0xffff
+
+#define SMC_MSG_ARG_0  					0x290
+
 #define VGA_HDP_CONTROL  				0x328
 #define		VGA_MEMORY_DISABLE				(1 << 4)
 
 #define DMIF_ADDR_CALC  				0xC00
 
+#define	PIPE0_DMIF_BUFFER_CONTROL			  0x0ca0
+#       define DMIF_BUFFERS_ALLOCATED(x)                  ((x) << 0)
+#       define DMIF_BUFFERS_ALLOCATED_COMPLETED           (1 << 4)
+
 #define	SRBM_GFX_CNTL				        0xE44
 #define		PIPEID(x)					((x) << 0)
 #define		MEID(x)						((x) << 2)
@@ -172,6 +526,10 @@
 #define	VM_CONTEXT0_PAGE_TABLE_END_ADDR			0x157C
 #define	VM_CONTEXT1_PAGE_TABLE_END_ADDR			0x1580
 
+#define VM_L2_CG           				0x15c0
+#define		MC_CG_ENABLE				(1 << 18)
+#define		MC_LS_ENABLE				(1 << 19)
+
 #define MC_SHARED_CHMAP						0x2004
 #define		NOOFCHAN_SHIFT					12
 #define		NOOFCHAN_MASK					0x0000f000
@@ -201,6 +559,17 @@
 
 #define MC_SHARED_BLACKOUT_CNTL           		0x20ac
 
+#define MC_HUB_MISC_HUB_CG           			0x20b8
+#define MC_HUB_MISC_VM_CG           			0x20bc
+
+#define MC_HUB_MISC_SIP_CG           			0x20c0
+
+#define MC_XPB_CLK_GAT           			0x2478
+
+#define MC_CITF_MISC_RD_CG           			0x2648
+#define MC_CITF_MISC_WR_CG           			0x264c
+#define MC_CITF_MISC_VM_CG           			0x2650
+
 #define	MC_ARB_RAMCFG					0x2760
 #define		NOOFBANK_SHIFT					0
 #define		NOOFBANK_MASK					0x00000003
@@ -215,9 +584,37 @@
 #define		NOOFGROUPS_SHIFT				12
 #define		NOOFGROUPS_MASK					0x00001000
 
+#define	MC_ARB_DRAM_TIMING				0x2774
+#define	MC_ARB_DRAM_TIMING2				0x2778
+
+#define MC_ARB_BURST_TIME                               0x2808
+#define		STATE0(x)				((x) << 0)
+#define		STATE0_MASK				(0x1f << 0)
+#define		STATE0_SHIFT				0
+#define		STATE1(x)				((x) << 5)
+#define		STATE1_MASK				(0x1f << 5)
+#define		STATE1_SHIFT				5
+#define		STATE2(x)				((x) << 10)
+#define		STATE2_MASK				(0x1f << 10)
+#define		STATE2_SHIFT				10
+#define		STATE3(x)				((x) << 15)
+#define		STATE3_MASK				(0x1f << 15)
+#define		STATE3_SHIFT				15
+
+#define MC_SEQ_RAS_TIMING                               0x28a0
+#define MC_SEQ_CAS_TIMING                               0x28a4
+#define MC_SEQ_MISC_TIMING                              0x28a8
+#define MC_SEQ_MISC_TIMING2                             0x28ac
+#define MC_SEQ_PMG_TIMING                               0x28b0
+#define MC_SEQ_RD_CTL_D0                                0x28b4
+#define MC_SEQ_RD_CTL_D1                                0x28b8
+#define MC_SEQ_WR_CTL_D0                                0x28bc
+#define MC_SEQ_WR_CTL_D1                                0x28c0
+
 #define MC_SEQ_SUP_CNTL           			0x28c8
 #define		RUN_MASK      				(1 << 0)
 #define MC_SEQ_SUP_PGM           			0x28cc
+#define MC_PMG_AUTO_CMD           			0x28d0
 
 #define	MC_SEQ_TRAIN_WAKEUP_CNTL			0x28e8
 #define		TRAIN_DONE_D0      			(1 << 30)
@@ -226,10 +623,92 @@
 #define MC_IO_PAD_CNTL_D0           			0x29d0
 #define		MEM_FALL_OUT_CMD      			(1 << 8)
 
+#define MC_SEQ_MISC0           				0x2a00
+#define 	MC_SEQ_MISC0_VEN_ID_SHIFT               8
+#define 	MC_SEQ_MISC0_VEN_ID_MASK                0x00000f00
+#define 	MC_SEQ_MISC0_VEN_ID_VALUE               3
+#define 	MC_SEQ_MISC0_REV_ID_SHIFT               12
+#define 	MC_SEQ_MISC0_REV_ID_MASK                0x0000f000
+#define 	MC_SEQ_MISC0_REV_ID_VALUE               1
+#define 	MC_SEQ_MISC0_GDDR5_SHIFT                28
+#define 	MC_SEQ_MISC0_GDDR5_MASK                 0xf0000000
+#define 	MC_SEQ_MISC0_GDDR5_VALUE                5
+#define MC_SEQ_MISC1                                    0x2a04
+#define MC_SEQ_RESERVE_M                                0x2a08
+#define MC_PMG_CMD_EMRS                                 0x2a0c
+
 #define MC_SEQ_IO_DEBUG_INDEX           		0x2a44
 #define MC_SEQ_IO_DEBUG_DATA           			0x2a48
 
+#define MC_SEQ_MISC5                                    0x2a54
+#define MC_SEQ_MISC6                                    0x2a58
+
+#define MC_SEQ_MISC7                                    0x2a64
+
+#define MC_SEQ_RAS_TIMING_LP                            0x2a6c
+#define MC_SEQ_CAS_TIMING_LP                            0x2a70
+#define MC_SEQ_MISC_TIMING_LP                           0x2a74
+#define MC_SEQ_MISC_TIMING2_LP                          0x2a78
+#define MC_SEQ_WR_CTL_D0_LP                             0x2a7c
+#define MC_SEQ_WR_CTL_D1_LP                             0x2a80
+#define MC_SEQ_PMG_CMD_EMRS_LP                          0x2a84
+#define MC_SEQ_PMG_CMD_MRS_LP                           0x2a88
+
+#define MC_PMG_CMD_MRS                                  0x2aac
+
+#define MC_SEQ_RD_CTL_D0_LP                             0x2b1c
+#define MC_SEQ_RD_CTL_D1_LP                             0x2b20
+
+#define MC_PMG_CMD_MRS1                                 0x2b44
+#define MC_SEQ_PMG_CMD_MRS1_LP                          0x2b48
+#define MC_SEQ_PMG_TIMING_LP                            0x2b4c
+
+#define MC_SEQ_WR_CTL_2                                 0x2b54
+#define MC_SEQ_WR_CTL_2_LP                              0x2b58
+#define MC_PMG_CMD_MRS2                                 0x2b5c
+#define MC_SEQ_PMG_CMD_MRS2_LP                          0x2b60
+
+#define	MCLK_PWRMGT_CNTL				0x2ba0
+#       define DLL_SPEED(x)				((x) << 0)
+#       define DLL_SPEED_MASK				(0x1f << 0)
+#       define DLL_READY                                (1 << 6)
+#       define MC_INT_CNTL                              (1 << 7)
+#       define MRDCK0_PDNB                              (1 << 8)
+#       define MRDCK1_PDNB                              (1 << 9)
+#       define MRDCK0_RESET                             (1 << 16)
+#       define MRDCK1_RESET                             (1 << 17)
+#       define DLL_READY_READ                           (1 << 24)
+#define	DLL_CNTL					0x2ba4
+#       define MRDCK0_BYPASS                            (1 << 24)
+#       define MRDCK1_BYPASS                            (1 << 25)
+
+#define	MPLL_FUNC_CNTL					0x2bb4
+#define		BWCTRL(x)				((x) << 20)
+#define		BWCTRL_MASK				(0xff << 20)
+#define	MPLL_FUNC_CNTL_1				0x2bb8
+#define		VCO_MODE(x)				((x) << 0)
+#define		VCO_MODE_MASK				(3 << 0)
+#define		CLKFRAC(x)				((x) << 4)
+#define		CLKFRAC_MASK				(0xfff << 4)
+#define		CLKF(x)					((x) << 16)
+#define		CLKF_MASK				(0xfff << 16)
+#define	MPLL_FUNC_CNTL_2				0x2bbc
+#define	MPLL_AD_FUNC_CNTL				0x2bc0
+#define		YCLK_POST_DIV(x)			((x) << 0)
+#define		YCLK_POST_DIV_MASK			(7 << 0)
+#define	MPLL_DQ_FUNC_CNTL				0x2bc4
+#define		YCLK_SEL(x)				((x) << 4)
+#define		YCLK_SEL_MASK				(1 << 4)
+
+#define	MPLL_SS1					0x2bcc
+#define		CLKV(x)					((x) << 0)
+#define		CLKV_MASK				(0x3ffffff << 0)
+#define	MPLL_SS2					0x2bd0
+#define		CLKS(x)					((x) << 0)
+#define		CLKS_MASK				(0xfff << 0)
+
 #define	HDP_HOST_PATH_CNTL				0x2C00
+#define 	CLOCK_GATING_DIS			(1 << 23)
 #define	HDP_NONSURFACE_BASE				0x2C04
 #define	HDP_NONSURFACE_INFO				0x2C08
 #define	HDP_NONSURFACE_SIZE				0x2C0C
@@ -237,6 +716,26 @@
 #define HDP_ADDR_CONFIG  				0x2F48
 #define HDP_MISC_CNTL					0x2F4C
 #define 	HDP_FLUSH_INVALIDATE_CACHE			(1 << 0)
+#define HDP_MEM_POWER_LS				0x2F50
+#define 	HDP_LS_ENABLE				(1 << 0)
+
+#define ATC_MISC_CG           				0x3350
+
+#define MC_SEQ_CNTL_3                                     0x3600
+#       define CAC_EN                                     (1 << 31)
+#define MC_SEQ_G5PDX_CTRL                                 0x3604
+#define MC_SEQ_G5PDX_CTRL_LP                              0x3608
+#define MC_SEQ_G5PDX_CMD0                                 0x360c
+#define MC_SEQ_G5PDX_CMD0_LP                              0x3610
+#define MC_SEQ_G5PDX_CMD1                                 0x3614
+#define MC_SEQ_G5PDX_CMD1_LP                              0x3618
+
+#define MC_SEQ_PMG_DVS_CTL                                0x3628
+#define MC_SEQ_PMG_DVS_CTL_LP                             0x362c
+#define MC_SEQ_PMG_DVS_CMD                                0x3630
+#define MC_SEQ_PMG_DVS_CMD_LP                             0x3634
+#define MC_SEQ_DLL_STBY                                   0x3638
+#define MC_SEQ_DLL_STBY_LP                                0x363c
 
 #define IH_RB_CNTL                                        0x3e00
 #       define IH_RB_ENABLE                               (1 << 0)
@@ -265,6 +764,9 @@
 #       define MC_WR_CLEAN_CNT(x)                         ((x) << 20)
 #       define MC_VMID(x)                                 ((x) << 25)
 
+#define	BIF_LNCNT_RESET					0x5220
+#       define RESET_LNCNT_EN                           (1 << 0)
+
 #define	CONFIG_MEMSIZE					0x5428
 
 #define INTERRUPT_CNTL                                    0x5468
@@ -401,6 +903,9 @@
 #       define DC_HPDx_RX_INT_TIMER(x)                    ((x) << 16)
 #       define DC_HPDx_EN                                 (1 << 28)
 
+#define DPG_PIPE_STUTTER_CONTROL                          0x6cd4
+#       define STUTTER_ENABLE                             (1 << 0)
+
 #define	GRBM_CNTL					0x8000
 #define		GRBM_READ_TIMEOUT(x)				((x) << 0)
 
@@ -504,6 +1009,9 @@
 
 #define	CP_RB0_RPTR					0x8700
 #define	CP_RB_WPTR_DELAY				0x8704
+#define	CP_RB_WPTR_POLL_CNTL				0x8708
+#define		IDLE_POLL_COUNT(x)			((x) << 16)
+#define		IDLE_POLL_COUNT_MASK			(0xffff << 16)
 
 #define CP_MEQ_THRESHOLDS				0x8764
 #define		MEQ1_START(x)				((x) << 0)
@@ -730,6 +1238,9 @@
 #       define CP_RINGID1_INT_STAT                      (1 << 30)
 #       define CP_RINGID0_INT_STAT                      (1 << 31)
 
+#define CP_MEM_SLP_CNTL                                 0xC1E4
+#       define CP_MEM_LS_EN                             (1 << 0)
+
 #define CP_CPF_DEBUG                                    0xC200
 
 #define CP_PQ_WPTR_POLL_CNTL                            0xC20C
@@ -775,14 +1286,20 @@
 
 #define RLC_MC_CNTL                                       0xC30C
 
+#define RLC_MEM_SLP_CNTL                                  0xC318
+#       define RLC_MEM_LS_EN                              (1 << 0)
+
 #define RLC_LB_CNTR_MAX                                   0xC348
 
 #define RLC_LB_CNTL                                       0xC364
+#       define LOAD_BALANCE_ENABLE                        (1 << 0)
 
 #define RLC_LB_CNTR_INIT                                  0xC36C
 
 #define RLC_SAVE_AND_RESTORE_BASE                         0xC374
-#define RLC_DRIVER_DMA_STATUS                             0xC378
+#define RLC_DRIVER_DMA_STATUS                             0xC378 /* dGPU */
+#define RLC_CP_TABLE_RESTORE                              0xC378 /* APU */
+#define RLC_PG_DELAY_2                                    0xC37C
 
 #define RLC_GPM_UCODE_ADDR                                0xC388
 #define RLC_GPM_UCODE_DATA                                0xC38C
@@ -791,12 +1308,52 @@
 #define RLC_CAPTURE_GPU_CLOCK_COUNT                       0xC398
 #define RLC_UCODE_CNTL                                    0xC39C
 
+#define RLC_GPM_STAT                                      0xC400
+#       define RLC_GPM_BUSY                               (1 << 0)
+#       define GFX_POWER_STATUS                           (1 << 1)
+#       define GFX_CLOCK_STATUS                           (1 << 2)
+
+#define RLC_PG_CNTL                                       0xC40C
+#       define GFX_PG_ENABLE                              (1 << 0)
+#       define GFX_PG_SRC                                 (1 << 1)
+#       define DYN_PER_CU_PG_ENABLE                       (1 << 2)
+#       define STATIC_PER_CU_PG_ENABLE                    (1 << 3)
+#       define DISABLE_GDS_PG                             (1 << 13)
+#       define DISABLE_CP_PG                              (1 << 15)
+#       define SMU_CLK_SLOWDOWN_ON_PU_ENABLE              (1 << 17)
+#       define SMU_CLK_SLOWDOWN_ON_PD_ENABLE              (1 << 18)
+
+#define RLC_CGTT_MGCG_OVERRIDE                            0xC420
 #define RLC_CGCG_CGLS_CTRL                                0xC424
+#       define CGCG_EN                                    (1 << 0)
+#       define CGLS_EN                                    (1 << 1)
+
+#define RLC_PG_DELAY                                      0xC434
 
 #define RLC_LB_INIT_CU_MASK                               0xC43C
 
 #define RLC_LB_PARAMS                                     0xC444
 
+#define RLC_PG_AO_CU_MASK                                 0xC44C
+
+#define	RLC_MAX_PG_CU					0xC450
+#	define MAX_PU_CU(x)				((x) << 0)
+#	define MAX_PU_CU_MASK				(0xff << 0)
+#define RLC_AUTO_PG_CTRL                                  0xC454
+#       define AUTO_PG_EN                                 (1 << 0)
+#	define GRBM_REG_SGIT(x)				((x) << 3)
+#	define GRBM_REG_SGIT_MASK			(0xffff << 3)
+
+#define RLC_SERDES_WR_CU_MASTER_MASK                      0xC474
+#define RLC_SERDES_WR_NONCU_MASTER_MASK                   0xC478
+#define RLC_SERDES_WR_CTRL                                0xC47C
+#define		BPM_ADDR(x)				((x) << 0)
+#define		BPM_ADDR_MASK      			(0xff << 0)
+#define		CGLS_ENABLE				(1 << 16)
+#define		CGCG_OVERRIDE_0				(1 << 20)
+#define		MGCG_OVERRIDE_0				(1 << 22)
+#define		MGCG_OVERRIDE_1				(1 << 23)
+
 #define RLC_SERDES_CU_MASTER_BUSY                         0xC484
 #define RLC_SERDES_NONCU_MASTER_BUSY                      0xC488
 #       define SE_MASTER_BUSY_MASK                        0x0000ffff
@@ -807,6 +1364,13 @@
 #define RLC_GPM_SCRATCH_ADDR                              0xC4B0
 #define RLC_GPM_SCRATCH_DATA                              0xC4B4
 
+#define RLC_GPR_REG2                                      0xC4E8
+#define		REQ      				0x00000001
+#define		MESSAGE(x)      			((x) << 1)
+#define		MESSAGE_MASK      			0x0000001e
+#define		MSG_ENTER_RLC_SAFE_MODE      			1
+#define		MSG_EXIT_RLC_SAFE_MODE      			0
+
 #define CP_HPD_EOP_BASE_ADDR                              0xC904
 #define CP_HPD_EOP_BASE_ADDR_HI                           0xC908
 #define CP_HPD_EOP_VMID                                   0xC90C
@@ -851,6 +1415,8 @@
 #define		MQD_VMID(x)				((x) << 0)
 #define		MQD_VMID_MASK      			(0xf << 0)
 
+#define DB_RENDER_CONTROL                               0x28000
+
 #define PA_SC_RASTER_CONFIG                             0x28350
 #       define RASTER_CONFIG_RB_MAP_0                   0
 #       define RASTER_CONFIG_RB_MAP_1                   1
@@ -944,6 +1510,16 @@
 
 #define	CP_PERFMON_CNTL					0x36020
 
+#define	CGTS_SM_CTRL_REG				0x3c000
+#define		SM_MODE(x)				((x) << 17)
+#define		SM_MODE_MASK				(0x7 << 17)
+#define		SM_MODE_ENABLE				(1 << 20)
+#define		CGTS_OVERRIDE				(1 << 21)
+#define		CGTS_LS_OVERRIDE			(1 << 22)
+#define		ON_MONITOR_ADD_EN			(1 << 23)
+#define		ON_MONITOR_ADD(x)			((x) << 24)
+#define		ON_MONITOR_ADD_MASK			(0xff << 24)
+
 #define	CGTS_TCC_DISABLE				0x3c00c
 #define	CGTS_USER_TCC_DISABLE				0x3c010
 #define		TCC_DISABLE_MASK				0xFFFF0000
@@ -1176,6 +1752,8 @@
 
 #define	SDMA0_UCODE_ADDR                                  0xD000
 #define	SDMA0_UCODE_DATA                                  0xD004
+#define	SDMA0_POWER_CNTL                                  0xD008
+#define	SDMA0_CLK_CTRL                                    0xD00C
 
 #define SDMA0_CNTL                                        0xD010
 #       define TRAP_ENABLE                                (1 << 0)
@@ -1300,6 +1878,13 @@
 #define UVD_RBC_RB_RPTR			0xf690
 #define UVD_RBC_RB_WPTR			0xf694
 
+#define	UVD_CGC_CTRL					0xF4B0
+#	define DCM					(1 << 0)
+#	define CG_DT(x)					((x) << 2)
+#	define CG_DT_MASK				(0xf << 2)
+#	define CLK_OD(x)				((x) << 6)
+#	define CLK_OD_MASK				(0x1f << 6)
+
 /* UVD clocks */
 
 #define CG_DCLK_CNTL			0xC050009C
@@ -1310,4 +1895,7 @@
 #define CG_VCLK_CNTL			0xC05000A4
 #define CG_VCLK_STATUS			0xC05000A8
 
+/* UVD CTX indirect */
+#define	UVD_CGC_MEM_CTRL				0xC0
+
 #endif
diff --git a/drivers/gpu/drm/radeon/clearstate_cayman.h b/drivers/gpu/drm/radeon/clearstate_cayman.h
index c00339440c5e..aa908c55a513 100644
--- a/drivers/gpu/drm/radeon/clearstate_cayman.h
+++ b/drivers/gpu/drm/radeon/clearstate_cayman.h
@@ -1073,7 +1073,7 @@ static const struct cs_extent_def SECT_CTRLCONST_defs[] =
     {SECT_CTRLCONST_def_1, 0x0000f3fc, 2 },
     { 0, 0, 0 }
 };
-struct cs_section_def cayman_cs_data[] = {
+static const struct cs_section_def cayman_cs_data[] = {
     { SECT_CONTEXT_defs, SECT_CONTEXT },
     { SECT_CLEAR_defs, SECT_CLEAR },
     { SECT_CTRLCONST_defs, SECT_CTRLCONST },
diff --git a/drivers/gpu/drm/radeon/clearstate_ci.h b/drivers/gpu/drm/radeon/clearstate_ci.h
new file mode 100644
index 000000000000..c3982f9475fb
--- /dev/null
+++ b/drivers/gpu/drm/radeon/clearstate_ci.h
@@ -0,0 +1,944 @@
+/*
+ * Copyright 2013 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+
+static const unsigned int ci_SECT_CONTEXT_def_1[] =
+{
+    0x00000000, // DB_RENDER_CONTROL
+    0x00000000, // DB_COUNT_CONTROL
+    0x00000000, // DB_DEPTH_VIEW
+    0x00000000, // DB_RENDER_OVERRIDE
+    0x00000000, // DB_RENDER_OVERRIDE2
+    0x00000000, // DB_HTILE_DATA_BASE
+    0, // HOLE
+    0, // HOLE
+    0x00000000, // DB_DEPTH_BOUNDS_MIN
+    0x00000000, // DB_DEPTH_BOUNDS_MAX
+    0x00000000, // DB_STENCIL_CLEAR
+    0x00000000, // DB_DEPTH_CLEAR
+    0x00000000, // PA_SC_SCREEN_SCISSOR_TL
+    0x40004000, // PA_SC_SCREEN_SCISSOR_BR
+    0, // HOLE
+    0x00000000, // DB_DEPTH_INFO
+    0x00000000, // DB_Z_INFO
+    0x00000000, // DB_STENCIL_INFO
+    0x00000000, // DB_Z_READ_BASE
+    0x00000000, // DB_STENCIL_READ_BASE
+    0x00000000, // DB_Z_WRITE_BASE
+    0x00000000, // DB_STENCIL_WRITE_BASE
+    0x00000000, // DB_DEPTH_SIZE
+    0x00000000, // DB_DEPTH_SLICE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0x00000000, // TA_BC_BASE_ADDR
+    0x00000000, // TA_BC_BASE_ADDR_HI
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0x00000000, // COHER_DEST_BASE_HI_0
+    0x00000000, // COHER_DEST_BASE_HI_1
+    0x00000000, // COHER_DEST_BASE_HI_2
+    0x00000000, // COHER_DEST_BASE_HI_3
+    0x00000000, // COHER_DEST_BASE_2
+    0x00000000, // COHER_DEST_BASE_3
+    0x00000000, // PA_SC_WINDOW_OFFSET
+    0x80000000, // PA_SC_WINDOW_SCISSOR_TL
+    0x40004000, // PA_SC_WINDOW_SCISSOR_BR
+    0x0000ffff, // PA_SC_CLIPRECT_RULE
+    0x00000000, // PA_SC_CLIPRECT_0_TL
+    0x40004000, // PA_SC_CLIPRECT_0_BR
+    0x00000000, // PA_SC_CLIPRECT_1_TL
+    0x40004000, // PA_SC_CLIPRECT_1_BR
+    0x00000000, // PA_SC_CLIPRECT_2_TL
+    0x40004000, // PA_SC_CLIPRECT_2_BR
+    0x00000000, // PA_SC_CLIPRECT_3_TL
+    0x40004000, // PA_SC_CLIPRECT_3_BR
+    0xaa99aaaa, // PA_SC_EDGERULE
+    0x00000000, // PA_SU_HARDWARE_SCREEN_OFFSET
+    0xffffffff, // CB_TARGET_MASK
+    0xffffffff, // CB_SHADER_MASK
+    0x80000000, // PA_SC_GENERIC_SCISSOR_TL
+    0x40004000, // PA_SC_GENERIC_SCISSOR_BR
+    0x00000000, // COHER_DEST_BASE_0
+    0x00000000, // COHER_DEST_BASE_1
+    0x80000000, // PA_SC_VPORT_SCISSOR_0_TL
+    0x40004000, // PA_SC_VPORT_SCISSOR_0_BR
+    0x80000000, // PA_SC_VPORT_SCISSOR_1_TL
+    0x40004000, // PA_SC_VPORT_SCISSOR_1_BR
+    0x80000000, // PA_SC_VPORT_SCISSOR_2_TL
+    0x40004000, // PA_SC_VPORT_SCISSOR_2_BR
+    0x80000000, // PA_SC_VPORT_SCISSOR_3_TL
+    0x40004000, // PA_SC_VPORT_SCISSOR_3_BR
+    0x80000000, // PA_SC_VPORT_SCISSOR_4_TL
+    0x40004000, // PA_SC_VPORT_SCISSOR_4_BR
+    0x80000000, // PA_SC_VPORT_SCISSOR_5_TL
+    0x40004000, // PA_SC_VPORT_SCISSOR_5_BR
+    0x80000000, // PA_SC_VPORT_SCISSOR_6_TL
+    0x40004000, // PA_SC_VPORT_SCISSOR_6_BR
+    0x80000000, // PA_SC_VPORT_SCISSOR_7_TL
+    0x40004000, // PA_SC_VPORT_SCISSOR_7_BR
+    0x80000000, // PA_SC_VPORT_SCISSOR_8_TL
+    0x40004000, // PA_SC_VPORT_SCISSOR_8_BR
+    0x80000000, // PA_SC_VPORT_SCISSOR_9_TL
+    0x40004000, // PA_SC_VPORT_SCISSOR_9_BR
+    0x80000000, // PA_SC_VPORT_SCISSOR_10_TL
+    0x40004000, // PA_SC_VPORT_SCISSOR_10_BR
+    0x80000000, // PA_SC_VPORT_SCISSOR_11_TL
+    0x40004000, // PA_SC_VPORT_SCISSOR_11_BR
+    0x80000000, // PA_SC_VPORT_SCISSOR_12_TL
+    0x40004000, // PA_SC_VPORT_SCISSOR_12_BR
+    0x80000000, // PA_SC_VPORT_SCISSOR_13_TL
+    0x40004000, // PA_SC_VPORT_SCISSOR_13_BR
+    0x80000000, // PA_SC_VPORT_SCISSOR_14_TL
+    0x40004000, // PA_SC_VPORT_SCISSOR_14_BR
+    0x80000000, // PA_SC_VPORT_SCISSOR_15_TL
+    0x40004000, // PA_SC_VPORT_SCISSOR_15_BR
+    0x00000000, // PA_SC_VPORT_ZMIN_0
+    0x3f800000, // PA_SC_VPORT_ZMAX_0
+    0x00000000, // PA_SC_VPORT_ZMIN_1
+    0x3f800000, // PA_SC_VPORT_ZMAX_1
+    0x00000000, // PA_SC_VPORT_ZMIN_2
+    0x3f800000, // PA_SC_VPORT_ZMAX_2
+    0x00000000, // PA_SC_VPORT_ZMIN_3
+    0x3f800000, // PA_SC_VPORT_ZMAX_3
+    0x00000000, // PA_SC_VPORT_ZMIN_4
+    0x3f800000, // PA_SC_VPORT_ZMAX_4
+    0x00000000, // PA_SC_VPORT_ZMIN_5
+    0x3f800000, // PA_SC_VPORT_ZMAX_5
+    0x00000000, // PA_SC_VPORT_ZMIN_6
+    0x3f800000, // PA_SC_VPORT_ZMAX_6
+    0x00000000, // PA_SC_VPORT_ZMIN_7
+    0x3f800000, // PA_SC_VPORT_ZMAX_7
+    0x00000000, // PA_SC_VPORT_ZMIN_8
+    0x3f800000, // PA_SC_VPORT_ZMAX_8
+    0x00000000, // PA_SC_VPORT_ZMIN_9
+    0x3f800000, // PA_SC_VPORT_ZMAX_9
+    0x00000000, // PA_SC_VPORT_ZMIN_10
+    0x3f800000, // PA_SC_VPORT_ZMAX_10
+    0x00000000, // PA_SC_VPORT_ZMIN_11
+    0x3f800000, // PA_SC_VPORT_ZMAX_11
+    0x00000000, // PA_SC_VPORT_ZMIN_12
+    0x3f800000, // PA_SC_VPORT_ZMAX_12
+    0x00000000, // PA_SC_VPORT_ZMIN_13
+    0x3f800000, // PA_SC_VPORT_ZMAX_13
+    0x00000000, // PA_SC_VPORT_ZMIN_14
+    0x3f800000, // PA_SC_VPORT_ZMAX_14
+    0x00000000, // PA_SC_VPORT_ZMIN_15
+    0x3f800000, // PA_SC_VPORT_ZMAX_15
+};
+static const unsigned int ci_SECT_CONTEXT_def_2[] =
+{
+    0x00000000, // PA_SC_SCREEN_EXTENT_CONTROL
+    0, // HOLE
+    0x00000000, // CP_PERFMON_CNTX_CNTL
+    0x00000000, // CP_RINGID
+    0x00000000, // CP_VMID
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0xffffffff, // VGT_MAX_VTX_INDX
+    0x00000000, // VGT_MIN_VTX_INDX
+    0x00000000, // VGT_INDX_OFFSET
+    0x00000000, // VGT_MULTI_PRIM_IB_RESET_INDX
+    0, // HOLE
+    0x00000000, // CB_BLEND_RED
+    0x00000000, // CB_BLEND_GREEN
+    0x00000000, // CB_BLEND_BLUE
+    0x00000000, // CB_BLEND_ALPHA
+    0, // HOLE
+    0, // HOLE
+    0x00000000, // DB_STENCIL_CONTROL
+    0x00000000, // DB_STENCILREFMASK
+    0x00000000, // DB_STENCILREFMASK_BF
+    0, // HOLE
+    0x00000000, // PA_CL_VPORT_XSCALE
+    0x00000000, // PA_CL_VPORT_XOFFSET
+    0x00000000, // PA_CL_VPORT_YSCALE
+    0x00000000, // PA_CL_VPORT_YOFFSET
+    0x00000000, // PA_CL_VPORT_ZSCALE
+    0x00000000, // PA_CL_VPORT_ZOFFSET
+    0x00000000, // PA_CL_VPORT_XSCALE_1
+    0x00000000, // PA_CL_VPORT_XOFFSET_1
+    0x00000000, // PA_CL_VPORT_YSCALE_1
+    0x00000000, // PA_CL_VPORT_YOFFSET_1
+    0x00000000, // PA_CL_VPORT_ZSCALE_1
+    0x00000000, // PA_CL_VPORT_ZOFFSET_1
+    0x00000000, // PA_CL_VPORT_XSCALE_2
+    0x00000000, // PA_CL_VPORT_XOFFSET_2
+    0x00000000, // PA_CL_VPORT_YSCALE_2
+    0x00000000, // PA_CL_VPORT_YOFFSET_2
+    0x00000000, // PA_CL_VPORT_ZSCALE_2
+    0x00000000, // PA_CL_VPORT_ZOFFSET_2
+    0x00000000, // PA_CL_VPORT_XSCALE_3
+    0x00000000, // PA_CL_VPORT_XOFFSET_3
+    0x00000000, // PA_CL_VPORT_YSCALE_3
+    0x00000000, // PA_CL_VPORT_YOFFSET_3
+    0x00000000, // PA_CL_VPORT_ZSCALE_3
+    0x00000000, // PA_CL_VPORT_ZOFFSET_3
+    0x00000000, // PA_CL_VPORT_XSCALE_4
+    0x00000000, // PA_CL_VPORT_XOFFSET_4
+    0x00000000, // PA_CL_VPORT_YSCALE_4
+    0x00000000, // PA_CL_VPORT_YOFFSET_4
+    0x00000000, // PA_CL_VPORT_ZSCALE_4
+    0x00000000, // PA_CL_VPORT_ZOFFSET_4
+    0x00000000, // PA_CL_VPORT_XSCALE_5
+    0x00000000, // PA_CL_VPORT_XOFFSET_5
+    0x00000000, // PA_CL_VPORT_YSCALE_5
+    0x00000000, // PA_CL_VPORT_YOFFSET_5
+    0x00000000, // PA_CL_VPORT_ZSCALE_5
+    0x00000000, // PA_CL_VPORT_ZOFFSET_5
+    0x00000000, // PA_CL_VPORT_XSCALE_6
+    0x00000000, // PA_CL_VPORT_XOFFSET_6
+    0x00000000, // PA_CL_VPORT_YSCALE_6
+    0x00000000, // PA_CL_VPORT_YOFFSET_6
+    0x00000000, // PA_CL_VPORT_ZSCALE_6
+    0x00000000, // PA_CL_VPORT_ZOFFSET_6
+    0x00000000, // PA_CL_VPORT_XSCALE_7
+    0x00000000, // PA_CL_VPORT_XOFFSET_7
+    0x00000000, // PA_CL_VPORT_YSCALE_7
+    0x00000000, // PA_CL_VPORT_YOFFSET_7
+    0x00000000, // PA_CL_VPORT_ZSCALE_7
+    0x00000000, // PA_CL_VPORT_ZOFFSET_7
+    0x00000000, // PA_CL_VPORT_XSCALE_8
+    0x00000000, // PA_CL_VPORT_XOFFSET_8
+    0x00000000, // PA_CL_VPORT_YSCALE_8
+    0x00000000, // PA_CL_VPORT_YOFFSET_8
+    0x00000000, // PA_CL_VPORT_ZSCALE_8
+    0x00000000, // PA_CL_VPORT_ZOFFSET_8
+    0x00000000, // PA_CL_VPORT_XSCALE_9
+    0x00000000, // PA_CL_VPORT_XOFFSET_9
+    0x00000000, // PA_CL_VPORT_YSCALE_9
+    0x00000000, // PA_CL_VPORT_YOFFSET_9
+    0x00000000, // PA_CL_VPORT_ZSCALE_9
+    0x00000000, // PA_CL_VPORT_ZOFFSET_9
+    0x00000000, // PA_CL_VPORT_XSCALE_10
+    0x00000000, // PA_CL_VPORT_XOFFSET_10
+    0x00000000, // PA_CL_VPORT_YSCALE_10
+    0x00000000, // PA_CL_VPORT_YOFFSET_10
+    0x00000000, // PA_CL_VPORT_ZSCALE_10
+    0x00000000, // PA_CL_VPORT_ZOFFSET_10
+    0x00000000, // PA_CL_VPORT_XSCALE_11
+    0x00000000, // PA_CL_VPORT_XOFFSET_11
+    0x00000000, // PA_CL_VPORT_YSCALE_11
+    0x00000000, // PA_CL_VPORT_YOFFSET_11
+    0x00000000, // PA_CL_VPORT_ZSCALE_11
+    0x00000000, // PA_CL_VPORT_ZOFFSET_11
+    0x00000000, // PA_CL_VPORT_XSCALE_12
+    0x00000000, // PA_CL_VPORT_XOFFSET_12
+    0x00000000, // PA_CL_VPORT_YSCALE_12
+    0x00000000, // PA_CL_VPORT_YOFFSET_12
+    0x00000000, // PA_CL_VPORT_ZSCALE_12
+    0x00000000, // PA_CL_VPORT_ZOFFSET_12
+    0x00000000, // PA_CL_VPORT_XSCALE_13
+    0x00000000, // PA_CL_VPORT_XOFFSET_13
+    0x00000000, // PA_CL_VPORT_YSCALE_13
+    0x00000000, // PA_CL_VPORT_YOFFSET_13
+    0x00000000, // PA_CL_VPORT_ZSCALE_13
+    0x00000000, // PA_CL_VPORT_ZOFFSET_13
+    0x00000000, // PA_CL_VPORT_XSCALE_14
+    0x00000000, // PA_CL_VPORT_XOFFSET_14
+    0x00000000, // PA_CL_VPORT_YSCALE_14
+    0x00000000, // PA_CL_VPORT_YOFFSET_14
+    0x00000000, // PA_CL_VPORT_ZSCALE_14
+    0x00000000, // PA_CL_VPORT_ZOFFSET_14
+    0x00000000, // PA_CL_VPORT_XSCALE_15
+    0x00000000, // PA_CL_VPORT_XOFFSET_15
+    0x00000000, // PA_CL_VPORT_YSCALE_15
+    0x00000000, // PA_CL_VPORT_YOFFSET_15
+    0x00000000, // PA_CL_VPORT_ZSCALE_15
+    0x00000000, // PA_CL_VPORT_ZOFFSET_15
+    0x00000000, // PA_CL_UCP_0_X
+    0x00000000, // PA_CL_UCP_0_Y
+    0x00000000, // PA_CL_UCP_0_Z
+    0x00000000, // PA_CL_UCP_0_W
+    0x00000000, // PA_CL_UCP_1_X
+    0x00000000, // PA_CL_UCP_1_Y
+    0x00000000, // PA_CL_UCP_1_Z
+    0x00000000, // PA_CL_UCP_1_W
+    0x00000000, // PA_CL_UCP_2_X
+    0x00000000, // PA_CL_UCP_2_Y
+    0x00000000, // PA_CL_UCP_2_Z
+    0x00000000, // PA_CL_UCP_2_W
+    0x00000000, // PA_CL_UCP_3_X
+    0x00000000, // PA_CL_UCP_3_Y
+    0x00000000, // PA_CL_UCP_3_Z
+    0x00000000, // PA_CL_UCP_3_W
+    0x00000000, // PA_CL_UCP_4_X
+    0x00000000, // PA_CL_UCP_4_Y
+    0x00000000, // PA_CL_UCP_4_Z
+    0x00000000, // PA_CL_UCP_4_W
+    0x00000000, // PA_CL_UCP_5_X
+    0x00000000, // PA_CL_UCP_5_Y
+    0x00000000, // PA_CL_UCP_5_Z
+    0x00000000, // PA_CL_UCP_5_W
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0x00000000, // SPI_PS_INPUT_CNTL_0
+    0x00000000, // SPI_PS_INPUT_CNTL_1
+    0x00000000, // SPI_PS_INPUT_CNTL_2
+    0x00000000, // SPI_PS_INPUT_CNTL_3
+    0x00000000, // SPI_PS_INPUT_CNTL_4
+    0x00000000, // SPI_PS_INPUT_CNTL_5
+    0x00000000, // SPI_PS_INPUT_CNTL_6
+    0x00000000, // SPI_PS_INPUT_CNTL_7
+    0x00000000, // SPI_PS_INPUT_CNTL_8
+    0x00000000, // SPI_PS_INPUT_CNTL_9
+    0x00000000, // SPI_PS_INPUT_CNTL_10
+    0x00000000, // SPI_PS_INPUT_CNTL_11
+    0x00000000, // SPI_PS_INPUT_CNTL_12
+    0x00000000, // SPI_PS_INPUT_CNTL_13
+    0x00000000, // SPI_PS_INPUT_CNTL_14
+    0x00000000, // SPI_PS_INPUT_CNTL_15
+    0x00000000, // SPI_PS_INPUT_CNTL_16
+    0x00000000, // SPI_PS_INPUT_CNTL_17
+    0x00000000, // SPI_PS_INPUT_CNTL_18
+    0x00000000, // SPI_PS_INPUT_CNTL_19
+    0x00000000, // SPI_PS_INPUT_CNTL_20
+    0x00000000, // SPI_PS_INPUT_CNTL_21
+    0x00000000, // SPI_PS_INPUT_CNTL_22
+    0x00000000, // SPI_PS_INPUT_CNTL_23
+    0x00000000, // SPI_PS_INPUT_CNTL_24
+    0x00000000, // SPI_PS_INPUT_CNTL_25
+    0x00000000, // SPI_PS_INPUT_CNTL_26
+    0x00000000, // SPI_PS_INPUT_CNTL_27
+    0x00000000, // SPI_PS_INPUT_CNTL_28
+    0x00000000, // SPI_PS_INPUT_CNTL_29
+    0x00000000, // SPI_PS_INPUT_CNTL_30
+    0x00000000, // SPI_PS_INPUT_CNTL_31
+    0x00000000, // SPI_VS_OUT_CONFIG
+    0, // HOLE
+    0x00000000, // SPI_PS_INPUT_ENA
+    0x00000000, // SPI_PS_INPUT_ADDR
+    0x00000000, // SPI_INTERP_CONTROL_0
+    0x00000002, // SPI_PS_IN_CONTROL
+    0, // HOLE
+    0x00000000, // SPI_BARYC_CNTL
+    0, // HOLE
+    0x00000000, // SPI_TMPRING_SIZE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0x00000000, // SPI_SHADER_POS_FORMAT
+    0x00000000, // SPI_SHADER_Z_FORMAT
+    0x00000000, // SPI_SHADER_COL_FORMAT
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0x00000000, // CB_BLEND0_CONTROL
+    0x00000000, // CB_BLEND1_CONTROL
+    0x00000000, // CB_BLEND2_CONTROL
+    0x00000000, // CB_BLEND3_CONTROL
+    0x00000000, // CB_BLEND4_CONTROL
+    0x00000000, // CB_BLEND5_CONTROL
+    0x00000000, // CB_BLEND6_CONTROL
+    0x00000000, // CB_BLEND7_CONTROL
+};
+static const unsigned int ci_SECT_CONTEXT_def_3[] =
+{
+    0x00000000, // PA_CL_POINT_X_RAD
+    0x00000000, // PA_CL_POINT_Y_RAD
+    0x00000000, // PA_CL_POINT_SIZE
+    0x00000000, // PA_CL_POINT_CULL_RAD
+    0x00000000, // VGT_DMA_BASE_HI
+    0x00000000, // VGT_DMA_BASE
+};
+static const unsigned int ci_SECT_CONTEXT_def_4[] =
+{
+    0x00000000, // DB_DEPTH_CONTROL
+    0x00000000, // DB_EQAA
+    0x00000000, // CB_COLOR_CONTROL
+    0x00000000, // DB_SHADER_CONTROL
+    0x00090000, // PA_CL_CLIP_CNTL
+    0x00000004, // PA_SU_SC_MODE_CNTL
+    0x00000000, // PA_CL_VTE_CNTL
+    0x00000000, // PA_CL_VS_OUT_CNTL
+    0x00000000, // PA_CL_NANINF_CNTL
+    0x00000000, // PA_SU_LINE_STIPPLE_CNTL
+    0x00000000, // PA_SU_LINE_STIPPLE_SCALE
+    0x00000000, // PA_SU_PRIM_FILTER_CNTL
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0x00000000, // PA_SU_POINT_SIZE
+    0x00000000, // PA_SU_POINT_MINMAX
+    0x00000000, // PA_SU_LINE_CNTL
+    0x00000000, // PA_SC_LINE_STIPPLE
+    0x00000000, // VGT_OUTPUT_PATH_CNTL
+    0x00000000, // VGT_HOS_CNTL
+    0x00000000, // VGT_HOS_MAX_TESS_LEVEL
+    0x00000000, // VGT_HOS_MIN_TESS_LEVEL
+    0x00000000, // VGT_HOS_REUSE_DEPTH
+    0x00000000, // VGT_GROUP_PRIM_TYPE
+    0x00000000, // VGT_GROUP_FIRST_DECR
+    0x00000000, // VGT_GROUP_DECR
+    0x00000000, // VGT_GROUP_VECT_0_CNTL
+    0x00000000, // VGT_GROUP_VECT_1_CNTL
+    0x00000000, // VGT_GROUP_VECT_0_FMT_CNTL
+    0x00000000, // VGT_GROUP_VECT_1_FMT_CNTL
+    0x00000000, // VGT_GS_MODE
+    0x00000000, // VGT_GS_ONCHIP_CNTL
+    0x00000000, // PA_SC_MODE_CNTL_0
+    0x00000000, // PA_SC_MODE_CNTL_1
+    0x00000000, // VGT_ENHANCE
+    0x00000100, // VGT_GS_PER_ES
+    0x00000080, // VGT_ES_PER_GS
+    0x00000002, // VGT_GS_PER_VS
+    0x00000000, // VGT_GSVS_RING_OFFSET_1
+    0x00000000, // VGT_GSVS_RING_OFFSET_2
+    0x00000000, // VGT_GSVS_RING_OFFSET_3
+    0x00000000, // VGT_GS_OUT_PRIM_TYPE
+    0x00000000, // IA_ENHANCE
+};
+static const unsigned int ci_SECT_CONTEXT_def_5[] =
+{
+    0x00000000, // WD_ENHANCE
+    0x00000000, // VGT_PRIMITIVEID_EN
+};
+static const unsigned int ci_SECT_CONTEXT_def_6[] =
+{
+    0x00000000, // VGT_PRIMITIVEID_RESET
+};
+static const unsigned int ci_SECT_CONTEXT_def_7[] =
+{
+    0x00000000, // VGT_MULTI_PRIM_IB_RESET_EN
+    0, // HOLE
+    0, // HOLE
+    0x00000000, // VGT_INSTANCE_STEP_RATE_0
+    0x00000000, // VGT_INSTANCE_STEP_RATE_1
+    0x000000ff, // IA_MULTI_VGT_PARAM
+    0x00000000, // VGT_ESGS_RING_ITEMSIZE
+    0x00000000, // VGT_GSVS_RING_ITEMSIZE
+    0x00000000, // VGT_REUSE_OFF
+    0x00000000, // VGT_VTX_CNT_EN
+    0x00000000, // DB_HTILE_SURFACE
+    0x00000000, // DB_SRESULTS_COMPARE_STATE0
+    0x00000000, // DB_SRESULTS_COMPARE_STATE1
+    0x00000000, // DB_PRELOAD_CONTROL
+    0, // HOLE
+    0x00000000, // VGT_STRMOUT_BUFFER_SIZE_0
+    0x00000000, // VGT_STRMOUT_VTX_STRIDE_0
+    0, // HOLE
+    0x00000000, // VGT_STRMOUT_BUFFER_OFFSET_0
+    0x00000000, // VGT_STRMOUT_BUFFER_SIZE_1
+    0x00000000, // VGT_STRMOUT_VTX_STRIDE_1
+    0, // HOLE
+    0x00000000, // VGT_STRMOUT_BUFFER_OFFSET_1
+    0x00000000, // VGT_STRMOUT_BUFFER_SIZE_2
+    0x00000000, // VGT_STRMOUT_VTX_STRIDE_2
+    0, // HOLE
+    0x00000000, // VGT_STRMOUT_BUFFER_OFFSET_2
+    0x00000000, // VGT_STRMOUT_BUFFER_SIZE_3
+    0x00000000, // VGT_STRMOUT_VTX_STRIDE_3
+    0, // HOLE
+    0x00000000, // VGT_STRMOUT_BUFFER_OFFSET_3
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0x00000000, // VGT_STRMOUT_DRAW_OPAQUE_OFFSET
+    0x00000000, // VGT_STRMOUT_DRAW_OPAQUE_BUFFER_FILLED_SIZE
+    0x00000000, // VGT_STRMOUT_DRAW_OPAQUE_VERTEX_STRIDE
+    0, // HOLE
+    0x00000000, // VGT_GS_MAX_VERT_OUT
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0x00000000, // VGT_SHADER_STAGES_EN
+    0x00000000, // VGT_LS_HS_CONFIG
+    0x00000000, // VGT_GS_VERT_ITEMSIZE
+    0x00000000, // VGT_GS_VERT_ITEMSIZE_1
+    0x00000000, // VGT_GS_VERT_ITEMSIZE_2
+    0x00000000, // VGT_GS_VERT_ITEMSIZE_3
+    0x00000000, // VGT_TF_PARAM
+    0x00000000, // DB_ALPHA_TO_MASK
+    0, // HOLE
+    0x00000000, // PA_SU_POLY_OFFSET_DB_FMT_CNTL
+    0x00000000, // PA_SU_POLY_OFFSET_CLAMP
+    0x00000000, // PA_SU_POLY_OFFSET_FRONT_SCALE
+    0x00000000, // PA_SU_POLY_OFFSET_FRONT_OFFSET
+    0x00000000, // PA_SU_POLY_OFFSET_BACK_SCALE
+    0x00000000, // PA_SU_POLY_OFFSET_BACK_OFFSET
+    0x00000000, // VGT_GS_INSTANCE_CNT
+    0x00000000, // VGT_STRMOUT_CONFIG
+    0x00000000, // VGT_STRMOUT_BUFFER_CONFIG
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0x00000000, // PA_SC_CENTROID_PRIORITY_0
+    0x00000000, // PA_SC_CENTROID_PRIORITY_1
+    0x00001000, // PA_SC_LINE_CNTL
+    0x00000000, // PA_SC_AA_CONFIG
+    0x00000005, // PA_SU_VTX_CNTL
+    0x3f800000, // PA_CL_GB_VERT_CLIP_ADJ
+    0x3f800000, // PA_CL_GB_VERT_DISC_ADJ
+    0x3f800000, // PA_CL_GB_HORZ_CLIP_ADJ
+    0x3f800000, // PA_CL_GB_HORZ_DISC_ADJ
+    0x00000000, // PA_SC_AA_SAMPLE_LOCS_PIXEL_X0Y0_0
+    0x00000000, // PA_SC_AA_SAMPLE_LOCS_PIXEL_X0Y0_1
+    0x00000000, // PA_SC_AA_SAMPLE_LOCS_PIXEL_X0Y0_2
+    0x00000000, // PA_SC_AA_SAMPLE_LOCS_PIXEL_X0Y0_3
+    0x00000000, // PA_SC_AA_SAMPLE_LOCS_PIXEL_X1Y0_0
+    0x00000000, // PA_SC_AA_SAMPLE_LOCS_PIXEL_X1Y0_1
+    0x00000000, // PA_SC_AA_SAMPLE_LOCS_PIXEL_X1Y0_2
+    0x00000000, // PA_SC_AA_SAMPLE_LOCS_PIXEL_X1Y0_3
+    0x00000000, // PA_SC_AA_SAMPLE_LOCS_PIXEL_X0Y1_0
+    0x00000000, // PA_SC_AA_SAMPLE_LOCS_PIXEL_X0Y1_1
+    0x00000000, // PA_SC_AA_SAMPLE_LOCS_PIXEL_X0Y1_2
+    0x00000000, // PA_SC_AA_SAMPLE_LOCS_PIXEL_X0Y1_3
+    0x00000000, // PA_SC_AA_SAMPLE_LOCS_PIXEL_X1Y1_0
+    0x00000000, // PA_SC_AA_SAMPLE_LOCS_PIXEL_X1Y1_1
+    0x00000000, // PA_SC_AA_SAMPLE_LOCS_PIXEL_X1Y1_2
+    0x00000000, // PA_SC_AA_SAMPLE_LOCS_PIXEL_X1Y1_3
+    0xffffffff, // PA_SC_AA_MASK_X0Y0_X1Y0
+    0xffffffff, // PA_SC_AA_MASK_X0Y1_X1Y1
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0, // HOLE
+    0x0000000e, // VGT_VERTEX_REUSE_BLOCK_CNTL
+    0x00000010, // VGT_OUT_DEALLOC_CNTL
+    0x00000000, // CB_COLOR0_BASE
+    0x00000000, // CB_COLOR0_PITCH
+    0x00000000, // CB_COLOR0_SLICE
+    0x00000000, // CB_COLOR0_VIEW
+    0x00000000, // CB_COLOR0_INFO
+    0x00000000, // CB_COLOR0_ATTRIB
+    0, // HOLE
+    0x00000000, // CB_COLOR0_CMASK
+    0x00000000, // CB_COLOR0_CMASK_SLICE
+    0x00000000, // CB_COLOR0_FMASK
+    0x00000000, // CB_COLOR0_FMASK_SLICE
+    0x00000000, // CB_COLOR0_CLEAR_WORD0
+    0x00000000, // CB_COLOR0_CLEAR_WORD1
+    0, // HOLE
+    0, // HOLE
+    0x00000000, // CB_COLOR1_BASE
+    0x00000000, // CB_COLOR1_PITCH
+    0x00000000, // CB_COLOR1_SLICE
+    0x00000000, // CB_COLOR1_VIEW
+    0x00000000, // CB_COLOR1_INFO
+    0x00000000, // CB_COLOR1_ATTRIB
+    0, // HOLE
+    0x00000000, // CB_COLOR1_CMASK
+    0x00000000, // CB_COLOR1_CMASK_SLICE
+    0x00000000, // CB_COLOR1_FMASK
+    0x00000000, // CB_COLOR1_FMASK_SLICE
+    0x00000000, // CB_COLOR1_CLEAR_WORD0
+    0x00000000, // CB_COLOR1_CLEAR_WORD1
+    0, // HOLE
+    0, // HOLE
+    0x00000000, // CB_COLOR2_BASE
+    0x00000000, // CB_COLOR2_PITCH
+    0x00000000, // CB_COLOR2_SLICE
+    0x00000000, // CB_COLOR2_VIEW
+    0x00000000, // CB_COLOR2_INFO
+    0x00000000, // CB_COLOR2_ATTRIB
+    0, // HOLE
+    0x00000000, // CB_COLOR2_CMASK
+    0x00000000, // CB_COLOR2_CMASK_SLICE
+    0x00000000, // CB_COLOR2_FMASK
+    0x00000000, // CB_COLOR2_FMASK_SLICE
+    0x00000000, // CB_COLOR2_CLEAR_WORD0
+    0x00000000, // CB_COLOR2_CLEAR_WORD1
+    0, // HOLE
+    0, // HOLE
+    0x00000000, // CB_COLOR3_BASE
+    0x00000000, // CB_COLOR3_PITCH
+    0x00000000, // CB_COLOR3_SLICE
+    0x00000000, // CB_COLOR3_VIEW
+    0x00000000, // CB_COLOR3_INFO
+    0x00000000, // CB_COLOR3_ATTRIB
+    0, // HOLE
+    0x00000000, // CB_COLOR3_CMASK
+    0x00000000, // CB_COLOR3_CMASK_SLICE
+    0x00000000, // CB_COLOR3_FMASK
+    0x00000000, // CB_COLOR3_FMASK_SLICE
+    0x00000000, // CB_COLOR3_CLEAR_WORD0
+    0x00000000, // CB_COLOR3_CLEAR_WORD1
+    0, // HOLE
+    0, // HOLE
+    0x00000000, // CB_COLOR4_BASE
+    0x00000000, // CB_COLOR4_PITCH
+    0x00000000, // CB_COLOR4_SLICE
+    0x00000000, // CB_COLOR4_VIEW
+    0x00000000, // CB_COLOR4_INFO
+    0x00000000, // CB_COLOR4_ATTRIB
+    0, // HOLE
+    0x00000000, // CB_COLOR4_CMASK
+    0x00000000, // CB_COLOR4_CMASK_SLICE
+    0x00000000, // CB_COLOR4_FMASK
+    0x00000000, // CB_COLOR4_FMASK_SLICE
+    0x00000000, // CB_COLOR4_CLEAR_WORD0
+    0x00000000, // CB_COLOR4_CLEAR_WORD1
+    0, // HOLE
+    0, // HOLE
+    0x00000000, // CB_COLOR5_BASE
+    0x00000000, // CB_COLOR5_PITCH
+    0x00000000, // CB_COLOR5_SLICE
+    0x00000000, // CB_COLOR5_VIEW
+    0x00000000, // CB_COLOR5_INFO
+    0x00000000, // CB_COLOR5_ATTRIB
+    0, // HOLE
+    0x00000000, // CB_COLOR5_CMASK
+    0x00000000, // CB_COLOR5_CMASK_SLICE
+    0x00000000, // CB_COLOR5_FMASK
+    0x00000000, // CB_COLOR5_FMASK_SLICE
+    0x00000000, // CB_COLOR5_CLEAR_WORD0
+    0x00000000, // CB_COLOR5_CLEAR_WORD1
+    0, // HOLE
+    0, // HOLE
+    0x00000000, // CB_COLOR6_BASE
+    0x00000000, // CB_COLOR6_PITCH
+    0x00000000, // CB_COLOR6_SLICE
+    0x00000000, // CB_COLOR6_VIEW
+    0x00000000, // CB_COLOR6_INFO
+    0x00000000, // CB_COLOR6_ATTRIB
+    0, // HOLE
+    0x00000000, // CB_COLOR6_CMASK
+    0x00000000, // CB_COLOR6_CMASK_SLICE
+    0x00000000, // CB_COLOR6_FMASK
+    0x00000000, // CB_COLOR6_FMASK_SLICE
+    0x00000000, // CB_COLOR6_CLEAR_WORD0
+    0x00000000, // CB_COLOR6_CLEAR_WORD1
+    0, // HOLE
+    0, // HOLE
+    0x00000000, // CB_COLOR7_BASE
+    0x00000000, // CB_COLOR7_PITCH
+    0x00000000, // CB_COLOR7_SLICE
+    0x00000000, // CB_COLOR7_VIEW
+    0x00000000, // CB_COLOR7_INFO
+    0x00000000, // CB_COLOR7_ATTRIB
+    0, // HOLE
+    0x00000000, // CB_COLOR7_CMASK
+    0x00000000, // CB_COLOR7_CMASK_SLICE
+    0x00000000, // CB_COLOR7_FMASK
+    0x00000000, // CB_COLOR7_FMASK_SLICE
+    0x00000000, // CB_COLOR7_CLEAR_WORD0
+    0x00000000, // CB_COLOR7_CLEAR_WORD1
+};
+static const struct cs_extent_def ci_SECT_CONTEXT_defs[] =
+{
+    {ci_SECT_CONTEXT_def_1, 0x0000a000, 212 },
+    {ci_SECT_CONTEXT_def_2, 0x0000a0d6, 274 },
+    {ci_SECT_CONTEXT_def_3, 0x0000a1f5, 6 },
+    {ci_SECT_CONTEXT_def_4, 0x0000a200, 157 },
+    {ci_SECT_CONTEXT_def_5, 0x0000a2a0, 2 },
+    {ci_SECT_CONTEXT_def_6, 0x0000a2a3, 1 },
+    {ci_SECT_CONTEXT_def_7, 0x0000a2a5, 233 },
+    { 0, 0, 0 }
+};
+static const struct cs_section_def ci_cs_data[] = {
+    { ci_SECT_CONTEXT_defs, SECT_CONTEXT },
+    { 0, SECT_NONE }
+};
diff --git a/drivers/gpu/drm/radeon/clearstate_evergreen.h b/drivers/gpu/drm/radeon/clearstate_evergreen.h
index 4791d856b7fd..63a1ffbb3ced 100644
--- a/drivers/gpu/drm/radeon/clearstate_evergreen.h
+++ b/drivers/gpu/drm/radeon/clearstate_evergreen.h
@@ -1072,7 +1072,7 @@ static const struct cs_extent_def SECT_CTRLCONST_defs[] =
     {SECT_CTRLCONST_def_1, 0x0000f3fc, 2 },
     { 0, 0, 0 }
 };
-struct cs_section_def evergreen_cs_data[] = {
+static const struct cs_section_def evergreen_cs_data[] = {
     { SECT_CONTEXT_defs, SECT_CONTEXT },
     { SECT_CLEAR_defs, SECT_CLEAR },
     { SECT_CTRLCONST_defs, SECT_CTRLCONST },
diff --git a/drivers/gpu/drm/radeon/cypress_dpm.c b/drivers/gpu/drm/radeon/cypress_dpm.c
index 7e5d0b570a30..91bb470de0a3 100644
--- a/drivers/gpu/drm/radeon/cypress_dpm.c
+++ b/drivers/gpu/drm/radeon/cypress_dpm.c
@@ -2014,12 +2014,6 @@ int cypress_dpm_set_power_state(struct radeon_device *rdev)
 	if (eg_pi->pcie_performance_request)
 		cypress_notify_link_speed_change_after_state_change(rdev, new_ps, old_ps);
 
-	ret = rv770_dpm_force_performance_level(rdev, RADEON_DPM_FORCED_LEVEL_AUTO);
-	if (ret) {
-		DRM_ERROR("rv770_dpm_force_performance_level failed\n");
-		return ret;
-	}
-
 	return 0;
 }
 
@@ -2166,7 +2160,8 @@ bool cypress_dpm_vblank_too_short(struct radeon_device *rdev)
 {
 	struct rv7xx_power_info *pi = rv770_get_pi(rdev);
 	u32 vblank_time = r600_dpm_get_vblank_time(rdev);
-	u32 switch_limit = pi->mem_gddr5 ? 450 : 300;
+	/* we never hit the non-gddr5 limit so disable it */
+	u32 switch_limit = pi->mem_gddr5 ? 450 : 0;
 
 	if (vblank_time < switch_limit)
 		return true;
diff --git a/drivers/gpu/drm/radeon/dce6_afmt.c b/drivers/gpu/drm/radeon/dce6_afmt.c
new file mode 100644
index 000000000000..85a69d2ea3d2
--- /dev/null
+++ b/drivers/gpu/drm/radeon/dce6_afmt.c
@@ -0,0 +1,286 @@
+/*
+ * Copyright 2013 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+#include <linux/hdmi.h>
+#include <drm/drmP.h>
+#include "radeon.h"
+#include "sid.h"
+
+static u32 dce6_endpoint_rreg(struct radeon_device *rdev,
+			      u32 block_offset, u32 reg)
+{
+	unsigned long flags;
+	u32 r;
+
+	spin_lock_irqsave(&rdev->end_idx_lock, flags);
+	WREG32(AZ_F0_CODEC_ENDPOINT_INDEX + block_offset, reg);
+	r = RREG32(AZ_F0_CODEC_ENDPOINT_DATA + block_offset);
+	spin_unlock_irqrestore(&rdev->end_idx_lock, flags);
+
+	return r;
+}
+
+static void dce6_endpoint_wreg(struct radeon_device *rdev,
+			       u32 block_offset, u32 reg, u32 v)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&rdev->end_idx_lock, flags);
+	if (ASIC_IS_DCE8(rdev))
+		WREG32(AZ_F0_CODEC_ENDPOINT_INDEX + block_offset, reg);
+	else
+		WREG32(AZ_F0_CODEC_ENDPOINT_INDEX + block_offset,
+		       AZ_ENDPOINT_REG_WRITE_EN | AZ_ENDPOINT_REG_INDEX(reg));
+	WREG32(AZ_F0_CODEC_ENDPOINT_DATA + block_offset, v);
+	spin_unlock_irqrestore(&rdev->end_idx_lock, flags);
+}
+
+#define RREG32_ENDPOINT(block, reg) dce6_endpoint_rreg(rdev, (block), (reg))
+#define WREG32_ENDPOINT(block, reg, v) dce6_endpoint_wreg(rdev, (block), (reg), (v))
+
+
+static void dce6_afmt_get_connected_pins(struct radeon_device *rdev)
+{
+	int i;
+	u32 offset, tmp;
+
+	for (i = 0; i < rdev->audio.num_pins; i++) {
+		offset = rdev->audio.pin[i].offset;
+		tmp = RREG32_ENDPOINT(offset,
+				      AZ_F0_CODEC_PIN_CONTROL_RESPONSE_CONFIGURATION_DEFAULT);
+		if (((tmp & PORT_CONNECTIVITY_MASK) >> PORT_CONNECTIVITY_SHIFT) == 1)
+			rdev->audio.pin[i].connected = false;
+		else
+			rdev->audio.pin[i].connected = true;
+	}
+}
+
+struct r600_audio_pin *dce6_audio_get_pin(struct radeon_device *rdev)
+{
+	int i;
+
+	dce6_afmt_get_connected_pins(rdev);
+
+	for (i = 0; i < rdev->audio.num_pins; i++) {
+		if (rdev->audio.pin[i].connected)
+			return &rdev->audio.pin[i];
+	}
+	DRM_ERROR("No connected audio pins found!\n");
+	return NULL;
+}
+
+void dce6_afmt_select_pin(struct drm_encoder *encoder)
+{
+	struct radeon_device *rdev = encoder->dev->dev_private;
+	struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
+	struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv;
+	u32 offset = dig->afmt->offset;
+
+	if (!dig->afmt->pin)
+		return;
+
+	WREG32(AFMT_AUDIO_SRC_CONTROL + offset,
+	       AFMT_AUDIO_SRC_SELECT(dig->afmt->pin->id));
+}
+
+void dce6_afmt_write_speaker_allocation(struct drm_encoder *encoder)
+{
+	struct radeon_device *rdev = encoder->dev->dev_private;
+	struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
+	struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv;
+	struct drm_connector *connector;
+	struct radeon_connector *radeon_connector = NULL;
+	u32 offset, tmp;
+	u8 *sadb;
+	int sad_count;
+
+	if (!dig->afmt->pin)
+		return;
+
+	offset = dig->afmt->pin->offset;
+
+	list_for_each_entry(connector, &encoder->dev->mode_config.connector_list, head) {
+		if (connector->encoder == encoder)
+			radeon_connector = to_radeon_connector(connector);
+	}
+
+	if (!radeon_connector) {
+		DRM_ERROR("Couldn't find encoder's connector\n");
+		return;
+	}
+
+	sad_count = drm_edid_to_speaker_allocation(radeon_connector->edid, &sadb);
+	if (sad_count < 0) {
+		DRM_ERROR("Couldn't read Speaker Allocation Data Block: %d\n", sad_count);
+		return;
+	}
+
+	/* program the speaker allocation */
+	tmp = RREG32_ENDPOINT(offset, AZ_F0_CODEC_PIN_CONTROL_CHANNEL_SPEAKER);
+	tmp &= ~(DP_CONNECTION | SPEAKER_ALLOCATION_MASK);
+	/* set HDMI mode */
+	tmp |= HDMI_CONNECTION;
+	if (sad_count)
+		tmp |= SPEAKER_ALLOCATION(sadb[0]);
+	else
+		tmp |= SPEAKER_ALLOCATION(5); /* stereo */
+	WREG32_ENDPOINT(offset, AZ_F0_CODEC_PIN_CONTROL_CHANNEL_SPEAKER, tmp);
+
+	kfree(sadb);
+}
+
+void dce6_afmt_write_sad_regs(struct drm_encoder *encoder)
+{
+	struct radeon_device *rdev = encoder->dev->dev_private;
+	struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
+	struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv;
+	u32 offset;
+	struct drm_connector *connector;
+	struct radeon_connector *radeon_connector = NULL;
+	struct cea_sad *sads;
+	int i, sad_count;
+
+	static const u16 eld_reg_to_type[][2] = {
+		{ AZ_F0_CODEC_PIN_CONTROL_AUDIO_DESCRIPTOR0, HDMI_AUDIO_CODING_TYPE_PCM },
+		{ AZ_F0_CODEC_PIN_CONTROL_AUDIO_DESCRIPTOR1, HDMI_AUDIO_CODING_TYPE_AC3 },
+		{ AZ_F0_CODEC_PIN_CONTROL_AUDIO_DESCRIPTOR2, HDMI_AUDIO_CODING_TYPE_MPEG1 },
+		{ AZ_F0_CODEC_PIN_CONTROL_AUDIO_DESCRIPTOR3, HDMI_AUDIO_CODING_TYPE_MP3 },
+		{ AZ_F0_CODEC_PIN_CONTROL_AUDIO_DESCRIPTOR4, HDMI_AUDIO_CODING_TYPE_MPEG2 },
+		{ AZ_F0_CODEC_PIN_CONTROL_AUDIO_DESCRIPTOR5, HDMI_AUDIO_CODING_TYPE_AAC_LC },
+		{ AZ_F0_CODEC_PIN_CONTROL_AUDIO_DESCRIPTOR6, HDMI_AUDIO_CODING_TYPE_DTS },
+		{ AZ_F0_CODEC_PIN_CONTROL_AUDIO_DESCRIPTOR7, HDMI_AUDIO_CODING_TYPE_ATRAC },
+		{ AZ_F0_CODEC_PIN_CONTROL_AUDIO_DESCRIPTOR9, HDMI_AUDIO_CODING_TYPE_EAC3 },
+		{ AZ_F0_CODEC_PIN_CONTROL_AUDIO_DESCRIPTOR10, HDMI_AUDIO_CODING_TYPE_DTS_HD },
+		{ AZ_F0_CODEC_PIN_CONTROL_AUDIO_DESCRIPTOR11, HDMI_AUDIO_CODING_TYPE_MLP },
+		{ AZ_F0_CODEC_PIN_CONTROL_AUDIO_DESCRIPTOR13, HDMI_AUDIO_CODING_TYPE_WMA_PRO },
+	};
+
+	if (!dig->afmt->pin)
+		return;
+
+	offset = dig->afmt->pin->offset;
+
+	list_for_each_entry(connector, &encoder->dev->mode_config.connector_list, head) {
+		if (connector->encoder == encoder)
+			radeon_connector = to_radeon_connector(connector);
+	}
+
+	if (!radeon_connector) {
+		DRM_ERROR("Couldn't find encoder's connector\n");
+		return;
+	}
+
+	sad_count = drm_edid_to_sad(radeon_connector->edid, &sads);
+	if (sad_count < 0) {
+		DRM_ERROR("Couldn't read SADs: %d\n", sad_count);
+		return;
+	}
+	BUG_ON(!sads);
+
+	for (i = 0; i < ARRAY_SIZE(eld_reg_to_type); i++) {
+		u32 value = 0;
+		int j;
+
+		for (j = 0; j < sad_count; j++) {
+			struct cea_sad *sad = &sads[j];
+
+			if (sad->format == eld_reg_to_type[i][1]) {
+				value = MAX_CHANNELS(sad->channels) |
+					DESCRIPTOR_BYTE_2(sad->byte2) |
+					SUPPORTED_FREQUENCIES(sad->freq);
+				if (sad->format == HDMI_AUDIO_CODING_TYPE_PCM)
+					value |= SUPPORTED_FREQUENCIES_STEREO(sad->freq);
+				break;
+			}
+		}
+		WREG32_ENDPOINT(offset, eld_reg_to_type[i][0], value);
+	}
+
+	kfree(sads);
+}
+
+static int dce6_audio_chipset_supported(struct radeon_device *rdev)
+{
+	return !ASIC_IS_NODCE(rdev);
+}
+
+static void dce6_audio_enable(struct radeon_device *rdev,
+			      struct r600_audio_pin *pin,
+			      bool enable)
+{
+	WREG32_ENDPOINT(pin->offset, AZ_F0_CODEC_PIN_CONTROL_HOTPLUG_CONTROL,
+			AUDIO_ENABLED);
+	DRM_INFO("%s audio %d support\n", enable ? "Enabling" : "Disabling", pin->id);
+}
+
+static const u32 pin_offsets[7] =
+{
+	(0x5e00 - 0x5e00),
+	(0x5e18 - 0x5e00),
+	(0x5e30 - 0x5e00),
+	(0x5e48 - 0x5e00),
+	(0x5e60 - 0x5e00),
+	(0x5e78 - 0x5e00),
+	(0x5e90 - 0x5e00),
+};
+
+int dce6_audio_init(struct radeon_device *rdev)
+{
+	int i;
+
+	if (!radeon_audio || !dce6_audio_chipset_supported(rdev))
+		return 0;
+
+	rdev->audio.enabled = true;
+
+	if (ASIC_IS_DCE8(rdev))
+		rdev->audio.num_pins = 7;
+	else
+		rdev->audio.num_pins = 6;
+
+	for (i = 0; i < rdev->audio.num_pins; i++) {
+		rdev->audio.pin[i].channels = -1;
+		rdev->audio.pin[i].rate = -1;
+		rdev->audio.pin[i].bits_per_sample = -1;
+		rdev->audio.pin[i].status_bits = 0;
+		rdev->audio.pin[i].category_code = 0;
+		rdev->audio.pin[i].connected = false;
+		rdev->audio.pin[i].offset = pin_offsets[i];
+		rdev->audio.pin[i].id = i;
+		dce6_audio_enable(rdev, &rdev->audio.pin[i], true);
+	}
+
+	return 0;
+}
+
+void dce6_audio_fini(struct radeon_device *rdev)
+{
+	int i;
+
+	if (!rdev->audio.enabled)
+		return;
+
+	for (i = 0; i < rdev->audio.num_pins; i++)
+		dce6_audio_enable(rdev, &rdev->audio.pin[i], false);
+
+	rdev->audio.enabled = false;
+}
diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c
index d5b49e33315e..b5c67a99dda9 100644
--- a/drivers/gpu/drm/radeon/evergreen.c
+++ b/drivers/gpu/drm/radeon/evergreen.c
@@ -47,7 +47,7 @@ static const u32 crtc_offsets[6] =
 
 #include "clearstate_evergreen.h"
 
-static u32 sumo_rlc_save_restore_register_list[] =
+static const u32 sumo_rlc_save_restore_register_list[] =
 {
 	0x98fc,
 	0x9830,
@@ -131,7 +131,6 @@ static u32 sumo_rlc_save_restore_register_list[] =
 	0x9150,
 	0x802c,
 };
-static u32 sumo_rlc_save_restore_register_list_size = ARRAY_SIZE(sumo_rlc_save_restore_register_list);
 
 static void evergreen_gpu_init(struct radeon_device *rdev);
 void evergreen_fini(struct radeon_device *rdev);
@@ -141,6 +140,12 @@ extern void cayman_cp_int_cntl_setup(struct radeon_device *rdev,
 				     int ring, u32 cp_int_cntl);
 extern void cayman_vm_decode_fault(struct radeon_device *rdev,
 				   u32 status, u32 addr);
+void cik_init_cp_pg_table(struct radeon_device *rdev);
+
+extern u32 si_get_csb_size(struct radeon_device *rdev);
+extern void si_get_csb_buffer(struct radeon_device *rdev, volatile u32 *buffer);
+extern u32 cik_get_csb_size(struct radeon_device *rdev);
+extern void cik_get_csb_buffer(struct radeon_device *rdev, volatile u32 *buffer);
 
 static const u32 evergreen_golden_registers[] =
 {
@@ -1807,7 +1812,8 @@ static u32 evergreen_line_buffer_adjust(struct radeon_device *rdev,
 					struct drm_display_mode *mode,
 					struct drm_display_mode *other_mode)
 {
-	u32 tmp;
+	u32 tmp, buffer_alloc, i;
+	u32 pipe_offset = radeon_crtc->crtc_id * 0x20;
 	/*
 	 * Line Buffer Setup
 	 * There are 3 line buffers, each one shared by 2 display controllers.
@@ -1830,18 +1836,34 @@ static u32 evergreen_line_buffer_adjust(struct radeon_device *rdev,
 	 * non-linked crtcs for maximum line buffer allocation.
 	 */
 	if (radeon_crtc->base.enabled && mode) {
-		if (other_mode)
+		if (other_mode) {
 			tmp = 0; /* 1/2 */
-		else
+			buffer_alloc = 1;
+		} else {
 			tmp = 2; /* whole */
-	} else
+			buffer_alloc = 2;
+		}
+	} else {
 		tmp = 0;
+		buffer_alloc = 0;
+	}
 
 	/* second controller of the pair uses second half of the lb */
 	if (radeon_crtc->crtc_id % 2)
 		tmp += 4;
 	WREG32(DC_LB_MEMORY_SPLIT + radeon_crtc->crtc_offset, tmp);
 
+	if (ASIC_IS_DCE41(rdev) || ASIC_IS_DCE5(rdev)) {
+		WREG32(PIPE0_DMIF_BUFFER_CONTROL + pipe_offset,
+		       DMIF_BUFFERS_ALLOCATED(buffer_alloc));
+		for (i = 0; i < rdev->usec_timeout; i++) {
+			if (RREG32(PIPE0_DMIF_BUFFER_CONTROL + pipe_offset) &
+			    DMIF_BUFFERS_ALLOCATED_COMPLETED)
+				break;
+			udelay(1);
+		}
+	}
+
 	if (radeon_crtc->base.enabled && mode) {
 		switch (tmp) {
 		case 0:
@@ -2881,8 +2903,8 @@ static int evergreen_cp_resume(struct radeon_device *rdev)
 	RREG32(GRBM_SOFT_RESET);
 
 	/* Set ring buffer size */
-	rb_bufsz = drm_order(ring->ring_size / 8);
-	tmp = (drm_order(RADEON_GPU_PAGE_SIZE/8) << 8) | rb_bufsz;
+	rb_bufsz = order_base_2(ring->ring_size / 8);
+	tmp = (order_base_2(RADEON_GPU_PAGE_SIZE/8) << 8) | rb_bufsz;
 #ifdef __BIG_ENDIAN
 	tmp |= BUF_SWAP_32BIT;
 #endif
@@ -3109,7 +3131,7 @@ static void evergreen_gpu_init(struct radeon_device *rdev)
 		rdev->config.evergreen.sx_max_export_size = 256;
 		rdev->config.evergreen.sx_max_export_pos_size = 64;
 		rdev->config.evergreen.sx_max_export_smx_size = 192;
-		rdev->config.evergreen.max_hw_contexts = 8;
+		rdev->config.evergreen.max_hw_contexts = 4;
 		rdev->config.evergreen.sq_num_cf_insts = 2;
 
 		rdev->config.evergreen.sc_prim_fifo_size = 0x40;
@@ -3613,7 +3635,7 @@ bool evergreen_is_display_hung(struct radeon_device *rdev)
 	return true;
 }
 
-static u32 evergreen_gpu_check_soft_reset(struct radeon_device *rdev)
+u32 evergreen_gpu_check_soft_reset(struct radeon_device *rdev)
 {
 	u32 reset_mask = 0;
 	u32 tmp;
@@ -3839,28 +3861,6 @@ bool evergreen_gfx_is_lockup(struct radeon_device *rdev, struct radeon_ring *rin
 	return radeon_ring_test_lockup(rdev, ring);
 }
 
-/**
- * evergreen_dma_is_lockup - Check if the DMA engine is locked up
- *
- * @rdev: radeon_device pointer
- * @ring: radeon_ring structure holding ring information
- *
- * Check if the async DMA engine is locked up.
- * Returns true if the engine appears to be locked up, false if not.
- */
-bool evergreen_dma_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
-{
-	u32 reset_mask = evergreen_gpu_check_soft_reset(rdev);
-
-	if (!(reset_mask & RADEON_RESET_DMA)) {
-		radeon_ring_lockup_update(ring);
-		return false;
-	}
-	/* force ring activities */
-	radeon_ring_force_activity(rdev, ring);
-	return radeon_ring_test_lockup(rdev, ring);
-}
-
 /*
  * RLC
  */
@@ -3894,147 +3894,231 @@ void sumo_rlc_fini(struct radeon_device *rdev)
 		radeon_bo_unref(&rdev->rlc.clear_state_obj);
 		rdev->rlc.clear_state_obj = NULL;
 	}
+
+	/* clear state block */
+	if (rdev->rlc.cp_table_obj) {
+		r = radeon_bo_reserve(rdev->rlc.cp_table_obj, false);
+		if (unlikely(r != 0))
+			dev_warn(rdev->dev, "(%d) reserve RLC cp table bo failed\n", r);
+		radeon_bo_unpin(rdev->rlc.cp_table_obj);
+		radeon_bo_unreserve(rdev->rlc.cp_table_obj);
+
+		radeon_bo_unref(&rdev->rlc.cp_table_obj);
+		rdev->rlc.cp_table_obj = NULL;
+	}
 }
 
+#define CP_ME_TABLE_SIZE    96
+
 int sumo_rlc_init(struct radeon_device *rdev)
 {
-	u32 *src_ptr;
+	const u32 *src_ptr;
 	volatile u32 *dst_ptr;
 	u32 dws, data, i, j, k, reg_num;
-	u32 reg_list_num, reg_list_hdr_blk_index, reg_list_blk_index;
+	u32 reg_list_num, reg_list_hdr_blk_index, reg_list_blk_index = 0;
 	u64 reg_list_mc_addr;
-	struct cs_section_def *cs_data;
+	const struct cs_section_def *cs_data;
 	int r;
 
 	src_ptr = rdev->rlc.reg_list;
 	dws = rdev->rlc.reg_list_size;
+	if (rdev->family >= CHIP_BONAIRE) {
+		dws += (5 * 16) + 48 + 48 + 64;
+	}
 	cs_data = rdev->rlc.cs_data;
 
-	/* save restore block */
-	if (rdev->rlc.save_restore_obj == NULL) {
-		r = radeon_bo_create(rdev, dws * 4, PAGE_SIZE, true,
-				     RADEON_GEM_DOMAIN_VRAM, NULL, &rdev->rlc.save_restore_obj);
+	if (src_ptr) {
+		/* save restore block */
+		if (rdev->rlc.save_restore_obj == NULL) {
+			r = radeon_bo_create(rdev, dws * 4, PAGE_SIZE, true,
+					     RADEON_GEM_DOMAIN_VRAM, NULL, &rdev->rlc.save_restore_obj);
+			if (r) {
+				dev_warn(rdev->dev, "(%d) create RLC sr bo failed\n", r);
+				return r;
+			}
+		}
+
+		r = radeon_bo_reserve(rdev->rlc.save_restore_obj, false);
+		if (unlikely(r != 0)) {
+			sumo_rlc_fini(rdev);
+			return r;
+		}
+		r = radeon_bo_pin(rdev->rlc.save_restore_obj, RADEON_GEM_DOMAIN_VRAM,
+				  &rdev->rlc.save_restore_gpu_addr);
 		if (r) {
-			dev_warn(rdev->dev, "(%d) create RLC sr bo failed\n", r);
+			radeon_bo_unreserve(rdev->rlc.save_restore_obj);
+			dev_warn(rdev->dev, "(%d) pin RLC sr bo failed\n", r);
+			sumo_rlc_fini(rdev);
 			return r;
 		}
-	}
 
-	r = radeon_bo_reserve(rdev->rlc.save_restore_obj, false);
-	if (unlikely(r != 0)) {
-		sumo_rlc_fini(rdev);
-		return r;
-	}
-	r = radeon_bo_pin(rdev->rlc.save_restore_obj, RADEON_GEM_DOMAIN_VRAM,
-			  &rdev->rlc.save_restore_gpu_addr);
-	if (r) {
+		r = radeon_bo_kmap(rdev->rlc.save_restore_obj, (void **)&rdev->rlc.sr_ptr);
+		if (r) {
+			dev_warn(rdev->dev, "(%d) map RLC sr bo failed\n", r);
+			sumo_rlc_fini(rdev);
+			return r;
+		}
+		/* write the sr buffer */
+		dst_ptr = rdev->rlc.sr_ptr;
+		if (rdev->family >= CHIP_TAHITI) {
+			/* SI */
+			for (i = 0; i < rdev->rlc.reg_list_size; i++)
+				dst_ptr[i] = src_ptr[i];
+		} else {
+			/* ON/LN/TN */
+			/* format:
+			 * dw0: (reg2 << 16) | reg1
+			 * dw1: reg1 save space
+			 * dw2: reg2 save space
+			 */
+			for (i = 0; i < dws; i++) {
+				data = src_ptr[i] >> 2;
+				i++;
+				if (i < dws)
+					data |= (src_ptr[i] >> 2) << 16;
+				j = (((i - 1) * 3) / 2);
+				dst_ptr[j] = data;
+			}
+			j = ((i * 3) / 2);
+			dst_ptr[j] = RLC_SAVE_RESTORE_LIST_END_MARKER;
+		}
+		radeon_bo_kunmap(rdev->rlc.save_restore_obj);
 		radeon_bo_unreserve(rdev->rlc.save_restore_obj);
-		dev_warn(rdev->dev, "(%d) pin RLC sr bo failed\n", r);
-		sumo_rlc_fini(rdev);
-		return r;
-	}
-	r = radeon_bo_kmap(rdev->rlc.save_restore_obj, (void **)&rdev->rlc.sr_ptr);
-	if (r) {
-		dev_warn(rdev->dev, "(%d) map RLC sr bo failed\n", r);
-		sumo_rlc_fini(rdev);
-		return r;
-	}
-	/* write the sr buffer */
-	dst_ptr = rdev->rlc.sr_ptr;
-	/* format:
-	 * dw0: (reg2 << 16) | reg1
-	 * dw1: reg1 save space
-	 * dw2: reg2 save space
-	 */
-	for (i = 0; i < dws; i++) {
-		data = src_ptr[i] >> 2;
-		i++;
-		if (i < dws)
-			data |= (src_ptr[i] >> 2) << 16;
-		j = (((i - 1) * 3) / 2);
-		dst_ptr[j] = data;
 	}
-	j = ((i * 3) / 2);
-	dst_ptr[j] = RLC_SAVE_RESTORE_LIST_END_MARKER;
-
-	radeon_bo_kunmap(rdev->rlc.save_restore_obj);
-	radeon_bo_unreserve(rdev->rlc.save_restore_obj);
 
-	/* clear state block */
-	reg_list_num = 0;
-	dws = 0;
-	for (i = 0; cs_data[i].section != NULL; i++) {
-		for (j = 0; cs_data[i].section[j].extent != NULL; j++) {
-			reg_list_num++;
-			dws += cs_data[i].section[j].reg_count;
+	if (cs_data) {
+		/* clear state block */
+		if (rdev->family >= CHIP_BONAIRE) {
+			rdev->rlc.clear_state_size = dws = cik_get_csb_size(rdev);
+		} else if (rdev->family >= CHIP_TAHITI) {
+			rdev->rlc.clear_state_size = si_get_csb_size(rdev);
+			dws = rdev->rlc.clear_state_size + (256 / 4);
+		} else {
+			reg_list_num = 0;
+			dws = 0;
+			for (i = 0; cs_data[i].section != NULL; i++) {
+				for (j = 0; cs_data[i].section[j].extent != NULL; j++) {
+					reg_list_num++;
+					dws += cs_data[i].section[j].reg_count;
+				}
+			}
+			reg_list_blk_index = (3 * reg_list_num + 2);
+			dws += reg_list_blk_index;
+			rdev->rlc.clear_state_size = dws;
 		}
-	}
-	reg_list_blk_index = (3 * reg_list_num + 2);
-	dws += reg_list_blk_index;
 
-	if (rdev->rlc.clear_state_obj == NULL) {
-		r = radeon_bo_create(rdev, dws * 4, PAGE_SIZE, true,
-				     RADEON_GEM_DOMAIN_VRAM, NULL, &rdev->rlc.clear_state_obj);
+		if (rdev->rlc.clear_state_obj == NULL) {
+			r = radeon_bo_create(rdev, dws * 4, PAGE_SIZE, true,
+					     RADEON_GEM_DOMAIN_VRAM, NULL, &rdev->rlc.clear_state_obj);
+			if (r) {
+				dev_warn(rdev->dev, "(%d) create RLC c bo failed\n", r);
+				sumo_rlc_fini(rdev);
+				return r;
+			}
+		}
+		r = radeon_bo_reserve(rdev->rlc.clear_state_obj, false);
+		if (unlikely(r != 0)) {
+			sumo_rlc_fini(rdev);
+			return r;
+		}
+		r = radeon_bo_pin(rdev->rlc.clear_state_obj, RADEON_GEM_DOMAIN_VRAM,
+				  &rdev->rlc.clear_state_gpu_addr);
 		if (r) {
-			dev_warn(rdev->dev, "(%d) create RLC c bo failed\n", r);
+			radeon_bo_unreserve(rdev->rlc.clear_state_obj);
+			dev_warn(rdev->dev, "(%d) pin RLC c bo failed\n", r);
 			sumo_rlc_fini(rdev);
 			return r;
 		}
-	}
-	r = radeon_bo_reserve(rdev->rlc.clear_state_obj, false);
-	if (unlikely(r != 0)) {
-		sumo_rlc_fini(rdev);
-		return r;
-	}
-	r = radeon_bo_pin(rdev->rlc.clear_state_obj, RADEON_GEM_DOMAIN_VRAM,
-			  &rdev->rlc.clear_state_gpu_addr);
-	if (r) {
-
-		radeon_bo_unreserve(rdev->rlc.clear_state_obj);
-		dev_warn(rdev->dev, "(%d) pin RLC c bo failed\n", r);
-		sumo_rlc_fini(rdev);
-		return r;
-	}
-	r = radeon_bo_kmap(rdev->rlc.clear_state_obj, (void **)&rdev->rlc.cs_ptr);
-	if (r) {
-		dev_warn(rdev->dev, "(%d) map RLC c bo failed\n", r);
-		sumo_rlc_fini(rdev);
-		return r;
-	}
-	/* set up the cs buffer */
-	dst_ptr = rdev->rlc.cs_ptr;
-	reg_list_hdr_blk_index = 0;
-	reg_list_mc_addr = rdev->rlc.clear_state_gpu_addr + (reg_list_blk_index * 4);
-	data = upper_32_bits(reg_list_mc_addr);
-	dst_ptr[reg_list_hdr_blk_index] = data;
-	reg_list_hdr_blk_index++;
-	for (i = 0; cs_data[i].section != NULL; i++) {
-		for (j = 0; cs_data[i].section[j].extent != NULL; j++) {
-			reg_num = cs_data[i].section[j].reg_count;
-			data = reg_list_mc_addr & 0xffffffff;
-			dst_ptr[reg_list_hdr_blk_index] = data;
-			reg_list_hdr_blk_index++;
-
-			data = (cs_data[i].section[j].reg_index * 4) & 0xffffffff;
-			dst_ptr[reg_list_hdr_blk_index] = data;
-			reg_list_hdr_blk_index++;
 
-			data = 0x08000000 | (reg_num * 4);
+		r = radeon_bo_kmap(rdev->rlc.clear_state_obj, (void **)&rdev->rlc.cs_ptr);
+		if (r) {
+			dev_warn(rdev->dev, "(%d) map RLC c bo failed\n", r);
+			sumo_rlc_fini(rdev);
+			return r;
+		}
+		/* set up the cs buffer */
+		dst_ptr = rdev->rlc.cs_ptr;
+		if (rdev->family >= CHIP_BONAIRE) {
+			cik_get_csb_buffer(rdev, dst_ptr);
+		} else if (rdev->family >= CHIP_TAHITI) {
+			reg_list_mc_addr = rdev->rlc.clear_state_gpu_addr + 256;
+			dst_ptr[0] = upper_32_bits(reg_list_mc_addr);
+			dst_ptr[1] = lower_32_bits(reg_list_mc_addr);
+			dst_ptr[2] = rdev->rlc.clear_state_size;
+			si_get_csb_buffer(rdev, &dst_ptr[(256/4)]);
+		} else {
+			reg_list_hdr_blk_index = 0;
+			reg_list_mc_addr = rdev->rlc.clear_state_gpu_addr + (reg_list_blk_index * 4);
+			data = upper_32_bits(reg_list_mc_addr);
 			dst_ptr[reg_list_hdr_blk_index] = data;
 			reg_list_hdr_blk_index++;
-
-			for (k = 0; k < reg_num; k++) {
-				data = cs_data[i].section[j].extent[k];
-				dst_ptr[reg_list_blk_index + k] = data;
+			for (i = 0; cs_data[i].section != NULL; i++) {
+				for (j = 0; cs_data[i].section[j].extent != NULL; j++) {
+					reg_num = cs_data[i].section[j].reg_count;
+					data = reg_list_mc_addr & 0xffffffff;
+					dst_ptr[reg_list_hdr_blk_index] = data;
+					reg_list_hdr_blk_index++;
+
+					data = (cs_data[i].section[j].reg_index * 4) & 0xffffffff;
+					dst_ptr[reg_list_hdr_blk_index] = data;
+					reg_list_hdr_blk_index++;
+
+					data = 0x08000000 | (reg_num * 4);
+					dst_ptr[reg_list_hdr_blk_index] = data;
+					reg_list_hdr_blk_index++;
+
+					for (k = 0; k < reg_num; k++) {
+						data = cs_data[i].section[j].extent[k];
+						dst_ptr[reg_list_blk_index + k] = data;
+					}
+					reg_list_mc_addr += reg_num * 4;
+					reg_list_blk_index += reg_num;
+				}
 			}
-			reg_list_mc_addr += reg_num * 4;
-			reg_list_blk_index += reg_num;
+			dst_ptr[reg_list_hdr_blk_index] = RLC_CLEAR_STATE_END_MARKER;
 		}
+		radeon_bo_kunmap(rdev->rlc.clear_state_obj);
+		radeon_bo_unreserve(rdev->rlc.clear_state_obj);
 	}
-	dst_ptr[reg_list_hdr_blk_index] = RLC_CLEAR_STATE_END_MARKER;
 
-	radeon_bo_kunmap(rdev->rlc.clear_state_obj);
-	radeon_bo_unreserve(rdev->rlc.clear_state_obj);
+	if (rdev->rlc.cp_table_size) {
+		if (rdev->rlc.cp_table_obj == NULL) {
+			r = radeon_bo_create(rdev, rdev->rlc.cp_table_size, PAGE_SIZE, true,
+					     RADEON_GEM_DOMAIN_VRAM, NULL, &rdev->rlc.cp_table_obj);
+			if (r) {
+				dev_warn(rdev->dev, "(%d) create RLC cp table bo failed\n", r);
+				sumo_rlc_fini(rdev);
+				return r;
+			}
+		}
+
+		r = radeon_bo_reserve(rdev->rlc.cp_table_obj, false);
+		if (unlikely(r != 0)) {
+			dev_warn(rdev->dev, "(%d) reserve RLC cp table bo failed\n", r);
+			sumo_rlc_fini(rdev);
+			return r;
+		}
+		r = radeon_bo_pin(rdev->rlc.cp_table_obj, RADEON_GEM_DOMAIN_VRAM,
+				  &rdev->rlc.cp_table_gpu_addr);
+		if (r) {
+			radeon_bo_unreserve(rdev->rlc.cp_table_obj);
+			dev_warn(rdev->dev, "(%d) pin RLC cp_table bo failed\n", r);
+			sumo_rlc_fini(rdev);
+			return r;
+		}
+		r = radeon_bo_kmap(rdev->rlc.cp_table_obj, (void **)&rdev->rlc.cp_table_ptr);
+		if (r) {
+			dev_warn(rdev->dev, "(%d) map RLC cp table bo failed\n", r);
+			sumo_rlc_fini(rdev);
+			return r;
+		}
+
+		cik_init_cp_pg_table(rdev);
+
+		radeon_bo_kunmap(rdev->rlc.cp_table_obj);
+		radeon_bo_unreserve(rdev->rlc.cp_table_obj);
+
+	}
 
 	return 0;
 }
@@ -4959,143 +5043,6 @@ restart_ih:
 	return IRQ_HANDLED;
 }
 
-/**
- * evergreen_dma_fence_ring_emit - emit a fence on the DMA ring
- *
- * @rdev: radeon_device pointer
- * @fence: radeon fence object
- *
- * Add a DMA fence packet to the ring to write
- * the fence seq number and DMA trap packet to generate
- * an interrupt if needed (evergreen-SI).
- */
-void evergreen_dma_fence_ring_emit(struct radeon_device *rdev,
-				   struct radeon_fence *fence)
-{
-	struct radeon_ring *ring = &rdev->ring[fence->ring];
-	u64 addr = rdev->fence_drv[fence->ring].gpu_addr;
-	/* write the fence */
-	radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_FENCE, 0, 0));
-	radeon_ring_write(ring, addr & 0xfffffffc);
-	radeon_ring_write(ring, (upper_32_bits(addr) & 0xff));
-	radeon_ring_write(ring, fence->seq);
-	/* generate an interrupt */
-	radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_TRAP, 0, 0));
-	/* flush HDP */
-	radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_SRBM_WRITE, 0, 0));
-	radeon_ring_write(ring, (0xf << 16) | (HDP_MEM_COHERENCY_FLUSH_CNTL >> 2));
-	radeon_ring_write(ring, 1);
-}
-
-/**
- * evergreen_dma_ring_ib_execute - schedule an IB on the DMA engine
- *
- * @rdev: radeon_device pointer
- * @ib: IB object to schedule
- *
- * Schedule an IB in the DMA ring (evergreen).
- */
-void evergreen_dma_ring_ib_execute(struct radeon_device *rdev,
-				   struct radeon_ib *ib)
-{
-	struct radeon_ring *ring = &rdev->ring[ib->ring];
-
-	if (rdev->wb.enabled) {
-		u32 next_rptr = ring->wptr + 4;
-		while ((next_rptr & 7) != 5)
-			next_rptr++;
-		next_rptr += 3;
-		radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_WRITE, 0, 1));
-		radeon_ring_write(ring, ring->next_rptr_gpu_addr & 0xfffffffc);
-		radeon_ring_write(ring, upper_32_bits(ring->next_rptr_gpu_addr) & 0xff);
-		radeon_ring_write(ring, next_rptr);
-	}
-
-	/* The indirect buffer packet must end on an 8 DW boundary in the DMA ring.
-	 * Pad as necessary with NOPs.
-	 */
-	while ((ring->wptr & 7) != 5)
-		radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_NOP, 0, 0));
-	radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_INDIRECT_BUFFER, 0, 0));
-	radeon_ring_write(ring, (ib->gpu_addr & 0xFFFFFFE0));
-	radeon_ring_write(ring, (ib->length_dw << 12) | (upper_32_bits(ib->gpu_addr) & 0xFF));
-
-}
-
-/**
- * evergreen_copy_dma - copy pages using the DMA engine
- *
- * @rdev: radeon_device pointer
- * @src_offset: src GPU address
- * @dst_offset: dst GPU address
- * @num_gpu_pages: number of GPU pages to xfer
- * @fence: radeon fence object
- *
- * Copy GPU paging using the DMA engine (evergreen-cayman).
- * Used by the radeon ttm implementation to move pages if
- * registered as the asic copy callback.
- */
-int evergreen_copy_dma(struct radeon_device *rdev,
-		       uint64_t src_offset, uint64_t dst_offset,
-		       unsigned num_gpu_pages,
-		       struct radeon_fence **fence)
-{
-	struct radeon_semaphore *sem = NULL;
-	int ring_index = rdev->asic->copy.dma_ring_index;
-	struct radeon_ring *ring = &rdev->ring[ring_index];
-	u32 size_in_dw, cur_size_in_dw;
-	int i, num_loops;
-	int r = 0;
-
-	r = radeon_semaphore_create(rdev, &sem);
-	if (r) {
-		DRM_ERROR("radeon: moving bo (%d).\n", r);
-		return r;
-	}
-
-	size_in_dw = (num_gpu_pages << RADEON_GPU_PAGE_SHIFT) / 4;
-	num_loops = DIV_ROUND_UP(size_in_dw, 0xfffff);
-	r = radeon_ring_lock(rdev, ring, num_loops * 5 + 11);
-	if (r) {
-		DRM_ERROR("radeon: moving bo (%d).\n", r);
-		radeon_semaphore_free(rdev, &sem, NULL);
-		return r;
-	}
-
-	if (radeon_fence_need_sync(*fence, ring->idx)) {
-		radeon_semaphore_sync_rings(rdev, sem, (*fence)->ring,
-					    ring->idx);
-		radeon_fence_note_sync(*fence, ring->idx);
-	} else {
-		radeon_semaphore_free(rdev, &sem, NULL);
-	}
-
-	for (i = 0; i < num_loops; i++) {
-		cur_size_in_dw = size_in_dw;
-		if (cur_size_in_dw > 0xFFFFF)
-			cur_size_in_dw = 0xFFFFF;
-		size_in_dw -= cur_size_in_dw;
-		radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_COPY, 0, cur_size_in_dw));
-		radeon_ring_write(ring, dst_offset & 0xfffffffc);
-		radeon_ring_write(ring, src_offset & 0xfffffffc);
-		radeon_ring_write(ring, upper_32_bits(dst_offset) & 0xff);
-		radeon_ring_write(ring, upper_32_bits(src_offset) & 0xff);
-		src_offset += cur_size_in_dw * 4;
-		dst_offset += cur_size_in_dw * 4;
-	}
-
-	r = radeon_fence_emit(rdev, fence, ring->idx);
-	if (r) {
-		radeon_ring_unlock_undo(rdev, ring);
-		return r;
-	}
-
-	radeon_ring_unlock_commit(rdev, ring);
-	radeon_semaphore_free(rdev, &sem, *fence);
-
-	return r;
-}
-
 static int evergreen_startup(struct radeon_device *rdev)
 {
 	struct radeon_ring *ring;
@@ -5106,6 +5053,11 @@ static int evergreen_startup(struct radeon_device *rdev)
 	/* enable aspm */
 	evergreen_program_aspm(rdev);
 
+	/* scratch needs to be initialized before MC */
+	r = r600_vram_scratch_init(rdev);
+	if (r)
+		return r;
+
 	evergreen_mc_program(rdev);
 
 	if (ASIC_IS_DCE5(rdev)) {
@@ -5131,10 +5083,6 @@ static int evergreen_startup(struct radeon_device *rdev)
 		}
 	}
 
-	r = r600_vram_scratch_init(rdev);
-	if (r)
-		return r;
-
 	if (rdev->flags & RADEON_IS_AGP) {
 		evergreen_agp_enable(rdev);
 	} else {
@@ -5144,17 +5092,11 @@ static int evergreen_startup(struct radeon_device *rdev)
 	}
 	evergreen_gpu_init(rdev);
 
-	r = evergreen_blit_init(rdev);
-	if (r) {
-		r600_blit_fini(rdev);
-		rdev->asic->copy.copy = NULL;
-		dev_warn(rdev->dev, "failed blitter (%d) falling back to memcpy\n", r);
-	}
-
 	/* allocate rlc buffers */
 	if (rdev->flags & RADEON_IS_IGP) {
 		rdev->rlc.reg_list = sumo_rlc_save_restore_register_list;
-		rdev->rlc.reg_list_size = sumo_rlc_save_restore_register_list_size;
+		rdev->rlc.reg_list_size =
+			(u32)ARRAY_SIZE(sumo_rlc_save_restore_register_list);
 		rdev->rlc.cs_data = evergreen_cs_data;
 		r = sumo_rlc_init(rdev);
 		if (r) {
@@ -5180,7 +5122,7 @@ static int evergreen_startup(struct radeon_device *rdev)
 		return r;
 	}
 
-	r = rv770_uvd_resume(rdev);
+	r = uvd_v2_2_resume(rdev);
 	if (!r) {
 		r = radeon_fence_driver_start_ring(rdev,
 						   R600_RING_TYPE_UVD_INDEX);
@@ -5209,14 +5151,14 @@ static int evergreen_startup(struct radeon_device *rdev)
 	ring = &rdev->ring[RADEON_RING_TYPE_GFX_INDEX];
 	r = radeon_ring_init(rdev, ring, ring->ring_size, RADEON_WB_CP_RPTR_OFFSET,
 			     R600_CP_RB_RPTR, R600_CP_RB_WPTR,
-			     0, 0xfffff, RADEON_CP_PACKET2);
+			     RADEON_CP_PACKET2);
 	if (r)
 		return r;
 
 	ring = &rdev->ring[R600_RING_TYPE_DMA_INDEX];
 	r = radeon_ring_init(rdev, ring, ring->ring_size, R600_WB_DMA_RPTR_OFFSET,
 			     DMA_RB_RPTR, DMA_RB_WPTR,
-			     2, 0x3fffc, DMA_PACKET(DMA_PACKET_NOP, 0, 0));
+			     DMA_PACKET(DMA_PACKET_NOP, 0, 0));
 	if (r)
 		return r;
 
@@ -5232,12 +5174,11 @@ static int evergreen_startup(struct radeon_device *rdev)
 
 	ring = &rdev->ring[R600_RING_TYPE_UVD_INDEX];
 	if (ring->ring_size) {
-		r = radeon_ring_init(rdev, ring, ring->ring_size,
-				     R600_WB_UVD_RPTR_OFFSET,
+		r = radeon_ring_init(rdev, ring, ring->ring_size, 0,
 				     UVD_RBC_RB_RPTR, UVD_RBC_RB_WPTR,
-				     0, 0xfffff, RADEON_CP_PACKET2);
+				     RADEON_CP_PACKET2);
 		if (!r)
-			r = r600_uvd_init(rdev);
+			r = uvd_v1_0_init(rdev);
 
 		if (r)
 			DRM_ERROR("radeon: error initializing UVD (%d).\n", r);
@@ -5292,7 +5233,7 @@ int evergreen_resume(struct radeon_device *rdev)
 int evergreen_suspend(struct radeon_device *rdev)
 {
 	r600_audio_fini(rdev);
-	r600_uvd_stop(rdev);
+	uvd_v1_0_fini(rdev);
 	radeon_uvd_suspend(rdev);
 	r700_cp_stop(rdev);
 	r600_dma_stop(rdev);
@@ -5420,7 +5361,6 @@ int evergreen_init(struct radeon_device *rdev)
 void evergreen_fini(struct radeon_device *rdev)
 {
 	r600_audio_fini(rdev);
-	r600_blit_fini(rdev);
 	r700_cp_fini(rdev);
 	r600_dma_fini(rdev);
 	r600_irq_fini(rdev);
@@ -5430,7 +5370,7 @@ void evergreen_fini(struct radeon_device *rdev)
 	radeon_ib_pool_fini(rdev);
 	radeon_irq_kms_fini(rdev);
 	evergreen_pcie_gart_fini(rdev);
-	r600_uvd_stop(rdev);
+	uvd_v1_0_fini(rdev);
 	radeon_uvd_fini(rdev);
 	r600_vram_scratch_fini(rdev);
 	radeon_gem_fini(rdev);
diff --git a/drivers/gpu/drm/radeon/evergreen_blit_kms.c b/drivers/gpu/drm/radeon/evergreen_blit_kms.c
deleted file mode 100644
index 057c87b6515a..000000000000
--- a/drivers/gpu/drm/radeon/evergreen_blit_kms.c
+++ /dev/null
@@ -1,729 +0,0 @@
-/*
- * Copyright 2010 Advanced Micro Devices, Inc.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice (including the next
- * paragraph) shall be included in all copies or substantial portions of the
- * Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE COPYRIGHT HOLDER(S) AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM, DAMAGES OR
- * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
- * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
- * DEALINGS IN THE SOFTWARE.
- *
- * Authors:
- *     Alex Deucher <alexander.deucher@amd.com>
- */
-
-#include <drm/drmP.h>
-#include <drm/radeon_drm.h>
-#include "radeon.h"
-
-#include "evergreend.h"
-#include "evergreen_blit_shaders.h"
-#include "cayman_blit_shaders.h"
-#include "radeon_blit_common.h"
-
-/* emits 17 */
-static void
-set_render_target(struct radeon_device *rdev, int format,
-		  int w, int h, u64 gpu_addr)
-{
-	struct radeon_ring *ring = &rdev->ring[RADEON_RING_TYPE_GFX_INDEX];
-	u32 cb_color_info;
-	int pitch, slice;
-
-	h = ALIGN(h, 8);
-	if (h < 8)
-		h = 8;
-
-	cb_color_info = CB_FORMAT(format) |
-		CB_SOURCE_FORMAT(CB_SF_EXPORT_NORM) |
-		CB_ARRAY_MODE(ARRAY_1D_TILED_THIN1);
-	pitch = (w / 8) - 1;
-	slice = ((w * h) / 64) - 1;
-
-	radeon_ring_write(ring, PACKET3(PACKET3_SET_CONTEXT_REG, 15));
-	radeon_ring_write(ring, (CB_COLOR0_BASE - PACKET3_SET_CONTEXT_REG_START) >> 2);
-	radeon_ring_write(ring, gpu_addr >> 8);
-	radeon_ring_write(ring, pitch);
-	radeon_ring_write(ring, slice);
-	radeon_ring_write(ring, 0);
-	radeon_ring_write(ring, cb_color_info);
-	radeon_ring_write(ring, 0);
-	radeon_ring_write(ring, (w - 1) | ((h - 1) << 16));
-	radeon_ring_write(ring, 0);
-	radeon_ring_write(ring, 0);
-	radeon_ring_write(ring, 0);
-	radeon_ring_write(ring, 0);
-	radeon_ring_write(ring, 0);
-	radeon_ring_write(ring, 0);
-	radeon_ring_write(ring, 0);
-	radeon_ring_write(ring, 0);
-}
-
-/* emits 5dw */
-static void
-cp_set_surface_sync(struct radeon_device *rdev,
-		    u32 sync_type, u32 size,
-		    u64 mc_addr)
-{
-	struct radeon_ring *ring = &rdev->ring[RADEON_RING_TYPE_GFX_INDEX];
-	u32 cp_coher_size;
-
-	if (size == 0xffffffff)
-		cp_coher_size = 0xffffffff;
-	else
-		cp_coher_size = ((size + 255) >> 8);
-
-	if (rdev->family >= CHIP_CAYMAN) {
-		/* CP_COHER_CNTL2 has to be set manually when submitting a surface_sync
-		 * to the RB directly. For IBs, the CP programs this as part of the
-		 * surface_sync packet.
-		 */
-		radeon_ring_write(ring, PACKET3(PACKET3_SET_CONFIG_REG, 1));
-		radeon_ring_write(ring, (0x85e8 - PACKET3_SET_CONFIG_REG_START) >> 2);
-		radeon_ring_write(ring, 0); /* CP_COHER_CNTL2 */
-	}
-	radeon_ring_write(ring, PACKET3(PACKET3_SURFACE_SYNC, 3));
-	radeon_ring_write(ring, sync_type);
-	radeon_ring_write(ring, cp_coher_size);
-	radeon_ring_write(ring, mc_addr >> 8);
-	radeon_ring_write(ring, 10); /* poll interval */
-}
-
-/* emits 11dw + 1 surface sync = 16dw */
-static void
-set_shaders(struct radeon_device *rdev)
-{
-	struct radeon_ring *ring = &rdev->ring[RADEON_RING_TYPE_GFX_INDEX];
-	u64 gpu_addr;
-
-	/* VS */
-	gpu_addr = rdev->r600_blit.shader_gpu_addr + rdev->r600_blit.vs_offset;
-	radeon_ring_write(ring, PACKET3(PACKET3_SET_CONTEXT_REG, 3));
-	radeon_ring_write(ring, (SQ_PGM_START_VS - PACKET3_SET_CONTEXT_REG_START) >> 2);
-	radeon_ring_write(ring, gpu_addr >> 8);
-	radeon_ring_write(ring, 2);
-	radeon_ring_write(ring, 0);
-
-	/* PS */
-	gpu_addr = rdev->r600_blit.shader_gpu_addr + rdev->r600_blit.ps_offset;
-	radeon_ring_write(ring, PACKET3(PACKET3_SET_CONTEXT_REG, 4));
-	radeon_ring_write(ring, (SQ_PGM_START_PS - PACKET3_SET_CONTEXT_REG_START) >> 2);
-	radeon_ring_write(ring, gpu_addr >> 8);
-	radeon_ring_write(ring, 1);
-	radeon_ring_write(ring, 0);
-	radeon_ring_write(ring, 2);
-
-	gpu_addr = rdev->r600_blit.shader_gpu_addr + rdev->r600_blit.vs_offset;
-	cp_set_surface_sync(rdev, PACKET3_SH_ACTION_ENA, 512, gpu_addr);
-}
-
-/* emits 10 + 1 sync (5) = 15 */
-static void
-set_vtx_resource(struct radeon_device *rdev, u64 gpu_addr)
-{
-	struct radeon_ring *ring = &rdev->ring[RADEON_RING_TYPE_GFX_INDEX];
-	u32 sq_vtx_constant_word2, sq_vtx_constant_word3;
-
-	/* high addr, stride */
-	sq_vtx_constant_word2 = SQ_VTXC_BASE_ADDR_HI(upper_32_bits(gpu_addr) & 0xff) |
-		SQ_VTXC_STRIDE(16);
-#ifdef __BIG_ENDIAN
-	sq_vtx_constant_word2 |= SQ_VTXC_ENDIAN_SWAP(SQ_ENDIAN_8IN32);
-#endif
-	/* xyzw swizzles */
-	sq_vtx_constant_word3 = SQ_VTCX_SEL_X(SQ_SEL_X) |
-		SQ_VTCX_SEL_Y(SQ_SEL_Y) |
-		SQ_VTCX_SEL_Z(SQ_SEL_Z) |
-		SQ_VTCX_SEL_W(SQ_SEL_W);
-
-	radeon_ring_write(ring, PACKET3(PACKET3_SET_RESOURCE, 8));
-	radeon_ring_write(ring, 0x580);
-	radeon_ring_write(ring, gpu_addr & 0xffffffff);
-	radeon_ring_write(ring, 48 - 1); /* size */
-	radeon_ring_write(ring, sq_vtx_constant_word2);
-	radeon_ring_write(ring, sq_vtx_constant_word3);
-	radeon_ring_write(ring, 0);
-	radeon_ring_write(ring, 0);
-	radeon_ring_write(ring, 0);
-	radeon_ring_write(ring, S__SQ_CONSTANT_TYPE(SQ_TEX_VTX_VALID_BUFFER));
-
-	if ((rdev->family == CHIP_CEDAR) ||
-	    (rdev->family == CHIP_PALM) ||
-	    (rdev->family == CHIP_SUMO) ||
-	    (rdev->family == CHIP_SUMO2) ||
-	    (rdev->family == CHIP_CAICOS))
-		cp_set_surface_sync(rdev,
-				    PACKET3_TC_ACTION_ENA, 48, gpu_addr);
-	else
-		cp_set_surface_sync(rdev,
-				    PACKET3_VC_ACTION_ENA, 48, gpu_addr);
-
-}
-
-/* emits 10 */
-static void
-set_tex_resource(struct radeon_device *rdev,
-		 int format, int w, int h, int pitch,
-		 u64 gpu_addr, u32 size)
-{
-	struct radeon_ring *ring = &rdev->ring[RADEON_RING_TYPE_GFX_INDEX];
-	u32 sq_tex_resource_word0, sq_tex_resource_word1;
-	u32 sq_tex_resource_word4, sq_tex_resource_word7;
-
-	if (h < 1)
-		h = 1;
-
-	sq_tex_resource_word0 = TEX_DIM(SQ_TEX_DIM_2D);
-	sq_tex_resource_word0 |= ((((pitch >> 3) - 1) << 6) |
-				  ((w - 1) << 18));
-	sq_tex_resource_word1 = ((h - 1) << 0) |
-				TEX_ARRAY_MODE(ARRAY_1D_TILED_THIN1);
-	/* xyzw swizzles */
-	sq_tex_resource_word4 = TEX_DST_SEL_X(SQ_SEL_X) |
-				TEX_DST_SEL_Y(SQ_SEL_Y) |
-				TEX_DST_SEL_Z(SQ_SEL_Z) |
-				TEX_DST_SEL_W(SQ_SEL_W);
-
-	sq_tex_resource_word7 = format |
-		S__SQ_CONSTANT_TYPE(SQ_TEX_VTX_VALID_TEXTURE);
-
-	cp_set_surface_sync(rdev,
-			    PACKET3_TC_ACTION_ENA, size, gpu_addr);
-
-	radeon_ring_write(ring, PACKET3(PACKET3_SET_RESOURCE, 8));
-	radeon_ring_write(ring, 0);
-	radeon_ring_write(ring, sq_tex_resource_word0);
-	radeon_ring_write(ring, sq_tex_resource_word1);
-	radeon_ring_write(ring, gpu_addr >> 8);
-	radeon_ring_write(ring, gpu_addr >> 8);
-	radeon_ring_write(ring, sq_tex_resource_word4);
-	radeon_ring_write(ring, 0);
-	radeon_ring_write(ring, 0);
-	radeon_ring_write(ring, sq_tex_resource_word7);
-}
-
-/* emits 12 */
-static void
-set_scissors(struct radeon_device *rdev, int x1, int y1,
-	     int x2, int y2)
-{
-	struct radeon_ring *ring = &rdev->ring[RADEON_RING_TYPE_GFX_INDEX];
-	/* workaround some hw bugs */
-	if (x2 == 0)
-		x1 = 1;
-	if (y2 == 0)
-		y1 = 1;
-	if (rdev->family >= CHIP_CAYMAN) {
-		if ((x2 == 1) && (y2 == 1))
-			x2 = 2;
-	}
-
-	radeon_ring_write(ring, PACKET3(PACKET3_SET_CONTEXT_REG, 2));
-	radeon_ring_write(ring, (PA_SC_SCREEN_SCISSOR_TL - PACKET3_SET_CONTEXT_REG_START) >> 2);
-	radeon_ring_write(ring, (x1 << 0) | (y1 << 16));
-	radeon_ring_write(ring, (x2 << 0) | (y2 << 16));
-
-	radeon_ring_write(ring, PACKET3(PACKET3_SET_CONTEXT_REG, 2));
-	radeon_ring_write(ring, (PA_SC_GENERIC_SCISSOR_TL - PACKET3_SET_CONTEXT_REG_START) >> 2);
-	radeon_ring_write(ring, (x1 << 0) | (y1 << 16) | (1 << 31));
-	radeon_ring_write(ring, (x2 << 0) | (y2 << 16));
-
-	radeon_ring_write(ring, PACKET3(PACKET3_SET_CONTEXT_REG, 2));
-	radeon_ring_write(ring, (PA_SC_WINDOW_SCISSOR_TL - PACKET3_SET_CONTEXT_REG_START) >> 2);
-	radeon_ring_write(ring, (x1 << 0) | (y1 << 16) | (1 << 31));
-	radeon_ring_write(ring, (x2 << 0) | (y2 << 16));
-}
-
-/* emits 10 */
-static void
-draw_auto(struct radeon_device *rdev)
-{
-	struct radeon_ring *ring = &rdev->ring[RADEON_RING_TYPE_GFX_INDEX];
-	radeon_ring_write(ring, PACKET3(PACKET3_SET_CONFIG_REG, 1));
-	radeon_ring_write(ring, (VGT_PRIMITIVE_TYPE - PACKET3_SET_CONFIG_REG_START) >> 2);
-	radeon_ring_write(ring, DI_PT_RECTLIST);
-
-	radeon_ring_write(ring, PACKET3(PACKET3_INDEX_TYPE, 0));
-	radeon_ring_write(ring,
-#ifdef __BIG_ENDIAN
-			  (2 << 2) |
-#endif
-			  DI_INDEX_SIZE_16_BIT);
-
-	radeon_ring_write(ring, PACKET3(PACKET3_NUM_INSTANCES, 0));
-	radeon_ring_write(ring, 1);
-
-	radeon_ring_write(ring, PACKET3(PACKET3_DRAW_INDEX_AUTO, 1));
-	radeon_ring_write(ring, 3);
-	radeon_ring_write(ring, DI_SRC_SEL_AUTO_INDEX);
-
-}
-
-/* emits 39 */
-static void
-set_default_state(struct radeon_device *rdev)
-{
-	struct radeon_ring *ring = &rdev->ring[RADEON_RING_TYPE_GFX_INDEX];
-	u32 sq_config, sq_gpr_resource_mgmt_1, sq_gpr_resource_mgmt_2, sq_gpr_resource_mgmt_3;
-	u32 sq_thread_resource_mgmt, sq_thread_resource_mgmt_2;
-	u32 sq_stack_resource_mgmt_1, sq_stack_resource_mgmt_2, sq_stack_resource_mgmt_3;
-	int num_ps_gprs, num_vs_gprs, num_temp_gprs;
-	int num_gs_gprs, num_es_gprs, num_hs_gprs, num_ls_gprs;
-	int num_ps_threads, num_vs_threads, num_gs_threads, num_es_threads;
-	int num_hs_threads, num_ls_threads;
-	int num_ps_stack_entries, num_vs_stack_entries, num_gs_stack_entries, num_es_stack_entries;
-	int num_hs_stack_entries, num_ls_stack_entries;
-	u64 gpu_addr;
-	int dwords;
-
-	/* set clear context state */
-	radeon_ring_write(ring, PACKET3(PACKET3_CLEAR_STATE, 0));
-	radeon_ring_write(ring, 0);
-
-	if (rdev->family < CHIP_CAYMAN) {
-		switch (rdev->family) {
-		case CHIP_CEDAR:
-		default:
-			num_ps_gprs = 93;
-			num_vs_gprs = 46;
-			num_temp_gprs = 4;
-			num_gs_gprs = 31;
-			num_es_gprs = 31;
-			num_hs_gprs = 23;
-			num_ls_gprs = 23;
-			num_ps_threads = 96;
-			num_vs_threads = 16;
-			num_gs_threads = 16;
-			num_es_threads = 16;
-			num_hs_threads = 16;
-			num_ls_threads = 16;
-			num_ps_stack_entries = 42;
-			num_vs_stack_entries = 42;
-			num_gs_stack_entries = 42;
-			num_es_stack_entries = 42;
-			num_hs_stack_entries = 42;
-			num_ls_stack_entries = 42;
-			break;
-		case CHIP_REDWOOD:
-			num_ps_gprs = 93;
-			num_vs_gprs = 46;
-			num_temp_gprs = 4;
-			num_gs_gprs = 31;
-			num_es_gprs = 31;
-			num_hs_gprs = 23;
-			num_ls_gprs = 23;
-			num_ps_threads = 128;
-			num_vs_threads = 20;
-			num_gs_threads = 20;
-			num_es_threads = 20;
-			num_hs_threads = 20;
-			num_ls_threads = 20;
-			num_ps_stack_entries = 42;
-			num_vs_stack_entries = 42;
-			num_gs_stack_entries = 42;
-			num_es_stack_entries = 42;
-			num_hs_stack_entries = 42;
-			num_ls_stack_entries = 42;
-			break;
-		case CHIP_JUNIPER:
-			num_ps_gprs = 93;
-			num_vs_gprs = 46;
-			num_temp_gprs = 4;
-			num_gs_gprs = 31;
-			num_es_gprs = 31;
-			num_hs_gprs = 23;
-			num_ls_gprs = 23;
-			num_ps_threads = 128;
-			num_vs_threads = 20;
-			num_gs_threads = 20;
-			num_es_threads = 20;
-			num_hs_threads = 20;
-			num_ls_threads = 20;
-			num_ps_stack_entries = 85;
-			num_vs_stack_entries = 85;
-			num_gs_stack_entries = 85;
-			num_es_stack_entries = 85;
-			num_hs_stack_entries = 85;
-			num_ls_stack_entries = 85;
-			break;
-		case CHIP_CYPRESS:
-		case CHIP_HEMLOCK:
-			num_ps_gprs = 93;
-			num_vs_gprs = 46;
-			num_temp_gprs = 4;
-			num_gs_gprs = 31;
-			num_es_gprs = 31;
-			num_hs_gprs = 23;
-			num_ls_gprs = 23;
-			num_ps_threads = 128;
-			num_vs_threads = 20;
-			num_gs_threads = 20;
-			num_es_threads = 20;
-			num_hs_threads = 20;
-			num_ls_threads = 20;
-			num_ps_stack_entries = 85;
-			num_vs_stack_entries = 85;
-			num_gs_stack_entries = 85;
-			num_es_stack_entries = 85;
-			num_hs_stack_entries = 85;
-			num_ls_stack_entries = 85;
-			break;
-		case CHIP_PALM:
-			num_ps_gprs = 93;
-			num_vs_gprs = 46;
-			num_temp_gprs = 4;
-			num_gs_gprs = 31;
-			num_es_gprs = 31;
-			num_hs_gprs = 23;
-			num_ls_gprs = 23;
-			num_ps_threads = 96;
-			num_vs_threads = 16;
-			num_gs_threads = 16;
-			num_es_threads = 16;
-			num_hs_threads = 16;
-			num_ls_threads = 16;
-			num_ps_stack_entries = 42;
-			num_vs_stack_entries = 42;
-			num_gs_stack_entries = 42;
-			num_es_stack_entries = 42;
-			num_hs_stack_entries = 42;
-			num_ls_stack_entries = 42;
-			break;
-		case CHIP_SUMO:
-			num_ps_gprs = 93;
-			num_vs_gprs = 46;
-			num_temp_gprs = 4;
-			num_gs_gprs = 31;
-			num_es_gprs = 31;
-			num_hs_gprs = 23;
-			num_ls_gprs = 23;
-			num_ps_threads = 96;
-			num_vs_threads = 25;
-			num_gs_threads = 25;
-			num_es_threads = 25;
-			num_hs_threads = 25;
-			num_ls_threads = 25;
-			num_ps_stack_entries = 42;
-			num_vs_stack_entries = 42;
-			num_gs_stack_entries = 42;
-			num_es_stack_entries = 42;
-			num_hs_stack_entries = 42;
-			num_ls_stack_entries = 42;
-			break;
-		case CHIP_SUMO2:
-			num_ps_gprs = 93;
-			num_vs_gprs = 46;
-			num_temp_gprs = 4;
-			num_gs_gprs = 31;
-			num_es_gprs = 31;
-			num_hs_gprs = 23;
-			num_ls_gprs = 23;
-			num_ps_threads = 96;
-			num_vs_threads = 25;
-			num_gs_threads = 25;
-			num_es_threads = 25;
-			num_hs_threads = 25;
-			num_ls_threads = 25;
-			num_ps_stack_entries = 85;
-			num_vs_stack_entries = 85;
-			num_gs_stack_entries = 85;
-			num_es_stack_entries = 85;
-			num_hs_stack_entries = 85;
-			num_ls_stack_entries = 85;
-			break;
-		case CHIP_BARTS:
-			num_ps_gprs = 93;
-			num_vs_gprs = 46;
-			num_temp_gprs = 4;
-			num_gs_gprs = 31;
-			num_es_gprs = 31;
-			num_hs_gprs = 23;
-			num_ls_gprs = 23;
-			num_ps_threads = 128;
-			num_vs_threads = 20;
-			num_gs_threads = 20;
-			num_es_threads = 20;
-			num_hs_threads = 20;
-			num_ls_threads = 20;
-			num_ps_stack_entries = 85;
-			num_vs_stack_entries = 85;
-			num_gs_stack_entries = 85;
-			num_es_stack_entries = 85;
-			num_hs_stack_entries = 85;
-			num_ls_stack_entries = 85;
-			break;
-		case CHIP_TURKS:
-			num_ps_gprs = 93;
-			num_vs_gprs = 46;
-			num_temp_gprs = 4;
-			num_gs_gprs = 31;
-			num_es_gprs = 31;
-			num_hs_gprs = 23;
-			num_ls_gprs = 23;
-			num_ps_threads = 128;
-			num_vs_threads = 20;
-			num_gs_threads = 20;
-			num_es_threads = 20;
-			num_hs_threads = 20;
-			num_ls_threads = 20;
-			num_ps_stack_entries = 42;
-			num_vs_stack_entries = 42;
-			num_gs_stack_entries = 42;
-			num_es_stack_entries = 42;
-			num_hs_stack_entries = 42;
-			num_ls_stack_entries = 42;
-			break;
-		case CHIP_CAICOS:
-			num_ps_gprs = 93;
-			num_vs_gprs = 46;
-			num_temp_gprs = 4;
-			num_gs_gprs = 31;
-			num_es_gprs = 31;
-			num_hs_gprs = 23;
-			num_ls_gprs = 23;
-			num_ps_threads = 128;
-			num_vs_threads = 10;
-			num_gs_threads = 10;
-			num_es_threads = 10;
-			num_hs_threads = 10;
-			num_ls_threads = 10;
-			num_ps_stack_entries = 42;
-			num_vs_stack_entries = 42;
-			num_gs_stack_entries = 42;
-			num_es_stack_entries = 42;
-			num_hs_stack_entries = 42;
-			num_ls_stack_entries = 42;
-			break;
-		}
-
-		if ((rdev->family == CHIP_CEDAR) ||
-		    (rdev->family == CHIP_PALM) ||
-		    (rdev->family == CHIP_SUMO) ||
-		    (rdev->family == CHIP_SUMO2) ||
-		    (rdev->family == CHIP_CAICOS))
-			sq_config = 0;
-		else
-			sq_config = VC_ENABLE;
-
-		sq_config |= (EXPORT_SRC_C |
-			      CS_PRIO(0) |
-			      LS_PRIO(0) |
-			      HS_PRIO(0) |
-			      PS_PRIO(0) |
-			      VS_PRIO(1) |
-			      GS_PRIO(2) |
-			      ES_PRIO(3));
-
-		sq_gpr_resource_mgmt_1 = (NUM_PS_GPRS(num_ps_gprs) |
-					  NUM_VS_GPRS(num_vs_gprs) |
-					  NUM_CLAUSE_TEMP_GPRS(num_temp_gprs));
-		sq_gpr_resource_mgmt_2 = (NUM_GS_GPRS(num_gs_gprs) |
-					  NUM_ES_GPRS(num_es_gprs));
-		sq_gpr_resource_mgmt_3 = (NUM_HS_GPRS(num_hs_gprs) |
-					  NUM_LS_GPRS(num_ls_gprs));
-		sq_thread_resource_mgmt = (NUM_PS_THREADS(num_ps_threads) |
-					   NUM_VS_THREADS(num_vs_threads) |
-					   NUM_GS_THREADS(num_gs_threads) |
-					   NUM_ES_THREADS(num_es_threads));
-		sq_thread_resource_mgmt_2 = (NUM_HS_THREADS(num_hs_threads) |
-					     NUM_LS_THREADS(num_ls_threads));
-		sq_stack_resource_mgmt_1 = (NUM_PS_STACK_ENTRIES(num_ps_stack_entries) |
-					    NUM_VS_STACK_ENTRIES(num_vs_stack_entries));
-		sq_stack_resource_mgmt_2 = (NUM_GS_STACK_ENTRIES(num_gs_stack_entries) |
-					    NUM_ES_STACK_ENTRIES(num_es_stack_entries));
-		sq_stack_resource_mgmt_3 = (NUM_HS_STACK_ENTRIES(num_hs_stack_entries) |
-					    NUM_LS_STACK_ENTRIES(num_ls_stack_entries));
-
-		/* disable dyn gprs */
-		radeon_ring_write(ring, PACKET3(PACKET3_SET_CONFIG_REG, 1));
-		radeon_ring_write(ring, (SQ_DYN_GPR_CNTL_PS_FLUSH_REQ - PACKET3_SET_CONFIG_REG_START) >> 2);
-		radeon_ring_write(ring, 0);
-
-		/* setup LDS */
-		radeon_ring_write(ring, PACKET3(PACKET3_SET_CONFIG_REG, 1));
-		radeon_ring_write(ring, (SQ_LDS_RESOURCE_MGMT - PACKET3_SET_CONFIG_REG_START) >> 2);
-		radeon_ring_write(ring, 0x10001000);
-
-		/* SQ config */
-		radeon_ring_write(ring, PACKET3(PACKET3_SET_CONFIG_REG, 11));
-		radeon_ring_write(ring, (SQ_CONFIG - PACKET3_SET_CONFIG_REG_START) >> 2);
-		radeon_ring_write(ring, sq_config);
-		radeon_ring_write(ring, sq_gpr_resource_mgmt_1);
-		radeon_ring_write(ring, sq_gpr_resource_mgmt_2);
-		radeon_ring_write(ring, sq_gpr_resource_mgmt_3);
-		radeon_ring_write(ring, 0);
-		radeon_ring_write(ring, 0);
-		radeon_ring_write(ring, sq_thread_resource_mgmt);
-		radeon_ring_write(ring, sq_thread_resource_mgmt_2);
-		radeon_ring_write(ring, sq_stack_resource_mgmt_1);
-		radeon_ring_write(ring, sq_stack_resource_mgmt_2);
-		radeon_ring_write(ring, sq_stack_resource_mgmt_3);
-	}
-
-	/* CONTEXT_CONTROL */
-	radeon_ring_write(ring, 0xc0012800);
-	radeon_ring_write(ring, 0x80000000);
-	radeon_ring_write(ring, 0x80000000);
-
-	/* SQ_VTX_BASE_VTX_LOC */
-	radeon_ring_write(ring, 0xc0026f00);
-	radeon_ring_write(ring, 0x00000000);
-	radeon_ring_write(ring, 0x00000000);
-	radeon_ring_write(ring, 0x00000000);
-
-	/* SET_SAMPLER */
-	radeon_ring_write(ring, 0xc0036e00);
-	radeon_ring_write(ring, 0x00000000);
-	radeon_ring_write(ring, 0x00000012);
-	radeon_ring_write(ring, 0x00000000);
-	radeon_ring_write(ring, 0x00000000);
-
-	/* set to DX10/11 mode */
-	radeon_ring_write(ring, PACKET3(PACKET3_MODE_CONTROL, 0));
-	radeon_ring_write(ring, 1);
-
-	/* emit an IB pointing at default state */
-	dwords = ALIGN(rdev->r600_blit.state_len, 0x10);
-	gpu_addr = rdev->r600_blit.shader_gpu_addr + rdev->r600_blit.state_offset;
-	radeon_ring_write(ring, PACKET3(PACKET3_INDIRECT_BUFFER, 2));
-	radeon_ring_write(ring, gpu_addr & 0xFFFFFFFC);
-	radeon_ring_write(ring, upper_32_bits(gpu_addr) & 0xFF);
-	radeon_ring_write(ring, dwords);
-
-}
-
-int evergreen_blit_init(struct radeon_device *rdev)
-{
-	u32 obj_size;
-	int i, r, dwords;
-	void *ptr;
-	u32 packet2s[16];
-	int num_packet2s = 0;
-
-	rdev->r600_blit.primitives.set_render_target = set_render_target;
-	rdev->r600_blit.primitives.cp_set_surface_sync = cp_set_surface_sync;
-	rdev->r600_blit.primitives.set_shaders = set_shaders;
-	rdev->r600_blit.primitives.set_vtx_resource = set_vtx_resource;
-	rdev->r600_blit.primitives.set_tex_resource = set_tex_resource;
-	rdev->r600_blit.primitives.set_scissors = set_scissors;
-	rdev->r600_blit.primitives.draw_auto = draw_auto;
-	rdev->r600_blit.primitives.set_default_state = set_default_state;
-
-	rdev->r600_blit.ring_size_common = 8; /* sync semaphore */
-	rdev->r600_blit.ring_size_common += 55; /* shaders + def state */
-	rdev->r600_blit.ring_size_common += 16; /* fence emit for VB IB */
-	rdev->r600_blit.ring_size_common += 5; /* done copy */
-	rdev->r600_blit.ring_size_common += 16; /* fence emit for done copy */
-
-	rdev->r600_blit.ring_size_per_loop = 74;
-	if (rdev->family >= CHIP_CAYMAN)
-		rdev->r600_blit.ring_size_per_loop += 9; /* additional DWs for surface sync */
-
-	rdev->r600_blit.max_dim = 16384;
-
-	rdev->r600_blit.state_offset = 0;
-
-	if (rdev->family < CHIP_CAYMAN)
-		rdev->r600_blit.state_len = evergreen_default_size;
-	else
-		rdev->r600_blit.state_len = cayman_default_size;
-
-	dwords = rdev->r600_blit.state_len;
-	while (dwords & 0xf) {
-		packet2s[num_packet2s++] = cpu_to_le32(PACKET2(0));
-		dwords++;
-	}
-
-	obj_size = dwords * 4;
-	obj_size = ALIGN(obj_size, 256);
-
-	rdev->r600_blit.vs_offset = obj_size;
-	if (rdev->family < CHIP_CAYMAN)
-		obj_size += evergreen_vs_size * 4;
-	else
-		obj_size += cayman_vs_size * 4;
-	obj_size = ALIGN(obj_size, 256);
-
-	rdev->r600_blit.ps_offset = obj_size;
-	if (rdev->family < CHIP_CAYMAN)
-		obj_size += evergreen_ps_size * 4;
-	else
-		obj_size += cayman_ps_size * 4;
-	obj_size = ALIGN(obj_size, 256);
-
-	/* pin copy shader into vram if not already initialized */
-	if (!rdev->r600_blit.shader_obj) {
-		r = radeon_bo_create(rdev, obj_size, PAGE_SIZE, true,
-				     RADEON_GEM_DOMAIN_VRAM,
-				     NULL, &rdev->r600_blit.shader_obj);
-		if (r) {
-			DRM_ERROR("evergreen failed to allocate shader\n");
-			return r;
-		}
-
-		r = radeon_bo_reserve(rdev->r600_blit.shader_obj, false);
-		if (unlikely(r != 0))
-			return r;
-		r = radeon_bo_pin(rdev->r600_blit.shader_obj, RADEON_GEM_DOMAIN_VRAM,
-				  &rdev->r600_blit.shader_gpu_addr);
-		radeon_bo_unreserve(rdev->r600_blit.shader_obj);
-		if (r) {
-			dev_err(rdev->dev, "(%d) pin blit object failed\n", r);
-			return r;
-		}
-	}
-
-	DRM_DEBUG("evergreen blit allocated bo %08x vs %08x ps %08x\n",
-		  obj_size,
-		  rdev->r600_blit.vs_offset, rdev->r600_blit.ps_offset);
-
-	r = radeon_bo_reserve(rdev->r600_blit.shader_obj, false);
-	if (unlikely(r != 0))
-		return r;
-	r = radeon_bo_kmap(rdev->r600_blit.shader_obj, &ptr);
-	if (r) {
-		DRM_ERROR("failed to map blit object %d\n", r);
-		return r;
-	}
-
-	if (rdev->family < CHIP_CAYMAN) {
-		memcpy_toio(ptr + rdev->r600_blit.state_offset,
-			    evergreen_default_state, rdev->r600_blit.state_len * 4);
-
-		if (num_packet2s)
-			memcpy_toio(ptr + rdev->r600_blit.state_offset + (rdev->r600_blit.state_len * 4),
-				    packet2s, num_packet2s * 4);
-		for (i = 0; i < evergreen_vs_size; i++)
-			*(u32 *)((unsigned long)ptr + rdev->r600_blit.vs_offset + i * 4) = cpu_to_le32(evergreen_vs[i]);
-		for (i = 0; i < evergreen_ps_size; i++)
-			*(u32 *)((unsigned long)ptr + rdev->r600_blit.ps_offset + i * 4) = cpu_to_le32(evergreen_ps[i]);
-	} else {
-		memcpy_toio(ptr + rdev->r600_blit.state_offset,
-			    cayman_default_state, rdev->r600_blit.state_len * 4);
-
-		if (num_packet2s)
-			memcpy_toio(ptr + rdev->r600_blit.state_offset + (rdev->r600_blit.state_len * 4),
-				    packet2s, num_packet2s * 4);
-		for (i = 0; i < cayman_vs_size; i++)
-			*(u32 *)((unsigned long)ptr + rdev->r600_blit.vs_offset + i * 4) = cpu_to_le32(cayman_vs[i]);
-		for (i = 0; i < cayman_ps_size; i++)
-			*(u32 *)((unsigned long)ptr + rdev->r600_blit.ps_offset + i * 4) = cpu_to_le32(cayman_ps[i]);
-	}
-	radeon_bo_kunmap(rdev->r600_blit.shader_obj);
-	radeon_bo_unreserve(rdev->r600_blit.shader_obj);
-
-	radeon_ttm_set_active_vram_size(rdev, rdev->mc.real_vram_size);
-	return 0;
-}
diff --git a/drivers/gpu/drm/radeon/evergreen_blit_shaders.c b/drivers/gpu/drm/radeon/evergreen_blit_shaders.c
index f85c0af115b5..d43383470cdf 100644
--- a/drivers/gpu/drm/radeon/evergreen_blit_shaders.c
+++ b/drivers/gpu/drm/radeon/evergreen_blit_shaders.c
@@ -300,58 +300,4 @@ const u32 evergreen_default_state[] =
 	0x00000010, /*  */
 };
 
-const u32 evergreen_vs[] =
-{
-	0x00000004,
-	0x80800400,
-	0x0000a03c,
-	0x95000688,
-	0x00004000,
-	0x15200688,
-	0x00000000,
-	0x00000000,
-	0x3c000000,
-	0x67961001,
-#ifdef __BIG_ENDIAN
-	0x000a0000,
-#else
-	0x00080000,
-#endif
-	0x00000000,
-	0x1c000000,
-	0x67961000,
-#ifdef __BIG_ENDIAN
-	0x00020008,
-#else
-	0x00000008,
-#endif
-	0x00000000,
-};
-
-const u32 evergreen_ps[] =
-{
-	0x00000003,
-	0xa00c0000,
-	0x00000008,
-	0x80400000,
-	0x00000000,
-	0x95200688,
-	0x00380400,
-	0x00146b10,
-	0x00380000,
-	0x20146b10,
-	0x00380400,
-	0x40146b00,
-	0x80380000,
-	0x60146b00,
-	0x00000000,
-	0x00000000,
-	0x00000010,
-	0x000d1000,
-	0xb0800000,
-	0x00000000,
-};
-
-const u32 evergreen_ps_size = ARRAY_SIZE(evergreen_ps);
-const u32 evergreen_vs_size = ARRAY_SIZE(evergreen_vs);
 const u32 evergreen_default_size = ARRAY_SIZE(evergreen_default_state);
diff --git a/drivers/gpu/drm/radeon/evergreen_dma.c b/drivers/gpu/drm/radeon/evergreen_dma.c
new file mode 100644
index 000000000000..6a0656d00ed0
--- /dev/null
+++ b/drivers/gpu/drm/radeon/evergreen_dma.c
@@ -0,0 +1,190 @@
+/*
+ * Copyright 2010 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: Alex Deucher
+ */
+#include <drm/drmP.h>
+#include "radeon.h"
+#include "radeon_asic.h"
+#include "evergreend.h"
+
+u32 evergreen_gpu_check_soft_reset(struct radeon_device *rdev);
+
+/**
+ * evergreen_dma_fence_ring_emit - emit a fence on the DMA ring
+ *
+ * @rdev: radeon_device pointer
+ * @fence: radeon fence object
+ *
+ * Add a DMA fence packet to the ring to write
+ * the fence seq number and DMA trap packet to generate
+ * an interrupt if needed (evergreen-SI).
+ */
+void evergreen_dma_fence_ring_emit(struct radeon_device *rdev,
+				   struct radeon_fence *fence)
+{
+	struct radeon_ring *ring = &rdev->ring[fence->ring];
+	u64 addr = rdev->fence_drv[fence->ring].gpu_addr;
+	/* write the fence */
+	radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_FENCE, 0, 0));
+	radeon_ring_write(ring, addr & 0xfffffffc);
+	radeon_ring_write(ring, (upper_32_bits(addr) & 0xff));
+	radeon_ring_write(ring, fence->seq);
+	/* generate an interrupt */
+	radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_TRAP, 0, 0));
+	/* flush HDP */
+	radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_SRBM_WRITE, 0, 0));
+	radeon_ring_write(ring, (0xf << 16) | (HDP_MEM_COHERENCY_FLUSH_CNTL >> 2));
+	radeon_ring_write(ring, 1);
+}
+
+/**
+ * evergreen_dma_ring_ib_execute - schedule an IB on the DMA engine
+ *
+ * @rdev: radeon_device pointer
+ * @ib: IB object to schedule
+ *
+ * Schedule an IB in the DMA ring (evergreen).
+ */
+void evergreen_dma_ring_ib_execute(struct radeon_device *rdev,
+				   struct radeon_ib *ib)
+{
+	struct radeon_ring *ring = &rdev->ring[ib->ring];
+
+	if (rdev->wb.enabled) {
+		u32 next_rptr = ring->wptr + 4;
+		while ((next_rptr & 7) != 5)
+			next_rptr++;
+		next_rptr += 3;
+		radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_WRITE, 0, 1));
+		radeon_ring_write(ring, ring->next_rptr_gpu_addr & 0xfffffffc);
+		radeon_ring_write(ring, upper_32_bits(ring->next_rptr_gpu_addr) & 0xff);
+		radeon_ring_write(ring, next_rptr);
+	}
+
+	/* The indirect buffer packet must end on an 8 DW boundary in the DMA ring.
+	 * Pad as necessary with NOPs.
+	 */
+	while ((ring->wptr & 7) != 5)
+		radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_NOP, 0, 0));
+	radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_INDIRECT_BUFFER, 0, 0));
+	radeon_ring_write(ring, (ib->gpu_addr & 0xFFFFFFE0));
+	radeon_ring_write(ring, (ib->length_dw << 12) | (upper_32_bits(ib->gpu_addr) & 0xFF));
+
+}
+
+/**
+ * evergreen_copy_dma - copy pages using the DMA engine
+ *
+ * @rdev: radeon_device pointer
+ * @src_offset: src GPU address
+ * @dst_offset: dst GPU address
+ * @num_gpu_pages: number of GPU pages to xfer
+ * @fence: radeon fence object
+ *
+ * Copy GPU paging using the DMA engine (evergreen-cayman).
+ * Used by the radeon ttm implementation to move pages if
+ * registered as the asic copy callback.
+ */
+int evergreen_copy_dma(struct radeon_device *rdev,
+		       uint64_t src_offset, uint64_t dst_offset,
+		       unsigned num_gpu_pages,
+		       struct radeon_fence **fence)
+{
+	struct radeon_semaphore *sem = NULL;
+	int ring_index = rdev->asic->copy.dma_ring_index;
+	struct radeon_ring *ring = &rdev->ring[ring_index];
+	u32 size_in_dw, cur_size_in_dw;
+	int i, num_loops;
+	int r = 0;
+
+	r = radeon_semaphore_create(rdev, &sem);
+	if (r) {
+		DRM_ERROR("radeon: moving bo (%d).\n", r);
+		return r;
+	}
+
+	size_in_dw = (num_gpu_pages << RADEON_GPU_PAGE_SHIFT) / 4;
+	num_loops = DIV_ROUND_UP(size_in_dw, 0xfffff);
+	r = radeon_ring_lock(rdev, ring, num_loops * 5 + 11);
+	if (r) {
+		DRM_ERROR("radeon: moving bo (%d).\n", r);
+		radeon_semaphore_free(rdev, &sem, NULL);
+		return r;
+	}
+
+	if (radeon_fence_need_sync(*fence, ring->idx)) {
+		radeon_semaphore_sync_rings(rdev, sem, (*fence)->ring,
+					    ring->idx);
+		radeon_fence_note_sync(*fence, ring->idx);
+	} else {
+		radeon_semaphore_free(rdev, &sem, NULL);
+	}
+
+	for (i = 0; i < num_loops; i++) {
+		cur_size_in_dw = size_in_dw;
+		if (cur_size_in_dw > 0xFFFFF)
+			cur_size_in_dw = 0xFFFFF;
+		size_in_dw -= cur_size_in_dw;
+		radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_COPY, 0, cur_size_in_dw));
+		radeon_ring_write(ring, dst_offset & 0xfffffffc);
+		radeon_ring_write(ring, src_offset & 0xfffffffc);
+		radeon_ring_write(ring, upper_32_bits(dst_offset) & 0xff);
+		radeon_ring_write(ring, upper_32_bits(src_offset) & 0xff);
+		src_offset += cur_size_in_dw * 4;
+		dst_offset += cur_size_in_dw * 4;
+	}
+
+	r = radeon_fence_emit(rdev, fence, ring->idx);
+	if (r) {
+		radeon_ring_unlock_undo(rdev, ring);
+		return r;
+	}
+
+	radeon_ring_unlock_commit(rdev, ring);
+	radeon_semaphore_free(rdev, &sem, *fence);
+
+	return r;
+}
+
+/**
+ * evergreen_dma_is_lockup - Check if the DMA engine is locked up
+ *
+ * @rdev: radeon_device pointer
+ * @ring: radeon_ring structure holding ring information
+ *
+ * Check if the async DMA engine is locked up.
+ * Returns true if the engine appears to be locked up, false if not.
+ */
+bool evergreen_dma_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
+{
+	u32 reset_mask = evergreen_gpu_check_soft_reset(rdev);
+
+	if (!(reset_mask & RADEON_RESET_DMA)) {
+		radeon_ring_lockup_update(ring);
+		return false;
+	}
+	/* force ring activities */
+	radeon_ring_force_activity(rdev, ring);
+	return radeon_ring_test_lockup(rdev, ring);
+}
+
+
diff --git a/drivers/gpu/drm/radeon/evergreen_hdmi.c b/drivers/gpu/drm/radeon/evergreen_hdmi.c
index b0e280058b9b..f815c20640bd 100644
--- a/drivers/gpu/drm/radeon/evergreen_hdmi.c
+++ b/drivers/gpu/drm/radeon/evergreen_hdmi.c
@@ -32,6 +32,10 @@
 #include "evergreend.h"
 #include "atom.h"
 
+extern void dce6_afmt_write_speaker_allocation(struct drm_encoder *encoder);
+extern void dce6_afmt_write_sad_regs(struct drm_encoder *encoder);
+extern void dce6_afmt_select_pin(struct drm_encoder *encoder);
+
 /*
  * update the N and CTS parameters for a given pixel clock rate
  */
@@ -54,6 +58,45 @@ static void evergreen_hdmi_update_ACR(struct drm_encoder *encoder, uint32_t cloc
 	WREG32(HDMI_ACR_48_1 + offset, acr.n_48khz);
 }
 
+static void dce4_afmt_write_speaker_allocation(struct drm_encoder *encoder)
+{
+	struct radeon_device *rdev = encoder->dev->dev_private;
+	struct drm_connector *connector;
+	struct radeon_connector *radeon_connector = NULL;
+	u32 tmp;
+	u8 *sadb;
+	int sad_count;
+
+	list_for_each_entry(connector, &encoder->dev->mode_config.connector_list, head) {
+		if (connector->encoder == encoder)
+			radeon_connector = to_radeon_connector(connector);
+	}
+
+	if (!radeon_connector) {
+		DRM_ERROR("Couldn't find encoder's connector\n");
+		return;
+	}
+
+	sad_count = drm_edid_to_speaker_allocation(radeon_connector->edid, &sadb);
+	if (sad_count < 0) {
+		DRM_ERROR("Couldn't read Speaker Allocation Data Block: %d\n", sad_count);
+		return;
+	}
+
+	/* program the speaker allocation */
+	tmp = RREG32(AZ_F0_CODEC_PIN0_CONTROL_CHANNEL_SPEAKER);
+	tmp &= ~(DP_CONNECTION | SPEAKER_ALLOCATION_MASK);
+	/* set HDMI mode */
+	tmp |= HDMI_CONNECTION;
+	if (sad_count)
+		tmp |= SPEAKER_ALLOCATION(sadb[0]);
+	else
+		tmp |= SPEAKER_ALLOCATION(5); /* stereo */
+	WREG32(AZ_F0_CODEC_PIN0_CONTROL_CHANNEL_SPEAKER, tmp);
+
+	kfree(sadb);
+}
+
 static void evergreen_hdmi_write_sad_regs(struct drm_encoder *encoder)
 {
 	struct radeon_device *rdev = encoder->dev->dev_private;
@@ -157,22 +200,26 @@ static void evergreen_audio_set_dto(struct drm_encoder *encoder, u32 clock)
 	if (!dig || !dig->afmt)
 		return;
 
-	if (max_ratio >= 8) {
-		dto_phase = 192 * 1000;
-		wallclock_ratio = 3;
-	} else if (max_ratio >= 4) {
-		dto_phase = 96 * 1000;
-		wallclock_ratio = 2;
-	} else if (max_ratio >= 2) {
-		dto_phase = 48 * 1000;
-		wallclock_ratio = 1;
-	} else {
+	if (ASIC_IS_DCE6(rdev)) {
 		dto_phase = 24 * 1000;
-		wallclock_ratio = 0;
+	} else {
+		if (max_ratio >= 8) {
+			dto_phase = 192 * 1000;
+			wallclock_ratio = 3;
+		} else if (max_ratio >= 4) {
+			dto_phase = 96 * 1000;
+			wallclock_ratio = 2;
+		} else if (max_ratio >= 2) {
+			dto_phase = 48 * 1000;
+			wallclock_ratio = 1;
+		} else {
+			dto_phase = 24 * 1000;
+			wallclock_ratio = 0;
+		}
+		dto_cntl = RREG32(DCCG_AUDIO_DTO0_CNTL) & ~DCCG_AUDIO_DTO_WALLCLOCK_RATIO_MASK;
+		dto_cntl |= DCCG_AUDIO_DTO_WALLCLOCK_RATIO(wallclock_ratio);
+		WREG32(DCCG_AUDIO_DTO0_CNTL, dto_cntl);
 	}
-	dto_cntl = RREG32(DCCG_AUDIO_DTO0_CNTL) & ~DCCG_AUDIO_DTO_WALLCLOCK_RATIO_MASK;
-	dto_cntl |= DCCG_AUDIO_DTO_WALLCLOCK_RATIO(wallclock_ratio);
-	WREG32(DCCG_AUDIO_DTO0_CNTL, dto_cntl);
 
 	/* XXX two dtos; generally use dto0 for hdmi */
 	/* Express [24MHz / target pixel clock] as an exact rational
@@ -241,8 +288,7 @@ void evergreen_hdmi_setmode(struct drm_encoder *encoder, struct drm_display_mode
 	/* fglrx clears sth in AFMT_AUDIO_PACKET_CONTROL2 here */
 
 	WREG32(HDMI_ACR_PACKET_CONTROL + offset,
-	       HDMI_ACR_AUTO_SEND | /* allow hw to sent ACR packets when required */
-	       HDMI_ACR_SOURCE); /* select SW CTS value */
+	       HDMI_ACR_AUTO_SEND); /* allow hw to sent ACR packets when required */
 
 	evergreen_hdmi_update_ACR(encoder, mode->clock);
 
@@ -260,13 +306,23 @@ void evergreen_hdmi_setmode(struct drm_encoder *encoder, struct drm_display_mode
 	       AFMT_60958_CS_CHANNEL_NUMBER_6(7) |
 	       AFMT_60958_CS_CHANNEL_NUMBER_7(8));
 
-	/* fglrx sets 0x0001005f | (x & 0x00fc0000) in 0x5f78 here */
+	if (ASIC_IS_DCE6(rdev)) {
+		dce6_afmt_write_speaker_allocation(encoder);
+	} else {
+		dce4_afmt_write_speaker_allocation(encoder);
+	}
 
 	WREG32(AFMT_AUDIO_PACKET_CONTROL2 + offset,
 	       AFMT_AUDIO_CHANNEL_ENABLE(0xff));
 
 	/* fglrx sets 0x40 in 0x5f80 here */
-	evergreen_hdmi_write_sad_regs(encoder);
+
+	if (ASIC_IS_DCE6(rdev)) {
+		dce6_afmt_select_pin(encoder);
+		dce6_afmt_write_sad_regs(encoder);
+	} else {
+		evergreen_hdmi_write_sad_regs(encoder);
+	}
 
 	err = drm_hdmi_avi_infoframe_from_display_mode(&frame, mode);
 	if (err < 0) {
@@ -302,6 +358,8 @@ void evergreen_hdmi_setmode(struct drm_encoder *encoder, struct drm_display_mode
 
 void evergreen_hdmi_enable(struct drm_encoder *encoder, bool enable)
 {
+	struct drm_device *dev = encoder->dev;
+	struct radeon_device *rdev = dev->dev_private;
 	struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
 	struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv;
 
@@ -314,6 +372,15 @@ void evergreen_hdmi_enable(struct drm_encoder *encoder, bool enable)
 	if (!enable && !dig->afmt->enabled)
 		return;
 
+	if (enable) {
+		if (ASIC_IS_DCE6(rdev))
+			dig->afmt->pin = dce6_audio_get_pin(rdev);
+		else
+			dig->afmt->pin = r600_audio_get_pin(rdev);
+	} else {
+		dig->afmt->pin = NULL;
+	}
+
 	dig->afmt->enabled = enable;
 
 	DRM_DEBUG("%sabling HDMI interface @ 0x%04X for encoder 0x%x\n",
diff --git a/drivers/gpu/drm/radeon/evergreend.h b/drivers/gpu/drm/radeon/evergreend.h
index 0d582ac1dc31..4f6d2962767d 100644
--- a/drivers/gpu/drm/radeon/evergreend.h
+++ b/drivers/gpu/drm/radeon/evergreend.h
@@ -714,6 +714,13 @@
 #define AFMT_GENERIC0_7                      0x7138
 
 /* DCE4/5 ELD audio interface */
+#define AZ_F0_CODEC_PIN0_CONTROL_CHANNEL_SPEAKER          0x5f78
+#define		SPEAKER_ALLOCATION(x)			(((x) & 0x7f) << 0)
+#define		SPEAKER_ALLOCATION_MASK			(0x7f << 0)
+#define		SPEAKER_ALLOCATION_SHIFT		0
+#define		HDMI_CONNECTION				(1 << 16)
+#define		DP_CONNECTION				(1 << 17)
+
 #define AZ_F0_CODEC_PIN0_CONTROL_AUDIO_DESCRIPTOR0        0x5f84 /* LPCM */
 #define AZ_F0_CODEC_PIN0_CONTROL_AUDIO_DESCRIPTOR1        0x5f88 /* AC3 */
 #define AZ_F0_CODEC_PIN0_CONTROL_AUDIO_DESCRIPTOR2        0x5f8c /* MPEG1 */
@@ -1153,6 +1160,10 @@
 #       define LATENCY_LOW_WATERMARK(x)                   ((x) << 0)
 #       define LATENCY_HIGH_WATERMARK(x)                  ((x) << 16)
 
+#define	PIPE0_DMIF_BUFFER_CONTROL			  0x0ca0
+#       define DMIF_BUFFERS_ALLOCATED(x)                  ((x) << 0)
+#       define DMIF_BUFFERS_ALLOCATED_COMPLETED           (1 << 4)
+
 #define IH_RB_CNTL                                        0x3e00
 #       define IH_RB_ENABLE                               (1 << 0)
 #       define IH_IB_SIZE(x)                              ((x) << 1) /* log2 */
@@ -1490,7 +1501,7 @@
  * 6. COMMAND [29:22] | BYTE_COUNT [20:0]
  */
 #              define PACKET3_CP_DMA_DST_SEL(x)    ((x) << 20)
-                /* 0 - SRC_ADDR
+                /* 0 - DST_ADDR
 		 * 1 - GDS
 		 */
 #              define PACKET3_CP_DMA_ENGINE(x)     ((x) << 27)
@@ -1505,7 +1516,7 @@
 #              define PACKET3_CP_DMA_CP_SYNC       (1 << 31)
 /* COMMAND */
 #              define PACKET3_CP_DMA_DIS_WC        (1 << 21)
-#              define PACKET3_CP_DMA_CMD_SRC_SWAP(x) ((x) << 23)
+#              define PACKET3_CP_DMA_CMD_SRC_SWAP(x) ((x) << 22)
                 /* 0 - none
 		 * 1 - 8 in 16
 		 * 2 - 8 in 32
diff --git a/drivers/gpu/drm/radeon/kv_dpm.c b/drivers/gpu/drm/radeon/kv_dpm.c
new file mode 100644
index 000000000000..71399065db04
--- /dev/null
+++ b/drivers/gpu/drm/radeon/kv_dpm.c
@@ -0,0 +1,2739 @@
+/*
+ * Copyright 2013 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+
+#include "drmP.h"
+#include "radeon.h"
+#include "cikd.h"
+#include "r600_dpm.h"
+#include "kv_dpm.h"
+#include "radeon_asic.h"
+#include <linux/seq_file.h>
+
+#define KV_MAX_DEEPSLEEP_DIVIDER_ID     5
+#define KV_MINIMUM_ENGINE_CLOCK         800
+#define SMC_RAM_END                     0x40000
+
+static void kv_init_graphics_levels(struct radeon_device *rdev);
+static int kv_calculate_ds_divider(struct radeon_device *rdev);
+static int kv_calculate_nbps_level_settings(struct radeon_device *rdev);
+static int kv_calculate_dpm_settings(struct radeon_device *rdev);
+static void kv_enable_new_levels(struct radeon_device *rdev);
+static void kv_program_nbps_index_settings(struct radeon_device *rdev,
+					   struct radeon_ps *new_rps);
+static int kv_set_enabled_level(struct radeon_device *rdev, u32 level);
+static int kv_set_enabled_levels(struct radeon_device *rdev);
+static int kv_force_dpm_highest(struct radeon_device *rdev);
+static int kv_force_dpm_lowest(struct radeon_device *rdev);
+static void kv_apply_state_adjust_rules(struct radeon_device *rdev,
+					struct radeon_ps *new_rps,
+					struct radeon_ps *old_rps);
+static int kv_set_thermal_temperature_range(struct radeon_device *rdev,
+					    int min_temp, int max_temp);
+static int kv_init_fps_limits(struct radeon_device *rdev);
+
+void kv_dpm_powergate_uvd(struct radeon_device *rdev, bool gate);
+static void kv_dpm_powergate_vce(struct radeon_device *rdev, bool gate);
+static void kv_dpm_powergate_samu(struct radeon_device *rdev, bool gate);
+static void kv_dpm_powergate_acp(struct radeon_device *rdev, bool gate);
+
+extern void cik_enter_rlc_safe_mode(struct radeon_device *rdev);
+extern void cik_exit_rlc_safe_mode(struct radeon_device *rdev);
+extern void cik_update_cg(struct radeon_device *rdev,
+			  u32 block, bool enable);
+
+static const struct kv_lcac_config_values sx_local_cac_cfg_kv[] =
+{
+	{  0,       4,        1    },
+	{  1,       4,        1    },
+	{  2,       5,        1    },
+	{  3,       4,        2    },
+	{  4,       1,        1    },
+	{  5,       5,        2    },
+	{  6,       6,        1    },
+	{  7,       9,        2    },
+	{ 0xffffffff }
+};
+
+static const struct kv_lcac_config_values mc0_local_cac_cfg_kv[] =
+{
+	{  0,       4,        1    },
+	{ 0xffffffff }
+};
+
+static const struct kv_lcac_config_values mc1_local_cac_cfg_kv[] =
+{
+	{  0,       4,        1    },
+	{ 0xffffffff }
+};
+
+static const struct kv_lcac_config_values mc2_local_cac_cfg_kv[] =
+{
+	{  0,       4,        1    },
+	{ 0xffffffff }
+};
+
+static const struct kv_lcac_config_values mc3_local_cac_cfg_kv[] =
+{
+	{  0,       4,        1    },
+	{ 0xffffffff }
+};
+
+static const struct kv_lcac_config_values cpl_local_cac_cfg_kv[] =
+{
+	{  0,       4,        1    },
+	{  1,       4,        1    },
+	{  2,       5,        1    },
+	{  3,       4,        1    },
+	{  4,       1,        1    },
+	{  5,       5,        1    },
+	{  6,       6,        1    },
+	{  7,       9,        1    },
+	{  8,       4,        1    },
+	{  9,       2,        1    },
+	{  10,      3,        1    },
+	{  11,      6,        1    },
+	{  12,      8,        2    },
+	{  13,      1,        1    },
+	{  14,      2,        1    },
+	{  15,      3,        1    },
+	{  16,      1,        1    },
+	{  17,      4,        1    },
+	{  18,      3,        1    },
+	{  19,      1,        1    },
+	{  20,      8,        1    },
+	{  21,      5,        1    },
+	{  22,      1,        1    },
+	{  23,      1,        1    },
+	{  24,      4,        1    },
+	{  27,      6,        1    },
+	{  28,      1,        1    },
+	{ 0xffffffff }
+};
+
+static const struct kv_lcac_config_reg sx0_cac_config_reg[] =
+{
+	{ 0xc0400d00, 0x003e0000, 17, 0x3fc00000, 22, 0x0001fffe, 1, 0x00000001, 0 }
+};
+
+static const struct kv_lcac_config_reg mc0_cac_config_reg[] =
+{
+	{ 0xc0400d30, 0x003e0000, 17, 0x3fc00000, 22, 0x0001fffe, 1, 0x00000001, 0 }
+};
+
+static const struct kv_lcac_config_reg mc1_cac_config_reg[] =
+{
+	{ 0xc0400d3c, 0x003e0000, 17, 0x3fc00000, 22, 0x0001fffe, 1, 0x00000001, 0 }
+};
+
+static const struct kv_lcac_config_reg mc2_cac_config_reg[] =
+{
+	{ 0xc0400d48, 0x003e0000, 17, 0x3fc00000, 22, 0x0001fffe, 1, 0x00000001, 0 }
+};
+
+static const struct kv_lcac_config_reg mc3_cac_config_reg[] =
+{
+	{ 0xc0400d54, 0x003e0000, 17, 0x3fc00000, 22, 0x0001fffe, 1, 0x00000001, 0 }
+};
+
+static const struct kv_lcac_config_reg cpl_cac_config_reg[] =
+{
+	{ 0xc0400d80, 0x003e0000, 17, 0x3fc00000, 22, 0x0001fffe, 1, 0x00000001, 0 }
+};
+
+static const struct kv_pt_config_reg didt_config_kv[] =
+{
+	{ 0x10, 0x000000ff, 0, 0x0, KV_CONFIGREG_DIDT_IND },
+	{ 0x10, 0x0000ff00, 8, 0x0, KV_CONFIGREG_DIDT_IND },
+	{ 0x10, 0x00ff0000, 16, 0x0, KV_CONFIGREG_DIDT_IND },
+	{ 0x10, 0xff000000, 24, 0x0, KV_CONFIGREG_DIDT_IND },
+	{ 0x11, 0x000000ff, 0, 0x0, KV_CONFIGREG_DIDT_IND },
+	{ 0x11, 0x0000ff00, 8, 0x0, KV_CONFIGREG_DIDT_IND },
+	{ 0x11, 0x00ff0000, 16, 0x0, KV_CONFIGREG_DIDT_IND },
+	{ 0x11, 0xff000000, 24, 0x0, KV_CONFIGREG_DIDT_IND },
+	{ 0x12, 0x000000ff, 0, 0x0, KV_CONFIGREG_DIDT_IND },
+	{ 0x12, 0x0000ff00, 8, 0x0, KV_CONFIGREG_DIDT_IND },
+	{ 0x12, 0x00ff0000, 16, 0x0, KV_CONFIGREG_DIDT_IND },
+	{ 0x12, 0xff000000, 24, 0x0, KV_CONFIGREG_DIDT_IND },
+	{ 0x2, 0x00003fff, 0, 0x4, KV_CONFIGREG_DIDT_IND },
+	{ 0x2, 0x03ff0000, 16, 0x80, KV_CONFIGREG_DIDT_IND },
+	{ 0x2, 0x78000000, 27, 0x3, KV_CONFIGREG_DIDT_IND },
+	{ 0x1, 0x0000ffff, 0, 0x3FFF, KV_CONFIGREG_DIDT_IND },
+	{ 0x1, 0xffff0000, 16, 0x3FFF, KV_CONFIGREG_DIDT_IND },
+	{ 0x0, 0x00000001, 0, 0x0, KV_CONFIGREG_DIDT_IND },
+	{ 0x30, 0x000000ff, 0, 0x0, KV_CONFIGREG_DIDT_IND },
+	{ 0x30, 0x0000ff00, 8, 0x0, KV_CONFIGREG_DIDT_IND },
+	{ 0x30, 0x00ff0000, 16, 0x0, KV_CONFIGREG_DIDT_IND },
+	{ 0x30, 0xff000000, 24, 0x0, KV_CONFIGREG_DIDT_IND },
+	{ 0x31, 0x000000ff, 0, 0x0, KV_CONFIGREG_DIDT_IND },
+	{ 0x31, 0x0000ff00, 8, 0x0, KV_CONFIGREG_DIDT_IND },
+	{ 0x31, 0x00ff0000, 16, 0x0, KV_CONFIGREG_DIDT_IND },
+	{ 0x31, 0xff000000, 24, 0x0, KV_CONFIGREG_DIDT_IND },
+	{ 0x32, 0x000000ff, 0, 0x0, KV_CONFIGREG_DIDT_IND },
+	{ 0x32, 0x0000ff00, 8, 0x0, KV_CONFIGREG_DIDT_IND },
+	{ 0x32, 0x00ff0000, 16, 0x0, KV_CONFIGREG_DIDT_IND },
+	{ 0x32, 0xff000000, 24, 0x0, KV_CONFIGREG_DIDT_IND },
+	{ 0x22, 0x00003fff, 0, 0x4, KV_CONFIGREG_DIDT_IND },
+	{ 0x22, 0x03ff0000, 16, 0x80, KV_CONFIGREG_DIDT_IND },
+	{ 0x22, 0x78000000, 27, 0x3, KV_CONFIGREG_DIDT_IND },
+	{ 0x21, 0x0000ffff, 0, 0x3FFF, KV_CONFIGREG_DIDT_IND },
+	{ 0x21, 0xffff0000, 16, 0x3FFF, KV_CONFIGREG_DIDT_IND },
+	{ 0x20, 0x00000001, 0, 0x0, KV_CONFIGREG_DIDT_IND },
+	{ 0x50, 0x000000ff, 0, 0x0, KV_CONFIGREG_DIDT_IND },
+	{ 0x50, 0x0000ff00, 8, 0x0, KV_CONFIGREG_DIDT_IND },
+	{ 0x50, 0x00ff0000, 16, 0x0, KV_CONFIGREG_DIDT_IND },
+	{ 0x50, 0xff000000, 24, 0x0, KV_CONFIGREG_DIDT_IND },
+	{ 0x51, 0x000000ff, 0, 0x0, KV_CONFIGREG_DIDT_IND },
+	{ 0x51, 0x0000ff00, 8, 0x0, KV_CONFIGREG_DIDT_IND },
+	{ 0x51, 0x00ff0000, 16, 0x0, KV_CONFIGREG_DIDT_IND },
+	{ 0x51, 0xff000000, 24, 0x0, KV_CONFIGREG_DIDT_IND },
+	{ 0x52, 0x000000ff, 0, 0x0, KV_CONFIGREG_DIDT_IND },
+	{ 0x52, 0x0000ff00, 8, 0x0, KV_CONFIGREG_DIDT_IND },
+	{ 0x52, 0x00ff0000, 16, 0x0, KV_CONFIGREG_DIDT_IND },
+	{ 0x52, 0xff000000, 24, 0x0, KV_CONFIGREG_DIDT_IND },
+	{ 0x42, 0x00003fff, 0, 0x4, KV_CONFIGREG_DIDT_IND },
+	{ 0x42, 0x03ff0000, 16, 0x80, KV_CONFIGREG_DIDT_IND },
+	{ 0x42, 0x78000000, 27, 0x3, KV_CONFIGREG_DIDT_IND },
+	{ 0x41, 0x0000ffff, 0, 0x3FFF, KV_CONFIGREG_DIDT_IND },
+	{ 0x41, 0xffff0000, 16, 0x3FFF, KV_CONFIGREG_DIDT_IND },
+	{ 0x40, 0x00000001, 0, 0x0, KV_CONFIGREG_DIDT_IND },
+	{ 0x70, 0x000000ff, 0, 0x0, KV_CONFIGREG_DIDT_IND },
+	{ 0x70, 0x0000ff00, 8, 0x0, KV_CONFIGREG_DIDT_IND },
+	{ 0x70, 0x00ff0000, 16, 0x0, KV_CONFIGREG_DIDT_IND },
+	{ 0x70, 0xff000000, 24, 0x0, KV_CONFIGREG_DIDT_IND },
+	{ 0x71, 0x000000ff, 0, 0x0, KV_CONFIGREG_DIDT_IND },
+	{ 0x71, 0x0000ff00, 8, 0x0, KV_CONFIGREG_DIDT_IND },
+	{ 0x71, 0x00ff0000, 16, 0x0, KV_CONFIGREG_DIDT_IND },
+	{ 0x71, 0xff000000, 24, 0x0, KV_CONFIGREG_DIDT_IND },
+	{ 0x72, 0x000000ff, 0, 0x0, KV_CONFIGREG_DIDT_IND },
+	{ 0x72, 0x0000ff00, 8, 0x0, KV_CONFIGREG_DIDT_IND },
+	{ 0x72, 0x00ff0000, 16, 0x0, KV_CONFIGREG_DIDT_IND },
+	{ 0x72, 0xff000000, 24, 0x0, KV_CONFIGREG_DIDT_IND },
+	{ 0x62, 0x00003fff, 0, 0x4, KV_CONFIGREG_DIDT_IND },
+	{ 0x62, 0x03ff0000, 16, 0x80, KV_CONFIGREG_DIDT_IND },
+	{ 0x62, 0x78000000, 27, 0x3, KV_CONFIGREG_DIDT_IND },
+	{ 0x61, 0x0000ffff, 0, 0x3FFF, KV_CONFIGREG_DIDT_IND },
+	{ 0x61, 0xffff0000, 16, 0x3FFF, KV_CONFIGREG_DIDT_IND },
+	{ 0x60, 0x00000001, 0, 0x0, KV_CONFIGREG_DIDT_IND },
+	{ 0xFFFFFFFF }
+};
+
+static struct kv_ps *kv_get_ps(struct radeon_ps *rps)
+{
+	struct kv_ps *ps = rps->ps_priv;
+
+	return ps;
+}
+
+static struct kv_power_info *kv_get_pi(struct radeon_device *rdev)
+{
+	struct kv_power_info *pi = rdev->pm.dpm.priv;
+
+	return pi;
+}
+
+#if 0
+static void kv_program_local_cac_table(struct radeon_device *rdev,
+				       const struct kv_lcac_config_values *local_cac_table,
+				       const struct kv_lcac_config_reg *local_cac_reg)
+{
+	u32 i, count, data;
+	const struct kv_lcac_config_values *values = local_cac_table;
+
+	while (values->block_id != 0xffffffff) {
+		count = values->signal_id;
+		for (i = 0; i < count; i++) {
+			data = ((values->block_id << local_cac_reg->block_shift) &
+				local_cac_reg->block_mask);
+			data |= ((i << local_cac_reg->signal_shift) &
+				 local_cac_reg->signal_mask);
+			data |= ((values->t << local_cac_reg->t_shift) &
+				 local_cac_reg->t_mask);
+			data |= ((1 << local_cac_reg->enable_shift) &
+				 local_cac_reg->enable_mask);
+			WREG32_SMC(local_cac_reg->cntl, data);
+		}
+		values++;
+	}
+}
+#endif
+
+static int kv_program_pt_config_registers(struct radeon_device *rdev,
+					  const struct kv_pt_config_reg *cac_config_regs)
+{
+	const struct kv_pt_config_reg *config_regs = cac_config_regs;
+	u32 data;
+	u32 cache = 0;
+
+	if (config_regs == NULL)
+		return -EINVAL;
+
+	while (config_regs->offset != 0xFFFFFFFF) {
+		if (config_regs->type == KV_CONFIGREG_CACHE) {
+			cache |= ((config_regs->value << config_regs->shift) & config_regs->mask);
+		} else {
+			switch (config_regs->type) {
+			case KV_CONFIGREG_SMC_IND:
+				data = RREG32_SMC(config_regs->offset);
+				break;
+			case KV_CONFIGREG_DIDT_IND:
+				data = RREG32_DIDT(config_regs->offset);
+				break;
+			default:
+				data = RREG32(config_regs->offset << 2);
+				break;
+			}
+
+			data &= ~config_regs->mask;
+			data |= ((config_regs->value << config_regs->shift) & config_regs->mask);
+			data |= cache;
+			cache = 0;
+
+			switch (config_regs->type) {
+			case KV_CONFIGREG_SMC_IND:
+				WREG32_SMC(config_regs->offset, data);
+				break;
+			case KV_CONFIGREG_DIDT_IND:
+				WREG32_DIDT(config_regs->offset, data);
+				break;
+			default:
+				WREG32(config_regs->offset << 2, data);
+				break;
+			}
+		}
+		config_regs++;
+	}
+
+	return 0;
+}
+
+static void kv_do_enable_didt(struct radeon_device *rdev, bool enable)
+{
+	struct kv_power_info *pi = kv_get_pi(rdev);
+	u32 data;
+
+	if (pi->caps_sq_ramping) {
+		data = RREG32_DIDT(DIDT_SQ_CTRL0);
+		if (enable)
+			data |= DIDT_CTRL_EN;
+		else
+			data &= ~DIDT_CTRL_EN;
+		WREG32_DIDT(DIDT_SQ_CTRL0, data);
+	}
+
+	if (pi->caps_db_ramping) {
+		data = RREG32_DIDT(DIDT_DB_CTRL0);
+		if (enable)
+			data |= DIDT_CTRL_EN;
+		else
+			data &= ~DIDT_CTRL_EN;
+		WREG32_DIDT(DIDT_DB_CTRL0, data);
+	}
+
+	if (pi->caps_td_ramping) {
+		data = RREG32_DIDT(DIDT_TD_CTRL0);
+		if (enable)
+			data |= DIDT_CTRL_EN;
+		else
+			data &= ~DIDT_CTRL_EN;
+		WREG32_DIDT(DIDT_TD_CTRL0, data);
+	}
+
+	if (pi->caps_tcp_ramping) {
+		data = RREG32_DIDT(DIDT_TCP_CTRL0);
+		if (enable)
+			data |= DIDT_CTRL_EN;
+		else
+			data &= ~DIDT_CTRL_EN;
+		WREG32_DIDT(DIDT_TCP_CTRL0, data);
+	}
+}
+
+static int kv_enable_didt(struct radeon_device *rdev, bool enable)
+{
+	struct kv_power_info *pi = kv_get_pi(rdev);
+	int ret;
+
+	if (pi->caps_sq_ramping ||
+	    pi->caps_db_ramping ||
+	    pi->caps_td_ramping ||
+	    pi->caps_tcp_ramping) {
+		cik_enter_rlc_safe_mode(rdev);
+
+		if (enable) {
+			ret = kv_program_pt_config_registers(rdev, didt_config_kv);
+			if (ret) {
+				cik_exit_rlc_safe_mode(rdev);
+				return ret;
+			}
+		}
+
+		kv_do_enable_didt(rdev, enable);
+
+		cik_exit_rlc_safe_mode(rdev);
+	}
+
+	return 0;
+}
+
+#if 0
+static void kv_initialize_hardware_cac_manager(struct radeon_device *rdev)
+{
+	struct kv_power_info *pi = kv_get_pi(rdev);
+
+	if (pi->caps_cac) {
+		WREG32_SMC(LCAC_SX0_OVR_SEL, 0);
+		WREG32_SMC(LCAC_SX0_OVR_VAL, 0);
+		kv_program_local_cac_table(rdev, sx_local_cac_cfg_kv, sx0_cac_config_reg);
+
+		WREG32_SMC(LCAC_MC0_OVR_SEL, 0);
+		WREG32_SMC(LCAC_MC0_OVR_VAL, 0);
+		kv_program_local_cac_table(rdev, mc0_local_cac_cfg_kv, mc0_cac_config_reg);
+
+		WREG32_SMC(LCAC_MC1_OVR_SEL, 0);
+		WREG32_SMC(LCAC_MC1_OVR_VAL, 0);
+		kv_program_local_cac_table(rdev, mc1_local_cac_cfg_kv, mc1_cac_config_reg);
+
+		WREG32_SMC(LCAC_MC2_OVR_SEL, 0);
+		WREG32_SMC(LCAC_MC2_OVR_VAL, 0);
+		kv_program_local_cac_table(rdev, mc2_local_cac_cfg_kv, mc2_cac_config_reg);
+
+		WREG32_SMC(LCAC_MC3_OVR_SEL, 0);
+		WREG32_SMC(LCAC_MC3_OVR_VAL, 0);
+		kv_program_local_cac_table(rdev, mc3_local_cac_cfg_kv, mc3_cac_config_reg);
+
+		WREG32_SMC(LCAC_CPL_OVR_SEL, 0);
+		WREG32_SMC(LCAC_CPL_OVR_VAL, 0);
+		kv_program_local_cac_table(rdev, cpl_local_cac_cfg_kv, cpl_cac_config_reg);
+	}
+}
+#endif
+
+static int kv_enable_smc_cac(struct radeon_device *rdev, bool enable)
+{
+	struct kv_power_info *pi = kv_get_pi(rdev);
+	int ret = 0;
+
+	if (pi->caps_cac) {
+		if (enable) {
+			ret = kv_notify_message_to_smu(rdev, PPSMC_MSG_EnableCac);
+			if (ret)
+				pi->cac_enabled = false;
+			else
+				pi->cac_enabled = true;
+		} else if (pi->cac_enabled) {
+			kv_notify_message_to_smu(rdev, PPSMC_MSG_DisableCac);
+			pi->cac_enabled = false;
+		}
+	}
+
+	return ret;
+}
+
+static int kv_process_firmware_header(struct radeon_device *rdev)
+{
+	struct kv_power_info *pi = kv_get_pi(rdev);
+	u32 tmp;
+	int ret;
+
+	ret = kv_read_smc_sram_dword(rdev, SMU7_FIRMWARE_HEADER_LOCATION +
+				     offsetof(SMU7_Firmware_Header, DpmTable),
+				     &tmp, pi->sram_end);
+
+	if (ret == 0)
+		pi->dpm_table_start = tmp;
+
+	ret = kv_read_smc_sram_dword(rdev, SMU7_FIRMWARE_HEADER_LOCATION +
+				     offsetof(SMU7_Firmware_Header, SoftRegisters),
+				     &tmp, pi->sram_end);
+
+	if (ret == 0)
+		pi->soft_regs_start = tmp;
+
+	return ret;
+}
+
+static int kv_enable_dpm_voltage_scaling(struct radeon_device *rdev)
+{
+	struct kv_power_info *pi = kv_get_pi(rdev);
+	int ret;
+
+	pi->graphics_voltage_change_enable = 1;
+
+	ret = kv_copy_bytes_to_smc(rdev,
+				   pi->dpm_table_start +
+				   offsetof(SMU7_Fusion_DpmTable, GraphicsVoltageChangeEnable),
+				   &pi->graphics_voltage_change_enable,
+				   sizeof(u8), pi->sram_end);
+
+	return ret;
+}
+
+static int kv_set_dpm_interval(struct radeon_device *rdev)
+{
+	struct kv_power_info *pi = kv_get_pi(rdev);
+	int ret;
+
+	pi->graphics_interval = 1;
+
+	ret = kv_copy_bytes_to_smc(rdev,
+				   pi->dpm_table_start +
+				   offsetof(SMU7_Fusion_DpmTable, GraphicsInterval),
+				   &pi->graphics_interval,
+				   sizeof(u8), pi->sram_end);
+
+	return ret;
+}
+
+static int kv_set_dpm_boot_state(struct radeon_device *rdev)
+{
+	struct kv_power_info *pi = kv_get_pi(rdev);
+	int ret;
+
+	ret = kv_copy_bytes_to_smc(rdev,
+				   pi->dpm_table_start +
+				   offsetof(SMU7_Fusion_DpmTable, GraphicsBootLevel),
+				   &pi->graphics_boot_level,
+				   sizeof(u8), pi->sram_end);
+
+	return ret;
+}
+
+static void kv_program_vc(struct radeon_device *rdev)
+{
+	WREG32_SMC(CG_FTV_0, 0x3FFFC100);
+}
+
+static void kv_clear_vc(struct radeon_device *rdev)
+{
+	WREG32_SMC(CG_FTV_0, 0);
+}
+
+static int kv_set_divider_value(struct radeon_device *rdev,
+				u32 index, u32 sclk)
+{
+	struct kv_power_info *pi = kv_get_pi(rdev);
+	struct atom_clock_dividers dividers;
+	int ret;
+
+	ret = radeon_atom_get_clock_dividers(rdev, COMPUTE_ENGINE_PLL_PARAM,
+					     sclk, false, &dividers);
+	if (ret)
+		return ret;
+
+	pi->graphics_level[index].SclkDid = (u8)dividers.post_div;
+	pi->graphics_level[index].SclkFrequency = cpu_to_be32(sclk);
+
+	return 0;
+}
+
+static u16 kv_convert_8bit_index_to_voltage(struct radeon_device *rdev,
+					    u16 voltage)
+{
+	return 6200 - (voltage * 25);
+}
+
+static u16 kv_convert_2bit_index_to_voltage(struct radeon_device *rdev,
+					    u32 vid_2bit)
+{
+	struct kv_power_info *pi = kv_get_pi(rdev);
+	u32 vid_8bit = sumo_convert_vid2_to_vid7(rdev,
+						 &pi->sys_info.vid_mapping_table,
+						 vid_2bit);
+
+	return kv_convert_8bit_index_to_voltage(rdev, (u16)vid_8bit);
+}
+
+
+static int kv_set_vid(struct radeon_device *rdev, u32 index, u32 vid)
+{
+	struct kv_power_info *pi = kv_get_pi(rdev);
+
+	pi->graphics_level[index].VoltageDownH = (u8)pi->voltage_drop_t;
+	pi->graphics_level[index].MinVddNb =
+		cpu_to_be32(kv_convert_2bit_index_to_voltage(rdev, vid));
+
+	return 0;
+}
+
+static int kv_set_at(struct radeon_device *rdev, u32 index, u32 at)
+{
+	struct kv_power_info *pi = kv_get_pi(rdev);
+
+	pi->graphics_level[index].AT = cpu_to_be16((u16)at);
+
+	return 0;
+}
+
+static void kv_dpm_power_level_enable(struct radeon_device *rdev,
+				      u32 index, bool enable)
+{
+	struct kv_power_info *pi = kv_get_pi(rdev);
+
+	pi->graphics_level[index].EnabledForActivity = enable ? 1 : 0;
+}
+
+static void kv_start_dpm(struct radeon_device *rdev)
+{
+	u32 tmp = RREG32_SMC(GENERAL_PWRMGT);
+
+	tmp |= GLOBAL_PWRMGT_EN;
+	WREG32_SMC(GENERAL_PWRMGT, tmp);
+
+	kv_smc_dpm_enable(rdev, true);
+}
+
+static void kv_stop_dpm(struct radeon_device *rdev)
+{
+	kv_smc_dpm_enable(rdev, false);
+}
+
+static void kv_start_am(struct radeon_device *rdev)
+{
+	u32 sclk_pwrmgt_cntl = RREG32_SMC(SCLK_PWRMGT_CNTL);
+
+	sclk_pwrmgt_cntl &= ~(RESET_SCLK_CNT | RESET_BUSY_CNT);
+	sclk_pwrmgt_cntl |= DYNAMIC_PM_EN;
+
+	WREG32_SMC(SCLK_PWRMGT_CNTL, sclk_pwrmgt_cntl);
+}
+
+static void kv_reset_am(struct radeon_device *rdev)
+{
+	u32 sclk_pwrmgt_cntl = RREG32_SMC(SCLK_PWRMGT_CNTL);
+
+	sclk_pwrmgt_cntl |= (RESET_SCLK_CNT | RESET_BUSY_CNT);
+
+	WREG32_SMC(SCLK_PWRMGT_CNTL, sclk_pwrmgt_cntl);
+}
+
+static int kv_freeze_sclk_dpm(struct radeon_device *rdev, bool freeze)
+{
+	return kv_notify_message_to_smu(rdev, freeze ?
+					PPSMC_MSG_SCLKDPM_FreezeLevel : PPSMC_MSG_SCLKDPM_UnfreezeLevel);
+}
+
+static int kv_force_lowest_valid(struct radeon_device *rdev)
+{
+	return kv_force_dpm_lowest(rdev);
+}
+
+static int kv_unforce_levels(struct radeon_device *rdev)
+{
+	if (rdev->family == CHIP_KABINI)
+		return kv_notify_message_to_smu(rdev, PPSMC_MSG_NoForcedLevel);
+	else
+		return kv_set_enabled_levels(rdev);
+}
+
+static int kv_update_sclk_t(struct radeon_device *rdev)
+{
+	struct kv_power_info *pi = kv_get_pi(rdev);
+	u32 low_sclk_interrupt_t = 0;
+	int ret = 0;
+
+	if (pi->caps_sclk_throttle_low_notification) {
+		low_sclk_interrupt_t = cpu_to_be32(pi->low_sclk_interrupt_t);
+
+		ret = kv_copy_bytes_to_smc(rdev,
+					   pi->dpm_table_start +
+					   offsetof(SMU7_Fusion_DpmTable, LowSclkInterruptT),
+					   (u8 *)&low_sclk_interrupt_t,
+					   sizeof(u32), pi->sram_end);
+	}
+	return ret;
+}
+
+static int kv_program_bootup_state(struct radeon_device *rdev)
+{
+	struct kv_power_info *pi = kv_get_pi(rdev);
+	u32 i;
+	struct radeon_clock_voltage_dependency_table *table =
+		&rdev->pm.dpm.dyn_state.vddc_dependency_on_sclk;
+
+	if (table && table->count) {
+		for (i = pi->graphics_dpm_level_count - 1; i > 0; i--) {
+			if (table->entries[i].clk == pi->boot_pl.sclk)
+				break;
+		}
+
+		pi->graphics_boot_level = (u8)i;
+		kv_dpm_power_level_enable(rdev, i, true);
+	} else {
+		struct sumo_sclk_voltage_mapping_table *table =
+			&pi->sys_info.sclk_voltage_mapping_table;
+
+		if (table->num_max_dpm_entries == 0)
+			return -EINVAL;
+
+		for (i = pi->graphics_dpm_level_count - 1; i > 0; i--) {
+			if (table->entries[i].sclk_frequency == pi->boot_pl.sclk)
+				break;
+		}
+
+		pi->graphics_boot_level = (u8)i;
+		kv_dpm_power_level_enable(rdev, i, true);
+	}
+	return 0;
+}
+
+static int kv_enable_auto_thermal_throttling(struct radeon_device *rdev)
+{
+	struct kv_power_info *pi = kv_get_pi(rdev);
+	int ret;
+
+	pi->graphics_therm_throttle_enable = 1;
+
+	ret = kv_copy_bytes_to_smc(rdev,
+				   pi->dpm_table_start +
+				   offsetof(SMU7_Fusion_DpmTable, GraphicsThermThrottleEnable),
+				   &pi->graphics_therm_throttle_enable,
+				   sizeof(u8), pi->sram_end);
+
+	return ret;
+}
+
+static int kv_upload_dpm_settings(struct radeon_device *rdev)
+{
+	struct kv_power_info *pi = kv_get_pi(rdev);
+	int ret;
+
+	ret = kv_copy_bytes_to_smc(rdev,
+				   pi->dpm_table_start +
+				   offsetof(SMU7_Fusion_DpmTable, GraphicsLevel),
+				   (u8 *)&pi->graphics_level,
+				   sizeof(SMU7_Fusion_GraphicsLevel) * SMU7_MAX_LEVELS_GRAPHICS,
+				   pi->sram_end);
+
+	if (ret)
+		return ret;
+
+	ret = kv_copy_bytes_to_smc(rdev,
+				   pi->dpm_table_start +
+				   offsetof(SMU7_Fusion_DpmTable, GraphicsDpmLevelCount),
+				   &pi->graphics_dpm_level_count,
+				   sizeof(u8), pi->sram_end);
+
+	return ret;
+}
+
+static u32 kv_get_clock_difference(u32 a, u32 b)
+{
+	return (a >= b) ? a - b : b - a;
+}
+
+static u32 kv_get_clk_bypass(struct radeon_device *rdev, u32 clk)
+{
+	struct kv_power_info *pi = kv_get_pi(rdev);
+	u32 value;
+
+	if (pi->caps_enable_dfs_bypass) {
+		if (kv_get_clock_difference(clk, 40000) < 200)
+			value = 3;
+		else if (kv_get_clock_difference(clk, 30000) < 200)
+			value = 2;
+		else if (kv_get_clock_difference(clk, 20000) < 200)
+			value = 7;
+		else if (kv_get_clock_difference(clk, 15000) < 200)
+			value = 6;
+		else if (kv_get_clock_difference(clk, 10000) < 200)
+			value = 8;
+		else
+			value = 0;
+	} else {
+		value = 0;
+	}
+
+	return value;
+}
+
+static int kv_populate_uvd_table(struct radeon_device *rdev)
+{
+	struct kv_power_info *pi = kv_get_pi(rdev);
+	struct radeon_uvd_clock_voltage_dependency_table *table =
+		&rdev->pm.dpm.dyn_state.uvd_clock_voltage_dependency_table;
+	struct atom_clock_dividers dividers;
+	int ret;
+	u32 i;
+
+	if (table == NULL || table->count == 0)
+		return 0;
+
+	pi->uvd_level_count = 0;
+	for (i = 0; i < table->count; i++) {
+		if (pi->high_voltage_t &&
+		    (pi->high_voltage_t < table->entries[i].v))
+			break;
+
+		pi->uvd_level[i].VclkFrequency = cpu_to_be32(table->entries[i].vclk);
+		pi->uvd_level[i].DclkFrequency = cpu_to_be32(table->entries[i].dclk);
+		pi->uvd_level[i].MinVddNb = cpu_to_be16(table->entries[i].v);
+
+		pi->uvd_level[i].VClkBypassCntl =
+			(u8)kv_get_clk_bypass(rdev, table->entries[i].vclk);
+		pi->uvd_level[i].DClkBypassCntl =
+			(u8)kv_get_clk_bypass(rdev, table->entries[i].dclk);
+
+		ret = radeon_atom_get_clock_dividers(rdev, COMPUTE_ENGINE_PLL_PARAM,
+						     table->entries[i].vclk, false, &dividers);
+		if (ret)
+			return ret;
+		pi->uvd_level[i].VclkDivider = (u8)dividers.post_div;
+
+		ret = radeon_atom_get_clock_dividers(rdev, COMPUTE_ENGINE_PLL_PARAM,
+						     table->entries[i].dclk, false, &dividers);
+		if (ret)
+			return ret;
+		pi->uvd_level[i].DclkDivider = (u8)dividers.post_div;
+
+		pi->uvd_level_count++;
+	}
+
+	ret = kv_copy_bytes_to_smc(rdev,
+				   pi->dpm_table_start +
+				   offsetof(SMU7_Fusion_DpmTable, UvdLevelCount),
+				   (u8 *)&pi->uvd_level_count,
+				   sizeof(u8), pi->sram_end);
+	if (ret)
+		return ret;
+
+	pi->uvd_interval = 1;
+
+	ret = kv_copy_bytes_to_smc(rdev,
+				   pi->dpm_table_start +
+				   offsetof(SMU7_Fusion_DpmTable, UVDInterval),
+				   &pi->uvd_interval,
+				   sizeof(u8), pi->sram_end);
+	if (ret)
+		return ret;
+
+	ret = kv_copy_bytes_to_smc(rdev,
+				   pi->dpm_table_start +
+				   offsetof(SMU7_Fusion_DpmTable, UvdLevel),
+				   (u8 *)&pi->uvd_level,
+				   sizeof(SMU7_Fusion_UvdLevel) * SMU7_MAX_LEVELS_UVD,
+				   pi->sram_end);
+
+	return ret;
+
+}
+
+static int kv_populate_vce_table(struct radeon_device *rdev)
+{
+	struct kv_power_info *pi = kv_get_pi(rdev);
+	int ret;
+	u32 i;
+	struct radeon_vce_clock_voltage_dependency_table *table =
+		&rdev->pm.dpm.dyn_state.vce_clock_voltage_dependency_table;
+	struct atom_clock_dividers dividers;
+
+	if (table == NULL || table->count == 0)
+		return 0;
+
+	pi->vce_level_count = 0;
+	for (i = 0; i < table->count; i++) {
+		if (pi->high_voltage_t &&
+		    pi->high_voltage_t < table->entries[i].v)
+			break;
+
+		pi->vce_level[i].Frequency = cpu_to_be32(table->entries[i].evclk);
+		pi->vce_level[i].MinVoltage = cpu_to_be16(table->entries[i].v);
+
+		pi->vce_level[i].ClkBypassCntl =
+			(u8)kv_get_clk_bypass(rdev, table->entries[i].evclk);
+
+		ret = radeon_atom_get_clock_dividers(rdev, COMPUTE_ENGINE_PLL_PARAM,
+						     table->entries[i].evclk, false, &dividers);
+		if (ret)
+			return ret;
+		pi->vce_level[i].Divider = (u8)dividers.post_div;
+
+		pi->vce_level_count++;
+	}
+
+	ret = kv_copy_bytes_to_smc(rdev,
+				   pi->dpm_table_start +
+				   offsetof(SMU7_Fusion_DpmTable, VceLevelCount),
+				   (u8 *)&pi->vce_level_count,
+				   sizeof(u8),
+				   pi->sram_end);
+	if (ret)
+		return ret;
+
+	pi->vce_interval = 1;
+
+	ret = kv_copy_bytes_to_smc(rdev,
+				   pi->dpm_table_start +
+				   offsetof(SMU7_Fusion_DpmTable, VCEInterval),
+				   (u8 *)&pi->vce_interval,
+				   sizeof(u8),
+				   pi->sram_end);
+	if (ret)
+		return ret;
+
+	ret = kv_copy_bytes_to_smc(rdev,
+				   pi->dpm_table_start +
+				   offsetof(SMU7_Fusion_DpmTable, VceLevel),
+				   (u8 *)&pi->vce_level,
+				   sizeof(SMU7_Fusion_ExtClkLevel) * SMU7_MAX_LEVELS_VCE,
+				   pi->sram_end);
+
+	return ret;
+}
+
+static int kv_populate_samu_table(struct radeon_device *rdev)
+{
+	struct kv_power_info *pi = kv_get_pi(rdev);
+	struct radeon_clock_voltage_dependency_table *table =
+		&rdev->pm.dpm.dyn_state.samu_clock_voltage_dependency_table;
+	struct atom_clock_dividers dividers;
+	int ret;
+	u32 i;
+
+	if (table == NULL || table->count == 0)
+		return 0;
+
+	pi->samu_level_count = 0;
+	for (i = 0; i < table->count; i++) {
+		if (pi->high_voltage_t &&
+		    pi->high_voltage_t < table->entries[i].v)
+			break;
+
+		pi->samu_level[i].Frequency = cpu_to_be32(table->entries[i].clk);
+		pi->samu_level[i].MinVoltage = cpu_to_be16(table->entries[i].v);
+
+		pi->samu_level[i].ClkBypassCntl =
+			(u8)kv_get_clk_bypass(rdev, table->entries[i].clk);
+
+		ret = radeon_atom_get_clock_dividers(rdev, COMPUTE_ENGINE_PLL_PARAM,
+						     table->entries[i].clk, false, &dividers);
+		if (ret)
+			return ret;
+		pi->samu_level[i].Divider = (u8)dividers.post_div;
+
+		pi->samu_level_count++;
+	}
+
+	ret = kv_copy_bytes_to_smc(rdev,
+				   pi->dpm_table_start +
+				   offsetof(SMU7_Fusion_DpmTable, SamuLevelCount),
+				   (u8 *)&pi->samu_level_count,
+				   sizeof(u8),
+				   pi->sram_end);
+	if (ret)
+		return ret;
+
+	pi->samu_interval = 1;
+
+	ret = kv_copy_bytes_to_smc(rdev,
+				   pi->dpm_table_start +
+				   offsetof(SMU7_Fusion_DpmTable, SAMUInterval),
+				   (u8 *)&pi->samu_interval,
+				   sizeof(u8),
+				   pi->sram_end);
+	if (ret)
+		return ret;
+
+	ret = kv_copy_bytes_to_smc(rdev,
+				   pi->dpm_table_start +
+				   offsetof(SMU7_Fusion_DpmTable, SamuLevel),
+				   (u8 *)&pi->samu_level,
+				   sizeof(SMU7_Fusion_ExtClkLevel) * SMU7_MAX_LEVELS_SAMU,
+				   pi->sram_end);
+	if (ret)
+		return ret;
+
+	return ret;
+}
+
+
+static int kv_populate_acp_table(struct radeon_device *rdev)
+{
+	struct kv_power_info *pi = kv_get_pi(rdev);
+	struct radeon_clock_voltage_dependency_table *table =
+		&rdev->pm.dpm.dyn_state.acp_clock_voltage_dependency_table;
+	struct atom_clock_dividers dividers;
+	int ret;
+	u32 i;
+
+	if (table == NULL || table->count == 0)
+		return 0;
+
+	pi->acp_level_count = 0;
+	for (i = 0; i < table->count; i++) {
+		pi->acp_level[i].Frequency = cpu_to_be32(table->entries[i].clk);
+		pi->acp_level[i].MinVoltage = cpu_to_be16(table->entries[i].v);
+
+		ret = radeon_atom_get_clock_dividers(rdev, COMPUTE_ENGINE_PLL_PARAM,
+						     table->entries[i].clk, false, &dividers);
+		if (ret)
+			return ret;
+		pi->acp_level[i].Divider = (u8)dividers.post_div;
+
+		pi->acp_level_count++;
+	}
+
+	ret = kv_copy_bytes_to_smc(rdev,
+				   pi->dpm_table_start +
+				   offsetof(SMU7_Fusion_DpmTable, AcpLevelCount),
+				   (u8 *)&pi->acp_level_count,
+				   sizeof(u8),
+				   pi->sram_end);
+	if (ret)
+		return ret;
+
+	pi->acp_interval = 1;
+
+	ret = kv_copy_bytes_to_smc(rdev,
+				   pi->dpm_table_start +
+				   offsetof(SMU7_Fusion_DpmTable, ACPInterval),
+				   (u8 *)&pi->acp_interval,
+				   sizeof(u8),
+				   pi->sram_end);
+	if (ret)
+		return ret;
+
+	ret = kv_copy_bytes_to_smc(rdev,
+				   pi->dpm_table_start +
+				   offsetof(SMU7_Fusion_DpmTable, AcpLevel),
+				   (u8 *)&pi->acp_level,
+				   sizeof(SMU7_Fusion_ExtClkLevel) * SMU7_MAX_LEVELS_ACP,
+				   pi->sram_end);
+	if (ret)
+		return ret;
+
+	return ret;
+}
+
+static void kv_calculate_dfs_bypass_settings(struct radeon_device *rdev)
+{
+	struct kv_power_info *pi = kv_get_pi(rdev);
+	u32 i;
+	struct radeon_clock_voltage_dependency_table *table =
+		&rdev->pm.dpm.dyn_state.vddc_dependency_on_sclk;
+
+	if (table && table->count) {
+		for (i = 0; i < pi->graphics_dpm_level_count; i++) {
+			if (pi->caps_enable_dfs_bypass) {
+				if (kv_get_clock_difference(table->entries[i].clk, 40000) < 200)
+					pi->graphics_level[i].ClkBypassCntl = 3;
+				else if (kv_get_clock_difference(table->entries[i].clk, 30000) < 200)
+					pi->graphics_level[i].ClkBypassCntl = 2;
+				else if (kv_get_clock_difference(table->entries[i].clk, 26600) < 200)
+					pi->graphics_level[i].ClkBypassCntl = 7;
+				else if (kv_get_clock_difference(table->entries[i].clk , 20000) < 200)
+					pi->graphics_level[i].ClkBypassCntl = 6;
+				else if (kv_get_clock_difference(table->entries[i].clk , 10000) < 200)
+					pi->graphics_level[i].ClkBypassCntl = 8;
+				else
+					pi->graphics_level[i].ClkBypassCntl = 0;
+			} else {
+				pi->graphics_level[i].ClkBypassCntl = 0;
+			}
+		}
+	} else {
+		struct sumo_sclk_voltage_mapping_table *table =
+			&pi->sys_info.sclk_voltage_mapping_table;
+		for (i = 0; i < pi->graphics_dpm_level_count; i++) {
+			if (pi->caps_enable_dfs_bypass) {
+				if (kv_get_clock_difference(table->entries[i].sclk_frequency, 40000) < 200)
+					pi->graphics_level[i].ClkBypassCntl = 3;
+				else if (kv_get_clock_difference(table->entries[i].sclk_frequency, 30000) < 200)
+					pi->graphics_level[i].ClkBypassCntl = 2;
+				else if (kv_get_clock_difference(table->entries[i].sclk_frequency, 26600) < 200)
+					pi->graphics_level[i].ClkBypassCntl = 7;
+				else if (kv_get_clock_difference(table->entries[i].sclk_frequency, 20000) < 200)
+					pi->graphics_level[i].ClkBypassCntl = 6;
+				else if (kv_get_clock_difference(table->entries[i].sclk_frequency, 10000) < 200)
+					pi->graphics_level[i].ClkBypassCntl = 8;
+				else
+					pi->graphics_level[i].ClkBypassCntl = 0;
+			} else {
+				pi->graphics_level[i].ClkBypassCntl = 0;
+			}
+		}
+	}
+}
+
+static int kv_enable_ulv(struct radeon_device *rdev, bool enable)
+{
+	return kv_notify_message_to_smu(rdev, enable ?
+					PPSMC_MSG_EnableULV : PPSMC_MSG_DisableULV);
+}
+
+static void kv_reset_acp_boot_level(struct radeon_device *rdev)
+{
+	struct kv_power_info *pi = kv_get_pi(rdev);
+
+	pi->acp_boot_level = 0xff;
+}
+
+static void kv_update_current_ps(struct radeon_device *rdev,
+				 struct radeon_ps *rps)
+{
+	struct kv_ps *new_ps = kv_get_ps(rps);
+	struct kv_power_info *pi = kv_get_pi(rdev);
+
+	pi->current_rps = *rps;
+	pi->current_ps = *new_ps;
+	pi->current_rps.ps_priv = &pi->current_ps;
+}
+
+static void kv_update_requested_ps(struct radeon_device *rdev,
+				   struct radeon_ps *rps)
+{
+	struct kv_ps *new_ps = kv_get_ps(rps);
+	struct kv_power_info *pi = kv_get_pi(rdev);
+
+	pi->requested_rps = *rps;
+	pi->requested_ps = *new_ps;
+	pi->requested_rps.ps_priv = &pi->requested_ps;
+}
+
+void kv_dpm_enable_bapm(struct radeon_device *rdev, bool enable)
+{
+	struct kv_power_info *pi = kv_get_pi(rdev);
+	int ret;
+
+	if (pi->bapm_enable) {
+		ret = kv_smc_bapm_enable(rdev, enable);
+		if (ret)
+			DRM_ERROR("kv_smc_bapm_enable failed\n");
+	}
+}
+
+int kv_dpm_enable(struct radeon_device *rdev)
+{
+	struct kv_power_info *pi = kv_get_pi(rdev);
+	int ret;
+
+	cik_update_cg(rdev, (RADEON_CG_BLOCK_GFX |
+			     RADEON_CG_BLOCK_SDMA |
+			     RADEON_CG_BLOCK_BIF |
+			     RADEON_CG_BLOCK_HDP), false);
+
+	ret = kv_process_firmware_header(rdev);
+	if (ret) {
+		DRM_ERROR("kv_process_firmware_header failed\n");
+		return ret;
+	}
+	kv_init_fps_limits(rdev);
+	kv_init_graphics_levels(rdev);
+	ret = kv_program_bootup_state(rdev);
+	if (ret) {
+		DRM_ERROR("kv_program_bootup_state failed\n");
+		return ret;
+	}
+	kv_calculate_dfs_bypass_settings(rdev);
+	ret = kv_upload_dpm_settings(rdev);
+	if (ret) {
+		DRM_ERROR("kv_upload_dpm_settings failed\n");
+		return ret;
+	}
+	ret = kv_populate_uvd_table(rdev);
+	if (ret) {
+		DRM_ERROR("kv_populate_uvd_table failed\n");
+		return ret;
+	}
+	ret = kv_populate_vce_table(rdev);
+	if (ret) {
+		DRM_ERROR("kv_populate_vce_table failed\n");
+		return ret;
+	}
+	ret = kv_populate_samu_table(rdev);
+	if (ret) {
+		DRM_ERROR("kv_populate_samu_table failed\n");
+		return ret;
+	}
+	ret = kv_populate_acp_table(rdev);
+	if (ret) {
+		DRM_ERROR("kv_populate_acp_table failed\n");
+		return ret;
+	}
+	kv_program_vc(rdev);
+#if 0
+	kv_initialize_hardware_cac_manager(rdev);
+#endif
+	kv_start_am(rdev);
+	if (pi->enable_auto_thermal_throttling) {
+		ret = kv_enable_auto_thermal_throttling(rdev);
+		if (ret) {
+			DRM_ERROR("kv_enable_auto_thermal_throttling failed\n");
+			return ret;
+		}
+	}
+	ret = kv_enable_dpm_voltage_scaling(rdev);
+	if (ret) {
+		DRM_ERROR("kv_enable_dpm_voltage_scaling failed\n");
+		return ret;
+	}
+	ret = kv_set_dpm_interval(rdev);
+	if (ret) {
+		DRM_ERROR("kv_set_dpm_interval failed\n");
+		return ret;
+	}
+	ret = kv_set_dpm_boot_state(rdev);
+	if (ret) {
+		DRM_ERROR("kv_set_dpm_boot_state failed\n");
+		return ret;
+	}
+	ret = kv_enable_ulv(rdev, true);
+	if (ret) {
+		DRM_ERROR("kv_enable_ulv failed\n");
+		return ret;
+	}
+	kv_start_dpm(rdev);
+	ret = kv_enable_didt(rdev, true);
+	if (ret) {
+		DRM_ERROR("kv_enable_didt failed\n");
+		return ret;
+	}
+	ret = kv_enable_smc_cac(rdev, true);
+	if (ret) {
+		DRM_ERROR("kv_enable_smc_cac failed\n");
+		return ret;
+	}
+
+	kv_reset_acp_boot_level(rdev);
+
+	if (rdev->irq.installed &&
+	    r600_is_internal_thermal_sensor(rdev->pm.int_thermal_type)) {
+		ret = kv_set_thermal_temperature_range(rdev, R600_TEMP_RANGE_MIN, R600_TEMP_RANGE_MAX);
+		if (ret) {
+			DRM_ERROR("kv_set_thermal_temperature_range failed\n");
+			return ret;
+		}
+		rdev->irq.dpm_thermal = true;
+		radeon_irq_set(rdev);
+	}
+
+	ret = kv_smc_bapm_enable(rdev, false);
+	if (ret) {
+		DRM_ERROR("kv_smc_bapm_enable failed\n");
+		return ret;
+	}
+
+	/* powerdown unused blocks for now */
+	kv_dpm_powergate_acp(rdev, true);
+	kv_dpm_powergate_samu(rdev, true);
+	kv_dpm_powergate_vce(rdev, true);
+	kv_dpm_powergate_uvd(rdev, true);
+
+	cik_update_cg(rdev, (RADEON_CG_BLOCK_GFX |
+			     RADEON_CG_BLOCK_SDMA |
+			     RADEON_CG_BLOCK_BIF |
+			     RADEON_CG_BLOCK_HDP), true);
+
+	kv_update_current_ps(rdev, rdev->pm.dpm.boot_ps);
+
+	return ret;
+}
+
+void kv_dpm_disable(struct radeon_device *rdev)
+{
+	cik_update_cg(rdev, (RADEON_CG_BLOCK_GFX |
+			     RADEON_CG_BLOCK_SDMA |
+			     RADEON_CG_BLOCK_BIF |
+			     RADEON_CG_BLOCK_HDP), false);
+
+	kv_smc_bapm_enable(rdev, false);
+
+	/* powerup blocks */
+	kv_dpm_powergate_acp(rdev, false);
+	kv_dpm_powergate_samu(rdev, false);
+	kv_dpm_powergate_vce(rdev, false);
+	kv_dpm_powergate_uvd(rdev, false);
+
+	kv_enable_smc_cac(rdev, false);
+	kv_enable_didt(rdev, false);
+	kv_clear_vc(rdev);
+	kv_stop_dpm(rdev);
+	kv_enable_ulv(rdev, false);
+	kv_reset_am(rdev);
+
+	kv_update_current_ps(rdev, rdev->pm.dpm.boot_ps);
+}
+
+#if 0
+static int kv_write_smc_soft_register(struct radeon_device *rdev,
+				      u16 reg_offset, u32 value)
+{
+	struct kv_power_info *pi = kv_get_pi(rdev);
+
+	return kv_copy_bytes_to_smc(rdev, pi->soft_regs_start + reg_offset,
+				    (u8 *)&value, sizeof(u16), pi->sram_end);
+}
+
+static int kv_read_smc_soft_register(struct radeon_device *rdev,
+				     u16 reg_offset, u32 *value)
+{
+	struct kv_power_info *pi = kv_get_pi(rdev);
+
+	return kv_read_smc_sram_dword(rdev, pi->soft_regs_start + reg_offset,
+				      value, pi->sram_end);
+}
+#endif
+
+static void kv_init_sclk_t(struct radeon_device *rdev)
+{
+	struct kv_power_info *pi = kv_get_pi(rdev);
+
+	pi->low_sclk_interrupt_t = 0;
+}
+
+static int kv_init_fps_limits(struct radeon_device *rdev)
+{
+	struct kv_power_info *pi = kv_get_pi(rdev);
+	int ret = 0;
+
+	if (pi->caps_fps) {
+		u16 tmp;
+
+		tmp = 45;
+		pi->fps_high_t = cpu_to_be16(tmp);
+		ret = kv_copy_bytes_to_smc(rdev,
+					   pi->dpm_table_start +
+					   offsetof(SMU7_Fusion_DpmTable, FpsHighT),
+					   (u8 *)&pi->fps_high_t,
+					   sizeof(u16), pi->sram_end);
+
+		tmp = 30;
+		pi->fps_low_t = cpu_to_be16(tmp);
+
+		ret = kv_copy_bytes_to_smc(rdev,
+					   pi->dpm_table_start +
+					   offsetof(SMU7_Fusion_DpmTable, FpsLowT),
+					   (u8 *)&pi->fps_low_t,
+					   sizeof(u16), pi->sram_end);
+
+	}
+	return ret;
+}
+
+static void kv_init_powergate_state(struct radeon_device *rdev)
+{
+	struct kv_power_info *pi = kv_get_pi(rdev);
+
+	pi->uvd_power_gated = false;
+	pi->vce_power_gated = false;
+	pi->samu_power_gated = false;
+	pi->acp_power_gated = false;
+
+}
+
+static int kv_enable_uvd_dpm(struct radeon_device *rdev, bool enable)
+{
+	return kv_notify_message_to_smu(rdev, enable ?
+					PPSMC_MSG_UVDDPM_Enable : PPSMC_MSG_UVDDPM_Disable);
+}
+
+#if 0
+static int kv_enable_vce_dpm(struct radeon_device *rdev, bool enable)
+{
+	return kv_notify_message_to_smu(rdev, enable ?
+					PPSMC_MSG_VCEDPM_Enable : PPSMC_MSG_VCEDPM_Disable);
+}
+#endif
+
+static int kv_enable_samu_dpm(struct radeon_device *rdev, bool enable)
+{
+	return kv_notify_message_to_smu(rdev, enable ?
+					PPSMC_MSG_SAMUDPM_Enable : PPSMC_MSG_SAMUDPM_Disable);
+}
+
+static int kv_enable_acp_dpm(struct radeon_device *rdev, bool enable)
+{
+	return kv_notify_message_to_smu(rdev, enable ?
+					PPSMC_MSG_ACPDPM_Enable : PPSMC_MSG_ACPDPM_Disable);
+}
+
+static int kv_update_uvd_dpm(struct radeon_device *rdev, bool gate)
+{
+	struct kv_power_info *pi = kv_get_pi(rdev);
+	struct radeon_uvd_clock_voltage_dependency_table *table =
+		&rdev->pm.dpm.dyn_state.uvd_clock_voltage_dependency_table;
+	int ret;
+
+	if (!gate) {
+		if (!pi->caps_uvd_dpm || table->count || pi->caps_stable_p_state)
+			pi->uvd_boot_level = table->count - 1;
+		else
+			pi->uvd_boot_level = 0;
+
+		ret = kv_copy_bytes_to_smc(rdev,
+					   pi->dpm_table_start +
+					   offsetof(SMU7_Fusion_DpmTable, UvdBootLevel),
+					   (uint8_t *)&pi->uvd_boot_level,
+					   sizeof(u8), pi->sram_end);
+		if (ret)
+			return ret;
+
+		if (!pi->caps_uvd_dpm ||
+		    pi->caps_stable_p_state)
+			kv_send_msg_to_smc_with_parameter(rdev,
+							  PPSMC_MSG_UVDDPM_SetEnabledMask,
+							  (1 << pi->uvd_boot_level));
+	}
+
+	return kv_enable_uvd_dpm(rdev, !gate);
+}
+
+#if 0
+static u8 kv_get_vce_boot_level(struct radeon_device *rdev)
+{
+	u8 i;
+	struct radeon_vce_clock_voltage_dependency_table *table =
+		&rdev->pm.dpm.dyn_state.vce_clock_voltage_dependency_table;
+
+	for (i = 0; i < table->count; i++) {
+		if (table->entries[i].evclk >= 0) /* XXX */
+			break;
+	}
+
+	return i;
+}
+
+static int kv_update_vce_dpm(struct radeon_device *rdev,
+			     struct radeon_ps *radeon_new_state,
+			     struct radeon_ps *radeon_current_state)
+{
+	struct kv_power_info *pi = kv_get_pi(rdev);
+	struct radeon_vce_clock_voltage_dependency_table *table =
+		&rdev->pm.dpm.dyn_state.vce_clock_voltage_dependency_table;
+	int ret;
+
+	if (radeon_new_state->evclk > 0 && radeon_current_state->evclk == 0) {
+		if (pi->caps_stable_p_state)
+			pi->vce_boot_level = table->count - 1;
+		else
+			pi->vce_boot_level = kv_get_vce_boot_level(rdev);
+
+		ret = kv_copy_bytes_to_smc(rdev,
+					   pi->dpm_table_start +
+					   offsetof(SMU7_Fusion_DpmTable, VceBootLevel),
+					   (u8 *)&pi->vce_boot_level,
+					   sizeof(u8),
+					   pi->sram_end);
+		if (ret)
+			return ret;
+
+		if (pi->caps_stable_p_state)
+			kv_send_msg_to_smc_with_parameter(rdev,
+							  PPSMC_MSG_VCEDPM_SetEnabledMask,
+							  (1 << pi->vce_boot_level));
+
+		kv_enable_vce_dpm(rdev, true);
+	} else if (radeon_new_state->evclk == 0 && radeon_current_state->evclk > 0) {
+		kv_enable_vce_dpm(rdev, false);
+	}
+
+	return 0;
+}
+#endif
+
+static int kv_update_samu_dpm(struct radeon_device *rdev, bool gate)
+{
+	struct kv_power_info *pi = kv_get_pi(rdev);
+	struct radeon_clock_voltage_dependency_table *table =
+		&rdev->pm.dpm.dyn_state.samu_clock_voltage_dependency_table;
+	int ret;
+
+	if (!gate) {
+		if (pi->caps_stable_p_state)
+			pi->samu_boot_level = table->count - 1;
+		else
+			pi->samu_boot_level = 0;
+
+		ret = kv_copy_bytes_to_smc(rdev,
+					   pi->dpm_table_start +
+					   offsetof(SMU7_Fusion_DpmTable, SamuBootLevel),
+					   (u8 *)&pi->samu_boot_level,
+					   sizeof(u8),
+					   pi->sram_end);
+		if (ret)
+			return ret;
+
+		if (pi->caps_stable_p_state)
+			kv_send_msg_to_smc_with_parameter(rdev,
+							  PPSMC_MSG_SAMUDPM_SetEnabledMask,
+							  (1 << pi->samu_boot_level));
+	}
+
+	return kv_enable_samu_dpm(rdev, !gate);
+}
+
+static u8 kv_get_acp_boot_level(struct radeon_device *rdev)
+{
+	u8 i;
+	struct radeon_clock_voltage_dependency_table *table =
+		&rdev->pm.dpm.dyn_state.acp_clock_voltage_dependency_table;
+
+	for (i = 0; i < table->count; i++) {
+		if (table->entries[i].clk >= 0) /* XXX */
+			break;
+	}
+
+	if (i >= table->count)
+		i = table->count - 1;
+
+	return i;
+}
+
+static void kv_update_acp_boot_level(struct radeon_device *rdev)
+{
+	struct kv_power_info *pi = kv_get_pi(rdev);
+	u8 acp_boot_level;
+
+	if (!pi->caps_stable_p_state) {
+		acp_boot_level = kv_get_acp_boot_level(rdev);
+		if (acp_boot_level != pi->acp_boot_level) {
+			pi->acp_boot_level = acp_boot_level;
+			kv_send_msg_to_smc_with_parameter(rdev,
+							  PPSMC_MSG_ACPDPM_SetEnabledMask,
+							  (1 << pi->acp_boot_level));
+		}
+	}
+}
+
+static int kv_update_acp_dpm(struct radeon_device *rdev, bool gate)
+{
+	struct kv_power_info *pi = kv_get_pi(rdev);
+	struct radeon_clock_voltage_dependency_table *table =
+		&rdev->pm.dpm.dyn_state.acp_clock_voltage_dependency_table;
+	int ret;
+
+	if (!gate) {
+		if (pi->caps_stable_p_state)
+			pi->acp_boot_level = table->count - 1;
+		else
+			pi->acp_boot_level = kv_get_acp_boot_level(rdev);
+
+		ret = kv_copy_bytes_to_smc(rdev,
+					   pi->dpm_table_start +
+					   offsetof(SMU7_Fusion_DpmTable, AcpBootLevel),
+					   (u8 *)&pi->acp_boot_level,
+					   sizeof(u8),
+					   pi->sram_end);
+		if (ret)
+			return ret;
+
+		if (pi->caps_stable_p_state)
+			kv_send_msg_to_smc_with_parameter(rdev,
+							  PPSMC_MSG_ACPDPM_SetEnabledMask,
+							  (1 << pi->acp_boot_level));
+	}
+
+	return kv_enable_acp_dpm(rdev, !gate);
+}
+
+void kv_dpm_powergate_uvd(struct radeon_device *rdev, bool gate)
+{
+	struct kv_power_info *pi = kv_get_pi(rdev);
+
+	if (pi->uvd_power_gated == gate)
+		return;
+
+	pi->uvd_power_gated = gate;
+
+	if (gate) {
+		if (pi->caps_uvd_pg) {
+			uvd_v1_0_stop(rdev);
+			cik_update_cg(rdev, RADEON_CG_BLOCK_UVD, false);
+		}
+		kv_update_uvd_dpm(rdev, gate);
+		if (pi->caps_uvd_pg)
+			kv_notify_message_to_smu(rdev, PPSMC_MSG_UVDPowerOFF);
+	} else {
+		if (pi->caps_uvd_pg) {
+			kv_notify_message_to_smu(rdev, PPSMC_MSG_UVDPowerON);
+			uvd_v4_2_resume(rdev);
+			uvd_v1_0_start(rdev);
+			cik_update_cg(rdev, RADEON_CG_BLOCK_UVD, true);
+		}
+		kv_update_uvd_dpm(rdev, gate);
+	}
+}
+
+static void kv_dpm_powergate_vce(struct radeon_device *rdev, bool gate)
+{
+	struct kv_power_info *pi = kv_get_pi(rdev);
+
+	if (pi->vce_power_gated == gate)
+		return;
+
+	pi->vce_power_gated = gate;
+
+	if (gate) {
+		if (pi->caps_vce_pg)
+			kv_notify_message_to_smu(rdev, PPSMC_MSG_VCEPowerOFF);
+	} else {
+		if (pi->caps_vce_pg)
+			kv_notify_message_to_smu(rdev, PPSMC_MSG_VCEPowerON);
+	}
+}
+
+static void kv_dpm_powergate_samu(struct radeon_device *rdev, bool gate)
+{
+	struct kv_power_info *pi = kv_get_pi(rdev);
+
+	if (pi->samu_power_gated == gate)
+		return;
+
+	pi->samu_power_gated = gate;
+
+	if (gate) {
+		kv_update_samu_dpm(rdev, true);
+		if (pi->caps_samu_pg)
+			kv_notify_message_to_smu(rdev, PPSMC_MSG_SAMPowerOFF);
+	} else {
+		if (pi->caps_samu_pg)
+			kv_notify_message_to_smu(rdev, PPSMC_MSG_SAMPowerON);
+		kv_update_samu_dpm(rdev, false);
+	}
+}
+
+static void kv_dpm_powergate_acp(struct radeon_device *rdev, bool gate)
+{
+	struct kv_power_info *pi = kv_get_pi(rdev);
+
+	if (pi->acp_power_gated == gate)
+		return;
+
+	if (rdev->family == CHIP_KABINI)
+		return;
+
+	pi->acp_power_gated = gate;
+
+	if (gate) {
+		kv_update_acp_dpm(rdev, true);
+		if (pi->caps_acp_pg)
+			kv_notify_message_to_smu(rdev, PPSMC_MSG_ACPPowerOFF);
+	} else {
+		if (pi->caps_acp_pg)
+			kv_notify_message_to_smu(rdev, PPSMC_MSG_ACPPowerON);
+		kv_update_acp_dpm(rdev, false);
+	}
+}
+
+static void kv_set_valid_clock_range(struct radeon_device *rdev,
+				     struct radeon_ps *new_rps)
+{
+	struct kv_ps *new_ps = kv_get_ps(new_rps);
+	struct kv_power_info *pi = kv_get_pi(rdev);
+	u32 i;
+	struct radeon_clock_voltage_dependency_table *table =
+		&rdev->pm.dpm.dyn_state.vddc_dependency_on_sclk;
+
+	if (table && table->count) {
+		for (i = 0; i < pi->graphics_dpm_level_count; i++) {
+			if ((table->entries[i].clk >= new_ps->levels[0].sclk) ||
+			    (i == (pi->graphics_dpm_level_count - 1))) {
+				pi->lowest_valid = i;
+				break;
+			}
+		}
+
+		for (i = pi->graphics_dpm_level_count - 1; i > 0; i--) {
+			if (table->entries[i].clk <= new_ps->levels[new_ps->num_levels - 1].sclk)
+				break;
+		}
+		pi->highest_valid = i;
+
+		if (pi->lowest_valid > pi->highest_valid) {
+			if ((new_ps->levels[0].sclk - table->entries[pi->highest_valid].clk) >
+			    (table->entries[pi->lowest_valid].clk - new_ps->levels[new_ps->num_levels - 1].sclk))
+				pi->highest_valid = pi->lowest_valid;
+			else
+				pi->lowest_valid =  pi->highest_valid;
+		}
+	} else {
+		struct sumo_sclk_voltage_mapping_table *table =
+			&pi->sys_info.sclk_voltage_mapping_table;
+
+		for (i = 0; i < (int)pi->graphics_dpm_level_count; i++) {
+			if (table->entries[i].sclk_frequency >= new_ps->levels[0].sclk ||
+			    i == (int)(pi->graphics_dpm_level_count - 1)) {
+				pi->lowest_valid = i;
+				break;
+			}
+		}
+
+		for (i = pi->graphics_dpm_level_count - 1; i > 0; i--) {
+			if (table->entries[i].sclk_frequency <=
+			    new_ps->levels[new_ps->num_levels - 1].sclk)
+				break;
+		}
+		pi->highest_valid = i;
+
+		if (pi->lowest_valid > pi->highest_valid) {
+			if ((new_ps->levels[0].sclk -
+			     table->entries[pi->highest_valid].sclk_frequency) >
+			    (table->entries[pi->lowest_valid].sclk_frequency -
+			     new_ps->levels[new_ps->num_levels -1].sclk))
+				pi->highest_valid = pi->lowest_valid;
+			else
+				pi->lowest_valid =  pi->highest_valid;
+		}
+	}
+}
+
+static int kv_update_dfs_bypass_settings(struct radeon_device *rdev,
+					 struct radeon_ps *new_rps)
+{
+	struct kv_ps *new_ps = kv_get_ps(new_rps);
+	struct kv_power_info *pi = kv_get_pi(rdev);
+	int ret = 0;
+	u8 clk_bypass_cntl;
+
+	if (pi->caps_enable_dfs_bypass) {
+		clk_bypass_cntl = new_ps->need_dfs_bypass ?
+			pi->graphics_level[pi->graphics_boot_level].ClkBypassCntl : 0;
+		ret = kv_copy_bytes_to_smc(rdev,
+					   (pi->dpm_table_start +
+					    offsetof(SMU7_Fusion_DpmTable, GraphicsLevel) +
+					    (pi->graphics_boot_level * sizeof(SMU7_Fusion_GraphicsLevel)) +
+					    offsetof(SMU7_Fusion_GraphicsLevel, ClkBypassCntl)),
+					   &clk_bypass_cntl,
+					   sizeof(u8), pi->sram_end);
+	}
+
+	return ret;
+}
+
+static int kv_enable_nb_dpm(struct radeon_device *rdev)
+{
+	struct kv_power_info *pi = kv_get_pi(rdev);
+	int ret = 0;
+
+	if (pi->enable_nb_dpm && !pi->nb_dpm_enabled) {
+		ret = kv_notify_message_to_smu(rdev, PPSMC_MSG_NBDPM_Enable);
+		if (ret == 0)
+			pi->nb_dpm_enabled = true;
+	}
+
+	return ret;
+}
+
+int kv_dpm_force_performance_level(struct radeon_device *rdev,
+				   enum radeon_dpm_forced_level level)
+{
+	int ret;
+
+	if (level == RADEON_DPM_FORCED_LEVEL_HIGH) {
+		ret = kv_force_dpm_highest(rdev);
+		if (ret)
+			return ret;
+	} else if (level == RADEON_DPM_FORCED_LEVEL_LOW) {
+		ret = kv_force_dpm_lowest(rdev);
+		if (ret)
+			return ret;
+	} else if (level == RADEON_DPM_FORCED_LEVEL_AUTO) {
+		ret = kv_unforce_levels(rdev);
+		if (ret)
+			return ret;
+	}
+
+	rdev->pm.dpm.forced_level = level;
+
+	return 0;
+}
+
+int kv_dpm_pre_set_power_state(struct radeon_device *rdev)
+{
+	struct kv_power_info *pi = kv_get_pi(rdev);
+	struct radeon_ps requested_ps = *rdev->pm.dpm.requested_ps;
+	struct radeon_ps *new_ps = &requested_ps;
+
+	kv_update_requested_ps(rdev, new_ps);
+
+	kv_apply_state_adjust_rules(rdev,
+				    &pi->requested_rps,
+				    &pi->current_rps);
+
+	return 0;
+}
+
+int kv_dpm_set_power_state(struct radeon_device *rdev)
+{
+	struct kv_power_info *pi = kv_get_pi(rdev);
+	struct radeon_ps *new_ps = &pi->requested_rps;
+	/*struct radeon_ps *old_ps = &pi->current_rps;*/
+	int ret;
+
+	cik_update_cg(rdev, (RADEON_CG_BLOCK_GFX |
+			     RADEON_CG_BLOCK_SDMA |
+			     RADEON_CG_BLOCK_BIF |
+			     RADEON_CG_BLOCK_HDP), false);
+
+	if (pi->bapm_enable) {
+		ret = kv_smc_bapm_enable(rdev, rdev->pm.dpm.ac_power);
+		if (ret) {
+			DRM_ERROR("kv_smc_bapm_enable failed\n");
+			return ret;
+		}
+	}
+
+	if (rdev->family == CHIP_KABINI) {
+		if (pi->enable_dpm) {
+			kv_set_valid_clock_range(rdev, new_ps);
+			kv_update_dfs_bypass_settings(rdev, new_ps);
+			ret = kv_calculate_ds_divider(rdev);
+			if (ret) {
+				DRM_ERROR("kv_calculate_ds_divider failed\n");
+				return ret;
+			}
+			kv_calculate_nbps_level_settings(rdev);
+			kv_calculate_dpm_settings(rdev);
+			kv_force_lowest_valid(rdev);
+			kv_enable_new_levels(rdev);
+			kv_upload_dpm_settings(rdev);
+			kv_program_nbps_index_settings(rdev, new_ps);
+			kv_unforce_levels(rdev);
+			kv_set_enabled_levels(rdev);
+			kv_force_lowest_valid(rdev);
+			kv_unforce_levels(rdev);
+#if 0
+			ret = kv_update_vce_dpm(rdev, new_ps, old_ps);
+			if (ret) {
+				DRM_ERROR("kv_update_vce_dpm failed\n");
+				return ret;
+			}
+#endif
+			kv_update_sclk_t(rdev);
+		}
+	} else {
+		if (pi->enable_dpm) {
+			kv_set_valid_clock_range(rdev, new_ps);
+			kv_update_dfs_bypass_settings(rdev, new_ps);
+			ret = kv_calculate_ds_divider(rdev);
+			if (ret) {
+				DRM_ERROR("kv_calculate_ds_divider failed\n");
+				return ret;
+			}
+			kv_calculate_nbps_level_settings(rdev);
+			kv_calculate_dpm_settings(rdev);
+			kv_freeze_sclk_dpm(rdev, true);
+			kv_upload_dpm_settings(rdev);
+			kv_program_nbps_index_settings(rdev, new_ps);
+			kv_freeze_sclk_dpm(rdev, false);
+			kv_set_enabled_levels(rdev);
+#if 0
+			ret = kv_update_vce_dpm(rdev, new_ps, old_ps);
+			if (ret) {
+				DRM_ERROR("kv_update_vce_dpm failed\n");
+				return ret;
+			}
+#endif
+			kv_update_acp_boot_level(rdev);
+			kv_update_sclk_t(rdev);
+			kv_enable_nb_dpm(rdev);
+		}
+	}
+
+	cik_update_cg(rdev, (RADEON_CG_BLOCK_GFX |
+			     RADEON_CG_BLOCK_SDMA |
+			     RADEON_CG_BLOCK_BIF |
+			     RADEON_CG_BLOCK_HDP), true);
+
+	return 0;
+}
+
+void kv_dpm_post_set_power_state(struct radeon_device *rdev)
+{
+	struct kv_power_info *pi = kv_get_pi(rdev);
+	struct radeon_ps *new_ps = &pi->requested_rps;
+
+	kv_update_current_ps(rdev, new_ps);
+}
+
+void kv_dpm_setup_asic(struct radeon_device *rdev)
+{
+	sumo_take_smu_control(rdev, true);
+	kv_init_powergate_state(rdev);
+	kv_init_sclk_t(rdev);
+}
+
+void kv_dpm_reset_asic(struct radeon_device *rdev)
+{
+	struct kv_power_info *pi = kv_get_pi(rdev);
+
+	if (rdev->family == CHIP_KABINI) {
+		kv_force_lowest_valid(rdev);
+		kv_init_graphics_levels(rdev);
+		kv_program_bootup_state(rdev);
+		kv_upload_dpm_settings(rdev);
+		kv_force_lowest_valid(rdev);
+		kv_unforce_levels(rdev);
+	} else {
+		kv_init_graphics_levels(rdev);
+		kv_program_bootup_state(rdev);
+		kv_freeze_sclk_dpm(rdev, true);
+		kv_upload_dpm_settings(rdev);
+		kv_freeze_sclk_dpm(rdev, false);
+		kv_set_enabled_level(rdev, pi->graphics_boot_level);
+	}
+}
+
+//XXX use sumo_dpm_display_configuration_changed
+
+static void kv_construct_max_power_limits_table(struct radeon_device *rdev,
+						struct radeon_clock_and_voltage_limits *table)
+{
+	struct kv_power_info *pi = kv_get_pi(rdev);
+
+	if (pi->sys_info.sclk_voltage_mapping_table.num_max_dpm_entries > 0) {
+		int idx = pi->sys_info.sclk_voltage_mapping_table.num_max_dpm_entries - 1;
+		table->sclk =
+			pi->sys_info.sclk_voltage_mapping_table.entries[idx].sclk_frequency;
+		table->vddc =
+			kv_convert_2bit_index_to_voltage(rdev,
+							 pi->sys_info.sclk_voltage_mapping_table.entries[idx].vid_2bit);
+	}
+
+	table->mclk = pi->sys_info.nbp_memory_clock[0];
+}
+
+static void kv_patch_voltage_values(struct radeon_device *rdev)
+{
+	int i;
+	struct radeon_uvd_clock_voltage_dependency_table *table =
+		&rdev->pm.dpm.dyn_state.uvd_clock_voltage_dependency_table;
+
+	if (table->count) {
+		for (i = 0; i < table->count; i++)
+			table->entries[i].v =
+				kv_convert_8bit_index_to_voltage(rdev,
+								 table->entries[i].v);
+	}
+
+}
+
+static void kv_construct_boot_state(struct radeon_device *rdev)
+{
+	struct kv_power_info *pi = kv_get_pi(rdev);
+
+	pi->boot_pl.sclk = pi->sys_info.bootup_sclk;
+	pi->boot_pl.vddc_index = pi->sys_info.bootup_nb_voltage_index;
+	pi->boot_pl.ds_divider_index = 0;
+	pi->boot_pl.ss_divider_index = 0;
+	pi->boot_pl.allow_gnb_slow = 1;
+	pi->boot_pl.force_nbp_state = 0;
+	pi->boot_pl.display_wm = 0;
+	pi->boot_pl.vce_wm = 0;
+}
+
+static int kv_force_dpm_highest(struct radeon_device *rdev)
+{
+	int ret;
+	u32 enable_mask, i;
+
+	ret = kv_dpm_get_enable_mask(rdev, &enable_mask);
+	if (ret)
+		return ret;
+
+	for (i = SMU7_MAX_LEVELS_GRAPHICS - 1; i > 0; i--) {
+		if (enable_mask & (1 << i))
+			break;
+	}
+
+	if (rdev->family == CHIP_KABINI)
+		return kv_send_msg_to_smc_with_parameter(rdev, PPSMC_MSG_DPM_ForceState, i);
+	else
+		return kv_set_enabled_level(rdev, i);
+}
+
+static int kv_force_dpm_lowest(struct radeon_device *rdev)
+{
+	int ret;
+	u32 enable_mask, i;
+
+	ret = kv_dpm_get_enable_mask(rdev, &enable_mask);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < SMU7_MAX_LEVELS_GRAPHICS; i++) {
+		if (enable_mask & (1 << i))
+			break;
+	}
+
+	if (rdev->family == CHIP_KABINI)
+		return kv_send_msg_to_smc_with_parameter(rdev, PPSMC_MSG_DPM_ForceState, i);
+	else
+		return kv_set_enabled_level(rdev, i);
+}
+
+static u8 kv_get_sleep_divider_id_from_clock(struct radeon_device *rdev,
+					     u32 sclk, u32 min_sclk_in_sr)
+{
+	struct kv_power_info *pi = kv_get_pi(rdev);
+	u32 i;
+	u32 temp;
+	u32 min = (min_sclk_in_sr > KV_MINIMUM_ENGINE_CLOCK) ?
+		min_sclk_in_sr : KV_MINIMUM_ENGINE_CLOCK;
+
+	if (sclk < min)
+		return 0;
+
+	if (!pi->caps_sclk_ds)
+		return 0;
+
+	for (i = KV_MAX_DEEPSLEEP_DIVIDER_ID; i > 0; i--) {
+		temp = sclk / sumo_get_sleep_divider_from_id(i);
+		if (temp >= min)
+			break;
+	}
+
+	return (u8)i;
+}
+
+static int kv_get_high_voltage_limit(struct radeon_device *rdev, int *limit)
+{
+	struct kv_power_info *pi = kv_get_pi(rdev);
+	struct radeon_clock_voltage_dependency_table *table =
+		&rdev->pm.dpm.dyn_state.vddc_dependency_on_sclk;
+	int i;
+
+	if (table && table->count) {
+		for (i = table->count - 1; i >= 0; i--) {
+			if (pi->high_voltage_t &&
+			    (kv_convert_8bit_index_to_voltage(rdev, table->entries[i].v) <=
+			     pi->high_voltage_t)) {
+				*limit = i;
+				return 0;
+			}
+		}
+	} else {
+		struct sumo_sclk_voltage_mapping_table *table =
+			&pi->sys_info.sclk_voltage_mapping_table;
+
+		for (i = table->num_max_dpm_entries - 1; i >= 0; i--) {
+			if (pi->high_voltage_t &&
+			    (kv_convert_2bit_index_to_voltage(rdev, table->entries[i].vid_2bit) <=
+			     pi->high_voltage_t)) {
+				*limit = i;
+				return 0;
+			}
+		}
+	}
+
+	*limit = 0;
+	return 0;
+}
+
+static void kv_apply_state_adjust_rules(struct radeon_device *rdev,
+					struct radeon_ps *new_rps,
+					struct radeon_ps *old_rps)
+{
+	struct kv_ps *ps = kv_get_ps(new_rps);
+	struct kv_power_info *pi = kv_get_pi(rdev);
+	u32 min_sclk = 10000; /* ??? */
+	u32 sclk, mclk = 0;
+	int i, limit;
+	bool force_high;
+	struct radeon_clock_voltage_dependency_table *table =
+		&rdev->pm.dpm.dyn_state.vddc_dependency_on_sclk;
+	u32 stable_p_state_sclk = 0;
+	struct radeon_clock_and_voltage_limits *max_limits =
+		&rdev->pm.dpm.dyn_state.max_clock_voltage_on_ac;
+
+	mclk = max_limits->mclk;
+	sclk = min_sclk;
+
+	if (pi->caps_stable_p_state) {
+		stable_p_state_sclk = (max_limits->sclk * 75) / 100;
+
+		for (i = table->count - 1; i >= 0; i++) {
+			if (stable_p_state_sclk >= table->entries[i].clk) {
+				stable_p_state_sclk = table->entries[i].clk;
+				break;
+			}
+		}
+
+		if (i > 0)
+			stable_p_state_sclk = table->entries[0].clk;
+
+		sclk = stable_p_state_sclk;
+	}
+
+	ps->need_dfs_bypass = true;
+
+	for (i = 0; i < ps->num_levels; i++) {
+		if (ps->levels[i].sclk < sclk)
+			ps->levels[i].sclk = sclk;
+	}
+
+	if (table && table->count) {
+		for (i = 0; i < ps->num_levels; i++) {
+			if (pi->high_voltage_t &&
+			    (pi->high_voltage_t <
+			     kv_convert_8bit_index_to_voltage(rdev, ps->levels[i].vddc_index))) {
+				kv_get_high_voltage_limit(rdev, &limit);
+				ps->levels[i].sclk = table->entries[limit].clk;
+			}
+		}
+	} else {
+		struct sumo_sclk_voltage_mapping_table *table =
+			&pi->sys_info.sclk_voltage_mapping_table;
+
+		for (i = 0; i < ps->num_levels; i++) {
+			if (pi->high_voltage_t &&
+			    (pi->high_voltage_t <
+			     kv_convert_8bit_index_to_voltage(rdev, ps->levels[i].vddc_index))) {
+				kv_get_high_voltage_limit(rdev, &limit);
+				ps->levels[i].sclk = table->entries[limit].sclk_frequency;
+			}
+		}
+	}
+
+	if (pi->caps_stable_p_state) {
+		for (i = 0; i < ps->num_levels; i++) {
+			ps->levels[i].sclk = stable_p_state_sclk;
+		}
+	}
+
+	pi->video_start = new_rps->dclk || new_rps->vclk;
+
+	if ((new_rps->class & ATOM_PPLIB_CLASSIFICATION_UI_MASK) ==
+	    ATOM_PPLIB_CLASSIFICATION_UI_BATTERY)
+		pi->battery_state = true;
+	else
+		pi->battery_state = false;
+
+	if (rdev->family == CHIP_KABINI) {
+		ps->dpm0_pg_nb_ps_lo = 0x1;
+		ps->dpm0_pg_nb_ps_hi = 0x0;
+		ps->dpmx_nb_ps_lo = 0x1;
+		ps->dpmx_nb_ps_hi = 0x0;
+	} else {
+		ps->dpm0_pg_nb_ps_lo = 0x3;
+		ps->dpm0_pg_nb_ps_hi = 0x0;
+		ps->dpmx_nb_ps_lo = 0x3;
+		ps->dpmx_nb_ps_hi = 0x0;
+
+		if (pi->sys_info.nb_dpm_enable) {
+			force_high = (mclk >= pi->sys_info.nbp_memory_clock[3]) ||
+				pi->video_start || (rdev->pm.dpm.new_active_crtc_count >= 3) ||
+				pi->disable_nb_ps3_in_battery;
+			ps->dpm0_pg_nb_ps_lo = force_high ? 0x2 : 0x3;
+			ps->dpm0_pg_nb_ps_hi = 0x2;
+			ps->dpmx_nb_ps_lo = force_high ? 0x2 : 0x3;
+			ps->dpmx_nb_ps_hi = 0x2;
+		}
+	}
+}
+
+static void kv_dpm_power_level_enabled_for_throttle(struct radeon_device *rdev,
+						    u32 index, bool enable)
+{
+	struct kv_power_info *pi = kv_get_pi(rdev);
+
+	pi->graphics_level[index].EnabledForThrottle = enable ? 1 : 0;
+}
+
+static int kv_calculate_ds_divider(struct radeon_device *rdev)
+{
+	struct kv_power_info *pi = kv_get_pi(rdev);
+	u32 sclk_in_sr = 10000; /* ??? */
+	u32 i;
+
+	if (pi->lowest_valid > pi->highest_valid)
+		return -EINVAL;
+
+	for (i = pi->lowest_valid; i <= pi->highest_valid; i++) {
+		pi->graphics_level[i].DeepSleepDivId =
+			kv_get_sleep_divider_id_from_clock(rdev,
+							   be32_to_cpu(pi->graphics_level[i].SclkFrequency),
+							   sclk_in_sr);
+	}
+	return 0;
+}
+
+static int kv_calculate_nbps_level_settings(struct radeon_device *rdev)
+{
+	struct kv_power_info *pi = kv_get_pi(rdev);
+	u32 i;
+	bool force_high;
+	struct radeon_clock_and_voltage_limits *max_limits =
+		&rdev->pm.dpm.dyn_state.max_clock_voltage_on_ac;
+	u32 mclk = max_limits->mclk;
+
+	if (pi->lowest_valid > pi->highest_valid)
+		return -EINVAL;
+
+	if (rdev->family == CHIP_KABINI) {
+		for (i = pi->lowest_valid; i <= pi->highest_valid; i++) {
+			pi->graphics_level[i].GnbSlow = 1;
+			pi->graphics_level[i].ForceNbPs1 = 0;
+			pi->graphics_level[i].UpH = 0;
+		}
+
+		if (!pi->sys_info.nb_dpm_enable)
+			return 0;
+
+		force_high = ((mclk >= pi->sys_info.nbp_memory_clock[3]) ||
+			      (rdev->pm.dpm.new_active_crtc_count >= 3) || pi->video_start);
+
+		if (force_high) {
+			for (i = pi->lowest_valid; i <= pi->highest_valid; i++)
+				pi->graphics_level[i].GnbSlow = 0;
+		} else {
+			if (pi->battery_state)
+				pi->graphics_level[0].ForceNbPs1 = 1;
+
+			pi->graphics_level[1].GnbSlow = 0;
+			pi->graphics_level[2].GnbSlow = 0;
+			pi->graphics_level[3].GnbSlow = 0;
+			pi->graphics_level[4].GnbSlow = 0;
+		}
+	} else {
+		for (i = pi->lowest_valid; i <= pi->highest_valid; i++) {
+			pi->graphics_level[i].GnbSlow = 1;
+			pi->graphics_level[i].ForceNbPs1 = 0;
+			pi->graphics_level[i].UpH = 0;
+		}
+
+		if (pi->sys_info.nb_dpm_enable && pi->battery_state) {
+			pi->graphics_level[pi->lowest_valid].UpH = 0x28;
+			pi->graphics_level[pi->lowest_valid].GnbSlow = 0;
+			if (pi->lowest_valid != pi->highest_valid)
+				pi->graphics_level[pi->lowest_valid].ForceNbPs1 = 1;
+		}
+	}
+	return 0;
+}
+
+static int kv_calculate_dpm_settings(struct radeon_device *rdev)
+{
+	struct kv_power_info *pi = kv_get_pi(rdev);
+	u32 i;
+
+	if (pi->lowest_valid > pi->highest_valid)
+		return -EINVAL;
+
+	for (i = pi->lowest_valid; i <= pi->highest_valid; i++)
+		pi->graphics_level[i].DisplayWatermark = (i == pi->highest_valid) ? 1 : 0;
+
+	return 0;
+}
+
+static void kv_init_graphics_levels(struct radeon_device *rdev)
+{
+	struct kv_power_info *pi = kv_get_pi(rdev);
+	u32 i;
+	struct radeon_clock_voltage_dependency_table *table =
+		&rdev->pm.dpm.dyn_state.vddc_dependency_on_sclk;
+
+	if (table && table->count) {
+		u32 vid_2bit;
+
+		pi->graphics_dpm_level_count = 0;
+		for (i = 0; i < table->count; i++) {
+			if (pi->high_voltage_t &&
+			    (pi->high_voltage_t <
+			     kv_convert_8bit_index_to_voltage(rdev, table->entries[i].v)))
+				break;
+
+			kv_set_divider_value(rdev, i, table->entries[i].clk);
+			vid_2bit = sumo_convert_vid7_to_vid2(rdev,
+							     &pi->sys_info.vid_mapping_table,
+							     table->entries[i].v);
+			kv_set_vid(rdev, i, vid_2bit);
+			kv_set_at(rdev, i, pi->at[i]);
+			kv_dpm_power_level_enabled_for_throttle(rdev, i, true);
+			pi->graphics_dpm_level_count++;
+		}
+	} else {
+		struct sumo_sclk_voltage_mapping_table *table =
+			&pi->sys_info.sclk_voltage_mapping_table;
+
+		pi->graphics_dpm_level_count = 0;
+		for (i = 0; i < table->num_max_dpm_entries; i++) {
+			if (pi->high_voltage_t &&
+			    pi->high_voltage_t <
+			    kv_convert_2bit_index_to_voltage(rdev, table->entries[i].vid_2bit))
+				break;
+
+			kv_set_divider_value(rdev, i, table->entries[i].sclk_frequency);
+			kv_set_vid(rdev, i, table->entries[i].vid_2bit);
+			kv_set_at(rdev, i, pi->at[i]);
+			kv_dpm_power_level_enabled_for_throttle(rdev, i, true);
+			pi->graphics_dpm_level_count++;
+		}
+	}
+
+	for (i = 0; i < SMU7_MAX_LEVELS_GRAPHICS; i++)
+		kv_dpm_power_level_enable(rdev, i, false);
+}
+
+static void kv_enable_new_levels(struct radeon_device *rdev)
+{
+	struct kv_power_info *pi = kv_get_pi(rdev);
+	u32 i;
+
+	for (i = 0; i < SMU7_MAX_LEVELS_GRAPHICS; i++) {
+		if (i >= pi->lowest_valid && i <= pi->highest_valid)
+			kv_dpm_power_level_enable(rdev, i, true);
+	}
+}
+
+static int kv_set_enabled_level(struct radeon_device *rdev, u32 level)
+{
+	u32 new_mask = (1 << level);
+
+	return kv_send_msg_to_smc_with_parameter(rdev,
+						 PPSMC_MSG_SCLKDPM_SetEnabledMask,
+						 new_mask);
+}
+
+static int kv_set_enabled_levels(struct radeon_device *rdev)
+{
+	struct kv_power_info *pi = kv_get_pi(rdev);
+	u32 i, new_mask = 0;
+
+	for (i = pi->lowest_valid; i <= pi->highest_valid; i++)
+		new_mask |= (1 << i);
+
+	return kv_send_msg_to_smc_with_parameter(rdev,
+						 PPSMC_MSG_SCLKDPM_SetEnabledMask,
+						 new_mask);
+}
+
+static void kv_program_nbps_index_settings(struct radeon_device *rdev,
+					   struct radeon_ps *new_rps)
+{
+	struct kv_ps *new_ps = kv_get_ps(new_rps);
+	struct kv_power_info *pi = kv_get_pi(rdev);
+	u32 nbdpmconfig1;
+
+	if (rdev->family == CHIP_KABINI)
+		return;
+
+	if (pi->sys_info.nb_dpm_enable) {
+		nbdpmconfig1 = RREG32_SMC(NB_DPM_CONFIG_1);
+		nbdpmconfig1 &= ~(Dpm0PgNbPsLo_MASK | Dpm0PgNbPsHi_MASK |
+				  DpmXNbPsLo_MASK | DpmXNbPsHi_MASK);
+		nbdpmconfig1 |= (Dpm0PgNbPsLo(new_ps->dpm0_pg_nb_ps_lo) |
+				 Dpm0PgNbPsHi(new_ps->dpm0_pg_nb_ps_hi) |
+				 DpmXNbPsLo(new_ps->dpmx_nb_ps_lo) |
+				 DpmXNbPsHi(new_ps->dpmx_nb_ps_hi));
+		WREG32_SMC(NB_DPM_CONFIG_1, nbdpmconfig1);
+	}
+}
+
+static int kv_set_thermal_temperature_range(struct radeon_device *rdev,
+					    int min_temp, int max_temp)
+{
+	int low_temp = 0 * 1000;
+	int high_temp = 255 * 1000;
+	u32 tmp;
+
+	if (low_temp < min_temp)
+		low_temp = min_temp;
+	if (high_temp > max_temp)
+		high_temp = max_temp;
+	if (high_temp < low_temp) {
+		DRM_ERROR("invalid thermal range: %d - %d\n", low_temp, high_temp);
+		return -EINVAL;
+	}
+
+	tmp = RREG32_SMC(CG_THERMAL_INT_CTRL);
+	tmp &= ~(DIG_THERM_INTH_MASK | DIG_THERM_INTL_MASK);
+	tmp |= (DIG_THERM_INTH(49 + (high_temp / 1000)) |
+		DIG_THERM_INTL(49 + (low_temp / 1000)));
+	WREG32_SMC(CG_THERMAL_INT_CTRL, tmp);
+
+	rdev->pm.dpm.thermal.min_temp = low_temp;
+	rdev->pm.dpm.thermal.max_temp = high_temp;
+
+	return 0;
+}
+
+union igp_info {
+	struct _ATOM_INTEGRATED_SYSTEM_INFO info;
+	struct _ATOM_INTEGRATED_SYSTEM_INFO_V2 info_2;
+	struct _ATOM_INTEGRATED_SYSTEM_INFO_V5 info_5;
+	struct _ATOM_INTEGRATED_SYSTEM_INFO_V6 info_6;
+	struct _ATOM_INTEGRATED_SYSTEM_INFO_V1_7 info_7;
+	struct _ATOM_INTEGRATED_SYSTEM_INFO_V1_8 info_8;
+};
+
+static int kv_parse_sys_info_table(struct radeon_device *rdev)
+{
+	struct kv_power_info *pi = kv_get_pi(rdev);
+	struct radeon_mode_info *mode_info = &rdev->mode_info;
+	int index = GetIndexIntoMasterTable(DATA, IntegratedSystemInfo);
+	union igp_info *igp_info;
+	u8 frev, crev;
+	u16 data_offset;
+	int i;
+
+	if (atom_parse_data_header(mode_info->atom_context, index, NULL,
+				   &frev, &crev, &data_offset)) {
+		igp_info = (union igp_info *)(mode_info->atom_context->bios +
+					      data_offset);
+
+		if (crev != 8) {
+			DRM_ERROR("Unsupported IGP table: %d %d\n", frev, crev);
+			return -EINVAL;
+		}
+		pi->sys_info.bootup_sclk = le32_to_cpu(igp_info->info_8.ulBootUpEngineClock);
+		pi->sys_info.bootup_uma_clk = le32_to_cpu(igp_info->info_8.ulBootUpUMAClock);
+		pi->sys_info.bootup_nb_voltage_index =
+			le16_to_cpu(igp_info->info_8.usBootUpNBVoltage);
+		if (igp_info->info_8.ucHtcTmpLmt == 0)
+			pi->sys_info.htc_tmp_lmt = 203;
+		else
+			pi->sys_info.htc_tmp_lmt = igp_info->info_8.ucHtcTmpLmt;
+		if (igp_info->info_8.ucHtcHystLmt == 0)
+			pi->sys_info.htc_hyst_lmt = 5;
+		else
+			pi->sys_info.htc_hyst_lmt = igp_info->info_8.ucHtcHystLmt;
+		if (pi->sys_info.htc_tmp_lmt <= pi->sys_info.htc_hyst_lmt) {
+			DRM_ERROR("The htcTmpLmt should be larger than htcHystLmt.\n");
+		}
+
+		if (le32_to_cpu(igp_info->info_8.ulSystemConfig) & (1 << 3))
+			pi->sys_info.nb_dpm_enable = true;
+		else
+			pi->sys_info.nb_dpm_enable = false;
+
+		for (i = 0; i < KV_NUM_NBPSTATES; i++) {
+			pi->sys_info.nbp_memory_clock[i] =
+				le32_to_cpu(igp_info->info_8.ulNbpStateMemclkFreq[i]);
+			pi->sys_info.nbp_n_clock[i] =
+				le32_to_cpu(igp_info->info_8.ulNbpStateNClkFreq[i]);
+		}
+		if (le32_to_cpu(igp_info->info_8.ulGPUCapInfo) &
+		    SYS_INFO_GPUCAPS__ENABEL_DFS_BYPASS)
+			pi->caps_enable_dfs_bypass = true;
+
+		sumo_construct_sclk_voltage_mapping_table(rdev,
+							  &pi->sys_info.sclk_voltage_mapping_table,
+							  igp_info->info_8.sAvail_SCLK);
+
+		sumo_construct_vid_mapping_table(rdev,
+						 &pi->sys_info.vid_mapping_table,
+						 igp_info->info_8.sAvail_SCLK);
+
+		kv_construct_max_power_limits_table(rdev,
+						    &rdev->pm.dpm.dyn_state.max_clock_voltage_on_ac);
+	}
+	return 0;
+}
+
+union power_info {
+	struct _ATOM_POWERPLAY_INFO info;
+	struct _ATOM_POWERPLAY_INFO_V2 info_2;
+	struct _ATOM_POWERPLAY_INFO_V3 info_3;
+	struct _ATOM_PPLIB_POWERPLAYTABLE pplib;
+	struct _ATOM_PPLIB_POWERPLAYTABLE2 pplib2;
+	struct _ATOM_PPLIB_POWERPLAYTABLE3 pplib3;
+};
+
+union pplib_clock_info {
+	struct _ATOM_PPLIB_R600_CLOCK_INFO r600;
+	struct _ATOM_PPLIB_RS780_CLOCK_INFO rs780;
+	struct _ATOM_PPLIB_EVERGREEN_CLOCK_INFO evergreen;
+	struct _ATOM_PPLIB_SUMO_CLOCK_INFO sumo;
+};
+
+union pplib_power_state {
+	struct _ATOM_PPLIB_STATE v1;
+	struct _ATOM_PPLIB_STATE_V2 v2;
+};
+
+static void kv_patch_boot_state(struct radeon_device *rdev,
+				struct kv_ps *ps)
+{
+	struct kv_power_info *pi = kv_get_pi(rdev);
+
+	ps->num_levels = 1;
+	ps->levels[0] = pi->boot_pl;
+}
+
+static void kv_parse_pplib_non_clock_info(struct radeon_device *rdev,
+					  struct radeon_ps *rps,
+					  struct _ATOM_PPLIB_NONCLOCK_INFO *non_clock_info,
+					  u8 table_rev)
+{
+	struct kv_ps *ps = kv_get_ps(rps);
+
+	rps->caps = le32_to_cpu(non_clock_info->ulCapsAndSettings);
+	rps->class = le16_to_cpu(non_clock_info->usClassification);
+	rps->class2 = le16_to_cpu(non_clock_info->usClassification2);
+
+	if (ATOM_PPLIB_NONCLOCKINFO_VER1 < table_rev) {
+		rps->vclk = le32_to_cpu(non_clock_info->ulVCLK);
+		rps->dclk = le32_to_cpu(non_clock_info->ulDCLK);
+	} else {
+		rps->vclk = 0;
+		rps->dclk = 0;
+	}
+
+	if (rps->class & ATOM_PPLIB_CLASSIFICATION_BOOT) {
+		rdev->pm.dpm.boot_ps = rps;
+		kv_patch_boot_state(rdev, ps);
+	}
+	if (rps->class & ATOM_PPLIB_CLASSIFICATION_UVDSTATE)
+		rdev->pm.dpm.uvd_ps = rps;
+}
+
+static void kv_parse_pplib_clock_info(struct radeon_device *rdev,
+				      struct radeon_ps *rps, int index,
+					union pplib_clock_info *clock_info)
+{
+	struct kv_power_info *pi = kv_get_pi(rdev);
+	struct kv_ps *ps = kv_get_ps(rps);
+	struct kv_pl *pl = &ps->levels[index];
+	u32 sclk;
+
+	sclk = le16_to_cpu(clock_info->sumo.usEngineClockLow);
+	sclk |= clock_info->sumo.ucEngineClockHigh << 16;
+	pl->sclk = sclk;
+	pl->vddc_index = clock_info->sumo.vddcIndex;
+
+	ps->num_levels = index + 1;
+
+	if (pi->caps_sclk_ds) {
+		pl->ds_divider_index = 5;
+		pl->ss_divider_index = 5;
+	}
+}
+
+static int kv_parse_power_table(struct radeon_device *rdev)
+{
+	struct radeon_mode_info *mode_info = &rdev->mode_info;
+	struct _ATOM_PPLIB_NONCLOCK_INFO *non_clock_info;
+	union pplib_power_state *power_state;
+	int i, j, k, non_clock_array_index, clock_array_index;
+	union pplib_clock_info *clock_info;
+	struct _StateArray *state_array;
+	struct _ClockInfoArray *clock_info_array;
+	struct _NonClockInfoArray *non_clock_info_array;
+	union power_info *power_info;
+	int index = GetIndexIntoMasterTable(DATA, PowerPlayInfo);
+        u16 data_offset;
+	u8 frev, crev;
+	u8 *power_state_offset;
+	struct kv_ps *ps;
+
+	if (!atom_parse_data_header(mode_info->atom_context, index, NULL,
+				   &frev, &crev, &data_offset))
+		return -EINVAL;
+	power_info = (union power_info *)(mode_info->atom_context->bios + data_offset);
+
+	state_array = (struct _StateArray *)
+		(mode_info->atom_context->bios + data_offset +
+		 le16_to_cpu(power_info->pplib.usStateArrayOffset));
+	clock_info_array = (struct _ClockInfoArray *)
+		(mode_info->atom_context->bios + data_offset +
+		 le16_to_cpu(power_info->pplib.usClockInfoArrayOffset));
+	non_clock_info_array = (struct _NonClockInfoArray *)
+		(mode_info->atom_context->bios + data_offset +
+		 le16_to_cpu(power_info->pplib.usNonClockInfoArrayOffset));
+
+	rdev->pm.dpm.ps = kzalloc(sizeof(struct radeon_ps) *
+				  state_array->ucNumEntries, GFP_KERNEL);
+	if (!rdev->pm.dpm.ps)
+		return -ENOMEM;
+	power_state_offset = (u8 *)state_array->states;
+	rdev->pm.dpm.platform_caps = le32_to_cpu(power_info->pplib.ulPlatformCaps);
+	rdev->pm.dpm.backbias_response_time = le16_to_cpu(power_info->pplib.usBackbiasTime);
+	rdev->pm.dpm.voltage_response_time = le16_to_cpu(power_info->pplib.usVoltageTime);
+	for (i = 0; i < state_array->ucNumEntries; i++) {
+		u8 *idx;
+		power_state = (union pplib_power_state *)power_state_offset;
+		non_clock_array_index = power_state->v2.nonClockInfoIndex;
+		non_clock_info = (struct _ATOM_PPLIB_NONCLOCK_INFO *)
+			&non_clock_info_array->nonClockInfo[non_clock_array_index];
+		if (!rdev->pm.power_state[i].clock_info)
+			return -EINVAL;
+		ps = kzalloc(sizeof(struct kv_ps), GFP_KERNEL);
+		if (ps == NULL) {
+			kfree(rdev->pm.dpm.ps);
+			return -ENOMEM;
+		}
+		rdev->pm.dpm.ps[i].ps_priv = ps;
+		k = 0;
+		idx = (u8 *)&power_state->v2.clockInfoIndex[0];
+		for (j = 0; j < power_state->v2.ucNumDPMLevels; j++) {
+			clock_array_index = idx[j];
+			if (clock_array_index >= clock_info_array->ucNumEntries)
+				continue;
+			if (k >= SUMO_MAX_HARDWARE_POWERLEVELS)
+				break;
+			clock_info = (union pplib_clock_info *)
+				((u8 *)&clock_info_array->clockInfo[0] +
+				 (clock_array_index * clock_info_array->ucEntrySize));
+			kv_parse_pplib_clock_info(rdev,
+						  &rdev->pm.dpm.ps[i], k,
+						  clock_info);
+			k++;
+		}
+		kv_parse_pplib_non_clock_info(rdev, &rdev->pm.dpm.ps[i],
+					      non_clock_info,
+					      non_clock_info_array->ucEntrySize);
+		power_state_offset += 2 + power_state->v2.ucNumDPMLevels;
+	}
+	rdev->pm.dpm.num_ps = state_array->ucNumEntries;
+	return 0;
+}
+
+int kv_dpm_init(struct radeon_device *rdev)
+{
+	struct kv_power_info *pi;
+	int ret, i;
+
+	pi = kzalloc(sizeof(struct kv_power_info), GFP_KERNEL);
+	if (pi == NULL)
+		return -ENOMEM;
+	rdev->pm.dpm.priv = pi;
+
+	ret = r600_parse_extended_power_table(rdev);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < SUMO_MAX_HARDWARE_POWERLEVELS; i++)
+		pi->at[i] = TRINITY_AT_DFLT;
+
+        pi->sram_end = SMC_RAM_END;
+
+	if (rdev->family == CHIP_KABINI)
+		pi->high_voltage_t = 4001;
+
+	pi->enable_nb_dpm = true;
+
+	pi->caps_power_containment = true;
+	pi->caps_cac = true;
+	pi->enable_didt = false;
+	if (pi->enable_didt) {
+		pi->caps_sq_ramping = true;
+		pi->caps_db_ramping = true;
+		pi->caps_td_ramping = true;
+		pi->caps_tcp_ramping = true;
+	}
+
+	pi->caps_sclk_ds = true;
+	pi->enable_auto_thermal_throttling = true;
+	pi->disable_nb_ps3_in_battery = false;
+	pi->bapm_enable = true;
+	pi->voltage_drop_t = 0;
+	pi->caps_sclk_throttle_low_notification = false;
+	pi->caps_fps = false; /* true? */
+	pi->caps_uvd_pg = true;
+	pi->caps_uvd_dpm = true;
+	pi->caps_vce_pg = false;
+	pi->caps_samu_pg = false;
+	pi->caps_acp_pg = false;
+	pi->caps_stable_p_state = false;
+
+	ret = kv_parse_sys_info_table(rdev);
+	if (ret)
+		return ret;
+
+	kv_patch_voltage_values(rdev);
+	kv_construct_boot_state(rdev);
+
+	ret = kv_parse_power_table(rdev);
+	if (ret)
+		return ret;
+
+	pi->enable_dpm = true;
+
+	return 0;
+}
+
+void kv_dpm_debugfs_print_current_performance_level(struct radeon_device *rdev,
+						    struct seq_file *m)
+{
+	struct kv_power_info *pi = kv_get_pi(rdev);
+	u32 current_index =
+		(RREG32_SMC(TARGET_AND_CURRENT_PROFILE_INDEX) & CURR_SCLK_INDEX_MASK) >>
+		CURR_SCLK_INDEX_SHIFT;
+	u32 sclk, tmp;
+	u16 vddc;
+
+	if (current_index >= SMU__NUM_SCLK_DPM_STATE) {
+		seq_printf(m, "invalid dpm profile %d\n", current_index);
+	} else {
+		sclk = be32_to_cpu(pi->graphics_level[current_index].SclkFrequency);
+		tmp = (RREG32_SMC(SMU_VOLTAGE_STATUS) & SMU_VOLTAGE_CURRENT_LEVEL_MASK) >>
+			SMU_VOLTAGE_CURRENT_LEVEL_SHIFT;
+		vddc = kv_convert_8bit_index_to_voltage(rdev, (u16)tmp);
+		seq_printf(m, "power level %d    sclk: %u vddc: %u\n",
+			   current_index, sclk, vddc);
+	}
+}
+
+void kv_dpm_print_power_state(struct radeon_device *rdev,
+			      struct radeon_ps *rps)
+{
+	int i;
+	struct kv_ps *ps = kv_get_ps(rps);
+
+	r600_dpm_print_class_info(rps->class, rps->class2);
+	r600_dpm_print_cap_info(rps->caps);
+	printk("\tuvd    vclk: %d dclk: %d\n", rps->vclk, rps->dclk);
+	for (i = 0; i < ps->num_levels; i++) {
+		struct kv_pl *pl = &ps->levels[i];
+		printk("\t\tpower level %d    sclk: %u vddc: %u\n",
+		       i, pl->sclk,
+		       kv_convert_8bit_index_to_voltage(rdev, pl->vddc_index));
+	}
+	r600_dpm_print_ps_status(rdev, rps);
+}
+
+void kv_dpm_fini(struct radeon_device *rdev)
+{
+	int i;
+
+	for (i = 0; i < rdev->pm.dpm.num_ps; i++) {
+		kfree(rdev->pm.dpm.ps[i].ps_priv);
+	}
+	kfree(rdev->pm.dpm.ps);
+	kfree(rdev->pm.dpm.priv);
+	r600_free_extended_power_table(rdev);
+}
+
+void kv_dpm_display_configuration_changed(struct radeon_device *rdev)
+{
+
+}
+
+u32 kv_dpm_get_sclk(struct radeon_device *rdev, bool low)
+{
+	struct kv_power_info *pi = kv_get_pi(rdev);
+	struct kv_ps *requested_state = kv_get_ps(&pi->requested_rps);
+
+	if (low)
+		return requested_state->levels[0].sclk;
+	else
+		return requested_state->levels[requested_state->num_levels - 1].sclk;
+}
+
+u32 kv_dpm_get_mclk(struct radeon_device *rdev, bool low)
+{
+	struct kv_power_info *pi = kv_get_pi(rdev);
+
+	return pi->sys_info.bootup_uma_clk;
+}
+
diff --git a/drivers/gpu/drm/radeon/kv_dpm.h b/drivers/gpu/drm/radeon/kv_dpm.h
new file mode 100644
index 000000000000..8cef7525d7a8
--- /dev/null
+++ b/drivers/gpu/drm/radeon/kv_dpm.h
@@ -0,0 +1,200 @@
+/*
+ * Copyright 2013 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+#ifndef __KV_DPM_H__
+#define __KV_DPM_H__
+
+#define SMU__NUM_SCLK_DPM_STATE  8
+#define SMU__NUM_MCLK_DPM_LEVELS 4
+#define SMU__NUM_LCLK_DPM_LEVELS 8
+#define SMU__NUM_PCIE_DPM_LEVELS 0 /* ??? */
+#include "smu7_fusion.h"
+#include "trinity_dpm.h"
+#include "ppsmc.h"
+
+#define KV_NUM_NBPSTATES   4
+
+enum kv_pt_config_reg_type {
+	KV_CONFIGREG_MMR = 0,
+	KV_CONFIGREG_SMC_IND,
+	KV_CONFIGREG_DIDT_IND,
+	KV_CONFIGREG_CACHE,
+	KV_CONFIGREG_MAX
+};
+
+struct kv_pt_config_reg {
+	u32 offset;
+	u32 mask;
+	u32 shift;
+	u32 value;
+	enum kv_pt_config_reg_type type;
+};
+
+struct kv_lcac_config_values {
+	u32 block_id;
+	u32 signal_id;
+	u32 t;
+};
+
+struct kv_lcac_config_reg {
+	u32 cntl;
+	u32 block_mask;
+	u32 block_shift;
+	u32 signal_mask;
+	u32 signal_shift;
+	u32 t_mask;
+	u32 t_shift;
+	u32 enable_mask;
+	u32 enable_shift;
+};
+
+struct kv_pl {
+	u32 sclk;
+	u8 vddc_index;
+	u8 ds_divider_index;
+	u8 ss_divider_index;
+	u8 allow_gnb_slow;
+	u8 force_nbp_state;
+	u8 display_wm;
+	u8 vce_wm;
+};
+
+struct kv_ps {
+	struct kv_pl levels[SUMO_MAX_HARDWARE_POWERLEVELS];
+	u32 num_levels;
+	bool need_dfs_bypass;
+	u8 dpm0_pg_nb_ps_lo;
+	u8 dpm0_pg_nb_ps_hi;
+	u8 dpmx_nb_ps_lo;
+	u8 dpmx_nb_ps_hi;
+};
+
+struct kv_sys_info {
+	u32 bootup_uma_clk;
+	u32 bootup_sclk;
+	u32 dentist_vco_freq;
+	u32 nb_dpm_enable;
+	u32 nbp_memory_clock[KV_NUM_NBPSTATES];
+	u32 nbp_n_clock[KV_NUM_NBPSTATES];
+	u16 bootup_nb_voltage_index;
+	u8 htc_tmp_lmt;
+	u8 htc_hyst_lmt;
+	struct sumo_sclk_voltage_mapping_table sclk_voltage_mapping_table;
+	struct sumo_vid_mapping_table vid_mapping_table;
+	u32 uma_channel_number;
+};
+
+struct kv_power_info {
+	u32 at[SUMO_MAX_HARDWARE_POWERLEVELS];
+	u32 voltage_drop_t;
+	struct kv_sys_info sys_info;
+	struct kv_pl boot_pl;
+	bool enable_nb_ps_policy;
+	bool disable_nb_ps3_in_battery;
+	bool video_start;
+	bool battery_state;
+	u32 lowest_valid;
+	u32 highest_valid;
+	u16 high_voltage_t;
+	bool cac_enabled;
+	bool bapm_enable;
+	/* smc offsets */
+	u32 sram_end;
+	u32 dpm_table_start;
+	u32 soft_regs_start;
+	/* dpm SMU tables */
+	u8 graphics_dpm_level_count;
+	u8 uvd_level_count;
+	u8 vce_level_count;
+	u8 acp_level_count;
+	u8 samu_level_count;
+	u16 fps_high_t;
+	SMU7_Fusion_GraphicsLevel graphics_level[SMU__NUM_SCLK_DPM_STATE];
+	SMU7_Fusion_ACPILevel acpi_level;
+	SMU7_Fusion_UvdLevel uvd_level[SMU7_MAX_LEVELS_UVD];
+	SMU7_Fusion_ExtClkLevel vce_level[SMU7_MAX_LEVELS_VCE];
+	SMU7_Fusion_ExtClkLevel acp_level[SMU7_MAX_LEVELS_ACP];
+	SMU7_Fusion_ExtClkLevel samu_level[SMU7_MAX_LEVELS_SAMU];
+	u8 uvd_boot_level;
+	u8 vce_boot_level;
+	u8 acp_boot_level;
+	u8 samu_boot_level;
+	u8 uvd_interval;
+	u8 vce_interval;
+	u8 acp_interval;
+	u8 samu_interval;
+	u8 graphics_boot_level;
+	u8 graphics_interval;
+	u8 graphics_therm_throttle_enable;
+	u8 graphics_voltage_change_enable;
+	u8 graphics_clk_slow_enable;
+	u8 graphics_clk_slow_divider;
+	u8 fps_low_t;
+	u32 low_sclk_interrupt_t;
+	bool uvd_power_gated;
+	bool vce_power_gated;
+	bool acp_power_gated;
+	bool samu_power_gated;
+	bool nb_dpm_enabled;
+	/* flags */
+	bool enable_didt;
+	bool enable_dpm;
+	bool enable_auto_thermal_throttling;
+	bool enable_nb_dpm;
+	/* caps */
+	bool caps_cac;
+	bool caps_power_containment;
+	bool caps_sq_ramping;
+	bool caps_db_ramping;
+	bool caps_td_ramping;
+	bool caps_tcp_ramping;
+	bool caps_sclk_throttle_low_notification;
+	bool caps_fps;
+	bool caps_uvd_dpm;
+	bool caps_uvd_pg;
+	bool caps_vce_pg;
+	bool caps_samu_pg;
+	bool caps_acp_pg;
+	bool caps_stable_p_state;
+	bool caps_enable_dfs_bypass;
+	bool caps_sclk_ds;
+	struct radeon_ps current_rps;
+	struct kv_ps current_ps;
+	struct radeon_ps requested_rps;
+	struct kv_ps requested_ps;
+};
+
+
+/* kv_smc.c */
+int kv_notify_message_to_smu(struct radeon_device *rdev, u32 id);
+int kv_dpm_get_enable_mask(struct radeon_device *rdev, u32 *enable_mask);
+int kv_send_msg_to_smc_with_parameter(struct radeon_device *rdev,
+				      PPSMC_Msg msg, u32 parameter);
+int kv_read_smc_sram_dword(struct radeon_device *rdev, u32 smc_address,
+			   u32 *value, u32 limit);
+int kv_smc_dpm_enable(struct radeon_device *rdev, bool enable);
+int kv_smc_bapm_enable(struct radeon_device *rdev, bool enable);
+int kv_copy_bytes_to_smc(struct radeon_device *rdev,
+			 u32 smc_start_address,
+			 const u8 *src, u32 byte_count, u32 limit);
+
+#endif
diff --git a/drivers/gpu/drm/radeon/kv_smc.c b/drivers/gpu/drm/radeon/kv_smc.c
new file mode 100644
index 000000000000..0000b59a6d05
--- /dev/null
+++ b/drivers/gpu/drm/radeon/kv_smc.c
@@ -0,0 +1,215 @@
+/*
+ * Copyright 2013 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: Alex Deucher
+ */
+
+#include "drmP.h"
+#include "radeon.h"
+#include "cikd.h"
+#include "kv_dpm.h"
+
+int kv_notify_message_to_smu(struct radeon_device *rdev, u32 id)
+{
+	u32 i;
+	u32 tmp = 0;
+
+	WREG32(SMC_MESSAGE_0, id & SMC_MSG_MASK);
+
+	for (i = 0; i < rdev->usec_timeout; i++) {
+		if ((RREG32(SMC_RESP_0) & SMC_RESP_MASK) != 0)
+			break;
+		udelay(1);
+	}
+	tmp = RREG32(SMC_RESP_0) & SMC_RESP_MASK;
+
+	if (tmp != 1) {
+		if (tmp == 0xFF)
+			return -EINVAL;
+		else if (tmp == 0xFE)
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
+int kv_dpm_get_enable_mask(struct radeon_device *rdev, u32 *enable_mask)
+{
+	int ret;
+
+	ret = kv_notify_message_to_smu(rdev, PPSMC_MSG_SCLKDPM_GetEnabledMask);
+
+	if (ret == 0)
+		*enable_mask = RREG32_SMC(SMC_SYSCON_MSG_ARG_0);
+
+	return ret;
+}
+
+int kv_send_msg_to_smc_with_parameter(struct radeon_device *rdev,
+				      PPSMC_Msg msg, u32 parameter)
+{
+
+	WREG32(SMC_MSG_ARG_0, parameter);
+
+	return kv_notify_message_to_smu(rdev, msg);
+}
+
+static int kv_set_smc_sram_address(struct radeon_device *rdev,
+				   u32 smc_address, u32 limit)
+{
+	if (smc_address & 3)
+		return -EINVAL;
+	if ((smc_address + 3) > limit)
+		return -EINVAL;
+
+	WREG32(SMC_IND_INDEX_0, smc_address);
+	WREG32_P(SMC_IND_ACCESS_CNTL, 0, ~AUTO_INCREMENT_IND_0);
+
+	return 0;
+}
+
+int kv_read_smc_sram_dword(struct radeon_device *rdev, u32 smc_address,
+			   u32 *value, u32 limit)
+{
+	int ret;
+
+	ret = kv_set_smc_sram_address(rdev, smc_address, limit);
+	if (ret)
+		return ret;
+
+	*value = RREG32(SMC_IND_DATA_0);
+	return 0;
+}
+
+int kv_smc_dpm_enable(struct radeon_device *rdev, bool enable)
+{
+	if (enable)
+		return kv_notify_message_to_smu(rdev, PPSMC_MSG_DPM_Enable);
+	else
+		return kv_notify_message_to_smu(rdev, PPSMC_MSG_DPM_Disable);
+}
+
+int kv_smc_bapm_enable(struct radeon_device *rdev, bool enable)
+{
+	if (enable)
+		return kv_notify_message_to_smu(rdev, PPSMC_MSG_EnableBAPM);
+	else
+		return kv_notify_message_to_smu(rdev, PPSMC_MSG_DisableBAPM);
+}
+
+int kv_copy_bytes_to_smc(struct radeon_device *rdev,
+			 u32 smc_start_address,
+			 const u8 *src, u32 byte_count, u32 limit)
+{
+	int ret;
+	u32 data, original_data, addr, extra_shift, t_byte, count, mask;
+
+	if ((smc_start_address + byte_count) > limit)
+		return -EINVAL;
+
+	addr = smc_start_address;
+	t_byte = addr & 3;
+
+	/* RMW for the initial bytes */
+	if  (t_byte != 0) {
+		addr -= t_byte;
+
+		ret = kv_set_smc_sram_address(rdev, addr, limit);
+		if (ret)
+			return ret;
+
+		original_data = RREG32(SMC_IND_DATA_0);
+
+		data = 0;
+		mask = 0;
+		count = 4;
+		while (count > 0) {
+			if (t_byte > 0) {
+				mask = (mask << 8) | 0xff;
+				t_byte--;
+			} else if (byte_count > 0) {
+				data = (data << 8) + *src++;
+				byte_count--;
+				mask <<= 8;
+			} else {
+				data <<= 8;
+				mask = (mask << 8) | 0xff;
+			}
+			count--;
+		}
+
+		data |= original_data & mask;
+
+		ret = kv_set_smc_sram_address(rdev, addr, limit);
+		if (ret)
+			return ret;
+
+		WREG32(SMC_IND_DATA_0, data);
+
+		addr += 4;
+	}
+
+	while (byte_count >= 4) {
+		/* SMC address space is BE */
+		data = (src[0] << 24) + (src[1] << 16) + (src[2] << 8) + src[3];
+
+		ret = kv_set_smc_sram_address(rdev, addr, limit);
+		if (ret)
+			return ret;
+
+		WREG32(SMC_IND_DATA_0, data);
+
+		src += 4;
+		byte_count -= 4;
+		addr += 4;
+	}
+
+	/* RMW for the final bytes */
+	if (byte_count > 0) {
+		data = 0;
+
+		ret = kv_set_smc_sram_address(rdev, addr, limit);
+		if (ret)
+			return ret;
+
+		original_data= RREG32(SMC_IND_DATA_0);
+
+		extra_shift = 8 * (4 - byte_count);
+
+		while (byte_count > 0) {
+			/* SMC address space is BE */
+			data = (data << 8) + *src++;
+			byte_count--;
+		}
+
+		data <<= extra_shift;
+
+		data |= (original_data & ~((~0UL) << extra_shift));
+
+		ret = kv_set_smc_sram_address(rdev, addr, limit);
+		if (ret)
+			return ret;
+
+		WREG32(SMC_IND_DATA_0, data);
+	}
+	return 0;
+}
+
diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c
index ccb4f8b54852..93c1f9ef5da9 100644
--- a/drivers/gpu/drm/radeon/ni.c
+++ b/drivers/gpu/drm/radeon/ni.c
@@ -35,7 +35,7 @@
 #include "radeon_ucode.h"
 #include "clearstate_cayman.h"
 
-static u32 tn_rlc_save_restore_register_list[] =
+static const u32 tn_rlc_save_restore_register_list[] =
 {
 	0x98fc,
 	0x98f0,
@@ -160,7 +160,6 @@ static u32 tn_rlc_save_restore_register_list[] =
 	0x9830,
 	0x802c,
 };
-static u32 tn_rlc_save_restore_register_list_size = ARRAY_SIZE(tn_rlc_save_restore_register_list);
 
 extern bool evergreen_is_display_hung(struct radeon_device *rdev);
 extern void evergreen_print_gpu_status_regs(struct radeon_device *rdev);
@@ -175,6 +174,11 @@ extern void evergreen_pcie_gen2_enable(struct radeon_device *rdev);
 extern void evergreen_program_aspm(struct radeon_device *rdev);
 extern void sumo_rlc_fini(struct radeon_device *rdev);
 extern int sumo_rlc_init(struct radeon_device *rdev);
+extern void cayman_dma_vm_set_page(struct radeon_device *rdev,
+				   struct radeon_ib *ib,
+				   uint64_t pe,
+				   uint64_t addr, unsigned count,
+				   uint32_t incr, uint32_t flags);
 
 /* Firmware Names */
 MODULE_FIRMWARE("radeon/BARTS_pfp.bin");
@@ -1374,23 +1378,6 @@ void cayman_ring_ib_execute(struct radeon_device *rdev, struct radeon_ib *ib)
 	radeon_ring_write(ring, 10); /* poll interval */
 }
 
-void cayman_uvd_semaphore_emit(struct radeon_device *rdev,
-			       struct radeon_ring *ring,
-			       struct radeon_semaphore *semaphore,
-			       bool emit_wait)
-{
-	uint64_t addr = semaphore->gpu_addr;
-
-	radeon_ring_write(ring, PACKET0(UVD_SEMA_ADDR_LOW, 0));
-	radeon_ring_write(ring, (addr >> 3) & 0x000FFFFF);
-
-	radeon_ring_write(ring, PACKET0(UVD_SEMA_ADDR_HIGH, 0));
-	radeon_ring_write(ring, (addr >> 23) & 0x000FFFFF);
-
-	radeon_ring_write(ring, PACKET0(UVD_SEMA_CMD, 0));
-	radeon_ring_write(ring, 0x80 | (emit_wait ? 1 : 0));
-}
-
 static void cayman_cp_enable(struct radeon_device *rdev, bool enable)
 {
 	if (enable)
@@ -1564,8 +1551,8 @@ static int cayman_cp_resume(struct radeon_device *rdev)
 
 		/* Set ring buffer size */
 		ring = &rdev->ring[ridx[i]];
-		rb_cntl = drm_order(ring->ring_size / 8);
-		rb_cntl |= drm_order(RADEON_GPU_PAGE_SIZE/8) << 8;
+		rb_cntl = order_base_2(ring->ring_size / 8);
+		rb_cntl |= order_base_2(RADEON_GPU_PAGE_SIZE/8) << 8;
 #ifdef __BIG_ENDIAN
 		rb_cntl |= BUF_SWAP_32BIT;
 #endif
@@ -1613,186 +1600,7 @@ static int cayman_cp_resume(struct radeon_device *rdev)
 	return 0;
 }
 
-/*
- * DMA
- * Starting with R600, the GPU has an asynchronous
- * DMA engine.  The programming model is very similar
- * to the 3D engine (ring buffer, IBs, etc.), but the
- * DMA controller has it's own packet format that is
- * different form the PM4 format used by the 3D engine.
- * It supports copying data, writing embedded data,
- * solid fills, and a number of other things.  It also
- * has support for tiling/detiling of buffers.
- * Cayman and newer support two asynchronous DMA engines.
- */
-/**
- * cayman_dma_ring_ib_execute - Schedule an IB on the DMA engine
- *
- * @rdev: radeon_device pointer
- * @ib: IB object to schedule
- *
- * Schedule an IB in the DMA ring (cayman-SI).
- */
-void cayman_dma_ring_ib_execute(struct radeon_device *rdev,
-				struct radeon_ib *ib)
-{
-	struct radeon_ring *ring = &rdev->ring[ib->ring];
-
-	if (rdev->wb.enabled) {
-		u32 next_rptr = ring->wptr + 4;
-		while ((next_rptr & 7) != 5)
-			next_rptr++;
-		next_rptr += 3;
-		radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_WRITE, 0, 0, 1));
-		radeon_ring_write(ring, ring->next_rptr_gpu_addr & 0xfffffffc);
-		radeon_ring_write(ring, upper_32_bits(ring->next_rptr_gpu_addr) & 0xff);
-		radeon_ring_write(ring, next_rptr);
-	}
-
-	/* The indirect buffer packet must end on an 8 DW boundary in the DMA ring.
-	 * Pad as necessary with NOPs.
-	 */
-	while ((ring->wptr & 7) != 5)
-		radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_NOP, 0, 0, 0));
-	radeon_ring_write(ring, DMA_IB_PACKET(DMA_PACKET_INDIRECT_BUFFER, ib->vm ? ib->vm->id : 0, 0));
-	radeon_ring_write(ring, (ib->gpu_addr & 0xFFFFFFE0));
-	radeon_ring_write(ring, (ib->length_dw << 12) | (upper_32_bits(ib->gpu_addr) & 0xFF));
-
-}
-
-/**
- * cayman_dma_stop - stop the async dma engines
- *
- * @rdev: radeon_device pointer
- *
- * Stop the async dma engines (cayman-SI).
- */
-void cayman_dma_stop(struct radeon_device *rdev)
-{
-	u32 rb_cntl;
-
-	radeon_ttm_set_active_vram_size(rdev, rdev->mc.visible_vram_size);
-
-	/* dma0 */
-	rb_cntl = RREG32(DMA_RB_CNTL + DMA0_REGISTER_OFFSET);
-	rb_cntl &= ~DMA_RB_ENABLE;
-	WREG32(DMA_RB_CNTL + DMA0_REGISTER_OFFSET, rb_cntl);
-
-	/* dma1 */
-	rb_cntl = RREG32(DMA_RB_CNTL + DMA1_REGISTER_OFFSET);
-	rb_cntl &= ~DMA_RB_ENABLE;
-	WREG32(DMA_RB_CNTL + DMA1_REGISTER_OFFSET, rb_cntl);
-
-	rdev->ring[R600_RING_TYPE_DMA_INDEX].ready = false;
-	rdev->ring[CAYMAN_RING_TYPE_DMA1_INDEX].ready = false;
-}
-
-/**
- * cayman_dma_resume - setup and start the async dma engines
- *
- * @rdev: radeon_device pointer
- *
- * Set up the DMA ring buffers and enable them. (cayman-SI).
- * Returns 0 for success, error for failure.
- */
-int cayman_dma_resume(struct radeon_device *rdev)
-{
-	struct radeon_ring *ring;
-	u32 rb_cntl, dma_cntl, ib_cntl;
-	u32 rb_bufsz;
-	u32 reg_offset, wb_offset;
-	int i, r;
-
-	/* Reset dma */
-	WREG32(SRBM_SOFT_RESET, SOFT_RESET_DMA | SOFT_RESET_DMA1);
-	RREG32(SRBM_SOFT_RESET);
-	udelay(50);
-	WREG32(SRBM_SOFT_RESET, 0);
-
-	for (i = 0; i < 2; i++) {
-		if (i == 0) {
-			ring = &rdev->ring[R600_RING_TYPE_DMA_INDEX];
-			reg_offset = DMA0_REGISTER_OFFSET;
-			wb_offset = R600_WB_DMA_RPTR_OFFSET;
-		} else {
-			ring = &rdev->ring[CAYMAN_RING_TYPE_DMA1_INDEX];
-			reg_offset = DMA1_REGISTER_OFFSET;
-			wb_offset = CAYMAN_WB_DMA1_RPTR_OFFSET;
-		}
-
-		WREG32(DMA_SEM_INCOMPLETE_TIMER_CNTL + reg_offset, 0);
-		WREG32(DMA_SEM_WAIT_FAIL_TIMER_CNTL + reg_offset, 0);
-
-		/* Set ring buffer size in dwords */
-		rb_bufsz = drm_order(ring->ring_size / 4);
-		rb_cntl = rb_bufsz << 1;
-#ifdef __BIG_ENDIAN
-		rb_cntl |= DMA_RB_SWAP_ENABLE | DMA_RPTR_WRITEBACK_SWAP_ENABLE;
-#endif
-		WREG32(DMA_RB_CNTL + reg_offset, rb_cntl);
-
-		/* Initialize the ring buffer's read and write pointers */
-		WREG32(DMA_RB_RPTR + reg_offset, 0);
-		WREG32(DMA_RB_WPTR + reg_offset, 0);
-
-		/* set the wb address whether it's enabled or not */
-		WREG32(DMA_RB_RPTR_ADDR_HI + reg_offset,
-		       upper_32_bits(rdev->wb.gpu_addr + wb_offset) & 0xFF);
-		WREG32(DMA_RB_RPTR_ADDR_LO + reg_offset,
-		       ((rdev->wb.gpu_addr + wb_offset) & 0xFFFFFFFC));
-
-		if (rdev->wb.enabled)
-			rb_cntl |= DMA_RPTR_WRITEBACK_ENABLE;
-
-		WREG32(DMA_RB_BASE + reg_offset, ring->gpu_addr >> 8);
-
-		/* enable DMA IBs */
-		ib_cntl = DMA_IB_ENABLE | CMD_VMID_FORCE;
-#ifdef __BIG_ENDIAN
-		ib_cntl |= DMA_IB_SWAP_ENABLE;
-#endif
-		WREG32(DMA_IB_CNTL + reg_offset, ib_cntl);
-
-		dma_cntl = RREG32(DMA_CNTL + reg_offset);
-		dma_cntl &= ~CTXEMPTY_INT_ENABLE;
-		WREG32(DMA_CNTL + reg_offset, dma_cntl);
-
-		ring->wptr = 0;
-		WREG32(DMA_RB_WPTR + reg_offset, ring->wptr << 2);
-
-		ring->rptr = RREG32(DMA_RB_RPTR + reg_offset) >> 2;
-
-		WREG32(DMA_RB_CNTL + reg_offset, rb_cntl | DMA_RB_ENABLE);
-
-		ring->ready = true;
-
-		r = radeon_ring_test(rdev, ring->idx, ring);
-		if (r) {
-			ring->ready = false;
-			return r;
-		}
-	}
-
-	radeon_ttm_set_active_vram_size(rdev, rdev->mc.real_vram_size);
-
-	return 0;
-}
-
-/**
- * cayman_dma_fini - tear down the async dma engines
- *
- * @rdev: radeon_device pointer
- *
- * Stop the async dma engines and free the rings (cayman-SI).
- */
-void cayman_dma_fini(struct radeon_device *rdev)
-{
-	cayman_dma_stop(rdev);
-	radeon_ring_fini(rdev, &rdev->ring[R600_RING_TYPE_DMA_INDEX]);
-	radeon_ring_fini(rdev, &rdev->ring[CAYMAN_RING_TYPE_DMA1_INDEX]);
-}
-
-static u32 cayman_gpu_check_soft_reset(struct radeon_device *rdev)
+u32 cayman_gpu_check_soft_reset(struct radeon_device *rdev)
 {
 	u32 reset_mask = 0;
 	u32 tmp;
@@ -2045,34 +1853,6 @@ bool cayman_gfx_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
 	return radeon_ring_test_lockup(rdev, ring);
 }
 
-/**
- * cayman_dma_is_lockup - Check if the DMA engine is locked up
- *
- * @rdev: radeon_device pointer
- * @ring: radeon_ring structure holding ring information
- *
- * Check if the async DMA engine is locked up.
- * Returns true if the engine appears to be locked up, false if not.
- */
-bool cayman_dma_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
-{
-	u32 reset_mask = cayman_gpu_check_soft_reset(rdev);
-	u32 mask;
-
-	if (ring->idx == R600_RING_TYPE_DMA_INDEX)
-		mask = RADEON_RESET_DMA;
-	else
-		mask = RADEON_RESET_DMA1;
-
-	if (!(reset_mask & mask)) {
-		radeon_ring_lockup_update(ring);
-		return false;
-	}
-	/* force ring activities */
-	radeon_ring_force_activity(rdev, ring);
-	return radeon_ring_test_lockup(rdev, ring);
-}
-
 static int cayman_startup(struct radeon_device *rdev)
 {
 	struct radeon_ring *ring = &rdev->ring[RADEON_RING_TYPE_GFX_INDEX];
@@ -2083,6 +1863,11 @@ static int cayman_startup(struct radeon_device *rdev)
 	/* enable aspm */
 	evergreen_program_aspm(rdev);
 
+	/* scratch needs to be initialized before MC */
+	r = r600_vram_scratch_init(rdev);
+	if (r)
+		return r;
+
 	evergreen_mc_program(rdev);
 
 	if (rdev->flags & RADEON_IS_IGP) {
@@ -2109,26 +1894,16 @@ static int cayman_startup(struct radeon_device *rdev)
 		}
 	}
 
-	r = r600_vram_scratch_init(rdev);
-	if (r)
-		return r;
-
 	r = cayman_pcie_gart_enable(rdev);
 	if (r)
 		return r;
 	cayman_gpu_init(rdev);
 
-	r = evergreen_blit_init(rdev);
-	if (r) {
-		r600_blit_fini(rdev);
-		rdev->asic->copy.copy = NULL;
-		dev_warn(rdev->dev, "failed blitter (%d) falling back to memcpy\n", r);
-	}
-
 	/* allocate rlc buffers */
 	if (rdev->flags & RADEON_IS_IGP) {
 		rdev->rlc.reg_list = tn_rlc_save_restore_register_list;
-		rdev->rlc.reg_list_size = tn_rlc_save_restore_register_list_size;
+		rdev->rlc.reg_list_size =
+			(u32)ARRAY_SIZE(tn_rlc_save_restore_register_list);
 		rdev->rlc.cs_data = cayman_cs_data;
 		r = sumo_rlc_init(rdev);
 		if (r) {
@@ -2148,7 +1923,7 @@ static int cayman_startup(struct radeon_device *rdev)
 		return r;
 	}
 
-	r = rv770_uvd_resume(rdev);
+	r = uvd_v2_2_resume(rdev);
 	if (!r) {
 		r = radeon_fence_driver_start_ring(rdev,
 						   R600_RING_TYPE_UVD_INDEX);
@@ -2199,7 +1974,7 @@ static int cayman_startup(struct radeon_device *rdev)
 
 	r = radeon_ring_init(rdev, ring, ring->ring_size, RADEON_WB_CP_RPTR_OFFSET,
 			     CP_RB0_RPTR, CP_RB0_WPTR,
-			     0, 0xfffff, RADEON_CP_PACKET2);
+			     RADEON_CP_PACKET2);
 	if (r)
 		return r;
 
@@ -2207,7 +1982,7 @@ static int cayman_startup(struct radeon_device *rdev)
 	r = radeon_ring_init(rdev, ring, ring->ring_size, R600_WB_DMA_RPTR_OFFSET,
 			     DMA_RB_RPTR + DMA0_REGISTER_OFFSET,
 			     DMA_RB_WPTR + DMA0_REGISTER_OFFSET,
-			     2, 0x3fffc, DMA_PACKET(DMA_PACKET_NOP, 0, 0, 0));
+			     DMA_PACKET(DMA_PACKET_NOP, 0, 0, 0));
 	if (r)
 		return r;
 
@@ -2215,7 +1990,7 @@ static int cayman_startup(struct radeon_device *rdev)
 	r = radeon_ring_init(rdev, ring, ring->ring_size, CAYMAN_WB_DMA1_RPTR_OFFSET,
 			     DMA_RB_RPTR + DMA1_REGISTER_OFFSET,
 			     DMA_RB_WPTR + DMA1_REGISTER_OFFSET,
-			     2, 0x3fffc, DMA_PACKET(DMA_PACKET_NOP, 0, 0, 0));
+			     DMA_PACKET(DMA_PACKET_NOP, 0, 0, 0));
 	if (r)
 		return r;
 
@@ -2232,12 +2007,11 @@ static int cayman_startup(struct radeon_device *rdev)
 
 	ring = &rdev->ring[R600_RING_TYPE_UVD_INDEX];
 	if (ring->ring_size) {
-		r = radeon_ring_init(rdev, ring, ring->ring_size,
-				     R600_WB_UVD_RPTR_OFFSET,
+		r = radeon_ring_init(rdev, ring, ring->ring_size, 0,
 				     UVD_RBC_RB_RPTR, UVD_RBC_RB_WPTR,
-				     0, 0xfffff, RADEON_CP_PACKET2);
+				     RADEON_CP_PACKET2);
 		if (!r)
-			r = r600_uvd_init(rdev);
+			r = uvd_v1_0_init(rdev);
 		if (r)
 			DRM_ERROR("radeon: failed initializing UVD (%d).\n", r);
 	}
@@ -2254,9 +2028,15 @@ static int cayman_startup(struct radeon_device *rdev)
 		return r;
 	}
 
-	r = r600_audio_init(rdev);
-	if (r)
-		return r;
+	if (ASIC_IS_DCE6(rdev)) {
+		r = dce6_audio_init(rdev);
+		if (r)
+			return r;
+	} else {
+		r = r600_audio_init(rdev);
+		if (r)
+			return r;
+	}
 
 	return 0;
 }
@@ -2287,11 +2067,14 @@ int cayman_resume(struct radeon_device *rdev)
 
 int cayman_suspend(struct radeon_device *rdev)
 {
-	r600_audio_fini(rdev);
+	if (ASIC_IS_DCE6(rdev))
+		dce6_audio_fini(rdev);
+	else
+		r600_audio_fini(rdev);
 	radeon_vm_manager_fini(rdev);
 	cayman_cp_enable(rdev, false);
 	cayman_dma_stop(rdev);
-	r600_uvd_stop(rdev);
+	uvd_v1_0_fini(rdev);
 	radeon_uvd_suspend(rdev);
 	evergreen_irq_suspend(rdev);
 	radeon_wb_disable(rdev);
@@ -2413,7 +2196,6 @@ int cayman_init(struct radeon_device *rdev)
 
 void cayman_fini(struct radeon_device *rdev)
 {
-	r600_blit_fini(rdev);
 	cayman_cp_fini(rdev);
 	cayman_dma_fini(rdev);
 	r600_irq_fini(rdev);
@@ -2423,7 +2205,7 @@ void cayman_fini(struct radeon_device *rdev)
 	radeon_vm_manager_fini(rdev);
 	radeon_ib_pool_fini(rdev);
 	radeon_irq_kms_fini(rdev);
-	r600_uvd_stop(rdev);
+	uvd_v1_0_fini(rdev);
 	radeon_uvd_fini(rdev);
 	cayman_pcie_gart_fini(rdev);
 	r600_vram_scratch_fini(rdev);
@@ -2684,61 +2466,7 @@ void cayman_vm_set_page(struct radeon_device *rdev,
 			}
 		}
 	} else {
-		if ((flags & RADEON_VM_PAGE_SYSTEM) ||
-		    (count == 1)) {
-			while (count) {
-				ndw = count * 2;
-				if (ndw > 0xFFFFE)
-					ndw = 0xFFFFE;
-
-				/* for non-physically contiguous pages (system) */
-				ib->ptr[ib->length_dw++] = DMA_PACKET(DMA_PACKET_WRITE, 0, 0, ndw);
-				ib->ptr[ib->length_dw++] = pe;
-				ib->ptr[ib->length_dw++] = upper_32_bits(pe) & 0xff;
-				for (; ndw > 0; ndw -= 2, --count, pe += 8) {
-					if (flags & RADEON_VM_PAGE_SYSTEM) {
-						value = radeon_vm_map_gart(rdev, addr);
-						value &= 0xFFFFFFFFFFFFF000ULL;
-					} else if (flags & RADEON_VM_PAGE_VALID) {
-						value = addr;
-					} else {
-						value = 0;
-					}
-					addr += incr;
-					value |= r600_flags;
-					ib->ptr[ib->length_dw++] = value;
-					ib->ptr[ib->length_dw++] = upper_32_bits(value);
-				}
-			}
-			while (ib->length_dw & 0x7)
-				ib->ptr[ib->length_dw++] = DMA_PACKET(DMA_PACKET_NOP, 0, 0, 0);
-		} else {
-			while (count) {
-				ndw = count * 2;
-				if (ndw > 0xFFFFE)
-					ndw = 0xFFFFE;
-
-				if (flags & RADEON_VM_PAGE_VALID)
-					value = addr;
-				else
-					value = 0;
-				/* for physically contiguous pages (vram) */
-				ib->ptr[ib->length_dw++] = DMA_PTE_PDE_PACKET(ndw);
-				ib->ptr[ib->length_dw++] = pe; /* dst addr */
-				ib->ptr[ib->length_dw++] = upper_32_bits(pe) & 0xff;
-				ib->ptr[ib->length_dw++] = r600_flags; /* mask */
-				ib->ptr[ib->length_dw++] = 0;
-				ib->ptr[ib->length_dw++] = value; /* value */
-				ib->ptr[ib->length_dw++] = upper_32_bits(value);
-				ib->ptr[ib->length_dw++] = incr; /* increment size */
-				ib->ptr[ib->length_dw++] = 0;
-				pe += ndw * 4;
-				addr += (ndw / 2) * incr;
-				count -= ndw / 2;
-			}
-		}
-		while (ib->length_dw & 0x7)
-			ib->ptr[ib->length_dw++] = DMA_PACKET(DMA_PACKET_NOP, 0, 0, 0);
+		cayman_dma_vm_set_page(rdev, ib, pe, addr, count, incr, flags);
 	}
 }
 
@@ -2772,26 +2500,3 @@ void cayman_vm_flush(struct radeon_device *rdev, int ridx, struct radeon_vm *vm)
 	radeon_ring_write(ring, PACKET3(PACKET3_PFP_SYNC_ME, 0));
 	radeon_ring_write(ring, 0x0);
 }
-
-void cayman_dma_vm_flush(struct radeon_device *rdev, int ridx, struct radeon_vm *vm)
-{
-	struct radeon_ring *ring = &rdev->ring[ridx];
-
-	if (vm == NULL)
-		return;
-
-	radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_SRBM_WRITE, 0, 0, 0));
-	radeon_ring_write(ring, (0xf << 16) | ((VM_CONTEXT0_PAGE_TABLE_BASE_ADDR + (vm->id << 2)) >> 2));
-	radeon_ring_write(ring, vm->pd_gpu_addr >> 12);
-
-	/* flush hdp cache */
-	radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_SRBM_WRITE, 0, 0, 0));
-	radeon_ring_write(ring, (0xf << 16) | (HDP_MEM_COHERENCY_FLUSH_CNTL >> 2));
-	radeon_ring_write(ring, 1);
-
-	/* bits 0-7 are the VM contexts0-7 */
-	radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_SRBM_WRITE, 0, 0, 0));
-	radeon_ring_write(ring, (0xf << 16) | (VM_INVALIDATE_REQUEST >> 2));
-	radeon_ring_write(ring, 1 << vm->id);
-}
-
diff --git a/drivers/gpu/drm/radeon/ni_dma.c b/drivers/gpu/drm/radeon/ni_dma.c
new file mode 100644
index 000000000000..dd6e9688fbef
--- /dev/null
+++ b/drivers/gpu/drm/radeon/ni_dma.c
@@ -0,0 +1,338 @@
+/*
+ * Copyright 2010 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: Alex Deucher
+ */
+#include <drm/drmP.h>
+#include "radeon.h"
+#include "radeon_asic.h"
+#include "nid.h"
+
+u32 cayman_gpu_check_soft_reset(struct radeon_device *rdev);
+
+/*
+ * DMA
+ * Starting with R600, the GPU has an asynchronous
+ * DMA engine.  The programming model is very similar
+ * to the 3D engine (ring buffer, IBs, etc.), but the
+ * DMA controller has it's own packet format that is
+ * different form the PM4 format used by the 3D engine.
+ * It supports copying data, writing embedded data,
+ * solid fills, and a number of other things.  It also
+ * has support for tiling/detiling of buffers.
+ * Cayman and newer support two asynchronous DMA engines.
+ */
+
+/**
+ * cayman_dma_ring_ib_execute - Schedule an IB on the DMA engine
+ *
+ * @rdev: radeon_device pointer
+ * @ib: IB object to schedule
+ *
+ * Schedule an IB in the DMA ring (cayman-SI).
+ */
+void cayman_dma_ring_ib_execute(struct radeon_device *rdev,
+				struct radeon_ib *ib)
+{
+	struct radeon_ring *ring = &rdev->ring[ib->ring];
+
+	if (rdev->wb.enabled) {
+		u32 next_rptr = ring->wptr + 4;
+		while ((next_rptr & 7) != 5)
+			next_rptr++;
+		next_rptr += 3;
+		radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_WRITE, 0, 0, 1));
+		radeon_ring_write(ring, ring->next_rptr_gpu_addr & 0xfffffffc);
+		radeon_ring_write(ring, upper_32_bits(ring->next_rptr_gpu_addr) & 0xff);
+		radeon_ring_write(ring, next_rptr);
+	}
+
+	/* The indirect buffer packet must end on an 8 DW boundary in the DMA ring.
+	 * Pad as necessary with NOPs.
+	 */
+	while ((ring->wptr & 7) != 5)
+		radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_NOP, 0, 0, 0));
+	radeon_ring_write(ring, DMA_IB_PACKET(DMA_PACKET_INDIRECT_BUFFER, ib->vm ? ib->vm->id : 0, 0));
+	radeon_ring_write(ring, (ib->gpu_addr & 0xFFFFFFE0));
+	radeon_ring_write(ring, (ib->length_dw << 12) | (upper_32_bits(ib->gpu_addr) & 0xFF));
+
+}
+
+/**
+ * cayman_dma_stop - stop the async dma engines
+ *
+ * @rdev: radeon_device pointer
+ *
+ * Stop the async dma engines (cayman-SI).
+ */
+void cayman_dma_stop(struct radeon_device *rdev)
+{
+	u32 rb_cntl;
+
+	radeon_ttm_set_active_vram_size(rdev, rdev->mc.visible_vram_size);
+
+	/* dma0 */
+	rb_cntl = RREG32(DMA_RB_CNTL + DMA0_REGISTER_OFFSET);
+	rb_cntl &= ~DMA_RB_ENABLE;
+	WREG32(DMA_RB_CNTL + DMA0_REGISTER_OFFSET, rb_cntl);
+
+	/* dma1 */
+	rb_cntl = RREG32(DMA_RB_CNTL + DMA1_REGISTER_OFFSET);
+	rb_cntl &= ~DMA_RB_ENABLE;
+	WREG32(DMA_RB_CNTL + DMA1_REGISTER_OFFSET, rb_cntl);
+
+	rdev->ring[R600_RING_TYPE_DMA_INDEX].ready = false;
+	rdev->ring[CAYMAN_RING_TYPE_DMA1_INDEX].ready = false;
+}
+
+/**
+ * cayman_dma_resume - setup and start the async dma engines
+ *
+ * @rdev: radeon_device pointer
+ *
+ * Set up the DMA ring buffers and enable them. (cayman-SI).
+ * Returns 0 for success, error for failure.
+ */
+int cayman_dma_resume(struct radeon_device *rdev)
+{
+	struct radeon_ring *ring;
+	u32 rb_cntl, dma_cntl, ib_cntl;
+	u32 rb_bufsz;
+	u32 reg_offset, wb_offset;
+	int i, r;
+
+	/* Reset dma */
+	WREG32(SRBM_SOFT_RESET, SOFT_RESET_DMA | SOFT_RESET_DMA1);
+	RREG32(SRBM_SOFT_RESET);
+	udelay(50);
+	WREG32(SRBM_SOFT_RESET, 0);
+
+	for (i = 0; i < 2; i++) {
+		if (i == 0) {
+			ring = &rdev->ring[R600_RING_TYPE_DMA_INDEX];
+			reg_offset = DMA0_REGISTER_OFFSET;
+			wb_offset = R600_WB_DMA_RPTR_OFFSET;
+		} else {
+			ring = &rdev->ring[CAYMAN_RING_TYPE_DMA1_INDEX];
+			reg_offset = DMA1_REGISTER_OFFSET;
+			wb_offset = CAYMAN_WB_DMA1_RPTR_OFFSET;
+		}
+
+		WREG32(DMA_SEM_INCOMPLETE_TIMER_CNTL + reg_offset, 0);
+		WREG32(DMA_SEM_WAIT_FAIL_TIMER_CNTL + reg_offset, 0);
+
+		/* Set ring buffer size in dwords */
+		rb_bufsz = order_base_2(ring->ring_size / 4);
+		rb_cntl = rb_bufsz << 1;
+#ifdef __BIG_ENDIAN
+		rb_cntl |= DMA_RB_SWAP_ENABLE | DMA_RPTR_WRITEBACK_SWAP_ENABLE;
+#endif
+		WREG32(DMA_RB_CNTL + reg_offset, rb_cntl);
+
+		/* Initialize the ring buffer's read and write pointers */
+		WREG32(DMA_RB_RPTR + reg_offset, 0);
+		WREG32(DMA_RB_WPTR + reg_offset, 0);
+
+		/* set the wb address whether it's enabled or not */
+		WREG32(DMA_RB_RPTR_ADDR_HI + reg_offset,
+		       upper_32_bits(rdev->wb.gpu_addr + wb_offset) & 0xFF);
+		WREG32(DMA_RB_RPTR_ADDR_LO + reg_offset,
+		       ((rdev->wb.gpu_addr + wb_offset) & 0xFFFFFFFC));
+
+		if (rdev->wb.enabled)
+			rb_cntl |= DMA_RPTR_WRITEBACK_ENABLE;
+
+		WREG32(DMA_RB_BASE + reg_offset, ring->gpu_addr >> 8);
+
+		/* enable DMA IBs */
+		ib_cntl = DMA_IB_ENABLE | CMD_VMID_FORCE;
+#ifdef __BIG_ENDIAN
+		ib_cntl |= DMA_IB_SWAP_ENABLE;
+#endif
+		WREG32(DMA_IB_CNTL + reg_offset, ib_cntl);
+
+		dma_cntl = RREG32(DMA_CNTL + reg_offset);
+		dma_cntl &= ~CTXEMPTY_INT_ENABLE;
+		WREG32(DMA_CNTL + reg_offset, dma_cntl);
+
+		ring->wptr = 0;
+		WREG32(DMA_RB_WPTR + reg_offset, ring->wptr << 2);
+
+		ring->rptr = RREG32(DMA_RB_RPTR + reg_offset) >> 2;
+
+		WREG32(DMA_RB_CNTL + reg_offset, rb_cntl | DMA_RB_ENABLE);
+
+		ring->ready = true;
+
+		r = radeon_ring_test(rdev, ring->idx, ring);
+		if (r) {
+			ring->ready = false;
+			return r;
+		}
+	}
+
+	radeon_ttm_set_active_vram_size(rdev, rdev->mc.real_vram_size);
+
+	return 0;
+}
+
+/**
+ * cayman_dma_fini - tear down the async dma engines
+ *
+ * @rdev: radeon_device pointer
+ *
+ * Stop the async dma engines and free the rings (cayman-SI).
+ */
+void cayman_dma_fini(struct radeon_device *rdev)
+{
+	cayman_dma_stop(rdev);
+	radeon_ring_fini(rdev, &rdev->ring[R600_RING_TYPE_DMA_INDEX]);
+	radeon_ring_fini(rdev, &rdev->ring[CAYMAN_RING_TYPE_DMA1_INDEX]);
+}
+
+/**
+ * cayman_dma_is_lockup - Check if the DMA engine is locked up
+ *
+ * @rdev: radeon_device pointer
+ * @ring: radeon_ring structure holding ring information
+ *
+ * Check if the async DMA engine is locked up.
+ * Returns true if the engine appears to be locked up, false if not.
+ */
+bool cayman_dma_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
+{
+	u32 reset_mask = cayman_gpu_check_soft_reset(rdev);
+	u32 mask;
+
+	if (ring->idx == R600_RING_TYPE_DMA_INDEX)
+		mask = RADEON_RESET_DMA;
+	else
+		mask = RADEON_RESET_DMA1;
+
+	if (!(reset_mask & mask)) {
+		radeon_ring_lockup_update(ring);
+		return false;
+	}
+	/* force ring activities */
+	radeon_ring_force_activity(rdev, ring);
+	return radeon_ring_test_lockup(rdev, ring);
+}
+
+/**
+ * cayman_dma_vm_set_page - update the page tables using the DMA
+ *
+ * @rdev: radeon_device pointer
+ * @ib: indirect buffer to fill with commands
+ * @pe: addr of the page entry
+ * @addr: dst addr to write into pe
+ * @count: number of page entries to update
+ * @incr: increase next addr by incr bytes
+ * @flags: access flags
+ * @r600_flags: hw access flags 
+ *
+ * Update the page tables using the DMA (cayman/TN).
+ */
+void cayman_dma_vm_set_page(struct radeon_device *rdev,
+			    struct radeon_ib *ib,
+			    uint64_t pe,
+			    uint64_t addr, unsigned count,
+			    uint32_t incr, uint32_t flags)
+{
+	uint32_t r600_flags = cayman_vm_page_flags(rdev, flags);
+	uint64_t value;
+	unsigned ndw;
+
+	if ((flags & RADEON_VM_PAGE_SYSTEM) || (count == 1)) {
+		while (count) {
+			ndw = count * 2;
+			if (ndw > 0xFFFFE)
+				ndw = 0xFFFFE;
+
+			/* for non-physically contiguous pages (system) */
+			ib->ptr[ib->length_dw++] = DMA_PACKET(DMA_PACKET_WRITE, 0, 0, ndw);
+			ib->ptr[ib->length_dw++] = pe;
+			ib->ptr[ib->length_dw++] = upper_32_bits(pe) & 0xff;
+			for (; ndw > 0; ndw -= 2, --count, pe += 8) {
+				if (flags & RADEON_VM_PAGE_SYSTEM) {
+					value = radeon_vm_map_gart(rdev, addr);
+					value &= 0xFFFFFFFFFFFFF000ULL;
+				} else if (flags & RADEON_VM_PAGE_VALID) {
+					value = addr;
+				} else {
+					value = 0;
+				}
+				addr += incr;
+				value |= r600_flags;
+				ib->ptr[ib->length_dw++] = value;
+				ib->ptr[ib->length_dw++] = upper_32_bits(value);
+			}
+		}
+	} else {
+		while (count) {
+			ndw = count * 2;
+			if (ndw > 0xFFFFE)
+				ndw = 0xFFFFE;
+
+			if (flags & RADEON_VM_PAGE_VALID)
+				value = addr;
+			else
+				value = 0;
+			/* for physically contiguous pages (vram) */
+			ib->ptr[ib->length_dw++] = DMA_PTE_PDE_PACKET(ndw);
+			ib->ptr[ib->length_dw++] = pe; /* dst addr */
+			ib->ptr[ib->length_dw++] = upper_32_bits(pe) & 0xff;
+			ib->ptr[ib->length_dw++] = r600_flags; /* mask */
+			ib->ptr[ib->length_dw++] = 0;
+			ib->ptr[ib->length_dw++] = value; /* value */
+			ib->ptr[ib->length_dw++] = upper_32_bits(value);
+			ib->ptr[ib->length_dw++] = incr; /* increment size */
+			ib->ptr[ib->length_dw++] = 0;
+			pe += ndw * 4;
+			addr += (ndw / 2) * incr;
+			count -= ndw / 2;
+		}
+	}
+	while (ib->length_dw & 0x7)
+		ib->ptr[ib->length_dw++] = DMA_PACKET(DMA_PACKET_NOP, 0, 0, 0);
+}
+
+void cayman_dma_vm_flush(struct radeon_device *rdev, int ridx, struct radeon_vm *vm)
+{
+	struct radeon_ring *ring = &rdev->ring[ridx];
+
+	if (vm == NULL)
+		return;
+
+	radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_SRBM_WRITE, 0, 0, 0));
+	radeon_ring_write(ring, (0xf << 16) | ((VM_CONTEXT0_PAGE_TABLE_BASE_ADDR + (vm->id << 2)) >> 2));
+	radeon_ring_write(ring, vm->pd_gpu_addr >> 12);
+
+	/* flush hdp cache */
+	radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_SRBM_WRITE, 0, 0, 0));
+	radeon_ring_write(ring, (0xf << 16) | (HDP_MEM_COHERENCY_FLUSH_CNTL >> 2));
+	radeon_ring_write(ring, 1);
+
+	/* bits 0-7 are the VM contexts0-7 */
+	radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_SRBM_WRITE, 0, 0, 0));
+	radeon_ring_write(ring, (0xf << 16) | (VM_INVALIDATE_REQUEST >> 2));
+	radeon_ring_write(ring, 1 << vm->id);
+}
+
diff --git a/drivers/gpu/drm/radeon/ni_dpm.c b/drivers/gpu/drm/radeon/ni_dpm.c
index f0f5f748938a..f26339028154 100644
--- a/drivers/gpu/drm/radeon/ni_dpm.c
+++ b/drivers/gpu/drm/radeon/ni_dpm.c
@@ -769,7 +769,8 @@ bool ni_dpm_vblank_too_short(struct radeon_device *rdev)
 {
 	struct rv7xx_power_info *pi = rv770_get_pi(rdev);
 	u32 vblank_time = r600_dpm_get_vblank_time(rdev);
-	u32 switch_limit = pi->mem_gddr5 ? 450 : 300;
+	/* we never hit the non-gddr5 limit so disable it */
+	u32 switch_limit = pi->mem_gddr5 ? 450 : 0;
 
 	if (vblank_time < switch_limit)
 		return true;
@@ -786,6 +787,7 @@ static void ni_apply_state_adjust_rules(struct radeon_device *rdev,
 	bool disable_mclk_switching;
 	u32 mclk, sclk;
 	u16 vddc, vddci;
+	u32 max_sclk_vddc, max_mclk_vddci, max_mclk_vddc;
 	int i;
 
 	if ((rdev->pm.dpm.new_active_crtc_count > 1) ||
@@ -812,6 +814,29 @@ static void ni_apply_state_adjust_rules(struct radeon_device *rdev,
 		}
 	}
 
+	/* limit clocks to max supported clocks based on voltage dependency tables */
+	btc_get_max_clock_from_voltage_dependency_table(&rdev->pm.dpm.dyn_state.vddc_dependency_on_sclk,
+							&max_sclk_vddc);
+	btc_get_max_clock_from_voltage_dependency_table(&rdev->pm.dpm.dyn_state.vddci_dependency_on_mclk,
+							&max_mclk_vddci);
+	btc_get_max_clock_from_voltage_dependency_table(&rdev->pm.dpm.dyn_state.vddc_dependency_on_mclk,
+							&max_mclk_vddc);
+
+	for (i = 0; i < ps->performance_level_count; i++) {
+		if (max_sclk_vddc) {
+			if (ps->performance_levels[i].sclk > max_sclk_vddc)
+				ps->performance_levels[i].sclk = max_sclk_vddc;
+		}
+		if (max_mclk_vddci) {
+			if (ps->performance_levels[i].mclk > max_mclk_vddci)
+				ps->performance_levels[i].mclk = max_mclk_vddci;
+		}
+		if (max_mclk_vddc) {
+			if (ps->performance_levels[i].mclk > max_mclk_vddc)
+				ps->performance_levels[i].mclk = max_mclk_vddc;
+		}
+	}
+
 	/* XXX validate the min clocks required for display */
 
 	if (disable_mclk_switching) {
@@ -3864,12 +3889,6 @@ int ni_dpm_set_power_state(struct radeon_device *rdev)
 		return ret;
 	}
 
-	ret = ni_dpm_force_performance_level(rdev, RADEON_DPM_FORCED_LEVEL_AUTO);
-	if (ret) {
-		DRM_ERROR("ni_dpm_force_performance_level failed\n");
-		return ret;
-	}
-
 	return 0;
 }
 
@@ -4037,6 +4056,7 @@ static int ni_parse_power_table(struct radeon_device *rdev)
 			 (power_state->v1.ucNonClockStateIndex *
 			  power_info->pplib.ucNonClockSize));
 		if (power_info->pplib.ucStateEntrySize - 1) {
+			u8 *idx;
 			ps = kzalloc(sizeof(struct ni_ps), GFP_KERNEL);
 			if (ps == NULL) {
 				kfree(rdev->pm.dpm.ps);
@@ -4046,12 +4066,12 @@ static int ni_parse_power_table(struct radeon_device *rdev)
 			ni_parse_pplib_non_clock_info(rdev, &rdev->pm.dpm.ps[i],
 							 non_clock_info,
 							 power_info->pplib.ucNonClockSize);
+			idx = (u8 *)&power_state->v1.ucClockStateIndices[0];
 			for (j = 0; j < (power_info->pplib.ucStateEntrySize - 1); j++) {
 				clock_info = (union pplib_clock_info *)
 					(mode_info->atom_context->bios + data_offset +
 					 le16_to_cpu(power_info->pplib.usClockInfoArrayOffset) +
-					 (power_state->v1.ucClockStateIndices[j] *
-					  power_info->pplib.ucClockInfoSize));
+					 (idx[j] * power_info->pplib.ucClockInfoSize));
 				ni_parse_pplib_clock_info(rdev,
 							  &rdev->pm.dpm.ps[i], j,
 							  clock_info);
@@ -4270,6 +4290,12 @@ int ni_dpm_init(struct radeon_device *rdev)
 
 	ni_pi->use_power_boost_limit = true;
 
+	/* make sure dc limits are valid */
+	if ((rdev->pm.dpm.dyn_state.max_clock_voltage_on_dc.sclk == 0) ||
+	    (rdev->pm.dpm.dyn_state.max_clock_voltage_on_dc.mclk == 0))
+		rdev->pm.dpm.dyn_state.max_clock_voltage_on_dc =
+			rdev->pm.dpm.dyn_state.max_clock_voltage_on_ac;
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/radeon/ppsmc.h b/drivers/gpu/drm/radeon/ppsmc.h
index b5564a3645d2..5670b8291285 100644
--- a/drivers/gpu/drm/radeon/ppsmc.h
+++ b/drivers/gpu/drm/radeon/ppsmc.h
@@ -99,13 +99,72 @@ typedef uint8_t PPSMC_Result;
 #define PPSMC_MSG_ThrottleOVRDSCLKDS        ((uint8_t)0x96)
 #define PPSMC_MSG_CancelThrottleOVRDSCLKDS  ((uint8_t)0x97)
 
+/* CI/KV/KB */
+#define PPSMC_MSG_UVDDPM_SetEnabledMask       ((uint16_t) 0x12D)
+#define PPSMC_MSG_VCEDPM_SetEnabledMask       ((uint16_t) 0x12E)
+#define PPSMC_MSG_ACPDPM_SetEnabledMask       ((uint16_t) 0x12F)
+#define PPSMC_MSG_SAMUDPM_SetEnabledMask      ((uint16_t) 0x130)
+#define PPSMC_MSG_MCLKDPM_ForceState          ((uint16_t) 0x131)
+#define PPSMC_MSG_MCLKDPM_NoForcedLevel       ((uint16_t) 0x132)
+#define PPSMC_MSG_Voltage_Cntl_Disable        ((uint16_t) 0x135)
+#define PPSMC_MSG_PCIeDPM_Enable              ((uint16_t) 0x136)
+#define PPSMC_MSG_PCIeDPM_Disable             ((uint16_t) 0x13d)
+#define PPSMC_MSG_ACPPowerOFF                 ((uint16_t) 0x137)
+#define PPSMC_MSG_ACPPowerON                  ((uint16_t) 0x138)
+#define PPSMC_MSG_SAMPowerOFF                 ((uint16_t) 0x139)
+#define PPSMC_MSG_SAMPowerON                  ((uint16_t) 0x13a)
+#define PPSMC_MSG_PCIeDPM_Disable             ((uint16_t) 0x13d)
+#define PPSMC_MSG_NBDPM_Enable                ((uint16_t) 0x140)
+#define PPSMC_MSG_NBDPM_Disable               ((uint16_t) 0x141)
+#define PPSMC_MSG_SCLKDPM_SetEnabledMask      ((uint16_t) 0x145)
+#define PPSMC_MSG_MCLKDPM_SetEnabledMask      ((uint16_t) 0x146)
+#define PPSMC_MSG_PCIeDPM_ForceLevel          ((uint16_t) 0x147)
+#define PPSMC_MSG_PCIeDPM_UnForceLevel        ((uint16_t) 0x148)
+#define PPSMC_MSG_EnableVRHotGPIOInterrupt    ((uint16_t) 0x14a)
+#define PPSMC_MSG_DPM_Enable                  ((uint16_t) 0x14e)
+#define PPSMC_MSG_DPM_Disable                 ((uint16_t) 0x14f)
+#define PPSMC_MSG_MCLKDPM_Enable              ((uint16_t) 0x150)
+#define PPSMC_MSG_MCLKDPM_Disable             ((uint16_t) 0x151)
+#define PPSMC_MSG_UVDDPM_Enable               ((uint16_t) 0x154)
+#define PPSMC_MSG_UVDDPM_Disable              ((uint16_t) 0x155)
+#define PPSMC_MSG_SAMUDPM_Enable              ((uint16_t) 0x156)
+#define PPSMC_MSG_SAMUDPM_Disable             ((uint16_t) 0x157)
+#define PPSMC_MSG_ACPDPM_Enable               ((uint16_t) 0x158)
+#define PPSMC_MSG_ACPDPM_Disable              ((uint16_t) 0x159)
+#define PPSMC_MSG_VCEDPM_Enable               ((uint16_t) 0x15a)
+#define PPSMC_MSG_VCEDPM_Disable              ((uint16_t) 0x15b)
+#define PPSMC_MSG_VddC_Request                ((uint16_t) 0x15f)
+#define PPSMC_MSG_SCLKDPM_GetEnabledMask      ((uint16_t) 0x162)
+#define PPSMC_MSG_PCIeDPM_SetEnabledMask      ((uint16_t) 0x167)
+#define PPSMC_MSG_TDCLimitEnable              ((uint16_t) 0x169)
+#define PPSMC_MSG_TDCLimitDisable             ((uint16_t) 0x16a)
+#define PPSMC_MSG_PkgPwrLimitEnable           ((uint16_t) 0x185)
+#define PPSMC_MSG_PkgPwrLimitDisable          ((uint16_t) 0x186)
+#define PPSMC_MSG_PkgPwrSetLimit              ((uint16_t) 0x187)
+#define PPSMC_MSG_OverDriveSetTargetTdp       ((uint16_t) 0x188)
+#define PPSMC_MSG_SCLKDPM_FreezeLevel         ((uint16_t) 0x189)
+#define PPSMC_MSG_SCLKDPM_UnfreezeLevel       ((uint16_t) 0x18A)
+#define PPSMC_MSG_MCLKDPM_FreezeLevel         ((uint16_t) 0x18B)
+#define PPSMC_MSG_MCLKDPM_UnfreezeLevel       ((uint16_t) 0x18C)
+#define PPSMC_MSG_MASTER_DeepSleep_ON         ((uint16_t) 0x18F)
+#define PPSMC_MSG_MASTER_DeepSleep_OFF        ((uint16_t) 0x190)
+#define PPSMC_MSG_Remove_DC_Clamp             ((uint16_t) 0x191)
+
+#define PPSMC_MSG_API_GetSclkFrequency        ((uint16_t) 0x200)
+#define PPSMC_MSG_API_GetMclkFrequency        ((uint16_t) 0x201)
+
 /* TN */
 #define PPSMC_MSG_DPM_Config                ((uint32_t) 0x102)
 #define PPSMC_MSG_DPM_ForceState            ((uint32_t) 0x104)
 #define PPSMC_MSG_PG_SIMD_Config            ((uint32_t) 0x108)
 #define PPSMC_MSG_DPM_N_LevelsDisabled      ((uint32_t) 0x112)
+#define PPSMC_MSG_Voltage_Cntl_Enable       ((uint32_t) 0x109)
+#define PPSMC_MSG_VCEPowerOFF               ((uint32_t) 0x10e)
+#define PPSMC_MSG_VCEPowerON                ((uint32_t) 0x10f)
 #define PPSMC_MSG_DCE_RemoveVoltageAdjustment   ((uint32_t) 0x11d)
 #define PPSMC_MSG_DCE_AllowVoltageAdjustment    ((uint32_t) 0x11e)
+#define PPSMC_MSG_EnableBAPM                ((uint32_t) 0x120)
+#define PPSMC_MSG_DisableBAPM               ((uint32_t) 0x121)
 #define PPSMC_MSG_UVD_DPM_Config            ((uint32_t) 0x124)
 
 
diff --git a/drivers/gpu/drm/radeon/pptable.h b/drivers/gpu/drm/radeon/pptable.h
new file mode 100644
index 000000000000..da43ab328833
--- /dev/null
+++ b/drivers/gpu/drm/radeon/pptable.h
@@ -0,0 +1,682 @@
+/*
+ * Copyright 2013 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+#ifndef _PPTABLE_H
+#define _PPTABLE_H
+
+#pragma pack(push, 1)
+
+typedef struct _ATOM_PPLIB_THERMALCONTROLLER
+
+{
+    UCHAR ucType;           // one of ATOM_PP_THERMALCONTROLLER_*
+    UCHAR ucI2cLine;        // as interpreted by DAL I2C
+    UCHAR ucI2cAddress;
+    UCHAR ucFanParameters;  // Fan Control Parameters.
+    UCHAR ucFanMinRPM;      // Fan Minimum RPM (hundreds) -- for display purposes only.
+    UCHAR ucFanMaxRPM;      // Fan Maximum RPM (hundreds) -- for display purposes only.
+    UCHAR ucReserved;       // ----
+    UCHAR ucFlags;          // to be defined
+} ATOM_PPLIB_THERMALCONTROLLER;
+
+#define ATOM_PP_FANPARAMETERS_TACHOMETER_PULSES_PER_REVOLUTION_MASK 0x0f
+#define ATOM_PP_FANPARAMETERS_NOFAN                                 0x80    // No fan is connected to this controller.
+
+#define ATOM_PP_THERMALCONTROLLER_NONE      0
+#define ATOM_PP_THERMALCONTROLLER_LM63      1  // Not used by PPLib
+#define ATOM_PP_THERMALCONTROLLER_ADM1032   2  // Not used by PPLib
+#define ATOM_PP_THERMALCONTROLLER_ADM1030   3  // Not used by PPLib
+#define ATOM_PP_THERMALCONTROLLER_MUA6649   4  // Not used by PPLib
+#define ATOM_PP_THERMALCONTROLLER_LM64      5
+#define ATOM_PP_THERMALCONTROLLER_F75375    6  // Not used by PPLib
+#define ATOM_PP_THERMALCONTROLLER_RV6xx     7
+#define ATOM_PP_THERMALCONTROLLER_RV770     8
+#define ATOM_PP_THERMALCONTROLLER_ADT7473   9
+#define ATOM_PP_THERMALCONTROLLER_KONG      10
+#define ATOM_PP_THERMALCONTROLLER_EXTERNAL_GPIO     11
+#define ATOM_PP_THERMALCONTROLLER_EVERGREEN 12
+#define ATOM_PP_THERMALCONTROLLER_EMC2103   13  /* 0x0D */ // Only fan control will be implemented, do NOT show this in PPGen.
+#define ATOM_PP_THERMALCONTROLLER_SUMO      14  /* 0x0E */ // Sumo type, used internally
+#define ATOM_PP_THERMALCONTROLLER_NISLANDS  15
+#define ATOM_PP_THERMALCONTROLLER_SISLANDS  16
+#define ATOM_PP_THERMALCONTROLLER_LM96163   17
+#define ATOM_PP_THERMALCONTROLLER_CISLANDS  18
+#define ATOM_PP_THERMALCONTROLLER_KAVERI    19
+
+
+// Thermal controller 'combo type' to use an external controller for Fan control and an internal controller for thermal.
+// We probably should reserve the bit 0x80 for this use.
+// To keep the number of these types low we should also use the same code for all ASICs (i.e. do not distinguish RV6xx and RV7xx Internal here).
+// The driver can pick the correct internal controller based on the ASIC.
+
+#define ATOM_PP_THERMALCONTROLLER_ADT7473_WITH_INTERNAL   0x89    // ADT7473 Fan Control + Internal Thermal Controller
+#define ATOM_PP_THERMALCONTROLLER_EMC2103_WITH_INTERNAL   0x8D    // EMC2103 Fan Control + Internal Thermal Controller
+
+typedef struct _ATOM_PPLIB_STATE
+{
+    UCHAR ucNonClockStateIndex;
+    UCHAR ucClockStateIndices[1]; // variable-sized
+} ATOM_PPLIB_STATE;
+
+
+typedef struct _ATOM_PPLIB_FANTABLE
+{
+    UCHAR   ucFanTableFormat;                // Change this if the table format changes or version changes so that the other fields are not the same.
+    UCHAR   ucTHyst;                         // Temperature hysteresis. Integer.
+    USHORT  usTMin;                          // The temperature, in 0.01 centigrades, below which we just run at a minimal PWM.
+    USHORT  usTMed;                          // The middle temperature where we change slopes.
+    USHORT  usTHigh;                         // The high point above TMed for adjusting the second slope.
+    USHORT  usPWMMin;                        // The minimum PWM value in percent (0.01% increments).
+    USHORT  usPWMMed;                        // The PWM value (in percent) at TMed.
+    USHORT  usPWMHigh;                       // The PWM value at THigh.
+} ATOM_PPLIB_FANTABLE;
+
+typedef struct _ATOM_PPLIB_FANTABLE2
+{
+    ATOM_PPLIB_FANTABLE basicTable;
+    USHORT  usTMax;                          // The max temperature
+} ATOM_PPLIB_FANTABLE2;
+
+typedef struct _ATOM_PPLIB_EXTENDEDHEADER
+{
+    USHORT  usSize;
+    ULONG   ulMaxEngineClock;   // For Overdrive.
+    ULONG   ulMaxMemoryClock;   // For Overdrive.
+    // Add extra system parameters here, always adjust size to include all fields.
+    USHORT  usVCETableOffset; //points to ATOM_PPLIB_VCE_Table
+    USHORT  usUVDTableOffset;   //points to ATOM_PPLIB_UVD_Table
+    USHORT  usSAMUTableOffset;  //points to ATOM_PPLIB_SAMU_Table
+    USHORT  usPPMTableOffset;   //points to ATOM_PPLIB_PPM_Table
+    USHORT  usACPTableOffset;  //points to ATOM_PPLIB_ACP_Table   
+    USHORT  usPowerTuneTableOffset; //points to ATOM_PPLIB_POWERTUNE_Table   
+} ATOM_PPLIB_EXTENDEDHEADER;
+
+//// ATOM_PPLIB_POWERPLAYTABLE::ulPlatformCaps
+#define ATOM_PP_PLATFORM_CAP_BACKBIAS 1
+#define ATOM_PP_PLATFORM_CAP_POWERPLAY 2
+#define ATOM_PP_PLATFORM_CAP_SBIOSPOWERSOURCE 4
+#define ATOM_PP_PLATFORM_CAP_ASPM_L0s 8
+#define ATOM_PP_PLATFORM_CAP_ASPM_L1 16
+#define ATOM_PP_PLATFORM_CAP_HARDWAREDC 32
+#define ATOM_PP_PLATFORM_CAP_GEMINIPRIMARY 64
+#define ATOM_PP_PLATFORM_CAP_STEPVDDC 128
+#define ATOM_PP_PLATFORM_CAP_VOLTAGECONTROL 256
+#define ATOM_PP_PLATFORM_CAP_SIDEPORTCONTROL 512
+#define ATOM_PP_PLATFORM_CAP_TURNOFFPLL_ASPML1 1024
+#define ATOM_PP_PLATFORM_CAP_HTLINKCONTROL 2048
+#define ATOM_PP_PLATFORM_CAP_MVDDCONTROL 4096
+#define ATOM_PP_PLATFORM_CAP_GOTO_BOOT_ON_ALERT 0x2000              // Go to boot state on alerts, e.g. on an AC->DC transition.
+#define ATOM_PP_PLATFORM_CAP_DONT_WAIT_FOR_VBLANK_ON_ALERT 0x4000   // Do NOT wait for VBLANK during an alert (e.g. AC->DC transition).
+#define ATOM_PP_PLATFORM_CAP_VDDCI_CONTROL 0x8000                   // Does the driver control VDDCI independently from VDDC.
+#define ATOM_PP_PLATFORM_CAP_REGULATOR_HOT 0x00010000               // Enable the 'regulator hot' feature.
+#define ATOM_PP_PLATFORM_CAP_BACO          0x00020000               // Does the driver supports BACO state.
+#define ATOM_PP_PLATFORM_CAP_NEW_CAC_VOLTAGE   0x00040000           // Does the driver supports new CAC voltage table.
+#define ATOM_PP_PLATFORM_CAP_REVERT_GPIO5_POLARITY   0x00080000     // Does the driver supports revert GPIO5 polarity.
+#define ATOM_PP_PLATFORM_CAP_OUTPUT_THERMAL2GPIO17   0x00100000     // Does the driver supports thermal2GPIO17.
+#define ATOM_PP_PLATFORM_CAP_VRHOT_GPIO_CONFIGURABLE   0x00200000   // Does the driver supports VR HOT GPIO Configurable.
+#define ATOM_PP_PLATFORM_CAP_TEMP_INVERSION   0x00400000            // Does the driver supports Temp Inversion feature.
+#define ATOM_PP_PLATFORM_CAP_EVV    0x00800000
+
+typedef struct _ATOM_PPLIB_POWERPLAYTABLE
+{
+      ATOM_COMMON_TABLE_HEADER sHeader;
+
+      UCHAR ucDataRevision;
+
+      UCHAR ucNumStates;
+      UCHAR ucStateEntrySize;
+      UCHAR ucClockInfoSize;
+      UCHAR ucNonClockSize;
+
+      // offset from start of this table to array of ucNumStates ATOM_PPLIB_STATE structures
+      USHORT usStateArrayOffset;
+
+      // offset from start of this table to array of ASIC-specific structures,
+      // currently ATOM_PPLIB_CLOCK_INFO.
+      USHORT usClockInfoArrayOffset;
+
+      // offset from start of this table to array of ATOM_PPLIB_NONCLOCK_INFO
+      USHORT usNonClockInfoArrayOffset;
+
+      USHORT usBackbiasTime;    // in microseconds
+      USHORT usVoltageTime;     // in microseconds
+      USHORT usTableSize;       //the size of this structure, or the extended structure
+
+      ULONG ulPlatformCaps;            // See ATOM_PPLIB_CAPS_*
+
+      ATOM_PPLIB_THERMALCONTROLLER    sThermalController;
+
+      USHORT usBootClockInfoOffset;
+      USHORT usBootNonClockInfoOffset;
+
+} ATOM_PPLIB_POWERPLAYTABLE;
+
+typedef struct _ATOM_PPLIB_POWERPLAYTABLE2
+{
+    ATOM_PPLIB_POWERPLAYTABLE basicTable;
+    UCHAR   ucNumCustomThermalPolicy;
+    USHORT  usCustomThermalPolicyArrayOffset;
+}ATOM_PPLIB_POWERPLAYTABLE2, *LPATOM_PPLIB_POWERPLAYTABLE2;
+
+typedef struct _ATOM_PPLIB_POWERPLAYTABLE3
+{
+    ATOM_PPLIB_POWERPLAYTABLE2 basicTable2;
+    USHORT                     usFormatID;                      // To be used ONLY by PPGen.
+    USHORT                     usFanTableOffset;
+    USHORT                     usExtendendedHeaderOffset;
+} ATOM_PPLIB_POWERPLAYTABLE3, *LPATOM_PPLIB_POWERPLAYTABLE3;
+
+typedef struct _ATOM_PPLIB_POWERPLAYTABLE4
+{
+    ATOM_PPLIB_POWERPLAYTABLE3 basicTable3;
+    ULONG                      ulGoldenPPID;                    // PPGen use only     
+    ULONG                      ulGoldenRevision;                // PPGen use only
+    USHORT                     usVddcDependencyOnSCLKOffset;
+    USHORT                     usVddciDependencyOnMCLKOffset;
+    USHORT                     usVddcDependencyOnMCLKOffset;
+    USHORT                     usMaxClockVoltageOnDCOffset;
+    USHORT                     usVddcPhaseShedLimitsTableOffset;    // Points to ATOM_PPLIB_PhaseSheddingLimits_Table
+    USHORT                     usMvddDependencyOnMCLKOffset;  
+} ATOM_PPLIB_POWERPLAYTABLE4, *LPATOM_PPLIB_POWERPLAYTABLE4;
+
+typedef struct _ATOM_PPLIB_POWERPLAYTABLE5
+{
+    ATOM_PPLIB_POWERPLAYTABLE4 basicTable4;
+    ULONG                      ulTDPLimit;
+    ULONG                      ulNearTDPLimit;
+    ULONG                      ulSQRampingThreshold;
+    USHORT                     usCACLeakageTableOffset;         // Points to ATOM_PPLIB_CAC_Leakage_Table
+    ULONG                      ulCACLeakage;                    // The iLeakage for driver calculated CAC leakage table
+    USHORT                     usTDPODLimit;
+    USHORT                     usLoadLineSlope;                 // in milliOhms * 100
+} ATOM_PPLIB_POWERPLAYTABLE5, *LPATOM_PPLIB_POWERPLAYTABLE5;
+
+//// ATOM_PPLIB_NONCLOCK_INFO::usClassification
+#define ATOM_PPLIB_CLASSIFICATION_UI_MASK          0x0007
+#define ATOM_PPLIB_CLASSIFICATION_UI_SHIFT         0
+#define ATOM_PPLIB_CLASSIFICATION_UI_NONE          0
+#define ATOM_PPLIB_CLASSIFICATION_UI_BATTERY       1
+#define ATOM_PPLIB_CLASSIFICATION_UI_BALANCED      3
+#define ATOM_PPLIB_CLASSIFICATION_UI_PERFORMANCE   5
+// 2, 4, 6, 7 are reserved
+
+#define ATOM_PPLIB_CLASSIFICATION_BOOT                   0x0008
+#define ATOM_PPLIB_CLASSIFICATION_THERMAL                0x0010
+#define ATOM_PPLIB_CLASSIFICATION_LIMITEDPOWERSOURCE     0x0020
+#define ATOM_PPLIB_CLASSIFICATION_REST                   0x0040
+#define ATOM_PPLIB_CLASSIFICATION_FORCED                 0x0080
+#define ATOM_PPLIB_CLASSIFICATION_3DPERFORMANCE          0x0100
+#define ATOM_PPLIB_CLASSIFICATION_OVERDRIVETEMPLATE      0x0200
+#define ATOM_PPLIB_CLASSIFICATION_UVDSTATE               0x0400
+#define ATOM_PPLIB_CLASSIFICATION_3DLOW                  0x0800
+#define ATOM_PPLIB_CLASSIFICATION_ACPI                   0x1000
+#define ATOM_PPLIB_CLASSIFICATION_HD2STATE               0x2000
+#define ATOM_PPLIB_CLASSIFICATION_HDSTATE                0x4000
+#define ATOM_PPLIB_CLASSIFICATION_SDSTATE                0x8000
+
+//// ATOM_PPLIB_NONCLOCK_INFO::usClassification2
+#define ATOM_PPLIB_CLASSIFICATION2_LIMITEDPOWERSOURCE_2     0x0001
+#define ATOM_PPLIB_CLASSIFICATION2_ULV                      0x0002
+#define ATOM_PPLIB_CLASSIFICATION2_MVC                      0x0004   //Multi-View Codec (BD-3D)
+
+//// ATOM_PPLIB_NONCLOCK_INFO::ulCapsAndSettings
+#define ATOM_PPLIB_SINGLE_DISPLAY_ONLY           0x00000001
+#define ATOM_PPLIB_SUPPORTS_VIDEO_PLAYBACK         0x00000002
+
+// 0 is 2.5Gb/s, 1 is 5Gb/s
+#define ATOM_PPLIB_PCIE_LINK_SPEED_MASK            0x00000004
+#define ATOM_PPLIB_PCIE_LINK_SPEED_SHIFT           2
+
+// lanes - 1: 1, 2, 4, 8, 12, 16 permitted by PCIE spec
+#define ATOM_PPLIB_PCIE_LINK_WIDTH_MASK            0x000000F8
+#define ATOM_PPLIB_PCIE_LINK_WIDTH_SHIFT           3
+
+// lookup into reduced refresh-rate table
+#define ATOM_PPLIB_LIMITED_REFRESHRATE_VALUE_MASK  0x00000F00
+#define ATOM_PPLIB_LIMITED_REFRESHRATE_VALUE_SHIFT 8
+
+#define ATOM_PPLIB_LIMITED_REFRESHRATE_UNLIMITED    0
+#define ATOM_PPLIB_LIMITED_REFRESHRATE_50HZ         1
+// 2-15 TBD as needed.
+
+#define ATOM_PPLIB_SOFTWARE_DISABLE_LOADBALANCING        0x00001000
+#define ATOM_PPLIB_SOFTWARE_ENABLE_SLEEP_FOR_TIMESTAMPS  0x00002000
+
+#define ATOM_PPLIB_DISALLOW_ON_DC                       0x00004000
+
+#define ATOM_PPLIB_ENABLE_VARIBRIGHT                     0x00008000
+
+//memory related flags
+#define ATOM_PPLIB_SWSTATE_MEMORY_DLL_OFF               0x000010000
+
+//M3 Arb    //2bits, current 3 sets of parameters in total
+#define ATOM_PPLIB_M3ARB_MASK                       0x00060000
+#define ATOM_PPLIB_M3ARB_SHIFT                      17
+
+#define ATOM_PPLIB_ENABLE_DRR                       0x00080000
+
+// remaining 16 bits are reserved
+typedef struct _ATOM_PPLIB_THERMAL_STATE
+{
+    UCHAR   ucMinTemperature;
+    UCHAR   ucMaxTemperature;
+    UCHAR   ucThermalAction;
+}ATOM_PPLIB_THERMAL_STATE, *LPATOM_PPLIB_THERMAL_STATE;
+
+// Contained in an array starting at the offset
+// in ATOM_PPLIB_POWERPLAYTABLE::usNonClockInfoArrayOffset.
+// referenced from ATOM_PPLIB_STATE_INFO::ucNonClockStateIndex
+#define ATOM_PPLIB_NONCLOCKINFO_VER1      12
+#define ATOM_PPLIB_NONCLOCKINFO_VER2      24
+typedef struct _ATOM_PPLIB_NONCLOCK_INFO
+{
+      USHORT usClassification;
+      UCHAR  ucMinTemperature;
+      UCHAR  ucMaxTemperature;
+      ULONG  ulCapsAndSettings;
+      UCHAR  ucRequiredPower;
+      USHORT usClassification2;
+      ULONG  ulVCLK;
+      ULONG  ulDCLK;
+      UCHAR  ucUnused[5];
+} ATOM_PPLIB_NONCLOCK_INFO;
+
+// Contained in an array starting at the offset
+// in ATOM_PPLIB_POWERPLAYTABLE::usClockInfoArrayOffset.
+// referenced from ATOM_PPLIB_STATE::ucClockStateIndices
+typedef struct _ATOM_PPLIB_R600_CLOCK_INFO
+{
+      USHORT usEngineClockLow;
+      UCHAR ucEngineClockHigh;
+
+      USHORT usMemoryClockLow;
+      UCHAR ucMemoryClockHigh;
+
+      USHORT usVDDC;
+      USHORT usUnused1;
+      USHORT usUnused2;
+
+      ULONG ulFlags; // ATOM_PPLIB_R600_FLAGS_*
+
+} ATOM_PPLIB_R600_CLOCK_INFO;
+
+// ulFlags in ATOM_PPLIB_R600_CLOCK_INFO
+#define ATOM_PPLIB_R600_FLAGS_PCIEGEN2          1
+#define ATOM_PPLIB_R600_FLAGS_UVDSAFE           2
+#define ATOM_PPLIB_R600_FLAGS_BACKBIASENABLE    4
+#define ATOM_PPLIB_R600_FLAGS_MEMORY_ODT_OFF    8
+#define ATOM_PPLIB_R600_FLAGS_MEMORY_DLL_OFF   16
+#define ATOM_PPLIB_R600_FLAGS_LOWPOWER         32   // On the RV770 use 'low power' setting (sequencer S0).
+
+typedef struct _ATOM_PPLIB_RS780_CLOCK_INFO
+
+{
+      USHORT usLowEngineClockLow;         // Low Engine clock in MHz (the same way as on the R600).
+      UCHAR  ucLowEngineClockHigh;
+      USHORT usHighEngineClockLow;        // High Engine clock in MHz.
+      UCHAR  ucHighEngineClockHigh;
+      USHORT usMemoryClockLow;            // For now one of the ATOM_PPLIB_RS780_SPMCLK_XXXX constants.
+      UCHAR  ucMemoryClockHigh;           // Currentyl unused.
+      UCHAR  ucPadding;                   // For proper alignment and size.
+      USHORT usVDDC;                      // For the 780, use: None, Low, High, Variable
+      UCHAR  ucMaxHTLinkWidth;            // From SBIOS - {2, 4, 8, 16}
+      UCHAR  ucMinHTLinkWidth;            // From SBIOS - {2, 4, 8, 16}. Effective only if CDLW enabled. Minimum down stream width could 
+      USHORT usHTLinkFreq;                // See definition ATOM_PPLIB_RS780_HTLINKFREQ_xxx or in MHz(>=200).
+      ULONG  ulFlags; 
+} ATOM_PPLIB_RS780_CLOCK_INFO;
+
+#define ATOM_PPLIB_RS780_VOLTAGE_NONE       0 
+#define ATOM_PPLIB_RS780_VOLTAGE_LOW        1 
+#define ATOM_PPLIB_RS780_VOLTAGE_HIGH       2 
+#define ATOM_PPLIB_RS780_VOLTAGE_VARIABLE   3 
+
+#define ATOM_PPLIB_RS780_SPMCLK_NONE        0   // We cannot change the side port memory clock, leave it as it is.
+#define ATOM_PPLIB_RS780_SPMCLK_LOW         1
+#define ATOM_PPLIB_RS780_SPMCLK_HIGH        2
+
+#define ATOM_PPLIB_RS780_HTLINKFREQ_NONE       0 
+#define ATOM_PPLIB_RS780_HTLINKFREQ_LOW        1 
+#define ATOM_PPLIB_RS780_HTLINKFREQ_HIGH       2 
+
+typedef struct _ATOM_PPLIB_EVERGREEN_CLOCK_INFO
+{
+      USHORT usEngineClockLow;
+      UCHAR  ucEngineClockHigh;
+
+      USHORT usMemoryClockLow;
+      UCHAR  ucMemoryClockHigh;
+
+      USHORT usVDDC;
+      USHORT usVDDCI;
+      USHORT usUnused;
+
+      ULONG ulFlags; // ATOM_PPLIB_R600_FLAGS_*
+
+} ATOM_PPLIB_EVERGREEN_CLOCK_INFO;
+
+typedef struct _ATOM_PPLIB_SI_CLOCK_INFO
+{
+      USHORT usEngineClockLow;
+      UCHAR  ucEngineClockHigh;
+
+      USHORT usMemoryClockLow;
+      UCHAR  ucMemoryClockHigh;
+
+      USHORT usVDDC;
+      USHORT usVDDCI;
+      UCHAR  ucPCIEGen;
+      UCHAR  ucUnused1;
+
+      ULONG ulFlags; // ATOM_PPLIB_SI_FLAGS_*, no flag is necessary for now
+
+} ATOM_PPLIB_SI_CLOCK_INFO;
+
+typedef struct _ATOM_PPLIB_CI_CLOCK_INFO
+{
+      USHORT usEngineClockLow;
+      UCHAR  ucEngineClockHigh;
+
+      USHORT usMemoryClockLow;
+      UCHAR  ucMemoryClockHigh;
+      
+      UCHAR  ucPCIEGen;
+      USHORT usPCIELane;
+} ATOM_PPLIB_CI_CLOCK_INFO;
+
+typedef struct _ATOM_PPLIB_SUMO_CLOCK_INFO{
+      USHORT usEngineClockLow;  //clockfrequency & 0xFFFF. The unit is in 10khz
+      UCHAR  ucEngineClockHigh; //clockfrequency >> 16. 
+      UCHAR  vddcIndex;         //2-bit vddc index;
+      USHORT tdpLimit;
+      //please initalize to 0
+      USHORT rsv1;
+      //please initialize to 0s
+      ULONG rsv2[2];
+}ATOM_PPLIB_SUMO_CLOCK_INFO;
+
+typedef struct _ATOM_PPLIB_STATE_V2
+{
+      //number of valid dpm levels in this state; Driver uses it to calculate the whole 
+      //size of the state: sizeof(ATOM_PPLIB_STATE_V2) + (ucNumDPMLevels - 1) * sizeof(UCHAR)
+      UCHAR ucNumDPMLevels;
+      
+      //a index to the array of nonClockInfos
+      UCHAR nonClockInfoIndex;
+      /**
+      * Driver will read the first ucNumDPMLevels in this array
+      */
+      UCHAR clockInfoIndex[1];
+} ATOM_PPLIB_STATE_V2;
+
+typedef struct _StateArray{
+    //how many states we have 
+    UCHAR ucNumEntries;
+    
+    ATOM_PPLIB_STATE_V2 states[1];
+}StateArray;
+
+
+typedef struct _ClockInfoArray{
+    //how many clock levels we have
+    UCHAR ucNumEntries;
+    
+    //sizeof(ATOM_PPLIB_CLOCK_INFO)
+    UCHAR ucEntrySize;
+    
+    UCHAR clockInfo[1];
+}ClockInfoArray;
+
+typedef struct _NonClockInfoArray{
+
+    //how many non-clock levels we have. normally should be same as number of states
+    UCHAR ucNumEntries;
+    //sizeof(ATOM_PPLIB_NONCLOCK_INFO)
+    UCHAR ucEntrySize;
+    
+    ATOM_PPLIB_NONCLOCK_INFO nonClockInfo[1];
+}NonClockInfoArray;
+
+typedef struct _ATOM_PPLIB_Clock_Voltage_Dependency_Record
+{
+    USHORT usClockLow;
+    UCHAR  ucClockHigh;
+    USHORT usVoltage;
+}ATOM_PPLIB_Clock_Voltage_Dependency_Record;
+
+typedef struct _ATOM_PPLIB_Clock_Voltage_Dependency_Table
+{
+    UCHAR ucNumEntries;                                                // Number of entries.
+    ATOM_PPLIB_Clock_Voltage_Dependency_Record entries[1];             // Dynamically allocate entries.
+}ATOM_PPLIB_Clock_Voltage_Dependency_Table;
+
+typedef struct _ATOM_PPLIB_Clock_Voltage_Limit_Record
+{
+    USHORT usSclkLow;
+    UCHAR  ucSclkHigh;
+    USHORT usMclkLow;
+    UCHAR  ucMclkHigh;
+    USHORT usVddc;
+    USHORT usVddci;
+}ATOM_PPLIB_Clock_Voltage_Limit_Record;
+
+typedef struct _ATOM_PPLIB_Clock_Voltage_Limit_Table
+{
+    UCHAR ucNumEntries;                                                // Number of entries.
+    ATOM_PPLIB_Clock_Voltage_Limit_Record entries[1];                  // Dynamically allocate entries.
+}ATOM_PPLIB_Clock_Voltage_Limit_Table;
+
+union _ATOM_PPLIB_CAC_Leakage_Record
+{
+    struct
+    {
+        USHORT usVddc;          // We use this field for the "fake" standardized VDDC for power calculations; For CI and newer, we use this as the real VDDC value. in CI we read it as StdVoltageHiSidd
+        ULONG  ulLeakageValue;  // For CI and newer we use this as the "fake" standar VDDC value. in CI we read it as StdVoltageLoSidd
+
+    };
+    struct
+     {
+        USHORT usVddc1;
+        USHORT usVddc2;
+        USHORT usVddc3;
+     };
+};
+
+typedef union _ATOM_PPLIB_CAC_Leakage_Record ATOM_PPLIB_CAC_Leakage_Record;
+
+typedef struct _ATOM_PPLIB_CAC_Leakage_Table
+{
+    UCHAR ucNumEntries;                                                 // Number of entries.
+    ATOM_PPLIB_CAC_Leakage_Record entries[1];                           // Dynamically allocate entries.
+}ATOM_PPLIB_CAC_Leakage_Table;
+
+typedef struct _ATOM_PPLIB_PhaseSheddingLimits_Record
+{
+    USHORT usVoltage;
+    USHORT usSclkLow;
+    UCHAR  ucSclkHigh;
+    USHORT usMclkLow;
+    UCHAR  ucMclkHigh;
+}ATOM_PPLIB_PhaseSheddingLimits_Record;
+
+typedef struct _ATOM_PPLIB_PhaseSheddingLimits_Table
+{
+    UCHAR ucNumEntries;                                                 // Number of entries.
+    ATOM_PPLIB_PhaseSheddingLimits_Record entries[1];                   // Dynamically allocate entries.
+}ATOM_PPLIB_PhaseSheddingLimits_Table;
+
+typedef struct _VCEClockInfo{
+    USHORT usEVClkLow;
+    UCHAR  ucEVClkHigh;
+    USHORT usECClkLow;
+    UCHAR  ucECClkHigh;
+}VCEClockInfo;
+
+typedef struct _VCEClockInfoArray{
+    UCHAR ucNumEntries;
+    VCEClockInfo entries[1];
+}VCEClockInfoArray;
+
+typedef struct _ATOM_PPLIB_VCE_Clock_Voltage_Limit_Record
+{
+    USHORT usVoltage;
+    UCHAR  ucVCEClockInfoIndex;
+}ATOM_PPLIB_VCE_Clock_Voltage_Limit_Record;
+
+typedef struct _ATOM_PPLIB_VCE_Clock_Voltage_Limit_Table
+{
+    UCHAR numEntries;
+    ATOM_PPLIB_VCE_Clock_Voltage_Limit_Record entries[1];
+}ATOM_PPLIB_VCE_Clock_Voltage_Limit_Table;
+
+typedef struct _ATOM_PPLIB_VCE_State_Record
+{
+    UCHAR  ucVCEClockInfoIndex;
+    UCHAR  ucClockInfoIndex; //highest 2 bits indicates memory p-states, lower 6bits indicates index to ClockInfoArrary
+}ATOM_PPLIB_VCE_State_Record;
+
+typedef struct _ATOM_PPLIB_VCE_State_Table
+{
+    UCHAR numEntries;
+    ATOM_PPLIB_VCE_State_Record entries[1];
+}ATOM_PPLIB_VCE_State_Table;
+
+
+typedef struct _ATOM_PPLIB_VCE_Table
+{
+      UCHAR revid;
+//    VCEClockInfoArray array;
+//    ATOM_PPLIB_VCE_Clock_Voltage_Limit_Table limits;
+//    ATOM_PPLIB_VCE_State_Table states;
+}ATOM_PPLIB_VCE_Table;
+
+
+typedef struct _UVDClockInfo{
+    USHORT usVClkLow;
+    UCHAR  ucVClkHigh;
+    USHORT usDClkLow;
+    UCHAR  ucDClkHigh;
+}UVDClockInfo;
+
+typedef struct _UVDClockInfoArray{
+    UCHAR ucNumEntries;
+    UVDClockInfo entries[1];
+}UVDClockInfoArray;
+
+typedef struct _ATOM_PPLIB_UVD_Clock_Voltage_Limit_Record
+{
+    USHORT usVoltage;
+    UCHAR  ucUVDClockInfoIndex;
+}ATOM_PPLIB_UVD_Clock_Voltage_Limit_Record;
+
+typedef struct _ATOM_PPLIB_UVD_Clock_Voltage_Limit_Table
+{
+    UCHAR numEntries;
+    ATOM_PPLIB_UVD_Clock_Voltage_Limit_Record entries[1];
+}ATOM_PPLIB_UVD_Clock_Voltage_Limit_Table;
+
+typedef struct _ATOM_PPLIB_UVD_Table
+{
+      UCHAR revid;
+//    UVDClockInfoArray array;
+//    ATOM_PPLIB_UVD_Clock_Voltage_Limit_Table limits;
+}ATOM_PPLIB_UVD_Table;
+
+typedef struct _ATOM_PPLIB_SAMClk_Voltage_Limit_Record
+{
+      USHORT usVoltage;
+      USHORT usSAMClockLow;
+      UCHAR  ucSAMClockHigh;
+}ATOM_PPLIB_SAMClk_Voltage_Limit_Record;
+
+typedef struct _ATOM_PPLIB_SAMClk_Voltage_Limit_Table{
+    UCHAR numEntries;
+    ATOM_PPLIB_SAMClk_Voltage_Limit_Record entries[1];
+}ATOM_PPLIB_SAMClk_Voltage_Limit_Table;
+
+typedef struct _ATOM_PPLIB_SAMU_Table
+{
+      UCHAR revid;
+      ATOM_PPLIB_SAMClk_Voltage_Limit_Table limits;
+}ATOM_PPLIB_SAMU_Table;
+
+typedef struct _ATOM_PPLIB_ACPClk_Voltage_Limit_Record
+{
+      USHORT usVoltage;
+      USHORT usACPClockLow;
+      UCHAR  ucACPClockHigh;
+}ATOM_PPLIB_ACPClk_Voltage_Limit_Record;
+
+typedef struct _ATOM_PPLIB_ACPClk_Voltage_Limit_Table{
+    UCHAR numEntries;
+    ATOM_PPLIB_ACPClk_Voltage_Limit_Record entries[1];
+}ATOM_PPLIB_ACPClk_Voltage_Limit_Table;
+
+typedef struct _ATOM_PPLIB_ACP_Table
+{
+      UCHAR revid;
+      ATOM_PPLIB_ACPClk_Voltage_Limit_Table limits;
+}ATOM_PPLIB_ACP_Table;
+
+typedef struct _ATOM_PowerTune_Table{
+    USHORT usTDP;
+    USHORT usConfigurableTDP;
+    USHORT usTDC;
+    USHORT usBatteryPowerLimit;
+    USHORT usSmallPowerLimit;
+    USHORT usLowCACLeakage;
+    USHORT usHighCACLeakage;
+}ATOM_PowerTune_Table;
+
+typedef struct _ATOM_PPLIB_POWERTUNE_Table
+{
+      UCHAR revid;
+      ATOM_PowerTune_Table power_tune_table;
+}ATOM_PPLIB_POWERTUNE_Table;
+
+typedef struct _ATOM_PPLIB_POWERTUNE_Table_V1
+{
+      UCHAR revid;
+      ATOM_PowerTune_Table power_tune_table;
+      USHORT usMaximumPowerDeliveryLimit;
+      USHORT usReserve[7];
+} ATOM_PPLIB_POWERTUNE_Table_V1;
+
+#define ATOM_PPM_A_A    1
+#define ATOM_PPM_A_I    2
+typedef struct _ATOM_PPLIB_PPM_Table
+{
+      UCHAR  ucRevId;
+      UCHAR  ucPpmDesign;          //A+I or A+A
+      USHORT usCpuCoreNumber;
+      ULONG  ulPlatformTDP;
+      ULONG  ulSmallACPlatformTDP;
+      ULONG  ulPlatformTDC;
+      ULONG  ulSmallACPlatformTDC;
+      ULONG  ulApuTDP;
+      ULONG  ulDGpuTDP;  
+      ULONG  ulDGpuUlvPower;
+      ULONG  ulTjmax;
+} ATOM_PPLIB_PPM_Table;
+
+#pragma pack(pop)
+
+#endif
diff --git a/drivers/gpu/drm/radeon/r100.c b/drivers/gpu/drm/radeon/r100.c
index 75349cdaa84b..d71333033b2b 100644
--- a/drivers/gpu/drm/radeon/r100.c
+++ b/drivers/gpu/drm/radeon/r100.c
@@ -1097,12 +1097,12 @@ int r100_cp_init(struct radeon_device *rdev, unsigned ring_size)
 	}
 
 	/* Align ring size */
-	rb_bufsz = drm_order(ring_size / 8);
+	rb_bufsz = order_base_2(ring_size / 8);
 	ring_size = (1 << (rb_bufsz + 1)) * 4;
 	r100_cp_load_microcode(rdev);
 	r = radeon_ring_init(rdev, ring, ring_size, RADEON_WB_CP_RPTR_OFFSET,
 			     RADEON_CP_RB_RPTR, RADEON_CP_RB_WPTR,
-			     0, 0x7fffff, RADEON_CP_PACKET2);
+			     RADEON_CP_PACKET2);
 	if (r) {
 		return r;
 	}
@@ -2853,21 +2853,28 @@ static void r100_pll_errata_after_data(struct radeon_device *rdev)
 
 uint32_t r100_pll_rreg(struct radeon_device *rdev, uint32_t reg)
 {
+	unsigned long flags;
 	uint32_t data;
 
+	spin_lock_irqsave(&rdev->pll_idx_lock, flags);
 	WREG8(RADEON_CLOCK_CNTL_INDEX, reg & 0x3f);
 	r100_pll_errata_after_index(rdev);
 	data = RREG32(RADEON_CLOCK_CNTL_DATA);
 	r100_pll_errata_after_data(rdev);
+	spin_unlock_irqrestore(&rdev->pll_idx_lock, flags);
 	return data;
 }
 
 void r100_pll_wreg(struct radeon_device *rdev, uint32_t reg, uint32_t v)
 {
+	unsigned long flags;
+
+	spin_lock_irqsave(&rdev->pll_idx_lock, flags);
 	WREG8(RADEON_CLOCK_CNTL_INDEX, ((reg & 0x3f) | RADEON_PLL_WR_EN));
 	r100_pll_errata_after_index(rdev);
 	WREG32(RADEON_CLOCK_CNTL_DATA, v);
 	r100_pll_errata_after_data(rdev);
+	spin_unlock_irqrestore(&rdev->pll_idx_lock, flags);
 }
 
 static void r100_set_safe_registers(struct radeon_device *rdev)
@@ -2926,9 +2933,11 @@ static int r100_debugfs_cp_ring_info(struct seq_file *m, void *data)
 	seq_printf(m, "CP_RB_RPTR 0x%08x\n", rdp);
 	seq_printf(m, "%u free dwords in ring\n", ring->ring_free_dw);
 	seq_printf(m, "%u dwords in ring\n", count);
-	for (j = 0; j <= count; j++) {
-		i = (rdp + j) & ring->ptr_mask;
-		seq_printf(m, "r[%04d]=0x%08x\n", i, ring->ring[i]);
+	if (ring->ready) {
+		for (j = 0; j <= count; j++) {
+			i = (rdp + j) & ring->ptr_mask;
+			seq_printf(m, "r[%04d]=0x%08x\n", i, ring->ring[i]);
+		}
 	}
 	return 0;
 }
diff --git a/drivers/gpu/drm/radeon/r300.c b/drivers/gpu/drm/radeon/r300.c
index b9b776f1e582..d8dd269b9159 100644
--- a/drivers/gpu/drm/radeon/r300.c
+++ b/drivers/gpu/drm/radeon/r300.c
@@ -1541,7 +1541,7 @@ int r300_init(struct radeon_device *rdev)
 	rdev->accel_working = true;
 	r = r300_startup(rdev);
 	if (r) {
-		/* Somethings want wront with the accel init stop accel */
+		/* Something went wrong with the accel init, so stop accel */
 		dev_err(rdev->dev, "Disabling GPU acceleration\n");
 		r100_cp_fini(rdev);
 		radeon_wb_fini(rdev);
diff --git a/drivers/gpu/drm/radeon/r420.c b/drivers/gpu/drm/radeon/r420.c
index 4e796ecf9ea4..6edf2b3a52b4 100644
--- a/drivers/gpu/drm/radeon/r420.c
+++ b/drivers/gpu/drm/radeon/r420.c
@@ -160,18 +160,25 @@ void r420_pipes_init(struct radeon_device *rdev)
 
 u32 r420_mc_rreg(struct radeon_device *rdev, u32 reg)
 {
+	unsigned long flags;
 	u32 r;
 
+	spin_lock_irqsave(&rdev->mc_idx_lock, flags);
 	WREG32(R_0001F8_MC_IND_INDEX, S_0001F8_MC_IND_ADDR(reg));
 	r = RREG32(R_0001FC_MC_IND_DATA);
+	spin_unlock_irqrestore(&rdev->mc_idx_lock, flags);
 	return r;
 }
 
 void r420_mc_wreg(struct radeon_device *rdev, u32 reg, u32 v)
 {
+	unsigned long flags;
+
+	spin_lock_irqsave(&rdev->mc_idx_lock, flags);
 	WREG32(R_0001F8_MC_IND_INDEX, S_0001F8_MC_IND_ADDR(reg) |
 		S_0001F8_MC_IND_WR_EN(1));
 	WREG32(R_0001FC_MC_IND_DATA, v);
+	spin_unlock_irqrestore(&rdev->mc_idx_lock, flags);
 }
 
 static void r420_debugfs(struct radeon_device *rdev)
diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c
index e66e72077350..2a1b1876b431 100644
--- a/drivers/gpu/drm/radeon/r600.c
+++ b/drivers/gpu/drm/radeon/r600.c
@@ -119,6 +119,11 @@ u32 r600_get_xclk(struct radeon_device *rdev)
 	return rdev->clock.spll.reference_freq;
 }
 
+int r600_set_uvd_clocks(struct radeon_device *rdev, u32 vclk, u32 dclk)
+{
+	return 0;
+}
+
 /* get temperature in millidegrees */
 int rv6xx_get_temp(struct radeon_device *rdev)
 {
@@ -1045,20 +1050,27 @@ int r600_mc_wait_for_idle(struct radeon_device *rdev)
 
 uint32_t rs780_mc_rreg(struct radeon_device *rdev, uint32_t reg)
 {
+	unsigned long flags;
 	uint32_t r;
 
+	spin_lock_irqsave(&rdev->mc_idx_lock, flags);
 	WREG32(R_0028F8_MC_INDEX, S_0028F8_MC_IND_ADDR(reg));
 	r = RREG32(R_0028FC_MC_DATA);
 	WREG32(R_0028F8_MC_INDEX, ~C_0028F8_MC_IND_ADDR);
+	spin_unlock_irqrestore(&rdev->mc_idx_lock, flags);
 	return r;
 }
 
 void rs780_mc_wreg(struct radeon_device *rdev, uint32_t reg, uint32_t v)
 {
+	unsigned long flags;
+
+	spin_lock_irqsave(&rdev->mc_idx_lock, flags);
 	WREG32(R_0028F8_MC_INDEX, S_0028F8_MC_IND_ADDR(reg) |
 		S_0028F8_MC_IND_WR_EN(1));
 	WREG32(R_0028FC_MC_DATA, v);
 	WREG32(R_0028F8_MC_INDEX, 0x7F);
+	spin_unlock_irqrestore(&rdev->mc_idx_lock, flags);
 }
 
 static void r600_mc_program(struct radeon_device *rdev)
@@ -1374,7 +1386,7 @@ static bool r600_is_display_hung(struct radeon_device *rdev)
 	return true;
 }
 
-static u32 r600_gpu_check_soft_reset(struct radeon_device *rdev)
+u32 r600_gpu_check_soft_reset(struct radeon_device *rdev)
 {
 	u32 reset_mask = 0;
 	u32 tmp;
@@ -1622,28 +1634,6 @@ bool r600_gfx_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
 	return radeon_ring_test_lockup(rdev, ring);
 }
 
-/**
- * r600_dma_is_lockup - Check if the DMA engine is locked up
- *
- * @rdev: radeon_device pointer
- * @ring: radeon_ring structure holding ring information
- *
- * Check if the async DMA engine is locked up.
- * Returns true if the engine appears to be locked up, false if not.
- */
-bool r600_dma_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
-{
-	u32 reset_mask = r600_gpu_check_soft_reset(rdev);
-
-	if (!(reset_mask & RADEON_RESET_DMA)) {
-		radeon_ring_lockup_update(ring);
-		return false;
-	}
-	/* force ring activities */
-	radeon_ring_force_activity(rdev, ring);
-	return radeon_ring_test_lockup(rdev, ring);
-}
-
 u32 r6xx_remap_render_backend(struct radeon_device *rdev,
 			      u32 tiling_pipe_num,
 			      u32 max_rb_num,
@@ -2114,20 +2104,27 @@ static void r600_gpu_init(struct radeon_device *rdev)
  */
 u32 r600_pciep_rreg(struct radeon_device *rdev, u32 reg)
 {
+	unsigned long flags;
 	u32 r;
 
+	spin_lock_irqsave(&rdev->pciep_idx_lock, flags);
 	WREG32(PCIE_PORT_INDEX, ((reg) & 0xff));
 	(void)RREG32(PCIE_PORT_INDEX);
 	r = RREG32(PCIE_PORT_DATA);
+	spin_unlock_irqrestore(&rdev->pciep_idx_lock, flags);
 	return r;
 }
 
 void r600_pciep_wreg(struct radeon_device *rdev, u32 reg, u32 v)
 {
+	unsigned long flags;
+
+	spin_lock_irqsave(&rdev->pciep_idx_lock, flags);
 	WREG32(PCIE_PORT_INDEX, ((reg) & 0xff));
 	(void)RREG32(PCIE_PORT_INDEX);
 	WREG32(PCIE_PORT_DATA, (v));
 	(void)RREG32(PCIE_PORT_DATA);
+	spin_unlock_irqrestore(&rdev->pciep_idx_lock, flags);
 }
 
 /*
@@ -2417,8 +2414,8 @@ int r600_cp_resume(struct radeon_device *rdev)
 	WREG32(GRBM_SOFT_RESET, 0);
 
 	/* Set ring buffer size */
-	rb_bufsz = drm_order(ring->ring_size / 8);
-	tmp = (drm_order(RADEON_GPU_PAGE_SIZE/8) << 8) | rb_bufsz;
+	rb_bufsz = order_base_2(ring->ring_size / 8);
+	tmp = (order_base_2(RADEON_GPU_PAGE_SIZE/8) << 8) | rb_bufsz;
 #ifdef __BIG_ENDIAN
 	tmp |= BUF_SWAP_32BIT;
 #endif
@@ -2471,7 +2468,7 @@ void r600_ring_init(struct radeon_device *rdev, struct radeon_ring *ring, unsign
 	int r;
 
 	/* Align ring size */
-	rb_bufsz = drm_order(ring_size / 8);
+	rb_bufsz = order_base_2(ring_size / 8);
 	ring_size = (1 << (rb_bufsz + 1)) * 4;
 	ring->ring_size = ring_size;
 	ring->align_mask = 16 - 1;
@@ -2494,345 +2491,6 @@ void r600_cp_fini(struct radeon_device *rdev)
 }
 
 /*
- * DMA
- * Starting with R600, the GPU has an asynchronous
- * DMA engine.  The programming model is very similar
- * to the 3D engine (ring buffer, IBs, etc.), but the
- * DMA controller has it's own packet format that is
- * different form the PM4 format used by the 3D engine.
- * It supports copying data, writing embedded data,
- * solid fills, and a number of other things.  It also
- * has support for tiling/detiling of buffers.
- */
-/**
- * r600_dma_stop - stop the async dma engine
- *
- * @rdev: radeon_device pointer
- *
- * Stop the async dma engine (r6xx-evergreen).
- */
-void r600_dma_stop(struct radeon_device *rdev)
-{
-	u32 rb_cntl = RREG32(DMA_RB_CNTL);
-
-	radeon_ttm_set_active_vram_size(rdev, rdev->mc.visible_vram_size);
-
-	rb_cntl &= ~DMA_RB_ENABLE;
-	WREG32(DMA_RB_CNTL, rb_cntl);
-
-	rdev->ring[R600_RING_TYPE_DMA_INDEX].ready = false;
-}
-
-/**
- * r600_dma_resume - setup and start the async dma engine
- *
- * @rdev: radeon_device pointer
- *
- * Set up the DMA ring buffer and enable it. (r6xx-evergreen).
- * Returns 0 for success, error for failure.
- */
-int r600_dma_resume(struct radeon_device *rdev)
-{
-	struct radeon_ring *ring = &rdev->ring[R600_RING_TYPE_DMA_INDEX];
-	u32 rb_cntl, dma_cntl, ib_cntl;
-	u32 rb_bufsz;
-	int r;
-
-	/* Reset dma */
-	if (rdev->family >= CHIP_RV770)
-		WREG32(SRBM_SOFT_RESET, RV770_SOFT_RESET_DMA);
-	else
-		WREG32(SRBM_SOFT_RESET, SOFT_RESET_DMA);
-	RREG32(SRBM_SOFT_RESET);
-	udelay(50);
-	WREG32(SRBM_SOFT_RESET, 0);
-
-	WREG32(DMA_SEM_INCOMPLETE_TIMER_CNTL, 0);
-	WREG32(DMA_SEM_WAIT_FAIL_TIMER_CNTL, 0);
-
-	/* Set ring buffer size in dwords */
-	rb_bufsz = drm_order(ring->ring_size / 4);
-	rb_cntl = rb_bufsz << 1;
-#ifdef __BIG_ENDIAN
-	rb_cntl |= DMA_RB_SWAP_ENABLE | DMA_RPTR_WRITEBACK_SWAP_ENABLE;
-#endif
-	WREG32(DMA_RB_CNTL, rb_cntl);
-
-	/* Initialize the ring buffer's read and write pointers */
-	WREG32(DMA_RB_RPTR, 0);
-	WREG32(DMA_RB_WPTR, 0);
-
-	/* set the wb address whether it's enabled or not */
-	WREG32(DMA_RB_RPTR_ADDR_HI,
-	       upper_32_bits(rdev->wb.gpu_addr + R600_WB_DMA_RPTR_OFFSET) & 0xFF);
-	WREG32(DMA_RB_RPTR_ADDR_LO,
-	       ((rdev->wb.gpu_addr + R600_WB_DMA_RPTR_OFFSET) & 0xFFFFFFFC));
-
-	if (rdev->wb.enabled)
-		rb_cntl |= DMA_RPTR_WRITEBACK_ENABLE;
-
-	WREG32(DMA_RB_BASE, ring->gpu_addr >> 8);
-
-	/* enable DMA IBs */
-	ib_cntl = DMA_IB_ENABLE;
-#ifdef __BIG_ENDIAN
-	ib_cntl |= DMA_IB_SWAP_ENABLE;
-#endif
-	WREG32(DMA_IB_CNTL, ib_cntl);
-
-	dma_cntl = RREG32(DMA_CNTL);
-	dma_cntl &= ~CTXEMPTY_INT_ENABLE;
-	WREG32(DMA_CNTL, dma_cntl);
-
-	if (rdev->family >= CHIP_RV770)
-		WREG32(DMA_MODE, 1);
-
-	ring->wptr = 0;
-	WREG32(DMA_RB_WPTR, ring->wptr << 2);
-
-	ring->rptr = RREG32(DMA_RB_RPTR) >> 2;
-
-	WREG32(DMA_RB_CNTL, rb_cntl | DMA_RB_ENABLE);
-
-	ring->ready = true;
-
-	r = radeon_ring_test(rdev, R600_RING_TYPE_DMA_INDEX, ring);
-	if (r) {
-		ring->ready = false;
-		return r;
-	}
-
-	radeon_ttm_set_active_vram_size(rdev, rdev->mc.real_vram_size);
-
-	return 0;
-}
-
-/**
- * r600_dma_fini - tear down the async dma engine
- *
- * @rdev: radeon_device pointer
- *
- * Stop the async dma engine and free the ring (r6xx-evergreen).
- */
-void r600_dma_fini(struct radeon_device *rdev)
-{
-	r600_dma_stop(rdev);
-	radeon_ring_fini(rdev, &rdev->ring[R600_RING_TYPE_DMA_INDEX]);
-}
-
-/*
- * UVD
- */
-int r600_uvd_rbc_start(struct radeon_device *rdev)
-{
-	struct radeon_ring *ring = &rdev->ring[R600_RING_TYPE_UVD_INDEX];
-	uint64_t rptr_addr;
-	uint32_t rb_bufsz, tmp;
-	int r;
-
-	rptr_addr = rdev->wb.gpu_addr + R600_WB_UVD_RPTR_OFFSET;
-
-	if (upper_32_bits(rptr_addr) != upper_32_bits(ring->gpu_addr)) {
-		DRM_ERROR("UVD ring and rptr not in the same 4GB segment!\n");
-		return -EINVAL;
-	}
-
-	/* force RBC into idle state */
-	WREG32(UVD_RBC_RB_CNTL, 0x11010101);
-
-	/* Set the write pointer delay */
-	WREG32(UVD_RBC_RB_WPTR_CNTL, 0);
-
-	/* set the wb address */
-	WREG32(UVD_RBC_RB_RPTR_ADDR, rptr_addr >> 2);
-
-	/* programm the 4GB memory segment for rptr and ring buffer */
-	WREG32(UVD_LMI_EXT40_ADDR, upper_32_bits(rptr_addr) |
-				   (0x7 << 16) | (0x1 << 31));
-
-	/* Initialize the ring buffer's read and write pointers */
-	WREG32(UVD_RBC_RB_RPTR, 0x0);
-
-	ring->wptr = ring->rptr = RREG32(UVD_RBC_RB_RPTR);
-	WREG32(UVD_RBC_RB_WPTR, ring->wptr);
-
-	/* set the ring address */
-	WREG32(UVD_RBC_RB_BASE, ring->gpu_addr);
-
-	/* Set ring buffer size */
-	rb_bufsz = drm_order(ring->ring_size);
-	rb_bufsz = (0x1 << 8) | rb_bufsz;
-	WREG32(UVD_RBC_RB_CNTL, rb_bufsz);
-
-	ring->ready = true;
-	r = radeon_ring_test(rdev, R600_RING_TYPE_UVD_INDEX, ring);
-	if (r) {
-		ring->ready = false;
-		return r;
-	}
-
-	r = radeon_ring_lock(rdev, ring, 10);
-	if (r) {
-		DRM_ERROR("radeon: ring failed to lock UVD ring (%d).\n", r);
-		return r;
-	}
-
-	tmp = PACKET0(UVD_SEMA_WAIT_FAULT_TIMEOUT_CNTL, 0);
-	radeon_ring_write(ring, tmp);
-	radeon_ring_write(ring, 0xFFFFF);
-
-	tmp = PACKET0(UVD_SEMA_WAIT_INCOMPLETE_TIMEOUT_CNTL, 0);
-	radeon_ring_write(ring, tmp);
-	radeon_ring_write(ring, 0xFFFFF);
-
-	tmp = PACKET0(UVD_SEMA_SIGNAL_INCOMPLETE_TIMEOUT_CNTL, 0);
-	radeon_ring_write(ring, tmp);
-	radeon_ring_write(ring, 0xFFFFF);
-
-	/* Clear timeout status bits */
-	radeon_ring_write(ring, PACKET0(UVD_SEMA_TIMEOUT_STATUS, 0));
-	radeon_ring_write(ring, 0x8);
-
-	radeon_ring_write(ring, PACKET0(UVD_SEMA_CNTL, 0));
-	radeon_ring_write(ring, 3);
-
-	radeon_ring_unlock_commit(rdev, ring);
-
-	return 0;
-}
-
-void r600_uvd_stop(struct radeon_device *rdev)
-{
-	struct radeon_ring *ring = &rdev->ring[R600_RING_TYPE_UVD_INDEX];
-
-	/* force RBC into idle state */
-	WREG32(UVD_RBC_RB_CNTL, 0x11010101);
-
-	/* Stall UMC and register bus before resetting VCPU */
-	WREG32_P(UVD_LMI_CTRL2, 1 << 8, ~(1 << 8));
-	WREG32_P(UVD_RB_ARB_CTRL, 1 << 3, ~(1 << 3));
-	mdelay(1);
-
-	/* put VCPU into reset */
-	WREG32(UVD_SOFT_RESET, VCPU_SOFT_RESET);
-	mdelay(5);
-
-	/* disable VCPU clock */
-	WREG32(UVD_VCPU_CNTL, 0x0);
-
-	/* Unstall UMC and register bus */
-	WREG32_P(UVD_LMI_CTRL2, 0, ~(1 << 8));
-	WREG32_P(UVD_RB_ARB_CTRL, 0, ~(1 << 3));
-
-	ring->ready = false;
-}
-
-int r600_uvd_init(struct radeon_device *rdev)
-{
-	int i, j, r;
-	/* disable byte swapping */
-	u32 lmi_swap_cntl = 0;
-	u32 mp_swap_cntl = 0;
-
-	/* raise clocks while booting up the VCPU */
-	radeon_set_uvd_clocks(rdev, 53300, 40000);
-
-	/* disable clock gating */
-	WREG32(UVD_CGC_GATE, 0);
-
-	/* disable interupt */
-	WREG32_P(UVD_MASTINT_EN, 0, ~(1 << 1));
-
-	/* Stall UMC and register bus before resetting VCPU */
-	WREG32_P(UVD_LMI_CTRL2, 1 << 8, ~(1 << 8));
-	WREG32_P(UVD_RB_ARB_CTRL, 1 << 3, ~(1 << 3));
-	mdelay(1);
-
-	/* put LMI, VCPU, RBC etc... into reset */
-	WREG32(UVD_SOFT_RESET, LMI_SOFT_RESET | VCPU_SOFT_RESET |
-	       LBSI_SOFT_RESET | RBC_SOFT_RESET | CSM_SOFT_RESET |
-	       CXW_SOFT_RESET | TAP_SOFT_RESET | LMI_UMC_SOFT_RESET);
-	mdelay(5);
-
-	/* take UVD block out of reset */
-	WREG32_P(SRBM_SOFT_RESET, 0, ~SOFT_RESET_UVD);
-	mdelay(5);
-
-	/* initialize UVD memory controller */
-	WREG32(UVD_LMI_CTRL, 0x40 | (1 << 8) | (1 << 13) |
-			     (1 << 21) | (1 << 9) | (1 << 20));
-
-#ifdef __BIG_ENDIAN
-	/* swap (8 in 32) RB and IB */
-	lmi_swap_cntl = 0xa;
-	mp_swap_cntl = 0;
-#endif
-	WREG32(UVD_LMI_SWAP_CNTL, lmi_swap_cntl);
-	WREG32(UVD_MP_SWAP_CNTL, mp_swap_cntl);
-
-	WREG32(UVD_MPC_SET_MUXA0, 0x40c2040);
-	WREG32(UVD_MPC_SET_MUXA1, 0x0);
-	WREG32(UVD_MPC_SET_MUXB0, 0x40c2040);
-	WREG32(UVD_MPC_SET_MUXB1, 0x0);
-	WREG32(UVD_MPC_SET_ALU, 0);
-	WREG32(UVD_MPC_SET_MUX, 0x88);
-
-	/* take all subblocks out of reset, except VCPU */
-	WREG32(UVD_SOFT_RESET, VCPU_SOFT_RESET);
-	mdelay(5);
-
-	/* enable VCPU clock */
-	WREG32(UVD_VCPU_CNTL,  1 << 9);
-
-	/* enable UMC */
-	WREG32_P(UVD_LMI_CTRL2, 0, ~(1 << 8));
-
-	/* boot up the VCPU */
-	WREG32(UVD_SOFT_RESET, 0);
-	mdelay(10);
-
-	WREG32_P(UVD_RB_ARB_CTRL, 0, ~(1 << 3));
-
-	for (i = 0; i < 10; ++i) {
-		uint32_t status;
-		for (j = 0; j < 100; ++j) {
-			status = RREG32(UVD_STATUS);
-			if (status & 2)
-				break;
-			mdelay(10);
-		}
-		r = 0;
-		if (status & 2)
-			break;
-
-		DRM_ERROR("UVD not responding, trying to reset the VCPU!!!\n");
-		WREG32_P(UVD_SOFT_RESET, VCPU_SOFT_RESET, ~VCPU_SOFT_RESET);
-		mdelay(10);
-		WREG32_P(UVD_SOFT_RESET, 0, ~VCPU_SOFT_RESET);
-		mdelay(10);
-		r = -1;
-	}
-
-	if (r) {
-		DRM_ERROR("UVD not responding, giving up!!!\n");
-		radeon_set_uvd_clocks(rdev, 0, 0);
-		return r;
-	}
-
-	/* enable interupt */
-	WREG32_P(UVD_MASTINT_EN, 3<<1, ~(3 << 1));
-
-	r = r600_uvd_rbc_start(rdev);
-	if (!r)
-		DRM_INFO("UVD initialized successfully.\n");
-
-	/* lower clocks again */
-	radeon_set_uvd_clocks(rdev, 0, 0);
-
-	return r;
-}
-
-/*
  * GPU scratch registers helpers function.
  */
 void r600_scratch_init(struct radeon_device *rdev)
@@ -2887,94 +2545,6 @@ int r600_ring_test(struct radeon_device *rdev, struct radeon_ring *ring)
 	return r;
 }
 
-/**
- * r600_dma_ring_test - simple async dma engine test
- *
- * @rdev: radeon_device pointer
- * @ring: radeon_ring structure holding ring information
- *
- * Test the DMA engine by writing using it to write an
- * value to memory. (r6xx-SI).
- * Returns 0 for success, error for failure.
- */
-int r600_dma_ring_test(struct radeon_device *rdev,
-		       struct radeon_ring *ring)
-{
-	unsigned i;
-	int r;
-	void __iomem *ptr = (void *)rdev->vram_scratch.ptr;
-	u32 tmp;
-
-	if (!ptr) {
-		DRM_ERROR("invalid vram scratch pointer\n");
-		return -EINVAL;
-	}
-
-	tmp = 0xCAFEDEAD;
-	writel(tmp, ptr);
-
-	r = radeon_ring_lock(rdev, ring, 4);
-	if (r) {
-		DRM_ERROR("radeon: dma failed to lock ring %d (%d).\n", ring->idx, r);
-		return r;
-	}
-	radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_WRITE, 0, 0, 1));
-	radeon_ring_write(ring, rdev->vram_scratch.gpu_addr & 0xfffffffc);
-	radeon_ring_write(ring, upper_32_bits(rdev->vram_scratch.gpu_addr) & 0xff);
-	radeon_ring_write(ring, 0xDEADBEEF);
-	radeon_ring_unlock_commit(rdev, ring);
-
-	for (i = 0; i < rdev->usec_timeout; i++) {
-		tmp = readl(ptr);
-		if (tmp == 0xDEADBEEF)
-			break;
-		DRM_UDELAY(1);
-	}
-
-	if (i < rdev->usec_timeout) {
-		DRM_INFO("ring test on %d succeeded in %d usecs\n", ring->idx, i);
-	} else {
-		DRM_ERROR("radeon: ring %d test failed (0x%08X)\n",
-			  ring->idx, tmp);
-		r = -EINVAL;
-	}
-	return r;
-}
-
-int r600_uvd_ring_test(struct radeon_device *rdev, struct radeon_ring *ring)
-{
-	uint32_t tmp = 0;
-	unsigned i;
-	int r;
-
-	WREG32(UVD_CONTEXT_ID, 0xCAFEDEAD);
-	r = radeon_ring_lock(rdev, ring, 3);
-	if (r) {
-		DRM_ERROR("radeon: cp failed to lock ring %d (%d).\n",
-			  ring->idx, r);
-		return r;
-	}
-	radeon_ring_write(ring, PACKET0(UVD_CONTEXT_ID, 0));
-	radeon_ring_write(ring, 0xDEADBEEF);
-	radeon_ring_unlock_commit(rdev, ring);
-	for (i = 0; i < rdev->usec_timeout; i++) {
-		tmp = RREG32(UVD_CONTEXT_ID);
-		if (tmp == 0xDEADBEEF)
-			break;
-		DRM_UDELAY(1);
-	}
-
-	if (i < rdev->usec_timeout) {
-		DRM_INFO("ring test on %d succeeded in %d usecs\n",
-			 ring->idx, i);
-	} else {
-		DRM_ERROR("radeon: ring %d test failed (0x%08X)\n",
-			  ring->idx, tmp);
-		r = -EINVAL;
-	}
-	return r;
-}
-
 /*
  * CP fences/semaphores
  */
@@ -3026,30 +2596,6 @@ void r600_fence_ring_emit(struct radeon_device *rdev,
 	}
 }
 
-void r600_uvd_fence_emit(struct radeon_device *rdev,
-			 struct radeon_fence *fence)
-{
-	struct radeon_ring *ring = &rdev->ring[fence->ring];
-	uint64_t addr = rdev->fence_drv[fence->ring].gpu_addr;
-
-	radeon_ring_write(ring, PACKET0(UVD_CONTEXT_ID, 0));
-	radeon_ring_write(ring, fence->seq);
-	radeon_ring_write(ring, PACKET0(UVD_GPCOM_VCPU_DATA0, 0));
-	radeon_ring_write(ring, addr & 0xffffffff);
-	radeon_ring_write(ring, PACKET0(UVD_GPCOM_VCPU_DATA1, 0));
-	radeon_ring_write(ring, upper_32_bits(addr) & 0xff);
-	radeon_ring_write(ring, PACKET0(UVD_GPCOM_VCPU_CMD, 0));
-	radeon_ring_write(ring, 0);
-
-	radeon_ring_write(ring, PACKET0(UVD_GPCOM_VCPU_DATA0, 0));
-	radeon_ring_write(ring, 0);
-	radeon_ring_write(ring, PACKET0(UVD_GPCOM_VCPU_DATA1, 0));
-	radeon_ring_write(ring, 0);
-	radeon_ring_write(ring, PACKET0(UVD_GPCOM_VCPU_CMD, 0));
-	radeon_ring_write(ring, 2);
-	return;
-}
-
 void r600_semaphore_ring_emit(struct radeon_device *rdev,
 			      struct radeon_ring *ring,
 			      struct radeon_semaphore *semaphore,
@@ -3066,95 +2612,6 @@ void r600_semaphore_ring_emit(struct radeon_device *rdev,
 	radeon_ring_write(ring, (upper_32_bits(addr) & 0xff) | sel);
 }
 
-/*
- * DMA fences/semaphores
- */
-
-/**
- * r600_dma_fence_ring_emit - emit a fence on the DMA ring
- *
- * @rdev: radeon_device pointer
- * @fence: radeon fence object
- *
- * Add a DMA fence packet to the ring to write
- * the fence seq number and DMA trap packet to generate
- * an interrupt if needed (r6xx-r7xx).
- */
-void r600_dma_fence_ring_emit(struct radeon_device *rdev,
-			      struct radeon_fence *fence)
-{
-	struct radeon_ring *ring = &rdev->ring[fence->ring];
-	u64 addr = rdev->fence_drv[fence->ring].gpu_addr;
-
-	/* write the fence */
-	radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_FENCE, 0, 0, 0));
-	radeon_ring_write(ring, addr & 0xfffffffc);
-	radeon_ring_write(ring, (upper_32_bits(addr) & 0xff));
-	radeon_ring_write(ring, lower_32_bits(fence->seq));
-	/* generate an interrupt */
-	radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_TRAP, 0, 0, 0));
-}
-
-/**
- * r600_dma_semaphore_ring_emit - emit a semaphore on the dma ring
- *
- * @rdev: radeon_device pointer
- * @ring: radeon_ring structure holding ring information
- * @semaphore: radeon semaphore object
- * @emit_wait: wait or signal semaphore
- *
- * Add a DMA semaphore packet to the ring wait on or signal
- * other rings (r6xx-SI).
- */
-void r600_dma_semaphore_ring_emit(struct radeon_device *rdev,
-				  struct radeon_ring *ring,
-				  struct radeon_semaphore *semaphore,
-				  bool emit_wait)
-{
-	u64 addr = semaphore->gpu_addr;
-	u32 s = emit_wait ? 0 : 1;
-
-	radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_SEMAPHORE, 0, s, 0));
-	radeon_ring_write(ring, addr & 0xfffffffc);
-	radeon_ring_write(ring, upper_32_bits(addr) & 0xff);
-}
-
-void r600_uvd_semaphore_emit(struct radeon_device *rdev,
-			     struct radeon_ring *ring,
-			     struct radeon_semaphore *semaphore,
-			     bool emit_wait)
-{
-	uint64_t addr = semaphore->gpu_addr;
-
-	radeon_ring_write(ring, PACKET0(UVD_SEMA_ADDR_LOW, 0));
-	radeon_ring_write(ring, (addr >> 3) & 0x000FFFFF);
-
-	radeon_ring_write(ring, PACKET0(UVD_SEMA_ADDR_HIGH, 0));
-	radeon_ring_write(ring, (addr >> 23) & 0x000FFFFF);
-
-	radeon_ring_write(ring, PACKET0(UVD_SEMA_CMD, 0));
-	radeon_ring_write(ring, emit_wait ? 1 : 0);
-}
-
-int r600_copy_blit(struct radeon_device *rdev,
-		   uint64_t src_offset,
-		   uint64_t dst_offset,
-		   unsigned num_gpu_pages,
-		   struct radeon_fence **fence)
-{
-	struct radeon_semaphore *sem = NULL;
-	struct radeon_sa_bo *vb = NULL;
-	int r;
-
-	r = r600_blit_prepare_copy(rdev, num_gpu_pages, fence, &vb, &sem);
-	if (r) {
-		return r;
-	}
-	r600_kms_blit_copy(rdev, src_offset, dst_offset, num_gpu_pages, vb);
-	r600_blit_done_copy(rdev, fence, vb, sem);
-	return 0;
-}
-
 /**
  * r600_copy_cpdma - copy pages using the CP DMA engine
  *
@@ -3239,80 +2696,6 @@ int r600_copy_cpdma(struct radeon_device *rdev,
 	return r;
 }
 
-/**
- * r600_copy_dma - copy pages using the DMA engine
- *
- * @rdev: radeon_device pointer
- * @src_offset: src GPU address
- * @dst_offset: dst GPU address
- * @num_gpu_pages: number of GPU pages to xfer
- * @fence: radeon fence object
- *
- * Copy GPU paging using the DMA engine (r6xx).
- * Used by the radeon ttm implementation to move pages if
- * registered as the asic copy callback.
- */
-int r600_copy_dma(struct radeon_device *rdev,
-		  uint64_t src_offset, uint64_t dst_offset,
-		  unsigned num_gpu_pages,
-		  struct radeon_fence **fence)
-{
-	struct radeon_semaphore *sem = NULL;
-	int ring_index = rdev->asic->copy.dma_ring_index;
-	struct radeon_ring *ring = &rdev->ring[ring_index];
-	u32 size_in_dw, cur_size_in_dw;
-	int i, num_loops;
-	int r = 0;
-
-	r = radeon_semaphore_create(rdev, &sem);
-	if (r) {
-		DRM_ERROR("radeon: moving bo (%d).\n", r);
-		return r;
-	}
-
-	size_in_dw = (num_gpu_pages << RADEON_GPU_PAGE_SHIFT) / 4;
-	num_loops = DIV_ROUND_UP(size_in_dw, 0xFFFE);
-	r = radeon_ring_lock(rdev, ring, num_loops * 4 + 8);
-	if (r) {
-		DRM_ERROR("radeon: moving bo (%d).\n", r);
-		radeon_semaphore_free(rdev, &sem, NULL);
-		return r;
-	}
-
-	if (radeon_fence_need_sync(*fence, ring->idx)) {
-		radeon_semaphore_sync_rings(rdev, sem, (*fence)->ring,
-					    ring->idx);
-		radeon_fence_note_sync(*fence, ring->idx);
-	} else {
-		radeon_semaphore_free(rdev, &sem, NULL);
-	}
-
-	for (i = 0; i < num_loops; i++) {
-		cur_size_in_dw = size_in_dw;
-		if (cur_size_in_dw > 0xFFFE)
-			cur_size_in_dw = 0xFFFE;
-		size_in_dw -= cur_size_in_dw;
-		radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_COPY, 0, 0, cur_size_in_dw));
-		radeon_ring_write(ring, dst_offset & 0xfffffffc);
-		radeon_ring_write(ring, src_offset & 0xfffffffc);
-		radeon_ring_write(ring, (((upper_32_bits(dst_offset) & 0xff) << 16) |
-					 (upper_32_bits(src_offset) & 0xff)));
-		src_offset += cur_size_in_dw * 4;
-		dst_offset += cur_size_in_dw * 4;
-	}
-
-	r = radeon_fence_emit(rdev, fence, ring->idx);
-	if (r) {
-		radeon_ring_unlock_undo(rdev, ring);
-		return r;
-	}
-
-	radeon_ring_unlock_commit(rdev, ring);
-	radeon_semaphore_free(rdev, &sem, *fence);
-
-	return r;
-}
-
 int r600_set_surface_reg(struct radeon_device *rdev, int reg,
 			 uint32_t tiling_flags, uint32_t pitch,
 			 uint32_t offset, uint32_t obj_size)
@@ -3334,6 +2717,11 @@ static int r600_startup(struct radeon_device *rdev)
 	/* enable pcie gen2 link */
 	r600_pcie_gen2_enable(rdev);
 
+	/* scratch needs to be initialized before MC */
+	r = r600_vram_scratch_init(rdev);
+	if (r)
+		return r;
+
 	r600_mc_program(rdev);
 
 	if (!rdev->me_fw || !rdev->pfp_fw || !rdev->rlc_fw) {
@@ -3344,10 +2732,6 @@ static int r600_startup(struct radeon_device *rdev)
 		}
 	}
 
-	r = r600_vram_scratch_init(rdev);
-	if (r)
-		return r;
-
 	if (rdev->flags & RADEON_IS_AGP) {
 		r600_agp_enable(rdev);
 	} else {
@@ -3356,12 +2740,6 @@ static int r600_startup(struct radeon_device *rdev)
 			return r;
 	}
 	r600_gpu_init(rdev);
-	r = r600_blit_init(rdev);
-	if (r) {
-		r600_blit_fini(rdev);
-		rdev->asic->copy.copy = NULL;
-		dev_warn(rdev->dev, "failed blitter (%d) falling back to memcpy\n", r);
-	}
 
 	/* allocate wb buffer */
 	r = radeon_wb_init(rdev);
@@ -3398,14 +2776,14 @@ static int r600_startup(struct radeon_device *rdev)
 	ring = &rdev->ring[RADEON_RING_TYPE_GFX_INDEX];
 	r = radeon_ring_init(rdev, ring, ring->ring_size, RADEON_WB_CP_RPTR_OFFSET,
 			     R600_CP_RB_RPTR, R600_CP_RB_WPTR,
-			     0, 0xfffff, RADEON_CP_PACKET2);
+			     RADEON_CP_PACKET2);
 	if (r)
 		return r;
 
 	ring = &rdev->ring[R600_RING_TYPE_DMA_INDEX];
 	r = radeon_ring_init(rdev, ring, ring->ring_size, R600_WB_DMA_RPTR_OFFSET,
 			     DMA_RB_RPTR, DMA_RB_WPTR,
-			     2, 0x3fffc, DMA_PACKET(DMA_PACKET_NOP, 0, 0, 0));
+			     DMA_PACKET(DMA_PACKET_NOP, 0, 0, 0));
 	if (r)
 		return r;
 
@@ -3574,7 +2952,6 @@ int r600_init(struct radeon_device *rdev)
 void r600_fini(struct radeon_device *rdev)
 {
 	r600_audio_fini(rdev);
-	r600_blit_fini(rdev);
 	r600_cp_fini(rdev);
 	r600_dma_fini(rdev);
 	r600_irq_fini(rdev);
@@ -3626,16 +3003,6 @@ void r600_ring_ib_execute(struct radeon_device *rdev, struct radeon_ib *ib)
 	radeon_ring_write(ring, ib->length_dw);
 }
 
-void r600_uvd_ib_execute(struct radeon_device *rdev, struct radeon_ib *ib)
-{
-	struct radeon_ring *ring = &rdev->ring[ib->ring];
-
-	radeon_ring_write(ring, PACKET0(UVD_RBC_IB_BASE, 0));
-	radeon_ring_write(ring, ib->gpu_addr);
-	radeon_ring_write(ring, PACKET0(UVD_RBC_IB_SIZE, 0));
-	radeon_ring_write(ring, ib->length_dw);
-}
-
 int r600_ib_test(struct radeon_device *rdev, struct radeon_ring *ring)
 {
 	struct radeon_ib ib;
@@ -3689,139 +3056,6 @@ free_scratch:
 	return r;
 }
 
-/**
- * r600_dma_ib_test - test an IB on the DMA engine
- *
- * @rdev: radeon_device pointer
- * @ring: radeon_ring structure holding ring information
- *
- * Test a simple IB in the DMA ring (r6xx-SI).
- * Returns 0 on success, error on failure.
- */
-int r600_dma_ib_test(struct radeon_device *rdev, struct radeon_ring *ring)
-{
-	struct radeon_ib ib;
-	unsigned i;
-	int r;
-	void __iomem *ptr = (void *)rdev->vram_scratch.ptr;
-	u32 tmp = 0;
-
-	if (!ptr) {
-		DRM_ERROR("invalid vram scratch pointer\n");
-		return -EINVAL;
-	}
-
-	tmp = 0xCAFEDEAD;
-	writel(tmp, ptr);
-
-	r = radeon_ib_get(rdev, ring->idx, &ib, NULL, 256);
-	if (r) {
-		DRM_ERROR("radeon: failed to get ib (%d).\n", r);
-		return r;
-	}
-
-	ib.ptr[0] = DMA_PACKET(DMA_PACKET_WRITE, 0, 0, 1);
-	ib.ptr[1] = rdev->vram_scratch.gpu_addr & 0xfffffffc;
-	ib.ptr[2] = upper_32_bits(rdev->vram_scratch.gpu_addr) & 0xff;
-	ib.ptr[3] = 0xDEADBEEF;
-	ib.length_dw = 4;
-
-	r = radeon_ib_schedule(rdev, &ib, NULL);
-	if (r) {
-		radeon_ib_free(rdev, &ib);
-		DRM_ERROR("radeon: failed to schedule ib (%d).\n", r);
-		return r;
-	}
-	r = radeon_fence_wait(ib.fence, false);
-	if (r) {
-		DRM_ERROR("radeon: fence wait failed (%d).\n", r);
-		return r;
-	}
-	for (i = 0; i < rdev->usec_timeout; i++) {
-		tmp = readl(ptr);
-		if (tmp == 0xDEADBEEF)
-			break;
-		DRM_UDELAY(1);
-	}
-	if (i < rdev->usec_timeout) {
-		DRM_INFO("ib test on ring %d succeeded in %u usecs\n", ib.fence->ring, i);
-	} else {
-		DRM_ERROR("radeon: ib test failed (0x%08X)\n", tmp);
-		r = -EINVAL;
-	}
-	radeon_ib_free(rdev, &ib);
-	return r;
-}
-
-int r600_uvd_ib_test(struct radeon_device *rdev, struct radeon_ring *ring)
-{
-	struct radeon_fence *fence = NULL;
-	int r;
-
-	r = radeon_set_uvd_clocks(rdev, 53300, 40000);
-	if (r) {
-		DRM_ERROR("radeon: failed to raise UVD clocks (%d).\n", r);
-		return r;
-	}
-
-	r = radeon_uvd_get_create_msg(rdev, ring->idx, 1, NULL);
-	if (r) {
-		DRM_ERROR("radeon: failed to get create msg (%d).\n", r);
-		goto error;
-	}
-
-	r = radeon_uvd_get_destroy_msg(rdev, ring->idx, 1, &fence);
-	if (r) {
-		DRM_ERROR("radeon: failed to get destroy ib (%d).\n", r);
-		goto error;
-	}
-
-	r = radeon_fence_wait(fence, false);
-	if (r) {
-		DRM_ERROR("radeon: fence wait failed (%d).\n", r);
-		goto error;
-	}
-	DRM_INFO("ib test on ring %d succeeded\n",  ring->idx);
-error:
-	radeon_fence_unref(&fence);
-	radeon_set_uvd_clocks(rdev, 0, 0);
-	return r;
-}
-
-/**
- * r600_dma_ring_ib_execute - Schedule an IB on the DMA engine
- *
- * @rdev: radeon_device pointer
- * @ib: IB object to schedule
- *
- * Schedule an IB in the DMA ring (r6xx-r7xx).
- */
-void r600_dma_ring_ib_execute(struct radeon_device *rdev, struct radeon_ib *ib)
-{
-	struct radeon_ring *ring = &rdev->ring[ib->ring];
-
-	if (rdev->wb.enabled) {
-		u32 next_rptr = ring->wptr + 4;
-		while ((next_rptr & 7) != 5)
-			next_rptr++;
-		next_rptr += 3;
-		radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_WRITE, 0, 0, 1));
-		radeon_ring_write(ring, ring->next_rptr_gpu_addr & 0xfffffffc);
-		radeon_ring_write(ring, upper_32_bits(ring->next_rptr_gpu_addr) & 0xff);
-		radeon_ring_write(ring, next_rptr);
-	}
-
-	/* The indirect buffer packet must end on an 8 DW boundary in the DMA ring.
-	 * Pad as necessary with NOPs.
-	 */
-	while ((ring->wptr & 7) != 5)
-		radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_NOP, 0, 0, 0));
-	radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_INDIRECT_BUFFER, 0, 0, 0));
-	radeon_ring_write(ring, (ib->gpu_addr & 0xFFFFFFE0));
-	radeon_ring_write(ring, (ib->length_dw << 16) | (upper_32_bits(ib->gpu_addr) & 0xFF));
-
-}
-
 /*
  * Interrupts
  *
@@ -3838,7 +3072,7 @@ void r600_ih_ring_init(struct radeon_device *rdev, unsigned ring_size)
 	u32 rb_bufsz;
 
 	/* Align ring size */
-	rb_bufsz = drm_order(ring_size / 4);
+	rb_bufsz = order_base_2(ring_size / 4);
 	ring_size = (1 << rb_bufsz) * 4;
 	rdev->ih.ring_size = ring_size;
 	rdev->ih.ptr_mask = rdev->ih.ring_size - 1;
@@ -4075,7 +3309,7 @@ int r600_irq_init(struct radeon_device *rdev)
 	WREG32(INTERRUPT_CNTL, interrupt_cntl);
 
 	WREG32(IH_RB_BASE, rdev->ih.gpu_addr >> 8);
-	rb_bufsz = drm_order(rdev->ih.ring_size / 4);
+	rb_bufsz = order_base_2(rdev->ih.ring_size / 4);
 
 	ih_rb_cntl = (IH_WPTR_OVERFLOW_ENABLE |
 		      IH_WPTR_OVERFLOW_CLEAR |
diff --git a/drivers/gpu/drm/radeon/r600_audio.c b/drivers/gpu/drm/radeon/r600_audio.c
index c92eb86a8e55..47fc2b886979 100644
--- a/drivers/gpu/drm/radeon/r600_audio.c
+++ b/drivers/gpu/drm/radeon/r600_audio.c
@@ -57,12 +57,12 @@ static bool radeon_dig_encoder(struct drm_encoder *encoder)
  */
 static int r600_audio_chipset_supported(struct radeon_device *rdev)
 {
-	return ASIC_IS_DCE2(rdev) && !ASIC_IS_DCE6(rdev);
+	return ASIC_IS_DCE2(rdev) && !ASIC_IS_NODCE(rdev);
 }
 
-struct r600_audio r600_audio_status(struct radeon_device *rdev)
+struct r600_audio_pin r600_audio_status(struct radeon_device *rdev)
 {
-	struct r600_audio status;
+	struct r600_audio_pin status;
 	uint32_t value;
 
 	value = RREG32(R600_AUDIO_RATE_BPS_CHANNEL);
@@ -120,16 +120,16 @@ void r600_audio_update_hdmi(struct work_struct *work)
 	struct radeon_device *rdev = container_of(work, struct radeon_device,
 						  audio_work);
 	struct drm_device *dev = rdev->ddev;
-	struct r600_audio audio_status = r600_audio_status(rdev);
+	struct r600_audio_pin audio_status = r600_audio_status(rdev);
 	struct drm_encoder *encoder;
 	bool changed = false;
 
-	if (rdev->audio_status.channels != audio_status.channels ||
-	    rdev->audio_status.rate != audio_status.rate ||
-	    rdev->audio_status.bits_per_sample != audio_status.bits_per_sample ||
-	    rdev->audio_status.status_bits != audio_status.status_bits ||
-	    rdev->audio_status.category_code != audio_status.category_code) {
-		rdev->audio_status = audio_status;
+	if (rdev->audio.pin[0].channels != audio_status.channels ||
+	    rdev->audio.pin[0].rate != audio_status.rate ||
+	    rdev->audio.pin[0].bits_per_sample != audio_status.bits_per_sample ||
+	    rdev->audio.pin[0].status_bits != audio_status.status_bits ||
+	    rdev->audio.pin[0].category_code != audio_status.category_code) {
+		rdev->audio.pin[0] = audio_status;
 		changed = true;
 	}
 
@@ -141,13 +141,13 @@ void r600_audio_update_hdmi(struct work_struct *work)
 	}
 }
 
-/*
- * turn on/off audio engine
- */
-static void r600_audio_engine_enable(struct radeon_device *rdev, bool enable)
+/* enable the audio stream */
+static void r600_audio_enable(struct radeon_device *rdev,
+			      struct r600_audio_pin *pin,
+			      bool enable)
 {
 	u32 value = 0;
-	DRM_INFO("%s audio support\n", enable ? "Enabling" : "Disabling");
+
 	if (ASIC_IS_DCE4(rdev)) {
 		if (enable) {
 			value |= 0x81000000; /* Required to enable audio */
@@ -158,7 +158,7 @@ static void r600_audio_engine_enable(struct radeon_device *rdev, bool enable)
 		WREG32_P(R600_AUDIO_ENABLE,
 			 enable ? 0x81000000 : 0x0, ~0x81000000);
 	}
-	rdev->audio_enabled = enable;
+	DRM_INFO("%s audio %d support\n", enable ? "Enabling" : "Disabling", pin->id);
 }
 
 /*
@@ -169,13 +169,17 @@ int r600_audio_init(struct radeon_device *rdev)
 	if (!radeon_audio || !r600_audio_chipset_supported(rdev))
 		return 0;
 
-	r600_audio_engine_enable(rdev, true);
+	rdev->audio.enabled = true;
+
+	rdev->audio.num_pins = 1;
+	rdev->audio.pin[0].channels = -1;
+	rdev->audio.pin[0].rate = -1;
+	rdev->audio.pin[0].bits_per_sample = -1;
+	rdev->audio.pin[0].status_bits = 0;
+	rdev->audio.pin[0].category_code = 0;
+	rdev->audio.pin[0].id = 0;
 
-	rdev->audio_status.channels = -1;
-	rdev->audio_status.rate = -1;
-	rdev->audio_status.bits_per_sample = -1;
-	rdev->audio_status.status_bits = 0;
-	rdev->audio_status.category_code = 0;
+	r600_audio_enable(rdev, &rdev->audio.pin[0], true);
 
 	return 0;
 }
@@ -186,8 +190,16 @@ int r600_audio_init(struct radeon_device *rdev)
  */
 void r600_audio_fini(struct radeon_device *rdev)
 {
-	if (!rdev->audio_enabled)
+	if (!rdev->audio.enabled)
 		return;
 
-	r600_audio_engine_enable(rdev, false);
+	r600_audio_enable(rdev, &rdev->audio.pin[0], false);
+
+	rdev->audio.enabled = false;
+}
+
+struct r600_audio_pin *r600_audio_get_pin(struct radeon_device *rdev)
+{
+	/* only one pin on 6xx-NI */
+	return &rdev->audio.pin[0];
 }
diff --git a/drivers/gpu/drm/radeon/r600_blit.c b/drivers/gpu/drm/radeon/r600_blit.c
index f651881eb0ae..daf7572be976 100644
--- a/drivers/gpu/drm/radeon/r600_blit.c
+++ b/drivers/gpu/drm/radeon/r600_blit.c
@@ -31,6 +31,37 @@
 
 #include "r600_blit_shaders.h"
 
+/* 23 bits of float fractional data */
+#define I2F_FRAC_BITS  23
+#define I2F_MASK ((1 << I2F_FRAC_BITS) - 1)
+
+/*
+ * Converts unsigned integer into 32-bit IEEE floating point representation.
+ * Will be exact from 0 to 2^24.  Above that, we round towards zero
+ * as the fractional bits will not fit in a float.  (It would be better to
+ * round towards even as the fpu does, but that is slower.)
+ */
+static __pure uint32_t int2float(uint32_t x)
+{
+	uint32_t msb, exponent, fraction;
+
+	/* Zero is special */
+	if (!x) return 0;
+
+	/* Get location of the most significant bit */
+	msb = __fls(x);
+
+	/*
+	 * Use a rotate instead of a shift because that works both leftwards
+	 * and rightwards due to the mod(32) behaviour.  This means we don't
+	 * need to check to see if we are above 2^24 or not.
+	 */
+	fraction = ror32(x, (msb - I2F_FRAC_BITS) & 0x1f) & I2F_MASK;
+	exponent = (127 + msb) << I2F_FRAC_BITS;
+
+	return fraction + exponent;
+}
+
 #define DI_PT_RECTLIST        0x11
 #define DI_INDEX_SIZE_16_BIT  0x0
 #define DI_SRC_SEL_AUTO_INDEX 0x2
diff --git a/drivers/gpu/drm/radeon/r600_blit_kms.c b/drivers/gpu/drm/radeon/r600_blit_kms.c
deleted file mode 100644
index 9fb5780a552f..000000000000
--- a/drivers/gpu/drm/radeon/r600_blit_kms.c
+++ /dev/null
@@ -1,785 +0,0 @@
-/*
- * Copyright 2009 Advanced Micro Devices, Inc.
- * Copyright 2009 Red Hat Inc.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice (including the next
- * paragraph) shall be included in all copies or substantial portions of the
- * Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE COPYRIGHT HOLDER(S) AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM, DAMAGES OR
- * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
- * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
- * DEALINGS IN THE SOFTWARE.
- *
- */
-
-#include <drm/drmP.h>
-#include <drm/radeon_drm.h>
-#include "radeon.h"
-
-#include "r600d.h"
-#include "r600_blit_shaders.h"
-#include "radeon_blit_common.h"
-
-/* 23 bits of float fractional data */
-#define I2F_FRAC_BITS  23
-#define I2F_MASK ((1 << I2F_FRAC_BITS) - 1)
-
-/*
- * Converts unsigned integer into 32-bit IEEE floating point representation.
- * Will be exact from 0 to 2^24.  Above that, we round towards zero
- * as the fractional bits will not fit in a float.  (It would be better to
- * round towards even as the fpu does, but that is slower.)
- */
-__pure uint32_t int2float(uint32_t x)
-{
-	uint32_t msb, exponent, fraction;
-
-	/* Zero is special */
-	if (!x) return 0;
-
-	/* Get location of the most significant bit */
-	msb = __fls(x);
-
-	/*
-	 * Use a rotate instead of a shift because that works both leftwards
-	 * and rightwards due to the mod(32) behaviour.  This means we don't
-	 * need to check to see if we are above 2^24 or not.
-	 */
-	fraction = ror32(x, (msb - I2F_FRAC_BITS) & 0x1f) & I2F_MASK;
-	exponent = (127 + msb) << I2F_FRAC_BITS;
-
-	return fraction + exponent;
-}
-
-/* emits 21 on rv770+, 23 on r600 */
-static void
-set_render_target(struct radeon_device *rdev, int format,
-		  int w, int h, u64 gpu_addr)
-{
-	struct radeon_ring *ring = &rdev->ring[RADEON_RING_TYPE_GFX_INDEX];
-	u32 cb_color_info;
-	int pitch, slice;
-
-	h = ALIGN(h, 8);
-	if (h < 8)
-		h = 8;
-
-	cb_color_info = CB_FORMAT(format) |
-		CB_SOURCE_FORMAT(CB_SF_EXPORT_NORM) |
-		CB_ARRAY_MODE(ARRAY_1D_TILED_THIN1);
-	pitch = (w / 8) - 1;
-	slice = ((w * h) / 64) - 1;
-
-	radeon_ring_write(ring, PACKET3(PACKET3_SET_CONTEXT_REG, 1));
-	radeon_ring_write(ring, (CB_COLOR0_BASE - PACKET3_SET_CONTEXT_REG_OFFSET) >> 2);
-	radeon_ring_write(ring, gpu_addr >> 8);
-
-	if (rdev->family > CHIP_R600 && rdev->family < CHIP_RV770) {
-		radeon_ring_write(ring, PACKET3(PACKET3_SURFACE_BASE_UPDATE, 0));
-		radeon_ring_write(ring, 2 << 0);
-	}
-
-	radeon_ring_write(ring, PACKET3(PACKET3_SET_CONTEXT_REG, 1));
-	radeon_ring_write(ring, (CB_COLOR0_SIZE - PACKET3_SET_CONTEXT_REG_OFFSET) >> 2);
-	radeon_ring_write(ring, (pitch << 0) | (slice << 10));
-
-	radeon_ring_write(ring, PACKET3(PACKET3_SET_CONTEXT_REG, 1));
-	radeon_ring_write(ring, (CB_COLOR0_VIEW - PACKET3_SET_CONTEXT_REG_OFFSET) >> 2);
-	radeon_ring_write(ring, 0);
-
-	radeon_ring_write(ring, PACKET3(PACKET3_SET_CONTEXT_REG, 1));
-	radeon_ring_write(ring, (CB_COLOR0_INFO - PACKET3_SET_CONTEXT_REG_OFFSET) >> 2);
-	radeon_ring_write(ring, cb_color_info);
-
-	radeon_ring_write(ring, PACKET3(PACKET3_SET_CONTEXT_REG, 1));
-	radeon_ring_write(ring, (CB_COLOR0_TILE - PACKET3_SET_CONTEXT_REG_OFFSET) >> 2);
-	radeon_ring_write(ring, 0);
-
-	radeon_ring_write(ring, PACKET3(PACKET3_SET_CONTEXT_REG, 1));
-	radeon_ring_write(ring, (CB_COLOR0_FRAG - PACKET3_SET_CONTEXT_REG_OFFSET) >> 2);
-	radeon_ring_write(ring, 0);
-
-	radeon_ring_write(ring, PACKET3(PACKET3_SET_CONTEXT_REG, 1));
-	radeon_ring_write(ring, (CB_COLOR0_MASK - PACKET3_SET_CONTEXT_REG_OFFSET) >> 2);
-	radeon_ring_write(ring, 0);
-}
-
-/* emits 5dw */
-static void
-cp_set_surface_sync(struct radeon_device *rdev,
-		    u32 sync_type, u32 size,
-		    u64 mc_addr)
-{
-	struct radeon_ring *ring = &rdev->ring[RADEON_RING_TYPE_GFX_INDEX];
-	u32 cp_coher_size;
-
-	if (size == 0xffffffff)
-		cp_coher_size = 0xffffffff;
-	else
-		cp_coher_size = ((size + 255) >> 8);
-
-	radeon_ring_write(ring, PACKET3(PACKET3_SURFACE_SYNC, 3));
-	radeon_ring_write(ring, sync_type);
-	radeon_ring_write(ring, cp_coher_size);
-	radeon_ring_write(ring, mc_addr >> 8);
-	radeon_ring_write(ring, 10); /* poll interval */
-}
-
-/* emits 21dw + 1 surface sync = 26dw */
-static void
-set_shaders(struct radeon_device *rdev)
-{
-	struct radeon_ring *ring = &rdev->ring[RADEON_RING_TYPE_GFX_INDEX];
-	u64 gpu_addr;
-	u32 sq_pgm_resources;
-
-	/* setup shader regs */
-	sq_pgm_resources = (1 << 0);
-
-	/* VS */
-	gpu_addr = rdev->r600_blit.shader_gpu_addr + rdev->r600_blit.vs_offset;
-	radeon_ring_write(ring, PACKET3(PACKET3_SET_CONTEXT_REG, 1));
-	radeon_ring_write(ring, (SQ_PGM_START_VS - PACKET3_SET_CONTEXT_REG_OFFSET) >> 2);
-	radeon_ring_write(ring, gpu_addr >> 8);
-
-	radeon_ring_write(ring, PACKET3(PACKET3_SET_CONTEXT_REG, 1));
-	radeon_ring_write(ring, (SQ_PGM_RESOURCES_VS - PACKET3_SET_CONTEXT_REG_OFFSET) >> 2);
-	radeon_ring_write(ring, sq_pgm_resources);
-
-	radeon_ring_write(ring, PACKET3(PACKET3_SET_CONTEXT_REG, 1));
-	radeon_ring_write(ring, (SQ_PGM_CF_OFFSET_VS - PACKET3_SET_CONTEXT_REG_OFFSET) >> 2);
-	radeon_ring_write(ring, 0);
-
-	/* PS */
-	gpu_addr = rdev->r600_blit.shader_gpu_addr + rdev->r600_blit.ps_offset;
-	radeon_ring_write(ring, PACKET3(PACKET3_SET_CONTEXT_REG, 1));
-	radeon_ring_write(ring, (SQ_PGM_START_PS - PACKET3_SET_CONTEXT_REG_OFFSET) >> 2);
-	radeon_ring_write(ring, gpu_addr >> 8);
-
-	radeon_ring_write(ring, PACKET3(PACKET3_SET_CONTEXT_REG, 1));
-	radeon_ring_write(ring, (SQ_PGM_RESOURCES_PS - PACKET3_SET_CONTEXT_REG_OFFSET) >> 2);
-	radeon_ring_write(ring, sq_pgm_resources | (1 << 28));
-
-	radeon_ring_write(ring, PACKET3(PACKET3_SET_CONTEXT_REG, 1));
-	radeon_ring_write(ring, (SQ_PGM_EXPORTS_PS - PACKET3_SET_CONTEXT_REG_OFFSET) >> 2);
-	radeon_ring_write(ring, 2);
-
-	radeon_ring_write(ring, PACKET3(PACKET3_SET_CONTEXT_REG, 1));
-	radeon_ring_write(ring, (SQ_PGM_CF_OFFSET_PS - PACKET3_SET_CONTEXT_REG_OFFSET) >> 2);
-	radeon_ring_write(ring, 0);
-
-	gpu_addr = rdev->r600_blit.shader_gpu_addr + rdev->r600_blit.vs_offset;
-	cp_set_surface_sync(rdev, PACKET3_SH_ACTION_ENA, 512, gpu_addr);
-}
-
-/* emits 9 + 1 sync (5) = 14*/
-static void
-set_vtx_resource(struct radeon_device *rdev, u64 gpu_addr)
-{
-	struct radeon_ring *ring = &rdev->ring[RADEON_RING_TYPE_GFX_INDEX];
-	u32 sq_vtx_constant_word2;
-
-	sq_vtx_constant_word2 = SQ_VTXC_BASE_ADDR_HI(upper_32_bits(gpu_addr) & 0xff) |
-		SQ_VTXC_STRIDE(16);
-#ifdef __BIG_ENDIAN
-	sq_vtx_constant_word2 |=  SQ_VTXC_ENDIAN_SWAP(SQ_ENDIAN_8IN32);
-#endif
-
-	radeon_ring_write(ring, PACKET3(PACKET3_SET_RESOURCE, 7));
-	radeon_ring_write(ring, 0x460);
-	radeon_ring_write(ring, gpu_addr & 0xffffffff);
-	radeon_ring_write(ring, 48 - 1);
-	radeon_ring_write(ring, sq_vtx_constant_word2);
-	radeon_ring_write(ring, 1 << 0);
-	radeon_ring_write(ring, 0);
-	radeon_ring_write(ring, 0);
-	radeon_ring_write(ring, SQ_TEX_VTX_VALID_BUFFER << 30);
-
-	if ((rdev->family == CHIP_RV610) ||
-	    (rdev->family == CHIP_RV620) ||
-	    (rdev->family == CHIP_RS780) ||
-	    (rdev->family == CHIP_RS880) ||
-	    (rdev->family == CHIP_RV710))
-		cp_set_surface_sync(rdev,
-				    PACKET3_TC_ACTION_ENA, 48, gpu_addr);
-	else
-		cp_set_surface_sync(rdev,
-				    PACKET3_VC_ACTION_ENA, 48, gpu_addr);
-}
-
-/* emits 9 */
-static void
-set_tex_resource(struct radeon_device *rdev,
-		 int format, int w, int h, int pitch,
-		 u64 gpu_addr, u32 size)
-{
-	struct radeon_ring *ring = &rdev->ring[RADEON_RING_TYPE_GFX_INDEX];
-	uint32_t sq_tex_resource_word0, sq_tex_resource_word1, sq_tex_resource_word4;
-
-	if (h < 1)
-		h = 1;
-
-	sq_tex_resource_word0 = S_038000_DIM(V_038000_SQ_TEX_DIM_2D) |
-		S_038000_TILE_MODE(V_038000_ARRAY_1D_TILED_THIN1);
-	sq_tex_resource_word0 |= S_038000_PITCH((pitch >> 3) - 1) |
-		S_038000_TEX_WIDTH(w - 1);
-
-	sq_tex_resource_word1 = S_038004_DATA_FORMAT(format);
-	sq_tex_resource_word1 |= S_038004_TEX_HEIGHT(h - 1);
-
-	sq_tex_resource_word4 = S_038010_REQUEST_SIZE(1) |
-		S_038010_DST_SEL_X(SQ_SEL_X) |
-		S_038010_DST_SEL_Y(SQ_SEL_Y) |
-		S_038010_DST_SEL_Z(SQ_SEL_Z) |
-		S_038010_DST_SEL_W(SQ_SEL_W);
-
-	cp_set_surface_sync(rdev,
-			    PACKET3_TC_ACTION_ENA, size, gpu_addr);
-
-	radeon_ring_write(ring, PACKET3(PACKET3_SET_RESOURCE, 7));
-	radeon_ring_write(ring, 0);
-	radeon_ring_write(ring, sq_tex_resource_word0);
-	radeon_ring_write(ring, sq_tex_resource_word1);
-	radeon_ring_write(ring, gpu_addr >> 8);
-	radeon_ring_write(ring, gpu_addr >> 8);
-	radeon_ring_write(ring, sq_tex_resource_word4);
-	radeon_ring_write(ring, 0);
-	radeon_ring_write(ring, SQ_TEX_VTX_VALID_TEXTURE << 30);
-}
-
-/* emits 12 */
-static void
-set_scissors(struct radeon_device *rdev, int x1, int y1,
-	     int x2, int y2)
-{
-	struct radeon_ring *ring = &rdev->ring[RADEON_RING_TYPE_GFX_INDEX];
-	radeon_ring_write(ring, PACKET3(PACKET3_SET_CONTEXT_REG, 2));
-	radeon_ring_write(ring, (PA_SC_SCREEN_SCISSOR_TL - PACKET3_SET_CONTEXT_REG_OFFSET) >> 2);
-	radeon_ring_write(ring, (x1 << 0) | (y1 << 16));
-	radeon_ring_write(ring, (x2 << 0) | (y2 << 16));
-
-	radeon_ring_write(ring, PACKET3(PACKET3_SET_CONTEXT_REG, 2));
-	radeon_ring_write(ring, (PA_SC_GENERIC_SCISSOR_TL - PACKET3_SET_CONTEXT_REG_OFFSET) >> 2);
-	radeon_ring_write(ring, (x1 << 0) | (y1 << 16) | (1 << 31));
-	radeon_ring_write(ring, (x2 << 0) | (y2 << 16));
-
-	radeon_ring_write(ring, PACKET3(PACKET3_SET_CONTEXT_REG, 2));
-	radeon_ring_write(ring, (PA_SC_WINDOW_SCISSOR_TL - PACKET3_SET_CONTEXT_REG_OFFSET) >> 2);
-	radeon_ring_write(ring, (x1 << 0) | (y1 << 16) | (1 << 31));
-	radeon_ring_write(ring, (x2 << 0) | (y2 << 16));
-}
-
-/* emits 10 */
-static void
-draw_auto(struct radeon_device *rdev)
-{
-	struct radeon_ring *ring = &rdev->ring[RADEON_RING_TYPE_GFX_INDEX];
-	radeon_ring_write(ring, PACKET3(PACKET3_SET_CONFIG_REG, 1));
-	radeon_ring_write(ring, (VGT_PRIMITIVE_TYPE - PACKET3_SET_CONFIG_REG_OFFSET) >> 2);
-	radeon_ring_write(ring, DI_PT_RECTLIST);
-
-	radeon_ring_write(ring, PACKET3(PACKET3_INDEX_TYPE, 0));
-	radeon_ring_write(ring,
-#ifdef __BIG_ENDIAN
-			  (2 << 2) |
-#endif
-			  DI_INDEX_SIZE_16_BIT);
-
-	radeon_ring_write(ring, PACKET3(PACKET3_NUM_INSTANCES, 0));
-	radeon_ring_write(ring, 1);
-
-	radeon_ring_write(ring, PACKET3(PACKET3_DRAW_INDEX_AUTO, 1));
-	radeon_ring_write(ring, 3);
-	radeon_ring_write(ring, DI_SRC_SEL_AUTO_INDEX);
-
-}
-
-/* emits 14 */
-static void
-set_default_state(struct radeon_device *rdev)
-{
-	struct radeon_ring *ring = &rdev->ring[RADEON_RING_TYPE_GFX_INDEX];
-	u32 sq_config, sq_gpr_resource_mgmt_1, sq_gpr_resource_mgmt_2;
-	u32 sq_thread_resource_mgmt, sq_stack_resource_mgmt_1, sq_stack_resource_mgmt_2;
-	int num_ps_gprs, num_vs_gprs, num_temp_gprs, num_gs_gprs, num_es_gprs;
-	int num_ps_threads, num_vs_threads, num_gs_threads, num_es_threads;
-	int num_ps_stack_entries, num_vs_stack_entries, num_gs_stack_entries, num_es_stack_entries;
-	u64 gpu_addr;
-	int dwords;
-
-	switch (rdev->family) {
-	case CHIP_R600:
-		num_ps_gprs = 192;
-		num_vs_gprs = 56;
-		num_temp_gprs = 4;
-		num_gs_gprs = 0;
-		num_es_gprs = 0;
-		num_ps_threads = 136;
-		num_vs_threads = 48;
-		num_gs_threads = 4;
-		num_es_threads = 4;
-		num_ps_stack_entries = 128;
-		num_vs_stack_entries = 128;
-		num_gs_stack_entries = 0;
-		num_es_stack_entries = 0;
-		break;
-	case CHIP_RV630:
-	case CHIP_RV635:
-		num_ps_gprs = 84;
-		num_vs_gprs = 36;
-		num_temp_gprs = 4;
-		num_gs_gprs = 0;
-		num_es_gprs = 0;
-		num_ps_threads = 144;
-		num_vs_threads = 40;
-		num_gs_threads = 4;
-		num_es_threads = 4;
-		num_ps_stack_entries = 40;
-		num_vs_stack_entries = 40;
-		num_gs_stack_entries = 32;
-		num_es_stack_entries = 16;
-		break;
-	case CHIP_RV610:
-	case CHIP_RV620:
-	case CHIP_RS780:
-	case CHIP_RS880:
-	default:
-		num_ps_gprs = 84;
-		num_vs_gprs = 36;
-		num_temp_gprs = 4;
-		num_gs_gprs = 0;
-		num_es_gprs = 0;
-		num_ps_threads = 136;
-		num_vs_threads = 48;
-		num_gs_threads = 4;
-		num_es_threads = 4;
-		num_ps_stack_entries = 40;
-		num_vs_stack_entries = 40;
-		num_gs_stack_entries = 32;
-		num_es_stack_entries = 16;
-		break;
-	case CHIP_RV670:
-		num_ps_gprs = 144;
-		num_vs_gprs = 40;
-		num_temp_gprs = 4;
-		num_gs_gprs = 0;
-		num_es_gprs = 0;
-		num_ps_threads = 136;
-		num_vs_threads = 48;
-		num_gs_threads = 4;
-		num_es_threads = 4;
-		num_ps_stack_entries = 40;
-		num_vs_stack_entries = 40;
-		num_gs_stack_entries = 32;
-		num_es_stack_entries = 16;
-		break;
-	case CHIP_RV770:
-		num_ps_gprs = 192;
-		num_vs_gprs = 56;
-		num_temp_gprs = 4;
-		num_gs_gprs = 0;
-		num_es_gprs = 0;
-		num_ps_threads = 188;
-		num_vs_threads = 60;
-		num_gs_threads = 0;
-		num_es_threads = 0;
-		num_ps_stack_entries = 256;
-		num_vs_stack_entries = 256;
-		num_gs_stack_entries = 0;
-		num_es_stack_entries = 0;
-		break;
-	case CHIP_RV730:
-	case CHIP_RV740:
-		num_ps_gprs = 84;
-		num_vs_gprs = 36;
-		num_temp_gprs = 4;
-		num_gs_gprs = 0;
-		num_es_gprs = 0;
-		num_ps_threads = 188;
-		num_vs_threads = 60;
-		num_gs_threads = 0;
-		num_es_threads = 0;
-		num_ps_stack_entries = 128;
-		num_vs_stack_entries = 128;
-		num_gs_stack_entries = 0;
-		num_es_stack_entries = 0;
-		break;
-	case CHIP_RV710:
-		num_ps_gprs = 192;
-		num_vs_gprs = 56;
-		num_temp_gprs = 4;
-		num_gs_gprs = 0;
-		num_es_gprs = 0;
-		num_ps_threads = 144;
-		num_vs_threads = 48;
-		num_gs_threads = 0;
-		num_es_threads = 0;
-		num_ps_stack_entries = 128;
-		num_vs_stack_entries = 128;
-		num_gs_stack_entries = 0;
-		num_es_stack_entries = 0;
-		break;
-	}
-
-	if ((rdev->family == CHIP_RV610) ||
-	    (rdev->family == CHIP_RV620) ||
-	    (rdev->family == CHIP_RS780) ||
-	    (rdev->family == CHIP_RS880) ||
-	    (rdev->family == CHIP_RV710))
-		sq_config = 0;
-	else
-		sq_config = VC_ENABLE;
-
-	sq_config |= (DX9_CONSTS |
-		      ALU_INST_PREFER_VECTOR |
-		      PS_PRIO(0) |
-		      VS_PRIO(1) |
-		      GS_PRIO(2) |
-		      ES_PRIO(3));
-
-	sq_gpr_resource_mgmt_1 = (NUM_PS_GPRS(num_ps_gprs) |
-				  NUM_VS_GPRS(num_vs_gprs) |
-				  NUM_CLAUSE_TEMP_GPRS(num_temp_gprs));
-	sq_gpr_resource_mgmt_2 = (NUM_GS_GPRS(num_gs_gprs) |
-				  NUM_ES_GPRS(num_es_gprs));
-	sq_thread_resource_mgmt = (NUM_PS_THREADS(num_ps_threads) |
-				   NUM_VS_THREADS(num_vs_threads) |
-				   NUM_GS_THREADS(num_gs_threads) |
-				   NUM_ES_THREADS(num_es_threads));
-	sq_stack_resource_mgmt_1 = (NUM_PS_STACK_ENTRIES(num_ps_stack_entries) |
-				    NUM_VS_STACK_ENTRIES(num_vs_stack_entries));
-	sq_stack_resource_mgmt_2 = (NUM_GS_STACK_ENTRIES(num_gs_stack_entries) |
-				    NUM_ES_STACK_ENTRIES(num_es_stack_entries));
-
-	/* emit an IB pointing at default state */
-	dwords = ALIGN(rdev->r600_blit.state_len, 0x10);
-	gpu_addr = rdev->r600_blit.shader_gpu_addr + rdev->r600_blit.state_offset;
-	radeon_ring_write(ring, PACKET3(PACKET3_INDIRECT_BUFFER, 2));
-	radeon_ring_write(ring,
-#ifdef __BIG_ENDIAN
-			  (2 << 0) |
-#endif
-			  (gpu_addr & 0xFFFFFFFC));
-	radeon_ring_write(ring, upper_32_bits(gpu_addr) & 0xFF);
-	radeon_ring_write(ring, dwords);
-
-	/* SQ config */
-	radeon_ring_write(ring, PACKET3(PACKET3_SET_CONFIG_REG, 6));
-	radeon_ring_write(ring, (SQ_CONFIG - PACKET3_SET_CONFIG_REG_OFFSET) >> 2);
-	radeon_ring_write(ring, sq_config);
-	radeon_ring_write(ring, sq_gpr_resource_mgmt_1);
-	radeon_ring_write(ring, sq_gpr_resource_mgmt_2);
-	radeon_ring_write(ring, sq_thread_resource_mgmt);
-	radeon_ring_write(ring, sq_stack_resource_mgmt_1);
-	radeon_ring_write(ring, sq_stack_resource_mgmt_2);
-}
-
-int r600_blit_init(struct radeon_device *rdev)
-{
-	u32 obj_size;
-	int i, r, dwords;
-	void *ptr;
-	u32 packet2s[16];
-	int num_packet2s = 0;
-
-	rdev->r600_blit.primitives.set_render_target = set_render_target;
-	rdev->r600_blit.primitives.cp_set_surface_sync = cp_set_surface_sync;
-	rdev->r600_blit.primitives.set_shaders = set_shaders;
-	rdev->r600_blit.primitives.set_vtx_resource = set_vtx_resource;
-	rdev->r600_blit.primitives.set_tex_resource = set_tex_resource;
-	rdev->r600_blit.primitives.set_scissors = set_scissors;
-	rdev->r600_blit.primitives.draw_auto = draw_auto;
-	rdev->r600_blit.primitives.set_default_state = set_default_state;
-
-	rdev->r600_blit.ring_size_common = 8; /* sync semaphore */
-	rdev->r600_blit.ring_size_common += 40; /* shaders + def state */
-	rdev->r600_blit.ring_size_common += 5; /* done copy */
-	rdev->r600_blit.ring_size_common += 16; /* fence emit for done copy */
-
-	rdev->r600_blit.ring_size_per_loop = 76;
-	/* set_render_target emits 2 extra dwords on rv6xx */
-	if (rdev->family > CHIP_R600 && rdev->family < CHIP_RV770)
-		rdev->r600_blit.ring_size_per_loop += 2;
-
-	rdev->r600_blit.max_dim = 8192;
-
-	rdev->r600_blit.state_offset = 0;
-
-	if (rdev->family >= CHIP_RV770)
-		rdev->r600_blit.state_len = r7xx_default_size;
-	else
-		rdev->r600_blit.state_len = r6xx_default_size;
-
-	dwords = rdev->r600_blit.state_len;
-	while (dwords & 0xf) {
-		packet2s[num_packet2s++] = cpu_to_le32(PACKET2(0));
-		dwords++;
-	}
-
-	obj_size = dwords * 4;
-	obj_size = ALIGN(obj_size, 256);
-
-	rdev->r600_blit.vs_offset = obj_size;
-	obj_size += r6xx_vs_size * 4;
-	obj_size = ALIGN(obj_size, 256);
-
-	rdev->r600_blit.ps_offset = obj_size;
-	obj_size += r6xx_ps_size * 4;
-	obj_size = ALIGN(obj_size, 256);
-
-	/* pin copy shader into vram if not already initialized */
-	if (rdev->r600_blit.shader_obj == NULL) {
-		r = radeon_bo_create(rdev, obj_size, PAGE_SIZE, true,
-				     RADEON_GEM_DOMAIN_VRAM,
-				     NULL, &rdev->r600_blit.shader_obj);
-		if (r) {
-			DRM_ERROR("r600 failed to allocate shader\n");
-			return r;
-		}
-
-		r = radeon_bo_reserve(rdev->r600_blit.shader_obj, false);
-		if (unlikely(r != 0))
-			return r;
-		r = radeon_bo_pin(rdev->r600_blit.shader_obj, RADEON_GEM_DOMAIN_VRAM,
-				  &rdev->r600_blit.shader_gpu_addr);
-		radeon_bo_unreserve(rdev->r600_blit.shader_obj);
-		if (r) {
-			dev_err(rdev->dev, "(%d) pin blit object failed\n", r);
-			return r;
-		}
-	}
-
-	DRM_DEBUG("r6xx blit allocated bo %08x vs %08x ps %08x\n",
-		  obj_size,
-		  rdev->r600_blit.vs_offset, rdev->r600_blit.ps_offset);
-
-	r = radeon_bo_reserve(rdev->r600_blit.shader_obj, false);
-	if (unlikely(r != 0))
-		return r;
-	r = radeon_bo_kmap(rdev->r600_blit.shader_obj, &ptr);
-	if (r) {
-		DRM_ERROR("failed to map blit object %d\n", r);
-		return r;
-	}
-	if (rdev->family >= CHIP_RV770)
-		memcpy_toio(ptr + rdev->r600_blit.state_offset,
-			    r7xx_default_state, rdev->r600_blit.state_len * 4);
-	else
-		memcpy_toio(ptr + rdev->r600_blit.state_offset,
-			    r6xx_default_state, rdev->r600_blit.state_len * 4);
-	if (num_packet2s)
-		memcpy_toio(ptr + rdev->r600_blit.state_offset + (rdev->r600_blit.state_len * 4),
-			    packet2s, num_packet2s * 4);
-	for (i = 0; i < r6xx_vs_size; i++)
-		*(u32 *)((unsigned long)ptr + rdev->r600_blit.vs_offset + i * 4) = cpu_to_le32(r6xx_vs[i]);
-	for (i = 0; i < r6xx_ps_size; i++)
-		*(u32 *)((unsigned long)ptr + rdev->r600_blit.ps_offset + i * 4) = cpu_to_le32(r6xx_ps[i]);
-	radeon_bo_kunmap(rdev->r600_blit.shader_obj);
-	radeon_bo_unreserve(rdev->r600_blit.shader_obj);
-
-	radeon_ttm_set_active_vram_size(rdev, rdev->mc.real_vram_size);
-	return 0;
-}
-
-void r600_blit_fini(struct radeon_device *rdev)
-{
-	int r;
-
-	radeon_ttm_set_active_vram_size(rdev, rdev->mc.visible_vram_size);
-	if (rdev->r600_blit.shader_obj == NULL)
-		return;
-	/* If we can't reserve the bo, unref should be enough to destroy
-	 * it when it becomes idle.
-	 */
-	r = radeon_bo_reserve(rdev->r600_blit.shader_obj, false);
-	if (!r) {
-		radeon_bo_unpin(rdev->r600_blit.shader_obj);
-		radeon_bo_unreserve(rdev->r600_blit.shader_obj);
-	}
-	radeon_bo_unref(&rdev->r600_blit.shader_obj);
-}
-
-static unsigned r600_blit_create_rect(unsigned num_gpu_pages,
-				      int *width, int *height, int max_dim)
-{
-	unsigned max_pages;
-	unsigned pages = num_gpu_pages;
-	int w, h;
-
-	if (num_gpu_pages == 0) {
-		/* not supposed to be called with no pages, but just in case */
-		h = 0;
-		w = 0;
-		pages = 0;
-		WARN_ON(1);
-	} else {
-		int rect_order = 2;
-		h = RECT_UNIT_H;
-		while (num_gpu_pages / rect_order) {
-			h *= 2;
-			rect_order *= 4;
-			if (h >= max_dim) {
-				h = max_dim;
-				break;
-			}
-		}
-		max_pages = (max_dim * h) / (RECT_UNIT_W * RECT_UNIT_H);
-		if (pages > max_pages)
-			pages = max_pages;
-		w = (pages * RECT_UNIT_W * RECT_UNIT_H) / h;
-		w = (w / RECT_UNIT_W) * RECT_UNIT_W;
-		pages = (w * h) / (RECT_UNIT_W * RECT_UNIT_H);
-		BUG_ON(pages == 0);
-	}
-
-
-	DRM_DEBUG("blit_rectangle: h=%d, w=%d, pages=%d\n", h, w, pages);
-
-	/* return width and height only of the caller wants it */
-	if (height)
-		*height = h;
-	if (width)
-		*width = w;
-
-	return pages;
-}
-
-
-int r600_blit_prepare_copy(struct radeon_device *rdev, unsigned num_gpu_pages,
-			   struct radeon_fence **fence, struct radeon_sa_bo **vb,
-			   struct radeon_semaphore **sem)
-{
-	struct radeon_ring *ring = &rdev->ring[RADEON_RING_TYPE_GFX_INDEX];
-	int r;
-	int ring_size;
-	int num_loops = 0;
-	int dwords_per_loop = rdev->r600_blit.ring_size_per_loop;
-
-	/* num loops */
-	while (num_gpu_pages) {
-		num_gpu_pages -=
-			r600_blit_create_rect(num_gpu_pages, NULL, NULL,
-					      rdev->r600_blit.max_dim);
-		num_loops++;
-	}
-
-	/* 48 bytes for vertex per loop */
-	r = radeon_sa_bo_new(rdev, &rdev->ring_tmp_bo, vb,
-			     (num_loops*48)+256, 256, true);
-	if (r) {
-		return r;
-	}
-
-	r = radeon_semaphore_create(rdev, sem);
-	if (r) {
-		radeon_sa_bo_free(rdev, vb, NULL);
-		return r;
-	}
-
-	/* calculate number of loops correctly */
-	ring_size = num_loops * dwords_per_loop;
-	ring_size += rdev->r600_blit.ring_size_common;
-	r = radeon_ring_lock(rdev, ring, ring_size);
-	if (r) {
-		radeon_sa_bo_free(rdev, vb, NULL);
-		radeon_semaphore_free(rdev, sem, NULL);
-		return r;
-	}
-
-	if (radeon_fence_need_sync(*fence, RADEON_RING_TYPE_GFX_INDEX)) {
-		radeon_semaphore_sync_rings(rdev, *sem, (*fence)->ring,
-					    RADEON_RING_TYPE_GFX_INDEX);
-		radeon_fence_note_sync(*fence, RADEON_RING_TYPE_GFX_INDEX);
-	} else {
-		radeon_semaphore_free(rdev, sem, NULL);
-	}
-
-	rdev->r600_blit.primitives.set_default_state(rdev);
-	rdev->r600_blit.primitives.set_shaders(rdev);
-	return 0;
-}
-
-void r600_blit_done_copy(struct radeon_device *rdev, struct radeon_fence **fence,
-			 struct radeon_sa_bo *vb, struct radeon_semaphore *sem)
-{
-	struct radeon_ring *ring = &rdev->ring[RADEON_RING_TYPE_GFX_INDEX];
-	int r;
-
-	r = radeon_fence_emit(rdev, fence, RADEON_RING_TYPE_GFX_INDEX);
-	if (r) {
-		radeon_ring_unlock_undo(rdev, ring);
-		return;
-	}
-
-	radeon_ring_unlock_commit(rdev, ring);
-	radeon_sa_bo_free(rdev, &vb, *fence);
-	radeon_semaphore_free(rdev, &sem, *fence);
-}
-
-void r600_kms_blit_copy(struct radeon_device *rdev,
-			u64 src_gpu_addr, u64 dst_gpu_addr,
-			unsigned num_gpu_pages,
-			struct radeon_sa_bo *vb)
-{
-	u64 vb_gpu_addr;
-	u32 *vb_cpu_addr;
-
-	DRM_DEBUG("emitting copy %16llx %16llx %d\n",
-		  src_gpu_addr, dst_gpu_addr, num_gpu_pages);
-	vb_cpu_addr = (u32 *)radeon_sa_bo_cpu_addr(vb);
-	vb_gpu_addr = radeon_sa_bo_gpu_addr(vb);
-
-	while (num_gpu_pages) {
-		int w, h;
-		unsigned size_in_bytes;
-		unsigned pages_per_loop =
-			r600_blit_create_rect(num_gpu_pages, &w, &h,
-					      rdev->r600_blit.max_dim);
-
-		size_in_bytes = pages_per_loop * RADEON_GPU_PAGE_SIZE;
-		DRM_DEBUG("rectangle w=%d h=%d\n", w, h);
-
-		vb_cpu_addr[0] = 0;
-		vb_cpu_addr[1] = 0;
-		vb_cpu_addr[2] = 0;
-		vb_cpu_addr[3] = 0;
-
-		vb_cpu_addr[4] = 0;
-		vb_cpu_addr[5] = int2float(h);
-		vb_cpu_addr[6] = 0;
-		vb_cpu_addr[7] = int2float(h);
-
-		vb_cpu_addr[8] = int2float(w);
-		vb_cpu_addr[9] = int2float(h);
-		vb_cpu_addr[10] = int2float(w);
-		vb_cpu_addr[11] = int2float(h);
-
-		rdev->r600_blit.primitives.set_tex_resource(rdev, FMT_8_8_8_8,
-							    w, h, w, src_gpu_addr, size_in_bytes);
-		rdev->r600_blit.primitives.set_render_target(rdev, COLOR_8_8_8_8,
-							     w, h, dst_gpu_addr);
-		rdev->r600_blit.primitives.set_scissors(rdev, 0, 0, w, h);
-		rdev->r600_blit.primitives.set_vtx_resource(rdev, vb_gpu_addr);
-		rdev->r600_blit.primitives.draw_auto(rdev);
-		rdev->r600_blit.primitives.cp_set_surface_sync(rdev,
-				    PACKET3_CB_ACTION_ENA | PACKET3_CB0_DEST_BASE_ENA,
-				    size_in_bytes, dst_gpu_addr);
-
-		vb_cpu_addr += 12;
-		vb_gpu_addr += 4*12;
-		src_gpu_addr += size_in_bytes;
-		dst_gpu_addr += size_in_bytes;
-		num_gpu_pages -= pages_per_loop;
-	}
-}
diff --git a/drivers/gpu/drm/radeon/r600_blit_shaders.h b/drivers/gpu/drm/radeon/r600_blit_shaders.h
index 2f3ce7a75976..f437d36dd98c 100644
--- a/drivers/gpu/drm/radeon/r600_blit_shaders.h
+++ b/drivers/gpu/drm/radeon/r600_blit_shaders.h
@@ -35,5 +35,4 @@ extern const u32 r6xx_default_state[];
 extern const u32 r6xx_ps_size, r6xx_vs_size;
 extern const u32 r6xx_default_size, r7xx_default_size;
 
-__pure uint32_t int2float(uint32_t x);
 #endif
diff --git a/drivers/gpu/drm/radeon/r600_cp.c b/drivers/gpu/drm/radeon/r600_cp.c
index 1c51c08b1fde..d8eb48bff0ed 100644
--- a/drivers/gpu/drm/radeon/r600_cp.c
+++ b/drivers/gpu/drm/radeon/r600_cp.c
@@ -2200,13 +2200,13 @@ int r600_do_init_cp(struct drm_device *dev, drm_radeon_init_t *init,
 	dev_priv->ring.end = ((u32 *) dev_priv->cp_ring->handle
 			      + init->ring_size / sizeof(u32));
 	dev_priv->ring.size = init->ring_size;
-	dev_priv->ring.size_l2qw = drm_order(init->ring_size / 8);
+	dev_priv->ring.size_l2qw = order_base_2(init->ring_size / 8);
 
 	dev_priv->ring.rptr_update = /* init->rptr_update */ 4096;
-	dev_priv->ring.rptr_update_l2qw = drm_order(/* init->rptr_update */ 4096 / 8);
+	dev_priv->ring.rptr_update_l2qw = order_base_2(/* init->rptr_update */ 4096 / 8);
 
 	dev_priv->ring.fetch_size = /* init->fetch_size */ 32;
-	dev_priv->ring.fetch_size_l2ow = drm_order(/* init->fetch_size */ 32 / 16);
+	dev_priv->ring.fetch_size_l2ow = order_base_2(/* init->fetch_size */ 32 / 16);
 
 	dev_priv->ring.tail_mask = (dev_priv->ring.size / sizeof(u32)) - 1;
 
diff --git a/drivers/gpu/drm/radeon/r600_dma.c b/drivers/gpu/drm/radeon/r600_dma.c
new file mode 100644
index 000000000000..3b317456512a
--- /dev/null
+++ b/drivers/gpu/drm/radeon/r600_dma.c
@@ -0,0 +1,497 @@
+/*
+ * Copyright 2013 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: Alex Deucher
+ */
+#include <drm/drmP.h>
+#include "radeon.h"
+#include "radeon_asic.h"
+#include "r600d.h"
+
+u32 r600_gpu_check_soft_reset(struct radeon_device *rdev);
+
+/*
+ * DMA
+ * Starting with R600, the GPU has an asynchronous
+ * DMA engine.  The programming model is very similar
+ * to the 3D engine (ring buffer, IBs, etc.), but the
+ * DMA controller has it's own packet format that is
+ * different form the PM4 format used by the 3D engine.
+ * It supports copying data, writing embedded data,
+ * solid fills, and a number of other things.  It also
+ * has support for tiling/detiling of buffers.
+ */
+
+/**
+ * r600_dma_get_rptr - get the current read pointer
+ *
+ * @rdev: radeon_device pointer
+ * @ring: radeon ring pointer
+ *
+ * Get the current rptr from the hardware (r6xx+).
+ */
+uint32_t r600_dma_get_rptr(struct radeon_device *rdev,
+			   struct radeon_ring *ring)
+{
+	return (radeon_ring_generic_get_rptr(rdev, ring) & 0x3fffc) >> 2;
+}
+
+/**
+ * r600_dma_get_wptr - get the current write pointer
+ *
+ * @rdev: radeon_device pointer
+ * @ring: radeon ring pointer
+ *
+ * Get the current wptr from the hardware (r6xx+).
+ */
+uint32_t r600_dma_get_wptr(struct radeon_device *rdev,
+			   struct radeon_ring *ring)
+{
+	return (RREG32(ring->wptr_reg) & 0x3fffc) >> 2;
+}
+
+/**
+ * r600_dma_set_wptr - commit the write pointer
+ *
+ * @rdev: radeon_device pointer
+ * @ring: radeon ring pointer
+ *
+ * Write the wptr back to the hardware (r6xx+).
+ */
+void r600_dma_set_wptr(struct radeon_device *rdev,
+		       struct radeon_ring *ring)
+{
+	WREG32(ring->wptr_reg, (ring->wptr << 2) & 0x3fffc);
+}
+
+/**
+ * r600_dma_stop - stop the async dma engine
+ *
+ * @rdev: radeon_device pointer
+ *
+ * Stop the async dma engine (r6xx-evergreen).
+ */
+void r600_dma_stop(struct radeon_device *rdev)
+{
+	u32 rb_cntl = RREG32(DMA_RB_CNTL);
+
+	radeon_ttm_set_active_vram_size(rdev, rdev->mc.visible_vram_size);
+
+	rb_cntl &= ~DMA_RB_ENABLE;
+	WREG32(DMA_RB_CNTL, rb_cntl);
+
+	rdev->ring[R600_RING_TYPE_DMA_INDEX].ready = false;
+}
+
+/**
+ * r600_dma_resume - setup and start the async dma engine
+ *
+ * @rdev: radeon_device pointer
+ *
+ * Set up the DMA ring buffer and enable it. (r6xx-evergreen).
+ * Returns 0 for success, error for failure.
+ */
+int r600_dma_resume(struct radeon_device *rdev)
+{
+	struct radeon_ring *ring = &rdev->ring[R600_RING_TYPE_DMA_INDEX];
+	u32 rb_cntl, dma_cntl, ib_cntl;
+	u32 rb_bufsz;
+	int r;
+
+	/* Reset dma */
+	if (rdev->family >= CHIP_RV770)
+		WREG32(SRBM_SOFT_RESET, RV770_SOFT_RESET_DMA);
+	else
+		WREG32(SRBM_SOFT_RESET, SOFT_RESET_DMA);
+	RREG32(SRBM_SOFT_RESET);
+	udelay(50);
+	WREG32(SRBM_SOFT_RESET, 0);
+
+	WREG32(DMA_SEM_INCOMPLETE_TIMER_CNTL, 0);
+	WREG32(DMA_SEM_WAIT_FAIL_TIMER_CNTL, 0);
+
+	/* Set ring buffer size in dwords */
+	rb_bufsz = order_base_2(ring->ring_size / 4);
+	rb_cntl = rb_bufsz << 1;
+#ifdef __BIG_ENDIAN
+	rb_cntl |= DMA_RB_SWAP_ENABLE | DMA_RPTR_WRITEBACK_SWAP_ENABLE;
+#endif
+	WREG32(DMA_RB_CNTL, rb_cntl);
+
+	/* Initialize the ring buffer's read and write pointers */
+	WREG32(DMA_RB_RPTR, 0);
+	WREG32(DMA_RB_WPTR, 0);
+
+	/* set the wb address whether it's enabled or not */
+	WREG32(DMA_RB_RPTR_ADDR_HI,
+	       upper_32_bits(rdev->wb.gpu_addr + R600_WB_DMA_RPTR_OFFSET) & 0xFF);
+	WREG32(DMA_RB_RPTR_ADDR_LO,
+	       ((rdev->wb.gpu_addr + R600_WB_DMA_RPTR_OFFSET) & 0xFFFFFFFC));
+
+	if (rdev->wb.enabled)
+		rb_cntl |= DMA_RPTR_WRITEBACK_ENABLE;
+
+	WREG32(DMA_RB_BASE, ring->gpu_addr >> 8);
+
+	/* enable DMA IBs */
+	ib_cntl = DMA_IB_ENABLE;
+#ifdef __BIG_ENDIAN
+	ib_cntl |= DMA_IB_SWAP_ENABLE;
+#endif
+	WREG32(DMA_IB_CNTL, ib_cntl);
+
+	dma_cntl = RREG32(DMA_CNTL);
+	dma_cntl &= ~CTXEMPTY_INT_ENABLE;
+	WREG32(DMA_CNTL, dma_cntl);
+
+	if (rdev->family >= CHIP_RV770)
+		WREG32(DMA_MODE, 1);
+
+	ring->wptr = 0;
+	WREG32(DMA_RB_WPTR, ring->wptr << 2);
+
+	ring->rptr = RREG32(DMA_RB_RPTR) >> 2;
+
+	WREG32(DMA_RB_CNTL, rb_cntl | DMA_RB_ENABLE);
+
+	ring->ready = true;
+
+	r = radeon_ring_test(rdev, R600_RING_TYPE_DMA_INDEX, ring);
+	if (r) {
+		ring->ready = false;
+		return r;
+	}
+
+	radeon_ttm_set_active_vram_size(rdev, rdev->mc.real_vram_size);
+
+	return 0;
+}
+
+/**
+ * r600_dma_fini - tear down the async dma engine
+ *
+ * @rdev: radeon_device pointer
+ *
+ * Stop the async dma engine and free the ring (r6xx-evergreen).
+ */
+void r600_dma_fini(struct radeon_device *rdev)
+{
+	r600_dma_stop(rdev);
+	radeon_ring_fini(rdev, &rdev->ring[R600_RING_TYPE_DMA_INDEX]);
+}
+
+/**
+ * r600_dma_is_lockup - Check if the DMA engine is locked up
+ *
+ * @rdev: radeon_device pointer
+ * @ring: radeon_ring structure holding ring information
+ *
+ * Check if the async DMA engine is locked up.
+ * Returns true if the engine appears to be locked up, false if not.
+ */
+bool r600_dma_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
+{
+	u32 reset_mask = r600_gpu_check_soft_reset(rdev);
+
+	if (!(reset_mask & RADEON_RESET_DMA)) {
+		radeon_ring_lockup_update(ring);
+		return false;
+	}
+	/* force ring activities */
+	radeon_ring_force_activity(rdev, ring);
+	return radeon_ring_test_lockup(rdev, ring);
+}
+
+
+/**
+ * r600_dma_ring_test - simple async dma engine test
+ *
+ * @rdev: radeon_device pointer
+ * @ring: radeon_ring structure holding ring information
+ *
+ * Test the DMA engine by writing using it to write an
+ * value to memory. (r6xx-SI).
+ * Returns 0 for success, error for failure.
+ */
+int r600_dma_ring_test(struct radeon_device *rdev,
+		       struct radeon_ring *ring)
+{
+	unsigned i;
+	int r;
+	void __iomem *ptr = (void *)rdev->vram_scratch.ptr;
+	u32 tmp;
+
+	if (!ptr) {
+		DRM_ERROR("invalid vram scratch pointer\n");
+		return -EINVAL;
+	}
+
+	tmp = 0xCAFEDEAD;
+	writel(tmp, ptr);
+
+	r = radeon_ring_lock(rdev, ring, 4);
+	if (r) {
+		DRM_ERROR("radeon: dma failed to lock ring %d (%d).\n", ring->idx, r);
+		return r;
+	}
+	radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_WRITE, 0, 0, 1));
+	radeon_ring_write(ring, rdev->vram_scratch.gpu_addr & 0xfffffffc);
+	radeon_ring_write(ring, upper_32_bits(rdev->vram_scratch.gpu_addr) & 0xff);
+	radeon_ring_write(ring, 0xDEADBEEF);
+	radeon_ring_unlock_commit(rdev, ring);
+
+	for (i = 0; i < rdev->usec_timeout; i++) {
+		tmp = readl(ptr);
+		if (tmp == 0xDEADBEEF)
+			break;
+		DRM_UDELAY(1);
+	}
+
+	if (i < rdev->usec_timeout) {
+		DRM_INFO("ring test on %d succeeded in %d usecs\n", ring->idx, i);
+	} else {
+		DRM_ERROR("radeon: ring %d test failed (0x%08X)\n",
+			  ring->idx, tmp);
+		r = -EINVAL;
+	}
+	return r;
+}
+
+/**
+ * r600_dma_fence_ring_emit - emit a fence on the DMA ring
+ *
+ * @rdev: radeon_device pointer
+ * @fence: radeon fence object
+ *
+ * Add a DMA fence packet to the ring to write
+ * the fence seq number and DMA trap packet to generate
+ * an interrupt if needed (r6xx-r7xx).
+ */
+void r600_dma_fence_ring_emit(struct radeon_device *rdev,
+			      struct radeon_fence *fence)
+{
+	struct radeon_ring *ring = &rdev->ring[fence->ring];
+	u64 addr = rdev->fence_drv[fence->ring].gpu_addr;
+
+	/* write the fence */
+	radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_FENCE, 0, 0, 0));
+	radeon_ring_write(ring, addr & 0xfffffffc);
+	radeon_ring_write(ring, (upper_32_bits(addr) & 0xff));
+	radeon_ring_write(ring, lower_32_bits(fence->seq));
+	/* generate an interrupt */
+	radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_TRAP, 0, 0, 0));
+}
+
+/**
+ * r600_dma_semaphore_ring_emit - emit a semaphore on the dma ring
+ *
+ * @rdev: radeon_device pointer
+ * @ring: radeon_ring structure holding ring information
+ * @semaphore: radeon semaphore object
+ * @emit_wait: wait or signal semaphore
+ *
+ * Add a DMA semaphore packet to the ring wait on or signal
+ * other rings (r6xx-SI).
+ */
+void r600_dma_semaphore_ring_emit(struct radeon_device *rdev,
+				  struct radeon_ring *ring,
+				  struct radeon_semaphore *semaphore,
+				  bool emit_wait)
+{
+	u64 addr = semaphore->gpu_addr;
+	u32 s = emit_wait ? 0 : 1;
+
+	radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_SEMAPHORE, 0, s, 0));
+	radeon_ring_write(ring, addr & 0xfffffffc);
+	radeon_ring_write(ring, upper_32_bits(addr) & 0xff);
+}
+
+/**
+ * r600_dma_ib_test - test an IB on the DMA engine
+ *
+ * @rdev: radeon_device pointer
+ * @ring: radeon_ring structure holding ring information
+ *
+ * Test a simple IB in the DMA ring (r6xx-SI).
+ * Returns 0 on success, error on failure.
+ */
+int r600_dma_ib_test(struct radeon_device *rdev, struct radeon_ring *ring)
+{
+	struct radeon_ib ib;
+	unsigned i;
+	int r;
+	void __iomem *ptr = (void *)rdev->vram_scratch.ptr;
+	u32 tmp = 0;
+
+	if (!ptr) {
+		DRM_ERROR("invalid vram scratch pointer\n");
+		return -EINVAL;
+	}
+
+	tmp = 0xCAFEDEAD;
+	writel(tmp, ptr);
+
+	r = radeon_ib_get(rdev, ring->idx, &ib, NULL, 256);
+	if (r) {
+		DRM_ERROR("radeon: failed to get ib (%d).\n", r);
+		return r;
+	}
+
+	ib.ptr[0] = DMA_PACKET(DMA_PACKET_WRITE, 0, 0, 1);
+	ib.ptr[1] = rdev->vram_scratch.gpu_addr & 0xfffffffc;
+	ib.ptr[2] = upper_32_bits(rdev->vram_scratch.gpu_addr) & 0xff;
+	ib.ptr[3] = 0xDEADBEEF;
+	ib.length_dw = 4;
+
+	r = radeon_ib_schedule(rdev, &ib, NULL);
+	if (r) {
+		radeon_ib_free(rdev, &ib);
+		DRM_ERROR("radeon: failed to schedule ib (%d).\n", r);
+		return r;
+	}
+	r = radeon_fence_wait(ib.fence, false);
+	if (r) {
+		DRM_ERROR("radeon: fence wait failed (%d).\n", r);
+		return r;
+	}
+	for (i = 0; i < rdev->usec_timeout; i++) {
+		tmp = readl(ptr);
+		if (tmp == 0xDEADBEEF)
+			break;
+		DRM_UDELAY(1);
+	}
+	if (i < rdev->usec_timeout) {
+		DRM_INFO("ib test on ring %d succeeded in %u usecs\n", ib.fence->ring, i);
+	} else {
+		DRM_ERROR("radeon: ib test failed (0x%08X)\n", tmp);
+		r = -EINVAL;
+	}
+	radeon_ib_free(rdev, &ib);
+	return r;
+}
+
+/**
+ * r600_dma_ring_ib_execute - Schedule an IB on the DMA engine
+ *
+ * @rdev: radeon_device pointer
+ * @ib: IB object to schedule
+ *
+ * Schedule an IB in the DMA ring (r6xx-r7xx).
+ */
+void r600_dma_ring_ib_execute(struct radeon_device *rdev, struct radeon_ib *ib)
+{
+	struct radeon_ring *ring = &rdev->ring[ib->ring];
+
+	if (rdev->wb.enabled) {
+		u32 next_rptr = ring->wptr + 4;
+		while ((next_rptr & 7) != 5)
+			next_rptr++;
+		next_rptr += 3;
+		radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_WRITE, 0, 0, 1));
+		radeon_ring_write(ring, ring->next_rptr_gpu_addr & 0xfffffffc);
+		radeon_ring_write(ring, upper_32_bits(ring->next_rptr_gpu_addr) & 0xff);
+		radeon_ring_write(ring, next_rptr);
+	}
+
+	/* The indirect buffer packet must end on an 8 DW boundary in the DMA ring.
+	 * Pad as necessary with NOPs.
+	 */
+	while ((ring->wptr & 7) != 5)
+		radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_NOP, 0, 0, 0));
+	radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_INDIRECT_BUFFER, 0, 0, 0));
+	radeon_ring_write(ring, (ib->gpu_addr & 0xFFFFFFE0));
+	radeon_ring_write(ring, (ib->length_dw << 16) | (upper_32_bits(ib->gpu_addr) & 0xFF));
+
+}
+
+/**
+ * r600_copy_dma - copy pages using the DMA engine
+ *
+ * @rdev: radeon_device pointer
+ * @src_offset: src GPU address
+ * @dst_offset: dst GPU address
+ * @num_gpu_pages: number of GPU pages to xfer
+ * @fence: radeon fence object
+ *
+ * Copy GPU paging using the DMA engine (r6xx).
+ * Used by the radeon ttm implementation to move pages if
+ * registered as the asic copy callback.
+ */
+int r600_copy_dma(struct radeon_device *rdev,
+		  uint64_t src_offset, uint64_t dst_offset,
+		  unsigned num_gpu_pages,
+		  struct radeon_fence **fence)
+{
+	struct radeon_semaphore *sem = NULL;
+	int ring_index = rdev->asic->copy.dma_ring_index;
+	struct radeon_ring *ring = &rdev->ring[ring_index];
+	u32 size_in_dw, cur_size_in_dw;
+	int i, num_loops;
+	int r = 0;
+
+	r = radeon_semaphore_create(rdev, &sem);
+	if (r) {
+		DRM_ERROR("radeon: moving bo (%d).\n", r);
+		return r;
+	}
+
+	size_in_dw = (num_gpu_pages << RADEON_GPU_PAGE_SHIFT) / 4;
+	num_loops = DIV_ROUND_UP(size_in_dw, 0xFFFE);
+	r = radeon_ring_lock(rdev, ring, num_loops * 4 + 8);
+	if (r) {
+		DRM_ERROR("radeon: moving bo (%d).\n", r);
+		radeon_semaphore_free(rdev, &sem, NULL);
+		return r;
+	}
+
+	if (radeon_fence_need_sync(*fence, ring->idx)) {
+		radeon_semaphore_sync_rings(rdev, sem, (*fence)->ring,
+					    ring->idx);
+		radeon_fence_note_sync(*fence, ring->idx);
+	} else {
+		radeon_semaphore_free(rdev, &sem, NULL);
+	}
+
+	for (i = 0; i < num_loops; i++) {
+		cur_size_in_dw = size_in_dw;
+		if (cur_size_in_dw > 0xFFFE)
+			cur_size_in_dw = 0xFFFE;
+		size_in_dw -= cur_size_in_dw;
+		radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_COPY, 0, 0, cur_size_in_dw));
+		radeon_ring_write(ring, dst_offset & 0xfffffffc);
+		radeon_ring_write(ring, src_offset & 0xfffffffc);
+		radeon_ring_write(ring, (((upper_32_bits(dst_offset) & 0xff) << 16) |
+					 (upper_32_bits(src_offset) & 0xff)));
+		src_offset += cur_size_in_dw * 4;
+		dst_offset += cur_size_in_dw * 4;
+	}
+
+	r = radeon_fence_emit(rdev, fence, ring->idx);
+	if (r) {
+		radeon_ring_unlock_undo(rdev, ring);
+		return r;
+	}
+
+	radeon_ring_unlock_commit(rdev, ring);
+	radeon_semaphore_free(rdev, &sem, *fence);
+
+	return r;
+}
diff --git a/drivers/gpu/drm/radeon/r600_dpm.c b/drivers/gpu/drm/radeon/r600_dpm.c
index e5c860f4ccbe..5513d8f06252 100644
--- a/drivers/gpu/drm/radeon/r600_dpm.c
+++ b/drivers/gpu/drm/radeon/r600_dpm.c
@@ -174,6 +174,24 @@ u32 r600_dpm_get_vblank_time(struct radeon_device *rdev)
 	return vblank_time_us;
 }
 
+u32 r600_dpm_get_vrefresh(struct radeon_device *rdev)
+{
+	struct drm_device *dev = rdev->ddev;
+	struct drm_crtc *crtc;
+	struct radeon_crtc *radeon_crtc;
+	u32 vrefresh = 0;
+
+	list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
+		radeon_crtc = to_radeon_crtc(crtc);
+		if (crtc->enabled && radeon_crtc->enabled && radeon_crtc->hw_mode.clock) {
+			vrefresh = radeon_crtc->hw_mode.vrefresh;
+			break;
+		}
+	}
+
+	return vrefresh;
+}
+
 void r600_calculate_u_and_p(u32 i, u32 r_c, u32 p_b,
 			    u32 *p, u32 *u)
 {
@@ -745,6 +763,8 @@ bool r600_is_internal_thermal_sensor(enum radeon_int_thermal_type sensor)
 	case THERMAL_TYPE_SUMO:
 	case THERMAL_TYPE_NI:
 	case THERMAL_TYPE_SI:
+	case THERMAL_TYPE_CI:
+	case THERMAL_TYPE_KV:
 		return true;
 	case THERMAL_TYPE_ADT7473_WITH_INTERNAL:
 	case THERMAL_TYPE_EMC2103_WITH_INTERNAL:
@@ -779,15 +799,19 @@ static int r600_parse_clk_voltage_dep_table(struct radeon_clock_voltage_dependen
 	u32 size = atom_table->ucNumEntries *
 		sizeof(struct radeon_clock_voltage_dependency_entry);
 	int i;
+	ATOM_PPLIB_Clock_Voltage_Dependency_Record *entry;
 
 	radeon_table->entries = kzalloc(size, GFP_KERNEL);
 	if (!radeon_table->entries)
 		return -ENOMEM;
 
+	entry = &atom_table->entries[0];
 	for (i = 0; i < atom_table->ucNumEntries; i++) {
-		radeon_table->entries[i].clk = le16_to_cpu(atom_table->entries[i].usClockLow) |
-			(atom_table->entries[i].ucClockHigh << 16);
-		radeon_table->entries[i].v = le16_to_cpu(atom_table->entries[i].usVoltage);
+		radeon_table->entries[i].clk = le16_to_cpu(entry->usClockLow) |
+			(entry->ucClockHigh << 16);
+		radeon_table->entries[i].v = le16_to_cpu(entry->usVoltage);
+		entry = (ATOM_PPLIB_Clock_Voltage_Dependency_Record *)
+			((u8 *)entry + sizeof(ATOM_PPLIB_Clock_Voltage_Dependency_Record));
 	}
 	radeon_table->count = atom_table->ucNumEntries;
 
@@ -875,6 +899,19 @@ int r600_parse_extended_power_table(struct radeon_device *rdev)
 				return ret;
 			}
 		}
+		if (power_info->pplib4.usMvddDependencyOnMCLKOffset) {
+			dep_table = (ATOM_PPLIB_Clock_Voltage_Dependency_Table *)
+				(mode_info->atom_context->bios + data_offset +
+				 le16_to_cpu(power_info->pplib4.usMvddDependencyOnMCLKOffset));
+			ret = r600_parse_clk_voltage_dep_table(&rdev->pm.dpm.dyn_state.mvdd_dependency_on_mclk,
+							       dep_table);
+			if (ret) {
+				kfree(rdev->pm.dpm.dyn_state.vddc_dependency_on_sclk.entries);
+				kfree(rdev->pm.dpm.dyn_state.vddci_dependency_on_mclk.entries);
+				kfree(rdev->pm.dpm.dyn_state.vddc_dependency_on_mclk.entries);
+				return ret;
+			}
+		}
 		if (power_info->pplib4.usMaxClockVoltageOnDCOffset) {
 			ATOM_PPLIB_Clock_Voltage_Limit_Table *clk_v =
 				(ATOM_PPLIB_Clock_Voltage_Limit_Table *)
@@ -898,27 +935,27 @@ int r600_parse_extended_power_table(struct radeon_device *rdev)
 				(ATOM_PPLIB_PhaseSheddingLimits_Table *)
 				(mode_info->atom_context->bios + data_offset +
 				 le16_to_cpu(power_info->pplib4.usVddcPhaseShedLimitsTableOffset));
+			ATOM_PPLIB_PhaseSheddingLimits_Record *entry;
 
 			rdev->pm.dpm.dyn_state.phase_shedding_limits_table.entries =
 				kzalloc(psl->ucNumEntries *
 					sizeof(struct radeon_phase_shedding_limits_entry),
 					GFP_KERNEL);
 			if (!rdev->pm.dpm.dyn_state.phase_shedding_limits_table.entries) {
-				kfree(rdev->pm.dpm.dyn_state.vddc_dependency_on_sclk.entries);
-				kfree(rdev->pm.dpm.dyn_state.vddci_dependency_on_mclk.entries);
-				kfree(rdev->pm.dpm.dyn_state.vddc_dependency_on_mclk.entries);
+				r600_free_extended_power_table(rdev);
 				return -ENOMEM;
 			}
 
+			entry = &psl->entries[0];
 			for (i = 0; i < psl->ucNumEntries; i++) {
 				rdev->pm.dpm.dyn_state.phase_shedding_limits_table.entries[i].sclk =
-					le16_to_cpu(psl->entries[i].usSclkLow) |
-					(psl->entries[i].ucSclkHigh << 16);
+					le16_to_cpu(entry->usSclkLow) | (entry->ucSclkHigh << 16);
 				rdev->pm.dpm.dyn_state.phase_shedding_limits_table.entries[i].mclk =
-					le16_to_cpu(psl->entries[i].usMclkLow) |
-					(psl->entries[i].ucMclkHigh << 16);
+					le16_to_cpu(entry->usMclkLow) | (entry->ucMclkHigh << 16);
 				rdev->pm.dpm.dyn_state.phase_shedding_limits_table.entries[i].voltage =
-					le16_to_cpu(psl->entries[i].usVoltage);
+					le16_to_cpu(entry->usVoltage);
+				entry = (ATOM_PPLIB_PhaseSheddingLimits_Record *)
+					((u8 *)entry + sizeof(ATOM_PPLIB_PhaseSheddingLimits_Record));
 			}
 			rdev->pm.dpm.dyn_state.phase_shedding_limits_table.count =
 				psl->ucNumEntries;
@@ -945,30 +982,140 @@ int r600_parse_extended_power_table(struct radeon_device *rdev)
 				(ATOM_PPLIB_CAC_Leakage_Table *)
 				(mode_info->atom_context->bios + data_offset +
 				 le16_to_cpu(power_info->pplib5.usCACLeakageTableOffset));
+			ATOM_PPLIB_CAC_Leakage_Record *entry;
 			u32 size = cac_table->ucNumEntries * sizeof(struct radeon_cac_leakage_table);
 			rdev->pm.dpm.dyn_state.cac_leakage_table.entries = kzalloc(size, GFP_KERNEL);
 			if (!rdev->pm.dpm.dyn_state.cac_leakage_table.entries) {
-				kfree(rdev->pm.dpm.dyn_state.vddc_dependency_on_sclk.entries);
-				kfree(rdev->pm.dpm.dyn_state.vddci_dependency_on_mclk.entries);
-				kfree(rdev->pm.dpm.dyn_state.vddc_dependency_on_mclk.entries);
+				r600_free_extended_power_table(rdev);
 				return -ENOMEM;
 			}
+			entry = &cac_table->entries[0];
 			for (i = 0; i < cac_table->ucNumEntries; i++) {
-				rdev->pm.dpm.dyn_state.cac_leakage_table.entries[i].vddc =
-					le16_to_cpu(cac_table->entries[i].usVddc);
-				rdev->pm.dpm.dyn_state.cac_leakage_table.entries[i].leakage =
-					le32_to_cpu(cac_table->entries[i].ulLeakageValue);
+				if (rdev->pm.dpm.platform_caps & ATOM_PP_PLATFORM_CAP_EVV) {
+					rdev->pm.dpm.dyn_state.cac_leakage_table.entries[i].vddc1 =
+						le16_to_cpu(entry->usVddc1);
+					rdev->pm.dpm.dyn_state.cac_leakage_table.entries[i].vddc2 =
+						le16_to_cpu(entry->usVddc2);
+					rdev->pm.dpm.dyn_state.cac_leakage_table.entries[i].vddc3 =
+						le16_to_cpu(entry->usVddc3);
+				} else {
+					rdev->pm.dpm.dyn_state.cac_leakage_table.entries[i].vddc =
+						le16_to_cpu(entry->usVddc);
+					rdev->pm.dpm.dyn_state.cac_leakage_table.entries[i].leakage =
+						le32_to_cpu(entry->ulLeakageValue);
+				}
+				entry = (ATOM_PPLIB_CAC_Leakage_Record *)
+					((u8 *)entry + sizeof(ATOM_PPLIB_CAC_Leakage_Record));
 			}
 			rdev->pm.dpm.dyn_state.cac_leakage_table.count = cac_table->ucNumEntries;
 		}
 	}
 
-	/* ppm table */
+	/* ext tables */
 	if (le16_to_cpu(power_info->pplib.usTableSize) >=
 	    sizeof(struct _ATOM_PPLIB_POWERPLAYTABLE3)) {
 		ATOM_PPLIB_EXTENDEDHEADER *ext_hdr = (ATOM_PPLIB_EXTENDEDHEADER *)
 			(mode_info->atom_context->bios + data_offset +
 			 le16_to_cpu(power_info->pplib3.usExtendendedHeaderOffset));
+		if ((le16_to_cpu(ext_hdr->usSize) >= SIZE_OF_ATOM_PPLIB_EXTENDEDHEADER_V2) &&
+			ext_hdr->usVCETableOffset) {
+			VCEClockInfoArray *array = (VCEClockInfoArray *)
+				(mode_info->atom_context->bios + data_offset +
+                                 le16_to_cpu(ext_hdr->usVCETableOffset) + 1);
+			ATOM_PPLIB_VCE_Clock_Voltage_Limit_Table *limits =
+				(ATOM_PPLIB_VCE_Clock_Voltage_Limit_Table *)
+				(mode_info->atom_context->bios + data_offset +
+				 le16_to_cpu(ext_hdr->usVCETableOffset) + 1 +
+				 1 + array->ucNumEntries * sizeof(VCEClockInfo));
+			ATOM_PPLIB_VCE_Clock_Voltage_Limit_Record *entry;
+			u32 size = limits->numEntries *
+				sizeof(struct radeon_vce_clock_voltage_dependency_entry);
+			rdev->pm.dpm.dyn_state.vce_clock_voltage_dependency_table.entries =
+				kzalloc(size, GFP_KERNEL);
+			if (!rdev->pm.dpm.dyn_state.vce_clock_voltage_dependency_table.entries) {
+				r600_free_extended_power_table(rdev);
+				return -ENOMEM;
+			}
+			rdev->pm.dpm.dyn_state.vce_clock_voltage_dependency_table.count =
+				limits->numEntries;
+			entry = &limits->entries[0];
+			for (i = 0; i < limits->numEntries; i++) {
+				VCEClockInfo *vce_clk = (VCEClockInfo *)
+					((u8 *)&array->entries[0] +
+					 (entry->ucVCEClockInfoIndex * sizeof(VCEClockInfo)));
+				rdev->pm.dpm.dyn_state.vce_clock_voltage_dependency_table.entries[i].evclk =
+					le16_to_cpu(vce_clk->usEVClkLow) | (vce_clk->ucEVClkHigh << 16);
+				rdev->pm.dpm.dyn_state.vce_clock_voltage_dependency_table.entries[i].ecclk =
+					le16_to_cpu(vce_clk->usECClkLow) | (vce_clk->ucECClkHigh << 16);
+				rdev->pm.dpm.dyn_state.vce_clock_voltage_dependency_table.entries[i].v =
+					le16_to_cpu(entry->usVoltage);
+				entry = (ATOM_PPLIB_VCE_Clock_Voltage_Limit_Record *)
+					((u8 *)entry + sizeof(ATOM_PPLIB_VCE_Clock_Voltage_Limit_Record));
+			}
+		}
+		if ((le16_to_cpu(ext_hdr->usSize) >= SIZE_OF_ATOM_PPLIB_EXTENDEDHEADER_V3) &&
+			ext_hdr->usUVDTableOffset) {
+			UVDClockInfoArray *array = (UVDClockInfoArray *)
+				(mode_info->atom_context->bios + data_offset +
+				 le16_to_cpu(ext_hdr->usUVDTableOffset) + 1);
+			ATOM_PPLIB_UVD_Clock_Voltage_Limit_Table *limits =
+				(ATOM_PPLIB_UVD_Clock_Voltage_Limit_Table *)
+				(mode_info->atom_context->bios + data_offset +
+				 le16_to_cpu(ext_hdr->usUVDTableOffset) + 1 +
+				 1 + (array->ucNumEntries * sizeof (UVDClockInfo)));
+			ATOM_PPLIB_UVD_Clock_Voltage_Limit_Record *entry;
+			u32 size = limits->numEntries *
+				sizeof(struct radeon_uvd_clock_voltage_dependency_entry);
+			rdev->pm.dpm.dyn_state.uvd_clock_voltage_dependency_table.entries =
+				kzalloc(size, GFP_KERNEL);
+			if (!rdev->pm.dpm.dyn_state.uvd_clock_voltage_dependency_table.entries) {
+				r600_free_extended_power_table(rdev);
+				return -ENOMEM;
+			}
+			rdev->pm.dpm.dyn_state.uvd_clock_voltage_dependency_table.count =
+				limits->numEntries;
+			entry = &limits->entries[0];
+			for (i = 0; i < limits->numEntries; i++) {
+				UVDClockInfo *uvd_clk = (UVDClockInfo *)
+					((u8 *)&array->entries[0] +
+					 (entry->ucUVDClockInfoIndex * sizeof(UVDClockInfo)));
+				rdev->pm.dpm.dyn_state.uvd_clock_voltage_dependency_table.entries[i].vclk =
+					le16_to_cpu(uvd_clk->usVClkLow) | (uvd_clk->ucVClkHigh << 16);
+				rdev->pm.dpm.dyn_state.uvd_clock_voltage_dependency_table.entries[i].dclk =
+					le16_to_cpu(uvd_clk->usDClkLow) | (uvd_clk->ucDClkHigh << 16);
+				rdev->pm.dpm.dyn_state.uvd_clock_voltage_dependency_table.entries[i].v =
+					le16_to_cpu(entry->usVoltage);
+				entry = (ATOM_PPLIB_UVD_Clock_Voltage_Limit_Record *)
+					((u8 *)entry + sizeof(ATOM_PPLIB_UVD_Clock_Voltage_Limit_Record));
+			}
+		}
+		if ((le16_to_cpu(ext_hdr->usSize) >= SIZE_OF_ATOM_PPLIB_EXTENDEDHEADER_V4) &&
+			ext_hdr->usSAMUTableOffset) {
+			ATOM_PPLIB_SAMClk_Voltage_Limit_Table *limits =
+				(ATOM_PPLIB_SAMClk_Voltage_Limit_Table *)
+				(mode_info->atom_context->bios + data_offset +
+				 le16_to_cpu(ext_hdr->usSAMUTableOffset) + 1);
+			ATOM_PPLIB_SAMClk_Voltage_Limit_Record *entry;
+			u32 size = limits->numEntries *
+				sizeof(struct radeon_clock_voltage_dependency_entry);
+			rdev->pm.dpm.dyn_state.samu_clock_voltage_dependency_table.entries =
+				kzalloc(size, GFP_KERNEL);
+			if (!rdev->pm.dpm.dyn_state.samu_clock_voltage_dependency_table.entries) {
+				r600_free_extended_power_table(rdev);
+				return -ENOMEM;
+			}
+			rdev->pm.dpm.dyn_state.samu_clock_voltage_dependency_table.count =
+				limits->numEntries;
+			entry = &limits->entries[0];
+			for (i = 0; i < limits->numEntries; i++) {
+				rdev->pm.dpm.dyn_state.samu_clock_voltage_dependency_table.entries[i].clk =
+					le16_to_cpu(entry->usSAMClockLow) | (entry->ucSAMClockHigh << 16);
+				rdev->pm.dpm.dyn_state.samu_clock_voltage_dependency_table.entries[i].v =
+					le16_to_cpu(entry->usVoltage);
+				entry = (ATOM_PPLIB_SAMClk_Voltage_Limit_Record *)
+					((u8 *)entry + sizeof(ATOM_PPLIB_SAMClk_Voltage_Limit_Record));
+			}
+		}
 		if ((le16_to_cpu(ext_hdr->usSize) >= SIZE_OF_ATOM_PPLIB_EXTENDEDHEADER_V5) &&
 		    ext_hdr->usPPMTableOffset) {
 			ATOM_PPLIB_PPM_Table *ppm = (ATOM_PPLIB_PPM_Table *)
@@ -977,10 +1124,7 @@ int r600_parse_extended_power_table(struct radeon_device *rdev)
 			rdev->pm.dpm.dyn_state.ppm_table =
 				kzalloc(sizeof(struct radeon_ppm_table), GFP_KERNEL);
 			if (!rdev->pm.dpm.dyn_state.ppm_table) {
-				kfree(rdev->pm.dpm.dyn_state.vddc_dependency_on_sclk.entries);
-				kfree(rdev->pm.dpm.dyn_state.vddci_dependency_on_mclk.entries);
-				kfree(rdev->pm.dpm.dyn_state.vddc_dependency_on_mclk.entries);
-				kfree(rdev->pm.dpm.dyn_state.cac_leakage_table.entries);
+				r600_free_extended_power_table(rdev);
 				return -ENOMEM;
 			}
 			rdev->pm.dpm.dyn_state.ppm_table->ppm_design = ppm->ucPpmDesign;
@@ -1003,6 +1147,71 @@ int r600_parse_extended_power_table(struct radeon_device *rdev)
 			rdev->pm.dpm.dyn_state.ppm_table->tj_max =
 				le32_to_cpu(ppm->ulTjmax);
 		}
+		if ((le16_to_cpu(ext_hdr->usSize) >= SIZE_OF_ATOM_PPLIB_EXTENDEDHEADER_V6) &&
+			ext_hdr->usACPTableOffset) {
+			ATOM_PPLIB_ACPClk_Voltage_Limit_Table *limits =
+				(ATOM_PPLIB_ACPClk_Voltage_Limit_Table *)
+				(mode_info->atom_context->bios + data_offset +
+				 le16_to_cpu(ext_hdr->usACPTableOffset) + 1);
+			ATOM_PPLIB_ACPClk_Voltage_Limit_Record *entry;
+			u32 size = limits->numEntries *
+				sizeof(struct radeon_clock_voltage_dependency_entry);
+			rdev->pm.dpm.dyn_state.acp_clock_voltage_dependency_table.entries =
+				kzalloc(size, GFP_KERNEL);
+			if (!rdev->pm.dpm.dyn_state.acp_clock_voltage_dependency_table.entries) {
+				r600_free_extended_power_table(rdev);
+				return -ENOMEM;
+			}
+			rdev->pm.dpm.dyn_state.acp_clock_voltage_dependency_table.count =
+				limits->numEntries;
+			entry = &limits->entries[0];
+			for (i = 0; i < limits->numEntries; i++) {
+				rdev->pm.dpm.dyn_state.acp_clock_voltage_dependency_table.entries[i].clk =
+					le16_to_cpu(entry->usACPClockLow) | (entry->ucACPClockHigh << 16);
+				rdev->pm.dpm.dyn_state.acp_clock_voltage_dependency_table.entries[i].v =
+					le16_to_cpu(entry->usVoltage);
+				entry = (ATOM_PPLIB_ACPClk_Voltage_Limit_Record *)
+					((u8 *)entry + sizeof(ATOM_PPLIB_ACPClk_Voltage_Limit_Record));
+			}
+		}
+		if ((le16_to_cpu(ext_hdr->usSize) >= SIZE_OF_ATOM_PPLIB_EXTENDEDHEADER_V7) &&
+			ext_hdr->usPowerTuneTableOffset) {
+			u8 rev = *(u8 *)(mode_info->atom_context->bios + data_offset +
+					 le16_to_cpu(ext_hdr->usPowerTuneTableOffset));
+			ATOM_PowerTune_Table *pt;
+			rdev->pm.dpm.dyn_state.cac_tdp_table =
+				kzalloc(sizeof(struct radeon_cac_tdp_table), GFP_KERNEL);
+			if (!rdev->pm.dpm.dyn_state.cac_tdp_table) {
+				r600_free_extended_power_table(rdev);
+				return -ENOMEM;
+			}
+			if (rev > 0) {
+				ATOM_PPLIB_POWERTUNE_Table_V1 *ppt = (ATOM_PPLIB_POWERTUNE_Table_V1 *)
+					(mode_info->atom_context->bios + data_offset +
+					 le16_to_cpu(ext_hdr->usPowerTuneTableOffset));
+				rdev->pm.dpm.dyn_state.cac_tdp_table->maximum_power_delivery_limit =
+					ppt->usMaximumPowerDeliveryLimit;
+				pt = &ppt->power_tune_table;
+			} else {
+				ATOM_PPLIB_POWERTUNE_Table *ppt = (ATOM_PPLIB_POWERTUNE_Table *)
+					(mode_info->atom_context->bios + data_offset +
+					 le16_to_cpu(ext_hdr->usPowerTuneTableOffset));
+				rdev->pm.dpm.dyn_state.cac_tdp_table->maximum_power_delivery_limit = 255;
+				pt = &ppt->power_tune_table;
+			}
+			rdev->pm.dpm.dyn_state.cac_tdp_table->tdp = le16_to_cpu(pt->usTDP);
+			rdev->pm.dpm.dyn_state.cac_tdp_table->configurable_tdp =
+				le16_to_cpu(pt->usConfigurableTDP);
+			rdev->pm.dpm.dyn_state.cac_tdp_table->tdc = le16_to_cpu(pt->usTDC);
+			rdev->pm.dpm.dyn_state.cac_tdp_table->battery_power_limit =
+				le16_to_cpu(pt->usBatteryPowerLimit);
+			rdev->pm.dpm.dyn_state.cac_tdp_table->small_power_limit =
+				le16_to_cpu(pt->usSmallPowerLimit);
+			rdev->pm.dpm.dyn_state.cac_tdp_table->low_cac_leakage =
+				le16_to_cpu(pt->usLowCACLeakage);
+			rdev->pm.dpm.dyn_state.cac_tdp_table->high_cac_leakage =
+				le16_to_cpu(pt->usHighCACLeakage);
+		}
 	}
 
 	return 0;
@@ -1010,18 +1219,20 @@ int r600_parse_extended_power_table(struct radeon_device *rdev)
 
 void r600_free_extended_power_table(struct radeon_device *rdev)
 {
-	if (rdev->pm.dpm.dyn_state.vddc_dependency_on_sclk.entries)
-		kfree(rdev->pm.dpm.dyn_state.vddc_dependency_on_sclk.entries);
-	if (rdev->pm.dpm.dyn_state.vddci_dependency_on_mclk.entries)
-		kfree(rdev->pm.dpm.dyn_state.vddci_dependency_on_mclk.entries);
-	if (rdev->pm.dpm.dyn_state.vddc_dependency_on_mclk.entries)
-		kfree(rdev->pm.dpm.dyn_state.vddc_dependency_on_mclk.entries);
-	if (rdev->pm.dpm.dyn_state.cac_leakage_table.entries)
-		kfree(rdev->pm.dpm.dyn_state.cac_leakage_table.entries);
-	if (rdev->pm.dpm.dyn_state.phase_shedding_limits_table.entries)
-		kfree(rdev->pm.dpm.dyn_state.phase_shedding_limits_table.entries);
-	if (rdev->pm.dpm.dyn_state.ppm_table)
-		kfree(rdev->pm.dpm.dyn_state.ppm_table);
+	struct radeon_dpm_dynamic_state *dyn_state = &rdev->pm.dpm.dyn_state;
+
+	kfree(dyn_state->vddc_dependency_on_sclk.entries);
+	kfree(dyn_state->vddci_dependency_on_mclk.entries);
+	kfree(dyn_state->vddc_dependency_on_mclk.entries);
+	kfree(dyn_state->mvdd_dependency_on_mclk.entries);
+	kfree(dyn_state->cac_leakage_table.entries);
+	kfree(dyn_state->phase_shedding_limits_table.entries);
+	kfree(dyn_state->ppm_table);
+	kfree(dyn_state->cac_tdp_table);
+	kfree(dyn_state->vce_clock_voltage_dependency_table.entries);
+	kfree(dyn_state->uvd_clock_voltage_dependency_table.entries);
+	kfree(dyn_state->samu_clock_voltage_dependency_table.entries);
+	kfree(dyn_state->acp_clock_voltage_dependency_table.entries);
 }
 
 enum radeon_pcie_gen r600_get_pcie_gen_support(struct radeon_device *rdev,
@@ -1046,3 +1257,36 @@ enum radeon_pcie_gen r600_get_pcie_gen_support(struct radeon_device *rdev,
 	}
 	return RADEON_PCIE_GEN1;
 }
+
+u16 r600_get_pcie_lane_support(struct radeon_device *rdev,
+			       u16 asic_lanes,
+			       u16 default_lanes)
+{
+	switch (asic_lanes) {
+	case 0:
+	default:
+		return default_lanes;
+	case 1:
+		return 1;
+	case 2:
+		return 2;
+	case 4:
+		return 4;
+	case 8:
+		return 8;
+	case 12:
+		return 12;
+	case 16:
+		return 16;
+	}
+}
+
+u8 r600_encode_pci_lane_width(u32 lanes)
+{
+	u8 encoded_lanes[] = { 0, 1, 2, 0, 3, 0, 0, 0, 4, 0, 0, 0, 5, 0, 0, 0, 6 };
+
+	if (lanes > 16)
+		return 0;
+
+	return encoded_lanes[lanes];
+}
diff --git a/drivers/gpu/drm/radeon/r600_dpm.h b/drivers/gpu/drm/radeon/r600_dpm.h
index 7c822d9ae53d..1000bf9719f2 100644
--- a/drivers/gpu/drm/radeon/r600_dpm.h
+++ b/drivers/gpu/drm/radeon/r600_dpm.h
@@ -130,6 +130,7 @@ void r600_dpm_print_cap_info(u32 caps);
 void r600_dpm_print_ps_status(struct radeon_device *rdev,
 			      struct radeon_ps *rps);
 u32 r600_dpm_get_vblank_time(struct radeon_device *rdev);
+u32 r600_dpm_get_vrefresh(struct radeon_device *rdev);
 bool r600_is_uvd_state(u32 class, u32 class2);
 void r600_calculate_u_and_p(u32 i, u32 r_c, u32 p_b,
 			    u32 *p, u32 *u);
@@ -224,4 +225,9 @@ enum radeon_pcie_gen r600_get_pcie_gen_support(struct radeon_device *rdev,
 					       enum radeon_pcie_gen asic_gen,
 					       enum radeon_pcie_gen default_gen);
 
+u16 r600_get_pcie_lane_support(struct radeon_device *rdev,
+			       u16 asic_lanes,
+			       u16 default_lanes);
+u8 r600_encode_pci_lane_width(u32 lanes);
+
 #endif
diff --git a/drivers/gpu/drm/radeon/r600_hdmi.c b/drivers/gpu/drm/radeon/r600_hdmi.c
index f264df5470f7..5b729319f27b 100644
--- a/drivers/gpu/drm/radeon/r600_hdmi.c
+++ b/drivers/gpu/drm/radeon/r600_hdmi.c
@@ -57,15 +57,15 @@ enum r600_hdmi_iec_status_bits {
 static const struct radeon_hdmi_acr r600_hdmi_predefined_acr[] = {
     /*	     32kHz	  44.1kHz	48kHz    */
     /* Clock      N     CTS      N     CTS      N     CTS */
-    {  25174,  4576,  28125,  7007,  31250,  6864,  28125 }, /*  25,20/1.001 MHz */
+    {  25175,  4576,  28125,  7007,  31250,  6864,  28125 }, /*  25,20/1.001 MHz */
     {  25200,  4096,  25200,  6272,  28000,  6144,  25200 }, /*  25.20       MHz */
     {  27000,  4096,  27000,  6272,  30000,  6144,  27000 }, /*  27.00       MHz */
     {  27027,  4096,  27027,  6272,  30030,  6144,  27027 }, /*  27.00*1.001 MHz */
     {  54000,  4096,  54000,  6272,  60000,  6144,  54000 }, /*  54.00       MHz */
     {  54054,  4096,  54054,  6272,  60060,  6144,  54054 }, /*  54.00*1.001 MHz */
-    {  74175, 11648, 210937, 17836, 234375, 11648, 140625 }, /*  74.25/1.001 MHz */
+    {  74176, 11648, 210937, 17836, 234375, 11648, 140625 }, /*  74.25/1.001 MHz */
     {  74250,  4096,  74250,  6272,  82500,  6144,  74250 }, /*  74.25       MHz */
-    { 148351, 11648, 421875,  8918, 234375,  5824, 140625 }, /* 148.50/1.001 MHz */
+    { 148352, 11648, 421875,  8918, 234375,  5824, 140625 }, /* 148.50/1.001 MHz */
     { 148500,  4096, 148500,  6272, 165000,  6144, 148500 }, /* 148.50       MHz */
     {      0,  4096,      0,  6272,      0,  6144,      0 }  /* Other */
 };
@@ -75,8 +75,15 @@ static const struct radeon_hdmi_acr r600_hdmi_predefined_acr[] = {
  */
 static void r600_hdmi_calc_cts(uint32_t clock, int *CTS, int N, int freq)
 {
-	if (*CTS == 0)
-		*CTS = clock * N / (128 * freq) * 1000;
+	u64 n;
+	u32 d;
+
+	if (*CTS == 0) {
+		n = (u64)clock * (u64)N * 1000ULL;
+		d = 128 * freq;
+		do_div(n, d);
+		*CTS = n;
+	}
 	DRM_DEBUG("Using ACR timing N=%d CTS=%d for frequency %d\n",
 		  N, *CTS, freq);
 }
@@ -257,10 +264,7 @@ void r600_audio_set_dto(struct drm_encoder *encoder, u32 clock)
 	 * number (coefficient of two integer numbers.  DCCG_AUDIO_DTOx_PHASE
 	 * is the numerator, DCCG_AUDIO_DTOx_MODULE is the denominator
 	 */
-	if (ASIC_IS_DCE3(rdev)) {
-		/* according to the reg specs, this should DCE3.2 only, but in
-		 * practice it seems to cover DCE3.0 as well.
-		 */
+	if (ASIC_IS_DCE32(rdev)) {
 		if (dig->dig_encoder == 0) {
 			dto_cntl = RREG32(DCCG_AUDIO_DTO0_CNTL) & ~DCCG_AUDIO_DTO_WALLCLOCK_RATIO_MASK;
 			dto_cntl |= DCCG_AUDIO_DTO_WALLCLOCK_RATIO(wallclock_ratio);
@@ -276,13 +280,127 @@ void r600_audio_set_dto(struct drm_encoder *encoder, u32 clock)
 			WREG32(DCCG_AUDIO_DTO1_MODULE, dto_modulo);
 			WREG32(DCCG_AUDIO_DTO_SELECT, 1); /* select DTO1 */
 		}
+	} else if (ASIC_IS_DCE3(rdev)) {
+		/* according to the reg specs, this should DCE3.2 only, but in
+		 * practice it seems to cover DCE3.0/3.1 as well.
+		 */
+		if (dig->dig_encoder == 0) {
+			WREG32(DCCG_AUDIO_DTO0_PHASE, base_rate * 100);
+			WREG32(DCCG_AUDIO_DTO0_MODULE, clock * 100);
+			WREG32(DCCG_AUDIO_DTO_SELECT, 0); /* select DTO0 */
+		} else {
+			WREG32(DCCG_AUDIO_DTO1_PHASE, base_rate * 100);
+			WREG32(DCCG_AUDIO_DTO1_MODULE, clock * 100);
+			WREG32(DCCG_AUDIO_DTO_SELECT, 1); /* select DTO1 */
+		}
 	} else {
-		/* according to the reg specs, this should be DCE2.0 and DCE3.0 */
+		/* according to the reg specs, this should be DCE2.0 and DCE3.0/3.1 */
 		WREG32(AUDIO_DTO, AUDIO_DTO_PHASE(base_rate / 10) |
 		       AUDIO_DTO_MODULE(clock / 10));
 	}
 }
 
+static void dce3_2_afmt_write_speaker_allocation(struct drm_encoder *encoder)
+{
+	struct radeon_device *rdev = encoder->dev->dev_private;
+	struct drm_connector *connector;
+	struct radeon_connector *radeon_connector = NULL;
+	u32 tmp;
+	u8 *sadb;
+	int sad_count;
+
+	list_for_each_entry(connector, &encoder->dev->mode_config.connector_list, head) {
+		if (connector->encoder == encoder)
+			radeon_connector = to_radeon_connector(connector);
+	}
+
+	if (!radeon_connector) {
+		DRM_ERROR("Couldn't find encoder's connector\n");
+		return;
+	}
+
+	sad_count = drm_edid_to_speaker_allocation(radeon_connector->edid, &sadb);
+	if (sad_count < 0) {
+		DRM_ERROR("Couldn't read Speaker Allocation Data Block: %d\n", sad_count);
+		return;
+	}
+
+	/* program the speaker allocation */
+	tmp = RREG32(AZ_F0_CODEC_PIN0_CONTROL_CHANNEL_SPEAKER);
+	tmp &= ~(DP_CONNECTION | SPEAKER_ALLOCATION_MASK);
+	/* set HDMI mode */
+	tmp |= HDMI_CONNECTION;
+	if (sad_count)
+		tmp |= SPEAKER_ALLOCATION(sadb[0]);
+	else
+		tmp |= SPEAKER_ALLOCATION(5); /* stereo */
+	WREG32(AZ_F0_CODEC_PIN0_CONTROL_CHANNEL_SPEAKER, tmp);
+
+	kfree(sadb);
+}
+
+static void dce3_2_afmt_write_sad_regs(struct drm_encoder *encoder)
+{
+	struct radeon_device *rdev = encoder->dev->dev_private;
+	struct drm_connector *connector;
+	struct radeon_connector *radeon_connector = NULL;
+	struct cea_sad *sads;
+	int i, sad_count;
+
+	static const u16 eld_reg_to_type[][2] = {
+		{ AZ_F0_CODEC_PIN0_CONTROL_AUDIO_DESCRIPTOR0, HDMI_AUDIO_CODING_TYPE_PCM },
+		{ AZ_F0_CODEC_PIN0_CONTROL_AUDIO_DESCRIPTOR1, HDMI_AUDIO_CODING_TYPE_AC3 },
+		{ AZ_F0_CODEC_PIN0_CONTROL_AUDIO_DESCRIPTOR2, HDMI_AUDIO_CODING_TYPE_MPEG1 },
+		{ AZ_F0_CODEC_PIN0_CONTROL_AUDIO_DESCRIPTOR3, HDMI_AUDIO_CODING_TYPE_MP3 },
+		{ AZ_F0_CODEC_PIN0_CONTROL_AUDIO_DESCRIPTOR4, HDMI_AUDIO_CODING_TYPE_MPEG2 },
+		{ AZ_F0_CODEC_PIN0_CONTROL_AUDIO_DESCRIPTOR5, HDMI_AUDIO_CODING_TYPE_AAC_LC },
+		{ AZ_F0_CODEC_PIN0_CONTROL_AUDIO_DESCRIPTOR6, HDMI_AUDIO_CODING_TYPE_DTS },
+		{ AZ_F0_CODEC_PIN0_CONTROL_AUDIO_DESCRIPTOR7, HDMI_AUDIO_CODING_TYPE_ATRAC },
+		{ AZ_F0_CODEC_PIN0_CONTROL_AUDIO_DESCRIPTOR9, HDMI_AUDIO_CODING_TYPE_EAC3 },
+		{ AZ_F0_CODEC_PIN0_CONTROL_AUDIO_DESCRIPTOR10, HDMI_AUDIO_CODING_TYPE_DTS_HD },
+		{ AZ_F0_CODEC_PIN0_CONTROL_AUDIO_DESCRIPTOR11, HDMI_AUDIO_CODING_TYPE_MLP },
+		{ AZ_F0_CODEC_PIN0_CONTROL_AUDIO_DESCRIPTOR13, HDMI_AUDIO_CODING_TYPE_WMA_PRO },
+	};
+
+	list_for_each_entry(connector, &encoder->dev->mode_config.connector_list, head) {
+		if (connector->encoder == encoder)
+			radeon_connector = to_radeon_connector(connector);
+	}
+
+	if (!radeon_connector) {
+		DRM_ERROR("Couldn't find encoder's connector\n");
+		return;
+	}
+
+	sad_count = drm_edid_to_sad(radeon_connector->edid, &sads);
+	if (sad_count < 0) {
+		DRM_ERROR("Couldn't read SADs: %d\n", sad_count);
+		return;
+	}
+	BUG_ON(!sads);
+
+	for (i = 0; i < ARRAY_SIZE(eld_reg_to_type); i++) {
+		u32 value = 0;
+		int j;
+
+		for (j = 0; j < sad_count; j++) {
+			struct cea_sad *sad = &sads[j];
+
+			if (sad->format == eld_reg_to_type[i][1]) {
+				value = MAX_CHANNELS(sad->channels) |
+					DESCRIPTOR_BYTE_2(sad->byte2) |
+					SUPPORTED_FREQUENCIES(sad->freq);
+				if (sad->format == HDMI_AUDIO_CODING_TYPE_PCM)
+					value |= SUPPORTED_FREQUENCIES_STEREO(sad->freq);
+				break;
+			}
+		}
+		WREG32(eld_reg_to_type[i][0], value);
+	}
+
+	kfree(sads);
+}
+
 /*
  * update the info frames with the data from the current display mode
  */
@@ -327,9 +445,14 @@ void r600_hdmi_setmode(struct drm_encoder *encoder, struct drm_display_mode *mod
 		       HDMI0_60958_CS_UPDATE); /* allow 60958 channel status fields to be updated */
 	}
 
+	if (ASIC_IS_DCE32(rdev)) {
+		dce3_2_afmt_write_speaker_allocation(encoder);
+		dce3_2_afmt_write_sad_regs(encoder);
+	}
+
 	WREG32(HDMI0_ACR_PACKET_CONTROL + offset,
-	       HDMI0_ACR_AUTO_SEND | /* allow hw to sent ACR packets when required */
-	       HDMI0_ACR_SOURCE); /* select SW CTS value */
+	       HDMI0_ACR_SOURCE | /* select SW CTS value - XXX verify that hw CTS works on all families */
+	       HDMI0_ACR_AUTO_SEND); /* allow hw to sent ACR packets when required */
 
 	WREG32(HDMI0_VBI_PACKET_CONTROL + offset,
 	       HDMI0_NULL_SEND | /* send null packets when required */
@@ -382,7 +505,7 @@ void r600_hdmi_update_audio_settings(struct drm_encoder *encoder)
 	struct radeon_device *rdev = dev->dev_private;
 	struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
 	struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv;
-	struct r600_audio audio = r600_audio_status(rdev);
+	struct r600_audio_pin audio = r600_audio_status(rdev);
 	uint8_t buffer[HDMI_INFOFRAME_HEADER_SIZE + HDMI_AUDIO_INFOFRAME_SIZE];
 	struct hdmi_audio_infoframe frame;
 	uint32_t offset;
@@ -491,6 +614,11 @@ void r600_hdmi_enable(struct drm_encoder *encoder, bool enable)
 	if (!enable && !dig->afmt->enabled)
 		return;
 
+	if (enable)
+		dig->afmt->pin = r600_audio_get_pin(rdev);
+	else
+		dig->afmt->pin = NULL;
+
 	/* Older chipsets require setting HDMI and routing manually */
 	if (!ASIC_IS_DCE3(rdev)) {
 		if (enable)
diff --git a/drivers/gpu/drm/radeon/r600d.h b/drivers/gpu/drm/radeon/r600d.h
index 7c780839a7f4..7b3c7b5932c5 100644
--- a/drivers/gpu/drm/radeon/r600d.h
+++ b/drivers/gpu/drm/radeon/r600d.h
@@ -960,6 +960,42 @@
 #       define DIG_MODE_SDVO             4
 #define DIG1_CNTL                        0x79a0
 
+#define AZ_F0_CODEC_PIN0_CONTROL_CHANNEL_SPEAKER          0x71bc
+#define		SPEAKER_ALLOCATION(x)			(((x) & 0x7f) << 0)
+#define		SPEAKER_ALLOCATION_MASK			(0x7f << 0)
+#define		SPEAKER_ALLOCATION_SHIFT		0
+#define		HDMI_CONNECTION				(1 << 16)
+#define		DP_CONNECTION				(1 << 17)
+
+#define AZ_F0_CODEC_PIN0_CONTROL_AUDIO_DESCRIPTOR0        0x71c8 /* LPCM */
+#define AZ_F0_CODEC_PIN0_CONTROL_AUDIO_DESCRIPTOR1        0x71cc /* AC3 */
+#define AZ_F0_CODEC_PIN0_CONTROL_AUDIO_DESCRIPTOR2        0x71d0 /* MPEG1 */
+#define AZ_F0_CODEC_PIN0_CONTROL_AUDIO_DESCRIPTOR3        0x71d4 /* MP3 */
+#define AZ_F0_CODEC_PIN0_CONTROL_AUDIO_DESCRIPTOR4        0x71d8 /* MPEG2 */
+#define AZ_F0_CODEC_PIN0_CONTROL_AUDIO_DESCRIPTOR5        0x71dc /* AAC */
+#define AZ_F0_CODEC_PIN0_CONTROL_AUDIO_DESCRIPTOR6        0x71e0 /* DTS */
+#define AZ_F0_CODEC_PIN0_CONTROL_AUDIO_DESCRIPTOR7        0x71e4 /* ATRAC */
+#define AZ_F0_CODEC_PIN0_CONTROL_AUDIO_DESCRIPTOR8        0x71e8 /* one bit audio - leave at 0 (default) */
+#define AZ_F0_CODEC_PIN0_CONTROL_AUDIO_DESCRIPTOR9        0x71ec /* Dolby Digital */
+#define AZ_F0_CODEC_PIN0_CONTROL_AUDIO_DESCRIPTOR10       0x71f0 /* DTS-HD */
+#define AZ_F0_CODEC_PIN0_CONTROL_AUDIO_DESCRIPTOR11       0x71f4 /* MAT-MLP */
+#define AZ_F0_CODEC_PIN0_CONTROL_AUDIO_DESCRIPTOR12       0x71f8 /* DTS */
+#define AZ_F0_CODEC_PIN0_CONTROL_AUDIO_DESCRIPTOR13       0x71fc /* WMA Pro */
+#       define MAX_CHANNELS(x)                            (((x) & 0x7) << 0)
+/* max channels minus one.  7 = 8 channels */
+#       define SUPPORTED_FREQUENCIES(x)                   (((x) & 0xff) << 8)
+#       define DESCRIPTOR_BYTE_2(x)                       (((x) & 0xff) << 16)
+#       define SUPPORTED_FREQUENCIES_STEREO(x)            (((x) & 0xff) << 24) /* LPCM only */
+/* SUPPORTED_FREQUENCIES, SUPPORTED_FREQUENCIES_STEREO
+ * bit0 = 32 kHz
+ * bit1 = 44.1 kHz
+ * bit2 = 48 kHz
+ * bit3 = 88.2 kHz
+ * bit4 = 96 kHz
+ * bit5 = 176.4 kHz
+ * bit6 = 192 kHz
+ */
+
 /* rs6xx/rs740 and r6xx share the same HDMI blocks, however, rs6xx has only one
  * instance of the blocks while r6xx has 2.  DCE 3.0 cards are slightly
  * different due to the new DIG blocks, but also have 2 instances.
@@ -1004,7 +1040,7 @@
 #       define HDMI0_AVI_INFO_CONT   (1 << 1)
 #       define HDMI0_AUDIO_INFO_SEND (1 << 4)
 #       define HDMI0_AUDIO_INFO_CONT (1 << 5)
-#       define HDMI0_AUDIO_INFO_SOURCE (1 << 6) /* 0 - sound block; 1 - hmdi regs */
+#       define HDMI0_AUDIO_INFO_SOURCE (1 << 6) /* 0 - sound block; 1 - hdmi regs */
 #       define HDMI0_AUDIO_INFO_UPDATE (1 << 7)
 #       define HDMI0_MPEG_INFO_SEND  (1 << 8)
 #       define HDMI0_MPEG_INFO_CONT  (1 << 9)
@@ -1487,7 +1523,7 @@
  */
 #              define PACKET3_CP_DMA_CP_SYNC       (1 << 31)
 /* COMMAND */
-#              define PACKET3_CP_DMA_CMD_SRC_SWAP(x) ((x) << 23)
+#              define PACKET3_CP_DMA_CMD_SRC_SWAP(x) ((x) << 22)
                 /* 0 - none
 		 * 1 - 8 in 16
 		 * 2 - 8 in 32
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index 9f19259667df..a400ac1c4147 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -152,6 +152,47 @@ extern int radeon_aspm;
 #define RADEON_RESET_MC				(1 << 10)
 #define RADEON_RESET_DISPLAY			(1 << 11)
 
+/* CG block flags */
+#define RADEON_CG_BLOCK_GFX			(1 << 0)
+#define RADEON_CG_BLOCK_MC			(1 << 1)
+#define RADEON_CG_BLOCK_SDMA			(1 << 2)
+#define RADEON_CG_BLOCK_UVD			(1 << 3)
+#define RADEON_CG_BLOCK_VCE			(1 << 4)
+#define RADEON_CG_BLOCK_HDP			(1 << 5)
+#define RADEON_CG_BLOCK_BIF			(1 << 6)
+
+/* CG flags */
+#define RADEON_CG_SUPPORT_GFX_MGCG		(1 << 0)
+#define RADEON_CG_SUPPORT_GFX_MGLS		(1 << 1)
+#define RADEON_CG_SUPPORT_GFX_CGCG		(1 << 2)
+#define RADEON_CG_SUPPORT_GFX_CGLS		(1 << 3)
+#define RADEON_CG_SUPPORT_GFX_CGTS		(1 << 4)
+#define RADEON_CG_SUPPORT_GFX_CGTS_LS		(1 << 5)
+#define RADEON_CG_SUPPORT_GFX_CP_LS		(1 << 6)
+#define RADEON_CG_SUPPORT_GFX_RLC_LS		(1 << 7)
+#define RADEON_CG_SUPPORT_MC_LS			(1 << 8)
+#define RADEON_CG_SUPPORT_MC_MGCG		(1 << 9)
+#define RADEON_CG_SUPPORT_SDMA_LS		(1 << 10)
+#define RADEON_CG_SUPPORT_SDMA_MGCG		(1 << 11)
+#define RADEON_CG_SUPPORT_BIF_LS		(1 << 12)
+#define RADEON_CG_SUPPORT_UVD_MGCG		(1 << 13)
+#define RADEON_CG_SUPPORT_VCE_MGCG		(1 << 14)
+#define RADEON_CG_SUPPORT_HDP_LS		(1 << 15)
+#define RADEON_CG_SUPPORT_HDP_MGCG		(1 << 16)
+
+/* PG flags */
+#define RADEON_PG_SUPPORT_GFX_PG		(1 << 0)
+#define RADEON_PG_SUPPORT_GFX_SMG		(1 << 1)
+#define RADEON_PG_SUPPORT_GFX_DMG		(1 << 2)
+#define RADEON_PG_SUPPORT_UVD			(1 << 3)
+#define RADEON_PG_SUPPORT_VCE			(1 << 4)
+#define RADEON_PG_SUPPORT_CP			(1 << 5)
+#define RADEON_PG_SUPPORT_GDS			(1 << 6)
+#define RADEON_PG_SUPPORT_RLC_SMU_HS		(1 << 7)
+#define RADEON_PG_SUPPORT_SDMA			(1 << 8)
+#define RADEON_PG_SUPPORT_ACP			(1 << 9)
+#define RADEON_PG_SUPPORT_SAMU			(1 << 10)
+
 /* max cursor sizes (in pixels) */
 #define CURSOR_WIDTH 64
 #define CURSOR_HEIGHT 64
@@ -238,6 +279,12 @@ int radeon_atom_get_max_vddc(struct radeon_device *rdev, u8 voltage_type,
 int radeon_atom_get_leakage_vddc_based_on_leakage_idx(struct radeon_device *rdev,
 						      u16 *voltage,
 						      u16 leakage_idx);
+int radeon_atom_get_leakage_id_from_vbios(struct radeon_device *rdev,
+					  u16 *leakage_id);
+int radeon_atom_get_leakage_vddc_based_on_leakage_params(struct radeon_device *rdev,
+							 u16 *vddc, u16 *vddci,
+							 u16 virtual_voltage_id,
+							 u16 vbios_voltage_id);
 int radeon_atom_round_to_true_voltage(struct radeon_device *rdev,
 				      u8 voltage_type,
 				      u16 nominal_voltage,
@@ -492,9 +539,6 @@ int radeon_mode_dumb_create(struct drm_file *file_priv,
 int radeon_mode_dumb_mmap(struct drm_file *filp,
 			  struct drm_device *dev,
 			  uint32_t handle, uint64_t *offset_p);
-int radeon_mode_dumb_destroy(struct drm_file *file_priv,
-			     struct drm_device *dev,
-			     uint32_t handle);
 
 /*
  * Semaphores.
@@ -682,7 +726,7 @@ union radeon_irq_stat_regs {
 
 #define RADEON_MAX_HPD_PINS 6
 #define RADEON_MAX_CRTCS 6
-#define RADEON_MAX_AFMT_BLOCKS 6
+#define RADEON_MAX_AFMT_BLOCKS 7
 
 struct radeon_irq {
 	bool				installed;
@@ -746,8 +790,6 @@ struct radeon_ring {
 	uint32_t		align_mask;
 	uint32_t		ptr_mask;
 	bool			ready;
-	u32			ptr_reg_shift;
-	u32			ptr_reg_mask;
 	u32			nop;
 	u32			idx;
 	u64			last_semaphore_signal_addr;
@@ -844,35 +886,6 @@ struct r600_ih {
 	bool                    enabled;
 };
 
-struct r600_blit_cp_primitives {
-	void (*set_render_target)(struct radeon_device *rdev, int format,
-				  int w, int h, u64 gpu_addr);
-	void (*cp_set_surface_sync)(struct radeon_device *rdev,
-				    u32 sync_type, u32 size,
-				    u64 mc_addr);
-	void (*set_shaders)(struct radeon_device *rdev);
-	void (*set_vtx_resource)(struct radeon_device *rdev, u64 gpu_addr);
-	void (*set_tex_resource)(struct radeon_device *rdev,
-				 int format, int w, int h, int pitch,
-				 u64 gpu_addr, u32 size);
-	void (*set_scissors)(struct radeon_device *rdev, int x1, int y1,
-			     int x2, int y2);
-	void (*draw_auto)(struct radeon_device *rdev);
-	void (*set_default_state)(struct radeon_device *rdev);
-};
-
-struct r600_blit {
-	struct radeon_bo	*shader_obj;
-	struct r600_blit_cp_primitives primitives;
-	int max_dim;
-	int ring_size_common;
-	int ring_size_per_loop;
-	u64 shader_gpu_addr;
-	u32 vs_offset, ps_offset;
-	u32 state_offset;
-	u32 state_len;
-};
-
 /*
  * RLC stuff
  */
@@ -883,13 +896,19 @@ struct radeon_rlc {
 	struct radeon_bo	*save_restore_obj;
 	uint64_t		save_restore_gpu_addr;
 	volatile uint32_t	*sr_ptr;
-	u32                     *reg_list;
+	const u32               *reg_list;
 	u32                     reg_list_size;
 	/* for clear state */
 	struct radeon_bo	*clear_state_obj;
 	uint64_t		clear_state_gpu_addr;
 	volatile uint32_t	*cs_ptr;
-	struct cs_section_def   *cs_data;
+	const struct cs_section_def   *cs_data;
+	u32                     clear_state_size;
+	/* for cp tables */
+	struct radeon_bo	*cp_table_obj;
+	uint64_t		cp_table_gpu_addr;
+	volatile uint32_t	*cp_table_ptr;
+	u32                     cp_table_size;
 };
 
 int radeon_ib_get(struct radeon_device *rdev, int ring,
@@ -921,8 +940,7 @@ unsigned radeon_ring_backup(struct radeon_device *rdev, struct radeon_ring *ring
 int radeon_ring_restore(struct radeon_device *rdev, struct radeon_ring *ring,
 			unsigned size, uint32_t *data);
 int radeon_ring_init(struct radeon_device *rdev, struct radeon_ring *cp, unsigned ring_size,
-		     unsigned rptr_offs, unsigned rptr_reg, unsigned wptr_reg,
-		     u32 ptr_reg_shift, u32 ptr_reg_mask, u32 nop);
+		     unsigned rptr_offs, unsigned rptr_reg, unsigned wptr_reg, u32 nop);
 void radeon_ring_fini(struct radeon_device *rdev, struct radeon_ring *cp);
 
 
@@ -1036,7 +1054,6 @@ struct radeon_wb {
 #define R600_WB_DMA_RPTR_OFFSET   1792
 #define R600_WB_IH_WPTR_OFFSET   2048
 #define CAYMAN_WB_DMA1_RPTR_OFFSET   2304
-#define R600_WB_UVD_RPTR_OFFSET  2560
 #define R600_WB_EVENT_OFFSET     3072
 #define CIK_WB_CP1_WPTR_OFFSET     3328
 #define CIK_WB_CP2_WPTR_OFFSET     3584
@@ -1147,6 +1164,7 @@ enum radeon_int_thermal_type {
 	THERMAL_TYPE_SI,
 	THERMAL_TYPE_EMC2103_WITH_INTERNAL,
 	THERMAL_TYPE_CI,
+	THERMAL_TYPE_KV,
 };
 
 struct radeon_voltage {
@@ -1220,6 +1238,9 @@ struct radeon_ps {
 	/* UVD clocks */
 	u32 vclk;
 	u32 dclk;
+	/* VCE clocks */
+	u32 evclk;
+	u32 ecclk;
 	/* asic priv */
 	void *ps_priv;
 };
@@ -1270,14 +1291,21 @@ struct radeon_clock_voltage_dependency_table {
 	struct radeon_clock_voltage_dependency_entry *entries;
 };
 
-struct radeon_cac_leakage_entry {
-	u16 vddc;
-	u32 leakage;
+union radeon_cac_leakage_entry {
+	struct {
+		u16 vddc;
+		u32 leakage;
+	};
+	struct {
+		u16 vddc1;
+		u16 vddc2;
+		u16 vddc3;
+	};
 };
 
 struct radeon_cac_leakage_table {
 	u32 count;
-	struct radeon_cac_leakage_entry *entries;
+	union radeon_cac_leakage_entry *entries;
 };
 
 struct radeon_phase_shedding_limits_entry {
@@ -1291,6 +1319,28 @@ struct radeon_phase_shedding_limits_table {
 	struct radeon_phase_shedding_limits_entry *entries;
 };
 
+struct radeon_uvd_clock_voltage_dependency_entry {
+	u32 vclk;
+	u32 dclk;
+	u16 v;
+};
+
+struct radeon_uvd_clock_voltage_dependency_table {
+	u8 count;
+	struct radeon_uvd_clock_voltage_dependency_entry *entries;
+};
+
+struct radeon_vce_clock_voltage_dependency_entry {
+	u32 ecclk;
+	u32 evclk;
+	u16 v;
+};
+
+struct radeon_vce_clock_voltage_dependency_table {
+	u8 count;
+	struct radeon_vce_clock_voltage_dependency_entry *entries;
+};
+
 struct radeon_ppm_table {
 	u8 ppm_design;
 	u16 cpu_core_number;
@@ -1304,11 +1354,27 @@ struct radeon_ppm_table {
 	u32 tj_max;
 };
 
+struct radeon_cac_tdp_table {
+	u16 tdp;
+	u16 configurable_tdp;
+	u16 tdc;
+	u16 battery_power_limit;
+	u16 small_power_limit;
+	u16 low_cac_leakage;
+	u16 high_cac_leakage;
+	u16 maximum_power_delivery_limit;
+};
+
 struct radeon_dpm_dynamic_state {
 	struct radeon_clock_voltage_dependency_table vddc_dependency_on_sclk;
 	struct radeon_clock_voltage_dependency_table vddci_dependency_on_mclk;
 	struct radeon_clock_voltage_dependency_table vddc_dependency_on_mclk;
+	struct radeon_clock_voltage_dependency_table mvdd_dependency_on_mclk;
 	struct radeon_clock_voltage_dependency_table vddc_dependency_on_dispclk;
+	struct radeon_uvd_clock_voltage_dependency_table uvd_clock_voltage_dependency_table;
+	struct radeon_vce_clock_voltage_dependency_table vce_clock_voltage_dependency_table;
+	struct radeon_clock_voltage_dependency_table samu_clock_voltage_dependency_table;
+	struct radeon_clock_voltage_dependency_table acp_clock_voltage_dependency_table;
 	struct radeon_clock_array valid_sclk_values;
 	struct radeon_clock_array valid_mclk_values;
 	struct radeon_clock_and_voltage_limits max_clock_voltage_on_dc;
@@ -1320,6 +1386,7 @@ struct radeon_dpm_dynamic_state {
 	struct radeon_cac_leakage_table cac_leakage_table;
 	struct radeon_phase_shedding_limits_table phase_shedding_limits_table;
 	struct radeon_ppm_table *ppm_table;
+	struct radeon_cac_tdp_table *cac_tdp_table;
 };
 
 struct radeon_dpm_fan {
@@ -1389,11 +1456,12 @@ struct radeon_dpm {
 	struct radeon_dpm_thermal thermal;
 	/* forced levels */
 	enum radeon_dpm_forced_level forced_level;
+	/* track UVD streams */
+	unsigned sd;
+	unsigned hd;
 };
 
-void radeon_dpm_enable_power_state(struct radeon_device *rdev,
-				    enum radeon_pm_state_type dpm_state);
-
+void radeon_dpm_enable_uvd(struct radeon_device *rdev, bool enable);
 
 struct radeon_pm {
 	struct mutex		mutex;
@@ -1470,6 +1538,7 @@ struct radeon_uvd {
 	void			*saved_bo;
 	atomic_t		handles[RADEON_MAX_UVD_HANDLES];
 	struct drm_file		*filp[RADEON_MAX_UVD_HANDLES];
+	unsigned		img_size[RADEON_MAX_UVD_HANDLES];
 	struct delayed_work	idle_work;
 };
 
@@ -1498,12 +1567,21 @@ int radeon_uvd_calc_upll_dividers(struct radeon_device *rdev,
 int radeon_uvd_send_upll_ctlreq(struct radeon_device *rdev,
                                 unsigned cg_upll_func_cntl);
 
-struct r600_audio {
+struct r600_audio_pin {
 	int			channels;
 	int			rate;
 	int			bits_per_sample;
 	u8			status_bits;
 	u8			category_code;
+	u32			offset;
+	bool			connected;
+	u32			id;
+};
+
+struct r600_audio {
+	bool enabled;
+	struct r600_audio_pin pin[RADEON_MAX_AFMT_BLOCKS];
+	int num_pins;
 };
 
 /*
@@ -1535,6 +1613,34 @@ int radeon_debugfs_add_files(struct radeon_device *rdev,
 			     unsigned nfiles);
 int radeon_debugfs_fence_init(struct radeon_device *rdev);
 
+/*
+ * ASIC ring specific functions.
+ */
+struct radeon_asic_ring {
+	/* ring read/write ptr handling */
+	u32 (*get_rptr)(struct radeon_device *rdev, struct radeon_ring *ring);
+	u32 (*get_wptr)(struct radeon_device *rdev, struct radeon_ring *ring);
+	void (*set_wptr)(struct radeon_device *rdev, struct radeon_ring *ring);
+
+	/* validating and patching of IBs */
+	int (*ib_parse)(struct radeon_device *rdev, struct radeon_ib *ib);
+	int (*cs_parse)(struct radeon_cs_parser *p);
+
+	/* command emmit functions */
+	void (*ib_execute)(struct radeon_device *rdev, struct radeon_ib *ib);
+	void (*emit_fence)(struct radeon_device *rdev, struct radeon_fence *fence);
+	void (*emit_semaphore)(struct radeon_device *rdev, struct radeon_ring *cp,
+			       struct radeon_semaphore *semaphore, bool emit_wait);
+	void (*vm_flush)(struct radeon_device *rdev, int ridx, struct radeon_vm *vm);
+
+	/* testing functions */
+	int (*ring_test)(struct radeon_device *rdev, struct radeon_ring *cp);
+	int (*ib_test)(struct radeon_device *rdev, struct radeon_ring *cp);
+	bool (*is_lockup)(struct radeon_device *rdev, struct radeon_ring *cp);
+
+	/* deprecated */
+	void (*ring_start)(struct radeon_device *rdev, struct radeon_ring *cp);
+};
 
 /*
  * ASIC specific functions.
@@ -1578,23 +1684,7 @@ struct radeon_asic {
 				 uint32_t incr, uint32_t flags);
 	} vm;
 	/* ring specific callbacks */
-	struct {
-		void (*ib_execute)(struct radeon_device *rdev, struct radeon_ib *ib);
-		int (*ib_parse)(struct radeon_device *rdev, struct radeon_ib *ib);
-		void (*emit_fence)(struct radeon_device *rdev, struct radeon_fence *fence);
-		void (*emit_semaphore)(struct radeon_device *rdev, struct radeon_ring *cp,
-				       struct radeon_semaphore *semaphore, bool emit_wait);
-		int (*cs_parse)(struct radeon_cs_parser *p);
-		void (*ring_start)(struct radeon_device *rdev, struct radeon_ring *cp);
-		int (*ring_test)(struct radeon_device *rdev, struct radeon_ring *cp);
-		int (*ib_test)(struct radeon_device *rdev, struct radeon_ring *cp);
-		bool (*is_lockup)(struct radeon_device *rdev, struct radeon_ring *cp);
-		void (*vm_flush)(struct radeon_device *rdev, int ridx, struct radeon_vm *vm);
-
-		u32 (*get_rptr)(struct radeon_device *rdev, struct radeon_ring *ring);
-		u32 (*get_wptr)(struct radeon_device *rdev, struct radeon_ring *ring);
-		void (*set_wptr)(struct radeon_device *rdev, struct radeon_ring *ring);
-	} ring[RADEON_NUM_RINGS];
+	struct radeon_asic_ring *ring[RADEON_NUM_RINGS];
 	/* irqs */
 	struct {
 		int (*set)(struct radeon_device *rdev);
@@ -1687,6 +1777,8 @@ struct radeon_asic {
 		void (*debugfs_print_current_performance_level)(struct radeon_device *rdev, struct seq_file *m);
 		int (*force_performance_level)(struct radeon_device *rdev, enum radeon_dpm_forced_level level);
 		bool (*vblank_too_short)(struct radeon_device *rdev);
+		void (*powergate_uvd)(struct radeon_device *rdev, bool gate);
+		void (*enable_bapm)(struct radeon_device *rdev, bool enable);
 	} dpm;
 	/* pageflipping */
 	struct {
@@ -2019,6 +2111,28 @@ struct radeon_device {
 	resource_size_t			rmmio_size;
 	/* protects concurrent MM_INDEX/DATA based register access */
 	spinlock_t mmio_idx_lock;
+	/* protects concurrent SMC based register access */
+	spinlock_t smc_idx_lock;
+	/* protects concurrent PLL register access */
+	spinlock_t pll_idx_lock;
+	/* protects concurrent MC register access */
+	spinlock_t mc_idx_lock;
+	/* protects concurrent PCIE register access */
+	spinlock_t pcie_idx_lock;
+	/* protects concurrent PCIE_PORT register access */
+	spinlock_t pciep_idx_lock;
+	/* protects concurrent PIF register access */
+	spinlock_t pif_idx_lock;
+	/* protects concurrent CG register access */
+	spinlock_t cg_idx_lock;
+	/* protects concurrent UVD register access */
+	spinlock_t uvd_idx_lock;
+	/* protects concurrent RCU register access */
+	spinlock_t rcu_idx_lock;
+	/* protects concurrent DIDT register access */
+	spinlock_t didt_idx_lock;
+	/* protects concurrent ENDPOINT (audio) register access */
+	spinlock_t end_idx_lock;
 	void __iomem			*rmmio;
 	radeon_rreg_t			mc_rreg;
 	radeon_wreg_t			mc_wreg;
@@ -2066,7 +2180,6 @@ struct radeon_device {
 	const struct firmware *sdma_fw;	/* CIK SDMA firmware */
 	const struct firmware *smc_fw;	/* SMC firmware */
 	const struct firmware *uvd_fw;	/* UVD firmware */
-	struct r600_blit r600_blit;
 	struct r600_vram_scratch vram_scratch;
 	int msi_enabled; /* msi enabled */
 	struct r600_ih ih; /* r6/700 interrupt ring */
@@ -2077,9 +2190,8 @@ struct radeon_device {
 	struct work_struct reset_work;
 	int num_crtc; /* number of crtcs */
 	struct mutex dc_hw_i2c_mutex; /* display controller hw i2c mutex */
-	bool audio_enabled;
 	bool has_uvd;
-	struct r600_audio audio_status; /* audio stuff */
+	struct r600_audio audio; /* audio stuff */
 	struct notifier_block acpi_nb;
 	/* only one userspace can use Hyperz features or CMASK at a time */
 	struct drm_file *hyperz_filp;
@@ -2097,6 +2209,9 @@ struct radeon_device {
 	struct radeon_atcs		atcs;
 	/* srbm instance registers */
 	struct mutex			srbm_mutex;
+	/* clock, powergating flags */
+	u32 cg_flags;
+	u32 pg_flags;
 };
 
 int radeon_device_init(struct radeon_device *rdev,
@@ -2155,6 +2270,8 @@ void cik_mm_wdoorbell(struct radeon_device *rdev, u32 offset, u32 v);
 #define WREG32_PIF_PHY1(reg, v) eg_pif_phy1_wreg(rdev, (reg), (v))
 #define RREG32_UVD_CTX(reg) r600_uvd_ctx_rreg(rdev, (reg))
 #define WREG32_UVD_CTX(reg, v) r600_uvd_ctx_wreg(rdev, (reg), (v))
+#define RREG32_DIDT(reg) cik_didt_rreg(rdev, (reg))
+#define WREG32_DIDT(reg, v) cik_didt_wreg(rdev, (reg), (v))
 #define WREG32_P(reg, val, mask)				\
 	do {							\
 		uint32_t tmp_ = RREG32(reg);			\
@@ -2183,107 +2300,179 @@ void cik_mm_wdoorbell(struct radeon_device *rdev, u32 offset, u32 v);
  */
 static inline uint32_t rv370_pcie_rreg(struct radeon_device *rdev, uint32_t reg)
 {
+	unsigned long flags;
 	uint32_t r;
 
+	spin_lock_irqsave(&rdev->pcie_idx_lock, flags);
 	WREG32(RADEON_PCIE_INDEX, ((reg) & rdev->pcie_reg_mask));
 	r = RREG32(RADEON_PCIE_DATA);
+	spin_unlock_irqrestore(&rdev->pcie_idx_lock, flags);
 	return r;
 }
 
 static inline void rv370_pcie_wreg(struct radeon_device *rdev, uint32_t reg, uint32_t v)
 {
+	unsigned long flags;
+
+	spin_lock_irqsave(&rdev->pcie_idx_lock, flags);
 	WREG32(RADEON_PCIE_INDEX, ((reg) & rdev->pcie_reg_mask));
 	WREG32(RADEON_PCIE_DATA, (v));
+	spin_unlock_irqrestore(&rdev->pcie_idx_lock, flags);
 }
 
 static inline u32 tn_smc_rreg(struct radeon_device *rdev, u32 reg)
 {
+	unsigned long flags;
 	u32 r;
 
+	spin_lock_irqsave(&rdev->smc_idx_lock, flags);
 	WREG32(TN_SMC_IND_INDEX_0, (reg));
 	r = RREG32(TN_SMC_IND_DATA_0);
+	spin_unlock_irqrestore(&rdev->smc_idx_lock, flags);
 	return r;
 }
 
 static inline void tn_smc_wreg(struct radeon_device *rdev, u32 reg, u32 v)
 {
+	unsigned long flags;
+
+	spin_lock_irqsave(&rdev->smc_idx_lock, flags);
 	WREG32(TN_SMC_IND_INDEX_0, (reg));
 	WREG32(TN_SMC_IND_DATA_0, (v));
+	spin_unlock_irqrestore(&rdev->smc_idx_lock, flags);
 }
 
 static inline u32 r600_rcu_rreg(struct radeon_device *rdev, u32 reg)
 {
+	unsigned long flags;
 	u32 r;
 
+	spin_lock_irqsave(&rdev->rcu_idx_lock, flags);
 	WREG32(R600_RCU_INDEX, ((reg) & 0x1fff));
 	r = RREG32(R600_RCU_DATA);
+	spin_unlock_irqrestore(&rdev->rcu_idx_lock, flags);
 	return r;
 }
 
 static inline void r600_rcu_wreg(struct radeon_device *rdev, u32 reg, u32 v)
 {
+	unsigned long flags;
+
+	spin_lock_irqsave(&rdev->rcu_idx_lock, flags);
 	WREG32(R600_RCU_INDEX, ((reg) & 0x1fff));
 	WREG32(R600_RCU_DATA, (v));
+	spin_unlock_irqrestore(&rdev->rcu_idx_lock, flags);
 }
 
 static inline u32 eg_cg_rreg(struct radeon_device *rdev, u32 reg)
 {
+	unsigned long flags;
 	u32 r;
 
+	spin_lock_irqsave(&rdev->cg_idx_lock, flags);
 	WREG32(EVERGREEN_CG_IND_ADDR, ((reg) & 0xffff));
 	r = RREG32(EVERGREEN_CG_IND_DATA);
+	spin_unlock_irqrestore(&rdev->cg_idx_lock, flags);
 	return r;
 }
 
 static inline void eg_cg_wreg(struct radeon_device *rdev, u32 reg, u32 v)
 {
+	unsigned long flags;
+
+	spin_lock_irqsave(&rdev->cg_idx_lock, flags);
 	WREG32(EVERGREEN_CG_IND_ADDR, ((reg) & 0xffff));
 	WREG32(EVERGREEN_CG_IND_DATA, (v));
+	spin_unlock_irqrestore(&rdev->cg_idx_lock, flags);
 }
 
 static inline u32 eg_pif_phy0_rreg(struct radeon_device *rdev, u32 reg)
 {
+	unsigned long flags;
 	u32 r;
 
+	spin_lock_irqsave(&rdev->pif_idx_lock, flags);
 	WREG32(EVERGREEN_PIF_PHY0_INDEX, ((reg) & 0xffff));
 	r = RREG32(EVERGREEN_PIF_PHY0_DATA);
+	spin_unlock_irqrestore(&rdev->pif_idx_lock, flags);
 	return r;
 }
 
 static inline void eg_pif_phy0_wreg(struct radeon_device *rdev, u32 reg, u32 v)
 {
+	unsigned long flags;
+
+	spin_lock_irqsave(&rdev->pif_idx_lock, flags);
 	WREG32(EVERGREEN_PIF_PHY0_INDEX, ((reg) & 0xffff));
 	WREG32(EVERGREEN_PIF_PHY0_DATA, (v));
+	spin_unlock_irqrestore(&rdev->pif_idx_lock, flags);
 }
 
 static inline u32 eg_pif_phy1_rreg(struct radeon_device *rdev, u32 reg)
 {
+	unsigned long flags;
 	u32 r;
 
+	spin_lock_irqsave(&rdev->pif_idx_lock, flags);
 	WREG32(EVERGREEN_PIF_PHY1_INDEX, ((reg) & 0xffff));
 	r = RREG32(EVERGREEN_PIF_PHY1_DATA);
+	spin_unlock_irqrestore(&rdev->pif_idx_lock, flags);
 	return r;
 }
 
 static inline void eg_pif_phy1_wreg(struct radeon_device *rdev, u32 reg, u32 v)
 {
+	unsigned long flags;
+
+	spin_lock_irqsave(&rdev->pif_idx_lock, flags);
 	WREG32(EVERGREEN_PIF_PHY1_INDEX, ((reg) & 0xffff));
 	WREG32(EVERGREEN_PIF_PHY1_DATA, (v));
+	spin_unlock_irqrestore(&rdev->pif_idx_lock, flags);
 }
 
 static inline u32 r600_uvd_ctx_rreg(struct radeon_device *rdev, u32 reg)
 {
+	unsigned long flags;
 	u32 r;
 
+	spin_lock_irqsave(&rdev->uvd_idx_lock, flags);
 	WREG32(R600_UVD_CTX_INDEX, ((reg) & 0x1ff));
 	r = RREG32(R600_UVD_CTX_DATA);
+	spin_unlock_irqrestore(&rdev->uvd_idx_lock, flags);
 	return r;
 }
 
 static inline void r600_uvd_ctx_wreg(struct radeon_device *rdev, u32 reg, u32 v)
 {
+	unsigned long flags;
+
+	spin_lock_irqsave(&rdev->uvd_idx_lock, flags);
 	WREG32(R600_UVD_CTX_INDEX, ((reg) & 0x1ff));
 	WREG32(R600_UVD_CTX_DATA, (v));
+	spin_unlock_irqrestore(&rdev->uvd_idx_lock, flags);
+}
+
+
+static inline u32 cik_didt_rreg(struct radeon_device *rdev, u32 reg)
+{
+	unsigned long flags;
+	u32 r;
+
+	spin_lock_irqsave(&rdev->didt_idx_lock, flags);
+	WREG32(CIK_DIDT_IND_INDEX, (reg));
+	r = RREG32(CIK_DIDT_IND_DATA);
+	spin_unlock_irqrestore(&rdev->didt_idx_lock, flags);
+	return r;
+}
+
+static inline void cik_didt_wreg(struct radeon_device *rdev, u32 reg, u32 v)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&rdev->didt_idx_lock, flags);
+	WREG32(CIK_DIDT_IND_INDEX, (reg));
+	WREG32(CIK_DIDT_IND_DATA, (v));
+	spin_unlock_irqrestore(&rdev->didt_idx_lock, flags);
 }
 
 void r100_pll_errata_after_index(struct radeon_device *rdev);
@@ -2381,7 +2570,7 @@ void radeon_ring_write(struct radeon_ring *ring, uint32_t v);
 #define radeon_fini(rdev) (rdev)->asic->fini((rdev))
 #define radeon_resume(rdev) (rdev)->asic->resume((rdev))
 #define radeon_suspend(rdev) (rdev)->asic->suspend((rdev))
-#define radeon_cs_parse(rdev, r, p) (rdev)->asic->ring[(r)].cs_parse((p))
+#define radeon_cs_parse(rdev, r, p) (rdev)->asic->ring[(r)]->cs_parse((p))
 #define radeon_vga_set_state(rdev, state) (rdev)->asic->vga_set_state((rdev), (state))
 #define radeon_asic_reset(rdev) (rdev)->asic->asic_reset((rdev))
 #define radeon_gart_tlb_flush(rdev) (rdev)->asic->gart.tlb_flush((rdev))
@@ -2389,16 +2578,16 @@ void radeon_ring_write(struct radeon_ring *ring, uint32_t v);
 #define radeon_asic_vm_init(rdev) (rdev)->asic->vm.init((rdev))
 #define radeon_asic_vm_fini(rdev) (rdev)->asic->vm.fini((rdev))
 #define radeon_asic_vm_set_page(rdev, ib, pe, addr, count, incr, flags) ((rdev)->asic->vm.set_page((rdev), (ib), (pe), (addr), (count), (incr), (flags)))
-#define radeon_ring_start(rdev, r, cp) (rdev)->asic->ring[(r)].ring_start((rdev), (cp))
-#define radeon_ring_test(rdev, r, cp) (rdev)->asic->ring[(r)].ring_test((rdev), (cp))
-#define radeon_ib_test(rdev, r, cp) (rdev)->asic->ring[(r)].ib_test((rdev), (cp))
-#define radeon_ring_ib_execute(rdev, r, ib) (rdev)->asic->ring[(r)].ib_execute((rdev), (ib))
-#define radeon_ring_ib_parse(rdev, r, ib) (rdev)->asic->ring[(r)].ib_parse((rdev), (ib))
-#define radeon_ring_is_lockup(rdev, r, cp) (rdev)->asic->ring[(r)].is_lockup((rdev), (cp))
-#define radeon_ring_vm_flush(rdev, r, vm) (rdev)->asic->ring[(r)].vm_flush((rdev), (r), (vm))
-#define radeon_ring_get_rptr(rdev, r) (rdev)->asic->ring[(r)->idx].get_rptr((rdev), (r))
-#define radeon_ring_get_wptr(rdev, r) (rdev)->asic->ring[(r)->idx].get_wptr((rdev), (r))
-#define radeon_ring_set_wptr(rdev, r) (rdev)->asic->ring[(r)->idx].set_wptr((rdev), (r))
+#define radeon_ring_start(rdev, r, cp) (rdev)->asic->ring[(r)]->ring_start((rdev), (cp))
+#define radeon_ring_test(rdev, r, cp) (rdev)->asic->ring[(r)]->ring_test((rdev), (cp))
+#define radeon_ib_test(rdev, r, cp) (rdev)->asic->ring[(r)]->ib_test((rdev), (cp))
+#define radeon_ring_ib_execute(rdev, r, ib) (rdev)->asic->ring[(r)]->ib_execute((rdev), (ib))
+#define radeon_ring_ib_parse(rdev, r, ib) (rdev)->asic->ring[(r)]->ib_parse((rdev), (ib))
+#define radeon_ring_is_lockup(rdev, r, cp) (rdev)->asic->ring[(r)]->is_lockup((rdev), (cp))
+#define radeon_ring_vm_flush(rdev, r, vm) (rdev)->asic->ring[(r)]->vm_flush((rdev), (r), (vm))
+#define radeon_ring_get_rptr(rdev, r) (rdev)->asic->ring[(r)->idx]->get_rptr((rdev), (r))
+#define radeon_ring_get_wptr(rdev, r) (rdev)->asic->ring[(r)->idx]->get_wptr((rdev), (r))
+#define radeon_ring_set_wptr(rdev, r) (rdev)->asic->ring[(r)->idx]->set_wptr((rdev), (r))
 #define radeon_irq_set(rdev) (rdev)->asic->irq.set((rdev))
 #define radeon_irq_process(rdev) (rdev)->asic->irq.process((rdev))
 #define radeon_get_vblank_counter(rdev, crtc) (rdev)->asic->display.get_vblank_counter((rdev), (crtc))
@@ -2406,8 +2595,8 @@ void radeon_ring_write(struct radeon_ring *ring, uint32_t v);
 #define radeon_get_backlight_level(rdev, e) (rdev)->asic->display.get_backlight_level((e))
 #define radeon_hdmi_enable(rdev, e, b) (rdev)->asic->display.hdmi_enable((e), (b))
 #define radeon_hdmi_setmode(rdev, e, m) (rdev)->asic->display.hdmi_setmode((e), (m))
-#define radeon_fence_ring_emit(rdev, r, fence) (rdev)->asic->ring[(r)].emit_fence((rdev), (fence))
-#define radeon_semaphore_ring_emit(rdev, r, cp, semaphore, emit_wait) (rdev)->asic->ring[(r)].emit_semaphore((rdev), (cp), (semaphore), (emit_wait))
+#define radeon_fence_ring_emit(rdev, r, fence) (rdev)->asic->ring[(r)]->emit_fence((rdev), (fence))
+#define radeon_semaphore_ring_emit(rdev, r, cp, semaphore, emit_wait) (rdev)->asic->ring[(r)]->emit_semaphore((rdev), (cp), (semaphore), (emit_wait))
 #define radeon_copy_blit(rdev, s, d, np, f) (rdev)->asic->copy.blit((rdev), (s), (d), (np), (f))
 #define radeon_copy_dma(rdev, s, d, np, f) (rdev)->asic->copy.dma((rdev), (s), (d), (np), (f))
 #define radeon_copy(rdev, s, d, np, f) (rdev)->asic->copy.copy((rdev), (s), (d), (np), (f))
@@ -2458,6 +2647,8 @@ void radeon_ring_write(struct radeon_ring *ring, uint32_t v);
 #define radeon_dpm_debugfs_print_current_performance_level(rdev, m) rdev->asic->dpm.debugfs_print_current_performance_level((rdev), (m))
 #define radeon_dpm_force_performance_level(rdev, l) rdev->asic->dpm.force_performance_level((rdev), (l))
 #define radeon_dpm_vblank_too_short(rdev) rdev->asic->dpm.vblank_too_short((rdev))
+#define radeon_dpm_powergate_uvd(rdev, g) rdev->asic->dpm.powergate_uvd((rdev), (g))
+#define radeon_dpm_enable_bapm(rdev, e) rdev->asic->dpm.enable_bapm((rdev), (e))
 
 /* Common functions */
 /* AGP */
@@ -2524,6 +2715,8 @@ int radeon_vm_bo_rmv(struct radeon_device *rdev,
 
 /* audio */
 void r600_audio_update_hdmi(struct work_struct *work);
+struct r600_audio_pin *r600_audio_get_pin(struct radeon_device *rdev);
+struct r600_audio_pin *dce6_audio_get_pin(struct radeon_device *rdev);
 
 /*
  * R600 vram scratch functions
diff --git a/drivers/gpu/drm/radeon/radeon_asic.c b/drivers/gpu/drm/radeon/radeon_asic.c
index f8f8b3113ddd..8f7e04538fd6 100644
--- a/drivers/gpu/drm/radeon/radeon_asic.c
+++ b/drivers/gpu/drm/radeon/radeon_asic.c
@@ -172,6 +172,21 @@ void radeon_agp_disable(struct radeon_device *rdev)
 /*
  * ASIC
  */
+
+static struct radeon_asic_ring r100_gfx_ring = {
+	.ib_execute = &r100_ring_ib_execute,
+	.emit_fence = &r100_fence_ring_emit,
+	.emit_semaphore = &r100_semaphore_ring_emit,
+	.cs_parse = &r100_cs_parse,
+	.ring_start = &r100_ring_start,
+	.ring_test = &r100_ring_test,
+	.ib_test = &r100_ib_test,
+	.is_lockup = &r100_gpu_is_lockup,
+	.get_rptr = &radeon_ring_generic_get_rptr,
+	.get_wptr = &radeon_ring_generic_get_wptr,
+	.set_wptr = &radeon_ring_generic_set_wptr,
+};
+
 static struct radeon_asic r100_asic = {
 	.init = &r100_init,
 	.fini = &r100_fini,
@@ -187,19 +202,7 @@ static struct radeon_asic r100_asic = {
 		.set_page = &r100_pci_gart_set_page,
 	},
 	.ring = {
-		[RADEON_RING_TYPE_GFX_INDEX] = {
-			.ib_execute = &r100_ring_ib_execute,
-			.emit_fence = &r100_fence_ring_emit,
-			.emit_semaphore = &r100_semaphore_ring_emit,
-			.cs_parse = &r100_cs_parse,
-			.ring_start = &r100_ring_start,
-			.ring_test = &r100_ring_test,
-			.ib_test = &r100_ib_test,
-			.is_lockup = &r100_gpu_is_lockup,
-			.get_rptr = &radeon_ring_generic_get_rptr,
-			.get_wptr = &radeon_ring_generic_get_wptr,
-			.set_wptr = &radeon_ring_generic_set_wptr,
-		}
+		[RADEON_RING_TYPE_GFX_INDEX] = &r100_gfx_ring
 	},
 	.irq = {
 		.set = &r100_irq_set,
@@ -266,19 +269,7 @@ static struct radeon_asic r200_asic = {
 		.set_page = &r100_pci_gart_set_page,
 	},
 	.ring = {
-		[RADEON_RING_TYPE_GFX_INDEX] = {
-			.ib_execute = &r100_ring_ib_execute,
-			.emit_fence = &r100_fence_ring_emit,
-			.emit_semaphore = &r100_semaphore_ring_emit,
-			.cs_parse = &r100_cs_parse,
-			.ring_start = &r100_ring_start,
-			.ring_test = &r100_ring_test,
-			.ib_test = &r100_ib_test,
-			.is_lockup = &r100_gpu_is_lockup,
-			.get_rptr = &radeon_ring_generic_get_rptr,
-			.get_wptr = &radeon_ring_generic_get_wptr,
-			.set_wptr = &radeon_ring_generic_set_wptr,
-		}
+		[RADEON_RING_TYPE_GFX_INDEX] = &r100_gfx_ring
 	},
 	.irq = {
 		.set = &r100_irq_set,
@@ -330,6 +321,20 @@ static struct radeon_asic r200_asic = {
 	},
 };
 
+static struct radeon_asic_ring r300_gfx_ring = {
+	.ib_execute = &r100_ring_ib_execute,
+	.emit_fence = &r300_fence_ring_emit,
+	.emit_semaphore = &r100_semaphore_ring_emit,
+	.cs_parse = &r300_cs_parse,
+	.ring_start = &r300_ring_start,
+	.ring_test = &r100_ring_test,
+	.ib_test = &r100_ib_test,
+	.is_lockup = &r100_gpu_is_lockup,
+	.get_rptr = &radeon_ring_generic_get_rptr,
+	.get_wptr = &radeon_ring_generic_get_wptr,
+	.set_wptr = &radeon_ring_generic_set_wptr,
+};
+
 static struct radeon_asic r300_asic = {
 	.init = &r300_init,
 	.fini = &r300_fini,
@@ -345,19 +350,7 @@ static struct radeon_asic r300_asic = {
 		.set_page = &r100_pci_gart_set_page,
 	},
 	.ring = {
-		[RADEON_RING_TYPE_GFX_INDEX] = {
-			.ib_execute = &r100_ring_ib_execute,
-			.emit_fence = &r300_fence_ring_emit,
-			.emit_semaphore = &r100_semaphore_ring_emit,
-			.cs_parse = &r300_cs_parse,
-			.ring_start = &r300_ring_start,
-			.ring_test = &r100_ring_test,
-			.ib_test = &r100_ib_test,
-			.is_lockup = &r100_gpu_is_lockup,
-			.get_rptr = &radeon_ring_generic_get_rptr,
-			.get_wptr = &radeon_ring_generic_get_wptr,
-			.set_wptr = &radeon_ring_generic_set_wptr,
-		}
+		[RADEON_RING_TYPE_GFX_INDEX] = &r300_gfx_ring
 	},
 	.irq = {
 		.set = &r100_irq_set,
@@ -424,19 +417,7 @@ static struct radeon_asic r300_asic_pcie = {
 		.set_page = &rv370_pcie_gart_set_page,
 	},
 	.ring = {
-		[RADEON_RING_TYPE_GFX_INDEX] = {
-			.ib_execute = &r100_ring_ib_execute,
-			.emit_fence = &r300_fence_ring_emit,
-			.emit_semaphore = &r100_semaphore_ring_emit,
-			.cs_parse = &r300_cs_parse,
-			.ring_start = &r300_ring_start,
-			.ring_test = &r100_ring_test,
-			.ib_test = &r100_ib_test,
-			.is_lockup = &r100_gpu_is_lockup,
-			.get_rptr = &radeon_ring_generic_get_rptr,
-			.get_wptr = &radeon_ring_generic_get_wptr,
-			.set_wptr = &radeon_ring_generic_set_wptr,
-		}
+		[RADEON_RING_TYPE_GFX_INDEX] = &r300_gfx_ring
 	},
 	.irq = {
 		.set = &r100_irq_set,
@@ -503,19 +484,7 @@ static struct radeon_asic r420_asic = {
 		.set_page = &rv370_pcie_gart_set_page,
 	},
 	.ring = {
-		[RADEON_RING_TYPE_GFX_INDEX] = {
-			.ib_execute = &r100_ring_ib_execute,
-			.emit_fence = &r300_fence_ring_emit,
-			.emit_semaphore = &r100_semaphore_ring_emit,
-			.cs_parse = &r300_cs_parse,
-			.ring_start = &r300_ring_start,
-			.ring_test = &r100_ring_test,
-			.ib_test = &r100_ib_test,
-			.is_lockup = &r100_gpu_is_lockup,
-			.get_rptr = &radeon_ring_generic_get_rptr,
-			.get_wptr = &radeon_ring_generic_get_wptr,
-			.set_wptr = &radeon_ring_generic_set_wptr,
-		}
+		[RADEON_RING_TYPE_GFX_INDEX] = &r300_gfx_ring
 	},
 	.irq = {
 		.set = &r100_irq_set,
@@ -582,19 +551,7 @@ static struct radeon_asic rs400_asic = {
 		.set_page = &rs400_gart_set_page,
 	},
 	.ring = {
-		[RADEON_RING_TYPE_GFX_INDEX] = {
-			.ib_execute = &r100_ring_ib_execute,
-			.emit_fence = &r300_fence_ring_emit,
-			.emit_semaphore = &r100_semaphore_ring_emit,
-			.cs_parse = &r300_cs_parse,
-			.ring_start = &r300_ring_start,
-			.ring_test = &r100_ring_test,
-			.ib_test = &r100_ib_test,
-			.is_lockup = &r100_gpu_is_lockup,
-			.get_rptr = &radeon_ring_generic_get_rptr,
-			.get_wptr = &radeon_ring_generic_get_wptr,
-			.set_wptr = &radeon_ring_generic_set_wptr,
-		}
+		[RADEON_RING_TYPE_GFX_INDEX] = &r300_gfx_ring
 	},
 	.irq = {
 		.set = &r100_irq_set,
@@ -661,19 +618,7 @@ static struct radeon_asic rs600_asic = {
 		.set_page = &rs600_gart_set_page,
 	},
 	.ring = {
-		[RADEON_RING_TYPE_GFX_INDEX] = {
-			.ib_execute = &r100_ring_ib_execute,
-			.emit_fence = &r300_fence_ring_emit,
-			.emit_semaphore = &r100_semaphore_ring_emit,
-			.cs_parse = &r300_cs_parse,
-			.ring_start = &r300_ring_start,
-			.ring_test = &r100_ring_test,
-			.ib_test = &r100_ib_test,
-			.is_lockup = &r100_gpu_is_lockup,
-			.get_rptr = &radeon_ring_generic_get_rptr,
-			.get_wptr = &radeon_ring_generic_get_wptr,
-			.set_wptr = &radeon_ring_generic_set_wptr,
-		}
+		[RADEON_RING_TYPE_GFX_INDEX] = &r300_gfx_ring
 	},
 	.irq = {
 		.set = &rs600_irq_set,
@@ -742,19 +687,7 @@ static struct radeon_asic rs690_asic = {
 		.set_page = &rs400_gart_set_page,
 	},
 	.ring = {
-		[RADEON_RING_TYPE_GFX_INDEX] = {
-			.ib_execute = &r100_ring_ib_execute,
-			.emit_fence = &r300_fence_ring_emit,
-			.emit_semaphore = &r100_semaphore_ring_emit,
-			.cs_parse = &r300_cs_parse,
-			.ring_start = &r300_ring_start,
-			.ring_test = &r100_ring_test,
-			.ib_test = &r100_ib_test,
-			.is_lockup = &r100_gpu_is_lockup,
-			.get_rptr = &radeon_ring_generic_get_rptr,
-			.get_wptr = &radeon_ring_generic_get_wptr,
-			.set_wptr = &radeon_ring_generic_set_wptr,
-		}
+		[RADEON_RING_TYPE_GFX_INDEX] = &r300_gfx_ring
 	},
 	.irq = {
 		.set = &rs600_irq_set,
@@ -823,19 +756,7 @@ static struct radeon_asic rv515_asic = {
 		.set_page = &rv370_pcie_gart_set_page,
 	},
 	.ring = {
-		[RADEON_RING_TYPE_GFX_INDEX] = {
-			.ib_execute = &r100_ring_ib_execute,
-			.emit_fence = &r300_fence_ring_emit,
-			.emit_semaphore = &r100_semaphore_ring_emit,
-			.cs_parse = &r300_cs_parse,
-			.ring_start = &rv515_ring_start,
-			.ring_test = &r100_ring_test,
-			.ib_test = &r100_ib_test,
-			.is_lockup = &r100_gpu_is_lockup,
-			.get_rptr = &radeon_ring_generic_get_rptr,
-			.get_wptr = &radeon_ring_generic_get_wptr,
-			.set_wptr = &radeon_ring_generic_set_wptr,
-		}
+		[RADEON_RING_TYPE_GFX_INDEX] = &r300_gfx_ring
 	},
 	.irq = {
 		.set = &rs600_irq_set,
@@ -902,19 +823,7 @@ static struct radeon_asic r520_asic = {
 		.set_page = &rv370_pcie_gart_set_page,
 	},
 	.ring = {
-		[RADEON_RING_TYPE_GFX_INDEX] = {
-			.ib_execute = &r100_ring_ib_execute,
-			.emit_fence = &r300_fence_ring_emit,
-			.emit_semaphore = &r100_semaphore_ring_emit,
-			.cs_parse = &r300_cs_parse,
-			.ring_start = &rv515_ring_start,
-			.ring_test = &r100_ring_test,
-			.ib_test = &r100_ib_test,
-			.is_lockup = &r100_gpu_is_lockup,
-			.get_rptr = &radeon_ring_generic_get_rptr,
-			.get_wptr = &radeon_ring_generic_get_wptr,
-			.set_wptr = &radeon_ring_generic_set_wptr,
-		}
+		[RADEON_RING_TYPE_GFX_INDEX] = &r300_gfx_ring
 	},
 	.irq = {
 		.set = &rs600_irq_set,
@@ -966,6 +875,32 @@ static struct radeon_asic r520_asic = {
 	},
 };
 
+static struct radeon_asic_ring r600_gfx_ring = {
+	.ib_execute = &r600_ring_ib_execute,
+	.emit_fence = &r600_fence_ring_emit,
+	.emit_semaphore = &r600_semaphore_ring_emit,
+	.cs_parse = &r600_cs_parse,
+	.ring_test = &r600_ring_test,
+	.ib_test = &r600_ib_test,
+	.is_lockup = &r600_gfx_is_lockup,
+	.get_rptr = &radeon_ring_generic_get_rptr,
+	.get_wptr = &radeon_ring_generic_get_wptr,
+	.set_wptr = &radeon_ring_generic_set_wptr,
+};
+
+static struct radeon_asic_ring r600_dma_ring = {
+	.ib_execute = &r600_dma_ring_ib_execute,
+	.emit_fence = &r600_dma_fence_ring_emit,
+	.emit_semaphore = &r600_dma_semaphore_ring_emit,
+	.cs_parse = &r600_dma_cs_parse,
+	.ring_test = &r600_dma_ring_test,
+	.ib_test = &r600_dma_ib_test,
+	.is_lockup = &r600_dma_is_lockup,
+	.get_rptr = &r600_dma_get_rptr,
+	.get_wptr = &r600_dma_get_wptr,
+	.set_wptr = &r600_dma_set_wptr,
+};
+
 static struct radeon_asic r600_asic = {
 	.init = &r600_init,
 	.fini = &r600_fini,
@@ -983,30 +918,8 @@ static struct radeon_asic r600_asic = {
 		.set_page = &rs600_gart_set_page,
 	},
 	.ring = {
-		[RADEON_RING_TYPE_GFX_INDEX] = {
-			.ib_execute = &r600_ring_ib_execute,
-			.emit_fence = &r600_fence_ring_emit,
-			.emit_semaphore = &r600_semaphore_ring_emit,
-			.cs_parse = &r600_cs_parse,
-			.ring_test = &r600_ring_test,
-			.ib_test = &r600_ib_test,
-			.is_lockup = &r600_gfx_is_lockup,
-			.get_rptr = &radeon_ring_generic_get_rptr,
-			.get_wptr = &radeon_ring_generic_get_wptr,
-			.set_wptr = &radeon_ring_generic_set_wptr,
-		},
-		[R600_RING_TYPE_DMA_INDEX] = {
-			.ib_execute = &r600_dma_ring_ib_execute,
-			.emit_fence = &r600_dma_fence_ring_emit,
-			.emit_semaphore = &r600_dma_semaphore_ring_emit,
-			.cs_parse = &r600_dma_cs_parse,
-			.ring_test = &r600_dma_ring_test,
-			.ib_test = &r600_dma_ib_test,
-			.is_lockup = &r600_dma_is_lockup,
-			.get_rptr = &radeon_ring_generic_get_rptr,
-			.get_wptr = &radeon_ring_generic_get_wptr,
-			.set_wptr = &radeon_ring_generic_set_wptr,
-		}
+		[RADEON_RING_TYPE_GFX_INDEX] = &r600_gfx_ring,
+		[R600_RING_TYPE_DMA_INDEX] = &r600_dma_ring,
 	},
 	.irq = {
 		.set = &r600_irq_set,
@@ -1022,7 +935,7 @@ static struct radeon_asic r600_asic = {
 		.hdmi_setmode = &r600_hdmi_setmode,
 	},
 	.copy = {
-		.blit = &r600_copy_blit,
+		.blit = &r600_copy_cpdma,
 		.blit_ring_index = RADEON_RING_TYPE_GFX_INDEX,
 		.dma = &r600_copy_dma,
 		.dma_ring_index = R600_RING_TYPE_DMA_INDEX,
@@ -1078,30 +991,8 @@ static struct radeon_asic rv6xx_asic = {
 		.set_page = &rs600_gart_set_page,
 	},
 	.ring = {
-		[RADEON_RING_TYPE_GFX_INDEX] = {
-			.ib_execute = &r600_ring_ib_execute,
-			.emit_fence = &r600_fence_ring_emit,
-			.emit_semaphore = &r600_semaphore_ring_emit,
-			.cs_parse = &r600_cs_parse,
-			.ring_test = &r600_ring_test,
-			.ib_test = &r600_ib_test,
-			.is_lockup = &r600_gfx_is_lockup,
-			.get_rptr = &radeon_ring_generic_get_rptr,
-			.get_wptr = &radeon_ring_generic_get_wptr,
-			.set_wptr = &radeon_ring_generic_set_wptr,
-		},
-		[R600_RING_TYPE_DMA_INDEX] = {
-			.ib_execute = &r600_dma_ring_ib_execute,
-			.emit_fence = &r600_dma_fence_ring_emit,
-			.emit_semaphore = &r600_dma_semaphore_ring_emit,
-			.cs_parse = &r600_dma_cs_parse,
-			.ring_test = &r600_dma_ring_test,
-			.ib_test = &r600_dma_ib_test,
-			.is_lockup = &r600_dma_is_lockup,
-			.get_rptr = &radeon_ring_generic_get_rptr,
-			.get_wptr = &radeon_ring_generic_get_wptr,
-			.set_wptr = &radeon_ring_generic_set_wptr,
-		}
+		[RADEON_RING_TYPE_GFX_INDEX] = &r600_gfx_ring,
+		[R600_RING_TYPE_DMA_INDEX] = &r600_dma_ring,
 	},
 	.irq = {
 		.set = &r600_irq_set,
@@ -1113,9 +1004,11 @@ static struct radeon_asic rv6xx_asic = {
 		.wait_for_vblank = &avivo_wait_for_vblank,
 		.set_backlight_level = &atombios_set_backlight_level,
 		.get_backlight_level = &atombios_get_backlight_level,
+		.hdmi_enable = &r600_hdmi_enable,
+		.hdmi_setmode = &r600_hdmi_setmode,
 	},
 	.copy = {
-		.blit = &r600_copy_blit,
+		.blit = &r600_copy_cpdma,
 		.blit_ring_index = RADEON_RING_TYPE_GFX_INDEX,
 		.dma = &r600_copy_dma,
 		.dma_ring_index = R600_RING_TYPE_DMA_INDEX,
@@ -1146,6 +1039,7 @@ static struct radeon_asic rv6xx_asic = {
 		.set_pcie_lanes = &r600_set_pcie_lanes,
 		.set_clock_gating = NULL,
 		.get_temperature = &rv6xx_get_temp,
+		.set_uvd_clocks = &r600_set_uvd_clocks,
 	},
 	.dpm = {
 		.init = &rv6xx_dpm_init,
@@ -1187,30 +1081,8 @@ static struct radeon_asic rs780_asic = {
 		.set_page = &rs600_gart_set_page,
 	},
 	.ring = {
-		[RADEON_RING_TYPE_GFX_INDEX] = {
-			.ib_execute = &r600_ring_ib_execute,
-			.emit_fence = &r600_fence_ring_emit,
-			.emit_semaphore = &r600_semaphore_ring_emit,
-			.cs_parse = &r600_cs_parse,
-			.ring_test = &r600_ring_test,
-			.ib_test = &r600_ib_test,
-			.is_lockup = &r600_gfx_is_lockup,
-			.get_rptr = &radeon_ring_generic_get_rptr,
-			.get_wptr = &radeon_ring_generic_get_wptr,
-			.set_wptr = &radeon_ring_generic_set_wptr,
-		},
-		[R600_RING_TYPE_DMA_INDEX] = {
-			.ib_execute = &r600_dma_ring_ib_execute,
-			.emit_fence = &r600_dma_fence_ring_emit,
-			.emit_semaphore = &r600_dma_semaphore_ring_emit,
-			.cs_parse = &r600_dma_cs_parse,
-			.ring_test = &r600_dma_ring_test,
-			.ib_test = &r600_dma_ib_test,
-			.is_lockup = &r600_dma_is_lockup,
-			.get_rptr = &radeon_ring_generic_get_rptr,
-			.get_wptr = &radeon_ring_generic_get_wptr,
-			.set_wptr = &radeon_ring_generic_set_wptr,
-		}
+		[RADEON_RING_TYPE_GFX_INDEX] = &r600_gfx_ring,
+		[R600_RING_TYPE_DMA_INDEX] = &r600_dma_ring,
 	},
 	.irq = {
 		.set = &r600_irq_set,
@@ -1226,7 +1098,7 @@ static struct radeon_asic rs780_asic = {
 		.hdmi_setmode = &r600_hdmi_setmode,
 	},
 	.copy = {
-		.blit = &r600_copy_blit,
+		.blit = &r600_copy_cpdma,
 		.blit_ring_index = RADEON_RING_TYPE_GFX_INDEX,
 		.dma = &r600_copy_dma,
 		.dma_ring_index = R600_RING_TYPE_DMA_INDEX,
@@ -1257,6 +1129,7 @@ static struct radeon_asic rs780_asic = {
 		.set_pcie_lanes = NULL,
 		.set_clock_gating = NULL,
 		.get_temperature = &rv6xx_get_temp,
+		.set_uvd_clocks = &r600_set_uvd_clocks,
 	},
 	.dpm = {
 		.init = &rs780_dpm_init,
@@ -1272,6 +1145,7 @@ static struct radeon_asic rs780_asic = {
 		.get_mclk = &rs780_dpm_get_mclk,
 		.print_power_state = &rs780_dpm_print_power_state,
 		.debugfs_print_current_performance_level = &rs780_dpm_debugfs_print_current_performance_level,
+		.force_performance_level = &rs780_dpm_force_performance_level,
 	},
 	.pflip = {
 		.pre_page_flip = &rs600_pre_page_flip,
@@ -1280,6 +1154,19 @@ static struct radeon_asic rs780_asic = {
 	},
 };
 
+static struct radeon_asic_ring rv770_uvd_ring = {
+	.ib_execute = &uvd_v1_0_ib_execute,
+	.emit_fence = &uvd_v2_2_fence_emit,
+	.emit_semaphore = &uvd_v1_0_semaphore_emit,
+	.cs_parse = &radeon_uvd_cs_parse,
+	.ring_test = &uvd_v1_0_ring_test,
+	.ib_test = &uvd_v1_0_ib_test,
+	.is_lockup = &radeon_ring_test_lockup,
+	.get_rptr = &uvd_v1_0_get_rptr,
+	.get_wptr = &uvd_v1_0_get_wptr,
+	.set_wptr = &uvd_v1_0_set_wptr,
+};
+
 static struct radeon_asic rv770_asic = {
 	.init = &rv770_init,
 	.fini = &rv770_fini,
@@ -1297,42 +1184,9 @@ static struct radeon_asic rv770_asic = {
 		.set_page = &rs600_gart_set_page,
 	},
 	.ring = {
-		[RADEON_RING_TYPE_GFX_INDEX] = {
-			.ib_execute = &r600_ring_ib_execute,
-			.emit_fence = &r600_fence_ring_emit,
-			.emit_semaphore = &r600_semaphore_ring_emit,
-			.cs_parse = &r600_cs_parse,
-			.ring_test = &r600_ring_test,
-			.ib_test = &r600_ib_test,
-			.is_lockup = &r600_gfx_is_lockup,
-			.get_rptr = &radeon_ring_generic_get_rptr,
-			.get_wptr = &radeon_ring_generic_get_wptr,
-			.set_wptr = &radeon_ring_generic_set_wptr,
-		},
-		[R600_RING_TYPE_DMA_INDEX] = {
-			.ib_execute = &r600_dma_ring_ib_execute,
-			.emit_fence = &r600_dma_fence_ring_emit,
-			.emit_semaphore = &r600_dma_semaphore_ring_emit,
-			.cs_parse = &r600_dma_cs_parse,
-			.ring_test = &r600_dma_ring_test,
-			.ib_test = &r600_dma_ib_test,
-			.is_lockup = &r600_dma_is_lockup,
-			.get_rptr = &radeon_ring_generic_get_rptr,
-			.get_wptr = &radeon_ring_generic_get_wptr,
-			.set_wptr = &radeon_ring_generic_set_wptr,
-		},
-		[R600_RING_TYPE_UVD_INDEX] = {
-			.ib_execute = &r600_uvd_ib_execute,
-			.emit_fence = &r600_uvd_fence_emit,
-			.emit_semaphore = &r600_uvd_semaphore_emit,
-			.cs_parse = &radeon_uvd_cs_parse,
-			.ring_test = &r600_uvd_ring_test,
-			.ib_test = &r600_uvd_ib_test,
-			.is_lockup = &radeon_ring_test_lockup,
-			.get_rptr = &radeon_ring_generic_get_rptr,
-			.get_wptr = &radeon_ring_generic_get_wptr,
-			.set_wptr = &radeon_ring_generic_set_wptr,
-		}
+		[RADEON_RING_TYPE_GFX_INDEX] = &r600_gfx_ring,
+		[R600_RING_TYPE_DMA_INDEX] = &r600_dma_ring,
+		[R600_RING_TYPE_UVD_INDEX] = &rv770_uvd_ring,
 	},
 	.irq = {
 		.set = &r600_irq_set,
@@ -1348,7 +1202,7 @@ static struct radeon_asic rv770_asic = {
 		.hdmi_setmode = &r600_hdmi_setmode,
 	},
 	.copy = {
-		.blit = &r600_copy_blit,
+		.blit = &r600_copy_cpdma,
 		.blit_ring_index = RADEON_RING_TYPE_GFX_INDEX,
 		.dma = &rv770_copy_dma,
 		.dma_ring_index = R600_RING_TYPE_DMA_INDEX,
@@ -1405,6 +1259,32 @@ static struct radeon_asic rv770_asic = {
 	},
 };
 
+static struct radeon_asic_ring evergreen_gfx_ring = {
+	.ib_execute = &evergreen_ring_ib_execute,
+	.emit_fence = &r600_fence_ring_emit,
+	.emit_semaphore = &r600_semaphore_ring_emit,
+	.cs_parse = &evergreen_cs_parse,
+	.ring_test = &r600_ring_test,
+	.ib_test = &r600_ib_test,
+	.is_lockup = &evergreen_gfx_is_lockup,
+	.get_rptr = &radeon_ring_generic_get_rptr,
+	.get_wptr = &radeon_ring_generic_get_wptr,
+	.set_wptr = &radeon_ring_generic_set_wptr,
+};
+
+static struct radeon_asic_ring evergreen_dma_ring = {
+	.ib_execute = &evergreen_dma_ring_ib_execute,
+	.emit_fence = &evergreen_dma_fence_ring_emit,
+	.emit_semaphore = &r600_dma_semaphore_ring_emit,
+	.cs_parse = &evergreen_dma_cs_parse,
+	.ring_test = &r600_dma_ring_test,
+	.ib_test = &r600_dma_ib_test,
+	.is_lockup = &evergreen_dma_is_lockup,
+	.get_rptr = &r600_dma_get_rptr,
+	.get_wptr = &r600_dma_get_wptr,
+	.set_wptr = &r600_dma_set_wptr,
+};
+
 static struct radeon_asic evergreen_asic = {
 	.init = &evergreen_init,
 	.fini = &evergreen_fini,
@@ -1422,42 +1302,9 @@ static struct radeon_asic evergreen_asic = {
 		.set_page = &rs600_gart_set_page,
 	},
 	.ring = {
-		[RADEON_RING_TYPE_GFX_INDEX] = {
-			.ib_execute = &evergreen_ring_ib_execute,
-			.emit_fence = &r600_fence_ring_emit,
-			.emit_semaphore = &r600_semaphore_ring_emit,
-			.cs_parse = &evergreen_cs_parse,
-			.ring_test = &r600_ring_test,
-			.ib_test = &r600_ib_test,
-			.is_lockup = &evergreen_gfx_is_lockup,
-			.get_rptr = &radeon_ring_generic_get_rptr,
-			.get_wptr = &radeon_ring_generic_get_wptr,
-			.set_wptr = &radeon_ring_generic_set_wptr,
-		},
-		[R600_RING_TYPE_DMA_INDEX] = {
-			.ib_execute = &evergreen_dma_ring_ib_execute,
-			.emit_fence = &evergreen_dma_fence_ring_emit,
-			.emit_semaphore = &r600_dma_semaphore_ring_emit,
-			.cs_parse = &evergreen_dma_cs_parse,
-			.ring_test = &r600_dma_ring_test,
-			.ib_test = &r600_dma_ib_test,
-			.is_lockup = &evergreen_dma_is_lockup,
-			.get_rptr = &radeon_ring_generic_get_rptr,
-			.get_wptr = &radeon_ring_generic_get_wptr,
-			.set_wptr = &radeon_ring_generic_set_wptr,
-		},
-		[R600_RING_TYPE_UVD_INDEX] = {
-			.ib_execute = &r600_uvd_ib_execute,
-			.emit_fence = &r600_uvd_fence_emit,
-			.emit_semaphore = &r600_uvd_semaphore_emit,
-			.cs_parse = &radeon_uvd_cs_parse,
-			.ring_test = &r600_uvd_ring_test,
-			.ib_test = &r600_uvd_ib_test,
-			.is_lockup = &radeon_ring_test_lockup,
-			.get_rptr = &radeon_ring_generic_get_rptr,
-			.get_wptr = &radeon_ring_generic_get_wptr,
-			.set_wptr = &radeon_ring_generic_set_wptr,
-		}
+		[RADEON_RING_TYPE_GFX_INDEX] = &evergreen_gfx_ring,
+		[R600_RING_TYPE_DMA_INDEX] = &evergreen_dma_ring,
+		[R600_RING_TYPE_UVD_INDEX] = &rv770_uvd_ring,
 	},
 	.irq = {
 		.set = &evergreen_irq_set,
@@ -1473,7 +1320,7 @@ static struct radeon_asic evergreen_asic = {
 		.hdmi_setmode = &evergreen_hdmi_setmode,
 	},
 	.copy = {
-		.blit = &r600_copy_blit,
+		.blit = &r600_copy_cpdma,
 		.blit_ring_index = RADEON_RING_TYPE_GFX_INDEX,
 		.dma = &evergreen_copy_dma,
 		.dma_ring_index = R600_RING_TYPE_DMA_INDEX,
@@ -1547,42 +1394,9 @@ static struct radeon_asic sumo_asic = {
 		.set_page = &rs600_gart_set_page,
 	},
 	.ring = {
-		[RADEON_RING_TYPE_GFX_INDEX] = {
-			.ib_execute = &evergreen_ring_ib_execute,
-			.emit_fence = &r600_fence_ring_emit,
-			.emit_semaphore = &r600_semaphore_ring_emit,
-			.cs_parse = &evergreen_cs_parse,
-			.ring_test = &r600_ring_test,
-			.ib_test = &r600_ib_test,
-			.is_lockup = &evergreen_gfx_is_lockup,
-			.get_rptr = &radeon_ring_generic_get_rptr,
-			.get_wptr = &radeon_ring_generic_get_wptr,
-			.set_wptr = &radeon_ring_generic_set_wptr,
-		},
-		[R600_RING_TYPE_DMA_INDEX] = {
-			.ib_execute = &evergreen_dma_ring_ib_execute,
-			.emit_fence = &evergreen_dma_fence_ring_emit,
-			.emit_semaphore = &r600_dma_semaphore_ring_emit,
-			.cs_parse = &evergreen_dma_cs_parse,
-			.ring_test = &r600_dma_ring_test,
-			.ib_test = &r600_dma_ib_test,
-			.is_lockup = &evergreen_dma_is_lockup,
-			.get_rptr = &radeon_ring_generic_get_rptr,
-			.get_wptr = &radeon_ring_generic_get_wptr,
-			.set_wptr = &radeon_ring_generic_set_wptr,
-		},
-		[R600_RING_TYPE_UVD_INDEX] = {
-			.ib_execute = &r600_uvd_ib_execute,
-			.emit_fence = &r600_uvd_fence_emit,
-			.emit_semaphore = &r600_uvd_semaphore_emit,
-			.cs_parse = &radeon_uvd_cs_parse,
-			.ring_test = &r600_uvd_ring_test,
-			.ib_test = &r600_uvd_ib_test,
-			.is_lockup = &radeon_ring_test_lockup,
-			.get_rptr = &radeon_ring_generic_get_rptr,
-			.get_wptr = &radeon_ring_generic_get_wptr,
-			.set_wptr = &radeon_ring_generic_set_wptr,
-		}
+		[RADEON_RING_TYPE_GFX_INDEX] = &evergreen_gfx_ring,
+		[R600_RING_TYPE_DMA_INDEX] = &evergreen_dma_ring,
+		[R600_RING_TYPE_UVD_INDEX] = &rv770_uvd_ring,
 	},
 	.irq = {
 		.set = &evergreen_irq_set,
@@ -1598,7 +1412,7 @@ static struct radeon_asic sumo_asic = {
 		.hdmi_setmode = &evergreen_hdmi_setmode,
 	},
 	.copy = {
-		.blit = &r600_copy_blit,
+		.blit = &r600_copy_cpdma,
 		.blit_ring_index = RADEON_RING_TYPE_GFX_INDEX,
 		.dma = &evergreen_copy_dma,
 		.dma_ring_index = R600_RING_TYPE_DMA_INDEX,
@@ -1671,42 +1485,9 @@ static struct radeon_asic btc_asic = {
 		.set_page = &rs600_gart_set_page,
 	},
 	.ring = {
-		[RADEON_RING_TYPE_GFX_INDEX] = {
-			.ib_execute = &evergreen_ring_ib_execute,
-			.emit_fence = &r600_fence_ring_emit,
-			.emit_semaphore = &r600_semaphore_ring_emit,
-			.cs_parse = &evergreen_cs_parse,
-			.ring_test = &r600_ring_test,
-			.ib_test = &r600_ib_test,
-			.is_lockup = &evergreen_gfx_is_lockup,
-			.get_rptr = &radeon_ring_generic_get_rptr,
-			.get_wptr = &radeon_ring_generic_get_wptr,
-			.set_wptr = &radeon_ring_generic_set_wptr,
-		},
-		[R600_RING_TYPE_DMA_INDEX] = {
-			.ib_execute = &evergreen_dma_ring_ib_execute,
-			.emit_fence = &evergreen_dma_fence_ring_emit,
-			.emit_semaphore = &r600_dma_semaphore_ring_emit,
-			.cs_parse = &evergreen_dma_cs_parse,
-			.ring_test = &r600_dma_ring_test,
-			.ib_test = &r600_dma_ib_test,
-			.is_lockup = &evergreen_dma_is_lockup,
-			.get_rptr = &radeon_ring_generic_get_rptr,
-			.get_wptr = &radeon_ring_generic_get_wptr,
-			.set_wptr = &radeon_ring_generic_set_wptr,
-		},
-		[R600_RING_TYPE_UVD_INDEX] = {
-			.ib_execute = &r600_uvd_ib_execute,
-			.emit_fence = &r600_uvd_fence_emit,
-			.emit_semaphore = &r600_uvd_semaphore_emit,
-			.cs_parse = &radeon_uvd_cs_parse,
-			.ring_test = &r600_uvd_ring_test,
-			.ib_test = &r600_uvd_ib_test,
-			.is_lockup = &radeon_ring_test_lockup,
-			.get_rptr = &radeon_ring_generic_get_rptr,
-			.get_wptr = &radeon_ring_generic_get_wptr,
-			.set_wptr = &radeon_ring_generic_set_wptr,
-		}
+		[RADEON_RING_TYPE_GFX_INDEX] = &evergreen_gfx_ring,
+		[R600_RING_TYPE_DMA_INDEX] = &evergreen_dma_ring,
+		[R600_RING_TYPE_UVD_INDEX] = &rv770_uvd_ring,
 	},
 	.irq = {
 		.set = &evergreen_irq_set,
@@ -1722,7 +1503,7 @@ static struct radeon_asic btc_asic = {
 		.hdmi_setmode = &evergreen_hdmi_setmode,
 	},
 	.copy = {
-		.blit = &r600_copy_blit,
+		.blit = &r600_copy_cpdma,
 		.blit_ring_index = RADEON_RING_TYPE_GFX_INDEX,
 		.dma = &evergreen_copy_dma,
 		.dma_ring_index = R600_RING_TYPE_DMA_INDEX,
@@ -1779,6 +1560,49 @@ static struct radeon_asic btc_asic = {
 	},
 };
 
+static struct radeon_asic_ring cayman_gfx_ring = {
+	.ib_execute = &cayman_ring_ib_execute,
+	.ib_parse = &evergreen_ib_parse,
+	.emit_fence = &cayman_fence_ring_emit,
+	.emit_semaphore = &r600_semaphore_ring_emit,
+	.cs_parse = &evergreen_cs_parse,
+	.ring_test = &r600_ring_test,
+	.ib_test = &r600_ib_test,
+	.is_lockup = &cayman_gfx_is_lockup,
+	.vm_flush = &cayman_vm_flush,
+	.get_rptr = &radeon_ring_generic_get_rptr,
+	.get_wptr = &radeon_ring_generic_get_wptr,
+	.set_wptr = &radeon_ring_generic_set_wptr,
+};
+
+static struct radeon_asic_ring cayman_dma_ring = {
+	.ib_execute = &cayman_dma_ring_ib_execute,
+	.ib_parse = &evergreen_dma_ib_parse,
+	.emit_fence = &evergreen_dma_fence_ring_emit,
+	.emit_semaphore = &r600_dma_semaphore_ring_emit,
+	.cs_parse = &evergreen_dma_cs_parse,
+	.ring_test = &r600_dma_ring_test,
+	.ib_test = &r600_dma_ib_test,
+	.is_lockup = &cayman_dma_is_lockup,
+	.vm_flush = &cayman_dma_vm_flush,
+	.get_rptr = &r600_dma_get_rptr,
+	.get_wptr = &r600_dma_get_wptr,
+	.set_wptr = &r600_dma_set_wptr
+};
+
+static struct radeon_asic_ring cayman_uvd_ring = {
+	.ib_execute = &uvd_v1_0_ib_execute,
+	.emit_fence = &uvd_v2_2_fence_emit,
+	.emit_semaphore = &uvd_v3_1_semaphore_emit,
+	.cs_parse = &radeon_uvd_cs_parse,
+	.ring_test = &uvd_v1_0_ring_test,
+	.ib_test = &uvd_v1_0_ib_test,
+	.is_lockup = &radeon_ring_test_lockup,
+	.get_rptr = &uvd_v1_0_get_rptr,
+	.get_wptr = &uvd_v1_0_get_wptr,
+	.set_wptr = &uvd_v1_0_set_wptr,
+};
+
 static struct radeon_asic cayman_asic = {
 	.init = &cayman_init,
 	.fini = &cayman_fini,
@@ -1802,88 +1626,12 @@ static struct radeon_asic cayman_asic = {
 		.set_page = &cayman_vm_set_page,
 	},
 	.ring = {
-		[RADEON_RING_TYPE_GFX_INDEX] = {
-			.ib_execute = &cayman_ring_ib_execute,
-			.ib_parse = &evergreen_ib_parse,
-			.emit_fence = &cayman_fence_ring_emit,
-			.emit_semaphore = &r600_semaphore_ring_emit,
-			.cs_parse = &evergreen_cs_parse,
-			.ring_test = &r600_ring_test,
-			.ib_test = &r600_ib_test,
-			.is_lockup = &cayman_gfx_is_lockup,
-			.vm_flush = &cayman_vm_flush,
-			.get_rptr = &radeon_ring_generic_get_rptr,
-			.get_wptr = &radeon_ring_generic_get_wptr,
-			.set_wptr = &radeon_ring_generic_set_wptr,
-		},
-		[CAYMAN_RING_TYPE_CP1_INDEX] = {
-			.ib_execute = &cayman_ring_ib_execute,
-			.ib_parse = &evergreen_ib_parse,
-			.emit_fence = &cayman_fence_ring_emit,
-			.emit_semaphore = &r600_semaphore_ring_emit,
-			.cs_parse = &evergreen_cs_parse,
-			.ring_test = &r600_ring_test,
-			.ib_test = &r600_ib_test,
-			.is_lockup = &cayman_gfx_is_lockup,
-			.vm_flush = &cayman_vm_flush,
-			.get_rptr = &radeon_ring_generic_get_rptr,
-			.get_wptr = &radeon_ring_generic_get_wptr,
-			.set_wptr = &radeon_ring_generic_set_wptr,
-		},
-		[CAYMAN_RING_TYPE_CP2_INDEX] = {
-			.ib_execute = &cayman_ring_ib_execute,
-			.ib_parse = &evergreen_ib_parse,
-			.emit_fence = &cayman_fence_ring_emit,
-			.emit_semaphore = &r600_semaphore_ring_emit,
-			.cs_parse = &evergreen_cs_parse,
-			.ring_test = &r600_ring_test,
-			.ib_test = &r600_ib_test,
-			.is_lockup = &cayman_gfx_is_lockup,
-			.vm_flush = &cayman_vm_flush,
-			.get_rptr = &radeon_ring_generic_get_rptr,
-			.get_wptr = &radeon_ring_generic_get_wptr,
-			.set_wptr = &radeon_ring_generic_set_wptr,
-		},
-		[R600_RING_TYPE_DMA_INDEX] = {
-			.ib_execute = &cayman_dma_ring_ib_execute,
-			.ib_parse = &evergreen_dma_ib_parse,
-			.emit_fence = &evergreen_dma_fence_ring_emit,
-			.emit_semaphore = &r600_dma_semaphore_ring_emit,
-			.cs_parse = &evergreen_dma_cs_parse,
-			.ring_test = &r600_dma_ring_test,
-			.ib_test = &r600_dma_ib_test,
-			.is_lockup = &cayman_dma_is_lockup,
-			.vm_flush = &cayman_dma_vm_flush,
-			.get_rptr = &radeon_ring_generic_get_rptr,
-			.get_wptr = &radeon_ring_generic_get_wptr,
-			.set_wptr = &radeon_ring_generic_set_wptr,
-		},
-		[CAYMAN_RING_TYPE_DMA1_INDEX] = {
-			.ib_execute = &cayman_dma_ring_ib_execute,
-			.ib_parse = &evergreen_dma_ib_parse,
-			.emit_fence = &evergreen_dma_fence_ring_emit,
-			.emit_semaphore = &r600_dma_semaphore_ring_emit,
-			.cs_parse = &evergreen_dma_cs_parse,
-			.ring_test = &r600_dma_ring_test,
-			.ib_test = &r600_dma_ib_test,
-			.is_lockup = &cayman_dma_is_lockup,
-			.vm_flush = &cayman_dma_vm_flush,
-			.get_rptr = &radeon_ring_generic_get_rptr,
-			.get_wptr = &radeon_ring_generic_get_wptr,
-			.set_wptr = &radeon_ring_generic_set_wptr,
-		},
-		[R600_RING_TYPE_UVD_INDEX] = {
-			.ib_execute = &r600_uvd_ib_execute,
-			.emit_fence = &r600_uvd_fence_emit,
-			.emit_semaphore = &cayman_uvd_semaphore_emit,
-			.cs_parse = &radeon_uvd_cs_parse,
-			.ring_test = &r600_uvd_ring_test,
-			.ib_test = &r600_uvd_ib_test,
-			.is_lockup = &radeon_ring_test_lockup,
-			.get_rptr = &radeon_ring_generic_get_rptr,
-			.get_wptr = &radeon_ring_generic_get_wptr,
-			.set_wptr = &radeon_ring_generic_set_wptr,
-		}
+		[RADEON_RING_TYPE_GFX_INDEX] = &cayman_gfx_ring,
+		[CAYMAN_RING_TYPE_CP1_INDEX] = &cayman_gfx_ring,
+		[CAYMAN_RING_TYPE_CP2_INDEX] = &cayman_gfx_ring,
+		[R600_RING_TYPE_DMA_INDEX] = &cayman_dma_ring,
+		[CAYMAN_RING_TYPE_DMA1_INDEX] = &cayman_dma_ring,
+		[R600_RING_TYPE_UVD_INDEX] = &cayman_uvd_ring,
 	},
 	.irq = {
 		.set = &evergreen_irq_set,
@@ -1899,7 +1647,7 @@ static struct radeon_asic cayman_asic = {
 		.hdmi_setmode = &evergreen_hdmi_setmode,
 	},
 	.copy = {
-		.blit = &r600_copy_blit,
+		.blit = &r600_copy_cpdma,
 		.blit_ring_index = RADEON_RING_TYPE_GFX_INDEX,
 		.dma = &evergreen_copy_dma,
 		.dma_ring_index = R600_RING_TYPE_DMA_INDEX,
@@ -1979,88 +1727,12 @@ static struct radeon_asic trinity_asic = {
 		.set_page = &cayman_vm_set_page,
 	},
 	.ring = {
-		[RADEON_RING_TYPE_GFX_INDEX] = {
-			.ib_execute = &cayman_ring_ib_execute,
-			.ib_parse = &evergreen_ib_parse,
-			.emit_fence = &cayman_fence_ring_emit,
-			.emit_semaphore = &r600_semaphore_ring_emit,
-			.cs_parse = &evergreen_cs_parse,
-			.ring_test = &r600_ring_test,
-			.ib_test = &r600_ib_test,
-			.is_lockup = &cayman_gfx_is_lockup,
-			.vm_flush = &cayman_vm_flush,
-			.get_rptr = &radeon_ring_generic_get_rptr,
-			.get_wptr = &radeon_ring_generic_get_wptr,
-			.set_wptr = &radeon_ring_generic_set_wptr,
-		},
-		[CAYMAN_RING_TYPE_CP1_INDEX] = {
-			.ib_execute = &cayman_ring_ib_execute,
-			.ib_parse = &evergreen_ib_parse,
-			.emit_fence = &cayman_fence_ring_emit,
-			.emit_semaphore = &r600_semaphore_ring_emit,
-			.cs_parse = &evergreen_cs_parse,
-			.ring_test = &r600_ring_test,
-			.ib_test = &r600_ib_test,
-			.is_lockup = &cayman_gfx_is_lockup,
-			.vm_flush = &cayman_vm_flush,
-			.get_rptr = &radeon_ring_generic_get_rptr,
-			.get_wptr = &radeon_ring_generic_get_wptr,
-			.set_wptr = &radeon_ring_generic_set_wptr,
-		},
-		[CAYMAN_RING_TYPE_CP2_INDEX] = {
-			.ib_execute = &cayman_ring_ib_execute,
-			.ib_parse = &evergreen_ib_parse,
-			.emit_fence = &cayman_fence_ring_emit,
-			.emit_semaphore = &r600_semaphore_ring_emit,
-			.cs_parse = &evergreen_cs_parse,
-			.ring_test = &r600_ring_test,
-			.ib_test = &r600_ib_test,
-			.is_lockup = &cayman_gfx_is_lockup,
-			.vm_flush = &cayman_vm_flush,
-			.get_rptr = &radeon_ring_generic_get_rptr,
-			.get_wptr = &radeon_ring_generic_get_wptr,
-			.set_wptr = &radeon_ring_generic_set_wptr,
-		},
-		[R600_RING_TYPE_DMA_INDEX] = {
-			.ib_execute = &cayman_dma_ring_ib_execute,
-			.ib_parse = &evergreen_dma_ib_parse,
-			.emit_fence = &evergreen_dma_fence_ring_emit,
-			.emit_semaphore = &r600_dma_semaphore_ring_emit,
-			.cs_parse = &evergreen_dma_cs_parse,
-			.ring_test = &r600_dma_ring_test,
-			.ib_test = &r600_dma_ib_test,
-			.is_lockup = &cayman_dma_is_lockup,
-			.vm_flush = &cayman_dma_vm_flush,
-			.get_rptr = &radeon_ring_generic_get_rptr,
-			.get_wptr = &radeon_ring_generic_get_wptr,
-			.set_wptr = &radeon_ring_generic_set_wptr,
-		},
-		[CAYMAN_RING_TYPE_DMA1_INDEX] = {
-			.ib_execute = &cayman_dma_ring_ib_execute,
-			.ib_parse = &evergreen_dma_ib_parse,
-			.emit_fence = &evergreen_dma_fence_ring_emit,
-			.emit_semaphore = &r600_dma_semaphore_ring_emit,
-			.cs_parse = &evergreen_dma_cs_parse,
-			.ring_test = &r600_dma_ring_test,
-			.ib_test = &r600_dma_ib_test,
-			.is_lockup = &cayman_dma_is_lockup,
-			.vm_flush = &cayman_dma_vm_flush,
-			.get_rptr = &radeon_ring_generic_get_rptr,
-			.get_wptr = &radeon_ring_generic_get_wptr,
-			.set_wptr = &radeon_ring_generic_set_wptr,
-		},
-		[R600_RING_TYPE_UVD_INDEX] = {
-			.ib_execute = &r600_uvd_ib_execute,
-			.emit_fence = &r600_uvd_fence_emit,
-			.emit_semaphore = &cayman_uvd_semaphore_emit,
-			.cs_parse = &radeon_uvd_cs_parse,
-			.ring_test = &r600_uvd_ring_test,
-			.ib_test = &r600_uvd_ib_test,
-			.is_lockup = &radeon_ring_test_lockup,
-			.get_rptr = &radeon_ring_generic_get_rptr,
-			.get_wptr = &radeon_ring_generic_get_wptr,
-			.set_wptr = &radeon_ring_generic_set_wptr,
-		}
+		[RADEON_RING_TYPE_GFX_INDEX] = &cayman_gfx_ring,
+		[CAYMAN_RING_TYPE_CP1_INDEX] = &cayman_gfx_ring,
+		[CAYMAN_RING_TYPE_CP2_INDEX] = &cayman_gfx_ring,
+		[R600_RING_TYPE_DMA_INDEX] = &cayman_dma_ring,
+		[CAYMAN_RING_TYPE_DMA1_INDEX] = &cayman_dma_ring,
+		[R600_RING_TYPE_UVD_INDEX] = &cayman_uvd_ring,
 	},
 	.irq = {
 		.set = &evergreen_irq_set,
@@ -2072,9 +1744,11 @@ static struct radeon_asic trinity_asic = {
 		.wait_for_vblank = &dce4_wait_for_vblank,
 		.set_backlight_level = &atombios_set_backlight_level,
 		.get_backlight_level = &atombios_get_backlight_level,
+		.hdmi_enable = &evergreen_hdmi_enable,
+		.hdmi_setmode = &evergreen_hdmi_setmode,
 	},
 	.copy = {
-		.blit = &r600_copy_blit,
+		.blit = &r600_copy_cpdma,
 		.blit_ring_index = RADEON_RING_TYPE_GFX_INDEX,
 		.dma = &evergreen_copy_dma,
 		.dma_ring_index = R600_RING_TYPE_DMA_INDEX,
@@ -2122,6 +1796,7 @@ static struct radeon_asic trinity_asic = {
 		.print_power_state = &trinity_dpm_print_power_state,
 		.debugfs_print_current_performance_level = &trinity_dpm_debugfs_print_current_performance_level,
 		.force_performance_level = &trinity_dpm_force_performance_level,
+		.enable_bapm = &trinity_dpm_enable_bapm,
 	},
 	.pflip = {
 		.pre_page_flip = &evergreen_pre_page_flip,
@@ -2130,6 +1805,36 @@ static struct radeon_asic trinity_asic = {
 	},
 };
 
+static struct radeon_asic_ring si_gfx_ring = {
+	.ib_execute = &si_ring_ib_execute,
+	.ib_parse = &si_ib_parse,
+	.emit_fence = &si_fence_ring_emit,
+	.emit_semaphore = &r600_semaphore_ring_emit,
+	.cs_parse = NULL,
+	.ring_test = &r600_ring_test,
+	.ib_test = &r600_ib_test,
+	.is_lockup = &si_gfx_is_lockup,
+	.vm_flush = &si_vm_flush,
+	.get_rptr = &radeon_ring_generic_get_rptr,
+	.get_wptr = &radeon_ring_generic_get_wptr,
+	.set_wptr = &radeon_ring_generic_set_wptr,
+};
+
+static struct radeon_asic_ring si_dma_ring = {
+	.ib_execute = &cayman_dma_ring_ib_execute,
+	.ib_parse = &evergreen_dma_ib_parse,
+	.emit_fence = &evergreen_dma_fence_ring_emit,
+	.emit_semaphore = &r600_dma_semaphore_ring_emit,
+	.cs_parse = NULL,
+	.ring_test = &r600_dma_ring_test,
+	.ib_test = &r600_dma_ib_test,
+	.is_lockup = &si_dma_is_lockup,
+	.vm_flush = &si_dma_vm_flush,
+	.get_rptr = &r600_dma_get_rptr,
+	.get_wptr = &r600_dma_get_wptr,
+	.set_wptr = &r600_dma_set_wptr,
+};
+
 static struct radeon_asic si_asic = {
 	.init = &si_init,
 	.fini = &si_fini,
@@ -2153,88 +1858,12 @@ static struct radeon_asic si_asic = {
 		.set_page = &si_vm_set_page,
 	},
 	.ring = {
-		[RADEON_RING_TYPE_GFX_INDEX] = {
-			.ib_execute = &si_ring_ib_execute,
-			.ib_parse = &si_ib_parse,
-			.emit_fence = &si_fence_ring_emit,
-			.emit_semaphore = &r600_semaphore_ring_emit,
-			.cs_parse = NULL,
-			.ring_test = &r600_ring_test,
-			.ib_test = &r600_ib_test,
-			.is_lockup = &si_gfx_is_lockup,
-			.vm_flush = &si_vm_flush,
-			.get_rptr = &radeon_ring_generic_get_rptr,
-			.get_wptr = &radeon_ring_generic_get_wptr,
-			.set_wptr = &radeon_ring_generic_set_wptr,
-		},
-		[CAYMAN_RING_TYPE_CP1_INDEX] = {
-			.ib_execute = &si_ring_ib_execute,
-			.ib_parse = &si_ib_parse,
-			.emit_fence = &si_fence_ring_emit,
-			.emit_semaphore = &r600_semaphore_ring_emit,
-			.cs_parse = NULL,
-			.ring_test = &r600_ring_test,
-			.ib_test = &r600_ib_test,
-			.is_lockup = &si_gfx_is_lockup,
-			.vm_flush = &si_vm_flush,
-			.get_rptr = &radeon_ring_generic_get_rptr,
-			.get_wptr = &radeon_ring_generic_get_wptr,
-			.set_wptr = &radeon_ring_generic_set_wptr,
-		},
-		[CAYMAN_RING_TYPE_CP2_INDEX] = {
-			.ib_execute = &si_ring_ib_execute,
-			.ib_parse = &si_ib_parse,
-			.emit_fence = &si_fence_ring_emit,
-			.emit_semaphore = &r600_semaphore_ring_emit,
-			.cs_parse = NULL,
-			.ring_test = &r600_ring_test,
-			.ib_test = &r600_ib_test,
-			.is_lockup = &si_gfx_is_lockup,
-			.vm_flush = &si_vm_flush,
-			.get_rptr = &radeon_ring_generic_get_rptr,
-			.get_wptr = &radeon_ring_generic_get_wptr,
-			.set_wptr = &radeon_ring_generic_set_wptr,
-		},
-		[R600_RING_TYPE_DMA_INDEX] = {
-			.ib_execute = &cayman_dma_ring_ib_execute,
-			.ib_parse = &evergreen_dma_ib_parse,
-			.emit_fence = &evergreen_dma_fence_ring_emit,
-			.emit_semaphore = &r600_dma_semaphore_ring_emit,
-			.cs_parse = NULL,
-			.ring_test = &r600_dma_ring_test,
-			.ib_test = &r600_dma_ib_test,
-			.is_lockup = &si_dma_is_lockup,
-			.vm_flush = &si_dma_vm_flush,
-			.get_rptr = &radeon_ring_generic_get_rptr,
-			.get_wptr = &radeon_ring_generic_get_wptr,
-			.set_wptr = &radeon_ring_generic_set_wptr,
-		},
-		[CAYMAN_RING_TYPE_DMA1_INDEX] = {
-			.ib_execute = &cayman_dma_ring_ib_execute,
-			.ib_parse = &evergreen_dma_ib_parse,
-			.emit_fence = &evergreen_dma_fence_ring_emit,
-			.emit_semaphore = &r600_dma_semaphore_ring_emit,
-			.cs_parse = NULL,
-			.ring_test = &r600_dma_ring_test,
-			.ib_test = &r600_dma_ib_test,
-			.is_lockup = &si_dma_is_lockup,
-			.vm_flush = &si_dma_vm_flush,
-			.get_rptr = &radeon_ring_generic_get_rptr,
-			.get_wptr = &radeon_ring_generic_get_wptr,
-			.set_wptr = &radeon_ring_generic_set_wptr,
-		},
-		[R600_RING_TYPE_UVD_INDEX] = {
-			.ib_execute = &r600_uvd_ib_execute,
-			.emit_fence = &r600_uvd_fence_emit,
-			.emit_semaphore = &cayman_uvd_semaphore_emit,
-			.cs_parse = &radeon_uvd_cs_parse,
-			.ring_test = &r600_uvd_ring_test,
-			.ib_test = &r600_uvd_ib_test,
-			.is_lockup = &radeon_ring_test_lockup,
-			.get_rptr = &radeon_ring_generic_get_rptr,
-			.get_wptr = &radeon_ring_generic_get_wptr,
-			.set_wptr = &radeon_ring_generic_set_wptr,
-		}
+		[RADEON_RING_TYPE_GFX_INDEX] = &si_gfx_ring,
+		[CAYMAN_RING_TYPE_CP1_INDEX] = &si_gfx_ring,
+		[CAYMAN_RING_TYPE_CP2_INDEX] = &si_gfx_ring,
+		[R600_RING_TYPE_DMA_INDEX] = &si_dma_ring,
+		[CAYMAN_RING_TYPE_DMA1_INDEX] = &si_dma_ring,
+		[R600_RING_TYPE_UVD_INDEX] = &cayman_uvd_ring,
 	},
 	.irq = {
 		.set = &si_irq_set,
@@ -2246,6 +1875,8 @@ static struct radeon_asic si_asic = {
 		.wait_for_vblank = &dce4_wait_for_vblank,
 		.set_backlight_level = &atombios_set_backlight_level,
 		.get_backlight_level = &atombios_get_backlight_level,
+		.hdmi_enable = &evergreen_hdmi_enable,
+		.hdmi_setmode = &evergreen_hdmi_setmode,
 	},
 	.copy = {
 		.blit = NULL,
@@ -2305,6 +1936,51 @@ static struct radeon_asic si_asic = {
 	},
 };
 
+static struct radeon_asic_ring ci_gfx_ring = {
+	.ib_execute = &cik_ring_ib_execute,
+	.ib_parse = &cik_ib_parse,
+	.emit_fence = &cik_fence_gfx_ring_emit,
+	.emit_semaphore = &cik_semaphore_ring_emit,
+	.cs_parse = NULL,
+	.ring_test = &cik_ring_test,
+	.ib_test = &cik_ib_test,
+	.is_lockup = &cik_gfx_is_lockup,
+	.vm_flush = &cik_vm_flush,
+	.get_rptr = &radeon_ring_generic_get_rptr,
+	.get_wptr = &radeon_ring_generic_get_wptr,
+	.set_wptr = &radeon_ring_generic_set_wptr,
+};
+
+static struct radeon_asic_ring ci_cp_ring = {
+	.ib_execute = &cik_ring_ib_execute,
+	.ib_parse = &cik_ib_parse,
+	.emit_fence = &cik_fence_compute_ring_emit,
+	.emit_semaphore = &cik_semaphore_ring_emit,
+	.cs_parse = NULL,
+	.ring_test = &cik_ring_test,
+	.ib_test = &cik_ib_test,
+	.is_lockup = &cik_gfx_is_lockup,
+	.vm_flush = &cik_vm_flush,
+	.get_rptr = &cik_compute_ring_get_rptr,
+	.get_wptr = &cik_compute_ring_get_wptr,
+	.set_wptr = &cik_compute_ring_set_wptr,
+};
+
+static struct radeon_asic_ring ci_dma_ring = {
+	.ib_execute = &cik_sdma_ring_ib_execute,
+	.ib_parse = &cik_ib_parse,
+	.emit_fence = &cik_sdma_fence_ring_emit,
+	.emit_semaphore = &cik_sdma_semaphore_ring_emit,
+	.cs_parse = NULL,
+	.ring_test = &cik_sdma_ring_test,
+	.ib_test = &cik_sdma_ib_test,
+	.is_lockup = &cik_sdma_is_lockup,
+	.vm_flush = &cik_dma_vm_flush,
+	.get_rptr = &r600_dma_get_rptr,
+	.get_wptr = &r600_dma_get_wptr,
+	.set_wptr = &r600_dma_set_wptr,
+};
+
 static struct radeon_asic ci_asic = {
 	.init = &cik_init,
 	.fini = &cik_fini,
@@ -2328,88 +2004,12 @@ static struct radeon_asic ci_asic = {
 		.set_page = &cik_vm_set_page,
 	},
 	.ring = {
-		[RADEON_RING_TYPE_GFX_INDEX] = {
-			.ib_execute = &cik_ring_ib_execute,
-			.ib_parse = &cik_ib_parse,
-			.emit_fence = &cik_fence_gfx_ring_emit,
-			.emit_semaphore = &cik_semaphore_ring_emit,
-			.cs_parse = NULL,
-			.ring_test = &cik_ring_test,
-			.ib_test = &cik_ib_test,
-			.is_lockup = &cik_gfx_is_lockup,
-			.vm_flush = &cik_vm_flush,
-			.get_rptr = &radeon_ring_generic_get_rptr,
-			.get_wptr = &radeon_ring_generic_get_wptr,
-			.set_wptr = &radeon_ring_generic_set_wptr,
-		},
-		[CAYMAN_RING_TYPE_CP1_INDEX] = {
-			.ib_execute = &cik_ring_ib_execute,
-			.ib_parse = &cik_ib_parse,
-			.emit_fence = &cik_fence_compute_ring_emit,
-			.emit_semaphore = &cik_semaphore_ring_emit,
-			.cs_parse = NULL,
-			.ring_test = &cik_ring_test,
-			.ib_test = &cik_ib_test,
-			.is_lockup = &cik_gfx_is_lockup,
-			.vm_flush = &cik_vm_flush,
-			.get_rptr = &cik_compute_ring_get_rptr,
-			.get_wptr = &cik_compute_ring_get_wptr,
-			.set_wptr = &cik_compute_ring_set_wptr,
-		},
-		[CAYMAN_RING_TYPE_CP2_INDEX] = {
-			.ib_execute = &cik_ring_ib_execute,
-			.ib_parse = &cik_ib_parse,
-			.emit_fence = &cik_fence_compute_ring_emit,
-			.emit_semaphore = &cik_semaphore_ring_emit,
-			.cs_parse = NULL,
-			.ring_test = &cik_ring_test,
-			.ib_test = &cik_ib_test,
-			.is_lockup = &cik_gfx_is_lockup,
-			.vm_flush = &cik_vm_flush,
-			.get_rptr = &cik_compute_ring_get_rptr,
-			.get_wptr = &cik_compute_ring_get_wptr,
-			.set_wptr = &cik_compute_ring_set_wptr,
-		},
-		[R600_RING_TYPE_DMA_INDEX] = {
-			.ib_execute = &cik_sdma_ring_ib_execute,
-			.ib_parse = &cik_ib_parse,
-			.emit_fence = &cik_sdma_fence_ring_emit,
-			.emit_semaphore = &cik_sdma_semaphore_ring_emit,
-			.cs_parse = NULL,
-			.ring_test = &cik_sdma_ring_test,
-			.ib_test = &cik_sdma_ib_test,
-			.is_lockup = &cik_sdma_is_lockup,
-			.vm_flush = &cik_dma_vm_flush,
-			.get_rptr = &radeon_ring_generic_get_rptr,
-			.get_wptr = &radeon_ring_generic_get_wptr,
-			.set_wptr = &radeon_ring_generic_set_wptr,
-		},
-		[CAYMAN_RING_TYPE_DMA1_INDEX] = {
-			.ib_execute = &cik_sdma_ring_ib_execute,
-			.ib_parse = &cik_ib_parse,
-			.emit_fence = &cik_sdma_fence_ring_emit,
-			.emit_semaphore = &cik_sdma_semaphore_ring_emit,
-			.cs_parse = NULL,
-			.ring_test = &cik_sdma_ring_test,
-			.ib_test = &cik_sdma_ib_test,
-			.is_lockup = &cik_sdma_is_lockup,
-			.vm_flush = &cik_dma_vm_flush,
-			.get_rptr = &radeon_ring_generic_get_rptr,
-			.get_wptr = &radeon_ring_generic_get_wptr,
-			.set_wptr = &radeon_ring_generic_set_wptr,
-		},
-		[R600_RING_TYPE_UVD_INDEX] = {
-			.ib_execute = &r600_uvd_ib_execute,
-			.emit_fence = &r600_uvd_fence_emit,
-			.emit_semaphore = &cayman_uvd_semaphore_emit,
-			.cs_parse = &radeon_uvd_cs_parse,
-			.ring_test = &r600_uvd_ring_test,
-			.ib_test = &r600_uvd_ib_test,
-			.is_lockup = &radeon_ring_test_lockup,
-			.get_rptr = &radeon_ring_generic_get_rptr,
-			.get_wptr = &radeon_ring_generic_get_wptr,
-			.set_wptr = &radeon_ring_generic_set_wptr,
-		}
+		[RADEON_RING_TYPE_GFX_INDEX] = &ci_gfx_ring,
+		[CAYMAN_RING_TYPE_CP1_INDEX] = &ci_cp_ring,
+		[CAYMAN_RING_TYPE_CP2_INDEX] = &ci_cp_ring,
+		[R600_RING_TYPE_DMA_INDEX] = &ci_dma_ring,
+		[CAYMAN_RING_TYPE_DMA1_INDEX] = &ci_dma_ring,
+		[R600_RING_TYPE_UVD_INDEX] = &cayman_uvd_ring,
 	},
 	.irq = {
 		.set = &cik_irq_set,
@@ -2419,6 +2019,8 @@ static struct radeon_asic ci_asic = {
 		.bandwidth_update = &dce8_bandwidth_update,
 		.get_vblank_counter = &evergreen_get_vblank_counter,
 		.wait_for_vblank = &dce4_wait_for_vblank,
+		.hdmi_enable = &evergreen_hdmi_enable,
+		.hdmi_setmode = &evergreen_hdmi_setmode,
 	},
 	.copy = {
 		.blit = NULL,
@@ -2452,6 +2054,25 @@ static struct radeon_asic ci_asic = {
 		.set_pcie_lanes = NULL,
 		.set_clock_gating = NULL,
 		.set_uvd_clocks = &cik_set_uvd_clocks,
+		.get_temperature = &ci_get_temp,
+	},
+	.dpm = {
+		.init = &ci_dpm_init,
+		.setup_asic = &ci_dpm_setup_asic,
+		.enable = &ci_dpm_enable,
+		.disable = &ci_dpm_disable,
+		.pre_set_power_state = &ci_dpm_pre_set_power_state,
+		.set_power_state = &ci_dpm_set_power_state,
+		.post_set_power_state = &ci_dpm_post_set_power_state,
+		.display_configuration_changed = &ci_dpm_display_configuration_changed,
+		.fini = &ci_dpm_fini,
+		.get_sclk = &ci_dpm_get_sclk,
+		.get_mclk = &ci_dpm_get_mclk,
+		.print_power_state = &ci_dpm_print_power_state,
+		.debugfs_print_current_performance_level = &ci_dpm_debugfs_print_current_performance_level,
+		.force_performance_level = &ci_dpm_force_performance_level,
+		.vblank_too_short = &ci_dpm_vblank_too_short,
+		.powergate_uvd = &ci_dpm_powergate_uvd,
 	},
 	.pflip = {
 		.pre_page_flip = &evergreen_pre_page_flip,
@@ -2483,88 +2104,12 @@ static struct radeon_asic kv_asic = {
 		.set_page = &cik_vm_set_page,
 	},
 	.ring = {
-		[RADEON_RING_TYPE_GFX_INDEX] = {
-			.ib_execute = &cik_ring_ib_execute,
-			.ib_parse = &cik_ib_parse,
-			.emit_fence = &cik_fence_gfx_ring_emit,
-			.emit_semaphore = &cik_semaphore_ring_emit,
-			.cs_parse = NULL,
-			.ring_test = &cik_ring_test,
-			.ib_test = &cik_ib_test,
-			.is_lockup = &cik_gfx_is_lockup,
-			.vm_flush = &cik_vm_flush,
-			.get_rptr = &radeon_ring_generic_get_rptr,
-			.get_wptr = &radeon_ring_generic_get_wptr,
-			.set_wptr = &radeon_ring_generic_set_wptr,
-		},
-		[CAYMAN_RING_TYPE_CP1_INDEX] = {
-			.ib_execute = &cik_ring_ib_execute,
-			.ib_parse = &cik_ib_parse,
-			.emit_fence = &cik_fence_compute_ring_emit,
-			.emit_semaphore = &cik_semaphore_ring_emit,
-			.cs_parse = NULL,
-			.ring_test = &cik_ring_test,
-			.ib_test = &cik_ib_test,
-			.is_lockup = &cik_gfx_is_lockup,
-			.vm_flush = &cik_vm_flush,
-			.get_rptr = &cik_compute_ring_get_rptr,
-			.get_wptr = &cik_compute_ring_get_wptr,
-			.set_wptr = &cik_compute_ring_set_wptr,
-		},
-		[CAYMAN_RING_TYPE_CP2_INDEX] = {
-			.ib_execute = &cik_ring_ib_execute,
-			.ib_parse = &cik_ib_parse,
-			.emit_fence = &cik_fence_compute_ring_emit,
-			.emit_semaphore = &cik_semaphore_ring_emit,
-			.cs_parse = NULL,
-			.ring_test = &cik_ring_test,
-			.ib_test = &cik_ib_test,
-			.is_lockup = &cik_gfx_is_lockup,
-			.vm_flush = &cik_vm_flush,
-			.get_rptr = &cik_compute_ring_get_rptr,
-			.get_wptr = &cik_compute_ring_get_wptr,
-			.set_wptr = &cik_compute_ring_set_wptr,
-		},
-		[R600_RING_TYPE_DMA_INDEX] = {
-			.ib_execute = &cik_sdma_ring_ib_execute,
-			.ib_parse = &cik_ib_parse,
-			.emit_fence = &cik_sdma_fence_ring_emit,
-			.emit_semaphore = &cik_sdma_semaphore_ring_emit,
-			.cs_parse = NULL,
-			.ring_test = &cik_sdma_ring_test,
-			.ib_test = &cik_sdma_ib_test,
-			.is_lockup = &cik_sdma_is_lockup,
-			.vm_flush = &cik_dma_vm_flush,
-			.get_rptr = &radeon_ring_generic_get_rptr,
-			.get_wptr = &radeon_ring_generic_get_wptr,
-			.set_wptr = &radeon_ring_generic_set_wptr,
-		},
-		[CAYMAN_RING_TYPE_DMA1_INDEX] = {
-			.ib_execute = &cik_sdma_ring_ib_execute,
-			.ib_parse = &cik_ib_parse,
-			.emit_fence = &cik_sdma_fence_ring_emit,
-			.emit_semaphore = &cik_sdma_semaphore_ring_emit,
-			.cs_parse = NULL,
-			.ring_test = &cik_sdma_ring_test,
-			.ib_test = &cik_sdma_ib_test,
-			.is_lockup = &cik_sdma_is_lockup,
-			.vm_flush = &cik_dma_vm_flush,
-			.get_rptr = &radeon_ring_generic_get_rptr,
-			.get_wptr = &radeon_ring_generic_get_wptr,
-			.set_wptr = &radeon_ring_generic_set_wptr,
-		},
-		[R600_RING_TYPE_UVD_INDEX] = {
-			.ib_execute = &r600_uvd_ib_execute,
-			.emit_fence = &r600_uvd_fence_emit,
-			.emit_semaphore = &cayman_uvd_semaphore_emit,
-			.cs_parse = &radeon_uvd_cs_parse,
-			.ring_test = &r600_uvd_ring_test,
-			.ib_test = &r600_uvd_ib_test,
-			.is_lockup = &radeon_ring_test_lockup,
-			.get_rptr = &radeon_ring_generic_get_rptr,
-			.get_wptr = &radeon_ring_generic_get_wptr,
-			.set_wptr = &radeon_ring_generic_set_wptr,
-		}
+		[RADEON_RING_TYPE_GFX_INDEX] = &ci_gfx_ring,
+		[CAYMAN_RING_TYPE_CP1_INDEX] = &ci_cp_ring,
+		[CAYMAN_RING_TYPE_CP2_INDEX] = &ci_cp_ring,
+		[R600_RING_TYPE_DMA_INDEX] = &ci_dma_ring,
+		[CAYMAN_RING_TYPE_DMA1_INDEX] = &ci_dma_ring,
+		[R600_RING_TYPE_UVD_INDEX] = &cayman_uvd_ring,
 	},
 	.irq = {
 		.set = &cik_irq_set,
@@ -2574,6 +2119,8 @@ static struct radeon_asic kv_asic = {
 		.bandwidth_update = &dce8_bandwidth_update,
 		.get_vblank_counter = &evergreen_get_vblank_counter,
 		.wait_for_vblank = &dce4_wait_for_vblank,
+		.hdmi_enable = &evergreen_hdmi_enable,
+		.hdmi_setmode = &evergreen_hdmi_setmode,
 	},
 	.copy = {
 		.blit = NULL,
@@ -2607,6 +2154,25 @@ static struct radeon_asic kv_asic = {
 		.set_pcie_lanes = NULL,
 		.set_clock_gating = NULL,
 		.set_uvd_clocks = &cik_set_uvd_clocks,
+		.get_temperature = &kv_get_temp,
+	},
+	.dpm = {
+		.init = &kv_dpm_init,
+		.setup_asic = &kv_dpm_setup_asic,
+		.enable = &kv_dpm_enable,
+		.disable = &kv_dpm_disable,
+		.pre_set_power_state = &kv_dpm_pre_set_power_state,
+		.set_power_state = &kv_dpm_set_power_state,
+		.post_set_power_state = &kv_dpm_post_set_power_state,
+		.display_configuration_changed = &kv_dpm_display_configuration_changed,
+		.fini = &kv_dpm_fini,
+		.get_sclk = &kv_dpm_get_sclk,
+		.get_mclk = &kv_dpm_get_mclk,
+		.print_power_state = &kv_dpm_print_power_state,
+		.debugfs_print_current_performance_level = &kv_dpm_debugfs_print_current_performance_level,
+		.force_performance_level = &kv_dpm_force_performance_level,
+		.powergate_uvd = &kv_dpm_powergate_uvd,
+		.enable_bapm = &kv_dpm_enable_bapm,
 	},
 	.pflip = {
 		.pre_page_flip = &evergreen_pre_page_flip,
@@ -2776,19 +2342,188 @@ int radeon_asic_init(struct radeon_device *rdev)
 			rdev->has_uvd = false;
 		else
 			rdev->has_uvd = true;
+		switch (rdev->family) {
+		case CHIP_TAHITI:
+			rdev->cg_flags =
+				RADEON_CG_SUPPORT_GFX_MGCG |
+				RADEON_CG_SUPPORT_GFX_MGLS |
+				/*RADEON_CG_SUPPORT_GFX_CGCG |*/
+				RADEON_CG_SUPPORT_GFX_CGLS |
+				RADEON_CG_SUPPORT_GFX_CGTS |
+				RADEON_CG_SUPPORT_GFX_CP_LS |
+				RADEON_CG_SUPPORT_MC_MGCG |
+				RADEON_CG_SUPPORT_SDMA_MGCG |
+				RADEON_CG_SUPPORT_BIF_LS |
+				RADEON_CG_SUPPORT_VCE_MGCG |
+				RADEON_CG_SUPPORT_UVD_MGCG |
+				RADEON_CG_SUPPORT_HDP_LS |
+				RADEON_CG_SUPPORT_HDP_MGCG;
+			rdev->pg_flags = 0;
+			break;
+		case CHIP_PITCAIRN:
+			rdev->cg_flags =
+				RADEON_CG_SUPPORT_GFX_MGCG |
+				RADEON_CG_SUPPORT_GFX_MGLS |
+				/*RADEON_CG_SUPPORT_GFX_CGCG |*/
+				RADEON_CG_SUPPORT_GFX_CGLS |
+				RADEON_CG_SUPPORT_GFX_CGTS |
+				RADEON_CG_SUPPORT_GFX_CP_LS |
+				RADEON_CG_SUPPORT_GFX_RLC_LS |
+				RADEON_CG_SUPPORT_MC_LS |
+				RADEON_CG_SUPPORT_MC_MGCG |
+				RADEON_CG_SUPPORT_SDMA_MGCG |
+				RADEON_CG_SUPPORT_BIF_LS |
+				RADEON_CG_SUPPORT_VCE_MGCG |
+				RADEON_CG_SUPPORT_UVD_MGCG |
+				RADEON_CG_SUPPORT_HDP_LS |
+				RADEON_CG_SUPPORT_HDP_MGCG;
+			rdev->pg_flags = 0;
+			break;
+		case CHIP_VERDE:
+			rdev->cg_flags =
+				RADEON_CG_SUPPORT_GFX_MGCG |
+				RADEON_CG_SUPPORT_GFX_MGLS |
+				/*RADEON_CG_SUPPORT_GFX_CGCG |*/
+				RADEON_CG_SUPPORT_GFX_CGLS |
+				RADEON_CG_SUPPORT_GFX_CGTS |
+				RADEON_CG_SUPPORT_GFX_CP_LS |
+				RADEON_CG_SUPPORT_GFX_RLC_LS |
+				RADEON_CG_SUPPORT_MC_LS |
+				RADEON_CG_SUPPORT_MC_MGCG |
+				RADEON_CG_SUPPORT_SDMA_MGCG |
+				RADEON_CG_SUPPORT_BIF_LS |
+				RADEON_CG_SUPPORT_VCE_MGCG |
+				RADEON_CG_SUPPORT_UVD_MGCG |
+				RADEON_CG_SUPPORT_HDP_LS |
+				RADEON_CG_SUPPORT_HDP_MGCG;
+			rdev->pg_flags = 0 |
+				/*RADEON_PG_SUPPORT_GFX_PG | */
+				RADEON_PG_SUPPORT_SDMA;
+			break;
+		case CHIP_OLAND:
+			rdev->cg_flags =
+				RADEON_CG_SUPPORT_GFX_MGCG |
+				RADEON_CG_SUPPORT_GFX_MGLS |
+				/*RADEON_CG_SUPPORT_GFX_CGCG |*/
+				RADEON_CG_SUPPORT_GFX_CGLS |
+				RADEON_CG_SUPPORT_GFX_CGTS |
+				RADEON_CG_SUPPORT_GFX_CP_LS |
+				RADEON_CG_SUPPORT_GFX_RLC_LS |
+				RADEON_CG_SUPPORT_MC_LS |
+				RADEON_CG_SUPPORT_MC_MGCG |
+				RADEON_CG_SUPPORT_SDMA_MGCG |
+				RADEON_CG_SUPPORT_BIF_LS |
+				RADEON_CG_SUPPORT_UVD_MGCG |
+				RADEON_CG_SUPPORT_HDP_LS |
+				RADEON_CG_SUPPORT_HDP_MGCG;
+			rdev->pg_flags = 0;
+			break;
+		case CHIP_HAINAN:
+			rdev->cg_flags =
+				RADEON_CG_SUPPORT_GFX_MGCG |
+				RADEON_CG_SUPPORT_GFX_MGLS |
+				/*RADEON_CG_SUPPORT_GFX_CGCG |*/
+				RADEON_CG_SUPPORT_GFX_CGLS |
+				RADEON_CG_SUPPORT_GFX_CGTS |
+				RADEON_CG_SUPPORT_GFX_CP_LS |
+				RADEON_CG_SUPPORT_GFX_RLC_LS |
+				RADEON_CG_SUPPORT_MC_LS |
+				RADEON_CG_SUPPORT_MC_MGCG |
+				RADEON_CG_SUPPORT_SDMA_MGCG |
+				RADEON_CG_SUPPORT_BIF_LS |
+				RADEON_CG_SUPPORT_HDP_LS |
+				RADEON_CG_SUPPORT_HDP_MGCG;
+			rdev->pg_flags = 0;
+			break;
+		default:
+			rdev->cg_flags = 0;
+			rdev->pg_flags = 0;
+			break;
+		}
 		break;
 	case CHIP_BONAIRE:
 		rdev->asic = &ci_asic;
 		rdev->num_crtc = 6;
+		rdev->has_uvd = true;
+		rdev->cg_flags =
+			RADEON_CG_SUPPORT_GFX_MGCG |
+			RADEON_CG_SUPPORT_GFX_MGLS |
+			/*RADEON_CG_SUPPORT_GFX_CGCG |*/
+			RADEON_CG_SUPPORT_GFX_CGLS |
+			RADEON_CG_SUPPORT_GFX_CGTS |
+			RADEON_CG_SUPPORT_GFX_CGTS_LS |
+			RADEON_CG_SUPPORT_GFX_CP_LS |
+			RADEON_CG_SUPPORT_MC_LS |
+			RADEON_CG_SUPPORT_MC_MGCG |
+			RADEON_CG_SUPPORT_SDMA_MGCG |
+			RADEON_CG_SUPPORT_SDMA_LS |
+			RADEON_CG_SUPPORT_BIF_LS |
+			RADEON_CG_SUPPORT_VCE_MGCG |
+			RADEON_CG_SUPPORT_UVD_MGCG |
+			RADEON_CG_SUPPORT_HDP_LS |
+			RADEON_CG_SUPPORT_HDP_MGCG;
+		rdev->pg_flags = 0;
 		break;
 	case CHIP_KAVERI:
 	case CHIP_KABINI:
 		rdev->asic = &kv_asic;
 		/* set num crtcs */
-		if (rdev->family == CHIP_KAVERI)
+		if (rdev->family == CHIP_KAVERI) {
 			rdev->num_crtc = 4;
-		else
+			rdev->cg_flags =
+				RADEON_CG_SUPPORT_GFX_MGCG |
+				RADEON_CG_SUPPORT_GFX_MGLS |
+				/*RADEON_CG_SUPPORT_GFX_CGCG |*/
+				RADEON_CG_SUPPORT_GFX_CGLS |
+				RADEON_CG_SUPPORT_GFX_CGTS |
+				RADEON_CG_SUPPORT_GFX_CGTS_LS |
+				RADEON_CG_SUPPORT_GFX_CP_LS |
+				RADEON_CG_SUPPORT_SDMA_MGCG |
+				RADEON_CG_SUPPORT_SDMA_LS |
+				RADEON_CG_SUPPORT_BIF_LS |
+				RADEON_CG_SUPPORT_VCE_MGCG |
+				RADEON_CG_SUPPORT_UVD_MGCG |
+				RADEON_CG_SUPPORT_HDP_LS |
+				RADEON_CG_SUPPORT_HDP_MGCG;
+			rdev->pg_flags = 0;
+				/*RADEON_PG_SUPPORT_GFX_PG |
+				RADEON_PG_SUPPORT_GFX_SMG |
+				RADEON_PG_SUPPORT_GFX_DMG |
+				RADEON_PG_SUPPORT_UVD |
+				RADEON_PG_SUPPORT_VCE |
+				RADEON_PG_SUPPORT_CP |
+				RADEON_PG_SUPPORT_GDS |
+				RADEON_PG_SUPPORT_RLC_SMU_HS |
+				RADEON_PG_SUPPORT_ACP |
+				RADEON_PG_SUPPORT_SAMU;*/
+		} else {
 			rdev->num_crtc = 2;
+			rdev->cg_flags =
+				RADEON_CG_SUPPORT_GFX_MGCG |
+				RADEON_CG_SUPPORT_GFX_MGLS |
+				/*RADEON_CG_SUPPORT_GFX_CGCG |*/
+				RADEON_CG_SUPPORT_GFX_CGLS |
+				RADEON_CG_SUPPORT_GFX_CGTS |
+				RADEON_CG_SUPPORT_GFX_CGTS_LS |
+				RADEON_CG_SUPPORT_GFX_CP_LS |
+				RADEON_CG_SUPPORT_SDMA_MGCG |
+				RADEON_CG_SUPPORT_SDMA_LS |
+				RADEON_CG_SUPPORT_BIF_LS |
+				RADEON_CG_SUPPORT_VCE_MGCG |
+				RADEON_CG_SUPPORT_UVD_MGCG |
+				RADEON_CG_SUPPORT_HDP_LS |
+				RADEON_CG_SUPPORT_HDP_MGCG;
+			rdev->pg_flags = 0;
+				/*RADEON_PG_SUPPORT_GFX_PG |
+				RADEON_PG_SUPPORT_GFX_SMG |
+				RADEON_PG_SUPPORT_UVD |
+				RADEON_PG_SUPPORT_VCE |
+				RADEON_PG_SUPPORT_CP |
+				RADEON_PG_SUPPORT_GDS |
+				RADEON_PG_SUPPORT_RLC_SMU_HS |
+				RADEON_PG_SUPPORT_SAMU;*/
+		}
+		rdev->has_uvd = true;
 		break;
 	default:
 		/* FIXME: not supported yet */
diff --git a/drivers/gpu/drm/radeon/radeon_asic.h b/drivers/gpu/drm/radeon/radeon_asic.h
index 3d61d5aac18f..70c29d5e080d 100644
--- a/drivers/gpu/drm/radeon/radeon_asic.h
+++ b/drivers/gpu/drm/radeon/radeon_asic.h
@@ -336,10 +336,6 @@ int r600_dma_ib_test(struct radeon_device *rdev, struct radeon_ring *ring);
 void r600_ring_ib_execute(struct radeon_device *rdev, struct radeon_ib *ib);
 int r600_ring_test(struct radeon_device *rdev, struct radeon_ring *cp);
 int r600_dma_ring_test(struct radeon_device *rdev, struct radeon_ring *cp);
-int r600_uvd_ring_test(struct radeon_device *rdev, struct radeon_ring *ring);
-int r600_copy_blit(struct radeon_device *rdev,
-		   uint64_t src_offset, uint64_t dst_offset,
-		   unsigned num_gpu_pages, struct radeon_fence **fence);
 int r600_copy_cpdma(struct radeon_device *rdev,
 		    uint64_t src_offset, uint64_t dst_offset,
 		    unsigned num_gpu_pages, struct radeon_fence **fence);
@@ -371,8 +367,6 @@ int r600_count_pipe_bits(uint32_t val);
 int r600_mc_wait_for_idle(struct radeon_device *rdev);
 int r600_pcie_gart_init(struct radeon_device *rdev);
 void r600_scratch_init(struct radeon_device *rdev);
-int r600_blit_init(struct radeon_device *rdev);
-void r600_blit_fini(struct radeon_device *rdev);
 int r600_init_microcode(struct radeon_device *rdev);
 /* r600 irq */
 int r600_irq_process(struct radeon_device *rdev);
@@ -385,28 +379,26 @@ void r600_disable_interrupts(struct radeon_device *rdev);
 void r600_rlc_stop(struct radeon_device *rdev);
 /* r600 audio */
 int r600_audio_init(struct radeon_device *rdev);
-struct r600_audio r600_audio_status(struct radeon_device *rdev);
+struct r600_audio_pin r600_audio_status(struct radeon_device *rdev);
 void r600_audio_fini(struct radeon_device *rdev);
 int r600_hdmi_buffer_status_changed(struct drm_encoder *encoder);
 void r600_hdmi_update_audio_settings(struct drm_encoder *encoder);
 void r600_hdmi_enable(struct drm_encoder *encoder, bool enable);
 void r600_hdmi_setmode(struct drm_encoder *encoder, struct drm_display_mode *mode);
-/* r600 blit */
-int r600_blit_prepare_copy(struct radeon_device *rdev, unsigned num_gpu_pages,
-			   struct radeon_fence **fence, struct radeon_sa_bo **vb,
-			   struct radeon_semaphore **sem);
-void r600_blit_done_copy(struct radeon_device *rdev, struct radeon_fence **fence,
-			 struct radeon_sa_bo *vb, struct radeon_semaphore *sem);
-void r600_kms_blit_copy(struct radeon_device *rdev,
-			u64 src_gpu_addr, u64 dst_gpu_addr,
-			unsigned num_gpu_pages,
-			struct radeon_sa_bo *vb);
 int r600_mc_wait_for_idle(struct radeon_device *rdev);
 u32 r600_get_xclk(struct radeon_device *rdev);
 uint64_t r600_get_gpu_clock_counter(struct radeon_device *rdev);
 int rv6xx_get_temp(struct radeon_device *rdev);
+int r600_set_uvd_clocks(struct radeon_device *rdev, u32 vclk, u32 dclk);
 int r600_dpm_pre_set_power_state(struct radeon_device *rdev);
 void r600_dpm_post_set_power_state(struct radeon_device *rdev);
+/* r600 dma */
+uint32_t r600_dma_get_rptr(struct radeon_device *rdev,
+			   struct radeon_ring *ring);
+uint32_t r600_dma_get_wptr(struct radeon_device *rdev,
+			   struct radeon_ring *ring);
+void r600_dma_set_wptr(struct radeon_device *rdev,
+		       struct radeon_ring *ring);
 /* rv6xx dpm */
 int rv6xx_dpm_init(struct radeon_device *rdev);
 int rv6xx_dpm_enable(struct radeon_device *rdev);
@@ -437,19 +429,8 @@ void rs780_dpm_print_power_state(struct radeon_device *rdev,
 				 struct radeon_ps *ps);
 void rs780_dpm_debugfs_print_current_performance_level(struct radeon_device *rdev,
 						       struct seq_file *m);
-
-/* uvd */
-int r600_uvd_init(struct radeon_device *rdev);
-int r600_uvd_rbc_start(struct radeon_device *rdev);
-void r600_uvd_stop(struct radeon_device *rdev);
-int r600_uvd_ib_test(struct radeon_device *rdev, struct radeon_ring *ring);
-void r600_uvd_fence_emit(struct radeon_device *rdev,
-			 struct radeon_fence *fence);
-void r600_uvd_semaphore_emit(struct radeon_device *rdev,
-			     struct radeon_ring *ring,
-			     struct radeon_semaphore *semaphore,
-			     bool emit_wait);
-void r600_uvd_ib_execute(struct radeon_device *rdev, struct radeon_ib *ib);
+int rs780_dpm_force_performance_level(struct radeon_device *rdev,
+				      enum radeon_dpm_forced_level level);
 
 /*
  * rv770,rv730,rv710,rv740
@@ -468,7 +449,6 @@ int rv770_copy_dma(struct radeon_device *rdev,
 		  unsigned num_gpu_pages,
 		   struct radeon_fence **fence);
 u32 rv770_get_xclk(struct radeon_device *rdev);
-int rv770_uvd_resume(struct radeon_device *rdev);
 int rv770_set_uvd_clocks(struct radeon_device *rdev, u32 vclk, u32 dclk);
 int rv770_get_temp(struct radeon_device *rdev);
 /* rv7xx pm */
@@ -530,7 +510,6 @@ extern u32 evergreen_page_flip(struct radeon_device *rdev, int crtc, u64 crtc_ba
 extern void evergreen_post_page_flip(struct radeon_device *rdev, int crtc);
 extern void dce4_wait_for_vblank(struct radeon_device *rdev, int crtc);
 void evergreen_disable_interrupt_state(struct radeon_device *rdev);
-int evergreen_blit_init(struct radeon_device *rdev);
 int evergreen_mc_wait_for_idle(struct radeon_device *rdev);
 void evergreen_dma_fence_ring_emit(struct radeon_device *rdev,
 				   struct radeon_fence *fence);
@@ -649,9 +628,12 @@ void trinity_dpm_debugfs_print_current_performance_level(struct radeon_device *r
 							 struct seq_file *m);
 int trinity_dpm_force_performance_level(struct radeon_device *rdev,
 					enum radeon_dpm_forced_level level);
+void trinity_dpm_enable_bapm(struct radeon_device *rdev, bool enable);
 
 /* DCE6 - SI */
 void dce6_bandwidth_update(struct radeon_device *rdev);
+int dce6_audio_init(struct radeon_device *rdev);
+void dce6_audio_fini(struct radeon_device *rdev);
 
 /*
  * si
@@ -712,7 +694,6 @@ u32 cik_get_xclk(struct radeon_device *rdev);
 uint32_t cik_pciep_rreg(struct radeon_device *rdev, uint32_t reg);
 void cik_pciep_wreg(struct radeon_device *rdev, uint32_t reg, uint32_t v);
 int cik_set_uvd_clocks(struct radeon_device *rdev, u32 vclk, u32 dclk);
-int cik_uvd_resume(struct radeon_device *rdev);
 void cik_sdma_fence_ring_emit(struct radeon_device *rdev,
 			      struct radeon_fence *fence);
 void cik_sdma_semaphore_ring_emit(struct radeon_device *rdev,
@@ -763,5 +744,82 @@ u32 cik_compute_ring_get_wptr(struct radeon_device *rdev,
 			      struct radeon_ring *ring);
 void cik_compute_ring_set_wptr(struct radeon_device *rdev,
 			       struct radeon_ring *ring);
+int ci_get_temp(struct radeon_device *rdev);
+int kv_get_temp(struct radeon_device *rdev);
+
+int ci_dpm_init(struct radeon_device *rdev);
+int ci_dpm_enable(struct radeon_device *rdev);
+void ci_dpm_disable(struct radeon_device *rdev);
+int ci_dpm_pre_set_power_state(struct radeon_device *rdev);
+int ci_dpm_set_power_state(struct radeon_device *rdev);
+void ci_dpm_post_set_power_state(struct radeon_device *rdev);
+void ci_dpm_setup_asic(struct radeon_device *rdev);
+void ci_dpm_display_configuration_changed(struct radeon_device *rdev);
+void ci_dpm_fini(struct radeon_device *rdev);
+u32 ci_dpm_get_sclk(struct radeon_device *rdev, bool low);
+u32 ci_dpm_get_mclk(struct radeon_device *rdev, bool low);
+void ci_dpm_print_power_state(struct radeon_device *rdev,
+			      struct radeon_ps *ps);
+void ci_dpm_debugfs_print_current_performance_level(struct radeon_device *rdev,
+						    struct seq_file *m);
+int ci_dpm_force_performance_level(struct radeon_device *rdev,
+				   enum radeon_dpm_forced_level level);
+bool ci_dpm_vblank_too_short(struct radeon_device *rdev);
+void ci_dpm_powergate_uvd(struct radeon_device *rdev, bool gate);
+
+int kv_dpm_init(struct radeon_device *rdev);
+int kv_dpm_enable(struct radeon_device *rdev);
+void kv_dpm_disable(struct radeon_device *rdev);
+int kv_dpm_pre_set_power_state(struct radeon_device *rdev);
+int kv_dpm_set_power_state(struct radeon_device *rdev);
+void kv_dpm_post_set_power_state(struct radeon_device *rdev);
+void kv_dpm_setup_asic(struct radeon_device *rdev);
+void kv_dpm_display_configuration_changed(struct radeon_device *rdev);
+void kv_dpm_fini(struct radeon_device *rdev);
+u32 kv_dpm_get_sclk(struct radeon_device *rdev, bool low);
+u32 kv_dpm_get_mclk(struct radeon_device *rdev, bool low);
+void kv_dpm_print_power_state(struct radeon_device *rdev,
+			      struct radeon_ps *ps);
+void kv_dpm_debugfs_print_current_performance_level(struct radeon_device *rdev,
+						    struct seq_file *m);
+int kv_dpm_force_performance_level(struct radeon_device *rdev,
+				   enum radeon_dpm_forced_level level);
+void kv_dpm_powergate_uvd(struct radeon_device *rdev, bool gate);
+void kv_dpm_enable_bapm(struct radeon_device *rdev, bool enable);
+
+/* uvd v1.0 */
+uint32_t uvd_v1_0_get_rptr(struct radeon_device *rdev,
+                           struct radeon_ring *ring);
+uint32_t uvd_v1_0_get_wptr(struct radeon_device *rdev,
+                           struct radeon_ring *ring);
+void uvd_v1_0_set_wptr(struct radeon_device *rdev,
+                       struct radeon_ring *ring);
+
+int uvd_v1_0_init(struct radeon_device *rdev);
+void uvd_v1_0_fini(struct radeon_device *rdev);
+int uvd_v1_0_start(struct radeon_device *rdev);
+void uvd_v1_0_stop(struct radeon_device *rdev);
+
+int uvd_v1_0_ring_test(struct radeon_device *rdev, struct radeon_ring *ring);
+int uvd_v1_0_ib_test(struct radeon_device *rdev, struct radeon_ring *ring);
+void uvd_v1_0_semaphore_emit(struct radeon_device *rdev,
+			     struct radeon_ring *ring,
+			     struct radeon_semaphore *semaphore,
+			     bool emit_wait);
+void uvd_v1_0_ib_execute(struct radeon_device *rdev, struct radeon_ib *ib);
+
+/* uvd v2.2 */
+int uvd_v2_2_resume(struct radeon_device *rdev);
+void uvd_v2_2_fence_emit(struct radeon_device *rdev,
+			 struct radeon_fence *fence);
+
+/* uvd v3.1 */
+void uvd_v3_1_semaphore_emit(struct radeon_device *rdev,
+			     struct radeon_ring *ring,
+			     struct radeon_semaphore *semaphore,
+			     bool emit_wait);
+
+/* uvd v4.2 */
+int uvd_v4_2_resume(struct radeon_device *rdev);
 
 #endif
diff --git a/drivers/gpu/drm/radeon/radeon_atombios.c b/drivers/gpu/drm/radeon/radeon_atombios.c
index 4ccd61f60eb6..f79ee184ffd5 100644
--- a/drivers/gpu/drm/radeon/radeon_atombios.c
+++ b/drivers/gpu/drm/radeon/radeon_atombios.c
@@ -163,8 +163,8 @@ static struct radeon_i2c_bus_rec radeon_lookup_i2c_gpio(struct radeon_device *rd
 		num_indices = (size - sizeof(ATOM_COMMON_TABLE_HEADER)) /
 			sizeof(ATOM_GPIO_I2C_ASSIGMENT);
 
+		gpio = &i2c_info->asGPIO_Info[0];
 		for (i = 0; i < num_indices; i++) {
-			gpio = &i2c_info->asGPIO_Info[i];
 
 			radeon_lookup_i2c_gpio_quirks(rdev, gpio, i);
 
@@ -172,6 +172,8 @@ static struct radeon_i2c_bus_rec radeon_lookup_i2c_gpio(struct radeon_device *rd
 				i2c = radeon_get_bus_rec_for_i2c_gpio(gpio);
 				break;
 			}
+			gpio = (ATOM_GPIO_I2C_ASSIGMENT *)
+				((u8 *)gpio + sizeof(ATOM_GPIO_I2C_ASSIGMENT));
 		}
 	}
 
@@ -195,9 +197,8 @@ void radeon_atombios_i2c_init(struct radeon_device *rdev)
 		num_indices = (size - sizeof(ATOM_COMMON_TABLE_HEADER)) /
 			sizeof(ATOM_GPIO_I2C_ASSIGMENT);
 
+		gpio = &i2c_info->asGPIO_Info[0];
 		for (i = 0; i < num_indices; i++) {
-			gpio = &i2c_info->asGPIO_Info[i];
-
 			radeon_lookup_i2c_gpio_quirks(rdev, gpio, i);
 
 			i2c = radeon_get_bus_rec_for_i2c_gpio(gpio);
@@ -206,12 +207,14 @@ void radeon_atombios_i2c_init(struct radeon_device *rdev)
 				sprintf(stmp, "0x%x", i2c.i2c_id);
 				rdev->i2c_bus[i] = radeon_i2c_create(rdev->ddev, &i2c, stmp);
 			}
+			gpio = (ATOM_GPIO_I2C_ASSIGMENT *)
+				((u8 *)gpio + sizeof(ATOM_GPIO_I2C_ASSIGMENT));
 		}
 	}
 }
 
 static struct radeon_gpio_rec radeon_lookup_gpio(struct radeon_device *rdev,
-							u8 id)
+						 u8 id)
 {
 	struct atom_context *ctx = rdev->mode_info.atom_context;
 	struct radeon_gpio_rec gpio;
@@ -230,8 +233,8 @@ static struct radeon_gpio_rec radeon_lookup_gpio(struct radeon_device *rdev,
 		num_indices = (size - sizeof(ATOM_COMMON_TABLE_HEADER)) /
 			sizeof(ATOM_GPIO_PIN_ASSIGNMENT);
 
+		pin = gpio_info->asGPIO_Pin;
 		for (i = 0; i < num_indices; i++) {
-			pin = &gpio_info->asGPIO_Pin[i];
 			if (id == pin->ucGPIO_ID) {
 				gpio.id = pin->ucGPIO_ID;
 				gpio.reg = le16_to_cpu(pin->usGpioPin_AIndex) * 4;
@@ -239,6 +242,8 @@ static struct radeon_gpio_rec radeon_lookup_gpio(struct radeon_device *rdev,
 				gpio.valid = true;
 				break;
 			}
+			pin = (ATOM_GPIO_PIN_ASSIGNMENT *)
+				((u8 *)pin + sizeof(ATOM_GPIO_PIN_ASSIGNMENT));
 		}
 	}
 
@@ -711,13 +716,16 @@ bool radeon_get_atom_connector_info_from_object_table(struct drm_device *dev)
 								(ATOM_SRC_DST_TABLE_FOR_ONE_OBJECT *)
 								(ctx->bios + data_offset +
 								 le16_to_cpu(router_obj->asObjects[k].usSrcDstTableOffset));
+							u8 *num_dst_objs = (u8 *)
+								((u8 *)router_src_dst_table + 1 +
+								 (router_src_dst_table->ucNumberOfSrc * 2));
+							u16 *dst_objs = (u16 *)(num_dst_objs + 1);
 							int enum_id;
 
 							router.router_id = router_obj_id;
-							for (enum_id = 0; enum_id < router_src_dst_table->ucNumberOfDst;
-							     enum_id++) {
+							for (enum_id = 0; enum_id < (*num_dst_objs); enum_id++) {
 								if (le16_to_cpu(path->usConnObjectId) ==
-								    le16_to_cpu(router_src_dst_table->usDstObjectID[enum_id]))
+								    le16_to_cpu(dst_objs[enum_id]))
 									break;
 							}
 
@@ -1359,6 +1367,7 @@ bool radeon_atombios_get_ppll_ss_info(struct radeon_device *rdev,
 	int index = GetIndexIntoMasterTable(DATA, PPLL_SS_Info);
 	uint16_t data_offset, size;
 	struct _ATOM_SPREAD_SPECTRUM_INFO *ss_info;
+	struct _ATOM_SPREAD_SPECTRUM_ASSIGNMENT *ss_assign;
 	uint8_t frev, crev;
 	int i, num_indices;
 
@@ -1370,18 +1379,21 @@ bool radeon_atombios_get_ppll_ss_info(struct radeon_device *rdev,
 
 		num_indices = (size - sizeof(ATOM_COMMON_TABLE_HEADER)) /
 			sizeof(ATOM_SPREAD_SPECTRUM_ASSIGNMENT);
-
+		ss_assign = (struct _ATOM_SPREAD_SPECTRUM_ASSIGNMENT*)
+			((u8 *)&ss_info->asSS_Info[0]);
 		for (i = 0; i < num_indices; i++) {
-			if (ss_info->asSS_Info[i].ucSS_Id == id) {
+			if (ss_assign->ucSS_Id == id) {
 				ss->percentage =
-					le16_to_cpu(ss_info->asSS_Info[i].usSpreadSpectrumPercentage);
-				ss->type = ss_info->asSS_Info[i].ucSpreadSpectrumType;
-				ss->step = ss_info->asSS_Info[i].ucSS_Step;
-				ss->delay = ss_info->asSS_Info[i].ucSS_Delay;
-				ss->range = ss_info->asSS_Info[i].ucSS_Range;
-				ss->refdiv = ss_info->asSS_Info[i].ucRecommendedRef_Div;
+					le16_to_cpu(ss_assign->usSpreadSpectrumPercentage);
+				ss->type = ss_assign->ucSpreadSpectrumType;
+				ss->step = ss_assign->ucSS_Step;
+				ss->delay = ss_assign->ucSS_Delay;
+				ss->range = ss_assign->ucSS_Range;
+				ss->refdiv = ss_assign->ucRecommendedRef_Div;
 				return true;
 			}
+			ss_assign = (struct _ATOM_SPREAD_SPECTRUM_ASSIGNMENT*)
+				((u8 *)ss_assign + sizeof(struct _ATOM_SPREAD_SPECTRUM_ASSIGNMENT));
 		}
 	}
 	return false;
@@ -1469,6 +1481,12 @@ union asic_ss_info {
 	struct _ATOM_ASIC_INTERNAL_SS_INFO_V3 info_3;
 };
 
+union asic_ss_assignment {
+	struct _ATOM_ASIC_SS_ASSIGNMENT v1;
+	struct _ATOM_ASIC_SS_ASSIGNMENT_V2 v2;
+	struct _ATOM_ASIC_SS_ASSIGNMENT_V3 v3;
+};
+
 bool radeon_atombios_get_asic_ss_info(struct radeon_device *rdev,
 				      struct radeon_atom_ss *ss,
 				      int id, u32 clock)
@@ -1477,9 +1495,19 @@ bool radeon_atombios_get_asic_ss_info(struct radeon_device *rdev,
 	int index = GetIndexIntoMasterTable(DATA, ASIC_InternalSS_Info);
 	uint16_t data_offset, size;
 	union asic_ss_info *ss_info;
+	union asic_ss_assignment *ss_assign;
 	uint8_t frev, crev;
 	int i, num_indices;
 
+	if (id == ASIC_INTERNAL_MEMORY_SS) {
+		if (!(rdev->mode_info.firmware_flags & ATOM_BIOS_INFO_MEMORY_CLOCK_SS_SUPPORT))
+			return false;
+	}
+	if (id == ASIC_INTERNAL_ENGINE_SS) {
+		if (!(rdev->mode_info.firmware_flags & ATOM_BIOS_INFO_ENGINE_CLOCK_SS_SUPPORT))
+			return false;
+	}
+
 	memset(ss, 0, sizeof(struct radeon_atom_ss));
 	if (atom_parse_data_header(mode_info->atom_context, index, &size,
 				   &frev, &crev, &data_offset)) {
@@ -1492,45 +1520,52 @@ bool radeon_atombios_get_asic_ss_info(struct radeon_device *rdev,
 			num_indices = (size - sizeof(ATOM_COMMON_TABLE_HEADER)) /
 				sizeof(ATOM_ASIC_SS_ASSIGNMENT);
 
+			ss_assign = (union asic_ss_assignment *)((u8 *)&ss_info->info.asSpreadSpectrum[0]);
 			for (i = 0; i < num_indices; i++) {
-				if ((ss_info->info.asSpreadSpectrum[i].ucClockIndication == id) &&
-				    (clock <= le32_to_cpu(ss_info->info.asSpreadSpectrum[i].ulTargetClockRange))) {
+				if ((ss_assign->v1.ucClockIndication == id) &&
+				    (clock <= le32_to_cpu(ss_assign->v1.ulTargetClockRange))) {
 					ss->percentage =
-						le16_to_cpu(ss_info->info.asSpreadSpectrum[i].usSpreadSpectrumPercentage);
-					ss->type = ss_info->info.asSpreadSpectrum[i].ucSpreadSpectrumMode;
-					ss->rate = le16_to_cpu(ss_info->info.asSpreadSpectrum[i].usSpreadRateInKhz);
+						le16_to_cpu(ss_assign->v1.usSpreadSpectrumPercentage);
+					ss->type = ss_assign->v1.ucSpreadSpectrumMode;
+					ss->rate = le16_to_cpu(ss_assign->v1.usSpreadRateInKhz);
 					return true;
 				}
+				ss_assign = (union asic_ss_assignment *)
+					((u8 *)ss_assign + sizeof(ATOM_ASIC_SS_ASSIGNMENT));
 			}
 			break;
 		case 2:
 			num_indices = (size - sizeof(ATOM_COMMON_TABLE_HEADER)) /
 				sizeof(ATOM_ASIC_SS_ASSIGNMENT_V2);
+			ss_assign = (union asic_ss_assignment *)((u8 *)&ss_info->info_2.asSpreadSpectrum[0]);
 			for (i = 0; i < num_indices; i++) {
-				if ((ss_info->info_2.asSpreadSpectrum[i].ucClockIndication == id) &&
-				    (clock <= le32_to_cpu(ss_info->info_2.asSpreadSpectrum[i].ulTargetClockRange))) {
+				if ((ss_assign->v2.ucClockIndication == id) &&
+				    (clock <= le32_to_cpu(ss_assign->v2.ulTargetClockRange))) {
 					ss->percentage =
-						le16_to_cpu(ss_info->info_2.asSpreadSpectrum[i].usSpreadSpectrumPercentage);
-					ss->type = ss_info->info_2.asSpreadSpectrum[i].ucSpreadSpectrumMode;
-					ss->rate = le16_to_cpu(ss_info->info_2.asSpreadSpectrum[i].usSpreadRateIn10Hz);
+						le16_to_cpu(ss_assign->v2.usSpreadSpectrumPercentage);
+					ss->type = ss_assign->v2.ucSpreadSpectrumMode;
+					ss->rate = le16_to_cpu(ss_assign->v2.usSpreadRateIn10Hz);
 					if ((crev == 2) &&
 					    ((id == ASIC_INTERNAL_ENGINE_SS) ||
 					     (id == ASIC_INTERNAL_MEMORY_SS)))
 						ss->rate /= 100;
 					return true;
 				}
+				ss_assign = (union asic_ss_assignment *)
+					((u8 *)ss_assign + sizeof(ATOM_ASIC_SS_ASSIGNMENT_V2));
 			}
 			break;
 		case 3:
 			num_indices = (size - sizeof(ATOM_COMMON_TABLE_HEADER)) /
 				sizeof(ATOM_ASIC_SS_ASSIGNMENT_V3);
+			ss_assign = (union asic_ss_assignment *)((u8 *)&ss_info->info_3.asSpreadSpectrum[0]);
 			for (i = 0; i < num_indices; i++) {
-				if ((ss_info->info_3.asSpreadSpectrum[i].ucClockIndication == id) &&
-				    (clock <= le32_to_cpu(ss_info->info_3.asSpreadSpectrum[i].ulTargetClockRange))) {
+				if ((ss_assign->v3.ucClockIndication == id) &&
+				    (clock <= le32_to_cpu(ss_assign->v3.ulTargetClockRange))) {
 					ss->percentage =
-						le16_to_cpu(ss_info->info_3.asSpreadSpectrum[i].usSpreadSpectrumPercentage);
-					ss->type = ss_info->info_3.asSpreadSpectrum[i].ucSpreadSpectrumMode;
-					ss->rate = le16_to_cpu(ss_info->info_3.asSpreadSpectrum[i].usSpreadRateIn10Hz);
+						le16_to_cpu(ss_assign->v3.usSpreadSpectrumPercentage);
+					ss->type = ss_assign->v3.ucSpreadSpectrumMode;
+					ss->rate = le16_to_cpu(ss_assign->v3.usSpreadRateIn10Hz);
 					if ((id == ASIC_INTERNAL_ENGINE_SS) ||
 					    (id == ASIC_INTERNAL_MEMORY_SS))
 						ss->rate /= 100;
@@ -1538,6 +1573,8 @@ bool radeon_atombios_get_asic_ss_info(struct radeon_device *rdev,
 						radeon_atombios_get_igp_ss_overrides(rdev, ss, id);
 					return true;
 				}
+				ss_assign = (union asic_ss_assignment *)
+					((u8 *)ss_assign + sizeof(ATOM_ASIC_SS_ASSIGNMENT_V3));
 			}
 			break;
 		default:
@@ -1672,7 +1709,9 @@ struct radeon_encoder_atom_dig *radeon_atombios_get_lvds_info(struct
 								kfree(edid);
 						}
 					}
-					record += sizeof(ATOM_FAKE_EDID_PATCH_RECORD);
+					record += fake_edid_record->ucFakeEDIDLength ?
+						fake_edid_record->ucFakeEDIDLength + 2 :
+						sizeof(ATOM_FAKE_EDID_PATCH_RECORD);
 					break;
 				case LCD_PANEL_RESOLUTION_RECORD_TYPE:
 					panel_res_record = (ATOM_PANEL_RESOLUTION_PATCH_RECORD *)record;
@@ -2237,6 +2276,11 @@ static void radeon_atombios_add_pplib_thermal_controller(struct radeon_device *r
 				 (controller->ucFanParameters &
 				  ATOM_PP_FANPARAMETERS_NOFAN) ? "without" : "with");
 			rdev->pm.int_thermal_type = THERMAL_TYPE_CI;
+		} else if (controller->ucType == ATOM_PP_THERMALCONTROLLER_KAVERI) {
+			DRM_INFO("Internal thermal controller %s fan control\n",
+				 (controller->ucFanParameters &
+				  ATOM_PP_FANPARAMETERS_NOFAN) ? "without" : "with");
+			rdev->pm.int_thermal_type = THERMAL_TYPE_KV;
 		} else if ((controller->ucType ==
 			    ATOM_PP_THERMALCONTROLLER_EXTERNAL_GPIO) ||
 			   (controller->ucType ==
@@ -3077,6 +3121,121 @@ int radeon_atom_get_leakage_vddc_based_on_leakage_idx(struct radeon_device *rdev
 	return radeon_atom_get_max_vddc(rdev, VOLTAGE_TYPE_VDDC, leakage_idx, voltage);
 }
 
+int radeon_atom_get_leakage_id_from_vbios(struct radeon_device *rdev,
+					  u16 *leakage_id)
+{
+	union set_voltage args;
+	int index = GetIndexIntoMasterTable(COMMAND, SetVoltage);
+	u8 frev, crev;
+
+	if (!atom_parse_cmd_header(rdev->mode_info.atom_context, index, &frev, &crev))
+		return -EINVAL;
+
+	switch (crev) {
+	case 3:
+	case 4:
+		args.v3.ucVoltageType = 0;
+		args.v3.ucVoltageMode = ATOM_GET_LEAKAGE_ID;
+		args.v3.usVoltageLevel = 0;
+
+		atom_execute_table(rdev->mode_info.atom_context, index, (uint32_t *)&args);
+
+		*leakage_id = le16_to_cpu(args.v3.usVoltageLevel);
+		break;
+	default:
+		DRM_ERROR("Unknown table version %d, %d\n", frev, crev);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+int radeon_atom_get_leakage_vddc_based_on_leakage_params(struct radeon_device *rdev,
+							 u16 *vddc, u16 *vddci,
+							 u16 virtual_voltage_id,
+							 u16 vbios_voltage_id)
+{
+	int index = GetIndexIntoMasterTable(DATA, ASIC_ProfilingInfo);
+	u8 frev, crev;
+	u16 data_offset, size;
+	int i, j;
+	ATOM_ASIC_PROFILING_INFO_V2_1 *profile;
+	u16 *leakage_bin, *vddc_id_buf, *vddc_buf, *vddci_id_buf, *vddci_buf;
+
+	*vddc = 0;
+	*vddci = 0;
+
+	if (!atom_parse_data_header(rdev->mode_info.atom_context, index, &size,
+				    &frev, &crev, &data_offset))
+		return -EINVAL;
+
+	profile = (ATOM_ASIC_PROFILING_INFO_V2_1 *)
+		(rdev->mode_info.atom_context->bios + data_offset);
+
+	switch (frev) {
+	case 1:
+		return -EINVAL;
+	case 2:
+		switch (crev) {
+		case 1:
+			if (size < sizeof(ATOM_ASIC_PROFILING_INFO_V2_1))
+				return -EINVAL;
+			leakage_bin = (u16 *)
+				(rdev->mode_info.atom_context->bios + data_offset +
+				 le16_to_cpu(profile->usLeakageBinArrayOffset));
+			vddc_id_buf = (u16 *)
+				(rdev->mode_info.atom_context->bios + data_offset +
+				 le16_to_cpu(profile->usElbVDDC_IdArrayOffset));
+			vddc_buf = (u16 *)
+				(rdev->mode_info.atom_context->bios + data_offset +
+				 le16_to_cpu(profile->usElbVDDC_LevelArrayOffset));
+			vddci_id_buf = (u16 *)
+				(rdev->mode_info.atom_context->bios + data_offset +
+				 le16_to_cpu(profile->usElbVDDCI_IdArrayOffset));
+			vddci_buf = (u16 *)
+				(rdev->mode_info.atom_context->bios + data_offset +
+				 le16_to_cpu(profile->usElbVDDCI_LevelArrayOffset));
+
+			if (profile->ucElbVDDC_Num > 0) {
+				for (i = 0; i < profile->ucElbVDDC_Num; i++) {
+					if (vddc_id_buf[i] == virtual_voltage_id) {
+						for (j = 0; j < profile->ucLeakageBinNum; j++) {
+							if (vbios_voltage_id <= leakage_bin[j]) {
+								*vddc = vddc_buf[j * profile->ucElbVDDC_Num + i];
+								break;
+							}
+						}
+						break;
+					}
+				}
+			}
+			if (profile->ucElbVDDCI_Num > 0) {
+				for (i = 0; i < profile->ucElbVDDCI_Num; i++) {
+					if (vddci_id_buf[i] == virtual_voltage_id) {
+						for (j = 0; j < profile->ucLeakageBinNum; j++) {
+							if (vbios_voltage_id <= leakage_bin[j]) {
+								*vddci = vddci_buf[j * profile->ucElbVDDCI_Num + i];
+								break;
+							}
+						}
+						break;
+					}
+				}
+			}
+			break;
+		default:
+			DRM_ERROR("Unknown table version %d, %d\n", frev, crev);
+			return -EINVAL;
+		}
+		break;
+	default:
+		DRM_ERROR("Unknown table version %d, %d\n", frev, crev);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 int radeon_atom_get_voltage_gpio_settings(struct radeon_device *rdev,
 					  u16 voltage_level, u8 voltage_type,
 					  u32 *gpio_value, u32 *gpio_mask)
@@ -3279,10 +3438,11 @@ int radeon_atom_get_max_voltage(struct radeon_device *rdev,
 				ATOM_VOLTAGE_FORMULA_V2 *formula =
 					&voltage_object->v2.asFormula;
 				if (formula->ucNumOfVoltageEntries) {
+					VOLTAGE_LUT_ENTRY *lut = (VOLTAGE_LUT_ENTRY *)
+						((u8 *)&formula->asVIDAdjustEntries[0] +
+						 (sizeof(VOLTAGE_LUT_ENTRY) * (formula->ucNumOfVoltageEntries - 1)));
 					*max_voltage =
-						le16_to_cpu(formula->asVIDAdjustEntries[
-								    formula->ucNumOfVoltageEntries - 1
-								    ].usVoltageValue);
+						le16_to_cpu(lut->usVoltageValue);
 					return 0;
 				}
 			}
@@ -3442,11 +3602,13 @@ int radeon_atom_get_voltage_table(struct radeon_device *rdev,
 				if (voltage_object) {
 					ATOM_VOLTAGE_FORMULA_V2 *formula =
 						&voltage_object->v2.asFormula;
+					VOLTAGE_LUT_ENTRY *lut;
 					if (formula->ucNumOfVoltageEntries > MAX_VOLTAGE_ENTRIES)
 						return -EINVAL;
+					lut = &formula->asVIDAdjustEntries[0];
 					for (i = 0; i < formula->ucNumOfVoltageEntries; i++) {
 						voltage_table->entries[i].value =
-							le16_to_cpu(formula->asVIDAdjustEntries[i].usVoltageValue);
+							le16_to_cpu(lut->usVoltageValue);
 						ret = radeon_atom_get_voltage_gpio_settings(rdev,
 											    voltage_table->entries[i].value,
 											    voltage_type,
@@ -3454,6 +3616,8 @@ int radeon_atom_get_voltage_table(struct radeon_device *rdev,
 											    &voltage_table->mask_low);
 						if (ret)
 							return ret;
+						lut = (VOLTAGE_LUT_ENTRY *)
+							((u8 *)lut + sizeof(VOLTAGE_LUT_ENTRY));
 					}
 					voltage_table->count = formula->ucNumOfVoltageEntries;
 					return 0;
@@ -3473,13 +3637,17 @@ int radeon_atom_get_voltage_table(struct radeon_device *rdev,
 				if (voltage_object) {
 					ATOM_GPIO_VOLTAGE_OBJECT_V3 *gpio =
 						&voltage_object->v3.asGpioVoltageObj;
+					VOLTAGE_LUT_ENTRY_V2 *lut;
 					if (gpio->ucGpioEntryNum > MAX_VOLTAGE_ENTRIES)
 						return -EINVAL;
+					lut = &gpio->asVolGpioLut[0];
 					for (i = 0; i < gpio->ucGpioEntryNum; i++) {
 						voltage_table->entries[i].value =
-							le16_to_cpu(gpio->asVolGpioLut[i].usVoltageValue);
+							le16_to_cpu(lut->usVoltageValue);
 						voltage_table->entries[i].smio_low =
-							le32_to_cpu(gpio->asVolGpioLut[i].ulVoltageId);
+							le32_to_cpu(lut->ulVoltageId);
+						lut = (VOLTAGE_LUT_ENTRY_V2 *)
+							((u8 *)lut + sizeof(VOLTAGE_LUT_ENTRY_V2));
 					}
 					voltage_table->mask_low = le32_to_cpu(gpio->ulGpioMaskVal);
 					voltage_table->count = gpio->ucGpioEntryNum;
@@ -3605,7 +3773,6 @@ int radeon_atom_get_mclk_range_table(struct radeon_device *rdev,
 	union vram_info *vram_info;
 	u32 mem_timing_size = gddr5 ?
 		sizeof(ATOM_MEMORY_TIMING_FORMAT_V2) : sizeof(ATOM_MEMORY_TIMING_FORMAT);
-	u8 *p;
 
 	memset(mclk_range_table, 0, sizeof(struct atom_memory_clock_range_table));
 
@@ -3624,6 +3791,7 @@ int radeon_atom_get_mclk_range_table(struct radeon_device *rdev,
 				if (module_index < vram_info->v1_4.ucNumOfVRAMModule) {
 					ATOM_VRAM_MODULE_V4 *vram_module =
 						(ATOM_VRAM_MODULE_V4 *)vram_info->v1_4.aVramInfo;
+					ATOM_MEMORY_TIMING_FORMAT *format;
 
 					for (i = 0; i < module_index; i++) {
 						if (le16_to_cpu(vram_module->usModuleSize) == 0)
@@ -3634,11 +3802,11 @@ int radeon_atom_get_mclk_range_table(struct radeon_device *rdev,
 					mclk_range_table->num_entries = (u8)
 						((le16_to_cpu(vram_module->usModuleSize) - offsetof(ATOM_VRAM_MODULE_V4, asMemTiming)) /
 						 mem_timing_size);
-					p = (u8 *)&vram_module->asMemTiming[0];
+					format = &vram_module->asMemTiming[0];
 					for (i = 0; i < mclk_range_table->num_entries; i++) {
-						ATOM_MEMORY_TIMING_FORMAT *format = (ATOM_MEMORY_TIMING_FORMAT *)p;
 						mclk_range_table->mclk[i] = le32_to_cpu(format->ulClkRange);
-						p += mem_timing_size;
+						format = (ATOM_MEMORY_TIMING_FORMAT *)
+							((u8 *)format + mem_timing_size);
 					}
 				} else
 					return -EINVAL;
diff --git a/drivers/gpu/drm/radeon/radeon_blit_common.h b/drivers/gpu/drm/radeon/radeon_blit_common.h
deleted file mode 100644
index 4ecbe72c9d2d..000000000000
--- a/drivers/gpu/drm/radeon/radeon_blit_common.h
+++ /dev/null
@@ -1,44 +0,0 @@
-/*
- * Copyright 2009 Advanced Micro Devices, Inc.
- * Copyright 2009 Red Hat Inc.
- * Copyright 2012 Alcatel-Lucent, Inc.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice (including the next
- * paragraph) shall be included in all copies or substantial portions of the
- * Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE COPYRIGHT HOLDER(S) AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM, DAMAGES OR
- * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
- * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
- * DEALINGS IN THE SOFTWARE.
- *
- */
-
-#ifndef __RADEON_BLIT_COMMON_H__
-
-#define DI_PT_RECTLIST        0x11
-#define DI_INDEX_SIZE_16_BIT  0x0
-#define DI_SRC_SEL_AUTO_INDEX 0x2
-
-#define FMT_8                 0x1
-#define FMT_5_6_5             0x8
-#define FMT_8_8_8_8           0x1a
-#define COLOR_8               0x1
-#define COLOR_5_6_5           0x8
-#define COLOR_8_8_8_8         0x1a
-
-#define RECT_UNIT_H           32
-#define RECT_UNIT_W           (RADEON_GPU_PAGE_SIZE / 4 / RECT_UNIT_H)
-
-#define __RADEON_BLIT_COMMON_H__
-#endif
diff --git a/drivers/gpu/drm/radeon/radeon_connectors.c b/drivers/gpu/drm/radeon/radeon_connectors.c
index 2399f25ec037..79159b5da05b 100644
--- a/drivers/gpu/drm/radeon/radeon_connectors.c
+++ b/drivers/gpu/drm/radeon/radeon_connectors.c
@@ -396,6 +396,21 @@ static int radeon_connector_set_property(struct drm_connector *connector, struct
 		}
 	}
 
+	if (property == rdev->mode_info.audio_property) {
+		struct radeon_connector *radeon_connector = to_radeon_connector(connector);
+		/* need to find digital encoder on connector */
+		encoder = radeon_find_encoder(connector, DRM_MODE_ENCODER_TMDS);
+		if (!encoder)
+			return 0;
+
+		radeon_encoder = to_radeon_encoder(encoder);
+
+		if (radeon_connector->audio != val) {
+			radeon_connector->audio = val;
+			radeon_property_change_mode(&radeon_encoder->base);
+		}
+	}
+
 	if (property == rdev->mode_info.underscan_property) {
 		/* need to find digital encoder on connector */
 		encoder = radeon_find_encoder(connector, DRM_MODE_ENCODER_TMDS);
@@ -1420,7 +1435,7 @@ radeon_dp_detect(struct drm_connector *connector, bool force)
 				if (radeon_dp_getdpcd(radeon_connector))
 					ret = connector_status_connected;
 			} else {
-				/* try non-aux ddc (DP to DVI/HMDI/etc. adapter) */
+				/* try non-aux ddc (DP to DVI/HDMI/etc. adapter) */
 				if (radeon_ddc_probe(radeon_connector, false))
 					ret = connector_status_connected;
 			}
@@ -1489,6 +1504,24 @@ static const struct drm_connector_funcs radeon_dp_connector_funcs = {
 	.force = radeon_dvi_force,
 };
 
+static const struct drm_connector_funcs radeon_edp_connector_funcs = {
+	.dpms = drm_helper_connector_dpms,
+	.detect = radeon_dp_detect,
+	.fill_modes = drm_helper_probe_single_connector_modes,
+	.set_property = radeon_lvds_set_property,
+	.destroy = radeon_dp_connector_destroy,
+	.force = radeon_dvi_force,
+};
+
+static const struct drm_connector_funcs radeon_lvds_bridge_connector_funcs = {
+	.dpms = drm_helper_connector_dpms,
+	.detect = radeon_dp_detect,
+	.fill_modes = drm_helper_probe_single_connector_modes,
+	.set_property = radeon_lvds_set_property,
+	.destroy = radeon_dp_connector_destroy,
+	.force = radeon_dvi_force,
+};
+
 void
 radeon_add_atom_connector(struct drm_device *dev,
 			  uint32_t connector_id,
@@ -1580,8 +1613,6 @@ radeon_add_atom_connector(struct drm_device *dev,
 			goto failed;
 		radeon_dig_connector->igp_lane_info = igp_lane_info;
 		radeon_connector->con_priv = radeon_dig_connector;
-		drm_connector_init(dev, &radeon_connector->base, &radeon_dp_connector_funcs, connector_type);
-		drm_connector_helper_add(&radeon_connector->base, &radeon_dp_connector_helper_funcs);
 		if (i2c_bus->valid) {
 			/* add DP i2c bus */
 			if (connector_type == DRM_MODE_CONNECTOR_eDP)
@@ -1598,6 +1629,10 @@ radeon_add_atom_connector(struct drm_device *dev,
 		case DRM_MODE_CONNECTOR_VGA:
 		case DRM_MODE_CONNECTOR_DVIA:
 		default:
+			drm_connector_init(dev, &radeon_connector->base,
+					   &radeon_dp_connector_funcs, connector_type);
+			drm_connector_helper_add(&radeon_connector->base,
+						 &radeon_dp_connector_helper_funcs);
 			connector->interlace_allowed = true;
 			connector->doublescan_allowed = true;
 			radeon_connector->dac_load_detect = true;
@@ -1610,6 +1645,10 @@ radeon_add_atom_connector(struct drm_device *dev,
 		case DRM_MODE_CONNECTOR_HDMIA:
 		case DRM_MODE_CONNECTOR_HDMIB:
 		case DRM_MODE_CONNECTOR_DisplayPort:
+			drm_connector_init(dev, &radeon_connector->base,
+					   &radeon_dp_connector_funcs, connector_type);
+			drm_connector_helper_add(&radeon_connector->base,
+						 &radeon_dp_connector_helper_funcs);
 			drm_object_attach_property(&radeon_connector->base.base,
 						      rdev->mode_info.underscan_property,
 						      UNDERSCAN_OFF);
@@ -1619,6 +1658,9 @@ radeon_add_atom_connector(struct drm_device *dev,
 			drm_object_attach_property(&radeon_connector->base.base,
 						      rdev->mode_info.underscan_vborder_property,
 						      0);
+			drm_object_attach_property(&radeon_connector->base.base,
+						   rdev->mode_info.audio_property,
+						   RADEON_AUDIO_DISABLE);
 			subpixel_order = SubPixelHorizontalRGB;
 			connector->interlace_allowed = true;
 			if (connector_type == DRM_MODE_CONNECTOR_HDMIB)
@@ -1634,6 +1676,10 @@ radeon_add_atom_connector(struct drm_device *dev,
 			break;
 		case DRM_MODE_CONNECTOR_LVDS:
 		case DRM_MODE_CONNECTOR_eDP:
+			drm_connector_init(dev, &radeon_connector->base,
+					   &radeon_lvds_bridge_connector_funcs, connector_type);
+			drm_connector_helper_add(&radeon_connector->base,
+						 &radeon_dp_connector_helper_funcs);
 			drm_object_attach_property(&radeon_connector->base.base,
 						      dev->mode_config.scaling_mode_property,
 						      DRM_MODE_SCALE_FULLSCREEN);
@@ -1708,6 +1754,11 @@ radeon_add_atom_connector(struct drm_device *dev,
 							      rdev->mode_info.underscan_vborder_property,
 							      0);
 			}
+			if (ASIC_IS_DCE2(rdev)) {
+				drm_object_attach_property(&radeon_connector->base.base,
+							      rdev->mode_info.audio_property,
+							      RADEON_AUDIO_DISABLE);
+			}
 			if (connector_type == DRM_MODE_CONNECTOR_DVII) {
 				radeon_connector->dac_load_detect = true;
 				drm_object_attach_property(&radeon_connector->base.base,
@@ -1748,6 +1799,11 @@ radeon_add_atom_connector(struct drm_device *dev,
 							      rdev->mode_info.underscan_vborder_property,
 							      0);
 			}
+			if (ASIC_IS_DCE2(rdev)) {
+				drm_object_attach_property(&radeon_connector->base.base,
+							      rdev->mode_info.audio_property,
+							      RADEON_AUDIO_DISABLE);
+			}
 			subpixel_order = SubPixelHorizontalRGB;
 			connector->interlace_allowed = true;
 			if (connector_type == DRM_MODE_CONNECTOR_HDMIB)
@@ -1787,6 +1843,11 @@ radeon_add_atom_connector(struct drm_device *dev,
 							      rdev->mode_info.underscan_vborder_property,
 							      0);
 			}
+			if (ASIC_IS_DCE2(rdev)) {
+				drm_object_attach_property(&radeon_connector->base.base,
+							      rdev->mode_info.audio_property,
+							      RADEON_AUDIO_DISABLE);
+			}
 			connector->interlace_allowed = true;
 			/* in theory with a DP to VGA converter... */
 			connector->doublescan_allowed = false;
@@ -1797,7 +1858,7 @@ radeon_add_atom_connector(struct drm_device *dev,
 				goto failed;
 			radeon_dig_connector->igp_lane_info = igp_lane_info;
 			radeon_connector->con_priv = radeon_dig_connector;
-			drm_connector_init(dev, &radeon_connector->base, &radeon_dp_connector_funcs, connector_type);
+			drm_connector_init(dev, &radeon_connector->base, &radeon_edp_connector_funcs, connector_type);
 			drm_connector_helper_add(&radeon_connector->base, &radeon_dp_connector_helper_funcs);
 			if (i2c_bus->valid) {
 				/* add DP i2c bus */
diff --git a/drivers/gpu/drm/radeon/radeon_cp.c b/drivers/gpu/drm/radeon/radeon_cp.c
index efc4f6441ef4..3cae2bbc1854 100644
--- a/drivers/gpu/drm/radeon/radeon_cp.c
+++ b/drivers/gpu/drm/radeon/radeon_cp.c
@@ -1444,13 +1444,13 @@ static int radeon_do_init_cp(struct drm_device *dev, drm_radeon_init_t *init,
 	dev_priv->ring.end = ((u32 *) dev_priv->cp_ring->handle
 			      + init->ring_size / sizeof(u32));
 	dev_priv->ring.size = init->ring_size;
-	dev_priv->ring.size_l2qw = drm_order(init->ring_size / 8);
+	dev_priv->ring.size_l2qw = order_base_2(init->ring_size / 8);
 
 	dev_priv->ring.rptr_update = /* init->rptr_update */ 4096;
-	dev_priv->ring.rptr_update_l2qw = drm_order( /* init->rptr_update */ 4096 / 8);
+	dev_priv->ring.rptr_update_l2qw = order_base_2( /* init->rptr_update */ 4096 / 8);
 
 	dev_priv->ring.fetch_size = /* init->fetch_size */ 32;
-	dev_priv->ring.fetch_size_l2ow = drm_order( /* init->fetch_size */ 32 / 16);
+	dev_priv->ring.fetch_size_l2ow = order_base_2( /* init->fetch_size */ 32 / 16);
 	dev_priv->ring.tail_mask = (dev_priv->ring.size / sizeof(u32)) - 1;
 
 	dev_priv->ring.high_mark = RADEON_RING_HIGH_MARK;
diff --git a/drivers/gpu/drm/radeon/radeon_cs.c b/drivers/gpu/drm/radeon/radeon_cs.c
index 13a130fb3517..66c222836631 100644
--- a/drivers/gpu/drm/radeon/radeon_cs.c
+++ b/drivers/gpu/drm/radeon/radeon_cs.c
@@ -28,6 +28,7 @@
 #include <drm/radeon_drm.h>
 #include "radeon_reg.h"
 #include "radeon.h"
+#include "radeon_trace.h"
 
 static int radeon_cs_parser_relocs(struct radeon_cs_parser *p)
 {
@@ -80,10 +81,13 @@ static int radeon_cs_parser_relocs(struct radeon_cs_parser *p)
 		p->relocs[i].lobj.bo = p->relocs[i].robj;
 		p->relocs[i].lobj.written = !!r->write_domain;
 
-		/* the first reloc of an UVD job is the
-		   msg and that must be in VRAM */
-		if (p->ring == R600_RING_TYPE_UVD_INDEX && i == 0) {
-			/* TODO: is this still needed for NI+ ? */
+		/* the first reloc of an UVD job is the msg and that must be in
+		   VRAM, also but everything into VRAM on AGP cards to avoid
+		   image corruptions */
+		if (p->ring == R600_RING_TYPE_UVD_INDEX &&
+		    p->rdev->family < CHIP_PALM &&
+		    (i == 0 || drm_pci_device_is_agp(p->rdev->ddev))) {
+
 			p->relocs[i].lobj.domain =
 				RADEON_GEM_DOMAIN_VRAM;
 
@@ -268,7 +272,7 @@ int radeon_cs_parser_init(struct radeon_cs_parser *p, void *data)
 			return -EINVAL;
 
 		/* we only support VM on some SI+ rings */
-		if ((p->rdev->asic->ring[p->ring].cs_parse == NULL) &&
+		if ((p->rdev->asic->ring[p->ring]->cs_parse == NULL) &&
 		   ((p->cs_flags & RADEON_CS_USE_VM) == 0)) {
 			DRM_ERROR("Ring %d requires VM!\n", p->ring);
 			return -EINVAL;
@@ -383,6 +387,10 @@ static int radeon_cs_ib_chunk(struct radeon_device *rdev,
 		DRM_ERROR("Invalid command stream !\n");
 		return r;
 	}
+
+	if (parser->ring == R600_RING_TYPE_UVD_INDEX)
+		radeon_uvd_note_usage(rdev);
+
 	radeon_cs_sync_rings(parser);
 	r = radeon_ib_schedule(rdev, &parser->ib, NULL);
 	if (r) {
@@ -474,6 +482,9 @@ static int radeon_cs_ib_vm_chunk(struct radeon_device *rdev,
 		return r;
 	}
 
+	if (parser->ring == R600_RING_TYPE_UVD_INDEX)
+		radeon_uvd_note_usage(rdev);
+
 	mutex_lock(&rdev->vm_manager.lock);
 	mutex_lock(&vm->mutex);
 	r = radeon_vm_alloc_pt(rdev, vm);
@@ -552,9 +563,7 @@ int radeon_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 		return r;
 	}
 
-	/* XXX pick SD/HD/MVC */
-	if (parser.ring == R600_RING_TYPE_UVD_INDEX)
-		radeon_uvd_note_usage(rdev);
+	trace_radeon_cs(&parser);
 
 	r = radeon_cs_ib_chunk(rdev, &parser);
 	if (r) {
diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c
index 63398ae1dbf5..841d0e09be3e 100644
--- a/drivers/gpu/drm/radeon/radeon_device.c
+++ b/drivers/gpu/drm/radeon/radeon_device.c
@@ -1003,16 +1003,28 @@ static void radeon_check_arguments(struct radeon_device *rdev)
 		radeon_vram_limit = 0;
 	}
 
+	if (radeon_gart_size == -1) {
+		/* default to a larger gart size on newer asics */
+		if (rdev->family >= CHIP_RV770)
+			radeon_gart_size = 1024;
+		else
+			radeon_gart_size = 512;
+	}
 	/* gtt size must be power of two and greater or equal to 32M */
 	if (radeon_gart_size < 32) {
-		dev_warn(rdev->dev, "gart size (%d) too small forcing to 512M\n",
+		dev_warn(rdev->dev, "gart size (%d) too small\n",
 				radeon_gart_size);
-		radeon_gart_size = 512;
-
+		if (rdev->family >= CHIP_RV770)
+			radeon_gart_size = 1024;
+		else
+			radeon_gart_size = 512;
 	} else if (!radeon_check_pot_argument(radeon_gart_size)) {
 		dev_warn(rdev->dev, "gart size (%d) must be a power of 2\n",
 				radeon_gart_size);
-		radeon_gart_size = 512;
+		if (rdev->family >= CHIP_RV770)
+			radeon_gart_size = 1024;
+		else
+			radeon_gart_size = 512;
 	}
 	rdev->mc.gtt_size = (uint64_t)radeon_gart_size << 20;
 
@@ -1144,7 +1156,7 @@ int radeon_device_init(struct radeon_device *rdev,
 	rdev->family = flags & RADEON_FAMILY_MASK;
 	rdev->is_atom_bios = false;
 	rdev->usec_timeout = RADEON_MAX_USEC_TIMEOUT;
-	rdev->mc.gtt_size = radeon_gart_size * 1024 * 1024;
+	rdev->mc.gtt_size = 512 * 1024 * 1024;
 	rdev->accel_working = false;
 	/* set up ring ids */
 	for (i = 0; i < RADEON_NUM_RINGS; i++) {
@@ -1237,6 +1249,17 @@ int radeon_device_init(struct radeon_device *rdev,
 	/* Registers mapping */
 	/* TODO: block userspace mapping of io register */
 	spin_lock_init(&rdev->mmio_idx_lock);
+	spin_lock_init(&rdev->smc_idx_lock);
+	spin_lock_init(&rdev->pll_idx_lock);
+	spin_lock_init(&rdev->mc_idx_lock);
+	spin_lock_init(&rdev->pcie_idx_lock);
+	spin_lock_init(&rdev->pciep_idx_lock);
+	spin_lock_init(&rdev->pif_idx_lock);
+	spin_lock_init(&rdev->cg_idx_lock);
+	spin_lock_init(&rdev->uvd_idx_lock);
+	spin_lock_init(&rdev->rcu_idx_lock);
+	spin_lock_init(&rdev->didt_idx_lock);
+	spin_lock_init(&rdev->end_idx_lock);
 	if (rdev->family >= CHIP_BONAIRE) {
 		rdev->rmmio_base = pci_resource_start(rdev->pdev, 5);
 		rdev->rmmio_size = pci_resource_len(rdev->pdev, 5);
@@ -1270,7 +1293,7 @@ int radeon_device_init(struct radeon_device *rdev,
 	/* this will fail for cards that aren't VGA class devices, just
 	 * ignore it */
 	vga_client_register(rdev->pdev, rdev, NULL, radeon_vga_set_decode);
-	vga_switcheroo_register_client(rdev->pdev, &radeon_switcheroo_ops);
+	vga_switcheroo_register_client(rdev->pdev, &radeon_switcheroo_ops, false);
 
 	r = radeon_init(rdev);
 	if (r)
@@ -1297,13 +1320,22 @@ int radeon_device_init(struct radeon_device *rdev,
 			return r;
 	}
 	if ((radeon_testing & 1)) {
-		radeon_test_moves(rdev);
+		if (rdev->accel_working)
+			radeon_test_moves(rdev);
+		else
+			DRM_INFO("radeon: acceleration disabled, skipping move tests\n");
 	}
 	if ((radeon_testing & 2)) {
-		radeon_test_syncing(rdev);
+		if (rdev->accel_working)
+			radeon_test_syncing(rdev);
+		else
+			DRM_INFO("radeon: acceleration disabled, skipping sync tests\n");
 	}
 	if (radeon_benchmarking) {
-		radeon_benchmark(rdev, radeon_benchmarking);
+		if (rdev->accel_working)
+			radeon_benchmark(rdev, radeon_benchmarking);
+		else
+			DRM_INFO("radeon: acceleration disabled, skipping benchmarks\n");
 	}
 	return 0;
 }
diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c
index c2b67b4e1ac2..0d1aa050d41d 100644
--- a/drivers/gpu/drm/radeon/radeon_display.c
+++ b/drivers/gpu/drm/radeon/radeon_display.c
@@ -345,7 +345,8 @@ void radeon_crtc_handle_flip(struct radeon_device *rdev, int crtc_id)
 
 static int radeon_crtc_page_flip(struct drm_crtc *crtc,
 				 struct drm_framebuffer *fb,
-				 struct drm_pending_vblank_event *event)
+				 struct drm_pending_vblank_event *event,
+				 uint32_t page_flip_flags)
 {
 	struct drm_device *dev = crtc->dev;
 	struct radeon_device *rdev = dev->dev_private;
@@ -1171,6 +1172,12 @@ static struct drm_prop_enum_list radeon_underscan_enum_list[] =
 	{ UNDERSCAN_AUTO, "auto" },
 };
 
+static struct drm_prop_enum_list radeon_audio_enum_list[] =
+{	{ RADEON_AUDIO_DISABLE, "off" },
+	{ RADEON_AUDIO_ENABLE, "on" },
+	{ RADEON_AUDIO_AUTO, "auto" },
+};
+
 static int radeon_modeset_create_props(struct radeon_device *rdev)
 {
 	int sz;
@@ -1221,6 +1228,12 @@ static int radeon_modeset_create_props(struct radeon_device *rdev)
 	if (!rdev->mode_info.underscan_vborder_property)
 		return -ENOMEM;
 
+	sz = ARRAY_SIZE(radeon_audio_enum_list);
+	rdev->mode_info.audio_property =
+		drm_property_create_enum(rdev->ddev, 0,
+					 "audio",
+					 radeon_audio_enum_list, sz);
+
 	return 0;
 }
 
@@ -1254,41 +1267,41 @@ static void radeon_afmt_init(struct radeon_device *rdev)
 	for (i = 0; i < RADEON_MAX_AFMT_BLOCKS; i++)
 		rdev->mode_info.afmt[i] = NULL;
 
-	if (ASIC_IS_DCE6(rdev)) {
-		/* todo */
+	if (ASIC_IS_NODCE(rdev)) {
+		/* nothing to do */
 	} else if (ASIC_IS_DCE4(rdev)) {
+		static uint32_t eg_offsets[] = {
+			EVERGREEN_CRTC0_REGISTER_OFFSET,
+			EVERGREEN_CRTC1_REGISTER_OFFSET,
+			EVERGREEN_CRTC2_REGISTER_OFFSET,
+			EVERGREEN_CRTC3_REGISTER_OFFSET,
+			EVERGREEN_CRTC4_REGISTER_OFFSET,
+			EVERGREEN_CRTC5_REGISTER_OFFSET,
+			0x13830 - 0x7030,
+		};
+		int num_afmt;
+
+		/* DCE8 has 7 audio blocks tied to DIG encoders */
+		/* DCE6 has 6 audio blocks tied to DIG encoders */
 		/* DCE4/5 has 6 audio blocks tied to DIG encoders */
 		/* DCE4.1 has 2 audio blocks tied to DIG encoders */
-		rdev->mode_info.afmt[0] = kzalloc(sizeof(struct radeon_afmt), GFP_KERNEL);
-		if (rdev->mode_info.afmt[0]) {
-			rdev->mode_info.afmt[0]->offset = EVERGREEN_CRTC0_REGISTER_OFFSET;
-			rdev->mode_info.afmt[0]->id = 0;
-		}
-		rdev->mode_info.afmt[1] = kzalloc(sizeof(struct radeon_afmt), GFP_KERNEL);
-		if (rdev->mode_info.afmt[1]) {
-			rdev->mode_info.afmt[1]->offset = EVERGREEN_CRTC1_REGISTER_OFFSET;
-			rdev->mode_info.afmt[1]->id = 1;
-		}
-		if (!ASIC_IS_DCE41(rdev)) {
-			rdev->mode_info.afmt[2] = kzalloc(sizeof(struct radeon_afmt), GFP_KERNEL);
-			if (rdev->mode_info.afmt[2]) {
-				rdev->mode_info.afmt[2]->offset = EVERGREEN_CRTC2_REGISTER_OFFSET;
-				rdev->mode_info.afmt[2]->id = 2;
-			}
-			rdev->mode_info.afmt[3] = kzalloc(sizeof(struct radeon_afmt), GFP_KERNEL);
-			if (rdev->mode_info.afmt[3]) {
-				rdev->mode_info.afmt[3]->offset = EVERGREEN_CRTC3_REGISTER_OFFSET;
-				rdev->mode_info.afmt[3]->id = 3;
-			}
-			rdev->mode_info.afmt[4] = kzalloc(sizeof(struct radeon_afmt), GFP_KERNEL);
-			if (rdev->mode_info.afmt[4]) {
-				rdev->mode_info.afmt[4]->offset = EVERGREEN_CRTC4_REGISTER_OFFSET;
-				rdev->mode_info.afmt[4]->id = 4;
-			}
-			rdev->mode_info.afmt[5] = kzalloc(sizeof(struct radeon_afmt), GFP_KERNEL);
-			if (rdev->mode_info.afmt[5]) {
-				rdev->mode_info.afmt[5]->offset = EVERGREEN_CRTC5_REGISTER_OFFSET;
-				rdev->mode_info.afmt[5]->id = 5;
+		if (ASIC_IS_DCE8(rdev))
+			num_afmt = 7;
+		else if (ASIC_IS_DCE6(rdev))
+			num_afmt = 6;
+		else if (ASIC_IS_DCE5(rdev))
+			num_afmt = 6;
+		else if (ASIC_IS_DCE41(rdev))
+			num_afmt = 2;
+		else /* DCE4 */
+			num_afmt = 6;
+
+		BUG_ON(num_afmt > ARRAY_SIZE(eg_offsets));
+		for (i = 0; i < num_afmt; i++) {
+			rdev->mode_info.afmt[i] = kzalloc(sizeof(struct radeon_afmt), GFP_KERNEL);
+			if (rdev->mode_info.afmt[i]) {
+				rdev->mode_info.afmt[i]->offset = eg_offsets[i];
+				rdev->mode_info.afmt[i]->id = i;
 			}
 		}
 	} else if (ASIC_IS_DCE3(rdev)) {
diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c
index 29876b1be8ec..cdd12dcd988b 100644
--- a/drivers/gpu/drm/radeon/radeon_drv.c
+++ b/drivers/gpu/drm/radeon/radeon_drv.c
@@ -81,7 +81,6 @@
 #define KMS_DRIVER_PATCHLEVEL	0
 int radeon_driver_load_kms(struct drm_device *dev, unsigned long flags);
 int radeon_driver_unload_kms(struct drm_device *dev);
-int radeon_driver_firstopen_kms(struct drm_device *dev);
 void radeon_driver_lastclose_kms(struct drm_device *dev);
 int radeon_driver_open_kms(struct drm_device *dev, struct drm_file *file_priv);
 void radeon_driver_postclose_kms(struct drm_device *dev,
@@ -101,8 +100,6 @@ void radeon_driver_irq_preinstall_kms(struct drm_device *dev);
 int radeon_driver_irq_postinstall_kms(struct drm_device *dev);
 void radeon_driver_irq_uninstall_kms(struct drm_device *dev);
 irqreturn_t radeon_driver_irq_handler_kms(DRM_IRQ_ARGS);
-int radeon_dma_ioctl_kms(struct drm_device *dev, void *data,
-			 struct drm_file *file_priv);
 int radeon_gem_object_init(struct drm_gem_object *obj);
 void radeon_gem_object_free(struct drm_gem_object *obj);
 int radeon_gem_object_open(struct drm_gem_object *obj,
@@ -111,7 +108,7 @@ void radeon_gem_object_close(struct drm_gem_object *obj,
 				struct drm_file *file_priv);
 extern int radeon_get_crtc_scanoutpos(struct drm_device *dev, int crtc,
 				      int *vpos, int *hpos);
-extern struct drm_ioctl_desc radeon_ioctls_kms[];
+extern const struct drm_ioctl_desc radeon_ioctls_kms[];
 extern int radeon_max_kms_ioctl;
 int radeon_mmap(struct file *filp, struct vm_area_struct *vma);
 int radeon_mode_dumb_mmap(struct drm_file *filp,
@@ -120,9 +117,6 @@ int radeon_mode_dumb_mmap(struct drm_file *filp,
 int radeon_mode_dumb_create(struct drm_file *file_priv,
 			    struct drm_device *dev,
 			    struct drm_mode_create_dumb *args);
-int radeon_mode_dumb_destroy(struct drm_file *file_priv,
-			     struct drm_device *dev,
-			     uint32_t handle);
 struct sg_table *radeon_gem_prime_get_sg_table(struct drm_gem_object *obj);
 struct drm_gem_object *radeon_gem_prime_import_sg_table(struct drm_device *dev,
 							size_t size,
@@ -154,12 +148,12 @@ int radeon_dynclks = -1;
 int radeon_r4xx_atom = 0;
 int radeon_agpmode = 0;
 int radeon_vram_limit = 0;
-int radeon_gart_size = 512; /* default gart size */
+int radeon_gart_size = -1; /* auto */
 int radeon_benchmarking = 0;
 int radeon_testing = 0;
 int radeon_connector_table = 0;
 int radeon_tv = 1;
-int radeon_audio = 0;
+int radeon_audio = 1;
 int radeon_disp_priority = 0;
 int radeon_hw_i2c = 0;
 int radeon_pcie_gen2 = -1;
@@ -187,7 +181,7 @@ module_param_named(vramlimit, radeon_vram_limit, int, 0600);
 MODULE_PARM_DESC(agpmode, "AGP Mode (-1 == PCI)");
 module_param_named(agpmode, radeon_agpmode, int, 0444);
 
-MODULE_PARM_DESC(gartsize, "Size of PCIE/IGP gart to setup in megabytes (32, 64, etc)");
+MODULE_PARM_DESC(gartsize, "Size of PCIE/IGP gart to setup in megabytes (32, 64, etc., -1 = auto)");
 module_param_named(gartsize, radeon_gart_size, int, 0600);
 
 MODULE_PARM_DESC(benchmark, "Run benchmark");
@@ -272,7 +266,6 @@ static const struct file_operations radeon_driver_old_fops = {
 	.unlocked_ioctl = drm_ioctl,
 	.mmap = drm_mmap,
 	.poll = drm_poll,
-	.fasync = drm_fasync,
 	.read = drm_read,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl = radeon_compat_ioctl,
@@ -282,7 +275,7 @@ static const struct file_operations radeon_driver_old_fops = {
 
 static struct drm_driver driver_old = {
 	.driver_features =
-	    DRIVER_USE_AGP | DRIVER_USE_MTRR | DRIVER_PCI_DMA | DRIVER_SG |
+	    DRIVER_USE_AGP | DRIVER_PCI_DMA | DRIVER_SG |
 	    DRIVER_HAVE_IRQ | DRIVER_HAVE_DMA | DRIVER_IRQ_SHARED,
 	.dev_priv_size = sizeof(drm_radeon_buf_priv_t),
 	.load = radeon_driver_load,
@@ -381,7 +374,6 @@ static const struct file_operations radeon_driver_kms_fops = {
 	.unlocked_ioctl = drm_ioctl,
 	.mmap = radeon_mmap,
 	.poll = drm_poll,
-	.fasync = drm_fasync,
 	.read = drm_read,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl = radeon_kms_compat_ioctl,
@@ -390,12 +382,11 @@ static const struct file_operations radeon_driver_kms_fops = {
 
 static struct drm_driver kms_driver = {
 	.driver_features =
-	    DRIVER_USE_AGP | DRIVER_USE_MTRR | DRIVER_PCI_DMA | DRIVER_SG |
-	    DRIVER_HAVE_IRQ | DRIVER_HAVE_DMA | DRIVER_IRQ_SHARED | DRIVER_GEM |
-	    DRIVER_PRIME,
+	    DRIVER_USE_AGP |
+	    DRIVER_HAVE_IRQ | DRIVER_IRQ_SHARED | DRIVER_GEM |
+	    DRIVER_PRIME | DRIVER_RENDER,
 	.dev_priv_size = 0,
 	.load = radeon_driver_load_kms,
-	.firstopen = radeon_driver_firstopen_kms,
 	.open = radeon_driver_open_kms,
 	.preclose = radeon_driver_preclose_kms,
 	.postclose = radeon_driver_postclose_kms,
@@ -421,10 +412,9 @@ static struct drm_driver kms_driver = {
 	.gem_free_object = radeon_gem_object_free,
 	.gem_open_object = radeon_gem_object_open,
 	.gem_close_object = radeon_gem_object_close,
-	.dma_ioctl = radeon_dma_ioctl_kms,
 	.dumb_create = radeon_mode_dumb_create,
 	.dumb_map_offset = radeon_mode_dumb_mmap,
-	.dumb_destroy = radeon_mode_dumb_destroy,
+	.dumb_destroy = drm_gem_dumb_destroy,
 	.fops = &radeon_driver_kms_fops,
 
 	.prime_handle_to_fd = drm_gem_prime_handle_to_fd,
diff --git a/drivers/gpu/drm/radeon/radeon_gem.c b/drivers/gpu/drm/radeon/radeon_gem.c
index aa796031ab65..dce99c8a5835 100644
--- a/drivers/gpu/drm/radeon/radeon_gem.c
+++ b/drivers/gpu/drm/radeon/radeon_gem.c
@@ -570,13 +570,6 @@ int radeon_mode_dumb_create(struct drm_file *file_priv,
 	return 0;
 }
 
-int radeon_mode_dumb_destroy(struct drm_file *file_priv,
-			     struct drm_device *dev,
-			     uint32_t handle)
-{
-	return drm_gem_handle_delete(file_priv, handle);
-}
-
 #if defined(CONFIG_DEBUG_FS)
 static int radeon_debugfs_gem_info(struct seq_file *m, void *data)
 {
diff --git a/drivers/gpu/drm/radeon/radeon_irq_kms.c b/drivers/gpu/drm/radeon/radeon_irq_kms.c
index 081886b0642d..cc9e8482cf30 100644
--- a/drivers/gpu/drm/radeon/radeon_irq_kms.c
+++ b/drivers/gpu/drm/radeon/radeon_irq_kms.c
@@ -275,17 +275,19 @@ int radeon_irq_kms_init(struct radeon_device *rdev)
 			dev_info(rdev->dev, "radeon: using MSI.\n");
 		}
 	}
+
+	INIT_WORK(&rdev->hotplug_work, radeon_hotplug_work_func);
+	INIT_WORK(&rdev->audio_work, r600_audio_update_hdmi);
+	INIT_WORK(&rdev->reset_work, radeon_irq_reset_work_func);
+
 	rdev->irq.installed = true;
 	r = drm_irq_install(rdev->ddev);
 	if (r) {
 		rdev->irq.installed = false;
+		flush_work(&rdev->hotplug_work);
 		return r;
 	}
 
-	INIT_WORK(&rdev->hotplug_work, radeon_hotplug_work_func);
-	INIT_WORK(&rdev->audio_work, r600_audio_update_hdmi);
-	INIT_WORK(&rdev->reset_work, radeon_irq_reset_work_func);
-
 	DRM_INFO("radeon: irq initialized.\n");
 	return 0;
 }
diff --git a/drivers/gpu/drm/radeon/radeon_kms.c b/drivers/gpu/drm/radeon/radeon_kms.c
index 49ff3d1a6102..61580ddc4eb2 100644
--- a/drivers/gpu/drm/radeon/radeon_kms.c
+++ b/drivers/gpu/drm/radeon/radeon_kms.c
@@ -433,6 +433,9 @@ int radeon_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 			return -EINVAL;
 		}
 		break;
+	case RADEON_INFO_SI_CP_DMA_COMPUTE:
+		*value = 1;
+		break;
 	default:
 		DRM_DEBUG_KMS("Invalid request %d\n", info->request);
 		return -EINVAL;
@@ -449,19 +452,6 @@ int radeon_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
  * Outdated mess for old drm with Xorg being in charge (void function now).
  */
 /**
- * radeon_driver_firstopen_kms - drm callback for first open
- *
- * @dev: drm dev pointer
- *
- * Nothing to be done for KMS (all asics).
- * Returns 0 on success.
- */
-int radeon_driver_firstopen_kms(struct drm_device *dev)
-{
-	return 0;
-}
-
-/**
  * radeon_driver_firstopen_kms - drm callback for last close
  *
  * @dev: drm dev pointer
@@ -683,16 +673,6 @@ int radeon_get_vblank_timestamp_kms(struct drm_device *dev, int crtc,
 						     drmcrtc);
 }
 
-/*
- * IOCTL.
- */
-int radeon_dma_ioctl_kms(struct drm_device *dev, void *data,
-			 struct drm_file *file_priv)
-{
-	/* Not valid in KMS. */
-	return -EINVAL;
-}
-
 #define KMS_INVALID_IOCTL(name)						\
 int name(struct drm_device *dev, void *data, struct drm_file *file_priv)\
 {									\
@@ -732,7 +712,7 @@ KMS_INVALID_IOCTL(radeon_surface_alloc_kms)
 KMS_INVALID_IOCTL(radeon_surface_free_kms)
 
 
-struct drm_ioctl_desc radeon_ioctls_kms[] = {
+const struct drm_ioctl_desc radeon_ioctls_kms[] = {
 	DRM_IOCTL_DEF_DRV(RADEON_CP_INIT, radeon_cp_init_kms, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
 	DRM_IOCTL_DEF_DRV(RADEON_CP_START, radeon_cp_start_kms, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
 	DRM_IOCTL_DEF_DRV(RADEON_CP_STOP, radeon_cp_stop_kms, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
@@ -761,18 +741,18 @@ struct drm_ioctl_desc radeon_ioctls_kms[] = {
 	DRM_IOCTL_DEF_DRV(RADEON_SURF_ALLOC, radeon_surface_alloc_kms, DRM_AUTH),
 	DRM_IOCTL_DEF_DRV(RADEON_SURF_FREE, radeon_surface_free_kms, DRM_AUTH),
 	/* KMS */
-	DRM_IOCTL_DEF_DRV(RADEON_GEM_INFO, radeon_gem_info_ioctl, DRM_AUTH|DRM_UNLOCKED),
-	DRM_IOCTL_DEF_DRV(RADEON_GEM_CREATE, radeon_gem_create_ioctl, DRM_AUTH|DRM_UNLOCKED),
-	DRM_IOCTL_DEF_DRV(RADEON_GEM_MMAP, radeon_gem_mmap_ioctl, DRM_AUTH|DRM_UNLOCKED),
-	DRM_IOCTL_DEF_DRV(RADEON_GEM_SET_DOMAIN, radeon_gem_set_domain_ioctl, DRM_AUTH|DRM_UNLOCKED),
+	DRM_IOCTL_DEF_DRV(RADEON_GEM_INFO, radeon_gem_info_ioctl, DRM_AUTH|DRM_UNLOCKED|DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(RADEON_GEM_CREATE, radeon_gem_create_ioctl, DRM_AUTH|DRM_UNLOCKED|DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(RADEON_GEM_MMAP, radeon_gem_mmap_ioctl, DRM_AUTH|DRM_UNLOCKED|DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(RADEON_GEM_SET_DOMAIN, radeon_gem_set_domain_ioctl, DRM_AUTH|DRM_UNLOCKED|DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(RADEON_GEM_PREAD, radeon_gem_pread_ioctl, DRM_AUTH|DRM_UNLOCKED),
 	DRM_IOCTL_DEF_DRV(RADEON_GEM_PWRITE, radeon_gem_pwrite_ioctl, DRM_AUTH|DRM_UNLOCKED),
-	DRM_IOCTL_DEF_DRV(RADEON_GEM_WAIT_IDLE, radeon_gem_wait_idle_ioctl, DRM_AUTH|DRM_UNLOCKED),
-	DRM_IOCTL_DEF_DRV(RADEON_CS, radeon_cs_ioctl, DRM_AUTH|DRM_UNLOCKED),
-	DRM_IOCTL_DEF_DRV(RADEON_INFO, radeon_info_ioctl, DRM_AUTH|DRM_UNLOCKED),
-	DRM_IOCTL_DEF_DRV(RADEON_GEM_SET_TILING, radeon_gem_set_tiling_ioctl, DRM_AUTH|DRM_UNLOCKED),
-	DRM_IOCTL_DEF_DRV(RADEON_GEM_GET_TILING, radeon_gem_get_tiling_ioctl, DRM_AUTH|DRM_UNLOCKED),
-	DRM_IOCTL_DEF_DRV(RADEON_GEM_BUSY, radeon_gem_busy_ioctl, DRM_AUTH|DRM_UNLOCKED),
-	DRM_IOCTL_DEF_DRV(RADEON_GEM_VA, radeon_gem_va_ioctl, DRM_AUTH|DRM_UNLOCKED),
+	DRM_IOCTL_DEF_DRV(RADEON_GEM_WAIT_IDLE, radeon_gem_wait_idle_ioctl, DRM_AUTH|DRM_UNLOCKED|DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(RADEON_CS, radeon_cs_ioctl, DRM_AUTH|DRM_UNLOCKED|DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(RADEON_INFO, radeon_info_ioctl, DRM_AUTH|DRM_UNLOCKED|DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(RADEON_GEM_SET_TILING, radeon_gem_set_tiling_ioctl, DRM_AUTH|DRM_UNLOCKED|DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(RADEON_GEM_GET_TILING, radeon_gem_get_tiling_ioctl, DRM_AUTH|DRM_UNLOCKED|DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(RADEON_GEM_BUSY, radeon_gem_busy_ioctl, DRM_AUTH|DRM_UNLOCKED|DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(RADEON_GEM_VA, radeon_gem_va_ioctl, DRM_AUTH|DRM_UNLOCKED|DRM_RENDER_ALLOW),
 };
 int radeon_max_kms_ioctl = DRM_ARRAY_SIZE(radeon_ioctls_kms);
diff --git a/drivers/gpu/drm/radeon/radeon_mode.h b/drivers/gpu/drm/radeon/radeon_mode.h
index 8296632a4235..ef63d3f00b2f 100644
--- a/drivers/gpu/drm/radeon/radeon_mode.h
+++ b/drivers/gpu/drm/radeon/radeon_mode.h
@@ -225,6 +225,7 @@ struct radeon_afmt {
 	int offset;
 	bool last_buffer_filled_status;
 	int id;
+	struct r600_audio_pin *pin;
 };
 
 struct radeon_mode_info {
@@ -233,7 +234,7 @@ struct radeon_mode_info {
 	enum radeon_connector_table connector_table;
 	bool mode_config_initialized;
 	struct radeon_crtc *crtcs[6];
-	struct radeon_afmt *afmt[6];
+	struct radeon_afmt *afmt[7];
 	/* DVI-I properties */
 	struct drm_property *coherent_mode_property;
 	/* DAC enable load detect */
@@ -246,6 +247,8 @@ struct radeon_mode_info {
 	struct drm_property *underscan_property;
 	struct drm_property *underscan_hborder_property;
 	struct drm_property *underscan_vborder_property;
+	/* audio */
+	struct drm_property *audio_property;
 	/* hardcoded DFP edid from BIOS */
 	struct edid *bios_hardcoded_edid;
 	int bios_hardcoded_edid_size;
@@ -470,6 +473,12 @@ struct radeon_router {
 	u8 cd_mux_state;
 };
 
+enum radeon_connector_audio {
+	RADEON_AUDIO_DISABLE = 0,
+	RADEON_AUDIO_ENABLE = 1,
+	RADEON_AUDIO_AUTO = 2
+};
+
 struct radeon_connector {
 	struct drm_connector base;
 	uint32_t connector_id;
@@ -488,6 +497,7 @@ struct radeon_connector {
 	struct radeon_hpd hpd;
 	struct radeon_router router;
 	struct radeon_i2c_chan *router_bus;
+	enum radeon_connector_audio audio;
 };
 
 struct radeon_framebuffer {
diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c
index 2020bf4a3830..c0fa4aa9ceea 100644
--- a/drivers/gpu/drm/radeon/radeon_object.c
+++ b/drivers/gpu/drm/radeon/radeon_object.c
@@ -142,7 +142,6 @@ int radeon_bo_create(struct radeon_device *rdev,
 		return r;
 	}
 	bo->rdev = rdev;
-	bo->gem_base.driver_private = NULL;
 	bo->surface_reg = -1;
 	INIT_LIST_HEAD(&bo->list);
 	INIT_LIST_HEAD(&bo->va);
diff --git a/drivers/gpu/drm/radeon/radeon_object.h b/drivers/gpu/drm/radeon/radeon_object.h
index 49c82c480013..209b11150263 100644
--- a/drivers/gpu/drm/radeon/radeon_object.h
+++ b/drivers/gpu/drm/radeon/radeon_object.h
@@ -113,13 +113,10 @@ static inline unsigned radeon_bo_gpu_page_alignment(struct radeon_bo *bo)
  * @bo:	radeon object for which we query the offset
  *
  * Returns mmap offset of the object.
- *
- * Note: addr_space_offset is constant after ttm bo init thus isn't protected
- * by any lock.
  */
 static inline u64 radeon_bo_mmap_offset(struct radeon_bo *bo)
 {
-	return bo->tbo.addr_space_offset;
+	return drm_vma_node_offset_addr(&bo->tbo.vma_node);
 }
 
 extern int radeon_bo_wait(struct radeon_bo *bo, u32 *mem_type,
diff --git a/drivers/gpu/drm/radeon/radeon_pm.c b/drivers/gpu/drm/radeon/radeon_pm.c
index c557850cd345..4f6b7fc7ad3c 100644
--- a/drivers/gpu/drm/radeon/radeon_pm.c
+++ b/drivers/gpu/drm/radeon/radeon_pm.c
@@ -67,7 +67,16 @@ int radeon_pm_get_type_index(struct radeon_device *rdev,
 
 void radeon_pm_acpi_event_handler(struct radeon_device *rdev)
 {
-	if (rdev->pm.pm_method == PM_METHOD_PROFILE) {
+	if ((rdev->pm.pm_method == PM_METHOD_DPM) && rdev->pm.dpm_enabled) {
+		mutex_lock(&rdev->pm.mutex);
+		if (power_supply_is_system_supplied() > 0)
+			rdev->pm.dpm.ac_power = true;
+		else
+			rdev->pm.dpm.ac_power = false;
+		if (rdev->asic->dpm.enable_bapm)
+			radeon_dpm_enable_bapm(rdev, rdev->pm.dpm.ac_power);
+		mutex_unlock(&rdev->pm.mutex);
+        } else if (rdev->pm.pm_method == PM_METHOD_PROFILE) {
 		if (rdev->pm.profile == PM_PROFILE_AUTO) {
 			mutex_lock(&rdev->pm.mutex);
 			radeon_pm_update_profile(rdev);
@@ -333,7 +342,7 @@ static ssize_t radeon_get_pm_profile(struct device *dev,
 				     struct device_attribute *attr,
 				     char *buf)
 {
-	struct drm_device *ddev = pci_get_drvdata(to_pci_dev(dev));
+	struct drm_device *ddev = dev_get_drvdata(dev);
 	struct radeon_device *rdev = ddev->dev_private;
 	int cp = rdev->pm.profile;
 
@@ -349,7 +358,7 @@ static ssize_t radeon_set_pm_profile(struct device *dev,
 				     const char *buf,
 				     size_t count)
 {
-	struct drm_device *ddev = pci_get_drvdata(to_pci_dev(dev));
+	struct drm_device *ddev = dev_get_drvdata(dev);
 	struct radeon_device *rdev = ddev->dev_private;
 
 	mutex_lock(&rdev->pm.mutex);
@@ -383,7 +392,7 @@ static ssize_t radeon_get_pm_method(struct device *dev,
 				    struct device_attribute *attr,
 				    char *buf)
 {
-	struct drm_device *ddev = pci_get_drvdata(to_pci_dev(dev));
+	struct drm_device *ddev = dev_get_drvdata(dev);
 	struct radeon_device *rdev = ddev->dev_private;
 	int pm = rdev->pm.pm_method;
 
@@ -397,7 +406,7 @@ static ssize_t radeon_set_pm_method(struct device *dev,
 				    const char *buf,
 				    size_t count)
 {
-	struct drm_device *ddev = pci_get_drvdata(to_pci_dev(dev));
+	struct drm_device *ddev = dev_get_drvdata(dev);
 	struct radeon_device *rdev = ddev->dev_private;
 
 	/* we don't support the legacy modes with dpm */
@@ -433,7 +442,7 @@ static ssize_t radeon_get_dpm_state(struct device *dev,
 				    struct device_attribute *attr,
 				    char *buf)
 {
-	struct drm_device *ddev = pci_get_drvdata(to_pci_dev(dev));
+	struct drm_device *ddev = dev_get_drvdata(dev);
 	struct radeon_device *rdev = ddev->dev_private;
 	enum radeon_pm_state_type pm = rdev->pm.dpm.user_state;
 
@@ -447,7 +456,7 @@ static ssize_t radeon_set_dpm_state(struct device *dev,
 				    const char *buf,
 				    size_t count)
 {
-	struct drm_device *ddev = pci_get_drvdata(to_pci_dev(dev));
+	struct drm_device *ddev = dev_get_drvdata(dev);
 	struct radeon_device *rdev = ddev->dev_private;
 
 	mutex_lock(&rdev->pm.mutex);
@@ -472,7 +481,7 @@ static ssize_t radeon_get_dpm_forced_performance_level(struct device *dev,
 						       struct device_attribute *attr,
 						       char *buf)
 {
-	struct drm_device *ddev = pci_get_drvdata(to_pci_dev(dev));
+	struct drm_device *ddev = dev_get_drvdata(dev);
 	struct radeon_device *rdev = ddev->dev_private;
 	enum radeon_dpm_forced_level level = rdev->pm.dpm.forced_level;
 
@@ -486,7 +495,7 @@ static ssize_t radeon_set_dpm_forced_performance_level(struct device *dev,
 						       const char *buf,
 						       size_t count)
 {
-	struct drm_device *ddev = pci_get_drvdata(to_pci_dev(dev));
+	struct drm_device *ddev = dev_get_drvdata(dev);
 	struct radeon_device *rdev = ddev->dev_private;
 	enum radeon_dpm_forced_level level;
 	int ret = 0;
@@ -524,7 +533,7 @@ static ssize_t radeon_hwmon_show_temp(struct device *dev,
 				      struct device_attribute *attr,
 				      char *buf)
 {
-	struct drm_device *ddev = pci_get_drvdata(to_pci_dev(dev));
+	struct drm_device *ddev = dev_get_drvdata(dev);
 	struct radeon_device *rdev = ddev->dev_private;
 	int temp;
 
@@ -536,6 +545,23 @@ static ssize_t radeon_hwmon_show_temp(struct device *dev,
 	return snprintf(buf, PAGE_SIZE, "%d\n", temp);
 }
 
+static ssize_t radeon_hwmon_show_temp_thresh(struct device *dev,
+					     struct device_attribute *attr,
+					     char *buf)
+{
+	struct drm_device *ddev = dev_get_drvdata(dev);
+	struct radeon_device *rdev = ddev->dev_private;
+	int hyst = to_sensor_dev_attr(attr)->index;
+	int temp;
+
+	if (hyst)
+		temp = rdev->pm.dpm.thermal.min_temp;
+	else
+		temp = rdev->pm.dpm.thermal.max_temp;
+
+	return snprintf(buf, PAGE_SIZE, "%d\n", temp);
+}
+
 static ssize_t radeon_hwmon_show_name(struct device *dev,
 				      struct device_attribute *attr,
 				      char *buf)
@@ -544,16 +570,37 @@ static ssize_t radeon_hwmon_show_name(struct device *dev,
 }
 
 static SENSOR_DEVICE_ATTR(temp1_input, S_IRUGO, radeon_hwmon_show_temp, NULL, 0);
+static SENSOR_DEVICE_ATTR(temp1_crit, S_IRUGO, radeon_hwmon_show_temp_thresh, NULL, 0);
+static SENSOR_DEVICE_ATTR(temp1_crit_hyst, S_IRUGO, radeon_hwmon_show_temp_thresh, NULL, 1);
 static SENSOR_DEVICE_ATTR(name, S_IRUGO, radeon_hwmon_show_name, NULL, 0);
 
 static struct attribute *hwmon_attributes[] = {
 	&sensor_dev_attr_temp1_input.dev_attr.attr,
+	&sensor_dev_attr_temp1_crit.dev_attr.attr,
+	&sensor_dev_attr_temp1_crit_hyst.dev_attr.attr,
 	&sensor_dev_attr_name.dev_attr.attr,
 	NULL
 };
 
+static umode_t hwmon_attributes_visible(struct kobject *kobj,
+					struct attribute *attr, int index)
+{
+	struct device *dev = container_of(kobj, struct device, kobj);
+	struct drm_device *ddev = dev_get_drvdata(dev);
+	struct radeon_device *rdev = ddev->dev_private;
+
+	/* Skip limit attributes if DPM is not enabled */
+	if (rdev->pm.pm_method != PM_METHOD_DPM &&
+	    (attr == &sensor_dev_attr_temp1_crit.dev_attr.attr ||
+	     attr == &sensor_dev_attr_temp1_crit_hyst.dev_attr.attr))
+		return 0;
+
+	return attr->mode;
+}
+
 static const struct attribute_group hwmon_attrgroup = {
 	.attrs = hwmon_attributes,
+	.is_visible = hwmon_attributes_visible,
 };
 
 static int radeon_hwmon_init(struct radeon_device *rdev)
@@ -569,6 +616,8 @@ static int radeon_hwmon_init(struct radeon_device *rdev)
 	case THERMAL_TYPE_NI:
 	case THERMAL_TYPE_SUMO:
 	case THERMAL_TYPE_SI:
+	case THERMAL_TYPE_CI:
+	case THERMAL_TYPE_KV:
 		if (rdev->asic->pm.get_temperature == NULL)
 			return err;
 		rdev->pm.int_hwmon_dev = hwmon_device_register(rdev->dev);
@@ -624,7 +673,15 @@ static void radeon_dpm_thermal_work_handler(struct work_struct *work)
 			/* switch back the user state */
 			dpm_state = rdev->pm.dpm.user_state;
 	}
-	radeon_dpm_enable_power_state(rdev, dpm_state);
+	mutex_lock(&rdev->pm.mutex);
+	if (dpm_state == POWER_STATE_TYPE_INTERNAL_THERMAL)
+		rdev->pm.dpm.thermal_active = true;
+	else
+		rdev->pm.dpm.thermal_active = false;
+	rdev->pm.dpm.state = dpm_state;
+	mutex_unlock(&rdev->pm.mutex);
+
+	radeon_pm_compute_clocks(rdev);
 }
 
 static struct radeon_ps *radeon_dpm_pick_power_state(struct radeon_device *rdev,
@@ -687,7 +744,10 @@ restart_search:
 			break;
 		/* internal states */
 		case POWER_STATE_TYPE_INTERNAL_UVD:
-			return rdev->pm.dpm.uvd_ps;
+			if (rdev->pm.dpm.uvd_ps)
+				return rdev->pm.dpm.uvd_ps;
+			else
+				break;
 		case POWER_STATE_TYPE_INTERNAL_UVD_SD:
 			if (ps->class & ATOM_PPLIB_CLASSIFICATION_SDSTATE)
 				return ps;
@@ -729,10 +789,17 @@ restart_search:
 	/* use a fallback state if we didn't match */
 	switch (dpm_state) {
 	case POWER_STATE_TYPE_INTERNAL_UVD_SD:
+		dpm_state = POWER_STATE_TYPE_INTERNAL_UVD_HD;
+		goto restart_search;
 	case POWER_STATE_TYPE_INTERNAL_UVD_HD:
 	case POWER_STATE_TYPE_INTERNAL_UVD_HD2:
 	case POWER_STATE_TYPE_INTERNAL_UVD_MVC:
-		return rdev->pm.dpm.uvd_ps;
+		if (rdev->pm.dpm.uvd_ps) {
+			return rdev->pm.dpm.uvd_ps;
+		} else {
+			dpm_state = POWER_STATE_TYPE_PERFORMANCE;
+			goto restart_search;
+		}
 	case POWER_STATE_TYPE_INTERNAL_THERMAL:
 		dpm_state = POWER_STATE_TYPE_INTERNAL_ACPI;
 		goto restart_search;
@@ -850,38 +917,57 @@ static void radeon_dpm_change_power_state_locked(struct radeon_device *rdev)
 
 	radeon_dpm_post_set_power_state(rdev);
 
+	if (rdev->asic->dpm.force_performance_level) {
+		if (rdev->pm.dpm.thermal_active)
+			/* force low perf level for thermal */
+			radeon_dpm_force_performance_level(rdev, RADEON_DPM_FORCED_LEVEL_LOW);
+		else
+			/* otherwise, enable auto */
+			radeon_dpm_force_performance_level(rdev, RADEON_DPM_FORCED_LEVEL_AUTO);
+	}
+
 done:
 	mutex_unlock(&rdev->ring_lock);
 	up_write(&rdev->pm.mclk_lock);
 	mutex_unlock(&rdev->ddev->struct_mutex);
 }
 
-void radeon_dpm_enable_power_state(struct radeon_device *rdev,
-				   enum radeon_pm_state_type dpm_state)
+void radeon_dpm_enable_uvd(struct radeon_device *rdev, bool enable)
 {
-	if (!rdev->pm.dpm_enabled)
-		return;
+	enum radeon_pm_state_type dpm_state;
 
-	mutex_lock(&rdev->pm.mutex);
-	switch (dpm_state) {
-	case POWER_STATE_TYPE_INTERNAL_THERMAL:
-		rdev->pm.dpm.thermal_active = true;
-		break;
-	case POWER_STATE_TYPE_INTERNAL_UVD:
-	case POWER_STATE_TYPE_INTERNAL_UVD_SD:
-	case POWER_STATE_TYPE_INTERNAL_UVD_HD:
-	case POWER_STATE_TYPE_INTERNAL_UVD_HD2:
-	case POWER_STATE_TYPE_INTERNAL_UVD_MVC:
-		rdev->pm.dpm.uvd_active = true;
-		break;
-	default:
-		rdev->pm.dpm.thermal_active = false;
-		rdev->pm.dpm.uvd_active = false;
-		break;
+	if (rdev->asic->dpm.powergate_uvd) {
+		mutex_lock(&rdev->pm.mutex);
+		/* enable/disable UVD */
+		radeon_dpm_powergate_uvd(rdev, !enable);
+		mutex_unlock(&rdev->pm.mutex);
+	} else {
+		if (enable) {
+			mutex_lock(&rdev->pm.mutex);
+			rdev->pm.dpm.uvd_active = true;
+			/* disable this for now */
+#if 0
+			if ((rdev->pm.dpm.sd == 1) && (rdev->pm.dpm.hd == 0))
+				dpm_state = POWER_STATE_TYPE_INTERNAL_UVD_SD;
+			else if ((rdev->pm.dpm.sd == 2) && (rdev->pm.dpm.hd == 0))
+				dpm_state = POWER_STATE_TYPE_INTERNAL_UVD_HD;
+			else if ((rdev->pm.dpm.sd == 0) && (rdev->pm.dpm.hd == 1))
+				dpm_state = POWER_STATE_TYPE_INTERNAL_UVD_HD;
+			else if ((rdev->pm.dpm.sd == 0) && (rdev->pm.dpm.hd == 2))
+				dpm_state = POWER_STATE_TYPE_INTERNAL_UVD_HD2;
+			else
+#endif
+				dpm_state = POWER_STATE_TYPE_INTERNAL_UVD;
+			rdev->pm.dpm.state = dpm_state;
+			mutex_unlock(&rdev->pm.mutex);
+		} else {
+			mutex_lock(&rdev->pm.mutex);
+			rdev->pm.dpm.uvd_active = false;
+			mutex_unlock(&rdev->pm.mutex);
+		}
+
+		radeon_pm_compute_clocks(rdev);
 	}
-	rdev->pm.dpm.state = dpm_state;
-	mutex_unlock(&rdev->pm.mutex);
-	radeon_pm_compute_clocks(rdev);
 }
 
 static void radeon_pm_suspend_old(struct radeon_device *rdev)
@@ -919,7 +1005,7 @@ static void radeon_pm_resume_old(struct radeon_device *rdev)
 {
 	/* set up the default clocks if the MC ucode is loaded */
 	if ((rdev->family >= CHIP_BARTS) &&
-	    (rdev->family <= CHIP_HAINAN) &&
+	    (rdev->family <= CHIP_CAYMAN) &&
 	    rdev->mc_fw) {
 		if (rdev->pm.default_vddc)
 			radeon_atom_set_voltage(rdev, rdev->pm.default_vddc,
@@ -963,7 +1049,7 @@ static void radeon_pm_resume_dpm(struct radeon_device *rdev)
 	if (ret) {
 		DRM_ERROR("radeon: dpm resume failed\n");
 		if ((rdev->family >= CHIP_BARTS) &&
-		    (rdev->family <= CHIP_HAINAN) &&
+		    (rdev->family <= CHIP_CAYMAN) &&
 		    rdev->mc_fw) {
 			if (rdev->pm.default_vddc)
 				radeon_atom_set_voltage(rdev, rdev->pm.default_vddc,
@@ -1014,7 +1100,7 @@ static int radeon_pm_init_old(struct radeon_device *rdev)
 		radeon_pm_init_profile(rdev);
 		/* set up the default clocks if the MC ucode is loaded */
 		if ((rdev->family >= CHIP_BARTS) &&
-		    (rdev->family <= CHIP_HAINAN) &&
+		    (rdev->family <= CHIP_CAYMAN) &&
 		    rdev->mc_fw) {
 			if (rdev->pm.default_vddc)
 				radeon_atom_set_voltage(rdev, rdev->pm.default_vddc,
@@ -1069,9 +1155,10 @@ static int radeon_pm_init_dpm(struct radeon_device *rdev)
 {
 	int ret;
 
-	/* default to performance state */
+	/* default to balanced state */
 	rdev->pm.dpm.state = POWER_STATE_TYPE_BALANCED;
 	rdev->pm.dpm.user_state = POWER_STATE_TYPE_BALANCED;
+	rdev->pm.dpm.forced_level = RADEON_DPM_FORCED_LEVEL_AUTO;
 	rdev->pm.default_sclk = rdev->clock.default_sclk;
 	rdev->pm.default_mclk = rdev->clock.default_mclk;
 	rdev->pm.current_sclk = rdev->clock.default_sclk;
@@ -1099,7 +1186,7 @@ static int radeon_pm_init_dpm(struct radeon_device *rdev)
 	if (ret) {
 		rdev->pm.dpm_enabled = false;
 		if ((rdev->family >= CHIP_BARTS) &&
-		    (rdev->family <= CHIP_HAINAN) &&
+		    (rdev->family <= CHIP_CAYMAN) &&
 		    rdev->mc_fw) {
 			if (rdev->pm.default_vddc)
 				radeon_atom_set_voltage(rdev, rdev->pm.default_vddc,
@@ -1176,6 +1263,9 @@ int radeon_pm_init(struct radeon_device *rdev)
 	case CHIP_VERDE:
 	case CHIP_OLAND:
 	case CHIP_HAINAN:
+	case CHIP_BONAIRE:
+	case CHIP_KABINI:
+	case CHIP_KAVERI:
 		/* DPM requires the RLC, RV770+ dGPU requires SMC */
 		if (!rdev->rlc_fw)
 			rdev->pm.pm_method = PM_METHOD_PROFILE;
diff --git a/drivers/gpu/drm/radeon/radeon_prime.c b/drivers/gpu/drm/radeon/radeon_prime.c
index 65b9eabd5a2f..20074560fc25 100644
--- a/drivers/gpu/drm/radeon/radeon_prime.c
+++ b/drivers/gpu/drm/radeon/radeon_prime.c
@@ -68,7 +68,6 @@ struct drm_gem_object *radeon_gem_prime_import_sg_table(struct drm_device *dev,
 			       RADEON_GEM_DOMAIN_GTT, sg, &bo);
 	if (ret)
 		return ERR_PTR(ret);
-	bo->gem_base.driver_private = bo;
 
 	mutex_lock(&rdev->gem.mutex);
 	list_add_tail(&bo->list, &rdev->gem.objects);
diff --git a/drivers/gpu/drm/radeon/radeon_ring.c b/drivers/gpu/drm/radeon/radeon_ring.c
index fb5ea6208970..18254e1c3e71 100644
--- a/drivers/gpu/drm/radeon/radeon_ring.c
+++ b/drivers/gpu/drm/radeon/radeon_ring.c
@@ -363,11 +363,10 @@ u32 radeon_ring_generic_get_rptr(struct radeon_device *rdev,
 {
 	u32 rptr;
 
-	if (rdev->wb.enabled && ring != &rdev->ring[R600_RING_TYPE_UVD_INDEX])
+	if (rdev->wb.enabled)
 		rptr = le32_to_cpu(rdev->wb.wb[ring->rptr_offs/4]);
 	else
 		rptr = RREG32(ring->rptr_reg);
-	rptr = (rptr & ring->ptr_reg_mask) >> ring->ptr_reg_shift;
 
 	return rptr;
 }
@@ -378,7 +377,6 @@ u32 radeon_ring_generic_get_wptr(struct radeon_device *rdev,
 	u32 wptr;
 
 	wptr = RREG32(ring->wptr_reg);
-	wptr = (wptr & ring->ptr_reg_mask) >> ring->ptr_reg_shift;
 
 	return wptr;
 }
@@ -386,7 +384,7 @@ u32 radeon_ring_generic_get_wptr(struct radeon_device *rdev,
 void radeon_ring_generic_set_wptr(struct radeon_device *rdev,
 				  struct radeon_ring *ring)
 {
-	WREG32(ring->wptr_reg, (ring->wptr << ring->ptr_reg_shift) & ring->ptr_reg_mask);
+	WREG32(ring->wptr_reg, ring->wptr);
 	(void)RREG32(ring->wptr_reg);
 }
 
@@ -719,16 +717,13 @@ int radeon_ring_restore(struct radeon_device *rdev, struct radeon_ring *ring,
  * @rptr_offs: offset of the rptr writeback location in the WB buffer
  * @rptr_reg: MMIO offset of the rptr register
  * @wptr_reg: MMIO offset of the wptr register
- * @ptr_reg_shift: bit offset of the rptr/wptr values
- * @ptr_reg_mask: bit mask of the rptr/wptr values
  * @nop: nop packet for this ring
  *
  * Initialize the driver information for the selected ring (all asics).
  * Returns 0 on success, error on failure.
  */
 int radeon_ring_init(struct radeon_device *rdev, struct radeon_ring *ring, unsigned ring_size,
-		     unsigned rptr_offs, unsigned rptr_reg, unsigned wptr_reg,
-		     u32 ptr_reg_shift, u32 ptr_reg_mask, u32 nop)
+		     unsigned rptr_offs, unsigned rptr_reg, unsigned wptr_reg, u32 nop)
 {
 	int r;
 
@@ -736,8 +731,6 @@ int radeon_ring_init(struct radeon_device *rdev, struct radeon_ring *ring, unsig
 	ring->rptr_offs = rptr_offs;
 	ring->rptr_reg = rptr_reg;
 	ring->wptr_reg = wptr_reg;
-	ring->ptr_reg_shift = ptr_reg_shift;
-	ring->ptr_reg_mask = ptr_reg_mask;
 	ring->nop = nop;
 	/* Allocate ring buffer */
 	if (ring->ring_obj == NULL) {
@@ -846,9 +839,11 @@ static int radeon_debugfs_ring_info(struct seq_file *m, void *data)
 	 * packet that is the root issue
 	 */
 	i = (ring->rptr + ring->ptr_mask + 1 - 32) & ring->ptr_mask;
-	for (j = 0; j <= (count + 32); j++) {
-		seq_printf(m, "r[%5d]=0x%08x\n", i, ring->ring[i]);
-		i = (i + 1) & ring->ptr_mask;
+	if (ring->ready) {
+		for (j = 0; j <= (count + 32); j++) {
+			seq_printf(m, "r[%5d]=0x%08x\n", i, ring->ring[i]);
+			i = (i + 1) & ring->ptr_mask;
+		}
 	}
 	return 0;
 }
diff --git a/drivers/gpu/drm/radeon/radeon_test.c b/drivers/gpu/drm/radeon/radeon_test.c
index f4d6bcee9006..12e8099a0823 100644
--- a/drivers/gpu/drm/radeon/radeon_test.c
+++ b/drivers/gpu/drm/radeon/radeon_test.c
@@ -36,8 +36,8 @@ static void radeon_do_test_moves(struct radeon_device *rdev, int flag)
 	struct radeon_bo *vram_obj = NULL;
 	struct radeon_bo **gtt_obj = NULL;
 	uint64_t gtt_addr, vram_addr;
-	unsigned i, n, size;
-	int r, ring;
+	unsigned n, size;
+	int i, r, ring;
 
 	switch (flag) {
 	case RADEON_TEST_COPY_DMA:
diff --git a/drivers/gpu/drm/radeon/radeon_trace.h b/drivers/gpu/drm/radeon/radeon_trace.h
index eafd8160a155..f7e367815964 100644
--- a/drivers/gpu/drm/radeon/radeon_trace.h
+++ b/drivers/gpu/drm/radeon/radeon_trace.h
@@ -27,6 +27,26 @@ TRACE_EVENT(radeon_bo_create,
 	    TP_printk("bo=%p, pages=%u", __entry->bo, __entry->pages)
 );
 
+TRACE_EVENT(radeon_cs,
+	    TP_PROTO(struct radeon_cs_parser *p),
+	    TP_ARGS(p),
+	    TP_STRUCT__entry(
+			     __field(u32, ring)
+			     __field(u32, dw)
+			     __field(u32, fences)
+			     ),
+
+	    TP_fast_assign(
+			   __entry->ring = p->ring;
+			   __entry->dw = p->chunks[p->chunk_ib_idx].length_dw;
+			   __entry->fences = radeon_fence_count_emitted(
+				p->rdev, p->ring);
+			   ),
+	    TP_printk("ring=%u, dw=%u, fences=%u",
+		      __entry->ring, __entry->dw,
+		      __entry->fences)
+);
+
 DECLARE_EVENT_CLASS(radeon_fence_request,
 
 	    TP_PROTO(struct drm_device *dev, u32 seqno),
@@ -53,13 +73,6 @@ DEFINE_EVENT(radeon_fence_request, radeon_fence_emit,
 	    TP_ARGS(dev, seqno)
 );
 
-DEFINE_EVENT(radeon_fence_request, radeon_fence_retire,
-
-	    TP_PROTO(struct drm_device *dev, u32 seqno),
-
-	    TP_ARGS(dev, seqno)
-);
-
 DEFINE_EVENT(radeon_fence_request, radeon_fence_wait_begin,
 
 	    TP_PROTO(struct drm_device *dev, u32 seqno),
diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c
index 6c0ce8915fac..71245d6f34a2 100644
--- a/drivers/gpu/drm/radeon/radeon_ttm.c
+++ b/drivers/gpu/drm/radeon/radeon_ttm.c
@@ -203,7 +203,9 @@ static void radeon_evict_flags(struct ttm_buffer_object *bo,
 
 static int radeon_verify_access(struct ttm_buffer_object *bo, struct file *filp)
 {
-	return 0;
+	struct radeon_bo *rbo = container_of(bo, struct radeon_bo, tbo);
+
+	return drm_vma_node_verify_access(&rbo->gem_base.vma_node, filp);
 }
 
 static void radeon_move_null(struct ttm_buffer_object *bo,
diff --git a/drivers/gpu/drm/radeon/radeon_ucode.h b/drivers/gpu/drm/radeon/radeon_ucode.h
index d8b05f7bcf1a..33858364fe89 100644
--- a/drivers/gpu/drm/radeon/radeon_ucode.h
+++ b/drivers/gpu/drm/radeon/radeon_ucode.h
@@ -35,6 +35,12 @@
 #define SI_PFP_UCODE_SIZE            2144
 #define SI_PM4_UCODE_SIZE            2144
 #define SI_CE_UCODE_SIZE             2144
+#define CIK_PFP_UCODE_SIZE           2144
+#define CIK_ME_UCODE_SIZE            2144
+#define CIK_CE_UCODE_SIZE            2144
+
+/* MEC */
+#define CIK_MEC_UCODE_SIZE           4192
 
 /* RLC */
 #define R600_RLC_UCODE_SIZE          768
@@ -43,12 +49,20 @@
 #define CAYMAN_RLC_UCODE_SIZE        1024
 #define ARUBA_RLC_UCODE_SIZE         1536
 #define SI_RLC_UCODE_SIZE            2048
+#define BONAIRE_RLC_UCODE_SIZE       2048
+#define KB_RLC_UCODE_SIZE            2560
+#define KV_RLC_UCODE_SIZE            2560
 
 /* MC */
 #define BTC_MC_UCODE_SIZE            6024
 #define CAYMAN_MC_UCODE_SIZE         6037
 #define SI_MC_UCODE_SIZE             7769
 #define OLAND_MC_UCODE_SIZE          7863
+#define CIK_MC_UCODE_SIZE            7866
+
+/* SDMA */
+#define CIK_SDMA_UCODE_SIZE          1050
+#define CIK_SDMA_UCODE_VERSION       64
 
 /* SMC */
 #define RV770_SMC_UCODE_START        0x0100
@@ -126,4 +140,7 @@
 #define HAINAN_SMC_UCODE_START       0x10000
 #define HAINAN_SMC_UCODE_SIZE        0xe67C
 
+#define BONAIRE_SMC_UCODE_START      0x20000
+#define BONAIRE_SMC_UCODE_SIZE       0x1FDEC
+
 #endif
diff --git a/drivers/gpu/drm/radeon/radeon_uvd.c b/drivers/gpu/drm/radeon/radeon_uvd.c
index b79f4f5cdd62..4f2e73f79638 100644
--- a/drivers/gpu/drm/radeon/radeon_uvd.c
+++ b/drivers/gpu/drm/radeon/radeon_uvd.c
@@ -147,6 +147,7 @@ int radeon_uvd_init(struct radeon_device *rdev)
 	for (i = 0; i < RADEON_MAX_UVD_HANDLES; ++i) {
 		atomic_set(&rdev->uvd.handles[i], 0);
 		rdev->uvd.filp[i] = NULL;
+		rdev->uvd.img_size[i] = 0;
 	}
 
 	return 0;
@@ -347,6 +348,7 @@ static int radeon_uvd_cs_msg(struct radeon_cs_parser *p, struct radeon_bo *bo,
 			     unsigned offset, unsigned buf_sizes[])
 {
 	int32_t *msg, msg_type, handle;
+	unsigned img_size = 0;
 	void *ptr;
 
 	int i, r;
@@ -383,6 +385,8 @@ static int radeon_uvd_cs_msg(struct radeon_cs_parser *p, struct radeon_bo *bo,
 	if (msg_type == 1) {
 		/* it's a decode msg, calc buffer sizes */
 		r = radeon_uvd_cs_msg_decode(msg, buf_sizes);
+		/* calc image size (width * height) */
+		img_size = msg[6] * msg[7];
 		radeon_bo_kunmap(bo);
 		if (r)
 			return r;
@@ -394,6 +398,8 @@ static int radeon_uvd_cs_msg(struct radeon_cs_parser *p, struct radeon_bo *bo,
 		radeon_bo_kunmap(bo);
 		return 0;
 	} else {
+		/* it's a create msg, calc image size (width * height) */
+		img_size = msg[7] * msg[8];
 		radeon_bo_kunmap(bo);
 
 		if (msg_type != 0) {
@@ -414,6 +420,7 @@ static int radeon_uvd_cs_msg(struct radeon_cs_parser *p, struct radeon_bo *bo,
 	for (i = 0; i < RADEON_MAX_UVD_HANDLES; ++i) {
 		if (!atomic_cmpxchg(&p->rdev->uvd.handles[i], 0, handle)) {
 			p->rdev->uvd.filp[i] = p->filp;
+			p->rdev->uvd.img_size[i] = img_size;
 			return 0;
 		}
 	}
@@ -469,8 +476,7 @@ static int radeon_uvd_cs_reloc(struct radeon_cs_parser *p,
 		return -EINVAL;
 	}
 
-	/* TODO: is this still necessary on NI+ ? */
-	if ((cmd == 0 || cmd == 0x3) &&
+	if (p->rdev->family < CHIP_PALM && (cmd == 0 || cmd == 0x3) &&
 	    (start >> 28) != (p->rdev->uvd.gpu_addr >> 28)) {
 		DRM_ERROR("msg/fb buffer %LX-%LX out of 256MB segment!\n",
 			  start, end);
@@ -733,6 +739,34 @@ int radeon_uvd_get_destroy_msg(struct radeon_device *rdev, int ring,
 	return radeon_uvd_send_msg(rdev, ring, bo, fence);
 }
 
+/**
+ * radeon_uvd_count_handles - count number of open streams
+ *
+ * @rdev: radeon_device pointer
+ * @sd: number of SD streams
+ * @hd: number of HD streams
+ *
+ * Count the number of open SD/HD streams as a hint for power mangement
+ */
+static void radeon_uvd_count_handles(struct radeon_device *rdev,
+				     unsigned *sd, unsigned *hd)
+{
+	unsigned i;
+
+	*sd = 0;
+	*hd = 0;
+
+	for (i = 0; i < RADEON_MAX_UVD_HANDLES; ++i) {
+		if (!atomic_read(&rdev->uvd.handles[i]))
+			continue;
+
+		if (rdev->uvd.img_size[i] >= 720*576)
+			++(*hd);
+		else
+			++(*sd);
+	}
+}
+
 static void radeon_uvd_idle_work_handler(struct work_struct *work)
 {
 	struct radeon_device *rdev =
@@ -740,10 +774,7 @@ static void radeon_uvd_idle_work_handler(struct work_struct *work)
 
 	if (radeon_fence_count_emitted(rdev, R600_RING_TYPE_UVD_INDEX) == 0) {
 		if ((rdev->pm.pm_method == PM_METHOD_DPM) && rdev->pm.dpm_enabled) {
-			mutex_lock(&rdev->pm.mutex);
-			rdev->pm.dpm.uvd_active = false;
-			mutex_unlock(&rdev->pm.mutex);
-			radeon_pm_compute_clocks(rdev);
+			radeon_dpm_enable_uvd(rdev, false);
 		} else {
 			radeon_set_uvd_clocks(rdev, 0, 0);
 		}
@@ -755,13 +786,26 @@ static void radeon_uvd_idle_work_handler(struct work_struct *work)
 
 void radeon_uvd_note_usage(struct radeon_device *rdev)
 {
+	bool streams_changed = false;
 	bool set_clocks = !cancel_delayed_work_sync(&rdev->uvd.idle_work);
 	set_clocks &= schedule_delayed_work(&rdev->uvd.idle_work,
 					    msecs_to_jiffies(UVD_IDLE_TIMEOUT_MS));
-	if (set_clocks) {
+
+	if ((rdev->pm.pm_method == PM_METHOD_DPM) && rdev->pm.dpm_enabled) {
+		unsigned hd = 0, sd = 0;
+		radeon_uvd_count_handles(rdev, &sd, &hd);
+		if ((rdev->pm.dpm.sd != sd) ||
+		    (rdev->pm.dpm.hd != hd)) {
+			rdev->pm.dpm.sd = sd;
+			rdev->pm.dpm.hd = hd;
+			/* disable this for now */
+			/*streams_changed = true;*/
+		}
+	}
+
+	if (set_clocks || streams_changed) {
 		if ((rdev->pm.pm_method == PM_METHOD_DPM) && rdev->pm.dpm_enabled) {
-			/* XXX pick SD/HD/MVC */
-			radeon_dpm_enable_power_state(rdev, POWER_STATE_TYPE_INTERNAL_UVD);
+			radeon_dpm_enable_uvd(rdev, true);
 		} else {
 			radeon_set_uvd_clocks(rdev, 53300, 40000);
 		}
diff --git a/drivers/gpu/drm/radeon/rs400.c b/drivers/gpu/drm/radeon/rs400.c
index 233a9b9fa1f7..9566b5940a5a 100644
--- a/drivers/gpu/drm/radeon/rs400.c
+++ b/drivers/gpu/drm/radeon/rs400.c
@@ -174,10 +174,13 @@ int rs400_gart_enable(struct radeon_device *rdev)
 	/* FIXME: according to doc we should set HIDE_MMCFG_BAR=0,
 	 * AGPMODE30=0 & AGP30ENHANCED=0 in NB_CNTL */
 	if ((rdev->family == CHIP_RS690) || (rdev->family == CHIP_RS740)) {
-		WREG32_MC(RS480_MC_MISC_CNTL,
-			  (RS480_GART_INDEX_REG_EN | RS690_BLOCK_GFX_D3_EN));
+		tmp = RREG32_MC(RS480_MC_MISC_CNTL);
+		tmp |= RS480_GART_INDEX_REG_EN | RS690_BLOCK_GFX_D3_EN;
+		WREG32_MC(RS480_MC_MISC_CNTL, tmp);
 	} else {
-		WREG32_MC(RS480_MC_MISC_CNTL, RS480_GART_INDEX_REG_EN);
+		tmp = RREG32_MC(RS480_MC_MISC_CNTL);
+		tmp |= RS480_GART_INDEX_REG_EN;
+		WREG32_MC(RS480_MC_MISC_CNTL, tmp);
 	}
 	/* Enable gart */
 	WREG32_MC(RS480_AGP_ADDRESS_SPACE_SIZE, (RS480_GART_EN | size_reg));
@@ -271,19 +274,26 @@ static void rs400_mc_init(struct radeon_device *rdev)
 
 uint32_t rs400_mc_rreg(struct radeon_device *rdev, uint32_t reg)
 {
+	unsigned long flags;
 	uint32_t r;
 
+	spin_lock_irqsave(&rdev->mc_idx_lock, flags);
 	WREG32(RS480_NB_MC_INDEX, reg & 0xff);
 	r = RREG32(RS480_NB_MC_DATA);
 	WREG32(RS480_NB_MC_INDEX, 0xff);
+	spin_unlock_irqrestore(&rdev->mc_idx_lock, flags);
 	return r;
 }
 
 void rs400_mc_wreg(struct radeon_device *rdev, uint32_t reg, uint32_t v)
 {
+	unsigned long flags;
+
+	spin_lock_irqsave(&rdev->mc_idx_lock, flags);
 	WREG32(RS480_NB_MC_INDEX, ((reg) & 0xff) | RS480_NB_MC_IND_WR_EN);
 	WREG32(RS480_NB_MC_DATA, (v));
 	WREG32(RS480_NB_MC_INDEX, 0xff);
+	spin_unlock_irqrestore(&rdev->mc_idx_lock, flags);
 }
 
 #if defined(CONFIG_DEBUG_FS)
diff --git a/drivers/gpu/drm/radeon/rs600.c b/drivers/gpu/drm/radeon/rs600.c
index 670b555d2ca2..6acba8017b9a 100644
--- a/drivers/gpu/drm/radeon/rs600.c
+++ b/drivers/gpu/drm/radeon/rs600.c
@@ -847,16 +847,26 @@ void rs600_bandwidth_update(struct radeon_device *rdev)
 
 uint32_t rs600_mc_rreg(struct radeon_device *rdev, uint32_t reg)
 {
+	unsigned long flags;
+	u32 r;
+
+	spin_lock_irqsave(&rdev->mc_idx_lock, flags);
 	WREG32(R_000070_MC_IND_INDEX, S_000070_MC_IND_ADDR(reg) |
 		S_000070_MC_IND_CITF_ARB0(1));
-	return RREG32(R_000074_MC_IND_DATA);
+	r = RREG32(R_000074_MC_IND_DATA);
+	spin_unlock_irqrestore(&rdev->mc_idx_lock, flags);
+	return r;
 }
 
 void rs600_mc_wreg(struct radeon_device *rdev, uint32_t reg, uint32_t v)
 {
+	unsigned long flags;
+
+	spin_lock_irqsave(&rdev->mc_idx_lock, flags);
 	WREG32(R_000070_MC_IND_INDEX, S_000070_MC_IND_ADDR(reg) |
 		S_000070_MC_IND_CITF_ARB0(1) | S_000070_MC_IND_WR_EN(1));
 	WREG32(R_000074_MC_IND_DATA, v);
+	spin_unlock_irqrestore(&rdev->mc_idx_lock, flags);
 }
 
 static void rs600_debugfs(struct radeon_device *rdev)
diff --git a/drivers/gpu/drm/radeon/rs690.c b/drivers/gpu/drm/radeon/rs690.c
index d8ddfb34545d..1447d794c22a 100644
--- a/drivers/gpu/drm/radeon/rs690.c
+++ b/drivers/gpu/drm/radeon/rs690.c
@@ -631,20 +631,27 @@ void rs690_bandwidth_update(struct radeon_device *rdev)
 
 uint32_t rs690_mc_rreg(struct radeon_device *rdev, uint32_t reg)
 {
+	unsigned long flags;
 	uint32_t r;
 
+	spin_lock_irqsave(&rdev->mc_idx_lock, flags);
 	WREG32(R_000078_MC_INDEX, S_000078_MC_IND_ADDR(reg));
 	r = RREG32(R_00007C_MC_DATA);
 	WREG32(R_000078_MC_INDEX, ~C_000078_MC_IND_ADDR);
+	spin_unlock_irqrestore(&rdev->mc_idx_lock, flags);
 	return r;
 }
 
 void rs690_mc_wreg(struct radeon_device *rdev, uint32_t reg, uint32_t v)
 {
+	unsigned long flags;
+
+	spin_lock_irqsave(&rdev->mc_idx_lock, flags);
 	WREG32(R_000078_MC_INDEX, S_000078_MC_IND_ADDR(reg) |
 		S_000078_MC_IND_WR_EN(1));
 	WREG32(R_00007C_MC_DATA, v);
 	WREG32(R_000078_MC_INDEX, 0x7F);
+	spin_unlock_irqrestore(&rdev->mc_idx_lock, flags);
 }
 
 static void rs690_mc_program(struct radeon_device *rdev)
diff --git a/drivers/gpu/drm/radeon/rs780_dpm.c b/drivers/gpu/drm/radeon/rs780_dpm.c
index d1a1ce73bd45..6af8505cf4d2 100644
--- a/drivers/gpu/drm/radeon/rs780_dpm.c
+++ b/drivers/gpu/drm/radeon/rs780_dpm.c
@@ -62,9 +62,7 @@ static void rs780_get_pm_mode_parameters(struct radeon_device *rdev)
 			radeon_crtc = to_radeon_crtc(crtc);
 			pi->crtc_id = radeon_crtc->crtc_id;
 			if (crtc->mode.htotal && crtc->mode.vtotal)
-				pi->refresh_rate =
-					(crtc->mode.clock * 1000) /
-					(crtc->mode.htotal * crtc->mode.vtotal);
+				pi->refresh_rate = drm_mode_vrefresh(&crtc->mode);
 			break;
 		}
 	}
@@ -376,9 +374,8 @@ static void rs780_disable_vbios_powersaving(struct radeon_device *rdev)
 	WREG32_P(CG_INTGFX_MISC, 0, ~0xFFF00000);
 }
 
-static void rs780_force_voltage_to_high(struct radeon_device *rdev)
+static void rs780_force_voltage(struct radeon_device *rdev, u16 voltage)
 {
-	struct igp_power_info *pi = rs780_get_pi(rdev);
 	struct igp_ps *current_state = rs780_get_ps(rdev->pm.dpm.current_ps);
 
 	if ((current_state->max_voltage == RS780_VDDC_LEVEL_HIGH) &&
@@ -390,7 +387,7 @@ static void rs780_force_voltage_to_high(struct radeon_device *rdev)
 	udelay(1);
 
 	WREG32_P(FVTHROT_PWM_CTRL_REG0,
-		 STARTING_PWM_HIGHTIME(pi->max_voltage),
+		 STARTING_PWM_HIGHTIME(voltage),
 		 ~STARTING_PWM_HIGHTIME_MASK);
 
 	WREG32_P(FVTHROT_PWM_CTRL_REG0,
@@ -404,6 +401,26 @@ static void rs780_force_voltage_to_high(struct radeon_device *rdev)
 	WREG32_P(GFX_MACRO_BYPASS_CNTL, 0, ~SPLL_BYPASS_CNTL);
 }
 
+static void rs780_force_fbdiv(struct radeon_device *rdev, u32 fb_div)
+{
+	struct igp_ps *current_state = rs780_get_ps(rdev->pm.dpm.current_ps);
+
+	if (current_state->sclk_low == current_state->sclk_high)
+		return;
+
+	WREG32_P(GFX_MACRO_BYPASS_CNTL, SPLL_BYPASS_CNTL, ~SPLL_BYPASS_CNTL);
+
+	WREG32_P(FVTHROT_FBDIV_REG2, FORCED_FEEDBACK_DIV(fb_div),
+		 ~FORCED_FEEDBACK_DIV_MASK);
+	WREG32_P(FVTHROT_FBDIV_REG1, STARTING_FEEDBACK_DIV(fb_div),
+		 ~STARTING_FEEDBACK_DIV_MASK);
+	WREG32_P(FVTHROT_FBDIV_REG1, FORCE_FEEDBACK_DIV, ~FORCE_FEEDBACK_DIV);
+
+	udelay(100);
+
+	WREG32_P(GFX_MACRO_BYPASS_CNTL, 0, ~SPLL_BYPASS_CNTL);
+}
+
 static int rs780_set_engine_clock_scaling(struct radeon_device *rdev,
 					  struct radeon_ps *new_ps,
 					  struct radeon_ps *old_ps)
@@ -432,17 +449,13 @@ static int rs780_set_engine_clock_scaling(struct radeon_device *rdev,
 	if (ret)
 		return ret;
 
-	WREG32_P(GFX_MACRO_BYPASS_CNTL, SPLL_BYPASS_CNTL, ~SPLL_BYPASS_CNTL);
-
-	WREG32_P(FVTHROT_FBDIV_REG2, FORCED_FEEDBACK_DIV(max_dividers.fb_div),
-		 ~FORCED_FEEDBACK_DIV_MASK);
-	WREG32_P(FVTHROT_FBDIV_REG1, STARTING_FEEDBACK_DIV(max_dividers.fb_div),
-		 ~STARTING_FEEDBACK_DIV_MASK);
-	WREG32_P(FVTHROT_FBDIV_REG1, FORCE_FEEDBACK_DIV, ~FORCE_FEEDBACK_DIV);
-
-	udelay(100);
+	if ((min_dividers.ref_div != max_dividers.ref_div) ||
+	    (min_dividers.post_div != max_dividers.post_div) ||
+	    (max_dividers.ref_div != current_max_dividers.ref_div) ||
+	    (max_dividers.post_div != current_max_dividers.post_div))
+		return -EINVAL;
 
-	WREG32_P(GFX_MACRO_BYPASS_CNTL, 0, ~SPLL_BYPASS_CNTL);
+	rs780_force_fbdiv(rdev, max_dividers.fb_div);
 
 	if (max_dividers.fb_div > min_dividers.fb_div) {
 		WREG32_P(FVTHROT_FBDIV_REG0,
@@ -486,6 +499,9 @@ static void rs780_activate_engine_clk_scaling(struct radeon_device *rdev,
 	    (new_state->sclk_low == old_state->sclk_low))
 		return;
 
+	if (new_state->sclk_high == new_state->sclk_low)
+		return;
+
 	rs780_clk_scaling_enable(rdev, true);
 }
 
@@ -649,7 +665,7 @@ int rs780_dpm_set_power_state(struct radeon_device *rdev)
 	rs780_set_uvd_clock_before_set_eng_clock(rdev, new_ps, old_ps);
 
 	if (pi->voltage_control) {
-		rs780_force_voltage_to_high(rdev);
+		rs780_force_voltage(rdev, pi->max_voltage);
 		mdelay(5);
 	}
 
@@ -717,14 +733,18 @@ static void rs780_parse_pplib_non_clock_info(struct radeon_device *rdev,
 	if (ATOM_PPLIB_NONCLOCKINFO_VER1 < table_rev) {
 		rps->vclk = le32_to_cpu(non_clock_info->ulVCLK);
 		rps->dclk = le32_to_cpu(non_clock_info->ulDCLK);
-	} else if (r600_is_uvd_state(rps->class, rps->class2)) {
-		rps->vclk = RS780_DEFAULT_VCLK_FREQ;
-		rps->dclk = RS780_DEFAULT_DCLK_FREQ;
 	} else {
 		rps->vclk = 0;
 		rps->dclk = 0;
 	}
 
+	if (r600_is_uvd_state(rps->class, rps->class2)) {
+		if ((rps->vclk == 0) || (rps->dclk == 0)) {
+			rps->vclk = RS780_DEFAULT_VCLK_FREQ;
+			rps->dclk = RS780_DEFAULT_DCLK_FREQ;
+		}
+	}
+
 	if (rps->class & ATOM_PPLIB_CLASSIFICATION_BOOT)
 		rdev->pm.dpm.boot_ps = rps;
 	if (rps->class & ATOM_PPLIB_CLASSIFICATION_UVDSTATE)
@@ -986,3 +1006,55 @@ void rs780_dpm_debugfs_print_current_performance_level(struct radeon_device *rde
 		seq_printf(m, "power level 1    sclk: %u vddc_index: %d\n",
 			   ps->sclk_high, ps->max_voltage);
 }
+
+int rs780_dpm_force_performance_level(struct radeon_device *rdev,
+				      enum radeon_dpm_forced_level level)
+{
+	struct igp_power_info *pi = rs780_get_pi(rdev);
+	struct radeon_ps *rps = rdev->pm.dpm.current_ps;
+	struct igp_ps *ps = rs780_get_ps(rps);
+	struct atom_clock_dividers dividers;
+	int ret;
+
+	rs780_clk_scaling_enable(rdev, false);
+	rs780_voltage_scaling_enable(rdev, false);
+
+	if (level == RADEON_DPM_FORCED_LEVEL_HIGH) {
+		if (pi->voltage_control)
+			rs780_force_voltage(rdev, pi->max_voltage);
+
+		ret = radeon_atom_get_clock_dividers(rdev, COMPUTE_ENGINE_PLL_PARAM,
+						     ps->sclk_high, false, &dividers);
+		if (ret)
+			return ret;
+
+		rs780_force_fbdiv(rdev, dividers.fb_div);
+	} else if (level == RADEON_DPM_FORCED_LEVEL_LOW) {
+		ret = radeon_atom_get_clock_dividers(rdev, COMPUTE_ENGINE_PLL_PARAM,
+						     ps->sclk_low, false, &dividers);
+		if (ret)
+			return ret;
+
+		rs780_force_fbdiv(rdev, dividers.fb_div);
+
+		if (pi->voltage_control)
+			rs780_force_voltage(rdev, pi->min_voltage);
+	} else {
+		if (pi->voltage_control)
+			rs780_force_voltage(rdev, pi->max_voltage);
+
+		if (ps->sclk_high != ps->sclk_low) {
+			WREG32_P(FVTHROT_FBDIV_REG1, 0, ~FORCE_FEEDBACK_DIV);
+			rs780_clk_scaling_enable(rdev, true);
+		}
+
+		if (pi->voltage_control) {
+			rs780_voltage_scaling_enable(rdev, true);
+			rs780_enable_voltage_scaling(rdev, rps);
+		}
+	}
+
+	rdev->pm.dpm.forced_level = level;
+
+	return 0;
+}
diff --git a/drivers/gpu/drm/radeon/rv515.c b/drivers/gpu/drm/radeon/rv515.c
index 8ea1573ae820..873eb4b193b4 100644
--- a/drivers/gpu/drm/radeon/rv515.c
+++ b/drivers/gpu/drm/radeon/rv515.c
@@ -209,19 +209,27 @@ static void rv515_mc_init(struct radeon_device *rdev)
 
 uint32_t rv515_mc_rreg(struct radeon_device *rdev, uint32_t reg)
 {
+	unsigned long flags;
 	uint32_t r;
 
+	spin_lock_irqsave(&rdev->mc_idx_lock, flags);
 	WREG32(MC_IND_INDEX, 0x7f0000 | (reg & 0xffff));
 	r = RREG32(MC_IND_DATA);
 	WREG32(MC_IND_INDEX, 0);
+	spin_unlock_irqrestore(&rdev->mc_idx_lock, flags);
+
 	return r;
 }
 
 void rv515_mc_wreg(struct radeon_device *rdev, uint32_t reg, uint32_t v)
 {
+	unsigned long flags;
+
+	spin_lock_irqsave(&rdev->mc_idx_lock, flags);
 	WREG32(MC_IND_INDEX, 0xff0000 | ((reg) & 0xffff));
 	WREG32(MC_IND_DATA, (v));
 	WREG32(MC_IND_INDEX, 0);
+	spin_unlock_irqrestore(&rdev->mc_idx_lock, flags);
 }
 
 #if defined(CONFIG_DEBUG_FS)
diff --git a/drivers/gpu/drm/radeon/rv6xx_dpm.c b/drivers/gpu/drm/radeon/rv6xx_dpm.c
index bdd888b4db2b..5811d277a36a 100644
--- a/drivers/gpu/drm/radeon/rv6xx_dpm.c
+++ b/drivers/gpu/drm/radeon/rv6xx_dpm.c
@@ -1758,8 +1758,6 @@ int rv6xx_dpm_set_power_state(struct radeon_device *rdev)
 
 	rv6xx_set_uvd_clock_after_set_eng_clock(rdev, new_ps, old_ps);
 
-	rdev->pm.dpm.forced_level = RADEON_DPM_FORCED_LEVEL_AUTO;
-
 	return 0;
 }
 
@@ -1918,6 +1916,7 @@ static int rv6xx_parse_power_table(struct radeon_device *rdev)
 			 (power_state->v1.ucNonClockStateIndex *
 			  power_info->pplib.ucNonClockSize));
 		if (power_info->pplib.ucStateEntrySize - 1) {
+			u8 *idx;
 			ps = kzalloc(sizeof(struct rv6xx_ps), GFP_KERNEL);
 			if (ps == NULL) {
 				kfree(rdev->pm.dpm.ps);
@@ -1926,12 +1925,12 @@ static int rv6xx_parse_power_table(struct radeon_device *rdev)
 			rdev->pm.dpm.ps[i].ps_priv = ps;
 			rv6xx_parse_pplib_non_clock_info(rdev, &rdev->pm.dpm.ps[i],
 							 non_clock_info);
+			idx = (u8 *)&power_state->v1.ucClockStateIndices[0];
 			for (j = 0; j < (power_info->pplib.ucStateEntrySize - 1); j++) {
 				clock_info = (union pplib_clock_info *)
 					(mode_info->atom_context->bios + data_offset +
 					 le16_to_cpu(power_info->pplib.usClockInfoArrayOffset) +
-					 (power_state->v1.ucClockStateIndices[j] *
-					  power_info->pplib.ucClockInfoSize));
+					 (idx[j] * power_info->pplib.ucClockInfoSize));
 				rv6xx_parse_pplib_clock_info(rdev,
 							     &rdev->pm.dpm.ps[i], j,
 							     clock_info);
diff --git a/drivers/gpu/drm/radeon/rv770.c b/drivers/gpu/drm/radeon/rv770.c
index f5e92cfcc140..9f5846743c9e 100644
--- a/drivers/gpu/drm/radeon/rv770.c
+++ b/drivers/gpu/drm/radeon/rv770.c
@@ -801,103 +801,6 @@ u32 rv770_get_xclk(struct radeon_device *rdev)
 	return reference_clock;
 }
 
-int rv770_uvd_resume(struct radeon_device *rdev)
-{
-	uint64_t addr;
-	uint32_t chip_id, size;
-	int r;
-
-	r = radeon_uvd_resume(rdev);
-	if (r)
-		return r;
-
-	/* programm the VCPU memory controller bits 0-27 */
-	addr = rdev->uvd.gpu_addr >> 3;
-	size = RADEON_GPU_PAGE_ALIGN(rdev->uvd_fw->size + 4) >> 3;
-	WREG32(UVD_VCPU_CACHE_OFFSET0, addr);
-	WREG32(UVD_VCPU_CACHE_SIZE0, size);
-
-	addr += size;
-	size = RADEON_UVD_STACK_SIZE >> 3;
-	WREG32(UVD_VCPU_CACHE_OFFSET1, addr);
-	WREG32(UVD_VCPU_CACHE_SIZE1, size);
-
-	addr += size;
-	size = RADEON_UVD_HEAP_SIZE >> 3;
-	WREG32(UVD_VCPU_CACHE_OFFSET2, addr);
-	WREG32(UVD_VCPU_CACHE_SIZE2, size);
-
-	/* bits 28-31 */
-	addr = (rdev->uvd.gpu_addr >> 28) & 0xF;
-	WREG32(UVD_LMI_ADDR_EXT, (addr << 12) | (addr << 0));
-
-	/* bits 32-39 */
-	addr = (rdev->uvd.gpu_addr >> 32) & 0xFF;
-	WREG32(UVD_LMI_EXT40_ADDR, addr | (0x9 << 16) | (0x1 << 31));
-
-	/* tell firmware which hardware it is running on */
-	switch (rdev->family) {
-	default:
-		return -EINVAL;
-	case CHIP_RV710:
-		chip_id = 0x01000005;
-		break;
-	case CHIP_RV730:
-		chip_id = 0x01000006;
-		break;
-	case CHIP_RV740:
-		chip_id = 0x01000007;
-		break;
-	case CHIP_CYPRESS:
-	case CHIP_HEMLOCK:
-		chip_id = 0x01000008;
-		break;
-	case CHIP_JUNIPER:
-		chip_id = 0x01000009;
-		break;
-	case CHIP_REDWOOD:
-		chip_id = 0x0100000a;
-		break;
-	case CHIP_CEDAR:
-		chip_id = 0x0100000b;
-		break;
-	case CHIP_SUMO:
-	case CHIP_SUMO2:
-		chip_id = 0x0100000c;
-		break;
-	case CHIP_PALM:
-		chip_id = 0x0100000e;
-		break;
-	case CHIP_CAYMAN:
-		chip_id = 0x0100000f;
-		break;
-	case CHIP_BARTS:
-		chip_id = 0x01000010;
-		break;
-	case CHIP_TURKS:
-		chip_id = 0x01000011;
-		break;
-	case CHIP_CAICOS:
-		chip_id = 0x01000012;
-		break;
-	case CHIP_TAHITI:
-		chip_id = 0x01000014;
-		break;
-	case CHIP_VERDE:
-		chip_id = 0x01000015;
-		break;
-	case CHIP_PITCAIRN:
-		chip_id = 0x01000016;
-		break;
-	case CHIP_ARUBA:
-		chip_id = 0x01000017;
-		break;
-	}
-	WREG32(UVD_VCPU_CHIP_ID, chip_id);
-
-	return 0;
-}
-
 u32 rv770_page_flip(struct radeon_device *rdev, int crtc_id, u64 crtc_base)
 {
 	struct radeon_crtc *radeon_crtc = rdev->mode_info.crtcs[crtc_id];
@@ -1747,80 +1650,6 @@ static int rv770_mc_init(struct radeon_device *rdev)
 	return 0;
 }
 
-/**
- * rv770_copy_dma - copy pages using the DMA engine
- *
- * @rdev: radeon_device pointer
- * @src_offset: src GPU address
- * @dst_offset: dst GPU address
- * @num_gpu_pages: number of GPU pages to xfer
- * @fence: radeon fence object
- *
- * Copy GPU paging using the DMA engine (r7xx).
- * Used by the radeon ttm implementation to move pages if
- * registered as the asic copy callback.
- */
-int rv770_copy_dma(struct radeon_device *rdev,
-		  uint64_t src_offset, uint64_t dst_offset,
-		  unsigned num_gpu_pages,
-		  struct radeon_fence **fence)
-{
-	struct radeon_semaphore *sem = NULL;
-	int ring_index = rdev->asic->copy.dma_ring_index;
-	struct radeon_ring *ring = &rdev->ring[ring_index];
-	u32 size_in_dw, cur_size_in_dw;
-	int i, num_loops;
-	int r = 0;
-
-	r = radeon_semaphore_create(rdev, &sem);
-	if (r) {
-		DRM_ERROR("radeon: moving bo (%d).\n", r);
-		return r;
-	}
-
-	size_in_dw = (num_gpu_pages << RADEON_GPU_PAGE_SHIFT) / 4;
-	num_loops = DIV_ROUND_UP(size_in_dw, 0xFFFF);
-	r = radeon_ring_lock(rdev, ring, num_loops * 5 + 8);
-	if (r) {
-		DRM_ERROR("radeon: moving bo (%d).\n", r);
-		radeon_semaphore_free(rdev, &sem, NULL);
-		return r;
-	}
-
-	if (radeon_fence_need_sync(*fence, ring->idx)) {
-		radeon_semaphore_sync_rings(rdev, sem, (*fence)->ring,
-					    ring->idx);
-		radeon_fence_note_sync(*fence, ring->idx);
-	} else {
-		radeon_semaphore_free(rdev, &sem, NULL);
-	}
-
-	for (i = 0; i < num_loops; i++) {
-		cur_size_in_dw = size_in_dw;
-		if (cur_size_in_dw > 0xFFFF)
-			cur_size_in_dw = 0xFFFF;
-		size_in_dw -= cur_size_in_dw;
-		radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_COPY, 0, 0, cur_size_in_dw));
-		radeon_ring_write(ring, dst_offset & 0xfffffffc);
-		radeon_ring_write(ring, src_offset & 0xfffffffc);
-		radeon_ring_write(ring, upper_32_bits(dst_offset) & 0xff);
-		radeon_ring_write(ring, upper_32_bits(src_offset) & 0xff);
-		src_offset += cur_size_in_dw * 4;
-		dst_offset += cur_size_in_dw * 4;
-	}
-
-	r = radeon_fence_emit(rdev, fence, ring->idx);
-	if (r) {
-		radeon_ring_unlock_undo(rdev, ring);
-		return r;
-	}
-
-	radeon_ring_unlock_commit(rdev, ring);
-	radeon_semaphore_free(rdev, &sem, *fence);
-
-	return r;
-}
-
 static int rv770_startup(struct radeon_device *rdev)
 {
 	struct radeon_ring *ring;
@@ -1829,6 +1658,11 @@ static int rv770_startup(struct radeon_device *rdev)
 	/* enable pcie gen2 link */
 	rv770_pcie_gen2_enable(rdev);
 
+	/* scratch needs to be initialized before MC */
+	r = r600_vram_scratch_init(rdev);
+	if (r)
+		return r;
+
 	rv770_mc_program(rdev);
 
 	if (!rdev->me_fw || !rdev->pfp_fw || !rdev->rlc_fw) {
@@ -1839,10 +1673,6 @@ static int rv770_startup(struct radeon_device *rdev)
 		}
 	}
 
-	r = r600_vram_scratch_init(rdev);
-	if (r)
-		return r;
-
 	if (rdev->flags & RADEON_IS_AGP) {
 		rv770_agp_enable(rdev);
 	} else {
@@ -1852,12 +1682,6 @@ static int rv770_startup(struct radeon_device *rdev)
 	}
 
 	rv770_gpu_init(rdev);
-	r = r600_blit_init(rdev);
-	if (r) {
-		r600_blit_fini(rdev);
-		rdev->asic->copy.copy = NULL;
-		dev_warn(rdev->dev, "failed blitter (%d) falling back to memcpy\n", r);
-	}
 
 	/* allocate wb buffer */
 	r = radeon_wb_init(rdev);
@@ -1876,7 +1700,7 @@ static int rv770_startup(struct radeon_device *rdev)
 		return r;
 	}
 
-	r = rv770_uvd_resume(rdev);
+	r = uvd_v2_2_resume(rdev);
 	if (!r) {
 		r = radeon_fence_driver_start_ring(rdev,
 						   R600_RING_TYPE_UVD_INDEX);
@@ -1905,14 +1729,14 @@ static int rv770_startup(struct radeon_device *rdev)
 	ring = &rdev->ring[RADEON_RING_TYPE_GFX_INDEX];
 	r = radeon_ring_init(rdev, ring, ring->ring_size, RADEON_WB_CP_RPTR_OFFSET,
 			     R600_CP_RB_RPTR, R600_CP_RB_WPTR,
-			     0, 0xfffff, RADEON_CP_PACKET2);
+			     RADEON_CP_PACKET2);
 	if (r)
 		return r;
 
 	ring = &rdev->ring[R600_RING_TYPE_DMA_INDEX];
 	r = radeon_ring_init(rdev, ring, ring->ring_size, R600_WB_DMA_RPTR_OFFSET,
 			     DMA_RB_RPTR, DMA_RB_WPTR,
-			     2, 0x3fffc, DMA_PACKET(DMA_PACKET_NOP, 0, 0, 0));
+			     DMA_PACKET(DMA_PACKET_NOP, 0, 0, 0));
 	if (r)
 		return r;
 
@@ -1929,12 +1753,11 @@ static int rv770_startup(struct radeon_device *rdev)
 
 	ring = &rdev->ring[R600_RING_TYPE_UVD_INDEX];
 	if (ring->ring_size) {
-		r = radeon_ring_init(rdev, ring, ring->ring_size,
-				     R600_WB_UVD_RPTR_OFFSET,
+		r = radeon_ring_init(rdev, ring, ring->ring_size, 0,
 				     UVD_RBC_RB_RPTR, UVD_RBC_RB_WPTR,
-				     0, 0xfffff, RADEON_CP_PACKET2);
+				     RADEON_CP_PACKET2);
 		if (!r)
-			r = r600_uvd_init(rdev);
+			r = uvd_v1_0_init(rdev);
 
 		if (r)
 			DRM_ERROR("radeon: failed initializing UVD (%d).\n", r);
@@ -1984,7 +1807,7 @@ int rv770_resume(struct radeon_device *rdev)
 int rv770_suspend(struct radeon_device *rdev)
 {
 	r600_audio_fini(rdev);
-	r600_uvd_stop(rdev);
+	uvd_v1_0_fini(rdev);
 	radeon_uvd_suspend(rdev);
 	r700_cp_stop(rdev);
 	r600_dma_stop(rdev);
@@ -2092,7 +1915,6 @@ int rv770_init(struct radeon_device *rdev)
 
 void rv770_fini(struct radeon_device *rdev)
 {
-	r600_blit_fini(rdev);
 	r700_cp_fini(rdev);
 	r600_dma_fini(rdev);
 	r600_irq_fini(rdev);
@@ -2100,7 +1922,7 @@ void rv770_fini(struct radeon_device *rdev)
 	radeon_ib_pool_fini(rdev);
 	radeon_irq_kms_fini(rdev);
 	rv770_pcie_gart_fini(rdev);
-	r600_uvd_stop(rdev);
+	uvd_v1_0_fini(rdev);
 	radeon_uvd_fini(rdev);
 	r600_vram_scratch_fini(rdev);
 	radeon_gem_fini(rdev);
diff --git a/drivers/gpu/drm/radeon/rv770_dma.c b/drivers/gpu/drm/radeon/rv770_dma.c
new file mode 100644
index 000000000000..f9b02e3d6830
--- /dev/null
+++ b/drivers/gpu/drm/radeon/rv770_dma.c
@@ -0,0 +1,101 @@
+/*
+ * Copyright 2013 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: Alex Deucher
+ */
+#include <drm/drmP.h>
+#include "radeon.h"
+#include "radeon_asic.h"
+#include "rv770d.h"
+
+/**
+ * rv770_copy_dma - copy pages using the DMA engine
+ *
+ * @rdev: radeon_device pointer
+ * @src_offset: src GPU address
+ * @dst_offset: dst GPU address
+ * @num_gpu_pages: number of GPU pages to xfer
+ * @fence: radeon fence object
+ *
+ * Copy GPU paging using the DMA engine (r7xx).
+ * Used by the radeon ttm implementation to move pages if
+ * registered as the asic copy callback.
+ */
+int rv770_copy_dma(struct radeon_device *rdev,
+		  uint64_t src_offset, uint64_t dst_offset,
+		  unsigned num_gpu_pages,
+		  struct radeon_fence **fence)
+{
+	struct radeon_semaphore *sem = NULL;
+	int ring_index = rdev->asic->copy.dma_ring_index;
+	struct radeon_ring *ring = &rdev->ring[ring_index];
+	u32 size_in_dw, cur_size_in_dw;
+	int i, num_loops;
+	int r = 0;
+
+	r = radeon_semaphore_create(rdev, &sem);
+	if (r) {
+		DRM_ERROR("radeon: moving bo (%d).\n", r);
+		return r;
+	}
+
+	size_in_dw = (num_gpu_pages << RADEON_GPU_PAGE_SHIFT) / 4;
+	num_loops = DIV_ROUND_UP(size_in_dw, 0xFFFF);
+	r = radeon_ring_lock(rdev, ring, num_loops * 5 + 8);
+	if (r) {
+		DRM_ERROR("radeon: moving bo (%d).\n", r);
+		radeon_semaphore_free(rdev, &sem, NULL);
+		return r;
+	}
+
+	if (radeon_fence_need_sync(*fence, ring->idx)) {
+		radeon_semaphore_sync_rings(rdev, sem, (*fence)->ring,
+					    ring->idx);
+		radeon_fence_note_sync(*fence, ring->idx);
+	} else {
+		radeon_semaphore_free(rdev, &sem, NULL);
+	}
+
+	for (i = 0; i < num_loops; i++) {
+		cur_size_in_dw = size_in_dw;
+		if (cur_size_in_dw > 0xFFFF)
+			cur_size_in_dw = 0xFFFF;
+		size_in_dw -= cur_size_in_dw;
+		radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_COPY, 0, 0, cur_size_in_dw));
+		radeon_ring_write(ring, dst_offset & 0xfffffffc);
+		radeon_ring_write(ring, src_offset & 0xfffffffc);
+		radeon_ring_write(ring, upper_32_bits(dst_offset) & 0xff);
+		radeon_ring_write(ring, upper_32_bits(src_offset) & 0xff);
+		src_offset += cur_size_in_dw * 4;
+		dst_offset += cur_size_in_dw * 4;
+	}
+
+	r = radeon_fence_emit(rdev, fence, ring->idx);
+	if (r) {
+		radeon_ring_unlock_undo(rdev, ring);
+		return r;
+	}
+
+	radeon_ring_unlock_commit(rdev, ring);
+	radeon_semaphore_free(rdev, &sem, *fence);
+
+	return r;
+}
diff --git a/drivers/gpu/drm/radeon/rv770_dpm.c b/drivers/gpu/drm/radeon/rv770_dpm.c
index 094c67a29d0d..913b025ae9b3 100644
--- a/drivers/gpu/drm/radeon/rv770_dpm.c
+++ b/drivers/gpu/drm/radeon/rv770_dpm.c
@@ -2064,12 +2064,6 @@ int rv770_dpm_set_power_state(struct radeon_device *rdev)
 		rv770_program_dcodt_after_state_switch(rdev, new_ps, old_ps);
 	rv770_set_uvd_clock_after_set_eng_clock(rdev, new_ps, old_ps);
 
-	ret = rv770_dpm_force_performance_level(rdev, RADEON_DPM_FORCED_LEVEL_AUTO);
-	if (ret) {
-		DRM_ERROR("rv770_dpm_force_performance_level failed\n");
-		return ret;
-	}
-
 	return 0;
 }
 
@@ -2147,14 +2141,18 @@ static void rv7xx_parse_pplib_non_clock_info(struct radeon_device *rdev,
 	if (ATOM_PPLIB_NONCLOCKINFO_VER1 < table_rev) {
 		rps->vclk = le32_to_cpu(non_clock_info->ulVCLK);
 		rps->dclk = le32_to_cpu(non_clock_info->ulDCLK);
-	} else if (r600_is_uvd_state(rps->class, rps->class2)) {
-		rps->vclk = RV770_DEFAULT_VCLK_FREQ;
-		rps->dclk = RV770_DEFAULT_DCLK_FREQ;
 	} else {
 		rps->vclk = 0;
 		rps->dclk = 0;
 	}
 
+	if (r600_is_uvd_state(rps->class, rps->class2)) {
+		if ((rps->vclk == 0) || (rps->dclk == 0)) {
+			rps->vclk = RV770_DEFAULT_VCLK_FREQ;
+			rps->dclk = RV770_DEFAULT_DCLK_FREQ;
+		}
+	}
+
 	if (rps->class & ATOM_PPLIB_CLASSIFICATION_BOOT)
 		rdev->pm.dpm.boot_ps = rps;
 	if (rps->class & ATOM_PPLIB_CLASSIFICATION_UVDSTATE)
@@ -2294,6 +2292,7 @@ int rv7xx_parse_power_table(struct radeon_device *rdev)
 			 (power_state->v1.ucNonClockStateIndex *
 			  power_info->pplib.ucNonClockSize));
 		if (power_info->pplib.ucStateEntrySize - 1) {
+			u8 *idx;
 			ps = kzalloc(sizeof(struct rv7xx_ps), GFP_KERNEL);
 			if (ps == NULL) {
 				kfree(rdev->pm.dpm.ps);
@@ -2303,12 +2302,12 @@ int rv7xx_parse_power_table(struct radeon_device *rdev)
 			rv7xx_parse_pplib_non_clock_info(rdev, &rdev->pm.dpm.ps[i],
 							 non_clock_info,
 							 power_info->pplib.ucNonClockSize);
+			idx = (u8 *)&power_state->v1.ucClockStateIndices[0];
 			for (j = 0; j < (power_info->pplib.ucStateEntrySize - 1); j++) {
 				clock_info = (union pplib_clock_info *)
 					(mode_info->atom_context->bios + data_offset +
 					 le16_to_cpu(power_info->pplib.usClockInfoArrayOffset) +
-					 (power_state->v1.ucClockStateIndices[j] *
-					  power_info->pplib.ucClockInfoSize));
+					 (idx[j] * power_info->pplib.ucClockInfoSize));
 				rv7xx_parse_pplib_clock_info(rdev,
 							     &rdev->pm.dpm.ps[i], j,
 							     clock_info);
@@ -2517,8 +2516,16 @@ u32 rv770_dpm_get_mclk(struct radeon_device *rdev, bool low)
 bool rv770_dpm_vblank_too_short(struct radeon_device *rdev)
 {
 	u32 vblank_time = r600_dpm_get_vblank_time(rdev);
+	u32 switch_limit = 300;
+
+	/* quirks */
+	/* ASUS K70AF */
+	if ((rdev->pdev->device == 0x9553) &&
+	    (rdev->pdev->subsystem_vendor == 0x1043) &&
+	    (rdev->pdev->subsystem_device == 0x1c42))
+		switch_limit = 200;
 
-	if (vblank_time < 300)
+	if (vblank_time < switch_limit)
 		return true;
 	else
 		return false;
diff --git a/drivers/gpu/drm/radeon/rv770_smc.c b/drivers/gpu/drm/radeon/rv770_smc.c
index ab95da570215..b2a224407365 100644
--- a/drivers/gpu/drm/radeon/rv770_smc.c
+++ b/drivers/gpu/drm/radeon/rv770_smc.c
@@ -274,8 +274,8 @@ static const u8 cayman_smc_int_vectors[] =
 	0x08, 0x72, 0x08, 0x72
 };
 
-int rv770_set_smc_sram_address(struct radeon_device *rdev,
-			       u16 smc_address, u16 limit)
+static int rv770_set_smc_sram_address(struct radeon_device *rdev,
+				      u16 smc_address, u16 limit)
 {
 	u32 addr;
 
@@ -296,9 +296,10 @@ int rv770_copy_bytes_to_smc(struct radeon_device *rdev,
 			    u16 smc_start_address, const u8 *src,
 			    u16 byte_count, u16 limit)
 {
+	unsigned long flags;
 	u32 data, original_data, extra_shift;
 	u16 addr;
-	int ret;
+	int ret = 0;
 
 	if (smc_start_address & 3)
 		return -EINVAL;
@@ -307,13 +308,14 @@ int rv770_copy_bytes_to_smc(struct radeon_device *rdev,
 
 	addr = smc_start_address;
 
+	spin_lock_irqsave(&rdev->smc_idx_lock, flags);
 	while (byte_count >= 4) {
 		/* SMC address space is BE */
 		data = (src[0] << 24) | (src[1] << 16) | (src[2] << 8) | src[3];
 
 		ret = rv770_set_smc_sram_address(rdev, addr, limit);
 		if (ret)
-			return ret;
+			goto done;
 
 		WREG32(SMC_SRAM_DATA, data);
 
@@ -328,7 +330,7 @@ int rv770_copy_bytes_to_smc(struct radeon_device *rdev,
 
 		ret = rv770_set_smc_sram_address(rdev, addr, limit);
 		if (ret)
-			return ret;
+			goto done;
 
 		original_data = RREG32(SMC_SRAM_DATA);
 
@@ -346,12 +348,15 @@ int rv770_copy_bytes_to_smc(struct radeon_device *rdev,
 
 		ret = rv770_set_smc_sram_address(rdev, addr, limit);
 		if (ret)
-			return ret;
+			goto done;
 
 		WREG32(SMC_SRAM_DATA, data);
 	}
 
-	return 0;
+done:
+	spin_unlock_irqrestore(&rdev->smc_idx_lock, flags);
+
+	return ret;
 }
 
 static int rv770_program_interrupt_vectors(struct radeon_device *rdev,
@@ -461,12 +466,15 @@ PPSMC_Result rv770_wait_for_smc_inactive(struct radeon_device *rdev)
 
 static void rv770_clear_smc_sram(struct radeon_device *rdev, u16 limit)
 {
+	unsigned long flags;
 	u16 i;
 
+	spin_lock_irqsave(&rdev->smc_idx_lock, flags);
 	for (i = 0;  i < limit; i += 4) {
 		rv770_set_smc_sram_address(rdev, i, limit);
 		WREG32(SMC_SRAM_DATA, 0);
 	}
+	spin_unlock_irqrestore(&rdev->smc_idx_lock, flags);
 }
 
 int rv770_load_smc_ucode(struct radeon_device *rdev,
@@ -595,27 +603,29 @@ int rv770_load_smc_ucode(struct radeon_device *rdev,
 int rv770_read_smc_sram_dword(struct radeon_device *rdev,
 			      u16 smc_address, u32 *value, u16 limit)
 {
+	unsigned long flags;
 	int ret;
 
+	spin_lock_irqsave(&rdev->smc_idx_lock, flags);
 	ret = rv770_set_smc_sram_address(rdev, smc_address, limit);
-	if (ret)
-		return ret;
-
-	*value = RREG32(SMC_SRAM_DATA);
+	if (ret == 0)
+		*value = RREG32(SMC_SRAM_DATA);
+	spin_unlock_irqrestore(&rdev->smc_idx_lock, flags);
 
-	return 0;
+	return ret;
 }
 
 int rv770_write_smc_sram_dword(struct radeon_device *rdev,
 			       u16 smc_address, u32 value, u16 limit)
 {
+	unsigned long flags;
 	int ret;
 
+	spin_lock_irqsave(&rdev->smc_idx_lock, flags);
 	ret = rv770_set_smc_sram_address(rdev, smc_address, limit);
-	if (ret)
-		return ret;
+	if (ret == 0)
+		WREG32(SMC_SRAM_DATA, value);
+	spin_unlock_irqrestore(&rdev->smc_idx_lock, flags);
 
-	WREG32(SMC_SRAM_DATA, value);
-
-	return 0;
+	return ret;
 }
diff --git a/drivers/gpu/drm/radeon/rv770_smc.h b/drivers/gpu/drm/radeon/rv770_smc.h
index f78d92a4b325..3b2c963c4880 100644
--- a/drivers/gpu/drm/radeon/rv770_smc.h
+++ b/drivers/gpu/drm/radeon/rv770_smc.h
@@ -187,8 +187,6 @@ typedef struct RV770_SMC_STATETABLE RV770_SMC_STATETABLE;
 #define RV770_SMC_SOFT_REGISTER_uvd_enabled             0x9C
 #define RV770_SMC_SOFT_REGISTER_is_asic_lombok          0xA0
 
-int rv770_set_smc_sram_address(struct radeon_device *rdev,
-			       u16 smc_address, u16 limit);
 int rv770_copy_bytes_to_smc(struct radeon_device *rdev,
 			    u16 smc_start_address, const u8 *src,
 			    u16 byte_count, u16 limit);
diff --git a/drivers/gpu/drm/radeon/rv770d.h b/drivers/gpu/drm/radeon/rv770d.h
index 6bef2b7d601b..1ae277152cc7 100644
--- a/drivers/gpu/drm/radeon/rv770d.h
+++ b/drivers/gpu/drm/radeon/rv770d.h
@@ -852,7 +852,7 @@
 #define AFMT_VBI_PACKET_CONTROL              0x7608
 #       define AFMT_GENERIC0_UPDATE          (1 << 2)
 #define AFMT_INFOFRAME_CONTROL0              0x760c
-#       define AFMT_AUDIO_INFO_SOURCE        (1 << 6) /* 0 - sound block; 1 - hmdi regs */
+#       define AFMT_AUDIO_INFO_SOURCE        (1 << 6) /* 0 - sound block; 1 - hdmi regs */
 #       define AFMT_AUDIO_INFO_UPDATE        (1 << 7)
 #       define AFMT_MPEG_INFO_UPDATE         (1 << 10)
 #define AFMT_GENERIC0_7                      0x7610
@@ -971,7 +971,21 @@
 #       define TARGET_LINK_SPEED_MASK                     (0xf << 0)
 #       define SELECTABLE_DEEMPHASIS                      (1 << 6)
 
+/*
+ * PM4
+ */
+#define PACKET0(reg, n)	((RADEON_PACKET_TYPE0 << 30) |			\
+			 (((reg) >> 2) & 0xFFFF) |			\
+			 ((n) & 0x3FFF) << 16)
+#define PACKET3(op, n)	((RADEON_PACKET_TYPE3 << 30) |			\
+			 (((op) & 0xFF) << 8) |				\
+			 ((n) & 0x3FFF) << 16)
+
 /* UVD */
+#define UVD_GPCOM_VCPU_CMD				0xef0c
+#define UVD_GPCOM_VCPU_DATA0				0xef10
+#define UVD_GPCOM_VCPU_DATA1				0xef14
+
 #define UVD_LMI_EXT40_ADDR				0xf498
 #define UVD_VCPU_CHIP_ID				0xf4d4
 #define UVD_VCPU_CACHE_OFFSET0				0xf4d8
@@ -985,4 +999,6 @@
 #define UVD_RBC_RB_RPTR					0xf690
 #define UVD_RBC_RB_WPTR					0xf694
 
+#define UVD_CONTEXT_ID					0xf6f4
+
 #endif
diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index daa8d2df8ec5..d4652af425b8 100644
--- a/drivers/gpu/drm/radeon/si.c
+++ b/drivers/gpu/drm/radeon/si.c
@@ -68,6 +68,8 @@ MODULE_FIRMWARE("radeon/HAINAN_smc.bin");
 
 static void si_pcie_gen3_enable(struct radeon_device *rdev);
 static void si_program_aspm(struct radeon_device *rdev);
+extern void sumo_rlc_fini(struct radeon_device *rdev);
+extern int sumo_rlc_init(struct radeon_device *rdev);
 extern int r600_ih_ring_alloc(struct radeon_device *rdev);
 extern void r600_ih_ring_fini(struct radeon_device *rdev);
 extern void evergreen_fix_pci_max_read_req_size(struct radeon_device *rdev);
@@ -76,6 +78,16 @@ extern void evergreen_mc_resume(struct radeon_device *rdev, struct evergreen_mc_
 extern u32 evergreen_get_number_of_dram_channels(struct radeon_device *rdev);
 extern void evergreen_print_gpu_status_regs(struct radeon_device *rdev);
 extern bool evergreen_is_display_hung(struct radeon_device *rdev);
+extern void si_dma_vm_set_page(struct radeon_device *rdev,
+			       struct radeon_ib *ib,
+			       uint64_t pe,
+			       uint64_t addr, unsigned count,
+			       uint32_t incr, uint32_t flags);
+static void si_enable_gui_idle_interrupt(struct radeon_device *rdev,
+					 bool enable);
+static void si_fini_pg(struct radeon_device *rdev);
+static void si_fini_cg(struct radeon_device *rdev);
+static void si_rlc_stop(struct radeon_device *rdev);
 
 static const u32 verde_rlc_save_restore_register_list[] =
 {
@@ -1704,7 +1716,8 @@ static u32 dce6_line_buffer_adjust(struct radeon_device *rdev,
 				   struct drm_display_mode *mode,
 				   struct drm_display_mode *other_mode)
 {
-	u32 tmp;
+	u32 tmp, buffer_alloc, i;
+	u32 pipe_offset = radeon_crtc->crtc_id * 0x20;
 	/*
 	 * Line Buffer Setup
 	 * There are 3 line buffers, each one shared by 2 display controllers.
@@ -1719,16 +1732,30 @@ static u32 dce6_line_buffer_adjust(struct radeon_device *rdev,
 	 * non-linked crtcs for maximum line buffer allocation.
 	 */
 	if (radeon_crtc->base.enabled && mode) {
-		if (other_mode)
+		if (other_mode) {
 			tmp = 0; /* 1/2 */
-		else
+			buffer_alloc = 1;
+		} else {
 			tmp = 2; /* whole */
-	} else
+			buffer_alloc = 2;
+		}
+	} else {
 		tmp = 0;
+		buffer_alloc = 0;
+	}
 
 	WREG32(DC_LB_MEMORY_SPLIT + radeon_crtc->crtc_offset,
 	       DC_LB_MEMORY_CONFIG(tmp));
 
+	WREG32(PIPE0_DMIF_BUFFER_CONTROL + pipe_offset,
+	       DMIF_BUFFERS_ALLOCATED(buffer_alloc));
+	for (i = 0; i < rdev->usec_timeout; i++) {
+		if (RREG32(PIPE0_DMIF_BUFFER_CONTROL + pipe_offset) &
+		    DMIF_BUFFERS_ALLOCATED_COMPLETED)
+			break;
+		udelay(1);
+	}
+
 	if (radeon_crtc->base.enabled && mode) {
 		switch (tmp) {
 		case 0:
@@ -3364,16 +3391,7 @@ static int si_cp_resume(struct radeon_device *rdev)
 	u32 rb_bufsz;
 	int r;
 
-	/* Reset cp; if cp is reset, then PA, SH, VGT also need to be reset */
-	WREG32(GRBM_SOFT_RESET, (SOFT_RESET_CP |
-				 SOFT_RESET_PA |
-				 SOFT_RESET_VGT |
-				 SOFT_RESET_SPI |
-				 SOFT_RESET_SX));
-	RREG32(GRBM_SOFT_RESET);
-	mdelay(15);
-	WREG32(GRBM_SOFT_RESET, 0);
-	RREG32(GRBM_SOFT_RESET);
+	si_enable_gui_idle_interrupt(rdev, false);
 
 	WREG32(CP_SEM_WAIT_TIMER, 0x0);
 	WREG32(CP_SEM_INCOMPLETE_TIMER_CNTL, 0x0);
@@ -3387,8 +3405,8 @@ static int si_cp_resume(struct radeon_device *rdev)
 	/* ring 0 - compute and gfx */
 	/* Set ring buffer size */
 	ring = &rdev->ring[RADEON_RING_TYPE_GFX_INDEX];
-	rb_bufsz = drm_order(ring->ring_size / 8);
-	tmp = (drm_order(RADEON_GPU_PAGE_SIZE/8) << 8) | rb_bufsz;
+	rb_bufsz = order_base_2(ring->ring_size / 8);
+	tmp = (order_base_2(RADEON_GPU_PAGE_SIZE/8) << 8) | rb_bufsz;
 #ifdef __BIG_ENDIAN
 	tmp |= BUF_SWAP_32BIT;
 #endif
@@ -3420,8 +3438,8 @@ static int si_cp_resume(struct radeon_device *rdev)
 	/* ring1  - compute only */
 	/* Set ring buffer size */
 	ring = &rdev->ring[CAYMAN_RING_TYPE_CP1_INDEX];
-	rb_bufsz = drm_order(ring->ring_size / 8);
-	tmp = (drm_order(RADEON_GPU_PAGE_SIZE/8) << 8) | rb_bufsz;
+	rb_bufsz = order_base_2(ring->ring_size / 8);
+	tmp = (order_base_2(RADEON_GPU_PAGE_SIZE/8) << 8) | rb_bufsz;
 #ifdef __BIG_ENDIAN
 	tmp |= BUF_SWAP_32BIT;
 #endif
@@ -3446,8 +3464,8 @@ static int si_cp_resume(struct radeon_device *rdev)
 	/* ring2 - compute only */
 	/* Set ring buffer size */
 	ring = &rdev->ring[CAYMAN_RING_TYPE_CP2_INDEX];
-	rb_bufsz = drm_order(ring->ring_size / 8);
-	tmp = (drm_order(RADEON_GPU_PAGE_SIZE/8) << 8) | rb_bufsz;
+	rb_bufsz = order_base_2(ring->ring_size / 8);
+	tmp = (order_base_2(RADEON_GPU_PAGE_SIZE/8) << 8) | rb_bufsz;
 #ifdef __BIG_ENDIAN
 	tmp |= BUF_SWAP_32BIT;
 #endif
@@ -3490,10 +3508,12 @@ static int si_cp_resume(struct radeon_device *rdev)
 		rdev->ring[CAYMAN_RING_TYPE_CP2_INDEX].ready = false;
 	}
 
+	si_enable_gui_idle_interrupt(rdev, true);
+
 	return 0;
 }
 
-static u32 si_gpu_check_soft_reset(struct radeon_device *rdev)
+u32 si_gpu_check_soft_reset(struct radeon_device *rdev)
 {
 	u32 reset_mask = 0;
 	u32 tmp;
@@ -3591,6 +3611,13 @@ static void si_gpu_soft_reset(struct radeon_device *rdev, u32 reset_mask)
 	dev_info(rdev->dev, "  VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x%08X\n",
 		 RREG32(VM_CONTEXT1_PROTECTION_FAULT_STATUS));
 
+	/* disable PG/CG */
+	si_fini_pg(rdev);
+	si_fini_cg(rdev);
+
+	/* stop the rlc */
+	si_rlc_stop(rdev);
+
 	/* Disable CP parsing/prefetching */
 	WREG32(CP_ME_CNTL, CP_ME_HALT | CP_PFP_HALT | CP_CE_HALT);
 
@@ -3742,34 +3769,6 @@ bool si_gfx_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
 	return radeon_ring_test_lockup(rdev, ring);
 }
 
-/**
- * si_dma_is_lockup - Check if the DMA engine is locked up
- *
- * @rdev: radeon_device pointer
- * @ring: radeon_ring structure holding ring information
- *
- * Check if the async DMA engine is locked up.
- * Returns true if the engine appears to be locked up, false if not.
- */
-bool si_dma_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
-{
-	u32 reset_mask = si_gpu_check_soft_reset(rdev);
-	u32 mask;
-
-	if (ring->idx == R600_RING_TYPE_DMA_INDEX)
-		mask = RADEON_RESET_DMA;
-	else
-		mask = RADEON_RESET_DMA1;
-
-	if (!(reset_mask & mask)) {
-		radeon_ring_lockup_update(ring);
-		return false;
-	}
-	/* force ring activities */
-	radeon_ring_force_activity(rdev, ring);
-	return radeon_ring_test_lockup(rdev, ring);
-}
-
 /* MC */
 static void si_mc_program(struct radeon_device *rdev)
 {
@@ -4083,13 +4082,64 @@ static int si_vm_packet3_ce_check(struct radeon_device *rdev,
 	return 0;
 }
 
+static int si_vm_packet3_cp_dma_check(u32 *ib, u32 idx)
+{
+	u32 start_reg, reg, i;
+	u32 command = ib[idx + 4];
+	u32 info = ib[idx + 1];
+	u32 idx_value = ib[idx];
+	if (command & PACKET3_CP_DMA_CMD_SAS) {
+		/* src address space is register */
+		if (((info & 0x60000000) >> 29) == 0) {
+			start_reg = idx_value << 2;
+			if (command & PACKET3_CP_DMA_CMD_SAIC) {
+				reg = start_reg;
+				if (!si_vm_reg_valid(reg)) {
+					DRM_ERROR("CP DMA Bad SRC register\n");
+					return -EINVAL;
+				}
+			} else {
+				for (i = 0; i < (command & 0x1fffff); i++) {
+					reg = start_reg + (4 * i);
+					if (!si_vm_reg_valid(reg)) {
+						DRM_ERROR("CP DMA Bad SRC register\n");
+						return -EINVAL;
+					}
+				}
+			}
+		}
+	}
+	if (command & PACKET3_CP_DMA_CMD_DAS) {
+		/* dst address space is register */
+		if (((info & 0x00300000) >> 20) == 0) {
+			start_reg = ib[idx + 2];
+			if (command & PACKET3_CP_DMA_CMD_DAIC) {
+				reg = start_reg;
+				if (!si_vm_reg_valid(reg)) {
+					DRM_ERROR("CP DMA Bad DST register\n");
+					return -EINVAL;
+				}
+			} else {
+				for (i = 0; i < (command & 0x1fffff); i++) {
+					reg = start_reg + (4 * i);
+				if (!si_vm_reg_valid(reg)) {
+						DRM_ERROR("CP DMA Bad DST register\n");
+						return -EINVAL;
+					}
+				}
+			}
+		}
+	}
+	return 0;
+}
+
 static int si_vm_packet3_gfx_check(struct radeon_device *rdev,
 				   u32 *ib, struct radeon_cs_packet *pkt)
 {
+	int r;
 	u32 idx = pkt->idx + 1;
 	u32 idx_value = ib[idx];
 	u32 start_reg, end_reg, reg, i;
-	u32 command, info;
 
 	switch (pkt->opcode) {
 	case PACKET3_NOP:
@@ -4190,50 +4240,9 @@ static int si_vm_packet3_gfx_check(struct radeon_device *rdev,
 		}
 		break;
 	case PACKET3_CP_DMA:
-		command = ib[idx + 4];
-		info = ib[idx + 1];
-		if (command & PACKET3_CP_DMA_CMD_SAS) {
-			/* src address space is register */
-			if (((info & 0x60000000) >> 29) == 0) {
-				start_reg = idx_value << 2;
-				if (command & PACKET3_CP_DMA_CMD_SAIC) {
-					reg = start_reg;
-					if (!si_vm_reg_valid(reg)) {
-						DRM_ERROR("CP DMA Bad SRC register\n");
-						return -EINVAL;
-					}
-				} else {
-					for (i = 0; i < (command & 0x1fffff); i++) {
-						reg = start_reg + (4 * i);
-						if (!si_vm_reg_valid(reg)) {
-							DRM_ERROR("CP DMA Bad SRC register\n");
-							return -EINVAL;
-						}
-					}
-				}
-			}
-		}
-		if (command & PACKET3_CP_DMA_CMD_DAS) {
-			/* dst address space is register */
-			if (((info & 0x00300000) >> 20) == 0) {
-				start_reg = ib[idx + 2];
-				if (command & PACKET3_CP_DMA_CMD_DAIC) {
-					reg = start_reg;
-					if (!si_vm_reg_valid(reg)) {
-						DRM_ERROR("CP DMA Bad DST register\n");
-						return -EINVAL;
-					}
-				} else {
-					for (i = 0; i < (command & 0x1fffff); i++) {
-						reg = start_reg + (4 * i);
-						if (!si_vm_reg_valid(reg)) {
-							DRM_ERROR("CP DMA Bad DST register\n");
-							return -EINVAL;
-						}
-					}
-				}
-			}
-		}
+		r = si_vm_packet3_cp_dma_check(ib, idx);
+		if (r)
+			return r;
 		break;
 	default:
 		DRM_ERROR("Invalid GFX packet3: 0x%x\n", pkt->opcode);
@@ -4245,6 +4254,7 @@ static int si_vm_packet3_gfx_check(struct radeon_device *rdev,
 static int si_vm_packet3_compute_check(struct radeon_device *rdev,
 				       u32 *ib, struct radeon_cs_packet *pkt)
 {
+	int r;
 	u32 idx = pkt->idx + 1;
 	u32 idx_value = ib[idx];
 	u32 start_reg, reg, i;
@@ -4317,6 +4327,11 @@ static int si_vm_packet3_compute_check(struct radeon_device *rdev,
 				return -EINVAL;
 		}
 		break;
+	case PACKET3_CP_DMA:
+		r = si_vm_packet3_cp_dma_check(ib, idx);
+		if (r)
+			return r;
+		break;
 	default:
 		DRM_ERROR("Invalid Compute packet3: 0x%x\n", pkt->opcode);
 		return -EINVAL;
@@ -4708,58 +4723,7 @@ void si_vm_set_page(struct radeon_device *rdev,
 		}
 	} else {
 		/* DMA */
-		if (flags & RADEON_VM_PAGE_SYSTEM) {
-			while (count) {
-				ndw = count * 2;
-				if (ndw > 0xFFFFE)
-					ndw = 0xFFFFE;
-
-				/* for non-physically contiguous pages (system) */
-				ib->ptr[ib->length_dw++] = DMA_PACKET(DMA_PACKET_WRITE, 0, 0, 0, ndw);
-				ib->ptr[ib->length_dw++] = pe;
-				ib->ptr[ib->length_dw++] = upper_32_bits(pe) & 0xff;
-				for (; ndw > 0; ndw -= 2, --count, pe += 8) {
-					if (flags & RADEON_VM_PAGE_SYSTEM) {
-						value = radeon_vm_map_gart(rdev, addr);
-						value &= 0xFFFFFFFFFFFFF000ULL;
-					} else if (flags & RADEON_VM_PAGE_VALID) {
-						value = addr;
-					} else {
-						value = 0;
-					}
-					addr += incr;
-					value |= r600_flags;
-					ib->ptr[ib->length_dw++] = value;
-					ib->ptr[ib->length_dw++] = upper_32_bits(value);
-				}
-			}
-		} else {
-			while (count) {
-				ndw = count * 2;
-				if (ndw > 0xFFFFE)
-					ndw = 0xFFFFE;
-
-				if (flags & RADEON_VM_PAGE_VALID)
-					value = addr;
-				else
-					value = 0;
-				/* for physically contiguous pages (vram) */
-				ib->ptr[ib->length_dw++] = DMA_PTE_PDE_PACKET(ndw);
-				ib->ptr[ib->length_dw++] = pe; /* dst addr */
-				ib->ptr[ib->length_dw++] = upper_32_bits(pe) & 0xff;
-				ib->ptr[ib->length_dw++] = r600_flags; /* mask */
-				ib->ptr[ib->length_dw++] = 0;
-				ib->ptr[ib->length_dw++] = value; /* value */
-				ib->ptr[ib->length_dw++] = upper_32_bits(value);
-				ib->ptr[ib->length_dw++] = incr; /* increment size */
-				ib->ptr[ib->length_dw++] = 0;
-				pe += ndw * 4;
-				addr += (ndw / 2) * incr;
-				count -= ndw / 2;
-			}
-		}
-		while (ib->length_dw & 0x7)
-			ib->ptr[ib->length_dw++] = DMA_PACKET(DMA_PACKET_NOP, 0, 0, 0, 0);
+		si_dma_vm_set_page(rdev, ib, pe, addr, count, incr, flags);
 	}
 }
 
@@ -4806,32 +4770,6 @@ void si_vm_flush(struct radeon_device *rdev, int ridx, struct radeon_vm *vm)
 	radeon_ring_write(ring, 0x0);
 }
 
-void si_dma_vm_flush(struct radeon_device *rdev, int ridx, struct radeon_vm *vm)
-{
-	struct radeon_ring *ring = &rdev->ring[ridx];
-
-	if (vm == NULL)
-		return;
-
-	radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_SRBM_WRITE, 0, 0, 0, 0));
-	if (vm->id < 8) {
-		radeon_ring_write(ring, (0xf << 16) | ((VM_CONTEXT0_PAGE_TABLE_BASE_ADDR + (vm->id << 2)) >> 2));
-	} else {
-		radeon_ring_write(ring, (0xf << 16) | ((VM_CONTEXT8_PAGE_TABLE_BASE_ADDR + ((vm->id - 8) << 2)) >> 2));
-	}
-	radeon_ring_write(ring, vm->pd_gpu_addr >> 12);
-
-	/* flush hdp cache */
-	radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_SRBM_WRITE, 0, 0, 0, 0));
-	radeon_ring_write(ring, (0xf << 16) | (HDP_MEM_COHERENCY_FLUSH_CNTL >> 2));
-	radeon_ring_write(ring, 1);
-
-	/* bits 0-7 are the VM contexts0-7 */
-	radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_SRBM_WRITE, 0, 0, 0, 0));
-	radeon_ring_write(ring, (0xf << 16) | (VM_INVALIDATE_REQUEST >> 2));
-	radeon_ring_write(ring, 1 << vm->id);
-}
-
 /*
  *  Power and clock gating
  */
@@ -4899,7 +4837,7 @@ static void si_set_uvd_dcm(struct radeon_device *rdev,
 	WREG32_UVD_CTX(UVD_CGC_CTRL2, tmp2);
 }
 
-static void si_init_uvd_internal_cg(struct radeon_device *rdev)
+void si_init_uvd_internal_cg(struct radeon_device *rdev)
 {
 	bool hw_mode = true;
 
@@ -4942,7 +4880,7 @@ static void si_enable_dma_pg(struct radeon_device *rdev, bool enable)
 	u32 data, orig;
 
 	orig = data = RREG32(DMA_PG);
-	if (enable)
+	if (enable && (rdev->pg_flags & RADEON_PG_SUPPORT_SDMA))
 		data |= PG_CNTL_ENABLE;
 	else
 		data &= ~PG_CNTL_ENABLE;
@@ -4966,7 +4904,7 @@ static void si_enable_gfx_cgpg(struct radeon_device *rdev,
 {
 	u32 tmp;
 
-	if (enable) {
+	if (enable && (rdev->pg_flags & RADEON_PG_SUPPORT_GFX_PG)) {
 		tmp = RLC_PUD(0x10) | RLC_PDD(0x10) | RLC_TTPD(0x10) | RLC_MSD(0x10);
 		WREG32(RLC_TTOP_D, tmp);
 
@@ -5069,9 +5007,9 @@ static void si_enable_cgcg(struct radeon_device *rdev,
 
 	orig = data = RREG32(RLC_CGCG_CGLS_CTRL);
 
-	si_enable_gui_idle_interrupt(rdev, enable);
+	if (enable && (rdev->cg_flags & RADEON_CG_SUPPORT_GFX_CGCG)) {
+		si_enable_gui_idle_interrupt(rdev, true);
 
-	if (enable) {
 		WREG32(RLC_GCPM_GENERAL_3, 0x00000080);
 
 		tmp = si_halt_rlc(rdev);
@@ -5088,6 +5026,8 @@ static void si_enable_cgcg(struct radeon_device *rdev,
 
 		data |= CGCG_EN | CGLS_EN;
 	} else {
+		si_enable_gui_idle_interrupt(rdev, false);
+
 		RREG32(CB_CGTT_SCLK_CTRL);
 		RREG32(CB_CGTT_SCLK_CTRL);
 		RREG32(CB_CGTT_SCLK_CTRL);
@@ -5105,16 +5045,18 @@ static void si_enable_mgcg(struct radeon_device *rdev,
 {
 	u32 data, orig, tmp = 0;
 
-	if (enable) {
+	if (enable && (rdev->cg_flags & RADEON_CG_SUPPORT_GFX_MGCG)) {
 		orig = data = RREG32(CGTS_SM_CTRL_REG);
 		data = 0x96940200;
 		if (orig != data)
 			WREG32(CGTS_SM_CTRL_REG, data);
 
-		orig = data = RREG32(CP_MEM_SLP_CNTL);
-		data |= CP_MEM_LS_EN;
-		if (orig != data)
-			WREG32(CP_MEM_SLP_CNTL, data);
+		if (rdev->cg_flags & RADEON_CG_SUPPORT_GFX_CP_LS) {
+			orig = data = RREG32(CP_MEM_SLP_CNTL);
+			data |= CP_MEM_LS_EN;
+			if (orig != data)
+				WREG32(CP_MEM_SLP_CNTL, data);
+		}
 
 		orig = data = RREG32(RLC_CGTT_MGCG_OVERRIDE);
 		data &= 0xffffffc0;
@@ -5159,7 +5101,7 @@ static void si_enable_uvd_mgcg(struct radeon_device *rdev,
 {
 	u32 orig, data, tmp;
 
-	if (enable) {
+	if (enable && (rdev->cg_flags & RADEON_CG_SUPPORT_UVD_MGCG)) {
 		tmp = RREG32_UVD_CTX(UVD_CGC_MEM_CTRL);
 		tmp |= 0x3fff;
 		WREG32_UVD_CTX(UVD_CGC_MEM_CTRL, tmp);
@@ -5207,7 +5149,7 @@ static void si_enable_mc_ls(struct radeon_device *rdev,
 
 	for (i = 0; i < ARRAY_SIZE(mc_cg_registers); i++) {
 		orig = data = RREG32(mc_cg_registers[i]);
-		if (enable)
+		if (enable && (rdev->cg_flags & RADEON_CG_SUPPORT_MC_LS))
 			data |= MC_LS_ENABLE;
 		else
 			data &= ~MC_LS_ENABLE;
@@ -5216,226 +5158,297 @@ static void si_enable_mc_ls(struct radeon_device *rdev,
 	}
 }
 
-
-static void si_init_cg(struct radeon_device *rdev)
+static void si_enable_mc_mgcg(struct radeon_device *rdev,
+			       bool enable)
 {
-	si_enable_mgcg(rdev, true);
-	si_enable_cgcg(rdev, false);
-	/* disable MC LS on Tahiti */
-	if (rdev->family == CHIP_TAHITI)
-		si_enable_mc_ls(rdev, false);
-	if (rdev->has_uvd) {
-		si_enable_uvd_mgcg(rdev, true);
-		si_init_uvd_internal_cg(rdev);
+	int i;
+	u32 orig, data;
+
+	for (i = 0; i < ARRAY_SIZE(mc_cg_registers); i++) {
+		orig = data = RREG32(mc_cg_registers[i]);
+		if (enable && (rdev->cg_flags & RADEON_CG_SUPPORT_MC_MGCG))
+			data |= MC_CG_ENABLE;
+		else
+			data &= ~MC_CG_ENABLE;
+		if (data != orig)
+			WREG32(mc_cg_registers[i], data);
 	}
 }
 
-static void si_fini_cg(struct radeon_device *rdev)
+static void si_enable_dma_mgcg(struct radeon_device *rdev,
+			       bool enable)
 {
-	if (rdev->has_uvd)
-		si_enable_uvd_mgcg(rdev, false);
-	si_enable_cgcg(rdev, false);
-	si_enable_mgcg(rdev, false);
-}
+	u32 orig, data, offset;
+	int i;
 
-static void si_init_pg(struct radeon_device *rdev)
-{
-	bool has_pg = false;
-#if 0
-	/* only cape verde supports PG */
-	if (rdev->family == CHIP_VERDE)
-		has_pg = true;
-#endif
-	if (has_pg) {
-		si_init_ao_cu_mask(rdev);
-		si_init_dma_pg(rdev);
-		si_enable_dma_pg(rdev, true);
-		si_init_gfx_cgpg(rdev);
-		si_enable_gfx_cgpg(rdev, true);
+	if (enable && (rdev->cg_flags & RADEON_CG_SUPPORT_SDMA_MGCG)) {
+		for (i = 0; i < 2; i++) {
+			if (i == 0)
+				offset = DMA0_REGISTER_OFFSET;
+			else
+				offset = DMA1_REGISTER_OFFSET;
+			orig = data = RREG32(DMA_POWER_CNTL + offset);
+			data &= ~MEM_POWER_OVERRIDE;
+			if (data != orig)
+				WREG32(DMA_POWER_CNTL + offset, data);
+			WREG32(DMA_CLK_CTRL + offset, 0x00000100);
+		}
 	} else {
-		WREG32(RLC_SAVE_AND_RESTORE_BASE, rdev->rlc.save_restore_gpu_addr >> 8);
-		WREG32(RLC_CLEAR_STATE_RESTORE_BASE, rdev->rlc.clear_state_gpu_addr >> 8);
+		for (i = 0; i < 2; i++) {
+			if (i == 0)
+				offset = DMA0_REGISTER_OFFSET;
+			else
+				offset = DMA1_REGISTER_OFFSET;
+			orig = data = RREG32(DMA_POWER_CNTL + offset);
+			data |= MEM_POWER_OVERRIDE;
+			if (data != orig)
+				WREG32(DMA_POWER_CNTL + offset, data);
+
+			orig = data = RREG32(DMA_CLK_CTRL + offset);
+			data = 0xff000000;
+			if (data != orig)
+				WREG32(DMA_CLK_CTRL + offset, data);
+		}
 	}
 }
 
-static void si_fini_pg(struct radeon_device *rdev)
+static void si_enable_bif_mgls(struct radeon_device *rdev,
+			       bool enable)
 {
-	bool has_pg = false;
+	u32 orig, data;
 
-	/* only cape verde supports PG */
-	if (rdev->family == CHIP_VERDE)
-		has_pg = true;
+	orig = data = RREG32_PCIE(PCIE_CNTL2);
 
-	if (has_pg) {
-		si_enable_dma_pg(rdev, false);
-		si_enable_gfx_cgpg(rdev, false);
-	}
+	if (enable && (rdev->cg_flags & RADEON_CG_SUPPORT_BIF_LS))
+		data |= SLV_MEM_LS_EN | MST_MEM_LS_EN |
+			REPLAY_MEM_LS_EN | SLV_MEM_AGGRESSIVE_LS_EN;
+	else
+		data &= ~(SLV_MEM_LS_EN | MST_MEM_LS_EN |
+			  REPLAY_MEM_LS_EN | SLV_MEM_AGGRESSIVE_LS_EN);
+
+	if (orig != data)
+		WREG32_PCIE(PCIE_CNTL2, data);
 }
 
-/*
- * RLC
- */
-void si_rlc_fini(struct radeon_device *rdev)
+static void si_enable_hdp_mgcg(struct radeon_device *rdev,
+			       bool enable)
 {
-	int r;
-
-	/* save restore block */
-	if (rdev->rlc.save_restore_obj) {
-		r = radeon_bo_reserve(rdev->rlc.save_restore_obj, false);
-		if (unlikely(r != 0))
-			dev_warn(rdev->dev, "(%d) reserve RLC sr bo failed\n", r);
-		radeon_bo_unpin(rdev->rlc.save_restore_obj);
-		radeon_bo_unreserve(rdev->rlc.save_restore_obj);
+	u32 orig, data;
 
-		radeon_bo_unref(&rdev->rlc.save_restore_obj);
-		rdev->rlc.save_restore_obj = NULL;
-	}
+	orig = data = RREG32(HDP_HOST_PATH_CNTL);
 
-	/* clear state block */
-	if (rdev->rlc.clear_state_obj) {
-		r = radeon_bo_reserve(rdev->rlc.clear_state_obj, false);
-		if (unlikely(r != 0))
-			dev_warn(rdev->dev, "(%d) reserve RLC c bo failed\n", r);
-		radeon_bo_unpin(rdev->rlc.clear_state_obj);
-		radeon_bo_unreserve(rdev->rlc.clear_state_obj);
+	if (enable && (rdev->cg_flags & RADEON_CG_SUPPORT_HDP_MGCG))
+		data &= ~CLOCK_GATING_DIS;
+	else
+		data |= CLOCK_GATING_DIS;
 
-		radeon_bo_unref(&rdev->rlc.clear_state_obj);
-		rdev->rlc.clear_state_obj = NULL;
-	}
+	if (orig != data)
+		WREG32(HDP_HOST_PATH_CNTL, data);
 }
 
-#define RLC_CLEAR_STATE_END_MARKER          0x00000001
-
-int si_rlc_init(struct radeon_device *rdev)
+static void si_enable_hdp_ls(struct radeon_device *rdev,
+			     bool enable)
 {
-	volatile u32 *dst_ptr;
-	u32 dws, data, i, j, k, reg_num;
-	u32 reg_list_num, reg_list_hdr_blk_index, reg_list_blk_index;
-	u64 reg_list_mc_addr;
-	const struct cs_section_def *cs_data = si_cs_data;
-	int r;
+	u32 orig, data;
 
-	/* save restore block */
-	if (rdev->rlc.save_restore_obj == NULL) {
-		r = radeon_bo_create(rdev, RADEON_GPU_PAGE_SIZE, PAGE_SIZE, true,
-				     RADEON_GEM_DOMAIN_VRAM, NULL,
-				     &rdev->rlc.save_restore_obj);
-		if (r) {
-			dev_warn(rdev->dev, "(%d) create RLC sr bo failed\n", r);
-			return r;
+	orig = data = RREG32(HDP_MEM_POWER_LS);
+
+	if (enable && (rdev->cg_flags & RADEON_CG_SUPPORT_HDP_LS))
+		data |= HDP_LS_ENABLE;
+	else
+		data &= ~HDP_LS_ENABLE;
+
+	if (orig != data)
+		WREG32(HDP_MEM_POWER_LS, data);
+}
+
+void si_update_cg(struct radeon_device *rdev,
+		  u32 block, bool enable)
+{
+	if (block & RADEON_CG_BLOCK_GFX) {
+		si_enable_gui_idle_interrupt(rdev, false);
+		/* order matters! */
+		if (enable) {
+			si_enable_mgcg(rdev, true);
+			si_enable_cgcg(rdev, true);
+		} else {
+			si_enable_cgcg(rdev, false);
+			si_enable_mgcg(rdev, false);
 		}
+		si_enable_gui_idle_interrupt(rdev, true);
 	}
 
-	r = radeon_bo_reserve(rdev->rlc.save_restore_obj, false);
-	if (unlikely(r != 0)) {
-		si_rlc_fini(rdev);
-		return r;
+	if (block & RADEON_CG_BLOCK_MC) {
+		si_enable_mc_mgcg(rdev, enable);
+		si_enable_mc_ls(rdev, enable);
 	}
-	r = radeon_bo_pin(rdev->rlc.save_restore_obj, RADEON_GEM_DOMAIN_VRAM,
-			  &rdev->rlc.save_restore_gpu_addr);
-	if (r) {
-		radeon_bo_unreserve(rdev->rlc.save_restore_obj);
-		dev_warn(rdev->dev, "(%d) pin RLC sr bo failed\n", r);
-		si_rlc_fini(rdev);
-		return r;
+
+	if (block & RADEON_CG_BLOCK_SDMA) {
+		si_enable_dma_mgcg(rdev, enable);
 	}
 
-	if (rdev->family == CHIP_VERDE) {
-		r = radeon_bo_kmap(rdev->rlc.save_restore_obj, (void **)&rdev->rlc.sr_ptr);
-		if (r) {
-			dev_warn(rdev->dev, "(%d) map RLC sr bo failed\n", r);
-			si_rlc_fini(rdev);
-		return r;
-		}
-		/* write the sr buffer */
-		dst_ptr = rdev->rlc.sr_ptr;
-		for (i = 0; i < ARRAY_SIZE(verde_rlc_save_restore_register_list); i++) {
-			dst_ptr[i] = verde_rlc_save_restore_register_list[i];
-		}
-		radeon_bo_kunmap(rdev->rlc.save_restore_obj);
+	if (block & RADEON_CG_BLOCK_BIF) {
+		si_enable_bif_mgls(rdev, enable);
 	}
-	radeon_bo_unreserve(rdev->rlc.save_restore_obj);
 
-	/* clear state block */
-	reg_list_num = 0;
-	dws = 0;
-	for (i = 0; cs_data[i].section != NULL; i++) {
-		for (j = 0; cs_data[i].section[j].extent != NULL; j++) {
-			reg_list_num++;
-			dws += cs_data[i].section[j].reg_count;
+	if (block & RADEON_CG_BLOCK_UVD) {
+		if (rdev->has_uvd) {
+			si_enable_uvd_mgcg(rdev, enable);
 		}
 	}
-	reg_list_blk_index = (3 * reg_list_num + 2);
-	dws += reg_list_blk_index;
 
-	if (rdev->rlc.clear_state_obj == NULL) {
-		r = radeon_bo_create(rdev, dws * 4, PAGE_SIZE, true,
-				     RADEON_GEM_DOMAIN_VRAM, NULL, &rdev->rlc.clear_state_obj);
-		if (r) {
-			dev_warn(rdev->dev, "(%d) create RLC c bo failed\n", r);
-			si_rlc_fini(rdev);
-			return r;
-		}
+	if (block & RADEON_CG_BLOCK_HDP) {
+		si_enable_hdp_mgcg(rdev, enable);
+		si_enable_hdp_ls(rdev, enable);
 	}
-	r = radeon_bo_reserve(rdev->rlc.clear_state_obj, false);
-	if (unlikely(r != 0)) {
-		si_rlc_fini(rdev);
-		return r;
+}
+
+static void si_init_cg(struct radeon_device *rdev)
+{
+	si_update_cg(rdev, (RADEON_CG_BLOCK_GFX |
+			    RADEON_CG_BLOCK_MC |
+			    RADEON_CG_BLOCK_SDMA |
+			    RADEON_CG_BLOCK_BIF |
+			    RADEON_CG_BLOCK_HDP), true);
+	if (rdev->has_uvd) {
+		si_update_cg(rdev, RADEON_CG_BLOCK_UVD, true);
+		si_init_uvd_internal_cg(rdev);
 	}
-	r = radeon_bo_pin(rdev->rlc.clear_state_obj, RADEON_GEM_DOMAIN_VRAM,
-			  &rdev->rlc.clear_state_gpu_addr);
-	if (r) {
+}
 
-		radeon_bo_unreserve(rdev->rlc.clear_state_obj);
-		dev_warn(rdev->dev, "(%d) pin RLC c bo failed\n", r);
-		si_rlc_fini(rdev);
-		return r;
+static void si_fini_cg(struct radeon_device *rdev)
+{
+	if (rdev->has_uvd) {
+		si_update_cg(rdev, RADEON_CG_BLOCK_UVD, false);
 	}
-	r = radeon_bo_kmap(rdev->rlc.clear_state_obj, (void **)&rdev->rlc.cs_ptr);
-	if (r) {
-		dev_warn(rdev->dev, "(%d) map RLC c bo failed\n", r);
-		si_rlc_fini(rdev);
-		return r;
+	si_update_cg(rdev, (RADEON_CG_BLOCK_GFX |
+			    RADEON_CG_BLOCK_MC |
+			    RADEON_CG_BLOCK_SDMA |
+			    RADEON_CG_BLOCK_BIF |
+			    RADEON_CG_BLOCK_HDP), false);
+}
+
+u32 si_get_csb_size(struct radeon_device *rdev)
+{
+	u32 count = 0;
+	const struct cs_section_def *sect = NULL;
+	const struct cs_extent_def *ext = NULL;
+
+	if (rdev->rlc.cs_data == NULL)
+		return 0;
+
+	/* begin clear state */
+	count += 2;
+	/* context control state */
+	count += 3;
+
+	for (sect = rdev->rlc.cs_data; sect->section != NULL; ++sect) {
+		for (ext = sect->section; ext->extent != NULL; ++ext) {
+			if (sect->id == SECT_CONTEXT)
+				count += 2 + ext->reg_count;
+			else
+				return 0;
+		}
 	}
-	/* set up the cs buffer */
-	dst_ptr = rdev->rlc.cs_ptr;
-	reg_list_hdr_blk_index = 0;
-	reg_list_mc_addr = rdev->rlc.clear_state_gpu_addr + (reg_list_blk_index * 4);
-	data = upper_32_bits(reg_list_mc_addr);
-	dst_ptr[reg_list_hdr_blk_index] = data;
-	reg_list_hdr_blk_index++;
-	for (i = 0; cs_data[i].section != NULL; i++) {
-		for (j = 0; cs_data[i].section[j].extent != NULL; j++) {
-			reg_num = cs_data[i].section[j].reg_count;
-			data = reg_list_mc_addr & 0xffffffff;
-			dst_ptr[reg_list_hdr_blk_index] = data;
-			reg_list_hdr_blk_index++;
-
-			data = (cs_data[i].section[j].reg_index * 4) & 0xffffffff;
-			dst_ptr[reg_list_hdr_blk_index] = data;
-			reg_list_hdr_blk_index++;
-
-			data = 0x08000000 | (reg_num * 4);
-			dst_ptr[reg_list_hdr_blk_index] = data;
-			reg_list_hdr_blk_index++;
-
-			for (k = 0; k < reg_num; k++) {
-				data = cs_data[i].section[j].extent[k];
-				dst_ptr[reg_list_blk_index + k] = data;
+	/* pa_sc_raster_config */
+	count += 3;
+	/* end clear state */
+	count += 2;
+	/* clear state */
+	count += 2;
+
+	return count;
+}
+
+void si_get_csb_buffer(struct radeon_device *rdev, volatile u32 *buffer)
+{
+	u32 count = 0, i;
+	const struct cs_section_def *sect = NULL;
+	const struct cs_extent_def *ext = NULL;
+
+	if (rdev->rlc.cs_data == NULL)
+		return;
+	if (buffer == NULL)
+		return;
+
+	buffer[count++] = PACKET3(PACKET3_PREAMBLE_CNTL, 0);
+	buffer[count++] = PACKET3_PREAMBLE_BEGIN_CLEAR_STATE;
+
+	buffer[count++] = PACKET3(PACKET3_CONTEXT_CONTROL, 1);
+	buffer[count++] = 0x80000000;
+	buffer[count++] = 0x80000000;
+
+	for (sect = rdev->rlc.cs_data; sect->section != NULL; ++sect) {
+		for (ext = sect->section; ext->extent != NULL; ++ext) {
+			if (sect->id == SECT_CONTEXT) {
+				buffer[count++] = PACKET3(PACKET3_SET_CONTEXT_REG, ext->reg_count);
+				buffer[count++] = ext->reg_index - 0xa000;
+				for (i = 0; i < ext->reg_count; i++)
+					buffer[count++] = ext->extent[i];
+			} else {
+				return;
 			}
-			reg_list_mc_addr += reg_num * 4;
-			reg_list_blk_index += reg_num;
 		}
 	}
-	dst_ptr[reg_list_hdr_blk_index] = RLC_CLEAR_STATE_END_MARKER;
 
-	radeon_bo_kunmap(rdev->rlc.clear_state_obj);
-	radeon_bo_unreserve(rdev->rlc.clear_state_obj);
+	buffer[count++] = PACKET3(PACKET3_SET_CONTEXT_REG, 1);
+	buffer[count++] = PA_SC_RASTER_CONFIG - PACKET3_SET_CONTEXT_REG_START;
+	switch (rdev->family) {
+	case CHIP_TAHITI:
+	case CHIP_PITCAIRN:
+		buffer[count++] = 0x2a00126a;
+		break;
+	case CHIP_VERDE:
+		buffer[count++] = 0x0000124a;
+		break;
+	case CHIP_OLAND:
+		buffer[count++] = 0x00000082;
+		break;
+	case CHIP_HAINAN:
+		buffer[count++] = 0x00000000;
+		break;
+	default:
+		buffer[count++] = 0x00000000;
+		break;
+	}
 
-	return 0;
+	buffer[count++] = PACKET3(PACKET3_PREAMBLE_CNTL, 0);
+	buffer[count++] = PACKET3_PREAMBLE_END_CLEAR_STATE;
+
+	buffer[count++] = PACKET3(PACKET3_CLEAR_STATE, 0);
+	buffer[count++] = 0;
+}
+
+static void si_init_pg(struct radeon_device *rdev)
+{
+	if (rdev->pg_flags) {
+		if (rdev->pg_flags & RADEON_PG_SUPPORT_SDMA) {
+			si_init_dma_pg(rdev);
+		}
+		si_init_ao_cu_mask(rdev);
+		if (rdev->pg_flags & RADEON_PG_SUPPORT_GFX_PG) {
+			si_init_gfx_cgpg(rdev);
+		}
+		si_enable_dma_pg(rdev, true);
+		si_enable_gfx_cgpg(rdev, true);
+	} else {
+		WREG32(RLC_SAVE_AND_RESTORE_BASE, rdev->rlc.save_restore_gpu_addr >> 8);
+		WREG32(RLC_CLEAR_STATE_RESTORE_BASE, rdev->rlc.clear_state_gpu_addr >> 8);
+	}
+}
+
+static void si_fini_pg(struct radeon_device *rdev)
+{
+	if (rdev->pg_flags) {
+		si_enable_dma_pg(rdev, false);
+		si_enable_gfx_cgpg(rdev, false);
+	}
 }
 
-static void si_rlc_reset(struct radeon_device *rdev)
+/*
+ * RLC
+ */
+void si_rlc_reset(struct radeon_device *rdev)
 {
 	u32 tmp = RREG32(GRBM_SOFT_RESET);
 
@@ -5565,7 +5578,9 @@ static void si_disable_interrupt_state(struct radeon_device *rdev)
 {
 	u32 tmp;
 
-	WREG32(CP_INT_CNTL_RING0, CNTX_BUSY_INT_ENABLE | CNTX_EMPTY_INT_ENABLE);
+	tmp = RREG32(CP_INT_CNTL_RING0) &
+		(CNTX_BUSY_INT_ENABLE | CNTX_EMPTY_INT_ENABLE);
+	WREG32(CP_INT_CNTL_RING0, tmp);
 	WREG32(CP_INT_CNTL_RING1, 0);
 	WREG32(CP_INT_CNTL_RING2, 0);
 	tmp = RREG32(DMA_CNTL + DMA0_REGISTER_OFFSET) & ~TRAP_ENABLE;
@@ -5651,7 +5666,7 @@ static int si_irq_init(struct radeon_device *rdev)
 	WREG32(INTERRUPT_CNTL, interrupt_cntl);
 
 	WREG32(IH_RB_BASE, rdev->ih.gpu_addr >> 8);
-	rb_bufsz = drm_order(rdev->ih.ring_size / 4);
+	rb_bufsz = order_base_2(rdev->ih.ring_size / 4);
 
 	ih_rb_cntl = (IH_WPTR_OVERFLOW_ENABLE |
 		      IH_WPTR_OVERFLOW_CLEAR |
@@ -5690,7 +5705,7 @@ static int si_irq_init(struct radeon_device *rdev)
 
 int si_irq_set(struct radeon_device *rdev)
 {
-	u32 cp_int_cntl = CNTX_BUSY_INT_ENABLE | CNTX_EMPTY_INT_ENABLE;
+	u32 cp_int_cntl;
 	u32 cp_int_cntl1 = 0, cp_int_cntl2 = 0;
 	u32 crtc1 = 0, crtc2 = 0, crtc3 = 0, crtc4 = 0, crtc5 = 0, crtc6 = 0;
 	u32 hpd1 = 0, hpd2 = 0, hpd3 = 0, hpd4 = 0, hpd5 = 0, hpd6 = 0;
@@ -5711,6 +5726,9 @@ int si_irq_set(struct radeon_device *rdev)
 		return 0;
 	}
 
+	cp_int_cntl = RREG32(CP_INT_CNTL_RING0) &
+		(CNTX_BUSY_INT_ENABLE | CNTX_EMPTY_INT_ENABLE);
+
 	if (!ASIC_IS_NODCE(rdev)) {
 		hpd1 = RREG32(DC_HPD1_INT_CONTROL) & ~DC_HPDx_INT_EN;
 		hpd2 = RREG32(DC_HPD2_INT_CONTROL) & ~DC_HPDx_INT_EN;
@@ -6335,80 +6353,6 @@ restart_ih:
 	return IRQ_HANDLED;
 }
 
-/**
- * si_copy_dma - copy pages using the DMA engine
- *
- * @rdev: radeon_device pointer
- * @src_offset: src GPU address
- * @dst_offset: dst GPU address
- * @num_gpu_pages: number of GPU pages to xfer
- * @fence: radeon fence object
- *
- * Copy GPU paging using the DMA engine (SI).
- * Used by the radeon ttm implementation to move pages if
- * registered as the asic copy callback.
- */
-int si_copy_dma(struct radeon_device *rdev,
-		uint64_t src_offset, uint64_t dst_offset,
-		unsigned num_gpu_pages,
-		struct radeon_fence **fence)
-{
-	struct radeon_semaphore *sem = NULL;
-	int ring_index = rdev->asic->copy.dma_ring_index;
-	struct radeon_ring *ring = &rdev->ring[ring_index];
-	u32 size_in_bytes, cur_size_in_bytes;
-	int i, num_loops;
-	int r = 0;
-
-	r = radeon_semaphore_create(rdev, &sem);
-	if (r) {
-		DRM_ERROR("radeon: moving bo (%d).\n", r);
-		return r;
-	}
-
-	size_in_bytes = (num_gpu_pages << RADEON_GPU_PAGE_SHIFT);
-	num_loops = DIV_ROUND_UP(size_in_bytes, 0xfffff);
-	r = radeon_ring_lock(rdev, ring, num_loops * 5 + 11);
-	if (r) {
-		DRM_ERROR("radeon: moving bo (%d).\n", r);
-		radeon_semaphore_free(rdev, &sem, NULL);
-		return r;
-	}
-
-	if (radeon_fence_need_sync(*fence, ring->idx)) {
-		radeon_semaphore_sync_rings(rdev, sem, (*fence)->ring,
-					    ring->idx);
-		radeon_fence_note_sync(*fence, ring->idx);
-	} else {
-		radeon_semaphore_free(rdev, &sem, NULL);
-	}
-
-	for (i = 0; i < num_loops; i++) {
-		cur_size_in_bytes = size_in_bytes;
-		if (cur_size_in_bytes > 0xFFFFF)
-			cur_size_in_bytes = 0xFFFFF;
-		size_in_bytes -= cur_size_in_bytes;
-		radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_COPY, 1, 0, 0, cur_size_in_bytes));
-		radeon_ring_write(ring, dst_offset & 0xffffffff);
-		radeon_ring_write(ring, src_offset & 0xffffffff);
-		radeon_ring_write(ring, upper_32_bits(dst_offset) & 0xff);
-		radeon_ring_write(ring, upper_32_bits(src_offset) & 0xff);
-		src_offset += cur_size_in_bytes;
-		dst_offset += cur_size_in_bytes;
-	}
-
-	r = radeon_fence_emit(rdev, fence, ring->idx);
-	if (r) {
-		radeon_ring_unlock_undo(rdev, ring);
-		return r;
-	}
-
-	radeon_ring_unlock_commit(rdev, ring);
-	radeon_semaphore_free(rdev, &sem, *fence);
-
-	return r;
-}
-
 /*
  * startup/shutdown callbacks
  */
@@ -6422,6 +6366,11 @@ static int si_startup(struct radeon_device *rdev)
 	/* enable aspm */
 	si_program_aspm(rdev);
 
+	/* scratch needs to be initialized before MC */
+	r = r600_vram_scratch_init(rdev);
+	if (r)
+		return r;
+
 	si_mc_program(rdev);
 
 	if (!rdev->me_fw || !rdev->pfp_fw || !rdev->ce_fw ||
@@ -6439,17 +6388,19 @@ static int si_startup(struct radeon_device *rdev)
 		return r;
 	}
 
-	r = r600_vram_scratch_init(rdev);
-	if (r)
-		return r;
-
 	r = si_pcie_gart_enable(rdev);
 	if (r)
 		return r;
 	si_gpu_init(rdev);
 
 	/* allocate rlc buffers */
-	r = si_rlc_init(rdev);
+	if (rdev->family == CHIP_VERDE) {
+		rdev->rlc.reg_list = verde_rlc_save_restore_register_list;
+		rdev->rlc.reg_list_size =
+			(u32)ARRAY_SIZE(verde_rlc_save_restore_register_list);
+	}
+	rdev->rlc.cs_data = si_cs_data;
+	r = sumo_rlc_init(rdev);
 	if (r) {
 		DRM_ERROR("Failed to init rlc BOs!\n");
 		return r;
@@ -6491,7 +6442,7 @@ static int si_startup(struct radeon_device *rdev)
 	}
 
 	if (rdev->has_uvd) {
-		r = rv770_uvd_resume(rdev);
+		r = uvd_v2_2_resume(rdev);
 		if (!r) {
 			r = radeon_fence_driver_start_ring(rdev,
 							   R600_RING_TYPE_UVD_INDEX);
@@ -6520,21 +6471,21 @@ static int si_startup(struct radeon_device *rdev)
 	ring = &rdev->ring[RADEON_RING_TYPE_GFX_INDEX];
 	r = radeon_ring_init(rdev, ring, ring->ring_size, RADEON_WB_CP_RPTR_OFFSET,
 			     CP_RB0_RPTR, CP_RB0_WPTR,
-			     0, 0xfffff, RADEON_CP_PACKET2);
+			     RADEON_CP_PACKET2);
 	if (r)
 		return r;
 
 	ring = &rdev->ring[CAYMAN_RING_TYPE_CP1_INDEX];
 	r = radeon_ring_init(rdev, ring, ring->ring_size, RADEON_WB_CP1_RPTR_OFFSET,
 			     CP_RB1_RPTR, CP_RB1_WPTR,
-			     0, 0xfffff, RADEON_CP_PACKET2);
+			     RADEON_CP_PACKET2);
 	if (r)
 		return r;
 
 	ring = &rdev->ring[CAYMAN_RING_TYPE_CP2_INDEX];
 	r = radeon_ring_init(rdev, ring, ring->ring_size, RADEON_WB_CP2_RPTR_OFFSET,
 			     CP_RB2_RPTR, CP_RB2_WPTR,
-			     0, 0xfffff, RADEON_CP_PACKET2);
+			     RADEON_CP_PACKET2);
 	if (r)
 		return r;
 
@@ -6542,7 +6493,7 @@ static int si_startup(struct radeon_device *rdev)
 	r = radeon_ring_init(rdev, ring, ring->ring_size, R600_WB_DMA_RPTR_OFFSET,
 			     DMA_RB_RPTR + DMA0_REGISTER_OFFSET,
 			     DMA_RB_WPTR + DMA0_REGISTER_OFFSET,
-			     2, 0x3fffc, DMA_PACKET(DMA_PACKET_NOP, 0, 0, 0, 0));
+			     DMA_PACKET(DMA_PACKET_NOP, 0, 0, 0, 0));
 	if (r)
 		return r;
 
@@ -6550,7 +6501,7 @@ static int si_startup(struct radeon_device *rdev)
 	r = radeon_ring_init(rdev, ring, ring->ring_size, CAYMAN_WB_DMA1_RPTR_OFFSET,
 			     DMA_RB_RPTR + DMA1_REGISTER_OFFSET,
 			     DMA_RB_WPTR + DMA1_REGISTER_OFFSET,
-			     2, 0x3fffc, DMA_PACKET(DMA_PACKET_NOP, 0, 0, 0, 0));
+			     DMA_PACKET(DMA_PACKET_NOP, 0, 0, 0, 0));
 	if (r)
 		return r;
 
@@ -6568,12 +6519,11 @@ static int si_startup(struct radeon_device *rdev)
 	if (rdev->has_uvd) {
 		ring = &rdev->ring[R600_RING_TYPE_UVD_INDEX];
 		if (ring->ring_size) {
-			r = radeon_ring_init(rdev, ring, ring->ring_size,
-					     R600_WB_UVD_RPTR_OFFSET,
+			r = radeon_ring_init(rdev, ring, ring->ring_size, 0,
 					     UVD_RBC_RB_RPTR, UVD_RBC_RB_WPTR,
-					     0, 0xfffff, RADEON_CP_PACKET2);
+					     RADEON_CP_PACKET2);
 			if (!r)
-				r = r600_uvd_init(rdev);
+				r = uvd_v1_0_init(rdev);
 			if (r)
 				DRM_ERROR("radeon: failed initializing UVD (%d).\n", r);
 		}
@@ -6591,6 +6541,10 @@ static int si_startup(struct radeon_device *rdev)
 		return r;
 	}
 
+	r = dce6_audio_init(rdev);
+	if (r)
+		return r;
+
 	return 0;
 }
 
@@ -6622,13 +6576,16 @@ int si_resume(struct radeon_device *rdev)
 
 int si_suspend(struct radeon_device *rdev)
 {
+	dce6_audio_fini(rdev);
 	radeon_vm_manager_fini(rdev);
 	si_cp_enable(rdev, false);
 	cayman_dma_stop(rdev);
 	if (rdev->has_uvd) {
-		r600_uvd_stop(rdev);
+		uvd_v1_0_fini(rdev);
 		radeon_uvd_suspend(rdev);
 	}
+	si_fini_pg(rdev);
+	si_fini_cg(rdev);
 	si_irq_suspend(rdev);
 	radeon_wb_disable(rdev);
 	si_pcie_gart_disable(rdev);
@@ -6735,7 +6692,7 @@ int si_init(struct radeon_device *rdev)
 		si_cp_fini(rdev);
 		cayman_dma_fini(rdev);
 		si_irq_fini(rdev);
-		si_rlc_fini(rdev);
+		sumo_rlc_fini(rdev);
 		radeon_wb_fini(rdev);
 		radeon_ib_pool_fini(rdev);
 		radeon_vm_manager_fini(rdev);
@@ -6760,16 +6717,16 @@ void si_fini(struct radeon_device *rdev)
 {
 	si_cp_fini(rdev);
 	cayman_dma_fini(rdev);
-	si_irq_fini(rdev);
-	si_rlc_fini(rdev);
-	si_fini_cg(rdev);
 	si_fini_pg(rdev);
+	si_fini_cg(rdev);
+	si_irq_fini(rdev);
+	sumo_rlc_fini(rdev);
 	radeon_wb_fini(rdev);
 	radeon_vm_manager_fini(rdev);
 	radeon_ib_pool_fini(rdev);
 	radeon_irq_kms_fini(rdev);
 	if (rdev->has_uvd) {
-		r600_uvd_stop(rdev);
+		uvd_v1_0_fini(rdev);
 		radeon_uvd_fini(rdev);
 	}
 	si_pcie_gart_fini(rdev);
diff --git a/drivers/gpu/drm/radeon/si_dma.c b/drivers/gpu/drm/radeon/si_dma.c
new file mode 100644
index 000000000000..49909d23dfce
--- /dev/null
+++ b/drivers/gpu/drm/radeon/si_dma.c
@@ -0,0 +1,235 @@
+/*
+ * Copyright 2013 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: Alex Deucher
+ */
+#include <drm/drmP.h>
+#include "radeon.h"
+#include "radeon_asic.h"
+#include "sid.h"
+
+u32 si_gpu_check_soft_reset(struct radeon_device *rdev);
+
+/**
+ * si_dma_is_lockup - Check if the DMA engine is locked up
+ *
+ * @rdev: radeon_device pointer
+ * @ring: radeon_ring structure holding ring information
+ *
+ * Check if the async DMA engine is locked up.
+ * Returns true if the engine appears to be locked up, false if not.
+ */
+bool si_dma_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
+{
+	u32 reset_mask = si_gpu_check_soft_reset(rdev);
+	u32 mask;
+
+	if (ring->idx == R600_RING_TYPE_DMA_INDEX)
+		mask = RADEON_RESET_DMA;
+	else
+		mask = RADEON_RESET_DMA1;
+
+	if (!(reset_mask & mask)) {
+		radeon_ring_lockup_update(ring);
+		return false;
+	}
+	/* force ring activities */
+	radeon_ring_force_activity(rdev, ring);
+	return radeon_ring_test_lockup(rdev, ring);
+}
+
+/**
+ * si_dma_vm_set_page - update the page tables using the DMA
+ *
+ * @rdev: radeon_device pointer
+ * @ib: indirect buffer to fill with commands
+ * @pe: addr of the page entry
+ * @addr: dst addr to write into pe
+ * @count: number of page entries to update
+ * @incr: increase next addr by incr bytes
+ * @flags: access flags
+ *
+ * Update the page tables using the DMA (SI).
+ */
+void si_dma_vm_set_page(struct radeon_device *rdev,
+			struct radeon_ib *ib,
+			uint64_t pe,
+			uint64_t addr, unsigned count,
+			uint32_t incr, uint32_t flags)
+{
+	uint32_t r600_flags = cayman_vm_page_flags(rdev, flags);
+	uint64_t value;
+	unsigned ndw;
+
+	if (flags & RADEON_VM_PAGE_SYSTEM) {
+		while (count) {
+			ndw = count * 2;
+			if (ndw > 0xFFFFE)
+				ndw = 0xFFFFE;
+
+			/* for non-physically contiguous pages (system) */
+			ib->ptr[ib->length_dw++] = DMA_PACKET(DMA_PACKET_WRITE, 0, 0, 0, ndw);
+			ib->ptr[ib->length_dw++] = pe;
+			ib->ptr[ib->length_dw++] = upper_32_bits(pe) & 0xff;
+			for (; ndw > 0; ndw -= 2, --count, pe += 8) {
+				if (flags & RADEON_VM_PAGE_SYSTEM) {
+					value = radeon_vm_map_gart(rdev, addr);
+					value &= 0xFFFFFFFFFFFFF000ULL;
+				} else if (flags & RADEON_VM_PAGE_VALID) {
+					value = addr;
+				} else {
+					value = 0;
+				}
+				addr += incr;
+				value |= r600_flags;
+				ib->ptr[ib->length_dw++] = value;
+				ib->ptr[ib->length_dw++] = upper_32_bits(value);
+			}
+		}
+	} else {
+		while (count) {
+			ndw = count * 2;
+			if (ndw > 0xFFFFE)
+				ndw = 0xFFFFE;
+
+			if (flags & RADEON_VM_PAGE_VALID)
+				value = addr;
+			else
+				value = 0;
+			/* for physically contiguous pages (vram) */
+			ib->ptr[ib->length_dw++] = DMA_PTE_PDE_PACKET(ndw);
+			ib->ptr[ib->length_dw++] = pe; /* dst addr */
+			ib->ptr[ib->length_dw++] = upper_32_bits(pe) & 0xff;
+			ib->ptr[ib->length_dw++] = r600_flags; /* mask */
+			ib->ptr[ib->length_dw++] = 0;
+			ib->ptr[ib->length_dw++] = value; /* value */
+			ib->ptr[ib->length_dw++] = upper_32_bits(value);
+			ib->ptr[ib->length_dw++] = incr; /* increment size */
+			ib->ptr[ib->length_dw++] = 0;
+			pe += ndw * 4;
+			addr += (ndw / 2) * incr;
+			count -= ndw / 2;
+		}
+	}
+	while (ib->length_dw & 0x7)
+		ib->ptr[ib->length_dw++] = DMA_PACKET(DMA_PACKET_NOP, 0, 0, 0, 0);
+}
+
+void si_dma_vm_flush(struct radeon_device *rdev, int ridx, struct radeon_vm *vm)
+{
+	struct radeon_ring *ring = &rdev->ring[ridx];
+
+	if (vm == NULL)
+		return;
+
+	radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_SRBM_WRITE, 0, 0, 0, 0));
+	if (vm->id < 8) {
+		radeon_ring_write(ring, (0xf << 16) | ((VM_CONTEXT0_PAGE_TABLE_BASE_ADDR + (vm->id << 2)) >> 2));
+	} else {
+		radeon_ring_write(ring, (0xf << 16) | ((VM_CONTEXT8_PAGE_TABLE_BASE_ADDR + ((vm->id - 8) << 2)) >> 2));
+	}
+	radeon_ring_write(ring, vm->pd_gpu_addr >> 12);
+
+	/* flush hdp cache */
+	radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_SRBM_WRITE, 0, 0, 0, 0));
+	radeon_ring_write(ring, (0xf << 16) | (HDP_MEM_COHERENCY_FLUSH_CNTL >> 2));
+	radeon_ring_write(ring, 1);
+
+	/* bits 0-7 are the VM contexts0-7 */
+	radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_SRBM_WRITE, 0, 0, 0, 0));
+	radeon_ring_write(ring, (0xf << 16) | (VM_INVALIDATE_REQUEST >> 2));
+	radeon_ring_write(ring, 1 << vm->id);
+}
+
+/**
+ * si_copy_dma - copy pages using the DMA engine
+ *
+ * @rdev: radeon_device pointer
+ * @src_offset: src GPU address
+ * @dst_offset: dst GPU address
+ * @num_gpu_pages: number of GPU pages to xfer
+ * @fence: radeon fence object
+ *
+ * Copy GPU paging using the DMA engine (SI).
+ * Used by the radeon ttm implementation to move pages if
+ * registered as the asic copy callback.
+ */
+int si_copy_dma(struct radeon_device *rdev,
+		uint64_t src_offset, uint64_t dst_offset,
+		unsigned num_gpu_pages,
+		struct radeon_fence **fence)
+{
+	struct radeon_semaphore *sem = NULL;
+	int ring_index = rdev->asic->copy.dma_ring_index;
+	struct radeon_ring *ring = &rdev->ring[ring_index];
+	u32 size_in_bytes, cur_size_in_bytes;
+	int i, num_loops;
+	int r = 0;
+
+	r = radeon_semaphore_create(rdev, &sem);
+	if (r) {
+		DRM_ERROR("radeon: moving bo (%d).\n", r);
+		return r;
+	}
+
+	size_in_bytes = (num_gpu_pages << RADEON_GPU_PAGE_SHIFT);
+	num_loops = DIV_ROUND_UP(size_in_bytes, 0xfffff);
+	r = radeon_ring_lock(rdev, ring, num_loops * 5 + 11);
+	if (r) {
+		DRM_ERROR("radeon: moving bo (%d).\n", r);
+		radeon_semaphore_free(rdev, &sem, NULL);
+		return r;
+	}
+
+	if (radeon_fence_need_sync(*fence, ring->idx)) {
+		radeon_semaphore_sync_rings(rdev, sem, (*fence)->ring,
+					    ring->idx);
+		radeon_fence_note_sync(*fence, ring->idx);
+	} else {
+		radeon_semaphore_free(rdev, &sem, NULL);
+	}
+
+	for (i = 0; i < num_loops; i++) {
+		cur_size_in_bytes = size_in_bytes;
+		if (cur_size_in_bytes > 0xFFFFF)
+			cur_size_in_bytes = 0xFFFFF;
+		size_in_bytes -= cur_size_in_bytes;
+		radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_COPY, 1, 0, 0, cur_size_in_bytes));
+		radeon_ring_write(ring, dst_offset & 0xffffffff);
+		radeon_ring_write(ring, src_offset & 0xffffffff);
+		radeon_ring_write(ring, upper_32_bits(dst_offset) & 0xff);
+		radeon_ring_write(ring, upper_32_bits(src_offset) & 0xff);
+		src_offset += cur_size_in_bytes;
+		dst_offset += cur_size_in_bytes;
+	}
+
+	r = radeon_fence_emit(rdev, fence, ring->idx);
+	if (r) {
+		radeon_ring_unlock_undo(rdev, ring);
+		return r;
+	}
+
+	radeon_ring_unlock_commit(rdev, ring);
+	radeon_semaphore_free(rdev, &sem, *fence);
+
+	return r;
+}
+
diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c
index 88699e3cd868..2332aa1bf93c 100644
--- a/drivers/gpu/drm/radeon/si_dpm.c
+++ b/drivers/gpu/drm/radeon/si_dpm.c
@@ -1753,6 +1753,9 @@ static int si_calculate_sclk_params(struct radeon_device *rdev,
 				    u32 engine_clock,
 				    SISLANDS_SMC_SCLK_VALUE *sclk);
 
+extern void si_update_cg(struct radeon_device *rdev,
+			 u32 block, bool enable);
+
 static struct si_power_info *si_get_pi(struct radeon_device *rdev)
 {
         struct si_power_info *pi = rdev->pm.dpm.priv;
@@ -2907,6 +2910,7 @@ static void si_apply_state_adjust_rules(struct radeon_device *rdev,
 	bool disable_sclk_switching = false;
 	u32 mclk, sclk;
 	u16 vddc, vddci;
+	u32 max_sclk_vddc, max_mclk_vddci, max_mclk_vddc;
 	int i;
 
 	if ((rdev->pm.dpm.new_active_crtc_count > 1) ||
@@ -2940,6 +2944,29 @@ static void si_apply_state_adjust_rules(struct radeon_device *rdev,
 		}
 	}
 
+	/* limit clocks to max supported clocks based on voltage dependency tables */
+	btc_get_max_clock_from_voltage_dependency_table(&rdev->pm.dpm.dyn_state.vddc_dependency_on_sclk,
+							&max_sclk_vddc);
+	btc_get_max_clock_from_voltage_dependency_table(&rdev->pm.dpm.dyn_state.vddci_dependency_on_mclk,
+							&max_mclk_vddci);
+	btc_get_max_clock_from_voltage_dependency_table(&rdev->pm.dpm.dyn_state.vddc_dependency_on_mclk,
+							&max_mclk_vddc);
+
+	for (i = 0; i < ps->performance_level_count; i++) {
+		if (max_sclk_vddc) {
+			if (ps->performance_levels[i].sclk > max_sclk_vddc)
+				ps->performance_levels[i].sclk = max_sclk_vddc;
+		}
+		if (max_mclk_vddci) {
+			if (ps->performance_levels[i].mclk > max_mclk_vddci)
+				ps->performance_levels[i].mclk = max_mclk_vddci;
+		}
+		if (max_mclk_vddc) {
+			if (ps->performance_levels[i].mclk > max_mclk_vddc)
+				ps->performance_levels[i].mclk = max_mclk_vddc;
+		}
+	}
+
 	/* XXX validate the min clocks required for display */
 
 	if (disable_mclk_switching) {
@@ -3663,7 +3690,7 @@ static void si_clear_vc(struct radeon_device *rdev)
 	WREG32(CG_FTV, 0);
 }
 
-static u8 si_get_ddr3_mclk_frequency_ratio(u32 memory_clock)
+u8 si_get_ddr3_mclk_frequency_ratio(u32 memory_clock)
 {
 	u8 mc_para_index;
 
@@ -3676,7 +3703,7 @@ static u8 si_get_ddr3_mclk_frequency_ratio(u32 memory_clock)
 	return mc_para_index;
 }
 
-static u8 si_get_mclk_frequency_ratio(u32 memory_clock, bool strobe_mode)
+u8 si_get_mclk_frequency_ratio(u32 memory_clock, bool strobe_mode)
 {
 	u8 mc_para_index;
 
@@ -3758,20 +3785,21 @@ static bool si_validate_phase_shedding_tables(struct radeon_device *rdev,
 	return true;
 }
 
-static void si_trim_voltage_table_to_fit_state_table(struct radeon_device *rdev,
-						     struct atom_voltage_table *voltage_table)
+void si_trim_voltage_table_to_fit_state_table(struct radeon_device *rdev,
+					      u32 max_voltage_steps,
+					      struct atom_voltage_table *voltage_table)
 {
 	unsigned int i, diff;
 
-	if (voltage_table->count <= SISLANDS_MAX_NO_VREG_STEPS)
+	if (voltage_table->count <= max_voltage_steps)
 		return;
 
-	diff = voltage_table->count - SISLANDS_MAX_NO_VREG_STEPS;
+	diff = voltage_table->count - max_voltage_steps;
 
-	for (i= 0; i < SISLANDS_MAX_NO_VREG_STEPS; i++)
+	for (i= 0; i < max_voltage_steps; i++)
 		voltage_table->entries[i] = voltage_table->entries[i + diff];
 
-	voltage_table->count = SISLANDS_MAX_NO_VREG_STEPS;
+	voltage_table->count = max_voltage_steps;
 }
 
 static int si_construct_voltage_tables(struct radeon_device *rdev)
@@ -3787,7 +3815,9 @@ static int si_construct_voltage_tables(struct radeon_device *rdev)
 		return ret;
 
 	if (eg_pi->vddc_voltage_table.count > SISLANDS_MAX_NO_VREG_STEPS)
-		si_trim_voltage_table_to_fit_state_table(rdev, &eg_pi->vddc_voltage_table);
+		si_trim_voltage_table_to_fit_state_table(rdev,
+							 SISLANDS_MAX_NO_VREG_STEPS,
+							 &eg_pi->vddc_voltage_table);
 
 	if (eg_pi->vddci_control) {
 		ret = radeon_atom_get_voltage_table(rdev, VOLTAGE_TYPE_VDDCI,
@@ -3796,7 +3826,9 @@ static int si_construct_voltage_tables(struct radeon_device *rdev)
 			return ret;
 
 		if (eg_pi->vddci_voltage_table.count > SISLANDS_MAX_NO_VREG_STEPS)
-			si_trim_voltage_table_to_fit_state_table(rdev, &eg_pi->vddci_voltage_table);
+			si_trim_voltage_table_to_fit_state_table(rdev,
+								 SISLANDS_MAX_NO_VREG_STEPS,
+								 &eg_pi->vddci_voltage_table);
 	}
 
 	if (pi->mvdd_control) {
@@ -3814,7 +3846,9 @@ static int si_construct_voltage_tables(struct radeon_device *rdev)
 		}
 
 		if (si_pi->mvdd_voltage_table.count > SISLANDS_MAX_NO_VREG_STEPS)
-			si_trim_voltage_table_to_fit_state_table(rdev, &si_pi->mvdd_voltage_table);
+			si_trim_voltage_table_to_fit_state_table(rdev,
+								 SISLANDS_MAX_NO_VREG_STEPS,
+								 &si_pi->mvdd_voltage_table);
 	}
 
 	if (si_pi->vddc_phase_shed_control) {
@@ -5174,7 +5208,7 @@ static int si_set_mc_special_registers(struct radeon_device *rdev,
 					table->mc_reg_table_entry[k].mc_data[j] |= 0x100;
 			}
 			j++;
-			if (j > SMC_SISLANDS_MC_REGISTER_ARRAY_SIZE)
+			if (j >= SMC_SISLANDS_MC_REGISTER_ARRAY_SIZE)
 				return -EINVAL;
 
 			if (!pi->mem_gddr5) {
@@ -5184,7 +5218,7 @@ static int si_set_mc_special_registers(struct radeon_device *rdev,
 					table->mc_reg_table_entry[k].mc_data[j] =
 						(table->mc_reg_table_entry[k].mc_data[i] & 0xffff0000) >> 16;
 				j++;
-				if (j > SMC_SISLANDS_MC_REGISTER_ARRAY_SIZE)
+				if (j >= SMC_SISLANDS_MC_REGISTER_ARRAY_SIZE)
 					return -EINVAL;
 			}
 			break;
@@ -5197,7 +5231,7 @@ static int si_set_mc_special_registers(struct radeon_device *rdev,
 					(temp_reg & 0xffff0000) |
 					(table->mc_reg_table_entry[k].mc_data[i] & 0x0000ffff);
 			j++;
-			if (j > SMC_SISLANDS_MC_REGISTER_ARRAY_SIZE)
+			if (j >= SMC_SISLANDS_MC_REGISTER_ARRAY_SIZE)
 				return -EINVAL;
 			break;
 		default:
@@ -5752,6 +5786,13 @@ int si_dpm_enable(struct radeon_device *rdev)
 	struct radeon_ps *boot_ps = rdev->pm.dpm.boot_ps;
 	int ret;
 
+	si_update_cg(rdev, (RADEON_CG_BLOCK_GFX |
+			    RADEON_CG_BLOCK_MC |
+			    RADEON_CG_BLOCK_SDMA |
+			    RADEON_CG_BLOCK_BIF |
+			    RADEON_CG_BLOCK_UVD |
+			    RADEON_CG_BLOCK_HDP), false);
+
 	if (si_is_smc_running(rdev))
 		return -EINVAL;
 	if (pi->voltage_control)
@@ -5871,6 +5912,13 @@ int si_dpm_enable(struct radeon_device *rdev)
 
 	si_enable_auto_throttle_source(rdev, RADEON_DPM_AUTO_THROTTLE_SRC_THERMAL, true);
 
+	si_update_cg(rdev, (RADEON_CG_BLOCK_GFX |
+			    RADEON_CG_BLOCK_MC |
+			    RADEON_CG_BLOCK_SDMA |
+			    RADEON_CG_BLOCK_BIF |
+			    RADEON_CG_BLOCK_UVD |
+			    RADEON_CG_BLOCK_HDP), true);
+
 	ni_update_current_ps(rdev, boot_ps);
 
 	return 0;
@@ -5881,6 +5929,13 @@ void si_dpm_disable(struct radeon_device *rdev)
 	struct rv7xx_power_info *pi = rv770_get_pi(rdev);
 	struct radeon_ps *boot_ps = rdev->pm.dpm.boot_ps;
 
+	si_update_cg(rdev, (RADEON_CG_BLOCK_GFX |
+			    RADEON_CG_BLOCK_MC |
+			    RADEON_CG_BLOCK_SDMA |
+			    RADEON_CG_BLOCK_BIF |
+			    RADEON_CG_BLOCK_UVD |
+			    RADEON_CG_BLOCK_HDP), false);
+
 	if (!si_is_smc_running(rdev))
 		return;
 	si_disable_ulv(rdev);
@@ -5945,6 +6000,13 @@ int si_dpm_set_power_state(struct radeon_device *rdev)
 	struct radeon_ps *old_ps = &eg_pi->current_rps;
 	int ret;
 
+	si_update_cg(rdev, (RADEON_CG_BLOCK_GFX |
+			    RADEON_CG_BLOCK_MC |
+			    RADEON_CG_BLOCK_SDMA |
+			    RADEON_CG_BLOCK_BIF |
+			    RADEON_CG_BLOCK_UVD |
+			    RADEON_CG_BLOCK_HDP), false);
+
 	ret = si_disable_ulv(rdev);
 	if (ret) {
 		DRM_ERROR("si_disable_ulv failed\n");
@@ -6037,11 +6099,12 @@ int si_dpm_set_power_state(struct radeon_device *rdev)
 		return ret;
 	}
 
-	ret = si_dpm_force_performance_level(rdev, RADEON_DPM_FORCED_LEVEL_AUTO);
-	if (ret) {
-		DRM_ERROR("si_dpm_force_performance_level failed\n");
-		return ret;
-	}
+	si_update_cg(rdev, (RADEON_CG_BLOCK_GFX |
+			    RADEON_CG_BLOCK_MC |
+			    RADEON_CG_BLOCK_SDMA |
+			    RADEON_CG_BLOCK_BIF |
+			    RADEON_CG_BLOCK_UVD |
+			    RADEON_CG_BLOCK_HDP), true);
 
 	return 0;
 }
@@ -6232,6 +6295,7 @@ static int si_parse_power_table(struct radeon_device *rdev)
 	rdev->pm.dpm.backbias_response_time = le16_to_cpu(power_info->pplib.usBackbiasTime);
 	rdev->pm.dpm.voltage_response_time = le16_to_cpu(power_info->pplib.usVoltageTime);
 	for (i = 0; i < state_array->ucNumEntries; i++) {
+		u8 *idx;
 		power_state = (union pplib_power_state *)power_state_offset;
 		non_clock_array_index = power_state->v2.nonClockInfoIndex;
 		non_clock_info = (struct _ATOM_PPLIB_NONCLOCK_INFO *)
@@ -6248,14 +6312,16 @@ static int si_parse_power_table(struct radeon_device *rdev)
 					      non_clock_info,
 					      non_clock_info_array->ucEntrySize);
 		k = 0;
+		idx = (u8 *)&power_state->v2.clockInfoIndex[0];
 		for (j = 0; j < power_state->v2.ucNumDPMLevels; j++) {
-			clock_array_index = power_state->v2.clockInfoIndex[j];
+			clock_array_index = idx[j];
 			if (clock_array_index >= clock_info_array->ucNumEntries)
 				continue;
 			if (k >= SISLANDS_MAX_HARDWARE_POWERLEVELS)
 				break;
 			clock_info = (union pplib_clock_info *)
-				&clock_info_array->clockInfo[clock_array_index * clock_info_array->ucEntrySize];
+				((u8 *)&clock_info_array->clockInfo[0] +
+				 (clock_array_index * clock_info_array->ucEntrySize));
 			si_parse_pplib_clock_info(rdev,
 						  &rdev->pm.dpm.ps[i], k,
 						  clock_info);
@@ -6401,6 +6467,12 @@ int si_dpm_init(struct radeon_device *rdev)
 
 	si_initialize_powertune_defaults(rdev);
 
+	/* make sure dc limits are valid */
+	if ((rdev->pm.dpm.dyn_state.max_clock_voltage_on_dc.sclk == 0) ||
+	    (rdev->pm.dpm.dyn_state.max_clock_voltage_on_dc.mclk == 0))
+		rdev->pm.dpm.dyn_state.max_clock_voltage_on_dc =
+			rdev->pm.dpm.dyn_state.max_clock_voltage_on_ac;
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/radeon/si_smc.c b/drivers/gpu/drm/radeon/si_smc.c
index 5f524c0a541e..d422a1cbf727 100644
--- a/drivers/gpu/drm/radeon/si_smc.c
+++ b/drivers/gpu/drm/radeon/si_smc.c
@@ -29,8 +29,8 @@
 #include "ppsmc.h"
 #include "radeon_ucode.h"
 
-int si_set_smc_sram_address(struct radeon_device *rdev,
-			    u32 smc_address, u32 limit)
+static int si_set_smc_sram_address(struct radeon_device *rdev,
+				   u32 smc_address, u32 limit)
 {
 	if (smc_address & 3)
 		return -EINVAL;
@@ -47,7 +47,8 @@ int si_copy_bytes_to_smc(struct radeon_device *rdev,
 			 u32 smc_start_address,
 			 const u8 *src, u32 byte_count, u32 limit)
 {
-	int ret;
+	unsigned long flags;
+	int ret = 0;
 	u32 data, original_data, addr, extra_shift;
 
 	if (smc_start_address & 3)
@@ -57,13 +58,14 @@ int si_copy_bytes_to_smc(struct radeon_device *rdev,
 
 	addr = smc_start_address;
 
+	spin_lock_irqsave(&rdev->smc_idx_lock, flags);
 	while (byte_count >= 4) {
 		/* SMC address space is BE */
 		data = (src[0] << 24) | (src[1] << 16) | (src[2] << 8) | src[3];
 
 		ret = si_set_smc_sram_address(rdev, addr, limit);
 		if (ret)
-			return ret;
+			goto done;
 
 		WREG32(SMC_IND_DATA_0, data);
 
@@ -78,7 +80,7 @@ int si_copy_bytes_to_smc(struct radeon_device *rdev,
 
 		ret = si_set_smc_sram_address(rdev, addr, limit);
 		if (ret)
-			return ret;
+			goto done;
 
 		original_data = RREG32(SMC_IND_DATA_0);
 
@@ -96,11 +98,15 @@ int si_copy_bytes_to_smc(struct radeon_device *rdev,
 
 		ret = si_set_smc_sram_address(rdev, addr, limit);
 		if (ret)
-			return ret;
+			goto done;
 
 		WREG32(SMC_IND_DATA_0, data);
 	}
-	return 0;
+
+done:
+	spin_unlock_irqrestore(&rdev->smc_idx_lock, flags);
+
+	return ret;
 }
 
 void si_start_smc(struct radeon_device *rdev)
@@ -203,6 +209,7 @@ PPSMC_Result si_wait_for_smc_inactive(struct radeon_device *rdev)
 
 int si_load_smc_ucode(struct radeon_device *rdev, u32 limit)
 {
+	unsigned long flags;
 	u32 ucode_start_address;
 	u32 ucode_size;
 	const u8 *src;
@@ -241,6 +248,7 @@ int si_load_smc_ucode(struct radeon_device *rdev, u32 limit)
 		return -EINVAL;
 
 	src = (const u8 *)rdev->smc_fw->data;
+	spin_lock_irqsave(&rdev->smc_idx_lock, flags);
 	WREG32(SMC_IND_INDEX_0, ucode_start_address);
 	WREG32_P(SMC_IND_ACCESS_CNTL, AUTO_INCREMENT_IND_0, ~AUTO_INCREMENT_IND_0);
 	while (ucode_size >= 4) {
@@ -253,6 +261,7 @@ int si_load_smc_ucode(struct radeon_device *rdev, u32 limit)
 		ucode_size -= 4;
 	}
 	WREG32_P(SMC_IND_ACCESS_CNTL, 0, ~AUTO_INCREMENT_IND_0);
+	spin_unlock_irqrestore(&rdev->smc_idx_lock, flags);
 
 	return 0;
 }
@@ -260,25 +269,29 @@ int si_load_smc_ucode(struct radeon_device *rdev, u32 limit)
 int si_read_smc_sram_dword(struct radeon_device *rdev, u32 smc_address,
 			   u32 *value, u32 limit)
 {
+	unsigned long flags;
 	int ret;
 
+	spin_lock_irqsave(&rdev->smc_idx_lock, flags);
 	ret = si_set_smc_sram_address(rdev, smc_address, limit);
-	if (ret)
-		return ret;
+	if (ret == 0)
+		*value = RREG32(SMC_IND_DATA_0);
+	spin_unlock_irqrestore(&rdev->smc_idx_lock, flags);
 
-	*value = RREG32(SMC_IND_DATA_0);
-	return 0;
+	return ret;
 }
 
 int si_write_smc_sram_dword(struct radeon_device *rdev, u32 smc_address,
 			    u32 value, u32 limit)
 {
+	unsigned long flags;
 	int ret;
 
+	spin_lock_irqsave(&rdev->smc_idx_lock, flags);
 	ret = si_set_smc_sram_address(rdev, smc_address, limit);
-	if (ret)
-		return ret;
+	if (ret == 0)
+		WREG32(SMC_IND_DATA_0, value);
+	spin_unlock_irqrestore(&rdev->smc_idx_lock, flags);
 
-	WREG32(SMC_IND_DATA_0, value);
-	return 0;
+	return ret;
 }
diff --git a/drivers/gpu/drm/radeon/sid.h b/drivers/gpu/drm/radeon/sid.h
index 2c8da27a929f..7e2e0ea66a00 100644
--- a/drivers/gpu/drm/radeon/sid.h
+++ b/drivers/gpu/drm/radeon/sid.h
@@ -282,6 +282,10 @@
 
 #define DMIF_ADDR_CALC  				0xC00
 
+#define	PIPE0_DMIF_BUFFER_CONTROL			  0x0ca0
+#       define DMIF_BUFFERS_ALLOCATED(x)                  ((x) << 0)
+#       define DMIF_BUFFERS_ALLOCATED_COMPLETED           (1 << 4)
+
 #define	SRBM_STATUS				        0xE50
 #define		GRBM_RQ_PENDING 			(1 << 5)
 #define		VMC_BUSY 				(1 << 8)
@@ -581,6 +585,7 @@
 #define		CLKS_MASK				(0xfff << 0)
 
 #define	HDP_HOST_PATH_CNTL				0x2C00
+#define 	CLOCK_GATING_DIS			(1 << 23)
 #define	HDP_NONSURFACE_BASE				0x2C04
 #define	HDP_NONSURFACE_INFO				0x2C08
 #define	HDP_NONSURFACE_SIZE				0x2C0C
@@ -588,6 +593,8 @@
 #define HDP_ADDR_CONFIG  				0x2F48
 #define HDP_MISC_CNTL					0x2F4C
 #define 	HDP_FLUSH_INVALIDATE_CACHE			(1 << 0)
+#define HDP_MEM_POWER_LS				0x2F50
+#define 	HDP_LS_ENABLE				(1 << 0)
 
 #define ATC_MISC_CG           				0x3350
 
@@ -635,6 +642,54 @@
 
 #define HDP_REG_COHERENCY_FLUSH_CNTL			0x54A0
 
+/* DCE6 ELD audio interface */
+#define AZ_F0_CODEC_ENDPOINT_INDEX                       0x5E00
+#       define AZ_ENDPOINT_REG_INDEX(x)                  (((x) & 0xff) << 0)
+#       define AZ_ENDPOINT_REG_WRITE_EN                  (1 << 8)
+#define AZ_F0_CODEC_ENDPOINT_DATA                        0x5E04
+
+#define AZ_F0_CODEC_PIN_CONTROL_CHANNEL_SPEAKER          0x25
+#define		SPEAKER_ALLOCATION(x)			(((x) & 0x7f) << 0)
+#define		SPEAKER_ALLOCATION_MASK			(0x7f << 0)
+#define		SPEAKER_ALLOCATION_SHIFT		0
+#define		HDMI_CONNECTION				(1 << 16)
+#define		DP_CONNECTION				(1 << 17)
+
+#define AZ_F0_CODEC_PIN_CONTROL_AUDIO_DESCRIPTOR0        0x28 /* LPCM */
+#define AZ_F0_CODEC_PIN_CONTROL_AUDIO_DESCRIPTOR1        0x29 /* AC3 */
+#define AZ_F0_CODEC_PIN_CONTROL_AUDIO_DESCRIPTOR2        0x2A /* MPEG1 */
+#define AZ_F0_CODEC_PIN_CONTROL_AUDIO_DESCRIPTOR3        0x2B /* MP3 */
+#define AZ_F0_CODEC_PIN_CONTROL_AUDIO_DESCRIPTOR4        0x2C /* MPEG2 */
+#define AZ_F0_CODEC_PIN_CONTROL_AUDIO_DESCRIPTOR5        0x2D /* AAC */
+#define AZ_F0_CODEC_PIN_CONTROL_AUDIO_DESCRIPTOR6        0x2E /* DTS */
+#define AZ_F0_CODEC_PIN_CONTROL_AUDIO_DESCRIPTOR7        0x2F /* ATRAC */
+#define AZ_F0_CODEC_PIN_CONTROL_AUDIO_DESCRIPTOR8        0x30 /* one bit audio - leave at 0 (default) */
+#define AZ_F0_CODEC_PIN_CONTROL_AUDIO_DESCRIPTOR9        0x31 /* Dolby Digital */
+#define AZ_F0_CODEC_PIN_CONTROL_AUDIO_DESCRIPTOR10       0x32 /* DTS-HD */
+#define AZ_F0_CODEC_PIN_CONTROL_AUDIO_DESCRIPTOR11       0x33 /* MAT-MLP */
+#define AZ_F0_CODEC_PIN_CONTROL_AUDIO_DESCRIPTOR12       0x34 /* DTS */
+#define AZ_F0_CODEC_PIN_CONTROL_AUDIO_DESCRIPTOR13       0x35 /* WMA Pro */
+#       define MAX_CHANNELS(x)                            (((x) & 0x7) << 0)
+/* max channels minus one.  7 = 8 channels */
+#       define SUPPORTED_FREQUENCIES(x)                   (((x) & 0xff) << 8)
+#       define DESCRIPTOR_BYTE_2(x)                       (((x) & 0xff) << 16)
+#       define SUPPORTED_FREQUENCIES_STEREO(x)            (((x) & 0xff) << 24) /* LPCM only */
+/* SUPPORTED_FREQUENCIES, SUPPORTED_FREQUENCIES_STEREO
+ * bit0 = 32 kHz
+ * bit1 = 44.1 kHz
+ * bit2 = 48 kHz
+ * bit3 = 88.2 kHz
+ * bit4 = 96 kHz
+ * bit5 = 176.4 kHz
+ * bit6 = 192 kHz
+ */
+#define AZ_F0_CODEC_PIN_CONTROL_HOTPLUG_CONTROL          0x54
+#       define AUDIO_ENABLED                             (1 << 31)
+
+#define AZ_F0_CODEC_PIN_CONTROL_RESPONSE_CONFIGURATION_DEFAULT  0x56
+#define		PORT_CONNECTIVITY_MASK				(3 << 30)
+#define		PORT_CONNECTIVITY_SHIFT				30
+
 #define	DC_LB_MEMORY_SPLIT					0x6b0c
 #define		DC_LB_MEMORY_CONFIG(x)				((x) << 20)
 
@@ -755,6 +810,17 @@
 /* 0x6e98, 0x7a98, 0x10698, 0x11298, 0x11e98, 0x12a98 */
 #define CRTC_STATUS_FRAME_COUNT                         0x6e98
 
+#define AFMT_AUDIO_SRC_CONTROL                          0x713c
+#define		AFMT_AUDIO_SRC_SELECT(x)		(((x) & 7) << 0)
+/* AFMT_AUDIO_SRC_SELECT
+ * 0 = stream0
+ * 1 = stream1
+ * 2 = stream2
+ * 3 = stream3
+ * 4 = stream4
+ * 5 = stream5
+ */
+
 #define	GRBM_CNTL					0x8000
 #define		GRBM_READ_TIMEOUT(x)				((x) << 0)
 
@@ -1295,6 +1361,7 @@
 /* PCIE registers idx/data 0x30/0x34 */
 #define PCIE_CNTL2                                        0x1c /* PCIE */
 #       define SLV_MEM_LS_EN                              (1 << 16)
+#       define SLV_MEM_AGGRESSIVE_LS_EN                   (1 << 17)
 #       define MST_MEM_LS_EN                              (1 << 18)
 #       define REPLAY_MEM_LS_EN                           (1 << 19)
 #define PCIE_LC_STATUS1                                   0x28 /* PCIE */
@@ -1486,7 +1553,7 @@
  * 6. COMMAND [30:21] | BYTE_COUNT [20:0]
  */
 #              define PACKET3_CP_DMA_DST_SEL(x)    ((x) << 20)
-                /* 0 - SRC_ADDR
+                /* 0 - DST_ADDR
 		 * 1 - GDS
 		 */
 #              define PACKET3_CP_DMA_ENGINE(x)     ((x) << 27)
@@ -1501,7 +1568,7 @@
 #              define PACKET3_CP_DMA_CP_SYNC       (1 << 31)
 /* COMMAND */
 #              define PACKET3_CP_DMA_DIS_WC        (1 << 21)
-#              define PACKET3_CP_DMA_CMD_SRC_SWAP(x) ((x) << 23)
+#              define PACKET3_CP_DMA_CMD_SRC_SWAP(x) ((x) << 22)
                 /* 0 - none
 		 * 1 - 8 in 16
 		 * 2 - 8 in 32
@@ -1644,6 +1711,10 @@
 #       define DMA_IDLE                                   (1 << 0)
 #define DMA_TILING_CONFIG  				  0xd0b8
 
+#define	DMA_POWER_CNTL					0xd0bc
+#       define MEM_POWER_OVERRIDE                       (1 << 8)
+#define	DMA_CLK_CTRL					0xd0c0
+
 #define	DMA_PG						0xd0d4
 #	define PG_CNTL_ENABLE				(1 << 0)
 #define	DMA_PGFSM_CONFIG				0xd0d8
diff --git a/drivers/gpu/drm/radeon/smu7.h b/drivers/gpu/drm/radeon/smu7.h
new file mode 100644
index 000000000000..75a380a15292
--- /dev/null
+++ b/drivers/gpu/drm/radeon/smu7.h
@@ -0,0 +1,170 @@
+/*
+ * Copyright 2013 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+
+#ifndef SMU7_H
+#define SMU7_H
+
+#pragma pack(push, 1)
+
+#define SMU7_CONTEXT_ID_SMC        1
+#define SMU7_CONTEXT_ID_VBIOS      2
+
+
+#define SMU7_CONTEXT_ID_SMC        1
+#define SMU7_CONTEXT_ID_VBIOS      2
+
+#define SMU7_MAX_LEVELS_VDDC            8
+#define SMU7_MAX_LEVELS_VDDCI           4
+#define SMU7_MAX_LEVELS_MVDD            4
+#define SMU7_MAX_LEVELS_VDDNB           8
+
+#define SMU7_MAX_LEVELS_GRAPHICS        SMU__NUM_SCLK_DPM_STATE   // SCLK + SQ DPM + ULV
+#define SMU7_MAX_LEVELS_MEMORY          SMU__NUM_MCLK_DPM_LEVELS   // MCLK Levels DPM
+#define SMU7_MAX_LEVELS_GIO             SMU__NUM_LCLK_DPM_LEVELS  // LCLK Levels
+#define SMU7_MAX_LEVELS_LINK            SMU__NUM_PCIE_DPM_LEVELS  // PCIe speed and number of lanes.
+#define SMU7_MAX_LEVELS_UVD             8   // VCLK/DCLK levels for UVD.
+#define SMU7_MAX_LEVELS_VCE             8   // ECLK levels for VCE.
+#define SMU7_MAX_LEVELS_ACP             8   // ACLK levels for ACP.
+#define SMU7_MAX_LEVELS_SAMU            8   // SAMCLK levels for SAMU.
+#define SMU7_MAX_ENTRIES_SMIO           32  // Number of entries in SMIO table.
+
+#define DPM_NO_LIMIT 0
+#define DPM_NO_UP 1
+#define DPM_GO_DOWN 2
+#define DPM_GO_UP 3
+
+#define SMU7_FIRST_DPM_GRAPHICS_LEVEL    0
+#define SMU7_FIRST_DPM_MEMORY_LEVEL      0
+
+#define GPIO_CLAMP_MODE_VRHOT      1
+#define GPIO_CLAMP_MODE_THERM      2
+#define GPIO_CLAMP_MODE_DC         4
+
+#define SCRATCH_B_TARG_PCIE_INDEX_SHIFT 0
+#define SCRATCH_B_TARG_PCIE_INDEX_MASK  (0x7<<SCRATCH_B_TARG_PCIE_INDEX_SHIFT)
+#define SCRATCH_B_CURR_PCIE_INDEX_SHIFT 3
+#define SCRATCH_B_CURR_PCIE_INDEX_MASK  (0x7<<SCRATCH_B_CURR_PCIE_INDEX_SHIFT)
+#define SCRATCH_B_TARG_UVD_INDEX_SHIFT  6
+#define SCRATCH_B_TARG_UVD_INDEX_MASK   (0x7<<SCRATCH_B_TARG_UVD_INDEX_SHIFT)
+#define SCRATCH_B_CURR_UVD_INDEX_SHIFT  9
+#define SCRATCH_B_CURR_UVD_INDEX_MASK   (0x7<<SCRATCH_B_CURR_UVD_INDEX_SHIFT)
+#define SCRATCH_B_TARG_VCE_INDEX_SHIFT  12
+#define SCRATCH_B_TARG_VCE_INDEX_MASK   (0x7<<SCRATCH_B_TARG_VCE_INDEX_SHIFT)
+#define SCRATCH_B_CURR_VCE_INDEX_SHIFT  15
+#define SCRATCH_B_CURR_VCE_INDEX_MASK   (0x7<<SCRATCH_B_CURR_VCE_INDEX_SHIFT)
+#define SCRATCH_B_TARG_ACP_INDEX_SHIFT  18
+#define SCRATCH_B_TARG_ACP_INDEX_MASK   (0x7<<SCRATCH_B_TARG_ACP_INDEX_SHIFT)
+#define SCRATCH_B_CURR_ACP_INDEX_SHIFT  21
+#define SCRATCH_B_CURR_ACP_INDEX_MASK   (0x7<<SCRATCH_B_CURR_ACP_INDEX_SHIFT)
+#define SCRATCH_B_TARG_SAMU_INDEX_SHIFT 24
+#define SCRATCH_B_TARG_SAMU_INDEX_MASK  (0x7<<SCRATCH_B_TARG_SAMU_INDEX_SHIFT)
+#define SCRATCH_B_CURR_SAMU_INDEX_SHIFT 27
+#define SCRATCH_B_CURR_SAMU_INDEX_MASK  (0x7<<SCRATCH_B_CURR_SAMU_INDEX_SHIFT)
+
+
+struct SMU7_PIDController
+{
+    uint32_t Ki;
+    int32_t LFWindupUL;
+    int32_t LFWindupLL;
+    uint32_t StatePrecision;
+    uint32_t LfPrecision;
+    uint32_t LfOffset;
+    uint32_t MaxState;
+    uint32_t MaxLfFraction;
+    uint32_t StateShift;
+};
+
+typedef struct SMU7_PIDController SMU7_PIDController;
+
+// -------------------------------------------------------------------------------------------------------------------------
+#define SMU7_MAX_PCIE_LINK_SPEEDS 3 /* 0:Gen1 1:Gen2 2:Gen3 */
+
+#define SMU7_SCLK_DPM_CONFIG_MASK                        0x01
+#define SMU7_VOLTAGE_CONTROLLER_CONFIG_MASK              0x02
+#define SMU7_THERMAL_CONTROLLER_CONFIG_MASK              0x04
+#define SMU7_MCLK_DPM_CONFIG_MASK                        0x08
+#define SMU7_UVD_DPM_CONFIG_MASK                         0x10
+#define SMU7_VCE_DPM_CONFIG_MASK                         0x20
+#define SMU7_ACP_DPM_CONFIG_MASK                         0x40
+#define SMU7_SAMU_DPM_CONFIG_MASK                        0x80
+#define SMU7_PCIEGEN_DPM_CONFIG_MASK                    0x100
+
+#define SMU7_ACP_MCLK_HANDSHAKE_DISABLE                  0x00000001
+#define SMU7_ACP_SCLK_HANDSHAKE_DISABLE                  0x00000002
+#define SMU7_UVD_MCLK_HANDSHAKE_DISABLE                  0x00000100
+#define SMU7_UVD_SCLK_HANDSHAKE_DISABLE                  0x00000200
+#define SMU7_VCE_MCLK_HANDSHAKE_DISABLE                  0x00010000
+#define SMU7_VCE_SCLK_HANDSHAKE_DISABLE                  0x00020000
+
+struct SMU7_Firmware_Header
+{
+    uint32_t Digest[5];
+    uint32_t Version;
+    uint32_t HeaderSize;
+    uint32_t Flags;
+    uint32_t EntryPoint;
+    uint32_t CodeSize;
+    uint32_t ImageSize;
+
+    uint32_t Rtos;
+    uint32_t SoftRegisters;
+    uint32_t DpmTable;
+    uint32_t FanTable;
+    uint32_t CacConfigTable;
+    uint32_t CacStatusTable;
+
+    uint32_t mcRegisterTable;
+
+    uint32_t mcArbDramTimingTable;
+
+    uint32_t PmFuseTable;
+    uint32_t Globals;
+    uint32_t Reserved[42];
+    uint32_t Signature;
+};
+
+typedef struct SMU7_Firmware_Header SMU7_Firmware_Header;
+
+#define SMU7_FIRMWARE_HEADER_LOCATION 0x20000
+
+enum  DisplayConfig {
+    PowerDown = 1,
+    DP54x4,
+    DP54x2,
+    DP54x1,
+    DP27x4,
+    DP27x2,
+    DP27x1,
+    HDMI297,
+    HDMI162,
+    LVDS,
+    DP324x4,
+    DP324x2,
+    DP324x1
+};
+
+#pragma pack(pop)
+
+#endif
+
diff --git a/drivers/gpu/drm/radeon/smu7_discrete.h b/drivers/gpu/drm/radeon/smu7_discrete.h
new file mode 100644
index 000000000000..82f70c90a9ee
--- /dev/null
+++ b/drivers/gpu/drm/radeon/smu7_discrete.h
@@ -0,0 +1,486 @@
+/*
+ * Copyright 2013 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+
+#ifndef SMU7_DISCRETE_H
+#define SMU7_DISCRETE_H
+
+#include "smu7.h"
+
+#pragma pack(push, 1)
+
+#define SMU7_DTE_ITERATIONS 5
+#define SMU7_DTE_SOURCES 3
+#define SMU7_DTE_SINKS 1
+#define SMU7_NUM_CPU_TES 0
+#define SMU7_NUM_GPU_TES 1
+#define SMU7_NUM_NON_TES 2
+
+struct SMU7_SoftRegisters
+{
+    uint32_t        RefClockFrequency;
+    uint32_t        PmTimerP;
+    uint32_t        FeatureEnables;
+    uint32_t        PreVBlankGap;
+    uint32_t        VBlankTimeout;
+    uint32_t        TrainTimeGap;
+
+    uint32_t        MvddSwitchTime;
+    uint32_t        LongestAcpiTrainTime;
+    uint32_t        AcpiDelay;
+    uint32_t        G5TrainTime;
+    uint32_t        DelayMpllPwron;
+    uint32_t        VoltageChangeTimeout;
+    uint32_t        HandshakeDisables;
+
+    uint8_t         DisplayPhy1Config;
+    uint8_t         DisplayPhy2Config;
+    uint8_t         DisplayPhy3Config;
+    uint8_t         DisplayPhy4Config;
+
+    uint8_t         DisplayPhy5Config;
+    uint8_t         DisplayPhy6Config;
+    uint8_t         DisplayPhy7Config;
+    uint8_t         DisplayPhy8Config;
+
+    uint32_t        AverageGraphicsA;
+    uint32_t        AverageMemoryA;
+    uint32_t        AverageGioA;
+
+    uint8_t         SClkDpmEnabledLevels;
+    uint8_t         MClkDpmEnabledLevels;
+    uint8_t         LClkDpmEnabledLevels;
+    uint8_t         PCIeDpmEnabledLevels;
+
+    uint8_t         UVDDpmEnabledLevels;
+    uint8_t         SAMUDpmEnabledLevels;
+    uint8_t         ACPDpmEnabledLevels;
+    uint8_t         VCEDpmEnabledLevels;
+
+    uint32_t        DRAM_LOG_ADDR_H;
+    uint32_t        DRAM_LOG_ADDR_L;
+    uint32_t        DRAM_LOG_PHY_ADDR_H;
+    uint32_t        DRAM_LOG_PHY_ADDR_L;
+    uint32_t        DRAM_LOG_BUFF_SIZE;
+    uint32_t        UlvEnterC;
+    uint32_t        UlvTime;
+    uint32_t        Reserved[3];
+
+};
+
+typedef struct SMU7_SoftRegisters SMU7_SoftRegisters;
+
+struct SMU7_Discrete_VoltageLevel
+{
+    uint16_t    Voltage;
+    uint16_t    StdVoltageHiSidd;
+    uint16_t    StdVoltageLoSidd;
+    uint8_t     Smio;
+    uint8_t     padding;
+};
+
+typedef struct SMU7_Discrete_VoltageLevel SMU7_Discrete_VoltageLevel;
+
+struct SMU7_Discrete_GraphicsLevel
+{
+    uint32_t    Flags;
+    uint32_t    MinVddc;
+    uint32_t    MinVddcPhases;
+
+    uint32_t    SclkFrequency;
+
+    uint8_t     padding1[2];
+    uint16_t    ActivityLevel;
+
+    uint32_t    CgSpllFuncCntl3;
+    uint32_t    CgSpllFuncCntl4;
+    uint32_t    SpllSpreadSpectrum;
+    uint32_t    SpllSpreadSpectrum2;
+    uint32_t    CcPwrDynRm;
+    uint32_t    CcPwrDynRm1;
+    uint8_t     SclkDid;
+    uint8_t     DisplayWatermark;
+    uint8_t     EnabledForActivity;
+    uint8_t     EnabledForThrottle;
+    uint8_t     UpH;
+    uint8_t     DownH;
+    uint8_t     VoltageDownH;
+    uint8_t     PowerThrottle;
+    uint8_t     DeepSleepDivId;
+    uint8_t     padding[3];
+};
+
+typedef struct SMU7_Discrete_GraphicsLevel SMU7_Discrete_GraphicsLevel;
+
+struct SMU7_Discrete_ACPILevel
+{
+    uint32_t    Flags;
+    uint32_t    MinVddc;
+    uint32_t    MinVddcPhases;
+    uint32_t    SclkFrequency;
+    uint8_t     SclkDid;
+    uint8_t     DisplayWatermark;
+    uint8_t     DeepSleepDivId;
+    uint8_t     padding;
+    uint32_t    CgSpllFuncCntl;
+    uint32_t    CgSpllFuncCntl2;
+    uint32_t    CgSpllFuncCntl3;
+    uint32_t    CgSpllFuncCntl4;
+    uint32_t    SpllSpreadSpectrum;
+    uint32_t    SpllSpreadSpectrum2;
+    uint32_t    CcPwrDynRm;
+    uint32_t    CcPwrDynRm1;
+};
+
+typedef struct SMU7_Discrete_ACPILevel SMU7_Discrete_ACPILevel;
+
+struct SMU7_Discrete_Ulv
+{
+    uint32_t    CcPwrDynRm;
+    uint32_t    CcPwrDynRm1;
+    uint16_t    VddcOffset;
+    uint8_t     VddcOffsetVid;
+    uint8_t     VddcPhase;
+    uint32_t    Reserved;
+};
+
+typedef struct SMU7_Discrete_Ulv SMU7_Discrete_Ulv;
+
+struct SMU7_Discrete_MemoryLevel
+{
+    uint32_t    MinVddc;
+    uint32_t    MinVddcPhases;
+    uint32_t    MinVddci;
+    uint32_t    MinMvdd;
+
+    uint32_t    MclkFrequency;
+
+    uint8_t     EdcReadEnable;
+    uint8_t     EdcWriteEnable;
+    uint8_t     RttEnable;
+    uint8_t     StutterEnable;
+
+    uint8_t     StrobeEnable;
+    uint8_t     StrobeRatio;
+    uint8_t     EnabledForThrottle;
+    uint8_t     EnabledForActivity;
+
+    uint8_t     UpH;
+    uint8_t     DownH;
+    uint8_t     VoltageDownH;
+    uint8_t     padding;
+
+    uint16_t    ActivityLevel;
+    uint8_t     DisplayWatermark;
+    uint8_t     padding1;
+
+    uint32_t    MpllFuncCntl;
+    uint32_t    MpllFuncCntl_1;
+    uint32_t    MpllFuncCntl_2;
+    uint32_t    MpllAdFuncCntl;
+    uint32_t    MpllDqFuncCntl;
+    uint32_t    MclkPwrmgtCntl;
+    uint32_t    DllCntl;
+    uint32_t    MpllSs1;
+    uint32_t    MpllSs2;
+};
+
+typedef struct SMU7_Discrete_MemoryLevel SMU7_Discrete_MemoryLevel;
+
+struct SMU7_Discrete_LinkLevel
+{
+    uint8_t     PcieGenSpeed;
+    uint8_t     PcieLaneCount;
+    uint8_t     EnabledForActivity;
+    uint8_t     Padding;
+    uint32_t    DownT;
+    uint32_t    UpT;
+    uint32_t    Reserved;
+};
+
+typedef struct SMU7_Discrete_LinkLevel SMU7_Discrete_LinkLevel;
+
+
+struct SMU7_Discrete_MCArbDramTimingTableEntry
+{
+    uint32_t McArbDramTiming;
+    uint32_t McArbDramTiming2;
+    uint8_t  McArbBurstTime;
+    uint8_t  padding[3];
+};
+
+typedef struct SMU7_Discrete_MCArbDramTimingTableEntry SMU7_Discrete_MCArbDramTimingTableEntry;
+
+struct SMU7_Discrete_MCArbDramTimingTable
+{
+    SMU7_Discrete_MCArbDramTimingTableEntry entries[SMU__NUM_SCLK_DPM_STATE][SMU__NUM_MCLK_DPM_LEVELS];
+};
+
+typedef struct SMU7_Discrete_MCArbDramTimingTable SMU7_Discrete_MCArbDramTimingTable;
+
+struct SMU7_Discrete_UvdLevel
+{
+    uint32_t VclkFrequency;
+    uint32_t DclkFrequency;
+    uint16_t MinVddc;
+    uint8_t  MinVddcPhases;
+    uint8_t  VclkDivider;
+    uint8_t  DclkDivider;
+    uint8_t  padding[3];
+};
+
+typedef struct SMU7_Discrete_UvdLevel SMU7_Discrete_UvdLevel;
+
+struct SMU7_Discrete_ExtClkLevel
+{
+    uint32_t Frequency;
+    uint16_t MinVoltage;
+    uint8_t  MinPhases;
+    uint8_t  Divider;
+};
+
+typedef struct SMU7_Discrete_ExtClkLevel SMU7_Discrete_ExtClkLevel;
+
+struct SMU7_Discrete_StateInfo
+{
+    uint32_t SclkFrequency;
+    uint32_t MclkFrequency;
+    uint32_t VclkFrequency;
+    uint32_t DclkFrequency;
+    uint32_t SamclkFrequency;
+    uint32_t AclkFrequency;
+    uint32_t EclkFrequency;
+    uint16_t MvddVoltage;
+    uint16_t padding16;
+    uint8_t  DisplayWatermark;
+    uint8_t  McArbIndex;
+    uint8_t  McRegIndex;
+    uint8_t  SeqIndex;
+    uint8_t  SclkDid;
+    int8_t   SclkIndex;
+    int8_t   MclkIndex;
+    uint8_t  PCIeGen;
+
+};
+
+typedef struct SMU7_Discrete_StateInfo SMU7_Discrete_StateInfo;
+
+
+struct SMU7_Discrete_DpmTable
+{
+    SMU7_PIDController                  GraphicsPIDController;
+    SMU7_PIDController                  MemoryPIDController;
+    SMU7_PIDController                  LinkPIDController;
+
+    uint32_t                            SystemFlags;
+
+
+    uint32_t                            SmioMaskVddcVid;
+    uint32_t                            SmioMaskVddcPhase;
+    uint32_t                            SmioMaskVddciVid;
+    uint32_t                            SmioMaskMvddVid;
+
+    uint32_t                            VddcLevelCount;
+    uint32_t                            VddciLevelCount;
+    uint32_t                            MvddLevelCount;
+
+    SMU7_Discrete_VoltageLevel          VddcLevel               [SMU7_MAX_LEVELS_VDDC];
+//    SMU7_Discrete_VoltageLevel          VddcStandardReference   [SMU7_MAX_LEVELS_VDDC];
+    SMU7_Discrete_VoltageLevel          VddciLevel              [SMU7_MAX_LEVELS_VDDCI];
+    SMU7_Discrete_VoltageLevel          MvddLevel               [SMU7_MAX_LEVELS_MVDD];
+
+    uint8_t                             GraphicsDpmLevelCount;
+    uint8_t                             MemoryDpmLevelCount;
+    uint8_t                             LinkLevelCount;
+    uint8_t                             UvdLevelCount;
+    uint8_t                             VceLevelCount;
+    uint8_t                             AcpLevelCount;
+    uint8_t                             SamuLevelCount;
+    uint8_t                             MasterDeepSleepControl;
+    uint32_t                            Reserved[5];
+//    uint32_t                            SamuDefaultLevel;
+
+    SMU7_Discrete_GraphicsLevel         GraphicsLevel           [SMU7_MAX_LEVELS_GRAPHICS];
+    SMU7_Discrete_MemoryLevel           MemoryACPILevel;
+    SMU7_Discrete_MemoryLevel           MemoryLevel             [SMU7_MAX_LEVELS_MEMORY];
+    SMU7_Discrete_LinkLevel             LinkLevel               [SMU7_MAX_LEVELS_LINK];
+    SMU7_Discrete_ACPILevel             ACPILevel;
+    SMU7_Discrete_UvdLevel              UvdLevel                [SMU7_MAX_LEVELS_UVD];
+    SMU7_Discrete_ExtClkLevel           VceLevel                [SMU7_MAX_LEVELS_VCE];
+    SMU7_Discrete_ExtClkLevel           AcpLevel                [SMU7_MAX_LEVELS_ACP];
+    SMU7_Discrete_ExtClkLevel           SamuLevel               [SMU7_MAX_LEVELS_SAMU];
+    SMU7_Discrete_Ulv                   Ulv;
+
+    uint32_t                            SclkStepSize;
+    uint32_t                            Smio                    [SMU7_MAX_ENTRIES_SMIO];
+
+    uint8_t                             UvdBootLevel;
+    uint8_t                             VceBootLevel;
+    uint8_t                             AcpBootLevel;
+    uint8_t                             SamuBootLevel;
+
+    uint8_t                             UVDInterval;
+    uint8_t                             VCEInterval;
+    uint8_t                             ACPInterval;
+    uint8_t                             SAMUInterval;
+
+    uint8_t                             GraphicsBootLevel;
+    uint8_t                             GraphicsVoltageChangeEnable;
+    uint8_t                             GraphicsThermThrottleEnable;
+    uint8_t                             GraphicsInterval;
+
+    uint8_t                             VoltageInterval;
+    uint8_t                             ThermalInterval;
+    uint16_t                            TemperatureLimitHigh;
+
+    uint16_t                            TemperatureLimitLow;
+    uint8_t                             MemoryBootLevel;
+    uint8_t                             MemoryVoltageChangeEnable;
+
+    uint8_t                             MemoryInterval;
+    uint8_t                             MemoryThermThrottleEnable;
+    uint16_t                            VddcVddciDelta;
+
+    uint16_t                            VoltageResponseTime;
+    uint16_t                            PhaseResponseTime;
+
+    uint8_t                             PCIeBootLinkLevel;
+    uint8_t                             PCIeGenInterval;
+    uint8_t                             DTEInterval;
+    uint8_t                             DTEMode;
+
+    uint8_t                             SVI2Enable;
+    uint8_t                             VRHotGpio;
+    uint8_t                             AcDcGpio;
+    uint8_t                             ThermGpio;
+
+    uint16_t                            PPM_PkgPwrLimit;
+    uint16_t                            PPM_TemperatureLimit;
+
+    uint16_t                            DefaultTdp;
+    uint16_t                            TargetTdp;
+
+    uint16_t                            FpsHighT;
+    uint16_t                            FpsLowT;
+
+    uint16_t                            BAPMTI_R  [SMU7_DTE_ITERATIONS][SMU7_DTE_SOURCES][SMU7_DTE_SINKS];
+    uint16_t                            BAPMTI_RC [SMU7_DTE_ITERATIONS][SMU7_DTE_SOURCES][SMU7_DTE_SINKS];
+
+    uint8_t                             DTEAmbientTempBase;
+    uint8_t                             DTETjOffset;
+    uint8_t                             GpuTjMax;
+    uint8_t                             GpuTjHyst;
+
+    uint16_t                            BootVddc;
+    uint16_t                            BootVddci;
+
+    uint16_t                            BootMVdd;
+    uint16_t                            padding;
+
+    uint32_t                            BAPM_TEMP_GRADIENT;
+
+    uint32_t                            LowSclkInterruptT;
+};
+
+typedef struct SMU7_Discrete_DpmTable SMU7_Discrete_DpmTable;
+
+#define SMU7_DISCRETE_MC_REGISTER_ARRAY_SIZE 16
+#define SMU7_DISCRETE_MC_REGISTER_ARRAY_SET_COUNT SMU7_MAX_LEVELS_MEMORY
+
+struct SMU7_Discrete_MCRegisterAddress
+{
+    uint16_t s0;
+    uint16_t s1;
+};
+
+typedef struct SMU7_Discrete_MCRegisterAddress SMU7_Discrete_MCRegisterAddress;
+
+struct SMU7_Discrete_MCRegisterSet
+{
+    uint32_t value[SMU7_DISCRETE_MC_REGISTER_ARRAY_SIZE];
+};
+
+typedef struct SMU7_Discrete_MCRegisterSet SMU7_Discrete_MCRegisterSet;
+
+struct SMU7_Discrete_MCRegisters
+{
+    uint8_t                             last;
+    uint8_t                             reserved[3];
+    SMU7_Discrete_MCRegisterAddress     address[SMU7_DISCRETE_MC_REGISTER_ARRAY_SIZE];
+    SMU7_Discrete_MCRegisterSet         data[SMU7_DISCRETE_MC_REGISTER_ARRAY_SET_COUNT];
+};
+
+typedef struct SMU7_Discrete_MCRegisters SMU7_Discrete_MCRegisters;
+
+struct SMU7_Discrete_PmFuses {
+  // dw0-dw1
+  uint8_t BapmVddCVidHiSidd[8];
+
+  // dw2-dw3
+  uint8_t BapmVddCVidLoSidd[8];
+
+  // dw4-dw5
+  uint8_t VddCVid[8];
+
+  // dw6
+  uint8_t SviLoadLineEn;
+  uint8_t SviLoadLineVddC;
+  uint8_t SviLoadLineTrimVddC;
+  uint8_t SviLoadLineOffsetVddC;
+
+  // dw7
+  uint16_t TDC_VDDC_PkgLimit;
+  uint8_t TDC_VDDC_ThrottleReleaseLimitPerc;
+  uint8_t TDC_MAWt;
+
+  // dw8
+  uint8_t TdcWaterfallCtl;
+  uint8_t LPMLTemperatureMin;
+  uint8_t LPMLTemperatureMax;
+  uint8_t Reserved;
+
+  // dw9-dw10
+  uint8_t BapmVddCVidHiSidd2[8];
+
+  // dw11-dw12
+  uint32_t Reserved6[2];
+
+  // dw13-dw16
+  uint8_t GnbLPML[16];
+
+  // dw17
+  uint8_t GnbLPMLMaxVid;
+  uint8_t GnbLPMLMinVid;
+  uint8_t Reserved1[2];
+
+  // dw18
+  uint16_t BapmVddCBaseLeakageHiSidd;
+  uint16_t BapmVddCBaseLeakageLoSidd;
+};
+
+typedef struct SMU7_Discrete_PmFuses SMU7_Discrete_PmFuses;
+
+
+#pragma pack(pop)
+
+#endif
+
diff --git a/drivers/gpu/drm/radeon/smu7_fusion.h b/drivers/gpu/drm/radeon/smu7_fusion.h
new file mode 100644
index 000000000000..78ada9ffd508
--- /dev/null
+++ b/drivers/gpu/drm/radeon/smu7_fusion.h
@@ -0,0 +1,300 @@
+/*
+ * Copyright 2013 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+
+#ifndef SMU7_FUSION_H
+#define SMU7_FUSION_H
+
+#include "smu7.h"
+
+#pragma pack(push, 1)
+
+#define SMU7_DTE_ITERATIONS 5
+#define SMU7_DTE_SOURCES 5
+#define SMU7_DTE_SINKS 3
+#define SMU7_NUM_CPU_TES 2
+#define SMU7_NUM_GPU_TES 1
+#define SMU7_NUM_NON_TES 2
+
+// All 'soft registers' should be uint32_t.
+struct SMU7_SoftRegisters
+{
+    uint32_t        RefClockFrequency;
+    uint32_t        PmTimerP;
+    uint32_t        FeatureEnables;
+    uint32_t        HandshakeDisables;
+
+    uint8_t         DisplayPhy1Config;
+    uint8_t         DisplayPhy2Config;
+    uint8_t         DisplayPhy3Config;
+    uint8_t         DisplayPhy4Config;
+
+    uint8_t         DisplayPhy5Config;
+    uint8_t         DisplayPhy6Config;
+    uint8_t         DisplayPhy7Config;
+    uint8_t         DisplayPhy8Config;
+
+    uint32_t        AverageGraphicsA;
+    uint32_t        AverageMemoryA;
+    uint32_t        AverageGioA;
+
+    uint8_t         SClkDpmEnabledLevels;
+    uint8_t         MClkDpmEnabledLevels;
+    uint8_t         LClkDpmEnabledLevels;
+    uint8_t         PCIeDpmEnabledLevels;
+
+    uint8_t         UVDDpmEnabledLevels;
+    uint8_t         SAMUDpmEnabledLevels;
+    uint8_t         ACPDpmEnabledLevels;
+    uint8_t         VCEDpmEnabledLevels;
+
+    uint32_t        DRAM_LOG_ADDR_H;
+    uint32_t        DRAM_LOG_ADDR_L;
+    uint32_t        DRAM_LOG_PHY_ADDR_H;
+    uint32_t        DRAM_LOG_PHY_ADDR_L;
+    uint32_t        DRAM_LOG_BUFF_SIZE;
+    uint32_t        UlvEnterC;
+    uint32_t        UlvTime;
+    uint32_t        Reserved[3];
+
+};
+
+typedef struct SMU7_SoftRegisters SMU7_SoftRegisters;
+
+struct SMU7_Fusion_GraphicsLevel
+{
+    uint32_t    MinVddNb;
+
+    uint32_t    SclkFrequency;
+
+    uint8_t     Vid;
+    uint8_t     VidOffset;
+    uint16_t    AT;
+
+    uint8_t     PowerThrottle;
+    uint8_t     GnbSlow;
+    uint8_t     ForceNbPs1;
+    uint8_t     SclkDid;
+
+    uint8_t     DisplayWatermark;
+    uint8_t     EnabledForActivity;
+    uint8_t     EnabledForThrottle;
+    uint8_t     UpH;
+
+    uint8_t     DownH;
+    uint8_t     VoltageDownH;
+    uint8_t     DeepSleepDivId;
+
+    uint8_t     ClkBypassCntl;
+
+    uint32_t    reserved;
+};
+
+typedef struct SMU7_Fusion_GraphicsLevel SMU7_Fusion_GraphicsLevel;
+
+struct SMU7_Fusion_GIOLevel
+{
+    uint8_t     EnabledForActivity;
+    uint8_t     LclkDid;
+    uint8_t     Vid;
+    uint8_t     VoltageDownH;
+
+    uint32_t    MinVddNb;
+
+    uint16_t    ResidencyCounter;
+    uint8_t     UpH;
+    uint8_t     DownH;
+
+    uint32_t    LclkFrequency;
+
+    uint8_t     ActivityLevel;
+    uint8_t     EnabledForThrottle;
+
+    uint8_t     ClkBypassCntl;
+
+    uint8_t     padding;
+};
+
+typedef struct SMU7_Fusion_GIOLevel SMU7_Fusion_GIOLevel;
+
+// UVD VCLK/DCLK state (level) definition.
+struct SMU7_Fusion_UvdLevel
+{
+    uint32_t VclkFrequency;
+    uint32_t DclkFrequency;
+    uint16_t MinVddNb;
+    uint8_t  VclkDivider;
+    uint8_t  DclkDivider;
+
+    uint8_t     VClkBypassCntl;
+    uint8_t     DClkBypassCntl;
+
+    uint8_t     padding[2];
+
+};
+
+typedef struct SMU7_Fusion_UvdLevel SMU7_Fusion_UvdLevel;
+
+// Clocks for other external blocks (VCE, ACP, SAMU).
+struct SMU7_Fusion_ExtClkLevel
+{
+    uint32_t Frequency;
+    uint16_t MinVoltage;
+    uint8_t  Divider;
+    uint8_t  ClkBypassCntl;
+
+    uint32_t Reserved;
+};
+typedef struct SMU7_Fusion_ExtClkLevel SMU7_Fusion_ExtClkLevel;
+
+struct SMU7_Fusion_ACPILevel
+{
+    uint32_t    Flags;
+    uint32_t    MinVddNb;
+    uint32_t    SclkFrequency;
+    uint8_t     SclkDid;
+    uint8_t     GnbSlow;
+    uint8_t     ForceNbPs1;
+    uint8_t     DisplayWatermark;
+    uint8_t     DeepSleepDivId;
+    uint8_t     padding[3];
+};
+
+typedef struct SMU7_Fusion_ACPILevel SMU7_Fusion_ACPILevel;
+
+struct SMU7_Fusion_NbDpm
+{
+    uint8_t DpmXNbPsHi;
+    uint8_t DpmXNbPsLo;
+    uint8_t Dpm0PgNbPsHi;
+    uint8_t Dpm0PgNbPsLo;
+    uint8_t EnablePsi1;
+    uint8_t SkipDPM0;
+    uint8_t SkipPG;
+    uint8_t Hysteresis;
+    uint8_t EnableDpmPstatePoll;
+    uint8_t padding[3];
+};
+
+typedef struct SMU7_Fusion_NbDpm SMU7_Fusion_NbDpm;
+
+struct SMU7_Fusion_StateInfo
+{
+    uint32_t SclkFrequency;
+    uint32_t LclkFrequency;
+    uint32_t VclkFrequency;
+    uint32_t DclkFrequency;
+    uint32_t SamclkFrequency;
+    uint32_t AclkFrequency;
+    uint32_t EclkFrequency;
+    uint8_t  DisplayWatermark;
+    uint8_t  McArbIndex;
+    int8_t   SclkIndex;
+    int8_t   MclkIndex;
+};
+
+typedef struct SMU7_Fusion_StateInfo SMU7_Fusion_StateInfo;
+
+struct SMU7_Fusion_DpmTable
+{
+    uint32_t                            SystemFlags;
+
+    SMU7_PIDController                  GraphicsPIDController;
+    SMU7_PIDController                  GioPIDController;
+
+    uint8_t                            GraphicsDpmLevelCount;
+    uint8_t                            GIOLevelCount;
+    uint8_t                            UvdLevelCount;
+    uint8_t                            VceLevelCount;
+
+    uint8_t                            AcpLevelCount;
+    uint8_t                            SamuLevelCount;
+    uint16_t                           FpsHighT;
+
+    SMU7_Fusion_GraphicsLevel         GraphicsLevel           [SMU__NUM_SCLK_DPM_STATE];
+    SMU7_Fusion_ACPILevel             ACPILevel;
+    SMU7_Fusion_UvdLevel              UvdLevel                [SMU7_MAX_LEVELS_UVD];
+    SMU7_Fusion_ExtClkLevel           VceLevel                [SMU7_MAX_LEVELS_VCE];
+    SMU7_Fusion_ExtClkLevel           AcpLevel                [SMU7_MAX_LEVELS_ACP];
+    SMU7_Fusion_ExtClkLevel           SamuLevel               [SMU7_MAX_LEVELS_SAMU];
+
+    uint8_t                           UvdBootLevel;
+    uint8_t                           VceBootLevel;
+    uint8_t                           AcpBootLevel;
+    uint8_t                           SamuBootLevel;
+    uint8_t                           UVDInterval;
+    uint8_t                           VCEInterval;
+    uint8_t                           ACPInterval;
+    uint8_t                           SAMUInterval;
+
+    uint8_t                           GraphicsBootLevel;
+    uint8_t                           GraphicsInterval;
+    uint8_t                           GraphicsThermThrottleEnable;
+    uint8_t                           GraphicsVoltageChangeEnable;
+
+    uint8_t                           GraphicsClkSlowEnable;
+    uint8_t                           GraphicsClkSlowDivider;
+    uint16_t                          FpsLowT;
+
+    uint32_t                          DisplayCac;
+    uint32_t                          LowSclkInterruptT;
+
+    uint32_t                          DRAM_LOG_ADDR_H;
+    uint32_t                          DRAM_LOG_ADDR_L;
+    uint32_t                          DRAM_LOG_PHY_ADDR_H;
+    uint32_t                          DRAM_LOG_PHY_ADDR_L;
+    uint32_t                          DRAM_LOG_BUFF_SIZE;
+
+};
+
+struct SMU7_Fusion_GIODpmTable
+{
+
+    SMU7_Fusion_GIOLevel              GIOLevel                [SMU7_MAX_LEVELS_GIO];
+
+    SMU7_PIDController                GioPIDController;
+
+    uint32_t                          GIOLevelCount;
+
+    uint8_t                           Enable;
+    uint8_t                           GIOVoltageChangeEnable;
+    uint8_t                           GIOBootLevel;
+    uint8_t                           padding;
+    uint8_t                           padding1[2];
+    uint8_t                           TargetState;
+    uint8_t                           CurrenttState;
+    uint8_t                           ThrottleOnHtc;
+    uint8_t                           ThermThrottleStatus;
+    uint8_t                           ThermThrottleTempSelect;
+    uint8_t                           ThermThrottleEnable;
+    uint16_t                          TemperatureLimitHigh;
+    uint16_t                          TemperatureLimitLow;
+
+};
+
+typedef struct SMU7_Fusion_DpmTable SMU7_Fusion_DpmTable;
+typedef struct SMU7_Fusion_GIODpmTable SMU7_Fusion_GIODpmTable;
+
+#pragma pack(pop)
+
+#endif
+
diff --git a/drivers/gpu/drm/radeon/sumo_dpm.c b/drivers/gpu/drm/radeon/sumo_dpm.c
index c0a850319908..96ea6db8bf57 100644
--- a/drivers/gpu/drm/radeon/sumo_dpm.c
+++ b/drivers/gpu/drm/radeon/sumo_dpm.c
@@ -1319,8 +1319,6 @@ int sumo_dpm_set_power_state(struct radeon_device *rdev)
 	if (pi->enable_dpm)
 		sumo_set_uvd_clock_after_set_eng_clock(rdev, new_ps, old_ps);
 
-	rdev->pm.dpm.forced_level = RADEON_DPM_FORCED_LEVEL_AUTO;
-
 	return 0;
 }
 
@@ -1483,6 +1481,7 @@ static int sumo_parse_power_table(struct radeon_device *rdev)
 	rdev->pm.dpm.backbias_response_time = le16_to_cpu(power_info->pplib.usBackbiasTime);
 	rdev->pm.dpm.voltage_response_time = le16_to_cpu(power_info->pplib.usVoltageTime);
 	for (i = 0; i < state_array->ucNumEntries; i++) {
+		u8 *idx;
 		power_state = (union pplib_power_state *)power_state_offset;
 		non_clock_array_index = power_state->v2.nonClockInfoIndex;
 		non_clock_info = (struct _ATOM_PPLIB_NONCLOCK_INFO *)
@@ -1496,12 +1495,15 @@ static int sumo_parse_power_table(struct radeon_device *rdev)
 		}
 		rdev->pm.dpm.ps[i].ps_priv = ps;
 		k = 0;
+		idx = (u8 *)&power_state->v2.clockInfoIndex[0];
 		for (j = 0; j < power_state->v2.ucNumDPMLevels; j++) {
-			clock_array_index = power_state->v2.clockInfoIndex[j];
+			clock_array_index = idx[j];
 			if (k >= SUMO_MAX_HARDWARE_POWERLEVELS)
 				break;
+
 			clock_info = (union pplib_clock_info *)
-				&clock_info_array->clockInfo[clock_array_index * clock_info_array->ucEntrySize];
+				((u8 *)&clock_info_array->clockInfo[0] +
+				 (clock_array_index * clock_info_array->ucEntrySize));
 			sumo_parse_pplib_clock_info(rdev,
 						    &rdev->pm.dpm.ps[i], k,
 						    clock_info);
@@ -1530,6 +1532,20 @@ u32 sumo_convert_vid2_to_vid7(struct radeon_device *rdev,
 	return vid_mapping_table->entries[vid_mapping_table->num_entries - 1].vid_7bit;
 }
 
+u32 sumo_convert_vid7_to_vid2(struct radeon_device *rdev,
+			      struct sumo_vid_mapping_table *vid_mapping_table,
+			      u32 vid_7bit)
+{
+	u32 i;
+
+	for (i = 0; i < vid_mapping_table->num_entries; i++) {
+		if (vid_mapping_table->entries[i].vid_7bit == vid_7bit)
+			return vid_mapping_table->entries[i].vid_2bit;
+	}
+
+	return vid_mapping_table->entries[vid_mapping_table->num_entries - 1].vid_2bit;
+}
+
 static u16 sumo_convert_voltage_index_to_value(struct radeon_device *rdev,
 					       u32 vid_2bit)
 {
diff --git a/drivers/gpu/drm/radeon/sumo_dpm.h b/drivers/gpu/drm/radeon/sumo_dpm.h
index 07dda299c784..db1ea32a907b 100644
--- a/drivers/gpu/drm/radeon/sumo_dpm.h
+++ b/drivers/gpu/drm/radeon/sumo_dpm.h
@@ -202,6 +202,9 @@ void sumo_construct_vid_mapping_table(struct radeon_device *rdev,
 u32 sumo_convert_vid2_to_vid7(struct radeon_device *rdev,
 			      struct sumo_vid_mapping_table *vid_mapping_table,
 			      u32 vid_2bit);
+u32 sumo_convert_vid7_to_vid2(struct radeon_device *rdev,
+			      struct sumo_vid_mapping_table *vid_mapping_table,
+			      u32 vid_7bit);
 u32 sumo_get_sleep_divider_from_id(u32 id);
 u32 sumo_get_sleep_divider_id_from_clock(struct radeon_device *rdev,
 					 u32 sclk,
diff --git a/drivers/gpu/drm/radeon/trinity_dpm.c b/drivers/gpu/drm/radeon/trinity_dpm.c
index a1eb5f59939f..9364129ba292 100644
--- a/drivers/gpu/drm/radeon/trinity_dpm.c
+++ b/drivers/gpu/drm/radeon/trinity_dpm.c
@@ -1068,6 +1068,17 @@ static void trinity_update_requested_ps(struct radeon_device *rdev,
 	pi->requested_rps.ps_priv = &pi->requested_ps;
 }
 
+void trinity_dpm_enable_bapm(struct radeon_device *rdev, bool enable)
+{
+	struct trinity_power_info *pi = trinity_get_pi(rdev);
+
+	if (pi->enable_bapm) {
+		trinity_acquire_mutex(rdev);
+		trinity_dpm_bapm_enable(rdev, enable);
+		trinity_release_mutex(rdev);
+	}
+}
+
 int trinity_dpm_enable(struct radeon_device *rdev)
 {
 	struct trinity_power_info *pi = trinity_get_pi(rdev);
@@ -1091,6 +1102,7 @@ int trinity_dpm_enable(struct radeon_device *rdev)
 	trinity_program_sclk_dpm(rdev);
 	trinity_start_dpm(rdev);
 	trinity_wait_for_dpm_enabled(rdev);
+	trinity_dpm_bapm_enable(rdev, false);
 	trinity_release_mutex(rdev);
 
 	if (rdev->irq.installed &&
@@ -1116,6 +1128,7 @@ void trinity_dpm_disable(struct radeon_device *rdev)
 		trinity_release_mutex(rdev);
 		return;
 	}
+	trinity_dpm_bapm_enable(rdev, false);
 	trinity_disable_clock_power_gating(rdev);
 	sumo_clear_vc(rdev);
 	trinity_wait_for_level_0(rdev);
@@ -1212,6 +1225,8 @@ int trinity_dpm_set_power_state(struct radeon_device *rdev)
 
 	trinity_acquire_mutex(rdev);
 	if (pi->enable_dpm) {
+		if (pi->enable_bapm)
+			trinity_dpm_bapm_enable(rdev, rdev->pm.dpm.ac_power);
 		trinity_set_uvd_clock_before_set_eng_clock(rdev, new_ps, old_ps);
 		trinity_enable_power_level_0(rdev);
 		trinity_force_level_0(rdev);
@@ -1221,7 +1236,6 @@ int trinity_dpm_set_power_state(struct radeon_device *rdev)
 		trinity_force_level_0(rdev);
 		trinity_unforce_levels(rdev);
 		trinity_set_uvd_clock_after_set_eng_clock(rdev, new_ps, old_ps);
-		rdev->pm.dpm.forced_level = RADEON_DPM_FORCED_LEVEL_AUTO;
 	}
 	trinity_release_mutex(rdev);
 
@@ -1675,6 +1689,7 @@ static int trinity_parse_power_table(struct radeon_device *rdev)
 	rdev->pm.dpm.backbias_response_time = le16_to_cpu(power_info->pplib.usBackbiasTime);
 	rdev->pm.dpm.voltage_response_time = le16_to_cpu(power_info->pplib.usVoltageTime);
 	for (i = 0; i < state_array->ucNumEntries; i++) {
+		u8 *idx;
 		power_state = (union pplib_power_state *)power_state_offset;
 		non_clock_array_index = power_state->v2.nonClockInfoIndex;
 		non_clock_info = (struct _ATOM_PPLIB_NONCLOCK_INFO *)
@@ -1688,14 +1703,16 @@ static int trinity_parse_power_table(struct radeon_device *rdev)
 		}
 		rdev->pm.dpm.ps[i].ps_priv = ps;
 		k = 0;
+		idx = (u8 *)&power_state->v2.clockInfoIndex[0];
 		for (j = 0; j < power_state->v2.ucNumDPMLevels; j++) {
-			clock_array_index = power_state->v2.clockInfoIndex[j];
+			clock_array_index = idx[j];
 			if (clock_array_index >= clock_info_array->ucNumEntries)
 				continue;
 			if (k >= SUMO_MAX_HARDWARE_POWERLEVELS)
 				break;
 			clock_info = (union pplib_clock_info *)
-				&clock_info_array->clockInfo[clock_array_index * clock_info_array->ucEntrySize];
+				((u8 *)&clock_info_array->clockInfo[0] +
+				 (clock_array_index * clock_info_array->ucEntrySize));
 			trinity_parse_pplib_clock_info(rdev,
 						       &rdev->pm.dpm.ps[i], k,
 						       clock_info);
@@ -1851,6 +1868,7 @@ int trinity_dpm_init(struct radeon_device *rdev)
 	for (i = 0; i < SUMO_MAX_HARDWARE_POWERLEVELS; i++)
 		pi->at[i] = TRINITY_AT_DFLT;
 
+	pi->enable_bapm = false;
 	pi->enable_nbps_policy = true;
 	pi->enable_sclk_ds = true;
 	pi->enable_gfx_power_gating = true;
diff --git a/drivers/gpu/drm/radeon/trinity_dpm.h b/drivers/gpu/drm/radeon/trinity_dpm.h
index e82df071f8b3..c261657750ca 100644
--- a/drivers/gpu/drm/radeon/trinity_dpm.h
+++ b/drivers/gpu/drm/radeon/trinity_dpm.h
@@ -108,6 +108,7 @@ struct trinity_power_info {
 	bool enable_auto_thermal_throttling;
 	bool enable_dpm;
 	bool enable_sclk_ds;
+	bool enable_bapm;
 	bool uvd_dpm;
 	struct radeon_ps current_rps;
 	struct trinity_ps current_ps;
@@ -118,6 +119,7 @@ struct trinity_power_info {
 #define TRINITY_AT_DFLT            30
 
 /* trinity_smc.c */
+int trinity_dpm_bapm_enable(struct radeon_device *rdev, bool enable);
 int trinity_dpm_config(struct radeon_device *rdev, bool enable);
 int trinity_uvd_dpm_config(struct radeon_device *rdev);
 int trinity_dpm_force_state(struct radeon_device *rdev, u32 n);
diff --git a/drivers/gpu/drm/radeon/trinity_smc.c b/drivers/gpu/drm/radeon/trinity_smc.c
index a42d89f1830c..9672bcbc7312 100644
--- a/drivers/gpu/drm/radeon/trinity_smc.c
+++ b/drivers/gpu/drm/radeon/trinity_smc.c
@@ -56,6 +56,14 @@ static int trinity_notify_message_to_smu(struct radeon_device *rdev, u32 id)
 	return 0;
 }
 
+int trinity_dpm_bapm_enable(struct radeon_device *rdev, bool enable)
+{
+	if (enable)
+		return trinity_notify_message_to_smu(rdev, PPSMC_MSG_EnableBAPM);
+	else
+		return trinity_notify_message_to_smu(rdev, PPSMC_MSG_DisableBAPM);
+}
+
 int trinity_dpm_config(struct radeon_device *rdev, bool enable)
 {
 	if (enable)
diff --git a/drivers/gpu/drm/radeon/uvd_v1_0.c b/drivers/gpu/drm/radeon/uvd_v1_0.c
new file mode 100644
index 000000000000..3100fa9cb52f
--- /dev/null
+++ b/drivers/gpu/drm/radeon/uvd_v1_0.c
@@ -0,0 +1,436 @@
+/*
+ * Copyright 2013 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: Christian König <christian.koenig@amd.com>
+ */
+
+#include <drm/drmP.h>
+#include "radeon.h"
+#include "radeon_asic.h"
+#include "r600d.h"
+
+/**
+ * uvd_v1_0_get_rptr - get read pointer
+ *
+ * @rdev: radeon_device pointer
+ * @ring: radeon_ring pointer
+ *
+ * Returns the current hardware read pointer
+ */
+uint32_t uvd_v1_0_get_rptr(struct radeon_device *rdev,
+			   struct radeon_ring *ring)
+{
+	return RREG32(UVD_RBC_RB_RPTR);
+}
+
+/**
+ * uvd_v1_0_get_wptr - get write pointer
+ *
+ * @rdev: radeon_device pointer
+ * @ring: radeon_ring pointer
+ *
+ * Returns the current hardware write pointer
+ */
+uint32_t uvd_v1_0_get_wptr(struct radeon_device *rdev,
+			   struct radeon_ring *ring)
+{
+	return RREG32(UVD_RBC_RB_WPTR);
+}
+
+/**
+ * uvd_v1_0_set_wptr - set write pointer
+ *
+ * @rdev: radeon_device pointer
+ * @ring: radeon_ring pointer
+ *
+ * Commits the write pointer to the hardware
+ */
+void uvd_v1_0_set_wptr(struct radeon_device *rdev,
+		       struct radeon_ring *ring)
+{
+	WREG32(UVD_RBC_RB_WPTR, ring->wptr);
+}
+
+/**
+ * uvd_v1_0_init - start and test UVD block
+ *
+ * @rdev: radeon_device pointer
+ *
+ * Initialize the hardware, boot up the VCPU and do some testing
+ */
+int uvd_v1_0_init(struct radeon_device *rdev)
+{
+	struct radeon_ring *ring = &rdev->ring[R600_RING_TYPE_UVD_INDEX];
+	uint32_t tmp;
+	int r;
+
+	/* raise clocks while booting up the VCPU */
+	radeon_set_uvd_clocks(rdev, 53300, 40000);
+
+	r = uvd_v1_0_start(rdev);
+	if (r)
+		goto done;
+
+	ring->ready = true;
+	r = radeon_ring_test(rdev, R600_RING_TYPE_UVD_INDEX, ring);
+	if (r) {
+		ring->ready = false;
+		goto done;
+	}
+
+	r = radeon_ring_lock(rdev, ring, 10);
+	if (r) {
+		DRM_ERROR("radeon: ring failed to lock UVD ring (%d).\n", r);
+		goto done;
+	}
+
+	tmp = PACKET0(UVD_SEMA_WAIT_FAULT_TIMEOUT_CNTL, 0);
+	radeon_ring_write(ring, tmp);
+	radeon_ring_write(ring, 0xFFFFF);
+
+	tmp = PACKET0(UVD_SEMA_WAIT_INCOMPLETE_TIMEOUT_CNTL, 0);
+	radeon_ring_write(ring, tmp);
+	radeon_ring_write(ring, 0xFFFFF);
+
+	tmp = PACKET0(UVD_SEMA_SIGNAL_INCOMPLETE_TIMEOUT_CNTL, 0);
+	radeon_ring_write(ring, tmp);
+	radeon_ring_write(ring, 0xFFFFF);
+
+	/* Clear timeout status bits */
+	radeon_ring_write(ring, PACKET0(UVD_SEMA_TIMEOUT_STATUS, 0));
+	radeon_ring_write(ring, 0x8);
+
+	radeon_ring_write(ring, PACKET0(UVD_SEMA_CNTL, 0));
+	radeon_ring_write(ring, 3);
+
+	radeon_ring_unlock_commit(rdev, ring);
+
+done:
+	/* lower clocks again */
+	radeon_set_uvd_clocks(rdev, 0, 0);
+
+	if (!r)
+		DRM_INFO("UVD initialized successfully.\n");
+
+	return r;
+}
+
+/**
+ * uvd_v1_0_fini - stop the hardware block
+ *
+ * @rdev: radeon_device pointer
+ *
+ * Stop the UVD block, mark ring as not ready any more
+ */
+void uvd_v1_0_fini(struct radeon_device *rdev)
+{
+	struct radeon_ring *ring = &rdev->ring[R600_RING_TYPE_UVD_INDEX];
+
+	uvd_v1_0_stop(rdev);
+	ring->ready = false;
+}
+
+/**
+ * uvd_v1_0_start - start UVD block
+ *
+ * @rdev: radeon_device pointer
+ *
+ * Setup and start the UVD block
+ */
+int uvd_v1_0_start(struct radeon_device *rdev)
+{
+	struct radeon_ring *ring = &rdev->ring[R600_RING_TYPE_UVD_INDEX];
+	uint32_t rb_bufsz;
+	int i, j, r;
+
+	/* disable byte swapping */
+	u32 lmi_swap_cntl = 0;
+	u32 mp_swap_cntl = 0;
+
+	/* disable clock gating */
+	WREG32(UVD_CGC_GATE, 0);
+
+	/* disable interupt */
+	WREG32_P(UVD_MASTINT_EN, 0, ~(1 << 1));
+
+	/* Stall UMC and register bus before resetting VCPU */
+	WREG32_P(UVD_LMI_CTRL2, 1 << 8, ~(1 << 8));
+	WREG32_P(UVD_RB_ARB_CTRL, 1 << 3, ~(1 << 3));
+	mdelay(1);
+
+	/* put LMI, VCPU, RBC etc... into reset */
+	WREG32(UVD_SOFT_RESET, LMI_SOFT_RESET | VCPU_SOFT_RESET |
+	       LBSI_SOFT_RESET | RBC_SOFT_RESET | CSM_SOFT_RESET |
+	       CXW_SOFT_RESET | TAP_SOFT_RESET | LMI_UMC_SOFT_RESET);
+	mdelay(5);
+
+	/* take UVD block out of reset */
+	WREG32_P(SRBM_SOFT_RESET, 0, ~SOFT_RESET_UVD);
+	mdelay(5);
+
+	/* initialize UVD memory controller */
+	WREG32(UVD_LMI_CTRL, 0x40 | (1 << 8) | (1 << 13) |
+			     (1 << 21) | (1 << 9) | (1 << 20));
+
+#ifdef __BIG_ENDIAN
+	/* swap (8 in 32) RB and IB */
+	lmi_swap_cntl = 0xa;
+	mp_swap_cntl = 0;
+#endif
+	WREG32(UVD_LMI_SWAP_CNTL, lmi_swap_cntl);
+	WREG32(UVD_MP_SWAP_CNTL, mp_swap_cntl);
+
+	WREG32(UVD_MPC_SET_MUXA0, 0x40c2040);
+	WREG32(UVD_MPC_SET_MUXA1, 0x0);
+	WREG32(UVD_MPC_SET_MUXB0, 0x40c2040);
+	WREG32(UVD_MPC_SET_MUXB1, 0x0);
+	WREG32(UVD_MPC_SET_ALU, 0);
+	WREG32(UVD_MPC_SET_MUX, 0x88);
+
+	/* take all subblocks out of reset, except VCPU */
+	WREG32(UVD_SOFT_RESET, VCPU_SOFT_RESET);
+	mdelay(5);
+
+	/* enable VCPU clock */
+	WREG32(UVD_VCPU_CNTL,  1 << 9);
+
+	/* enable UMC and NC0 */
+	WREG32_P(UVD_LMI_CTRL2, 1 << 13, ~((1 << 8) | (1 << 13)));
+
+	/* boot up the VCPU */
+	WREG32(UVD_SOFT_RESET, 0);
+	mdelay(10);
+
+	WREG32_P(UVD_RB_ARB_CTRL, 0, ~(1 << 3));
+
+	for (i = 0; i < 10; ++i) {
+		uint32_t status;
+		for (j = 0; j < 100; ++j) {
+			status = RREG32(UVD_STATUS);
+			if (status & 2)
+				break;
+			mdelay(10);
+		}
+		r = 0;
+		if (status & 2)
+			break;
+
+		DRM_ERROR("UVD not responding, trying to reset the VCPU!!!\n");
+		WREG32_P(UVD_SOFT_RESET, VCPU_SOFT_RESET, ~VCPU_SOFT_RESET);
+		mdelay(10);
+		WREG32_P(UVD_SOFT_RESET, 0, ~VCPU_SOFT_RESET);
+		mdelay(10);
+		r = -1;
+	}
+
+	if (r) {
+		DRM_ERROR("UVD not responding, giving up!!!\n");
+		return r;
+	}
+
+	/* enable interupt */
+	WREG32_P(UVD_MASTINT_EN, 3<<1, ~(3 << 1));
+
+	/* force RBC into idle state */
+	WREG32(UVD_RBC_RB_CNTL, 0x11010101);
+
+	/* Set the write pointer delay */
+	WREG32(UVD_RBC_RB_WPTR_CNTL, 0);
+
+	/* programm the 4GB memory segment for rptr and ring buffer */
+	WREG32(UVD_LMI_EXT40_ADDR, upper_32_bits(ring->gpu_addr) |
+				   (0x7 << 16) | (0x1 << 31));
+
+	/* Initialize the ring buffer's read and write pointers */
+	WREG32(UVD_RBC_RB_RPTR, 0x0);
+
+	ring->wptr = ring->rptr = RREG32(UVD_RBC_RB_RPTR);
+	WREG32(UVD_RBC_RB_WPTR, ring->wptr);
+
+	/* set the ring address */
+	WREG32(UVD_RBC_RB_BASE, ring->gpu_addr);
+
+	/* Set ring buffer size */
+	rb_bufsz = order_base_2(ring->ring_size);
+	rb_bufsz = (0x1 << 8) | rb_bufsz;
+	WREG32_P(UVD_RBC_RB_CNTL, rb_bufsz, ~0x11f1f);
+
+	return 0;
+}
+
+/**
+ * uvd_v1_0_stop - stop UVD block
+ *
+ * @rdev: radeon_device pointer
+ *
+ * stop the UVD block
+ */
+void uvd_v1_0_stop(struct radeon_device *rdev)
+{
+	/* force RBC into idle state */
+	WREG32(UVD_RBC_RB_CNTL, 0x11010101);
+
+	/* Stall UMC and register bus before resetting VCPU */
+	WREG32_P(UVD_LMI_CTRL2, 1 << 8, ~(1 << 8));
+	WREG32_P(UVD_RB_ARB_CTRL, 1 << 3, ~(1 << 3));
+	mdelay(1);
+
+	/* put VCPU into reset */
+	WREG32(UVD_SOFT_RESET, VCPU_SOFT_RESET);
+	mdelay(5);
+
+	/* disable VCPU clock */
+	WREG32(UVD_VCPU_CNTL, 0x0);
+
+	/* Unstall UMC and register bus */
+	WREG32_P(UVD_LMI_CTRL2, 0, ~(1 << 8));
+	WREG32_P(UVD_RB_ARB_CTRL, 0, ~(1 << 3));
+}
+
+/**
+ * uvd_v1_0_ring_test - register write test
+ *
+ * @rdev: radeon_device pointer
+ * @ring: radeon_ring pointer
+ *
+ * Test if we can successfully write to the context register
+ */
+int uvd_v1_0_ring_test(struct radeon_device *rdev, struct radeon_ring *ring)
+{
+	uint32_t tmp = 0;
+	unsigned i;
+	int r;
+
+	WREG32(UVD_CONTEXT_ID, 0xCAFEDEAD);
+	r = radeon_ring_lock(rdev, ring, 3);
+	if (r) {
+		DRM_ERROR("radeon: cp failed to lock ring %d (%d).\n",
+			  ring->idx, r);
+		return r;
+	}
+	radeon_ring_write(ring, PACKET0(UVD_CONTEXT_ID, 0));
+	radeon_ring_write(ring, 0xDEADBEEF);
+	radeon_ring_unlock_commit(rdev, ring);
+	for (i = 0; i < rdev->usec_timeout; i++) {
+		tmp = RREG32(UVD_CONTEXT_ID);
+		if (tmp == 0xDEADBEEF)
+			break;
+		DRM_UDELAY(1);
+	}
+
+	if (i < rdev->usec_timeout) {
+		DRM_INFO("ring test on %d succeeded in %d usecs\n",
+			 ring->idx, i);
+	} else {
+		DRM_ERROR("radeon: ring %d test failed (0x%08X)\n",
+			  ring->idx, tmp);
+		r = -EINVAL;
+	}
+	return r;
+}
+
+/**
+ * uvd_v1_0_semaphore_emit - emit semaphore command
+ *
+ * @rdev: radeon_device pointer
+ * @ring: radeon_ring pointer
+ * @semaphore: semaphore to emit commands for
+ * @emit_wait: true if we should emit a wait command
+ *
+ * Emit a semaphore command (either wait or signal) to the UVD ring.
+ */
+void uvd_v1_0_semaphore_emit(struct radeon_device *rdev,
+			     struct radeon_ring *ring,
+			     struct radeon_semaphore *semaphore,
+			     bool emit_wait)
+{
+	uint64_t addr = semaphore->gpu_addr;
+
+	radeon_ring_write(ring, PACKET0(UVD_SEMA_ADDR_LOW, 0));
+	radeon_ring_write(ring, (addr >> 3) & 0x000FFFFF);
+
+	radeon_ring_write(ring, PACKET0(UVD_SEMA_ADDR_HIGH, 0));
+	radeon_ring_write(ring, (addr >> 23) & 0x000FFFFF);
+
+	radeon_ring_write(ring, PACKET0(UVD_SEMA_CMD, 0));
+	radeon_ring_write(ring, emit_wait ? 1 : 0);
+}
+
+/**
+ * uvd_v1_0_ib_execute - execute indirect buffer
+ *
+ * @rdev: radeon_device pointer
+ * @ib: indirect buffer to execute
+ *
+ * Write ring commands to execute the indirect buffer
+ */
+void uvd_v1_0_ib_execute(struct radeon_device *rdev, struct radeon_ib *ib)
+{
+	struct radeon_ring *ring = &rdev->ring[ib->ring];
+
+	radeon_ring_write(ring, PACKET0(UVD_RBC_IB_BASE, 0));
+	radeon_ring_write(ring, ib->gpu_addr);
+	radeon_ring_write(ring, PACKET0(UVD_RBC_IB_SIZE, 0));
+	radeon_ring_write(ring, ib->length_dw);
+}
+
+/**
+ * uvd_v1_0_ib_test - test ib execution
+ *
+ * @rdev: radeon_device pointer
+ * @ring: radeon_ring pointer
+ *
+ * Test if we can successfully execute an IB
+ */
+int uvd_v1_0_ib_test(struct radeon_device *rdev, struct radeon_ring *ring)
+{
+	struct radeon_fence *fence = NULL;
+	int r;
+
+	r = radeon_set_uvd_clocks(rdev, 53300, 40000);
+	if (r) {
+		DRM_ERROR("radeon: failed to raise UVD clocks (%d).\n", r);
+		return r;
+	}
+
+	r = radeon_uvd_get_create_msg(rdev, ring->idx, 1, NULL);
+	if (r) {
+		DRM_ERROR("radeon: failed to get create msg (%d).\n", r);
+		goto error;
+	}
+
+	r = radeon_uvd_get_destroy_msg(rdev, ring->idx, 1, &fence);
+	if (r) {
+		DRM_ERROR("radeon: failed to get destroy ib (%d).\n", r);
+		goto error;
+	}
+
+	r = radeon_fence_wait(fence, false);
+	if (r) {
+		DRM_ERROR("radeon: fence wait failed (%d).\n", r);
+		goto error;
+	}
+	DRM_INFO("ib test on ring %d succeeded\n",  ring->idx);
+error:
+	radeon_fence_unref(&fence);
+	radeon_set_uvd_clocks(rdev, 0, 0);
+	return r;
+}
diff --git a/drivers/gpu/drm/radeon/uvd_v2_2.c b/drivers/gpu/drm/radeon/uvd_v2_2.c
new file mode 100644
index 000000000000..b19ef4951085
--- /dev/null
+++ b/drivers/gpu/drm/radeon/uvd_v2_2.c
@@ -0,0 +1,165 @@
+/*
+ * Copyright 2013 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: Christian König <christian.koenig@amd.com>
+ */
+
+#include <linux/firmware.h>
+#include <drm/drmP.h>
+#include "radeon.h"
+#include "radeon_asic.h"
+#include "rv770d.h"
+
+/**
+ * uvd_v2_2_fence_emit - emit an fence & trap command
+ *
+ * @rdev: radeon_device pointer
+ * @fence: fence to emit
+ *
+ * Write a fence and a trap command to the ring.
+ */
+void uvd_v2_2_fence_emit(struct radeon_device *rdev,
+			 struct radeon_fence *fence)
+{
+	struct radeon_ring *ring = &rdev->ring[fence->ring];
+	uint64_t addr = rdev->fence_drv[fence->ring].gpu_addr;
+
+	radeon_ring_write(ring, PACKET0(UVD_CONTEXT_ID, 0));
+	radeon_ring_write(ring, fence->seq);
+	radeon_ring_write(ring, PACKET0(UVD_GPCOM_VCPU_DATA0, 0));
+	radeon_ring_write(ring, addr & 0xffffffff);
+	radeon_ring_write(ring, PACKET0(UVD_GPCOM_VCPU_DATA1, 0));
+	radeon_ring_write(ring, upper_32_bits(addr) & 0xff);
+	radeon_ring_write(ring, PACKET0(UVD_GPCOM_VCPU_CMD, 0));
+	radeon_ring_write(ring, 0);
+
+	radeon_ring_write(ring, PACKET0(UVD_GPCOM_VCPU_DATA0, 0));
+	radeon_ring_write(ring, 0);
+	radeon_ring_write(ring, PACKET0(UVD_GPCOM_VCPU_DATA1, 0));
+	radeon_ring_write(ring, 0);
+	radeon_ring_write(ring, PACKET0(UVD_GPCOM_VCPU_CMD, 0));
+	radeon_ring_write(ring, 2);
+	return;
+}
+
+/**
+ * uvd_v2_2_resume - memory controller programming
+ *
+ * @rdev: radeon_device pointer
+ *
+ * Let the UVD memory controller know it's offsets
+ */
+int uvd_v2_2_resume(struct radeon_device *rdev)
+{
+	uint64_t addr;
+	uint32_t chip_id, size;
+	int r;
+
+	r = radeon_uvd_resume(rdev);
+	if (r)
+		return r;
+
+	/* programm the VCPU memory controller bits 0-27 */
+	addr = rdev->uvd.gpu_addr >> 3;
+	size = RADEON_GPU_PAGE_ALIGN(rdev->uvd_fw->size + 4) >> 3;
+	WREG32(UVD_VCPU_CACHE_OFFSET0, addr);
+	WREG32(UVD_VCPU_CACHE_SIZE0, size);
+
+	addr += size;
+	size = RADEON_UVD_STACK_SIZE >> 3;
+	WREG32(UVD_VCPU_CACHE_OFFSET1, addr);
+	WREG32(UVD_VCPU_CACHE_SIZE1, size);
+
+	addr += size;
+	size = RADEON_UVD_HEAP_SIZE >> 3;
+	WREG32(UVD_VCPU_CACHE_OFFSET2, addr);
+	WREG32(UVD_VCPU_CACHE_SIZE2, size);
+
+	/* bits 28-31 */
+	addr = (rdev->uvd.gpu_addr >> 28) & 0xF;
+	WREG32(UVD_LMI_ADDR_EXT, (addr << 12) | (addr << 0));
+
+	/* bits 32-39 */
+	addr = (rdev->uvd.gpu_addr >> 32) & 0xFF;
+	WREG32(UVD_LMI_EXT40_ADDR, addr | (0x9 << 16) | (0x1 << 31));
+
+	/* tell firmware which hardware it is running on */
+	switch (rdev->family) {
+	default:
+		return -EINVAL;
+	case CHIP_RV710:
+		chip_id = 0x01000005;
+		break;
+	case CHIP_RV730:
+		chip_id = 0x01000006;
+		break;
+	case CHIP_RV740:
+		chip_id = 0x01000007;
+		break;
+	case CHIP_CYPRESS:
+	case CHIP_HEMLOCK:
+		chip_id = 0x01000008;
+		break;
+	case CHIP_JUNIPER:
+		chip_id = 0x01000009;
+		break;
+	case CHIP_REDWOOD:
+		chip_id = 0x0100000a;
+		break;
+	case CHIP_CEDAR:
+		chip_id = 0x0100000b;
+		break;
+	case CHIP_SUMO:
+	case CHIP_SUMO2:
+		chip_id = 0x0100000c;
+		break;
+	case CHIP_PALM:
+		chip_id = 0x0100000e;
+		break;
+	case CHIP_CAYMAN:
+		chip_id = 0x0100000f;
+		break;
+	case CHIP_BARTS:
+		chip_id = 0x01000010;
+		break;
+	case CHIP_TURKS:
+		chip_id = 0x01000011;
+		break;
+	case CHIP_CAICOS:
+		chip_id = 0x01000012;
+		break;
+	case CHIP_TAHITI:
+		chip_id = 0x01000014;
+		break;
+	case CHIP_VERDE:
+		chip_id = 0x01000015;
+		break;
+	case CHIP_PITCAIRN:
+		chip_id = 0x01000016;
+		break;
+	case CHIP_ARUBA:
+		chip_id = 0x01000017;
+		break;
+	}
+	WREG32(UVD_VCPU_CHIP_ID, chip_id);
+
+	return 0;
+}
diff --git a/drivers/gpu/drm/radeon/uvd_v3_1.c b/drivers/gpu/drm/radeon/uvd_v3_1.c
new file mode 100644
index 000000000000..5b6fa1f62d4e
--- /dev/null
+++ b/drivers/gpu/drm/radeon/uvd_v3_1.c
@@ -0,0 +1,55 @@
+/*
+ * Copyright 2013 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: Christian König <christian.koenig@amd.com>
+ */
+
+#include <drm/drmP.h>
+#include "radeon.h"
+#include "radeon_asic.h"
+#include "nid.h"
+
+/**
+ * uvd_v3_1_semaphore_emit - emit semaphore command
+ *
+ * @rdev: radeon_device pointer
+ * @ring: radeon_ring pointer
+ * @semaphore: semaphore to emit commands for
+ * @emit_wait: true if we should emit a wait command
+ *
+ * Emit a semaphore command (either wait or signal) to the UVD ring.
+ */
+void uvd_v3_1_semaphore_emit(struct radeon_device *rdev,
+			     struct radeon_ring *ring,
+			     struct radeon_semaphore *semaphore,
+			     bool emit_wait)
+{
+	uint64_t addr = semaphore->gpu_addr;
+
+	radeon_ring_write(ring, PACKET0(UVD_SEMA_ADDR_LOW, 0));
+	radeon_ring_write(ring, (addr >> 3) & 0x000FFFFF);
+
+	radeon_ring_write(ring, PACKET0(UVD_SEMA_ADDR_HIGH, 0));
+	radeon_ring_write(ring, (addr >> 23) & 0x000FFFFF);
+
+	radeon_ring_write(ring, PACKET0(UVD_SEMA_CMD, 0));
+	radeon_ring_write(ring, 0x80 | (emit_wait ? 1 : 0));
+}
diff --git a/drivers/gpu/drm/radeon/uvd_v4_2.c b/drivers/gpu/drm/radeon/uvd_v4_2.c
new file mode 100644
index 000000000000..d04d5073eef2
--- /dev/null
+++ b/drivers/gpu/drm/radeon/uvd_v4_2.c
@@ -0,0 +1,68 @@
+/*
+ * Copyright 2013 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: Christian König <christian.koenig@amd.com>
+ */
+
+#include <linux/firmware.h>
+#include <drm/drmP.h>
+#include "radeon.h"
+#include "radeon_asic.h"
+#include "cikd.h"
+
+/**
+ * uvd_v4_2_resume - memory controller programming
+ *
+ * @rdev: radeon_device pointer
+ *
+ * Let the UVD memory controller know it's offsets
+ */
+int uvd_v4_2_resume(struct radeon_device *rdev)
+{
+	uint64_t addr;
+	uint32_t size;
+
+	/* programm the VCPU memory controller bits 0-27 */
+	addr = rdev->uvd.gpu_addr >> 3;
+	size = RADEON_GPU_PAGE_ALIGN(rdev->uvd_fw->size + 4) >> 3;
+	WREG32(UVD_VCPU_CACHE_OFFSET0, addr);
+	WREG32(UVD_VCPU_CACHE_SIZE0, size);
+
+	addr += size;
+	size = RADEON_UVD_STACK_SIZE >> 3;
+	WREG32(UVD_VCPU_CACHE_OFFSET1, addr);
+	WREG32(UVD_VCPU_CACHE_SIZE1, size);
+
+	addr += size;
+	size = RADEON_UVD_HEAP_SIZE >> 3;
+	WREG32(UVD_VCPU_CACHE_OFFSET2, addr);
+	WREG32(UVD_VCPU_CACHE_SIZE2, size);
+
+	/* bits 28-31 */
+	addr = (rdev->uvd.gpu_addr >> 28) & 0xF;
+	WREG32(UVD_LMI_ADDR_EXT, (addr << 12) | (addr << 0));
+
+	/* bits 32-39 */
+	addr = (rdev->uvd.gpu_addr >> 32) & 0xFF;
+	WREG32(UVD_LMI_EXT40_ADDR, addr | (0x9 << 16) | (0x1 << 31));
+
+	return 0;
+}
diff --git a/drivers/gpu/drm/rcar-du/Kconfig b/drivers/gpu/drm/rcar-du/Kconfig
index 72887df8dd76..c590cd9dca0b 100644
--- a/drivers/gpu/drm/rcar-du/Kconfig
+++ b/drivers/gpu/drm/rcar-du/Kconfig
@@ -7,3 +7,10 @@ config DRM_RCAR_DU
 	help
 	  Choose this option if you have an R-Car chipset.
 	  If M is selected the module will be called rcar-du-drm.
+
+config DRM_RCAR_LVDS
+	bool "R-Car DU LVDS Encoder Support"
+	depends on DRM_RCAR_DU
+	help
+	  Enable support the R-Car Display Unit embedded LVDS encoders
+	  (currently only on R8A7790).
diff --git a/drivers/gpu/drm/rcar-du/Makefile b/drivers/gpu/drm/rcar-du/Makefile
index 7333c0094015..12b8d4477835 100644
--- a/drivers/gpu/drm/rcar-du/Makefile
+++ b/drivers/gpu/drm/rcar-du/Makefile
@@ -1,8 +1,12 @@
 rcar-du-drm-y := rcar_du_crtc.o \
 		 rcar_du_drv.o \
+		 rcar_du_encoder.o \
+		 rcar_du_group.o \
 		 rcar_du_kms.o \
-		 rcar_du_lvds.o \
+		 rcar_du_lvdscon.o \
 		 rcar_du_plane.o \
-		 rcar_du_vga.o
+		 rcar_du_vgacon.o
 
-obj-$(CONFIG_DRM_RCAR_DU)	+= rcar-du-drm.o
+rcar-du-drm-$(CONFIG_DRM_RCAR_LVDS)	+= rcar_du_lvdsenc.o
+
+obj-$(CONFIG_DRM_RCAR_DU)		+= rcar-du-drm.o
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_crtc.c b/drivers/gpu/drm/rcar-du/rcar_du_crtc.c
index 24183fb93592..a9d24e4bf792 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_crtc.c
+++ b/drivers/gpu/drm/rcar-du/rcar_du_crtc.c
@@ -23,30 +23,26 @@
 #include "rcar_du_crtc.h"
 #include "rcar_du_drv.h"
 #include "rcar_du_kms.h"
-#include "rcar_du_lvds.h"
 #include "rcar_du_plane.h"
 #include "rcar_du_regs.h"
-#include "rcar_du_vga.h"
-
-#define to_rcar_crtc(c)	container_of(c, struct rcar_du_crtc, crtc)
 
 static u32 rcar_du_crtc_read(struct rcar_du_crtc *rcrtc, u32 reg)
 {
-	struct rcar_du_device *rcdu = rcrtc->crtc.dev->dev_private;
+	struct rcar_du_device *rcdu = rcrtc->group->dev;
 
 	return rcar_du_read(rcdu, rcrtc->mmio_offset + reg);
 }
 
 static void rcar_du_crtc_write(struct rcar_du_crtc *rcrtc, u32 reg, u32 data)
 {
-	struct rcar_du_device *rcdu = rcrtc->crtc.dev->dev_private;
+	struct rcar_du_device *rcdu = rcrtc->group->dev;
 
 	rcar_du_write(rcdu, rcrtc->mmio_offset + reg, data);
 }
 
 static void rcar_du_crtc_clr(struct rcar_du_crtc *rcrtc, u32 reg, u32 clr)
 {
-	struct rcar_du_device *rcdu = rcrtc->crtc.dev->dev_private;
+	struct rcar_du_device *rcdu = rcrtc->group->dev;
 
 	rcar_du_write(rcdu, rcrtc->mmio_offset + reg,
 		      rcar_du_read(rcdu, rcrtc->mmio_offset + reg) & ~clr);
@@ -54,7 +50,7 @@ static void rcar_du_crtc_clr(struct rcar_du_crtc *rcrtc, u32 reg, u32 clr)
 
 static void rcar_du_crtc_set(struct rcar_du_crtc *rcrtc, u32 reg, u32 set)
 {
-	struct rcar_du_device *rcdu = rcrtc->crtc.dev->dev_private;
+	struct rcar_du_device *rcdu = rcrtc->group->dev;
 
 	rcar_du_write(rcdu, rcrtc->mmio_offset + reg,
 		      rcar_du_read(rcdu, rcrtc->mmio_offset + reg) | set);
@@ -63,29 +59,48 @@ static void rcar_du_crtc_set(struct rcar_du_crtc *rcrtc, u32 reg, u32 set)
 static void rcar_du_crtc_clr_set(struct rcar_du_crtc *rcrtc, u32 reg,
 				 u32 clr, u32 set)
 {
-	struct rcar_du_device *rcdu = rcrtc->crtc.dev->dev_private;
+	struct rcar_du_device *rcdu = rcrtc->group->dev;
 	u32 value = rcar_du_read(rcdu, rcrtc->mmio_offset + reg);
 
 	rcar_du_write(rcdu, rcrtc->mmio_offset + reg, (value & ~clr) | set);
 }
 
+static int rcar_du_crtc_get(struct rcar_du_crtc *rcrtc)
+{
+	int ret;
+
+	ret = clk_prepare_enable(rcrtc->clock);
+	if (ret < 0)
+		return ret;
+
+	ret = rcar_du_group_get(rcrtc->group);
+	if (ret < 0)
+		clk_disable_unprepare(rcrtc->clock);
+
+	return ret;
+}
+
+static void rcar_du_crtc_put(struct rcar_du_crtc *rcrtc)
+{
+	rcar_du_group_put(rcrtc->group);
+	clk_disable_unprepare(rcrtc->clock);
+}
+
 static void rcar_du_crtc_set_display_timing(struct rcar_du_crtc *rcrtc)
 {
-	struct drm_crtc *crtc = &rcrtc->crtc;
-	struct rcar_du_device *rcdu = crtc->dev->dev_private;
-	const struct drm_display_mode *mode = &crtc->mode;
+	const struct drm_display_mode *mode = &rcrtc->crtc.mode;
 	unsigned long clk;
 	u32 value;
 	u32 div;
 
 	/* Dot clock */
-	clk = clk_get_rate(rcdu->clock);
+	clk = clk_get_rate(rcrtc->clock);
 	div = DIV_ROUND_CLOSEST(clk, mode->clock * 1000);
 	div = clamp(div, 1U, 64U) - 1;
 
-	rcar_du_write(rcdu, rcrtc->index ? ESCR2 : ESCR,
-		      ESCR_DCLKSEL_CLKS | div);
-	rcar_du_write(rcdu, rcrtc->index ? OTAR2 : OTAR, 0);
+	rcar_du_group_write(rcrtc->group, rcrtc->index % 2 ? ESCR2 : ESCR,
+			    ESCR_DCLKSEL_CLKS | div);
+	rcar_du_group_write(rcrtc->group, rcrtc->index % 2 ? OTAR2 : OTAR, 0);
 
 	/* Signal polarities */
 	value = ((mode->flags & DRM_MODE_FLAG_PVSYNC) ? 0 : DSMR_VSL)
@@ -112,68 +127,25 @@ static void rcar_du_crtc_set_display_timing(struct rcar_du_crtc *rcrtc)
 	rcar_du_crtc_write(rcrtc, DEWR,  mode->hdisplay);
 }
 
-static void rcar_du_crtc_set_routing(struct rcar_du_crtc *rcrtc)
-{
-	struct rcar_du_device *rcdu = rcrtc->crtc.dev->dev_private;
-	u32 dorcr = rcar_du_read(rcdu, DORCR);
-
-	dorcr &= ~(DORCR_PG2T | DORCR_DK2S | DORCR_PG2D_MASK);
-
-	/* Set the DU1 pins sources. Select CRTC 0 if explicitly requested and
-	 * CRTC 1 in all other cases to avoid cloning CRTC 0 to DU0 and DU1 by
-	 * default.
-	 */
-	if (rcrtc->outputs & (1 << 1) && rcrtc->index == 0)
-		dorcr |= DORCR_PG2D_DS1;
-	else
-		dorcr |= DORCR_PG2T | DORCR_DK2S | DORCR_PG2D_DS2;
-
-	rcar_du_write(rcdu, DORCR, dorcr);
-}
-
-static void __rcar_du_start_stop(struct rcar_du_device *rcdu, bool start)
-{
-	rcar_du_write(rcdu, DSYSR,
-		      (rcar_du_read(rcdu, DSYSR) & ~(DSYSR_DRES | DSYSR_DEN)) |
-		      (start ? DSYSR_DEN : DSYSR_DRES));
-}
-
-static void rcar_du_start_stop(struct rcar_du_device *rcdu, bool start)
-{
-	/* Many of the configuration bits are only updated when the display
-	 * reset (DRES) bit in DSYSR is set to 1, disabling *both* CRTCs. Some
-	 * of those bits could be pre-configured, but others (especially the
-	 * bits related to plane assignment to display timing controllers) need
-	 * to be modified at runtime.
-	 *
-	 * Restart the display controller if a start is requested. Sorry for the
-	 * flicker. It should be possible to move most of the "DRES-update" bits
-	 * setup to driver initialization time and minimize the number of cases
-	 * when the display controller will have to be restarted.
-	 */
-	if (start) {
-		if (rcdu->used_crtcs++ != 0)
-			__rcar_du_start_stop(rcdu, false);
-		__rcar_du_start_stop(rcdu, true);
-	} else {
-		if (--rcdu->used_crtcs == 0)
-			__rcar_du_start_stop(rcdu, false);
-	}
-}
-
-void rcar_du_crtc_route_output(struct drm_crtc *crtc, unsigned int output)
+void rcar_du_crtc_route_output(struct drm_crtc *crtc,
+			       enum rcar_du_output output)
 {
 	struct rcar_du_crtc *rcrtc = to_rcar_crtc(crtc);
+	struct rcar_du_device *rcdu = rcrtc->group->dev;
 
 	/* Store the route from the CRTC output to the DU output. The DU will be
 	 * configured when starting the CRTC.
 	 */
-	rcrtc->outputs |= 1 << output;
+	rcrtc->outputs |= BIT(output);
+
+	/* Store RGB routing to DPAD0 for R8A7790. */
+	if (rcar_du_has(rcdu, RCAR_DU_FEATURE_DEFR8) &&
+	    output == RCAR_DU_OUTPUT_DPAD0)
+		rcdu->dpad0_source = rcrtc->index;
 }
 
 void rcar_du_crtc_update_planes(struct drm_crtc *crtc)
 {
-	struct rcar_du_device *rcdu = crtc->dev->dev_private;
 	struct rcar_du_crtc *rcrtc = to_rcar_crtc(crtc);
 	struct rcar_du_plane *planes[RCAR_DU_NUM_HW_PLANES];
 	unsigned int num_planes = 0;
@@ -182,8 +154,8 @@ void rcar_du_crtc_update_planes(struct drm_crtc *crtc)
 	u32 dptsr = 0;
 	u32 dspr = 0;
 
-	for (i = 0; i < ARRAY_SIZE(rcdu->planes.planes); ++i) {
-		struct rcar_du_plane *plane = &rcdu->planes.planes[i];
+	for (i = 0; i < ARRAY_SIZE(rcrtc->group->planes.planes); ++i) {
+		struct rcar_du_plane *plane = &rcrtc->group->planes.planes[i];
 		unsigned int j;
 
 		if (plane->crtc != &rcrtc->crtc || !plane->enabled)
@@ -220,8 +192,8 @@ void rcar_du_crtc_update_planes(struct drm_crtc *crtc)
 	/* Select display timing and dot clock generator 2 for planes associated
 	 * with superposition controller 2.
 	 */
-	if (rcrtc->index) {
-		u32 value = rcar_du_read(rcdu, DPTSR);
+	if (rcrtc->index % 2) {
+		u32 value = rcar_du_group_read(rcrtc->group, DPTSR);
 
 		/* The DPTSR register is updated when the display controller is
 		 * stopped. We thus need to restart the DU. Once again, sorry
@@ -231,21 +203,19 @@ void rcar_du_crtc_update_planes(struct drm_crtc *crtc)
 		 * occur only if we need to break the pre-association.
 		 */
 		if (value != dptsr) {
-			rcar_du_write(rcdu, DPTSR, dptsr);
-			if (rcdu->used_crtcs) {
-				__rcar_du_start_stop(rcdu, false);
-				__rcar_du_start_stop(rcdu, true);
-			}
+			rcar_du_group_write(rcrtc->group, DPTSR, dptsr);
+			if (rcrtc->group->used_crtcs)
+				rcar_du_group_restart(rcrtc->group);
 		}
 	}
 
-	rcar_du_write(rcdu, rcrtc->index ? DS2PR : DS1PR, dspr);
+	rcar_du_group_write(rcrtc->group, rcrtc->index % 2 ? DS2PR : DS1PR,
+			    dspr);
 }
 
 static void rcar_du_crtc_start(struct rcar_du_crtc *rcrtc)
 {
 	struct drm_crtc *crtc = &rcrtc->crtc;
-	struct rcar_du_device *rcdu = crtc->dev->dev_private;
 	unsigned int i;
 
 	if (rcrtc->started)
@@ -260,16 +230,16 @@ static void rcar_du_crtc_start(struct rcar_du_crtc *rcrtc)
 
 	/* Configure display timings and output routing */
 	rcar_du_crtc_set_display_timing(rcrtc);
-	rcar_du_crtc_set_routing(rcrtc);
+	rcar_du_group_set_routing(rcrtc->group);
 
-	mutex_lock(&rcdu->planes.lock);
+	mutex_lock(&rcrtc->group->planes.lock);
 	rcrtc->plane->enabled = true;
 	rcar_du_crtc_update_planes(crtc);
-	mutex_unlock(&rcdu->planes.lock);
+	mutex_unlock(&rcrtc->group->planes.lock);
 
 	/* Setup planes. */
-	for (i = 0; i < ARRAY_SIZE(rcdu->planes.planes); ++i) {
-		struct rcar_du_plane *plane = &rcdu->planes.planes[i];
+	for (i = 0; i < ARRAY_SIZE(rcrtc->group->planes.planes); ++i) {
+		struct rcar_du_plane *plane = &rcrtc->group->planes.planes[i];
 
 		if (plane->crtc != crtc || !plane->enabled)
 			continue;
@@ -283,7 +253,7 @@ static void rcar_du_crtc_start(struct rcar_du_crtc *rcrtc)
 	 */
 	rcar_du_crtc_clr_set(rcrtc, DSYSR, DSYSR_TVM_MASK, DSYSR_TVM_MASTER);
 
-	rcar_du_start_stop(rcdu, true);
+	rcar_du_group_start_stop(rcrtc->group, true);
 
 	rcrtc->started = true;
 }
@@ -291,42 +261,37 @@ static void rcar_du_crtc_start(struct rcar_du_crtc *rcrtc)
 static void rcar_du_crtc_stop(struct rcar_du_crtc *rcrtc)
 {
 	struct drm_crtc *crtc = &rcrtc->crtc;
-	struct rcar_du_device *rcdu = crtc->dev->dev_private;
 
 	if (!rcrtc->started)
 		return;
 
-	mutex_lock(&rcdu->planes.lock);
+	mutex_lock(&rcrtc->group->planes.lock);
 	rcrtc->plane->enabled = false;
 	rcar_du_crtc_update_planes(crtc);
-	mutex_unlock(&rcdu->planes.lock);
+	mutex_unlock(&rcrtc->group->planes.lock);
 
 	/* Select switch sync mode. This stops display operation and configures
 	 * the HSYNC and VSYNC signals as inputs.
 	 */
 	rcar_du_crtc_clr_set(rcrtc, DSYSR, DSYSR_TVM_MASK, DSYSR_TVM_SWITCH);
 
-	rcar_du_start_stop(rcdu, false);
+	rcar_du_group_start_stop(rcrtc->group, false);
 
 	rcrtc->started = false;
 }
 
 void rcar_du_crtc_suspend(struct rcar_du_crtc *rcrtc)
 {
-	struct rcar_du_device *rcdu = rcrtc->crtc.dev->dev_private;
-
 	rcar_du_crtc_stop(rcrtc);
-	rcar_du_put(rcdu);
+	rcar_du_crtc_put(rcrtc);
 }
 
 void rcar_du_crtc_resume(struct rcar_du_crtc *rcrtc)
 {
-	struct rcar_du_device *rcdu = rcrtc->crtc.dev->dev_private;
-
 	if (rcrtc->dpms != DRM_MODE_DPMS_ON)
 		return;
 
-	rcar_du_get(rcdu);
+	rcar_du_crtc_get(rcrtc);
 	rcar_du_crtc_start(rcrtc);
 }
 
@@ -340,18 +305,17 @@ static void rcar_du_crtc_update_base(struct rcar_du_crtc *rcrtc)
 
 static void rcar_du_crtc_dpms(struct drm_crtc *crtc, int mode)
 {
-	struct rcar_du_device *rcdu = crtc->dev->dev_private;
 	struct rcar_du_crtc *rcrtc = to_rcar_crtc(crtc);
 
 	if (rcrtc->dpms == mode)
 		return;
 
 	if (mode == DRM_MODE_DPMS_ON) {
-		rcar_du_get(rcdu);
+		rcar_du_crtc_get(rcrtc);
 		rcar_du_crtc_start(rcrtc);
 	} else {
 		rcar_du_crtc_stop(rcrtc);
-		rcar_du_put(rcdu);
+		rcar_du_crtc_put(rcrtc);
 	}
 
 	rcrtc->dpms = mode;
@@ -367,13 +331,12 @@ static bool rcar_du_crtc_mode_fixup(struct drm_crtc *crtc,
 
 static void rcar_du_crtc_mode_prepare(struct drm_crtc *crtc)
 {
-	struct rcar_du_device *rcdu = crtc->dev->dev_private;
 	struct rcar_du_crtc *rcrtc = to_rcar_crtc(crtc);
 
 	/* We need to access the hardware during mode set, acquire a reference
-	 * to the DU.
+	 * to the CRTC.
 	 */
-	rcar_du_get(rcdu);
+	rcar_du_crtc_get(rcrtc);
 
 	/* Stop the CRTC and release the plane. Force the DPMS mode to off as a
 	 * result.
@@ -390,8 +353,8 @@ static int rcar_du_crtc_mode_set(struct drm_crtc *crtc,
 				 int x, int y,
 				 struct drm_framebuffer *old_fb)
 {
-	struct rcar_du_device *rcdu = crtc->dev->dev_private;
 	struct rcar_du_crtc *rcrtc = to_rcar_crtc(crtc);
+	struct rcar_du_device *rcdu = rcrtc->group->dev;
 	const struct rcar_du_format_info *format;
 	int ret;
 
@@ -423,10 +386,10 @@ static int rcar_du_crtc_mode_set(struct drm_crtc *crtc,
 
 error:
 	/* There's no rollback/abort operation to clean up in case of error. We
-	 * thus need to release the reference to the DU acquired in prepare()
+	 * thus need to release the reference to the CRTC acquired in prepare()
 	 * here.
 	 */
-	rcar_du_put(rcdu);
+	rcar_du_crtc_put(rcrtc);
 	return ret;
 }
 
@@ -514,9 +477,28 @@ static void rcar_du_crtc_finish_page_flip(struct rcar_du_crtc *rcrtc)
 	drm_vblank_put(dev, rcrtc->index);
 }
 
+static irqreturn_t rcar_du_crtc_irq(int irq, void *arg)
+{
+	struct rcar_du_crtc *rcrtc = arg;
+	irqreturn_t ret = IRQ_NONE;
+	u32 status;
+
+	status = rcar_du_crtc_read(rcrtc, DSSR);
+	rcar_du_crtc_write(rcrtc, DSRCR, status & DSRCR_MASK);
+
+	if (status & DSSR_VBK) {
+		drm_handle_vblank(rcrtc->crtc.dev, rcrtc->index);
+		rcar_du_crtc_finish_page_flip(rcrtc);
+		ret = IRQ_HANDLED;
+	}
+
+	return ret;
+}
+
 static int rcar_du_crtc_page_flip(struct drm_crtc *crtc,
 				  struct drm_framebuffer *fb,
-				  struct drm_pending_vblank_event *event)
+				  struct drm_pending_vblank_event *event,
+				  uint32_t page_flip_flags)
 {
 	struct rcar_du_crtc *rcrtc = to_rcar_crtc(crtc);
 	struct drm_device *dev = rcrtc->crtc.dev;
@@ -549,16 +531,41 @@ static const struct drm_crtc_funcs crtc_funcs = {
 	.page_flip = rcar_du_crtc_page_flip,
 };
 
-int rcar_du_crtc_create(struct rcar_du_device *rcdu, unsigned int index)
+int rcar_du_crtc_create(struct rcar_du_group *rgrp, unsigned int index)
 {
+	static const unsigned int mmio_offsets[] = {
+		DU0_REG_OFFSET, DU1_REG_OFFSET, DU2_REG_OFFSET
+	};
+
+	struct rcar_du_device *rcdu = rgrp->dev;
+	struct platform_device *pdev = to_platform_device(rcdu->dev);
 	struct rcar_du_crtc *rcrtc = &rcdu->crtcs[index];
 	struct drm_crtc *crtc = &rcrtc->crtc;
+	unsigned int irqflags;
+	char clk_name[5];
+	char *name;
+	int irq;
 	int ret;
 
-	rcrtc->mmio_offset = index ? DISP2_REG_OFFSET : 0;
+	/* Get the CRTC clock. */
+	if (rcar_du_has(rcdu, RCAR_DU_FEATURE_CRTC_IRQ_CLOCK)) {
+		sprintf(clk_name, "du.%u", index);
+		name = clk_name;
+	} else {
+		name = NULL;
+	}
+
+	rcrtc->clock = devm_clk_get(rcdu->dev, name);
+	if (IS_ERR(rcrtc->clock)) {
+		dev_err(rcdu->dev, "no clock for CRTC %u\n", index);
+		return PTR_ERR(rcrtc->clock);
+	}
+
+	rcrtc->group = rgrp;
+	rcrtc->mmio_offset = mmio_offsets[index];
 	rcrtc->index = index;
 	rcrtc->dpms = DRM_MODE_DPMS_OFF;
-	rcrtc->plane = &rcdu->planes.planes[index];
+	rcrtc->plane = &rgrp->planes.planes[index % 2];
 
 	rcrtc->plane->crtc = crtc;
 
@@ -568,6 +575,28 @@ int rcar_du_crtc_create(struct rcar_du_device *rcdu, unsigned int index)
 
 	drm_crtc_helper_add(crtc, &crtc_helper_funcs);
 
+	/* Register the interrupt handler. */
+	if (rcar_du_has(rcdu, RCAR_DU_FEATURE_CRTC_IRQ_CLOCK)) {
+		irq = platform_get_irq(pdev, index);
+		irqflags = 0;
+	} else {
+		irq = platform_get_irq(pdev, 0);
+		irqflags = IRQF_SHARED;
+	}
+
+	if (irq < 0) {
+		dev_err(rcdu->dev, "no IRQ for CRTC %u\n", index);
+		return ret;
+	}
+
+	ret = devm_request_irq(rcdu->dev, irq, rcar_du_crtc_irq, irqflags,
+			       dev_name(rcdu->dev), rcrtc);
+	if (ret < 0) {
+		dev_err(rcdu->dev,
+			"failed to register IRQ for CRTC %u\n", index);
+		return ret;
+	}
+
 	return 0;
 }
 
@@ -580,16 +609,3 @@ void rcar_du_crtc_enable_vblank(struct rcar_du_crtc *rcrtc, bool enable)
 		rcar_du_crtc_clr(rcrtc, DIER, DIER_VBE);
 	}
 }
-
-void rcar_du_crtc_irq(struct rcar_du_crtc *rcrtc)
-{
-	u32 status;
-
-	status = rcar_du_crtc_read(rcrtc, DSSR);
-	rcar_du_crtc_write(rcrtc, DSRCR, status & DSRCR_MASK);
-
-	if (status & DSSR_VBK) {
-		drm_handle_vblank(rcrtc->crtc.dev, rcrtc->index);
-		rcar_du_crtc_finish_page_flip(rcrtc);
-	}
-}
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_crtc.h b/drivers/gpu/drm/rcar-du/rcar_du_crtc.h
index 2a0365bcbd14..43e7575c700c 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_crtc.h
+++ b/drivers/gpu/drm/rcar-du/rcar_du_crtc.h
@@ -15,16 +15,18 @@
 #define __RCAR_DU_CRTC_H__
 
 #include <linux/mutex.h>
+#include <linux/platform_data/rcar-du.h>
 
 #include <drm/drmP.h>
 #include <drm/drm_crtc.h>
 
-struct rcar_du_device;
+struct rcar_du_group;
 struct rcar_du_plane;
 
 struct rcar_du_crtc {
 	struct drm_crtc crtc;
 
+	struct clk *clock;
 	unsigned int mmio_offset;
 	unsigned int index;
 	bool started;
@@ -33,18 +35,21 @@ struct rcar_du_crtc {
 	unsigned int outputs;
 	int dpms;
 
+	struct rcar_du_group *group;
 	struct rcar_du_plane *plane;
 };
 
-int rcar_du_crtc_create(struct rcar_du_device *rcdu, unsigned int index);
+#define to_rcar_crtc(c)	container_of(c, struct rcar_du_crtc, crtc)
+
+int rcar_du_crtc_create(struct rcar_du_group *rgrp, unsigned int index);
 void rcar_du_crtc_enable_vblank(struct rcar_du_crtc *rcrtc, bool enable);
-void rcar_du_crtc_irq(struct rcar_du_crtc *rcrtc);
 void rcar_du_crtc_cancel_page_flip(struct rcar_du_crtc *rcrtc,
 				   struct drm_file *file);
 void rcar_du_crtc_suspend(struct rcar_du_crtc *rcrtc);
 void rcar_du_crtc_resume(struct rcar_du_crtc *rcrtc);
 
-void rcar_du_crtc_route_output(struct drm_crtc *crtc, unsigned int output);
+void rcar_du_crtc_route_output(struct drm_crtc *crtc,
+			       enum rcar_du_output output);
 void rcar_du_crtc_update_planes(struct drm_crtc *crtc);
 
 #endif /* __RCAR_DU_CRTC_H__ */
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_drv.c b/drivers/gpu/drm/rcar-du/rcar_du_drv.c
index dc0fe09b2ba1..0023f9719cf1 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_drv.c
+++ b/drivers/gpu/drm/rcar-du/rcar_du_drv.c
@@ -21,6 +21,7 @@
 
 #include <drm/drmP.h>
 #include <drm/drm_crtc_helper.h>
+#include <drm/drm_fb_cma_helper.h>
 #include <drm/drm_gem_cma_helper.h>
 
 #include "rcar_du_crtc.h"
@@ -29,74 +30,21 @@
 #include "rcar_du_regs.h"
 
 /* -----------------------------------------------------------------------------
- * Core device operations
- */
-
-/*
- * rcar_du_get - Acquire a reference to the DU
- *
- * Acquiring a reference enables the device clock and setup core registers. A
- * reference must be held before accessing any hardware registers.
- *
- * This function must be called with the DRM mode_config lock held.
- *
- * Return 0 in case of success or a negative error code otherwise.
- */
-int rcar_du_get(struct rcar_du_device *rcdu)
-{
-	int ret;
-
-	if (rcdu->use_count)
-		goto done;
-
-	/* Enable clocks before accessing the hardware. */
-	ret = clk_prepare_enable(rcdu->clock);
-	if (ret < 0)
-		return ret;
-
-	/* Enable extended features */
-	rcar_du_write(rcdu, DEFR, DEFR_CODE | DEFR_DEFE);
-	rcar_du_write(rcdu, DEFR2, DEFR2_CODE | DEFR2_DEFE2G);
-	rcar_du_write(rcdu, DEFR3, DEFR3_CODE | DEFR3_DEFE3);
-	rcar_du_write(rcdu, DEFR4, DEFR4_CODE);
-	rcar_du_write(rcdu, DEFR5, DEFR5_CODE | DEFR5_DEFE5);
-
-	/* Use DS1PR and DS2PR to configure planes priorities and connects the
-	 * superposition 0 to DU0 pins. DU1 pins will be configured dynamically.
-	 */
-	rcar_du_write(rcdu, DORCR, DORCR_PG1D_DS1 | DORCR_DPRS);
-
-done:
-	rcdu->use_count++;
-	return 0;
-}
-
-/*
- * rcar_du_put - Release a reference to the DU
- *
- * Releasing the last reference disables the device clock.
- *
- * This function must be called with the DRM mode_config lock held.
- */
-void rcar_du_put(struct rcar_du_device *rcdu)
-{
-	if (--rcdu->use_count)
-		return;
-
-	clk_disable_unprepare(rcdu->clock);
-}
-
-/* -----------------------------------------------------------------------------
  * DRM operations
  */
 
 static int rcar_du_unload(struct drm_device *dev)
 {
+	struct rcar_du_device *rcdu = dev->dev_private;
+
+	if (rcdu->fbdev)
+		drm_fbdev_cma_fini(rcdu->fbdev);
+
 	drm_kms_helper_poll_fini(dev);
 	drm_mode_config_cleanup(dev);
 	drm_vblank_cleanup(dev);
-	drm_irq_uninstall(dev);
 
+	dev->irq_enabled = 0;
 	dev->dev_private = NULL;
 
 	return 0;
@@ -107,7 +55,6 @@ static int rcar_du_load(struct drm_device *dev, unsigned long flags)
 	struct platform_device *pdev = dev->platformdev;
 	struct rcar_du_platform_data *pdata = pdev->dev.platform_data;
 	struct rcar_du_device *rcdu;
-	struct resource *ioarea;
 	struct resource *mem;
 	int ret;
 
@@ -124,35 +71,15 @@ static int rcar_du_load(struct drm_device *dev, unsigned long flags)
 
 	rcdu->dev = &pdev->dev;
 	rcdu->pdata = pdata;
+	rcdu->info = (struct rcar_du_device_info *)pdev->id_entry->driver_data;
 	rcdu->ddev = dev;
 	dev->dev_private = rcdu;
 
-	/* I/O resources and clocks */
+	/* I/O resources */
 	mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (mem == NULL) {
-		dev_err(&pdev->dev, "failed to get memory resource\n");
-		return -EINVAL;
-	}
-
-	ioarea = devm_request_mem_region(&pdev->dev, mem->start,
-					 resource_size(mem), pdev->name);
-	if (ioarea == NULL) {
-		dev_err(&pdev->dev, "failed to request memory region\n");
-		return -EBUSY;
-	}
-
-	rcdu->mmio = devm_ioremap_nocache(&pdev->dev, ioarea->start,
-					  resource_size(ioarea));
-	if (rcdu->mmio == NULL) {
-		dev_err(&pdev->dev, "failed to remap memory resource\n");
-		return -ENOMEM;
-	}
-
-	rcdu->clock = devm_clk_get(&pdev->dev, NULL);
-	if (IS_ERR(rcdu->clock)) {
-		dev_err(&pdev->dev, "failed to get clock\n");
-		return -ENOENT;
-	}
+	rcdu->mmio = devm_ioremap_resource(&pdev->dev, mem);
+	if (IS_ERR(rcdu->mmio))
+		return PTR_ERR(rcdu->mmio);
 
 	/* DRM/KMS objects */
 	ret = rcar_du_modeset_init(rcdu);
@@ -161,18 +88,14 @@ static int rcar_du_load(struct drm_device *dev, unsigned long flags)
 		goto done;
 	}
 
-	/* IRQ and vblank handling */
+	/* vblank handling */
 	ret = drm_vblank_init(dev, (1 << rcdu->num_crtcs) - 1);
 	if (ret < 0) {
 		dev_err(&pdev->dev, "failed to initialize vblank\n");
 		goto done;
 	}
 
-	ret = drm_irq_install(dev);
-	if (ret < 0) {
-		dev_err(&pdev->dev, "failed to install IRQ handler\n");
-		goto done;
-	}
+	dev->irq_enabled = 1;
 
 	platform_set_drvdata(pdev, rcdu);
 
@@ -188,20 +111,15 @@ static void rcar_du_preclose(struct drm_device *dev, struct drm_file *file)
 	struct rcar_du_device *rcdu = dev->dev_private;
 	unsigned int i;
 
-	for (i = 0; i < ARRAY_SIZE(rcdu->crtcs); ++i)
+	for (i = 0; i < rcdu->num_crtcs; ++i)
 		rcar_du_crtc_cancel_page_flip(&rcdu->crtcs[i], file);
 }
 
-static irqreturn_t rcar_du_irq(int irq, void *arg)
+static void rcar_du_lastclose(struct drm_device *dev)
 {
-	struct drm_device *dev = arg;
 	struct rcar_du_device *rcdu = dev->dev_private;
-	unsigned int i;
-
-	for (i = 0; i < ARRAY_SIZE(rcdu->crtcs); ++i)
-		rcar_du_crtc_irq(&rcdu->crtcs[i]);
 
-	return IRQ_HANDLED;
+	drm_fbdev_cma_restore_mode(rcdu->fbdev);
 }
 
 static int rcar_du_enable_vblank(struct drm_device *dev, int crtc)
@@ -230,18 +148,16 @@ static const struct file_operations rcar_du_fops = {
 #endif
 	.poll		= drm_poll,
 	.read		= drm_read,
-	.fasync		= drm_fasync,
 	.llseek		= no_llseek,
 	.mmap		= drm_gem_cma_mmap,
 };
 
 static struct drm_driver rcar_du_driver = {
-	.driver_features	= DRIVER_HAVE_IRQ | DRIVER_GEM | DRIVER_MODESET
-				| DRIVER_PRIME,
+	.driver_features	= DRIVER_GEM | DRIVER_MODESET | DRIVER_PRIME,
 	.load			= rcar_du_load,
 	.unload			= rcar_du_unload,
 	.preclose		= rcar_du_preclose,
-	.irq_handler		= rcar_du_irq,
+	.lastclose		= rcar_du_lastclose,
 	.get_vblank_counter	= drm_vblank_count,
 	.enable_vblank		= rcar_du_enable_vblank,
 	.disable_vblank		= rcar_du_disable_vblank,
@@ -258,7 +174,7 @@ static struct drm_driver rcar_du_driver = {
 	.gem_prime_mmap		= drm_gem_cma_prime_mmap,
 	.dumb_create		= rcar_du_dumb_create,
 	.dumb_map_offset	= drm_gem_cma_dumb_map_offset,
-	.dumb_destroy		= drm_gem_cma_dumb_destroy,
+	.dumb_destroy		= drm_gem_dumb_destroy,
 	.fops			= &rcar_du_fops,
 	.name			= "rcar-du",
 	.desc			= "Renesas R-Car Display Unit",
@@ -313,6 +229,57 @@ static int rcar_du_remove(struct platform_device *pdev)
 	return 0;
 }
 
+static const struct rcar_du_device_info rcar_du_r8a7779_info = {
+	.features = 0,
+	.num_crtcs = 2,
+	.routes = {
+		/* R8A7779 has two RGB outputs and one (currently unsupported)
+		 * TCON output.
+		 */
+		[RCAR_DU_OUTPUT_DPAD0] = {
+			.possible_crtcs = BIT(0),
+			.encoder_type = DRM_MODE_ENCODER_NONE,
+		},
+		[RCAR_DU_OUTPUT_DPAD1] = {
+			.possible_crtcs = BIT(1) | BIT(0),
+			.encoder_type = DRM_MODE_ENCODER_NONE,
+		},
+	},
+	.num_lvds = 0,
+};
+
+static const struct rcar_du_device_info rcar_du_r8a7790_info = {
+	.features = RCAR_DU_FEATURE_CRTC_IRQ_CLOCK | RCAR_DU_FEATURE_ALIGN_128B
+		  | RCAR_DU_FEATURE_DEFR8,
+	.num_crtcs = 3,
+	.routes = {
+		/* R8A7790 has one RGB output, two LVDS outputs and one
+		 * (currently unsupported) TCON output.
+		 */
+		[RCAR_DU_OUTPUT_DPAD0] = {
+			.possible_crtcs = BIT(2) | BIT(1) | BIT(0),
+			.encoder_type = DRM_MODE_ENCODER_NONE,
+		},
+		[RCAR_DU_OUTPUT_LVDS0] = {
+			.possible_crtcs = BIT(0),
+			.encoder_type = DRM_MODE_ENCODER_LVDS,
+		},
+		[RCAR_DU_OUTPUT_LVDS1] = {
+			.possible_crtcs = BIT(2) | BIT(1),
+			.encoder_type = DRM_MODE_ENCODER_LVDS,
+		},
+	},
+	.num_lvds = 2,
+};
+
+static const struct platform_device_id rcar_du_id_table[] = {
+	{ "rcar-du-r8a7779", (kernel_ulong_t)&rcar_du_r8a7779_info },
+	{ "rcar-du-r8a7790", (kernel_ulong_t)&rcar_du_r8a7790_info },
+	{ }
+};
+
+MODULE_DEVICE_TABLE(platform, rcar_du_id_table);
+
 static struct platform_driver rcar_du_platform_driver = {
 	.probe		= rcar_du_probe,
 	.remove		= rcar_du_remove,
@@ -321,6 +288,7 @@ static struct platform_driver rcar_du_platform_driver = {
 		.name	= "rcar-du",
 		.pm	= &rcar_du_pm_ops,
 	},
+	.id_table	= rcar_du_id_table,
 };
 
 module_platform_driver(rcar_du_platform_driver);
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_drv.h b/drivers/gpu/drm/rcar-du/rcar_du_drv.h
index 193cc59d495c..65d2d636b002 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_drv.h
+++ b/drivers/gpu/drm/rcar-du/rcar_du_drv.h
@@ -15,43 +15,74 @@
 #define __RCAR_DU_DRV_H__
 
 #include <linux/kernel.h>
-#include <linux/mutex.h>
 #include <linux/platform_data/rcar-du.h>
 
 #include "rcar_du_crtc.h"
-#include "rcar_du_plane.h"
+#include "rcar_du_group.h"
 
 struct clk;
 struct device;
 struct drm_device;
+struct drm_fbdev_cma;
+struct rcar_du_device;
+struct rcar_du_lvdsenc;
+
+#define RCAR_DU_FEATURE_CRTC_IRQ_CLOCK	(1 << 0)	/* Per-CRTC IRQ and clock */
+#define RCAR_DU_FEATURE_ALIGN_128B	(1 << 1)	/* Align pitches to 128 bytes */
+#define RCAR_DU_FEATURE_DEFR8		(1 << 2)	/* Has DEFR8 register */
+
+/*
+ * struct rcar_du_output_routing - Output routing specification
+ * @possible_crtcs: bitmask of possible CRTCs for the output
+ * @encoder_type: DRM type of the internal encoder associated with the output
+ *
+ * The DU has 5 possible outputs (DPAD0/1, LVDS0/1, TCON). Output routing data
+ * specify the valid SoC outputs, which CRTCs can drive the output, and the type
+ * of in-SoC encoder for the output.
+ */
+struct rcar_du_output_routing {
+	unsigned int possible_crtcs;
+	unsigned int encoder_type;
+};
+
+/*
+ * struct rcar_du_device_info - DU model-specific information
+ * @features: device features (RCAR_DU_FEATURE_*)
+ * @num_crtcs: total number of CRTCs
+ * @routes: array of CRTC to output routes, indexed by output (RCAR_DU_OUTPUT_*)
+ * @num_lvds: number of internal LVDS encoders
+ */
+struct rcar_du_device_info {
+	unsigned int features;
+	unsigned int num_crtcs;
+	struct rcar_du_output_routing routes[RCAR_DU_OUTPUT_MAX];
+	unsigned int num_lvds;
+};
 
 struct rcar_du_device {
 	struct device *dev;
 	const struct rcar_du_platform_data *pdata;
+	const struct rcar_du_device_info *info;
 
 	void __iomem *mmio;
-	struct clk *clock;
-	unsigned int use_count;
 
 	struct drm_device *ddev;
+	struct drm_fbdev_cma *fbdev;
 
-	struct rcar_du_crtc crtcs[2];
-	unsigned int used_crtcs;
+	struct rcar_du_crtc crtcs[3];
 	unsigned int num_crtcs;
 
-	struct {
-		struct rcar_du_plane planes[RCAR_DU_NUM_SW_PLANES];
-		unsigned int free;
-		struct mutex lock;
+	struct rcar_du_group groups[2];
 
-		struct drm_property *alpha;
-		struct drm_property *colorkey;
-		struct drm_property *zpos;
-	} planes;
+	unsigned int dpad0_source;
+	struct rcar_du_lvdsenc *lvds[2];
 };
 
-int rcar_du_get(struct rcar_du_device *rcdu);
-void rcar_du_put(struct rcar_du_device *rcdu);
+static inline bool rcar_du_has(struct rcar_du_device *rcdu,
+			       unsigned int feature)
+{
+	return rcdu->info->features & feature;
+}
 
 static inline u32 rcar_du_read(struct rcar_du_device *rcdu, u32 reg)
 {
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_encoder.c b/drivers/gpu/drm/rcar-du/rcar_du_encoder.c
new file mode 100644
index 000000000000..3daa7a168dc6
--- /dev/null
+++ b/drivers/gpu/drm/rcar-du/rcar_du_encoder.c
@@ -0,0 +1,202 @@
+/*
+ * rcar_du_encoder.c  --  R-Car Display Unit Encoder
+ *
+ * Copyright (C) 2013 Renesas Corporation
+ *
+ * Contact: Laurent Pinchart (laurent.pinchart@ideasonboard.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/export.h>
+
+#include <drm/drmP.h>
+#include <drm/drm_crtc.h>
+#include <drm/drm_crtc_helper.h>
+
+#include "rcar_du_drv.h"
+#include "rcar_du_encoder.h"
+#include "rcar_du_kms.h"
+#include "rcar_du_lvdscon.h"
+#include "rcar_du_lvdsenc.h"
+#include "rcar_du_vgacon.h"
+
+/* -----------------------------------------------------------------------------
+ * Common connector functions
+ */
+
+struct drm_encoder *
+rcar_du_connector_best_encoder(struct drm_connector *connector)
+{
+	struct rcar_du_connector *rcon = to_rcar_connector(connector);
+
+	return &rcon->encoder->encoder;
+}
+
+/* -----------------------------------------------------------------------------
+ * Encoder
+ */
+
+static void rcar_du_encoder_dpms(struct drm_encoder *encoder, int mode)
+{
+	struct rcar_du_encoder *renc = to_rcar_encoder(encoder);
+
+	if (renc->lvds)
+		rcar_du_lvdsenc_dpms(renc->lvds, encoder->crtc, mode);
+}
+
+static bool rcar_du_encoder_mode_fixup(struct drm_encoder *encoder,
+				       const struct drm_display_mode *mode,
+				       struct drm_display_mode *adjusted_mode)
+{
+	struct rcar_du_encoder *renc = to_rcar_encoder(encoder);
+	const struct drm_display_mode *panel_mode;
+	struct drm_device *dev = encoder->dev;
+	struct drm_connector *connector;
+	bool found = false;
+
+	/* DAC encoders have currently no restriction on the mode. */
+	if (encoder->encoder_type == DRM_MODE_ENCODER_DAC)
+		return true;
+
+	list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
+		if (connector->encoder == encoder) {
+			found = true;
+			break;
+		}
+	}
+
+	if (!found) {
+		dev_dbg(dev->dev, "mode_fixup: no connector found\n");
+		return false;
+	}
+
+	if (list_empty(&connector->modes)) {
+		dev_dbg(dev->dev, "mode_fixup: empty modes list\n");
+		return false;
+	}
+
+	panel_mode = list_first_entry(&connector->modes,
+				      struct drm_display_mode, head);
+
+	/* We're not allowed to modify the resolution. */
+	if (mode->hdisplay != panel_mode->hdisplay ||
+	    mode->vdisplay != panel_mode->vdisplay)
+		return false;
+
+	/* The flat panel mode is fixed, just copy it to the adjusted mode. */
+	drm_mode_copy(adjusted_mode, panel_mode);
+
+	/* The internal LVDS encoder has a clock frequency operating range of
+	 * 30MHz to 150MHz. Clamp the clock accordingly.
+	 */
+	if (renc->lvds)
+		adjusted_mode->clock = clamp(adjusted_mode->clock,
+					     30000, 150000);
+
+	return true;
+}
+
+static void rcar_du_encoder_mode_prepare(struct drm_encoder *encoder)
+{
+	struct rcar_du_encoder *renc = to_rcar_encoder(encoder);
+
+	if (renc->lvds)
+		rcar_du_lvdsenc_dpms(renc->lvds, encoder->crtc,
+				     DRM_MODE_DPMS_OFF);
+}
+
+static void rcar_du_encoder_mode_commit(struct drm_encoder *encoder)
+{
+	struct rcar_du_encoder *renc = to_rcar_encoder(encoder);
+
+	if (renc->lvds)
+		rcar_du_lvdsenc_dpms(renc->lvds, encoder->crtc,
+				     DRM_MODE_DPMS_ON);
+}
+
+static void rcar_du_encoder_mode_set(struct drm_encoder *encoder,
+				     struct drm_display_mode *mode,
+				     struct drm_display_mode *adjusted_mode)
+{
+	struct rcar_du_encoder *renc = to_rcar_encoder(encoder);
+
+	rcar_du_crtc_route_output(encoder->crtc, renc->output);
+}
+
+static const struct drm_encoder_helper_funcs encoder_helper_funcs = {
+	.dpms = rcar_du_encoder_dpms,
+	.mode_fixup = rcar_du_encoder_mode_fixup,
+	.prepare = rcar_du_encoder_mode_prepare,
+	.commit = rcar_du_encoder_mode_commit,
+	.mode_set = rcar_du_encoder_mode_set,
+};
+
+static const struct drm_encoder_funcs encoder_funcs = {
+	.destroy = drm_encoder_cleanup,
+};
+
+int rcar_du_encoder_init(struct rcar_du_device *rcdu,
+			 enum rcar_du_encoder_type type,
+			 enum rcar_du_output output,
+			 const struct rcar_du_encoder_data *data)
+{
+	struct rcar_du_encoder *renc;
+	unsigned int encoder_type;
+	int ret;
+
+	renc = devm_kzalloc(rcdu->dev, sizeof(*renc), GFP_KERNEL);
+	if (renc == NULL)
+		return -ENOMEM;
+
+	renc->output = output;
+
+	switch (output) {
+	case RCAR_DU_OUTPUT_LVDS0:
+		renc->lvds = rcdu->lvds[0];
+		break;
+
+	case RCAR_DU_OUTPUT_LVDS1:
+		renc->lvds = rcdu->lvds[1];
+		break;
+
+	default:
+		break;
+	}
+
+	switch (type) {
+	case RCAR_DU_ENCODER_VGA:
+		encoder_type = DRM_MODE_ENCODER_DAC;
+		break;
+	case RCAR_DU_ENCODER_LVDS:
+		encoder_type = DRM_MODE_ENCODER_LVDS;
+		break;
+	case RCAR_DU_ENCODER_NONE:
+	default:
+		/* No external encoder, use the internal encoder type. */
+		encoder_type = rcdu->info->routes[output].encoder_type;
+		break;
+	}
+
+	ret = drm_encoder_init(rcdu->ddev, &renc->encoder, &encoder_funcs,
+			       encoder_type);
+	if (ret < 0)
+		return ret;
+
+	drm_encoder_helper_add(&renc->encoder, &encoder_helper_funcs);
+
+	switch (encoder_type) {
+	case DRM_MODE_ENCODER_LVDS:
+		return rcar_du_lvds_connector_init(rcdu, renc,
+						   &data->connector.lvds.panel);
+
+	case DRM_MODE_ENCODER_DAC:
+		return rcar_du_vga_connector_init(rcdu, renc);
+
+	default:
+		return -EINVAL;
+	}
+}
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_encoder.h b/drivers/gpu/drm/rcar-du/rcar_du_encoder.h
new file mode 100644
index 000000000000..0e5a65e45d0e
--- /dev/null
+++ b/drivers/gpu/drm/rcar-du/rcar_du_encoder.h
@@ -0,0 +1,49 @@
+/*
+ * rcar_du_encoder.h  --  R-Car Display Unit Encoder
+ *
+ * Copyright (C) 2013 Renesas Corporation
+ *
+ * Contact: Laurent Pinchart (laurent.pinchart@ideasonboard.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#ifndef __RCAR_DU_ENCODER_H__
+#define __RCAR_DU_ENCODER_H__
+
+#include <linux/platform_data/rcar-du.h>
+
+#include <drm/drm_crtc.h>
+
+struct rcar_du_device;
+struct rcar_du_lvdsenc;
+
+struct rcar_du_encoder {
+	struct drm_encoder encoder;
+	enum rcar_du_output output;
+	struct rcar_du_lvdsenc *lvds;
+};
+
+#define to_rcar_encoder(e) \
+	container_of(e, struct rcar_du_encoder, encoder)
+
+struct rcar_du_connector {
+	struct drm_connector connector;
+	struct rcar_du_encoder *encoder;
+};
+
+#define to_rcar_connector(c) \
+	container_of(c, struct rcar_du_connector, connector)
+
+struct drm_encoder *
+rcar_du_connector_best_encoder(struct drm_connector *connector);
+
+int rcar_du_encoder_init(struct rcar_du_device *rcdu,
+			 enum rcar_du_encoder_type type,
+			 enum rcar_du_output output,
+			 const struct rcar_du_encoder_data *data);
+
+#endif /* __RCAR_DU_ENCODER_H__ */
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_group.c b/drivers/gpu/drm/rcar-du/rcar_du_group.c
new file mode 100644
index 000000000000..eb53cd97e8c6
--- /dev/null
+++ b/drivers/gpu/drm/rcar-du/rcar_du_group.c
@@ -0,0 +1,187 @@
+/*
+ * rcar_du_group.c  --  R-Car Display Unit Channels Pair
+ *
+ * Copyright (C) 2013 Renesas Corporation
+ *
+ * Contact: Laurent Pinchart (laurent.pinchart@ideasonboard.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+/*
+ * The R8A7779 DU is split in per-CRTC resources (scan-out engine, blending
+ * unit, timings generator, ...) and device-global resources (start/stop
+ * control, planes, ...) shared between the two CRTCs.
+ *
+ * The R8A7790 introduced a third CRTC with its own set of global resources.
+ * This would be modeled as two separate DU device instances if it wasn't for
+ * a handful or resources that are shared between the three CRTCs (mostly
+ * related to input and output routing). For this reason the R8A7790 DU must be
+ * modeled as a single device with three CRTCs, two sets of "semi-global"
+ * resources, and a few device-global resources.
+ *
+ * The rcar_du_group object is a driver specific object, without any real
+ * counterpart in the DU documentation, that models those semi-global resources.
+ */
+
+#include <linux/clk.h>
+#include <linux/io.h>
+
+#include "rcar_du_drv.h"
+#include "rcar_du_group.h"
+#include "rcar_du_regs.h"
+
+u32 rcar_du_group_read(struct rcar_du_group *rgrp, u32 reg)
+{
+	return rcar_du_read(rgrp->dev, rgrp->mmio_offset + reg);
+}
+
+void rcar_du_group_write(struct rcar_du_group *rgrp, u32 reg, u32 data)
+{
+	rcar_du_write(rgrp->dev, rgrp->mmio_offset + reg, data);
+}
+
+static void rcar_du_group_setup_defr8(struct rcar_du_group *rgrp)
+{
+	u32 defr8 = DEFR8_CODE | DEFR8_DEFE8;
+
+	if (!rcar_du_has(rgrp->dev, RCAR_DU_FEATURE_DEFR8))
+		return;
+
+	/* The DEFR8 register for the first group also controls RGB output
+	 * routing to DPAD0
+	 */
+	if (rgrp->index == 0)
+		defr8 |= DEFR8_DRGBS_DU(rgrp->dev->dpad0_source);
+
+	rcar_du_group_write(rgrp, DEFR8, defr8);
+}
+
+static void rcar_du_group_setup(struct rcar_du_group *rgrp)
+{
+	/* Enable extended features */
+	rcar_du_group_write(rgrp, DEFR, DEFR_CODE | DEFR_DEFE);
+	rcar_du_group_write(rgrp, DEFR2, DEFR2_CODE | DEFR2_DEFE2G);
+	rcar_du_group_write(rgrp, DEFR3, DEFR3_CODE | DEFR3_DEFE3);
+	rcar_du_group_write(rgrp, DEFR4, DEFR4_CODE);
+	rcar_du_group_write(rgrp, DEFR5, DEFR5_CODE | DEFR5_DEFE5);
+
+	rcar_du_group_setup_defr8(rgrp);
+
+	/* Use DS1PR and DS2PR to configure planes priorities and connects the
+	 * superposition 0 to DU0 pins. DU1 pins will be configured dynamically.
+	 */
+	rcar_du_group_write(rgrp, DORCR, DORCR_PG1D_DS1 | DORCR_DPRS);
+}
+
+/*
+ * rcar_du_group_get - Acquire a reference to the DU channels group
+ *
+ * Acquiring the first reference setups core registers. A reference must be held
+ * before accessing any hardware registers.
+ *
+ * This function must be called with the DRM mode_config lock held.
+ *
+ * Return 0 in case of success or a negative error code otherwise.
+ */
+int rcar_du_group_get(struct rcar_du_group *rgrp)
+{
+	if (rgrp->use_count)
+		goto done;
+
+	rcar_du_group_setup(rgrp);
+
+done:
+	rgrp->use_count++;
+	return 0;
+}
+
+/*
+ * rcar_du_group_put - Release a reference to the DU
+ *
+ * This function must be called with the DRM mode_config lock held.
+ */
+void rcar_du_group_put(struct rcar_du_group *rgrp)
+{
+	--rgrp->use_count;
+}
+
+static void __rcar_du_group_start_stop(struct rcar_du_group *rgrp, bool start)
+{
+	rcar_du_group_write(rgrp, DSYSR,
+		(rcar_du_group_read(rgrp, DSYSR) & ~(DSYSR_DRES | DSYSR_DEN)) |
+		(start ? DSYSR_DEN : DSYSR_DRES));
+}
+
+void rcar_du_group_start_stop(struct rcar_du_group *rgrp, bool start)
+{
+	/* Many of the configuration bits are only updated when the display
+	 * reset (DRES) bit in DSYSR is set to 1, disabling *both* CRTCs. Some
+	 * of those bits could be pre-configured, but others (especially the
+	 * bits related to plane assignment to display timing controllers) need
+	 * to be modified at runtime.
+	 *
+	 * Restart the display controller if a start is requested. Sorry for the
+	 * flicker. It should be possible to move most of the "DRES-update" bits
+	 * setup to driver initialization time and minimize the number of cases
+	 * when the display controller will have to be restarted.
+	 */
+	if (start) {
+		if (rgrp->used_crtcs++ != 0)
+			__rcar_du_group_start_stop(rgrp, false);
+		__rcar_du_group_start_stop(rgrp, true);
+	} else {
+		if (--rgrp->used_crtcs == 0)
+			__rcar_du_group_start_stop(rgrp, false);
+	}
+}
+
+void rcar_du_group_restart(struct rcar_du_group *rgrp)
+{
+	__rcar_du_group_start_stop(rgrp, false);
+	__rcar_du_group_start_stop(rgrp, true);
+}
+
+static int rcar_du_set_dpad0_routing(struct rcar_du_device *rcdu)
+{
+	int ret;
+
+	/* RGB output routing to DPAD0 is configured in the DEFR8 register of
+	 * the first group. As this function can be called with the DU0 and DU1
+	 * CRTCs disabled, we need to enable the first group clock before
+	 * accessing the register.
+	 */
+	ret = clk_prepare_enable(rcdu->crtcs[0].clock);
+	if (ret < 0)
+		return ret;
+
+	rcar_du_group_setup_defr8(&rcdu->groups[0]);
+
+	clk_disable_unprepare(rcdu->crtcs[0].clock);
+
+	return 0;
+}
+
+int rcar_du_group_set_routing(struct rcar_du_group *rgrp)
+{
+	struct rcar_du_crtc *crtc0 = &rgrp->dev->crtcs[rgrp->index * 2];
+	u32 dorcr = rcar_du_group_read(rgrp, DORCR);
+
+	dorcr &= ~(DORCR_PG2T | DORCR_DK2S | DORCR_PG2D_MASK);
+
+	/* Set the DPAD1 pins sources. Select CRTC 0 if explicitly requested and
+	 * CRTC 1 in all other cases to avoid cloning CRTC 0 to DPAD0 and DPAD1
+	 * by default.
+	 */
+	if (crtc0->outputs & BIT(RCAR_DU_OUTPUT_DPAD1))
+		dorcr |= DORCR_PG2D_DS1;
+	else
+		dorcr |= DORCR_PG2T | DORCR_DK2S | DORCR_PG2D_DS2;
+
+	rcar_du_group_write(rgrp, DORCR, dorcr);
+
+	return rcar_du_set_dpad0_routing(rgrp->dev);
+}
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_group.h b/drivers/gpu/drm/rcar-du/rcar_du_group.h
new file mode 100644
index 000000000000..5025930972ec
--- /dev/null
+++ b/drivers/gpu/drm/rcar-du/rcar_du_group.h
@@ -0,0 +1,50 @@
+/*
+ * rcar_du_group.c  --  R-Car Display Unit Planes and CRTCs Group
+ *
+ * Copyright (C) 2013 Renesas Corporation
+ *
+ * Contact: Laurent Pinchart (laurent.pinchart@ideasonboard.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#ifndef __RCAR_DU_GROUP_H__
+#define __RCAR_DU_GROUP_H__
+
+#include "rcar_du_plane.h"
+
+struct rcar_du_device;
+
+/*
+ * struct rcar_du_group - CRTCs and planes group
+ * @dev: the DU device
+ * @mmio_offset: registers offset in the device memory map
+ * @index: group index
+ * @use_count: number of users of the group (rcar_du_group_(get|put))
+ * @used_crtcs: number of CRTCs currently in use
+ * @planes: planes handled by the group
+ */
+struct rcar_du_group {
+	struct rcar_du_device *dev;
+	unsigned int mmio_offset;
+	unsigned int index;
+
+	unsigned int use_count;
+	unsigned int used_crtcs;
+
+	struct rcar_du_planes planes;
+};
+
+u32 rcar_du_group_read(struct rcar_du_group *rgrp, u32 reg);
+void rcar_du_group_write(struct rcar_du_group *rgrp, u32 reg, u32 data);
+
+int rcar_du_group_get(struct rcar_du_group *rgrp);
+void rcar_du_group_put(struct rcar_du_group *rgrp);
+void rcar_du_group_start_stop(struct rcar_du_group *rgrp, bool start);
+void rcar_du_group_restart(struct rcar_du_group *rgrp);
+int rcar_du_group_set_routing(struct rcar_du_group *rgrp);
+
+#endif /* __RCAR_DU_GROUP_H__ */
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_kms.c b/drivers/gpu/drm/rcar-du/rcar_du_kms.c
index d30c2e29bee2..b31ac080c4a7 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_kms.c
+++ b/drivers/gpu/drm/rcar-du/rcar_du_kms.c
@@ -19,10 +19,10 @@
 
 #include "rcar_du_crtc.h"
 #include "rcar_du_drv.h"
+#include "rcar_du_encoder.h"
 #include "rcar_du_kms.h"
-#include "rcar_du_lvds.h"
+#include "rcar_du_lvdsenc.h"
 #include "rcar_du_regs.h"
-#include "rcar_du_vga.h"
 
 /* -----------------------------------------------------------------------------
  * Format helpers
@@ -106,46 +106,24 @@ const struct rcar_du_format_info *rcar_du_format_info(u32 fourcc)
 }
 
 /* -----------------------------------------------------------------------------
- * Common connector and encoder functions
- */
-
-struct drm_encoder *
-rcar_du_connector_best_encoder(struct drm_connector *connector)
-{
-	struct rcar_du_connector *rcon = to_rcar_connector(connector);
-
-	return &rcon->encoder->encoder;
-}
-
-void rcar_du_encoder_mode_prepare(struct drm_encoder *encoder)
-{
-}
-
-void rcar_du_encoder_mode_set(struct drm_encoder *encoder,
-			      struct drm_display_mode *mode,
-			      struct drm_display_mode *adjusted_mode)
-{
-	struct rcar_du_encoder *renc = to_rcar_encoder(encoder);
-
-	rcar_du_crtc_route_output(encoder->crtc, renc->output);
-}
-
-void rcar_du_encoder_mode_commit(struct drm_encoder *encoder)
-{
-}
-
-/* -----------------------------------------------------------------------------
  * Frame buffer
  */
 
 int rcar_du_dumb_create(struct drm_file *file, struct drm_device *dev,
 			struct drm_mode_create_dumb *args)
 {
+	struct rcar_du_device *rcdu = dev->dev_private;
 	unsigned int min_pitch = DIV_ROUND_UP(args->width * args->bpp, 8);
 	unsigned int align;
 
-	/* The pitch must be aligned to a 16 pixels boundary. */
-	align = 16 * args->bpp / 8;
+	/* The R8A7779 DU requires a 16 pixels pitch alignment as documented,
+	 * but the R8A7790 DU seems to require a 128 bytes pitch alignment.
+	 */
+	if (rcar_du_has(rcdu, RCAR_DU_FEATURE_ALIGN_128B))
+		align = 128;
+	else
+		align = 16 * args->bpp / 8;
+
 	args->pitch = roundup(max(args->pitch, min_pitch), align);
 
 	return drm_gem_cma_dumb_create(file, dev, args);
@@ -155,6 +133,7 @@ static struct drm_framebuffer *
 rcar_du_fb_create(struct drm_device *dev, struct drm_file *file_priv,
 		  struct drm_mode_fb_cmd2 *mode_cmd)
 {
+	struct rcar_du_device *rcdu = dev->dev_private;
 	const struct rcar_du_format_info *format;
 	unsigned int align;
 
@@ -165,7 +144,10 @@ rcar_du_fb_create(struct drm_device *dev, struct drm_file *file_priv,
 		return ERR_PTR(-EINVAL);
 	}
 
-	align = 16 * format->bpp / 8;
+	if (rcar_du_has(rcdu, RCAR_DU_FEATURE_ALIGN_128B))
+		align = 128;
+	else
+		align = 16 * format->bpp / 8;
 
 	if (mode_cmd->pitches[0] & (align - 1) ||
 	    mode_cmd->pitches[0] >= 8192) {
@@ -185,81 +167,124 @@ rcar_du_fb_create(struct drm_device *dev, struct drm_file *file_priv,
 	return drm_fb_cma_create(dev, file_priv, mode_cmd);
 }
 
+static void rcar_du_output_poll_changed(struct drm_device *dev)
+{
+	struct rcar_du_device *rcdu = dev->dev_private;
+
+	drm_fbdev_cma_hotplug_event(rcdu->fbdev);
+}
+
 static const struct drm_mode_config_funcs rcar_du_mode_config_funcs = {
 	.fb_create = rcar_du_fb_create,
+	.output_poll_changed = rcar_du_output_poll_changed,
 };
 
 int rcar_du_modeset_init(struct rcar_du_device *rcdu)
 {
+	static const unsigned int mmio_offsets[] = {
+		DU0_REG_OFFSET, DU2_REG_OFFSET
+	};
+
 	struct drm_device *dev = rcdu->ddev;
 	struct drm_encoder *encoder;
+	struct drm_fbdev_cma *fbdev;
+	unsigned int num_groups;
 	unsigned int i;
 	int ret;
 
-	drm_mode_config_init(rcdu->ddev);
+	drm_mode_config_init(dev);
 
-	rcdu->ddev->mode_config.min_width = 0;
-	rcdu->ddev->mode_config.min_height = 0;
-	rcdu->ddev->mode_config.max_width = 4095;
-	rcdu->ddev->mode_config.max_height = 2047;
-	rcdu->ddev->mode_config.funcs = &rcar_du_mode_config_funcs;
+	dev->mode_config.min_width = 0;
+	dev->mode_config.min_height = 0;
+	dev->mode_config.max_width = 4095;
+	dev->mode_config.max_height = 2047;
+	dev->mode_config.funcs = &rcar_du_mode_config_funcs;
 
-	ret = rcar_du_plane_init(rcdu);
-	if (ret < 0)
-		return ret;
+	rcdu->num_crtcs = rcdu->info->num_crtcs;
+
+	/* Initialize the groups. */
+	num_groups = DIV_ROUND_UP(rcdu->num_crtcs, 2);
+
+	for (i = 0; i < num_groups; ++i) {
+		struct rcar_du_group *rgrp = &rcdu->groups[i];
+
+		rgrp->dev = rcdu;
+		rgrp->mmio_offset = mmio_offsets[i];
+		rgrp->index = i;
+
+		ret = rcar_du_planes_init(rgrp);
+		if (ret < 0)
+			return ret;
+	}
+
+	/* Create the CRTCs. */
+	for (i = 0; i < rcdu->num_crtcs; ++i) {
+		struct rcar_du_group *rgrp = &rcdu->groups[i / 2];
 
-	for (i = 0; i < ARRAY_SIZE(rcdu->crtcs); ++i) {
-		ret = rcar_du_crtc_create(rcdu, i);
+		ret = rcar_du_crtc_create(rgrp, i);
 		if (ret < 0)
 			return ret;
 	}
 
-	rcdu->used_crtcs = 0;
-	rcdu->num_crtcs = i;
+	/* Initialize the encoders. */
+	ret = rcar_du_lvdsenc_init(rcdu);
+	if (ret < 0)
+		return ret;
 
 	for (i = 0; i < rcdu->pdata->num_encoders; ++i) {
 		const struct rcar_du_encoder_data *pdata =
 			&rcdu->pdata->encoders[i];
+		const struct rcar_du_output_routing *route =
+			&rcdu->info->routes[pdata->output];
+
+		if (pdata->type == RCAR_DU_ENCODER_UNUSED)
+			continue;
 
-		if (pdata->output >= ARRAY_SIZE(rcdu->crtcs)) {
+		if (pdata->output >= RCAR_DU_OUTPUT_MAX ||
+		    route->possible_crtcs == 0) {
 			dev_warn(rcdu->dev,
 				 "encoder %u references unexisting output %u, skipping\n",
 				 i, pdata->output);
 			continue;
 		}
 
-		switch (pdata->encoder) {
-		case RCAR_DU_ENCODER_VGA:
-			rcar_du_vga_init(rcdu, &pdata->u.vga, pdata->output);
-			break;
-
-		case RCAR_DU_ENCODER_LVDS:
-			rcar_du_lvds_init(rcdu, &pdata->u.lvds, pdata->output);
-			break;
-
-		default:
-			break;
-		}
+		rcar_du_encoder_init(rcdu, pdata->type, pdata->output, pdata);
 	}
 
-	/* Set the possible CRTCs and possible clones. All encoders can be
-	 * driven by the CRTC associated with the output they're connected to,
-	 * as well as by CRTC 0.
+	/* Set the possible CRTCs and possible clones. There's always at least
+	 * one way for all encoders to clone each other, set all bits in the
+	 * possible clones field.
 	 */
 	list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) {
 		struct rcar_du_encoder *renc = to_rcar_encoder(encoder);
+		const struct rcar_du_output_routing *route =
+			&rcdu->info->routes[renc->output];
 
-		encoder->possible_crtcs = (1 << 0) | (1 << renc->output);
-		encoder->possible_clones = 1 << 0;
+		encoder->possible_crtcs = route->possible_crtcs;
+		encoder->possible_clones = (1 << rcdu->pdata->num_encoders) - 1;
 	}
 
-	ret = rcar_du_plane_register(rcdu);
-	if (ret < 0)
-		return ret;
+	/* Now that the CRTCs have been initialized register the planes. */
+	for (i = 0; i < num_groups; ++i) {
+		ret = rcar_du_planes_register(&rcdu->groups[i]);
+		if (ret < 0)
+			return ret;
+	}
+
+	drm_kms_helper_poll_init(dev);
+
+	drm_helper_disable_unused_functions(dev);
+
+	fbdev = drm_fbdev_cma_init(dev, 32, dev->mode_config.num_crtc,
+				   dev->mode_config.num_connector);
+	if (IS_ERR(fbdev))
+		return PTR_ERR(fbdev);
 
-	drm_kms_helper_poll_init(rcdu->ddev);
+#ifndef CONFIG_FRAMEBUFFER_CONSOLE
+	drm_fbdev_cma_restore_mode(fbdev);
+#endif
 
-	drm_helper_disable_unused_functions(rcdu->ddev);
+	rcdu->fbdev = fbdev;
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_kms.h b/drivers/gpu/drm/rcar-du/rcar_du_kms.h
index dba472263486..5750e6af5655 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_kms.h
+++ b/drivers/gpu/drm/rcar-du/rcar_du_kms.h
@@ -16,8 +16,9 @@
 
 #include <linux/types.h>
 
-#include <drm/drm_crtc.h>
-
+struct drm_file;
+struct drm_device;
+struct drm_mode_create_dumb;
 struct rcar_du_device;
 
 struct rcar_du_format_info {
@@ -28,32 +29,8 @@ struct rcar_du_format_info {
 	unsigned int edf;
 };
 
-struct rcar_du_encoder {
-	struct drm_encoder encoder;
-	unsigned int output;
-};
-
-#define to_rcar_encoder(e) \
-	container_of(e, struct rcar_du_encoder, encoder)
-
-struct rcar_du_connector {
-	struct drm_connector connector;
-	struct rcar_du_encoder *encoder;
-};
-
-#define to_rcar_connector(c) \
-	container_of(c, struct rcar_du_connector, connector)
-
 const struct rcar_du_format_info *rcar_du_format_info(u32 fourcc);
 
-struct drm_encoder *
-rcar_du_connector_best_encoder(struct drm_connector *connector);
-void rcar_du_encoder_mode_prepare(struct drm_encoder *encoder);
-void rcar_du_encoder_mode_set(struct drm_encoder *encoder,
-			      struct drm_display_mode *mode,
-			      struct drm_display_mode *adjusted_mode);
-void rcar_du_encoder_mode_commit(struct drm_encoder *encoder);
-
 int rcar_du_modeset_init(struct rcar_du_device *rcdu);
 
 int rcar_du_dumb_create(struct drm_file *file, struct drm_device *dev,
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_lvds.c b/drivers/gpu/drm/rcar-du/rcar_du_lvdscon.c
index 7aefe7267e1d..4f3ba93cd91d 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_lvds.c
+++ b/drivers/gpu/drm/rcar-du/rcar_du_lvdscon.c
@@ -1,5 +1,5 @@
 /*
- * rcar_du_lvds.c  --  R-Car Display Unit LVDS Encoder and Connector
+ * rcar_du_lvdscon.c  --  R-Car Display Unit LVDS Connector
  *
  * Copyright (C) 2013 Renesas Corporation
  *
@@ -16,8 +16,9 @@
 #include <drm/drm_crtc_helper.h>
 
 #include "rcar_du_drv.h"
+#include "rcar_du_encoder.h"
 #include "rcar_du_kms.h"
-#include "rcar_du_lvds.h"
+#include "rcar_du_lvdscon.h"
 
 struct rcar_du_lvds_connector {
 	struct rcar_du_connector connector;
@@ -28,13 +29,10 @@ struct rcar_du_lvds_connector {
 #define to_rcar_lvds_connector(c) \
 	container_of(c, struct rcar_du_lvds_connector, connector.connector)
 
-/* -----------------------------------------------------------------------------
- * Connector
- */
-
 static int rcar_du_lvds_connector_get_modes(struct drm_connector *connector)
 {
-	struct rcar_du_lvds_connector *lvdscon = to_rcar_lvds_connector(connector);
+	struct rcar_du_lvds_connector *lvdscon =
+		to_rcar_lvds_connector(connector);
 	struct drm_display_mode *mode;
 
 	mode = drm_mode_create(connector->dev);
@@ -90,9 +88,9 @@ static const struct drm_connector_funcs connector_funcs = {
 	.destroy = rcar_du_lvds_connector_destroy,
 };
 
-static int rcar_du_lvds_connector_init(struct rcar_du_device *rcdu,
-				       struct rcar_du_encoder *renc,
-				       const struct rcar_du_panel_data *panel)
+int rcar_du_lvds_connector_init(struct rcar_du_device *rcdu,
+				struct rcar_du_encoder *renc,
+				const struct rcar_du_panel_data *panel)
 {
 	struct rcar_du_lvds_connector *lvdscon;
 	struct drm_connector *connector;
@@ -131,86 +129,3 @@ static int rcar_du_lvds_connector_init(struct rcar_du_device *rcdu,
 
 	return 0;
 }
-
-/* -----------------------------------------------------------------------------
- * Encoder
- */
-
-static void rcar_du_lvds_encoder_dpms(struct drm_encoder *encoder, int mode)
-{
-}
-
-static bool rcar_du_lvds_encoder_mode_fixup(struct drm_encoder *encoder,
-					   const struct drm_display_mode *mode,
-					   struct drm_display_mode *adjusted_mode)
-{
-	const struct drm_display_mode *panel_mode;
-	struct drm_device *dev = encoder->dev;
-	struct drm_connector *connector;
-	bool found = false;
-
-	list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
-		if (connector->encoder == encoder) {
-			found = true;
-			break;
-		}
-	}
-
-	if (!found) {
-		dev_dbg(dev->dev, "mode_fixup: no connector found\n");
-		return false;
-	}
-
-	if (list_empty(&connector->modes)) {
-		dev_dbg(dev->dev, "mode_fixup: empty modes list\n");
-		return false;
-	}
-
-	panel_mode = list_first_entry(&connector->modes,
-				      struct drm_display_mode, head);
-
-	/* We're not allowed to modify the resolution. */
-	if (mode->hdisplay != panel_mode->hdisplay ||
-	    mode->vdisplay != panel_mode->vdisplay)
-		return false;
-
-	/* The flat panel mode is fixed, just copy it to the adjusted mode. */
-	drm_mode_copy(adjusted_mode, panel_mode);
-
-	return true;
-}
-
-static const struct drm_encoder_helper_funcs encoder_helper_funcs = {
-	.dpms = rcar_du_lvds_encoder_dpms,
-	.mode_fixup = rcar_du_lvds_encoder_mode_fixup,
-	.prepare = rcar_du_encoder_mode_prepare,
-	.commit = rcar_du_encoder_mode_commit,
-	.mode_set = rcar_du_encoder_mode_set,
-};
-
-static const struct drm_encoder_funcs encoder_funcs = {
-	.destroy = drm_encoder_cleanup,
-};
-
-int rcar_du_lvds_init(struct rcar_du_device *rcdu,
-		      const struct rcar_du_encoder_lvds_data *data,
-		      unsigned int output)
-{
-	struct rcar_du_encoder *renc;
-	int ret;
-
-	renc = devm_kzalloc(rcdu->dev, sizeof(*renc), GFP_KERNEL);
-	if (renc == NULL)
-		return -ENOMEM;
-
-	renc->output = output;
-
-	ret = drm_encoder_init(rcdu->ddev, &renc->encoder, &encoder_funcs,
-			       DRM_MODE_ENCODER_LVDS);
-	if (ret < 0)
-		return ret;
-
-	drm_encoder_helper_add(&renc->encoder, &encoder_helper_funcs);
-
-	return rcar_du_lvds_connector_init(rcdu, renc, &data->panel);
-}
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_lvds.h b/drivers/gpu/drm/rcar-du/rcar_du_lvdscon.h
index b47f8328e103..bff8683699ca 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_lvds.h
+++ b/drivers/gpu/drm/rcar-du/rcar_du_lvdscon.h
@@ -1,5 +1,5 @@
 /*
- * rcar_du_lvds.h  --  R-Car Display Unit LVDS Encoder and Connector
+ * rcar_du_lvdscon.h  --  R-Car Display Unit LVDS Connector
  *
  * Copyright (C) 2013 Renesas Corporation
  *
@@ -11,14 +11,15 @@
  * (at your option) any later version.
  */
 
-#ifndef __RCAR_DU_LVDS_H__
-#define __RCAR_DU_LVDS_H__
+#ifndef __RCAR_DU_LVDSCON_H__
+#define __RCAR_DU_LVDSCON_H__
 
 struct rcar_du_device;
-struct rcar_du_encoder_lvds_data;
+struct rcar_du_encoder;
+struct rcar_du_panel_data;
 
-int rcar_du_lvds_init(struct rcar_du_device *rcdu,
-		      const struct rcar_du_encoder_lvds_data *data,
-		      unsigned int output);
+int rcar_du_lvds_connector_init(struct rcar_du_device *rcdu,
+				struct rcar_du_encoder *renc,
+				const struct rcar_du_panel_data *panel);
 
-#endif /* __RCAR_DU_LVDS_H__ */
+#endif /* __RCAR_DU_LVDSCON_H__ */
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_lvdsenc.c b/drivers/gpu/drm/rcar-du/rcar_du_lvdsenc.c
new file mode 100644
index 000000000000..a0f6a1781925
--- /dev/null
+++ b/drivers/gpu/drm/rcar-du/rcar_du_lvdsenc.c
@@ -0,0 +1,196 @@
+/*
+ * rcar_du_lvdsenc.c  --  R-Car Display Unit LVDS Encoder
+ *
+ * Copyright (C) 2013 Renesas Corporation
+ *
+ * Contact: Laurent Pinchart (laurent.pinchart@ideasonboard.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/clk.h>
+#include <linux/delay.h>
+#include <linux/io.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+
+#include "rcar_du_drv.h"
+#include "rcar_du_encoder.h"
+#include "rcar_du_lvdsenc.h"
+#include "rcar_lvds_regs.h"
+
+struct rcar_du_lvdsenc {
+	struct rcar_du_device *dev;
+
+	unsigned int index;
+	void __iomem *mmio;
+	struct clk *clock;
+	int dpms;
+
+	enum rcar_lvds_input input;
+};
+
+static void rcar_lvds_write(struct rcar_du_lvdsenc *lvds, u32 reg, u32 data)
+{
+	iowrite32(data, lvds->mmio + reg);
+}
+
+static int rcar_du_lvdsenc_start(struct rcar_du_lvdsenc *lvds,
+				 struct rcar_du_crtc *rcrtc)
+{
+	const struct drm_display_mode *mode = &rcrtc->crtc.mode;
+	unsigned int freq = mode->clock;
+	u32 lvdcr0;
+	u32 pllcr;
+	int ret;
+
+	if (lvds->dpms == DRM_MODE_DPMS_ON)
+		return 0;
+
+	ret = clk_prepare_enable(lvds->clock);
+	if (ret < 0)
+		return ret;
+
+	/* PLL clock configuration */
+	if (freq <= 38000)
+		pllcr = LVDPLLCR_CEEN | LVDPLLCR_COSEL | LVDPLLCR_PLLDLYCNT_38M;
+	else if (freq <= 60000)
+		pllcr = LVDPLLCR_CEEN | LVDPLLCR_COSEL | LVDPLLCR_PLLDLYCNT_60M;
+	else if (freq <= 121000)
+		pllcr = LVDPLLCR_CEEN | LVDPLLCR_COSEL | LVDPLLCR_PLLDLYCNT_121M;
+	else
+		pllcr = LVDPLLCR_PLLDLYCNT_150M;
+
+	rcar_lvds_write(lvds, LVDPLLCR, pllcr);
+
+	/* Hardcode the channels and control signals routing for now.
+	 *
+	 * HSYNC -> CTRL0
+	 * VSYNC -> CTRL1
+	 * DISP  -> CTRL2
+	 * 0     -> CTRL3
+	 *
+	 * Channels 1 and 3 are switched on ES1.
+	 */
+	rcar_lvds_write(lvds, LVDCTRCR, LVDCTRCR_CTR3SEL_ZERO |
+			LVDCTRCR_CTR2SEL_DISP | LVDCTRCR_CTR1SEL_VSYNC |
+			LVDCTRCR_CTR0SEL_HSYNC);
+	rcar_lvds_write(lvds, LVDCHCR,
+			LVDCHCR_CHSEL_CH(0, 0) | LVDCHCR_CHSEL_CH(1, 3) |
+			LVDCHCR_CHSEL_CH(2, 2) | LVDCHCR_CHSEL_CH(3, 1));
+
+	/* Select the input, hardcode mode 0, enable LVDS operation and turn
+	 * bias circuitry on.
+	 */
+	lvdcr0 = LVDCR0_BEN | LVDCR0_LVEN;
+	if (rcrtc->index == 2)
+		lvdcr0 |= LVDCR0_DUSEL;
+	rcar_lvds_write(lvds, LVDCR0, lvdcr0);
+
+	/* Turn all the channels on. */
+	rcar_lvds_write(lvds, LVDCR1, LVDCR1_CHSTBY(3) | LVDCR1_CHSTBY(2) |
+			LVDCR1_CHSTBY(1) | LVDCR1_CHSTBY(0) | LVDCR1_CLKSTBY);
+
+	/* Turn the PLL on, wait for the startup delay, and turn the output
+	 * on.
+	 */
+	lvdcr0 |= LVDCR0_PLLEN;
+	rcar_lvds_write(lvds, LVDCR0, lvdcr0);
+
+	usleep_range(100, 150);
+
+	lvdcr0 |= LVDCR0_LVRES;
+	rcar_lvds_write(lvds, LVDCR0, lvdcr0);
+
+	lvds->dpms = DRM_MODE_DPMS_ON;
+	return 0;
+}
+
+static void rcar_du_lvdsenc_stop(struct rcar_du_lvdsenc *lvds)
+{
+	if (lvds->dpms == DRM_MODE_DPMS_OFF)
+		return;
+
+	rcar_lvds_write(lvds, LVDCR0, 0);
+	rcar_lvds_write(lvds, LVDCR1, 0);
+
+	clk_disable_unprepare(lvds->clock);
+
+	lvds->dpms = DRM_MODE_DPMS_OFF;
+}
+
+int rcar_du_lvdsenc_dpms(struct rcar_du_lvdsenc *lvds,
+			 struct drm_crtc *crtc, int mode)
+{
+	if (mode == DRM_MODE_DPMS_OFF) {
+		rcar_du_lvdsenc_stop(lvds);
+		return 0;
+	} else if (crtc) {
+		struct rcar_du_crtc *rcrtc = to_rcar_crtc(crtc);
+		return rcar_du_lvdsenc_start(lvds, rcrtc);
+	} else
+		return -EINVAL;
+}
+
+static int rcar_du_lvdsenc_get_resources(struct rcar_du_lvdsenc *lvds,
+					 struct platform_device *pdev)
+{
+	struct resource *mem;
+	char name[7];
+
+	sprintf(name, "lvds.%u", lvds->index);
+
+	mem = platform_get_resource_byname(pdev, IORESOURCE_MEM, name);
+	if (mem == NULL) {
+		dev_err(&pdev->dev, "failed to get memory resource for %s\n",
+			name);
+		return -EINVAL;
+	}
+
+	lvds->mmio = devm_ioremap_resource(&pdev->dev, mem);
+	if (lvds->mmio == NULL) {
+		dev_err(&pdev->dev, "failed to remap memory resource for %s\n",
+			name);
+		return -ENOMEM;
+	}
+
+	lvds->clock = devm_clk_get(&pdev->dev, name);
+	if (IS_ERR(lvds->clock)) {
+		dev_err(&pdev->dev, "failed to get clock for %s\n", name);
+		return PTR_ERR(lvds->clock);
+	}
+
+	return 0;
+}
+
+int rcar_du_lvdsenc_init(struct rcar_du_device *rcdu)
+{
+	struct platform_device *pdev = to_platform_device(rcdu->dev);
+	struct rcar_du_lvdsenc *lvds;
+	unsigned int i;
+	int ret;
+
+	for (i = 0; i < rcdu->info->num_lvds; ++i) {
+		lvds = devm_kzalloc(&pdev->dev, sizeof(*lvds), GFP_KERNEL);
+		if (lvds == NULL) {
+			dev_err(&pdev->dev, "failed to allocate private data\n");
+			return -ENOMEM;
+		}
+
+		lvds->dev = rcdu;
+		lvds->index = i;
+		lvds->input = i ? RCAR_LVDS_INPUT_DU1 : RCAR_LVDS_INPUT_DU0;
+		lvds->dpms = DRM_MODE_DPMS_OFF;
+
+		ret = rcar_du_lvdsenc_get_resources(lvds, pdev);
+		if (ret < 0)
+			return ret;
+
+		rcdu->lvds[i] = lvds;
+	}
+
+	return 0;
+}
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_lvdsenc.h b/drivers/gpu/drm/rcar-du/rcar_du_lvdsenc.h
new file mode 100644
index 000000000000..7051c6de19ae
--- /dev/null
+++ b/drivers/gpu/drm/rcar-du/rcar_du_lvdsenc.h
@@ -0,0 +1,46 @@
+/*
+ * rcar_du_lvdsenc.h  --  R-Car Display Unit LVDS Encoder
+ *
+ * Copyright (C) 2013 Renesas Corporation
+ *
+ * Contact: Laurent Pinchart (laurent.pinchart@ideasonboard.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#ifndef __RCAR_DU_LVDSENC_H__
+#define __RCAR_DU_LVDSENC_H__
+
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/platform_data/rcar-du.h>
+
+struct rcar_drm_crtc;
+struct rcar_du_lvdsenc;
+
+enum rcar_lvds_input {
+	RCAR_LVDS_INPUT_DU0,
+	RCAR_LVDS_INPUT_DU1,
+	RCAR_LVDS_INPUT_DU2,
+};
+
+#if IS_ENABLED(CONFIG_DRM_RCAR_LVDS)
+int rcar_du_lvdsenc_init(struct rcar_du_device *rcdu);
+int rcar_du_lvdsenc_dpms(struct rcar_du_lvdsenc *lvds,
+			 struct drm_crtc *crtc, int mode);
+#else
+static inline int rcar_du_lvdsenc_init(struct rcar_du_device *rcdu)
+{
+	return 0;
+}
+static inline int rcar_du_lvdsenc_dpms(struct rcar_du_lvdsenc *lvds,
+				       struct drm_crtc *crtc, int mode)
+{
+	return 0;
+}
+#endif
+
+#endif /* __RCAR_DU_LVDSENC_H__ */
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_plane.c b/drivers/gpu/drm/rcar-du/rcar_du_plane.c
index a65f81ddf51d..53000644733f 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_plane.c
+++ b/drivers/gpu/drm/rcar-du/rcar_du_plane.c
@@ -36,90 +36,95 @@ static inline struct rcar_du_plane *to_rcar_plane(struct drm_plane *plane)
 	return container_of(plane, struct rcar_du_kms_plane, plane)->hwplane;
 }
 
-static u32 rcar_du_plane_read(struct rcar_du_device *rcdu,
+static u32 rcar_du_plane_read(struct rcar_du_group *rgrp,
 			      unsigned int index, u32 reg)
 {
-	return rcar_du_read(rcdu, index * PLANE_OFF + reg);
+	return rcar_du_read(rgrp->dev,
+			    rgrp->mmio_offset + index * PLANE_OFF + reg);
 }
 
-static void rcar_du_plane_write(struct rcar_du_device *rcdu,
+static void rcar_du_plane_write(struct rcar_du_group *rgrp,
 				unsigned int index, u32 reg, u32 data)
 {
-	rcar_du_write(rcdu, index * PLANE_OFF + reg, data);
+	rcar_du_write(rgrp->dev, rgrp->mmio_offset + index * PLANE_OFF + reg,
+		      data);
 }
 
 int rcar_du_plane_reserve(struct rcar_du_plane *plane,
 			  const struct rcar_du_format_info *format)
 {
-	struct rcar_du_device *rcdu = plane->dev;
+	struct rcar_du_group *rgrp = plane->group;
 	unsigned int i;
 	int ret = -EBUSY;
 
-	mutex_lock(&rcdu->planes.lock);
+	mutex_lock(&rgrp->planes.lock);
 
-	for (i = 0; i < ARRAY_SIZE(rcdu->planes.planes); ++i) {
-		if (!(rcdu->planes.free & (1 << i)))
+	for (i = 0; i < ARRAY_SIZE(rgrp->planes.planes); ++i) {
+		if (!(rgrp->planes.free & (1 << i)))
 			continue;
 
 		if (format->planes == 1 ||
-		    rcdu->planes.free & (1 << ((i + 1) % 8)))
+		    rgrp->planes.free & (1 << ((i + 1) % 8)))
 			break;
 	}
 
-	if (i == ARRAY_SIZE(rcdu->planes.planes))
+	if (i == ARRAY_SIZE(rgrp->planes.planes))
 		goto done;
 
-	rcdu->planes.free &= ~(1 << i);
+	rgrp->planes.free &= ~(1 << i);
 	if (format->planes == 2)
-		rcdu->planes.free &= ~(1 << ((i + 1) % 8));
+		rgrp->planes.free &= ~(1 << ((i + 1) % 8));
 
 	plane->hwindex = i;
 
 	ret = 0;
 
 done:
-	mutex_unlock(&rcdu->planes.lock);
+	mutex_unlock(&rgrp->planes.lock);
 	return ret;
 }
 
 void rcar_du_plane_release(struct rcar_du_plane *plane)
 {
-	struct rcar_du_device *rcdu = plane->dev;
+	struct rcar_du_group *rgrp = plane->group;
 
 	if (plane->hwindex == -1)
 		return;
 
-	mutex_lock(&rcdu->planes.lock);
-	rcdu->planes.free |= 1 << plane->hwindex;
+	mutex_lock(&rgrp->planes.lock);
+	rgrp->planes.free |= 1 << plane->hwindex;
 	if (plane->format->planes == 2)
-		rcdu->planes.free |= 1 << ((plane->hwindex + 1) % 8);
-	mutex_unlock(&rcdu->planes.lock);
+		rgrp->planes.free |= 1 << ((plane->hwindex + 1) % 8);
+	mutex_unlock(&rgrp->planes.lock);
 
 	plane->hwindex = -1;
 }
 
 void rcar_du_plane_update_base(struct rcar_du_plane *plane)
 {
-	struct rcar_du_device *rcdu = plane->dev;
+	struct rcar_du_group *rgrp = plane->group;
 	unsigned int index = plane->hwindex;
 
-	/* According to the datasheet the Y position is expressed in raster line
-	 * units. However, 32bpp formats seem to require a doubled Y position
-	 * value. Similarly, for the second plane, NV12 and NV21 formats seem to
+	/* The Y position is expressed in raster line units and must be doubled
+	 * for 32bpp formats, according to the R8A7790 datasheet. No mention of
+	 * doubling the Y position is found in the R8A7779 datasheet, but the
+	 * rule seems to apply there as well.
+	 *
+	 * Similarly, for the second plane, NV12 and NV21 formats seem to
 	 * require a halved Y position value.
 	 */
-	rcar_du_plane_write(rcdu, index, PnSPXR, plane->src_x);
-	rcar_du_plane_write(rcdu, index, PnSPYR, plane->src_y *
+	rcar_du_plane_write(rgrp, index, PnSPXR, plane->src_x);
+	rcar_du_plane_write(rgrp, index, PnSPYR, plane->src_y *
 			    (plane->format->bpp == 32 ? 2 : 1));
-	rcar_du_plane_write(rcdu, index, PnDSA0R, plane->dma[0]);
+	rcar_du_plane_write(rgrp, index, PnDSA0R, plane->dma[0]);
 
 	if (plane->format->planes == 2) {
 		index = (index + 1) % 8;
 
-		rcar_du_plane_write(rcdu, index, PnSPXR, plane->src_x);
-		rcar_du_plane_write(rcdu, index, PnSPYR, plane->src_y *
+		rcar_du_plane_write(rgrp, index, PnSPXR, plane->src_x);
+		rcar_du_plane_write(rgrp, index, PnSPYR, plane->src_y *
 				    (plane->format->bpp == 16 ? 2 : 1) / 2);
-		rcar_du_plane_write(rcdu, index, PnDSA0R, plane->dma[1]);
+		rcar_du_plane_write(rgrp, index, PnDSA0R, plane->dma[1]);
 	}
 }
 
@@ -140,7 +145,7 @@ void rcar_du_plane_compute_base(struct rcar_du_plane *plane,
 static void rcar_du_plane_setup_mode(struct rcar_du_plane *plane,
 				     unsigned int index)
 {
-	struct rcar_du_device *rcdu = plane->dev;
+	struct rcar_du_group *rgrp = plane->group;
 	u32 colorkey;
 	u32 pnmr;
 
@@ -154,9 +159,9 @@ static void rcar_du_plane_setup_mode(struct rcar_du_plane *plane,
 	 * enable alpha-blending regardless of the X bit value.
 	 */
 	if (plane->format->fourcc != DRM_FORMAT_XRGB1555)
-		rcar_du_plane_write(rcdu, index, PnALPHAR, PnALPHAR_ABIT_0);
+		rcar_du_plane_write(rgrp, index, PnALPHAR, PnALPHAR_ABIT_0);
 	else
-		rcar_du_plane_write(rcdu, index, PnALPHAR,
+		rcar_du_plane_write(rgrp, index, PnALPHAR,
 				    PnALPHAR_ABIT_X | plane->alpha);
 
 	pnmr = PnMR_BM_MD | plane->format->pnmr;
@@ -172,14 +177,14 @@ static void rcar_du_plane_setup_mode(struct rcar_du_plane *plane,
 	if (plane->format->fourcc == DRM_FORMAT_YUYV)
 		pnmr |= PnMR_YCDF_YUYV;
 
-	rcar_du_plane_write(rcdu, index, PnMR, pnmr);
+	rcar_du_plane_write(rgrp, index, PnMR, pnmr);
 
 	switch (plane->format->fourcc) {
 	case DRM_FORMAT_RGB565:
 		colorkey = ((plane->colorkey & 0xf80000) >> 8)
 			 | ((plane->colorkey & 0x00fc00) >> 5)
 			 | ((plane->colorkey & 0x0000f8) >> 3);
-		rcar_du_plane_write(rcdu, index, PnTC2R, colorkey);
+		rcar_du_plane_write(rgrp, index, PnTC2R, colorkey);
 		break;
 
 	case DRM_FORMAT_ARGB1555:
@@ -187,12 +192,12 @@ static void rcar_du_plane_setup_mode(struct rcar_du_plane *plane,
 		colorkey = ((plane->colorkey & 0xf80000) >> 9)
 			 | ((plane->colorkey & 0x00f800) >> 6)
 			 | ((plane->colorkey & 0x0000f8) >> 3);
-		rcar_du_plane_write(rcdu, index, PnTC2R, colorkey);
+		rcar_du_plane_write(rgrp, index, PnTC2R, colorkey);
 		break;
 
 	case DRM_FORMAT_XRGB8888:
 	case DRM_FORMAT_ARGB8888:
-		rcar_du_plane_write(rcdu, index, PnTC3R,
+		rcar_du_plane_write(rgrp, index, PnTC3R,
 				    PnTC3R_CODE | (plane->colorkey & 0xffffff));
 		break;
 	}
@@ -201,7 +206,7 @@ static void rcar_du_plane_setup_mode(struct rcar_du_plane *plane,
 static void __rcar_du_plane_setup(struct rcar_du_plane *plane,
 				  unsigned int index)
 {
-	struct rcar_du_device *rcdu = plane->dev;
+	struct rcar_du_group *rgrp = plane->group;
 	u32 ddcr2 = PnDDCR2_CODE;
 	u32 ddcr4;
 	u32 mwr;
@@ -211,7 +216,7 @@ static void __rcar_du_plane_setup(struct rcar_du_plane *plane,
 	 * The data format is selected by the DDDF field in PnMR and the EDF
 	 * field in DDCR4.
 	 */
-	ddcr4 = rcar_du_plane_read(rcdu, index, PnDDCR4);
+	ddcr4 = rcar_du_plane_read(rgrp, index, PnDDCR4);
 	ddcr4 &= ~PnDDCR4_EDF_MASK;
 	ddcr4 |= plane->format->edf | PnDDCR4_CODE;
 
@@ -232,8 +237,8 @@ static void __rcar_du_plane_setup(struct rcar_du_plane *plane,
 		}
 	}
 
-	rcar_du_plane_write(rcdu, index, PnDDCR2, ddcr2);
-	rcar_du_plane_write(rcdu, index, PnDDCR4, ddcr4);
+	rcar_du_plane_write(rgrp, index, PnDDCR2, ddcr2);
+	rcar_du_plane_write(rgrp, index, PnDDCR4, ddcr4);
 
 	/* Memory pitch (expressed in pixels) */
 	if (plane->format->planes == 2)
@@ -241,19 +246,19 @@ static void __rcar_du_plane_setup(struct rcar_du_plane *plane,
 	else
 		mwr = plane->pitch * 8 / plane->format->bpp;
 
-	rcar_du_plane_write(rcdu, index, PnMWR, mwr);
+	rcar_du_plane_write(rgrp, index, PnMWR, mwr);
 
 	/* Destination position and size */
-	rcar_du_plane_write(rcdu, index, PnDSXR, plane->width);
-	rcar_du_plane_write(rcdu, index, PnDSYR, plane->height);
-	rcar_du_plane_write(rcdu, index, PnDPXR, plane->dst_x);
-	rcar_du_plane_write(rcdu, index, PnDPYR, plane->dst_y);
+	rcar_du_plane_write(rgrp, index, PnDSXR, plane->width);
+	rcar_du_plane_write(rgrp, index, PnDSYR, plane->height);
+	rcar_du_plane_write(rgrp, index, PnDPXR, plane->dst_x);
+	rcar_du_plane_write(rgrp, index, PnDPYR, plane->dst_y);
 
 	/* Wrap-around and blinking, disabled */
-	rcar_du_plane_write(rcdu, index, PnWASPR, 0);
-	rcar_du_plane_write(rcdu, index, PnWAMWR, 4095);
-	rcar_du_plane_write(rcdu, index, PnBTR, 0);
-	rcar_du_plane_write(rcdu, index, PnMLR, 0);
+	rcar_du_plane_write(rgrp, index, PnWASPR, 0);
+	rcar_du_plane_write(rgrp, index, PnWAMWR, 4095);
+	rcar_du_plane_write(rgrp, index, PnBTR, 0);
+	rcar_du_plane_write(rgrp, index, PnMLR, 0);
 }
 
 void rcar_du_plane_setup(struct rcar_du_plane *plane)
@@ -273,7 +278,7 @@ rcar_du_plane_update(struct drm_plane *plane, struct drm_crtc *crtc,
 		       uint32_t src_w, uint32_t src_h)
 {
 	struct rcar_du_plane *rplane = to_rcar_plane(plane);
-	struct rcar_du_device *rcdu = plane->dev->dev_private;
+	struct rcar_du_device *rcdu = rplane->group->dev;
 	const struct rcar_du_format_info *format;
 	unsigned int nplanes;
 	int ret;
@@ -316,26 +321,25 @@ rcar_du_plane_update(struct drm_plane *plane, struct drm_crtc *crtc,
 	rcar_du_plane_compute_base(rplane, fb);
 	rcar_du_plane_setup(rplane);
 
-	mutex_lock(&rcdu->planes.lock);
+	mutex_lock(&rplane->group->planes.lock);
 	rplane->enabled = true;
 	rcar_du_crtc_update_planes(rplane->crtc);
-	mutex_unlock(&rcdu->planes.lock);
+	mutex_unlock(&rplane->group->planes.lock);
 
 	return 0;
 }
 
 static int rcar_du_plane_disable(struct drm_plane *plane)
 {
-	struct rcar_du_device *rcdu = plane->dev->dev_private;
 	struct rcar_du_plane *rplane = to_rcar_plane(plane);
 
 	if (!rplane->enabled)
 		return 0;
 
-	mutex_lock(&rcdu->planes.lock);
+	mutex_lock(&rplane->group->planes.lock);
 	rplane->enabled = false;
 	rcar_du_crtc_update_planes(rplane->crtc);
-	mutex_unlock(&rcdu->planes.lock);
+	mutex_unlock(&rplane->group->planes.lock);
 
 	rcar_du_plane_release(rplane);
 
@@ -377,9 +381,7 @@ static void rcar_du_plane_set_colorkey(struct rcar_du_plane *plane,
 static void rcar_du_plane_set_zpos(struct rcar_du_plane *plane,
 				   unsigned int zpos)
 {
-	struct rcar_du_device *rcdu = plane->dev;
-
-	mutex_lock(&rcdu->planes.lock);
+	mutex_lock(&plane->group->planes.lock);
 	if (plane->zpos == zpos)
 		goto done;
 
@@ -390,21 +392,21 @@ static void rcar_du_plane_set_zpos(struct rcar_du_plane *plane,
 	rcar_du_crtc_update_planes(plane->crtc);
 
 done:
-	mutex_unlock(&rcdu->planes.lock);
+	mutex_unlock(&plane->group->planes.lock);
 }
 
 static int rcar_du_plane_set_property(struct drm_plane *plane,
 				      struct drm_property *property,
 				      uint64_t value)
 {
-	struct rcar_du_device *rcdu = plane->dev->dev_private;
 	struct rcar_du_plane *rplane = to_rcar_plane(plane);
+	struct rcar_du_group *rgrp = rplane->group;
 
-	if (property == rcdu->planes.alpha)
+	if (property == rgrp->planes.alpha)
 		rcar_du_plane_set_alpha(rplane, value);
-	else if (property == rcdu->planes.colorkey)
+	else if (property == rgrp->planes.colorkey)
 		rcar_du_plane_set_colorkey(rplane, value);
-	else if (property == rcdu->planes.zpos)
+	else if (property == rgrp->planes.zpos)
 		rcar_du_plane_set_zpos(rplane, value);
 	else
 		return -EINVAL;
@@ -432,37 +434,39 @@ static const uint32_t formats[] = {
 	DRM_FORMAT_NV16,
 };
 
-int rcar_du_plane_init(struct rcar_du_device *rcdu)
+int rcar_du_planes_init(struct rcar_du_group *rgrp)
 {
+	struct rcar_du_planes *planes = &rgrp->planes;
+	struct rcar_du_device *rcdu = rgrp->dev;
 	unsigned int i;
 
-	mutex_init(&rcdu->planes.lock);
-	rcdu->planes.free = 0xff;
+	mutex_init(&planes->lock);
+	planes->free = 0xff;
 
-	rcdu->planes.alpha =
+	planes->alpha =
 		drm_property_create_range(rcdu->ddev, 0, "alpha", 0, 255);
-	if (rcdu->planes.alpha == NULL)
+	if (planes->alpha == NULL)
 		return -ENOMEM;
 
 	/* The color key is expressed as an RGB888 triplet stored in a 32-bit
 	 * integer in XRGB8888 format. Bit 24 is used as a flag to disable (0)
 	 * or enable source color keying (1).
 	 */
-	rcdu->planes.colorkey =
+	planes->colorkey =
 		drm_property_create_range(rcdu->ddev, 0, "colorkey",
 					  0, 0x01ffffff);
-	if (rcdu->planes.colorkey == NULL)
+	if (planes->colorkey == NULL)
 		return -ENOMEM;
 
-	rcdu->planes.zpos =
+	planes->zpos =
 		drm_property_create_range(rcdu->ddev, 0, "zpos", 1, 7);
-	if (rcdu->planes.zpos == NULL)
+	if (planes->zpos == NULL)
 		return -ENOMEM;
 
-	for (i = 0; i < ARRAY_SIZE(rcdu->planes.planes); ++i) {
-		struct rcar_du_plane *plane = &rcdu->planes.planes[i];
+	for (i = 0; i < ARRAY_SIZE(planes->planes); ++i) {
+		struct rcar_du_plane *plane = &planes->planes[i];
 
-		plane->dev = rcdu;
+		plane->group = rgrp;
 		plane->hwindex = -1;
 		plane->alpha = 255;
 		plane->colorkey = RCAR_DU_COLORKEY_NONE;
@@ -472,11 +476,16 @@ int rcar_du_plane_init(struct rcar_du_device *rcdu)
 	return 0;
 }
 
-int rcar_du_plane_register(struct rcar_du_device *rcdu)
+int rcar_du_planes_register(struct rcar_du_group *rgrp)
 {
+	struct rcar_du_planes *planes = &rgrp->planes;
+	struct rcar_du_device *rcdu = rgrp->dev;
+	unsigned int crtcs;
 	unsigned int i;
 	int ret;
 
+	crtcs = ((1 << rcdu->num_crtcs) - 1) & (3 << (2 * rgrp->index));
+
 	for (i = 0; i < RCAR_DU_NUM_KMS_PLANES; ++i) {
 		struct rcar_du_kms_plane *plane;
 
@@ -484,23 +493,22 @@ int rcar_du_plane_register(struct rcar_du_device *rcdu)
 		if (plane == NULL)
 			return -ENOMEM;
 
-		plane->hwplane = &rcdu->planes.planes[i + 2];
+		plane->hwplane = &planes->planes[i + 2];
 		plane->hwplane->zpos = 1;
 
-		ret = drm_plane_init(rcdu->ddev, &plane->plane,
-				     (1 << rcdu->num_crtcs) - 1,
+		ret = drm_plane_init(rcdu->ddev, &plane->plane, crtcs,
 				     &rcar_du_plane_funcs, formats,
 				     ARRAY_SIZE(formats), false);
 		if (ret < 0)
 			return ret;
 
 		drm_object_attach_property(&plane->plane.base,
-					   rcdu->planes.alpha, 255);
+					   planes->alpha, 255);
 		drm_object_attach_property(&plane->plane.base,
-					   rcdu->planes.colorkey,
+					   planes->colorkey,
 					   RCAR_DU_COLORKEY_NONE);
 		drm_object_attach_property(&plane->plane.base,
-					   rcdu->planes.zpos, 1);
+					   planes->zpos, 1);
 	}
 
 	return 0;
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_plane.h b/drivers/gpu/drm/rcar-du/rcar_du_plane.h
index 5397dba2fe57..f94f9ce84998 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_plane.h
+++ b/drivers/gpu/drm/rcar-du/rcar_du_plane.h
@@ -14,10 +14,13 @@
 #ifndef __RCAR_DU_PLANE_H__
 #define __RCAR_DU_PLANE_H__
 
-struct drm_crtc;
-struct drm_framebuffer;
-struct rcar_du_device;
+#include <linux/mutex.h>
+
+#include <drm/drmP.h>
+#include <drm/drm_crtc.h>
+
 struct rcar_du_format_info;
+struct rcar_du_group;
 
 /* The RCAR DU has 8 hardware planes, shared between KMS planes and CRTCs. As
  * using KMS planes requires at least one of the CRTCs being enabled, no more
@@ -30,7 +33,7 @@ struct rcar_du_format_info;
 #define RCAR_DU_NUM_SW_PLANES		9
 
 struct rcar_du_plane {
-	struct rcar_du_device *dev;
+	struct rcar_du_group *group;
 	struct drm_crtc *crtc;
 
 	bool enabled;
@@ -54,8 +57,19 @@ struct rcar_du_plane {
 	unsigned int dst_y;
 };
 
-int rcar_du_plane_init(struct rcar_du_device *rcdu);
-int rcar_du_plane_register(struct rcar_du_device *rcdu);
+struct rcar_du_planes {
+	struct rcar_du_plane planes[RCAR_DU_NUM_SW_PLANES];
+	unsigned int free;
+	struct mutex lock;
+
+	struct drm_property *alpha;
+	struct drm_property *colorkey;
+	struct drm_property *zpos;
+};
+
+int rcar_du_planes_init(struct rcar_du_group *rgrp);
+int rcar_du_planes_register(struct rcar_du_group *rgrp);
+
 void rcar_du_plane_setup(struct rcar_du_plane *plane);
 void rcar_du_plane_update_base(struct rcar_du_plane *plane);
 void rcar_du_plane_compute_base(struct rcar_du_plane *plane,
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_regs.h b/drivers/gpu/drm/rcar-du/rcar_du_regs.h
index 69f21f19b51c..73f7347f740b 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_regs.h
+++ b/drivers/gpu/drm/rcar-du/rcar_du_regs.h
@@ -13,14 +13,15 @@
 #ifndef __RCAR_DU_REGS_H__
 #define __RCAR_DU_REGS_H__
 
-#define DISP2_REG_OFFSET	 0x30000
+#define DU0_REG_OFFSET		0x00000
+#define DU1_REG_OFFSET		0x30000
+#define DU2_REG_OFFSET		0x40000
 
 /* -----------------------------------------------------------------------------
  * Display Control Registers
  */
 
 #define DSYSR			0x00000	/* display 1 */
-#define D2SYSR			0x30000	/* display 2 */
 #define DSYSR_ILTS		(1 << 29)
 #define DSYSR_DSEC		(1 << 20)
 #define DSYSR_IUPD		(1 << 16)
@@ -35,7 +36,6 @@
 #define DSYSR_SCM_INT_VIDEO	(3 << 4)
 
 #define DSMR			0x00004
-#define D2SMR			0x30004
 #define DSMR_VSPM		(1 << 28)
 #define DSMR_ODPM		(1 << 27)
 #define DSMR_DIPM_DISP		(0 << 25)
@@ -60,7 +60,6 @@
 #define DSMR_CSY_MASK		(3 << 6)
 
 #define DSSR			0x00008
-#define D2SSR			0x30008
 #define DSSR_VC1FB_DSA0		(0 << 30)
 #define DSSR_VC1FB_DSA1		(1 << 30)
 #define DSSR_VC1FB_DSA2		(2 << 30)
@@ -80,7 +79,6 @@
 #define DSSR_ADC(n)		(1 << ((n)-1))
 
 #define DSRCR			0x0000c
-#define D2SRCR			0x3000c
 #define DSRCR_TVCL		(1 << 15)
 #define DSRCR_FRCL		(1 << 14)
 #define DSRCR_VBCL		(1 << 11)
@@ -90,7 +88,6 @@
 #define DSRCR_MASK		0x0000cbff
 
 #define DIER			0x00010
-#define D2IER			0x30010
 #define DIER_TVE		(1 << 15)
 #define DIER_FRE		(1 << 14)
 #define DIER_VBE		(1 << 11)
@@ -114,7 +111,6 @@
 #define DPPR_BPP32		(DPPR_BPP32_P1 | DPPR_BPP32_P2)	/* plane1 & 2 */
 
 #define DEFR			0x00020
-#define D2EFR			0x30020
 #define DEFR_CODE		(0x7773 << 16)
 #define DEFR_EXSL		(1 << 12)
 #define DEFR_EXVL		(1 << 11)
@@ -137,12 +133,10 @@
 #define DCPCR_DCE		(1 << 0)
 
 #define DEFR2			0x00034
-#define D2EFR2			0x30034
 #define DEFR2_CODE		(0x7775 << 16)
 #define DEFR2_DEFE2G		(1 << 0)
 
 #define DEFR3			0x00038
-#define D2EFR3			0x30038
 #define DEFR3_CODE		(0x7776 << 16)
 #define DEFR3_EVDA		(1 << 14)
 #define DEFR3_EVDM_1		(1 << 12)
@@ -153,7 +147,6 @@
 #define DEFR3_DEFE3		(1 << 0)
 
 #define DEFR4			0x0003c
-#define D2EFR4			0x3003c
 #define DEFR4_CODE		(0x7777 << 16)
 #define DEFR4_LRUO		(1 << 5)
 #define DEFR4_SPCE		(1 << 4)
@@ -205,6 +198,68 @@
 #define DEFR6_DEFAULT		(DEFR6_CODE | DEFR6_TCNE2)
 
 /* -----------------------------------------------------------------------------
+ * R8A7790-only Control Registers
+ */
+
+#define DD1SSR			0x20008
+#define DD1SSR_TVR		(1 << 15)
+#define DD1SSR_FRM		(1 << 14)
+#define DD1SSR_BUF		(1 << 12)
+#define DD1SSR_VBK		(1 << 11)
+#define DD1SSR_RINT		(1 << 9)
+#define DD1SSR_HBK		(1 << 8)
+#define DD1SSR_ADC(n)		(1 << ((n)-1))
+
+#define DD1SRCR			0x2000c
+#define DD1SRCR_TVR		(1 << 15)
+#define DD1SRCR_FRM		(1 << 14)
+#define DD1SRCR_BUF		(1 << 12)
+#define DD1SRCR_VBK		(1 << 11)
+#define DD1SRCR_RINT		(1 << 9)
+#define DD1SRCR_HBK		(1 << 8)
+#define DD1SRCR_ADC(n)		(1 << ((n)-1))
+
+#define DD1IER			0x20010
+#define DD1IER_TVR		(1 << 15)
+#define DD1IER_FRM		(1 << 14)
+#define DD1IER_BUF		(1 << 12)
+#define DD1IER_VBK		(1 << 11)
+#define DD1IER_RINT		(1 << 9)
+#define DD1IER_HBK		(1 << 8)
+#define DD1IER_ADC(n)		(1 << ((n)-1))
+
+#define DEFR8			0x20020
+#define DEFR8_CODE		(0x7790 << 16)
+#define DEFR8_VSCS		(1 << 6)
+#define DEFR8_DRGBS_DU(n)	((n) << 4)
+#define DEFR8_DRGBS_MASK	(3 << 4)
+#define DEFR8_DEFE8		(1 << 0)
+
+#define DOFLR			0x20024
+#define DOFLR_CODE		(0x7790 << 16)
+#define DOFLR_HSYCFL1		(1 << 13)
+#define DOFLR_VSYCFL1		(1 << 12)
+#define DOFLR_ODDFL1		(1 << 11)
+#define DOFLR_DISPFL1		(1 << 10)
+#define DOFLR_CDEFL1		(1 << 9)
+#define DOFLR_RGBFL1		(1 << 8)
+#define DOFLR_HSYCFL0		(1 << 5)
+#define DOFLR_VSYCFL0		(1 << 4)
+#define DOFLR_ODDFL0		(1 << 3)
+#define DOFLR_DISPFL0		(1 << 2)
+#define DOFLR_CDEFL0		(1 << 1)
+#define DOFLR_RGBFL0		(1 << 0)
+
+#define DIDSR			0x20028
+#define DIDSR_CODE		(0x7790 << 16)
+#define DIDSR_LCDS_DCLKIN(n)	(0 << (8 + (n) * 2))
+#define DIDSR_LCDS_LVDS0(n)	(2 << (8 + (n) * 2))
+#define DIDSR_LCDS_LVDS1(n)	(3 << (8 + (n) * 2))
+#define DIDSR_LCDS_MASK(n)	(3 << (8 + (n) * 2))
+#define DIDSR_PCDS_CLK(n, clk)	(clk << ((n) * 2))
+#define DIDSR_PCDS_MASK(n)	(3 << ((n) * 2))
+
+/* -----------------------------------------------------------------------------
  * Display Timing Generation Registers
  */
 
@@ -349,21 +404,34 @@
 #define APnMR_BM_AD		(2 << 4)	/* Auto Display Change Mode */
 
 #define APnMWR			0x0a104
+
+#define APnDSXR			0x0a110
+#define APnDSYR			0x0a114
+#define APnDPXR			0x0a118
+#define APnDPYR			0x0a11c
+
 #define APnDSA0R		0x0a120
 #define APnDSA1R		0x0a124
 #define APnDSA2R		0x0a128
+
+#define APnSPXR			0x0a130
+#define APnSPYR			0x0a134
+#define APnWASPR		0x0a138
+#define APnWAMWR		0x0a13c
+
+#define APnBTR			0x0a140
+
 #define APnMLR			0x0a150
+#define APnSWAPR		0x0a180
 
 /* -----------------------------------------------------------------------------
  * Display Capture Registers
  */
 
+#define DCMR			0x0c100
 #define DCMWR			0x0c104
-#define DC2MWR			0x0c204
 #define DCSAR			0x0c120
-#define DC2SAR			0x0c220
 #define DCMLR			0x0c150
-#define DC2MLR			0x0c250
 
 /* -----------------------------------------------------------------------------
  * Color Palette Registers
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_vga.c b/drivers/gpu/drm/rcar-du/rcar_du_vgacon.c
index 327289ec380d..41d563adfeaa 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_vga.c
+++ b/drivers/gpu/drm/rcar-du/rcar_du_vgacon.c
@@ -1,5 +1,5 @@
 /*
- * rcar_du_vga.c  --  R-Car Display Unit VGA DAC and Connector
+ * rcar_du_vgacon.c  --  R-Car Display Unit VGA Connector
  *
  * Copyright (C) 2013 Renesas Corporation
  *
@@ -16,12 +16,9 @@
 #include <drm/drm_crtc_helper.h>
 
 #include "rcar_du_drv.h"
+#include "rcar_du_encoder.h"
 #include "rcar_du_kms.h"
-#include "rcar_du_vga.h"
-
-/* -----------------------------------------------------------------------------
- * Connector
- */
+#include "rcar_du_vgacon.h"
 
 static int rcar_du_vga_connector_get_modes(struct drm_connector *connector)
 {
@@ -49,7 +46,7 @@ static void rcar_du_vga_connector_destroy(struct drm_connector *connector)
 static enum drm_connector_status
 rcar_du_vga_connector_detect(struct drm_connector *connector, bool force)
 {
-	return connector_status_unknown;
+	return connector_status_connected;
 }
 
 static const struct drm_connector_funcs connector_funcs = {
@@ -59,8 +56,8 @@ static const struct drm_connector_funcs connector_funcs = {
 	.destroy = rcar_du_vga_connector_destroy,
 };
 
-static int rcar_du_vga_connector_init(struct rcar_du_device *rcdu,
-				      struct rcar_du_encoder *renc)
+int rcar_du_vga_connector_init(struct rcar_du_device *rcdu,
+			       struct rcar_du_encoder *renc)
 {
 	struct rcar_du_connector *rcon;
 	struct drm_connector *connector;
@@ -97,53 +94,3 @@ static int rcar_du_vga_connector_init(struct rcar_du_device *rcdu,
 
 	return 0;
 }
-
-/* -----------------------------------------------------------------------------
- * Encoder
- */
-
-static void rcar_du_vga_encoder_dpms(struct drm_encoder *encoder, int mode)
-{
-}
-
-static bool rcar_du_vga_encoder_mode_fixup(struct drm_encoder *encoder,
-					   const struct drm_display_mode *mode,
-					   struct drm_display_mode *adjusted_mode)
-{
-	return true;
-}
-
-static const struct drm_encoder_helper_funcs encoder_helper_funcs = {
-	.dpms = rcar_du_vga_encoder_dpms,
-	.mode_fixup = rcar_du_vga_encoder_mode_fixup,
-	.prepare = rcar_du_encoder_mode_prepare,
-	.commit = rcar_du_encoder_mode_commit,
-	.mode_set = rcar_du_encoder_mode_set,
-};
-
-static const struct drm_encoder_funcs encoder_funcs = {
-	.destroy = drm_encoder_cleanup,
-};
-
-int rcar_du_vga_init(struct rcar_du_device *rcdu,
-		     const struct rcar_du_encoder_vga_data *data,
-		     unsigned int output)
-{
-	struct rcar_du_encoder *renc;
-	int ret;
-
-	renc = devm_kzalloc(rcdu->dev, sizeof(*renc), GFP_KERNEL);
-	if (renc == NULL)
-		return -ENOMEM;
-
-	renc->output = output;
-
-	ret = drm_encoder_init(rcdu->ddev, &renc->encoder, &encoder_funcs,
-			       DRM_MODE_ENCODER_DAC);
-	if (ret < 0)
-		return ret;
-
-	drm_encoder_helper_add(&renc->encoder, &encoder_helper_funcs);
-
-	return rcar_du_vga_connector_init(rcdu, renc);
-}
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_vga.h b/drivers/gpu/drm/rcar-du/rcar_du_vgacon.h
index 66b4d2d7190d..b12b0cf7f117 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_vga.h
+++ b/drivers/gpu/drm/rcar-du/rcar_du_vgacon.h
@@ -1,5 +1,5 @@
 /*
- * rcar_du_vga.h  --  R-Car Display Unit VGA DAC and Connector
+ * rcar_du_vgacon.h  --  R-Car Display Unit VGA Connector
  *
  * Copyright (C) 2013 Renesas Corporation
  *
@@ -11,14 +11,13 @@
  * (at your option) any later version.
  */
 
-#ifndef __RCAR_DU_VGA_H__
-#define __RCAR_DU_VGA_H__
+#ifndef __RCAR_DU_VGACON_H__
+#define __RCAR_DU_VGACON_H__
 
 struct rcar_du_device;
-struct rcar_du_encoder_vga_data;
+struct rcar_du_encoder;
 
-int rcar_du_vga_init(struct rcar_du_device *rcdu,
-		     const struct rcar_du_encoder_vga_data *data,
-		     unsigned int output);
+int rcar_du_vga_connector_init(struct rcar_du_device *rcdu,
+			       struct rcar_du_encoder *renc);
 
-#endif /* __RCAR_DU_VGA_H__ */
+#endif /* __RCAR_DU_VGACON_H__ */
diff --git a/drivers/gpu/drm/rcar-du/rcar_lvds_regs.h b/drivers/gpu/drm/rcar-du/rcar_lvds_regs.h
new file mode 100644
index 000000000000..77cf9289ab65
--- /dev/null
+++ b/drivers/gpu/drm/rcar-du/rcar_lvds_regs.h
@@ -0,0 +1,69 @@
+/*
+ * rcar_lvds_regs.h  --  R-Car LVDS Interface Registers Definitions
+ *
+ * Copyright (C) 2013 Renesas Electronics Corporation
+ *
+ * Contact: Laurent Pinchart (laurent.pinchart@ideasonboard.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation.
+ */
+
+#ifndef __RCAR_LVDS_REGS_H__
+#define __RCAR_LVDS_REGS_H__
+
+#define LVDCR0				0x0000
+#define LVDCR0_DUSEL			(1 << 15)
+#define LVDCR0_DMD			(1 << 12)
+#define LVDCR0_LVMD_MASK		(0xf << 8)
+#define LVDCR0_LVMD_SHIFT		8
+#define LVDCR0_PLLEN			(1 << 4)
+#define LVDCR0_BEN			(1 << 2)
+#define LVDCR0_LVEN			(1 << 1)
+#define LVDCR0_LVRES			(1 << 0)
+
+#define LVDCR1				0x0004
+#define LVDCR1_CKSEL			(1 << 15)
+#define LVDCR1_CHSTBY(n)		(3 << (2 + (n) * 2))
+#define LVDCR1_CLKSTBY			(3 << 0)
+
+#define LVDPLLCR			0x0008
+#define LVDPLLCR_CEEN			(1 << 14)
+#define LVDPLLCR_FBEN			(1 << 13)
+#define LVDPLLCR_COSEL			(1 << 12)
+#define LVDPLLCR_PLLDLYCNT_150M		(0x1bf << 0)
+#define LVDPLLCR_PLLDLYCNT_121M		(0x22c << 0)
+#define LVDPLLCR_PLLDLYCNT_60M		(0x77b << 0)
+#define LVDPLLCR_PLLDLYCNT_38M		(0x69a << 0)
+#define LVDPLLCR_PLLDLYCNT_MASK		(0x7ff << 0)
+
+#define LVDCTRCR			0x000c
+#define LVDCTRCR_CTR3SEL_ZERO		(0 << 12)
+#define LVDCTRCR_CTR3SEL_ODD		(1 << 12)
+#define LVDCTRCR_CTR3SEL_CDE		(2 << 12)
+#define LVDCTRCR_CTR3SEL_MASK		(7 << 12)
+#define LVDCTRCR_CTR2SEL_DISP		(0 << 8)
+#define LVDCTRCR_CTR2SEL_ODD		(1 << 8)
+#define LVDCTRCR_CTR2SEL_CDE		(2 << 8)
+#define LVDCTRCR_CTR2SEL_HSYNC		(3 << 8)
+#define LVDCTRCR_CTR2SEL_VSYNC		(4 << 8)
+#define LVDCTRCR_CTR2SEL_MASK		(7 << 8)
+#define LVDCTRCR_CTR1SEL_VSYNC		(0 << 4)
+#define LVDCTRCR_CTR1SEL_DISP		(1 << 4)
+#define LVDCTRCR_CTR1SEL_ODD		(2 << 4)
+#define LVDCTRCR_CTR1SEL_CDE		(3 << 4)
+#define LVDCTRCR_CTR1SEL_HSYNC		(4 << 4)
+#define LVDCTRCR_CTR1SEL_MASK		(7 << 4)
+#define LVDCTRCR_CTR0SEL_HSYNC		(0 << 0)
+#define LVDCTRCR_CTR0SEL_VSYNC		(1 << 0)
+#define LVDCTRCR_CTR0SEL_DISP		(2 << 0)
+#define LVDCTRCR_CTR0SEL_ODD		(3 << 0)
+#define LVDCTRCR_CTR0SEL_CDE		(4 << 0)
+#define LVDCTRCR_CTR0SEL_MASK		(7 << 0)
+
+#define LVDCHCR				0x0010
+#define LVDCHCR_CHSEL_CH(n, c)		((((c) - (n)) & 3) << ((n) * 4))
+#define LVDCHCR_CHSEL_MASK(n)		(3 << ((n) * 4))
+
+#endif /* __RCAR_LVDS_REGS_H__ */
diff --git a/drivers/gpu/drm/savage/savage_bci.c b/drivers/gpu/drm/savage/savage_bci.c
index bd6b2cf508d5..b17d0710871a 100644
--- a/drivers/gpu/drm/savage/savage_bci.c
+++ b/drivers/gpu/drm/savage/savage_bci.c
@@ -1072,7 +1072,7 @@ void savage_reclaim_buffers(struct drm_device *dev, struct drm_file *file_priv)
 		drm_idlelock_release(&file_priv->master->lock);
 }
 
-struct drm_ioctl_desc savage_ioctls[] = {
+const struct drm_ioctl_desc savage_ioctls[] = {
 	DRM_IOCTL_DEF_DRV(SAVAGE_BCI_INIT, savage_bci_init, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
 	DRM_IOCTL_DEF_DRV(SAVAGE_BCI_CMDBUF, savage_bci_cmdbuf, DRM_AUTH),
 	DRM_IOCTL_DEF_DRV(SAVAGE_BCI_EVENT_EMIT, savage_bci_event_emit, DRM_AUTH),
diff --git a/drivers/gpu/drm/savage/savage_drv.c b/drivers/gpu/drm/savage/savage_drv.c
index 71b2081e7835..3c030216e888 100644
--- a/drivers/gpu/drm/savage/savage_drv.c
+++ b/drivers/gpu/drm/savage/savage_drv.c
@@ -42,7 +42,6 @@ static const struct file_operations savage_driver_fops = {
 	.unlocked_ioctl = drm_ioctl,
 	.mmap = drm_mmap,
 	.poll = drm_poll,
-	.fasync = drm_fasync,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl = drm_compat_ioctl,
 #endif
@@ -51,7 +50,7 @@ static const struct file_operations savage_driver_fops = {
 
 static struct drm_driver driver = {
 	.driver_features =
-	    DRIVER_USE_AGP | DRIVER_USE_MTRR | DRIVER_HAVE_DMA | DRIVER_PCI_DMA,
+	    DRIVER_USE_AGP | DRIVER_HAVE_DMA | DRIVER_PCI_DMA,
 	.dev_priv_size = sizeof(drm_savage_buf_priv_t),
 	.load = savage_driver_load,
 	.firstopen = savage_driver_firstopen,
diff --git a/drivers/gpu/drm/savage/savage_drv.h b/drivers/gpu/drm/savage/savage_drv.h
index c05082a59f6f..335f8fcf1041 100644
--- a/drivers/gpu/drm/savage/savage_drv.h
+++ b/drivers/gpu/drm/savage/savage_drv.h
@@ -104,7 +104,7 @@ enum savage_family {
 	S3_LAST
 };
 
-extern struct drm_ioctl_desc savage_ioctls[];
+extern const struct drm_ioctl_desc savage_ioctls[];
 extern int savage_max_ioctl;
 
 #define S3_SAVAGE3D_SERIES(chip)  ((chip>=S3_SAVAGE3D) && (chip<=S3_SAVAGE_MX))
diff --git a/drivers/gpu/drm/shmobile/shmob_drm_crtc.c b/drivers/gpu/drm/shmobile/shmob_drm_crtc.c
index 99e2034e49cc..54bad98e9477 100644
--- a/drivers/gpu/drm/shmobile/shmob_drm_crtc.c
+++ b/drivers/gpu/drm/shmobile/shmob_drm_crtc.c
@@ -465,7 +465,8 @@ void shmob_drm_crtc_finish_page_flip(struct shmob_drm_crtc *scrtc)
 
 static int shmob_drm_crtc_page_flip(struct drm_crtc *crtc,
 				    struct drm_framebuffer *fb,
-				    struct drm_pending_vblank_event *event)
+				    struct drm_pending_vblank_event *event,
+				    uint32_t page_flip_flags)
 {
 	struct shmob_drm_crtc *scrtc = to_shmob_crtc(crtc);
 	struct drm_device *dev = scrtc->crtc.dev;
diff --git a/drivers/gpu/drm/shmobile/shmob_drm_drv.c b/drivers/gpu/drm/shmobile/shmob_drm_drv.c
index 5f83f9a3ef59..015551866b4a 100644
--- a/drivers/gpu/drm/shmobile/shmob_drm_drv.c
+++ b/drivers/gpu/drm/shmobile/shmob_drm_drv.c
@@ -257,7 +257,6 @@ static const struct file_operations shmob_drm_fops = {
 #endif
 	.poll		= drm_poll,
 	.read		= drm_read,
-	.fasync		= drm_fasync,
 	.llseek		= no_llseek,
 	.mmap		= drm_gem_cma_mmap,
 };
@@ -285,7 +284,7 @@ static struct drm_driver shmob_drm_driver = {
 	.gem_prime_mmap		= drm_gem_cma_prime_mmap,
 	.dumb_create		= drm_gem_cma_dumb_create,
 	.dumb_map_offset	= drm_gem_cma_dumb_map_offset,
-	.dumb_destroy		= drm_gem_cma_dumb_destroy,
+	.dumb_destroy		= drm_gem_dumb_destroy,
 	.fops			= &shmob_drm_fops,
 	.name			= "shmob-drm",
 	.desc			= "Renesas SH Mobile DRM",
diff --git a/drivers/gpu/drm/sis/sis_drv.c b/drivers/gpu/drm/sis/sis_drv.c
index 5a5325e6b759..4383b74a3aa4 100644
--- a/drivers/gpu/drm/sis/sis_drv.c
+++ b/drivers/gpu/drm/sis/sis_drv.c
@@ -72,7 +72,6 @@ static const struct file_operations sis_driver_fops = {
 	.unlocked_ioctl = drm_ioctl,
 	.mmap = drm_mmap,
 	.poll = drm_poll,
-	.fasync = drm_fasync,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl = drm_compat_ioctl,
 #endif
@@ -103,7 +102,7 @@ void sis_driver_postclose(struct drm_device *dev, struct drm_file *file)
 }
 
 static struct drm_driver driver = {
-	.driver_features = DRIVER_USE_AGP | DRIVER_USE_MTRR,
+	.driver_features = DRIVER_USE_AGP,
 	.load = sis_driver_load,
 	.unload = sis_driver_unload,
 	.open = sis_driver_open,
diff --git a/drivers/gpu/drm/sis/sis_drv.h b/drivers/gpu/drm/sis/sis_drv.h
index 13b527bb83be..c31c0253054d 100644
--- a/drivers/gpu/drm/sis/sis_drv.h
+++ b/drivers/gpu/drm/sis/sis_drv.h
@@ -70,7 +70,7 @@ extern void sis_reclaim_buffers_locked(struct drm_device *dev,
 				       struct drm_file *file_priv);
 extern void sis_lastclose(struct drm_device *dev);
 
-extern struct drm_ioctl_desc sis_ioctls[];
+extern const struct drm_ioctl_desc sis_ioctls[];
 extern int sis_max_ioctl;
 
 #endif
diff --git a/drivers/gpu/drm/sis/sis_mm.c b/drivers/gpu/drm/sis/sis_mm.c
index 9a43d98e5003..01857d836350 100644
--- a/drivers/gpu/drm/sis/sis_mm.c
+++ b/drivers/gpu/drm/sis/sis_mm.c
@@ -109,7 +109,8 @@ static int sis_drm_alloc(struct drm_device *dev, struct drm_file *file,
 	if (pool == AGP_TYPE) {
 		retval = drm_mm_insert_node(&dev_priv->agp_mm,
 					    &item->mm_node,
-					    mem->size, 0);
+					    mem->size, 0,
+					    DRM_MM_SEARCH_DEFAULT);
 		offset = item->mm_node.start;
 	} else {
 #if defined(CONFIG_FB_SIS) || defined(CONFIG_FB_SIS_MODULE)
@@ -121,7 +122,8 @@ static int sis_drm_alloc(struct drm_device *dev, struct drm_file *file,
 #else
 		retval = drm_mm_insert_node(&dev_priv->vram_mm,
 					    &item->mm_node,
-					    mem->size, 0);
+					    mem->size, 0,
+					    DRM_MM_SEARCH_DEFAULT);
 		offset = item->mm_node.start;
 #endif
 	}
@@ -348,7 +350,7 @@ void sis_reclaim_buffers_locked(struct drm_device *dev,
 	return;
 }
 
-struct drm_ioctl_desc sis_ioctls[] = {
+const struct drm_ioctl_desc sis_ioctls[] = {
 	DRM_IOCTL_DEF_DRV(SIS_FB_ALLOC, sis_fb_alloc, DRM_AUTH),
 	DRM_IOCTL_DEF_DRV(SIS_FB_FREE, sis_drm_free, DRM_AUTH),
 	DRM_IOCTL_DEF_DRV(SIS_AGP_INIT, sis_ioctl_agp_init, DRM_AUTH | DRM_MASTER | DRM_ROOT_ONLY),
diff --git a/drivers/gpu/drm/tdfx/tdfx_drv.c b/drivers/gpu/drm/tdfx/tdfx_drv.c
index ddfa743459d0..3492ca5c46d3 100644
--- a/drivers/gpu/drm/tdfx/tdfx_drv.c
+++ b/drivers/gpu/drm/tdfx/tdfx_drv.c
@@ -48,7 +48,6 @@ static const struct file_operations tdfx_driver_fops = {
 	.unlocked_ioctl = drm_ioctl,
 	.mmap = drm_mmap,
 	.poll = drm_poll,
-	.fasync = drm_fasync,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl = drm_compat_ioctl,
 #endif
@@ -56,7 +55,6 @@ static const struct file_operations tdfx_driver_fops = {
 };
 
 static struct drm_driver driver = {
-	.driver_features = DRIVER_USE_MTRR,
 	.fops = &tdfx_driver_fops,
 	.name = DRIVER_NAME,
 	.desc = DRIVER_DESC,
diff --git a/drivers/gpu/drm/tilcdc/tilcdc_crtc.c b/drivers/gpu/drm/tilcdc/tilcdc_crtc.c
index 7418dcd986d3..d36efc13b16f 100644
--- a/drivers/gpu/drm/tilcdc/tilcdc_crtc.c
+++ b/drivers/gpu/drm/tilcdc/tilcdc_crtc.c
@@ -15,7 +15,7 @@
  * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
-#include <linux/kfifo.h>
+#include "drm_flip_work.h"
 
 #include "tilcdc_drv.h"
 #include "tilcdc_regs.h"
@@ -35,21 +35,18 @@ struct tilcdc_crtc {
 	struct drm_framebuffer *scanout[2];
 
 	/* for deferred fb unref's: */
-	DECLARE_KFIFO_PTR(unref_fifo, struct drm_framebuffer *);
-	struct work_struct work;
+	struct drm_flip_work unref_work;
 };
 #define to_tilcdc_crtc(x) container_of(x, struct tilcdc_crtc, base)
 
-static void unref_worker(struct work_struct *work)
+static void unref_worker(struct drm_flip_work *work, void *val)
 {
 	struct tilcdc_crtc *tilcdc_crtc =
-		container_of(work, struct tilcdc_crtc, work);
+		container_of(work, struct tilcdc_crtc, unref_work);
 	struct drm_device *dev = tilcdc_crtc->base.dev;
-	struct drm_framebuffer *fb;
 
 	mutex_lock(&dev->mode_config.mutex);
-	while (kfifo_get(&tilcdc_crtc->unref_fifo, &fb))
-		drm_framebuffer_unreference(fb);
+	drm_framebuffer_unreference(val);
 	mutex_unlock(&dev->mode_config.mutex);
 }
 
@@ -68,19 +65,14 @@ static void set_scanout(struct drm_crtc *crtc, int n)
 	};
 	struct tilcdc_crtc *tilcdc_crtc = to_tilcdc_crtc(crtc);
 	struct drm_device *dev = crtc->dev;
+	struct tilcdc_drm_private *priv = dev->dev_private;
 
 	pm_runtime_get_sync(dev->dev);
 	tilcdc_write(dev, base_reg[n], tilcdc_crtc->start);
 	tilcdc_write(dev, ceil_reg[n], tilcdc_crtc->end);
 	if (tilcdc_crtc->scanout[n]) {
-		if (kfifo_put(&tilcdc_crtc->unref_fifo,
-				(const struct drm_framebuffer **)&tilcdc_crtc->scanout[n])) {
-			struct tilcdc_drm_private *priv = dev->dev_private;
-			queue_work(priv->wq, &tilcdc_crtc->work);
-		} else {
-			dev_err(dev->dev, "unref fifo full!\n");
-			drm_framebuffer_unreference(tilcdc_crtc->scanout[n]);
-		}
+		drm_flip_work_queue(&tilcdc_crtc->unref_work, tilcdc_crtc->scanout[n]);
+		drm_flip_work_commit(&tilcdc_crtc->unref_work, priv->wq);
 	}
 	tilcdc_crtc->scanout[n] = crtc->fb;
 	drm_framebuffer_reference(tilcdc_crtc->scanout[n]);
@@ -149,14 +141,15 @@ static void tilcdc_crtc_destroy(struct drm_crtc *crtc)
 	WARN_ON(tilcdc_crtc->dpms == DRM_MODE_DPMS_ON);
 
 	drm_crtc_cleanup(crtc);
-	WARN_ON(!kfifo_is_empty(&tilcdc_crtc->unref_fifo));
-	kfifo_free(&tilcdc_crtc->unref_fifo);
+	drm_flip_work_cleanup(&tilcdc_crtc->unref_work);
+
 	kfree(tilcdc_crtc);
 }
 
 static int tilcdc_crtc_page_flip(struct drm_crtc *crtc,
 		struct drm_framebuffer *fb,
-		struct drm_pending_vblank_event *event)
+		struct drm_pending_vblank_event *event,
+		uint32_t page_flip_flags)
 {
 	struct tilcdc_crtc *tilcdc_crtc = to_tilcdc_crtc(crtc);
 	struct drm_device *dev = crtc->dev;
@@ -379,7 +372,12 @@ static int tilcdc_crtc_mode_set(struct drm_crtc *crtc,
 	else
 		tilcdc_clear(dev, LCDC_RASTER_TIMING_2_REG, LCDC_SYNC_EDGE);
 
-	if (mode->flags & DRM_MODE_FLAG_NHSYNC)
+	/*
+	 * use value from adjusted_mode here as this might have been
+	 * changed as part of the fixup for slave encoders to solve the
+	 * issue where tilcdc timings are not VESA compliant
+	 */
+	if (adjusted_mode->flags & DRM_MODE_FLAG_NHSYNC)
 		tilcdc_set(dev, LCDC_RASTER_TIMING_2_REG, LCDC_INVERT_HSYNC);
 	else
 		tilcdc_clear(dev, LCDC_RASTER_TIMING_2_REG, LCDC_INVERT_HSYNC);
@@ -666,14 +664,13 @@ struct drm_crtc *tilcdc_crtc_create(struct drm_device *dev)
 	tilcdc_crtc->dpms = DRM_MODE_DPMS_OFF;
 	init_waitqueue_head(&tilcdc_crtc->frame_done_wq);
 
-	ret = kfifo_alloc(&tilcdc_crtc->unref_fifo, 16, GFP_KERNEL);
+	ret = drm_flip_work_init(&tilcdc_crtc->unref_work, 16,
+			"unref", unref_worker);
 	if (ret) {
 		dev_err(dev->dev, "could not allocate unref FIFO\n");
 		goto fail;
 	}
 
-	INIT_WORK(&tilcdc_crtc->work, unref_worker);
-
 	ret = drm_crtc_init(dev, crtc, &tilcdc_crtc_funcs);
 	if (ret < 0)
 		goto fail;
diff --git a/drivers/gpu/drm/tilcdc/tilcdc_drv.c b/drivers/gpu/drm/tilcdc/tilcdc_drv.c
index 40b71da5a214..116da199b942 100644
--- a/drivers/gpu/drm/tilcdc/tilcdc_drv.c
+++ b/drivers/gpu/drm/tilcdc/tilcdc_drv.c
@@ -497,7 +497,6 @@ static const struct file_operations fops = {
 #endif
 	.poll               = drm_poll,
 	.read               = drm_read,
-	.fasync             = drm_fasync,
 	.llseek             = no_llseek,
 	.mmap               = drm_gem_cma_mmap,
 };
@@ -519,7 +518,7 @@ static struct drm_driver tilcdc_driver = {
 	.gem_vm_ops         = &drm_gem_cma_vm_ops,
 	.dumb_create        = drm_gem_cma_dumb_create,
 	.dumb_map_offset    = drm_gem_cma_dumb_map_offset,
-	.dumb_destroy       = drm_gem_cma_dumb_destroy,
+	.dumb_destroy       = drm_gem_dumb_destroy,
 #ifdef CONFIG_DEBUG_FS
 	.debugfs_init       = tilcdc_debugfs_init,
 	.debugfs_cleanup    = tilcdc_debugfs_cleanup,
diff --git a/drivers/gpu/drm/tilcdc/tilcdc_slave.c b/drivers/gpu/drm/tilcdc/tilcdc_slave.c
index dfffaf014022..595068ba2d5e 100644
--- a/drivers/gpu/drm/tilcdc/tilcdc_slave.c
+++ b/drivers/gpu/drm/tilcdc/tilcdc_slave.c
@@ -16,7 +16,6 @@
  */
 
 #include <linux/i2c.h>
-#include <linux/of_i2c.h>
 #include <linux/pinctrl/pinmux.h>
 #include <linux/pinctrl/consumer.h>
 #include <drm/drm_encoder_slave.h>
@@ -73,13 +72,38 @@ static void slave_encoder_prepare(struct drm_encoder *encoder)
 	tilcdc_crtc_set_panel_info(encoder->crtc, &slave_info);
 }
 
+static bool slave_encoder_fixup(struct drm_encoder *encoder,
+		const struct drm_display_mode *mode,
+		struct drm_display_mode *adjusted_mode)
+{
+	/*
+	 * tilcdc does not generate VESA-complient sync but aligns
+	 * VS on the second edge of HS instead of first edge.
+	 * We use adjusted_mode, to fixup sync by aligning both rising
+	 * edges and add HSKEW offset to let the slave encoder fix it up.
+	 */
+	adjusted_mode->hskew = mode->hsync_end - mode->hsync_start;
+	adjusted_mode->flags |= DRM_MODE_FLAG_HSKEW;
+
+	if (mode->flags & DRM_MODE_FLAG_NHSYNC) {
+		adjusted_mode->flags |= DRM_MODE_FLAG_PHSYNC;
+		adjusted_mode->flags &= ~DRM_MODE_FLAG_NHSYNC;
+	} else {
+		adjusted_mode->flags |= DRM_MODE_FLAG_NHSYNC;
+		adjusted_mode->flags &= ~DRM_MODE_FLAG_PHSYNC;
+	}
+
+	return drm_i2c_encoder_mode_fixup(encoder, mode, adjusted_mode);
+}
+
+
 static const struct drm_encoder_funcs slave_encoder_funcs = {
 		.destroy        = slave_encoder_destroy,
 };
 
 static const struct drm_encoder_helper_funcs slave_encoder_helper_funcs = {
 		.dpms           = drm_i2c_encoder_dpms,
-		.mode_fixup     = drm_i2c_encoder_mode_fixup,
+		.mode_fixup     = slave_encoder_fixup,
 		.prepare        = slave_encoder_prepare,
 		.commit         = drm_i2c_encoder_commit,
 		.mode_set       = drm_i2c_encoder_mode_set,
diff --git a/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c b/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c
index 925c7cddeff9..c38b56b268ac 100644
--- a/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c
+++ b/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c
@@ -16,7 +16,6 @@
  */
 
 #include <linux/i2c.h>
-#include <linux/of_i2c.h>
 #include <linux/gpio.h>
 #include <linux/of_gpio.h>
 #include <linux/pinctrl/pinmux.h>
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index cb9dd674670c..f1a857ec1021 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -45,7 +45,6 @@
 #define TTM_DEBUG(fmt, arg...)
 #define TTM_BO_HASH_ORDER 13
 
-static int ttm_bo_setup_vm(struct ttm_buffer_object *bo);
 static int ttm_bo_swapout(struct ttm_mem_shrink *shrink);
 static void ttm_bo_global_kobj_release(struct kobject *kobj);
 
@@ -615,13 +614,7 @@ static void ttm_bo_release(struct kref *kref)
 	struct ttm_bo_device *bdev = bo->bdev;
 	struct ttm_mem_type_manager *man = &bdev->man[bo->mem.mem_type];
 
-	write_lock(&bdev->vm_lock);
-	if (likely(bo->vm_node != NULL)) {
-		rb_erase(&bo->vm_rb, &bdev->addr_space_rb);
-		drm_mm_put_block(bo->vm_node);
-		bo->vm_node = NULL;
-	}
-	write_unlock(&bdev->vm_lock);
+	drm_vma_offset_remove(&bdev->vma_manager, &bo->vma_node);
 	ttm_mem_io_lock(man, false);
 	ttm_mem_io_free_vm(bo);
 	ttm_mem_io_unlock(man);
@@ -1129,6 +1122,7 @@ int ttm_bo_init(struct ttm_bo_device *bdev,
 	bo->resv = &bo->ttm_resv;
 	reservation_object_init(bo->resv);
 	atomic_inc(&bo->glob->bo_count);
+	drm_vma_node_reset(&bo->vma_node);
 
 	ret = ttm_bo_check_placement(bo, placement);
 
@@ -1139,7 +1133,8 @@ int ttm_bo_init(struct ttm_bo_device *bdev,
 	if (likely(!ret) &&
 	    (bo->type == ttm_bo_type_device ||
 	     bo->type == ttm_bo_type_sg))
-		ret = ttm_bo_setup_vm(bo);
+		ret = drm_vma_offset_add(&bdev->vma_manager, &bo->vma_node,
+					 bo->mem.num_pages);
 
 	locked = ww_mutex_trylock(&bo->resv->lock);
 	WARN_ON(!locked);
@@ -1424,10 +1419,7 @@ int ttm_bo_device_release(struct ttm_bo_device *bdev)
 		TTM_DEBUG("Swap list was clean\n");
 	spin_unlock(&glob->lru_lock);
 
-	BUG_ON(!drm_mm_clean(&bdev->addr_space_mm));
-	write_lock(&bdev->vm_lock);
-	drm_mm_takedown(&bdev->addr_space_mm);
-	write_unlock(&bdev->vm_lock);
+	drm_vma_offset_manager_destroy(&bdev->vma_manager);
 
 	return ret;
 }
@@ -1441,7 +1433,6 @@ int ttm_bo_device_init(struct ttm_bo_device *bdev,
 {
 	int ret = -EINVAL;
 
-	rwlock_init(&bdev->vm_lock);
 	bdev->driver = driver;
 
 	memset(bdev->man, 0, sizeof(bdev->man));
@@ -1454,9 +1445,8 @@ int ttm_bo_device_init(struct ttm_bo_device *bdev,
 	if (unlikely(ret != 0))
 		goto out_no_sys;
 
-	bdev->addr_space_rb = RB_ROOT;
-	drm_mm_init(&bdev->addr_space_mm, file_page_offset, 0x10000000);
-
+	drm_vma_offset_manager_init(&bdev->vma_manager, file_page_offset,
+				    0x10000000);
 	INIT_DELAYED_WORK(&bdev->wq, ttm_bo_delayed_workqueue);
 	INIT_LIST_HEAD(&bdev->ddestroy);
 	bdev->dev_mapping = NULL;
@@ -1498,12 +1488,8 @@ bool ttm_mem_reg_is_pci(struct ttm_bo_device *bdev, struct ttm_mem_reg *mem)
 void ttm_bo_unmap_virtual_locked(struct ttm_buffer_object *bo)
 {
 	struct ttm_bo_device *bdev = bo->bdev;
-	loff_t offset = (loff_t) bo->addr_space_offset;
-	loff_t holelen = ((loff_t) bo->mem.num_pages) << PAGE_SHIFT;
 
-	if (!bdev->dev_mapping)
-		return;
-	unmap_mapping_range(bdev->dev_mapping, offset, holelen, 1);
+	drm_vma_node_unmap(&bo->vma_node, bdev->dev_mapping);
 	ttm_mem_io_free_vm(bo);
 }
 
@@ -1520,78 +1506,6 @@ void ttm_bo_unmap_virtual(struct ttm_buffer_object *bo)
 
 EXPORT_SYMBOL(ttm_bo_unmap_virtual);
 
-static void ttm_bo_vm_insert_rb(struct ttm_buffer_object *bo)
-{
-	struct ttm_bo_device *bdev = bo->bdev;
-	struct rb_node **cur = &bdev->addr_space_rb.rb_node;
-	struct rb_node *parent = NULL;
-	struct ttm_buffer_object *cur_bo;
-	unsigned long offset = bo->vm_node->start;
-	unsigned long cur_offset;
-
-	while (*cur) {
-		parent = *cur;
-		cur_bo = rb_entry(parent, struct ttm_buffer_object, vm_rb);
-		cur_offset = cur_bo->vm_node->start;
-		if (offset < cur_offset)
-			cur = &parent->rb_left;
-		else if (offset > cur_offset)
-			cur = &parent->rb_right;
-		else
-			BUG();
-	}
-
-	rb_link_node(&bo->vm_rb, parent, cur);
-	rb_insert_color(&bo->vm_rb, &bdev->addr_space_rb);
-}
-
-/**
- * ttm_bo_setup_vm:
- *
- * @bo: the buffer to allocate address space for
- *
- * Allocate address space in the drm device so that applications
- * can mmap the buffer and access the contents. This only
- * applies to ttm_bo_type_device objects as others are not
- * placed in the drm device address space.
- */
-
-static int ttm_bo_setup_vm(struct ttm_buffer_object *bo)
-{
-	struct ttm_bo_device *bdev = bo->bdev;
-	int ret;
-
-retry_pre_get:
-	ret = drm_mm_pre_get(&bdev->addr_space_mm);
-	if (unlikely(ret != 0))
-		return ret;
-
-	write_lock(&bdev->vm_lock);
-	bo->vm_node = drm_mm_search_free(&bdev->addr_space_mm,
-					 bo->mem.num_pages, 0, 0);
-
-	if (unlikely(bo->vm_node == NULL)) {
-		ret = -ENOMEM;
-		goto out_unlock;
-	}
-
-	bo->vm_node = drm_mm_get_block_atomic(bo->vm_node,
-					      bo->mem.num_pages, 0);
-
-	if (unlikely(bo->vm_node == NULL)) {
-		write_unlock(&bdev->vm_lock);
-		goto retry_pre_get;
-	}
-
-	ttm_bo_vm_insert_rb(bo);
-	write_unlock(&bdev->vm_lock);
-	bo->addr_space_offset = ((uint64_t) bo->vm_node->start) << PAGE_SHIFT;
-
-	return 0;
-out_unlock:
-	write_unlock(&bdev->vm_lock);
-	return ret;
-}
 
 int ttm_bo_wait(struct ttm_buffer_object *bo,
 		bool lazy, bool interruptible, bool no_wait)
diff --git a/drivers/gpu/drm/ttm/ttm_bo_manager.c b/drivers/gpu/drm/ttm/ttm_bo_manager.c
index e4367f91472a..c58eba33bd5f 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_manager.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_manager.c
@@ -61,28 +61,25 @@ static int ttm_bo_man_get_node(struct ttm_mem_type_manager *man,
 	lpfn = placement->lpfn;
 	if (!lpfn)
 		lpfn = man->size;
-	do {
-		ret = drm_mm_pre_get(mm);
-		if (unlikely(ret))
-			return ret;
 
-		spin_lock(&rman->lock);
-		node = drm_mm_search_free_in_range(mm,
-					mem->num_pages, mem->page_alignment,
-					placement->fpfn, lpfn, 1);
-		if (unlikely(node == NULL)) {
-			spin_unlock(&rman->lock);
-			return 0;
-		}
-		node = drm_mm_get_block_atomic_range(node, mem->num_pages,
-						     mem->page_alignment,
-						     placement->fpfn,
-						     lpfn);
-		spin_unlock(&rman->lock);
-	} while (node == NULL);
+	node = kzalloc(sizeof(*node), GFP_KERNEL);
+	if (!node)
+		return -ENOMEM;
+
+	spin_lock(&rman->lock);
+	ret = drm_mm_insert_node_in_range(mm, node, mem->num_pages,
+					  mem->page_alignment,
+					  placement->fpfn, lpfn,
+					  DRM_MM_SEARCH_BEST);
+	spin_unlock(&rman->lock);
+
+	if (unlikely(ret)) {
+		kfree(node);
+	} else {
+		mem->mm_node = node;
+		mem->start = node->start;
+	}
 
-	mem->mm_node = node;
-	mem->start = node->start;
 	return 0;
 }
 
@@ -93,8 +90,10 @@ static void ttm_bo_man_put_node(struct ttm_mem_type_manager *man,
 
 	if (mem->mm_node) {
 		spin_lock(&rman->lock);
-		drm_mm_put_block(mem->mm_node);
+		drm_mm_remove_node(mem->mm_node);
 		spin_unlock(&rman->lock);
+
+		kfree(mem->mm_node);
 		mem->mm_node = NULL;
 	}
 }
diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
index 319cf4127c5b..7cc904d3a4d1 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_util.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
@@ -30,6 +30,7 @@
 
 #include <drm/ttm/ttm_bo_driver.h>
 #include <drm/ttm/ttm_placement.h>
+#include <drm/drm_vma_manager.h>
 #include <linux/io.h>
 #include <linux/highmem.h>
 #include <linux/wait.h>
@@ -450,7 +451,7 @@ static int ttm_buffer_object_transfer(struct ttm_buffer_object *bo,
 	INIT_LIST_HEAD(&fbo->lru);
 	INIT_LIST_HEAD(&fbo->swap);
 	INIT_LIST_HEAD(&fbo->io_reserve_lru);
-	fbo->vm_node = NULL;
+	drm_vma_node_reset(&fbo->vma_node);
 	atomic_set(&fbo->cpu_writers, 0);
 
 	spin_lock(&bdev->fence_lock);
diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c
index 3df9f16b041c..1006c15445e9 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_vm.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c
@@ -33,6 +33,7 @@
 #include <ttm/ttm_module.h>
 #include <ttm/ttm_bo_driver.h>
 #include <ttm/ttm_placement.h>
+#include <drm/drm_vma_manager.h>
 #include <linux/mm.h>
 #include <linux/rbtree.h>
 #include <linux/module.h>
@@ -40,37 +41,6 @@
 
 #define TTM_BO_VM_NUM_PREFAULT 16
 
-static struct ttm_buffer_object *ttm_bo_vm_lookup_rb(struct ttm_bo_device *bdev,
-						     unsigned long page_start,
-						     unsigned long num_pages)
-{
-	struct rb_node *cur = bdev->addr_space_rb.rb_node;
-	unsigned long cur_offset;
-	struct ttm_buffer_object *bo;
-	struct ttm_buffer_object *best_bo = NULL;
-
-	while (likely(cur != NULL)) {
-		bo = rb_entry(cur, struct ttm_buffer_object, vm_rb);
-		cur_offset = bo->vm_node->start;
-		if (page_start >= cur_offset) {
-			cur = cur->rb_right;
-			best_bo = bo;
-			if (page_start == cur_offset)
-				break;
-		} else
-			cur = cur->rb_left;
-	}
-
-	if (unlikely(best_bo == NULL))
-		return NULL;
-
-	if (unlikely((best_bo->vm_node->start + best_bo->num_pages) <
-		     (page_start + num_pages)))
-		return NULL;
-
-	return best_bo;
-}
-
 static int ttm_bo_vm_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
 	struct ttm_buffer_object *bo = (struct ttm_buffer_object *)
@@ -146,9 +116,9 @@ static int ttm_bo_vm_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	}
 
 	page_offset = ((address - vma->vm_start) >> PAGE_SHIFT) +
-	    bo->vm_node->start - vma->vm_pgoff;
+	    drm_vma_node_start(&bo->vma_node) - vma->vm_pgoff;
 	page_last = vma_pages(vma) +
-	    bo->vm_node->start - vma->vm_pgoff;
+	    drm_vma_node_start(&bo->vma_node) - vma->vm_pgoff;
 
 	if (unlikely(page_offset >= bo->num_pages)) {
 		retval = VM_FAULT_SIGBUS;
@@ -249,6 +219,30 @@ static const struct vm_operations_struct ttm_bo_vm_ops = {
 	.close = ttm_bo_vm_close
 };
 
+static struct ttm_buffer_object *ttm_bo_vm_lookup(struct ttm_bo_device *bdev,
+						  unsigned long offset,
+						  unsigned long pages)
+{
+	struct drm_vma_offset_node *node;
+	struct ttm_buffer_object *bo = NULL;
+
+	drm_vma_offset_lock_lookup(&bdev->vma_manager);
+
+	node = drm_vma_offset_lookup_locked(&bdev->vma_manager, offset, pages);
+	if (likely(node)) {
+		bo = container_of(node, struct ttm_buffer_object, vma_node);
+		if (!kref_get_unless_zero(&bo->kref))
+			bo = NULL;
+	}
+
+	drm_vma_offset_unlock_lookup(&bdev->vma_manager);
+
+	if (!bo)
+		pr_err("Could not find buffer object to map\n");
+
+	return bo;
+}
+
 int ttm_bo_mmap(struct file *filp, struct vm_area_struct *vma,
 		struct ttm_bo_device *bdev)
 {
@@ -256,17 +250,9 @@ int ttm_bo_mmap(struct file *filp, struct vm_area_struct *vma,
 	struct ttm_buffer_object *bo;
 	int ret;
 
-	read_lock(&bdev->vm_lock);
-	bo = ttm_bo_vm_lookup_rb(bdev, vma->vm_pgoff,
-				 vma_pages(vma));
-	if (likely(bo != NULL) && !kref_get_unless_zero(&bo->kref))
-		bo = NULL;
-	read_unlock(&bdev->vm_lock);
-
-	if (unlikely(bo == NULL)) {
-		pr_err("Could not find buffer object to map\n");
+	bo = ttm_bo_vm_lookup(bdev, vma->vm_pgoff, vma_pages(vma));
+	if (unlikely(!bo))
 		return -EINVAL;
-	}
 
 	driver = bo->bdev->driver;
 	if (unlikely(!driver->verify_access)) {
@@ -304,162 +290,3 @@ int ttm_fbdev_mmap(struct vm_area_struct *vma, struct ttm_buffer_object *bo)
 	return 0;
 }
 EXPORT_SYMBOL(ttm_fbdev_mmap);
-
-
-ssize_t ttm_bo_io(struct ttm_bo_device *bdev, struct file *filp,
-		  const char __user *wbuf, char __user *rbuf, size_t count,
-		  loff_t *f_pos, bool write)
-{
-	struct ttm_buffer_object *bo;
-	struct ttm_bo_driver *driver;
-	struct ttm_bo_kmap_obj map;
-	unsigned long dev_offset = (*f_pos >> PAGE_SHIFT);
-	unsigned long kmap_offset;
-	unsigned long kmap_end;
-	unsigned long kmap_num;
-	size_t io_size;
-	unsigned int page_offset;
-	char *virtual;
-	int ret;
-	bool no_wait = false;
-	bool dummy;
-
-	read_lock(&bdev->vm_lock);
-	bo = ttm_bo_vm_lookup_rb(bdev, dev_offset, 1);
-	if (likely(bo != NULL))
-		ttm_bo_reference(bo);
-	read_unlock(&bdev->vm_lock);
-
-	if (unlikely(bo == NULL))
-		return -EFAULT;
-
-	driver = bo->bdev->driver;
-	if (unlikely(!driver->verify_access)) {
-		ret = -EPERM;
-		goto out_unref;
-	}
-
-	ret = driver->verify_access(bo, filp);
-	if (unlikely(ret != 0))
-		goto out_unref;
-
-	kmap_offset = dev_offset - bo->vm_node->start;
-	if (unlikely(kmap_offset >= bo->num_pages)) {
-		ret = -EFBIG;
-		goto out_unref;
-	}
-
-	page_offset = *f_pos & ~PAGE_MASK;
-	io_size = bo->num_pages - kmap_offset;
-	io_size = (io_size << PAGE_SHIFT) - page_offset;
-	if (count < io_size)
-		io_size = count;
-
-	kmap_end = (*f_pos + count - 1) >> PAGE_SHIFT;
-	kmap_num = kmap_end - kmap_offset + 1;
-
-	ret = ttm_bo_reserve(bo, true, no_wait, false, 0);
-
-	switch (ret) {
-	case 0:
-		break;
-	case -EBUSY:
-		ret = -EAGAIN;
-		goto out_unref;
-	default:
-		goto out_unref;
-	}
-
-	ret = ttm_bo_kmap(bo, kmap_offset, kmap_num, &map);
-	if (unlikely(ret != 0)) {
-		ttm_bo_unreserve(bo);
-		goto out_unref;
-	}
-
-	virtual = ttm_kmap_obj_virtual(&map, &dummy);
-	virtual += page_offset;
-
-	if (write)
-		ret = copy_from_user(virtual, wbuf, io_size);
-	else
-		ret = copy_to_user(rbuf, virtual, io_size);
-
-	ttm_bo_kunmap(&map);
-	ttm_bo_unreserve(bo);
-	ttm_bo_unref(&bo);
-
-	if (unlikely(ret != 0))
-		return -EFBIG;
-
-	*f_pos += io_size;
-
-	return io_size;
-out_unref:
-	ttm_bo_unref(&bo);
-	return ret;
-}
-
-ssize_t ttm_bo_fbdev_io(struct ttm_buffer_object *bo, const char __user *wbuf,
-			char __user *rbuf, size_t count, loff_t *f_pos,
-			bool write)
-{
-	struct ttm_bo_kmap_obj map;
-	unsigned long kmap_offset;
-	unsigned long kmap_end;
-	unsigned long kmap_num;
-	size_t io_size;
-	unsigned int page_offset;
-	char *virtual;
-	int ret;
-	bool no_wait = false;
-	bool dummy;
-
-	kmap_offset = (*f_pos >> PAGE_SHIFT);
-	if (unlikely(kmap_offset >= bo->num_pages))
-		return -EFBIG;
-
-	page_offset = *f_pos & ~PAGE_MASK;
-	io_size = bo->num_pages - kmap_offset;
-	io_size = (io_size << PAGE_SHIFT) - page_offset;
-	if (count < io_size)
-		io_size = count;
-
-	kmap_end = (*f_pos + count - 1) >> PAGE_SHIFT;
-	kmap_num = kmap_end - kmap_offset + 1;
-
-	ret = ttm_bo_reserve(bo, true, no_wait, false, 0);
-
-	switch (ret) {
-	case 0:
-		break;
-	case -EBUSY:
-		return -EAGAIN;
-	default:
-		return ret;
-	}
-
-	ret = ttm_bo_kmap(bo, kmap_offset, kmap_num, &map);
-	if (unlikely(ret != 0)) {
-		ttm_bo_unreserve(bo);
-		return ret;
-	}
-
-	virtual = ttm_kmap_obj_virtual(&map, &dummy);
-	virtual += page_offset;
-
-	if (write)
-		ret = copy_from_user(virtual, wbuf, io_size);
-	else
-		ret = copy_to_user(rbuf, virtual, io_size);
-
-	ttm_bo_kunmap(&map);
-	ttm_bo_unreserve(bo);
-	ttm_bo_unref(&bo);
-
-	if (unlikely(ret != 0))
-		return ret;
-
-	*f_pos += io_size;
-
-	return io_size;
-}
diff --git a/drivers/gpu/drm/ttm/ttm_object.c b/drivers/gpu/drm/ttm/ttm_object.c
index 58a5f3261c0b..a868176c258a 100644
--- a/drivers/gpu/drm/ttm/ttm_object.c
+++ b/drivers/gpu/drm/ttm/ttm_object.c
@@ -218,7 +218,7 @@ struct ttm_base_object *ttm_base_object_lookup(struct ttm_object_file *tfile,
 					       uint32_t key)
 {
 	struct ttm_object_device *tdev = tfile->tdev;
-	struct ttm_base_object *base;
+	struct ttm_base_object *uninitialized_var(base);
 	struct drm_hash_item *hash;
 	int ret;
 
diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc.c b/drivers/gpu/drm/ttm/ttm_page_alloc.c
index bd2a3b40cd12..863bef9f9234 100644
--- a/drivers/gpu/drm/ttm/ttm_page_alloc.c
+++ b/drivers/gpu/drm/ttm/ttm_page_alloc.c
@@ -377,28 +377,26 @@ out:
 	return nr_free;
 }
 
-/* Get good estimation how many pages are free in pools */
-static int ttm_pool_get_num_unused_pages(void)
-{
-	unsigned i;
-	int total = 0;
-	for (i = 0; i < NUM_POOLS; ++i)
-		total += _manager->pools[i].npages;
-
-	return total;
-}
-
 /**
  * Callback for mm to request pool to reduce number of page held.
+ *
+ * XXX: (dchinner) Deadlock warning!
+ *
+ * ttm_page_pool_free() does memory allocation using GFP_KERNEL.  that means
+ * this can deadlock when called a sc->gfp_mask that is not equal to
+ * GFP_KERNEL.
+ *
+ * This code is crying out for a shrinker per pool....
  */
-static int ttm_pool_mm_shrink(struct shrinker *shrink,
-			      struct shrink_control *sc)
+static unsigned long
+ttm_pool_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
 {
 	static atomic_t start_pool = ATOMIC_INIT(0);
 	unsigned i;
 	unsigned pool_offset = atomic_add_return(1, &start_pool);
 	struct ttm_page_pool *pool;
 	int shrink_pages = sc->nr_to_scan;
+	unsigned long freed = 0;
 
 	pool_offset = pool_offset % NUM_POOLS;
 	/* select start pool in round robin fashion */
@@ -408,14 +406,28 @@ static int ttm_pool_mm_shrink(struct shrinker *shrink,
 			break;
 		pool = &_manager->pools[(i + pool_offset)%NUM_POOLS];
 		shrink_pages = ttm_page_pool_free(pool, nr_free);
+		freed += nr_free - shrink_pages;
 	}
-	/* return estimated number of unused pages in pool */
-	return ttm_pool_get_num_unused_pages();
+	return freed;
+}
+
+
+static unsigned long
+ttm_pool_shrink_count(struct shrinker *shrink, struct shrink_control *sc)
+{
+	unsigned i;
+	unsigned long count = 0;
+
+	for (i = 0; i < NUM_POOLS; ++i)
+		count += _manager->pools[i].npages;
+
+	return count;
 }
 
 static void ttm_pool_mm_shrink_init(struct ttm_pool_manager *manager)
 {
-	manager->mm_shrink.shrink = &ttm_pool_mm_shrink;
+	manager->mm_shrink.count_objects = ttm_pool_shrink_count;
+	manager->mm_shrink.scan_objects = ttm_pool_shrink_scan;
 	manager->mm_shrink.seeks = 1;
 	register_shrinker(&manager->mm_shrink);
 }
diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c b/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
index b8b394319b45..7957beeeaf73 100644
--- a/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
+++ b/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
@@ -918,19 +918,6 @@ int ttm_dma_populate(struct ttm_dma_tt *ttm_dma, struct device *dev)
 }
 EXPORT_SYMBOL_GPL(ttm_dma_populate);
 
-/* Get good estimation how many pages are free in pools */
-static int ttm_dma_pool_get_num_unused_pages(void)
-{
-	struct device_pools *p;
-	unsigned total = 0;
-
-	mutex_lock(&_manager->lock);
-	list_for_each_entry(p, &_manager->pools, pools)
-		total += p->pool->npages_free;
-	mutex_unlock(&_manager->lock);
-	return total;
-}
-
 /* Put all pages in pages list to correct pool to wait for reuse */
 void ttm_dma_unpopulate(struct ttm_dma_tt *ttm_dma, struct device *dev)
 {
@@ -1002,18 +989,29 @@ EXPORT_SYMBOL_GPL(ttm_dma_unpopulate);
 
 /**
  * Callback for mm to request pool to reduce number of page held.
+ *
+ * XXX: (dchinner) Deadlock warning!
+ *
+ * ttm_dma_page_pool_free() does GFP_KERNEL memory allocation, and so attention
+ * needs to be paid to sc->gfp_mask to determine if this can be done or not.
+ * GFP_KERNEL memory allocation in a GFP_ATOMIC reclaim context woul dbe really
+ * bad.
+ *
+ * I'm getting sadder as I hear more pathetical whimpers about needing per-pool
+ * shrinkers
  */
-static int ttm_dma_pool_mm_shrink(struct shrinker *shrink,
-				  struct shrink_control *sc)
+static unsigned long
+ttm_dma_pool_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
 {
 	static atomic_t start_pool = ATOMIC_INIT(0);
 	unsigned idx = 0;
 	unsigned pool_offset = atomic_add_return(1, &start_pool);
 	unsigned shrink_pages = sc->nr_to_scan;
 	struct device_pools *p;
+	unsigned long freed = 0;
 
 	if (list_empty(&_manager->pools))
-		return 0;
+		return SHRINK_STOP;
 
 	mutex_lock(&_manager->lock);
 	pool_offset = pool_offset % _manager->npools;
@@ -1029,18 +1027,33 @@ static int ttm_dma_pool_mm_shrink(struct shrinker *shrink,
 			continue;
 		nr_free = shrink_pages;
 		shrink_pages = ttm_dma_page_pool_free(p->pool, nr_free);
+		freed += nr_free - shrink_pages;
+
 		pr_debug("%s: (%s:%d) Asked to shrink %d, have %d more to go\n",
 			 p->pool->dev_name, p->pool->name, current->pid,
 			 nr_free, shrink_pages);
 	}
 	mutex_unlock(&_manager->lock);
-	/* return estimated number of unused pages in pool */
-	return ttm_dma_pool_get_num_unused_pages();
+	return freed;
+}
+
+static unsigned long
+ttm_dma_pool_shrink_count(struct shrinker *shrink, struct shrink_control *sc)
+{
+	struct device_pools *p;
+	unsigned long count = 0;
+
+	mutex_lock(&_manager->lock);
+	list_for_each_entry(p, &_manager->pools, pools)
+		count += p->pool->npages_free;
+	mutex_unlock(&_manager->lock);
+	return count;
 }
 
 static void ttm_dma_pool_mm_shrink_init(struct ttm_pool_manager *manager)
 {
-	manager->mm_shrink.shrink = &ttm_dma_pool_mm_shrink;
+	manager->mm_shrink.count_objects = ttm_dma_pool_shrink_count;
+	manager->mm_shrink.scan_objects = &ttm_dma_pool_shrink_scan;
 	manager->mm_shrink.seeks = 1;
 	register_shrinker(&manager->mm_shrink);
 }
diff --git a/drivers/gpu/drm/ttm/ttm_tt.c b/drivers/gpu/drm/ttm/ttm_tt.c
index 5e93a52d4f2c..210d50365162 100644
--- a/drivers/gpu/drm/ttm/ttm_tt.c
+++ b/drivers/gpu/drm/ttm/ttm_tt.c
@@ -170,7 +170,7 @@ void ttm_tt_destroy(struct ttm_tt *ttm)
 		ttm_tt_unbind(ttm);
 	}
 
-	if (likely(ttm->pages != NULL)) {
+	if (ttm->state == tt_unbound) {
 		ttm->bdev->driver->ttm_tt_unpopulate(ttm);
 	}
 
diff --git a/drivers/gpu/drm/udl/udl_drv.c b/drivers/gpu/drm/udl/udl_drv.c
index c0770dbba74a..7650dc0d78ce 100644
--- a/drivers/gpu/drm/udl/udl_drv.c
+++ b/drivers/gpu/drm/udl/udl_drv.c
@@ -65,7 +65,6 @@ static const struct file_operations udl_driver_fops = {
 	.read = drm_read,
 	.unlocked_ioctl	= drm_ioctl,
 	.release = drm_release,
-	.fasync = drm_fasync,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl = drm_compat_ioctl,
 #endif
@@ -84,7 +83,7 @@ static struct drm_driver driver = {
 
 	.dumb_create = udl_dumb_create,
 	.dumb_map_offset = udl_gem_mmap,
-	.dumb_destroy = udl_dumb_destroy,
+	.dumb_destroy = drm_gem_dumb_destroy,
 	.fops = &udl_driver_fops,
 
 	.prime_fd_to_handle = drm_gem_prime_fd_to_handle,
diff --git a/drivers/gpu/drm/udl/udl_drv.h b/drivers/gpu/drm/udl/udl_drv.h
index cc6d90f28c71..56aec9409fa3 100644
--- a/drivers/gpu/drm/udl/udl_drv.h
+++ b/drivers/gpu/drm/udl/udl_drv.h
@@ -114,8 +114,6 @@ int udl_dumb_create(struct drm_file *file_priv,
 		    struct drm_mode_create_dumb *args);
 int udl_gem_mmap(struct drm_file *file_priv, struct drm_device *dev,
 		 uint32_t handle, uint64_t *offset);
-int udl_dumb_destroy(struct drm_file *file_priv, struct drm_device *dev,
-		     uint32_t handle);
 
 int udl_gem_init_object(struct drm_gem_object *obj);
 void udl_gem_free_object(struct drm_gem_object *gem_obj);
diff --git a/drivers/gpu/drm/udl/udl_gem.c b/drivers/gpu/drm/udl/udl_gem.c
index ef034fa3e6f5..8bf646183bac 100644
--- a/drivers/gpu/drm/udl/udl_gem.c
+++ b/drivers/gpu/drm/udl/udl_gem.c
@@ -66,12 +66,6 @@ int udl_dumb_create(struct drm_file *file,
 			      args->size, &args->handle);
 }
 
-int udl_dumb_destroy(struct drm_file *file, struct drm_device *dev,
-		     uint32_t handle)
-{
-	return drm_gem_handle_delete(file, handle);
-}
-
 int udl_drm_gem_mmap(struct file *filp, struct vm_area_struct *vma)
 {
 	int ret;
@@ -103,7 +97,6 @@ int udl_gem_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	ret = vm_insert_page(vma, (unsigned long)vmf->virtual_address, page);
 	switch (ret) {
 	case -EAGAIN:
-		set_need_resched();
 	case 0:
 	case -ERESTARTSYS:
 		return VM_FAULT_NOPAGE;
@@ -123,55 +116,23 @@ int udl_gem_init_object(struct drm_gem_object *obj)
 
 static int udl_gem_get_pages(struct udl_gem_object *obj, gfp_t gfpmask)
 {
-	int page_count, i;
-	struct page *page;
-	struct inode *inode;
-	struct address_space *mapping;
+	struct page **pages;
 
 	if (obj->pages)
 		return 0;
 
-	page_count = obj->base.size / PAGE_SIZE;
-	BUG_ON(obj->pages != NULL);
-	obj->pages = drm_malloc_ab(page_count, sizeof(struct page *));
-	if (obj->pages == NULL)
-		return -ENOMEM;
+	pages = drm_gem_get_pages(&obj->base, gfpmask);
+	if (IS_ERR(pages))
+		return PTR_ERR(pages);
 
-	inode = file_inode(obj->base.filp);
-	mapping = inode->i_mapping;
-	gfpmask |= mapping_gfp_mask(mapping);
-
-	for (i = 0; i < page_count; i++) {
-		page = shmem_read_mapping_page_gfp(mapping, i, gfpmask);
-		if (IS_ERR(page))
-			goto err_pages;
-		obj->pages[i] = page;
-	}
+	obj->pages = pages;
 
 	return 0;
-err_pages:
-	while (i--)
-		page_cache_release(obj->pages[i]);
-	drm_free_large(obj->pages);
-	obj->pages = NULL;
-	return PTR_ERR(page);
 }
 
 static void udl_gem_put_pages(struct udl_gem_object *obj)
 {
-	int page_count = obj->base.size / PAGE_SIZE;
-	int i;
-
-	if (obj->base.import_attach) {
-		drm_free_large(obj->pages);
-		obj->pages = NULL;
-		return;
-	}
-
-	for (i = 0; i < page_count; i++)
-		page_cache_release(obj->pages[i]);
-
-	drm_free_large(obj->pages);
+	drm_gem_put_pages(&obj->base, obj->pages, false, false);
 	obj->pages = NULL;
 }
 
@@ -223,8 +184,7 @@ void udl_gem_free_object(struct drm_gem_object *gem_obj)
 	if (obj->pages)
 		udl_gem_put_pages(obj);
 
-	if (gem_obj->map_list.map)
-		drm_gem_free_mmap_offset(gem_obj);
+	drm_gem_free_mmap_offset(gem_obj);
 }
 
 /* the dumb interface doesn't work with the GEM straight MMAP
@@ -247,13 +207,11 @@ int udl_gem_mmap(struct drm_file *file, struct drm_device *dev,
 	ret = udl_gem_get_pages(gobj, GFP_KERNEL);
 	if (ret)
 		goto out;
-	if (!gobj->base.map_list.map) {
-		ret = drm_gem_create_mmap_offset(obj);
-		if (ret)
-			goto out;
-	}
+	ret = drm_gem_create_mmap_offset(obj);
+	if (ret)
+		goto out;
 
-	*offset = (u64)gobj->base.map_list.hash.key << PAGE_SHIFT;
+	*offset = drm_vma_node_offset_addr(&gobj->base.vma_node);
 
 out:
 	drm_gem_object_unreference(&gobj->base);
diff --git a/drivers/gpu/drm/udl/udl_main.c b/drivers/gpu/drm/udl/udl_main.c
index 0ce2d7195256..f5ae57406f34 100644
--- a/drivers/gpu/drm/udl/udl_main.c
+++ b/drivers/gpu/drm/udl/udl_main.c
@@ -41,8 +41,8 @@ static int udl_parse_vendor_descriptor(struct drm_device *dev,
 	total_len = usb_get_descriptor(usbdev, 0x5f, /* vendor specific */
 				    0, desc, MAX_VENDOR_DESCRIPTOR_SIZE);
 	if (total_len > 5) {
-		DRM_INFO("vendor descriptor length:%x data:%*ph\n",
-			total_len, 11, desc);
+		DRM_INFO("vendor descriptor length:%x data:%11ph\n",
+			total_len, desc);
 
 		if ((desc[0] != total_len) || /* descriptor length */
 		    (desc[1] != 0x5f) ||   /* vendor descriptor type */
diff --git a/drivers/gpu/drm/via/via_dma.c b/drivers/gpu/drm/via/via_dma.c
index 13558f5a2422..652f9b43ec9d 100644
--- a/drivers/gpu/drm/via/via_dma.c
+++ b/drivers/gpu/drm/via/via_dma.c
@@ -720,7 +720,7 @@ static int via_cmdbuf_size(struct drm_device *dev, void *data, struct drm_file *
 	return ret;
 }
 
-struct drm_ioctl_desc via_ioctls[] = {
+const struct drm_ioctl_desc via_ioctls[] = {
 	DRM_IOCTL_DEF_DRV(VIA_ALLOCMEM, via_mem_alloc, DRM_AUTH),
 	DRM_IOCTL_DEF_DRV(VIA_FREEMEM, via_mem_free, DRM_AUTH),
 	DRM_IOCTL_DEF_DRV(VIA_AGP_INIT, via_agp_init, DRM_AUTH|DRM_MASTER),
diff --git a/drivers/gpu/drm/via/via_drv.c b/drivers/gpu/drm/via/via_drv.c
index f4ae20327941..92684a9b7e34 100644
--- a/drivers/gpu/drm/via/via_drv.c
+++ b/drivers/gpu/drm/via/via_drv.c
@@ -64,7 +64,6 @@ static const struct file_operations via_driver_fops = {
 	.unlocked_ioctl = drm_ioctl,
 	.mmap = drm_mmap,
 	.poll = drm_poll,
-	.fasync = drm_fasync,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl = drm_compat_ioctl,
 #endif
@@ -73,7 +72,7 @@ static const struct file_operations via_driver_fops = {
 
 static struct drm_driver driver = {
 	.driver_features =
-	    DRIVER_USE_AGP | DRIVER_USE_MTRR | DRIVER_HAVE_IRQ |
+	    DRIVER_USE_AGP | DRIVER_HAVE_IRQ |
 	    DRIVER_IRQ_SHARED,
 	.load = via_driver_load,
 	.unload = via_driver_unload,
diff --git a/drivers/gpu/drm/via/via_drv.h b/drivers/gpu/drm/via/via_drv.h
index 893a65090c36..a811ef2b505f 100644
--- a/drivers/gpu/drm/via/via_drv.h
+++ b/drivers/gpu/drm/via/via_drv.h
@@ -114,7 +114,7 @@ enum via_family {
 #define VIA_READ8(reg)		DRM_READ8(VIA_BASE, reg)
 #define VIA_WRITE8(reg, val)	DRM_WRITE8(VIA_BASE, reg, val)
 
-extern struct drm_ioctl_desc via_ioctls[];
+extern const struct drm_ioctl_desc via_ioctls[];
 extern int via_max_ioctl;
 
 extern int via_fb_init(struct drm_device *dev, void *data, struct drm_file *file_priv);
diff --git a/drivers/gpu/drm/via/via_mm.c b/drivers/gpu/drm/via/via_mm.c
index 0ab93ff09873..7e3ad87c366c 100644
--- a/drivers/gpu/drm/via/via_mm.c
+++ b/drivers/gpu/drm/via/via_mm.c
@@ -140,11 +140,11 @@ int via_mem_alloc(struct drm_device *dev, void *data,
 	if (mem->type == VIA_MEM_AGP)
 		retval = drm_mm_insert_node(&dev_priv->agp_mm,
 					    &item->mm_node,
-					    tmpSize, 0);
+					    tmpSize, 0, DRM_MM_SEARCH_DEFAULT);
 	else
 		retval = drm_mm_insert_node(&dev_priv->vram_mm,
 					    &item->mm_node,
-					    tmpSize, 0);
+					    tmpSize, 0, DRM_MM_SEARCH_DEFAULT);
 	if (retval)
 		goto fail_alloc;
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
index 78e21649d48a..1a90f0a2f7e5 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
@@ -124,7 +124,7 @@
  * Ioctl definitions.
  */
 
-static struct drm_ioctl_desc vmw_ioctls[] = {
+static const struct drm_ioctl_desc vmw_ioctls[] = {
 	VMW_IOCTL_DEF(VMW_GET_PARAM, vmw_getparam_ioctl,
 		      DRM_AUTH | DRM_UNLOCKED),
 	VMW_IOCTL_DEF(VMW_ALLOC_DMABUF, vmw_dmabuf_alloc_ioctl,
@@ -622,8 +622,10 @@ static int vmw_driver_load(struct drm_device *dev, unsigned long chipset)
 	}
 
 	dev_priv->fman = vmw_fence_manager_init(dev_priv);
-	if (unlikely(dev_priv->fman == NULL))
+	if (unlikely(dev_priv->fman == NULL)) {
+		ret = -ENOMEM;
 		goto out_no_fman;
+	}
 
 	vmw_kms_save_vga(dev_priv);
 
@@ -782,7 +784,7 @@ static long vmw_unlocked_ioctl(struct file *filp, unsigned int cmd,
 
 	if ((nr >= DRM_COMMAND_BASE) && (nr < DRM_COMMAND_END)
 	    && (nr < DRM_COMMAND_BASE + dev->driver->num_ioctls)) {
-		struct drm_ioctl_desc *ioctl =
+		const struct drm_ioctl_desc *ioctl =
 		    &vmw_ioctls[nr - DRM_COMMAND_BASE];
 
 		if (unlikely(ioctl->cmd_drv != cmd)) {
@@ -795,29 +797,12 @@ static long vmw_unlocked_ioctl(struct file *filp, unsigned int cmd,
 	return drm_ioctl(filp, cmd, arg);
 }
 
-static int vmw_firstopen(struct drm_device *dev)
-{
-	struct vmw_private *dev_priv = vmw_priv(dev);
-	dev_priv->is_opened = true;
-
-	return 0;
-}
-
 static void vmw_lastclose(struct drm_device *dev)
 {
-	struct vmw_private *dev_priv = vmw_priv(dev);
 	struct drm_crtc *crtc;
 	struct drm_mode_set set;
 	int ret;
 
-	/**
-	 * Do nothing on the lastclose call from drm_unload.
-	 */
-
-	if (!dev_priv->is_opened)
-		return;
-
-	dev_priv->is_opened = false;
 	set.x = 0;
 	set.y = 0;
 	set.fb = NULL;
@@ -1120,7 +1105,6 @@ static const struct file_operations vmwgfx_driver_fops = {
 	.mmap = vmw_mmap,
 	.poll = vmw_fops_poll,
 	.read = vmw_fops_read,
-	.fasync = drm_fasync,
 #if defined(CONFIG_COMPAT)
 	.compat_ioctl = drm_compat_ioctl,
 #endif
@@ -1132,7 +1116,6 @@ static struct drm_driver driver = {
 	DRIVER_MODESET,
 	.load = vmw_driver_load,
 	.unload = vmw_driver_unload,
-	.firstopen = vmw_firstopen,
 	.lastclose = vmw_lastclose,
 	.irq_preinstall = vmw_irq_preinstall,
 	.irq_postinstall = vmw_irq_postinstall,
@@ -1143,7 +1126,6 @@ static struct drm_driver driver = {
 	.disable_vblank = vmw_disable_vblank,
 	.ioctls = vmw_ioctls,
 	.num_ioctls = DRM_ARRAY_SIZE(vmw_ioctls),
-	.dma_quiescent = NULL,	/*vmw_dma_quiescent, */
 	.master_create = vmw_master_create,
 	.master_destroy = vmw_master_destroy,
 	.master_set = vmw_master_set,
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
index 13aeda71280e..150ec64af617 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
@@ -324,7 +324,6 @@ struct vmw_private {
 	 */
 
 	bool stealth;
-	bool is_opened;
 	bool enable_fb;
 
 	/**
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
index d4607b2530d6..fc43c0601236 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
@@ -1706,7 +1706,8 @@ int vmw_du_update_layout(struct vmw_private *dev_priv, unsigned num,
 
 int vmw_du_page_flip(struct drm_crtc *crtc,
 		     struct drm_framebuffer *fb,
-		     struct drm_pending_vblank_event *event)
+		     struct drm_pending_vblank_event *event,
+		     uint32_t page_flip_flags)
 {
 	struct vmw_private *dev_priv = vmw_priv(crtc->dev);
 	struct drm_framebuffer *old_fb = crtc->fb;
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h
index 6fa89c9d6214..8d038c36bd57 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h
@@ -123,7 +123,8 @@ struct vmw_display_unit {
 void vmw_display_unit_cleanup(struct vmw_display_unit *du);
 int vmw_du_page_flip(struct drm_crtc *crtc,
 		     struct drm_framebuffer *fb,
-		     struct drm_pending_vblank_event *event);
+		     struct drm_pending_vblank_event *event,
+		     uint32_t page_flip_flags);
 void vmw_du_crtc_save(struct drm_crtc *crtc);
 void vmw_du_crtc_restore(struct drm_crtc *crtc);
 void vmw_du_crtc_gamma_set(struct drm_crtc *crtc,
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
index 7953d1f90b63..0e67cf41065d 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
@@ -500,7 +500,7 @@ int vmw_dmabuf_alloc_ioctl(struct drm_device *dev, void *data,
 		goto out_no_dmabuf;
 
 	rep->handle = handle;
-	rep->map_handle = dma_buf->base.addr_space_offset;
+	rep->map_handle = drm_vma_node_offset_addr(&dma_buf->base.vma_node);
 	rep->cur_gmr_id = handle;
 	rep->cur_gmr_offset = 0;
 
@@ -834,7 +834,7 @@ int vmw_dumb_map_offset(struct drm_file *file_priv,
 	if (ret != 0)
 		return -EINVAL;
 
-	*offset = out_buf->base.addr_space_offset;
+	*offset = drm_vma_node_offset_addr(&out_buf->base.vma_node);
 	vmw_dmabuf_unreference(&out_buf);
 	return 0;
 }
diff --git a/drivers/gpu/host1x/dev.c b/drivers/gpu/host1x/dev.c
index 28e28a23d444..471630299878 100644
--- a/drivers/gpu/host1x/dev.c
+++ b/drivers/gpu/host1x/dev.c
@@ -43,7 +43,7 @@ void host1x_set_drm_data(struct device *dev, void *data)
 void *host1x_get_drm_data(struct device *dev)
 {
 	struct host1x *host1x = dev_get_drvdata(dev);
-	return host1x->drm_data;
+	return host1x ? host1x->drm_data : NULL;
 }
 
 void host1x_sync_writel(struct host1x *host1x, u32 v, u32 r)
diff --git a/drivers/gpu/host1x/dev.h b/drivers/gpu/host1x/dev.h
index 790ddf114e58..bed90a8131be 100644
--- a/drivers/gpu/host1x/dev.h
+++ b/drivers/gpu/host1x/dev.h
@@ -301,8 +301,8 @@ static inline void host1x_hw_show_mlocks(struct host1x *host, struct output *o)
 	host->debug_op->show_mlocks(host, o);
 }
 
-extern struct platform_driver tegra_hdmi_driver;
 extern struct platform_driver tegra_dc_driver;
+extern struct platform_driver tegra_hdmi_driver;
 extern struct platform_driver tegra_gr2d_driver;
 
 #endif
diff --git a/drivers/gpu/host1x/drm/dc.c b/drivers/gpu/host1x/drm/dc.c
index 5360e5a57ecc..b1a05ad901c3 100644
--- a/drivers/gpu/host1x/drm/dc.c
+++ b/drivers/gpu/host1x/drm/dc.c
@@ -235,7 +235,7 @@ void tegra_dc_cancel_page_flip(struct drm_crtc *crtc, struct drm_file *file)
 }
 
 static int tegra_dc_page_flip(struct drm_crtc *crtc, struct drm_framebuffer *fb,
-			      struct drm_pending_vblank_event *event)
+			      struct drm_pending_vblank_event *event, uint32_t page_flip_flags)
 {
 	struct tegra_dc *dc = to_tegra_dc(crtc);
 	struct drm_device *drm = crtc->dev;
diff --git a/drivers/gpu/host1x/drm/drm.c b/drivers/gpu/host1x/drm/drm.c
index e184b00faacd..8c61ceeaa12d 100644
--- a/drivers/gpu/host1x/drm/drm.c
+++ b/drivers/gpu/host1x/drm/drm.c
@@ -356,7 +356,7 @@ static int tegra_gem_mmap(struct drm_device *drm, void *data,
 
 	bo = to_tegra_bo(gem);
 
-	args->offset = tegra_bo_get_mmap_offset(bo);
+	args->offset = drm_vma_node_offset_addr(&bo->gem.vma_node);
 
 	drm_gem_object_unreference(gem);
 
@@ -487,7 +487,7 @@ static int tegra_submit(struct drm_device *drm, void *data,
 }
 #endif
 
-static struct drm_ioctl_desc tegra_drm_ioctls[] = {
+static const struct drm_ioctl_desc tegra_drm_ioctls[] = {
 #ifdef CONFIG_DRM_TEGRA_STAGING
 	DRM_IOCTL_DEF_DRV(TEGRA_GEM_CREATE, tegra_gem_create, DRM_UNLOCKED | DRM_AUTH),
 	DRM_IOCTL_DEF_DRV(TEGRA_GEM_MMAP, tegra_gem_mmap, DRM_UNLOCKED),
@@ -508,7 +508,6 @@ static const struct file_operations tegra_drm_fops = {
 	.unlocked_ioctl = drm_ioctl,
 	.mmap = tegra_drm_mmap,
 	.poll = drm_poll,
-	.fasync = drm_fasync,
 	.read = drm_read,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl = drm_compat_ioctl,
@@ -633,7 +632,7 @@ struct drm_driver tegra_drm_driver = {
 	.gem_vm_ops = &tegra_bo_vm_ops,
 	.dumb_create = tegra_bo_dumb_create,
 	.dumb_map_offset = tegra_bo_dumb_map_offset,
-	.dumb_destroy = tegra_bo_dumb_destroy,
+	.dumb_destroy = drm_gem_dumb_destroy,
 
 	.ioctls = tegra_drm_ioctls,
 	.num_ioctls = ARRAY_SIZE(tegra_drm_ioctls),
diff --git a/drivers/gpu/host1x/drm/gem.c b/drivers/gpu/host1x/drm/gem.c
index c5e9a9b494c2..59623de4ee15 100644
--- a/drivers/gpu/host1x/drm/gem.c
+++ b/drivers/gpu/host1x/drm/gem.c
@@ -106,11 +106,6 @@ static void tegra_bo_destroy(struct drm_device *drm, struct tegra_bo *bo)
 	dma_free_writecombine(drm->dev, bo->gem.size, bo->vaddr, bo->paddr);
 }
 
-unsigned int tegra_bo_get_mmap_offset(struct tegra_bo *bo)
-{
-	return (unsigned int)bo->gem.map_list.hash.key << PAGE_SHIFT;
-}
-
 struct tegra_bo *tegra_bo_create(struct drm_device *drm, unsigned int size)
 {
 	struct tegra_bo *bo;
@@ -182,8 +177,7 @@ void tegra_bo_free_object(struct drm_gem_object *gem)
 {
 	struct tegra_bo *bo = to_tegra_bo(gem);
 
-	if (gem->map_list.map)
-		drm_gem_free_mmap_offset(gem);
+	drm_gem_free_mmap_offset(gem);
 
 	drm_gem_object_release(gem);
 	tegra_bo_destroy(gem->dev, bo);
@@ -228,7 +222,7 @@ int tegra_bo_dumb_map_offset(struct drm_file *file, struct drm_device *drm,
 
 	bo = to_tegra_bo(gem);
 
-	*offset = tegra_bo_get_mmap_offset(bo);
+	*offset = drm_vma_node_offset_addr(&bo->gem.vma_node);
 
 	drm_gem_object_unreference(gem);
 
@@ -262,9 +256,3 @@ int tegra_drm_mmap(struct file *file, struct vm_area_struct *vma)
 
 	return ret;
 }
-
-int tegra_bo_dumb_destroy(struct drm_file *file, struct drm_device *drm,
-			  unsigned int handle)
-{
-	return drm_gem_handle_delete(file, handle);
-}
diff --git a/drivers/gpu/host1x/drm/gem.h b/drivers/gpu/host1x/drm/gem.h
index 34de2b486eb7..492533a2dacb 100644
--- a/drivers/gpu/host1x/drm/gem.h
+++ b/drivers/gpu/host1x/drm/gem.h
@@ -44,13 +44,10 @@ struct tegra_bo *tegra_bo_create_with_handle(struct drm_file *file,
 					    unsigned int size,
 					    unsigned int *handle);
 void tegra_bo_free_object(struct drm_gem_object *gem);
-unsigned int tegra_bo_get_mmap_offset(struct tegra_bo *bo);
 int tegra_bo_dumb_create(struct drm_file *file, struct drm_device *drm,
 			 struct drm_mode_create_dumb *args);
 int tegra_bo_dumb_map_offset(struct drm_file *file, struct drm_device *drm,
 			     uint32_t handle, uint64_t *offset);
-int tegra_bo_dumb_destroy(struct drm_file *file, struct drm_device *drm,
-			  unsigned int handle);
 
 int tegra_drm_mmap(struct file *file, struct vm_area_struct *vma);
 
diff --git a/drivers/gpu/host1x/drm/hdmi.c b/drivers/gpu/host1x/drm/hdmi.c
index 01097da09f7f..644d95c7d489 100644
--- a/drivers/gpu/host1x/drm/hdmi.c
+++ b/drivers/gpu/host1x/drm/hdmi.c
@@ -551,24 +551,8 @@ static void tegra_hdmi_setup_stereo_infoframe(struct tegra_hdmi *hdmi)
 		return;
 	}
 
-	memset(&frame, 0, sizeof(frame));
-
-	frame.type = HDMI_INFOFRAME_TYPE_VENDOR;
-	frame.version = 0x01;
-	frame.length = 6;
-
-	frame.data[0] = 0x03; /* regid0 */
-	frame.data[1] = 0x0c; /* regid1 */
-	frame.data[2] = 0x00; /* regid2 */
-	frame.data[3] = 0x02 << 5; /* video format */
-
-	/* TODO: 74 MHz limit? */
-	if (1) {
-		frame.data[4] = 0x00 << 4; /* 3D structure */
-	} else {
-		frame.data[4] = 0x08 << 4; /* 3D structure */
-		frame.data[5] = 0x00 << 4; /* 3D ext. data */
-	}
+	hdmi_vendor_infoframe_init(&frame);
+	frame.s3d_struct = HDMI_3D_STRUCTURE_FRAME_PACKING;
 
 	err = hdmi_vendor_infoframe_pack(&frame, buffer, sizeof(buffer));
 	if (err < 0) {
@@ -904,6 +888,11 @@ static int tegra_hdmi_show_regs(struct seq_file *s, void *data)
 {
 	struct drm_info_node *node = s->private;
 	struct tegra_hdmi *hdmi = node->info_ent->data;
+	int err;
+
+	err = clk_enable(hdmi->clk);
+	if (err)
+		return err;
 
 #define DUMP_REG(name)						\
 	seq_printf(s, "%-56s %#05x %08lx\n", #name, name,	\
@@ -1069,6 +1058,8 @@ static int tegra_hdmi_show_regs(struct seq_file *s, void *data)
 
 #undef DUMP_REG
 
+	clk_disable(hdmi->clk);
+
 	return 0;
 }
 
diff --git a/drivers/gpu/host1x/drm/output.c b/drivers/gpu/host1x/drm/output.c
index 8140fc6c34d8..137ae81ab80e 100644
--- a/drivers/gpu/host1x/drm/output.c
+++ b/drivers/gpu/host1x/drm/output.c
@@ -9,7 +9,7 @@
 
 #include <linux/module.h>
 #include <linux/of_gpio.h>
-#include <linux/of_i2c.h>
+#include <linux/i2c.h>
 
 #include "drm.h"
 
diff --git a/drivers/gpu/host1x/drm/rgb.c b/drivers/gpu/host1x/drm/rgb.c
index ed4416f20260..5aa66ef7a946 100644
--- a/drivers/gpu/host1x/drm/rgb.c
+++ b/drivers/gpu/host1x/drm/rgb.c
@@ -147,6 +147,13 @@ int tegra_dc_rgb_probe(struct tegra_dc *dc)
 	if (!rgb)
 		return -ENOMEM;
 
+	rgb->output.dev = dc->dev;
+	rgb->output.of_node = np;
+
+	err = tegra_output_parse_dt(&rgb->output);
+	if (err < 0)
+		return err;
+
 	rgb->clk = devm_clk_get(dc->dev, NULL);
 	if (IS_ERR(rgb->clk)) {
 		dev_err(dc->dev, "failed to get clock\n");
@@ -165,13 +172,6 @@ int tegra_dc_rgb_probe(struct tegra_dc *dc)
 		return err;
 	}
 
-	rgb->output.dev = dc->dev;
-	rgb->output.of_node = np;
-
-	err = tegra_output_parse_dt(&rgb->output);
-	if (err < 0)
-		return err;
-
 	dc->rgb = &rgb->output;
 
 	return 0;
diff --git a/drivers/gpu/host1x/job.c b/drivers/gpu/host1x/job.c
index cc807667d8f1..c4e1050f2252 100644
--- a/drivers/gpu/host1x/job.c
+++ b/drivers/gpu/host1x/job.c
@@ -42,12 +42,12 @@ struct host1x_job *host1x_job_alloc(struct host1x_channel *ch,
 
 	/* Check that we're not going to overflow */
 	total = sizeof(struct host1x_job) +
-		num_relocs * sizeof(struct host1x_reloc) +
-		num_unpins * sizeof(struct host1x_job_unpin_data) +
-		num_waitchks * sizeof(struct host1x_waitchk) +
-		num_cmdbufs * sizeof(struct host1x_job_gather) +
-		num_unpins * sizeof(dma_addr_t) +
-		num_unpins * sizeof(u32 *);
+		(u64)num_relocs * sizeof(struct host1x_reloc) +
+		(u64)num_unpins * sizeof(struct host1x_job_unpin_data) +
+		(u64)num_waitchks * sizeof(struct host1x_waitchk) +
+		(u64)num_cmdbufs * sizeof(struct host1x_job_gather) +
+		(u64)num_unpins * sizeof(dma_addr_t) +
+		(u64)num_unpins * sizeof(u32 *);
 	if (total > ULONG_MAX)
 		return NULL;
 
@@ -466,9 +466,8 @@ static inline int copy_gathers(struct host1x_job *job, struct device *dev)
 							 &job->gather_copy,
 							 GFP_KERNEL);
 	if (!job->gather_copy_mapped) {
-		int err = PTR_ERR(job->gather_copy_mapped);
 		job->gather_copy_mapped = NULL;
-		return err;
+		return -ENOMEM;
 	}
 
 	job->gather_copy_size = size;
diff --git a/drivers/gpu/vga/vga_switcheroo.c b/drivers/gpu/vga/vga_switcheroo.c
index cf787e1d9322..ec0ae2d1686a 100644
--- a/drivers/gpu/vga/vga_switcheroo.c
+++ b/drivers/gpu/vga/vga_switcheroo.c
@@ -27,6 +27,7 @@
 #include <linux/pci.h>
 #include <linux/console.h>
 #include <linux/vga_switcheroo.h>
+#include <linux/pm_runtime.h>
 
 #include <linux/vgaarb.h>
 
@@ -37,6 +38,7 @@ struct vga_switcheroo_client {
 	const struct vga_switcheroo_client_ops *ops;
 	int id;
 	bool active;
+	bool driver_power_control;
 	struct list_head list;
 };
 
@@ -132,7 +134,7 @@ EXPORT_SYMBOL(vga_switcheroo_unregister_handler);
 
 static int register_client(struct pci_dev *pdev,
 			   const struct vga_switcheroo_client_ops *ops,
-			   int id, bool active)
+			   int id, bool active, bool driver_power_control)
 {
 	struct vga_switcheroo_client *client;
 
@@ -145,6 +147,7 @@ static int register_client(struct pci_dev *pdev,
 	client->ops = ops;
 	client->id = id;
 	client->active = active;
+	client->driver_power_control = driver_power_control;
 
 	mutex_lock(&vgasr_mutex);
 	list_add_tail(&client->list, &vgasr_priv.clients);
@@ -160,10 +163,11 @@ static int register_client(struct pci_dev *pdev,
 }
 
 int vga_switcheroo_register_client(struct pci_dev *pdev,
-				   const struct vga_switcheroo_client_ops *ops)
+				   const struct vga_switcheroo_client_ops *ops,
+				   bool driver_power_control)
 {
 	return register_client(pdev, ops, -1,
-			       pdev == vga_default_device());
+			       pdev == vga_default_device(), driver_power_control);
 }
 EXPORT_SYMBOL(vga_switcheroo_register_client);
 
@@ -171,7 +175,7 @@ int vga_switcheroo_register_audio_client(struct pci_dev *pdev,
 					 const struct vga_switcheroo_client_ops *ops,
 					 int id, bool active)
 {
-	return register_client(pdev, ops, id | ID_BIT_AUDIO, active);
+	return register_client(pdev, ops, id | ID_BIT_AUDIO, active, false);
 }
 EXPORT_SYMBOL(vga_switcheroo_register_audio_client);
 
@@ -258,10 +262,11 @@ static int vga_switcheroo_show(struct seq_file *m, void *v)
 	int i = 0;
 	mutex_lock(&vgasr_mutex);
 	list_for_each_entry(client, &vgasr_priv.clients, list) {
-		seq_printf(m, "%d:%s%s:%c:%s:%s\n", i,
+		seq_printf(m, "%d:%s%s:%c:%s%s:%s\n", i,
 			   client_id(client) == VGA_SWITCHEROO_DIS ? "DIS" : "IGD",
 			   client_is_vga(client) ? "" : "-Audio",
 			   client->active ? '+' : ' ',
+			   client->driver_power_control ? "Dyn" : "",
 			   client->pwr_state ? "Pwr" : "Off",
 			   pci_name(client->pdev));
 		i++;
@@ -277,6 +282,8 @@ static int vga_switcheroo_debugfs_open(struct inode *inode, struct file *file)
 
 static int vga_switchon(struct vga_switcheroo_client *client)
 {
+	if (client->driver_power_control)
+		return 0;
 	if (vgasr_priv.handler->power_state)
 		vgasr_priv.handler->power_state(client->id, VGA_SWITCHEROO_ON);
 	/* call the driver callback to turn on device */
@@ -287,6 +294,8 @@ static int vga_switchon(struct vga_switcheroo_client *client)
 
 static int vga_switchoff(struct vga_switcheroo_client *client)
 {
+	if (client->driver_power_control)
+		return 0;
 	/* call the driver callback to turn off device */
 	client->ops->set_gpu_state(client->pdev, VGA_SWITCHEROO_OFF);
 	if (vgasr_priv.handler->power_state)
@@ -402,6 +411,8 @@ vga_switcheroo_debugfs_write(struct file *filp, const char __user *ubuf,
 		list_for_each_entry(client, &vgasr_priv.clients, list) {
 			if (client->active || client_is_audio(client))
 				continue;
+			if (client->driver_power_control)
+				continue;
 			set_audio_state(client->id, VGA_SWITCHEROO_OFF);
 			if (client->pwr_state == VGA_SWITCHEROO_ON)
 				vga_switchoff(client);
@@ -413,6 +424,8 @@ vga_switcheroo_debugfs_write(struct file *filp, const char __user *ubuf,
 		list_for_each_entry(client, &vgasr_priv.clients, list) {
 			if (client->active || client_is_audio(client))
 				continue;
+			if (client->driver_power_control)
+				continue;
 			if (client->pwr_state == VGA_SWITCHEROO_OFF)
 				vga_switchon(client);
 			set_audio_state(client->id, VGA_SWITCHEROO_ON);
@@ -565,3 +578,127 @@ err:
 	return err;
 }
 EXPORT_SYMBOL(vga_switcheroo_process_delayed_switch);
+
+static void vga_switcheroo_power_switch(struct pci_dev *pdev, enum vga_switcheroo_state state)
+{
+	struct vga_switcheroo_client *client;
+
+	if (!vgasr_priv.handler->power_state)
+		return;
+
+	client = find_client_from_pci(&vgasr_priv.clients, pdev);
+	if (!client)
+		return;
+
+	if (!client->driver_power_control)
+		return;
+
+	vgasr_priv.handler->power_state(client->id, state);
+}
+
+/* force a PCI device to a certain state - mainly to turn off audio clients */
+
+void vga_switcheroo_set_dynamic_switch(struct pci_dev *pdev, enum vga_switcheroo_state dynamic)
+{
+	struct vga_switcheroo_client *client;
+
+	client = find_client_from_pci(&vgasr_priv.clients, pdev);
+	if (!client)
+		return;
+
+	if (!client->driver_power_control)
+		return;
+
+	client->pwr_state = dynamic;
+	set_audio_state(client->id, dynamic);
+}
+EXPORT_SYMBOL(vga_switcheroo_set_dynamic_switch);
+
+/* switcheroo power domain */
+static int vga_switcheroo_runtime_suspend(struct device *dev)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	int ret;
+
+	ret = dev->bus->pm->runtime_suspend(dev);
+	if (ret)
+		return ret;
+
+	vga_switcheroo_power_switch(pdev, VGA_SWITCHEROO_OFF);
+	return 0;
+}
+
+static int vga_switcheroo_runtime_resume(struct device *dev)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	int ret;
+
+	vga_switcheroo_power_switch(pdev, VGA_SWITCHEROO_ON);
+	ret = dev->bus->pm->runtime_resume(dev);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+/* this version is for the case where the power switch is separate
+   to the device being powered down. */
+int vga_switcheroo_init_domain_pm_ops(struct device *dev, struct dev_pm_domain *domain)
+{
+	/* copy over all the bus versions */
+	if (dev->bus && dev->bus->pm) {
+		domain->ops = *dev->bus->pm;
+		domain->ops.runtime_suspend = vga_switcheroo_runtime_suspend;
+		domain->ops.runtime_resume = vga_switcheroo_runtime_resume;
+
+		dev->pm_domain = domain;
+		return 0;
+	}
+	dev->pm_domain = NULL;
+	return -EINVAL;
+}
+EXPORT_SYMBOL(vga_switcheroo_init_domain_pm_ops);
+
+static int vga_switcheroo_runtime_resume_hdmi_audio(struct device *dev)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	int ret;
+	struct vga_switcheroo_client *client, *found = NULL;
+
+	/* we need to check if we have to switch back on the video
+	   device so the audio device can come back */
+	list_for_each_entry(client, &vgasr_priv.clients, list) {
+		if (PCI_SLOT(client->pdev->devfn) == PCI_SLOT(pdev->devfn) && client_is_vga(client)) {
+			found = client;
+			ret = pm_runtime_get_sync(&client->pdev->dev);
+			if (ret) {
+				if (ret != 1)
+					return ret;
+			}
+			break;
+		}
+	}
+	ret = dev->bus->pm->runtime_resume(dev);
+
+	/* put the reference for the gpu */
+	if (found) {
+		pm_runtime_mark_last_busy(&found->pdev->dev);
+		pm_runtime_put_autosuspend(&found->pdev->dev);
+	}
+	return ret;
+}
+
+int vga_switcheroo_init_domain_pm_optimus_hdmi_audio(struct device *dev, struct dev_pm_domain *domain)
+{
+	/* copy over all the bus versions */
+	if (dev->bus && dev->bus->pm) {
+		domain->ops = *dev->bus->pm;
+		domain->ops.runtime_resume = vga_switcheroo_runtime_resume_hdmi_audio;
+
+		dev->pm_domain = domain;
+		return 0;
+	}
+	dev->pm_domain = NULL;
+	return -EINVAL;
+}
+EXPORT_SYMBOL(vga_switcheroo_init_domain_pm_optimus_hdmi_audio);
diff --git a/drivers/gpu/vga/vgaarb.c b/drivers/gpu/vga/vgaarb.c
index e893f6e1937d..af0259708358 100644
--- a/drivers/gpu/vga/vgaarb.c
+++ b/drivers/gpu/vga/vgaarb.c
@@ -257,9 +257,9 @@ static struct vga_device *__vga_tryget(struct vga_device *vgadev,
 		if (!conflict->bridge_has_one_vga) {
 			vga_irq_set_state(conflict, false);
 			flags |= PCI_VGA_STATE_CHANGE_DECODES;
-			if (lwants & (VGA_RSRC_LEGACY_MEM|VGA_RSRC_NORMAL_MEM))
+			if (match & (VGA_RSRC_LEGACY_MEM|VGA_RSRC_NORMAL_MEM))
 				pci_bits |= PCI_COMMAND_MEMORY;
-			if (lwants & (VGA_RSRC_LEGACY_IO|VGA_RSRC_NORMAL_IO))
+			if (match & (VGA_RSRC_LEGACY_IO|VGA_RSRC_NORMAL_IO))
 				pci_bits |= PCI_COMMAND_IO;
 		}
 
@@ -267,11 +267,11 @@ static struct vga_device *__vga_tryget(struct vga_device *vgadev,
 			flags |= PCI_VGA_STATE_CHANGE_BRIDGE;
 
 		pci_set_vga_state(conflict->pdev, false, pci_bits, flags);
-		conflict->owns &= ~lwants;
+		conflict->owns &= ~match;
 		/* If he also owned non-legacy, that is no longer the case */
-		if (lwants & VGA_RSRC_LEGACY_MEM)
+		if (match & VGA_RSRC_LEGACY_MEM)
 			conflict->owns &= ~VGA_RSRC_NORMAL_MEM;
-		if (lwants & VGA_RSRC_LEGACY_IO)
+		if (match & VGA_RSRC_LEGACY_IO)
 			conflict->owns &= ~VGA_RSRC_NORMAL_IO;
 	}
 
@@ -644,10 +644,12 @@ bail:
 static inline void vga_update_device_decodes(struct vga_device *vgadev,
 					     int new_decodes)
 {
-	int old_decodes;
-	struct vga_device *new_vgadev, *conflict;
+	int old_decodes, decodes_removed, decodes_unlocked;
 
 	old_decodes = vgadev->decodes;
+	decodes_removed = ~new_decodes & old_decodes;
+	decodes_unlocked = vgadev->locks & decodes_removed;
+	vgadev->owns &= ~decodes_removed;
 	vgadev->decodes = new_decodes;
 
 	pr_info("vgaarb: device changed decodes: PCI:%s,olddecodes=%s,decodes=%s:owns=%s\n",
@@ -656,31 +658,22 @@ static inline void vga_update_device_decodes(struct vga_device *vgadev,
 		vga_iostate_to_str(vgadev->decodes),
 		vga_iostate_to_str(vgadev->owns));
 
-
-	/* if we own the decodes we should move them along to
-	   another card */
-	if ((vgadev->owns & old_decodes) && (vga_count > 1)) {
-		/* set us to own nothing */
-		vgadev->owns &= ~old_decodes;
-		list_for_each_entry(new_vgadev, &vga_list, list) {
-			if ((new_vgadev != vgadev) &&
-			    (new_vgadev->decodes & VGA_RSRC_LEGACY_MASK)) {
-				pr_info("vgaarb: transferring owner from PCI:%s to PCI:%s\n", pci_name(vgadev->pdev), pci_name(new_vgadev->pdev));
-				conflict = __vga_tryget(new_vgadev, VGA_RSRC_LEGACY_MASK);
-				if (!conflict)
-					__vga_put(new_vgadev, VGA_RSRC_LEGACY_MASK);
-				break;
-			}
-		}
+	/* if we removed locked decodes, lock count goes to zero, and release */
+	if (decodes_unlocked) {
+		if (decodes_unlocked & VGA_RSRC_LEGACY_IO)
+			vgadev->io_lock_cnt = 0;
+		if (decodes_unlocked & VGA_RSRC_LEGACY_MEM)
+			vgadev->mem_lock_cnt = 0;
+		__vga_put(vgadev, decodes_unlocked);
 	}
 
 	/* change decodes counter */
-	if (old_decodes != new_decodes) {
-		if (new_decodes & (VGA_RSRC_LEGACY_IO | VGA_RSRC_LEGACY_MEM))
-			vga_decode_count++;
-		else
-			vga_decode_count--;
-	}
+	if (old_decodes & VGA_RSRC_LEGACY_MASK &&
+	    !(new_decodes & VGA_RSRC_LEGACY_MASK))
+		vga_decode_count--;
+	if (!(old_decodes & VGA_RSRC_LEGACY_MASK) &&
+	    new_decodes & VGA_RSRC_LEGACY_MASK)
+		vga_decode_count++;
 	pr_debug("vgaarb: decoding count now is: %d\n", vga_decode_count);
 }
 
diff --git a/drivers/hid/Kconfig b/drivers/hid/Kconfig
index 14ef6ab69790..c91d547191dd 100644
--- a/drivers/hid/Kconfig
+++ b/drivers/hid/Kconfig
@@ -241,6 +241,7 @@ config HID_HOLTEK
 	  - Sharkoon Drakonia / Perixx MX-2000 gaming mice
 	  - Tracer Sniper TRM-503 / NOVA Gaming Slider X200 /
 	    Zalman ZM-GM1
+	  - SHARKOON DarkGlider Gaming mouse
 
 config HOLTEK_FF
 	bool "Holtek On Line Grip force feedback support"
@@ -743,6 +744,14 @@ config HID_WIIMOTE
 	To compile this driver as a module, choose M here: the
 	module will be called hid-wiimote.
 
+config HID_XINMO
+	tristate "Xin-Mo non-fully compliant devices"
+	depends on HID
+	---help---
+	Support for Xin-Mo devices that are not fully compliant with the HID
+	standard. Currently only supports the Xin-Mo Dual Arcade. Say Y here
+	if you have a Xin-Mo Dual Arcade controller.
+
 config HID_ZEROPLUS
 	tristate "Zeroplus based game controller support"
 	depends on HID
@@ -765,7 +774,7 @@ config HID_ZYDACRON
 
 config HID_SENSOR_HUB
 	tristate "HID Sensors framework support"
-	depends on HID && GENERIC_HARDIRQS
+	depends on HID
 	select MFD_CORE
 	default n
 	---help---
diff --git a/drivers/hid/Makefile b/drivers/hid/Makefile
index 6f687287e212..a959f4aecaf5 100644
--- a/drivers/hid/Makefile
+++ b/drivers/hid/Makefile
@@ -110,6 +110,7 @@ obj-$(CONFIG_HID_TIVO)		+= hid-tivo.o
 obj-$(CONFIG_HID_TOPSEED)	+= hid-topseed.o
 obj-$(CONFIG_HID_TWINHAN)	+= hid-twinhan.o
 obj-$(CONFIG_HID_UCLOGIC)	+= hid-uclogic.o
+obj-$(CONFIG_HID_XINMO)		+= hid-xinmo.o
 obj-$(CONFIG_HID_ZEROPLUS)	+= hid-zpff.o
 obj-$(CONFIG_HID_ZYDACRON)	+= hid-zydacron.o
 obj-$(CONFIG_HID_WACOM)		+= hid-wacom.o
diff --git a/drivers/hid/hid-a4tech.c b/drivers/hid/hid-a4tech.c
index 7c5507e94820..9428ea7cdf8a 100644
--- a/drivers/hid/hid-a4tech.c
+++ b/drivers/hid/hid-a4tech.c
@@ -90,11 +90,10 @@ static int a4_probe(struct hid_device *hdev, const struct hid_device_id *id)
 	struct a4tech_sc *a4;
 	int ret;
 
-	a4 = kzalloc(sizeof(*a4), GFP_KERNEL);
+	a4 = devm_kzalloc(&hdev->dev, sizeof(*a4), GFP_KERNEL);
 	if (a4 == NULL) {
 		hid_err(hdev, "can't alloc device descriptor\n");
-		ret = -ENOMEM;
-		goto err_free;
+		return -ENOMEM;
 	}
 
 	a4->quirks = id->driver_data;
@@ -104,27 +103,16 @@ static int a4_probe(struct hid_device *hdev, const struct hid_device_id *id)
 	ret = hid_parse(hdev);
 	if (ret) {
 		hid_err(hdev, "parse failed\n");
-		goto err_free;
+		return ret;
 	}
 
 	ret = hid_hw_start(hdev, HID_CONNECT_DEFAULT);
 	if (ret) {
 		hid_err(hdev, "hw start failed\n");
-		goto err_free;
+		return ret;
 	}
 
 	return 0;
-err_free:
-	kfree(a4);
-	return ret;
-}
-
-static void a4_remove(struct hid_device *hdev)
-{
-	struct a4tech_sc *a4 = hid_get_drvdata(hdev);
-
-	hid_hw_stop(hdev);
-	kfree(a4);
 }
 
 static const struct hid_device_id a4_devices[] = {
@@ -144,7 +132,6 @@ static struct hid_driver a4_driver = {
 	.input_mapped = a4_input_mapped,
 	.event = a4_event,
 	.probe = a4_probe,
-	.remove = a4_remove,
 };
 module_hid_driver(a4_driver);
 
diff --git a/drivers/hid/hid-apple.c b/drivers/hid/hid-apple.c
index c7710b5c69af..881cf7b4f9a4 100644
--- a/drivers/hid/hid-apple.c
+++ b/drivers/hid/hid-apple.c
@@ -349,7 +349,7 @@ static int apple_probe(struct hid_device *hdev,
 	unsigned int connect_mask = HID_CONNECT_DEFAULT;
 	int ret;
 
-	asc = kzalloc(sizeof(*asc), GFP_KERNEL);
+	asc = devm_kzalloc(&hdev->dev, sizeof(*asc), GFP_KERNEL);
 	if (asc == NULL) {
 		hid_err(hdev, "can't alloc apple descriptor\n");
 		return -ENOMEM;
@@ -362,7 +362,7 @@ static int apple_probe(struct hid_device *hdev,
 	ret = hid_parse(hdev);
 	if (ret) {
 		hid_err(hdev, "parse failed\n");
-		goto err_free;
+		return ret;
 	}
 
 	if (quirks & APPLE_HIDDEV)
@@ -373,19 +373,10 @@ static int apple_probe(struct hid_device *hdev,
 	ret = hid_hw_start(hdev, connect_mask);
 	if (ret) {
 		hid_err(hdev, "hw start failed\n");
-		goto err_free;
+		return ret;
 	}
 
 	return 0;
-err_free:
-	kfree(asc);
-	return ret;
-}
-
-static void apple_remove(struct hid_device *hdev)
-{
-	hid_hw_stop(hdev);
-	kfree(hid_get_drvdata(hdev));
 }
 
 static const struct hid_device_id apple_devices[] = {
@@ -551,7 +542,6 @@ static struct hid_driver apple_driver = {
 	.id_table = apple_devices,
 	.report_fixup = apple_report_fixup,
 	.probe = apple_probe,
-	.remove = apple_remove,
 	.event = apple_event,
 	.input_mapping = apple_input_mapping,
 	.input_mapped = apple_input_mapped,
diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c
index 36668d1aca8f..5a8c01112a23 100644
--- a/drivers/hid/hid-core.c
+++ b/drivers/hid/hid-core.c
@@ -63,6 +63,8 @@ struct hid_report *hid_register_report(struct hid_device *device, unsigned type,
 	struct hid_report_enum *report_enum = device->report_enum + type;
 	struct hid_report *report;
 
+	if (id >= HID_MAX_IDS)
+		return NULL;
 	if (report_enum->report_id_hash[id])
 		return report_enum->report_id_hash[id];
 
@@ -92,7 +94,6 @@ EXPORT_SYMBOL_GPL(hid_register_report);
 static struct hid_field *hid_register_field(struct hid_report *report, unsigned usages, unsigned values)
 {
 	struct hid_field *field;
-	int i;
 
 	if (report->maxfield == HID_MAX_FIELDS) {
 		hid_err(report->device, "too many fields in report\n");
@@ -111,9 +112,6 @@ static struct hid_field *hid_register_field(struct hid_report *report, unsigned
 	field->value = (s32 *)(field->usage + usages);
 	field->report = report;
 
-	for (i = 0; i < usages; i++)
-		field->usage[i].usage_index = i;
-
 	return field;
 }
 
@@ -224,9 +222,9 @@ static int hid_add_field(struct hid_parser *parser, unsigned report_type, unsign
 {
 	struct hid_report *report;
 	struct hid_field *field;
-	int usages;
+	unsigned usages;
 	unsigned offset;
-	int i;
+	unsigned i;
 
 	report = hid_register_report(parser->device, report_type, parser->global.report_id);
 	if (!report) {
@@ -253,7 +251,8 @@ static int hid_add_field(struct hid_parser *parser, unsigned report_type, unsign
 	if (!parser->local.usage_index) /* Ignore padding fields */
 		return 0;
 
-	usages = max_t(int, parser->local.usage_index, parser->global.report_count);
+	usages = max_t(unsigned, parser->local.usage_index,
+				 parser->global.report_count);
 
 	field = hid_register_field(report, usages, parser->global.report_count);
 	if (!field)
@@ -264,13 +263,14 @@ static int hid_add_field(struct hid_parser *parser, unsigned report_type, unsign
 	field->application = hid_lookup_collection(parser, HID_COLLECTION_APPLICATION);
 
 	for (i = 0; i < usages; i++) {
-		int j = i;
+		unsigned j = i;
 		/* Duplicate the last usage we parsed if we have excess values */
 		if (i >= parser->local.usage_index)
 			j = parser->local.usage_index - 1;
 		field->usage[i].hid = parser->local.usage[j];
 		field->usage[i].collection_index =
 			parser->local.collection_index[j];
+		field->usage[i].usage_index = i;
 	}
 
 	field->maxusage = usages;
@@ -404,8 +404,10 @@ static int hid_parser_global(struct hid_parser *parser, struct hid_item *item)
 
 	case HID_GLOBAL_ITEM_TAG_REPORT_ID:
 		parser->global.report_id = item_udata(item);
-		if (parser->global.report_id == 0) {
-			hid_err(parser->device, "report_id 0 is invalid\n");
+		if (parser->global.report_id == 0 ||
+		    parser->global.report_id >= HID_MAX_IDS) {
+			hid_err(parser->device, "report_id %u is invalid\n",
+				parser->global.report_id);
 			return -1;
 		}
 		return 0;
@@ -450,7 +452,7 @@ static int hid_parser_local(struct hid_parser *parser, struct hid_item *item)
 			}
 			parser->local.delimiter_depth--;
 		}
-		return 1;
+		return 0;
 
 	case HID_LOCAL_ITEM_TAG_USAGE:
 
@@ -575,7 +577,7 @@ static void hid_close_report(struct hid_device *device)
 	for (i = 0; i < HID_REPORT_TYPES; i++) {
 		struct hid_report_enum *report_enum = device->report_enum + i;
 
-		for (j = 0; j < 256; j++) {
+		for (j = 0; j < HID_MAX_IDS; j++) {
 			struct hid_report *report = report_enum->report_id_hash[j];
 			if (report)
 				hid_free_report(report);
@@ -677,12 +679,61 @@ static u8 *fetch_item(__u8 *start, __u8 *end, struct hid_item *item)
 	return NULL;
 }
 
-static void hid_scan_usage(struct hid_device *hid, u32 usage)
+static void hid_scan_input_usage(struct hid_parser *parser, u32 usage)
 {
+	struct hid_device *hid = parser->device;
+
 	if (usage == HID_DG_CONTACTID)
 		hid->group = HID_GROUP_MULTITOUCH;
 }
 
+static void hid_scan_feature_usage(struct hid_parser *parser, u32 usage)
+{
+	if (usage == 0xff0000c5 && parser->global.report_count == 256 &&
+	    parser->global.report_size == 8)
+		parser->scan_flags |= HID_SCAN_FLAG_MT_WIN_8;
+}
+
+static void hid_scan_collection(struct hid_parser *parser, unsigned type)
+{
+	struct hid_device *hid = parser->device;
+
+	if (((parser->global.usage_page << 16) == HID_UP_SENSOR) &&
+	    type == HID_COLLECTION_PHYSICAL)
+		hid->group = HID_GROUP_SENSOR_HUB;
+}
+
+static int hid_scan_main(struct hid_parser *parser, struct hid_item *item)
+{
+	__u32 data;
+	int i;
+
+	data = item_udata(item);
+
+	switch (item->tag) {
+	case HID_MAIN_ITEM_TAG_BEGIN_COLLECTION:
+		hid_scan_collection(parser, data & 0xff);
+		break;
+	case HID_MAIN_ITEM_TAG_END_COLLECTION:
+		break;
+	case HID_MAIN_ITEM_TAG_INPUT:
+		for (i = 0; i < parser->local.usage_index; i++)
+			hid_scan_input_usage(parser, parser->local.usage[i]);
+		break;
+	case HID_MAIN_ITEM_TAG_OUTPUT:
+		break;
+	case HID_MAIN_ITEM_TAG_FEATURE:
+		for (i = 0; i < parser->local.usage_index; i++)
+			hid_scan_feature_usage(parser, parser->local.usage[i]);
+		break;
+	}
+
+	/* Reset the local parser environment */
+	memset(&parser->local, 0, sizeof(parser->local));
+
+	return 0;
+}
+
 /*
  * Scan a report descriptor before the device is added to the bus.
  * Sets device groups and other properties that determine what driver
@@ -690,48 +741,41 @@ static void hid_scan_usage(struct hid_device *hid, u32 usage)
  */
 static int hid_scan_report(struct hid_device *hid)
 {
-	unsigned int page = 0, delim = 0;
+	struct hid_parser *parser;
+	struct hid_item item;
 	__u8 *start = hid->dev_rdesc;
 	__u8 *end = start + hid->dev_rsize;
-	unsigned int u, u_min = 0, u_max = 0;
-	struct hid_item item;
+	static int (*dispatch_type[])(struct hid_parser *parser,
+				      struct hid_item *item) = {
+		hid_scan_main,
+		hid_parser_global,
+		hid_parser_local,
+		hid_parser_reserved
+	};
+
+	parser = vzalloc(sizeof(struct hid_parser));
+	if (!parser)
+		return -ENOMEM;
 
+	parser->device = hid;
 	hid->group = HID_GROUP_GENERIC;
-	while ((start = fetch_item(start, end, &item)) != NULL) {
-		if (item.format != HID_ITEM_FORMAT_SHORT)
-			return -EINVAL;
-		if (item.type == HID_ITEM_TYPE_GLOBAL) {
-			if (item.tag == HID_GLOBAL_ITEM_TAG_USAGE_PAGE)
-				page = item_udata(&item) << 16;
-		} else if (item.type == HID_ITEM_TYPE_LOCAL) {
-			if (delim > 1)
-				break;
-			u = item_udata(&item);
-			if (item.size <= 2)
-				u += page;
-			switch (item.tag) {
-			case HID_LOCAL_ITEM_TAG_DELIMITER:
-				delim += !!u;
-				break;
-			case HID_LOCAL_ITEM_TAG_USAGE:
-				hid_scan_usage(hid, u);
-				break;
-			case HID_LOCAL_ITEM_TAG_USAGE_MINIMUM:
-				u_min = u;
-				break;
-			case HID_LOCAL_ITEM_TAG_USAGE_MAXIMUM:
-				u_max = u;
-				for (u = u_min; u <= u_max; u++)
-					hid_scan_usage(hid, u);
-				break;
-			}
-		} else if (page == HID_UP_SENSOR &&
-			item.type == HID_ITEM_TYPE_MAIN &&
-			item.tag == HID_MAIN_ITEM_TAG_BEGIN_COLLECTION &&
-			(item_udata(&item) & 0xff) == HID_COLLECTION_PHYSICAL)
-			hid->group = HID_GROUP_SENSOR_HUB;
-	}
 
+	/*
+	 * The parsing is simpler than the one in hid_open_report() as we should
+	 * be robust against hid errors. Those errors will be raised by
+	 * hid_open_report() anyway.
+	 */
+	while ((start = fetch_item(start, end, &item)) != NULL)
+		dispatch_type[item.type](parser, &item);
+
+	/*
+	 * Handle special flags set during scanning.
+	 */
+	if ((parser->scan_flags & HID_SCAN_FLAG_MT_WIN_8) &&
+	    (hid->group == HID_GROUP_MULTITOUCH))
+		hid->group = HID_GROUP_MULTITOUCH_WIN_8;
+
+	vfree(parser);
 	return 0;
 }
 
@@ -755,6 +799,64 @@ int hid_parse_report(struct hid_device *hid, __u8 *start, unsigned size)
 }
 EXPORT_SYMBOL_GPL(hid_parse_report);
 
+static const char * const hid_report_names[] = {
+	"HID_INPUT_REPORT",
+	"HID_OUTPUT_REPORT",
+	"HID_FEATURE_REPORT",
+};
+/**
+ * hid_validate_values - validate existing device report's value indexes
+ *
+ * @device: hid device
+ * @type: which report type to examine
+ * @id: which report ID to examine (0 for first)
+ * @field_index: which report field to examine
+ * @report_counts: expected number of values
+ *
+ * Validate the number of values in a given field of a given report, after
+ * parsing.
+ */
+struct hid_report *hid_validate_values(struct hid_device *hid,
+				       unsigned int type, unsigned int id,
+				       unsigned int field_index,
+				       unsigned int report_counts)
+{
+	struct hid_report *report;
+
+	if (type > HID_FEATURE_REPORT) {
+		hid_err(hid, "invalid HID report type %u\n", type);
+		return NULL;
+	}
+
+	if (id >= HID_MAX_IDS) {
+		hid_err(hid, "invalid HID report id %u\n", id);
+		return NULL;
+	}
+
+	/*
+	 * Explicitly not using hid_get_report() here since it depends on
+	 * ->numbered being checked, which may not always be the case when
+	 * drivers go to access report values.
+	 */
+	report = hid->report_enum[type].report_id_hash[id];
+	if (!report) {
+		hid_err(hid, "missing %s %u\n", hid_report_names[type], id);
+		return NULL;
+	}
+	if (report->maxfield <= field_index) {
+		hid_err(hid, "not enough fields in %s %u\n",
+			hid_report_names[type], id);
+		return NULL;
+	}
+	if (report->field[field_index]->report_count < report_counts) {
+		hid_err(hid, "not enough values in %s %u field %u\n",
+			hid_report_names[type], id, field_index);
+		return NULL;
+	}
+	return report;
+}
+EXPORT_SYMBOL_GPL(hid_validate_values);
+
 /**
  * hid_open_report - open a driver-specific device report
  *
@@ -1128,7 +1230,8 @@ static void hid_output_field(const struct hid_device *hid,
 }
 
 /*
- * Create a report.
+ * Create a report. 'data' has to be allocated using
+ * hid_alloc_report_buf() so that it has proper size.
  */
 
 void hid_output_report(struct hid_report *report, __u8 *data)
@@ -1145,6 +1248,22 @@ void hid_output_report(struct hid_report *report, __u8 *data)
 EXPORT_SYMBOL_GPL(hid_output_report);
 
 /*
+ * Allocator for buffer that is going to be passed to hid_output_report()
+ */
+u8 *hid_alloc_report_buf(struct hid_report *report, gfp_t flags)
+{
+	/*
+	 * 7 extra bytes are necessary to achieve proper functionality
+	 * of implement() working on 8 byte chunks
+	 */
+
+	int len = ((report->size - 1) >> 3) + 1 + (report->id > 0) + 7;
+
+	return kmalloc(len, flags);
+}
+EXPORT_SYMBOL_GPL(hid_alloc_report_buf);
+
+/*
  * Set a field value. The report this field belongs to has to be
  * created and transferred to the device, to set this value in the
  * device.
@@ -1152,7 +1271,12 @@ EXPORT_SYMBOL_GPL(hid_output_report);
 
 int hid_set_field(struct hid_field *field, unsigned offset, __s32 value)
 {
-	unsigned size = field->report_size;
+	unsigned size;
+
+	if (!field)
+		return -1;
+
+	size = field->report_size;
 
 	hid_dump_input(field->report->device, field->usage + offset, value);
 
@@ -1228,7 +1352,7 @@ int hid_report_raw_event(struct hid_device *hid, int type, u8 *data, int size,
 			goto out;
 	}
 
-	if (hid->claimed != HID_CLAIMED_HIDRAW) {
+	if (hid->claimed != HID_CLAIMED_HIDRAW && report->maxfield) {
 		for (a = 0; a < report->maxfield; a++)
 			hid_input_field(hid, report->field[a], cdata, interrupt);
 		hdrv = hid->driver;
@@ -1591,12 +1715,14 @@ static const struct hid_device_id hid_have_special_driver[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_HOLTEK_ALT, USB_DEVICE_ID_HOLTEK_ALT_KEYBOARD) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_HOLTEK_ALT, USB_DEVICE_ID_HOLTEK_ALT_MOUSE_A04A) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_HOLTEK_ALT, USB_DEVICE_ID_HOLTEK_ALT_MOUSE_A067) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_HOLTEK_ALT, USB_DEVICE_ID_HOLTEK_ALT_MOUSE_A081) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_HUION, USB_DEVICE_ID_HUION_580) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_JESS2, USB_DEVICE_ID_JESS2_COLOR_RUMBLE_PAD) },
 	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_ION, USB_DEVICE_ID_ICADE) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_KENSINGTON, USB_DEVICE_ID_KS_SLIMBLADE) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_KEYTOUCH, USB_DEVICE_ID_KEYTOUCH_IEC) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_GENIUS_GILA_GAMING_MOUSE) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_GENIUS_GX_IMPERATOR) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_ERGO_525V) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_EASYPEN_I405X) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_MOUSEPEN_I608X) },
@@ -1679,6 +1805,7 @@ static const struct hid_device_id hid_have_special_driver[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ROCCAT, USB_DEVICE_ID_ROCCAT_ISKU) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ROCCAT, USB_DEVICE_ID_ROCCAT_KONEPLUS) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ROCCAT, USB_DEVICE_ID_ROCCAT_KONEPURE) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_ROCCAT, USB_DEVICE_ID_ROCCAT_KONEPURE_OPTICAL) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ROCCAT, USB_DEVICE_ID_ROCCAT_KOVAPLUS) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ROCCAT, USB_DEVICE_ID_ROCCAT_LUA) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ROCCAT, USB_DEVICE_ID_ROCCAT_PYRA_WIRED) },
@@ -1736,6 +1863,7 @@ static const struct hid_device_id hid_have_special_driver[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_WALTOP, USB_DEVICE_ID_WALTOP_MEDIA_TABLET_14_1_INCH) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_WALTOP, USB_DEVICE_ID_WALTOP_SIRIUS_BATTERY_FREE_TABLET) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_X_TENSIONS, USB_DEVICE_ID_SPEEDLINK_VAD_CEZANNE) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_XIN_MO, USB_DEVICE_ID_XIN_MO_DUAL_ARCADE) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ZEROPLUS, 0x0005) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ZEROPLUS, 0x0030) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ZYDACRON, USB_DEVICE_ID_ZYDACRON_REMOTE_CONTROL) },
@@ -1917,11 +2045,13 @@ static ssize_t modalias_show(struct device *dev, struct device_attribute *a,
 
 	return (len >= PAGE_SIZE) ? (PAGE_SIZE - 1) : len;
 }
+static DEVICE_ATTR_RO(modalias);
 
-static struct device_attribute hid_dev_attrs[] = {
-	__ATTR_RO(modalias),
-	__ATTR_NULL,
+static struct attribute *hid_dev_attrs[] = {
+	&dev_attr_modalias.attr,
+	NULL,
 };
+ATTRIBUTE_GROUPS(hid_dev);
 
 static int hid_uevent(struct device *dev, struct kobj_uevent_env *env)
 {
@@ -1949,7 +2079,7 @@ static int hid_uevent(struct device *dev, struct kobj_uevent_env *env)
 
 static struct bus_type hid_bus_type = {
 	.name		= "hid",
-	.dev_attrs	= hid_dev_attrs,
+	.dev_groups	= hid_dev_groups,
 	.match		= hid_bus_match,
 	.probe		= hid_device_probe,
 	.remove		= hid_device_remove,
diff --git a/drivers/hid/hid-holtek-mouse.c b/drivers/hid/hid-holtek-mouse.c
index 7e6db3cf46f9..e696566cde46 100644
--- a/drivers/hid/hid-holtek-mouse.c
+++ b/drivers/hid/hid-holtek-mouse.c
@@ -27,6 +27,7 @@
  * - USB ID 04d9:a067, sold as Sharkoon Drakonia and Perixx MX-2000
  * - USB ID 04d9:a04a, sold as Tracer Sniper TRM-503, NOVA Gaming Slider X200
  *   and Zalman ZM-GM1
+ * - USB ID 04d9:a081, sold as SHARKOON DarkGlider Gaming mouse
  */
 
 static __u8 *holtek_mouse_report_fixup(struct hid_device *hdev, __u8 *rdesc,
@@ -46,6 +47,7 @@ static __u8 *holtek_mouse_report_fixup(struct hid_device *hdev, __u8 *rdesc,
 			}
 			break;
 		case USB_DEVICE_ID_HOLTEK_ALT_MOUSE_A04A:
+		case USB_DEVICE_ID_HOLTEK_ALT_MOUSE_A081:
 			if (*rsize >= 113 && rdesc[106] == 0xff && rdesc[107] == 0x7f
 					&& rdesc[111] == 0xff && rdesc[112] == 0x7f) {
 				hid_info(hdev, "Fixing up report descriptor\n");
@@ -63,6 +65,8 @@ static const struct hid_device_id holtek_mouse_devices[] = {
 			USB_DEVICE_ID_HOLTEK_ALT_MOUSE_A067) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_HOLTEK_ALT,
 			USB_DEVICE_ID_HOLTEK_ALT_MOUSE_A04A) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_HOLTEK_ALT,
+			USB_DEVICE_ID_HOLTEK_ALT_MOUSE_A081) },
 	{ }
 };
 MODULE_DEVICE_TABLE(hid, holtek_mouse_devices);
diff --git a/drivers/hid/hid-holtekff.c b/drivers/hid/hid-holtekff.c
index 9a8f05124525..9325545fc3ae 100644
--- a/drivers/hid/hid-holtekff.c
+++ b/drivers/hid/hid-holtekff.c
@@ -98,7 +98,7 @@ static void holtekff_send(struct holtekff_device *holtekff,
 		holtekff->field->value[i] = data[i];
 	}
 
-	dbg_hid("sending %*ph\n", 7, data);
+	dbg_hid("sending %7ph\n", data);
 
 	hid_hw_request(hid, holtekff->field->report, HID_REQ_SET_REPORT);
 }
diff --git a/drivers/hid/hid-hyperv.c b/drivers/hid/hid-hyperv.c
index 713217380b44..8fae6d1414cc 100644
--- a/drivers/hid/hid-hyperv.c
+++ b/drivers/hid/hid-hyperv.c
@@ -590,6 +590,5 @@ static void __exit mousevsc_exit(void)
 }
 
 MODULE_LICENSE("GPL");
-MODULE_VERSION(HV_DRV_VERSION);
 module_init(mousevsc_init);
 module_exit(mousevsc_exit);
diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index ffe4c7ae3340..9cbc7ab07dfa 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -135,9 +135,9 @@
 #define USB_DEVICE_ID_APPLE_ALU_WIRELESS_2009_JIS   0x023b
 #define USB_DEVICE_ID_APPLE_ALU_WIRELESS_2011_ANSI  0x0255
 #define USB_DEVICE_ID_APPLE_ALU_WIRELESS_2011_ISO   0x0256
-#define USB_DEVICE_ID_APPLE_WELLSPRING8_ANSI	0x0291
-#define USB_DEVICE_ID_APPLE_WELLSPRING8_ISO	0x0292
-#define USB_DEVICE_ID_APPLE_WELLSPRING8_JIS	0x0293
+#define USB_DEVICE_ID_APPLE_WELLSPRING8_ANSI	0x0290
+#define USB_DEVICE_ID_APPLE_WELLSPRING8_ISO	0x0291
+#define USB_DEVICE_ID_APPLE_WELLSPRING8_JIS	0x0292
 #define USB_DEVICE_ID_APPLE_FOUNTAIN_TP_ONLY	0x030a
 #define USB_DEVICE_ID_APPLE_GEYSER1_TP_ONLY	0x030b
 #define USB_DEVICE_ID_APPLE_IRCONTROL	0x8240
@@ -450,6 +450,7 @@
 #define USB_DEVICE_ID_HOLTEK_ALT_KEYBOARD	0xa055
 #define USB_DEVICE_ID_HOLTEK_ALT_MOUSE_A067	0xa067
 #define USB_DEVICE_ID_HOLTEK_ALT_MOUSE_A04A	0xa04a
+#define USB_DEVICE_ID_HOLTEK_ALT_MOUSE_A081	0xa081
 
 #define USB_VENDOR_ID_IMATION		0x0718
 #define USB_DEVICE_ID_DISC_STAKKA	0xd000
@@ -482,6 +483,7 @@
 #define USB_VENDOR_ID_KYE		0x0458
 #define USB_DEVICE_ID_KYE_ERGO_525V	0x0087
 #define USB_DEVICE_ID_GENIUS_GILA_GAMING_MOUSE	0x0138
+#define USB_DEVICE_ID_GENIUS_GX_IMPERATOR	0x4018
 #define USB_DEVICE_ID_KYE_GPEN_560	0x5003
 #define USB_DEVICE_ID_KYE_EASYPEN_I405X	0x5010
 #define USB_DEVICE_ID_KYE_MOUSEPEN_I608X	0x5011
@@ -658,6 +660,7 @@
 #define USB_DEVICE_ID_NTRIG_TOUCH_SCREEN_16   0x0012
 #define USB_DEVICE_ID_NTRIG_TOUCH_SCREEN_17   0x0013
 #define USB_DEVICE_ID_NTRIG_TOUCH_SCREEN_18   0x0014
+#define USB_DEVICE_ID_NTRIG_DUOSENSE 0x1500
 
 #define USB_VENDOR_ID_ONTRAK		0x0a07
 #define USB_DEVICE_ID_ONTRAK_ADU100	0x0064
@@ -716,6 +719,7 @@
 #define USB_DEVICE_ID_ROCCAT_KONE	0x2ced
 #define USB_DEVICE_ID_ROCCAT_KONEPLUS	0x2d51
 #define USB_DEVICE_ID_ROCCAT_KONEPURE	0x2dbe
+#define USB_DEVICE_ID_ROCCAT_KONEPURE_OPTICAL	0x2db4
 #define USB_DEVICE_ID_ROCCAT_KONEXTD	0x2e22
 #define USB_DEVICE_ID_ROCCAT_KOVAPLUS	0x2d50
 #define USB_DEVICE_ID_ROCCAT_LUA	0x2c2e
@@ -887,6 +891,9 @@
 #define USB_VENDOR_ID_XAT	0x2505
 #define USB_DEVICE_ID_XAT_CSR	0x0220
 
+#define USB_VENDOR_ID_XIN_MO			0x16c0
+#define USB_DEVICE_ID_XIN_MO_DUAL_ARCADE	0x05e1
+
 #define USB_VENDOR_ID_XIROKU		0x1477
 #define USB_DEVICE_ID_XIROKU_SPX	0x1006
 #define USB_DEVICE_ID_XIROKU_MPX	0x1007
diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c
index 7480799e535c..8741d953dcc8 100644
--- a/drivers/hid/hid-input.c
+++ b/drivers/hid/hid-input.c
@@ -340,7 +340,7 @@ static int hidinput_get_battery_property(struct power_supply *psy,
 {
 	struct hid_device *dev = container_of(psy, struct hid_device, battery);
 	int ret = 0;
-	__u8 buf[2] = {};
+	__u8 *buf;
 
 	switch (prop) {
 	case POWER_SUPPLY_PROP_PRESENT:
@@ -349,12 +349,19 @@ static int hidinput_get_battery_property(struct power_supply *psy,
 		break;
 
 	case POWER_SUPPLY_PROP_CAPACITY:
+
+		buf = kmalloc(2 * sizeof(__u8), GFP_KERNEL);
+		if (!buf) {
+			ret = -ENOMEM;
+			break;
+		}
 		ret = dev->hid_get_raw_report(dev, dev->battery_report_id,
-					      buf, sizeof(buf),
+					      buf, 2,
 					      dev->battery_report_type);
 
 		if (ret != 2) {
 			ret = -ENODATA;
+			kfree(buf);
 			break;
 		}
 		ret = 0;
@@ -364,6 +371,7 @@ static int hidinput_get_battery_property(struct power_supply *psy,
 		    buf[1] <= dev->battery_max)
 			val->intval = (100 * (buf[1] - dev->battery_min)) /
 				(dev->battery_max - dev->battery_min);
+		kfree(buf);
 		break;
 
 	case POWER_SUPPLY_PROP_MODEL_NAME:
@@ -477,6 +485,10 @@ static void hidinput_configure_usage(struct hid_input *hidinput, struct hid_fiel
 	if (field->flags & HID_MAIN_ITEM_CONSTANT)
 		goto ignore;
 
+	/* Ignore if report count is out of bounds. */
+	if (field->report_count < 1)
+		goto ignore;
+
 	/* only LED usages are supported in output fields */
 	if (field->report_type == HID_OUTPUT_REPORT &&
 			(usage->hid & HID_USAGE_PAGE) != HID_UP_LED) {
@@ -1137,6 +1149,74 @@ unsigned int hidinput_count_leds(struct hid_device *hid)
 }
 EXPORT_SYMBOL_GPL(hidinput_count_leds);
 
+static void hidinput_led_worker(struct work_struct *work)
+{
+	struct hid_device *hid = container_of(work, struct hid_device,
+					      led_work);
+	struct hid_field *field;
+	struct hid_report *report;
+	int len;
+	__u8 *buf;
+
+	field = hidinput_get_led_field(hid);
+	if (!field)
+		return;
+
+	/*
+	 * field->report is accessed unlocked regarding HID core. So there might
+	 * be another incoming SET-LED request from user-space, which changes
+	 * the LED state while we assemble our outgoing buffer. However, this
+	 * doesn't matter as hid_output_report() correctly converts it into a
+	 * boolean value no matter what information is currently set on the LED
+	 * field (even garbage). So the remote device will always get a valid
+	 * request.
+	 * And in case we send a wrong value, a next led worker is spawned
+	 * for every SET-LED request so the following worker will send the
+	 * correct value, guaranteed!
+	 */
+
+	report = field->report;
+
+	/* use custom SET_REPORT request if possible (asynchronous) */
+	if (hid->ll_driver->request)
+		return hid->ll_driver->request(hid, report, HID_REQ_SET_REPORT);
+
+	/* fall back to generic raw-output-report */
+	len = ((report->size - 1) >> 3) + 1 + (report->id > 0);
+	buf = kmalloc(len, GFP_KERNEL);
+	if (!buf)
+		return;
+
+	hid_output_report(report, buf);
+	/* synchronous output report */
+	hid->hid_output_raw_report(hid, buf, len, HID_OUTPUT_REPORT);
+	kfree(buf);
+}
+
+static int hidinput_input_event(struct input_dev *dev, unsigned int type,
+				unsigned int code, int value)
+{
+	struct hid_device *hid = input_get_drvdata(dev);
+	struct hid_field *field;
+	int offset;
+
+	if (type == EV_FF)
+		return input_ff_event(dev, type, code, value);
+
+	if (type != EV_LED)
+		return -1;
+
+	if ((offset = hidinput_find_field(hid, type, code, &field)) == -1) {
+		hid_warn(dev, "event field not found\n");
+		return -1;
+	}
+
+	hid_set_field(field, offset, value);
+
+	schedule_work(&hid->led_work);
+	return 0;
+}
+
 static int hidinput_open(struct input_dev *dev)
 {
 	struct hid_device *hid = input_get_drvdata(dev);
@@ -1160,7 +1240,11 @@ static void report_features(struct hid_device *hid)
 
 	rep_enum = &hid->report_enum[HID_FEATURE_REPORT];
 	list_for_each_entry(rep, &rep_enum->report_list, list)
-		for (i = 0; i < rep->maxfield; i++)
+		for (i = 0; i < rep->maxfield; i++) {
+			/* Ignore if report count is out of bounds. */
+			if (rep->field[i]->report_count < 1)
+				continue;
+
 			for (j = 0; j < rep->field[i]->maxusage; j++) {
 				/* Verify if Battery Strength feature is available */
 				hidinput_setup_battery(hid, HID_FEATURE_REPORT, rep->field[i]);
@@ -1169,6 +1253,7 @@ static void report_features(struct hid_device *hid)
 					drv->feature_mapping(hid, rep->field[i],
 							     rep->field[i]->usage + j);
 			}
+		}
 }
 
 static struct hid_input *hidinput_allocate(struct hid_device *hid)
@@ -1183,7 +1268,10 @@ static struct hid_input *hidinput_allocate(struct hid_device *hid)
 	}
 
 	input_set_drvdata(input_dev, hid);
-	input_dev->event = hid->ll_driver->hidinput_input_event;
+	if (hid->ll_driver->hidinput_input_event)
+		input_dev->event = hid->ll_driver->hidinput_input_event;
+	else if (hid->ll_driver->request || hid->hid_output_raw_report)
+		input_dev->event = hidinput_input_event;
 	input_dev->open = hidinput_open;
 	input_dev->close = hidinput_close;
 	input_dev->setkeycode = hidinput_setkeycode;
@@ -1278,6 +1366,7 @@ int hidinput_connect(struct hid_device *hid, unsigned int force)
 	int i, j, k;
 
 	INIT_LIST_HEAD(&hid->inputs);
+	INIT_WORK(&hid->led_work, hidinput_led_worker);
 
 	if (!force) {
 		for (i = 0; i < hid->maxcollection; i++) {
@@ -1379,6 +1468,12 @@ void hidinput_disconnect(struct hid_device *hid)
 		input_unregister_device(hidinput->input);
 		kfree(hidinput);
 	}
+
+	/* led_work is spawned by input_dev callbacks, but doesn't access the
+	 * parent input_dev at all. Once all input devices are removed, we
+	 * know that led_work will never get restarted, so we can cancel it
+	 * synchronously and are safe. */
+	cancel_work_sync(&hid->led_work);
 }
 EXPORT_SYMBOL_GPL(hidinput_disconnect);
 
diff --git a/drivers/hid/hid-kye.c b/drivers/hid/hid-kye.c
index 1e2ee2aa84a0..73845120295e 100644
--- a/drivers/hid/hid-kye.c
+++ b/drivers/hid/hid-kye.c
@@ -268,6 +268,26 @@ static __u8 easypen_m610x_rdesc_fixed[] = {
 	0xC0                          /*  End Collection                  */
 };
 
+static __u8 *kye_consumer_control_fixup(struct hid_device *hdev, __u8 *rdesc,
+		unsigned int *rsize, int offset, const char *device_name) {
+	/*
+	 * the fixup that need to be done:
+	 *   - change Usage Maximum in the Comsumer Control
+	 *     (report ID 3) to a reasonable value
+	 */
+	if (*rsize >= offset + 31 &&
+	    /* Usage Page (Consumer Devices) */
+	    rdesc[offset] == 0x05 && rdesc[offset + 1] == 0x0c &&
+	    /* Usage (Consumer Control) */
+	    rdesc[offset + 2] == 0x09 && rdesc[offset + 3] == 0x01 &&
+	    /*   Usage Maximum > 12287 */
+	    rdesc[offset + 10] == 0x2a && rdesc[offset + 12] > 0x2f) {
+		hid_info(hdev, "fixing up %s report descriptor\n", device_name);
+		rdesc[offset + 12] = 0x2f;
+	}
+	return rdesc;
+}
+
 static __u8 *kye_report_fixup(struct hid_device *hdev, __u8 *rdesc,
 		unsigned int *rsize)
 {
@@ -315,23 +335,12 @@ static __u8 *kye_report_fixup(struct hid_device *hdev, __u8 *rdesc,
 		}
 		break;
 	case USB_DEVICE_ID_GENIUS_GILA_GAMING_MOUSE:
-		/*
-		 * the fixup that need to be done:
-		 *   - change Usage Maximum in the Comsumer Control
-		 *     (report ID 3) to a reasonable value
-		 */
-		if (*rsize >= 135 &&
-			/* Usage Page (Consumer Devices) */
-			rdesc[104] == 0x05 && rdesc[105] == 0x0c &&
-			/* Usage (Consumer Control) */
-			rdesc[106] == 0x09 && rdesc[107] == 0x01 &&
-			/*   Usage Maximum > 12287 */
-			rdesc[114] == 0x2a && rdesc[116] > 0x2f) {
-			hid_info(hdev,
-				 "fixing up Genius Gila Gaming Mouse "
-				 "report descriptor\n");
-			rdesc[116] = 0x2f;
-		}
+		rdesc = kye_consumer_control_fixup(hdev, rdesc, rsize, 104,
+					"Genius Gila Gaming Mouse");
+		break;
+	case USB_DEVICE_ID_GENIUS_GX_IMPERATOR:
+		rdesc = kye_consumer_control_fixup(hdev, rdesc, rsize, 83,
+					"Genius Gx Imperator Keyboard");
 		break;
 	}
 	return rdesc;
@@ -428,6 +437,8 @@ static const struct hid_device_id kye_devices[] = {
 				USB_DEVICE_ID_KYE_EASYPEN_M610X) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_KYE,
 				USB_DEVICE_ID_GENIUS_GILA_GAMING_MOUSE) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_KYE,
+				USB_DEVICE_ID_GENIUS_GX_IMPERATOR) },
 	{ }
 };
 MODULE_DEVICE_TABLE(hid, kye_devices);
diff --git a/drivers/hid/hid-lenovo-tpkbd.c b/drivers/hid/hid-lenovo-tpkbd.c
index 07837f5a4eb8..31cf29a6ba17 100644
--- a/drivers/hid/hid-lenovo-tpkbd.c
+++ b/drivers/hid/hid-lenovo-tpkbd.c
@@ -339,7 +339,15 @@ static int tpkbd_probe_tp(struct hid_device *hdev)
 	struct tpkbd_data_pointer *data_pointer;
 	size_t name_sz = strlen(dev_name(dev)) + 16;
 	char *name_mute, *name_micmute;
-	int ret;
+	int i, ret;
+
+	/* Validate required reports. */
+	for (i = 0; i < 4; i++) {
+		if (!hid_validate_values(hdev, HID_FEATURE_REPORT, 4, i, 1))
+			return -ENODEV;
+	}
+	if (!hid_validate_values(hdev, HID_OUTPUT_REPORT, 3, 0, 2))
+		return -ENODEV;
 
 	if (sysfs_create_group(&hdev->dev.kobj,
 				&tpkbd_attr_group_pointer)) {
@@ -406,22 +414,27 @@ static int tpkbd_probe(struct hid_device *hdev,
 	ret = hid_parse(hdev);
 	if (ret) {
 		hid_err(hdev, "hid_parse failed\n");
-		goto err_free;
+		goto err;
 	}
 
 	ret = hid_hw_start(hdev, HID_CONNECT_DEFAULT);
 	if (ret) {
 		hid_err(hdev, "hid_hw_start failed\n");
-		goto err_free;
+		goto err;
 	}
 
 	uhdev = (struct usbhid_device *) hdev->driver_data;
 
-	if (uhdev->ifnum == 1)
-		return tpkbd_probe_tp(hdev);
+	if (uhdev->ifnum == 1) {
+		ret = tpkbd_probe_tp(hdev);
+		if (ret)
+			goto err_hid;
+	}
 
 	return 0;
-err_free:
+err_hid:
+	hid_hw_stop(hdev);
+err:
 	return ret;
 }
 
diff --git a/drivers/hid/hid-lg2ff.c b/drivers/hid/hid-lg2ff.c
index b3cd1507dda2..1a42eaa6ca02 100644
--- a/drivers/hid/hid-lg2ff.c
+++ b/drivers/hid/hid-lg2ff.c
@@ -64,26 +64,13 @@ int lg2ff_init(struct hid_device *hid)
 	struct hid_report *report;
 	struct hid_input *hidinput = list_entry(hid->inputs.next,
 						struct hid_input, list);
-	struct list_head *report_list =
-			&hid->report_enum[HID_OUTPUT_REPORT].report_list;
 	struct input_dev *dev = hidinput->input;
 	int error;
 
-	if (list_empty(report_list)) {
-		hid_err(hid, "no output report found\n");
+	/* Check that the report looks ok */
+	report = hid_validate_values(hid, HID_OUTPUT_REPORT, 0, 0, 7);
+	if (!report)
 		return -ENODEV;
-	}
-
-	report = list_entry(report_list->next, struct hid_report, list);
-
-	if (report->maxfield < 1) {
-		hid_err(hid, "output report is empty\n");
-		return -ENODEV;
-	}
-	if (report->field[0]->report_count < 7) {
-		hid_err(hid, "not enough values in the field\n");
-		return -ENODEV;
-	}
 
 	lg2ff = kmalloc(sizeof(struct lg2ff_device), GFP_KERNEL);
 	if (!lg2ff)
diff --git a/drivers/hid/hid-lg3ff.c b/drivers/hid/hid-lg3ff.c
index e52f181f6aa1..8c2da183d3bc 100644
--- a/drivers/hid/hid-lg3ff.c
+++ b/drivers/hid/hid-lg3ff.c
@@ -66,10 +66,11 @@ static int hid_lg3ff_play(struct input_dev *dev, void *data,
 	int x, y;
 
 /*
- * Maxusage should always be 63 (maximum fields)
- * likely a better way to ensure this data is clean
+ * Available values in the field should always be 63, but we only use up to
+ * 35. Instead, clear the entire area, however big it is.
  */
-	memset(report->field[0]->value, 0, sizeof(__s32)*report->field[0]->maxusage);
+	memset(report->field[0]->value, 0,
+	       sizeof(__s32) * report->field[0]->report_count);
 
 	switch (effect->type) {
 	case FF_CONSTANT:
@@ -129,32 +130,14 @@ static const signed short ff3_joystick_ac[] = {
 int lg3ff_init(struct hid_device *hid)
 {
 	struct hid_input *hidinput = list_entry(hid->inputs.next, struct hid_input, list);
-	struct list_head *report_list = &hid->report_enum[HID_OUTPUT_REPORT].report_list;
 	struct input_dev *dev = hidinput->input;
-	struct hid_report *report;
-	struct hid_field *field;
 	const signed short *ff_bits = ff3_joystick_ac;
 	int error;
 	int i;
 
-	/* Find the report to use */
-	if (list_empty(report_list)) {
-		hid_err(hid, "No output report found\n");
-		return -1;
-	}
-
 	/* Check that the report looks ok */
-	report = list_entry(report_list->next, struct hid_report, list);
-	if (!report) {
-		hid_err(hid, "NULL output report\n");
-		return -1;
-	}
-
-	field = report->field[0];
-	if (!field) {
-		hid_err(hid, "NULL field\n");
-		return -1;
-	}
+	if (!hid_validate_values(hid, HID_OUTPUT_REPORT, 0, 0, 35))
+		return -ENODEV;
 
 	/* Assume single fixed device G940 */
 	for (i = 0; ff_bits[i] >= 0; i++)
diff --git a/drivers/hid/hid-lg4ff.c b/drivers/hid/hid-lg4ff.c
index 0ddae2a00d59..8782fe1aaa07 100644
--- a/drivers/hid/hid-lg4ff.c
+++ b/drivers/hid/hid-lg4ff.c
@@ -484,34 +484,16 @@ static enum led_brightness lg4ff_led_get_brightness(struct led_classdev *led_cde
 int lg4ff_init(struct hid_device *hid)
 {
 	struct hid_input *hidinput = list_entry(hid->inputs.next, struct hid_input, list);
-	struct list_head *report_list = &hid->report_enum[HID_OUTPUT_REPORT].report_list;
 	struct input_dev *dev = hidinput->input;
-	struct hid_report *report;
-	struct hid_field *field;
 	struct lg4ff_device_entry *entry;
 	struct lg_drv_data *drv_data;
 	struct usb_device_descriptor *udesc;
 	int error, i, j;
 	__u16 bcdDevice, rev_maj, rev_min;
 
-	/* Find the report to use */
-	if (list_empty(report_list)) {
-		hid_err(hid, "No output report found\n");
-		return -1;
-	}
-
 	/* Check that the report looks ok */
-	report = list_entry(report_list->next, struct hid_report, list);
-	if (!report) {
-		hid_err(hid, "NULL output report\n");
+	if (!hid_validate_values(hid, HID_OUTPUT_REPORT, 0, 0, 7))
 		return -1;
-	}
-
-	field = report->field[0];
-	if (!field) {
-		hid_err(hid, "NULL field\n");
-		return -1;
-	}
 
 	/* Check what wheel has been connected */
 	for (i = 0; i < ARRAY_SIZE(lg4ff_devices); i++) {
diff --git a/drivers/hid/hid-lgff.c b/drivers/hid/hid-lgff.c
index d7ea8c845b40..e1394af0ae7b 100644
--- a/drivers/hid/hid-lgff.c
+++ b/drivers/hid/hid-lgff.c
@@ -128,27 +128,14 @@ static void hid_lgff_set_autocenter(struct input_dev *dev, u16 magnitude)
 int lgff_init(struct hid_device* hid)
 {
 	struct hid_input *hidinput = list_entry(hid->inputs.next, struct hid_input, list);
-	struct list_head *report_list = &hid->report_enum[HID_OUTPUT_REPORT].report_list;
 	struct input_dev *dev = hidinput->input;
-	struct hid_report *report;
-	struct hid_field *field;
 	const signed short *ff_bits = ff_joystick;
 	int error;
 	int i;
 
-	/* Find the report to use */
-	if (list_empty(report_list)) {
-		hid_err(hid, "No output report found\n");
-		return -1;
-	}
-
 	/* Check that the report looks ok */
-	report = list_entry(report_list->next, struct hid_report, list);
-	field = report->field[0];
-	if (!field) {
-		hid_err(hid, "NULL field\n");
-		return -1;
-	}
+	if (!hid_validate_values(hid, HID_OUTPUT_REPORT, 0, 0, 7))
+		return -ENODEV;
 
 	for (i = 0; i < ARRAY_SIZE(devices); i++) {
 		if (dev->id.vendor == devices[i].idVendor &&
diff --git a/drivers/hid/hid-logitech-dj.c b/drivers/hid/hid-logitech-dj.c
index cd33084c7860..2e5302462efb 100644
--- a/drivers/hid/hid-logitech-dj.c
+++ b/drivers/hid/hid-logitech-dj.c
@@ -461,7 +461,7 @@ static int logi_dj_recv_send_report(struct dj_receiver_dev *djrcv_dev,
 	struct hid_report *report;
 	struct hid_report_enum *output_report_enum;
 	u8 *data = (u8 *)(&dj_report->device_index);
-	int i;
+	unsigned int i;
 
 	output_report_enum = &hdev->report_enum[HID_OUTPUT_REPORT];
 	report = output_report_enum->report_id_hash[REPORT_ID_DJ_SHORT];
@@ -471,7 +471,7 @@ static int logi_dj_recv_send_report(struct dj_receiver_dev *djrcv_dev,
 		return -ENODEV;
 	}
 
-	for (i = 0; i < report->field[0]->report_count; i++)
+	for (i = 0; i < DJREPORT_SHORT_LENGTH - 1; i++)
 		report->field[0]->value[i] = data[i];
 
 	hid_hw_request(hdev, report, HID_REQ_SET_REPORT);
@@ -619,7 +619,7 @@ static int logi_dj_ll_input_event(struct input_dev *dev, unsigned int type,
 
 	struct hid_field *field;
 	struct hid_report *report;
-	unsigned char data[8];
+	unsigned char *data;
 	int offset;
 
 	dbg_hid("%s: %s, type:%d | code:%d | value:%d\n",
@@ -635,6 +635,13 @@ static int logi_dj_ll_input_event(struct input_dev *dev, unsigned int type,
 		return -1;
 	}
 	hid_set_field(field, offset, value);
+
+	data = hid_alloc_report_buf(field->report, GFP_ATOMIC);
+	if (!data) {
+		dev_warn(&dev->dev, "failed to allocate report buf memory\n");
+		return -1;
+	}
+
 	hid_output_report(field->report, &data[0]);
 
 	output_report_enum = &dj_rcv_hiddev->report_enum[HID_OUTPUT_REPORT];
@@ -645,8 +652,9 @@ static int logi_dj_ll_input_event(struct input_dev *dev, unsigned int type,
 
 	hid_hw_request(dj_rcv_hiddev, report, HID_REQ_SET_REPORT);
 
-	return 0;
+	kfree(data);
 
+	return 0;
 }
 
 static int logi_dj_ll_start(struct hid_device *hid)
@@ -783,6 +791,12 @@ static int logi_dj_probe(struct hid_device *hdev,
 		goto hid_parse_fail;
 	}
 
+	if (!hid_validate_values(hdev, HID_OUTPUT_REPORT, REPORT_ID_DJ_SHORT,
+				 0, DJREPORT_SHORT_LENGTH - 1)) {
+		retval = -ENODEV;
+		goto hid_parse_fail;
+	}
+
 	/* Starts the usb device and connects to upper interfaces hiddev and
 	 * hidraw */
 	retval = hid_hw_start(hdev, HID_CONNECT_DEFAULT);
@@ -801,10 +815,10 @@ static int logi_dj_probe(struct hid_device *hdev,
 	}
 
 	/* This is enabling the polling urb on the IN endpoint */
-	retval = hdev->ll_driver->open(hdev);
+	retval = hid_hw_open(hdev);
 	if (retval < 0) {
-		dev_err(&hdev->dev, "%s:hdev->ll_driver->open returned "
-			"error:%d\n", __func__, retval);
+		dev_err(&hdev->dev, "%s:hid_hw_open returned error:%d\n",
+			__func__, retval);
 		goto llopen_failed;
 	}
 
@@ -821,7 +835,7 @@ static int logi_dj_probe(struct hid_device *hdev,
 	return retval;
 
 logi_dj_recv_query_paired_devices_failed:
-	hdev->ll_driver->close(hdev);
+	hid_hw_close(hdev);
 
 llopen_failed:
 switch_to_dj_mode_fail:
@@ -863,7 +877,7 @@ static void logi_dj_remove(struct hid_device *hdev)
 
 	cancel_work_sync(&djrcv_dev->work);
 
-	hdev->ll_driver->close(hdev);
+	hid_hw_close(hdev);
 	hid_hw_stop(hdev);
 
 	/* I suppose that at this point the only context that can access
diff --git a/drivers/hid/hid-magicmouse.c b/drivers/hid/hid-magicmouse.c
index 5bc37343eb22..3b43d1cfa936 100644
--- a/drivers/hid/hid-magicmouse.c
+++ b/drivers/hid/hid-magicmouse.c
@@ -36,7 +36,7 @@ MODULE_PARM_DESC(emulate_scroll_wheel, "Emulate a scroll wheel");
 static unsigned int scroll_speed = 32;
 static int param_set_scroll_speed(const char *val, struct kernel_param *kp) {
 	unsigned long speed;
-	if (!val || strict_strtoul(val, 0, &speed) || speed > 63)
+	if (!val || kstrtoul(val, 0, &speed) || speed > 63)
 		return -EINVAL;
 	scroll_speed = speed;
 	return 0;
@@ -484,7 +484,7 @@ static int magicmouse_probe(struct hid_device *hdev,
 	struct hid_report *report;
 	int ret;
 
-	msc = kzalloc(sizeof(*msc), GFP_KERNEL);
+	msc = devm_kzalloc(&hdev->dev, sizeof(*msc), GFP_KERNEL);
 	if (msc == NULL) {
 		hid_err(hdev, "can't alloc magicmouse descriptor\n");
 		return -ENOMEM;
@@ -498,13 +498,13 @@ static int magicmouse_probe(struct hid_device *hdev,
 	ret = hid_parse(hdev);
 	if (ret) {
 		hid_err(hdev, "magicmouse hid parse failed\n");
-		goto err_free;
+		return ret;
 	}
 
 	ret = hid_hw_start(hdev, HID_CONNECT_DEFAULT);
 	if (ret) {
 		hid_err(hdev, "magicmouse hw start failed\n");
-		goto err_free;
+		return ret;
 	}
 
 	if (!msc->input) {
@@ -548,19 +548,9 @@ static int magicmouse_probe(struct hid_device *hdev,
 	return 0;
 err_stop_hw:
 	hid_hw_stop(hdev);
-err_free:
-	kfree(msc);
 	return ret;
 }
 
-static void magicmouse_remove(struct hid_device *hdev)
-{
-	struct magicmouse_sc *msc = hid_get_drvdata(hdev);
-
-	hid_hw_stop(hdev);
-	kfree(msc);
-}
-
 static const struct hid_device_id magic_mice[] = {
 	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE,
 		USB_DEVICE_ID_APPLE_MAGICMOUSE), .driver_data = 0 },
@@ -574,7 +564,6 @@ static struct hid_driver magicmouse_driver = {
 	.name = "magicmouse",
 	.id_table = magic_mice,
 	.probe = magicmouse_probe,
-	.remove = magicmouse_remove,
 	.raw_event = magicmouse_raw_event,
 	.input_mapping = magicmouse_input_mapping,
 	.input_configured = magicmouse_input_configured,
diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c
index cb0e361d7a4b..5e5fe1b8eebb 100644
--- a/drivers/hid/hid-multitouch.c
+++ b/drivers/hid/hid-multitouch.c
@@ -101,9 +101,9 @@ struct mt_device {
 	unsigned last_slot_field;	/* the last field of a slot */
 	unsigned mt_report_id;	/* the report ID of the multitouch device */
 	unsigned pen_report_id;	/* the report ID of the pen device */
-	__s8 inputmode;		/* InputMode HID feature, -1 if non-existent */
-	__s8 inputmode_index;	/* InputMode HID feature index in the report */
-	__s8 maxcontact_report_id;	/* Maximum Contact Number HID feature,
+	__s16 inputmode;	/* InputMode HID feature, -1 if non-existent */
+	__s16 inputmode_index;	/* InputMode HID feature index in the report */
+	__s16 maxcontact_report_id;	/* Maximum Contact Number HID feature,
 				   -1 if non-existent */
 	__u8 num_received;	/* how many contacts we received */
 	__u8 num_expected;	/* expected last contact index */
@@ -133,6 +133,7 @@ static void mt_post_parse(struct mt_device *td);
 #define MT_CLS_NSMU				0x000a
 #define MT_CLS_DUAL_CONTACT_NUMBER		0x0010
 #define MT_CLS_DUAL_CONTACT_ID			0x0011
+#define MT_CLS_WIN_8				0x0012
 
 /* vendor specific classes */
 #define MT_CLS_3M				0x0101
@@ -205,6 +206,11 @@ static struct mt_class mt_classes[] = {
 			MT_QUIRK_CONTACT_CNT_ACCURATE |
 			MT_QUIRK_SLOT_IS_CONTACTID,
 		.maxcontacts = 2 },
+	{ .name = MT_CLS_WIN_8,
+		.quirks = MT_QUIRK_ALWAYS_VALID |
+			MT_QUIRK_IGNORE_DUPLICATES |
+			MT_QUIRK_HOVERING |
+			MT_QUIRK_CONTACT_CNT_ACCURATE },
 
 	/*
 	 * vendor specific classes
@@ -261,17 +267,6 @@ static struct mt_class mt_classes[] = {
 	{ }
 };
 
-static void mt_free_input_name(struct hid_input *hi)
-{
-	struct hid_device *hdev = hi->report->device;
-	const char *name = hi->input->name;
-
-	if (name != hdev->name) {
-		hi->input->name = hdev->name;
-		kfree(name);
-	}
-}
-
 static ssize_t mt_show_quirks(struct device *dev,
 			   struct device_attribute *attr,
 			   char *buf)
@@ -317,20 +312,18 @@ static void mt_feature_mapping(struct hid_device *hdev,
 		struct hid_field *field, struct hid_usage *usage)
 {
 	struct mt_device *td = hid_get_drvdata(hdev);
-	int i;
 
 	switch (usage->hid) {
 	case HID_DG_INPUTMODE:
-		td->inputmode = field->report->id;
-		td->inputmode_index = 0; /* has to be updated below */
-
-		for (i=0; i < field->maxusage; i++) {
-			if (field->usage[i].hid == usage->hid) {
-				td->inputmode_index = i;
-				break;
-			}
+		/* Ignore if value index is out of bounds. */
+		if (usage->usage_index >= field->report_count) {
+			dev_err(&hdev->dev, "HID_DG_INPUTMODE out of range\n");
+			break;
 		}
 
+		td->inputmode = field->report->id;
+		td->inputmode_index = usage->usage_index;
+
 		break;
 	case HID_DG_CONTACTMAX:
 		td->maxcontact_report_id = field->report->id;
@@ -343,19 +336,6 @@ static void mt_feature_mapping(struct hid_device *hdev,
 			td->maxcontacts = td->mtclass.maxcontacts;
 
 		break;
-	case 0xff0000c5:
-		if (field->report_count == 256 && field->report_size == 8) {
-			/* Win 8 devices need special quirks */
-			__s32 *quirks = &td->mtclass.quirks;
-			*quirks |= MT_QUIRK_ALWAYS_VALID;
-			*quirks |= MT_QUIRK_IGNORE_DUPLICATES;
-			*quirks |= MT_QUIRK_HOVERING;
-			*quirks |= MT_QUIRK_CONTACT_CNT_ACCURATE;
-			*quirks &= ~MT_QUIRK_NOT_SEEN_MEANS_UP;
-			*quirks &= ~MT_QUIRK_VALID_IS_INRANGE;
-			*quirks &= ~MT_QUIRK_VALID_IS_CONFIDENCE;
-		}
-		break;
 	}
 }
 
@@ -415,13 +395,6 @@ static void mt_pen_report(struct hid_device *hid, struct hid_report *report)
 static void mt_pen_input_configured(struct hid_device *hdev,
 					struct hid_input *hi)
 {
-	char *name = kzalloc(strlen(hi->input->name) + 5, GFP_KERNEL);
-	if (name) {
-		sprintf(name, "%s Pen", hi->input->name);
-		mt_free_input_name(hi);
-		hi->input->name = name;
-	}
-
 	/* force BTN_STYLUS to allow tablet matching in udev */
 	__set_bit(BTN_STYLUS, hi->input->keybit);
 }
@@ -536,6 +509,10 @@ static int mt_touch_input_mapping(struct hid_device *hdev, struct hid_input *hi,
 			mt_store_field(usage, td, hi);
 			return 1;
 		case HID_DG_CONTACTCOUNT:
+			/* Ignore if indexes are out of bounds. */
+			if (field->index >= field->report->maxfield ||
+			    usage->usage_index >= field->report_count)
+				return 1;
 			td->cc_index = field->index;
 			td->cc_value_index = usage->usage_index;
 			return 1;
@@ -928,16 +905,26 @@ static void mt_post_parse(struct mt_device *td)
 static void mt_input_configured(struct hid_device *hdev, struct hid_input *hi)
 {
 	struct mt_device *td = hid_get_drvdata(hdev);
-	char *name = kstrdup(hdev->name, GFP_KERNEL);
-
-	if (name)
-		hi->input->name = name;
+	char *name;
+	const char *suffix = NULL;
 
 	if (hi->report->id == td->mt_report_id)
 		mt_touch_input_configured(hdev, hi);
 
-	if (hi->report->id == td->pen_report_id)
+	if (hi->report->field[0]->physical == HID_DG_STYLUS) {
+		suffix = "Pen";
 		mt_pen_input_configured(hdev, hi);
+	}
+
+	if (suffix) {
+		name = devm_kzalloc(&hi->input->dev,
+				    strlen(hdev->name) + strlen(suffix) + 2,
+				    GFP_KERNEL);
+		if (name) {
+			sprintf(name, "%s %s", hdev->name, suffix);
+			hi->input->name = name;
+		}
+	}
 }
 
 static int mt_probe(struct hid_device *hdev, const struct hid_device_id *id)
@@ -945,7 +932,6 @@ static int mt_probe(struct hid_device *hdev, const struct hid_device_id *id)
 	int ret, i;
 	struct mt_device *td;
 	struct mt_class *mtclass = mt_classes; /* MT_CLS_DEFAULT */
-	struct hid_input *hi;
 
 	for (i = 0; mt_classes[i].name ; i++) {
 		if (id->driver_data == mt_classes[i].name) {
@@ -967,7 +953,19 @@ static int mt_probe(struct hid_device *hdev, const struct hid_device_id *id)
 	hdev->quirks |= HID_QUIRK_MULTI_INPUT;
 	hdev->quirks |= HID_QUIRK_NO_EMPTY_INPUT;
 
-	td = kzalloc(sizeof(struct mt_device), GFP_KERNEL);
+	/*
+	 * Handle special quirks for Windows 8 certified devices.
+	 */
+	if (id->group == HID_GROUP_MULTITOUCH_WIN_8)
+		/*
+		 * Some multitouch screens do not like to be polled for input
+		 * reports. Fortunately, the Win8 spec says that all touches
+		 * should be sent during each report, making the initialization
+		 * of input reports unnecessary.
+		 */
+		hdev->quirks |= HID_QUIRK_NO_INIT_INPUT_REPORTS;
+
+	td = devm_kzalloc(&hdev->dev, sizeof(struct mt_device), GFP_KERNEL);
 	if (!td) {
 		dev_err(&hdev->dev, "cannot allocate multitouch data\n");
 		return -ENOMEM;
@@ -980,11 +978,11 @@ static int mt_probe(struct hid_device *hdev, const struct hid_device_id *id)
 	td->pen_report_id = -1;
 	hid_set_drvdata(hdev, td);
 
-	td->fields = kzalloc(sizeof(struct mt_fields), GFP_KERNEL);
+	td->fields = devm_kzalloc(&hdev->dev, sizeof(struct mt_fields),
+				  GFP_KERNEL);
 	if (!td->fields) {
 		dev_err(&hdev->dev, "cannot allocate multitouch fields data\n");
-		ret = -ENOMEM;
-		goto fail;
+		return -ENOMEM;
 	}
 
 	if (id->vendor == HID_ANY_ID && id->product == HID_ANY_ID)
@@ -992,29 +990,22 @@ static int mt_probe(struct hid_device *hdev, const struct hid_device_id *id)
 
 	ret = hid_parse(hdev);
 	if (ret != 0)
-		goto fail;
+		return ret;
 
 	ret = hid_hw_start(hdev, HID_CONNECT_DEFAULT);
 	if (ret)
-		goto hid_fail;
+		return ret;
 
 	ret = sysfs_create_group(&hdev->dev.kobj, &mt_attribute_group);
 
 	mt_set_maxcontacts(hdev);
 	mt_set_input_mode(hdev);
 
-	kfree(td->fields);
+	/* release .fields memory as it is not used anymore */
+	devm_kfree(&hdev->dev, td->fields);
 	td->fields = NULL;
 
 	return 0;
-
-hid_fail:
-	list_for_each_entry(hi, &hdev->inputs, list)
-		mt_free_input_name(hi);
-fail:
-	kfree(td->fields);
-	kfree(td);
-	return ret;
 }
 
 #ifdef CONFIG_PM
@@ -1039,17 +1030,8 @@ static int mt_resume(struct hid_device *hdev)
 
 static void mt_remove(struct hid_device *hdev)
 {
-	struct mt_device *td = hid_get_drvdata(hdev);
-	struct hid_input *hi;
-
 	sysfs_remove_group(&hdev->dev.kobj, &mt_attribute_group);
-	list_for_each_entry(hi, &hdev->inputs, list)
-		mt_free_input_name(hi);
-
 	hid_hw_stop(hdev);
-
-	kfree(td);
-	hid_set_drvdata(hdev, NULL);
 }
 
 static const struct hid_device_id mt_devices[] = {
@@ -1371,6 +1353,11 @@ static const struct hid_device_id mt_devices[] = {
 
 	/* Generic MT device */
 	{ HID_DEVICE(HID_BUS_ANY, HID_GROUP_MULTITOUCH, HID_ANY_ID, HID_ANY_ID) },
+
+	/* Generic Win 8 certified MT device */
+	{  .driver_data = MT_CLS_WIN_8,
+		HID_DEVICE(HID_BUS_ANY, HID_GROUP_MULTITOUCH_WIN_8,
+			HID_ANY_ID, HID_ANY_ID) },
 	{ }
 };
 MODULE_DEVICE_TABLE(hid, mt_devices);
diff --git a/drivers/hid/hid-ntrig.c b/drivers/hid/hid-ntrig.c
index ef95102515e4..600f2075512f 100644
--- a/drivers/hid/hid-ntrig.c
+++ b/drivers/hid/hid-ntrig.c
@@ -115,7 +115,8 @@ static inline int ntrig_get_mode(struct hid_device *hdev)
 	struct hid_report *report = hdev->report_enum[HID_FEATURE_REPORT].
 				    report_id_hash[0x0d];
 
-	if (!report)
+	if (!report || report->maxfield < 1 ||
+	    report->field[0]->report_count < 1)
 		return -EINVAL;
 
 	hid_hw_request(hdev, report, HID_REQ_GET_REPORT);
@@ -237,7 +238,7 @@ static ssize_t set_min_width(struct device *dev,
 
 	unsigned long val;
 
-	if (strict_strtoul(buf, 0, &val))
+	if (kstrtoul(buf, 0, &val))
 		return -EINVAL;
 
 	if (val > nd->sensor_physical_width)
@@ -272,7 +273,7 @@ static ssize_t set_min_height(struct device *dev,
 
 	unsigned long val;
 
-	if (strict_strtoul(buf, 0, &val))
+	if (kstrtoul(buf, 0, &val))
 		return -EINVAL;
 
 	if (val > nd->sensor_physical_height)
@@ -306,7 +307,7 @@ static ssize_t set_activate_slack(struct device *dev,
 
 	unsigned long val;
 
-	if (strict_strtoul(buf, 0, &val))
+	if (kstrtoul(buf, 0, &val))
 		return -EINVAL;
 
 	if (val > 0x7f)
@@ -341,7 +342,7 @@ static ssize_t set_activation_width(struct device *dev,
 
 	unsigned long val;
 
-	if (strict_strtoul(buf, 0, &val))
+	if (kstrtoul(buf, 0, &val))
 		return -EINVAL;
 
 	if (val > nd->sensor_physical_width)
@@ -377,7 +378,7 @@ static ssize_t set_activation_height(struct device *dev,
 
 	unsigned long val;
 
-	if (strict_strtoul(buf, 0, &val))
+	if (kstrtoul(buf, 0, &val))
 		return -EINVAL;
 
 	if (val > nd->sensor_physical_height)
@@ -411,7 +412,7 @@ static ssize_t set_deactivate_slack(struct device *dev,
 
 	unsigned long val;
 
-	if (strict_strtoul(buf, 0, &val))
+	if (kstrtoul(buf, 0, &val))
 		return -EINVAL;
 
 	/*
diff --git a/drivers/hid/hid-picolcd_cir.c b/drivers/hid/hid-picolcd_cir.c
index e346038f0f11..59d5eb1e742c 100644
--- a/drivers/hid/hid-picolcd_cir.c
+++ b/drivers/hid/hid-picolcd_cir.c
@@ -145,6 +145,7 @@ void picolcd_exit_cir(struct picolcd_data *data)
 	struct rc_dev *rdev = data->rc_dev;
 
 	data->rc_dev = NULL;
-	rc_unregister_device(rdev);
+	if (rdev)
+		rc_unregister_device(rdev);
 }
 
diff --git a/drivers/hid/hid-picolcd_core.c b/drivers/hid/hid-picolcd_core.c
index b48092d0e139..acbb021065ec 100644
--- a/drivers/hid/hid-picolcd_core.c
+++ b/drivers/hid/hid-picolcd_core.c
@@ -290,7 +290,7 @@ static ssize_t picolcd_operation_mode_store(struct device *dev,
 		buf += 10;
 		cnt -= 10;
 	}
-	if (!report)
+	if (!report || report->maxfield != 1)
 		return -EINVAL;
 
 	while (cnt > 0 && (buf[cnt-1] == '\n' || buf[cnt-1] == '\r'))
diff --git a/drivers/hid/hid-picolcd_debugfs.c b/drivers/hid/hid-picolcd_debugfs.c
index 59ab8e157e6b..024cdf3c2297 100644
--- a/drivers/hid/hid-picolcd_debugfs.c
+++ b/drivers/hid/hid-picolcd_debugfs.c
@@ -394,7 +394,7 @@ static void dump_buff_as_hex(char *dst, size_t dst_sz, const u8 *data,
 void picolcd_debug_out_report(struct picolcd_data *data,
 		struct hid_device *hdev, struct hid_report *report)
 {
-	u8 raw_data[70];
+	u8 *raw_data;
 	int raw_size = (report->size >> 3) + 1;
 	char *buff;
 #define BUFF_SZ 256
@@ -407,20 +407,20 @@ void picolcd_debug_out_report(struct picolcd_data *data,
 	if (!buff)
 		return;
 
-	snprintf(buff, BUFF_SZ, "\nout report %d (size %d) =  ",
-			report->id, raw_size);
-	hid_debug_event(hdev, buff);
-	if (raw_size + 5 > sizeof(raw_data)) {
+	raw_data = hid_alloc_report_buf(report, GFP_ATOMIC);
+	if (!raw_data) {
 		kfree(buff);
-		hid_debug_event(hdev, " TOO BIG\n");
 		return;
-	} else {
-		raw_data[0] = report->id;
-		hid_output_report(report, raw_data);
-		dump_buff_as_hex(buff, BUFF_SZ, raw_data, raw_size);
-		hid_debug_event(hdev, buff);
 	}
 
+	snprintf(buff, BUFF_SZ, "\nout report %d (size %d) =  ",
+			report->id, raw_size);
+	hid_debug_event(hdev, buff);
+	raw_data[0] = report->id;
+	hid_output_report(report, raw_data);
+	dump_buff_as_hex(buff, BUFF_SZ, raw_data, raw_size);
+	hid_debug_event(hdev, buff);
+
 	switch (report->id) {
 	case REPORT_LED_STATE:
 		/* 1 data byte with GPO state */
@@ -644,6 +644,7 @@ void picolcd_debug_out_report(struct picolcd_data *data,
 		break;
 	}
 	wake_up_interruptible(&hdev->debug_wait);
+	kfree(raw_data);
 	kfree(buff);
 }
 
diff --git a/drivers/hid/hid-picolcd_fb.c b/drivers/hid/hid-picolcd_fb.c
index 591f6b22aa94..c930ab8554ea 100644
--- a/drivers/hid/hid-picolcd_fb.c
+++ b/drivers/hid/hid-picolcd_fb.c
@@ -593,10 +593,14 @@ err_nomem:
 void picolcd_exit_framebuffer(struct picolcd_data *data)
 {
 	struct fb_info *info = data->fb_info;
-	struct picolcd_fb_data *fbdata = info->par;
+	struct picolcd_fb_data *fbdata;
 	unsigned long flags;
 
+	if (!info)
+		return;
+
 	device_remove_file(&data->hdev->dev, &dev_attr_fb_update_rate);
+	fbdata = info->par;
 
 	/* disconnect framebuffer from HID dev */
 	spin_lock_irqsave(&fbdata->lock, flags);
diff --git a/drivers/hid/hid-pl.c b/drivers/hid/hid-pl.c
index d29112fa5cd5..2dcd7d98dbd6 100644
--- a/drivers/hid/hid-pl.c
+++ b/drivers/hid/hid-pl.c
@@ -132,8 +132,14 @@ static int plff_init(struct hid_device *hid)
 			strong = &report->field[0]->value[2];
 			weak = &report->field[0]->value[3];
 			debug("detected single-field device");
-		} else if (report->maxfield >= 4 && report->field[0]->maxusage == 1 &&
-				report->field[0]->usage[0].hid == (HID_UP_LED | 0x43)) {
+		} else if (report->field[0]->maxusage == 1 &&
+			   report->field[0]->usage[0].hid ==
+				(HID_UP_LED | 0x43) &&
+			   report->maxfield >= 4 &&
+			   report->field[0]->report_count >= 1 &&
+			   report->field[1]->report_count >= 1 &&
+			   report->field[2]->report_count >= 1 &&
+			   report->field[3]->report_count >= 1) {
 			report->field[0]->value[0] = 0x00;
 			report->field[1]->value[0] = 0x00;
 			strong = &report->field[2]->value[0];
diff --git a/drivers/hid/hid-roccat-arvo.c b/drivers/hid/hid-roccat-arvo.c
index 327f9b8ed1f4..1948208fe038 100644
--- a/drivers/hid/hid-roccat-arvo.c
+++ b/drivers/hid/hid-roccat-arvo.c
@@ -59,7 +59,7 @@ static ssize_t arvo_sysfs_set_mode_key(struct device *dev,
 	unsigned long state;
 	int retval;
 
-	retval = strict_strtoul(buf, 10, &state);
+	retval = kstrtoul(buf, 10, &state);
 	if (retval)
 		return retval;
 
@@ -75,6 +75,8 @@ static ssize_t arvo_sysfs_set_mode_key(struct device *dev,
 
 	return size;
 }
+static DEVICE_ATTR(mode_key, 0660,
+		   arvo_sysfs_show_mode_key, arvo_sysfs_set_mode_key);
 
 static ssize_t arvo_sysfs_show_key_mask(struct device *dev,
 		struct device_attribute *attr, char *buf)
@@ -107,7 +109,7 @@ static ssize_t arvo_sysfs_set_key_mask(struct device *dev,
 	unsigned long key_mask;
 	int retval;
 
-	retval = strict_strtoul(buf, 10, &key_mask);
+	retval = kstrtoul(buf, 10, &key_mask);
 	if (retval)
 		return retval;
 
@@ -123,6 +125,8 @@ static ssize_t arvo_sysfs_set_key_mask(struct device *dev,
 
 	return size;
 }
+static DEVICE_ATTR(key_mask, 0660,
+		   arvo_sysfs_show_key_mask, arvo_sysfs_set_key_mask);
 
 /* retval is 1-5 on success, < 0 on error */
 static int arvo_get_actual_profile(struct usb_device *usb_dev)
@@ -159,7 +163,7 @@ static ssize_t arvo_sysfs_set_actual_profile(struct device *dev,
 	unsigned long profile;
 	int retval;
 
-	retval = strict_strtoul(buf, 10, &profile);
+	retval = kstrtoul(buf, 10, &profile);
 	if (retval)
 		return retval;
 
@@ -179,6 +183,9 @@ static ssize_t arvo_sysfs_set_actual_profile(struct device *dev,
 	mutex_unlock(&arvo->arvo_lock);
 	return retval;
 }
+static DEVICE_ATTR(actual_profile, 0660,
+		   arvo_sysfs_show_actual_profile,
+		   arvo_sysfs_set_actual_profile);
 
 static ssize_t arvo_sysfs_write(struct file *fp,
 		struct kobject *kobj, void const *buf,
@@ -230,6 +237,8 @@ static ssize_t arvo_sysfs_write_button(struct file *fp,
 	return arvo_sysfs_write(fp, kobj, buf, off, count,
 			sizeof(struct arvo_button), ARVO_COMMAND_BUTTON);
 }
+static BIN_ATTR(button, 0220, NULL, arvo_sysfs_write_button,
+		sizeof(struct arvo_button));
 
 static ssize_t arvo_sysfs_read_info(struct file *fp,
 		struct kobject *kobj, struct bin_attribute *attr, char *buf,
@@ -238,31 +247,30 @@ static ssize_t arvo_sysfs_read_info(struct file *fp,
 	return arvo_sysfs_read(fp, kobj, buf, off, count,
 			sizeof(struct arvo_info), ARVO_COMMAND_INFO);
 }
+static BIN_ATTR(info, 0440, arvo_sysfs_read_info, NULL,
+		sizeof(struct arvo_info));
+
+static struct attribute *arvo_attrs[] = {
+	&dev_attr_mode_key.attr,
+	&dev_attr_key_mask.attr,
+	&dev_attr_actual_profile.attr,
+	NULL,
+};
 
+static struct bin_attribute *arvo_bin_attributes[] = {
+	&bin_attr_button,
+	&bin_attr_info,
+	NULL,
+};
 
-static struct device_attribute arvo_attributes[] = {
-	__ATTR(mode_key, 0660,
-			arvo_sysfs_show_mode_key, arvo_sysfs_set_mode_key),
-	__ATTR(key_mask, 0660,
-			arvo_sysfs_show_key_mask, arvo_sysfs_set_key_mask),
-	__ATTR(actual_profile, 0660,
-			arvo_sysfs_show_actual_profile,
-			arvo_sysfs_set_actual_profile),
-	__ATTR_NULL
+static const struct attribute_group arvo_group = {
+	.attrs = arvo_attrs,
+	.bin_attrs = arvo_bin_attributes,
 };
 
-static struct bin_attribute arvo_bin_attributes[] = {
-	{
-		.attr = { .name = "button", .mode = 0220 },
-		.size = sizeof(struct arvo_button),
-		.write = arvo_sysfs_write_button
-	},
-	{
-		.attr = { .name = "info", .mode = 0440 },
-		.size = sizeof(struct arvo_info),
-		.read = arvo_sysfs_read_info
-	},
-	__ATTR_NULL
+static const struct attribute_group *arvo_groups[] = {
+	&arvo_group,
+	NULL,
 };
 
 static int arvo_init_arvo_device_struct(struct usb_device *usb_dev,
@@ -430,8 +438,7 @@ static int __init arvo_init(void)
 	arvo_class = class_create(THIS_MODULE, "arvo");
 	if (IS_ERR(arvo_class))
 		return PTR_ERR(arvo_class);
-	arvo_class->dev_attrs = arvo_attributes;
-	arvo_class->dev_bin_attrs = arvo_bin_attributes;
+	arvo_class->dev_groups = arvo_groups;
 
 	retval = hid_register_driver(&arvo_driver);
 	if (retval)
diff --git a/drivers/hid/hid-roccat-isku.c b/drivers/hid/hid-roccat-isku.c
index 8023751d5257..bc62ed91e451 100644
--- a/drivers/hid/hid-roccat-isku.c
+++ b/drivers/hid/hid-roccat-isku.c
@@ -82,7 +82,7 @@ static ssize_t isku_sysfs_set_actual_profile(struct device *dev,
 	isku = hid_get_drvdata(dev_get_drvdata(dev));
 	usb_dev = interface_to_usbdev(to_usb_interface(dev));
 
-	retval = strict_strtoul(buf, 10, &profile);
+	retval = kstrtoul(buf, 10, &profile);
 	if (retval)
 		return retval;
 
@@ -109,12 +109,12 @@ static ssize_t isku_sysfs_set_actual_profile(struct device *dev,
 
 	return size;
 }
+static DEVICE_ATTR(actual_profile, 0660, isku_sysfs_show_actual_profile,
+		   isku_sysfs_set_actual_profile);
 
-static struct device_attribute isku_attributes[] = {
-	__ATTR(actual_profile, 0660,
-			isku_sysfs_show_actual_profile,
-			isku_sysfs_set_actual_profile),
-	__ATTR_NULL
+static struct attribute *isku_attrs[] = {
+	&dev_attr_actual_profile.attr,
+	NULL,
 };
 
 static ssize_t isku_sysfs_read(struct file *fp, struct kobject *kobj,
@@ -184,7 +184,8 @@ ISKU_SYSFS_R(thingy, THINGY) \
 ISKU_SYSFS_W(thingy, THINGY)
 
 #define ISKU_BIN_ATTR_RW(thingy, THINGY) \
-{ \
+ISKU_SYSFS_RW(thingy, THINGY); \
+static struct bin_attribute bin_attr_##thingy = { \
 	.attr = { .name = #thingy, .mode = 0660 }, \
 	.size = ISKU_SIZE_ ## THINGY, \
 	.read = isku_sysfs_read_ ## thingy, \
@@ -192,52 +193,64 @@ ISKU_SYSFS_W(thingy, THINGY)
 }
 
 #define ISKU_BIN_ATTR_R(thingy, THINGY) \
-{ \
+ISKU_SYSFS_R(thingy, THINGY); \
+static struct bin_attribute bin_attr_##thingy = { \
 	.attr = { .name = #thingy, .mode = 0440 }, \
 	.size = ISKU_SIZE_ ## THINGY, \
 	.read = isku_sysfs_read_ ## thingy, \
 }
 
 #define ISKU_BIN_ATTR_W(thingy, THINGY) \
-{ \
+ISKU_SYSFS_W(thingy, THINGY); \
+static struct bin_attribute bin_attr_##thingy = { \
 	.attr = { .name = #thingy, .mode = 0220 }, \
 	.size = ISKU_SIZE_ ## THINGY, \
 	.write = isku_sysfs_write_ ## thingy \
 }
 
-ISKU_SYSFS_RW(macro, MACRO)
-ISKU_SYSFS_RW(keys_function, KEYS_FUNCTION)
-ISKU_SYSFS_RW(keys_easyzone, KEYS_EASYZONE)
-ISKU_SYSFS_RW(keys_media, KEYS_MEDIA)
-ISKU_SYSFS_RW(keys_thumbster, KEYS_THUMBSTER)
-ISKU_SYSFS_RW(keys_macro, KEYS_MACRO)
-ISKU_SYSFS_RW(keys_capslock, KEYS_CAPSLOCK)
-ISKU_SYSFS_RW(light, LIGHT)
-ISKU_SYSFS_RW(key_mask, KEY_MASK)
-ISKU_SYSFS_RW(last_set, LAST_SET)
-ISKU_SYSFS_W(talk, TALK)
-ISKU_SYSFS_W(talkfx, TALKFX)
-ISKU_SYSFS_R(info, INFO)
-ISKU_SYSFS_W(control, CONTROL)
-ISKU_SYSFS_W(reset, RESET)
-
-static struct bin_attribute isku_bin_attributes[] = {
-	ISKU_BIN_ATTR_RW(macro, MACRO),
-	ISKU_BIN_ATTR_RW(keys_function, KEYS_FUNCTION),
-	ISKU_BIN_ATTR_RW(keys_easyzone, KEYS_EASYZONE),
-	ISKU_BIN_ATTR_RW(keys_media, KEYS_MEDIA),
-	ISKU_BIN_ATTR_RW(keys_thumbster, KEYS_THUMBSTER),
-	ISKU_BIN_ATTR_RW(keys_macro, KEYS_MACRO),
-	ISKU_BIN_ATTR_RW(keys_capslock, KEYS_CAPSLOCK),
-	ISKU_BIN_ATTR_RW(light, LIGHT),
-	ISKU_BIN_ATTR_RW(key_mask, KEY_MASK),
-	ISKU_BIN_ATTR_RW(last_set, LAST_SET),
-	ISKU_BIN_ATTR_W(talk, TALK),
-	ISKU_BIN_ATTR_W(talkfx, TALKFX),
-	ISKU_BIN_ATTR_R(info, INFO),
-	ISKU_BIN_ATTR_W(control, CONTROL),
-	ISKU_BIN_ATTR_W(reset, RESET),
-	__ATTR_NULL
+ISKU_BIN_ATTR_RW(macro, MACRO);
+ISKU_BIN_ATTR_RW(keys_function, KEYS_FUNCTION);
+ISKU_BIN_ATTR_RW(keys_easyzone, KEYS_EASYZONE);
+ISKU_BIN_ATTR_RW(keys_media, KEYS_MEDIA);
+ISKU_BIN_ATTR_RW(keys_thumbster, KEYS_THUMBSTER);
+ISKU_BIN_ATTR_RW(keys_macro, KEYS_MACRO);
+ISKU_BIN_ATTR_RW(keys_capslock, KEYS_CAPSLOCK);
+ISKU_BIN_ATTR_RW(light, LIGHT);
+ISKU_BIN_ATTR_RW(key_mask, KEY_MASK);
+ISKU_BIN_ATTR_RW(last_set, LAST_SET);
+ISKU_BIN_ATTR_W(talk, TALK);
+ISKU_BIN_ATTR_W(talkfx, TALKFX);
+ISKU_BIN_ATTR_W(control, CONTROL);
+ISKU_BIN_ATTR_W(reset, RESET);
+ISKU_BIN_ATTR_R(info, INFO);
+
+static struct bin_attribute *isku_bin_attributes[] = {
+	&bin_attr_macro,
+	&bin_attr_keys_function,
+	&bin_attr_keys_easyzone,
+	&bin_attr_keys_media,
+	&bin_attr_keys_thumbster,
+	&bin_attr_keys_macro,
+	&bin_attr_keys_capslock,
+	&bin_attr_light,
+	&bin_attr_key_mask,
+	&bin_attr_last_set,
+	&bin_attr_talk,
+	&bin_attr_talkfx,
+	&bin_attr_control,
+	&bin_attr_reset,
+	&bin_attr_info,
+	NULL,
+};
+
+static const struct attribute_group isku_group = {
+	.attrs = isku_attrs,
+	.bin_attrs = isku_bin_attributes,
+};
+
+static const struct attribute_group *isku_groups[] = {
+	&isku_group,
+	NULL,
 };
 
 static int isku_init_isku_device_struct(struct usb_device *usb_dev,
@@ -427,8 +440,7 @@ static int __init isku_init(void)
 	isku_class = class_create(THIS_MODULE, "isku");
 	if (IS_ERR(isku_class))
 		return PTR_ERR(isku_class);
-	isku_class->dev_attrs = isku_attributes;
-	isku_class->dev_bin_attrs = isku_bin_attributes;
+	isku_class->dev_groups = isku_groups;
 
 	retval = hid_register_driver(&isku_driver);
 	if (retval)
diff --git a/drivers/hid/hid-roccat-kone.c b/drivers/hid/hid-roccat-kone.c
index 7fae070788fa..6101816a7ddd 100644
--- a/drivers/hid/hid-roccat-kone.c
+++ b/drivers/hid/hid-roccat-kone.c
@@ -324,6 +324,8 @@ static ssize_t kone_sysfs_write_settings(struct file *fp, struct kobject *kobj,
 
 	return sizeof(struct kone_settings);
 }
+static BIN_ATTR(settings, 0660, kone_sysfs_read_settings,
+		kone_sysfs_write_settings, sizeof(struct kone_settings));
 
 static ssize_t kone_sysfs_read_profilex(struct file *fp,
 		struct kobject *kobj, struct bin_attribute *attr,
@@ -378,6 +380,19 @@ static ssize_t kone_sysfs_write_profilex(struct file *fp,
 
 	return sizeof(struct kone_profile);
 }
+#define PROFILE_ATTR(number)					\
+static struct bin_attribute bin_attr_profile##number = {	\
+	.attr = { .name = "profile" #number, .mode = 0660 },	\
+	.size = sizeof(struct kone_profile),			\
+	.read = kone_sysfs_read_profilex,			\
+	.write = kone_sysfs_write_profilex,			\
+	.private = &profile_numbers[number-1],			\
+};
+PROFILE_ATTR(1);
+PROFILE_ATTR(2);
+PROFILE_ATTR(3);
+PROFILE_ATTR(4);
+PROFILE_ATTR(5);
 
 static ssize_t kone_sysfs_show_actual_profile(struct device *dev,
 		struct device_attribute *attr, char *buf)
@@ -386,6 +401,7 @@ static ssize_t kone_sysfs_show_actual_profile(struct device *dev,
 			hid_get_drvdata(dev_get_drvdata(dev->parent->parent));
 	return snprintf(buf, PAGE_SIZE, "%d\n", kone->actual_profile);
 }
+static DEVICE_ATTR(actual_profile, 0440, kone_sysfs_show_actual_profile, NULL);
 
 static ssize_t kone_sysfs_show_actual_dpi(struct device *dev,
 		struct device_attribute *attr, char *buf)
@@ -394,6 +410,7 @@ static ssize_t kone_sysfs_show_actual_dpi(struct device *dev,
 			hid_get_drvdata(dev_get_drvdata(dev->parent->parent));
 	return snprintf(buf, PAGE_SIZE, "%d\n", kone->actual_dpi);
 }
+static DEVICE_ATTR(actual_dpi, 0440, kone_sysfs_show_actual_dpi, NULL);
 
 /* weight is read each time, since we don't get informed when it's changed */
 static ssize_t kone_sysfs_show_weight(struct device *dev,
@@ -416,6 +433,7 @@ static ssize_t kone_sysfs_show_weight(struct device *dev,
 		return retval;
 	return snprintf(buf, PAGE_SIZE, "%d\n", weight);
 }
+static DEVICE_ATTR(weight, 0440, kone_sysfs_show_weight, NULL);
 
 static ssize_t kone_sysfs_show_firmware_version(struct device *dev,
 		struct device_attribute *attr, char *buf)
@@ -424,6 +442,8 @@ static ssize_t kone_sysfs_show_firmware_version(struct device *dev,
 			hid_get_drvdata(dev_get_drvdata(dev->parent->parent));
 	return snprintf(buf, PAGE_SIZE, "%d\n", kone->firmware_version);
 }
+static DEVICE_ATTR(firmware_version, 0440, kone_sysfs_show_firmware_version,
+		   NULL);
 
 static ssize_t kone_sysfs_show_tcu(struct device *dev,
 		struct device_attribute *attr, char *buf)
@@ -456,7 +476,7 @@ static ssize_t kone_sysfs_set_tcu(struct device *dev,
 	kone = hid_get_drvdata(dev_get_drvdata(dev));
 	usb_dev = interface_to_usbdev(to_usb_interface(dev));
 
-	retval = strict_strtoul(buf, 10, &state);
+	retval = kstrtoul(buf, 10, &state);
 	if (retval)
 		return retval;
 
@@ -524,6 +544,7 @@ exit_unlock:
 	mutex_unlock(&kone->kone_lock);
 	return retval;
 }
+static DEVICE_ATTR(tcu, 0660, kone_sysfs_show_tcu, kone_sysfs_set_tcu);
 
 static ssize_t kone_sysfs_show_startup_profile(struct device *dev,
 		struct device_attribute *attr, char *buf)
@@ -545,7 +566,7 @@ static ssize_t kone_sysfs_set_startup_profile(struct device *dev,
 	kone = hid_get_drvdata(dev_get_drvdata(dev));
 	usb_dev = interface_to_usbdev(to_usb_interface(dev));
 
-	retval = strict_strtoul(buf, 10, &new_startup_profile);
+	retval = kstrtoul(buf, 10, &new_startup_profile);
 	if (retval)
 		return retval;
 
@@ -570,15 +591,17 @@ static ssize_t kone_sysfs_set_startup_profile(struct device *dev,
 	mutex_unlock(&kone->kone_lock);
 	return size;
 }
+static DEVICE_ATTR(startup_profile, 0660, kone_sysfs_show_startup_profile,
+		   kone_sysfs_set_startup_profile);
 
-static struct device_attribute kone_attributes[] = {
+static struct attribute *kone_attrs[] = {
 	/*
 	 * Read actual dpi settings.
 	 * Returns raw value for further processing. Refer to enum
 	 * kone_polling_rates to get real value.
 	 */
-	__ATTR(actual_dpi, 0440, kone_sysfs_show_actual_dpi, NULL),
-	__ATTR(actual_profile, 0440, kone_sysfs_show_actual_profile, NULL),
+	&dev_attr_actual_dpi.attr,
+	&dev_attr_actual_profile.attr,
 
 	/*
 	 * The mouse can be equipped with one of four supplied weights from 5
@@ -587,7 +610,7 @@ static struct device_attribute kone_attributes[] = {
 	 * by software. Refer to enum kone_weights to get corresponding real
 	 * weight.
 	 */
-	__ATTR(weight, 0440, kone_sysfs_show_weight, NULL),
+	&dev_attr_weight.attr,
 
 	/*
 	 * Prints firmware version stored in mouse as integer.
@@ -595,66 +618,38 @@ static struct device_attribute kone_attributes[] = {
 	 * to get the real version number the decimal point has to be shifted 2
 	 * positions to the left. E.g. a value of 138 means 1.38.
 	 */
-	__ATTR(firmware_version, 0440,
-			kone_sysfs_show_firmware_version, NULL),
+	&dev_attr_firmware_version.attr,
 
 	/*
 	 * Prints state of Tracking Control Unit as number where 0 = off and
 	 * 1 = on. Writing 0 deactivates tcu and writing 1 calibrates and
 	 * activates the tcu
 	 */
-	__ATTR(tcu, 0660, kone_sysfs_show_tcu, kone_sysfs_set_tcu),
+	&dev_attr_tcu.attr,
 
 	/* Prints and takes the number of the profile the mouse starts with */
-	__ATTR(startup_profile, 0660,
-			kone_sysfs_show_startup_profile,
-			kone_sysfs_set_startup_profile),
-	__ATTR_NULL
+	&dev_attr_startup_profile.attr,
+	NULL,
+};
+
+static struct bin_attribute *kone_bin_attributes[] = {
+	&bin_attr_settings,
+	&bin_attr_profile1,
+	&bin_attr_profile2,
+	&bin_attr_profile3,
+	&bin_attr_profile4,
+	&bin_attr_profile5,
+	NULL,
+};
+
+static const struct attribute_group kone_group = {
+	.attrs = kone_attrs,
+	.bin_attrs = kone_bin_attributes,
 };
 
-static struct bin_attribute kone_bin_attributes[] = {
-	{
-		.attr = { .name = "settings", .mode = 0660 },
-		.size = sizeof(struct kone_settings),
-		.read = kone_sysfs_read_settings,
-		.write = kone_sysfs_write_settings
-	},
-	{
-		.attr = { .name = "profile1", .mode = 0660 },
-		.size = sizeof(struct kone_profile),
-		.read = kone_sysfs_read_profilex,
-		.write = kone_sysfs_write_profilex,
-		.private = &profile_numbers[0]
-	},
-	{
-		.attr = { .name = "profile2", .mode = 0660 },
-		.size = sizeof(struct kone_profile),
-		.read = kone_sysfs_read_profilex,
-		.write = kone_sysfs_write_profilex,
-		.private = &profile_numbers[1]
-	},
-	{
-		.attr = { .name = "profile3", .mode = 0660 },
-		.size = sizeof(struct kone_profile),
-		.read = kone_sysfs_read_profilex,
-		.write = kone_sysfs_write_profilex,
-		.private = &profile_numbers[2]
-	},
-	{
-		.attr = { .name = "profile4", .mode = 0660 },
-		.size = sizeof(struct kone_profile),
-		.read = kone_sysfs_read_profilex,
-		.write = kone_sysfs_write_profilex,
-		.private = &profile_numbers[3]
-	},
-	{
-		.attr = { .name = "profile5", .mode = 0660 },
-		.size = sizeof(struct kone_profile),
-		.read = kone_sysfs_read_profilex,
-		.write = kone_sysfs_write_profilex,
-		.private = &profile_numbers[4]
-	},
-	__ATTR_NULL
+static const struct attribute_group *kone_groups[] = {
+	&kone_group,
+	NULL,
 };
 
 static int kone_init_kone_device_struct(struct usb_device *usb_dev,
@@ -891,8 +886,7 @@ static int __init kone_init(void)
 	kone_class = class_create(THIS_MODULE, "kone");
 	if (IS_ERR(kone_class))
 		return PTR_ERR(kone_class);
-	kone_class->dev_attrs = kone_attributes;
-	kone_class->dev_bin_attrs = kone_bin_attributes;
+	kone_class->dev_groups = kone_groups;
 
 	retval = hid_register_driver(&kone_driver);
 	if (retval)
diff --git a/drivers/hid/hid-roccat-koneplus.c b/drivers/hid/hid-roccat-koneplus.c
index 6a48fa3c7da9..5e99fcdc71b9 100644
--- a/drivers/hid/hid-roccat-koneplus.c
+++ b/drivers/hid/hid-roccat-koneplus.c
@@ -156,7 +156,8 @@ KONEPLUS_SYSFS_W(thingy, THINGY) \
 KONEPLUS_SYSFS_R(thingy, THINGY)
 
 #define KONEPLUS_BIN_ATTRIBUTE_RW(thingy, THINGY) \
-{ \
+KONEPLUS_SYSFS_RW(thingy, THINGY); \
+static struct bin_attribute bin_attr_##thingy = { \
 	.attr = { .name = #thingy, .mode = 0660 }, \
 	.size = KONEPLUS_SIZE_ ## THINGY, \
 	.read = koneplus_sysfs_read_ ## thingy, \
@@ -164,28 +165,29 @@ KONEPLUS_SYSFS_R(thingy, THINGY)
 }
 
 #define KONEPLUS_BIN_ATTRIBUTE_R(thingy, THINGY) \
-{ \
+KONEPLUS_SYSFS_R(thingy, THINGY); \
+static struct bin_attribute bin_attr_##thingy = { \
 	.attr = { .name = #thingy, .mode = 0440 }, \
 	.size = KONEPLUS_SIZE_ ## THINGY, \
 	.read = koneplus_sysfs_read_ ## thingy, \
 }
 
 #define KONEPLUS_BIN_ATTRIBUTE_W(thingy, THINGY) \
-{ \
+KONEPLUS_SYSFS_W(thingy, THINGY); \
+static struct bin_attribute bin_attr_##thingy = { \
 	.attr = { .name = #thingy, .mode = 0220 }, \
 	.size = KONEPLUS_SIZE_ ## THINGY, \
 	.write = koneplus_sysfs_write_ ## thingy \
 }
-
-KONEPLUS_SYSFS_W(control, CONTROL)
-KONEPLUS_SYSFS_RW(info, INFO)
-KONEPLUS_SYSFS_W(talk, TALK)
-KONEPLUS_SYSFS_W(macro, MACRO)
-KONEPLUS_SYSFS_RW(sensor, SENSOR)
-KONEPLUS_SYSFS_RW(tcu, TCU)
-KONEPLUS_SYSFS_R(tcu_image, TCU_IMAGE)
-KONEPLUS_SYSFS_RW(profile_settings, PROFILE_SETTINGS)
-KONEPLUS_SYSFS_RW(profile_buttons, PROFILE_BUTTONS)
+KONEPLUS_BIN_ATTRIBUTE_W(control, CONTROL);
+KONEPLUS_BIN_ATTRIBUTE_W(talk, TALK);
+KONEPLUS_BIN_ATTRIBUTE_W(macro, MACRO);
+KONEPLUS_BIN_ATTRIBUTE_R(tcu_image, TCU_IMAGE);
+KONEPLUS_BIN_ATTRIBUTE_RW(info, INFO);
+KONEPLUS_BIN_ATTRIBUTE_RW(sensor, SENSOR);
+KONEPLUS_BIN_ATTRIBUTE_RW(tcu, TCU);
+KONEPLUS_BIN_ATTRIBUTE_RW(profile_settings, PROFILE_SETTINGS);
+KONEPLUS_BIN_ATTRIBUTE_RW(profile_buttons, PROFILE_BUTTONS);
 
 static ssize_t koneplus_sysfs_read_profilex_settings(struct file *fp,
 		struct kobject *kobj, struct bin_attribute *attr, char *buf,
@@ -225,6 +227,25 @@ static ssize_t koneplus_sysfs_read_profilex_buttons(struct file *fp,
 			KONEPLUS_COMMAND_PROFILE_BUTTONS);
 }
 
+#define PROFILE_ATTR(number)						\
+static struct bin_attribute bin_attr_profile##number##_settings = {	\
+	.attr = { .name = "profile" #number "_settings", .mode = 0440 },	\
+	.size = KONEPLUS_SIZE_PROFILE_SETTINGS,				\
+	.read = koneplus_sysfs_read_profilex_settings,			\
+	.private = &profile_numbers[number-1],				\
+};									\
+static struct bin_attribute bin_attr_profile##number##_buttons = {	\
+	.attr = { .name = "profile" #number "_buttons", .mode = 0440 },	\
+	.size = KONEPLUS_SIZE_PROFILE_BUTTONS,				\
+	.read = koneplus_sysfs_read_profilex_buttons,			\
+	.private = &profile_numbers[number-1],				\
+};
+PROFILE_ATTR(1);
+PROFILE_ATTR(2);
+PROFILE_ATTR(3);
+PROFILE_ATTR(4);
+PROFILE_ATTR(5);
+
 static ssize_t koneplus_sysfs_show_actual_profile(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
@@ -246,7 +267,7 @@ static ssize_t koneplus_sysfs_set_actual_profile(struct device *dev,
 	koneplus = hid_get_drvdata(dev_get_drvdata(dev));
 	usb_dev = interface_to_usbdev(to_usb_interface(dev));
 
-	retval = strict_strtoul(buf, 10, &profile);
+	retval = kstrtoul(buf, 10, &profile);
 	if (retval)
 		return retval;
 
@@ -274,6 +295,12 @@ static ssize_t koneplus_sysfs_set_actual_profile(struct device *dev,
 
 	return size;
 }
+static DEVICE_ATTR(actual_profile, 0660,
+		   koneplus_sysfs_show_actual_profile,
+		   koneplus_sysfs_set_actual_profile);
+static DEVICE_ATTR(startup_profile, 0660,
+		   koneplus_sysfs_show_actual_profile,
+		   koneplus_sysfs_set_actual_profile);
 
 static ssize_t koneplus_sysfs_show_firmware_version(struct device *dev,
 		struct device_attribute *attr, char *buf)
@@ -293,90 +320,47 @@ static ssize_t koneplus_sysfs_show_firmware_version(struct device *dev,
 
 	return snprintf(buf, PAGE_SIZE, "%d\n", info.firmware_version);
 }
+static DEVICE_ATTR(firmware_version, 0440,
+		   koneplus_sysfs_show_firmware_version, NULL);
+
+static struct attribute *koneplus_attrs[] = {
+	&dev_attr_actual_profile.attr,
+	&dev_attr_startup_profile.attr,
+	&dev_attr_firmware_version.attr,
+	NULL,
+};
+
+static struct bin_attribute *koneplus_bin_attributes[] = {
+	&bin_attr_control,
+	&bin_attr_talk,
+	&bin_attr_macro,
+	&bin_attr_tcu_image,
+	&bin_attr_info,
+	&bin_attr_sensor,
+	&bin_attr_tcu,
+	&bin_attr_profile_settings,
+	&bin_attr_profile_buttons,
+	&bin_attr_profile1_settings,
+	&bin_attr_profile2_settings,
+	&bin_attr_profile3_settings,
+	&bin_attr_profile4_settings,
+	&bin_attr_profile5_settings,
+	&bin_attr_profile1_buttons,
+	&bin_attr_profile2_buttons,
+	&bin_attr_profile3_buttons,
+	&bin_attr_profile4_buttons,
+	&bin_attr_profile5_buttons,
+	NULL,
+};
 
-static struct device_attribute koneplus_attributes[] = {
-	__ATTR(actual_profile, 0660,
-			koneplus_sysfs_show_actual_profile,
-			koneplus_sysfs_set_actual_profile),
-	__ATTR(startup_profile, 0660,
-			koneplus_sysfs_show_actual_profile,
-			koneplus_sysfs_set_actual_profile),
-	__ATTR(firmware_version, 0440,
-			koneplus_sysfs_show_firmware_version, NULL),
-	__ATTR_NULL
+static const struct attribute_group koneplus_group = {
+	.attrs = koneplus_attrs,
+	.bin_attrs = koneplus_bin_attributes,
 };
 
-static struct bin_attribute koneplus_bin_attributes[] = {
-	KONEPLUS_BIN_ATTRIBUTE_W(control, CONTROL),
-	KONEPLUS_BIN_ATTRIBUTE_RW(info, INFO),
-	KONEPLUS_BIN_ATTRIBUTE_W(talk, TALK),
-	KONEPLUS_BIN_ATTRIBUTE_W(macro, MACRO),
-	KONEPLUS_BIN_ATTRIBUTE_RW(sensor, SENSOR),
-	KONEPLUS_BIN_ATTRIBUTE_RW(tcu, TCU),
-	KONEPLUS_BIN_ATTRIBUTE_R(tcu_image, TCU_IMAGE),
-	KONEPLUS_BIN_ATTRIBUTE_RW(profile_settings, PROFILE_SETTINGS),
-	KONEPLUS_BIN_ATTRIBUTE_RW(profile_buttons, PROFILE_BUTTONS),
-	{
-		.attr = { .name = "profile1_settings", .mode = 0440 },
-		.size = KONEPLUS_SIZE_PROFILE_SETTINGS,
-		.read = koneplus_sysfs_read_profilex_settings,
-		.private = &profile_numbers[0]
-	},
-	{
-		.attr = { .name = "profile2_settings", .mode = 0440 },
-		.size = KONEPLUS_SIZE_PROFILE_SETTINGS,
-		.read = koneplus_sysfs_read_profilex_settings,
-		.private = &profile_numbers[1]
-	},
-	{
-		.attr = { .name = "profile3_settings", .mode = 0440 },
-		.size = KONEPLUS_SIZE_PROFILE_SETTINGS,
-		.read = koneplus_sysfs_read_profilex_settings,
-		.private = &profile_numbers[2]
-	},
-	{
-		.attr = { .name = "profile4_settings", .mode = 0440 },
-		.size = KONEPLUS_SIZE_PROFILE_SETTINGS,
-		.read = koneplus_sysfs_read_profilex_settings,
-		.private = &profile_numbers[3]
-	},
-	{
-		.attr = { .name = "profile5_settings", .mode = 0440 },
-		.size = KONEPLUS_SIZE_PROFILE_SETTINGS,
-		.read = koneplus_sysfs_read_profilex_settings,
-		.private = &profile_numbers[4]
-	},
-	{
-		.attr = { .name = "profile1_buttons", .mode = 0440 },
-		.size = KONEPLUS_SIZE_PROFILE_BUTTONS,
-		.read = koneplus_sysfs_read_profilex_buttons,
-		.private = &profile_numbers[0]
-	},
-	{
-		.attr = { .name = "profile2_buttons", .mode = 0440 },
-		.size = KONEPLUS_SIZE_PROFILE_BUTTONS,
-		.read = koneplus_sysfs_read_profilex_buttons,
-		.private = &profile_numbers[1]
-	},
-	{
-		.attr = { .name = "profile3_buttons", .mode = 0440 },
-		.size = KONEPLUS_SIZE_PROFILE_BUTTONS,
-		.read = koneplus_sysfs_read_profilex_buttons,
-		.private = &profile_numbers[2]
-	},
-	{
-		.attr = { .name = "profile4_buttons", .mode = 0440 },
-		.size = KONEPLUS_SIZE_PROFILE_BUTTONS,
-		.read = koneplus_sysfs_read_profilex_buttons,
-		.private = &profile_numbers[3]
-	},
-	{
-		.attr = { .name = "profile5_buttons", .mode = 0440 },
-		.size = KONEPLUS_SIZE_PROFILE_BUTTONS,
-		.read = koneplus_sysfs_read_profilex_buttons,
-		.private = &profile_numbers[4]
-	},
-	__ATTR_NULL
+static const struct attribute_group *koneplus_groups[] = {
+	&koneplus_group,
+	NULL,
 };
 
 static int koneplus_init_koneplus_device_struct(struct usb_device *usb_dev,
@@ -572,8 +556,7 @@ static int __init koneplus_init(void)
 	koneplus_class = class_create(THIS_MODULE, "koneplus");
 	if (IS_ERR(koneplus_class))
 		return PTR_ERR(koneplus_class);
-	koneplus_class->dev_attrs = koneplus_attributes;
-	koneplus_class->dev_bin_attrs = koneplus_bin_attributes;
+	koneplus_class->dev_groups = koneplus_groups;
 
 	retval = hid_register_driver(&koneplus_driver);
 	if (retval)
diff --git a/drivers/hid/hid-roccat-konepure.c b/drivers/hid/hid-roccat-konepure.c
index c79d0b06c143..99a605ebb665 100644
--- a/drivers/hid/hid-roccat-konepure.c
+++ b/drivers/hid/hid-roccat-konepure.c
@@ -94,7 +94,8 @@ KONEPURE_SYSFS_W(thingy, THINGY) \
 KONEPURE_SYSFS_R(thingy, THINGY)
 
 #define KONEPURE_BIN_ATTRIBUTE_RW(thingy, THINGY) \
-{ \
+KONEPURE_SYSFS_RW(thingy, THINGY); \
+static struct bin_attribute bin_attr_##thingy = { \
 	.attr = { .name = #thingy, .mode = 0660 }, \
 	.size = KONEPURE_SIZE_ ## THINGY, \
 	.read = konepure_sysfs_read_ ## thingy, \
@@ -102,44 +103,56 @@ KONEPURE_SYSFS_R(thingy, THINGY)
 }
 
 #define KONEPURE_BIN_ATTRIBUTE_R(thingy, THINGY) \
-{ \
+KONEPURE_SYSFS_R(thingy, THINGY); \
+static struct bin_attribute bin_attr_##thingy = { \
 	.attr = { .name = #thingy, .mode = 0440 }, \
 	.size = KONEPURE_SIZE_ ## THINGY, \
 	.read = konepure_sysfs_read_ ## thingy, \
 }
 
 #define KONEPURE_BIN_ATTRIBUTE_W(thingy, THINGY) \
-{ \
+KONEPURE_SYSFS_W(thingy, THINGY); \
+static struct bin_attribute bin_attr_##thingy = { \
 	.attr = { .name = #thingy, .mode = 0220 }, \
 	.size = KONEPURE_SIZE_ ## THINGY, \
 	.write = konepure_sysfs_write_ ## thingy \
 }
 
-KONEPURE_SYSFS_RW(actual_profile, ACTUAL_PROFILE)
-KONEPURE_SYSFS_W(control, CONTROL)
-KONEPURE_SYSFS_RW(info, INFO)
-KONEPURE_SYSFS_W(talk, TALK)
-KONEPURE_SYSFS_W(macro, MACRO)
-KONEPURE_SYSFS_RW(sensor, SENSOR)
-KONEPURE_SYSFS_RW(tcu, TCU)
-KONEPURE_SYSFS_R(tcu_image, TCU_IMAGE)
-KONEPURE_SYSFS_RW(profile_settings, PROFILE_SETTINGS)
-KONEPURE_SYSFS_RW(profile_buttons, PROFILE_BUTTONS)
-
-static struct bin_attribute konepure_bin_attributes[] = {
-	KONEPURE_BIN_ATTRIBUTE_RW(actual_profile, ACTUAL_PROFILE),
-	KONEPURE_BIN_ATTRIBUTE_W(control, CONTROL),
-	KONEPURE_BIN_ATTRIBUTE_RW(info, INFO),
-	KONEPURE_BIN_ATTRIBUTE_W(talk, TALK),
-	KONEPURE_BIN_ATTRIBUTE_W(macro, MACRO),
-	KONEPURE_BIN_ATTRIBUTE_RW(sensor, SENSOR),
-	KONEPURE_BIN_ATTRIBUTE_RW(tcu, TCU),
-	KONEPURE_BIN_ATTRIBUTE_R(tcu_image, TCU_IMAGE),
-	KONEPURE_BIN_ATTRIBUTE_RW(profile_settings, PROFILE_SETTINGS),
-	KONEPURE_BIN_ATTRIBUTE_RW(profile_buttons, PROFILE_BUTTONS),
-	__ATTR_NULL
+KONEPURE_BIN_ATTRIBUTE_RW(actual_profile, ACTUAL_PROFILE);
+KONEPURE_BIN_ATTRIBUTE_RW(info, INFO);
+KONEPURE_BIN_ATTRIBUTE_RW(sensor, SENSOR);
+KONEPURE_BIN_ATTRIBUTE_RW(tcu, TCU);
+KONEPURE_BIN_ATTRIBUTE_RW(profile_settings, PROFILE_SETTINGS);
+KONEPURE_BIN_ATTRIBUTE_RW(profile_buttons, PROFILE_BUTTONS);
+KONEPURE_BIN_ATTRIBUTE_W(control, CONTROL);
+KONEPURE_BIN_ATTRIBUTE_W(talk, TALK);
+KONEPURE_BIN_ATTRIBUTE_W(macro, MACRO);
+KONEPURE_BIN_ATTRIBUTE_R(tcu_image, TCU_IMAGE);
+
+static struct bin_attribute *konepure_bin_attributes[] = {
+	&bin_attr_actual_profile,
+	&bin_attr_info,
+	&bin_attr_sensor,
+	&bin_attr_tcu,
+	&bin_attr_profile_settings,
+	&bin_attr_profile_buttons,
+	&bin_attr_control,
+	&bin_attr_talk,
+	&bin_attr_macro,
+	&bin_attr_tcu_image,
+	NULL,
+};
+
+static const struct attribute_group konepure_group = {
+	.bin_attrs = konepure_bin_attributes,
+};
+
+static const struct attribute_group *konepure_groups[] = {
+	&konepure_group,
+	NULL,
 };
 
+
 static int konepure_init_konepure_device_struct(struct usb_device *usb_dev,
 		struct konepure_device *konepure)
 {
@@ -262,6 +275,7 @@ static int konepure_raw_event(struct hid_device *hdev,
 
 static const struct hid_device_id konepure_devices[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ROCCAT, USB_DEVICE_ID_ROCCAT_KONEPURE) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_ROCCAT, USB_DEVICE_ID_ROCCAT_KONEPURE_OPTICAL) },
 	{ }
 };
 
@@ -282,7 +296,7 @@ static int __init konepure_init(void)
 	konepure_class = class_create(THIS_MODULE, "konepure");
 	if (IS_ERR(konepure_class))
 		return PTR_ERR(konepure_class);
-	konepure_class->dev_bin_attrs = konepure_bin_attributes;
+	konepure_class->dev_groups = konepure_groups;
 
 	retval = hid_register_driver(&konepure_driver);
 	if (retval)
@@ -300,5 +314,5 @@ module_init(konepure_init);
 module_exit(konepure_exit);
 
 MODULE_AUTHOR("Stefan Achatz");
-MODULE_DESCRIPTION("USB Roccat KonePure driver");
+MODULE_DESCRIPTION("USB Roccat KonePure/Optical driver");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/hid/hid-roccat-kovaplus.c b/drivers/hid/hid-roccat-kovaplus.c
index b8b37789b864..0c8e1ef0b67d 100644
--- a/drivers/hid/hid-roccat-kovaplus.c
+++ b/drivers/hid/hid-roccat-kovaplus.c
@@ -197,31 +197,25 @@ KOVAPLUS_SYSFS_W(thingy, THINGY) \
 KOVAPLUS_SYSFS_R(thingy, THINGY)
 
 #define KOVAPLUS_BIN_ATTRIBUTE_RW(thingy, THINGY) \
-{ \
+KOVAPLUS_SYSFS_RW(thingy, THINGY); \
+static struct bin_attribute bin_attr_##thingy = { \
 	.attr = { .name = #thingy, .mode = 0660 }, \
 	.size = KOVAPLUS_SIZE_ ## THINGY, \
 	.read = kovaplus_sysfs_read_ ## thingy, \
 	.write = kovaplus_sysfs_write_ ## thingy \
 }
 
-#define KOVAPLUS_BIN_ATTRIBUTE_R(thingy, THINGY) \
-{ \
-	.attr = { .name = #thingy, .mode = 0440 }, \
-	.size = KOVAPLUS_SIZE_ ## THINGY, \
-	.read = kovaplus_sysfs_read_ ## thingy, \
-}
-
 #define KOVAPLUS_BIN_ATTRIBUTE_W(thingy, THINGY) \
-{ \
+KOVAPLUS_SYSFS_W(thingy, THINGY); \
+static struct bin_attribute bin_attr_##thingy = { \
 	.attr = { .name = #thingy, .mode = 0220 }, \
 	.size = KOVAPLUS_SIZE_ ## THINGY, \
 	.write = kovaplus_sysfs_write_ ## thingy \
 }
-
-KOVAPLUS_SYSFS_W(control, CONTROL)
-KOVAPLUS_SYSFS_RW(info, INFO)
-KOVAPLUS_SYSFS_RW(profile_settings, PROFILE_SETTINGS)
-KOVAPLUS_SYSFS_RW(profile_buttons, PROFILE_BUTTONS)
+KOVAPLUS_BIN_ATTRIBUTE_W(control, CONTROL);
+KOVAPLUS_BIN_ATTRIBUTE_RW(info, INFO);
+KOVAPLUS_BIN_ATTRIBUTE_RW(profile_settings, PROFILE_SETTINGS);
+KOVAPLUS_BIN_ATTRIBUTE_RW(profile_buttons, PROFILE_BUTTONS);
 
 static ssize_t kovaplus_sysfs_read_profilex_settings(struct file *fp,
 		struct kobject *kobj, struct bin_attribute *attr, char *buf,
@@ -261,6 +255,25 @@ static ssize_t kovaplus_sysfs_read_profilex_buttons(struct file *fp,
 			KOVAPLUS_COMMAND_PROFILE_BUTTONS);
 }
 
+#define PROFILE_ATTR(number)						\
+static struct bin_attribute bin_attr_profile##number##_settings = {	\
+	.attr = { .name = "profile" #number "_settings", .mode = 0440 },	\
+	.size = KOVAPLUS_SIZE_PROFILE_SETTINGS,				\
+	.read = kovaplus_sysfs_read_profilex_settings,			\
+	.private = &profile_numbers[number-1],				\
+};									\
+static struct bin_attribute bin_attr_profile##number##_buttons = {	\
+	.attr = { .name = "profile" #number "_buttons", .mode = 0440 },	\
+	.size = KOVAPLUS_SIZE_PROFILE_BUTTONS,				\
+	.read = kovaplus_sysfs_read_profilex_buttons,			\
+	.private = &profile_numbers[number-1],				\
+};
+PROFILE_ATTR(1);
+PROFILE_ATTR(2);
+PROFILE_ATTR(3);
+PROFILE_ATTR(4);
+PROFILE_ATTR(5);
+
 static ssize_t kovaplus_sysfs_show_actual_profile(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
@@ -282,7 +295,7 @@ static ssize_t kovaplus_sysfs_set_actual_profile(struct device *dev,
 	kovaplus = hid_get_drvdata(dev_get_drvdata(dev));
 	usb_dev = interface_to_usbdev(to_usb_interface(dev));
 
-	retval = strict_strtoul(buf, 10, &profile);
+	retval = kstrtoul(buf, 10, &profile);
 	if (retval)
 		return retval;
 
@@ -310,6 +323,9 @@ static ssize_t kovaplus_sysfs_set_actual_profile(struct device *dev,
 
 	return size;
 }
+static DEVICE_ATTR(actual_profile, 0660,
+		   kovaplus_sysfs_show_actual_profile,
+		   kovaplus_sysfs_set_actual_profile);
 
 static ssize_t kovaplus_sysfs_show_actual_cpi(struct device *dev,
 		struct device_attribute *attr, char *buf)
@@ -318,6 +334,7 @@ static ssize_t kovaplus_sysfs_show_actual_cpi(struct device *dev,
 			hid_get_drvdata(dev_get_drvdata(dev->parent->parent));
 	return snprintf(buf, PAGE_SIZE, "%d\n", kovaplus->actual_cpi);
 }
+static DEVICE_ATTR(actual_cpi, 0440, kovaplus_sysfs_show_actual_cpi, NULL);
 
 static ssize_t kovaplus_sysfs_show_actual_sensitivity_x(struct device *dev,
 		struct device_attribute *attr, char *buf)
@@ -326,6 +343,8 @@ static ssize_t kovaplus_sysfs_show_actual_sensitivity_x(struct device *dev,
 			hid_get_drvdata(dev_get_drvdata(dev->parent->parent));
 	return snprintf(buf, PAGE_SIZE, "%d\n", kovaplus->actual_x_sensitivity);
 }
+static DEVICE_ATTR(actual_sensitivity_x, 0440,
+		   kovaplus_sysfs_show_actual_sensitivity_x, NULL);
 
 static ssize_t kovaplus_sysfs_show_actual_sensitivity_y(struct device *dev,
 		struct device_attribute *attr, char *buf)
@@ -334,6 +353,8 @@ static ssize_t kovaplus_sysfs_show_actual_sensitivity_y(struct device *dev,
 			hid_get_drvdata(dev_get_drvdata(dev->parent->parent));
 	return snprintf(buf, PAGE_SIZE, "%d\n", kovaplus->actual_y_sensitivity);
 }
+static DEVICE_ATTR(actual_sensitivity_y, 0440,
+		   kovaplus_sysfs_show_actual_sensitivity_y, NULL);
 
 static ssize_t kovaplus_sysfs_show_firmware_version(struct device *dev,
 		struct device_attribute *attr, char *buf)
@@ -353,88 +374,44 @@ static ssize_t kovaplus_sysfs_show_firmware_version(struct device *dev,
 
 	return snprintf(buf, PAGE_SIZE, "%d\n", info.firmware_version);
 }
+static DEVICE_ATTR(firmware_version, 0440,
+		   kovaplus_sysfs_show_firmware_version, NULL);
+
+static struct attribute *kovaplus_attrs[] = {
+	&dev_attr_actual_cpi.attr,
+	&dev_attr_firmware_version.attr,
+	&dev_attr_actual_profile.attr,
+	&dev_attr_actual_sensitivity_x.attr,
+	&dev_attr_actual_sensitivity_y.attr,
+	NULL,
+};
+
+static struct bin_attribute *kovaplus_bin_attributes[] = {
+	&bin_attr_control,
+	&bin_attr_info,
+	&bin_attr_profile_settings,
+	&bin_attr_profile_buttons,
+	&bin_attr_profile1_settings,
+	&bin_attr_profile2_settings,
+	&bin_attr_profile3_settings,
+	&bin_attr_profile4_settings,
+	&bin_attr_profile5_settings,
+	&bin_attr_profile1_buttons,
+	&bin_attr_profile2_buttons,
+	&bin_attr_profile3_buttons,
+	&bin_attr_profile4_buttons,
+	&bin_attr_profile5_buttons,
+	NULL,
+};
 
-static struct device_attribute kovaplus_attributes[] = {
-	__ATTR(actual_cpi, 0440,
-		kovaplus_sysfs_show_actual_cpi, NULL),
-	__ATTR(firmware_version, 0440,
-		kovaplus_sysfs_show_firmware_version, NULL),
-	__ATTR(actual_profile, 0660,
-		kovaplus_sysfs_show_actual_profile,
-		kovaplus_sysfs_set_actual_profile),
-	__ATTR(actual_sensitivity_x, 0440,
-		kovaplus_sysfs_show_actual_sensitivity_x, NULL),
-	__ATTR(actual_sensitivity_y, 0440,
-		kovaplus_sysfs_show_actual_sensitivity_y, NULL),
-	__ATTR_NULL
+static const struct attribute_group kovaplus_group = {
+	.attrs = kovaplus_attrs,
+	.bin_attrs = kovaplus_bin_attributes,
 };
 
-static struct bin_attribute kovaplus_bin_attributes[] = {
-	KOVAPLUS_BIN_ATTRIBUTE_W(control, CONTROL),
-	KOVAPLUS_BIN_ATTRIBUTE_RW(info, INFO),
-	KOVAPLUS_BIN_ATTRIBUTE_RW(profile_settings, PROFILE_SETTINGS),
-	KOVAPLUS_BIN_ATTRIBUTE_RW(profile_buttons, PROFILE_BUTTONS),
-	{
-		.attr = { .name = "profile1_settings", .mode = 0440 },
-		.size = KOVAPLUS_SIZE_PROFILE_SETTINGS,
-		.read = kovaplus_sysfs_read_profilex_settings,
-		.private = &profile_numbers[0]
-	},
-	{
-		.attr = { .name = "profile2_settings", .mode = 0440 },
-		.size = KOVAPLUS_SIZE_PROFILE_SETTINGS,
-		.read = kovaplus_sysfs_read_profilex_settings,
-		.private = &profile_numbers[1]
-	},
-	{
-		.attr = { .name = "profile3_settings", .mode = 0440 },
-		.size = KOVAPLUS_SIZE_PROFILE_SETTINGS,
-		.read = kovaplus_sysfs_read_profilex_settings,
-		.private = &profile_numbers[2]
-	},
-	{
-		.attr = { .name = "profile4_settings", .mode = 0440 },
-		.size = KOVAPLUS_SIZE_PROFILE_SETTINGS,
-		.read = kovaplus_sysfs_read_profilex_settings,
-		.private = &profile_numbers[3]
-	},
-	{
-		.attr = { .name = "profile5_settings", .mode = 0440 },
-		.size = KOVAPLUS_SIZE_PROFILE_SETTINGS,
-		.read = kovaplus_sysfs_read_profilex_settings,
-		.private = &profile_numbers[4]
-	},
-	{
-		.attr = { .name = "profile1_buttons", .mode = 0440 },
-		.size = KOVAPLUS_SIZE_PROFILE_BUTTONS,
-		.read = kovaplus_sysfs_read_profilex_buttons,
-		.private = &profile_numbers[0]
-	},
-	{
-		.attr = { .name = "profile2_buttons", .mode = 0440 },
-		.size = KOVAPLUS_SIZE_PROFILE_BUTTONS,
-		.read = kovaplus_sysfs_read_profilex_buttons,
-		.private = &profile_numbers[1]
-	},
-	{
-		.attr = { .name = "profile3_buttons", .mode = 0440 },
-		.size = KOVAPLUS_SIZE_PROFILE_BUTTONS,
-		.read = kovaplus_sysfs_read_profilex_buttons,
-		.private = &profile_numbers[2]
-	},
-	{
-		.attr = { .name = "profile4_buttons", .mode = 0440 },
-		.size = KOVAPLUS_SIZE_PROFILE_BUTTONS,
-		.read = kovaplus_sysfs_read_profilex_buttons,
-		.private = &profile_numbers[3]
-	},
-	{
-		.attr = { .name = "profile5_buttons", .mode = 0440 },
-		.size = KOVAPLUS_SIZE_PROFILE_BUTTONS,
-		.read = kovaplus_sysfs_read_profilex_buttons,
-		.private = &profile_numbers[4]
-	},
-	__ATTR_NULL
+static const struct attribute_group *kovaplus_groups[] = {
+	&kovaplus_group,
+	NULL,
 };
 
 static int kovaplus_init_kovaplus_device_struct(struct usb_device *usb_dev,
@@ -662,8 +639,7 @@ static int __init kovaplus_init(void)
 	kovaplus_class = class_create(THIS_MODULE, "kovaplus");
 	if (IS_ERR(kovaplus_class))
 		return PTR_ERR(kovaplus_class);
-	kovaplus_class->dev_attrs = kovaplus_attributes;
-	kovaplus_class->dev_bin_attrs = kovaplus_bin_attributes;
+	kovaplus_class->dev_groups = kovaplus_groups;
 
 	retval = hid_register_driver(&kovaplus_driver);
 	if (retval)
diff --git a/drivers/hid/hid-roccat-pyra.c b/drivers/hid/hid-roccat-pyra.c
index d4f1e3bee590..1a07e07d99a0 100644
--- a/drivers/hid/hid-roccat-pyra.c
+++ b/drivers/hid/hid-roccat-pyra.c
@@ -156,7 +156,8 @@ PYRA_SYSFS_W(thingy, THINGY) \
 PYRA_SYSFS_R(thingy, THINGY)
 
 #define PYRA_BIN_ATTRIBUTE_RW(thingy, THINGY) \
-{ \
+PYRA_SYSFS_RW(thingy, THINGY); \
+static struct bin_attribute bin_attr_##thingy = { \
 	.attr = { .name = #thingy, .mode = 0660 }, \
 	.size = PYRA_SIZE_ ## THINGY, \
 	.read = pyra_sysfs_read_ ## thingy, \
@@ -164,24 +165,25 @@ PYRA_SYSFS_R(thingy, THINGY)
 }
 
 #define PYRA_BIN_ATTRIBUTE_R(thingy, THINGY) \
-{ \
+PYRA_SYSFS_R(thingy, THINGY); \
+static struct bin_attribute bin_attr_##thingy = { \
 	.attr = { .name = #thingy, .mode = 0440 }, \
 	.size = PYRA_SIZE_ ## THINGY, \
 	.read = pyra_sysfs_read_ ## thingy, \
 }
 
 #define PYRA_BIN_ATTRIBUTE_W(thingy, THINGY) \
-{ \
+PYRA_SYSFS_W(thingy, THINGY); \
+static struct bin_attribute bin_attr_##thingy = { \
 	.attr = { .name = #thingy, .mode = 0220 }, \
 	.size = PYRA_SIZE_ ## THINGY, \
 	.write = pyra_sysfs_write_ ## thingy \
 }
 
-PYRA_SYSFS_W(control, CONTROL)
-PYRA_SYSFS_RW(info, INFO)
-PYRA_SYSFS_RW(profile_settings, PROFILE_SETTINGS)
-PYRA_SYSFS_RW(profile_buttons, PROFILE_BUTTONS)
-PYRA_SYSFS_R(settings, SETTINGS)
+PYRA_BIN_ATTRIBUTE_W(control, CONTROL);
+PYRA_BIN_ATTRIBUTE_RW(info, INFO);
+PYRA_BIN_ATTRIBUTE_RW(profile_settings, PROFILE_SETTINGS);
+PYRA_BIN_ATTRIBUTE_RW(profile_buttons, PROFILE_BUTTONS);
 
 static ssize_t pyra_sysfs_read_profilex_settings(struct file *fp,
 		struct kobject *kobj, struct bin_attribute *attr, char *buf,
@@ -221,6 +223,25 @@ static ssize_t pyra_sysfs_read_profilex_buttons(struct file *fp,
 			PYRA_COMMAND_PROFILE_BUTTONS);
 }
 
+#define PROFILE_ATTR(number)						\
+static struct bin_attribute bin_attr_profile##number##_settings = {	\
+	.attr = { .name = "profile" #number "_settings", .mode = 0440 },	\
+	.size = PYRA_SIZE_PROFILE_SETTINGS,				\
+	.read = pyra_sysfs_read_profilex_settings,			\
+	.private = &profile_numbers[number-1],				\
+};									\
+static struct bin_attribute bin_attr_profile##number##_buttons = {	\
+	.attr = { .name = "profile" #number "_buttons", .mode = 0440 },	\
+	.size = PYRA_SIZE_PROFILE_BUTTONS,				\
+	.read = pyra_sysfs_read_profilex_buttons,			\
+	.private = &profile_numbers[number-1],				\
+};
+PROFILE_ATTR(1);
+PROFILE_ATTR(2);
+PROFILE_ATTR(3);
+PROFILE_ATTR(4);
+PROFILE_ATTR(5);
+
 static ssize_t pyra_sysfs_write_settings(struct file *fp,
 		struct kobject *kobj, struct bin_attribute *attr, char *buf,
 		loff_t off, size_t count)
@@ -258,6 +279,11 @@ static ssize_t pyra_sysfs_write_settings(struct file *fp,
 	return PYRA_SIZE_SETTINGS;
 }
 
+PYRA_SYSFS_R(settings, SETTINGS);
+static struct bin_attribute bin_attr_settings =
+	__BIN_ATTR(settings, (S_IWUSR | S_IRUGO),
+		   pyra_sysfs_read_settings, pyra_sysfs_write_settings,
+		   PYRA_SIZE_SETTINGS);
 
 static ssize_t pyra_sysfs_show_actual_cpi(struct device *dev,
 		struct device_attribute *attr, char *buf)
@@ -266,6 +292,7 @@ static ssize_t pyra_sysfs_show_actual_cpi(struct device *dev,
 			hid_get_drvdata(dev_get_drvdata(dev->parent->parent));
 	return snprintf(buf, PAGE_SIZE, "%d\n", pyra->actual_cpi);
 }
+static DEVICE_ATTR(actual_cpi, 0440, pyra_sysfs_show_actual_cpi, NULL);
 
 static ssize_t pyra_sysfs_show_actual_profile(struct device *dev,
 		struct device_attribute *attr, char *buf)
@@ -282,6 +309,8 @@ static ssize_t pyra_sysfs_show_actual_profile(struct device *dev,
 
 	return snprintf(buf, PAGE_SIZE, "%d\n", settings.startup_profile);
 }
+static DEVICE_ATTR(actual_profile, 0440, pyra_sysfs_show_actual_profile, NULL);
+static DEVICE_ATTR(startup_profile, 0440, pyra_sysfs_show_actual_profile, NULL);
 
 static ssize_t pyra_sysfs_show_firmware_version(struct device *dev,
 		struct device_attribute *attr, char *buf)
@@ -301,84 +330,44 @@ static ssize_t pyra_sysfs_show_firmware_version(struct device *dev,
 
 	return snprintf(buf, PAGE_SIZE, "%d\n", info.firmware_version);
 }
+static DEVICE_ATTR(firmware_version, 0440, pyra_sysfs_show_firmware_version,
+		   NULL);
+
+static struct attribute *pyra_attrs[] = {
+	&dev_attr_actual_cpi.attr,
+	&dev_attr_actual_profile.attr,
+	&dev_attr_firmware_version.attr,
+	&dev_attr_startup_profile.attr,
+	NULL,
+};
+
+static struct bin_attribute *pyra_bin_attributes[] = {
+	&bin_attr_control,
+	&bin_attr_info,
+	&bin_attr_profile_settings,
+	&bin_attr_profile_buttons,
+	&bin_attr_settings,
+	&bin_attr_profile1_settings,
+	&bin_attr_profile2_settings,
+	&bin_attr_profile3_settings,
+	&bin_attr_profile4_settings,
+	&bin_attr_profile5_settings,
+	&bin_attr_profile1_buttons,
+	&bin_attr_profile2_buttons,
+	&bin_attr_profile3_buttons,
+	&bin_attr_profile4_buttons,
+	&bin_attr_profile5_buttons,
+	NULL,
+};
 
-static struct device_attribute pyra_attributes[] = {
-	__ATTR(actual_cpi, 0440, pyra_sysfs_show_actual_cpi, NULL),
-	__ATTR(actual_profile, 0440, pyra_sysfs_show_actual_profile, NULL),
-	__ATTR(firmware_version, 0440,
-			pyra_sysfs_show_firmware_version, NULL),
-	__ATTR(startup_profile, 0440,
-			pyra_sysfs_show_actual_profile, NULL),
-	__ATTR_NULL
+static const struct attribute_group pyra_group = {
+	.attrs = pyra_attrs,
+	.bin_attrs = pyra_bin_attributes,
 };
 
-static struct bin_attribute pyra_bin_attributes[] = {
-	PYRA_BIN_ATTRIBUTE_W(control, CONTROL),
-	PYRA_BIN_ATTRIBUTE_RW(info, INFO),
-	PYRA_BIN_ATTRIBUTE_RW(profile_settings, PROFILE_SETTINGS),
-	PYRA_BIN_ATTRIBUTE_RW(profile_buttons, PROFILE_BUTTONS),
-	PYRA_BIN_ATTRIBUTE_RW(settings, SETTINGS),
-	{
-		.attr = { .name = "profile1_settings", .mode = 0440 },
-		.size = PYRA_SIZE_PROFILE_SETTINGS,
-		.read = pyra_sysfs_read_profilex_settings,
-		.private = &profile_numbers[0]
-	},
-	{
-		.attr = { .name = "profile2_settings", .mode = 0440 },
-		.size = PYRA_SIZE_PROFILE_SETTINGS,
-		.read = pyra_sysfs_read_profilex_settings,
-		.private = &profile_numbers[1]
-	},
-	{
-		.attr = { .name = "profile3_settings", .mode = 0440 },
-		.size = PYRA_SIZE_PROFILE_SETTINGS,
-		.read = pyra_sysfs_read_profilex_settings,
-		.private = &profile_numbers[2]
-	},
-	{
-		.attr = { .name = "profile4_settings", .mode = 0440 },
-		.size = PYRA_SIZE_PROFILE_SETTINGS,
-		.read = pyra_sysfs_read_profilex_settings,
-		.private = &profile_numbers[3]
-	},
-	{
-		.attr = { .name = "profile5_settings", .mode = 0440 },
-		.size = PYRA_SIZE_PROFILE_SETTINGS,
-		.read = pyra_sysfs_read_profilex_settings,
-		.private = &profile_numbers[4]
-	},
-	{
-		.attr = { .name = "profile1_buttons", .mode = 0440 },
-		.size = PYRA_SIZE_PROFILE_BUTTONS,
-		.read = pyra_sysfs_read_profilex_buttons,
-		.private = &profile_numbers[0]
-	},
-	{
-		.attr = { .name = "profile2_buttons", .mode = 0440 },
-		.size = PYRA_SIZE_PROFILE_BUTTONS,
-		.read = pyra_sysfs_read_profilex_buttons,
-		.private = &profile_numbers[1]
-	},
-	{
-		.attr = { .name = "profile3_buttons", .mode = 0440 },
-		.size = PYRA_SIZE_PROFILE_BUTTONS,
-		.read = pyra_sysfs_read_profilex_buttons,
-		.private = &profile_numbers[2]
-	},
-	{
-		.attr = { .name = "profile4_buttons", .mode = 0440 },
-		.size = PYRA_SIZE_PROFILE_BUTTONS,
-		.read = pyra_sysfs_read_profilex_buttons,
-		.private = &profile_numbers[3]
-	},
-	{
-		.attr = { .name = "profile5_buttons", .mode = 0440 },
-		.size = PYRA_SIZE_PROFILE_BUTTONS,
-		.read = pyra_sysfs_read_profilex_buttons,
-		.private = &profile_numbers[4]
-	},
-	__ATTR_NULL
+static const struct attribute_group *pyra_groups[] = {
+	&pyra_group,
+	NULL,
 };
 
 static int pyra_init_pyra_device_struct(struct usb_device *usb_dev,
@@ -600,8 +589,7 @@ static int __init pyra_init(void)
 	pyra_class = class_create(THIS_MODULE, "pyra");
 	if (IS_ERR(pyra_class))
 		return PTR_ERR(pyra_class);
-	pyra_class->dev_attrs = pyra_attributes;
-	pyra_class->dev_bin_attrs = pyra_bin_attributes;
+	pyra_class->dev_groups = pyra_groups;
 
 	retval = hid_register_driver(&pyra_driver);
 	if (retval)
diff --git a/drivers/hid/hid-roccat-savu.c b/drivers/hid/hid-roccat-savu.c
index 31747a29c093..0332267199d5 100644
--- a/drivers/hid/hid-roccat-savu.c
+++ b/drivers/hid/hid-roccat-savu.c
@@ -94,44 +94,48 @@ SAVU_SYSFS_W(thingy, THINGY) \
 SAVU_SYSFS_R(thingy, THINGY)
 
 #define SAVU_BIN_ATTRIBUTE_RW(thingy, THINGY) \
-{ \
+SAVU_SYSFS_RW(thingy, THINGY); \
+static struct bin_attribute bin_attr_##thingy = { \
 	.attr = { .name = #thingy, .mode = 0660 }, \
 	.size = SAVU_SIZE_ ## THINGY, \
 	.read = savu_sysfs_read_ ## thingy, \
 	.write = savu_sysfs_write_ ## thingy \
 }
 
-#define SAVU_BIN_ATTRIBUTE_R(thingy, THINGY) \
-{ \
-	.attr = { .name = #thingy, .mode = 0440 }, \
-	.size = SAVU_SIZE_ ## THINGY, \
-	.read = savu_sysfs_read_ ## thingy, \
-}
-
 #define SAVU_BIN_ATTRIBUTE_W(thingy, THINGY) \
-{ \
+SAVU_SYSFS_W(thingy, THINGY); \
+static struct bin_attribute bin_attr_##thingy = { \
 	.attr = { .name = #thingy, .mode = 0220 }, \
 	.size = SAVU_SIZE_ ## THINGY, \
 	.write = savu_sysfs_write_ ## thingy \
 }
 
-SAVU_SYSFS_W(control, CONTROL)
-SAVU_SYSFS_RW(profile, PROFILE)
-SAVU_SYSFS_RW(general, GENERAL)
-SAVU_SYSFS_RW(buttons, BUTTONS)
-SAVU_SYSFS_RW(macro, MACRO)
-SAVU_SYSFS_RW(info, INFO)
-SAVU_SYSFS_RW(sensor, SENSOR)
-
-static struct bin_attribute savu_bin_attributes[] = {
-	SAVU_BIN_ATTRIBUTE_W(control, CONTROL),
-	SAVU_BIN_ATTRIBUTE_RW(profile, PROFILE),
-	SAVU_BIN_ATTRIBUTE_RW(general, GENERAL),
-	SAVU_BIN_ATTRIBUTE_RW(buttons, BUTTONS),
-	SAVU_BIN_ATTRIBUTE_RW(macro, MACRO),
-	SAVU_BIN_ATTRIBUTE_RW(info, INFO),
-	SAVU_BIN_ATTRIBUTE_RW(sensor, SENSOR),
-	__ATTR_NULL
+SAVU_BIN_ATTRIBUTE_W(control, CONTROL);
+SAVU_BIN_ATTRIBUTE_RW(profile, PROFILE);
+SAVU_BIN_ATTRIBUTE_RW(general, GENERAL);
+SAVU_BIN_ATTRIBUTE_RW(buttons, BUTTONS);
+SAVU_BIN_ATTRIBUTE_RW(macro, MACRO);
+SAVU_BIN_ATTRIBUTE_RW(info, INFO);
+SAVU_BIN_ATTRIBUTE_RW(sensor, SENSOR);
+
+static struct bin_attribute *savu_bin_attributes[] = {
+	&bin_attr_control,
+	&bin_attr_profile,
+	&bin_attr_general,
+	&bin_attr_buttons,
+	&bin_attr_macro,
+	&bin_attr_info,
+	&bin_attr_sensor,
+	NULL,
+};
+
+static const struct attribute_group savu_group = {
+	.bin_attrs = savu_bin_attributes,
+};
+
+static const struct attribute_group *savu_groups[] = {
+	&savu_group,
+	NULL,
 };
 
 static int savu_init_savu_device_struct(struct usb_device *usb_dev,
@@ -294,7 +298,7 @@ static int __init savu_init(void)
 	savu_class = class_create(THIS_MODULE, "savu");
 	if (IS_ERR(savu_class))
 		return PTR_ERR(savu_class);
-	savu_class->dev_bin_attrs = savu_bin_attributes;
+	savu_class->dev_groups = savu_groups;
 
 	retval = hid_register_driver(&savu_driver);
 	if (retval)
diff --git a/drivers/hid/hid-sensor-hub.c b/drivers/hid/hid-sensor-hub.c
index ca7498107327..10e1581022cf 100644
--- a/drivers/hid/hid-sensor-hub.c
+++ b/drivers/hid/hid-sensor-hub.c
@@ -103,8 +103,7 @@ static int sensor_hub_get_physical_device_count(
 
 	list_for_each_entry(report, &report_enum->report_list, list) {
 		field = report->field[0];
-		if (report->maxfield && field &&
-					field->physical)
+		if (report->maxfield && field && field->physical)
 			cnt++;
 	}
 
@@ -192,12 +191,12 @@ int sensor_hub_set_feature(struct hid_sensor_hub_device *hsdev, u32 report_id,
 				u32 field_index, s32 value)
 {
 	struct hid_report *report;
-	struct sensor_hub_data *data =  hid_get_drvdata(hsdev->hdev);
+	struct sensor_hub_data *data = hid_get_drvdata(hsdev->hdev);
 	int ret = 0;
 
 	mutex_lock(&data->mutex);
 	report = sensor_hub_report(report_id, hsdev->hdev, HID_FEATURE_REPORT);
-	if (!report || (field_index >=  report->maxfield)) {
+	if (!report || (field_index >= report->maxfield)) {
 		ret = -EINVAL;
 		goto done_proc;
 	}
@@ -216,12 +215,13 @@ int sensor_hub_get_feature(struct hid_sensor_hub_device *hsdev, u32 report_id,
 				u32 field_index, s32 *value)
 {
 	struct hid_report *report;
-	struct sensor_hub_data *data =  hid_get_drvdata(hsdev->hdev);
+	struct sensor_hub_data *data = hid_get_drvdata(hsdev->hdev);
 	int ret = 0;
 
 	mutex_lock(&data->mutex);
 	report = sensor_hub_report(report_id, hsdev->hdev, HID_FEATURE_REPORT);
-	if (!report || (field_index >=  report->maxfield)) {
+	if (!report || (field_index >= report->maxfield) ||
+	    report->field[field_index]->report_count < 1) {
 		ret = -EINVAL;
 		goto done_proc;
 	}
@@ -241,7 +241,7 @@ int sensor_hub_input_attr_get_raw_value(struct hid_sensor_hub_device *hsdev,
 					u32 usage_id,
 					u32 attr_usage_id, u32 report_id)
 {
-	struct sensor_hub_data *data =  hid_get_drvdata(hsdev->hdev);
+	struct sensor_hub_data *data = hid_get_drvdata(hsdev->hdev);
 	unsigned long flags;
 	struct hid_report *report;
 	int ret_val = 0;
@@ -302,7 +302,7 @@ int sensor_hub_input_get_attribute_info(struct hid_sensor_hub_device *hsdev,
 
 	/* Initialize with defaults */
 	info->usage_id = usage_id;
-	info->attrib_id =  attr_usage_id;
+	info->attrib_id = attr_usage_id;
 	info->report_id = -1;
 	info->index = -1;
 	info->units = -1;
@@ -333,7 +333,7 @@ int sensor_hub_input_get_attribute_info(struct hid_sensor_hub_device *hsdev,
 					if (field->usage[j].hid ==
 					attr_usage_id &&
 					field->usage[j].collection_index ==
-					collection_index)  {
+					collection_index) {
 						sensor_hub_fill_attr_info(info,
 							i, report->id,
 							field->unit,
@@ -357,7 +357,7 @@ EXPORT_SYMBOL_GPL(sensor_hub_input_get_attribute_info);
 #ifdef CONFIG_PM
 static int sensor_hub_suspend(struct hid_device *hdev, pm_message_t message)
 {
-	struct sensor_hub_data *pdata =  hid_get_drvdata(hdev);
+	struct sensor_hub_data *pdata = hid_get_drvdata(hdev);
 	struct hid_sensor_hub_callbacks_list *callback;
 
 	hid_dbg(hdev, " sensor_hub_suspend\n");
@@ -374,7 +374,7 @@ static int sensor_hub_suspend(struct hid_device *hdev, pm_message_t message)
 
 static int sensor_hub_resume(struct hid_device *hdev)
 {
-	struct sensor_hub_data *pdata =  hid_get_drvdata(hdev);
+	struct sensor_hub_data *pdata = hid_get_drvdata(hdev);
 	struct hid_sensor_hub_callbacks_list *callback;
 
 	hid_dbg(hdev, " sensor_hub_resume\n");
@@ -394,6 +394,7 @@ static int sensor_hub_reset_resume(struct hid_device *hdev)
 	return 0;
 }
 #endif
+
 /*
  * Handle raw report as sent by device
  */
@@ -416,12 +417,11 @@ static int sensor_hub_raw_event(struct hid_device *hdev,
 		return 1;
 
 	ptr = raw_data;
-	ptr++; /*Skip report id*/
+	ptr++; /* Skip report id */
 
 	spin_lock_irqsave(&pdata->lock, flags);
 
 	for (i = 0; i < report->maxfield; ++i) {
-
 		hid_dbg(hdev, "%d collection_index:%x hid:%x sz:%x\n",
 				i, report->field[i]->usage->collection_index,
 				report->field[i]->usage->hid,
@@ -431,11 +431,10 @@ static int sensor_hub_raw_event(struct hid_device *hdev,
 		if (pdata->pending.status && pdata->pending.attr_usage_id ==
 				report->field[i]->usage->hid) {
 			hid_dbg(hdev, "data was pending ...\n");
-			pdata->pending.raw_data = kmalloc(sz, GFP_ATOMIC);
-			if (pdata->pending.raw_data) {
-				memcpy(pdata->pending.raw_data, ptr, sz);
-				pdata->pending.raw_size  = sz;
-			} else
+			pdata->pending.raw_data = kmemdup(ptr, sz, GFP_ATOMIC);
+			if (pdata->pending.raw_data)
+				pdata->pending.raw_size = sz;
+			else
 				pdata->pending.raw_size = 0;
 			complete(&pdata->pending.ready);
 		}
@@ -478,16 +477,15 @@ static int sensor_hub_probe(struct hid_device *hdev,
 	struct hid_field *field;
 	int dev_cnt;
 
-	sd = kzalloc(sizeof(struct sensor_hub_data), GFP_KERNEL);
+	sd = devm_kzalloc(&hdev->dev, sizeof(*sd), GFP_KERNEL);
 	if (!sd) {
 		hid_err(hdev, "cannot allocate Sensor data\n");
 		return -ENOMEM;
 	}
-	sd->hsdev = kzalloc(sizeof(struct hid_sensor_hub_device), GFP_KERNEL);
+	sd->hsdev = devm_kzalloc(&hdev->dev, sizeof(*sd->hsdev), GFP_KERNEL);
 	if (!sd->hsdev) {
 		hid_err(hdev, "cannot allocate hid_sensor_hub_device\n");
-		ret = -ENOMEM;
-		goto err_free_hub;
+		return -ENOMEM;
 	}
 	hid_set_drvdata(hdev, sd);
 	sd->hsdev->hdev = hdev;
@@ -499,14 +497,14 @@ static int sensor_hub_probe(struct hid_device *hdev,
 	ret = hid_parse(hdev);
 	if (ret) {
 		hid_err(hdev, "parse failed\n");
-		goto err_free;
+		return ret;
 	}
 	INIT_LIST_HEAD(&hdev->inputs);
 
 	ret = hid_hw_start(hdev, 0);
 	if (ret) {
 		hid_err(hdev, "hw start failed\n");
-		goto err_free;
+		return ret;
 	}
 	ret = hid_hw_open(hdev);
 	if (ret) {
@@ -539,7 +537,7 @@ static int sensor_hub_probe(struct hid_device *hdev,
 					field->physical) {
 			name = kasprintf(GFP_KERNEL, "HID-SENSOR-%x",
 						field->physical);
-			if (name  == NULL) {
+			if (name == NULL) {
 				hid_err(hdev, "Failed MFD device name\n");
 					ret = -ENOMEM;
 					goto err_free_names;
@@ -571,10 +569,6 @@ err_close:
 	hid_hw_close(hdev);
 err_stop_hw:
 	hid_hw_stop(hdev);
-err_free:
-	kfree(sd->hsdev);
-err_free_hub:
-	kfree(sd);
 
 	return ret;
 }
@@ -598,8 +592,6 @@ static void sensor_hub_remove(struct hid_device *hdev)
 	kfree(data->hid_sensor_hub_client_devs);
 	hid_set_drvdata(hdev, NULL);
 	mutex_destroy(&data->mutex);
-	kfree(data->hsdev);
-	kfree(data);
 }
 
 static const struct hid_device_id sensor_hub_devices[] = {
@@ -617,8 +609,8 @@ static struct hid_driver sensor_hub_driver = {
 	.raw_event = sensor_hub_raw_event,
 #ifdef CONFIG_PM
 	.suspend = sensor_hub_suspend,
-	.resume =  sensor_hub_resume,
-	.reset_resume =  sensor_hub_reset_resume,
+	.resume = sensor_hub_resume,
+	.reset_resume = sensor_hub_reset_resume,
 #endif
 };
 module_hid_driver(sensor_hub_driver);
diff --git a/drivers/hid/hid-sony.c b/drivers/hid/hid-sony.c
index 87fbe2924cfa..b18320db5f7d 100644
--- a/drivers/hid/hid-sony.c
+++ b/drivers/hid/hid-sony.c
@@ -537,6 +537,10 @@ static int buzz_init(struct hid_device *hdev)
 	drv_data = hid_get_drvdata(hdev);
 	BUG_ON(!(drv_data->quirks & BUZZ_CONTROLLER));
 
+	/* Validate expected report characteristics. */
+	if (!hid_validate_values(hdev, HID_OUTPUT_REPORT, 0, 0, 7))
+		return -ENODEV;
+
 	buzz = kzalloc(sizeof(*buzz), GFP_KERNEL);
 	if (!buzz) {
 		hid_err(hdev, "Insufficient memory, cannot allocate driver data\n");
@@ -624,7 +628,7 @@ static int sony_probe(struct hid_device *hdev, const struct hid_device_id *id)
 	struct sony_sc *sc;
 	unsigned int connect_mask = HID_CONNECT_DEFAULT;
 
-	sc = kzalloc(sizeof(*sc), GFP_KERNEL);
+	sc = devm_kzalloc(&hdev->dev, sizeof(*sc), GFP_KERNEL);
 	if (sc == NULL) {
 		hid_err(hdev, "can't alloc sony descriptor\n");
 		return -ENOMEM;
@@ -636,7 +640,7 @@ static int sony_probe(struct hid_device *hdev, const struct hid_device_id *id)
 	ret = hid_parse(hdev);
 	if (ret) {
 		hid_err(hdev, "parse failed\n");
-		goto err_free;
+		return ret;
 	}
 
 	if (sc->quirks & VAIO_RDESC_CONSTANT)
@@ -649,7 +653,7 @@ static int sony_probe(struct hid_device *hdev, const struct hid_device_id *id)
 	ret = hid_hw_start(hdev, connect_mask);
 	if (ret) {
 		hid_err(hdev, "hw start failed\n");
-		goto err_free;
+		return ret;
 	}
 
 	if (sc->quirks & SIXAXIS_CONTROLLER_USB) {
@@ -669,8 +673,6 @@ static int sony_probe(struct hid_device *hdev, const struct hid_device_id *id)
 	return 0;
 err_stop:
 	hid_hw_stop(hdev);
-err_free:
-	kfree(sc);
 	return ret;
 }
 
@@ -682,7 +684,6 @@ static void sony_remove(struct hid_device *hdev)
 		buzz_remove(hdev);
 
 	hid_hw_stop(hdev);
-	kfree(sc);
 }
 
 static const struct hid_device_id sony_devices[] = {
diff --git a/drivers/hid/hid-speedlink.c b/drivers/hid/hid-speedlink.c
index a2f587d004e1..7112f3e832ee 100644
--- a/drivers/hid/hid-speedlink.c
+++ b/drivers/hid/hid-speedlink.c
@@ -3,7 +3,7 @@
  *  Fixes "jumpy" cursor and removes nonexistent keyboard LEDS from
  *  the HID descriptor.
  *
- *  Copyright (c) 2011 Stefan Kriwanek <mail@stefankriwanek.de>
+ *  Copyright (c) 2011, 2013 Stefan Kriwanek <dev@stefankriwanek.de>
  */
 
 /*
@@ -46,8 +46,13 @@ static int speedlink_event(struct hid_device *hdev, struct hid_field *field,
 		struct hid_usage *usage, __s32 value)
 {
 	/* No other conditions due to usage_table. */
-	/* Fix "jumpy" cursor (invalid events sent by device). */
-	if (value == 256)
+
+	/* This fixes the "jumpy" cursor occuring due to invalid events sent
+	 * by the device. Some devices only send them with value==+256, others
+	 * don't. However, catching abs(value)>=256 is restrictive enough not
+	 * to interfere with devices that were bug-free (has been tested).
+	 */
+	if (abs(value) >= 256)
 		return 1;
 	/* Drop useless distance 0 events (on button clicks etc.) as well */
 	if (value == 0)
diff --git a/drivers/hid/hid-steelseries.c b/drivers/hid/hid-steelseries.c
index d16491192112..29f328f411fb 100644
--- a/drivers/hid/hid-steelseries.c
+++ b/drivers/hid/hid-steelseries.c
@@ -249,6 +249,11 @@ static int steelseries_srws1_probe(struct hid_device *hdev,
 		goto err_free;
 	}
 
+	if (!hid_validate_values(hdev, HID_OUTPUT_REPORT, 0, 0, 16)) {
+		ret = -ENODEV;
+		goto err_free;
+	}
+
 	ret = hid_hw_start(hdev, HID_CONNECT_DEFAULT);
 	if (ret) {
 		hid_err(hdev, "hw start failed\n");
diff --git a/drivers/hid/hid-wiimote-core.c b/drivers/hid/hid-wiimote-core.c
index 0c06054cab8f..abb20db2b443 100644
--- a/drivers/hid/hid-wiimote-core.c
+++ b/drivers/hid/hid-wiimote-core.c
@@ -212,10 +212,12 @@ static __u8 select_drm(struct wiimote_data *wdata)
 
 	if (ir == WIIPROTO_FLAG_IR_BASIC) {
 		if (wdata->state.flags & WIIPROTO_FLAG_ACCEL) {
-			if (ext)
-				return WIIPROTO_REQ_DRM_KAIE;
-			else
-				return WIIPROTO_REQ_DRM_KAI;
+			/* GEN10 and ealier devices bind IR formats to DRMs.
+			 * Hence, we cannot use DRM_KAI here as it might be
+			 * bound to IR_EXT. Use DRM_KAIE unconditionally so we
+			 * work with all devices and our parsers can use the
+			 * fixed formats, too. */
+			return WIIPROTO_REQ_DRM_KAIE;
 		} else {
 			return WIIPROTO_REQ_DRM_KIE;
 		}
@@ -439,8 +441,7 @@ static __u8 wiimote_cmd_read_ext(struct wiimote_data *wdata, __u8 *rmem)
 	if (ret != 6)
 		return WIIMOTE_EXT_NONE;
 
-	hid_dbg(wdata->hdev, "extension ID: %02x:%02x %02x:%02x %02x:%02x\n",
-		rmem[0], rmem[1], rmem[2], rmem[3], rmem[4], rmem[5]);
+	hid_dbg(wdata->hdev, "extension ID: %6phC\n", rmem);
 
 	if (rmem[0] == 0xff && rmem[1] == 0xff && rmem[2] == 0xff &&
 	    rmem[3] == 0xff && rmem[4] == 0xff && rmem[5] == 0xff)
@@ -510,14 +511,12 @@ static bool wiimote_cmd_read_mp(struct wiimote_data *wdata, __u8 *rmem)
 	if (ret != 6)
 		return false;
 
-	hid_dbg(wdata->hdev, "motion plus ID: %02x:%02x %02x:%02x %02x:%02x\n",
-		rmem[0], rmem[1], rmem[2], rmem[3], rmem[4], rmem[5]);
+	hid_dbg(wdata->hdev, "motion plus ID: %6phC\n", rmem);
 
 	if (rmem[5] == 0x05)
 		return true;
 
-	hid_info(wdata->hdev, "unknown motion plus ID: %02x:%02x %02x:%02x %02x:%02x\n",
-		 rmem[0], rmem[1], rmem[2], rmem[3], rmem[4], rmem[5]);
+	hid_info(wdata->hdev, "unknown motion plus ID: %6phC\n", rmem);
 
 	return false;
 }
@@ -533,8 +532,7 @@ static __u8 wiimote_cmd_read_mp_mapped(struct wiimote_data *wdata)
 	if (ret != 6)
 		return WIIMOTE_MP_NONE;
 
-	hid_dbg(wdata->hdev, "mapped motion plus ID: %02x:%02x %02x:%02x %02x:%02x\n",
-		rmem[0], rmem[1], rmem[2], rmem[3], rmem[4], rmem[5]);
+	hid_dbg(wdata->hdev, "mapped motion plus ID: %6phC\n", rmem);
 
 	if (rmem[0] == 0xff && rmem[1] == 0xff && rmem[2] == 0xff &&
 	    rmem[3] == 0xff && rmem[4] == 0xff && rmem[5] == 0xff)
@@ -1126,9 +1124,8 @@ static void wiimote_init_hotplug(struct wiimote_data *wdata)
 		wiimote_ext_unload(wdata);
 
 		if (exttype == WIIMOTE_EXT_UNKNOWN) {
-			hid_info(wdata->hdev, "cannot detect extension; %02x:%02x %02x:%02x %02x:%02x\n",
-				 extdata[0], extdata[1], extdata[2],
-				 extdata[3], extdata[4], extdata[5]);
+			hid_info(wdata->hdev, "cannot detect extension; %6phC\n",
+				 extdata);
 		} else if (exttype == WIIMOTE_EXT_NONE) {
 			spin_lock_irq(&wdata->state.lock);
 			wdata->state.exttype = WIIMOTE_EXT_NONE;
diff --git a/drivers/hid/hid-wiimote-modules.c b/drivers/hid/hid-wiimote-modules.c
index 2e7d644dba18..71adf9e60b13 100644
--- a/drivers/hid/hid-wiimote-modules.c
+++ b/drivers/hid/hid-wiimote-modules.c
@@ -119,12 +119,22 @@ static const struct wiimod_ops wiimod_keys = {
  * the rumble motor, this flag shouldn't be set.
  */
 
+/* used by wiimod_rumble and wiipro_rumble */
+static void wiimod_rumble_worker(struct work_struct *work)
+{
+	struct wiimote_data *wdata = container_of(work, struct wiimote_data,
+						  rumble_worker);
+
+	spin_lock_irq(&wdata->state.lock);
+	wiiproto_req_rumble(wdata, wdata->state.cache_rumble);
+	spin_unlock_irq(&wdata->state.lock);
+}
+
 static int wiimod_rumble_play(struct input_dev *dev, void *data,
 			      struct ff_effect *eff)
 {
 	struct wiimote_data *wdata = input_get_drvdata(dev);
 	__u8 value;
-	unsigned long flags;
 
 	/*
 	 * The wiimote supports only a single rumble motor so if any magnitude
@@ -137,9 +147,10 @@ static int wiimod_rumble_play(struct input_dev *dev, void *data,
 	else
 		value = 0;
 
-	spin_lock_irqsave(&wdata->state.lock, flags);
-	wiiproto_req_rumble(wdata, value);
-	spin_unlock_irqrestore(&wdata->state.lock, flags);
+	/* Locking state.lock here might deadlock with input_event() calls.
+	 * schedule_work acts as barrier. Merging multiple changes is fine. */
+	wdata->state.cache_rumble = value;
+	schedule_work(&wdata->rumble_worker);
 
 	return 0;
 }
@@ -147,6 +158,8 @@ static int wiimod_rumble_play(struct input_dev *dev, void *data,
 static int wiimod_rumble_probe(const struct wiimod_ops *ops,
 			       struct wiimote_data *wdata)
 {
+	INIT_WORK(&wdata->rumble_worker, wiimod_rumble_worker);
+
 	set_bit(FF_RUMBLE, wdata->input->ffbit);
 	if (input_ff_create_memless(wdata->input, NULL, wiimod_rumble_play))
 		return -ENOMEM;
@@ -159,6 +172,8 @@ static void wiimod_rumble_remove(const struct wiimod_ops *ops,
 {
 	unsigned long flags;
 
+	cancel_work_sync(&wdata->rumble_worker);
+
 	spin_lock_irqsave(&wdata->state.lock, flags);
 	wiiproto_req_rumble(wdata, 0);
 	spin_unlock_irqrestore(&wdata->state.lock, flags);
@@ -1731,7 +1746,6 @@ static int wiimod_pro_play(struct input_dev *dev, void *data,
 {
 	struct wiimote_data *wdata = input_get_drvdata(dev);
 	__u8 value;
-	unsigned long flags;
 
 	/*
 	 * The wiimote supports only a single rumble motor so if any magnitude
@@ -1744,9 +1758,10 @@ static int wiimod_pro_play(struct input_dev *dev, void *data,
 	else
 		value = 0;
 
-	spin_lock_irqsave(&wdata->state.lock, flags);
-	wiiproto_req_rumble(wdata, value);
-	spin_unlock_irqrestore(&wdata->state.lock, flags);
+	/* Locking state.lock here might deadlock with input_event() calls.
+	 * schedule_work acts as barrier. Merging multiple changes is fine. */
+	wdata->state.cache_rumble = value;
+	schedule_work(&wdata->rumble_worker);
 
 	return 0;
 }
@@ -1756,6 +1771,8 @@ static int wiimod_pro_probe(const struct wiimod_ops *ops,
 {
 	int ret, i;
 
+	INIT_WORK(&wdata->rumble_worker, wiimod_rumble_worker);
+
 	wdata->extension.input = input_allocate_device();
 	if (!wdata->extension.input)
 		return -ENOMEM;
@@ -1817,12 +1834,13 @@ static void wiimod_pro_remove(const struct wiimod_ops *ops,
 	if (!wdata->extension.input)
 		return;
 
+	input_unregister_device(wdata->extension.input);
+	wdata->extension.input = NULL;
+	cancel_work_sync(&wdata->rumble_worker);
+
 	spin_lock_irqsave(&wdata->state.lock, flags);
 	wiiproto_req_rumble(wdata, 0);
 	spin_unlock_irqrestore(&wdata->state.lock, flags);
-
-	input_unregister_device(wdata->extension.input);
-	wdata->extension.input = NULL;
 }
 
 static const struct wiimod_ops wiimod_pro = {
diff --git a/drivers/hid/hid-wiimote.h b/drivers/hid/hid-wiimote.h
index f1474f372c0b..75db0c400037 100644
--- a/drivers/hid/hid-wiimote.h
+++ b/drivers/hid/hid-wiimote.h
@@ -133,13 +133,15 @@ struct wiimote_state {
 	__u8 *cmd_read_buf;
 	__u8 cmd_read_size;
 
-	/* calibration data */
+	/* calibration/cache data */
 	__u16 calib_bboard[4][3];
+	__u8 cache_rumble;
 };
 
 struct wiimote_data {
 	struct hid_device *hdev;
 	struct input_dev *input;
+	struct work_struct rumble_worker;
 	struct led_classdev *leds[4];
 	struct input_dev *accel;
 	struct input_dev *ir;
diff --git a/drivers/hid/hid-xinmo.c b/drivers/hid/hid-xinmo.c
new file mode 100644
index 000000000000..7df5227a7e61
--- /dev/null
+++ b/drivers/hid/hid-xinmo.c
@@ -0,0 +1,61 @@
+/*
+ *  HID driver for Xin-Mo devices, currently only the Dual Arcade controller.
+ *  Fixes the negative axis event values (the devices sends -2) to match the
+ *  logical axis minimum of the HID report descriptor (the report announces
+ *  -1). It is needed because hid-input discards out of bounds values.
+ *  (This module is based on "hid-saitek" and "hid-lg".)
+ *
+ *  Copyright (c) 2013 Olivier Scherler
+ */
+
+/*
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ */
+
+#include <linux/device.h>
+#include <linux/hid.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+
+#include "hid-ids.h"
+
+/*
+ * Fix negative events that are out of bounds.
+ */
+static int xinmo_event(struct hid_device *hdev, struct hid_field *field,
+		struct hid_usage *usage, __s32 value)
+{
+	switch (usage->code) {
+	case ABS_X:
+	case ABS_Y:
+	case ABS_Z:
+	case ABS_RX:
+		if (value < -1) {
+			input_event(field->hidinput->input, usage->type,
+				usage->code, -1);
+			return 1;
+		}
+		break;
+	}
+
+	return 0;
+}
+
+static const struct hid_device_id xinmo_devices[] = {
+	{ HID_USB_DEVICE(USB_VENDOR_ID_XIN_MO, USB_DEVICE_ID_XIN_MO_DUAL_ARCADE) },
+	{ }
+};
+
+MODULE_DEVICE_TABLE(hid, xinmo_devices);
+
+static struct hid_driver xinmo_driver = {
+	.name = "xinmo",
+	.id_table = xinmo_devices,
+	.event = xinmo_event
+};
+
+module_hid_driver(xinmo_driver);
+MODULE_LICENSE("GPL");
diff --git a/drivers/hid/hid-zpff.c b/drivers/hid/hid-zpff.c
index 6ec28a37c146..a29756c6ca02 100644
--- a/drivers/hid/hid-zpff.c
+++ b/drivers/hid/hid-zpff.c
@@ -68,21 +68,13 @@ static int zpff_init(struct hid_device *hid)
 	struct hid_report *report;
 	struct hid_input *hidinput = list_entry(hid->inputs.next,
 						struct hid_input, list);
-	struct list_head *report_list =
-			&hid->report_enum[HID_OUTPUT_REPORT].report_list;
 	struct input_dev *dev = hidinput->input;
-	int error;
+	int i, error;
 
-	if (list_empty(report_list)) {
-		hid_err(hid, "no output report found\n");
-		return -ENODEV;
-	}
-
-	report = list_entry(report_list->next, struct hid_report, list);
-
-	if (report->maxfield < 4) {
-		hid_err(hid, "not enough fields in report\n");
-		return -ENODEV;
+	for (i = 0; i < 4; i++) {
+		report = hid_validate_values(hid, HID_OUTPUT_REPORT, 0, i, 1);
+		if (!report)
+			return -ENODEV;
 	}
 
 	zpff = kzalloc(sizeof(struct zpff_device), GFP_KERNEL);
diff --git a/drivers/hid/hid-zydacron.c b/drivers/hid/hid-zydacron.c
index e4cddeccd6b5..1a660bd97ab2 100644
--- a/drivers/hid/hid-zydacron.c
+++ b/drivers/hid/hid-zydacron.c
@@ -169,7 +169,7 @@ static int zc_probe(struct hid_device *hdev, const struct hid_device_id *id)
 	int ret;
 	struct zc_device *zc;
 
-	zc = kzalloc(sizeof(*zc), GFP_KERNEL);
+	zc = devm_kzalloc(&hdev->dev, sizeof(*zc), GFP_KERNEL);
 	if (zc == NULL) {
 		hid_err(hdev, "can't alloc descriptor\n");
 		return -ENOMEM;
@@ -180,28 +180,16 @@ static int zc_probe(struct hid_device *hdev, const struct hid_device_id *id)
 	ret = hid_parse(hdev);
 	if (ret) {
 		hid_err(hdev, "parse failed\n");
-		goto err_free;
+		return ret;
 	}
 
 	ret = hid_hw_start(hdev, HID_CONNECT_DEFAULT);
 	if (ret) {
 		hid_err(hdev, "hw start failed\n");
-		goto err_free;
+		return ret;
 	}
 
 	return 0;
-err_free:
-	kfree(zc);
-
-	return ret;
-}
-
-static void zc_remove(struct hid_device *hdev)
-{
-	struct zc_device *zc = hid_get_drvdata(hdev);
-
-	hid_hw_stop(hdev);
-	kfree(zc);
 }
 
 static const struct hid_device_id zc_devices[] = {
@@ -217,7 +205,6 @@ static struct hid_driver zc_driver = {
 	.input_mapping = zc_input_mapping,
 	.raw_event = zc_raw_event,
 	.probe = zc_probe,
-	.remove = zc_remove,
 };
 module_hid_driver(zc_driver);
 
diff --git a/drivers/hid/hidraw.c b/drivers/hid/hidraw.c
index 6f1feb2c2e97..6a6dd5cd7833 100644
--- a/drivers/hid/hidraw.c
+++ b/drivers/hid/hidraw.c
@@ -113,7 +113,7 @@ static ssize_t hidraw_send_report(struct file *file, const char __user *buffer,
 	__u8 *buf;
 	int ret = 0;
 
-	if (!hidraw_table[minor]) {
+	if (!hidraw_table[minor] || !hidraw_table[minor]->exist) {
 		ret = -ENODEV;
 		goto out;
 	}
@@ -253,6 +253,7 @@ static int hidraw_open(struct inode *inode, struct file *file)
 	unsigned int minor = iminor(inode);
 	struct hidraw *dev;
 	struct hidraw_list *list;
+	unsigned long flags;
 	int err = 0;
 
 	if (!(list = kzalloc(sizeof(struct hidraw_list), GFP_KERNEL))) {
@@ -261,16 +262,11 @@ static int hidraw_open(struct inode *inode, struct file *file)
 	}
 
 	mutex_lock(&minors_lock);
-	if (!hidraw_table[minor]) {
+	if (!hidraw_table[minor] || !hidraw_table[minor]->exist) {
 		err = -ENODEV;
 		goto out_unlock;
 	}
 
-	list->hidraw = hidraw_table[minor];
-	mutex_init(&list->read_mutex);
-	list_add_tail(&list->node, &hidraw_table[minor]->list);
-	file->private_data = list;
-
 	dev = hidraw_table[minor];
 	if (!dev->open++) {
 		err = hid_hw_power(dev->hid, PM_HINT_FULLON);
@@ -283,9 +279,16 @@ static int hidraw_open(struct inode *inode, struct file *file)
 		if (err < 0) {
 			hid_hw_power(dev->hid, PM_HINT_NORMAL);
 			dev->open--;
+			goto out_unlock;
 		}
 	}
 
+	list->hidraw = hidraw_table[minor];
+	mutex_init(&list->read_mutex);
+	spin_lock_irqsave(&hidraw_table[minor]->list_lock, flags);
+	list_add_tail(&list->node, &hidraw_table[minor]->list);
+	spin_unlock_irqrestore(&hidraw_table[minor]->list_lock, flags);
+	file->private_data = list;
 out_unlock:
 	mutex_unlock(&minors_lock);
 out:
@@ -302,39 +305,48 @@ static int hidraw_fasync(int fd, struct file *file, int on)
 	return fasync_helper(fd, file, on, &list->fasync);
 }
 
+static void drop_ref(struct hidraw *hidraw, int exists_bit)
+{
+	if (exists_bit) {
+		hidraw->exist = 0;
+		if (hidraw->open) {
+			hid_hw_close(hidraw->hid);
+			wake_up_interruptible(&hidraw->wait);
+		}
+	} else {
+		--hidraw->open;
+	}
+	if (!hidraw->open) {
+		if (!hidraw->exist) {
+			device_destroy(hidraw_class,
+					MKDEV(hidraw_major, hidraw->minor));
+			hidraw_table[hidraw->minor] = NULL;
+			kfree(hidraw);
+		} else {
+			/* close device for last reader */
+			hid_hw_power(hidraw->hid, PM_HINT_NORMAL);
+			hid_hw_close(hidraw->hid);
+		}
+	}
+}
+
 static int hidraw_release(struct inode * inode, struct file * file)
 {
 	unsigned int minor = iminor(inode);
-	struct hidraw *dev;
 	struct hidraw_list *list = file->private_data;
-	int ret;
-	int i;
+	unsigned long flags;
 
 	mutex_lock(&minors_lock);
-	if (!hidraw_table[minor]) {
-		ret = -ENODEV;
-		goto unlock;
-	}
 
+	spin_lock_irqsave(&hidraw_table[minor]->list_lock, flags);
 	list_del(&list->node);
-	dev = hidraw_table[minor];
-	if (!--dev->open) {
-		if (list->hidraw->exist) {
-			hid_hw_power(dev->hid, PM_HINT_NORMAL);
-			hid_hw_close(dev->hid);
-		} else {
-			kfree(list->hidraw);
-		}
-	}
-
-	for (i = 0; i < HIDRAW_BUFFER_SIZE; ++i)
-		kfree(list->buffer[i].value);
+	spin_unlock_irqrestore(&hidraw_table[minor]->list_lock, flags);
 	kfree(list);
-	ret = 0;
-unlock:
-	mutex_unlock(&minors_lock);
 
-	return ret;
+	drop_ref(hidraw_table[minor], 0);
+
+	mutex_unlock(&minors_lock);
+	return 0;
 }
 
 static long hidraw_ioctl(struct file *file, unsigned int cmd,
@@ -457,7 +469,9 @@ int hidraw_report_event(struct hid_device *hid, u8 *data, int len)
 	struct hidraw *dev = hid->hidraw;
 	struct hidraw_list *list;
 	int ret = 0;
+	unsigned long flags;
 
+	spin_lock_irqsave(&dev->list_lock, flags);
 	list_for_each_entry(list, &dev->list, node) {
 		int new_head = (list->head + 1) & (HIDRAW_BUFFER_SIZE - 1);
 
@@ -472,6 +486,7 @@ int hidraw_report_event(struct hid_device *hid, u8 *data, int len)
 		list->head = new_head;
 		kill_fasync(&list->fasync, SIGIO, POLL_IN);
 	}
+	spin_unlock_irqrestore(&dev->list_lock, flags);
 
 	wake_up_interruptible(&dev->wait);
 	return ret;
@@ -519,6 +534,7 @@ int hidraw_connect(struct hid_device *hid)
 	}
 
 	init_waitqueue_head(&dev->wait);
+	spin_lock_init(&dev->list_lock);
 	INIT_LIST_HEAD(&dev->list);
 
 	dev->hid = hid;
@@ -539,18 +555,9 @@ void hidraw_disconnect(struct hid_device *hid)
 	struct hidraw *hidraw = hid->hidraw;
 
 	mutex_lock(&minors_lock);
-	hidraw->exist = 0;
-
-	device_destroy(hidraw_class, MKDEV(hidraw_major, hidraw->minor));
 
-	hidraw_table[hidraw->minor] = NULL;
+	drop_ref(hidraw, 1);
 
-	if (hidraw->open) {
-		hid_hw_close(hid);
-		wake_up_interruptible(&hidraw->wait);
-	} else {
-		kfree(hidraw);
-	}
 	mutex_unlock(&minors_lock);
 }
 EXPORT_SYMBOL_GPL(hidraw_disconnect);
diff --git a/drivers/hid/i2c-hid/i2c-hid.c b/drivers/hid/i2c-hid/i2c-hid.c
index 879b0ed701a3..c1336193b04b 100644
--- a/drivers/hid/i2c-hid/i2c-hid.c
+++ b/drivers/hid/i2c-hid/i2c-hid.c
@@ -35,6 +35,7 @@
 #include <linux/hid.h>
 #include <linux/mutex.h>
 #include <linux/acpi.h>
+#include <linux/of.h>
 
 #include <linux/i2c/i2c-hid.h>
 
@@ -756,29 +757,6 @@ static int i2c_hid_power(struct hid_device *hid, int lvl)
 	return ret;
 }
 
-static int i2c_hid_hidinput_input_event(struct input_dev *dev,
-		unsigned int type, unsigned int code, int value)
-{
-	struct hid_device *hid = input_get_drvdata(dev);
-	struct hid_field *field;
-	int offset;
-
-	if (type == EV_FF)
-		return input_ff_event(dev, type, code, value);
-
-	if (type != EV_LED)
-		return -1;
-
-	offset = hidinput_find_field(hid, type, code, &field);
-
-	if (offset == -1) {
-		hid_warn(dev, "event field not found\n");
-		return -1;
-	}
-
-	return hid_set_field(field, offset, value);
-}
-
 static struct hid_ll_driver i2c_hid_ll_driver = {
 	.parse = i2c_hid_parse,
 	.start = i2c_hid_start,
@@ -787,7 +765,6 @@ static struct hid_ll_driver i2c_hid_ll_driver = {
 	.close = i2c_hid_close,
 	.power = i2c_hid_power,
 	.request = i2c_hid_request,
-	.hidinput_input_event = i2c_hid_hidinput_input_event,
 };
 
 static int i2c_hid_init_irq(struct i2c_client *client)
@@ -824,8 +801,8 @@ static int i2c_hid_fetch_hid_descriptor(struct i2c_hid *ihid)
 	 * bytes 2-3 -> bcdVersion (has to be 1.00) */
 	ret = i2c_hid_command(client, &hid_descr_cmd, ihid->hdesc_buffer, 4);
 
-	i2c_hid_dbg(ihid, "%s, ihid->hdesc_buffer: %*ph\n",
-			__func__, 4, ihid->hdesc_buffer);
+	i2c_hid_dbg(ihid, "%s, ihid->hdesc_buffer: %4ph\n", __func__,
+			ihid->hdesc_buffer);
 
 	if (ret) {
 		dev_err(&client->dev,
@@ -897,8 +874,9 @@ static int i2c_hid_acpi_pdata(struct i2c_client *client,
 	params[1].integer.value = 1;
 	params[2].type = ACPI_TYPE_INTEGER;
 	params[2].integer.value = 1; /* HID function */
-	params[3].type = ACPI_TYPE_INTEGER;
-	params[3].integer.value = 0;
+	params[3].type = ACPI_TYPE_PACKAGE;
+	params[3].package.count = 0;
+	params[3].package.elements = NULL;
 
 	if (ACPI_FAILURE(acpi_evaluate_object(handle, "_DSM", &input, &buf))) {
 		dev_err(&client->dev, "device _DSM execution failed\n");
@@ -933,6 +911,42 @@ static inline int i2c_hid_acpi_pdata(struct i2c_client *client,
 }
 #endif
 
+#ifdef CONFIG_OF
+static int i2c_hid_of_probe(struct i2c_client *client,
+		struct i2c_hid_platform_data *pdata)
+{
+	struct device *dev = &client->dev;
+	u32 val;
+	int ret;
+
+	ret = of_property_read_u32(dev->of_node, "hid-descr-addr", &val);
+	if (ret) {
+		dev_err(&client->dev, "HID register address not provided\n");
+		return -ENODEV;
+	}
+	if (val >> 16) {
+		dev_err(&client->dev, "Bad HID register address: 0x%08x\n",
+			val);
+		return -EINVAL;
+	}
+	pdata->hid_descriptor_address = val;
+
+	return 0;
+}
+
+static const struct of_device_id i2c_hid_of_match[] = {
+	{ .compatible = "hid-over-i2c" },
+	{},
+};
+MODULE_DEVICE_TABLE(of, i2c_hid_of_match);
+#else
+static inline int i2c_hid_of_probe(struct i2c_client *client,
+		struct i2c_hid_platform_data *pdata)
+{
+	return -ENODEV;
+}
+#endif
+
 static int i2c_hid_probe(struct i2c_client *client,
 			 const struct i2c_device_id *dev_id)
 {
@@ -954,7 +968,11 @@ static int i2c_hid_probe(struct i2c_client *client,
 	if (!ihid)
 		return -ENOMEM;
 
-	if (!platform_data) {
+	if (client->dev.of_node) {
+		ret = i2c_hid_of_probe(client, &ihid->pdata);
+		if (ret)
+			goto err;
+	} else if (!platform_data) {
 		ret = i2c_hid_acpi_pdata(client, &ihid->pdata);
 		if (ret) {
 			dev_err(&client->dev,
@@ -1095,6 +1113,7 @@ static struct i2c_driver i2c_hid_driver = {
 		.owner	= THIS_MODULE,
 		.pm	= &i2c_hid_pm,
 		.acpi_match_table = ACPI_PTR(i2c_hid_acpi_match),
+		.of_match_table = of_match_ptr(i2c_hid_of_match),
 	},
 
 	.probe		= i2c_hid_probe,
diff --git a/drivers/hid/uhid.c b/drivers/hid/uhid.c
index fc307e0422af..93b00d76374c 100644
--- a/drivers/hid/uhid.c
+++ b/drivers/hid/uhid.c
@@ -116,30 +116,6 @@ static void uhid_hid_close(struct hid_device *hid)
 	uhid_queue_event(uhid, UHID_CLOSE);
 }
 
-static int uhid_hid_input(struct input_dev *input, unsigned int type,
-			  unsigned int code, int value)
-{
-	struct hid_device *hid = input_get_drvdata(input);
-	struct uhid_device *uhid = hid->driver_data;
-	unsigned long flags;
-	struct uhid_event *ev;
-
-	ev = kzalloc(sizeof(*ev), GFP_ATOMIC);
-	if (!ev)
-		return -ENOMEM;
-
-	ev->type = UHID_OUTPUT_EV;
-	ev->u.output_ev.type = type;
-	ev->u.output_ev.code = code;
-	ev->u.output_ev.value = value;
-
-	spin_lock_irqsave(&uhid->qlock, flags);
-	uhid_queue(uhid, ev);
-	spin_unlock_irqrestore(&uhid->qlock, flags);
-
-	return 0;
-}
-
 static int uhid_hid_parse(struct hid_device *hid)
 {
 	struct uhid_device *uhid = hid->driver_data;
@@ -273,7 +249,6 @@ static struct hid_ll_driver uhid_hid_driver = {
 	.stop = uhid_hid_stop,
 	.open = uhid_hid_open,
 	.close = uhid_hid_close,
-	.hidinput_input_event = uhid_hid_input,
 	.parse = uhid_hid_parse,
 };
 
@@ -640,7 +615,7 @@ static const struct file_operations uhid_fops = {
 
 static struct miscdevice uhid_misc = {
 	.fops		= &uhid_fops,
-	.minor		= MISC_DYNAMIC_MINOR,
+	.minor		= UHID_MINOR,
 	.name		= UHID_NAME,
 };
 
@@ -659,3 +634,5 @@ module_exit(uhid_exit);
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("David Herrmann <dh.herrmann@gmail.com>");
 MODULE_DESCRIPTION("User-space I/O driver support for HID subsystem");
+MODULE_ALIAS_MISCDEV(UHID_MINOR);
+MODULE_ALIAS("devname:" UHID_NAME);
diff --git a/drivers/hid/usbhid/hid-core.c b/drivers/hid/usbhid/hid-core.c
index 99418285222c..44df131d390a 100644
--- a/drivers/hid/usbhid/hid-core.c
+++ b/drivers/hid/usbhid/hid-core.c
@@ -535,7 +535,6 @@ static void __usbhid_submit_report(struct hid_device *hid, struct hid_report *re
 {
 	int head;
 	struct usbhid_device *usbhid = hid->driver_data;
-	int len = ((report->size - 1) >> 3) + 1 + (report->id > 0);
 
 	if ((hid->quirks & HID_QUIRK_NOGET) && dir == USB_DIR_IN)
 		return;
@@ -546,7 +545,7 @@ static void __usbhid_submit_report(struct hid_device *hid, struct hid_report *re
 			return;
 		}
 
-		usbhid->out[usbhid->outhead].raw_report = kmalloc(len, GFP_ATOMIC);
+		usbhid->out[usbhid->outhead].raw_report = hid_alloc_report_buf(report, GFP_ATOMIC);
 		if (!usbhid->out[usbhid->outhead].raw_report) {
 			hid_warn(hid, "output queueing failed\n");
 			return;
@@ -595,7 +594,7 @@ static void __usbhid_submit_report(struct hid_device *hid, struct hid_report *re
 	}
 
 	if (dir == USB_DIR_OUT) {
-		usbhid->ctrl[usbhid->ctrlhead].raw_report = kmalloc(len, GFP_ATOMIC);
+		usbhid->ctrl[usbhid->ctrlhead].raw_report = hid_alloc_report_buf(report, GFP_ATOMIC);
 		if (!usbhid->ctrl[usbhid->ctrlhead].raw_report) {
 			hid_warn(hid, "control queueing failed\n");
 			return;
@@ -649,62 +648,6 @@ static void usbhid_submit_report(struct hid_device *hid, struct hid_report *repo
 	spin_unlock_irqrestore(&usbhid->lock, flags);
 }
 
-/* Workqueue routine to send requests to change LEDs */
-static void hid_led(struct work_struct *work)
-{
-	struct usbhid_device *usbhid =
-		container_of(work, struct usbhid_device, led_work);
-	struct hid_device *hid = usbhid->hid;
-	struct hid_field *field;
-	unsigned long flags;
-
-	field = hidinput_get_led_field(hid);
-	if (!field) {
-		hid_warn(hid, "LED event field not found\n");
-		return;
-	}
-
-	spin_lock_irqsave(&usbhid->lock, flags);
-	if (!test_bit(HID_DISCONNECTED, &usbhid->iofl)) {
-		usbhid->ledcount = hidinput_count_leds(hid);
-		hid_dbg(usbhid->hid, "New ledcount = %u\n", usbhid->ledcount);
-		__usbhid_submit_report(hid, field->report, USB_DIR_OUT);
-	}
-	spin_unlock_irqrestore(&usbhid->lock, flags);
-}
-
-static int usb_hidinput_input_event(struct input_dev *dev, unsigned int type, unsigned int code, int value)
-{
-	struct hid_device *hid = input_get_drvdata(dev);
-	struct usbhid_device *usbhid = hid->driver_data;
-	struct hid_field *field;
-	unsigned long flags;
-	int offset;
-
-	if (type == EV_FF)
-		return input_ff_event(dev, type, code, value);
-
-	if (type != EV_LED)
-		return -1;
-
-	if ((offset = hidinput_find_field(hid, type, code, &field)) == -1) {
-		hid_warn(dev, "event field not found\n");
-		return -1;
-	}
-
-	spin_lock_irqsave(&usbhid->lock, flags);
-	hid_set_field(field, offset, value);
-	spin_unlock_irqrestore(&usbhid->lock, flags);
-
-	/*
-	 * Defer performing requested LED action.
-	 * This is more likely gather all LED changes into a single URB.
-	 */
-	schedule_work(&usbhid->led_work);
-
-	return 0;
-}
-
 static int usbhid_wait_io(struct hid_device *hid)
 {
 	struct usbhid_device *usbhid = hid->driver_data;
@@ -807,12 +750,17 @@ void usbhid_init_reports(struct hid_device *hid)
 {
 	struct hid_report *report;
 	struct usbhid_device *usbhid = hid->driver_data;
+	struct hid_report_enum *report_enum;
 	int err, ret;
 
-	list_for_each_entry(report, &hid->report_enum[HID_INPUT_REPORT].report_list, list)
-		usbhid_submit_report(hid, report, USB_DIR_IN);
+	if (!(hid->quirks & HID_QUIRK_NO_INIT_INPUT_REPORTS)) {
+		report_enum = &hid->report_enum[HID_INPUT_REPORT];
+		list_for_each_entry(report, &report_enum->report_list, list)
+			usbhid_submit_report(hid, report, USB_DIR_IN);
+	}
 
-	list_for_each_entry(report, &hid->report_enum[HID_FEATURE_REPORT].report_list, list)
+	report_enum = &hid->report_enum[HID_FEATURE_REPORT];
+	list_for_each_entry(report, &report_enum->report_list, list)
 		usbhid_submit_report(hid, report, USB_DIR_IN);
 
 	err = 0;
@@ -857,7 +805,7 @@ static int hid_find_field_early(struct hid_device *hid, unsigned int page,
 	return -1;
 }
 
-void usbhid_set_leds(struct hid_device *hid)
+static void usbhid_set_leds(struct hid_device *hid)
 {
 	struct hid_field *field;
 	int offset;
@@ -867,7 +815,6 @@ void usbhid_set_leds(struct hid_device *hid)
 		usbhid_submit_report(hid, field->report, USB_DIR_OUT);
 	}
 }
-EXPORT_SYMBOL_GPL(usbhid_set_leds);
 
 /*
  * Traverse the supplied list of reports and find the longest
@@ -1274,7 +1221,6 @@ static struct hid_ll_driver usb_hid_driver = {
 	.open = usbhid_open,
 	.close = usbhid_close,
 	.power = usbhid_power,
-	.hidinput_input_event = usb_hidinput_input_event,
 	.request = usbhid_request,
 	.wait = usbhid_wait_io,
 	.idle = usbhid_idle,
@@ -1368,8 +1314,6 @@ static int usbhid_probe(struct usb_interface *intf, const struct usb_device_id *
 	setup_timer(&usbhid->io_retry, hid_retry_timeout, (unsigned long) hid);
 	spin_lock_init(&usbhid->lock);
 
-	INIT_WORK(&usbhid->led_work, hid_led);
-
 	ret = hid_add_device(hid);
 	if (ret) {
 		if (ret != -ENODEV)
@@ -1402,7 +1346,6 @@ static void hid_cancel_delayed_stuff(struct usbhid_device *usbhid)
 {
 	del_timer_sync(&usbhid->io_retry);
 	cancel_work_sync(&usbhid->reset_work);
-	cancel_work_sync(&usbhid->led_work);
 }
 
 static void hid_cease_io(struct usbhid_device *usbhid)
@@ -1522,15 +1465,17 @@ static int hid_suspend(struct usb_interface *intf, pm_message_t message)
 	struct usbhid_device *usbhid = hid->driver_data;
 	int status = 0;
 	bool driver_suspended = false;
+	unsigned int ledcount;
 
 	if (PMSG_IS_AUTO(message)) {
+		ledcount = hidinput_count_leds(hid);
 		spin_lock_irq(&usbhid->lock);	/* Sync with error handler */
 		if (!test_bit(HID_RESET_PENDING, &usbhid->iofl)
 		    && !test_bit(HID_CLEAR_HALT, &usbhid->iofl)
 		    && !test_bit(HID_OUT_RUNNING, &usbhid->iofl)
 		    && !test_bit(HID_CTRL_RUNNING, &usbhid->iofl)
 		    && !test_bit(HID_KEYS_PRESSED, &usbhid->iofl)
-		    && (!usbhid->ledcount || ignoreled))
+		    && (!ledcount || ignoreled))
 		{
 			set_bit(HID_SUSPENDED, &usbhid->iofl);
 			spin_unlock_irq(&usbhid->lock);
diff --git a/drivers/hid/usbhid/hid-quirks.c b/drivers/hid/usbhid/hid-quirks.c
index 19b8360f2330..07345521f421 100644
--- a/drivers/hid/usbhid/hid-quirks.c
+++ b/drivers/hid/usbhid/hid-quirks.c
@@ -109,6 +109,8 @@ static const struct hid_blacklist {
 	{ USB_VENDOR_ID_SIGMA_MICRO, USB_DEVICE_ID_SIGMA_MICRO_KEYBOARD, HID_QUIRK_NO_INIT_REPORTS },
 	{ USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_MOUSEPEN_I608X, HID_QUIRK_MULTI_INPUT },
 	{ USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_EASYPEN_M610X, HID_QUIRK_MULTI_INPUT },
+	{ USB_VENDOR_ID_NTRIG, USB_DEVICE_ID_NTRIG_DUOSENSE, HID_QUIRK_NO_INIT_REPORTS },
+
 	{ 0, 0 }
 };
 
diff --git a/drivers/hid/usbhid/usbhid.h b/drivers/hid/usbhid/usbhid.h
index dbb6af699135..f633c24ce28b 100644
--- a/drivers/hid/usbhid/usbhid.h
+++ b/drivers/hid/usbhid/usbhid.h
@@ -92,9 +92,6 @@ struct usbhid_device {
 	unsigned int retry_delay;                                       /* Delay length in ms */
 	struct work_struct reset_work;                                  /* Task context for resets */
 	wait_queue_head_t wait;						/* For sleeping */
-	int ledcount;							/* counting the number of active leds */
-
-	struct work_struct led_work;					/* Task context for setting LEDs */
 };
 
 #define	hid_to_usb_dev(hid_dev) \
diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c
index 0df75908200e..bbff5f200bef 100644
--- a/drivers/hv/channel_mgmt.c
+++ b/drivers/hv/channel_mgmt.c
@@ -48,30 +48,39 @@ struct vmbus_channel_message_table_entry {
  * @negop is of type &struct icmsg_negotiate.
  * Set up and fill in default negotiate response message.
  *
- * The max_fw_version specifies the maximum framework version that
- * we can support and max _srv_version specifies the maximum service
- * version we can support. A special value MAX_SRV_VER can be
- * specified to indicate that we can handle the maximum version
- * exposed by the host.
+ * The fw_version specifies the  framework version that
+ * we can support and srv_version specifies the service
+ * version we can support.
  *
  * Mainly used by Hyper-V drivers.
  */
-void vmbus_prep_negotiate_resp(struct icmsg_hdr *icmsghdrp,
+bool vmbus_prep_negotiate_resp(struct icmsg_hdr *icmsghdrp,
 				struct icmsg_negotiate *negop, u8 *buf,
-				int max_fw_version, int max_srv_version)
+				int fw_version, int srv_version)
 {
-	int icframe_vercnt;
-	int icmsg_vercnt;
+	int icframe_major, icframe_minor;
+	int icmsg_major, icmsg_minor;
+	int fw_major, fw_minor;
+	int srv_major, srv_minor;
 	int i;
+	bool found_match = false;
 
 	icmsghdrp->icmsgsize = 0x10;
+	fw_major = (fw_version >> 16);
+	fw_minor = (fw_version & 0xFFFF);
+
+	srv_major = (srv_version >> 16);
+	srv_minor = (srv_version & 0xFFFF);
 
 	negop = (struct icmsg_negotiate *)&buf[
 		sizeof(struct vmbuspipe_hdr) +
 		sizeof(struct icmsg_hdr)];
 
-	icframe_vercnt = negop->icframe_vercnt;
-	icmsg_vercnt = negop->icmsg_vercnt;
+	icframe_major = negop->icframe_vercnt;
+	icframe_minor = 0;
+
+	icmsg_major = negop->icmsg_vercnt;
+	icmsg_minor = 0;
 
 	/*
 	 * Select the framework version number we will
@@ -79,26 +88,48 @@ void vmbus_prep_negotiate_resp(struct icmsg_hdr *icmsghdrp,
 	 */
 
 	for (i = 0; i < negop->icframe_vercnt; i++) {
-		if (negop->icversion_data[i].major <= max_fw_version)
-			icframe_vercnt = negop->icversion_data[i].major;
+		if ((negop->icversion_data[i].major == fw_major) &&
+		   (negop->icversion_data[i].minor == fw_minor)) {
+			icframe_major = negop->icversion_data[i].major;
+			icframe_minor = negop->icversion_data[i].minor;
+			found_match = true;
+		}
 	}
 
+	if (!found_match)
+		goto fw_error;
+
+	found_match = false;
+
 	for (i = negop->icframe_vercnt;
 		 (i < negop->icframe_vercnt + negop->icmsg_vercnt); i++) {
-		if (negop->icversion_data[i].major <= max_srv_version)
-			icmsg_vercnt = negop->icversion_data[i].major;
+		if ((negop->icversion_data[i].major == srv_major) &&
+		   (negop->icversion_data[i].minor == srv_minor)) {
+			icmsg_major = negop->icversion_data[i].major;
+			icmsg_minor = negop->icversion_data[i].minor;
+			found_match = true;
+		}
 	}
 
 	/*
-	 * Respond with the maximum framework and service
+	 * Respond with the framework and service
 	 * version numbers we can support.
 	 */
-	negop->icframe_vercnt = 1;
-	negop->icmsg_vercnt = 1;
-	negop->icversion_data[0].major = icframe_vercnt;
-	negop->icversion_data[0].minor = 0;
-	negop->icversion_data[1].major = icmsg_vercnt;
-	negop->icversion_data[1].minor = 0;
+
+fw_error:
+	if (!found_match) {
+		negop->icframe_vercnt = 0;
+		negop->icmsg_vercnt = 0;
+	} else {
+		negop->icframe_vercnt = 1;
+		negop->icmsg_vercnt = 1;
+	}
+
+	negop->icversion_data[0].major = icframe_major;
+	negop->icversion_data[0].minor = icframe_minor;
+	negop->icversion_data[1].major = icmsg_major;
+	negop->icversion_data[1].minor = icmsg_minor;
+	return found_match;
 }
 
 EXPORT_SYMBOL_GPL(vmbus_prep_negotiate_resp);
@@ -262,6 +293,13 @@ static void vmbus_process_offer(struct work_struct *work)
 	}
 
 	/*
+	 * This state is used to indicate a successful open
+	 * so that when we do close the channel normally, we
+	 * can cleanup properly
+	 */
+	newchannel->state = CHANNEL_OPEN_STATE;
+
+	/*
 	 * Start the process of binding this offer to the driver
 	 * We need to set the DeviceObject field before calling
 	 * vmbus_child_dev_add()
@@ -287,13 +325,6 @@ static void vmbus_process_offer(struct work_struct *work)
 		kfree(newchannel->device_obj);
 
 		free_channel(newchannel);
-	} else {
-		/*
-		 * This state is used to indicate a successful open
-		 * so that when we do close the channel normally, we
-		 * can cleanup properly
-		 */
-		newchannel->state = CHANNEL_OPEN_STATE;
 	}
 }
 
diff --git a/drivers/hv/connection.c b/drivers/hv/connection.c
index ec3b8cdf1e04..936093e0271e 100644
--- a/drivers/hv/connection.c
+++ b/drivers/hv/connection.c
@@ -195,7 +195,10 @@ int vmbus_connect(void)
 
 	do {
 		ret = vmbus_negotiate_version(msginfo, version);
-		if (ret == 0)
+		if (ret == -ETIMEDOUT)
+			goto cleanup;
+
+		if (vmbus_connection.conn_state == CONNECTED)
 			break;
 
 		version = vmbus_get_next_version(version);
diff --git a/drivers/hv/hv_balloon.c b/drivers/hv/hv_balloon.c
index deb5c25305af..7e17a5495e02 100644
--- a/drivers/hv/hv_balloon.c
+++ b/drivers/hv/hv_balloon.c
@@ -825,7 +825,6 @@ static void hot_add_req(struct work_struct *dummy)
 	memset(&resp, 0, sizeof(struct dm_hot_add_response));
 	resp.hdr.type = DM_MEM_HOT_ADD_RESPONSE;
 	resp.hdr.size = sizeof(struct dm_hot_add_response);
-	resp.hdr.trans_id = atomic_inc_return(&trans_id);
 
 #ifdef CONFIG_MEMORY_HOTPLUG
 	pg_start = dm->ha_wrk.ha_page_range.finfo.start_page;
@@ -887,6 +886,7 @@ static void hot_add_req(struct work_struct *dummy)
 		pr_info("Memory hot add failed\n");
 
 	dm->state = DM_INITIALIZED;
+	resp.hdr.trans_id = atomic_inc_return(&trans_id);
 	vmbus_sendpacket(dm->dev->channel, &resp,
 			sizeof(struct dm_hot_add_response),
 			(unsigned long)NULL,
@@ -1081,7 +1081,6 @@ static void balloon_up(struct work_struct *dummy)
 		bl_resp = (struct dm_balloon_response *)send_buffer;
 		memset(send_buffer, 0, PAGE_SIZE);
 		bl_resp->hdr.type = DM_BALLOON_RESPONSE;
-		bl_resp->hdr.trans_id = atomic_inc_return(&trans_id);
 		bl_resp->hdr.size = sizeof(struct dm_balloon_response);
 		bl_resp->more_pages = 1;
 
@@ -1109,6 +1108,7 @@ static void balloon_up(struct work_struct *dummy)
 		 */
 
 		do {
+			bl_resp->hdr.trans_id = atomic_inc_return(&trans_id);
 			ret = vmbus_sendpacket(dm_device.dev->channel,
 						bl_resp,
 						bl_resp->hdr.size,
@@ -1526,5 +1526,4 @@ static int __init init_balloon_drv(void)
 module_init(init_balloon_drv);
 
 MODULE_DESCRIPTION("Hyper-V Balloon");
-MODULE_VERSION(HV_DRV_VERSION);
 MODULE_LICENSE("GPL");
diff --git a/drivers/hv/hv_kvp.c b/drivers/hv/hv_kvp.c
index ed50e9e83c61..09988b289622 100644
--- a/drivers/hv/hv_kvp.c
+++ b/drivers/hv/hv_kvp.c
@@ -29,6 +29,20 @@
 #include <linux/hyperv.h>
 
 
+/*
+ * Pre win8 version numbers used in ws2008 and ws 2008 r2 (win7)
+ */
+#define WS2008_SRV_MAJOR	1
+#define WS2008_SRV_MINOR	0
+#define WS2008_SRV_VERSION     (WS2008_SRV_MAJOR << 16 | WS2008_SRV_MINOR)
+
+#define WIN7_SRV_MAJOR   3
+#define WIN7_SRV_MINOR   0
+#define WIN7_SRV_VERSION     (WIN7_SRV_MAJOR << 16 | WIN7_SRV_MINOR)
+
+#define WIN8_SRV_MAJOR   4
+#define WIN8_SRV_MINOR   0
+#define WIN8_SRV_VERSION     (WIN8_SRV_MAJOR << 16 | WIN8_SRV_MINOR)
 
 /*
  * Global state maintained for transaction that is being processed.
@@ -76,7 +90,9 @@ static u8 *recv_buffer;
 /*
  * Register the kernel component with the user-level daemon.
  * As part of this registration, pass the LIC version number.
+ * This number has no meaning, it satisfies the registration protocol.
  */
+#define HV_DRV_VERSION           "3.1"
 
 static void
 kvp_register(int reg_value)
@@ -575,6 +591,8 @@ void hv_kvp_onchannelcallback(void *context)
 
 	struct icmsg_hdr *icmsghdrp;
 	struct icmsg_negotiate *negop = NULL;
+	int util_fw_version;
+	int kvp_srv_version;
 
 	if (kvp_transaction.active) {
 		/*
@@ -593,8 +611,28 @@ void hv_kvp_onchannelcallback(void *context)
 			sizeof(struct vmbuspipe_hdr)];
 
 		if (icmsghdrp->icmsgtype == ICMSGTYPE_NEGOTIATE) {
+			/*
+			 * Based on the host, select appropriate
+			 * framework and service versions we will
+			 * negotiate.
+			 */
+			switch (vmbus_proto_version) {
+			case (VERSION_WS2008):
+				util_fw_version = UTIL_WS2K8_FW_VERSION;
+				kvp_srv_version = WS2008_SRV_VERSION;
+				break;
+			case (VERSION_WIN7):
+				util_fw_version = UTIL_FW_VERSION;
+				kvp_srv_version = WIN7_SRV_VERSION;
+				break;
+			default:
+				util_fw_version = UTIL_FW_VERSION;
+				kvp_srv_version = WIN8_SRV_VERSION;
+			}
 			vmbus_prep_negotiate_resp(icmsghdrp, negop,
-				 recv_buffer, MAX_SRV_VER, MAX_SRV_VER);
+				 recv_buffer, util_fw_version,
+				 kvp_srv_version);
+
 		} else {
 			kvp_msg = (struct hv_kvp_msg *)&recv_buffer[
 				sizeof(struct vmbuspipe_hdr) +
diff --git a/drivers/hv/hv_snapshot.c b/drivers/hv/hv_snapshot.c
index 8ad5653ce447..0c3546224376 100644
--- a/drivers/hv/hv_snapshot.c
+++ b/drivers/hv/hv_snapshot.c
@@ -24,6 +24,10 @@
 #include <linux/workqueue.h>
 #include <linux/hyperv.h>
 
+#define VSS_MAJOR  5
+#define VSS_MINOR  0
+#define VSS_VERSION    (VSS_MAJOR << 16 | VSS_MINOR)
+
 
 
 /*
@@ -186,18 +190,8 @@ void hv_vss_onchannelcallback(void *context)
 
 		if (icmsghdrp->icmsgtype == ICMSGTYPE_NEGOTIATE) {
 			vmbus_prep_negotiate_resp(icmsghdrp, negop,
-				 recv_buffer, MAX_SRV_VER, MAX_SRV_VER);
-			/*
-			 * We currently negotiate the highest number the
-			 * host has presented. If this version is not
-			 * atleast 5.0, reject.
-			 */
-			negop = (struct icmsg_negotiate *)&recv_buffer[
-				sizeof(struct vmbuspipe_hdr) +
-				sizeof(struct icmsg_hdr)];
-
-			if (negop->icversion_data[1].major < 5)
-				negop->icframe_vercnt = 0;
+				 recv_buffer, UTIL_FW_VERSION,
+				 VSS_VERSION);
 		} else {
 			vss_msg = (struct hv_vss_msg *)&recv_buffer[
 				sizeof(struct vmbuspipe_hdr) +
diff --git a/drivers/hv/hv_util.c b/drivers/hv/hv_util.c
index 2f561c5dfe24..273e3ddb3a20 100644
--- a/drivers/hv/hv_util.c
+++ b/drivers/hv/hv_util.c
@@ -28,6 +28,33 @@
 #include <linux/reboot.h>
 #include <linux/hyperv.h>
 
+
+#define SD_MAJOR	3
+#define SD_MINOR	0
+#define SD_VERSION	(SD_MAJOR << 16 | SD_MINOR)
+
+#define SD_WS2008_MAJOR		1
+#define SD_WS2008_VERSION	(SD_WS2008_MAJOR << 16 | SD_MINOR)
+
+#define TS_MAJOR	3
+#define TS_MINOR	0
+#define TS_VERSION	(TS_MAJOR << 16 | TS_MINOR)
+
+#define TS_WS2008_MAJOR		1
+#define TS_WS2008_VERSION	(TS_WS2008_MAJOR << 16 | TS_MINOR)
+
+#define HB_MAJOR	3
+#define HB_MINOR 0
+#define HB_VERSION	(HB_MAJOR << 16 | HB_MINOR)
+
+#define HB_WS2008_MAJOR	1
+#define HB_WS2008_VERSION	(HB_WS2008_MAJOR << 16 | HB_MINOR)
+
+static int sd_srv_version;
+static int ts_srv_version;
+static int hb_srv_version;
+static int util_fw_version;
+
 static void shutdown_onchannelcallback(void *context);
 static struct hv_util_service util_shutdown = {
 	.util_cb = shutdown_onchannelcallback,
@@ -87,7 +114,8 @@ static void shutdown_onchannelcallback(void *context)
 
 		if (icmsghdrp->icmsgtype == ICMSGTYPE_NEGOTIATE) {
 			vmbus_prep_negotiate_resp(icmsghdrp, negop,
-					shut_txf_buf, MAX_SRV_VER, MAX_SRV_VER);
+					shut_txf_buf, util_fw_version,
+					sd_srv_version);
 		} else {
 			shutdown_msg =
 				(struct shutdown_msg_data *)&shut_txf_buf[
@@ -203,6 +231,7 @@ static void timesync_onchannelcallback(void *context)
 	struct icmsg_hdr *icmsghdrp;
 	struct ictimesync_data *timedatap;
 	u8 *time_txf_buf = util_timesynch.recv_buffer;
+	struct icmsg_negotiate *negop = NULL;
 
 	vmbus_recvpacket(channel, time_txf_buf,
 			 PAGE_SIZE, &recvlen, &requestid);
@@ -212,8 +241,10 @@ static void timesync_onchannelcallback(void *context)
 				sizeof(struct vmbuspipe_hdr)];
 
 		if (icmsghdrp->icmsgtype == ICMSGTYPE_NEGOTIATE) {
-			vmbus_prep_negotiate_resp(icmsghdrp, NULL, time_txf_buf,
-						MAX_SRV_VER, MAX_SRV_VER);
+			vmbus_prep_negotiate_resp(icmsghdrp, negop,
+						time_txf_buf,
+						util_fw_version,
+						ts_srv_version);
 		} else {
 			timedatap = (struct ictimesync_data *)&time_txf_buf[
 				sizeof(struct vmbuspipe_hdr) +
@@ -243,6 +274,7 @@ static void heartbeat_onchannelcallback(void *context)
 	struct icmsg_hdr *icmsghdrp;
 	struct heartbeat_msg_data *heartbeat_msg;
 	u8 *hbeat_txf_buf = util_heartbeat.recv_buffer;
+	struct icmsg_negotiate *negop = NULL;
 
 	vmbus_recvpacket(channel, hbeat_txf_buf,
 			 PAGE_SIZE, &recvlen, &requestid);
@@ -252,8 +284,9 @@ static void heartbeat_onchannelcallback(void *context)
 				sizeof(struct vmbuspipe_hdr)];
 
 		if (icmsghdrp->icmsgtype == ICMSGTYPE_NEGOTIATE) {
-			vmbus_prep_negotiate_resp(icmsghdrp, NULL,
-				hbeat_txf_buf, MAX_SRV_VER, MAX_SRV_VER);
+			vmbus_prep_negotiate_resp(icmsghdrp, negop,
+				hbeat_txf_buf, util_fw_version,
+				hb_srv_version);
 		} else {
 			heartbeat_msg =
 				(struct heartbeat_msg_data *)&hbeat_txf_buf[
@@ -306,6 +339,25 @@ static int util_probe(struct hv_device *dev,
 		goto error;
 
 	hv_set_drvdata(dev, srv);
+	/*
+	 * Based on the host; initialize the framework and
+	 * service version numbers we will negotiate.
+	 */
+	switch (vmbus_proto_version) {
+	case (VERSION_WS2008):
+		util_fw_version = UTIL_WS2K8_FW_VERSION;
+		sd_srv_version = SD_WS2008_VERSION;
+		ts_srv_version = TS_WS2008_VERSION;
+		hb_srv_version = HB_WS2008_VERSION;
+		break;
+
+	default:
+		util_fw_version = UTIL_FW_VERSION;
+		sd_srv_version = SD_VERSION;
+		ts_srv_version = TS_VERSION;
+		hb_srv_version = HB_VERSION;
+	}
+
 	return 0;
 
 error:
@@ -380,5 +432,4 @@ module_init(init_hyperv_utils);
 module_exit(exit_hyperv_utils);
 
 MODULE_DESCRIPTION("Hyper-V Utilities");
-MODULE_VERSION(HV_DRV_VERSION);
 MODULE_LICENSE("GPL");
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index e8e071fc1d6d..f9fe46f52cfa 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -816,7 +816,6 @@ static void __exit vmbus_exit(void)
 
 
 MODULE_LICENSE("GPL");
-MODULE_VERSION(HV_DRV_VERSION);
 
 subsys_initcall(hv_acpi_init);
 module_exit(vmbus_exit);
diff --git a/drivers/hwmon/Kconfig b/drivers/hwmon/Kconfig
index e989f7fd645b..b3ab9d43bb3e 100644
--- a/drivers/hwmon/Kconfig
+++ b/drivers/hwmon/Kconfig
@@ -296,8 +296,8 @@ config SENSORS_K10TEMP
 	  If you say yes here you get support for the temperature
 	  sensor(s) inside your CPU. Supported are later revisions of
 	  the AMD Family 10h and all revisions of the AMD Family 11h,
-	  12h (Llano), 14h (Brazos) and 15h (Bulldozer/Trinity)
-	  microarchitectures.
+	  12h (Llano), 14h (Brazos), 15h (Bulldozer/Trinity) and
+	  16h (Kabini) microarchitectures.
 
 	  This driver can also be built as a module.  If so, the module
 	  will be called k10temp.
@@ -511,6 +511,16 @@ config SENSORS_HIH6130
 	  This driver can also be built as a module.  If so, the module
 	  will be called hih6130.
 
+config SENSORS_HTU21
+	tristate "Measurement Specialties HTU21D humidity/temperature sensors"
+	depends on I2C
+	help
+	  If you say yes here you get support for the Measurement Specialties
+	  HTU21D humidity and temperature sensors.
+
+	  This driver can also be built as a module.  If so, the module
+	  will be called htu21.
+
 config SENSORS_CORETEMP
 	tristate "Intel Core/Core2/Atom temperature sensor"
 	depends on X86
@@ -1202,8 +1212,8 @@ config SENSORS_ADS1015
 	tristate "Texas Instruments ADS1015"
 	depends on I2C
 	help
-	  If you say yes here you get support for Texas Instruments ADS1015
-	  12-bit 4-input ADC device.
+	  If you say yes here you get support for Texas Instruments
+	  ADS1015/ADS1115 12/16-bit 4-input ADC device.
 
 	  This driver can also be built as a module.  If so, the module
 	  will be called ads1015.
diff --git a/drivers/hwmon/Makefile b/drivers/hwmon/Makefile
index 4f0fb5235f42..ec7cde06eb52 100644
--- a/drivers/hwmon/Makefile
+++ b/drivers/hwmon/Makefile
@@ -65,6 +65,7 @@ obj-$(CONFIG_SENSORS_GL518SM)	+= gl518sm.o
 obj-$(CONFIG_SENSORS_GL520SM)	+= gl520sm.o
 obj-$(CONFIG_SENSORS_GPIO_FAN)	+= gpio-fan.o
 obj-$(CONFIG_SENSORS_HIH6130)	+= hih6130.o
+obj-$(CONFIG_SENSORS_HTU21)	+= htu21.o
 obj-$(CONFIG_SENSORS_ULTRA45)	+= ultra45_env.o
 obj-$(CONFIG_SENSORS_I5K_AMB)	+= i5k_amb.o
 obj-$(CONFIG_SENSORS_IBMAEM)	+= ibmaem.o
diff --git a/drivers/hwmon/acpi_power_meter.c b/drivers/hwmon/acpi_power_meter.c
index 6351aba8819c..a9e3d0152c0b 100644
--- a/drivers/hwmon/acpi_power_meter.c
+++ b/drivers/hwmon/acpi_power_meter.c
@@ -2,7 +2,7 @@
  * A hwmon driver for ACPI 4.0 power meters
  * Copyright (C) 2009 IBM
  *
- * Author: Darrick J. Wong <djwong@us.ibm.com>
+ * Author: Darrick J. Wong <darrick.wong@oracle.com>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -1001,7 +1001,7 @@ static void __exit acpi_power_meter_exit(void)
 	acpi_bus_unregister_driver(&acpi_power_meter_driver);
 }
 
-MODULE_AUTHOR("Darrick J. Wong <djwong@us.ibm.com>");
+MODULE_AUTHOR("Darrick J. Wong <darrick.wong@oracle.com>");
 MODULE_DESCRIPTION("ACPI 4.0 power meter driver");
 MODULE_LICENSE("GPL");
 
diff --git a/drivers/hwmon/ads1015.c b/drivers/hwmon/ads1015.c
index 2798246ad814..7f9dc2f86b63 100644
--- a/drivers/hwmon/ads1015.c
+++ b/drivers/hwmon/ads1015.c
@@ -46,17 +46,28 @@ static const unsigned int fullscale_table[8] = {
 	6144, 4096, 2048, 1024, 512, 256, 256, 256 };
 
 /* Data rates in samples per second */
-static const unsigned int data_rate_table[8] = {
-	128, 250, 490, 920, 1600, 2400, 3300, 3300 };
+static const unsigned int data_rate_table_1015[8] = {
+	128, 250, 490, 920, 1600, 2400, 3300, 3300
+};
+
+static const unsigned int data_rate_table_1115[8] = {
+	8, 16, 32, 64, 128, 250, 475, 860
+};
 
 #define ADS1015_DEFAULT_CHANNELS 0xff
 #define ADS1015_DEFAULT_PGA 2
 #define ADS1015_DEFAULT_DATA_RATE 4
 
+enum ads1015_chips {
+	ads1015,
+	ads1115,
+};
+
 struct ads1015_data {
 	struct device *hwmon_dev;
 	struct mutex update_lock; /* mutex protect updates */
 	struct ads1015_channel_data channel_data[ADS1015_CHANNELS];
+	enum ads1015_chips id;
 };
 
 static int ads1015_read_adc(struct i2c_client *client, unsigned int channel)
@@ -66,6 +77,8 @@ static int ads1015_read_adc(struct i2c_client *client, unsigned int channel)
 	unsigned int pga = data->channel_data[channel].pga;
 	unsigned int data_rate = data->channel_data[channel].data_rate;
 	unsigned int conversion_time_ms;
+	const unsigned int * const rate_table = data->id == ads1115 ?
+		data_rate_table_1115 : data_rate_table_1015;
 	int res;
 
 	mutex_lock(&data->update_lock);
@@ -75,7 +88,7 @@ static int ads1015_read_adc(struct i2c_client *client, unsigned int channel)
 	if (res < 0)
 		goto err_unlock;
 	config = res;
-	conversion_time_ms = DIV_ROUND_UP(1000, data_rate_table[data_rate]);
+	conversion_time_ms = DIV_ROUND_UP(1000, rate_table[data_rate]);
 
 	/* setup and start single conversion */
 	config &= 0x001f;
@@ -113,8 +126,9 @@ static int ads1015_reg_to_mv(struct i2c_client *client, unsigned int channel,
 	struct ads1015_data *data = i2c_get_clientdata(client);
 	unsigned int pga = data->channel_data[channel].pga;
 	int fullscale = fullscale_table[pga];
+	const unsigned mask = data->id == ads1115 ? 0x7fff : 0x7ff0;
 
-	return DIV_ROUND_CLOSEST(reg * fullscale, 0x7ff0);
+	return DIV_ROUND_CLOSEST(reg * fullscale, mask);
 }
 
 /* sysfs callback function */
@@ -257,7 +271,7 @@ static int ads1015_probe(struct i2c_client *client,
 			    GFP_KERNEL);
 	if (!data)
 		return -ENOMEM;
-
+	data->id = id->driver_data;
 	i2c_set_clientdata(client, data);
 	mutex_init(&data->update_lock);
 
@@ -286,7 +300,8 @@ exit_remove:
 }
 
 static const struct i2c_device_id ads1015_id[] = {
-	{ "ads1015", 0 },
+	{ "ads1015",  ads1015},
+	{ "ads1115",  ads1115},
 	{ }
 };
 MODULE_DEVICE_TABLE(i2c, ads1015_id);
diff --git a/drivers/hwmon/ads7828.c b/drivers/hwmon/ads7828.c
index ba962ac4b81f..7092c78f814f 100644
--- a/drivers/hwmon/ads7828.c
+++ b/drivers/hwmon/ads7828.c
@@ -145,7 +145,7 @@ static int ads7828_remove(struct i2c_client *client)
 static int ads7828_probe(struct i2c_client *client,
 			 const struct i2c_device_id *id)
 {
-	struct ads7828_platform_data *pdata = client->dev.platform_data;
+	struct ads7828_platform_data *pdata = dev_get_platdata(&client->dev);
 	struct ads7828_data *data;
 	int err;
 
diff --git a/drivers/hwmon/adt7462.c b/drivers/hwmon/adt7462.c
index 69481d3a3d23..addb5a4d5064 100644
--- a/drivers/hwmon/adt7462.c
+++ b/drivers/hwmon/adt7462.c
@@ -2,7 +2,7 @@
  * A hwmon driver for the Analog Devices ADT7462
  * Copyright (C) 2008 IBM
  *
- * Author: Darrick J. Wong <djwong@us.ibm.com>
+ * Author: Darrick J. Wong <darrick.wong@oracle.com>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -333,7 +333,7 @@ static int ADT7462_REG_VOLT_MAX(struct adt7462_data *data, int which)
 			return 0x4C;
 		break;
 	}
-	return -ENODEV;
+	return 0;
 }
 
 static int ADT7462_REG_VOLT_MIN(struct adt7462_data *data, int which)
@@ -392,7 +392,7 @@ static int ADT7462_REG_VOLT_MIN(struct adt7462_data *data, int which)
 			return 0x77;
 		break;
 	}
-	return -ENODEV;
+	return 0;
 }
 
 static int ADT7462_REG_VOLT(struct adt7462_data *data, int which)
@@ -1970,6 +1970,6 @@ static int adt7462_remove(struct i2c_client *client)
 
 module_i2c_driver(adt7462_driver);
 
-MODULE_AUTHOR("Darrick J. Wong <djwong@us.ibm.com>");
+MODULE_AUTHOR("Darrick J. Wong <darrick.wong@oracle.com>");
 MODULE_DESCRIPTION("ADT7462 driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/hwmon/adt7470.c b/drivers/hwmon/adt7470.c
index 6099f50b28aa..0f4dea5ccf17 100644
--- a/drivers/hwmon/adt7470.c
+++ b/drivers/hwmon/adt7470.c
@@ -2,7 +2,7 @@
  * A hwmon driver for the Analog Devices ADT7470
  * Copyright (C) 2007 IBM
  *
- * Author: Darrick J. Wong <djwong@us.ibm.com>
+ * Author: Darrick J. Wong <darrick.wong@oracle.com>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -1314,6 +1314,6 @@ static int adt7470_remove(struct i2c_client *client)
 
 module_i2c_driver(adt7470_driver);
 
-MODULE_AUTHOR("Darrick J. Wong <djwong@us.ibm.com>");
+MODULE_AUTHOR("Darrick J. Wong <darrick.wong@oracle.com>");
 MODULE_DESCRIPTION("ADT7470 driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/hwmon/amc6821.c b/drivers/hwmon/amc6821.c
index 4fe49d2bfe1d..eea817296513 100644
--- a/drivers/hwmon/amc6821.c
+++ b/drivers/hwmon/amc6821.c
@@ -364,7 +364,7 @@ static ssize_t set_pwm1_enable(
 	if (config < 0) {
 			dev_err(&client->dev,
 			"Error reading configuration register, aborting.\n");
-			return -EIO;
+			return config;
 	}
 
 	switch (val) {
@@ -416,11 +416,9 @@ static ssize_t get_temp_auto_point_temp(
 	case 1:
 		return sprintf(buf, "%d\n",
 			data->temp1_auto_point_temp[ix] * 1000);
-		break;
 	case 2:
 		return sprintf(buf, "%d\n",
 			data->temp2_auto_point_temp[ix] * 1000);
-		break;
 	default:
 		dev_dbg(dev, "Unknown attr->nr (%d).\n", nr);
 		return -EINVAL;
@@ -513,7 +511,6 @@ static ssize_t set_temp_auto_point_temp(
 				count = -EIO;
 		}
 		goto EXIT;
-		break;
 	case 1:
 		ptemp[1] = clamp_val(val / 1000, (ptemp[0] & 0x7C) + 4, 124);
 		ptemp[1] &= 0x7C;
@@ -665,7 +662,7 @@ static ssize_t set_fan1_div(
 	if (config < 0) {
 		dev_err(&client->dev,
 			"Error reading configuration register, aborting.\n");
-		return -EIO;
+		return config;
 	}
 	mutex_lock(&data->update_lock);
 	switch (val) {
diff --git a/drivers/hwmon/applesmc.c b/drivers/hwmon/applesmc.c
index 62c2e32e25ef..3288f13d2d87 100644
--- a/drivers/hwmon/applesmc.c
+++ b/drivers/hwmon/applesmc.c
@@ -230,6 +230,7 @@ static int send_argument(const char *key)
 
 static int read_smc(u8 cmd, const char *key, u8 *buffer, u8 len)
 {
+	u8 status, data = 0;
 	int i;
 
 	if (send_command(cmd) || send_argument(key)) {
@@ -237,6 +238,7 @@ static int read_smc(u8 cmd, const char *key, u8 *buffer, u8 len)
 		return -EIO;
 	}
 
+	/* This has no effect on newer (2012) SMCs */
 	if (send_byte(len, APPLESMC_DATA_PORT)) {
 		pr_warn("%.4s: read len fail\n", key);
 		return -EIO;
@@ -250,6 +252,17 @@ static int read_smc(u8 cmd, const char *key, u8 *buffer, u8 len)
 		buffer[i] = inb(APPLESMC_DATA_PORT);
 	}
 
+	/* Read the data port until bit0 is cleared */
+	for (i = 0; i < 16; i++) {
+		udelay(APPLESMC_MIN_WAIT);
+		status = inb(APPLESMC_CMD_PORT);
+		if (!(status & 0x01))
+			break;
+		data = inb(APPLESMC_DATA_PORT);
+	}
+	if (i)
+		pr_warn("flushed %d bytes, last value is: %d\n", i, data);
+
 	return 0;
 }
 
@@ -525,16 +538,25 @@ static int applesmc_init_smcreg_try(void)
 {
 	struct applesmc_registers *s = &smcreg;
 	bool left_light_sensor, right_light_sensor;
+	unsigned int count;
 	u8 tmp[1];
 	int ret;
 
 	if (s->init_complete)
 		return 0;
 
-	ret = read_register_count(&s->key_count);
+	ret = read_register_count(&count);
 	if (ret)
 		return ret;
 
+	if (s->cache && s->key_count != count) {
+		pr_warn("key count changed from %d to %d\n",
+			s->key_count, count);
+		kfree(s->cache);
+		s->cache = NULL;
+	}
+	s->key_count = count;
+
 	if (!s->cache)
 		s->cache = kcalloc(s->key_count, sizeof(*s->cache), GFP_KERNEL);
 	if (!s->cache)
diff --git a/drivers/hwmon/coretemp.c b/drivers/hwmon/coretemp.c
index 2e5e2dc47eaf..78be66176840 100644
--- a/drivers/hwmon/coretemp.c
+++ b/drivers/hwmon/coretemp.c
@@ -316,6 +316,18 @@ static int adjust_tjmax(struct cpuinfo_x86 *c, u32 id, struct device *dev)
 	return tjmax;
 }
 
+static bool cpu_has_tjmax(struct cpuinfo_x86 *c)
+{
+	u8 model = c->x86_model;
+
+	return model > 0xe &&
+	       model != 0x1c &&
+	       model != 0x26 &&
+	       model != 0x27 &&
+	       model != 0x35 &&
+	       model != 0x36;
+}
+
 static int get_tjmax(struct cpuinfo_x86 *c, u32 id, struct device *dev)
 {
 	int err;
@@ -328,7 +340,7 @@ static int get_tjmax(struct cpuinfo_x86 *c, u32 id, struct device *dev)
 	 */
 	err = rdmsr_safe_on_cpu(id, MSR_IA32_TEMPERATURE_TARGET, &eax, &edx);
 	if (err) {
-		if (c->x86_model > 0xe && c->x86_model != 0x1c)
+		if (cpu_has_tjmax(c))
 			dev_warn(dev, "Unable to read TjMax from CPU %u\n", id);
 	} else {
 		val = (eax >> 16) & 0xff;
diff --git a/drivers/hwmon/ds620.c b/drivers/hwmon/ds620.c
index f1d6b422cf06..0918b9136588 100644
--- a/drivers/hwmon/ds620.c
+++ b/drivers/hwmon/ds620.c
@@ -77,7 +77,7 @@ struct ds620_data {
 
 static void ds620_init_client(struct i2c_client *client)
 {
-	struct ds620_platform_data *ds620_info = client->dev.platform_data;
+	struct ds620_platform_data *ds620_info = dev_get_platdata(&client->dev);
 	u16 conf, new_conf;
 
 	new_conf = conf =
diff --git a/drivers/hwmon/emc2103.c b/drivers/hwmon/emc2103.c
index b07305622087..2c137b26acb4 100644
--- a/drivers/hwmon/emc2103.c
+++ b/drivers/hwmon/emc2103.c
@@ -248,7 +248,7 @@ static ssize_t set_temp_min(struct device *dev, struct device_attribute *da,
 
 	int result = kstrtol(buf, 10, &val);
 	if (result < 0)
-		return -EINVAL;
+		return result;
 
 	val = DIV_ROUND_CLOSEST(val, 1000);
 	if ((val < -63) || (val > 127))
@@ -272,7 +272,7 @@ static ssize_t set_temp_max(struct device *dev, struct device_attribute *da,
 
 	int result = kstrtol(buf, 10, &val);
 	if (result < 0)
-		return -EINVAL;
+		return result;
 
 	val = DIV_ROUND_CLOSEST(val, 1000);
 	if ((val < -63) || (val > 127))
@@ -320,7 +320,7 @@ static ssize_t set_fan_div(struct device *dev, struct device_attribute *da,
 
 	int status = kstrtol(buf, 10, &new_div);
 	if (status < 0)
-		return -EINVAL;
+		return status;
 
 	if (new_div == old_div) /* No change */
 		return count;
@@ -394,7 +394,7 @@ static ssize_t set_fan_target(struct device *dev, struct device_attribute *da,
 
 	int result = kstrtol(buf, 10, &rpm_target);
 	if (result < 0)
-		return -EINVAL;
+		return result;
 
 	/* Datasheet states 16384 as maximum RPM target (table 3.2) */
 	if ((rpm_target < 0) || (rpm_target > 16384))
@@ -440,7 +440,7 @@ static ssize_t set_pwm_enable(struct device *dev, struct device_attribute *da,
 
 	int result = kstrtol(buf, 10, &new_value);
 	if (result < 0)
-		return -EINVAL;
+		return result;
 
 	mutex_lock(&data->update_lock);
 	switch (new_value) {
diff --git a/drivers/hwmon/emc6w201.c b/drivers/hwmon/emc6w201.c
index 936898f82f94..82e661e8241b 100644
--- a/drivers/hwmon/emc6w201.c
+++ b/drivers/hwmon/emc6w201.c
@@ -49,7 +49,7 @@ static const unsigned short normal_i2c[] = { 0x2c, 0x2d, 0x2e, I2C_CLIENT_END };
 #define EMC6W201_REG_TEMP_HIGH(nr)	(0x57 + (nr) * 2)
 #define EMC6W201_REG_FAN_MIN(nr)	(0x62 + (nr) * 2)
 
-enum { input, min, max } subfeature;
+enum subfeature { input, min, max };
 
 /*
  * Per-device data
diff --git a/drivers/hwmon/f71805f.c b/drivers/hwmon/f71805f.c
index 0c9f3da242bf..15b7f5281def 100644
--- a/drivers/hwmon/f71805f.c
+++ b/drivers/hwmon/f71805f.c
@@ -1375,7 +1375,7 @@ static void f71805f_init_device(struct f71805f_data *data)
 
 static int f71805f_probe(struct platform_device *pdev)
 {
-	struct f71805f_sio_data *sio_data = pdev->
author	Mikulas Patocka <mpatocka@redhat.com>	2018-10-08 12:57:35 +0200
committer	Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>	2018-10-08 12:57:35 +0200
commit	01c40a17249727472da3f52e2f344cc2cc4138c4 (patch)
tree	8ec4aa2139d8f3a2bda32432481f8fef0388da83 /tools/perf/scripts/python
parent	c09bcc91bb94ed91f1391bffcbe294963d605732 (diff)